From 7c0631d494b95fa5697d297ae443d7787321b5a1 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sat, 18 Feb 2023 08:27:24 -0800 Subject: [PATCH 0001/5631] perf test: Fix offcpu test prev_state check On Fedora 36, the 'perf record' offcpu profiling tests are failing. It was because the BPF checks the prev task's state being S or D but actually it has more bits set. Let's check the LSB 8 bits for the purpose of offcpu profiling. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230218162724.1292657-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/off_cpu.bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c index 38e3b287dbb2..d877a0a9731f 100644 --- a/tools/perf/util/bpf_skel/off_cpu.bpf.c +++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c @@ -277,7 +277,7 @@ int on_switch(u64 *ctx) else prev_state = get_task_state(prev); - return off_cpu_stat(ctx, prev, next, prev_state); + return off_cpu_stat(ctx, prev, next, prev_state & 0xff); } char LICENSE[] SEC("license") = "Dual BSD/GPL"; -- GitLab From 484b2a8442d2ad413ac983775232544e2940fdd1 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:27:58 -0800 Subject: [PATCH 0002/5631] perf tools: Ensure evsel name is initialized Use the evsel__name accessor as otherwise name may be NULL resulting in a segv. This was observed with the perf stat shell test. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/synthetic-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 9ab9308ee80c..6def01036eb5 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -2004,7 +2004,7 @@ int perf_event__synthesize_event_update_name(struct perf_tool *tool, struct evse perf_event__handler_t process) { struct perf_record_event_update *ev; - size_t len = strlen(evsel->name); + size_t len = strlen(evsel__name(evsel)); int err; ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->core.id[0]); -- GitLab From 180a501346d19f2613f41208b5d67dc037638018 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:27:59 -0800 Subject: [PATCH 0003/5631] perf metrics: Improve variable names has_constraint implies the NMI_WATCHDOG_CONSTRAINT and if the constraint is detected it causes events not to be grouped. Most of the code cares about whether events are grouped or not, so rename has_constraint to group_events. Also remove group from metricgroup___watchdog_constraint_hint as the warning is specific to a metric. Make the warning message agree with this too. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 45 +++++++++++++++++------------------ 1 file changed, 22 insertions(+), 23 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index f3559be95541..b2aa6e049804 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -136,10 +136,9 @@ struct metric { /** Optional null terminated array of referenced metrics. */ struct metric_ref *metric_refs; /** - * Is there a constraint on the group of events? In which case the - * events won't be grouped. + * Should events of the metric be grouped? */ - bool has_constraint; + bool group_events; /** * Parsed events for the metric. Optional as events may be taken from a * different metric whose group contains all the IDs necessary for this @@ -148,12 +147,12 @@ struct metric { struct evlist *evlist; }; -static void metricgroup___watchdog_constraint_hint(const char *name, bool foot) +static void metric__watchdog_constraint_hint(const char *name, bool foot) { static bool violate_nmi_constraint; if (!foot) { - pr_warning("Splitting metric group %s into standalone metrics.\n", name); + pr_warning("Not grouping metric %s's events.\n", name); violate_nmi_constraint = true; return; } @@ -167,18 +166,18 @@ static void metricgroup___watchdog_constraint_hint(const char *name, bool foot) " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); } -static bool metricgroup__has_constraint(const struct pmu_metric *pm) +static bool metric__group_events(const struct pmu_metric *pm) { if (!pm->metric_constraint) - return false; + return true; if (!strcmp(pm->metric_constraint, "NO_NMI_WATCHDOG") && sysctl__nmi_watchdog_enabled()) { - metricgroup___watchdog_constraint_hint(pm->metric_name, false); - return true; + metric__watchdog_constraint_hint(pm->metric_name, /*foot=*/false); + return false; } - return false; + return true; } static void metric__free(struct metric *m) @@ -227,7 +226,7 @@ static struct metric *metric__new(const struct pmu_metric *pm, } m->pctx->sctx.runtime = runtime; m->pctx->sctx.system_wide = system_wide; - m->has_constraint = metric_no_group || metricgroup__has_constraint(pm); + m->group_events = !metric_no_group && metric__group_events(pm); m->metric_refs = NULL; m->evlist = NULL; @@ -637,7 +636,7 @@ static int decode_all_metric_ids(struct evlist *perf_evlist, const char *modifie static int metricgroup__build_event_string(struct strbuf *events, const struct expr_parse_ctx *ctx, const char *modifier, - bool has_constraint) + bool group_events) { struct hashmap_entry *cur; size_t bkt; @@ -662,7 +661,7 @@ static int metricgroup__build_event_string(struct strbuf *events, } /* Separate events with commas and open the group if necessary. */ if (no_group) { - if (!has_constraint) { + if (group_events) { ret = strbuf_addch(events, '{'); RETURN_IF_NON_ZERO(ret); } @@ -716,7 +715,7 @@ static int metricgroup__build_event_string(struct strbuf *events, RETURN_IF_NON_ZERO(ret); } } - if (!no_group && !has_constraint) { + if (!no_group && group_events) { ret = strbuf_addf(events, "}:W"); RETURN_IF_NON_ZERO(ret); } @@ -1252,7 +1251,7 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, * Warn about nmi_watchdog if any parsed metrics had the * NO_NMI_WATCHDOG constraint. */ - metricgroup___watchdog_constraint_hint(NULL, true); + metric__watchdog_constraint_hint(NULL, /*foot=*/true); /* No metrics. */ if (count == 0) return -EINVAL; @@ -1295,7 +1294,7 @@ static void find_tool_events(const struct list_head *metric_list, } /** - * build_combined_expr_ctx - Make an expr_parse_ctx with all has_constraint + * build_combined_expr_ctx - Make an expr_parse_ctx with all !group_events * metric IDs, as the IDs are held in a set, * duplicates will be removed. * @metric_list: List to take metrics from. @@ -1315,7 +1314,7 @@ static int build_combined_expr_ctx(const struct list_head *metric_list, return -ENOMEM; list_for_each_entry(m, metric_list, nd) { - if (m->has_constraint && !m->modifier) { + if (!m->group_events && !m->modifier) { hashmap__for_each_entry(m->pctx->ids, cur, bkt) { dup = strdup(cur->pkey); if (!dup) { @@ -1342,14 +1341,14 @@ static int build_combined_expr_ctx(const struct list_head *metric_list, * @fake_pmu: used when testing metrics not supported by the current CPU. * @ids: the event identifiers parsed from a metric. * @modifier: any modifiers added to the events. - * @has_constraint: false if events should be placed in a weak group. + * @group_events: should events be placed in a weak group. * @tool_events: entries set true if the tool event of index could be present in * the overall list of metrics. * @out_evlist: the created list of events. */ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids, const char *modifier, - bool has_constraint, const bool tool_events[PERF_TOOL_MAX], + bool group_events, const bool tool_events[PERF_TOOL_MAX], struct evlist **out_evlist) { struct parse_events_error parse_error; @@ -1393,7 +1392,7 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, } } ret = metricgroup__build_event_string(&events, ids, modifier, - has_constraint); + group_events); if (ret) return ret; @@ -1458,7 +1457,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, if (!ret && combined && hashmap__size(combined->ids)) { ret = parse_ids(metric_no_merge, fake_pmu, combined, /*modifier=*/NULL, - /*has_constraint=*/true, + /*group_events=*/false, tool_events, &combined_evlist); } @@ -1476,7 +1475,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, struct metric *n; struct metric_expr *expr; - if (combined_evlist && m->has_constraint) { + if (combined_evlist && !m->group_events) { metric_evlist = combined_evlist; } else if (!metric_no_merge) { /* @@ -1507,7 +1506,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, } if (!metric_evlist) { ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier, - m->has_constraint, tool_events, &m->evlist); + m->group_events, tool_events, &m->evlist); if (ret) goto out; -- GitLab From 36d19bbbdf9310699603203b332d69dc32c971d0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:00 -0800 Subject: [PATCH 0004/5631] perf pmu-events: Remove aggr_mode from pmu_event aggr_mode is used on Power to set a flag for metrics. For pmu_event it is unused. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 2 +- tools/perf/pmu-events/pmu-events.h | 1 - tools/perf/tests/pmu-events.c | 6 ------ 3 files changed, 1 insertion(+), 8 deletions(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 2bcd07ce609f..db8b92de113e 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -44,7 +44,7 @@ _json_event_attributes = [ # Seems useful, put it early. 'event', # Short things in alphabetical order. - 'aggr_mode', 'compat', 'deprecated', 'perpkg', 'unit', + 'compat', 'deprecated', 'perpkg', 'unit', # Longer things (the last won't be iterated over during decompress). 'long_desc' ] diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7d4a66b8ad2..cee8b83792f8 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -22,7 +22,6 @@ struct pmu_event { const char *pmu; const char *unit; const char *perpkg; - const char *aggr_mode; const char *deprecated; }; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index accf44b3d968..9b4c94ba5460 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -331,12 +331,6 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event return -1; } - if (!is_same(e1->aggr_mode, e2->aggr_mode)) { - pr_debug2("testing event e1 %s: mismatched aggr_mode, %s vs %s\n", - e1->name, e1->aggr_mode, e2->aggr_mode); - return -1; - } - if (!is_same(e1->deprecated, e2->deprecated)) { pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", e1->name, e1->deprecated, e2->deprecated); -- GitLab From 1fa0c371c9824743fe373e624a55cb036bbb2de1 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:01 -0800 Subject: [PATCH 0005/5631] perf pmu-events: Change aggr_mode to be an enum Rather than use a string to encode aggr_mode, use an enum value. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/powerpc/util/header.c | 2 +- tools/perf/pmu-events/jevents.py | 17 +++++++++++------ tools/perf/pmu-events/pmu-events.h | 2 +- 3 files changed, 13 insertions(+), 8 deletions(-) diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index 78eef77d8a8d..c8d0dc775e5d 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -45,6 +45,6 @@ int arch_get_runtimeparam(const struct pmu_metric *pm) int count; char path[PATH_MAX] = "/devices/hv_24x7/interface/"; - atoi(pm->aggr_mode) == PerChip ? strcat(path, "sockets") : strcat(path, "coresperchip"); + strcat(path, pm->aggr_mode == PerChip ? "sockets" : "coresperchip"); return sysfs__read_int(path, &count) < 0 ? 1 : count; } diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index db8b92de113e..2b08d7c18f4b 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -678,10 +678,13 @@ static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) + enum_attributes = ['aggr_mode'] for attr in _json_event_attributes: - _args.output_file.write(f""" -\tpe->{attr} = (*p == '\\0' ? NULL : p); -""") + _args.output_file.write(f'\n\tpe->{attr} = ') + if attr in enum_attributes: + _args.output_file.write("(*p == '\\0' ? 0 : *p - '0');\n") + else: + _args.output_file.write("(*p == '\\0' ? NULL : p);\n") if attr == _json_event_attributes[-1]: continue _args.output_file.write('\twhile (*p++);') @@ -692,9 +695,11 @@ static void decompress_metric(int offset, struct pmu_metric *pm) \tconst char *p = &big_c_string[offset]; """) for attr in _json_metric_attributes: - _args.output_file.write(f""" -\tpm->{attr} = (*p == '\\0' ? NULL : p); -""") + _args.output_file.write(f'\n\tpm->{attr} = ') + if attr in enum_attributes: + _args.output_file.write("(*p == '\\0' ? 0 : *p - '0');\n") + else: + _args.output_file.write("(*p == '\\0' ? NULL : p);\n") if attr == _json_metric_attributes[-1]: continue _args.output_file.write('\twhile (*p++);') diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index cee8b83792f8..7225efc4e4df 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -31,10 +31,10 @@ struct pmu_metric { const char *metric_expr; const char *unit; const char *compat; - const char *aggr_mode; const char *metric_constraint; const char *desc; const char *long_desc; + enum aggr_mode_class aggr_mode; }; struct pmu_events_table; -- GitLab From 9ed8b7dcb0e7816294b2f8d8ab907e8c5402008d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:02 -0800 Subject: [PATCH 0006/5631] perf pmu-events: Change deprecated to be a bool Switch to a more natural bool rather than string encoding, where NULL implicitly meant false. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 2 +- tools/perf/pmu-events/pmu-events.h | 4 +++- tools/perf/tests/pmu-events.c | 4 ++-- tools/perf/util/pmu.c | 10 ++++------ 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 2b08d7c18f4b..35ca34eca74a 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -678,7 +678,7 @@ static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) - enum_attributes = ['aggr_mode'] + enum_attributes = ['aggr_mode', 'deprecated'] for attr in _json_event_attributes: _args.output_file.write(f'\n\tpe->{attr} = ') if attr in enum_attributes: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 7225efc4e4df..2434bc7cf92d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -2,6 +2,8 @@ #ifndef PMU_EVENTS_H #define PMU_EVENTS_H +#include + struct perf_pmu; enum aggr_mode_class { @@ -22,7 +24,7 @@ struct pmu_event { const char *pmu; const char *unit; const char *perpkg; - const char *deprecated; + bool deprecated; }; struct pmu_metric { diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 9b4c94ba5460..937804c84e29 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -331,8 +331,8 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event return -1; } - if (!is_same(e1->deprecated, e2->deprecated)) { - pr_debug2("testing event e1 %s: mismatched deprecated, %s vs %s\n", + if (e1->deprecated != e2->deprecated) { + pr_debug2("testing event e1 %s: mismatched deprecated, %d vs %d\n", e1->name, e1->deprecated, e2->deprecated); return -1; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index c256b29defad..80644e25a568 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -331,14 +331,15 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, int num; char newval[256]; char *long_desc = NULL, *topic = NULL, *unit = NULL, *perpkg = NULL, - *deprecated = NULL, *pmu_name = NULL; + *pmu_name = NULL; + bool deprecated = false; if (pe) { long_desc = (char *)pe->long_desc; topic = (char *)pe->topic; unit = (char *)pe->unit; perpkg = (char *)pe->perpkg; - deprecated = (char *)pe->deprecated; + deprecated = pe->deprecated; pmu_name = (char *)pe->pmu; } @@ -351,7 +352,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->unit[0] = '\0'; alias->per_pkg = false; alias->snapshot = false; - alias->deprecated = false; + alias->deprecated = deprecated; ret = parse_events_terms(&alias->terms, val); if (ret) { @@ -405,9 +406,6 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->str = strdup(newval); alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; - if (deprecated) - alias->deprecated = true; - if (!perf_pmu_merge_alias(alias, list)) list_add_tail(&alias->list, list); -- GitLab From bd6808618ceb7d5bb4d5488afc030b48ae612f63 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:03 -0800 Subject: [PATCH 0007/5631] perf pmu-events: Change perpkg to be a bool Switch to a more natural bool rather than string encoding, where NULL implicitly meant false. The only value of 'PerPkg' in the event json is '1'. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 2 +- tools/perf/pmu-events/pmu-events.h | 2 +- tools/perf/tests/pmu-events.c | 4 ++-- tools/perf/util/pmu.c | 11 ++++------- 4 files changed, 8 insertions(+), 11 deletions(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 35ca34eca74a..2da55408398f 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -678,7 +678,7 @@ static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) - enum_attributes = ['aggr_mode', 'deprecated'] + enum_attributes = ['aggr_mode', 'deprecated', 'perpkg'] for attr in _json_event_attributes: _args.output_file.write(f'\n\tpe->{attr} = ') if attr in enum_attributes: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 2434bc7cf92d..4d236bb32fd3 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -23,7 +23,7 @@ struct pmu_event { const char *long_desc; const char *pmu; const char *unit; - const char *perpkg; + bool perpkg; bool deprecated; }; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 937804c84e29..521557c396bc 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -325,8 +325,8 @@ static int compare_pmu_events(const struct pmu_event *e1, const struct pmu_event return -1; } - if (!is_same(e1->perpkg, e2->perpkg)) { - pr_debug2("testing event e1 %s: mismatched perpkg, %s vs %s\n", + if (e1->perpkg != e2->perpkg) { + pr_debug2("testing event e1 %s: mismatched perpkg, %d vs %d\n", e1->name, e1->perpkg, e2->perpkg); return -1; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 80644e25a568..43b6182d96b7 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -328,17 +328,15 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, struct parse_events_term *term; struct perf_pmu_alias *alias; int ret; - int num; char newval[256]; - char *long_desc = NULL, *topic = NULL, *unit = NULL, *perpkg = NULL, - *pmu_name = NULL; - bool deprecated = false; + char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL; + bool deprecated = false, perpkg = false; if (pe) { long_desc = (char *)pe->long_desc; topic = (char *)pe->topic; unit = (char *)pe->unit; - perpkg = (char *)pe->perpkg; + perpkg = pe->perpkg; deprecated = pe->deprecated; pmu_name = (char *)pe->pmu; } @@ -350,7 +348,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, INIT_LIST_HEAD(&alias->terms); alias->scale = 1.0; alias->unit[0] = '\0'; - alias->per_pkg = false; + alias->per_pkg = perpkg; alias->snapshot = false; alias->deprecated = deprecated; @@ -402,7 +400,6 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, return -1; snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } - alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1; alias->str = strdup(newval); alias->pmu_name = pmu_name ? strdup(pmu_name) : NULL; -- GitLab From 207f7df7271c346da4a421c5b8cdadda99a37964 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:04 -0800 Subject: [PATCH 0008/5631] perf expr: Make the online topology accessible globally Knowing the topology of online CPUs is useful for more than just expr literals. Move to a global function that caches the value. An additional upside is that this may also avoid computing the CPU topology in some situations. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 7 ++----- tools/perf/util/cputopo.c | 14 ++++++++++++++ tools/perf/util/cputopo.h | 5 +++++ tools/perf/util/expr.c | 16 ++++++---------- tools/perf/util/smt.c | 11 +++++------ tools/perf/util/smt.h | 12 ++++++------ 6 files changed, 38 insertions(+), 27 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index a9eb1ed6bd63..cbf0e0c74906 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -154,13 +154,10 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u /* Only EVENT1 or EVENT2 need be measured depending on the value of smt_on. */ { - struct cpu_topology *topology = cpu_topology__new(); - bool smton = smt_on(topology); + bool smton = smt_on(); bool corewide = core_wide(/*system_wide=*/false, - /*user_requested_cpus=*/false, - topology); + /*user_requested_cpus=*/false); - cpu_topology__delete(topology); expr__ctx_clear(ctx); TEST_ASSERT_VAL("find ids", expr__find_ids("EVENT1 if #smt_on else EVENT2", diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c index e08797c3cdbc..ca1d833a0c26 100644 --- a/tools/perf/util/cputopo.c +++ b/tools/perf/util/cputopo.c @@ -238,6 +238,20 @@ static bool has_die_topology(void) return true; } +const struct cpu_topology *online_topology(void) +{ + static const struct cpu_topology *topology; + + if (!topology) { + topology = cpu_topology__new(); + if (!topology) { + pr_err("Error creating CPU topology"); + abort(); + } + } + return topology; +} + struct cpu_topology *cpu_topology__new(void) { struct cpu_topology *tp = NULL; diff --git a/tools/perf/util/cputopo.h b/tools/perf/util/cputopo.h index 969e5920a00e..8d42f6102954 100644 --- a/tools/perf/util/cputopo.h +++ b/tools/perf/util/cputopo.h @@ -56,6 +56,11 @@ struct hybrid_topology { struct hybrid_topology_node nodes[]; }; +/* + * The topology for online CPUs, lazily created. + */ +const struct cpu_topology *online_topology(void); + struct cpu_topology *cpu_topology__new(void); void cpu_topology__delete(struct cpu_topology *tp); /* Determine from the core list whether SMT was enabled. */ diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index c1da20b868db..d46a1878bc9e 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -402,7 +402,7 @@ double arch_get_tsc_freq(void) double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx) { - static struct cpu_topology *topology; + const struct cpu_topology *topology; double result = NAN; if (!strcmp("#num_cpus", literal)) { @@ -421,31 +421,27 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx * these strings gives an indication of the number of packages, dies, * etc. */ - if (!topology) { - topology = cpu_topology__new(); - if (!topology) { - pr_err("Error creating CPU topology"); - goto out; - } - } if (!strcasecmp("#smt_on", literal)) { - result = smt_on(topology) ? 1.0 : 0.0; + result = smt_on() ? 1.0 : 0.0; goto out; } if (!strcmp("#core_wide", literal)) { - result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list, topology) + result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list) ? 1.0 : 0.0; goto out; } if (!strcmp("#num_packages", literal)) { + topology = online_topology(); result = topology->package_cpus_lists; goto out; } if (!strcmp("#num_dies", literal)) { + topology = online_topology(); result = topology->die_cpus_lists; goto out; } if (!strcmp("#num_cores", literal)) { + topology = online_topology(); result = topology->core_cpus_lists; goto out; } diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 994e9e418227..650e804d0adc 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -4,7 +4,7 @@ #include "cputopo.h" #include "smt.h" -bool smt_on(const struct cpu_topology *topology) +bool smt_on(void) { static bool cached; static bool cached_result; @@ -16,22 +16,21 @@ bool smt_on(const struct cpu_topology *topology) if (sysfs__read_int("devices/system/cpu/smt/active", &fs_value) >= 0) cached_result = (fs_value == 1); else - cached_result = cpu_topology__smt_on(topology); + cached_result = cpu_topology__smt_on(online_topology()); cached = true; return cached_result; } -bool core_wide(bool system_wide, const char *user_requested_cpu_list, - const struct cpu_topology *topology) +bool core_wide(bool system_wide, const char *user_requested_cpu_list) { /* If not everything running on a core is being recorded then we can't use core_wide. */ if (!system_wide) return false; /* Cheap case that SMT is disabled and therefore we're inherently core_wide. */ - if (!smt_on(topology)) + if (!smt_on()) return true; - return cpu_topology__core_wide(topology, user_requested_cpu_list); + return cpu_topology__core_wide(online_topology(), user_requested_cpu_list); } diff --git a/tools/perf/util/smt.h b/tools/perf/util/smt.h index ae9095f2c38c..01441fd2c0a2 100644 --- a/tools/perf/util/smt.h +++ b/tools/perf/util/smt.h @@ -2,16 +2,16 @@ #ifndef __SMT_H #define __SMT_H 1 -struct cpu_topology; - -/* Returns true if SMT (aka hyperthreading) is enabled. */ -bool smt_on(const struct cpu_topology *topology); +/* + * Returns true if SMT (aka hyperthreading) is enabled. Determined via sysfs or + * the online topology. + */ +bool smt_on(void); /* * Returns true when system wide and all SMT threads for a core are in the * user_requested_cpus map. */ -bool core_wide(bool system_wide, const char *user_requested_cpu_list, - const struct cpu_topology *topology); +bool core_wide(bool system_wide, const char *user_requested_cpu_list); #endif /* __SMT_H */ -- GitLab From 900536349d12516114eed9f5b47d30c362e68cdc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:05 -0800 Subject: [PATCH 0009/5631] perf pmu-events: Make the metric_constraint an enum Rename metric_constraint to event_grouping to better explain what the variable is used for. Switch to use an enum for encoding instead of a string. Rather than just no constraint/grouping information or "NO_NMI_WATCHDOG", have 4 enum values. The values encode whether to group or not, and two cases where the behavior is dependent on either the NMI watchdog being enabled or SMT being enabled. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 20 ++++++++++++++++---- tools/perf/pmu-events/pmu-events.h | 25 ++++++++++++++++++++++++- tools/perf/util/metricgroup.c | 19 ++++++++++++------- 3 files changed, 52 insertions(+), 12 deletions(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 2da55408398f..dc0c56dccb5e 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -51,8 +51,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ - 'metric_name', 'metric_group', 'metric_constraint', 'metric_expr', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode' + 'metric_name', 'metric_group', 'metric_expr', 'desc', + 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' ] def removesuffix(s: str, suffix: str) -> str: @@ -204,6 +204,18 @@ class JsonEvent: } return aggr_mode_to_enum[aggr_mode] + def convert_metric_constraint(metric_constraint: str) -> Optional[str]: + """Returns the metric_event_groups enum value associated with the JSON string.""" + if not metric_constraint: + return None + metric_constraint_to_enum = { + 'NO_GROUP_EVENTS': '1', + 'NO_GROUP_EVENTS_NMI': '2', + 'NO_NMI_WATCHDOG': '2', + 'NO_GROUP_EVENTS_SMT': '3', + } + return metric_constraint_to_enum[metric_constraint] + def lookup_msr(num: str) -> Optional[str]: """Converts the msr number, or first in a list to the appropriate event field.""" if not num: @@ -288,7 +300,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') - self.metric_constraint = jd.get('MetricConstraint') + self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: self.metric_expr = metric.ParsePerfJson(jd['MetricExpr']).Simplify() @@ -678,7 +690,7 @@ static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) - enum_attributes = ['aggr_mode', 'deprecated', 'perpkg'] + enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] for attr in _json_event_attributes: _args.output_file.write(f'\n\tpe->{attr} = ') if attr in enum_attributes: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 4d236bb32fd3..57a38e3e5c32 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -11,6 +11,29 @@ enum aggr_mode_class { PerCore }; +/** + * enum metric_event_groups - How events within a pmu_metric should be grouped. + */ +enum metric_event_groups { + /** + * @MetricGroupEvents: Default, group events within the metric. + */ + MetricGroupEvents = 0, + /** + * @MetricNoGroupEvents: Don't group events for the metric. + */ + MetricNoGroupEvents = 1, + /** + * @MetricNoGroupEventsNmi: Don't group events for the metric if the NMI + * watchdog is enabled. + */ + MetricNoGroupEventsNmi = 2, + /** + * @MetricNoGroupEventsSmt: Don't group events for the metric if SMT is + * enabled. + */ + MetricNoGroupEventsSmt = 3, +}; /* * Describe each PMU event. Each CPU has a table of PMU events. */ @@ -33,10 +56,10 @@ struct pmu_metric { const char *metric_expr; const char *unit; const char *compat; - const char *metric_constraint; const char *desc; const char *long_desc; enum aggr_mode_class aggr_mode; + enum metric_event_groups event_grouping; }; struct pmu_events_table; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index b2aa6e049804..868fc9c35606 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -13,6 +13,7 @@ #include "pmu.h" #include "pmu-hybrid.h" #include "print-events.h" +#include "smt.h" #include "expr.h" #include "rblist.h" #include @@ -168,16 +169,20 @@ static void metric__watchdog_constraint_hint(const char *name, bool foot) static bool metric__group_events(const struct pmu_metric *pm) { - if (!pm->metric_constraint) - return true; - - if (!strcmp(pm->metric_constraint, "NO_NMI_WATCHDOG") && - sysctl__nmi_watchdog_enabled()) { + switch (pm->event_grouping) { + case MetricNoGroupEvents: + return false; + case MetricNoGroupEventsNmi: + if (!sysctl__nmi_watchdog_enabled()) + return true; metric__watchdog_constraint_hint(pm->metric_name, /*foot=*/false); return false; + case MetricNoGroupEventsSmt: + return !smt_on(); + case MetricGroupEvents: + default: + return true; } - - return true; } static void metric__free(struct metric *m) -- GitLab From aa44724cb3179228bbfa509649ef021d14e4476f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:06 -0800 Subject: [PATCH 0010/5631] perf pmu-events: Don't '\0' terminate enum values Encoding enums like '1\0' wastes a byte and could be '1' (no '\0' terminator) if the 0 case is '0', it also removes a branch for decompressing. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-10-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index dc0c56dccb5e..e82dff3a1228 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -54,6 +54,8 @@ _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'desc', 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' ] +# Attributes that are bools or enum int values, encoded as '0', '1',... +_json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] def removesuffix(s: str, suffix: str) -> str: """Remove the suffix from a string @@ -360,7 +362,10 @@ class JsonEvent: # Convert parsed metric expressions into a string. Slashes # must be doubled in the file. x = x.ToPerfJson().replace('\\', '\\\\') - s += f'{x}\\000' if x else '\\000' + if attr in _json_enum_attributes: + s += x if x else '0' + else: + s += f'{x}\\000' if x else '\\000' return s def to_c_string(self, metric: bool) -> str: @@ -690,16 +695,18 @@ static void decompress_event(int offset, struct pmu_event *pe) { \tconst char *p = &big_c_string[offset]; """) - enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] for attr in _json_event_attributes: _args.output_file.write(f'\n\tpe->{attr} = ') - if attr in enum_attributes: - _args.output_file.write("(*p == '\\0' ? 0 : *p - '0');\n") + if attr in _json_enum_attributes: + _args.output_file.write("*p - '0';\n") else: _args.output_file.write("(*p == '\\0' ? NULL : p);\n") if attr == _json_event_attributes[-1]: continue - _args.output_file.write('\twhile (*p++);') + if attr in _json_enum_attributes: + _args.output_file.write('\tp++;') + else: + _args.output_file.write('\twhile (*p++);') _args.output_file.write("""} static void decompress_metric(int offset, struct pmu_metric *pm) @@ -708,13 +715,16 @@ static void decompress_metric(int offset, struct pmu_metric *pm) """) for attr in _json_metric_attributes: _args.output_file.write(f'\n\tpm->{attr} = ') - if attr in enum_attributes: - _args.output_file.write("(*p == '\\0' ? 0 : *p - '0');\n") + if attr in _json_enum_attributes: + _args.output_file.write("*p - '0';\n") else: _args.output_file.write("(*p == '\\0' ? NULL : p);\n") if attr == _json_metric_attributes[-1]: continue - _args.output_file.write('\twhile (*p++);') + if attr in _json_enum_attributes: + _args.output_file.write('\tp++;') + else: + _args.output_file.write('\twhile (*p++);') _args.output_file.write("""} int pmu_events_table_for_each_event(const struct pmu_events_table *table, -- GitLab From ad10c9201d827f85195eb4d94bfcfd2b2ca000f4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:07 -0800 Subject: [PATCH 0011/5631] perf vendor events intel: Refresh alderlake events Update the alderlake events from 1.16 to 1.18. Generation was done using https://github.com/intel/perfmon. Notable changes are new events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-11-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlake/adl-metrics.json | 3190 ++++++++++------- .../pmu-events/arch/x86/alderlake/cache.json | 36 +- .../arch/x86/alderlake/floating-point.json | 27 + .../arch/x86/alderlake/frontend.json | 9 + .../pmu-events/arch/x86/alderlake/memory.json | 3 +- .../arch/x86/alderlake/pipeline.json | 14 +- .../arch/x86/alderlake/uncore-other.json | 28 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 8 files changed, 1902 insertions(+), 1407 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 2eb3d7464d9f..7bb8410a2bf9 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -1,2034 +1,2440 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_DATA.STALLS / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_TAG.STALLS / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CLKS + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / CLKS", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "DECODE.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_decoder0_alone", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "FetchBW;LSD;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_lsd", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", + "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", + "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_alloc_restriction", + "MetricThreshold": "tma_alloc_restriction > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.1", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "tma_backend_bound", "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "MetricName": "tma_backend_bound_aux", + "MetricThreshold": "tma_backend_bound_aux > 0.2", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", + "MetricExpr": "(tma_info_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "BriefDescription": "Counts the number of uops that are not from the microsequencer.", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_base", + "MetricThreshold": "tma_base > 0.6", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_branch_detect", + "MetricThreshold": "tma_branch_detect > 0.05", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_branch_resteer", + "MetricThreshold": "tma_branch_resteer > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls.", + "MetricExpr": "max(0, tma_backend_bound - tma_load_store_bound)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_decode", + "MetricThreshold": "tma_decode > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_disambiguation", + "MetricThreshold": "tma_disambiguation > 0.02", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_fast_nuke", + "MetricThreshold": "tma_fast_nuke > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(25 * Average_Frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 24 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_fp_assist", + "MetricThreshold": "tma_fp_assist > 0.02", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "24 * Average_Frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", + "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", + "MetricName": "tma_fp_uops", + "MetricThreshold": "tma_fp_uops > 0.2", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * Average_Frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_frontend_bandwidth", + "MetricThreshold": "tma_frontend_bandwidth > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.2", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_frontend_latency", + "MetricThreshold": "tma_frontend_latency > 0.15", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_icache", + "MetricThreshold": "tma_icache > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", + "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_address_alias_blocks", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "tma_st_buffer", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_branch_mispredict_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "28 * Average_Frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "", + "MetricExpr": "CPU_CLK_UNHALTED.CORE", + "MetricGroup": " ", + "MetricName": "tma_info_clks", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", + "MetricGroup": " ", + "MetricName": "tma_info_clks_p", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_streaming_stores", - "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Cycles Per Instruction", + "MetricExpr": "tma_info_clks / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_cpi", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": " ", + "MetricName": "tma_info_cpu_utilization", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Cycle cost per DRAM hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_dram_hit", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Cycle cost per L2 hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_l2_hit", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Cycle cost per LLC hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_l3_hit", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_fpdiv_uop_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / CLKS if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / CLKS)", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_idiv_uop_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CLKS + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percent of instruction miss cost that hit in DRAM", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_dramhit_percent", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CLKS", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percent of instruction miss cost that hit in the L2", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_l2hit_percent", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / CLKS", - "MetricGroup": "TopdownL6;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percent of instruction miss cost that hit in the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_l3hit_percent", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricExpr": "13 * MISC2_RETIRED.LFENCE / CLKS", - "MetricGroup": "TopdownL6;tma_serializing_operation_group", - "MetricName": "tma_memory_fence", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_ipbranch", + "Unit": "cpu_atom" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / CLKS", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": " ", + "MetricName": "tma_info_ipc", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", + "MetricGroup": " ", + "MetricName": "tma_info_ipcall", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instructions per Far Branch", + "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", + "MetricGroup": " ", + "MetricName": "tma_info_ipfarbranch", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instructions per Load", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": " ", + "MetricName": "tma_info_ipload", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_ipmispredict", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED.PORT_0", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Instructions per Store", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": " ", + "MetricName": "tma_info_ipstore", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED.PORT_1", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": " ", + "MetricName": "tma_info_kernel_utilization", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED.PORT_6", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of total non-speculative loads that are splits", + "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_load_splits", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3_10", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "load ops retired per 1000 instruction", + "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_memloadpki", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations Sample with: UOPS_DISPATCHED.PORT_7_8", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of all uops which are ucode ops", + "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_microcode_uop_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "", + "MetricExpr": "5 * tma_info_clks", + "MetricGroup": " ", + "MetricName": "tma_info_slots", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_store_fwd_blocks", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": " ", + "MetricName": "tma_info_turbo_utilization", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_upi", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%", - "Unit": "cpu_core" + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_x87_uop_ratio", + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_itlb", + "MetricThreshold": "tma_itlb > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", + "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b + tma_shuffles", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_int_operations", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", - "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_int_operations_group", - "MetricName": "tma_int_vector_128b", + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full", + "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_ld_buffer", + "MetricThreshold": "tma_ld_buffer > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", - "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_int_operations_group", - "MetricName": "tma_int_vector_256b", + "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_load_store_bound", + "MetricThreshold": "tma_load_store_bound > 0.2", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", - "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * SLOTS)", - "MetricGroup": "HPC;Pipeline;TopdownL4;tma_int_operations_group", - "MetricName": "tma_shuffles", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_memory_operations", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", + "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_mem_scheduler", + "MetricThreshold": "tma_mem_scheduler > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fused_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_memory_ordering", + "MetricThreshold": "tma_memory_ordering > 0.02", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_non_fused_branches", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_ms_uops", + "MetricThreshold": "tma_ms_uops > 0.05", + "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", + "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "tma_non_mem_scheduler > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_other_light_ops", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_nuke", + "MetricThreshold": "tma_nuke > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_other_fb", + "MetricThreshold": "tma_other_fb > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", + "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_other_l1", + "MetricThreshold": "tma_other_l1 > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_ms_uops", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS", + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", + "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_other_load_store", + "MetricThreshold": "tma_other_load_store > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * cpu_core@ASSISTS.ANY\\,umask\\=0x1B@ / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", + "MetricName": "tma_other_ret", + "MetricThreshold": "tma_other_ret > 0.3", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", - "MetricExpr": "99 * ASSISTS.PAGE_FAULT / SLOTS", - "MetricGroup": "TopdownL5;tma_assists_group", - "MetricName": "tma_page_faults", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_page_fault", + "MetricThreshold": "tma_page_fault > 0.02", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", - "MetricExpr": "30 * ASSISTS.FP / SLOTS", - "MetricGroup": "HPC;TopdownL5;tma_assists_group", - "MetricName": "tma_fp_assists", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called denormals).", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_predecode", + "MetricThreshold": "tma_predecode > 0.05", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists. ", - "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / SLOTS", - "MetricGroup": "HPC;TopdownL5;tma_assists_group", - "MetricName": "tma_avx_assists", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", + "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_register", + "MetricThreshold": "tma_register > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", + "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_reorder_buffer", + "MetricThreshold": "tma_reorder_buffer > 0.1", "ScaleUnit": "100%", - "Unit": "cpu_core" + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions", - "Unit": "cpu_core" + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "tma_backend_bound", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", + "MetricName": "tma_resource_bound", + "MetricThreshold": "tma_resource_bound > 0.2", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth", - "Unit": "cpu_core" + "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", + "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.75", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative", + "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_rsv", + "MetricThreshold": "tma_rsv > 0.05", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", + "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_serialization", + "MetricThreshold": "tma_serialization > 0.1", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_smc", + "MetricThreshold": "tma_smc > 0.02", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to store buffer full", + "MetricExpr": "tma_store_bound", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_st_buffer", + "MetricThreshold": "tma_st_buffer > 0.05", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", + "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_stlb_hit", + "MetricThreshold": "tma_stlb_hit > 0.05", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", + "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_stlb_miss", + "MetricThreshold": "tma_stlb_miss > 0.05", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", + "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.1", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB", - "Unit": "cpu_core" + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", + "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd", + "MetricThreshold": "tma_store_fwd > 0.05", + "ScaleUnit": "100%", + "Unit": "cpu_atom" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * cpu_core@ASSISTS.ANY\\,umask\\=0x1B@ / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_avx_assists", + "MetricThreshold": "tma_avx_assists > 0.1", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;tma_L1_group", - "MetricName": "Slots_Utilization", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(25 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 24 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "24 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore", + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu_core@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu_core@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu_core@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW.", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu_core@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "28 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * SLOTS / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire", + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * ASSISTS.FP / tma_info_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_fp_assists", + "MetricThreshold": "tma_fp_assists > 0.1", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Strings_Cycles", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "IpAssist", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "Fed;LSD", - "MetricName": "LSD_Coverage", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%", "Unit": "cpu_core" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret", + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency", "Unit": "cpu_core" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict", + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead", "Unit": "cpu_core" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost", + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT", + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK", + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code", "Unit": "cpu_core" }, { "BriefDescription": "Fraction of branches that are CALL or RET", "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", "MetricGroup": "Bad;Branches", - "MetricName": "CallRet", + "MetricName": "tma_info_callret", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump", - "Unit": "cpu_core" - }, - { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "Other_Branches", + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks", "Unit": "cpu_core" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency", + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki", "Unit": "cpu_core" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP", + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt", "Unit": "cpu_core" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI", + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk", "Unit": "cpu_core" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load", + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5", "Unit": "cpu_core" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI", + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks", "Unit": "cpu_core" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All", + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc", "Unit": "cpu_core" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load", + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi", "Unit": "cpu_core" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All", + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization", "Unit": "cpu_core" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load", + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp", "Unit": "cpu_core" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI", + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full", "Unit": "cpu_core" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 6 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "Unit": "cpu_core" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization", + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW", + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu_core@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW", + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu_core@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW", + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage.", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW", + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T", + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu_core@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T", + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T", + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common).", "Unit": "cpu_core" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T", + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine.", "Unit": "cpu_core" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization", + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: ", "Unit": "cpu_core" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency", + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / cpu_core@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency", "Unit": "cpu_core" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine.", + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp", "Unit": "cpu_core" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization", + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization", + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST", "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization", + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu_core@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu_core@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW.", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI", + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use", + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests", + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS", + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting.", "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch", + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "INST_RETIRED.ANY / cpu_core@ASSISTS.ANY\\,umask\\=0x1B@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_ipassist", + "MetricThreshold": "tma_info_ipassist < 100e3", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", "Unit": "cpu_core" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_frontend_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / SLOTS", - "MetricGroup": "TopdownL2;tma_frontend_bound_group", - "MetricName": "tma_frontend_latency", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_icache", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_itlb", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_branch_detect", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_branch_resteer", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / SLOTS", - "MetricGroup": "TopdownL2;tma_frontend_bound_group", - "MetricName": "tma_frontend_bandwidth", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_FE_BOUND.CISC / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_cisc", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_taken", + "MetricThreshold": "tma_info_ipmisp_cond_taken < 200", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_decode", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "cpu_core@BR_MISP_RETIRED.INDIRECT_CALL\\,umask\\=0x80@ / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", - "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_predecode", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_ret", + "MetricThreshold": "tma_info_ipmisp_ret < 500", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", - "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_other_fb", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", - "MetricExpr": "(SLOTS - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_bad_speculation", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / SLOTS", - "MetricGroup": "TopdownL2;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu_core@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / SLOTS", - "MetricGroup": "TopdownL2;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 13", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / SLOTS", - "MetricGroup": "TopdownL3;tma_machine_clears_group", - "MetricName": "tma_nuke", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_smc", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_memory_ordering", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_fp_assist", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_disambiguation", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_page_fault", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / SLOTS", - "MetricGroup": "TopdownL3;tma_machine_clears_group", - "MetricName": "tma_fast_nuke", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "TOPDOWN_BE_BOUND.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_backend_bound", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls. ", - "MetricExpr": "max(0, tma_backend_bound - tma_load_store_bound)", - "MetricGroup": "TopdownL2;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads. ", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / CLKS + tma_store_bound)", - "MetricGroup": "TopdownL2;tma_backend_bound_group", - "MetricName": "tma_load_store_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", - "MetricExpr": "tma_st_buffer", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_store_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", - "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / CLKS", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l1_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", - "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_stlb_hit", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", - "MetricExpr": "LD_HEAD.PGWALK_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_stlb_miss", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", - "MetricExpr": "LD_HEAD.OTHER_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_other_l1", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l2_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l3_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_dram_bound", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", - "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_other_load_store", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "tma_backend_bound", - "MetricGroup": "TopdownL1", - "MetricName": "tma_backend_bound_aux", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation. ", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "tma_backend_bound", - "MetricGroup": "TopdownL2;tma_backend_bound_aux_group", - "MetricName": "tma_resource_bound", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. ", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_mem_scheduler", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to store buffer full", - "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_st_buffer", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu_core@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_ld_buffer", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l3_miss_latency", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative ", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_rsv", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_non_mem_scheduler", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_register", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_lsd_coverage", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_reorder_buffer", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / cpu_core@UNC_ARB_DAT_OCCUPANCY.RD\\,cmask\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", - "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_alloc_restriction", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_serialization", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the numer of issue slots that result in retirement slots. ", - "MetricExpr": "TOPDOWN_RETIRING.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_retiring", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of uops that are not from the microsequencer. ", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / SLOTS", - "MetricGroup": "TopdownL2;tma_retiring_group", - "MetricName": "tma_base", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", - "MetricExpr": "UOPS_RETIRED.FPDIV / SLOTS", - "MetricGroup": "TopdownL3;tma_base_group", - "MetricName": "tma_fp_uops", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / SLOTS", - "MetricGroup": "TopdownL3;tma_base_group", - "MetricName": "tma_other_ret", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", - "MetricExpr": "UOPS_RETIRED.MS / SLOTS", - "MetricGroup": "TopdownL2;tma_retiring_group", - "MetricName": "tma_ms_uops", - "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", - "ScaleUnit": "100%", - "Unit": "cpu_atom" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "Unit": "cpu_core" }, { - "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE", - "MetricName": "CLKS", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_other_branches", + "Unit": "cpu_core" }, { - "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", - "MetricName": "CLKS_P", - "Unit": "cpu_atom" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5", + "Unit": "cpu_core" }, { - "BriefDescription": "", - "MetricExpr": "5 * CLKS", - "MetricName": "SLOTS", - "Unit": "cpu_atom" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_slots / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire", + "Unit": "cpu_core" }, { - "BriefDescription": "Instructions Per Cycle", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricName": "IPC", - "Unit": "cpu_atom" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots", + "Unit": "cpu_core" }, { - "BriefDescription": "Cycles Per Instruction", - "MetricExpr": "CLKS / INST_RETIRED.ANY", - "MetricName": "CPI", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_slots_utilization", + "Unit": "cpu_core" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", - "MetricName": "UPI", - "Unit": "cpu_atom" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Store_Fwd_Blocks", - "Unit": "cpu_atom" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", - "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Address_Alias_Blocks", - "Unit": "cpu_atom" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of total non-speculative loads that are splits", - "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Load_Splits", - "Unit": "cpu_atom" + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu_core@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_strings_cycles", + "MetricThreshold": "tma_info_strings_cycles > 0.1", + "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricName": "IpBranch", - "Unit": "cpu_atom" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization", + "Unit": "cpu_core" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", - "MetricName": "IpCall", - "Unit": "cpu_atom" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05", + "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Load", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "IpLoad", - "Unit": "cpu_atom" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 9", + "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Store", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricName": "IpStore", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b + tma_shuffles", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_int_operations", + "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricName": "IpMispredict", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_128b", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Instructions per Far Branch", - "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", - "MetricName": "IpFarBranch", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_256b", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Ratio of all branches which mispredict", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", - "MetricName": "Branch_Mispredict_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_TAG.STALLS / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Ratio between Mispredicted branches and unknown branches", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", - "MetricName": "Branch_Mispredict_to_Unknown_Branch_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of all uops which are ucode ops", - "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", - "MetricName": "Microcode_Uop_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of all uops which are FPDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", - "MetricName": "FPDiv_Uop_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of all uops which are IDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", - "MetricName": "IDiv_Uop_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "9 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percentage of all uops which are x87 uops", - "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", - "MetricName": "X87_Uop_Ratio", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "DECODE.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricName": "Turbo_Utilization", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu_atom@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", - "MetricName": "Kernel_Utilization", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "CPU_Utilization", - "Unit": "cpu_atom" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Cycle cost per L2 hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", - "MetricName": "Cycles_per_Demand_Load_L2_Hit", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Cycle cost per LLC hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", - "MetricName": "Cycles_per_Demand_Load_L3_Hit", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Cycle cost per DRAM hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "MetricName": "Cycles_per_Demand_Load_DRAM_Hit", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L2", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_L2Hit_Percent", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_L3Hit_Percent", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu_core@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "Percent of instruction miss cost that hit in DRAM", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_DRAMHit_Percent", - "Unit": "cpu_atom" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "load ops retired per 1000 instruction", - "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "MemLoadPKI", - "Unit": "cpu_atom" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C1_Core_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * cpu_core@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / UOPS_ISSUED.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C8_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%", + "Unit": "cpu_core" }, { - "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C10_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_page_faults", + "MetricThreshold": "tma_page_faults > 0.05", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu_core@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu_core@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", + "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_slots)", + "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", + "MetricName": "tma_shuffles", + "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlake/cache.json b/tools/perf/pmu-events/arch/x86/alderlake/cache.json index adc9887b8ae0..51770416bcc2 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/cache.json @@ -92,19 +92,19 @@ "Unit": "cpu_core" }, { - "BriefDescription": "All accesses to L2 cache[This event is alias to L2_RQSTS.REFERENCES]", + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses.[This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" }, { - "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_RQSTS.MISS]", + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_RQSTS.MISS]", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses.[This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" @@ -198,19 +198,19 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_REQUEST.MISS]", + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_REQUEST.MISS]", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses.[This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f", "Unit": "cpu_core" }, { - "BriefDescription": "All accesses to L2 cache[This event is alias to L2_REQUEST.ALL]", + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses.[This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff", "Unit": "cpu_core" @@ -895,7 +895,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -980,6 +980,15 @@ "UMask": "0x8", "Unit": "cpu_core" }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, { "BriefDescription": "For every cycle where the core is waiting on at least 1 outstanding Demand RFO request, increments by 1.", "CounterMask": "1", @@ -999,6 +1008,15 @@ "UMask": "0x8", "Unit": "cpu_core" }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", "EventCode": "0x40", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json index 3eb7cab9b431..c8ba96c4a7f8 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/floating-point.json @@ -85,6 +85,24 @@ "UMask": "0x20", "Unit": "cpu_core" }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -103,6 +121,15 @@ "UMask": "0x2", "Unit": "cpu_core" }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0xfc", + "Unit": "cpu_core" + }, { "BriefDescription": "Counts the number of floating point operations retired that required microcode assist.", "EventCode": "0xc3", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json index 250cd128b674..81349100fe32 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json @@ -8,6 +8,15 @@ "UMask": "0x1", "Unit": "cpu_atom" }, + { + "BriefDescription": "Clears due to Unknown Branches.", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, { "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "EventCode": "0x87", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 7595eb4ab46f..37f3d062a788 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -278,10 +278,9 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Demand Data Read requests who miss L3 cache", + "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Demand Data Read requests who miss L3 cache.", "SampleAfterValue": "100003", "UMask": "0x10", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index f46fa7ba168a..2dba3a115f97 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -793,13 +793,25 @@ "Unit": "cpu_core" }, { - "BriefDescription": "INST_RETIRED.REP_ITERATION", + "BriefDescription": "Iterations of Repeat string retired instructions.", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8", "Unit": "cpu_core" }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1", + "Unit": "cpu_core" + }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0xad", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json index bc5fb6b76065..5f3b4c6e2e39 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json @@ -24,7 +24,7 @@ "Unit": "ARB" }, { - "BriefDescription": "Number of coherent read requests sent to memory controller that were issued by any core.", + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", "EventCode": "0x81", "EventName": "UNC_ARB_DAT_REQUESTS.RD", "PerPkg": "1", @@ -40,7 +40,15 @@ "Unit": "ARB" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_REQUESTS.RD", + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", "EventCode": "0x81", "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", "PerPkg": "1", @@ -55,6 +63,14 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", "EventCode": "0x81", @@ -63,6 +79,14 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "EventCode": "0xff", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 5facdac6fe8e..4bcccab07ea9 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,5 +1,5 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.16,alderlake,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.18,alderlake,core GenuineIntel-6-BE,v1.16,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v26,broadwell,core -- GitLab From fa6073700b6e44fec8c4c9aa23497d3fe1f9a869 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:08 -0800 Subject: [PATCH 0012/5631] perf vendor events intel: Refresh alderlake-n metrics Update the alderlake-n events from 1.16 to 1.18 (no change) and metrics. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-12-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlaken/adln-metrics.json | 811 ++++++++++-------- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 2 files changed, 454 insertions(+), 359 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 9ab1d5bcf4a2..5078c468480f 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -1,583 +1,678 @@ [ { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_frontend_bound", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / SLOTS", - "MetricGroup": "TopdownL2;tma_frontend_bound_group", - "MetricName": "tma_frontend_latency", + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_icache", + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", - "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_itlb", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_branch_detect", - "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", - "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_latency_group", - "MetricName": "tma_branch_resteer", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / SLOTS", - "MetricGroup": "TopdownL2;tma_frontend_bound_group", - "MetricName": "tma_frontend_bandwidth", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_FE_BOUND.CISC / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_cisc", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", - "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_decode", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", - "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_predecode", + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", - "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / SLOTS", - "MetricGroup": "TopdownL3;tma_frontend_bandwidth_group", - "MetricName": "tma_other_fb", + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", - "MetricExpr": "(SLOTS - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_bad_speculation", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / SLOTS", - "MetricGroup": "TopdownL2;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / SLOTS", - "MetricGroup": "TopdownL2;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", + "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_alloc_restriction", + "MetricThreshold": "tma_alloc_restriction > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / SLOTS", - "MetricGroup": "TopdownL3;tma_machine_clears_group", - "MetricName": "tma_nuke", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "TOPDOWN_BE_BOUND.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.1", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_smc", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "tma_backend_bound", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound_aux", + "MetricThreshold": "tma_backend_bound_aux > 0.2", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_memory_ordering", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear", + "MetricExpr": "(tma_info_slots - (TOPDOWN_FE_BOUND.ALL + TOPDOWN_BE_BOUND.ALL + TOPDOWN_RETIRING.ALL)) / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_fp_assist", + "BriefDescription": "Counts the number of uops that are not from the microsequencer.", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_base", + "MetricThreshold": "tma_base > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_disambiguation", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_branch_detect", + "MetricThreshold": "tma_branch_detect > 0.05", + "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults. ", - "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)", - "MetricGroup": "TopdownL4;tma_nuke_group", - "MetricName": "tma_page_fault", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to branch mispredicts.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MISPREDICT / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", - "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / SLOTS", - "MetricGroup": "TopdownL3;tma_machine_clears_group", - "MetricName": "tma_fast_nuke", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", + "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_branch_resteer", + "MetricThreshold": "tma_branch_resteer > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "TOPDOWN_BE_BOUND.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_backend_bound", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", + "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls. ", + "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls.", "MetricExpr": "max(0, tma_backend_bound - tma_load_store_bound)", - "MetricGroup": "TopdownL2;tma_backend_bound_group", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads. ", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / CLKS + tma_store_bound)", - "MetricGroup": "TopdownL2;tma_backend_bound_group", - "MetricName": "tma_load_store_bound", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", + "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_decode", + "MetricThreshold": "tma_decode > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", - "MetricExpr": "tma_st_buffer", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_store_bound", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory disambiguation.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.DISAMBIGUATION / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_disambiguation", + "MetricThreshold": "tma_disambiguation > 0.02", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", - "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / CLKS", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l1_bound", + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", - "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear classified as a fast nuke due to memory ordering, memory disambiguation and memory renaming.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.FASTNUKE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_fast_nuke", + "MetricThreshold": "tma_fast_nuke > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", - "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_stlb_hit", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_fp_assist", + "MetricThreshold": "tma_fp_assist > 0.02", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", - "MetricExpr": "LD_HEAD.PGWALK_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_stlb_miss", + "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", + "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", + "MetricName": "tma_fp_uops", + "MetricThreshold": "tma_fp_uops > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", - "MetricExpr": "LD_HEAD.OTHER_AT_RET / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_other_l1", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_frontend_bandwidth", + "MetricThreshold": "tma_frontend_bandwidth > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l2_bound", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to frontend stalls.", + "MetricExpr": "TOPDOWN_FE_BOUND.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.2", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_l3_bound", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_frontend_latency", + "MetricThreshold": "tma_frontend_latency > 0.15", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / CLKS - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_dram_bound", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", + "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_icache", + "MetricThreshold": "tma_icache > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", - "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", - "MetricGroup": "TopdownL3;tma_load_store_bound_group", - "MetricName": "tma_other_load_store", - "ScaleUnit": "100%" + "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", + "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_address_alias_blocks" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "tma_backend_bound", - "MetricGroup": "TopdownL1", - "MetricName": "tma_backend_bound_aux", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation. ", - "ScaleUnit": "100%" + "BriefDescription": "Ratio of all branches which mispredict", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_branch_mispredict_ratio" }, { - "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", - "MetricExpr": "tma_backend_bound", - "MetricGroup": "TopdownL2;tma_backend_bound_aux_group", - "MetricName": "tma_resource_bound", - "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. ", - "ScaleUnit": "100%" + "BriefDescription": "Ratio between Mispredicted branches and unknown branches", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_branch_mispredict_to_unknown_branch_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_mem_scheduler", - "ScaleUnit": "100%" + "BriefDescription": "", + "MetricExpr": "CPU_CLK_UNHALTED.CORE", + "MetricGroup": " ", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to store buffer full", - "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_st_buffer", - "ScaleUnit": "100%" + "BriefDescription": "", + "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", + "MetricGroup": " ", + "MetricName": "tma_info_clks_p" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_ld_buffer", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction", + "MetricExpr": "tma_info_clks / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative ", - "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL", - "MetricGroup": "TopdownL4;tma_mem_scheduler_group", - "MetricName": "tma_rsv", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": " ", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", - "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_non_mem_scheduler", - "ScaleUnit": "100%" + "BriefDescription": "Cycle cost per DRAM hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_dram_hit" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_register", - "ScaleUnit": "100%" + "BriefDescription": "Cycle cost per L2 hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_l2_hit" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", - "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_reorder_buffer", - "ScaleUnit": "100%" + "BriefDescription": "Cycle cost per LLC hit", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", + "MetricGroup": " ", + "MetricName": "tma_info_cycles_per_demand_load_l3_hit" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to certain allocation restrictions.", - "MetricExpr": "TOPDOWN_BE_BOUND.ALLOC_RESTRICTIONS / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_alloc_restriction", - "ScaleUnit": "100%" + "BriefDescription": "Percentage of all uops which are FPDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_fpdiv_uop_ratio" }, { - "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", - "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / SLOTS", - "MetricGroup": "TopdownL3;tma_resource_bound_group", - "MetricName": "tma_serialization", - "ScaleUnit": "100%" + "BriefDescription": "Percentage of all uops which are IDiv uops", + "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_idiv_uop_ratio" }, { - "BriefDescription": "Counts the numer of issue slots that result in retirement slots. ", - "MetricExpr": "TOPDOWN_RETIRING.ALL / SLOTS", - "MetricGroup": "TopdownL1", - "MetricName": "tma_retiring", - "ScaleUnit": "100%" + "BriefDescription": "Percent of instruction miss cost that hit in DRAM", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_dramhit_percent" }, { - "BriefDescription": "Counts the number of uops that are not from the microsequencer. ", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS) / SLOTS", - "MetricGroup": "TopdownL2;tma_retiring_group", - "MetricName": "tma_base", - "ScaleUnit": "100%" + "BriefDescription": "Percent of instruction miss cost that hit in the L2", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_l2hit_percent" }, { - "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", - "MetricExpr": "UOPS_RETIRED.FPDIV / SLOTS", - "MetricGroup": "TopdownL3;tma_base_group", - "MetricName": "tma_fp_uops", - "ScaleUnit": "100%" + "BriefDescription": "Percent of instruction miss cost that hit in the L3", + "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", + "MetricGroup": " ", + "MetricName": "tma_info_inst_miss_cost_l3hit_percent" }, { - "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", - "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / SLOTS", - "MetricGroup": "TopdownL3;tma_base_group", - "MetricName": "tma_other_ret", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_ipbranch" }, { - "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", - "MetricExpr": "UOPS_RETIRED.MS / SLOTS", - "MetricGroup": "TopdownL2;tma_retiring_group", - "MetricName": "tma_ms_uops", - "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": " ", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE", - "MetricName": "CLKS" + "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", + "MetricGroup": " ", + "MetricName": "tma_info_ipcall" }, { - "BriefDescription": "", - "MetricExpr": "CPU_CLK_UNHALTED.CORE_P", - "MetricName": "CLKS_P" + "BriefDescription": "Instructions per Far Branch", + "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", + "MetricGroup": " ", + "MetricName": "tma_info_ipfarbranch" }, { - "BriefDescription": "", - "MetricExpr": "5 * CLKS", - "MetricName": "SLOTS" + "BriefDescription": "Instructions per Load", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": " ", + "MetricName": "tma_info_ipload" }, { - "BriefDescription": "Instructions Per Cycle", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricName": "IPC" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": " ", + "MetricName": "tma_info_ipmispredict" }, { - "BriefDescription": "Cycles Per Instruction", - "MetricExpr": "CLKS / INST_RETIRED.ANY", - "MetricName": "CPI" + "BriefDescription": "Instructions per Store", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": " ", + "MetricName": "tma_info_ipstore" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", - "MetricName": "UPI" + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", + "MetricGroup": " ", + "MetricName": "tma_info_kernel_utilization" }, { - "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", - "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Store_Fwd_Blocks" + "BriefDescription": "Percentage of total non-speculative loads that are splits", + "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_load_splits" }, { - "BriefDescription": "Percentage of total non-speculative loads with a address aliasing block", - "MetricExpr": "100 * LD_BLOCKS.4K_ALIAS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Address_Alias_Blocks" + "BriefDescription": "load ops retired per 1000 instruction", + "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_memloadpki" }, { - "BriefDescription": "Percentage of total non-speculative loads that are splits", - "MetricExpr": "100 * MEM_UOPS_RETIRED.SPLIT_LOADS / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "Load_Splits" + "BriefDescription": "Percentage of all uops which are ucode ops", + "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_microcode_uop_ratio" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricName": "IpBranch" + "BriefDescription": "", + "MetricExpr": "5 * tma_info_clks", + "MetricGroup": " ", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", - "MetricName": "IpCall" + "BriefDescription": "Percentage of total non-speculative loads with a store forward or unknown store address block", + "MetricExpr": "100 * LD_BLOCKS.DATA_UNKNOWN / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricName": "tma_info_store_fwd_blocks" }, { - "BriefDescription": "Instructions per Load", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricName": "IpLoad" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": " ", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Instructions per Store", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricName": "IpStore" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.ALL / INST_RETIRED.ANY", + "MetricGroup": " ", + "MetricName": "tma_info_upi" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricName": "IpMispredict" + "BriefDescription": "Percentage of all uops which are x87 uops", + "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", + "MetricGroup": " ", + "MetricName": "tma_info_x87_uop_ratio" }, { - "BriefDescription": "Instructions per Far Branch", - "MetricExpr": "INST_RETIRED.ANY / (BR_INST_RETIRED.FAR_BRANCH / 2)", - "MetricName": "IpFarBranch" + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", + "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricName": "tma_itlb", + "MetricThreshold": "tma_itlb > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Ratio of all branches which mispredict", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.ALL_BRANCHES", - "MetricName": "Branch_Mispredict_Ratio" + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", + "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Ratio between Mispredicted branches and unknown branches", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / BACLEARS.ANY", - "MetricName": "Branch_Mispredict_to_Unknown_Branch_Ratio" + "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of all uops which are ucode ops", - "MetricExpr": "100 * UOPS_RETIRED.MS / UOPS_RETIRED.ALL", - "MetricName": "Microcode_Uop_Ratio" + "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", + "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of all uops which are FPDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.FPDIV / UOPS_RETIRED.ALL", - "MetricName": "FPDiv_Uop_Ratio" + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to load buffer full", + "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.LD_BUF / MEM_SCHEDULER_BLOCK.ALL", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_ld_buffer", + "MetricThreshold": "tma_ld_buffer > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of all uops which are IDiv uops", - "MetricExpr": "100 * UOPS_RETIRED.IDIV / UOPS_RETIRED.ALL", - "MetricName": "IDiv_Uop_Ratio" + "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_load_store_bound", + "MetricThreshold": "tma_load_store_bound > 0.2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percentage of all uops which are x87 uops", - "MetricExpr": "100 * UOPS_RETIRED.X87 / UOPS_RETIRED.ALL", - "MetricName": "X87_Uop_Ratio" + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to memory reservation stalls in which a scheduler is not able to accept uops.", + "MetricExpr": "TOPDOWN_BE_BOUND.MEM_SCHEDULER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_mem_scheduler", + "MetricThreshold": "tma_mem_scheduler > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in Kernel mode", - "MetricExpr": "cpu@CPU_CLK_UNHALTED.CORE@k / CPU_CLK_UNHALTED.CORE", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_memory_ordering", + "MetricThreshold": "tma_memory_ordering > 0.02", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "CPU_Utilization" + "BriefDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS)", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_ms_uops", + "MetricThreshold": "tma_ms_uops > 0.05", + "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycle cost per L2 hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_LOAD_UOPS_RETIRED.L2_HIT", - "MetricName": "Cycles_per_Demand_Load_L2_Hit" + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to IEC or FPC RAT stalls, which can be due to FIQ or IEC reservation stalls in which the integer, floating point or SIMD scheduler is not able to accept uops.", + "MetricExpr": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_non_mem_scheduler", + "MetricThreshold": "tma_non_mem_scheduler > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycle cost per LLC hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_LOAD_UOPS_RETIRED.L3_HIT", - "MetricName": "Cycles_per_Demand_Load_L3_Hit" + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to a machine clear (slow nuke).", + "MetricExpr": "TOPDOWN_BAD_SPECULATION.NUKE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_machine_clears_group", + "MetricName": "tma_nuke", + "MetricThreshold": "tma_nuke > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycle cost per DRAM hit", - "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_LOAD_UOPS_RETIRED.DRAM_HIT", - "MetricName": "Cycles_per_Demand_Load_DRAM_Hit" + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", + "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_other_fb", + "MetricThreshold": "tma_other_fb > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L2", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_L2_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_L2Hit_Percent" + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a number of other load blocks.", + "MetricExpr": "LD_HEAD.OTHER_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_other_l1", + "MetricThreshold": "tma_other_l1 > 0.05", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percent of instruction miss cost that hit in the L3", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_LLC_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_L3Hit_Percent" + "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", + "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_other_load_store", + "MetricThreshold": "tma_other_load_store > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Percent of instruction miss cost that hit in DRAM", - "MetricExpr": "100 * MEM_BOUND_STALLS.IFETCH_DRAM_HIT / MEM_BOUND_STALLS.IFETCH", - "MetricName": "Inst_Miss_Cost_DRAMHit_Percent" + "BriefDescription": "Counts the number of uops retired excluding ms and fp div uops.", + "MetricExpr": "(TOPDOWN_RETIRING.ALL - UOPS_RETIRED.MS - UOPS_RETIRED.FPDIV) / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", + "MetricName": "tma_other_ret", + "MetricThreshold": "tma_other_ret > 0.3", + "ScaleUnit": "100%" }, { - "BriefDescription": "load ops retired per 1000 instruction", - "MetricExpr": "1e3 * MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "MemLoadPKI" + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to page faults.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.PAGE_FAULT / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_page_fault", + "MetricThreshold": "tma_page_fault > 0.02", + "ScaleUnit": "100%" }, { - "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C1_Core_Residency", + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", + "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricName": "tma_predecode", + "MetricThreshold": "tma_predecode > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the physical register file unable to accept an entry (marble stalls).", + "MetricExpr": "TOPDOWN_BE_BOUND.REGISTER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_register", + "MetricThreshold": "tma_register > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to the reorder buffer being full (ROB stalls).", + "MetricExpr": "TOPDOWN_BE_BOUND.REORDER_BUFFER / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_reorder_buffer", + "MetricThreshold": "tma_reorder_buffer > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls", + "MetricExpr": "tma_backend_bound", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", + "MetricName": "tma_resource_bound", + "MetricThreshold": "tma_resource_bound > 0.2", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", + "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_slots", + "MetricGroup": "TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.75", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to RSV full relative", + "MetricExpr": "tma_mem_scheduler * MEM_SCHEDULER_BLOCK.RSV / MEM_SCHEDULER_BLOCK.ALL", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_rsv", + "MetricThreshold": "tma_rsv > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend due to scoreboards from the instruction queue (IQ), jump execution unit (JEU), or microcode sequencer (MS).", + "MetricExpr": "TOPDOWN_BE_BOUND.SERIALIZATION / tma_info_slots", + "MetricGroup": "TopdownL3;tma_L3_group;tma_resource_bound_group", + "MetricName": "tma_serialization", + "MetricThreshold": "tma_serialization > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C8_Pkg_Residency", + "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to SMC.", + "MetricExpr": "tma_nuke * (MACHINE_CLEARS.SMC / MACHINE_CLEARS.SLOW)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_nuke_group", + "MetricName": "tma_smc", + "MetricThreshold": "tma_smc > 0.02", "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", + "BriefDescription": "Counts the number of cycles, relative to the number of mem_scheduler slots, in which uops are blocked due to store buffer full", + "MetricExpr": "tma_store_bound", + "MetricGroup": "TopdownL4;tma_L4_group;tma_mem_scheduler_group", + "MetricName": "tma_st_buffer", + "MetricThreshold": "tma_st_buffer > 0.05", "ScaleUnit": "100%" }, { - "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C10_Pkg_Residency", + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a first level TLB miss.", + "MetricExpr": "LD_HEAD.DTLB_MISS_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_stlb_hit", + "MetricThreshold": "tma_stlb_hit > 0.05", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a second level TLB miss requiring a page walk.", + "MetricExpr": "LD_HEAD.PGWALK_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_stlb_miss", + "MetricThreshold": "tma_stlb_miss > 0.05", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", + "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", + "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd", + "MetricThreshold": "tma_store_fwd > 0.05", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 4bcccab07ea9..cad51223d0ea 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType GenuineIntel-6-(97|9A|B7|BA|BF),v1.18,alderlake,core -GenuineIntel-6-BE,v1.16,alderlaken,core +GenuineIntel-6-BE,v1.18,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v26,broadwell,core GenuineIntel-6-56,v7,broadwellde,core -- GitLab From 1ab15f66b918425d9ea2529b54db0552025c9cc0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:09 -0800 Subject: [PATCH 0013/5631] perf vendor events intel: Refresh broadwell metrics Update the broadwell metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-13-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwell/bdw-metrics.json | 1439 +++++++++-------- 1 file changed, 805 insertions(+), 634 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index c3ea39d6c944..51cf8560a8d3 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -1,965 +1,1136 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: BACLEARS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_6", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address) Sample with: UOPS_DISPATCHED_PORT.PORT_7", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_7", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "MetricName": "tma_info_retire" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / CORE_CLKS", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "MEM_Parallel_Requests", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Request_Latency" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From 7d38ef20bab229f40e671533c0c6c39e41c2cfa3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:10 -0800 Subject: [PATCH 0014/5631] perf vendor events intel: Refresh broadwellde metrics Update the broadwellde metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-14-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwellde/bdwde-metrics.json | 1405 +++++++++-------- 1 file changed, 785 insertions(+), 620 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index d35d30932b68..fb57c7382408 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -1,937 +1,1102 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE.IFDATA_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" - }, + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" + }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED.PORT_6", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3_10", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations Sample with: UOPS_DISPATCHED.PORT_7_8", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_7", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "MetricName": "tma_info_retire" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Related metrics: tma_split_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From 46db21af50510376d7e68116b1bfd2094b38cbc0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:11 -0800 Subject: [PATCH 0015/5631] perf vendor events intel: Refresh broadwellx metrics Update the broadwellx metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, "Sample with" documentation is added to many TMA metrics, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwellx/bdx-metrics.json | 1626 ++++++++--------- .../arch/x86/broadwellx/uncore-cache.json | 74 +- .../x86/broadwellx/uncore-interconnect.json | 64 +- .../arch/x86/broadwellx/uncore-other.json | 4 +- 4 files changed, 873 insertions(+), 895 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index f5c8f707c692..65ec0c9e55d1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -1,1189 +1,1167 @@ [ { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "ScaleUnit": "100%" }, { "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." - }, - { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" - }, - { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" - }, - { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" - }, - { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" - }, - { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_mispredicts_resteers" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cbox_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_UOPS_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x192@) / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x181@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x191@) / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Intel(R) Quick Path Interconnect (QPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_Q_TxL_FLITS_G0.DATA * 8 / 1e6 / duration_time", - "MetricName": "qpi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ + cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x180\\,filter_tid\\=0x3e@) * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Uops delivered from loop stream detector(LSD) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_loop_stream_detector", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "MACHINE_CLEARS.COUNT * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit).", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * (DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED)) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + UOPS_RETIRED.RETIRE_SLOTS / SLOTS)", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_LOAD_MISSES.WALK_COMPLETED) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min(MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ITLB_MISSES.WALK_COMPLETED) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / CPU_CLK_UNHALTED.THREAD", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_MISS / tma_info_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min((60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min(43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min(41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min((1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_MISS / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min(310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min((200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min((200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((8 * DTLB_STORE_MISSES.STLB_HIT + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=0x1@ + 7 * DTLB_STORE_MISSES.WALK_COMPLETED) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + RESOURCE_STALLS.SB) / (CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES * tma_branch_resteers / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY)", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", "MetricExpr": "tma_store_op_utilization", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", - "MetricName": "tma_port_7", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_TOTAL + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (CYCLE_ACTIVITY.STALLS_TOTAL - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_heavy_operations", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_heavy_operations - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "tma_branch_resteers - tma_mispredicts_resteers - tma_clears_resteers", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json index 38eaac5afd4b..746954775437 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -5,7 +5,7 @@ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", "Filter": "filter_opc=0x191", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -16,7 +16,7 @@ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", "Filter": "filter_opc=0x192", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -27,7 +27,7 @@ "EventName": "LLC_MISSES.DATA_READ", "Filter": "filter_opc=0x182", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -38,7 +38,7 @@ "EventName": "LLC_MISSES.MMIO_READ", "Filter": "filter_opc=0x187,filter_nc=1", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -49,7 +49,7 @@ "EventName": "LLC_MISSES.MMIO_WRITE", "Filter": "filter_opc=0x18f,filter_nc=1", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -60,7 +60,7 @@ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", "Filter": "filter_opc=0x1c8,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -71,7 +71,7 @@ "EventName": "LLC_MISSES.PCIE_READ", "Filter": "filter_opc=0x19e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -82,7 +82,7 @@ "EventName": "LLC_MISSES.PCIE_WRITE", "Filter": "filter_opc=0x1c8", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -93,7 +93,7 @@ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", "Filter": "filter_opc=0x190", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -104,7 +104,7 @@ "EventName": "LLC_MISSES.UNCACHEABLE", "Filter": "filter_opc=0x187", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -115,7 +115,7 @@ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", "Filter": "filter_opc=0x181", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -126,7 +126,7 @@ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", "Filter": "filter_opc=0x180,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", "Unit": "CBO" }, @@ -136,7 +136,7 @@ "EventName": "LLC_REFERENCES.PCIE_READ", "Filter": "filter_opc=0x19e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -147,7 +147,7 @@ "EventName": "LLC_REFERENCES.PCIE_WRITE", "Filter": "filter_opc=0x1c8,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -158,7 +158,7 @@ "EventName": "LLC_REFERENCES.STREAMING_FULL", "Filter": "filter_opc=0x18c", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -169,7 +169,7 @@ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", "Filter": "filter_opc=0x18d", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -1157,7 +1157,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", "Unit": "CBO" }, @@ -1166,7 +1166,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", "Unit": "CBO" }, @@ -1175,7 +1175,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by locally HOMed memory.", "UMask": "0x28", "Unit": "CBO" }, @@ -1184,7 +1184,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", "UMask": "0x21", "Unit": "CBO" }, @@ -1193,7 +1193,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by locally HOMed memory.", "UMask": "0x2a", "Unit": "CBO" }, @@ -1202,7 +1202,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", "UMask": "0x23", "Unit": "CBO" }, @@ -1211,7 +1211,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", "Unit": "CBO" }, @@ -1220,7 +1220,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by remote caches or remote memory.", "UMask": "0x8a", "Unit": "CBO" }, @@ -1229,7 +1229,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", "UMask": "0x83", "Unit": "CBO" }, @@ -1238,7 +1238,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", "Unit": "CBO" }, @@ -1247,7 +1247,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", "Unit": "CBO" }, @@ -1256,7 +1256,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", "Unit": "CBO" }, @@ -1265,7 +1265,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", "Unit": "CBO" }, @@ -1274,7 +1274,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", "Unit": "CBO" }, @@ -1283,7 +1283,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", "Unit": "CBO" }, @@ -1292,7 +1292,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", "Unit": "CBO" }, @@ -1301,7 +1301,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by remote caches or remote memory.", "UMask": "0x88", "Unit": "CBO" }, @@ -1310,7 +1310,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", "UMask": "0x81", "Unit": "CBO" }, @@ -1319,7 +1319,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", + "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", "Unit": "CBO" }, @@ -1590,7 +1590,7 @@ "EventCode": "0x2", "EventName": "UNC_C_TxR_INSERTS.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transfering writeback data to the cache.", "UMask": "0x40", "Unit": "CBO" }, @@ -1737,7 +1737,7 @@ "EventCode": "0x41", "EventName": "UNC_H_DIRECTORY_LAT_OPT", "PerPkg": "1", - "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory returned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", + "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory retuned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", "Unit": "HA" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json index a5457c7ba58b..489a3673323d 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -3,7 +3,7 @@ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", "EventName": "QPI_CTL_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "ScaleUnit": "8Bytes", "UMask": "0x4", "Unit": "QPI LL" @@ -12,7 +12,7 @@ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", "EventName": "QPI_DATA_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "ScaleUnit": "8Bytes", "UMask": "0x2", "Unit": "QPI LL" @@ -134,7 +134,7 @@ "EventCode": "0x9", "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", "Unit": "QPI LL" }, { @@ -391,7 +391,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generall not considered part of the QPI bandwidth.", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generall not considered part of the QPI bandwidth.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -400,7 +400,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -409,7 +409,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", "Unit": "QPI LL" }, @@ -418,7 +418,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -427,7 +427,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -436,7 +436,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -445,7 +445,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -454,7 +454,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -463,7 +463,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -472,7 +472,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -481,7 +481,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -490,7 +490,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -499,7 +499,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -508,7 +508,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -924,7 +924,7 @@ "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -932,7 +932,7 @@ "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -940,7 +940,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", "EventName": "UNC_Q_TxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -948,7 +948,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", "Unit": "QPI LL" }, @@ -956,7 +956,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -964,7 +964,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -972,7 +972,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -980,7 +980,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -988,7 +988,7 @@ "BriefDescription": "Flits Transferred - Group 1; SNP Flits", "EventName": "UNC_Q_TxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -997,7 +997,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -1006,7 +1006,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not te NCB headers.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not te NCB headers.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -1015,7 +1015,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -1024,7 +1024,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -1033,7 +1033,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -1042,7 +1042,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", "Unit": "QPI LL" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json index 495e34ee5bfb..a80d931dc3d5 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json @@ -2312,7 +2312,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transfered). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transfered in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", "Unit": "R3QPI" }, @@ -2321,7 +2321,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transfered). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transfered in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x4", "Unit": "R3QPI" }, -- GitLab From 6635df2f4cde6124accbb909b51961603908950c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:12 -0800 Subject: [PATCH 0016/5631] perf vendor events intel: Refresh cascadelakex events Update the cascadelakex events from 1.16 to 1.17. Generation was done using https://github.com/intel/perfmon. Notable changes are new events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, "Sample with" documentation is added to many TMA metrics, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-16-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/cascadelakex/cache.json | 24 +- .../arch/x86/cascadelakex/clx-metrics.json | 2198 +++++++++-------- .../arch/x86/cascadelakex/frontend.json | 8 +- .../arch/x86/cascadelakex/pipeline.json | 16 + .../arch/x86/cascadelakex/uncore-memory.json | 18 +- .../arch/x86/cascadelakex/uncore-other.json | 120 +- .../arch/x86/cascadelakex/uncore-power.json | 8 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 8 files changed, 1236 insertions(+), 1158 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json index 1070ad317ec9..a842f05cb60d 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/cache.json @@ -234,20 +234,22 @@ "UMask": "0x4f" }, { - "BriefDescription": "All retired load instructions.", + "BriefDescription": "Retired load instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "All retired store instructions.", + "BriefDescription": "Retired store instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_STORES", "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "2000003", "UMask": "0x82" }, @@ -388,12 +390,12 @@ "UMask": "0x4" }, { - "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches. Precise event.", + "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.", "Data_LA": "1", "EventCode": "0xD3", "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM", "PEBS": "1", - "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode). Precise event", + "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode).", "SampleAfterValue": "100007", "UMask": "0x10" }, @@ -477,12 +479,12 @@ "UMask": "0x20" }, { - "BriefDescription": "Retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches. Precise event.", + "BriefDescription": "Retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.", "Data_LA": "1", "EventCode": "0xD1", "EventName": "MEM_LOAD_RETIRED.LOCAL_PMM", "PEBS": "1", - "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode). Precise event", + "PublicDescription": "Counts retired load instructions with local Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3 (AppDirect or Memory Mode) and DRAM cache(Memory Mode).", "SampleAfterValue": "100003", "UMask": "0x80" }, @@ -5039,7 +5041,7 @@ "UMask": "0x80" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", @@ -5146,14 +5148,6 @@ "SampleAfterValue": "2000003", "UMask": "0x4" }, - { - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, { "BriefDescription": "This event is deprecated. Refer to new event OCR.ALL_DATA_RD.ANY_RESPONSE", "Deprecated": "1", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 356cf6603b69..4e993a3220e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1,1548 +1,1608 @@ [ { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" - }, - { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" - }, - { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" - }, - { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" - }, - { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" - }, - { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" - }, - { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" - }, - { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + 44 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(110 * tma_info_average_frequency * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_average_frequency * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_Silent_PKI" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_NonSilent_PKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License0_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License1_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License2_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_PMM_Read_Latency" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_DRAM_Read_Latency" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Read_BW" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Write_BW" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Write_BW" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Read_BW" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Percentage of time spent in the active CPU power state C0", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "cpu_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_read_bw" }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_write_bw" }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x12D4043300000000@ / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x12CC023300000000@ / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043300000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043300000000@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043200000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043100000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "dtlb_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ / (cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ + cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@ / (cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ + cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", - "MetricName": "upi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_silent_pki" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit).", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", - "MetricName": "tma_decoder0_alone", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_read_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min((12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_write_bw" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license1_utilization", + "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license2_utilization", + "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min(((47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) + (47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min((47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OCR.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OCR.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cha_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min((20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound - min(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0), 1), 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min((80 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min((147.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min(((110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "min(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0), 1)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module. ", + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "17 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min((110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * (OCR.DEMAND_RFO.L3_MISS.REMOTE_HITM + OCR.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * (OCR.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OCR.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "59.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD)", - "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions.", - "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY, 1)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_pmm_bound", + "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", "MetricExpr": "tma_store_op_utilization", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", - "MetricName": "tma_port_7", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - (UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "127 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_memory_operations", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fused_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_non_fused_branches", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "40 * ROB_MISC_EVENTS.PAUSE_INST / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body.", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_other_light_ops", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / SLOTS, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json index 13ccf50db43d..04f08e4d2402 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json @@ -322,7 +322,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", @@ -331,7 +331,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -340,7 +340,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", @@ -358,7 +358,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json index 64e1fe351333..0f06e314fe36 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json @@ -93,6 +93,22 @@ "SampleAfterValue": "400009", "UMask": "0x10" }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "PublicDescription": "This event counts both taken and not taken speculative and retired mispredicted branch instructions.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "All mispredicted macro branch instructions retired.", "EventCode": "0xC5", diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json index 70a2c0ff8dfd..aafd2c9b813b 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json @@ -192,7 +192,7 @@ "EventCode": "0x9", "EventName": "UNC_M_ECC_CORRECTABLE_ERRORS", "PerPkg": "1", - "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit erros in lockstep mode.", + "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit errors in lockstep mode.", "Unit": "iMC" }, { @@ -212,7 +212,7 @@ "Unit": "iMC" }, { - "BriefDescription": "UNC_M_MAJMODE2.PMM_CYC", + "BriefDescription": "Major Mode 2 : Cycles in PMM major mode", "EventCode": "0xED", "EventName": "UNC_M_MAJMODE2.PMM_CYC", "PerPkg": "1", @@ -220,7 +220,7 @@ "Unit": "iMC" }, { - "BriefDescription": "UNC_M_MAJMODE2.PMM_ENTER", + "BriefDescription": "Major Mode 2 : Entered PMM major mode", "EventCode": "0xED", "EventName": "UNC_M_MAJMODE2.PMM_ENTER", "PerPkg": "1", @@ -290,7 +290,7 @@ "Unit": "iMC" }, { - "BriefDescription": "All commands for Intel Optane DC persistent memory", + "BriefDescription": "All commands for Intel(R) Optane(TM) DC persistent memory", "EventCode": "0xEA", "EventName": "UNC_M_PMM_CMD1.ALL", "PerPkg": "1", @@ -314,7 +314,7 @@ "Unit": "iMC" }, { - "BriefDescription": "Regular reads(RPQ) commands for Intel Optane DC persistent memory", + "BriefDescription": "Regular reads(RPQ) commands for Intel(R) Optane(TM) DC persistent memory", "EventCode": "0xEA", "EventName": "UNC_M_PMM_CMD1.RD", "PerPkg": "1", @@ -331,7 +331,7 @@ "Unit": "iMC" }, { - "BriefDescription": "Underfill read commands for Intel Optane DC persistent memory", + "BriefDescription": "Underfill read commands for Intel(R) Optane(TM) DC persistent memory", "EventCode": "0xEA", "EventName": "UNC_M_PMM_CMD1.UFILL_RD", "PerPkg": "1", @@ -348,7 +348,7 @@ "Unit": "iMC" }, { - "BriefDescription": "Write commands for Intel Optane DC persistent memory", + "BriefDescription": "Write commands for Intel(R) Optane(TM) DC persistent memory", "EventCode": "0xEA", "EventName": "UNC_M_PMM_CMD1.WR", "PerPkg": "1", @@ -522,7 +522,7 @@ "Unit": "iMC" }, { - "BriefDescription": "Write Pending Queue Occupancy of all write requests for Intel Optane DC persistent memory", + "BriefDescription": "Write Pending Queue Occupancy of all write requests for Intel(R) Optane(TM) DC persistent memory", "EventCode": "0xE4", "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL", "PerPkg": "1", @@ -2735,7 +2735,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json index ef4767feb4e2..5f3ed5e843b9 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json @@ -44,7 +44,7 @@ "MetricName": "LLC_MISSES.PCIE_WRITE", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit onthe main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "ScaleUnit": "4Bytes", "UMask": "0x1", "Unit": "IIO" @@ -856,7 +856,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HtiME$ on Reads without RspFwdI*", + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", "EventCode": "0x61", "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", "PerPkg": "1", @@ -1210,7 +1210,7 @@ "EventCode": "0x34", "EventName": "UNC_CHA_LLC_LOOKUP.WRITE", "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cachable and UC.", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", "Unit": "CHA" }, @@ -3481,7 +3481,7 @@ "EventCode": "0x5D", "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its currentl copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", "UMask": "0x8", "Unit": "CHA" }, @@ -4082,10 +4082,11 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.ALL", + "BriefDescription": "TOR Occupancy : All", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0xff", "Unit": "CHA" }, @@ -4153,20 +4154,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", "Filter": "config1=0x40233", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", "Filter": "config1=0x40433", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, @@ -4189,20 +4192,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", "Filter": "config1=0x4b033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", "Filter": "config1=0x40033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, @@ -4216,11 +4221,12 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", "Filter": "config1=0x40233", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, @@ -4253,20 +4259,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", "Filter": "config1=0x4b033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", "Filter": "config1=0x40033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, @@ -4308,7 +4316,7 @@ "Unit": "CHA" }, { - "BriefDescription": "TOR Occupancy; RDCUR isses from Local IO", + "BriefDescription": "TOR Occupancy; RDCUR misses from Local IO", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", "Filter": "config1=0x43C33", @@ -11637,7 +11645,7 @@ "FCMask": "0x07", "PerPkg": "1", "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit onthe main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", "UMask": "0x1", "Unit": "IIO" }, @@ -12024,7 +12032,7 @@ "Unit": "IIO" }, { - "BriefDescription": "UNC_IIO_NOTHING", + "BriefDescription": "Counting disabled", "EventName": "UNC_IIO_NOTHING", "PerPkg": "1", "Unit": "IIO" @@ -15622,7 +15630,7 @@ "EventCode": "0xC", "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -16128,35 +16136,35 @@ "Unit": "M2M" }, { - "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", "EventCode": "0x28", "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", "Unit": "M2M" }, { - "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", "EventCode": "0x27", "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", "PerPkg": "1", - "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", "Unit": "M2M" }, { - "BriefDescription": "Messages sent direct to the Intel UPI", + "BriefDescription": "Messages sent direct to the Intel(R) UPI", "EventCode": "0x26", "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)", + "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", "Unit": "M2M" }, { - "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", "EventCode": "0x29", "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", "PerPkg": "1", - "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden", + "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", "Unit": "M2M" }, { @@ -16583,7 +16591,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Read requests to Intel Optane DC persistent memory issued to the iMC from M2M", + "BriefDescription": "Read requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", "EventCode": "0x37", "EventName": "UNC_M2M_IMC_READS.TO_PMM", "PerPkg": "1", @@ -16650,7 +16658,7 @@ "Unit": "M2M" }, { - "BriefDescription": "Write requests to Intel Optane DC persistent memory issued to the iMC from M2M", + "BriefDescription": "Write requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", "EventCode": "0x38", "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", "PerPkg": "1", @@ -16675,7 +16683,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 0", + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 0", "EventCode": "0x4F", "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN0", "PerPkg": "1", @@ -16683,7 +16691,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 1", + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 1", "EventCode": "0x4F", "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN1", "PerPkg": "1", @@ -16691,7 +16699,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 2", + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 2", "EventCode": "0x4F", "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN2", "PerPkg": "1", @@ -16699,7 +16707,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", "EventCode": "0x51", "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN0", "PerPkg": "1", @@ -16707,7 +16715,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", "EventCode": "0x51", "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN1", "PerPkg": "1", @@ -16715,7 +16723,7 @@ "Unit": "M2M" }, { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", "EventCode": "0x51", "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN2", "PerPkg": "1", @@ -16737,11 +16745,11 @@ "Unit": "M2M" }, { - "BriefDescription": "Prefecth requests that got turn into a demand request", + "BriefDescription": "Prefetch requests that got turn into a demand request", "EventCode": "0x56", "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefecth queue is made of CAM (Content Addressable Memory)", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefetch queue is made of CAM (Content Addressable Memory)", "Unit": "M2M" }, { @@ -20804,7 +20812,7 @@ "EventCode": "0x40", "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", "PerPkg": "1", - "PublicDescription": "Number ot times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", "UMask": "0x2", "Unit": "M3UPI" }, @@ -20813,7 +20821,7 @@ "EventCode": "0x40", "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", "PerPkg": "1", - "PublicDescription": "Number ot times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", "UMask": "0x1", "Unit": "M3UPI" }, @@ -20822,7 +20830,7 @@ "EventCode": "0x40", "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", "PerPkg": "1", - "PublicDescription": "Number ot times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", "UMask": "0x4", "Unit": "M3UPI" }, @@ -20831,7 +20839,7 @@ "EventCode": "0x40", "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", "PerPkg": "1", - "PublicDescription": "Number ot times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", "UMask": "0x8", "Unit": "M3UPI" }, @@ -21397,7 +21405,7 @@ "Unit": "M3UPI" }, { - "BriefDescription": "Flit Gen - Header 1; Acumullate", + "BriefDescription": "Flit Gen - Header 1; Accumulate", "EventCode": "0x53", "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", "PerPkg": "1", @@ -24618,7 +24626,7 @@ "EventCode": "0x29", "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", "PerPkg": "1", - "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", "Unit": "M3UPI" }, { @@ -24973,11 +24981,11 @@ "Unit": "M2M" }, { - "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)", + "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", "EventCode": "0x1", "EventName": "UNC_UPI_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", "Unit": "UPI LL" }, { @@ -24999,11 +25007,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Data Response packets that go direct to Intel UPI", + "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", "EventCode": "0x12", "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", "UMask": "0x2", "Unit": "UPI LL" }, @@ -25072,11 +25080,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)", + "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", "EventCode": "0x21", "EventName": "UNC_UPI_L1_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", "Unit": "UPI LL" }, { @@ -25238,11 +25246,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode", + "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", "EventCode": "0x25", "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", "Unit": "UPI LL" }, { @@ -25451,7 +25459,7 @@ "EventCode": "0x3", "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", "UMask": "0xf", "Unit": "UPI LL" }, @@ -25460,7 +25468,7 @@ "EventCode": "0x3", "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", "UMask": "0x27", "Unit": "UPI LL" }, @@ -25784,11 +25792,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode", + "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", "EventCode": "0x27", "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", "Unit": "UPI LL" }, { @@ -25960,7 +25968,7 @@ "EventCode": "0x41", "EventName": "UNC_UPI_TxL_BYPASSED", "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", "Unit": "UPI LL" }, { @@ -25968,7 +25976,7 @@ "EventCode": "0x2", "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel Ultra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", "UMask": "0xf", "Unit": "UPI LL" }, @@ -25977,7 +25985,7 @@ "EventCode": "0x2", "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", "UMask": "0x27", "Unit": "UPI LL" }, @@ -26328,7 +26336,7 @@ "EventCode": "0x2", "EventName": "UPI_DATA_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel Ultra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", "ScaleUnit": "7.11E-06Bytes", "UMask": "0xf", "Unit": "UPI LL" diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-power.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-power.json index 6835e14cd42c..c6254af7a468 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-power.json @@ -143,7 +143,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -151,7 +151,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -159,7 +159,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -175,7 +175,7 @@ "EventCode": "0x9", "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that we are in Interal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", "Unit": "PCU" }, { diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index cad51223d0ea..793076e00188 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -5,7 +5,7 @@ GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v26,broadwell,core GenuineIntel-6-56,v7,broadwellde,core GenuineIntel-6-4F,v19,broadwellx,core -GenuineIntel-6-55-[56789ABCDEF],v1.16,cascadelakex,core +GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -- GitLab From 1e8ad07e3425ec37e37b6035defc856fc7cdcd7f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:13 -0800 Subject: [PATCH 0017/5631] perf vendor events intel: Add graniterapids events Add version 1.00 of the graniterapids events from https://github.com/intel/perfmon. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-17-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/graniterapids/cache.json | 54 ++++++ .../arch/x86/graniterapids/frontend.json | 10 + .../arch/x86/graniterapids/memory.json | 174 ++++++++++++++++++ .../arch/x86/graniterapids/other.json | 29 +++ .../arch/x86/graniterapids/pipeline.json | 102 ++++++++++ .../x86/graniterapids/virtual-memory.json | 26 +++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + 7 files changed, 396 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/frontend.json create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/other.json create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json create mode 100644 tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/cache.json b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json new file mode 100644 index 000000000000..56212827870c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/cache.json @@ -0,0 +1,54 @@ +[ + { + "BriefDescription": "L2 code requests", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Retired load instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "SampleAfterValue": "1000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Retired store instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json new file mode 100644 index 000000000000..dfd9c5ea1584 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json @@ -0,0 +1,10 @@ +[ + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the nominator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json new file mode 100644 index 000000000000..1c0e0e86e58e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/memory.json @@ -0,0 +1,174 @@ +[ + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", + "PEBS": "2", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an RTM execution aborted.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "PublicDescription": "Counts the number of times RTM abort was triggered.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_READ", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/other.json b/tools/perf/pmu-events/arch/x86/graniterapids/other.json new file mode 100644 index 000000000000..5e799bae03ea --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/other.json @@ -0,0 +1,29 @@ +[ + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json new file mode 100644 index 000000000000..d6aafb258708 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -0,0 +1,102 @@ +[ + { + "BriefDescription": "All branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x82" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the nominator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "SampleAfterValue": "10000003", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "SampleAfterValue": "10000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the nominator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json new file mode 100644 index 000000000000..8784c97b7534 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/graniterapids/virtual-memory.json @@ -0,0 +1,26 @@ +[ + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 793076e00188..1677ec22e2e3 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -9,6 +9,7 @@ GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core +GenuineIntel-6-A[DE],v1.00,graniterapids,core GenuineIntel-6-(3C|45|46),v32,haswell,core GenuineIntel-6-3F,v26,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.15,icelake,core -- GitLab From 2f244993435516a46a1c1d45030781de69b372fd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:14 -0800 Subject: [PATCH 0018/5631] perf vendor events intel: Refresh haswell metrics Update the haswell metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-18-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/haswell/hsw-metrics.json | 1220 ++++++++++------- 1 file changed, 687 insertions(+), 533 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2e032beee542..2528418200bb 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -1,799 +1,953 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if IPC > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB) if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB))) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "10 * ARITH.DIVIDER_UOPS / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if IPC > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB) if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_6", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" - }, + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" + }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address) Sample with: UOPS_DISPATCHED_PORT.PORT_7", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_7", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "MetricName": "tma_info_retire" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / CORE_CLKS", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.L3_MISS))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "MEM_Parallel_Requests", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Request_Latency" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From 05dd42fe61453bf23b548e9cd10e8b94b33ab121 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:15 -0800 Subject: [PATCH 0019/5631] perf vendor events intel: Refresh haswellx metrics Update the haswellx metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added and "Sample with" documentation is added to many TMA metrics, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-19-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/haswellx/hsx-metrics.json | 1397 ++++++++--------- 1 file changed, 679 insertions(+), 718 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 2e1fbc936d25..11f152c346eb 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -1,1023 +1,984 @@ [ { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" - }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" - }, - { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" - }, - { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" - }, - { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" - }, - { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" - }, - { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" - }, - { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" - }, - { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" - }, - { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / CORE_CLKS", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "10 * ARITH.DIVIDER_UOPS / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cbox_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_UOPS_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "ScaleUnit": "100%" }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_UOPS_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "ScaleUnit": "100%" }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (cbox@UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@) / (UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "(UOPS_EXECUTED.CORE / 2 / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) if #SMT_on else UOPS_EXECUTED.CORE / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@))", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_C_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Intel(R) Quick Path Interconnect (QPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_Q_TxL_FLITS_G0.DATA * 8 / 1e6 / duration_time", - "MetricName": "qpi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x19e@ * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.OPCODE\\,filter_opc\\=0x1c8\\,filter_tid\\=0x3e@ * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Uops delivered from loop stream detector(LSD) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "(UOPS_ISSUED.ANY - IDQ.MITE_UOPS - IDQ.MS_UOPS - IDQ.DSB_UOPS) / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_loop_stream_detector", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x192@) / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x181@ + cbox@UNC_C_TOR_INSERTS.MISS_OPCODE\\,filter_opc\\=0x191@) / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@ / (cbox@UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE\\,filter_opc\\=0x182@ + cbox@UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE\\,filter_opc\\=0x182@)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + UOPS_RETIRED.RETIRE_SLOTS / SLOTS)", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(8 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min(MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.REQUEST_FB_FULL\\,cmask\\=0x1@ / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CPU_CLK_UNHALTED.THREAD", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CPU_CLK_UNHALTED.THREAD", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min((60 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min(43 * (MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min(41 * (MEM_LOAD_UOPS_RETIRED.L3_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min((1 - MEM_LOAD_UOPS_RETIRED.L3_HIT / (MEM_LOAD_UOPS_RETIRED.L3_HIT + 7 * MEM_LOAD_UOPS_RETIRED.L3_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x6@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min(310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min((200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min((200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((8 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "10 * ARITH.DIVIDER_UOPS / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ if INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / CPU_CLK_UNHALTED.THREAD", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@)) / 2 - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - (cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\=0x1\\,cmask\\=0x1@ / 2 if #SMT_on else min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / CORE_CLKS", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=0x3@) / CORE_CLKS", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / tma_info_core_clks", "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "310 * (MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.L3_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", - "MetricName": "tma_port_2", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", - "MetricName": "tma_port_3", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", - "MetricExpr": "tma_store_op_utilization", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", - "MetricName": "tma_port_4", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", - "MetricName": "tma_port_7", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", "ScaleUnit": "100%" }, { "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "INST_RETIRED.X87 * UPI / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricExpr": "INST_RETIRED.X87 * tma_info_uoppi / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1", "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_heavy_operations", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_heavy_operations - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", - "ScaleUnit": "100%" } ] -- GitLab From 5d48694714b9d887b99e3175ccb9a065e52976e5 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:16 -0800 Subject: [PATCH 0020/5631] perf vendor events intel: Refresh icelake events Update the icelake events from 1.15 to 1.17. Generation was done using https://github.com/intel/perfmon. Notable changes are new events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-20-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/icelake/cache.json | 16 + .../arch/x86/icelake/floating-point.json | 31 + .../arch/x86/icelake/icl-metrics.json | 1932 ++++++++++------- .../pmu-events/arch/x86/icelake/pipeline.json | 23 +- .../arch/x86/icelake/uncore-other.json | 56 + tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 6 files changed, 1235 insertions(+), 825 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json index bc6587391760..a9174a0837f0 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json @@ -154,6 +154,22 @@ "SampleAfterValue": "200003", "UMask": "0x21" }, + { + "BriefDescription": "All requests that miss L2 cache. This event is not supported on ICL and ICX products, only supported on RKL products.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts all requests that miss L2 cache. This event is not supported on ICL and ICX products, only supported on RKL products.", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "All L2 requests. This event is not supported on ICL and ICX products, only supported on RKL products.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all L2 requests. This event is not supported on ICL and ICX products, only supported on RKL products.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, { "BriefDescription": "RFO requests that hit L2 cache", "EventCode": "0x24", diff --git a/tools/perf/pmu-events/arch/x86/icelake/floating-point.json b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json index 655342dadac6..85c26c889088 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json @@ -39,6 +39,14 @@ "SampleAfterValue": "100003", "UMask": "0x20" }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -55,6 +63,22 @@ "SampleAfterValue": "100003", "UMask": "0x80" }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -70,5 +94,12 @@ "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0xfc" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index 2ad36e00d289..f45ae3483df4 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -1,1230 +1,1518 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CLKS + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / CLKS", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: BACLEARS.ANY", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_decoder0_alone", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_mite_4wide", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "FetchBW;LSD;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_lsd", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_branch_instructions", + "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" + }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(29 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "23.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "32.5 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(29 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 23.5 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "23.5 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "9 * Average_Frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / CLKS + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS - tma_l2_bound", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "32.5 * Average_Frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_streaming_stores", - "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", - "ScaleUnit": "100%" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CLKS if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CLKS)", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CLKS + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CLKS", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / CLKS", - "MetricGroup": "TopdownL6;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "CLKS * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED.PORT_0", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED.PORT_1", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED.PORT_6", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations Sample with: UOPS_DISPATCHED.PORT_7_8", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_memory_operations", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_branch_instructions", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_other_light_ops", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_retiring * SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * ASSISTS.ANY / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_taken", + "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_ret", + "MetricThreshold": "tma_info_ipmisp_ret < 500" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;tma_L1_group", - "MetricName": "Slots_Utilization" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_instructions", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * SLOTS / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "Fed;LSD", - "MetricName": "LSD_Coverage" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l3_miss_latency" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_lsd_coverage" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", + "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", "MetricGroup": "Bad;Branches", - "MetricName": "Other_Branches" - }, - { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "MetricName": "tma_info_other_branches" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license1_utilization", + "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license2_utilization", + "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / Instructions", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_slots_utilization" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * CORE_CLKS)", + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 7.5" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "9 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License0_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License1_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License2_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", + "MetricName": "tma_mite_4wide", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { - "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C8_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C10_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelake/pipeline.json b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json index 3b31a842a0b1..154fee4b60fb 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/icelake/pipeline.json @@ -158,6 +158,15 @@ "SampleAfterValue": "50021", "UMask": "0x20" }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "50021", + "UMask": "0x8" + }, { "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", "EventCode": "0xec", @@ -375,6 +384,16 @@ "SampleAfterValue": "2000003", "UMask": "0x3" }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0x0d", @@ -747,7 +766,7 @@ "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", "EventCode": "0x0e", "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to 'Mixing Intel AVX and Intel SSE Code' section of the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -775,7 +794,7 @@ "EventCode": "0xc2", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "Invert": "1", - "PublicDescription": "Counts the number of cycles using always true condition (uops_ret &lt; 16) applied to non PEBS uops retired event.", + "PublicDescription": "Counts the number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "1000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json index f7aff8818f46..b27d95b2c857 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json @@ -7,6 +7,54 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", "EventCode": "0x81", @@ -15,6 +63,14 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "UNC_CLOCK.SOCKET", "EventCode": "0xff", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 1677ec22e2e3..b258702e0666 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -12,7 +12,7 @@ GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-A[DE],v1.00,graniterapids,core GenuineIntel-6-(3C|45|46),v32,haswell,core GenuineIntel-6-3F,v26,haswellx,core -GenuineIntel-6-(7D|7E|A7),v1.15,icelake,core +GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.17,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core -- GitLab From 384133a4ede3d2eee056feaf26292574d8d71095 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:17 -0800 Subject: [PATCH 0021/5631] perf vendor events intel: Refresh icelakex metrics Update the icelakex metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, "Sample with" documentation is added to many TMA metrics, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-21-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/icelakex/icx-metrics.json | 2153 +++++++++-------- .../arch/x86/icelakex/uncore-memory.json | 2 +- .../arch/x86/icelakex/uncore-other.json | 4 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 4 files changed, 1100 insertions(+), 1061 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 22b2a97d0ff8..8109088a4df7 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -1,1529 +1,1568 @@ [ { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" - }, - { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" - }, - { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" - }, - { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" - }, - { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" - }, - { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" - }, - { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;tma_L1_group", - "MetricName": "Slots_Utilization" - }, - { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." - }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, - { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." - }, - { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" - }, - { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" - }, - { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" - }, - { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" - }, - { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" - }, - { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" - }, - { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * SLOTS / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_branch_instructions", + "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 43.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43.5 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "Other_Branches" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "48 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / Instructions", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_Silent_PKI" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_NonSilent_PKI" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License0_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License1_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License2_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_PMM_Read_Latency" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_DRAM_Read_Latency" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Read_BW" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Write_BW" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Write_BW" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Read_BW" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "Percentage of time spent in the active CPU power state C0", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "cpu_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", + "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_read_bw" }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_write_bw" }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_CRD + UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF) / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_to_pmem_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_to_dram_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_taken", + "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_ret", + "MetricThreshold": "tma_info_ipmisp_ret < 500" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", - "MetricName": "upi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR + UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR) * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_HIT_ITOM + UNC_CHA_TOR_INSERTS.IO_MISS_ITOM + UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR + UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR) * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_silent_pki" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS) / tma_info_instructions", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit).", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l3_miss_latency" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / cha_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CPU_CLK_UNHALTED.DISTRIBUTED / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", - "MetricName": "tma_decoder0_alone", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=0x4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=0x5@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", - "MetricName": "tma_mite_4wide", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CPU_CLK_UNHALTED.DISTRIBUTED / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)), 0)", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=0x1\\,edge\\=0x1@ / slots", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_other_branches" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_read_bw" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_write_bw" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license1_utilization", + "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min((16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license2_utilization", + "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_slots_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cha_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min(((48 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 4 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 4 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min((47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 4 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min((23 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 4 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 7.5" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound - min(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0), 1), 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min((66.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 23 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min((131 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 23 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "19 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min(((120 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 23 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (120 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 23 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "min(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0), 1)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module. ", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min(48 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "43.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "min(9 * OCR.STREAMING_WR.ANY_RESPONSE / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_streaming_stores", - "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck.", + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CPU_CLK_UNHALTED.DISTRIBUTED, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) + 0 * slots", - "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CPU_CLK_UNHALTED.THREAD + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance.", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions.", - "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", + "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", + "MetricName": "tma_mite_4wide", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY, 1)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", + "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_pmm_bound", + "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - tma_heavy_operations)", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + 0 * slots", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricExpr": "(97 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 97 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "108 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "37 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_memory_operations", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_branch_instructions", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body.", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_other_light_ops", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=0x1@) / IDQ.MITE_UOPS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / slots", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * ASSISTS.ANY / slots, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, { - "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C1_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json index 0d495ae53f3d..66bb4538c6f2 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json @@ -538,7 +538,7 @@ "EventCode": "0x02", "EventName": "UNC_M_PRE_COUNT.PGT", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel. : Prechages from Page Table", + "PublicDescription": "DRAM Precharge commands. : Precharge due to page table : Counts the number of DRAM Precharge commands sent on this channel. : Precharges from Page Table", "UMask": "0x10", "Unit": "iMC" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json index 8c09d1358849..b1d29877c141 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json @@ -1296,7 +1296,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HtiME$ on Reads without RspFwdI*", + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HitME$ on Reads without RspFwdI*", "EventCode": "0x61", "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", "PerPkg": "1", @@ -14927,7 +14927,7 @@ "EventCode": "0x0C", "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Outbound Request Queue Occupancy : Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index b258702e0666..77af9d0bf6d4 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -13,7 +13,7 @@ GenuineIntel-6-A[DE],v1.00,graniterapids,core GenuineIntel-6-(3C|45|46),v32,haswell,core GenuineIntel-6-3F,v26,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core -GenuineIntel-6-6[AC],v1.17,icelakex,core +GenuineIntel-6-6[AC],v1.18,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core GenuineIntel-6-2D,v21,jaketown,core -- GitLab From 115ae94c517c01d843ddef80700d22a7da079596 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:18 -0800 Subject: [PATCH 0022/5631] perf vendor events intel: Refresh ivybridge metrics Update the ivybridge metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-22-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/ivybridge/ivb-metrics.json | 1270 +++++++++-------- 1 file changed, 712 insertions(+), 558 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 88980c1a3a64..5247f69c13b6 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -1,842 +1,996 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFETCH_STALL / CLKS - tma_itlb_misses", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "13 * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", + "MetricExpr": "60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_clks - tma_itlb_misses", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "MetricName": "tma_info_load_miss_real_latency" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / CORE_CLKS", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "29 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_RETIRED.LLC_MISS))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "MEM_Parallel_Requests", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Request_Latency" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From 56c178be7775dda3448171efef6326861ba142d8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:19 -0800 Subject: [PATCH 0023/5631] perf vendor events intel: Refresh ivytown metrics Update the ivytown metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/ivytown/ivt-metrics.json | 1311 +++++++++-------- 1 file changed, 736 insertions(+), 575 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 80444bc4e66e..89469b10fa30 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -1,866 +1,1027 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE.IFETCH_STALL / CLKS - tma_itlb_misses", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "13 * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(60 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "43 * (MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", - "MetricGroup": "Server;TopdownL5;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / CLKS", - "MetricGroup": "Server;Snoop;TopdownL5;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "(200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / CLKS", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "(200 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM + 60 * OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", + "MetricExpr": "ICACHE.IFETCH_STALL / tma_info_clks - tma_itlb_misses", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * DTLB_STORE_MISSES.STLB_HIT + DTLB_STORE_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_UOPS_RETIRED.STLB_MISS_STORES_PS", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if IPC > 1.8 else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS)", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5) / (3 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * OTHER_ASSISTS.ANY_WB_ASSIST / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "0", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "1 / (tma_fp_scalar + tma_fp_vector)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / tma_info_core_clks", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "MetricName": "tma_info_retire" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_UOPS_RETIRED.L1_MISS + MEM_LOAD_UOPS_RETIRED.HIT_LFB)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) - CYCLE_ACTIVITY.STALLS_L1D_PENDING) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_UOPS_RETIRED.L1_HIT_PS;MEM_LOAD_UOPS_RETIRED.HIT_LFB_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION) / CORE_CLKS", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L1D_PENDING - CYCLE_ACTIVITY.STALLS_L2_PENDING) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "41 * (MEM_LOAD_UOPS_RETIRED.LLC_HIT * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS. Related metrics: tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "0", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_UOPS_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cbox_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) + UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - (UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC if tma_info_ipc > 1.8 else UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_LDM_PENDING)) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,inv\\,cmask\\=1@ / 2 if #SMT_on else (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_EXECUTE) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0)) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC - UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((cpu@UOPS_EXECUTED.CORE\\,cmask\\=2@ - cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@) / 2 if #SMT_on else (UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC - UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks)", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(cpu@UOPS_EXECUTED.CORE\\,cmask\\=3@ / 2 if #SMT_on else UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(200 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) + 180 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD)))) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "310 * (MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_UOPS_RETIRED.HIT_LFB / (MEM_LOAD_UOPS_RETIRED.L2_HIT + MEM_LOAD_UOPS_RETIRED.LLC_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM + MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS + MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_DRAM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_HITM + MEM_LOAD_UOPS_LLC_MISS_RETIRED.REMOTE_FWD))) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_UOPS_L3_MISS_RETIRED.REMOTE_DRAM_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "13 * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_UOPS_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "2 * MEM_UOPS_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_UOPS_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) + (1 - MEM_UOPS_RETIRED.LOCK_LOADS / MEM_UOPS_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From 5c3f73c124813869dfba07198aa1030da4690a43 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:20 -0800 Subject: [PATCH 0024/5631] perf vendor events intel: Refresh jaketown events Update the jaketown events from 21 to 22. Generation was done using https://github.com/intel/perfmon. Notable changes are improved event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-24-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/jaketown/cache.json | 6 +- .../arch/x86/jaketown/floating-point.json | 2 +- .../arch/x86/jaketown/frontend.json | 12 +- .../arch/x86/jaketown/jkt-metrics.json | 602 ++++++++++-------- .../arch/x86/jaketown/pipeline.json | 2 +- .../arch/x86/jaketown/uncore-cache.json | 22 +- .../x86/jaketown/uncore-interconnect.json | 74 +-- .../arch/x86/jaketown/uncore-memory.json | 4 +- .../arch/x86/jaketown/uncore-other.json | 22 +- .../arch/x86/jaketown/uncore-power.json | 8 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 11 files changed, 409 insertions(+), 347 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json index f1271039b6b2..b9769d39940c 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/cache.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json @@ -37,7 +37,7 @@ "UMask": "0x5" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -45,7 +45,7 @@ "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles.", + "BriefDescription": "L1D miss outstanding duration in cycles.", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "SampleAfterValue": "2000003", @@ -500,7 +500,7 @@ "UMask": "0x8" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests.", + "BriefDescription": "Cacheable and non-cacheable code read requests.", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "SampleAfterValue": "100003", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json b/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json index 8c2a246adef9..79e8f403c426 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/floating-point.json @@ -64,7 +64,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULsand IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", + "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json index 3f4fc3481112..754ee2749485 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/frontend.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/frontend.json @@ -134,7 +134,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", @@ -143,7 +143,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -151,7 +151,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -160,14 +160,14 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "SampleAfterValue": "2000003", @@ -183,7 +183,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index cb1420df3768..e8f4e5c01c9f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -1,449 +1,511 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, - { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" - }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", + "MetricExpr": "1 / tma_info_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", + "MetricName": "tma_info_execute_per_issue", "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / CORE_CLKS", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "MetricName": "tma_info_flopc" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_INSERTS.MISS_OPCODE@filter_opc\\=0x182@) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182@ / UNC_C_TOR_OCCUPANCY.MISS_OPCODE@filter_opc\\=0x182\\,thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cbox_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_dram_bw_use", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: ", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_DISPATCHED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json index 11d41ce8c922..85c04fe7632a 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json @@ -501,7 +501,7 @@ "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", "SampleAfterValue": "100003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json index b9e68f9f33ea..47830ca5c682 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -572,7 +572,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x4", "Unit": "CBO" }, @@ -581,7 +581,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0xa", "Unit": "CBO" }, @@ -590,7 +590,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x3", "Unit": "CBO" }, @@ -599,7 +599,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x48", "Unit": "CBO" }, @@ -608,7 +608,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x44", "Unit": "CBO" }, @@ -617,7 +617,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x4a", "Unit": "CBO" }, @@ -626,7 +626,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x43", "Unit": "CBO" }, @@ -635,7 +635,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x41", "Unit": "CBO" }, @@ -644,7 +644,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x50", "Unit": "CBO" }, @@ -653,7 +653,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x1", "Unit": "CBO" }, @@ -662,7 +662,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x10", "Unit": "CBO" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json index 1c2cf94889a1..b16bb649225d 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -20,7 +20,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -29,7 +29,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -38,7 +38,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -47,7 +47,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.SUCCESS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -80,7 +80,7 @@ "EventCode": "0x9", "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", "Unit": "QPI LL" }, { @@ -176,7 +176,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_RxL_FLITS_G0.DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -185,7 +185,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -194,7 +194,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_RxL_FLITS_G0.NON_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -203,7 +203,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -212,7 +212,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -221,7 +221,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -230,7 +230,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -239,7 +239,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -248,7 +248,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -257,7 +257,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -266,7 +266,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -275,7 +275,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -284,7 +284,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -293,7 +293,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -302,7 +302,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -311,7 +311,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -553,7 +553,7 @@ "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -561,7 +561,7 @@ "BriefDescription": "Flits Transferred - Group 0; Idle and Null Flits", "EventName": "UNC_Q_TxL_FLITS_G0.IDLE", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -569,7 +569,7 @@ "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -577,7 +577,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", "EventName": "UNC_Q_TxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -585,7 +585,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -593,7 +593,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -601,7 +601,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -609,7 +609,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -617,7 +617,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -625,7 +625,7 @@ "BriefDescription": "Flits Transferred - Group 1; SNP Flits", "EventName": "UNC_Q_TxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -634,7 +634,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -643,7 +643,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -652,7 +652,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -661,7 +661,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -670,7 +670,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -679,7 +679,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", "Unit": "QPI LL" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json index 2faf0dc6675d..6dcc9415a462 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json @@ -101,7 +101,7 @@ "EventCode": "0x9", "EventName": "UNC_M_ECC_CORRECTABLE_ERRORS", "PerPkg": "1", - "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit erros in lockstep mode.", + "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit errors in lockstep mode.", "Unit": "iMC" }, { @@ -413,7 +413,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "PublicDescription": "Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json index 51a9a4e81046..ca727c0e1865 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json @@ -284,7 +284,7 @@ "EventCode": "0xD", "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -630,7 +630,7 @@ "EventCode": "0x20", "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquried in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x8", "Unit": "R3QPI" }, @@ -639,7 +639,7 @@ "EventCode": "0x20", "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquried in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x10", "Unit": "R3QPI" }, @@ -648,7 +648,7 @@ "EventCode": "0x20", "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquried in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x20", "Unit": "R3QPI" }, @@ -657,7 +657,7 @@ "EventCode": "0x21", "EventName": "UNC_R3_IIO_CREDITS_REJECT.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x8", "Unit": "R3QPI" }, @@ -666,7 +666,7 @@ "EventCode": "0x21", "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x10", "Unit": "R3QPI" }, @@ -675,7 +675,7 @@ "EventCode": "0x21", "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x20", "Unit": "R3QPI" }, @@ -684,7 +684,7 @@ "EventCode": "0x22", "EventName": "UNC_R3_IIO_CREDITS_USED.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x8", "Unit": "R3QPI" }, @@ -693,7 +693,7 @@ "EventCode": "0x22", "EventName": "UNC_R3_IIO_CREDITS_USED.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x10", "Unit": "R3QPI" }, @@ -702,7 +702,7 @@ "EventCode": "0x22", "EventName": "UNC_R3_IIO_CREDITS_USED.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transfering data without coherency, and DRS is used for transfering data with coherency (cachable PCI transactions). This event can only track one message class at a time.", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", "UMask": "0x20", "Unit": "R3QPI" }, @@ -1107,7 +1107,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transfered). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transfered in a given message class using an qfclk event.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", "Unit": "R3QPI" }, { diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json index 638aa8a35cdb..b3ee5d741015 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json @@ -234,7 +234,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -242,7 +242,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -250,7 +250,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -266,7 +266,7 @@ "EventCode": "0x9", "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that we are in Interal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", "Unit": "PCU" }, { diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 77af9d0bf6d4..afe811f154d7 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -16,7 +16,7 @@ GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.18,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core -GenuineIntel-6-2D,v21,jaketown,core +GenuineIntel-6-2D,v22,jaketown,core GenuineIntel-6-(57|85),v9,knightslanding,core GenuineIntel-6-A[AC],v1.00,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core -- GitLab From 0a080050433f49fe885de824670472b4c133637b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:21 -0800 Subject: [PATCH 0025/5631] perf vendor events intel: Refresh knightslanding events Update the knightslanding events from 9 to 10. Generation was done using https://github.com/intel/perfmon. The most notable change is in corrections to event descriptions. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-25-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/knightslanding/cache.json | 94 +++++++++---------- .../arch/x86/knightslanding/pipeline.json | 8 +- .../arch/x86/knightslanding/uncore-other.json | 8 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 4 files changed, 56 insertions(+), 56 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json index 01aea3d2832e..d9876cb06b08 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json @@ -6,7 +6,7 @@ "SampleAfterValue": "200003" }, { - "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses.", + "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of core cycles the fetch stalled for all icache misses.", "EventCode": "0x86", "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES", "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", @@ -28,7 +28,7 @@ "UMask": "0x4f" }, { - "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) exlcuding SW prefetches filling only to L2 cache and L1 evictions (automatically exlcudes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times", + "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically exlcudes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times", "EventCode": "0x30", "EventName": "L2_REQUESTS_REJECT.ALL", "SampleAfterValue": "200003" @@ -108,7 +108,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -135,7 +135,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -198,7 +198,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -216,7 +216,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -243,7 +243,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -306,7 +306,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -324,7 +324,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Prefetch requests that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -351,7 +351,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Prefetch requests that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts any Prefetch requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -405,7 +405,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING", "MSRIndex": "0x1a6", @@ -423,7 +423,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Read request that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts any Read request that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -450,7 +450,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Read request that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts any Read request that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -513,7 +513,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING", "MSRIndex": "0x1a6", @@ -531,7 +531,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any request that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts any request that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -558,7 +558,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any request that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts any request that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -621,7 +621,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", "MSRIndex": "0x1a6", @@ -639,7 +639,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data write requests that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -666,7 +666,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data write requests that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Demand cacheable data write requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -729,7 +729,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING", "MSRIndex": "0x1a6", @@ -747,7 +747,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Bus locks and split lock requests that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -774,7 +774,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Bus locks and split lock requests that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -837,7 +837,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING", "MSRIndex": "0x1a6", @@ -855,7 +855,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -882,7 +882,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -945,7 +945,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1035,7 +1035,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1053,7 +1053,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data writes that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1080,7 +1080,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data writes that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1143,7 +1143,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1170,7 +1170,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1197,7 +1197,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1260,7 +1260,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1287,7 +1287,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE", "MSRIndex": "0x1a7", @@ -1314,7 +1314,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a7", @@ -1386,7 +1386,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data HW prefetches that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1413,7 +1413,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data HW prefetches that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1476,7 +1476,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1494,7 +1494,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L2 code HW prefetches that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1521,7 +1521,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L2 code HW prefetches that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1566,7 +1566,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1602,7 +1602,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1683,7 +1683,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Software Prefetches that accounts for reponses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", + "BriefDescription": "Counts Software Prefetches that accounts for responses from snoop request hit with data forwarded from it Far(not in the same quadrant as the request)-other tile L2 in E/F/M state. Valid only in SNC4 Cluster mode.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1710,7 +1710,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Software Prefetches that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts Software Prefetches that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1773,7 +1773,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING", "MSRIndex": "0x1a6", @@ -1818,7 +1818,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for reponses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that accounts for responses from snoop request hit with data forwarded from its Near-other tile L2 in E/F/M state", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE", "MSRIndex": "0x1a6,0x1a7", @@ -1881,7 +1881,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.", + "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING", "MSRIndex": "0x1a6", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json index 1b803fa38641..3dc532107ead 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json @@ -254,14 +254,14 @@ "UMask": "0x80" }, { - "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address overlaps with a store whose data is not ready", + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address overlaps with a store whose data is not ready", "EventCode": "0x03", "EventName": "RECYCLEQ.LD_BLOCK_STD_NOTREADY", "SampleAfterValue": "200003", "UMask": "0x2" }, { - "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store", + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with a store", "Data_LA": "1", "EventCode": "0x03", "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD", @@ -270,7 +270,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of occurences a retired load that is a cache line split. Each split should be counted only once.", + "BriefDescription": "Counts the number of occurrences a retired load that is a cache line split. Each split should be counted only once.", "Data_LA": "1", "EventCode": "0x03", "EventName": "RECYCLEQ.LD_SPLITS", @@ -293,7 +293,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Counts the number of occurences a retired store that is a cache line split. Each split should be counted only once.", + "BriefDescription": "Counts the number of occurrences a retired store that is a cache line split. Each split should be counted only once.", "EventCode": "0x03", "EventName": "RECYCLEQ.ST_SPLITS", "PublicDescription": "This event counts the number of retired store that experienced a cache line boundary split(Precise Event). Note that each spilt should be counted only once.", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json index 3abd9c3fdc48..491cb37ddab0 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json @@ -1084,7 +1084,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Cache Lookups. Counts the number of times the LLC was accessed. Writeback transactions from L2 to the LLC This includes all write transactions -- both Cachable and UC.", + "BriefDescription": "Cache Lookups. Counts the number of times the LLC was accessed. Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "EventCode": "0x37", "EventName": "UNC_H_CACHE_LINES_VICTIMIZED.E_STATE", "PerPkg": "1", @@ -1843,7 +1843,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Counts cycles source throttling is adderted - horizontal", + "BriefDescription": "Counts cycles source throttling is asserted - horizontal", "EventCode": "0xA5", "EventName": "UNC_H_FAST_ASSERTED.HORZ", "PerPkg": "1", @@ -1851,7 +1851,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Counts cycles source throttling is adderted - vertical", + "BriefDescription": "Counts cycles source throttling is asserted - vertical", "EventCode": "0xA5", "EventName": "UNC_H_FAST_ASSERTED.VERT", "PerPkg": "1", @@ -2929,7 +2929,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Cache Lookups. Counts the number of times the LLC was accessed. Writeback transactions from L2 to the LLC This includes all write transactions -- both Cachable and UC.", + "BriefDescription": "Cache Lookups. Counts the number of times the LLC was accessed. Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "EventCode": "0x34", "EventName": "UNC_H_SF_LOOKUP.WRITE", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index afe811f154d7..41bd13baa265 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -17,7 +17,7 @@ GenuineIntel-6-6[AC],v1.18,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core GenuineIntel-6-2D,v22,jaketown,core -GenuineIntel-6-(57|85),v9,knightslanding,core +GenuineIntel-6-(57|85),v10,knightslanding,core GenuineIntel-6-A[AC],v1.00,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core -- GitLab From 4507f603ffd21598f93d55ffb592bbaa27f2356e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:22 -0800 Subject: [PATCH 0026/5631] perf vendor events intel: Refresh sandybridge events Update the sandybridge events from 17 to 18. Generation was done using https://github.com/intel/perfmon. Notable changes are improved event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, and the smi_cost metric group is added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-26-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/sandybridge/cache.json | 8 +- .../arch/x86/sandybridge/floating-point.json | 2 +- .../arch/x86/sandybridge/frontend.json | 12 +- .../arch/x86/sandybridge/pipeline.json | 2 +- .../arch/x86/sandybridge/snb-metrics.json | 601 ++++++++++-------- 6 files changed, 344 insertions(+), 283 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 41bd13baa265..02715cbe4fd8 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -21,7 +21,7 @@ GenuineIntel-6-(57|85),v10,knightslanding,core GenuineIntel-6-A[AC],v1.00,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core -GenuineIntel-6-2A,v17,sandybridge,core +GenuineIntel-6-2A,v18,sandybridge,core GenuineIntel-6-(8F|CF),v1.09,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v14,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v53,skylake,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json index 65696ea2a581..4e5572ee7dfe 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json @@ -37,7 +37,7 @@ "UMask": "0x5" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -45,7 +45,7 @@ "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles.", + "BriefDescription": "L1D miss outstanding duration in cycles.", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "SampleAfterValue": "2000003", @@ -493,7 +493,7 @@ "UMask": "0x8" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests.", + "BriefDescription": "Cacheable and noncacheable code read requests.", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "SampleAfterValue": "100003", @@ -898,7 +898,7 @@ "UMask": "0x1" }, { - "BriefDescription": "COREWB & ANY_RESPONSE", + "BriefDescription": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json index 8c2a246adef9..79e8f403c426 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json @@ -64,7 +64,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULsand IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", + "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s.", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json index 69ab8d215f84..700716b42f1a 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json @@ -134,7 +134,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", @@ -143,7 +143,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -151,7 +151,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -160,14 +160,14 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "SampleAfterValue": "2000003", @@ -183,7 +183,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json index 53ab5993e8b0..54454e5e262c 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json @@ -509,7 +509,7 @@ "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.", "SampleAfterValue": "100003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index a7b3c835b03d..4a99fe515f4b 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -1,449 +1,510 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", "MetricExpr": "1 - (tma_frontend_bound + tma_bad_speculation + tma_retiring)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "RESOURCE_STALLS.SB / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "12 * (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.FPU_DIV_ACTIVE / CORE_CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", + "MetricExpr": "ARITH.FPU_DIV_ACTIVE / tma_info_core_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_UOPS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if IPC > 1.8 else (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@ - RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else RESOURCE_STALLS.SB)) - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / CLKS", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "(1 - MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS)) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "(7 * DTLB_LOAD_MISSES.STLB_HIT + DTLB_LOAD_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_UOPS_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * min(CPU_CLK_UNHALTED.THREAD, IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, - { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" - }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE) / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", "MetricExpr": "(FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) / UOPS_DISPATCHED.THREAD", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_512b, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", "MetricExpr": "tma_microcode_sequencer", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" + }, + { + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", + "MetricExpr": "1 / tma_info_ipc", "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_mem_bandwidth" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_lcp" }, { "BriefDescription": "The ratio of Executed- by Issued-Uops", "MetricExpr": "UOPS_DISPATCHED.THREAD / UOPS_ISSUED.ANY", "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", + "MetricName": "tma_info_execute_per_issue", "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, - { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" - }, { "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / CORE_CLKS", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / tma_info_core_clks", "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "MetricName": "tma_info_flopc" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", "MetricExpr": "UOPS_DISPATCHED.THREAD / (cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)", "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * (FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE) + 8 * SIMD_FP_256.PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "MEM_Parallel_Requests", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Request_Latency" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "(12 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: ITLB_MISSES.WALK_COMPLETED", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricConstraint": "NO_GROUP_EVENTS_SMT", + "MetricExpr": "MEM_LOAD_UOPS_RETIRED.LLC_HIT / (MEM_LOAD_UOPS_RETIRED.LLC_HIT + 7 * MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS) * CYCLE_ACTIVITY.STALLS_L2_PENDING / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_UOPS_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=6@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_info_dram_bw_use", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: ", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING) + RESOURCE_STALLS.SB) / (min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.CYCLES_NO_DISPATCH) + cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=1@ - (cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=3@ if tma_info_ipc > 1.8 else cpu@UOPS_DISPATCHED.THREAD\\,cmask\\=2@) - (RS_EVENTS.EMPTY_CYCLES if tma_fetch_latency > 0.1 else 0) + RESOURCE_STALLS.SB - RESOURCE_STALLS.SB - min(CPU_CLK_UNHALTED.THREAD, CYCLE_ACTIVITY.STALLS_L1D_PENDING)) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "RESOURCE_STALLS.SB / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_UOPS_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS * FP_COMP_OPS_EXE.X87 / UOPS_DISPATCHED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" } ] -- GitLab From aa2050030d65777596498256acd5f1584421e33a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:23 -0800 Subject: [PATCH 0027/5631] perf vendor events intel: Refresh sapphirerapids events Update the sapphirerapids events from 1.09 to 1.11. Generation was done using https://github.com/intel/perfmon. Notable changes are new events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-27-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/sapphirerapids/cache.json | 24 +- .../x86/sapphirerapids/floating-point.json | 32 + .../arch/x86/sapphirerapids/frontend.json | 8 + .../arch/x86/sapphirerapids/pipeline.json | 19 +- .../arch/x86/sapphirerapids/spr-metrics.json | 2283 +++++++++-------- .../arch/x86/sapphirerapids/uncore-other.json | 60 + 7 files changed, 1304 insertions(+), 1124 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 02715cbe4fd8..1f611a7dbdda 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -22,7 +22,7 @@ GenuineIntel-6-A[AC],v1.00,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v18,sandybridge,core -GenuineIntel-6-(8F|CF),v1.09,sapphirerapids,core +GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v14,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v53,skylake,core GenuineIntel-6-55-[01234],v1.28,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json index 92a605ecac6e..9606e76b98d6 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json @@ -97,18 +97,18 @@ "UMask": "0x4" }, { - "BriefDescription": "All accesses to L2 cache[This event is alias to L2_RQSTS.REFERENCES]", + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]", "EventCode": "0x24", "EventName": "L2_REQUEST.ALL", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses.[This event is alias to L2_RQSTS.REFERENCES]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", "SampleAfterValue": "200003", "UMask": "0xff" }, { - "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_RQSTS.MISS]", + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_RQSTS.MISS]", "EventCode": "0x24", "EventName": "L2_REQUEST.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses.[This event is alias to L2_RQSTS.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, @@ -199,18 +199,18 @@ "UMask": "0x30" }, { - "BriefDescription": "Read requests with true-miss in L2 cache.[This event is alias to L2_REQUEST.MISS]", + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_REQUEST.MISS]", "EventCode": "0x24", "EventName": "L2_RQSTS.MISS", - "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses.[This event is alias to L2_REQUEST.MISS]", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", "SampleAfterValue": "200003", "UMask": "0x3f" }, { - "BriefDescription": "All accesses to L2 cache[This event is alias to L2_REQUEST.ALL]", + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]", "EventCode": "0x24", "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses.[This event is alias to L2_REQUEST.ALL]", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", "SampleAfterValue": "200003", "UMask": "0xff" }, @@ -863,6 +863,14 @@ "SampleAfterValue": "1000003", "UMask": "0x1" }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", "EventCode": "0x40", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json index 01baea3df562..4a9d211e9d4f 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/floating-point.json @@ -75,6 +75,14 @@ "SampleAfterValue": "100003", "UMask": "0x20" }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -91,6 +99,22 @@ "SampleAfterValue": "100003", "UMask": "0x80" }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -107,6 +131,14 @@ "SampleAfterValue": "100003", "UMask": "0x2" }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0xfc" + }, { "BriefDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", "EventCode": "0xcf", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json index 2c7c617f27ed..860a415e5e79 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -1,4 +1,12 @@ [ + { + "BriefDescription": "Clears due to Unknown Branches.", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, { "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "EventCode": "0x87", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json index ceb14181ebc8..40e52357ade1 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -1,15 +1,17 @@ [ { - "BriefDescription": "AMX_OPS_RETIRED.BF16", + "BriefDescription": "AMX retired arithmetic BF16 operations.", "EventCode": "0xce", "EventName": "AMX_OPS_RETIRED.BF16", + "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4", "SampleAfterValue": "1000003", "UMask": "0x2" }, { - "BriefDescription": "AMX_OPS_RETIRED.INT8", + "BriefDescription": "AMX retired arithmetic integer 8-bit operations.", "EventCode": "0xce", "EventName": "AMX_OPS_RETIRED.INT8", + "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.", "SampleAfterValue": "1000003", "UMask": "0x1" }, @@ -461,12 +463,23 @@ "UMask": "0x1" }, { - "BriefDescription": "INST_RETIRED.REP_ITERATION", + "BriefDescription": "Iterations of Repeat string retired instructions.", "EventCode": "0xc0", "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", "SampleAfterValue": "2000003", "UMask": "0x8" }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0xad", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index ce18fc458e37..149cc4c07fb5 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -1,1616 +1,1675 @@ [ { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" - }, - { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" + "BriefDescription": "C1 residency percent per core", + "MetricExpr": "cstate_core@c1\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C1_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "This metric estimates fraction of cycles where the Advanced Matrix Extensions (AMX) execution engine was busy with tile (arithmetic) operations", + "MetricExpr": "EXE.AMX_BUSY / tma_info_core_clks", + "MetricGroup": "Compute;HPC;Server;TopdownL5;tma_L5_group;tma_ports_utilized_0_group", + "MetricName": "tma_amx_busy", + "MetricThreshold": "tma_amx_busy > 0.5 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * cpu@ASSISTS.ANY\\,umask\\=0x1B@ / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists.", + "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / tma_info_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_avx_assists", + "MetricThreshold": "tma_avx_assists > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;tma_L1_group", - "MetricName": "Slots_Utilization" + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources. Sample with: FRONTEND_RETIRED.MS_FLOWS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - tma_branch_mispredicts / tma_bad_speculation) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(76 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 75.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "75.5 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIV_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.VECTOR))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "80 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "max(0, tma_heavy_operations - tma_microcode_sequencer)", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.BF16\\,cmask\\=1@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;HPC;Pipeline;Server;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_fp_amx", + "MetricThreshold": "tma_fp_amx > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine). Refer to AMX_Busy and GFLOPs metrics for actual AMX utilization and FP performance, resp.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.BF16", - "MetricGroup": "Flops;FpVector;InsType;Server", - "MetricName": "IpArith_AMX_F16", - "PublicDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector + tma_fp_amx", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.INT8", - "MetricGroup": "InsType;IntVector;Server", - "MetricName": "IpArith_AMX_Int8", - "PublicDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", + "MetricExpr": "30 * ASSISTS.FP / tma_info_slots", + "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_fp_assists", + "MetricThreshold": "tma_fp_assists > 0.1", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called Denormals).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ + FP_ARITH_INST_RETIRED2.VECTOR) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * SLOTS / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", - "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Strings_Cycles" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@ASSISTS.ANY\\,umask\\=0x1B@", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "IpAssist" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.MACRO_FUSED / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" - }, - { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" - }, - { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" - }, - { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" - }, - { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" - }, - { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "Other_Branches" - }, - { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" - }, - { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" - }, - { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" - }, - { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" - }, - { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" - }, - { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" - }, - { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" - }, - { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" - }, - { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" - }, - { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" - }, - { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_Silent_PKI" + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_NonSilent_PKI" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" - }, - { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" - }, - { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Tera Integer (matrix) Operations Per Second", - "MetricExpr": "8 * AMX_OPS_RETIRED.INT8 / 1e12 / duration_time", - "MetricGroup": "Cor;HPC;IntVector;Server", - "MetricName": "TIOPS" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 6 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_PMM_Read_Latency" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_DRAM_Read_Latency" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR_HALF + 2 * (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF) + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * (FP_ARITH_INST_RETIRED2.128B_PACKED_HALF + cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@) + 16 * (FP_ARITH_INST_RETIRED2.256B_PACKED_HALF + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) + 32 * FP_ARITH_INST_RETIRED2.512B_PACKED_HALF + 4 * AMX_OPS_RETIRED.BF16", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Read_BW" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_DISPATCHED.PORT_0 + FP_ARITH_DISPATCHED.PORT_1 + FP_ARITH_DISPATCHED.PORT_5) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Server;SoC", - "MetricName": "PMM_Write_BW" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "tma_info_flopc / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Write_BW" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "uncore_cha_0@event\\=0x1@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_DATA.STALLS / cpu@ICACHE_DATA.STALLS\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "Percentage of time spent in the active CPU power state C0", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "cpu_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_write_bw" }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + FP_ARITH_INST_RETIRED2.SCALAR + (cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ + FP_ARITH_INST_RETIRED2.VECTOR))", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.BF16", + "MetricGroup": "Flops;FpVector;InsType;Server", + "MetricName": "tma_info_iparith_amx_f16", + "MetricThreshold": "tma_info_iparith_amx_f16 < 10", + "PublicDescription": "Instructions per FP Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / AMX_OPS_RETIRED.INT8", + "MetricGroup": "InsType;IntVector;Server", + "MetricName": "tma_info_iparith_amx_int8", + "MetricThreshold": "tma_info_iparith_amx_int8 < 10", + "PublicDescription": "Instructions per Integer Arithmetic AMX operation (lower number means higher occurrence rate). Operations factored per matrices' sizes of the AMX instructions." }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per a microcode Assist invocation", + "MetricExpr": "INST_RETIRED.ANY / cpu@ASSISTS.ANY\\,umask\\=0x1B@", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_ipassist", + "MetricThreshold": "tma_info_ipassist < 100e3", + "PublicDescription": "Instructions per a microcode Assist invocation. See Assists tree node for details (lower number means higher occurrence rate)" }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA + UNC_CHA_TOR_INSERTS.IA_MISS_DRD + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF) / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_flopc", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to Intel(R) Optane(TM) Persistent Memory(PMEM) in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_to_pmem_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand data read miss (read memory access) addressed to DRAM in nano seconds", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / (UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR) * #num_packages)) * duration_time", - "MetricName": "llc_demand_data_read_miss_to_dram_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_2nd_level_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_taken", + "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_2nd_level_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_ret", + "MetricThreshold": "tma_info_ipmisp_ret < 500" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_2nd_level_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE) / (UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE + UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 13", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_CHA_CLOCKTICKS / (source_count(UNC_CHA_CLOCKTICKS) * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", - "MetricName": "upi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_RPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_PMM_WPQ_INSERTS * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Intel(R) Optane(TM) Persistent Memory(PMEM) memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_PMM_RPQ_INSERTS + UNC_M_PMM_WPQ_INSERTS) * 64 / 1e6 / duration_time", - "MetricName": "pmem_memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "(UNC_CHA_TOR_INSERTS.IO_ITOM + UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR) * 64 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_silent_pki" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS + LSD.UOPS)", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) / max(1 - (tma_frontend_bound + topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)), 0) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "(1 - topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) / max(1 - (tma_frontend_bound + topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)), 0)) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit).", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "DECODE.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l3_miss_latency" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / MEM_LOAD_COMPLETED.L1_MISS_ANY", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CPU_CLK_UNHALTED.DISTRIBUTED / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR) / uncore_cha_0@event\\=0x1@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", - "MetricName": "tma_decoder0_alone", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CPU_CLK_UNHALTED.DISTRIBUTED / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_pmm_read_latency", + "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "max(1 - (tma_frontend_bound + topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)), 0)", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_fb_full / (tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "max(0, tma_bad_speculation - topdown\\-br\\-mispredict / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound))", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_pmm_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - MEMORY_ACTIVITY.CYCLES_L1D_MISS, 0)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_other_branches" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_read_bw" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Server;SoC", + "MetricName": "tma_info_pmm_write_bw" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min((16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_slots_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "uncore_cha_0@event\\=0x1@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min(((28 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (27 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min((27 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", - "ScaleUnit": "100%" + "BriefDescription": "Estimated fraction of retirement-cycles dealing with repeat instructions", + "MetricExpr": "INST_RETIRED.REP_ITERATION / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_strings_cycles", + "MetricThreshold": "tma_info_strings_cycles > 0.1" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min((12 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Tera Integer (matrix) Operations Per Second", + "MetricExpr": "8 * AMX_OPS_RETIRED.INT8 / 1e12 / duration_time", + "MetricGroup": "Cor;HPC;IntVector;Server", + "MetricName": "tma_info_tiops" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min(MEMORY_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD - tma_pmm_bound, 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", - "ScaleUnit": "100%" + "BriefDescription": "Cross-socket Ultra Path Interconnect (UPI) data transmit bandwidth for data only [MB / sec]", + "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 64 / 9 / 1e6", + "MetricGroup": "Server;SoC", + "MetricName": "tma_info_upi_data_transmit_bw" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", - "MetricExpr": "INT_MISC.MBA_STALLS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", - "MetricName": "tma_mba_stalls", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 9" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine)", + "MetricExpr": "cpu@AMX_OPS_RETIRED.INT8\\,cmask\\=1@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;HPC;IntVector;Pipeline;Server;TopdownL4;tma_L4_group;tma_int_operations_group", + "MetricName": "tma_int_amx", + "MetricThreshold": "tma_int_amx > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine). Refer to AMX_Busy and TIOPs metrics for actual AMX utilization and Int performance, resp.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min((66.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 12 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", + "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b + tma_shuffles + tma_int_amx", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_int_operations", + "MetricThreshold": "tma_int_operations > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min((131 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 12 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_128b", + "MetricThreshold": "tma_int_vector_128b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min(((120 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 12 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (120 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 12 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired", + "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group;tma_issue2P", + "MetricName": "tma_int_vector_256b", + "MetricThreshold": "tma_int_vector_256b > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", + "PublicDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "min(((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0), 1)", - "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_pmm_bound", - "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module. ", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_TAG.STALLS / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((EXE_ACTIVITY.BOUND_ON_LOADS - MEMORY_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L1D_MISS - MEMORY_ACTIVITY.STALLS_L2_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min(28 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L2_MISS - MEMORY_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "33 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "min(9 * OCR.STREAMING_WR.ANY_RESPONSE / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_streaming_stores", - "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck.", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "DECODE.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CPU_CLK_UNHALTED.DISTRIBUTED, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3_10", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) + 0 * slots", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "71 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / CPU_CLK_UNHALTED.THREAD) + 0 * slots", - "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CPU_CLK_UNHALTED.THREAD + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance.", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to memory bandwidth Allocation feature (RDT's memory bandwidth throttling).", + "MetricExpr": "INT_MISC.MBA_STALLS / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;Server;TopdownL5;tma_L5_group;tma_mem_bandwidth_group", + "MetricName": "tma_mba_stalls", + "MetricThreshold": "tma_mba_stalls > 0.1 & (tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions.", - "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", - "MetricExpr": "min(13 * MISC2_RETIRED.LFENCE / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", - "MetricName": "tma_memory_fence", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "min(160 * ASSISTS.SSE_AVX_MIX / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the Advanced Matrix Extensions (AMX) execution engine was busy with tile (arithmetic) operations", - "MetricExpr": "EXE.AMX_BUSY / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "Compute;HPC;Server;TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_amx_busy", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to LFENCE Instructions.", + "MetricExpr": "13 * MISC2_RETIRED.LFENCE / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_memory_fence", + "MetricThreshold": "tma_memory_fence > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_UOP_RETIRED.ANY / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.MS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: UOPS_RETIRED.MS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "tma_branch_mispredicts / tma_bad_speculation * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5_11 + UOPS_DISPATCHED.PORT_6) / (5 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "160 * ASSISTS.SSE_AVX_MIX / tma_info_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * cpu@UOPS_RETIRED.MS\\,cmask\\=1\\,edge@ / (tma_retiring * tma_info_slots / UOPS_ISSUED.ANY) / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: FRONTEND_RETIRED.MS_FLOWS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3_10 / (3 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CPU_CLK_UNHALTED.DISTRIBUTED)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", + "MetricExpr": "99 * ASSISTS.PAGE_FAULT / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", + "MetricName": "tma_page_faults", + "MetricThreshold": "tma_page_faults > 0.05", + "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) + 0 * slots", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", + "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_pmm_bound", + "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a. IXP) memory by loads, PMM stands for Persistent Memory Module.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + tma_fp_scalar + tma_fp_vector + tma_fp_amx", - "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + 0 * slots", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + FP_ARITH_INST_RETIRED2.SCALAR) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.VECTOR) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / tma_info_clks if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.128B_PACKED_HALF) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.256B_PACKED_HALF) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE + FP_ARITH_INST_RETIRED2.512B_PACKED_HALF) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots), 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_int_vector_128b, tma_int_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine)", - "MetricExpr": "cpu@AMX_OPS_RETIRED.BF16\\,cmask\\=0x1@ / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;Flops;HPC;Pipeline;Server;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_amx", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) matrix uops fraction the CPU has retired (aggregated across all supported FP datatypes in AMX engine). Refer to AMX_Busy and GFLOPs metrics for actual AMX utilization and FP performance, resp.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_int_vector_128b + tma_int_vector_256b + tma_shuffles", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_int_operations", - "PublicDescription": "This metric represents overall Integer (Int) select operations fraction the CPU has executed (retired). Vector/Matrix Int operations and shuffles are counted. Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricExpr": "(135.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 135.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents 128-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", - "MetricExpr": "(INT_VEC_RETIRED.ADD_128 + INT_VEC_RETIRED.VNNI_128) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", - "MetricName": "tma_int_vector_128b", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "149 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents 256-bit vector Integer ADD/SUB/SAD or VNNI (Vector Neural Network Instructions) uops fraction the CPU has retired.", - "MetricExpr": "(INT_VEC_RETIRED.ADD_256 + INT_VEC_RETIRED.MUL_256 + INT_VEC_RETIRED.VNNI_256) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;IntVector;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", - "MetricName": "tma_int_vector_256b", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine)", - "MetricExpr": "cpu@AMX_OPS_RETIRED.INT8\\,cmask\\=0x1@ / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Compute;HPC;IntVector;Pipeline;Server;TopdownL4;tma_L4_group;tma_int_operations_group", - "MetricName": "tma_int_amx", - "PublicDescription": "This metric approximates arithmetic Integer (Int) matrix uops fraction the CPU has retired (aggregated across all supported Int datatypes in AMX engine). Refer to AMX_Busy and TIOPs metrics for actual AMX utilization and Int performance, resp.", + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Shuffle (cross \"vector lane\" data transfers) uops fraction the CPU has retired.", - "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", + "MetricExpr": "INT_VEC_RETIRED.SHUFFLES / (tma_retiring * tma_info_slots)", "MetricGroup": "HPC;Pipeline;TopdownL4;tma_L4_group;tma_int_operations_group", "MetricName": "tma_shuffles", + "MetricThreshold": "tma_shuffles > 0.1 & (tma_int_operations > 0.1 & tma_light_operations > 0.6)", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) * MEM_UOP_RETIRED.ANY / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_memory_operations", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "CPU_CLK_UNHALTED.PAUSE / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: CPU_CLK_UNHALTED.PAUSE_INST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) * INST_RETIRED.MACRO_FUSED / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fused_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) * (BR_INST_RETIRED.ALL_BRANCHES - INST_RETIRED.MACRO_FUSED) / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_non_fused_branches", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) * INST_RETIRED.NOP / (topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * slots)", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body.", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(XQ.FULL_CYCLES + L1D_PEND_MISS.L2_STALLS) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, max(0, topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) - (tma_fp_arith + tma_int_operations + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_other_light_ops", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * slots", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "topdown\\-heavy\\-ops / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(MEM_STORE_RETIRED.L2_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.MS / slots", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * cpu@ASSISTS.ANY\\,umask\\=0x1B@ / slots, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults", - "MetricExpr": "99 * ASSISTS.PAGE_FAULT / slots", - "MetricGroup": "TopdownL5;tma_L5_group;tma_assists_group", - "MetricName": "tma_page_faults", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Page Faults. A Page Fault may apply on first application access to a memory page. Note operating system handling of page faults accounts for the majority of its cost.", + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists", - "MetricExpr": "30 * ASSISTS.FP / slots", - "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", - "MetricName": "tma_fp_assists", - "PublicDescription": "This metric roughly estimates fraction of slots the CPU retired uops as a result of handing Floating Point (FP) Assists. FP Assist may apply when working with very small floating point values (so-called denormals).", + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops as a result of handing SSE to AVX* or AVX* to SSE transition Assists. ", - "MetricExpr": "63 * ASSISTS.SSE_AVX_MIX / slots", - "MetricGroup": "HPC;TopdownL5;tma_L5_group;tma_assists_group", - "MetricName": "tma_avx_assists", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "INT_MISC.UNKNOWN_BRANCH_CYCLES / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: FRONTEND_RETIRED.UNKNOWN_BRANCH", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { - "BriefDescription": "C1 residency percent per core", - "MetricExpr": "cstate_core@c1\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C1_Core_Residency", + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", - "ScaleUnit": "100%" + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json index fd253e3276df..11c037e8291d 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json @@ -2832,6 +2832,16 @@ "UMask": "0x80", "Unit": "IIO" }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x4", + "Unit": "IIO" + }, { "BriefDescription": "Read request for 4 bytes made by IIO Part0 to Memory", "EventCode": "0x83", @@ -2920,6 +2930,16 @@ "UMask": "0x4", "Unit": "IIO" }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x1", + "Unit": "IIO" + }, { "BriefDescription": "Write request of 4 bytes made by IIO Part0 to Memory", "EventCode": "0x83", @@ -4038,6 +4058,46 @@ "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", "Unit": "M3UPI" }, + { + "BriefDescription": "All CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.ALL", + "PerPkg": "1", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS commands issued (regular and underfill)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0xcf", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Regular read CAS commands issued (does not include underfills)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_REG", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill read CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0xf0", + "Unit": "MCHBM" + }, { "BriefDescription": "UPI Clockticks", "EventCode": "0x01", -- GitLab From c3fdd79d6161559b2b3dd111e593842e65ccbd8b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:24 -0800 Subject: [PATCH 0028/5631] perf vendor events intel: Refresh silvermont events Update the silvermont events from 14 to 15. Generation was done using https://github.com/intel/perfmon. The most notable change is in corrections to event descriptions. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-28-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- tools/perf/pmu-events/arch/x86/silvermont/frontend.json | 2 +- tools/perf/pmu-events/arch/x86/silvermont/pipeline.json | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 1f611a7dbdda..d1d40d0f2b2c 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -23,7 +23,7 @@ GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v18,sandybridge,core GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core -GenuineIntel-6-(37|4A|4C|4D|5A),v14,silvermont,core +GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v53,skylake,core GenuineIntel-6-55-[01234],v1.28,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core diff --git a/tools/perf/pmu-events/arch/x86/silvermont/frontend.json b/tools/perf/pmu-events/arch/x86/silvermont/frontend.json index c35da10f7133..cd6ed3f59e26 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/frontend.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/frontend.json @@ -11,7 +11,7 @@ "BriefDescription": "Counts the number of JCC baclears", "EventCode": "0xE6", "EventName": "BACLEARS.COND", - "PublicDescription": "The BACLEARS event counts the number of times the front end is resteered, mainly when the Branch Prediction Unit cannot provide a correct prediction and this is corrected by the Branch Address Calculator at the front end. The BACLEARS.COND event counts the number of JCC (Jump on Condtional Code) baclears.", + "PublicDescription": "The BACLEARS event counts the number of times the front end is resteered, mainly when the Branch Prediction Unit cannot provide a correct prediction and this is corrected by the Branch Address Calculator at the front end. The BACLEARS.COND event counts the number of JCC (Jump on Conditional Code) baclears.", "SampleAfterValue": "200003", "UMask": "0x10" }, diff --git a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json index 59f6116a7eae..2d4214bf9e39 100644 --- a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json @@ -228,7 +228,7 @@ "BriefDescription": "Counts the number of cycles when no uops are allocated, the IQ is empty, and no other condition is blocking allocation.", "EventCode": "0xCA", "EventName": "NO_ALLOC_CYCLES.NOT_DELIVERED", - "PublicDescription": "The NO_ALLOC_CYCLES.NOT_DELIVERED event is used to measure front-end inefficiencies, i.e. when front-end of the machine is not delivering micro-ops to the back-end and the back-end is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into micro-ops (uops) in machine understandable format and putting them into a micro-op queue to be consumed by back end. The back-end then takes these micro-ops, allocates the required resources. When all resources are ready, micro-ops are executed. If the back-end is not ready to accept micro-ops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more UOPS. This event counts the cycles only when back-end is requesting more uops and front-end is not able to provide them. Some examples of conditions that cause front-end efficiencies are: Icache misses, ITLB misses, and decoder restrictions that limit the the front-end bandwidth.", + "PublicDescription": "The NO_ALLOC_CYCLES.NOT_DELIVERED event is used to measure front-end inefficiencies, i.e. when front-end of the machine is not delivering micro-ops to the back-end and the back-end is not stalled. This event can be used to identify if the machine is truly front-end bound. When this event occurs, it is an indication that the front-end of the machine is operating at less than its theoretical peak performance. Background: We can think of the processor pipeline as being divided into 2 broader parts: Front-end and Back-end. Front-end is responsible for fetching the instruction, decoding into micro-ops (uops) in machine understandable format and putting them into a micro-op queue to be consumed by back end. The back-end then takes these micro-ops, allocates the required resources. When all resources are ready, micro-ops are executed. If the back-end is not ready to accept micro-ops from the front-end, then we do not want to count these as front-end bottlenecks. However, whenever we have bottlenecks in the back-end, we will have allocation unit stalls and eventually forcing the front-end to wait until the back-end is ready to receive more UOPS. This event counts the cycles only when back-end is requesting more uops and front-end is not able to provide them. Some examples of conditions that cause front-end efficiencies are: Icache misses, ITLB misses, and decoder restrictions that limit the front-end bandwidth.", "SampleAfterValue": "200003", "UMask": "0x50" }, -- GitLab From 9d9675bb411b08bc6c5bb2f399ee497f5880b551 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:25 -0800 Subject: [PATCH 0029/5631] perf vendor events intel: Refresh skylake events Update the skylake events from 53 to 54. Generation was done using https://github.com/intel/perfmon. Notable changes are updated events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_ and MetricThreshold expressions are added, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-29-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/skylake/cache.json | 25 +- .../pmu-events/arch/x86/skylake/frontend.json | 8 +- .../pmu-events/arch/x86/skylake/other.json | 1 + .../pmu-events/arch/x86/skylake/pipeline.json | 16 + .../arch/x86/skylake/skl-metrics.json | 1877 ++++++++++------- .../arch/x86/skylake/uncore-other.json | 1 + 7 files changed, 1115 insertions(+), 815 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d1d40d0f2b2c..22aa63f90f89 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -24,7 +24,7 @@ GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v18,sandybridge,core GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core -GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v53,skylake,core +GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v54,skylake,core GenuineIntel-6-55-[01234],v1.28,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core GenuineIntel-6-8[CD],v1.08,tigerlake,core diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 1538ddb5752f..0080ac27b899 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -72,6 +72,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", + "Deprecated": "1", "EventCode": "0xF2", "EventName": "L2_LINES_OUT.USELESS_PREF", "SampleAfterValue": "200003", @@ -232,20 +233,22 @@ "UMask": "0x4f" }, { - "BriefDescription": "All retired load instructions.", + "BriefDescription": "Retired load instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "All retired store instructions.", + "BriefDescription": "Retired store instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_STORES", "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "2000003", "UMask": "0x82" }, @@ -443,7 +446,7 @@ "UMask": "0x80" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", @@ -551,15 +554,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all demand code readshave any response type.", + "BriefDescription": "Counts all demand code reads have any response type.", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -946,7 +941,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data readshave any response type.", + "BriefDescription": "Counts demand data reads have any response type.", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1333,7 +1328,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs)have any response type.", + "BriefDescription": "Counts all demand data writes (RFOs) have any response type.", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -1720,7 +1715,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts any other requestshave any response type.", + "BriefDescription": "Counts any other requests have any response type.", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json index 13ccf50db43d..04f08e4d2402 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json @@ -322,7 +322,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", @@ -331,7 +331,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -340,7 +340,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", @@ -358,7 +358,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", diff --git a/tools/perf/pmu-events/arch/x86/skylake/other.json b/tools/perf/pmu-events/arch/x86/skylake/other.json index 9f3a9dffb807..d75d53279b4e 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/other.json +++ b/tools/perf/pmu-events/arch/x86/skylake/other.json @@ -8,6 +8,7 @@ "UMask": "0x1" }, { + "BriefDescription": "MEMORY_DISAMBIGUATION.HISTORY_RESET", "EventCode": "0x09", "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index cf35a535c2f6..2c827d806554 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -93,6 +93,22 @@ "SampleAfterValue": "400009", "UMask": "0x10" }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "PublicDescription": "This event counts both taken and not taken speculative and retired mispredicted branch instructions.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "All mispredicted macro branch instructions retired.", "EventCode": "0xC5", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 972d3744c2c8..a6d212b349f5 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1,1197 +1,1484 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CLKS + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / CLKS", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: BACLEARS.ANY", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", - "ScaleUnit": "100%" + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_decoder0_alone", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(18.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "16.5 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "22 * tma_info_average_frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(18.5 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM + 16.5 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "16.5 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "6.5 * Average_Frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / CLKS + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS - tma_l2_bound", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "22 * Average_Frequency * OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CLKS if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CLKS)", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / CLKS", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "CLKS * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED_PORT.PORT_0", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_1", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED_PORT.PORT_6", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_2", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_2", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads) Sample with: UOPS_DISPATCHED_PORT.PORT_3", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_load_op_utilization_group", - "MetricName": "tma_port_3", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "tma_port_4", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data) Sample with: UOPS_DISPATCHED_PORT.PORT_4", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_4", - "ScaleUnit": "100%" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address) Sample with: UOPS_DISPATCHED_PORT.PORT_7", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_store_op_utilization_group", - "MetricName": "tma_port_7", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - tma_heavy_operations", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_memory_operations", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fused_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_non_fused_branches", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0x3c@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_other_light_ops", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" + }, + { + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" + }, + { + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" + }, + { + "BriefDescription": "Average number of parallel requests to external memory", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_parallel_requests", + "PublicDescription": "Average number of parallel requests to external memory. Accounts for all requests" + }, + { + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" + }, + { + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" + }, + { + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" + }, + { + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" + }, + { + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" + }, + { + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "MetricName": "tma_info_retire" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "6.5 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (9 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", + "MetricName": "tma_port_3", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", + "MetricExpr": "tma_store_op_utilization", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", + "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_ARB_TRK_REQUESTS.ALL + UNC_ARB_COH_TRK_REQUESTS.ALL) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", - "MetricExpr": "MEM_Parallel_Requests", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Request_Latency" + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / UNC_ARB_TRK_REQUESTS.ALL", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_REQUESTS.DATA_READ) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.DATA_READ / UNC_ARB_TRK_OCCUPANCY.DATA_READ@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "UNC_CLOCK.SOCKET", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 9 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json index e6d4cd625597..ef804df3f41e 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json @@ -33,6 +33,7 @@ "Unit": "ARB" }, { + "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.ALL", "PerPkg": "1", -- GitLab From 100ee7c3de193df9e6fd54f9190aae73b1b43ee8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:26 -0800 Subject: [PATCH 0030/5631] perf vendor events intel: Refresh skylakex metrics Update the skylakex events from 1.28 to 1.29 and metrics to TMA version 4.5. Generation was done using https://github.com/intel/perfmon. Notable changes are TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, "Sample with" documentation is added to many TMA metrics, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-30-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/skylakex/cache.json | 8 +- .../arch/x86/skylakex/frontend.json | 8 +- .../arch/x86/skylakex/pipeline.json | 16 + .../arch/x86/skylakex/skx-metrics.json | 2097 +++++++++-------- .../arch/x86/skylakex/uncore-memory.json | 2 +- .../arch/x86/skylakex/uncore-other.json | 96 +- .../arch/x86/skylakex/uncore-power.json | 6 +- 8 files changed, 1167 insertions(+), 1068 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 22aa63f90f89..07f0b4758a83 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -25,7 +25,7 @@ GenuineIntel-6-2A,v18,sandybridge,core GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v54,skylake,core -GenuineIntel-6-55-[01234],v1.28,skylakex,core +GenuineIntel-6-55-[01234],v1.29,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core GenuineIntel-6-8[CD],v1.08,tigerlake,core GenuineIntel-6-2C,v3,westmereep-dp,core diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index 92da692795e7..d28d8822a51a 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -234,20 +234,22 @@ "UMask": "0x4f" }, { - "BriefDescription": "All retired load instructions.", + "BriefDescription": "Retired load instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "All retired store instructions.", + "BriefDescription": "Retired store instructions.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_INST_RETIRED.ALL_STORES", "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "2000003", "UMask": "0x82" }, @@ -484,7 +486,7 @@ "UMask": "0x80" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json index 13ccf50db43d..04f08e4d2402 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -322,7 +322,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", @@ -331,7 +331,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -340,7 +340,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", @@ -358,7 +358,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index 64e1fe351333..0f06e314fe36 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -93,6 +93,22 @@ "SampleAfterValue": "400009", "UMask": "0x10" }, + { + "BriefDescription": "Speculative and retired mispredicted macro conditional branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.ALL_BRANCHES", + "PublicDescription": "This event counts both taken and not taken speculative and retired mispredicted branch instructions.", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "All mispredicted macro branch instructions retired.", "EventCode": "0xC5", diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 1f8d60cce3ce..fa2f7f126a30 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1,1497 +1,1570 @@ [ { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" - }, - { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" - }, - { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" - }, - { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" - }, - { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" - }, - { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" - }, - { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" - }, - { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" - }, - { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "cstate_core@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "4 * CORE_CLKS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else CLKS))", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / tma_info_slots", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: OTHER_ASSISTS.ANY", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", + "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", + "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", + "MetricName": "tma_branch_mispredicts", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 44 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS_PS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_backend_bound - tma_memory_bound", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "44 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT_PS. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(110 * tma_info_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * tma_info_average_frequency * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM_PS;OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@ / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", + "ScaleUnit": "100%" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "tma_frontend_bound - tma_fetch_latency", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", + "ScaleUnit": "100%" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", - "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", - "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", + "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fused_instructions", + "MetricThreshold": "tma_fused_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "ScaleUnit": "100%" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / tma_info_slots", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@) / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.CONDITIONAL + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * CORE_CLKS)", - "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.NOT_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "(BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", - "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_Silent_PKI" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_clks))", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", - "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / Instructions", - "MetricGroup": "L2Evicts;Mem;Server", - "MetricName": "L2_Evictions_NonSilent_PKI" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 4 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / DSB2MITE_SWITCHES.COUNT", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License0_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License1_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / CORE_CLKS if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / CORE_CLKS)", - "MetricGroup": "Power", - "MetricName": "Power_License2_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (Socket_CLKS / duration_time)", - "MetricGroup": "Mem;MemoryLat;SoC", - "MetricName": "MEM_Read_Latency" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@ + 2", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches", - "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", - "MetricGroup": "Mem;MemoryBW;SoC", - "MetricName": "MEM_Parallel_Reads" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches", - "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", - "MetricGroup": "Mem;MemoryLat;Server;SoC", - "MetricName": "MEM_DRAM_Read_Latency" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", - "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Write_BW" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { "BriefDescription": "Average IO (network or disk) Bandwidth Use for Reads [GB / sec]", "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3) * 4 / 1e9 / duration_time", "MetricGroup": "IoBW;Mem;Server;SoC", - "MetricName": "IO_Read_BW" + "MetricName": "tma_info_io_read_bw" }, { - "BriefDescription": "Socket actual clocks when any core is active on that socket", - "MetricExpr": "cha_0@event\\=0x0@", - "MetricGroup": "SoC", - "MetricName": "Socket_CLKS" + "BriefDescription": "Average IO (network or disk) Bandwidth Use for Writes [GB / sec]", + "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e9 / duration_time", + "MetricGroup": "IoBW;Mem;Server;SoC", + "MetricName": "tma_info_io_write_bw" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "Uncore frequency per die [GHZ]", - "MetricExpr": "Socket_CLKS / #num_dies / duration_time / 1e9", - "MetricGroup": "SoC", - "MetricName": "UNCORE_FREQ" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Percentage of time spent in the active CPU power state C0", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricName": "cpu_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "CPU operating frequency (in GHz)", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / duration_time", - "MetricName": "cpu_operating_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Cycles per instruction retired; indicating how much time each executed instruction took; in units of cycles.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD / INST_RETIRED.ANY", - "MetricName": "cpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "The ratio of number of completed memory load instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_LOADS / INST_RETIRED.ANY", - "MetricName": "loads_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "The ratio of number of completed memory store instructions to the total number completed instructions", - "MetricExpr": "MEM_INST_RETIRED.ALL_STORES / INST_RETIRED.ANY", - "MetricName": "stores_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Ratio of number of requests missing L1 data cache (includes data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L1D.REPLACEMENT / INST_RETIRED.ANY", - "MetricName": "l1d_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Ratio of number of demand load requests hitting in L1 data cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L1_HIT / INST_RETIRED.ANY", - "MetricName": "l1d_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Ratio of number of code read requests missing in L1 instruction cache (includes prefetches) to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.ALL_CODE_RD / INST_RETIRED.ANY", - "MetricName": "l1_i_code_read_misses_with_prefetches_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Ratio of number of completed demand load requests hitting in L2 cache to the total number of completed instructions ", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_hits_per_instr", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Ratio of number of requests missing L2 cache (includes code+data+rfo w/ prefetches) to the total number of completed instructions", - "MetricExpr": "L2_LINES_IN.ALL / INST_RETIRED.ANY", - "MetricName": "l2_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Ratio of number of completed data read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_data_read_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Ratio of number of code read request missing L2 cache to the total number of completed instructions", - "MetricExpr": "L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", - "MetricName": "l2_demand_code_mpi", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "tma_info_instructions / (UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * cpu@BR_MISP_EXEC.ALL_BRANCHES\\,umask\\=0xE4@)", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Ratio of number of data read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x12D4043300000000@ / INST_RETIRED.ANY", - "MetricName": "llc_data_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Ratio of number of code read requests missing last level core cache (includes demand w/ prefetches) to the total number of completed instructions", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x12CC023300000000@ / INST_RETIRED.ANY", - "MetricName": "llc_code_read_mpi_demand_plus_prefetch", - "ScaleUnit": "1per_instr" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043300000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043300000000@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to local memory in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043200000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_local_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 9", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Average latency of a last level cache (LLC) demand and prefetch data read miss (read memory access) addressed to remote memory in nano seconds", - "MetricExpr": "1e9 * (cha@unc_cha_tor_occupancy.ia_miss\\,config1\\=0x4043100000000@ / cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@) / (UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages)) * duration_time", - "MetricName": "llc_data_read_demand_plus_prefetch_miss_latency_for_remote_requests", - "ScaleUnit": "1ns" + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "itlb_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - (BR_INST_RETIRED.CONDITIONAL - BR_INST_RETIRED.NOT_TAKEN) - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions", - "MetricExpr": "ITLB_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "itlb_large_page_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte and 4 megabyte page sizes) caused by a code fetch to the total number of completed instructions. This implies it missed in the Instruction Translation Lookaside Buffer (ITLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M / INST_RETIRED.ANY", - "MetricName": "dtlb_2mb_large_page_load_mpi", - "PublicDescription": "Ratio of number of completed page walks (for 2 megabyte page sizes) caused by demand data loads to the total number of completed instructions. This implies it missed in the Data Translation Lookaside Buffer (DTLB) and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions", - "MetricExpr": "DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", - "MetricName": "dtlb_store_mpi", - "PublicDescription": "Ratio of number of completed page walks (for all page sizes) caused by demand data stores to the total number of completed instructions. This implies it missed in the DTLB and further levels of TLB.", - "ScaleUnit": "1per_instr" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Memory read that miss the last level cache (LLC) addressed to local DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ / (cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ + cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@)", - "MetricName": "numa_reads_addressed_to_local_dram", - "ScaleUnit": "100%" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Memory reads that miss the last level cache (LLC) addressed to remote DRAM as a percentage of total memory read accesses, does not include LLC prefetches.", - "MetricExpr": "cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@ / (cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043200000000@ + cha@unc_cha_tor_inserts.ia_miss\\,config1\\=0x4043100000000@)", - "MetricName": "numa_reads_addressed_to_remote_dram", - "ScaleUnit": "100%" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Uncore operating frequency in GHz", - "MetricExpr": "UNC_CHA_CLOCKTICKS / (#num_cores / #num_packages * #num_packages) / 1e9 / duration_time", - "MetricName": "uncore_frequency", - "ScaleUnit": "1GHz" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Intel(R) Ultra Path Interconnect (UPI) data transmit bandwidth (MB/sec)", - "MetricExpr": "UNC_UPI_TxL_FLITS.ALL_DATA * 7.111111111111111 / 1e6 / duration_time", - "MetricName": "upi_data_transmit_bw", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "DDR memory read bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.RD * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction", + "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_nonsilent_pki" }, { - "BriefDescription": "DDR memory write bandwidth (MB/sec)", - "MetricExpr": "UNC_M_CAS_COUNT.WR * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)", + "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / tma_info_instructions", + "MetricGroup": "L2Evicts;Mem;Server", + "MetricName": "tma_info_l2_evictions_silent_pki" }, { - "BriefDescription": "DDR memory bandwidth (MB/sec)", - "MetricExpr": "(UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) * 64 / 1e6 / duration_time", - "MetricName": "memory_bandwidth_total", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Bandwidth of IO reads that are initiated by end device controllers that are requesting memory from the CPU.", - "MetricExpr": "(UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3) * 4 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_writes", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Bandwidth of IO writes that are initiated by end device controllers that are writing memory to the CPU.", - "MetricExpr": "(UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2 + UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3) * 4 / 1e6 / duration_time", - "MetricName": "io_bandwidth_disk_or_network_reads", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Uops delivered from decoded instruction cache (decoded stream buffer or DSB) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_decoded_icache", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Uops delivered from legacy decode pipeline (Micro-instruction Translation Engine or MITE) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MITE_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_legacy_decode_pipeline", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "Uops delivered from microcode sequencer (MS) as a percent of total uops delivered to Instruction Decode Queue", - "MetricExpr": "IDQ.MS_UOPS / UOPS_ISSUED.ANY", - "MetricName": "percent_uops_delivered_from_microcode_sequencer", - "ScaleUnit": "100%" + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Bandwidth (MB/sec) of write requests that miss the last level cache (LLC) and go to local memory.", - "MetricExpr": "UNC_CHA_REQUESTS.WRITES_LOCAL * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_local_memory_bandwidth_write", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "Bandwidth (MB/sec) of read requests that miss the last level cache (LLC) and go to remote memory.", - "MetricExpr": "UNC_CHA_REQUESTS.READS_REMOTE * 64 / 1e6 / duration_time", - "MetricName": "llc_miss_remote_memory_bandwidth_read", - "ScaleUnit": "1MB/s" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period.", - "ScaleUnit": "100%" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses.", - "MetricExpr": "(ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "ScaleUnit": "100%" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses.", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. ", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "ScaleUnit": "100%" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. ", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit).", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]", + "MetricExpr": "1e9 * (UNC_M_RPQ_OCCUPANCY / UNC_M_RPQ_INSERTS) / imc_0@event\\=0x0@", + "MetricGroup": "Mem;MemoryLat;Server;SoC", + "MetricName": "tma_info_mem_dram_read_latency", + "PublicDescription": "Average latency of data read request to external DRAM memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD@thresh\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", - "ScaleUnit": "100%" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD / UNC_CHA_TOR_INSERTS.IA_MISS_DRD) / (tma_info_socket_clks / duration_time)", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "tma_frontend_bound - tma_fetch_latency", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=0x1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=0x2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", - "MetricName": "tma_decoder0_alone", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.ALL_DSB_CYCLES_ANY_UOPS - IDQ.ALL_DSB_CYCLES_4_UOPS) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", - "ScaleUnit": "100%" + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", + "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Mem;MemoryBW;MemoryBound", + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", - "MetricExpr": "(UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_bad_speculation", - "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", - "ScaleUnit": "100%" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "(CORE_POWER.LVL0_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "(CORE_POWER.LVL1_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license1_utilization", + "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "1 - tma_frontend_bound - (UOPS_ISSUED.ANY + 4 * (INT_MISC.RECOVERY_CYCLES_ANY / 2 if #SMT_on else INT_MISC.RECOVERY_CYCLES)) / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "(CORE_POWER.LVL2_TURBO_LICENSE / 2 / tma_info_core_clks if #SMT_on else CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks)", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license2_utilization", + "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CPU_CLK_UNHALTED.THREAD, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache.", - "ScaleUnit": "100%" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "4 * tma_info_core_clks", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(9 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / (CPU_CLK_UNHALTED.REF_XCLK_ANY / 2) if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cha_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_socket_clks" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "min(13 * LD_BLOCKS.STORE_FORWARD / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", - "ScaleUnit": "100%" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "min((12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them.", - "ScaleUnit": "100%" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. ", - "MetricExpr": "min(Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "ScaleUnit": "100%" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 6" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "Load_Miss_Real_Latency * cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@ / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=0x1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + cpu@L1D_PEND_MISS.FB_FULL\\,cmask\\=1@) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance.", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CPU_CLK_UNHALTED.THREAD", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "min(((47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + (47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "min((47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * (MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT + MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM * (1 - OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE / (OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance.", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "min((20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 3.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_l3_bound_group", + "MetricExpr": "17 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / CORE_CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "min(CYCLE_ACTIVITY.STALLS_L3_MISS / CPU_CLK_UNHALTED.THREAD + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CPU_CLK_UNHALTED.THREAD - tma_l2_bound, 1)", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance.", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=0x4@) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CPU_CLK_UNHALTED.THREAD - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", - "MetricExpr": "min((80 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_local_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance.", + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", - "MetricExpr": "min((147.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_dram", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "tma_retiring - tma_heavy_operations", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", - "MetricExpr": "min(((110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + (110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) - 20.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3))) * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", - "MetricName": "tma_remote_cache", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck.", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "min((110 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * (OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM + OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM) + 47.5 * (CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC * #SYSTEM_TSC_FREQ / 1e9 / (duration_time * 1e3 / 1e3)) * (OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE + OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE)) / CPU_CLK_UNHALTED.THREAD, 1)", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. ", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory", + "MetricExpr": "59.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_local_dram", + "MetricThreshold": "tma_local_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from local memory. Caching will improve the latency and increase performance. Sample with: MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity.", + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricExpr": "(12 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (11 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "min((9 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=0x1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS, 1)", - "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data.", + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "tma_bad_speculation - tma_branch_mispredicts", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "tma_backend_bound - tma_memory_bound", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + UOPS_RETIRED.RETIRE_SLOTS / SLOTS * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD)", - "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance.", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.ALL_MITE_CYCLES_ANY_UOPS - IDQ.ALL_MITE_CYCLES_4_UOPS) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY, 1)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_0_group", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful.", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "2 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", + "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_non_fused_branches", + "MetricThreshold": "tma_non_fused_branches > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", - "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / CORE_CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_0 + UOPS_DISPATCHED_PORT.PORT_1 + UOPS_DISPATCHED_PORT.PORT_5 + UOPS_DISPATCHED_PORT.PORT_6) / SLOTS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED_PORT.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", "MetricName": "tma_port_1", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", - "MetricExpr": "(UOPS_DISPATCHED_PORT.PORT_2 + UOPS_DISPATCHED_PORT.PORT_3 + UOPS_DISPATCHED_PORT.PORT_7 - UOPS_DISPATCHED_PORT.PORT_4) / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_2 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_2", + "MetricThreshold": "tma_port_2 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 2 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_2", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / CORE_CLKS", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_3 / tma_info_core_clks", "MetricGroup": "TopdownL6;tma_L6_group;tma_load_op_utilization_group", "MetricName": "tma_port_3", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / CORE_CLKS", - "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_port_3 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 3 ([SNB+]Loads and Store-address; [ICL+] Loads). Sample with: UOPS_DISPATCHED_PORT.PORT_3", "ScaleUnit": "100%" }, { "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data)", "MetricExpr": "tma_store_op_utilization", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricGroup": "TopdownL6;tma_L6_group;tma_issueSpSt;tma_store_op_utilization_group", "MetricName": "tma_port_4", + "MetricThreshold": "tma_port_4 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 4 (Store-data). Sample with: UOPS_DISPATCHED_PORT.PORT_4. Related metrics: tma_split_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", - "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", - "MetricName": "tma_port_7", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. ", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED_PORT.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "tma_retiring - (UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address)", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_7 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_store_op_utilization_group", + "MetricName": "tma_port_7", + "MetricThreshold": "tma_port_7 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 7 ([HSW+]simple Store-address). Sample with: UOPS_DISPATCHED_PORT.PORT_7", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((EXE_ACTIVITY.EXE_BOUND_0_PORTS + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_NONE / 2 if #SMT_on else CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_1 - UOPS_EXECUTED.CORE_CYCLES_GE_2) / 2 if #SMT_on else EXE_ACTIVITY.1_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Related metrics: tma_l1_bound", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "((UOPS_EXECUTED.CORE_CYCLES_GE_2 - UOPS_EXECUTED.CORE_CYCLES_GE_3) / 2 if #SMT_on else EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise).", + "MetricExpr": "(UOPS_EXECUTED.CORE_CYCLES_GE_3 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_3) / tma_info_core_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM + 89.5 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Server;Snoop;TopdownL5;tma_L5_group;tma_issueSyncxn;tma_mem_latency_group", + "MetricName": "tma_remote_cache", + "MetricThreshold": "tma_remote_cache > 0.05 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote cache in other sockets including synchronizations issues. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM_PS;MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD_PS. Related metrics: tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_machine_clears", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "min((FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / UOPS_RETIRED.RETIRE_SLOTS, 1)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory", + "MetricExpr": "127 * tma_info_average_frequency * MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Server;Snoop;TopdownL5;tma_L5_group;tma_mem_latency_group", + "MetricName": "tma_remote_dram", + "MetricThreshold": "tma_remote_dram > 0.1 & (tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling loads from remote memory. This is caused often due to non-optimal NUMA allocations. #link to NUMA article. Sample with: MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_memory_operations", + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions", - "MetricExpr": "tma_light_operations * UOPS_RETIRED.MACRO_FUSED / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_fused_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring fused instructions -- where one uop can represent multiple contiguous instructions. The instruction pairs of CMP+JCC or DEC+JCC are commonly used examples.", + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "PARTIAL_RAT_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: PARTIAL_RAT_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused", - "MetricExpr": "tma_light_operations * (BR_INST_RETIRED.ALL_BRANCHES - UOPS_RETIRED.MACRO_FUSED) / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_non_fused_branches", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions that were not fused. Non-conditional branches like direct JMP or CALL would count here. Can be used to examine fusible conditional jumps that were not fused.", + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / UOPS_RETIRED.RETIRE_SLOTS", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body.", + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_fused_instructions + tma_non_fused_branches + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", - "MetricName": "tma_other_light_ops", + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "(OFFCORE_REQUESTS_BUFFER.SQ_FULL / 2 if #SMT_on else OFFCORE_REQUESTS_BUFFER.SQ_FULL) / tma_info_core_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "(UOPS_RETIRED.RETIRE_SLOTS + UOPS_RETIRED.MACRO_FUSED - INST_RETIRED.ANY) / SLOTS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided.", + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricConstraint": "NO_GROUP_EVENTS_NMI", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 11 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "min(100 * (FP_ASSIST.ANY + OTHER_ASSISTS.ANY) / SLOTS, 1)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases.", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "UOPS_DISPATCHED_PORT.PORT_4 / tma_info_core_clks", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per core", - "MetricExpr": "cstate_core@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Core_Residency", + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "9 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", - "ScaleUnit": "100%" + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json index 8784118123b4..e0840c24e7aa 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -1952,7 +1952,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happenning in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json index 37003115c6c7..92a4bdcd4bd7 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json @@ -804,7 +804,7 @@ "Unit": "CHA" }, { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HtiME$ on Reads without RspFwdI*", + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", "EventCode": "0x61", "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", "PerPkg": "1", @@ -3321,7 +3321,7 @@ "EventCode": "0x5C", "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", "UMask": "0x20", "Unit": "CHA" }, @@ -4039,20 +4039,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", "Filter": "config1=0x40233", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", "Filter": "config1=0x40433", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, @@ -4075,20 +4077,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", "Filter": "config1=0x4b033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", "Filter": "config1=0x40033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x11", "Unit": "CHA" }, @@ -4102,20 +4106,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", "Filter": "config1=0x40233", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", "Filter": "config1=0x40433", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, @@ -4138,20 +4144,22 @@ "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", "Filter": "config1=0x4b033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", "Filter": "config1=0x40033", "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", "UMask": "0x21", "Unit": "CHA" }, @@ -11909,7 +11917,7 @@ "Unit": "IIO" }, { - "BriefDescription": "UNC_IIO_NOTHING", + "BriefDescription": "Counting disabled", "EventName": "UNC_IIO_NOTHING", "PerPkg": "1", "Unit": "IIO" @@ -15507,7 +15515,7 @@ "EventCode": "0xC", "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -16013,35 +16021,35 @@ "Unit": "M2M" }, { - "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", "EventCode": "0x28", "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to Intel Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", "Unit": "M2M" }, { - "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", "EventCode": "0x27", "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", "PerPkg": "1", - "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel Ultra Path Interconnect (bypassing the CHA) was disabled", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", "Unit": "M2M" }, { - "BriefDescription": "Messages sent direct to the Intel UPI", + "BriefDescription": "Messages sent direct to the Intel(R) UPI", "EventCode": "0x26", "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to the Intel Ultra Path Interconnect (bypassing the CHA)", + "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", "Unit": "M2M" }, { - "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", "EventCode": "0x29", "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", "PerPkg": "1", - "PublicDescription": "Counts when a read message that was sent direct to the Intel Ultra Path Interconnect (bypassing the CHA) was overridden", + "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", "Unit": "M2M" }, { @@ -20785,7 +20793,7 @@ "EventCode": "0x61", "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", "UMask": "0x2", "Unit": "M3UPI" }, @@ -20794,7 +20802,7 @@ "EventCode": "0x61", "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", "UMask": "0x4", "Unit": "M3UPI" }, @@ -21180,7 +21188,7 @@ "Unit": "M3UPI" }, { - "BriefDescription": "Flit Gen - Header 1; Acumullate", + "BriefDescription": "Flit Gen - Header 1; Accumulate", "EventCode": "0x53", "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", "PerPkg": "1", @@ -21851,7 +21859,7 @@ "Unit": "M3UPI" }, { - "BriefDescription": "Remote VNA Credits; Level < 1", + "BriefDescription": "Remote VNA Credits; Level < 1", "EventCode": "0x5B", "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", "PerPkg": "1", @@ -21860,7 +21868,7 @@ "Unit": "M3UPI" }, { - "BriefDescription": "Remote VNA Credits; Level < 4", + "BriefDescription": "Remote VNA Credits; Level < 4", "EventCode": "0x5B", "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", "PerPkg": "1", @@ -21869,7 +21877,7 @@ "Unit": "M3UPI" }, { - "BriefDescription": "Remote VNA Credits; Level < 5", + "BriefDescription": "Remote VNA Credits; Level < 5", "EventCode": "0x5B", "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", "PerPkg": "1", @@ -24401,7 +24409,7 @@ "EventCode": "0x29", "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", "PerPkg": "1", - "PublicDescription": "Count cases where flow control queue that sits between the Intel Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", "Unit": "M3UPI" }, { @@ -24756,11 +24764,11 @@ "Unit": "M2M" }, { - "BriefDescription": "Clocks of the Intel Ultra Path Interconnect (UPI)", + "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", "EventCode": "0x1", "EventName": "UNC_UPI_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", "Unit": "UPI LL" }, { @@ -24782,11 +24790,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Data Response packets that go direct to Intel UPI", + "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", "EventCode": "0x12", "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel Ultra Path Interconnect (UPI) bypassing the CHA .", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", "UMask": "0x2", "Unit": "UPI LL" }, @@ -24855,11 +24863,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles Intel UPI is in L1 power mode (shutdown)", + "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", "EventCode": "0x21", "EventName": "UNC_UPI_L1_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the Intel Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", "Unit": "UPI LL" }, { @@ -25021,11 +25029,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles the Rx of the Intel UPI is in L0p power mode", + "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", "EventCode": "0x25", "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", "Unit": "UPI LL" }, { @@ -25218,7 +25226,7 @@ "EventCode": "0x8", "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", "PerPkg": "1", - "PublicDescription": "Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", + "PublicDescription": "Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", "Unit": "UPI LL" }, { @@ -25250,7 +25258,7 @@ "EventCode": "0x3", "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", "UMask": "0xf", "Unit": "UPI LL" }, @@ -25259,7 +25267,7 @@ "EventCode": "0x3", "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", "UMask": "0x27", "Unit": "UPI LL" }, @@ -25583,11 +25591,11 @@ "Unit": "UPI LL" }, { - "BriefDescription": "Cycles in which the Tx of the Intel Ultra Path Interconnect (UPI) is in L0p power mode", + "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", "EventCode": "0x27", "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", "Unit": "UPI LL" }, { @@ -25759,7 +25767,7 @@ "EventCode": "0x41", "EventName": "UNC_UPI_TxL_BYPASSED", "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", "Unit": "UPI LL" }, { @@ -25767,7 +25775,7 @@ "EventCode": "0x2", "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel Ultra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", "UMask": "0xf", "Unit": "UPI LL" }, @@ -25776,7 +25784,7 @@ "EventCode": "0x2", "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel Ulra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", "UMask": "0x27", "Unit": "UPI LL" }, @@ -26127,7 +26135,7 @@ "EventCode": "0x2", "EventName": "UPI_DATA_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel Ultra Path Interconnect (UPI) slots on this UPI unit.", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", "ScaleUnit": "7.11E-06Bytes", "UMask": "0xf", "Unit": "UPI LL" diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-power.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-power.json index 8e21dc3eff16..c6254af7a468 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-power.json @@ -143,7 +143,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -151,7 +151,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -159,7 +159,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { -- GitLab From de44486fd46134e10c42f3acc09695e74ad91be8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:27 -0800 Subject: [PATCH 0031/5631] perf vendor events intel: Refresh tigerlake events Update the tigerlake events from 1.08 to 1.10. Generation was done using https://github.com/intel/perfmon. Notable changes are new events and event descriptions, TMA metrics are updated to version 4.5, TMA info metrics are renamed from their node name to be lower case and prefixed by tma_info_, MetricThreshold expressions are added, smi_cost and transaction metric groups are added replicating existing hard coded metrics in stat-shadow. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-31-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/tigerlake/floating-point.json | 31 + .../arch/x86/tigerlake/pipeline.json | 18 + .../arch/x86/tigerlake/tgl-metrics.json | 1942 ++++++++++------- .../arch/x86/tigerlake/uncore-other.json | 28 +- 5 files changed, 1198 insertions(+), 823 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 07f0b4758a83..bc2c4e756f44 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -27,7 +27,7 @@ GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v54,skylake,core GenuineIntel-6-55-[01234],v1.29,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core -GenuineIntel-6-8[CD],v1.08,tigerlake,core +GenuineIntel-6-8[CD],v1.10,tigerlake,core GenuineIntel-6-2C,v3,westmereep-dp,core GenuineIntel-6-25,v3,westmereep-sp,core GenuineIntel-6-2F,v3,westmereex,core diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json index 655342dadac6..63b5b56d1ed0 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json @@ -39,6 +39,14 @@ "SampleAfterValue": "100003", "UMask": "0x20" }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -55,6 +63,22 @@ "SampleAfterValue": "100003", "UMask": "0x80" }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -70,5 +94,12 @@ "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0xfc" } ] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json index 9d43decd75ec..a0aeeb801fd7 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json @@ -158,6 +158,15 @@ "SampleAfterValue": "50021", "UMask": "0x20" }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "50021", + "UMask": "0x8" + }, { "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", "EventCode": "0xec", @@ -383,6 +392,15 @@ "SampleAfterValue": "2000003", "UMask": "0x3" }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EventCode": "0x0d", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0x0d", diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 7e22a9127156..4c80d6be6cf1 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -1,1230 +1,1532 @@ [ { - "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", - "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / SLOTS", - "MetricGroup": "PGO;TopdownL1;tma_L1_group", - "MetricName": "tma_frontend_bound", - "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Machine_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", - "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / SLOTS", - "MetricGroup": "Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_latency", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", - "MetricExpr": "ICACHE_16B.IFDATA_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_icache_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", + "BriefDescription": "C10 residency percent per package", + "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C10_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", - "MetricExpr": "ICACHE_64B.IFTAG_STALL / CLKS", - "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_itlb_misses", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", - "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / CLKS + tma_unknown_branches", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_branch_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", - "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_mispredicts_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "cstate_core@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", - "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / CLKS", - "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_clears_resteers", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES", + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", - "MetricExpr": "10 * BACLEARS.ANY / CLKS", - "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_branch_resteers_group", - "MetricName": "tma_unknown_branches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (First fetch or hitting BPU capacity limit). Sample with: BACLEARS.ANY", + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "cstate_core@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / CLKS", - "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_dsb_switches", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS", + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", - "MetricExpr": "ILD_STALL.LCP / CLKS", - "MetricGroup": "FetchLat;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_lcp", - "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs.", + "BriefDescription": "C8 residency percent per package", + "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C8_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", - "MetricExpr": "3 * IDQ.MS_SWITCHES / CLKS", - "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_fetch_latency_group", - "MetricName": "tma_ms_switches", - "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES", + "BriefDescription": "C9 residency percent per package", + "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", + "MetricGroup": "Power", + "MetricName": "C9_Pkg_Residency", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", - "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", - "MetricGroup": "FetchBW;Frontend;TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_fetch_bandwidth", - "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS", + "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", + "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", + "MetricGroup": "smi", + "MetricName": "smi_cycles", + "MetricThreshold": "smi_cycles > 0.1", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", - "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_mite", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", - "ScaleUnit": "100%" + "BriefDescription": "Number of SMI interrupts.", + "MetricExpr": "msr@smi@", + "MetricGroup": "smi", + "MetricName": "smi_num", + "ScaleUnit": "1SMI#" }, { - "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", - "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / CORE_CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_decoder0_alone", + "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", + "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_4k_aliasing", + "MetricThreshold": "tma_4k_aliasing > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", - "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / CLKS", - "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_mite_group", - "MetricName": "tma_mite_4wide", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", + "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_alu_op_utilization", + "MetricThreshold": "tma_alu_op_utilization > 0.6", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", - "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "DSB;FetchBW;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_dsb", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", + "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", + "MetricExpr": "100 * ASSISTS.ANY / tma_info_slots", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_assists", + "MetricThreshold": "tma_assists > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", - "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / CORE_CLKS / 2", - "MetricGroup": "FetchBW;LSD;TopdownL3;tma_fetch_bandwidth_group", - "MetricName": "tma_lsd", - "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", + "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_backend_bound", + "MetricThreshold": "tma_backend_bound > 0.2", + "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, { "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations", "MetricExpr": "max(1 - (tma_frontend_bound + tma_backend_bound + tma_retiring), 0)", - "MetricGroup": "TopdownL1;tma_L1_group", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", + "MetricThreshold": "tma_bad_speculation > 0.15", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, + { + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", + "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_branch_instructions", + "MetricThreshold": "tma_branch_instructions > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" + }, { "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction", "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * tma_bad_speculation", - "MetricGroup": "BadSpec;BrMispredicts;TopdownL2;tma_L2_group;tma_bad_speculation_group", + "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", + "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", - "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", - "MetricGroup": "BadSpec;MachineClears;TopdownL2;tma_L2_group;tma_bad_speculation_group", - "MetricName": "tma_machine_clears", - "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers", + "MetricExpr": "INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks + tma_unknown_branches", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_branch_resteers", + "MetricThreshold": "tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers. Branch Resteers estimates the Frontend delay in fetching operations from corrected path; following all sorts of miss-predicted branches. For example; branchy code with lots of miss-predictions might get categorized under Branch Resteers. Note the value of this node may overlap with its siblings. Sample with: BR_MISP_RETIRED.ALL_BRANCHES", "ScaleUnit": "100%" }, { - "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend", - "MetricExpr": "topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * cpu@INT_MISC.RECOVERY_CYCLES\\,cmask\\=1\\,edge@ / SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_backend_bound", - "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", + "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", + "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", + "MetricGroup": "TopdownL4;tma_L4_group;tma_microcode_sequencer_group", + "MetricName": "tma_cisc", + "MetricThreshold": "tma_cisc > 0.1 & (tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1)", + "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", - "MetricGroup": "Backend;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_memory_bound", - "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears", + "MetricExpr": "(1 - BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT)) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;MachineClears;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueMC", + "MetricName": "tma_clears_resteers", + "MetricThreshold": "tma_clears_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Machine Clears. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", - "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / CLKS, 0)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l1_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(49 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * tma_info_average_frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_contested_accesses", + "MetricThreshold": "tma_contested_accesses > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS. Related metrics: tma_data_sharing, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", - "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_dtlb_load", - "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS", + "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", + "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_core_bound", + "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_hit", + "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "48 * tma_info_average_frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_l3_bound_group", + "MetricName": "tma_data_sharing", + "MetricThreshold": "tma_data_sharing > 0.05 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD. Related metrics: tma_contested_accesses, tma_false_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", - "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_load_group", - "MetricName": "tma_load_stlb_miss", + "BriefDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder", + "MetricExpr": "(cpu@INST_DECODED.DECODERS\\,cmask\\=1@ - cpu@INST_DECODED.DECODERS\\,cmask\\=2@) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_issueD0;tma_mite_group", + "MetricName": "tma_decoder0_alone", + "MetricThreshold": "tma_decoder0_alone > 0.1 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", + "PublicDescription": "This metric represents fraction of cycles where decoder-0 was the only active decoder. Related metrics: tma_few_uops_instructions", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", - "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_store_fwd_blk", - "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", + "MetricExpr": "ARITH.DIVIDER_ACTIVE / tma_info_clks", + "MetricGroup": "TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_divider", + "MetricThreshold": "tma_divider > 0.2 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", - "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / CLKS", - "MetricGroup": "Offcore;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_lock_latency", - "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS", + "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_dram_bound", + "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", - "MetricExpr": "Load_Miss_Real_Latency * LD_BLOCKS.NO_SR / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_split_loads", - "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline", + "MetricExpr": "(IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSB;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_dsb", + "MetricThreshold": "tma_dsb > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to DSB (decoded uop cache) fetch pipeline. For example; inefficient utilization of the DSB cache structure or bank conflict when reading from it; are categorized here.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset", - "MetricExpr": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS / CLKS", - "MetricGroup": "TopdownL4;tma_l1_bound_group", - "MetricName": "tma_4k_aliasing", - "PublicDescription": "This metric estimates how often memory load accesses were aliased by preceding stores (in program order) with a 4K address offset. False match is possible; which incur a few cycles load re-issue. However; the short re-issue duration is often hidden by the out-of-order core and HW optimizations; hence a user may safely ignore a high value of this metric unless it manages to propagate up into parent nodes of the hierarchy (e.g. to L1_Bound).", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / tma_info_clks", + "MetricGroup": "DSBmiss;FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_dsb_switches", + "MetricThreshold": "tma_dsb_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to switches from DSB to MITE pipelines. The DSB (decoded i-cache) is a Uop Cache where the front-end directly delivers Uops (micro operations) avoiding heavy x86 decoding. The DSB pipeline has shorter latency and delivered higher bandwidth than the MITE (legacy instruction decode pipeline). Switching between the two pipelines can cause penalties hence this metric measures the exposed penalty. Sample with: FRONTEND_RETIRED.DSB_MISS_PS. Related metrics: tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", - "MetricExpr": "L1D_PEND_MISS.FB_FULL / CLKS", - "MetricGroup": "MemoryBW;TopdownL4;tma_l1_bound_group", - "MetricName": "tma_fb_full", - "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory).", + "BriefDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses", + "MetricExpr": "min(7 * cpu@DTLB_LOAD_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_LOAD_MISSES.WALK_ACTIVE, max(CYCLE_ACTIVITY.CYCLES_MEM_ANY - CYCLE_ACTIVITY.CYCLES_L1D_MISS, 0)) / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_l1_bound_group", + "MetricName": "tma_dtlb_load", + "MetricThreshold": "tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles where the Data TLB (DTLB) was missed by load accesses. TLBs (Translation Look-aside Buffers) are processor caches for recently used entries out of the Page Tables that are used to map virtual- to physical-addresses by the operating system. This metric approximates the potential delay of demand loads missing the first-level data TLB (assuming worst case scenario with back to back misses to different pages). This includes hitting in the second-level TLB (STLB) as well as performing a hardware page walk on an STLB miss. Sample with: MEM_INST_RETIRED.STLB_MISS_LOADS_PS. Related metrics: tma_dtlb_store, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", - "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS)", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l2_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", + "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL4;tma_L4_group;tma_issueTLB;tma_store_bound_group", + "MetricName": "tma_dtlb_store", + "MetricThreshold": "tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS. Related metrics: tma_dtlb_load, tma_info_memory_data_tlbs", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", - "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / CLKS", - "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_l3_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", + "MetricExpr": "54 * tma_info_average_frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / tma_info_clks", + "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_L4_group;tma_issueSyncxn;tma_store_bound_group", + "MetricName": "tma_false_sharing", + "MetricThreshold": "tma_false_sharing > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM. Related metrics: tma_contested_accesses, tma_data_sharing, tma_machine_clears, tma_remote_cache", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses", - "MetricExpr": "(49 * Average_Frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) + 48 * Average_Frequency * MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_contested_accesses", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to contested accesses. Contested accesses occur when data written by one Logical Processor are read by another Logical Processor on a different Physical Core. Examples of contested accesses include synchronizations such as locks; true data sharing such as modified locked variables; and false sharing. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD;MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "BriefDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed", + "MetricExpr": "L1D_PEND_MISS.FB_FULL / tma_info_clks", + "MetricGroup": "MemoryBW;TopdownL4;tma_L4_group;tma_issueBW;tma_issueSL;tma_issueSmSt;tma_l1_bound_group", + "MetricName": "tma_fb_full", + "MetricThreshold": "tma_fb_full > 0.3", + "PublicDescription": "This metric does a *rough estimation* of how often L1D Fill Buffer unavailability limited additional L1D miss memory access requests to proceed. The higher the metric value; the deeper the memory hierarchy level the misses are satisfied from (metric values >1 are valid). Often it hints on approaching bandwidth limits (to L2 cache; L3 cache or external memory). Related metrics: tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full, tma_store_latency, tma_streaming_stores", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses", - "MetricExpr": "48 * Average_Frequency * (MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD + MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD * (1 - OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM / (OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM + OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD))) * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "Offcore;Snoop;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_data_sharing", - "PublicDescription": "This metric estimates fraction of cycles while the memory subsystem was handling synchronizations due to data-sharing accesses. Data shared by multiple Logical Processors (even just read shared) may cause increased access latency due to cache coherency. Excessive data sharing can drastically harm multithreaded performance. Sample with: MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues", + "MetricExpr": "max(0, tma_frontend_bound - tma_fetch_latency)", + "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", - "MetricExpr": "17.5 * Average_Frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / CLKS", - "MetricGroup": "MemoryLat;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_l3_hit_latency", - "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "BriefDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues", + "MetricExpr": "(5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / tma_info_slots", + "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", - "MetricExpr": "L1D_PEND_MISS.L2_STALL / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_l3_bound_group", - "MetricName": "tma_sq_full", - "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). The Super Queue is used for requests to access the L2 cache or to go out to the Uncore.", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", + "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", + "MetricGroup": "TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueD0", + "MetricName": "tma_few_uops_instructions", + "MetricThreshold": "tma_few_uops_instructions > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions. Related metrics: tma_decoder0_alone", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / CLKS + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / CLKS - tma_l2_bound", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_dram_bound", - "PublicDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads. Better caching can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_MISS_PS", + "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", + "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", + "MetricGroup": "HPC;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_fp_arith", + "MetricThreshold": "tma_fp_arith > 0.2 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_bandwidth", - "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_scalar", + "MetricThreshold": "tma_fp_scalar > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting. Related metrics: tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", - "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / CLKS - tma_mem_bandwidth", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_dram_bound_group", - "MetricName": "tma_mem_latency", - "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that).", + "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", + "MetricExpr": "cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@ / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL4;tma_L4_group;tma_fp_arith_group;tma_issue2P", + "MetricName": "tma_fp_vector", + "MetricThreshold": "tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", - "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / CLKS", - "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_memory_bound_group", - "MetricName": "tma_store_bound", - "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_128b", + "MetricThreshold": "tma_fp_vector_128b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", - "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / CLKS", - "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_store_latency", - "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full)", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_256b", + "MetricThreshold": "tma_fp_vector_256b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing", - "MetricExpr": "54 * Average_Frequency * OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM / CLKS", - "MetricGroup": "DataSharing;Offcore;Snoop;TopdownL4;tma_store_bound_group", - "MetricName": "tma_false_sharing", - "PublicDescription": "This metric roughly estimates how often CPU was handling synchronizations due to False Sharing. False Sharing is a multithreading hiccup; where multiple Logical Processors contend on different data-elements mapped into the same cache line. Sample with: OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", + "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * tma_info_slots)", + "MetricGroup": "Compute;Flops;TopdownL5;tma_L5_group;tma_fp_vector_group;tma_issue2P", + "MetricName": "tma_fp_vector_512b", + "MetricThreshold": "tma_fp_vector_512b > 0.1 & (tma_fp_vector > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6))", + "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_port_0, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric represents rate of split store accesses", - "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / CORE_CLKS", - "MetricGroup": "TopdownL4;tma_store_bound_group", - "MetricName": "tma_split_stores", - "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS", + "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend", + "MetricExpr": "topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / tma_info_slots", + "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_frontend_bound", + "MetricThreshold": "tma_frontend_bound > 0.15", + "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", - "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / CLKS", - "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_store_bound_group", - "MetricName": "tma_streaming_stores", - "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences", + "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_heavy_operations", + "MetricThreshold": "tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses", - "MetricExpr": "(7 * cpu@DTLB_STORE_MISSES.STLB_HIT\\,cmask\\=1@ + DTLB_STORE_MISSES.WALK_ACTIVE) / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL4;tma_store_bound_group", - "MetricName": "tma_dtlb_store", - "PublicDescription": "This metric roughly estimates the fraction of cycles spent handling first-level data TLB store misses. As with ordinary data caching; focus on improving data locality and reducing working-set size to reduce DTLB overhead. Additionally; consider using profile-guided optimization (PGO) to collocate frequently-used data on the same page. Try using larger page sizes for large amounts of frequently-used data. Sample with: MEM_INST_RETIRED.STLB_MISS_STORES_PS", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;IcMiss;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to instruction cache misses. Sample with: FRONTEND_RETIRED.L2_MISS_PS;FRONTEND_RETIRED.L1I_MISS_PS", "ScaleUnit": "100%" }, { - "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", - "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_hit", - "ScaleUnit": "100%" + "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", + "MetricExpr": "tma_info_turbo_utilization * TSC / 1e9 / duration_time", + "MetricGroup": "Power;Summary", + "MetricName": "tma_info_average_frequency" }, { - "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", - "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / CORE_CLKS", - "MetricGroup": "MemoryTLB;TopdownL5;tma_dtlb_store_group", - "MetricName": "tma_store_stlb_miss", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", + "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB;tma_issueBC", + "MetricName": "tma_info_big_code", + "MetricThreshold": "tma_info_big_code > 20", + "PublicDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses). Related metrics: tma_info_branching_overhead" }, { - "BriefDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck", - "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", - "MetricGroup": "Backend;Compute;TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_core_bound", - "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", - "ScaleUnit": "100%" + "BriefDescription": "Branch instructions per taken branch.", + "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_bptkbranch" }, { - "BriefDescription": "This metric represents fraction of cycles where the Divider unit was active", - "MetricExpr": "ARITH.DIVIDER_ACTIVE / CLKS", - "MetricGroup": "TopdownL3;tma_core_bound_group", - "MetricName": "tma_divider", - "PublicDescription": "This metric represents fraction of cycles where the Divider unit was active. Divide and square root instructions are performed by the Divider unit and can take considerably longer latency than integer or Floating Point addition; subtraction; or multiplication. Sample with: ARITH.DIVIDER_ACTIVE", - "ScaleUnit": "100%" + "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", + "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * tma_info_slots / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_branch_misprediction_cost", + "PublicDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear). Related metrics: tma_branch_mispredicts, tma_info_mispredictions, tma_mispredicts_resteers" }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", - "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CLKS if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CLKS)", - "MetricGroup": "PortsUtil;TopdownL3;tma_core_bound_group", - "MetricName": "tma_ports_utilization", - "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", + "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / tma_info_slots)", + "MetricGroup": "Ret;tma_issueBC", + "MetricName": "tma_info_branching_overhead", + "MetricThreshold": "tma_info_branching_overhead > 10", + "PublicDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls). Related metrics: tma_info_big_code" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / CLKS + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_0", - "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are CALL or RET", + "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_callret" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", - "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / CLKS", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_serializing_operation", - "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD", - "ScaleUnit": "100%" + "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Pipeline", + "MetricName": "tma_info_clks" }, { - "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", - "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / CLKS", - "MetricGroup": "TopdownL6;tma_serializing_operation_group", - "MetricName": "tma_slow_pause", - "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", - "ScaleUnit": "100%" + "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * ITLB_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Fed;MemoryTLB", + "MetricName": "tma_info_code_stlb_mpki" }, { - "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", - "MetricExpr": "CLKS * UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", - "MetricGroup": "TopdownL5;tma_ports_utilized_0_group", - "MetricName": "tma_mixing_vectors", - "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic.", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are non-taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_nt" }, { - "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_1", - "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of branches that are taken conditionals", + "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches;CodeGen;PGO", + "MetricName": "tma_info_cond_tk" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_2", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL", - "ScaleUnit": "100%" + "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", + "MetricExpr": "(100 * (1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if tma_info_smt_2t_utilization > 0.5 else 0)", + "MetricGroup": "Cor;SMT", + "MetricName": "tma_info_core_bound_likely", + "MetricThreshold": "tma_info_core_bound_likely > 0.5" }, { - "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", - "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / CLKS", - "MetricGroup": "PortsUtil;TopdownL4;tma_ports_utilization_group", - "MetricName": "tma_ports_utilized_3m", - "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", - "ScaleUnit": "100%" + "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", + "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", + "MetricGroup": "SMT", + "MetricName": "tma_info_core_clks" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution ports for ALU operations.", - "MetricExpr": "(UOPS_DISPATCHED.PORT_0 + UOPS_DISPATCHED.PORT_1 + UOPS_DISPATCHED.PORT_5 + UOPS_DISPATCHED.PORT_6) / (4 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_alu_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_core_clks", + "MetricGroup": "Ret;SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_coreipc" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch) Sample with: UOPS_DISPATCHED.PORT_0", - "MetricExpr": "UOPS_DISPATCHED.PORT_0 / CORE_CLKS", - "MetricGroup": "Compute;TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_0", - "ScaleUnit": "100%" + "BriefDescription": "Cycles Per Instruction (per Logical Processor)", + "MetricExpr": "1 / tma_info_ipc", + "MetricGroup": "Mem;Pipeline", + "MetricName": "tma_info_cpi" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU) Sample with: UOPS_DISPATCHED.PORT_1", - "MetricExpr": "UOPS_DISPATCHED.PORT_1 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_1", - "ScaleUnit": "100%" + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", + "MetricGroup": "HPC;Summary", + "MetricName": "tma_info_cpu_utilization" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU) Sample with: UOPS_DISPATCHED.PORT_5", - "MetricExpr": "UOPS_DISPATCHED.PORT_5 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_5", - "ScaleUnit": "100%" + "BriefDescription": "Average Parallel L2 cache miss data reads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_data_l2_mlp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU) Sample with: UOPS_DISPATCHED.PORT_6", - "MetricExpr": "UOPS_DISPATCHED.PORT_6 / CORE_CLKS", - "MetricGroup": "TopdownL6;tma_alu_op_utilization_group", - "MetricName": "tma_port_6", - "ScaleUnit": "100%" + "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", + "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", + "MetricName": "tma_info_dram_bw_use", + "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_info_memory_bandwidth, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations Sample with: UOPS_DISPATCHED.PORT_2_3", - "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_load_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "DSB;Fed;FetchBW;tma_issueFB", + "MetricName": "tma_info_dsb_coverage", + "MetricThreshold": "tma_info_dsb_coverage < 0.7 & tma_info_ipc / 5 > 0.35", + "PublicDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache). Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_misses, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations Sample with: UOPS_DISPATCHED.PORT_7_8", - "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * CORE_CLKS)", - "MetricGroup": "TopdownL5;tma_ports_utilized_3m_group", - "MetricName": "tma_store_op_utilization", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", + "MetricGroup": "DSBmiss;Fed;tma_issueFB", + "MetricName": "tma_info_dsb_misses", + "MetricThreshold": "tma_info_dsb_misses > 10", + "PublicDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_iptb, tma_lcp" }, { - "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", - "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * SLOTS", - "MetricGroup": "TopdownL1;tma_L1_group", - "MetricName": "tma_retiring", - "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", - "ScaleUnit": "100%" + "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", + "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", + "MetricGroup": "DSBmiss", + "MetricName": "tma_info_dsb_switch_cost" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", - "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_light_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-thread", + "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", + "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", + "MetricName": "tma_info_execute" }, { - "BriefDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired)", - "MetricExpr": "tma_x87_use + tma_fp_scalar + tma_fp_vector", - "MetricGroup": "HPC;TopdownL3;tma_light_operations_group", - "MetricName": "tma_fp_arith", - "PublicDescription": "This metric represents overall arithmetic floating-point (FP) operations fraction the CPU has executed (retired). Note this metric's value may exceed its parent due to use of \"Uops\" CountDomain and FMA double-counting.", - "ScaleUnit": "100%" + "BriefDescription": "The ratio of Executed- by Issued-Uops", + "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", + "MetricGroup": "Cor;Pipeline", + "MetricName": "tma_info_execute_per_issue", + "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." }, { - "BriefDescription": "This metric serves as an approximation of legacy x87 usage", - "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", - "MetricGroup": "Compute;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_x87_use", - "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", - "ScaleUnit": "100%" + "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_fb_hpki" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_scalar", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) scalar uops fraction the CPU has retired. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Average number of Uops issued by front-end when it issued something", + "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", + "MetricGroup": "Fed;FetchBW", + "MetricName": "tma_info_fetch_upc" }, { - "BriefDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL4;tma_fp_arith_group", - "MetricName": "tma_fp_vector", - "PublicDescription": "This metric approximates arithmetic floating-point (FP) vector uops fraction the CPU has retired aggregated across all vector widths. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Floating Point Operations Per Cycle", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / tma_info_core_clks", + "MetricGroup": "Flops;Ret", + "MetricName": "tma_info_flopc" }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_128b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 128-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@) / (2 * tma_info_core_clks)", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_fp_arith_utilization", + "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_256b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 256-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "(cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", + "MetricGroup": "Cor;Flops;HPC", + "MetricName": "tma_info_gflops", + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." }, { - "BriefDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors", - "MetricExpr": "(FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / (tma_retiring * SLOTS)", - "MetricGroup": "Compute;Flops;TopdownL5;tma_fp_vector_group", - "MetricName": "tma_fp_vector_512b", - "PublicDescription": "This metric approximates arithmetic FP vector uops fraction the CPU has retired for 512-bit wide vectors. May overcount due to FMA double counting.", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck", + "MetricExpr": "100 * (tma_fetch_latency * tma_icache_misses / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Fed;FetchLat;IcMiss;tma_issueFL", + "MetricName": "tma_info_ic_misses", + "MetricThreshold": "tma_info_ic_misses > 5", + "PublicDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck. Related metrics: " }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", - "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_memory_operations", - "ScaleUnit": "100%" + "BriefDescription": "Average Latency for L1 instruction cache misses", + "MetricExpr": "ICACHE_16B.IFDATA_STALL / cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=1\\,edge@", + "MetricGroup": "Fed;FetchLat;IcMiss", + "MetricName": "tma_info_icache_miss_latency" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring branch instructions.", - "MetricExpr": "tma_light_operations * BR_INST_RETIRED.ALL_BRANCHES / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_branch_instructions", - "ScaleUnit": "100%" + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", + "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", + "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", + "MetricName": "tma_info_ilp" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", - "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * SLOTS)", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_nop_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", - "ScaleUnit": "100%" + "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", + "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - tma_info_big_code", + "MetricGroup": "Fed;FetchBW;Frontend", + "MetricName": "tma_info_instruction_fetch_bw", + "MetricThreshold": "tma_info_instruction_fetch_bw > 20" }, { - "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", - "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", - "MetricGroup": "Pipeline;TopdownL3;tma_light_operations_group", - "MetricName": "tma_other_light_ops", - "ScaleUnit": "100%" + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary;TmaL1;tma_L1_group", + "MetricName": "tma_info_instructions", + "PublicDescription": "Total number of retired Instructions. Sample with: INST_RETIRED.PREC_DIST" }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences", - "MetricExpr": "tma_microcode_sequencer + tma_retiring * (UOPS_DECODED.DEC0 - cpu@UOPS_DECODED.DEC0\\,cmask\\=1@) / IDQ.MITE_UOPS", - "MetricGroup": "Retire;TopdownL2;tma_L2_group;tma_retiring_group", - "MetricName": "tma_heavy_operations", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or microcoded sequences. This highly-correlates with the uop length of these instructions/sequences.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + cpu@FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE\\,umask\\=0xfc@)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_iparith", + "MetricThreshold": "tma_info_iparith < 10", + "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." }, { - "BriefDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops", - "MetricExpr": "tma_heavy_operations - tma_microcode_sequencer", - "MetricGroup": "TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_few_uops_instructions", - "PublicDescription": "This metric represents fraction of slots where the CPU was retiring instructions that that are decoder into two or up to ([SNB+] four; [ADL+] five) uops. This highly-correlates with the number of uops in such instructions.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx128", + "MetricThreshold": "tma_info_iparith_avx128 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", - "MetricExpr": "tma_retiring * SLOTS / UOPS_ISSUED.ANY * IDQ.MS_UOPS / SLOTS", - "MetricGroup": "MicroSeq;TopdownL3;tma_heavy_operations_group", - "MetricName": "tma_microcode_sequencer", - "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx256", + "MetricThreshold": "tma_info_iparith_avx256 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists", - "MetricExpr": "100 * ASSISTS.ANY / SLOTS", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_assists", - "PublicDescription": "This metric estimates fraction of slots the CPU retired uops delivered by the Microcode_Sequencer as a result of Assists. Assists are long sequences of uops that are required in certain corner-cases for operations that cannot be handled natively by the execution pipeline. For example; when working with very small floating point values (so-called Denormals); the FP units are not set up to perform these operations natively. Instead; a sequence of instructions to perform the computation on the Denormals is injected into the pipeline. Since these microcode sequences might be dozens of uops long; Assists can be extremely deleterious to performance and they can be avoided in many cases. Sample with: ASSISTS.ANY", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;FpVector;InsType", + "MetricName": "tma_info_iparith_avx512", + "MetricThreshold": "tma_info_iparith_avx512 < 10", + "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction", - "MetricExpr": "max(0, tma_microcode_sequencer - tma_assists)", - "MetricGroup": "TopdownL4;tma_microcode_sequencer_group", - "MetricName": "tma_cisc", - "PublicDescription": "This metric estimates fraction of cycles the CPU retired uops originated from CISC (complex instruction set computer) instruction. A CISC instruction has multiple uops that are required to perform the instruction's functionality as in the case of read-modify-write as an example. Since these instructions require multiple uops they may or may not imply sub-optimal use of machine resources.", - "ScaleUnit": "100%" + "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_dp", + "MetricThreshold": "tma_info_iparith_scalar_dp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", - "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "Mispredictions" + "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "MetricGroup": "Flops;FpScalar;InsType", + "MetricName": "tma_info_iparith_scalar_sp", + "MetricThreshold": "tma_info_iparith_scalar_sp < 10", + "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." }, { - "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "Memory_Bandwidth" + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Branches;Fed;InsType", + "MetricName": "tma_info_ipbranch", + "MetricThreshold": "tma_info_ipbranch < 8" }, { - "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", - "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", - "MetricGroup": "Mem;MemoryLat;Offcore", - "MetricName": "Memory_Latency" + "BriefDescription": "Instructions Per Cycle (per Logical Processor)", + "MetricExpr": "INST_RETIRED.ANY / tma_info_clks", + "MetricGroup": "Ret;Summary", + "MetricName": "tma_info_ipc" }, { - "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", - "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", - "MetricGroup": "Mem;MemoryTLB;Offcore", - "MetricName": "Memory_Data_TLBs" + "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", + "MetricGroup": "Branches;Fed;PGO", + "MetricName": "tma_info_ipcall", + "MetricThreshold": "tma_info_ipcall < 200" }, { - "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)", - "MetricExpr": "100 * ((BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL)) / SLOTS)", - "MetricGroup": "Ret", - "MetricName": "Branching_Overhead" + "BriefDescription": "Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", + "MetricGroup": "DSBmiss;Fed", + "MetricName": "tma_info_ipdsb_miss_ret", + "MetricThreshold": "tma_info_ipdsb_miss_ret < 50" }, { - "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)", - "MetricExpr": "100 * tma_fetch_latency * (tma_itlb_misses + tma_icache_misses + tma_unknown_branches) / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)", - "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB", - "MetricName": "Big_Code" + "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", + "MetricGroup": "Branches;OS", + "MetricName": "tma_info_ipfarbranch", + "MetricThreshold": "tma_info_ipfarbranch < 1e6" }, { - "BriefDescription": "Total pipeline cost of instruction fetch bandwidth related bottlenecks", - "MetricExpr": "100 * (tma_frontend_bound - tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) - Big_Code", - "MetricGroup": "Fed;FetchBW;Frontend", - "MetricName": "Instruction_Fetch_BW" + "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / (cpu@FP_ARITH_INST_RETIRED.SCALAR_SINGLE\\,umask\\=0x03@ + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * cpu@FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE\\,umask\\=0x18@ + 8 * cpu@FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE\\,umask\\=0x60@ + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", + "MetricGroup": "Flops;InsType", + "MetricName": "tma_info_ipflop", + "MetricThreshold": "tma_info_ipflop < 10" }, { - "BriefDescription": "Instructions Per Cycle (per Logical Processor)", - "MetricExpr": "INST_RETIRED.ANY / CLKS", - "MetricGroup": "Ret;Summary", - "MetricName": "IPC" + "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipload", + "MetricThreshold": "tma_info_ipload < 3" }, { - "BriefDescription": "Uops Per Instruction", - "MetricExpr": "tma_retiring * SLOTS / INST_RETIRED.ANY", - "MetricGroup": "Pipeline;Ret;Retire", - "MetricName": "UPI" + "BriefDescription": "Instructions per retired mispredicts for conditional non-taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_NTAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "MetricThreshold": "tma_info_ipmisp_cond_ntaken < 200" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "tma_retiring * SLOTS / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW", - "MetricName": "UpTB" + "BriefDescription": "Instructions per retired mispredicts for conditional taken branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_cond_taken", + "MetricThreshold": "tma_info_ipmisp_cond_taken < 200" }, { - "BriefDescription": "Cycles Per Instruction (per Logical Processor)", - "MetricExpr": "1 / IPC", - "MetricGroup": "Mem;Pipeline", - "MetricName": "CPI" + "BriefDescription": "Instructions per retired mispredicts for indirect CALL or JMP branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_indirect", + "MetricThreshold": "tma_info_ipmisp_indirect < 1e3" }, { - "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "Pipeline", - "MetricName": "CLKS" + "BriefDescription": "Instructions per retired mispredicts for return branches (lower number means higher occurrence rate).", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RET", + "MetricGroup": "Bad;BrMispredicts", + "MetricName": "tma_info_ipmisp_ret", + "MetricThreshold": "tma_info_ipmisp_ret < 500" }, { - "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", - "MetricExpr": "TOPDOWN.SLOTS", - "MetricGroup": "tma_L1_group", - "MetricName": "SLOTS" + "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;BadSpec;BrMispredicts", + "MetricName": "tma_info_ipmispredict", + "MetricThreshold": "tma_info_ipmispredict < 200" }, { - "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", - "MetricExpr": "(SLOTS / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", - "MetricGroup": "SMT;tma_L1_group", - "MetricName": "Slots_Utilization" + "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", + "MetricGroup": "InsType", + "MetricName": "tma_info_ipstore", + "MetricThreshold": "tma_info_ipstore < 8" }, { - "BriefDescription": "The ratio of Executed- by Issued-Uops", - "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY", - "MetricGroup": "Cor;Pipeline", - "MetricName": "Execute_per_Issue", - "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage." + "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", + "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", + "MetricGroup": "Prefetches", + "MetricName": "tma_info_ipswpf", + "MetricThreshold": "tma_info_ipswpf < 100" }, { - "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / CORE_CLKS", - "MetricGroup": "Ret;SMT;tma_L1_group", - "MetricName": "CoreIPC" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO;tma_issueFB", + "MetricName": "tma_info_iptb", + "MetricThreshold": "tma_info_iptb < 11", + "PublicDescription": "Instruction per taken branch. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_lcp" }, { - "BriefDescription": "Floating Point Operations Per Cycle", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / CORE_CLKS", - "MetricGroup": "Flops;Ret", - "MetricName": "FLOPc" - }, - { - "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width)", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)) / (2 * CORE_CLKS)", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "FP_Arith_Utilization", - "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)." + "BriefDescription": "Instructions per speculative Unknown Branch Misprediction (BAClear) (lower number means higher occurrence rate)", + "MetricExpr": "tma_info_instructions / BACLEARS.ANY", + "MetricGroup": "Fed", + "MetricName": "tma_info_ipunknown_branch" }, { - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core", - "MetricExpr": "UOPS_EXECUTED.THREAD / (UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", - "MetricGroup": "Backend;Cor;Pipeline;PortsUtil", - "MetricName": "ILP" + "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", + "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_jump" }, { - "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts", - "MetricExpr": "((1 - tma_core_bound / tma_ports_utilization if tma_core_bound < tma_ports_utilization else 1) if SMT_2T_Utilization > 0.5 else 0)", - "MetricGroup": "Cor;SMT", - "MetricName": "Core_Bound_Likely" + "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_cpi" }, { - "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core", - "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED", - "MetricGroup": "SMT", - "MetricName": "CORE_CLKS" + "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "OS", + "MetricName": "tma_info_kernel_utilization", + "MetricThreshold": "tma_info_kernel_utilization > 0.05" }, { - "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS", - "MetricGroup": "InsType", - "MetricName": "IpLoad" + "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw" }, { - "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES", - "MetricGroup": "InsType", - "MetricName": "IpStore" + "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", + "MetricExpr": "tma_info_l1d_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l1d_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Branches;Fed;InsType", - "MetricName": "IpBranch" + "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki" }, { - "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "IpCall" + "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l1mpki_load" }, { - "BriefDescription": "Instruction per taken branch", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO", - "MetricName": "IpTB" + "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw" }, { - "BriefDescription": "Branch instructions per taken branch. ", - "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN", - "MetricGroup": "Branches;Fed;PGO", - "MetricName": "BpTkBranch" + "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", + "MetricExpr": "tma_info_l2_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l2_cache_fill_bw_1t" }, { - "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;InsType", - "MetricName": "IpFLOP" + "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_all" }, { - "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE))", - "MetricGroup": "Flops;InsType", - "MetricName": "IpArith", - "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW." + "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2hpki_load" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_SP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "Backend;CacheMisses;Mem", + "MetricName": "tma_info_l2mpki" }, { - "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", - "MetricGroup": "Flops;FpScalar;InsType", - "MetricName": "IpArith_Scalar_DP", - "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem;Offcore", + "MetricName": "tma_info_l2mpki_all" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX128", - "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache true code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * FRONTEND_RETIRED.L2_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX256", - "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache speculative code cacheline misses per kilo instruction", + "MetricExpr": "1e3 * L2_RQSTS.CODE_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "IcMiss", + "MetricName": "tma_info_l2mpki_code_all" }, { - "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / (FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE)", - "MetricGroup": "Flops;FpVector;InsType", - "MetricName": "IpArith_AVX512", - "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting." + "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", + "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l2mpki_load" }, { - "BriefDescription": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@", - "MetricGroup": "Prefetches", - "MetricName": "IpSWPF" + "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw" }, { - "BriefDescription": "Total number of retired Instructions Sample with: INST_RETIRED.PREC_DIST", - "MetricExpr": "INST_RETIRED.ANY", - "MetricGroup": "Summary;tma_L1_group", - "MetricName": "Instructions" + "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_access_bw", + "MetricGroup": "Mem;MemoryBW;Offcore", + "MetricName": "tma_info_l3_cache_access_bw_1t" }, { - "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", - "MetricExpr": "tma_retiring * SLOTS / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", - "MetricGroup": "Pipeline;Ret", - "MetricName": "Retire" + "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw" }, { - "BriefDescription": "", - "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@", - "MetricGroup": "Cor;Pipeline;PortsUtil;SMT", - "MetricName": "Execute" + "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", + "MetricExpr": "tma_info_l3_cache_fill_bw", + "MetricGroup": "Mem;MemoryBW", + "MetricName": "tma_info_l3_cache_fill_bw_1t" }, { - "BriefDescription": "Average number of Uops issued by front-end when it issued something", - "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@", - "MetricGroup": "Fed;FetchBW", - "MetricName": "Fetch_UpC" + "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", + "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", + "MetricGroup": "CacheMisses;Mem", + "MetricName": "tma_info_l3mpki" }, { - "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", - "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "Fed;LSD", - "MetricName": "LSD_Coverage" + "BriefDescription": "Average Latency for L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l2_miss_latency" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", - "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)", - "MetricGroup": "DSB;Fed;FetchBW", - "MetricName": "DSB_Coverage" + "BriefDescription": "Average Parallel L2 cache miss demand Loads", + "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=1@", + "MetricGroup": "Memory_BW;Offcore", + "MetricName": "tma_info_load_l2_mlp" }, { - "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.", - "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@", - "MetricGroup": "DSBmiss", - "MetricName": "DSB_Switch_Cost" + "BriefDescription": "Average Latency for L3 cache miss demand Loads", + "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "MetricGroup": "Memory_Lat;Offcore", + "MetricName": "tma_info_load_l3_miss_latency" }, { - "BriefDescription": "Total penalty related to DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.", - "MetricExpr": "100 * (tma_fetch_latency * tma_dsb_switches / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches) + tma_fetch_bandwidth * tma_mite / (tma_dsb + tma_lsd + tma_mite))", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "DSB_Misses" + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", + "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", + "MetricGroup": "Mem;MemoryBound;MemoryLat", + "MetricName": "tma_info_load_miss_real_latency" }, { - "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS", - "MetricGroup": "DSBmiss;Fed", - "MetricName": "IpDSB_Miss_Ret" + "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_LOAD_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_load_stlb_mpki" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)", - "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BadSpec;BrMispredicts", - "MetricName": "IpMispredict" + "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)", + "MetricExpr": "LSD.UOPS / UOPS_ISSUED.ANY", + "MetricGroup": "Fed;LSD", + "MetricName": "tma_info_lsd_coverage" }, { - "BriefDescription": "Branch Misprediction Cost: Fraction of TMA slots wasted per non-speculative branch misprediction (retired JEClear)", - "MetricExpr": "(tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches)) * SLOTS / BR_MISP_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;BrMispredicts", - "MetricName": "Branch_Misprediction_Cost" + "BriefDescription": "Average number of parallel data read requests to external memory", + "MetricExpr": "UNC_ARB_DAT_OCCUPANCY.RD / UNC_ARB_DAT_OCCUPANCY.RD@cmask\\=1@", + "MetricGroup": "Mem;MemoryBW;SoC", + "MetricName": "tma_info_mem_parallel_reads", + "PublicDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches" }, { - "BriefDescription": "Fraction of branches that are non-taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_NT" + "BriefDescription": "Average latency of data read request to external memory (in nanoseconds)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.RD + UNC_ARB_DAT_OCCUPANCY.RD) / UNC_ARB_TRK_REQUESTS.RD", + "MetricGroup": "Mem;MemoryLat;SoC", + "MetricName": "tma_info_mem_read_latency", + "PublicDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches. ([RKL+]memory-controller only)" }, { - "BriefDescription": "Fraction of branches that are taken conditionals", - "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches;CodeGen;PGO", - "MetricName": "Cond_TK" + "BriefDescription": "Average latency of all requests to external memory (in Uncore cycles)", + "MetricExpr": "(UNC_ARB_TRK_OCCUPANCY.ALL + UNC_ARB_DAT_OCCUPANCY.RD) / arb@event\\=0x81\\,umask\\=0x1@", + "MetricGroup": "Mem;SoC", + "MetricName": "tma_info_mem_request_latency" }, { - "BriefDescription": "Fraction of branches that are CALL or RET", - "MetricExpr": "(BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "CallRet" + "BriefDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_bandwidth / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_sq_full / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full))) + tma_l1_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_fb_full / (tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk))", + "MetricGroup": "Mem;MemoryBW;Offcore;tma_issueBW", + "MetricName": "tma_info_memory_bandwidth", + "MetricThreshold": "tma_info_memory_bandwidth > 20", + "PublicDescription": "Total pipeline cost of (external) Memory Bandwidth related bottlenecks. Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_mem_bandwidth, tma_sq_full" }, { - "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps", - "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES", - "MetricGroup": "Bad;Branches", - "MetricName": "Jump" + "BriefDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs)", + "MetricExpr": "100 * tma_memory_bound * (tma_l1_bound / max(tma_memory_bound, tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_load / max(tma_l1_bound, tma_4k_aliasing + tma_dtlb_load + tma_fb_full + tma_lock_latency + tma_split_loads + tma_store_fwd_blk)) + tma_store_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_dtlb_store / (tma_dtlb_store + tma_false_sharing + tma_split_stores + tma_store_latency + tma_streaming_stores)))", + "MetricGroup": "Mem;MemoryTLB;Offcore;tma_issueTLB", + "MetricName": "tma_info_memory_data_tlbs", + "MetricThreshold": "tma_info_memory_data_tlbs > 20", + "PublicDescription": "Total pipeline cost of Memory Address Translation related bottlenecks (data-side TLBs). Related metrics: tma_dtlb_load, tma_dtlb_store" }, { - "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", - "MetricExpr": "1 - (Cond_NT + Cond_TK + CallRet + Jump)", - "MetricGroup": "Bad;Branches", - "MetricName": "Other_Branches" + "BriefDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches)", + "MetricExpr": "100 * tma_memory_bound * (tma_dram_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_mem_latency / (tma_mem_bandwidth + tma_mem_latency)) + tma_l3_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound) * (tma_l3_hit_latency / (tma_contested_accesses + tma_data_sharing + tma_l3_hit_latency + tma_sq_full)) + tma_l2_bound / (tma_dram_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_store_bound))", + "MetricGroup": "Mem;MemoryLat;Offcore;tma_issueLat", + "MetricName": "tma_info_memory_latency", + "MetricThreshold": "tma_info_memory_latency > 20", + "PublicDescription": "Total pipeline cost of Memory Latency related bottlenecks (external memory and off-core caches). Related metrics: tma_l3_hit_latency, tma_mem_latency" }, { - "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)", - "MetricExpr": "L1D_PEND_MISS.PENDING / (MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT)", - "MetricGroup": "Mem;MemoryBound;MemoryLat", - "MetricName": "Load_Miss_Real_Latency" + "BriefDescription": "Total pipeline cost of Branch Misprediction related bottlenecks", + "MetricExpr": "100 * (tma_branch_mispredicts + tma_fetch_latency * tma_mispredicts_resteers / (tma_branch_resteers + tma_dsb_switches + tma_icache_misses + tma_itlb_misses + tma_lcp + tma_ms_switches))", + "MetricGroup": "Bad;BadSpec;BrMispredicts;tma_issueBM", + "MetricName": "tma_info_mispredictions", + "MetricThreshold": "tma_info_mispredictions > 20", + "PublicDescription": "Total pipeline cost of Branch Misprediction related bottlenecks. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_mispredicts_resteers" }, { - "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)", + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss", "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES", "MetricGroup": "Mem;MemoryBW;MemoryBound", - "MetricName": "MLP" + "MetricName": "tma_info_mlp", + "PublicDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI" + "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)", + "MetricExpr": "1 - (tma_info_cond_nt + tma_info_cond_tk + tma_info_callret + tma_info_jump)", + "MetricGroup": "Bad;Branches", + "MetricName": "tma_info_other_branches" }, { - "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L1MPKI_Load" + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * tma_info_core_clks)", + "MetricGroup": "Mem;MemoryTLB", + "MetricName": "tma_info_page_walks_utilization", + "MetricThreshold": "tma_info_page_walks_utilization > 0.5" }, { - "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY", - "MetricGroup": "Backend;CacheMisses;Mem", - "MetricName": "L2MPKI" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", + "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license0_utilization", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem;Offcore", - "MetricName": "L2MPKI_All" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", + "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license1_utilization", + "MetricThreshold": "tma_info_power_license1_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." }, { - "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2MPKI_Load" + "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", + "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / tma_info_core_clks", + "MetricGroup": "Power", + "MetricName": "tma_info_power_license2_utilization", + "MetricThreshold": "tma_info_power_license2_utilization > 0.5", + "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." }, { - "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)", - "MetricExpr": "1e3 * (L2_RQSTS.REFERENCES - L2_RQSTS.MISS) / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_All" + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.", + "MetricExpr": "tma_retiring * tma_info_slots / cpu@UOPS_RETIRED.SLOTS\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ret", + "MetricName": "tma_info_retire" }, { - "BriefDescription": "L2 cache hits per kilo instruction for all demand loads (including speculative)", - "MetricExpr": "1e3 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L2HPKI_Load" + "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)", + "MetricExpr": "TOPDOWN.SLOTS", + "MetricGroup": "TmaL1;tma_L1_group", + "MetricName": "tma_info_slots" }, { - "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "L3MPKI" + "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor", + "MetricExpr": "(tma_info_slots / (TOPDOWN.SLOTS / 2) if #SMT_on else 1)", + "MetricGroup": "SMT;TmaL1;tma_L1_group", + "MetricName": "tma_info_slots_utilization" }, { - "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)", - "MetricExpr": "1e3 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY", - "MetricGroup": "CacheMisses;Mem", - "MetricName": "FB_HPKI" + "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", + "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", + "MetricGroup": "SMT", + "MetricName": "tma_info_smt_2t_utilization" }, { - "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricConstraint": "NO_NMI_WATCHDOG", - "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * CORE_CLKS)", + "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)", + "MetricExpr": "1e3 * DTLB_STORE_MISSES.WALK_COMPLETED / INST_RETIRED.ANY", "MetricGroup": "Mem;MemoryTLB", - "MetricName": "Page_Walks_Utilization" + "MetricName": "tma_info_store_stlb_mpki" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW" + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "tma_info_clks / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "tma_info_turbo_utilization" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW" + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "tma_retiring * tma_info_slots / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;Ret;Retire", + "MetricName": "tma_info_uoppi", + "MetricThreshold": "tma_info_uoppi > 1.05" }, { - "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW" + "BriefDescription": "Instruction per taken branch", + "MetricExpr": "tma_retiring * tma_info_slots / BR_INST_RETIRED.NEAR_TAKEN", + "MetricGroup": "Branches;Fed;FetchBW", + "MetricName": "tma_info_uptb", + "MetricThreshold": "tma_info_uptb < 7.5" }, { - "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / duration_time", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW" + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses", + "MetricExpr": "ICACHE_64B.IFTAG_STALL / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;MemoryTLB;TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Instruction TLB (ITLB) misses. Sample with: FRONTEND_RETIRED.STLB_MISS_PS;FRONTEND_RETIRED.ITLB_MISS_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]", - "MetricExpr": "L1D_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L1D_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache", + "MetricExpr": "max((CYCLE_ACTIVITY.STALLS_MEM_ANY - CYCLE_ACTIVITY.STALLS_L1D_MISS) / tma_info_clks, 0)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_issueL1;tma_issueMC;tma_memory_bound_group", + "MetricName": "tma_l1_bound", + "MetricThreshold": "tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled without loads missing the L1 data cache. The L1 data cache typically has the shortest latency. However; in certain cases like loads blocked on older stores; a load might suffer due to high latency even though it is being satisfied by the L1. Another example is loads who miss in the TLB. These cases are characterized by execution unit stalls; while some non-completed demand load lives in the machine without having that demand load missing the L1 cache. Sample with: MEM_LOAD_RETIRED.L1_HIT_PS;MEM_LOAD_RETIRED.FB_HIT_PS. Related metrics: tma_clears_resteers, tma_machine_clears, tma_microcode_sequencer, tma_ms_switches, tma_ports_utilized_1", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]", - "MetricExpr": "L2_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L2_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) / (MEM_LOAD_RETIRED.L2_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + L1D_PEND_MISS.FB_FULL_PERIODS) * ((CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks)", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l2_bound", + "MetricThreshold": "tma_l2_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to L2 cache accesses by loads. Avoiding cache misses (i.e. L1 misses/L2 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L2_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Fill_BW", - "MetricGroup": "Mem;MemoryBW", - "MetricName": "L3_Cache_Fill_BW_1T" + "BriefDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L2_MISS - CYCLE_ACTIVITY.STALLS_L3_MISS) / tma_info_clks", + "MetricGroup": "CacheMisses;MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_l3_bound", + "MetricThreshold": "tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often the CPU was stalled due to loads accesses to L3 cache or contended with a sibling Core. Avoiding cache misses (i.e. L2 misses/L3 hits) can improve the latency and increase performance. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]", - "MetricExpr": "L3_Cache_Access_BW", - "MetricGroup": "Mem;MemoryBW;Offcore", - "MetricName": "L3_Cache_Access_BW_1T" + "BriefDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited)", + "MetricExpr": "17.5 * tma_info_average_frequency * MEM_LOAD_RETIRED.L3_HIT * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS / 2) / tma_info_clks", + "MetricGroup": "MemoryLat;TopdownL4;tma_L4_group;tma_issueLat;tma_l3_bound_group", + "MetricName": "tma_l3_hit_latency", + "MetricThreshold": "tma_l3_hit_latency > 0.1 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles with demand load accesses that hit the L3 cache under unloaded scenarios (possibly L3 latency limited). Avoiding private cache misses (i.e. L2 misses/L3 hits) will improve the latency; reduce contention with sibling physical cores and increase performance. Note the value of this node may overlap with its siblings. Sample with: MEM_LOAD_RETIRED.L3_HIT_PS. Related metrics: tma_info_memory_latency, tma_mem_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average CPU Utilization", - "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / TSC", - "MetricGroup": "HPC;Summary", - "MetricName": "CPU_Utilization" + "BriefDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs)", + "MetricExpr": "ILD_STALL.LCP / tma_info_clks", + "MetricGroup": "FetchLat;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueFB", + "MetricName": "tma_lcp", + "MetricThreshold": "tma_lcp > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric represents fraction of cycles CPU was stalled due to Length Changing Prefixes (LCPs). Using proper compiler flags or Intel Compiler by default will certainly avoid this. #Link: Optimization Guide about LCP BKMs. Related metrics: tma_dsb_switches, tma_fetch_bandwidth, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb", + "ScaleUnit": "100%" }, { - "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]", - "MetricExpr": "Turbo_Utilization * TSC / 1e9 / duration_time", - "MetricGroup": "Power;Summary", - "MetricName": "Average_Frequency" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation)", + "MetricExpr": "max(0, tma_retiring - tma_heavy_operations)", + "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", + "MetricName": "tma_light_operations", + "MetricThreshold": "tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", + "ScaleUnit": "100%" }, { - "BriefDescription": "Giga Floating Point Operations Per Second", - "MetricExpr": "(FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * (FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE) + 8 * (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1e9 / duration_time", - "MetricGroup": "Cor;Flops;HPC", - "MetricName": "GFLOPs", - "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine." + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations", + "MetricExpr": "UOPS_DISPATCHED.PORT_2_3 / (2 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_load_op_utilization", + "MetricThreshold": "tma_load_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Load operations. Sample with: UOPS_DISPATCHED.PORT_2_3", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average Frequency Utilization relative nominal frequency", - "MetricExpr": "CLKS / CPU_CLK_UNHALTED.REF_TSC", - "MetricGroup": "Power", - "MetricName": "Turbo_Utilization" + "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) DTLB was missed by load accesses, that later on hit in second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_load - tma_load_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_hit", + "MetricThreshold": "tma_load_stlb_hit > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0", - "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License0_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0. This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes." + "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by load accesses, performing a hardware page walk", + "MetricExpr": "DTLB_LOAD_MISSES.WALK_ACTIVE / tma_info_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_load_group", + "MetricName": "tma_load_stlb_miss", + "MetricThreshold": "tma_load_stlb_miss > 0.05 & (tma_dtlb_load > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1", - "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License1_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1. This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions." + "BriefDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(16 * max(0, MEM_INST_RETIRED.LOCK_LOADS - L2_RQSTS.ALL_RFO) + MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES * (10 * L2_RQSTS.RFO_HIT + min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO))) / tma_info_clks", + "MetricGroup": "Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_l1_bound_group", + "MetricName": "tma_lock_latency", + "MetricThreshold": "tma_lock_latency > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles the CPU spent handling cache misses due to lock operations. Due to the microarchitecture handling of locks; they are classified as L1_Bound regardless of what memory source satisfied them. Sample with: MEM_INST_RETIRED.LOCK_LOADS_PS. Related metrics: tma_store_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)", - "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CORE_CLKS", - "MetricGroup": "Power", - "MetricName": "Power_License2_Utilization", - "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX). This includes high current AVX 512-bit instructions." + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit", + "MetricExpr": "(LSD.CYCLES_ACTIVE - LSD.CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "FetchBW;LSD;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_lsd", + "MetricThreshold": "tma_lsd > 0.15 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to LSD (Loop Stream Detector) unit. LSD typically does well sustaining Uop supply. However; in some rare cases; optimal uop-delivery could not be reached for small loops whose size (in terms of number of uops) does not suit well the LSD structure.", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active", - "MetricExpr": "(1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0)", - "MetricGroup": "SMT", - "MetricName": "SMT_2T_Utilization" + "BriefDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears", + "MetricExpr": "max(0, tma_bad_speculation - tma_branch_mispredicts)", + "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", + "MetricName": "tma_machine_clears", + "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", + "ScaleUnit": "100%" }, { - "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD", - "MetricGroup": "OS", - "MetricName": "Kernel_Utilization" + "BriefDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, cpu@OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD\\,cmask\\=4@) / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueBW", + "MetricName": "tma_mem_bandwidth", + "MetricThreshold": "tma_mem_bandwidth > 0.2 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the core's performance was likely hurt due to approaching bandwidth limits of external memory (DRAM). The underlying heuristic assumes that a similar off-core traffic is generated by all IA cores. This metric does not aggregate non-data-read requests by this logical processor; requests from other IA Logical Processors/Physical Cores/sockets; or other non-IA devices like GPU; hence the maximum external memory bandwidth limits may or may not be approached when this metric is flagged (see Uncore counters for that). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_sq_full", + "ScaleUnit": "100%" }, { - "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k", - "MetricGroup": "OS", - "MetricName": "Kernel_CPI" + "BriefDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM)", + "MetricExpr": "min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD) / tma_info_clks - tma_mem_bandwidth", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_dram_bound_group;tma_issueLat", + "MetricName": "tma_mem_latency", + "MetricThreshold": "tma_mem_latency > 0.1 & (tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles where the performance was likely hurt due to latency from external memory (DRAM). This metric does not aggregate requests from other Logical Processors/Physical Cores/sockets (see Uncore counters for that). Related metrics: tma_info_memory_latency, tma_l3_hit_latency", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", - "MetricGroup": "HPC;Mem;MemoryBW;SoC", - "MetricName": "DRAM_BW_Use" + "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * tma_backend_bound", + "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", + "ScaleUnit": "100%" }, { - "BriefDescription": "Average number of parallel requests to external memory. Accounts for all requests", - "MetricExpr": "UNC_ARB_TRK_OCCUPANCY.ALL / arb@event\\=0x81\\,umask\\=0x1@", - "MetricGroup": "Mem;SoC", - "MetricName": "MEM_Parallel_Requests" + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring memory operations -- uops for memory load or store accesses.", + "MetricExpr": "tma_light_operations * MEM_INST_RETIRED.ANY / INST_RETIRED.ANY", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_memory_operations", + "MetricThreshold": "tma_memory_operations > 0.1 & tma_light_operations > 0.6", + "ScaleUnit": "100%" }, { - "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]", - "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u", - "MetricGroup": "Branches;OS", - "MetricName": "IpFarBranch" + "BriefDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit", + "MetricExpr": "tma_retiring * tma_info_slots / UOPS_ISSUED.ANY * IDQ.MS_UOPS / tma_info_slots", + "MetricGroup": "MicroSeq;TopdownL3;tma_L3_group;tma_heavy_operations_group;tma_issueMC;tma_issueMS", + "MetricName": "tma_microcode_sequencer", + "MetricThreshold": "tma_microcode_sequencer > 0.05 & tma_heavy_operations > 0.1", + "PublicDescription": "This metric represents fraction of slots the CPU was retiring uops fetched by the Microcode Sequencer (MS) unit. The MS is used for CISC instructions not supported by the default decoders (like repeat move strings; or CPUID); or by microcode assists used to address some operation modes (like in Floating Point assists). These cases can often be avoided. Sample with: IDQ.MS_UOPS. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_ms_switches", + "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per core", - "MetricExpr": "cstate_core@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Core_Residency", + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage", + "MetricExpr": "BR_MISP_RETIRED.ALL_BRANCHES / (BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT) * INT_MISC.CLEAR_RESTEER_CYCLES / tma_info_clks", + "MetricGroup": "BadSpec;BrMispredicts;TopdownL4;tma_L4_group;tma_branch_resteers_group;tma_issueBM", + "MetricName": "tma_mispredicts_resteers", + "MetricThreshold": "tma_mispredicts_resteers > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to Branch Resteers as a result of Branch Misprediction at execution stage. Sample with: INT_MISC.CLEAR_RESTEER_CYCLES. Related metrics: tma_branch_mispredicts, tma_info_branch_misprediction_cost, tma_info_mispredictions", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per core", - "MetricExpr": "cstate_core@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Core_Residency", + "BriefDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline)", + "MetricExpr": "(IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / tma_info_core_clks / 2", + "MetricGroup": "DSBmiss;FetchBW;TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", + "MetricName": "tma_mite", + "MetricThreshold": "tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35)", + "PublicDescription": "This metric represents Core fraction of cycles in which CPU was likely limited due to the MITE pipeline (the legacy decode pipeline). This pipeline is used for code that was not pre-cached in the DSB or LSD. For example; inefficiencies due to asymmetric decoders; use of long immediate or LCP can manifest as MITE fetch bandwidth bottleneck. Sample with: FRONTEND_RETIRED.ANY_DSB_MISS", "ScaleUnit": "100%" }, { - "BriefDescription": "C2 residency percent per package", - "MetricExpr": "cstate_pkg@c2\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C2_Pkg_Residency", + "BriefDescription": "This metric represents fraction of cycles where (only) 4 uops were delivered by the MITE pipeline", + "MetricExpr": "(cpu@IDQ.MITE_UOPS\\,cmask\\=4@ - cpu@IDQ.MITE_UOPS\\,cmask\\=5@) / tma_info_clks", + "MetricGroup": "DSBmiss;FetchBW;TopdownL4;tma_L4_group;tma_mite_group", + "MetricName": "tma_mite_4wide", + "MetricThreshold": "tma_mite_4wide > 0.05 & (tma_mite > 0.1 & (tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35))", "ScaleUnit": "100%" }, { - "BriefDescription": "C3 residency percent per package", - "MetricExpr": "cstate_pkg@c3\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C3_Pkg_Residency", + "BriefDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued", + "MetricExpr": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH / UOPS_ISSUED.ANY", + "MetricGroup": "TopdownL5;tma_L5_group;tma_issueMV;tma_ports_utilized_0_group", + "MetricName": "tma_mixing_vectors", + "MetricThreshold": "tma_mixing_vectors > 0.05", + "PublicDescription": "The Mixing_Vectors metric gives the percentage of injected blend uops out of all uops issued. Usually a Mixing_Vectors over 5% is worth investigating. Read more in Appendix B1 of the Optimizations Guide for this topic. Related metrics: tma_ms_switches", "ScaleUnit": "100%" }, { - "BriefDescription": "C6 residency percent per package", - "MetricExpr": "cstate_pkg@c6\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C6_Pkg_Residency", + "BriefDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS)", + "MetricExpr": "3 * IDQ.MS_SWITCHES / tma_info_clks", + "MetricGroup": "FetchLat;MicroSeq;TopdownL3;tma_L3_group;tma_fetch_latency_group;tma_issueMC;tma_issueMS;tma_issueMV;tma_issueSO", + "MetricName": "tma_ms_switches", + "MetricThreshold": "tma_ms_switches > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15)", + "PublicDescription": "This metric estimates the fraction of cycles when the CPU was stalled due to switches of uop delivery to the Microcode Sequencer (MS). Commonly used instructions are optimized for delivery by the DSB (decoded i-cache) or MITE (legacy instruction decode) pipelines. Certain operations cannot be handled natively by the execution pipeline; and must be performed by microcode (small programs injected into the execution stream). Switching to the MS too often can negatively impact performance. The MS is designated to deliver long uop flows required by CISC instructions like CPUID; or uncommon conditions like Floating Point Assists when dealing with Denormals. Sample with: IDQ.MS_SWITCHES. Related metrics: tma_clears_resteers, tma_l1_bound, tma_machine_clears, tma_microcode_sequencer, tma_mixing_vectors, tma_serializing_operation", "ScaleUnit": "100%" }, { - "BriefDescription": "C7 residency percent per package", - "MetricExpr": "cstate_pkg@c7\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C7_Pkg_Residency", + "BriefDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions", + "MetricExpr": "tma_light_operations * INST_RETIRED.NOP / (tma_retiring * tma_info_slots)", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_nop_instructions", + "MetricThreshold": "tma_nop_instructions > 0.1 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents fraction of slots where the CPU was retiring NOP (no op) instructions. Compilers often use NOPs for certain address alignments - e.g. start address of a function or loop body. Sample with: INST_RETIRED.NOP", "ScaleUnit": "100%" }, { - "BriefDescription": "C8 residency percent per package", - "MetricExpr": "cstate_pkg@c8\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C8_Pkg_Residency", + "BriefDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes", + "MetricExpr": "max(0, tma_light_operations - (tma_fp_arith + tma_memory_operations + tma_branch_instructions + tma_nop_instructions))", + "MetricGroup": "Pipeline;TopdownL3;tma_L3_group;tma_light_operations_group", + "MetricName": "tma_other_light_ops", + "MetricThreshold": "tma_other_light_ops > 0.3 & tma_light_operations > 0.6", + "PublicDescription": "This metric represents the remaining light uops fraction the CPU has executed - remaining means not covered by other sibling nodes. May undercount due to FMA double counting", "ScaleUnit": "100%" }, { - "BriefDescription": "C9 residency percent per package", - "MetricExpr": "cstate_pkg@c9\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C9_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch)", + "MetricExpr": "UOPS_DISPATCHED.PORT_0 / tma_info_core_clks", + "MetricGroup": "Compute;TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_0", + "MetricThreshold": "tma_port_0 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 0 ([SNB+] ALU; [HSW+] ALU and 2nd branch). Sample with: UOPS_DISPATCHED.PORT_0. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_1, tma_port_5, tma_port_6, tma_ports_utilized_2", "ScaleUnit": "100%" }, { - "BriefDescription": "C10 residency percent per package", - "MetricExpr": "cstate_pkg@c10\\-residency@ / TSC", - "MetricGroup": "Power", - "MetricName": "C10_Pkg_Residency", + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_1 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_1", + "MetricThreshold": "tma_port_1 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 1 (ALU). Sample with: UOPS_DISPATCHED.PORT_1. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_5, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_5 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_5", + "MetricThreshold": "tma_port_5 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 5 ([SNB+] Branches and ALU; [HSW+] ALU). Sample with: UOPS_DISPATCHED.PORT_5. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_6, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU)", + "MetricExpr": "UOPS_DISPATCHED.PORT_6 / tma_info_core_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_alu_op_utilization_group;tma_issue2P", + "MetricName": "tma_port_6", + "MetricThreshold": "tma_port_6 > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port 6 ([HSW+]Primary Branch and simple ALU). Sample with: UOPS_DISPATCHED.PORT_6. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_ports_utilized_2", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related)", + "MetricExpr": "((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / tma_info_clks if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / tma_info_clks)", + "MetricGroup": "PortsUtil;TopdownL3;tma_L3_group;tma_core_bound_group", + "MetricName": "tma_ports_utilization", + "MetricThreshold": "tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates fraction of cycles the CPU performance was potentially limited due to Core computation issues (non divider-related). Two distinct categories can be attributed into this metric: (1) heavy data-dependency among contiguous instructions would manifest in this metric - such cases are often referred to as low Instruction Level Parallelism (ILP). (2) Contention on some hardware execution unit other than Divider. For example; when there are too many multiply operations.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ / tma_info_clks + tma_serializing_operation * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_0", + "MetricThreshold": "tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed no uops on any execution port (Logical Processor cycles since ICL, Physical Core cycles otherwise). Long-latency instructions like divides may contribute to this metric.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.1_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issueL1;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_1", + "MetricThreshold": "tma_ports_utilized_1 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles where the CPU executed total of 1 uop per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). This can be due to heavy data-dependency among software instructions; or over oversubscribing a particular hardware resource. In some other cases with high 1_Port_Utilized and L1_Bound; this metric can point to L1 data-cache latency bottleneck that may not necessarily manifest with complete execution starvation (due to the short L1 latency e.g. walking a linked list) - looking at the assembly can be helpful. Sample with: EXE_ACTIVITY.1_PORTS_UTIL. Related metrics: tma_l1_bound", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "EXE_ACTIVITY.2_PORTS_UTIL / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_issue2P;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_2", + "MetricThreshold": "tma_ports_utilized_2 > 0.15 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 2 uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Loop Vectorization -most compilers feature auto-Vectorization options today- reduces pressure on the execution ports as multiple elements are calculated with same uop. Sample with: EXE_ACTIVITY.2_PORTS_UTIL. Related metrics: tma_fp_scalar, tma_fp_vector, tma_fp_vector_128b, tma_fp_vector_256b, tma_fp_vector_512b, tma_port_0, tma_port_1, tma_port_5, tma_port_6", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise)", + "MetricExpr": "UOPS_EXECUTED.CYCLES_GE_3 / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL4;tma_L4_group;tma_ports_utilization_group", + "MetricName": "tma_ports_utilized_3m", + "MetricThreshold": "tma_ports_utilized_3m > 0.7 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents fraction of cycles CPU executed total of 3 or more uops per cycle on all execution ports (Logical Processor cycles since ICL, Physical Core cycles otherwise). Sample with: UOPS_EXECUTED.CYCLES_GE_3", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired", + "MetricExpr": "topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", + "MetricName": "tma_retiring", + "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations", + "MetricExpr": "RESOURCE_STALLS.SCOREBOARD / tma_info_clks", + "MetricGroup": "PortsUtil;TopdownL5;tma_L5_group;tma_issueSO;tma_ports_utilized_0_group", + "MetricName": "tma_serializing_operation", + "MetricThreshold": "tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2)))", + "PublicDescription": "This metric represents fraction of cycles the CPU issue-pipeline was stalled due to serializing operations. Instructions like CPUID; WRMSR or LFENCE serialize the out-of-order execution which may limit performance. Sample with: RESOURCE_STALLS.SCOREBOARD. Related metrics: tma_ms_switches", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions", + "MetricExpr": "140 * MISC_RETIRED.PAUSE_INST / tma_info_clks", + "MetricGroup": "TopdownL6;tma_L6_group;tma_serializing_operation_group", + "MetricName": "tma_slow_pause", + "MetricThreshold": "tma_slow_pause > 0.05 & (tma_serializing_operation > 0.1 & (tma_ports_utilized_0 > 0.2 & (tma_ports_utilization > 0.15 & (tma_core_bound > 0.1 & tma_backend_bound > 0.2))))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to PAUSE Instructions. Sample with: MISC_RETIRED.PAUSE_INST", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary", + "MetricExpr": "tma_info_load_miss_real_latency * LD_BLOCKS.NO_SR / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_split_loads", + "MetricThreshold": "tma_split_loads > 0.2 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles handling memory load split accesses - load that cross 64-byte cache line boundary. Sample with: MEM_INST_RETIRED.SPLIT_LOADS_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents rate of split store accesses", + "MetricExpr": "MEM_INST_RETIRED.SPLIT_STORES / tma_info_core_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_issueSpSt;tma_store_bound_group", + "MetricName": "tma_split_stores", + "MetricThreshold": "tma_split_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric represents rate of split store accesses. Consider aligning your data to the 64-byte cache line granularity. Sample with: MEM_INST_RETIRED.SPLIT_STORES_PS. Related metrics: tma_port_4", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors)", + "MetricExpr": "L1D_PEND_MISS.L2_STALL / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueBW;tma_l3_bound_group", + "MetricName": "tma_sq_full", + "MetricThreshold": "tma_sq_full > 0.3 & (tma_l3_bound > 0.05 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric measures fraction of cycles where the Super Queue (SQ) was full taking into account all request-types and both hardware SMT threads (Logical Processors). Related metrics: tma_fb_full, tma_info_dram_bw_use, tma_info_memory_bandwidth, tma_mem_bandwidth", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write", + "MetricExpr": "EXE_ACTIVITY.BOUND_ON_STORES / tma_info_clks", + "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", + "MetricName": "tma_store_bound", + "MetricThreshold": "tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", + "PublicDescription": "This metric estimates how often CPU was stalled due to RFO store memory accesses; RFO store issue a read-for-ownership request before the write. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should RFO stores be a bottleneck. Sample with: MEM_INST_RETIRED.ALL_STORES_PS", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores", + "MetricExpr": "13 * LD_BLOCKS.STORE_FORWARD / tma_info_clks", + "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.1 & (tma_l1_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric roughly estimates fraction of cycles when the memory subsystem had loads blocked since they could not forward data from earlier (in program order) overlapping stores. To streamline memory operations in the pipeline; a load can avoid waiting for memory if a prior in-flight store is writing the data that the load wants to read (store forwarding process). However; in some cases the load may be blocked for a significant time pending the store forward. For example; when the prior store is writing a smaller region than the load is reading.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses", + "MetricExpr": "(L2_RQSTS.RFO_HIT * 10 * (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) + (1 - MEM_INST_RETIRED.LOCK_LOADS / MEM_INST_RETIRED.ALL_STORES) * min(CPU_CLK_UNHALTED.THREAD, OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO)) / tma_info_clks", + "MetricGroup": "MemoryLat;Offcore;TopdownL4;tma_L4_group;tma_issueRFO;tma_issueSL;tma_store_bound_group", + "MetricName": "tma_store_latency", + "MetricThreshold": "tma_store_latency > 0.1 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates fraction of cycles the CPU spent handling L1D store misses. Store accesses usually less impact out-of-order core performance; however; holding resources for longer time can lead into undesired implications (e.g. contention on L1D fill-buffer entries - see FB_Full). Related metrics: tma_fb_full, tma_lock_latency", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations", + "MetricExpr": "(UOPS_DISPATCHED.PORT_4_9 + UOPS_DISPATCHED.PORT_7_8) / (4 * tma_info_core_clks)", + "MetricGroup": "TopdownL5;tma_L5_group;tma_ports_utilized_3m_group", + "MetricName": "tma_store_op_utilization", + "MetricThreshold": "tma_store_op_utilization > 0.6", + "PublicDescription": "This metric represents Core fraction of cycles CPU dispatched uops on execution port for Store operations. Sample with: UOPS_DISPATCHED.PORT_7_8", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric roughly estimates the fraction of cycles where the TLB was missed by store accesses, hitting in the second-level TLB (STLB)", + "MetricExpr": "tma_dtlb_store - tma_store_stlb_miss", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_hit", + "MetricThreshold": "tma_store_stlb_hit > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates the fraction of cycles where the STLB was missed by store accesses, performing a hardware page walk", + "MetricExpr": "DTLB_STORE_MISSES.WALK_ACTIVE / tma_info_core_clks", + "MetricGroup": "MemoryTLB;TopdownL5;tma_L5_group;tma_dtlb_store_group", + "MetricName": "tma_store_stlb_miss", + "MetricThreshold": "tma_store_stlb_miss > 0.05 & (tma_dtlb_store > 0.05 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)))", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores", + "MetricExpr": "9 * OCR.STREAMING_WR.ANY_RESPONSE / tma_info_clks", + "MetricGroup": "MemoryBW;Offcore;TopdownL4;tma_L4_group;tma_issueSmSt;tma_store_bound_group", + "MetricName": "tma_streaming_stores", + "MetricThreshold": "tma_streaming_stores > 0.2 & (tma_store_bound > 0.2 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2))", + "PublicDescription": "This metric estimates how often CPU was stalled due to Streaming store memory accesses; Streaming store optimize out a read request required by RFO stores. Even though store accesses do not typically stall out-of-order CPUs; there are few cases where stores can lead to actual stalls. This metric will be flagged should Streaming stores be a bottleneck. Sample with: OCR.STREAMING_WR.ANY_RESPONSE. Related metrics: tma_fb_full", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears", + "MetricExpr": "10 * BACLEARS.ANY / tma_info_clks", + "MetricGroup": "BigFoot;FetchLat;TopdownL4;tma_L4_group;tma_branch_resteers_group", + "MetricName": "tma_unknown_branches", + "MetricThreshold": "tma_unknown_branches > 0.05 & (tma_branch_resteers > 0.05 & (tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15))", + "PublicDescription": "This metric represents fraction of cycles the CPU was stalled due to new branch address clears. These are fetched branches the Branch Prediction Unit was unable to recognize (e.g. first time the branch is fetched or hitting BTB capacity limit). Sample with: BACLEARS.ANY", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "This metric serves as an approximation of legacy x87 usage", + "MetricExpr": "tma_retiring * UOPS_EXECUTED.X87 / UOPS_EXECUTED.THREAD", + "MetricGroup": "Compute;TopdownL4;tma_L4_group;tma_fp_arith_group", + "MetricName": "tma_x87_use", + "MetricThreshold": "tma_x87_use > 0.1 & (tma_fp_arith > 0.2 & tma_light_operations > 0.6)", + "PublicDescription": "This metric serves as an approximation of legacy x87 usage. It accounts for instructions beyond X87 FP arithmetic operations; hence may be used as a thermometer to avoid X87 high usage and preferably upgrade to modern ISA. See Tip under Tuning Hint.", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Percentage of cycles in aborted transactions.", + "MetricExpr": "max(cpu@cycles\\-t@ - cpu@cycles\\-ct@, 0) / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_aborted_cycles", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@el\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_elision", + "ScaleUnit": "1cycles / elision" + }, + { + "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", + "MetricExpr": "cpu@cycles\\-t@ / cpu@tx\\-start@", + "MetricGroup": "transaction", + "MetricName": "tsx_cycles_per_transaction", + "ScaleUnit": "1cycles / transaction" + }, + { + "BriefDescription": "Percentage of cycles within a transaction region.", + "MetricExpr": "cpu@cycles\\-t@ / cycles", + "MetricGroup": "transaction", + "MetricName": "tsx_transactional_cycles", "ScaleUnit": "100%" } ] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json index e2ea5ccfe3bc..a5a254327ae9 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json @@ -24,7 +24,7 @@ "Unit": "ARB" }, { - "BriefDescription": "Number of coherent read requests sent to memory controller that were issued by any core.", + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", "EventCode": "0x81", "EventName": "UNC_ARB_DAT_REQUESTS.RD", "PerPkg": "1", @@ -40,7 +40,15 @@ "Unit": "ARB" }, { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_REQUESTS.RD", + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", "EventCode": "0x81", "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", "PerPkg": "1", @@ -55,6 +63,14 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", "EventCode": "0x81", @@ -63,6 +79,14 @@ "UMask": "0x1", "Unit": "ARB" }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, { "BriefDescription": "UNC_CLOCK.SOCKET", "EventCode": "0xff", -- GitLab From 1aa52f9490d50cba4a8872f34d297bc8400735b7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:28 -0800 Subject: [PATCH 0032/5631] perf vendor events intel: Refresh westmereep-dp events Update the westmereep-dp events from 3 to 4. Generation was done using https://github.com/intel/perfmon. The most notable change is in corrections to event descriptions. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-32-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json | 2 +- .../perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index bc2c4e756f44..1c6eef118e61 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -28,7 +28,7 @@ GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v54,skylake,core GenuineIntel-6-55-[01234],v1.29,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core GenuineIntel-6-8[CD],v1.10,tigerlake,core -GenuineIntel-6-2C,v3,westmereep-dp,core +GenuineIntel-6-2C,v4,westmereep-dp,core GenuineIntel-6-25,v3,westmereep-sp,core GenuineIntel-6-2F,v3,westmereex,core AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json index 5c897da3cd6b..4dae735fb636 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/cache.json @@ -182,7 +182,7 @@ "UMask": "0x20" }, { - "BriefDescription": "L2 lines alloacated", + "BriefDescription": "L2 lines allocated", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ANY", "SampleAfterValue": "100000", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json index ef635bff1522..f75084309041 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/virtual-memory.json @@ -56,7 +56,7 @@ "UMask": "0x80" }, { - "BriefDescription": "DTLB misses casued by low part of address", + "BriefDescription": "DTLB misses caused by low part of address", "EventCode": "0x49", "EventName": "DTLB_MISSES.PDE_MISS", "SampleAfterValue": "200000", -- GitLab From 77d78b4c19f25810202d7033f4b9d7be2cdc898f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:29 -0800 Subject: [PATCH 0033/5631] perf jevents: Add rand support to metrics rand (reverse and) is useful in the parsing of metric thresholds. Update the documentation on operator precedence to clarify the simple expression parser and python differences wrt binary/logical operators. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-33-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/metric.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 77ea6ff98538..8ec0ba884673 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -44,6 +44,9 @@ class Expression: def __and__(self, other: Union[int, float, 'Expression']) -> 'Operator': return Operator('&', self, other) + def __rand__(self, other: Union[int, float, 'Expression']) -> 'Operator': + return Operator('&', other, self) + def __lt__(self, other: Union[int, float, 'Expression']) -> 'Operator': return Operator('<', self, other) @@ -88,7 +91,10 @@ def _Constify(val: Union[bool, int, float, Expression]) -> Expression: # Simple lookup for operator precedence, used to avoid unnecessary -# brackets. Precedence matches that of python and the simple expression parser. +# brackets. Precedence matches that of the simple expression parser +# but differs from python where comparisons are lower precedence than +# the bitwise &, ^, | but not the logical versions that the expression +# parser doesn't have. _PRECEDENCE = { '|': 0, '^': 1, -- GitLab From 45e8867a962a069763f0978d30f1d7cd82ead0cb Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:30 -0800 Subject: [PATCH 0034/5631] perf jevent: Parse metric thresholds Parse the metric threshold and add to the pmu-events.c file. The metric isn't parsed as the parser uses python's parser and will break the operator precedence. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-34-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 7 ++++++- tools/perf/pmu-events/pmu-events.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index e82dff3a1228..40b9e626fc15 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -51,7 +51,7 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ - 'metric_name', 'metric_group', 'metric_expr', 'desc', + 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... @@ -306,6 +306,9 @@ class JsonEvent: self.metric_expr = None if 'MetricExpr' in jd: self.metric_expr = metric.ParsePerfJson(jd['MetricExpr']).Simplify() + # Note, the metric formula for the threshold isn't parsed as the & + # and > have incorrect precedence. + self.metric_threshold = jd.get('MetricThreshold') arch_std = jd.get('ArchStdEvent') if precise and self.desc and '(Precise Event)' not in self.desc: @@ -362,6 +365,8 @@ class JsonEvent: # Convert parsed metric expressions into a string. Slashes # must be doubled in the file. x = x.ToPerfJson().replace('\\', '\\\\') + if metric and x and attr == 'metric_threshold': + x = x.replace('\\', '\\\\') if attr in _json_enum_attributes: s += x if x else '0' else: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index 57a38e3e5c32..b7dff8f1021f 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -54,6 +54,7 @@ struct pmu_metric { const char *metric_name; const char *metric_group; const char *metric_expr; + const char *metric_threshold; const char *unit; const char *compat; const char *desc; -- GitLab From 62e10d937d6d5d0f100d6d13c17b4376d1466044 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:31 -0800 Subject: [PATCH 0035/5631] perf pmu-events: Test parsing metric thresholds with the fake PMU Test the correctness of metric thresholds by testing them all with the fake PMU logic. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-35-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/pmu-events.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 521557c396bc..db2fed0c6993 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -1021,12 +1021,34 @@ static int test__parsing_fake(struct test_suite *test __maybe_unused, return pmu_for_each_sys_metric(test__parsing_fake_callback, NULL); } +static int test__parsing_threshold_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *data __maybe_unused) +{ + if (!pm->metric_threshold) + return 0; + return metric_parse_fake(pm->metric_name, pm->metric_threshold); +} + +static int test__parsing_threshold(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + int err = 0; + + err = pmu_for_each_core_metric(test__parsing_threshold_callback, NULL); + if (err) + return err; + + return pmu_for_each_sys_metric(test__parsing_threshold_callback, NULL); +} + static struct test_case pmu_events_tests[] = { TEST_CASE("PMU event table sanity", pmu_event_table), TEST_CASE("PMU event map aliases", aliases), TEST_CASE_REASON("Parsing of PMU event table metrics", parsing, "some metrics failed"), TEST_CASE("Parsing of PMU event table metrics with fake PMUs", parsing_fake), + TEST_CASE("Parsing of metric thresholds with fake PMUs", parsing_threshold), { .name = NULL, } }; -- GitLab From c7551a2e33c60189147f84b17934cb5f1784d0dd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:32 -0800 Subject: [PATCH 0036/5631] perf list: Support for printing metric thresholds Add to json output by default. For regular output, only enable with the --detail flag. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-36-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 13 ++++++++++++- tools/perf/util/metricgroup.c | 3 +++ tools/perf/util/print-events.h | 1 + 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 791f513ae5b4..76e1d31a68ee 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -168,6 +168,7 @@ static void default_print_metric(void *ps, const char *desc, const char *long_desc, const char *expr, + const char *threshold, const char *unit __maybe_unused) { struct print_state *print_state = ps; @@ -227,6 +228,11 @@ static void default_print_metric(void *ps, wordwrap(expr, 8, pager_get_columns(), 0); printf("]\n"); } + if (threshold && print_state->detailed) { + printf("%*s", 8, "["); + wordwrap(threshold, 8, pager_get_columns(), 0); + printf("]\n"); + } } struct json_print_state { @@ -367,7 +373,7 @@ static void json_print_event(void *ps, const char *pmu_name, const char *topic, static void json_print_metric(void *ps __maybe_unused, const char *group, const char *name, const char *desc, const char *long_desc, const char *expr, - const char *unit) + const char *threshold, const char *unit) { struct json_print_state *print_state = ps; bool need_sep = false; @@ -388,6 +394,11 @@ static void json_print_metric(void *ps __maybe_unused, const char *group, fix_escape_printf(&buf, "%s\t\"MetricExpr\": \"%S\"", need_sep ? ",\n" : "", expr); need_sep = true; } + if (threshold) { + fix_escape_printf(&buf, "%s\t\"MetricThreshold\": \"%S\"", need_sep ? ",\n" : "", + threshold); + need_sep = true; + } if (unit) { fix_escape_printf(&buf, "%s\t\"ScaleUnit\": \"%S\"", need_sep ? ",\n" : "", unit); need_sep = true; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 868fc9c35606..b1d56a73223d 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -368,6 +368,7 @@ struct mep { const char *metric_desc; const char *metric_long_desc; const char *metric_expr; + const char *metric_threshold; const char *metric_unit; }; @@ -447,6 +448,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm, me->metric_desc = pm->desc; me->metric_long_desc = pm->long_desc; me->metric_expr = pm->metric_expr; + me->metric_threshold = pm->metric_threshold; me->metric_unit = pm->unit; } } @@ -522,6 +524,7 @@ void metricgroup__print(const struct print_callbacks *print_cb, void *print_stat me->metric_desc, me->metric_long_desc, me->metric_expr, + me->metric_threshold, me->metric_unit); next = rb_next(node); rblist__remove_node(&groups, node); diff --git a/tools/perf/util/print-events.h b/tools/perf/util/print-events.h index 716dcf4b4859..e75a3d7e3fe3 100644 --- a/tools/perf/util/print-events.h +++ b/tools/perf/util/print-events.h @@ -23,6 +23,7 @@ struct print_callbacks { const char *desc, const char *long_desc, const char *expr, + const char *threshold, const char *unit); }; -- GitLab From d0a3052f6faefffcb15e93853c06f56207c32743 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:33 -0800 Subject: [PATCH 0037/5631] perf metric: Compute and print threshold values Compute the threshold metric and use it to color the metric value as red or green. The threshold expression is used to generate the set of events as the threshold may require additional events. A later patch make this behavior optional with a --metric-no-threshold flag. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-37-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 24 +++++++++++++++++++++--- tools/perf/util/metricgroup.h | 1 + tools/perf/util/stat-shadow.c | 24 ++++++++++++++++-------- 3 files changed, 38 insertions(+), 11 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index b1d56a73223d..d83885697125 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -129,6 +129,8 @@ struct metric { const char *modifier; /** The expression to parse, for example, "instructions/cycles". */ const char *metric_expr; + /** Optional threshold expression where zero value is green, otherwise red. */ + const char *metric_threshold; /** * The "ScaleUnit" that scales and adds a unit to the metric during * output. @@ -222,6 +224,7 @@ static struct metric *metric__new(const struct pmu_metric *pm, goto out_err; } m->metric_expr = pm->metric_expr; + m->metric_threshold = pm->metric_threshold; m->metric_unit = pm->unit; m->pctx->sctx.user_requested_cpu_list = NULL; if (user_requested_cpu_list) { @@ -901,6 +904,7 @@ static int __add_metric(struct list_head *metric_list, const struct visited_metric *vm; int ret; bool is_root = !root_metric; + const char *expr; struct visited_metric visited_node = { .name = pm->metric_name, .parent = visited, @@ -963,16 +967,29 @@ static int __add_metric(struct list_head *metric_list, * For both the parent and referenced metrics, we parse * all the metric's IDs and add it to the root context. */ - if (expr__find_ids(pm->metric_expr, NULL, root_metric->pctx) < 0) { + ret = 0; + expr = pm->metric_expr; + if (is_root && pm->metric_threshold) { + /* + * Threshold expressions are built off the actual metric. Switch + * to use that in case of additional necessary events. Change + * the visited node name to avoid this being flagged as + * recursion. + */ + assert(strstr(pm->metric_threshold, pm->metric_name)); + expr = pm->metric_threshold; + visited_node.name = "__threshold__"; + } + if (expr__find_ids(expr, NULL, root_metric->pctx) < 0) { /* Broken metric. */ ret = -EINVAL; - } else { + } + if (!ret) { /* Resolve referenced metrics. */ ret = resolve_metric(metric_list, modifier, metric_no_group, user_requested_cpu_list, system_wide, root_metric, &visited_node, table); } - if (ret) { if (is_root) metric__free(root_metric); @@ -1554,6 +1571,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, free(metric_events); goto out; } + expr->metric_threshold = m->metric_threshold; expr->metric_unit = m->metric_unit; expr->metric_events = metric_events; expr->runtime = m->pctx->sctx.runtime; diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 84030321a057..32eb3a5381fb 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -47,6 +47,7 @@ struct metric_expr { const char *metric_expr; /** The name of the meric such as "IPC". */ const char *metric_name; + const char *metric_threshold; /** * The "ScaleUnit" that scales and adds a unit to the metric during * output. For example, "6.4e-05MiB" means to scale the resulting metric diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 806b32156459..a41f186c6ec8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -777,6 +777,7 @@ static int prepare_metric(struct evsel **metric_events, static void generic_metric(struct perf_stat_config *config, const char *metric_expr, + const char *metric_threshold, struct evsel **metric_events, struct metric_ref *metric_refs, char *name, @@ -789,9 +790,10 @@ static void generic_metric(struct perf_stat_config *config, { print_metric_t print_metric = out->print_metric; struct expr_parse_ctx *pctx; - double ratio, scale; + double ratio, scale, threshold; int i; void *ctxp = out->ctx; + const char *color = NULL; pctx = expr__ctx_new(); if (!pctx) @@ -811,6 +813,12 @@ static void generic_metric(struct perf_stat_config *config, char *unit; char metric_bf[64]; + if (metric_threshold && + expr__parse(&threshold, pctx, metric_threshold) == 0) { + color = fpclassify(threshold) == FP_ZERO + ? PERF_COLOR_GREEN : PERF_COLOR_RED; + } + if (metric_unit && metric_name) { if (perf_pmu__convert_scale(metric_unit, &unit, &scale) >= 0) { @@ -823,22 +831,22 @@ static void generic_metric(struct perf_stat_config *config, scnprintf(metric_bf, sizeof(metric_bf), "%s %s", unit, metric_name); - print_metric(config, ctxp, NULL, "%8.1f", + print_metric(config, ctxp, color, "%8.1f", metric_bf, ratio); } else { - print_metric(config, ctxp, NULL, "%8.2f", + print_metric(config, ctxp, color, "%8.2f", metric_name ? metric_name : out->force_header ? name : "", ratio); } } else { - print_metric(config, ctxp, NULL, NULL, + print_metric(config, ctxp, color, /*unit=*/NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); } } else { - print_metric(config, ctxp, NULL, NULL, + print_metric(config, ctxp, color, /*unit=*/NULL, out->force_header ? (metric_name ? metric_name : name) : "", 0); } @@ -1214,9 +1222,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, list_for_each_entry (mexp, &me->head, nd) { if (num++ > 0) out->new_line(config, ctxp); - generic_metric(config, mexp->metric_expr, mexp->metric_events, - mexp->metric_refs, evsel->name, mexp->metric_name, - mexp->metric_unit, mexp->runtime, + generic_metric(config, mexp->metric_expr, mexp->metric_threshold, + mexp->metric_events, mexp->metric_refs, evsel->name, + mexp->metric_name, mexp->metric_unit, mexp->runtime, map_idx, out, st); } } -- GitLab From 798029341baf398b519591f2bba897b08e4cdc27 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:34 -0800 Subject: [PATCH 0038/5631] perf expr: More explicit NAN handling Comparison and logical operations on NAN won't ensure the result is NAN. Ensure NANs are propogated so that threshold expressions like "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15" don't yield a number when the components are NAN. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-38-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.y | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 635e562350c5..250e444bf032 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -127,7 +127,11 @@ static struct ids handle_id(struct expr_parse_ctx *ctx, char *id, if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ assert(LHS.ids == NULL); \ assert(RHS.ids == NULL); \ - RESULT.val = (long)LHS.val OP (long)RHS.val; \ + if (isnan(LHS.val) || isnan(RHS.val)) { \ + RESULT.val = NAN; \ + } else { \ + RESULT.val = (long)LHS.val OP (long)RHS.val; \ + } \ RESULT.ids = NULL; \ } else { \ RESULT = union_expr(LHS, RHS); \ @@ -137,7 +141,11 @@ static struct ids handle_id(struct expr_parse_ctx *ctx, char *id, if (!compute_ids || (is_const(LHS.val) && is_const(RHS.val))) { \ assert(LHS.ids == NULL); \ assert(RHS.ids == NULL); \ - RESULT.val = LHS.val OP RHS.val; \ + if (isnan(LHS.val) || isnan(RHS.val)) { \ + RESULT.val = NAN; \ + } else { \ + RESULT.val = LHS.val OP RHS.val; \ + } \ RESULT.ids = NULL; \ } else { \ RESULT = union_expr(LHS, RHS); \ -- GitLab From 1fd09e299bdd434b259da3ffcfdcae2dfeac9b2e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:35 -0800 Subject: [PATCH 0039/5631] perf metric: Add --metric-no-threshold option Thresholds may need additional events, this can impact things like sharing groups of events to avoid multiplexing. Add a flag to make the threshold calculations optional. The threshold will still be computed if no additional events are necessary. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-39-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 4 +++ tools/perf/tests/expand-cgroup.c | 3 +- tools/perf/tests/parse-metric.c | 1 - tools/perf/tests/pmu-events.c | 4 +-- tools/perf/util/metricgroup.c | 62 ++++++++++++++++++++------------ tools/perf/util/metricgroup.h | 3 +- tools/perf/util/stat-shadow.c | 3 +- tools/perf/util/stat.h | 1 + 8 files changed, 49 insertions(+), 32 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5d18a5a6f662..5e13171a7bba 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1256,6 +1256,8 @@ static struct option stat_options[] = { "don't group metric events, impacts multiplexing"), OPT_BOOLEAN(0, "metric-no-merge", &stat_config.metric_no_merge, "don't try to share events between metrics in a group"), + OPT_BOOLEAN(0, "metric-no-threshold", &stat_config.metric_no_threshold, + "don't try to share events between metrics in a group "), OPT_BOOLEAN(0, "topdown", &topdown_run, "measure top-down statistics"), OPT_UINTEGER(0, "td-level", &stat_config.topdown_level, @@ -1852,6 +1854,7 @@ static int add_default_attributes(void) return metricgroup__parse_groups(evsel_list, "transaction", stat_config.metric_no_group, stat_config.metric_no_merge, + stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, &stat_config.metric_events); @@ -2519,6 +2522,7 @@ int cmd_stat(int argc, const char **argv) metricgroup__parse_groups(evsel_list, metrics, stat_config.metric_no_group, stat_config.metric_no_merge, + stat_config.metric_no_threshold, stat_config.user_requested_cpu_list, stat_config.system_wide, &stat_config.metric_events); diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index 672a27f37060..ec340880a848 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -187,8 +187,7 @@ static int expand_metric_events(void) rblist__init(&metric_events); pme_test = find_core_metrics_table("testarch", "testcpu"); - ret = metricgroup__parse_groups_test(evlist, pme_test, metric_str, - false, false, &metric_events); + ret = metricgroup__parse_groups_test(evlist, pme_test, metric_str, &metric_events); if (ret < 0) { pr_debug("failed to parse '%s' metric\n", metric_str); goto out; diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 9fec6040950c..132c9b945a42 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -98,7 +98,6 @@ static int __compute_metric(const char *name, struct value *vals, /* Parse the metric into metric_events list. */ pme_test = find_core_metrics_table("testarch", "testcpu"); err = metricgroup__parse_groups_test(evlist, pme_test, name, - false, false, &metric_events); if (err) goto out; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index db2fed0c6993..50b99a0f8f59 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -846,9 +846,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, perf_evlist__set_maps(&evlist->core, cpus, NULL); runtime_stat__init(&st); - err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, - false, false, - &metric_events); + err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, &metric_events); if (err) { if (!strcmp(pm->metric_name, "M1") || !strcmp(pm->metric_name, "M2") || !strcmp(pm->metric_name, "M3")) { diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index d83885697125..afb6f2fdc24e 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -771,6 +771,7 @@ struct metricgroup_add_iter_data { int *ret; bool *has_match; bool metric_no_group; + bool metric_no_threshold; const char *user_requested_cpu_list; bool system_wide; struct metric *root_metric; @@ -786,6 +787,7 @@ static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -813,6 +815,7 @@ static int add_metric(struct list_head *metric_list, static int resolve_metric(struct list_head *metric_list, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -861,8 +864,8 @@ static int resolve_metric(struct list_head *metric_list, */ for (i = 0; i < pending_cnt; i++) { ret = add_metric(metric_list, &pending[i].pm, modifier, metric_no_group, - user_requested_cpu_list, system_wide, root_metric, visited, - table); + metric_no_threshold, user_requested_cpu_list, system_wide, + root_metric, visited, table); if (ret) break; } @@ -879,6 +882,7 @@ static int resolve_metric(struct list_head *metric_list, * @metric_no_group: Should events written to events be grouped "{}" or * global. Grouping is the default but due to multiplexing the * user may override. + * @metric_no_threshold: Should threshold expressions be ignored? * @runtime: A special argument for the parser only known at runtime. * @user_requested_cpu_list: Command line specified CPUs to record on. * @system_wide: Are events for all processes recorded. @@ -894,6 +898,7 @@ static int __add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, int runtime, const char *user_requested_cpu_list, bool system_wide, @@ -974,10 +979,12 @@ static int __add_metric(struct list_head *metric_list, * Threshold expressions are built off the actual metric. Switch * to use that in case of additional necessary events. Change * the visited node name to avoid this being flagged as - * recursion. + * recursion. If the threshold events are disabled, just use the + * metric's name as a reference. This allows metric threshold + * computation if there are sufficient events. */ assert(strstr(pm->metric_threshold, pm->metric_name)); - expr = pm->metric_threshold; + expr = metric_no_threshold ? pm->metric_name : pm->metric_threshold; visited_node.name = "__threshold__"; } if (expr__find_ids(expr, NULL, root_metric->pctx) < 0) { @@ -987,8 +994,8 @@ static int __add_metric(struct list_head *metric_list, if (!ret) { /* Resolve referenced metrics. */ ret = resolve_metric(metric_list, modifier, metric_no_group, - user_requested_cpu_list, system_wide, - root_metric, &visited_node, table); + metric_no_threshold, user_requested_cpu_list, + system_wide, root_metric, &visited_node, table); } if (ret) { if (is_root) @@ -1035,6 +1042,7 @@ static int add_metric(struct list_head *metric_list, const struct pmu_metric *pm, const char *modifier, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct metric *root_metric, @@ -1046,9 +1054,9 @@ static int add_metric(struct list_head *metric_list, pr_debug("metric expr %s for %s\n", pm->metric_expr, pm->metric_name); if (!strstr(pm->metric_expr, "?")) { - ret = __add_metric(metric_list, pm, modifier, metric_no_group, 0, - user_requested_cpu_list, system_wide, root_metric, - visited, table); + ret = __add_metric(metric_list, pm, modifier, metric_no_group, + metric_no_threshold, 0, user_requested_cpu_list, + system_wide, root_metric, visited, table); } else { int j, count; @@ -1060,9 +1068,9 @@ static int add_metric(struct list_head *metric_list, */ for (j = 0; j < count && !ret; j++) - ret = __add_metric(metric_list, pm, modifier, metric_no_group, j, - user_requested_cpu_list, system_wide, - root_metric, visited, table); + ret = __add_metric(metric_list, pm, modifier, metric_no_group, + metric_no_threshold, j, user_requested_cpu_list, + system_wide, root_metric, visited, table); } return ret; @@ -1079,8 +1087,8 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_metric *pm, return 0; ret = add_metric(d->metric_list, pm, d->modifier, d->metric_no_group, - d->user_requested_cpu_list, d->system_wide, - d->root_metric, d->visited, d->table); + d->metric_no_threshold, d->user_requested_cpu_list, + d->system_wide, d->root_metric, d->visited, d->table); if (ret) goto out; @@ -1124,6 +1132,7 @@ struct metricgroup__add_metric_data { const char *modifier; const char *user_requested_cpu_list; bool metric_no_group; + bool metric_no_threshold; bool system_wide; bool has_match; }; @@ -1141,8 +1150,9 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, data->has_match = true; ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, - data->user_requested_cpu_list, data->system_wide, - /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); + data->metric_no_threshold, data->user_requested_cpu_list, + data->system_wide, /*root_metric=*/NULL, + /*visited_metrics=*/NULL, table); } return ret; } @@ -1163,7 +1173,7 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, * architecture perf is running upon. */ static int metricgroup__add_metric(const char *metric_name, const char *modifier, - bool metric_no_group, + bool metric_no_group, bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, @@ -1179,6 +1189,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier .metric_name = metric_name, .modifier = modifier, .metric_no_group = metric_no_group, + .metric_no_threshold = metric_no_threshold, .user_requested_cpu_list = user_requested_cpu_list, .system_wide = system_wide, .has_match = false, @@ -1241,6 +1252,7 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier * architecture perf is running upon. */ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct list_head *metric_list, const struct pmu_metrics_table *table) @@ -1259,7 +1271,8 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group, *modifier++ = '\0'; ret = metricgroup__add_metric(metric_name, modifier, - metric_no_group, user_requested_cpu_list, + metric_no_group, metric_no_threshold, + user_requested_cpu_list, system_wide, metric_list, table); if (ret == -EINVAL) pr_err("Cannot find metric or group `%s'\n", metric_name); @@ -1449,6 +1462,7 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, static int parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct perf_pmu *fake_pmu, @@ -1463,7 +1477,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str, if (metric_events_list->nr_entries == 0) metricgroup__rblist_init(metric_events_list); - ret = metricgroup__add_metric_list(str, metric_no_group, + ret = metricgroup__add_metric_list(str, metric_no_group, metric_no_threshold, user_requested_cpu_list, system_wide, &metric_list, table); if (ret) @@ -1598,6 +1612,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct rblist *metric_events) @@ -1608,18 +1623,19 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, return -EINVAL; return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge, - user_requested_cpu_list, system_wide, + metric_no_threshold, user_requested_cpu_list, system_wide, /*fake_pmu=*/NULL, metric_events, table); } int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, const char *str, - bool metric_no_group, - bool metric_no_merge, struct rblist *metric_events) { - return parse_groups(evlist, str, metric_no_group, metric_no_merge, + return parse_groups(evlist, str, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/false, /*user_requested_cpu_list=*/NULL, /*system_wide=*/false, &perf_pmu__fake, metric_events, table); diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 32eb3a5381fb..8d50052c5b4c 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -70,14 +70,13 @@ int metricgroup__parse_groups(struct evlist *perf_evlist, const char *str, bool metric_no_group, bool metric_no_merge, + bool metric_no_threshold, const char *user_requested_cpu_list, bool system_wide, struct rblist *metric_events); int metricgroup__parse_groups_test(struct evlist *evlist, const struct pmu_metrics_table *table, const char *str, - bool metric_no_group, - bool metric_no_merge, struct rblist *metric_events); void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index a41f186c6ec8..77483eeda0d8 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -814,7 +814,8 @@ static void generic_metric(struct perf_stat_config *config, char metric_bf[64]; if (metric_threshold && - expr__parse(&threshold, pctx, metric_threshold) == 0) { + expr__parse(&threshold, pctx, metric_threshold) == 0 && + !isnan(threshold)) { color = fpclassify(threshold) == FP_ZERO ? PERF_COLOR_GREEN : PERF_COLOR_RED; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b1c29156c560..cf2d8aa445f3 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -159,6 +159,7 @@ struct perf_stat_config { bool no_csv_summary; bool metric_no_group; bool metric_no_merge; + bool metric_no_threshold; bool stop_read_counter; bool iostat_run; char *user_requested_cpu_list; -- GitLab From 94b1a603fca78388ef7575411aed4b1fabd843f9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:36 -0800 Subject: [PATCH 0040/5631] perf stat: Add TopdownL1 metric as a default if present When there are no events and on Intel, the topdown events will be added by default if present. To display the metrics associated with these request special handling in stat-shadow.c. To more easily update these metrics use the json metric version via the TopdownL1 group. This makes the handling less platform specific. Modify the metricgroup__has_metric code to also cover metric groups. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-40-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/evlist.c | 6 +++--- tools/perf/arch/x86/util/topdown.c | 30 ------------------------------ tools/perf/arch/x86/util/topdown.h | 1 - tools/perf/builtin-stat.c | 14 ++++++++++++++ tools/perf/util/metricgroup.c | 6 ++---- 5 files changed, 19 insertions(+), 38 deletions(-) diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index cb59ce9b9638..8a7ae4162563 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -59,10 +59,10 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { - if (nr_attrs) - return ___evlist__add_default_attrs(evlist, attrs, nr_attrs); + if (!nr_attrs) + return 0; - return topdown_parse_events(evlist); + return ___evlist__add_default_attrs(evlist, attrs, nr_attrs); } struct evsel *arch_evlist__leader(struct list_head *list) diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index 54810f9acd6f..eb3a7d9652ab 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -9,11 +9,6 @@ #include "topdown.h" #include "evsel.h" -#define TOPDOWN_L1_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}" -#define TOPDOWN_L1_EVENTS_CORE "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/}" -#define TOPDOWN_L2_EVENTS "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}" -#define TOPDOWN_L2_EVENTS_CORE "{slots,cpu_core/topdown-retiring/,cpu_core/topdown-bad-spec/,cpu_core/topdown-fe-bound/,cpu_core/topdown-be-bound/,cpu_core/topdown-heavy-ops/,cpu_core/topdown-br-mispredict/,cpu_core/topdown-fetch-lat/,cpu_core/topdown-mem-bound/}" - /* Check whether there is a PMU which supports the perf metrics. */ bool topdown_sys_has_perf_metrics(void) { @@ -99,28 +94,3 @@ const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn) return pmu_name; } - -int topdown_parse_events(struct evlist *evlist) -{ - const char *topdown_events; - const char *pmu_name; - - if (!topdown_sys_has_perf_metrics()) - return 0; - - pmu_name = arch_get_topdown_pmu_name(evlist, false); - - if (pmu_have_event(pmu_name, "topdown-heavy-ops")) { - if (!strcmp(pmu_name, "cpu_core")) - topdown_events = TOPDOWN_L2_EVENTS_CORE; - else - topdown_events = TOPDOWN_L2_EVENTS; - } else { - if (!strcmp(pmu_name, "cpu_core")) - topdown_events = TOPDOWN_L1_EVENTS_CORE; - else - topdown_events = TOPDOWN_L1_EVENTS; - } - - return parse_event(evlist, topdown_events); -} diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h index 7eb81f042838..46bf9273e572 100644 --- a/tools/perf/arch/x86/util/topdown.h +++ b/tools/perf/arch/x86/util/topdown.h @@ -3,6 +3,5 @@ #define _TOPDOWN_H 1 bool topdown_sys_has_perf_metrics(void); -int topdown_parse_events(struct evlist *evlist); #endif diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 5e13171a7bba..796e98e453f6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1996,6 +1996,7 @@ static int add_default_attributes(void) stat_config.topdown_level = TOPDOWN_MAX_LEVEL; if (!evsel_list->core.nr_entries) { + /* No events so add defaults. */ if (target__has_cpu(&target)) default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK; @@ -2011,6 +2012,19 @@ static int add_default_attributes(void) } if (evlist__add_default_attrs(evsel_list, default_attrs1) < 0) return -1; + /* + * Add TopdownL1 metrics if they exist. To minimize + * multiplexing, don't request threshold computation. + */ + if (metricgroup__has_metric("TopdownL1") && + metricgroup__parse_groups(evsel_list, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) return -1; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index afb6f2fdc24e..64a35f2787dc 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1647,10 +1647,8 @@ static int metricgroup__has_metric_callback(const struct pmu_metric *pm, { const char *metric = vdata; - if (!pm->metric_expr) - return 0; - - if (match_metric(pm->metric_name, metric)) + if (match_metric(pm->metric_name, metric) || + match_metric(pm->metric_group, metric)) return 1; return 0; -- GitLab From 1647cd5b8802698fb49ccb851b07b098520b5092 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:37 -0800 Subject: [PATCH 0041/5631] perf stat: Implement --topdown using json metrics Request the topdown metric group of a level with the metrics in the group 'TopdownL' rather than through specific events. As more topdown levels are supported this way, such as 6 on Intel Ice Lake, default to just showing the level 1 metrics. This can be overridden using '--td-level'. Rather than determine the maximum topdown level from sysfs, use the metric group names. Remove some now unused topdown code. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-41-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/topdown.c | 48 +----------- tools/perf/builtin-stat.c | 118 +++++------------------------ tools/perf/util/metricgroup.c | 31 ++++++++ tools/perf/util/metricgroup.h | 1 + tools/perf/util/topdown.c | 68 +---------------- tools/perf/util/topdown.h | 11 +-- 6 files changed, 58 insertions(+), 219 deletions(-) diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c index eb3a7d9652ab..9ad5e5c7bd27 100644 --- a/tools/perf/arch/x86/util/topdown.c +++ b/tools/perf/arch/x86/util/topdown.c @@ -1,11 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include #include "api/fs/fs.h" +#include "util/evsel.h" #include "util/pmu.h" #include "util/topdown.h" -#include "util/evlist.h" -#include "util/debug.h" -#include "util/pmu-hybrid.h" #include "topdown.h" #include "evsel.h" @@ -33,30 +30,6 @@ bool topdown_sys_has_perf_metrics(void) return has_perf_metrics; } -/* - * Check whether we can use a group for top down. - * Without a group may get bad results due to multiplexing. - */ -bool arch_topdown_check_group(bool *warn) -{ - int n; - - if (sysctl__read_int("kernel/nmi_watchdog", &n) < 0) - return false; - if (n > 0) { - *warn = true; - return false; - } - return true; -} - -void arch_topdown_group_warn(void) -{ - fprintf(stderr, - "nmi_watchdog enabled with topdown. May give wrong results.\n" - "Disable with echo 0 > /proc/sys/kernel/nmi_watchdog\n"); -} - #define TOPDOWN_SLOTS 0x0400 /* @@ -65,7 +38,6 @@ void arch_topdown_group_warn(void) * Only Topdown metric supports sample-read. The slots * event must be the leader of the topdown group. */ - bool arch_topdown_sample_read(struct evsel *leader) { if (!evsel__sys_has_perf_metrics(leader)) @@ -76,21 +48,3 @@ bool arch_topdown_sample_read(struct evsel *leader) return false; } - -const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn) -{ - const char *pmu_name; - - if (!perf_pmu__has_hybrid()) - return "cpu"; - - if (!evlist->hybrid_pmu_name) { - if (warn) - pr_warning("WARNING: default to use cpu_core topdown events\n"); - evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu("core"); - } - - pmu_name = evlist->hybrid_pmu_name; - - return pmu_name; -} diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 796e98e453f6..bdb1ef4fc6ad 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -124,39 +124,6 @@ static const char * transaction_limited_attrs = { "}" }; -static const char * topdown_attrs[] = { - "topdown-total-slots", - "topdown-slots-retired", - "topdown-recovery-bubbles", - "topdown-fetch-bubbles", - "topdown-slots-issued", - NULL, -}; - -static const char *topdown_metric_attrs[] = { - "slots", - "topdown-retiring", - "topdown-bad-spec", - "topdown-fe-bound", - "topdown-be-bound", - NULL, -}; - -static const char *topdown_metric_L2_attrs[] = { - "slots", - "topdown-retiring", - "topdown-bad-spec", - "topdown-fe-bound", - "topdown-be-bound", - "topdown-heavy-ops", - "topdown-br-mispredict", - "topdown-fetch-lat", - "topdown-mem-bound", - NULL, -}; - -#define TOPDOWN_MAX_LEVEL 2 - static const char *smi_cost_attrs = { "{" "msr/aperf/," @@ -1914,86 +1881,41 @@ static int add_default_attributes(void) } if (topdown_run) { - const char **metric_attrs = topdown_metric_attrs; - unsigned int max_level = 1; - char *str = NULL; - bool warn = false; - const char *pmu_name = arch_get_topdown_pmu_name(evsel_list, true); + unsigned int max_level = metricgroups__topdown_max_level(); + char str[] = "TopdownL1"; if (!force_metric_only) stat_config.metric_only = true; - if (pmu_have_event(pmu_name, topdown_metric_L2_attrs[5])) { - metric_attrs = topdown_metric_L2_attrs; - max_level = 2; + if (!max_level) { + pr_err("Topdown requested but the topdown metric groups aren't present.\n" + "(See perf list the metric groups have names like TopdownL1)"); + return -1; } - if (stat_config.topdown_level > max_level) { pr_err("Invalid top-down metrics level. The max level is %u.\n", max_level); return -1; } else if (!stat_config.topdown_level) - stat_config.topdown_level = max_level; + stat_config.topdown_level = 1; - if (topdown_filter_events(metric_attrs, &str, 1, pmu_name) < 0) { - pr_err("Out of memory\n"); - return -1; - } - - if (metric_attrs[0] && str) { - if (!stat_config.interval && !stat_config.metric_only) { - fprintf(stat_config.output, - "Topdown accuracy may decrease when measuring long periods.\n" - "Please print the result regularly, e.g. -I1000\n"); - } - goto setup_metrics; - } - - zfree(&str); - - if (stat_config.aggr_mode != AGGR_GLOBAL && - stat_config.aggr_mode != AGGR_CORE) { - pr_err("top down event configuration requires --per-core mode\n"); - return -1; - } - stat_config.aggr_mode = AGGR_CORE; - if (nr_cgroups || !target__has_cpu(&target)) { - pr_err("top down event configuration requires system-wide mode (-a)\n"); - return -1; - } - - if (topdown_filter_events(topdown_attrs, &str, - arch_topdown_check_group(&warn), - pmu_name) < 0) { - pr_err("Out of memory\n"); - return -1; + if (!stat_config.interval && !stat_config.metric_only) { + fprintf(stat_config.output, + "Topdown accuracy may decrease when measuring long periods.\n" + "Please print the result regularly, e.g. -I1000\n"); } - - if (topdown_attrs[0] && str) { - struct parse_events_error errinfo; - if (warn) - arch_topdown_group_warn(); -setup_metrics: - parse_events_error__init(&errinfo); - err = parse_events(evsel_list, str, &errinfo); - if (err) { - fprintf(stderr, - "Cannot set up top down events %s: %d\n", - str, err); - parse_events_error__print(&errinfo, str); - parse_events_error__exit(&errinfo); - free(str); - return -1; - } - parse_events_error__exit(&errinfo); - } else { - fprintf(stderr, "System does not support topdown\n"); + str[8] = stat_config.topdown_level + '0'; + if (metricgroup__parse_groups(evsel_list, str, + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) return -1; - } - free(str); } if (!stat_config.topdown_level) - stat_config.topdown_level = TOPDOWN_MAX_LEVEL; + stat_config.topdown_level = 1; if (!evsel_list->core.nr_entries) { /* No events so add defaults. */ diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 64a35f2787dc..de6dd527a2ba 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1665,6 +1665,37 @@ bool metricgroup__has_metric(const char *metric) (void *)metric) ? true : false; } +static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, + const struct pmu_metrics_table *table __maybe_unused, + void *data) +{ + unsigned int *max_level = data; + unsigned int level; + const char *p = strstr(pm->metric_group, "TopdownL"); + + if (!p || p[8] == '\0') + return 0; + + level = p[8] - '0'; + if (level > *max_level) + *max_level = level; + + return 0; +} + +unsigned int metricgroups__topdown_max_level(void) +{ + unsigned int max_level = 0; + const struct pmu_metrics_table *table = pmu_metrics_table__find(); + + if (!table) + return false; + + pmu_metrics_table_for_each_metric(table, metricgroup__topdown_max_level_callback, + &max_level); + return max_level; +} + int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, struct rblist *new_metric_events, struct rblist *old_metric_events) diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h index 8d50052c5b4c..77472e35705e 100644 --- a/tools/perf/util/metricgroup.h +++ b/tools/perf/util/metricgroup.h @@ -81,6 +81,7 @@ int metricgroup__parse_groups_test(struct evlist *evlist, void metricgroup__print(const struct print_callbacks *print_cb, void *print_state); bool metricgroup__has_metric(const char *metric); +unsigned int metricgroups__topdown_max_level(void); int arch_get_runtimeparam(const struct pmu_metric *pm); void metricgroup__rblist_exit(struct rblist *metric_events); diff --git a/tools/perf/util/topdown.c b/tools/perf/util/topdown.c index 1090841550f7..18fd5fed5d1a 100644 --- a/tools/perf/util/topdown.c +++ b/tools/perf/util/topdown.c @@ -1,74 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include "pmu.h" -#include "pmu-hybrid.h" #include "topdown.h" - -int topdown_filter_events(const char **attr, char **str, bool use_group, - const char *pmu_name) -{ - int off = 0; - int i; - int len = 0; - char *s; - bool is_hybrid = perf_pmu__is_hybrid(pmu_name); - - for (i = 0; attr[i]; i++) { - if (pmu_have_event(pmu_name, attr[i])) { - if (is_hybrid) - len += strlen(attr[i]) + strlen(pmu_name) + 3; - else - len += strlen(attr[i]) + 1; - attr[i - off] = attr[i]; - } else - off++; - } - attr[i - off] = NULL; - - *str = malloc(len + 1 + 2); - if (!*str) - return -1; - s = *str; - if (i - off == 0) { - *s = 0; - return 0; - } - if (use_group) - *s++ = '{'; - for (i = 0; attr[i]; i++) { - if (!is_hybrid) - strcpy(s, attr[i]); - else - sprintf(s, "%s/%s/", pmu_name, attr[i]); - s += strlen(s); - *s++ = ','; - } - if (use_group) { - s[-1] = '}'; - *s = 0; - } else - s[-1] = 0; - return 0; -} - -__weak bool arch_topdown_check_group(bool *warn) -{ - *warn = false; - return false; -} - -__weak void arch_topdown_group_warn(void) -{ -} +#include __weak bool arch_topdown_sample_read(struct evsel *leader __maybe_unused) { return false; } - -__weak const char *arch_get_topdown_pmu_name(struct evlist *evlist - __maybe_unused, - bool warn __maybe_unused) -{ - return "cpu"; -} diff --git a/tools/perf/util/topdown.h b/tools/perf/util/topdown.h index f9531528c559..1996c5fedcd7 100644 --- a/tools/perf/util/topdown.h +++ b/tools/perf/util/topdown.h @@ -1,14 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef TOPDOWN_H #define TOPDOWN_H 1 -#include "evsel.h" -#include "evlist.h" -bool arch_topdown_check_group(bool *warn); -void arch_topdown_group_warn(void); +#include + +struct evsel; + bool arch_topdown_sample_read(struct evsel *leader); -const char *arch_get_topdown_pmu_name(struct evlist *evlist, bool warn); -int topdown_filter_events(const char **attr, char **str, bool use_group, - const char *pmu_name); #endif -- GitLab From 7b86475f02ac7d198fc52cfa780f8b93b17321ad Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:38 -0800 Subject: [PATCH 0042/5631] perf stat: Remove topdown event special handling Now the events are computed from json metrics, the hard coded logic can be removed. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-42-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 346 ---------------------------------- tools/perf/util/stat.c | 13 -- tools/perf/util/stat.h | 26 --- 3 files changed, 385 deletions(-) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 77483eeda0d8..5189756bf16d 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -241,45 +241,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_TRANSACTION, map_idx, count, &rsd); else if (perf_stat_evsel__is(counter, ELISION_START)) update_runtime_stat(st, STAT_ELISION, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS)) - update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED)) - update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED)) - update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES)) - update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES)) - update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING)) - update_runtime_stat(st, STAT_TOPDOWN_RETIRING, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC)) - update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS)) - update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT)) - update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT)) - update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT, - map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND)) - update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND, - map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); @@ -524,156 +485,6 @@ static void print_ll_cache_misses(struct perf_stat_config *config, out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); } -/* - * High level "TopDown" CPU core pipe line bottleneck break down. - * - * Basic concept following - * Yasin, A Top Down Method for Performance analysis and Counter architecture - * ISPASS14 - * - * The CPU pipeline is divided into 4 areas that can be bottlenecks: - * - * Frontend -> Backend -> Retiring - * BadSpeculation in addition means out of order execution that is thrown away - * (for example branch mispredictions) - * Frontend is instruction decoding. - * Backend is execution, like computation and accessing data in memory - * Retiring is good execution that is not directly bottlenecked - * - * The formulas are computed in slots. - * A slot is an entry in the pipeline each for the pipeline width - * (for example a 4-wide pipeline has 4 slots for each cycle) - * - * Formulas: - * BadSpeculation = ((SlotsIssued - SlotsRetired) + RecoveryBubbles) / - * TotalSlots - * Retiring = SlotsRetired / TotalSlots - * FrontendBound = FetchBubbles / TotalSlots - * BackendBound = 1.0 - BadSpeculation - Retiring - FrontendBound - * - * The kernel provides the mapping to the low level CPU events and any scaling - * needed for the CPU pipeline width, for example: - * - * TotalSlots = Cycles * 4 - * - * The scaling factor is communicated in the sysfs unit. - * - * In some cases the CPU may not be able to measure all the formulas due to - * missing events. In this case multiple formulas are combined, as possible. - * - * Full TopDown supports more levels to sub-divide each area: for example - * BackendBound into computing bound and memory bound. For now we only - * support Level 1 TopDown. - */ - -static double sanitize_val(double x) -{ - if (x < 0 && x >= -0.02) - return 0.0; - return x; -} - -static double td_total_slots(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, map_idx, rsd); -} - -static double td_bad_spec(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double bad_spec = 0; - double total_slots; - double total; - - total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, map_idx, rsd) - - runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, map_idx, rsd) + - runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, map_idx, rsd); - - total_slots = td_total_slots(map_idx, st, rsd); - if (total_slots) - bad_spec = total / total_slots; - return sanitize_val(bad_spec); -} - -static double td_retiring(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double retiring = 0; - double total_slots = td_total_slots(map_idx, st, rsd); - double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, - map_idx, rsd); - - if (total_slots) - retiring = ret_slots / total_slots; - return retiring; -} - -static double td_fe_bound(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double fe_bound = 0; - double total_slots = td_total_slots(map_idx, st, rsd); - double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES, - map_idx, rsd); - - if (total_slots) - fe_bound = fetch_bub / total_slots; - return fe_bound; -} - -static double td_be_bound(int map_idx, struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double sum = (td_fe_bound(map_idx, st, rsd) + - td_bad_spec(map_idx, st, rsd) + - td_retiring(map_idx, st, rsd)); - if (sum == 0) - return 0; - return sanitize_val(1.0 - sum); -} - -/* - * Kernel reports metrics multiplied with slots. To get back - * the ratios we need to recreate the sum. - */ - -static double td_metric_ratio(int map_idx, enum stat_type type, - struct runtime_stat *stat, - struct runtime_stat_data *rsd) -{ - double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) + - runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd); - double d = runtime_stat_avg(stat, type, map_idx, rsd); - - if (sum) - return d / sum; - return 0; -} - -/* - * ... but only if most of the values are actually available. - * We allow two missing. - */ - -static bool full_td(int map_idx, struct runtime_stat *stat, - struct runtime_stat_data *rsd) -{ - int c = 0; - - if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, map_idx, rsd) > 0) - c++; - if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, map_idx, rsd) > 0) - c++; - return c >= 2; -} - static void print_smi_cost(struct perf_stat_config *config, int map_idx, struct perf_stat_output_ctx *out, struct runtime_stat *st, @@ -885,7 +696,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; double total, ratio = 0.0, total2; - const char *color = NULL; struct runtime_stat_data rsd = { .ctx = evsel_context(evsel), .cgrp = evsel->cgrp, @@ -1044,162 +854,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) { - double fe_bound = td_fe_bound(map_idx, st, &rsd); - - if (fe_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "frontend bound", - fe_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) { - double retiring = td_retiring(map_idx, st, &rsd); - - if (retiring > 0.7) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "retiring", - retiring * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) { - double bad_spec = td_bad_spec(map_idx, st, &rsd); - - if (bad_spec > 0.1) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "bad speculation", - bad_spec * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) { - double be_bound = td_be_bound(map_idx, st, &rsd); - const char *name = "backend bound"; - static int have_recovery_bubbles = -1; - - /* In case the CPU does not support topdown-recovery-bubbles */ - if (have_recovery_bubbles < 0) - have_recovery_bubbles = pmu_have_event("cpu", - "topdown-recovery-bubbles"); - if (!have_recovery_bubbles) - name = "backend bound/bad spec"; - - if (be_bound > 0.2) - color = PERF_COLOR_RED; - if (td_total_slots(map_idx, st, &rsd) > 0) - print_metric(config, ctxp, color, "%8.1f%%", name, - be_bound * 100.); - else - print_metric(config, ctxp, NULL, NULL, name, 0); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) && - full_td(map_idx, st, &rsd)) { - double retiring = td_metric_ratio(map_idx, - STAT_TOPDOWN_RETIRING, st, - &rsd); - if (retiring > 0.7) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "Retiring", - retiring * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) && - full_td(map_idx, st, &rsd)) { - double fe_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_FE_BOUND, st, - &rsd); - if (fe_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Frontend Bound", - fe_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) && - full_td(map_idx, st, &rsd)) { - double be_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_BE_BOUND, st, - &rsd); - if (be_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Backend Bound", - be_bound * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) && - full_td(map_idx, st, &rsd)) { - double bad_spec = td_metric_ratio(map_idx, - STAT_TOPDOWN_BAD_SPEC, st, - &rsd); - if (bad_spec > 0.1) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Bad Speculation", - bad_spec * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double retiring = td_metric_ratio(map_idx, - STAT_TOPDOWN_RETIRING, st, - &rsd); - double heavy_ops = td_metric_ratio(map_idx, - STAT_TOPDOWN_HEAVY_OPS, st, - &rsd); - double light_ops = retiring - heavy_ops; - - if (retiring > 0.7 && heavy_ops > 0.1) - color = PERF_COLOR_GREEN; - print_metric(config, ctxp, color, "%8.1f%%", "Heavy Operations", - heavy_ops * 100.); - if (retiring > 0.7 && light_ops > 0.6) - color = PERF_COLOR_GREEN; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Light Operations", - light_ops * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double bad_spec = td_metric_ratio(map_idx, - STAT_TOPDOWN_BAD_SPEC, st, - &rsd); - double br_mis = td_metric_ratio(map_idx, - STAT_TOPDOWN_BR_MISPREDICT, st, - &rsd); - double m_clears = bad_spec - br_mis; - - if (bad_spec > 0.1 && br_mis > 0.05) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Branch Mispredict", - br_mis * 100.); - if (bad_spec > 0.1 && m_clears > 0.05) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Machine Clears", - m_clears * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double fe_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_FE_BOUND, st, - &rsd); - double fetch_lat = td_metric_ratio(map_idx, - STAT_TOPDOWN_FETCH_LAT, st, - &rsd); - double fetch_bw = fe_bound - fetch_lat; - - if (fe_bound > 0.2 && fetch_lat > 0.15) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Fetch Latency", - fetch_lat * 100.); - if (fe_bound > 0.2 && fetch_bw > 0.1) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Fetch Bandwidth", - fetch_bw * 100.); - } else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) && - full_td(map_idx, st, &rsd) && (config->topdown_level > 1)) { - double be_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_BE_BOUND, st, - &rsd); - double mem_bound = td_metric_ratio(map_idx, - STAT_TOPDOWN_MEM_BOUND, st, - &rsd); - double core_bound = be_bound - mem_bound; - - if (be_bound > 0.2 && mem_bound > 0.2) - color = PERF_COLOR_RED; - print_metric(config, ctxp, color, "%8.1f%%", "Memory Bound", - mem_bound * 100.); - if (be_bound > 0.2 && core_bound > 0.1) - color = PERF_COLOR_RED; - else - color = NULL; - print_metric(config, ctxp, color, "%8.1f%%", "Core Bound", - core_bound * 100.); } else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 534d36d26fc3..0b8c91ca13cd 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -91,19 +91,6 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(TRANSACTION_START, cpu/tx-start/), ID(ELISION_START, cpu/el-start/), ID(CYCLES_IN_TX_CP, cpu/cycles-ct/), - ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots), - ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued), - ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired), - ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles), - ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles), - ID(TOPDOWN_RETIRING, topdown-retiring), - ID(TOPDOWN_BAD_SPEC, topdown-bad-spec), - ID(TOPDOWN_FE_BOUND, topdown-fe-bound), - ID(TOPDOWN_BE_BOUND, topdown-be-bound), - ID(TOPDOWN_HEAVY_OPS, topdown-heavy-ops), - ID(TOPDOWN_BR_MISPREDICT, topdown-br-mispredict), - ID(TOPDOWN_FETCH_LAT, topdown-fetch-lat), - ID(TOPDOWN_MEM_BOUND, topdown-mem-bound), ID(SMI_NUM, msr/smi/), ID(APERF, msr/aperf/), }; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index cf2d8aa445f3..42af350a96d9 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -25,19 +25,6 @@ enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__TRANSACTION_START, PERF_STAT_EVSEL_ID__ELISION_START, PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP, - PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS, - PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED, - PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED, - PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES, - PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES, - PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING, - PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC, - PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND, - PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND, - PERF_STAT_EVSEL_ID__TOPDOWN_HEAVY_OPS, - PERF_STAT_EVSEL_ID__TOPDOWN_BR_MISPREDICT, - PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_LAT, - PERF_STAT_EVSEL_ID__TOPDOWN_MEM_BOUND, PERF_STAT_EVSEL_ID__SMI_NUM, PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, @@ -108,19 +95,6 @@ enum stat_type { STAT_CYCLES_IN_TX, STAT_TRANSACTION, STAT_ELISION, - STAT_TOPDOWN_TOTAL_SLOTS, - STAT_TOPDOWN_SLOTS_ISSUED, - STAT_TOPDOWN_SLOTS_RETIRED, - STAT_TOPDOWN_FETCH_BUBBLES, - STAT_TOPDOWN_RECOVERY_BUBBLES, - STAT_TOPDOWN_RETIRING, - STAT_TOPDOWN_BAD_SPEC, - STAT_TOPDOWN_FE_BOUND, - STAT_TOPDOWN_BE_BOUND, - STAT_TOPDOWN_HEAVY_OPS, - STAT_TOPDOWN_BR_MISPREDICT, - STAT_TOPDOWN_FETCH_LAT, - STAT_TOPDOWN_MEM_BOUND, STAT_SMI_NUM, STAT_APERF, STAT_MAX -- GitLab From 20cb10eadbddcacda277f471c32000da9ae60d41 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:39 -0800 Subject: [PATCH 0043/5631] perf doc: Refresh topdown documentation perf stat now supports --topdown for any platform with the TopdownL1 metric group including Intel before Icelake. Tweak the documentation to reflect this. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-43-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 27 +++++----- tools/perf/Documentation/topdown.txt | 70 +++++++++++--------------- 2 files changed, 44 insertions(+), 53 deletions(-) diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 18abdc1dce05..29bdcfa93f04 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -394,10 +394,10 @@ See perf list output for the possible metrics and metricgroups. Do not aggregate counts across all monitored CPUs. --topdown:: -Print complete top-down metrics supported by the CPU. This allows to -determine bottle necks in the CPU pipeline for CPU bound workloads, -by breaking the cycles consumed down into frontend bound, backend bound, -bad speculation and retiring. +Print top-down metrics supported by the CPU. This allows to determine +bottle necks in the CPU pipeline for CPU bound workloads, by breaking +the cycles consumed down into frontend bound, backend bound, bad +speculation and retiring. Frontend bound means that the CPU cannot fetch and decode instructions fast enough. Backend bound means that computation or memory access is the bottle @@ -430,15 +430,18 @@ CPUs the workload runs on. If needed the CPUs can be forced using taskset. --td-level:: -Print the top-down statistics that equal to or lower than the input level. -It allows users to print the interested top-down metrics level instead of -the complete top-down metrics. +Print the top-down statistics that equal the input level. It allows +users to print the interested top-down metrics level instead of the +level 1 top-down metrics. + +As the higher levels gather more metrics and use more counters they +will be less accurate. By convention a metric can be examined by +appending '_group' to it and this will increase accuracy compared to +gathering all metrics for a level. For example, level 1 analysis may +highlight 'tma_frontend_bound'. This metric may be drilled into with +'tma_frontend_bound_group' with +'perf stat -M tma_frontend_bound_group...'. -The availability of the top-down metrics level depends on the hardware. For -example, Ice Lake only supports L1 top-down metrics. The Sapphire Rapids -supports both L1 and L2 top-down metrics. - -Default: 0 means the max level that the current hardware support. Error out if the input is higher than the supported max level. --no-merge:: diff --git a/tools/perf/Documentation/topdown.txt b/tools/perf/Documentation/topdown.txt index a15b93fdcf50..ae0aee86844f 100644 --- a/tools/perf/Documentation/topdown.txt +++ b/tools/perf/Documentation/topdown.txt @@ -1,46 +1,35 @@ -Using TopDown metrics in user space ------------------------------------ +Using TopDown metrics +--------------------- -Intel CPUs (since Sandy Bridge and Silvermont) support a TopDown -methodology to break down CPU pipeline execution into 4 bottlenecks: -frontend bound, backend bound, bad speculation, retiring. +TopDown metrics break apart performance bottlenecks. Starting at level +1 it is typical to get metrics on retiring, bad speculation, frontend +bound, and backend bound. Higher levels provide more detail in to the +level 1 bottlenecks, such as at level 2: core bound, memory bound, +heavy operations, light operations, branch mispredicts, machine +clears, fetch latency and fetch bandwidth. For more details see [1][2][3]. -For more details on Topdown see [1][5] +perf stat --topdown implements this using available metrics that vary +per architecture. -Traditionally this was implemented by events in generic counters -and specific formulas to compute the bottlenecks. - -perf stat --topdown implements this. - -Full Top Down includes more levels that can break down the -bottlenecks further. This is not directly implemented in perf, -but available in other tools that can run on top of perf, -such as toplev[2] or vtune[3] +% perf stat -a --topdown -I1000 +# time % tma_retiring % tma_backend_bound % tma_frontend_bound % tma_bad_speculation + 1.001141351 11.5 34.9 46.9 6.7 + 2.006141972 13.4 28.1 50.4 8.1 + 3.010162040 12.9 28.1 51.1 8.0 + 4.014009311 12.5 28.6 51.8 7.2 + 5.017838554 11.8 33.0 48.0 7.2 + 5.704818971 14.0 27.5 51.3 7.3 +... -New Topdown features in Ice Lake -=============================== +New Topdown features in Intel Ice Lake +====================================== With Ice Lake CPUs the TopDown metrics are directly available as fixed counters and do not require generic counters. This allows to collect TopDown always in addition to other events. -% perf stat -a --topdown -I1000 -# time retiring bad speculation frontend bound backend bound - 1.001281330 23.0% 15.3% 29.6% 32.1% - 2.003009005 5.0% 6.8% 46.6% 41.6% - 3.004646182 6.7% 6.7% 46.0% 40.6% - 4.006326375 5.0% 6.4% 47.6% 41.0% - 5.007991804 5.1% 6.3% 46.3% 42.3% - 6.009626773 6.2% 7.1% 47.3% 39.3% - 7.011296356 4.7% 6.7% 46.2% 42.4% - 8.012951831 4.7% 6.7% 47.5% 41.1% -... - -This also enables measuring TopDown per thread/process instead -of only per core. - -Using TopDown through RDPMC in applications on Ice Lake -====================================================== +Using TopDown through RDPMC in applications on Intel Ice Lake +============================================================= For more fine grained measurements it can be useful to access the new directly from user space. This is more complicated, @@ -301,8 +290,8 @@ This "opens" a new measurement period. A program using RDPMC for TopDown should schedule such a reset regularly, as in every few seconds. -Limits on Ice Lake -================== +Limits on Intel Ice Lake +======================== Four pseudo TopDown metric events are exposed for the end-users, topdown-retiring, topdown-bad-spec, topdown-fe-bound and topdown-be-bound. @@ -318,8 +307,8 @@ a sampling read group. Since the SLOTS event must be the leader of a TopDown group, the second event of the group is the sampling event. For example, perf record -e '{slots, $sampling_event, topdown-retiring}:S' -Extension on Sapphire Rapids Server -=================================== +Extension on Intel Sapphire Rapids Server +========================================= The metrics counter is extended to support TMA method level 2 metrics. The lower half of the register is the TMA level 1 metrics (legacy). The upper half is also divided into four 8-bit fields for the new level 2 @@ -338,7 +327,6 @@ other four level 2 metrics by subtracting corresponding metrics as below. [1] https://software.intel.com/en-us/top-down-microarchitecture-analysis-method-win -[2] https://github.com/andikleen/pmu-tools/wiki/toplev-manual -[3] https://software.intel.com/en-us/intel-vtune-amplifier-xe +[2] https://sites.google.com/site/analysismethods/yasin-pubs +[3] https://perf.wiki.kernel.org/index.php/Top-Down_Analysis [4] https://github.com/andikleen/pmu-tools/tree/master/jevents -[5] https://sites.google.com/site/analysismethods/yasin-pubs -- GitLab From d6964c5b1f76518e425f9aef05670a0933903207 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:40 -0800 Subject: [PATCH 0044/5631] perf stat: Remove hard coded transaction events The metric group "transaction" is now present for Intel architectures so the legacy hard coded approach won't be used. Remove the associated logic. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-44-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 59 ++++++----------------------------- tools/perf/util/stat-shadow.c | 48 +--------------------------- tools/perf/util/stat.c | 4 --- tools/perf/util/stat.h | 7 ----- 4 files changed, 11 insertions(+), 107 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index bdb1ef4fc6ad..e6b60b058257 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -100,30 +100,6 @@ static void print_counters(struct timespec *ts, int argc, const char **argv); -/* Default events used for perf stat -T */ -static const char *transaction_attrs = { - "task-clock," - "{" - "instructions," - "cycles," - "cpu/cycles-t/," - "cpu/tx-start/," - "cpu/el-start/," - "cpu/cycles-ct/" - "}" -}; - -/* More limited version when the CPU does not have all events. */ -static const char * transaction_limited_attrs = { - "task-clock," - "{" - "instructions," - "cycles," - "cpu/cycles-t/," - "cpu/tx-start/" - "}" -}; - static const char *smi_cost_attrs = { "{" "msr/aperf/," @@ -1811,37 +1787,22 @@ static int add_default_attributes(void) return 0; if (transaction_run) { - struct parse_events_error errinfo; /* Handle -T as -M transaction. Once platform specific metrics * support has been added to the json files, all architectures * will use this approach. To determine transaction support * on an architecture test for such a metric name. */ - if (metricgroup__has_metric("transaction")) { - return metricgroup__parse_groups(evsel_list, "transaction", - stat_config.metric_no_group, - stat_config.metric_no_merge, - stat_config.metric_no_threshold, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events); - } - - parse_events_error__init(&errinfo); - if (pmu_have_event("cpu", "cycles-ct") && - pmu_have_event("cpu", "el-start")) - err = parse_events(evsel_list, transaction_attrs, - &errinfo); - else - err = parse_events(evsel_list, - transaction_limited_attrs, - &errinfo); - if (err) { - fprintf(stderr, "Cannot set up transaction events\n"); - parse_events_error__print(&errinfo, transaction_attrs); + if (!metricgroup__has_metric("transaction")) { + pr_err("Missing transaction metrics"); + return -1; } - parse_events_error__exit(&errinfo); - return err ? -1 : 0; + return metricgroup__parse_groups(evsel_list, "transaction", + stat_config.metric_no_group, + stat_config.metric_no_merge, + stat_config.metric_no_threshold, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events); } if (smi_cost) { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 5189756bf16d..3cfe4b4eb3de 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -235,12 +235,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_NSECS, map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) update_runtime_stat(st, STAT_CYCLES, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, CYCLES_IN_TX)) - update_runtime_stat(st, STAT_CYCLES_IN_TX, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, TRANSACTION_START)) - update_runtime_stat(st, STAT_TRANSACTION, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, ELISION_START)) - update_runtime_stat(st, STAT_ELISION, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); @@ -695,7 +689,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, { void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; - double total, ratio = 0.0, total2; + double total, ratio = 0.0; struct runtime_stat_data rsd = { .ctx = evsel_context(evsel), .cgrp = evsel->cgrp, @@ -808,46 +802,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, } else { print_metric(config, ctxp, NULL, NULL, "Ghz", 0); } - } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); - - if (total) - print_metric(config, ctxp, NULL, - "%7.2f%%", "transactional cycles", - 100.0 * (avg / total)); - else - print_metric(config, ctxp, NULL, NULL, "transactional cycles", - 0); - } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); - total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (total2 < avg) - total2 = avg; - if (total) - print_metric(config, ctxp, NULL, "%7.2f%%", "aborted cycles", - 100.0 * ((total2-avg) / total)); - else - print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0); - } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (avg) - ratio = total / avg; - - if (runtime_stat_n(st, STAT_CYCLES_IN_TX, map_idx, &rsd) != 0) - print_metric(config, ctxp, NULL, "%8.0f", - "cycles / transaction", ratio); - else - print_metric(config, ctxp, NULL, NULL, "cycles / transaction", - 0); - } else if (perf_stat_evsel__is(evsel, ELISION_START)) { - total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, map_idx, &rsd); - - if (avg) - ratio = total / avg; - - print_metric(config, ctxp, NULL, "%8.0f", "cycles / elision", ratio); } else if (evsel__is_clock(evsel)) { if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 0b8c91ca13cd..b5b18d457254 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -87,10 +87,6 @@ bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) #define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(NONE, x), - ID(CYCLES_IN_TX, cpu/cycles-t/), - ID(TRANSACTION_START, cpu/tx-start/), - ID(ELISION_START, cpu/el-start/), - ID(CYCLES_IN_TX_CP, cpu/cycles-ct/), ID(SMI_NUM, msr/smi/), ID(APERF, msr/aperf/), }; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 42af350a96d9..c5fe847dd344 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -21,10 +21,6 @@ struct stats { enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__NONE = 0, - PERF_STAT_EVSEL_ID__CYCLES_IN_TX, - PERF_STAT_EVSEL_ID__TRANSACTION_START, - PERF_STAT_EVSEL_ID__ELISION_START, - PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP, PERF_STAT_EVSEL_ID__SMI_NUM, PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, @@ -92,9 +88,6 @@ enum stat_type { STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, - STAT_CYCLES_IN_TX, - STAT_TRANSACTION, - STAT_ELISION, STAT_SMI_NUM, STAT_APERF, STAT_MAX -- GitLab From c23f5cc06ac5dc556fccd2c9ac648fa84fb876fd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:41 -0800 Subject: [PATCH 0045/5631] perf stat: Use metrics for --smi-cost Rather than parsing events for --smi-cost, use the json metric group 'smi'. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-45-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 34 +++++++++++----------------------- tools/perf/util/stat-shadow.c | 30 ------------------------------ tools/perf/util/stat.c | 2 -- tools/perf/util/stat.h | 4 ---- 4 files changed, 11 insertions(+), 59 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index e6b60b058257..9c1fbf154ee3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -100,14 +100,6 @@ static void print_counters(struct timespec *ts, int argc, const char **argv); -static const char *smi_cost_attrs = { - "{" - "msr/aperf/," - "msr/smi/," - "cycles" - "}" -}; - static struct evlist *evsel_list; static bool all_counters_use_bpf = true; @@ -1666,7 +1658,6 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st) */ static int add_default_attributes(void) { - int err; struct perf_event_attr default_attrs0[] = { { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK }, @@ -1806,11 +1797,10 @@ static int add_default_attributes(void) } if (smi_cost) { - struct parse_events_error errinfo; int smi; if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) { - fprintf(stderr, "freeze_on_smi is not supported.\n"); + pr_err("freeze_on_smi is not supported."); return -1; } @@ -1822,23 +1812,21 @@ static int add_default_attributes(void) smi_reset = true; } - if (!pmu_have_event("msr", "aperf") || - !pmu_have_event("msr", "smi")) { - fprintf(stderr, "To measure SMI cost, it needs " - "msr/aperf/, msr/smi/ and cpu/cycles/ support\n"); + if (!metricgroup__has_metric("smi")) { + pr_err("Missing smi metrics"); return -1; } + if (!force_metric_only) stat_config.metric_only = true; - parse_events_error__init(&errinfo); - err = parse_events(evsel_list, smi_cost_attrs, &errinfo); - if (err) { - parse_events_error__print(&errinfo, smi_cost_attrs); - fprintf(stderr, "Cannot set up SMI cost events\n"); - } - parse_events_error__exit(&errinfo); - return err ? -1 : 0; + return metricgroup__parse_groups(evsel_list, "smi", + stat_config.metric_no_group, + stat_config.metric_no_merge, + stat_config.metric_no_threshold, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events); } if (topdown_run) { diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 3cfe4b4eb3de..d14fa531ee27 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -255,10 +255,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(st, STAT_DTLB_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_runtime_stat(st, STAT_ITLB_CACHE, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, SMI_NUM)) - update_runtime_stat(st, STAT_SMI_NUM, map_idx, count, &rsd); - else if (perf_stat_evsel__is(counter, APERF)) - update_runtime_stat(st, STAT_APERF, map_idx, count, &rsd); if (counter->collect_stat) { v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, st, @@ -479,30 +475,6 @@ static void print_ll_cache_misses(struct perf_stat_config *config, out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); } -static void print_smi_cost(struct perf_stat_config *config, int map_idx, - struct perf_stat_output_ctx *out, - struct runtime_stat *st, - struct runtime_stat_data *rsd) -{ - double smi_num, aperf, cycles, cost = 0.0; - const char *color = NULL; - - smi_num = runtime_stat_avg(st, STAT_SMI_NUM, map_idx, rsd); - aperf = runtime_stat_avg(st, STAT_APERF, map_idx, rsd); - cycles = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); - - if ((cycles == 0) || (aperf == 0)) - return; - - if (smi_num) - cost = (aperf - cycles) / aperf * 100.00; - - if (cost > 10) - color = PERF_COLOR_RED; - out->print_metric(config, out->ctx, color, "%8.1f%%", "SMI cycles%", cost); - out->print_metric(config, out->ctx, NULL, "%4.0f", "SMI#", smi_num); -} - static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, @@ -819,8 +791,6 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (unit != ' ') snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); - } else if (perf_stat_evsel__is(evsel, SMI_NUM)) { - print_smi_cost(config, map_idx, out, st, &rsd); } else { num = 0; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index b5b18d457254..d51d7457f12d 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -87,8 +87,6 @@ bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) #define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { ID(NONE, x), - ID(SMI_NUM, msr/smi/), - ID(APERF, msr/aperf/), }; #undef ID diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index c5fe847dd344..9af4af3bc3f2 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -21,8 +21,6 @@ struct stats { enum perf_stat_evsel_id { PERF_STAT_EVSEL_ID__NONE = 0, - PERF_STAT_EVSEL_ID__SMI_NUM, - PERF_STAT_EVSEL_ID__APERF, PERF_STAT_EVSEL_ID__MAX, }; @@ -88,8 +86,6 @@ enum stat_type { STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, - STAT_SMI_NUM, - STAT_APERF, STAT_MAX }; -- GitLab From d74192c7478e7fe90c2897b9237098283573f443 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:42 -0800 Subject: [PATCH 0046/5631] perf stat: Remove perf_stat_evsel_id perf_stat_evsel_id was used for hard coded metrics. These have now migrated to json metrics and so the id values are no longer necessary. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-46-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat.c | 31 ------------------------------- tools/perf/util/stat.h | 12 ------------ 2 files changed, 43 deletions(-) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index d51d7457f12d..8d83d2f4a082 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -77,36 +77,6 @@ double rel_stddev_stats(double stddev, double avg) return pct; } -bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id) -{ - struct perf_stat_evsel *ps = evsel->stats; - - return ps->id == id; -} - -#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name -static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = { - ID(NONE, x), -}; -#undef ID - -static void perf_stat_evsel_id_init(struct evsel *evsel) -{ - struct perf_stat_evsel *ps = evsel->stats; - int i; - - /* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */ - - for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) { - if (!strcmp(evsel__name(evsel), id_str[i]) || - (strstr(evsel__name(evsel), id_str[i]) && evsel->pmu_name - && strstr(evsel__name(evsel), evsel->pmu_name))) { - ps->id = i; - break; - } - } -} - static void evsel__reset_aggr_stats(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; @@ -166,7 +136,6 @@ static int evsel__alloc_stat_priv(struct evsel *evsel, int nr_aggr) return -ENOMEM; } - perf_stat_evsel_id_init(evsel); evsel__reset_stat_priv(evsel); return 0; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 9af4af3bc3f2..df6068a3f7bb 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -19,11 +19,6 @@ struct stats { u64 max, min; }; -enum perf_stat_evsel_id { - PERF_STAT_EVSEL_ID__NONE = 0, - PERF_STAT_EVSEL_ID__MAX, -}; - /* hold aggregated event info */ struct perf_stat_aggr { /* aggregated values */ @@ -40,8 +35,6 @@ struct perf_stat_aggr { struct perf_stat_evsel { /* used for repeated runs */ struct stats res_stats; - /* evsel id for quick check */ - enum perf_stat_evsel_id id; /* number of allocated 'aggr' */ int nr_aggr; /* aggregated event values */ @@ -187,11 +180,6 @@ static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rus struct evsel; struct evlist; -bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id); - -#define perf_stat_evsel__is(evsel, id) \ - __perf_stat_evsel__is(evsel, PERF_STAT_EVSEL_ID__ ## id) - extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; extern struct rusage_stats ru_stats; -- GitLab From 758bc8e626b76b53ac643dae4128d6f617e24467 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:43 -0800 Subject: [PATCH 0047/5631] perf stat: Move enums from header The enums are only used in stat-shadow.c, so narrow their scope by moving to the C file. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-47-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 25 +++++++++++++++++++++++++ tools/perf/util/stat.h | 27 --------------------------- 2 files changed, 25 insertions(+), 27 deletions(-) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index d14fa531ee27..fc948a7e83b7 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -29,6 +29,31 @@ struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; +enum { + CTX_BIT_USER = 1 << 0, + CTX_BIT_KERNEL = 1 << 1, + CTX_BIT_HV = 1 << 2, + CTX_BIT_HOST = 1 << 3, + CTX_BIT_IDLE = 1 << 4, + CTX_BIT_MAX = 1 << 5, +}; + +enum stat_type { + STAT_NONE = 0, + STAT_NSECS, + STAT_CYCLES, + STAT_STALLED_CYCLES_FRONT, + STAT_STALLED_CYCLES_BACK, + STAT_BRANCHES, + STAT_CACHEREFS, + STAT_L1_DCACHE, + STAT_L1_ICACHE, + STAT_LL_CACHE, + STAT_ITLB_CACHE, + STAT_DTLB_CACHE, + STAT_MAX +}; + struct saved_value { struct rb_node rb_node; struct evsel *evsel; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index df6068a3f7bb..215c0f5c4db7 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -55,33 +55,6 @@ enum aggr_mode { AGGR_MAX }; -enum { - CTX_BIT_USER = 1 << 0, - CTX_BIT_KERNEL = 1 << 1, - CTX_BIT_HV = 1 << 2, - CTX_BIT_HOST = 1 << 3, - CTX_BIT_IDLE = 1 << 4, - CTX_BIT_MAX = 1 << 5, -}; - -#define NUM_CTX CTX_BIT_MAX - -enum stat_type { - STAT_NONE = 0, - STAT_NSECS, - STAT_CYCLES, - STAT_STALLED_CYCLES_FRONT, - STAT_STALLED_CYCLES_BACK, - STAT_BRANCHES, - STAT_CACHEREFS, - STAT_L1_DCACHE, - STAT_L1_ICACHE, - STAT_LL_CACHE, - STAT_ITLB_CACHE, - STAT_DTLB_CACHE, - STAT_MAX -}; - struct runtime_stat { struct rblist value_list; }; -- GitLab From cc26ffaa01f04cbe5c958df5532f3c23599e7a04 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:44 -0800 Subject: [PATCH 0048/5631] perf stat: Hide runtime_stat runtime_stat is only shared for the sake of tests that don't care about its value. Move the definition into stat-shadow.c and have the tests also use the global version. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-48-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 6 +- tools/perf/builtin-stat.c | 4 +- tools/perf/tests/parse-metric.c | 19 ++-- tools/perf/tests/pmu-events.c | 8 +- tools/perf/util/stat-display.c | 5 +- tools/perf/util/stat-shadow.c | 165 +++++++++++++------------------- tools/perf/util/stat.c | 2 +- tools/perf/util/stat.h | 17 +--- 8 files changed, 90 insertions(+), 136 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a792214d1af8..e9b5387161df 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2074,8 +2074,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, val = sample->period * evsel->scale; perf_stat__update_shadow_stats(evsel, val, - sample->cpu, - &rt_stat); + sample->cpu); evsel_script(evsel)->val = val; if (evsel_script(leader)->gnum == leader->core.nr_members) { for_each_group_member (ev2, leader) { @@ -2083,8 +2082,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, evsel_script(ev2)->val, sample->cpu, &ctx, - NULL, - &rt_stat); + NULL); } evsel_script(leader)->gnum = 0; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9c1fbf154ee3..619387459914 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -434,7 +434,7 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); - perf_stat__reset_shadow_per_stat(&rt_stat); + perf_stat__reset_shadow_per_stat(); evlist__reset_aggr_stats(evsel_list); if (read_counters(&rs) == 0) @@ -910,7 +910,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) evlist__copy_prev_raw_counts(evsel_list); evlist__reset_prev_raw_counts(evsel_list); evlist__reset_aggr_stats(evsel_list); - perf_stat__reset_shadow_per_stat(&rt_stat); + perf_stat__reset_shadow_per_stat(); } else { update_stats(&walltime_nsecs_stats, t1 - t0); update_rusage_stats(&ru_stats, &stat_config.ru_data); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 132c9b945a42..37e3371d978e 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -30,8 +30,7 @@ static u64 find_value(const char *name, struct value *values) return 0; } -static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, - struct value *vals) +static void load_runtime_stat(struct evlist *evlist, struct value *vals) { struct evsel *evsel; u64 count; @@ -39,14 +38,14 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); - perf_stat__update_shadow_stats(evsel, count, 0, st); + perf_stat__update_shadow_stats(evsel, count, 0); if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, count); } } static double compute_single(struct rblist *metric_events, struct evlist *evlist, - struct runtime_stat *st, const char *name) + const char *name) { struct metric_expr *mexp; struct metric_event *me; @@ -58,7 +57,7 @@ static double compute_single(struct rblist *metric_events, struct evlist *evlist list_for_each_entry (mexp, &me->head, nd) { if (strcmp(mexp->metric_name, name)) continue; - return test_generic_metric(mexp, 0, st); + return test_generic_metric(mexp, 0); } } } @@ -74,7 +73,6 @@ static int __compute_metric(const char *name, struct value *vals, }; const struct pmu_metrics_table *pme_test; struct perf_cpu_map *cpus; - struct runtime_stat st; struct evlist *evlist; int err; @@ -93,7 +91,6 @@ static int __compute_metric(const char *name, struct value *vals, } perf_evlist__set_maps(&evlist->core, cpus, NULL); - runtime_stat__init(&st); /* Parse the metric into metric_events list. */ pme_test = find_core_metrics_table("testarch", "testcpu"); @@ -107,18 +104,17 @@ static int __compute_metric(const char *name, struct value *vals, goto out; /* Load the runtime stats with given numbers for events. */ - load_runtime_stat(&st, evlist, vals); + load_runtime_stat(evlist, vals); /* And execute the metric */ if (name1 && ratio1) - *ratio1 = compute_single(&metric_events, evlist, &st, name1); + *ratio1 = compute_single(&metric_events, evlist, name1); if (name2 && ratio2) - *ratio2 = compute_single(&metric_events, evlist, &st, name2); + *ratio2 = compute_single(&metric_events, evlist, name2); out: /* ... cleanup. */ metricgroup__rblist_exit(&metric_events); - runtime_stat__exit(&st); evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); @@ -300,6 +296,7 @@ static int test_metric_group(void) static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { + perf_stat__init_shadow_stats(); TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 50b99a0f8f59..122e74c282a7 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -816,7 +816,6 @@ static int test__parsing_callback(const struct pmu_metric *pm, int k; struct evlist *evlist; struct perf_cpu_map *cpus; - struct runtime_stat st; struct evsel *evsel; struct rblist metric_events = { .nr_entries = 0, @@ -844,7 +843,6 @@ static int test__parsing_callback(const struct pmu_metric *pm, } perf_evlist__set_maps(&evlist->core, cpus, NULL); - runtime_stat__init(&st); err = metricgroup__parse_groups_test(evlist, table, pm->metric_name, &metric_events); if (err) { @@ -867,7 +865,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, k = 1; perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { - perf_stat__update_shadow_stats(evsel, k, 0, &st); + perf_stat__update_shadow_stats(evsel, k, 0); if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; @@ -881,7 +879,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, list_for_each_entry (mexp, &me->head, nd) { if (strcmp(mexp->metric_name, pm->metric_name)) continue; - pr_debug("Result %f\n", test_generic_metric(mexp, 0, &st)); + pr_debug("Result %f\n", test_generic_metric(mexp, 0)); err = 0; (*failures)--; goto out_err; @@ -896,7 +894,6 @@ static int test__parsing_callback(const struct pmu_metric *pm, /* ... cleanup. */ metricgroup__rblist_exit(&metric_events); - runtime_stat__exit(&st); evlist__free_stats(evlist); perf_cpu_map__put(cpus); evlist__delete(evlist); @@ -908,6 +905,7 @@ static int test__parsing(struct test_suite *test __maybe_unused, { int failures = 0; + perf_stat__init_shadow_stats(); pmu_for_each_core_metric(test__parsing_callback, &failures); pmu_for_each_sys_metric(test__parsing_callback, &failures); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 1b5cb20efd23..6c065d0624c3 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -729,7 +729,7 @@ static void printout(struct perf_stat_config *config, struct outstate *os, if (ok) { perf_stat__print_shadow_stats(config, counter, uval, map_idx, - &out, &config->metric_events, &rt_stat); + &out, &config->metric_events); } else { pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0); } @@ -1089,8 +1089,7 @@ static void print_metric_headers(struct perf_stat_config *config, perf_stat__print_shadow_stats(config, counter, 0, 0, &out, - &config->metric_events, - &rt_stat); + &config->metric_events); } if (!config->json_output) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index fc948a7e83b7..f80be6abac90 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -25,10 +25,13 @@ * AGGR_THREAD: Not supported? */ -struct runtime_stat rt_stat; struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; +static struct runtime_stat { + struct rblist value_list; +} rt_stat; + enum { CTX_BIT_USER = 1 << 0, CTX_BIT_KERNEL = 1 << 1, @@ -125,7 +128,6 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, bool create, enum stat_type type, int ctx, - struct runtime_stat *st, struct cgroup *cgrp) { struct rblist *rblist; @@ -138,7 +140,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, .cgrp = cgrp, }; - rblist = &st->value_list; + rblist = &rt_stat.value_list; /* don't use context info for clock events */ if (type == STAT_NSECS) @@ -156,9 +158,9 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel, return NULL; } -void runtime_stat__init(struct runtime_stat *st) +void perf_stat__init_shadow_stats(void) { - struct rblist *rblist = &st->value_list; + struct rblist *rblist = &rt_stat.value_list; rblist__init(rblist); rblist->node_cmp = saved_value_cmp; @@ -166,16 +168,6 @@ void runtime_stat__init(struct runtime_stat *st) rblist->node_delete = saved_value_delete; } -void runtime_stat__exit(struct runtime_stat *st) -{ - rblist__exit(&st->value_list); -} - -void perf_stat__init_shadow_stats(void) -{ - runtime_stat__init(&rt_stat); -} - static int evsel_context(struct evsel *evsel) { int ctx = 0; @@ -194,12 +186,12 @@ static int evsel_context(struct evsel *evsel) return ctx; } -static void reset_stat(struct runtime_stat *st) +void perf_stat__reset_shadow_per_stat(void) { struct rblist *rblist; struct rb_node *pos, *next; - rblist = &st->value_list; + rblist = &rt_stat.value_list; next = rb_first_cached(&rblist->entries); while (next) { pos = next; @@ -212,28 +204,22 @@ static void reset_stat(struct runtime_stat *st) void perf_stat__reset_shadow_stats(void) { - reset_stat(&rt_stat); + perf_stat__reset_shadow_per_stat(); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); memset(&ru_stats, 0, sizeof(ru_stats)); } -void perf_stat__reset_shadow_per_stat(struct runtime_stat *st) -{ - reset_stat(st); -} - struct runtime_stat_data { int ctx; struct cgroup *cgrp; }; -static void update_runtime_stat(struct runtime_stat *st, - enum stat_type type, +static void update_runtime_stat(enum stat_type type, int map_idx, u64 count, struct runtime_stat_data *rsd) { struct saved_value *v = saved_value_lookup(NULL, map_idx, true, type, - rsd->ctx, st, rsd->cgrp); + rsd->ctx, rsd->cgrp); if (v) update_stats(&v->stats, count); @@ -245,7 +231,7 @@ static void update_runtime_stat(struct runtime_stat *st, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx, struct runtime_stat *st) + int map_idx) { u64 count_ns = count; struct saved_value *v; @@ -253,43 +239,42 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, .ctx = evsel_context(counter), .cgrp = counter->cgrp, }; - count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(st, STAT_NSECS, map_idx, count_ns, &rsd); + update_runtime_stat(STAT_NSECS, map_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(st, STAT_CYCLES, map_idx, count, &rsd); + update_runtime_stat(STAT_CYCLES, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT, + update_runtime_stat(STAT_STALLED_CYCLES_FRONT, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_runtime_stat(st, STAT_STALLED_CYCLES_BACK, + update_runtime_stat(STAT_STALLED_CYCLES_BACK, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(st, STAT_BRANCHES, map_idx, count, &rsd); + update_runtime_stat(STAT_BRANCHES, map_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(st, STAT_CACHEREFS, map_idx, count, &rsd); + update_runtime_stat(STAT_CACHEREFS, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(st, STAT_L1_DCACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_DCACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(st, STAT_L1_ICACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_ICACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(st, STAT_LL_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_LL_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(st, STAT_DTLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_DTLB_CACHE, map_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(st, STAT_ITLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_ITLB_CACHE, map_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, st, + v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader && !counter->merged_stat) { v = saved_value_lookup(counter->metric_leader, - map_idx, true, STAT_NONE, 0, st, rsd.cgrp); + map_idx, true, STAT_NONE, 0, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -322,26 +307,24 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static double runtime_stat_avg(struct runtime_stat *st, - enum stat_type type, int map_idx, +static double runtime_stat_avg(enum stat_type type, int map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; return avg_stats(&v->stats); } -static double runtime_stat_n(struct runtime_stat *st, - enum stat_type type, int map_idx, +static double runtime_stat_n(enum stat_type type, int map_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, st, rsd->cgrp); + v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; @@ -351,13 +334,12 @@ static double runtime_stat_n(struct runtime_stat *st, static void print_stalled_cycles_frontend(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -374,13 +356,12 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, static void print_stalled_cycles_backend(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -393,13 +374,12 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, static void print_branch_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_BRANCHES, map_idx, rsd); + total = runtime_stat_avg(STAT_BRANCHES, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -412,13 +392,12 @@ static void print_branch_misses(struct perf_stat_config *config, static void print_l1_dcache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_DCACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_DCACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -431,13 +410,12 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, static void print_l1_icache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_L1_ICACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_ICACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -449,13 +427,12 @@ static void print_l1_icache_misses(struct perf_stat_config *config, static void print_dtlb_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_DTLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_DTLB_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -467,13 +444,12 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, static void print_itlb_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_ITLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_ITLB_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -485,13 +461,12 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, static void print_ll_cache_misses(struct perf_stat_config *config, int map_idx, double avg, struct perf_stat_output_ctx *out, - struct runtime_stat *st, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(st, STAT_LL_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_LL_CACHE, map_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -503,8 +478,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int map_idx, - struct runtime_stat *st) + int map_idx) { double scale; char *n; @@ -543,7 +517,7 @@ static int prepare_metric(struct evsel **metric_events, } } else { v = saved_value_lookup(metric_events[i], map_idx, false, - STAT_NONE, 0, st, + STAT_NONE, 0, metric_events[i]->cgrp); if (!v) break; @@ -587,8 +561,7 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_unit, int runtime, int map_idx, - struct perf_stat_output_ctx *out, - struct runtime_stat *st) + struct perf_stat_output_ctx *out) { print_metric_t print_metric = out->print_metric; struct expr_parse_ctx *pctx; @@ -605,7 +578,7 @@ static void generic_metric(struct perf_stat_config *config, pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list); pctx->sctx.runtime = runtime; pctx->sctx.system_wide = config->system_wide; - i = prepare_metric(metric_events, metric_refs, pctx, map_idx, st); + i = prepare_metric(metric_events, metric_refs, pctx, map_idx); if (i < 0) { expr__ctx_free(pctx); return; @@ -657,7 +630,7 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime_stat *st) +double test_generic_metric(struct metric_expr *mexp, int map_idx) { struct expr_parse_ctx *pctx; double ratio = 0.0; @@ -666,7 +639,7 @@ double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime if (!pctx) return NAN; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx, st) < 0) + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -681,8 +654,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, double avg, int map_idx, struct perf_stat_output_ctx *out, - struct rblist *metric_events, - struct runtime_stat *st) + struct rblist *metric_events) { void *ctxp = out->ctx; print_metric_t print_metric = out->print_metric; @@ -697,7 +669,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(st, STAT_CYCLES, map_idx, &rsd); + total = runtime_stat_avg(STAT_CYCLES, map_idx, &rsd); if (total) { ratio = avg / total; @@ -707,10 +679,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); + total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); - total = max(total, runtime_stat_avg(st, - STAT_STALLED_CYCLES_BACK, + total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, map_idx, &rsd)); if (total && avg) { @@ -721,8 +692,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(st, STAT_BRANCHES, map_idx, &rsd) != 0) - print_branch_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_BRANCHES, map_idx, &rsd) != 0) + print_branch_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -731,8 +702,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_DCACHE, map_idx, &rsd) != 0) - print_l1_dcache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_L1_DCACHE, map_idx, &rsd) != 0) + print_l1_dcache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -741,8 +712,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_L1_ICACHE, map_idx, &rsd) != 0) - print_l1_icache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_L1_ICACHE, map_idx, &rsd) != 0) + print_l1_icache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -751,8 +722,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_DTLB_CACHE, map_idx, &rsd) != 0) - print_dtlb_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_DTLB_CACHE, map_idx, &rsd) != 0) + print_dtlb_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -761,8 +732,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_ITLB_CACHE, map_idx, &rsd) != 0) - print_itlb_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_ITLB_CACHE, map_idx, &rsd) != 0) + print_itlb_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -771,27 +742,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(st, STAT_LL_CACHE, map_idx, &rsd) != 0) - print_ll_cache_misses(config, map_idx, avg, out, st, &rsd); + if (runtime_stat_n(STAT_LL_CACHE, map_idx, &rsd) != 0) + print_ll_cache_misses(config, map_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(st, STAT_CACHEREFS, map_idx, &rsd); + total = runtime_stat_avg(STAT_CACHEREFS, map_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(st, STAT_CACHEREFS, map_idx, &rsd) != 0) + if (runtime_stat_n(STAT_CACHEREFS, map_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, map_idx, avg, out, st, &rsd); + print_stalled_cycles_frontend(config, map_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, map_idx, avg, out, st, &rsd); + print_stalled_cycles_backend(config, map_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(st, STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); if (total) { ratio = avg / total; @@ -805,11 +776,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(st, STAT_NSECS, map_idx, &rsd) != 0) { + } else if (runtime_stat_n(STAT_NSECS, map_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(st, STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -829,7 +800,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, generic_metric(config, mexp->metric_expr, mexp->metric_threshold, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, mexp->metric_unit, mexp->runtime, - map_idx, out, st); + map_idx, out); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 8d83d2f4a082..0d7538670d67 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -659,7 +659,7 @@ static void evsel__update_shadow_stats(struct evsel *evsel) for (i = 0; i < ps->nr_aggr; i++) { struct perf_counts_values *aggr_counts = &ps->aggr[i].counts; - perf_stat__update_shadow_stats(evsel, aggr_counts->val, i, &rt_stat); + perf_stat__update_shadow_stats(evsel, aggr_counts->val, i); } } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 215c0f5c4db7..09975e098bd0 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -55,10 +55,6 @@ enum aggr_mode { AGGR_MAX }; -struct runtime_stat { - struct rblist value_list; -}; - struct rusage_stats { struct stats ru_utime_usec_stat; struct stats ru_stime_usec_stat; @@ -153,7 +149,6 @@ static inline void update_rusage_stats(struct rusage_stats *ru_stats, struct rus struct evsel; struct evlist; -extern struct runtime_stat rt_stat; extern struct stats walltime_nsecs_stats; extern struct rusage_stats ru_stats; @@ -162,13 +157,10 @@ typedef void (*print_metric_t)(struct perf_stat_config *config, const char *fmt, double val); typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); -void runtime_stat__init(struct runtime_stat *st); -void runtime_stat__exit(struct runtime_stat *st); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); -void perf_stat__reset_shadow_per_stat(struct runtime_stat *st); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx, struct runtime_stat *st); +void perf_stat__reset_shadow_per_stat(void); +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int map_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -180,8 +172,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, double avg, int map_idx, struct perf_stat_output_ctx *out, - struct rblist *metric_events, - struct runtime_stat *st); + struct rblist *metric_events); int evlist__alloc_stats(struct perf_stat_config *config, struct evlist *evlist, bool alloc_raw); @@ -220,5 +211,5 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int map_idx, struct runtime_stat *st); +double test_generic_metric(struct metric_expr *mexp, int map_idx); #endif -- GitLab From 8945bef30684b5ffb6778de1e979a7fcef6a760b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:45 -0800 Subject: [PATCH 0049/5631] perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.h | 3 + tools/perf/util/stat-display.c | 112 +++++++++++++++-------------- tools/perf/util/stat-shadow.c | 128 ++++++++++++++++----------------- tools/perf/util/stat.c | 8 +-- tools/perf/util/stat.h | 6 +- 5 files changed, 132 insertions(+), 125 deletions(-) diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index c2f5824a3a22..e3426541e0aa 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -35,6 +35,9 @@ struct cpu_aggr_map { struct aggr_cpu_id map[]; }; +#define cpu_aggr_map__for_each_idx(idx, aggr_map) \ + for ((idx) = 0; (idx) < aggr_map->nr; (idx)++) + struct perf_record_cpu_map_data; bool perf_record_cpu_map_data__test_bit(int i, const struct perf_record_cpu_map_data *data); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 6c065d0624c3..e6035ecbeee8 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -183,7 +183,7 @@ static void print_cgroup(struct perf_stat_config *config, struct cgroup *cgrp) } static void print_aggr_id_std(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; int idx = config->aggr_mode; @@ -225,11 +225,11 @@ static void print_aggr_id_std(struct perf_stat_config *config, return; } - fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, nr); + fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, aggr_nr); } static void print_aggr_id_csv(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; const char *sep = config->csv_sep; @@ -237,19 +237,19 @@ static void print_aggr_id_csv(struct perf_stat_config *config, switch (config->aggr_mode) { case AGGR_CORE: fprintf(output, "S%d-D%d-C%d%s%d%s", - id.socket, id.die, id.core, sep, nr, sep); + id.socket, id.die, id.core, sep, aggr_nr, sep); break; case AGGR_DIE: fprintf(output, "S%d-D%d%s%d%s", - id.socket, id.die, sep, nr, sep); + id.socket, id.die, sep, aggr_nr, sep); break; case AGGR_SOCKET: fprintf(output, "S%d%s%d%s", - id.socket, sep, nr, sep); + id.socket, sep, aggr_nr, sep); break; case AGGR_NODE: fprintf(output, "N%d%s%d%s", - id.node, sep, nr, sep); + id.node, sep, aggr_nr, sep); break; case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { @@ -275,26 +275,26 @@ static void print_aggr_id_csv(struct perf_stat_config *config, } static void print_aggr_id_json(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { FILE *output = config->output; switch (config->aggr_mode) { case AGGR_CORE: fprintf(output, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ", - id.socket, id.die, id.core, nr); + id.socket, id.die, id.core, aggr_nr); break; case AGGR_DIE: fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ", - id.socket, id.die, nr); + id.socket, id.die, aggr_nr); break; case AGGR_SOCKET: fprintf(output, "\"socket\" : \"S%d\", \"aggregate-number\" : %d, ", - id.socket, nr); + id.socket, aggr_nr); break; case AGGR_NODE: fprintf(output, "\"node\" : \"N%d\", \"aggregate-number\" : %d, ", - id.node, nr); + id.node, aggr_nr); break; case AGGR_NONE: if (evsel->percore && !config->percore_show_thread) { @@ -319,14 +319,14 @@ static void print_aggr_id_json(struct perf_stat_config *config, } static void aggr_printout(struct perf_stat_config *config, - struct evsel *evsel, struct aggr_cpu_id id, int nr) + struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr) { if (config->json_output) - print_aggr_id_json(config, evsel, id, nr); + print_aggr_id_json(config, evsel, id, aggr_nr); else if (config->csv_output) - print_aggr_id_csv(config, evsel, id, nr); + print_aggr_id_csv(config, evsel, id, aggr_nr); else - print_aggr_id_std(config, evsel, id, nr); + print_aggr_id_std(config, evsel, id, aggr_nr); } struct outstate { @@ -335,7 +335,7 @@ struct outstate { bool first; const char *prefix; int nfields; - int nr; + int aggr_nr; struct aggr_cpu_id id; struct evsel *evsel; struct cgroup *cgrp; @@ -355,7 +355,7 @@ static void do_new_line_std(struct perf_stat_config *config, fputc('\n', os->fh); if (os->prefix) fputs(os->prefix, os->fh); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); if (config->aggr_mode == AGGR_NONE) fprintf(os->fh, " "); fprintf(os->fh, " "); @@ -396,7 +396,7 @@ static void new_line_csv(struct perf_stat_config *config, void *ctx) fputc('\n', os->fh); if (os->prefix) fprintf(os->fh, "%s", os->prefix); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); for (i = 0; i < os->nfields; i++) fputs(config->csv_sep, os->fh); } @@ -444,7 +444,7 @@ static void new_line_json(struct perf_stat_config *config, void *ctx) fputs("\n{", os->fh); if (os->prefix) fprintf(os->fh, "%s", os->prefix); - aggr_printout(config, os->evsel, os->id, os->nr); + aggr_printout(config, os->evsel, os->id, os->aggr_nr); } /* Filter out some columns that don't work well in metrics only mode */ @@ -645,10 +645,10 @@ static void print_counter_value(struct perf_stat_config *config, } static void abs_printout(struct perf_stat_config *config, - struct aggr_cpu_id id, int nr, + struct aggr_cpu_id id, int aggr_nr, struct evsel *evsel, double avg, bool ok) { - aggr_printout(config, evsel, id, nr); + aggr_printout(config, evsel, id, aggr_nr); print_counter_value(config, evsel, avg, ok); print_cgroup(config, evsel->cgrp); } @@ -678,7 +678,7 @@ static bool is_mixed_hw_group(struct evsel *counter) } static void printout(struct perf_stat_config *config, struct outstate *os, - double uval, u64 run, u64 ena, double noise, int map_idx) + double uval, u64 run, u64 ena, double noise, int aggr_idx) { struct perf_stat_output_ctx out; print_metric_t pm; @@ -721,14 +721,14 @@ static void printout(struct perf_stat_config *config, struct outstate *os, out.force_header = false; if (!config->metric_only) { - abs_printout(config, os->id, os->nr, counter, uval, ok); + abs_printout(config, os->id, os->aggr_nr, counter, uval, ok); print_noise(config, counter, noise, /*before_metric=*/true); print_running(config, run, ena, /*before_metric=*/true); } if (ok) { - perf_stat__print_shadow_stats(config, counter, uval, map_idx, + perf_stat__print_shadow_stats(config, counter, uval, aggr_idx, &out, &config->metric_events); } else { pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0); @@ -833,20 +833,20 @@ static bool should_skip_zero_counter(struct perf_stat_config *config, } static void print_counter_aggrdata(struct perf_stat_config *config, - struct evsel *counter, int s, + struct evsel *counter, int aggr_idx, struct outstate *os) { FILE *output = config->output; u64 ena, run, val; double uval; struct perf_stat_evsel *ps = counter->stats; - struct perf_stat_aggr *aggr = &ps->aggr[s]; - struct aggr_cpu_id id = config->aggr_map->map[s]; + struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx]; + struct aggr_cpu_id id = config->aggr_map->map[aggr_idx]; double avg = aggr->counts.val; bool metric_only = config->metric_only; os->id = id; - os->nr = aggr->nr; + os->aggr_nr = aggr->nr; os->evsel = counter; /* Skip already merged uncore/hybrid events */ @@ -874,7 +874,7 @@ static void print_counter_aggrdata(struct perf_stat_config *config, uval = val * counter->scale; - printout(config, os, uval, run, ena, avg, s); + printout(config, os, uval, run, ena, avg, aggr_idx); if (!metric_only) fputc('\n', output); @@ -925,7 +925,7 @@ static void print_aggr(struct perf_stat_config *config, struct outstate *os) { struct evsel *counter; - int s; + int aggr_idx; if (!config->aggr_map || !config->aggr_get_id) return; @@ -934,11 +934,11 @@ static void print_aggr(struct perf_stat_config *config, * With metric_only everything is on a single line. * Without each counter has its own line. */ - for (s = 0; s < config->aggr_map->nr; s++) { - print_metric_begin(config, evlist, os, s); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_metric_begin(config, evlist, os, aggr_idx); evlist__for_each_entry(evlist, counter) { - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); } print_metric_end(config, os); } @@ -949,7 +949,7 @@ static void print_aggr_cgroup(struct perf_stat_config *config, struct outstate *os) { struct evsel *counter, *evsel; - int s; + int aggr_idx; if (!config->aggr_map || !config->aggr_get_id) return; @@ -960,14 +960,14 @@ static void print_aggr_cgroup(struct perf_stat_config *config, os->cgrp = evsel->cgrp; - for (s = 0; s < config->aggr_map->nr; s++) { - print_metric_begin(config, evlist, os, s); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_metric_begin(config, evlist, os, aggr_idx); evlist__for_each_entry(evlist, counter) { if (counter->cgrp != os->cgrp) continue; - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); } print_metric_end(config, os); } @@ -977,14 +977,14 @@ static void print_aggr_cgroup(struct perf_stat_config *config, static void print_counter(struct perf_stat_config *config, struct evsel *counter, struct outstate *os) { - int s; + int aggr_idx; /* AGGR_THREAD doesn't have config->aggr_get_id */ if (!config->aggr_map) return; - for (s = 0; s < config->aggr_map->nr; s++) { - print_counter_aggrdata(config, counter, s, os); + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + print_counter_aggrdata(config, counter, aggr_idx, os); } } @@ -1003,23 +1003,23 @@ static void print_no_aggr_metric(struct perf_stat_config *config, u64 ena, run, val; double uval; struct perf_stat_evsel *ps = counter->stats; - int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); + int aggr_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu); - if (counter_idx < 0) + if (aggr_idx < 0) continue; os->evsel = counter; os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL); if (first) { - print_metric_begin(config, evlist, os, counter_idx); + print_metric_begin(config, evlist, os, aggr_idx); first = false; } - val = ps->aggr[counter_idx].counts.val; - ena = ps->aggr[counter_idx].counts.ena; - run = ps->aggr[counter_idx].counts.run; + val = ps->aggr[aggr_idx].counts.val; + ena = ps->aggr[aggr_idx].counts.ena; + run = ps->aggr[aggr_idx].counts.run; uval = val * counter->scale; - printout(config, os, uval, run, ena, 1.0, counter_idx); + printout(config, os, uval, run, ena, 1.0, aggr_idx); } if (!first) print_metric_end(config, os); @@ -1338,7 +1338,7 @@ static void print_percore(struct perf_stat_config *config, bool metric_only = config->metric_only; FILE *output = config->output; struct cpu_aggr_map *core_map; - int s, c, i; + int aggr_idx, core_map_len = 0; if (!config->aggr_map || !config->aggr_get_id) return; @@ -1346,18 +1346,22 @@ static void print_percore(struct perf_stat_config *config, if (config->percore_show_thread) return print_counter(config, counter, os); + /* + * core_map will hold the aggr_cpu_id for the cores that have been + * printed so that each core is printed just once. + */ core_map = cpu_aggr_map__empty_new(config->aggr_map->nr); if (core_map == NULL) { fprintf(output, "Cannot allocate per-core aggr map for display\n"); return; } - for (s = 0, c = 0; s < config->aggr_map->nr; s++) { - struct perf_cpu curr_cpu = config->aggr_map->map[s].cpu; + cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) { + struct perf_cpu curr_cpu = config->aggr_map->map[aggr_idx].cpu; struct aggr_cpu_id core_id = aggr_cpu_id__core(curr_cpu, NULL); bool found = false; - for (i = 0; i < c; i++) { + for (int i = 0; i < core_map_len; i++) { if (aggr_cpu_id__equal(&core_map->map[i], &core_id)) { found = true; break; @@ -1366,9 +1370,9 @@ static void print_percore(struct perf_stat_config *config, if (found) continue; - print_counter_aggrdata(config, counter, s, os); + print_counter_aggrdata(config, counter, aggr_idx, os); - core_map->map[c++] = core_id; + core_map->map[core_map_len++] = core_id; } free(core_map); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index f80be6abac90..7b48e2bd3ba1 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -231,7 +231,7 @@ static void update_runtime_stat(enum stat_type type, * instruction rates, etc: */ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int map_idx) + int aggr_idx) { u64 count_ns = count; struct saved_value *v; @@ -242,39 +242,39 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, count *= counter->scale; if (evsel__is_clock(counter)) - update_runtime_stat(STAT_NSECS, map_idx, count_ns, &rsd); + update_runtime_stat(STAT_NSECS, aggr_idx, count_ns, &rsd); else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(STAT_CYCLES, map_idx, count, &rsd); + update_runtime_stat(STAT_CYCLES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) update_runtime_stat(STAT_STALLED_CYCLES_FRONT, - map_idx, count, &rsd); + aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) update_runtime_stat(STAT_STALLED_CYCLES_BACK, - map_idx, count, &rsd); + aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(STAT_BRANCHES, map_idx, count, &rsd); + update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHEREFS, map_idx, count, &rsd); + update_runtime_stat(STAT_CACHEREFS, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(STAT_L1_DCACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(STAT_L1_ICACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_L1_ICACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(STAT_LL_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_LL_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(STAT_DTLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(STAT_ITLB_CACHE, map_idx, count, &rsd); + update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); if (counter->collect_stat) { - v = saved_value_lookup(counter, map_idx, true, STAT_NONE, 0, + v = saved_value_lookup(counter, aggr_idx, true, STAT_NONE, 0, rsd.cgrp); update_stats(&v->stats, count); if (counter->metric_leader) v->metric_total += count; } else if (counter->metric_leader && !counter->merged_stat) { v = saved_value_lookup(counter->metric_leader, - map_idx, true, STAT_NONE, 0, rsd.cgrp); + aggr_idx, true, STAT_NONE, 0, rsd.cgrp); v->metric_total += count; v->metric_other++; } @@ -307,24 +307,24 @@ static const char *get_ratio_color(enum grc_type type, double ratio) return color; } -static double runtime_stat_avg(enum stat_type type, int map_idx, +static double runtime_stat_avg(enum stat_type type, int aggr_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); + v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; return avg_stats(&v->stats); } -static double runtime_stat_n(enum stat_type type, int map_idx, +static double runtime_stat_n(enum stat_type type, int aggr_idx, struct runtime_stat_data *rsd) { struct saved_value *v; - v = saved_value_lookup(NULL, map_idx, false, type, rsd->ctx, rsd->cgrp); + v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); if (!v) return 0.0; @@ -332,14 +332,14 @@ static double runtime_stat_n(enum stat_type type, int map_idx, } static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -354,14 +354,14 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config, } static void print_stalled_cycles_backend(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_CYCLES, map_idx, rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -372,14 +372,14 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config, } static void print_branch_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_BRANCHES, map_idx, rsd); + total = runtime_stat_avg(STAT_BRANCHES, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -390,14 +390,14 @@ static void print_branch_misses(struct perf_stat_config *config, } static void print_l1_dcache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_L1_DCACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_DCACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -408,14 +408,14 @@ static void print_l1_dcache_misses(struct perf_stat_config *config, } static void print_l1_icache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_L1_ICACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_L1_ICACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -425,14 +425,14 @@ static void print_l1_icache_misses(struct perf_stat_config *config, } static void print_dtlb_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_DTLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_DTLB_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -442,14 +442,14 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config, } static void print_itlb_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_ITLB_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_ITLB_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -459,14 +459,14 @@ static void print_itlb_cache_misses(struct perf_stat_config *config, } static void print_ll_cache_misses(struct perf_stat_config *config, - int map_idx, double avg, + int aggr_idx, double avg, struct perf_stat_output_ctx *out, struct runtime_stat_data *rsd) { double total, ratio = 0.0; const char *color; - total = runtime_stat_avg(STAT_LL_CACHE, map_idx, rsd); + total = runtime_stat_avg(STAT_LL_CACHE, aggr_idx, rsd); if (total) ratio = avg / total * 100.0; @@ -478,7 +478,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config, static int prepare_metric(struct evsel **metric_events, struct metric_ref *metric_refs, struct expr_parse_ctx *pctx, - int map_idx) + int aggr_idx) { double scale; char *n; @@ -516,7 +516,7 @@ static int prepare_metric(struct evsel **metric_events, abort(); } } else { - v = saved_value_lookup(metric_events[i], map_idx, false, + v = saved_value_lookup(metric_events[i], aggr_idx, false, STAT_NONE, 0, metric_events[i]->cgrp); if (!v) @@ -560,7 +560,7 @@ static void generic_metric(struct perf_stat_config *config, const char *metric_name, const char *metric_unit, int runtime, - int map_idx, + int aggr_idx, struct perf_stat_output_ctx *out) { print_metric_t print_metric = out->print_metric; @@ -578,7 +578,7 @@ static void generic_metric(struct perf_stat_config *config, pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list); pctx->sctx.runtime = runtime; pctx->sctx.system_wide = config->system_wide; - i = prepare_metric(metric_events, metric_refs, pctx, map_idx); + i = prepare_metric(metric_events, metric_refs, pctx, aggr_idx); if (i < 0) { expr__ctx_free(pctx); return; @@ -630,7 +630,7 @@ static void generic_metric(struct perf_stat_config *config, expr__ctx_free(pctx); } -double test_generic_metric(struct metric_expr *mexp, int map_idx) +double test_generic_metric(struct metric_expr *mexp, int aggr_idx) { struct expr_parse_ctx *pctx; double ratio = 0.0; @@ -639,7 +639,7 @@ double test_generic_metric(struct metric_expr *mexp, int map_idx) if (!pctx) return NAN; - if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, map_idx) < 0) + if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, aggr_idx) < 0) goto out; if (expr__parse(&ratio, pctx, mexp->metric_expr)) @@ -652,7 +652,7 @@ double test_generic_metric(struct metric_expr *mexp, int map_idx) void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int map_idx, + double avg, int aggr_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events) { @@ -669,7 +669,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, if (config->iostat_run) { iostat_print_metric(config, evsel, out); } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(STAT_CYCLES, map_idx, &rsd); + total = runtime_stat_avg(STAT_CYCLES, aggr_idx, &rsd); if (total) { ratio = avg / total; @@ -679,10 +679,10 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); } - total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, map_idx, &rsd); + total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, aggr_idx, &rsd); total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, - map_idx, &rsd)); + aggr_idx, &rsd)); if (total && avg) { out->new_line(config, ctxp); @@ -692,8 +692,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ratio); } } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(STAT_BRANCHES, map_idx, &rsd) != 0) - print_branch_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_BRANCHES, aggr_idx, &rsd) != 0) + print_branch_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all branches", 0); } else if ( @@ -702,8 +702,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_L1_DCACHE, map_idx, &rsd) != 0) - print_l1_dcache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_L1_DCACHE, aggr_idx, &rsd) != 0) + print_l1_dcache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); } else if ( @@ -712,8 +712,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_L1_ICACHE, map_idx, &rsd) != 0) - print_l1_icache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_L1_ICACHE, aggr_idx, &rsd) != 0) + print_l1_icache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); } else if ( @@ -722,8 +722,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_DTLB_CACHE, map_idx, &rsd) != 0) - print_dtlb_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_DTLB_CACHE, aggr_idx, &rsd) != 0) + print_dtlb_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); } else if ( @@ -732,8 +732,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_ITLB_CACHE, map_idx, &rsd) != 0) - print_itlb_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_ITLB_CACHE, aggr_idx, &rsd) != 0) + print_itlb_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); } else if ( @@ -742,27 +742,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - if (runtime_stat_n(STAT_LL_CACHE, map_idx, &rsd) != 0) - print_ll_cache_misses(config, map_idx, avg, out, &rsd); + if (runtime_stat_n(STAT_LL_CACHE, aggr_idx, &rsd) != 0) + print_ll_cache_misses(config, aggr_idx, avg, out, &rsd); else print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(STAT_CACHEREFS, map_idx, &rsd); + total = runtime_stat_avg(STAT_CACHEREFS, aggr_idx, &rsd); if (total) ratio = avg * 100 / total; - if (runtime_stat_n(STAT_CACHEREFS, map_idx, &rsd) != 0) + if (runtime_stat_n(STAT_CACHEREFS, aggr_idx, &rsd) != 0) print_metric(config, ctxp, NULL, "%8.3f %%", "of all cache refs", ratio); else print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, map_idx, avg, out, &rsd); + print_stalled_cycles_frontend(config, aggr_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, map_idx, avg, out, &rsd); + print_stalled_cycles_backend(config, aggr_idx, avg, out, &rsd); } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); if (total) { ratio = avg / total; @@ -776,11 +776,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, avg / (ratio * evsel->scale)); else print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(STAT_NSECS, map_idx, &rsd) != 0) { + } else if (runtime_stat_n(STAT_NSECS, aggr_idx, &rsd) != 0) { char unit = ' '; char unit_buf[10] = "/sec"; - total = runtime_stat_avg(STAT_NSECS, map_idx, &rsd); + total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); if (total) ratio = convert_unit_double(1000000000.0 * avg / total, &unit); @@ -800,7 +800,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, generic_metric(config, mexp->metric_expr, mexp->metric_threshold, mexp->metric_events, mexp->metric_refs, evsel->name, mexp->metric_name, mexp->metric_unit, mexp->runtime, - map_idx, out); + aggr_idx, out); } } if (num == 0) diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 0d7538670d67..83dc4c1f4b12 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -651,15 +651,15 @@ void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *e static void evsel__update_shadow_stats(struct evsel *evsel) { struct perf_stat_evsel *ps = evsel->stats; - int i; + int aggr_idx; if (ps->aggr == NULL) return; - for (i = 0; i < ps->nr_aggr; i++) { - struct perf_counts_values *aggr_counts = &ps->aggr[i].counts; + for (aggr_idx = 0; aggr_idx < ps->nr_aggr; aggr_idx++) { + struct perf_counts_values *aggr_counts = &ps->aggr[aggr_idx].counts; - perf_stat__update_shadow_stats(evsel, aggr_counts->val, i); + perf_stat__update_shadow_stats(evsel, aggr_counts->val, aggr_idx); } } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 09975e098bd0..b01c828c3799 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -160,7 +160,7 @@ typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); void perf_stat__reset_shadow_per_stat(void); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int map_idx); +void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -170,7 +170,7 @@ struct perf_stat_output_ctx { void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct evsel *evsel, - double avg, int map_idx, + double avg, int aggr_idx, struct perf_stat_output_ctx *out, struct rblist *metric_events); @@ -211,5 +211,5 @@ void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *conf struct target *_target, struct timespec *ts, int argc, const char **argv); struct metric_expr; -double test_generic_metric(struct metric_expr *mexp, int map_idx); +double test_generic_metric(struct metric_expr *mexp, int aggr_idx); #endif -- GitLab From 37cc8ad77cf81f3ffd226856c367b0e15333a738 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:46 -0800 Subject: [PATCH 0050/5631] perf metric: Directly use counts rather than saved_value Bugs with double aggregation have been introduced because of aggregation of counters and again with saved_value. Remove the generic metric use-case. Update parse-metric and pmu-events tests to update aggregate rather than saved_value counts. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-50-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-metric.c | 4 +-- tools/perf/tests/pmu-events.c | 4 +-- tools/perf/util/stat-shadow.c | 56 +++++++++++---------------------- 3 files changed, 23 insertions(+), 41 deletions(-) diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 37e3371d978e..b9b8a48289c4 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -35,10 +35,10 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) struct evsel *evsel; u64 count; - perf_stat__reset_shadow_stats(); + evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); - perf_stat__update_shadow_stats(evsel, count, 0); + evsel->stats->aggr->counts.val = count; if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, count); } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 122e74c282a7..4ec2a4ca1a82 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -863,9 +863,9 @@ static int test__parsing_callback(const struct pmu_metric *pm, * zero when subtracted and so try to make them unique. */ k = 1; - perf_stat__reset_shadow_stats(); + evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { - perf_stat__update_shadow_stats(evsel, k, 0); + evsel->stats->aggr->counts.val = k; if (!strcmp(evsel->name, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 7b48e2bd3ba1..eba98520cea2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -234,7 +234,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx) { u64 count_ns = count; - struct saved_value *v; struct runtime_stat_data rsd = { .ctx = evsel_context(counter), .cgrp = counter->cgrp, @@ -265,19 +264,6 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); - - if (counter->collect_stat) { - v = saved_value_lookup(counter, aggr_idx, true, STAT_NONE, 0, - rsd.cgrp); - update_stats(&v->stats, count); - if (counter->metric_leader) - v->metric_total += count; - } else if (counter->metric_leader && !counter->merged_stat) { - v = saved_value_lookup(counter->metric_leader, - aggr_idx, true, STAT_NONE, 0, rsd.cgrp); - v->metric_total += count; - v->metric_other++; - } } /* used for get_ratio_color() */ @@ -480,18 +466,17 @@ static int prepare_metric(struct evsel **metric_events, struct expr_parse_ctx *pctx, int aggr_idx) { - double scale; - char *n; - int i, j, ret; + int i; for (i = 0; metric_events[i]; i++) { - struct saved_value *v; - struct stats *stats; - u64 metric_total = 0; - int source_count; + char *n; + double val; + int source_count = 0; if (evsel__is_tool(metric_events[i])) { - source_count = 1; + struct stats *stats; + double scale; + switch (metric_events[i]->tool_event) { case PERF_TOOL_DURATION_TIME: stats = &walltime_nsecs_stats; @@ -515,35 +500,32 @@ static int prepare_metric(struct evsel **metric_events, pr_err("Unknown tool event '%s'", evsel__name(metric_events[i])); abort(); } + val = avg_stats(stats) * scale; + source_count = 1; } else { - v = saved_value_lookup(metric_events[i], aggr_idx, false, - STAT_NONE, 0, - metric_events[i]->cgrp); - if (!v) + struct perf_stat_evsel *ps = metric_events[i]->stats; + struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx]; + + if (!aggr) break; - stats = &v->stats; + /* * If an event was scaled during stat gathering, reverse * the scale before computing the metric. */ - scale = 1.0 / metric_events[i]->scale; - + val = aggr->counts.val * (1.0 / metric_events[i]->scale); source_count = evsel__source_count(metric_events[i]); - - if (v->metric_other) - metric_total = v->metric_total * scale; } n = strdup(evsel__metric_id(metric_events[i])); if (!n) return -ENOMEM; - expr__add_id_val_source_count(pctx, n, - metric_total ? : avg_stats(stats) * scale, - source_count); + expr__add_id_val_source_count(pctx, n, val, source_count); } - for (j = 0; metric_refs && metric_refs[j].metric_name; j++) { - ret = expr__add_ref(pctx, &metric_refs[j]); + for (int j = 0; metric_refs && metric_refs[j].metric_name; j++) { + int ret = expr__add_ref(pctx, &metric_refs[j]); + if (ret) return ret; } -- GitLab From 0a57b910807ad16381d39578ffc51a7055e4dfd6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:47 -0800 Subject: [PATCH 0051/5631] perf stat: Use counts rather than saved_value Switch the hard coded metrics to use the aggregate value rather than from saved_value. When computing a metric like IPC the aggregate count comes from instructions then cycles is looked up and if present IPC computed. Rather than lookup from the saved_value rbtree, search the counter's evlist for the desired counter. A new helper evsel__stat_type is used to both quickly find a metric function and to identify when a counter is the one being sought. So that both total and miss counts can be sought, the stat_type enum is expanded. The ratio functions are rewritten to share a common helper with the ratios being directly passed rather than computed from an enum value. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-51-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.h | 2 +- tools/perf/util/stat-shadow.c | 534 +++++++++++++++++----------------- 2 files changed, 270 insertions(+), 266 deletions(-) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 24cb807ef6ce..814a49ebb7e3 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -436,7 +436,7 @@ static inline bool evsel__is_bpf_output(struct evsel *evsel) return evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT); } -static inline bool evsel__is_clock(struct evsel *evsel) +static inline bool evsel__is_clock(const struct evsel *evsel) { return evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) || evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eba98520cea2..9d22cde09dc9 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -45,15 +45,23 @@ enum stat_type { STAT_NONE = 0, STAT_NSECS, STAT_CYCLES, + STAT_INSTRUCTIONS, STAT_STALLED_CYCLES_FRONT, STAT_STALLED_CYCLES_BACK, STAT_BRANCHES, - STAT_CACHEREFS, + STAT_BRANCH_MISS, + STAT_CACHE_REFS, + STAT_CACHE_MISSES, STAT_L1_DCACHE, STAT_L1_ICACHE, STAT_LL_CACHE, STAT_ITLB_CACHE, STAT_DTLB_CACHE, + STAT_L1D_MISS, + STAT_L1I_MISS, + STAT_LL_MISS, + STAT_DTLB_MISS, + STAT_ITLB_MISS, STAT_MAX }; @@ -168,7 +176,7 @@ void perf_stat__init_shadow_stats(void) rblist->node_delete = saved_value_delete; } -static int evsel_context(struct evsel *evsel) +static int evsel_context(const struct evsel *evsel) { int ctx = 0; @@ -253,7 +261,7 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHEREFS, aggr_idx, count, &rsd); + update_runtime_stat(STAT_CACHE_REFS, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) @@ -266,199 +274,283 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); } -/* used for get_ratio_color() */ -enum grc_type { - GRC_STALLED_CYCLES_FE, - GRC_STALLED_CYCLES_BE, - GRC_CACHE_MISSES, - GRC_MAX_NR -}; +static enum stat_type evsel__stat_type(const struct evsel *evsel) +{ + /* Fake perf_hw_cache_op_id values for use with evsel__match. */ + u64 PERF_COUNT_hw_cache_l1d_miss = PERF_COUNT_HW_CACHE_L1D | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_l1i_miss = PERF_COUNT_HW_CACHE_L1I | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_ll_miss = PERF_COUNT_HW_CACHE_LL | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_dtlb_miss = PERF_COUNT_HW_CACHE_DTLB | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + u64 PERF_COUNT_hw_cache_itlb_miss = PERF_COUNT_HW_CACHE_ITLB | + ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | + ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16); + + if (evsel__is_clock(evsel)) + return STAT_NSECS; + else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) + return STAT_CYCLES; + else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) + return STAT_INSTRUCTIONS; + else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) + return STAT_STALLED_CYCLES_FRONT; + else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) + return STAT_STALLED_CYCLES_BACK; + else if (evsel__match(evsel, HARDWARE, HW_BRANCH_INSTRUCTIONS)) + return STAT_BRANCHES; + else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) + return STAT_BRANCH_MISS; + else if (evsel__match(evsel, HARDWARE, HW_CACHE_REFERENCES)) + return STAT_CACHE_REFS; + else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) + return STAT_CACHE_MISSES; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1D)) + return STAT_L1_DCACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_L1I)) + return STAT_L1_ICACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_LL)) + return STAT_LL_CACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_DTLB)) + return STAT_DTLB_CACHE; + else if (evsel__match(evsel, HW_CACHE, HW_CACHE_ITLB)) + return STAT_ITLB_CACHE; + else if (evsel__match(evsel, HW_CACHE, hw_cache_l1d_miss)) + return STAT_L1D_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_l1i_miss)) + return STAT_L1I_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_ll_miss)) + return STAT_LL_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_dtlb_miss)) + return STAT_DTLB_MISS; + else if (evsel__match(evsel, HW_CACHE, hw_cache_itlb_miss)) + return STAT_ITLB_MISS; + return STAT_NONE; +} -static const char *get_ratio_color(enum grc_type type, double ratio) +static const char *get_ratio_color(const double ratios[3], double val) { - static const double grc_table[GRC_MAX_NR][3] = { - [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 }, - [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 }, - [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 }, - }; const char *color = PERF_COLOR_NORMAL; - if (ratio > grc_table[type][0]) + if (val > ratios[0]) color = PERF_COLOR_RED; - else if (ratio > grc_table[type][1]) + else if (val > ratios[1]) color = PERF_COLOR_MAGENTA; - else if (ratio > grc_table[type][2]) + else if (val > ratios[2]) color = PERF_COLOR_YELLOW; return color; } -static double runtime_stat_avg(enum stat_type type, int aggr_idx, - struct runtime_stat_data *rsd) +static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type type) { - struct saved_value *v; - - v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); - if (!v) - return 0.0; - - return avg_stats(&v->stats); + const struct evsel *cur; + int evsel_ctx = evsel_context(evsel); + + evlist__for_each_entry(evsel->evlist, cur) { + struct perf_stat_aggr *aggr; + + /* Ignore the evsel that is being searched from. */ + if (evsel == cur) + continue; + + /* Ignore evsels that are part of different groups. */ + if (evsel->core.leader->nr_members && + evsel->core.leader != cur->core.leader) + continue; + /* Ignore evsels with mismatched modifiers. */ + if (evsel_ctx != evsel_context(cur)) + continue; + /* Ignore if not the cgroup we're looking for. */ + if (evsel->cgrp != cur->cgrp) + continue; + /* Ignore if not the stat we're looking for. */ + if (type != evsel__stat_type(cur)) + continue; + + aggr = &cur->stats->aggr[aggr_idx]; + if (type == STAT_NSECS) + return aggr->counts.val; + return aggr->counts.val * cur->scale; + } + return 0.0; } -static double runtime_stat_n(enum stat_type type, int aggr_idx, - struct runtime_stat_data *rsd) +static void print_ratio(struct perf_stat_config *config, + const struct evsel *evsel, int aggr_idx, + double numerator, struct perf_stat_output_ctx *out, + enum stat_type denominator_type, + const double color_ratios[3], const char *unit) { - struct saved_value *v; + double denominator = find_stat(evsel, aggr_idx, denominator_type); - v = saved_value_lookup(NULL, aggr_idx, false, type, rsd->ctx, rsd->cgrp); - if (!v) - return 0.0; + if (numerator && denominator) { + double ratio = numerator / denominator * 100.0; + const char *color = get_ratio_color(color_ratios, ratio); - return v->stats.n; + out->print_metric(config, out->ctx, color, "%7.2f%%", unit, ratio); + } else + out->print_metric(config, out->ctx, NULL, NULL, unit, 0); } -static void print_stalled_cycles_frontend(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_stalled_cycles_front(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double stalled, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {50.0, 30.0, 10.0}; - color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio); - - if (ratio) - out->print_metric(config, out->ctx, color, "%7.2f%%", "frontend cycles idle", - ratio); - else - out->print_metric(config, out->ctx, NULL, NULL, "frontend cycles idle", 0); + print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios, + "frontend cycles idle"); } -static void print_stalled_cycles_backend(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_stalled_cycles_back(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double stalled, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {75.0, 50.0, 20.0}; - color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - - out->print_metric(config, out->ctx, color, "%7.2f%%", "backend cycles idle", ratio); + print_ratio(config, evsel, aggr_idx, stalled, out, STAT_CYCLES, color_ratios, + "backend cycles idle"); } -static void print_branch_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_branch_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_BRANCHES, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all branches", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_BRANCHES, color_ratios, + "of all branches"); } -static void print_l1_dcache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_l1d_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_L1_DCACHE, aggr_idx, rsd); + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - if (total) - ratio = avg / total * 100.0; + print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_DCACHE, color_ratios, + "of all L1-dcache accesses"); +} - color = get_ratio_color(GRC_CACHE_MISSES, ratio); +static void print_l1i_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-dcache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_L1_ICACHE, color_ratios, + "of all L1-icache accesses"); } -static void print_l1_icache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_ll_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - total = runtime_stat_avg(STAT_L1_ICACHE, aggr_idx, rsd); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_LL_CACHE, color_ratios, + "of all L1-icache accesses"); +} - if (total) - ratio = avg / total * 100.0; +static void print_dtlb_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all L1-icache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_DTLB_CACHE, color_ratios, + "of all dTLB cache accesses"); } -static void print_dtlb_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_itlb_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - total = runtime_stat_avg(STAT_DTLB_CACHE, aggr_idx, rsd); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_ITLB_CACHE, color_ratios, + "of all iTLB cache accesses"); +} - if (total) - ratio = avg / total * 100.0; +static void print_cache_miss(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out) +{ + static const double color_ratios[3] = {20.0, 10.0, 5.0}; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all dTLB cache accesses", ratio); + print_ratio(config, evsel, aggr_idx, misses, out, STAT_CACHE_REFS, color_ratios, + "of all cache refs"); } -static void print_itlb_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_instructions(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double instructions, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; + double cycles = find_stat(evsel, aggr_idx, STAT_CYCLES); + double max_stalled = max(find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_FRONT), + find_stat(evsel, aggr_idx, STAT_STALLED_CYCLES_BACK)); + + if (cycles) { + print_metric(config, ctxp, NULL, "%7.2f ", "insn per cycle", + instructions / cycles); + } else + print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); + + if (max_stalled && instructions) { + out->new_line(config, ctxp); + print_metric(config, ctxp, NULL, "%7.2f ", "stalled cycles per insn", + max_stalled / instructions); + } +} - total = runtime_stat_avg(STAT_ITLB_CACHE, aggr_idx, rsd); +static void print_cycles(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double cycles, + struct perf_stat_output_ctx *out) +{ + double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); - if (total) - ratio = avg / total * 100.0; + if (cycles && nsecs) { + double ratio = cycles / nsecs; - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all iTLB cache accesses", ratio); + out->print_metric(config, out->ctx, NULL, "%8.3f", "GHz", ratio); + } else + out->print_metric(config, out->ctx, NULL, NULL, "GHz", 0); } -static void print_ll_cache_misses(struct perf_stat_config *config, - int aggr_idx, double avg, - struct perf_stat_output_ctx *out, - struct runtime_stat_data *rsd) +static void print_nsecs(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx __maybe_unused, double nsecs, + struct perf_stat_output_ctx *out) { - double total, ratio = 0.0; - const char *color; - - total = runtime_stat_avg(STAT_LL_CACHE, aggr_idx, rsd); - - if (total) - ratio = avg / total * 100.0; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; + double wall_time = avg_stats(&walltime_nsecs_stats); - color = get_ratio_color(GRC_CACHE_MISSES, ratio); - out->print_metric(config, out->ctx, color, "%7.2f%%", "of all LL-cache accesses", ratio); + if (wall_time) { + print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", + nsecs / (wall_time * evsel->scale)); + } else + print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); } static int prepare_metric(struct evsel **metric_events, @@ -638,139 +730,51 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config, struct perf_stat_output_ctx *out, struct rblist *metric_events) { - void *ctxp = out->ctx; - print_metric_t print_metric = out->print_metric; - double total, ratio = 0.0; - struct runtime_stat_data rsd = { - .ctx = evsel_context(evsel), - .cgrp = evsel->cgrp, + typedef void (*stat_print_function_t)(struct perf_stat_config *config, + const struct evsel *evsel, + int aggr_idx, double misses, + struct perf_stat_output_ctx *out); + static const stat_print_function_t stat_print_function[STAT_MAX] = { + [STAT_INSTRUCTIONS] = print_instructions, + [STAT_BRANCH_MISS] = print_branch_miss, + [STAT_L1D_MISS] = print_l1d_miss, + [STAT_L1I_MISS] = print_l1i_miss, + [STAT_DTLB_MISS] = print_dtlb_miss, + [STAT_ITLB_MISS] = print_itlb_miss, + [STAT_LL_MISS] = print_ll_miss, + [STAT_CACHE_MISSES] = print_cache_miss, + [STAT_STALLED_CYCLES_FRONT] = print_stalled_cycles_front, + [STAT_STALLED_CYCLES_BACK] = print_stalled_cycles_back, + [STAT_CYCLES] = print_cycles, + [STAT_NSECS] = print_nsecs, }; + print_metric_t print_metric = out->print_metric; + void *ctxp = out->ctx; struct metric_event *me; int num = 1; if (config->iostat_run) { iostat_print_metric(config, evsel, out); - } else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = runtime_stat_avg(STAT_CYCLES, aggr_idx, &rsd); - - if (total) { - ratio = avg / total; - print_metric(config, ctxp, NULL, "%7.2f ", - "insn per cycle", ratio); - } else { - print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0); - } - - total = runtime_stat_avg(STAT_STALLED_CYCLES_FRONT, aggr_idx, &rsd); - - total = max(total, runtime_stat_avg(STAT_STALLED_CYCLES_BACK, - aggr_idx, &rsd)); - - if (total && avg) { - out->new_line(config, ctxp); - ratio = total / avg; - print_metric(config, ctxp, NULL, "%7.2f ", - "stalled cycles per insn", - ratio); - } - } else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) { - if (runtime_stat_n(STAT_BRANCHES, aggr_idx, &rsd) != 0) - print_branch_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all branches", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1D | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_L1_DCACHE, aggr_idx, &rsd) != 0) - print_l1_dcache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_L1I | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_L1_ICACHE, aggr_idx, &rsd) != 0) - print_l1_icache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_DTLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_DTLB_CACHE, aggr_idx, &rsd) != 0) - print_dtlb_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_ITLB | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_ITLB_CACHE, aggr_idx, &rsd) != 0) - print_itlb_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0); - } else if ( - evsel->core.attr.type == PERF_TYPE_HW_CACHE && - evsel->core.attr.config == ( PERF_COUNT_HW_CACHE_LL | - ((PERF_COUNT_HW_CACHE_OP_READ) << 8) | - ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) { - - if (runtime_stat_n(STAT_LL_CACHE, aggr_idx, &rsd) != 0) - print_ll_cache_misses(config, aggr_idx, avg, out, &rsd); - else - print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0); - } else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) { - total = runtime_stat_avg(STAT_CACHEREFS, aggr_idx, &rsd); - - if (total) - ratio = avg * 100 / total; - - if (runtime_stat_n(STAT_CACHEREFS, aggr_idx, &rsd) != 0) - print_metric(config, ctxp, NULL, "%8.3f %%", - "of all cache refs", ratio); - else - print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0); - } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) { - print_stalled_cycles_frontend(config, aggr_idx, avg, out, &rsd); - } else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) { - print_stalled_cycles_backend(config, aggr_idx, avg, out, &rsd); - } else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); - - if (total) { - ratio = avg / total; - print_metric(config, ctxp, NULL, "%8.3f", "GHz", ratio); - } else { - print_metric(config, ctxp, NULL, NULL, "Ghz", 0); - } - } else if (evsel__is_clock(evsel)) { - if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0) - print_metric(config, ctxp, NULL, "%8.3f", "CPUs utilized", - avg / (ratio * evsel->scale)); - else - print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0); - } else if (runtime_stat_n(STAT_NSECS, aggr_idx, &rsd) != 0) { - char unit = ' '; - char unit_buf[10] = "/sec"; - - total = runtime_stat_avg(STAT_NSECS, aggr_idx, &rsd); - if (total) - ratio = convert_unit_double(1000000000.0 * avg / total, &unit); - - if (unit != ' ') - snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); - print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); } else { - num = 0; + stat_print_function_t fn = stat_print_function[evsel__stat_type(evsel)]; + + if (fn) + fn(config, evsel, aggr_idx, avg, out); + else { + double nsecs = find_stat(evsel, aggr_idx, STAT_NSECS); + + if (nsecs) { + char unit = ' '; + char unit_buf[10] = "/sec"; + double ratio = convert_unit_double(1000000000.0 * avg / nsecs, + &unit); + + if (unit != ' ') + snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit); + print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio); + } else + num = 0; + } } if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) { -- GitLab From aa0964e3ecebe92243bac30f9317117037adecb9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Feb 2023 01:28:48 -0800 Subject: [PATCH 0052/5631] perf stat: Remove saved_value/runtime_stat As saved_value/runtime_stat are only written to and not read, remove the associated logic and writes. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexandre Torgue Cc: Andrii Nakryiko Cc: Athira Rajeev Cc: Caleb Biggers Cc: Eduard Zingerman Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Maxime Coquelin Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sandipan Das Cc: Sean Christopherson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-52-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 - tools/perf/builtin-stat.c | 6 - tools/perf/tests/parse-metric.c | 1 - tools/perf/tests/pmu-events.c | 1 - tools/perf/util/stat-shadow.c | 198 -------------------------------- tools/perf/util/stat.c | 24 ---- tools/perf/util/stat.h | 4 - 7 files changed, 239 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index e9b5387161df..522226114263 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2072,9 +2072,6 @@ static void perf_sample__fprint_metric(struct perf_script *script, if (evsel_script(leader)->gnum++ == 0) perf_stat__reset_shadow_stats(); val = sample->period * evsel->scale; - perf_stat__update_shadow_stats(evsel, - val, - sample->cpu); evsel_script(evsel)->val = val; if (evsel_script(leader)->gnum == leader->core.nr_members) { for_each_group_member (ev2, leader) { @@ -2792,8 +2789,6 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); - perf_stat__init_shadow_stats(); - /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 619387459914..d70b1ec88594 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -424,7 +424,6 @@ static void process_counters(void) perf_stat_merge_counters(&stat_config, evsel_list); perf_stat_process_percore(&stat_config, evsel_list); - perf_stat_process_shadow_stats(&stat_config, evsel_list); } static void process_interval(void) @@ -434,7 +433,6 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); - perf_stat__reset_shadow_per_stat(); evlist__reset_aggr_stats(evsel_list); if (read_counters(&rs) == 0) @@ -910,7 +908,6 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) evlist__copy_prev_raw_counts(evsel_list); evlist__reset_prev_raw_counts(evsel_list); evlist__reset_aggr_stats(evsel_list); - perf_stat__reset_shadow_per_stat(); } else { update_stats(&walltime_nsecs_stats, t1 - t0); update_rusage_stats(&ru_stats, &stat_config.ru_data); @@ -2132,8 +2129,6 @@ static int __cmd_report(int argc, const char **argv) input_name = "perf.data"; } - perf_stat__init_shadow_stats(); - perf_stat.data.path = input_name; perf_stat.data.mode = PERF_DATA_MODE_READ; @@ -2413,7 +2408,6 @@ int cmd_stat(int argc, const char **argv) &stat_config.metric_events); zfree(&metrics); } - perf_stat__init_shadow_stats(); if (add_default_attributes()) goto out; diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index b9b8a48289c4..c43b056f9fa3 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -296,7 +296,6 @@ static int test_metric_group(void) static int test__parse_metric(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { - perf_stat__init_shadow_stats(); TEST_ASSERT_VAL("IPC failed", test_ipc() == 0); TEST_ASSERT_VAL("frontend failed", test_frontend() == 0); TEST_ASSERT_VAL("DCache_L2 failed", test_dcache_l2() == 0); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 4ec2a4ca1a82..6ccd413b5983 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -905,7 +905,6 @@ static int test__parsing(struct test_suite *test __maybe_unused, { int failures = 0; - perf_stat__init_shadow_stats(); pmu_for_each_core_metric(test__parsing_callback, &failures); pmu_for_each_sys_metric(test__parsing_callback, &failures); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index 9d22cde09dc9..ef85f1ae1ab2 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -16,22 +16,9 @@ #include "iostat.h" #include "util/hashmap.h" -/* - * AGGR_GLOBAL: Use CPU 0 - * AGGR_SOCKET: Use first CPU of socket - * AGGR_DIE: Use first CPU of die - * AGGR_CORE: Use first CPU of core - * AGGR_NONE: Use matching CPU - * AGGR_THREAD: Not supported? - */ - struct stats walltime_nsecs_stats; struct rusage_stats ru_stats; -static struct runtime_stat { - struct rblist value_list; -} rt_stat; - enum { CTX_BIT_USER = 1 << 0, CTX_BIT_KERNEL = 1 << 1, @@ -65,117 +52,6 @@ enum stat_type { STAT_MAX }; -struct saved_value { - struct rb_node rb_node; - struct evsel *evsel; - enum stat_type type; - int ctx; - int map_idx; /* cpu or thread map index */ - struct cgroup *cgrp; - struct stats stats; - u64 metric_total; - int metric_other; -}; - -static int saved_value_cmp(struct rb_node *rb_node, const void *entry) -{ - struct saved_value *a = container_of(rb_node, - struct saved_value, - rb_node); - const struct saved_value *b = entry; - - if (a->map_idx != b->map_idx) - return a->map_idx - b->map_idx; - - /* - * Previously the rbtree was used to link generic metrics. - * The keys were evsel/cpu. Now the rbtree is extended to support - * per-thread shadow stats. For shadow stats case, the keys - * are cpu/type/ctx/stat (evsel is NULL). For generic metrics - * case, the keys are still evsel/cpu (type/ctx/stat are 0 or NULL). - */ - if (a->type != b->type) - return a->type - b->type; - - if (a->ctx != b->ctx) - return a->ctx - b->ctx; - - if (a->cgrp != b->cgrp) - return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1; - - if (a->evsel == b->evsel) - return 0; - if ((char *)a->evsel < (char *)b->evsel) - return -1; - return +1; -} - -static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, - const void *entry) -{ - struct saved_value *nd = malloc(sizeof(struct saved_value)); - - if (!nd) - return NULL; - memcpy(nd, entry, sizeof(struct saved_value)); - return &nd->rb_node; -} - -static void saved_value_delete(struct rblist *rblist __maybe_unused, - struct rb_node *rb_node) -{ - struct saved_value *v; - - BUG_ON(!rb_node); - v = container_of(rb_node, struct saved_value, rb_node); - free(v); -} - -static struct saved_value *saved_value_lookup(struct evsel *evsel, - int map_idx, - bool create, - enum stat_type type, - int ctx, - struct cgroup *cgrp) -{ - struct rblist *rblist; - struct rb_node *nd; - struct saved_value dm = { - .map_idx = map_idx, - .evsel = evsel, - .type = type, - .ctx = ctx, - .cgrp = cgrp, - }; - - rblist = &rt_stat.value_list; - - /* don't use context info for clock events */ - if (type == STAT_NSECS) - dm.ctx = 0; - - nd = rblist__find(rblist, &dm); - if (nd) - return container_of(nd, struct saved_value, rb_node); - if (create) { - rblist__add_node(rblist, &dm); - nd = rblist__find(rblist, &dm); - if (nd) - return container_of(nd, struct saved_value, rb_node); - } - return NULL; -} - -void perf_stat__init_shadow_stats(void) -{ - struct rblist *rblist = &rt_stat.value_list; - - rblist__init(rblist); - rblist->node_cmp = saved_value_cmp; - rblist->node_new = saved_value_new; - rblist->node_delete = saved_value_delete; -} - static int evsel_context(const struct evsel *evsel) { int ctx = 0; @@ -194,86 +70,12 @@ static int evsel_context(const struct evsel *evsel) return ctx; } -void perf_stat__reset_shadow_per_stat(void) -{ - struct rblist *rblist; - struct rb_node *pos, *next; - - rblist = &rt_stat.value_list; - next = rb_first_cached(&rblist->entries); - while (next) { - pos = next; - next = rb_next(pos); - memset(&container_of(pos, struct saved_value, rb_node)->stats, - 0, - sizeof(struct stats)); - } -} - void perf_stat__reset_shadow_stats(void) { - perf_stat__reset_shadow_per_stat(); memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); memset(&ru_stats, 0, sizeof(ru_stats)); } -struct runtime_stat_data { - int ctx; - struct cgroup *cgrp; -}; - -static void update_runtime_stat(enum stat_type type, - int map_idx, u64 count, - struct runtime_stat_data *rsd) -{ - struct saved_value *v = saved_value_lookup(NULL, map_idx, true, type, - rsd->ctx, rsd->cgrp); - - if (v) - update_stats(&v->stats, count); -} - -/* - * Update various tracking values we maintain to print - * more semantic information such as miss/hit ratios, - * instruction rates, etc: - */ -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, - int aggr_idx) -{ - u64 count_ns = count; - struct runtime_stat_data rsd = { - .ctx = evsel_context(counter), - .cgrp = counter->cgrp, - }; - count *= counter->scale; - - if (evsel__is_clock(counter)) - update_runtime_stat(STAT_NSECS, aggr_idx, count_ns, &rsd); - else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_runtime_stat(STAT_CYCLES, aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_runtime_stat(STAT_STALLED_CYCLES_FRONT, - aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_runtime_stat(STAT_STALLED_CYCLES_BACK, - aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_runtime_stat(STAT_BRANCHES, aggr_idx, count, &rsd); - else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_runtime_stat(STAT_CACHE_REFS, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_runtime_stat(STAT_L1_DCACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_runtime_stat(STAT_L1_ICACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_runtime_stat(STAT_LL_CACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_runtime_stat(STAT_DTLB_CACHE, aggr_idx, count, &rsd); - else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_runtime_stat(STAT_ITLB_CACHE, aggr_idx, count, &rsd); -} - static enum stat_type evsel__stat_type(const struct evsel *evsel) { /* Fake perf_hw_cache_op_id values for use with evsel__match. */ diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 83dc4c1f4b12..4abfd87c5352 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -648,30 +648,6 @@ void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *e evsel__process_percore(evsel); } -static void evsel__update_shadow_stats(struct evsel *evsel) -{ - struct perf_stat_evsel *ps = evsel->stats; - int aggr_idx; - - if (ps->aggr == NULL) - return; - - for (aggr_idx = 0; aggr_idx < ps->nr_aggr; aggr_idx++) { - struct perf_counts_values *aggr_counts = &ps->aggr[aggr_idx].counts; - - perf_stat__update_shadow_stats(evsel, aggr_counts->val, aggr_idx); - } -} - -void perf_stat_process_shadow_stats(struct perf_stat_config *config __maybe_unused, - struct evlist *evlist) -{ - struct evsel *evsel; - - evlist__for_each_entry(evlist, evsel) - evsel__update_shadow_stats(evsel); -} - int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index b01c828c3799..41204547b76b 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -157,10 +157,7 @@ typedef void (*print_metric_t)(struct perf_stat_config *config, const char *fmt, double val); typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx); -void perf_stat__init_shadow_stats(void); void perf_stat__reset_shadow_stats(void); -void perf_stat__reset_shadow_per_stat(void); -void perf_stat__update_shadow_stats(struct evsel *counter, u64 count, int aggr_idx); struct perf_stat_output_ctx { void *ctx; print_metric_t print_metric; @@ -189,7 +186,6 @@ int perf_stat_process_counter(struct perf_stat_config *config, struct evsel *counter); void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist); void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *evlist); -void perf_stat_process_shadow_stats(struct perf_stat_config *config, struct evlist *evlist); struct perf_tool; union perf_event; -- GitLab From 40e40fdfec3faf08951c2a600177e23f4d43fc32 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Tue, 21 Feb 2023 11:41:45 -0800 Subject: [PATCH 0053/5631] Input: bbnsm_pwrkey - add bbnsm power key support The ON/OFF logic inside the BBNSM allows for connecting directly into a PMIC or other voltage regulator device. The module has an button input signal and a wakeup request input signal. It also has two interrupts (set_pwr_off_irq and set_pwr_on_irq) and an active-low PMIC enable (pmic_en_b) output. Add the power key support for the ON/OFF button function found in BBNSM module. Signed-off-by: Jacky Bai Reviewed-by: Peng Fan Link: https://lore.kernel.org/r/20230215024117.3357341-2-ping.bai@nxp.com Signed-off-by: Dmitry Torokhov --- drivers/input/misc/Kconfig | 11 ++ drivers/input/misc/Makefile | 1 + drivers/input/misc/nxp-bbnsm-pwrkey.c | 193 ++++++++++++++++++++++++++ 3 files changed, 205 insertions(+) create mode 100644 drivers/input/misc/nxp-bbnsm-pwrkey.c diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 5c2d0c06d2a5..81a54a59e13c 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -119,6 +119,17 @@ config INPUT_ATMEL_CAPTOUCH To compile this driver as a module, choose M here: the module will be called atmel_captouch. +config INPUT_BBNSM_PWRKEY + tristate "NXP BBNSM Power Key Driver" + depends on ARCH_MXC || COMPILE_TEST + depends on OF + help + This is the bbnsm powerkey driver for the NXP i.MX application + processors. + + To compile this driver as a module, choose M here; the + module will be called bbnsm_pwrkey. + config INPUT_BMA150 tristate "BMA150/SMB380 acceleration sensor support" depends on I2C diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index 61949263300d..04296a4abe8e 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_INPUT_ATC260X_ONKEY) += atc260x-onkey.o obj-$(CONFIG_INPUT_ATI_REMOTE2) += ati_remote2.o obj-$(CONFIG_INPUT_ATLAS_BTNS) += atlas_btns.o obj-$(CONFIG_INPUT_ATMEL_CAPTOUCH) += atmel_captouch.o +obj-$(CONFIG_INPUT_BBNSM_PWRKEY) += nxp-bbnsm-pwrkey.o obj-$(CONFIG_INPUT_BMA150) += bma150.o obj-$(CONFIG_INPUT_CM109) += cm109.o obj-$(CONFIG_INPUT_CMA3000) += cma3000_d0x.o diff --git a/drivers/input/misc/nxp-bbnsm-pwrkey.c b/drivers/input/misc/nxp-bbnsm-pwrkey.c new file mode 100644 index 000000000000..1d99206dd3a8 --- /dev/null +++ b/drivers/input/misc/nxp-bbnsm-pwrkey.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright 2022 NXP. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define BBNSM_CTRL 0x8 +#define BBNSM_INT_EN 0x10 +#define BBNSM_EVENTS 0x14 +#define BBNSM_PAD_CTRL 0x24 + +#define BBNSM_BTN_PRESSED BIT(7) +#define BBNSM_PWR_ON BIT(6) +#define BBNSM_BTN_OFF BIT(5) +#define BBNSM_EMG_OFF BIT(4) +#define BBNSM_PWRKEY_EVENTS (BBNSM_PWR_ON | BBNSM_BTN_OFF | BBNSM_EMG_OFF) +#define BBNSM_DP_EN BIT(24) + +#define DEBOUNCE_TIME 30 +#define REPEAT_INTERVAL 60 + +struct bbnsm_pwrkey { + struct regmap *regmap; + int irq; + int keycode; + int keystate; /* 1:pressed */ + struct timer_list check_timer; + struct input_dev *input; +}; + +static void bbnsm_pwrkey_check_for_events(struct timer_list *t) +{ + struct bbnsm_pwrkey *bbnsm = from_timer(bbnsm, t, check_timer); + struct input_dev *input = bbnsm->input; + u32 state; + + regmap_read(bbnsm->regmap, BBNSM_EVENTS, &state); + + state = state & BBNSM_BTN_PRESSED ? 1 : 0; + + /* only report new event if status changed */ + if (state ^ bbnsm->keystate) { + bbnsm->keystate = state; + input_event(input, EV_KEY, bbnsm->keycode, state); + input_sync(input); + pm_relax(bbnsm->input->dev.parent); + } + + /* repeat check if pressed long */ + if (state) + mod_timer(&bbnsm->check_timer, + jiffies + msecs_to_jiffies(REPEAT_INTERVAL)); +} + +static irqreturn_t bbnsm_pwrkey_interrupt(int irq, void *dev_id) +{ + struct platform_device *pdev = dev_id; + struct bbnsm_pwrkey *bbnsm = platform_get_drvdata(pdev); + u32 event; + + regmap_read(bbnsm->regmap, BBNSM_EVENTS, &event); + if (!(event & BBNSM_BTN_OFF)) + return IRQ_NONE; + + pm_wakeup_event(bbnsm->input->dev.parent, 0); + + mod_timer(&bbnsm->check_timer, + jiffies + msecs_to_jiffies(DEBOUNCE_TIME)); + + /* clear PWR OFF */ + regmap_write(bbnsm->regmap, BBNSM_EVENTS, BBNSM_BTN_OFF); + + return IRQ_HANDLED; +} + +static void bbnsm_pwrkey_act(void *pdata) +{ + struct bbnsm_pwrkey *bbnsm = pdata; + + timer_shutdown_sync(&bbnsm->check_timer); +} + +static int bbnsm_pwrkey_probe(struct platform_device *pdev) +{ + struct bbnsm_pwrkey *bbnsm; + struct input_dev *input; + struct device_node *np = pdev->dev.of_node; + int error; + + bbnsm = devm_kzalloc(&pdev->dev, sizeof(*bbnsm), GFP_KERNEL); + if (!bbnsm) + return -ENOMEM; + + bbnsm->regmap = syscon_node_to_regmap(np->parent); + if (IS_ERR(bbnsm->regmap)) { + dev_err(&pdev->dev, "bbnsm pwerkey get regmap failed\n"); + return PTR_ERR(bbnsm->regmap); + } + + if (device_property_read_u32(&pdev->dev, "linux,code", + &bbnsm->keycode)) { + bbnsm->keycode = KEY_POWER; + dev_warn(&pdev->dev, "key code is not specified, using default KEY_POWER\n"); + } + + bbnsm->irq = platform_get_irq(pdev, 0); + if (bbnsm->irq < 0) + return -EINVAL; + + /* config the BBNSM power related register */ + regmap_update_bits(bbnsm->regmap, BBNSM_CTRL, BBNSM_DP_EN, BBNSM_DP_EN); + + /* clear the unexpected interrupt before driver ready */ + regmap_write_bits(bbnsm->regmap, BBNSM_EVENTS, BBNSM_PWRKEY_EVENTS, + BBNSM_PWRKEY_EVENTS); + + timer_setup(&bbnsm->check_timer, bbnsm_pwrkey_check_for_events, 0); + + input = devm_input_allocate_device(&pdev->dev); + if (!input) { + dev_err(&pdev->dev, "failed to allocate the input device\n"); + return -ENOMEM; + } + + input->name = pdev->name; + input->phys = "bbnsm-pwrkey/input0"; + input->id.bustype = BUS_HOST; + + input_set_capability(input, EV_KEY, bbnsm->keycode); + + /* input customer action to cancel release timer */ + error = devm_add_action(&pdev->dev, bbnsm_pwrkey_act, bbnsm); + if (error) { + dev_err(&pdev->dev, "failed to register remove action\n"); + return error; + } + + bbnsm->input = input; + platform_set_drvdata(pdev, bbnsm); + + error = devm_request_irq(&pdev->dev, bbnsm->irq, bbnsm_pwrkey_interrupt, + IRQF_SHARED, pdev->name, pdev); + if (error) { + dev_err(&pdev->dev, "interrupt not available.\n"); + return error; + } + + error = input_register_device(input); + if (error) { + dev_err(&pdev->dev, "failed to register input device\n"); + return error; + } + + device_init_wakeup(&pdev->dev, true); + error = dev_pm_set_wake_irq(&pdev->dev, bbnsm->irq); + if (error) + dev_warn(&pdev->dev, "irq wake enable failed.\n"); + + return 0; +} + +static const struct of_device_id bbnsm_pwrkey_ids[] = { + { .compatible = "nxp,imx93-bbnsm-pwrkey" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, bbnsm_pwrkey_ids); + +static struct platform_driver bbnsm_pwrkey_driver = { + .driver = { + .name = "bbnsm_pwrkey", + .of_match_table = bbnsm_pwrkey_ids, + }, + .probe = bbnsm_pwrkey_probe, +}; +module_platform_driver(bbnsm_pwrkey_driver); + +MODULE_AUTHOR("Jacky Bai "); +MODULE_DESCRIPTION("NXP bbnsm power key Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 4b665e1781e2cd64b3b9492e49156925ba02bfa9 Mon Sep 17 00:00:00 2001 From: Gergo Koteles Date: Tue, 21 Feb 2023 11:47:48 -0800 Subject: [PATCH 0054/5631] Input: gpio-keys - add support for linux,input-value DTS property Allows setting the value of EV_ABS events from DTS. This property is included in the gpio-keys.yaml scheme, but was only implemented for gpio-keys-polled. Signed-off-by: Gergo Koteles Link: https://lore.kernel.org/r/3519a11b0ef5324a2befbd137cd2aa0cb8fd057d.1676850819.git.soyer@irl.hu Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/gpio_keys.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c index 5496482a38c1..c42f86ad0766 100644 --- a/drivers/input/keyboard/gpio_keys.c +++ b/drivers/input/keyboard/gpio_keys.c @@ -770,6 +770,9 @@ gpio_keys_get_devtree_pdata(struct device *dev) &button->type)) button->type = EV_KEY; + fwnode_property_read_u32(child, "linux,input-value", + (u32 *)&button->value); + button->wakeup = fwnode_property_read_bool(child, "wakeup-source") || /* legacy name */ -- GitLab From c6f3b684c2c4e8d4700fe8c4a173c0a70df6cc14 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 21 Feb 2023 13:25:17 -0800 Subject: [PATCH 0055/5631] dt-bindings: google,cros-ec-keyb: Fix spelling error The dependency had an obvious spelling error. Fix it. Signed-off-by: Linus Walleij Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230220135531.1987351-1-linus.walleij@linaro.org Signed-off-by: Dmitry Torokhov --- .../devicetree/bindings/input/google,cros-ec-keyb.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml index e05690b3e963..a8abdb39623b 100644 --- a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml +++ b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml @@ -45,7 +45,7 @@ properties: when the keyboard has a custom design for the top row keys. dependencies: - function-row-phsymap: [ 'linux,keymap' ] + function-row-physmap: [ 'linux,keymap' ] google,needs-ghost-filter: [ 'linux,keymap' ] required: -- GitLab From 586dc36226dd748b197eea8642c087cae611129b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 9 Feb 2023 16:44:06 -0800 Subject: [PATCH 0056/5631] Input: hp_sdc_rtc - mark an unused function as __maybe_unused When CONFIG_PROC_FS is not set, one procfs-related function is not used, causing a build error or warning. Mark this function as __maybe_unused to quieten the build. ../drivers/input/misc/hp_sdc_rtc.c:268:12: warning: 'hp_sdc_rtc_proc_show' defined but not used [-Wunused-function] 268 | static int hp_sdc_rtc_proc_show(struct seq_file *m, void *v) | ^~~~~~~~~~~~~~~~~~~~ Fixes: c18bd9a1ff47 ("hp_sdc_rtc: Don't use create_proc_read_entry()") Signed-off-by: Randy Dunlap Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230209010125.23690-1-rdunlap@infradead.org Signed-off-by: Dmitry Torokhov --- drivers/input/misc/hp_sdc_rtc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c index 199bc17ddb1d..afc0d6dc5787 100644 --- a/drivers/input/misc/hp_sdc_rtc.c +++ b/drivers/input/misc/hp_sdc_rtc.c @@ -265,7 +265,7 @@ static inline int hp_sdc_rtc_read_ct(struct timespec64 *res) { return 0; } -static int hp_sdc_rtc_proc_show(struct seq_file *m, void *v) +static int __maybe_unused hp_sdc_rtc_proc_show(struct seq_file *m, void *v) { #define YN(bit) ("no") #define NY(bit) ("yes") -- GitLab From 9e03024ce27625e42d3a9a76af37f5369db652cd Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 23 Feb 2023 22:11:21 -0800 Subject: [PATCH 0057/5631] ARM: spitz: include header defining input event codes The board file for Sharp SL-Cxx00 Series of PDAs uses various KEY_* defines, but does not include the relevant header directly and instead relies on other headers to include it indirectly. With the upcoming cleanup of matrix_keypad.h this indirection is now broken and we should include the relevant header directly. Reported: Guenter Roeck Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/Y/U+3PZsbLw++SnG@google.com Signed-off-by: Dmitry Torokhov --- arch/arm/mach-pxa/spitz.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 9964729cd428..75634ef6688d 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include -- GitLab From d5f7638eb5fed0eb12e45a127764c4111b11c50e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 24 Oct 2022 05:34:14 -0700 Subject: [PATCH 0058/5631] Input: matrix_keypad - replace header inclusions by forward declarations When the data structure is only referred by pointer, compiler may not need to see the contents of the data type. Thus, we may replace header inclusions by respective forward declarations. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220923184632.2157-2-andriy.shevchenko@linux.intel.com Signed-off-by: Dmitry Torokhov --- include/linux/input/matrix_keypad.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 9476768c3b90..b8d8d69eba29 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -3,8 +3,9 @@ #define _MATRIX_KEYPAD_H #include -#include -#include + +struct device; +struct input_dev; #define MATRIX_MAX_ROWS 32 #define MATRIX_MAX_COLS 32 -- GitLab From b0365c147f7b2aeb500456601bf6a3e08133b178 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Feb 2023 21:53:04 -0800 Subject: [PATCH 0059/5631] perf vendor events intel: Update alderlake to v1.19 Update alderlake perf json from v1.18 to v1.19. Based on: https://github.com/intel/perfmon/pull/58 perf JSON files created using: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230223055306.296179-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/alderlake/memory.json | 8 ++++++++ tools/perf/pmu-events/arch/x86/alderlake/pipeline.json | 10 ++++++++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 37f3d062a788..55827b276e6e 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -24,6 +24,14 @@ "UMask": "0xf4", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", "EventCode": "0x05", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index 2dba3a115f97..f848530fbf07 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -361,6 +361,16 @@ "UMask": "0xeb", "Unit": "cpu_atom" }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PEBS": "1", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80", + "Unit": "cpu_core" + }, { "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired.", "EventCode": "0xc5", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 1c6eef118e61..e69b29123327 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,5 +1,5 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.18,alderlake,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.19,alderlake,core GenuineIntel-6-BE,v1.18,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v26,broadwell,core -- GitLab From b42d103bc02de484dc4aefe457ffcc35637b6754 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Feb 2023 21:53:05 -0800 Subject: [PATCH 0060/5631] perf vendor events intel: Update alderlaken to v1.19 Update alderlaken perf json from v1.18 to v1.19. Based on: https://github.com/intel/perfmon/pull/58 perf JSON files created using: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230223055306.296179-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/alderlaken/memory.json | 7 +++++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json index f84bf8c43495..37259d38a222 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json @@ -13,6 +13,13 @@ "SampleAfterValue": "1000003", "UMask": "0xf4" }, + { + "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to a DL1 miss.", + "EventCode": "0x05", + "EventName": "LD_HEAD.L1_MISS_AT_RET", + "SampleAfterValue": "1000003", + "UMask": "0x81" + }, { "BriefDescription": "Counts the number of cycles that the head (oldest load) of the load buffer and retirement are both stalled due to other block cases.", "EventCode": "0x05", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index e69b29123327..1c5776e37120 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType GenuineIntel-6-(97|9A|B7|BA|BF),v1.19,alderlake,core -GenuineIntel-6-BE,v1.18,alderlaken,core +GenuineIntel-6-BE,v1.19,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v26,broadwell,core GenuineIntel-6-56,v7,broadwellde,core -- GitLab From 0ec73817ca21f6ed4f2cca44b63e81a688c0ba0b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Feb 2023 21:53:06 -0800 Subject: [PATCH 0061/5631] perf vendor events intel: Update icelakex to v1.19 Update icelakex perf json from v1.18 to v1.19. Based on: https://github.com/intel/perfmon/pull/58 perf JSON files created using: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230223055306.296179-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/icelakex/cache.json | 8 +++++ .../arch/x86/icelakex/floating-point.json | 31 +++++++++++++++++++ .../arch/x86/icelakex/pipeline.json | 10 ++++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 4 files changed, 50 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/icelakex/cache.json b/tools/perf/pmu-events/arch/x86/icelakex/cache.json index d6463c8d9462..3bdc56a75097 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/cache.json @@ -825,6 +825,14 @@ "SampleAfterValue": "1000003", "UMask": "0x1" }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0xF4", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, { "BriefDescription": "Cycles the queue waiting for offcore responses is full.", "EventCode": "0xf4", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/floating-point.json b/tools/perf/pmu-events/arch/x86/icelakex/floating-point.json index 655342dadac6..85c26c889088 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/floating-point.json @@ -39,6 +39,14 @@ "SampleAfterValue": "100003", "UMask": "0x20" }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, { "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -55,6 +63,22 @@ "SampleAfterValue": "100003", "UMask": "0x80" }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, { "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", @@ -70,5 +94,12 @@ "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "100003", "UMask": "0x2" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "1000003", + "UMask": "0xfc" } ] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json index 4cf16a1fcad4..442a4c7539dd 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json @@ -374,6 +374,16 @@ "SampleAfterValue": "2000003", "UMask": "0x3" }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, { "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", "EventCode": "0x0d", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 1c5776e37120..bb4e545fa100 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -13,7 +13,7 @@ GenuineIntel-6-A[DE],v1.00,graniterapids,core GenuineIntel-6-(3C|45|46),v32,haswell,core GenuineIntel-6-3F,v26,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core -GenuineIntel-6-6[AC],v1.18,icelakex,core +GenuineIntel-6-6[AC],v1.19,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core GenuineIntel-6-2D,v22,jaketown,core -- GitLab From 721da5cee9d43901105f5b8bd33fcb9101b12fc3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 23 Feb 2023 08:33:26 +0100 Subject: [PATCH 0062/5631] driver core: remove CONFIG_SYSFS_DEPRECATED and CONFIG_SYSFS_DEPRECATED_V2 CONFIG_SYSFS_DEPRECATED was added in commit 88a22c985e35 ("CONFIG_SYSFS_DEPRECATED") in 2006 to allow systems with older versions of some tools (i.e. Fedora 3's version of udev) to boot properly. Four years later, in 2010, the option was attempted to be removed as most of userspace should have been fixed up properly by then, but some kernel developers clung to those old systems and refused to update, so we added CONFIG_SYSFS_DEPRECATED_V2 in commit e52eec13cd6b ("SYSFS: Allow boot time switching between deprecated and modern sysfs layout") to allow them to continue to boot properly, and we allowed a boot time parameter to be used to switch back to the old format if needed. Over time, the logic that was covered under these config options was slowly removed from individual driver subsystems successfully, removed, and the only thing that is now left in the kernel are some changes in the block layer's representation in sysfs where real directories are used instead of symlinks like normal. Because the original changes were done to userspace tools in 2006, and all distros that use those tools are long end-of-life, and older non-udev-based systems do not care about the block layer's sysfs representation, it is time to finally remove this old logic and the config entries from the kernel. Cc: Jonathan Corbet Cc: "Rafael J. Wysocki" Cc: linux-block@vger.kernel.org Cc: linux-doc@vger.kernel.org Acked-by: Jens Axboe Link: https://lore.kernel.org/r/20230223073326.2073220-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- .../admin-guide/kernel-parameters.txt | 9 ----- block/genhd.c | 19 ++++------ drivers/base/class.c | 2 +- drivers/base/core.c | 37 ------------------ include/linux/device.h | 6 --- init/Kconfig | 38 ------------------- 6 files changed, 8 insertions(+), 103 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..207ca1d6e3d3 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6130,15 +6130,6 @@ later by a loaded module cannot be set this way. Example: sysctl.vm.swappiness=40 - sysfs.deprecated=0|1 [KNL] - Enable/disable old style sysfs layout for old udev - on older distributions. When this option is enabled - very new udev will not work anymore. When this option - is disabled (or CONFIG_SYSFS_DEPRECATED not compiled) - in older udev will not work anymore. - Default depends on CONFIG_SYSFS_DEPRECATED_V2 set in - the kernel configuration. - sysrq_always_enabled [KNL] Ignore sysrq setting - this boot parameter will diff --git a/block/genhd.c b/block/genhd.c index 3ee5577e1586..e1e1230b1b9f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -466,12 +466,10 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, if (ret) goto out_device_del; - if (!sysfs_deprecated) { - ret = sysfs_create_link(block_depr, &ddev->kobj, - kobject_name(&ddev->kobj)); - if (ret) - goto out_device_del; - } + ret = sysfs_create_link(block_depr, &ddev->kobj, + kobject_name(&ddev->kobj)); + if (ret) + goto out_device_del; /* * avoid probable deadlock caused by allocating memory with @@ -554,8 +552,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, out_del_integrity: blk_integrity_del(disk); out_del_block_link: - if (!sysfs_deprecated) - sysfs_remove_link(block_depr, dev_name(ddev)); + sysfs_remove_link(block_depr, dev_name(ddev)); out_device_del: device_del(ddev); out_free_ext_minor: @@ -657,8 +654,7 @@ void del_gendisk(struct gendisk *disk) part_stat_set_all(disk->part0, 0); disk->part0->bd_stamp = 0; - if (!sysfs_deprecated) - sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); + sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); @@ -912,8 +908,7 @@ static int __init genhd_device_init(void) register_blkdev(BLOCK_EXT_MAJOR, "blkext"); /* create top-level block dir */ - if (!sysfs_deprecated) - block_depr = kobject_create_and_add("block", NULL); + block_depr = kobject_create_and_add("block", NULL); return 0; } diff --git a/drivers/base/class.c b/drivers/base/class.c index 2373b3e210d8..fb8f2a1e1c19 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -180,7 +180,7 @@ int __class_register(struct class *cls, struct lock_class_key *key) #if defined(CONFIG_BLOCK) /* let the block class directory show up in the root of sysfs */ - if (!sysfs_deprecated || cls != &block_class) + if (cls != &block_class) cp->subsys.kobj.kset = class_kset; #else cp->subsys.kobj.kset = class_kset; diff --git a/drivers/base/core.c b/drivers/base/core.c index 6878dfcbf0d6..ba11b51ce4ee 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -36,19 +36,6 @@ #include "physical_location.h" #include "power/power.h" -#ifdef CONFIG_SYSFS_DEPRECATED -#ifdef CONFIG_SYSFS_DEPRECATED_V2 -long sysfs_deprecated = 1; -#else -long sysfs_deprecated = 0; -#endif -static int __init sysfs_deprecated_setup(char *arg) -{ - return kstrtol(arg, 10, &sysfs_deprecated); -} -early_param("sysfs.deprecated", sysfs_deprecated_setup); -#endif - /* Device links support. */ static LIST_HEAD(deferred_sync); static unsigned int defer_sync_state_count = 1; @@ -3137,15 +3124,6 @@ static struct kobject *get_device_parent(struct device *dev, struct kobject *parent_kobj; struct kobject *k; -#ifdef CONFIG_BLOCK - /* block disks show up in /sys/block */ - if (sysfs_deprecated && dev->class == &block_class) { - if (parent && parent->class == &block_class) - return &parent->kobj; - return &block_class.p->subsys.kobj; - } -#endif - /* * If we have no parent, we live in "virtual". * Class-devices with a non class-device as parent, live @@ -3324,12 +3302,6 @@ static int device_add_class_symlinks(struct device *dev) goto out_subsys; } -#ifdef CONFIG_BLOCK - /* /sys/block has directories and does not need symlinks */ - if (sysfs_deprecated && dev->class == &block_class) - return 0; -#endif - /* link in the class directory pointing to the device */ error = sysfs_create_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); @@ -3359,10 +3331,6 @@ static void device_remove_class_symlinks(struct device *dev) if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->kobj, "subsystem"); -#ifdef CONFIG_BLOCK - if (sysfs_deprecated && dev->class == &block_class) - return; -#endif sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); } @@ -4652,11 +4620,6 @@ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) if (error) goto out; -#ifdef CONFIG_BLOCK - if (sysfs_deprecated && dev->class == &block_class) - goto out; -#endif - /* * Change the owner of the symlink located in the class directory of * the device class associated with @dev which points to the actual diff --git a/include/linux/device.h b/include/linux/device.h index 1508e637bb26..19b6ba478fbf 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1092,10 +1092,4 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") -#ifdef CONFIG_SYSFS_DEPRECATED -extern long sysfs_deprecated; -#else -#define sysfs_deprecated 0 -#endif - #endif /* _DEVICE_H_ */ diff --git a/init/Kconfig b/init/Kconfig index 1fb5f313d18f..4464ef98ea0b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1297,44 +1297,6 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. -config SYSFS_DEPRECATED - bool "Enable deprecated sysfs features to support old userspace tools" - depends on SYSFS - default n - help - This option adds code that switches the layout of the "block" class - devices, to not show up in /sys/class/block/, but only in - /sys/block/. - - This switch is only active when the sysfs.deprecated=1 boot option is - passed or the SYSFS_DEPRECATED_V2 option is set. - - This option allows new kernels to run on old distributions and tools, - which might get confused by /sys/class/block/. Since 2007/2008 all - major distributions and tools handle this just fine. - - Recent distributions and userspace tools after 2009/2010 depend on - the existence of /sys/class/block/, and will not work with this - option enabled. - - Only if you are using a new kernel on an old distribution, you might - need to say Y here. - -config SYSFS_DEPRECATED_V2 - bool "Enable deprecated sysfs features by default" - default n - depends on SYSFS - depends on SYSFS_DEPRECATED - help - Enable deprecated sysfs by default. - - See the CONFIG_SYSFS_DEPRECATED option for more details about this - option. - - Only if you are using a new kernel on an old distribution, you might - need to say Y here. Even then, odds are you would not need it - enabled, you can always pass the boot option if absolutely necessary. - config RELAY bool "Kernel->user space relay support (formerly relayfs)" select IRQ_WORK -- GitLab From 8c3223a50faf1d173e0159eff10a9de902407135 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Sat, 18 Jun 2022 23:42:38 +0800 Subject: [PATCH 0063/5631] x86/entry: Change stale function name in comment to error_return() Correct old function name error_exit() in the comment to what it is now called: error_return(). [ bp: Provide a commit message and massage. ] Signed-off-by: Jingyu Wang Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20220618154238.27749-1-jingyuwang_vip@163.com --- arch/x86/entry/entry_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index eccc3431e515..048866c20ba6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1027,7 +1027,7 @@ SYM_CODE_START_LOCAL(paranoid_exit) * * NB to anyone to try to optimize this code: this code does * not execute at all for exceptions from user mode. Those - * exceptions go through error_exit instead. + * exceptions go through error_return instead. */ RESTORE_CR3 scratch_reg=%rax save_reg=%r14 -- GitLab From 75a2f9734e9bf297959a1e8cf16655a50075f531 Mon Sep 17 00:00:00 2001 From: Takeshi Kihara Date: Thu, 2 Feb 2023 01:03:14 +0000 Subject: [PATCH 0064/5631] clk: renesas: cpg-mssr: Update MSSR register range for R-Car V4H The SRCR, SRSTCLR, MSTPCR and MSTPSR registers for R-Car V4H (R8A779G0) each have registers up to offset 0x74. Update the corresponding arrays. Signed-off-by: Takeshi Kihara Signed-off-by: Kuninori Morimoto Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/87a61wanfx.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/renesas-cpg-mssr.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index b9f210437ddf..9927bc0dde97 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -61,7 +61,7 @@ static const u16 mstpsr_for_gen4[] = { 0x2E00, 0x2E04, 0x2E08, 0x2E0C, 0x2E10, 0x2E14, 0x2E18, 0x2E1C, 0x2E20, 0x2E24, 0x2E28, 0x2E2C, 0x2E30, 0x2E34, 0x2E38, 0x2E3C, 0x2E40, 0x2E44, 0x2E48, 0x2E4C, 0x2E50, 0x2E54, 0x2E58, 0x2E5C, - 0x2E60, 0x2E64, 0x2E68, 0x2E6C, + 0x2E60, 0x2E64, 0x2E68, 0x2E6C, 0x2E70, 0x2E74, }; /* @@ -77,7 +77,7 @@ static const u16 mstpcr_for_gen4[] = { 0x2D00, 0x2D04, 0x2D08, 0x2D0C, 0x2D10, 0x2D14, 0x2D18, 0x2D1C, 0x2D20, 0x2D24, 0x2D28, 0x2D2C, 0x2D30, 0x2D34, 0x2D38, 0x2D3C, 0x2D40, 0x2D44, 0x2D48, 0x2D4C, 0x2D50, 0x2D54, 0x2D58, 0x2D5C, - 0x2D60, 0x2D64, 0x2D68, 0x2D6C, + 0x2D60, 0x2D64, 0x2D68, 0x2D6C, 0x2D70, 0x2D74, }; /* @@ -103,7 +103,7 @@ static const u16 srcr_for_gen4[] = { 0x2C00, 0x2C04, 0x2C08, 0x2C0C, 0x2C10, 0x2C14, 0x2C18, 0x2C1C, 0x2C20, 0x2C24, 0x2C28, 0x2C2C, 0x2C30, 0x2C34, 0x2C38, 0x2C3C, 0x2C40, 0x2C44, 0x2C48, 0x2C4C, 0x2C50, 0x2C54, 0x2C58, 0x2C5C, - 0x2C60, 0x2C64, 0x2C68, 0x2C6C, + 0x2C60, 0x2C64, 0x2C68, 0x2C6C, 0x2C70, 0x2C74, }; /* @@ -119,7 +119,7 @@ static const u16 srstclr_for_gen4[] = { 0x2C80, 0x2C84, 0x2C88, 0x2C8C, 0x2C90, 0x2C94, 0x2C98, 0x2C9C, 0x2CA0, 0x2CA4, 0x2CA8, 0x2CAC, 0x2CB0, 0x2CB4, 0x2CB8, 0x2CBC, 0x2CC0, 0x2CC4, 0x2CC8, 0x2CCC, 0x2CD0, 0x2CD4, 0x2CD8, 0x2CDC, - 0x2CE0, 0x2CE4, 0x2CE8, 0x2CEC, + 0x2CE0, 0x2CE4, 0x2CE8, 0x2CEC, 0x2CF0, 0x2CF4, }; /** -- GitLab From 8dffb520ace48bcb996db049540c78261730213c Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 2 Feb 2023 01:03:24 +0000 Subject: [PATCH 0065/5631] clk: renesas: r8a779g0: Add Audio clocks Add module clocks for the Audio (SSI/SSIU) blocks on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Kuninori Morimoto Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/878rhganfo.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a779g0-cpg-mssr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 7fca11204f74..18a9462dab76 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -213,6 +213,8 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("pfc1", 916, R8A779G0_CLK_CL16M), DEF_MOD("pfc2", 917, R8A779G0_CLK_CL16M), DEF_MOD("pfc3", 918, R8A779G0_CLK_CL16M), + DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), + DEF_MOD("ssi", 2927, R8A779G0_CLK_S0D6_PER), }; /* -- GitLab From 7502a04dae0e614bc14553e31461e50499bc67aa Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 9 Feb 2023 17:03:00 +0100 Subject: [PATCH 0066/5631] clk: renesas: r8a779g0: Add thermal clock Add the module clock used by the Thermal Sensor/Chip Internal Voltage Monitor/Core Voltage Monitor (THS/CIVM/CVM) on the Renesas R-Car V4H (R8A779G0) SoC. Based on a large patch in the BSP by Kazuya Mizuguchi. Signed-off-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/59461effd0d9f7a39e0c91352c87f2b7071b1891.1675958536.git.geert+renesas@glider.be --- drivers/clk/renesas/r8a779g0-cpg-mssr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 18a9462dab76..e2e006a7ae4a 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -213,6 +213,7 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("pfc1", 916, R8A779G0_CLK_CL16M), DEF_MOD("pfc2", 917, R8A779G0_CLK_CL16M), DEF_MOD("pfc3", 918, R8A779G0_CLK_CL16M), + DEF_MOD("tsc", 919, R8A779G0_CLK_CL16M), DEF_MOD("ssiu", 2926, R8A779G0_CLK_S0D6_PER), DEF_MOD("ssi", 2927, R8A779G0_CLK_S0D6_PER), }; -- GitLab From 8b406fd422d568a407a98c2809c0b2c6bdc95be3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 15:36:53 +0100 Subject: [PATCH 0067/5631] clk: renesas: r8a779g0: Add CSI-2 clocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the CSI core clock and the CSI40 and CSI41 module clocks, which are used by the CSI-2 Interfaces on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Niklas Söderlund Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230211143655.3809756-2-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a779g0-cpg-mssr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index e2e006a7ae4a..e2987a21ce83 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -146,6 +146,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("vcbus", R8A779G0_CLK_VCBUS, CLK_VC, 1, 1), DEF_FIXED("vcbusd2", R8A779G0_CLK_VCBUSD2, CLK_VC, 2, 1), DEF_DIV6P1("canfd", R8A779G0_CLK_CANFD, CLK_PLL5_DIV4, 0x878), + DEF_DIV6P1("csi", R8A779G0_CLK_CSI, CLK_PLL5_DIV4, 0x880), DEF_FIXED("dsiref", R8A779G0_CLK_DSIREF, CLK_PLL5_DIV4, 48, 1), DEF_DIV6P1("dsiext", R8A779G0_CLK_DSIEXT, CLK_PLL5_DIV4, 0x884), @@ -165,6 +166,8 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("avb1", 212, R8A779G0_CLK_S0D4_HSC), DEF_MOD("avb2", 213, R8A779G0_CLK_S0D4_HSC), DEF_MOD("canfd0", 328, R8A779G0_CLK_SASYNCPERD2), + DEF_MOD("csi40", 331, R8A779G0_CLK_CSI), + DEF_MOD("csi41", 400, R8A779G0_CLK_CSI), DEF_MOD("dis0", 411, R8A779G0_CLK_VIOBUSD2), DEF_MOD("dsitxlink0", 415, R8A779G0_CLK_VIOBUSD2), DEF_MOD("dsitxlink1", 416, R8A779G0_CLK_VIOBUSD2), -- GitLab From 8947e5ae9589c57af246cdd149cf469aec5e4d3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 15:36:54 +0100 Subject: [PATCH 0068/5631] clk: renesas: r8a779g0: Add ISPCS clocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the ISPCS0 and ISPCS1 module clocks, which are used by the ISPCS modules on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Niklas Söderlund Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230211143655.3809756-3-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a779g0-cpg-mssr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index e2987a21ce83..0e3c8b1a7774 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -184,6 +184,8 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("i2c4", 522, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c5", 523, R8A779G0_CLK_S0D6_PER), DEF_MOD("irqc", 611, R8A779G0_CLK_CL16M), + DEF_MOD("ispcs0", 612, R8A779G0_CLK_S0D2_VIO), + DEF_MOD("ispcs1", 613, R8A779G0_CLK_S0D2_VIO), DEF_MOD("msi0", 618, R8A779G0_CLK_MSO), DEF_MOD("msi1", 619, R8A779G0_CLK_MSO), DEF_MOD("msi2", 620, R8A779G0_CLK_MSO), -- GitLab From 049f39d6d8cdf1ddae0e22021155d3af4e65e18c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 15:36:55 +0100 Subject: [PATCH 0069/5631] clk: renesas: r8a779g0: Add VIN clocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the VIN module clocks, which are used by the VIN modules on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Niklas Söderlund Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230211143655.3809756-4-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a779g0-cpg-mssr.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 0e3c8b1a7774..7cc580d67362 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -207,6 +207,22 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("tmu3", 716, R8A779G0_CLK_SASYNCPERD2), DEF_MOD("tmu4", 717, R8A779G0_CLK_SASYNCPERD2), DEF_MOD("tpu0", 718, R8A779G0_CLK_SASYNCPERD4), + DEF_MOD("vin00", 730, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin01", 731, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin02", 800, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin03", 801, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin04", 802, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin05", 803, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin06", 804, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin07", 805, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin10", 806, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin11", 807, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin12", 808, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin13", 809, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin14", 810, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin15", 811, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin16", 812, R8A779G0_CLK_S0D4_VIO), + DEF_MOD("vin17", 813, R8A779G0_CLK_S0D4_VIO), DEF_MOD("vspd0", 830, R8A779G0_CLK_VIOBUSD2), DEF_MOD("vspd1", 831, R8A779G0_CLK_VIOBUSD2), DEF_MOD("wdt1:wdt0", 907, R8A779G0_CLK_R), -- GitLab From 3c876432e772201dabe3d9d5585226be5f2b9a8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 16:30:26 +0100 Subject: [PATCH 0070/5631] clk: renesas: r8a77980: Add VIN clocks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the VIN module clocks, which are used by the VIN modules on the Renesas R-Car V3H (R8A77980) SoC. Signed-off-by: Niklas Söderlund Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230211153026.3898491-1-niklas.soderlund+renesas@ragnatech.se Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a77980-cpg-mssr.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/clk/renesas/r8a77980-cpg-mssr.c b/drivers/clk/renesas/r8a77980-cpg-mssr.c index 06f925aff407..6dc63eaf1155 100644 --- a/drivers/clk/renesas/r8a77980-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77980-cpg-mssr.c @@ -150,11 +150,27 @@ static const struct mssr_mod_clk r8a77980_mod_clks[] __initconst = { DEF_MOD("imp-ocv3", 529, R8A77980_CLK_S1D1), DEF_MOD("imp-ocv2", 531, R8A77980_CLK_S1D1), DEF_MOD("fcpvd0", 603, R8A77980_CLK_S3D1), + DEF_MOD("vin15", 604, R8A77980_CLK_S2D1), + DEF_MOD("vin14", 605, R8A77980_CLK_S2D1), + DEF_MOD("vin13", 608, R8A77980_CLK_S2D1), + DEF_MOD("vin12", 612, R8A77980_CLK_S2D1), + DEF_MOD("vin11", 618, R8A77980_CLK_S2D1), DEF_MOD("vspd0", 623, R8A77980_CLK_S3D1), + DEF_MOD("vin10", 625, R8A77980_CLK_S2D1), + DEF_MOD("vin9", 627, R8A77980_CLK_S2D1), + DEF_MOD("vin8", 628, R8A77980_CLK_S2D1), DEF_MOD("csi41", 715, R8A77980_CLK_CSI0), DEF_MOD("csi40", 716, R8A77980_CLK_CSI0), DEF_MOD("du0", 724, R8A77980_CLK_S2D1), DEF_MOD("lvds", 727, R8A77980_CLK_S2D1), + DEF_MOD("vin7", 804, R8A77980_CLK_S2D1), + DEF_MOD("vin6", 805, R8A77980_CLK_S2D1), + DEF_MOD("vin5", 806, R8A77980_CLK_S2D1), + DEF_MOD("vin4", 807, R8A77980_CLK_S2D1), + DEF_MOD("vin3", 808, R8A77980_CLK_S2D1), + DEF_MOD("vin2", 809, R8A77980_CLK_S2D1), + DEF_MOD("vin1", 810, R8A77980_CLK_S2D1), + DEF_MOD("vin0", 811, R8A77980_CLK_S2D1), DEF_MOD("etheravb", 812, R8A77980_CLK_S3D2), DEF_MOD("gether", 813, R8A77980_CLK_S3D2), DEF_MOD("imp3", 824, R8A77980_CLK_S1D1), -- GitLab From 1f04b7939704fce82d2bb5ef5561e2499a91170a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 14 Feb 2023 11:02:07 +0100 Subject: [PATCH 0071/5631] clk: renesas: r8a77995: Fix VIN parent clock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the R-Car Series, 3rd Generation Hardware User’s Manual Rev. 2.30, the parent clock of the Video Input Module (VIN) on R-Car D3 is S3D1. Update the driver to match the documentation. This has no functional impact, as both S1D2 and S3D1 have the same clock rate, and are always-on clocks. Signed-off-by: Geert Uytterhoeven Reviewed-by: Niklas Söderlund Link: https://lore.kernel.org/r/9b655843a260e06fa6f3349cdafac180e2bf38a5.1676368776.git.geert+renesas@glider.be --- drivers/clk/renesas/r8a77995-cpg-mssr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/renesas/r8a77995-cpg-mssr.c b/drivers/clk/renesas/r8a77995-cpg-mssr.c index 24ba9093a72f..3a73f6f911dd 100644 --- a/drivers/clk/renesas/r8a77995-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77995-cpg-mssr.c @@ -167,7 +167,7 @@ static const struct mssr_mod_clk r8a77995_mod_clks[] __initconst = { DEF_MOD("du0", 724, R8A77995_CLK_S1D1), DEF_MOD("lvds", 727, R8A77995_CLK_S2D1), DEF_MOD("mlp", 802, R8A77995_CLK_S2D1), - DEF_MOD("vin4", 807, R8A77995_CLK_S1D2), + DEF_MOD("vin4", 807, R8A77995_CLK_S3D1), DEF_MOD("etheravb", 812, R8A77995_CLK_S3D2), DEF_MOD("imr0", 823, R8A77995_CLK_S1D2), DEF_MOD("gpio6", 906, R8A77995_CLK_S3D4), -- GitLab From a145c9a8674ac8fbfa1595276e1b6cbfc5139038 Mon Sep 17 00:00:00 2001 From: Hai Pham Date: Fri, 27 Jan 2023 14:10:31 +0100 Subject: [PATCH 0072/5631] pinctrl: renesas: r8a779a0: Remove incorrect AVB[01] pinmux configuration AVB[01]_{MAGIC,MDC,MDIO,TXCREFCLK} are registered as both PINMUX_SINGLE(fn) and PINMUX_IPSR_GPSR(fn) in the pinmux_data array. The latter are correct, hence remove the former. Without this fix, the Ethernet PHY is not operational on the MDIO bus. Signed-off-by: Hai Pham Signed-off-by: LUU HOAI Fixes: 741a7370fc3b8b54 ("pinctrl: renesas: Initial R8A779A0 (V3U) PFC support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/6fd217b71e83ba9a8157513ed671a1fa218b23b6.1674824958.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779a0.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779a0.c b/drivers/pinctrl/renesas/pfc-r8a779a0.c index 760c83a8740b..6069869353bb 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779a0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779a0.c @@ -696,16 +696,8 @@ static const u16 pinmux_data[] = { PINMUX_SINGLE(PCIE0_CLKREQ_N), PINMUX_SINGLE(AVB0_PHY_INT), - PINMUX_SINGLE(AVB0_MAGIC), - PINMUX_SINGLE(AVB0_MDC), - PINMUX_SINGLE(AVB0_MDIO), - PINMUX_SINGLE(AVB0_TXCREFCLK), PINMUX_SINGLE(AVB1_PHY_INT), - PINMUX_SINGLE(AVB1_MAGIC), - PINMUX_SINGLE(AVB1_MDC), - PINMUX_SINGLE(AVB1_MDIO), - PINMUX_SINGLE(AVB1_TXCREFCLK), PINMUX_SINGLE(AVB2_AVTP_PPS), PINMUX_SINGLE(AVB2_AVTP_CAPTURE), -- GitLab From 60003351e99167d8cfa7c161e95856efc016f381 Mon Sep 17 00:00:00 2001 From: Phong Hoang Date: Fri, 27 Jan 2023 14:11:59 +0100 Subject: [PATCH 0073/5631] pinctrl: renesas: r8a779f0: Fix tsn1_avtp_pps pin group Correct a typo mistake in the definition of the tsn1_avtp_pps pin group mux. Signed-off-by: Phong Hoang Fixes: babe298e9caaa3d7 ("pinctrl: renesas: r8a779f0: Add Ethernet pins, groups, and functions") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/45ea6e87b91c36fd0b9706cf58ff50a4d1a99c44.1674825039.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779f0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779f0.c b/drivers/pinctrl/renesas/pfc-r8a779f0.c index 417c357f16b1..65c141ce909a 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779f0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779f0.c @@ -1213,7 +1213,7 @@ static const unsigned int tsn1_avtp_pps_pins[] = { RCAR_GP_PIN(3, 13), }; static const unsigned int tsn1_avtp_pps_mux[] = { - TSN0_AVTP_PPS_MARK, + TSN1_AVTP_PPS_MARK, }; static const unsigned int tsn1_avtp_capture_a_pins[] = { /* TSN1_AVTP_CAPTURE_A */ -- GitLab From 59e579a6af8c3f1cc73bc30f894abbb766113456 Mon Sep 17 00:00:00 2001 From: Linh Phung Date: Thu, 2 Feb 2023 01:03:01 +0000 Subject: [PATCH 0074/5631] pinctrl: renesas: r8a779g0: Add Audio Clock pins, groups, and functions Add pins, groups, and functions for the Audio Clock on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Linh Phung Signed-off-by: Kuninori Morimoto Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/87cz6sanga.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index bf7fcce2d9c6..8fcbe211df8f 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -1196,6 +1196,22 @@ static const struct sh_pfc_pin pinmux_pins[] = { PINMUX_GPIO_GP_ALL(), }; +/* - AUDIO CLOCK ----------------------------------------- */ +static const unsigned int audio_clkin_pins[] = { + /* CLK IN */ + RCAR_GP_PIN(1, 22), +}; +static const unsigned int audio_clkin_mux[] = { + AUDIO_CLKIN_MARK, +}; +static const unsigned int audio_clkout_pins[] = { + /* CLK OUT */ + RCAR_GP_PIN(1, 21), +}; +static const unsigned int audio_clkout_mux[] = { + AUDIO_CLKOUT_MARK, +}; + /* - AVB0 ------------------------------------------------ */ static const unsigned int avb0_link_pins[] = { /* AVB0_LINK */ @@ -2461,6 +2477,9 @@ static const unsigned int tsn0_avtp_match_mux[] = { }; static const struct sh_pfc_pin_group pinmux_groups[] = { + SH_PFC_PIN_GROUP(audio_clkin), + SH_PFC_PIN_GROUP(audio_clkout), + SH_PFC_PIN_GROUP(avb0_link), SH_PFC_PIN_GROUP(avb0_magic), SH_PFC_PIN_GROUP(avb0_phy_int), @@ -2640,6 +2659,11 @@ static const struct sh_pfc_pin_group pinmux_groups[] = { SH_PFC_PIN_GROUP(tsn0_avtp_match), }; +static const char * const audio_clk_groups[] = { + "audio_clkin", + "audio_clkout", +}; + static const char * const avb0_groups[] = { "avb0_link", "avb0_magic", @@ -2957,6 +2981,8 @@ static const char * const tsn0_groups[] = { }; static const struct sh_pfc_function pinmux_functions[] = { + SH_PFC_FUNCTION(audio_clk), + SH_PFC_FUNCTION(avb0), SH_PFC_FUNCTION(avb1), SH_PFC_FUNCTION(avb2), -- GitLab From b37d57e1daccbc1a0393d9207d5c48f9181fe85a Mon Sep 17 00:00:00 2001 From: Linh Phung Date: Thu, 2 Feb 2023 01:03:09 +0000 Subject: [PATCH 0075/5631] pinctrl: renesas: r8a779g0: Add Audio SSI pins, groups, and functions Add pins, groups, and functions for the Serial Sound Interface (SSI) on the Renesas R-Car V4H (R8A779G0) SoC. Signed-off-by: Linh Phung Signed-off-by: Kuninori Morimoto Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/87bkmcang2.wl-kuninori.morimoto.gx@renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 8fcbe211df8f..9671d668a3c3 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -2345,6 +2345,22 @@ static const unsigned int scif_clk_mux[] = { SCIF_CLK_MARK, }; +/* - SSI ------------------------------------------------- */ +static const unsigned int ssi_data_pins[] = { + /* SSI_SD */ + RCAR_GP_PIN(1, 20), +}; +static const unsigned int ssi_data_mux[] = { + SSI_SD_MARK, +}; +static const unsigned int ssi_ctrl_pins[] = { + /* SSI_SCK, SSI_WS */ + RCAR_GP_PIN(1, 18), RCAR_GP_PIN(1, 19), +}; +static const unsigned int ssi_ctrl_mux[] = { + SSI_SCK_MARK, SSI_WS_MARK, +}; + /* - TPU ------------------------------------------------------------------- */ static const unsigned int tpu_to0_pins[] = { /* TPU0TO0 */ @@ -2640,6 +2656,9 @@ static const struct sh_pfc_pin_group pinmux_groups[] = { SH_PFC_PIN_GROUP(scif4_ctrl), SH_PFC_PIN_GROUP(scif_clk), + SH_PFC_PIN_GROUP(ssi_data), + SH_PFC_PIN_GROUP(ssi_ctrl), + SH_PFC_PIN_GROUP(tpu_to0), /* suffix might be updated */ SH_PFC_PIN_GROUP(tpu_to0_a), /* suffix might be updated */ SH_PFC_PIN_GROUP(tpu_to1), /* suffix might be updated */ @@ -2957,6 +2976,11 @@ static const char * const scif_clk_groups[] = { "scif_clk", }; +static const char * const ssi_groups[] = { + "ssi_data", + "ssi_ctrl", +}; + static const char * const tpu_groups[] = { /* suffix might be updated */ "tpu_to0", @@ -3040,6 +3064,8 @@ static const struct sh_pfc_function pinmux_functions[] = { SH_PFC_FUNCTION(scif4), SH_PFC_FUNCTION(scif_clk), + SH_PFC_FUNCTION(ssi), + SH_PFC_FUNCTION(tpu), SH_PFC_FUNCTION(tsn0), -- GitLab From dc3c7404ed76870bec52e2f0760bc150b173e57e Mon Sep 17 00:00:00 2001 From: Trevor Woerner Date: Thu, 9 Feb 2023 21:51:31 -0500 Subject: [PATCH 0076/5631] dt-bindings: gpio: nxp,pcf8575: add gpio-line-names The devices described in this binding represent 8-bit and 16-bit i2c i/o expanders. Allow the user to specify names for up to 16 gpio lines. Signed-off-by: Trevor Woerner Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230210025132.36605-1-twoerner@gmail.com Signed-off-by: Linus Walleij --- Documentation/devicetree/bindings/gpio/nxp,pcf8575.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/gpio/nxp,pcf8575.yaml b/Documentation/devicetree/bindings/gpio/nxp,pcf8575.yaml index f0ff66c4c74e..3718103e966a 100644 --- a/Documentation/devicetree/bindings/gpio/nxp,pcf8575.yaml +++ b/Documentation/devicetree/bindings/gpio/nxp,pcf8575.yaml @@ -39,6 +39,10 @@ properties: reg: maxItems: 1 + gpio-line-names: + minItems: 1 + maxItems: 16 + gpio-controller: true '#gpio-cells': -- GitLab From f494c1913cbb34b9e2078b7b045c87c1ca6df791 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 15:42:38 +0200 Subject: [PATCH 0077/5631] pinctrl: at91: use devm_kasprintf() to avoid potential leaks (part 2) Use devm_kasprintf() instead of kasprintf() to avoid any potential leaks. At the moment drivers have no remove functionality hence there is no need for fixes tag. While at it, switch to use devm_kasprintf_strarray(). Signed-off-by: Andy Shevchenko Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230215134242.37618-2-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 735c501e7a06..9fa68ca4a412 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -18,6 +18,7 @@ #include #include #include +#include /* Since we request GPIOs from ourself */ #include @@ -1371,6 +1372,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, static int at91_pinctrl_probe(struct platform_device *pdev) { + struct device *dev = &pdev->dev; struct at91_pinctrl *info; struct pinctrl_pin_desc *pdesc; int ret, i, j, k; @@ -1394,9 +1396,19 @@ static int at91_pinctrl_probe(struct platform_device *pdev) return -ENOMEM; for (i = 0, k = 0; i < gpio_banks; i++) { + char **names; + + names = devm_kasprintf_strarray(dev, "pio", MAX_NB_GPIO_PER_BANK); + if (!names) + return -ENOMEM; + for (j = 0; j < MAX_NB_GPIO_PER_BANK; j++, k++) { + char *name = names[j]; + + strreplace(name, '-', i + 'A'); + pdesc->number = k; - pdesc->name = kasprintf(GFP_KERNEL, "pio%c%d", i + 'A', j); + pdesc->name = name; pdesc++; } } @@ -1797,7 +1809,8 @@ static const struct of_device_id at91_gpio_of_match[] = { static int at91_gpio_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; struct at91_gpio_chip *at91_chip = NULL; struct gpio_chip *chip; struct pinctrl_gpio_range *range; @@ -1866,16 +1879,14 @@ static int at91_gpio_probe(struct platform_device *pdev) chip->ngpio = ngpio; } - names = devm_kcalloc(&pdev->dev, chip->ngpio, sizeof(char *), - GFP_KERNEL); - + names = devm_kasprintf_strarray(dev, "pio", chip->ngpio); if (!names) { ret = -ENOMEM; goto clk_enable_err; } for (i = 0; i < chip->ngpio; i++) - names[i] = devm_kasprintf(&pdev->dev, GFP_KERNEL, "pio%c%d", alias_idx + 'A', i); + strreplace(names[i], '-', alias_idx + 'A'); chip->names = (const char *const *)names; -- GitLab From 415a099ea55ae716b69beefdcaa654b96087c016 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 15:42:39 +0200 Subject: [PATCH 0078/5631] pinctrl: at91: Don't mix non-devm calls with devm ones Replace devm_clk_get() by devm_clk_get_enabled() and drop unneeded code pieces. This will make sure we keep the ordering of the resource allocation correct. Signed-off-by: Andy Shevchenko Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230215134242.37618-3-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 9fa68ca4a412..f0b139a1cc3e 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1849,19 +1849,13 @@ static int at91_gpio_probe(struct platform_device *pdev) at91_chip->pioc_virq = irq; at91_chip->pioc_idx = alias_idx; - at91_chip->clock = devm_clk_get(&pdev->dev, NULL); + at91_chip->clock = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(at91_chip->clock)) { dev_err(&pdev->dev, "failed to get clock, ignoring.\n"); ret = PTR_ERR(at91_chip->clock); goto err; } - ret = clk_prepare_enable(at91_chip->clock); - if (ret) { - dev_err(&pdev->dev, "failed to prepare and enable clock, ignoring.\n"); - goto clk_enable_err; - } - at91_chip->chip = at91_gpio_template; at91_chip->id = alias_idx; @@ -1882,7 +1876,7 @@ static int at91_gpio_probe(struct platform_device *pdev) names = devm_kasprintf_strarray(dev, "pio", chip->ngpio); if (!names) { ret = -ENOMEM; - goto clk_enable_err; + goto err; } for (i = 0; i < chip->ngpio; i++) @@ -1915,8 +1909,6 @@ static int at91_gpio_probe(struct platform_device *pdev) return 0; gpiochip_add_err: -clk_enable_err: - clk_disable_unprepare(at91_chip->clock); err: dev_err(&pdev->dev, "Failure %i for GPIO %i\n", ret, alias_idx); -- GitLab From 6194485db61846cb76c2479d39643db539aa4b53 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 15:42:40 +0200 Subject: [PATCH 0079/5631] pinctrl: at91: Use of_device_get_match_data() Use of_device_get_match_data() to simplify the code. Signed-off-by: Andy Shevchenko Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230215134242.37618-4-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index f0b139a1cc3e..8a8de1c5dee2 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1304,8 +1304,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, return -ENODEV; info->dev = &pdev->dev; - info->ops = (const struct at91_pinctrl_mux_ops *) - of_match_device(at91_pinctrl_of_match, &pdev->dev)->data; + info->ops = of_device_get_match_data(dev); at91_pinctrl_child_count(info, np); /* @@ -1844,8 +1843,7 @@ static int at91_gpio_probe(struct platform_device *pdev) goto err; } - at91_chip->ops = (const struct at91_pinctrl_mux_ops *) - of_match_device(at91_gpio_of_match, &pdev->dev)->data; + at91_chip->ops = of_device_get_match_data(dev); at91_chip->pioc_virq = irq; at91_chip->pioc_idx = alias_idx; -- GitLab From 472bbb2cfd6384fe4c4b956af2170c1225fe2a92 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 15:42:41 +0200 Subject: [PATCH 0080/5631] pinctrl: at91: Use dev_err_probe() instead of custom messaging The custom message has no value except printing the error code, the same does dev_err_probe(). Let's use the latter for the sake of unification. Note that some APIs already have messaging in them and some simply do not require the current noise. Signed-off-by: Andy Shevchenko Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230215134242.37618-5-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 64 +++++++++++----------------------- 1 file changed, 21 insertions(+), 43 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 8a8de1c5dee2..0958eb1cc861 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1294,10 +1294,11 @@ static const struct of_device_id at91_pinctrl_of_match[] = { static int at91_pinctrl_probe_dt(struct platform_device *pdev, struct at91_pinctrl *info) { + struct device *dev = &pdev->dev; int ret = 0; int i, j, ngpio_chips_enabled = 0; uint32_t *tmp; - struct device_node *np = pdev->dev.of_node; + struct device_node *np = dev->of_node; struct device_node *child; if (!np) @@ -1360,9 +1361,8 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, continue; ret = at91_pinctrl_parse_functions(child, info, i++); if (ret) { - dev_err(&pdev->dev, "failed to parse function\n"); of_node_put(child); - return ret; + return dev_err_probe(dev, ret, "failed to parse function\n"); } } @@ -1415,11 +1415,8 @@ static int at91_pinctrl_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); info->pctl = devm_pinctrl_register(&pdev->dev, &at91_pinctrl_desc, info); - - if (IS_ERR(info->pctl)) { - dev_err(&pdev->dev, "could not register AT91 pinctrl driver\n"); - return PTR_ERR(info->pctl); - } + if (IS_ERR(info->pctl)) + return dev_err_probe(dev, PTR_ERR(info->pctl), "could not register AT91 pinctrl driver\n"); /* We will handle a range of GPIO pins */ for (i = 0; i < gpio_banks; i++) @@ -1820,39 +1817,28 @@ static int at91_gpio_probe(struct platform_device *pdev) char **names; BUG_ON(alias_idx >= ARRAY_SIZE(gpio_chips)); - if (gpio_chips[alias_idx]) { - ret = -EBUSY; - goto err; - } + if (gpio_chips[alias_idx]) + return dev_err_probe(dev, -EBUSY, "%d slot is occupied.\n", alias_idx); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = irq; - goto err; - } + if (irq < 0) + return irq; at91_chip = devm_kzalloc(&pdev->dev, sizeof(*at91_chip), GFP_KERNEL); - if (!at91_chip) { - ret = -ENOMEM; - goto err; - } + if (!at91_chip) + return -ENOMEM; at91_chip->regbase = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(at91_chip->regbase)) { - ret = PTR_ERR(at91_chip->regbase); - goto err; - } + if (IS_ERR(at91_chip->regbase)) + return PTR_ERR(at91_chip->regbase); at91_chip->ops = of_device_get_match_data(dev); at91_chip->pioc_virq = irq; at91_chip->pioc_idx = alias_idx; at91_chip->clock = devm_clk_get_enabled(&pdev->dev, NULL); - if (IS_ERR(at91_chip->clock)) { - dev_err(&pdev->dev, "failed to get clock, ignoring.\n"); - ret = PTR_ERR(at91_chip->clock); - goto err; - } + if (IS_ERR(at91_chip->clock)) + return dev_err_probe(dev, PTR_ERR(at91_chip->clock), "failed to get clock, ignoring.\n"); at91_chip->chip = at91_gpio_template; at91_chip->id = alias_idx; @@ -1865,17 +1851,15 @@ static int at91_gpio_probe(struct platform_device *pdev) if (!of_property_read_u32(np, "#gpio-lines", &ngpio)) { if (ngpio >= MAX_NB_GPIO_PER_BANK) - pr_err("at91_gpio.%d, gpio-nb >= %d failback to %d\n", - alias_idx, MAX_NB_GPIO_PER_BANK, MAX_NB_GPIO_PER_BANK); + dev_err(dev, "at91_gpio.%d, gpio-nb >= %d failback to %d\n", + alias_idx, MAX_NB_GPIO_PER_BANK, MAX_NB_GPIO_PER_BANK); else chip->ngpio = ngpio; } names = devm_kasprintf_strarray(dev, "pio", chip->ngpio); - if (!names) { - ret = -ENOMEM; - goto err; - } + if (!names) + return -ENOMEM; for (i = 0; i < chip->ngpio; i++) strreplace(names[i], '-', alias_idx + 'A'); @@ -1892,11 +1876,11 @@ static int at91_gpio_probe(struct platform_device *pdev) ret = at91_gpio_of_irq_setup(pdev, at91_chip); if (ret) - goto gpiochip_add_err; + return ret; ret = gpiochip_add_data(chip, at91_chip); if (ret) - goto gpiochip_add_err; + return ret; gpio_chips[alias_idx] = at91_chip; platform_set_drvdata(pdev, at91_chip); @@ -1905,12 +1889,6 @@ static int at91_gpio_probe(struct platform_device *pdev) dev_info(&pdev->dev, "at address %p\n", at91_chip->regbase); return 0; - -gpiochip_add_err: -err: - dev_err(&pdev->dev, "Failure %i for GPIO %i\n", ret, alias_idx); - - return ret; } static const struct dev_pm_ops at91_gpio_pm_ops = { -- GitLab From 00408f28c344fd1cafe6e66fe0f454607a2605f9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 15:42:42 +0200 Subject: [PATCH 0081/5631] pinctrl: at91: Utilise temporary variable for struct device We have a temporary variable to keep pointer to struct device. Utilise it inside the ->probe() implementation. Signed-off-by: Andy Shevchenko Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230215134242.37618-6-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 60 +++++++++++++++------------------- 1 file changed, 26 insertions(+), 34 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 0958eb1cc861..79b7061fc8f3 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1304,7 +1304,7 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, if (!np) return -ENODEV; - info->dev = &pdev->dev; + info->dev = dev; info->ops = of_device_get_match_data(dev); at91_pinctrl_child_count(info, np); @@ -1324,35 +1324,31 @@ static int at91_pinctrl_probe_dt(struct platform_device *pdev, if (ret) return ret; - dev_dbg(&pdev->dev, "nmux = %d\n", info->nmux); + dev_dbg(dev, "nmux = %d\n", info->nmux); - dev_dbg(&pdev->dev, "mux-mask\n"); + dev_dbg(dev, "mux-mask\n"); tmp = info->mux_mask; for (i = 0; i < gpio_banks; i++) { for (j = 0; j < info->nmux; j++, tmp++) { - dev_dbg(&pdev->dev, "%d:%d\t0x%x\n", i, j, tmp[0]); + dev_dbg(dev, "%d:%d\t0x%x\n", i, j, tmp[0]); } } - dev_dbg(&pdev->dev, "nfunctions = %d\n", info->nfunctions); - dev_dbg(&pdev->dev, "ngroups = %d\n", info->ngroups); - info->functions = devm_kcalloc(&pdev->dev, - info->nfunctions, - sizeof(struct at91_pmx_func), - GFP_KERNEL); + dev_dbg(dev, "nfunctions = %d\n", info->nfunctions); + dev_dbg(dev, "ngroups = %d\n", info->ngroups); + info->functions = devm_kcalloc(dev, info->nfunctions, sizeof(*info->functions), + GFP_KERNEL); if (!info->functions) return -ENOMEM; - info->groups = devm_kcalloc(&pdev->dev, - info->ngroups, - sizeof(struct at91_pin_group), - GFP_KERNEL); + info->groups = devm_kcalloc(dev, info->ngroups, sizeof(*info->groups), + GFP_KERNEL); if (!info->groups) return -ENOMEM; - dev_dbg(&pdev->dev, "nbanks = %d\n", gpio_banks); - dev_dbg(&pdev->dev, "nfunctions = %d\n", info->nfunctions); - dev_dbg(&pdev->dev, "ngroups = %d\n", info->ngroups); + dev_dbg(dev, "nbanks = %d\n", gpio_banks); + dev_dbg(dev, "nfunctions = %d\n", info->nfunctions); + dev_dbg(dev, "ngroups = %d\n", info->ngroups); i = 0; @@ -1376,7 +1372,7 @@ static int at91_pinctrl_probe(struct platform_device *pdev) struct pinctrl_pin_desc *pdesc; int ret, i, j, k; - info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL); + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); if (!info) return -ENOMEM; @@ -1384,13 +1380,10 @@ static int at91_pinctrl_probe(struct platform_device *pdev) if (ret) return ret; - at91_pinctrl_desc.name = dev_name(&pdev->dev); + at91_pinctrl_desc.name = dev_name(dev); at91_pinctrl_desc.npins = gpio_banks * MAX_NB_GPIO_PER_BANK; at91_pinctrl_desc.pins = pdesc = - devm_kcalloc(&pdev->dev, - at91_pinctrl_desc.npins, sizeof(*pdesc), - GFP_KERNEL); - + devm_kcalloc(dev, at91_pinctrl_desc.npins, sizeof(*pdesc), GFP_KERNEL); if (!at91_pinctrl_desc.pins) return -ENOMEM; @@ -1413,8 +1406,7 @@ static int at91_pinctrl_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, info); - info->pctl = devm_pinctrl_register(&pdev->dev, &at91_pinctrl_desc, - info); + info->pctl = devm_pinctrl_register(dev, &at91_pinctrl_desc, info); if (IS_ERR(info->pctl)) return dev_err_probe(dev, PTR_ERR(info->pctl), "could not register AT91 pinctrl driver\n"); @@ -1423,7 +1415,7 @@ static int at91_pinctrl_probe(struct platform_device *pdev) if (gpio_chips[i]) pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range); - dev_info(&pdev->dev, "initialized AT91 pinctrl driver\n"); + dev_info(dev, "initialized AT91 pinctrl driver\n"); return 0; } @@ -1714,6 +1706,7 @@ static void gpio_irq_handler(struct irq_desc *desc) static int at91_gpio_of_irq_setup(struct platform_device *pdev, struct at91_gpio_chip *at91_gpio) { + struct device *dev = &pdev->dev; struct gpio_chip *gpiochip_prev = NULL; struct at91_gpio_chip *prev = NULL; struct irq_data *d = irq_get_irq_data(at91_gpio->pioc_virq); @@ -1721,8 +1714,7 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev, struct gpio_irq_chip *girq; int i; - gpio_irqchip = devm_kzalloc(&pdev->dev, sizeof(*gpio_irqchip), - GFP_KERNEL); + gpio_irqchip = devm_kzalloc(dev, sizeof(*gpio_irqchip), GFP_KERNEL); if (!gpio_irqchip) return -ENOMEM; @@ -1758,7 +1750,7 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev, if (!gpiochip_prev) { girq->parent_handler = gpio_irq_handler; girq->num_parents = 1; - girq->parents = devm_kcalloc(&pdev->dev, 1, + girq->parents = devm_kcalloc(dev, girq->num_parents, sizeof(*girq->parents), GFP_KERNEL); if (!girq->parents) @@ -1824,7 +1816,7 @@ static int at91_gpio_probe(struct platform_device *pdev) if (irq < 0) return irq; - at91_chip = devm_kzalloc(&pdev->dev, sizeof(*at91_chip), GFP_KERNEL); + at91_chip = devm_kzalloc(dev, sizeof(*at91_chip), GFP_KERNEL); if (!at91_chip) return -ENOMEM; @@ -1836,7 +1828,7 @@ static int at91_gpio_probe(struct platform_device *pdev) at91_chip->pioc_virq = irq; at91_chip->pioc_idx = alias_idx; - at91_chip->clock = devm_clk_get_enabled(&pdev->dev, NULL); + at91_chip->clock = devm_clk_get_enabled(dev, NULL); if (IS_ERR(at91_chip->clock)) return dev_err_probe(dev, PTR_ERR(at91_chip->clock), "failed to get clock, ignoring.\n"); @@ -1844,8 +1836,8 @@ static int at91_gpio_probe(struct platform_device *pdev) at91_chip->id = alias_idx; chip = &at91_chip->chip; - chip->label = dev_name(&pdev->dev); - chip->parent = &pdev->dev; + chip->label = dev_name(dev); + chip->parent = dev; chip->owner = THIS_MODULE; chip->base = alias_idx * MAX_NB_GPIO_PER_BANK; @@ -1886,7 +1878,7 @@ static int at91_gpio_probe(struct platform_device *pdev) platform_set_drvdata(pdev, at91_chip); gpio_banks = max(gpio_banks, alias_idx + 1); - dev_info(&pdev->dev, "at address %p\n", at91_chip->regbase); + dev_info(dev, "at address %p\n", at91_chip->regbase); return 0; } -- GitLab From 2545625b8b244c7ecc473aeb188164caa55cc71b Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 20 Feb 2023 10:33:18 +0800 Subject: [PATCH 0082/5631] dt-bindings: pinctrl: add schema for NXP S32 SoCs Add DT schema for the pinctrl driver of NXP S32 SoC family. Signed-off-by: Larisa Grigore Signed-off-by: Ghennadi Procopciuc Signed-off-by: Chester Lin Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230220023320.3499-2-clin@suse.com Signed-off-by: Linus Walleij --- .../pinctrl/nxp,s32g2-siul2-pinctrl.yaml | 123 ++++++++++++++++++ 1 file changed, 123 insertions(+) create mode 100644 Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml new file mode 100644 index 000000000000..d49aafd8c5f4 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/nxp,s32g2-siul2-pinctrl.yaml @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright 2022 NXP +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/nxp,s32g2-siul2-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP S32G2 pin controller + +maintainers: + - Ghennadi Procopciuc + - Chester Lin + +description: | + S32G2 pinmux is implemented in SIUL2 (System Integration Unit Lite2), + whose memory map is split into two regions: + SIUL2_0 @ 0x4009c000 + SIUL2_1 @ 0x44010000 + + Every SIUL2 region has multiple register types, and here only MSCR and + IMCR registers need to be revealed for kernel to configure pinmux. + + Please note that some register indexes are reserved in S32G2, such as + MSCR102-MSCR111, MSCR123-MSCR143, IMCR84-IMCR118 and IMCR398-IMCR429. + +properties: + compatible: + enum: + - nxp,s32g2-siul2-pinctrl + + reg: + description: | + A list of MSCR/IMCR register regions to be reserved. + - MSCR (Multiplexed Signal Configuration Register) + An MSCR register can configure the associated pin as either a GPIO pin + or a function output pin depends on the selected signal source. + - IMCR (Input Multiplexed Signal Configuration Register) + An IMCR register can configure the associated pin as function input + pin depends on the selected signal source. + items: + - description: MSCR registers group 0 in SIUL2_0 + - description: MSCR registers group 1 in SIUL2_1 + - description: MSCR registers group 2 in SIUL2_1 + - description: IMCR registers group 0 in SIUL2_0 + - description: IMCR registers group 1 in SIUL2_1 + - description: IMCR registers group 2 in SIUL2_1 + +patternProperties: + '-pins$': + type: object + additionalProperties: false + + patternProperties: + '-grp[0-9]$': + type: object + allOf: + - $ref: pinmux-node.yaml# + - $ref: pincfg-node.yaml# + description: | + Pinctrl node's client devices specify pin muxes using subnodes, + which in turn use the standard properties below. + + properties: + bias-disable: true + bias-high-impedance: true + bias-pull-up: true + bias-pull-down: true + drive-open-drain: true + input-enable: true + output-enable: true + + pinmux: + description: | + An integer array for representing pinmux configurations of + a device. Each integer consists of a PIN_ID and a 4-bit + selected signal source(SSS) as IOMUX setting, which is + calculated as: pinmux = (PIN_ID << 4 | SSS) + + slew-rate: + description: Supported slew rate based on Fmax values (MHz) + enum: [83, 133, 150, 166, 208] + + additionalProperties: false + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + pinctrl@4009c240 { + compatible = "nxp,s32g2-siul2-pinctrl"; + + /* MSCR0-MSCR101 registers on siul2_0 */ + reg = <0x4009c240 0x198>, + /* MSCR112-MSCR122 registers on siul2_1 */ + <0x44010400 0x2c>, + /* MSCR144-MSCR190 registers on siul2_1 */ + <0x44010480 0xbc>, + /* IMCR0-IMCR83 registers on siul2_0 */ + <0x4009ca40 0x150>, + /* IMCR119-IMCR397 registers on siul2_1 */ + <0x44010c1c 0x45c>, + /* IMCR430-IMCR495 registers on siul2_1 */ + <0x440110f8 0x108>; + + llce-can0-pins { + llce-can0-grp0 { + pinmux = <0x2b0>; + input-enable; + slew-rate = <208>; + }; + + llce-can0-grp1 { + pinmux = <0x2c2>; + output-enable; + slew-rate = <208>; + }; + }; + }; +... -- GitLab From fd84aaa8173d3ff86f8df2009921336a1ea53a8a Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 20 Feb 2023 10:33:19 +0800 Subject: [PATCH 0083/5631] pinctrl: add NXP S32 SoC family support Add the pinctrl driver for NXP S32 SoC family. This driver is mainly based on NXP's downstream implementation on nxp-auto-linux repo[1]. [1] https://github.com/nxp-auto-linux/linux/tree/bsp35.0-5.15.73-rt/drivers/pinctrl/freescale Signed-off-by: Matthew Nunez Signed-off-by: Phu Luu An Signed-off-by: Stefan-Gabriel Mirea Signed-off-by: Larisa Grigore Signed-off-by: Ghennadi Procopciuc Signed-off-by: Andrei Stefanescu Signed-off-by: Radu Pirea Signed-off-by: Chester Lin Link: https://lore.kernel.org/r/20230220023320.3499-3-clin@suse.com Signed-off-by: Linus Walleij --- drivers/pinctrl/Kconfig | 1 + drivers/pinctrl/Makefile | 1 + drivers/pinctrl/nxp/Kconfig | 15 + drivers/pinctrl/nxp/Makefile | 4 + drivers/pinctrl/nxp/pinctrl-s32.h | 75 +++ drivers/pinctrl/nxp/pinctrl-s32cc.c | 945 ++++++++++++++++++++++++++++ drivers/pinctrl/nxp/pinctrl-s32g2.c | 773 +++++++++++++++++++++++ 7 files changed, 1814 insertions(+) create mode 100644 drivers/pinctrl/nxp/Kconfig create mode 100644 drivers/pinctrl/nxp/Makefile create mode 100644 drivers/pinctrl/nxp/pinctrl-s32.h create mode 100644 drivers/pinctrl/nxp/pinctrl-s32cc.c create mode 100644 drivers/pinctrl/nxp/pinctrl-s32g2.c diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index dcb53c4a9584..694f47fe6d11 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -535,6 +535,7 @@ source "drivers/pinctrl/meson/Kconfig" source "drivers/pinctrl/mvebu/Kconfig" source "drivers/pinctrl/nomadik/Kconfig" source "drivers/pinctrl/nuvoton/Kconfig" +source "drivers/pinctrl/nxp/Kconfig" source "drivers/pinctrl/pxa/Kconfig" source "drivers/pinctrl/qcom/Kconfig" source "drivers/pinctrl/ralink/Kconfig" diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index d5939840bb2a..c40397af024b 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -64,6 +64,7 @@ obj-$(CONFIG_PINCTRL_MESON) += meson/ obj-y += mvebu/ obj-y += nomadik/ obj-y += nuvoton/ +obj-y += nxp/ obj-$(CONFIG_PINCTRL_PXA) += pxa/ obj-$(CONFIG_ARCH_QCOM) += qcom/ obj-$(CONFIG_PINCTRL_RALINK) += ralink/ diff --git a/drivers/pinctrl/nxp/Kconfig b/drivers/pinctrl/nxp/Kconfig new file mode 100644 index 000000000000..abca7ef97003 --- /dev/null +++ b/drivers/pinctrl/nxp/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +config PINCTRL_S32CC + bool + depends on ARCH_S32 && OF + select GENERIC_PINCTRL_GROUPS + select GENERIC_PINMUX_FUNCTIONS + select GENERIC_PINCONF + select REGMAP_MMIO + +config PINCTRL_S32G2 + depends on ARCH_S32 && OF + bool "NXP S32G2 pinctrl driver" + select PINCTRL_S32CC + help + Say Y here to enable the pinctrl driver for NXP S32G2 family SoCs diff --git a/drivers/pinctrl/nxp/Makefile b/drivers/pinctrl/nxp/Makefile new file mode 100644 index 000000000000..c1cff4870b02 --- /dev/null +++ b/drivers/pinctrl/nxp/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +# NXP pin control +obj-$(CONFIG_PINCTRL_S32CC) += pinctrl-s32cc.o +obj-$(CONFIG_PINCTRL_S32G2) += pinctrl-s32g2.o diff --git a/drivers/pinctrl/nxp/pinctrl-s32.h b/drivers/pinctrl/nxp/pinctrl-s32.h new file mode 100644 index 000000000000..b6d530a62051 --- /dev/null +++ b/drivers/pinctrl/nxp/pinctrl-s32.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * S32 pinmux core definitions + * + * Copyright 2016-2020, 2022 NXP + * Copyright (C) 2022 SUSE LLC + * Copyright 2015-2016 Freescale Semiconductor, Inc. + * Copyright (C) 2012 Linaro Ltd. + */ + +#ifndef __DRIVERS_PINCTRL_S32_H +#define __DRIVERS_PINCTRL_S32_H + +struct platform_device; + +/** + * struct s32_pin_group - describes an S32 pin group + * @name: the name of this specific pin group + * @npins: the number of pins in this group array, i.e. the number of + * elements in pin_ids and pin_sss so we can iterate over that array + * @pin_ids: an array of pin IDs in this group + * @pin_sss: an array of source signal select configs paired with pin_ids + */ +struct s32_pin_group { + const char *name; + unsigned int npins; + unsigned int *pin_ids; + unsigned int *pin_sss; +}; + +/** + * struct s32_pmx_func - describes S32 pinmux functions + * @name: the name of this specific function + * @groups: corresponding pin groups + * @num_groups: the number of groups + */ +struct s32_pmx_func { + const char *name; + const char **groups; + unsigned int num_groups; +}; + +/** + * struct s32_pin_range - pin ID range for each memory region. + * @start: start pin ID + * @end: end pin ID + */ +struct s32_pin_range { + unsigned int start; + unsigned int end; +}; + +struct s32_pinctrl_soc_info { + struct device *dev; + const struct pinctrl_pin_desc *pins; + unsigned int npins; + struct s32_pin_group *groups; + unsigned int ngroups; + struct s32_pmx_func *functions; + unsigned int nfunctions; + unsigned int grp_index; + const struct s32_pin_range *mem_pin_ranges; + unsigned int mem_regions; +}; + +#define S32_PINCTRL_PIN(pin) PINCTRL_PIN(pin, #pin) +#define S32_PIN_RANGE(_start, _end) { .start = _start, .end = _end } + +int s32_pinctrl_probe(struct platform_device *pdev, + struct s32_pinctrl_soc_info *info); +#ifdef CONFIG_PM_SLEEP +int __maybe_unused s32_pinctrl_resume(struct device *dev); +int __maybe_unused s32_pinctrl_suspend(struct device *dev); +#endif +#endif /* __DRIVERS_PINCTRL_S32_H */ diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c new file mode 100644 index 000000000000..2c945523af80 --- /dev/null +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -0,0 +1,945 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Core driver for the S32 CC (Common Chassis) pin controller + * + * Copyright 2017-2022 NXP + * Copyright (C) 2022 SUSE LLC + * Copyright 2015-2016 Freescale Semiconductor, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../core.h" +#include "../pinconf.h" +#include "../pinctrl-utils.h" +#include "pinctrl-s32.h" + +#define S32_PIN_ID_MASK GENMASK(31, 4) + +#define S32_MSCR_SSS_MASK GENMASK(2, 0) +#define S32_MSCR_PUS BIT(12) +#define S32_MSCR_PUE BIT(13) +#define S32_MSCR_SRE(X) (((X) & GENMASK(3, 0)) << 14) +#define S32_MSCR_IBE BIT(19) +#define S32_MSCR_ODE BIT(20) +#define S32_MSCR_OBE BIT(21) + +static struct regmap_config s32_regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + +static u32 get_pin_no(u32 pinmux) +{ + return (pinmux & S32_PIN_ID_MASK) >> __ffs(S32_PIN_ID_MASK); +} + +static u32 get_pin_func(u32 pinmux) +{ + return pinmux & GENMASK(3, 0); +} + +struct s32_pinctrl_mem_region { + struct regmap *map; + const struct s32_pin_range *pin_range; + char name[8]; +}; + +/* + * Holds pin configuration for GPIO's. + * @pin_id: Pin ID for this GPIO + * @config: Pin settings + * @list: Linked list entry for each gpio pin + */ +struct gpio_pin_config { + unsigned int pin_id; + unsigned int config; + struct list_head list; +}; + +/* + * Pad config save/restore for power suspend/resume. + */ +struct s32_pinctrl_context { + unsigned int *pads; +}; + +/* + * @dev: a pointer back to containing device + * @pctl: a pointer to the pinctrl device structure + * @regions: reserved memory regions with start/end pin + * @info: structure containing information about the pin + * @gpio_configs: Saved configurations for GPIO pins + * @gpiop_configs_lock: lock for the `gpio_configs` list + * @s32_pinctrl_context: Configuration saved over system sleep + */ +struct s32_pinctrl { + struct device *dev; + struct pinctrl_dev *pctl; + struct s32_pinctrl_mem_region *regions; + struct s32_pinctrl_soc_info *info; + struct list_head gpio_configs; + spinlock_t gpio_configs_lock; +#ifdef CONFIG_PM_SLEEP + struct s32_pinctrl_context saved_context; +#endif +}; + +static struct s32_pinctrl_mem_region * +s32_get_region(struct pinctrl_dev *pctldev, unsigned int pin) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pin_range *pin_range; + unsigned int mem_regions = ipctl->info->mem_regions; + unsigned int i; + + for (i = 0; i < mem_regions; ++i) { + pin_range = ipctl->regions[i].pin_range; + if (pin >= pin_range->start && pin <= pin_range->end) + return &ipctl->regions[i]; + } + + return NULL; +} + +static inline int s32_check_pin(struct pinctrl_dev *pctldev, + unsigned int pin) +{ + return s32_get_region(pctldev, pin) ? 0 : -EINVAL; +} + +static inline int s32_regmap_read(struct pinctrl_dev *pctldev, + unsigned int pin, unsigned int *val) +{ + struct s32_pinctrl_mem_region *region; + unsigned int offset; + + region = s32_get_region(pctldev, pin); + if (!region) + return -EINVAL; + + offset = (pin - region->pin_range->start) * + regmap_get_reg_stride(region->map); + + return regmap_read(region->map, offset, val); +} + +static inline int s32_regmap_write(struct pinctrl_dev *pctldev, + unsigned int pin, + unsigned int val) +{ + struct s32_pinctrl_mem_region *region; + unsigned int offset; + + region = s32_get_region(pctldev, pin); + if (!region) + return -EINVAL; + + offset = (pin - region->pin_range->start) * + regmap_get_reg_stride(region->map); + + return regmap_write(region->map, offset, val); + +} + +static inline int s32_regmap_update(struct pinctrl_dev *pctldev, unsigned int pin, + unsigned int mask, unsigned int val) +{ + struct s32_pinctrl_mem_region *region; + unsigned int offset; + + region = s32_get_region(pctldev, pin); + if (!region) + return -EINVAL; + + offset = (pin - region->pin_range->start) * + regmap_get_reg_stride(region->map); + + return regmap_update_bits(region->map, offset, mask, val); +} + +static int s32_get_groups_count(struct pinctrl_dev *pctldev) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + return info->ngroups; +} + +static const char *s32_get_group_name(struct pinctrl_dev *pctldev, + unsigned int selector) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + return info->groups[selector].name; +} + +static int s32_get_group_pins(struct pinctrl_dev *pctldev, + unsigned int selector, const unsigned int **pins, + unsigned int *npins) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + *pins = info->groups[selector].pin_ids; + *npins = info->groups[selector].npins; + + return 0; +} + +static void s32_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, + unsigned int offset) +{ + seq_printf(s, "%s", dev_name(pctldev->dev)); +} + +static int s32_dt_group_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *np, + struct pinctrl_map **map, + unsigned int *reserved_maps, + unsigned int *num_maps, + const char *func_name) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + struct device *dev = ipctl->dev; + unsigned long *cfgs = NULL; + unsigned int n_cfgs, reserve = 1; + int n_pins, ret; + + n_pins = of_property_count_elems_of_size(np, "pinmux", sizeof(u32)); + if (n_pins < 0) { + dev_warn(dev, "Unable to find 'pinmux' property in node %s.\n", + np->name); + } else if (!n_pins) { + return -EINVAL; + } + + ret = pinconf_generic_parse_dt_config(np, pctldev, &cfgs, &n_cfgs); + if (ret) { + dev_err(dev, "%pOF: could not parse node property\n", np); + return ret; + } + + if (n_cfgs) + reserve++; + + ret = pinctrl_utils_reserve_map(pctldev, map, reserved_maps, num_maps, + reserve); + if (ret < 0) + goto free_cfgs; + + ret = pinctrl_utils_add_map_mux(pctldev, map, reserved_maps, num_maps, + np->name, func_name); + if (ret < 0) + goto free_cfgs; + + if (n_cfgs) { + ret = pinctrl_utils_add_map_configs(pctldev, map, reserved_maps, + num_maps, np->name, cfgs, n_cfgs, + PIN_MAP_TYPE_CONFIGS_GROUP); + if (ret < 0) + goto free_cfgs; + } + +free_cfgs: + kfree(cfgs); + return ret; +} + +static int s32_dt_node_to_map(struct pinctrl_dev *pctldev, + struct device_node *np_config, + struct pinctrl_map **map, + unsigned int *num_maps) +{ + unsigned int reserved_maps; + struct device_node *np; + int ret = 0; + + reserved_maps = 0; + *map = NULL; + *num_maps = 0; + + for_each_available_child_of_node(np_config, np) { + ret = s32_dt_group_node_to_map(pctldev, np, map, + &reserved_maps, num_maps, + np_config->name); + if (ret < 0) + break; + } + + if (ret) + pinctrl_utils_free_map(pctldev, *map, *num_maps); + + return ret; + +} + +static const struct pinctrl_ops s32_pctrl_ops = { + .get_groups_count = s32_get_groups_count, + .get_group_name = s32_get_group_name, + .get_group_pins = s32_get_group_pins, + .pin_dbg_show = s32_pin_dbg_show, + .dt_node_to_map = s32_dt_node_to_map, + .dt_free_map = pinctrl_utils_free_map, +}; + +static int s32_pmx_set(struct pinctrl_dev *pctldev, unsigned int selector, + unsigned int group) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + int i, ret; + struct s32_pin_group *grp; + + /* + * Configure the mux mode for each pin in the group for a specific + * function. + */ + grp = &info->groups[group]; + + dev_dbg(ipctl->dev, "set mux for function %s group %s\n", + info->functions[selector].name, grp->name); + + /* Check beforehand so we don't have a partial config. */ + for (i = 0; i < grp->npins; ++i) { + if (s32_check_pin(pctldev, grp->pin_ids[i]) != 0) { + dev_err(info->dev, "invalid pin: %d in group: %d\n", + grp->pin_ids[i], group); + return -EINVAL; + } + } + + for (i = 0, ret = 0; i < grp->npins && !ret; ++i) { + ret = s32_regmap_update(pctldev, grp->pin_ids[i], + S32_MSCR_SSS_MASK, grp->pin_sss[i]); + } + + return ret; +} + +static int s32_pmx_get_funcs_count(struct pinctrl_dev *pctldev) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + return info->nfunctions; +} + +static const char *s32_pmx_get_func_name(struct pinctrl_dev *pctldev, + unsigned int selector) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + return info->functions[selector].name; +} + +static int s32_pmx_get_groups(struct pinctrl_dev *pctldev, + unsigned int selector, + const char * const **groups, + unsigned int * const num_groups) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + + *groups = info->functions[selector].groups; + *num_groups = info->functions[selector].num_groups; + + return 0; +} + +static int s32_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + struct gpio_pin_config *gpio_pin; + unsigned int config; + unsigned long flags; + int ret; + + ret = s32_regmap_read(pctldev, offset, &config); + if (ret != 0) + return -EINVAL; + + /* Save current configuration */ + gpio_pin = kmalloc(sizeof(*gpio_pin), GFP_KERNEL); + if (!gpio_pin) + return -ENOMEM; + + gpio_pin->pin_id = offset; + gpio_pin->config = config; + + spin_lock_irqsave(&ipctl->gpio_configs_lock, flags); + list_add(&(gpio_pin->list), &(ipctl->gpio_configs)); + spin_unlock_irqrestore(&ipctl->gpio_configs_lock, flags); + + /* GPIO pin means SSS = 0 */ + config &= ~S32_MSCR_SSS_MASK; + + return s32_regmap_write(pctldev, offset, config); +} + +static void s32_pmx_gpio_disable_free(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + struct list_head *pos, *tmp; + struct gpio_pin_config *gpio_pin; + unsigned long flags; + int ret; + + spin_lock_irqsave(&ipctl->gpio_configs_lock, flags); + + list_for_each_safe(pos, tmp, &ipctl->gpio_configs) { + gpio_pin = list_entry(pos, struct gpio_pin_config, list); + + if (gpio_pin->pin_id == offset) { + ret = s32_regmap_write(pctldev, gpio_pin->pin_id, + gpio_pin->config); + if (ret != 0) + goto unlock; + + list_del(pos); + kfree(gpio_pin); + break; + } + } + +unlock: + spin_unlock_irqrestore(&ipctl->gpio_configs_lock, flags); +} + +static int s32_pmx_gpio_set_direction(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset, + bool input) +{ + unsigned int config; + unsigned int mask = S32_MSCR_IBE | S32_MSCR_OBE; + + if (input) { + /* Disable output buffer and enable input buffer */ + config = S32_MSCR_IBE; + } else { + /* Disable input buffer and enable output buffer */ + config = S32_MSCR_OBE; + } + + return s32_regmap_update(pctldev, offset, mask, config); +} + +static const struct pinmux_ops s32_pmx_ops = { + .get_functions_count = s32_pmx_get_funcs_count, + .get_function_name = s32_pmx_get_func_name, + .get_function_groups = s32_pmx_get_groups, + .set_mux = s32_pmx_set, + .gpio_request_enable = s32_pmx_gpio_request_enable, + .gpio_disable_free = s32_pmx_gpio_disable_free, + .gpio_set_direction = s32_pmx_gpio_set_direction, +}; + +/* Set the reserved elements as -1 */ +static const int support_slew[] = {208, -1, -1, -1, 166, 150, 133, 83}; + +static int s32_get_slew_regval(int arg) +{ + int i; + /* Translate a real slew rate (MHz) to a register value */ + for (i = 0; i < ARRAY_SIZE(support_slew); i++) { + if (arg == support_slew[i]) + return i; + } + + return -EINVAL; +} + +static int s32_get_pin_conf(enum pin_config_param param, u32 arg, + unsigned int *mask, unsigned int *config) +{ + int ret; + + switch (param) { + /* All pins are persistent over suspend */ + case PIN_CONFIG_PERSIST_STATE: + return 0; + case PIN_CONFIG_DRIVE_OPEN_DRAIN: + *config |= S32_MSCR_ODE; + *mask |= S32_MSCR_ODE; + break; + case PIN_CONFIG_OUTPUT_ENABLE: + if (arg) + *config |= S32_MSCR_OBE; + else + *config &= ~S32_MSCR_OBE; + *mask |= S32_MSCR_OBE; + break; + case PIN_CONFIG_INPUT_ENABLE: + if (arg) + *config |= S32_MSCR_IBE; + else + *config &= ~S32_MSCR_IBE; + *mask |= S32_MSCR_IBE; + break; + case PIN_CONFIG_SLEW_RATE: + ret = s32_get_slew_regval(arg); + if (ret < 0) + return ret; + *config |= S32_MSCR_SRE((u32)ret); + *mask |= S32_MSCR_SRE(~0); + break; + case PIN_CONFIG_BIAS_PULL_UP: + if (arg) + *config |= S32_MSCR_PUS; + else + *config &= ~S32_MSCR_PUS; + fallthrough; + case PIN_CONFIG_BIAS_PULL_DOWN: + if (arg) + *config |= S32_MSCR_PUE; + else + *config &= ~S32_MSCR_PUE; + *mask |= S32_MSCR_PUE | S32_MSCR_PUS; + break; + case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: + *config &= ~(S32_MSCR_ODE | S32_MSCR_OBE | S32_MSCR_IBE); + *mask |= S32_MSCR_ODE | S32_MSCR_OBE | S32_MSCR_IBE; + fallthrough; + case PIN_CONFIG_BIAS_DISABLE: + *config &= ~(S32_MSCR_PUS | S32_MSCR_PUE); + *mask |= S32_MSCR_PUS | S32_MSCR_PUE; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int s32_pinconf_mscr_update(struct pinctrl_dev *pctldev, + unsigned int pin_id, + unsigned long *configs, + unsigned int num_configs) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + unsigned int config = 0, mask = 0; + int i, ret; + + if (s32_check_pin(pctldev, pin_id) != 0) + return -EINVAL; + + dev_dbg(ipctl->dev, "pinconf set pin %s with %d configs\n", + pin_get_name(pctldev, pin_id), num_configs); + + for (i = 0; i < num_configs; i++) { + ret = s32_get_pin_conf(pinconf_to_config_param(configs[i]), + pinconf_to_config_argument(configs[i]), + &mask, &config); + if (ret) + return ret; + } + + if (!config && !mask) + return 0; + + ret = s32_regmap_update(pctldev, pin_id, mask, config); + + dev_dbg(ipctl->dev, "update: pin %d cfg 0x%x\n", pin_id, config); + + return ret; +} + +static int s32_pinconf_get(struct pinctrl_dev *pctldev, + unsigned int pin_id, + unsigned long *config) +{ + return s32_regmap_read(pctldev, pin_id, (unsigned int *)config); +} + +static int s32_pinconf_set(struct pinctrl_dev *pctldev, + unsigned int pin_id, unsigned long *configs, + unsigned int num_configs) +{ + return s32_pinconf_mscr_update(pctldev, pin_id, configs, + num_configs); +} + +static int s32_pconf_group_set(struct pinctrl_dev *pctldev, unsigned int selector, + unsigned long *configs, unsigned int num_configs) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + struct s32_pin_group *grp; + int i, ret; + + grp = &info->groups[selector]; + for (i = 0; i < grp->npins; i++) { + ret = s32_pinconf_mscr_update(pctldev, grp->pin_ids[i], + configs, num_configs); + if (ret) + return ret; + } + + return 0; +} + +static void s32_pinconf_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, unsigned int pin_id) +{ + unsigned int config; + int ret = s32_regmap_read(pctldev, pin_id, &config); + + if (!ret) + seq_printf(s, "0x%x", config); +} + +static void s32_pinconf_group_dbg_show(struct pinctrl_dev *pctldev, + struct seq_file *s, unsigned int selector) +{ + struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + struct s32_pin_group *grp; + unsigned int config; + const char *name; + int i, ret; + + seq_puts(s, "\n"); + grp = &info->groups[selector]; + for (i = 0; i < grp->npins; i++) { + name = pin_get_name(pctldev, grp->pin_ids[i]); + ret = s32_regmap_read(pctldev, grp->pin_ids[i], &config); + if (ret) + return; + seq_printf(s, "%s: 0x%x\n", name, config); + } +} + +static const struct pinconf_ops s32_pinconf_ops = { + .pin_config_get = s32_pinconf_get, + .pin_config_set = s32_pinconf_set, + .pin_config_group_set = s32_pconf_group_set, + .pin_config_dbg_show = s32_pinconf_dbg_show, + .pin_config_group_dbg_show = s32_pinconf_group_dbg_show, +}; + +#ifdef CONFIG_PM_SLEEP +static bool s32_pinctrl_should_save(struct s32_pinctrl *ipctl, + unsigned int pin) +{ + const struct pin_desc *pd = pin_desc_get(ipctl->pctl, pin); + + if (!pd) + return false; + + /* + * Only restore the pin if it is actually in use by the kernel (or + * by userspace). + */ + if (pd->mux_owner || pd->gpio_owner) + return true; + + return false; +} + +int __maybe_unused s32_pinctrl_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct s32_pinctrl *ipctl = platform_get_drvdata(pdev); + const struct pinctrl_pin_desc *pin; + const struct s32_pinctrl_soc_info *info = ipctl->info; + struct s32_pinctrl_context *saved_context = &ipctl->saved_context; + int i; + int ret; + unsigned int config; + + for (i = 0; i < info->npins; i++) { + pin = &info->pins[i]; + + if (!s32_pinctrl_should_save(ipctl, pin->number)) + continue; + + ret = s32_regmap_read(ipctl->pctl, pin->number, &config); + if (ret) + return -EINVAL; + + saved_context->pads[i] = config; + } + + return 0; +} + +int __maybe_unused s32_pinctrl_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct s32_pinctrl *ipctl = platform_get_drvdata(pdev); + const struct s32_pinctrl_soc_info *info = ipctl->info; + const struct pinctrl_pin_desc *pin; + struct s32_pinctrl_context *saved_context = &ipctl->saved_context; + int ret, i; + + for (i = 0; i < info->npins; i++) { + pin = &info->pins[i]; + + if (!s32_pinctrl_should_save(ipctl, pin->number)) + continue; + + ret = s32_regmap_write(ipctl->pctl, pin->number, + saved_context->pads[i]); + if (ret) + return ret; + } + + return 0; +} +#endif + +static void s32_pinctrl_parse_groups(struct device_node *np, + struct s32_pin_group *grp, + struct s32_pinctrl_soc_info *info) +{ + const __be32 *p; + struct device *dev; + struct property *prop; + int i, npins; + u32 pinmux; + + dev = info->dev; + + dev_dbg(dev, "group: %s\n", np->name); + + /* Initialise group */ + grp->name = np->name; + + npins = of_property_count_elems_of_size(np, "pinmux", sizeof(u32)); + + if (npins < 0) { + dev_err(dev, "Failed to read 'pinmux' property in node %s.\n", + np->name); + return; + } + if (!npins) { + dev_err(dev, "The group %s has no pins.\n", np->name); + return; + } + + grp->npins = npins; + + grp->pin_ids = devm_kcalloc(info->dev, grp->npins, + sizeof(unsigned int), GFP_KERNEL); + grp->pin_sss = devm_kcalloc(info->dev, grp->npins, + sizeof(unsigned int), GFP_KERNEL); + + if (!grp->pin_ids || !grp->pin_sss) { + dev_err(dev, "Failed to allocate memory for the group %s.\n", + np->name); + return; + } + + i = 0; + of_property_for_each_u32(np, "pinmux", prop, p, pinmux) { + grp->pin_ids[i] = get_pin_no(pinmux); + grp->pin_sss[i] = get_pin_func(pinmux); + + dev_dbg(info->dev, "pin-id: 0x%x, sss: 0x%x", + grp->pin_ids[i], grp->pin_sss[i]); + i++; + } +} + +static void s32_pinctrl_parse_functions(struct device_node *np, + struct s32_pinctrl_soc_info *info, + u32 index) +{ + struct device_node *child; + struct s32_pmx_func *func; + struct s32_pin_group *grp; + u32 i = 0; + + dev_dbg(info->dev, "parse function(%d): %s\n", index, np->name); + + func = &info->functions[index]; + + /* Initialise function */ + func->name = np->name; + func->num_groups = of_get_child_count(np); + if (func->num_groups == 0) { + dev_err(info->dev, "no groups defined in %s\n", np->full_name); + return; + } + func->groups = devm_kzalloc(info->dev, + func->num_groups * sizeof(char *), GFP_KERNEL); + + for_each_child_of_node(np, child) { + func->groups[i] = child->name; + grp = &info->groups[info->grp_index++]; + s32_pinctrl_parse_groups(child, grp, info); + i++; + } +} + +static int s32_pinctrl_probe_dt(struct platform_device *pdev, + struct s32_pinctrl *ipctl) +{ + struct s32_pinctrl_soc_info *info = ipctl->info; + struct device_node *np = pdev->dev.of_node; + struct device_node *child; + struct resource *res; + struct regmap *map; + void __iomem *base; + int mem_regions = info->mem_regions; + u32 nfuncs = 0; + u32 i = 0; + + if (!np) + return -ENODEV; + + if (mem_regions == 0) { + dev_err(&pdev->dev, "mem_regions is 0\n"); + return -EINVAL; + } + + ipctl->regions = devm_kzalloc(&pdev->dev, + mem_regions * sizeof(*(ipctl->regions)), + GFP_KERNEL); + if (!ipctl->regions) + return -ENOMEM; + + for (i = 0; i < mem_regions; ++i) { + base = devm_platform_get_and_ioremap_resource(pdev, i, &res); + if (IS_ERR(base)) + return PTR_ERR(base); + + snprintf(ipctl->regions[i].name, + sizeof(ipctl->regions[i].name), "map%u", i); + + s32_regmap_config.name = ipctl->regions[i].name; + s32_regmap_config.max_register = resource_size(res) - + s32_regmap_config.reg_stride; + + map = devm_regmap_init_mmio(&pdev->dev, base, + &s32_regmap_config); + if (IS_ERR(map)) { + dev_err(&pdev->dev, "Failed to init regmap[%u]\n", i); + return PTR_ERR(map); + } + + ipctl->regions[i].map = map; + ipctl->regions[i].pin_range = &info->mem_pin_ranges[i]; + } + + nfuncs = of_get_child_count(np); + if (nfuncs <= 0) { + dev_err(&pdev->dev, "no functions defined\n"); + return -EINVAL; + } + + info->nfunctions = nfuncs; + info->functions = devm_kzalloc(&pdev->dev, + nfuncs * sizeof(struct s32_pmx_func), + GFP_KERNEL); + if (!info->functions) + return -ENOMEM; + + info->ngroups = 0; + for_each_child_of_node(np, child) + info->ngroups += of_get_child_count(child); + info->groups = devm_kzalloc(&pdev->dev, + info->ngroups * sizeof(struct s32_pin_group), + GFP_KERNEL); + if (!info->groups) + return -ENOMEM; + + i = 0; + for_each_child_of_node(np, child) + s32_pinctrl_parse_functions(child, info, i++); + + return 0; +} + +int s32_pinctrl_probe(struct platform_device *pdev, + struct s32_pinctrl_soc_info *info) +{ + struct s32_pinctrl *ipctl; + int ret; + struct pinctrl_desc *s32_pinctrl_desc; +#ifdef CONFIG_PM_SLEEP + struct s32_pinctrl_context *saved_context; +#endif + + if (!info || !info->pins || !info->npins) { + dev_err(&pdev->dev, "wrong pinctrl info\n"); + return -EINVAL; + } + + info->dev = &pdev->dev; + + /* Create state holders etc for this driver */ + ipctl = devm_kzalloc(&pdev->dev, sizeof(*ipctl), GFP_KERNEL); + if (!ipctl) + return -ENOMEM; + + ipctl->info = info; + ipctl->dev = info->dev; + platform_set_drvdata(pdev, ipctl); + + INIT_LIST_HEAD(&ipctl->gpio_configs); + spin_lock_init(&ipctl->gpio_configs_lock); + + s32_pinctrl_desc = + devm_kmalloc(&pdev->dev, sizeof(*s32_pinctrl_desc), GFP_KERNEL); + if (!s32_pinctrl_desc) + return -ENOMEM; + + s32_pinctrl_desc->name = dev_name(&pdev->dev); + s32_pinctrl_desc->pins = info->pins; + s32_pinctrl_desc->npins = info->npins; + s32_pinctrl_desc->pctlops = &s32_pctrl_ops; + s32_pinctrl_desc->pmxops = &s32_pmx_ops; + s32_pinctrl_desc->confops = &s32_pinconf_ops; + s32_pinctrl_desc->owner = THIS_MODULE; + + ret = s32_pinctrl_probe_dt(pdev, ipctl); + if (ret) { + dev_err(&pdev->dev, "fail to probe dt properties\n"); + return ret; + } + + ipctl->pctl = devm_pinctrl_register(&pdev->dev, s32_pinctrl_desc, + ipctl); + + if (IS_ERR(ipctl->pctl)) { + dev_err(&pdev->dev, "could not register s32 pinctrl driver\n"); + return PTR_ERR(ipctl->pctl); + } + +#ifdef CONFIG_PM_SLEEP + saved_context = &ipctl->saved_context; + saved_context->pads = + devm_kcalloc(&pdev->dev, info->npins, + sizeof(*saved_context->pads), + GFP_KERNEL); + if (!saved_context->pads) + return -ENOMEM; +#endif + + dev_info(&pdev->dev, "initialized s32 pinctrl driver\n"); + + return 0; +} diff --git a/drivers/pinctrl/nxp/pinctrl-s32g2.c b/drivers/pinctrl/nxp/pinctrl-s32g2.c new file mode 100644 index 000000000000..7dd0b4f8904d --- /dev/null +++ b/drivers/pinctrl/nxp/pinctrl-s32g2.c @@ -0,0 +1,773 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * NXP S32G pinctrl driver + * + * Copyright 2015-2016 Freescale Semiconductor, Inc. + * Copyright 2017-2018, 2020-2022 NXP + * Copyright (C) 2022 SUSE LLC + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "pinctrl-s32.h" + +enum s32_pins { + S32G_MSCR_PA_00 = 0, + S32G_MSCR_PA_01 = 1, + S32G_MSCR_PA_02 = 2, + S32G_MSCR_PA_03 = 3, + S32G_MSCR_PA_04 = 4, + S32G_MSCR_PA_05 = 5, + S32G_MSCR_PA_06 = 6, + S32G_MSCR_PA_07 = 7, + S32G_MSCR_PA_08 = 8, + S32G_MSCR_PA_09 = 9, + S32G_MSCR_PA_10 = 10, + S32G_MSCR_PA_11 = 11, + S32G_MSCR_PA_12 = 12, + S32G_MSCR_PA_13 = 13, + S32G_MSCR_PA_14 = 14, + S32G_MSCR_PA_15 = 15, + S32G_MSCR_PB_00 = 16, + S32G_MSCR_PB_01 = 17, + S32G_MSCR_PB_02 = 18, + S32G_MSCR_PB_03 = 19, + S32G_MSCR_PB_04 = 20, + S32G_MSCR_PB_05 = 21, + S32G_MSCR_PB_06 = 22, + S32G_MSCR_PB_07 = 23, + S32G_MSCR_PB_08 = 24, + S32G_MSCR_PB_09 = 25, + S32G_MSCR_PB_10 = 26, + S32G_MSCR_PB_11 = 27, + S32G_MSCR_PB_12 = 28, + S32G_MSCR_PB_13 = 29, + S32G_MSCR_PB_14 = 30, + S32G_MSCR_PB_15 = 31, + S32G_MSCR_PC_00 = 32, + S32G_MSCR_PC_01 = 33, + S32G_MSCR_PC_02 = 34, + S32G_MSCR_PC_03 = 35, + S32G_MSCR_PC_04 = 36, + S32G_MSCR_PC_05 = 37, + S32G_MSCR_PC_06 = 38, + S32G_MSCR_PC_07 = 39, + S32G_MSCR_PC_08 = 40, + S32G_MSCR_PC_09 = 41, + S32G_MSCR_PC_10 = 42, + S32G_MSCR_PC_11 = 43, + S32G_MSCR_PC_12 = 44, + S32G_MSCR_PC_13 = 45, + S32G_MSCR_PC_14 = 46, + S32G_MSCR_PC_15 = 47, + S32G_MSCR_PD_00 = 48, + S32G_MSCR_PD_01 = 49, + S32G_MSCR_PD_02 = 50, + S32G_MSCR_PD_03 = 51, + S32G_MSCR_PD_04 = 52, + S32G_MSCR_PD_05 = 53, + S32G_MSCR_PD_06 = 54, + S32G_MSCR_PD_07 = 55, + S32G_MSCR_PD_08 = 56, + S32G_MSCR_PD_09 = 57, + S32G_MSCR_PD_10 = 58, + S32G_MSCR_PD_11 = 59, + S32G_MSCR_PD_12 = 60, + S32G_MSCR_PD_13 = 61, + S32G_MSCR_PD_14 = 62, + S32G_MSCR_PD_15 = 63, + S32G_MSCR_PE_00 = 64, + S32G_MSCR_PE_01 = 65, + S32G_MSCR_PE_02 = 66, + S32G_MSCR_PE_03 = 67, + S32G_MSCR_PE_04 = 68, + S32G_MSCR_PE_05 = 69, + S32G_MSCR_PE_06 = 70, + S32G_MSCR_PE_07 = 71, + S32G_MSCR_PE_08 = 72, + S32G_MSCR_PE_09 = 73, + S32G_MSCR_PE_10 = 74, + S32G_MSCR_PE_11 = 75, + S32G_MSCR_PE_12 = 76, + S32G_MSCR_PE_13 = 77, + S32G_MSCR_PE_14 = 78, + S32G_MSCR_PE_15 = 79, + S32G_MSCR_PF_00 = 80, + S32G_MSCR_PF_01 = 81, + S32G_MSCR_PF_02 = 82, + S32G_MSCR_PF_03 = 83, + S32G_MSCR_PF_04 = 84, + S32G_MSCR_PF_05 = 85, + S32G_MSCR_PF_06 = 86, + S32G_MSCR_PF_07 = 87, + S32G_MSCR_PF_08 = 88, + S32G_MSCR_PF_09 = 89, + S32G_MSCR_PF_10 = 90, + S32G_MSCR_PF_11 = 91, + S32G_MSCR_PF_12 = 92, + S32G_MSCR_PF_13 = 93, + S32G_MSCR_PF_14 = 94, + S32G_MSCR_PF_15 = 95, + S32G_MSCR_PG_00 = 96, + S32G_MSCR_PG_01 = 97, + S32G_MSCR_PG_02 = 98, + S32G_MSCR_PG_03 = 99, + S32G_MSCR_PG_04 = 100, + S32G_MSCR_PG_05 = 101, + S32G_MSCR_PH_00 = 112, + S32G_MSCR_PH_01 = 113, + S32G_MSCR_PH_02 = 114, + S32G_MSCR_PH_03 = 115, + S32G_MSCR_PH_04 = 116, + S32G_MSCR_PH_05 = 117, + S32G_MSCR_PH_06 = 118, + S32G_MSCR_PH_07 = 119, + S32G_MSCR_PH_08 = 120, + S32G_MSCR_PH_09 = 121, + S32G_MSCR_PH_10 = 122, + S32G_MSCR_PJ_00 = 144, + S32G_MSCR_PJ_01 = 145, + S32G_MSCR_PJ_02 = 146, + S32G_MSCR_PJ_03 = 147, + S32G_MSCR_PJ_04 = 148, + S32G_MSCR_PJ_05 = 149, + S32G_MSCR_PJ_06 = 150, + S32G_MSCR_PJ_07 = 151, + S32G_MSCR_PJ_08 = 152, + S32G_MSCR_PJ_09 = 153, + S32G_MSCR_PJ_10 = 154, + S32G_MSCR_PJ_11 = 155, + S32G_MSCR_PJ_12 = 156, + S32G_MSCR_PJ_13 = 157, + S32G_MSCR_PJ_14 = 158, + S32G_MSCR_PJ_15 = 159, + S32G_MSCR_PK_00 = 160, + S32G_MSCR_PK_01 = 161, + S32G_MSCR_PK_02 = 162, + S32G_MSCR_PK_03 = 163, + S32G_MSCR_PK_04 = 164, + S32G_MSCR_PK_05 = 165, + S32G_MSCR_PK_06 = 166, + S32G_MSCR_PK_07 = 167, + S32G_MSCR_PK_08 = 168, + S32G_MSCR_PK_09 = 169, + S32G_MSCR_PK_10 = 170, + S32G_MSCR_PK_11 = 171, + S32G_MSCR_PK_12 = 172, + S32G_MSCR_PK_13 = 173, + S32G_MSCR_PK_14 = 174, + S32G_MSCR_PK_15 = 175, + S32G_MSCR_PL_00 = 176, + S32G_MSCR_PL_01 = 177, + S32G_MSCR_PL_02 = 178, + S32G_MSCR_PL_03 = 179, + S32G_MSCR_PL_04 = 180, + S32G_MSCR_PL_05 = 181, + S32G_MSCR_PL_06 = 182, + S32G_MSCR_PL_07 = 183, + S32G_MSCR_PL_08 = 184, + S32G_MSCR_PL_09 = 185, + S32G_MSCR_PL_10 = 186, + S32G_MSCR_PL_11 = 187, + S32G_MSCR_PL_12 = 188, + S32G_MSCR_PL_13 = 189, + S32G_MSCR_PL_14 = 190, + + S32G_IMCR_QSPI_A_DATA0 = 540, + S32G_IMCR_QSPI_A_DATA1 = 541, + S32G_IMCR_QSPI_A_DATA2 = 542, + S32G_IMCR_QSPI_A_DATA3 = 543, + S32G_IMCR_QSPI_A_DATA4 = 544, + S32G_IMCR_QSPI_A_DATA5 = 545, + S32G_IMCR_QSPI_A_DATA6 = 546, + S32G_IMCR_QSPI_A_DATA7 = 547, + S32G_IMCR_QSPI_DQS_A = 548, + S32G_IMCR_QSPI_B_DATA0 = 552, + S32G_IMCR_QSPI_B_DATA1 = 554, + S32G_IMCR_QSPI_B_DATA2 = 551, + S32G_IMCR_QSPI_B_DATA3 = 553, + S32G_IMCR_QSPI_B_DATA4 = 557, + S32G_IMCR_QSPI_B_DATA5 = 550, + S32G_IMCR_QSPI_B_DATA6 = 556, + S32G_IMCR_QSPI_B_DATA7 = 555, + S32G_IMCR_QSPI_DQS_B = 558, + S32G_IMCR_BOOT_BOOTMOD0 = 560, + S32G_IMCR_BOOT_BOOTMOD1 = 561, + S32G_IMCR_I2C0_SCL = 566, + S32G_IMCR_I2C0_SDA = 565, + S32G_IMCR_LIN0_RX = 512, + S32G_IMCR_USDHC_CMD = 515, + S32G_IMCR_USDHC_DAT0 = 516, + S32G_IMCR_USDHC_DAT1 = 517, + S32G_IMCR_USDHC_DAT2 = 520, + S32G_IMCR_USDHC_DAT3 = 521, + S32G_IMCR_USDHC_DAT4 = 522, + S32G_IMCR_USDHC_DAT5 = 523, + S32G_IMCR_USDHC_DAT6 = 519, + S32G_IMCR_USDHC_DAT7 = 518, + S32G_IMCR_USDHC_DQS = 524, + S32G_IMCR_CAN0_RXD = 513, + S32G_IMCR_CAN1_RXD = 631, + S32G_IMCR_CAN2_RXD = 632, + S32G_IMCR_CAN3_RXD = 633, + /* GMAC0 */ + S32G_IMCR_Ethernet_MDIO = 527, + S32G_IMCR_Ethernet_CRS = 526, + S32G_IMCR_Ethernet_COL = 525, + S32G_IMCR_Ethernet_RX_D0 = 531, + S32G_IMCR_Ethernet_RX_D1 = 532, + S32G_IMCR_Ethernet_RX_D2 = 533, + S32G_IMCR_Ethernet_RX_D3 = 534, + S32G_IMCR_Ethernet_RX_ER = 528, + S32G_IMCR_Ethernet_RX_CLK = 529, + S32G_IMCR_Ethernet_RX_DV = 530, + S32G_IMCR_Ethernet_TX_CLK = 538, + S32G_IMCR_Ethernet_REF_CLK = 535, + /* PFE EMAC 0 MII */ + /* PFE EMAC 1 MII */ + S32G_IMCR_PFE_EMAC_1_MDIO = 857, + S32G_IMCR_PFE_EMAC_1_CRS = 856, + S32G_IMCR_PFE_EMAC_1_COL = 855, + S32G_IMCR_PFE_EMAC_1_RX_D0 = 861, + S32G_IMCR_PFE_EMAC_1_RX_D1 = 862, + S32G_IMCR_PFE_EMAC_1_RX_D2 = 863, + S32G_IMCR_PFE_EMAC_1_RX_D3 = 864, + S32G_IMCR_PFE_EMAC_1_RX_ER = 860, + S32G_IMCR_PFE_EMAC_1_RX_CLK = 859, + S32G_IMCR_PFE_EMAC_1_RX_DV = 865, + S32G_IMCR_PFE_EMAC_1_TX_CLK = 866, + S32G_IMCR_PFE_EMAC_1_REF_CLK = 858, + /* PFE EMAC 2 MII */ + S32G_IMCR_PFE_EMAC_2_MDIO = 877, + S32G_IMCR_PFE_EMAC_2_CRS = 876, + S32G_IMCR_PFE_EMAC_2_COL = 875, + S32G_IMCR_PFE_EMAC_2_RX_D0 = 881, + S32G_IMCR_PFE_EMAC_2_RX_D1 = 882, + S32G_IMCR_PFE_EMAC_2_RX_D2 = 883, + S32G_IMCR_PFE_EMAC_2_RX_D3 = 884, + S32G_IMCR_PFE_EMAC_2_RX_ER = 880, + S32G_IMCR_PFE_EMAC_2_RX_CLK = 879, + S32G_IMCR_PFE_EMAC_2_RX_DV = 885, + S32G_IMCR_PFE_EMAC_2_TX_CLK = 886, + S32G_IMCR_PFE_EMAC_2_REF_CLK = 878, + + S32G_IMCR_FlexRay0_A_RX = 785, + S32G_IMCR_FlexRay0_B_RX = 786, + S32G_IMCR_FlexTimer0_CH0 = 655, + S32G_IMCR_FlexTimer1_CH0 = 665, + S32G_IMCR_FlexTimer0_CH1 = 656, + S32G_IMCR_FlexTimer1_CH1 = 666, + S32G_IMCR_FlexTimer0_CH2 = 657, + S32G_IMCR_FlexTimer1_CH2 = 667, + S32G_IMCR_FlexTimer0_CH3 = 658, + S32G_IMCR_FlexTimer1_CH3 = 668, + S32G_IMCR_FlexTimer0_CH4 = 659, + S32G_IMCR_FlexTimer1_CH4 = 669, + S32G_IMCR_FlexTimer0_CH5 = 660, + S32G_IMCR_FlexTimer1_CH5 = 670, + S32G_IMCR_FlexTimer0_EXTCLK = 661, + S32G_IMCR_FlexTimer1_EXTCLK = 671, + S32G_IMCR_I2C1_SCL = 717, + S32G_IMCR_I2C1_SDA = 718, + S32G_IMCR_I2C2_SCL = 719, + S32G_IMCR_I2C2_SDA = 720, + S32G_IMCR_I2C3_SCL = 721, + S32G_IMCR_I2C3_SDA = 722, + S32G_IMCR_I2C4_SCL = 723, + S32G_IMCR_I2C4_SDA = 724, + S32G_IMCR_LIN1_RX = 736, + S32G_IMCR_LIN2_RX = 737, + S32G_IMCR_DSPI0_PCS0 = 980, + S32G_IMCR_DSPI0_SCK = 981, + S32G_IMCR_DSPI0_SIN = 982, + S32G_IMCR_DSPI1_PCS0 = 985, + S32G_IMCR_DSPI1_SCK = 986, + S32G_IMCR_DSPI1_SIN = 987, + S32G_IMCR_DSPI2_PCS0 = 990, + S32G_IMCR_DSPI2_SCK = 991, + S32G_IMCR_DSPI2_SIN = 992, + S32G_IMCR_DSPI3_PCS0 = 995, + S32G_IMCR_DSPI3_SCK = 996, + S32G_IMCR_DSPI3_SIN = 997, + S32G_IMCR_DSPI4_PCS0 = 1000, + S32G_IMCR_DSPI4_SCK = 1001, + S32G_IMCR_DSPI4_SIN = 1002, + S32G_IMCR_DSPI5_PCS0 = 1005, + S32G_IMCR_DSPI5_SCK = 1006, + S32G_IMCR_DSPI5_SIN = 1007, + S32G_IMCR_LLCE_CAN0_RXD = 745, + S32G_IMCR_LLCE_CAN1_RXD = 746, + S32G_IMCR_LLCE_CAN2_RXD = 747, + S32G_IMCR_LLCE_CAN3_RXD = 748, + S32G_IMCR_LLCE_CAN4_RXD = 749, + S32G_IMCR_LLCE_CAN5_RXD = 750, + S32G_IMCR_LLCE_CAN6_RXD = 751, + S32G_IMCR_LLCE_CAN7_RXD = 752, + S32G_IMCR_LLCE_CAN8_RXD = 753, + S32G_IMCR_LLCE_CAN9_RXD = 754, + S32G_IMCR_LLCE_CAN10_RXD = 755, + S32G_IMCR_LLCE_CAN11_RXD = 756, + S32G_IMCR_LLCE_CAN12_RXD = 757, + S32G_IMCR_LLCE_CAN13_RXD = 758, + S32G_IMCR_LLCE_CAN14_RXD = 759, + S32G_IMCR_LLCE_CAN15_RXD = 760, + S32G_IMCR_USB_CLK = 895, + S32G_IMCR_USB_DATA0 = 896, + S32G_IMCR_USB_DATA1 = 897, + S32G_IMCR_USB_DATA2 = 898, + S32G_IMCR_USB_DATA3 = 899, + S32G_IMCR_USB_DATA4 = 900, + S32G_IMCR_USB_DATA5 = 901, + S32G_IMCR_USB_DATA6 = 902, + S32G_IMCR_USB_DATA7 = 903, + S32G_IMCR_USB_DIR = 904, + S32G_IMCR_USB_NXT = 905, + + S32G_IMCR_SIUL_EIRQ0 = 910, + S32G_IMCR_SIUL_EIRQ1 = 911, + S32G_IMCR_SIUL_EIRQ2 = 912, + S32G_IMCR_SIUL_EIRQ3 = 913, + S32G_IMCR_SIUL_EIRQ4 = 914, + S32G_IMCR_SIUL_EIRQ5 = 915, + S32G_IMCR_SIUL_EIRQ6 = 916, + S32G_IMCR_SIUL_EIRQ7 = 917, + S32G_IMCR_SIUL_EIRQ8 = 918, + S32G_IMCR_SIUL_EIRQ9 = 919, + S32G_IMCR_SIUL_EIRQ10 = 920, + S32G_IMCR_SIUL_EIRQ11 = 921, + S32G_IMCR_SIUL_EIRQ12 = 922, + S32G_IMCR_SIUL_EIRQ13 = 923, + S32G_IMCR_SIUL_EIRQ14 = 924, + S32G_IMCR_SIUL_EIRQ15 = 925, + S32G_IMCR_SIUL_EIRQ16 = 926, + S32G_IMCR_SIUL_EIRQ17 = 927, + S32G_IMCR_SIUL_EIRQ18 = 928, + S32G_IMCR_SIUL_EIRQ19 = 929, + S32G_IMCR_SIUL_EIRQ20 = 930, + S32G_IMCR_SIUL_EIRQ21 = 931, + S32G_IMCR_SIUL_EIRQ22 = 932, + S32G_IMCR_SIUL_EIRQ23 = 933, + S32G_IMCR_SIUL_EIRQ24 = 934, + S32G_IMCR_SIUL_EIRQ25 = 935, + S32G_IMCR_SIUL_EIRQ26 = 936, + S32G_IMCR_SIUL_EIRQ27 = 937, + S32G_IMCR_SIUL_EIRQ28 = 938, + S32G_IMCR_SIUL_EIRQ29 = 939, + S32G_IMCR_SIUL_EIRQ30 = 940, + S32G_IMCR_SIUL_EIRQ31 = 941, +}; + +/* Pad names for the pinmux subsystem */ +static const struct pinctrl_pin_desc s32_pinctrl_pads_siul2[] = { + + /* SIUL2_0 pins. */ + + S32_PINCTRL_PIN(S32G_MSCR_PA_00), + S32_PINCTRL_PIN(S32G_MSCR_PA_01), + S32_PINCTRL_PIN(S32G_MSCR_PA_02), + S32_PINCTRL_PIN(S32G_MSCR_PA_03), + S32_PINCTRL_PIN(S32G_MSCR_PA_04), + S32_PINCTRL_PIN(S32G_MSCR_PA_05), + S32_PINCTRL_PIN(S32G_MSCR_PA_06), + S32_PINCTRL_PIN(S32G_MSCR_PA_07), + S32_PINCTRL_PIN(S32G_MSCR_PA_08), + S32_PINCTRL_PIN(S32G_MSCR_PA_09), + S32_PINCTRL_PIN(S32G_MSCR_PA_10), + S32_PINCTRL_PIN(S32G_MSCR_PA_11), + S32_PINCTRL_PIN(S32G_MSCR_PA_12), + S32_PINCTRL_PIN(S32G_MSCR_PA_13), + S32_PINCTRL_PIN(S32G_MSCR_PA_14), + S32_PINCTRL_PIN(S32G_MSCR_PA_15), + S32_PINCTRL_PIN(S32G_MSCR_PB_00), + S32_PINCTRL_PIN(S32G_MSCR_PB_01), + S32_PINCTRL_PIN(S32G_MSCR_PB_02), + S32_PINCTRL_PIN(S32G_MSCR_PB_03), + S32_PINCTRL_PIN(S32G_MSCR_PB_04), + S32_PINCTRL_PIN(S32G_MSCR_PB_05), + S32_PINCTRL_PIN(S32G_MSCR_PB_06), + S32_PINCTRL_PIN(S32G_MSCR_PB_07), + S32_PINCTRL_PIN(S32G_MSCR_PB_08), + S32_PINCTRL_PIN(S32G_MSCR_PB_09), + S32_PINCTRL_PIN(S32G_MSCR_PB_10), + S32_PINCTRL_PIN(S32G_MSCR_PB_11), + S32_PINCTRL_PIN(S32G_MSCR_PB_12), + S32_PINCTRL_PIN(S32G_MSCR_PB_13), + S32_PINCTRL_PIN(S32G_MSCR_PB_14), + S32_PINCTRL_PIN(S32G_MSCR_PB_15), + S32_PINCTRL_PIN(S32G_MSCR_PC_00), + S32_PINCTRL_PIN(S32G_MSCR_PC_01), + S32_PINCTRL_PIN(S32G_MSCR_PC_02), + S32_PINCTRL_PIN(S32G_MSCR_PC_03), + S32_PINCTRL_PIN(S32G_MSCR_PC_04), + S32_PINCTRL_PIN(S32G_MSCR_PC_05), + S32_PINCTRL_PIN(S32G_MSCR_PC_06), + S32_PINCTRL_PIN(S32G_MSCR_PC_07), + S32_PINCTRL_PIN(S32G_MSCR_PC_08), + S32_PINCTRL_PIN(S32G_MSCR_PC_09), + S32_PINCTRL_PIN(S32G_MSCR_PC_10), + S32_PINCTRL_PIN(S32G_MSCR_PC_11), + S32_PINCTRL_PIN(S32G_MSCR_PC_12), + S32_PINCTRL_PIN(S32G_MSCR_PC_13), + S32_PINCTRL_PIN(S32G_MSCR_PC_14), + S32_PINCTRL_PIN(S32G_MSCR_PC_15), + S32_PINCTRL_PIN(S32G_MSCR_PD_00), + S32_PINCTRL_PIN(S32G_MSCR_PD_01), + S32_PINCTRL_PIN(S32G_MSCR_PD_02), + S32_PINCTRL_PIN(S32G_MSCR_PD_03), + S32_PINCTRL_PIN(S32G_MSCR_PD_04), + S32_PINCTRL_PIN(S32G_MSCR_PD_05), + S32_PINCTRL_PIN(S32G_MSCR_PD_06), + S32_PINCTRL_PIN(S32G_MSCR_PD_07), + S32_PINCTRL_PIN(S32G_MSCR_PD_08), + S32_PINCTRL_PIN(S32G_MSCR_PD_09), + S32_PINCTRL_PIN(S32G_MSCR_PD_10), + S32_PINCTRL_PIN(S32G_MSCR_PD_11), + S32_PINCTRL_PIN(S32G_MSCR_PD_12), + S32_PINCTRL_PIN(S32G_MSCR_PD_13), + S32_PINCTRL_PIN(S32G_MSCR_PD_14), + S32_PINCTRL_PIN(S32G_MSCR_PD_15), + S32_PINCTRL_PIN(S32G_MSCR_PE_00), + S32_PINCTRL_PIN(S32G_MSCR_PE_01), + S32_PINCTRL_PIN(S32G_MSCR_PE_02), + S32_PINCTRL_PIN(S32G_MSCR_PE_03), + S32_PINCTRL_PIN(S32G_MSCR_PE_04), + S32_PINCTRL_PIN(S32G_MSCR_PE_05), + S32_PINCTRL_PIN(S32G_MSCR_PE_06), + S32_PINCTRL_PIN(S32G_MSCR_PE_07), + S32_PINCTRL_PIN(S32G_MSCR_PE_08), + S32_PINCTRL_PIN(S32G_MSCR_PE_09), + S32_PINCTRL_PIN(S32G_MSCR_PE_10), + S32_PINCTRL_PIN(S32G_MSCR_PE_11), + S32_PINCTRL_PIN(S32G_MSCR_PE_12), + S32_PINCTRL_PIN(S32G_MSCR_PE_13), + S32_PINCTRL_PIN(S32G_MSCR_PE_14), + S32_PINCTRL_PIN(S32G_MSCR_PE_15), + S32_PINCTRL_PIN(S32G_MSCR_PF_00), + S32_PINCTRL_PIN(S32G_MSCR_PF_01), + S32_PINCTRL_PIN(S32G_MSCR_PF_02), + S32_PINCTRL_PIN(S32G_MSCR_PF_03), + S32_PINCTRL_PIN(S32G_MSCR_PF_04), + S32_PINCTRL_PIN(S32G_MSCR_PF_05), + S32_PINCTRL_PIN(S32G_MSCR_PF_06), + S32_PINCTRL_PIN(S32G_MSCR_PF_07), + S32_PINCTRL_PIN(S32G_MSCR_PF_08), + S32_PINCTRL_PIN(S32G_MSCR_PF_09), + S32_PINCTRL_PIN(S32G_MSCR_PF_10), + S32_PINCTRL_PIN(S32G_MSCR_PF_11), + S32_PINCTRL_PIN(S32G_MSCR_PF_12), + S32_PINCTRL_PIN(S32G_MSCR_PF_13), + S32_PINCTRL_PIN(S32G_MSCR_PF_14), + S32_PINCTRL_PIN(S32G_MSCR_PF_15), + S32_PINCTRL_PIN(S32G_MSCR_PG_00), + S32_PINCTRL_PIN(S32G_MSCR_PG_01), + S32_PINCTRL_PIN(S32G_MSCR_PG_02), + S32_PINCTRL_PIN(S32G_MSCR_PG_03), + S32_PINCTRL_PIN(S32G_MSCR_PG_04), + S32_PINCTRL_PIN(S32G_MSCR_PG_05), + + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA0), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA1), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA2), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA3), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA4), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA5), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA6), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_A_DATA7), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_DQS_A), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA0), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA1), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA2), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA3), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA4), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA5), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA6), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_B_DATA7), + S32_PINCTRL_PIN(S32G_IMCR_QSPI_DQS_B), + S32_PINCTRL_PIN(S32G_IMCR_I2C0_SCL), + S32_PINCTRL_PIN(S32G_IMCR_I2C0_SDA), + S32_PINCTRL_PIN(S32G_IMCR_LIN0_RX), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_CMD), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT0), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT1), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT2), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT3), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT4), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT5), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT6), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DAT7), + S32_PINCTRL_PIN(S32G_IMCR_USDHC_DQS), + S32_PINCTRL_PIN(S32G_IMCR_CAN0_RXD), + /* GMAC0 */ + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_MDIO), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_CRS), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_COL), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_D0), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_D1), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_D2), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_D3), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_ER), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_RX_DV), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_TX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_Ethernet_REF_CLK), + + /* SIUL2_1 pins. */ + + S32_PINCTRL_PIN(S32G_MSCR_PH_00), + S32_PINCTRL_PIN(S32G_MSCR_PH_01), + S32_PINCTRL_PIN(S32G_MSCR_PH_02), + S32_PINCTRL_PIN(S32G_MSCR_PH_03), + S32_PINCTRL_PIN(S32G_MSCR_PH_04), + S32_PINCTRL_PIN(S32G_MSCR_PH_05), + S32_PINCTRL_PIN(S32G_MSCR_PH_06), + S32_PINCTRL_PIN(S32G_MSCR_PH_07), + S32_PINCTRL_PIN(S32G_MSCR_PH_08), + S32_PINCTRL_PIN(S32G_MSCR_PH_09), + S32_PINCTRL_PIN(S32G_MSCR_PH_10), + S32_PINCTRL_PIN(S32G_MSCR_PJ_00), + S32_PINCTRL_PIN(S32G_MSCR_PJ_01), + S32_PINCTRL_PIN(S32G_MSCR_PJ_02), + S32_PINCTRL_PIN(S32G_MSCR_PJ_03), + S32_PINCTRL_PIN(S32G_MSCR_PJ_04), + S32_PINCTRL_PIN(S32G_MSCR_PJ_05), + S32_PINCTRL_PIN(S32G_MSCR_PJ_06), + S32_PINCTRL_PIN(S32G_MSCR_PJ_07), + S32_PINCTRL_PIN(S32G_MSCR_PJ_08), + S32_PINCTRL_PIN(S32G_MSCR_PJ_09), + S32_PINCTRL_PIN(S32G_MSCR_PJ_10), + S32_PINCTRL_PIN(S32G_MSCR_PJ_11), + S32_PINCTRL_PIN(S32G_MSCR_PJ_12), + S32_PINCTRL_PIN(S32G_MSCR_PJ_13), + S32_PINCTRL_PIN(S32G_MSCR_PJ_14), + S32_PINCTRL_PIN(S32G_MSCR_PJ_15), + S32_PINCTRL_PIN(S32G_MSCR_PK_00), + S32_PINCTRL_PIN(S32G_MSCR_PK_01), + S32_PINCTRL_PIN(S32G_MSCR_PK_02), + S32_PINCTRL_PIN(S32G_MSCR_PK_03), + S32_PINCTRL_PIN(S32G_MSCR_PK_04), + S32_PINCTRL_PIN(S32G_MSCR_PK_05), + S32_PINCTRL_PIN(S32G_MSCR_PK_06), + S32_PINCTRL_PIN(S32G_MSCR_PK_07), + S32_PINCTRL_PIN(S32G_MSCR_PK_08), + S32_PINCTRL_PIN(S32G_MSCR_PK_09), + S32_PINCTRL_PIN(S32G_MSCR_PK_10), + S32_PINCTRL_PIN(S32G_MSCR_PK_11), + S32_PINCTRL_PIN(S32G_MSCR_PK_12), + S32_PINCTRL_PIN(S32G_MSCR_PK_13), + S32_PINCTRL_PIN(S32G_MSCR_PK_14), + S32_PINCTRL_PIN(S32G_MSCR_PK_15), + S32_PINCTRL_PIN(S32G_MSCR_PL_00), + S32_PINCTRL_PIN(S32G_MSCR_PL_01), + S32_PINCTRL_PIN(S32G_MSCR_PL_02), + S32_PINCTRL_PIN(S32G_MSCR_PL_03), + S32_PINCTRL_PIN(S32G_MSCR_PL_04), + S32_PINCTRL_PIN(S32G_MSCR_PL_05), + S32_PINCTRL_PIN(S32G_MSCR_PL_06), + S32_PINCTRL_PIN(S32G_MSCR_PL_07), + S32_PINCTRL_PIN(S32G_MSCR_PL_08), + S32_PINCTRL_PIN(S32G_MSCR_PL_09), + S32_PINCTRL_PIN(S32G_MSCR_PL_10), + S32_PINCTRL_PIN(S32G_MSCR_PL_11), + S32_PINCTRL_PIN(S32G_MSCR_PL_12), + S32_PINCTRL_PIN(S32G_MSCR_PL_13), + S32_PINCTRL_PIN(S32G_MSCR_PL_14), + + S32_PINCTRL_PIN(S32G_IMCR_FlexRay0_A_RX), + S32_PINCTRL_PIN(S32G_IMCR_FlexRay0_B_RX), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH0), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH0), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH1), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH1), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH2), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH2), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH3), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH3), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH4), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH4), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_CH5), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_CH5), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer0_EXTCLK), + S32_PINCTRL_PIN(S32G_IMCR_FlexTimer1_EXTCLK), + S32_PINCTRL_PIN(S32G_IMCR_I2C1_SCL), + S32_PINCTRL_PIN(S32G_IMCR_I2C1_SDA), + S32_PINCTRL_PIN(S32G_IMCR_I2C2_SCL), + S32_PINCTRL_PIN(S32G_IMCR_I2C2_SDA), + S32_PINCTRL_PIN(S32G_IMCR_I2C3_SCL), + S32_PINCTRL_PIN(S32G_IMCR_I2C3_SDA), + S32_PINCTRL_PIN(S32G_IMCR_I2C4_SCL), + S32_PINCTRL_PIN(S32G_IMCR_I2C4_SDA), + S32_PINCTRL_PIN(S32G_IMCR_LIN1_RX), + S32_PINCTRL_PIN(S32G_IMCR_LIN2_RX), + S32_PINCTRL_PIN(S32G_IMCR_DSPI0_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI0_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI0_SIN), + S32_PINCTRL_PIN(S32G_IMCR_DSPI1_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI1_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI1_SIN), + S32_PINCTRL_PIN(S32G_IMCR_DSPI2_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI2_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI2_SIN), + S32_PINCTRL_PIN(S32G_IMCR_DSPI3_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI3_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI3_SIN), + S32_PINCTRL_PIN(S32G_IMCR_DSPI4_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI4_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI4_SIN), + S32_PINCTRL_PIN(S32G_IMCR_DSPI5_PCS0), + S32_PINCTRL_PIN(S32G_IMCR_DSPI5_SCK), + S32_PINCTRL_PIN(S32G_IMCR_DSPI5_SIN), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN0_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN1_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN2_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN3_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN4_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN5_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN6_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN7_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN8_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN9_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN10_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN11_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN12_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN13_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN14_RXD), + S32_PINCTRL_PIN(S32G_IMCR_LLCE_CAN15_RXD), + S32_PINCTRL_PIN(S32G_IMCR_CAN1_RXD), + S32_PINCTRL_PIN(S32G_IMCR_CAN2_RXD), + S32_PINCTRL_PIN(S32G_IMCR_CAN3_RXD), + S32_PINCTRL_PIN(S32G_IMCR_USB_CLK), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA0), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA1), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA2), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA3), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA4), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA5), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA6), + S32_PINCTRL_PIN(S32G_IMCR_USB_DATA7), + S32_PINCTRL_PIN(S32G_IMCR_USB_DIR), + S32_PINCTRL_PIN(S32G_IMCR_USB_NXT), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_MDIO), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_CRS), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_COL), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_D0), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_D1), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_D2), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_D3), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_ER), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_RX_DV), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_TX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_1_REF_CLK), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_MDIO), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_CRS), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_COL), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_D0), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_D1), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_D2), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_D3), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_ER), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_RX_DV), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_TX_CLK), + S32_PINCTRL_PIN(S32G_IMCR_PFE_EMAC_2_REF_CLK), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ0), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ1), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ2), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ3), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ4), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ5), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ6), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ7), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ8), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ9), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ10), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ11), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ12), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ13), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ14), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ15), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ16), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ17), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ18), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ19), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ20), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ21), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ22), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ23), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ24), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ25), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ26), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ27), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ28), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ29), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ30), + S32_PINCTRL_PIN(S32G_IMCR_SIUL_EIRQ31), +}; + +static const struct s32_pin_range s32_pin_ranges_siul2[] = { + /* MSCR pin ID ranges */ + S32_PIN_RANGE(0, 101), + S32_PIN_RANGE(112, 122), + S32_PIN_RANGE(144, 190), + /* IMCR pin ID ranges */ + S32_PIN_RANGE(512, 595), + S32_PIN_RANGE(631, 909), + S32_PIN_RANGE(942, 1007), +}; + +static struct s32_pinctrl_soc_info s32_pinctrl_info = { + .pins = s32_pinctrl_pads_siul2, + .npins = ARRAY_SIZE(s32_pinctrl_pads_siul2), + .mem_pin_ranges = s32_pin_ranges_siul2, + .mem_regions = ARRAY_SIZE(s32_pin_ranges_siul2), +}; + +static const struct of_device_id s32_pinctrl_of_match[] = { + { + + .compatible = "nxp,s32g2-siul2-pinctrl", + .data = (void *) &s32_pinctrl_info, + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, s32_pinctrl_of_match); + +static int s32g_pinctrl_probe(struct platform_device *pdev) +{ + const struct of_device_id *of_id = + of_match_device(s32_pinctrl_of_match, &pdev->dev); + + if (!of_id) + return -ENODEV; + + return s32_pinctrl_probe + (pdev, (struct s32_pinctrl_soc_info *) of_id->data); +} + +static const struct dev_pm_ops s32g_pinctrl_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(s32_pinctrl_suspend, + s32_pinctrl_resume) +}; + +static struct platform_driver s32g_pinctrl_driver = { + .driver = { + .name = "s32g-siul2-pinctrl", + .owner = THIS_MODULE, + .of_match_table = s32_pinctrl_of_match, + .pm = &s32g_pinctrl_pm_ops, + .suppress_bind_attrs = true, + }, + .probe = s32g_pinctrl_probe, +}; + +builtin_platform_driver(s32g_pinctrl_driver); + +MODULE_AUTHOR("Matthew Nunez "); +MODULE_DESCRIPTION("NXP S32G pinctrl driver"); +MODULE_LICENSE("GPL"); -- GitLab From 46c59901d47930b4782e34720f13d71012ce43a3 Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 20 Feb 2023 10:33:20 +0800 Subject: [PATCH 0084/5631] MAINTAINERS: Add NXP S32 pinctrl maintainer and reviewer Add myself as a maintainer and add NXP S32 Linux Team as a review group for S32 pinctrl patches. Signed-off-by: Chester Lin Link: https://lore.kernel.org/r/20230220023320.3499-4-clin@suse.com Signed-off-by: Linus Walleij --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..6048bbe0e672 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16529,6 +16529,14 @@ S: Supported F: drivers/gpio/gpio-sama5d2-piobu.c F: drivers/pinctrl/pinctrl-at91* +PIN CONTROLLER - NXP S32 +M: Chester Lin +R: NXP S32 Linux Team +L: linux-gpio@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pinctrl/nxp,s32* +F: drivers/pinctrl/nxp/ + PIN CONTROLLER - QUALCOMM M: Bjorn Andersson L: linux-arm-msm@vger.kernel.org -- GitLab From 45dab81899800e0e2874f6c9e58b8b0343f33edf Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:19:34 -0600 Subject: [PATCH 0085/5631] clk: samsung: Remove np argument from samsung_clk_init() The code using `np' argument was removed from samsung_clk_init(). Remove that leftover parameter as well. No functional change. Fixes: d5e136a21b20 ("clk: samsung: Register clk provider only after registering its all clocks") Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230223041938.22732-3-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos4.c | 2 +- drivers/clk/samsung/clk-exynos4412-isp.c | 2 +- drivers/clk/samsung/clk-exynos5250.c | 2 +- drivers/clk/samsung/clk-exynos5420.c | 2 +- drivers/clk/samsung/clk-s3c64xx.c | 2 +- drivers/clk/samsung/clk-s5pv210.c | 2 +- drivers/clk/samsung/clk.c | 6 +++--- drivers/clk/samsung/clk.h | 3 +-- 8 files changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index 22009cb53428..7756b21e8925 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -1251,7 +1251,7 @@ static void __init exynos4_clk_init(struct device_node *np, if (!reg_base) panic("%s: failed to map registers\n", __func__); - ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos4_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-exynos4412-isp.c b/drivers/clk/samsung/clk-exynos4412-isp.c index 471a6fb82670..0b6390e04533 100644 --- a/drivers/clk/samsung/clk-exynos4412-isp.c +++ b/drivers/clk/samsung/clk-exynos4412-isp.c @@ -121,7 +121,7 @@ static int __init exynos4x12_isp_clk_probe(struct platform_device *pdev) if (!exynos4x12_save_isp) return -ENOMEM; - ctx = samsung_clk_init(np, reg_base, CLK_NR_ISP_CLKS); + ctx = samsung_clk_init(reg_base, CLK_NR_ISP_CLKS); ctx->dev = dev; platform_set_drvdata(pdev, ctx); diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c index 113df773ee44..e77e455466f9 100644 --- a/drivers/clk/samsung/clk-exynos5250.c +++ b/drivers/clk/samsung/clk-exynos5250.c @@ -797,7 +797,7 @@ static void __init exynos5250_clk_init(struct device_node *np) panic("%s: unable to determine soc\n", __func__); } - ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos5250_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index caad74dee297..27b1c5d56bb3 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -1587,7 +1587,7 @@ static void __init exynos5x_clk_init(struct device_node *np, exynos5x_soc = soc; - ctx = samsung_clk_init(np, reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos5x_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c index d6b432a26d63..772f776572a1 100644 --- a/drivers/clk/samsung/clk-s3c64xx.c +++ b/drivers/clk/samsung/clk-s3c64xx.c @@ -405,7 +405,7 @@ void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f, panic("%s: failed to map registers\n", __func__); } - ctx = samsung_clk_init(np, reg_base, NR_CLKS); + ctx = samsung_clk_init(reg_base, NR_CLKS); hws = ctx->clk_data.hws; /* Register external clocks. */ diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c index 4425186bdcab..b3e9f775ffdb 100644 --- a/drivers/clk/samsung/clk-s5pv210.c +++ b/drivers/clk/samsung/clk-s5pv210.c @@ -743,7 +743,7 @@ static void __init __s5pv210_clk_init(struct device_node *np, struct samsung_clk_provider *ctx; struct clk_hw **hws; - ctx = samsung_clk_init(np, reg_base, NR_CLKS); + ctx = samsung_clk_init(reg_base, NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_register_mux(ctx, early_mux_clks, diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c index bca4731b14ea..c2758f4175a1 100644 --- a/drivers/clk/samsung/clk.c +++ b/drivers/clk/samsung/clk.c @@ -54,8 +54,8 @@ struct samsung_clk_reg_dump *samsung_clk_alloc_reg_dump( } /* setup the essentials required to support clock lookup using ccf */ -struct samsung_clk_provider *__init samsung_clk_init(struct device_node *np, - void __iomem *base, unsigned long nr_clks) +struct samsung_clk_provider * __init samsung_clk_init(void __iomem *base, + unsigned long nr_clks) { struct samsung_clk_provider *ctx; int i; @@ -341,7 +341,7 @@ struct samsung_clk_provider * __init samsung_cmu_register_one( return NULL; } - ctx = samsung_clk_init(np, reg_base, cmu->nr_clk_ids); + ctx = samsung_clk_init(reg_base, cmu->nr_clk_ids); if (cmu->pll_clks) samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks, diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h index b46e83a2581f..475f1d28cca6 100644 --- a/drivers/clk/samsung/clk.h +++ b/drivers/clk/samsung/clk.h @@ -337,8 +337,7 @@ struct samsung_cmu_info { const char *clk_name; }; -struct samsung_clk_provider * samsung_clk_init( - struct device_node *np, void __iomem *base, +struct samsung_clk_provider *samsung_clk_init(void __iomem *base, unsigned long nr_clks); void samsung_clk_of_add_provider(struct device_node *np, struct samsung_clk_provider *ctx); -- GitLab From 65bf1fbe784cafaa10906b1ba1402920c61f4a7e Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:19:33 -0600 Subject: [PATCH 0086/5631] clk: samsung: Don't pass reg_base to samsung_clk_register_pll() Base address can be derived from context structure. Remove `base' argument from samsung_clk_register_pll() and use `ctx->reg_base' instead, as it's done in other clock registering functions. No functional change. Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230223041938.22732-2-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos4.c | 4 ++-- drivers/clk/samsung/clk-exynos5250.c | 3 +-- drivers/clk/samsung/clk-exynos5420.c | 3 +-- drivers/clk/samsung/clk-exynos5433.c | 4 ++-- drivers/clk/samsung/clk-pll.c | 11 +++++------ drivers/clk/samsung/clk-s3c64xx.c | 2 +- drivers/clk/samsung/clk-s5pv210.c | 4 ++-- drivers/clk/samsung/clk.c | 3 +-- drivers/clk/samsung/clk.h | 2 +- 9 files changed, 16 insertions(+), 20 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index 7756b21e8925..7a9994144d72 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -1276,7 +1276,7 @@ static void __init exynos4_clk_init(struct device_node *np, exynos4210_vpll_rates; samsung_clk_register_pll(ctx, exynos4210_plls, - ARRAY_SIZE(exynos4210_plls), reg_base); + ARRAY_SIZE(exynos4210_plls)); } else { if (clk_hw_get_rate(hws[CLK_FIN_PLL]) == 24000000) { exynos4x12_plls[apll].rate_table = @@ -1288,7 +1288,7 @@ static void __init exynos4_clk_init(struct device_node *np, } samsung_clk_register_pll(ctx, exynos4x12_plls, - ARRAY_SIZE(exynos4x12_plls), reg_base); + ARRAY_SIZE(exynos4x12_plls)); } samsung_clk_register_fixed_rate(ctx, exynos4_fixed_rate_clks, diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c index e77e455466f9..f1cb69aea10e 100644 --- a/drivers/clk/samsung/clk-exynos5250.c +++ b/drivers/clk/samsung/clk-exynos5250.c @@ -815,8 +815,7 @@ static void __init exynos5250_clk_init(struct device_node *np) exynos5250_plls[vpll].rate_table = vpll_24mhz_tbl; samsung_clk_register_pll(ctx, exynos5250_plls, - ARRAY_SIZE(exynos5250_plls), - reg_base); + ARRAY_SIZE(exynos5250_plls)); samsung_clk_register_fixed_rate(ctx, exynos5250_fixed_rate_clks, ARRAY_SIZE(exynos5250_fixed_rate_clks)); samsung_clk_register_fixed_factor(ctx, exynos5250_fixed_factor_clks, diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index 27b1c5d56bb3..46cac4980be2 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -1606,8 +1606,7 @@ static void __init exynos5x_clk_init(struct device_node *np, else exynos5x_plls[bpll].rate_table = exynos5422_bpll_rate_table; - samsung_clk_register_pll(ctx, exynos5x_plls, ARRAY_SIZE(exynos5x_plls), - reg_base); + samsung_clk_register_pll(ctx, exynos5x_plls, ARRAY_SIZE(exynos5x_plls)); samsung_clk_register_fixed_rate(ctx, exynos5x_fixed_rate_clks, ARRAY_SIZE(exynos5x_fixed_rate_clks)); samsung_clk_register_fixed_factor(ctx, exynos5x_fixed_factor_clks, diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index f9daae20f393..eb72bf2aaee8 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -5610,8 +5610,8 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev) pm_runtime_enable(dev); if (info->pll_clks) - samsung_clk_register_pll(ctx, info->pll_clks, info->nr_pll_clks, - reg_base); + samsung_clk_register_pll(ctx, info->pll_clks, + info->nr_pll_clks); if (info->mux_clks) samsung_clk_register_mux(ctx, info->mux_clks, info->nr_mux_clks); diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c index df7812371d70..5ceac4c25c1c 100644 --- a/drivers/clk/samsung/clk-pll.c +++ b/drivers/clk/samsung/clk-pll.c @@ -1259,8 +1259,7 @@ static const struct clk_ops samsung_pll2650xx_clk_min_ops = { }; static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, - const struct samsung_pll_clock *pll_clk, - void __iomem *base) + const struct samsung_pll_clock *pll_clk) { struct samsung_clk_pll *pll; struct clk_init_data init; @@ -1395,8 +1394,8 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, pll->hw.init = &init; pll->type = pll_clk->type; - pll->lock_reg = base + pll_clk->lock_offset; - pll->con_reg = base + pll_clk->con_offset; + pll->lock_reg = ctx->reg_base + pll_clk->lock_offset; + pll->con_reg = ctx->reg_base + pll_clk->con_offset; ret = clk_hw_register(ctx->dev, &pll->hw); if (ret) { @@ -1412,10 +1411,10 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, void __init samsung_clk_register_pll(struct samsung_clk_provider *ctx, const struct samsung_pll_clock *pll_list, - unsigned int nr_pll, void __iomem *base) + unsigned int nr_pll) { int cnt; for (cnt = 0; cnt < nr_pll; cnt++) - _samsung_clk_register_pll(ctx, &pll_list[cnt], base); + _samsung_clk_register_pll(ctx, &pll_list[cnt]); } diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c index 772f776572a1..47e9d19486dc 100644 --- a/drivers/clk/samsung/clk-s3c64xx.c +++ b/drivers/clk/samsung/clk-s3c64xx.c @@ -414,7 +414,7 @@ void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f, /* Register PLLs. */ samsung_clk_register_pll(ctx, s3c64xx_pll_clks, - ARRAY_SIZE(s3c64xx_pll_clks), reg_base); + ARRAY_SIZE(s3c64xx_pll_clks)); /* Register common internal clocks. */ samsung_clk_register_fixed_rate(ctx, s3c64xx_fixed_rate_clks, diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c index b3e9f775ffdb..b0ab6bc9d21d 100644 --- a/drivers/clk/samsung/clk-s5pv210.c +++ b/drivers/clk/samsung/clk-s5pv210.c @@ -753,7 +753,7 @@ static void __init __s5pv210_clk_init(struct device_node *np, samsung_clk_register_fixed_rate(ctx, s5p6442_frate_clks, ARRAY_SIZE(s5p6442_frate_clks)); samsung_clk_register_pll(ctx, s5p6442_pll_clks, - ARRAY_SIZE(s5p6442_pll_clks), reg_base); + ARRAY_SIZE(s5p6442_pll_clks)); samsung_clk_register_mux(ctx, s5p6442_mux_clks, ARRAY_SIZE(s5p6442_mux_clks)); samsung_clk_register_div(ctx, s5p6442_div_clks, @@ -764,7 +764,7 @@ static void __init __s5pv210_clk_init(struct device_node *np, samsung_clk_register_fixed_rate(ctx, s5pv210_frate_clks, ARRAY_SIZE(s5pv210_frate_clks)); samsung_clk_register_pll(ctx, s5pv210_pll_clks, - ARRAY_SIZE(s5pv210_pll_clks), reg_base); + ARRAY_SIZE(s5pv210_pll_clks)); samsung_clk_register_mux(ctx, s5pv210_mux_clks, ARRAY_SIZE(s5pv210_mux_clks)); samsung_clk_register_div(ctx, s5pv210_div_clks, diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c index c2758f4175a1..2436223aac1a 100644 --- a/drivers/clk/samsung/clk.c +++ b/drivers/clk/samsung/clk.c @@ -344,8 +344,7 @@ struct samsung_clk_provider * __init samsung_cmu_register_one( ctx = samsung_clk_init(reg_base, cmu->nr_clk_ids); if (cmu->pll_clks) - samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks, - reg_base); + samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks); if (cmu->mux_clks) samsung_clk_register_mux(ctx, cmu->mux_clks, cmu->nr_mux_clks); diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h index 475f1d28cca6..98753b0e5055 100644 --- a/drivers/clk/samsung/clk.h +++ b/drivers/clk/samsung/clk.h @@ -372,7 +372,7 @@ void samsung_clk_register_gate(struct samsung_clk_provider *ctx, unsigned int nr_clk); void samsung_clk_register_pll(struct samsung_clk_provider *ctx, const struct samsung_pll_clock *pll_list, - unsigned int nr_clk, void __iomem *base); + unsigned int nr_clk); void samsung_clk_register_cpu(struct samsung_clk_provider *ctx, const struct samsung_cpu_clock *list, unsigned int nr_clk); -- GitLab From a4c78367f62ae36aa3529029346788cc7f5e3073 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:19:35 -0600 Subject: [PATCH 0087/5631] clk: samsung: Set dev in samsung_clk_init() Some drivers set dev to context in order to implement PM. Make that part of samsung_clk_init() instead of assigning `ctx->dev = dev' separately. No functional change. Acked-by: Marek Szyprowski Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230223041938.22732-4-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos4.c | 2 +- drivers/clk/samsung/clk-exynos4412-isp.c | 3 +-- drivers/clk/samsung/clk-exynos5250.c | 2 +- drivers/clk/samsung/clk-exynos5420.c | 2 +- drivers/clk/samsung/clk-s3c64xx.c | 2 +- drivers/clk/samsung/clk-s5pv210.c | 2 +- drivers/clk/samsung/clk.c | 19 +++++++++++++++---- drivers/clk/samsung/clk.h | 5 +++-- 8 files changed, 24 insertions(+), 13 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index 7a9994144d72..d7dbb3858347 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -1251,7 +1251,7 @@ static void __init exynos4_clk_init(struct device_node *np, if (!reg_base) panic("%s: failed to map registers\n", __func__); - ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(NULL, reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos4_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-exynos4412-isp.c b/drivers/clk/samsung/clk-exynos4412-isp.c index 0b6390e04533..1470c15e95da 100644 --- a/drivers/clk/samsung/clk-exynos4412-isp.c +++ b/drivers/clk/samsung/clk-exynos4412-isp.c @@ -121,8 +121,7 @@ static int __init exynos4x12_isp_clk_probe(struct platform_device *pdev) if (!exynos4x12_save_isp) return -ENOMEM; - ctx = samsung_clk_init(reg_base, CLK_NR_ISP_CLKS); - ctx->dev = dev; + ctx = samsung_clk_init(dev, reg_base, CLK_NR_ISP_CLKS); platform_set_drvdata(pdev, ctx); diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c index f1cb69aea10e..92fb09922f28 100644 --- a/drivers/clk/samsung/clk-exynos5250.c +++ b/drivers/clk/samsung/clk-exynos5250.c @@ -797,7 +797,7 @@ static void __init exynos5250_clk_init(struct device_node *np) panic("%s: unable to determine soc\n", __func__); } - ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(NULL, reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos5250_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index 46cac4980be2..1e0cbf762408 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -1587,7 +1587,7 @@ static void __init exynos5x_clk_init(struct device_node *np, exynos5x_soc = soc; - ctx = samsung_clk_init(reg_base, CLK_NR_CLKS); + ctx = samsung_clk_init(NULL, reg_base, CLK_NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_of_register_fixed_ext(ctx, exynos5x_fixed_rate_ext_clks, diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c index 47e9d19486dc..d27a1f73f077 100644 --- a/drivers/clk/samsung/clk-s3c64xx.c +++ b/drivers/clk/samsung/clk-s3c64xx.c @@ -405,7 +405,7 @@ void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f, panic("%s: failed to map registers\n", __func__); } - ctx = samsung_clk_init(reg_base, NR_CLKS); + ctx = samsung_clk_init(NULL, reg_base, NR_CLKS); hws = ctx->clk_data.hws; /* Register external clocks. */ diff --git a/drivers/clk/samsung/clk-s5pv210.c b/drivers/clk/samsung/clk-s5pv210.c index b0ab6bc9d21d..cd85342e4ddb 100644 --- a/drivers/clk/samsung/clk-s5pv210.c +++ b/drivers/clk/samsung/clk-s5pv210.c @@ -743,7 +743,7 @@ static void __init __s5pv210_clk_init(struct device_node *np, struct samsung_clk_provider *ctx; struct clk_hw **hws; - ctx = samsung_clk_init(reg_base, NR_CLKS); + ctx = samsung_clk_init(NULL, reg_base, NR_CLKS); hws = ctx->clk_data.hws; samsung_clk_register_mux(ctx, early_mux_clks, diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c index 2436223aac1a..912dfbe5ac20 100644 --- a/drivers/clk/samsung/clk.c +++ b/drivers/clk/samsung/clk.c @@ -53,9 +53,19 @@ struct samsung_clk_reg_dump *samsung_clk_alloc_reg_dump( return rd; } -/* setup the essentials required to support clock lookup using ccf */ -struct samsung_clk_provider * __init samsung_clk_init(void __iomem *base, - unsigned long nr_clks) +/** + * samsung_clk_init() - Create and initialize a clock provider object + * @dev: CMU device to enable runtime PM, or NULL if RPM is not needed + * @base: Start address (mapped) of CMU registers + * @nr_clks: Total clock count to allocate in clock provider object + * + * Setup the essentials required to support clock lookup using Common Clock + * Framework. + * + * Return: Allocated and initialized clock provider object. + */ +struct samsung_clk_provider * __init samsung_clk_init(struct device *dev, + void __iomem *base, unsigned long nr_clks) { struct samsung_clk_provider *ctx; int i; @@ -67,6 +77,7 @@ struct samsung_clk_provider * __init samsung_clk_init(void __iomem *base, for (i = 0; i < nr_clks; ++i) ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); + ctx->dev = dev; ctx->reg_base = base; ctx->clk_data.num = nr_clks; spin_lock_init(&ctx->lock); @@ -341,7 +352,7 @@ struct samsung_clk_provider * __init samsung_cmu_register_one( return NULL; } - ctx = samsung_clk_init(reg_base, cmu->nr_clk_ids); + ctx = samsung_clk_init(NULL, reg_base, cmu->nr_clk_ids); if (cmu->pll_clks) samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks); diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h index 98753b0e5055..3fd6c0868921 100644 --- a/drivers/clk/samsung/clk.h +++ b/drivers/clk/samsung/clk.h @@ -16,6 +16,7 @@ /** * struct samsung_clk_provider: information about clock provider * @reg_base: virtual address for the register base. + * @dev: clock provider device needed for runtime PM. * @lock: maintains exclusion between callbacks for a given clock-provider. * @clk_data: holds clock related data like clk_hw* and number of clocks. */ @@ -337,8 +338,8 @@ struct samsung_cmu_info { const char *clk_name; }; -struct samsung_clk_provider *samsung_clk_init(void __iomem *base, - unsigned long nr_clks); +struct samsung_clk_provider *samsung_clk_init(struct device *dev, + void __iomem *base, unsigned long nr_clks); void samsung_clk_of_add_provider(struct device_node *np, struct samsung_clk_provider *ctx); void samsung_clk_of_register_fixed_ext( -- GitLab From f2819ea168ef6a66c6b91fc30ce659a030268add Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:21:30 -0600 Subject: [PATCH 0088/5631] clk: samsung: clk-pll: Implement pll0818x PLL type pll0818x PLL is used in Exynos850 SoC for CMU_G3D PLL. Operation-wise, pll0818x is the same as pll0822x. The only difference is: - pl0822x is integer PLL with Middle FVCO (950 to 2400 MHz) - pl0818x is integer PLL with Low FVCO (600 to 1200 MHz) Add pll0818x type as an alias to pll0822x. Reviewed-by: Chanho Park Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230223042133.26551-4-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-pll.c | 1 + drivers/clk/samsung/clk-pll.h | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c index 5ceac4c25c1c..74934c6182ce 100644 --- a/drivers/clk/samsung/clk-pll.c +++ b/drivers/clk/samsung/clk-pll.c @@ -1314,6 +1314,7 @@ static void __init _samsung_clk_register_pll(struct samsung_clk_provider *ctx, init.ops = &samsung_pll35xx_clk_ops; break; case pll_1417x: + case pll_0818x: case pll_0822x: pll->enable_offs = PLL0822X_ENABLE_SHIFT; pll->lock_offs = PLL0822X_LOCK_STAT_SHIFT; diff --git a/drivers/clk/samsung/clk-pll.h b/drivers/clk/samsung/clk-pll.h index 5d5a58d40e7e..0725d485c6ee 100644 --- a/drivers/clk/samsung/clk-pll.h +++ b/drivers/clk/samsung/clk-pll.h @@ -34,6 +34,7 @@ enum samsung_pll_type { pll_1451x, pll_1452x, pll_1460x, + pll_0818x, pll_0822x, pll_0831x, pll_142xx, -- GitLab From e145c7650728cad74f18328478777849a5e5e1de Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:21:31 -0600 Subject: [PATCH 0089/5631] clk: samsung: exynos850: Implement CMU_G3D domain CMU_G3D clock domain provides clocks for Mali-G52 GPU and bus clocks for BLK_G3D. This patch adds next clocks: - bus clocks in CMU_TOP for CMU_G3D - all internal CMU_G3D clocks - leaf clocks for GPU, TZPC (TrustZone Protection Controller) and SysReg G3D_CMU_G3D clock was marked as CLK_IGNORE_UNUSED, as system hangs on boot otherwise. Reviewed-by: Chanho Park Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230223042133.26551-5-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos850.c | 120 ++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index 541761e96aeb..601fe05e8555 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -36,6 +36,7 @@ #define CLK_CON_MUX_MUX_CLKCMU_CORE_MMC_EMBD 0x101c #define CLK_CON_MUX_MUX_CLKCMU_CORE_SSS 0x1020 #define CLK_CON_MUX_MUX_CLKCMU_DPU 0x1034 +#define CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH 0x1038 #define CLK_CON_MUX_MUX_CLKCMU_HSI_BUS 0x103c #define CLK_CON_MUX_MUX_CLKCMU_HSI_MMC_CARD 0x1040 #define CLK_CON_MUX_MUX_CLKCMU_HSI_USB20DRD 0x1044 @@ -57,6 +58,7 @@ #define CLK_CON_DIV_CLKCMU_CORE_MMC_EMBD 0x1828 #define CLK_CON_DIV_CLKCMU_CORE_SSS 0x182c #define CLK_CON_DIV_CLKCMU_DPU 0x1840 +#define CLK_CON_DIV_CLKCMU_G3D_SWITCH 0x1844 #define CLK_CON_DIV_CLKCMU_HSI_BUS 0x1848 #define CLK_CON_DIV_CLKCMU_HSI_MMC_CARD 0x184c #define CLK_CON_DIV_CLKCMU_HSI_USB20DRD 0x1850 @@ -84,6 +86,7 @@ #define CLK_CON_GAT_GATE_CLKCMU_CORE_MMC_EMBD 0x2024 #define CLK_CON_GAT_GATE_CLKCMU_CORE_SSS 0x2028 #define CLK_CON_GAT_GATE_CLKCMU_DPU 0x203c +#define CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH 0x2040 #define CLK_CON_GAT_GATE_CLKCMU_HSI_BUS 0x2044 #define CLK_CON_GAT_GATE_CLKCMU_HSI_MMC_CARD 0x2048 #define CLK_CON_GAT_GATE_CLKCMU_HSI_USB20DRD 0x204c @@ -116,6 +119,7 @@ static const unsigned long top_clk_regs[] __initconst = { CLK_CON_MUX_MUX_CLKCMU_CORE_MMC_EMBD, CLK_CON_MUX_MUX_CLKCMU_CORE_SSS, CLK_CON_MUX_MUX_CLKCMU_DPU, + CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH, CLK_CON_MUX_MUX_CLKCMU_HSI_BUS, CLK_CON_MUX_MUX_CLKCMU_HSI_MMC_CARD, CLK_CON_MUX_MUX_CLKCMU_HSI_USB20DRD, @@ -137,6 +141,7 @@ static const unsigned long top_clk_regs[] __initconst = { CLK_CON_DIV_CLKCMU_CORE_MMC_EMBD, CLK_CON_DIV_CLKCMU_CORE_SSS, CLK_CON_DIV_CLKCMU_DPU, + CLK_CON_DIV_CLKCMU_G3D_SWITCH, CLK_CON_DIV_CLKCMU_HSI_BUS, CLK_CON_DIV_CLKCMU_HSI_MMC_CARD, CLK_CON_DIV_CLKCMU_HSI_USB20DRD, @@ -164,6 +169,7 @@ static const unsigned long top_clk_regs[] __initconst = { CLK_CON_GAT_GATE_CLKCMU_CORE_MMC_EMBD, CLK_CON_GAT_GATE_CLKCMU_CORE_SSS, CLK_CON_GAT_GATE_CLKCMU_DPU, + CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH, CLK_CON_GAT_GATE_CLKCMU_HSI_BUS, CLK_CON_GAT_GATE_CLKCMU_HSI_MMC_CARD, CLK_CON_GAT_GATE_CLKCMU_HSI_USB20DRD, @@ -216,6 +222,9 @@ PNAME(mout_core_mmc_embd_p) = { "oscclk", "dout_shared0_div2", "oscclk", "oscclk" }; PNAME(mout_core_sss_p) = { "dout_shared0_div3", "dout_shared1_div3", "dout_shared0_div4", "dout_shared1_div4" }; +/* List of parent clocks for Muxes in CMU_TOP: for CMU_G3D */ +PNAME(mout_g3d_switch_p) = { "dout_shared0_div2", "dout_shared1_div2", + "dout_shared0_div3", "dout_shared1_div3" }; /* List of parent clocks for Muxes in CMU_TOP: for CMU_HSI */ PNAME(mout_hsi_bus_p) = { "dout_shared0_div2", "dout_shared1_div2" }; PNAME(mout_hsi_mmc_card_p) = { "oscclk", "dout_shared0_div2", @@ -283,6 +292,10 @@ static const struct samsung_mux_clock top_mux_clks[] __initconst = { MUX(CLK_MOUT_DPU, "mout_dpu", mout_dpu_p, CLK_CON_MUX_MUX_CLKCMU_DPU, 0, 2), + /* G3D */ + MUX(CLK_MOUT_G3D_SWITCH, "mout_g3d_switch", mout_g3d_switch_p, + CLK_CON_MUX_MUX_CLKCMU_G3D_SWITCH, 0, 2), + /* HSI */ MUX(CLK_MOUT_HSI_BUS, "mout_hsi_bus", mout_hsi_bus_p, CLK_CON_MUX_MUX_CLKCMU_HSI_BUS, 0, 1), @@ -357,6 +370,10 @@ static const struct samsung_div_clock top_div_clks[] __initconst = { DIV(CLK_DOUT_DPU, "dout_dpu", "gout_dpu", CLK_CON_DIV_CLKCMU_DPU, 0, 4), + /* G3D */ + DIV(CLK_DOUT_G3D_SWITCH, "dout_g3d_switch", "gout_g3d_switch", + CLK_CON_DIV_CLKCMU_G3D_SWITCH, 0, 3), + /* HSI */ DIV(CLK_DOUT_HSI_BUS, "dout_hsi_bus", "gout_hsi_bus", CLK_CON_DIV_CLKCMU_HSI_BUS, 0, 4), @@ -417,6 +434,10 @@ static const struct samsung_gate_clock top_gate_clks[] __initconst = { GATE(CLK_GOUT_DPU, "gout_dpu", "mout_dpu", CLK_CON_GAT_GATE_CLKCMU_DPU, 21, 0, 0), + /* G3D */ + GATE(CLK_GOUT_G3D_SWITCH, "gout_g3d_switch", "mout_g3d_switch", + CLK_CON_GAT_GATE_CLKCMU_G3D_SWITCH, 21, 0, 0), + /* HSI */ GATE(CLK_GOUT_HSI_BUS, "gout_hsi_bus", "mout_hsi_bus", CLK_CON_GAT_GATE_CLKCMU_HSI_BUS, 21, 0, 0), @@ -992,6 +1013,102 @@ static const struct samsung_cmu_info cmgp_cmu_info __initconst = { .clk_name = "gout_clkcmu_cmgp_bus", }; +/* ---- CMU_G3D ------------------------------------------------------------- */ + +/* Register Offset definitions for CMU_G3D (0x11400000) */ +#define PLL_LOCKTIME_PLL_G3D 0x0000 +#define PLL_CON0_PLL_G3D 0x0100 +#define PLL_CON3_PLL_G3D 0x010c +#define PLL_CON0_MUX_CLKCMU_G3D_SWITCH_USER 0x0600 +#define CLK_CON_MUX_MUX_CLK_G3D_BUSD 0x1000 +#define CLK_CON_DIV_DIV_CLK_G3D_BUSP 0x1804 +#define CLK_CON_GAT_CLK_G3D_CMU_G3D_PCLK 0x2000 +#define CLK_CON_GAT_CLK_G3D_GPU_CLK 0x2004 +#define CLK_CON_GAT_GOUT_G3D_TZPC_PCLK 0x200c +#define CLK_CON_GAT_GOUT_G3D_GRAY2BIN_CLK 0x2010 +#define CLK_CON_GAT_GOUT_G3D_BUSD_CLK 0x2024 +#define CLK_CON_GAT_GOUT_G3D_BUSP_CLK 0x2028 +#define CLK_CON_GAT_GOUT_G3D_SYSREG_PCLK 0x202c + +static const unsigned long g3d_clk_regs[] __initconst = { + PLL_LOCKTIME_PLL_G3D, + PLL_CON0_PLL_G3D, + PLL_CON3_PLL_G3D, + PLL_CON0_MUX_CLKCMU_G3D_SWITCH_USER, + CLK_CON_MUX_MUX_CLK_G3D_BUSD, + CLK_CON_DIV_DIV_CLK_G3D_BUSP, + CLK_CON_GAT_CLK_G3D_CMU_G3D_PCLK, + CLK_CON_GAT_CLK_G3D_GPU_CLK, + CLK_CON_GAT_GOUT_G3D_TZPC_PCLK, + CLK_CON_GAT_GOUT_G3D_GRAY2BIN_CLK, + CLK_CON_GAT_GOUT_G3D_BUSD_CLK, + CLK_CON_GAT_GOUT_G3D_BUSP_CLK, + CLK_CON_GAT_GOUT_G3D_SYSREG_PCLK, +}; + +/* List of parent clocks for Muxes in CMU_G3D */ +PNAME(mout_g3d_pll_p) = { "oscclk", "fout_g3d_pll" }; +PNAME(mout_g3d_switch_user_p) = { "oscclk", "dout_g3d_switch" }; +PNAME(mout_g3d_busd_p) = { "mout_g3d_pll", "mout_g3d_switch_user" }; + +/* + * Do not provide PLL table to PLL_G3D, as MANUAL_PLL_CTRL bit is not set + * for that PLL by default, so set_rate operation would fail. + */ +static const struct samsung_pll_clock g3d_pll_clks[] __initconst = { + PLL(pll_0818x, CLK_FOUT_G3D_PLL, "fout_g3d_pll", "oscclk", + PLL_LOCKTIME_PLL_G3D, PLL_CON3_PLL_G3D, NULL), +}; + +static const struct samsung_mux_clock g3d_mux_clks[] __initconst = { + MUX(CLK_MOUT_G3D_PLL, "mout_g3d_pll", mout_g3d_pll_p, + PLL_CON0_PLL_G3D, 4, 1), + MUX(CLK_MOUT_G3D_SWITCH_USER, "mout_g3d_switch_user", + mout_g3d_switch_user_p, + PLL_CON0_MUX_CLKCMU_G3D_SWITCH_USER, 4, 1), + MUX(CLK_MOUT_G3D_BUSD, "mout_g3d_busd", mout_g3d_busd_p, + CLK_CON_MUX_MUX_CLK_G3D_BUSD, 0, 1), +}; + +static const struct samsung_div_clock g3d_div_clks[] __initconst = { + DIV(CLK_DOUT_G3D_BUSP, "dout_g3d_busp", "mout_g3d_busd", + CLK_CON_DIV_DIV_CLK_G3D_BUSP, 0, 3), +}; + +static const struct samsung_gate_clock g3d_gate_clks[] __initconst = { + GATE(CLK_GOUT_G3D_CMU_G3D_PCLK, "gout_g3d_cmu_g3d_pclk", + "dout_g3d_busp", + CLK_CON_GAT_CLK_G3D_CMU_G3D_PCLK, 21, CLK_IGNORE_UNUSED, 0), + GATE(CLK_GOUT_G3D_GPU_CLK, "gout_g3d_gpu_clk", "mout_g3d_busd", + CLK_CON_GAT_CLK_G3D_GPU_CLK, 21, 0, 0), + GATE(CLK_GOUT_G3D_TZPC_PCLK, "gout_g3d_tzpc_pclk", "dout_g3d_busp", + CLK_CON_GAT_GOUT_G3D_TZPC_PCLK, 21, 0, 0), + GATE(CLK_GOUT_G3D_GRAY2BIN_CLK, "gout_g3d_gray2bin_clk", + "mout_g3d_busd", + CLK_CON_GAT_GOUT_G3D_GRAY2BIN_CLK, 21, 0, 0), + GATE(CLK_GOUT_G3D_BUSD_CLK, "gout_g3d_busd_clk", "mout_g3d_busd", + CLK_CON_GAT_GOUT_G3D_BUSD_CLK, 21, 0, 0), + GATE(CLK_GOUT_G3D_BUSP_CLK, "gout_g3d_busp_clk", "dout_g3d_busp", + CLK_CON_GAT_GOUT_G3D_BUSP_CLK, 21, 0, 0), + GATE(CLK_GOUT_G3D_SYSREG_PCLK, "gout_g3d_sysreg_pclk", "dout_g3d_busp", + CLK_CON_GAT_GOUT_G3D_SYSREG_PCLK, 21, 0, 0), +}; + +static const struct samsung_cmu_info g3d_cmu_info __initconst = { + .pll_clks = g3d_pll_clks, + .nr_pll_clks = ARRAY_SIZE(g3d_pll_clks), + .mux_clks = g3d_mux_clks, + .nr_mux_clks = ARRAY_SIZE(g3d_mux_clks), + .div_clks = g3d_div_clks, + .nr_div_clks = ARRAY_SIZE(g3d_div_clks), + .gate_clks = g3d_gate_clks, + .nr_gate_clks = ARRAY_SIZE(g3d_gate_clks), + .nr_clk_ids = G3D_NR_CLK, + .clk_regs = g3d_clk_regs, + .nr_clk_regs = ARRAY_SIZE(g3d_clk_regs), + .clk_name = "dout_g3d_switch", +}; + /* ---- CMU_HSI ------------------------------------------------------------- */ /* Register Offset definitions for CMU_HSI (0x13400000) */ @@ -1700,6 +1817,9 @@ static const struct of_device_id exynos850_cmu_of_match[] = { }, { .compatible = "samsung,exynos850-cmu-cmgp", .data = &cmgp_cmu_info, + }, { + .compatible = "samsung,exynos850-cmu-g3d", + .data = &g3d_cmu_info, }, { .compatible = "samsung,exynos850-cmu-hsi", .data = &hsi_cmu_info, -- GitLab From 9a8ab39f7f8d32cf36dcd80cdaaec4998e834cf5 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 22 Feb 2023 22:21:32 -0600 Subject: [PATCH 0090/5631] clk: samsung: exynos850: Add AUD and HSI main gate clocks Add main gate clocks for controlling AUD and HSI CMUs: - gout_aud_cmu_aud_pclk - gout_hsi_cmu_hsi_pclk Those clocks were marked as CLK_IGNORE_UNUSED, as system hangs on boot otherwise. While at it, add missing PPMU (Performance Profiling Monitor Unit) clocks for CMU_HSI. Signed-off-by: Sam Protsenko Reviewed-by: Chanho Park Link: https://lore.kernel.org/r/20230223042133.26551-6-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos850.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index 601fe05e8555..6ab5fa8c2ef3 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -674,6 +674,7 @@ static const struct samsung_cmu_info apm_cmu_info __initconst = { #define CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF4 0x2014 #define CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF5 0x2018 #define CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF6 0x201c +#define CLK_CON_GAT_CLK_AUD_CMU_AUD_PCLK 0x2020 #define CLK_CON_GAT_GOUT_AUD_ABOX_ACLK 0x2048 #define CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_SPDY 0x204c #define CLK_CON_GAT_GOUT_AUD_ABOX_CCLK_ASB 0x2050 @@ -729,6 +730,7 @@ static const unsigned long aud_clk_regs[] __initconst = { CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF4, CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF5, CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_UAIF6, + CLK_CON_GAT_CLK_AUD_CMU_AUD_PCLK, CLK_CON_GAT_GOUT_AUD_ABOX_ACLK, CLK_CON_GAT_GOUT_AUD_ABOX_BCLK_SPDY, CLK_CON_GAT_GOUT_AUD_ABOX_CCLK_ASB, @@ -848,6 +850,9 @@ static const struct samsung_div_clock aud_div_clks[] __initconst = { }; static const struct samsung_gate_clock aud_gate_clks[] __initconst = { + GATE(CLK_GOUT_AUD_CMU_AUD_PCLK, "gout_aud_cmu_aud_pclk", + "dout_aud_busd", + CLK_CON_GAT_CLK_AUD_CMU_AUD_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_AUD_CA32_CCLK, "gout_aud_ca32_cclk", "mout_aud_cpu_hch", CLK_CON_GAT_GOUT_AUD_ABOX_CCLK_CA32, 21, 0, 0), GATE(CLK_GOUT_AUD_ASB_CCLK, "gout_aud_asb_cclk", "dout_aud_cpu_aclk", @@ -1116,12 +1121,15 @@ static const struct samsung_cmu_info g3d_cmu_info __initconst = { #define PLL_CON0_MUX_CLKCMU_HSI_MMC_CARD_USER 0x0610 #define PLL_CON0_MUX_CLKCMU_HSI_USB20DRD_USER 0x0620 #define CLK_CON_MUX_MUX_CLK_HSI_RTC 0x1000 +#define CLK_CON_GAT_CLK_HSI_CMU_HSI_PCLK 0x2000 #define CLK_CON_GAT_HSI_USB20DRD_TOP_I_RTC_CLK__ALV 0x2008 #define CLK_CON_GAT_HSI_USB20DRD_TOP_I_REF_CLK_50 0x200c #define CLK_CON_GAT_HSI_USB20DRD_TOP_I_PHY_REFCLK_26 0x2010 #define CLK_CON_GAT_GOUT_HSI_GPIO_HSI_PCLK 0x2018 #define CLK_CON_GAT_GOUT_HSI_MMC_CARD_I_ACLK 0x2024 #define CLK_CON_GAT_GOUT_HSI_MMC_CARD_SDCLKIN 0x2028 +#define CLK_CON_GAT_GOUT_HSI_PPMU_ACLK 0x202c +#define CLK_CON_GAT_GOUT_HSI_PPMU_PCLK 0x2030 #define CLK_CON_GAT_GOUT_HSI_SYSREG_HSI_PCLK 0x2038 #define CLK_CON_GAT_GOUT_HSI_USB20DRD_TOP_ACLK_PHYCTRL_20 0x203c #define CLK_CON_GAT_GOUT_HSI_USB20DRD_TOP_BUS_CLK_EARLY 0x2040 @@ -1131,12 +1139,15 @@ static const unsigned long hsi_clk_regs[] __initconst = { PLL_CON0_MUX_CLKCMU_HSI_MMC_CARD_USER, PLL_CON0_MUX_CLKCMU_HSI_USB20DRD_USER, CLK_CON_MUX_MUX_CLK_HSI_RTC, + CLK_CON_GAT_CLK_HSI_CMU_HSI_PCLK, CLK_CON_GAT_HSI_USB20DRD_TOP_I_RTC_CLK__ALV, CLK_CON_GAT_HSI_USB20DRD_TOP_I_REF_CLK_50, CLK_CON_GAT_HSI_USB20DRD_TOP_I_PHY_REFCLK_26, CLK_CON_GAT_GOUT_HSI_GPIO_HSI_PCLK, CLK_CON_GAT_GOUT_HSI_MMC_CARD_I_ACLK, CLK_CON_GAT_GOUT_HSI_MMC_CARD_SDCLKIN, + CLK_CON_GAT_GOUT_HSI_PPMU_ACLK, + CLK_CON_GAT_GOUT_HSI_PPMU_PCLK, CLK_CON_GAT_GOUT_HSI_SYSREG_HSI_PCLK, CLK_CON_GAT_GOUT_HSI_USB20DRD_TOP_ACLK_PHYCTRL_20, CLK_CON_GAT_GOUT_HSI_USB20DRD_TOP_BUS_CLK_EARLY, @@ -1162,6 +1173,10 @@ static const struct samsung_mux_clock hsi_mux_clks[] __initconst = { }; static const struct samsung_gate_clock hsi_gate_clks[] __initconst = { + /* TODO: Should be enabled in corresponding driver */ + GATE(CLK_GOUT_HSI_CMU_HSI_PCLK, "gout_hsi_cmu_hsi_pclk", + "mout_hsi_bus_user", + CLK_CON_GAT_CLK_HSI_CMU_HSI_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_USB_RTC_CLK, "gout_usb_rtc", "mout_hsi_rtc", CLK_CON_GAT_HSI_USB20DRD_TOP_I_RTC_CLK__ALV, 21, 0, 0), GATE(CLK_GOUT_USB_REF_CLK, "gout_usb_ref", "mout_hsi_usb20drd_user", @@ -1176,6 +1191,10 @@ static const struct samsung_gate_clock hsi_gate_clks[] __initconst = { GATE(CLK_GOUT_MMC_CARD_SDCLKIN, "gout_mmc_card_sdclkin", "mout_hsi_mmc_card_user", CLK_CON_GAT_GOUT_HSI_MMC_CARD_SDCLKIN, 21, CLK_SET_RATE_PARENT, 0), + GATE(CLK_GOUT_HSI_PPMU_ACLK, "gout_hsi_ppmu_aclk", "mout_hsi_bus_user", + CLK_CON_GAT_GOUT_HSI_PPMU_ACLK, 21, 0, 0), + GATE(CLK_GOUT_HSI_PPMU_PCLK, "gout_hsi_ppmu_pclk", "mout_hsi_bus_user", + CLK_CON_GAT_GOUT_HSI_PPMU_PCLK, 21, 0, 0), GATE(CLK_GOUT_SYSREG_HSI_PCLK, "gout_sysreg_hsi_pclk", "mout_hsi_bus_user", CLK_CON_GAT_GOUT_HSI_SYSREG_HSI_PCLK, 21, 0, 0), -- GitLab From 7e626a080bb2db47c27c29fea569ff18afec52ed Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 2 Mar 2023 21:50:28 +0100 Subject: [PATCH 0091/5631] clk: visconti: remove unused visconti_pll_provider::regmap Field regmap of struct visconti_pll_provider is never used. Remove it. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230302205028.2539197-1-dario.binacchi@amarulasolutions.com Acked-by: Nobuhiro Iwamatsu Signed-off-by: Stephen Boyd --- drivers/clk/visconti/pll.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/visconti/pll.h b/drivers/clk/visconti/pll.h index 16dae35ab370..01d07f1bf01b 100644 --- a/drivers/clk/visconti/pll.h +++ b/drivers/clk/visconti/pll.h @@ -15,7 +15,6 @@ struct visconti_pll_provider { void __iomem *reg_base; - struct regmap *regmap; struct clk_hw_onecell_data clk_data; struct device_node *node; }; -- GitLab From 1bd8e27fd0db0fe7f489213836dcbab92934f8fa Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Mon, 27 Feb 2023 12:59:31 +0200 Subject: [PATCH 0092/5631] clk: at91: clk-sam9x60-pll: fix return value check sam9x60_frac_pll_compute_mul_frac() can't return zero. Remove the check against zero to reflect this. Fixes: 43b1bb4a9b3e ("clk: at91: clk-sam9x60-pll: re-factor to support plls with multiple outputs") Reported-by: Dan Carpenter Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230227105931.2812412-1-claudiu.beznea@microchip.com Signed-off-by: Stephen Boyd --- drivers/clk/at91/clk-sam9x60-pll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c index d757003004cb..0882ed01d5c2 100644 --- a/drivers/clk/at91/clk-sam9x60-pll.c +++ b/drivers/clk/at91/clk-sam9x60-pll.c @@ -668,7 +668,7 @@ sam9x60_clk_register_frac_pll(struct regmap *regmap, spinlock_t *lock, ret = sam9x60_frac_pll_compute_mul_frac(&frac->core, FCORE_MIN, parent_rate, true); - if (ret <= 0) { + if (ret < 0) { hw = ERR_PTR(ret); goto free; } -- GitLab From f0dd78de23539397e5f004fe6c41d3d45b36c7cf Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:29 +0800 Subject: [PATCH 0093/5631] clk: ast2600: allow empty entries in aspeed_g6_gates We're about to remove an entry from aspeed_g6_gates, but we won't want to alter/reorder existing entries. Allow empty entries in this array. Reviewed-by: Joel Stanley Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-2-jk@codeconstruct.com.au Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- drivers/clk/clk-ast2600.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 9c3305bcb27a..1f08ff3c60fa 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -652,6 +652,9 @@ static int aspeed_g6_clk_probe(struct platform_device *pdev) const struct aspeed_gate_data *gd = &aspeed_g6_gates[i]; u32 gate_flags; + if (!gd->name) + continue; + /* * Special case: the USB port 1 clock (bit 14) is always * working the opposite way from the other ones. -- GitLab From 1038b6978b438d954e2e827d4d553bed94cd83e0 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:30 +0800 Subject: [PATCH 0094/5631] dt-bindings: clock: ast2600: Add top-level I3C clock The ast2600 hardware has a top-level clock for all i3c controller peripherals (then gated to each individual controller), so add a top-level i3c clock line to control this. This is a partial cherry-pick and rework of ed44b8cdfdb and 1a35eb926d7 from Aspeed's own tree, originally by Dylan Hung . Acked-by: Krzysztof Kozlowski Reviewed-by: Joel Stanley Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-3-jk@codeconstruct.com.au Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/ast2600-clock.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/dt-bindings/clock/ast2600-clock.h b/include/dt-bindings/clock/ast2600-clock.h index d8b0db2f7a7d..dd1581bfdf58 100644 --- a/include/dt-bindings/clock/ast2600-clock.h +++ b/include/dt-bindings/clock/ast2600-clock.h @@ -87,6 +87,7 @@ #define ASPEED_CLK_MAC2RCLK 68 #define ASPEED_CLK_MAC3RCLK 69 #define ASPEED_CLK_MAC4RCLK 70 +#define ASPEED_CLK_I3C 71 /* Only list resets here that are not part of a gate */ #define ASPEED_RESET_ADC 55 -- GitLab From e9d230146f1521d24b286b75dfec96a66caf359b Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:31 +0800 Subject: [PATCH 0095/5631] clk: ast2600: Add full configs for I3C clocks The current ast2600 I3C clock definitions are top-level (rather than based on their actual hw sources: either HCLK or APLL), and include a couple of definitions for (non-existent) i3c6 and i3c7. Re-parent the individual I3C controller clocks to the main i3c clock, explicitly sourced from the APLL rather than whatever G6_CLK_SELECTION5 was last set to. While we're at it, remove the definitions for the i3c6 and i3c7 clock lines; this hardware isn't present. This is a partial cherry-pick and rework of ed44b8cdfdb and 1a35eb926d7 from Aspeed's own tree, originally by Dylan Hung . Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-4-jk@codeconstruct.com.au Reviewed-by: Joel Stanley Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- drivers/clk/clk-ast2600.c | 43 +++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 9 deletions(-) diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 1f08ff3c60fa..09f26ab5f9af 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -15,7 +15,11 @@ #include "clk-aspeed.h" -#define ASPEED_G6_NUM_CLKS 71 +/* + * This includes the gates (configured from aspeed_g6_gates), plus the + * explicitly-configured clocks (ASPEED_CLK_HPLL and up). + */ +#define ASPEED_G6_NUM_CLKS 72 #define ASPEED_G6_SILICON_REV 0x014 #define CHIP_REVISION_ID GENMASK(23, 16) @@ -32,6 +36,20 @@ #define ASPEED_G6_CLK_SELECTION1 0x300 #define ASPEED_G6_CLK_SELECTION2 0x304 #define ASPEED_G6_CLK_SELECTION4 0x310 +#define ASPEED_G6_CLK_SELECTION5 0x314 +#define I3C_CLK_SELECTION_SHIFT 31 +#define I3C_CLK_SELECTION BIT(31) +#define I3C_CLK_SELECT_HCLK (0 << I3C_CLK_SELECTION_SHIFT) +#define I3C_CLK_SELECT_APLL_DIV (1 << I3C_CLK_SELECTION_SHIFT) +#define APLL_DIV_SELECTION_SHIFT 28 +#define APLL_DIV_SELECTION GENMASK(30, 28) +#define APLL_DIV_2 (0b001 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_3 (0b010 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_4 (0b011 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_5 (0b100 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_6 (0b101 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_7 (0b110 << APLL_DIV_SELECTION_SHIFT) +#define APLL_DIV_8 (0b111 << APLL_DIV_SELECTION_SHIFT) #define ASPEED_HPLL_PARAM 0x200 #define ASPEED_APLL_PARAM 0x210 @@ -97,14 +115,13 @@ static const struct aspeed_gate_data aspeed_g6_gates[] = { [ASPEED_CLK_GATE_LHCCLK] = { 37, -1, "lhclk-gate", "lhclk", 0 }, /* LPC master/LPC+ */ /* Reserved 38 RSA: no longer used */ /* Reserved 39 */ - [ASPEED_CLK_GATE_I3C0CLK] = { 40, 40, "i3c0clk-gate", NULL, 0 }, /* I3C0 */ - [ASPEED_CLK_GATE_I3C1CLK] = { 41, 41, "i3c1clk-gate", NULL, 0 }, /* I3C1 */ - [ASPEED_CLK_GATE_I3C2CLK] = { 42, 42, "i3c2clk-gate", NULL, 0 }, /* I3C2 */ - [ASPEED_CLK_GATE_I3C3CLK] = { 43, 43, "i3c3clk-gate", NULL, 0 }, /* I3C3 */ - [ASPEED_CLK_GATE_I3C4CLK] = { 44, 44, "i3c4clk-gate", NULL, 0 }, /* I3C4 */ - [ASPEED_CLK_GATE_I3C5CLK] = { 45, 45, "i3c5clk-gate", NULL, 0 }, /* I3C5 */ - [ASPEED_CLK_GATE_I3C6CLK] = { 46, 46, "i3c6clk-gate", NULL, 0 }, /* I3C6 */ - [ASPEED_CLK_GATE_I3C7CLK] = { 47, 47, "i3c7clk-gate", NULL, 0 }, /* I3C7 */ + [ASPEED_CLK_GATE_I3C0CLK] = { 40, 40, "i3c0clk-gate", "i3cclk", 0 }, /* I3C0 */ + [ASPEED_CLK_GATE_I3C1CLK] = { 41, 41, "i3c1clk-gate", "i3cclk", 0 }, /* I3C1 */ + [ASPEED_CLK_GATE_I3C2CLK] = { 42, 42, "i3c2clk-gate", "i3cclk", 0 }, /* I3C2 */ + [ASPEED_CLK_GATE_I3C3CLK] = { 43, 43, "i3c3clk-gate", "i3cclk", 0 }, /* I3C3 */ + [ASPEED_CLK_GATE_I3C4CLK] = { 44, 44, "i3c4clk-gate", "i3cclk", 0 }, /* I3C4 */ + [ASPEED_CLK_GATE_I3C5CLK] = { 45, 45, "i3c5clk-gate", "i3cclk", 0 }, /* I3C5 */ + /* Reserved: 46 & 47 */ [ASPEED_CLK_GATE_UART1CLK] = { 48, -1, "uart1clk-gate", "uart", 0 }, /* UART1 */ [ASPEED_CLK_GATE_UART2CLK] = { 49, -1, "uart2clk-gate", "uart", 0 }, /* UART2 */ [ASPEED_CLK_GATE_UART3CLK] = { 50, -1, "uart3clk-gate", "uart", 0 }, /* UART3 */ @@ -775,6 +792,14 @@ static void __init aspeed_g6_cc(struct regmap *map) /* USB 2.0 port1 phy 40MHz clock */ hw = clk_hw_register_fixed_rate(NULL, "usb-phy-40m", NULL, 0, 40000000); aspeed_g6_clk_data->hws[ASPEED_CLK_USBPHY_40M] = hw; + + /* i3c clock: source from apll, divide by 8 */ + regmap_update_bits(map, ASPEED_G6_CLK_SELECTION5, + I3C_CLK_SELECTION | APLL_DIV_SELECTION, + I3C_CLK_SELECT_APLL_DIV | APLL_DIV_8); + + hw = clk_hw_register_fixed_factor(NULL, "i3cclk", "apll", 0, 1, 8); + aspeed_g6_clk_data->hws[ASPEED_CLK_I3C] = hw; }; static void __init aspeed_g6_cc_init(struct device_node *np) -- GitLab From 1f15e0486b6e29d7b327d3150215ddec31fca679 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:32 +0800 Subject: [PATCH 0096/5631] dt-bindings: clock: ast2600: remove IC36 & I3C7 clock definitions The current ast2600 clock definitions include entries for i3c6 and i3c7 devices, which don't exist: there are no clock control lines documented for these, and only i3c devices 0 through 5 are present. So, remove the definitions for I3C6 and I3C7. Although this is a potential ABI-breaking change, there are no in-tree users of these, and any references would be broken anyway, as the hardware doesn't exist. This is a partial cherry-pick and rework of ed44b8cdfdb and 1a35eb926d7 from Aspeed's own tree, originally by Dylan Hung . Reviewed-by: Joel Stanley Acked-by: Krzysztof Kozlowski Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-5-jk@codeconstruct.com.au Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/ast2600-clock.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/dt-bindings/clock/ast2600-clock.h b/include/dt-bindings/clock/ast2600-clock.h index dd1581bfdf58..b4d69103d722 100644 --- a/include/dt-bindings/clock/ast2600-clock.h +++ b/include/dt-bindings/clock/ast2600-clock.h @@ -57,8 +57,6 @@ #define ASPEED_CLK_GATE_I3C3CLK 40 #define ASPEED_CLK_GATE_I3C4CLK 41 #define ASPEED_CLK_GATE_I3C5CLK 42 -#define ASPEED_CLK_GATE_I3C6CLK 43 -#define ASPEED_CLK_GATE_I3C7CLK 44 #define ASPEED_CLK_GATE_FSICLK 45 -- GitLab From 1ef491e29cdb26ca60898bc2c853a944d7fe1117 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:33 +0800 Subject: [PATCH 0097/5631] clk: ast2600: Add comment about combined clock + reset handling Add a little description about how reset lines can be implicit with clock enable/disable. This is mostly based on the commit message from the original submission in 15ed8ce5f8. Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-6-jk@codeconstruct.com.au Reviewed-by: Joel Stanley Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- drivers/clk/clk-ast2600.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c index 09f26ab5f9af..a094a2601a37 100644 --- a/drivers/clk/clk-ast2600.c +++ b/drivers/clk/clk-ast2600.c @@ -73,6 +73,27 @@ static void __iomem *scu_g6_base; static u8 soc_rev; /* + * The majority of the clocks in the system are gates paired with a reset + * controller that holds the IP in reset; this is represented by the @reset_idx + * member of entries here. + * + * This borrows from clk_hw_register_gate, but registers two 'gates', one + * to control the clock enable register and the other to control the reset + * IP. This allows us to enforce the ordering: + * + * 1. Place IP in reset + * 2. Enable clock + * 3. Delay + * 4. Release reset + * + * Consequently, if reset_idx is set, reset control is implicit: the clock + * consumer does not need its own reset handling, as enabling the clock will + * also deassert reset. + * + * There are some gates that do not have an associated reset; these are + * handled by using -1 as the index for the reset, and the consumer must + * explictly assert/deassert reset lines as required. + * * Clocks marked with CLK_IS_CRITICAL: * * ref0 and ref1 are essential for the SoC to operate -- GitLab From ced8a02b3452291171e9988a3c862c56e1628a1d Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 2 Mar 2023 08:58:34 +0800 Subject: [PATCH 0098/5631] dt-bindings: clock: ast2600: Expand comment on reset definitions The current "not part of a gate" is a little ambiguous. Expand this a little to clarify the reference to the paired clock + reset control. Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230302005834.13171-7-jk@codeconstruct.com.au Reviewed-by: Joel Stanley Acked-by: Krzysztof Kozlowski Tested-by: Joel Stanley Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/ast2600-clock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/dt-bindings/clock/ast2600-clock.h b/include/dt-bindings/clock/ast2600-clock.h index b4d69103d722..e149eee61588 100644 --- a/include/dt-bindings/clock/ast2600-clock.h +++ b/include/dt-bindings/clock/ast2600-clock.h @@ -87,7 +87,7 @@ #define ASPEED_CLK_MAC4RCLK 70 #define ASPEED_CLK_I3C 71 -/* Only list resets here that are not part of a gate */ +/* Only list resets here that are not part of a clock gate + reset pair */ #define ASPEED_RESET_ADC 55 #define ASPEED_RESET_JTAG_MASTER2 54 #define ASPEED_RESET_I3C_DMA 39 -- GitLab From 1e8a0be5ed3aaa26dd77927df32bbd0df3449a1e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:35 -0800 Subject: [PATCH 0099/5631] alpha/cpu: Expose arch_cpu_idle_dead()'s prototype declaration Include to make sure arch_cpu_idle_dead() matches its prototype going forward. Link: https://lore.kernel.org/r/b0405c2ac5686303b6026e1ac27cfd769b21a7d0.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/alpha/kernel/process.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index e9cf7193eb81..3251102a9a47 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -9,6 +9,7 @@ * This file handles the architecture-dependent parts of process handling. */ +#include #include #include #include -- GitLab From 550db6795e9bb0b1b40f9c52bbe3d0ee735dbdb0 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:36 -0800 Subject: [PATCH 0100/5631] alpha/cpu: Make sure arch_cpu_idle_dead() doesn't return arch_cpu_idle_dead() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Link: https://lore.kernel.org/r/19ffef09a175fecb783abcd44d6bcfeade2857eb.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/alpha/kernel/process.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 3251102a9a47..a82fefa31bdb 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -63,6 +63,7 @@ void arch_cpu_idle(void) void arch_cpu_idle_dead(void) { wtint(INT_MAX); + BUG(); } #endif /* ALPHA_WTINT */ -- GitLab From b40c7d6d31ac2f6b78371cdc08bc1b6b62f01375 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 16 Feb 2023 10:38:55 -0800 Subject: [PATCH 0101/5631] arm/cpu: Add unreachable() to arch_cpu_idle_dead() arch_cpu_idle_dead() doesn't return. Make that visible to the compiler with an unreachable() code annotation. Link: https://lkml.kernel.org/r/20230216183851.s5bnvniomq44rytu@treble Signed-off-by: Josh Poimboeuf --- arch/arm/kernel/smp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 0b8c25763adc..441ea5cff390 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -382,6 +382,8 @@ void arch_cpu_idle_dead(void) : "r" (task_stack_page(current) + THREAD_SIZE - 8), "r" (current) : "r0"); + + unreachable(); } #endif /* CONFIG_HOTPLUG_CPU */ -- GitLab From 9bdc61ef27db5eaac48f1cc5deb8224603e79c89 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 16 Feb 2023 10:42:01 -0800 Subject: [PATCH 0102/5631] arm64/cpu: Mark cpu_die() __noreturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cpu_die() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Acked-by: Mark Rutland Reviewed-by: Philippe Mathieu-Daudé Link: https://lkml.kernel.org/r/20230216184157.4hup6y6mmspr2kll@treble Signed-off-by: Josh Poimboeuf --- arch/arm64/include/asm/smp.h | 2 +- arch/arm64/kernel/smp.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index fc55f5a57a06..5733a31bab08 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -100,7 +100,7 @@ static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask) extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); -extern void cpu_die(void); +extern void __noreturn cpu_die(void); extern void cpu_die_early(void); static inline void cpu_park_loop(void) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 4e8327264255..d5d09a18b4f8 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -361,7 +361,7 @@ void __cpu_die(unsigned int cpu) * Called from the idle thread for the CPU which has been shutdown. * */ -void cpu_die(void) +void __noreturn cpu_die(void) { unsigned int cpu = smp_processor_id(); const struct cpu_operations *ops = get_cpu_ops(cpu); -- GitLab From 1b2442a835a0acc7d76ae2f48ca7a94f962b29c8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:39 -0800 Subject: [PATCH 0103/5631] csky/cpu: Make sure arch_cpu_idle_dead() doesn't return arch_cpu_idle_dead() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Acked-by: Guo Ren Link: https://lore.kernel.org/r/1e9ecc3d248e82973e80bc336fc9f97e3ba2708d.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/csky/kernel/smp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b45d1073307f..0ec20efaf5fd 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -317,5 +317,7 @@ void arch_cpu_idle_dead(void) "jmpi csky_start_secondary" : : "r" (secondary_stack)); + + BUG(); } #endif -- GitLab From 93c0edffbc92abe1efb8c7081df0cc1577a79ace Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:40 -0800 Subject: [PATCH 0104/5631] ia64/cpu: Mark play_dead() __noreturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/7575bb38417bd8bcb5be980443f99cab29319342.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/ia64/kernel/process.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index f6195a0a00ae..78f5794b2dde 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -201,7 +201,7 @@ __setup("nohalt", nohalt_setup); #ifdef CONFIG_HOTPLUG_CPU /* We don't actually take CPU down, just spin without interrupts. */ -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { unsigned int this_cpu = smp_processor_id(); @@ -219,7 +219,7 @@ static inline void play_dead(void) BUG(); } #else -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { BUG(); } -- GitLab From 13bf7923a4dd34f3d2681768a148b10ddbdb95ed Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:41 -0800 Subject: [PATCH 0105/5631] loongarch/cpu: Make sure play_dead() doesn't return play_dead() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Link: https://lore.kernel.org/r/21245d687ffeda34dbcf04961a2df3724f04f7c8.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/loongarch/kernel/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 8c6e227cb29d..51f328169a7b 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -336,7 +336,7 @@ void play_dead(void) iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR); init_fn(); - unreachable(); + BUG(); } #endif -- GitLab From 6c0f2d071eded22cb72413e0abfaa5b3373b4d96 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:42 -0800 Subject: [PATCH 0106/5631] loongarch/cpu: Mark play_dead() __noreturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/4da55acfdec8a9132c4e21ffb7edb1f846841193.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/loongarch/include/asm/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index d82687390b4a..416b653bccb4 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -99,7 +99,7 @@ static inline void __cpu_die(unsigned int cpu) loongson_cpu_die(cpu); } -extern void play_dead(void); +extern void __noreturn play_dead(void); #endif #endif /* __ASM_SMP_H */ -- GitLab From bed76f697a9adda26c40ce4a064f371d54e71331 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Mon, 6 Mar 2023 18:24:21 -0600 Subject: [PATCH 0107/5631] clk: samsung: Extract clocks registration to common function It might be useful to have a separate clocks registration function, so it can be called from different users. Extract that common code from samsung_cmu_register_one() to samsung_cmu_register_clocks(). Also make that new function global as it's going to be used in other modules further. Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230307002423.24454-2-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk.c | 46 ++++++++++++++++++++++++--------------- drivers/clk/samsung/clk.h | 2 ++ 2 files changed, 30 insertions(+), 18 deletions(-) diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c index 912dfbe5ac20..b6701905f254 100644 --- a/drivers/clk/samsung/clk.c +++ b/drivers/clk/samsung/clk.c @@ -335,6 +335,33 @@ void samsung_clk_extended_sleep_init(void __iomem *reg_base, } #endif +/** + * samsung_cmu_register_clocks() - Register all clocks provided in CMU object + * @ctx: Clock provider object + * @cmu: CMU object with clocks to register + */ +void __init samsung_cmu_register_clocks(struct samsung_clk_provider *ctx, + const struct samsung_cmu_info *cmu) +{ + if (cmu->pll_clks) + samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks); + if (cmu->mux_clks) + samsung_clk_register_mux(ctx, cmu->mux_clks, cmu->nr_mux_clks); + if (cmu->div_clks) + samsung_clk_register_div(ctx, cmu->div_clks, cmu->nr_div_clks); + if (cmu->gate_clks) + samsung_clk_register_gate(ctx, cmu->gate_clks, + cmu->nr_gate_clks); + if (cmu->fixed_clks) + samsung_clk_register_fixed_rate(ctx, cmu->fixed_clks, + cmu->nr_fixed_clks); + if (cmu->fixed_factor_clks) + samsung_clk_register_fixed_factor(ctx, cmu->fixed_factor_clks, + cmu->nr_fixed_factor_clks); + if (cmu->cpu_clks) + samsung_clk_register_cpu(ctx, cmu->cpu_clks, cmu->nr_cpu_clks); +} + /* * Common function which registers plls, muxes, dividers and gates * for each CMU. It also add CMU register list to register cache. @@ -353,29 +380,12 @@ struct samsung_clk_provider * __init samsung_cmu_register_one( } ctx = samsung_clk_init(NULL, reg_base, cmu->nr_clk_ids); + samsung_cmu_register_clocks(ctx, cmu); - if (cmu->pll_clks) - samsung_clk_register_pll(ctx, cmu->pll_clks, cmu->nr_pll_clks); - if (cmu->mux_clks) - samsung_clk_register_mux(ctx, cmu->mux_clks, - cmu->nr_mux_clks); - if (cmu->div_clks) - samsung_clk_register_div(ctx, cmu->div_clks, cmu->nr_div_clks); - if (cmu->gate_clks) - samsung_clk_register_gate(ctx, cmu->gate_clks, - cmu->nr_gate_clks); - if (cmu->fixed_clks) - samsung_clk_register_fixed_rate(ctx, cmu->fixed_clks, - cmu->nr_fixed_clks); - if (cmu->fixed_factor_clks) - samsung_clk_register_fixed_factor(ctx, cmu->fixed_factor_clks, - cmu->nr_fixed_factor_clks); if (cmu->clk_regs) samsung_clk_extended_sleep_init(reg_base, cmu->clk_regs, cmu->nr_clk_regs, cmu->suspend_regs, cmu->nr_suspend_regs); - if (cmu->cpu_clks) - samsung_clk_register_cpu(ctx, cmu->cpu_clks, cmu->nr_cpu_clks); samsung_clk_of_add_provider(np, ctx); diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h index 3fd6c0868921..ab9c3d7a25b3 100644 --- a/drivers/clk/samsung/clk.h +++ b/drivers/clk/samsung/clk.h @@ -377,6 +377,8 @@ void samsung_clk_register_pll(struct samsung_clk_provider *ctx, void samsung_clk_register_cpu(struct samsung_clk_provider *ctx, const struct samsung_cpu_clock *list, unsigned int nr_clk); +void samsung_cmu_register_clocks(struct samsung_clk_provider *ctx, + const struct samsung_cmu_info *cmu); struct samsung_clk_provider *samsung_cmu_register_one( struct device_node *, const struct samsung_cmu_info *); -- GitLab From 454e8d296ce4267ca1728bf4f6fe6d41eabe080e Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Mon, 6 Mar 2023 18:24:22 -0600 Subject: [PATCH 0108/5631] clk: samsung: Extract parent clock enabling to common function Extract parent clock enabling from exynos_arm64_register_cmu() to dedicated function. Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230307002423.24454-3-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos-arm64.c | 57 ++++++++++++++++++-------- 1 file changed, 41 insertions(+), 16 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos-arm64.c b/drivers/clk/samsung/clk-exynos-arm64.c index b921b9a1134a..60fd820c14aa 100644 --- a/drivers/clk/samsung/clk-exynos-arm64.c +++ b/drivers/clk/samsung/clk-exynos-arm64.c @@ -56,6 +56,37 @@ static void __init exynos_arm64_init_clocks(struct device_node *np, iounmap(reg_base); } +/** + * exynos_arm64_enable_bus_clk - Enable parent clock of specified CMU + * + * @dev: Device object; may be NULL if this function is not being + * called from platform driver probe function + * @np: CMU device tree node + * @cmu: CMU data + * + * Keep CMU parent clock running (needed for CMU registers access). + * + * Return: 0 on success or a negative error code on failure. + */ +static int __init exynos_arm64_enable_bus_clk(struct device *dev, + struct device_node *np, const struct samsung_cmu_info *cmu) +{ + struct clk *parent_clk; + + if (!cmu->clk_name) + return 0; + + if (dev) + parent_clk = clk_get(dev, cmu->clk_name); + else + parent_clk = of_clk_get_by_name(np, cmu->clk_name); + + if (IS_ERR(parent_clk)) + return PTR_ERR(parent_clk); + + return clk_prepare_enable(parent_clk); +} + /** * exynos_arm64_register_cmu - Register specified Exynos CMU domain * @dev: Device object; may be NULL if this function is not being @@ -72,22 +103,16 @@ static void __init exynos_arm64_init_clocks(struct device_node *np, void __init exynos_arm64_register_cmu(struct device *dev, struct device_node *np, const struct samsung_cmu_info *cmu) { - /* Keep CMU parent clock running (needed for CMU registers access) */ - if (cmu->clk_name) { - struct clk *parent_clk; - - if (dev) - parent_clk = clk_get(dev, cmu->clk_name); - else - parent_clk = of_clk_get_by_name(np, cmu->clk_name); - - if (IS_ERR(parent_clk)) { - pr_err("%s: could not find bus clock %s; err = %ld\n", - __func__, cmu->clk_name, PTR_ERR(parent_clk)); - } else { - clk_prepare_enable(parent_clk); - } - } + int err; + + /* + * Try to boot even if the parent clock enablement fails, as it might be + * already enabled by bootloader. + */ + err = exynos_arm64_enable_bus_clk(dev, np, cmu); + if (err) + pr_err("%s: could not enable bus clock %s; err = %d\n", + __func__, cmu->clk_name, err); exynos_arm64_init_clocks(np, cmu->clk_regs, cmu->nr_clk_regs); samsung_cmu_register_one(np, cmu); -- GitLab From f05dc20243163d0218bbb258b6461681865cff5c Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Mon, 6 Mar 2023 18:24:23 -0600 Subject: [PATCH 0109/5631] clk: samsung: exynos5433: Extract PM support to common ARM64 layer Exynos5433 clock driver implements PM support internally, which might be also useful for other Exynos clock drivers. Extract all PM related code from clk-exynos5433 to common ARM64 functions. Tested-by: Marek Szyprowski Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230307002423.24454-4-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos-arm64.c | 176 ++++++++++++++++++++++++- drivers/clk/samsung/clk-exynos-arm64.h | 3 + drivers/clk/samsung/clk-exynos5433.c | 157 +--------------------- 3 files changed, 180 insertions(+), 156 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos-arm64.c b/drivers/clk/samsung/clk-exynos-arm64.c index 60fd820c14aa..7d8937caf22a 100644 --- a/drivers/clk/samsung/clk-exynos-arm64.c +++ b/drivers/clk/samsung/clk-exynos-arm64.c @@ -10,6 +10,9 @@ */ #include #include +#include +#include +#include #include "clk-exynos-arm64.h" @@ -21,6 +24,19 @@ #define GATE_OFF_START 0x2000 #define GATE_OFF_END 0x2fff +struct exynos_arm64_cmu_data { + struct samsung_clk_reg_dump *clk_save; + unsigned int nr_clk_save; + const struct samsung_clk_reg_dump *clk_suspend; + unsigned int nr_clk_suspend; + + struct clk *clk; + struct clk **pclks; + int nr_pclks; + + struct samsung_clk_provider *ctx; +}; + /** * exynos_arm64_init_clocks - Set clocks initial configuration * @np: CMU device tree node with "reg" property (CMU addr) @@ -76,10 +92,16 @@ static int __init exynos_arm64_enable_bus_clk(struct device *dev, if (!cmu->clk_name) return 0; - if (dev) + if (dev) { + struct exynos_arm64_cmu_data *data; + parent_clk = clk_get(dev, cmu->clk_name); - else + data = dev_get_drvdata(dev); + if (data) + data->clk = parent_clk; + } else { parent_clk = of_clk_get_by_name(np, cmu->clk_name); + } if (IS_ERR(parent_clk)) return PTR_ERR(parent_clk); @@ -87,6 +109,46 @@ static int __init exynos_arm64_enable_bus_clk(struct device *dev, return clk_prepare_enable(parent_clk); } +static int __init exynos_arm64_cmu_prepare_pm(struct device *dev, + const struct samsung_cmu_info *cmu) +{ + struct exynos_arm64_cmu_data *data = dev_get_drvdata(dev); + int i; + + data->clk_save = samsung_clk_alloc_reg_dump(cmu->clk_regs, + cmu->nr_clk_regs); + if (!data->clk_save) + return -ENOMEM; + + data->nr_clk_save = cmu->nr_clk_regs; + data->clk_suspend = cmu->suspend_regs; + data->nr_clk_suspend = cmu->nr_suspend_regs; + data->nr_pclks = of_clk_get_parent_count(dev->of_node); + if (!data->nr_pclks) + return 0; + + data->pclks = devm_kcalloc(dev, sizeof(struct clk *), data->nr_pclks, + GFP_KERNEL); + if (!data->pclks) { + kfree(data->clk_save); + return -ENOMEM; + } + + for (i = 0; i < data->nr_pclks; i++) { + struct clk *clk = of_clk_get(dev->of_node, i); + + if (IS_ERR(clk)) { + kfree(data->clk_save); + while (--i >= 0) + clk_put(data->pclks[i]); + return PTR_ERR(clk); + } + data->pclks[i] = clk; + } + + return 0; +} + /** * exynos_arm64_register_cmu - Register specified Exynos CMU domain * @dev: Device object; may be NULL if this function is not being @@ -117,3 +179,113 @@ void __init exynos_arm64_register_cmu(struct device *dev, exynos_arm64_init_clocks(np, cmu->clk_regs, cmu->nr_clk_regs); samsung_cmu_register_one(np, cmu); } + +/** + * exynos_arm64_register_cmu_pm - Register Exynos CMU domain with PM support + * + * @pdev: Platform device object + * @set_manual: If true, set gate clocks to manual mode + * + * It's a version of exynos_arm64_register_cmu() with PM support. Should be + * called from probe function of platform driver. + * + * Return: 0 on success, or negative error code on error. + */ +int __init exynos_arm64_register_cmu_pm(struct platform_device *pdev, + bool set_manual) +{ + const struct samsung_cmu_info *cmu; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct exynos_arm64_cmu_data *data; + void __iomem *reg_base; + int ret; + + cmu = of_device_get_match_data(dev); + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + platform_set_drvdata(pdev, data); + + ret = exynos_arm64_cmu_prepare_pm(dev, cmu); + if (ret) + return ret; + + /* + * Try to boot even if the parent clock enablement fails, as it might be + * already enabled by bootloader. + */ + ret = exynos_arm64_enable_bus_clk(dev, NULL, cmu); + if (ret) + dev_err(dev, "%s: could not enable bus clock %s; err = %d\n", + __func__, cmu->clk_name, ret); + + if (set_manual) + exynos_arm64_init_clocks(np, cmu->clk_regs, cmu->nr_clk_regs); + + reg_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(reg_base)) + return PTR_ERR(reg_base); + + data->ctx = samsung_clk_init(dev, reg_base, cmu->nr_clk_ids); + + /* + * Enable runtime PM here to allow the clock core using runtime PM + * for the registered clocks. Additionally, we increase the runtime + * PM usage count before registering the clocks, to prevent the + * clock core from runtime suspending the device. + */ + pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + pm_runtime_enable(dev); + + samsung_cmu_register_clocks(data->ctx, cmu); + samsung_clk_of_add_provider(dev->of_node, data->ctx); + pm_runtime_put_sync(dev); + + return 0; +} + +int exynos_arm64_cmu_suspend(struct device *dev) +{ + struct exynos_arm64_cmu_data *data = dev_get_drvdata(dev); + int i; + + samsung_clk_save(data->ctx->reg_base, data->clk_save, + data->nr_clk_save); + + for (i = 0; i < data->nr_pclks; i++) + clk_prepare_enable(data->pclks[i]); + + /* For suspend some registers have to be set to certain values */ + samsung_clk_restore(data->ctx->reg_base, data->clk_suspend, + data->nr_clk_suspend); + + for (i = 0; i < data->nr_pclks; i++) + clk_disable_unprepare(data->pclks[i]); + + clk_disable_unprepare(data->clk); + + return 0; +} + +int exynos_arm64_cmu_resume(struct device *dev) +{ + struct exynos_arm64_cmu_data *data = dev_get_drvdata(dev); + int i; + + clk_prepare_enable(data->clk); + + for (i = 0; i < data->nr_pclks; i++) + clk_prepare_enable(data->pclks[i]); + + samsung_clk_restore(data->ctx->reg_base, data->clk_save, + data->nr_clk_save); + + for (i = 0; i < data->nr_pclks; i++) + clk_disable_unprepare(data->pclks[i]); + + return 0; +} diff --git a/drivers/clk/samsung/clk-exynos-arm64.h b/drivers/clk/samsung/clk-exynos-arm64.h index 0dd174693935..969979e714bc 100644 --- a/drivers/clk/samsung/clk-exynos-arm64.h +++ b/drivers/clk/samsung/clk-exynos-arm64.h @@ -16,5 +16,8 @@ void exynos_arm64_register_cmu(struct device *dev, struct device_node *np, const struct samsung_cmu_info *cmu); +int exynos_arm64_register_cmu_pm(struct platform_device *pdev, bool set_manual); +int exynos_arm64_cmu_suspend(struct device *dev); +int exynos_arm64_cmu_resume(struct device *dev); #endif /* __CLK_EXYNOS_ARM64_H */ diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c index eb72bf2aaee8..ed43233649ae 100644 --- a/drivers/clk/samsung/clk-exynos5433.c +++ b/drivers/clk/samsung/clk-exynos5433.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -19,6 +18,7 @@ #include "clk.h" #include "clk-cpu.h" +#include "clk-exynos-arm64.h" #include "clk-pll.h" /* @@ -5478,160 +5478,9 @@ static const struct samsung_cmu_info imem_cmu_info __initconst = { .clk_name = "aclk_imem_200", }; -struct exynos5433_cmu_data { - struct samsung_clk_reg_dump *clk_save; - unsigned int nr_clk_save; - const struct samsung_clk_reg_dump *clk_suspend; - unsigned int nr_clk_suspend; - - struct clk *clk; - struct clk **pclks; - int nr_pclks; - - /* must be the last entry */ - struct samsung_clk_provider ctx; -}; - -static int __maybe_unused exynos5433_cmu_suspend(struct device *dev) -{ - struct exynos5433_cmu_data *data = dev_get_drvdata(dev); - int i; - - samsung_clk_save(data->ctx.reg_base, data->clk_save, - data->nr_clk_save); - - for (i = 0; i < data->nr_pclks; i++) - clk_prepare_enable(data->pclks[i]); - - /* for suspend some registers have to be set to certain values */ - samsung_clk_restore(data->ctx.reg_base, data->clk_suspend, - data->nr_clk_suspend); - - for (i = 0; i < data->nr_pclks; i++) - clk_disable_unprepare(data->pclks[i]); - - clk_disable_unprepare(data->clk); - - return 0; -} - -static int __maybe_unused exynos5433_cmu_resume(struct device *dev) -{ - struct exynos5433_cmu_data *data = dev_get_drvdata(dev); - int i; - - clk_prepare_enable(data->clk); - - for (i = 0; i < data->nr_pclks; i++) - clk_prepare_enable(data->pclks[i]); - - samsung_clk_restore(data->ctx.reg_base, data->clk_save, - data->nr_clk_save); - - for (i = 0; i < data->nr_pclks; i++) - clk_disable_unprepare(data->pclks[i]); - - return 0; -} - static int __init exynos5433_cmu_probe(struct platform_device *pdev) { - const struct samsung_cmu_info *info; - struct exynos5433_cmu_data *data; - struct samsung_clk_provider *ctx; - struct device *dev = &pdev->dev; - void __iomem *reg_base; - int i; - - info = of_device_get_match_data(dev); - - data = devm_kzalloc(dev, - struct_size(data, ctx.clk_data.hws, info->nr_clk_ids), - GFP_KERNEL); - if (!data) - return -ENOMEM; - ctx = &data->ctx; - - reg_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(reg_base)) - return PTR_ERR(reg_base); - - for (i = 0; i < info->nr_clk_ids; ++i) - ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); - - ctx->clk_data.num = info->nr_clk_ids; - ctx->reg_base = reg_base; - ctx->dev = dev; - spin_lock_init(&ctx->lock); - - data->clk_save = samsung_clk_alloc_reg_dump(info->clk_regs, - info->nr_clk_regs); - if (!data->clk_save) - return -ENOMEM; - data->nr_clk_save = info->nr_clk_regs; - data->clk_suspend = info->suspend_regs; - data->nr_clk_suspend = info->nr_suspend_regs; - data->nr_pclks = of_clk_get_parent_count(dev->of_node); - - if (data->nr_pclks > 0) { - data->pclks = devm_kcalloc(dev, sizeof(struct clk *), - data->nr_pclks, GFP_KERNEL); - if (!data->pclks) { - kfree(data->clk_save); - return -ENOMEM; - } - for (i = 0; i < data->nr_pclks; i++) { - struct clk *clk = of_clk_get(dev->of_node, i); - - if (IS_ERR(clk)) { - kfree(data->clk_save); - while (--i >= 0) - clk_put(data->pclks[i]); - return PTR_ERR(clk); - } - data->pclks[i] = clk; - } - } - - if (info->clk_name) - data->clk = clk_get(dev, info->clk_name); - clk_prepare_enable(data->clk); - - platform_set_drvdata(pdev, data); - - /* - * Enable runtime PM here to allow the clock core using runtime PM - * for the registered clocks. Additionally, we increase the runtime - * PM usage count before registering the clocks, to prevent the - * clock core from runtime suspending the device. - */ - pm_runtime_get_noresume(dev); - pm_runtime_set_active(dev); - pm_runtime_enable(dev); - - if (info->pll_clks) - samsung_clk_register_pll(ctx, info->pll_clks, - info->nr_pll_clks); - if (info->mux_clks) - samsung_clk_register_mux(ctx, info->mux_clks, - info->nr_mux_clks); - if (info->div_clks) - samsung_clk_register_div(ctx, info->div_clks, - info->nr_div_clks); - if (info->gate_clks) - samsung_clk_register_gate(ctx, info->gate_clks, - info->nr_gate_clks); - if (info->fixed_clks) - samsung_clk_register_fixed_rate(ctx, info->fixed_clks, - info->nr_fixed_clks); - if (info->fixed_factor_clks) - samsung_clk_register_fixed_factor(ctx, info->fixed_factor_clks, - info->nr_fixed_factor_clks); - - samsung_clk_of_add_provider(dev->of_node, ctx); - pm_runtime_put_sync(dev); - - return 0; + return exynos_arm64_register_cmu_pm(pdev, false); } static const struct of_device_id exynos5433_cmu_of_match[] = { @@ -5679,7 +5528,7 @@ static const struct of_device_id exynos5433_cmu_of_match[] = { }; static const struct dev_pm_ops exynos5433_cmu_pm_ops = { - SET_RUNTIME_PM_OPS(exynos5433_cmu_suspend, exynos5433_cmu_resume, + SET_RUNTIME_PM_OPS(exynos_arm64_cmu_suspend, exynos_arm64_cmu_resume, NULL) SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) -- GitLab From 22fd6153c16a40d123d8c9936967d0a59e417129 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 7 Mar 2023 08:51:02 +0100 Subject: [PATCH 0110/5631] driver core: class: fix block class problem when removing CONFIG_SYSFS_DEPRECATED* In removing the CONFIG_SYSFS_DEPRECATED and CONFIG_SYSFS_DEPRECATED_V2 config options, I messed up in the __class_register() function and got the logic incorrect. Fix this all up by just removing the special case of a block device class logic in this function, as that is what is intended. In testing, this solves the boot problem on my systems, hopefully on others as well. Cc: "Rafael J. Wysocki" Reported-by: Stephen Rothwell Fixes: 721da5cee9d4 ("driver core: remove CONFIG_SYSFS_DEPRECATED and CONFIG_SYSFS_DEPRECATED_V2") Link: https://lore.kernel.org/r/20230307075102.3537-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index fb8f2a1e1c19..5983eead8391 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -178,13 +178,7 @@ int __class_register(struct class *cls, struct lock_class_key *key) if (!cls->dev_kobj) cls->dev_kobj = sysfs_dev_char_kobj; -#if defined(CONFIG_BLOCK) - /* let the block class directory show up in the root of sysfs */ - if (cls != &block_class) - cp->subsys.kobj.kset = class_kset; -#else cp->subsys.kobj.kset = class_kset; -#endif cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; cls->p = cp; -- GitLab From 933bf364e152cd60902cf9585c2ba310d593e69f Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 17 Nov 2022 13:04:31 +0100 Subject: [PATCH 0111/5631] clk: rockchip: rk3399: allow clk_cifout to force clk_cifout_src to reparent clk_cifout is derived from clk_cifout_src through an integer divider limited to 32. clk_cifout_src is a child of either cpll, gpll or npll without any possibility of a divider of any sort. The default clock parent is cpll. Let's allow clk_cifout to ask its parent clk_cifout_src to reparent in order to find the real closest possible rate for clk_cifout and not one derived from cpll only. Cc: stable@vger.kernel.org # 4.10+ Fixes: fd8bc829336a ("clk: rockchip: fix the rk3399 cifout clock") Signed-off-by: Quentin Schulz Link: https://lore.kernel.org/r/20221117-rk3399-cifout-set-rate-parent-v1-0-432548d04081@theobroma-systems.com Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3399.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 306910a3a0d3..9ebd6c451b3d 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -1263,7 +1263,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { RK3399_CLKSEL_CON(56), 6, 2, MFLAGS, RK3399_CLKGATE_CON(10), 7, GFLAGS), - COMPOSITE_NOGATE(SCLK_CIF_OUT, "clk_cifout", mux_clk_cif_p, 0, + COMPOSITE_NOGATE(SCLK_CIF_OUT, "clk_cifout", mux_clk_cif_p, CLK_SET_RATE_PARENT, RK3399_CLKSEL_CON(56), 5, 1, MFLAGS, 0, 5, DFLAGS), /* gic */ -- GitLab From 8d35039d762d879543dec68ac15398b26fd8c759 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 2 Mar 2023 13:01:13 +0200 Subject: [PATCH 0112/5631] pinctrl: at91-pio4: use devm_clk_get_enabled() Use devm_clk_get_enabled() to simplify the code. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230302110116.342486-2-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91-pio4.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 373eed8bc4be..f7c37b90b711 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1098,7 +1098,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) if (IS_ERR(atmel_pioctrl->reg_base)) return PTR_ERR(atmel_pioctrl->reg_base); - atmel_pioctrl->clk = devm_clk_get(dev, NULL); + atmel_pioctrl->clk = devm_clk_get_enabled(dev, NULL); if (IS_ERR(atmel_pioctrl->clk)) { dev_err(dev, "failed to get clock\n"); return PTR_ERR(atmel_pioctrl->clk); @@ -1219,25 +1219,19 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) i, irq); } - ret = clk_prepare_enable(atmel_pioctrl->clk); - if (ret) { - dev_err(dev, "failed to prepare and enable clock\n"); - goto clk_prepare_enable_error; - } - atmel_pioctrl->pinctrl_dev = devm_pinctrl_register(&pdev->dev, &atmel_pinctrl_desc, atmel_pioctrl); if (IS_ERR(atmel_pioctrl->pinctrl_dev)) { ret = PTR_ERR(atmel_pioctrl->pinctrl_dev); dev_err(dev, "pinctrl registration failed\n"); - goto clk_unprep; + goto irq_domain_remove_error; } ret = gpiochip_add_data(atmel_pioctrl->gpio_chip, atmel_pioctrl); if (ret) { dev_err(dev, "failed to add gpiochip\n"); - goto clk_unprep; + goto irq_domain_remove_error; } ret = gpiochip_add_pin_range(atmel_pioctrl->gpio_chip, dev_name(dev), @@ -1254,10 +1248,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) gpiochip_add_pin_range_error: gpiochip_remove(atmel_pioctrl->gpio_chip); -clk_unprep: - clk_disable_unprepare(atmel_pioctrl->clk); - -clk_prepare_enable_error: +irq_domain_remove_error: irq_domain_remove(atmel_pioctrl->irq_domain); return ret; -- GitLab From 1ffd07c619499f013aa087e0855c5bc7170dce97 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 2 Mar 2023 13:01:14 +0200 Subject: [PATCH 0113/5631] pinctrl: at91-pio4: use device_get_match_data() Use device_get_match_data() to simplify the code. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230302110116.342486-3-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91-pio4.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index f7c37b90b711..58bce1457063 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1067,7 +1067,6 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct pinctrl_pin_desc *pin_desc; const char **group_names; - const struct of_device_id *match; int i, ret; struct atmel_pioctrl *atmel_pioctrl; const struct atmel_pioctrl_data *atmel_pioctrl_data; @@ -1079,12 +1078,11 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) atmel_pioctrl->node = dev->of_node; platform_set_drvdata(pdev, atmel_pioctrl); - match = of_match_node(atmel_pctrl_of_match, dev->of_node); - if (!match) { - dev_err(dev, "unknown compatible string\n"); + atmel_pioctrl_data = device_get_match_data(dev); + if (!atmel_pioctrl_data) { + dev_err(dev, "Invalid device data\n"); return -ENODEV; } - atmel_pioctrl_data = match->data; atmel_pioctrl->nbanks = atmel_pioctrl_data->nbanks; atmel_pioctrl->npins = atmel_pioctrl->nbanks * ATMEL_PIO_NPINS_PER_BANK; /* if last bank has limited number of pins, adjust accordingly */ -- GitLab From f03fff55e676d475a023fb820466ed6b280005ee Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 2 Mar 2023 13:01:15 +0200 Subject: [PATCH 0114/5631] pinctrl: at91-pio4: use dev_err_probe() Use dev_err_probe() to simplify the code. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230302110116.342486-4-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91-pio4.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 58bce1457063..86ff3dd8d3a6 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1079,10 +1079,9 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) platform_set_drvdata(pdev, atmel_pioctrl); atmel_pioctrl_data = device_get_match_data(dev); - if (!atmel_pioctrl_data) { - dev_err(dev, "Invalid device data\n"); - return -ENODEV; - } + if (!atmel_pioctrl_data) + return dev_err_probe(dev, -ENODEV, "Invalid device data\n"); + atmel_pioctrl->nbanks = atmel_pioctrl_data->nbanks; atmel_pioctrl->npins = atmel_pioctrl->nbanks * ATMEL_PIO_NPINS_PER_BANK; /* if last bank has limited number of pins, adjust accordingly */ @@ -1097,10 +1096,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(atmel_pioctrl->reg_base); atmel_pioctrl->clk = devm_clk_get_enabled(dev, NULL); - if (IS_ERR(atmel_pioctrl->clk)) { - dev_err(dev, "failed to get clock\n"); - return PTR_ERR(atmel_pioctrl->clk); - } + if (IS_ERR(atmel_pioctrl->clk)) + return dev_err_probe(dev, PTR_ERR(atmel_pioctrl->clk), "failed to get clock\n"); atmel_pioctrl->pins = devm_kcalloc(dev, atmel_pioctrl->npins, @@ -1200,10 +1197,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) atmel_pioctrl->irq_domain = irq_domain_add_linear(dev->of_node, atmel_pioctrl->gpio_chip->ngpio, &irq_domain_simple_ops, NULL); - if (!atmel_pioctrl->irq_domain) { - dev_err(dev, "can't add the irq domain\n"); - return -ENODEV; - } + if (!atmel_pioctrl->irq_domain) + return dev_err_probe(dev, -ENODEV, "can't add the irq domain\n"); atmel_pioctrl->irq_domain->name = "atmel gpio"; for (i = 0; i < atmel_pioctrl->npins; i++) { -- GitLab From 5a8f9cf269e8e33b8381f6dafb034c6da49f8228 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Thu, 2 Mar 2023 13:01:16 +0200 Subject: [PATCH 0115/5631] pinctrl: at91-pio4: use proper format specifier for unsigned int Use %u instead of %d as line is unsigned int. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230302110116.342486-5-claudiu.beznea@microchip.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91-pio4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 86ff3dd8d3a6..e40487be2038 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1144,7 +1144,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) pin_desc[i].number = i; /* Pin naming convention: P(bank_name)(bank_pin_number). */ - pin_desc[i].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "P%c%d", + pin_desc[i].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "P%c%u", bank + 'A', line); group->name = group_names[i] = pin_desc[i].name; -- GitLab From 6cf103bc03f8a915c8b5c8733a0e7404112f88d8 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 2 Mar 2023 08:21:31 +0100 Subject: [PATCH 0116/5631] pinctrl: freescale: remove generic pin config core support No instance of "struct imx_pinctrl_soc_info" sets '.generic_pinconf = true', so all of this is effectively dead code. To make it easier to understand the actual code, remove all the unused cruft. This effectively reverts a5cadbbb081c ("pinctrl: imx: add generic pin config core support"). It was only in use by a single SOC (imx7ulp) for a few releases, and the commit message of dbffda08f0e9 ("pinctrl: fsl: imx7ulp: change to use imx legacy binding") suggests that it won't be used in the future. Certainly no new user has appeared in 20+ releases, and should the need arise, this can be dug out of git history again. Signed-off-by: Rasmus Villemoes Reviewed-by: Fabio Estevam Link: https://lore.kernel.org/r/20230302072132.1051590-1-linux@rasmusvillemoes.dk Signed-off-by: Linus Walleij --- drivers/pinctrl/freescale/Kconfig | 2 +- drivers/pinctrl/freescale/pinctrl-imx.c | 80 ++----------------------- drivers/pinctrl/freescale/pinctrl-imx.h | 24 -------- 3 files changed, 6 insertions(+), 100 deletions(-) diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig index 7a32f77792d9..27bdc548f3a7 100644 --- a/drivers/pinctrl/freescale/Kconfig +++ b/drivers/pinctrl/freescale/Kconfig @@ -4,7 +4,7 @@ config PINCTRL_IMX depends on OF select GENERIC_PINCTRL_GROUPS select GENERIC_PINMUX_FUNCTIONS - select GENERIC_PINCONF + select PINCONF select REGMAP config PINCTRL_IMX_SCU diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c index e9aef764138f..93ffb5fc04e7 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.c +++ b/drivers/pinctrl/freescale/pinctrl-imx.c @@ -292,62 +292,6 @@ struct pinmux_ops imx_pmx_ops = { .set_mux = imx_pmx_set, }; -/* decode generic config into raw register values */ -static u32 imx_pinconf_decode_generic_config(struct imx_pinctrl *ipctl, - unsigned long *configs, - unsigned int num_configs) -{ - const struct imx_pinctrl_soc_info *info = ipctl->info; - const struct imx_cfg_params_decode *decode; - enum pin_config_param param; - u32 raw_config = 0; - u32 param_val; - int i, j; - - WARN_ON(num_configs > info->num_decodes); - - for (i = 0; i < num_configs; i++) { - param = pinconf_to_config_param(configs[i]); - param_val = pinconf_to_config_argument(configs[i]); - decode = info->decodes; - for (j = 0; j < info->num_decodes; j++) { - if (param == decode->param) { - if (decode->invert) - param_val = !param_val; - raw_config |= (param_val << decode->shift) - & decode->mask; - break; - } - decode++; - } - } - - if (info->fixup) - info->fixup(configs, num_configs, &raw_config); - - return raw_config; -} - -static u32 imx_pinconf_parse_generic_config(struct device_node *np, - struct imx_pinctrl *ipctl) -{ - const struct imx_pinctrl_soc_info *info = ipctl->info; - struct pinctrl_dev *pctl = ipctl->pctl; - unsigned int num_configs; - unsigned long *configs; - int ret; - - if (!info->generic_pinconf) - return 0; - - ret = pinconf_generic_parse_dt_config(np, pctl, &configs, - &num_configs); - if (ret) - return 0; - - return imx_pinconf_decode_generic_config(ipctl, configs, num_configs); -} - static int imx_pinconf_get_mmio(struct pinctrl_dev *pctldev, unsigned pin_id, unsigned long *config) { @@ -500,7 +444,6 @@ static const struct pinconf_ops imx_pinconf_ops = { /* * Each pin represented in fsl,pins consists of a number of u32 PIN_FUNC_ID * and 1 u32 CONFIG, the total size is PIN_FUNC_ID + CONFIG for each pin. - * For generic_pinconf case, there's no extra u32 CONFIG. * * PIN_FUNC_ID format: * Default: @@ -548,18 +491,12 @@ static void imx_pinctrl_parse_pin_mmio(struct imx_pinctrl *ipctl, pin_mmio->mux_mode = be32_to_cpu(*list++); pin_mmio->input_val = be32_to_cpu(*list++); - if (info->generic_pinconf) { - /* generic pin config decoded */ - pin_mmio->config = imx_pinconf_parse_generic_config(np, ipctl); - } else { - /* legacy pin config read from devicetree */ - config = be32_to_cpu(*list++); + config = be32_to_cpu(*list++); - /* SION bit is in mux register */ - if (config & IMX_PAD_SION) - pin_mmio->mux_mode |= IOMUXC_CONFIG_SION; - pin_mmio->config = config & ~IMX_PAD_SION; - } + /* SION bit is in mux register */ + if (config & IMX_PAD_SION) + pin_mmio->mux_mode |= IOMUXC_CONFIG_SION; + pin_mmio->config = config & ~IMX_PAD_SION; *list_p = list; @@ -587,9 +524,6 @@ static int imx_pinctrl_parse_groups(struct device_node *np, else pin_size = FSL_PIN_SIZE; - if (info->generic_pinconf) - pin_size -= 4; - /* Initialise group */ grp->name = np->name; @@ -855,10 +789,6 @@ int imx_pinctrl_probe(struct platform_device *pdev, imx_pinctrl_desc->confops = &imx_pinconf_ops; imx_pinctrl_desc->owner = THIS_MODULE; - /* for generic pinconf */ - imx_pinctrl_desc->custom_params = info->custom_params; - imx_pinctrl_desc->num_custom_params = info->num_custom_params; - /* platform specific callback */ imx_pmx_ops.gpio_set_direction = info->gpio_set_direction; diff --git a/drivers/pinctrl/freescale/pinctrl-imx.h b/drivers/pinctrl/freescale/pinctrl-imx.h index fd8c4b6b3e36..f65ff45b4003 100644 --- a/drivers/pinctrl/freescale/pinctrl-imx.h +++ b/drivers/pinctrl/freescale/pinctrl-imx.h @@ -11,7 +11,6 @@ #ifndef __DRIVERS_PINCTRL_IMX_H #define __DRIVERS_PINCTRL_IMX_H -#include #include struct platform_device; @@ -67,14 +66,6 @@ struct imx_pin_reg { s16 conf_reg; }; -/* decode a generic config into raw register value */ -struct imx_cfg_params_decode { - enum pin_config_param param; - u32 mask; - u8 shift; - bool invert; -}; - /** * @dev: a pointer back to containing device * @base: the offset to the controller in virtual memory @@ -100,15 +91,6 @@ struct imx_pinctrl_soc_info { unsigned int mux_mask; u8 mux_shift; - /* generic pinconf */ - bool generic_pinconf; - const struct pinconf_generic_params *custom_params; - unsigned int num_custom_params; - const struct imx_cfg_params_decode *decodes; - unsigned int num_decodes; - void (*fixup)(unsigned long *configs, unsigned int num_configs, - u32 *raw_config); - int (*gpio_set_direction)(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range, unsigned offset, @@ -122,12 +104,6 @@ struct imx_pinctrl_soc_info { const __be32 **list_p); }; -#define IMX_CFG_PARAMS_DECODE(p, m, o) \ - { .param = p, .mask = m, .shift = o, .invert = false, } - -#define IMX_CFG_PARAMS_DECODE_INVERT(p, m, o) \ - { .param = p, .mask = m, .shift = o, .invert = true, } - #define SHARE_MUX_CONF_REG BIT(0) #define ZERO_OFFSET_VALID BIT(1) #define IMX_USE_SCU BIT(2) -- GitLab From 5da094ac80cd4f6d4114ad220468f602f86d9980 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 24 Feb 2023 17:31:47 +0530 Subject: [PATCH 0117/5631] bus: mhi: host: Remove mhi_poll() API mhi_poll() API is not used within the MHI stack and also not by any client drivers in mainline. So let's remove it until any consumer is available. Reviewed-by: Jeffrey Hugo Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/main.c | 15 --------------- include/linux/mhi.h | 7 ------- 2 files changed, 22 deletions(-) diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index df0fbfee7b78..4fa0969472fc 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -1679,18 +1679,3 @@ void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev) } } EXPORT_SYMBOL_GPL(mhi_unprepare_from_transfer); - -int mhi_poll(struct mhi_device *mhi_dev, u32 budget) -{ - struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; - struct mhi_chan *mhi_chan = mhi_dev->dl_chan; - struct mhi_event *mhi_event = &mhi_cntrl->mhi_event[mhi_chan->er_index]; - int ret; - - spin_lock_bh(&mhi_event->lock); - ret = mhi_event->process_event(mhi_cntrl, mhi_event, budget); - spin_unlock_bh(&mhi_event->lock); - - return ret; -} -EXPORT_SYMBOL_GPL(mhi_poll); diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5441ad33c74..f6de4b6ecfc7 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -765,13 +765,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); */ void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev); -/** - * mhi_poll - Poll for any available data in DL direction - * @mhi_dev: Device associated with the channels - * @budget: # of events to process - */ -int mhi_poll(struct mhi_device *mhi_dev, u32 budget); - /** * mhi_queue_dma - Send or receive DMA mapped buffers from client device * over MHI channel -- GitLab From 94e19f4fbb1efc21cab860723662b3a9228b428f Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Tue, 7 Mar 2023 13:12:48 +0530 Subject: [PATCH 0118/5631] bus: mhi: ep: Demote unsupported channel error log to debug Not all MHI endpoints will support all available channels. Most of them support only a selected number of channels based on the implementations. In those cases, it is not needed to print error messages in the endpoint. So let's demote the error log to debug. Reviewed-by: Jeffrey Hugo Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/ep/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c index a6a48e515478..600881808982 100644 --- a/drivers/bus/mhi/ep/main.c +++ b/drivers/bus/mhi/ep/main.c @@ -126,7 +126,7 @@ static int mhi_ep_process_cmd_ring(struct mhi_ep_ring *ring, struct mhi_ring_ele /* Check if the channel is supported by the controller */ if ((ch_id >= mhi_cntrl->max_chan) || !mhi_cntrl->mhi_chan[ch_id].name) { - dev_err(dev, "Channel (%u) not supported!\n", ch_id); + dev_dbg(dev, "Channel (%u) not supported!\n", ch_id); return -ENODEV; } @@ -702,7 +702,7 @@ static void mhi_ep_cmd_ring_worker(struct work_struct *work) el = &ring->ring_cache[ring->rd_offset]; ret = mhi_ep_process_cmd_ring(ring, el); - if (ret) + if (ret && ret != -ENODEV) dev_err(dev, "Error processing cmd ring element: %zu\n", ring->rd_offset); mhi_ep_ring_inc_index(ring); -- GitLab From 23ad288aaf153a78b042e10062be1a6284909f95 Mon Sep 17 00:00:00 2001 From: Qinglin Pan Date: Thu, 9 Feb 2023 21:16:45 +0800 Subject: [PATCH 0119/5631] riscv: mm: modify pte format for Svnapot Add one alternative to enable/disable svnapot support, enable this static key when "svnapot" is in the "riscv,isa" field of fdt and SVNAPOT compile option is set. It will influence the behavior of has_svnapot. All code dependent on svnapot should make sure that has_svnapot return true firstly. Modify PTE definition for Svnapot, and creates some functions in pgtable.h to mark a PTE as napot and check if it is a Svnapot PTE. Until now, only 64KB napot size is supported in spec, so some macros has only 64KB version. Signed-off-by: Qinglin Pan Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230209131647.17245-2-panqinglin00@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 19 ++++++++++++++ arch/riscv/include/asm/hwcap.h | 9 ++++--- arch/riscv/include/asm/page.h | 5 ---- arch/riscv/include/asm/pgtable-64.h | 34 +++++++++++++++++++++++++ arch/riscv/include/asm/pgtable.h | 39 ++++++++++++++++++++++++++++- arch/riscv/kernel/cpu.c | 1 + arch/riscv/kernel/cpufeature.c | 1 + 7 files changed, 98 insertions(+), 10 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7c814fbf9527..abbb7b94488d 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -397,6 +397,25 @@ config RISCV_ISA_C If you don't know what to do here, say Y. +config RISCV_ISA_SVNAPOT + bool "SVNAPOT extension support" + depends on 64BIT && MMU + default y + select RISCV_ALTERNATIVE + help + Allow kernel to detect the SVNAPOT ISA-extension dynamically at boot + time and enable its usage. + + The SVNAPOT extension is used to mark contiguous PTEs as a range + of contiguous virtual-to-physical translations for a naturally + aligned power-of-2 (NAPOT) granularity larger than the base 4KB page + size. When HUGETLBFS is also selected this option unconditionally + allocates some memory for each NAPOT page size supported by the kernel. + When optimizing for low memory consumption and for platforms without + the SVNAPOT extension, it may be better to say N here. + + If you don't know what to do here, say Y. + config RISCV_ISA_SVPBMT bool "SVPBMT extension support" depends on 64BIT && MMU diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index ee9c80fe0062..6e368d3f6631 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -43,10 +43,11 @@ #define RISCV_ISA_EXT_SSCOFPMF 26 #define RISCV_ISA_EXT_SSTC 27 #define RISCV_ISA_EXT_SVINVAL 28 -#define RISCV_ISA_EXT_SVPBMT 29 -#define RISCV_ISA_EXT_ZBB 30 -#define RISCV_ISA_EXT_ZICBOM 31 -#define RISCV_ISA_EXT_ZIHINTPAUSE 32 +#define RISCV_ISA_EXT_SVNAPOT 29 +#define RISCV_ISA_EXT_SVPBMT 30 +#define RISCV_ISA_EXT_ZBB 31 +#define RISCV_ISA_EXT_ZICBOM 32 +#define RISCV_ISA_EXT_ZIHINTPAUSE 33 #ifndef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 9f432c1b5289..24a3dd265183 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -16,11 +16,6 @@ #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE - 1)) -#ifdef CONFIG_64BIT -#define HUGE_MAX_HSTATE 2 -#else -#define HUGE_MAX_HSTATE 1 -#endif #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 42a042c0e13e..7a5097202e15 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -78,6 +78,40 @@ typedef struct { */ #define _PAGE_PFN_MASK GENMASK(53, 10) +/* + * [63] Svnapot definitions: + * 0 Svnapot disabled + * 1 Svnapot enabled + */ +#define _PAGE_NAPOT_SHIFT 63 +#define _PAGE_NAPOT BIT(_PAGE_NAPOT_SHIFT) +/* + * Only 64KB (order 4) napot ptes supported. + */ +#define NAPOT_CONT_ORDER_BASE 4 +enum napot_cont_order { + NAPOT_CONT64KB_ORDER = NAPOT_CONT_ORDER_BASE, + NAPOT_ORDER_MAX, +}; + +#define for_each_napot_order(order) \ + for (order = NAPOT_CONT_ORDER_BASE; order < NAPOT_ORDER_MAX; order++) +#define for_each_napot_order_rev(order) \ + for (order = NAPOT_ORDER_MAX - 1; \ + order >= NAPOT_CONT_ORDER_BASE; order--) +#define napot_cont_order(val) (__builtin_ctzl((val.pte >> _PAGE_PFN_SHIFT) << 1)) + +#define napot_cont_shift(order) ((order) + PAGE_SHIFT) +#define napot_cont_size(order) BIT(napot_cont_shift(order)) +#define napot_cont_mask(order) (~(napot_cont_size(order) - 1UL)) +#define napot_pte_num(order) BIT(order) + +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define HUGE_MAX_HSTATE (2 + (NAPOT_ORDER_MAX - NAPOT_CONT_ORDER_BASE)) +#else +#define HUGE_MAX_HSTATE 2 +#endif + /* * [62:61] Svpbmt Memory Type definitions: * diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 2a88362dffa5..76502bc7bef2 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -264,10 +264,47 @@ static inline pte_t pud_pte(pud_t pud) return __pte(pud_val(pud)); } +#ifdef CONFIG_RISCV_ISA_SVNAPOT + +static __always_inline bool has_svnapot(void) +{ + return riscv_has_extension_likely(RISCV_ISA_EXT_SVNAPOT); +} + +static inline unsigned long pte_napot(pte_t pte) +{ + return pte_val(pte) & _PAGE_NAPOT; +} + +static inline pte_t pte_mknapot(pte_t pte, unsigned int order) +{ + int pos = order - 1 + _PAGE_PFN_SHIFT; + unsigned long napot_bit = BIT(pos); + unsigned long napot_mask = ~GENMASK(pos, _PAGE_PFN_SHIFT); + + return __pte((pte_val(pte) & napot_mask) | napot_bit | _PAGE_NAPOT); +} + +#else + +static __always_inline bool has_svnapot(void) { return false; } + +static inline unsigned long pte_napot(pte_t pte) +{ + return 0; +} + +#endif /* CONFIG_RISCV_ISA_SVNAPOT */ + /* Yields the page frame number (PFN) of a page table entry */ static inline unsigned long pte_pfn(pte_t pte) { - return __page_val_to_pfn(pte_val(pte)); + unsigned long res = __page_val_to_pfn(pte_val(pte)); + + if (has_svnapot() && pte_napot(pte)) + res = res & (res - 1UL); + + return res; } #define pte_page(x) pfn_to_page(pte_pfn(x)) diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 420228e219f7..5670909619c8 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -191,6 +191,7 @@ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), + __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), }; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 21fb567e1b22..271e391d436d 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -223,6 +223,7 @@ void __init riscv_fill_hwcap(void) SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC); SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); + SET_ISA_EXT_MAP("svnapot", RISCV_ISA_EXT_SVNAPOT); SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); -- GitLab From 82a1a1f3bfb628c4a44652349b94c66c7e8be7c9 Mon Sep 17 00:00:00 2001 From: Qinglin Pan Date: Thu, 9 Feb 2023 21:16:46 +0800 Subject: [PATCH 0120/5631] riscv: mm: support Svnapot in hugetlb page Svnapot can be used to support 64KB hugetlb page, so it can become a new option when using hugetlbfs. Add a basic implementation of hugetlb page, and support 64KB as a size in it by using Svnapot. For test, boot kernel with command line contains "default_hugepagesz=64K hugepagesz=64K hugepages=20" and run a simple test like this: tools/testing/selftests/vm/map_hugetlb 1 16 And it should be passed. Signed-off-by: Qinglin Pan Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230209131647.17245-3-panqinglin00@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 2 +- arch/riscv/include/asm/hugetlb.h | 34 +++- arch/riscv/mm/hugetlbpage.c | 301 +++++++++++++++++++++++++++++++ 3 files changed, 335 insertions(+), 2 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index abbb7b94488d..a81a89131bb9 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -44,7 +44,7 @@ config RISCV select ARCH_USE_QUEUED_RWLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS - select ARCH_WANT_GENERAL_HUGETLB + select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index ec19d6afc896..fe6f23006641 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -2,7 +2,6 @@ #ifndef _ASM_RISCV_HUGETLB_H #define _ASM_RISCV_HUGETLB_H -#include #include static inline void arch_clear_hugepage_flags(struct page *page) @@ -11,4 +10,37 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define __HAVE_ARCH_HUGE_PTE_CLEAR +void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long sz); + +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT +void set_huge_pte_at(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pte); + +#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH +pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); + +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); +#define arch_make_huge_pte arch_make_huge_pte + +#endif /*CONFIG_RISCV_ISA_SVNAPOT*/ + +#include + #endif /* _ASM_RISCV_HUGETLB_H */ diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 932dadfdca54..a163a3e0f0d4 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -2,6 +2,305 @@ #include #include +#ifdef CONFIG_RISCV_ISA_SVNAPOT +pte_t *huge_pte_alloc(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + unsigned long sz) +{ + unsigned long order; + pte_t *pte = NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + goto out; + } + + if (sz == PMD_SIZE) { + if (want_pmd_share(vma, addr) && pud_none(*pud)) + pte = huge_pmd_share(mm, vma, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + goto out; + } + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + for_each_napot_order(order) { + if (napot_cont_size(order) == sz) { + pte = pte_alloc_map(mm, pmd, addr & napot_cont_mask(order)); + break; + } + } + +out: + WARN_ON_ONCE(pte && pte_present(*pte) && !pte_huge(*pte)); + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, + unsigned long addr, + unsigned long sz) +{ + unsigned long order; + pte_t *pte = NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) + return NULL; + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return NULL; + + pud = pud_offset(p4d, addr); + if (sz == PUD_SIZE) + /* must be pud huge, non-present or none */ + return (pte_t *)pud; + + if (!pud_present(*pud)) + return NULL; + + pmd = pmd_offset(pud, addr); + if (sz == PMD_SIZE) + /* must be pmd huge, non-present or none */ + return (pte_t *)pmd; + + if (!pmd_present(*pmd)) + return NULL; + + for_each_napot_order(order) { + if (napot_cont_size(order) == sz) { + pte = pte_offset_kernel(pmd, addr & napot_cont_mask(order)); + break; + } + } + return pte; +} + +static pte_t get_clear_contig(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pte_num) +{ + pte_t orig_pte = ptep_get(ptep); + unsigned long i; + + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) { + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + + if (pte_dirty(pte)) + orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); + } + + return orig_pte; +} + +static pte_t get_clear_contig_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pte_num) +{ + pte_t orig_pte = get_clear_contig(mm, addr, ptep, pte_num); + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + bool valid = !pte_none(orig_pte); + + if (valid) + flush_tlb_range(&vma, addr, addr + (PAGE_SIZE * pte_num)); + + return orig_pte; +} + +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) +{ + unsigned long order; + + for_each_napot_order(order) { + if (shift == napot_cont_shift(order)) { + entry = pte_mknapot(entry, order); + break; + } + } + if (order == NAPOT_ORDER_MAX) + entry = pte_mkhuge(entry); + + return entry; +} + +void set_huge_pte_at(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + pte_t pte) +{ + int i, pte_num; + + if (!pte_napot(pte)) { + set_pte_at(mm, addr, ptep, pte); + return; + } + + pte_num = napot_pte_num(napot_cont_order(pte)); + for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE) + set_pte_at(mm, addr, ptep, pte); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, + pte_t pte, + int dirty) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long order; + pte_t orig_pte; + int i, pte_num; + + if (!pte_napot(pte)) + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + + order = napot_cont_order(pte); + pte_num = napot_pte_num(order); + ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num); + + if (pte_dirty(orig_pte)) + pte = pte_mkdirty(pte); + + if (pte_young(orig_pte)) + pte = pte_mkyoung(pte); + + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + set_pte_at(mm, addr, ptep, pte); + + return true; +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep) +{ + pte_t orig_pte = ptep_get(ptep); + int pte_num; + + if (!pte_napot(orig_pte)) + return ptep_get_and_clear(mm, addr, ptep); + + pte_num = napot_pte_num(napot_cont_order(orig_pte)); + + return get_clear_contig(mm, addr, ptep, pte_num); +} + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + unsigned long order; + int i, pte_num; + + if (!pte_napot(pte)) { + ptep_set_wrprotect(mm, addr, ptep); + return; + } + + order = napot_cont_order(pte); + pte_num = napot_pte_num(order); + ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + ptep_set_wrprotect(mm, addr, ptep); +} + +pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + int pte_num; + + if (!pte_napot(pte)) + return ptep_clear_flush(vma, addr, ptep); + + pte_num = napot_pte_num(napot_cont_order(pte)); + + return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num); +} + +void huge_pte_clear(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long sz) +{ + pte_t pte = READ_ONCE(*ptep); + int i, pte_num; + + if (!pte_napot(pte)) { + pte_clear(mm, addr, ptep); + return; + } + + pte_num = napot_pte_num(napot_cont_order(pte)); + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + pte_clear(mm, addr, ptep); +} + +static __init bool is_napot_size(unsigned long size) +{ + unsigned long order; + + if (!has_svnapot()) + return false; + + for_each_napot_order(order) { + if (size == napot_cont_size(order)) + return true; + } + return false; +} + +static __init int napot_hugetlbpages_init(void) +{ + if (has_svnapot()) { + unsigned long order; + + for_each_napot_order(order) + hugetlb_add_hstate(order); + } + return 0; +} +arch_initcall(napot_hugetlbpages_init); + +#else + +static __init bool is_napot_size(unsigned long size) +{ + return false; +} + +#endif /*CONFIG_RISCV_ISA_SVNAPOT*/ + int pud_huge(pud_t pud) { return pud_leaf(pud); @@ -18,6 +317,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return true; else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE) return true; + else if (is_napot_size(size)) + return true; else return false; } -- GitLab From ce173474cf19fe7fbe8f0fc74e3c81ec9c3d9807 Mon Sep 17 00:00:00 2001 From: Qinglin Pan Date: Thu, 9 Feb 2023 21:16:47 +0800 Subject: [PATCH 0121/5631] riscv: mm: support Svnapot in huge vmap As HAVE_ARCH_HUGE_VMAP and HAVE_ARCH_HUGE_VMALLOC is supported, we can implement arch_vmap_pte_range_map_size and arch_vmap_pte_supported_shift for Svnapot to support huge vmap about napot size. It can be tested by huge vmap used in pci driver. Huge vmalloc with svnapot can be tested by test_vmalloc with [1] applied, and probe this module to run fix_size_alloc_test with use_huge true. [1]https://lore.kernel.org/all/20221212055657.698420-1-panqinglin2020@iscas.ac.cn/ Signed-off-by: Qinglin Pan Reviewed-by: Andrew Jones Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20230209131647.17245-4-panqinglin00@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/vmalloc.h | 61 +++++++++++++++++++++++++++++++- 1 file changed, 60 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 48da5371f1e9..58d3e447f191 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -17,6 +17,65 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) return true; } -#endif +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#include +#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + unsigned long map_size = PAGE_SIZE; + unsigned long size, order; + + if (!has_svnapot()) + return map_size; + + for_each_napot_order_rev(order) { + if (napot_cont_shift(order) > max_page_shift) + continue; + + size = napot_cont_size(order); + if (end - addr < size) + continue; + + if (!IS_ALIGNED(addr, size)) + continue; + + if (!IS_ALIGNED(PFN_PHYS(pfn), size)) + continue; + + map_size = size; + break; + } + + return map_size; +} + +#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + int shift = PAGE_SHIFT; + unsigned long order; + + if (!has_svnapot()) + return shift; + + WARN_ON_ONCE(size >= PMD_SIZE); + + for_each_napot_order_rev(order) { + if (napot_cont_size(order) > size) + continue; + + if (!IS_ALIGNED(size, napot_cont_size(order))) + continue; + + shift = napot_cont_shift(order); + break; + } + + return shift; +} + +#endif /* CONFIG_RISCV_ISA_SVNAPOT */ +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* _ASM_RISCV_VMALLOC_H */ -- GitLab From 45581e663703b7d36da1bc884950f199976bc8b3 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 14:16:25 -0600 Subject: [PATCH 0122/5631] bus: mhi: host: pci_generic: Drop redundant pci_enable_pcie_error_reporting() pci_enable_pcie_error_reporting() enables the device to send ERR_* Messages. Since commit ("PCI/AER: Enable error reporting when AER is native"), the PCI core does this for all devices during enumeration, so the driver doesn't need to do it itself. Remove the redundant pci_enable_pcie_error_reporting() call from the driver. Also remove the corresponding pci_disable_pcie_error_reporting() from the driver .remove() path. Note that this only controls ERR_* Messages from the device. An ERR_* Message may cause the Root Port to generate an interrupt, depending on the AER Root Error Command register managed by the AER service driver. Signed-off-by: Bjorn Helgaas Reviewed-by: Manivannan Sadhasivam Reviewed-by: Jeffrey Hugo Link: https://lore.kernel.org/r/20230307201625.879567-1-helgaas@kernel.org Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/pci_generic.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index f39657f71483..6e13c43a84d1 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -8,7 +8,6 @@ * Copyright (C) 2020 Linaro Ltd */ -#include #include #include #include @@ -903,11 +902,9 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mhi_pdev->pci_state = pci_store_saved_state(pdev); pci_load_saved_state(pdev, NULL); - pci_enable_pcie_error_reporting(pdev); - err = mhi_register_controller(mhi_cntrl, mhi_cntrl_config); if (err) - goto err_disable_reporting; + return err; /* MHI bus does not power up the controller by default */ err = mhi_prepare_for_power_up(mhi_cntrl); @@ -941,8 +938,6 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mhi_unprepare_after_power_down(mhi_cntrl); err_unregister: mhi_unregister_controller(mhi_cntrl); -err_disable_reporting: - pci_disable_pcie_error_reporting(pdev); return err; } @@ -965,7 +960,6 @@ static void mhi_pci_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); mhi_unregister_controller(mhi_cntrl); - pci_disable_pcie_error_reporting(pdev); } static void mhi_pci_shutdown(struct pci_dev *pdev) -- GitLab From d1c1ace35e1586025a56c39eb201b6d54a592a09 Mon Sep 17 00:00:00 2001 From: Shibo Li Date: Mon, 20 Feb 2023 09:04:30 +0000 Subject: [PATCH 0123/5631] staging: rtl8712: Remove extra spaces This patch fixes the problem of irregular indentation Signed-off-by: Shibo Li Link: https://lore.kernel.org/r/20230220090430.19589-1-zzutcyha@163.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/rtl871x_mlme.c | 93 +++++++++++++------------- 1 file changed, 47 insertions(+), 46 deletions(-) diff --git a/drivers/staging/rtl8712/rtl871x_mlme.c b/drivers/staging/rtl8712/rtl871x_mlme.c index 63e12b157001..d42ec1053a6e 100644 --- a/drivers/staging/rtl8712/rtl871x_mlme.c +++ b/drivers/staging/rtl8712/rtl871x_mlme.c @@ -663,7 +663,7 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) if (!pnetwork) return; memcpy((u8 *)pnetwork + 16, (u8 *)pbuf + 8, - sizeof(struct wlan_network) - 16); + sizeof(struct wlan_network) - 16); } else { pnetwork = (struct wlan_network *)pbuf; } @@ -674,36 +674,36 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) pnetwork->network_type = le32_to_cpu(pnetwork->network_type); pnetwork->network.Length = le32_to_cpu(pnetwork->network.Length); pnetwork->network.Ssid.SsidLength = - le32_to_cpu(pnetwork->network.Ssid.SsidLength); + le32_to_cpu(pnetwork->network.Ssid.SsidLength); pnetwork->network.Privacy = le32_to_cpu(pnetwork->network.Privacy); pnetwork->network.Rssi = le32_to_cpu(pnetwork->network.Rssi); pnetwork->network.NetworkTypeInUse = - le32_to_cpu(pnetwork->network.NetworkTypeInUse); + le32_to_cpu(pnetwork->network.NetworkTypeInUse); pnetwork->network.Configuration.ATIMWindow = - le32_to_cpu(pnetwork->network.Configuration.ATIMWindow); + le32_to_cpu(pnetwork->network.Configuration.ATIMWindow); pnetwork->network.Configuration.BeaconPeriod = - le32_to_cpu(pnetwork->network.Configuration.BeaconPeriod); + le32_to_cpu(pnetwork->network.Configuration.BeaconPeriod); pnetwork->network.Configuration.DSConfig = - le32_to_cpu(pnetwork->network.Configuration.DSConfig); + le32_to_cpu(pnetwork->network.Configuration.DSConfig); pnetwork->network.Configuration.FHConfig.DwellTime = - le32_to_cpu(pnetwork->network.Configuration.FHConfig.DwellTime); + le32_to_cpu(pnetwork->network.Configuration.FHConfig.DwellTime); pnetwork->network.Configuration.FHConfig.HopPattern = - le32_to_cpu(pnetwork->network.Configuration.FHConfig.HopPattern); + le32_to_cpu(pnetwork->network.Configuration.FHConfig.HopPattern); pnetwork->network.Configuration.FHConfig.HopSet = - le32_to_cpu(pnetwork->network.Configuration.FHConfig.HopSet); + le32_to_cpu(pnetwork->network.Configuration.FHConfig.HopSet); pnetwork->network.Configuration.FHConfig.Length = - le32_to_cpu(pnetwork->network.Configuration.FHConfig.Length); + le32_to_cpu(pnetwork->network.Configuration.FHConfig.Length); pnetwork->network.Configuration.Length = - le32_to_cpu(pnetwork->network.Configuration.Length); + le32_to_cpu(pnetwork->network.Configuration.Length); pnetwork->network.InfrastructureMode = - le32_to_cpu(pnetwork->network.InfrastructureMode); + le32_to_cpu(pnetwork->network.InfrastructureMode); pnetwork->network.IELength = le32_to_cpu(pnetwork->network.IELength); #endif the_same_macaddr = !memcmp(pnetwork->network.MacAddress, - cur_network->network.MacAddress, ETH_ALEN); + cur_network->network.MacAddress, ETH_ALEN); pnetwork->network.Length = - r8712_get_wlan_bssid_ex_sz(&pnetwork->network); + r8712_get_wlan_bssid_ex_sz(&pnetwork->network); spin_lock_irqsave(&pmlmepriv->lock, irqL); if (pnetwork->network.Length > sizeof(struct wlan_bssid_ex)) goto ignore_joinbss_callback; @@ -713,24 +713,24 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) if (check_fwstate(pmlmepriv, _FW_LINKED)) { if (the_same_macaddr) { ptarget_wlan = - r8712_find_network(&pmlmepriv->scanned_queue, - cur_network->network.MacAddress); + r8712_find_network(&pmlmepriv->scanned_queue, + cur_network->network.MacAddress); } else { pcur_wlan = - r8712_find_network(&pmlmepriv->scanned_queue, - cur_network->network.MacAddress); + r8712_find_network(&pmlmepriv->scanned_queue, + cur_network->network.MacAddress); if (pcur_wlan) pcur_wlan->fixed = false; pcur_sta = r8712_get_stainfo(pstapriv, - cur_network->network.MacAddress); + cur_network->network.MacAddress); spin_lock_irqsave(&pstapriv->sta_hash_lock, irqL2); r8712_free_stainfo(adapter, pcur_sta); spin_unlock_irqrestore(&(pstapriv->sta_hash_lock), irqL2); ptarget_wlan = - r8712_find_network(&pmlmepriv->scanned_queue, - pnetwork->network.MacAddress); + r8712_find_network(&pmlmepriv->scanned_queue, + pnetwork->network.MacAddress); if (ptarget_wlan) ptarget_wlan->fixed = true; } @@ -745,7 +745,7 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) if (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)) pmlmepriv->fw_state ^= - _FW_UNDER_LINKING; + _FW_UNDER_LINKING; goto ignore_joinbss_callback; } @@ -753,16 +753,16 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) if (check_fwstate(pmlmepriv, WIFI_STATION_STATE)) { if (the_same_macaddr) { ptarget_sta = - r8712_get_stainfo(pstapriv, - pnetwork->network.MacAddress); + r8712_get_stainfo(pstapriv, + pnetwork->network.MacAddress); if (!ptarget_sta) ptarget_sta = - r8712_alloc_stainfo(pstapriv, - pnetwork->network.MacAddress); + r8712_alloc_stainfo(pstapriv, + pnetwork->network.MacAddress); } else { ptarget_sta = - r8712_alloc_stainfo(pstapriv, - pnetwork->network.MacAddress); + r8712_alloc_stainfo(pstapriv, + pnetwork->network.MacAddress); } if (ptarget_sta) /*update ptarget_sta*/ { ptarget_sta->aid = pnetwork->join_res; @@ -776,24 +776,25 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) ptarget_sta->XPrivacy = adapter-> securitypriv.PrivacyAlgrthm; memset((u8 *)&ptarget_sta->x_UncstKey, - 0, - sizeof(union Keytype)); + 0, + sizeof(union Keytype)); memset((u8 *)&ptarget_sta->tkiprxmickey, - 0, - sizeof(union Keytype)); + 0, + sizeof(union Keytype)); memset((u8 *)&ptarget_sta->tkiptxmickey, - 0, - sizeof(union Keytype)); - memset((u8 *)&ptarget_sta->txpn, 0, - sizeof(union pn48)); - memset((u8 *)&ptarget_sta->rxpn, 0, - sizeof(union pn48)); + 0, + sizeof(union Keytype)); + memset((u8 *)&ptarget_sta->txpn, + 0, + sizeof(union pn48)); + memset((u8 *)&ptarget_sta->rxpn, + 0, + sizeof(union pn48)); } } else { - if (check_fwstate(pmlmepriv, - _FW_UNDER_LINKING)) + if (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)) pmlmepriv->fw_state ^= - _FW_UNDER_LINKING; + _FW_UNDER_LINKING; goto ignore_joinbss_callback; } } @@ -815,12 +816,12 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) break; } r8712_update_protection(adapter, - (cur_network->network.IEs) + - sizeof(struct NDIS_802_11_FIXED_IEs), - (cur_network->network.IELength)); + (cur_network->network.IEs) + + sizeof(struct NDIS_802_11_FIXED_IEs), + (cur_network->network.IELength)); /*TODO: update HT_Capability*/ update_ht_cap(adapter, cur_network->network.IEs, - cur_network->network.IELength); + cur_network->network.IELength); /*indicate connect*/ if (check_fwstate(pmlmepriv, WIFI_STATION_STATE)) r8712_indicate_connect(adapter); @@ -831,7 +832,7 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) } else { if (check_fwstate(pmlmepriv, _FW_UNDER_LINKING)) { mod_timer(&pmlmepriv->assoc_timer, - jiffies + msecs_to_jiffies(1)); + jiffies + msecs_to_jiffies(1)); _clr_fwstate_(pmlmepriv, _FW_UNDER_LINKING); } } -- GitLab From dd680522f6aefeae94107bf4106b6f2da31c5025 Mon Sep 17 00:00:00 2001 From: Shibo Li Date: Mon, 20 Feb 2023 08:40:50 +0000 Subject: [PATCH 0124/5631] staging: rtl8712: Fix multiple line dereference This patch fixes the following warning in rtl871x_mlme.c WARNING: Avoid multiple line dereference - prefer 'adapter->securitypriv.PrivacyAlgrthm' Signed-off-by: Shibo Li Tested-by: Philipp Hortmann AW-NU120 Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20230220084050.18459-1-zzutcyha@163.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/rtl871x_mlme.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/rtl8712/rtl871x_mlme.c b/drivers/staging/rtl8712/rtl871x_mlme.c index d42ec1053a6e..fccfa0915a02 100644 --- a/drivers/staging/rtl8712/rtl871x_mlme.c +++ b/drivers/staging/rtl8712/rtl871x_mlme.c @@ -773,8 +773,8 @@ void r8712_joinbss_event_callback(struct _adapter *adapter, u8 *pbuf) adapter->securitypriv.busetkipkey = false; adapter->securitypriv.bgrpkey_handshake = false; ptarget_sta->ieee8021x_blocked = true; - ptarget_sta->XPrivacy = adapter-> - securitypriv.PrivacyAlgrthm; + ptarget_sta->XPrivacy = + adapter->securitypriv.PrivacyAlgrthm; memset((u8 *)&ptarget_sta->x_UncstKey, 0, sizeof(union Keytype)); -- GitLab From 5e1209d025741d2b021d7938eca18f27332ba545 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Wed, 8 Mar 2023 14:36:53 +0800 Subject: [PATCH 0125/5631] staging: most: dim2: Use devm_platform_get_and_ioremap_resource() According to commit 890cc39a8799 ("drivers: provide devm_platform_get_and_ioremap_resource()"), convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Yang Li Link: https://lore.kernel.org/r/20230308063653.92879-1-yang.lee@linux.alibaba.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/dim2/dim2.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/most/dim2/dim2.c b/drivers/staging/most/dim2/dim2.c index 7a5f80e637a0..b8bd01ca1f11 100644 --- a/drivers/staging/most/dim2/dim2.c +++ b/drivers/staging/most/dim2/dim2.c @@ -775,8 +775,7 @@ static int dim2_probe(struct platform_device *pdev) goto err_free_dev; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dev->io_base = devm_ioremap_resource(&pdev->dev, res); + dev->io_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(dev->io_base)) { ret = PTR_ERR(dev->io_base); goto err_free_dev; -- GitLab From 81201b66b311f23c74fe6ce34d4a204c06f862df Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:15:33 +0100 Subject: [PATCH 0126/5631] staging: rtl8192e: Remove entry .get_eeprom_size from struct rtl819x_ops Remove entry .get_eeprom_size and replace it with function name rtl92e_get_eeprom_size. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/1323e1ae2b4f52dc42b7ce5debca5608c9c5aafd.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 104b16cfa979..73f3d0973a5a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -27,7 +27,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, - .get_eeprom_size = rtl92e_get_eeprom_size, .init_adapter_variable = rtl92e_init_variables, .initialize_adapter = rtl92e_start_adapter, .link_change = rtl92e_link_change, @@ -974,7 +973,7 @@ static short _rtl92e_init(struct net_device *dev) _rtl92e_init_priv_variable(dev); _rtl92e_init_priv_lock(priv); _rtl92e_init_priv_task(dev); - priv->ops->get_eeprom_size(dev); + rtl92e_get_eeprom_size(dev); priv->ops->init_adapter_variable(dev); _rtl92e_get_channel_map(dev); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index fd96eef90c7f..00e413a644d2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -205,7 +205,6 @@ struct rtl8192_tx_ring { struct rtl819x_ops { enum nic_t nic_type; - void (*get_eeprom_size)(struct net_device *dev); void (*init_adapter_variable)(struct net_device *dev); void (*init_before_adapter_start)(struct net_device *dev); bool (*initialize_adapter)(struct net_device *dev); -- GitLab From 379fbe28a157aa6e25c36d208080653c3613ee59 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:15:40 +0100 Subject: [PATCH 0127/5631] staging: rtl8192e: Remove entry .init_adapter_.. from struct rtl819x_ops Remove entry .init_adapter_variable and replace it with function name rtl92e_init_variables. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/cc6134e1cf43a8b74615f9eb4377988e3edd0bca.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 73f3d0973a5a..7b8683a9bdb1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -27,7 +27,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, - .init_adapter_variable = rtl92e_init_variables, .initialize_adapter = rtl92e_start_adapter, .link_change = rtl92e_link_change, .tx_fill_descriptor = rtl92e_fill_tx_desc, @@ -974,7 +973,7 @@ static short _rtl92e_init(struct net_device *dev) _rtl92e_init_priv_lock(priv); _rtl92e_init_priv_task(dev); rtl92e_get_eeprom_size(dev); - priv->ops->init_adapter_variable(dev); + rtl92e_init_variables(dev); _rtl92e_get_channel_map(dev); rtl92e_dm_init(dev); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 00e413a644d2..541b7aa366a5 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -205,7 +205,6 @@ struct rtl8192_tx_ring { struct rtl819x_ops { enum nic_t nic_type; - void (*init_adapter_variable)(struct net_device *dev); void (*init_before_adapter_start)(struct net_device *dev); bool (*initialize_adapter)(struct net_device *dev); void (*link_change)(struct net_device *dev); -- GitLab From e42c99ead8308aa58b73bda044d2f9dd82756b15 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:15:46 +0100 Subject: [PATCH 0128/5631] staging: rtl8192e: Remove entry .initialize_ad.. from struct rtl819x_ops Remove entry .initialize_adapter and replace it with function name rtl92e_start_adapter. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/7457e18ea9f3b2415bf41fca8ac2b22349d2edd1.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 5 ++--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 7b8683a9bdb1..3bebc1153572 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -27,7 +27,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, - .initialize_adapter = rtl92e_start_adapter, .link_change = rtl92e_link_change, .tx_fill_descriptor = rtl92e_fill_tx_desc, .tx_fill_cmd_descriptor = rtl92e_fill_tx_cmd_desc, @@ -690,7 +689,7 @@ static int _rtl92e_sta_up(struct net_device *dev, bool is_silent_reset) priv->rtllib->ieee_up = 1; priv->up_first_time = 0; - init_status = priv->ops->initialize_adapter(dev); + init_status = rtl92e_start_adapter(dev); if (!init_status) { netdev_err(dev, "%s(): Initialization failed!\n", __func__); return -1; @@ -2381,7 +2380,7 @@ bool rtl92e_enable_nic(struct net_device *dev) return false; } - init_status = priv->ops->initialize_adapter(dev); + init_status = rtl92e_start_adapter(dev); if (!init_status) { netdev_warn(dev, "%s(): Initialization failed!\n", __func__); priv->bdisable_nic = false; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 541b7aa366a5..9edadc62faa9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -206,7 +206,6 @@ struct rtl8192_tx_ring { struct rtl819x_ops { enum nic_t nic_type; void (*init_before_adapter_start)(struct net_device *dev); - bool (*initialize_adapter)(struct net_device *dev); void (*link_change)(struct net_device *dev); void (*tx_fill_descriptor)(struct net_device *dev, struct tx_desc *tx_desc, -- GitLab From 5de8f7b149eea9905b148cc6d7b2c0087d24c58f Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:15:52 +0100 Subject: [PATCH 0129/5631] staging: rtl8192e: Remove entry .tx_fill_descr.. from struct rtl819x_ops Remove entry .tx_fill_descriptor and replace it with function name rtl92e_fill_tx_desc. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/1ae7d44ef74dc6cb61ff43f670b21d702403d7fb.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 5 ++--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 4 ---- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 3bebc1153572..dd1f4a3c4bf9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -28,7 +28,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, - .tx_fill_descriptor = rtl92e_fill_tx_desc, .tx_fill_cmd_descriptor = rtl92e_fill_tx_cmd_desc, .rx_query_status_descriptor = rtl92e_get_rx_stats, .rx_command_packet_handler = NULL, @@ -496,7 +495,7 @@ static void _rtl92e_prepare_beacon(struct tasklet_struct *t) skb_push(pnewskb, priv->rtllib->tx_headroom); pdesc = &ring->desc[0]; - priv->ops->tx_fill_descriptor(dev, pdesc, tcb_desc, pnewskb); + rtl92e_fill_tx_desc(dev, pdesc, tcb_desc, pnewskb); __skb_queue_tail(&ring->queue, pnewskb); pdesc->OWN = 1; } @@ -1637,7 +1636,7 @@ static short _rtl92e_tx(struct net_device *dev, struct sk_buff *skb) if (priv->rtllib->LedControlHandler) priv->rtllib->LedControlHandler(dev, LED_CTL_TX); } - priv->ops->tx_fill_descriptor(dev, pdesc, tcb_desc, skb); + rtl92e_fill_tx_desc(dev, pdesc, tcb_desc, skb); __skb_queue_tail(&ring->queue, skb); pdesc->OWN = 1; spin_unlock_irqrestore(&priv->irq_th_lock, flags); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 9edadc62faa9..0d4ae3a310da 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -207,10 +207,6 @@ struct rtl819x_ops { enum nic_t nic_type; void (*init_before_adapter_start)(struct net_device *dev); void (*link_change)(struct net_device *dev); - void (*tx_fill_descriptor)(struct net_device *dev, - struct tx_desc *tx_desc, - struct cb_desc *cb_desc, - struct sk_buff *skb); void (*tx_fill_cmd_descriptor)(struct net_device *dev, struct tx_desc_cmd *entry, struct cb_desc *cb_desc, -- GitLab From ec1a4fe412090c2e1574462548597e7aaa1d772f Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:00 +0100 Subject: [PATCH 0130/5631] staging: rtl8192e: Remove entry .tx_fill_cmd_d.. from struct rtl819x_ops Remove entry .tx_fill_cmd_descriptor and replace it with function name rtl92e_fill_tx_cmd_desc. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/713a48fcd6d56c3cc4e32aea0eeba881e0d092c5.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 4 ---- 2 files changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index dd1f4a3c4bf9..372bb4810c31 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -28,7 +28,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, - .tx_fill_cmd_descriptor = rtl92e_fill_tx_cmd_desc, .rx_query_status_descriptor = rtl92e_get_rx_stats, .rx_command_packet_handler = NULL, .stop_adapter = rtl92e_stop_adapter, @@ -1577,7 +1576,7 @@ static void _rtl92e_tx_cmd(struct net_device *dev, struct sk_buff *skb) tcb_desc = (struct cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE); - priv->ops->tx_fill_cmd_descriptor(dev, entry, tcb_desc, skb); + rtl92e_fill_tx_cmd_desc(dev, entry, tcb_desc, skb); __skb_queue_tail(&ring->queue, skb); spin_unlock_irqrestore(&priv->irq_th_lock, flags); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 0d4ae3a310da..5af14837df31 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -207,10 +207,6 @@ struct rtl819x_ops { enum nic_t nic_type; void (*init_before_adapter_start)(struct net_device *dev); void (*link_change)(struct net_device *dev); - void (*tx_fill_cmd_descriptor)(struct net_device *dev, - struct tx_desc_cmd *entry, - struct cb_desc *cb_desc, - struct sk_buff *skb); bool (*rx_query_status_descriptor)(struct net_device *dev, struct rtllib_rx_stats *stats, struct rx_desc *pdesc, -- GitLab From 8fd527818fbb71b7caca2065547a5fdf96f8fc48 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:12 +0100 Subject: [PATCH 0131/5631] staging: rtl8192e: Remove entry .rx_query_stat.. from struct rtl819x_ops Remove entry .rx_query_status_descriptor and replace it with function name rtl92e_get_rx_stats. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/889c557f6e312645eb40173b7ffa210cabf10110.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 4 +--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 4 ---- 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 372bb4810c31..a4796330f86d 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -28,7 +28,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, - .rx_query_status_descriptor = rtl92e_get_rx_stats, .rx_command_packet_handler = NULL, .stop_adapter = rtl92e_stop_adapter, .update_ratr_table = rtl92e_update_ratr_table, @@ -1885,8 +1884,7 @@ static void _rtl92e_rx_normal(struct net_device *dev) if (pdesc->OWN) return; - if (!priv->ops->rx_query_status_descriptor(dev, &stats, - pdesc, skb)) + if (!rtl92e_get_rx_stats(dev, &stats, pdesc, skb)) goto done; new_skb = dev_alloc_skb(priv->rxbuffersize); /* if allocation of new skb failed - drop current packet diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 5af14837df31..d83af5f8ce82 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -207,10 +207,6 @@ struct rtl819x_ops { enum nic_t nic_type; void (*init_before_adapter_start)(struct net_device *dev); void (*link_change)(struct net_device *dev); - bool (*rx_query_status_descriptor)(struct net_device *dev, - struct rtllib_rx_stats *stats, - struct rx_desc *pdesc, - struct sk_buff *skb); bool (*rx_command_packet_handler)(struct net_device *dev, struct sk_buff *skb, struct rx_desc *pdesc); -- GitLab From 7529b539899a6848e907ee914e01188c54f693ef Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:19 +0100 Subject: [PATCH 0132/5631] staging: rtl8192e: Remove entry .stop_adapter from struct rtl819x_ops Remove entry .stop_adapter and replace it with function name rtl92e_stop_adapter. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/87f874eae22027956b9f1140b8d460ed8b63a9f9.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 7 +++---- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index a4796330f86d..566513338089 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -29,7 +29,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, - .stop_adapter = rtl92e_stop_adapter, .update_ratr_table = rtl92e_update_ratr_table, .irq_enable = rtl92e_enable_irq, .irq_disable = rtl92e_disable_irq, @@ -756,7 +755,7 @@ static int _rtl92e_sta_down(struct net_device *dev, bool shutdownrf) } priv->rf_change_in_progress = true; spin_unlock_irqrestore(&priv->rf_ps_lock, flags); - priv->ops->stop_adapter(dev, false); + rtl92e_stop_adapter(dev, false); spin_lock_irqsave(&priv->rf_ps_lock, flags); priv->rf_change_in_progress = false; spin_unlock_irqrestore(&priv->rf_ps_lock, flags); @@ -2055,7 +2054,7 @@ void rtl92e_commit(struct net_device *dev) return; rtllib_softmac_stop_protocol(priv->rtllib, 0, true); rtl92e_irq_disable(dev); - priv->ops->stop_adapter(dev, true); + rtl92e_stop_adapter(dev, true); _rtl92e_up(dev, false); } @@ -2401,7 +2400,7 @@ bool rtl92e_disable_nic(struct net_device *dev) _rtl92e_cancel_deferred_work(priv); rtl92e_irq_disable(dev); - priv->ops->stop_adapter(dev, false); + rtl92e_stop_adapter(dev, false); return true; } diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index d83af5f8ce82..083bba3dc51b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -210,7 +210,6 @@ struct rtl819x_ops { bool (*rx_command_packet_handler)(struct net_device *dev, struct sk_buff *skb, struct rx_desc *pdesc); - void (*stop_adapter)(struct net_device *dev, bool reset); void (*update_ratr_table)(struct net_device *dev); void (*irq_enable)(struct net_device *dev); void (*irq_disable)(struct net_device *dev); -- GitLab From 51515f0a10c6a2127ec422d5ced9ae7fdec78c9b Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:28 +0100 Subject: [PATCH 0133/5631] staging: rtl8192e: Remove entry .update_ratr_t.. from struct rtl819x_ops Remove entry .update_ratr_table and replace it with function name rtl92e_update_ratr_table. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/b9557fd44fde0261acd867124aae4d318587a497.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 3 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 0b5b2ae27f9e..1e307789ee93 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -806,7 +806,7 @@ void rtl92e_link_change(struct net_device *dev) if (ieee->state == RTLLIB_LINKED) { _rtl92e_net_update(dev); - priv->ops->update_ratr_table(dev); + rtl92e_update_ratr_table(dev); if ((ieee->pairwise_key_type == KEY_TYPE_WEP40) || (ieee->pairwise_key_type == KEY_TYPE_WEP104)) rtl92e_enable_hw_security_config(dev); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 566513338089..c7561e486359 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -29,7 +29,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, - .update_ratr_table = rtl92e_update_ratr_table, .irq_enable = rtl92e_enable_irq, .irq_disable = rtl92e_disable_irq, .irq_clear = rtl92e_clear_irq, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 083bba3dc51b..10ff4f9ec760 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -210,7 +210,6 @@ struct rtl819x_ops { bool (*rx_command_packet_handler)(struct net_device *dev, struct sk_buff *skb, struct rx_desc *pdesc); - void (*update_ratr_table)(struct net_device *dev); void (*irq_enable)(struct net_device *dev); void (*irq_disable)(struct net_device *dev); void (*irq_clear)(struct net_device *dev); -- GitLab From 555034bcd0afea9494cb0a87047329683bc8ed7e Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:35 +0100 Subject: [PATCH 0134/5631] staging: rtl8192e: Remove entry .irq_enable from struct rtl819x_ops Remove entry .irq_enable and replace it with function name rtl92e_enable_irq. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/c23a034632e06b0d9dcb98bd2311010561b6645e.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index c7561e486359..0b6d3b3c6415 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -29,7 +29,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, - .irq_enable = rtl92e_enable_irq, .irq_disable = rtl92e_disable_irq, .irq_clear = rtl92e_clear_irq, .rx_enable = rtl92e_enable_rx, @@ -247,7 +246,7 @@ void rtl92e_irq_enable(struct net_device *dev) priv->irq_enabled = 1; - priv->ops->irq_enable(dev); + rtl92e_enable_irq(dev); } void rtl92e_irq_disable(struct net_device *dev) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 10ff4f9ec760..6b5761374d54 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -210,7 +210,6 @@ struct rtl819x_ops { bool (*rx_command_packet_handler)(struct net_device *dev, struct sk_buff *skb, struct rx_desc *pdesc); - void (*irq_enable)(struct net_device *dev); void (*irq_disable)(struct net_device *dev); void (*irq_clear)(struct net_device *dev); void (*rx_enable)(struct net_device *dev); -- GitLab From bba6744fd3ffb7ed9a1606f336e55cac36cbc4a6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:43 +0100 Subject: [PATCH 0135/5631] staging: rtl8192e: Remove entry .irq_disable from struct rtl819x_ops Remove entry .irq_disable and replace it with function name rtl92e_disable_irq. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6d981b554a73ca965096e434d687b9827b0b96b2.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 0b6d3b3c6415..978088ab076c 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -29,7 +29,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, - .irq_disable = rtl92e_disable_irq, .irq_clear = rtl92e_clear_irq, .rx_enable = rtl92e_enable_rx, .tx_enable = rtl92e_enable_tx, @@ -253,7 +252,7 @@ void rtl92e_irq_disable(struct net_device *dev) { struct r8192_priv *priv = rtllib_priv(dev); - priv->ops->irq_disable(dev); + rtl92e_disable_irq(dev); priv->irq_enabled = 0; } diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 6b5761374d54..eb2b1e2ce4a6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -210,7 +210,6 @@ struct rtl819x_ops { bool (*rx_command_packet_handler)(struct net_device *dev, struct sk_buff *skb, struct rx_desc *pdesc); - void (*irq_disable)(struct net_device *dev); void (*irq_clear)(struct net_device *dev); void (*rx_enable)(struct net_device *dev); void (*tx_enable)(struct net_device *dev); -- GitLab From 026616a187a67d6472c61b917c300d381ccbb1cc Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 19 Feb 2023 22:16:49 +0100 Subject: [PATCH 0136/5631] staging: rtl8192e: Remove entry .rx_enable from struct rtl819x_ops Remove entry .rx_enable and replace it with function name rtl92e_enable_rx. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/8fd6c4b18cff8662215e27d299205646ce720a3b.1676840647.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 5 +---- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 978088ab076c..aa0456931b09 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -30,7 +30,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, .irq_clear = rtl92e_clear_irq, - .rx_enable = rtl92e_enable_rx, .tx_enable = rtl92e_enable_tx, .interrupt_recognized = rtl92e_ack_irq, .tx_check_stuck_handler = rtl92e_is_tx_stuck, @@ -1400,9 +1399,7 @@ static void _rtl92e_watchdog_timer_cb(struct timer_list *t) ****************************************************************************/ void rtl92e_rx_enable(struct net_device *dev) { - struct r8192_priv *priv = rtllib_priv(dev); - - priv->ops->rx_enable(dev); + rtl92e_enable_rx(dev); } void rtl92e_tx_enable(struct net_device *dev) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index eb2b1e2ce4a6..71958c7a4cbf 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -211,7 +211,6 @@ struct rtl819x_ops { struct sk_buff *skb, struct rx_desc *pdesc); void (*irq_clear)(struct net_device *dev); - void (*rx_enable)(struct net_device *dev); void (*tx_enable)(struct net_device *dev); void (*interrupt_recognized)(struct net_device *dev, u32 *p_inta, u32 *p_intb); -- GitLab From 45554ebbdad590733e9e8a0479e965feaa94abff Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:52:55 +0100 Subject: [PATCH 0137/5631] staging: rtl8192e: Remove entry .tx_enable from struct rtl819x_ops Remove entry .tx_enable and replace it with function name rtl92e_enable_tx. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/76955e787fd161dea83d10e81054fafb3b334b5c.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index aa0456931b09..f1cde3fc8634 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -30,7 +30,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, .irq_clear = rtl92e_clear_irq, - .tx_enable = rtl92e_enable_tx, .interrupt_recognized = rtl92e_ack_irq, .tx_check_stuck_handler = rtl92e_is_tx_stuck, .rx_check_stuck_handler = rtl92e_is_rx_stuck, @@ -1406,7 +1405,7 @@ void rtl92e_tx_enable(struct net_device *dev) { struct r8192_priv *priv = rtllib_priv(dev); - priv->ops->tx_enable(dev); + rtl92e_enable_tx(dev); rtllib_reset_queue(priv->rtllib); } diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 71958c7a4cbf..79281c077182 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -211,7 +211,6 @@ struct rtl819x_ops { struct sk_buff *skb, struct rx_desc *pdesc); void (*irq_clear)(struct net_device *dev); - void (*tx_enable)(struct net_device *dev); void (*interrupt_recognized)(struct net_device *dev, u32 *p_inta, u32 *p_intb); bool (*tx_check_stuck_handler)(struct net_device *dev); -- GitLab From 302c42c556ce29470414b66abb00b8f82c3c9bc8 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:03 +0100 Subject: [PATCH 0138/5631] staging: rtl8192e: Remove entry .interrupt_re.. from struct rtl819x_ops Remove entry .interrupt_recognized and replace it with function name rtl92e_ack_irq. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/a972ff8963b426f20651810b5161c8759ffa2d05.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 2 -- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index f1cde3fc8634..3323bdf564ee 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -30,7 +30,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, .irq_clear = rtl92e_clear_irq, - .interrupt_recognized = rtl92e_ack_irq, .tx_check_stuck_handler = rtl92e_is_tx_stuck, .rx_check_stuck_handler = rtl92e_is_rx_stuck, }; @@ -2103,7 +2102,7 @@ static irqreturn_t _rtl92e_irq(int irq, void *netdev) spin_lock_irqsave(&priv->irq_th_lock, flags); - priv->ops->interrupt_recognized(dev, &inta, &intb); + rtl92e_ack_irq(dev, &inta, &intb); if (!inta) { spin_unlock_irqrestore(&priv->irq_th_lock, flags); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 79281c077182..d3558bf6ce23 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -211,8 +211,6 @@ struct rtl819x_ops { struct sk_buff *skb, struct rx_desc *pdesc); void (*irq_clear)(struct net_device *dev); - void (*interrupt_recognized)(struct net_device *dev, - u32 *p_inta, u32 *p_intb); bool (*tx_check_stuck_handler)(struct net_device *dev); bool (*rx_check_stuck_handler)(struct net_device *dev); }; -- GitLab From e1ac4b672fd2adcfc4ae19de29ae29e07f701376 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:11 +0100 Subject: [PATCH 0139/5631] staging: rtl8192e: Remove entry .tx_check_stuc.. from struct rtl819x_ops Remove entry .tx_check_stuck_handler and replace it with function name rtl92e_is_tx_stuck. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/f58cc7b39f4a6bce0606bdd90a706b35b87d8256.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 3323bdf564ee..410c03833b9f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -30,7 +30,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, .irq_clear = rtl92e_clear_irq, - .tx_check_stuck_handler = rtl92e_is_tx_stuck, .rx_check_stuck_handler = rtl92e_is_rx_stuck, }; @@ -1055,7 +1054,7 @@ static enum reset_type _rtl92e_tx_check_stuck(struct net_device *dev) spin_unlock_irqrestore(&priv->irq_th_lock, flags); if (bCheckFwTxCnt) { - if (priv->ops->tx_check_stuck_handler(dev)) + if (rtl92e_is_tx_stuck(dev)) return RESET_TYPE_SILENT; } diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index d3558bf6ce23..87be8aaa7822 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -211,7 +211,6 @@ struct rtl819x_ops { struct sk_buff *skb, struct rx_desc *pdesc); void (*irq_clear)(struct net_device *dev); - bool (*tx_check_stuck_handler)(struct net_device *dev); bool (*rx_check_stuck_handler)(struct net_device *dev); }; -- GitLab From 3caa21422f62d4dffb70949a35a9b9f0b4855f63 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:17 +0100 Subject: [PATCH 0140/5631] staging: rtl8192e: Remove entry .rx_check_stuc.. from struct rtl819x_ops Remove entry .rx_check_stuck_handler and replace it with function name rtl92e_is_rx_stuck. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6538f1e158664837f6d1e7a20583ff20fc4f1403.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 5 +---- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 410c03833b9f..15eab612b08f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -30,7 +30,6 @@ static const struct rtl819x_ops rtl819xp_ops = { .link_change = rtl92e_link_change, .rx_command_packet_handler = NULL, .irq_clear = rtl92e_clear_irq, - .rx_check_stuck_handler = rtl92e_is_rx_stuck, }; static struct pci_device_id rtl8192_pci_id_tbl[] = { @@ -1063,9 +1062,7 @@ static enum reset_type _rtl92e_tx_check_stuck(struct net_device *dev) static enum reset_type _rtl92e_rx_check_stuck(struct net_device *dev) { - struct r8192_priv *priv = rtllib_priv(dev); - - if (priv->ops->rx_check_stuck_handler(dev)) + if (rtl92e_is_rx_stuck(dev)) return RESET_TYPE_SILENT; return RESET_TYPE_NORESET; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 87be8aaa7822..43e1c651e6d2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -211,7 +211,6 @@ struct rtl819x_ops { struct sk_buff *skb, struct rx_desc *pdesc); void (*irq_clear)(struct net_device *dev); - bool (*rx_check_stuck_handler)(struct net_device *dev); }; struct r8192_priv { -- GitLab From 210b02c8f1c9c6ac672558384709f561a3aeec01 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:24 +0100 Subject: [PATCH 0141/5631] staging: rtl8192e: Remove dead code from struct rtl819x_ops Remove entry .rx_command_packet_handler, .irq_clear and .init_before_adapter_start as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/93427f1b2ad5841451d7e8cc8a621d7eff8cd916.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 2 -- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 5 ----- 2 files changed, 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 15eab612b08f..0c1eb75f37f6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -28,8 +28,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, .link_change = rtl92e_link_change, - .rx_command_packet_handler = NULL, - .irq_clear = rtl92e_clear_irq, }; static struct pci_device_id rtl8192_pci_id_tbl[] = { diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 43e1c651e6d2..e572915c1fd2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -205,12 +205,7 @@ struct rtl8192_tx_ring { struct rtl819x_ops { enum nic_t nic_type; - void (*init_before_adapter_start)(struct net_device *dev); void (*link_change)(struct net_device *dev); - bool (*rx_command_packet_handler)(struct net_device *dev, - struct sk_buff *skb, - struct rx_desc *pdesc); - void (*irq_clear)(struct net_device *dev); }; struct r8192_priv { -- GitLab From 5ac30dd269df943bfd37fbd72e09a07f2bf450c5 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:32 +0100 Subject: [PATCH 0142/5631] staging: rtl8192e: Remove entry .link_change from struct rtl819x_ops Remove entry .link_change and replace it with function name rtl92e_link_change. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/9b451317eb4c13db007476c30212ffb09ced2356.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 0c1eb75f37f6..2d2f9d4a0ff5 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -27,7 +27,6 @@ static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { .nic_type = NIC_8192E, - .link_change = rtl92e_link_change, }; static struct pci_device_id rtl8192_pci_id_tbl[] = { @@ -762,7 +761,7 @@ static void _rtl92e_init_priv_handler(struct net_device *dev) priv->rtllib->softmac_hard_start_xmit = _rtl92e_hard_start_xmit; priv->rtllib->set_chan = _rtl92e_set_chan; - priv->rtllib->link_change = priv->ops->link_change; + priv->rtllib->link_change = rtl92e_link_change; priv->rtllib->softmac_data_hard_start_xmit = _rtl92e_hard_data_xmit; priv->rtllib->check_nic_enough_desc = _rtl92e_check_nic_enough_desc; priv->rtllib->handle_assoc_response = _rtl92e_handle_assoc_response; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index e572915c1fd2..fa72f8891409 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -205,7 +205,6 @@ struct rtl8192_tx_ring { struct rtl819x_ops { enum nic_t nic_type; - void (*link_change)(struct net_device *dev); }; struct r8192_priv { -- GitLab From 0296ef43567a292f171708769660705385db77a6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 21 Feb 2023 21:53:43 +0100 Subject: [PATCH 0143/5631] staging: rtl8192e: Remove entry .nic_type from struct rtl819x_ops Remove unchanged entry .nic_type and replace it with constant NIC_8192E. This increases readability of the code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/f1fd37a2d2b90bef8caac31a98f3eeff404b3095.1677010997.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_pci.c | 6 +++--- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 2d2f9d4a0ff5..044cab649ff1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -26,7 +26,6 @@ int hwwep = 1; static char *ifname = "wlan%d"; static const struct rtl819x_ops rtl819xp_ops = { - .nic_type = NIC_8192E, }; static struct pci_device_id rtl8192_pci_id_tbl[] = { diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index fa72f8891409..f75cc96052d9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -204,7 +204,6 @@ struct rtl8192_tx_ring { }; struct rtl819x_ops { - enum nic_t nic_type; }; struct r8192_priv { diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_pci.c b/drivers/staging/rtl8192e/rtl8192e/rtl_pci.c index 81e1bb856c60..0bc3e013001e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_pci.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_pci.c @@ -39,7 +39,7 @@ bool rtl92e_check_adapter(struct pci_dev *pdev, struct net_device *dev) revision_id = pdev->revision; pci_read_config_word(pdev, 0x3C, &irq_line); - priv->card_8192 = priv->ops->nic_type; + priv->card_8192 = NIC_8192E; if (device_id == 0x8192) { switch (revision_id) { @@ -64,10 +64,10 @@ bool rtl92e_check_adapter(struct pci_dev *pdev, struct net_device *dev) } } - if (priv->ops->nic_type != priv->card_8192) { + if (priv->card_8192 != NIC_8192E) { dev_info(&pdev->dev, "Detect info(%x) and hardware info(%x) not match!\n", - priv->ops->nic_type, priv->card_8192); + NIC_8192E, priv->card_8192); dev_info(&pdev->dev, "Please select proper driver before install!!!!\n"); return false; -- GitLab From fda2093860df4812d69052a8cf4997e53853a340 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Thu, 23 Feb 2023 07:47:21 +0100 Subject: [PATCH 0144/5631] staging: rtl8192e: Replace macro RTL_PCI_DEVICE with PCI_DEVICE Replace macro RTL_PCI_DEVICE with PCI_DEVICE to get rid of rtl819xp_ops which is empty. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/8b45ee783fa91196b7c9d6fc840a189496afd2f4.1677133271.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 6 +++--- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 5 ----- 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 044cab649ff1..f5a155d1a81a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -29,9 +29,9 @@ static const struct rtl819x_ops rtl819xp_ops = { }; static struct pci_device_id rtl8192_pci_id_tbl[] = { - {RTL_PCI_DEVICE(0x10ec, 0x8192, rtl819xp_ops)}, - {RTL_PCI_DEVICE(0x07aa, 0x0044, rtl819xp_ops)}, - {RTL_PCI_DEVICE(0x07aa, 0x0047, rtl819xp_ops)}, + {PCI_DEVICE(0x10ec, 0x8192)}, + {PCI_DEVICE(0x07aa, 0x0044)}, + {PCI_DEVICE(0x07aa, 0x0047)}, {} }; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index f75cc96052d9..c2a4b2ae6a81 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -55,11 +55,6 @@ #define IS_HARDWARE_TYPE_8192SE(_priv) \ (((struct r8192_priv *)rtllib_priv(dev))->card_8192 == NIC_8192SE) -#define RTL_PCI_DEVICE(vend, dev, cfg) \ - .vendor = (vend), .device = (dev), \ - .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, \ - .driver_data = (kernel_ulong_t)&(cfg) - #define TOTAL_CAM_ENTRY 32 #define CAM_CONTENT_COUNT 8 -- GitLab From 5e2b6593f27052ca997ecf822f62b5a301a25b78 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Thu, 23 Feb 2023 07:47:28 +0100 Subject: [PATCH 0145/5631] staging: rtl8192e: Remove empty struct rtl819x_ops Remove empty struct rtl819x_ops as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/31b5b0ba88d7b07b0407956d56446e8f0e62e3e7.1677133271.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 6 ------ drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 4 ---- 2 files changed, 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index f5a155d1a81a..718d69b4ce16 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -25,9 +25,6 @@ int hwwep = 1; static char *ifname = "wlan%d"; -static const struct rtl819x_ops rtl819xp_ops = { -}; - static struct pci_device_id rtl8192_pci_id_tbl[] = { {PCI_DEVICE(0x10ec, 0x8192)}, {PCI_DEVICE(0x07aa, 0x0044)}, @@ -2190,7 +2187,6 @@ static int _rtl92e_pci_probe(struct pci_dev *pdev, unsigned long ioaddr = 0; struct net_device *dev = NULL; struct r8192_priv *priv = NULL; - struct rtl819x_ops *ops = (struct rtl819x_ops *)(id->driver_data); unsigned long pmem_start, pmem_len, pmem_flags; int err = -ENOMEM; u8 revision_id; @@ -2257,8 +2253,6 @@ static int _rtl92e_pci_probe(struct pci_dev *pdev, if (pdev->device == 0x8192 && revision_id == 0x10) goto err_unmap; - priv->ops = ops; - if (!rtl92e_check_adapter(pdev, dev)) goto err_unmap; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index c2a4b2ae6a81..c8816c44ca51 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -198,9 +198,6 @@ struct rtl8192_tx_ring { struct sk_buff_head queue; }; -struct rtl819x_ops { -}; - struct r8192_priv { struct pci_dev *pdev; struct pci_dev *bridge_pdev; @@ -218,7 +215,6 @@ struct r8192_priv { struct delayed_work txpower_tracking_wq; struct delayed_work rfpath_check_wq; struct delayed_work gpio_change_rf_wq; - struct rtl819x_ops *ops; struct rtllib_device *rtllib; struct work_struct reset_wq; -- GitLab From 237fea2f2dc618cc89b49c2713468f86cab63ed6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Feb 2023 19:20:26 +0100 Subject: [PATCH 0146/5631] staging: rtl8192e: Remove checks of pointer to handle_a.. and handle_b.. Function pointers of handle_assoc_response and handle_beacon is set while executing the probe function. Therefore a NULL pointer check is not required. Remove checks as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/5c0fd114c24616bc03271ccb0a72a6bc68e45d61.1677345331.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 4 +--- drivers/staging/rtl8192e/rtllib_softmac.c | 6 ++---- 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 669e74a67190..35b36f7c0f28 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -2689,9 +2689,7 @@ static inline void rtllib_process_probe_response( is_same_network(&ieee->current_network, network, (network->ssid_len ? 1 : 0)) && (ieee->state == RTLLIB_LINKED)) { - if (ieee->handle_beacon != NULL) - ieee->handle_beacon(ieee->dev, beacon, - &ieee->current_network); + ieee->handle_beacon(ieee->dev, beacon, &ieee->current_network); } free_network: kfree(network); diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index 2552aa089700..d697089e0cad 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -2241,10 +2241,8 @@ rtllib_rx_assoc_resp(struct rtllib_device *ieee, struct sk_buff *skb, memcpy(ieee->ht_info->PeerHTInfoBuf, network->bssht.bd_ht_info_buf, network->bssht.bd_ht_info_len); - if (ieee->handle_assoc_response != NULL) - ieee->handle_assoc_response(ieee->dev, - (struct rtllib_assoc_response_frame *)header, - network); + ieee->handle_assoc_response(ieee->dev, + (struct rtllib_assoc_response_frame *)header, network); } kfree(network); -- GitLab From f7cc87391a203ab713877fdbce2956ced91b9ed6 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Feb 2023 19:20:33 +0100 Subject: [PATCH 0147/5631] staging: rtl8192e: Remove checks of pointer to LeisureP.. and start_se.. Function pointers of LeisurePSLeave and start_send_beacons is set while executing the probe function. Therefore a NULL pointer check is not required. Remove checks as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/cd828bb1c8dfbb6d2a85d770c82afbb9889e0ea2.1677345331.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 3 +-- drivers/staging/rtl8192e/rtllib_softmac.c | 3 +-- drivers/staging/rtl8192e/rtllib_softmac_wx.c | 3 +-- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 35b36f7c0f28..c394c21beefb 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -1214,8 +1214,7 @@ static void rtllib_rx_check_leave_lps(struct rtllib_device *ieee, u8 unicast, if (((ieee->link_detect_info.NumRxUnicastOkInPeriod + ieee->link_detect_info.NumTxOkInPeriod) > 8) || (ieee->link_detect_info.NumRxUnicastOkInPeriod > 2)) { - if (ieee->LeisurePSLeave) - ieee->LeisurePSLeave(ieee->dev); + ieee->LeisurePSLeave(ieee->dev); } } } diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index d697089e0cad..b06baf5ff6d4 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -669,8 +669,7 @@ EXPORT_SYMBOL(rtllib_stop_send_beacons); void rtllib_start_send_beacons(struct rtllib_device *ieee) { - if (ieee->start_send_beacons) - ieee->start_send_beacons(ieee->dev); + ieee->start_send_beacons(ieee->dev); if (ieee->softmac_features & IEEE_SOFTMAC_BEACONS) rtllib_beacons_start(ieee); } diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c index 06f3d75dc102..f90764d1d9ab 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c +++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c @@ -340,8 +340,7 @@ void rtllib_wx_sync_scan_wq(void *data) chan = ieee->current_network.channel; - if (ieee->LeisurePSLeave) - ieee->LeisurePSLeave(ieee->dev); + ieee->LeisurePSLeave(ieee->dev); /* notify AP to be in PS mode */ rtllib_sta_ps_send_null_frame(ieee, 1); rtllib_sta_ps_send_null_frame(ieee, 1); -- GitLab From 997f7f0c2c32fa7679673242eb67b970636c7aeb Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Feb 2023 19:20:41 +0100 Subject: [PATCH 0148/5631] staging: rtl8192e: Remove checks of pointer to stop_send.. and rtllib_.. Function pointers of stop_send_beacons and rtllib_ips_leave_wq is set while executing the probe function. Therefore a NULL pointer check is not required. Remove checks as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/f12e9167499344059f77991d2058c050bbe744d2.1677345331.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_softmac.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index b06baf5ff6d4..7b73c5df5e2a 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -659,8 +659,7 @@ static void rtllib_beacons_stop(struct rtllib_device *ieee) void rtllib_stop_send_beacons(struct rtllib_device *ieee) { - if (ieee->stop_send_beacons) - ieee->stop_send_beacons(ieee->dev); + ieee->stop_send_beacons(ieee->dev); if (ieee->softmac_features & IEEE_SOFTMAC_BEACONS) rtllib_beacons_stop(ieee); } @@ -728,8 +727,7 @@ EXPORT_SYMBOL(rtllib_act_scanning); /* called with ieee->lock held */ static void rtllib_start_scan(struct rtllib_device *ieee) { - if (ieee->rtllib_ips_leave_wq != NULL) - ieee->rtllib_ips_leave_wq(ieee->dev); + ieee->rtllib_ips_leave_wq(ieee->dev); if (IS_DOT11D_ENABLE(ieee)) { if (IS_COUNTRY_IE_VALID(ieee)) @@ -1584,8 +1582,7 @@ static void rtllib_associate_procedure_wq(void *data) rtllib_stop_scan(ieee); HTSetConnectBwMode(ieee, HT_CHANNEL_WIDTH_20, HT_EXTCHNL_OFFSET_NO_EXT); if (ieee->rf_power_state == rf_off) { - if (ieee->rtllib_ips_leave_wq != NULL) - ieee->rtllib_ips_leave_wq(ieee->dev); + ieee->rtllib_ips_leave_wq(ieee->dev); mutex_unlock(&ieee->wx_mutex); return; } -- GitLab From 4bd92a7714d19413eb477d4c02fbca4aae27abb5 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Feb 2023 19:20:50 +0100 Subject: [PATCH 0149/5631] staging: rtl8192e: Remove checks of pointer to rtllib.. and ScanOpera.. Function pointers of rtllib_ips_leave and ScanOperationBackupHandler is set while executing the probe function. Therefore a NULL pointer check is not required. Remove checks as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/8b01cbfaad2db4666b98bfeae29dd429d8c6cd07.1677345331.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_wx.c | 8 ++------ drivers/staging/rtl8192e/rtllib_softmac.c | 6 ++---- drivers/staging/rtl8192e/rtllib_softmac_wx.c | 6 ++---- 4 files changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 718d69b4ce16..47feb4248d25 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -703,8 +703,7 @@ static int _rtl92e_sta_down(struct net_device *dev, bool shutdownrf) if (priv->up == 0) return -1; - if (priv->rtllib->rtllib_ips_leave) - priv->rtllib->rtllib_ips_leave(dev); + priv->rtllib->rtllib_ips_leave(dev); if (priv->rtllib->state == RTLLIB_LINKED) rtl92e_leisure_ps_leave(dev); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c index bf0030144e5d..cb28288a618b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_wx.c @@ -432,15 +432,11 @@ static int _rtl92e_wx_set_scan(struct net_device *dev, if (priv->rtllib->rf_power_state != rf_off) { priv->rtllib->actscanning = true; - if (ieee->ScanOperationBackupHandler) - ieee->ScanOperationBackupHandler(ieee->dev, - SCAN_OPT_BACKUP); + ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_BACKUP); rtllib_start_scan_syncro(priv->rtllib, 0); - if (ieee->ScanOperationBackupHandler) - ieee->ScanOperationBackupHandler(ieee->dev, - SCAN_OPT_RESTORE); + ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_RESTORE); } ret = 0; } else { diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index 7b73c5df5e2a..4923423aa85b 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -1572,8 +1572,7 @@ static void rtllib_associate_procedure_wq(void *data) struct rtllib_device, associate_procedure_wq); rtllib_stop_scan_syncro(ieee); - if (ieee->rtllib_ips_leave != NULL) - ieee->rtllib_ips_leave(ieee->dev); + ieee->rtllib_ips_leave(ieee->dev); mutex_lock(&ieee->wx_mutex); if (ieee->data_hard_stop) @@ -2850,8 +2849,7 @@ void rtllib_stop_protocol(struct rtllib_device *ieee, u8 shutdown) if (shutdown) { ieee->proto_started = 0; ieee->proto_stoppping = 1; - if (ieee->rtllib_ips_leave != NULL) - ieee->rtllib_ips_leave(ieee->dev); + ieee->rtllib_ips_leave(ieee->dev); } rtllib_stop_send_beacons(ieee); diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c index f90764d1d9ab..06f1d6de5cc7 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c +++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c @@ -355,8 +355,7 @@ void rtllib_wx_sync_scan_wq(void *data) /* wait for ps packet to be kicked out successfully */ msleep(50); - if (ieee->ScanOperationBackupHandler) - ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_BACKUP); + ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_BACKUP); if (ieee->ht_info->bCurrentHTSupport && ieee->ht_info->enable_ht && ieee->ht_info->bCurBW40MHz) { @@ -381,8 +380,7 @@ void rtllib_wx_sync_scan_wq(void *data) ieee->set_chan(ieee->dev, chan); } - if (ieee->ScanOperationBackupHandler) - ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_RESTORE); + ieee->ScanOperationBackupHandler(ieee->dev, SCAN_OPT_RESTORE); ieee->state = RTLLIB_LINKED; ieee->link_change(ieee->dev); -- GitLab From fa0dcd5909ad9168bc51ad4f577f3631803d2ab2 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Thu, 2 Mar 2023 20:14:57 +0100 Subject: [PATCH 0150/5631] staging: rtl8192e: Change filename r8192E_hwimg.x to table.x Change r8192E_hwimg.c to table.c and r8192E_hwimg.h to table.h to adapt filenames from drivers/net/wireless/realtek/rtlwifi rtl8192ee and rtl8192se. Task is from TODO file. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230302191457.GA17628@matrix-ESPRIMO-P710 Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/Makefile | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_firmware.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/{r8192E_hwimg.c => table.c} | 2 +- drivers/staging/rtl8192e/rtl8192e/{r8192E_hwimg.h => table.h} | 0 5 files changed, 4 insertions(+), 4 deletions(-) rename drivers/staging/rtl8192e/rtl8192e/{r8192E_hwimg.c => table.c} (99%) rename drivers/staging/rtl8192e/rtl8192e/{r8192E_hwimg.h => table.h} (100%) diff --git a/drivers/staging/rtl8192e/rtl8192e/Makefile b/drivers/staging/rtl8192e/rtl8192e/Makefile index 75e6ec510555..a442d79ea71e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/Makefile +++ b/drivers/staging/rtl8192e/rtl8192e/Makefile @@ -4,7 +4,7 @@ r8192e_pci-objs := \ r8192E_phy.o \ r8192E_firmware.o \ r8192E_cmdpkt.o \ - r8192E_hwimg.o \ + table.o \ r8190P_rtl8256.o \ rtl_cam.o \ rtl_core.o \ diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_firmware.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_firmware.c index b011ec8c8a41..ddf998cf2041 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_firmware.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_firmware.c @@ -6,7 +6,7 @@ */ #include "rtl_core.h" #include "r8192E_hw.h" -#include "r8192E_hwimg.h" +#include "table.h" #include "r8192E_firmware.h" #include "r8192E_cmdpkt.h" #include diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index c6cbdea6d5b2..6388f1220575 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -12,7 +12,7 @@ #include "r8192E_phy.h" #include "rtl_dm.h" -#include "r8192E_hwimg.h" +#include "table.h" static u32 RF_CHANNEL_TABLE_ZEBRA[] = { 0, diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_hwimg.c b/drivers/staging/rtl8192e/rtl8192e/table.c similarity index 99% rename from drivers/staging/rtl8192e/rtl8192e/r8192E_hwimg.c rename to drivers/staging/rtl8192e/rtl8192e/table.c index e6fce749e65b..1f80dbeb17b5 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_hwimg.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -4,7 +4,7 @@ * * Contact Information: wlanfae */ -#include "r8192E_hwimg.h" +#include "table.h" u32 Rtl8192PciEPHY_REGArray[PHY_REGArrayLengthPciE] = {0x0,}; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_hwimg.h b/drivers/staging/rtl8192e/rtl8192e/table.h similarity index 100% rename from drivers/staging/rtl8192e/rtl8192e/r8192E_hwimg.h rename to drivers/staging/rtl8192e/rtl8192e/table.h -- GitLab From 718e16d6fb5552817ee2cdba56b2fff20e3308e1 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 4 Mar 2023 20:13:22 +0100 Subject: [PATCH 0151/5631] staging: rtl8192e: Remove empty Array Rtl8192PciEPHY_REGArray Remove empty array Rtl8192PciEPHY_REGArray and the code where it is used because it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/511bd239bf033dca3efcc64a640d5343c98fa897.1677955334.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 5 +---- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- drivers/staging/rtl8192e/rtl8192e/table.c | 2 -- drivers/staging/rtl8192e/rtl8192e/table.h | 2 -- 4 files changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 6388f1220575..385ceb3a9636 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -334,10 +334,7 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) AGCTAB_ArrayLen = AGCTAB_ArrayLength; Rtl819XAGCTAB_Array_Table = Rtl819XAGCTAB_Array; - if (priv->rf_type == RF_2T4R) { - PHY_REGArrayLen = PHY_REGArrayLength; - Rtl819XPHY_REGArray_Table = Rtl819XPHY_REGArray; - } else if (priv->rf_type == RF_1T2R) { + if (priv->rf_type == RF_1T2R) { PHY_REGArrayLen = PHY_REG_1T2RArrayLength; Rtl819XPHY_REGArray_Table = Rtl819XPHY_REG_1T2RArray; } diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 75629f5df954..561a4c874fe3 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -16,7 +16,6 @@ #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE #define RadioC_ArrayLength RadioC_ArrayLengthPciE #define RadioD_ArrayLength RadioD_ArrayLengthPciE -#define PHY_REGArrayLength PHY_REGArrayLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE #define Rtl819XMACPHY_Array_PG Rtl8192PciEMACPHY_Array_PG @@ -26,7 +25,6 @@ #define Rtl819XRadioC_Array Rtl8192PciERadioC_Array #define Rtl819XRadioD_Array Rtl8192PciERadioD_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array -#define Rtl819XPHY_REGArray Rtl8192PciEPHY_REGArray #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray extern u32 rtl819XAGCTAB_Array[]; diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 1f80dbeb17b5..d04608d99cbf 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -6,8 +6,6 @@ */ #include "table.h" -u32 Rtl8192PciEPHY_REGArray[PHY_REGArrayLengthPciE] = {0x0,}; - u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE] = { 0x800, 0x00000000, 0x804, 0x00000001, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 7d63f5a5c1b7..177fe2173430 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -11,8 +11,6 @@ #include -#define PHY_REGArrayLengthPciE 1 -extern u32 Rtl8192PciEPHY_REGArray[PHY_REGArrayLengthPciE]; #define PHY_REG_1T2RArrayLengthPciE 296 extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; #define RadioA_ArrayLengthPciE 246 -- GitLab From 50cbec61ad7f66ecbe6786f8e03351454e17ee9e Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 4 Mar 2023 20:13:41 +0100 Subject: [PATCH 0152/5631] staging: rtl8192e: Remove conditions for RF_2T4R Remove conditions for RF_2T4R because hardware that uses RF_2T4R does not exist. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/af7dcd620fdad63b2f324d626f1c97601895823a.1677955334.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_dev.c | 3 +- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 21 +--- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 109 ++++-------------- drivers/staging/rtl8192e/rtllib.h | 1 - 4 files changed, 25 insertions(+), 109 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 1e307789ee93..8edfaaeda910 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -353,8 +353,7 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) if (tempval&0x80) priv->rf_type = RF_1T2R; - else - priv->rf_type = RF_2T4R; + } else { priv->eeprom_legacy_ht_tx_pwr_diff = 0x04; } diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 385ceb3a9636..35ca01ab65ff 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -52,9 +52,7 @@ u8 rtl92e_is_legal_rf_path(struct net_device *dev, u32 eRFPath) u8 ret = 1; struct r8192_priv *priv = rtllib_priv(dev); - if (priv->rf_type == RF_2T4R) - ret = 0; - else if (priv->rf_type == RF_1T2R) { + if (priv->rf_type == RF_1T2R) { if (eRFPath == RF90_PATH_A || eRFPath == RF90_PATH_B) ret = 1; else if (eRFPath == RF90_PATH_C || eRFPath == RF90_PATH_D) @@ -531,12 +529,7 @@ static bool _rtl92e_bb_config_para_file(struct net_device *dev) _rtl92e_phy_config_bb(dev, BB_CONFIG_AGC_TAB); if (priv->ic_cut > VERSION_8190_BD) { - if (priv->rf_type == RF_2T4R) - dwRegValue = priv->antenna_tx_pwr_diff[2] << 8 | - priv->antenna_tx_pwr_diff[1] << 4 | - priv->antenna_tx_pwr_diff[0]; - else - dwRegValue = 0x0; + dwRegValue = 0x0; rtl92e_set_bb_reg(dev, rFPGA0_TxGainStage, (bXBTxAGC|bXCTxAGC|bXDTxAGC), dwRegValue); @@ -587,16 +580,8 @@ void rtl92e_set_tx_power(struct net_device *dev, u8 channel) if (priv->epromtype == EEPROM_93C46) { powerlevel = priv->tx_pwr_level_cck[channel - 1]; powerlevelOFDM24G = priv->tx_pwr_level_ofdm_24g[channel - 1]; - } else if (priv->epromtype == EEPROM_93C56) { - if (priv->rf_type == RF_2T4R) { - priv->antenna_tx_pwr_diff[2] = 0; - priv->antenna_tx_pwr_diff[1] = 0; - priv->antenna_tx_pwr_diff[0] = 0; - - rtl92e_set_bb_reg(dev, rFPGA0_TxGainStage, - (bXBTxAGC | bXCTxAGC | bXDTxAGC), 0); - } } + switch (priv->rf_chip) { case RF_8225: break; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index d8455b23e555..a1bd119b8983 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -297,14 +297,7 @@ void rtl92e_init_adaptive_rate(struct net_device *dev) pra->ping_rssi_thresh_for_ra = 15; - if (priv->rf_type == RF_2T4R) { - pra->upper_rssi_threshold_ratr = 0x8f0f0000; - pra->middle_rssi_threshold_ratr = 0x8f0ff000; - pra->low_rssi_threshold_ratr = 0x8f0ff001; - pra->low_rssi_threshold_ratr_40M = 0x8f0ff005; - pra->low_rssi_threshold_ratr_20M = 0x8f0ff001; - pra->ping_rssi_ratr = 0x0000000d; - } else if (priv->rf_type == RF_1T2R) { + if (priv->rf_type == RF_1T2R) { pra->upper_rssi_threshold_ratr = 0x000fc000; pra->middle_rssi_threshold_ratr = 0x000ff000; pra->low_rssi_threshold_ratr = 0x000ff001; @@ -518,47 +511,18 @@ static void _rtl92e_dm_tx_update_tssi_weak_signal(struct net_device *dev, { struct r8192_priv *p = rtllib_priv(dev); - if (RF_Type == RF_2T4R) { - if ((p->rfa_txpowertrackingindex > 0) && - (p->rfc_txpowertrackingindex > 0)) { - p->rfa_txpowertrackingindex--; - if (p->rfa_txpowertrackingindex_real > 4) { - p->rfa_txpowertrackingindex_real--; - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); - } - - p->rfc_txpowertrackingindex--; - if (p->rfc_txpowertrackingindex_real > 4) { - p->rfc_txpowertrackingindex_real--; - rtl92e_set_bb_reg(dev, - rOFDM0_XCTxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfc_txpowertrackingindex_real]); - } - } else { - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[4]); + if (p->rfa_txpowertrackingindex > 0) { + p->rfa_txpowertrackingindex--; + if (p->rfa_txpowertrackingindex_real > 4) { + p->rfa_txpowertrackingindex_real--; rtl92e_set_bb_reg(dev, - rOFDM0_XCTxIQImbalance, - bMaskDWord, dm_tx_bb_gain[4]); + rOFDM0_XATxIQImbalance, + bMaskDWord, + dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); } } else { - if (p->rfa_txpowertrackingindex > 0) { - p->rfa_txpowertrackingindex--; - if (p->rfa_txpowertrackingindex_real > 4) { - p->rfa_txpowertrackingindex_real--; - rtl92e_set_bb_reg(dev, - rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); - } - } else { - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, dm_tx_bb_gain[4]); - } + rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, + bMaskDWord, dm_tx_bb_gain[4]); } } @@ -567,39 +531,16 @@ static void _rtl92e_dm_tx_update_tssi_strong_signal(struct net_device *dev, { struct r8192_priv *p = rtllib_priv(dev); - if (RF_Type == RF_2T4R) { - if ((p->rfa_txpowertrackingindex < TX_BB_GAIN_TABLE_LEN - 1) && - (p->rfc_txpowertrackingindex < TX_BB_GAIN_TABLE_LEN - 1)) { - p->rfa_txpowertrackingindex++; - p->rfa_txpowertrackingindex_real++; - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); - p->rfc_txpowertrackingindex++; - p->rfc_txpowertrackingindex_real++; - rtl92e_set_bb_reg(dev, rOFDM0_XCTxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfc_txpowertrackingindex_real]); - } else { - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[TX_BB_GAIN_TABLE_LEN - 1]); - rtl92e_set_bb_reg(dev, rOFDM0_XCTxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[TX_BB_GAIN_TABLE_LEN - 1]); - } + if (p->rfa_txpowertrackingindex < (TX_BB_GAIN_TABLE_LEN - 1)) { + p->rfa_txpowertrackingindex++; + p->rfa_txpowertrackingindex_real++; + rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, + bMaskDWord, + dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); } else { - if (p->rfa_txpowertrackingindex < (TX_BB_GAIN_TABLE_LEN - 1)) { - p->rfa_txpowertrackingindex++; - p->rfa_txpowertrackingindex_real++; - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[p->rfa_txpowertrackingindex_real]); - } else { - rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, - bMaskDWord, - dm_tx_bb_gain[TX_BB_GAIN_TABLE_LEN - 1]); - } + rtl92e_set_bb_reg(dev, rOFDM0_XATxIQImbalance, + bMaskDWord, + dm_tx_bb_gain[TX_BB_GAIN_TABLE_LEN - 1]); } } @@ -705,13 +646,8 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) else _rtl92e_dm_tx_update_tssi_strong_signal(dev, RF_Type); - if (RF_Type == RF_2T4R) { - priv->cck_present_attn_diff - = priv->rfa_txpowertrackingindex - priv->rfa_txpowertracking_default; - } else { - priv->cck_present_attn_diff - = priv->rfa_txpowertrackingindex_real - priv->rfa_txpowertracking_default; - } + priv->cck_present_attn_diff + = priv->rfa_txpowertrackingindex_real - priv->rfa_txpowertracking_default; if (priv->current_chnl_bw == HT_CHANNEL_WIDTH_20) priv->cck_present_attn = @@ -1765,9 +1701,6 @@ static void _rtl92e_dm_rx_path_sel_byrssi(struct net_device *dev) static u8 disabled_rf_cnt, cck_Rx_Path_initialized; u8 update_cck_rx_path; - if (priv->rf_type != RF_2T4R) - return; - if (!cck_Rx_Path_initialized) { dm_rx_path_sel_table.cck_rx_path = (rtl92e_readb(dev, 0xa07)&0xf); cck_Rx_Path_initialized = 1; diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 1152fbf43383..8e5e29ce8f0d 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -451,7 +451,6 @@ enum led_ctl_mode { enum rt_rf_type_def { RF_1T2R = 0, - RF_2T4R, }; enum wireless_mode { -- GitLab From f5f7aaa87ffdfd1b0c57b7d35d744c4a46eebcfa Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 7 Mar 2023 22:01:06 +0100 Subject: [PATCH 0153/5631] staging: rtl8192e: Remove unused Array Rtl8192PciERadioC_Array The array Rtl8192PciERadioC_Array is only used in function rtl92e_config_rf_path which is only called in function rtl92e_config_rf. In function rtl92e_config_rf a termination condition for the loop is set to priv->num_total_rf_path = RTL819X_TOTAL_RF_PATH = 2. The loop is only executed with numbers 0 and 1 for eRFPath. So the function rtl92e_config_rf_path is only called with eRFPath for 0 and 1 and never with 2 that would make the "case RF90_PATH_C:" be called. Remove resulting dead code. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/ed1e0df7ed677c335340f42c1108e7b5c0f18462.1678222487.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 12 ------------ drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- drivers/staging/rtl8192e/rtl8192e/table.c | 3 --- drivers/staging/rtl8192e/rtl8192e/table.h | 2 -- 4 files changed, 19 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 35ca01ab65ff..fe0ef52c163a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -649,18 +649,6 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) bMask12Bits, Rtl819XRadioB_Array[i+1]); - } - break; - case RF90_PATH_C: - for (i = 0; i < RadioC_ArrayLength; i += 2) { - if (Rtl819XRadioC_Array[i] == 0xfe) { - msleep(100); - continue; - } - rtl92e_set_rf_reg(dev, eRFPath, Rtl819XRadioC_Array[i], - bMask12Bits, - Rtl819XRadioC_Array[i+1]); - } break; case RF90_PATH_D: diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 561a4c874fe3..6772ed300591 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -14,7 +14,6 @@ #define RadioA_ArrayLength RadioA_ArrayLengthPciE #define RadioB_ArrayLength RadioB_ArrayLengthPciE #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE -#define RadioC_ArrayLength RadioC_ArrayLengthPciE #define RadioD_ArrayLength RadioD_ArrayLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE @@ -22,7 +21,6 @@ #define Rtl819XMACPHY_Array Rtl8192PciEMACPHY_Array #define Rtl819XRadioA_Array Rtl8192PciERadioA_Array #define Rtl819XRadioB_Array Rtl8192PciERadioB_Array -#define Rtl819XRadioC_Array Rtl8192PciERadioC_Array #define Rtl819XRadioD_Array Rtl8192PciERadioD_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index d04608d99cbf..4e97ad4b8fd7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -325,9 +325,6 @@ u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE] = { 0x007, 0x00000700, }; -u32 Rtl8192PciERadioC_Array[RadioC_ArrayLengthPciE] = { - 0x0, }; - u32 Rtl8192PciERadioD_Array[RadioD_ArrayLengthPciE] = { 0x0, }; diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 177fe2173430..981e8b57d3de 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -17,8 +17,6 @@ extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; extern u32 Rtl8192PciERadioA_Array[RadioA_ArrayLengthPciE]; #define RadioB_ArrayLengthPciE 78 extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; -#define RadioC_ArrayLengthPciE 2 -extern u32 Rtl8192PciERadioC_Array[RadioC_ArrayLengthPciE]; #define RadioD_ArrayLengthPciE 2 extern u32 Rtl8192PciERadioD_Array[RadioD_ArrayLengthPciE]; #define MACPHY_ArrayLengthPciE 18 -- GitLab From 0a689b8241ae3a3d082d3ce706dfc6405fabe9d5 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 7 Mar 2023 22:01:25 +0100 Subject: [PATCH 0154/5631] staging: rtl8192e: Remove unused Array Rtl8192PciERadioD_Array The array Rtl8192PciERadioD_Array is only used in function rtl92e_config_rf_path which is only called in function rtl92e_config_rf. In function rtl92e_config_rf a termination condition for the loop is set to priv->num_total_rf_path = RTL819X_TOTAL_RF_PATH = 2. The loop is only executed with numbers 0 and 1 for eRFPath. So the function rtl92e_config_rf_path is only called with eRFPath for 0 and 1 and never with 3 that would make the "case RF90_PATH_D:" be called. Remove resulting dead code. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/608ced17b85ca321fdc0026c686e3c62a9d6d8cd.1678222487.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 12 ------------ drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- drivers/staging/rtl8192e/rtl8192e/table.c | 3 --- drivers/staging/rtl8192e/rtl8192e/table.h | 2 -- 4 files changed, 19 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index fe0ef52c163a..a9e83ba811b0 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -649,18 +649,6 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) bMask12Bits, Rtl819XRadioB_Array[i+1]); - } - break; - case RF90_PATH_D: - for (i = 0; i < RadioD_ArrayLength; i += 2) { - if (Rtl819XRadioD_Array[i] == 0xfe) { - msleep(100); - continue; - } - rtl92e_set_rf_reg(dev, eRFPath, Rtl819XRadioD_Array[i], - bMask12Bits, - Rtl819XRadioD_Array[i+1]); - } break; default: diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 6772ed300591..ac640033e843 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -14,14 +14,12 @@ #define RadioA_ArrayLength RadioA_ArrayLengthPciE #define RadioB_ArrayLength RadioB_ArrayLengthPciE #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE -#define RadioD_ArrayLength RadioD_ArrayLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE #define Rtl819XMACPHY_Array_PG Rtl8192PciEMACPHY_Array_PG #define Rtl819XMACPHY_Array Rtl8192PciEMACPHY_Array #define Rtl819XRadioA_Array Rtl8192PciERadioA_Array #define Rtl819XRadioB_Array Rtl8192PciERadioB_Array -#define Rtl819XRadioD_Array Rtl8192PciERadioD_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 4e97ad4b8fd7..7101061e3519 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -325,9 +325,6 @@ u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE] = { 0x007, 0x00000700, }; -u32 Rtl8192PciERadioD_Array[RadioD_ArrayLengthPciE] = { - 0x0, }; - u32 Rtl8192PciEMACPHY_Array[] = { 0x03c, 0xffff0000, 0x00000f0f, 0x340, 0xffffffff, 0x161a1a1a, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 981e8b57d3de..b6d4e9696452 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -17,8 +17,6 @@ extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; extern u32 Rtl8192PciERadioA_Array[RadioA_ArrayLengthPciE]; #define RadioB_ArrayLengthPciE 78 extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; -#define RadioD_ArrayLengthPciE 2 -extern u32 Rtl8192PciERadioD_Array[RadioD_ArrayLengthPciE]; #define MACPHY_ArrayLengthPciE 18 extern u32 Rtl8192PciEMACPHY_Array[MACPHY_ArrayLengthPciE]; #define MACPHY_Array_PGLengthPciE 30 -- GitLab From 142dbcf3b6a93ecfe8ccbee60c611175f5459c23 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 16 Feb 2023 10:42:52 -0800 Subject: [PATCH 0155/5631] mips/cpu: Expose play_dead()'s prototype definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include to make sure play_dead() matches its prototype going forward. Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Link: https://lkml.kernel.org/r/20230216184249.ogaqsaykottpxtcb@treble Signed-off-by: Josh Poimboeuf --- arch/mips/cavium-octeon/smp.c | 1 + arch/mips/kernel/smp-bmips.c | 2 ++ arch/mips/kernel/smp-cps.c | 1 + arch/mips/loongson64/smp.c | 1 + 4 files changed, 5 insertions(+) diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 89954f5f87fb..4212584e6efa 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -20,6 +20,7 @@ #include #include #include +#include #include diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index f5d7bfa3472a..51d5dae1d2f0 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -54,6 +54,8 @@ static void bmips_set_reset_vec(int cpu, u32 val); #ifdef CONFIG_SMP +#include + /* initial $sp, $gp - used by arch/mips/kernel/bmips_vec.S */ unsigned long bmips_smp_boot_sp; unsigned long bmips_smp_boot_gp; diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 4fc288bb85b9..00a0e2571768 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index 660e1de4412a..4e24b317e7cb 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include -- GitLab From a80ceed6c9c24088d7a2e3c414eae1fe88a8ccbe Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:44 -0800 Subject: [PATCH 0156/5631] mips/cpu: Make sure play_dead() doesn't return MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit play_dead() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/b195e4da190bb06b7d4af15d66ce6129e2347630.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/mips/kernel/smp-bmips.c | 2 ++ arch/mips/loongson64/smp.c | 1 + 2 files changed, 3 insertions(+) diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 51d5dae1d2f0..15466d4cf4a0 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -415,6 +415,8 @@ void __ref play_dead(void) " wait\n" " j bmips_secondary_reentry\n" : : : "memory"); + + BUG(); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index 4e24b317e7cb..df8d789ede3c 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -823,6 +823,7 @@ void play_dead(void) state_addr = &per_cpu(cpu_state, cpu); mb(); play_dead_at_ckseg1(state_addr); + BUG(); } static int loongson3_disable_clock(unsigned int cpu) -- GitLab From 9e57f049d1571db1dc77c69c87403defc9d3e5ae Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:45 -0800 Subject: [PATCH 0157/5631] mips/cpu: Mark play_dead() __noreturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Acked-by: Florian Fainelli Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/2897b51a9b8beb5b594fe66fb1d3a479ddd2a0e2.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/mips/include/asm/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 5d9ff61004ca..4eee29b7845c 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -88,7 +88,7 @@ static inline void __cpu_die(unsigned int cpu) mp_ops->cpu_die(cpu); } -extern void play_dead(void); +extern void __noreturn play_dead(void); #endif #ifdef CONFIG_KEXEC -- GitLab From 5e00d69cdef4cd1c737e6286a39f83ce20a91034 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:46 -0800 Subject: [PATCH 0158/5631] powerpc/cpu: Mark start_secondary_resume() __noreturn start_secondary_resume() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Acked-by: Michael Ellerman (powerpc) Reviewed-by: Christophe Leroy Link: https://lore.kernel.org/r/b6b2141f832d8cd8ade65f190d04b011cda5f9bb.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/powerpc/include/asm/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 6c6cb53d7045..aaaa576d0e15 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -67,7 +67,7 @@ void start_secondary(void *unused); extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); -extern void start_secondary_resume(void); +extern void __noreturn start_secondary_resume(void); extern void smp_generic_give_timebase(void); extern void smp_generic_take_timebase(void); -- GitLab From 243971885418fcf772f18019eb3fabadcf0205d1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:47 -0800 Subject: [PATCH 0159/5631] sh/cpu: Make sure play_dead() doesn't return play_dead() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Link: https://lore.kernel.org/r/d0c3ff5349adfe8fd227acc236ae2c278a05eb4c.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/sh/include/asm/smp-ops.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/include/asm/smp-ops.h b/arch/sh/include/asm/smp-ops.h index e27702130eb6..63866b1595a0 100644 --- a/arch/sh/include/asm/smp-ops.h +++ b/arch/sh/include/asm/smp-ops.h @@ -27,6 +27,7 @@ static inline void plat_smp_setup(void) static inline void play_dead(void) { mp_ops->play_dead(); + BUG(); } extern void register_smp_ops(struct plat_smp_ops *ops); -- GitLab From 1644b74192265875cdf37dadfa33f34e0ea4fcc8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:48 -0800 Subject: [PATCH 0160/5631] sh/cpu: Mark play_dead() __noreturn play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Link: https://lore.kernel.org/r/03549a74fad9f73576d57e6fc0b5102322f9cff4.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/sh/include/asm/smp-ops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/sh/include/asm/smp-ops.h b/arch/sh/include/asm/smp-ops.h index 63866b1595a0..97331fcb7b85 100644 --- a/arch/sh/include/asm/smp-ops.h +++ b/arch/sh/include/asm/smp-ops.h @@ -24,7 +24,7 @@ static inline void plat_smp_setup(void) mp_ops->smp_setup(); } -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { mp_ops->play_dead(); BUG(); @@ -43,7 +43,7 @@ static inline void register_smp_ops(struct plat_smp_ops *ops) { } -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { BUG(); } -- GitLab From fd49efb3c75475b65d7541ee40603498807ff110 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:49 -0800 Subject: [PATCH 0161/5631] sh/cpu: Expose arch_cpu_idle_dead()'s prototype definition Include to make sure arch_cpu_idle_dead() matches its prototype going forward. Link: https://lore.kernel.org/r/3d9661e97828fb464a48d4becf18f12604831903.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/sh/kernel/idle.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 3418c40f0099..114f0c4abeac 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -4,6 +4,7 @@ * * Copyright (C) 2002 - 2009 Paul Mundt */ +#include #include #include #include -- GitLab From b9952d5009440b01dedd793a57abbe6cfe10f995 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:50 -0800 Subject: [PATCH 0162/5631] sparc/cpu: Mark cpu_play_dead() __noreturn MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cpu_play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/847fdb53cc7124bb7c94e3e104e443a29be85184.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/sparc/include/asm/smp_64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index e75783b6abc4..505b6700805d 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -49,7 +49,7 @@ int hard_smp_processor_id(void); void smp_fill_in_cpu_possible_map(void); void smp_fill_in_sib_core_maps(void); -void cpu_play_dead(void); +void __noreturn cpu_play_dead(void); void smp_fetch_global_regs(void); void smp_fetch_global_pmu(void); -- GitLab From a02f50b573b3c90a3633a5ab67435fe4c0de144d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:51 -0800 Subject: [PATCH 0163/5631] x86/cpu: Make sure play_dead() doesn't return After commit 076cbf5d2163 ("x86/xen: don't let xen_pv_play_dead() return"), play_dead() never returns. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Link: https://lore.kernel.org/r/11e6ac1cf10f92967882926e3ac16287b50642f2.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/x86/include/asm/smp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index b4dbb20dab1a..8f628e08b25a 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -96,6 +96,7 @@ static inline void __cpu_die(unsigned int cpu) static inline void play_dead(void) { smp_ops.play_dead(); + BUG(); } static inline void smp_send_reschedule(int cpu) -- GitLab From eab89405b6b59947ee29cc21fb39ead66142c9b5 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:52 -0800 Subject: [PATCH 0164/5631] x86/cpu: Mark play_dead() __noreturn play_dead() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Link: https://lore.kernel.org/r/f3a069e6869c51ccfdda656b76882363bc9fcfa4.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/x86/include/asm/smp.h | 2 +- arch/x86/kernel/process.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 8f628e08b25a..e6d1d2810e38 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu) smp_ops.cpu_die(cpu); } -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { smp_ops.play_dead(); BUG(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b650cde3f64d..f1ec36caf1d8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -715,7 +715,7 @@ static bool x86_idle_set(void) } #ifndef CONFIG_SMP -static inline void play_dead(void) +static inline void __noreturn play_dead(void) { BUG(); } -- GitLab From d08e12e8126ec88d6cb1a7eb160d8d7b52c8699f Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:53 -0800 Subject: [PATCH 0165/5631] xtensa/cpu: Make sure cpu_die() doesn't return cpu_die() doesn't return. Make that more explicit with a BUG(). BUG() is preferable to unreachable() because BUG() is a more explicit failure mode and avoids undefined behavior like falling off the edge of the function into whatever code happens to be next. Link: https://lore.kernel.org/r/cca346b5c87693499e630291d78fb0bf12c24290.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/xtensa/kernel/smp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 4dc109dd6214..7bad78495536 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -341,6 +341,8 @@ void __ref cpu_die(void) __asm__ __volatile__( " movi a2, cpu_restart\n" " jx a2\n"); + + BUG(); } #endif /* CONFIG_HOTPLUG_CPU */ -- GitLab From 69dee6f0338a20c76a7bc61c0a6b59f25e1b25c8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:54 -0800 Subject: [PATCH 0166/5631] xtensa/cpu: Mark cpu_die() __noreturn cpu_die() doesn't return. Annotate it as such. By extension this also makes arch_cpu_idle_dead() noreturn. Acked-by: Max Filippov Link: https://lore.kernel.org/r/ad801544cab7c26a0f3bbf7cfefb67303f4cd866.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/xtensa/include/asm/smp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/xtensa/include/asm/smp.h b/arch/xtensa/include/asm/smp.h index 4e43f5643891..5dc5bf8cdd77 100644 --- a/arch/xtensa/include/asm/smp.h +++ b/arch/xtensa/include/asm/smp.h @@ -33,7 +33,7 @@ void show_ipi_list(struct seq_file *p, int prec); void __cpu_die(unsigned int cpu); int __cpu_disable(void); -void cpu_die(void); +void __noreturn cpu_die(void); void cpu_restart(void); #endif /* CONFIG_HOTPLUG_CPU */ -- GitLab From dfb0f170cadb03da4f408ae53cc2908120e1f90e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:55 -0800 Subject: [PATCH 0167/5631] sched/idle: Make sure weak version of arch_cpu_idle_dead() doesn't return arch_cpu_idle_dead() should never return. Make it so. Link: https://lore.kernel.org/r/cf5ad95eef50f7704bb30e7770c59bfe23372af7.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- kernel/sched/idle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index e9ef66be2870..56e152f06d0f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -75,7 +75,7 @@ static noinline int __cpuidle cpu_idle_poll(void) void __weak arch_cpu_idle_prepare(void) { } void __weak arch_cpu_idle_enter(void) { } void __weak arch_cpu_idle_exit(void) { } -void __weak arch_cpu_idle_dead(void) { } +void __weak arch_cpu_idle_dead(void) { while (1); } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; -- GitLab From 071c44e4278156f18a6a56958617223b6bffa6ab Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Feb 2023 23:05:58 -0800 Subject: [PATCH 0168/5631] sched/idle: Mark arch_cpu_idle_dead() __noreturn Before commit 076cbf5d2163 ("x86/xen: don't let xen_pv_play_dead() return"), in Xen, when a previously offlined CPU was brought back online, it unexpectedly resumed execution where it left off in the middle of the idle loop. There were some hacks to make that work, but the behavior was surprising as do_idle() doesn't expect an offlined CPU to return from the dead (in arch_cpu_idle_dead()). Now that Xen has been fixed, and the arch-specific implementations of arch_cpu_idle_dead() also don't return, give it a __noreturn attribute. This will cause the compiler to complain if an arch-specific implementation might return. It also improves code generation for both caller and callee. Also fixes the following warning: vmlinux.o: warning: objtool: do_idle+0x25f: unreachable instruction Reported-by: Paul E. McKenney Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/60d527353da8c99d4cf13b6473131d46719ed16d.1676358308.git.jpoimboe@kernel.org Signed-off-by: Josh Poimboeuf --- arch/alpha/kernel/process.c | 2 +- arch/arm/kernel/smp.c | 2 +- arch/arm64/kernel/process.c | 2 +- arch/csky/kernel/smp.c | 2 +- arch/ia64/kernel/process.c | 2 +- arch/loongarch/kernel/process.c | 2 +- arch/mips/kernel/process.c | 2 +- arch/parisc/kernel/process.c | 2 +- arch/powerpc/kernel/smp.c | 2 +- arch/riscv/kernel/cpu-hotplug.c | 2 +- arch/s390/kernel/idle.c | 2 +- arch/sh/kernel/idle.c | 2 +- arch/sparc/kernel/process_64.c | 2 +- arch/x86/kernel/process.c | 2 +- arch/xtensa/kernel/smp.c | 2 +- include/linux/cpu.h | 2 +- kernel/sched/idle.c | 2 +- tools/objtool/check.c | 1 + 18 files changed, 18 insertions(+), 17 deletions(-) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index a82fefa31bdb..582d96548385 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -60,7 +60,7 @@ void arch_cpu_idle(void) wtint(0); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { wtint(INT_MAX); BUG(); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 441ea5cff390..d6be4507d22d 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -320,7 +320,7 @@ void __cpu_die(unsigned int cpu) * of the other hotplug-cpu capable cores, so presumably coming * out of idle fixes this. */ -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { unsigned int cpu = smp_processor_id(); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 71d59b5abede..089ced6d6bd6 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -69,7 +69,7 @@ void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); #ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { cpu_die(); } diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index 0ec20efaf5fd..9c7a20b73ac6 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -300,7 +300,7 @@ void __cpu_die(unsigned int cpu) pr_notice("CPU%u: shutdown\n", cpu); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { idle_task_exit(); diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 78f5794b2dde..9a5cd9fad3a9 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -225,7 +225,7 @@ static inline void __noreturn play_dead(void) } #endif /* CONFIG_HOTPLUG_CPU */ -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index fa2443c7afb2..b71e17c1cc0c 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -62,7 +62,7 @@ unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE; EXPORT_SYMBOL(boot_option_idle_override); #ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 093dbbd6b843..a3225912c862 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -40,7 +40,7 @@ #include #ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index c064719b49b0..97c6f875bd0e 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -159,7 +159,7 @@ EXPORT_SYMBOL(running_on_qemu); /* * Called from the idle thread for the CPU which has been shutdown. */ -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { #ifdef CONFIG_HOTPLUG_CPU idle_task_exit(); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6b90f10a6c81..f62e5e651bcd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1752,7 +1752,7 @@ void __cpu_die(unsigned int cpu) smp_ops->cpu_die(cpu); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { /* * Disable on the down path. This will be re-enabled by diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c index f7a832e3a1d1..59b80211c25f 100644 --- a/arch/riscv/kernel/cpu-hotplug.c +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -71,7 +71,7 @@ void __cpu_die(unsigned int cpu) /* * Called from the idle thread for the CPU which has been shutdown. */ -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { idle_task_exit(); diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 38e267c7bff7..e7239aaf428b 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -88,7 +88,7 @@ void arch_cpu_idle_exit(void) { } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { cpu_die(); } diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index 114f0c4abeac..d662503b0665 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -30,7 +30,7 @@ void default_idle(void) clear_bl_bit(); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 91c2b8124527..b51d8fb0ecdc 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -95,7 +95,7 @@ void arch_cpu_idle(void) } #ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { sched_preempt_enable_no_resched(); cpu_play_dead(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f1ec36caf1d8..3e30147a537e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -727,7 +727,7 @@ void arch_cpu_idle_enter(void) local_touch_nmi(); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { play_dead(); } diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 7bad78495536..054bd64eab19 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -322,7 +322,7 @@ void __cpu_die(unsigned int cpu) pr_err("CPU%u: unable to kill\n", cpu); } -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { cpu_die(); } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f83e4519c5f0..8582a7142623 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -182,7 +182,7 @@ void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); -void arch_cpu_idle_dead(void); +void __noreturn arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 56e152f06d0f..342f58a329f5 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -75,7 +75,7 @@ static noinline int __cpuidle cpu_idle_poll(void) void __weak arch_cpu_idle_prepare(void) { } void __weak arch_cpu_idle_enter(void) { } void __weak arch_cpu_idle_exit(void) { } -void __weak arch_cpu_idle_dead(void) { while (1); } +void __weak __noreturn arch_cpu_idle_dead(void) { while (1); } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f937be1afe65..37c36dc1d868 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -202,6 +202,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__reiserfs_panic", "__stack_chk_fail", "__ubsan_handle_builtin_unreachable", + "arch_cpu_idle_dead", "cpu_bringup_and_idle", "cpu_startup_entry", "do_exit", -- GitLab From b4c108d7daf1039cf19388baff30a94563de3f3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= Date: Tue, 14 Feb 2023 09:38:57 +0100 Subject: [PATCH 0169/5631] x86/cpu: Expose arch_cpu_idle_dead()'s prototype definition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Include to make sure arch_cpu_idle_dead() matches its prototype going forward. Inspired-by: Josh Poimboeuf Signed-off-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/20230214083857.50163-1-philmd@linaro.org Signed-off-by: Josh Poimboeuf --- arch/x86/kernel/process.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 3e30147a537e..d9ecaa618430 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include -- GitLab From af5a5587a1d4c6c0a242f41751958f264ac3b0b2 Mon Sep 17 00:00:00 2001 From: Rohit Chavan Date: Fri, 24 Feb 2023 18:04:01 +0530 Subject: [PATCH 0170/5631] staging: vme: remove blank line after return statement This patch resolves a checkpatch issue by removing blank line, after return statement at end of the function. Signed-off-by: Rohit Chavan Link: https://lore.kernel.org/r/20230224123401.1365-1-roheetchavan@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme_user/vme_fake.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/staging/vme_user/vme_fake.c b/drivers/staging/vme_user/vme_fake.c index f5d2c345978a..7c53a8a7b79b 100644 --- a/drivers/staging/vme_user/vme_fake.c +++ b/drivers/staging/vme_user/vme_fake.c @@ -329,7 +329,6 @@ static int fake_master_set(struct vme_master_resource *image, int enabled, err_dwidth: err_window: return retval; - } /* @@ -638,7 +637,6 @@ static noinline_for_stack void fake_vmewrite8(struct fake_driver *bridge, } fake_lm_check(bridge, addr, aspace, cycle); - } static noinline_for_stack void fake_vmewrite16(struct fake_driver *bridge, @@ -669,7 +667,6 @@ static noinline_for_stack void fake_vmewrite16(struct fake_driver *bridge, } fake_lm_check(bridge, addr, aspace, cycle); - } static noinline_for_stack void fake_vmewrite32(struct fake_driver *bridge, @@ -700,7 +697,6 @@ static noinline_for_stack void fake_vmewrite32(struct fake_driver *bridge, } fake_lm_check(bridge, addr, aspace, cycle); - } static ssize_t fake_master_write(struct vme_master_resource *image, void *buf, @@ -1234,7 +1230,6 @@ static int __init fake_init(void) kfree(fake_bridge); err_struct: return retval; - } static void __exit fake_exit(void) -- GitLab From 215792eda008f6a1e7ed9d77fa20d582d22bb114 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 21 Feb 2023 15:53:23 +0100 Subject: [PATCH 0171/5631] drivers: staging: rtl8723bs: Fix locking in _rtw_join_timeout_handler() Commit 041879b12ddb ("drivers: staging: rtl8192bs: Fix deadlock in rtw_joinbss_event_prehandle()") besides fixing the deadlock also modified _rtw_join_timeout_handler() to use spin_[un]lock_irq() instead of spin_[un]lock_bh(). _rtw_join_timeout_handler() calls rtw_do_join() which takes pmlmepriv->scanned_queue.lock using spin_[un]lock_bh(). This spin_unlock_bh() call re-enables softirqs which triggers an oops in kernel/softirq.c: __local_bh_enable_ip() when it calls lockdep_assert_irqs_enabled(): [ 244.506087] WARNING: CPU: 2 PID: 0 at kernel/softirq.c:376 __local_bh_enable_ip+0xa6/0x100 ... [ 244.509022] Call Trace: [ 244.509048] [ 244.509100] _rtw_join_timeout_handler+0x134/0x170 [r8723bs] [ 244.509468] ? __pfx__rtw_join_timeout_handler+0x10/0x10 [r8723bs] [ 244.509772] ? __pfx__rtw_join_timeout_handler+0x10/0x10 [r8723bs] [ 244.510076] call_timer_fn+0x95/0x2a0 [ 244.510200] __run_timers.part.0+0x1da/0x2d0 This oops is causd by the switch to spin_[un]lock_irq() which disables the IRQs for the entire duration of _rtw_join_timeout_handler(). Disabling the IRQs is not necessary since all code taking this lock runs from either user contexts or from softirqs, switch back to spin_[un]lock_bh() to fix this. Fixes: 041879b12ddb ("drivers: staging: rtl8192bs: Fix deadlock in rtw_joinbss_event_prehandle()") Cc: Duoming Zhou Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230221145326.7808-1-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index c6fd6cf741ef..ea2a6566e51b 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -1549,7 +1549,7 @@ void _rtw_join_timeout_handler(struct timer_list *t) if (adapter->bDriverStopped || adapter->bSurpriseRemoved) return; - spin_lock_irq(&pmlmepriv->lock); + spin_lock_bh(&pmlmepriv->lock); if (rtw_to_roam(adapter) > 0) { /* join timeout caused by roaming */ while (1) { @@ -1577,7 +1577,7 @@ void _rtw_join_timeout_handler(struct timer_list *t) } - spin_unlock_irq(&pmlmepriv->lock); + spin_unlock_bh(&pmlmepriv->lock); } /* -- GitLab From 3f467036093fedd7e231924327455fc609b5ef02 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 21 Feb 2023 15:53:24 +0100 Subject: [PATCH 0172/5631] drivers: staging: rtl8723bs: Fix locking in rtw_scan_timeout_handler() Commit cc7ad0d77b51 ("drivers: staging: rtl8723bs: Fix deadlock in rtw_surveydone_event_callback()") besides fixing the deadlock also modified rtw_scan_timeout_handler() to use spin_[un]lock_irq() instead of spin_[un]lock_bh(). Disabling the IRQs is not necessary since all code taking this lock runs from either user contexts or from softirqs rtw_scan_timeout_handler() is the only function taking pmlmepriv->lock which uses spin_[un]lock_irq() for this. Switch back to spin_[un]lock_bh() to make it consistent with the rest of the code. Fixes: cc7ad0d77b51 ("drivers: staging: rtl8723bs: Fix deadlock in rtw_surveydone_event_callback()") Cc: Duoming Zhou Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230221145326.7808-2-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index ea2a6566e51b..091842d70d48 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -1590,11 +1590,11 @@ void rtw_scan_timeout_handler(struct timer_list *t) mlmepriv.scan_to_timer); struct mlme_priv *pmlmepriv = &adapter->mlmepriv; - spin_lock_irq(&pmlmepriv->lock); + spin_lock_bh(&pmlmepriv->lock); _clr_fwstate_(pmlmepriv, _FW_UNDER_SURVEY); - spin_unlock_irq(&pmlmepriv->lock); + spin_unlock_bh(&pmlmepriv->lock); rtw_indicate_scan_done(adapter, true); } -- GitLab From fea50d5fba5a03ddb5c81863533afdaa91002690 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 21 Feb 2023 15:53:25 +0100 Subject: [PATCH 0173/5631] drivers: staging: rtl8723bs: Remove unused clr_fwstate() function The clr_fwstate() function is not used anywhere, remove it. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230221145326.7808-3-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/include/rtw_mlme.h | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/staging/rtl8723bs/include/rtw_mlme.h b/drivers/staging/rtl8723bs/include/rtw_mlme.h index 1b343b434f4d..ee748620107f 100644 --- a/drivers/staging/rtl8723bs/include/rtw_mlme.h +++ b/drivers/staging/rtl8723bs/include/rtw_mlme.h @@ -490,18 +490,6 @@ static inline void _clr_fwstate_(struct mlme_priv *pmlmepriv, signed int state) pmlmepriv->bScanInProcess = false; } -/* - * No Limit on the calling context, - * therefore set it to be the critical section... - */ -static inline void clr_fwstate(struct mlme_priv *pmlmepriv, signed int state) -{ - spin_lock_bh(&pmlmepriv->lock); - if (check_fwstate(pmlmepriv, state) == true) - pmlmepriv->fw_state ^= state; - spin_unlock_bh(&pmlmepriv->lock); -} - static inline void set_scanned_network_val(struct mlme_priv *pmlmepriv, signed int val) { spin_lock_bh(&pmlmepriv->lock); -- GitLab From 5a50c621a4513d9664c55b661400c0f04444c190 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 21 Feb 2023 15:53:26 +0100 Subject: [PATCH 0174/5631] drivers: staging: rtl8723bs: Remove pmlmepriv->num_of_scanned pmlmepriv->num_of_scanned is only ever set and never read, remove it. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230221145326.7808-4-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/core/rtw_mlme.c | 9 --------- drivers/staging/rtl8723bs/include/rtw_mlme.h | 8 -------- 2 files changed, 17 deletions(-) diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme.c b/drivers/staging/rtl8723bs/core/rtw_mlme.c index 091842d70d48..7e2c61c75150 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme.c @@ -32,8 +32,6 @@ int rtw_init_mlme_priv(struct adapter *padapter) INIT_LIST_HEAD(&pmlmepriv->scanned_queue.queue); spin_lock_init(&pmlmepriv->scanned_queue.lock); - set_scanned_network_val(pmlmepriv, 0); - memset(&pmlmepriv->assoc_ssid, 0, sizeof(struct ndis_802_11_ssid)); pbuf = vzalloc(array_size(MAX_BSS_CNT, sizeof(struct wlan_network))); @@ -161,8 +159,6 @@ struct wlan_network *rtw_alloc_network(struct mlme_priv *pmlmepriv) pnetwork->aid = 0; pnetwork->join_res = 0; - pmlmepriv->num_of_scanned++; - exit: spin_unlock_bh(&free_queue->lock); @@ -198,8 +194,6 @@ void _rtw_free_network(struct mlme_priv *pmlmepriv, struct wlan_network *pnetwor list_add_tail(&(pnetwork->list), &(free_queue->queue)); - pmlmepriv->num_of_scanned--; - spin_unlock_bh(&free_queue->lock); } @@ -220,8 +214,6 @@ void _rtw_free_network_nolock(struct mlme_priv *pmlmepriv, struct wlan_network * list_add_tail(&(pnetwork->list), get_list_head(free_queue)); - pmlmepriv->num_of_scanned--; - /* spin_unlock_irqrestore(&free_queue->lock, irqL); */ } @@ -863,7 +855,6 @@ static void free_scanqueue(struct mlme_priv *pmlmepriv) list_del_init(plist); list_add_tail(plist, &free_queue->queue); plist = ptemp; - pmlmepriv->num_of_scanned--; } spin_unlock_bh(&free_queue->lock); diff --git a/drivers/staging/rtl8723bs/include/rtw_mlme.h b/drivers/staging/rtl8723bs/include/rtw_mlme.h index ee748620107f..fc0b43d38d9a 100644 --- a/drivers/staging/rtl8723bs/include/rtw_mlme.h +++ b/drivers/staging/rtl8723bs/include/rtw_mlme.h @@ -303,7 +303,6 @@ struct mlme_priv { struct __queue free_bss_pool; struct __queue scanned_queue; u8 *free_bss_buf; - u32 num_of_scanned; struct ndis_802_11_ssid assoc_ssid; u8 assoc_bssid[6]; @@ -490,13 +489,6 @@ static inline void _clr_fwstate_(struct mlme_priv *pmlmepriv, signed int state) pmlmepriv->bScanInProcess = false; } -static inline void set_scanned_network_val(struct mlme_priv *pmlmepriv, signed int val) -{ - spin_lock_bh(&pmlmepriv->lock); - pmlmepriv->num_of_scanned = val; - spin_unlock_bh(&pmlmepriv->lock); -} - extern u16 rtw_get_capability(struct wlan_bssid_ex *bss); extern void rtw_update_scanned_network(struct adapter *adapter, struct wlan_bssid_ex *target); extern void rtw_disconnect_hdl_under_linked(struct adapter *adapter, struct sta_info *psta, u8 free_assoc); -- GitLab From 5239a89b06d6b199f133bf0ffea421683187f257 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 8 Mar 2023 20:40:43 +0000 Subject: [PATCH 0175/5631] pstore: Revert pmsg_lock back to a normal mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit 76d62f24db07f22ccf9bc18ca793c27d4ebef721. So while priority inversion on the pmsg_lock is an occasional problem that an rt_mutex would help with, in uses where logging is writing to pmsg heavily from multiple threads, the pmsg_lock can be heavily contended. After this change landed, it was reported that cases where the mutex locking overhead was commonly adding on the order of 10s of usecs delay had suddenly jumped to ~msec delay with rtmutex. It seems the slight differences in the locks under this level of contention causes the normal mutexes to utilize the spinning optimizations, while the rtmutexes end up in the sleeping slowpath (which allows additional threads to pile on trying to take the lock). In this case, it devolves to a worse case senerio where the lock acquisition and scheduling overhead dominates, and each thread is waiting on the order of ~ms to do ~us of work. Obviously, having tons of threads all contending on a single lock for logging is non-optimal, so the proper fix is probably reworking pstore pmsg to have per-cpu buffers so we don't have contention. Additionally, Steven Rostedt has provided some furhter optimizations for rtmutexes that improves the rtmutex spinning path, but at least in my testing, I still see the test tripping into the sleeping path on rtmutexes while utilizing the spinning path with mutexes. But in the short term, lets revert the change to the rt_mutex and go back to normal mutexes to avoid a potentially major performance regression. And we can work on optimizations to both rtmutexes and finer-grained locking for pstore pmsg in the future. Cc: Wei Wang Cc: Midas Chien Cc: "Chunhui Li (李春辉)" Cc: Steven Rostedt Cc: Kees Cook Cc: Anton Vorontsov Cc: "Guilherme G. Piccoli" Cc: Tony Luck Cc: kernel-team@android.com Fixes: 76d62f24db07 ("pstore: Switch pmsg_lock to an rt_mutex to avoid priority inversion") Reported-by: "Chunhui Li (李春辉)" Signed-off-by: John Stultz Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230308204043.2061631-1-jstultz@google.com --- fs/pstore/pmsg.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index ab82e5f05346..b31c9c72d90b 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -7,10 +7,9 @@ #include #include #include -#include #include "internal.h" -static DEFINE_RT_MUTEX(pmsg_lock); +static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -29,9 +28,9 @@ static ssize_t write_pmsg(struct file *file, const char __user *buf, if (!access_ok(buf, count)) return -EFAULT; - rt_mutex_lock(&pmsg_lock); + mutex_lock(&pmsg_lock); ret = psinfo->write_user(&record, buf); - rt_mutex_unlock(&pmsg_lock); + mutex_unlock(&pmsg_lock); return ret ? ret : count; } -- GitLab From 466123c54f3153b77c7460e08850c385fa4fe3fc Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Thu, 9 Mar 2023 12:04:39 +0100 Subject: [PATCH 0176/5631] staging: rtl8192e: rtl92e_clear_irq() is not used The function rtl92e_clear_irq() is not used. Remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230309110439.24504-1-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 9 --------- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.h | 1 - 2 files changed, 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 8edfaaeda910..db26e431f8b7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -1969,15 +1969,6 @@ void rtl92e_disable_irq(struct net_device *dev) priv->irq_enabled = 0; } -void rtl92e_clear_irq(struct net_device *dev) -{ - u32 tmp; - - tmp = rtl92e_readl(dev, ISR); - rtl92e_writel(dev, ISR, tmp); -} - - void rtl92e_enable_rx(struct net_device *dev) { struct r8192_priv *priv = (struct r8192_priv *)rtllib_priv(dev); diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.h index 1713381dc2b4..fa3b71dbb091 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.h @@ -18,7 +18,6 @@ void rtl92e_enable_rx(struct net_device *dev); void rtl92e_enable_tx(struct net_device *dev); void rtl92e_enable_irq(struct net_device *dev); void rtl92e_disable_irq(struct net_device *dev); -void rtl92e_clear_irq(struct net_device *dev); void rtl92e_init_variables(struct net_device *dev); void rtl92e_start_beacon(struct net_device *dev); void rtl92e_set_reg(struct net_device *dev, u8 variable, u8 *val); -- GitLab From 3abe84ea065128f5ad1025f2176156dd04b777ee Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 2 Mar 2023 16:52:55 +0100 Subject: [PATCH 0177/5631] dt-bindings: pinctrl: qcom: lpass-lpi: correct description of second reg The description of second IO address is a bit confusing. It is supposed to be the MCC range which contains the slew rate registers, not the slew rate register base. The Linux driver then accesses slew rate register with hard-coded offset (0xa000). Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230302155255.857065-1-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- .../bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml | 2 +- .../bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml | 2 +- .../bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml index 200b3b6ccd87..a9167dac9ab5 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-lpass-lpi-pinctrl.yaml @@ -20,7 +20,7 @@ properties: reg: items: - description: LPASS LPI TLMM Control and Status registers - - description: LPASS LPI pins SLEW registers + - description: LPASS LPI MCC registers clocks: items: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml index 8bf51df0b231..1eefa9aa6a86 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-lpass-lpi-pinctrl.yaml @@ -20,7 +20,7 @@ properties: reg: items: - description: LPASS LPI TLMM Control and Status registers - - description: LPASS LPI pins SLEW registers + - description: LPASS LPI MCC registers clocks: items: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml index 5e90051ed314..691bf60abb8c 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-lpass-lpi-pinctrl.yaml @@ -21,7 +21,7 @@ properties: reg: items: - description: LPASS LPI TLMM Control and Status registers - - description: LPASS LPI pins SLEW registers + - description: LPASS LPI MCC registers clocks: items: -- GitLab From 713834cf2cd47cfdb79da523c8b243fca71615f5 Mon Sep 17 00:00:00 2001 From: Md Sadre Alam Date: Mon, 6 Mar 2023 20:16:41 +0530 Subject: [PATCH 0178/5631] pinctrl: qcom: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Md Sadre Alam Link: https://lore.kernel.org/r/20230306144641.21955-1-quic_mdalam@quicinc.com Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-msm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index daeb79a9a602..e25e7b5cdda2 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -1480,8 +1480,7 @@ int msm_pinctrl_probe(struct platform_device *pdev, return PTR_ERR(pctrl->regs[i]); } } else { - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pctrl->regs[0] = devm_ioremap_resource(&pdev->dev, res); + pctrl->regs[0] = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(pctrl->regs[0])) return PTR_ERR(pctrl->regs[0]); -- GitLab From e1edf95e0f4274f4d68aa00387a03a92b51cbbe3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 28 Feb 2023 17:53:22 -0600 Subject: [PATCH 0179/5631] usb: host: xhci-tegra: Drop using of_irq_parse_one() Drivers generally shouldn't be using of_irq_parse_one() directly as it is a low-level interrupt parsing API. The exceptions are cases that need the values from the 'interrupts' property. This is not the case for Tegra XHCI driver as it just uses of_irq_parse_one() to test for 'interrupts' being absent or invalid. Instead, just make the interrupt optional on any error other than deferred probe. The exact reason for failing to get the interrupt is not that important. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230228235322.13289-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-tegra.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 1ff22f675930..b9349b8c8ff1 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1535,7 +1535,6 @@ static void tegra_xusb_deinit_usb_phy(struct tegra_xusb *tegra) static int tegra_xusb_probe(struct platform_device *pdev) { - struct of_phandle_args args; struct tegra_xusb *tegra; struct device_node *np; struct resource *regs; @@ -1594,15 +1593,13 @@ static int tegra_xusb_probe(struct platform_device *pdev) goto put_padctl; } - /* Older device-trees don't have padctrl interrupt */ - err = of_irq_parse_one(np, 0, &args); - if (!err) { - tegra->padctl_irq = of_irq_get(np, 0); - if (tegra->padctl_irq <= 0) { - err = (tegra->padctl_irq == 0) ? -ENODEV : tegra->padctl_irq; - goto put_padctl; - } - } else { + tegra->padctl_irq = of_irq_get(np, 0); + if (tegra->padctl_irq == -EPROBE_DEFER) { + err = tegra->padctl_irq; + goto put_padctl; + } else if (tegra->padctl_irq <= 0) { + /* Older device-trees don't have padctrl interrupt */ + tegra->padctl_irq = 0; dev_dbg(&pdev->dev, "%pOF is missing an interrupt, disabling PM support\n", np); } -- GitLab From 1d8ce4d889643dd0e8dd196c8ff959d7cc2698c6 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 23 Feb 2023 21:44:28 -0600 Subject: [PATCH 0180/5631] usb: host: oxu210hp-hcd: Replace fake flex-array with flexible-array member MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Zero-length arrays as fake flexible arrays are deprecated and we are moving towards adopting C99 flexible-array members instead. Transform zero-length array into flexible-array member in struct ehci_regs. Address the following warnings found with GCC-13 and -fstrict-flex-arrays=3 enabled: drivers/usb/host/oxu210hp-hcd.c:3983:30: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3986:38: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3971:30: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3978:30: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3523:30: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:2774:39: warning: array subscript port is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3569:35: warning: array subscript is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:3888:36: warning: array subscript port is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] drivers/usb/host/oxu210hp-hcd.c:2911:45: warning: array subscript i is outside array bounds of ‘u32[0]’ {aka ‘unsigned int[]’} [-Warray-bounds=] This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help us make progress towards globally enabling -fstrict-flex-arrays=3 [1]. Link: https://github.com/KSPP/linux/issues/21 Link: https://github.com/KSPP/linux/issues/259 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [1] Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/Y/gynI9Wv8RZTD8M@work Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/oxu210hp-hcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c index 3a441310c713..f998d3f1a78a 100644 --- a/drivers/usb/host/oxu210hp-hcd.c +++ b/drivers/usb/host/oxu210hp-hcd.c @@ -169,7 +169,7 @@ struct ehci_regs { #define FLAG_CF (1<<0) /* true: we'll support "high speed" */ /* PORTSC: offset 0x44 */ - u32 port_status[0]; /* up to N_PORTS */ + u32 port_status[]; /* up to N_PORTS */ /* 31:23 reserved */ #define PORT_WKOC_E (1<<22) /* wake on overcurrent (enable) */ #define PORT_WKDISC_E (1<<21) /* wake on disconnect (enable) */ -- GitLab From 5d67f4861884762ebc2bddb5d667444e45f25782 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 17:30:37 +0100 Subject: [PATCH 0181/5631] usb: host: xhci-rcar: remove leftover quirk handling Loading V3 firmware does not need a quirk anymore, remove the leftover code. Fixes: ed8603e11124 ("usb: host: xhci-rcar: Simplify getting the firmware name for R-Car Gen3") Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230307163041.3815-10-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-rcar.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index 7f18509a1d39..567b096a24e9 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -80,7 +80,6 @@ MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V3); /* For soc_device_attribute */ #define RCAR_XHCI_FIRMWARE_V2 BIT(0) /* FIRMWARE V2 */ -#define RCAR_XHCI_FIRMWARE_V3 BIT(1) /* FIRMWARE V3 */ static const struct soc_device_attribute rcar_quirks_match[] = { { @@ -152,8 +151,6 @@ static int xhci_rcar_download_firmware(struct usb_hcd *hcd) if (quirks & RCAR_XHCI_FIRMWARE_V2) firmware_name = XHCI_RCAR_FIRMWARE_NAME_V2; - else if (quirks & RCAR_XHCI_FIRMWARE_V3) - firmware_name = XHCI_RCAR_FIRMWARE_NAME_V3; else firmware_name = priv->firmware_name; -- GitLab From 87b383f82e4ea8f7fb8e6d6c4d42d0e4a213dd7b Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 17:30:38 +0100 Subject: [PATCH 0182/5631] usb: host: xhci-rcar: remove R-Car H3 ES1.* handling R-Car H3 ES1.* was only available to an internal development group and needed a lot of quirks and workarounds. These become a maintenance burden now, so our development group decided to remove upstream support and disable booting for this SoC. Public users only have ES2 onwards. Reviewed-by: Laurent Pinchart Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230307163041.3815-11-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-rcar.c | 31 ++----------------------------- 1 file changed, 2 insertions(+), 29 deletions(-) diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index 567b096a24e9..c4925f8d6b06 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -12,26 +12,22 @@ #include #include #include -#include #include "xhci.h" #include "xhci-plat.h" #include "xhci-rzv2m.h" #define XHCI_RCAR_FIRMWARE_NAME_V1 "r8a779x_usb3_v1.dlmem" -#define XHCI_RCAR_FIRMWARE_NAME_V2 "r8a779x_usb3_v2.dlmem" #define XHCI_RCAR_FIRMWARE_NAME_V3 "r8a779x_usb3_v3.dlmem" /* -* - The V3 firmware is for almost all R-Car Gen3 (except r8a7795 ES1.x) -* - The V2 firmware is for r8a7795 ES1.x. +* - The V3 firmware is for all R-Car Gen3 * - The V2 firmware is possible to use on R-Car Gen2. However, the V2 causes * performance degradation. So, this driver continues to use the V1 if R-Car * Gen2. * - The V1 firmware is impossible to use on R-Car Gen3. */ MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V1); -MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V2); MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V3); /*** Register Offset ***/ @@ -78,17 +74,6 @@ MODULE_FIRMWARE(XHCI_RCAR_FIRMWARE_NAME_V3); #define RCAR_USB3_RX_POL_VAL BIT(21) #define RCAR_USB3_TX_POL_VAL BIT(4) -/* For soc_device_attribute */ -#define RCAR_XHCI_FIRMWARE_V2 BIT(0) /* FIRMWARE V2 */ - -static const struct soc_device_attribute rcar_quirks_match[] = { - { - .soc_id = "r8a7795", .revision = "ES1.*", - .data = (void *)RCAR_XHCI_FIRMWARE_V2, - }, - { /* sentinel */ } -}; - static void xhci_rcar_start_gen2(struct usb_hcd *hcd) { /* LCLK Select */ @@ -134,9 +119,6 @@ static int xhci_rcar_download_firmware(struct usb_hcd *hcd) const struct firmware *fw; int retval, index, j; u32 data, val, temp; - u32 quirks = 0; - const struct soc_device_attribute *attr; - const char *firmware_name; /* * According to the datasheet, "Upon the completion of FW Download, @@ -145,17 +127,8 @@ static int xhci_rcar_download_firmware(struct usb_hcd *hcd) if (readl(regs + RCAR_USB3_DL_CTRL) & RCAR_USB3_DL_CTRL_FW_SUCCESS) return 0; - attr = soc_device_match(rcar_quirks_match); - if (attr) - quirks = (uintptr_t)attr->data; - - if (quirks & RCAR_XHCI_FIRMWARE_V2) - firmware_name = XHCI_RCAR_FIRMWARE_NAME_V2; - else - firmware_name = priv->firmware_name; - /* request R-Car USB3.0 firmware */ - retval = request_firmware(&fw, firmware_name, dev); + retval = request_firmware(&fw, priv->firmware_name, dev); if (retval) return retval; -- GitLab From f3323cd03e5852e2a2f725d67f1b01777341c706 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 17:30:39 +0100 Subject: [PATCH 0183/5631] usb: gadget: udc: renesas_usb3: remove R-Car H3 ES1.* handling R-Car H3 ES1.* was only available to an internal development group and needed a lot of quirks and workarounds. These become a maintenance burden now, so our development group decided to remove upstream support and disable booting for this SoC. Public users only have ES2 onwards. Reviewed-by: Laurent Pinchart Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230307163041.3815-12-wsa+renesas@sang-engineering.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/renesas_usb3.c | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index bee6bceafc4f..f2ac6447b748 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -2781,13 +2780,6 @@ static void renesas_usb3_init_ram(struct renesas_usb3 *usb3, struct device *dev, } } -static const struct renesas_usb3_priv renesas_usb3_priv_r8a7795_es1 = { - .ramsize_per_ramif = SZ_16K, - .num_ramif = 2, - .ramsize_per_pipe = SZ_4K, - .workaround_for_vbus = true, -}; - static const struct renesas_usb3_priv renesas_usb3_priv_gen3 = { .ramsize_per_ramif = SZ_16K, .num_ramif = 4, @@ -2829,14 +2821,6 @@ static const struct of_device_id usb3_of_match[] = { }; MODULE_DEVICE_TABLE(of, usb3_of_match); -static const struct soc_device_attribute renesas_usb3_quirks_match[] = { - { - .soc_id = "r8a7795", .revision = "ES1.*", - .data = &renesas_usb3_priv_r8a7795_es1, - }, - { /* sentinel */ } -}; - static const unsigned int renesas_usb3_cable[] = { EXTCON_USB, EXTCON_USB_HOST, @@ -2854,13 +2838,8 @@ static int renesas_usb3_probe(struct platform_device *pdev) struct renesas_usb3 *usb3; int irq, ret; const struct renesas_usb3_priv *priv; - const struct soc_device_attribute *attr; - attr = soc_device_match(renesas_usb3_quirks_match); - if (attr) - priv = attr->data; - else - priv = of_device_get_match_data(&pdev->dev); + priv = of_device_get_match_data(&pdev->dev); irq = platform_get_irq(pdev, 0); if (irq < 0) -- GitLab From 2da1b848e366bd8881137b5bdfc2bfaf4bee8b2d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 4 Mar 2023 14:03:02 +0100 Subject: [PATCH 0184/5631] dt-bindings: usb: snps,dwc3: document extcon property The DWC3 USB Linux driver and several DTS use extcon property, so document it, even though it is deprecated, to fix warnings like: sm6125-sony-xperia-seine-pdx201.dtb: usb@4ef8800: usb@4e00000: Unevaluated properties are not allowed ('extcon' was unexpected) Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230304130302.51497-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/snps,dwc3.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index be36956af53b..cad2efd5f8c9 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -70,6 +70,10 @@ properties: dma-coherent: true + extcon: + maxItems: 1 + deprecated: true + iommus: maxItems: 1 -- GitLab From f81a8591db7330a4caa0d430f50e54369a8520ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 28 Feb 2023 19:29:09 +0100 Subject: [PATCH 0185/5631] dt-bindings: usb: usb-device: make "compatible" optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This binding was originally meant to describe hard-wired USB devices but in some situations we need to describe USB ports. That is needed e.g. if USB port is meant to be used as a trigger source but it can have any device plugged. It's a common case for home routers which have USB ports (with no hard-wired devices) and USB LEDs to indicate ports state. There is no point (and no easy way) to add separate binding covering just USB ports. Adjust existing devices binding to allow describing ports. This fixes: arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@21000: port@1: 'compatible' is a required property From schema: Documentation/devicetree/bindings/usb/generic-ehci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@21000: port@2: 'compatible' is a required property From schema: Documentation/devicetree/bindings/usb/generic-ehci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@21000: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'port@1', 'port@2' were unexpected) From schema: Documentation/devicetree/bindings/usb/generic-ehci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@22000: port@1: 'compatible' is a required property From schema: Documentation/devicetree/bindings/usb/generic-ohci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@22000: port@2: 'compatible' is a required property From schema: Documentation/devicetree/bindings/usb/generic-ohci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@22000: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'port@1', 'port@2' were unexpected) From schema: Documentation/devicetree/bindings/usb/generic-ohci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@23000: port@1: 'compatible' is a required property From schema: Documentation/devicetree/bindings/usb/generic-xhci.yaml arch/arm/boot/dts/bcm4708-asus-rt-ac56u.dtb: usb@23000: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'phy-names', 'phys', 'port@1' were unexpected) From schema: Documentation/devicetree/bindings/usb/generic-xhci.yaml Signed-off-by: Rafał Miłecki Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230228182909.1011-1-zajec5@gmail.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/usb-device.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/usb/usb-device.yaml b/Documentation/devicetree/bindings/usb/usb-device.yaml index 7a771125ec76..da890ee60ce6 100644 --- a/Documentation/devicetree/bindings/usb/usb-device.yaml +++ b/Documentation/devicetree/bindings/usb/usb-device.yaml @@ -76,7 +76,6 @@ patternProperties: maxItems: 1 required: - - compatible - reg additionalProperties: true -- GitLab From aa78a736a94f1e2771d5400d4286d907624f5f8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 28 Feb 2023 16:21:05 +0100 Subject: [PATCH 0186/5631] dt-bindings: usb: allow evaluated properties in OHCI controllers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This binding uses usb-hcd.yaml so replace additionalProperties with unevaluatedProperties to allow generic USB HCD properties. It's how EHCI and XHCI bindings work too. Signed-off-by: Rafał Miłecki Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230228152105.25358-1-zajec5@gmail.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/generic-ohci.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/usb/generic-ohci.yaml b/Documentation/devicetree/bindings/usb/generic-ohci.yaml index a9ba7257b884..d06d1e7d8876 100644 --- a/Documentation/devicetree/bindings/usb/generic-ohci.yaml +++ b/Documentation/devicetree/bindings/usb/generic-ohci.yaml @@ -148,7 +148,7 @@ allOf: properties: transceiver: false -additionalProperties: false +unevaluatedProperties: false examples: - | -- GitLab From 487e6f420b7a3eed775118635d310ffa024ff7ef Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 15 Feb 2023 15:01:45 +0530 Subject: [PATCH 0187/5631] dt-bindings: usb: dwc3: Add snps,ulpi-ext-vbus-drv quirk Some ULPI USB PHYs do not support an internal vBus supply, to drive the CPEN pin properly, it requires configuration of the ULPI DRVVBUSEXTERNAL bit of the USB ULPI PHY OTG_CTRL register. Added 'snps,ulpi-ext-vbus-drv' DT property to configure the USB2 PHY to drives VBUS with an external supply. When the ULPIEXTVBUSDRV bit is set to '1' in the Global USB2 PHY Configuration registers, PHY drive vBus with an external 5V supply source. Signed-off-by: Piyush Mehta Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230215093146.5812-2-piyush.mehta@amd.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/snps,dwc3.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index cad2efd5f8c9..c167fd577cae 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -260,6 +260,14 @@ properties: of resume. This option is to support certain legacy ULPI PHYs. type: boolean + snps,ulpi-ext-vbus-drv: + description: + Some ULPI USB PHY does not support internal VBUS supply, and driving + the CPEN pin, requires the configuration of the ulpi DRVVBUSEXTERNAL + bit. When set, the xhci host will configure the USB2 PHY drives VBUS + with an external supply. + type: boolean + snps,is-utmi-l1-suspend: description: True when DWC3 asserts output signal utmi_l1_suspend_n, false when -- GitLab From b84ba26c922a99c7541d53ab1971f070b65264fe Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 15 Feb 2023 15:01:46 +0530 Subject: [PATCH 0188/5631] usb: dwc3: core: add external vBus supply support for ulpi phy Some ULPI USB PHY does not support internal VBUS supply, to drive the CPEN pin, which requires the configuration of the ULPI DRVVBUSEXTERNAL bit of OTG_CTRL register. Added 'snps,ulpi-ext-vbus-drv' a DT property to configure the USB2 PHY to drive VBUS with an external supply, by setting the USB2 PHY ULPIEXTVBUSDRV bit[:17] of the GUSB2PHYCFG register to drive VBUS with an external supply. Signed-off-by: Piyush Mehta Link: https://lore.kernel.org/r/20230215093146.5812-3-piyush.mehta@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 12 ++++++++++++ drivers/usb/dwc3/core.h | 4 ++++ 2 files changed, 16 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 476b63618511..ed0ab90d3fac 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -800,6 +800,16 @@ static int dwc3_phy_setup(struct dwc3 *dwc) if (dwc->dis_u2_freeclk_exists_quirk || dwc->gfladj_refclk_lpm_sel) reg &= ~DWC3_GUSB2PHYCFG_U2_FREECLK_EXISTS; + /* + * Some ULPI USB PHY does not support internal VBUS supply, to drive + * the CPEN pin requires the configuration of the ULPI DRVVBUSEXTERNAL + * bit of OTG_CTRL register. Controller configures the USB2 PHY + * ULPIEXTVBUSDRV bit[17] of the GUSB2PHYCFG register to drive vBus + * with an external supply. + */ + if (dwc->ulpi_ext_vbus_drv) + reg |= DWC3_GUSB2PHYCFG_ULPIEXTVBUSDRV; + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); return 0; @@ -1553,6 +1563,8 @@ static void dwc3_get_properties(struct dwc3 *dwc) "snps,dis-tx-ipgap-linecheck-quirk"); dwc->resume_hs_terminations = device_property_read_bool(dev, "snps,resume-hs-terminations"); + dwc->ulpi_ext_vbus_drv = device_property_read_bool(dev, + "snps,ulpi-ext-vbus-drv"); dwc->parkmode_disable_ss_quirk = device_property_read_bool(dev, "snps,parkmode-disable-ss-quirk"); dwc->gfladj_refclk_lpm_sel = device_property_read_bool(dev, diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 582ebd9cf9c2..b1bd63188f52 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -280,6 +280,7 @@ /* Global USB2 PHY Configuration Register */ #define DWC3_GUSB2PHYCFG_PHYSOFTRST BIT(31) #define DWC3_GUSB2PHYCFG_U2_FREECLK_EXISTS BIT(30) +#define DWC3_GUSB2PHYCFG_ULPIEXTVBUSDRV BIT(17) #define DWC3_GUSB2PHYCFG_SUSPHY BIT(6) #define DWC3_GUSB2PHYCFG_ULPI_UTMI BIT(4) #define DWC3_GUSB2PHYCFG_ENBLSLPM BIT(8) @@ -1100,6 +1101,8 @@ struct dwc3_scratchpad_array { * check during HS transmit. * @resume-hs-terminations: Set if we enable quirk for fixing improper crc * generation after resume from suspend. + * @ulpi_ext_vbus_drv: Set to confiure the upli chip to drives CPEN pin + * VBUS with an external supply. * @parkmode_disable_ss_quirk: set if we need to disable all SuperSpeed * instances in park mode. * @tx_de_emphasis_quirk: set if we enable Tx de-emphasis quirk @@ -1317,6 +1320,7 @@ struct dwc3 { unsigned dis_del_phy_power_chg_quirk:1; unsigned dis_tx_ipgap_linecheck_quirk:1; unsigned resume_hs_terminations:1; + unsigned ulpi_ext_vbus_drv:1; unsigned parkmode_disable_ss_quirk:1; unsigned gfladj_refclk_lpm_sel:1; -- GitLab From 4decf4060ecfee1f7a710999fcd421645ac0c419 Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 24 Feb 2023 11:16:58 +0530 Subject: [PATCH 0189/5631] usb: dwc3: gadget: Change condition for processing suspend event Currently we process the suspend interrupt event only if the device is in configured state. Consider a case where device is not configured and got suspend interrupt, in that case our gadget will still use 100mA as composite_suspend didn't happen. But battery charging specification (BC1.2) expects a downstream device to draw less than 2.5mA when unconnected OR suspended. Fix this by removing the condition for processing suspend event, and thus composite_resume would set vbus draw to 2. Fixes: 72704f876f50 ("dwc3: gadget: Implement the suspend entry event handler") Signed-off-by: Prashanth K Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/1677217619-10261-2-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 3c63fa97a680..07989c645a94 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4239,15 +4239,8 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, break; case DWC3_DEVICE_EVENT_SUSPEND: /* It changed to be suspend event for version 2.30a and above */ - if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) { - /* - * Ignore suspend event until the gadget enters into - * USB_STATE_CONFIGURED state. - */ - if (dwc->gadget->state >= USB_STATE_CONFIGURED) - dwc3_gadget_suspend_interrupt(dwc, - event->event_info); - } + if (!DWC3_VER_IS_PRIOR(DWC3, 230A)) + dwc3_gadget_suspend_interrupt(dwc, event->event_info); break; case DWC3_DEVICE_EVENT_SOF: case DWC3_DEVICE_EVENT_ERRATIC_ERROR: -- GitLab From 2ae4e0dea3b0c7b380821bac05e03a71da1f452f Mon Sep 17 00:00:00 2001 From: Prashanth K Date: Fri, 24 Feb 2023 11:16:59 +0530 Subject: [PATCH 0190/5631] usb: gadget: composite: Draw 100mA current if not configured Currently we don't change the current value if device isn't in configured state. But in battery charging specification (section 1.2 and 1.4.13), it is mentioned that the device can draw up to 100mA of current if it's in unconfigured state. Hence add vbus draw work in composite_resume to draw 100mA if the device isn't configured. Signed-off-by: Prashanth K Link: https://lore.kernel.org/r/1677217619-10261-3-git-send-email-quic_prashk@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index fa7dd6cf014d..36add1879ed2 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2531,6 +2531,10 @@ void composite_resume(struct usb_gadget *gadget) usb_gadget_clear_selfpowered(gadget); usb_gadget_vbus_draw(gadget, maxpower); + } else { + maxpower = CONFIG_USB_GADGET_VBUS_DRAW; + maxpower = min(maxpower, 100U); + usb_gadget_vbus_draw(gadget, maxpower); } cdev->suspended = 0; -- GitLab From 5aacc9d540cea790fe4419b61bfa8a1218a4474a Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Sat, 25 Feb 2023 12:11:48 +0800 Subject: [PATCH 0191/5631] usb: gadget: udc: add return value check of kzalloc in mv_udc_probe Even an 8-byte kzalloc will fail when we don't have enough memory, so we need a nullptr check and do the cleanup when it fails. Reported-by: eriri <1527030098@qq.com> Link: https://bugzilla.kernel.org/show_bug.cgi?id=217081 Signed-off-by: Kang Chen Link: https://lore.kernel.org/r/20230225041149.136-1-void0red@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/mv_udc_core.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index b397f3a848cf..6dd6d52de3af 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -2230,6 +2230,10 @@ static int mv_udc_probe(struct platform_device *pdev) /* allocate a small amount of memory to get valid address */ udc->status_req->req.buf = kzalloc(8, GFP_KERNEL); + if (!udc->status_req->req.buf) { + retval = -ENOMEM; + goto err_destroy_dma; + } udc->status_req->req.dma = DMA_ADDR_INVALID; udc->resume_state = USB_STATE_NOTATTACHED; -- GitLab From 514c7ff5fe56164b769d2d105f0a382ca98c0851 Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Sat, 25 Feb 2023 12:11:49 +0800 Subject: [PATCH 0192/5631] usb: gadget: udc: replace kzalloc with devm_kzalloc in mv_udc_probe This driver uses the unified memory management api, so replace kzalloc with devm_kzalloc to avoid a memory leak. Reported-by: Dongliang Mu Link: https://lore.kernel.org/all/CAD-N9QX5i5toj8cs7DxBjYWtRGf3ZRnfTAf809sFW6iX0Ktfmw@mail.gmail.com Signed-off-by: Kang Chen Link: https://lore.kernel.org/r/20230225041149.136-2-void0red@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/mv_udc_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index 6dd6d52de3af..08474c08d874 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -2229,7 +2229,7 @@ static int mv_udc_probe(struct platform_device *pdev) INIT_LIST_HEAD(&udc->status_req->queue); /* allocate a small amount of memory to get valid address */ - udc->status_req->req.buf = kzalloc(8, GFP_KERNEL); + udc->status_req->req.buf = devm_kzalloc(&pdev->dev, 8, GFP_KERNEL); if (!udc->status_req->req.buf) { retval = -ENOMEM; goto err_destroy_dma; -- GitLab From 180bb831b232b43bbd658dcdb20a49020059c1b8 Mon Sep 17 00:00:00 2001 From: Yuta Hayama Date: Tue, 28 Feb 2023 17:56:37 +0900 Subject: [PATCH 0193/5631] usb: gadget: f_fs: Fix incorrect version checking of OS descs Currently, the USB gadget framework supports only version 1.0 of the MS OS descriptor. OS desc has a field bcdVersion indicating its version, with v1.0 represented by the value 0x100. However, __ffs_do_os_desc_header() was expecting the incorrect value 0x1, so allow the correct value 0x100. The bcdVersion field of the descriptor that is actually sent to the host is set by composite_setup() (in composite.c) to the fixed value 0x100. Therefore, it can be understood that __ffs_do_os_desc_header() is only performing a format check of the OS desc passed to functionfs. If a value other than 0x100 is accepted, there is no effect on communication over the USB bus. Indeed, until now __ffs_do_os_desc_header() has only accepted the incorrect value 0x1, but there was no problem with the communication over the USB bus. However, this can be confusing for functionfs userspace drivers. Since bcdVersion=0x100 is used in actual communication, functionfs should accept the value 0x100. Note that the correct value for bcdVersion in OS desc v1.0 is 0x100, but to avoid breaking old userspace drivers, the value 0x1 is also accepted as an exception. At this time, a message is output to notify the user to fix the userspace driver. Signed-off-by: Yuta Hayama Reviewed-by: Andrzej Pietrasiewicz Link: https://lore.kernel.org/r/290f96db-1877-5137-373a-318e7b4f2dde@lineo.co.jp Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ddfc537c7526..a277c70aac84 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2292,8 +2292,11 @@ static int __ffs_do_os_desc_header(enum ffs_os_desc_type *next_type, u16 bcd_version = le16_to_cpu(desc->bcdVersion); u16 w_index = le16_to_cpu(desc->wIndex); - if (bcd_version != 1) { - pr_vdebug("unsupported os descriptors version: %d", + if (bcd_version == 0x1) { + pr_warn("bcdVersion must be 0x0100, stored in Little Endian order. " + "Userspace driver should be fixed, accepting 0x0001 for compatibility.\n"); + } else if (bcd_version != 0x100) { + pr_vdebug("unsupported os descriptors version: 0x%x\n", bcd_version); return -EINVAL; } -- GitLab From 195a58cb3617d46f274a8cb47ee151d74d39ce0e Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 27 Feb 2023 10:44:07 +0800 Subject: [PATCH 0194/5631] usb: cdns3: change trace event cdns3_ring() operation the original design seem have several problems, first during trace event output stage, cdns3_dbg_ring() still refer to priv_ep->trb_pool which data content may changed during runtime, second when ring number is greater than TRBS_PER_SEGMENT, it has no change to show "too big" message, third in cdns3_log_ring event class definition, it allocate too much trace event buffer. change cdns3_dbg_ring() to be called at trace event fast assign time, and change trace buffer real dynamic according ring numbers. Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/1677465850-1396-2-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdns3-debug.h | 8 ++------ drivers/usb/cdns3/cdns3-trace.h | 16 +++++----------- 2 files changed, 7 insertions(+), 17 deletions(-) diff --git a/drivers/usb/cdns3/cdns3-debug.h b/drivers/usb/cdns3/cdns3-debug.h index a5c6a29e1340..4618cfe85a4f 100644 --- a/drivers/usb/cdns3/cdns3-debug.h +++ b/drivers/usb/cdns3/cdns3-debug.h @@ -107,8 +107,7 @@ static inline char *cdns3_decode_ep0_irq(char *str, * Prints out all TRBs in the endpoint ring, even those after the Link TRB. *. */ -static inline char *cdns3_dbg_ring(struct cdns3_endpoint *priv_ep, - struct cdns3_trb *ring, char *str) +static inline char *cdns3_dbg_ring(struct cdns3_endpoint *priv_ep, char *str) { dma_addr_t addr = priv_ep->trb_pool_dma; struct cdns3_trb *trb; @@ -136,9 +135,6 @@ static inline char *cdns3_dbg_ring(struct cdns3_endpoint *priv_ep, "\t\tfree trbs: %d, CCS=%d, PCS=%d\n", priv_ep->free_trbs, priv_ep->ccs, priv_ep->pcs); - if (trb_per_sector > TRBS_PER_SEGMENT) - trb_per_sector = TRBS_PER_SEGMENT; - if (trb_per_sector > TRBS_PER_SEGMENT) { sprintf(str + ret, "\t\tTransfer ring %d too big\n", trb_per_sector); @@ -146,7 +142,7 @@ static inline char *cdns3_dbg_ring(struct cdns3_endpoint *priv_ep, } for (i = 0; i < trb_per_sector; ++i) { - trb = &ring[i]; + trb = &priv_ep->trb_pool[i]; ret += sprintf(str + ret, "\t\t@%pad %08x %08x %08x\n", &addr, le32_to_cpu(trb->buffer), diff --git a/drivers/usb/cdns3/cdns3-trace.h b/drivers/usb/cdns3/cdns3-trace.h index 7574b4a62813..99057186393b 100644 --- a/drivers/usb/cdns3/cdns3-trace.h +++ b/drivers/usb/cdns3/cdns3-trace.h @@ -438,22 +438,16 @@ DECLARE_EVENT_CLASS(cdns3_log_ring, TP_PROTO(struct cdns3_endpoint *priv_ep), TP_ARGS(priv_ep), TP_STRUCT__entry( - __dynamic_array(u8, ring, TRB_RING_SIZE) - __dynamic_array(u8, priv_ep, sizeof(struct cdns3_endpoint)) __dynamic_array(char, buffer, - (TRBS_PER_SEGMENT * 65) + CDNS3_MSG_MAX) + GET_TRBS_PER_SEGMENT(priv_ep->type) > TRBS_PER_SEGMENT ? + CDNS3_MSG_MAX : + (GET_TRBS_PER_SEGMENT(priv_ep->type) * 65) + CDNS3_MSG_MAX) ), TP_fast_assign( - memcpy(__get_dynamic_array(priv_ep), priv_ep, - sizeof(struct cdns3_endpoint)); - memcpy(__get_dynamic_array(ring), priv_ep->trb_pool, - TRB_RING_SIZE); + cdns3_dbg_ring(priv_ep, __get_str(buffer)); ), - TP_printk("%s", - cdns3_dbg_ring((struct cdns3_endpoint *)__get_str(priv_ep), - (struct cdns3_trb *)__get_str(ring), - __get_str(buffer))) + TP_printk("%s", __get_str(buffer)) ); DEFINE_EVENT(cdns3_log_ring, cdns3_ring, -- GitLab From 47ebfd604f9b48e44d2f88caf527180463a2fb2c Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 27 Feb 2023 10:44:08 +0800 Subject: [PATCH 0195/5631] usb: cdns3: change some trace event __dynamic_array() to __get_buf() some __dynamic_array() buffer will only used at trace event output time, change to __get_buf() which will allocate tempary trace seq buffer for output purpose. Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/1677465850-1396-3-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/cdns3/cdns3-trace.h | 12 ++++-------- drivers/usb/cdns3/cdnsp-trace.h | 12 ++++-------- 2 files changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/usb/cdns3/cdns3-trace.h b/drivers/usb/cdns3/cdns3-trace.h index 99057186393b..40db89e3333c 100644 --- a/drivers/usb/cdns3/cdns3-trace.h +++ b/drivers/usb/cdns3/cdns3-trace.h @@ -100,13 +100,12 @@ DECLARE_EVENT_CLASS(cdns3_log_usb_irq, TP_STRUCT__entry( __field(enum usb_device_speed, speed) __field(u32, usb_ists) - __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( __entry->speed = cdns3_get_speed(priv_dev); __entry->usb_ists = usb_ists; ), - TP_printk("%s", cdns3_decode_usb_irq(__get_str(str), __entry->speed, + TP_printk("%s", cdns3_decode_usb_irq(__get_buf(CDNS3_MSG_MAX), __entry->speed, __entry->usb_ists)) ); @@ -124,7 +123,6 @@ DECLARE_EVENT_CLASS(cdns3_log_epx_irq, __field(u32, ep_traddr) __field(u32, ep_last_sid) __field(u32, use_streams) - __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( __assign_str(ep_name, priv_ep->name); @@ -134,7 +132,7 @@ DECLARE_EVENT_CLASS(cdns3_log_epx_irq, __entry->use_streams = priv_ep->use_streams; ), TP_printk("%s, ep_traddr: %08x ep_last_sid: %08x use_streams: %d", - cdns3_decode_epx_irq(__get_str(str), + cdns3_decode_epx_irq(__get_buf(CDNS3_MSG_MAX), __get_str(ep_name), __entry->ep_sts), __entry->ep_traddr, @@ -153,13 +151,12 @@ DECLARE_EVENT_CLASS(cdns3_log_ep0_irq, TP_STRUCT__entry( __field(int, ep_dir) __field(u32, ep_sts) - __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( __entry->ep_dir = priv_dev->selected_ep; __entry->ep_sts = ep_sts; ), - TP_printk("%s", cdns3_decode_ep0_irq(__get_str(str), + TP_printk("%s", cdns3_decode_ep0_irq(__get_buf(CDNS3_MSG_MAX), __entry->ep_dir, __entry->ep_sts)) ); @@ -178,7 +175,6 @@ DECLARE_EVENT_CLASS(cdns3_log_ctrl, __field(u16, wValue) __field(u16, wIndex) __field(u16, wLength) - __dynamic_array(char, str, CDNS3_MSG_MAX) ), TP_fast_assign( __entry->bRequestType = ctrl->bRequestType; @@ -187,7 +183,7 @@ DECLARE_EVENT_CLASS(cdns3_log_ctrl, __entry->wIndex = le16_to_cpu(ctrl->wIndex); __entry->wLength = le16_to_cpu(ctrl->wLength); ), - TP_printk("%s", usb_decode_ctrl(__get_str(str), CDNS3_MSG_MAX, + TP_printk("%s", usb_decode_ctrl(__get_buf(CDNS3_MSG_MAX), CDNS3_MSG_MAX, __entry->bRequestType, __entry->bRequest, __entry->wValue, __entry->wIndex, __entry->wLength) diff --git a/drivers/usb/cdns3/cdnsp-trace.h b/drivers/usb/cdns3/cdnsp-trace.h index 5983dfb99653..4b51011eb00b 100644 --- a/drivers/usb/cdns3/cdnsp-trace.h +++ b/drivers/usb/cdns3/cdnsp-trace.h @@ -271,7 +271,6 @@ DECLARE_EVENT_CLASS(cdnsp_log_ctrl, __field(u16, wValue) __field(u16, wIndex) __field(u16, wLength) - __dynamic_array(char, str, CDNSP_MSG_MAX) ), TP_fast_assign( __entry->bRequestType = ctrl->bRequestType; @@ -280,7 +279,7 @@ DECLARE_EVENT_CLASS(cdnsp_log_ctrl, __entry->wIndex = le16_to_cpu(ctrl->wIndex); __entry->wLength = le16_to_cpu(ctrl->wLength); ), - TP_printk("%s", usb_decode_ctrl(__get_str(str), CDNSP_MSG_MAX, + TP_printk("%s", usb_decode_ctrl(__get_buf(CDNSP_MSG_MAX), CDNSP_MSG_MAX, __entry->bRequestType, __entry->bRequest, __entry->wValue, __entry->wIndex, __entry->wLength) @@ -345,7 +344,6 @@ DECLARE_EVENT_CLASS(cdnsp_log_trb, __field(u32, field3) __field(union cdnsp_trb *, trb) __field(dma_addr_t, trb_dma) - __dynamic_array(char, str, CDNSP_MSG_MAX) ), TP_fast_assign( __entry->type = ring->type; @@ -359,7 +357,7 @@ DECLARE_EVENT_CLASS(cdnsp_log_trb, ), TP_printk("%s: %s trb: %p(%pad)", cdnsp_ring_type_string(__entry->type), - cdnsp_decode_trb(__get_str(str), CDNSP_MSG_MAX, + cdnsp_decode_trb(__get_buf(CDNSP_MSG_MAX), CDNSP_MSG_MAX, __entry->field0, __entry->field1, __entry->field2, __entry->field3), __entry->trb, &__entry->trb_dma @@ -544,7 +542,6 @@ DECLARE_EVENT_CLASS(cdnsp_log_ep_ctx, __field(u32, info2) __field(u64, deq) __field(u32, tx_info) - __dynamic_array(char, str, CDNSP_MSG_MAX) ), TP_fast_assign( __entry->info = le32_to_cpu(ctx->ep_info); @@ -552,7 +549,7 @@ DECLARE_EVENT_CLASS(cdnsp_log_ep_ctx, __entry->deq = le64_to_cpu(ctx->deq); __entry->tx_info = le32_to_cpu(ctx->tx_info); ), - TP_printk("%s", cdnsp_decode_ep_context(__get_str(str), CDNSP_MSG_MAX, + TP_printk("%s", cdnsp_decode_ep_context(__get_buf(CDNSP_MSG_MAX), CDNSP_MSG_MAX, __entry->info, __entry->info2, __entry->deq, __entry->tx_info) ) @@ -777,7 +774,6 @@ DECLARE_EVENT_CLASS(cdnsp_log_portsc, TP_STRUCT__entry( __field(u32, portnum) __field(u32, portsc) - __dynamic_array(char, str, CDNSP_MSG_MAX) ), TP_fast_assign( __entry->portnum = portnum; @@ -785,7 +781,7 @@ DECLARE_EVENT_CLASS(cdnsp_log_portsc, ), TP_printk("port-%d: %s", __entry->portnum, - cdnsp_decode_portsc(__get_str(str), CDNSP_MSG_MAX, + cdnsp_decode_portsc(__get_buf(CDNSP_MSG_MAX), CDNSP_MSG_MAX, __entry->portsc) ) ); -- GitLab From f09d24aa463c51672ff37462fed17eff824b8b18 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 27 Feb 2023 10:44:09 +0800 Subject: [PATCH 0196/5631] usb: dwc3: change some trace event __dynamic_array() to __get_buf() some __dynamic_array() buffer will only used at trace event output time, change to __get_buf() which will allocate tempary trace seq buffer for output purpose. Signed-off-by: Linyu Yuan Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/1677465850-1396-4-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/trace.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/dwc3/trace.h b/drivers/usb/dwc3/trace.h index 1975aec8d36d..d2997d17cfbe 100644 --- a/drivers/usb/dwc3/trace.h +++ b/drivers/usb/dwc3/trace.h @@ -54,14 +54,13 @@ DECLARE_EVENT_CLASS(dwc3_log_event, TP_STRUCT__entry( __field(u32, event) __field(u32, ep0state) - __dynamic_array(char, str, DWC3_MSG_MAX) ), TP_fast_assign( __entry->event = event; __entry->ep0state = dwc->ep0state; ), TP_printk("event (%08x): %s", __entry->event, - dwc3_decode_event(__get_str(str), DWC3_MSG_MAX, + dwc3_decode_event(__get_buf(DWC3_MSG_MAX), DWC3_MSG_MAX, __entry->event, __entry->ep0state)) ); @@ -79,7 +78,6 @@ DECLARE_EVENT_CLASS(dwc3_log_ctrl, __field(__u16, wValue) __field(__u16, wIndex) __field(__u16, wLength) - __dynamic_array(char, str, DWC3_MSG_MAX) ), TP_fast_assign( __entry->bRequestType = ctrl->bRequestType; @@ -88,7 +86,7 @@ DECLARE_EVENT_CLASS(dwc3_log_ctrl, __entry->wIndex = le16_to_cpu(ctrl->wIndex); __entry->wLength = le16_to_cpu(ctrl->wLength); ), - TP_printk("%s", usb_decode_ctrl(__get_str(str), DWC3_MSG_MAX, + TP_printk("%s", usb_decode_ctrl(__get_buf(DWC3_MSG_MAX), DWC3_MSG_MAX, __entry->bRequestType, __entry->bRequest, __entry->wValue, __entry->wIndex, __entry->wLength) -- GitLab From 7d1a898f52288f068f163aa970f029872c21c031 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 27 Feb 2023 10:44:10 +0800 Subject: [PATCH 0197/5631] usb: xhci: change some trace event __dynamic_array() to __get_buf() some __dynamic_array() buffer will only used at trace event output time, change to __get_buf() which will allocate tempary trace seq buffer for output purpose. Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/1677465850-1396-5-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-trace.h | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/usb/host/xhci-trace.h b/drivers/usb/host/xhci-trace.h index 61e93a3540a7..4286dba5b157 100644 --- a/drivers/usb/host/xhci-trace.h +++ b/drivers/usb/host/xhci-trace.h @@ -120,7 +120,6 @@ DECLARE_EVENT_CLASS(xhci_log_trb, __field(u32, field1) __field(u32, field2) __field(u32, field3) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->type = ring->type; @@ -130,8 +129,8 @@ DECLARE_EVENT_CLASS(xhci_log_trb, __entry->field3 = le32_to_cpu(trb->field[3]); ), TP_printk("%s: %s", xhci_ring_type_string(__entry->type), - xhci_decode_trb(__get_str(str), XHCI_MSG_MAX, __entry->field0, __entry->field1, - __entry->field2, __entry->field3) + xhci_decode_trb(__get_buf(XHCI_MSG_MAX), XHCI_MSG_MAX, __entry->field0, + __entry->field1, __entry->field2, __entry->field3) ) ); @@ -322,7 +321,6 @@ DECLARE_EVENT_CLASS(xhci_log_ep_ctx, __field(u32, info2) __field(u64, deq) __field(u32, tx_info) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->info = le32_to_cpu(ctx->ep_info); @@ -330,7 +328,7 @@ DECLARE_EVENT_CLASS(xhci_log_ep_ctx, __entry->deq = le64_to_cpu(ctx->deq); __entry->tx_info = le32_to_cpu(ctx->tx_info); ), - TP_printk("%s", xhci_decode_ep_context(__get_str(str), + TP_printk("%s", xhci_decode_ep_context(__get_buf(XHCI_MSG_MAX), __entry->info, __entry->info2, __entry->deq, __entry->tx_info) ) ); @@ -368,7 +366,6 @@ DECLARE_EVENT_CLASS(xhci_log_slot_ctx, __field(u32, info2) __field(u32, tt_info) __field(u32, state) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->info = le32_to_cpu(ctx->dev_info); @@ -376,7 +373,7 @@ DECLARE_EVENT_CLASS(xhci_log_slot_ctx, __entry->tt_info = le64_to_cpu(ctx->tt_info); __entry->state = le32_to_cpu(ctx->dev_state); ), - TP_printk("%s", xhci_decode_slot_context(__get_str(str), + TP_printk("%s", xhci_decode_slot_context(__get_buf(XHCI_MSG_MAX), __entry->info, __entry->info2, __entry->tt_info, __entry->state) ) @@ -433,13 +430,12 @@ DECLARE_EVENT_CLASS(xhci_log_ctrl_ctx, TP_STRUCT__entry( __field(u32, drop) __field(u32, add) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->drop = le32_to_cpu(ctrl_ctx->drop_flags); __entry->add = le32_to_cpu(ctrl_ctx->add_flags); ), - TP_printk("%s", xhci_decode_ctrl_ctx(__get_str(str), __entry->drop, __entry->add) + TP_printk("%s", xhci_decode_ctrl_ctx(__get_buf(XHCI_MSG_MAX), __entry->drop, __entry->add) ) ); @@ -525,7 +521,6 @@ DECLARE_EVENT_CLASS(xhci_log_portsc, TP_STRUCT__entry( __field(u32, portnum) __field(u32, portsc) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->portnum = portnum; @@ -533,7 +528,7 @@ DECLARE_EVENT_CLASS(xhci_log_portsc, ), TP_printk("port-%d: %s", __entry->portnum, - xhci_decode_portsc(__get_str(str), __entry->portsc) + xhci_decode_portsc(__get_buf(XHCI_MSG_MAX), __entry->portsc) ) ); @@ -558,14 +553,13 @@ DECLARE_EVENT_CLASS(xhci_log_doorbell, TP_STRUCT__entry( __field(u32, slot) __field(u32, doorbell) - __dynamic_array(char, str, XHCI_MSG_MAX) ), TP_fast_assign( __entry->slot = slot; __entry->doorbell = doorbell; ), TP_printk("Ring doorbell for %s", - xhci_decode_doorbell(__get_str(str), __entry->slot, __entry->doorbell) + xhci_decode_doorbell(__get_buf(XHCI_MSG_MAX), __entry->slot, __entry->doorbell) ) ); -- GitLab From 3754c41c76867e41fe720555dc186ba4b3cccad9 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 3 Feb 2023 09:45:26 +0800 Subject: [PATCH 0198/5631] dt-bindings: usb: snps,dwc3: support i.MX8MQ i.MX8MQ use Synopsys DesignWare USB3 Controller IP, so add the compatible. Signed-off-by: Peng Fan Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230203014526.1461386-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/snps,dwc3.yaml | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index c167fd577cae..16c7d06c9172 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -30,11 +30,13 @@ allOf: properties: compatible: - contains: - oneOf: - - const: snps,dwc3 - - const: synopsys,dwc3 - deprecated: true + oneOf: + - items: + - const: fsl,imx8mq-dwc3 + - const: snps,dwc3 + - const: snps,dwc3 + - const: synopsys,dwc3 + deprecated: true reg: maxItems: 1 -- GitLab From 728648c7c8bb054023b9b9f367e349d5b0afafd8 Mon Sep 17 00:00:00 2001 From: Li zeming Date: Thu, 23 Feb 2023 04:23:03 +0800 Subject: [PATCH 0199/5631] tty: tty_ldisc: Remove the ret variable The int variable ret does not receive the return value in this function. It should be removed and returned 0 directly. Signed-off-by: Li zeming Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/20230222202303.3195-1-zeming@nfschina.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ldisc.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index e758f44729e7..3f68e213df1f 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -58,7 +58,6 @@ static struct tty_ldisc_ops *tty_ldiscs[NR_LDISCS]; int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc) { unsigned long flags; - int ret = 0; if (new_ldisc->num < N_TTY || new_ldisc->num >= NR_LDISCS) return -EINVAL; @@ -67,7 +66,7 @@ int tty_register_ldisc(struct tty_ldisc_ops *new_ldisc) tty_ldiscs[new_ldisc->num] = new_ldisc; raw_spin_unlock_irqrestore(&tty_ldiscs_lock, flags); - return ret; + return 0; } EXPORT_SYMBOL(tty_register_ldisc); -- GitLab From cf8d4027a748b713d239cedaa77193e2e60b8811 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 19 Feb 2023 15:22:49 +0100 Subject: [PATCH 0200/5631] dt-bindings: serial: imx: Document optional DMA properties The UART IP can be connected to DMA engine, document the properties in DT bindings. Update example to match Linux arch/arm/boot/dts/imx51.dtsi . Acked-by: Krzysztof Kozlowski Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20230219142250.10176-1-marex@denx.de Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/serial/fsl-imx-uart.yaml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml index 4cbe76e1715b..c22aab8c55f8 100644 --- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml +++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml @@ -49,6 +49,16 @@ properties: reg: maxItems: 1 + dmas: + items: + - description: DMA controller phandle and request line for RX + - description: DMA controller phandle and request line for TX + + dma-names: + items: + - const: rx + - const: tx + interrupts: maxItems: 1 @@ -100,6 +110,8 @@ examples: compatible = "fsl,imx51-uart", "fsl,imx21-uart"; reg = <0x73fbc000 0x4000>; interrupts = <31>; + dmas = <&sdma 18 4 1>, <&sdma 19 4 2>; + dma-names = "rx", "tx"; uart-has-rtscts; fsl,dte-mode; }; -- GitLab From 872eb918d8e10a6293240e0dd89a45842079c03c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 19 Feb 2023 15:22:50 +0100 Subject: [PATCH 0201/5631] dt-bindings: serial: imx: Document mandatory clock properties The UART IP must be connected to clock, document the properties in DT bindings. Update example to match Linux arch/arm/boot/dts/imx51.dtsi . Signed-off-by: Marek Vasut Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230219142250.10176-2-marex@denx.de Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/serial/fsl-imx-uart.yaml | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml index c22aab8c55f8..40414247d61a 100644 --- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml +++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml @@ -49,6 +49,14 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 2 + + clock-names: + items: + - const: ipg + - const: per + dmas: items: - description: DMA controller phandle and request line for RX @@ -96,12 +104,16 @@ properties: required: - compatible - reg + - clocks + - clock-names - interrupts unevaluatedProperties: false examples: - | + #include + aliases { serial0 = &uart1; }; @@ -110,6 +122,9 @@ examples: compatible = "fsl,imx51-uart", "fsl,imx21-uart"; reg = <0x73fbc000 0x4000>; interrupts = <31>; + clocks = <&clks IMX5_CLK_UART1_IPG_GATE>, + <&clks IMX5_CLK_UART1_PER_GATE>; + clock-names = "ipg", "per"; dmas = <&sdma 18 4 1>, <&sdma 19 4 2>; dma-names = "rx", "tx"; uart-has-rtscts; -- GitLab From 46ce64bbfe0c84d1cf14fb325c8c7c323cabf3b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 2 Mar 2023 12:54:17 +0100 Subject: [PATCH 0202/5631] serial: imx: Drop a few unneeded casts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no point in casting a struct uart_port to a struct imx_port just to access the first member of the latter (a struct uart_port). This introduces no code changes. Signed-off-by: Uwe Kleine-König Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230302115417.1860210-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 523f296d5747..84bc0e768726 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -1808,9 +1808,7 @@ imx_uart_set_termios(struct uart_port *port, struct ktermios *termios, static const char *imx_uart_type(struct uart_port *port) { - struct imx_port *sport = (struct imx_port *)port; - - return sport->port.type == PORT_IMX ? "IMX" : NULL; + return port->type == PORT_IMX ? "IMX" : NULL; } /* @@ -1818,10 +1816,8 @@ static const char *imx_uart_type(struct uart_port *port) */ static void imx_uart_config_port(struct uart_port *port, int flags) { - struct imx_port *sport = (struct imx_port *)port; - if (flags & UART_CONFIG_TYPE) - sport->port.type = PORT_IMX; + port->type = PORT_IMX; } /* @@ -1832,20 +1828,19 @@ static void imx_uart_config_port(struct uart_port *port, int flags) static int imx_uart_verify_port(struct uart_port *port, struct serial_struct *ser) { - struct imx_port *sport = (struct imx_port *)port; int ret = 0; if (ser->type != PORT_UNKNOWN && ser->type != PORT_IMX) ret = -EINVAL; - if (sport->port.irq != ser->irq) + if (port->irq != ser->irq) ret = -EINVAL; if (ser->io_type != UPIO_MEM) ret = -EINVAL; - if (sport->port.uartclk / 16 != ser->baud_base) + if (port->uartclk / 16 != ser->baud_base) ret = -EINVAL; - if (sport->port.mapbase != (unsigned long)ser->iomem_base) + if (port->mapbase != (unsigned long)ser->iomem_base) ret = -EINVAL; - if (sport->port.iobase != ser->port) + if (port->iobase != ser->port) ret = -EINVAL; if (ser->hub6 != 0) ret = -EINVAL; -- GitLab From 6d12b774c9295a04695d52e38b1517e9a41f9881 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:11 -0800 Subject: [PATCH 0203/5631] tty: simplify sysctl registration register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl_init() can do the directory creation for you so just use that Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230302204612.782387-7-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_io.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 36fb945fdad4..766750e355ac 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3614,31 +3614,13 @@ static struct ctl_table tty_table[] = { { } }; -static struct ctl_table tty_dir_table[] = { - { - .procname = "tty", - .mode = 0555, - .child = tty_table, - }, - { } -}; - -static struct ctl_table tty_root_table[] = { - { - .procname = "dev", - .mode = 0555, - .child = tty_dir_table, - }, - { } -}; - /* * Ok, now we can initialize the rest of the tty devices and can count * on memory allocations, interrupts etc.. */ int __init tty_init(void) { - register_sysctl_table(tty_root_table); + register_sysctl_init("dev/tty", tty_table); cdev_init(&tty_cdev, &tty_fops); if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0) -- GitLab From b4fd0afaa07f9f46c733e7cf17e4b4cb45461c3c Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 23 Feb 2023 05:22:51 +0100 Subject: [PATCH 0204/5631] serial: stm32: Remove unused struct stm32_port txdone element The txdone element is only ever assigned, once, and never used. Drop it. Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20230223042252.95480-1-marex@denx.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/stm32-usart.c | 1 - drivers/tty/serial/stm32-usart.h | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 767ff9fdb2e5..bf51e2152dd5 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -743,7 +743,6 @@ static void stm32_usart_transmit_chars(struct uart_port *port) stm32_usart_tx_interrupt_disable(port); if (!stm32_port->hw_flow_control && port->rs485.flags & SER_RS485_ENABLED) { - stm32_port->txdone = true; stm32_usart_tc_interrupt_enable(port); } } diff --git a/drivers/tty/serial/stm32-usart.h b/drivers/tty/serial/stm32-usart.h index 0ec41a732c88..903285b5aea7 100644 --- a/drivers/tty/serial/stm32-usart.h +++ b/drivers/tty/serial/stm32-usart.h @@ -203,7 +203,6 @@ struct stm32_port { bool hw_flow_control; bool swap; /* swap RX & TX pins */ bool fifoen; - bool txdone; int rxftcfg; /* RX FIFO threshold CFG */ int txftcfg; /* TX FIFO threshold CFG */ bool wakeup_src; -- GitLab From c47527cbcc3c50800f34b8c684f29721f75de246 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 23 Feb 2023 05:22:52 +0100 Subject: [PATCH 0205/5631] serial: stm32: Re-assert RTS/DE GPIO in RS485 mode only if more data are transmitted The stm32_usart_transmit_chars() may be called with empty or stopped transmit queue, and no XON/OFF character pending. This can happen at the end of transmission, where this last call is used to either handle the XON/XOFF x_char, or disable TX interrupt if queue is empty or stopped. If that occurs, do not assert the RS485 RTS/DE GPIO anymore, as the GPIO would remain asserted past the end of transmission and that would block the RS485 bus after the transmission. Only assert the RS485 RTS/DE GPIO if there is either pending XON/XOFF x_char, or at least one character in running transmit queue. Fixes: d7c76716169d ("serial: stm32: Use TC interrupt to deassert GPIO RTS in RS485 mode") Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20230223042252.95480-2-marex@denx.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/stm32-usart.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index bf51e2152dd5..1e38fc9b10c1 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -693,8 +693,9 @@ static void stm32_usart_transmit_chars(struct uart_port *port) int ret; if (!stm32_port->hw_flow_control && - port->rs485.flags & SER_RS485_ENABLED) { - stm32_port->txdone = false; + port->rs485.flags & SER_RS485_ENABLED && + (port->x_char || + !(uart_circ_empty(xmit) || uart_tx_stopped(port)))) { stm32_usart_tc_interrupt_disable(port); stm32_usart_rs485_rts_enable(port); } -- GitLab From 85bce38a7e1f392f5051e67fd5fcfbffe71e9b81 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 17 Feb 2023 21:22:57 +0100 Subject: [PATCH 0206/5631] serial: 8250: Reorder fields in 'struct plat_serial8250_port' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct plat_serial8250_port' from 144 to 128 bytes. It saves a few bytes of memory. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/f3cb1efe1454e0615840fd331ee335bc441589a9.1676665358.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 19376bee9667..741ed4807a9c 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -18,16 +18,16 @@ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ resource_size_t mapbase; /* resource base */ + unsigned int uartclk; /* UART clock rate */ unsigned int irq; /* interrupt number */ unsigned long irqflags; /* request_irq flags */ - unsigned int uartclk; /* UART clock rate */ void *private_data; unsigned char regshift; /* register shift */ unsigned char iotype; /* UPIO_* */ unsigned char hub6; unsigned char has_sysrq; /* supports magic SysRq */ - upf_t flags; /* UPF_* flags */ unsigned int type; /* If UPF_FIXED_TYPE */ + upf_t flags; /* UPF_* flags */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, -- GitLab From cb46a3e2d6b8e937f44f73a6991f7e3d60008449 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bernhard=20Rosenkr=C3=A4nzer?= Date: Thu, 9 Mar 2023 15:34:58 +0100 Subject: [PATCH 0207/5631] dt-bindings: serial: mediatek,uart: add MT8365 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add binding description for mediatek,mt8365-uart Signed-off-by: Bernhard Rosenkränzer Acked-by: Krzysztof Kozlowski Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230309143459.401783-3-bero@baylibre.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/mediatek,uart.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/serial/mediatek,uart.yaml b/Documentation/devicetree/bindings/serial/mediatek,uart.yaml index fe098d98af6e..303d02ca4e1b 100644 --- a/Documentation/devicetree/bindings/serial/mediatek,uart.yaml +++ b/Documentation/devicetree/bindings/serial/mediatek,uart.yaml @@ -45,6 +45,7 @@ properties: - mediatek,mt8188-uart - mediatek,mt8192-uart - mediatek,mt8195-uart + - mediatek,mt8365-uart - mediatek,mt8516-uart - const: mediatek,mt6577-uart -- GitLab From add5dfe87abe962cf9884193d9467f23d898fb8b Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Tue, 7 Mar 2023 23:26:49 +0100 Subject: [PATCH 0208/5631] dt-bindings: serial: amlogic,meson-uart: Add compatible string for G12A Amlogic G12A SoCs gained a new "divide XTAL by 2" bit. Everything else (we know about) is identical to the UART IP on GX (GXBB/GXL/GXM) SoCs. Add a new compatible string for this SoC so this new bit can be managed accordingly while keeping "amlogic,meson-gx-uart" as fallback compatible string. Signed-off-by: Martin Blumenstingl Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230307222651.2106615-2-martin.blumenstingl@googlemail.com Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/serial/amlogic,meson-uart.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml index 3cbdde85ed71..22656efe8ddc 100644 --- a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml +++ b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml @@ -34,6 +34,11 @@ properties: - amlogic,meson-gx-uart - amlogic,meson-s4-uart - const: amlogic,meson-ao-uart + - description: Always-on power domain UART controller on G12A SoCs + items: + - const: amlogic,meson-g12a-uart + - const: amlogic,meson-gx-uart + - const: amlogic,meson-ao-uart - description: Everything-Else power domain UART controller enum: - amlogic,meson6-uart @@ -41,6 +46,10 @@ properties: - amlogic,meson8b-uart - amlogic,meson-gx-uart - amlogic,meson-s4-uart + - description: Everything-Else power domain UART controller on G12A SoCs + items: + - const: amlogic,meson-g12a-uart + - const: amlogic,meson-gx-uart reg: maxItems: 1 -- GitLab From 804e6d6998f7528d23e9cb16f9dbb357bfab5f77 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Tue, 7 Mar 2023 23:26:50 +0100 Subject: [PATCH 0209/5631] tty: serial: meson: Add a new compatible string for the G12A SoC Amlogic Meson G12A (and later) SoCs also have the "divide XTAL by 2" bit as the S4 UART controllers. Add a new compatible string for these SoCs and enable the has_xtal_div2 flag for them. Tested-by: Christian Hewitt Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230307222651.2106615-3-martin.blumenstingl@googlemail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/meson_uart.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/meson_uart.c b/drivers/tty/serial/meson_uart.c index 74110017988a..2501db5a7aaf 100644 --- a/drivers/tty/serial/meson_uart.c +++ b/drivers/tty/serial/meson_uart.c @@ -779,7 +779,7 @@ static int meson_uart_remove(struct platform_device *pdev) return 0; } -static struct meson_uart_data s4_uart_data = { +static struct meson_uart_data meson_g12a_uart_data = { .has_xtal_div2 = true, }; @@ -788,9 +788,13 @@ static const struct of_device_id meson_uart_dt_match[] = { { .compatible = "amlogic,meson8-uart" }, { .compatible = "amlogic,meson8b-uart" }, { .compatible = "amlogic,meson-gx-uart" }, + { + .compatible = "amlogic,meson-g12a-uart", + .data = (void *)&meson_g12a_uart_data, + }, { .compatible = "amlogic,meson-s4-uart", - .data = (void *)&s4_uart_data, + .data = (void *)&meson_g12a_uart_data, }, { /* sentinel */ }, }; -- GitLab From f335201ba28fc20f7878127455dbae6e2f8eb6de Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Tue, 7 Mar 2023 23:26:51 +0100 Subject: [PATCH 0210/5631] arm64: dts: meson-g12-common: Use the G12A UART compatible string Switch meson-12-common.dtsi to use the Meson G12A specific UART compatible string. This enables the "divide XTAL by 2" divider which improves support for UART attached Bluetooth modules (for example RTL8822CS) running at a baud rate of 1500000. Without dividing XTAL (24MHz) by 2 a baud rate of 1500000 cannot be generated cleanly and the resulting jitter breaks communication with the module. Tested-by: Christian Hewitt Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230307222651.2106615-4-martin.blumenstingl@googlemail.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 123a56f7f818..904bcd4d2acf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2046,7 +2046,8 @@ }; uart_AO: serial@3000 { - compatible = "amlogic,meson-gx-uart", + compatible = "amlogic,meson-g12a-uart", + "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; reg = <0x0 0x3000 0x0 0x18>; interrupts = ; @@ -2056,7 +2057,8 @@ }; uart_AO_B: serial@4000 { - compatible = "amlogic,meson-gx-uart", + compatible = "amlogic,meson-g12a-uart", + "amlogic,meson-gx-uart", "amlogic,meson-ao-uart"; reg = <0x0 0x4000 0x0 0x18>; interrupts = ; @@ -2293,7 +2295,8 @@ }; uart_C: serial@22000 { - compatible = "amlogic,meson-gx-uart"; + compatible = "amlogic,meson-g12a-uart", + "amlogic,meson-gx-uart"; reg = <0x0 0x22000 0x0 0x18>; interrupts = ; clocks = <&xtal>, <&clkc CLKID_UART2>, <&xtal>; @@ -2302,7 +2305,8 @@ }; uart_B: serial@23000 { - compatible = "amlogic,meson-gx-uart"; + compatible = "amlogic,meson-g12a-uart", + "amlogic,meson-gx-uart"; reg = <0x0 0x23000 0x0 0x18>; interrupts = ; clocks = <&xtal>, <&clkc CLKID_UART1>, <&xtal>; @@ -2311,7 +2315,8 @@ }; uart_A: serial@24000 { - compatible = "amlogic,meson-gx-uart"; + compatible = "amlogic,meson-g12a-uart", + "amlogic,meson-gx-uart"; reg = <0x0 0x24000 0x0 0x18>; interrupts = ; clocks = <&xtal>, <&clkc CLKID_UART0>, <&xtal>; -- GitLab From 302a22a4fa8a4e3216161b3cb63acc434afc87f5 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:46 +0000 Subject: [PATCH 0211/5631] serial: 8250_em: Fix UART port type As per HW manual for EMEV2 "R19UH0040EJ0400 Rev.4.00", the UART IP found on EMMA mobile SoC is Register-compatible with the general-purpose 16750 UART chip. Fix UART port type as 16750 and enable 64-bytes fifo support. Fixes: 22886ee96895 ("serial8250-em: Emma Mobile UART driver V2") Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-2-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index f8e99995eee9..d94c3811a8f7 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -106,8 +106,8 @@ static int serial8250_em_probe(struct platform_device *pdev) memset(&up, 0, sizeof(up)); up.port.mapbase = regs->start; up.port.irq = irq; - up.port.type = PORT_UNKNOWN; - up.port.flags = UPF_BOOT_AUTOCONF | UPF_FIXED_PORT | UPF_IOREMAP; + up.port.type = PORT_16750; + up.port.flags = UPF_FIXED_PORT | UPF_IOREMAP | UPF_FIXED_TYPE; up.port.dev = &pdev->dev; up.port.private_data = priv; -- GitLab From 6b5f1e2e22ffd562075eaf6e018607e7dffe154d Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:47 +0000 Subject: [PATCH 0212/5631] serial: 8250_em: Simplify probe() Simplify probe() by using dev_err_probe() instead of dev_err() and add a local variable 'dev' to replace '&pdev->dev'. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-3-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index d94c3811a8f7..17c0aa424df8 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -79,6 +79,7 @@ static void serial8250_em_serial_dl_write(struct uart_8250_port *up, int value) static int serial8250_em_probe(struct platform_device *pdev) { struct serial8250_em_priv *priv; + struct device *dev = &pdev->dev; struct uart_8250_port up; struct resource *regs; int irq, ret; @@ -88,27 +89,23 @@ static int serial8250_em_probe(struct platform_device *pdev) return irq; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!regs) { - dev_err(&pdev->dev, "missing registers\n"); - return -EINVAL; - } + if (!regs) + return dev_err_probe(dev, -EINVAL, "missing registers\n"); - priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - priv->sclk = devm_clk_get(&pdev->dev, "sclk"); - if (IS_ERR(priv->sclk)) { - dev_err(&pdev->dev, "unable to get clock\n"); - return PTR_ERR(priv->sclk); - } + priv->sclk = devm_clk_get(dev, "sclk"); + if (IS_ERR(priv->sclk)) + return dev_err_probe(dev, PTR_ERR(priv->sclk), "unable to get clock\n"); memset(&up, 0, sizeof(up)); up.port.mapbase = regs->start; up.port.irq = irq; up.port.type = PORT_16750; up.port.flags = UPF_FIXED_PORT | UPF_IOREMAP | UPF_FIXED_TYPE; - up.port.dev = &pdev->dev; + up.port.dev = dev; up.port.private_data = priv; clk_prepare_enable(priv->sclk); @@ -122,9 +119,8 @@ static int serial8250_em_probe(struct platform_device *pdev) ret = serial8250_register_8250_port(&up); if (ret < 0) { - dev_err(&pdev->dev, "unable to register 8250 port\n"); clk_disable_unprepare(priv->sclk); - return ret; + return dev_err_probe(dev, ret, "unable to register 8250 port\n"); } priv->line = ret; -- GitLab From e335354d2348ce2ea0d3e978b2f49c64354ca189 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:48 +0000 Subject: [PATCH 0213/5631] serial: 8250_em: Drop unused header file Drop unused header file slab.h from the driver. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-4-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index 17c0aa424df8..045a2110b5c5 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -13,7 +13,6 @@ #include #include #include -#include #include "8250.h" -- GitLab From 54769d865683e96eeca32e325f586978c11fbbb7 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:49 +0000 Subject: [PATCH 0214/5631] serial: 8250_em: Add missing break statement Add missing break statement in serial8250_em_serial_out(). Suggested-by: Andy Shevchenko Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-5-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index 045a2110b5c5..621abca93694 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -42,6 +42,7 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) case UART_DLL_EM: /* DLL @ 0x24 (+9) */ case UART_DLM_EM: /* DLM @ 0x28 (+9) */ writel(value, p->membase + (offset << 2)); + break; } } -- GitLab From 7eada8a122a2683ec63ad43982a4552b054d59ca Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:50 +0000 Subject: [PATCH 0215/5631] serial: 8250_em: Use devm_clk_get_enabled() Simplify clk handling in probe() by replacing devm_clk_get()->devm_ clk_get_enabled(). This replaces the usage of clk_prepare_enable/clk_ disable_unprepare() in probe()/remove(). After that sclk is no longer required in struct serial8250_em_priv and is replaced by a local variable sclk in probe(). Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-6-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index 621abca93694..dcf1761e8ef5 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -20,7 +20,6 @@ #define UART_DLM_EM 10 struct serial8250_em_priv { - struct clk *sclk; int line; }; @@ -82,6 +81,7 @@ static int serial8250_em_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct uart_8250_port up; struct resource *regs; + struct clk *sclk; int irq, ret; irq = platform_get_irq(pdev, 0); @@ -96,9 +96,9 @@ static int serial8250_em_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->sclk = devm_clk_get(dev, "sclk"); - if (IS_ERR(priv->sclk)) - return dev_err_probe(dev, PTR_ERR(priv->sclk), "unable to get clock\n"); + sclk = devm_clk_get_enabled(dev, "sclk"); + if (IS_ERR(sclk)) + return dev_err_probe(dev, PTR_ERR(sclk), "unable to get clock\n"); memset(&up, 0, sizeof(up)); up.port.mapbase = regs->start; @@ -108,8 +108,7 @@ static int serial8250_em_probe(struct platform_device *pdev) up.port.dev = dev; up.port.private_data = priv; - clk_prepare_enable(priv->sclk); - up.port.uartclk = clk_get_rate(priv->sclk); + up.port.uartclk = clk_get_rate(sclk); up.port.iotype = UPIO_MEM32; up.port.serial_in = serial8250_em_serial_in; @@ -118,10 +117,8 @@ static int serial8250_em_probe(struct platform_device *pdev) up.dl_write = serial8250_em_serial_dl_write; ret = serial8250_register_8250_port(&up); - if (ret < 0) { - clk_disable_unprepare(priv->sclk); + if (ret < 0) return dev_err_probe(dev, ret, "unable to register 8250 port\n"); - } priv->line = ret; platform_set_drvdata(pdev, priv); @@ -133,7 +130,6 @@ static int serial8250_em_remove(struct platform_device *pdev) struct serial8250_em_priv *priv = platform_get_drvdata(pdev); serial8250_unregister_port(priv->line); - clk_disable_unprepare(priv->sclk); return 0; } -- GitLab From 59d6558fb5fd750777edfde028ea1f9e7eed8a46 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:51 +0000 Subject: [PATCH 0216/5631] serial: 8250_em: Use pseudo offset for UART_FCR MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UART_FCR shares the same offset with UART_IIR. We cannot use UART_FCR in serial8250_em_serial_in() as it overlaps with UART_IIR. Define UART_FCR_EM macro with a high value to avoid overlapping with existing UART_* register defines and define another macro UART_FCR_EM_HW for the real offset. Use these macros in serial8250_em_serial{_in/_out} function to read/write FCR register. Suggested-by: Ilpo Järvinen Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-7-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index dcf1761e8ef5..7614ced9377e 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -19,6 +19,13 @@ #define UART_DLL_EM 9 #define UART_DLM_EM 10 +/* + * A high value for UART_FCR_EM avoids overlapping with existing UART_* + * register defines. UART_FCR_EM_HW is the real HW register offset. + */ +#define UART_FCR_EM 0x10003 +#define UART_FCR_EM_HW 3 + struct serial8250_em_priv { int line; }; @@ -29,12 +36,15 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) case UART_TX: /* TX @ 0x00 */ writeb(value, p->membase); break; - case UART_FCR: /* FCR @ 0x0c (+1) */ case UART_LCR: /* LCR @ 0x10 (+1) */ case UART_MCR: /* MCR @ 0x14 (+1) */ case UART_SCR: /* SCR @ 0x20 (+1) */ writel(value, p->membase + ((offset + 1) << 2)); break; + case UART_FCR: + case UART_FCR_EM: + writel(value, p->membase + (UART_FCR_EM_HW << 2)); + break; case UART_IER: /* IER @ 0x04 */ value &= 0x0f; /* only 4 valid bits - not Xscale */ fallthrough; @@ -55,6 +65,8 @@ static unsigned int serial8250_em_serial_in(struct uart_port *p, int offset) case UART_MSR: /* MSR @ 0x1c (+1) */ case UART_SCR: /* SCR @ 0x20 (+1) */ return readl(p->membase + ((offset + 1) << 2)); + case UART_FCR_EM: + return readl(p->membase + (UART_FCR_EM_HW << 2)); case UART_IER: /* IER @ 0x04 */ case UART_IIR: /* IIR @ 0x08 */ case UART_DLL_EM: /* DLL @ 0x24 (+9) */ -- GitLab From b22ea7df56b2ee1f9a0212210b51f83a3c2c75c6 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Mon, 27 Feb 2023 11:41:52 +0000 Subject: [PATCH 0217/5631] serial: 8250_em: Add serial8250_em_{reg_update(),out_helper()} As per RZ/V2M hardware manual(Rev.1.30 Jun, 2022), UART IP has a restriction as mentioned below. 40.6.1 Point for Caution when Changing the Register Settings: When changing the settings of the following registers, a PRESETn master reset or FIFO reset + SW reset (FCR[2],FCR[1], HCR0[7]) must be input to re-initialize them. Target Registers: FCR, LCR, MCR, DLL, DLM, HCR0. Add serial8250_em_reg_update() and serial8250_em_serial_out_helper() to handle this restriction. serial8250_em_serial_out_helper() is identical to previous serial8250_em_serial_out() except that UART_FCR macro is removed from serial8250_em_serial_out_helper() as it is now handled by serial8250_ em_serial_out(). DLL/DLM register can be updated only by setting LCR[7]. So the updation of LCR[7] will perform reset for DLL/DLM register changes. EMMA mobile has the same register set as RZ/V2M and this patch is tested on EMEV2 board. So, there is no harm in applying the same restriction here as well as the HW manual for EMMA mobile is not updated for a long time. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230227114152.22265-8-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_em.c | 67 ++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c index 7614ced9377e..25a9ecf26be6 100644 --- a/drivers/tty/serial/8250/8250_em.c +++ b/drivers/tty/serial/8250/8250_em.c @@ -18,6 +18,7 @@ #define UART_DLL_EM 9 #define UART_DLM_EM 10 +#define UART_HCR0_EM 11 /* * A high value for UART_FCR_EM avoids overlapping with existing UART_* @@ -26,11 +27,14 @@ #define UART_FCR_EM 0x10003 #define UART_FCR_EM_HW 3 +#define UART_HCR0_EM_SW_RESET BIT(7) /* SW Reset */ + struct serial8250_em_priv { int line; }; -static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) +static void serial8250_em_serial_out_helper(struct uart_port *p, int offset, + int value) { switch (offset) { case UART_TX: /* TX @ 0x00 */ @@ -41,7 +45,6 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) case UART_SCR: /* SCR @ 0x20 (+1) */ writel(value, p->membase + ((offset + 1) << 2)); break; - case UART_FCR: case UART_FCR_EM: writel(value, p->membase + (UART_FCR_EM_HW << 2)); break; @@ -50,6 +53,7 @@ static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) fallthrough; case UART_DLL_EM: /* DLL @ 0x24 (+9) */ case UART_DLM_EM: /* DLM @ 0x28 (+9) */ + case UART_HCR0_EM: /* HCR0 @ 0x2c */ writel(value, p->membase + (offset << 2)); break; } @@ -60,6 +64,7 @@ static unsigned int serial8250_em_serial_in(struct uart_port *p, int offset) switch (offset) { case UART_RX: /* RX @ 0x00 */ return readb(p->membase); + case UART_LCR: /* LCR @ 0x10 (+1) */ case UART_MCR: /* MCR @ 0x14 (+1) */ case UART_LSR: /* LSR @ 0x18 (+1) */ case UART_MSR: /* MSR @ 0x1c (+1) */ @@ -71,11 +76,69 @@ static unsigned int serial8250_em_serial_in(struct uart_port *p, int offset) case UART_IIR: /* IIR @ 0x08 */ case UART_DLL_EM: /* DLL @ 0x24 (+9) */ case UART_DLM_EM: /* DLM @ 0x28 (+9) */ + case UART_HCR0_EM: /* HCR0 @ 0x2c */ return readl(p->membase + (offset << 2)); } return 0; } +static void serial8250_em_reg_update(struct uart_port *p, int off, int value) +{ + unsigned int ier, fcr, lcr, mcr, hcr0; + + ier = serial8250_em_serial_in(p, UART_IER); + fcr = serial8250_em_serial_in(p, UART_FCR_EM); + lcr = serial8250_em_serial_in(p, UART_LCR); + mcr = serial8250_em_serial_in(p, UART_MCR); + hcr0 = serial8250_em_serial_in(p, UART_HCR0_EM); + + serial8250_em_serial_out_helper(p, UART_FCR_EM, fcr | + UART_FCR_CLEAR_RCVR | + UART_FCR_CLEAR_XMIT); + serial8250_em_serial_out_helper(p, UART_HCR0_EM, hcr0 | + UART_HCR0_EM_SW_RESET); + serial8250_em_serial_out_helper(p, UART_HCR0_EM, hcr0 & + ~UART_HCR0_EM_SW_RESET); + + switch (off) { + case UART_FCR_EM: + fcr = value; + break; + case UART_LCR: + lcr = value; + break; + case UART_MCR: + mcr = value; + break; + } + + serial8250_em_serial_out_helper(p, UART_IER, ier); + serial8250_em_serial_out_helper(p, UART_FCR_EM, fcr); + serial8250_em_serial_out_helper(p, UART_MCR, mcr); + serial8250_em_serial_out_helper(p, UART_LCR, lcr); + serial8250_em_serial_out_helper(p, UART_HCR0_EM, hcr0); +} + +static void serial8250_em_serial_out(struct uart_port *p, int offset, int value) +{ + switch (offset) { + case UART_TX: + case UART_SCR: + case UART_IER: + case UART_DLL_EM: + case UART_DLM_EM: + serial8250_em_serial_out_helper(p, offset, value); + break; + case UART_FCR: + serial8250_em_reg_update(p, UART_FCR_EM, value); + break; + case UART_LCR: + case UART_MCR: + serial8250_em_reg_update(p, offset, value); + break; + } +} + static int serial8250_em_serial_dl_read(struct uart_8250_port *up) { return serial_in(up, UART_DLL_EM) | serial_in(up, UART_DLM_EM) << 8; -- GitLab From 571079f5ba93f08ac2563d40e46d42d56615c096 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Wed, 8 Mar 2023 12:24:33 +0100 Subject: [PATCH 0218/5631] Documentation/serial-console: Document the behavior when the last console= parameter is not used The console= kernel command-line parameter defines where the kernel messages appear. It can be used multiple times to make the kernel log visible on more devices. The ordering of the console= parameters is important. In particular, the last one defines which device can be accessed also via /dev/console. The behavior is more complicated when the last console= parameter is ignored by kernel. It might be surprising because it was not intentional. The kernel just works this way historically. There were few attempts to change the behavior. Unfortunately, it can't be done because it would break existing users. Document the historical behavior at least. Link: https://lore.kernel.org/r/20170606143149.GB7604@pathway.suse.cz Link: https://lore.kernel.org/r/20230213113912.1237943-1-rkanwal@rivosinc.com Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20230308112433.24292-1-pmladek@suse.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/serial-console.rst | 36 ++++++++++++++++++-- 1 file changed, 33 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/serial-console.rst b/Documentation/admin-guide/serial-console.rst index 58b32832e50a..8c8b94e54e26 100644 --- a/Documentation/admin-guide/serial-console.rst +++ b/Documentation/admin-guide/serial-console.rst @@ -33,8 +33,11 @@ The format of this option is:: 9600n8. The maximum baudrate is 115200. You can specify multiple console= options on the kernel command line. -Output will appear on all of them. The last device will be used when -you open ``/dev/console``. So, for example:: + +The behavior is well defined when each device type is mentioned only once. +In this case, the output will appear on all requested consoles. And +the last device will be used when you open ``/dev/console``. +So, for example:: console=ttyS1,9600 console=tty0 @@ -42,7 +45,34 @@ defines that opening ``/dev/console`` will get you the current foreground virtual console, and kernel messages will appear on both the VGA console and the 2nd serial port (ttyS1 or COM2) at 9600 baud. -Note that you can only define one console per device type (serial, video). +The behavior is more complicated when the same device type is defined more +times. In this case, there are the following two rules: + +1. The output will appear only on the first device of each defined type. + +2. ``/dev/console`` will be associated with the first registered device. + Where the registration order depends on how kernel initializes various + subsystems. + + This rule is used also when the last console= parameter is not used + for other reasons. For example, because of a typo or because + the hardware is not available. + +The result might be surprising. For example, the following two command +lines have the same result: + + console=ttyS1,9600 console=tty0 console=tty1 + console=tty0 console=ttyS1,9600 console=tty1 + +The kernel messages are printed only on ``tty0`` and ``ttyS1``. And +``/dev/console`` gets associated with ``tty0``. It is because kernel +tries to register graphical consoles before serial ones. It does it +because of the default behavior when no console device is specified, +see below. + +Note that the last ``console=tty1`` parameter still makes a difference. +The kernel command line is used also by systemd. It would use the last +defined ``tty1`` as the login console. If no console device is specified, the first device found capable of acting as a system console will be used. At this time, the system -- GitLab From 3996954fa071aa20945c8ac7694684fa3c1fed68 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 22 Feb 2023 10:23:01 +0100 Subject: [PATCH 0219/5631] tty: ipwireless: move Kconfig entry to tty The ipwireless' Kconfig entry is currently sitting in char/pcmcia. But the driver is in tty/. So move the entry to tty/ too. First, it makes sense to have the entry along the driver. Second, whole char/pcmcia is about to pass away. Signed-off-by: Jiri Slaby (SUSE) Cc: Jiri Kosina Cc: David Sterba Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Acked-by: David Sterba Link: https://lore.kernel.org/r/20230222092302.6348-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/char/pcmcia/Kconfig | 9 --------- drivers/tty/Kconfig | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/char/pcmcia/Kconfig b/drivers/char/pcmcia/Kconfig index f5d589b2be44..26724990074c 100644 --- a/drivers/char/pcmcia/Kconfig +++ b/drivers/char/pcmcia/Kconfig @@ -55,14 +55,5 @@ config SCR24X If unsure say N. -config IPWIRELESS - tristate "IPWireless 3G UMTS PCMCIA card support" - depends on PCMCIA && NETDEVICES && TTY - select PPP - help - This is a driver for 3G UMTS PCMCIA card from IPWireless company. In - some countries (for example Czech Republic, T-Mobile ISP) this card - is shipped for service called UMTS 4G. - endmenu diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig index d35fc068da74..4de4fb9ce61a 100644 --- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -301,6 +301,15 @@ config GOLDFISH_TTY_EARLY_CONSOLE default y if GOLDFISH_TTY=y select SERIAL_EARLYCON +config IPWIRELESS + tristate "IPWireless 3G UMTS PCMCIA card support" + depends on PCMCIA && NETDEVICES + select PPP + help + This is a driver for 3G UMTS PCMCIA card from IPWireless company. In + some countries (for example Czech Republic, T-Mobile ISP) this card + is shipped for service called UMTS 4G. + config N_GSM tristate "GSM MUX line discipline support (EXPERIMENTAL)" depends on NET -- GitLab From 9b12f050c76f090cc6d0aebe0ef76fed79ec3f15 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 22 Feb 2023 10:23:02 +0100 Subject: [PATCH 0220/5631] char: pcmcia: remove all the drivers These char PCMCIA drivers are buggy[1] and receive only minimal care. It was concluded[2], that we should try to remove most pcmcia drivers completely. Let's start with these char broken one. Note that I also removed a UAPI header: include/uapi/linux/cm4000_cs.h. I found only coccinelle tests mentioning some ioctl constants from that file. But they are not actually used. Anyway, should someone complain, we may reintroduce the header (or its parts). [1] https://lore.kernel.org/all/f41c2765-80e0-48bc-b1e4-8cfd3230fd4a@www.fastmail.com/ [2] https://lore.kernel.org/all/c5b39544-a4fb-4796-a046-0b9be9853787@app.fastmail.com/ Signed-off-by: Jiri Slaby (SUSE) Cc: "Hyunwoo Kim" Cc: Harald Welte Cc: Lubomir Rintel Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Acked-by: Dominik Brodowski Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230222092302.6348-2-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- Documentation/process/magic-number.rst | 1 - .../it_IT/process/magic-number.rst | 1 - .../sp_SP/process/magic-number.rst | 1 - .../zh_CN/process/magic-number.rst | 1 - .../zh_TW/process/magic-number.rst | 1 - .../userspace-api/ioctl/ioctl-number.rst | 1 - MAINTAINERS | 17 - arch/powerpc/configs/ppc6xx_defconfig | 2 - drivers/char/Kconfig | 2 - drivers/char/Makefile | 1 - drivers/char/pcmcia/Kconfig | 59 - drivers/char/pcmcia/Makefile | 11 - drivers/char/pcmcia/cm4000_cs.c | 1912 -------- drivers/char/pcmcia/cm4040_cs.c | 684 --- drivers/char/pcmcia/cm4040_cs.h | 48 - drivers/char/pcmcia/scr24x_cs.c | 359 -- drivers/char/pcmcia/synclink_cs.c | 4290 ----------------- include/linux/cm4000_cs.h | 11 - include/uapi/linux/cm4000_cs.h | 64 - 19 files changed, 7466 deletions(-) delete mode 100644 drivers/char/pcmcia/Kconfig delete mode 100644 drivers/char/pcmcia/Makefile delete mode 100644 drivers/char/pcmcia/cm4000_cs.c delete mode 100644 drivers/char/pcmcia/cm4040_cs.c delete mode 100644 drivers/char/pcmcia/cm4040_cs.h delete mode 100644 drivers/char/pcmcia/scr24x_cs.c delete mode 100644 drivers/char/pcmcia/synclink_cs.c delete mode 100644 include/linux/cm4000_cs.h delete mode 100644 include/uapi/linux/cm4000_cs.h diff --git a/Documentation/process/magic-number.rst b/Documentation/process/magic-number.rst index 64b5948fc1d4..7029c3c084ee 100644 --- a/Documentation/process/magic-number.rst +++ b/Documentation/process/magic-number.rst @@ -72,7 +72,6 @@ PG_MAGIC 'P' pg_{read,write}_hdr ``include/linux/ APM_BIOS_MAGIC 0x4101 apm_user ``arch/x86/kernel/apm_32.c`` FASYNC_MAGIC 0x4601 fasync_struct ``include/linux/fs.h`` SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h`` -MGSLPC_MAGIC 0x5402 mgslpc_info ``drivers/char/pcmcia/synclink_cs.c`` BAYCOM_MAGIC 0x19730510 baycom_state ``drivers/net/baycom_epp.c`` HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state ``include/linux/hdlcdrv.h`` KV_MAGIC 0x5f4b565f kernel_vars_s ``arch/mips/include/asm/sn/klkernvars.h`` diff --git a/Documentation/translations/it_IT/process/magic-number.rst b/Documentation/translations/it_IT/process/magic-number.rst index 02eb7eb2448e..ae92ab633c16 100644 --- a/Documentation/translations/it_IT/process/magic-number.rst +++ b/Documentation/translations/it_IT/process/magic-number.rst @@ -78,7 +78,6 @@ PG_MAGIC 'P' pg_{read,write}_hdr ``include/linux/ APM_BIOS_MAGIC 0x4101 apm_user ``arch/x86/kernel/apm_32.c`` FASYNC_MAGIC 0x4601 fasync_struct ``include/linux/fs.h`` SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h`` -MGSLPC_MAGIC 0x5402 mgslpc_info ``drivers/char/pcmcia/synclink_cs.c`` BAYCOM_MAGIC 0x19730510 baycom_state ``drivers/net/baycom_epp.c`` HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state ``include/linux/hdlcdrv.h`` KV_MAGIC 0x5f4b565f kernel_vars_s ``arch/mips/include/asm/sn/klkernvars.h`` diff --git a/Documentation/translations/sp_SP/process/magic-number.rst b/Documentation/translations/sp_SP/process/magic-number.rst index 2b62cec34e8e..7c7dfb4ba80b 100644 --- a/Documentation/translations/sp_SP/process/magic-number.rst +++ b/Documentation/translations/sp_SP/process/magic-number.rst @@ -77,7 +77,6 @@ PG_MAGIC 'P' pg_{read,write}_hdr ``include/linux/ APM_BIOS_MAGIC 0x4101 apm_user ``arch/x86/kernel/apm_32.c`` FASYNC_MAGIC 0x4601 fasync_struct ``include/linux/fs.h`` SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h`` -MGSLPC_MAGIC 0x5402 mgslpc_info ``drivers/char/pcmcia/synclink_cs.c`` BAYCOM_MAGIC 0x19730510 baycom_state ``drivers/net/baycom_epp.c`` HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state ``include/linux/hdlcdrv.h`` KV_MAGIC 0x5f4b565f kernel_vars_s ``arch/mips/include/asm/sn/klkernvars.h`` diff --git a/Documentation/translations/zh_CN/process/magic-number.rst b/Documentation/translations/zh_CN/process/magic-number.rst index 0617ce125e12..37ed33034134 100644 --- a/Documentation/translations/zh_CN/process/magic-number.rst +++ b/Documentation/translations/zh_CN/process/magic-number.rst @@ -61,7 +61,6 @@ PG_MAGIC 'P' pg_{read,write}_hdr ``include/linux/ APM_BIOS_MAGIC 0x4101 apm_user ``arch/x86/kernel/apm_32.c`` FASYNC_MAGIC 0x4601 fasync_struct ``include/linux/fs.h`` SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h`` -MGSLPC_MAGIC 0x5402 mgslpc_info ``drivers/char/pcmcia/synclink_cs.c`` BAYCOM_MAGIC 0x19730510 baycom_state ``drivers/net/baycom_epp.c`` HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state ``include/linux/hdlcdrv.h`` KV_MAGIC 0x5f4b565f kernel_vars_s ``arch/mips/include/asm/sn/klkernvars.h`` diff --git a/Documentation/translations/zh_TW/process/magic-number.rst b/Documentation/translations/zh_TW/process/magic-number.rst index f3f7082e17c6..1d48e1bbf5f2 100644 --- a/Documentation/translations/zh_TW/process/magic-number.rst +++ b/Documentation/translations/zh_TW/process/magic-number.rst @@ -64,7 +64,6 @@ PG_MAGIC 'P' pg_{read,write}_hdr ``include/linux/ APM_BIOS_MAGIC 0x4101 apm_user ``arch/x86/kernel/apm_32.c`` FASYNC_MAGIC 0x4601 fasync_struct ``include/linux/fs.h`` SLIP_MAGIC 0x5302 slip ``drivers/net/slip.h`` -MGSLPC_MAGIC 0x5402 mgslpc_info ``drivers/char/pcmcia/synclink_cs.c`` BAYCOM_MAGIC 0x19730510 baycom_state ``drivers/net/baycom_epp.c`` HDLCDRV_MAGIC 0x5ac6e778 hdlcdrv_state ``include/linux/hdlcdrv.h`` KV_MAGIC 0x5f4b565f kernel_vars_s ``arch/mips/include/asm/sn/klkernvars.h`` diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 0a1882e296ae..176e8fc3f31b 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -222,7 +222,6 @@ Code Seq# Include File Comments 'b' 00-FF conflict! bit3 vme host bridge 'b' 00-0F linux/dma-buf.h conflict! -'c' all linux/cm4000_cs.h conflict! 'c' 00-7F linux/comstats.h conflict! 'c' 00-7F linux/coda.h conflict! 'c' 00-1F linux/chio.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..64068a601e59 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15322,18 +15322,6 @@ S: Maintained F: Documentation/filesystems/omfs.rst F: fs/omfs/ -OMNIKEY CARDMAN 4000 DRIVER -M: Harald Welte -S: Maintained -F: drivers/char/pcmcia/cm4000_cs.c -F: include/linux/cm4000_cs.h -F: include/uapi/linux/cm4000_cs.h - -OMNIKEY CARDMAN 4040 DRIVER -M: Harald Welte -S: Maintained -F: drivers/char/pcmcia/cm4040_cs.* - OMNIVISION OG01A1B SENSOR DRIVER M: Shawn Tu L: linux-media@vger.kernel.org @@ -18609,11 +18597,6 @@ F: include/linux/wait.h F: include/uapi/linux/sched.h F: kernel/sched/ -SCR24X CHIP CARD INTERFACE DRIVER -M: Lubomir Rintel -S: Supported -F: drivers/char/pcmcia/scr24x_cs.c - SCSI RDMA PROTOCOL (SRP) INITIATOR M: Bart Van Assche L: linux-rdma@vger.kernel.org diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 110258277959..d8729b94400e 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -614,8 +614,6 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=m CONFIG_NVRAM=y CONFIG_DTLK=m -CONFIG_CARDMAN_4000=m -CONFIG_CARDMAN_4040=m CONFIG_IPWIRELESS=m CONFIG_I2C_CHARDEV=m CONFIG_I2C_HYDRA=m diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 30fe9848dac1..801d6c83f896 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -247,8 +247,6 @@ config SONYPI To compile this driver as a module, choose M here: the module will be called sonypi. -source "drivers/char/pcmcia/Kconfig" - config MWAVE tristate "ACP Modem (Mwave) support" depends on X86 && TTY diff --git a/drivers/char/Makefile b/drivers/char/Makefile index 1b35d1724565..c5f532e412f1 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -35,7 +35,6 @@ obj-$(CONFIG_TELCLOCK) += tlclk.o obj-$(CONFIG_MWAVE) += mwave/ obj-y += agp/ -obj-$(CONFIG_PCMCIA) += pcmcia/ obj-$(CONFIG_HANGCHECK_TIMER) += hangcheck-timer.o obj-$(CONFIG_TCG_TPM) += tpm/ diff --git a/drivers/char/pcmcia/Kconfig b/drivers/char/pcmcia/Kconfig deleted file mode 100644 index 26724990074c..000000000000 --- a/drivers/char/pcmcia/Kconfig +++ /dev/null @@ -1,59 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# PCMCIA character device configuration -# - -menu "PCMCIA character devices" - depends on PCMCIA!=n - -config SYNCLINK_CS - tristate "SyncLink PC Card support" - depends on PCMCIA && TTY - help - Enable support for the SyncLink PC Card serial adapter, running - asynchronous and HDLC communications up to 512Kbps. The port is - selectable for RS-232, V.35, RS-449, RS-530, and X.21 - - This driver may be built as a module ( = code which can be - inserted in and removed from the running kernel whenever you want). - The module will be called synclink_cs. If you want to do that, say M - here. - -config CARDMAN_4000 - tristate "Omnikey Cardman 4000 support" - depends on PCMCIA - select BITREVERSE - help - Enable support for the Omnikey Cardman 4000 PCMCIA Smartcard - reader. - - This kernel driver requires additional userspace support, either - by the vendor-provided PC/SC ifd_handler (http://www.omnikey.com/), - or via the cm4000 backend of OpenCT (http://www.opensc-project.org/opensc). - -config CARDMAN_4040 - tristate "Omnikey CardMan 4040 support" - depends on PCMCIA - help - Enable support for the Omnikey CardMan 4040 PCMCIA Smartcard - reader. - - This card is basically a USB CCID device connected to a FIFO - in I/O space. To use the kernel driver, you will need either the - PC/SC ifdhandler provided from the Omnikey homepage - (http://www.omnikey.com/), or a current development version of OpenCT - (http://www.opensc-project.org/opensc). - -config SCR24X - tristate "SCR24x Chip Card Interface support" - depends on PCMCIA - help - Enable support for the SCR24x PCMCIA Chip Card Interface. - - To compile this driver as a module, choose M here. - The module will be called scr24x_cs.. - - If unsure say N. - -endmenu - diff --git a/drivers/char/pcmcia/Makefile b/drivers/char/pcmcia/Makefile deleted file mode 100644 index 024eed1c4ca5..000000000000 --- a/drivers/char/pcmcia/Makefile +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# drivers/char/pcmcia/Makefile -# -# Makefile for the Linux PCMCIA char device drivers. -# - -obj-$(CONFIG_SYNCLINK_CS) += synclink_cs.o -obj-$(CONFIG_CARDMAN_4000) += cm4000_cs.o -obj-$(CONFIG_CARDMAN_4040) += cm4040_cs.o -obj-$(CONFIG_SCR24X) += scr24x_cs.o diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c deleted file mode 100644 index e656f42a28ac..000000000000 --- a/drivers/char/pcmcia/cm4000_cs.c +++ /dev/null @@ -1,1912 +0,0 @@ - /* - * A driver for the PCMCIA Smartcard Reader "Omnikey CardMan Mobile 4000" - * - * cm4000_cs.c support.linux@omnikey.com - * - * Tue Oct 23 11:32:43 GMT 2001 herp - cleaned up header files - * Sun Jan 20 10:11:15 MET 2002 herp - added modversion header files - * Thu Nov 14 16:34:11 GMT 2002 mh - added PPS functionality - * Tue Nov 19 16:36:27 GMT 2002 mh - added SUSPEND/RESUME functionailty - * Wed Jul 28 12:55:01 CEST 2004 mh - kernel 2.6 adjustments - * - * current version: 2.4.0gm4 - * - * (C) 2000,2001,2002,2003,2004 Omnikey AG - * - * (C) 2005-2006 Harald Welte - * - Adhere to Kernel process/coding-style.rst - * - Port to 2.6.13 "new" style PCMCIA - * - Check for copy_{from,to}_user return values - * - Use nonseekable_open() - * - add class interface for udev device creation - * - * All rights reserved. Licensed under dual BSD/GPL license. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include - -/* #define ATR_CSUM */ - -#define reader_to_dev(x) (&x->p_dev->dev) - -/* n (debug level) is ignored */ -/* additional debug output may be enabled by re-compiling with - * CM4000_DEBUG set */ -/* #define CM4000_DEBUG */ -#define DEBUGP(n, rdr, x, args...) do { \ - dev_dbg(reader_to_dev(rdr), "%s:" x, \ - __func__ , ## args); \ - } while (0) - -static DEFINE_MUTEX(cmm_mutex); - -#define T_1SEC (HZ) -#define T_10MSEC msecs_to_jiffies(10) -#define T_20MSEC msecs_to_jiffies(20) -#define T_40MSEC msecs_to_jiffies(40) -#define T_50MSEC msecs_to_jiffies(50) -#define T_100MSEC msecs_to_jiffies(100) -#define T_500MSEC msecs_to_jiffies(500) - -static void cm4000_release(struct pcmcia_device *link); - -static int major; /* major number we get from the kernel */ - -/* note: the first state has to have number 0 always */ - -#define M_FETCH_ATR 0 -#define M_TIMEOUT_WAIT 1 -#define M_READ_ATR_LEN 2 -#define M_READ_ATR 3 -#define M_ATR_PRESENT 4 -#define M_BAD_CARD 5 -#define M_CARDOFF 6 - -#define LOCK_IO 0 -#define LOCK_MONITOR 1 - -#define IS_AUTOPPS_ACT 6 -#define IS_PROCBYTE_PRESENT 7 -#define IS_INVREV 8 -#define IS_ANY_T0 9 -#define IS_ANY_T1 10 -#define IS_ATR_PRESENT 11 -#define IS_ATR_VALID 12 -#define IS_CMM_ABSENT 13 -#define IS_BAD_LENGTH 14 -#define IS_BAD_CSUM 15 -#define IS_BAD_CARD 16 - -#define REG_FLAGS0(x) (x + 0) -#define REG_FLAGS1(x) (x + 1) -#define REG_NUM_BYTES(x) (x + 2) -#define REG_BUF_ADDR(x) (x + 3) -#define REG_BUF_DATA(x) (x + 4) -#define REG_NUM_SEND(x) (x + 5) -#define REG_BAUDRATE(x) (x + 6) -#define REG_STOPBITS(x) (x + 7) - -struct cm4000_dev { - struct pcmcia_device *p_dev; - - unsigned char atr[MAX_ATR]; - unsigned char rbuf[512]; - unsigned char sbuf[512]; - - wait_queue_head_t devq; /* when removing cardman must not be - zeroed! */ - - wait_queue_head_t ioq; /* if IO is locked, wait on this Q */ - wait_queue_head_t atrq; /* wait for ATR valid */ - wait_queue_head_t readq; /* used by write to wake blk.read */ - - /* warning: do not move this struct group. - * initialising to zero depends on it - see ZERO_DEV below. */ - struct_group(init, - unsigned char atr_csum; - unsigned char atr_len_retry; - unsigned short atr_len; - unsigned short rlen; /* bytes avail. after write */ - unsigned short rpos; /* latest read pos. write zeroes */ - unsigned char procbyte; /* T=0 procedure byte */ - unsigned char mstate; /* state of card monitor */ - unsigned char cwarn; /* slow down warning */ - unsigned char flags0; /* cardman IO-flags 0 */ - unsigned char flags1; /* cardman IO-flags 1 */ - unsigned int mdelay; /* variable monitor speeds, in jiffies */ - - unsigned int baudv; /* baud value for speed */ - unsigned char ta1; - unsigned char proto; /* T=0, T=1, ... */ - unsigned long flags; /* lock+flags (MONITOR,IO,ATR) * for concurrent - access */ - - unsigned char pts[4]; - - struct timer_list timer; /* used to keep monitor running */ - int monitor_running; - ); -}; - -#define ZERO_DEV(dev) memset(&((dev)->init), 0, sizeof((dev)->init)) - -static struct pcmcia_device *dev_table[CM4000_MAX_DEV]; -static struct class *cmm_class; - -/* This table doesn't use spaces after the comma between fields and thus - * violates process/coding-style.rst. However, I don't really think wrapping it around will - * make it any clearer to read -HW */ -static unsigned char fi_di_table[10][14] = { -/*FI 00 01 02 03 04 05 06 07 08 09 10 11 12 13 */ -/*DI */ -/* 0 */ {0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11}, -/* 1 */ {0x01,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x91,0x11,0x11,0x11,0x11}, -/* 2 */ {0x02,0x12,0x22,0x32,0x11,0x11,0x11,0x11,0x11,0x92,0xA2,0xB2,0x11,0x11}, -/* 3 */ {0x03,0x13,0x23,0x33,0x43,0x53,0x63,0x11,0x11,0x93,0xA3,0xB3,0xC3,0xD3}, -/* 4 */ {0x04,0x14,0x24,0x34,0x44,0x54,0x64,0x11,0x11,0x94,0xA4,0xB4,0xC4,0xD4}, -/* 5 */ {0x00,0x15,0x25,0x35,0x45,0x55,0x65,0x11,0x11,0x95,0xA5,0xB5,0xC5,0xD5}, -/* 6 */ {0x06,0x16,0x26,0x36,0x46,0x56,0x66,0x11,0x11,0x96,0xA6,0xB6,0xC6,0xD6}, -/* 7 */ {0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11,0x11}, -/* 8 */ {0x08,0x11,0x28,0x38,0x48,0x58,0x68,0x11,0x11,0x98,0xA8,0xB8,0xC8,0xD8}, -/* 9 */ {0x09,0x19,0x29,0x39,0x49,0x59,0x69,0x11,0x11,0x99,0xA9,0xB9,0xC9,0xD9} -}; - -#ifndef CM4000_DEBUG -#define xoutb outb -#define xinb inb -#else -static inline void xoutb(unsigned char val, unsigned short port) -{ - pr_debug("outb(val=%.2x,port=%.4x)\n", val, port); - outb(val, port); -} -static inline unsigned char xinb(unsigned short port) -{ - unsigned char val; - - val = inb(port); - pr_debug("%.2x=inb(%.4x)\n", val, port); - - return val; -} -#endif - -static inline unsigned char invert_revert(unsigned char ch) -{ - return bitrev8(~ch); -} - -static void str_invert_revert(unsigned char *b, int len) -{ - int i; - - for (i = 0; i < len; i++) - b[i] = invert_revert(b[i]); -} - -#define ATRLENCK(dev,pos) \ - if (pos>=dev->atr_len || pos>=MAX_ATR) \ - goto return_0; - -static unsigned int calc_baudv(unsigned char fidi) -{ - unsigned int wcrcf, wbrcf, fi_rfu, di_rfu; - - fi_rfu = 372; - di_rfu = 1; - - /* FI */ - switch ((fidi >> 4) & 0x0F) { - case 0x00: - wcrcf = 372; - break; - case 0x01: - wcrcf = 372; - break; - case 0x02: - wcrcf = 558; - break; - case 0x03: - wcrcf = 744; - break; - case 0x04: - wcrcf = 1116; - break; - case 0x05: - wcrcf = 1488; - break; - case 0x06: - wcrcf = 1860; - break; - case 0x07: - wcrcf = fi_rfu; - break; - case 0x08: - wcrcf = fi_rfu; - break; - case 0x09: - wcrcf = 512; - break; - case 0x0A: - wcrcf = 768; - break; - case 0x0B: - wcrcf = 1024; - break; - case 0x0C: - wcrcf = 1536; - break; - case 0x0D: - wcrcf = 2048; - break; - default: - wcrcf = fi_rfu; - break; - } - - /* DI */ - switch (fidi & 0x0F) { - case 0x00: - wbrcf = di_rfu; - break; - case 0x01: - wbrcf = 1; - break; - case 0x02: - wbrcf = 2; - break; - case 0x03: - wbrcf = 4; - break; - case 0x04: - wbrcf = 8; - break; - case 0x05: - wbrcf = 16; - break; - case 0x06: - wbrcf = 32; - break; - case 0x07: - wbrcf = di_rfu; - break; - case 0x08: - wbrcf = 12; - break; - case 0x09: - wbrcf = 20; - break; - default: - wbrcf = di_rfu; - break; - } - - return (wcrcf / wbrcf); -} - -static unsigned short io_read_num_rec_bytes(unsigned int iobase, - unsigned short *s) -{ - unsigned short tmp; - - tmp = *s = 0; - do { - *s = tmp; - tmp = inb(REG_NUM_BYTES(iobase)) | - (inb(REG_FLAGS0(iobase)) & 4 ? 0x100 : 0); - } while (tmp != *s); - - return *s; -} - -static int parse_atr(struct cm4000_dev *dev) -{ - unsigned char any_t1, any_t0; - unsigned char ch, ifno; - int ix, done; - - DEBUGP(3, dev, "-> parse_atr: dev->atr_len = %i\n", dev->atr_len); - - if (dev->atr_len < 3) { - DEBUGP(5, dev, "parse_atr: atr_len < 3\n"); - return 0; - } - - if (dev->atr[0] == 0x3f) - set_bit(IS_INVREV, &dev->flags); - else - clear_bit(IS_INVREV, &dev->flags); - ix = 1; - ifno = 1; - ch = dev->atr[1]; - dev->proto = 0; /* XXX PROTO */ - any_t1 = any_t0 = done = 0; - dev->ta1 = 0x11; /* defaults to 9600 baud */ - do { - if (ifno == 1 && (ch & 0x10)) { - /* read first interface byte and TA1 is present */ - dev->ta1 = dev->atr[2]; - DEBUGP(5, dev, "Card says FiDi is 0x%.2x\n", dev->ta1); - ifno++; - } else if ((ifno == 2) && (ch & 0x10)) { /* TA(2) */ - dev->ta1 = 0x11; - ifno++; - } - - DEBUGP(5, dev, "Yi=%.2x\n", ch & 0xf0); - ix += ((ch & 0x10) >> 4) /* no of int.face chars */ - +((ch & 0x20) >> 5) - + ((ch & 0x40) >> 6) - + ((ch & 0x80) >> 7); - /* ATRLENCK(dev,ix); */ - if (ch & 0x80) { /* TDi */ - ch = dev->atr[ix]; - if ((ch & 0x0f)) { - any_t1 = 1; - DEBUGP(5, dev, "card is capable of T=1\n"); - } else { - any_t0 = 1; - DEBUGP(5, dev, "card is capable of T=0\n"); - } - } else - done = 1; - } while (!done); - - DEBUGP(5, dev, "ix=%d noHist=%d any_t1=%d\n", - ix, dev->atr[1] & 15, any_t1); - if (ix + 1 + (dev->atr[1] & 0x0f) + any_t1 != dev->atr_len) { - DEBUGP(5, dev, "length error\n"); - return 0; - } - if (any_t0) - set_bit(IS_ANY_T0, &dev->flags); - - if (any_t1) { /* compute csum */ - dev->atr_csum = 0; -#ifdef ATR_CSUM - for (i = 1; i < dev->atr_len; i++) - dev->atr_csum ^= dev->atr[i]; - if (dev->atr_csum) { - set_bit(IS_BAD_CSUM, &dev->flags); - DEBUGP(5, dev, "bad checksum\n"); - goto return_0; - } -#endif - if (any_t0 == 0) - dev->proto = 1; /* XXX PROTO */ - set_bit(IS_ANY_T1, &dev->flags); - } - - return 1; -} - -struct card_fixup { - char atr[12]; - u_int8_t atr_len; - u_int8_t stopbits; -}; - -static struct card_fixup card_fixups[] = { - { /* ACOS */ - .atr = { 0x3b, 0xb3, 0x11, 0x00, 0x00, 0x41, 0x01 }, - .atr_len = 7, - .stopbits = 0x03, - }, - { /* Motorola */ - .atr = {0x3b, 0x76, 0x13, 0x00, 0x00, 0x80, 0x62, 0x07, - 0x41, 0x81, 0x81 }, - .atr_len = 11, - .stopbits = 0x04, - }, -}; - -static void set_cardparameter(struct cm4000_dev *dev) -{ - int i; - unsigned int iobase = dev->p_dev->resource[0]->start; - u_int8_t stopbits = 0x02; /* ISO default */ - - DEBUGP(3, dev, "-> set_cardparameter\n"); - - dev->flags1 = dev->flags1 | (((dev->baudv - 1) & 0x0100) >> 8); - xoutb(dev->flags1, REG_FLAGS1(iobase)); - DEBUGP(5, dev, "flags1 = 0x%02x\n", dev->flags1); - - /* set baudrate */ - xoutb((unsigned char)((dev->baudv - 1) & 0xFF), REG_BAUDRATE(iobase)); - - DEBUGP(5, dev, "baudv = %i -> write 0x%02x\n", dev->baudv, - ((dev->baudv - 1) & 0xFF)); - - /* set stopbits */ - for (i = 0; i < ARRAY_SIZE(card_fixups); i++) { - if (!memcmp(dev->atr, card_fixups[i].atr, - card_fixups[i].atr_len)) - stopbits = card_fixups[i].stopbits; - } - xoutb(stopbits, REG_STOPBITS(iobase)); - - DEBUGP(3, dev, "<- set_cardparameter\n"); -} - -static int set_protocol(struct cm4000_dev *dev, struct ptsreq *ptsreq) -{ - - unsigned long tmp, i; - unsigned short num_bytes_read; - unsigned char pts_reply[4]; - ssize_t rc; - unsigned int iobase = dev->p_dev->resource[0]->start; - - rc = 0; - - DEBUGP(3, dev, "-> set_protocol\n"); - DEBUGP(5, dev, "ptsreq->Protocol = 0x%.8x, ptsreq->Flags=0x%.8x, " - "ptsreq->pts1=0x%.2x, ptsreq->pts2=0x%.2x, " - "ptsreq->pts3=0x%.2x\n", (unsigned int)ptsreq->protocol, - (unsigned int)ptsreq->flags, ptsreq->pts1, ptsreq->pts2, - ptsreq->pts3); - - /* Fill PTS structure */ - dev->pts[0] = 0xff; - dev->pts[1] = 0x00; - tmp = ptsreq->protocol; - while ((tmp = (tmp >> 1)) > 0) - dev->pts[1]++; - dev->proto = dev->pts[1]; /* Set new protocol */ - dev->pts[1] = (0x01 << 4) | (dev->pts[1]); - - /* Correct Fi/Di according to CM4000 Fi/Di table */ - DEBUGP(5, dev, "Ta(1) from ATR is 0x%.2x\n", dev->ta1); - /* set Fi/Di according to ATR TA(1) */ - dev->pts[2] = fi_di_table[dev->ta1 & 0x0F][(dev->ta1 >> 4) & 0x0F]; - - /* Calculate PCK character */ - dev->pts[3] = dev->pts[0] ^ dev->pts[1] ^ dev->pts[2]; - - DEBUGP(5, dev, "pts0=%.2x, pts1=%.2x, pts2=%.2x, pts3=%.2x\n", - dev->pts[0], dev->pts[1], dev->pts[2], dev->pts[3]); - - /* check card convention */ - if (test_bit(IS_INVREV, &dev->flags)) - str_invert_revert(dev->pts, 4); - - /* reset SM */ - xoutb(0x80, REG_FLAGS0(iobase)); - - /* Enable access to the message buffer */ - DEBUGP(5, dev, "Enable access to the messages buffer\n"); - dev->flags1 = 0x20 /* T_Active */ - | (test_bit(IS_INVREV, &dev->flags) ? 0x02 : 0x00) /* inv parity */ - | ((dev->baudv >> 8) & 0x01); /* MSB-baud */ - xoutb(dev->flags1, REG_FLAGS1(iobase)); - - DEBUGP(5, dev, "Enable message buffer -> flags1 = 0x%.2x\n", - dev->flags1); - - /* write challenge to the buffer */ - DEBUGP(5, dev, "Write challenge to buffer: "); - for (i = 0; i < 4; i++) { - xoutb(i, REG_BUF_ADDR(iobase)); - xoutb(dev->pts[i], REG_BUF_DATA(iobase)); /* buf data */ -#ifdef CM4000_DEBUG - pr_debug("0x%.2x ", dev->pts[i]); - } - pr_debug("\n"); -#else - } -#endif - - /* set number of bytes to write */ - DEBUGP(5, dev, "Set number of bytes to write\n"); - xoutb(0x04, REG_NUM_SEND(iobase)); - - /* Trigger CARDMAN CONTROLLER */ - xoutb(0x50, REG_FLAGS0(iobase)); - - /* Monitor progress */ - /* wait for xmit done */ - DEBUGP(5, dev, "Waiting for NumRecBytes getting valid\n"); - - for (i = 0; i < 100; i++) { - if (inb(REG_FLAGS0(iobase)) & 0x08) { - DEBUGP(5, dev, "NumRecBytes is valid\n"); - break; - } - /* can not sleep as this is in atomic context */ - mdelay(10); - } - if (i == 100) { - DEBUGP(5, dev, "Timeout waiting for NumRecBytes getting " - "valid\n"); - rc = -EIO; - goto exit_setprotocol; - } - - DEBUGP(5, dev, "Reading NumRecBytes\n"); - for (i = 0; i < 100; i++) { - io_read_num_rec_bytes(iobase, &num_bytes_read); - if (num_bytes_read >= 4) { - DEBUGP(2, dev, "NumRecBytes = %i\n", num_bytes_read); - if (num_bytes_read > 4) { - rc = -EIO; - goto exit_setprotocol; - } - break; - } - /* can not sleep as this is in atomic context */ - mdelay(10); - } - - /* check whether it is a short PTS reply? */ - if (num_bytes_read == 3) - i = 0; - - if (i == 100) { - DEBUGP(5, dev, "Timeout reading num_bytes_read\n"); - rc = -EIO; - goto exit_setprotocol; - } - - DEBUGP(5, dev, "Reset the CARDMAN CONTROLLER\n"); - xoutb(0x80, REG_FLAGS0(iobase)); - - /* Read PPS reply */ - DEBUGP(5, dev, "Read PPS reply\n"); - for (i = 0; i < num_bytes_read; i++) { - xoutb(i, REG_BUF_ADDR(iobase)); - pts_reply[i] = inb(REG_BUF_DATA(iobase)); - } - -#ifdef CM4000_DEBUG - DEBUGP(2, dev, "PTSreply: "); - for (i = 0; i < num_bytes_read; i++) { - pr_debug("0x%.2x ", pts_reply[i]); - } - pr_debug("\n"); -#endif /* CM4000_DEBUG */ - - DEBUGP(5, dev, "Clear Tactive in Flags1\n"); - xoutb(0x20, REG_FLAGS1(iobase)); - - /* Compare ptsreq and ptsreply */ - if ((dev->pts[0] == pts_reply[0]) && - (dev->pts[1] == pts_reply[1]) && - (dev->pts[2] == pts_reply[2]) && (dev->pts[3] == pts_reply[3])) { - /* setcardparameter according to PPS */ - dev->baudv = calc_baudv(dev->pts[2]); - set_cardparameter(dev); - } else if ((dev->pts[0] == pts_reply[0]) && - ((dev->pts[1] & 0xef) == pts_reply[1]) && - ((pts_reply[0] ^ pts_reply[1]) == pts_reply[2])) { - /* short PTS reply, set card parameter to default values */ - dev->baudv = calc_baudv(0x11); - set_cardparameter(dev); - } else - rc = -EIO; - -exit_setprotocol: - DEBUGP(3, dev, "<- set_protocol\n"); - return rc; -} - -static int io_detect_cm4000(unsigned int iobase, struct cm4000_dev *dev) -{ - - /* note: statemachine is assumed to be reset */ - if (inb(REG_FLAGS0(iobase)) & 8) { - clear_bit(IS_ATR_VALID, &dev->flags); - set_bit(IS_CMM_ABSENT, &dev->flags); - return 0; /* detect CMM = 1 -> failure */ - } - /* xoutb(0x40, REG_FLAGS1(iobase)); detectCMM */ - xoutb(dev->flags1 | 0x40, REG_FLAGS1(iobase)); - if ((inb(REG_FLAGS0(iobase)) & 8) == 0) { - clear_bit(IS_ATR_VALID, &dev->flags); - set_bit(IS_CMM_ABSENT, &dev->flags); - return 0; /* detect CMM=0 -> failure */ - } - /* clear detectCMM again by restoring original flags1 */ - xoutb(dev->flags1, REG_FLAGS1(iobase)); - return 1; -} - -static void terminate_monitor(struct cm4000_dev *dev) -{ - - /* tell the monitor to stop and wait until - * it terminates. - */ - DEBUGP(3, dev, "-> terminate_monitor\n"); - wait_event_interruptible(dev->devq, - test_and_set_bit(LOCK_MONITOR, - (void *)&dev->flags)); - - /* now, LOCK_MONITOR has been set. - * allow a last cycle in the monitor. - * the monitor will indicate that it has - * finished by clearing this bit. - */ - DEBUGP(5, dev, "Now allow last cycle of monitor!\n"); - while (test_bit(LOCK_MONITOR, (void *)&dev->flags)) - msleep(25); - - DEBUGP(5, dev, "Delete timer\n"); - del_timer_sync(&dev->timer); -#ifdef CM4000_DEBUG - dev->monitor_running = 0; -#endif - - DEBUGP(3, dev, "<- terminate_monitor\n"); -} - -/* - * monitor the card every 50msec. as a side-effect, retrieve the - * atr once a card is inserted. another side-effect of retrieving the - * atr is that the card will be powered on, so there is no need to - * power on the card explicitly from the application: the driver - * is already doing that for you. - */ - -static void monitor_card(struct timer_list *t) -{ - struct cm4000_dev *dev = from_timer(dev, t, timer); - unsigned int iobase = dev->p_dev->resource[0]->start; - unsigned short s; - struct ptsreq ptsreq; - int i, atrc; - - DEBUGP(7, dev, "-> monitor_card\n"); - - /* if someone has set the lock for us: we're done! */ - if (test_and_set_bit(LOCK_MONITOR, &dev->flags)) { - DEBUGP(4, dev, "About to stop monitor\n"); - /* no */ - dev->rlen = - dev->rpos = - dev->atr_csum = dev->atr_len_retry = dev->cwarn = 0; - dev->mstate = M_FETCH_ATR; - clear_bit(LOCK_MONITOR, &dev->flags); - /* close et al. are sleeping on devq, so wake it */ - wake_up_interruptible(&dev->devq); - DEBUGP(2, dev, "<- monitor_card (we are done now)\n"); - return; - } - - /* try to lock io: if it is already locked, just add another timer */ - if (test_and_set_bit(LOCK_IO, (void *)&dev->flags)) { - DEBUGP(4, dev, "Couldn't get IO lock\n"); - goto return_with_timer; - } - - /* is a card/a reader inserted at all ? */ - dev->flags0 = xinb(REG_FLAGS0(iobase)); - DEBUGP(7, dev, "dev->flags0 = 0x%2x\n", dev->flags0); - DEBUGP(7, dev, "smartcard present: %s\n", - dev->flags0 & 1 ? "yes" : "no"); - DEBUGP(7, dev, "cardman present: %s\n", - dev->flags0 == 0xff ? "no" : "yes"); - - if ((dev->flags0 & 1) == 0 /* no smartcard inserted */ - || dev->flags0 == 0xff) { /* no cardman inserted */ - /* no */ - dev->rlen = - dev->rpos = - dev->atr_csum = dev->atr_len_retry = dev->cwarn = 0; - dev->mstate = M_FETCH_ATR; - - dev->flags &= 0x000000ff; /* only keep IO and MONITOR locks */ - - if (dev->flags0 == 0xff) { - DEBUGP(4, dev, "set IS_CMM_ABSENT bit\n"); - set_bit(IS_CMM_ABSENT, &dev->flags); - } else if (test_bit(IS_CMM_ABSENT, &dev->flags)) { - DEBUGP(4, dev, "clear IS_CMM_ABSENT bit " - "(card is removed)\n"); - clear_bit(IS_CMM_ABSENT, &dev->flags); - } - - goto release_io; - } else if ((dev->flags0 & 1) && test_bit(IS_CMM_ABSENT, &dev->flags)) { - /* cardman and card present but cardman was absent before - * (after suspend with inserted card) */ - DEBUGP(4, dev, "clear IS_CMM_ABSENT bit (card is inserted)\n"); - clear_bit(IS_CMM_ABSENT, &dev->flags); - } - - if (test_bit(IS_ATR_VALID, &dev->flags) == 1) { - DEBUGP(7, dev, "believe ATR is already valid (do nothing)\n"); - goto release_io; - } - - switch (dev->mstate) { - case M_CARDOFF: { - unsigned char flags0; - - DEBUGP(4, dev, "M_CARDOFF\n"); - flags0 = inb(REG_FLAGS0(iobase)); - if (flags0 & 0x02) { - /* wait until Flags0 indicate power is off */ - dev->mdelay = T_10MSEC; - } else { - /* Flags0 indicate power off and no card inserted now; - * Reset CARDMAN CONTROLLER */ - xoutb(0x80, REG_FLAGS0(iobase)); - - /* prepare for fetching ATR again: after card off ATR - * is read again automatically */ - dev->rlen = - dev->rpos = - dev->atr_csum = - dev->atr_len_retry = dev->cwarn = 0; - dev->mstate = M_FETCH_ATR; - - /* minimal gap between CARDOFF and read ATR is 50msec */ - dev->mdelay = T_50MSEC; - } - break; - } - case M_FETCH_ATR: - DEBUGP(4, dev, "M_FETCH_ATR\n"); - xoutb(0x80, REG_FLAGS0(iobase)); - DEBUGP(4, dev, "Reset BAUDV to 9600\n"); - dev->baudv = 0x173; /* 9600 */ - xoutb(0x02, REG_STOPBITS(iobase)); /* stopbits=2 */ - xoutb(0x73, REG_BAUDRATE(iobase)); /* baud value */ - xoutb(0x21, REG_FLAGS1(iobase)); /* T_Active=1, baud - value */ - /* warm start vs. power on: */ - xoutb(dev->flags0 & 2 ? 0x46 : 0x44, REG_FLAGS0(iobase)); - dev->mdelay = T_40MSEC; - dev->mstate = M_TIMEOUT_WAIT; - break; - case M_TIMEOUT_WAIT: - DEBUGP(4, dev, "M_TIMEOUT_WAIT\n"); - /* numRecBytes */ - io_read_num_rec_bytes(iobase, &dev->atr_len); - dev->mdelay = T_10MSEC; - dev->mstate = M_READ_ATR_LEN; - break; - case M_READ_ATR_LEN: - DEBUGP(4, dev, "M_READ_ATR_LEN\n"); - /* infinite loop possible, since there is no timeout */ - -#define MAX_ATR_LEN_RETRY 100 - - if (dev->atr_len == io_read_num_rec_bytes(iobase, &s)) { - if (dev->atr_len_retry++ >= MAX_ATR_LEN_RETRY) { /* + XX msec */ - dev->mdelay = T_10MSEC; - dev->mstate = M_READ_ATR; - } - } else { - dev->atr_len = s; - dev->atr_len_retry = 0; /* set new timeout */ - } - - DEBUGP(4, dev, "Current ATR_LEN = %i\n", dev->atr_len); - break; - case M_READ_ATR: - DEBUGP(4, dev, "M_READ_ATR\n"); - xoutb(0x80, REG_FLAGS0(iobase)); /* reset SM */ - for (i = 0; i < dev->atr_len; i++) { - xoutb(i, REG_BUF_ADDR(iobase)); - dev->atr[i] = inb(REG_BUF_DATA(iobase)); - } - /* Deactivate T_Active flags */ - DEBUGP(4, dev, "Deactivate T_Active flags\n"); - dev->flags1 = 0x01; - xoutb(dev->flags1, REG_FLAGS1(iobase)); - - /* atr is present (which doesn't mean it's valid) */ - set_bit(IS_ATR_PRESENT, &dev->flags); - if (dev->atr[0] == 0x03) - str_invert_revert(dev->atr, dev->atr_len); - atrc = parse_atr(dev); - if (atrc == 0) { /* atr invalid */ - dev->mdelay = 0; - dev->mstate = M_BAD_CARD; - } else { - dev->mdelay = T_50MSEC; - dev->mstate = M_ATR_PRESENT; - set_bit(IS_ATR_VALID, &dev->flags); - } - - if (test_bit(IS_ATR_VALID, &dev->flags) == 1) { - DEBUGP(4, dev, "monitor_card: ATR valid\n"); - /* if ta1 == 0x11, no PPS necessary (default values) */ - /* do not do PPS with multi protocol cards */ - if ((test_bit(IS_AUTOPPS_ACT, &dev->flags) == 0) && - (dev->ta1 != 0x11) && - !(test_bit(IS_ANY_T0, &dev->flags) && - test_bit(IS_ANY_T1, &dev->flags))) { - DEBUGP(4, dev, "Perform AUTOPPS\n"); - set_bit(IS_AUTOPPS_ACT, &dev->flags); - ptsreq.protocol = (0x01 << dev->proto); - ptsreq.flags = 0x01; - ptsreq.pts1 = 0x00; - ptsreq.pts2 = 0x00; - ptsreq.pts3 = 0x00; - if (set_protocol(dev, &ptsreq) == 0) { - DEBUGP(4, dev, "AUTOPPS ret SUCC\n"); - clear_bit(IS_AUTOPPS_ACT, &dev->flags); - wake_up_interruptible(&dev->atrq); - } else { - DEBUGP(4, dev, "AUTOPPS failed: " - "repower using defaults\n"); - /* prepare for repowering */ - clear_bit(IS_ATR_PRESENT, &dev->flags); - clear_bit(IS_ATR_VALID, &dev->flags); - dev->rlen = - dev->rpos = - dev->atr_csum = - dev->atr_len_retry = dev->cwarn = 0; - dev->mstate = M_FETCH_ATR; - - dev->mdelay = T_50MSEC; - } - } else { - /* for cards which use slightly different - * params (extra guard time) */ - set_cardparameter(dev); - if (test_bit(IS_AUTOPPS_ACT, &dev->flags) == 1) - DEBUGP(4, dev, "AUTOPPS already active " - "2nd try:use default values\n"); - if (dev->ta1 == 0x11) - DEBUGP(4, dev, "No AUTOPPS necessary " - "TA(1)==0x11\n"); - if (test_bit(IS_ANY_T0, &dev->flags) - && test_bit(IS_ANY_T1, &dev->flags)) - DEBUGP(4, dev, "Do NOT perform AUTOPPS " - "with multiprotocol cards\n"); - clear_bit(IS_AUTOPPS_ACT, &dev->flags); - wake_up_interruptible(&dev->atrq); - } - } else { - DEBUGP(4, dev, "ATR invalid\n"); - wake_up_interruptible(&dev->atrq); - } - break; - case M_BAD_CARD: - DEBUGP(4, dev, "M_BAD_CARD\n"); - /* slow down warning, but prompt immediately after insertion */ - if (dev->cwarn == 0 || dev->cwarn == 10) { - set_bit(IS_BAD_CARD, &dev->flags); - dev_warn(&dev->p_dev->dev, MODULE_NAME ": "); - if (test_bit(IS_BAD_CSUM, &dev->flags)) { - DEBUGP(4, dev, "ATR checksum (0x%.2x, should " - "be zero) failed\n", dev->atr_csum); - } -#ifdef CM4000_DEBUG - else if (test_bit(IS_BAD_LENGTH, &dev->flags)) { - DEBUGP(4, dev, "ATR length error\n"); - } else { - DEBUGP(4, dev, "card damaged or wrong way " - "inserted\n"); - } -#endif - dev->cwarn = 0; - wake_up_interruptible(&dev->atrq); /* wake open */ - } - dev->cwarn++; - dev->mdelay = T_100MSEC; - dev->mstate = M_FETCH_ATR; - break; - default: - DEBUGP(7, dev, "Unknown action\n"); - break; /* nothing */ - } - -release_io: - DEBUGP(7, dev, "release_io\n"); - clear_bit(LOCK_IO, &dev->flags); - wake_up_interruptible(&dev->ioq); /* whoever needs IO */ - -return_with_timer: - DEBUGP(7, dev, "<- monitor_card (returns with timer)\n"); - mod_timer(&dev->timer, jiffies + dev->mdelay); - clear_bit(LOCK_MONITOR, &dev->flags); -} - -/* Interface to userland (file_operations) */ - -static ssize_t cmm_read(struct file *filp, __user char *buf, size_t count, - loff_t *ppos) -{ - struct cm4000_dev *dev = filp->private_data; - unsigned int iobase = dev->p_dev->resource[0]->start; - ssize_t rc; - int i, j, k; - - DEBUGP(2, dev, "-> cmm_read(%s,%d)\n", current->comm, current->pid); - - if (count == 0) /* according to manpage */ - return 0; - - if (!pcmcia_dev_present(dev->p_dev) || /* device removed */ - test_bit(IS_CMM_ABSENT, &dev->flags)) - return -ENODEV; - - if (test_bit(IS_BAD_CSUM, &dev->flags)) - return -EIO; - - /* also see the note about this in cmm_write */ - if (wait_event_interruptible - (dev->atrq, - ((filp->f_flags & O_NONBLOCK) - || (test_bit(IS_ATR_PRESENT, (void *)&dev->flags) != 0)))) { - if (filp->f_flags & O_NONBLOCK) - return -EAGAIN; - return -ERESTARTSYS; - } - - if (test_bit(IS_ATR_VALID, &dev->flags) == 0) - return -EIO; - - /* this one implements blocking IO */ - if (wait_event_interruptible - (dev->readq, - ((filp->f_flags & O_NONBLOCK) || (dev->rpos < dev->rlen)))) { - if (filp->f_flags & O_NONBLOCK) - return -EAGAIN; - return -ERESTARTSYS; - } - - /* lock io */ - if (wait_event_interruptible - (dev->ioq, - ((filp->f_flags & O_NONBLOCK) - || (test_and_set_bit(LOCK_IO, (void *)&dev->flags) == 0)))) { - if (filp->f_flags & O_NONBLOCK) - return -EAGAIN; - return -ERESTARTSYS; - } - - rc = 0; - dev->flags0 = inb(REG_FLAGS0(iobase)); - if ((dev->flags0 & 1) == 0 /* no smartcard inserted */ - || dev->flags0 == 0xff) { /* no cardman inserted */ - clear_bit(IS_ATR_VALID, &dev->flags); - if (dev->flags0 & 1) { - set_bit(IS_CMM_ABSENT, &dev->flags); - rc = -ENODEV; - } else { - rc = -EIO; - } - goto release_io; - } - - DEBUGP(4, dev, "begin read answer\n"); - j = min(count, (size_t)(dev->rlen - dev->rpos)); - k = dev->rpos; - if (k + j > 255) - j = 256 - k; - DEBUGP(4, dev, "read1 j=%d\n", j); - for (i = 0; i < j; i++) { - xoutb(k++, REG_BUF_ADDR(iobase)); - dev->rbuf[i] = xinb(REG_BUF_DATA(iobase)); - } - j = min(count, (size_t)(dev->rlen - dev->rpos)); - if (k + j > 255) { - DEBUGP(4, dev, "read2 j=%d\n", j); - dev->flags1 |= 0x10; /* MSB buf addr set */ - xoutb(dev->flags1, REG_FLAGS1(iobase)); - for (; i < j; i++) { - xoutb(k++, REG_BUF_ADDR(iobase)); - dev->rbuf[i] = xinb(REG_BUF_DATA(iobase)); - } - } - - if (dev->proto == 0 && count > dev->rlen - dev->rpos && i) { - DEBUGP(4, dev, "T=0 and count > buffer\n"); - dev->rbuf[i] = dev->rbuf[i - 1]; - dev->rbuf[i - 1] = dev->procbyte; - j++; - } - count = j; - - dev->rpos = dev->rlen + 1; - - /* Clear T1Active */ - DEBUGP(4, dev, "Clear T1Active\n"); - dev->flags1 &= 0xdf; - xoutb(dev->flags1, REG_FLAGS1(iobase)); - - xoutb(0, REG_FLAGS1(iobase)); /* clear detectCMM */ - /* last check before exit */ - if (!io_detect_cm4000(iobase, dev)) { - rc = -ENODEV; - goto release_io; - } - - if (test_bit(IS_INVREV, &dev->flags) && count > 0) - str_invert_revert(dev->rbuf, count); - - if (copy_to_user(buf, dev->rbuf, count)) - rc = -EFAULT; - -release_io: - clear_bit(LOCK_IO, &dev->flags); - wake_up_interruptible(&dev->ioq); - - DEBUGP(2, dev, "<- cmm_read returns: rc = %zi\n", - (rc < 0 ? rc : count)); - return rc < 0 ? rc : count; -} - -static ssize_t cmm_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct cm4000_dev *dev = filp->private_data; - unsigned int iobase = dev->p_dev->resource[0]->start; - unsigned short s; - unsigned char infolen; - unsigned char sendT0; - unsigned short nsend; - unsigned short nr; - ssize_t rc; - int i; - - DEBUGP(2, dev, "-> cmm_write(%s,%d)\n", current->comm, current->pid); - - if (count == 0) /* according to manpage */ - return 0; - - if (dev->proto == 0 && count < 4) { - /* T0 must have at least 4 bytes */ - DEBUGP(4, dev, "T0 short write\n"); - return -EIO; - } - - nr = count & 0x1ff; /* max bytes to write */ - - sendT0 = dev->proto ? 0 : nr > 5 ? 0x08 : 0; - - if (!pcmcia_dev_present(dev->p_dev) || /* device removed */ - test_bit(IS_CMM_ABSENT, &dev->flags)) - return -ENODEV; - - if (test_bit(IS_BAD_CSUM, &dev->flags)) { - DEBUGP(4, dev, "bad csum\n"); - return -EIO; - } - - /* - * wait for atr to become valid. - * note: it is important to lock this code. if we dont, the monitor - * could be run between test_bit and the call to sleep on the - * atr-queue. if *then* the monitor detects atr valid, it will wake up - * any process on the atr-queue, *but* since we have been interrupted, - * we do not yet sleep on this queue. this would result in a missed - * wake_up and the calling process would sleep forever (until - * interrupted). also, do *not* restore_flags before sleep_on, because - * this could result in the same situation! - */ - if (wait_event_interruptible - (dev->atrq, - ((filp->f_flags & O_NONBLOCK) - || (test_bit(IS_ATR_PRESENT, (void *)&dev->flags) != 0)))) { - if (filp->f_flags & O_NONBLOCK) - return -EAGAIN; - return -ERESTARTSYS; - } - - if (test_bit(IS_ATR_VALID, &dev->flags) == 0) { /* invalid atr */ - DEBUGP(4, dev, "invalid ATR\n"); - return -EIO; - } - - /* lock io */ - if (wait_event_interruptible - (dev->ioq, - ((filp->f_flags & O_NONBLOCK) - || (test_and_set_bit(LOCK_IO, (void *)&dev->flags) == 0)))) { - if (filp->f_flags & O_NONBLOCK) - return -EAGAIN; - return -ERESTARTSYS; - } - - if (copy_from_user(dev->sbuf, buf, ((count > 512) ? 512 : count))) - return -EFAULT; - - rc = 0; - dev->flags0 = inb(REG_FLAGS0(iobase)); - if ((dev->flags0 & 1) == 0 /* no smartcard inserted */ - || dev->flags0 == 0xff) { /* no cardman inserted */ - clear_bit(IS_ATR_VALID, &dev->flags); - if (dev->flags0 & 1) { - set_bit(IS_CMM_ABSENT, &dev->flags); - rc = -ENODEV; - } else { - DEBUGP(4, dev, "IO error\n"); - rc = -EIO; - } - goto release_io; - } - - xoutb(0x80, REG_FLAGS0(iobase)); /* reset SM */ - - if (!io_detect_cm4000(iobase, dev)) { - rc = -ENODEV; - goto release_io; - } - - /* reflect T=0 send/read mode in flags1 */ - dev->flags1 |= (sendT0); - - set_cardparameter(dev); - - /* dummy read, reset flag procedure received */ - inb(REG_FLAGS1(iobase)); - - dev->flags1 = 0x20 /* T_Active */ - | (sendT0) - | (test_bit(IS_INVREV, &dev->flags) ? 2 : 0)/* inverse parity */ - | (((dev->baudv - 1) & 0x0100) >> 8); /* MSB-Baud */ - DEBUGP(1, dev, "set dev->flags1 = 0x%.2x\n", dev->flags1); - xoutb(dev->flags1, REG_FLAGS1(iobase)); - - /* xmit data */ - DEBUGP(4, dev, "Xmit data\n"); - for (i = 0; i < nr; i++) { - if (i >= 256) { - dev->flags1 = 0x20 /* T_Active */ - | (sendT0) /* SendT0 */ - /* inverse parity: */ - | (test_bit(IS_INVREV, &dev->flags) ? 2 : 0) - | (((dev->baudv - 1) & 0x0100) >> 8) /* MSB-Baud */ - | 0x10; /* set address high */ - DEBUGP(4, dev, "dev->flags = 0x%.2x - set address " - "high\n", dev->flags1); - xoutb(dev->flags1, REG_FLAGS1(iobase)); - } - if (test_bit(IS_INVREV, &dev->flags)) { - DEBUGP(4, dev, "Apply inverse convention for 0x%.2x " - "-> 0x%.2x\n", (unsigned char)dev->sbuf[i], - invert_revert(dev->sbuf[i])); - xoutb(i, REG_BUF_ADDR(iobase)); - xoutb(invert_revert(dev->sbuf[i]), - REG_BUF_DATA(iobase)); - } else { - xoutb(i, REG_BUF_ADDR(iobase)); - xoutb(dev->sbuf[i], REG_BUF_DATA(iobase)); - } - } - DEBUGP(4, dev, "Xmit done\n"); - - if (dev->proto == 0) { - /* T=0 proto: 0 byte reply */ - if (nr == 4) { - DEBUGP(4, dev, "T=0 assumes 0 byte reply\n"); - xoutb(i, REG_BUF_ADDR(iobase)); - if (test_bit(IS_INVREV, &dev->flags)) - xoutb(0xff, REG_BUF_DATA(iobase)); - else - xoutb(0x00, REG_BUF_DATA(iobase)); - } - - /* numSendBytes */ - if (sendT0) - nsend = nr; - else { - if (nr == 4) - nsend = 5; - else { - nsend = 5 + (unsigned char)dev->sbuf[4]; - if (dev->sbuf[4] == 0) - nsend += 0x100; - } - } - } else - nsend = nr; - - /* T0: output procedure byte */ - if (test_bit(IS_INVREV, &dev->flags)) { - DEBUGP(4, dev, "T=0 set Procedure byte (inverse-reverse) " - "0x%.2x\n", invert_revert(dev->sbuf[1])); - xoutb(invert_revert(dev->sbuf[1]), REG_NUM_BYTES(iobase)); - } else { - DEBUGP(4, dev, "T=0 set Procedure byte 0x%.2x\n", dev->sbuf[1]); - xoutb(dev->sbuf[1], REG_NUM_BYTES(iobase)); - } - - DEBUGP(1, dev, "set NumSendBytes = 0x%.2x\n", - (unsigned char)(nsend & 0xff)); - xoutb((unsigned char)(nsend & 0xff), REG_NUM_SEND(iobase)); - - DEBUGP(1, dev, "Trigger CARDMAN CONTROLLER (0x%.2x)\n", - 0x40 /* SM_Active */ - | (dev->flags0 & 2 ? 0 : 4) /* power on if needed */ - |(dev->proto ? 0x10 : 0x08) /* T=1/T=0 */ - |(nsend & 0x100) >> 8 /* MSB numSendBytes */ ); - xoutb(0x40 /* SM_Active */ - | (dev->flags0 & 2 ? 0 : 4) /* power on if needed */ - |(dev->proto ? 0x10 : 0x08) /* T=1/T=0 */ - |(nsend & 0x100) >> 8, /* MSB numSendBytes */ - REG_FLAGS0(iobase)); - - /* wait for xmit done */ - if (dev->proto == 1) { - DEBUGP(4, dev, "Wait for xmit done\n"); - for (i = 0; i < 1000; i++) { - if (inb(REG_FLAGS0(iobase)) & 0x08) - break; - msleep_interruptible(10); - } - if (i == 1000) { - DEBUGP(4, dev, "timeout waiting for xmit done\n"); - rc = -EIO; - goto release_io; - } - } - - /* T=1: wait for infoLen */ - - infolen = 0; - if (dev->proto) { - /* wait until infoLen is valid */ - for (i = 0; i < 6000; i++) { /* max waiting time of 1 min */ - io_read_num_rec_bytes(iobase, &s); - if (s >= 3) { - infolen = inb(REG_FLAGS1(iobase)); - DEBUGP(4, dev, "infolen=%d\n", infolen); - break; - } - msleep_interruptible(10); - } - if (i == 6000) { - DEBUGP(4, dev, "timeout waiting for infoLen\n"); - rc = -EIO; - goto release_io; - } - } else - clear_bit(IS_PROCBYTE_PRESENT, &dev->flags); - - /* numRecBytes | bit9 of numRecytes */ - io_read_num_rec_bytes(iobase, &dev->rlen); - for (i = 0; i < 600; i++) { /* max waiting time of 2 sec */ - if (dev->proto) { - if (dev->rlen >= infolen + 4) - break; - } - msleep_interruptible(10); - /* numRecBytes | bit9 of numRecytes */ - io_read_num_rec_bytes(iobase, &s); - if (s > dev->rlen) { - DEBUGP(1, dev, "NumRecBytes inc (reset timeout)\n"); - i = 0; /* reset timeout */ - dev->rlen = s; - } - /* T=0: we are done when numRecBytes doesn't - * increment any more and NoProcedureByte - * is set and numRecBytes == bytes sent + 6 - * (header bytes + data + 1 for sw2) - * except when the card replies an error - * which means, no data will be sent back. - */ - else if (dev->proto == 0) { - if ((inb(REG_BUF_ADDR(iobase)) & 0x80)) { - /* no procedure byte received since last read */ - DEBUGP(1, dev, "NoProcedure byte set\n"); - /* i=0; */ - } else { - /* procedure byte received since last read */ - DEBUGP(1, dev, "NoProcedure byte unset " - "(reset timeout)\n"); - dev->procbyte = inb(REG_FLAGS1(iobase)); - DEBUGP(1, dev, "Read procedure byte 0x%.2x\n", - dev->procbyte); - i = 0; /* resettimeout */ - } - if (inb(REG_FLAGS0(iobase)) & 0x08) { - DEBUGP(1, dev, "T0Done flag (read reply)\n"); - break; - } - } - if (dev->proto) - infolen = inb(REG_FLAGS1(iobase)); - } - if (i == 600) { - DEBUGP(1, dev, "timeout waiting for numRecBytes\n"); - rc = -EIO; - goto release_io; - } else { - if (dev->proto == 0) { - DEBUGP(1, dev, "Wait for T0Done bit to be set\n"); - for (i = 0; i < 1000; i++) { - if (inb(REG_FLAGS0(iobase)) & 0x08) - break; - msleep_interruptible(10); - } - if (i == 1000) { - DEBUGP(1, dev, "timeout waiting for T0Done\n"); - rc = -EIO; - goto release_io; - } - - dev->procbyte = inb(REG_FLAGS1(iobase)); - DEBUGP(4, dev, "Read procedure byte 0x%.2x\n", - dev->procbyte); - - io_read_num_rec_bytes(iobase, &dev->rlen); - DEBUGP(4, dev, "Read NumRecBytes = %i\n", dev->rlen); - - } - } - /* T=1: read offset=zero, T=0: read offset=after challenge */ - dev->rpos = dev->proto ? 0 : nr == 4 ? 5 : nr > dev->rlen ? 5 : nr; - DEBUGP(4, dev, "dev->rlen = %i, dev->rpos = %i, nr = %i\n", - dev->rlen, dev->rpos, nr); - -release_io: - DEBUGP(4, dev, "Reset SM\n"); - xoutb(0x80, REG_FLAGS0(iobase)); /* reset SM */ - - if (rc < 0) { - DEBUGP(4, dev, "Write failed but clear T_Active\n"); - dev->flags1 &= 0xdf; - xoutb(dev->flags1, REG_FLAGS1(iobase)); - } - - clear_bit(LOCK_IO, &dev->flags); - wake_up_interruptible(&dev->ioq); - wake_up_interruptible(&dev->readq); /* tell read we have data */ - - /* ITSEC E2: clear write buffer */ - memset((char *)dev->sbuf, 0, 512); - - /* return error or actually written bytes */ - DEBUGP(2, dev, "<- cmm_write\n"); - return rc < 0 ? rc : nr; -} - -static void start_monitor(struct cm4000_dev *dev) -{ - DEBUGP(3, dev, "-> start_monitor\n"); - if (!dev->monitor_running) { - DEBUGP(5, dev, "create, init and add timer\n"); - timer_setup(&dev->timer, monitor_card, 0); - dev->monitor_running = 1; - mod_timer(&dev->timer, jiffies); - } else - DEBUGP(5, dev, "monitor already running\n"); - DEBUGP(3, dev, "<- start_monitor\n"); -} - -static void stop_monitor(struct cm4000_dev *dev) -{ - DEBUGP(3, dev, "-> stop_monitor\n"); - if (dev->monitor_running) { - DEBUGP(5, dev, "stopping monitor\n"); - terminate_monitor(dev); - /* reset monitor SM */ - clear_bit(IS_ATR_VALID, &dev->flags); - clear_bit(IS_ATR_PRESENT, &dev->flags); - } else - DEBUGP(5, dev, "monitor already stopped\n"); - DEBUGP(3, dev, "<- stop_monitor\n"); -} - -static long cmm_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) -{ - struct cm4000_dev *dev = filp->private_data; - unsigned int iobase = dev->p_dev->resource[0]->start; - struct inode *inode = file_inode(filp); - struct pcmcia_device *link; - int rc; - void __user *argp = (void __user *)arg; -#ifdef CM4000_DEBUG - char *ioctl_names[CM_IOC_MAXNR + 1] = { - [_IOC_NR(CM_IOCGSTATUS)] "CM_IOCGSTATUS", - [_IOC_NR(CM_IOCGATR)] "CM_IOCGATR", - [_IOC_NR(CM_IOCARDOFF)] "CM_IOCARDOFF", - [_IOC_NR(CM_IOCSPTS)] "CM_IOCSPTS", - [_IOC_NR(CM_IOSDBGLVL)] "CM4000_DBGLVL", - }; - DEBUGP(3, dev, "cmm_ioctl(device=%d.%d) %s\n", imajor(inode), - iminor(inode), ioctl_names[_IOC_NR(cmd)]); -#endif - - mutex_lock(&cmm_mutex); - rc = -ENODEV; - link = dev_table[iminor(inode)]; - if (!pcmcia_dev_present(link)) { - DEBUGP(4, dev, "DEV_OK false\n"); - goto out; - } - - if (test_bit(IS_CMM_ABSENT, &dev->flags)) { - DEBUGP(4, dev, "CMM_ABSENT flag set\n"); - goto out; - } - rc = -EINVAL; - - if (_IOC_TYPE(cmd) != CM_IOC_MAGIC) { - DEBUGP(4, dev, "ioctype mismatch\n"); - goto out; - } - if (_IOC_NR(cmd) > CM_IOC_MAXNR) { - DEBUGP(4, dev, "iocnr mismatch\n"); - goto out; - } - rc = 0; - - switch (cmd) { - case CM_IOCGSTATUS: - DEBUGP(4, dev, " ... in CM_IOCGSTATUS\n"); - { - int status; - - /* clear other bits, but leave inserted & powered as - * they are */ - status = dev->flags0 & 3; - if (test_bit(IS_ATR_PRESENT, &dev->flags)) - status |= CM_ATR_PRESENT; - if (test_bit(IS_ATR_VALID, &dev->flags)) - status |= CM_ATR_VALID; - if (test_bit(IS_CMM_ABSENT, &dev->flags)) - status |= CM_NO_READER; - if (test_bit(IS_BAD_CARD, &dev->flags)) - status |= CM_BAD_CARD; - if (copy_to_user(argp, &status, sizeof(int))) - rc = -EFAULT; - } - break; - case CM_IOCGATR: - DEBUGP(4, dev, "... in CM_IOCGATR\n"); - { - struct atreq __user *atreq = argp; - int tmp; - /* allow nonblocking io and being interrupted */ - if (wait_event_interruptible - (dev->atrq, - ((filp->f_flags & O_NONBLOCK) - || (test_bit(IS_ATR_PRESENT, (void *)&dev->flags) - != 0)))) { - if (filp->f_flags & O_NONBLOCK) - rc = -EAGAIN; - else - rc = -ERESTARTSYS; - break; - } - - rc = -EFAULT; - if (test_bit(IS_ATR_VALID, &dev->flags) == 0) { - tmp = -1; - if (copy_to_user(&(atreq->atr_len), &tmp, - sizeof(int))) - break; - } else { - if (copy_to_user(atreq->atr, dev->atr, - dev->atr_len)) - break; - - tmp = dev->atr_len; - if (copy_to_user(&(atreq->atr_len), &tmp, sizeof(int))) - break; - } - rc = 0; - break; - } - case CM_IOCARDOFF: - -#ifdef CM4000_DEBUG - DEBUGP(4, dev, "... in CM_IOCARDOFF\n"); - if (dev->flags0 & 0x01) { - DEBUGP(4, dev, " Card inserted\n"); - } else { - DEBUGP(2, dev, " No card inserted\n"); - } - if (dev->flags0 & 0x02) { - DEBUGP(4, dev, " Card powered\n"); - } else { - DEBUGP(2, dev, " Card not powered\n"); - } -#endif - - /* is a card inserted and powered? */ - if ((dev->flags0 & 0x01) && (dev->flags0 & 0x02)) { - - /* get IO lock */ - if (wait_event_interruptible - (dev->ioq, - ((filp->f_flags & O_NONBLOCK) - || (test_and_set_bit(LOCK_IO, (void *)&dev->flags) - == 0)))) { - if (filp->f_flags & O_NONBLOCK) - rc = -EAGAIN; - else - rc = -ERESTARTSYS; - break; - } - /* Set Flags0 = 0x42 */ - DEBUGP(4, dev, "Set Flags0=0x42 \n"); - xoutb(0x42, REG_FLAGS0(iobase)); - clear_bit(IS_ATR_PRESENT, &dev->flags); - clear_bit(IS_ATR_VALID, &dev->flags); - dev->mstate = M_CARDOFF; - clear_bit(LOCK_IO, &dev->flags); - if (wait_event_interruptible - (dev->atrq, - ((filp->f_flags & O_NONBLOCK) - || (test_bit(IS_ATR_VALID, (void *)&dev->flags) != - 0)))) { - if (filp->f_flags & O_NONBLOCK) - rc = -EAGAIN; - else - rc = -ERESTARTSYS; - break; - } - } - /* release lock */ - clear_bit(LOCK_IO, &dev->flags); - wake_up_interruptible(&dev->ioq); - - rc = 0; - break; - case CM_IOCSPTS: - { - struct ptsreq krnptsreq; - - if (copy_from_user(&krnptsreq, argp, - sizeof(struct ptsreq))) { - rc = -EFAULT; - break; - } - - rc = 0; - DEBUGP(4, dev, "... in CM_IOCSPTS\n"); - /* wait for ATR to get valid */ - if (wait_event_interruptible - (dev->atrq, - ((filp->f_flags & O_NONBLOCK) - || (test_bit(IS_ATR_PRESENT, (void *)&dev->flags) - != 0)))) { - if (filp->f_flags & O_NONBLOCK) - rc = -EAGAIN; - else - rc = -ERESTARTSYS; - break; - } - /* get IO lock */ - if (wait_event_interruptible - (dev->ioq, - ((filp->f_flags & O_NONBLOCK) - || (test_and_set_bit(LOCK_IO, (void *)&dev->flags) - == 0)))) { - if (filp->f_flags & O_NONBLOCK) - rc = -EAGAIN; - else - rc = -ERESTARTSYS; - break; - } - - if ((rc = set_protocol(dev, &krnptsreq)) != 0) { - /* auto power_on again */ - dev->mstate = M_FETCH_ATR; - clear_bit(IS_ATR_VALID, &dev->flags); - } - /* release lock */ - clear_bit(LOCK_IO, &dev->flags); - wake_up_interruptible(&dev->ioq); - - } - break; -#ifdef CM4000_DEBUG - case CM_IOSDBGLVL: - rc = -ENOTTY; - break; -#endif - default: - DEBUGP(4, dev, "... in default (unknown IOCTL code)\n"); - rc = -ENOTTY; - } -out: - mutex_unlock(&cmm_mutex); - return rc; -} - -static int cmm_open(struct inode *inode, struct file *filp) -{ - struct cm4000_dev *dev; - struct pcmcia_device *link; - int minor = iminor(inode); - int ret; - - if (minor >= CM4000_MAX_DEV) - return -ENODEV; - - mutex_lock(&cmm_mutex); - link = dev_table[minor]; - if (link == NULL || !pcmcia_dev_present(link)) { - ret = -ENODEV; - goto out; - } - - if (link->open) { - ret = -EBUSY; - goto out; - } - - dev = link->priv; - filp->private_data = dev; - - DEBUGP(2, dev, "-> cmm_open(device=%d.%d process=%s,%d)\n", - imajor(inode), minor, current->comm, current->pid); - - /* init device variables, they may be "polluted" after close - * or, the device may never have been closed (i.e. open failed) - */ - - ZERO_DEV(dev); - - /* opening will always block since the - * monitor will be started by open, which - * means we have to wait for ATR becoming - * valid = block until valid (or card - * inserted) - */ - if (filp->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - goto out; - } - - dev->mdelay = T_50MSEC; - - /* start monitoring the cardstatus */ - start_monitor(dev); - - link->open = 1; /* only one open per device */ - - DEBUGP(2, dev, "<- cmm_open\n"); - ret = stream_open(inode, filp); -out: - mutex_unlock(&cmm_mutex); - return ret; -} - -static int cmm_close(struct inode *inode, struct file *filp) -{ - struct cm4000_dev *dev; - struct pcmcia_device *link; - int minor = iminor(inode); - - if (minor >= CM4000_MAX_DEV) - return -ENODEV; - - link = dev_table[minor]; - if (link == NULL) - return -ENODEV; - - dev = link->priv; - - DEBUGP(2, dev, "-> cmm_close(maj/min=%d.%d)\n", - imajor(inode), minor); - - stop_monitor(dev); - - ZERO_DEV(dev); - - link->open = 0; /* only one open per device */ - wake_up(&dev->devq); /* socket removed? */ - - DEBUGP(2, dev, "cmm_close\n"); - return 0; -} - -static void cmm_cm4000_release(struct pcmcia_device * link) -{ - struct cm4000_dev *dev = link->priv; - - /* dont terminate the monitor, rather rely on - * close doing that for us. - */ - DEBUGP(3, dev, "-> cmm_cm4000_release\n"); - while (link->open) { - printk(KERN_INFO MODULE_NAME ": delaying release until " - "process has terminated\n"); - /* note: don't interrupt us: - * close the applications which own - * the devices _first_ ! - */ - wait_event(dev->devq, (link->open == 0)); - } - /* dev->devq=NULL; this cannot be zeroed earlier */ - DEBUGP(3, dev, "<- cmm_cm4000_release\n"); - return; -} - -/*==== Interface to PCMCIA Layer =======================================*/ - -static int cm4000_config_check(struct pcmcia_device *p_dev, void *priv_data) -{ - return pcmcia_request_io(p_dev); -} - -static int cm4000_config(struct pcmcia_device * link, int devno) -{ - link->config_flags |= CONF_AUTO_SET_IO; - - /* read the config-tuples */ - if (pcmcia_loop_config(link, cm4000_config_check, NULL)) - goto cs_release; - - if (pcmcia_enable_device(link)) - goto cs_release; - - return 0; - -cs_release: - cm4000_release(link); - return -ENODEV; -} - -static int cm4000_suspend(struct pcmcia_device *link) -{ - struct cm4000_dev *dev; - - dev = link->priv; - stop_monitor(dev); - - return 0; -} - -static int cm4000_resume(struct pcmcia_device *link) -{ - struct cm4000_dev *dev; - - dev = link->priv; - if (link->open) - start_monitor(dev); - - return 0; -} - -static void cm4000_release(struct pcmcia_device *link) -{ - cmm_cm4000_release(link); /* delay release until device closed */ - pcmcia_disable_device(link); -} - -static int cm4000_probe(struct pcmcia_device *link) -{ - struct cm4000_dev *dev; - int i, ret; - - for (i = 0; i < CM4000_MAX_DEV; i++) - if (dev_table[i] == NULL) - break; - - if (i == CM4000_MAX_DEV) { - printk(KERN_NOTICE MODULE_NAME ": all devices in use\n"); - return -ENODEV; - } - - /* create a new cm4000_cs device */ - dev = kzalloc(sizeof(struct cm4000_dev), GFP_KERNEL); - if (dev == NULL) - return -ENOMEM; - - dev->p_dev = link; - link->priv = dev; - dev_table[i] = link; - - init_waitqueue_head(&dev->devq); - init_waitqueue_head(&dev->ioq); - init_waitqueue_head(&dev->atrq); - init_waitqueue_head(&dev->readq); - - ret = cm4000_config(link, i); - if (ret) { - dev_table[i] = NULL; - kfree(dev); - return ret; - } - - device_create(cmm_class, NULL, MKDEV(major, i), NULL, "cmm%d", i); - - return 0; -} - -static void cm4000_detach(struct pcmcia_device *link) -{ - struct cm4000_dev *dev = link->priv; - int devno; - - /* find device */ - for (devno = 0; devno < CM4000_MAX_DEV; devno++) - if (dev_table[devno] == link) - break; - if (devno == CM4000_MAX_DEV) - return; - - stop_monitor(dev); - - cm4000_release(link); - - dev_table[devno] = NULL; - kfree(dev); - - device_destroy(cmm_class, MKDEV(major, devno)); - - return; -} - -static const struct file_operations cm4000_fops = { - .owner = THIS_MODULE, - .read = cmm_read, - .write = cmm_write, - .unlocked_ioctl = cmm_ioctl, - .open = cmm_open, - .release= cmm_close, - .llseek = no_llseek, -}; - -static const struct pcmcia_device_id cm4000_ids[] = { - PCMCIA_DEVICE_MANF_CARD(0x0223, 0x0002), - PCMCIA_DEVICE_PROD_ID12("CardMan", "4000", 0x2FB368CA, 0xA2BD8C39), - PCMCIA_DEVICE_NULL, -}; -MODULE_DEVICE_TABLE(pcmcia, cm4000_ids); - -static struct pcmcia_driver cm4000_driver = { - .owner = THIS_MODULE, - .name = "cm4000_cs", - .probe = cm4000_probe, - .remove = cm4000_detach, - .suspend = cm4000_suspend, - .resume = cm4000_resume, - .id_table = cm4000_ids, -}; - -static int __init cmm_init(void) -{ - int rc; - - cmm_class = class_create(THIS_MODULE, "cardman_4000"); - if (IS_ERR(cmm_class)) - return PTR_ERR(cmm_class); - - major = register_chrdev(0, DEVICE_NAME, &cm4000_fops); - if (major < 0) { - printk(KERN_WARNING MODULE_NAME - ": could not get major number\n"); - class_destroy(cmm_class); - return major; - } - - rc = pcmcia_register_driver(&cm4000_driver); - if (rc < 0) { - unregister_chrdev(major, DEVICE_NAME); - class_destroy(cmm_class); - return rc; - } - - return 0; -} - -static void __exit cmm_exit(void) -{ - pcmcia_unregister_driver(&cm4000_driver); - unregister_chrdev(major, DEVICE_NAME); - class_destroy(cmm_class); -}; - -module_init(cmm_init); -module_exit(cmm_exit); -MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c deleted file mode 100644 index 827711911da4..000000000000 --- a/drivers/char/pcmcia/cm4040_cs.c +++ /dev/null @@ -1,684 +0,0 @@ -/* - * A driver for the Omnikey PCMCIA smartcard reader CardMan 4040 - * - * (c) 2000-2004 Omnikey AG (http://www.omnikey.com/) - * - * (C) 2005-2006 Harald Welte - * - add support for poll() - * - driver cleanup - * - add waitqueues - * - adhere to linux kernel coding style and policies - * - support 2.6.13 "new style" pcmcia interface - * - add class interface for udev device creation - * - * The device basically is a USB CCID compliant device that has been - * attached to an I/O-Mapped FIFO. - * - * All rights reserved, Dual BSD/GPL Licensed. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include "cm4040_cs.h" - - -#define reader_to_dev(x) (&x->p_dev->dev) - -/* n (debug level) is ignored */ -/* additional debug output may be enabled by re-compiling with - * CM4040_DEBUG set */ -/* #define CM4040_DEBUG */ -#define DEBUGP(n, rdr, x, args...) do { \ - dev_dbg(reader_to_dev(rdr), "%s:" x, \ - __func__ , ## args); \ - } while (0) - -static DEFINE_MUTEX(cm4040_mutex); - -#define CCID_DRIVER_BULK_DEFAULT_TIMEOUT (150*HZ) -#define CCID_DRIVER_ASYNC_POWERUP_TIMEOUT (35*HZ) -#define CCID_DRIVER_MINIMUM_TIMEOUT (3*HZ) -#define READ_WRITE_BUFFER_SIZE 512 -#define POLL_LOOP_COUNT 1000 - -/* how often to poll for fifo status change */ -#define POLL_PERIOD msecs_to_jiffies(10) - -static void reader_release(struct pcmcia_device *link); - -static int major; -static struct class *cmx_class; - -#define BS_READABLE 0x01 -#define BS_WRITABLE 0x02 - -struct reader_dev { - struct pcmcia_device *p_dev; - wait_queue_head_t devq; - wait_queue_head_t poll_wait; - wait_queue_head_t read_wait; - wait_queue_head_t write_wait; - unsigned long buffer_status; - unsigned long timeout; - unsigned char s_buf[READ_WRITE_BUFFER_SIZE]; - unsigned char r_buf[READ_WRITE_BUFFER_SIZE]; - struct timer_list poll_timer; -}; - -static struct pcmcia_device *dev_table[CM_MAX_DEV]; - -#ifndef CM4040_DEBUG -#define xoutb outb -#define xinb inb -#else -static inline void xoutb(unsigned char val, unsigned short port) -{ - pr_debug("outb(val=%.2x,port=%.4x)\n", val, port); - outb(val, port); -} - -static inline unsigned char xinb(unsigned short port) -{ - unsigned char val; - - val = inb(port); - pr_debug("%.2x=inb(%.4x)\n", val, port); - return val; -} -#endif - -/* poll the device fifo status register. not to be confused with - * the poll syscall. */ -static void cm4040_do_poll(struct timer_list *t) -{ - struct reader_dev *dev = from_timer(dev, t, poll_timer); - unsigned int obs = xinb(dev->p_dev->resource[0]->start - + REG_OFFSET_BUFFER_STATUS); - - if ((obs & BSR_BULK_IN_FULL)) { - set_bit(BS_READABLE, &dev->buffer_status); - DEBUGP(4, dev, "waking up read_wait\n"); - wake_up_interruptible(&dev->read_wait); - } else - clear_bit(BS_READABLE, &dev->buffer_status); - - if (!(obs & BSR_BULK_OUT_FULL)) { - set_bit(BS_WRITABLE, &dev->buffer_status); - DEBUGP(4, dev, "waking up write_wait\n"); - wake_up_interruptible(&dev->write_wait); - } else - clear_bit(BS_WRITABLE, &dev->buffer_status); - - if (dev->buffer_status) - wake_up_interruptible(&dev->poll_wait); - - mod_timer(&dev->poll_timer, jiffies + POLL_PERIOD); -} - -static void cm4040_stop_poll(struct reader_dev *dev) -{ - del_timer_sync(&dev->poll_timer); -} - -static int wait_for_bulk_out_ready(struct reader_dev *dev) -{ - int i, rc; - int iobase = dev->p_dev->resource[0]->start; - - for (i = 0; i < POLL_LOOP_COUNT; i++) { - if ((xinb(iobase + REG_OFFSET_BUFFER_STATUS) - & BSR_BULK_OUT_FULL) == 0) { - DEBUGP(4, dev, "BulkOut empty (i=%d)\n", i); - return 1; - } - } - - DEBUGP(4, dev, "wait_event_interruptible_timeout(timeout=%ld\n", - dev->timeout); - rc = wait_event_interruptible_timeout(dev->write_wait, - test_and_clear_bit(BS_WRITABLE, - &dev->buffer_status), - dev->timeout); - - if (rc > 0) - DEBUGP(4, dev, "woke up: BulkOut empty\n"); - else if (rc == 0) - DEBUGP(4, dev, "woke up: BulkOut full, returning 0 :(\n"); - else if (rc < 0) - DEBUGP(4, dev, "woke up: signal arrived\n"); - - return rc; -} - -/* Write to Sync Control Register */ -static int write_sync_reg(unsigned char val, struct reader_dev *dev) -{ - int iobase = dev->p_dev->resource[0]->start; - int rc; - - rc = wait_for_bulk_out_ready(dev); - if (rc <= 0) - return rc; - - xoutb(val, iobase + REG_OFFSET_SYNC_CONTROL); - rc = wait_for_bulk_out_ready(dev); - if (rc <= 0) - return rc; - - return 1; -} - -static int wait_for_bulk_in_ready(struct reader_dev *dev) -{ - int i, rc; - int iobase = dev->p_dev->resource[0]->start; - - for (i = 0; i < POLL_LOOP_COUNT; i++) { - if ((xinb(iobase + REG_OFFSET_BUFFER_STATUS) - & BSR_BULK_IN_FULL) == BSR_BULK_IN_FULL) { - DEBUGP(3, dev, "BulkIn full (i=%d)\n", i); - return 1; - } - } - - DEBUGP(4, dev, "wait_event_interruptible_timeout(timeout=%ld\n", - dev->timeout); - rc = wait_event_interruptible_timeout(dev->read_wait, - test_and_clear_bit(BS_READABLE, - &dev->buffer_status), - dev->timeout); - if (rc > 0) - DEBUGP(4, dev, "woke up: BulkIn full\n"); - else if (rc == 0) - DEBUGP(4, dev, "woke up: BulkIn not full, returning 0 :(\n"); - else if (rc < 0) - DEBUGP(4, dev, "woke up: signal arrived\n"); - - return rc; -} - -static ssize_t cm4040_read(struct file *filp, char __user *buf, - size_t count, loff_t *ppos) -{ - struct reader_dev *dev = filp->private_data; - int iobase = dev->p_dev->resource[0]->start; - size_t bytes_to_read; - unsigned long i; - size_t min_bytes_to_read; - int rc; - - DEBUGP(2, dev, "-> cm4040_read(%s,%d)\n", current->comm, current->pid); - - if (count == 0) - return 0; - - if (count < 10) - return -EFAULT; - - if (filp->f_flags & O_NONBLOCK) { - DEBUGP(4, dev, "filep->f_flags O_NONBLOCK set\n"); - DEBUGP(2, dev, "<- cm4040_read (failure)\n"); - return -EAGAIN; - } - - if (!pcmcia_dev_present(dev->p_dev)) - return -ENODEV; - - for (i = 0; i < 5; i++) { - rc = wait_for_bulk_in_ready(dev); - if (rc <= 0) { - DEBUGP(5, dev, "wait_for_bulk_in_ready rc=%.2x\n", rc); - DEBUGP(2, dev, "<- cm4040_read (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - return -EIO; - } - dev->r_buf[i] = xinb(iobase + REG_OFFSET_BULK_IN); -#ifdef CM4040_DEBUG - pr_debug("%lu:%2x ", i, dev->r_buf[i]); - } - pr_debug("\n"); -#else - } -#endif - - bytes_to_read = 5 + le32_to_cpu(*(__le32 *)&dev->r_buf[1]); - - DEBUGP(6, dev, "BytesToRead=%zu\n", bytes_to_read); - - min_bytes_to_read = min(count, bytes_to_read + 5); - min_bytes_to_read = min_t(size_t, min_bytes_to_read, READ_WRITE_BUFFER_SIZE); - - DEBUGP(6, dev, "Min=%zu\n", min_bytes_to_read); - - for (i = 0; i < (min_bytes_to_read-5); i++) { - rc = wait_for_bulk_in_ready(dev); - if (rc <= 0) { - DEBUGP(5, dev, "wait_for_bulk_in_ready rc=%.2x\n", rc); - DEBUGP(2, dev, "<- cm4040_read (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - return -EIO; - } - dev->r_buf[i+5] = xinb(iobase + REG_OFFSET_BULK_IN); -#ifdef CM4040_DEBUG - pr_debug("%lu:%2x ", i, dev->r_buf[i]); - } - pr_debug("\n"); -#else - } -#endif - - *ppos = min_bytes_to_read; - if (copy_to_user(buf, dev->r_buf, min_bytes_to_read)) - return -EFAULT; - - rc = wait_for_bulk_in_ready(dev); - if (rc <= 0) { - DEBUGP(5, dev, "wait_for_bulk_in_ready rc=%.2x\n", rc); - DEBUGP(2, dev, "<- cm4040_read (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - return -EIO; - } - - rc = write_sync_reg(SCR_READER_TO_HOST_DONE, dev); - if (rc <= 0) { - DEBUGP(5, dev, "write_sync_reg c=%.2x\n", rc); - DEBUGP(2, dev, "<- cm4040_read (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - else - return -EIO; - } - - xinb(iobase + REG_OFFSET_BULK_IN); - - DEBUGP(2, dev, "<- cm4040_read (successfully)\n"); - return min_bytes_to_read; -} - -static ssize_t cm4040_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct reader_dev *dev = filp->private_data; - int iobase = dev->p_dev->resource[0]->start; - ssize_t rc; - int i; - unsigned int bytes_to_write; - - DEBUGP(2, dev, "-> cm4040_write(%s,%d)\n", current->comm, current->pid); - - if (count == 0) { - DEBUGP(2, dev, "<- cm4040_write empty read (successfully)\n"); - return 0; - } - - if ((count < 5) || (count > READ_WRITE_BUFFER_SIZE)) { - DEBUGP(2, dev, "<- cm4040_write buffersize=%zd < 5\n", count); - return -EIO; - } - - if (filp->f_flags & O_NONBLOCK) { - DEBUGP(4, dev, "filep->f_flags O_NONBLOCK set\n"); - DEBUGP(4, dev, "<- cm4040_write (failure)\n"); - return -EAGAIN; - } - - if (!pcmcia_dev_present(dev->p_dev)) - return -ENODEV; - - bytes_to_write = count; - if (copy_from_user(dev->s_buf, buf, bytes_to_write)) - return -EFAULT; - - switch (dev->s_buf[0]) { - case CMD_PC_TO_RDR_XFRBLOCK: - case CMD_PC_TO_RDR_SECURE: - case CMD_PC_TO_RDR_TEST_SECURE: - case CMD_PC_TO_RDR_OK_SECURE: - dev->timeout = CCID_DRIVER_BULK_DEFAULT_TIMEOUT; - break; - - case CMD_PC_TO_RDR_ICCPOWERON: - dev->timeout = CCID_DRIVER_ASYNC_POWERUP_TIMEOUT; - break; - - case CMD_PC_TO_RDR_GETSLOTSTATUS: - case CMD_PC_TO_RDR_ICCPOWEROFF: - case CMD_PC_TO_RDR_GETPARAMETERS: - case CMD_PC_TO_RDR_RESETPARAMETERS: - case CMD_PC_TO_RDR_SETPARAMETERS: - case CMD_PC_TO_RDR_ESCAPE: - case CMD_PC_TO_RDR_ICCCLOCK: - default: - dev->timeout = CCID_DRIVER_MINIMUM_TIMEOUT; - break; - } - - rc = write_sync_reg(SCR_HOST_TO_READER_START, dev); - if (rc <= 0) { - DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc); - DEBUGP(2, dev, "<- cm4040_write (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - else - return -EIO; - } - - DEBUGP(4, dev, "start \n"); - - for (i = 0; i < bytes_to_write; i++) { - rc = wait_for_bulk_out_ready(dev); - if (rc <= 0) { - DEBUGP(5, dev, "wait_for_bulk_out_ready rc=%.2zx\n", - rc); - DEBUGP(2, dev, "<- cm4040_write (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - else - return -EIO; - } - - xoutb(dev->s_buf[i],iobase + REG_OFFSET_BULK_OUT); - } - DEBUGP(4, dev, "end\n"); - - rc = write_sync_reg(SCR_HOST_TO_READER_DONE, dev); - - if (rc <= 0) { - DEBUGP(5, dev, "write_sync_reg c=%.2zx\n", rc); - DEBUGP(2, dev, "<- cm4040_write (failed)\n"); - if (rc == -ERESTARTSYS) - return rc; - else - return -EIO; - } - - DEBUGP(2, dev, "<- cm4040_write (successfully)\n"); - return count; -} - -static __poll_t cm4040_poll(struct file *filp, poll_table *wait) -{ - struct reader_dev *dev = filp->private_data; - __poll_t mask = 0; - - poll_wait(filp, &dev->poll_wait, wait); - - if (test_and_clear_bit(BS_READABLE, &dev->buffer_status)) - mask |= EPOLLIN | EPOLLRDNORM; - if (test_and_clear_bit(BS_WRITABLE, &dev->buffer_status)) - mask |= EPOLLOUT | EPOLLWRNORM; - - DEBUGP(2, dev, "<- cm4040_poll(%u)\n", mask); - - return mask; -} - -static int cm4040_open(struct inode *inode, struct file *filp) -{ - struct reader_dev *dev; - struct pcmcia_device *link; - int minor = iminor(inode); - int ret; - - if (minor >= CM_MAX_DEV) - return -ENODEV; - - mutex_lock(&cm4040_mutex); - link = dev_table[minor]; - if (link == NULL || !pcmcia_dev_present(link)) { - ret = -ENODEV; - goto out; - } - - if (link->open) { - ret = -EBUSY; - goto out; - } - - dev = link->priv; - filp->private_data = dev; - - if (filp->f_flags & O_NONBLOCK) { - DEBUGP(4, dev, "filep->f_flags O_NONBLOCK set\n"); - ret = -EAGAIN; - goto out; - } - - link->open = 1; - - mod_timer(&dev->poll_timer, jiffies + POLL_PERIOD); - - DEBUGP(2, dev, "<- cm4040_open (successfully)\n"); - ret = nonseekable_open(inode, filp); -out: - mutex_unlock(&cm4040_mutex); - return ret; -} - -static int cm4040_close(struct inode *inode, struct file *filp) -{ - struct reader_dev *dev = filp->private_data; - struct pcmcia_device *link; - int minor = iminor(inode); - - DEBUGP(2, dev, "-> cm4040_close(maj/min=%d.%d)\n", imajor(inode), - iminor(inode)); - - if (minor >= CM_MAX_DEV) - return -ENODEV; - - link = dev_table[minor]; - if (link == NULL) - return -ENODEV; - - cm4040_stop_poll(dev); - - link->open = 0; - wake_up(&dev->devq); - - DEBUGP(2, dev, "<- cm4040_close\n"); - return 0; -} - -static void cm4040_reader_release(struct pcmcia_device *link) -{ - struct reader_dev *dev = link->priv; - - DEBUGP(3, dev, "-> cm4040_reader_release\n"); - while (link->open) { - DEBUGP(3, dev, MODULE_NAME ": delaying release " - "until process has terminated\n"); - wait_event(dev->devq, (link->open == 0)); - } - DEBUGP(3, dev, "<- cm4040_reader_release\n"); - return; -} - -static int cm4040_config_check(struct pcmcia_device *p_dev, void *priv_data) -{ - return pcmcia_request_io(p_dev); -} - - -static int reader_config(struct pcmcia_device *link, int devno) -{ - struct reader_dev *dev; - int fail_rc; - - link->config_flags |= CONF_AUTO_SET_IO; - - if (pcmcia_loop_config(link, cm4040_config_check, NULL)) - goto cs_release; - - fail_rc = pcmcia_enable_device(link); - if (fail_rc != 0) { - dev_info(&link->dev, "pcmcia_enable_device failed 0x%x\n", - fail_rc); - goto cs_release; - } - - dev = link->priv; - - DEBUGP(2, dev, "device " DEVICE_NAME "%d at %pR\n", devno, - link->resource[0]); - DEBUGP(2, dev, "<- reader_config (succ)\n"); - - return 0; - -cs_release: - reader_release(link); - return -ENODEV; -} - -static void reader_release(struct pcmcia_device *link) -{ - cm4040_reader_release(link); - pcmcia_disable_device(link); -} - -static int reader_probe(struct pcmcia_device *link) -{ - struct reader_dev *dev; - int i, ret; - - for (i = 0; i < CM_MAX_DEV; i++) { - if (dev_table[i] == NULL) - break; - } - - if (i == CM_MAX_DEV) - return -ENODEV; - - dev = kzalloc(sizeof(struct reader_dev), GFP_KERNEL); - if (dev == NULL) - return -ENOMEM; - - dev->timeout = CCID_DRIVER_MINIMUM_TIMEOUT; - dev->buffer_status = 0; - - link->priv = dev; - dev->p_dev = link; - - dev_table[i] = link; - - init_waitqueue_head(&dev->devq); - init_waitqueue_head(&dev->poll_wait); - init_waitqueue_head(&dev->read_wait); - init_waitqueue_head(&dev->write_wait); - timer_setup(&dev->poll_timer, cm4040_do_poll, 0); - - ret = reader_config(link, i); - if (ret) { - dev_table[i] = NULL; - kfree(dev); - return ret; - } - - device_create(cmx_class, NULL, MKDEV(major, i), NULL, "cmx%d", i); - - return 0; -} - -static void reader_detach(struct pcmcia_device *link) -{ - struct reader_dev *dev = link->priv; - int devno; - - /* find device */ - for (devno = 0; devno < CM_MAX_DEV; devno++) { - if (dev_table[devno] == link) - break; - } - if (devno == CM_MAX_DEV) - return; - - reader_release(link); - - dev_table[devno] = NULL; - kfree(dev); - - device_destroy(cmx_class, MKDEV(major, devno)); - - return; -} - -static const struct file_operations reader_fops = { - .owner = THIS_MODULE, - .read = cm4040_read, - .write = cm4040_write, - .open = cm4040_open, - .release = cm4040_close, - .poll = cm4040_poll, - .llseek = no_llseek, -}; - -static const struct pcmcia_device_id cm4040_ids[] = { - PCMCIA_DEVICE_MANF_CARD(0x0223, 0x0200), - PCMCIA_DEVICE_PROD_ID12("OMNIKEY", "CardMan 4040", - 0xE32CDD8C, 0x8F23318B), - PCMCIA_DEVICE_NULL, -}; -MODULE_DEVICE_TABLE(pcmcia, cm4040_ids); - -static struct pcmcia_driver reader_driver = { - .owner = THIS_MODULE, - .name = "cm4040_cs", - .probe = reader_probe, - .remove = reader_detach, - .id_table = cm4040_ids, -}; - -static int __init cm4040_init(void) -{ - int rc; - - cmx_class = class_create(THIS_MODULE, "cardman_4040"); - if (IS_ERR(cmx_class)) - return PTR_ERR(cmx_class); - - major = register_chrdev(0, DEVICE_NAME, &reader_fops); - if (major < 0) { - printk(KERN_WARNING MODULE_NAME - ": could not get major number\n"); - class_destroy(cmx_class); - return major; - } - - rc = pcmcia_register_driver(&reader_driver); - if (rc < 0) { - unregister_chrdev(major, DEVICE_NAME); - class_destroy(cmx_class); - return rc; - } - - return 0; -} - -static void __exit cm4040_exit(void) -{ - pcmcia_unregister_driver(&reader_driver); - unregister_chrdev(major, DEVICE_NAME); - class_destroy(cmx_class); -} - -module_init(cm4040_init); -module_exit(cm4040_exit); -MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/char/pcmcia/cm4040_cs.h b/drivers/char/pcmcia/cm4040_cs.h deleted file mode 100644 index e2ffff995d51..000000000000 --- a/drivers/char/pcmcia/cm4040_cs.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CM4040_H_ -#define _CM4040_H_ - -#define CM_MAX_DEV 4 - -#define DEVICE_NAME "cmx" -#define MODULE_NAME "cm4040_cs" - -#define REG_OFFSET_BULK_OUT 0 -#define REG_OFFSET_BULK_IN 0 -#define REG_OFFSET_BUFFER_STATUS 1 -#define REG_OFFSET_SYNC_CONTROL 2 - -#define BSR_BULK_IN_FULL 0x02 -#define BSR_BULK_OUT_FULL 0x01 - -#define SCR_HOST_TO_READER_START 0x80 -#define SCR_ABORT 0x40 -#define SCR_EN_NOTIFY 0x20 -#define SCR_ACK_NOTIFY 0x10 -#define SCR_READER_TO_HOST_DONE 0x08 -#define SCR_HOST_TO_READER_DONE 0x04 -#define SCR_PULSE_INTERRUPT 0x02 -#define SCR_POWER_DOWN 0x01 - - -#define CMD_PC_TO_RDR_ICCPOWERON 0x62 -#define CMD_PC_TO_RDR_GETSLOTSTATUS 0x65 -#define CMD_PC_TO_RDR_ICCPOWEROFF 0x63 -#define CMD_PC_TO_RDR_SECURE 0x69 -#define CMD_PC_TO_RDR_GETPARAMETERS 0x6C -#define CMD_PC_TO_RDR_RESETPARAMETERS 0x6D -#define CMD_PC_TO_RDR_SETPARAMETERS 0x61 -#define CMD_PC_TO_RDR_XFRBLOCK 0x6F -#define CMD_PC_TO_RDR_ESCAPE 0x6B -#define CMD_PC_TO_RDR_ICCCLOCK 0x6E -#define CMD_PC_TO_RDR_TEST_SECURE 0x74 -#define CMD_PC_TO_RDR_OK_SECURE 0x89 - - -#define CMD_RDR_TO_PC_SLOTSTATUS 0x81 -#define CMD_RDR_TO_PC_DATABLOCK 0x80 -#define CMD_RDR_TO_PC_PARAMETERS 0x82 -#define CMD_RDR_TO_PC_ESCAPE 0x83 -#define CMD_RDR_TO_PC_OK_SECURE 0x89 - -#endif /* _CM4040_H_ */ diff --git a/drivers/char/pcmcia/scr24x_cs.c b/drivers/char/pcmcia/scr24x_cs.c deleted file mode 100644 index 1bdce08fae3d..000000000000 --- a/drivers/char/pcmcia/scr24x_cs.c +++ /dev/null @@ -1,359 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SCR24x PCMCIA Smart Card Reader Driver - * - * Copyright (C) 2005-2006 TL Sudheendran - * Copyright (C) 2016 Lubomir Rintel - * - * Derived from "scr24x_v4.2.6_Release.tar.gz" driver by TL Sudheendran. - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#define CCID_HEADER_SIZE 10 -#define CCID_LENGTH_OFFSET 1 -#define CCID_MAX_LEN 271 - -#define SCR24X_DATA(n) (1 + n) -#define SCR24X_CMD_STATUS 7 -#define CMD_START 0x40 -#define CMD_WRITE_BYTE 0x41 -#define CMD_READ_BYTE 0x42 -#define STATUS_BUSY 0x80 - -struct scr24x_dev { - struct device *dev; - struct cdev c_dev; - unsigned char buf[CCID_MAX_LEN]; - int devno; - struct mutex lock; - struct kref refcnt; - u8 __iomem *regs; -}; - -#define SCR24X_DEVS 8 -static DECLARE_BITMAP(scr24x_minors, SCR24X_DEVS); - -static struct class *scr24x_class; -static dev_t scr24x_devt; - -static void scr24x_delete(struct kref *kref) -{ - struct scr24x_dev *dev = container_of(kref, struct scr24x_dev, - refcnt); - - kfree(dev); -} - -static int scr24x_wait_ready(struct scr24x_dev *dev) -{ - u_char status; - int timeout = 100; - - do { - status = ioread8(dev->regs + SCR24X_CMD_STATUS); - if (!(status & STATUS_BUSY)) - return 0; - - msleep(20); - } while (--timeout); - - return -EIO; -} - -static int scr24x_open(struct inode *inode, struct file *filp) -{ - struct scr24x_dev *dev = container_of(inode->i_cdev, - struct scr24x_dev, c_dev); - - kref_get(&dev->refcnt); - filp->private_data = dev; - - return stream_open(inode, filp); -} - -static int scr24x_release(struct inode *inode, struct file *filp) -{ - struct scr24x_dev *dev = filp->private_data; - - /* We must not take the dev->lock here as scr24x_delete() - * might be called to remove the dev structure altogether. - * We don't need the lock anyway, since after the reference - * acquired in probe() is released in remove() the chrdev - * is already unregistered and noone can possibly acquire - * a reference via open() anymore. */ - kref_put(&dev->refcnt, scr24x_delete); - return 0; -} - -static int read_chunk(struct scr24x_dev *dev, size_t offset, size_t limit) -{ - size_t i, y; - int ret; - - for (i = offset; i < limit; i += 5) { - iowrite8(CMD_READ_BYTE, dev->regs + SCR24X_CMD_STATUS); - ret = scr24x_wait_ready(dev); - if (ret < 0) - return ret; - - for (y = 0; y < 5 && i + y < limit; y++) - dev->buf[i + y] = ioread8(dev->regs + SCR24X_DATA(y)); - } - - return 0; -} - -static ssize_t scr24x_read(struct file *filp, char __user *buf, size_t count, - loff_t *ppos) -{ - struct scr24x_dev *dev = filp->private_data; - int ret; - int len; - - if (count < CCID_HEADER_SIZE) - return -EINVAL; - - if (mutex_lock_interruptible(&dev->lock)) - return -ERESTARTSYS; - - if (!dev->dev) { - ret = -ENODEV; - goto out; - } - - ret = scr24x_wait_ready(dev); - if (ret < 0) - goto out; - len = CCID_HEADER_SIZE; - ret = read_chunk(dev, 0, len); - if (ret < 0) - goto out; - - len += le32_to_cpu(*(__le32 *)(&dev->buf[CCID_LENGTH_OFFSET])); - if (len > sizeof(dev->buf)) { - ret = -EIO; - goto out; - } - ret = read_chunk(dev, CCID_HEADER_SIZE, len); - if (ret < 0) - goto out; - - if (len < count) - count = len; - - if (copy_to_user(buf, dev->buf, count)) { - ret = -EFAULT; - goto out; - } - - ret = count; -out: - mutex_unlock(&dev->lock); - return ret; -} - -static ssize_t scr24x_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct scr24x_dev *dev = filp->private_data; - size_t i, y; - int ret; - - if (mutex_lock_interruptible(&dev->lock)) - return -ERESTARTSYS; - - if (!dev->dev) { - ret = -ENODEV; - goto out; - } - - if (count > sizeof(dev->buf)) { - ret = -EINVAL; - goto out; - } - - if (copy_from_user(dev->buf, buf, count)) { - ret = -EFAULT; - goto out; - } - - ret = scr24x_wait_ready(dev); - if (ret < 0) - goto out; - - iowrite8(CMD_START, dev->regs + SCR24X_CMD_STATUS); - ret = scr24x_wait_ready(dev); - if (ret < 0) - goto out; - - for (i = 0; i < count; i += 5) { - for (y = 0; y < 5 && i + y < count; y++) - iowrite8(dev->buf[i + y], dev->regs + SCR24X_DATA(y)); - - iowrite8(CMD_WRITE_BYTE, dev->regs + SCR24X_CMD_STATUS); - ret = scr24x_wait_ready(dev); - if (ret < 0) - goto out; - } - - ret = count; -out: - mutex_unlock(&dev->lock); - return ret; -} - -static const struct file_operations scr24x_fops = { - .owner = THIS_MODULE, - .read = scr24x_read, - .write = scr24x_write, - .open = scr24x_open, - .release = scr24x_release, - .llseek = no_llseek, -}; - -static int scr24x_config_check(struct pcmcia_device *link, void *priv_data) -{ - if (resource_size(link->resource[PCMCIA_IOPORT_0]) != 0x11) - return -ENODEV; - return pcmcia_request_io(link); -} - -static int scr24x_probe(struct pcmcia_device *link) -{ - struct scr24x_dev *dev; - int ret; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return -ENOMEM; - - dev->devno = find_first_zero_bit(scr24x_minors, SCR24X_DEVS); - if (dev->devno >= SCR24X_DEVS) { - ret = -EBUSY; - goto err; - } - - mutex_init(&dev->lock); - kref_init(&dev->refcnt); - - link->priv = dev; - link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO; - - ret = pcmcia_loop_config(link, scr24x_config_check, NULL); - if (ret < 0) - goto err; - - dev->dev = &link->dev; - dev->regs = devm_ioport_map(&link->dev, - link->resource[PCMCIA_IOPORT_0]->start, - resource_size(link->resource[PCMCIA_IOPORT_0])); - if (!dev->regs) { - ret = -EIO; - goto err; - } - - cdev_init(&dev->c_dev, &scr24x_fops); - dev->c_dev.owner = THIS_MODULE; - ret = cdev_add(&dev->c_dev, MKDEV(MAJOR(scr24x_devt), dev->devno), 1); - if (ret < 0) - goto err; - - ret = pcmcia_enable_device(link); - if (ret < 0) { - pcmcia_disable_device(link); - goto err; - } - - device_create(scr24x_class, NULL, MKDEV(MAJOR(scr24x_devt), dev->devno), - NULL, "scr24x%d", dev->devno); - - dev_info(&link->dev, "SCR24x Chip Card Interface\n"); - return 0; - -err: - if (dev->devno < SCR24X_DEVS) - clear_bit(dev->devno, scr24x_minors); - kfree (dev); - return ret; -} - -static void scr24x_remove(struct pcmcia_device *link) -{ - struct scr24x_dev *dev = (struct scr24x_dev *)link->priv; - - device_destroy(scr24x_class, MKDEV(MAJOR(scr24x_devt), dev->devno)); - mutex_lock(&dev->lock); - pcmcia_disable_device(link); - cdev_del(&dev->c_dev); - clear_bit(dev->devno, scr24x_minors); - dev->dev = NULL; - mutex_unlock(&dev->lock); - - kref_put(&dev->refcnt, scr24x_delete); -} - -static const struct pcmcia_device_id scr24x_ids[] = { - PCMCIA_DEVICE_PROD_ID12("HP", "PC Card Smart Card Reader", - 0x53cb94f9, 0xbfdf89a5), - PCMCIA_DEVICE_PROD_ID1("SCR241 PCMCIA", 0x6271efa3), - PCMCIA_DEVICE_PROD_ID1("SCR243 PCMCIA", 0x2054e8de), - PCMCIA_DEVICE_PROD_ID1("SCR24x PCMCIA", 0x54a33665), - PCMCIA_DEVICE_NULL -}; -MODULE_DEVICE_TABLE(pcmcia, scr24x_ids); - -static struct pcmcia_driver scr24x_driver = { - .owner = THIS_MODULE, - .name = "scr24x_cs", - .probe = scr24x_probe, - .remove = scr24x_remove, - .id_table = scr24x_ids, -}; - -static int __init scr24x_init(void) -{ - int ret; - - scr24x_class = class_create(THIS_MODULE, "scr24x"); - if (IS_ERR(scr24x_class)) - return PTR_ERR(scr24x_class); - - ret = alloc_chrdev_region(&scr24x_devt, 0, SCR24X_DEVS, "scr24x"); - if (ret < 0) { - class_destroy(scr24x_class); - return ret; - } - - ret = pcmcia_register_driver(&scr24x_driver); - if (ret < 0) { - unregister_chrdev_region(scr24x_devt, SCR24X_DEVS); - class_destroy(scr24x_class); - } - - return ret; -} - -static void __exit scr24x_exit(void) -{ - pcmcia_unregister_driver(&scr24x_driver); - unregister_chrdev_region(scr24x_devt, SCR24X_DEVS); - class_destroy(scr24x_class); -} - -module_init(scr24x_init); -module_exit(scr24x_exit); - -MODULE_AUTHOR("Lubomir Rintel"); -MODULE_DESCRIPTION("SCR24x PCMCIA Smart Card Reader Driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c deleted file mode 100644 index 6ddfeb2fe98f..000000000000 --- a/drivers/char/pcmcia/synclink_cs.c +++ /dev/null @@ -1,4290 +0,0 @@ -/* - * linux/drivers/char/pcmcia/synclink_cs.c - * - * $Id: synclink_cs.c,v 4.34 2005/09/08 13:20:54 paulkf Exp $ - * - * Device driver for Microgate SyncLink PC Card - * multiprotocol serial adapter. - * - * written by Paul Fulghum for Microgate Corporation - * paulkf@microgate.com - * - * Microgate and SyncLink are trademarks of Microgate Corporation - * - * This code is released under the GNU General Public License (GPL) - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES - * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, - * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES - * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR - * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) - * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, - * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED - * OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -#define VERSION(ver,rel,seq) (((ver)<<16) | ((rel)<<8) | (seq)) -#if defined(__i386__) -# define BREAKPOINT() asm(" int $3"); -#else -# define BREAKPOINT() { } -#endif - -#define MAX_DEVICE_COUNT 4 - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#if defined(CONFIG_HDLC) || (defined(CONFIG_HDLC_MODULE) && defined(CONFIG_SYNCLINK_CS_MODULE)) -#define SYNCLINK_GENERIC_HDLC 1 -#else -#define SYNCLINK_GENERIC_HDLC 0 -#endif - -#define GET_USER(error,value,addr) error = get_user(value,addr) -#define COPY_FROM_USER(error,dest,src,size) error = copy_from_user(dest,src,size) ? -EFAULT : 0 -#define PUT_USER(error,value,addr) error = put_user(value,addr) -#define COPY_TO_USER(error,dest,src,size) error = copy_to_user(dest,src,size) ? -EFAULT : 0 - -#include - -static MGSL_PARAMS default_params = { - MGSL_MODE_HDLC, /* unsigned long mode */ - 0, /* unsigned char loopback; */ - HDLC_FLAG_UNDERRUN_ABORT15, /* unsigned short flags; */ - HDLC_ENCODING_NRZI_SPACE, /* unsigned char encoding; */ - 0, /* unsigned long clock_speed; */ - 0xff, /* unsigned char addr_filter; */ - HDLC_CRC_16_CCITT, /* unsigned short crc_type; */ - HDLC_PREAMBLE_LENGTH_8BITS, /* unsigned char preamble_length; */ - HDLC_PREAMBLE_PATTERN_NONE, /* unsigned char preamble; */ - 9600, /* unsigned long data_rate; */ - 8, /* unsigned char data_bits; */ - 1, /* unsigned char stop_bits; */ - ASYNC_PARITY_NONE /* unsigned char parity; */ -}; - -typedef struct { - int count; - unsigned char status; - char data[1]; -} RXBUF; - -/* The queue of BH actions to be performed */ - -#define BH_RECEIVE 1 -#define BH_TRANSMIT 2 -#define BH_STATUS 4 - -#define IO_PIN_SHUTDOWN_LIMIT 100 - -#define RELEVANT_IFLAG(iflag) (iflag & (IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK)) - -struct _input_signal_events { - int ri_up; - int ri_down; - int dsr_up; - int dsr_down; - int dcd_up; - int dcd_down; - int cts_up; - int cts_down; -}; - - -/* - * Device instance data structure - */ - -typedef struct _mgslpc_info { - struct tty_port port; - void *if_ptr; /* General purpose pointer (used by SPPP) */ - int magic; - int line; - - struct mgsl_icount icount; - - int timeout; - int x_char; /* xon/xoff character */ - unsigned char read_status_mask; - unsigned char ignore_status_mask; - - unsigned char *tx_buf; - int tx_put; - int tx_get; - int tx_count; - - /* circular list of fixed length rx buffers */ - - unsigned char *rx_buf; /* memory allocated for all rx buffers */ - int rx_buf_total_size; /* size of memory allocated for rx buffers */ - int rx_put; /* index of next empty rx buffer */ - int rx_get; /* index of next full rx buffer */ - int rx_buf_size; /* size in bytes of single rx buffer */ - int rx_buf_count; /* total number of rx buffers */ - int rx_frame_count; /* number of full rx buffers */ - - wait_queue_head_t status_event_wait_q; - wait_queue_head_t event_wait_q; - struct timer_list tx_timer; /* HDLC transmit timeout timer */ - struct _mgslpc_info *next_device; /* device list link */ - - unsigned short imra_value; - unsigned short imrb_value; - unsigned char pim_value; - - spinlock_t lock; - struct work_struct task; /* task structure for scheduling bh */ - - u32 max_frame_size; - - u32 pending_bh; - - bool bh_running; - bool bh_requested; - - int dcd_chkcount; /* check counts to prevent */ - int cts_chkcount; /* too many IRQs if a signal */ - int dsr_chkcount; /* is floating */ - int ri_chkcount; - - bool rx_enabled; - bool rx_overflow; - - bool tx_enabled; - bool tx_active; - bool tx_aborting; - u32 idle_mode; - - int if_mode; /* serial interface selection (RS-232, v.35 etc) */ - - char device_name[25]; /* device instance name */ - - unsigned int io_base; /* base I/O address of adapter */ - unsigned int irq_level; - - MGSL_PARAMS params; /* communications parameters */ - - unsigned char serial_signals; /* current serial signal states */ - - bool irq_occurred; /* for diagnostics use */ - char testing_irq; - unsigned int init_error; /* startup error (DIAGS) */ - - char *flag_buf; - bool drop_rts_on_tx_done; - - struct _input_signal_events input_signal_events; - - /* PCMCIA support */ - struct pcmcia_device *p_dev; - int stop; - - /* SPPP/Cisco HDLC device parts */ - int netcount; - spinlock_t netlock; - -#if SYNCLINK_GENERIC_HDLC - struct net_device *netdev; -#endif - -} MGSLPC_INFO; - -#define MGSLPC_MAGIC 0x5402 - -/* - * The size of the serial xmit buffer is 1 page, or 4096 bytes - */ -#define TXBUFSIZE 4096 - - -#define CHA 0x00 /* channel A offset */ -#define CHB 0x40 /* channel B offset */ - -/* - * FIXME: PPC has PVR defined in asm/reg.h. For now we just undef it. - */ -#undef PVR - -#define RXFIFO 0 -#define TXFIFO 0 -#define STAR 0x20 -#define CMDR 0x20 -#define RSTA 0x21 -#define PRE 0x21 -#define MODE 0x22 -#define TIMR 0x23 -#define XAD1 0x24 -#define XAD2 0x25 -#define RAH1 0x26 -#define RAH2 0x27 -#define DAFO 0x27 -#define RAL1 0x28 -#define RFC 0x28 -#define RHCR 0x29 -#define RAL2 0x29 -#define RBCL 0x2a -#define XBCL 0x2a -#define RBCH 0x2b -#define XBCH 0x2b -#define CCR0 0x2c -#define CCR1 0x2d -#define CCR2 0x2e -#define CCR3 0x2f -#define VSTR 0x34 -#define BGR 0x34 -#define RLCR 0x35 -#define AML 0x36 -#define AMH 0x37 -#define GIS 0x38 -#define IVA 0x38 -#define IPC 0x39 -#define ISR 0x3a -#define IMR 0x3a -#define PVR 0x3c -#define PIS 0x3d -#define PIM 0x3d -#define PCR 0x3e -#define CCR4 0x3f - -// IMR/ISR - -#define IRQ_BREAK_ON BIT15 // rx break detected -#define IRQ_DATAOVERRUN BIT14 // receive data overflow -#define IRQ_ALLSENT BIT13 // all sent -#define IRQ_UNDERRUN BIT12 // transmit data underrun -#define IRQ_TIMER BIT11 // timer interrupt -#define IRQ_CTS BIT10 // CTS status change -#define IRQ_TXREPEAT BIT9 // tx message repeat -#define IRQ_TXFIFO BIT8 // transmit pool ready -#define IRQ_RXEOM BIT7 // receive message end -#define IRQ_EXITHUNT BIT6 // receive frame start -#define IRQ_RXTIME BIT6 // rx char timeout -#define IRQ_DCD BIT2 // carrier detect status change -#define IRQ_OVERRUN BIT1 // receive frame overflow -#define IRQ_RXFIFO BIT0 // receive pool full - -// STAR - -#define XFW BIT6 // transmit FIFO write enable -#define CEC BIT2 // command executing -#define CTS BIT1 // CTS state - -#define PVR_DTR BIT0 -#define PVR_DSR BIT1 -#define PVR_RI BIT2 -#define PVR_AUTOCTS BIT3 -#define PVR_RS232 0x20 /* 0010b */ -#define PVR_V35 0xe0 /* 1110b */ -#define PVR_RS422 0x40 /* 0100b */ - -/* Register access functions */ - -#define write_reg(info, reg, val) outb((val),(info)->io_base + (reg)) -#define read_reg(info, reg) inb((info)->io_base + (reg)) - -#define read_reg16(info, reg) inw((info)->io_base + (reg)) -#define write_reg16(info, reg, val) outw((val), (info)->io_base + (reg)) - -#define set_reg_bits(info, reg, mask) \ - write_reg(info, (reg), \ - (unsigned char) (read_reg(info, (reg)) | (mask))) -#define clear_reg_bits(info, reg, mask) \ - write_reg(info, (reg), \ - (unsigned char) (read_reg(info, (reg)) & ~(mask))) -/* - * interrupt enable/disable routines - */ -static void irq_disable(MGSLPC_INFO *info, unsigned char channel, unsigned short mask) -{ - if (channel == CHA) { - info->imra_value |= mask; - write_reg16(info, CHA + IMR, info->imra_value); - } else { - info->imrb_value |= mask; - write_reg16(info, CHB + IMR, info->imrb_value); - } -} -static void irq_enable(MGSLPC_INFO *info, unsigned char channel, unsigned short mask) -{ - if (channel == CHA) { - info->imra_value &= ~mask; - write_reg16(info, CHA + IMR, info->imra_value); - } else { - info->imrb_value &= ~mask; - write_reg16(info, CHB + IMR, info->imrb_value); - } -} - -#define port_irq_disable(info, mask) \ - { info->pim_value |= (mask); write_reg(info, PIM, info->pim_value); } - -#define port_irq_enable(info, mask) \ - { info->pim_value &= ~(mask); write_reg(info, PIM, info->pim_value); } - -static void rx_start(MGSLPC_INFO *info); -static void rx_stop(MGSLPC_INFO *info); - -static void tx_start(MGSLPC_INFO *info, struct tty_struct *tty); -static void tx_stop(MGSLPC_INFO *info); -static void tx_set_idle(MGSLPC_INFO *info); - -static void get_signals(MGSLPC_INFO *info); -static void set_signals(MGSLPC_INFO *info); - -static void reset_device(MGSLPC_INFO *info); - -static void hdlc_mode(MGSLPC_INFO *info); -static void async_mode(MGSLPC_INFO *info); - -static void tx_timeout(struct timer_list *t); - -static bool carrier_raised(struct tty_port *port); -static void dtr_rts(struct tty_port *port, bool active); - -#if SYNCLINK_GENERIC_HDLC -#define dev_to_port(D) (dev_to_hdlc(D)->priv) -static void hdlcdev_tx_done(MGSLPC_INFO *info); -static void hdlcdev_rx(MGSLPC_INFO *info, char *buf, int size); -static int hdlcdev_init(MGSLPC_INFO *info); -static void hdlcdev_exit(MGSLPC_INFO *info); -#endif - -static void trace_block(MGSLPC_INFO *info,const char* data, int count, int xmit); - -static bool register_test(MGSLPC_INFO *info); -static bool irq_test(MGSLPC_INFO *info); -static int adapter_test(MGSLPC_INFO *info); - -static int claim_resources(MGSLPC_INFO *info); -static void release_resources(MGSLPC_INFO *info); -static int mgslpc_add_device(MGSLPC_INFO *info); -static void mgslpc_remove_device(MGSLPC_INFO *info); - -static bool rx_get_frame(MGSLPC_INFO *info, struct tty_struct *tty); -static void rx_reset_buffers(MGSLPC_INFO *info); -static int rx_alloc_buffers(MGSLPC_INFO *info); -static void rx_free_buffers(MGSLPC_INFO *info); - -static irqreturn_t mgslpc_isr(int irq, void *dev_id); - -/* - * Bottom half interrupt handlers - */ -static void bh_handler(struct work_struct *work); -static void bh_transmit(MGSLPC_INFO *info, struct tty_struct *tty); -static void bh_status(MGSLPC_INFO *info); - -/* - * ioctl handlers - */ -static int tiocmget(struct tty_struct *tty); -static int tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear); -static int get_stats(MGSLPC_INFO *info, struct mgsl_icount __user *user_icount); -static int get_params(MGSLPC_INFO *info, MGSL_PARAMS __user *user_params); -static int set_params(MGSLPC_INFO *info, MGSL_PARAMS __user *new_params, struct tty_struct *tty); -static int get_txidle(MGSLPC_INFO *info, int __user *idle_mode); -static int set_txidle(MGSLPC_INFO *info, int idle_mode); -static int set_txenable(MGSLPC_INFO *info, int enable, struct tty_struct *tty); -static int tx_abort(MGSLPC_INFO *info); -static int set_rxenable(MGSLPC_INFO *info, int enable); -static int wait_events(MGSLPC_INFO *info, int __user *mask); - -static MGSLPC_INFO *mgslpc_device_list = NULL; -static int mgslpc_device_count = 0; - -/* - * Set this param to non-zero to load eax with the - * .text section address and breakpoint on module load. - * This is useful for use with gdb and add-symbol-file command. - */ -static bool break_on_load; - -/* - * Driver major number, defaults to zero to get auto - * assigned major number. May be forced as module parameter. - */ -static int ttymajor=0; - -static int debug_level = 0; -static int maxframe[MAX_DEVICE_COUNT] = {0,}; - -module_param(break_on_load, bool, 0); -module_param(ttymajor, int, 0); -module_param(debug_level, int, 0); -module_param_array(maxframe, int, NULL, 0); - -MODULE_LICENSE("GPL"); - -static char *driver_name = "SyncLink PC Card driver"; -static char *driver_version = "$Revision: 4.34 $"; - -static struct tty_driver *serial_driver; - -/* number of characters left in xmit buffer before we ask for more */ -#define WAKEUP_CHARS 256 - -static void mgslpc_change_params(MGSLPC_INFO *info, struct tty_struct *tty); -static void mgslpc_wait_until_sent(struct tty_struct *tty, int timeout); - -/* PCMCIA prototypes */ - -static int mgslpc_config(struct pcmcia_device *link); -static void mgslpc_release(u_long arg); -static void mgslpc_detach(struct pcmcia_device *p_dev); - -/* - * 1st function defined in .text section. Calling this function in - * init_module() followed by a breakpoint allows a remote debugger - * (gdb) to get the .text address for the add-symbol-file command. - * This allows remote debugging of dynamically loadable modules. - */ -static void* mgslpc_get_text_ptr(void) -{ - return mgslpc_get_text_ptr; -} - -/* - * line discipline callback wrappers - * - * The wrappers maintain line discipline references - * while calling into the line discipline. - * - * ldisc_receive_buf - pass receive data to line discipline - */ - -static void ldisc_receive_buf(struct tty_struct *tty, - const __u8 *data, char *flags, int count) -{ - struct tty_ldisc *ld; - if (!tty) - return; - ld = tty_ldisc_ref(tty); - if (ld) { - if (ld->ops->receive_buf) - ld->ops->receive_buf(tty, data, flags, count); - tty_ldisc_deref(ld); - } -} - -static const struct tty_port_operations mgslpc_port_ops = { - .carrier_raised = carrier_raised, - .dtr_rts = dtr_rts -}; - -static int mgslpc_probe(struct pcmcia_device *link) -{ - MGSLPC_INFO *info; - int ret; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("mgslpc_attach\n"); - - info = kzalloc(sizeof(MGSLPC_INFO), GFP_KERNEL); - if (!info) { - printk("Error can't allocate device instance data\n"); - return -ENOMEM; - } - - info->magic = MGSLPC_MAGIC; - tty_port_init(&info->port); - info->port.ops = &mgslpc_port_ops; - INIT_WORK(&info->task, bh_handler); - info->max_frame_size = 4096; - init_waitqueue_head(&info->status_event_wait_q); - init_waitqueue_head(&info->event_wait_q); - spin_lock_init(&info->lock); - spin_lock_init(&info->netlock); - memcpy(&info->params,&default_params,sizeof(MGSL_PARAMS)); - info->idle_mode = HDLC_TXIDLE_FLAGS; - info->imra_value = 0xffff; - info->imrb_value = 0xffff; - info->pim_value = 0xff; - - info->p_dev = link; - link->priv = info; - - /* Initialize the struct pcmcia_device structure */ - - ret = mgslpc_config(link); - if (ret != 0) - goto failed; - - ret = mgslpc_add_device(info); - if (ret != 0) - goto failed_release; - - return 0; - -failed_release: - mgslpc_release((u_long)link); -failed: - tty_port_destroy(&info->port); - kfree(info); - return ret; -} - -/* Card has been inserted. - */ - -static int mgslpc_ioprobe(struct pcmcia_device *p_dev, void *priv_data) -{ - return pcmcia_request_io(p_dev); -} - -static int mgslpc_config(struct pcmcia_device *link) -{ - MGSLPC_INFO *info = link->priv; - int ret; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("mgslpc_config(0x%p)\n", link); - - link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_IO; - - ret = pcmcia_loop_config(link, mgslpc_ioprobe, NULL); - if (ret != 0) - goto failed; - - link->config_index = 8; - link->config_regs = PRESENT_OPTION; - - ret = pcmcia_request_irq(link, mgslpc_isr); - if (ret) - goto failed; - ret = pcmcia_enable_device(link); - if (ret) - goto failed; - - info->io_base = link->resource[0]->start; - info->irq_level = link->irq; - return 0; - -failed: - mgslpc_release((u_long)link); - return -ENODEV; -} - -/* Card has been removed. - * Unregister device and release PCMCIA configuration. - * If device is open, postpone until it is closed. - */ -static void mgslpc_release(u_long arg) -{ - struct pcmcia_device *link = (struct pcmcia_device *)arg; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("mgslpc_release(0x%p)\n", link); - - pcmcia_disable_device(link); -} - -static void mgslpc_detach(struct pcmcia_device *link) -{ - if (debug_level >= DEBUG_LEVEL_INFO) - printk("mgslpc_detach(0x%p)\n", link); - - ((MGSLPC_INFO *)link->priv)->stop = 1; - mgslpc_release((u_long)link); - - mgslpc_remove_device((MGSLPC_INFO *)link->priv); -} - -static int mgslpc_suspend(struct pcmcia_device *link) -{ - MGSLPC_INFO *info = link->priv; - - info->stop = 1; - - return 0; -} - -static int mgslpc_resume(struct pcmcia_device *link) -{ - MGSLPC_INFO *info = link->priv; - - info->stop = 0; - - return 0; -} - - -static inline bool mgslpc_paranoia_check(MGSLPC_INFO *info, - char *name, const char *routine) -{ -#ifdef MGSLPC_PARANOIA_CHECK - static const char *badmagic = - "Warning: bad magic number for mgsl struct (%s) in %s\n"; - static const char *badinfo = - "Warning: null mgslpc_info for (%s) in %s\n"; - - if (!info) { - printk(badinfo, name, routine); - return true; - } - if (info->magic != MGSLPC_MAGIC) { - printk(badmagic, name, routine); - return true; - } -#else - if (!info) - return true; -#endif - return false; -} - - -#define CMD_RXFIFO BIT7 // release current rx FIFO -#define CMD_RXRESET BIT6 // receiver reset -#define CMD_RXFIFO_READ BIT5 -#define CMD_START_TIMER BIT4 -#define CMD_TXFIFO BIT3 // release current tx FIFO -#define CMD_TXEOM BIT1 // transmit end message -#define CMD_TXRESET BIT0 // transmit reset - -static bool wait_command_complete(MGSLPC_INFO *info, unsigned char channel) -{ - int i = 0; - /* wait for command completion */ - while (read_reg(info, (unsigned char)(channel+STAR)) & BIT2) { - udelay(1); - if (i++ == 1000) - return false; - } - return true; -} - -static void issue_command(MGSLPC_INFO *info, unsigned char channel, unsigned char cmd) -{ - wait_command_complete(info, channel); - write_reg(info, (unsigned char) (channel + CMDR), cmd); -} - -static void tx_pause(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (mgslpc_paranoia_check(info, tty->name, "tx_pause")) - return; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("tx_pause(%s)\n", info->device_name); - - spin_lock_irqsave(&info->lock, flags); - if (info->tx_enabled) - tx_stop(info); - spin_unlock_irqrestore(&info->lock, flags); -} - -static void tx_release(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (mgslpc_paranoia_check(info, tty->name, "tx_release")) - return; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("tx_release(%s)\n", info->device_name); - - spin_lock_irqsave(&info->lock, flags); - if (!info->tx_enabled) - tx_start(info, tty); - spin_unlock_irqrestore(&info->lock, flags); -} - -/* Return next bottom half action to perform. - * or 0 if nothing to do. - */ -static int bh_action(MGSLPC_INFO *info) -{ - unsigned long flags; - int rc = 0; - - spin_lock_irqsave(&info->lock, flags); - - if (info->pending_bh & BH_RECEIVE) { - info->pending_bh &= ~BH_RECEIVE; - rc = BH_RECEIVE; - } else if (info->pending_bh & BH_TRANSMIT) { - info->pending_bh &= ~BH_TRANSMIT; - rc = BH_TRANSMIT; - } else if (info->pending_bh & BH_STATUS) { - info->pending_bh &= ~BH_STATUS; - rc = BH_STATUS; - } - - if (!rc) { - /* Mark BH routine as complete */ - info->bh_running = false; - info->bh_requested = false; - } - - spin_unlock_irqrestore(&info->lock, flags); - - return rc; -} - -static void bh_handler(struct work_struct *work) -{ - MGSLPC_INFO *info = container_of(work, MGSLPC_INFO, task); - struct tty_struct *tty; - int action; - - if (debug_level >= DEBUG_LEVEL_BH) - printk("%s(%d):bh_handler(%s) entry\n", - __FILE__,__LINE__,info->device_name); - - info->bh_running = true; - tty = tty_port_tty_get(&info->port); - - while((action = bh_action(info)) != 0) { - - /* Process work item */ - if (debug_level >= DEBUG_LEVEL_BH) - printk("%s(%d):bh_handler() work item action=%d\n", - __FILE__,__LINE__,action); - - switch (action) { - - case BH_RECEIVE: - while(rx_get_frame(info, tty)); - break; - case BH_TRANSMIT: - bh_transmit(info, tty); - break; - case BH_STATUS: - bh_status(info); - break; - default: - /* unknown work item ID */ - printk("Unknown work item ID=%08X!\n", action); - break; - } - } - - tty_kref_put(tty); - if (debug_level >= DEBUG_LEVEL_BH) - printk("%s(%d):bh_handler(%s) exit\n", - __FILE__,__LINE__,info->device_name); -} - -static void bh_transmit(MGSLPC_INFO *info, struct tty_struct *tty) -{ - if (debug_level >= DEBUG_LEVEL_BH) - printk("bh_transmit() entry on %s\n", info->device_name); - - if (tty) - tty_wakeup(tty); -} - -static void bh_status(MGSLPC_INFO *info) -{ - info->ri_chkcount = 0; - info->dsr_chkcount = 0; - info->dcd_chkcount = 0; - info->cts_chkcount = 0; -} - -/* eom: non-zero = end of frame */ -static void rx_ready_hdlc(MGSLPC_INFO *info, int eom) -{ - unsigned char data[2]; - unsigned char fifo_count, read_count, i; - RXBUF *buf = (RXBUF*)(info->rx_buf + (info->rx_put * info->rx_buf_size)); - - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):rx_ready_hdlc(eom=%d)\n", __FILE__, __LINE__, eom); - - if (!info->rx_enabled) - return; - - if (info->rx_frame_count >= info->rx_buf_count) { - /* no more free buffers */ - issue_command(info, CHA, CMD_RXRESET); - info->pending_bh |= BH_RECEIVE; - info->rx_overflow = true; - info->icount.buf_overrun++; - return; - } - - if (eom) { - /* end of frame, get FIFO count from RBCL register */ - fifo_count = (unsigned char)(read_reg(info, CHA+RBCL) & 0x1f); - if (fifo_count == 0) - fifo_count = 32; - } else - fifo_count = 32; - - do { - if (fifo_count == 1) { - read_count = 1; - data[0] = read_reg(info, CHA + RXFIFO); - } else { - read_count = 2; - *((unsigned short *) data) = read_reg16(info, CHA + RXFIFO); - } - fifo_count -= read_count; - if (!fifo_count && eom) - buf->status = data[--read_count]; - - for (i = 0; i < read_count; i++) { - if (buf->count >= info->max_frame_size) { - /* frame too large, reset receiver and reset current buffer */ - issue_command(info, CHA, CMD_RXRESET); - buf->count = 0; - return; - } - *(buf->data + buf->count) = data[i]; - buf->count++; - } - } while (fifo_count); - - if (eom) { - info->pending_bh |= BH_RECEIVE; - info->rx_frame_count++; - info->rx_put++; - if (info->rx_put >= info->rx_buf_count) - info->rx_put = 0; - } - issue_command(info, CHA, CMD_RXFIFO); -} - -static void rx_ready_async(MGSLPC_INFO *info, int tcd) -{ - struct tty_port *port = &info->port; - unsigned char data, status, flag; - int fifo_count; - int work = 0; - struct mgsl_icount *icount = &info->icount; - - if (tcd) { - /* early termination, get FIFO count from RBCL register */ - fifo_count = (unsigned char)(read_reg(info, CHA+RBCL) & 0x1f); - - /* Zero fifo count could mean 0 or 32 bytes available. - * If BIT5 of STAR is set then at least 1 byte is available. - */ - if (!fifo_count && (read_reg(info,CHA+STAR) & BIT5)) - fifo_count = 32; - } else - fifo_count = 32; - - tty_buffer_request_room(port, fifo_count); - /* Flush received async data to receive data buffer. */ - while (fifo_count) { - data = read_reg(info, CHA + RXFIFO); - status = read_reg(info, CHA + RXFIFO); - fifo_count -= 2; - - icount->rx++; - flag = TTY_NORMAL; - - // if no frameing/crc error then save data - // BIT7:parity error - // BIT6:framing error - - if (status & (BIT7 | BIT6)) { - if (status & BIT7) - icount->parity++; - else - icount->frame++; - - /* discard char if tty control flags say so */ - if (status & info->ignore_status_mask) - continue; - - status &= info->read_status_mask; - - if (status & BIT7) - flag = TTY_PARITY; - else if (status & BIT6) - flag = TTY_FRAME; - } - work += tty_insert_flip_char(port, data, flag); - } - issue_command(info, CHA, CMD_RXFIFO); - - if (debug_level >= DEBUG_LEVEL_ISR) { - printk("%s(%d):rx_ready_async", - __FILE__,__LINE__); - printk("%s(%d):rx=%d brk=%d parity=%d frame=%d overrun=%d\n", - __FILE__,__LINE__,icount->rx,icount->brk, - icount->parity,icount->frame,icount->overrun); - } - - if (work) - tty_flip_buffer_push(port); -} - - -static void tx_done(MGSLPC_INFO *info, struct tty_struct *tty) -{ - if (!info->tx_active) - return; - - info->tx_active = false; - info->tx_aborting = false; - - if (info->params.mode == MGSL_MODE_ASYNC) - return; - - info->tx_count = info->tx_put = info->tx_get = 0; - del_timer(&info->tx_timer); - - if (info->drop_rts_on_tx_done) { - get_signals(info); - if (info->serial_signals & SerialSignal_RTS) { - info->serial_signals &= ~SerialSignal_RTS; - set_signals(info); - } - info->drop_rts_on_tx_done = false; - } - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_tx_done(info); - else -#endif - { - if (tty && (tty->flow.stopped || tty->hw_stopped)) { - tx_stop(info); - return; - } - info->pending_bh |= BH_TRANSMIT; - } -} - -static void tx_ready(MGSLPC_INFO *info, struct tty_struct *tty) -{ - unsigned char fifo_count = 32; - int c; - - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):tx_ready(%s)\n", __FILE__, __LINE__, info->device_name); - - if (info->params.mode == MGSL_MODE_HDLC) { - if (!info->tx_active) - return; - } else { - if (tty && (tty->flow.stopped || tty->hw_stopped)) { - tx_stop(info); - return; - } - if (!info->tx_count) - info->tx_active = false; - } - - if (!info->tx_count) - return; - - while (info->tx_count && fifo_count) { - c = min(2, min_t(int, fifo_count, min(info->tx_count, TXBUFSIZE - info->tx_get))); - - if (c == 1) { - write_reg(info, CHA + TXFIFO, *(info->tx_buf + info->tx_get)); - } else { - write_reg16(info, CHA + TXFIFO, - *((unsigned short*)(info->tx_buf + info->tx_get))); - } - info->tx_count -= c; - info->tx_get = (info->tx_get + c) & (TXBUFSIZE - 1); - fifo_count -= c; - } - - if (info->params.mode == MGSL_MODE_ASYNC) { - if (info->tx_count < WAKEUP_CHARS) - info->pending_bh |= BH_TRANSMIT; - issue_command(info, CHA, CMD_TXFIFO); - } else { - if (info->tx_count) - issue_command(info, CHA, CMD_TXFIFO); - else - issue_command(info, CHA, CMD_TXFIFO + CMD_TXEOM); - } -} - -static void cts_change(MGSLPC_INFO *info, struct tty_struct *tty) -{ - get_signals(info); - if ((info->cts_chkcount)++ >= IO_PIN_SHUTDOWN_LIMIT) - irq_disable(info, CHB, IRQ_CTS); - info->icount.cts++; - if (info->serial_signals & SerialSignal_CTS) - info->input_signal_events.cts_up++; - else - info->input_signal_events.cts_down++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - - if (tty && tty_port_cts_enabled(&info->port)) { - if (tty->hw_stopped) { - if (info->serial_signals & SerialSignal_CTS) { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("CTS tx start..."); - tty->hw_stopped = 0; - tx_start(info, tty); - info->pending_bh |= BH_TRANSMIT; - return; - } - } else { - if (!(info->serial_signals & SerialSignal_CTS)) { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("CTS tx stop..."); - tty->hw_stopped = 1; - tx_stop(info); - } - } - } - info->pending_bh |= BH_STATUS; -} - -static void dcd_change(MGSLPC_INFO *info, struct tty_struct *tty) -{ - get_signals(info); - if ((info->dcd_chkcount)++ >= IO_PIN_SHUTDOWN_LIMIT) - irq_disable(info, CHB, IRQ_DCD); - info->icount.dcd++; - if (info->serial_signals & SerialSignal_DCD) { - info->input_signal_events.dcd_up++; - } - else - info->input_signal_events.dcd_down++; -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) { - if (info->serial_signals & SerialSignal_DCD) - netif_carrier_on(info->netdev); - else - netif_carrier_off(info->netdev); - } -#endif - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - - if (tty_port_check_carrier(&info->port)) { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s CD now %s...", info->device_name, - (info->serial_signals & SerialSignal_DCD) ? "on" : "off"); - if (info->serial_signals & SerialSignal_DCD) - wake_up_interruptible(&info->port.open_wait); - else { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("doing serial hangup..."); - if (tty) - tty_hangup(tty); - } - } - info->pending_bh |= BH_STATUS; -} - -static void dsr_change(MGSLPC_INFO *info) -{ - get_signals(info); - if ((info->dsr_chkcount)++ >= IO_PIN_SHUTDOWN_LIMIT) - port_irq_disable(info, PVR_DSR); - info->icount.dsr++; - if (info->serial_signals & SerialSignal_DSR) - info->input_signal_events.dsr_up++; - else - info->input_signal_events.dsr_down++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; -} - -static void ri_change(MGSLPC_INFO *info) -{ - get_signals(info); - if ((info->ri_chkcount)++ >= IO_PIN_SHUTDOWN_LIMIT) - port_irq_disable(info, PVR_RI); - info->icount.rng++; - if (info->serial_signals & SerialSignal_RI) - info->input_signal_events.ri_up++; - else - info->input_signal_events.ri_down++; - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - info->pending_bh |= BH_STATUS; -} - -/* Interrupt service routine entry point. - * - * Arguments: - * - * irq interrupt number that caused interrupt - * dev_id device ID supplied during interrupt registration - */ -static irqreturn_t mgslpc_isr(int dummy, void *dev_id) -{ - MGSLPC_INFO *info = dev_id; - struct tty_struct *tty; - unsigned short isr; - unsigned char gis, pis; - int count=0; - - if (debug_level >= DEBUG_LEVEL_ISR) - printk("mgslpc_isr(%d) entry.\n", info->irq_level); - - if (!(info->p_dev->_locked)) - return IRQ_HANDLED; - - tty = tty_port_tty_get(&info->port); - - spin_lock(&info->lock); - - while ((gis = read_reg(info, CHA + GIS))) { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("mgslpc_isr %s gis=%04X\n", info->device_name,gis); - - if ((gis & 0x70) || count > 1000) { - printk("synclink_cs:hardware failed or ejected\n"); - break; - } - count++; - - if (gis & (BIT1 | BIT0)) { - isr = read_reg16(info, CHB + ISR); - if (isr & IRQ_DCD) - dcd_change(info, tty); - if (isr & IRQ_CTS) - cts_change(info, tty); - } - if (gis & (BIT3 | BIT2)) - { - isr = read_reg16(info, CHA + ISR); - if (isr & IRQ_TIMER) { - info->irq_occurred = true; - irq_disable(info, CHA, IRQ_TIMER); - } - - /* receive IRQs */ - if (isr & IRQ_EXITHUNT) { - info->icount.exithunt++; - wake_up_interruptible(&info->event_wait_q); - } - if (isr & IRQ_BREAK_ON) { - info->icount.brk++; - if (info->port.flags & ASYNC_SAK) - do_SAK(tty); - } - if (isr & IRQ_RXTIME) { - issue_command(info, CHA, CMD_RXFIFO_READ); - } - if (isr & (IRQ_RXEOM | IRQ_RXFIFO)) { - if (info->params.mode == MGSL_MODE_HDLC) - rx_ready_hdlc(info, isr & IRQ_RXEOM); - else - rx_ready_async(info, isr & IRQ_RXEOM); - } - - /* transmit IRQs */ - if (isr & IRQ_UNDERRUN) { - if (info->tx_aborting) - info->icount.txabort++; - else - info->icount.txunder++; - tx_done(info, tty); - } - else if (isr & IRQ_ALLSENT) { - info->icount.txok++; - tx_done(info, tty); - } - else if (isr & IRQ_TXFIFO) - tx_ready(info, tty); - } - if (gis & BIT7) { - pis = read_reg(info, CHA + PIS); - if (pis & BIT1) - dsr_change(info); - if (pis & BIT2) - ri_change(info); - } - } - - /* Request bottom half processing if there's something - * for it to do and the bh is not already running - */ - - if (info->pending_bh && !info->bh_running && !info->bh_requested) { - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):%s queueing bh task.\n", - __FILE__,__LINE__,info->device_name); - schedule_work(&info->task); - info->bh_requested = true; - } - - spin_unlock(&info->lock); - tty_kref_put(tty); - - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):mgslpc_isr(%d)exit.\n", - __FILE__, __LINE__, info->irq_level); - - return IRQ_HANDLED; -} - -/* Initialize and start device. - */ -static int startup(MGSLPC_INFO * info, struct tty_struct *tty) -{ - int retval = 0; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):startup(%s)\n", __FILE__, __LINE__, info->device_name); - - if (tty_port_initialized(&info->port)) - return 0; - - if (!info->tx_buf) { - /* allocate a page of memory for a transmit buffer */ - info->tx_buf = (unsigned char *)get_zeroed_page(GFP_KERNEL); - if (!info->tx_buf) { - printk(KERN_ERR"%s(%d):%s can't allocate transmit buffer\n", - __FILE__, __LINE__, info->device_name); - return -ENOMEM; - } - } - - info->pending_bh = 0; - - memset(&info->icount, 0, sizeof(info->icount)); - - timer_setup(&info->tx_timer, tx_timeout, 0); - - /* Allocate and claim adapter resources */ - retval = claim_resources(info); - - /* perform existence check and diagnostics */ - if (!retval) - retval = adapter_test(info); - - if (retval) { - if (capable(CAP_SYS_ADMIN) && tty) - set_bit(TTY_IO_ERROR, &tty->flags); - release_resources(info); - return retval; - } - - /* program hardware for current parameters */ - mgslpc_change_params(info, tty); - - if (tty) - clear_bit(TTY_IO_ERROR, &tty->flags); - - tty_port_set_initialized(&info->port, true); - - return 0; -} - -/* Called by mgslpc_close() and mgslpc_hangup() to shutdown hardware - */ -static void shutdown(MGSLPC_INFO * info, struct tty_struct *tty) -{ - unsigned long flags; - - if (!tty_port_initialized(&info->port)) - return; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_shutdown(%s)\n", - __FILE__, __LINE__, info->device_name); - - /* clear status wait queue because status changes */ - /* can't happen after shutting down the hardware */ - wake_up_interruptible(&info->status_event_wait_q); - wake_up_interruptible(&info->event_wait_q); - - del_timer_sync(&info->tx_timer); - - if (info->tx_buf) { - free_page((unsigned long) info->tx_buf); - info->tx_buf = NULL; - } - - spin_lock_irqsave(&info->lock, flags); - - rx_stop(info); - tx_stop(info); - - /* TODO:disable interrupts instead of reset to preserve signal states */ - reset_device(info); - - if (!tty || C_HUPCL(tty)) { - info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); - } - - spin_unlock_irqrestore(&info->lock, flags); - - release_resources(info); - - if (tty) - set_bit(TTY_IO_ERROR, &tty->flags); - - tty_port_set_initialized(&info->port, false); -} - -static void mgslpc_program_hw(MGSLPC_INFO *info, struct tty_struct *tty) -{ - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - - rx_stop(info); - tx_stop(info); - info->tx_count = info->tx_put = info->tx_get = 0; - - if (info->params.mode == MGSL_MODE_HDLC || info->netcount) - hdlc_mode(info); - else - async_mode(info); - - set_signals(info); - - info->dcd_chkcount = 0; - info->cts_chkcount = 0; - info->ri_chkcount = 0; - info->dsr_chkcount = 0; - - irq_enable(info, CHB, IRQ_DCD | IRQ_CTS); - port_irq_enable(info, (unsigned char) PVR_DSR | PVR_RI); - get_signals(info); - - if (info->netcount || (tty && C_CREAD(tty))) - rx_start(info); - - spin_unlock_irqrestore(&info->lock, flags); -} - -/* Reconfigure adapter based on new parameters - */ -static void mgslpc_change_params(MGSLPC_INFO *info, struct tty_struct *tty) -{ - unsigned cflag; - int bits_per_char; - - if (!tty) - return; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_change_params(%s)\n", - __FILE__, __LINE__, info->device_name); - - cflag = tty->termios.c_cflag; - - /* if B0 rate (hangup) specified then negate RTS and DTR */ - /* otherwise assert RTS and DTR */ - if (cflag & CBAUD) - info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR; - else - info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - - /* byte size and parity */ - if ((cflag & CSIZE) != CS8) { - cflag &= ~CSIZE; - cflag |= CS7; - tty->termios.c_cflag = cflag; - } - info->params.data_bits = tty_get_char_size(cflag); - - if (cflag & CSTOPB) - info->params.stop_bits = 2; - else - info->params.stop_bits = 1; - - info->params.parity = ASYNC_PARITY_NONE; - if (cflag & PARENB) { - if (cflag & PARODD) - info->params.parity = ASYNC_PARITY_ODD; - else - info->params.parity = ASYNC_PARITY_EVEN; - if (cflag & CMSPAR) - info->params.parity = ASYNC_PARITY_SPACE; - } - - /* calculate number of jiffies to transmit a full - * FIFO (32 bytes) at specified data rate - */ - bits_per_char = info->params.data_bits + - info->params.stop_bits + 1; - - /* if port data rate is set to 460800 or less then - * allow tty settings to override, otherwise keep the - * current data rate. - */ - if (info->params.data_rate <= 460800) { - info->params.data_rate = tty_get_baud_rate(tty); - } - - if (info->params.data_rate) { - info->timeout = (32*HZ*bits_per_char) / - info->params.data_rate; - } - info->timeout += HZ/50; /* Add .02 seconds of slop */ - - tty_port_set_cts_flow(&info->port, cflag & CRTSCTS); - tty_port_set_check_carrier(&info->port, ~cflag & CLOCAL); - - /* process tty input control flags */ - - info->read_status_mask = 0; - if (I_INPCK(tty)) - info->read_status_mask |= BIT7 | BIT6; - if (I_IGNPAR(tty)) - info->ignore_status_mask |= BIT7 | BIT6; - - mgslpc_program_hw(info, tty); -} - -/* Add a character to the transmit buffer - */ -static int mgslpc_put_char(struct tty_struct *tty, unsigned char ch) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) { - printk("%s(%d):mgslpc_put_char(%d) on %s\n", - __FILE__, __LINE__, ch, info->device_name); - } - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_put_char")) - return 0; - - if (!info->tx_buf) - return 0; - - spin_lock_irqsave(&info->lock, flags); - - if (info->params.mode == MGSL_MODE_ASYNC || !info->tx_active) { - if (info->tx_count < TXBUFSIZE - 1) { - info->tx_buf[info->tx_put++] = ch; - info->tx_put &= TXBUFSIZE-1; - info->tx_count++; - } - } - - spin_unlock_irqrestore(&info->lock, flags); - return 1; -} - -/* Enable transmitter so remaining characters in the - * transmit buffer are sent. - */ -static void mgslpc_flush_chars(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_flush_chars() entry on %s tx_count=%d\n", - __FILE__, __LINE__, info->device_name, info->tx_count); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_flush_chars")) - return; - - if (info->tx_count <= 0 || tty->flow.stopped || - tty->hw_stopped || !info->tx_buf) - return; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_flush_chars() entry on %s starting transmitter\n", - __FILE__, __LINE__, info->device_name); - - spin_lock_irqsave(&info->lock, flags); - if (!info->tx_active) - tx_start(info, tty); - spin_unlock_irqrestore(&info->lock, flags); -} - -/* Send a block of data - * - * Arguments: - * - * tty pointer to tty information structure - * buf pointer to buffer containing send data - * count size of send data in bytes - * - * Returns: number of characters written - */ -static int mgslpc_write(struct tty_struct * tty, - const unsigned char *buf, int count) -{ - int c, ret = 0; - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_write(%s) count=%d\n", - __FILE__, __LINE__, info->device_name, count); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_write") || - !info->tx_buf) - goto cleanup; - - if (info->params.mode == MGSL_MODE_HDLC) { - if (count > TXBUFSIZE) { - ret = -EIO; - goto cleanup; - } - if (info->tx_active) - goto cleanup; - else if (info->tx_count) - goto start; - } - - for (;;) { - c = min(count, - min(TXBUFSIZE - info->tx_count - 1, - TXBUFSIZE - info->tx_put)); - if (c <= 0) - break; - - memcpy(info->tx_buf + info->tx_put, buf, c); - - spin_lock_irqsave(&info->lock, flags); - info->tx_put = (info->tx_put + c) & (TXBUFSIZE-1); - info->tx_count += c; - spin_unlock_irqrestore(&info->lock, flags); - - buf += c; - count -= c; - ret += c; - } -start: - if (info->tx_count && !tty->flow.stopped && !tty->hw_stopped) { - spin_lock_irqsave(&info->lock, flags); - if (!info->tx_active) - tx_start(info, tty); - spin_unlock_irqrestore(&info->lock, flags); - } -cleanup: - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_write(%s) returning=%d\n", - __FILE__, __LINE__, info->device_name, ret); - return ret; -} - -/* Return the count of free bytes in transmit buffer - */ -static unsigned int mgslpc_write_room(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - int ret; - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_write_room")) - return 0; - - if (info->params.mode == MGSL_MODE_HDLC) { - /* HDLC (frame oriented) mode */ - if (info->tx_active) - return 0; - else - return HDLC_MAX_FRAME_SIZE; - } else { - ret = TXBUFSIZE - info->tx_count - 1; - if (ret < 0) - ret = 0; - } - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_write_room(%s)=%d\n", - __FILE__, __LINE__, info->device_name, ret); - return ret; -} - -/* Return the count of bytes in transmit buffer - */ -static unsigned int mgslpc_chars_in_buffer(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned int rc; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_chars_in_buffer(%s)\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_chars_in_buffer")) - return 0; - - if (info->params.mode == MGSL_MODE_HDLC) - rc = info->tx_active ? info->max_frame_size : 0; - else - rc = info->tx_count; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_chars_in_buffer(%s)=%u\n", - __FILE__, __LINE__, info->device_name, rc); - - return rc; -} - -/* Discard all data in the send buffer - */ -static void mgslpc_flush_buffer(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_flush_buffer(%s) entry\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_flush_buffer")) - return; - - spin_lock_irqsave(&info->lock, flags); - info->tx_count = info->tx_put = info->tx_get = 0; - del_timer(&info->tx_timer); - spin_unlock_irqrestore(&info->lock, flags); - - wake_up_interruptible(&tty->write_wait); - tty_wakeup(tty); -} - -/* Send a high-priority XON/XOFF character - */ -static void mgslpc_send_xchar(struct tty_struct *tty, char ch) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_send_xchar(%s,%d)\n", - __FILE__, __LINE__, info->device_name, ch); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_send_xchar")) - return; - - info->x_char = ch; - if (ch) { - spin_lock_irqsave(&info->lock, flags); - if (!info->tx_enabled) - tx_start(info, tty); - spin_unlock_irqrestore(&info->lock, flags); - } -} - -/* Signal remote device to throttle send data (our receive data) - */ -static void mgslpc_throttle(struct tty_struct * tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_throttle(%s) entry\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_throttle")) - return; - - if (I_IXOFF(tty)) - mgslpc_send_xchar(tty, STOP_CHAR(tty)); - - if (C_CRTSCTS(tty)) { - spin_lock_irqsave(&info->lock, flags); - info->serial_signals &= ~SerialSignal_RTS; - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - } -} - -/* Signal remote device to stop throttling send data (our receive data) - */ -static void mgslpc_unthrottle(struct tty_struct * tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_unthrottle(%s) entry\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_unthrottle")) - return; - - if (I_IXOFF(tty)) { - if (info->x_char) - info->x_char = 0; - else - mgslpc_send_xchar(tty, START_CHAR(tty)); - } - - if (C_CRTSCTS(tty)) { - spin_lock_irqsave(&info->lock, flags); - info->serial_signals |= SerialSignal_RTS; - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - } -} - -/* get the current serial statistics - */ -static int get_stats(MGSLPC_INFO * info, struct mgsl_icount __user *user_icount) -{ - int err; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("get_params(%s)\n", info->device_name); - if (!user_icount) { - memset(&info->icount, 0, sizeof(info->icount)); - } else { - COPY_TO_USER(err, user_icount, &info->icount, sizeof(struct mgsl_icount)); - if (err) - return -EFAULT; - } - return 0; -} - -/* get the current serial parameters - */ -static int get_params(MGSLPC_INFO * info, MGSL_PARAMS __user *user_params) -{ - int err; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("get_params(%s)\n", info->device_name); - COPY_TO_USER(err,user_params, &info->params, sizeof(MGSL_PARAMS)); - if (err) - return -EFAULT; - return 0; -} - -/* set the serial parameters - * - * Arguments: - * - * info pointer to device instance data - * new_params user buffer containing new serial params - * - * Returns: 0 if success, otherwise error code - */ -static int set_params(MGSLPC_INFO * info, MGSL_PARAMS __user *new_params, struct tty_struct *tty) -{ - unsigned long flags; - MGSL_PARAMS tmp_params; - int err; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):set_params %s\n", __FILE__,__LINE__, - info->device_name); - COPY_FROM_USER(err,&tmp_params, new_params, sizeof(MGSL_PARAMS)); - if (err) { - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):set_params(%s) user buffer copy failed\n", - __FILE__, __LINE__, info->device_name); - return -EFAULT; - } - - spin_lock_irqsave(&info->lock, flags); - memcpy(&info->params,&tmp_params,sizeof(MGSL_PARAMS)); - spin_unlock_irqrestore(&info->lock, flags); - - mgslpc_change_params(info, tty); - - return 0; -} - -static int get_txidle(MGSLPC_INFO * info, int __user *idle_mode) -{ - int err; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("get_txidle(%s)=%d\n", info->device_name, info->idle_mode); - COPY_TO_USER(err,idle_mode, &info->idle_mode, sizeof(int)); - if (err) - return -EFAULT; - return 0; -} - -static int set_txidle(MGSLPC_INFO * info, int idle_mode) -{ - unsigned long flags; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("set_txidle(%s,%d)\n", info->device_name, idle_mode); - spin_lock_irqsave(&info->lock, flags); - info->idle_mode = idle_mode; - tx_set_idle(info); - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int get_interface(MGSLPC_INFO * info, int __user *if_mode) -{ - int err; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("get_interface(%s)=%d\n", info->device_name, info->if_mode); - COPY_TO_USER(err,if_mode, &info->if_mode, sizeof(int)); - if (err) - return -EFAULT; - return 0; -} - -static int set_interface(MGSLPC_INFO * info, int if_mode) -{ - unsigned long flags; - unsigned char val; - if (debug_level >= DEBUG_LEVEL_INFO) - printk("set_interface(%s,%d)\n", info->device_name, if_mode); - spin_lock_irqsave(&info->lock, flags); - info->if_mode = if_mode; - - val = read_reg(info, PVR) & 0x0f; - switch (info->if_mode) - { - case MGSL_INTERFACE_RS232: val |= PVR_RS232; break; - case MGSL_INTERFACE_V35: val |= PVR_V35; break; - case MGSL_INTERFACE_RS422: val |= PVR_RS422; break; - } - write_reg(info, PVR, val); - - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int set_txenable(MGSLPC_INFO * info, int enable, struct tty_struct *tty) -{ - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("set_txenable(%s,%d)\n", info->device_name, enable); - - spin_lock_irqsave(&info->lock, flags); - if (enable) { - if (!info->tx_enabled) - tx_start(info, tty); - } else { - if (info->tx_enabled) - tx_stop(info); - } - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int tx_abort(MGSLPC_INFO * info) -{ - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("tx_abort(%s)\n", info->device_name); - - spin_lock_irqsave(&info->lock, flags); - if (info->tx_active && info->tx_count && - info->params.mode == MGSL_MODE_HDLC) { - /* clear data count so FIFO is not filled on next IRQ. - * This results in underrun and abort transmission. - */ - info->tx_count = info->tx_put = info->tx_get = 0; - info->tx_aborting = true; - } - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int set_rxenable(MGSLPC_INFO * info, int enable) -{ - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("set_rxenable(%s,%d)\n", info->device_name, enable); - - spin_lock_irqsave(&info->lock, flags); - if (enable) { - if (!info->rx_enabled) - rx_start(info); - } else { - if (info->rx_enabled) - rx_stop(info); - } - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -/* wait for specified event to occur - * - * Arguments: info pointer to device instance data - * mask pointer to bitmask of events to wait for - * Return Value: 0 if successful and bit mask updated with - * of events triggerred, - * otherwise error code - */ -static int wait_events(MGSLPC_INFO * info, int __user *mask_ptr) -{ - unsigned long flags; - int s; - int rc=0; - struct mgsl_icount cprev, cnow; - int events; - int mask; - struct _input_signal_events oldsigs, newsigs; - DECLARE_WAITQUEUE(wait, current); - - COPY_FROM_USER(rc,&mask, mask_ptr, sizeof(int)); - if (rc) - return -EFAULT; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("wait_events(%s,%d)\n", info->device_name, mask); - - spin_lock_irqsave(&info->lock, flags); - - /* return immediately if state matches requested events */ - get_signals(info); - s = info->serial_signals; - events = mask & - ( ((s & SerialSignal_DSR) ? MgslEvent_DsrActive:MgslEvent_DsrInactive) + - ((s & SerialSignal_DCD) ? MgslEvent_DcdActive:MgslEvent_DcdInactive) + - ((s & SerialSignal_CTS) ? MgslEvent_CtsActive:MgslEvent_CtsInactive) + - ((s & SerialSignal_RI) ? MgslEvent_RiActive :MgslEvent_RiInactive) ); - if (events) { - spin_unlock_irqrestore(&info->lock, flags); - goto exit; - } - - /* save current irq counts */ - cprev = info->icount; - oldsigs = info->input_signal_events; - - if ((info->params.mode == MGSL_MODE_HDLC) && - (mask & MgslEvent_ExitHuntMode)) - irq_enable(info, CHA, IRQ_EXITHUNT); - - set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&info->event_wait_q, &wait); - - spin_unlock_irqrestore(&info->lock, flags); - - - for(;;) { - schedule(); - if (signal_pending(current)) { - rc = -ERESTARTSYS; - break; - } - - /* get current irq counts */ - spin_lock_irqsave(&info->lock, flags); - cnow = info->icount; - newsigs = info->input_signal_events; - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock, flags); - - /* if no change, wait aborted for some reason */ - if (newsigs.dsr_up == oldsigs.dsr_up && - newsigs.dsr_down == oldsigs.dsr_down && - newsigs.dcd_up == oldsigs.dcd_up && - newsigs.dcd_down == oldsigs.dcd_down && - newsigs.cts_up == oldsigs.cts_up && - newsigs.cts_down == oldsigs.cts_down && - newsigs.ri_up == oldsigs.ri_up && - newsigs.ri_down == oldsigs.ri_down && - cnow.exithunt == cprev.exithunt && - cnow.rxidle == cprev.rxidle) { - rc = -EIO; - break; - } - - events = mask & - ( (newsigs.dsr_up != oldsigs.dsr_up ? MgslEvent_DsrActive:0) + - (newsigs.dsr_down != oldsigs.dsr_down ? MgslEvent_DsrInactive:0) + - (newsigs.dcd_up != oldsigs.dcd_up ? MgslEvent_DcdActive:0) + - (newsigs.dcd_down != oldsigs.dcd_down ? MgslEvent_DcdInactive:0) + - (newsigs.cts_up != oldsigs.cts_up ? MgslEvent_CtsActive:0) + - (newsigs.cts_down != oldsigs.cts_down ? MgslEvent_CtsInactive:0) + - (newsigs.ri_up != oldsigs.ri_up ? MgslEvent_RiActive:0) + - (newsigs.ri_down != oldsigs.ri_down ? MgslEvent_RiInactive:0) + - (cnow.exithunt != cprev.exithunt ? MgslEvent_ExitHuntMode:0) + - (cnow.rxidle != cprev.rxidle ? MgslEvent_IdleReceived:0) ); - if (events) - break; - - cprev = cnow; - oldsigs = newsigs; - } - - remove_wait_queue(&info->event_wait_q, &wait); - set_current_state(TASK_RUNNING); - - if (mask & MgslEvent_ExitHuntMode) { - spin_lock_irqsave(&info->lock, flags); - if (!waitqueue_active(&info->event_wait_q)) - irq_disable(info, CHA, IRQ_EXITHUNT); - spin_unlock_irqrestore(&info->lock, flags); - } -exit: - if (rc == 0) - PUT_USER(rc, events, mask_ptr); - return rc; -} - -static int modem_input_wait(MGSLPC_INFO *info,int arg) -{ - unsigned long flags; - int rc; - struct mgsl_icount cprev, cnow; - DECLARE_WAITQUEUE(wait, current); - - /* save current irq counts */ - spin_lock_irqsave(&info->lock, flags); - cprev = info->icount; - add_wait_queue(&info->status_event_wait_q, &wait); - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock, flags); - - for(;;) { - schedule(); - if (signal_pending(current)) { - rc = -ERESTARTSYS; - break; - } - - /* get new irq counts */ - spin_lock_irqsave(&info->lock, flags); - cnow = info->icount; - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&info->lock, flags); - - /* if no change, wait aborted for some reason */ - if (cnow.rng == cprev.rng && cnow.dsr == cprev.dsr && - cnow.dcd == cprev.dcd && cnow.cts == cprev.cts) { - rc = -EIO; - break; - } - - /* check for change in caller specified modem input */ - if ((arg & TIOCM_RNG && cnow.rng != cprev.rng) || - (arg & TIOCM_DSR && cnow.dsr != cprev.dsr) || - (arg & TIOCM_CD && cnow.dcd != cprev.dcd) || - (arg & TIOCM_CTS && cnow.cts != cprev.cts)) { - rc = 0; - break; - } - - cprev = cnow; - } - remove_wait_queue(&info->status_event_wait_q, &wait); - set_current_state(TASK_RUNNING); - return rc; -} - -/* return the state of the serial control and status signals - */ -static int tiocmget(struct tty_struct *tty) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned int result; - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - get_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - - result = ((info->serial_signals & SerialSignal_RTS) ? TIOCM_RTS:0) + - ((info->serial_signals & SerialSignal_DTR) ? TIOCM_DTR:0) + - ((info->serial_signals & SerialSignal_DCD) ? TIOCM_CAR:0) + - ((info->serial_signals & SerialSignal_RI) ? TIOCM_RNG:0) + - ((info->serial_signals & SerialSignal_DSR) ? TIOCM_DSR:0) + - ((info->serial_signals & SerialSignal_CTS) ? TIOCM_CTS:0); - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):%s tiocmget() value=%08X\n", - __FILE__, __LINE__, info->device_name, result); - return result; -} - -/* set modem control signals (DTR/RTS) - */ -static int tiocmset(struct tty_struct *tty, - unsigned int set, unsigned int clear) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):%s tiocmset(%x,%x)\n", - __FILE__, __LINE__, info->device_name, set, clear); - - if (set & TIOCM_RTS) - info->serial_signals |= SerialSignal_RTS; - if (set & TIOCM_DTR) - info->serial_signals |= SerialSignal_DTR; - if (clear & TIOCM_RTS) - info->serial_signals &= ~SerialSignal_RTS; - if (clear & TIOCM_DTR) - info->serial_signals &= ~SerialSignal_DTR; - - spin_lock_irqsave(&info->lock, flags); - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - - return 0; -} - -/* Set or clear transmit break condition - * - * Arguments: tty pointer to tty instance data - * break_state -1=set break condition, 0=clear - */ -static int mgslpc_break(struct tty_struct *tty, int break_state) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_break(%s,%d)\n", - __FILE__, __LINE__, info->device_name, break_state); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_break")) - return -EINVAL; - - spin_lock_irqsave(&info->lock, flags); - if (break_state == -1) - set_reg_bits(info, CHA+DAFO, BIT6); - else - clear_reg_bits(info, CHA+DAFO, BIT6); - spin_unlock_irqrestore(&info->lock, flags); - return 0; -} - -static int mgslpc_get_icount(struct tty_struct *tty, - struct serial_icounter_struct *icount) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - struct mgsl_icount cnow; /* kernel counter temps */ - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - cnow = info->icount; - spin_unlock_irqrestore(&info->lock, flags); - - icount->cts = cnow.cts; - icount->dsr = cnow.dsr; - icount->rng = cnow.rng; - icount->dcd = cnow.dcd; - icount->rx = cnow.rx; - icount->tx = cnow.tx; - icount->frame = cnow.frame; - icount->overrun = cnow.overrun; - icount->parity = cnow.parity; - icount->brk = cnow.brk; - icount->buf_overrun = cnow.buf_overrun; - - return 0; -} - -/* Service an IOCTL request - * - * Arguments: - * - * tty pointer to tty instance data - * cmd IOCTL command code - * arg command argument/context - * - * Return Value: 0 if success, otherwise error code - */ -static int mgslpc_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - void __user *argp = (void __user *)arg; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_ioctl %s cmd=%08X\n", __FILE__, __LINE__, - info->device_name, cmd); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_ioctl")) - return -ENODEV; - - if (cmd != TIOCMIWAIT) { - if (tty_io_error(tty)) - return -EIO; - } - - switch (cmd) { - case MGSL_IOCGPARAMS: - return get_params(info, argp); - case MGSL_IOCSPARAMS: - return set_params(info, argp, tty); - case MGSL_IOCGTXIDLE: - return get_txidle(info, argp); - case MGSL_IOCSTXIDLE: - return set_txidle(info, (int)arg); - case MGSL_IOCGIF: - return get_interface(info, argp); - case MGSL_IOCSIF: - return set_interface(info,(int)arg); - case MGSL_IOCTXENABLE: - return set_txenable(info,(int)arg, tty); - case MGSL_IOCRXENABLE: - return set_rxenable(info,(int)arg); - case MGSL_IOCTXABORT: - return tx_abort(info); - case MGSL_IOCGSTATS: - return get_stats(info, argp); - case MGSL_IOCWAITEVENT: - return wait_events(info, argp); - case TIOCMIWAIT: - return modem_input_wait(info,(int)arg); - default: - return -ENOIOCTLCMD; - } - return 0; -} - -/* Set new termios settings - * - * Arguments: - * - * tty pointer to tty structure - * termios pointer to buffer to hold returned old termios - */ -static void mgslpc_set_termios(struct tty_struct *tty, - const struct ktermios *old_termios) -{ - MGSLPC_INFO *info = (MGSLPC_INFO *)tty->driver_data; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_set_termios %s\n", __FILE__, __LINE__, - tty->driver->name); - - /* just return if nothing has changed */ - if ((tty->termios.c_cflag == old_termios->c_cflag) - && (RELEVANT_IFLAG(tty->termios.c_iflag) - == RELEVANT_IFLAG(old_termios->c_iflag))) - return; - - mgslpc_change_params(info, tty); - - /* Handle transition to B0 status */ - if ((old_termios->c_cflag & CBAUD) && !C_BAUD(tty)) { - info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - spin_lock_irqsave(&info->lock, flags); - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - } - - /* Handle transition away from B0 status */ - if (!(old_termios->c_cflag & CBAUD) && C_BAUD(tty)) { - info->serial_signals |= SerialSignal_DTR; - if (!C_CRTSCTS(tty) || !tty_throttled(tty)) - info->serial_signals |= SerialSignal_RTS; - spin_lock_irqsave(&info->lock, flags); - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - } - - /* Handle turning off CRTSCTS */ - if (old_termios->c_cflag & CRTSCTS && !C_CRTSCTS(tty)) { - tty->hw_stopped = 0; - tx_release(tty); - } -} - -static void mgslpc_close(struct tty_struct *tty, struct file * filp) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - struct tty_port *port = &info->port; - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_close")) - return; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_close(%s) entry, count=%d\n", - __FILE__, __LINE__, info->device_name, port->count); - - if (tty_port_close_start(port, tty, filp) == 0) - goto cleanup; - - if (tty_port_initialized(port)) - mgslpc_wait_until_sent(tty, info->timeout); - - mgslpc_flush_buffer(tty); - - tty_ldisc_flush(tty); - shutdown(info, tty); - - tty_port_close_end(port, tty); - tty_port_tty_set(port, NULL); -cleanup: - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_close(%s) exit, count=%d\n", __FILE__, __LINE__, - tty->driver->name, port->count); -} - -/* Wait until the transmitter is empty. - */ -static void mgslpc_wait_until_sent(struct tty_struct *tty, int timeout) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - unsigned long orig_jiffies, char_time; - - if (!info) - return; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_wait_until_sent(%s) entry\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_wait_until_sent")) - return; - - if (!tty_port_initialized(&info->port)) - goto exit; - - orig_jiffies = jiffies; - - /* Set check interval to 1/5 of estimated time to - * send a character, and make it at least 1. The check - * interval should also be less than the timeout. - * Note: use tight timings here to satisfy the NIST-PCTS. - */ - - if (info->params.data_rate) { - char_time = info->timeout/(32 * 5); - if (!char_time) - char_time++; - } else - char_time = 1; - - if (timeout) - char_time = min_t(unsigned long, char_time, timeout); - - if (info->params.mode == MGSL_MODE_HDLC) { - while (info->tx_active) { - msleep_interruptible(jiffies_to_msecs(char_time)); - if (signal_pending(current)) - break; - if (timeout && time_after(jiffies, orig_jiffies + timeout)) - break; - } - } else { - while ((info->tx_count || info->tx_active) && - info->tx_enabled) { - msleep_interruptible(jiffies_to_msecs(char_time)); - if (signal_pending(current)) - break; - if (timeout && time_after(jiffies, orig_jiffies + timeout)) - break; - } - } - -exit: - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_wait_until_sent(%s) exit\n", - __FILE__, __LINE__, info->device_name); -} - -/* Called by tty_hangup() when a hangup is signaled. - * This is the same as closing all open files for the port. - */ -static void mgslpc_hangup(struct tty_struct *tty) -{ - MGSLPC_INFO * info = (MGSLPC_INFO *)tty->driver_data; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_hangup(%s)\n", - __FILE__, __LINE__, info->device_name); - - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_hangup")) - return; - - mgslpc_flush_buffer(tty); - shutdown(info, tty); - tty_port_hangup(&info->port); -} - -static bool carrier_raised(struct tty_port *port) -{ - MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port); - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - get_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - - return info->serial_signals & SerialSignal_DCD; -} - -static void dtr_rts(struct tty_port *port, bool active) -{ - MGSLPC_INFO *info = container_of(port, MGSLPC_INFO, port); - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - if (active) - info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR; - else - info->serial_signals &= ~(SerialSignal_RTS | SerialSignal_DTR); - set_signals(info); - spin_unlock_irqrestore(&info->lock, flags); -} - - -static int mgslpc_open(struct tty_struct *tty, struct file * filp) -{ - MGSLPC_INFO *info; - struct tty_port *port; - int retval, line; - unsigned long flags; - - /* verify range of specified line number */ - line = tty->index; - if (line >= mgslpc_device_count) { - printk("%s(%d):mgslpc_open with invalid line #%d.\n", - __FILE__, __LINE__, line); - return -ENODEV; - } - - /* find the info structure for the specified line */ - info = mgslpc_device_list; - while(info && info->line != line) - info = info->next_device; - if (mgslpc_paranoia_check(info, tty->name, "mgslpc_open")) - return -ENODEV; - - port = &info->port; - tty->driver_data = info; - tty_port_tty_set(port, tty); - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_open(%s), old ref count = %d\n", - __FILE__, __LINE__, tty->driver->name, port->count); - - spin_lock_irqsave(&info->netlock, flags); - if (info->netcount) { - retval = -EBUSY; - spin_unlock_irqrestore(&info->netlock, flags); - goto cleanup; - } - spin_lock(&port->lock); - port->count++; - spin_unlock(&port->lock); - spin_unlock_irqrestore(&info->netlock, flags); - - if (port->count == 1) { - /* 1st open on this device, init hardware */ - retval = startup(info, tty); - if (retval < 0) - goto cleanup; - } - - retval = tty_port_block_til_ready(&info->port, tty, filp); - if (retval) { - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):block_til_ready(%s) returned %d\n", - __FILE__, __LINE__, info->device_name, retval); - goto cleanup; - } - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):mgslpc_open(%s) success\n", - __FILE__, __LINE__, info->device_name); - retval = 0; - -cleanup: - return retval; -} - -/* - * /proc fs routines.... - */ - -static inline void line_info(struct seq_file *m, MGSLPC_INFO *info) -{ - char stat_buf[30]; - unsigned long flags; - - seq_printf(m, "%s:io:%04X irq:%d", - info->device_name, info->io_base, info->irq_level); - - /* output current serial signal states */ - spin_lock_irqsave(&info->lock, flags); - get_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - - stat_buf[0] = 0; - stat_buf[1] = 0; - if (info->serial_signals & SerialSignal_RTS) - strcat(stat_buf, "|RTS"); - if (info->serial_signals & SerialSignal_CTS) - strcat(stat_buf, "|CTS"); - if (info->serial_signals & SerialSignal_DTR) - strcat(stat_buf, "|DTR"); - if (info->serial_signals & SerialSignal_DSR) - strcat(stat_buf, "|DSR"); - if (info->serial_signals & SerialSignal_DCD) - strcat(stat_buf, "|CD"); - if (info->serial_signals & SerialSignal_RI) - strcat(stat_buf, "|RI"); - - if (info->params.mode == MGSL_MODE_HDLC) { - seq_printf(m, " HDLC txok:%d rxok:%d", - info->icount.txok, info->icount.rxok); - if (info->icount.txunder) - seq_printf(m, " txunder:%d", info->icount.txunder); - if (info->icount.txabort) - seq_printf(m, " txabort:%d", info->icount.txabort); - if (info->icount.rxshort) - seq_printf(m, " rxshort:%d", info->icount.rxshort); - if (info->icount.rxlong) - seq_printf(m, " rxlong:%d", info->icount.rxlong); - if (info->icount.rxover) - seq_printf(m, " rxover:%d", info->icount.rxover); - if (info->icount.rxcrc) - seq_printf(m, " rxcrc:%d", info->icount.rxcrc); - } else { - seq_printf(m, " ASYNC tx:%d rx:%d", - info->icount.tx, info->icount.rx); - if (info->icount.frame) - seq_printf(m, " fe:%d", info->icount.frame); - if (info->icount.parity) - seq_printf(m, " pe:%d", info->icount.parity); - if (info->icount.brk) - seq_printf(m, " brk:%d", info->icount.brk); - if (info->icount.overrun) - seq_printf(m, " oe:%d", info->icount.overrun); - } - - /* Append serial signal status to end */ - seq_printf(m, " %s\n", stat_buf+1); - - seq_printf(m, "txactive=%d bh_req=%d bh_run=%d pending_bh=%x\n", - info->tx_active,info->bh_requested,info->bh_running, - info->pending_bh); -} - -/* Called to print information about devices - */ -static int mgslpc_proc_show(struct seq_file *m, void *v) -{ - MGSLPC_INFO *info; - - seq_printf(m, "synclink driver:%s\n", driver_version); - - info = mgslpc_device_list; - while (info) { - line_info(m, info); - info = info->next_device; - } - return 0; -} - -static int rx_alloc_buffers(MGSLPC_INFO *info) -{ - /* each buffer has header and data */ - info->rx_buf_size = sizeof(RXBUF) + info->max_frame_size; - - /* calculate total allocation size for 8 buffers */ - info->rx_buf_total_size = info->rx_buf_size * 8; - - /* limit total allocated memory */ - if (info->rx_buf_total_size > 0x10000) - info->rx_buf_total_size = 0x10000; - - /* calculate number of buffers */ - info->rx_buf_count = info->rx_buf_total_size / info->rx_buf_size; - - info->rx_buf = kmalloc(info->rx_buf_total_size, GFP_KERNEL); - if (info->rx_buf == NULL) - return -ENOMEM; - - /* unused flag buffer to satisfy receive_buf calling interface */ - info->flag_buf = kzalloc(info->max_frame_size, GFP_KERNEL); - if (!info->flag_buf) { - kfree(info->rx_buf); - info->rx_buf = NULL; - return -ENOMEM; - } - - rx_reset_buffers(info); - return 0; -} - -static void rx_free_buffers(MGSLPC_INFO *info) -{ - kfree(info->rx_buf); - info->rx_buf = NULL; - kfree(info->flag_buf); - info->flag_buf = NULL; -} - -static int claim_resources(MGSLPC_INFO *info) -{ - if (rx_alloc_buffers(info) < 0) { - printk("Can't allocate rx buffer %s\n", info->device_name); - release_resources(info); - return -ENODEV; - } - return 0; -} - -static void release_resources(MGSLPC_INFO *info) -{ - if (debug_level >= DEBUG_LEVEL_INFO) - printk("release_resources(%s)\n", info->device_name); - rx_free_buffers(info); -} - -/* Add the specified device instance data structure to the - * global linked list of devices and increment the device count. - * - * Arguments: info pointer to device instance data - */ -static int mgslpc_add_device(MGSLPC_INFO *info) -{ - MGSLPC_INFO *current_dev = NULL; - struct device *tty_dev; - int ret; - - info->next_device = NULL; - info->line = mgslpc_device_count; - sprintf(info->device_name,"ttySLP%d",info->line); - - if (info->line < MAX_DEVICE_COUNT) { - if (maxframe[info->line]) - info->max_frame_size = maxframe[info->line]; - } - - mgslpc_device_count++; - - if (!mgslpc_device_list) - mgslpc_device_list = info; - else { - current_dev = mgslpc_device_list; - while (current_dev->next_device) - current_dev = current_dev->next_device; - current_dev->next_device = info; - } - - if (info->max_frame_size < 4096) - info->max_frame_size = 4096; - else if (info->max_frame_size > 65535) - info->max_frame_size = 65535; - - printk("SyncLink PC Card %s:IO=%04X IRQ=%d\n", - info->device_name, info->io_base, info->irq_level); - -#if SYNCLINK_GENERIC_HDLC - ret = hdlcdev_init(info); - if (ret != 0) - goto failed; -#endif - - tty_dev = tty_port_register_device(&info->port, serial_driver, info->line, - &info->p_dev->dev); - if (IS_ERR(tty_dev)) { - ret = PTR_ERR(tty_dev); -#if SYNCLINK_GENERIC_HDLC - hdlcdev_exit(info); -#endif - goto failed; - } - - return 0; - -failed: - if (current_dev) - current_dev->next_device = NULL; - else - mgslpc_device_list = NULL; - mgslpc_device_count--; - return ret; -} - -static void mgslpc_remove_device(MGSLPC_INFO *remove_info) -{ - MGSLPC_INFO *info = mgslpc_device_list; - MGSLPC_INFO *last = NULL; - - while(info) { - if (info == remove_info) { - if (last) - last->next_device = info->next_device; - else - mgslpc_device_list = info->next_device; - tty_unregister_device(serial_driver, info->line); -#if SYNCLINK_GENERIC_HDLC - hdlcdev_exit(info); -#endif - release_resources(info); - tty_port_destroy(&info->port); - kfree(info); - mgslpc_device_count--; - return; - } - last = info; - info = info->next_device; - } -} - -static const struct pcmcia_device_id mgslpc_ids[] = { - PCMCIA_DEVICE_MANF_CARD(0x02c5, 0x0050), - PCMCIA_DEVICE_NULL -}; -MODULE_DEVICE_TABLE(pcmcia, mgslpc_ids); - -static struct pcmcia_driver mgslpc_driver = { - .owner = THIS_MODULE, - .name = "synclink_cs", - .probe = mgslpc_probe, - .remove = mgslpc_detach, - .id_table = mgslpc_ids, - .suspend = mgslpc_suspend, - .resume = mgslpc_resume, -}; - -static const struct tty_operations mgslpc_ops = { - .open = mgslpc_open, - .close = mgslpc_close, - .write = mgslpc_write, - .put_char = mgslpc_put_char, - .flush_chars = mgslpc_flush_chars, - .write_room = mgslpc_write_room, - .chars_in_buffer = mgslpc_chars_in_buffer, - .flush_buffer = mgslpc_flush_buffer, - .ioctl = mgslpc_ioctl, - .throttle = mgslpc_throttle, - .unthrottle = mgslpc_unthrottle, - .send_xchar = mgslpc_send_xchar, - .break_ctl = mgslpc_break, - .wait_until_sent = mgslpc_wait_until_sent, - .set_termios = mgslpc_set_termios, - .stop = tx_pause, - .start = tx_release, - .hangup = mgslpc_hangup, - .tiocmget = tiocmget, - .tiocmset = tiocmset, - .get_icount = mgslpc_get_icount, - .proc_show = mgslpc_proc_show, -}; - -static int __init synclink_cs_init(void) -{ - int rc; - - if (break_on_load) { - mgslpc_get_text_ptr(); - BREAKPOINT(); - } - - serial_driver = tty_alloc_driver(MAX_DEVICE_COUNT, - TTY_DRIVER_REAL_RAW | - TTY_DRIVER_DYNAMIC_DEV); - if (IS_ERR(serial_driver)) { - rc = PTR_ERR(serial_driver); - goto err; - } - - /* Initialize the tty_driver structure */ - serial_driver->driver_name = "synclink_cs"; - serial_driver->name = "ttySLP"; - serial_driver->major = ttymajor; - serial_driver->minor_start = 64; - serial_driver->type = TTY_DRIVER_TYPE_SERIAL; - serial_driver->subtype = SERIAL_TYPE_NORMAL; - serial_driver->init_termios = tty_std_termios; - serial_driver->init_termios.c_cflag = - B9600 | CS8 | CREAD | HUPCL | CLOCAL; - tty_set_operations(serial_driver, &mgslpc_ops); - - rc = tty_register_driver(serial_driver); - if (rc < 0) { - printk(KERN_ERR "%s(%d):Couldn't register serial driver\n", - __FILE__, __LINE__); - goto err_put_tty; - } - - rc = pcmcia_register_driver(&mgslpc_driver); - if (rc < 0) - goto err_unreg_tty; - - printk(KERN_INFO "%s %s, tty major#%d\n", driver_name, driver_version, - serial_driver->major); - - return 0; -err_unreg_tty: - tty_unregister_driver(serial_driver); -err_put_tty: - tty_driver_kref_put(serial_driver); -err: - return rc; -} - -static void __exit synclink_cs_exit(void) -{ - pcmcia_unregister_driver(&mgslpc_driver); - tty_unregister_driver(serial_driver); - tty_driver_kref_put(serial_driver); -} - -module_init(synclink_cs_init); -module_exit(synclink_cs_exit); - -static void mgslpc_set_rate(MGSLPC_INFO *info, unsigned char channel, unsigned int rate) -{ - unsigned int M, N; - unsigned char val; - - /* note:standard BRG mode is broken in V3.2 chip - * so enhanced mode is always used - */ - - if (rate) { - N = 3686400 / rate; - if (!N) - N = 1; - N >>= 1; - for (M = 1; N > 64 && M < 16; M++) - N >>= 1; - N--; - - /* BGR[5..0] = N - * BGR[9..6] = M - * BGR[7..0] contained in BGR register - * BGR[9..8] contained in CCR2[7..6] - * divisor = (N+1)*2^M - * - * Note: M *must* not be zero (causes asymetric duty cycle) - */ - write_reg(info, (unsigned char) (channel + BGR), - (unsigned char) ((M << 6) + N)); - val = read_reg(info, (unsigned char) (channel + CCR2)) & 0x3f; - val |= ((M << 4) & 0xc0); - write_reg(info, (unsigned char) (channel + CCR2), val); - } -} - -/* Enabled the AUX clock output at the specified frequency. - */ -static void enable_auxclk(MGSLPC_INFO *info) -{ - unsigned char val; - - /* MODE - * - * 07..06 MDS[1..0] 10 = transparent HDLC mode - * 05 ADM Address Mode, 0 = no addr recognition - * 04 TMD Timer Mode, 0 = external - * 03 RAC Receiver Active, 0 = inactive - * 02 RTS 0=RTS active during xmit, 1=RTS always active - * 01 TRS Timer Resolution, 1=512 - * 00 TLP Test Loop, 0 = no loop - * - * 1000 0010 - */ - val = 0x82; - - /* channel B RTS is used to enable AUXCLK driver on SP505 */ - if (info->params.mode == MGSL_MODE_HDLC && info->params.clock_speed) - val |= BIT2; - write_reg(info, CHB + MODE, val); - - /* CCR0 - * - * 07 PU Power Up, 1=active, 0=power down - * 06 MCE Master Clock Enable, 1=enabled - * 05 Reserved, 0 - * 04..02 SC[2..0] Encoding - * 01..00 SM[1..0] Serial Mode, 00=HDLC - * - * 11000000 - */ - write_reg(info, CHB + CCR0, 0xc0); - - /* CCR1 - * - * 07 SFLG Shared Flag, 0 = disable shared flags - * 06 GALP Go Active On Loop, 0 = not used - * 05 GLP Go On Loop, 0 = not used - * 04 ODS Output Driver Select, 1=TxD is push-pull output - * 03 ITF Interframe Time Fill, 0=mark, 1=flag - * 02..00 CM[2..0] Clock Mode - * - * 0001 0111 - */ - write_reg(info, CHB + CCR1, 0x17); - - /* CCR2 (Channel B) - * - * 07..06 BGR[9..8] Baud rate bits 9..8 - * 05 BDF Baud rate divisor factor, 0=1, 1=BGR value - * 04 SSEL Clock source select, 1=submode b - * 03 TOE 0=TxCLK is input, 1=TxCLK is output - * 02 RWX Read/Write Exchange 0=disabled - * 01 C32, CRC select, 0=CRC-16, 1=CRC-32 - * 00 DIV, data inversion 0=disabled, 1=enabled - * - * 0011 1000 - */ - if (info->params.mode == MGSL_MODE_HDLC && info->params.clock_speed) - write_reg(info, CHB + CCR2, 0x38); - else - write_reg(info, CHB + CCR2, 0x30); - - /* CCR4 - * - * 07 MCK4 Master Clock Divide by 4, 1=enabled - * 06 EBRG Enhanced Baud Rate Generator Mode, 1=enabled - * 05 TST1 Test Pin, 0=normal operation - * 04 ICD Ivert Carrier Detect, 1=enabled (active low) - * 03..02 Reserved, must be 0 - * 01..00 RFT[1..0] RxFIFO Threshold 00=32 bytes - * - * 0101 0000 - */ - write_reg(info, CHB + CCR4, 0x50); - - /* if auxclk not enabled, set internal BRG so - * CTS transitions can be detected (requires TxC) - */ - if (info->params.mode == MGSL_MODE_HDLC && info->params.clock_speed) - mgslpc_set_rate(info, CHB, info->params.clock_speed); - else - mgslpc_set_rate(info, CHB, 921600); -} - -static void loopback_enable(MGSLPC_INFO *info) -{ - unsigned char val; - - /* CCR1:02..00 CM[2..0] Clock Mode = 111 (clock mode 7) */ - val = read_reg(info, CHA + CCR1) | (BIT2 | BIT1 | BIT0); - write_reg(info, CHA + CCR1, val); - - /* CCR2:04 SSEL Clock source select, 1=submode b */ - val = read_reg(info, CHA + CCR2) | (BIT4 | BIT5); - write_reg(info, CHA + CCR2, val); - - /* set LinkSpeed if available, otherwise default to 2Mbps */ - if (info->params.clock_speed) - mgslpc_set_rate(info, CHA, info->params.clock_speed); - else - mgslpc_set_rate(info, CHA, 1843200); - - /* MODE:00 TLP Test Loop, 1=loopback enabled */ - val = read_reg(info, CHA + MODE) | BIT0; - write_reg(info, CHA + MODE, val); -} - -static void hdlc_mode(MGSLPC_INFO *info) -{ - unsigned char val; - unsigned char clkmode, clksubmode; - - /* disable all interrupts */ - irq_disable(info, CHA, 0xffff); - irq_disable(info, CHB, 0xffff); - port_irq_disable(info, 0xff); - - /* assume clock mode 0a, rcv=RxC xmt=TxC */ - clkmode = clksubmode = 0; - if (info->params.flags & HDLC_FLAG_RXC_DPLL - && info->params.flags & HDLC_FLAG_TXC_DPLL) { - /* clock mode 7a, rcv = DPLL, xmt = DPLL */ - clkmode = 7; - } else if (info->params.flags & HDLC_FLAG_RXC_BRG - && info->params.flags & HDLC_FLAG_TXC_BRG) { - /* clock mode 7b, rcv = BRG, xmt = BRG */ - clkmode = 7; - clksubmode = 1; - } else if (info->params.flags & HDLC_FLAG_RXC_DPLL) { - if (info->params.flags & HDLC_FLAG_TXC_BRG) { - /* clock mode 6b, rcv = DPLL, xmt = BRG/16 */ - clkmode = 6; - clksubmode = 1; - } else { - /* clock mode 6a, rcv = DPLL, xmt = TxC */ - clkmode = 6; - } - } else if (info->params.flags & HDLC_FLAG_TXC_BRG) { - /* clock mode 0b, rcv = RxC, xmt = BRG */ - clksubmode = 1; - } - - /* MODE - * - * 07..06 MDS[1..0] 10 = transparent HDLC mode - * 05 ADM Address Mode, 0 = no addr recognition - * 04 TMD Timer Mode, 0 = external - * 03 RAC Receiver Active, 0 = inactive - * 02 RTS 0=RTS active during xmit, 1=RTS always active - * 01 TRS Timer Resolution, 1=512 - * 00 TLP Test Loop, 0 = no loop - * - * 1000 0010 - */ - val = 0x82; - if (info->params.loopback) - val |= BIT0; - - /* preserve RTS state */ - if (info->serial_signals & SerialSignal_RTS) - val |= BIT2; - write_reg(info, CHA + MODE, val); - - /* CCR0 - * - * 07 PU Power Up, 1=active, 0=power down - * 06 MCE Master Clock Enable, 1=enabled - * 05 Reserved, 0 - * 04..02 SC[2..0] Encoding - * 01..00 SM[1..0] Serial Mode, 00=HDLC - * - * 11000000 - */ - val = 0xc0; - switch (info->params.encoding) - { - case HDLC_ENCODING_NRZI: - val |= BIT3; - break; - case HDLC_ENCODING_BIPHASE_SPACE: - val |= BIT4; - break; // FM0 - case HDLC_ENCODING_BIPHASE_MARK: - val |= BIT4 | BIT2; - break; // FM1 - case HDLC_ENCODING_BIPHASE_LEVEL: - val |= BIT4 | BIT3; - break; // Manchester - } - write_reg(info, CHA + CCR0, val); - - /* CCR1 - * - * 07 SFLG Shared Flag, 0 = disable shared flags - * 06 GALP Go Active On Loop, 0 = not used - * 05 GLP Go On Loop, 0 = not used - * 04 ODS Output Driver Select, 1=TxD is push-pull output - * 03 ITF Interframe Time Fill, 0=mark, 1=flag - * 02..00 CM[2..0] Clock Mode - * - * 0001 0000 - */ - val = 0x10 + clkmode; - write_reg(info, CHA + CCR1, val); - - /* CCR2 - * - * 07..06 BGR[9..8] Baud rate bits 9..8 - * 05 BDF Baud rate divisor factor, 0=1, 1=BGR value - * 04 SSEL Clock source select, 1=submode b - * 03 TOE 0=TxCLK is input, 0=TxCLK is input - * 02 RWX Read/Write Exchange 0=disabled - * 01 C32, CRC select, 0=CRC-16, 1=CRC-32 - * 00 DIV, data inversion 0=disabled, 1=enabled - * - * 0000 0000 - */ - val = 0x00; - if (clkmode == 2 || clkmode == 3 || clkmode == 6 - || clkmode == 7 || (clkmode == 0 && clksubmode == 1)) - val |= BIT5; - if (clksubmode) - val |= BIT4; - if (info->params.crc_type == HDLC_CRC_32_CCITT) - val |= BIT1; - if (info->params.encoding == HDLC_ENCODING_NRZB) - val |= BIT0; - write_reg(info, CHA + CCR2, val); - - /* CCR3 - * - * 07..06 PRE[1..0] Preamble count 00=1, 01=2, 10=4, 11=8 - * 05 EPT Enable preamble transmission, 1=enabled - * 04 RADD Receive address pushed to FIFO, 0=disabled - * 03 CRL CRC Reset Level, 0=FFFF - * 02 RCRC Rx CRC 0=On 1=Off - * 01 TCRC Tx CRC 0=On 1=Off - * 00 PSD DPLL Phase Shift Disable - * - * 0000 0000 - */ - val = 0x00; - if (info->params.crc_type == HDLC_CRC_NONE) - val |= BIT2 | BIT1; - if (info->params.preamble != HDLC_PREAMBLE_PATTERN_NONE) - val |= BIT5; - switch (info->params.preamble_length) - { - case HDLC_PREAMBLE_LENGTH_16BITS: - val |= BIT6; - break; - case HDLC_PREAMBLE_LENGTH_32BITS: - val |= BIT6; - break; - case HDLC_PREAMBLE_LENGTH_64BITS: - val |= BIT7 | BIT6; - break; - } - write_reg(info, CHA + CCR3, val); - - /* PRE - Preamble pattern */ - val = 0; - switch (info->params.preamble) - { - case HDLC_PREAMBLE_PATTERN_FLAGS: val = 0x7e; break; - case HDLC_PREAMBLE_PATTERN_10: val = 0xaa; break; - case HDLC_PREAMBLE_PATTERN_01: val = 0x55; break; - case HDLC_PREAMBLE_PATTERN_ONES: val = 0xff; break; - } - write_reg(info, CHA + PRE, val); - - /* CCR4 - * - * 07 MCK4 Master Clock Divide by 4, 1=enabled - * 06 EBRG Enhanced Baud Rate Generator Mode, 1=enabled - * 05 TST1 Test Pin, 0=normal operation - * 04 ICD Ivert Carrier Detect, 1=enabled (active low) - * 03..02 Reserved, must be 0 - * 01..00 RFT[1..0] RxFIFO Threshold 00=32 bytes - * - * 0101 0000 - */ - val = 0x50; - write_reg(info, CHA + CCR4, val); - if (info->params.flags & HDLC_FLAG_RXC_DPLL) - mgslpc_set_rate(info, CHA, info->params.clock_speed * 16); - else - mgslpc_set_rate(info, CHA, info->params.clock_speed); - - /* RLCR Receive length check register - * - * 7 1=enable receive length check - * 6..0 Max frame length = (RL + 1) * 32 - */ - write_reg(info, CHA + RLCR, 0); - - /* XBCH Transmit Byte Count High - * - * 07 DMA mode, 0 = interrupt driven - * 06 NRM, 0=ABM (ignored) - * 05 CAS Carrier Auto Start - * 04 XC Transmit Continuously (ignored) - * 03..00 XBC[10..8] Transmit byte count bits 10..8 - * - * 0000 0000 - */ - val = 0x00; - if (info->params.flags & HDLC_FLAG_AUTO_DCD) - val |= BIT5; - write_reg(info, CHA + XBCH, val); - enable_auxclk(info); - if (info->params.loopback || info->testing_irq) - loopback_enable(info); - if (info->params.flags & HDLC_FLAG_AUTO_CTS) - { - irq_enable(info, CHB, IRQ_CTS); - /* PVR[3] 1=AUTO CTS active */ - set_reg_bits(info, CHA + PVR, BIT3); - } else - clear_reg_bits(info, CHA + PVR, BIT3); - - irq_enable(info, CHA, - IRQ_RXEOM | IRQ_RXFIFO | IRQ_ALLSENT | - IRQ_UNDERRUN | IRQ_TXFIFO); - issue_command(info, CHA, CMD_TXRESET + CMD_RXRESET); - wait_command_complete(info, CHA); - read_reg16(info, CHA + ISR); /* clear pending IRQs */ - - /* Master clock mode enabled above to allow reset commands - * to complete even if no data clocks are present. - * - * Disable master clock mode for normal communications because - * V3.2 of the ESCC2 has a bug that prevents the transmit all sent - * IRQ when in master clock mode. - * - * Leave master clock mode enabled for IRQ test because the - * timer IRQ used by the test can only happen in master clock mode. - */ - if (!info->testing_irq) - clear_reg_bits(info, CHA + CCR0, BIT6); - - tx_set_idle(info); - - tx_stop(info); - rx_stop(info); -} - -static void rx_stop(MGSLPC_INFO *info) -{ - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):rx_stop(%s)\n", - __FILE__, __LINE__, info->device_name); - - /* MODE:03 RAC Receiver Active, 0=inactive */ - clear_reg_bits(info, CHA + MODE, BIT3); - - info->rx_enabled = false; - info->rx_overflow = false; -} - -static void rx_start(MGSLPC_INFO *info) -{ - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):rx_start(%s)\n", - __FILE__, __LINE__, info->device_name); - - rx_reset_buffers(info); - info->rx_enabled = false; - info->rx_overflow = false; - - /* MODE:03 RAC Receiver Active, 1=active */ - set_reg_bits(info, CHA + MODE, BIT3); - - info->rx_enabled = true; -} - -static void tx_start(MGSLPC_INFO *info, struct tty_struct *tty) -{ - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):tx_start(%s)\n", - __FILE__, __LINE__, info->device_name); - - if (info->tx_count) { - /* If auto RTS enabled and RTS is inactive, then assert */ - /* RTS and set a flag indicating that the driver should */ - /* negate RTS when the transmission completes. */ - info->drop_rts_on_tx_done = false; - - if (info->params.flags & HDLC_FLAG_AUTO_RTS) { - get_signals(info); - if (!(info->serial_signals & SerialSignal_RTS)) { - info->serial_signals |= SerialSignal_RTS; - set_signals(info); - info->drop_rts_on_tx_done = true; - } - } - - if (info->params.mode == MGSL_MODE_ASYNC) { - if (!info->tx_active) { - info->tx_active = true; - tx_ready(info, tty); - } - } else { - info->tx_active = true; - tx_ready(info, tty); - mod_timer(&info->tx_timer, jiffies + - msecs_to_jiffies(5000)); - } - } - - if (!info->tx_enabled) - info->tx_enabled = true; -} - -static void tx_stop(MGSLPC_INFO *info) -{ - if (debug_level >= DEBUG_LEVEL_ISR) - printk("%s(%d):tx_stop(%s)\n", - __FILE__, __LINE__, info->device_name); - - del_timer(&info->tx_timer); - - info->tx_enabled = false; - info->tx_active = false; -} - -/* Reset the adapter to a known state and prepare it for further use. - */ -static void reset_device(MGSLPC_INFO *info) -{ - /* power up both channels (set BIT7) */ - write_reg(info, CHA + CCR0, 0x80); - write_reg(info, CHB + CCR0, 0x80); - write_reg(info, CHA + MODE, 0); - write_reg(info, CHB + MODE, 0); - - /* disable all interrupts */ - irq_disable(info, CHA, 0xffff); - irq_disable(info, CHB, 0xffff); - port_irq_disable(info, 0xff); - - /* PCR Port Configuration Register - * - * 07..04 DEC[3..0] Serial I/F select outputs - * 03 output, 1=AUTO CTS control enabled - * 02 RI Ring Indicator input 0=active - * 01 DSR input 0=active - * 00 DTR output 0=active - * - * 0000 0110 - */ - write_reg(info, PCR, 0x06); - - /* PVR Port Value Register - * - * 07..04 DEC[3..0] Serial I/F select (0000=disabled) - * 03 AUTO CTS output 1=enabled - * 02 RI Ring Indicator input - * 01 DSR input - * 00 DTR output (1=inactive) - * - * 0000 0001 - */ -// write_reg(info, PVR, PVR_DTR); - - /* IPC Interrupt Port Configuration - * - * 07 VIS 1=Masked interrupts visible - * 06..05 Reserved, 0 - * 04..03 SLA Slave address, 00 ignored - * 02 CASM Cascading Mode, 1=daisy chain - * 01..00 IC[1..0] Interrupt Config, 01=push-pull output, active low - * - * 0000 0101 - */ - write_reg(info, IPC, 0x05); -} - -static void async_mode(MGSLPC_INFO *info) -{ - unsigned char val; - - /* disable all interrupts */ - irq_disable(info, CHA, 0xffff); - irq_disable(info, CHB, 0xffff); - port_irq_disable(info, 0xff); - - /* MODE - * - * 07 Reserved, 0 - * 06 FRTS RTS State, 0=active - * 05 FCTS Flow Control on CTS - * 04 FLON Flow Control Enable - * 03 RAC Receiver Active, 0 = inactive - * 02 RTS 0=Auto RTS, 1=manual RTS - * 01 TRS Timer Resolution, 1=512 - * 00 TLP Test Loop, 0 = no loop - * - * 0000 0110 - */ - val = 0x06; - if (info->params.loopback) - val |= BIT0; - - /* preserve RTS state */ - if (!(info->serial_signals & SerialSignal_RTS)) - val |= BIT6; - write_reg(info, CHA + MODE, val); - - /* CCR0 - * - * 07 PU Power Up, 1=active, 0=power down - * 06 MCE Master Clock Enable, 1=enabled - * 05 Reserved, 0 - * 04..02 SC[2..0] Encoding, 000=NRZ - * 01..00 SM[1..0] Serial Mode, 11=Async - * - * 1000 0011 - */ - write_reg(info, CHA + CCR0, 0x83); - - /* CCR1 - * - * 07..05 Reserved, 0 - * 04 ODS Output Driver Select, 1=TxD is push-pull output - * 03 BCR Bit Clock Rate, 1=16x - * 02..00 CM[2..0] Clock Mode, 111=BRG - * - * 0001 1111 - */ - write_reg(info, CHA + CCR1, 0x1f); - - /* CCR2 (channel A) - * - * 07..06 BGR[9..8] Baud rate bits 9..8 - * 05 BDF Baud rate divisor factor, 0=1, 1=BGR value - * 04 SSEL Clock source select, 1=submode b - * 03 TOE 0=TxCLK is input, 0=TxCLK is input - * 02 RWX Read/Write Exchange 0=disabled - * 01 Reserved, 0 - * 00 DIV, data inversion 0=disabled, 1=enabled - * - * 0001 0000 - */ - write_reg(info, CHA + CCR2, 0x10); - - /* CCR3 - * - * 07..01 Reserved, 0 - * 00 PSD DPLL Phase Shift Disable - * - * 0000 0000 - */ - write_reg(info, CHA + CCR3, 0); - - /* CCR4 - * - * 07 MCK4 Master Clock Divide by 4, 1=enabled - * 06 EBRG Enhanced Baud Rate Generator Mode, 1=enabled - * 05 TST1 Test Pin, 0=normal operation - * 04 ICD Ivert Carrier Detect, 1=enabled (active low) - * 03..00 Reserved, must be 0 - * - * 0101 0000 - */ - write_reg(info, CHA + CCR4, 0x50); - mgslpc_set_rate(info, CHA, info->params.data_rate * 16); - - /* DAFO Data Format - * - * 07 Reserved, 0 - * 06 XBRK transmit break, 0=normal operation - * 05 Stop bits (0=1, 1=2) - * 04..03 PAR[1..0] Parity (01=odd, 10=even) - * 02 PAREN Parity Enable - * 01..00 CHL[1..0] Character Length (00=8, 01=7) - * - */ - val = 0x00; - if (info->params.data_bits != 8) - val |= BIT0; /* 7 bits */ - if (info->params.stop_bits != 1) - val |= BIT5; - if (info->params.parity != ASYNC_PARITY_NONE) - { - val |= BIT2; /* Parity enable */ - if (info->params.parity == ASYNC_PARITY_ODD) - val |= BIT3; - else - val |= BIT4; - } - write_reg(info, CHA + DAFO, val); - - /* RFC Rx FIFO Control - * - * 07 Reserved, 0 - * 06 DPS, 1=parity bit not stored in data byte - * 05 DXS, 0=all data stored in FIFO (including XON/XOFF) - * 04 RFDF Rx FIFO Data Format, 1=status byte stored in FIFO - * 03..02 RFTH[1..0], rx threshold, 11=16 status + 16 data byte - * 01 Reserved, 0 - * 00 TCDE Terminate Char Detect Enable, 0=disabled - * - * 0101 1100 - */ - write_reg(info, CHA + RFC, 0x5c); - - /* RLCR Receive length check register - * - * Max frame length = (RL + 1) * 32 - */ - write_reg(info, CHA + RLCR, 0); - - /* XBCH Transmit Byte Count High - * - * 07 DMA mode, 0 = interrupt driven - * 06 NRM, 0=ABM (ignored) - * 05 CAS Carrier Auto Start - * 04 XC Transmit Continuously (ignored) - * 03..00 XBC[10..8] Transmit byte count bits 10..8 - * - * 0000 0000 - */ - val = 0x00; - if (info->params.flags & HDLC_FLAG_AUTO_DCD) - val |= BIT5; - write_reg(info, CHA + XBCH, val); - if (info->params.flags & HDLC_FLAG_AUTO_CTS) - irq_enable(info, CHA, IRQ_CTS); - - /* MODE:03 RAC Receiver Active, 1=active */ - set_reg_bits(info, CHA + MODE, BIT3); - enable_auxclk(info); - if (info->params.flags & HDLC_FLAG_AUTO_CTS) { - irq_enable(info, CHB, IRQ_CTS); - /* PVR[3] 1=AUTO CTS active */ - set_reg_bits(info, CHA + PVR, BIT3); - } else - clear_reg_bits(info, CHA + PVR, BIT3); - irq_enable(info, CHA, - IRQ_RXEOM | IRQ_RXFIFO | IRQ_BREAK_ON | IRQ_RXTIME | - IRQ_ALLSENT | IRQ_TXFIFO); - issue_command(info, CHA, CMD_TXRESET + CMD_RXRESET); - wait_command_complete(info, CHA); - read_reg16(info, CHA + ISR); /* clear pending IRQs */ -} - -/* Set the HDLC idle mode for the transmitter. - */ -static void tx_set_idle(MGSLPC_INFO *info) -{ - /* Note: ESCC2 only supports flags and one idle modes */ - if (info->idle_mode == HDLC_TXIDLE_FLAGS) - set_reg_bits(info, CHA + CCR1, BIT3); - else - clear_reg_bits(info, CHA + CCR1, BIT3); -} - -/* get state of the V24 status (input) signals. - */ -static void get_signals(MGSLPC_INFO *info) -{ - unsigned char status = 0; - - /* preserve RTS and DTR */ - info->serial_signals &= SerialSignal_RTS | SerialSignal_DTR; - - if (read_reg(info, CHB + VSTR) & BIT7) - info->serial_signals |= SerialSignal_DCD; - if (read_reg(info, CHB + STAR) & BIT1) - info->serial_signals |= SerialSignal_CTS; - - status = read_reg(info, CHA + PVR); - if (!(status & PVR_RI)) - info->serial_signals |= SerialSignal_RI; - if (!(status & PVR_DSR)) - info->serial_signals |= SerialSignal_DSR; -} - -/* Set the state of RTS and DTR based on contents of - * serial_signals member of device extension. - */ -static void set_signals(MGSLPC_INFO *info) -{ - unsigned char val; - - val = read_reg(info, CHA + MODE); - if (info->params.mode == MGSL_MODE_ASYNC) { - if (info->serial_signals & SerialSignal_RTS) - val &= ~BIT6; - else - val |= BIT6; - } else { - if (info->serial_signals & SerialSignal_RTS) - val |= BIT2; - else - val &= ~BIT2; - } - write_reg(info, CHA + MODE, val); - - if (info->serial_signals & SerialSignal_DTR) - clear_reg_bits(info, CHA + PVR, PVR_DTR); - else - set_reg_bits(info, CHA + PVR, PVR_DTR); -} - -static void rx_reset_buffers(MGSLPC_INFO *info) -{ - RXBUF *buf; - int i; - - info->rx_put = 0; - info->rx_get = 0; - info->rx_frame_count = 0; - for (i=0 ; i < info->rx_buf_count ; i++) { - buf = (RXBUF*)(info->rx_buf + (i * info->rx_buf_size)); - buf->status = buf->count = 0; - } -} - -/* Attempt to return a received HDLC frame - * Only frames received without errors are returned. - * - * Returns true if frame returned, otherwise false - */ -static bool rx_get_frame(MGSLPC_INFO *info, struct tty_struct *tty) -{ - unsigned short status; - RXBUF *buf; - unsigned int framesize = 0; - unsigned long flags; - bool return_frame = false; - - if (info->rx_frame_count == 0) - return false; - - buf = (RXBUF*)(info->rx_buf + (info->rx_get * info->rx_buf_size)); - - status = buf->status; - - /* 07 VFR 1=valid frame - * 06 RDO 1=data overrun - * 05 CRC 1=OK, 0=error - * 04 RAB 1=frame aborted - */ - if ((status & 0xf0) != 0xA0) { - if (!(status & BIT7) || (status & BIT4)) - info->icount.rxabort++; - else if (status & BIT6) - info->icount.rxover++; - else if (!(status & BIT5)) { - info->icount.rxcrc++; - if (info->params.crc_type & HDLC_CRC_RETURN_EX) - return_frame = true; - } - framesize = 0; -#if SYNCLINK_GENERIC_HDLC - { - info->netdev->stats.rx_errors++; - info->netdev->stats.rx_frame_errors++; - } -#endif - } else - return_frame = true; - - if (return_frame) - framesize = buf->count; - - if (debug_level >= DEBUG_LEVEL_BH) - printk("%s(%d):rx_get_frame(%s) status=%04X size=%d\n", - __FILE__, __LINE__, info->device_name, status, framesize); - - if (debug_level >= DEBUG_LEVEL_DATA) - trace_block(info, buf->data, framesize, 0); - - if (framesize) { - if ((info->params.crc_type & HDLC_CRC_RETURN_EX && - framesize+1 > info->max_frame_size) || - framesize > info->max_frame_size) - info->icount.rxlong++; - else { - if (status & BIT5) - info->icount.rxok++; - - if (info->params.crc_type & HDLC_CRC_RETURN_EX) { - *(buf->data + framesize) = status & BIT5 ? RX_OK:RX_CRC_ERROR; - ++framesize; - } - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_rx(info, buf->data, framesize); - else -#endif - ldisc_receive_buf(tty, buf->data, info->flag_buf, framesize); - } - } - - spin_lock_irqsave(&info->lock, flags); - buf->status = buf->count = 0; - info->rx_frame_count--; - info->rx_get++; - if (info->rx_get >= info->rx_buf_count) - info->rx_get = 0; - spin_unlock_irqrestore(&info->lock, flags); - - return true; -} - -static bool register_test(MGSLPC_INFO *info) -{ - static unsigned char patterns[] = - { 0x00, 0xff, 0xaa, 0x55, 0x69, 0x96, 0x0f }; - static unsigned int count = ARRAY_SIZE(patterns); - unsigned int i; - bool rc = true; - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - reset_device(info); - - for (i = 0; i < count; i++) { - write_reg(info, XAD1, patterns[i]); - write_reg(info, XAD2, patterns[(i + 1) % count]); - if ((read_reg(info, XAD1) != patterns[i]) || - (read_reg(info, XAD2) != patterns[(i + 1) % count])) { - rc = false; - break; - } - } - - spin_unlock_irqrestore(&info->lock, flags); - return rc; -} - -static bool irq_test(MGSLPC_INFO *info) -{ - unsigned long end_time; - unsigned long flags; - - spin_lock_irqsave(&info->lock, flags); - reset_device(info); - - info->testing_irq = true; - hdlc_mode(info); - - info->irq_occurred = false; - - /* init hdlc mode */ - - irq_enable(info, CHA, IRQ_TIMER); - write_reg(info, CHA + TIMR, 0); /* 512 cycles */ - issue_command(info, CHA, CMD_START_TIMER); - - spin_unlock_irqrestore(&info->lock, flags); - - end_time=100; - while(end_time-- && !info->irq_occurred) { - msleep_interruptible(10); - } - - info->testing_irq = false; - - spin_lock_irqsave(&info->lock, flags); - reset_device(info); - spin_unlock_irqrestore(&info->lock, flags); - - return info->irq_occurred; -} - -static int adapter_test(MGSLPC_INFO *info) -{ - if (!register_test(info)) { - info->init_error = DiagStatus_AddressFailure; - printk("%s(%d):Register test failure for device %s Addr=%04X\n", - __FILE__, __LINE__, info->device_name, (unsigned short)(info->io_base)); - return -ENODEV; - } - - if (!irq_test(info)) { - info->init_error = DiagStatus_IrqFailure; - printk("%s(%d):Interrupt test failure for device %s IRQ=%d\n", - __FILE__, __LINE__, info->device_name, (unsigned short)(info->irq_level)); - return -ENODEV; - } - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):device %s passed diagnostics\n", - __FILE__, __LINE__, info->device_name); - return 0; -} - -static void trace_block(MGSLPC_INFO *info,const char* data, int count, int xmit) -{ - int i; - int linecount; - if (xmit) - printk("%s tx data:\n", info->device_name); - else - printk("%s rx data:\n", info->device_name); - - while(count) { - if (count > 16) - linecount = 16; - else - linecount = count; - - for(i=0;i=040 && data[i]<=0176) - printk("%c", data[i]); - else - printk("."); - } - printk("\n"); - - data += linecount; - count -= linecount; - } -} - -/* HDLC frame time out - * update stats and do tx completion processing - */ -static void tx_timeout(struct timer_list *t) -{ - MGSLPC_INFO *info = from_timer(info, t, tx_timer); - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s(%d):tx_timeout(%s)\n", - __FILE__, __LINE__, info->device_name); - if (info->tx_active && - info->params.mode == MGSL_MODE_HDLC) { - info->icount.txtimeout++; - } - spin_lock_irqsave(&info->lock, flags); - info->tx_active = false; - info->tx_count = info->tx_put = info->tx_get = 0; - - spin_unlock_irqrestore(&info->lock, flags); - -#if SYNCLINK_GENERIC_HDLC - if (info->netcount) - hdlcdev_tx_done(info); - else -#endif - { - struct tty_struct *tty = tty_port_tty_get(&info->port); - bh_transmit(info, tty); - tty_kref_put(tty); - } -} - -#if SYNCLINK_GENERIC_HDLC - -/* - * called by generic HDLC layer when protocol selected (PPP, frame relay, etc.) - * set encoding and frame check sequence (FCS) options - * - * dev pointer to network device structure - * encoding serial encoding setting - * parity FCS setting - * - * returns 0 if success, otherwise error code - */ -static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, - unsigned short parity) -{ - MGSLPC_INFO *info = dev_to_port(dev); - struct tty_struct *tty; - unsigned char new_encoding; - unsigned short new_crctype; - - /* return error if TTY interface open */ - if (info->port.count) - return -EBUSY; - - switch (encoding) - { - case ENCODING_NRZ: new_encoding = HDLC_ENCODING_NRZ; break; - case ENCODING_NRZI: new_encoding = HDLC_ENCODING_NRZI_SPACE; break; - case ENCODING_FM_MARK: new_encoding = HDLC_ENCODING_BIPHASE_MARK; break; - case ENCODING_FM_SPACE: new_encoding = HDLC_ENCODING_BIPHASE_SPACE; break; - case ENCODING_MANCHESTER: new_encoding = HDLC_ENCODING_BIPHASE_LEVEL; break; - default: return -EINVAL; - } - - switch (parity) - { - case PARITY_NONE: new_crctype = HDLC_CRC_NONE; break; - case PARITY_CRC16_PR1_CCITT: new_crctype = HDLC_CRC_16_CCITT; break; - case PARITY_CRC32_PR1_CCITT: new_crctype = HDLC_CRC_32_CCITT; break; - default: return -EINVAL; - } - - info->params.encoding = new_encoding; - info->params.crc_type = new_crctype; - - /* if network interface up, reprogram hardware */ - if (info->netcount) { - tty = tty_port_tty_get(&info->port); - mgslpc_program_hw(info, tty); - tty_kref_put(tty); - } - - return 0; -} - -/* - * called by generic HDLC layer to send frame - * - * skb socket buffer containing HDLC frame - * dev pointer to network device structure - */ -static netdev_tx_t hdlcdev_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - MGSLPC_INFO *info = dev_to_port(dev); - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk(KERN_INFO "%s:hdlc_xmit(%s)\n", __FILE__, dev->name); - - /* stop sending until this frame completes */ - netif_stop_queue(dev); - - /* copy data to device buffers */ - skb_copy_from_linear_data(skb, info->tx_buf, skb->len); - info->tx_get = 0; - info->tx_put = info->tx_count = skb->len; - - /* update network statistics */ - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - - /* done with socket buffer, so free it */ - dev_kfree_skb(skb); - - /* save start time for transmit timeout detection */ - netif_trans_update(dev); - - /* start hardware transmitter if necessary */ - spin_lock_irqsave(&info->lock, flags); - if (!info->tx_active) { - struct tty_struct *tty = tty_port_tty_get(&info->port); - tx_start(info, tty); - tty_kref_put(tty); - } - spin_unlock_irqrestore(&info->lock, flags); - - return NETDEV_TX_OK; -} - -/* - * called by network layer when interface enabled - * claim resources and initialize hardware - * - * dev pointer to network device structure - * - * returns 0 if success, otherwise error code - */ -static int hdlcdev_open(struct net_device *dev) -{ - MGSLPC_INFO *info = dev_to_port(dev); - struct tty_struct *tty; - int rc; - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s:hdlcdev_open(%s)\n", __FILE__, dev->name); - - /* generic HDLC layer open processing */ - rc = hdlc_open(dev); - if (rc != 0) - return rc; - - /* arbitrate between network and tty opens */ - spin_lock_irqsave(&info->netlock, flags); - if (info->port.count != 0 || info->netcount != 0) { - printk(KERN_WARNING "%s: hdlc_open returning busy\n", dev->name); - spin_unlock_irqrestore(&info->netlock, flags); - return -EBUSY; - } - info->netcount=1; - spin_unlock_irqrestore(&info->netlock, flags); - - tty = tty_port_tty_get(&info->port); - /* claim resources and init adapter */ - rc = startup(info, tty); - if (rc != 0) { - tty_kref_put(tty); - spin_lock_irqsave(&info->netlock, flags); - info->netcount=0; - spin_unlock_irqrestore(&info->netlock, flags); - return rc; - } - /* assert RTS and DTR, apply hardware settings */ - info->serial_signals |= SerialSignal_RTS | SerialSignal_DTR; - mgslpc_program_hw(info, tty); - tty_kref_put(tty); - - /* enable network layer transmit */ - netif_trans_update(dev); - netif_start_queue(dev); - - /* inform generic HDLC layer of current DCD status */ - spin_lock_irqsave(&info->lock, flags); - get_signals(info); - spin_unlock_irqrestore(&info->lock, flags); - if (info->serial_signals & SerialSignal_DCD) - netif_carrier_on(dev); - else - netif_carrier_off(dev); - return 0; -} - -/* - * called by network layer when interface is disabled - * shutdown hardware and release resources - * - * dev pointer to network device structure - * - * returns 0 if success, otherwise error code - */ -static int hdlcdev_close(struct net_device *dev) -{ - MGSLPC_INFO *info = dev_to_port(dev); - struct tty_struct *tty = tty_port_tty_get(&info->port); - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s:hdlcdev_close(%s)\n", __FILE__, dev->name); - - netif_stop_queue(dev); - - /* shutdown adapter and release resources */ - shutdown(info, tty); - tty_kref_put(tty); - hdlc_close(dev); - - spin_lock_irqsave(&info->netlock, flags); - info->netcount=0; - spin_unlock_irqrestore(&info->netlock, flags); - - return 0; -} - -/* - * called by network layer to process IOCTL call to network device - * - * dev pointer to network device structure - * ifs pointer to network interface settings structure - * - * returns 0 if success, otherwise error code - */ -static int hdlcdev_wan_ioctl(struct net_device *dev, struct if_settings *ifs) -{ - const size_t size = sizeof(sync_serial_settings); - sync_serial_settings new_line; - sync_serial_settings __user *line = ifs->ifs_ifsu.sync; - MGSLPC_INFO *info = dev_to_port(dev); - unsigned int flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("%s:hdlcdev_ioctl(%s)\n", __FILE__, dev->name); - - /* return error if TTY interface open */ - if (info->port.count) - return -EBUSY; - - memset(&new_line, 0, size); - - switch (ifs->type) { - case IF_GET_IFACE: /* return current sync_serial_settings */ - - ifs->type = IF_IFACE_SYNC_SERIAL; - if (ifs->size < size) { - ifs->size = size; /* data size wanted */ - return -ENOBUFS; - } - - flags = info->params.flags & (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); - - switch (flags){ - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_TXCPIN): new_line.clock_type = CLOCK_EXT; break; - case (HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG): new_line.clock_type = CLOCK_INT; break; - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_BRG): new_line.clock_type = CLOCK_TXINT; break; - case (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_RXCPIN): new_line.clock_type = CLOCK_TXFROMRX; break; - default: new_line.clock_type = CLOCK_DEFAULT; - } - - new_line.clock_rate = info->params.clock_speed; - new_line.loopback = info->params.loopback ? 1:0; - - if (copy_to_user(line, &new_line, size)) - return -EFAULT; - return 0; - - case IF_IFACE_SYNC_SERIAL: /* set sync_serial_settings */ - - if(!capable(CAP_NET_ADMIN)) - return -EPERM; - if (copy_from_user(&new_line, line, size)) - return -EFAULT; - - switch (new_line.clock_type) - { - case CLOCK_EXT: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_TXCPIN; break; - case CLOCK_TXFROMRX: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_RXCPIN; break; - case CLOCK_INT: flags = HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG; break; - case CLOCK_TXINT: flags = HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_TXC_BRG; break; - case CLOCK_DEFAULT: flags = info->params.flags & - (HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); break; - default: return -EINVAL; - } - - if (new_line.loopback != 0 && new_line.loopback != 1) - return -EINVAL; - - info->params.flags &= ~(HDLC_FLAG_RXC_RXCPIN | HDLC_FLAG_RXC_DPLL | - HDLC_FLAG_RXC_BRG | HDLC_FLAG_RXC_TXCPIN | - HDLC_FLAG_TXC_TXCPIN | HDLC_FLAG_TXC_DPLL | - HDLC_FLAG_TXC_BRG | HDLC_FLAG_TXC_RXCPIN); - info->params.flags |= flags; - - info->params.loopback = new_line.loopback; - - if (flags & (HDLC_FLAG_RXC_BRG | HDLC_FLAG_TXC_BRG)) - info->params.clock_speed = new_line.clock_rate; - else - info->params.clock_speed = 0; - - /* if network interface up, reprogram hardware */ - if (info->netcount) { - struct tty_struct *tty = tty_port_tty_get(&info->port); - mgslpc_program_hw(info, tty); - tty_kref_put(tty); - } - return 0; - default: - return hdlc_ioctl(dev, ifs); - } -} - -/* - * called by network layer when transmit timeout is detected - * - * dev pointer to network device structure - */ -static void hdlcdev_tx_timeout(struct net_device *dev, unsigned int txqueue) -{ - MGSLPC_INFO *info = dev_to_port(dev); - unsigned long flags; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("hdlcdev_tx_timeout(%s)\n", dev->name); - - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - - spin_lock_irqsave(&info->lock, flags); - tx_stop(info); - spin_unlock_irqrestore(&info->lock, flags); - - netif_wake_queue(dev); -} - -/* - * called by device driver when transmit completes - * reenable network layer transmit if stopped - * - * info pointer to device instance information - */ -static void hdlcdev_tx_done(MGSLPC_INFO *info) -{ - if (netif_queue_stopped(info->netdev)) - netif_wake_queue(info->netdev); -} - -/* - * called by device driver when frame received - * pass frame to network layer - * - * info pointer to device instance information - * buf pointer to buffer contianing frame data - * size count of data bytes in buf - */ -static void hdlcdev_rx(MGSLPC_INFO *info, char *buf, int size) -{ - struct sk_buff *skb = dev_alloc_skb(size); - struct net_device *dev = info->netdev; - - if (debug_level >= DEBUG_LEVEL_INFO) - printk("hdlcdev_rx(%s)\n", dev->name); - - if (skb == NULL) { - printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", dev->name); - dev->stats.rx_dropped++; - return; - } - - skb_put_data(skb, buf, size); - - skb->protocol = hdlc_type_trans(skb, dev); - - dev->stats.rx_packets++; - dev->stats.rx_bytes += size; - - netif_rx(skb); -} - -static const struct net_device_ops hdlcdev_ops = { - .ndo_open = hdlcdev_open, - .ndo_stop = hdlcdev_close, - .ndo_start_xmit = hdlc_start_xmit, - .ndo_siocwandev = hdlcdev_wan_ioctl, - .ndo_tx_timeout = hdlcdev_tx_timeout, -}; - -/* - * called by device driver when adding device instance - * do generic HDLC initialization - * - * info pointer to device instance information - * - * returns 0 if success, otherwise error code - */ -static int hdlcdev_init(MGSLPC_INFO *info) -{ - int rc; - struct net_device *dev; - hdlc_device *hdlc; - - /* allocate and initialize network and HDLC layer objects */ - - dev = alloc_hdlcdev(info); - if (dev == NULL) { - printk(KERN_ERR "%s:hdlc device allocation failure\n", __FILE__); - return -ENOMEM; - } - - /* for network layer reporting purposes only */ - dev->base_addr = info->io_base; - dev->irq = info->irq_level; - - /* network layer callbacks and settings */ - dev->netdev_ops = &hdlcdev_ops; - dev->watchdog_timeo = 10 * HZ; - dev->tx_queue_len = 50; - - /* generic HDLC layer callbacks and settings */ - hdlc = dev_to_hdlc(dev); - hdlc->attach = hdlcdev_attach; - hdlc->xmit = hdlcdev_xmit; - - /* register objects with HDLC layer */ - rc = register_hdlc_device(dev); - if (rc) { - printk(KERN_WARNING "%s:unable to register hdlc device\n", __FILE__); - free_netdev(dev); - return rc; - } - - info->netdev = dev; - return 0; -} - -/* - * called by device driver when removing device instance - * do generic HDLC cleanup - * - * info pointer to device instance information - */ -static void hdlcdev_exit(MGSLPC_INFO *info) -{ - unregister_hdlc_device(info->netdev); - free_netdev(info->netdev); - info->netdev = NULL; -} - -#endif /* CONFIG_HDLC */ - diff --git a/include/linux/cm4000_cs.h b/include/linux/cm4000_cs.h deleted file mode 100644 index ea4958e07a14..000000000000 --- a/include/linux/cm4000_cs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CM4000_H_ -#define _CM4000_H_ - -#include - - -#define DEVICE_NAME "cmm" -#define MODULE_NAME "cm4000_cs" - -#endif /* _CM4000_H_ */ diff --git a/include/uapi/linux/cm4000_cs.h b/include/uapi/linux/cm4000_cs.h deleted file mode 100644 index c70a62ec8a49..000000000000 --- a/include/uapi/linux/cm4000_cs.h +++ /dev/null @@ -1,64 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI_CM4000_H_ -#define _UAPI_CM4000_H_ - -#include -#include - -#define MAX_ATR 33 - -#define CM4000_MAX_DEV 4 - -/* those two structures are passed via ioctl() from/to userspace. They are - * used by existing userspace programs, so I kepth the awkward "bIFSD" naming - * not to break compilation of userspace apps. -HW */ - -typedef struct atreq { - __s32 atr_len; - unsigned char atr[64]; - __s32 power_act; - unsigned char bIFSD; - unsigned char bIFSC; -} atreq_t; - - -/* what is particularly stupid in the original driver is the arch-dependent - * member sizes. This leads to CONFIG_COMPAT breakage, since 32bit userspace - * will lay out the structure members differently than the 64bit kernel. - * - * I've changed "ptsreq.protocol" from "unsigned long" to "__u32". - * On 32bit this will make no difference. With 64bit kernels, it will make - * 32bit apps work, too. - */ - -typedef struct ptsreq { - __u32 protocol; /*T=0: 2^0, T=1: 2^1*/ - unsigned char flags; - unsigned char pts1; - unsigned char pts2; - unsigned char pts3; -} ptsreq_t; - -#define CM_IOC_MAGIC 'c' -#define CM_IOC_MAXNR 255 - -#define CM_IOCGSTATUS _IOR (CM_IOC_MAGIC, 0, unsigned char *) -#define CM_IOCGATR _IOWR(CM_IOC_MAGIC, 1, atreq_t *) -#define CM_IOCSPTS _IOW (CM_IOC_MAGIC, 2, ptsreq_t *) -#define CM_IOCSRDR _IO (CM_IOC_MAGIC, 3) -#define CM_IOCARDOFF _IO (CM_IOC_MAGIC, 4) - -#define CM_IOSDBGLVL _IOW(CM_IOC_MAGIC, 250, int*) - -/* card and device states */ -#define CM_CARD_INSERTED 0x01 -#define CM_CARD_POWERED 0x02 -#define CM_ATR_PRESENT 0x04 -#define CM_ATR_VALID 0x08 -#define CM_STATE_VALID 0x0f -/* extra info only from CM4000 */ -#define CM_NO_READER 0x10 -#define CM_BAD_CARD 0x20 - - -#endif /* _UAPI_CM4000_H_ */ -- GitLab From 81773c98a808ee9881e2c503d6b9a5316c130694 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 27 Feb 2023 03:17:37 +0000 Subject: [PATCH 0221/5631] firmware: dmi-sysfs: make kobj_type structures constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definitions to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230227-kobj_type-firmware-dmi-v1-1-d1131d4e7a2b@weissschuh.net Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/dmi-sysfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/dmi-sysfs.c b/drivers/firmware/dmi-sysfs.c index ed5aff0a4204..03708ab64e56 100644 --- a/drivers/firmware/dmi-sysfs.c +++ b/drivers/firmware/dmi-sysfs.c @@ -304,7 +304,7 @@ static struct attribute *dmi_sysfs_sel_attrs[] = { }; ATTRIBUTE_GROUPS(dmi_sysfs_sel); -static struct kobj_type dmi_system_event_log_ktype = { +static const struct kobj_type dmi_system_event_log_ktype = { .release = dmi_entry_free, .sysfs_ops = &dmi_sysfs_specialize_attr_ops, .default_groups = dmi_sysfs_sel_groups, @@ -563,7 +563,7 @@ static void dmi_sysfs_entry_release(struct kobject *kobj) kfree(entry); } -static struct kobj_type dmi_sysfs_entry_ktype = { +static const struct kobj_type dmi_sysfs_entry_ktype = { .release = dmi_sysfs_entry_release, .sysfs_ops = &dmi_sysfs_attr_ops, .default_groups = dmi_sysfs_entry_groups, -- GitLab From 7ef1a2c1c9dffa177ecc3ea50b7f5ee63a621137 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Wed, 1 Mar 2023 15:03:08 +0100 Subject: [PATCH 0222/5631] fpga: bridge: fix kernel-doc parameter description Fix the kernel-doc description for the "struct fpga_image_info *info" parameter of the fpga_bridge_get() function. Fixes: 060ac5c8fa7b ("fpga: bridge: kernel-doc fixes") Signed-off-by: Marco Pagani Reviewed-by: Tom Rix Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20230301140309.512578-1-marpagan@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/fpga/fpga-bridge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 5cd40acab5bf..ff4470067ed5 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -115,7 +115,7 @@ static int fpga_bridge_dev_match(struct device *dev, const void *data) /** * fpga_bridge_get - get an exclusive reference to an fpga bridge * @dev: parent device that fpga bridge was registered with - * @info: fpga manager info + * @info: fpga image specific information * * Given a device, get an exclusive reference to an fpga bridge. * -- GitLab From 9263271a61fcb07b8a30379e785391415d10aa72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 2 Mar 2023 10:12:51 +0100 Subject: [PATCH 0223/5631] misc: sram: Improve and simplify clk handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current code tries to get an associated clk, ignores any errors in the process and if there is a clock enables it unconditionally for the whole lifetime of the sram device. Instead use an "optional" variant of devm_clk_get() which handles the case where no clk is needed for the sram device and do proper error handling for the remaining error cases. Also use an "enabled" variant of devm_clk_get() to simplify. With that .probe() is the only function using struct sram_dev::clk, so it can be replaced by a local variable. Signed-off-by: Uwe Kleine-König Reviewed-by: Philipp Zabel Link: https://lore.kernel.org/r/20230302091251.1852454-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/misc/sram.c | 17 +++++------------ drivers/misc/sram.h | 1 - 2 files changed, 5 insertions(+), 13 deletions(-) diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c index f0e7f02605eb..dec92580a42c 100644 --- a/drivers/misc/sram.c +++ b/drivers/misc/sram.c @@ -381,6 +381,7 @@ static int sram_probe(struct platform_device *pdev) struct sram_dev *sram; int ret; struct resource *res; + struct clk *clk; config = of_device_get_match_data(&pdev->dev); @@ -409,16 +410,14 @@ static int sram_probe(struct platform_device *pdev) return PTR_ERR(sram->pool); } - sram->clk = devm_clk_get(sram->dev, NULL); - if (IS_ERR(sram->clk)) - sram->clk = NULL; - else - clk_prepare_enable(sram->clk); + clk = devm_clk_get_optional_enabled(sram->dev, NULL); + if (IS_ERR(clk)) + return PTR_ERR(clk); ret = sram_reserve_regions(sram, platform_get_resource(pdev, IORESOURCE_MEM, 0)); if (ret) - goto err_disable_clk; + return ret; platform_set_drvdata(pdev, sram); @@ -436,9 +435,6 @@ static int sram_probe(struct platform_device *pdev) err_free_partitions: sram_free_partitions(sram); -err_disable_clk: - if (sram->clk) - clk_disable_unprepare(sram->clk); return ret; } @@ -452,9 +448,6 @@ static int sram_remove(struct platform_device *pdev) if (sram->pool && gen_pool_avail(sram->pool) < gen_pool_size(sram->pool)) dev_err(sram->dev, "removed while SRAM allocated\n"); - if (sram->clk) - clk_disable_unprepare(sram->clk); - return 0; } diff --git a/drivers/misc/sram.h b/drivers/misc/sram.h index d2058d8c8f1d..397205b8bf6f 100644 --- a/drivers/misc/sram.h +++ b/drivers/misc/sram.h @@ -27,7 +27,6 @@ struct sram_dev { bool no_memory_wc; struct gen_pool *pool; - struct clk *clk; struct sram_partition *partition; u32 partitions; -- GitLab From b085dbf6c955c34f735cac433f8551832138e154 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:10 -0800 Subject: [PATCH 0224/5631] sgi-xp: simplify sysctl registration Although this driver is a good use case for having a directory that is not other directories and then subdirectories with more entries, the usage of register_sysctl_table() can recurse and increases complexity so to avoid that just split out the registration to each directory with its own entries. register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl() can do the directory creation for you so just use that. Signed-off-by: Luis Chamberlain Reviewed-by: Steve Wahl Link: https://lore.kernel.org/r/20230302204612.782387-6-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/sgi-xp/xpc_main.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index b2c3c22fc13c..6da509d692bb 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT; static int xpc_disengage_min_timelimit; /* = 0 */ static int xpc_disengage_max_timelimit = 120; -static struct ctl_table xpc_sys_xpc_hb_dir[] = { +static struct ctl_table xpc_sys_xpc_hb[] = { { .procname = "hb_interval", .data = &xpc_hb_interval, @@ -112,11 +112,7 @@ static struct ctl_table xpc_sys_xpc_hb_dir[] = { .extra2 = &xpc_hb_check_max_interval}, {} }; -static struct ctl_table xpc_sys_xpc_dir[] = { - { - .procname = "hb", - .mode = 0555, - .child = xpc_sys_xpc_hb_dir}, +static struct ctl_table xpc_sys_xpc[] = { { .procname = "disengage_timelimit", .data = &xpc_disengage_timelimit, @@ -127,14 +123,9 @@ static struct ctl_table xpc_sys_xpc_dir[] = { .extra2 = &xpc_disengage_max_timelimit}, {} }; -static struct ctl_table xpc_sys_dir[] = { - { - .procname = "xpc", - .mode = 0555, - .child = xpc_sys_xpc_dir}, - {} -}; + static struct ctl_table_header *xpc_sysctl; +static struct ctl_table_header *xpc_sysctl_hb; /* non-zero if any remote partition disengage was timed out */ int xpc_disengage_timedout; @@ -1041,6 +1032,8 @@ xpc_do_exit(enum xp_retval reason) if (xpc_sysctl) unregister_sysctl_table(xpc_sysctl); + if (xpc_sysctl_hb) + unregister_sysctl_table(xpc_sysctl_hb); xpc_teardown_partitions(); @@ -1243,7 +1236,8 @@ xpc_init(void) goto out_1; } - xpc_sysctl = register_sysctl_table(xpc_sys_dir); + xpc_sysctl = register_sysctl("xpc", xpc_sys_xpc); + xpc_sysctl_hb = register_sysctl("xpc/hb", xpc_sys_xpc_hb); /* * Fill the partition reserved page with the information needed by @@ -1308,6 +1302,8 @@ xpc_init(void) (void)unregister_die_notifier(&xpc_die_notifier); (void)unregister_reboot_notifier(&xpc_reboot_notifier); out_2: + if (xpc_sysctl_hb) + unregister_sysctl_table(xpc_sysctl_hb); if (xpc_sysctl) unregister_sysctl_table(xpc_sysctl); -- GitLab From 8efc52743ecb5c69d2e4faba965a3e14418c2494 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 15:38:16 -0600 Subject: [PATCH 0225/5631] misc: alcor_pci: Use PCI core to manage ASPM instead of open-coding "priv->ext_config_dev_aspm" was never set to a non-zero value. Therefore, alcor_pci_aspm_ctrl(priv, 1) did nothing, and alcor_pci_aspm_ctrl(priv, 0) always disabled ASPM in the device and the upstream bridge. The driver disabled ASPM in alcor_pci_probe() and alcor_resume(), so it's possible the device doesn't work well when ASPM is enabled. Remove all the ASPM-related code and replace the alcor_pci_aspm_ctrl(0) calls with pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1), which asks the PCI core to disable ASPM. Signed-off-by: Bjorn Helgaas Cc: Oleksij Rempel Reviewed-by: Oleksij Rempel Link: https://lore.kernel.org/r/20230307213816.886308-1-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/alcor_pci.c | 144 +--------------------------- include/linux/alcor_pci.h | 7 -- 2 files changed, 4 insertions(+), 147 deletions(-) diff --git a/drivers/misc/cardreader/alcor_pci.c b/drivers/misc/cardreader/alcor_pci.c index 9080f9f150a2..5b637171c46c 100644 --- a/drivers/misc/cardreader/alcor_pci.c +++ b/drivers/misc/cardreader/alcor_pci.c @@ -95,137 +95,6 @@ u32 alcor_read32be(struct alcor_pci_priv *priv, unsigned int addr) } EXPORT_SYMBOL_GPL(alcor_read32be); -static int alcor_pci_find_cap_offset(struct alcor_pci_priv *priv, - struct pci_dev *pci) -{ - int where; - u8 val8; - u32 val32; - - where = ALCOR_CAP_START_OFFSET; - pci_read_config_byte(pci, where, &val8); - if (!val8) - return 0; - - where = (int)val8; - while (1) { - pci_read_config_dword(pci, where, &val32); - if (val32 == 0xffffffff) { - dev_dbg(priv->dev, "find_cap_offset invalid value %x.\n", - val32); - return 0; - } - - if ((val32 & 0xff) == 0x10) { - dev_dbg(priv->dev, "pcie cap offset: %x\n", where); - return where; - } - - if ((val32 & 0xff00) == 0x00) { - dev_dbg(priv->dev, "pci_find_cap_offset invalid value %x.\n", - val32); - break; - } - where = (int)((val32 >> 8) & 0xff); - } - - return 0; -} - -static void alcor_pci_init_check_aspm(struct alcor_pci_priv *priv) -{ - struct pci_dev *pci; - int where; - u32 val32; - - priv->pdev_cap_off = alcor_pci_find_cap_offset(priv, priv->pdev); - /* - * A device might be attached to root complex directly and - * priv->parent_pdev will be NULL. In this case we don't check its - * capability and disable ASPM completely. - */ - if (priv->parent_pdev) - priv->parent_cap_off = alcor_pci_find_cap_offset(priv, - priv->parent_pdev); - - if ((priv->pdev_cap_off == 0) || (priv->parent_cap_off == 0)) { - dev_dbg(priv->dev, "pci_cap_off: %x, parent_cap_off: %x\n", - priv->pdev_cap_off, priv->parent_cap_off); - return; - } - - /* link capability */ - pci = priv->pdev; - where = priv->pdev_cap_off + ALCOR_PCIE_LINK_CAP_OFFSET; - pci_read_config_dword(pci, where, &val32); - priv->pdev_aspm_cap = (u8)(val32 >> 10) & 0x03; - - pci = priv->parent_pdev; - where = priv->parent_cap_off + ALCOR_PCIE_LINK_CAP_OFFSET; - pci_read_config_dword(pci, where, &val32); - priv->parent_aspm_cap = (u8)(val32 >> 10) & 0x03; - - if (priv->pdev_aspm_cap != priv->parent_aspm_cap) { - u8 aspm_cap; - - dev_dbg(priv->dev, "pdev_aspm_cap: %x, parent_aspm_cap: %x\n", - priv->pdev_aspm_cap, priv->parent_aspm_cap); - aspm_cap = priv->pdev_aspm_cap & priv->parent_aspm_cap; - priv->pdev_aspm_cap = aspm_cap; - priv->parent_aspm_cap = aspm_cap; - } - - dev_dbg(priv->dev, "ext_config_dev_aspm: %x, pdev_aspm_cap: %x\n", - priv->ext_config_dev_aspm, priv->pdev_aspm_cap); - priv->ext_config_dev_aspm &= priv->pdev_aspm_cap; -} - -static void alcor_pci_aspm_ctrl(struct alcor_pci_priv *priv, u8 aspm_enable) -{ - struct pci_dev *pci; - u8 aspm_ctrl, i; - int where; - u32 val32; - - if ((!priv->pdev_cap_off) || (!priv->parent_cap_off)) { - dev_dbg(priv->dev, "pci_cap_off: %x, parent_cap_off: %x\n", - priv->pdev_cap_off, priv->parent_cap_off); - return; - } - - if (!priv->pdev_aspm_cap) - return; - - aspm_ctrl = 0; - if (aspm_enable) { - aspm_ctrl = priv->ext_config_dev_aspm; - - if (!aspm_ctrl) { - dev_dbg(priv->dev, "aspm_ctrl == 0\n"); - return; - } - } - - for (i = 0; i < 2; i++) { - - if (i) { - pci = priv->parent_pdev; - where = priv->parent_cap_off - + ALCOR_PCIE_LINK_CTRL_OFFSET; - } else { - pci = priv->pdev; - where = priv->pdev_cap_off - + ALCOR_PCIE_LINK_CTRL_OFFSET; - } - - pci_read_config_dword(pci, where, &val32); - val32 &= (~0x03); - val32 |= (aspm_ctrl & priv->pdev_aspm_cap); - pci_write_config_byte(pci, where, (u8)val32); - } - -} - static inline void alcor_mask_sd_irqs(struct alcor_pci_priv *priv) { alcor_write32(priv, 0, AU6601_REG_INT_ENABLE); @@ -308,7 +177,6 @@ static int alcor_pci_probe(struct pci_dev *pdev, pci_set_master(pdev); pci_set_drvdata(pdev, priv); - alcor_pci_init_check_aspm(priv); for (i = 0; i < ARRAY_SIZE(alcor_pci_cells); i++) { alcor_pci_cells[i].platform_data = priv; @@ -319,7 +187,7 @@ static int alcor_pci_probe(struct pci_dev *pdev, if (ret < 0) goto error_clear_drvdata; - alcor_pci_aspm_ctrl(priv, 0); + pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); return 0; @@ -339,8 +207,6 @@ static void alcor_pci_remove(struct pci_dev *pdev) priv = pci_get_drvdata(pdev); - alcor_pci_aspm_ctrl(priv, 1); - mfd_remove_devices(&pdev->dev); ida_free(&alcor_pci_idr, priv->id); @@ -353,18 +219,16 @@ static void alcor_pci_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int alcor_suspend(struct device *dev) { - struct alcor_pci_priv *priv = dev_get_drvdata(dev); - - alcor_pci_aspm_ctrl(priv, 1); return 0; } static int alcor_resume(struct device *dev) { - struct alcor_pci_priv *priv = dev_get_drvdata(dev); - alcor_pci_aspm_ctrl(priv, 0); + pci_disable_link_state(priv->pdev, + PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); + return 0; } #endif /* CONFIG_PM_SLEEP */ diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index 8274ed525e9f..c4a0b23846d8 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -268,13 +268,6 @@ struct alcor_pci_priv { unsigned long id; /* idr id */ struct alcor_dev_cfg *cfg; - - /* PCI ASPM related vars */ - int pdev_cap_off; - u8 pdev_aspm_cap; - int parent_cap_off; - u8 parent_aspm_cap; - u8 ext_config_dev_aspm; }; void alcor_write8(struct alcor_pci_priv *priv, u8 val, unsigned int addr); -- GitLab From 1a0aae883093f304c4dac441d527a893eb840c5d Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 14:24:35 -0600 Subject: [PATCH 0226/5631] misc: genwqe: Drop redundant pci_enable_pcie_error_reporting() pci_enable_pcie_error_reporting() enables the device to send ERR_* Messages. Since f26e58bf6f54 ("PCI/AER: Enable error reporting when AER is native"), the PCI core does this for all devices during enumeration, so the driver doesn't need to do it itself. Remove the redundant pci_enable_pcie_error_reporting() call from the driver. Note that this only controls ERR_* Messages from the device. An ERR_* Message may cause the Root Port to generate an interrupt, depending on the AER Root Error Command register managed by the AER service driver. Signed-off-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20230307202435.880921-1-helgaas@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/genwqe/card_base.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c index 5b63d179b24e..4829bc2208d6 100644 --- a/drivers/misc/genwqe/card_base.c +++ b/drivers/misc/genwqe/card_base.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -1099,7 +1098,6 @@ static int genwqe_pci_setup(struct genwqe_dev *cd) } pci_set_master(pci_dev); - pci_enable_pcie_error_reporting(pci_dev); /* EEH recovery requires PCIe fundamental reset */ pci_dev->needs_freset = 1; -- GitLab From 8f118f61540e23fb0e4ec84aec361f6758dbe93a Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Fri, 24 Feb 2023 17:37:37 +0530 Subject: [PATCH 0227/5631] firmware: xilinx: Add pm api function for PL config reg readback Adds PM API for performing Programmable Logic(PL) configuration register readback. It provides an interface to the firmware(pmufw) to readback the FPGA configuration register. Signed-off-by: Nava kishore Manne Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20230224120738.329416-2-nava.kishore.manne@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/xilinx/zynqmp.c | 33 ++++++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 11 ++++++++++ 2 files changed, 44 insertions(+) diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index acd83d29c866..3b3ffb223c4c 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -971,6 +971,39 @@ int zynqmp_pm_fpga_get_status(u32 *value) } EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_status); +/** + * zynqmp_pm_fpga_get_config_status - Get the FPGA configuration status. + * @value: Buffer to store FPGA configuration status. + * + * This function provides access to the pmufw to get the FPGA configuration + * status + * + * Return: 0 on success, a negative value on error + */ +int zynqmp_pm_fpga_get_config_status(u32 *value) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + u32 buf, lower_addr, upper_addr; + int ret; + + if (!value) + return -EINVAL; + + lower_addr = lower_32_bits((u64)&buf); + upper_addr = upper_32_bits((u64)&buf); + + ret = zynqmp_pm_invoke_fn(PM_FPGA_READ, + XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET, + lower_addr, upper_addr, + XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG, + ret_payload); + + *value = ret_payload[1]; + + return ret; +} +EXPORT_SYMBOL_GPL(zynqmp_pm_fpga_get_config_status); + /** * zynqmp_pm_pinctrl_request - Request Pin from firmware * @pin: Pin number to request diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0e4c70987e6a..f5da51677069 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -71,6 +71,10 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* FPGA Status Reg */ +#define XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET 7U +#define XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG 0U + /* * Node IDs for the Error Events. */ @@ -124,6 +128,7 @@ enum pm_api_id { PM_CLOCK_GETRATE = 42, PM_CLOCK_SETPARENT = 43, PM_CLOCK_GETPARENT = 44, + PM_FPGA_READ = 46, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -519,6 +524,7 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_fpga_get_config_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); @@ -725,6 +731,11 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) return -ENODEV; } +static inline int zynqmp_pm_fpga_get_config_status(u32 *value) +{ + return -ENODEV; +} + static inline int zynqmp_pm_write_ggs(u32 index, u32 value) { return -ENODEV; -- GitLab From 995a3bb72101e7492572d48936cea0fa14c8b794 Mon Sep 17 00:00:00 2001 From: Nava kishore Manne Date: Fri, 24 Feb 2023 17:37:38 +0530 Subject: [PATCH 0228/5631] fpga: zynqmp-fpga: Adds status interface Adds status interface for zynqmp-fpga. It's a read only interface which allows the user to get the Programmable Logic(PL) configuration status. Usage: To read the Programmable Logic(PL) configuration status. cat /sys/bus/platform/drivers/zynqmp_fpga_manager/firmware:zynqmp-firmware:pcap/status Signed-off-by: Nava kishore Manne Acked-by: Xu Yilun Link: https://lore.kernel.org/r/20230224120738.329416-3-nava.kishore.manne@amd.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-driver-zynqmp-fpga | 73 +++++++++++++++++++ drivers/fpga/zynqmp-fpga.c | 21 ++++++ 2 files changed, 94 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-driver-zynqmp-fpga diff --git a/Documentation/ABI/testing/sysfs-driver-zynqmp-fpga b/Documentation/ABI/testing/sysfs-driver-zynqmp-fpga new file mode 100644 index 000000000000..8f93d27b6d91 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-zynqmp-fpga @@ -0,0 +1,73 @@ +What: /sys/bus/platform/drivers/zynqmp_fpga_manager/firmware:zynqmp-firmware:pcap/status +Date: February 2023 +KernelVersion: 6.4 +Contact: Nava kishore Manne +Description: (RO) Read fpga status. + Read returns a hexadecimal value that tells the current status + of the FPGA device. Each bit position in the status value is + described Below(see ug570 chapter 9). + https://docs.xilinx.com/v/u/en-US/ug570-ultrascale-configuration + + ====================== ============================================== + BIT(0) 0: No CRC error + 1: CRC error + + BIT(1) 0: Decryptor security not set + 1: Decryptor security set + + BIT(2) 0: MMCMs/PLLs are not locked + 1: MMCMs/PLLs are locked + + BIT(3) 0: DCI not matched + 1: DCI matched + + BIT(4) 0: Start-up sequence has not finished + 1: Start-up sequence has finished + + BIT(5) 0: All I/Os are placed in High-Z state + 1: All I/Os behave as configured + + BIT(6) 0: Flip-flops and block RAM are write disabled + 1: Flip-flops and block RAM are write enabled + + BIT(7) 0: GHIGH_B_STATUS asserted + 1: GHIGH_B_STATUS deasserted + + BIT(8) to BIT(10) Status of the mode pins + + BIT(11) 0: Initialization has not finished + 1: Initialization finished + + BIT(12) Value on INIT_B_PIN pin + + BIT(13) 0: Signal not released + 1: Signal released + + BIT(14) Value on DONE_PIN pin. + + BIT(15) 0: No IDCODE_ERROR + 1: IDCODE_ERROR + + BIT(16) 0: No SECURITY_ERROR + 1: SECURITY_ERROR + + BIT(17) System Monitor over-temperature if set + + BIT(18) to BIT(20) Start-up state machine (0 to 7) + Phase 0 = 000 + Phase 1 = 001 + Phase 2 = 011 + Phase 3 = 010 + Phase 4 = 110 + Phase 5 = 111 + Phase 6 = 101 + Phase 7 = 100 + + BIT(25) to BIT(26) Indicates the detected bus width + 00 = x1 + 01 = x8 + 10 = x16 + 11 = x32 + ====================== ============================================== + + The other bits are reserved. diff --git a/drivers/fpga/zynqmp-fpga.c b/drivers/fpga/zynqmp-fpga.c index c60f20949c47..f3434e2c487b 100644 --- a/drivers/fpga/zynqmp-fpga.c +++ b/drivers/fpga/zynqmp-fpga.c @@ -77,6 +77,26 @@ static enum fpga_mgr_states zynqmp_fpga_ops_state(struct fpga_manager *mgr) return FPGA_MGR_STATE_UNKNOWN; } +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u32 status; + int ret; + + ret = zynqmp_pm_fpga_get_config_status(&status); + if (ret) + return ret; + + return sysfs_emit(buf, "0x%x\n", status); +} +static DEVICE_ATTR_RO(status); + +static struct attribute *zynqmp_fpga_attrs[] = { + &dev_attr_status.attr, + NULL, +}; +ATTRIBUTE_GROUPS(zynqmp_fpga); + static const struct fpga_manager_ops zynqmp_fpga_ops = { .state = zynqmp_fpga_ops_state, .write_init = zynqmp_fpga_ops_write_init, @@ -113,6 +133,7 @@ static struct platform_driver zynqmp_fpga_driver = { .driver = { .name = "zynqmp_fpga_manager", .of_match_table = of_match_ptr(zynqmp_fpga_of_match), + .dev_groups = zynqmp_fpga_groups, }, }; -- GitLab From 1274b37ab31211beb0f1c6e12e059d6b58a6e40a Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 23 Feb 2023 14:32:52 +0100 Subject: [PATCH 0229/5631] misc: microchip: pci1xxxx: Convert to immutable irqchip Convert the driver to immutable irq-chip with a bit of intuition. Cc: linux-gpio@vger.kernel.org Cc: Marc Zyngier Signed-off-by: Linus Walleij Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20230223133252.2257276-1-linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c index 3389803cb281..e616e3ec2b42 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c @@ -175,9 +175,13 @@ static void pci1xxxx_gpio_irq_set_mask(struct irq_data *data, bool set) unsigned int gpio = irqd_to_hwirq(data); unsigned long flags; + if (!set) + gpiochip_enable_irq(chip, gpio); spin_lock_irqsave(&priv->lock, flags); pci1xxx_assign_bit(priv->reg_base, INTR_MASK_OFFSET(gpio), (gpio % 32), set); spin_unlock_irqrestore(&priv->lock, flags); + if (set) + gpiochip_disable_irq(chip, gpio); } static void pci1xxxx_gpio_irq_mask(struct irq_data *data) @@ -283,12 +287,14 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irq_chip pci1xxxx_gpio_irqchip = { +static const struct irq_chip pci1xxxx_gpio_irqchip = { .name = "pci1xxxx_gpio", .irq_ack = pci1xxxx_gpio_irq_ack, .irq_mask = pci1xxxx_gpio_irq_mask, .irq_unmask = pci1xxxx_gpio_irq_unmask, .irq_set_type = pci1xxxx_gpio_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; static int pci1xxxx_gpio_suspend(struct device *dev) @@ -351,7 +357,7 @@ static int pci1xxxx_gpio_setup(struct pci1xxxx_gpio *priv, int irq) return retval; girq = &priv->gpio.irq; - girq->chip = &pci1xxxx_gpio_irqchip; + gpio_irq_chip_set_chip(girq, &pci1xxxx_gpio_irqchip); girq->parent_handler = NULL; girq->num_parents = 0; girq->parents = NULL; -- GitLab From f0312cbd2af1c458a8441bb7364133d8242446b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 27 Feb 2023 03:14:02 +0000 Subject: [PATCH 0230/5631] edd: make kobj_type structure constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230227-kobj_type-firmware-edd-v1-1-c626afe5bd05@weissschuh.net Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/edd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/edd.c b/drivers/firmware/edd.c index 5cc238916551..55dec4eb2c00 100644 --- a/drivers/firmware/edd.c +++ b/drivers/firmware/edd.c @@ -608,7 +608,7 @@ static void edd_release(struct kobject * kobj) kfree(dev); } -static struct kobj_type edd_ktype = { +static const struct kobj_type edd_ktype = { .release = edd_release, .sysfs_ops = &edd_attr_ops, }; -- GitLab From ac3b43283923440900b4f36ca5f9f0b1ca43b70e Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 6 Feb 2023 16:28:02 -0800 Subject: [PATCH 0231/5631] module: replace module_layout with module_memory module_layout manages different types of memory (text, data, rodata, etc.) in one allocation, which is problematic for some reasons: 1. It is hard to enable CONFIG_STRICT_MODULE_RWX. 2. It is hard to use huge pages in modules (and not break strict rwx). 3. Many archs uses module_layout for arch-specific data, but it is not obvious how these data are used (are they RO, RX, or RW?) Improve the scenario by replacing 2 (or 3) module_layout per module with up to 7 module_memory per module: MOD_TEXT, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, and allocating them separately. This adds slightly more entries to mod_tree (from up to 3 entries per module, to up to 7 entries per module). However, this at most adds a small constant overhead to __module_address(), which is expected to be fast. Various archs use module_layout for different data. These data are put into different module_memory based on their location in module_layout. IOW, data that used to go with text is allocated with MOD_MEM_TYPE_TEXT; data that used to go with data is allocated with MOD_MEM_TYPE_DATA, etc. module_memory simplifies quite some of the module code. For example, ARCH_WANTS_MODULES_DATA_IN_VMALLOC is a lot cleaner, as it just uses a different allocator for the data. kernel/module/strict_rwx.c is also much cleaner with module_memory. Signed-off-by: Song Liu Cc: Luis Chamberlain Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Guenter Roeck Cc: Christophe Leroy Reviewed-by: Thomas Gleixner Reviewed-by: Christophe Leroy Reviewed-by: Luis Chamberlain Signed-off-by: Luis Chamberlain --- arch/arc/kernel/unwind.c | 12 +- arch/arm/kernel/module-plts.c | 9 +- arch/arm64/kernel/module-plts.c | 13 +- arch/ia64/kernel/module.c | 24 +- arch/mips/kernel/vpe.c | 11 +- arch/parisc/kernel/module.c | 51 ++--- arch/powerpc/kernel/module_32.c | 7 +- arch/s390/kernel/module.c | 26 ++- arch/x86/kernel/callthunks.c | 4 +- arch/x86/kernel/module.c | 4 +- include/linux/module.h | 89 +++++--- kernel/module/internal.h | 40 ++-- kernel/module/kallsyms.c | 58 ++--- kernel/module/kdb.c | 17 +- kernel/module/main.c | 375 ++++++++++++++++---------------- kernel/module/procfs.c | 16 +- kernel/module/strict_rwx.c | 99 ++------- kernel/module/tree_lookup.c | 39 ++-- 18 files changed, 427 insertions(+), 467 deletions(-) diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 200270a94558..9270d0a713c3 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -369,6 +369,8 @@ void *unwind_add_table(struct module *module, const void *table_start, unsigned long table_size) { struct unwind_table *table; + struct module_memory *core_text; + struct module_memory *init_text; if (table_size <= 0) return NULL; @@ -377,11 +379,11 @@ void *unwind_add_table(struct module *module, const void *table_start, if (!table) return NULL; - init_unwind_table(table, module->name, - module->core_layout.base, module->core_layout.size, - module->init_layout.base, module->init_layout.size, - table_start, table_size, - NULL, 0); + core_text = &module->mem[MOD_TEXT]; + init_text = &module->mem[MOD_INIT_TEXT]; + + init_unwind_table(table, module->name, core_text->base, core_text->size, + init_text->base, init_text->size, table_start, table_size, NULL, 0); init_unwind_hdr(table, unw_hdr_alloc); diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c index af7c322ebed6..f5a43fd8c163 100644 --- a/arch/arm/kernel/module-plts.c +++ b/arch/arm/kernel/module-plts.c @@ -28,11 +28,6 @@ static const u32 fixed_plts[] = { #endif }; -static bool in_init(const struct module *mod, unsigned long loc) -{ - return loc - (u32)mod->init_layout.base < mod->init_layout.size; -} - static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt) { int i; @@ -50,8 +45,8 @@ static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt) u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) { - struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : - &mod->arch.init; + struct mod_plt_sec *pltsec = !within_module_init(loc, mod) ? + &mod->arch.core : &mod->arch.init; struct plt_entries *plt; int idx; diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 5a0a8f552a61..543493bf924d 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -65,17 +65,12 @@ static bool plt_entries_equal(const struct plt_entry *a, (q + aarch64_insn_adrp_get_offset(le32_to_cpu(b->adrp))); } -static bool in_init(const struct module *mod, void *loc) -{ - return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size; -} - u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, void *loc, const Elf64_Rela *rela, Elf64_Sym *sym) { - struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : - &mod->arch.init; + struct mod_plt_sec *pltsec = !within_module_init((unsigned long)loc, mod) ? + &mod->arch.core : &mod->arch.init; struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries; int j = i - 1; @@ -105,8 +100,8 @@ u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs, void *loc, u64 val) { - struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : - &mod->arch.init; + struct mod_plt_sec *pltsec = !within_module_init((unsigned long)loc, mod) ? + &mod->arch.core : &mod->arch.init; struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries++; u32 br; diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 8f62cf97f691..3661135da9d9 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -485,19 +485,19 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, return 0; } -static inline int +static inline bool in_init (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->init_layout.base < mod->init_layout.size; + return within_module_init(addr, mod); } -static inline int +static inline bool in_core (const struct module *mod, uint64_t addr) { - return addr - (uint64_t) mod->core_layout.base < mod->core_layout.size; + return within_module_core(addr, mod); } -static inline int +static inline bool is_internal (const struct module *mod, uint64_t value) { return in_init(mod, value) || in_core(mod, value); @@ -677,7 +677,8 @@ do_reloc (struct module *mod, uint8_t r_type, Elf64_Sym *sym, uint64_t addend, break; case RV_BDREL: - val -= (uint64_t) (in_init(mod, val) ? mod->init_layout.base : mod->core_layout.base); + val -= (uint64_t) (in_init(mod, val) ? mod->mem[MOD_INIT_TEXT].base : + mod->mem[MOD_TEXT].base); break; case RV_LTV: @@ -812,15 +813,18 @@ apply_relocate_add (Elf64_Shdr *sechdrs, const char *strtab, unsigned int symind * addresses have been selected... */ uint64_t gp; - if (mod->core_layout.size > MAX_LTOFF) + struct module_memory *mod_mem; + + mod_mem = &mod->mem[MOD_DATA]; + if (mod_mem->size > MAX_LTOFF) /* * This takes advantage of fact that SHF_ARCH_SMALL gets allocated * at the end of the module. */ - gp = mod->core_layout.size - MAX_LTOFF / 2; + gp = mod_mem->size - MAX_LTOFF / 2; else - gp = mod->core_layout.size / 2; - gp = (uint64_t) mod->core_layout.base + ((gp + 7) & -8); + gp = mod_mem->size / 2; + gp = (uint64_t) mod_mem->base + ((gp + 7) & -8); mod->arch.gp = gp; DEBUGP("%s: placing gp at 0x%lx\n", __func__, gp); } diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 13294972707b..ab114c686f9d 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -199,18 +199,17 @@ static void layout_sections(struct module *mod, const Elf_Ehdr *hdr, for (m = 0; m < ARRAY_SIZE(masks); ++m) { for (i = 0; i < hdr->e_shnum; ++i) { Elf_Shdr *s = &sechdrs[i]; + struct module_memory *mod_mem; + + mod_mem = &mod->mem[MOD_TEXT]; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL) continue; s->sh_entsize = - get_offset((unsigned long *)&mod->core_layout.size, s); + get_offset((unsigned long *)&mod_mem->size, s); } - - if (m == 0) - mod->core_layout.text_size = mod->core_layout.size; - } } @@ -641,7 +640,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.core_layout.size); + v->load_addr = alloc_progmem(mod.mod_mem[MOD_TEXT].size); if (!v->load_addr) return -ENOMEM; diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 7df140545b22..f6e38c4d3904 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -27,9 +27,9 @@ * We are not doing SEGREL32 handling correctly. According to the ABI, we * should do a value offset, like this: * if (in_init(me, (void *)val)) - * val -= (uint32_t)me->init_layout.base; + * val -= (uint32_t)me->mem[MOD_INIT_TEXT].base; * else - * val -= (uint32_t)me->core_layout.base; + * val -= (uint32_t)me->mem[MOD_TEXT].base; * However, SEGREL32 is used only for PARISC unwind entries, and we want * those entries to have an absolute address, and not just an offset. * @@ -76,25 +76,6 @@ * allows us to allocate up to 4095 GOT entries. */ #define MAX_GOTS 4095 -/* three functions to determine where in the module core - * or init pieces the location is */ -static inline int in_init(struct module *me, void *loc) -{ - return (loc >= me->init_layout.base && - loc <= (me->init_layout.base + me->init_layout.size)); -} - -static inline int in_core(struct module *me, void *loc) -{ - return (loc >= me->core_layout.base && - loc <= (me->core_layout.base + me->core_layout.size)); -} - -static inline int in_local(struct module *me, void *loc) -{ - return in_init(me, loc) || in_core(me, loc); -} - #ifndef CONFIG_64BIT struct got_entry { Elf32_Addr addr; @@ -302,6 +283,7 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, { unsigned long gots = 0, fdescs = 0, len; unsigned int i; + struct module_memory *mod_mem; len = hdr->e_shnum * sizeof(me->arch.section[0]); me->arch.section = kzalloc(len, GFP_KERNEL); @@ -346,14 +328,15 @@ int module_frob_arch_sections(CONST Elf_Ehdr *hdr, me->arch.section[s].stub_entries += count; } + mod_mem = &me->mem[MOD_TEXT]; /* align things a bit */ - me->core_layout.size = ALIGN(me->core_layout.size, 16); - me->arch.got_offset = me->core_layout.size; - me->core_layout.size += gots * sizeof(struct got_entry); + mod_mem->size = ALIGN(mod_mem->size, 16); + me->arch.got_offset = mod_mem->size; + mod_mem->size += gots * sizeof(struct got_entry); - me->core_layout.size = ALIGN(me->core_layout.size, 16); - me->arch.fdesc_offset = me->core_layout.size; - me->core_layout.size += fdescs * sizeof(Elf_Fdesc); + mod_mem->size = ALIGN(mod_mem->size, 16); + me->arch.fdesc_offset = mod_mem->size; + mod_mem->size += fdescs * sizeof(Elf_Fdesc); me->arch.got_max = gots; me->arch.fdesc_max = fdescs; @@ -371,7 +354,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) BUG_ON(value == 0); - got = me->core_layout.base + me->arch.got_offset; + got = me->mem[MOD_TEXT].base + me->arch.got_offset; for (i = 0; got[i].addr; i++) if (got[i].addr == value) goto out; @@ -389,7 +372,7 @@ static Elf64_Word get_got(struct module *me, unsigned long value, long addend) #ifdef CONFIG_64BIT static Elf_Addr get_fdesc(struct module *me, unsigned long value) { - Elf_Fdesc *fdesc = me->core_layout.base + me->arch.fdesc_offset; + Elf_Fdesc *fdesc = me->mem[MOD_TEXT].base + me->arch.fdesc_offset; if (!value) { printk(KERN_ERR "%s: zero OPD requested!\n", me->name); @@ -407,7 +390,7 @@ static Elf_Addr get_fdesc(struct module *me, unsigned long value) /* Create new one */ fdesc->addr = value; - fdesc->gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; + fdesc->gp = (Elf_Addr)me->mem[MOD_TEXT].base + me->arch.got_offset; return (Elf_Addr)fdesc; } #endif /* CONFIG_64BIT */ @@ -742,7 +725,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, loc, val); val += addend; /* can we reach it locally? */ - if (in_local(me, (void *)val)) { + if (within_module(val, me)) { /* this is the case where the symbol is local * to the module, but in a different section, * so stub the jump in case it's more than 22 @@ -801,7 +784,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, break; case R_PARISC_FPTR64: /* 64-bit function address */ - if(in_local(me, (void *)(val + addend))) { + if (within_module(val + addend, me)) { *loc64 = get_fdesc(me, val+addend); pr_debug("FDESC for %s at %llx points to %llx\n", strtab + sym->st_name, *loc64, @@ -839,7 +822,7 @@ register_unwind_table(struct module *me, table = (unsigned char *)sechdrs[me->arch.unwind_section].sh_addr; end = table + sechdrs[me->arch.unwind_section].sh_size; - gp = (Elf_Addr)me->core_layout.base + me->arch.got_offset; + gp = (Elf_Addr)me->mem[MOD_TEXT].base + me->arch.got_offset; pr_debug("register_unwind_table(), sect = %d at 0x%p - 0x%p (gp=0x%lx)\n", me->arch.unwind_section, table, end, gp); @@ -977,7 +960,7 @@ void module_arch_cleanup(struct module *mod) #ifdef CONFIG_64BIT void *dereference_module_function_descriptor(struct module *mod, void *ptr) { - unsigned long start_opd = (Elf64_Addr)mod->core_layout.base + + unsigned long start_opd = (Elf64_Addr)mod->mem[MOD_TEXT].base + mod->arch.fdesc_offset; unsigned long end_opd = start_opd + mod->arch.fdesc_count * sizeof(Elf64_Fdesc); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index ea6536171778..816a63fd71fb 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -163,8 +163,7 @@ static uint32_t do_plt_call(void *location, pr_debug("Doing plt for call to 0x%x at 0x%x\n", val, (unsigned int)location); /* Init, or core PLT? */ - if (location >= mod->core_layout.base - && location < mod->core_layout.base + mod->core_layout.size) + if (within_module_core((unsigned long)location, mod)) entry = (void *)sechdrs[mod->arch.core_plt_section].sh_addr; else entry = (void *)sechdrs[mod->arch.init_plt_section].sh_addr; @@ -322,14 +321,14 @@ notrace int module_trampoline_target(struct module *mod, unsigned long addr, int module_finalize_ftrace(struct module *module, const Elf_Shdr *sechdrs) { - module->arch.tramp = do_plt_call(module->core_layout.base, + module->arch.tramp = do_plt_call(module->mem[MOD_TEXT].base, (unsigned long)ftrace_caller, sechdrs, module); if (!module->arch.tramp) return -ENOENT; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - module->arch.tramp_regs = do_plt_call(module->core_layout.base, + module->arch.tramp_regs = do_plt_call(module->mem[MOD_TEXT].base, (unsigned long)ftrace_regs_caller, sechdrs, module); if (!module->arch.tramp_regs) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 2d159b32885b..b9dbf0c483ed 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -126,6 +126,7 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, Elf_Rela *rela; char *strings; int nrela, i, j; + struct module_memory *mod_mem; /* Find symbol table and string table. */ symtab = NULL; @@ -173,14 +174,15 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, /* Increase core size by size of got & plt and set start offsets for got and plt. */ - me->core_layout.size = ALIGN(me->core_layout.size, 4); - me->arch.got_offset = me->core_layout.size; - me->core_layout.size += me->arch.got_size; - me->arch.plt_offset = me->core_layout.size; + mod_mem = &me->mem[MOD_TEXT]; + mod_mem->size = ALIGN(mod_mem->size, 4); + me->arch.got_offset = mod_mem->size; + mod_mem->size += me->arch.got_size; + me->arch.plt_offset = mod_mem->size; if (me->arch.plt_size) { if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) me->arch.plt_size += PLT_ENTRY_SIZE; - me->core_layout.size += me->arch.plt_size; + mod_mem->size += me->arch.plt_size; } return 0; } @@ -304,7 +306,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTPLT64: /* 64 bit offset to jump slot. */ case R_390_GOTPLTENT: /* 32 bit rel. offset to jump slot >> 1. */ if (info->got_initialized == 0) { - Elf_Addr *gotent = me->core_layout.base + + Elf_Addr *gotent = me->mem[MOD_TEXT].base + me->arch.got_offset + info->got_offset; @@ -329,7 +331,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, rc = apply_rela_bits(loc, val, 0, 64, 0, write); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { - val += (Elf_Addr) me->core_layout.base - loc; + val += (Elf_Addr) me->mem[MOD_TEXT].base - loc; rc = apply_rela_bits(loc, val, 1, 32, 1, write); } break; @@ -345,7 +347,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, char *plt_base; char *ip; - plt_base = me->core_layout.base + me->arch.plt_offset; + plt_base = me->mem[MOD_TEXT].base + me->arch.plt_offset; ip = plt_base + info->plt_offset; *(int *)insn = 0x0d10e310; /* basr 1,0 */ *(int *)&insn[4] = 0x100c0004; /* lg 1,12(1) */ @@ -375,7 +377,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val - loc + 0xffffUL < 0x1ffffeUL) || (r_type == R_390_PLT32DBL && val - loc + 0xffffffffULL < 0x1fffffffeULL))) - val = (Elf_Addr) me->core_layout.base + + val = (Elf_Addr) me->mem[MOD_TEXT].base + me->arch.plt_offset + info->plt_offset; val += rela->r_addend - loc; @@ -397,7 +399,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTOFF32: /* 32 bit offset to GOT. */ case R_390_GOTOFF64: /* 64 bit offset to GOT. */ val = val + rela->r_addend - - ((Elf_Addr) me->core_layout.base + me->arch.got_offset); + ((Elf_Addr) me->mem[MOD_TEXT].base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) rc = apply_rela_bits(loc, val, 0, 16, 0, write); else if (r_type == R_390_GOTOFF32) @@ -407,7 +409,7 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ - val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + + val = (Elf_Addr) me->mem[MOD_TEXT].base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) rc = apply_rela_bits(loc, val, 1, 32, 0, write); @@ -515,7 +517,7 @@ int module_finalize(const Elf_Ehdr *hdr, !nospec_disable && me->arch.plt_size) { unsigned int *ij; - ij = me->core_layout.base + me->arch.plt_offset + + ij = me->mem[MOD_TEXT].base + me->arch.plt_offset + me->arch.plt_size - PLT_ENTRY_SIZE; ij[0] = 0xc6000000; /* exrl %r0,.+10 */ ij[1] = 0x0005a7f4; /* j . */ diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index ffea98f9064b..22ab13966427 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -330,8 +330,8 @@ void noinline callthunks_patch_module_calls(struct callthunk_sites *cs, struct module *mod) { struct core_text ct = { - .base = (unsigned long)mod->core_layout.base, - .end = (unsigned long)mod->core_layout.base + mod->core_layout.size, + .base = (unsigned long)mod->mem[MOD_TEXT].base, + .end = (unsigned long)mod->mem[MOD_TEXT].base + mod->mem[MOD_TEXT].size, .name = mod->name, }; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 84ad0e61ba6e..b05f62ee2344 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -362,8 +362,8 @@ int module_finalize(const Elf_Ehdr *hdr, } if (locks) { void *lseg = (void *)locks->sh_addr; - void *text = me->core_layout.base; - void *text_end = text + me->core_layout.text_size; + void *text = me->mem[MOD_TEXT].base; + void *text_end = text + me->mem[MOD_TEXT].size; alternatives_smp_module_add(me, me->name, lseg, lseg + locks->sh_size, text, text_end); diff --git a/include/linux/module.h b/include/linux/module.h index 4435ad9439ab..c0593a96e158 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -320,17 +320,47 @@ struct mod_tree_node { struct latch_tree_node node; }; -struct module_layout { - /* The actual code + data. */ +enum mod_mem_type { + MOD_TEXT = 0, + MOD_DATA, + MOD_RODATA, + MOD_RO_AFTER_INIT, + MOD_INIT_TEXT, + MOD_INIT_DATA, + MOD_INIT_RODATA, + + MOD_MEM_NUM_TYPES, + MOD_INVALID = -1, +}; + +#define mod_mem_type_is_init(type) \ + ((type) == MOD_INIT_TEXT || \ + (type) == MOD_INIT_DATA || \ + (type) == MOD_INIT_RODATA) + +#define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) + +#define mod_mem_type_is_text(type) \ + ((type) == MOD_TEXT || \ + (type) == MOD_INIT_TEXT) + +#define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) + +#define mod_mem_type_is_core_data(type) \ + (mod_mem_type_is_core(type) && \ + mod_mem_type_is_data(type)) + +#define for_each_mod_mem_type(type) \ + for (enum mod_mem_type (type) = 0; \ + (type) < MOD_MEM_NUM_TYPES; (type)++) + +#define for_class_mod_mem_type(type, class) \ + for_each_mod_mem_type(type) \ + if (mod_mem_type_is_##class(type)) + +struct module_memory { void *base; - /* Total size. */ unsigned int size; - /* The size of the executable code. */ - unsigned int text_size; - /* Size of RO section of the module (text+rodata) */ - unsigned int ro_size; - /* Size of RO after init section */ - unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -339,9 +369,9 @@ struct module_layout { #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ -#define __module_layout_align ____cacheline_aligned +#define __module_memory_align ____cacheline_aligned #else -#define __module_layout_align +#define __module_memory_align #endif struct mod_kallsyms { @@ -426,12 +456,7 @@ struct module { /* Startup function. */ int (*init)(void); - /* Core layout: rbtree is accessed frequently, so keep together. */ - struct module_layout core_layout __module_layout_align; - struct module_layout init_layout; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - struct module_layout data_layout; -#endif + struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -581,23 +606,35 @@ bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); +static inline bool within_module_mem_type(unsigned long addr, + const struct module *mod, + enum mod_mem_type type) +{ + unsigned long base, size; + + base = (unsigned long)mod->mem[type].base; + size = mod->mem[type].size; + return addr - base < size; +} + static inline bool within_module_core(unsigned long addr, const struct module *mod) { -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - if ((unsigned long)mod->data_layout.base <= addr && - addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) - return true; -#endif - return (unsigned long)mod->core_layout.base <= addr && - addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; + for_class_mod_mem_type(type, core) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->init_layout.base <= addr && - addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; + for_class_mod_mem_type(type, init) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module(unsigned long addr, const struct module *mod) diff --git a/kernel/module/internal.h b/kernel/module/internal.h index 2e2bf236f558..c6c44ceca07a 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -17,27 +17,19 @@ #define ARCH_SHF_SMALL 0 #endif -/* If this is set, the section belongs in the init part of the module */ -#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG - 1)) -/* Maximum number of characters written by module_flags() */ -#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4) - -#ifndef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC -#define data_layout core_layout -#endif - /* - * Modules' sections will be aligned on page boundaries - * to ensure complete separation of code and data, but - * only when CONFIG_STRICT_MODULE_RWX=y + * Use highest 4 bits of sh_entsize to store the mod_mem_type of this + * section. This leaves 28 bits for offset on 32-bit systems, which is + * about 256 MiB (WARN_ON_ONCE if we exceed that). */ -static inline unsigned int strict_align(unsigned int size) -{ - if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - return PAGE_ALIGN(size); - else - return size; -} + +#define SH_ENTSIZE_TYPE_BITS 4 +#define SH_ENTSIZE_TYPE_SHIFT (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS) +#define SH_ENTSIZE_TYPE_MASK ((1UL << SH_ENTSIZE_TYPE_BITS) - 1) +#define SH_ENTSIZE_OFFSET_MASK ((1UL << (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)) - 1) + +/* Maximum number of characters written by module_flags() */ +#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4) extern struct mutex module_mutex; extern struct list_head modules; @@ -101,8 +93,8 @@ int try_to_force_load(struct module *mod, const char *reason); bool find_symbol(struct find_symbol_arg *fsa); struct module *find_module_all(const char *name, size_t len, bool even_unformed); int cmp_name(const void *name, const void *sym); -long module_get_offset(struct module *mod, unsigned int *size, Elf_Shdr *sechdr, - unsigned int section); +long module_get_offset_and_type(struct module *mod, enum mod_mem_type type, + Elf_Shdr *sechdr, unsigned int section); char *module_flags(struct module *mod, char *buf, bool show_state); size_t module_flags_taint(unsigned long taints, char *buf); @@ -190,10 +182,13 @@ struct mod_tree_root { #endif unsigned long addr_min; unsigned long addr_max; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + unsigned long data_addr_min; + unsigned long data_addr_max; +#endif }; extern struct mod_tree_root mod_tree; -extern struct mod_tree_root mod_data_tree; #ifdef CONFIG_MODULES_TREE_LOOKUP void mod_tree_insert(struct module *mod); @@ -224,7 +219,6 @@ void module_enable_nx(const struct module *mod); void module_enable_x(const struct module *mod); int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod); -bool module_check_misalignment(const struct module *mod); #ifdef CONFIG_MODULE_SIG int module_sig_check(struct load_info *info, int flags); diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index ab2376a1be88..8e89f459ffdd 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -78,6 +78,7 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, unsigned int shnum, unsigned int pcpundx) { const Elf_Shdr *sec; + enum mod_mem_type type; if (src->st_shndx == SHN_UNDEF || src->st_shndx >= shnum || @@ -90,11 +91,12 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, #endif sec = sechdrs + src->st_shndx; + type = sec->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; if (!(sec->sh_flags & SHF_ALLOC) #ifndef CONFIG_KALLSYMS_ALL || !(sec->sh_flags & SHF_EXECINSTR) #endif - || (sec->sh_entsize & INIT_OFFSET_MASK)) + || mod_mem_type_is_init(type)) return false; return true; @@ -113,11 +115,13 @@ void layout_symtab(struct module *mod, struct load_info *info) Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; unsigned int i, nsrc, ndst, strtab_size = 0; + struct module_memory *mod_mem_data = &mod->mem[MOD_DATA]; + struct module_memory *mod_mem_init_data = &mod->mem[MOD_INIT_DATA]; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, symsect, - info->index.sym) | INIT_OFFSET_MASK; + symsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA, + symsect, info->index.sym); pr_debug("\t%s\n", info->secstrings + symsect->sh_name); src = (void *)info->hdr + symsect->sh_offset; @@ -134,28 +138,27 @@ void layout_symtab(struct module *mod, struct load_info *info) } /* Append room for core symbols at end of core part. */ - info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); - info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->data_layout.size += strtab_size; + info->symoffs = ALIGN(mod_mem_data->size, symsect->sh_addralign ?: 1); + info->stroffs = mod_mem_data->size = info->symoffs + ndst * sizeof(Elf_Sym); + mod_mem_data->size += strtab_size; /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ - info->core_typeoffs = mod->data_layout.size; - mod->data_layout.size += ndst * sizeof(char); - mod->data_layout.size = strict_align(mod->data_layout.size); + info->core_typeoffs = mod_mem_data->size; + mod_mem_data->size += ndst * sizeof(char); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; - strsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, strsect, - info->index.str) | INIT_OFFSET_MASK; + strsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA, + strsect, info->index.str); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); /* We'll tack temporary mod_kallsyms on the end. */ - mod->init_layout.size = ALIGN(mod->init_layout.size, - __alignof__(struct mod_kallsyms)); - info->mod_kallsyms_init_off = mod->init_layout.size; - mod->init_layout.size += sizeof(struct mod_kallsyms); - info->init_typeoffs = mod->init_layout.size; - mod->init_layout.size += nsrc * sizeof(char); - mod->init_layout.size = strict_align(mod->init_layout.size); + mod_mem_init_data->size = ALIGN(mod_mem_init_data->size, + __alignof__(struct mod_kallsyms)); + info->mod_kallsyms_init_off = mod_mem_init_data->size; + + mod_mem_init_data->size += sizeof(struct mod_kallsyms); + info->init_typeoffs = mod_mem_init_data->size; + mod_mem_init_data->size += nsrc * sizeof(char); } /* @@ -171,9 +174,11 @@ void add_kallsyms(struct module *mod, const struct load_info *info) char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; unsigned long strtab_size; + void *data_base = mod->mem[MOD_DATA].base; + void *init_data_base = mod->mem[MOD_INIT_DATA].base; /* Set up to point into init section. */ - mod->kallsyms = (void __rcu *)mod->init_layout.base + + mod->kallsyms = (void __rcu *)init_data_base + info->mod_kallsyms_init_off; rcu_read_lock(); @@ -183,15 +188,15 @@ void add_kallsyms(struct module *mod, const struct load_info *info) /* Make sure we get permanent strtab: don't use info->strtab. */ rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - rcu_dereference(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + rcu_dereference(mod->kallsyms)->typetab = init_data_base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init * and set types up while we still have access to sections. */ - mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; - mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; - mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; + mod->core_kallsyms.symtab = dst = data_base + info->symoffs; + mod->core_kallsyms.strtab = s = data_base + info->stroffs; + mod->core_kallsyms.typetab = data_base + info->core_typeoffs; strtab_size = info->core_typeoffs - info->stroffs; src = rcu_dereference(mod->kallsyms)->symtab; for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { @@ -267,12 +272,15 @@ static const char *find_kallsyms_symbol(struct module *mod, unsigned int i, best = 0; unsigned long nextval, bestval; struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); + struct module_memory *mod_mem; /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->init_layout.base + mod->init_layout.text_size; + mod_mem = &mod->mem[MOD_INIT_TEXT]; else - nextval = (unsigned long)mod->core_layout.base + mod->core_layout.text_size; + mod_mem = &mod->mem[MOD_TEXT]; + + nextval = (unsigned long)mod_mem->base + mod_mem->size; bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); diff --git a/kernel/module/kdb.c b/kernel/module/kdb.c index f4317f92e189..995c32d3698f 100644 --- a/kernel/module/kdb.c +++ b/kernel/module/kdb.c @@ -26,10 +26,11 @@ int kdb_lsmod(int argc, const char **argv) if (mod->state == MODULE_STATE_UNFORMED) continue; - kdb_printf("%-20s%8u", mod->name, mod->core_layout.size); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - kdb_printf("/%8u", mod->data_layout.size); -#endif + kdb_printf("%-20s%8u", mod->name, mod->mem[MOD_TEXT].size); + kdb_printf("/%8u", mod->mem[MOD_RODATA].size); + kdb_printf("/%8u", mod->mem[MOD_RO_AFTER_INIT].size); + kdb_printf("/%8u", mod->mem[MOD_DATA].size); + kdb_printf(" 0x%px ", (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); @@ -40,10 +41,10 @@ int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%px", mod->core_layout.base); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - kdb_printf("/0x%px", mod->data_layout.base); -#endif + kdb_printf(" 0x%px", mod->mem[MOD_TEXT].base); + kdb_printf("/0x%px", mod->mem[MOD_RODATA].base); + kdb_printf("/0x%px", mod->mem[MOD_RO_AFTER_INIT].base); + kdb_printf("/0x%px", mod->mem[MOD_DATA].base); #ifdef CONFIG_MODULE_UNLOAD { diff --git a/kernel/module/main.c b/kernel/module/main.c index d3be89de706d..2724bc1b9a90 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -80,12 +80,6 @@ struct mod_tree_root mod_tree __cacheline_aligned = { .addr_min = -1UL, }; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC -struct mod_tree_root mod_data_tree __cacheline_aligned = { - .addr_min = -1UL, -}; -#endif - struct symsearch { const struct kernel_symbol *start, *stop; const s32 *crcs; @@ -93,14 +87,24 @@ struct symsearch { }; /* - * Bounds of module text, for speeding up __module_address. + * Bounds of module memory, for speeding up __module_address. * Protected by module_mutex. */ -static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_root *tree) +static void __mod_update_bounds(enum mod_mem_type type __maybe_unused, void *base, + unsigned int size, struct mod_tree_root *tree) { unsigned long min = (unsigned long)base; unsigned long max = min + size; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + if (mod_mem_type_is_core_data(type)) { + if (min < tree->data_addr_min) + tree->data_addr_min = min; + if (max > tree->data_addr_max) + tree->data_addr_max = max; + return; + } +#endif if (min < tree->addr_min) tree->addr_min = min; if (max > tree->addr_max) @@ -109,12 +113,12 @@ static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_r static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree); - if (mod->init_layout.size) - __mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - __mod_update_bounds(mod->data_layout.base, mod->data_layout.size, &mod_data_tree); -#endif + for_each_mod_mem_type(type) { + struct module_memory *mod_mem = &mod->mem[type]; + + if (mod_mem->size) + __mod_update_bounds(type, mod_mem->base, mod_mem->size, &mod_tree); + } } /* Block module loading/unloading? */ @@ -926,7 +930,13 @@ struct module_attribute module_uevent = static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->core_layout.size); + unsigned int size = mk->mod->mem[MOD_TEXT].size; + + if (!IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC)) { + for_class_mod_mem_type(type, core_data) + size += mk->mod->mem[type].size; + } + return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_coresize = @@ -936,7 +946,11 @@ static struct module_attribute modinfo_coresize = static ssize_t show_datasize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->data_layout.size); + unsigned int size = 0; + + for_class_mod_mem_type(type, core_data) + size += mk->mod->mem[type].size; + return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_datasize = @@ -946,7 +960,11 @@ static struct module_attribute modinfo_datasize = static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->init_layout.size); + unsigned int size = 0; + + for_class_mod_mem_type(type, init) + size += mk->mod->mem[type].size; + return sprintf(buffer, "%u\n", size); } static struct module_attribute modinfo_initsize = @@ -1143,6 +1161,46 @@ void __weak module_arch_freeing_init(struct module *mod) { } +static bool mod_mem_use_vmalloc(enum mod_mem_type type) +{ + return IS_ENABLED(CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC) && + mod_mem_type_is_core_data(type); +} + +static void *module_memory_alloc(unsigned int size, enum mod_mem_type type) +{ + if (mod_mem_use_vmalloc(type)) + return vzalloc(size); + return module_alloc(size); +} + +static void module_memory_free(void *ptr, enum mod_mem_type type) +{ + if (mod_mem_use_vmalloc(type)) + vfree(ptr); + else + module_memfree(ptr); +} + +static void free_mod_mem(struct module *mod) +{ + for_each_mod_mem_type(type) { + struct module_memory *mod_mem = &mod->mem[type]; + + if (type == MOD_DATA) + continue; + + /* Free lock-classes; relies on the preceding sync_rcu(). */ + lockdep_free_key_range(mod_mem->base, mod_mem->size); + if (mod_mem->size) + module_memory_free(mod_mem->base, type); + } + + /* MOD_DATA hosts mod, so free it at last */ + lockdep_free_key_range(mod->mem[MOD_DATA].base, mod->mem[MOD_DATA].size); + module_memory_free(mod->mem[MOD_DATA].base, MOD_DATA); +} + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -1189,18 +1247,10 @@ static void free_module(struct module *mod) /* This may be empty, but that's OK */ module_arch_freeing_init(mod); - module_memfree(mod->init_layout.base); kfree(mod->args); percpu_modfree(mod); - /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size); - - /* Finally, free the core (containing the module structure) */ - module_memfree(mod->core_layout.base); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - vfree(mod->data_layout.base); -#endif + free_mod_mem(mod); } void *__symbol_get(const char *symbol) @@ -1387,16 +1437,18 @@ unsigned int __weak arch_mod_section_prepend(struct module *mod, return 0; } -/* Update size with this section: return offset. */ -long module_get_offset(struct module *mod, unsigned int *size, - Elf_Shdr *sechdr, unsigned int section) +long module_get_offset_and_type(struct module *mod, enum mod_mem_type type, + Elf_Shdr *sechdr, unsigned int section) { - long ret; + long offset; + long mask = ((unsigned long)(type) & SH_ENTSIZE_TYPE_MASK) << SH_ENTSIZE_TYPE_SHIFT; - *size += arch_mod_section_prepend(mod, section); - ret = ALIGN(*size, sechdr->sh_addralign ?: 1); - *size = ret + sechdr->sh_size; - return ret; + mod->mem[type].size += arch_mod_section_prepend(mod, section); + offset = ALIGN(mod->mem[type].size, sechdr->sh_addralign ?: 1); + mod->mem[type].size = offset + sechdr->sh_size; + + WARN_ON_ONCE(offset & mask); + return offset | mask; } static bool module_init_layout_section(const char *sname) @@ -1408,15 +1460,11 @@ static bool module_init_layout_section(const char *sname) return module_init_section(sname); } -/* - * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld - * might -- code, read-only data, read-write data, small data. Tally - * sizes, and place the offsets into sh_entsize fields: high bit means it - * belongs in init. - */ -static void layout_sections(struct module *mod, struct load_info *info) +static void __layout_sections(struct module *mod, struct load_info *info, bool is_init) { - static unsigned long const masks[][2] = { + unsigned int m, i; + + static const unsigned long masks[][2] = { /* * NOTE: all executable code must be the first section * in this array; otherwise modify the text_size @@ -1428,84 +1476,63 @@ static void layout_sections(struct module *mod, struct load_info *info) { SHF_WRITE | SHF_ALLOC, ARCH_SHF_SMALL }, { ARCH_SHF_SMALL | SHF_ALLOC, 0 } }; - unsigned int m, i; - - for (i = 0; i < info->hdr->e_shnum; i++) - info->sechdrs[i].sh_entsize = ~0UL; + static const int core_m_to_mem_type[] = { + MOD_TEXT, + MOD_RODATA, + MOD_RO_AFTER_INIT, + MOD_DATA, + MOD_INVALID, /* This is needed to match the masks array */ + }; + static const int init_m_to_mem_type[] = { + MOD_INIT_TEXT, + MOD_INIT_RODATA, + MOD_INVALID, + MOD_INIT_DATA, + MOD_INVALID, /* This is needed to match the masks array */ + }; - pr_debug("Core section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { + enum mod_mem_type type = is_init ? init_m_to_mem_type[m] : core_m_to_mem_type[m]; + for (i = 0; i < info->hdr->e_shnum; ++i) { Elf_Shdr *s = &info->sechdrs[i]; const char *sname = info->secstrings + s->sh_name; - unsigned int *sizep; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || module_init_layout_section(sname)) + || is_init != module_init_layout_section(sname)) continue; - sizep = m ? &mod->data_layout.size : &mod->core_layout.size; - s->sh_entsize = module_get_offset(mod, sizep, s, i); - pr_debug("\t%s\n", sname); - } - switch (m) { - case 0: /* executable */ - mod->core_layout.size = strict_align(mod->core_layout.size); - mod->core_layout.text_size = mod->core_layout.size; - break; - case 1: /* RO: text and ro-data */ - mod->data_layout.size = strict_align(mod->data_layout.size); - mod->data_layout.ro_size = mod->data_layout.size; - break; - case 2: /* RO after init */ - mod->data_layout.size = strict_align(mod->data_layout.size); - mod->data_layout.ro_after_init_size = mod->data_layout.size; - break; - case 4: /* whole core */ - mod->data_layout.size = strict_align(mod->data_layout.size); - break; - } - } - - pr_debug("Init section allocation order:\n"); - for (m = 0; m < ARRAY_SIZE(masks); ++m) { - for (i = 0; i < info->hdr->e_shnum; ++i) { - Elf_Shdr *s = &info->sechdrs[i]; - const char *sname = info->secstrings + s->sh_name; - if ((s->sh_flags & masks[m][0]) != masks[m][0] - || (s->sh_flags & masks[m][1]) - || s->sh_entsize != ~0UL - || !module_init_layout_section(sname)) + if (WARN_ON_ONCE(type == MOD_INVALID)) continue; - s->sh_entsize = (module_get_offset(mod, &mod->init_layout.size, s, i) - | INIT_OFFSET_MASK); + + s->sh_entsize = module_get_offset_and_type(mod, type, s, i); pr_debug("\t%s\n", sname); } - switch (m) { - case 0: /* executable */ - mod->init_layout.size = strict_align(mod->init_layout.size); - mod->init_layout.text_size = mod->init_layout.size; - break; - case 1: /* RO: text and ro-data */ - mod->init_layout.size = strict_align(mod->init_layout.size); - mod->init_layout.ro_size = mod->init_layout.size; - break; - case 2: - /* - * RO after init doesn't apply to init_layout (only - * core_layout), so it just takes the value of ro_size. - */ - mod->init_layout.ro_after_init_size = mod->init_layout.ro_size; - break; - case 4: /* whole init */ - mod->init_layout.size = strict_align(mod->init_layout.size); - break; - } } } +/* + * Lay out the SHF_ALLOC sections in a way not dissimilar to how ld + * might -- code, read-only data, read-write data, small data. Tally + * sizes, and place the offsets into sh_entsize fields: high bit means it + * belongs in init. + */ +static void layout_sections(struct module *mod, struct load_info *info) +{ + unsigned int i; + + for (i = 0; i < info->hdr->e_shnum; i++) + info->sechdrs[i].sh_entsize = ~0UL; + + pr_debug("Core section allocation order:\n"); + __layout_sections(mod, info, false); + + pr_debug("Init section allocation order:\n"); + __layout_sections(mod, info, true); +} + static void set_license(struct module *mod, const char *license) { if (!license) @@ -2122,72 +2149,41 @@ static int move_module(struct module *mod, struct load_info *info) { int i; void *ptr; + enum mod_mem_type t; - /* Do the allocs. */ - ptr = module_alloc(mod->core_layout.size); - /* - * The pointer to this block is stored in the module structure - * which is inside the block. Just mark it as not being a - * leak. - */ - kmemleak_not_leak(ptr); - if (!ptr) - return -ENOMEM; - - memset(ptr, 0, mod->core_layout.size); - mod->core_layout.base = ptr; + for_each_mod_mem_type(type) { + if (!mod->mem[type].size) { + mod->mem[type].base = NULL; + continue; + } + mod->mem[type].size = PAGE_ALIGN(mod->mem[type].size); + ptr = module_memory_alloc(mod->mem[type].size, type); - if (mod->init_layout.size) { - ptr = module_alloc(mod->init_layout.size); /* * The pointer to this block is stored in the module structure - * which is inside the block. This block doesn't need to be - * scanned as it contains data and code that will be freed - * after the module is initialized. + * which is inside the block. Just mark it as not being a + * leak. */ kmemleak_ignore(ptr); if (!ptr) { - module_memfree(mod->core_layout.base); - return -ENOMEM; + t = type; + goto out_enomem; } - memset(ptr, 0, mod->init_layout.size); - mod->init_layout.base = ptr; - } else - mod->init_layout.base = NULL; - -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - /* Do the allocs. */ - ptr = vzalloc(mod->data_layout.size); - /* - * The pointer to this block is stored in the module structure - * which is inside the block. Just mark it as not being a - * leak. - */ - kmemleak_not_leak(ptr); - if (!ptr) { - module_memfree(mod->core_layout.base); - module_memfree(mod->init_layout.base); - return -ENOMEM; + memset(ptr, 0, mod->mem[type].size); + mod->mem[type].base = ptr; } - mod->data_layout.base = ptr; -#endif /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; + enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; if (!(shdr->sh_flags & SHF_ALLOC)) continue; - if (shdr->sh_entsize & INIT_OFFSET_MASK) - dest = mod->init_layout.base - + (shdr->sh_entsize & ~INIT_OFFSET_MASK); - else if (!(shdr->sh_flags & SHF_EXECINSTR)) - dest = mod->data_layout.base + shdr->sh_entsize; - else - dest = mod->core_layout.base + shdr->sh_entsize; + dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK); if (shdr->sh_type != SHT_NOBITS) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); @@ -2198,6 +2194,10 @@ static int move_module(struct module *mod, struct load_info *info) } return 0; +out_enomem: + for (t--; t >= 0; t--) + module_memory_free(mod->mem[t].base, t); + return -ENOMEM; } static int check_module_license_and_versions(struct module *mod) @@ -2242,12 +2242,14 @@ static void flush_module_icache(const struct module *mod) * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ - if (mod->init_layout.base) - flush_icache_range((unsigned long)mod->init_layout.base, - (unsigned long)mod->init_layout.base - + mod->init_layout.size); - flush_icache_range((unsigned long)mod->core_layout.base, - (unsigned long)mod->core_layout.base + mod->core_layout.size); + for_each_mod_mem_type(type) { + const struct module_memory *mod_mem = &mod->mem[type]; + + if (mod_mem->size) { + flush_icache_range((unsigned long)mod_mem->base, + (unsigned long)mod_mem->base + mod_mem->size); + } + } } bool __weak module_elf_check_arch(Elf_Ehdr *hdr) @@ -2350,11 +2352,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_memfree(mod->init_layout.base); - module_memfree(mod->core_layout.base); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - vfree(mod->data_layout.base); -#endif + + free_mod_mem(mod); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -2415,7 +2414,9 @@ static void do_mod_ctors(struct module *mod) /* For freeing module_init on success, in case kallsyms traversing */ struct mod_initfree { struct llist_node node; - void *module_init; + void *init_text; + void *init_data; + void *init_rodata; }; static void do_free_init(struct work_struct *w) @@ -2429,7 +2430,9 @@ static void do_free_init(struct work_struct *w) llist_for_each_safe(pos, n, list) { initfree = container_of(pos, struct mod_initfree, node); - module_memfree(initfree->module_init); + module_memfree(initfree->init_text); + module_memfree(initfree->init_data); + module_memfree(initfree->init_rodata); kfree(initfree); } } @@ -2456,7 +2459,9 @@ static noinline int do_init_module(struct module *mod) ret = -ENOMEM; goto fail; } - freeinit->module_init = mod->init_layout.base; + freeinit->init_text = mod->mem[MOD_INIT_TEXT].base; + freeinit->init_data = mod->mem[MOD_INIT_DATA].base; + freeinit->init_rodata = mod->mem[MOD_INIT_RODATA].base; do_mod_ctors(mod); /* Start the module */ @@ -2492,8 +2497,8 @@ static noinline int do_init_module(struct module *mod) if (!mod->async_probe_requested) async_synchronize_full(); - ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + - mod->init_layout.size); + ftrace_free_mem(mod, mod->mem[MOD_INIT_TEXT].base, + mod->mem[MOD_INIT_TEXT].base + mod->mem[MOD_INIT_TEXT].size); mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); @@ -2505,11 +2510,10 @@ static noinline int do_init_module(struct module *mod) module_enable_ro(mod, true); mod_tree_remove_init(mod); module_arch_freeing_init(mod); - mod->init_layout.base = NULL; - mod->init_layout.size = 0; - mod->init_layout.ro_size = 0; - mod->init_layout.ro_after_init_size = 0; - mod->init_layout.text_size = 0; + for_class_mod_mem_type(type, init) { + mod->mem[type].base = NULL; + mod->mem[type].size = 0; + } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ mod->btf_data = NULL; @@ -2628,9 +2632,6 @@ static int complete_formation(struct module *mod, struct load_info *info) module_bug_finalize(info->hdr, info->sechdrs, mod); module_cfi_finalize(info->hdr, info->sechdrs, mod); - if (module_check_misalignment(mod)) - goto out_misaligned; - module_enable_ro(mod, false); module_enable_nx(mod); module_enable_x(mod); @@ -2644,8 +2645,6 @@ static int complete_formation(struct module *mod, struct load_info *info) return 0; -out_misaligned: - err = -EINVAL; out: mutex_unlock(&module_mutex); return err; @@ -2909,7 +2908,10 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size); + for_class_mod_mem_type(type, core_data) { + lockdep_free_key_range(mod->mem[type].base, + mod->mem[type].size); + } module_deallocate(mod, info); free_copy: @@ -3060,20 +3062,21 @@ bool is_module_address(unsigned long addr) struct module *__module_address(unsigned long addr) { struct module *mod; - struct mod_tree_root *tree; if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max) - tree = &mod_tree; + goto lookup; + #ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - else if (addr >= mod_data_tree.addr_min && addr <= mod_data_tree.addr_max) - tree = &mod_data_tree; + if (addr >= mod_tree.data_addr_min && addr <= mod_tree.data_addr_max) + goto lookup; #endif - else - return NULL; + return NULL; + +lookup: module_assert_mutex_or_preempt(); - mod = mod_find(addr, tree); + mod = mod_find(addr, &mod_tree); if (mod) { BUG_ON(!within_module(addr, mod)); if (mod->state == MODULE_STATE_UNFORMED) @@ -3113,8 +3116,8 @@ struct module *__module_text_address(unsigned long addr) struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ - if (!within(addr, mod->init_layout.base, mod->init_layout.text_size) - && !within(addr, mod->core_layout.base, mod->core_layout.text_size)) + if (!within_module_mem_type(addr, mod, MOD_TEXT) && + !within_module_mem_type(addr, mod, MOD_INIT_TEXT)) mod = NULL; } return mod; diff --git a/kernel/module/procfs.c b/kernel/module/procfs.c index cf5b9f1e6ec4..0a4841e88adb 100644 --- a/kernel/module/procfs.c +++ b/kernel/module/procfs.c @@ -62,6 +62,15 @@ static void m_stop(struct seq_file *m, void *p) mutex_unlock(&module_mutex); } +static unsigned int module_total_size(struct module *mod) +{ + int size = 0; + + for_each_mod_mem_type(type) + size += mod->mem[type].size; + return size; +} + static int m_show(struct seq_file *m, void *p) { struct module *mod = list_entry(p, struct module, list); @@ -73,10 +82,7 @@ static int m_show(struct seq_file *m, void *p) if (mod->state == MODULE_STATE_UNFORMED) return 0; - size = mod->init_layout.size + mod->core_layout.size; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - size += mod->data_layout.size; -#endif + size = module_total_size(mod); seq_printf(m, "%s %u", mod->name, size); print_unload_info(m, mod); @@ -86,7 +92,7 @@ static int m_show(struct seq_file *m, void *p) mod->state == MODULE_STATE_COMING ? "Loading" : "Live"); /* Used by oprofile and other similar tools. */ - value = m->private ? NULL : mod->core_layout.base; + value = m->private ? NULL : mod->mem[MOD_TEXT].base; seq_printf(m, " 0x%px", value); /* Taints info */ diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c index 14fbea66f12f..a2b656b4e3d2 100644 --- a/kernel/module/strict_rwx.c +++ b/kernel/module/strict_rwx.c @@ -11,82 +11,25 @@ #include #include "internal.h" -/* - * LKM RO/NX protection: protect module's text/ro-data - * from modification and any data from execution. - * - * General layout of module is: - * [text] [read-only-data] [ro-after-init] [writable data] - * text_size -----^ ^ ^ ^ - * ro_size ------------------------| | | - * ro_after_init_size -----------------------------| | - * size -----------------------------------------------------------| - * - * These values are always page-aligned (as is base) when - * CONFIG_STRICT_MODULE_RWX is set. - */ +static void module_set_memory(const struct module *mod, enum mod_mem_type type, + int (*set_memory)(unsigned long start, int num_pages)) +{ + const struct module_memory *mod_mem = &mod->mem[type]; + + set_vm_flush_reset_perms(mod_mem->base); + set_memory((unsigned long)mod_mem->base, mod_mem->size >> PAGE_SHIFT); +} /* * Since some arches are moving towards PAGE_KERNEL module allocations instead - * of PAGE_KERNEL_EXEC, keep frob_text() and module_enable_x() independent of + * of PAGE_KERNEL_EXEC, keep module_enable_x() independent of * CONFIG_STRICT_MODULE_RWX because they are needed regardless of whether we * are strict. */ -static void frob_text(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - set_memory((unsigned long)layout->base, - PAGE_ALIGN(layout->text_size) >> PAGE_SHIFT); -} - -static void frob_rodata(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - set_memory((unsigned long)layout->base + layout->text_size, - (layout->ro_size - layout->text_size) >> PAGE_SHIFT); -} - -static void frob_ro_after_init(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - set_memory((unsigned long)layout->base + layout->ro_size, - (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT); -} - -static void frob_writable_data(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - set_memory((unsigned long)layout->base + layout->ro_after_init_size, - (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT); -} - -static bool layout_check_misalignment(const struct module_layout *layout) -{ - return WARN_ON(!PAGE_ALIGNED(layout->base)) || - WARN_ON(!PAGE_ALIGNED(layout->text_size)) || - WARN_ON(!PAGE_ALIGNED(layout->ro_size)) || - WARN_ON(!PAGE_ALIGNED(layout->ro_after_init_size)) || - WARN_ON(!PAGE_ALIGNED(layout->size)); -} - -bool module_check_misalignment(const struct module *mod) -{ - if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - return false; - - return layout_check_misalignment(&mod->core_layout) || - layout_check_misalignment(&mod->data_layout) || - layout_check_misalignment(&mod->init_layout); -} - void module_enable_x(const struct module *mod) { - if (!PAGE_ALIGNED(mod->core_layout.base) || - !PAGE_ALIGNED(mod->init_layout.base)) - return; - - frob_text(&mod->core_layout, set_memory_x); - frob_text(&mod->init_layout, set_memory_x); + for_class_mod_mem_type(type, text) + module_set_memory(mod, type, set_memory_x); } void module_enable_ro(const struct module *mod, bool after_init) @@ -98,16 +41,13 @@ void module_enable_ro(const struct module *mod, bool after_init) return; #endif - set_vm_flush_reset_perms(mod->core_layout.base); - set_vm_flush_reset_perms(mod->init_layout.base); - frob_text(&mod->core_layout, set_memory_ro); - - frob_rodata(&mod->data_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - frob_rodata(&mod->init_layout, set_memory_ro); + module_set_memory(mod, MOD_TEXT, set_memory_ro); + module_set_memory(mod, MOD_INIT_TEXT, set_memory_ro); + module_set_memory(mod, MOD_RODATA, set_memory_ro); + module_set_memory(mod, MOD_INIT_RODATA, set_memory_ro); if (after_init) - frob_ro_after_init(&mod->data_layout, set_memory_ro); + module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro); } void module_enable_nx(const struct module *mod) @@ -115,11 +55,8 @@ void module_enable_nx(const struct module *mod) if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) return; - frob_rodata(&mod->data_layout, set_memory_nx); - frob_ro_after_init(&mod->data_layout, set_memory_nx); - frob_writable_data(&mod->data_layout, set_memory_nx); - frob_rodata(&mod->init_layout, set_memory_nx); - frob_writable_data(&mod->init_layout, set_memory_nx); + for_class_mod_mem_type(type, data) + module_set_memory(mod, type, set_memory_nx); } int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, diff --git a/kernel/module/tree_lookup.c b/kernel/module/tree_lookup.c index 8ec5cfd60496..277197977d43 100644 --- a/kernel/module/tree_lookup.c +++ b/kernel/module/tree_lookup.c @@ -21,16 +21,16 @@ static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - struct module_layout *layout = container_of(n, struct module_layout, mtn.node); + struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node); - return (unsigned long)layout->base; + return (unsigned long)mod_mem->base; } static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) { - struct module_layout *layout = container_of(n, struct module_layout, mtn.node); + struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node); - return (unsigned long)layout->size; + return (unsigned long)mod_mem->size; } static __always_inline bool @@ -77,32 +77,27 @@ static void __mod_tree_remove(struct mod_tree_node *node, struct mod_tree_root * */ void mod_tree_insert(struct module *mod) { - mod->core_layout.mtn.mod = mod; - mod->init_layout.mtn.mod = mod; - - __mod_tree_insert(&mod->core_layout.mtn, &mod_tree); - if (mod->init_layout.size) - __mod_tree_insert(&mod->init_layout.mtn, &mod_tree); - -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - mod->data_layout.mtn.mod = mod; - __mod_tree_insert(&mod->data_layout.mtn, &mod_data_tree); -#endif + for_each_mod_mem_type(type) { + mod->mem[type].mtn.mod = mod; + if (mod->mem[type].size) + __mod_tree_insert(&mod->mem[type].mtn, &mod_tree); + } } void mod_tree_remove_init(struct module *mod) { - if (mod->init_layout.size) - __mod_tree_remove(&mod->init_layout.mtn, &mod_tree); + for_class_mod_mem_type(type, init) { + if (mod->mem[type].size) + __mod_tree_remove(&mod->mem[type].mtn, &mod_tree); + } } void mod_tree_remove(struct module *mod) { - __mod_tree_remove(&mod->core_layout.mtn, &mod_tree); - mod_tree_remove_init(mod); -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - __mod_tree_remove(&mod->data_layout.mtn, &mod_data_tree); -#endif + for_each_mod_mem_type(type) { + if (mod->mem[type].size) + __mod_tree_remove(&mod->mem[type].mtn, &mod_tree); + } } struct module *mod_find(unsigned long addr, struct mod_tree_root *tree) -- GitLab From 9e07f161717ab8e8ac1206bf82546511e24cbb7b Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 10 Feb 2023 14:42:43 +0800 Subject: [PATCH 0232/5631] module: Remove the unused function within The function within is defined in the main.c file, but not called elsewhere, so remove this unused function. This routine became no longer used after commit ("module: replace module_layout with module_memory"). kernel/module/main.c:3007:19: warning: unused function 'within'. Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4035 Signed-off-by: Jiapeng Chong [mcgrof: adjust commit log to explain why this change is needed] Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 2724bc1b9a90..1fa529668a45 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2975,11 +2975,6 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) return load_module(&info, uargs, flags); } -static inline int within(unsigned long addr, void *start, unsigned long size) -{ - return ((void *)addr >= start && (void *)addr < start + size); -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- GitLab From efaa2496bae66f0a78efa60d9b73ceef5ec63d79 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 13 Feb 2023 16:54:00 -0800 Subject: [PATCH 0233/5631] module: fix MIPS module_layout -> module_memory Correct the struct's field/member name from mod_mem to mem. Fixes this build error: ../arch/mips/kernel/vpe.c: In function 'vpe_elfload': ../arch/mips/kernel/vpe.c:643:41: error: 'struct module' has no member named 'mod_mem' 643 | v->load_addr = alloc_progmem(mod.mod_mem[MOD_TEXT].size); Fixes: 2ece476a2346 ("module: replace module_layout with module_memory") Signed-off-by: Randy Dunlap Cc: Song Liu Cc: Luis Chamberlain Cc: Thomas Bogendoerfer Cc: linux-mips@vger.kernel.org Signed-off-by: Luis Chamberlain --- arch/mips/kernel/vpe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index ab114c686f9d..5c4adc6ff0c1 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -640,7 +640,7 @@ static int vpe_elfload(struct vpe *v) layout_sections(&mod, hdr, sechdrs, secstrings); } - v->load_addr = alloc_progmem(mod.mod_mem[MOD_TEXT].size); + v->load_addr = alloc_progmem(mod.mem[MOD_TEXT].size); if (!v->load_addr) return -ENOMEM; -- GitLab From 042edf1ebb49a63f299c4cdfb9c1e2ba299c0b91 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 4 Feb 2023 05:44:46 +0000 Subject: [PATCH 0234/5631] module: make module_ktype structure constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Signed-off-by: Luis Chamberlain --- include/linux/module.h | 2 +- kernel/params.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/module.h b/include/linux/module.h index c0593a96e158..dbc9124b71bc 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -871,7 +871,7 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) #ifdef CONFIG_SYSFS extern struct kset *module_kset; -extern struct kobj_type module_ktype; +extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) diff --git a/kernel/params.c b/kernel/params.c index 6e34ca89ebae..6a7548979aa9 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -948,7 +948,7 @@ static void module_kobj_release(struct kobject *kobj) complete(mk->kobj_completion); } -struct kobj_type module_ktype = { +const struct kobj_type module_ktype = { .release = module_kobj_release, .sysfs_ops = &module_sysfs_ops, }; -- GitLab From 85c37208b0cb178084600dd01d9f97a32b6a21ea Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 3 Mar 2023 11:50:55 -0500 Subject: [PATCH 0235/5631] dyndbg: remove unused 'base' arg from __ddebug_add_module() The 'base' parameter to __ddebug_add_module() is no longer in use after: Commit b7b4eebdba7b ("dyndbg: gather __dyndbg[] state into struct _ddebug_info"). Cc: Jim Cromie Cc: Greg Kroah-Hartman Tested-by: Jim Cromie Reviewed-by: Vincenzo Palazzo Signed-off-by: Jason Baron Signed-off-by: Luis Chamberlain --- lib/dynamic_debug.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 009f2ead09c1..8136e5236b7b 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -1223,8 +1223,7 @@ static void ddebug_attach_module_classes(struct ddebug_table *dt, * Allocate a new ddebug_table for the given module * and add it to the global list. */ -static int __ddebug_add_module(struct _ddebug_info *di, unsigned int base, - const char *modname) +static int __ddebug_add_module(struct _ddebug_info *di, const char *modname) { struct ddebug_table *dt; @@ -1265,7 +1264,7 @@ static int __ddebug_add_module(struct _ddebug_info *di, unsigned int base, int ddebug_add_module(struct _ddebug_info *di, const char *modname) { - return __ddebug_add_module(di, 0, modname); + return __ddebug_add_module(di, modname); } /* helper for ddebug_dyndbg_(boot|module)_param_cb */ @@ -1408,7 +1407,7 @@ static int __init dynamic_debug_init(void) mod_ct++; di.num_descs = mod_sites; di.descs = iter_mod_start; - ret = __ddebug_add_module(&di, i - mod_sites, modname); + ret = __ddebug_add_module(&di, modname); if (ret) goto out_err; @@ -1419,7 +1418,7 @@ static int __init dynamic_debug_init(void) } di.num_descs = mod_sites; di.descs = iter_mod_start; - ret = __ddebug_add_module(&di, i - mod_sites, modname); + ret = __ddebug_add_module(&di, modname); if (ret) goto out_err; -- GitLab From 7deabd67498869640c937c9bd83472574b7dea0b Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 3 Mar 2023 11:50:56 -0500 Subject: [PATCH 0236/5631] dyndbg: use the module notifier callbacks Bring dynamic debug in line with other subsystems by using the module notifier callbacks. This results in a net decrease in core module code. Additionally, Jim Cromie has a new dynamic debug classmap feature, which requires that jump labels be initialized prior to dynamic debug. Specifically, the new feature toggles a jump label from the existing dynamic_debug_setup() function. However, this does not currently work properly, because jump labels are initialized via the 'module_notify_list' notifier chain, which is invoked after the current call to dynamic_debug_setup(). Thus, this patch ensures that jump labels are initialized prior to dynamic debug by setting the dynamic debug notifier priority to 0, while jump labels have the higher priority of 1. Tested by Jim using his new test case, and I've verfied the correct printing via: # modprobe test_dynamic_debug dyndbg. Link: https://lore.kernel.org/lkml/20230113193016.749791-21-jim.cromie@gmail.com/ Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202302190427.9iIK2NfJ-lkp@intel.com/ Tested-by: Jim Cromie Reviewed-by: Vincenzo Palazzo Cc: Peter Zijlstra CC: Jim Cromie Cc: Luis Chamberlain Cc: Greg Kroah-Hartman Signed-off-by: Jason Baron Signed-off-by: Luis Chamberlain --- include/linux/dynamic_debug.h | 13 --------- include/linux/module.h | 4 +++ kernel/module/internal.h | 2 -- kernel/module/main.c | 30 ++++++--------------- lib/dynamic_debug.c | 50 ++++++++++++++++++++++++++++------- 5 files changed, 53 insertions(+), 46 deletions(-) diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 41682278d2e8..f401414341fb 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -130,9 +130,6 @@ struct ddebug_class_param { #if defined(CONFIG_DYNAMIC_DEBUG_CORE) -int ddebug_add_module(struct _ddebug_info *dyndbg, const char *modname); - -extern int ddebug_remove_module(const char *mod_name); extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); @@ -304,16 +301,6 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); #include #include -static inline int ddebug_add_module(struct _ddebug_info *dinfo, const char *modname) -{ - return 0; -} - -static inline int ddebug_remove_module(const char *mod) -{ - return 0; -} - static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) { diff --git a/include/linux/module.h b/include/linux/module.h index dbc9124b71bc..91726444d55f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -579,6 +580,9 @@ struct module { struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + struct _ddebug_info dyndbg_info; +#endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} diff --git a/kernel/module/internal.h b/kernel/module/internal.h index c6c44ceca07a..e3883b7d4840 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -45,7 +45,6 @@ extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const s32 __start___kcrctab[]; extern const s32 __start___kcrctab_gpl[]; -#include struct load_info { const char *name; /* pointer to module in temporary copy, freed at end of load_module() */ @@ -55,7 +54,6 @@ struct load_info { Elf_Shdr *sechdrs; char *secstrings, *strtab; unsigned long symoffs, stroffs, init_typeoffs, core_typeoffs; - struct _ddebug_info dyndbg; bool sig_ok; #ifdef CONFIG_KALLSYMS unsigned long mod_kallsyms_init_off; diff --git a/kernel/module/main.c b/kernel/module/main.c index 1fa529668a45..b4759f1695b7 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1216,9 +1216,6 @@ static void free_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; mutex_unlock(&module_mutex); - /* Remove dynamic debug info */ - ddebug_remove_module(mod->name); - /* Arch-specific cleanup. */ module_arch_cleanup(mod); @@ -1619,19 +1616,6 @@ static void free_modinfo(struct module *mod) } } -static void dynamic_debug_setup(struct module *mod, struct _ddebug_info *dyndbg) -{ - if (!dyndbg->num_descs) - return; - ddebug_add_module(dyndbg, mod->name); -} - -static void dynamic_debug_remove(struct module *mod, struct _ddebug_info *dyndbg) -{ - if (dyndbg->num_descs) - ddebug_remove_module(mod->name); -} - void * __weak module_alloc(unsigned long size) { return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, @@ -2137,10 +2121,14 @@ static int find_module_sections(struct module *mod, struct load_info *info) if (section_addr(info, "__obsparm")) pr_warn("%s: Ignoring obsolete parameters\n", mod->name); - info->dyndbg.descs = section_objs(info, "__dyndbg", - sizeof(*info->dyndbg.descs), &info->dyndbg.num_descs); - info->dyndbg.classes = section_objs(info, "__dyndbg_classes", - sizeof(*info->dyndbg.classes), &info->dyndbg.num_classes); +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + mod->dyndbg_info.descs = section_objs(info, "__dyndbg", + sizeof(*mod->dyndbg_info.descs), + &mod->dyndbg_info.num_descs); + mod->dyndbg_info.classes = section_objs(info, "__dyndbg_classes", + sizeof(*mod->dyndbg_info.classes), + &mod->dyndbg_info.num_classes); +#endif return 0; } @@ -2824,7 +2812,6 @@ static int load_module(struct load_info *info, const char __user *uargs, } init_build_id(mod, info); - dynamic_debug_setup(mod, &info->dyndbg); /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ ftrace_module_init(mod); @@ -2888,7 +2875,6 @@ static int load_module(struct load_info *info, const char __user *uargs, ddebug_cleanup: ftrace_release_mod(mod); - dynamic_debug_remove(mod, &info->dyndbg); synchronize_rcu(); kfree(mod->args); free_arch_cleanup: diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 8136e5236b7b..fdd6d9800a70 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -1223,7 +1223,7 @@ static void ddebug_attach_module_classes(struct ddebug_table *dt, * Allocate a new ddebug_table for the given module * and add it to the global list. */ -static int __ddebug_add_module(struct _ddebug_info *di, const char *modname) +static int ddebug_add_module(struct _ddebug_info *di, const char *modname) { struct ddebug_table *dt; @@ -1262,11 +1262,6 @@ static int __ddebug_add_module(struct _ddebug_info *di, const char *modname) return 0; } -int ddebug_add_module(struct _ddebug_info *di, const char *modname) -{ - return __ddebug_add_module(di, modname); -} - /* helper for ddebug_dyndbg_(boot|module)_param_cb */ static int ddebug_dyndbg_param_cb(char *param, char *val, const char *modname, int on_err) @@ -1313,11 +1308,13 @@ static void ddebug_table_free(struct ddebug_table *dt) kfree(dt); } +#ifdef CONFIG_MODULES + /* * Called in response to a module being unloaded. Removes * any ddebug_table's which point at the module. */ -int ddebug_remove_module(const char *mod_name) +static int ddebug_remove_module(const char *mod_name) { struct ddebug_table *dt, *nextdt; int ret = -ENOENT; @@ -1336,6 +1333,33 @@ int ddebug_remove_module(const char *mod_name) return ret; } +static int ddebug_module_notify(struct notifier_block *self, unsigned long val, + void *data) +{ + struct module *mod = data; + int ret = 0; + + switch (val) { + case MODULE_STATE_COMING: + ret = ddebug_add_module(&mod->dyndbg_info, mod->name); + if (ret) + WARN(1, "Failed to allocate memory: dyndbg may not work properly.\n"); + break; + case MODULE_STATE_GOING: + ddebug_remove_module(mod->name); + break; + } + + return notifier_from_errno(ret); +} + +static struct notifier_block ddebug_module_nb = { + .notifier_call = ddebug_module_notify, + .priority = 0, /* dynamic debug depends on jump label */ +}; + +#endif /* CONFIG_MODULES */ + static void ddebug_remove_all_tables(void) { mutex_lock(&ddebug_lock); @@ -1387,6 +1411,14 @@ static int __init dynamic_debug_init(void) .num_classes = __stop___dyndbg_classes - __start___dyndbg_classes, }; +#ifdef CONFIG_MODULES + ret = register_module_notifier(&ddebug_module_nb); + if (ret) { + pr_warn("Failed to register dynamic debug module notifier\n"); + return ret; + } +#endif /* CONFIG_MODULES */ + if (&__start___dyndbg == &__stop___dyndbg) { if (IS_ENABLED(CONFIG_DYNAMIC_DEBUG)) { pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n"); @@ -1407,7 +1439,7 @@ static int __init dynamic_debug_init(void) mod_ct++; di.num_descs = mod_sites; di.descs = iter_mod_start; - ret = __ddebug_add_module(&di, modname); + ret = ddebug_add_module(&di, modname); if (ret) goto out_err; @@ -1418,7 +1450,7 @@ static int __init dynamic_debug_init(void) } di.num_descs = mod_sites; di.descs = iter_mod_start; - ret = __ddebug_add_module(&di, modname); + ret = ddebug_add_module(&di, modname); if (ret) goto out_err; -- GitLab From ffbe08a8e86d03513dc45b5389fab7f3477433b6 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 3 Mar 2023 16:53:53 -0800 Subject: [PATCH 0237/5631] driver core: Add fw_devlink.sync_state command line param When all devices that could probe have finished probing (based on deferred_probe_timeout configuration or late_initcall() when !CONFIG_MODULES), this parameter controls what to do with devices that haven't yet received their sync_state() calls. fw_devlink.sync_state=strict is the default and the driver core will continue waiting on all consumers of a device to probe successfully before sync_state() is called for the device. This is the default behavior since calling sync_state() on a device when all its consumers haven't probed could make some systems unusable/unstable. When this option is selected, we also print the list of devices that haven't had sync_state() called on them by the time all devices the could probe have finished probing. fw_devlink.sync_state=timeout will cause the driver core to give up waiting on consumers and call sync_state() on any devices that haven't yet received their sync_state() calls. This option is provided for systems that won't become unusable/unstable as they might be able to save power (depends on state of hardware before kernel starts) if all devices get their sync_state(). Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230304005355.746421-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- .../admin-guide/kernel-parameters.txt | 14 +++++ drivers/base/base.h | 1 + drivers/base/core.c | 58 +++++++++++++++++++ drivers/base/dd.c | 6 ++ 4 files changed, 79 insertions(+) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 207ca1d6e3d3..76d8fdf04326 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1582,6 +1582,20 @@ dependencies. This only applies for fw_devlink=on|rpm. Format: + fw_devlink.sync_state = + [KNL] When all devices that could probe have finished + probing, this parameter controls what to do with + devices that haven't yet received their sync_state() + calls. + Format: { strict | timeout } + strict -- Default. Continue waiting on consumers to + probe successfully. + timeout -- Give up waiting on consumers and call + sync_state() on any devices that haven't yet + received their sync_state() calls after + deferred_probe_timeout has expired or by + late_initcall() if !CONFIG_MODULES. + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) diff --git a/drivers/base/base.h b/drivers/base/base.h index 726a12a244c0..6fcd71803d35 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -209,6 +209,7 @@ extern void device_links_no_driver(struct device *dev); extern bool device_links_busy(struct device *dev); extern void device_links_unbind_consumers(struct device *dev); extern void fw_devlink_drivers_done(void); +extern void fw_devlink_probing_done(void); /* device pm support */ void device_pm_move_to_tail(struct device *dev); diff --git a/drivers/base/core.c b/drivers/base/core.c index ba11b51ce4ee..871e6513a6c8 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1672,6 +1672,26 @@ static int __init fw_devlink_strict_setup(char *arg) } early_param("fw_devlink.strict", fw_devlink_strict_setup); +#define FW_DEVLINK_SYNC_STATE_STRICT 0 +#define FW_DEVLINK_SYNC_STATE_TIMEOUT 1 + +static int fw_devlink_sync_state; +static int __init fw_devlink_sync_state_setup(char *arg) +{ + if (!arg) + return -EINVAL; + + if (strcmp(arg, "strict") == 0) { + fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_STRICT; + return 0; + } else if (strcmp(arg, "timeout") == 0) { + fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT; + return 0; + } + return -EINVAL; +} +early_param("fw_devlink.sync_state", fw_devlink_sync_state_setup); + static inline u32 fw_devlink_get_flags(u8 fwlink_flags) { if (fwlink_flags & FWLINK_FLAG_CYCLE) @@ -1742,6 +1762,44 @@ void fw_devlink_drivers_done(void) device_links_write_unlock(); } +static int fw_devlink_dev_sync_state(struct device *dev, void *data) +{ + struct device_link *link = to_devlink(dev); + struct device *sup = link->supplier; + + if (!(link->flags & DL_FLAG_MANAGED) || + link->status == DL_STATE_ACTIVE || sup->state_synced || + !dev_has_sync_state(sup)) + return 0; + + if (fw_devlink_sync_state == FW_DEVLINK_SYNC_STATE_STRICT) { + dev_warn(sup, "sync_state() pending due to %s\n", + dev_name(link->consumer)); + return 0; + } + + if (!list_empty(&sup->links.defer_sync)) + return 0; + + dev_warn(sup, "Timed out. Forcing sync_state()\n"); + sup->state_synced = true; + get_device(sup); + list_add_tail(&sup->links.defer_sync, data); + + return 0; +} + +void fw_devlink_probing_done(void) +{ + LIST_HEAD(sync_list); + + device_links_write_lock(); + class_for_each_device(&devlink_class, NULL, &sync_list, + fw_devlink_dev_sync_state); + device_links_write_unlock(); + device_links_flush_sync_list(&sync_list, NULL); +} + /** * wait_for_init_devices_probe - Try to probe any device needed for init * diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 8def2ba08a82..84f07e0050dd 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -315,6 +315,8 @@ static void deferred_probe_timeout_work_func(struct work_struct *work) list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) dev_info(p->device, "deferred probe pending\n"); mutex_unlock(&deferred_probe_mutex); + + fw_devlink_probing_done(); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); @@ -364,6 +366,10 @@ static int deferred_probe_initcall(void) schedule_delayed_work(&deferred_probe_timeout_work, driver_deferred_probe_timeout * HZ); } + + if (!IS_ENABLED(CONFIG_MODULES)) + fw_devlink_probing_done(); + return 0; } late_initcall(deferred_probe_initcall); -- GitLab From f8fb576658a3e19796e2e1a12a5ec8f44dac02b6 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 3 Mar 2023 16:53:54 -0800 Subject: [PATCH 0238/5631] driver core: Make state_synced device attribute writeable If the file is written to and sync_state() hasn't been called for the device yet, then call sync_state() for the device independent of the state of its consumers. This is useful for supplier devices that have one or more consumers that don't have a driver but the consumers are in a state that don't use the resources supplied by the supplier device. This gives finer grained control than using the fw_devlink.sync_state=timeout kernel commandline parameter. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230304005355.746421-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-devices-state_synced | 5 ++++ drivers/base/base.h | 8 +++++++ drivers/base/core.c | 5 +--- drivers/base/dd.c | 23 ++++++++++++++++++- 4 files changed, 36 insertions(+), 5 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-devices-state_synced b/Documentation/ABI/testing/sysfs-devices-state_synced index 0c922d7d02fc..c64636ddac41 100644 --- a/Documentation/ABI/testing/sysfs-devices-state_synced +++ b/Documentation/ABI/testing/sysfs-devices-state_synced @@ -21,4 +21,9 @@ Description: at the time the kernel starts are not affected or limited in any way by sync_state() callbacks. + Writing "1" to this file will force a call to the device's + sync_state() function if it hasn't been called already. The + sync_state() call happens independent of the state of the + consumer devices. + diff --git a/drivers/base/base.h b/drivers/base/base.h index 6fcd71803d35..b055eba1ec30 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -164,6 +164,14 @@ static inline int driver_match_device(struct device_driver *drv, return drv->bus->match ? drv->bus->match(dev, drv) : 1; } +static inline void dev_sync_state(struct device *dev) +{ + if (dev->bus->sync_state) + dev->bus->sync_state(dev); + else if (dev->driver && dev->driver->sync_state) + dev->driver->sync_state(dev); +} + extern int driver_add_groups(struct device_driver *drv, const struct attribute_group **groups); extern void driver_remove_groups(struct device_driver *drv, diff --git a/drivers/base/core.c b/drivers/base/core.c index 871e6513a6c8..fe74a786e2c3 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1160,10 +1160,7 @@ static void device_links_flush_sync_list(struct list_head *list, if (dev != dont_lock_dev) device_lock(dev); - if (dev->bus->sync_state) - dev->bus->sync_state(dev); - else if (dev->driver && dev->driver->sync_state) - dev->driver->sync_state(dev); + dev_sync_state(dev); if (dev != dont_lock_dev) device_unlock(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 84f07e0050dd..7b9ab2050b84 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -510,6 +510,27 @@ EXPORT_SYMBOL_GPL(device_bind_driver); static atomic_t probe_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue); +static ssize_t state_synced_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int ret = 0; + + if (strcmp("1", buf)) + return -EINVAL; + + device_lock(dev); + if (!dev->state_synced) { + dev->state_synced = true; + dev_sync_state(dev); + } else { + ret = -EINVAL; + } + device_unlock(dev); + + return ret ? ret : count; +} + static ssize_t state_synced_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -521,7 +542,7 @@ static ssize_t state_synced_show(struct device *dev, return sysfs_emit(buf, "%u\n", val); } -static DEVICE_ATTR_RO(state_synced); +static DEVICE_ATTR_RW(state_synced); static void device_unbind_cleanup(struct device *dev) { -- GitLab From 295209ca7b5b3aa6375d6190311b2ae804dbcf65 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Feb 2023 15:33:44 +0200 Subject: [PATCH 0239/5631] device property: Clarify description of returned value in some functions Some of the functions do not provide Return: section on absence of which kernel-doc complains. Besides that several functions return the fwnode handle with incremented reference count. Add a respective note to make sure that the caller decrements it when it's not needed anymore. While at it, unify the style of the Return: sections. Reported-by: Daniel Kaehn Signed-off-by: Andy Shevchenko Acked-by: Sakari Ailus Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230217133344.79278-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/property.c | 124 +++++++++++++++++++++++++++++----------- 1 file changed, 90 insertions(+), 34 deletions(-) diff --git a/drivers/base/property.c b/drivers/base/property.c index 083a95791d3b..3fc25e568598 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -37,6 +37,8 @@ EXPORT_SYMBOL_GPL(__dev_fwnode_const); * @propname: Name of the property * * Check if property @propname is present in the device firmware description. + * + * Return: true if property @propname is present. Otherwise, returns false. */ bool device_property_present(struct device *dev, const char *propname) { @@ -48,6 +50,8 @@ EXPORT_SYMBOL_GPL(device_property_present); * fwnode_property_present - check if a property of a firmware node is present * @fwnode: Firmware node whose property to check * @propname: Name of the property + * + * Return: true if property @propname is present. Otherwise, returns false. */ bool fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) @@ -508,10 +512,10 @@ EXPORT_SYMBOL_GPL(fwnode_property_match_string); * Obtain a reference based on a named property in an fwnode, with * integer arguments. * - * Caller is responsible to call fwnode_handle_put() on the returned - * args->fwnode pointer. + * The caller is responsible for calling fwnode_handle_put() on the returned + * @args->fwnode pointer. * - * Returns: %0 on success + * Return: %0 on success * %-ENOENT when the index is out of bounds, the index has an empty * reference or the property was not found * %-EINVAL on parse error @@ -547,8 +551,11 @@ EXPORT_SYMBOL_GPL(fwnode_property_get_reference_args); * * @index can be used when the named reference holds a table of references. * - * Returns pointer to the reference fwnode, or ERR_PTR. Caller is responsible to - * call fwnode_handle_put() on the returned fwnode pointer. + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * + * Return: a pointer to the reference fwnode, when found. Otherwise, + * returns an error pointer. */ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, const char *name, @@ -567,7 +574,7 @@ EXPORT_SYMBOL_GPL(fwnode_find_reference); * fwnode_get_name - Return the name of a node * @fwnode: The firmware node * - * Returns a pointer to the node name. + * Return: a pointer to the node name, or %NULL. */ const char *fwnode_get_name(const struct fwnode_handle *fwnode) { @@ -579,7 +586,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_name); * fwnode_get_name_prefix - Return the prefix of node for printing purposes * @fwnode: The firmware node * - * Returns the prefix of a node, intended to be printed right before the node. + * Return: the prefix of a node, intended to be printed right before the node. * The prefix works also as a separator between the nodes. */ const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode) @@ -591,7 +598,10 @@ const char *fwnode_get_name_prefix(const struct fwnode_handle *fwnode) * fwnode_get_parent - Return parent firwmare node * @fwnode: Firmware whose parent is retrieved * - * Return parent firmware node of the given node if possible or %NULL if no + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * + * Return: parent firmware node of the given node if possible or %NULL if no * parent was available. */ struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode) @@ -608,8 +618,12 @@ EXPORT_SYMBOL_GPL(fwnode_get_parent); * on the passed node, making it suitable for iterating through a * node's parents. * - * Returns a node pointer with refcount incremented, use - * fwnode_handle_put() on it when done. + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. Note that this function also puts a reference to @fwnode + * unconditionally. + * + * Return: parent firmware node of the given node if possible or %NULL if no + * parent was available. */ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode) { @@ -629,8 +643,10 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_parent); * firmware node that has a corresponding struct device and returns that struct * device. * - * The caller of this function is expected to call put_device() on the returned - * device when they are done. + * The caller is responsible for calling put_device() on the returned device + * pointer. + * + * Return: a pointer to the device of the @fwnode's closest ancestor. */ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode) { @@ -651,7 +667,7 @@ struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode) * fwnode_count_parents - Return the number of parents a node has * @fwnode: The node the parents of which are to be counted * - * Returns the number of parents a node has. + * Return: the number of parents a node has. */ unsigned int fwnode_count_parents(const struct fwnode_handle *fwnode) { @@ -670,12 +686,12 @@ EXPORT_SYMBOL_GPL(fwnode_count_parents); * @fwnode: The node the parent of which is requested * @depth: Distance of the parent from the node * - * Returns the nth parent of a node. If there is no parent at the requested + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * + * Return: the nth parent of a node. If there is no parent at the requested * @depth, %NULL is returned. If @depth is 0, the functionality is equivalent to * fwnode_handle_get(). For @depth == 1, it is fwnode_get_parent() and so on. - * - * The caller is responsible for calling fwnode_handle_put() for the returned - * node. */ struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwnode, unsigned int depth) @@ -700,7 +716,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_nth_parent); * * A node is considered an ancestor of itself too. * - * Returns true if @ancestor is an ancestor of @child. Otherwise, returns false. + * Return: true if @ancestor is an ancestor of @child. Otherwise, returns false. */ bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child) { @@ -725,6 +741,10 @@ bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle * fwnode_get_next_child_node - Return the next child node handle for a node * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the node's child nodes or a %NULL handle. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. Note that this function also puts a reference to @child + * unconditionally. */ struct fwnode_handle * fwnode_get_next_child_node(const struct fwnode_handle *fwnode, @@ -735,10 +755,13 @@ fwnode_get_next_child_node(const struct fwnode_handle *fwnode, EXPORT_SYMBOL_GPL(fwnode_get_next_child_node); /** - * fwnode_get_next_available_child_node - Return the next - * available child node handle for a node + * fwnode_get_next_available_child_node - Return the next available child node handle for a node * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the node's child nodes or a %NULL handle. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. Note that this function also puts a reference to @child + * unconditionally. */ struct fwnode_handle * fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode, @@ -762,7 +785,11 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node); /** * device_get_next_child_node - Return the next child node handle for a device * @dev: Device to find the next child node for. - * @child: Handle to one of the device's child nodes or a null handle. + * @child: Handle to one of the device's child nodes or a %NULL handle. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. Note that this function also puts a reference to @child + * unconditionally. */ struct fwnode_handle *device_get_next_child_node(const struct device *dev, struct fwnode_handle *child) @@ -787,6 +814,9 @@ EXPORT_SYMBOL_GPL(device_get_next_child_node); * fwnode_get_named_child_node - Return first matching named child node handle * @fwnode: Firmware node to find the named child node for. * @childname: String to match child node name against. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. */ struct fwnode_handle * fwnode_get_named_child_node(const struct fwnode_handle *fwnode, @@ -800,6 +830,9 @@ EXPORT_SYMBOL_GPL(fwnode_get_named_child_node); * device_get_named_child_node - Return first matching named child node handle * @dev: Device to find the named child node for. * @childname: String to match child node name against. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. */ struct fwnode_handle *device_get_named_child_node(const struct device *dev, const char *childname) @@ -812,7 +845,10 @@ EXPORT_SYMBOL_GPL(device_get_named_child_node); * fwnode_handle_get - Obtain a reference to a device node * @fwnode: Pointer to the device node to obtain the reference to. * - * Returns the fwnode handle. + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * + * Return: the fwnode handle. */ struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode) { @@ -841,6 +877,8 @@ EXPORT_SYMBOL_GPL(fwnode_handle_put); * fwnode_device_is_available - check if a device is available for use * @fwnode: Pointer to the fwnode of the device. * + * Return: true if device is available for use. Otherwise, returns false. + * * For fwnode node types that don't implement the .device_is_available() * operation, this function returns true. */ @@ -859,6 +897,8 @@ EXPORT_SYMBOL_GPL(fwnode_device_is_available); /** * device_get_child_node_count - return the number of child nodes for device * @dev: Device to cound the child nodes for + * + * Return: the number of child nodes for a given device. */ unsigned int device_get_child_node_count(const struct device *dev) { @@ -934,7 +974,7 @@ EXPORT_SYMBOL_GPL(device_get_phy_mode); * @fwnode: Pointer to the firmware node * @index: Index of the IO range * - * Returns a pointer to the mapped memory. + * Return: a pointer to the mapped memory. */ void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index) { @@ -947,8 +987,8 @@ EXPORT_SYMBOL(fwnode_iomap); * @fwnode: Pointer to the firmware node * @index: Zero-based index of the IRQ * - * Returns Linux IRQ number on success. Other values are determined - * accordingly to acpi_/of_ irq_get() operation. + * Return: Linux IRQ number on success. Other values are determined + * according to acpi_irq_get() or of_irq_get() operation. */ int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { @@ -967,8 +1007,7 @@ EXPORT_SYMBOL(fwnode_irq_get); * number of the IRQ resource corresponding to the index of the matched * string. * - * Return: - * Linux IRQ number on success, or negative errno otherwise. + * Return: Linux IRQ number on success, or negative errno otherwise. */ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name) { @@ -990,7 +1029,11 @@ EXPORT_SYMBOL(fwnode_irq_get_byname); * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * - * Returns an endpoint firmware node pointer or %NULL if no more endpoints + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. Note that this function also puts a reference to @prev + * unconditionally. + * + * Return: an endpoint firmware node pointer or %NULL if no more endpoints * are available. */ struct fwnode_handle * @@ -1030,6 +1073,9 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint); * fwnode_graph_get_port_parent - Return the device fwnode of a port endpoint * @endpoint: Endpoint firmware node of the port * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * * Return: the firmware node of the device the @endpoint belongs to. */ struct fwnode_handle * @@ -1051,6 +1097,9 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_port_parent); * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote device the @fwnode points to. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_port_parent(const struct fwnode_handle *fwnode) @@ -1071,6 +1120,9 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port_parent); * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote port the @fwnode points to. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_port(const struct fwnode_handle *fwnode) @@ -1084,6 +1136,9 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port); * @fwnode: Endpoint firmware node pointing to the remote endpoint * * Extracts firmware node of a remote endpoint the @fwnode points to. + * + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. */ struct fwnode_handle * fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) @@ -1111,8 +1166,11 @@ static bool fwnode_graph_remote_available(struct fwnode_handle *ep) * @endpoint: identifier of the endpoint node under the port node * @flags: fwnode lookup flags * - * Return the fwnode handle of the local endpoint corresponding the port and - * endpoint IDs or NULL if not found. + * The caller is responsible for calling fwnode_handle_put() on the returned + * fwnode pointer. + * + * Return: the fwnode handle of the local endpoint corresponding the port and + * endpoint IDs or %NULL if not found. * * If FWNODE_GRAPH_ENDPOINT_NEXT is passed in @flags and the specified endpoint * has not been found, look for the closest endpoint ID greater than the @@ -1120,9 +1178,6 @@ static bool fwnode_graph_remote_available(struct fwnode_handle *ep) * * Does not return endpoints that belong to disabled devices or endpoints that * are unconnected, unless FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags. - * - * The returned endpoint needs to be released by calling fwnode_handle_put() on - * it when it is not needed any more. */ struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, @@ -1328,7 +1383,8 @@ EXPORT_SYMBOL_GPL(fwnode_connection_find_match); * @fwnode and other device nodes. @match will be used to convert the * connection description to data the caller is expecting to be returned * through the @matches array. - * If @matches is NULL @matches_len is ignored and the total number of resolved + * + * If @matches is %NULL @matches_len is ignored and the total number of resolved * matches is returned. * * Return: Number of matches resolved, or negative errno. -- GitLab From 0433686c6092f65b552eadad651f620e51b6aad1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Feb 2023 22:07:45 +0200 Subject: [PATCH 0240/5631] devres: Pass unique name of the resource to devm_add_action() Pass the unique name of the resource to devm_add_action(), so it will be easier to debug managed resources. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230224200745.17324-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/devres.c | 11 ++++++----- include/linux/device.h | 5 ++++- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/base/devres.c b/drivers/base/devres.c index c0e100074aa3..5c998cfac335 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -722,20 +722,21 @@ static void devm_action_release(struct device *dev, void *res) } /** - * devm_add_action() - add a custom action to list of managed resources + * __devm_add_action() - add a custom action to list of managed resources * @dev: Device that owns the action * @action: Function that should be called * @data: Pointer to data passed to @action implementation + * @name: Name of the resource (for debugging purposes) * * This adds a custom action to the list of managed resources so that * it gets executed as part of standard resource unwinding. */ -int devm_add_action(struct device *dev, void (*action)(void *), void *data) +int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name) { struct action_devres *devres; - devres = devres_alloc(devm_action_release, - sizeof(struct action_devres), GFP_KERNEL); + devres = __devres_alloc_node(devm_action_release, sizeof(struct action_devres), + GFP_KERNEL, NUMA_NO_NODE, name); if (!devres) return -ENOMEM; @@ -745,7 +746,7 @@ int devm_add_action(struct device *dev, void (*action)(void *), void *data) devres_add(dev, devres); return 0; } -EXPORT_SYMBOL_GPL(devm_add_action); +EXPORT_SYMBOL_GPL(__devm_add_action); /** * devm_remove_action() - removes previously added custom action diff --git a/include/linux/device.h b/include/linux/device.h index 19b6ba478fbf..0f128520f6e5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -243,10 +243,13 @@ void __iomem *devm_of_iomap(struct device *dev, resource_size_t *size); /* allows to add/remove a custom action to devres stack */ -int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); +int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); +#define devm_add_action(release, action, data) \ + __devm_add_action(release, action, data, #action) + static inline int devm_add_action_or_reset(struct device *dev, void (*action)(void *), void *data) { -- GitLab From b0f64c80cb8c1adcdae59fa09bbc9d34adc29911 Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Fri, 10 Mar 2023 15:34:15 +0700 Subject: [PATCH 0241/5631] misc: smpro-errmon: Add DIMM 2x Refresh rate event In high temperature condition, JEDEC spec requires memory controller to double the refresh rate. This commit adds event_dimm_2x_refresh sysfs to report that events for all memory channels. Signed-off-by: Quan Nguyen Link: https://lore.kernel.org/r/20230310083416.3670980-2-quan@os.amperecomputing.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/sysfs-bus-platform-devices-ampere-smpro | 9 ++++++--- drivers/misc/smpro-errmon.c | 5 +++++ 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro b/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro index ca93c215ef99..14b58c893df5 100644 --- a/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro +++ b/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro @@ -234,8 +234,8 @@ Description: For details, see section `5.10 RAS Internal Error Register Definitions, Altra Family Soc BMC Interface Specification`. -What: /sys/bus/platform/devices/smpro-errmon.*/event_[vrd_warn_fault|vrd_hot|dimm_hot] -KernelVersion: 6.1 +What: /sys/bus/platform/devices/smpro-errmon.*/event_[vrd_warn_fault|vrd_hot|dimm_hot|dimm_2x_refresh] +KernelVersion: 6.1 (event_[vrd_warn_fault|vrd_hot|dimm_hot]), 6.4 (event_dimm_2x_refresh) Contact: Quan Nguyen Description: (RO) Contains the detail information in case of VRD/DIMM warning/hot events @@ -258,8 +258,11 @@ Description: +---------------+---------------------------------------------------------------+---------------------+ | DIMM HOT | /sys/bus/platform/devices/smpro-errmon.*/event_dimm_hot | DIMM Hot | +---------------+---------------------------------------------------------------+---------------------+ + | DIMM 2X | /sys/bus/platform/devices/smpro-errmon.*/event_dimm_2x_refresh| DIMM 2x refresh rate| + | REFRESH RATE | | event in high temp | + +---------------+---------------------------------------------------------------+---------------------+ - For more details, see section `5.7 GPI Status Registers, + For more details, see section `5.7 GPI Status Registers and 5.9 Memory Error Register Definitions, Altra Family Soc BMC Interface Specification`. What: /sys/bus/platform/devices/smpro-misc.*/boot_progress diff --git a/drivers/misc/smpro-errmon.c b/drivers/misc/smpro-errmon.c index d1431d419aa4..1635e881aefb 100644 --- a/drivers/misc/smpro-errmon.c +++ b/drivers/misc/smpro-errmon.c @@ -67,6 +67,7 @@ #define VRD_WARN_FAULT_EVENT_DATA 0x78 #define VRD_HOT_EVENT_DATA 0x79 #define DIMM_HOT_EVENT_DATA 0x7A +#define DIMM_2X_REFRESH_EVENT_DATA 0x96 #define MAX_READ_BLOCK_LENGTH 48 @@ -190,6 +191,7 @@ enum EVENT_TYPES { VRD_WARN_FAULT_EVENT, VRD_HOT_EVENT, DIMM_HOT_EVENT, + DIMM_2X_REFRESH_EVENT, NUM_EVENTS_TYPE, }; @@ -198,6 +200,7 @@ static u8 smpro_event_table[NUM_EVENTS_TYPE] = { VRD_WARN_FAULT_EVENT_DATA, VRD_HOT_EVENT_DATA, DIMM_HOT_EVENT_DATA, + DIMM_2X_REFRESH_EVENT_DATA, }; static ssize_t smpro_event_data_read(struct device *dev, @@ -463,6 +466,7 @@ static DEVICE_ATTR_RO(warn_pmpro); EVENT_RO(vrd_warn_fault, VRD_WARN_FAULT_EVENT); EVENT_RO(vrd_hot, VRD_HOT_EVENT); EVENT_RO(dimm_hot, DIMM_HOT_EVENT); +EVENT_RO(dimm_2x_refresh, DIMM_2X_REFRESH_EVENT); static struct attribute *smpro_errmon_attrs[] = { &dev_attr_overflow_core_ce.attr, @@ -488,6 +492,7 @@ static struct attribute *smpro_errmon_attrs[] = { &dev_attr_event_vrd_warn_fault.attr, &dev_attr_event_vrd_hot.attr, &dev_attr_event_dimm_hot.attr, + &dev_attr_event_dimm_2x_refresh.attr, NULL }; -- GitLab From c2c99326cc0176cbc3e7c11e97db11ca56077d10 Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Fri, 10 Mar 2023 15:34:16 +0700 Subject: [PATCH 0242/5631] misc: smpro-errmon: Add dimm training failure syndrome Adds event_dimm[0-15]_syndrome sysfs to report the failure syndrome to BMC when DIMM training failed. Signed-off-by: Quan Nguyen Link: https://lore.kernel.org/r/20230310083416.3670980-3-quan@os.amperecomputing.com Signed-off-by: Greg Kroah-Hartman --- .../sysfs-bus-platform-devices-ampere-smpro | 10 +++ drivers/misc/smpro-errmon.c | 77 +++++++++++++++++++ 2 files changed, 87 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro b/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro index 14b58c893df5..fead760dcf77 100644 --- a/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro +++ b/Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro @@ -265,6 +265,16 @@ Description: For more details, see section `5.7 GPI Status Registers and 5.9 Memory Error Register Definitions, Altra Family Soc BMC Interface Specification`. +What: /sys/bus/platform/devices/smpro-errmon.*/event_dimm[0-15]_syndrome +KernelVersion: 6.4 +Contact: Quan Nguyen +Description: + (RO) The sysfs returns the 2-byte DIMM failure syndrome data for slot + 0-15 if it failed to initialize. + + For more details, see section `5.11 Boot Stage Register Definitions, + Altra Family Soc BMC Interface Specification`. + What: /sys/bus/platform/devices/smpro-misc.*/boot_progress KernelVersion: 6.1 Contact: Quan Nguyen diff --git a/drivers/misc/smpro-errmon.c b/drivers/misc/smpro-errmon.c index 1635e881aefb..a1f0b2c77fac 100644 --- a/drivers/misc/smpro-errmon.c +++ b/drivers/misc/smpro-errmon.c @@ -47,6 +47,12 @@ #define WARN_PMPRO_INFO_LO 0xAC #define WARN_PMPRO_INFO_HI 0xAD +/* Boot Stage Register */ +#define BOOTSTAGE 0xB0 +#define DIMM_SYNDROME_SEL 0xB4 +#define DIMM_SYNDROME_ERR 0xB5 +#define DIMM_SYNDROME_STAGE 4 + /* PCIE Error Registers */ #define PCIE_CE_ERR_CNT 0xC0 #define PCIE_CE_ERR_LEN 0xC1 @@ -468,6 +474,61 @@ EVENT_RO(vrd_hot, VRD_HOT_EVENT); EVENT_RO(dimm_hot, DIMM_HOT_EVENT); EVENT_RO(dimm_2x_refresh, DIMM_2X_REFRESH_EVENT); +static ssize_t smpro_dimm_syndrome_read(struct device *dev, struct device_attribute *da, + char *buf, unsigned int slot) +{ + struct smpro_errmon *errmon = dev_get_drvdata(dev); + unsigned int data; + int ret; + + ret = regmap_read(errmon->regmap, BOOTSTAGE, &data); + if (ret) + return ret; + + /* check for valid stage */ + data = (data >> 8) & 0xff; + if (data != DIMM_SYNDROME_STAGE) + return ret; + + /* Write the slot ID to retrieve Error Syndrome */ + ret = regmap_write(errmon->regmap, DIMM_SYNDROME_SEL, slot); + if (ret) + return ret; + + /* Read the Syndrome error */ + ret = regmap_read(errmon->regmap, DIMM_SYNDROME_ERR, &data); + if (ret || !data) + return ret; + + return sysfs_emit(buf, "%04x\n", data); +} + +#define EVENT_DIMM_SYNDROME(_slot) \ + static ssize_t event_dimm##_slot##_syndrome_show(struct device *dev, \ + struct device_attribute *da, \ + char *buf) \ + { \ + return smpro_dimm_syndrome_read(dev, da, buf, _slot); \ + } \ + static DEVICE_ATTR_RO(event_dimm##_slot##_syndrome) + +EVENT_DIMM_SYNDROME(0); +EVENT_DIMM_SYNDROME(1); +EVENT_DIMM_SYNDROME(2); +EVENT_DIMM_SYNDROME(3); +EVENT_DIMM_SYNDROME(4); +EVENT_DIMM_SYNDROME(5); +EVENT_DIMM_SYNDROME(6); +EVENT_DIMM_SYNDROME(7); +EVENT_DIMM_SYNDROME(8); +EVENT_DIMM_SYNDROME(9); +EVENT_DIMM_SYNDROME(10); +EVENT_DIMM_SYNDROME(11); +EVENT_DIMM_SYNDROME(12); +EVENT_DIMM_SYNDROME(13); +EVENT_DIMM_SYNDROME(14); +EVENT_DIMM_SYNDROME(15); + static struct attribute *smpro_errmon_attrs[] = { &dev_attr_overflow_core_ce.attr, &dev_attr_overflow_core_ue.attr, @@ -493,6 +554,22 @@ static struct attribute *smpro_errmon_attrs[] = { &dev_attr_event_vrd_hot.attr, &dev_attr_event_dimm_hot.attr, &dev_attr_event_dimm_2x_refresh.attr, + &dev_attr_event_dimm0_syndrome.attr, + &dev_attr_event_dimm1_syndrome.attr, + &dev_attr_event_dimm2_syndrome.attr, + &dev_attr_event_dimm3_syndrome.attr, + &dev_attr_event_dimm4_syndrome.attr, + &dev_attr_event_dimm5_syndrome.attr, + &dev_attr_event_dimm6_syndrome.attr, + &dev_attr_event_dimm7_syndrome.attr, + &dev_attr_event_dimm8_syndrome.attr, + &dev_attr_event_dimm9_syndrome.attr, + &dev_attr_event_dimm10_syndrome.attr, + &dev_attr_event_dimm11_syndrome.attr, + &dev_attr_event_dimm12_syndrome.attr, + &dev_attr_event_dimm13_syndrome.attr, + &dev_attr_event_dimm14_syndrome.attr, + &dev_attr_event_dimm15_syndrome.attr, NULL }; -- GitLab From 14853a0676c126aad836eb249499552fa9d6e85a Mon Sep 17 00:00:00 2001 From: Slark Xiao Date: Fri, 10 Mar 2023 18:17:15 +0800 Subject: [PATCH 0243/5631] bus: mhi: host: pci_generic: Revert "Add a secondary AT port to Telit FN990" This reverts commit 2d5253a096c6057bbf7caa5520856dcdf7eca8bb. There are 2 commits with commit message "Add a secondary AT port to Telit FN990": commit 2d5253a096c6 ("bus: mhi: host: pci_generic: Add a secondary AT port to Telit FN990") commit 479aa3b0ec2e ("bus: mhi: host: pci_generic: Add a secondary AT port to Telit FN990") This turned out to be due to the patch getting applied through different trees and git settled on a resolution while applying it second time. But the second AT port of Foxconn devices don't work in PCIe mode. So the second commit needs to be reverted. Cc: stable@vger.kernel.org # 6.2 Fixes: 2d5253a096c6 ("bus: mhi: host: pci_generic: Add a secondary AT port to Telit FN990") Signed-off-by: Slark Xiao Reviewed-by: Fabio Porcedda Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230310101715.69209-1-slark_xiao@163.com [mani: massaged the commit message a bit, added fixes tag and CCed stable] Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/pci_generic.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 6e13c43a84d1..91d02f84ba21 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -343,8 +343,6 @@ static const struct mhi_channel_config mhi_foxconn_sdx55_channels[] = { MHI_CHANNEL_CONFIG_DL(13, "MBIM", 32, 0), MHI_CHANNEL_CONFIG_UL(32, "DUN", 32, 0), MHI_CHANNEL_CONFIG_DL(33, "DUN", 32, 0), - MHI_CHANNEL_CONFIG_UL(92, "DUN2", 32, 1), - MHI_CHANNEL_CONFIG_DL(93, "DUN2", 32, 1), MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0_MBIM", 128, 2), MHI_CHANNEL_CONFIG_HW_DL(101, "IP_HW0_MBIM", 128, 3), }; -- GitLab From 88ddf98aa511a5e0c2c76e5dfcf3c6b2581d0e85 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Feb 2023 16:20:18 +0100 Subject: [PATCH 0244/5631] clk: renesas: r8a77970: Add Z2 clock Add support for the Z2 (Cortex-A53 System CPU) clock on R-Car V3M, which uses a fixed SYS-CPU divider. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/6a9169e5bc92c2b9549292769a0814e04b9147cf.1676560357.git.geert+renesas@glider.be --- drivers/clk/renesas/r8a77970-cpg-mssr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/renesas/r8a77970-cpg-mssr.c b/drivers/clk/renesas/r8a77970-cpg-mssr.c index 0f59c84229a8..7e90e94c4b68 100644 --- a/drivers/clk/renesas/r8a77970-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77970-cpg-mssr.c @@ -76,6 +76,7 @@ static const struct cpg_core_clk r8a77970_core_clks[] __initconst = { DEF_FIXED(".pll1_div4", CLK_PLL1_DIV4, CLK_PLL1_DIV2, 2, 1), /* Core Clock Outputs */ + DEF_FIXED("z2", R8A77970_CLK_Z2, CLK_PLL1_DIV4, 1, 1), DEF_FIXED("ztr", R8A77970_CLK_ZTR, CLK_PLL1_DIV2, 6, 1), DEF_FIXED("ztrd2", R8A77970_CLK_ZTRD2, CLK_PLL1_DIV2, 12, 1), DEF_FIXED("zt", R8A77970_CLK_ZT, CLK_PLL1_DIV2, 4, 1), -- GitLab From 85af88b8f7d606be8a9b89fcda61a5df28a2028d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 16 Feb 2023 16:20:19 +0100 Subject: [PATCH 0245/5631] clk: renesas: r8a77980: Add Z2 clock Add support for the Z2 (Cortex-A53 System CPU) clock on R-Car V3H, which uses a fixed SYS-CPU divider. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/aad9eaa57acf65cbe43e4d374066a72d760d54d8.1676560357.git.geert+renesas@glider.be --- drivers/clk/renesas/r8a77980-cpg-mssr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/renesas/r8a77980-cpg-mssr.c b/drivers/clk/renesas/r8a77980-cpg-mssr.c index 6dc63eaf1155..bac92c606d0b 100644 --- a/drivers/clk/renesas/r8a77980-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77980-cpg-mssr.c @@ -72,6 +72,7 @@ static const struct cpg_core_clk r8a77980_core_clks[] __initconst = { DEF_RATE(".oco", CLK_OCO, 32768), /* Core Clock Outputs */ + DEF_FIXED("z2", R8A77980_CLK_Z2, CLK_PLL2, 4, 1), DEF_FIXED("ztr", R8A77980_CLK_ZTR, CLK_PLL1_DIV2, 6, 1), DEF_FIXED("ztrd2", R8A77980_CLK_ZTRD2, CLK_PLL1_DIV2, 12, 1), DEF_FIXED("zt", R8A77980_CLK_ZT, CLK_PLL1_DIV2, 4, 1), -- GitLab From a1aae0a6b122300d057e30487fc8291d3cd730ca Mon Sep 17 00:00:00 2001 From: Ralph Siemsen Date: Wed, 1 Mar 2023 16:55:17 -0500 Subject: [PATCH 0246/5631] clk: renesas: r9a06g032: Improve readability Several small readability improvements: - Move enum gate_type definition up and add comments to each field. - Use this enum instead of generic uint32_t type in clock desc struct. - Tidy up bitfield syntax and comments in clock desc structure - Reformat macros for building clock desc to have one assignment per line There is no functional change. Signed-off-by: Ralph Siemsen Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230301215520.828455-2-ralph.siemsen@linaro.org Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a06g032-clocks.c | 121 ++++++++++++++++--------- 1 file changed, 80 insertions(+), 41 deletions(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index 087146f2ee06..cc479d95ef55 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -34,64 +34,103 @@ struct r9a06g032_gate { scon, mirack, mistat; }; +enum gate_type { + K_GATE = 0, /* gate which enable/disable */ + K_FFC, /* fixed factor clock */ + K_DIV, /* divisor */ + K_BITSEL, /* special for UARTs */ + K_DUALGATE /* special for UARTs */ +}; + /* This is used to describe a clock for instantiation */ struct r9a06g032_clkdesc { const char *name; - uint32_t managed: 1; - uint32_t type: 3; - uint32_t index: 8; - uint32_t source : 8; /* source index + 1 (0 == none) */ - /* these are used to populate the bitsel struct */ + uint32_t managed:1; + enum gate_type type:3; + uint32_t index:8; + uint32_t source:8; /* source index + 1 (0 == none) */ union { + /* type = K_GATE */ struct r9a06g032_gate gate; - /* for dividers */ + /* type = K_DIV */ struct { - unsigned int div_min : 10, div_max : 10, reg: 10; + unsigned int div_min:10, div_max:10, reg:10; u16 div_table[4]; }; - /* For fixed-factor ones */ + /* type = K_FFC */ struct { u16 div, mul; }; - /* for dual gate */ + /* type = K_DUALGATE */ struct { - uint16_t group : 1; + uint16_t group:1; u16 sel, g1, r1, g2, r2; } dual; }; }; -#define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) \ - { .gate = _clk, .reset = _rst, \ - .ready = _rdy, .midle = _midle, \ - .scon = _scon, .mirack = _mirack, .mistat = _mistat } -#define D_GATE(_idx, _n, _src, ...) \ - { .type = K_GATE, .index = R9A06G032_##_idx, \ - .source = 1 + R9A06G032_##_src, .name = _n, \ - .gate = I_GATE(__VA_ARGS__) } -#define D_MODULE(_idx, _n, _src, ...) \ - { .type = K_GATE, .index = R9A06G032_##_idx, \ - .source = 1 + R9A06G032_##_src, .name = _n, \ - .managed = 1, .gate = I_GATE(__VA_ARGS__) } -#define D_ROOT(_idx, _n, _mul, _div) \ - { .type = K_FFC, .index = R9A06G032_##_idx, .name = _n, \ - .div = _div, .mul = _mul } -#define D_FFC(_idx, _n, _src, _div) \ - { .type = K_FFC, .index = R9A06G032_##_idx, \ - .source = 1 + R9A06G032_##_src, .name = _n, \ - .div = _div, .mul = 1} -#define D_DIV(_idx, _n, _src, _reg, _min, _max, ...) \ - { .type = K_DIV, .index = R9A06G032_##_idx, \ - .source = 1 + R9A06G032_##_src, .name = _n, \ - .reg = _reg, .div_min = _min, .div_max = _max, \ - .div_table = { __VA_ARGS__ } } -#define D_UGATE(_idx, _n, _src, _g, _g1, _r1, _g2, _r2) \ - { .type = K_DUALGATE, .index = R9A06G032_##_idx, \ - .source = 1 + R9A06G032_##_src, .name = _n, \ - .dual = { .group = _g, \ - .g1 = _g1, .r1 = _r1, .g2 = _g2, .r2 = _r2 }, } - -enum { K_GATE = 0, K_FFC, K_DIV, K_BITSEL, K_DUALGATE }; +#define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) { \ + .gate = _clk, \ + .reset = _rst, \ + .ready = _rdy, \ + .midle = _midle, \ + .scon = _scon, \ + .mirack = _mirack, \ + .mistat = _mistat \ +} +#define D_GATE(_idx, _n, _src, ...) { \ + .type = K_GATE, \ + .index = R9A06G032_##_idx, \ + .source = 1 + R9A06G032_##_src, \ + .name = _n, \ + .gate = I_GATE(__VA_ARGS__) \ +} +#define D_MODULE(_idx, _n, _src, ...) { \ + .type = K_GATE, \ + .index = R9A06G032_##_idx, \ + .source = 1 + R9A06G032_##_src, \ + .name = _n, \ + .managed = 1, \ + .gate = I_GATE(__VA_ARGS__) \ +} +#define D_ROOT(_idx, _n, _mul, _div) { \ + .type = K_FFC, \ + .index = R9A06G032_##_idx, \ + .name = _n, \ + .div = _div, \ + .mul = _mul \ +} +#define D_FFC(_idx, _n, _src, _div) { \ + .type = K_FFC, \ + .index = R9A06G032_##_idx, \ + .source = 1 + R9A06G032_##_src, \ + .name = _n, \ + .div = _div, \ + .mul = 1 \ +} +#define D_DIV(_idx, _n, _src, _reg, _min, _max, ...) { \ + .type = K_DIV, \ + .index = R9A06G032_##_idx, \ + .source = 1 + R9A06G032_##_src, \ + .name = _n, \ + .reg = _reg, \ + .div_min = _min, \ + .div_max = _max, \ + .div_table = { __VA_ARGS__ } \ +} +#define D_UGATE(_idx, _n, _src, _g, _g1, _r1, _g2, _r2) { \ + .type = K_DUALGATE, \ + .index = R9A06G032_##_idx, \ + .source = 1 + R9A06G032_##_src, \ + .name = _n, \ + .dual = { \ + .group = _g, \ + .g1 = _g1, \ + .r1 = _r1, \ + .g2 = _g2, \ + .r2 = _r2 \ + }, \ +} /* Internal clock IDs */ #define R9A06G032_CLKOUT 0 -- GitLab From 2689c123317a74e751069d68df9e9900993b6a63 Mon Sep 17 00:00:00 2001 From: Ralph Siemsen Date: Wed, 1 Mar 2023 16:55:18 -0500 Subject: [PATCH 0247/5631] clk: renesas: r9a06g032: Drop unused fields Drop three unused fields from the clock descriptor structure, and update the macros for filling such structures accordingly. The values for such fields are kept in the source code, now unused, in case they are needed later. Signed-off-by: Ralph Siemsen Reviewed-by: Miquel Raynal Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230301215520.828455-3-ralph.siemsen@linaro.org Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a06g032-clocks.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index cc479d95ef55..79b78e68c272 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -30,8 +30,9 @@ #define R9A06G032_SYSCTRL_DMAMUX 0xA0 struct r9a06g032_gate { - u16 gate, reset, ready, midle, - scon, mirack, mistat; + u16 gate, reset, ready, midle; + /* Unused fields omitted to save space */ + /* u16 scon, mirack, mistat; */ }; enum gate_type { @@ -69,14 +70,18 @@ struct r9a06g032_clkdesc { }; }; +/* + * The last three arguments are not currently used, + * but are kept in the r9a06g032_clocks table below. + */ #define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) { \ .gate = _clk, \ .reset = _rst, \ .ready = _rdy, \ .midle = _midle, \ - .scon = _scon, \ - .mirack = _mirack, \ - .mistat = _mistat \ + /* .scon = _scon, */ \ + /* .mirack = _mirack, */ \ + /* .mistat = _mistat */ \ } #define D_GATE(_idx, _n, _src, ...) { \ .type = K_GATE, \ -- GitLab From 5a5ca2c758c200663fdf5c04f71796a8f300151a Mon Sep 17 00:00:00 2001 From: Ralph Siemsen Date: Wed, 1 Mar 2023 16:55:19 -0500 Subject: [PATCH 0248/5631] clk: renesas: r9a06g032: Document structs Add some kerneldoc comments for the structures. Signed-off-by: Ralph Siemsen Reviewed-by: Miquel Raynal Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230301215520.828455-4-ralph.siemsen@linaro.org Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a06g032-clocks.c | 50 +++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index 79b78e68c272..689c25ef33bc 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -29,6 +29,27 @@ #define R9A06G032_SYSCTRL_USB_H2MODE (1<<1) #define R9A06G032_SYSCTRL_DMAMUX 0xA0 +/** + * struct r9a06g032_gate - clock-related control bits + * @gate: clock enable/disable + * @reset: clock module reset (active low) + * @ready: enables NoC forwarding of read/write requests to device, + * (eg. device is ready to handle read/write requests) + * @midle: request to idle the NoC interconnect + * + * Each of these fields describes a single bit in a register, + * which controls some aspect of clock gating. The @gate field + * is mandatory, this one enables/disables the clock. The + * other fields are optional, with zero indicating "not used". + * + * In most cases there is a @reset bit which needs to be + * de-asserted to bring the module out of reset. + * + * Modules may also need to signal when they are @ready to + * handle requests (read/writes) from the NoC interconnect. + * + * Similarly, the @midle bit is used to idle the master. + */ struct r9a06g032_gate { u16 gate, reset, ready, midle; /* Unused fields omitted to save space */ @@ -43,7 +64,34 @@ enum gate_type { K_DUALGATE /* special for UARTs */ }; -/* This is used to describe a clock for instantiation */ +/** + * struct r9a06g032_clkdesc - describe a single clock + * @name: string describing this clock + * @managed: boolean indicating if this clock should be + * started/stopped as part of power management + * @type: see enum @gate_type + * @index: the ID of this clock element + * @source: the ID+1 of the parent clock element. + * Root clock uses ID of ~0 (PARENT_ID); + * @gate: clock enable/disable + * @div_min: smallest permitted clock divider + * @div_max: largest permitted clock divider + * @reg: clock divider register offset, in 32-bit words + * @div_table: optional list of fixed clock divider values; + * must be in ascending order, zero for unused + * @div: divisor for fixed-factor clock + * @mul: multiplier for fixed-factor clock + * @group: UART group, 0=UART0/1/2, 1=UART3/4/5/6/7 + * @sel: select either g1/r1 or g2/r2 as clock source + * @g1: 1st source gate (clock enable/disable) + * @r1: 1st source reset (module reset) + * @g2: 2nd source gate (clock enable/disable) + * @r2: 2nd source reset (module reset) + * + * Describes a single element in the clock tree hierarchy. + * As there are quite a large number of clock elements, this + * structure is packed tightly to conserve space. + */ struct r9a06g032_clkdesc { const char *name; uint32_t managed:1; -- GitLab From 1ef48138f90785ba7091fb8fa317039cd3cf9494 Mon Sep 17 00:00:00 2001 From: Ralph Siemsen Date: Wed, 1 Mar 2023 16:55:20 -0500 Subject: [PATCH 0249/5631] clk: renesas: r9a06g032: Improve clock tables Each entry in the clock table specifies a number of individual bits in registers, for contolling clock reset, gaiting, etc. These reg/bit were packed into a u16 to save space. The combined value is difficult to understand when reviewing the clock table entries. Introduce a "struct regbit" which still occupies only 16 bits, but allows the register and bit values to be specified explicitly. Convert all previous uses of u16 for reg/bit into "struct regbit". The bulk of this patch converts the clock table to use struct regbit, making use of the RB() helper macro. The conversion was automated by script, and as a further verification, the compiled binary of the table was compared before/after the change (with objdump -D). The clk_rdesc_set() function now checks for zero reg/bit internally. This allows callers of that function to remove those checks. Signed-off-by: Ralph Siemsen Reviewed-by: Miquel Raynal Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230301215520.828455-5-ralph.siemsen@linaro.org Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r9a06g032-clocks.c | 560 ++++++++++++++++++------- 1 file changed, 407 insertions(+), 153 deletions(-) diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c index 689c25ef33bc..40828616f723 100644 --- a/drivers/clk/renesas/r9a06g032-clocks.c +++ b/drivers/clk/renesas/r9a06g032-clocks.c @@ -29,6 +29,34 @@ #define R9A06G032_SYSCTRL_USB_H2MODE (1<<1) #define R9A06G032_SYSCTRL_DMAMUX 0xA0 +/** + * struct regbit - describe one bit in a register + * @reg: offset of register relative to base address, + * expressed in units of 32-bit words (not bytes), + * @bit: which bit (0 to 31) in the register + * + * This structure is used to compactly encode the location + * of a single bit in a register. Five bits are needed to + * encode the bit number. With uint16_t data type, this + * leaves 11 bits to encode a register offset up to 2047. + * + * Since registers are aligned on 32-bit boundaries, the + * offset will be specified in 32-bit words rather than bytes. + * This allows encoding an offset up to 0x1FFC (8188) bytes. + * + * Helper macro RB() takes care of converting the register + * offset from bytes to 32-bit words. + */ +struct regbit { + u16 bit:5; + u16 reg:11; +}; + +#define RB(_reg, _bit) ((struct regbit) { \ + .reg = (_reg) / 4, \ + .bit = (_bit) \ +}) + /** * struct r9a06g032_gate - clock-related control bits * @gate: clock enable/disable @@ -51,9 +79,9 @@ * Similarly, the @midle bit is used to idle the master. */ struct r9a06g032_gate { - u16 gate, reset, ready, midle; + struct regbit gate, reset, ready, midle; /* Unused fields omitted to save space */ - /* u16 scon, mirack, mistat; */ + /* struct regbit scon, mirack, mistat */; }; enum gate_type { @@ -113,7 +141,7 @@ struct r9a06g032_clkdesc { /* type = K_DUALGATE */ struct { uint16_t group:1; - u16 sel, g1, r1, g2, r2; + struct regbit sel, g1, r1, g2, r2; } dual; }; }; @@ -252,58 +280,160 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = { D_DIV(DIV_SDIO1, "div_sdio1", CLKOUT, 75, 20, 128), D_DIV(DIV_SWITCH, "div_switch", CLKOUT, 37, 5, 40), D_DIV(DIV_UART, "div_uart", CLKOUT, 79, 12, 128), - D_GATE(CLK_25_PG4, "clk_25_pg4", CLKOUT_D40, 0x749, 0x74a, 0x74b, 0, 0xae3, 0, 0), - D_GATE(CLK_25_PG5, "clk_25_pg5", CLKOUT_D40, 0x74c, 0x74d, 0x74e, 0, 0xae4, 0, 0), - D_GATE(CLK_25_PG6, "clk_25_pg6", CLKOUT_D40, 0x74f, 0x750, 0x751, 0, 0xae5, 0, 0), - D_GATE(CLK_25_PG7, "clk_25_pg7", CLKOUT_D40, 0x752, 0x753, 0x754, 0, 0xae6, 0, 0), - D_GATE(CLK_25_PG8, "clk_25_pg8", CLKOUT_D40, 0x755, 0x756, 0x757, 0, 0xae7, 0, 0), - D_GATE(CLK_ADC, "clk_adc", DIV_ADC, 0x1ea, 0x1eb, 0, 0, 0, 0, 0), - D_GATE(CLK_ECAT100, "clk_ecat100", CLKOUT_D10, 0x405, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_HSR100, "clk_hsr100", CLKOUT_D10, 0x483, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_I2C0, "clk_i2c0", DIV_I2C, 0x1e6, 0x1e7, 0, 0, 0, 0, 0), - D_GATE(CLK_I2C1, "clk_i2c1", DIV_I2C, 0x1e8, 0x1e9, 0, 0, 0, 0, 0), - D_GATE(CLK_MII_REF, "clk_mii_ref", CLKOUT_D40, 0x342, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_NAND, "clk_nand", DIV_NAND, 0x284, 0x285, 0, 0, 0, 0, 0), - D_GATE(CLK_NOUSBP2_PG6, "clk_nousbp2_pg6", DIV_P2_PG, 0x774, 0x775, 0, 0, 0, 0, 0), - D_GATE(CLK_P1_PG2, "clk_p1_pg2", DIV_P1_PG, 0x862, 0x863, 0, 0, 0, 0, 0), - D_GATE(CLK_P1_PG3, "clk_p1_pg3", DIV_P1_PG, 0x864, 0x865, 0, 0, 0, 0, 0), - D_GATE(CLK_P1_PG4, "clk_p1_pg4", DIV_P1_PG, 0x866, 0x867, 0, 0, 0, 0, 0), - D_GATE(CLK_P4_PG3, "clk_p4_pg3", DIV_P4_PG, 0x824, 0x825, 0, 0, 0, 0, 0), - D_GATE(CLK_P4_PG4, "clk_p4_pg4", DIV_P4_PG, 0x826, 0x827, 0, 0, 0, 0, 0), - D_GATE(CLK_P6_PG1, "clk_p6_pg1", DIV_P6_PG, 0x8a0, 0x8a1, 0x8a2, 0, 0xb60, 0, 0), - D_GATE(CLK_P6_PG2, "clk_p6_pg2", DIV_P6_PG, 0x8a3, 0x8a4, 0x8a5, 0, 0xb61, 0, 0), - D_GATE(CLK_P6_PG3, "clk_p6_pg3", DIV_P6_PG, 0x8a6, 0x8a7, 0x8a8, 0, 0xb62, 0, 0), - D_GATE(CLK_P6_PG4, "clk_p6_pg4", DIV_P6_PG, 0x8a9, 0x8aa, 0x8ab, 0, 0xb63, 0, 0), - D_MODULE(CLK_PCI_USB, "clk_pci_usb", CLKOUT_D40, 0xe6, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_QSPI0, "clk_qspi0", DIV_QSPI0, 0x2a4, 0x2a5, 0, 0, 0, 0, 0), - D_GATE(CLK_QSPI1, "clk_qspi1", DIV_QSPI1, 0x484, 0x485, 0, 0, 0, 0, 0), - D_GATE(CLK_RGMII_REF, "clk_rgmii_ref", CLKOUT_D8, 0x340, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_RMII_REF, "clk_rmii_ref", CLKOUT_D20, 0x341, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_SDIO0, "clk_sdio0", DIV_SDIO0, 0x64, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_SDIO1, "clk_sdio1", DIV_SDIO1, 0x644, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_SERCOS100, "clk_sercos100", CLKOUT_D10, 0x425, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_SLCD, "clk_slcd", DIV_P1_PG, 0x860, 0x861, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI0, "clk_spi0", DIV_P3_PG, 0x7e0, 0x7e1, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI1, "clk_spi1", DIV_P3_PG, 0x7e2, 0x7e3, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI2, "clk_spi2", DIV_P3_PG, 0x7e4, 0x7e5, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI3, "clk_spi3", DIV_P3_PG, 0x7e6, 0x7e7, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI4, "clk_spi4", DIV_P4_PG, 0x820, 0x821, 0, 0, 0, 0, 0), - D_GATE(CLK_SPI5, "clk_spi5", DIV_P4_PG, 0x822, 0x823, 0, 0, 0, 0, 0), - D_GATE(CLK_SWITCH, "clk_switch", DIV_SWITCH, 0x982, 0x983, 0, 0, 0, 0, 0), + D_GATE(CLK_25_PG4, "clk_25_pg4", CLKOUT_D40, RB(0xe8, 9), + RB(0xe8, 10), RB(0xe8, 11), RB(0x00, 0), + RB(0x15c, 3), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_25_PG5, "clk_25_pg5", CLKOUT_D40, RB(0xe8, 12), + RB(0xe8, 13), RB(0xe8, 14), RB(0x00, 0), + RB(0x15c, 4), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_25_PG6, "clk_25_pg6", CLKOUT_D40, RB(0xe8, 15), + RB(0xe8, 16), RB(0xe8, 17), RB(0x00, 0), + RB(0x15c, 5), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_25_PG7, "clk_25_pg7", CLKOUT_D40, RB(0xe8, 18), + RB(0xe8, 19), RB(0xe8, 20), RB(0x00, 0), + RB(0x15c, 6), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_25_PG8, "clk_25_pg8", CLKOUT_D40, RB(0xe8, 21), + RB(0xe8, 22), RB(0xe8, 23), RB(0x00, 0), + RB(0x15c, 7), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_ADC, "clk_adc", DIV_ADC, RB(0x3c, 10), + RB(0x3c, 11), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_ECAT100, "clk_ecat100", CLKOUT_D10, RB(0x80, 5), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_HSR100, "clk_hsr100", CLKOUT_D10, RB(0x90, 3), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_I2C0, "clk_i2c0", DIV_I2C, RB(0x3c, 6), + RB(0x3c, 7), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_I2C1, "clk_i2c1", DIV_I2C, RB(0x3c, 8), + RB(0x3c, 9), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_MII_REF, "clk_mii_ref", CLKOUT_D40, RB(0x68, 2), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_NAND, "clk_nand", DIV_NAND, RB(0x50, 4), + RB(0x50, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_NOUSBP2_PG6, "clk_nousbp2_pg6", DIV_P2_PG, RB(0xec, 20), + RB(0xec, 21), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P1_PG2, "clk_p1_pg2", DIV_P1_PG, RB(0x10c, 2), + RB(0x10c, 3), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P1_PG3, "clk_p1_pg3", DIV_P1_PG, RB(0x10c, 4), + RB(0x10c, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P1_PG4, "clk_p1_pg4", DIV_P1_PG, RB(0x10c, 6), + RB(0x10c, 7), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P4_PG3, "clk_p4_pg3", DIV_P4_PG, RB(0x104, 4), + RB(0x104, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P4_PG4, "clk_p4_pg4", DIV_P4_PG, RB(0x104, 6), + RB(0x104, 7), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P6_PG1, "clk_p6_pg1", DIV_P6_PG, RB(0x114, 0), + RB(0x114, 1), RB(0x114, 2), RB(0x00, 0), + RB(0x16c, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P6_PG2, "clk_p6_pg2", DIV_P6_PG, RB(0x114, 3), + RB(0x114, 4), RB(0x114, 5), RB(0x00, 0), + RB(0x16c, 1), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P6_PG3, "clk_p6_pg3", DIV_P6_PG, RB(0x114, 6), + RB(0x114, 7), RB(0x114, 8), RB(0x00, 0), + RB(0x16c, 2), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_P6_PG4, "clk_p6_pg4", DIV_P6_PG, RB(0x114, 9), + RB(0x114, 10), RB(0x114, 11), RB(0x00, 0), + RB(0x16c, 3), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(CLK_PCI_USB, "clk_pci_usb", CLKOUT_D40, RB(0x1c, 6), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_QSPI0, "clk_qspi0", DIV_QSPI0, RB(0x54, 4), + RB(0x54, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_QSPI1, "clk_qspi1", DIV_QSPI1, RB(0x90, 4), + RB(0x90, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_RGMII_REF, "clk_rgmii_ref", CLKOUT_D8, RB(0x68, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_RMII_REF, "clk_rmii_ref", CLKOUT_D20, RB(0x68, 1), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SDIO0, "clk_sdio0", DIV_SDIO0, RB(0x0c, 4), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SDIO1, "clk_sdio1", DIV_SDIO1, RB(0xc8, 4), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SERCOS100, "clk_sercos100", CLKOUT_D10, RB(0x84, 5), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SLCD, "clk_slcd", DIV_P1_PG, RB(0x10c, 0), + RB(0x10c, 1), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI0, "clk_spi0", DIV_P3_PG, RB(0xfc, 0), + RB(0xfc, 1), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI1, "clk_spi1", DIV_P3_PG, RB(0xfc, 2), + RB(0xfc, 3), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI2, "clk_spi2", DIV_P3_PG, RB(0xfc, 4), + RB(0xfc, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI3, "clk_spi3", DIV_P3_PG, RB(0xfc, 6), + RB(0xfc, 7), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI4, "clk_spi4", DIV_P4_PG, RB(0x104, 0), + RB(0x104, 1), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SPI5, "clk_spi5", DIV_P4_PG, RB(0x104, 2), + RB(0x104, 3), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SWITCH, "clk_switch", DIV_SWITCH, RB(0x130, 2), + RB(0x130, 3), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), D_DIV(DIV_MOTOR, "div_motor", CLKOUT_D5, 84, 2, 8), - D_MODULE(HCLK_ECAT125, "hclk_ecat125", CLKOUT_D8, 0x400, 0x401, 0, 0x402, 0, 0x440, 0x441), - D_MODULE(HCLK_PINCONFIG, "hclk_pinconfig", CLKOUT_D40, 0x740, 0x741, 0x742, 0, 0xae0, 0, 0), - D_MODULE(HCLK_SERCOS, "hclk_sercos", CLKOUT_D10, 0x420, 0x422, 0, 0x421, 0, 0x460, 0x461), - D_MODULE(HCLK_SGPIO2, "hclk_sgpio2", DIV_P5_PG, 0x8c3, 0x8c4, 0x8c5, 0, 0xb41, 0, 0), - D_MODULE(HCLK_SGPIO3, "hclk_sgpio3", DIV_P5_PG, 0x8c6, 0x8c7, 0x8c8, 0, 0xb42, 0, 0), - D_MODULE(HCLK_SGPIO4, "hclk_sgpio4", DIV_P5_PG, 0x8c9, 0x8ca, 0x8cb, 0, 0xb43, 0, 0), - D_MODULE(HCLK_TIMER0, "hclk_timer0", CLKOUT_D40, 0x743, 0x744, 0x745, 0, 0xae1, 0, 0), - D_MODULE(HCLK_TIMER1, "hclk_timer1", CLKOUT_D40, 0x746, 0x747, 0x748, 0, 0xae2, 0, 0), - D_MODULE(HCLK_USBF, "hclk_usbf", CLKOUT_D8, 0xe3, 0, 0, 0xe4, 0, 0x102, 0x103), - D_MODULE(HCLK_USBH, "hclk_usbh", CLKOUT_D8, 0xe0, 0xe1, 0, 0xe2, 0, 0x100, 0x101), - D_MODULE(HCLK_USBPM, "hclk_usbpm", CLKOUT_D8, 0xe5, 0, 0, 0, 0, 0, 0), - D_GATE(CLK_48_PG_F, "clk_48_pg_f", CLK_48, 0x78c, 0x78d, 0, 0x78e, 0, 0xb04, 0xb05), - D_GATE(CLK_48_PG4, "clk_48_pg4", CLK_48, 0x789, 0x78a, 0x78b, 0, 0xb03, 0, 0), + D_MODULE(HCLK_ECAT125, "hclk_ecat125", CLKOUT_D8, RB(0x80, 0), + RB(0x80, 1), RB(0x00, 0), RB(0x80, 2), + RB(0x00, 0), RB(0x88, 0), RB(0x88, 1)), + D_MODULE(HCLK_PINCONFIG, "hclk_pinconfig", CLKOUT_D40, RB(0xe8, 0), + RB(0xe8, 1), RB(0xe8, 2), RB(0x00, 0), + RB(0x15c, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SERCOS, "hclk_sercos", CLKOUT_D10, RB(0x84, 0), + RB(0x84, 2), RB(0x00, 0), RB(0x84, 1), + RB(0x00, 0), RB(0x8c, 0), RB(0x8c, 1)), + D_MODULE(HCLK_SGPIO2, "hclk_sgpio2", DIV_P5_PG, RB(0x118, 3), + RB(0x118, 4), RB(0x118, 5), RB(0x00, 0), + RB(0x168, 1), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SGPIO3, "hclk_sgpio3", DIV_P5_PG, RB(0x118, 6), + RB(0x118, 7), RB(0x118, 8), RB(0x00, 0), + RB(0x168, 2), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SGPIO4, "hclk_sgpio4", DIV_P5_PG, RB(0x118, 9), + RB(0x118, 10), RB(0x118, 11), RB(0x00, 0), + RB(0x168, 3), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_TIMER0, "hclk_timer0", CLKOUT_D40, RB(0xe8, 3), + RB(0xe8, 4), RB(0xe8, 5), RB(0x00, 0), + RB(0x15c, 1), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_TIMER1, "hclk_timer1", CLKOUT_D40, RB(0xe8, 6), + RB(0xe8, 7), RB(0xe8, 8), RB(0x00, 0), + RB(0x15c, 2), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_USBF, "hclk_usbf", CLKOUT_D8, RB(0x1c, 3), + RB(0x00, 0), RB(0x00, 0), RB(0x1c, 4), + RB(0x00, 0), RB(0x20, 2), RB(0x20, 3)), + D_MODULE(HCLK_USBH, "hclk_usbh", CLKOUT_D8, RB(0x1c, 0), + RB(0x1c, 1), RB(0x00, 0), RB(0x1c, 2), + RB(0x00, 0), RB(0x20, 0), RB(0x20, 1)), + D_MODULE(HCLK_USBPM, "hclk_usbpm", CLKOUT_D8, RB(0x1c, 5), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_48_PG_F, "clk_48_pg_f", CLK_48, RB(0xf0, 12), + RB(0xf0, 13), RB(0x00, 0), RB(0xf0, 14), + RB(0x00, 0), RB(0x160, 4), RB(0x160, 5)), + D_GATE(CLK_48_PG4, "clk_48_pg4", CLK_48, RB(0xf0, 9), + RB(0xf0, 10), RB(0xf0, 11), RB(0x00, 0), + RB(0x160, 3), RB(0x00, 0), RB(0x00, 0)), D_FFC(CLK_DDRPHY_PLLCLK_D4, "clk_ddrphy_pllclk_d4", CLK_DDRPHY_PLLCLK, 4), D_FFC(CLK_ECAT100_D4, "clk_ecat100_d4", CLK_ECAT100, 4), D_FFC(CLK_HSR100_D2, "clk_hsr100_d2", CLK_HSR100, 2), @@ -311,67 +441,187 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = { D_FFC(CLK_REF_SYNC_D8, "clk_ref_sync_d8", CLK_REF_SYNC, 8), D_FFC(CLK_SERCOS100_D2, "clk_sercos100_d2", CLK_SERCOS100, 2), D_DIV(DIV_CA7, "div_ca7", CLK_REF_SYNC, 57, 1, 4, 1, 2, 4), - D_MODULE(HCLK_CAN0, "hclk_can0", CLK_48, 0x783, 0x784, 0x785, 0, 0xb01, 0, 0), - D_MODULE(HCLK_CAN1, "hclk_can1", CLK_48, 0x786, 0x787, 0x788, 0, 0xb02, 0, 0), - D_MODULE(HCLK_DELTASIGMA, "hclk_deltasigma", DIV_MOTOR, 0x1ef, 0x1f0, 0x1f1, 0, 0, 0, 0), - D_MODULE(HCLK_PWMPTO, "hclk_pwmpto", DIV_MOTOR, 0x1ec, 0x1ed, 0x1ee, 0, 0, 0, 0), - D_MODULE(HCLK_RSV, "hclk_rsv", CLK_48, 0x780, 0x781, 0x782, 0, 0xb00, 0, 0), - D_MODULE(HCLK_SGPIO0, "hclk_sgpio0", DIV_MOTOR, 0x1e0, 0x1e1, 0x1e2, 0, 0, 0, 0), - D_MODULE(HCLK_SGPIO1, "hclk_sgpio1", DIV_MOTOR, 0x1e3, 0x1e4, 0x1e5, 0, 0, 0, 0), + D_MODULE(HCLK_CAN0, "hclk_can0", CLK_48, RB(0xf0, 3), + RB(0xf0, 4), RB(0xf0, 5), RB(0x00, 0), + RB(0x160, 1), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_CAN1, "hclk_can1", CLK_48, RB(0xf0, 6), + RB(0xf0, 7), RB(0xf0, 8), RB(0x00, 0), + RB(0x160, 2), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_DELTASIGMA, "hclk_deltasigma", DIV_MOTOR, RB(0x3c, 15), + RB(0x3c, 16), RB(0x3c, 17), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_PWMPTO, "hclk_pwmpto", DIV_MOTOR, RB(0x3c, 12), + RB(0x3c, 13), RB(0x3c, 14), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_RSV, "hclk_rsv", CLK_48, RB(0xf0, 0), + RB(0xf0, 1), RB(0xf0, 2), RB(0x00, 0), + RB(0x160, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SGPIO0, "hclk_sgpio0", DIV_MOTOR, RB(0x3c, 0), + RB(0x3c, 1), RB(0x3c, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SGPIO1, "hclk_sgpio1", DIV_MOTOR, RB(0x3c, 3), + RB(0x3c, 4), RB(0x3c, 5), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), D_DIV(RTOS_MDC, "rtos_mdc", CLK_REF_SYNC, 100, 80, 640, 80, 160, 320, 640), - D_GATE(CLK_CM3, "clk_cm3", CLK_REF_SYNC_D4, 0xba0, 0xba1, 0, 0xba2, 0, 0xbc0, 0xbc1), - D_GATE(CLK_DDRC, "clk_ddrc", CLK_DDRPHY_PLLCLK_D4, 0x323, 0x324, 0, 0, 0, 0, 0), - D_GATE(CLK_ECAT25, "clk_ecat25", CLK_ECAT100_D4, 0x403, 0x404, 0, 0, 0, 0, 0), - D_GATE(CLK_HSR50, "clk_hsr50", CLK_HSR100_D2, 0x484, 0x485, 0, 0, 0, 0, 0), - D_GATE(CLK_HW_RTOS, "clk_hw_rtos", CLK_REF_SYNC_D4, 0xc60, 0xc61, 0, 0, 0, 0, 0), - D_GATE(CLK_SERCOS50, "clk_sercos50", CLK_SERCOS100_D2, 0x424, 0x423, 0, 0, 0, 0, 0), - D_MODULE(HCLK_ADC, "hclk_adc", CLK_REF_SYNC_D8, 0x1af, 0x1b0, 0x1b1, 0, 0, 0, 0), - D_MODULE(HCLK_CM3, "hclk_cm3", CLK_REF_SYNC_D4, 0xc20, 0xc21, 0xc22, 0, 0, 0, 0), - D_MODULE(HCLK_CRYPTO_EIP150, "hclk_crypto_eip150", CLK_REF_SYNC_D4, 0x123, 0x124, 0x125, 0, 0x142, 0, 0), - D_MODULE(HCLK_CRYPTO_EIP93, "hclk_crypto_eip93", CLK_REF_SYNC_D4, 0x120, 0x121, 0, 0x122, 0, 0x140, 0x141), - D_MODULE(HCLK_DDRC, "hclk_ddrc", CLK_REF_SYNC_D4, 0x320, 0x322, 0, 0x321, 0, 0x3a0, 0x3a1), - D_MODULE(HCLK_DMA0, "hclk_dma0", CLK_REF_SYNC_D4, 0x260, 0x261, 0x262, 0x263, 0x2c0, 0x2c1, 0x2c2), - D_MODULE(HCLK_DMA1, "hclk_dma1", CLK_REF_SYNC_D4, 0x264, 0x265, 0x266, 0x267, 0x2c3, 0x2c4, 0x2c5), - D_MODULE(HCLK_GMAC0, "hclk_gmac0", CLK_REF_SYNC_D4, 0x360, 0x361, 0x362, 0x363, 0x3c0, 0x3c1, 0x3c2), - D_MODULE(HCLK_GMAC1, "hclk_gmac1", CLK_REF_SYNC_D4, 0x380, 0x381, 0x382, 0x383, 0x3e0, 0x3e1, 0x3e2), - D_MODULE(HCLK_GPIO0, "hclk_gpio0", CLK_REF_SYNC_D4, 0x212, 0x213, 0x214, 0, 0, 0, 0), - D_MODULE(HCLK_GPIO1, "hclk_gpio1", CLK_REF_SYNC_D4, 0x215, 0x216, 0x217, 0, 0, 0, 0), - D_MODULE(HCLK_GPIO2, "hclk_gpio2", CLK_REF_SYNC_D4, 0x229, 0x22a, 0x22b, 0, 0, 0, 0), - D_MODULE(HCLK_HSR, "hclk_hsr", CLK_HSR100_D2, 0x480, 0x482, 0, 0x481, 0, 0x4c0, 0x4c1), - D_MODULE(HCLK_I2C0, "hclk_i2c0", CLK_REF_SYNC_D8, 0x1a9, 0x1aa, 0x1ab, 0, 0, 0, 0), - D_MODULE(HCLK_I2C1, "hclk_i2c1", CLK_REF_SYNC_D8, 0x1ac, 0x1ad, 0x1ae, 0, 0, 0, 0), - D_MODULE(HCLK_LCD, "hclk_lcd", CLK_REF_SYNC_D4, 0x7a0, 0x7a1, 0x7a2, 0, 0xb20, 0, 0), - D_MODULE(HCLK_MSEBI_M, "hclk_msebi_m", CLK_REF_SYNC_D4, 0x164, 0x165, 0x166, 0, 0x183, 0, 0), - D_MODULE(HCLK_MSEBI_S, "hclk_msebi_s", CLK_REF_SYNC_D4, 0x160, 0x161, 0x162, 0x163, 0x180, 0x181, 0x182), - D_MODULE(HCLK_NAND, "hclk_nand", CLK_REF_SYNC_D4, 0x280, 0x281, 0x282, 0x283, 0x2e0, 0x2e1, 0x2e2), - D_MODULE(HCLK_PG_I, "hclk_pg_i", CLK_REF_SYNC_D4, 0x7ac, 0x7ad, 0, 0x7ae, 0, 0xb24, 0xb25), - D_MODULE(HCLK_PG19, "hclk_pg19", CLK_REF_SYNC_D4, 0x22c, 0x22d, 0x22e, 0, 0, 0, 0), - D_MODULE(HCLK_PG20, "hclk_pg20", CLK_REF_SYNC_D4, 0x22f, 0x230, 0x231, 0, 0, 0, 0), - D_MODULE(HCLK_PG3, "hclk_pg3", CLK_REF_SYNC_D4, 0x7a6, 0x7a7, 0x7a8, 0, 0xb22, 0, 0), - D_MODULE(HCLK_PG4, "hclk_pg4", CLK_REF_SYNC_D4, 0x7a9, 0x7aa, 0x7ab, 0, 0xb23, 0, 0), - D_MODULE(HCLK_QSPI0, "hclk_qspi0", CLK_REF_SYNC_D4, 0x2a0, 0x2a1, 0x2a2, 0x2a3, 0x300, 0x301, 0x302), - D_MODULE(HCLK_QSPI1, "hclk_qspi1", CLK_REF_SYNC_D4, 0x480, 0x481, 0x482, 0x483, 0x4c0, 0x4c1, 0x4c2), - D_MODULE(HCLK_ROM, "hclk_rom", CLK_REF_SYNC_D4, 0xaa0, 0xaa1, 0xaa2, 0, 0xb80, 0, 0), - D_MODULE(HCLK_RTC, "hclk_rtc", CLK_REF_SYNC_D8, 0xa00, 0xa03, 0, 0xa02, 0, 0, 0), - D_MODULE(HCLK_SDIO0, "hclk_sdio0", CLK_REF_SYNC_D4, 0x60, 0x61, 0x62, 0x63, 0x80, 0x81, 0x82), - D_MODULE(HCLK_SDIO1, "hclk_sdio1", CLK_REF_SYNC_D4, 0x640, 0x641, 0x642, 0x643, 0x660, 0x661, 0x662), - D_MODULE(HCLK_SEMAP, "hclk_semap", CLK_REF_SYNC_D4, 0x7a3, 0x7a4, 0x7a5, 0, 0xb21, 0, 0), - D_MODULE(HCLK_SPI0, "hclk_spi0", CLK_REF_SYNC_D4, 0x200, 0x201, 0x202, 0, 0, 0, 0), - D_MODULE(HCLK_SPI1, "hclk_spi1", CLK_REF_SYNC_D4, 0x203, 0x204, 0x205, 0, 0, 0, 0), - D_MODULE(HCLK_SPI2, "hclk_spi2", CLK_REF_SYNC_D4, 0x206, 0x207, 0x208, 0, 0, 0, 0), - D_MODULE(HCLK_SPI3, "hclk_spi3", CLK_REF_SYNC_D4, 0x209, 0x20a, 0x20b, 0, 0, 0, 0), - D_MODULE(HCLK_SPI4, "hclk_spi4", CLK_REF_SYNC_D4, 0x20c, 0x20d, 0x20e, 0, 0, 0, 0), - D_MODULE(HCLK_SPI5, "hclk_spi5", CLK_REF_SYNC_D4, 0x20f, 0x210, 0x211, 0, 0, 0, 0), - D_MODULE(HCLK_SWITCH, "hclk_switch", CLK_REF_SYNC_D4, 0x980, 0, 0x981, 0, 0, 0, 0), - D_MODULE(HCLK_SWITCH_RG, "hclk_switch_rg", CLK_REF_SYNC_D4, 0xc40, 0xc41, 0xc42, 0, 0, 0, 0), - D_MODULE(HCLK_UART0, "hclk_uart0", CLK_REF_SYNC_D8, 0x1a0, 0x1a1, 0x1a2, 0, 0, 0, 0), - D_MODULE(HCLK_UART1, "hclk_uart1", CLK_REF_SYNC_D8, 0x1a3, 0x1a4, 0x1a5, 0, 0, 0, 0), - D_MODULE(HCLK_UART2, "hclk_uart2", CLK_REF_SYNC_D8, 0x1a6, 0x1a7, 0x1a8, 0, 0, 0, 0), - D_MODULE(HCLK_UART3, "hclk_uart3", CLK_REF_SYNC_D4, 0x218, 0x219, 0x21a, 0, 0, 0, 0), - D_MODULE(HCLK_UART4, "hclk_uart4", CLK_REF_SYNC_D4, 0x21b, 0x21c, 0x21d, 0, 0, 0, 0), - D_MODULE(HCLK_UART5, "hclk_uart5", CLK_REF_SYNC_D4, 0x220, 0x221, 0x222, 0, 0, 0, 0), - D_MODULE(HCLK_UART6, "hclk_uart6", CLK_REF_SYNC_D4, 0x223, 0x224, 0x225, 0, 0, 0, 0), - D_MODULE(HCLK_UART7, "hclk_uart7", CLK_REF_SYNC_D4, 0x226, 0x227, 0x228, 0, 0, 0, 0), + D_GATE(CLK_CM3, "clk_cm3", CLK_REF_SYNC_D4, RB(0x174, 0), + RB(0x174, 1), RB(0x00, 0), RB(0x174, 2), + RB(0x00, 0), RB(0x178, 0), RB(0x178, 1)), + D_GATE(CLK_DDRC, "clk_ddrc", CLK_DDRPHY_PLLCLK_D4, RB(0x64, 3), + RB(0x64, 4), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_ECAT25, "clk_ecat25", CLK_ECAT100_D4, RB(0x80, 3), + RB(0x80, 4), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_HSR50, "clk_hsr50", CLK_HSR100_D2, RB(0x90, 4), + RB(0x90, 5), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_HW_RTOS, "clk_hw_rtos", CLK_REF_SYNC_D4, RB(0x18c, 0), + RB(0x18c, 1), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_GATE(CLK_SERCOS50, "clk_sercos50", CLK_SERCOS100_D2, RB(0x84, 4), + RB(0x84, 3), RB(0x00, 0), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_ADC, "hclk_adc", CLK_REF_SYNC_D8, RB(0x34, 15), + RB(0x34, 16), RB(0x34, 17), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_CM3, "hclk_cm3", CLK_REF_SYNC_D4, RB(0x184, 0), + RB(0x184, 1), RB(0x184, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_CRYPTO_EIP150, "hclk_crypto_eip150", CLK_REF_SYNC_D4, RB(0x24, 3), + RB(0x24, 4), RB(0x24, 5), RB(0x00, 0), + RB(0x28, 2), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_CRYPTO_EIP93, "hclk_crypto_eip93", CLK_REF_SYNC_D4, RB(0x24, 0), + RB(0x24, 1), RB(0x00, 0), RB(0x24, 2), + RB(0x00, 0), RB(0x28, 0), RB(0x28, 1)), + D_MODULE(HCLK_DDRC, "hclk_ddrc", CLK_REF_SYNC_D4, RB(0x64, 0), + RB(0x64, 2), RB(0x00, 0), RB(0x64, 1), + RB(0x00, 0), RB(0x74, 0), RB(0x74, 1)), + D_MODULE(HCLK_DMA0, "hclk_dma0", CLK_REF_SYNC_D4, RB(0x4c, 0), + RB(0x4c, 1), RB(0x4c, 2), RB(0x4c, 3), + RB(0x58, 0), RB(0x58, 1), RB(0x58, 2)), + D_MODULE(HCLK_DMA1, "hclk_dma1", CLK_REF_SYNC_D4, RB(0x4c, 4), + RB(0x4c, 5), RB(0x4c, 6), RB(0x4c, 7), + RB(0x58, 3), RB(0x58, 4), RB(0x58, 5)), + D_MODULE(HCLK_GMAC0, "hclk_gmac0", CLK_REF_SYNC_D4, RB(0x6c, 0), + RB(0x6c, 1), RB(0x6c, 2), RB(0x6c, 3), + RB(0x78, 0), RB(0x78, 1), RB(0x78, 2)), + D_MODULE(HCLK_GMAC1, "hclk_gmac1", CLK_REF_SYNC_D4, RB(0x70, 0), + RB(0x70, 1), RB(0x70, 2), RB(0x70, 3), + RB(0x7c, 0), RB(0x7c, 1), RB(0x7c, 2)), + D_MODULE(HCLK_GPIO0, "hclk_gpio0", CLK_REF_SYNC_D4, RB(0x40, 18), + RB(0x40, 19), RB(0x40, 20), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_GPIO1, "hclk_gpio1", CLK_REF_SYNC_D4, RB(0x40, 21), + RB(0x40, 22), RB(0x40, 23), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_GPIO2, "hclk_gpio2", CLK_REF_SYNC_D4, RB(0x44, 9), + RB(0x44, 10), RB(0x44, 11), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_HSR, "hclk_hsr", CLK_HSR100_D2, RB(0x90, 0), + RB(0x90, 2), RB(0x00, 0), RB(0x90, 1), + RB(0x00, 0), RB(0x98, 0), RB(0x98, 1)), + D_MODULE(HCLK_I2C0, "hclk_i2c0", CLK_REF_SYNC_D8, RB(0x34, 9), + RB(0x34, 10), RB(0x34, 11), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_I2C1, "hclk_i2c1", CLK_REF_SYNC_D8, RB(0x34, 12), + RB(0x34, 13), RB(0x34, 14), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_LCD, "hclk_lcd", CLK_REF_SYNC_D4, RB(0xf4, 0), + RB(0xf4, 1), RB(0xf4, 2), RB(0x00, 0), + RB(0x164, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_MSEBI_M, "hclk_msebi_m", CLK_REF_SYNC_D4, RB(0x2c, 4), + RB(0x2c, 5), RB(0x2c, 6), RB(0x00, 0), + RB(0x30, 3), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_MSEBI_S, "hclk_msebi_s", CLK_REF_SYNC_D4, RB(0x2c, 0), + RB(0x2c, 1), RB(0x2c, 2), RB(0x2c, 3), + RB(0x30, 0), RB(0x30, 1), RB(0x30, 2)), + D_MODULE(HCLK_NAND, "hclk_nand", CLK_REF_SYNC_D4, RB(0x50, 0), + RB(0x50, 1), RB(0x50, 2), RB(0x50, 3), + RB(0x5c, 0), RB(0x5c, 1), RB(0x5c, 2)), + D_MODULE(HCLK_PG_I, "hclk_pg_i", CLK_REF_SYNC_D4, RB(0xf4, 12), + RB(0xf4, 13), RB(0x00, 0), RB(0xf4, 14), + RB(0x00, 0), RB(0x164, 4), RB(0x164, 5)), + D_MODULE(HCLK_PG19, "hclk_pg19", CLK_REF_SYNC_D4, RB(0x44, 12), + RB(0x44, 13), RB(0x44, 14), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_PG20, "hclk_pg20", CLK_REF_SYNC_D4, RB(0x44, 15), + RB(0x44, 16), RB(0x44, 17), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_PG3, "hclk_pg3", CLK_REF_SYNC_D4, RB(0xf4, 6), + RB(0xf4, 7), RB(0xf4, 8), RB(0x00, 0), + RB(0x164, 2), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_PG4, "hclk_pg4", CLK_REF_SYNC_D4, RB(0xf4, 9), + RB(0xf4, 10), RB(0xf4, 11), RB(0x00, 0), + RB(0x164, 3), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_QSPI0, "hclk_qspi0", CLK_REF_SYNC_D4, RB(0x54, 0), + RB(0x54, 1), RB(0x54, 2), RB(0x54, 3), + RB(0x60, 0), RB(0x60, 1), RB(0x60, 2)), + D_MODULE(HCLK_QSPI1, "hclk_qspi1", CLK_REF_SYNC_D4, RB(0x90, 0), + RB(0x90, 1), RB(0x90, 2), RB(0x90, 3), + RB(0x98, 0), RB(0x98, 1), RB(0x98, 2)), + D_MODULE(HCLK_ROM, "hclk_rom", CLK_REF_SYNC_D4, RB(0x154, 0), + RB(0x154, 1), RB(0x154, 2), RB(0x00, 0), + RB(0x170, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_RTC, "hclk_rtc", CLK_REF_SYNC_D8, RB(0x140, 0), + RB(0x140, 3), RB(0x00, 0), RB(0x140, 2), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SDIO0, "hclk_sdio0", CLK_REF_SYNC_D4, RB(0x0c, 0), + RB(0x0c, 1), RB(0x0c, 2), RB(0x0c, 3), + RB(0x10, 0), RB(0x10, 1), RB(0x10, 2)), + D_MODULE(HCLK_SDIO1, "hclk_sdio1", CLK_REF_SYNC_D4, RB(0xc8, 0), + RB(0xc8, 1), RB(0xc8, 2), RB(0xc8, 3), + RB(0xcc, 0), RB(0xcc, 1), RB(0xcc, 2)), + D_MODULE(HCLK_SEMAP, "hclk_semap", CLK_REF_SYNC_D4, RB(0xf4, 3), + RB(0xf4, 4), RB(0xf4, 5), RB(0x00, 0), + RB(0x164, 1), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI0, "hclk_spi0", CLK_REF_SYNC_D4, RB(0x40, 0), + RB(0x40, 1), RB(0x40, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI1, "hclk_spi1", CLK_REF_SYNC_D4, RB(0x40, 3), + RB(0x40, 4), RB(0x40, 5), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI2, "hclk_spi2", CLK_REF_SYNC_D4, RB(0x40, 6), + RB(0x40, 7), RB(0x40, 8), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI3, "hclk_spi3", CLK_REF_SYNC_D4, RB(0x40, 9), + RB(0x40, 10), RB(0x40, 11), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI4, "hclk_spi4", CLK_REF_SYNC_D4, RB(0x40, 12), + RB(0x40, 13), RB(0x40, 14), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SPI5, "hclk_spi5", CLK_REF_SYNC_D4, RB(0x40, 15), + RB(0x40, 16), RB(0x40, 17), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SWITCH, "hclk_switch", CLK_REF_SYNC_D4, RB(0x130, 0), + RB(0x00, 0), RB(0x130, 1), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_SWITCH_RG, "hclk_switch_rg", CLK_REF_SYNC_D4, RB(0x188, 0), + RB(0x188, 1), RB(0x188, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART0, "hclk_uart0", CLK_REF_SYNC_D8, RB(0x34, 0), + RB(0x34, 1), RB(0x34, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART1, "hclk_uart1", CLK_REF_SYNC_D8, RB(0x34, 3), + RB(0x34, 4), RB(0x34, 5), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART2, "hclk_uart2", CLK_REF_SYNC_D8, RB(0x34, 6), + RB(0x34, 7), RB(0x34, 8), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART3, "hclk_uart3", CLK_REF_SYNC_D4, RB(0x40, 24), + RB(0x40, 25), RB(0x40, 26), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART4, "hclk_uart4", CLK_REF_SYNC_D4, RB(0x40, 27), + RB(0x40, 28), RB(0x40, 29), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART5, "hclk_uart5", CLK_REF_SYNC_D4, RB(0x44, 0), + RB(0x44, 1), RB(0x44, 2), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART6, "hclk_uart6", CLK_REF_SYNC_D4, RB(0x44, 3), + RB(0x44, 4), RB(0x44, 5), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), + D_MODULE(HCLK_UART7, "hclk_uart7", CLK_REF_SYNC_D4, RB(0x44, 6), + RB(0x44, 7), RB(0x44, 8), RB(0x00, 0), + RB(0x00, 0), RB(0x00, 0), RB(0x00, 0)), /* * These are not hardware clocks, but are needed to handle the special * case where we have a 'selector bit' that doesn't just change the @@ -383,7 +633,7 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = { .type = K_BITSEL, .source = 1 + R9A06G032_DIV_UART, /* R9A06G032_SYSCTRL_REG_PWRCTRL_PG0_0 */ - .dual.sel = ((0x34 / 4) << 5) | 30, + .dual.sel = RB(0x34, 30), .dual.group = 0, }, { @@ -392,17 +642,25 @@ static const struct r9a06g032_clkdesc r9a06g032_clocks[] = { .type = K_BITSEL, .source = 1 + R9A06G032_DIV_P2_PG, /* R9A06G032_SYSCTRL_REG_PWRCTRL_PG1_PR2 */ - .dual.sel = ((0xec / 4) << 5) | 24, + .dual.sel = RB(0xec, 24), .dual.group = 1, }, - D_UGATE(CLK_UART0, "clk_uart0", UART_GROUP_012, 0, 0x1b2, 0x1b3, 0x1b4, 0x1b5), - D_UGATE(CLK_UART1, "clk_uart1", UART_GROUP_012, 0, 0x1b6, 0x1b7, 0x1b8, 0x1b9), - D_UGATE(CLK_UART2, "clk_uart2", UART_GROUP_012, 0, 0x1ba, 0x1bb, 0x1bc, 0x1bd), - D_UGATE(CLK_UART3, "clk_uart3", UART_GROUP_34567, 1, 0x760, 0x761, 0x762, 0x763), - D_UGATE(CLK_UART4, "clk_uart4", UART_GROUP_34567, 1, 0x764, 0x765, 0x766, 0x767), - D_UGATE(CLK_UART5, "clk_uart5", UART_GROUP_34567, 1, 0x768, 0x769, 0x76a, 0x76b), - D_UGATE(CLK_UART6, "clk_uart6", UART_GROUP_34567, 1, 0x76c, 0x76d, 0x76e, 0x76f), - D_UGATE(CLK_UART7, "clk_uart7", UART_GROUP_34567, 1, 0x770, 0x771, 0x772, 0x773), + D_UGATE(CLK_UART0, "clk_uart0", UART_GROUP_012, 0, + RB(0x34, 18), RB(0x34, 19), RB(0x34, 20), RB(0x34, 21)), + D_UGATE(CLK_UART1, "clk_uart1", UART_GROUP_012, 0, + RB(0x34, 22), RB(0x34, 23), RB(0x34, 24), RB(0x34, 25)), + D_UGATE(CLK_UART2, "clk_uart2", UART_GROUP_012, 0, + RB(0x34, 26), RB(0x34, 27), RB(0x34, 28), RB(0x34, 29)), + D_UGATE(CLK_UART3, "clk_uart3", UART_GROUP_34567, 1, + RB(0xec, 0), RB(0xec, 1), RB(0xec, 2), RB(0xec, 3)), + D_UGATE(CLK_UART4, "clk_uart4", UART_GROUP_34567, 1, + RB(0xec, 4), RB(0xec, 5), RB(0xec, 6), RB(0xec, 7)), + D_UGATE(CLK_UART5, "clk_uart5", UART_GROUP_34567, 1, + RB(0xec, 8), RB(0xec, 9), RB(0xec, 10), RB(0xec, 11)), + D_UGATE(CLK_UART6, "clk_uart6", UART_GROUP_34567, 1, + RB(0xec, 12), RB(0xec, 13), RB(0xec, 14), RB(0xec, 15)), + D_UGATE(CLK_UART7, "clk_uart7", UART_GROUP_34567, 1, + RB(0xec, 16), RB(0xec, 17), RB(0xec, 18), RB(0xec, 19)), }; struct r9a06g032_priv { @@ -435,26 +693,26 @@ int r9a06g032_sysctrl_set_dmamux(u32 mask, u32 val) } EXPORT_SYMBOL_GPL(r9a06g032_sysctrl_set_dmamux); -/* register/bit pairs are encoded as an uint16_t */ -static void -clk_rdesc_set(struct r9a06g032_priv *clocks, - u16 one, unsigned int on) +static void clk_rdesc_set(struct r9a06g032_priv *clocks, + struct regbit rb, unsigned int on) { - u32 __iomem *reg = clocks->reg + (4 * (one >> 5)); - u32 val = readl(reg); + u32 __iomem *reg = clocks->reg + (rb.reg * 4); + u32 val; - val = (val & ~(1U << (one & 0x1f))) | ((!!on) << (one & 0x1f)); + if (!rb.reg && !rb.bit) + return; + + val = readl(reg); + val = (val & ~BIT(rb.bit)) | ((!!on) << rb.bit); writel(val, reg); } -static int -clk_rdesc_get(struct r9a06g032_priv *clocks, - uint16_t one) +static int clk_rdesc_get(struct r9a06g032_priv *clocks, struct regbit rb) { - u32 __iomem *reg = clocks->reg + (4 * (one >> 5)); + u32 __iomem *reg = clocks->reg + (rb.reg * 4); u32 val = readl(reg); - return !!(val & (1U << (one & 0x1f))); + return !!(val & BIT(rb.bit)); } /* @@ -556,13 +814,12 @@ r9a06g032_clk_gate_set(struct r9a06g032_priv *clocks, { unsigned long flags; - WARN_ON(!g->gate); + WARN_ON(!g->gate.reg && !g->gate.bit); spin_lock_irqsave(&clocks->lock, flags); clk_rdesc_set(clocks, g->gate, on); /* De-assert reset */ - if (g->reset) - clk_rdesc_set(clocks, g->reset, 1); + clk_rdesc_set(clocks, g->reset, 1); spin_unlock_irqrestore(&clocks->lock, flags); /* Hardware manual recommends 5us delay after enabling clock & reset */ @@ -572,15 +829,12 @@ r9a06g032_clk_gate_set(struct r9a06g032_priv *clocks, * associated SLVRDY bit in the System Controller that needs to be set * so that the FlexWAY bus fabric passes on the read/write requests. */ - if (g->ready || g->midle) { - spin_lock_irqsave(&clocks->lock, flags); - if (g->ready) - clk_rdesc_set(clocks, g->ready, on); - /* Clear 'Master Idle Request' bit */ - if (g->midle) - clk_rdesc_set(clocks, g->midle, !on); - spin_unlock_irqrestore(&clocks->lock, flags); - } + spin_lock_irqsave(&clocks->lock, flags); + clk_rdesc_set(clocks, g->ready, on); + /* Clear 'Master Idle Request' bit */ + clk_rdesc_set(clocks, g->midle, !on); + spin_unlock_irqrestore(&clocks->lock, flags); + /* Note: We don't wait for FlexWAY Socket Connection signal */ } @@ -604,7 +858,7 @@ static int r9a06g032_clk_gate_is_enabled(struct clk_hw *hw) struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw); /* if clock is in reset, the gate might be on, and still not 'be' on */ - if (g->gate.reset && !clk_rdesc_get(g->clocks, g->gate.reset)) + if (g->gate.reset.reg && !clk_rdesc_get(g->clocks, g->gate.reset)) return 0; return clk_rdesc_get(g->clocks, g->gate.gate); @@ -843,7 +1097,7 @@ struct r9a06g032_clk_bitsel { struct clk_hw hw; struct r9a06g032_priv *clocks; u16 index; - u16 selector; /* selector register + bit */ + struct regbit selector; /* selector register + bit */ }; #define to_clk_bitselect(_hw) \ @@ -912,7 +1166,7 @@ struct r9a06g032_clk_dualgate { struct clk_hw hw; struct r9a06g032_priv *clocks; u16 index; - u16 selector; /* selector register + bit */ + struct regbit selector; /* selector register + bit */ struct r9a06g032_gate gate[2]; }; @@ -965,7 +1219,7 @@ static struct clk * r9a06g032_register_dualgate(struct r9a06g032_priv *clocks, const char *parent_name, const struct r9a06g032_clkdesc *desc, - uint16_t sel) + struct regbit sel) { struct r9a06g032_clk_dualgate *g; struct clk *clk; @@ -1043,7 +1297,7 @@ static int __init r9a06g032_clocks_probe(struct platform_device *pdev) struct clk **clks; struct clk *mclk; unsigned int i; - u16 uart_group_sel[2]; + struct regbit uart_group_sel[2]; int error; clocks = devm_kzalloc(dev, sizeof(*clocks), GFP_KERNEL); -- GitLab From 0a7a5226e7b177c68800985a19a80c1df9bceff6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 21 Nov 2022 14:18:37 +0100 Subject: [PATCH 0250/5631] pinctrl: renesas: r8a779g0: Fix Group 4/5 pin functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to R-Car V4H Series User’s Manual: Hardware Rev. 0.54, pin groups 4 and 5 do not use Module Select Registers to configure pin functions, but use Peripheral Function Select Registers instead. Hence: - Remove the non-existent Module Select Registers (MODSEL[45]), - Add the missing Peripheral Function Select Registers (IPxSR[45]), - Correct the GPIO / Peripheral Function Select Register definitions (GPSR]45_*), - Correct the affected PINMUX definitions. Fixes: 36611d28f5130d8b ("pinctrl: renesas: r8a779g0: Add missing MODSELx for AVBx") Fixes: 36fb7b8af55b83e0 ("pinctrl: renesas: r8a779g0: Add missing MODSELx for TSN0") Fixes: ad9bb2fec66262b0 ("pinctrl: renesas: Initial R8A779G0 (R-Car V4H) PFC support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/3d3833d1738f5e8fcc4c1002aa93832464d129a0.1669036423.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 467 +++++++++++++++---------- 1 file changed, 279 insertions(+), 188 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 9671d668a3c3..a2fa1c5bc3f6 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -156,54 +156,54 @@ #define GPSR3_0 F_(MMC_SD_D1, IP0SR3_3_0) /* GPSR4 */ -#define GPSR4_24 FM(AVS1) -#define GPSR4_23 FM(AVS0) -#define GPSR4_22 FM(PCIE1_CLKREQ_N) -#define GPSR4_21 FM(PCIE0_CLKREQ_N) -#define GPSR4_20 FM(TSN0_TXCREFCLK) -#define GPSR4_19 FM(TSN0_TD2) -#define GPSR4_18 FM(TSN0_TD3) -#define GPSR4_17 FM(TSN0_RD2) -#define GPSR4_16 FM(TSN0_RD3) -#define GPSR4_15 FM(TSN0_TD0) -#define GPSR4_14 FM(TSN0_TD1) -#define GPSR4_13 FM(TSN0_RD1) -#define GPSR4_12 FM(TSN0_TXC) -#define GPSR4_11 FM(TSN0_RXC) -#define GPSR4_10 FM(TSN0_RD0) -#define GPSR4_9 FM(TSN0_TX_CTL) -#define GPSR4_8 FM(TSN0_AVTP_PPS0) -#define GPSR4_7 FM(TSN0_RX_CTL) -#define GPSR4_6 FM(TSN0_AVTP_CAPTURE) -#define GPSR4_5 FM(TSN0_AVTP_MATCH) -#define GPSR4_4 FM(TSN0_LINK) -#define GPSR4_3 FM(TSN0_PHY_INT) -#define GPSR4_2 FM(TSN0_AVTP_PPS1) -#define GPSR4_1 FM(TSN0_MDC) -#define GPSR4_0 FM(TSN0_MDIO) +#define GPSR4_24 F_(AVS1, IP3SR4_3_0) +#define GPSR4_23 F_(AVS0, IP2SR4_31_28) +#define GPSR4_22 F_(PCIE1_CLKREQ_N, IP2SR4_27_24) +#define GPSR4_21 F_(PCIE0_CLKREQ_N, IP2SR4_23_20) +#define GPSR4_20 F_(TSN0_TXCREFCLK, IP2SR4_19_16) +#define GPSR4_19 F_(TSN0_TD2, IP2SR4_15_12) +#define GPSR4_18 F_(TSN0_TD3, IP2SR4_11_8) +#define GPSR4_17 F_(TSN0_RD2, IP2SR4_7_4) +#define GPSR4_16 F_(TSN0_RD3, IP2SR4_3_0) +#define GPSR4_15 F_(TSN0_TD0, IP1SR4_31_28) +#define GPSR4_14 F_(TSN0_TD1, IP1SR4_27_24) +#define GPSR4_13 F_(TSN0_RD1, IP1SR4_23_20) +#define GPSR4_12 F_(TSN0_TXC, IP1SR4_19_16) +#define GPSR4_11 F_(TSN0_RXC, IP1SR4_15_12) +#define GPSR4_10 F_(TSN0_RD0, IP1SR4_11_8) +#define GPSR4_9 F_(TSN0_TX_CTL, IP1SR4_7_4) +#define GPSR4_8 F_(TSN0_AVTP_PPS0, IP1SR4_3_0) +#define GPSR4_7 F_(TSN0_RX_CTL, IP0SR4_31_28) +#define GPSR4_6 F_(TSN0_AVTP_CAPTURE, IP0SR4_27_24) +#define GPSR4_5 F_(TSN0_AVTP_MATCH, IP0SR4_23_20) +#define GPSR4_4 F_(TSN0_LINK, IP0SR4_19_16) +#define GPSR4_3 F_(TSN0_PHY_INT, IP0SR4_15_12) +#define GPSR4_2 F_(TSN0_AVTP_PPS1, IP0SR4_11_8) +#define GPSR4_1 F_(TSN0_MDC, IP0SR4_7_4) +#define GPSR4_0 F_(TSN0_MDIO, IP0SR4_3_0) /* GPSR 5 */ -#define GPSR5_20 FM(AVB2_RX_CTL) -#define GPSR5_19 FM(AVB2_TX_CTL) -#define GPSR5_18 FM(AVB2_RXC) -#define GPSR5_17 FM(AVB2_RD0) -#define GPSR5_16 FM(AVB2_TXC) -#define GPSR5_15 FM(AVB2_TD0) -#define GPSR5_14 FM(AVB2_RD1) -#define GPSR5_13 FM(AVB2_RD2) -#define GPSR5_12 FM(AVB2_TD1) -#define GPSR5_11 FM(AVB2_TD2) -#define GPSR5_10 FM(AVB2_MDIO) -#define GPSR5_9 FM(AVB2_RD3) -#define GPSR5_8 FM(AVB2_TD3) -#define GPSR5_7 FM(AVB2_TXCREFCLK) -#define GPSR5_6 FM(AVB2_MDC) -#define GPSR5_5 FM(AVB2_MAGIC) -#define GPSR5_4 FM(AVB2_PHY_INT) -#define GPSR5_3 FM(AVB2_LINK) -#define GPSR5_2 FM(AVB2_AVTP_MATCH) -#define GPSR5_1 FM(AVB2_AVTP_CAPTURE) -#define GPSR5_0 FM(AVB2_AVTP_PPS) +#define GPSR5_20 F_(AVB2_RX_CTL, IP2SR5_19_16) +#define GPSR5_19 F_(AVB2_TX_CTL, IP2SR5_15_12) +#define GPSR5_18 F_(AVB2_RXC, IP2SR5_11_8) +#define GPSR5_17 F_(AVB2_RD0, IP2SR5_7_4) +#define GPSR5_16 F_(AVB2_TXC, IP2SR5_3_0) +#define GPSR5_15 F_(AVB2_TD0, IP1SR5_31_28) +#define GPSR5_14 F_(AVB2_RD1, IP1SR5_27_24) +#define GPSR5_13 F_(AVB2_RD2, IP1SR5_23_20) +#define GPSR5_12 F_(AVB2_TD1, IP1SR5_19_16) +#define GPSR5_11 F_(AVB2_TD2, IP1SR5_15_12) +#define GPSR5_10 F_(AVB2_MDIO, IP1SR5_11_8) +#define GPSR5_9 F_(AVB2_RD3, IP1SR5_7_4) +#define GPSR5_8 F_(AVB2_TD3, IP1SR5_3_0) +#define GPSR5_7 F_(AVB2_TXCREFCLK, IP0SR5_31_28) +#define GPSR5_6 F_(AVB2_MDC, IP0SR5_27_24) +#define GPSR5_5 F_(AVB2_MAGIC, IP0SR5_23_20) +#define GPSR5_4 F_(AVB2_PHY_INT, IP0SR5_19_16) +#define GPSR5_3 F_(AVB2_LINK, IP0SR5_15_12) +#define GPSR5_2 F_(AVB2_AVTP_MATCH, IP0SR5_11_8) +#define GPSR5_1 F_(AVB2_AVTP_CAPTURE, IP0SR5_7_4) +#define GPSR5_0 F_(AVB2_AVTP_PPS, IP0SR5_3_0) /* GPSR 6 */ #define GPSR6_20 F_(AVB1_TXCREFCLK, IP2SR6_19_16) @@ -397,6 +397,68 @@ #define IP3SR3_19_16 FM(RPC_WP_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) #define IP3SR3_23_20 FM(RPC_INT_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* SR4 */ +/* IP0SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR4_3_0 FM(TSN0_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_7_4 FM(TSN0_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_11_8 FM(TSN0_AVTP_PPS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_15_12 FM(TSN0_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_19_16 FM(TSN0_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_23_20 FM(TSN0_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_27_24 FM(TSN0_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_31_28 FM(TSN0_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR4_3_0 FM(TSN0_AVTP_PPS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_7_4 FM(TSN0_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_11_8 FM(TSN0_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_15_12 FM(TSN0_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_19_16 FM(TSN0_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_23_20 FM(TSN0_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_27_24 FM(TSN0_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_31_28 FM(TSN0_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR4_3_0 FM(TSN0_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_7_4 FM(TSN0_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_11_8 FM(TSN0_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_15_12 FM(TSN0_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_19_16 FM(TSN0_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_23_20 FM(PCIE0_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_27_24 FM(PCIE1_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_31_28 FM(AVS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP3SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP3SR4_3_0 FM(AVS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* SR5 */ +/* IP0SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR5_3_0 FM(AVB2_AVTP_PPS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_7_4 FM(AVB2_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_11_8 FM(AVB2_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_15_12 FM(AVB2_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_19_16 FM(AVB2_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_23_20 FM(AVB2_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_27_24 FM(AVB2_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_31_28 FM(AVB2_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR5_3_0 FM(AVB2_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_7_4 FM(AVB2_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_11_8 FM(AVB2_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_15_12 FM(AVB2_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_19_16 FM(AVB2_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_23_20 FM(AVB2_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_27_24 FM(AVB2_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_31_28 FM(AVB2_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR5_3_0 FM(AVB2_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_7_4 FM(AVB2_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_11_8 FM(AVB2_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_15_12 FM(AVB2_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_19_16 FM(AVB2_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + /* SR6 */ /* IP0SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ #define IP0SR6_3_0 FM(AVB1_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) @@ -542,6 +604,24 @@ FM(IP0SR3_23_20) IP0SR3_23_20 FM(IP1SR3_23_20) IP1SR3_23_20 FM(IP2SR3_23_20) IP2 FM(IP0SR3_27_24) IP0SR3_27_24 FM(IP1SR3_27_24) IP1SR3_27_24 FM(IP2SR3_27_24) IP2SR3_27_24 \ FM(IP0SR3_31_28) IP0SR3_31_28 FM(IP1SR3_31_28) IP1SR3_31_28 FM(IP2SR3_31_28) IP2SR3_31_28 \ \ +FM(IP0SR4_3_0) IP0SR4_3_0 FM(IP1SR4_3_0) IP1SR4_3_0 FM(IP2SR4_3_0) IP2SR4_3_0 FM(IP3SR4_3_0) IP3SR4_3_0 \ +FM(IP0SR4_7_4) IP0SR4_7_4 FM(IP1SR4_7_4) IP1SR4_7_4 FM(IP2SR4_7_4) IP2SR4_7_4 \ +FM(IP0SR4_11_8) IP0SR4_11_8 FM(IP1SR4_11_8) IP1SR4_11_8 FM(IP2SR4_11_8) IP2SR4_11_8 \ +FM(IP0SR4_15_12) IP0SR4_15_12 FM(IP1SR4_15_12) IP1SR4_15_12 FM(IP2SR4_15_12) IP2SR4_15_12 \ +FM(IP0SR4_19_16) IP0SR4_19_16 FM(IP1SR4_19_16) IP1SR4_19_16 FM(IP2SR4_19_16) IP2SR4_19_16 \ +FM(IP0SR4_23_20) IP0SR4_23_20 FM(IP1SR4_23_20) IP1SR4_23_20 FM(IP2SR4_23_20) IP2SR4_23_20 \ +FM(IP0SR4_27_24) IP0SR4_27_24 FM(IP1SR4_27_24) IP1SR4_27_24 FM(IP2SR4_27_24) IP2SR4_27_24 \ +FM(IP0SR4_31_28) IP0SR4_31_28 FM(IP1SR4_31_28) IP1SR4_31_28 FM(IP2SR4_31_28) IP2SR4_31_28 \ +\ +FM(IP0SR5_3_0) IP0SR5_3_0 FM(IP1SR5_3_0) IP1SR5_3_0 FM(IP2SR5_3_0) IP2SR5_3_0 \ +FM(IP0SR5_7_4) IP0SR5_7_4 FM(IP1SR5_7_4) IP1SR5_7_4 FM(IP2SR5_7_4) IP2SR5_7_4 \ +FM(IP0SR5_11_8) IP0SR5_11_8 FM(IP1SR5_11_8) IP1SR5_11_8 FM(IP2SR5_11_8) IP2SR5_11_8 \ +FM(IP0SR5_15_12) IP0SR5_15_12 FM(IP1SR5_15_12) IP1SR5_15_12 FM(IP2SR5_15_12) IP2SR5_15_12 \ +FM(IP0SR5_19_16) IP0SR5_19_16 FM(IP1SR5_19_16) IP1SR5_19_16 FM(IP2SR5_19_16) IP2SR5_19_16 \ +FM(IP0SR5_23_20) IP0SR5_23_20 FM(IP1SR5_23_20) IP1SR5_23_20 \ +FM(IP0SR5_27_24) IP0SR5_27_24 FM(IP1SR5_27_24) IP1SR5_27_24 \ +FM(IP0SR5_31_28) IP0SR5_31_28 FM(IP1SR5_31_28) IP1SR5_31_28 \ +\ FM(IP0SR6_3_0) IP0SR6_3_0 FM(IP1SR6_3_0) IP1SR6_3_0 FM(IP2SR6_3_0) IP2SR6_3_0 \ FM(IP0SR6_7_4) IP0SR6_7_4 FM(IP1SR6_7_4) IP1SR6_7_4 FM(IP2SR6_7_4) IP2SR6_7_4 \ FM(IP0SR6_11_8) IP0SR6_11_8 FM(IP1SR6_11_8) IP1SR6_11_8 FM(IP2SR6_11_8) IP2SR6_11_8 \ @@ -569,30 +649,6 @@ FM(IP0SR8_23_20) IP0SR8_23_20 FM(IP1SR8_23_20) IP1SR8_23_20 \ FM(IP0SR8_27_24) IP0SR8_27_24 \ FM(IP0SR8_31_28) IP0SR8_31_28 -/* MOD_SEL4 */ /* 0 */ /* 1 */ -#define MOD_SEL4_19 FM(SEL_TSN0_TD2_0) FM(SEL_TSN0_TD2_1) -#define MOD_SEL4_18 FM(SEL_TSN0_TD3_0) FM(SEL_TSN0_TD3_1) -#define MOD_SEL4_15 FM(SEL_TSN0_TD0_0) FM(SEL_TSN0_TD0_1) -#define MOD_SEL4_14 FM(SEL_TSN0_TD1_0) FM(SEL_TSN0_TD1_1) -#define MOD_SEL4_12 FM(SEL_TSN0_TXC_0) FM(SEL_TSN0_TXC_1) -#define MOD_SEL4_9 FM(SEL_TSN0_TX_CTL_0) FM(SEL_TSN0_TX_CTL_1) -#define MOD_SEL4_8 FM(SEL_TSN0_AVTP_PPS0_0) FM(SEL_TSN0_AVTP_PPS0_1) -#define MOD_SEL4_5 FM(SEL_TSN0_AVTP_MATCH_0) FM(SEL_TSN0_AVTP_MATCH_1) -#define MOD_SEL4_2 FM(SEL_TSN0_AVTP_PPS1_0) FM(SEL_TSN0_AVTP_PPS1_1) -#define MOD_SEL4_1 FM(SEL_TSN0_MDC_0) FM(SEL_TSN0_MDC_1) - -/* MOD_SEL5 */ /* 0 */ /* 1 */ -#define MOD_SEL5_19 FM(SEL_AVB2_TX_CTL_0) FM(SEL_AVB2_TX_CTL_1) -#define MOD_SEL5_16 FM(SEL_AVB2_TXC_0) FM(SEL_AVB2_TXC_1) -#define MOD_SEL5_15 FM(SEL_AVB2_TD0_0) FM(SEL_AVB2_TD0_1) -#define MOD_SEL5_12 FM(SEL_AVB2_TD1_0) FM(SEL_AVB2_TD1_1) -#define MOD_SEL5_11 FM(SEL_AVB2_TD2_0) FM(SEL_AVB2_TD2_1) -#define MOD_SEL5_8 FM(SEL_AVB2_TD3_0) FM(SEL_AVB2_TD3_1) -#define MOD_SEL5_6 FM(SEL_AVB2_MDC_0) FM(SEL_AVB2_MDC_1) -#define MOD_SEL5_5 FM(SEL_AVB2_MAGIC_0) FM(SEL_AVB2_MAGIC_1) -#define MOD_SEL5_2 FM(SEL_AVB2_AVTP_MATCH_0) FM(SEL_AVB2_AVTP_MATCH_1) -#define MOD_SEL5_0 FM(SEL_AVB2_AVTP_PPS_0) FM(SEL_AVB2_AVTP_PPS_1) - /* MOD_SEL6 */ /* 0 */ /* 1 */ #define MOD_SEL6_18 FM(SEL_AVB1_TD3_0) FM(SEL_AVB1_TD3_1) #define MOD_SEL6_16 FM(SEL_AVB1_TD2_0) FM(SEL_AVB1_TD2_1) @@ -633,26 +689,23 @@ FM(IP0SR8_31_28) IP0SR8_31_28 #define PINMUX_MOD_SELS \ \ -MOD_SEL4_19 MOD_SEL5_19 \ -MOD_SEL4_18 MOD_SEL6_18 \ - \ - MOD_SEL5_16 MOD_SEL6_16 MOD_SEL7_16 \ -MOD_SEL4_15 MOD_SEL5_15 MOD_SEL7_15 \ -MOD_SEL4_14 \ - MOD_SEL6_13 MOD_SEL7_13 \ -MOD_SEL4_12 MOD_SEL5_12 MOD_SEL6_12 \ - MOD_SEL5_11 MOD_SEL7_11 MOD_SEL8_11 \ - MOD_SEL6_10 MOD_SEL7_10 MOD_SEL8_10 \ -MOD_SEL4_9 MOD_SEL8_9 \ -MOD_SEL4_8 MOD_SEL5_8 MOD_SEL8_8 \ - MOD_SEL6_7 MOD_SEL7_7 MOD_SEL8_7 \ - MOD_SEL5_6 MOD_SEL6_6 MOD_SEL7_6 MOD_SEL8_6 \ -MOD_SEL4_5 MOD_SEL5_5 MOD_SEL6_5 MOD_SEL8_5 \ - MOD_SEL8_4 \ - MOD_SEL7_3 MOD_SEL8_3 \ -MOD_SEL4_2 MOD_SEL5_2 MOD_SEL6_2 MOD_SEL7_2 MOD_SEL8_2 \ -MOD_SEL4_1 MOD_SEL6_1 MOD_SEL8_1 \ - MOD_SEL5_0 MOD_SEL7_0 MOD_SEL8_0 +MOD_SEL6_18 \ +MOD_SEL6_16 MOD_SEL7_16 \ + MOD_SEL7_15 \ +MOD_SEL6_13 MOD_SEL7_13 \ +MOD_SEL6_12 \ + MOD_SEL7_11 MOD_SEL8_11 \ +MOD_SEL6_10 MOD_SEL7_10 MOD_SEL8_10 \ + MOD_SEL8_9 \ + MOD_SEL8_8 \ +MOD_SEL6_7 MOD_SEL7_7 MOD_SEL8_7 \ +MOD_SEL6_6 MOD_SEL7_6 MOD_SEL8_6 \ +MOD_SEL6_5 MOD_SEL8_5 \ + MOD_SEL8_4 \ + MOD_SEL7_3 MOD_SEL8_3 \ +MOD_SEL6_2 MOD_SEL7_2 MOD_SEL8_2 \ +MOD_SEL6_1 MOD_SEL8_1 \ + MOD_SEL7_0 MOD_SEL8_0 enum { PINMUX_RESERVED = 0, @@ -686,59 +739,6 @@ enum { static const u16 pinmux_data[] = { PINMUX_DATA_GP_ALL(), - PINMUX_SINGLE(AVS1), - PINMUX_SINGLE(AVS0), - PINMUX_SINGLE(PCIE1_CLKREQ_N), - PINMUX_SINGLE(PCIE0_CLKREQ_N), - - /* TSN0 without MODSEL4 */ - PINMUX_SINGLE(TSN0_TXCREFCLK), - PINMUX_SINGLE(TSN0_RD2), - PINMUX_SINGLE(TSN0_RD3), - PINMUX_SINGLE(TSN0_RD1), - PINMUX_SINGLE(TSN0_RXC), - PINMUX_SINGLE(TSN0_RD0), - PINMUX_SINGLE(TSN0_RX_CTL), - PINMUX_SINGLE(TSN0_AVTP_CAPTURE), - PINMUX_SINGLE(TSN0_LINK), - PINMUX_SINGLE(TSN0_PHY_INT), - PINMUX_SINGLE(TSN0_MDIO), - /* TSN0 with MODSEL4 */ - PINMUX_IPSR_NOGM(0, TSN0_TD2, SEL_TSN0_TD2_1), - PINMUX_IPSR_NOGM(0, TSN0_TD3, SEL_TSN0_TD3_1), - PINMUX_IPSR_NOGM(0, TSN0_TD0, SEL_TSN0_TD0_1), - PINMUX_IPSR_NOGM(0, TSN0_TD1, SEL_TSN0_TD1_1), - PINMUX_IPSR_NOGM(0, TSN0_TXC, SEL_TSN0_TXC_1), - PINMUX_IPSR_NOGM(0, TSN0_TX_CTL, SEL_TSN0_TX_CTL_1), - PINMUX_IPSR_NOGM(0, TSN0_AVTP_PPS0, SEL_TSN0_AVTP_PPS0_1), - PINMUX_IPSR_NOGM(0, TSN0_AVTP_MATCH, SEL_TSN0_AVTP_MATCH_1), - PINMUX_IPSR_NOGM(0, TSN0_AVTP_PPS1, SEL_TSN0_AVTP_PPS1_1), - PINMUX_IPSR_NOGM(0, TSN0_MDC, SEL_TSN0_MDC_1), - - /* TSN0 without MODSEL5 */ - PINMUX_SINGLE(AVB2_RX_CTL), - PINMUX_SINGLE(AVB2_RXC), - PINMUX_SINGLE(AVB2_RD0), - PINMUX_SINGLE(AVB2_RD1), - PINMUX_SINGLE(AVB2_RD2), - PINMUX_SINGLE(AVB2_MDIO), - PINMUX_SINGLE(AVB2_RD3), - PINMUX_SINGLE(AVB2_TXCREFCLK), - PINMUX_SINGLE(AVB2_PHY_INT), - PINMUX_SINGLE(AVB2_LINK), - PINMUX_SINGLE(AVB2_AVTP_CAPTURE), - /* TSN0 with MODSEL5 */ - PINMUX_IPSR_NOGM(0, AVB2_TX_CTL, SEL_AVB2_TX_CTL_1), - PINMUX_IPSR_NOGM(0, AVB2_TXC, SEL_AVB2_TXC_1), - PINMUX_IPSR_NOGM(0, AVB2_TD0, SEL_AVB2_TD0_1), - PINMUX_IPSR_NOGM(0, AVB2_TD1, SEL_AVB2_TD1_1), - PINMUX_IPSR_NOGM(0, AVB2_TD2, SEL_AVB2_TD2_1), - PINMUX_IPSR_NOGM(0, AVB2_TD3, SEL_AVB2_TD3_1), - PINMUX_IPSR_NOGM(0, AVB2_MDC, SEL_AVB2_MDC_1), - PINMUX_IPSR_NOGM(0, AVB2_MAGIC, SEL_AVB2_MAGIC_1), - PINMUX_IPSR_NOGM(0, AVB2_AVTP_MATCH, SEL_AVB2_AVTP_MATCH_1), - PINMUX_IPSR_NOGM(0, AVB2_AVTP_PPS, SEL_AVB2_AVTP_PPS_1), - /* IP0SR0 */ PINMUX_IPSR_GPSR(IP0SR0_3_0, ERROROUTC_B), PINMUX_IPSR_GPSR(IP0SR0_3_0, TCLK2_A), @@ -1029,6 +1029,66 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP3SR3_19_16, RPC_WP_N), PINMUX_IPSR_GPSR(IP3SR3_23_20, RPC_INT_N), + /* IP0SR4 */ + PINMUX_IPSR_GPSR(IP0SR4_3_0, TSN0_MDIO), + PINMUX_IPSR_GPSR(IP0SR4_7_4, TSN0_MDC), + PINMUX_IPSR_GPSR(IP0SR4_11_8, TSN0_AVTP_PPS1), + PINMUX_IPSR_GPSR(IP0SR4_15_12, TSN0_PHY_INT), + PINMUX_IPSR_GPSR(IP0SR4_19_16, TSN0_LINK), + PINMUX_IPSR_GPSR(IP0SR4_23_20, TSN0_AVTP_MATCH), + PINMUX_IPSR_GPSR(IP0SR4_27_24, TSN0_AVTP_CAPTURE), + PINMUX_IPSR_GPSR(IP0SR4_31_28, TSN0_RX_CTL), + + /* IP1SR4 */ + PINMUX_IPSR_GPSR(IP1SR4_3_0, TSN0_AVTP_PPS0), + PINMUX_IPSR_GPSR(IP1SR4_7_4, TSN0_TX_CTL), + PINMUX_IPSR_GPSR(IP1SR4_11_8, TSN0_RD0), + PINMUX_IPSR_GPSR(IP1SR4_15_12, TSN0_RXC), + PINMUX_IPSR_GPSR(IP1SR4_19_16, TSN0_TXC), + PINMUX_IPSR_GPSR(IP1SR4_23_20, TSN0_RD1), + PINMUX_IPSR_GPSR(IP1SR4_27_24, TSN0_TD1), + PINMUX_IPSR_GPSR(IP1SR4_31_28, TSN0_TD0), + + /* IP2SR4 */ + PINMUX_IPSR_GPSR(IP2SR4_3_0, TSN0_RD3), + PINMUX_IPSR_GPSR(IP2SR4_7_4, TSN0_RD2), + PINMUX_IPSR_GPSR(IP2SR4_11_8, TSN0_TD3), + PINMUX_IPSR_GPSR(IP2SR4_15_12, TSN0_TD2), + PINMUX_IPSR_GPSR(IP2SR4_19_16, TSN0_TXCREFCLK), + PINMUX_IPSR_GPSR(IP2SR4_23_20, PCIE0_CLKREQ_N), + PINMUX_IPSR_GPSR(IP2SR4_27_24, PCIE1_CLKREQ_N), + PINMUX_IPSR_GPSR(IP2SR4_31_28, AVS0), + + /* IP3SR4 */ + PINMUX_IPSR_GPSR(IP3SR4_3_0, AVS1), + + /* IP0SR5 */ + PINMUX_IPSR_GPSR(IP0SR5_3_0, AVB2_AVTP_PPS), + PINMUX_IPSR_GPSR(IP0SR5_7_4, AVB2_AVTP_CAPTURE), + PINMUX_IPSR_GPSR(IP0SR5_11_8, AVB2_AVTP_MATCH), + PINMUX_IPSR_GPSR(IP0SR5_15_12, AVB2_LINK), + PINMUX_IPSR_GPSR(IP0SR5_19_16, AVB2_PHY_INT), + PINMUX_IPSR_GPSR(IP0SR5_23_20, AVB2_MAGIC), + PINMUX_IPSR_GPSR(IP0SR5_27_24, AVB2_MDC), + PINMUX_IPSR_GPSR(IP0SR5_31_28, AVB2_TXCREFCLK), + + /* IP1SR5 */ + PINMUX_IPSR_GPSR(IP1SR5_3_0, AVB2_TD3), + PINMUX_IPSR_GPSR(IP1SR5_7_4, AVB2_RD3), + PINMUX_IPSR_GPSR(IP1SR5_11_8, AVB2_MDIO), + PINMUX_IPSR_GPSR(IP1SR5_15_12, AVB2_TD2), + PINMUX_IPSR_GPSR(IP1SR5_19_16, AVB2_TD1), + PINMUX_IPSR_GPSR(IP1SR5_23_20, AVB2_RD2), + PINMUX_IPSR_GPSR(IP1SR5_27_24, AVB2_RD1), + PINMUX_IPSR_GPSR(IP1SR5_31_28, AVB2_TD0), + + /* IP2SR5 */ + PINMUX_IPSR_GPSR(IP2SR5_3_0, AVB2_TXC), + PINMUX_IPSR_GPSR(IP2SR5_7_4, AVB2_RD0), + PINMUX_IPSR_GPSR(IP2SR5_11_8, AVB2_RXC), + PINMUX_IPSR_GPSR(IP2SR5_15_12, AVB2_TX_CTL), + PINMUX_IPSR_GPSR(IP2SR5_19_16, AVB2_RX_CTL), + /* IP0SR6 */ PINMUX_IPSR_GPSR(IP0SR6_3_0, AVB1_MDIO), @@ -3471,6 +3531,82 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { IP3SR3_7_4 IP3SR3_3_0)) }, + { PINMUX_CFG_REG_VAR("IP0SR4", 0xE6060060, 32, + GROUP(4, 4, 4, 4, 4, 4, 4, 4), + GROUP( + IP0SR4_31_28 + IP0SR4_27_24 + IP0SR4_23_20 + IP0SR4_19_16 + IP0SR4_15_12 + IP0SR4_11_8 + IP0SR4_7_4 + IP0SR4_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP1SR4", 0xE6060064, 32, + GROUP(4, 4, 4, 4, 4, 4, 4, 4), + GROUP( + IP1SR4_31_28 + IP1SR4_27_24 + IP1SR4_23_20 + IP1SR4_19_16 + IP1SR4_15_12 + IP1SR4_11_8 + IP1SR4_7_4 + IP1SR4_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP2SR4", 0xE6060068, 32, + GROUP(4, 4, 4, 4, 4, 4, 4, 4), + GROUP( + IP2SR4_31_28 + IP2SR4_27_24 + IP2SR4_23_20 + IP2SR4_19_16 + IP2SR4_15_12 + IP2SR4_11_8 + IP2SR4_7_4 + IP2SR4_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP3SR4", 0xE606006C, 32, + GROUP(-28, 4), + GROUP( + /* IP3SR4_31_4 RESERVED */ + IP3SR4_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP0SR5", 0xE6060860, 32, + GROUP(4, 4, 4, 4, 4, 4, 4, 4), + GROUP( + IP0SR5_31_28 + IP0SR5_27_24 + IP0SR5_23_20 + IP0SR5_19_16 + IP0SR5_15_12 + IP0SR5_11_8 + IP0SR5_7_4 + IP0SR5_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP1SR5", 0xE6060864, 32, + GROUP(4, 4, 4, 4, 4, 4, 4, 4), + GROUP( + IP1SR5_31_28 + IP1SR5_27_24 + IP1SR5_23_20 + IP1SR5_19_16 + IP1SR5_15_12 + IP1SR5_11_8 + IP1SR5_7_4 + IP1SR5_3_0)) + }, + { PINMUX_CFG_REG_VAR("IP2SR5", 0xE6060868, 32, + GROUP(-12, 4, 4, 4, 4, 4), + GROUP( + /* IP2SR5_31_20 RESERVED */ + IP2SR5_19_16 + IP2SR5_15_12 + IP2SR5_11_8 + IP2SR5_7_4 + IP2SR5_3_0)) + }, { PINMUX_CFG_REG("IP0SR6", 0xE6061060, 32, 4, GROUP( IP0SR6_31_28 IP0SR6_27_24 @@ -3557,51 +3693,6 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { #define F_(x, y) x, #define FM(x) FN_##x, - { PINMUX_CFG_REG_VAR("MOD_SEL4", 0xE6060100, 32, - GROUP(-12, 1, 1, -2, 1, 1, -1, 1, -2, 1, 1, -2, 1, - -2, 1, 1, -1), - GROUP( - /* RESERVED 31-20 */ - MOD_SEL4_19 - MOD_SEL4_18 - /* RESERVED 17-16 */ - MOD_SEL4_15 - MOD_SEL4_14 - /* RESERVED 13 */ - MOD_SEL4_12 - /* RESERVED 11-10 */ - MOD_SEL4_9 - MOD_SEL4_8 - /* RESERVED 7-6 */ - MOD_SEL4_5 - /* RESERVED 4-3 */ - MOD_SEL4_2 - MOD_SEL4_1 - /* RESERVED 0 */ - )) - }, - { PINMUX_CFG_REG_VAR("MOD_SEL5", 0xE6060900, 32, - GROUP(-12, 1, -2, 1, 1, -2, 1, 1, -2, 1, -1, - 1, 1, -2, 1, -1, 1), - GROUP( - /* RESERVED 31-20 */ - MOD_SEL5_19 - /* RESERVED 18-17 */ - MOD_SEL5_16 - MOD_SEL5_15 - /* RESERVED 14-13 */ - MOD_SEL5_12 - MOD_SEL5_11 - /* RESERVED 10-9 */ - MOD_SEL5_8 - /* RESERVED 7 */ - MOD_SEL5_6 - MOD_SEL5_5 - /* RESERVED 4-3 */ - MOD_SEL5_2 - /* RESERVED 1 */ - MOD_SEL5_0)) - }, { PINMUX_CFG_REG_VAR("MOD_SEL6", 0xE6061100, 32, GROUP(-13, 1, -1, 1, -2, 1, 1, -1, 1, -2, 1, 1, 1, -2, 1, 1, -1), -- GitLab From 203734a0419cade9c76016f66e2c7ba354c249b4 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 21 Nov 2022 14:18:38 +0100 Subject: [PATCH 0251/5631] pinctrl: renesas: r8a779g0: Fix Group 6/7 pin functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to R-Car V4H Series User’s Manual: Hardware Rev. 0.54, pin groups 6 and 7 do not use Module Select Registers to configure pin functions. Hence: - Remove the non-existent Module Select Registers (MODSEL[67]), - Correct the affected PINMUX definitions. Fixes: 36611d28f5130d8b ("pinctrl: renesas: r8a779g0: Add missing MODSELx for AVBx") Fixes: ad9bb2fec66262b0 ("pinctrl: renesas: Initial R8A779G0 (R-Car V4H) PFC support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/06972cafd0efa4cfb395cfa76000a1bdae5e9e73.1669036423.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 171 +++++++------------------ 1 file changed, 49 insertions(+), 122 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index a2fa1c5bc3f6..70f81844748b 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -649,30 +649,6 @@ FM(IP0SR8_23_20) IP0SR8_23_20 FM(IP1SR8_23_20) IP1SR8_23_20 \ FM(IP0SR8_27_24) IP0SR8_27_24 \ FM(IP0SR8_31_28) IP0SR8_31_28 -/* MOD_SEL6 */ /* 0 */ /* 1 */ -#define MOD_SEL6_18 FM(SEL_AVB1_TD3_0) FM(SEL_AVB1_TD3_1) -#define MOD_SEL6_16 FM(SEL_AVB1_TD2_0) FM(SEL_AVB1_TD2_1) -#define MOD_SEL6_13 FM(SEL_AVB1_TD0_0) FM(SEL_AVB1_TD0_1) -#define MOD_SEL6_12 FM(SEL_AVB1_TD1_0) FM(SEL_AVB1_TD1_1) -#define MOD_SEL6_10 FM(SEL_AVB1_AVTP_PPS_0) FM(SEL_AVB1_AVTP_PPS_1) -#define MOD_SEL6_7 FM(SEL_AVB1_TX_CTL_0) FM(SEL_AVB1_TX_CTL_1) -#define MOD_SEL6_6 FM(SEL_AVB1_TXC_0) FM(SEL_AVB1_TXC_1) -#define MOD_SEL6_5 FM(SEL_AVB1_AVTP_MATCH_0) FM(SEL_AVB1_AVTP_MATCH_1) -#define MOD_SEL6_2 FM(SEL_AVB1_MDC_0) FM(SEL_AVB1_MDC_1) -#define MOD_SEL6_1 FM(SEL_AVB1_MAGIC_0) FM(SEL_AVB1_MAGIC_1) - -/* MOD_SEL7 */ /* 0 */ /* 1 */ -#define MOD_SEL7_16 FM(SEL_AVB0_TX_CTL_0) FM(SEL_AVB0_TX_CTL_1) -#define MOD_SEL7_15 FM(SEL_AVB0_TXC_0) FM(SEL_AVB0_TXC_1) -#define MOD_SEL7_13 FM(SEL_AVB0_MDC_0) FM(SEL_AVB0_MDC_1) -#define MOD_SEL7_11 FM(SEL_AVB0_TD0_0) FM(SEL_AVB0_TD0_1) -#define MOD_SEL7_10 FM(SEL_AVB0_MAGIC_0) FM(SEL_AVB0_MAGIC_1) -#define MOD_SEL7_7 FM(SEL_AVB0_TD1_0) FM(SEL_AVB0_TD1_1) -#define MOD_SEL7_6 FM(SEL_AVB0_TD2_0) FM(SEL_AVB0_TD2_1) -#define MOD_SEL7_3 FM(SEL_AVB0_TD3_0) FM(SEL_AVB0_TD3_1) -#define MOD_SEL7_2 FM(SEL_AVB0_AVTP_MATCH_0) FM(SEL_AVB0_AVTP_MATCH_1) -#define MOD_SEL7_0 FM(SEL_AVB0_AVTP_PPS_0) FM(SEL_AVB0_AVTP_PPS_1) - /* MOD_SEL8 */ /* 0 */ /* 1 */ #define MOD_SEL8_11 FM(SEL_SDA5_0) FM(SEL_SDA5_1) #define MOD_SEL8_10 FM(SEL_SCL5_0) FM(SEL_SCL5_1) @@ -689,23 +665,18 @@ FM(IP0SR8_31_28) IP0SR8_31_28 #define PINMUX_MOD_SELS \ \ -MOD_SEL6_18 \ -MOD_SEL6_16 MOD_SEL7_16 \ - MOD_SEL7_15 \ -MOD_SEL6_13 MOD_SEL7_13 \ -MOD_SEL6_12 \ - MOD_SEL7_11 MOD_SEL8_11 \ -MOD_SEL6_10 MOD_SEL7_10 MOD_SEL8_10 \ - MOD_SEL8_9 \ - MOD_SEL8_8 \ -MOD_SEL6_7 MOD_SEL7_7 MOD_SEL8_7 \ -MOD_SEL6_6 MOD_SEL7_6 MOD_SEL8_6 \ -MOD_SEL6_5 MOD_SEL8_5 \ - MOD_SEL8_4 \ - MOD_SEL7_3 MOD_SEL8_3 \ -MOD_SEL6_2 MOD_SEL7_2 MOD_SEL8_2 \ -MOD_SEL6_1 MOD_SEL8_1 \ - MOD_SEL7_0 MOD_SEL8_0 +MOD_SEL8_11 \ +MOD_SEL8_10 \ +MOD_SEL8_9 \ +MOD_SEL8_8 \ +MOD_SEL8_7 \ +MOD_SEL8_6 \ +MOD_SEL8_5 \ +MOD_SEL8_4 \ +MOD_SEL8_3 \ +MOD_SEL8_2 \ +MOD_SEL8_1 \ +MOD_SEL8_0 enum { PINMUX_RESERVED = 0, @@ -1092,23 +1063,23 @@ static const u16 pinmux_data[] = { /* IP0SR6 */ PINMUX_IPSR_GPSR(IP0SR6_3_0, AVB1_MDIO), - PINMUX_IPSR_MSEL(IP0SR6_7_4, AVB1_MAGIC, SEL_AVB1_MAGIC_1), + PINMUX_IPSR_GPSR(IP0SR6_7_4, AVB1_MAGIC), - PINMUX_IPSR_MSEL(IP0SR6_11_8, AVB1_MDC, SEL_AVB1_MDC_1), + PINMUX_IPSR_GPSR(IP0SR6_11_8, AVB1_MDC), PINMUX_IPSR_GPSR(IP0SR6_15_12, AVB1_PHY_INT), PINMUX_IPSR_GPSR(IP0SR6_19_16, AVB1_LINK), PINMUX_IPSR_GPSR(IP0SR6_19_16, AVB1_MII_TX_ER), - PINMUX_IPSR_MSEL(IP0SR6_23_20, AVB1_AVTP_MATCH, SEL_AVB1_AVTP_MATCH_1), - PINMUX_IPSR_MSEL(IP0SR6_23_20, AVB1_MII_RX_ER, SEL_AVB1_AVTP_MATCH_0), + PINMUX_IPSR_GPSR(IP0SR6_23_20, AVB1_AVTP_MATCH), + PINMUX_IPSR_GPSR(IP0SR6_23_20, AVB1_MII_RX_ER), - PINMUX_IPSR_MSEL(IP0SR6_27_24, AVB1_TXC, SEL_AVB1_TXC_1), - PINMUX_IPSR_MSEL(IP0SR6_27_24, AVB1_MII_TXC, SEL_AVB1_TXC_0), + PINMUX_IPSR_GPSR(IP0SR6_27_24, AVB1_TXC), + PINMUX_IPSR_GPSR(IP0SR6_27_24, AVB1_MII_TXC), - PINMUX_IPSR_MSEL(IP0SR6_31_28, AVB1_TX_CTL, SEL_AVB1_TX_CTL_1), - PINMUX_IPSR_MSEL(IP0SR6_31_28, AVB1_MII_TX_EN, SEL_AVB1_TX_CTL_0), + PINMUX_IPSR_GPSR(IP0SR6_31_28, AVB1_TX_CTL), + PINMUX_IPSR_GPSR(IP0SR6_31_28, AVB1_MII_TX_EN), /* IP1SR6 */ PINMUX_IPSR_GPSR(IP1SR6_3_0, AVB1_RXC), @@ -1117,17 +1088,17 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP1SR6_7_4, AVB1_RX_CTL), PINMUX_IPSR_GPSR(IP1SR6_7_4, AVB1_MII_RX_DV), - PINMUX_IPSR_MSEL(IP1SR6_11_8, AVB1_AVTP_PPS, SEL_AVB1_AVTP_PPS_1), - PINMUX_IPSR_MSEL(IP1SR6_11_8, AVB1_MII_COL, SEL_AVB1_AVTP_PPS_0), + PINMUX_IPSR_GPSR(IP1SR6_11_8, AVB1_AVTP_PPS), + PINMUX_IPSR_GPSR(IP1SR6_11_8, AVB1_MII_COL), PINMUX_IPSR_GPSR(IP1SR6_15_12, AVB1_AVTP_CAPTURE), PINMUX_IPSR_GPSR(IP1SR6_15_12, AVB1_MII_CRS), - PINMUX_IPSR_MSEL(IP1SR6_19_16, AVB1_TD1, SEL_AVB1_TD1_1), - PINMUX_IPSR_MSEL(IP1SR6_19_16, AVB1_MII_TD1, SEL_AVB1_TD1_0), + PINMUX_IPSR_GPSR(IP1SR6_19_16, AVB1_TD1), + PINMUX_IPSR_GPSR(IP1SR6_19_16, AVB1_MII_TD1), - PINMUX_IPSR_MSEL(IP1SR6_23_20, AVB1_TD0, SEL_AVB1_TD0_1), - PINMUX_IPSR_MSEL(IP1SR6_23_20, AVB1_MII_TD0, SEL_AVB1_TD0_0), + PINMUX_IPSR_GPSR(IP1SR6_23_20, AVB1_TD0), + PINMUX_IPSR_GPSR(IP1SR6_23_20, AVB1_MII_TD0), PINMUX_IPSR_GPSR(IP1SR6_27_24, AVB1_RD1), PINMUX_IPSR_GPSR(IP1SR6_27_24, AVB1_MII_RD1), @@ -1136,14 +1107,14 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP1SR6_31_28, AVB1_MII_RD0), /* IP2SR6 */ - PINMUX_IPSR_MSEL(IP2SR6_3_0, AVB1_TD2, SEL_AVB1_TD2_1), - PINMUX_IPSR_MSEL(IP2SR6_3_0, AVB1_MII_TD2, SEL_AVB1_TD2_0), + PINMUX_IPSR_GPSR(IP2SR6_3_0, AVB1_TD2), + PINMUX_IPSR_GPSR(IP2SR6_3_0, AVB1_MII_TD2), PINMUX_IPSR_GPSR(IP2SR6_7_4, AVB1_RD2), PINMUX_IPSR_GPSR(IP2SR6_7_4, AVB1_MII_RD2), - PINMUX_IPSR_MSEL(IP2SR6_11_8, AVB1_TD3, SEL_AVB1_TD3_1), - PINMUX_IPSR_MSEL(IP2SR6_11_8, AVB1_MII_TD3, SEL_AVB1_TD3_0), + PINMUX_IPSR_GPSR(IP2SR6_11_8, AVB1_TD3), + PINMUX_IPSR_GPSR(IP2SR6_11_8, AVB1_MII_TD3), PINMUX_IPSR_GPSR(IP2SR6_15_12, AVB1_RD3), PINMUX_IPSR_GPSR(IP2SR6_15_12, AVB1_MII_RD3), @@ -1151,29 +1122,29 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP2SR6_19_16, AVB1_TXCREFCLK), /* IP0SR7 */ - PINMUX_IPSR_MSEL(IP0SR7_3_0, AVB0_AVTP_PPS, SEL_AVB0_AVTP_PPS_1), - PINMUX_IPSR_MSEL(IP0SR7_3_0, AVB0_MII_COL, SEL_AVB0_AVTP_PPS_0), + PINMUX_IPSR_GPSR(IP0SR7_3_0, AVB0_AVTP_PPS), + PINMUX_IPSR_GPSR(IP0SR7_3_0, AVB0_MII_COL), PINMUX_IPSR_GPSR(IP0SR7_7_4, AVB0_AVTP_CAPTURE), PINMUX_IPSR_GPSR(IP0SR7_7_4, AVB0_MII_CRS), - PINMUX_IPSR_MSEL(IP0SR7_11_8, AVB0_AVTP_MATCH, SEL_AVB0_AVTP_MATCH_1), - PINMUX_IPSR_MSEL(IP0SR7_11_8, AVB0_MII_RX_ER, SEL_AVB0_AVTP_MATCH_0), - PINMUX_IPSR_MSEL(IP0SR7_11_8, CC5_OSCOUT, SEL_AVB0_AVTP_MATCH_0), + PINMUX_IPSR_GPSR(IP0SR7_11_8, AVB0_AVTP_MATCH), + PINMUX_IPSR_GPSR(IP0SR7_11_8, AVB0_MII_RX_ER), + PINMUX_IPSR_GPSR(IP0SR7_11_8, CC5_OSCOUT), - PINMUX_IPSR_MSEL(IP0SR7_15_12, AVB0_TD3, SEL_AVB0_TD3_1), - PINMUX_IPSR_MSEL(IP0SR7_15_12, AVB0_MII_TD3, SEL_AVB0_TD3_0), + PINMUX_IPSR_GPSR(IP0SR7_15_12, AVB0_TD3), + PINMUX_IPSR_GPSR(IP0SR7_15_12, AVB0_MII_TD3), PINMUX_IPSR_GPSR(IP0SR7_19_16, AVB0_LINK), PINMUX_IPSR_GPSR(IP0SR7_19_16, AVB0_MII_TX_ER), PINMUX_IPSR_GPSR(IP0SR7_23_20, AVB0_PHY_INT), - PINMUX_IPSR_MSEL(IP0SR7_27_24, AVB0_TD2, SEL_AVB0_TD2_1), - PINMUX_IPSR_MSEL(IP0SR7_27_24, AVB0_MII_TD2, SEL_AVB0_TD2_0), + PINMUX_IPSR_GPSR(IP0SR7_27_24, AVB0_TD2), + PINMUX_IPSR_GPSR(IP0SR7_27_24, AVB0_MII_TD2), - PINMUX_IPSR_MSEL(IP0SR7_31_28, AVB0_TD1, SEL_AVB0_TD1_1), - PINMUX_IPSR_MSEL(IP0SR7_31_28, AVB0_MII_TD1, SEL_AVB0_TD1_0), + PINMUX_IPSR_GPSR(IP0SR7_31_28, AVB0_TD1), + PINMUX_IPSR_GPSR(IP0SR7_31_28, AVB0_MII_TD1), /* IP1SR7 */ PINMUX_IPSR_GPSR(IP1SR7_3_0, AVB0_RD3), @@ -1181,24 +1152,24 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP1SR7_7_4, AVB0_TXCREFCLK), - PINMUX_IPSR_MSEL(IP1SR7_11_8, AVB0_MAGIC, SEL_AVB0_MAGIC_1), + PINMUX_IPSR_GPSR(IP1SR7_11_8, AVB0_MAGIC), - PINMUX_IPSR_MSEL(IP1SR7_15_12, AVB0_TD0, SEL_AVB0_TD0_1), - PINMUX_IPSR_MSEL(IP1SR7_15_12, AVB0_MII_TD0, SEL_AVB0_TD0_0), + PINMUX_IPSR_GPSR(IP1SR7_15_12, AVB0_TD0), + PINMUX_IPSR_GPSR(IP1SR7_15_12, AVB0_MII_TD0), PINMUX_IPSR_GPSR(IP1SR7_19_16, AVB0_RD2), PINMUX_IPSR_GPSR(IP1SR7_19_16, AVB0_MII_RD2), - PINMUX_IPSR_MSEL(IP1SR7_23_20, AVB0_MDC, SEL_AVB0_MDC_1), + PINMUX_IPSR_GPSR(IP1SR7_23_20, AVB0_MDC), PINMUX_IPSR_GPSR(IP1SR7_27_24, AVB0_MDIO), - PINMUX_IPSR_MSEL(IP1SR7_31_28, AVB0_TXC, SEL_AVB0_TXC_1), - PINMUX_IPSR_MSEL(IP1SR7_31_28, AVB0_MII_TXC, SEL_AVB0_TXC_0), + PINMUX_IPSR_GPSR(IP1SR7_31_28, AVB0_TXC), + PINMUX_IPSR_GPSR(IP1SR7_31_28, AVB0_MII_TXC), /* IP2SR7 */ - PINMUX_IPSR_MSEL(IP2SR7_3_0, AVB0_TX_CTL, SEL_AVB0_TX_CTL_1), - PINMUX_IPSR_MSEL(IP2SR7_3_0, AVB0_MII_TX_EN, SEL_AVB0_TX_CTL_0), + PINMUX_IPSR_GPSR(IP2SR7_3_0, AVB0_TX_CTL), + PINMUX_IPSR_GPSR(IP2SR7_3_0, AVB0_MII_TX_EN), PINMUX_IPSR_GPSR(IP2SR7_7_4, AVB0_RD1), PINMUX_IPSR_GPSR(IP2SR7_7_4, AVB0_MII_RD1), @@ -3693,50 +3664,6 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { #define F_(x, y) x, #define FM(x) FN_##x, - { PINMUX_CFG_REG_VAR("MOD_SEL6", 0xE6061100, 32, - GROUP(-13, 1, -1, 1, -2, 1, 1, - -1, 1, -2, 1, 1, 1, -2, 1, 1, -1), - GROUP( - /* RESERVED 31-19 */ - MOD_SEL6_18 - /* RESERVED 17 */ - MOD_SEL6_16 - /* RESERVED 15-14 */ - MOD_SEL6_13 - MOD_SEL6_12 - /* RESERVED 11 */ - MOD_SEL6_10 - /* RESERVED 9-8 */ - MOD_SEL6_7 - MOD_SEL6_6 - MOD_SEL6_5 - /* RESERVED 4-3 */ - MOD_SEL6_2 - MOD_SEL6_1 - /* RESERVED 0 */ - )) - }, - { PINMUX_CFG_REG_VAR("MOD_SEL7", 0xE6061900, 32, - GROUP(-15, 1, 1, -1, 1, -1, 1, 1, -2, 1, 1, - -2, 1, 1, -1, 1), - GROUP( - /* RESERVED 31-17 */ - MOD_SEL7_16 - MOD_SEL7_15 - /* RESERVED 14 */ - MOD_SEL7_13 - /* RESERVED 12 */ - MOD_SEL7_11 - MOD_SEL7_10 - /* RESERVED 9-8 */ - MOD_SEL7_7 - MOD_SEL7_6 - /* RESERVED 5-4 */ - MOD_SEL7_3 - MOD_SEL7_2 - /* RESERVED 1 */ - MOD_SEL7_0)) - }, { PINMUX_CFG_REG_VAR("MOD_SEL8", 0xE6068100, 32, GROUP(-20, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1), GROUP( -- GitLab From 9da805344d2a2d27a32cc9271230055d8818e887 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 21 Nov 2022 14:18:39 +0100 Subject: [PATCH 0252/5631] pinctrl: renesas: r8a779g0: Fix ERROROUTC function names MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to R-Car V4H Series User’s Manual: Hardware Rev. 0.54, the ERROROUTC signal is active-low. Hence add the missing "_N" suffix to the pin function's names. Resize column 2 of all IPxSR* definitions to accomodate the longer names. Fixes: b811062e5fd0343c ("pinctrl: renesas: r8a779g0: Add missing ERROROUTC_A") Fixes: ad9bb2fec66262b0 ("pinctrl: renesas: Initial R8A779G0 (R-Car V4H) PFC support") Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/1774303989e7d61f08fa81f1c2fa1b394505645f.1669036423.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 502 ++++++++++++------------- 1 file changed, 251 insertions(+), 251 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 70f81844748b..7c5379e2ede8 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -268,271 +268,271 @@ #define GPSR8_0 F_(SCL0, IP0SR8_3_0) /* SR0 */ -/* IP0SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR0_3_0 F_(0, 0) FM(ERROROUTC_B) FM(TCLK2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_7_4 F_(0, 0) FM(MSIOF3_SS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_11_8 F_(0, 0) FM(MSIOF3_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_15_12 FM(IRQ3) FM(MSIOF3_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_19_16 FM(IRQ2) FM(MSIOF3_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_23_20 FM(IRQ1) FM(MSIOF3_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_27_24 FM(IRQ0) FM(MSIOF3_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR0_31_28 FM(MSIOF5_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR0_3_0 FM(MSIOF5_SS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_7_4 FM(MSIOF5_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_11_8 FM(MSIOF5_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_15_12 FM(MSIOF5_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_19_16 FM(MSIOF5_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_23_20 FM(MSIOF2_SS2) FM(TCLK1) FM(IRQ2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_27_24 FM(MSIOF2_SS1) FM(HTX1) FM(TX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR0_31_28 FM(MSIOF2_SYNC) FM(HRX1) FM(RX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR0_3_0 FM(MSIOF2_TXD) FM(HCTS1_N) FM(CTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR0_7_4 FM(MSIOF2_SCK) FM(HRTS1_N) FM(RTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR0_11_8 FM(MSIOF2_RXD) FM(HSCK1) FM(SCK1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR0_3_0 F_(0, 0) FM(ERROROUTC_N_B) FM(TCLK2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_7_4 F_(0, 0) FM(MSIOF3_SS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_11_8 F_(0, 0) FM(MSIOF3_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_15_12 FM(IRQ3) FM(MSIOF3_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_19_16 FM(IRQ2) FM(MSIOF3_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_23_20 FM(IRQ1) FM(MSIOF3_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_27_24 FM(IRQ0) FM(MSIOF3_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR0_31_28 FM(MSIOF5_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR0_3_0 FM(MSIOF5_SS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_7_4 FM(MSIOF5_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_11_8 FM(MSIOF5_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_15_12 FM(MSIOF5_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_19_16 FM(MSIOF5_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_23_20 FM(MSIOF2_SS2) FM(TCLK1) FM(IRQ2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_27_24 FM(MSIOF2_SS1) FM(HTX1) FM(TX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR0_31_28 FM(MSIOF2_SYNC) FM(HRX1) FM(RX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR0_3_0 FM(MSIOF2_TXD) FM(HCTS1_N) FM(CTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR0_7_4 FM(MSIOF2_SCK) FM(HRTS1_N) FM(RTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR0_11_8 FM(MSIOF2_RXD) FM(HSCK1) FM(SCK1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR1 */ -/* IP0SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR1_3_0 FM(MSIOF1_SS2) FM(HTX3_A) FM(TX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_7_4 FM(MSIOF1_SS1) FM(HCTS3_N_A) FM(RX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_11_8 FM(MSIOF1_SYNC) FM(HRTS3_N_A) FM(RTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_15_12 FM(MSIOF1_SCK) FM(HSCK3_A) FM(CTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_19_16 FM(MSIOF1_TXD) FM(HRX3_A) FM(SCK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_23_20 FM(MSIOF1_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_27_24 FM(MSIOF0_SS2) FM(HTX1_X) FM(TX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR1_31_28 FM(MSIOF0_SS1) FM(HRX1_X) FM(RX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR1_3_0 FM(MSIOF0_SYNC) FM(HCTS1_N_X) FM(CTS1_N_X) FM(CANFD5_TX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_7_4 FM(MSIOF0_TXD) FM(HRTS1_N_X) FM(RTS1_N_X) FM(CANFD5_RX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_11_8 FM(MSIOF0_SCK) FM(HSCK1_X) FM(SCK1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_15_12 FM(MSIOF0_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_19_16 FM(HTX0) FM(TX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_23_20 FM(HCTS0_N) FM(CTS0_N) FM(PWM8_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_27_24 FM(HRTS0_N) FM(RTS0_N) FM(PWM9_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR1_31_28 FM(HSCK0) FM(SCK0) FM(PWM0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR1_3_0 FM(HRX0) FM(RX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_7_4 FM(SCIF_CLK) FM(IRQ4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_11_8 FM(SSI_SCK) FM(TCLK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_15_12 FM(SSI_WS) FM(TCLK4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_19_16 FM(SSI_SD) FM(IRQ0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_23_20 FM(AUDIO_CLKOUT) FM(IRQ1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_27_24 FM(AUDIO_CLKIN) FM(PWM3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR1_31_28 F_(0, 0) FM(TCLK2) FM(MSIOF4_SS1) FM(IRQ3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP3SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP3SR1_3_0 FM(HRX3) FM(SCK3_A) FM(MSIOF4_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR1_7_4 FM(HSCK3) FM(CTS3_N_A) FM(MSIOF4_SCK) FM(TPU0TO0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR1_11_8 FM(HRTS3_N) FM(RTS3_N_A) FM(MSIOF4_TXD) FM(TPU0TO1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR1_15_12 FM(HCTS3_N) FM(RX3_A) FM(MSIOF4_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR1_19_16 FM(HTX3) FM(TX3_A) FM(MSIOF4_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR1_3_0 FM(MSIOF1_SS2) FM(HTX3_A) FM(TX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_7_4 FM(MSIOF1_SS1) FM(HCTS3_N_A) FM(RX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_11_8 FM(MSIOF1_SYNC) FM(HRTS3_N_A) FM(RTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_15_12 FM(MSIOF1_SCK) FM(HSCK3_A) FM(CTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_19_16 FM(MSIOF1_TXD) FM(HRX3_A) FM(SCK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_23_20 FM(MSIOF1_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_27_24 FM(MSIOF0_SS2) FM(HTX1_X) FM(TX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR1_31_28 FM(MSIOF0_SS1) FM(HRX1_X) FM(RX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR1_3_0 FM(MSIOF0_SYNC) FM(HCTS1_N_X) FM(CTS1_N_X) FM(CANFD5_TX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_7_4 FM(MSIOF0_TXD) FM(HRTS1_N_X) FM(RTS1_N_X) FM(CANFD5_RX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_11_8 FM(MSIOF0_SCK) FM(HSCK1_X) FM(SCK1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_15_12 FM(MSIOF0_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_19_16 FM(HTX0) FM(TX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_23_20 FM(HCTS0_N) FM(CTS0_N) FM(PWM8_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_27_24 FM(HRTS0_N) FM(RTS0_N) FM(PWM9_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR1_31_28 FM(HSCK0) FM(SCK0) FM(PWM0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR1_3_0 FM(HRX0) FM(RX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_7_4 FM(SCIF_CLK) FM(IRQ4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_11_8 FM(SSI_SCK) FM(TCLK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_15_12 FM(SSI_WS) FM(TCLK4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_19_16 FM(SSI_SD) FM(IRQ0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_23_20 FM(AUDIO_CLKOUT) FM(IRQ1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_27_24 FM(AUDIO_CLKIN) FM(PWM3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR1_31_28 F_(0, 0) FM(TCLK2) FM(MSIOF4_SS1) FM(IRQ3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP3SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP3SR1_3_0 FM(HRX3) FM(SCK3_A) FM(MSIOF4_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR1_7_4 FM(HSCK3) FM(CTS3_N_A) FM(MSIOF4_SCK) FM(TPU0TO0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR1_11_8 FM(HRTS3_N) FM(RTS3_N_A) FM(MSIOF4_TXD) FM(TPU0TO1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR1_15_12 FM(HCTS3_N) FM(RX3_A) FM(MSIOF4_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR1_19_16 FM(HTX3) FM(TX3_A) FM(MSIOF4_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR2 */ -/* IP0SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR2_3_0 FM(FXR_TXDA) FM(CANFD1_TX) FM(TPU0TO2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_7_4 FM(FXR_TXENA_N) FM(CANFD1_RX) FM(TPU0TO3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_11_8 FM(RXDA_EXTFXR) FM(CANFD5_TX) FM(IRQ5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_15_12 FM(CLK_EXTFXR) FM(CANFD5_RX) FM(IRQ4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_19_16 FM(RXDB_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_23_20 FM(FXR_TXENB_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_27_24 FM(FXR_TXDB) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR2_31_28 FM(TPU0TO1) FM(CANFD6_TX) F_(0, 0) FM(TCLK2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR2_3_0 FM(TPU0TO0) FM(CANFD6_RX) F_(0, 0) FM(TCLK1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_7_4 FM(CAN_CLK) FM(FXR_TXENA_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_11_8 FM(CANFD0_TX) FM(FXR_TXENB_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_15_12 FM(CANFD0_RX) FM(STPWT_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_19_16 FM(CANFD2_TX) FM(TPU0TO2) F_(0, 0) FM(TCLK3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_23_20 FM(CANFD2_RX) FM(TPU0TO3) FM(PWM1_B) FM(TCLK4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_27_24 FM(CANFD3_TX) F_(0, 0) FM(PWM2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR2_31_28 FM(CANFD3_RX) F_(0, 0) FM(PWM3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR2_3_0 FM(CANFD4_TX) F_(0, 0) FM(PWM4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR2_7_4 FM(CANFD4_RX) F_(0, 0) FM(PWM5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR2_11_8 FM(CANFD7_TX) F_(0, 0) FM(PWM6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR2_15_12 FM(CANFD7_RX) F_(0, 0) FM(PWM7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR2_3_0 FM(FXR_TXDA) FM(CANFD1_TX) FM(TPU0TO2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_7_4 FM(FXR_TXENA_N) FM(CANFD1_RX) FM(TPU0TO3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_11_8 FM(RXDA_EXTFXR) FM(CANFD5_TX) FM(IRQ5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_15_12 FM(CLK_EXTFXR) FM(CANFD5_RX) FM(IRQ4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_19_16 FM(RXDB_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_23_20 FM(FXR_TXENB_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_27_24 FM(FXR_TXDB) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR2_31_28 FM(TPU0TO1) FM(CANFD6_TX) F_(0, 0) FM(TCLK2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR2_3_0 FM(TPU0TO0) FM(CANFD6_RX) F_(0, 0) FM(TCLK1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_7_4 FM(CAN_CLK) FM(FXR_TXENA_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_11_8 FM(CANFD0_TX) FM(FXR_TXENB_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_15_12 FM(CANFD0_RX) FM(STPWT_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_19_16 FM(CANFD2_TX) FM(TPU0TO2) F_(0, 0) FM(TCLK3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_23_20 FM(CANFD2_RX) FM(TPU0TO3) FM(PWM1_B) FM(TCLK4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_27_24 FM(CANFD3_TX) F_(0, 0) FM(PWM2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR2_31_28 FM(CANFD3_RX) F_(0, 0) FM(PWM3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR2_3_0 FM(CANFD4_TX) F_(0, 0) FM(PWM4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR2_7_4 FM(CANFD4_RX) F_(0, 0) FM(PWM5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR2_11_8 FM(CANFD7_TX) F_(0, 0) FM(PWM6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR2_15_12 FM(CANFD7_RX) F_(0, 0) FM(PWM7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR3 */ -/* IP0SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR3_3_0 FM(MMC_SD_D1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_7_4 FM(MMC_SD_D0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_11_8 FM(MMC_SD_D2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_15_12 FM(MMC_SD_CLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_19_16 FM(MMC_DS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_23_20 FM(MMC_SD_D3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_27_24 FM(MMC_D5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR3_31_28 FM(MMC_D4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR3_3_0 FM(MMC_D7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_7_4 FM(MMC_D6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_11_8 FM(MMC_SD_CMD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_15_12 FM(SD_CD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_19_16 FM(SD_WP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_23_20 FM(IPC_CLKIN) FM(IPC_CLKEN_IN) FM(PWM1_A) FM(TCLK3_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_27_24 FM(IPC_CLKOUT) FM(IPC_CLKEN_OUT) FM(ERROROUTC_A) FM(TCLK4_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR3_31_28 FM(QSPI0_SSL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR3_3_0 FM(QSPI0_IO3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_7_4 FM(QSPI0_IO2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_11_8 FM(QSPI0_MISO_IO1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_15_12 FM(QSPI0_MOSI_IO0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_19_16 FM(QSPI0_SPCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_23_20 FM(QSPI1_MOSI_IO0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_27_24 FM(QSPI1_SPCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR3_31_28 FM(QSPI1_MISO_IO1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP3SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP3SR3_3_0 FM(QSPI1_IO2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR3_7_4 FM(QSPI1_SSL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR3_11_8 FM(QSPI1_IO3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR3_15_12 FM(RPC_RESET_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR3_19_16 FM(RPC_WP_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3SR3_23_20 FM(RPC_INT_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR3_3_0 FM(MMC_SD_D1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_7_4 FM(MMC_SD_D0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_11_8 FM(MMC_SD_D2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_15_12 FM(MMC_SD_CLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_19_16 FM(MMC_DS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_23_20 FM(MMC_SD_D3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_27_24 FM(MMC_D5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR3_31_28 FM(MMC_D4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR3_3_0 FM(MMC_D7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_7_4 FM(MMC_D6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_11_8 FM(MMC_SD_CMD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_15_12 FM(SD_CD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_19_16 FM(SD_WP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_23_20 FM(IPC_CLKIN) FM(IPC_CLKEN_IN) FM(PWM1_A) FM(TCLK3_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_27_24 FM(IPC_CLKOUT) FM(IPC_CLKEN_OUT) FM(ERROROUTC_N_A) FM(TCLK4_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR3_31_28 FM(QSPI0_SSL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR3_3_0 FM(QSPI0_IO3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_7_4 FM(QSPI0_IO2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_11_8 FM(QSPI0_MISO_IO1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_15_12 FM(QSPI0_MOSI_IO0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_19_16 FM(QSPI0_SPCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_23_20 FM(QSPI1_MOSI_IO0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_27_24 FM(QSPI1_SPCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR3_31_28 FM(QSPI1_MISO_IO1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP3SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP3SR3_3_0 FM(QSPI1_IO2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR3_7_4 FM(QSPI1_SSL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR3_11_8 FM(QSPI1_IO3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR3_15_12 FM(RPC_RESET_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR3_19_16 FM(RPC_WP_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP3SR3_23_20 FM(RPC_INT_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR4 */ -/* IP0SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR4_3_0 FM(TSN0_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_7_4 FM(TSN0_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_11_8 FM(TSN0_AVTP_PPS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_15_12 FM(TSN0_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_19_16 FM(TSN0_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_23_20 FM(TSN0_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_27_24 FM(TSN0_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR4_31_28 FM(TSN0_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR4_3_0 FM(TSN0_AVTP_PPS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_7_4 FM(TSN0_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_11_8 FM(TSN0_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_15_12 FM(TSN0_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_19_16 FM(TSN0_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_23_20 FM(TSN0_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_27_24 FM(TSN0_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR4_31_28 FM(TSN0_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR4_3_0 FM(TSN0_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_7_4 FM(TSN0_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_11_8 FM(TSN0_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_15_12 FM(TSN0_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_19_16 FM(TSN0_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_23_20 FM(PCIE0_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_27_24 FM(PCIE1_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR4_31_28 FM(AVS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP3SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP3SR4_3_0 FM(AVS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR4_3_0 FM(TSN0_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_7_4 FM(TSN0_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_11_8 FM(TSN0_AVTP_PPS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_15_12 FM(TSN0_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_19_16 FM(TSN0_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_23_20 FM(TSN0_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_27_24 FM(TSN0_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR4_31_28 FM(TSN0_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR4_3_0 FM(TSN0_AVTP_PPS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_7_4 FM(TSN0_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_11_8 FM(TSN0_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_15_12 FM(TSN0_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_19_16 FM(TSN0_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_23_20 FM(TSN0_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_27_24 FM(TSN0_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR4_31_28 FM(TSN0_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR4_3_0 FM(TSN0_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_7_4 FM(TSN0_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_11_8 FM(TSN0_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_15_12 FM(TSN0_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_19_16 FM(TSN0_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_23_20 FM(PCIE0_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_27_24 FM(PCIE1_CLKREQ_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR4_31_28 FM(AVS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP3SR4 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP3SR4_3_0 FM(AVS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR5 */ -/* IP0SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR5_3_0 FM(AVB2_AVTP_PPS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_7_4 FM(AVB2_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_11_8 FM(AVB2_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_15_12 FM(AVB2_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_19_16 FM(AVB2_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_23_20 FM(AVB2_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_27_24 FM(AVB2_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR5_31_28 FM(AVB2_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR5_3_0 FM(AVB2_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_7_4 FM(AVB2_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_11_8 FM(AVB2_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_15_12 FM(AVB2_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_19_16 FM(AVB2_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_23_20 FM(AVB2_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_27_24 FM(AVB2_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR5_31_28 FM(AVB2_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR5_3_0 FM(AVB2_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR5_7_4 FM(AVB2_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR5_11_8 FM(AVB2_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR5_15_12 FM(AVB2_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR5_19_16 FM(AVB2_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR5_3_0 FM(AVB2_AVTP_PPS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_7_4 FM(AVB2_AVTP_CAPTURE) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_11_8 FM(AVB2_AVTP_MATCH) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_15_12 FM(AVB2_LINK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_19_16 FM(AVB2_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_23_20 FM(AVB2_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_27_24 FM(AVB2_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR5_31_28 FM(AVB2_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR5_3_0 FM(AVB2_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_7_4 FM(AVB2_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_11_8 FM(AVB2_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_15_12 FM(AVB2_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_19_16 FM(AVB2_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_23_20 FM(AVB2_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_27_24 FM(AVB2_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR5_31_28 FM(AVB2_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR5 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR5_3_0 FM(AVB2_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_7_4 FM(AVB2_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_11_8 FM(AVB2_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_15_12 FM(AVB2_TX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR5_19_16 FM(AVB2_RX_CTL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR6 */ -/* IP0SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR6_3_0 FM(AVB1_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_7_4 FM(AVB1_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_11_8 FM(AVB1_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_15_12 FM(AVB1_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_19_16 FM(AVB1_LINK) FM(AVB1_MII_TX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_23_20 FM(AVB1_AVTP_MATCH) FM(AVB1_MII_RX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_27_24 FM(AVB1_TXC) FM(AVB1_MII_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR6_31_28 FM(AVB1_TX_CTL) FM(AVB1_MII_TX_EN) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR6_3_0 FM(AVB1_RXC) FM(AVB1_MII_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_7_4 FM(AVB1_RX_CTL) FM(AVB1_MII_RX_DV) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_11_8 FM(AVB1_AVTP_PPS) FM(AVB1_MII_COL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_15_12 FM(AVB1_AVTP_CAPTURE) FM(AVB1_MII_CRS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_19_16 FM(AVB1_TD1) FM(AVB1_MII_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_23_20 FM(AVB1_TD0) FM(AVB1_MII_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_27_24 FM(AVB1_RD1) FM(AVB1_MII_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR6_31_28 FM(AVB1_RD0) FM(AVB1_MII_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR6_3_0 FM(AVB1_TD2) FM(AVB1_MII_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR6_7_4 FM(AVB1_RD2) FM(AVB1_MII_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR6_11_8 FM(AVB1_TD3) FM(AVB1_MII_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR6_15_12 FM(AVB1_RD3) FM(AVB1_MII_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR6_19_16 FM(AVB1_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR6_3_0 FM(AVB1_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_7_4 FM(AVB1_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_11_8 FM(AVB1_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_15_12 FM(AVB1_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_19_16 FM(AVB1_LINK) FM(AVB1_MII_TX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_23_20 FM(AVB1_AVTP_MATCH) FM(AVB1_MII_RX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_27_24 FM(AVB1_TXC) FM(AVB1_MII_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR6_31_28 FM(AVB1_TX_CTL) FM(AVB1_MII_TX_EN) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR6_3_0 FM(AVB1_RXC) FM(AVB1_MII_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_7_4 FM(AVB1_RX_CTL) FM(AVB1_MII_RX_DV) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_11_8 FM(AVB1_AVTP_PPS) FM(AVB1_MII_COL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_15_12 FM(AVB1_AVTP_CAPTURE) FM(AVB1_MII_CRS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_19_16 FM(AVB1_TD1) FM(AVB1_MII_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_23_20 FM(AVB1_TD0) FM(AVB1_MII_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_27_24 FM(AVB1_RD1) FM(AVB1_MII_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR6_31_28 FM(AVB1_RD0) FM(AVB1_MII_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR6 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR6_3_0 FM(AVB1_TD2) FM(AVB1_MII_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR6_7_4 FM(AVB1_RD2) FM(AVB1_MII_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR6_11_8 FM(AVB1_TD3) FM(AVB1_MII_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR6_15_12 FM(AVB1_RD3) FM(AVB1_MII_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR6_19_16 FM(AVB1_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR7 */ -/* IP0SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR7_3_0 FM(AVB0_AVTP_PPS) FM(AVB0_MII_COL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_7_4 FM(AVB0_AVTP_CAPTURE) FM(AVB0_MII_CRS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_11_8 FM(AVB0_AVTP_MATCH) FM(AVB0_MII_RX_ER) FM(CC5_OSCOUT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_15_12 FM(AVB0_TD3) FM(AVB0_MII_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_19_16 FM(AVB0_LINK) FM(AVB0_MII_TX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_23_20 FM(AVB0_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_27_24 FM(AVB0_TD2) FM(AVB0_MII_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR7_31_28 FM(AVB0_TD1) FM(AVB0_MII_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR7_3_0 FM(AVB0_RD3) FM(AVB0_MII_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_7_4 FM(AVB0_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_11_8 FM(AVB0_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_15_12 FM(AVB0_TD0) FM(AVB0_MII_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_19_16 FM(AVB0_RD2) FM(AVB0_MII_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_23_20 FM(AVB0_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_27_24 FM(AVB0_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR7_31_28 FM(AVB0_TXC) FM(AVB0_MII_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP2SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP2SR7_3_0 FM(AVB0_TX_CTL) FM(AVB0_MII_TX_EN) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR7_7_4 FM(AVB0_RD1) FM(AVB0_MII_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR7_11_8 FM(AVB0_RD0) FM(AVB0_MII_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR7_15_12 FM(AVB0_RXC) FM(AVB0_MII_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2SR7_19_16 FM(AVB0_RX_CTL) FM(AVB0_MII_RX_DV) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR7_3_0 FM(AVB0_AVTP_PPS) FM(AVB0_MII_COL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_7_4 FM(AVB0_AVTP_CAPTURE) FM(AVB0_MII_CRS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_11_8 FM(AVB0_AVTP_MATCH) FM(AVB0_MII_RX_ER) FM(CC5_OSCOUT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_15_12 FM(AVB0_TD3) FM(AVB0_MII_TD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_19_16 FM(AVB0_LINK) FM(AVB0_MII_TX_ER) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_23_20 FM(AVB0_PHY_INT) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_27_24 FM(AVB0_TD2) FM(AVB0_MII_TD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR7_31_28 FM(AVB0_TD1) FM(AVB0_MII_TD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR7_3_0 FM(AVB0_RD3) FM(AVB0_MII_RD3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_7_4 FM(AVB0_TXCREFCLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_11_8 FM(AVB0_MAGIC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_15_12 FM(AVB0_TD0) FM(AVB0_MII_TD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_19_16 FM(AVB0_RD2) FM(AVB0_MII_RD2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_23_20 FM(AVB0_MDC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_27_24 FM(AVB0_MDIO) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR7_31_28 FM(AVB0_TXC) FM(AVB0_MII_TXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP2SR7 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP2SR7_3_0 FM(AVB0_TX_CTL) FM(AVB0_MII_TX_EN) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR7_7_4 FM(AVB0_RD1) FM(AVB0_MII_RD1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR7_11_8 FM(AVB0_RD0) FM(AVB0_MII_RD0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR7_15_12 FM(AVB0_RXC) FM(AVB0_MII_RXC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP2SR7_19_16 FM(AVB0_RX_CTL) FM(AVB0_MII_RX_DV) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) /* SR8 */ -/* IP0SR8 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP0SR8_3_0 FM(SCL0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_7_4 FM(SDA0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_11_8 FM(SCL1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_15_12 FM(SDA1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_19_16 FM(SCL2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_23_20 FM(SDA2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_27_24 FM(SCL3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0SR8_31_28 FM(SDA3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IP1SR8 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ -#define IP1SR8_3_0 FM(SCL4) FM(HRX2) FM(SCK4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR8_7_4 FM(SDA4) FM(HTX2) FM(CTS4_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR8_11_8 FM(SCL5) FM(HRTS2_N) FM(RTS4_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR8_15_12 FM(SDA5) FM(SCIF_CLK2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR8_19_16 F_(0, 0) FM(HCTS2_N) FM(TX4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1SR8_23_20 F_(0, 0) FM(HSCK2) FM(RX4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +/* IP0SR8 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP0SR8_3_0 FM(SCL0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_7_4 FM(SDA0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_11_8 FM(SCL1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_15_12 FM(SDA1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_19_16 FM(SCL2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_23_20 FM(SDA2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_27_24 FM(SCL3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP0SR8_31_28 FM(SDA3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) + +/* IP1SR8 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */ +#define IP1SR8_3_0 FM(SCL4) FM(HRX2) FM(SCK4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR8_7_4 FM(SDA4) FM(HTX2) FM(CTS4_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR8_11_8 FM(SCL5) FM(HRTS2_N) FM(RTS4_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR8_15_12 FM(SDA5) FM(SCIF_CLK2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR8_19_16 F_(0, 0) FM(HCTS2_N) FM(TX4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) +#define IP1SR8_23_20 F_(0, 0) FM(HSCK2) FM(RX4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) #define PINMUX_GPSR \ GPSR3_29 \ @@ -711,7 +711,7 @@ static const u16 pinmux_data[] = { PINMUX_DATA_GP_ALL(), /* IP0SR0 */ - PINMUX_IPSR_GPSR(IP0SR0_3_0, ERROROUTC_B), + PINMUX_IPSR_GPSR(IP0SR0_3_0, ERROROUTC_N_B), PINMUX_IPSR_GPSR(IP0SR0_3_0, TCLK2_A), PINMUX_IPSR_GPSR(IP0SR0_7_4, MSIOF3_SS1), @@ -977,7 +977,7 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_GPSR(IP1SR3_27_24, IPC_CLKOUT), PINMUX_IPSR_GPSR(IP1SR3_27_24, IPC_CLKEN_OUT), - PINMUX_IPSR_GPSR(IP1SR3_27_24, ERROROUTC_A), + PINMUX_IPSR_GPSR(IP1SR3_27_24, ERROROUTC_N_A), PINMUX_IPSR_GPSR(IP1SR3_27_24, TCLK4_X), PINMUX_IPSR_GPSR(IP1SR3_31_28, QSPI0_SSL), -- GitLab From 47ea7ff19f0bedba4209a641bca60e0ef6fdabc0 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 11:56:37 +0100 Subject: [PATCH 0253/5631] pinctrl: renesas: Remove R-Car H3 ES1.* handling R-Car H3 ES1.* was only available to an internal development group and needed a lot of quirks and workarounds. These become a maintenance burden now, so our development group decided to remove upstream support and disable booting for this SoC. Public users only have ES2 onwards. Signed-off-by: Wolfram Sang Reviewed-by: Laurent Pinchart Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230307105645.5285-2-wsa+renesas@sang-engineering.com Signed-off-by: Geert Uytterhoeven --- drivers/pinctrl/renesas/Kconfig | 5 - drivers/pinctrl/renesas/Makefile | 1 - drivers/pinctrl/renesas/core.c | 41 +- drivers/pinctrl/renesas/pfc-r8a77950.c | 5947 ------------------------ drivers/pinctrl/renesas/sh_pfc.h | 1 - 5 files changed, 3 insertions(+), 5992 deletions(-) delete mode 100644 drivers/pinctrl/renesas/pfc-r8a77950.c diff --git a/drivers/pinctrl/renesas/Kconfig b/drivers/pinctrl/renesas/Kconfig index 0903a0a41831..77730dc548ed 100644 --- a/drivers/pinctrl/renesas/Kconfig +++ b/drivers/pinctrl/renesas/Kconfig @@ -27,7 +27,6 @@ config PINCTRL_RENESAS select PINCTRL_PFC_R8A7792 if ARCH_R8A7792 select PINCTRL_PFC_R8A7793 if ARCH_R8A7793 select PINCTRL_PFC_R8A7794 if ARCH_R8A7794 - select PINCTRL_PFC_R8A77950 if ARCH_R8A77950 select PINCTRL_PFC_R8A77951 if ARCH_R8A77951 select PINCTRL_PFC_R8A77960 if ARCH_R8A77960 select PINCTRL_PFC_R8A77961 if ARCH_R8A77961 @@ -103,10 +102,6 @@ config PINCTRL_PFC_R8A7790 bool "pin control support for R-Car H2" if COMPILE_TEST select PINCTRL_SH_PFC -config PINCTRL_PFC_R8A77950 - bool "pin control support for R-Car H3 ES1.x" if COMPILE_TEST - select PINCTRL_SH_PFC - config PINCTRL_PFC_R8A77951 bool "pin control support for R-Car H3 ES2.0+" if COMPILE_TEST select PINCTRL_SH_PFC diff --git a/drivers/pinctrl/renesas/Makefile b/drivers/pinctrl/renesas/Makefile index 558b30ce0dec..3e776955bd4b 100644 --- a/drivers/pinctrl/renesas/Makefile +++ b/drivers/pinctrl/renesas/Makefile @@ -20,7 +20,6 @@ obj-$(CONFIG_PINCTRL_PFC_R8A7791) += pfc-r8a7791.o obj-$(CONFIG_PINCTRL_PFC_R8A7792) += pfc-r8a7792.o obj-$(CONFIG_PINCTRL_PFC_R8A7793) += pfc-r8a7791.o obj-$(CONFIG_PINCTRL_PFC_R8A7794) += pfc-r8a7794.o -obj-$(CONFIG_PINCTRL_PFC_R8A77950) += pfc-r8a77950.o obj-$(CONFIG_PINCTRL_PFC_R8A77951) += pfc-r8a77951.o obj-$(CONFIG_PINCTRL_PFC_R8A77960) += pfc-r8a7796.o obj-$(CONFIG_PINCTRL_PFC_R8A77961) += pfc-r8a7796.o diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index c91102d3f1d1..ed092ca314dd 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -573,23 +573,12 @@ static const struct of_device_id sh_pfc_of_table[] = { .data = &r8a7794_pinmux_info, }, #endif -/* - * Both r8a7795 entries must be present to make sanity checks work, but only - * the first entry is actually used. - * R-Car H3 ES1.x is matched using soc_device_match() instead. - */ #ifdef CONFIG_PINCTRL_PFC_R8A77951 { .compatible = "renesas,pfc-r8a7795", .data = &r8a77951_pinmux_info, }, #endif -#ifdef CONFIG_PINCTRL_PFC_R8A77950 - { - .compatible = "renesas,pfc-r8a7795", - .data = &r8a77950_pinmux_info, - }, -#endif #ifdef CONFIG_PINCTRL_PFC_R8A77960 { .compatible = "renesas,pfc-r8a7796", @@ -1309,28 +1298,6 @@ static void __init sh_pfc_check_driver(const struct platform_driver *pdrv) static inline void sh_pfc_check_driver(struct platform_driver *pdrv) {} #endif /* !DEBUG */ -#ifdef CONFIG_OF -static const void *sh_pfc_quirk_match(void) -{ -#ifdef CONFIG_PINCTRL_PFC_R8A77950 - const struct soc_device_attribute *match; - static const struct soc_device_attribute quirks[] = { - { - .soc_id = "r8a7795", .revision = "ES1.*", - .data = &r8a77950_pinmux_info, - }, - { /* sentinel */ } - }; - - match = soc_device_match(quirks); - if (match) - return match->data; -#endif /* CONFIG_PINCTRL_PFC_R8A77950 */ - - return NULL; -} -#endif /* CONFIG_OF */ - static int sh_pfc_probe(struct platform_device *pdev) { const struct sh_pfc_soc_info *info; @@ -1338,11 +1305,9 @@ static int sh_pfc_probe(struct platform_device *pdev) int ret; #ifdef CONFIG_OF - if (pdev->dev.of_node) { - info = sh_pfc_quirk_match(); - if (!info) - info = of_device_get_match_data(&pdev->dev); - } else + if (pdev->dev.of_node) + info = of_device_get_match_data(&pdev->dev); + else #endif info = (const void *)platform_get_device_id(pdev)->driver_data; diff --git a/drivers/pinctrl/renesas/pfc-r8a77950.c b/drivers/pinctrl/renesas/pfc-r8a77950.c deleted file mode 100644 index cc66c6de045c..000000000000 --- a/drivers/pinctrl/renesas/pfc-r8a77950.c +++ /dev/null @@ -1,5947 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * R8A77950 processor support - PFC hardware block. - * - * Copyright (C) 2015-2017 Renesas Electronics Corporation - */ - -#include -#include - -#include "sh_pfc.h" - -#define CFG_FLAGS (SH_PFC_PIN_CFG_DRIVE_STRENGTH | SH_PFC_PIN_CFG_PULL_UP_DOWN) - -#define CPU_ALL_GP(fn, sfx) \ - PORT_GP_CFG_16(0, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_15(2, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_26(5, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_32(6, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_4(7, fn, sfx, CFG_FLAGS) - -#define CPU_ALL_NOGP(fn) \ - PIN_NOGP_CFG(ASEBRK, "ASEBRK", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_MDIO, "AVB_MDIO", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RD0, "AVB_RD0", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RD1, "AVB_RD1", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RD2, "AVB_RD2", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RD3, "AVB_RD3", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RXC, "AVB_RXC", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_RX_CTL, "AVB_RX_CTL", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TD0, "AVB_TD0", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TD1, "AVB_TD1", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TD2, "AVB_TD2", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TD3, "AVB_TD3", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TXC, "AVB_TXC", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TXCREFCLK, "AVB_TXCREFCLK", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(AVB_TX_CTL, "AVB_TX_CTL", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(CLKOUT, "CLKOUT", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(DU_DOTCLKIN0, "DU_DOTCLKIN0", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(DU_DOTCLKIN1, "DU_DOTCLKIN1", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(DU_DOTCLKIN2, "DU_DOTCLKIN2", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(DU_DOTCLKIN3, "DU_DOTCLKIN3", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(EXTALR, "EXTALR", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN),\ - PIN_NOGP_CFG(FSCLKST_N, "FSCLKST#", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(MLB_REF, "MLB_REF", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(PRESETOUT_N, "PRESETOUT#", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_IO2, "QSPI0_IO2", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_IO3, "QSPI0_IO3", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_MISO_IO1, "QSPI0_MISO_IO1", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_MOSI_IO0, "QSPI0_MOSI_IO0", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_SPCLK, "QSPI0_SPCLK", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI0_SSL, "QSPI0_SSL", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_IO2, "QSPI1_IO2", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_IO3, "QSPI1_IO3", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_MISO_IO1, "QSPI1_MISO_IO1", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_MOSI_IO0, "QSPI1_MOSI_IO0", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_SPCLK, "QSPI1_SPCLK", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(QSPI1_SSL, "QSPI1_SSL", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(RPC_INT_N, "RPC_INT#", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(RPC_RESET_N, "RPC_RESET#", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(RPC_WP_N, "RPC_WP#", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(TCK, "TCK", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PIN_NOGP_CFG(TDI, "TDI", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PIN_NOGP_CFG(TDO, "TDO", fn, SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ - PIN_NOGP_CFG(TMS, "TMS", fn, CFG_FLAGS), \ - PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN) - -/* - * F_() : just information - * FM() : macro for FN_xxx / xxx_MARK - */ - -/* GPSR0 */ -#define GPSR0_15 F_(D15, IP7_11_8) -#define GPSR0_14 F_(D14, IP7_7_4) -#define GPSR0_13 F_(D13, IP7_3_0) -#define GPSR0_12 F_(D12, IP6_31_28) -#define GPSR0_11 F_(D11, IP6_27_24) -#define GPSR0_10 F_(D10, IP6_23_20) -#define GPSR0_9 F_(D9, IP6_19_16) -#define GPSR0_8 F_(D8, IP6_15_12) -#define GPSR0_7 F_(D7, IP6_11_8) -#define GPSR0_6 F_(D6, IP6_7_4) -#define GPSR0_5 F_(D5, IP6_3_0) -#define GPSR0_4 F_(D4, IP5_31_28) -#define GPSR0_3 F_(D3, IP5_27_24) -#define GPSR0_2 F_(D2, IP5_23_20) -#define GPSR0_1 F_(D1, IP5_19_16) -#define GPSR0_0 F_(D0, IP5_15_12) - -/* GPSR1 */ -#define GPSR1_27 F_(EX_WAIT0_A, IP5_11_8) -#define GPSR1_26 F_(WE1_N, IP5_7_4) -#define GPSR1_25 F_(WE0_N, IP5_3_0) -#define GPSR1_24 F_(RD_WR_N, IP4_31_28) -#define GPSR1_23 F_(RD_N, IP4_27_24) -#define GPSR1_22 F_(BS_N, IP4_23_20) -#define GPSR1_21 F_(CS1_N_A26, IP4_19_16) -#define GPSR1_20 F_(CS0_N, IP4_15_12) -#define GPSR1_19 F_(A19, IP4_11_8) -#define GPSR1_18 F_(A18, IP4_7_4) -#define GPSR1_17 F_(A17, IP4_3_0) -#define GPSR1_16 F_(A16, IP3_31_28) -#define GPSR1_15 F_(A15, IP3_27_24) -#define GPSR1_14 F_(A14, IP3_23_20) -#define GPSR1_13 F_(A13, IP3_19_16) -#define GPSR1_12 F_(A12, IP3_15_12) -#define GPSR1_11 F_(A11, IP3_11_8) -#define GPSR1_10 F_(A10, IP3_7_4) -#define GPSR1_9 F_(A9, IP3_3_0) -#define GPSR1_8 F_(A8, IP2_31_28) -#define GPSR1_7 F_(A7, IP2_27_24) -#define GPSR1_6 F_(A6, IP2_23_20) -#define GPSR1_5 F_(A5, IP2_19_16) -#define GPSR1_4 F_(A4, IP2_15_12) -#define GPSR1_3 F_(A3, IP2_11_8) -#define GPSR1_2 F_(A2, IP2_7_4) -#define GPSR1_1 F_(A1, IP2_3_0) -#define GPSR1_0 F_(A0, IP1_31_28) - -/* GPSR2 */ -#define GPSR2_14 F_(AVB_AVTP_CAPTURE_A, IP0_23_20) -#define GPSR2_13 F_(AVB_AVTP_MATCH_A, IP0_19_16) -#define GPSR2_12 F_(AVB_LINK, IP0_15_12) -#define GPSR2_11 F_(AVB_PHY_INT, IP0_11_8) -#define GPSR2_10 F_(AVB_MAGIC, IP0_7_4) -#define GPSR2_9 F_(AVB_MDC, IP0_3_0) -#define GPSR2_8 F_(PWM2_A, IP1_27_24) -#define GPSR2_7 F_(PWM1_A, IP1_23_20) -#define GPSR2_6 F_(PWM0, IP1_19_16) -#define GPSR2_5 F_(IRQ5, IP1_15_12) -#define GPSR2_4 F_(IRQ4, IP1_11_8) -#define GPSR2_3 F_(IRQ3, IP1_7_4) -#define GPSR2_2 F_(IRQ2, IP1_3_0) -#define GPSR2_1 F_(IRQ1, IP0_31_28) -#define GPSR2_0 F_(IRQ0, IP0_27_24) - -/* GPSR3 */ -#define GPSR3_15 F_(SD1_WP, IP10_23_20) -#define GPSR3_14 F_(SD1_CD, IP10_19_16) -#define GPSR3_13 F_(SD0_WP, IP10_15_12) -#define GPSR3_12 F_(SD0_CD, IP10_11_8) -#define GPSR3_11 F_(SD1_DAT3, IP8_31_28) -#define GPSR3_10 F_(SD1_DAT2, IP8_27_24) -#define GPSR3_9 F_(SD1_DAT1, IP8_23_20) -#define GPSR3_8 F_(SD1_DAT0, IP8_19_16) -#define GPSR3_7 F_(SD1_CMD, IP8_15_12) -#define GPSR3_6 F_(SD1_CLK, IP8_11_8) -#define GPSR3_5 F_(SD0_DAT3, IP8_7_4) -#define GPSR3_4 F_(SD0_DAT2, IP8_3_0) -#define GPSR3_3 F_(SD0_DAT1, IP7_31_28) -#define GPSR3_2 F_(SD0_DAT0, IP7_27_24) -#define GPSR3_1 F_(SD0_CMD, IP7_23_20) -#define GPSR3_0 F_(SD0_CLK, IP7_19_16) - -/* GPSR4 */ -#define GPSR4_17 FM(SD3_DS) -#define GPSR4_16 F_(SD3_DAT7, IP10_7_4) -#define GPSR4_15 F_(SD3_DAT6, IP10_3_0) -#define GPSR4_14 F_(SD3_DAT5, IP9_31_28) -#define GPSR4_13 F_(SD3_DAT4, IP9_27_24) -#define GPSR4_12 FM(SD3_DAT3) -#define GPSR4_11 FM(SD3_DAT2) -#define GPSR4_10 FM(SD3_DAT1) -#define GPSR4_9 FM(SD3_DAT0) -#define GPSR4_8 FM(SD3_CMD) -#define GPSR4_7 FM(SD3_CLK) -#define GPSR4_6 F_(SD2_DS, IP9_23_20) -#define GPSR4_5 F_(SD2_DAT3, IP9_19_16) -#define GPSR4_4 F_(SD2_DAT2, IP9_15_12) -#define GPSR4_3 F_(SD2_DAT1, IP9_11_8) -#define GPSR4_2 F_(SD2_DAT0, IP9_7_4) -#define GPSR4_1 FM(SD2_CMD) -#define GPSR4_0 F_(SD2_CLK, IP9_3_0) - -/* GPSR5 */ -#define GPSR5_25 F_(MLB_DAT, IP13_19_16) -#define GPSR5_24 F_(MLB_SIG, IP13_15_12) -#define GPSR5_23 F_(MLB_CLK, IP13_11_8) -#define GPSR5_22 FM(MSIOF0_RXD) -#define GPSR5_21 F_(MSIOF0_SS2, IP13_7_4) -#define GPSR5_20 FM(MSIOF0_TXD) -#define GPSR5_19 F_(MSIOF0_SS1, IP13_3_0) -#define GPSR5_18 F_(MSIOF0_SYNC, IP12_31_28) -#define GPSR5_17 FM(MSIOF0_SCK) -#define GPSR5_16 F_(HRTS0_N, IP12_27_24) -#define GPSR5_15 F_(HCTS0_N, IP12_23_20) -#define GPSR5_14 F_(HTX0, IP12_19_16) -#define GPSR5_13 F_(HRX0, IP12_15_12) -#define GPSR5_12 F_(HSCK0, IP12_11_8) -#define GPSR5_11 F_(RX2_A, IP12_7_4) -#define GPSR5_10 F_(TX2_A, IP12_3_0) -#define GPSR5_9 F_(SCK2, IP11_31_28) -#define GPSR5_8 F_(RTS1_N, IP11_27_24) -#define GPSR5_7 F_(CTS1_N, IP11_23_20) -#define GPSR5_6 F_(TX1_A, IP11_19_16) -#define GPSR5_5 F_(RX1_A, IP11_15_12) -#define GPSR5_4 F_(RTS0_N, IP11_11_8) -#define GPSR5_3 F_(CTS0_N, IP11_7_4) -#define GPSR5_2 F_(TX0, IP11_3_0) -#define GPSR5_1 F_(RX0, IP10_31_28) -#define GPSR5_0 F_(SCK0, IP10_27_24) - -/* GPSR6 */ -#define GPSR6_31 F_(USB31_OVC, IP17_7_4) -#define GPSR6_30 F_(USB31_PWEN, IP17_3_0) -#define GPSR6_29 F_(USB30_OVC, IP16_31_28) -#define GPSR6_28 F_(USB30_PWEN, IP16_27_24) -#define GPSR6_27 F_(USB1_OVC, IP16_23_20) -#define GPSR6_26 F_(USB1_PWEN, IP16_19_16) -#define GPSR6_25 F_(USB0_OVC, IP16_15_12) -#define GPSR6_24 F_(USB0_PWEN, IP16_11_8) -#define GPSR6_23 F_(AUDIO_CLKB_B, IP16_7_4) -#define GPSR6_22 F_(AUDIO_CLKA_A, IP16_3_0) -#define GPSR6_21 F_(SSI_SDATA9_A, IP15_31_28) -#define GPSR6_20 F_(SSI_SDATA8, IP15_27_24) -#define GPSR6_19 F_(SSI_SDATA7, IP15_23_20) -#define GPSR6_18 F_(SSI_WS78, IP15_19_16) -#define GPSR6_17 F_(SSI_SCK78, IP15_15_12) -#define GPSR6_16 F_(SSI_SDATA6, IP15_11_8) -#define GPSR6_15 F_(SSI_WS6, IP15_7_4) -#define GPSR6_14 F_(SSI_SCK6, IP15_3_0) -#define GPSR6_13 FM(SSI_SDATA5) -#define GPSR6_12 FM(SSI_WS5) -#define GPSR6_11 FM(SSI_SCK5) -#define GPSR6_10 F_(SSI_SDATA4, IP14_31_28) -#define GPSR6_9 F_(SSI_WS4, IP14_27_24) -#define GPSR6_8 F_(SSI_SCK4, IP14_23_20) -#define GPSR6_7 F_(SSI_SDATA3, IP14_19_16) -#define GPSR6_6 F_(SSI_WS349, IP14_15_12) -#define GPSR6_5 F_(SSI_SCK349, IP14_11_8) -#define GPSR6_4 F_(SSI_SDATA2_A, IP14_7_4) -#define GPSR6_3 F_(SSI_SDATA1_A, IP14_3_0) -#define GPSR6_2 F_(SSI_SDATA0, IP13_31_28) -#define GPSR6_1 F_(SSI_WS01239, IP13_27_24) -#define GPSR6_0 F_(SSI_SCK01239, IP13_23_20) - -/* GPSR7 */ -#define GPSR7_3 FM(GP7_03) -#define GPSR7_2 FM(GP7_02) -#define GPSR7_1 FM(AVS2) -#define GPSR7_0 FM(AVS1) - - -/* IPSRx */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ /* 8 */ /* 9 */ /* A */ /* B */ /* C - F */ -#define IP0_3_0 FM(AVB_MDC) F_(0, 0) FM(MSIOF2_SS2_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_7_4 FM(AVB_MAGIC) F_(0, 0) FM(MSIOF2_SS1_C) FM(SCK4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_11_8 FM(AVB_PHY_INT) F_(0, 0) FM(MSIOF2_SYNC_C) FM(RX4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_15_12 FM(AVB_LINK) F_(0, 0) FM(MSIOF2_SCK_C) FM(TX4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_19_16 FM(AVB_AVTP_MATCH_A) F_(0, 0) FM(MSIOF2_RXD_C) FM(CTS4_N_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_23_20 FM(AVB_AVTP_CAPTURE_A) F_(0, 0) FM(MSIOF2_TXD_C) FM(RTS4_N_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_27_24 FM(IRQ0) FM(QPOLB) F_(0, 0) FM(DU_CDE) FM(VI4_DATA0_B) FM(CAN0_TX_B) FM(CANFD0_TX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP0_31_28 FM(IRQ1) FM(QPOLA) F_(0, 0) FM(DU_DISP) FM(VI4_DATA1_B) FM(CAN0_RX_B) FM(CANFD0_RX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_3_0 FM(IRQ2) FM(QCPV_QDE) F_(0, 0) FM(DU_EXODDF_DU_ODDF_DISP_CDE) FM(VI4_DATA2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(PWM3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_7_4 FM(IRQ3) FM(QSTVB_QVE) FM(A25) FM(DU_DOTCLKOUT1) FM(VI4_DATA3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(PWM4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_11_8 FM(IRQ4) FM(QSTH_QHS) FM(A24) FM(DU_EXHSYNC_DU_HSYNC) FM(VI4_DATA4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(PWM5_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_15_12 FM(IRQ5) FM(QSTB_QHE) FM(A23) FM(DU_EXVSYNC_DU_VSYNC) FM(VI4_DATA5_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(PWM6_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_19_16 FM(PWM0) FM(AVB_AVTP_PPS)FM(A22) F_(0, 0) FM(VI4_DATA6_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(IECLK_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_23_20 FM(PWM1_A) F_(0, 0) FM(A21) FM(HRX3_D) FM(VI4_DATA7_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(IERX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_27_24 FM(PWM2_A) F_(0, 0) FM(A20) FM(HTX3_D) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(IETX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP1_31_28 FM(A0) FM(LCDOUT16) FM(MSIOF3_SYNC_B) F_(0, 0) FM(VI4_DATA8) F_(0, 0) FM(DU_DB0) F_(0, 0) F_(0, 0) FM(PWM3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_3_0 FM(A1) FM(LCDOUT17) FM(MSIOF3_TXD_B) F_(0, 0) FM(VI4_DATA9) F_(0, 0) FM(DU_DB1) F_(0, 0) F_(0, 0) FM(PWM4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_7_4 FM(A2) FM(LCDOUT18) FM(MSIOF3_SCK_B) F_(0, 0) FM(VI4_DATA10) F_(0, 0) FM(DU_DB2) F_(0, 0) F_(0, 0) FM(PWM5_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_11_8 FM(A3) FM(LCDOUT19) FM(MSIOF3_RXD_B) F_(0, 0) FM(VI4_DATA11) F_(0, 0) FM(DU_DB3) F_(0, 0) F_(0, 0) FM(PWM6_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IPSRx */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ /* 8 */ /* 9 */ /* A */ /* B */ /* C - F */ -#define IP2_15_12 FM(A4) FM(LCDOUT20) FM(MSIOF3_SS1_B) F_(0, 0) FM(VI4_DATA12) FM(VI5_DATA12) FM(DU_DB4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_19_16 FM(A5) FM(LCDOUT21) FM(MSIOF3_SS2_B) FM(SCK4_B) FM(VI4_DATA13) FM(VI5_DATA13) FM(DU_DB5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_23_20 FM(A6) FM(LCDOUT22) FM(MSIOF2_SS1_A) FM(RX4_B) FM(VI4_DATA14) FM(VI5_DATA14) FM(DU_DB6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_27_24 FM(A7) FM(LCDOUT23) FM(MSIOF2_SS2_A) FM(TX4_B) FM(VI4_DATA15) FM(VI5_DATA15) FM(DU_DB7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP2_31_28 FM(A8) FM(RX3_B) FM(MSIOF2_SYNC_A) FM(HRX4_B) F_(0, 0) F_(0, 0) F_(0, 0) FM(SDA6_A) FM(AVB_AVTP_MATCH_B) FM(PWM1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_3_0 FM(A9) F_(0, 0) FM(MSIOF2_SCK_A) FM(CTS4_N_B) F_(0, 0) FM(VI5_VSYNC_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_7_4 FM(A10) F_(0, 0) FM(MSIOF2_RXD_A) FM(RTS4_N_B) F_(0, 0) FM(VI5_HSYNC_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_11_8 FM(A11) FM(TX3_B) FM(MSIOF2_TXD_A) FM(HTX4_B) FM(HSCK4) FM(VI5_FIELD) F_(0, 0) FM(SCL6_A) FM(AVB_AVTP_CAPTURE_B) FM(PWM2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_15_12 FM(A12) FM(LCDOUT12) FM(MSIOF3_SCK_C) F_(0, 0) FM(HRX4_A) FM(VI5_DATA8) FM(DU_DG4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_19_16 FM(A13) FM(LCDOUT13) FM(MSIOF3_SYNC_C) F_(0, 0) FM(HTX4_A) FM(VI5_DATA9) FM(DU_DG5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_23_20 FM(A14) FM(LCDOUT14) FM(MSIOF3_RXD_C) F_(0, 0) FM(HCTS4_N) FM(VI5_DATA10) FM(DU_DG6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_27_24 FM(A15) FM(LCDOUT15) FM(MSIOF3_TXD_C) F_(0, 0) FM(HRTS4_N) FM(VI5_DATA11) FM(DU_DG7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP3_31_28 FM(A16) FM(LCDOUT8) F_(0, 0) F_(0, 0) FM(VI4_FIELD) F_(0, 0) FM(DU_DG0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_3_0 FM(A17) FM(LCDOUT9) F_(0, 0) F_(0, 0) FM(VI4_VSYNC_N) F_(0, 0) FM(DU_DG1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_7_4 FM(A18) FM(LCDOUT10) F_(0, 0) F_(0, 0) FM(VI4_HSYNC_N) F_(0, 0) FM(DU_DG2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_11_8 FM(A19) FM(LCDOUT11) F_(0, 0) F_(0, 0) FM(VI4_CLKENB) F_(0, 0) FM(DU_DG3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_15_12 FM(CS0_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(VI5_CLKENB) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_19_16 FM(CS1_N_A26) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(VI5_CLK) F_(0, 0) FM(EX_WAIT0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_23_20 FM(BS_N) FM(QSTVA_QVS) FM(MSIOF3_SCK_D) FM(SCK3) FM(HSCK3) F_(0, 0) F_(0, 0) F_(0, 0) FM(CAN1_TX) FM(CANFD1_TX) FM(IETX_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_27_24 FM(RD_N) F_(0, 0) FM(MSIOF3_SYNC_D) FM(RX3_A) FM(HRX3_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(CAN0_TX_A) FM(CANFD0_TX_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP4_31_28 FM(RD_WR_N) F_(0, 0) FM(MSIOF3_RXD_D) FM(TX3_A) FM(HTX3_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(CAN0_RX_A) FM(CANFD0_RX_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_3_0 FM(WE0_N) F_(0, 0) FM(MSIOF3_TXD_D) FM(CTS3_N) FM(HCTS3_N) F_(0, 0) F_(0, 0) FM(SCL6_B) FM(CAN_CLK) F_(0, 0) FM(IECLK_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_7_4 FM(WE1_N) F_(0, 0) FM(MSIOF3_SS1_D) FM(RTS3_N) FM(HRTS3_N) F_(0, 0) F_(0, 0) FM(SDA6_B) FM(CAN1_RX) FM(CANFD1_RX) FM(IERX_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_11_8 FM(EX_WAIT0_A) FM(QCLK) F_(0, 0) F_(0, 0) FM(VI4_CLK) F_(0, 0) FM(DU_DOTCLKOUT0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_15_12 FM(D0) FM(MSIOF2_SS1_B)FM(MSIOF3_SCK_A) F_(0, 0) FM(VI4_DATA16) FM(VI5_DATA0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_19_16 FM(D1) FM(MSIOF2_SS2_B)FM(MSIOF3_SYNC_A) F_(0, 0) FM(VI4_DATA17) FM(VI5_DATA1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_23_20 FM(D2) F_(0, 0) FM(MSIOF3_RXD_A) F_(0, 0) FM(VI4_DATA18) FM(VI5_DATA2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_27_24 FM(D3) F_(0, 0) FM(MSIOF3_TXD_A) F_(0, 0) FM(VI4_DATA19) FM(VI5_DATA3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP5_31_28 FM(D4) FM(MSIOF2_SCK_B)F_(0, 0) F_(0, 0) FM(VI4_DATA20) FM(VI5_DATA4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_3_0 FM(D5) FM(MSIOF2_SYNC_B)F_(0, 0) F_(0, 0) FM(VI4_DATA21) FM(VI5_DATA5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_7_4 FM(D6) FM(MSIOF2_RXD_B)F_(0, 0) F_(0, 0) FM(VI4_DATA22) FM(VI5_DATA6) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_11_8 FM(D7) FM(MSIOF2_TXD_B)F_(0, 0) F_(0, 0) FM(VI4_DATA23) FM(VI5_DATA7) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_15_12 FM(D8) FM(LCDOUT0) FM(MSIOF2_SCK_D) FM(SCK4_C) FM(VI4_DATA0_A) F_(0, 0) FM(DU_DR0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_19_16 FM(D9) FM(LCDOUT1) FM(MSIOF2_SYNC_D) F_(0, 0) FM(VI4_DATA1_A) F_(0, 0) FM(DU_DR1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_23_20 FM(D10) FM(LCDOUT2) FM(MSIOF2_RXD_D) FM(HRX3_B) FM(VI4_DATA2_A) FM(CTS4_N_C) FM(DU_DR2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_27_24 FM(D11) FM(LCDOUT3) FM(MSIOF2_TXD_D) FM(HTX3_B) FM(VI4_DATA3_A) FM(RTS4_N_C) FM(DU_DR3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP6_31_28 FM(D12) FM(LCDOUT4) FM(MSIOF2_SS1_D) FM(RX4_C) FM(VI4_DATA4_A) F_(0, 0) FM(DU_DR4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_3_0 FM(D13) FM(LCDOUT5) FM(MSIOF2_SS2_D) FM(TX4_C) FM(VI4_DATA5_A) F_(0, 0) FM(DU_DR5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_7_4 FM(D14) FM(LCDOUT6) FM(MSIOF3_SS1_A) FM(HRX3_C) FM(VI4_DATA6_A) F_(0, 0) FM(DU_DR6) FM(SCL6_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_11_8 FM(D15) FM(LCDOUT7) FM(MSIOF3_SS2_A) FM(HTX3_C) FM(VI4_DATA7_A) F_(0, 0) FM(DU_DR7) FM(SDA6_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_15_12 FM(FSCLKST) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_19_16 FM(SD0_CLK) F_(0, 0) FM(MSIOF1_SCK_E) F_(0, 0) F_(0, 0) F_(0, 0) FM(STP_OPWM_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IPSRx */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ /* 8 */ /* 9 */ /* A */ /* B */ /* C - F */ -#define IP7_23_20 FM(SD0_CMD) F_(0, 0) FM(MSIOF1_SYNC_E) F_(0, 0) F_(0, 0) F_(0, 0) FM(STP_IVCXO27_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_27_24 FM(SD0_DAT0) F_(0, 0) FM(MSIOF1_RXD_E) F_(0, 0) F_(0, 0) FM(TS_SCK0_B) FM(STP_ISCLK_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP7_31_28 FM(SD0_DAT1) F_(0, 0) FM(MSIOF1_TXD_E) F_(0, 0) F_(0, 0) FM(TS_SPSYNC0_B)FM(STP_ISSYNC_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_3_0 FM(SD0_DAT2) F_(0, 0) FM(MSIOF1_SS1_E) F_(0, 0) F_(0, 0) FM(TS_SDAT0_B) FM(STP_ISD_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_7_4 FM(SD0_DAT3) F_(0, 0) FM(MSIOF1_SS2_E) F_(0, 0) F_(0, 0) FM(TS_SDEN0_B) FM(STP_ISEN_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_11_8 FM(SD1_CLK) F_(0, 0) FM(MSIOF1_SCK_G) F_(0, 0) F_(0, 0) FM(SIM0_CLK_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_15_12 FM(SD1_CMD) F_(0, 0) FM(MSIOF1_SYNC_G) F_(0, 0) F_(0, 0) FM(SIM0_D_A) FM(STP_IVCXO27_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_19_16 FM(SD1_DAT0) FM(SD2_DAT4) FM(MSIOF1_RXD_G) F_(0, 0) F_(0, 0) FM(TS_SCK1_B) FM(STP_ISCLK_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_23_20 FM(SD1_DAT1) FM(SD2_DAT5) FM(MSIOF1_TXD_G) F_(0, 0) F_(0, 0) FM(TS_SPSYNC1_B)FM(STP_ISSYNC_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_27_24 FM(SD1_DAT2) FM(SD2_DAT6) FM(MSIOF1_SS1_G) F_(0, 0) F_(0, 0) FM(TS_SDAT1_B) FM(STP_ISD_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP8_31_28 FM(SD1_DAT3) FM(SD2_DAT7) FM(MSIOF1_SS2_G) F_(0, 0) F_(0, 0) FM(TS_SDEN1_B) FM(STP_ISEN_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_3_0 FM(SD2_CLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_7_4 FM(SD2_DAT0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_11_8 FM(SD2_DAT1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_15_12 FM(SD2_DAT2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_19_16 FM(SD2_DAT3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_23_20 FM(SD2_DS) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(SATA_DEVSLP_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_27_24 FM(SD3_DAT4) FM(SD2_CD_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP9_31_28 FM(SD3_DAT5) FM(SD2_WP_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_3_0 FM(SD3_DAT6) FM(SD3_CD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_7_4 FM(SD3_DAT7) FM(SD3_WP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_11_8 FM(SD0_CD) F_(0, 0) F_(0, 0) F_(0, 0) FM(SCL2_B) FM(SIM0_RST_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_15_12 FM(SD0_WP) F_(0, 0) F_(0, 0) F_(0, 0) FM(SDA2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_19_16 FM(SD1_CD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(SIM0_CLK_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_23_20 FM(SD1_WP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(SIM0_D_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_27_24 FM(SCK0) FM(HSCK1_B) FM(MSIOF1_SS2_B) FM(AUDIO_CLKC_B) FM(SDA2_A) FM(SIM0_RST_B) FM(STP_OPWM_0_C) FM(RIF0_CLK_B) F_(0, 0) FM(ADICHS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP10_31_28 FM(RX0) FM(HRX1_B) F_(0, 0) F_(0, 0) F_(0, 0) FM(TS_SCK0_C) FM(STP_ISCLK_0_C) FM(RIF0_D0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_3_0 FM(TX0) FM(HTX1_B) F_(0, 0) F_(0, 0) F_(0, 0) FM(TS_SPSYNC0_C)FM(STP_ISSYNC_0_C) FM(RIF0_D1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_7_4 FM(CTS0_N) FM(HCTS1_N_B) FM(MSIOF1_SYNC_B) F_(0, 0) F_(0, 0) FM(TS_SPSYNC1_C)FM(STP_ISSYNC_1_C) FM(RIF1_SYNC_B) FM(AUDIO_CLKOUT_C) FM(ADICS_SAMP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_11_8 FM(RTS0_N) FM(HRTS1_N_B) FM(MSIOF1_SS1_B) FM(AUDIO_CLKA_B) FM(SCL2_A) F_(0, 0) FM(STP_IVCXO27_1_C) FM(RIF0_SYNC_B) F_(0, 0) FM(ADICHS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_15_12 FM(RX1_A) FM(HRX1_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(TS_SDAT0_C) FM(STP_ISD_0_C) FM(RIF1_CLK_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_19_16 FM(TX1_A) FM(HTX1_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(TS_SDEN0_C) FM(STP_ISEN_0_C) FM(RIF1_D0_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_23_20 FM(CTS1_N) FM(HCTS1_N_A) FM(MSIOF1_RXD_B) F_(0, 0) F_(0, 0) FM(TS_SDEN1_C) FM(STP_ISEN_1_C) FM(RIF1_D0_B) F_(0, 0) FM(ADIDATA) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_27_24 FM(RTS1_N) FM(HRTS1_N_A) FM(MSIOF1_TXD_B) F_(0, 0) F_(0, 0) FM(TS_SDAT1_C) FM(STP_ISD_1_C) FM(RIF1_D1_B) F_(0, 0) FM(ADICHS0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP11_31_28 FM(SCK2) FM(SCIF_CLK_B) FM(MSIOF1_SCK_B) F_(0, 0) F_(0, 0) FM(TS_SCK1_C) FM(STP_ISCLK_1_C) FM(RIF1_CLK_B) F_(0, 0) FM(ADICLK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_3_0 FM(TX2_A) F_(0, 0) F_(0, 0) FM(SD2_CD_B) FM(SCL1_A) F_(0, 0) FM(FMCLK_A) FM(RIF1_D1_C) F_(0, 0) FM(FSO_CFE_0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_7_4 FM(RX2_A) F_(0, 0) F_(0, 0) FM(SD2_WP_B) FM(SDA1_A) F_(0, 0) FM(FMIN_A) FM(RIF1_SYNC_C) F_(0, 0) FM(FSO_CFE_1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_11_8 FM(HSCK0) F_(0, 0) FM(MSIOF1_SCK_D) FM(AUDIO_CLKB_A) FM(SSI_SDATA1_B)FM(TS_SCK0_D) FM(STP_ISCLK_0_D) FM(RIF0_CLK_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_15_12 FM(HRX0) F_(0, 0) FM(MSIOF1_RXD_D) F_(0, 0) FM(SSI_SDATA2_B)FM(TS_SDEN0_D) FM(STP_ISEN_0_D) FM(RIF0_D0_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_19_16 FM(HTX0) F_(0, 0) FM(MSIOF1_TXD_D) F_(0, 0) FM(SSI_SDATA9_B)FM(TS_SDAT0_D) FM(STP_ISD_0_D) FM(RIF0_D1_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_23_20 FM(HCTS0_N) FM(RX2_B) FM(MSIOF1_SYNC_D) F_(0, 0) FM(SSI_SCK9_A) FM(TS_SPSYNC0_D)FM(STP_ISSYNC_0_D) FM(RIF0_SYNC_C) FM(AUDIO_CLKOUT1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP12_27_24 FM(HRTS0_N) FM(TX2_B) FM(MSIOF1_SS1_D) F_(0, 0) FM(SSI_WS9_A) F_(0, 0) FM(STP_IVCXO27_0_D) FM(BPFCLK_A) FM(AUDIO_CLKOUT2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -/* IPSRx */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ /* 8 */ /* 9 */ /* A */ /* B */ /* C - F */ -#define IP12_31_28 FM(MSIOF0_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(AUDIO_CLKOUT_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_3_0 FM(MSIOF0_SS1) FM(RX5) F_(0, 0) FM(AUDIO_CLKA_C) FM(SSI_SCK2_A) F_(0, 0) FM(STP_IVCXO27_0_C) F_(0, 0) FM(AUDIO_CLKOUT3_A) F_(0, 0) FM(TCLK1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_7_4 FM(MSIOF0_SS2) FM(TX5) FM(MSIOF1_SS2_D) FM(AUDIO_CLKC_A) FM(SSI_WS2_A) F_(0, 0) FM(STP_OPWM_0_D) F_(0, 0) FM(AUDIO_CLKOUT_D) F_(0, 0) FM(SPEEDIN_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_11_8 FM(MLB_CLK) F_(0, 0) FM(MSIOF1_SCK_F) F_(0, 0) FM(SCL1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_15_12 FM(MLB_SIG) FM(RX1_B) FM(MSIOF1_SYNC_F) F_(0, 0) FM(SDA1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_19_16 FM(MLB_DAT) FM(TX1_B) FM(MSIOF1_RXD_F) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_23_20 FM(SSI_SCK01239) F_(0, 0) FM(MSIOF1_TXD_F) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_27_24 FM(SSI_WS01239) F_(0, 0) FM(MSIOF1_SS1_F) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP13_31_28 FM(SSI_SDATA0) F_(0, 0) FM(MSIOF1_SS2_F) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_3_0 FM(SSI_SDATA1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_7_4 FM(SSI_SDATA2_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(SSI_SCK1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_11_8 FM(SSI_SCK349) F_(0, 0) FM(MSIOF1_SS1_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(STP_OPWM_0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_15_12 FM(SSI_WS349) FM(HCTS2_N_A) FM(MSIOF1_SS2_A) F_(0, 0) F_(0, 0) F_(0, 0) FM(STP_IVCXO27_0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_19_16 FM(SSI_SDATA3) FM(HRTS2_N_A) FM(MSIOF1_TXD_A) F_(0, 0) F_(0, 0) FM(TS_SCK0_A) FM(STP_ISCLK_0_A) FM(RIF0_D1_A) FM(RIF2_D0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_23_20 FM(SSI_SCK4) FM(HRX2_A) FM(MSIOF1_SCK_A) F_(0, 0) F_(0, 0) FM(TS_SDAT0_A) FM(STP_ISD_0_A) FM(RIF0_CLK_A) FM(RIF2_CLK_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_27_24 FM(SSI_WS4) FM(HTX2_A) FM(MSIOF1_SYNC_A) F_(0, 0) F_(0, 0) FM(TS_SDEN0_A) FM(STP_ISEN_0_A) FM(RIF0_SYNC_A) FM(RIF2_SYNC_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP14_31_28 FM(SSI_SDATA4) FM(HSCK2_A) FM(MSIOF1_RXD_A) F_(0, 0) F_(0, 0) FM(TS_SPSYNC0_A)FM(STP_ISSYNC_0_A) FM(RIF0_D0_A) FM(RIF2_D1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_3_0 FM(SSI_SCK6) FM(USB2_PWEN) F_(0, 0) FM(SIM0_RST_D) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_7_4 FM(SSI_WS6) FM(USB2_OVC) F_(0, 0) FM(SIM0_D_D) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_11_8 FM(SSI_SDATA6) F_(0, 0) F_(0, 0) FM(SIM0_CLK_D) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(SATA_DEVSLP_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_15_12 FM(SSI_SCK78) FM(HRX2_B) FM(MSIOF1_SCK_C) F_(0, 0) F_(0, 0) FM(TS_SCK1_A) FM(STP_ISCLK_1_A) FM(RIF1_CLK_A) FM(RIF3_CLK_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_19_16 FM(SSI_WS78) FM(HTX2_B) FM(MSIOF1_SYNC_C) F_(0, 0) F_(0, 0) FM(TS_SDAT1_A) FM(STP_ISD_1_A) FM(RIF1_SYNC_A) FM(RIF3_SYNC_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_23_20 FM(SSI_SDATA7) FM(HCTS2_N_B) FM(MSIOF1_RXD_C) F_(0, 0) F_(0, 0) FM(TS_SDEN1_A) FM(STP_ISEN_1_A) FM(RIF1_D0_A) FM(RIF3_D0_A) F_(0, 0) FM(TCLK2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_27_24 FM(SSI_SDATA8) FM(HRTS2_N_B) FM(MSIOF1_TXD_C) F_(0, 0) F_(0, 0) FM(TS_SPSYNC1_A)FM(STP_ISSYNC_1_A) FM(RIF1_D1_A) FM(RIF3_D1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP15_31_28 FM(SSI_SDATA9_A) FM(HSCK2_B) FM(MSIOF1_SS1_C) FM(HSCK1_A) FM(SSI_WS1_B) FM(SCK1) FM(STP_IVCXO27_1_A) FM(SCK5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_3_0 FM(AUDIO_CLKA_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_7_4 FM(AUDIO_CLKB_B) FM(SCIF_CLK_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) FM(STP_IVCXO27_1_D) FM(REMOCON_A) F_(0, 0) F_(0, 0) FM(TCLK1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_11_8 FM(USB0_PWEN) F_(0, 0) F_(0, 0) FM(SIM0_RST_C) F_(0, 0) FM(TS_SCK1_D) FM(STP_ISCLK_1_D) FM(BPFCLK_B) FM(RIF3_CLK_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_15_12 FM(USB0_OVC) F_(0, 0) F_(0, 0) FM(SIM0_D_C) F_(0, 0) FM(TS_SDAT1_D) FM(STP_ISD_1_D) F_(0, 0) FM(RIF3_SYNC_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_19_16 FM(USB1_PWEN) F_(0, 0) F_(0, 0) FM(SIM0_CLK_C) FM(SSI_SCK1_A) FM(TS_SCK0_E) FM(STP_ISCLK_0_E) FM(FMCLK_B) FM(RIF2_CLK_B) F_(0, 0) FM(SPEEDIN_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_23_20 FM(USB1_OVC) F_(0, 0) FM(MSIOF1_SS2_C) F_(0, 0) FM(SSI_WS1_A) FM(TS_SDAT0_E) FM(STP_ISD_0_E) FM(FMIN_B) FM(RIF2_SYNC_B) F_(0, 0) FM(REMOCON_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_27_24 FM(USB30_PWEN) F_(0, 0) F_(0, 0) FM(AUDIO_CLKOUT_B) FM(SSI_SCK2_B) FM(TS_SDEN1_D) FM(STP_ISEN_1_D) FM(STP_OPWM_0_E)FM(RIF3_D0_B) F_(0, 0) FM(TCLK2_B) FM(TPU0TO0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP16_31_28 FM(USB30_OVC) F_(0, 0) F_(0, 0) FM(AUDIO_CLKOUT1_B) FM(SSI_WS2_B) FM(TS_SPSYNC1_D)FM(STP_ISSYNC_1_D) FM(STP_IVCXO27_0_E)FM(RIF3_D1_B) F_(0, 0) FM(FSO_TOE_B) FM(TPU0TO1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP17_3_0 FM(USB31_PWEN) F_(0, 0) F_(0, 0) FM(AUDIO_CLKOUT2_B) FM(SSI_SCK9_B) FM(TS_SDEN0_E) FM(STP_ISEN_0_E) F_(0, 0) FM(RIF2_D0_B) F_(0, 0) F_(0, 0) FM(TPU0TO2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) -#define IP17_7_4 FM(USB31_OVC) F_(0, 0) F_(0, 0) FM(AUDIO_CLKOUT3_B) FM(SSI_WS9_B) FM(TS_SPSYNC0_E)FM(STP_ISSYNC_0_E) F_(0, 0) FM(RIF2_D1_B) F_(0, 0) F_(0, 0) FM(TPU0TO3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) - -#define PINMUX_GPSR \ -\ - GPSR6_31 \ - GPSR6_30 \ - GPSR6_29 \ - GPSR6_28 \ - GPSR1_27 GPSR6_27 \ - GPSR1_26 GPSR6_26 \ - GPSR1_25 GPSR5_25 GPSR6_25 \ - GPSR1_24 GPSR5_24 GPSR6_24 \ - GPSR1_23 GPSR5_23 GPSR6_23 \ - GPSR1_22 GPSR5_22 GPSR6_22 \ - GPSR1_21 GPSR5_21 GPSR6_21 \ - GPSR1_20 GPSR5_20 GPSR6_20 \ - GPSR1_19 GPSR5_19 GPSR6_19 \ - GPSR1_18 GPSR5_18 GPSR6_18 \ - GPSR1_17 GPSR4_17 GPSR5_17 GPSR6_17 \ - GPSR1_16 GPSR4_16 GPSR5_16 GPSR6_16 \ -GPSR0_15 GPSR1_15 GPSR3_15 GPSR4_15 GPSR5_15 GPSR6_15 \ -GPSR0_14 GPSR1_14 GPSR2_14 GPSR3_14 GPSR4_14 GPSR5_14 GPSR6_14 \ -GPSR0_13 GPSR1_13 GPSR2_13 GPSR3_13 GPSR4_13 GPSR5_13 GPSR6_13 \ -GPSR0_12 GPSR1_12 GPSR2_12 GPSR3_12 GPSR4_12 GPSR5_12 GPSR6_12 \ -GPSR0_11 GPSR1_11 GPSR2_11 GPSR3_11 GPSR4_11 GPSR5_11 GPSR6_11 \ -GPSR0_10 GPSR1_10 GPSR2_10 GPSR3_10 GPSR4_10 GPSR5_10 GPSR6_10 \ -GPSR0_9 GPSR1_9 GPSR2_9 GPSR3_9 GPSR4_9 GPSR5_9 GPSR6_9 \ -GPSR0_8 GPSR1_8 GPSR2_8 GPSR3_8 GPSR4_8 GPSR5_8 GPSR6_8 \ -GPSR0_7 GPSR1_7 GPSR2_7 GPSR3_7 GPSR4_7 GPSR5_7 GPSR6_7 \ -GPSR0_6 GPSR1_6 GPSR2_6 GPSR3_6 GPSR4_6 GPSR5_6 GPSR6_6 \ -GPSR0_5 GPSR1_5 GPSR2_5 GPSR3_5 GPSR4_5 GPSR5_5 GPSR6_5 \ -GPSR0_4 GPSR1_4 GPSR2_4 GPSR3_4 GPSR4_4 GPSR5_4 GPSR6_4 \ -GPSR0_3 GPSR1_3 GPSR2_3 GPSR3_3 GPSR4_3 GPSR5_3 GPSR6_3 GPSR7_3 \ -GPSR0_2 GPSR1_2 GPSR2_2 GPSR3_2 GPSR4_2 GPSR5_2 GPSR6_2 GPSR7_2 \ -GPSR0_1 GPSR1_1 GPSR2_1 GPSR3_1 GPSR4_1 GPSR5_1 GPSR6_1 GPSR7_1 \ -GPSR0_0 GPSR1_0 GPSR2_0 GPSR3_0 GPSR4_0 GPSR5_0 GPSR6_0 GPSR7_0 - -#define PINMUX_IPSR \ -\ -FM(IP0_3_0) IP0_3_0 FM(IP1_3_0) IP1_3_0 FM(IP2_3_0) IP2_3_0 FM(IP3_3_0) IP3_3_0 \ -FM(IP0_7_4) IP0_7_4 FM(IP1_7_4) IP1_7_4 FM(IP2_7_4) IP2_7_4 FM(IP3_7_4) IP3_7_4 \ -FM(IP0_11_8) IP0_11_8 FM(IP1_11_8) IP1_11_8 FM(IP2_11_8) IP2_11_8 FM(IP3_11_8) IP3_11_8 \ -FM(IP0_15_12) IP0_15_12 FM(IP1_15_12) IP1_15_12 FM(IP2_15_12) IP2_15_12 FM(IP3_15_12) IP3_15_12 \ -FM(IP0_19_16) IP0_19_16 FM(IP1_19_16) IP1_19_16 FM(IP2_19_16) IP2_19_16 FM(IP3_19_16) IP3_19_16 \ -FM(IP0_23_20) IP0_23_20 FM(IP1_23_20) IP1_23_20 FM(IP2_23_20) IP2_23_20 FM(IP3_23_20) IP3_23_20 \ -FM(IP0_27_24) IP0_27_24 FM(IP1_27_24) IP1_27_24 FM(IP2_27_24) IP2_27_24 FM(IP3_27_24) IP3_27_24 \ -FM(IP0_31_28) IP0_31_28 FM(IP1_31_28) IP1_31_28 FM(IP2_31_28) IP2_31_28 FM(IP3_31_28) IP3_31_28 \ -\ -FM(IP4_3_0) IP4_3_0 FM(IP5_3_0) IP5_3_0 FM(IP6_3_0) IP6_3_0 FM(IP7_3_0) IP7_3_0 \ -FM(IP4_7_4) IP4_7_4 FM(IP5_7_4) IP5_7_4 FM(IP6_7_4) IP6_7_4 FM(IP7_7_4) IP7_7_4 \ -FM(IP4_11_8) IP4_11_8 FM(IP5_11_8) IP5_11_8 FM(IP6_11_8) IP6_11_8 FM(IP7_11_8) IP7_11_8 \ -FM(IP4_15_12) IP4_15_12 FM(IP5_15_12) IP5_15_12 FM(IP6_15_12) IP6_15_12 FM(IP7_15_12) IP7_15_12 \ -FM(IP4_19_16) IP4_19_16 FM(IP5_19_16) IP5_19_16 FM(IP6_19_16) IP6_19_16 FM(IP7_19_16) IP7_19_16 \ -FM(IP4_23_20) IP4_23_20 FM(IP5_23_20) IP5_23_20 FM(IP6_23_20) IP6_23_20 FM(IP7_23_20) IP7_23_20 \ -FM(IP4_27_24) IP4_27_24 FM(IP5_27_24) IP5_27_24 FM(IP6_27_24) IP6_27_24 FM(IP7_27_24) IP7_27_24 \ -FM(IP4_31_28) IP4_31_28 FM(IP5_31_28) IP5_31_28 FM(IP6_31_28) IP6_31_28 FM(IP7_31_28) IP7_31_28 \ -\ -FM(IP8_3_0) IP8_3_0 FM(IP9_3_0) IP9_3_0 FM(IP10_3_0) IP10_3_0 FM(IP11_3_0) IP11_3_0 \ -FM(IP8_7_4) IP8_7_4 FM(IP9_7_4) IP9_7_4 FM(IP10_7_4) IP10_7_4 FM(IP11_7_4) IP11_7_4 \ -FM(IP8_11_8) IP8_11_8 FM(IP9_11_8) IP9_11_8 FM(IP10_11_8) IP10_11_8 FM(IP11_11_8) IP11_11_8 \ -FM(IP8_15_12) IP8_15_12 FM(IP9_15_12) IP9_15_12 FM(IP10_15_12) IP10_15_12 FM(IP11_15_12) IP11_15_12 \ -FM(IP8_19_16) IP8_19_16 FM(IP9_19_16) IP9_19_16 FM(IP10_19_16) IP10_19_16 FM(IP11_19_16) IP11_19_16 \ -FM(IP8_23_20) IP8_23_20 FM(IP9_23_20) IP9_23_20 FM(IP10_23_20) IP10_23_20 FM(IP11_23_20) IP11_23_20 \ -FM(IP8_27_24) IP8_27_24 FM(IP9_27_24) IP9_27_24 FM(IP10_27_24) IP10_27_24 FM(IP11_27_24) IP11_27_24 \ -FM(IP8_31_28) IP8_31_28 FM(IP9_31_28) IP9_31_28 FM(IP10_31_28) IP10_31_28 FM(IP11_31_28) IP11_31_28 \ -\ -FM(IP12_3_0) IP12_3_0 FM(IP13_3_0) IP13_3_0 FM(IP14_3_0) IP14_3_0 FM(IP15_3_0) IP15_3_0 \ -FM(IP12_7_4) IP12_7_4 FM(IP13_7_4) IP13_7_4 FM(IP14_7_4) IP14_7_4 FM(IP15_7_4) IP15_7_4 \ -FM(IP12_11_8) IP12_11_8 FM(IP13_11_8) IP13_11_8 FM(IP14_11_8) IP14_11_8 FM(IP15_11_8) IP15_11_8 \ -FM(IP12_15_12) IP12_15_12 FM(IP13_15_12) IP13_15_12 FM(IP14_15_12) IP14_15_12 FM(IP15_15_12) IP15_15_12 \ -FM(IP12_19_16) IP12_19_16 FM(IP13_19_16) IP13_19_16 FM(IP14_19_16) IP14_19_16 FM(IP15_19_16) IP15_19_16 \ -FM(IP12_23_20) IP12_23_20 FM(IP13_23_20) IP13_23_20 FM(IP14_23_20) IP14_23_20 FM(IP15_23_20) IP15_23_20 \ -FM(IP12_27_24) IP12_27_24 FM(IP13_27_24) IP13_27_24 FM(IP14_27_24) IP14_27_24 FM(IP15_27_24) IP15_27_24 \ -FM(IP12_31_28) IP12_31_28 FM(IP13_31_28) IP13_31_28 FM(IP14_31_28) IP14_31_28 FM(IP15_31_28) IP15_31_28 \ -\ -FM(IP16_3_0) IP16_3_0 FM(IP17_3_0) IP17_3_0 \ -FM(IP16_7_4) IP16_7_4 FM(IP17_7_4) IP17_7_4 \ -FM(IP16_11_8) IP16_11_8 \ -FM(IP16_15_12) IP16_15_12 \ -FM(IP16_19_16) IP16_19_16 \ -FM(IP16_23_20) IP16_23_20 \ -FM(IP16_27_24) IP16_27_24 \ -FM(IP16_31_28) IP16_31_28 - -/* MOD_SEL0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ -#define MOD_SEL0_30_29 FM(SEL_MSIOF3_0) FM(SEL_MSIOF3_1) FM(SEL_MSIOF3_2) FM(SEL_MSIOF3_3) -#define MOD_SEL0_28_27 FM(SEL_MSIOF2_0) FM(SEL_MSIOF2_1) FM(SEL_MSIOF2_2) FM(SEL_MSIOF2_3) -#define MOD_SEL0_26_25_24 FM(SEL_MSIOF1_0) FM(SEL_MSIOF1_1) FM(SEL_MSIOF1_2) FM(SEL_MSIOF1_3) FM(SEL_MSIOF1_4) FM(SEL_MSIOF1_5) FM(SEL_MSIOF1_6) F_(0, 0) -#define MOD_SEL0_23 FM(SEL_LBSC_0) FM(SEL_LBSC_1) -#define MOD_SEL0_22 FM(SEL_IEBUS_0) FM(SEL_IEBUS_1) -#define MOD_SEL0_21_20 FM(SEL_I2C6_0) FM(SEL_I2C6_1) FM(SEL_I2C6_2) F_(0, 0) -#define MOD_SEL0_19 FM(SEL_I2C2_0) FM(SEL_I2C2_1) -#define MOD_SEL0_18 FM(SEL_I2C1_0) FM(SEL_I2C1_1) -#define MOD_SEL0_17 FM(SEL_HSCIF4_0) FM(SEL_HSCIF4_1) -#define MOD_SEL0_16_15 FM(SEL_HSCIF3_0) FM(SEL_HSCIF3_1) FM(SEL_HSCIF3_2) FM(SEL_HSCIF3_3) -#define MOD_SEL0_14 FM(SEL_HSCIF2_0) FM(SEL_HSCIF2_1) -#define MOD_SEL0_13 FM(SEL_HSCIF1_0) FM(SEL_HSCIF1_1) -#define MOD_SEL0_12 FM(SEL_FSO_0) FM(SEL_FSO_1) -#define MOD_SEL0_11 FM(SEL_FM_0) FM(SEL_FM_1) -#define MOD_SEL0_10 FM(SEL_ETHERAVB_0) FM(SEL_ETHERAVB_1) -#define MOD_SEL0_9 FM(SEL_DRIF3_0) FM(SEL_DRIF3_1) -#define MOD_SEL0_8 FM(SEL_DRIF2_0) FM(SEL_DRIF2_1) -#define MOD_SEL0_7_6 FM(SEL_DRIF1_0) FM(SEL_DRIF1_1) FM(SEL_DRIF1_2) F_(0, 0) -#define MOD_SEL0_5_4 FM(SEL_DRIF0_0) FM(SEL_DRIF0_1) FM(SEL_DRIF0_2) F_(0, 0) -#define MOD_SEL0_3 FM(SEL_CANFD0_0) FM(SEL_CANFD0_1) -#define MOD_SEL0_2_1 FM(SEL_ADG_0) FM(SEL_ADG_1) FM(SEL_ADG_2) FM(SEL_ADG_3) - -/* MOD_SEL1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ /* 4 */ /* 5 */ /* 6 */ /* 7 */ -#define MOD_SEL1_31_30 FM(SEL_TSIF1_0) FM(SEL_TSIF1_1) FM(SEL_TSIF1_2) FM(SEL_TSIF1_3) -#define MOD_SEL1_29_28_27 FM(SEL_TSIF0_0) FM(SEL_TSIF0_1) FM(SEL_TSIF0_2) FM(SEL_TSIF0_3) FM(SEL_TSIF0_4) F_(0, 0) F_(0, 0) F_(0, 0) -#define MOD_SEL1_26 FM(SEL_TIMER_TMU_0) FM(SEL_TIMER_TMU_1) -#define MOD_SEL1_25_24 FM(SEL_SSP1_1_0) FM(SEL_SSP1_1_1) FM(SEL_SSP1_1_2) FM(SEL_SSP1_1_3) -#define MOD_SEL1_23_22_21 FM(SEL_SSP1_0_0) FM(SEL_SSP1_0_1) FM(SEL_SSP1_0_2) FM(SEL_SSP1_0_3) FM(SEL_SSP1_0_4) F_(0, 0) F_(0, 0) F_(0, 0) -#define MOD_SEL1_20 FM(SEL_SSI_0) FM(SEL_SSI_1) -#define MOD_SEL1_19 FM(SEL_SPEED_PULSE_0) FM(SEL_SPEED_PULSE_1) -#define MOD_SEL1_18_17 FM(SEL_SIMCARD_0) FM(SEL_SIMCARD_1) FM(SEL_SIMCARD_2) FM(SEL_SIMCARD_3) -#define MOD_SEL1_16 FM(SEL_SDHI2_0) FM(SEL_SDHI2_1) -#define MOD_SEL1_15_14 FM(SEL_SCIF4_0) FM(SEL_SCIF4_1) FM(SEL_SCIF4_2) F_(0, 0) -#define MOD_SEL1_13 FM(SEL_SCIF3_0) FM(SEL_SCIF3_1) -#define MOD_SEL1_12 FM(SEL_SCIF2_0) FM(SEL_SCIF2_1) -#define MOD_SEL1_11 FM(SEL_SCIF1_0) FM(SEL_SCIF1_1) -#define MOD_SEL1_10 FM(SEL_SATA_0) FM(SEL_SATA_1) -#define MOD_SEL1_9 FM(SEL_REMOCON_0) FM(SEL_REMOCON_1) -#define MOD_SEL1_6 FM(SEL_RCAN0_0) FM(SEL_RCAN0_1) -#define MOD_SEL1_5 FM(SEL_PWM6_0) FM(SEL_PWM6_1) -#define MOD_SEL1_4 FM(SEL_PWM5_0) FM(SEL_PWM5_1) -#define MOD_SEL1_3 FM(SEL_PWM4_0) FM(SEL_PWM4_1) -#define MOD_SEL1_2 FM(SEL_PWM3_0) FM(SEL_PWM3_1) -#define MOD_SEL1_1 FM(SEL_PWM2_0) FM(SEL_PWM2_1) -#define MOD_SEL1_0 FM(SEL_PWM1_0) FM(SEL_PWM1_1) - -/* MOD_SEL2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 */ -#define MOD_SEL2_31 FM(I2C_SEL_5_0) FM(I2C_SEL_5_1) -#define MOD_SEL2_30 FM(I2C_SEL_3_0) FM(I2C_SEL_3_1) -#define MOD_SEL2_29 FM(I2C_SEL_0_0) FM(I2C_SEL_0_1) -#define MOD_SEL2_0 FM(SEL_VIN4_0) FM(SEL_VIN4_1) - -#define PINMUX_MOD_SELS\ -\ - MOD_SEL1_31_30 MOD_SEL2_31 \ -MOD_SEL0_30_29 MOD_SEL2_30 \ - MOD_SEL1_29_28_27 MOD_SEL2_29 \ -MOD_SEL0_28_27 \ -\ -MOD_SEL0_26_25_24 MOD_SEL1_26 \ - MOD_SEL1_25_24 \ -\ -MOD_SEL0_23 MOD_SEL1_23_22_21 \ -MOD_SEL0_22 \ -MOD_SEL0_21_20 \ - MOD_SEL1_20 \ -MOD_SEL0_19 MOD_SEL1_19 \ -MOD_SEL0_18 MOD_SEL1_18_17 \ -MOD_SEL0_17 \ -MOD_SEL0_16_15 MOD_SEL1_16 \ - MOD_SEL1_15_14 \ -MOD_SEL0_14 \ -MOD_SEL0_13 MOD_SEL1_13 \ -MOD_SEL0_12 MOD_SEL1_12 \ -MOD_SEL0_11 MOD_SEL1_11 \ -MOD_SEL0_10 MOD_SEL1_10 \ -MOD_SEL0_9 MOD_SEL1_9 \ -MOD_SEL0_8 \ -MOD_SEL0_7_6 \ - MOD_SEL1_6 \ -MOD_SEL0_5_4 MOD_SEL1_5 \ - MOD_SEL1_4 \ -MOD_SEL0_3 MOD_SEL1_3 \ -MOD_SEL0_2_1 MOD_SEL1_2 \ - MOD_SEL1_1 \ - MOD_SEL1_0 MOD_SEL2_0 - -/* - * These pins are not able to be muxed but have other properties - * that can be set, such as drive-strength or pull-up/pull-down enable. - */ -#define PINMUX_STATIC \ - FM(QSPI0_SPCLK) FM(QSPI0_SSL) FM(QSPI0_MOSI_IO0) FM(QSPI0_MISO_IO1) \ - FM(QSPI0_IO2) FM(QSPI0_IO3) \ - FM(QSPI1_SPCLK) FM(QSPI1_SSL) FM(QSPI1_MOSI_IO0) FM(QSPI1_MISO_IO1) \ - FM(QSPI1_IO2) FM(QSPI1_IO3) \ - FM(RPC_INT) FM(RPC_WP) FM(RPC_RESET) \ - FM(AVB_TX_CTL) FM(AVB_TXC) FM(AVB_TD0) FM(AVB_TD1) FM(AVB_TD2) FM(AVB_TD3) \ - FM(AVB_RX_CTL) FM(AVB_RXC) FM(AVB_RD0) FM(AVB_RD1) FM(AVB_RD2) FM(AVB_RD3) \ - FM(AVB_TXCREFCLK) FM(AVB_MDIO) \ - FM(CLKOUT) FM(PRESETOUT) \ - FM(DU_DOTCLKIN0) FM(DU_DOTCLKIN1) FM(DU_DOTCLKIN2) FM(DU_DOTCLKIN3) \ - FM(TMS) FM(TDO) FM(ASEBRK) FM(MLB_REF) FM(TDI) FM(TCK) FM(TRST) FM(EXTALR) - -#define PINMUX_PHYS \ - FM(SCL0) FM(SDA0) FM(SCL3) FM(SDA3) FM(SCL5) FM(SDA5) - -enum { - PINMUX_RESERVED = 0, - - PINMUX_DATA_BEGIN, - GP_ALL(DATA), - PINMUX_DATA_END, - -#define F_(x, y) -#define FM(x) FN_##x, - PINMUX_FUNCTION_BEGIN, - GP_ALL(FN), - PINMUX_GPSR - PINMUX_IPSR - PINMUX_MOD_SELS - PINMUX_FUNCTION_END, -#undef F_ -#undef FM - -#define F_(x, y) -#define FM(x) x##_MARK, - PINMUX_MARK_BEGIN, - PINMUX_GPSR - PINMUX_IPSR - PINMUX_MOD_SELS - PINMUX_STATIC - PINMUX_PHYS - PINMUX_MARK_END, -#undef F_ -#undef FM -}; - -static const u16 pinmux_data[] = { - PINMUX_DATA_GP_ALL(), - - PINMUX_SINGLE(AVS1), - PINMUX_SINGLE(AVS2), - PINMUX_SINGLE(GP7_02), - PINMUX_SINGLE(GP7_03), - PINMUX_SINGLE(MSIOF0_RXD), - PINMUX_SINGLE(MSIOF0_SCK), - PINMUX_SINGLE(MSIOF0_TXD), - PINMUX_SINGLE(SD2_CMD), - PINMUX_SINGLE(SD3_CLK), - PINMUX_SINGLE(SD3_CMD), - PINMUX_SINGLE(SD3_DAT0), - PINMUX_SINGLE(SD3_DAT1), - PINMUX_SINGLE(SD3_DAT2), - PINMUX_SINGLE(SD3_DAT3), - PINMUX_SINGLE(SD3_DS), - PINMUX_SINGLE(SSI_SCK5), - PINMUX_SINGLE(SSI_SDATA5), - PINMUX_SINGLE(SSI_WS5), - - /* IPSR0 */ - PINMUX_IPSR_GPSR(IP0_3_0, AVB_MDC), - PINMUX_IPSR_MSEL(IP0_3_0, MSIOF2_SS2_C, SEL_MSIOF2_2), - - PINMUX_IPSR_GPSR(IP0_7_4, AVB_MAGIC), - PINMUX_IPSR_MSEL(IP0_7_4, MSIOF2_SS1_C, SEL_MSIOF2_2), - PINMUX_IPSR_MSEL(IP0_7_4, SCK4_A, SEL_SCIF4_0), - - PINMUX_IPSR_GPSR(IP0_11_8, AVB_PHY_INT), - PINMUX_IPSR_MSEL(IP0_11_8, MSIOF2_SYNC_C, SEL_MSIOF2_2), - PINMUX_IPSR_MSEL(IP0_11_8, RX4_A, SEL_SCIF4_0), - - PINMUX_IPSR_GPSR(IP0_15_12, AVB_LINK), - PINMUX_IPSR_MSEL(IP0_15_12, MSIOF2_SCK_C, SEL_MSIOF2_2), - PINMUX_IPSR_MSEL(IP0_15_12, TX4_A, SEL_SCIF4_0), - - PINMUX_IPSR_PHYS_MSEL(IP0_19_16, AVB_AVTP_MATCH_A, I2C_SEL_5_0, SEL_ETHERAVB_0), - PINMUX_IPSR_PHYS_MSEL(IP0_19_16, MSIOF2_RXD_C, I2C_SEL_5_0, SEL_MSIOF2_2), - PINMUX_IPSR_PHYS_MSEL(IP0_19_16, CTS4_N_A, I2C_SEL_5_0, SEL_SCIF4_0), - PINMUX_IPSR_PHYS(IP0_19_16, SCL5, I2C_SEL_5_1), - - PINMUX_IPSR_PHYS_MSEL(IP0_23_20, AVB_AVTP_CAPTURE_A, I2C_SEL_5_0, SEL_ETHERAVB_0), - PINMUX_IPSR_PHYS_MSEL(IP0_23_20, MSIOF2_TXD_C, I2C_SEL_5_0, SEL_MSIOF2_2), - PINMUX_IPSR_PHYS_MSEL(IP0_23_20, RTS4_N_A, I2C_SEL_5_0, SEL_SCIF4_0), - PINMUX_IPSR_PHYS(IP0_23_20, SDA5, I2C_SEL_5_1), - - PINMUX_IPSR_GPSR(IP0_27_24, IRQ0), - PINMUX_IPSR_GPSR(IP0_27_24, QPOLB), - PINMUX_IPSR_GPSR(IP0_27_24, DU_CDE), - PINMUX_IPSR_MSEL(IP0_27_24, VI4_DATA0_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP0_27_24, CAN0_TX_B, SEL_RCAN0_1), - PINMUX_IPSR_MSEL(IP0_27_24, CANFD0_TX_B, SEL_CANFD0_1), - - PINMUX_IPSR_GPSR(IP0_31_28, IRQ1), - PINMUX_IPSR_GPSR(IP0_31_28, QPOLA), - PINMUX_IPSR_GPSR(IP0_31_28, DU_DISP), - PINMUX_IPSR_MSEL(IP0_31_28, VI4_DATA1_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP0_31_28, CAN0_RX_B, SEL_RCAN0_1), - PINMUX_IPSR_MSEL(IP0_31_28, CANFD0_RX_B, SEL_CANFD0_1), - - /* IPSR1 */ - PINMUX_IPSR_GPSR(IP1_3_0, IRQ2), - PINMUX_IPSR_GPSR(IP1_3_0, QCPV_QDE), - PINMUX_IPSR_GPSR(IP1_3_0, DU_EXODDF_DU_ODDF_DISP_CDE), - PINMUX_IPSR_MSEL(IP1_3_0, VI4_DATA2_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP1_3_0, PWM3_B, SEL_PWM3_1), - - PINMUX_IPSR_GPSR(IP1_7_4, IRQ3), - PINMUX_IPSR_GPSR(IP1_7_4, QSTVB_QVE), - PINMUX_IPSR_GPSR(IP1_7_4, A25), - PINMUX_IPSR_GPSR(IP1_7_4, DU_DOTCLKOUT1), - PINMUX_IPSR_MSEL(IP1_7_4, VI4_DATA3_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP1_7_4, PWM4_B, SEL_PWM4_1), - - PINMUX_IPSR_GPSR(IP1_11_8, IRQ4), - PINMUX_IPSR_GPSR(IP1_11_8, QSTH_QHS), - PINMUX_IPSR_GPSR(IP1_11_8, A24), - PINMUX_IPSR_GPSR(IP1_11_8, DU_EXHSYNC_DU_HSYNC), - PINMUX_IPSR_MSEL(IP1_11_8, VI4_DATA4_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP1_11_8, PWM5_B, SEL_PWM5_1), - - PINMUX_IPSR_GPSR(IP1_15_12, IRQ5), - PINMUX_IPSR_GPSR(IP1_15_12, QSTB_QHE), - PINMUX_IPSR_GPSR(IP1_15_12, A23), - PINMUX_IPSR_GPSR(IP1_15_12, DU_EXVSYNC_DU_VSYNC), - PINMUX_IPSR_MSEL(IP1_15_12, VI4_DATA5_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP1_15_12, PWM6_B, SEL_PWM6_1), - - PINMUX_IPSR_GPSR(IP1_19_16, PWM0), - PINMUX_IPSR_GPSR(IP1_19_16, AVB_AVTP_PPS), - PINMUX_IPSR_GPSR(IP1_19_16, A22), - PINMUX_IPSR_MSEL(IP1_19_16, VI4_DATA6_B, SEL_VIN4_1), - PINMUX_IPSR_MSEL(IP1_19_16, IECLK_B, SEL_IEBUS_1), - - PINMUX_IPSR_PHYS_MSEL(IP1_23_20, PWM1_A, I2C_SEL_3_0, SEL_PWM1_0), - PINMUX_IPSR_MSEL(IP1_23_20, A21, I2C_SEL_3_0), - PINMUX_IPSR_PHYS_MSEL(IP1_23_20, HRX3_D, I2C_SEL_3_0, SEL_HSCIF3_3), - PINMUX_IPSR_PHYS_MSEL(IP1_23_20, VI4_DATA7_B, I2C_SEL_3_0, SEL_VIN4_1), - PINMUX_IPSR_PHYS_MSEL(IP1_23_20, IERX_B, I2C_SEL_3_0, SEL_IEBUS_1), - PINMUX_IPSR_PHYS(IP1_23_20, SCL3, I2C_SEL_3_1), - - PINMUX_IPSR_PHYS_MSEL(IP1_27_24, PWM2_A, I2C_SEL_3_0, SEL_PWM2_0), - PINMUX_IPSR_MSEL(IP1_27_24, A20, I2C_SEL_3_0), - PINMUX_IPSR_PHYS_MSEL(IP1_27_24, HTX3_D, I2C_SEL_3_0, SEL_HSCIF3_3), - PINMUX_IPSR_PHYS_MSEL(IP1_27_24, IETX_B, I2C_SEL_3_0, SEL_IEBUS_1), - PINMUX_IPSR_PHYS(IP1_27_24, SDA3, I2C_SEL_3_1), - - PINMUX_IPSR_GPSR(IP1_31_28, A0), - PINMUX_IPSR_GPSR(IP1_31_28, LCDOUT16), - PINMUX_IPSR_MSEL(IP1_31_28, MSIOF3_SYNC_B, SEL_MSIOF3_1), - PINMUX_IPSR_GPSR(IP1_31_28, VI4_DATA8), - PINMUX_IPSR_GPSR(IP1_31_28, DU_DB0), - PINMUX_IPSR_MSEL(IP1_31_28, PWM3_A, SEL_PWM3_0), - - /* IPSR2 */ - PINMUX_IPSR_GPSR(IP2_3_0, A1), - PINMUX_IPSR_GPSR(IP2_3_0, LCDOUT17), - PINMUX_IPSR_MSEL(IP2_3_0, MSIOF3_TXD_B, SEL_MSIOF3_1), - PINMUX_IPSR_GPSR(IP2_3_0, VI4_DATA9), - PINMUX_IPSR_GPSR(IP2_3_0, DU_DB1), - PINMUX_IPSR_MSEL(IP2_3_0, PWM4_A, SEL_PWM4_0), - - PINMUX_IPSR_GPSR(IP2_7_4, A2), - PINMUX_IPSR_GPSR(IP2_7_4, LCDOUT18), - PINMUX_IPSR_MSEL(IP2_7_4, MSIOF3_SCK_B, SEL_MSIOF3_1), - PINMUX_IPSR_GPSR(IP2_7_4, VI4_DATA10), - PINMUX_IPSR_GPSR(IP2_7_4, DU_DB2), - PINMUX_IPSR_MSEL(IP2_7_4, PWM5_A, SEL_PWM5_0), - - PINMUX_IPSR_GPSR(IP2_11_8, A3), - PINMUX_IPSR_GPSR(IP2_11_8, LCDOUT19), - PINMUX_IPSR_MSEL(IP2_11_8, MSIOF3_RXD_B, SEL_MSIOF3_1), - PINMUX_IPSR_GPSR(IP2_11_8, VI4_DATA11), - PINMUX_IPSR_GPSR(IP2_11_8, DU_DB3), - PINMUX_IPSR_MSEL(IP2_11_8, PWM6_A, SEL_PWM6_0), - - PINMUX_IPSR_GPSR(IP2_15_12, A4), - PINMUX_IPSR_GPSR(IP2_15_12, LCDOUT20), - PINMUX_IPSR_MSEL(IP2_15_12, MSIOF3_SS1_B, SEL_MSIOF3_1), - PINMUX_IPSR_GPSR(IP2_15_12, VI4_DATA12), - PINMUX_IPSR_GPSR(IP2_15_12, VI5_DATA12), - PINMUX_IPSR_GPSR(IP2_15_12, DU_DB4), - - PINMUX_IPSR_GPSR(IP2_19_16, A5), - PINMUX_IPSR_GPSR(IP2_19_16, LCDOUT21), - PINMUX_IPSR_MSEL(IP2_19_16, MSIOF3_SS2_B, SEL_MSIOF3_1), - PINMUX_IPSR_MSEL(IP2_19_16, SCK4_B, SEL_SCIF4_1), - PINMUX_IPSR_GPSR(IP2_19_16, VI4_DATA13), - PINMUX_IPSR_GPSR(IP2_19_16, VI5_DATA13), - PINMUX_IPSR_GPSR(IP2_19_16, DU_DB5), - - PINMUX_IPSR_GPSR(IP2_23_20, A6), - PINMUX_IPSR_GPSR(IP2_23_20, LCDOUT22), - PINMUX_IPSR_MSEL(IP2_23_20, MSIOF2_SS1_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP2_23_20, RX4_B, SEL_SCIF4_1), - PINMUX_IPSR_GPSR(IP2_23_20, VI4_DATA14), - PINMUX_IPSR_GPSR(IP2_23_20, VI5_DATA14), - PINMUX_IPSR_GPSR(IP2_23_20, DU_DB6), - - PINMUX_IPSR_GPSR(IP2_27_24, A7), - PINMUX_IPSR_GPSR(IP2_27_24, LCDOUT23), - PINMUX_IPSR_MSEL(IP2_27_24, MSIOF2_SS2_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP2_27_24, TX4_B, SEL_SCIF4_1), - PINMUX_IPSR_GPSR(IP2_27_24, VI4_DATA15), - PINMUX_IPSR_GPSR(IP2_27_24, VI5_DATA15), - PINMUX_IPSR_GPSR(IP2_27_24, DU_DB7), - - PINMUX_IPSR_GPSR(IP2_31_28, A8), - PINMUX_IPSR_MSEL(IP2_31_28, RX3_B, SEL_SCIF3_1), - PINMUX_IPSR_MSEL(IP2_31_28, MSIOF2_SYNC_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP2_31_28, HRX4_B, SEL_HSCIF4_1), - PINMUX_IPSR_MSEL(IP2_31_28, SDA6_A, SEL_I2C6_0), - PINMUX_IPSR_MSEL(IP2_31_28, AVB_AVTP_MATCH_B, SEL_ETHERAVB_1), - PINMUX_IPSR_MSEL(IP2_31_28, PWM1_B, SEL_PWM1_1), - - /* IPSR3 */ - PINMUX_IPSR_GPSR(IP3_3_0, A9), - PINMUX_IPSR_MSEL(IP3_3_0, MSIOF2_SCK_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP3_3_0, CTS4_N_B, SEL_SCIF4_1), - PINMUX_IPSR_GPSR(IP3_3_0, VI5_VSYNC_N), - - PINMUX_IPSR_GPSR(IP3_7_4, A10), - PINMUX_IPSR_MSEL(IP3_7_4, MSIOF2_RXD_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP3_7_4, RTS4_N_B, SEL_SCIF4_1), - PINMUX_IPSR_GPSR(IP3_7_4, VI5_HSYNC_N), - - PINMUX_IPSR_GPSR(IP3_11_8, A11), - PINMUX_IPSR_MSEL(IP3_11_8, TX3_B, SEL_SCIF3_1), - PINMUX_IPSR_MSEL(IP3_11_8, MSIOF2_TXD_A, SEL_MSIOF2_0), - PINMUX_IPSR_MSEL(IP3_11_8, HTX4_B, SEL_HSCIF4_1), - PINMUX_IPSR_GPSR(IP3_11_8, HSCK4), - PINMUX_IPSR_GPSR(IP3_11_8, VI5_FIELD), - PINMUX_IPSR_MSEL(IP3_11_8, SCL6_A, SEL_I2C6_0), - PINMUX_IPSR_MSEL(IP3_11_8, AVB_AVTP_CAPTURE_B, SEL_ETHERAVB_1), - PINMUX_IPSR_MSEL(IP3_11_8, PWM2_B, SEL_PWM2_1), - - PINMUX_IPSR_GPSR(IP3_15_12, A12), - PINMUX_IPSR_GPSR(IP3_15_12, LCDOUT12), - PINMUX_IPSR_MSEL(IP3_15_12, MSIOF3_SCK_C, SEL_MSIOF3_2), - PINMUX_IPSR_MSEL(IP3_15_12, HRX4_A, SEL_HSCIF4_0), - PINMUX_IPSR_GPSR(IP3_15_12, VI5_DATA8), - PINMUX_IPSR_GPSR(IP3_15_12, DU_DG4), - - PINMUX_IPSR_GPSR(IP3_19_16, A13), - PINMUX_IPSR_GPSR(IP3_19_16, LCDOUT13), - PINMUX_IPSR_MSEL(IP3_19_16, MSIOF3_SYNC_C, SEL_MSIOF3_2), - PINMUX_IPSR_MSEL(IP3_19_16, HTX4_A, SEL_HSCIF4_0), - PINMUX_IPSR_GPSR(IP3_19_16, VI5_DATA9), - PINMUX_IPSR_GPSR(IP3_19_16, DU_DG5), - - PINMUX_IPSR_GPSR(IP3_23_20, A14), - PINMUX_IPSR_GPSR(IP3_23_20, LCDOUT14), - PINMUX_IPSR_MSEL(IP3_23_20, MSIOF3_RXD_C, SEL_MSIOF3_2), - PINMUX_IPSR_GPSR(IP3_23_20, HCTS4_N), - PINMUX_IPSR_GPSR(IP3_23_20, VI5_DATA10), - PINMUX_IPSR_GPSR(IP3_23_20, DU_DG6), - - PINMUX_IPSR_GPSR(IP3_27_24, A15), - PINMUX_IPSR_GPSR(IP3_27_24, LCDOUT15), - PINMUX_IPSR_MSEL(IP3_27_24, MSIOF3_TXD_C, SEL_MSIOF3_2), - PINMUX_IPSR_GPSR(IP3_27_24, HRTS4_N), - PINMUX_IPSR_GPSR(IP3_27_24, VI5_DATA11), - PINMUX_IPSR_GPSR(IP3_27_24, DU_DG7), - - PINMUX_IPSR_GPSR(IP3_31_28, A16), - PINMUX_IPSR_GPSR(IP3_31_28, LCDOUT8), - PINMUX_IPSR_GPSR(IP3_31_28, VI4_FIELD), - PINMUX_IPSR_GPSR(IP3_31_28, DU_DG0), - - /* IPSR4 */ - PINMUX_IPSR_GPSR(IP4_3_0, A17), - PINMUX_IPSR_GPSR(IP4_3_0, LCDOUT9), - PINMUX_IPSR_GPSR(IP4_3_0, VI4_VSYNC_N), - PINMUX_IPSR_GPSR(IP4_3_0, DU_DG1), - - PINMUX_IPSR_GPSR(IP4_7_4, A18), - PINMUX_IPSR_GPSR(IP4_7_4, LCDOUT10), - PINMUX_IPSR_GPSR(IP4_7_4, VI4_HSYNC_N), - PINMUX_IPSR_GPSR(IP4_7_4, DU_DG2), - - PINMUX_IPSR_GPSR(IP4_11_8, A19), - PINMUX_IPSR_GPSR(IP4_11_8, LCDOUT11), - PINMUX_IPSR_GPSR(IP4_11_8, VI4_CLKENB), - PINMUX_IPSR_GPSR(IP4_11_8, DU_DG3), - - PINMUX_IPSR_GPSR(IP4_15_12, CS0_N), - PINMUX_IPSR_GPSR(IP4_15_12, VI5_CLKENB), - - PINMUX_IPSR_GPSR(IP4_19_16, CS1_N_A26), - PINMUX_IPSR_GPSR(IP4_19_16, VI5_CLK), - PINMUX_IPSR_MSEL(IP4_19_16, EX_WAIT0_B, SEL_LBSC_1), - - PINMUX_IPSR_GPSR(IP4_23_20, BS_N), - PINMUX_IPSR_GPSR(IP4_23_20, QSTVA_QVS), - PINMUX_IPSR_MSEL(IP4_23_20, MSIOF3_SCK_D, SEL_MSIOF3_3), - PINMUX_IPSR_GPSR(IP4_23_20, SCK3), - PINMUX_IPSR_GPSR(IP4_23_20, HSCK3), - PINMUX_IPSR_GPSR(IP4_23_20, CAN1_TX), - PINMUX_IPSR_GPSR(IP4_23_20, CANFD1_TX), - PINMUX_IPSR_MSEL(IP4_23_20, IETX_A, SEL_IEBUS_0), - - PINMUX_IPSR_GPSR(IP4_27_24, RD_N), - PINMUX_IPSR_MSEL(IP4_27_24, MSIOF3_SYNC_D, SEL_MSIOF3_3), - PINMUX_IPSR_MSEL(IP4_27_24, RX3_A, SEL_SCIF3_0), - PINMUX_IPSR_MSEL(IP4_27_24, HRX3_A, SEL_HSCIF3_0), - PINMUX_IPSR_MSEL(IP4_27_24, CAN0_TX_A, SEL_RCAN0_0), - PINMUX_IPSR_MSEL(IP4_27_24, CANFD0_TX_A, SEL_CANFD0_0), - - PINMUX_IPSR_GPSR(IP4_31_28, RD_WR_N), - PINMUX_IPSR_MSEL(IP4_31_28, MSIOF3_RXD_D, SEL_MSIOF3_3), - PINMUX_IPSR_MSEL(IP4_31_28, TX3_A, SEL_SCIF3_0), - PINMUX_IPSR_MSEL(IP4_31_28, HTX3_A, SEL_HSCIF3_0), - PINMUX_IPSR_MSEL(IP4_31_28, CAN0_RX_A, SEL_RCAN0_0), - PINMUX_IPSR_MSEL(IP4_31_28, CANFD0_RX_A, SEL_CANFD0_0), - - /* IPSR5 */ - PINMUX_IPSR_GPSR(IP5_3_0, WE0_N), - PINMUX_IPSR_MSEL(IP5_3_0, MSIOF3_TXD_D, SEL_MSIOF3_3), - PINMUX_IPSR_GPSR(IP5_3_0, CTS3_N), - PINMUX_IPSR_GPSR(IP5_3_0, HCTS3_N), - PINMUX_IPSR_MSEL(IP5_3_0, SCL6_B, SEL_I2C6_1), - PINMUX_IPSR_GPSR(IP5_3_0, CAN_CLK), - PINMUX_IPSR_MSEL(IP5_3_0, IECLK_A, SEL_IEBUS_0), - - PINMUX_IPSR_GPSR(IP5_7_4, WE1_N), - PINMUX_IPSR_MSEL(IP5_7_4, MSIOF3_SS1_D, SEL_MSIOF3_3), - PINMUX_IPSR_GPSR(IP5_7_4, RTS3_N), - PINMUX_IPSR_GPSR(IP5_7_4, HRTS3_N), - PINMUX_IPSR_MSEL(IP5_7_4, SDA6_B, SEL_I2C6_1), - PINMUX_IPSR_GPSR(IP5_7_4, CAN1_RX), - PINMUX_IPSR_GPSR(IP5_7_4, CANFD1_RX), - PINMUX_IPSR_MSEL(IP5_7_4, IERX_A, SEL_IEBUS_0), - - PINMUX_IPSR_MSEL(IP5_11_8, EX_WAIT0_A, SEL_LBSC_0), - PINMUX_IPSR_GPSR(IP5_11_8, QCLK), - PINMUX_IPSR_GPSR(IP5_11_8, VI4_CLK), - PINMUX_IPSR_GPSR(IP5_11_8, DU_DOTCLKOUT0), - - PINMUX_IPSR_GPSR(IP5_15_12, D0), - PINMUX_IPSR_MSEL(IP5_15_12, MSIOF2_SS1_B, SEL_MSIOF2_1), - PINMUX_IPSR_MSEL(IP5_15_12, MSIOF3_SCK_A, SEL_MSIOF3_0), - PINMUX_IPSR_GPSR(IP5_15_12, VI4_DATA16), - PINMUX_IPSR_GPSR(IP5_15_12, VI5_DATA0), - - PINMUX_IPSR_GPSR(IP5_19_16, D1), - PINMUX_IPSR_MSEL(IP5_19_16, MSIOF2_SS2_B, SEL_MSIOF2_1), - PINMUX_IPSR_MSEL(IP5_19_16, MSIOF3_SYNC_A, SEL_MSIOF3_0), - PINMUX_IPSR_GPSR(IP5_19_16, VI4_DATA17), - PINMUX_IPSR_GPSR(IP5_19_16, VI5_DATA1), - - PINMUX_IPSR_GPSR(IP5_23_20, D2), - PINMUX_IPSR_MSEL(IP5_23_20, MSIOF3_RXD_A, SEL_MSIOF3_0), - PINMUX_IPSR_GPSR(IP5_23_20, VI4_DATA18), - PINMUX_IPSR_GPSR(IP5_23_20, VI5_DATA2), - - PINMUX_IPSR_GPSR(IP5_27_24, D3), - PINMUX_IPSR_MSEL(IP5_27_24, MSIOF3_TXD_A, SEL_MSIOF3_0), - PINMUX_IPSR_GPSR(IP5_27_24, VI4_DATA19), - PINMUX_IPSR_GPSR(IP5_27_24, VI5_DATA3), - - PINMUX_IPSR_GPSR(IP5_31_28, D4), - PINMUX_IPSR_MSEL(IP5_31_28, MSIOF2_SCK_B, SEL_MSIOF2_1), - PINMUX_IPSR_GPSR(IP5_31_28, VI4_DATA20), - PINMUX_IPSR_GPSR(IP5_31_28, VI5_DATA4), - - /* IPSR6 */ - PINMUX_IPSR_GPSR(IP6_3_0, D5), - PINMUX_IPSR_MSEL(IP6_3_0, MSIOF2_SYNC_B, SEL_MSIOF2_1), - PINMUX_IPSR_GPSR(IP6_3_0, VI4_DATA21), - PINMUX_IPSR_GPSR(IP6_3_0, VI5_DATA5), - - PINMUX_IPSR_GPSR(IP6_7_4, D6), - PINMUX_IPSR_MSEL(IP6_7_4, MSIOF2_RXD_B, SEL_MSIOF2_1), - PINMUX_IPSR_GPSR(IP6_7_4, VI4_DATA22), - PINMUX_IPSR_GPSR(IP6_7_4, VI5_DATA6), - - PINMUX_IPSR_GPSR(IP6_11_8, D7), - PINMUX_IPSR_MSEL(IP6_11_8, MSIOF2_TXD_B, SEL_MSIOF2_1), - PINMUX_IPSR_GPSR(IP6_11_8, VI4_DATA23), - PINMUX_IPSR_GPSR(IP6_11_8, VI5_DATA7), - - PINMUX_IPSR_GPSR(IP6_15_12, D8), - PINMUX_IPSR_GPSR(IP6_15_12, LCDOUT0), - PINMUX_IPSR_MSEL(IP6_15_12, MSIOF2_SCK_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP6_15_12, SCK4_C, SEL_SCIF4_2), - PINMUX_IPSR_MSEL(IP6_15_12, VI4_DATA0_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP6_15_12, DU_DR0), - - PINMUX_IPSR_GPSR(IP6_19_16, D9), - PINMUX_IPSR_GPSR(IP6_19_16, LCDOUT1), - PINMUX_IPSR_MSEL(IP6_19_16, MSIOF2_SYNC_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP6_19_16, VI4_DATA1_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP6_19_16, DU_DR1), - - PINMUX_IPSR_GPSR(IP6_23_20, D10), - PINMUX_IPSR_GPSR(IP6_23_20, LCDOUT2), - PINMUX_IPSR_MSEL(IP6_23_20, MSIOF2_RXD_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP6_23_20, HRX3_B, SEL_HSCIF3_1), - PINMUX_IPSR_MSEL(IP6_23_20, VI4_DATA2_A, SEL_VIN4_0), - PINMUX_IPSR_MSEL(IP6_23_20, CTS4_N_C, SEL_SCIF4_2), - PINMUX_IPSR_GPSR(IP6_23_20, DU_DR2), - - PINMUX_IPSR_GPSR(IP6_27_24, D11), - PINMUX_IPSR_GPSR(IP6_27_24, LCDOUT3), - PINMUX_IPSR_MSEL(IP6_27_24, MSIOF2_TXD_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP6_27_24, HTX3_B, SEL_HSCIF3_1), - PINMUX_IPSR_MSEL(IP6_27_24, VI4_DATA3_A, SEL_VIN4_0), - PINMUX_IPSR_MSEL(IP6_27_24, RTS4_N_C, SEL_SCIF4_2), - PINMUX_IPSR_GPSR(IP6_27_24, DU_DR3), - - PINMUX_IPSR_GPSR(IP6_31_28, D12), - PINMUX_IPSR_GPSR(IP6_31_28, LCDOUT4), - PINMUX_IPSR_MSEL(IP6_31_28, MSIOF2_SS1_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP6_31_28, RX4_C, SEL_SCIF4_2), - PINMUX_IPSR_MSEL(IP6_31_28, VI4_DATA4_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP6_31_28, DU_DR4), - - /* IPSR7 */ - PINMUX_IPSR_GPSR(IP7_3_0, D13), - PINMUX_IPSR_GPSR(IP7_3_0, LCDOUT5), - PINMUX_IPSR_MSEL(IP7_3_0, MSIOF2_SS2_D, SEL_MSIOF2_3), - PINMUX_IPSR_MSEL(IP7_3_0, TX4_C, SEL_SCIF4_2), - PINMUX_IPSR_MSEL(IP7_3_0, VI4_DATA5_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP7_3_0, DU_DR5), - - PINMUX_IPSR_GPSR(IP7_7_4, D14), - PINMUX_IPSR_GPSR(IP7_7_4, LCDOUT6), - PINMUX_IPSR_MSEL(IP7_7_4, MSIOF3_SS1_A, SEL_MSIOF3_0), - PINMUX_IPSR_MSEL(IP7_7_4, HRX3_C, SEL_HSCIF3_2), - PINMUX_IPSR_MSEL(IP7_7_4, VI4_DATA6_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP7_7_4, DU_DR6), - PINMUX_IPSR_MSEL(IP7_7_4, SCL6_C, SEL_I2C6_2), - - PINMUX_IPSR_GPSR(IP7_11_8, D15), - PINMUX_IPSR_GPSR(IP7_11_8, LCDOUT7), - PINMUX_IPSR_MSEL(IP7_11_8, MSIOF3_SS2_A, SEL_MSIOF3_0), - PINMUX_IPSR_MSEL(IP7_11_8, HTX3_C, SEL_HSCIF3_2), - PINMUX_IPSR_MSEL(IP7_11_8, VI4_DATA7_A, SEL_VIN4_0), - PINMUX_IPSR_GPSR(IP7_11_8, DU_DR7), - PINMUX_IPSR_MSEL(IP7_11_8, SDA6_C, SEL_I2C6_2), - - PINMUX_IPSR_GPSR(IP7_15_12, FSCLKST), - - PINMUX_IPSR_GPSR(IP7_19_16, SD0_CLK), - PINMUX_IPSR_MSEL(IP7_19_16, MSIOF1_SCK_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP7_19_16, STP_OPWM_0_B, SEL_SSP1_0_1), - - PINMUX_IPSR_GPSR(IP7_23_20, SD0_CMD), - PINMUX_IPSR_MSEL(IP7_23_20, MSIOF1_SYNC_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP7_23_20, STP_IVCXO27_0_B, SEL_SSP1_0_1), - - PINMUX_IPSR_GPSR(IP7_27_24, SD0_DAT0), - PINMUX_IPSR_MSEL(IP7_27_24, MSIOF1_RXD_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP7_27_24, TS_SCK0_B, SEL_TSIF0_1), - PINMUX_IPSR_MSEL(IP7_27_24, STP_ISCLK_0_B, SEL_SSP1_0_1), - - PINMUX_IPSR_GPSR(IP7_31_28, SD0_DAT1), - PINMUX_IPSR_MSEL(IP7_31_28, MSIOF1_TXD_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP7_31_28, TS_SPSYNC0_B, SEL_TSIF0_1), - PINMUX_IPSR_MSEL(IP7_31_28, STP_ISSYNC_0_B, SEL_SSP1_0_1), - - /* IPSR8 */ - PINMUX_IPSR_GPSR(IP8_3_0, SD0_DAT2), - PINMUX_IPSR_MSEL(IP8_3_0, MSIOF1_SS1_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP8_3_0, TS_SDAT0_B, SEL_TSIF0_1), - PINMUX_IPSR_MSEL(IP8_3_0, STP_ISD_0_B, SEL_SSP1_0_1), - - PINMUX_IPSR_GPSR(IP8_7_4, SD0_DAT3), - PINMUX_IPSR_MSEL(IP8_7_4, MSIOF1_SS2_E, SEL_MSIOF1_4), - PINMUX_IPSR_MSEL(IP8_7_4, TS_SDEN0_B, SEL_TSIF0_1), - PINMUX_IPSR_MSEL(IP8_7_4, STP_ISEN_0_B, SEL_SSP1_0_1), - - PINMUX_IPSR_GPSR(IP8_11_8, SD1_CLK), - PINMUX_IPSR_MSEL(IP8_11_8, MSIOF1_SCK_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_11_8, SIM0_CLK_A, SEL_SIMCARD_0), - - PINMUX_IPSR_GPSR(IP8_15_12, SD1_CMD), - PINMUX_IPSR_MSEL(IP8_15_12, MSIOF1_SYNC_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_15_12, SIM0_D_A, SEL_SIMCARD_0), - PINMUX_IPSR_MSEL(IP8_15_12, STP_IVCXO27_1_B, SEL_SSP1_1_1), - - PINMUX_IPSR_GPSR(IP8_19_16, SD1_DAT0), - PINMUX_IPSR_GPSR(IP8_19_16, SD2_DAT4), - PINMUX_IPSR_MSEL(IP8_19_16, MSIOF1_RXD_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_19_16, TS_SCK1_B, SEL_TSIF1_1), - PINMUX_IPSR_MSEL(IP8_19_16, STP_ISCLK_1_B, SEL_SSP1_1_1), - - PINMUX_IPSR_GPSR(IP8_23_20, SD1_DAT1), - PINMUX_IPSR_GPSR(IP8_23_20, SD2_DAT5), - PINMUX_IPSR_MSEL(IP8_23_20, MSIOF1_TXD_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_23_20, TS_SPSYNC1_B, SEL_TSIF1_1), - PINMUX_IPSR_MSEL(IP8_23_20, STP_ISSYNC_1_B, SEL_SSP1_1_1), - - PINMUX_IPSR_GPSR(IP8_27_24, SD1_DAT2), - PINMUX_IPSR_GPSR(IP8_27_24, SD2_DAT6), - PINMUX_IPSR_MSEL(IP8_27_24, MSIOF1_SS1_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_27_24, TS_SDAT1_B, SEL_TSIF1_1), - PINMUX_IPSR_MSEL(IP8_27_24, STP_ISD_1_B, SEL_SSP1_1_1), - - PINMUX_IPSR_GPSR(IP8_31_28, SD1_DAT3), - PINMUX_IPSR_GPSR(IP8_31_28, SD2_DAT7), - PINMUX_IPSR_MSEL(IP8_31_28, MSIOF1_SS2_G, SEL_MSIOF1_6), - PINMUX_IPSR_MSEL(IP8_31_28, TS_SDEN1_B, SEL_TSIF1_1), - PINMUX_IPSR_MSEL(IP8_31_28, STP_ISEN_1_B, SEL_SSP1_1_1), - - /* IPSR9 */ - PINMUX_IPSR_GPSR(IP9_3_0, SD2_CLK), - - PINMUX_IPSR_GPSR(IP9_7_4, SD2_DAT0), - - PINMUX_IPSR_GPSR(IP9_11_8, SD2_DAT1), - - PINMUX_IPSR_GPSR(IP9_15_12, SD2_DAT2), - - PINMUX_IPSR_GPSR(IP9_19_16, SD2_DAT3), - - PINMUX_IPSR_GPSR(IP9_23_20, SD2_DS), - PINMUX_IPSR_MSEL(IP9_23_20, SATA_DEVSLP_B, SEL_SATA_1), - - PINMUX_IPSR_GPSR(IP9_27_24, SD3_DAT4), - PINMUX_IPSR_MSEL(IP9_27_24, SD2_CD_A, SEL_SDHI2_0), - - PINMUX_IPSR_GPSR(IP9_31_28, SD3_DAT5), - PINMUX_IPSR_MSEL(IP9_31_28, SD2_WP_A, SEL_SDHI2_0), - - /* IPSR10 */ - PINMUX_IPSR_GPSR(IP10_3_0, SD3_DAT6), - PINMUX_IPSR_GPSR(IP10_3_0, SD3_CD), - - PINMUX_IPSR_GPSR(IP10_7_4, SD3_DAT7), - PINMUX_IPSR_GPSR(IP10_7_4, SD3_WP), - - PINMUX_IPSR_GPSR(IP10_11_8, SD0_CD), - PINMUX_IPSR_MSEL(IP10_11_8, SCL2_B, SEL_I2C2_1), - PINMUX_IPSR_MSEL(IP10_11_8, SIM0_RST_A, SEL_SIMCARD_0), - - PINMUX_IPSR_GPSR(IP10_15_12, SD0_WP), - PINMUX_IPSR_MSEL(IP10_15_12, SDA2_B, SEL_I2C2_1), - - PINMUX_IPSR_MSEL(IP10_19_16, SD1_CD, I2C_SEL_0_0), - PINMUX_IPSR_PHYS_MSEL(IP10_19_16, SIM0_CLK_B, I2C_SEL_0_0, SEL_SIMCARD_1), - PINMUX_IPSR_PHYS(IP10_19_16, SCL0, I2C_SEL_0_1), - - PINMUX_IPSR_MSEL(IP10_23_20, SD1_WP, I2C_SEL_0_0), - PINMUX_IPSR_PHYS_MSEL(IP10_23_20, SIM0_D_B, I2C_SEL_0_0, SEL_SIMCARD_1), - PINMUX_IPSR_PHYS(IP10_23_20, SDA0, I2C_SEL_0_1), - - PINMUX_IPSR_GPSR(IP10_27_24, SCK0), - PINMUX_IPSR_MSEL(IP10_27_24, HSCK1_B, SEL_HSCIF1_1), - PINMUX_IPSR_MSEL(IP10_27_24, MSIOF1_SS2_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP10_27_24, AUDIO_CLKC_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP10_27_24, SDA2_A, SEL_I2C2_0), - PINMUX_IPSR_MSEL(IP10_27_24, SIM0_RST_B, SEL_SIMCARD_1), - PINMUX_IPSR_MSEL(IP10_27_24, STP_OPWM_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP10_27_24, RIF0_CLK_B, SEL_DRIF0_1), - PINMUX_IPSR_GPSR(IP10_27_24, ADICHS2), - - PINMUX_IPSR_GPSR(IP10_31_28, RX0), - PINMUX_IPSR_MSEL(IP10_31_28, HRX1_B, SEL_HSCIF1_1), - PINMUX_IPSR_MSEL(IP10_31_28, TS_SCK0_C, SEL_TSIF0_2), - PINMUX_IPSR_MSEL(IP10_31_28, STP_ISCLK_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP10_31_28, RIF0_D0_B, SEL_DRIF0_1), - - /* IPSR11 */ - PINMUX_IPSR_GPSR(IP11_3_0, TX0), - PINMUX_IPSR_MSEL(IP11_3_0, HTX1_B, SEL_HSCIF1_1), - PINMUX_IPSR_MSEL(IP11_3_0, TS_SPSYNC0_C, SEL_TSIF0_2), - PINMUX_IPSR_MSEL(IP11_3_0, STP_ISSYNC_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP11_3_0, RIF0_D1_B, SEL_DRIF0_1), - - PINMUX_IPSR_GPSR(IP11_7_4, CTS0_N), - PINMUX_IPSR_MSEL(IP11_7_4, HCTS1_N_B, SEL_HSCIF1_1), - PINMUX_IPSR_MSEL(IP11_7_4, MSIOF1_SYNC_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP11_7_4, TS_SPSYNC1_C, SEL_TSIF1_2), - PINMUX_IPSR_MSEL(IP11_7_4, STP_ISSYNC_1_C, SEL_SSP1_1_2), - PINMUX_IPSR_MSEL(IP11_7_4, RIF1_SYNC_B, SEL_DRIF1_1), - PINMUX_IPSR_MSEL(IP11_7_4, AUDIO_CLKOUT_C, SEL_ADG_2), - PINMUX_IPSR_GPSR(IP11_7_4, ADICS_SAMP), - - PINMUX_IPSR_GPSR(IP11_11_8, RTS0_N), - PINMUX_IPSR_MSEL(IP11_11_8, HRTS1_N_B, SEL_HSCIF1_1), - PINMUX_IPSR_MSEL(IP11_11_8, MSIOF1_SS1_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP11_11_8, AUDIO_CLKA_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP11_11_8, SCL2_A, SEL_I2C2_0), - PINMUX_IPSR_MSEL(IP11_11_8, STP_IVCXO27_1_C, SEL_SSP1_1_2), - PINMUX_IPSR_MSEL(IP11_11_8, RIF0_SYNC_B, SEL_DRIF0_1), - PINMUX_IPSR_GPSR(IP11_11_8, ADICHS1), - - PINMUX_IPSR_MSEL(IP11_15_12, RX1_A, SEL_SCIF1_0), - PINMUX_IPSR_MSEL(IP11_15_12, HRX1_A, SEL_HSCIF1_0), - PINMUX_IPSR_MSEL(IP11_15_12, TS_SDAT0_C, SEL_TSIF0_2), - PINMUX_IPSR_MSEL(IP11_15_12, STP_ISD_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP11_15_12, RIF1_CLK_C, SEL_DRIF1_2), - - PINMUX_IPSR_MSEL(IP11_19_16, TX1_A, SEL_SCIF1_0), - PINMUX_IPSR_MSEL(IP11_19_16, HTX1_A, SEL_HSCIF1_0), - PINMUX_IPSR_MSEL(IP11_19_16, TS_SDEN0_C, SEL_TSIF0_2), - PINMUX_IPSR_MSEL(IP11_19_16, STP_ISEN_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP11_19_16, RIF1_D0_C, SEL_DRIF1_2), - - PINMUX_IPSR_GPSR(IP11_23_20, CTS1_N), - PINMUX_IPSR_MSEL(IP11_23_20, HCTS1_N_A, SEL_HSCIF1_0), - PINMUX_IPSR_MSEL(IP11_23_20, MSIOF1_RXD_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP11_23_20, TS_SDEN1_C, SEL_TSIF1_2), - PINMUX_IPSR_MSEL(IP11_23_20, STP_ISEN_1_C, SEL_SSP1_1_2), - PINMUX_IPSR_MSEL(IP11_23_20, RIF1_D0_B, SEL_DRIF1_1), - PINMUX_IPSR_GPSR(IP11_23_20, ADIDATA), - - PINMUX_IPSR_GPSR(IP11_27_24, RTS1_N), - PINMUX_IPSR_MSEL(IP11_27_24, HRTS1_N_A, SEL_HSCIF1_0), - PINMUX_IPSR_MSEL(IP11_27_24, MSIOF1_TXD_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP11_27_24, TS_SDAT1_C, SEL_TSIF1_2), - PINMUX_IPSR_MSEL(IP11_27_24, STP_ISD_1_C, SEL_SSP1_1_2), - PINMUX_IPSR_MSEL(IP11_27_24, RIF1_D1_B, SEL_DRIF1_1), - PINMUX_IPSR_GPSR(IP11_27_24, ADICHS0), - - PINMUX_IPSR_GPSR(IP11_31_28, SCK2), - PINMUX_IPSR_MSEL(IP11_31_28, SCIF_CLK_B, SEL_SCIF1_1), - PINMUX_IPSR_MSEL(IP11_31_28, MSIOF1_SCK_B, SEL_MSIOF1_1), - PINMUX_IPSR_MSEL(IP11_31_28, TS_SCK1_C, SEL_TSIF1_2), - PINMUX_IPSR_MSEL(IP11_31_28, STP_ISCLK_1_C, SEL_SSP1_1_2), - PINMUX_IPSR_MSEL(IP11_31_28, RIF1_CLK_B, SEL_DRIF1_1), - PINMUX_IPSR_GPSR(IP11_31_28, ADICLK), - - /* IPSR12 */ - PINMUX_IPSR_MSEL(IP12_3_0, TX2_A, SEL_SCIF2_0), - PINMUX_IPSR_MSEL(IP12_3_0, SD2_CD_B, SEL_SDHI2_1), - PINMUX_IPSR_MSEL(IP12_3_0, SCL1_A, SEL_I2C1_0), - PINMUX_IPSR_MSEL(IP12_3_0, FMCLK_A, SEL_FM_0), - PINMUX_IPSR_MSEL(IP12_3_0, RIF1_D1_C, SEL_DRIF1_2), - PINMUX_IPSR_MSEL(IP12_3_0, FSO_CFE_0_B, SEL_FSO_1), - - PINMUX_IPSR_MSEL(IP12_7_4, RX2_A, SEL_SCIF2_0), - PINMUX_IPSR_MSEL(IP12_7_4, SD2_WP_B, SEL_SDHI2_1), - PINMUX_IPSR_MSEL(IP12_7_4, SDA1_A, SEL_I2C1_0), - PINMUX_IPSR_MSEL(IP12_7_4, FMIN_A, SEL_FM_0), - PINMUX_IPSR_MSEL(IP12_7_4, RIF1_SYNC_C, SEL_DRIF1_2), - PINMUX_IPSR_MSEL(IP12_7_4, FSO_CFE_1_B, SEL_FSO_1), - - PINMUX_IPSR_GPSR(IP12_11_8, HSCK0), - PINMUX_IPSR_MSEL(IP12_11_8, MSIOF1_SCK_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP12_11_8, AUDIO_CLKB_A, SEL_ADG_0), - PINMUX_IPSR_MSEL(IP12_11_8, SSI_SDATA1_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP12_11_8, TS_SCK0_D, SEL_TSIF0_3), - PINMUX_IPSR_MSEL(IP12_11_8, STP_ISCLK_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP12_11_8, RIF0_CLK_C, SEL_DRIF0_2), - - PINMUX_IPSR_GPSR(IP12_15_12, HRX0), - PINMUX_IPSR_MSEL(IP12_15_12, MSIOF1_RXD_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP12_15_12, SSI_SDATA2_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP12_15_12, TS_SDEN0_D, SEL_TSIF0_3), - PINMUX_IPSR_MSEL(IP12_15_12, STP_ISEN_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP12_15_12, RIF0_D0_C, SEL_DRIF0_2), - - PINMUX_IPSR_GPSR(IP12_19_16, HTX0), - PINMUX_IPSR_MSEL(IP12_19_16, MSIOF1_TXD_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP12_19_16, SSI_SDATA9_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP12_19_16, TS_SDAT0_D, SEL_TSIF0_3), - PINMUX_IPSR_MSEL(IP12_19_16, STP_ISD_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP12_19_16, RIF0_D1_C, SEL_DRIF0_2), - - PINMUX_IPSR_GPSR(IP12_23_20, HCTS0_N), - PINMUX_IPSR_MSEL(IP12_23_20, RX2_B, SEL_SCIF2_1), - PINMUX_IPSR_MSEL(IP12_23_20, MSIOF1_SYNC_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP12_23_20, SSI_SCK9_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP12_23_20, TS_SPSYNC0_D, SEL_TSIF0_3), - PINMUX_IPSR_MSEL(IP12_23_20, STP_ISSYNC_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP12_23_20, RIF0_SYNC_C, SEL_DRIF0_2), - PINMUX_IPSR_MSEL(IP12_23_20, AUDIO_CLKOUT1_A, SEL_ADG_0), - - PINMUX_IPSR_GPSR(IP12_27_24, HRTS0_N), - PINMUX_IPSR_MSEL(IP12_27_24, TX2_B, SEL_SCIF2_1), - PINMUX_IPSR_MSEL(IP12_27_24, MSIOF1_SS1_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP12_27_24, SSI_WS9_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP12_27_24, STP_IVCXO27_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP12_27_24, BPFCLK_A, SEL_FM_0), - PINMUX_IPSR_MSEL(IP12_27_24, AUDIO_CLKOUT2_A, SEL_ADG_0), - - PINMUX_IPSR_GPSR(IP12_31_28, MSIOF0_SYNC), - PINMUX_IPSR_MSEL(IP12_31_28, AUDIO_CLKOUT_A, SEL_ADG_0), - - /* IPSR13 */ - PINMUX_IPSR_GPSR(IP13_3_0, MSIOF0_SS1), - PINMUX_IPSR_GPSR(IP13_3_0, RX5), - PINMUX_IPSR_MSEL(IP13_3_0, AUDIO_CLKA_C, SEL_ADG_2), - PINMUX_IPSR_MSEL(IP13_3_0, SSI_SCK2_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP13_3_0, STP_IVCXO27_0_C, SEL_SSP1_0_2), - PINMUX_IPSR_MSEL(IP13_3_0, AUDIO_CLKOUT3_A, SEL_ADG_0), - PINMUX_IPSR_MSEL(IP13_3_0, TCLK1_B, SEL_TIMER_TMU_1), - - PINMUX_IPSR_GPSR(IP13_7_4, MSIOF0_SS2), - PINMUX_IPSR_GPSR(IP13_7_4, TX5), - PINMUX_IPSR_MSEL(IP13_7_4, MSIOF1_SS2_D, SEL_MSIOF1_3), - PINMUX_IPSR_MSEL(IP13_7_4, AUDIO_CLKC_A, SEL_ADG_0), - PINMUX_IPSR_MSEL(IP13_7_4, SSI_WS2_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP13_7_4, STP_OPWM_0_D, SEL_SSP1_0_3), - PINMUX_IPSR_MSEL(IP13_7_4, AUDIO_CLKOUT_D, SEL_ADG_3), - PINMUX_IPSR_MSEL(IP13_7_4, SPEEDIN_B, SEL_SPEED_PULSE_1), - - PINMUX_IPSR_GPSR(IP13_11_8, MLB_CLK), - PINMUX_IPSR_MSEL(IP13_11_8, MSIOF1_SCK_F, SEL_MSIOF1_5), - PINMUX_IPSR_MSEL(IP13_11_8, SCL1_B, SEL_I2C1_1), - - PINMUX_IPSR_GPSR(IP13_15_12, MLB_SIG), - PINMUX_IPSR_MSEL(IP13_15_12, RX1_B, SEL_SCIF1_1), - PINMUX_IPSR_MSEL(IP13_15_12, MSIOF1_SYNC_F, SEL_MSIOF1_5), - PINMUX_IPSR_MSEL(IP13_15_12, SDA1_B, SEL_I2C1_1), - - PINMUX_IPSR_GPSR(IP13_19_16, MLB_DAT), - PINMUX_IPSR_MSEL(IP13_19_16, TX1_B, SEL_SCIF1_1), - PINMUX_IPSR_MSEL(IP13_19_16, MSIOF1_RXD_F, SEL_MSIOF1_5), - - PINMUX_IPSR_GPSR(IP13_23_20, SSI_SCK01239), - PINMUX_IPSR_MSEL(IP13_23_20, MSIOF1_TXD_F, SEL_MSIOF1_5), - - PINMUX_IPSR_GPSR(IP13_27_24, SSI_WS01239), - PINMUX_IPSR_MSEL(IP13_27_24, MSIOF1_SS1_F, SEL_MSIOF1_5), - - PINMUX_IPSR_GPSR(IP13_31_28, SSI_SDATA0), - PINMUX_IPSR_MSEL(IP13_31_28, MSIOF1_SS2_F, SEL_MSIOF1_5), - - /* IPSR14 */ - PINMUX_IPSR_MSEL(IP14_3_0, SSI_SDATA1_A, SEL_SSI_0), - - PINMUX_IPSR_MSEL(IP14_7_4, SSI_SDATA2_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP14_7_4, SSI_SCK1_B, SEL_SSI_1), - - PINMUX_IPSR_GPSR(IP14_11_8, SSI_SCK349), - PINMUX_IPSR_MSEL(IP14_11_8, MSIOF1_SS1_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_11_8, STP_OPWM_0_A, SEL_SSP1_0_0), - - PINMUX_IPSR_GPSR(IP14_15_12, SSI_WS349), - PINMUX_IPSR_MSEL(IP14_15_12, HCTS2_N_A, SEL_HSCIF2_0), - PINMUX_IPSR_MSEL(IP14_15_12, MSIOF1_SS2_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_15_12, STP_IVCXO27_0_A, SEL_SSP1_0_0), - - PINMUX_IPSR_GPSR(IP14_19_16, SSI_SDATA3), - PINMUX_IPSR_MSEL(IP14_19_16, HRTS2_N_A, SEL_HSCIF2_0), - PINMUX_IPSR_MSEL(IP14_19_16, MSIOF1_TXD_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_19_16, TS_SCK0_A, SEL_TSIF0_0), - PINMUX_IPSR_MSEL(IP14_19_16, STP_ISCLK_0_A, SEL_SSP1_0_0), - PINMUX_IPSR_MSEL(IP14_19_16, RIF0_D1_A, SEL_DRIF0_0), - PINMUX_IPSR_MSEL(IP14_19_16, RIF2_D0_A, SEL_DRIF2_0), - - PINMUX_IPSR_GPSR(IP14_23_20, SSI_SCK4), - PINMUX_IPSR_MSEL(IP14_23_20, HRX2_A, SEL_HSCIF2_0), - PINMUX_IPSR_MSEL(IP14_23_20, MSIOF1_SCK_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_23_20, TS_SDAT0_A, SEL_TSIF0_0), - PINMUX_IPSR_MSEL(IP14_23_20, STP_ISD_0_A, SEL_SSP1_0_0), - PINMUX_IPSR_MSEL(IP14_23_20, RIF0_CLK_A, SEL_DRIF0_0), - PINMUX_IPSR_MSEL(IP14_23_20, RIF2_CLK_A, SEL_DRIF2_0), - - PINMUX_IPSR_GPSR(IP14_27_24, SSI_WS4), - PINMUX_IPSR_MSEL(IP14_27_24, HTX2_A, SEL_HSCIF2_0), - PINMUX_IPSR_MSEL(IP14_27_24, MSIOF1_SYNC_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_27_24, TS_SDEN0_A, SEL_TSIF0_0), - PINMUX_IPSR_MSEL(IP14_27_24, STP_ISEN_0_A, SEL_SSP1_0_0), - PINMUX_IPSR_MSEL(IP14_27_24, RIF0_SYNC_A, SEL_DRIF0_0), - PINMUX_IPSR_MSEL(IP14_27_24, RIF2_SYNC_A, SEL_DRIF2_0), - - PINMUX_IPSR_GPSR(IP14_31_28, SSI_SDATA4), - PINMUX_IPSR_MSEL(IP14_31_28, HSCK2_A, SEL_HSCIF2_0), - PINMUX_IPSR_MSEL(IP14_31_28, MSIOF1_RXD_A, SEL_MSIOF1_0), - PINMUX_IPSR_MSEL(IP14_31_28, TS_SPSYNC0_A, SEL_TSIF0_0), - PINMUX_IPSR_MSEL(IP14_31_28, STP_ISSYNC_0_A, SEL_SSP1_0_0), - PINMUX_IPSR_MSEL(IP14_31_28, RIF0_D0_A, SEL_DRIF0_0), - PINMUX_IPSR_MSEL(IP14_31_28, RIF2_D1_A, SEL_DRIF2_0), - - /* IPSR15 */ - PINMUX_IPSR_GPSR(IP15_3_0, SSI_SCK6), - PINMUX_IPSR_GPSR(IP15_3_0, USB2_PWEN), - PINMUX_IPSR_MSEL(IP15_3_0, SIM0_RST_D, SEL_SIMCARD_3), - - PINMUX_IPSR_GPSR(IP15_7_4, SSI_WS6), - PINMUX_IPSR_GPSR(IP15_7_4, USB2_OVC), - PINMUX_IPSR_MSEL(IP15_7_4, SIM0_D_D, SEL_SIMCARD_3), - - PINMUX_IPSR_GPSR(IP15_11_8, SSI_SDATA6), - PINMUX_IPSR_MSEL(IP15_11_8, SIM0_CLK_D, SEL_SIMCARD_3), - PINMUX_IPSR_MSEL(IP15_11_8, SATA_DEVSLP_A, SEL_SATA_0), - - PINMUX_IPSR_GPSR(IP15_15_12, SSI_SCK78), - PINMUX_IPSR_MSEL(IP15_15_12, HRX2_B, SEL_HSCIF2_1), - PINMUX_IPSR_MSEL(IP15_15_12, MSIOF1_SCK_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP15_15_12, TS_SCK1_A, SEL_TSIF1_0), - PINMUX_IPSR_MSEL(IP15_15_12, STP_ISCLK_1_A, SEL_SSP1_1_0), - PINMUX_IPSR_MSEL(IP15_15_12, RIF1_CLK_A, SEL_DRIF1_0), - PINMUX_IPSR_MSEL(IP15_15_12, RIF3_CLK_A, SEL_DRIF3_0), - - PINMUX_IPSR_GPSR(IP15_19_16, SSI_WS78), - PINMUX_IPSR_MSEL(IP15_19_16, HTX2_B, SEL_HSCIF2_1), - PINMUX_IPSR_MSEL(IP15_19_16, MSIOF1_SYNC_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP15_19_16, TS_SDAT1_A, SEL_TSIF1_0), - PINMUX_IPSR_MSEL(IP15_19_16, STP_ISD_1_A, SEL_SSP1_1_0), - PINMUX_IPSR_MSEL(IP15_19_16, RIF1_SYNC_A, SEL_DRIF1_0), - PINMUX_IPSR_MSEL(IP15_19_16, RIF3_SYNC_A, SEL_DRIF3_0), - - PINMUX_IPSR_GPSR(IP15_23_20, SSI_SDATA7), - PINMUX_IPSR_MSEL(IP15_23_20, HCTS2_N_B, SEL_HSCIF2_1), - PINMUX_IPSR_MSEL(IP15_23_20, MSIOF1_RXD_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP15_23_20, TS_SDEN1_A, SEL_TSIF1_0), - PINMUX_IPSR_MSEL(IP15_23_20, STP_ISEN_1_A, SEL_SSP1_1_0), - PINMUX_IPSR_MSEL(IP15_23_20, RIF1_D0_A, SEL_DRIF1_0), - PINMUX_IPSR_MSEL(IP15_23_20, RIF3_D0_A, SEL_DRIF3_0), - PINMUX_IPSR_MSEL(IP15_23_20, TCLK2_A, SEL_TIMER_TMU_0), - - PINMUX_IPSR_GPSR(IP15_27_24, SSI_SDATA8), - PINMUX_IPSR_MSEL(IP15_27_24, HRTS2_N_B, SEL_HSCIF2_1), - PINMUX_IPSR_MSEL(IP15_27_24, MSIOF1_TXD_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP15_27_24, TS_SPSYNC1_A, SEL_TSIF1_0), - PINMUX_IPSR_MSEL(IP15_27_24, STP_ISSYNC_1_A, SEL_SSP1_1_0), - PINMUX_IPSR_MSEL(IP15_27_24, RIF1_D1_A, SEL_DRIF1_0), - PINMUX_IPSR_MSEL(IP15_27_24, RIF3_D1_A, SEL_DRIF3_0), - - PINMUX_IPSR_MSEL(IP15_31_28, SSI_SDATA9_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP15_31_28, HSCK2_B, SEL_HSCIF2_1), - PINMUX_IPSR_MSEL(IP15_31_28, MSIOF1_SS1_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP15_31_28, HSCK1_A, SEL_HSCIF1_0), - PINMUX_IPSR_MSEL(IP15_31_28, SSI_WS1_B, SEL_SSI_1), - PINMUX_IPSR_GPSR(IP15_31_28, SCK1), - PINMUX_IPSR_MSEL(IP15_31_28, STP_IVCXO27_1_A, SEL_SSP1_1_0), - PINMUX_IPSR_GPSR(IP15_31_28, SCK5), - - /* IPSR16 */ - PINMUX_IPSR_MSEL(IP16_3_0, AUDIO_CLKA_A, SEL_ADG_0), - - PINMUX_IPSR_MSEL(IP16_7_4, AUDIO_CLKB_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP16_7_4, SCIF_CLK_A, SEL_SCIF1_0), - PINMUX_IPSR_MSEL(IP16_7_4, STP_IVCXO27_1_D, SEL_SSP1_1_3), - PINMUX_IPSR_MSEL(IP16_7_4, REMOCON_A, SEL_REMOCON_0), - PINMUX_IPSR_MSEL(IP16_7_4, TCLK1_A, SEL_TIMER_TMU_0), - - PINMUX_IPSR_GPSR(IP16_11_8, USB0_PWEN), - PINMUX_IPSR_MSEL(IP16_11_8, SIM0_RST_C, SEL_SIMCARD_2), - PINMUX_IPSR_MSEL(IP16_11_8, TS_SCK1_D, SEL_TSIF1_3), - PINMUX_IPSR_MSEL(IP16_11_8, STP_ISCLK_1_D, SEL_SSP1_1_3), - PINMUX_IPSR_MSEL(IP16_11_8, BPFCLK_B, SEL_FM_1), - PINMUX_IPSR_MSEL(IP16_11_8, RIF3_CLK_B, SEL_DRIF3_1), - - PINMUX_IPSR_GPSR(IP16_15_12, USB0_OVC), - PINMUX_IPSR_MSEL(IP16_11_8, SIM0_D_C, SEL_SIMCARD_2), - PINMUX_IPSR_MSEL(IP16_11_8, TS_SDAT1_D, SEL_TSIF1_3), - PINMUX_IPSR_MSEL(IP16_11_8, STP_ISD_1_D, SEL_SSP1_1_3), - PINMUX_IPSR_MSEL(IP16_11_8, RIF3_SYNC_B, SEL_DRIF3_1), - - PINMUX_IPSR_GPSR(IP16_19_16, USB1_PWEN), - PINMUX_IPSR_MSEL(IP16_19_16, SIM0_CLK_C, SEL_SIMCARD_2), - PINMUX_IPSR_MSEL(IP16_19_16, SSI_SCK1_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP16_19_16, TS_SCK0_E, SEL_TSIF0_4), - PINMUX_IPSR_MSEL(IP16_19_16, STP_ISCLK_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP16_19_16, FMCLK_B, SEL_FM_1), - PINMUX_IPSR_MSEL(IP16_19_16, RIF2_CLK_B, SEL_DRIF2_1), - PINMUX_IPSR_MSEL(IP16_19_16, SPEEDIN_A, SEL_SPEED_PULSE_0), - - PINMUX_IPSR_GPSR(IP16_23_20, USB1_OVC), - PINMUX_IPSR_MSEL(IP16_23_20, MSIOF1_SS2_C, SEL_MSIOF1_2), - PINMUX_IPSR_MSEL(IP16_23_20, SSI_WS1_A, SEL_SSI_0), - PINMUX_IPSR_MSEL(IP16_23_20, TS_SDAT0_E, SEL_TSIF0_4), - PINMUX_IPSR_MSEL(IP16_23_20, STP_ISD_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP16_23_20, FMIN_B, SEL_FM_1), - PINMUX_IPSR_MSEL(IP16_23_20, RIF2_SYNC_B, SEL_DRIF2_1), - PINMUX_IPSR_MSEL(IP16_23_20, REMOCON_B, SEL_REMOCON_1), - - PINMUX_IPSR_GPSR(IP16_27_24, USB30_PWEN), - PINMUX_IPSR_MSEL(IP16_27_24, AUDIO_CLKOUT_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP16_27_24, SSI_SCK2_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP16_27_24, TS_SDEN1_D, SEL_TSIF1_3), - PINMUX_IPSR_MSEL(IP16_27_24, STP_ISEN_1_D, SEL_SSP1_1_3), - PINMUX_IPSR_MSEL(IP16_27_24, STP_OPWM_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP16_27_24, RIF3_D0_B, SEL_DRIF3_1), - PINMUX_IPSR_MSEL(IP16_27_24, TCLK2_B, SEL_TIMER_TMU_1), - PINMUX_IPSR_GPSR(IP16_27_24, TPU0TO0), - - PINMUX_IPSR_GPSR(IP16_31_28, USB30_OVC), - PINMUX_IPSR_MSEL(IP16_31_28, AUDIO_CLKOUT1_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP16_31_28, SSI_WS2_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP16_31_28, TS_SPSYNC1_D, SEL_TSIF1_3), - PINMUX_IPSR_MSEL(IP16_31_28, STP_ISSYNC_1_D, SEL_SSP1_1_3), - PINMUX_IPSR_MSEL(IP16_31_28, STP_IVCXO27_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP16_31_28, RIF3_D1_B, SEL_DRIF3_1), - PINMUX_IPSR_MSEL(IP16_31_28, FSO_TOE_B, SEL_FSO_1), - PINMUX_IPSR_GPSR(IP16_31_28, TPU0TO1), - - /* IPSR17 */ - PINMUX_IPSR_GPSR(IP17_3_0, USB31_PWEN), - PINMUX_IPSR_MSEL(IP17_3_0, AUDIO_CLKOUT2_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP17_3_0, SSI_SCK9_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP17_3_0, TS_SDEN0_E, SEL_TSIF0_4), - PINMUX_IPSR_MSEL(IP17_3_0, STP_ISEN_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP17_3_0, RIF2_D0_B, SEL_DRIF2_1), - PINMUX_IPSR_GPSR(IP17_3_0, TPU0TO2), - - PINMUX_IPSR_GPSR(IP17_7_4, USB31_OVC), - PINMUX_IPSR_MSEL(IP17_7_4, AUDIO_CLKOUT3_B, SEL_ADG_1), - PINMUX_IPSR_MSEL(IP17_7_4, SSI_WS9_B, SEL_SSI_1), - PINMUX_IPSR_MSEL(IP17_7_4, TS_SPSYNC0_E, SEL_TSIF0_4), - PINMUX_IPSR_MSEL(IP17_7_4, STP_ISSYNC_0_E, SEL_SSP1_0_4), - PINMUX_IPSR_MSEL(IP17_7_4, RIF2_D1_B, SEL_DRIF2_1), - PINMUX_IPSR_GPSR(IP17_7_4, TPU0TO3), - -/* - * Static pins can not be muxed between different functions but - * still need mark entries in the pinmux list. Add each static - * pin to the list without an associated function. The sh-pfc - * core will do the right thing and skip trying to mux the pin - * while still applying configuration to it. - */ -#define FM(x) PINMUX_DATA(x##_MARK, 0), - PINMUX_STATIC -#undef FM -}; - -/* - * Pins not associated with a GPIO port. - */ -enum { - GP_ASSIGN_LAST(), - NOGP_ALL(), -}; - -static const struct sh_pfc_pin pinmux_pins[] = { - PINMUX_GPIO_GP_ALL(), - PINMUX_NOGP_ALL(), -}; - -/* - AUDIO CLOCK ------------------------------------------------------------ */ -static const unsigned int audio_clk_a_a_pins[] = { - /* CLK A */ - RCAR_GP_PIN(6, 22), -}; -static const unsigned int audio_clk_a_a_mux[] = { - AUDIO_CLKA_A_MARK, -}; -static const unsigned int audio_clk_a_b_pins[] = { - /* CLK A */ - RCAR_GP_PIN(5, 4), -}; -static const unsigned int audio_clk_a_b_mux[] = { - AUDIO_CLKA_B_MARK, -}; -static const unsigned int audio_clk_a_c_pins[] = { - /* CLK A */ - RCAR_GP_PIN(5, 19), -}; -static const unsigned int audio_clk_a_c_mux[] = { - AUDIO_CLKA_C_MARK, -}; -static const unsigned int audio_clk_b_a_pins[] = { - /* CLK B */ - RCAR_GP_PIN(5, 12), -}; -static const unsigned int audio_clk_b_a_mux[] = { - AUDIO_CLKB_A_MARK, -}; -static const unsigned int audio_clk_b_b_pins[] = { - /* CLK B */ - RCAR_GP_PIN(6, 23), -}; -static const unsigned int audio_clk_b_b_mux[] = { - AUDIO_CLKB_B_MARK, -}; -static const unsigned int audio_clk_c_a_pins[] = { - /* CLK C */ - RCAR_GP_PIN(5, 21), -}; -static const unsigned int audio_clk_c_a_mux[] = { - AUDIO_CLKC_A_MARK, -}; -static const unsigned int audio_clk_c_b_pins[] = { - /* CLK C */ - RCAR_GP_PIN(5, 0), -}; -static const unsigned int audio_clk_c_b_mux[] = { - AUDIO_CLKC_B_MARK, -}; -static const unsigned int audio_clkout_a_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(5, 18), -}; -static const unsigned int audio_clkout_a_mux[] = { - AUDIO_CLKOUT_A_MARK, -}; -static const unsigned int audio_clkout_b_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(6, 28), -}; -static const unsigned int audio_clkout_b_mux[] = { - AUDIO_CLKOUT_B_MARK, -}; -static const unsigned int audio_clkout_c_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(5, 3), -}; -static const unsigned int audio_clkout_c_mux[] = { - AUDIO_CLKOUT_C_MARK, -}; -static const unsigned int audio_clkout_d_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(5, 21), -}; -static const unsigned int audio_clkout_d_mux[] = { - AUDIO_CLKOUT_D_MARK, -}; -static const unsigned int audio_clkout1_a_pins[] = { - /* CLKOUT1 */ - RCAR_GP_PIN(5, 15), -}; -static const unsigned int audio_clkout1_a_mux[] = { - AUDIO_CLKOUT1_A_MARK, -}; -static const unsigned int audio_clkout1_b_pins[] = { - /* CLKOUT1 */ - RCAR_GP_PIN(6, 29), -}; -static const unsigned int audio_clkout1_b_mux[] = { - AUDIO_CLKOUT1_B_MARK, -}; -static const unsigned int audio_clkout2_a_pins[] = { - /* CLKOUT2 */ - RCAR_GP_PIN(5, 16), -}; -static const unsigned int audio_clkout2_a_mux[] = { - AUDIO_CLKOUT2_A_MARK, -}; -static const unsigned int audio_clkout2_b_pins[] = { - /* CLKOUT2 */ - RCAR_GP_PIN(6, 30), -}; -static const unsigned int audio_clkout2_b_mux[] = { - AUDIO_CLKOUT2_B_MARK, -}; - -static const unsigned int audio_clkout3_a_pins[] = { - /* CLKOUT3 */ - RCAR_GP_PIN(5, 19), -}; -static const unsigned int audio_clkout3_a_mux[] = { - AUDIO_CLKOUT3_A_MARK, -}; -static const unsigned int audio_clkout3_b_pins[] = { - /* CLKOUT3 */ - RCAR_GP_PIN(6, 31), -}; -static const unsigned int audio_clkout3_b_mux[] = { - AUDIO_CLKOUT3_B_MARK, -}; - -/* - EtherAVB --------------------------------------------------------------- */ -static const unsigned int avb_link_pins[] = { - /* AVB_LINK */ - RCAR_GP_PIN(2, 12), -}; -static const unsigned int avb_link_mux[] = { - AVB_LINK_MARK, -}; -static const unsigned int avb_magic_pins[] = { - /* AVB_MAGIC_ */ - RCAR_GP_PIN(2, 10), -}; -static const unsigned int avb_magic_mux[] = { - AVB_MAGIC_MARK, -}; -static const unsigned int avb_phy_int_pins[] = { - /* AVB_PHY_INT */ - RCAR_GP_PIN(2, 11), -}; -static const unsigned int avb_phy_int_mux[] = { - AVB_PHY_INT_MARK, -}; -static const unsigned int avb_mdio_pins[] = { - /* AVB_MDC, AVB_MDIO */ - RCAR_GP_PIN(2, 9), PIN_AVB_MDIO, -}; -static const unsigned int avb_mdio_mux[] = { - AVB_MDC_MARK, AVB_MDIO_MARK, -}; -static const unsigned int avb_mii_pins[] = { - /* - * AVB_TX_CTL, AVB_TXC, AVB_TD0, - * AVB_TD1, AVB_TD2, AVB_TD3, - * AVB_RX_CTL, AVB_RXC, AVB_RD0, - * AVB_RD1, AVB_RD2, AVB_RD3, - * AVB_TXCREFCLK - */ - PIN_AVB_TX_CTL, PIN_AVB_TXC, PIN_AVB_TD0, - PIN_AVB_TD1, PIN_AVB_TD2, PIN_AVB_TD3, - PIN_AVB_RX_CTL, PIN_AVB_RXC, PIN_AVB_RD0, - PIN_AVB_RD1, PIN_AVB_RD2, PIN_AVB_RD3, - PIN_AVB_TXCREFCLK, -}; -static const unsigned int avb_mii_mux[] = { - AVB_TX_CTL_MARK, AVB_TXC_MARK, AVB_TD0_MARK, - AVB_TD1_MARK, AVB_TD2_MARK, AVB_TD3_MARK, - AVB_RX_CTL_MARK, AVB_RXC_MARK, AVB_RD0_MARK, - AVB_RD1_MARK, AVB_RD2_MARK, AVB_RD3_MARK, - AVB_TXCREFCLK_MARK, -}; -static const unsigned int avb_avtp_pps_pins[] = { - /* AVB_AVTP_PPS */ - RCAR_GP_PIN(2, 6), -}; -static const unsigned int avb_avtp_pps_mux[] = { - AVB_AVTP_PPS_MARK, -}; -static const unsigned int avb_avtp_match_a_pins[] = { - /* AVB_AVTP_MATCH_A */ - RCAR_GP_PIN(2, 13), -}; -static const unsigned int avb_avtp_match_a_mux[] = { - AVB_AVTP_MATCH_A_MARK, -}; -static const unsigned int avb_avtp_capture_a_pins[] = { - /* AVB_AVTP_CAPTURE_A */ - RCAR_GP_PIN(2, 14), -}; -static const unsigned int avb_avtp_capture_a_mux[] = { - AVB_AVTP_CAPTURE_A_MARK, -}; -static const unsigned int avb_avtp_match_b_pins[] = { - /* AVB_AVTP_MATCH_B */ - RCAR_GP_PIN(1, 8), -}; -static const unsigned int avb_avtp_match_b_mux[] = { - AVB_AVTP_MATCH_B_MARK, -}; -static const unsigned int avb_avtp_capture_b_pins[] = { - /* AVB_AVTP_CAPTURE_B */ - RCAR_GP_PIN(1, 11), -}; -static const unsigned int avb_avtp_capture_b_mux[] = { - AVB_AVTP_CAPTURE_B_MARK, -}; - -/* - CAN ------------------------------------------------------------------ */ -static const unsigned int can0_data_a_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24), -}; -static const unsigned int can0_data_a_mux[] = { - CAN0_TX_A_MARK, CAN0_RX_A_MARK, -}; -static const unsigned int can0_data_b_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(2, 0), RCAR_GP_PIN(2, 1), -}; -static const unsigned int can0_data_b_mux[] = { - CAN0_TX_B_MARK, CAN0_RX_B_MARK, -}; -static const unsigned int can1_data_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(1, 22), RCAR_GP_PIN(1, 26), -}; -static const unsigned int can1_data_mux[] = { - CAN1_TX_MARK, CAN1_RX_MARK, -}; - -/* - CAN Clock -------------------------------------------------------------- */ -static const unsigned int can_clk_pins[] = { - /* CLK */ - RCAR_GP_PIN(1, 25), -}; -static const unsigned int can_clk_mux[] = { - CAN_CLK_MARK, -}; - -/* - CAN FD --------------------------------------------------------------- */ -static const unsigned int canfd0_data_a_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24), -}; -static const unsigned int canfd0_data_a_mux[] = { - CANFD0_TX_A_MARK, CANFD0_RX_A_MARK, -}; -static const unsigned int canfd0_data_b_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(2, 0), RCAR_GP_PIN(2, 1), -}; -static const unsigned int canfd0_data_b_mux[] = { - CANFD0_TX_B_MARK, CANFD0_RX_B_MARK, -}; -static const unsigned int canfd1_data_pins[] = { - /* TX, RX */ - RCAR_GP_PIN(1, 22), RCAR_GP_PIN(1, 26), -}; -static const unsigned int canfd1_data_mux[] = { - CANFD1_TX_MARK, CANFD1_RX_MARK, -}; - -/* - DRIF0 --------------------------------------------------------------- */ -static const unsigned int drif0_ctrl_a_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9), -}; -static const unsigned int drif0_ctrl_a_mux[] = { - RIF0_CLK_A_MARK, RIF0_SYNC_A_MARK, -}; -static const unsigned int drif0_data0_a_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 10), -}; -static const unsigned int drif0_data0_a_mux[] = { - RIF0_D0_A_MARK, -}; -static const unsigned int drif0_data1_a_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 7), -}; -static const unsigned int drif0_data1_a_mux[] = { - RIF0_D1_A_MARK, -}; -static const unsigned int drif0_ctrl_b_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4), -}; -static const unsigned int drif0_ctrl_b_mux[] = { - RIF0_CLK_B_MARK, RIF0_SYNC_B_MARK, -}; -static const unsigned int drif0_data0_b_pins[] = { - /* D0 */ - RCAR_GP_PIN(5, 1), -}; -static const unsigned int drif0_data0_b_mux[] = { - RIF0_D0_B_MARK, -}; -static const unsigned int drif0_data1_b_pins[] = { - /* D1 */ - RCAR_GP_PIN(5, 2), -}; -static const unsigned int drif0_data1_b_mux[] = { - RIF0_D1_B_MARK, -}; -static const unsigned int drif0_ctrl_c_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(5, 12), RCAR_GP_PIN(5, 15), -}; -static const unsigned int drif0_ctrl_c_mux[] = { - RIF0_CLK_C_MARK, RIF0_SYNC_C_MARK, -}; -static const unsigned int drif0_data0_c_pins[] = { - /* D0 */ - RCAR_GP_PIN(5, 13), -}; -static const unsigned int drif0_data0_c_mux[] = { - RIF0_D0_C_MARK, -}; -static const unsigned int drif0_data1_c_pins[] = { - /* D1 */ - RCAR_GP_PIN(5, 14), -}; -static const unsigned int drif0_data1_c_mux[] = { - RIF0_D1_C_MARK, -}; -/* - DRIF1 --------------------------------------------------------------- */ -static const unsigned int drif1_ctrl_a_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18), -}; -static const unsigned int drif1_ctrl_a_mux[] = { - RIF1_CLK_A_MARK, RIF1_SYNC_A_MARK, -}; -static const unsigned int drif1_data0_a_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 19), -}; -static const unsigned int drif1_data0_a_mux[] = { - RIF1_D0_A_MARK, -}; -static const unsigned int drif1_data1_a_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 20), -}; -static const unsigned int drif1_data1_a_mux[] = { - RIF1_D1_A_MARK, -}; -static const unsigned int drif1_ctrl_b_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(5, 9), RCAR_GP_PIN(5, 3), -}; -static const unsigned int drif1_ctrl_b_mux[] = { - RIF1_CLK_B_MARK, RIF1_SYNC_B_MARK, -}; -static const unsigned int drif1_data0_b_pins[] = { - /* D0 */ - RCAR_GP_PIN(5, 7), -}; -static const unsigned int drif1_data0_b_mux[] = { - RIF1_D0_B_MARK, -}; -static const unsigned int drif1_data1_b_pins[] = { - /* D1 */ - RCAR_GP_PIN(5, 8), -}; -static const unsigned int drif1_data1_b_mux[] = { - RIF1_D1_B_MARK, -}; -static const unsigned int drif1_ctrl_c_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 11), -}; -static const unsigned int drif1_ctrl_c_mux[] = { - RIF1_CLK_C_MARK, RIF1_SYNC_C_MARK, -}; -static const unsigned int drif1_data0_c_pins[] = { - /* D0 */ - RCAR_GP_PIN(5, 6), -}; -static const unsigned int drif1_data0_c_mux[] = { - RIF1_D0_C_MARK, -}; -static const unsigned int drif1_data1_c_pins[] = { - /* D1 */ - RCAR_GP_PIN(5, 10), -}; -static const unsigned int drif1_data1_c_mux[] = { - RIF1_D1_C_MARK, -}; -/* - DRIF2 --------------------------------------------------------------- */ -static const unsigned int drif2_ctrl_a_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9), -}; -static const unsigned int drif2_ctrl_a_mux[] = { - RIF2_CLK_A_MARK, RIF2_SYNC_A_MARK, -}; -static const unsigned int drif2_data0_a_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 7), -}; -static const unsigned int drif2_data0_a_mux[] = { - RIF2_D0_A_MARK, -}; -static const unsigned int drif2_data1_a_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 10), -}; -static const unsigned int drif2_data1_a_mux[] = { - RIF2_D1_A_MARK, -}; -static const unsigned int drif2_ctrl_b_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27), -}; -static const unsigned int drif2_ctrl_b_mux[] = { - RIF2_CLK_B_MARK, RIF2_SYNC_B_MARK, -}; -static const unsigned int drif2_data0_b_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 30), -}; -static const unsigned int drif2_data0_b_mux[] = { - RIF2_D0_B_MARK, -}; -static const unsigned int drif2_data1_b_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 31), -}; -static const unsigned int drif2_data1_b_mux[] = { - RIF2_D1_B_MARK, -}; -/* - DRIF3 --------------------------------------------------------------- */ -static const unsigned int drif3_ctrl_a_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18), -}; -static const unsigned int drif3_ctrl_a_mux[] = { - RIF3_CLK_A_MARK, RIF3_SYNC_A_MARK, -}; -static const unsigned int drif3_data0_a_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 19), -}; -static const unsigned int drif3_data0_a_mux[] = { - RIF3_D0_A_MARK, -}; -static const unsigned int drif3_data1_a_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 20), -}; -static const unsigned int drif3_data1_a_mux[] = { - RIF3_D1_A_MARK, -}; -static const unsigned int drif3_ctrl_b_pins[] = { - /* CLK, SYNC */ - RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25), -}; -static const unsigned int drif3_ctrl_b_mux[] = { - RIF3_CLK_B_MARK, RIF3_SYNC_B_MARK, -}; -static const unsigned int drif3_data0_b_pins[] = { - /* D0 */ - RCAR_GP_PIN(6, 28), -}; -static const unsigned int drif3_data0_b_mux[] = { - RIF3_D0_B_MARK, -}; -static const unsigned int drif3_data1_b_pins[] = { - /* D1 */ - RCAR_GP_PIN(6, 29), -}; -static const unsigned int drif3_data1_b_mux[] = { - RIF3_D1_B_MARK, -}; - -/* - DU --------------------------------------------------------------------- */ -static const unsigned int du_rgb666_pins[] = { - /* R[7:2], G[7:2], B[7:2] */ - RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13), - RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10), - RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13), - RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18), - RCAR_GP_PIN(1, 7), RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 3), RCAR_GP_PIN(1, 2), -}; -static const unsigned int du_rgb666_mux[] = { - DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK, - DU_DR3_MARK, DU_DR2_MARK, - DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK, - DU_DG3_MARK, DU_DG2_MARK, - DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK, - DU_DB3_MARK, DU_DB2_MARK, -}; -static const unsigned int du_rgb888_pins[] = { - /* R[7:0], G[7:0], B[7:0] */ - RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 13), - RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10), - RCAR_GP_PIN(0, 9), RCAR_GP_PIN(0, 8), - RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 13), - RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 19), RCAR_GP_PIN(1, 18), - RCAR_GP_PIN(1, 17), RCAR_GP_PIN(1, 16), - RCAR_GP_PIN(1, 7), RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 3), RCAR_GP_PIN(1, 2), - RCAR_GP_PIN(1, 1), RCAR_GP_PIN(1, 0), -}; -static const unsigned int du_rgb888_mux[] = { - DU_DR7_MARK, DU_DR6_MARK, DU_DR5_MARK, DU_DR4_MARK, - DU_DR3_MARK, DU_DR2_MARK, DU_DR1_MARK, DU_DR0_MARK, - DU_DG7_MARK, DU_DG6_MARK, DU_DG5_MARK, DU_DG4_MARK, - DU_DG3_MARK, DU_DG2_MARK, DU_DG1_MARK, DU_DG0_MARK, - DU_DB7_MARK, DU_DB6_MARK, DU_DB5_MARK, DU_DB4_MARK, - DU_DB3_MARK, DU_DB2_MARK, DU_DB1_MARK, DU_DB0_MARK, -}; -static const unsigned int du_clk_out_0_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(1, 27), -}; -static const unsigned int du_clk_out_0_mux[] = { - DU_DOTCLKOUT0_MARK -}; -static const unsigned int du_clk_out_1_pins[] = { - /* CLKOUT */ - RCAR_GP_PIN(2, 3), -}; -static const unsigned int du_clk_out_1_mux[] = { - DU_DOTCLKOUT1_MARK -}; -static const unsigned int du_sync_pins[] = { - /* EXVSYNC/VSYNC, EXHSYNC/HSYNC */ - RCAR_GP_PIN(2, 5), RCAR_GP_PIN(2, 4), -}; -static const unsigned int du_sync_mux[] = { - DU_EXVSYNC_DU_VSYNC_MARK, DU_EXHSYNC_DU_HSYNC_MARK -}; -static const unsigned int du_oddf_pins[] = { - /* EXDISP/EXODDF/EXCDE */ - RCAR_GP_PIN(2, 2), -}; -static const unsigned int du_oddf_mux[] = { - DU_EXODDF_DU_ODDF_DISP_CDE_MARK, -}; -static const unsigned int du_cde_pins[] = { - /* CDE */ - RCAR_GP_PIN(2, 0), -}; -static const unsigned int du_cde_mux[] = { - DU_CDE_MARK, -}; -static const unsigned int du_disp_pins[] = { - /* DISP */ - RCAR_GP_PIN(2, 1), -}; -static const unsigned int du_disp_mux[] = { - DU_DISP_MARK, -}; -/* - HSCIF0 ----------------------------------------------------------------- */ -static const unsigned int hscif0_data_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14), -}; -static const unsigned int hscif0_data_mux[] = { - HRX0_MARK, HTX0_MARK, -}; -static const unsigned int hscif0_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 12), -}; -static const unsigned int hscif0_clk_mux[] = { - HSCK0_MARK, -}; -static const unsigned int hscif0_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15), -}; -static const unsigned int hscif0_ctrl_mux[] = { - HRTS0_N_MARK, HCTS0_N_MARK, -}; -/* - HSCIF1 ----------------------------------------------------------------- */ -static const unsigned int hscif1_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6), -}; -static const unsigned int hscif1_data_a_mux[] = { - HRX1_A_MARK, HTX1_A_MARK, -}; -static const unsigned int hscif1_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int hscif1_clk_a_mux[] = { - HSCK1_A_MARK, -}; -static const unsigned int hscif1_ctrl_a_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7), -}; -static const unsigned int hscif1_ctrl_a_mux[] = { - HRTS1_N_A_MARK, HCTS1_N_A_MARK, -}; - -static const unsigned int hscif1_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2), -}; -static const unsigned int hscif1_data_b_mux[] = { - HRX1_B_MARK, HTX1_B_MARK, -}; -static const unsigned int hscif1_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 0), -}; -static const unsigned int hscif1_clk_b_mux[] = { - HSCK1_B_MARK, -}; -static const unsigned int hscif1_ctrl_b_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3), -}; -static const unsigned int hscif1_ctrl_b_mux[] = { - HRTS1_N_B_MARK, HCTS1_N_B_MARK, -}; -/* - HSCIF2 ----------------------------------------------------------------- */ -static const unsigned int hscif2_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9), -}; -static const unsigned int hscif2_data_a_mux[] = { - HRX2_A_MARK, HTX2_A_MARK, -}; -static const unsigned int hscif2_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 10), -}; -static const unsigned int hscif2_clk_a_mux[] = { - HSCK2_A_MARK, -}; -static const unsigned int hscif2_ctrl_a_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6), -}; -static const unsigned int hscif2_ctrl_a_mux[] = { - HRTS2_N_A_MARK, HCTS2_N_A_MARK, -}; - -static const unsigned int hscif2_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18), -}; -static const unsigned int hscif2_data_b_mux[] = { - HRX2_B_MARK, HTX2_B_MARK, -}; -static const unsigned int hscif2_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int hscif2_clk_b_mux[] = { - HSCK2_B_MARK, -}; -static const unsigned int hscif2_ctrl_b_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19), -}; -static const unsigned int hscif2_ctrl_b_mux[] = { - HRTS2_N_B_MARK, HCTS2_N_B_MARK, -}; -/* - HSCIF3 ----------------------------------------------------------------- */ -static const unsigned int hscif3_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24), -}; -static const unsigned int hscif3_data_a_mux[] = { - HRX3_A_MARK, HTX3_A_MARK, -}; -static const unsigned int hscif3_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 22), -}; -static const unsigned int hscif3_clk_mux[] = { - HSCK3_MARK, -}; -static const unsigned int hscif3_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25), -}; -static const unsigned int hscif3_ctrl_mux[] = { - HRTS3_N_MARK, HCTS3_N_MARK, -}; - -static const unsigned int hscif3_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11), -}; -static const unsigned int hscif3_data_b_mux[] = { - HRX3_B_MARK, HTX3_B_MARK, -}; -static const unsigned int hscif3_data_c_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15), -}; -static const unsigned int hscif3_data_c_mux[] = { - HRX3_C_MARK, HTX3_C_MARK, -}; -static const unsigned int hscif3_data_d_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8), -}; -static const unsigned int hscif3_data_d_mux[] = { - HRX3_D_MARK, HTX3_D_MARK, -}; -/* - HSCIF4 ----------------------------------------------------------------- */ -static const unsigned int hscif4_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13), -}; -static const unsigned int hscif4_data_a_mux[] = { - HRX4_A_MARK, HTX4_A_MARK, -}; -static const unsigned int hscif4_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 11), -}; -static const unsigned int hscif4_clk_mux[] = { - HSCK4_MARK, -}; -static const unsigned int hscif4_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14), -}; -static const unsigned int hscif4_ctrl_mux[] = { - HRTS4_N_MARK, HCTS4_N_MARK, -}; - -static const unsigned int hscif4_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11), -}; -static const unsigned int hscif4_data_b_mux[] = { - HRX4_B_MARK, HTX4_B_MARK, -}; - -/* - I2C -------------------------------------------------------------------- */ -static const unsigned int i2c0_pins[] = { - /* SCL, SDA */ - RCAR_GP_PIN(3, 14), RCAR_GP_PIN(3, 15), -}; - -static const unsigned int i2c0_mux[] = { - SCL0_MARK, SDA0_MARK, -}; - -static const unsigned int i2c1_a_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 10), -}; -static const unsigned int i2c1_a_mux[] = { - SDA1_A_MARK, SCL1_A_MARK, -}; -static const unsigned int i2c1_b_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 23), -}; -static const unsigned int i2c1_b_mux[] = { - SDA1_B_MARK, SCL1_B_MARK, -}; -static const unsigned int i2c2_a_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(5, 0), RCAR_GP_PIN(5, 4), -}; -static const unsigned int i2c2_a_mux[] = { - SDA2_A_MARK, SCL2_A_MARK, -}; -static const unsigned int i2c2_b_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(3, 13), RCAR_GP_PIN(3, 12), -}; -static const unsigned int i2c2_b_mux[] = { - SDA2_B_MARK, SCL2_B_MARK, -}; - -static const unsigned int i2c3_pins[] = { - /* SCL, SDA */ - RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8), -}; - -static const unsigned int i2c3_mux[] = { - SCL3_MARK, SDA3_MARK, -}; - -static const unsigned int i2c5_pins[] = { - /* SCL, SDA */ - RCAR_GP_PIN(2, 13), RCAR_GP_PIN(2, 14), -}; - -static const unsigned int i2c5_mux[] = { - SCL5_MARK, SDA5_MARK, -}; - -static const unsigned int i2c6_a_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11), -}; -static const unsigned int i2c6_a_mux[] = { - SDA6_A_MARK, SCL6_A_MARK, -}; -static const unsigned int i2c6_b_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25), -}; -static const unsigned int i2c6_b_mux[] = { - SDA6_B_MARK, SCL6_B_MARK, -}; -static const unsigned int i2c6_c_pins[] = { - /* SDA, SCL */ - RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14), -}; -static const unsigned int i2c6_c_mux[] = { - SDA6_C_MARK, SCL6_C_MARK, -}; - -/* - INTC-EX ---------------------------------------------------------------- */ -static const unsigned int intc_ex_irq0_pins[] = { - /* IRQ0 */ - RCAR_GP_PIN(2, 0), -}; -static const unsigned int intc_ex_irq0_mux[] = { - IRQ0_MARK, -}; -static const unsigned int intc_ex_irq1_pins[] = { - /* IRQ1 */ - RCAR_GP_PIN(2, 1), -}; -static const unsigned int intc_ex_irq1_mux[] = { - IRQ1_MARK, -}; -static const unsigned int intc_ex_irq2_pins[] = { - /* IRQ2 */ - RCAR_GP_PIN(2, 2), -}; -static const unsigned int intc_ex_irq2_mux[] = { - IRQ2_MARK, -}; -static const unsigned int intc_ex_irq3_pins[] = { - /* IRQ3 */ - RCAR_GP_PIN(2, 3), -}; -static const unsigned int intc_ex_irq3_mux[] = { - IRQ3_MARK, -}; -static const unsigned int intc_ex_irq4_pins[] = { - /* IRQ4 */ - RCAR_GP_PIN(2, 4), -}; -static const unsigned int intc_ex_irq4_mux[] = { - IRQ4_MARK, -}; -static const unsigned int intc_ex_irq5_pins[] = { - /* IRQ5 */ - RCAR_GP_PIN(2, 5), -}; -static const unsigned int intc_ex_irq5_mux[] = { - IRQ5_MARK, -}; - -/* - MLB+ ------------------------------------------------------------------- */ -static const unsigned int mlb_3pin_pins[] = { - RCAR_GP_PIN(5, 23), RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 25), -}; -static const unsigned int mlb_3pin_mux[] = { - MLB_CLK_MARK, MLB_SIG_MARK, MLB_DAT_MARK, -}; - -/* - MSIOF0 ----------------------------------------------------------------- */ -static const unsigned int msiof0_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 17), -}; -static const unsigned int msiof0_clk_mux[] = { - MSIOF0_SCK_MARK, -}; -static const unsigned int msiof0_sync_pins[] = { - /* SYNC */ - RCAR_GP_PIN(5, 18), -}; -static const unsigned int msiof0_sync_mux[] = { - MSIOF0_SYNC_MARK, -}; -static const unsigned int msiof0_ss1_pins[] = { - /* SS1 */ - RCAR_GP_PIN(5, 19), -}; -static const unsigned int msiof0_ss1_mux[] = { - MSIOF0_SS1_MARK, -}; -static const unsigned int msiof0_ss2_pins[] = { - /* SS2 */ - RCAR_GP_PIN(5, 21), -}; -static const unsigned int msiof0_ss2_mux[] = { - MSIOF0_SS2_MARK, -}; -static const unsigned int msiof0_txd_pins[] = { - /* TXD */ - RCAR_GP_PIN(5, 20), -}; -static const unsigned int msiof0_txd_mux[] = { - MSIOF0_TXD_MARK, -}; -static const unsigned int msiof0_rxd_pins[] = { - /* RXD */ - RCAR_GP_PIN(5, 22), -}; -static const unsigned int msiof0_rxd_mux[] = { - MSIOF0_RXD_MARK, -}; -/* - MSIOF1 ----------------------------------------------------------------- */ -static const unsigned int msiof1_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 8), -}; -static const unsigned int msiof1_clk_a_mux[] = { - MSIOF1_SCK_A_MARK, -}; -static const unsigned int msiof1_sync_a_pins[] = { - /* SYNC */ - RCAR_GP_PIN(6, 9), -}; -static const unsigned int msiof1_sync_a_mux[] = { - MSIOF1_SYNC_A_MARK, -}; -static const unsigned int msiof1_ss1_a_pins[] = { - /* SS1 */ - RCAR_GP_PIN(6, 5), -}; -static const unsigned int msiof1_ss1_a_mux[] = { - MSIOF1_SS1_A_MARK, -}; -static const unsigned int msiof1_ss2_a_pins[] = { - /* SS2 */ - RCAR_GP_PIN(6, 6), -}; -static const unsigned int msiof1_ss2_a_mux[] = { - MSIOF1_SS2_A_MARK, -}; -static const unsigned int msiof1_txd_a_pins[] = { - /* TXD */ - RCAR_GP_PIN(6, 7), -}; -static const unsigned int msiof1_txd_a_mux[] = { - MSIOF1_TXD_A_MARK, -}; -static const unsigned int msiof1_rxd_a_pins[] = { - /* RXD */ - RCAR_GP_PIN(6, 10), -}; -static const unsigned int msiof1_rxd_a_mux[] = { - MSIOF1_RXD_A_MARK, -}; -static const unsigned int msiof1_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 9), -}; -static const unsigned int msiof1_clk_b_mux[] = { - MSIOF1_SCK_B_MARK, -}; -static const unsigned int msiof1_sync_b_pins[] = { - /* SYNC */ - RCAR_GP_PIN(5, 3), -}; -static const unsigned int msiof1_sync_b_mux[] = { - MSIOF1_SYNC_B_MARK, -}; -static const unsigned int msiof1_ss1_b_pins[] = { - /* SS1 */ - RCAR_GP_PIN(5, 4), -}; -static const unsigned int msiof1_ss1_b_mux[] = { - MSIOF1_SS1_B_MARK, -}; -static const unsigned int msiof1_ss2_b_pins[] = { - /* SS2 */ - RCAR_GP_PIN(5, 0), -}; -static const unsigned int msiof1_ss2_b_mux[] = { - MSIOF1_SS2_B_MARK, -}; -static const unsigned int msiof1_txd_b_pins[] = { - /* TXD */ - RCAR_GP_PIN(5, 8), -}; -static const unsigned int msiof1_txd_b_mux[] = { - MSIOF1_TXD_B_MARK, -}; -static const unsigned int msiof1_rxd_b_pins[] = { - /* RXD */ - RCAR_GP_PIN(5, 7), -}; -static const unsigned int msiof1_rxd_b_mux[] = { - MSIOF1_RXD_B_MARK, -}; -static const unsigned int msiof1_clk_c_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 17), -}; -static const unsigned int msiof1_clk_c_mux[] = { - MSIOF1_SCK_C_MARK, -}; -static const unsigned int msiof1_sync_c_pins[] = { - /* SYNC */ - RCAR_GP_PIN(6, 18), -}; -static const unsigned int msiof1_sync_c_mux[] = { - MSIOF1_SYNC_C_MARK, -}; -static const unsigned int msiof1_ss1_c_pins[] = { - /* SS1 */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int msiof1_ss1_c_mux[] = { - MSIOF1_SS1_C_MARK, -}; -static const unsigned int msiof1_ss2_c_pins[] = { - /* SS2 */ - RCAR_GP_PIN(6, 27), -}; -static const unsigned int msiof1_ss2_c_mux[] = { - MSIOF1_SS2_C_MARK, -}; -static const unsigned int msiof1_txd_c_pins[] = { - /* TXD */ - RCAR_GP_PIN(6, 20), -}; -static const unsigned int msiof1_txd_c_mux[] = { - MSIOF1_TXD_C_MARK, -}; -static const unsigned int msiof1_rxd_c_pins[] = { - /* RXD */ - RCAR_GP_PIN(6, 19), -}; -static const unsigned int msiof1_rxd_c_mux[] = { - MSIOF1_RXD_C_MARK, -}; -static const unsigned int msiof1_clk_d_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 12), -}; -static const unsigned int msiof1_clk_d_mux[] = { - MSIOF1_SCK_D_MARK, -}; -static const unsigned int msiof1_sync_d_pins[] = { - /* SYNC */ - RCAR_GP_PIN(5, 15), -}; -static const unsigned int msiof1_sync_d_mux[] = { - MSIOF1_SYNC_D_MARK, -}; -static const unsigned int msiof1_ss1_d_pins[] = { - /* SS1 */ - RCAR_GP_PIN(5, 16), -}; -static const unsigned int msiof1_ss1_d_mux[] = { - MSIOF1_SS1_D_MARK, -}; -static const unsigned int msiof1_ss2_d_pins[] = { - /* SS2 */ - RCAR_GP_PIN(5, 21), -}; -static const unsigned int msiof1_ss2_d_mux[] = { - MSIOF1_SS2_D_MARK, -}; -static const unsigned int msiof1_txd_d_pins[] = { - /* TXD */ - RCAR_GP_PIN(5, 14), -}; -static const unsigned int msiof1_txd_d_mux[] = { - MSIOF1_TXD_D_MARK, -}; -static const unsigned int msiof1_rxd_d_pins[] = { - /* RXD */ - RCAR_GP_PIN(5, 13), -}; -static const unsigned int msiof1_rxd_d_mux[] = { - MSIOF1_RXD_D_MARK, -}; -static const unsigned int msiof1_clk_e_pins[] = { - /* SCK */ - RCAR_GP_PIN(3, 0), -}; -static const unsigned int msiof1_clk_e_mux[] = { - MSIOF1_SCK_E_MARK, -}; -static const unsigned int msiof1_sync_e_pins[] = { - /* SYNC */ - RCAR_GP_PIN(3, 1), -}; -static const unsigned int msiof1_sync_e_mux[] = { - MSIOF1_SYNC_E_MARK, -}; -static const unsigned int msiof1_ss1_e_pins[] = { - /* SS1 */ - RCAR_GP_PIN(3, 4), -}; -static const unsigned int msiof1_ss1_e_mux[] = { - MSIOF1_SS1_E_MARK, -}; -static const unsigned int msiof1_ss2_e_pins[] = { - /* SS2 */ - RCAR_GP_PIN(3, 5), -}; -static const unsigned int msiof1_ss2_e_mux[] = { - MSIOF1_SS2_E_MARK, -}; -static const unsigned int msiof1_txd_e_pins[] = { - /* TXD */ - RCAR_GP_PIN(3, 3), -}; -static const unsigned int msiof1_txd_e_mux[] = { - MSIOF1_TXD_E_MARK, -}; -static const unsigned int msiof1_rxd_e_pins[] = { - /* RXD */ - RCAR_GP_PIN(3, 2), -}; -static const unsigned int msiof1_rxd_e_mux[] = { - MSIOF1_RXD_E_MARK, -}; -static const unsigned int msiof1_clk_f_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 23), -}; -static const unsigned int msiof1_clk_f_mux[] = { - MSIOF1_SCK_F_MARK, -}; -static const unsigned int msiof1_sync_f_pins[] = { - /* SYNC */ - RCAR_GP_PIN(5, 24), -}; -static const unsigned int msiof1_sync_f_mux[] = { - MSIOF1_SYNC_F_MARK, -}; -static const unsigned int msiof1_ss1_f_pins[] = { - /* SS1 */ - RCAR_GP_PIN(6, 1), -}; -static const unsigned int msiof1_ss1_f_mux[] = { - MSIOF1_SS1_F_MARK, -}; -static const unsigned int msiof1_ss2_f_pins[] = { - /* SS2 */ - RCAR_GP_PIN(6, 2), -}; -static const unsigned int msiof1_ss2_f_mux[] = { - MSIOF1_SS2_F_MARK, -}; -static const unsigned int msiof1_txd_f_pins[] = { - /* TXD */ - RCAR_GP_PIN(6, 0), -}; -static const unsigned int msiof1_txd_f_mux[] = { - MSIOF1_TXD_F_MARK, -}; -static const unsigned int msiof1_rxd_f_pins[] = { - /* RXD */ - RCAR_GP_PIN(5, 25), -}; -static const unsigned int msiof1_rxd_f_mux[] = { - MSIOF1_RXD_F_MARK, -}; -static const unsigned int msiof1_clk_g_pins[] = { - /* SCK */ - RCAR_GP_PIN(3, 6), -}; -static const unsigned int msiof1_clk_g_mux[] = { - MSIOF1_SCK_G_MARK, -}; -static const unsigned int msiof1_sync_g_pins[] = { - /* SYNC */ - RCAR_GP_PIN(3, 7), -}; -static const unsigned int msiof1_sync_g_mux[] = { - MSIOF1_SYNC_G_MARK, -}; -static const unsigned int msiof1_ss1_g_pins[] = { - /* SS1 */ - RCAR_GP_PIN(3, 10), -}; -static const unsigned int msiof1_ss1_g_mux[] = { - MSIOF1_SS1_G_MARK, -}; -static const unsigned int msiof1_ss2_g_pins[] = { - /* SS2 */ - RCAR_GP_PIN(3, 11), -}; -static const unsigned int msiof1_ss2_g_mux[] = { - MSIOF1_SS2_G_MARK, -}; -static const unsigned int msiof1_txd_g_pins[] = { - /* TXD */ - RCAR_GP_PIN(3, 9), -}; -static const unsigned int msiof1_txd_g_mux[] = { - MSIOF1_TXD_G_MARK, -}; -static const unsigned int msiof1_rxd_g_pins[] = { - /* RXD */ - RCAR_GP_PIN(3, 8), -}; -static const unsigned int msiof1_rxd_g_mux[] = { - MSIOF1_RXD_G_MARK, -}; -/* - MSIOF2 ----------------------------------------------------------------- */ -static const unsigned int msiof2_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 9), -}; -static const unsigned int msiof2_clk_a_mux[] = { - MSIOF2_SCK_A_MARK, -}; -static const unsigned int msiof2_sync_a_pins[] = { - /* SYNC */ - RCAR_GP_PIN(1, 8), -}; -static const unsigned int msiof2_sync_a_mux[] = { - MSIOF2_SYNC_A_MARK, -}; -static const unsigned int msiof2_ss1_a_pins[] = { - /* SS1 */ - RCAR_GP_PIN(1, 6), -}; -static const unsigned int msiof2_ss1_a_mux[] = { - MSIOF2_SS1_A_MARK, -}; -static const unsigned int msiof2_ss2_a_pins[] = { - /* SS2 */ - RCAR_GP_PIN(1, 7), -}; -static const unsigned int msiof2_ss2_a_mux[] = { - MSIOF2_SS2_A_MARK, -}; -static const unsigned int msiof2_txd_a_pins[] = { - /* TXD */ - RCAR_GP_PIN(1, 11), -}; -static const unsigned int msiof2_txd_a_mux[] = { - MSIOF2_TXD_A_MARK, -}; -static const unsigned int msiof2_rxd_a_pins[] = { - /* RXD */ - RCAR_GP_PIN(1, 10), -}; -static const unsigned int msiof2_rxd_a_mux[] = { - MSIOF2_RXD_A_MARK, -}; -static const unsigned int msiof2_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(0, 4), -}; -static const unsigned int msiof2_clk_b_mux[] = { - MSIOF2_SCK_B_MARK, -}; -static const unsigned int msiof2_sync_b_pins[] = { - /* SYNC */ - RCAR_GP_PIN(0, 5), -}; -static const unsigned int msiof2_sync_b_mux[] = { - MSIOF2_SYNC_B_MARK, -}; -static const unsigned int msiof2_ss1_b_pins[] = { - /* SS1 */ - RCAR_GP_PIN(0, 0), -}; -static const unsigned int msiof2_ss1_b_mux[] = { - MSIOF2_SS1_B_MARK, -}; -static const unsigned int msiof2_ss2_b_pins[] = { - /* SS2 */ - RCAR_GP_PIN(0, 1), -}; -static const unsigned int msiof2_ss2_b_mux[] = { - MSIOF2_SS2_B_MARK, -}; -static const unsigned int msiof2_txd_b_pins[] = { - /* TXD */ - RCAR_GP_PIN(0, 7), -}; -static const unsigned int msiof2_txd_b_mux[] = { - MSIOF2_TXD_B_MARK, -}; -static const unsigned int msiof2_rxd_b_pins[] = { - /* RXD */ - RCAR_GP_PIN(0, 6), -}; -static const unsigned int msiof2_rxd_b_mux[] = { - MSIOF2_RXD_B_MARK, -}; -static const unsigned int msiof2_clk_c_pins[] = { - /* SCK */ - RCAR_GP_PIN(2, 12), -}; -static const unsigned int msiof2_clk_c_mux[] = { - MSIOF2_SCK_C_MARK, -}; -static const unsigned int msiof2_sync_c_pins[] = { - /* SYNC */ - RCAR_GP_PIN(2, 11), -}; -static const unsigned int msiof2_sync_c_mux[] = { - MSIOF2_SYNC_C_MARK, -}; -static const unsigned int msiof2_ss1_c_pins[] = { - /* SS1 */ - RCAR_GP_PIN(2, 10), -}; -static const unsigned int msiof2_ss1_c_mux[] = { - MSIOF2_SS1_C_MARK, -}; -static const unsigned int msiof2_ss2_c_pins[] = { - /* SS2 */ - RCAR_GP_PIN(2, 9), -}; -static const unsigned int msiof2_ss2_c_mux[] = { - MSIOF2_SS2_C_MARK, -}; -static const unsigned int msiof2_txd_c_pins[] = { - /* TXD */ - RCAR_GP_PIN(2, 14), -}; -static const unsigned int msiof2_txd_c_mux[] = { - MSIOF2_TXD_C_MARK, -}; -static const unsigned int msiof2_rxd_c_pins[] = { - /* RXD */ - RCAR_GP_PIN(2, 13), -}; -static const unsigned int msiof2_rxd_c_mux[] = { - MSIOF2_RXD_C_MARK, -}; -static const unsigned int msiof2_clk_d_pins[] = { - /* SCK */ - RCAR_GP_PIN(0, 8), -}; -static const unsigned int msiof2_clk_d_mux[] = { - MSIOF2_SCK_D_MARK, -}; -static const unsigned int msiof2_sync_d_pins[] = { - /* SYNC */ - RCAR_GP_PIN(0, 9), -}; -static const unsigned int msiof2_sync_d_mux[] = { - MSIOF2_SYNC_D_MARK, -}; -static const unsigned int msiof2_ss1_d_pins[] = { - /* SS1 */ - RCAR_GP_PIN(0, 12), -}; -static const unsigned int msiof2_ss1_d_mux[] = { - MSIOF2_SS1_D_MARK, -}; -static const unsigned int msiof2_ss2_d_pins[] = { - /* SS2 */ - RCAR_GP_PIN(0, 13), -}; -static const unsigned int msiof2_ss2_d_mux[] = { - MSIOF2_SS2_D_MARK, -}; -static const unsigned int msiof2_txd_d_pins[] = { - /* TXD */ - RCAR_GP_PIN(0, 11), -}; -static const unsigned int msiof2_txd_d_mux[] = { - MSIOF2_TXD_D_MARK, -}; -static const unsigned int msiof2_rxd_d_pins[] = { - /* RXD */ - RCAR_GP_PIN(0, 10), -}; -static const unsigned int msiof2_rxd_d_mux[] = { - MSIOF2_RXD_D_MARK, -}; -/* - MSIOF3 ----------------------------------------------------------------- */ -static const unsigned int msiof3_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(0, 0), -}; -static const unsigned int msiof3_clk_a_mux[] = { - MSIOF3_SCK_A_MARK, -}; -static const unsigned int msiof3_sync_a_pins[] = { - /* SYNC */ - RCAR_GP_PIN(0, 1), -}; -static const unsigned int msiof3_sync_a_mux[] = { - MSIOF3_SYNC_A_MARK, -}; -static const unsigned int msiof3_ss1_a_pins[] = { - /* SS1 */ - RCAR_GP_PIN(0, 14), -}; -static const unsigned int msiof3_ss1_a_mux[] = { - MSIOF3_SS1_A_MARK, -}; -static const unsigned int msiof3_ss2_a_pins[] = { - /* SS2 */ - RCAR_GP_PIN(0, 15), -}; -static const unsigned int msiof3_ss2_a_mux[] = { - MSIOF3_SS2_A_MARK, -}; -static const unsigned int msiof3_txd_a_pins[] = { - /* TXD */ - RCAR_GP_PIN(0, 3), -}; -static const unsigned int msiof3_txd_a_mux[] = { - MSIOF3_TXD_A_MARK, -}; -static const unsigned int msiof3_rxd_a_pins[] = { - /* RXD */ - RCAR_GP_PIN(0, 2), -}; -static const unsigned int msiof3_rxd_a_mux[] = { - MSIOF3_RXD_A_MARK, -}; -static const unsigned int msiof3_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 2), -}; -static const unsigned int msiof3_clk_b_mux[] = { - MSIOF3_SCK_B_MARK, -}; -static const unsigned int msiof3_sync_b_pins[] = { - /* SYNC */ - RCAR_GP_PIN(1, 0), -}; -static const unsigned int msiof3_sync_b_mux[] = { - MSIOF3_SYNC_B_MARK, -}; -static const unsigned int msiof3_ss1_b_pins[] = { - /* SS1 */ - RCAR_GP_PIN(1, 4), -}; -static const unsigned int msiof3_ss1_b_mux[] = { - MSIOF3_SS1_B_MARK, -}; -static const unsigned int msiof3_ss2_b_pins[] = { - /* SS2 */ - RCAR_GP_PIN(1, 5), -}; -static const unsigned int msiof3_ss2_b_mux[] = { - MSIOF3_SS2_B_MARK, -}; -static const unsigned int msiof3_txd_b_pins[] = { - /* TXD */ - RCAR_GP_PIN(1, 1), -}; -static const unsigned int msiof3_txd_b_mux[] = { - MSIOF3_TXD_B_MARK, -}; -static const unsigned int msiof3_rxd_b_pins[] = { - /* RXD */ - RCAR_GP_PIN(1, 3), -}; -static const unsigned int msiof3_rxd_b_mux[] = { - MSIOF3_RXD_B_MARK, -}; -static const unsigned int msiof3_clk_c_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 12), -}; -static const unsigned int msiof3_clk_c_mux[] = { - MSIOF3_SCK_C_MARK, -}; -static const unsigned int msiof3_sync_c_pins[] = { - /* SYNC */ - RCAR_GP_PIN(1, 13), -}; -static const unsigned int msiof3_sync_c_mux[] = { - MSIOF3_SYNC_C_MARK, -}; -static const unsigned int msiof3_txd_c_pins[] = { - /* TXD */ - RCAR_GP_PIN(1, 15), -}; -static const unsigned int msiof3_txd_c_mux[] = { - MSIOF3_TXD_C_MARK, -}; -static const unsigned int msiof3_rxd_c_pins[] = { - /* RXD */ - RCAR_GP_PIN(1, 14), -}; -static const unsigned int msiof3_rxd_c_mux[] = { - MSIOF3_RXD_C_MARK, -}; -static const unsigned int msiof3_clk_d_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 22), -}; -static const unsigned int msiof3_clk_d_mux[] = { - MSIOF3_SCK_D_MARK, -}; -static const unsigned int msiof3_sync_d_pins[] = { - /* SYNC */ - RCAR_GP_PIN(1, 23), -}; -static const unsigned int msiof3_sync_d_mux[] = { - MSIOF3_SYNC_D_MARK, -}; -static const unsigned int msiof3_ss1_d_pins[] = { - /* SS1 */ - RCAR_GP_PIN(1, 26), -}; -static const unsigned int msiof3_ss1_d_mux[] = { - MSIOF3_SS1_D_MARK, -}; -static const unsigned int msiof3_txd_d_pins[] = { - /* TXD */ - RCAR_GP_PIN(1, 25), -}; -static const unsigned int msiof3_txd_d_mux[] = { - MSIOF3_TXD_D_MARK, -}; -static const unsigned int msiof3_rxd_d_pins[] = { - /* RXD */ - RCAR_GP_PIN(1, 24), -}; -static const unsigned int msiof3_rxd_d_mux[] = { - MSIOF3_RXD_D_MARK, -}; - -/* - PWM0 --------------------------------------------------------------------*/ -static const unsigned int pwm0_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 6), -}; -static const unsigned int pwm0_mux[] = { - PWM0_MARK, -}; -/* - PWM1 --------------------------------------------------------------------*/ -static const unsigned int pwm1_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 7), -}; -static const unsigned int pwm1_a_mux[] = { - PWM1_A_MARK, -}; -static const unsigned int pwm1_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 8), -}; -static const unsigned int pwm1_b_mux[] = { - PWM1_B_MARK, -}; -/* - PWM2 --------------------------------------------------------------------*/ -static const unsigned int pwm2_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 8), -}; -static const unsigned int pwm2_a_mux[] = { - PWM2_A_MARK, -}; -static const unsigned int pwm2_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 11), -}; -static const unsigned int pwm2_b_mux[] = { - PWM2_B_MARK, -}; -/* - PWM3 --------------------------------------------------------------------*/ -static const unsigned int pwm3_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 0), -}; -static const unsigned int pwm3_a_mux[] = { - PWM3_A_MARK, -}; -static const unsigned int pwm3_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 2), -}; -static const unsigned int pwm3_b_mux[] = { - PWM3_B_MARK, -}; -/* - PWM4 --------------------------------------------------------------------*/ -static const unsigned int pwm4_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 1), -}; -static const unsigned int pwm4_a_mux[] = { - PWM4_A_MARK, -}; -static const unsigned int pwm4_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 3), -}; -static const unsigned int pwm4_b_mux[] = { - PWM4_B_MARK, -}; -/* - PWM5 --------------------------------------------------------------------*/ -static const unsigned int pwm5_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 2), -}; -static const unsigned int pwm5_a_mux[] = { - PWM5_A_MARK, -}; -static const unsigned int pwm5_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 4), -}; -static const unsigned int pwm5_b_mux[] = { - PWM5_B_MARK, -}; -/* - PWM6 --------------------------------------------------------------------*/ -static const unsigned int pwm6_a_pins[] = { - /* PWM */ - RCAR_GP_PIN(1, 3), -}; -static const unsigned int pwm6_a_mux[] = { - PWM6_A_MARK, -}; -static const unsigned int pwm6_b_pins[] = { - /* PWM */ - RCAR_GP_PIN(2, 5), -}; -static const unsigned int pwm6_b_mux[] = { - PWM6_B_MARK, -}; - -/* - QSPI0 ------------------------------------------------------------------ */ -static const unsigned int qspi0_ctrl_pins[] = { - /* QSPI0_SPCLK, QSPI0_SSL */ - PIN_QSPI0_SPCLK, PIN_QSPI0_SSL, -}; -static const unsigned int qspi0_ctrl_mux[] = { - QSPI0_SPCLK_MARK, QSPI0_SSL_MARK, -}; -static const unsigned int qspi0_data_pins[] = { - /* QSPI0_MOSI_IO0, QSPI0_MISO_IO1, QSPI0_IO2, QSPI0_IO3 */ - PIN_QSPI0_MOSI_IO0, PIN_QSPI0_MISO_IO1, PIN_QSPI0_IO2, PIN_QSPI0_IO3, -}; -static const unsigned int qspi0_data_mux[] = { - QSPI0_MOSI_IO0_MARK, QSPI0_MISO_IO1_MARK, - QSPI0_IO2_MARK, QSPI0_IO3_MARK, -}; -/* - QSPI1 ------------------------------------------------------------------ */ -static const unsigned int qspi1_ctrl_pins[] = { - /* QSPI1_SPCLK, QSPI1_SSL */ - PIN_QSPI1_SPCLK, PIN_QSPI1_SSL, -}; -static const unsigned int qspi1_ctrl_mux[] = { - QSPI1_SPCLK_MARK, QSPI1_SSL_MARK, -}; -static const unsigned int qspi1_data_pins[] = { - /* QSPI1_MOSI_IO0, QSPI1_MISO_IO1, QSPI1_IO2, QSPI1_IO3 */ - PIN_QSPI1_MOSI_IO0, PIN_QSPI1_MISO_IO1, PIN_QSPI1_IO2, PIN_QSPI1_IO3, -}; -static const unsigned int qspi1_data_mux[] = { - QSPI1_MOSI_IO0_MARK, QSPI1_MISO_IO1_MARK, - QSPI1_IO2_MARK, QSPI1_IO3_MARK, -}; - -/* - SATA --------------------------------------------------------------------*/ -static const unsigned int sata0_devslp_a_pins[] = { - /* DEVSLP */ - RCAR_GP_PIN(6, 16), -}; -static const unsigned int sata0_devslp_a_mux[] = { - SATA_DEVSLP_A_MARK, -}; -static const unsigned int sata0_devslp_b_pins[] = { - /* DEVSLP */ - RCAR_GP_PIN(4, 6), -}; -static const unsigned int sata0_devslp_b_mux[] = { - SATA_DEVSLP_B_MARK, -}; - -/* - SCIF0 ------------------------------------------------------------------ */ -static const unsigned int scif0_data_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2), -}; -static const unsigned int scif0_data_mux[] = { - RX0_MARK, TX0_MARK, -}; -static const unsigned int scif0_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 0), -}; -static const unsigned int scif0_clk_mux[] = { - SCK0_MARK, -}; -static const unsigned int scif0_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3), -}; -static const unsigned int scif0_ctrl_mux[] = { - RTS0_N_MARK, CTS0_N_MARK, -}; -/* - SCIF1 ------------------------------------------------------------------ */ -static const unsigned int scif1_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6), -}; -static const unsigned int scif1_data_a_mux[] = { - RX1_A_MARK, TX1_A_MARK, -}; -static const unsigned int scif1_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int scif1_clk_mux[] = { - SCK1_MARK, -}; -static const unsigned int scif1_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7), -}; -static const unsigned int scif1_ctrl_mux[] = { - RTS1_N_MARK, CTS1_N_MARK, -}; - -static const unsigned int scif1_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 24), RCAR_GP_PIN(5, 25), -}; -static const unsigned int scif1_data_b_mux[] = { - RX1_B_MARK, TX1_B_MARK, -}; -/* - SCIF2 ------------------------------------------------------------------ */ -static const unsigned int scif2_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 11), RCAR_GP_PIN(5, 10), -}; -static const unsigned int scif2_data_a_mux[] = { - RX2_A_MARK, TX2_A_MARK, -}; -static const unsigned int scif2_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(5, 9), -}; -static const unsigned int scif2_clk_mux[] = { - SCK2_MARK, -}; -static const unsigned int scif2_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 16), -}; -static const unsigned int scif2_data_b_mux[] = { - RX2_B_MARK, TX2_B_MARK, -}; -/* - SCIF3 ------------------------------------------------------------------ */ -static const unsigned int scif3_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24), -}; -static const unsigned int scif3_data_a_mux[] = { - RX3_A_MARK, TX3_A_MARK, -}; -static const unsigned int scif3_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 22), -}; -static const unsigned int scif3_clk_mux[] = { - SCK3_MARK, -}; -static const unsigned int scif3_ctrl_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25), -}; -static const unsigned int scif3_ctrl_mux[] = { - RTS3_N_MARK, CTS3_N_MARK, -}; -static const unsigned int scif3_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11), -}; -static const unsigned int scif3_data_b_mux[] = { - RX3_B_MARK, TX3_B_MARK, -}; -/* - SCIF4 ------------------------------------------------------------------ */ -static const unsigned int scif4_data_a_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(2, 11), RCAR_GP_PIN(2, 12), -}; -static const unsigned int scif4_data_a_mux[] = { - RX4_A_MARK, TX4_A_MARK, -}; -static const unsigned int scif4_clk_a_pins[] = { - /* SCK */ - RCAR_GP_PIN(2, 10), -}; -static const unsigned int scif4_clk_a_mux[] = { - SCK4_A_MARK, -}; -static const unsigned int scif4_ctrl_a_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(2, 14), RCAR_GP_PIN(2, 13), -}; -static const unsigned int scif4_ctrl_a_mux[] = { - RTS4_N_A_MARK, CTS4_N_A_MARK, -}; -static const unsigned int scif4_data_b_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), -}; -static const unsigned int scif4_data_b_mux[] = { - RX4_B_MARK, TX4_B_MARK, -}; -static const unsigned int scif4_clk_b_pins[] = { - /* SCK */ - RCAR_GP_PIN(1, 5), -}; -static const unsigned int scif4_clk_b_mux[] = { - SCK4_B_MARK, -}; -static const unsigned int scif4_ctrl_b_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(1, 10), RCAR_GP_PIN(1, 9), -}; -static const unsigned int scif4_ctrl_b_mux[] = { - RTS4_N_B_MARK, CTS4_N_B_MARK, -}; -static const unsigned int scif4_data_c_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 13), -}; -static const unsigned int scif4_data_c_mux[] = { - RX4_C_MARK, TX4_C_MARK, -}; -static const unsigned int scif4_clk_c_pins[] = { - /* SCK */ - RCAR_GP_PIN(0, 8), -}; -static const unsigned int scif4_clk_c_mux[] = { - SCK4_C_MARK, -}; -static const unsigned int scif4_ctrl_c_pins[] = { - /* RTS, CTS */ - RCAR_GP_PIN(0, 11), RCAR_GP_PIN(0, 10), -}; -static const unsigned int scif4_ctrl_c_mux[] = { - RTS4_N_C_MARK, CTS4_N_C_MARK, -}; -/* - SCIF5 ------------------------------------------------------------------ */ -static const unsigned int scif5_data_pins[] = { - /* RX, TX */ - RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21), -}; -static const unsigned int scif5_data_mux[] = { - RX5_MARK, TX5_MARK, -}; -static const unsigned int scif5_clk_pins[] = { - /* SCK */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int scif5_clk_mux[] = { - SCK5_MARK, -}; - -/* - SCIF Clock ------------------------------------------------------------- */ -static const unsigned int scif_clk_a_pins[] = { - /* SCIF_CLK */ - RCAR_GP_PIN(6, 23), -}; -static const unsigned int scif_clk_a_mux[] = { - SCIF_CLK_A_MARK, -}; -static const unsigned int scif_clk_b_pins[] = { - /* SCIF_CLK */ - RCAR_GP_PIN(5, 9), -}; -static const unsigned int scif_clk_b_mux[] = { - SCIF_CLK_B_MARK, -}; - -/* - SDHI0 ------------------------------------------------------------------ */ -static const unsigned int sdhi0_data_pins[] = { - /* D[0:3] */ - RCAR_GP_PIN(3, 2), RCAR_GP_PIN(3, 3), - RCAR_GP_PIN(3, 4), RCAR_GP_PIN(3, 5), -}; -static const unsigned int sdhi0_data_mux[] = { - SD0_DAT0_MARK, SD0_DAT1_MARK, - SD0_DAT2_MARK, SD0_DAT3_MARK, -}; -static const unsigned int sdhi0_ctrl_pins[] = { - /* CLK, CMD */ - RCAR_GP_PIN(3, 0), RCAR_GP_PIN(3, 1), -}; -static const unsigned int sdhi0_ctrl_mux[] = { - SD0_CLK_MARK, SD0_CMD_MARK, -}; -static const unsigned int sdhi0_cd_pins[] = { - /* CD */ - RCAR_GP_PIN(3, 12), -}; -static const unsigned int sdhi0_cd_mux[] = { - SD0_CD_MARK, -}; -static const unsigned int sdhi0_wp_pins[] = { - /* WP */ - RCAR_GP_PIN(3, 13), -}; -static const unsigned int sdhi0_wp_mux[] = { - SD0_WP_MARK, -}; -/* - SDHI1 ------------------------------------------------------------------ */ -static const unsigned int sdhi1_data_pins[] = { - /* D[0:3] */ - RCAR_GP_PIN(3, 8), RCAR_GP_PIN(3, 9), - RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11), -}; -static const unsigned int sdhi1_data_mux[] = { - SD1_DAT0_MARK, SD1_DAT1_MARK, - SD1_DAT2_MARK, SD1_DAT3_MARK, -}; -static const unsigned int sdhi1_ctrl_pins[] = { - /* CLK, CMD */ - RCAR_GP_PIN(3, 6), RCAR_GP_PIN(3, 7), -}; -static const unsigned int sdhi1_ctrl_mux[] = { - SD1_CLK_MARK, SD1_CMD_MARK, -}; -static const unsigned int sdhi1_cd_pins[] = { - /* CD */ - RCAR_GP_PIN(3, 14), -}; -static const unsigned int sdhi1_cd_mux[] = { - SD1_CD_MARK, -}; -static const unsigned int sdhi1_wp_pins[] = { - /* WP */ - RCAR_GP_PIN(3, 15), -}; -static const unsigned int sdhi1_wp_mux[] = { - SD1_WP_MARK, -}; -/* - SDHI2 ------------------------------------------------------------------ */ -static const unsigned int sdhi2_data_pins[] = { - /* D[0:7] */ - RCAR_GP_PIN(4, 2), RCAR_GP_PIN(4, 3), - RCAR_GP_PIN(4, 4), RCAR_GP_PIN(4, 5), - RCAR_GP_PIN(3, 8), RCAR_GP_PIN(3, 9), - RCAR_GP_PIN(3, 10), RCAR_GP_PIN(3, 11), -}; -static const unsigned int sdhi2_data_mux[] = { - SD2_DAT0_MARK, SD2_DAT1_MARK, - SD2_DAT2_MARK, SD2_DAT3_MARK, - SD2_DAT4_MARK, SD2_DAT5_MARK, - SD2_DAT6_MARK, SD2_DAT7_MARK, -}; -static const unsigned int sdhi2_ctrl_pins[] = { - /* CLK, CMD */ - RCAR_GP_PIN(4, 0), RCAR_GP_PIN(4, 1), -}; -static const unsigned int sdhi2_ctrl_mux[] = { - SD2_CLK_MARK, SD2_CMD_MARK, -}; -static const unsigned int sdhi2_cd_a_pins[] = { - /* CD */ - RCAR_GP_PIN(4, 13), -}; -static const unsigned int sdhi2_cd_a_mux[] = { - SD2_CD_A_MARK, -}; -static const unsigned int sdhi2_cd_b_pins[] = { - /* CD */ - RCAR_GP_PIN(5, 10), -}; -static const unsigned int sdhi2_cd_b_mux[] = { - SD2_CD_B_MARK, -}; -static const unsigned int sdhi2_wp_a_pins[] = { - /* WP */ - RCAR_GP_PIN(4, 14), -}; -static const unsigned int sdhi2_wp_a_mux[] = { - SD2_WP_A_MARK, -}; -static const unsigned int sdhi2_wp_b_pins[] = { - /* WP */ - RCAR_GP_PIN(5, 11), -}; -static const unsigned int sdhi2_wp_b_mux[] = { - SD2_WP_B_MARK, -}; -static const unsigned int sdhi2_ds_pins[] = { - /* DS */ - RCAR_GP_PIN(4, 6), -}; -static const unsigned int sdhi2_ds_mux[] = { - SD2_DS_MARK, -}; -/* - SDHI3 ------------------------------------------------------------------ */ -static const unsigned int sdhi3_data_pins[] = { - /* D[0:7] */ - RCAR_GP_PIN(4, 9), RCAR_GP_PIN(4, 10), - RCAR_GP_PIN(4, 11), RCAR_GP_PIN(4, 12), - RCAR_GP_PIN(4, 13), RCAR_GP_PIN(4, 14), - RCAR_GP_PIN(4, 15), RCAR_GP_PIN(4, 16), -}; -static const unsigned int sdhi3_data_mux[] = { - SD3_DAT0_MARK, SD3_DAT1_MARK, - SD3_DAT2_MARK, SD3_DAT3_MARK, - SD3_DAT4_MARK, SD3_DAT5_MARK, - SD3_DAT6_MARK, SD3_DAT7_MARK, -}; -static const unsigned int sdhi3_ctrl_pins[] = { - /* CLK, CMD */ - RCAR_GP_PIN(4, 7), RCAR_GP_PIN(4, 8), -}; -static const unsigned int sdhi3_ctrl_mux[] = { - SD3_CLK_MARK, SD3_CMD_MARK, -}; -static const unsigned int sdhi3_cd_pins[] = { - /* CD */ - RCAR_GP_PIN(4, 15), -}; -static const unsigned int sdhi3_cd_mux[] = { - SD3_CD_MARK, -}; -static const unsigned int sdhi3_wp_pins[] = { - /* WP */ - RCAR_GP_PIN(4, 16), -}; -static const unsigned int sdhi3_wp_mux[] = { - SD3_WP_MARK, -}; -static const unsigned int sdhi3_ds_pins[] = { - /* DS */ - RCAR_GP_PIN(4, 17), -}; -static const unsigned int sdhi3_ds_mux[] = { - SD3_DS_MARK, -}; - -/* - SSI -------------------------------------------------------------------- */ -static const unsigned int ssi0_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 2), -}; -static const unsigned int ssi0_data_mux[] = { - SSI_SDATA0_MARK, -}; -static const unsigned int ssi01239_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 0), RCAR_GP_PIN(6, 1), -}; -static const unsigned int ssi01239_ctrl_mux[] = { - SSI_SCK01239_MARK, SSI_WS01239_MARK, -}; -static const unsigned int ssi1_data_a_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 3), -}; -static const unsigned int ssi1_data_a_mux[] = { - SSI_SDATA1_A_MARK, -}; -static const unsigned int ssi1_data_b_pins[] = { - /* SDATA */ - RCAR_GP_PIN(5, 12), -}; -static const unsigned int ssi1_data_b_mux[] = { - SSI_SDATA1_B_MARK, -}; -static const unsigned int ssi1_ctrl_a_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27), -}; -static const unsigned int ssi1_ctrl_a_mux[] = { - SSI_SCK1_A_MARK, SSI_WS1_A_MARK, -}; -static const unsigned int ssi1_ctrl_b_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 4), RCAR_GP_PIN(6, 21), -}; -static const unsigned int ssi1_ctrl_b_mux[] = { - SSI_SCK1_B_MARK, SSI_WS1_B_MARK, -}; -static const unsigned int ssi2_data_a_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 4), -}; -static const unsigned int ssi2_data_a_mux[] = { - SSI_SDATA2_A_MARK, -}; -static const unsigned int ssi2_data_b_pins[] = { - /* SDATA */ - RCAR_GP_PIN(5, 13), -}; -static const unsigned int ssi2_data_b_mux[] = { - SSI_SDATA2_B_MARK, -}; -static const unsigned int ssi2_ctrl_a_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(5, 19), RCAR_GP_PIN(5, 21), -}; -static const unsigned int ssi2_ctrl_a_mux[] = { - SSI_SCK2_A_MARK, SSI_WS2_A_MARK, -}; -static const unsigned int ssi2_ctrl_b_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 29), -}; -static const unsigned int ssi2_ctrl_b_mux[] = { - SSI_SCK2_B_MARK, SSI_WS2_B_MARK, -}; -static const unsigned int ssi3_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 7), -}; -static const unsigned int ssi3_data_mux[] = { - SSI_SDATA3_MARK, -}; -static const unsigned int ssi349_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 5), RCAR_GP_PIN(6, 6), -}; -static const unsigned int ssi349_ctrl_mux[] = { - SSI_SCK349_MARK, SSI_WS349_MARK, -}; -static const unsigned int ssi4_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 10), -}; -static const unsigned int ssi4_data_mux[] = { - SSI_SDATA4_MARK, -}; -static const unsigned int ssi4_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9), -}; -static const unsigned int ssi4_ctrl_mux[] = { - SSI_SCK4_MARK, SSI_WS4_MARK, -}; -static const unsigned int ssi5_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 13), -}; -static const unsigned int ssi5_data_mux[] = { - SSI_SDATA5_MARK, -}; -static const unsigned int ssi5_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12), -}; -static const unsigned int ssi5_ctrl_mux[] = { - SSI_SCK5_MARK, SSI_WS5_MARK, -}; -static const unsigned int ssi6_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 16), -}; -static const unsigned int ssi6_data_mux[] = { - SSI_SDATA6_MARK, -}; -static const unsigned int ssi6_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15), -}; -static const unsigned int ssi6_ctrl_mux[] = { - SSI_SCK6_MARK, SSI_WS6_MARK, -}; -static const unsigned int ssi7_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 19), -}; -static const unsigned int ssi7_data_mux[] = { - SSI_SDATA7_MARK, -}; -static const unsigned int ssi78_ctrl_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18), -}; -static const unsigned int ssi78_ctrl_mux[] = { - SSI_SCK78_MARK, SSI_WS78_MARK, -}; -static const unsigned int ssi8_data_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 20), -}; -static const unsigned int ssi8_data_mux[] = { - SSI_SDATA8_MARK, -}; -static const unsigned int ssi9_data_a_pins[] = { - /* SDATA */ - RCAR_GP_PIN(6, 21), -}; -static const unsigned int ssi9_data_a_mux[] = { - SSI_SDATA9_A_MARK, -}; -static const unsigned int ssi9_data_b_pins[] = { - /* SDATA */ - RCAR_GP_PIN(5, 14), -}; -static const unsigned int ssi9_data_b_mux[] = { - SSI_SDATA9_B_MARK, -}; -static const unsigned int ssi9_ctrl_a_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(5, 15), RCAR_GP_PIN(5, 16), -}; -static const unsigned int ssi9_ctrl_a_mux[] = { - SSI_SCK9_A_MARK, SSI_WS9_A_MARK, -}; -static const unsigned int ssi9_ctrl_b_pins[] = { - /* SCK, WS */ - RCAR_GP_PIN(6, 30), RCAR_GP_PIN(6, 31), -}; -static const unsigned int ssi9_ctrl_b_mux[] = { - SSI_SCK9_B_MARK, SSI_WS9_B_MARK, -}; - -/* - TMU -------------------------------------------------------------------- */ -static const unsigned int tmu_tclk1_a_pins[] = { - /* TCLK */ - RCAR_GP_PIN(6, 23), -}; -static const unsigned int tmu_tclk1_a_mux[] = { - TCLK1_A_MARK, -}; -static const unsigned int tmu_tclk1_b_pins[] = { - /* TCLK */ - RCAR_GP_PIN(5, 19), -}; -static const unsigned int tmu_tclk1_b_mux[] = { - TCLK1_B_MARK, -}; -static const unsigned int tmu_tclk2_a_pins[] = { - /* TCLK */ - RCAR_GP_PIN(6, 19), -}; -static const unsigned int tmu_tclk2_a_mux[] = { - TCLK2_A_MARK, -}; -static const unsigned int tmu_tclk2_b_pins[] = { - /* TCLK */ - RCAR_GP_PIN(6, 28), -}; -static const unsigned int tmu_tclk2_b_mux[] = { - TCLK2_B_MARK, -}; - -/* - TPU ------------------------------------------------------------------- */ -static const unsigned int tpu_to0_pins[] = { - /* TPU0TO0 */ - RCAR_GP_PIN(6, 28), -}; -static const unsigned int tpu_to0_mux[] = { - TPU0TO0_MARK, -}; -static const unsigned int tpu_to1_pins[] = { - /* TPU0TO1 */ - RCAR_GP_PIN(6, 29), -}; -static const unsigned int tpu_to1_mux[] = { - TPU0TO1_MARK, -}; -static const unsigned int tpu_to2_pins[] = { - /* TPU0TO2 */ - RCAR_GP_PIN(6, 30), -}; -static const unsigned int tpu_to2_mux[] = { - TPU0TO2_MARK, -}; -static const unsigned int tpu_to3_pins[] = { - /* TPU0TO3 */ - RCAR_GP_PIN(6, 31), -}; -static const unsigned int tpu_to3_mux[] = { - TPU0TO3_MARK, -}; - -/* - USB0 ------------------------------------------------------------------- */ -static const unsigned int usb0_pins[] = { - /* PWEN, OVC */ - RCAR_GP_PIN(6, 24), RCAR_GP_PIN(6, 25), -}; -static const unsigned int usb0_mux[] = { - USB0_PWEN_MARK, USB0_OVC_MARK, -}; -/* - USB1 ------------------------------------------------------------------- */ -static const unsigned int usb1_pins[] = { - /* PWEN, OVC */ - RCAR_GP_PIN(6, 26), RCAR_GP_PIN(6, 27), -}; -static const unsigned int usb1_mux[] = { - USB1_PWEN_MARK, USB1_OVC_MARK, -}; -/* - USB2 ------------------------------------------------------------------- */ -static const unsigned int usb2_pins[] = { - /* PWEN, OVC */ - RCAR_GP_PIN(6, 14), RCAR_GP_PIN(6, 15), -}; -static const unsigned int usb2_mux[] = { - USB2_PWEN_MARK, USB2_OVC_MARK, -}; - -/* - USB30 ------------------------------------------------------------------ */ -static const unsigned int usb30_pins[] = { - /* PWEN, OVC */ - RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 29), -}; -static const unsigned int usb30_mux[] = { - USB30_PWEN_MARK, USB30_OVC_MARK, -}; -/* - USB31 ------------------------------------------------------------------ */ -static const unsigned int usb31_pins[] = { - /* PWEN, OVC */ - RCAR_GP_PIN(6, 30), RCAR_GP_PIN(6, 31), -}; -static const unsigned int usb31_mux[] = { - USB31_PWEN_MARK, USB31_OVC_MARK, -}; - -/* - VIN4 ------------------------------------------------------------------- */ -static const unsigned int vin4_data18_a_pins[] = { - RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11), - RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 13), - RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15), - RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), - RCAR_GP_PIN(0, 2), RCAR_GP_PIN(0, 3), - RCAR_GP_PIN(0, 4), RCAR_GP_PIN(0, 5), - RCAR_GP_PIN(0, 6), RCAR_GP_PIN(0, 7), -}; -static const unsigned int vin4_data18_a_mux[] = { - VI4_DATA2_A_MARK, VI4_DATA3_A_MARK, - VI4_DATA4_A_MARK, VI4_DATA5_A_MARK, - VI4_DATA6_A_MARK, VI4_DATA7_A_MARK, - VI4_DATA10_MARK, VI4_DATA11_MARK, - VI4_DATA12_MARK, VI4_DATA13_MARK, - VI4_DATA14_MARK, VI4_DATA15_MARK, - VI4_DATA18_MARK, VI4_DATA19_MARK, - VI4_DATA20_MARK, VI4_DATA21_MARK, - VI4_DATA22_MARK, VI4_DATA23_MARK, -}; -static const unsigned int vin4_data18_b_pins[] = { - RCAR_GP_PIN(2, 2), RCAR_GP_PIN(2, 3), - RCAR_GP_PIN(2, 4), RCAR_GP_PIN(2, 5), - RCAR_GP_PIN(2, 6), RCAR_GP_PIN(2, 7), - RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), - RCAR_GP_PIN(0, 2), RCAR_GP_PIN(0, 3), - RCAR_GP_PIN(0, 4), RCAR_GP_PIN(0, 5), - RCAR_GP_PIN(0, 6), RCAR_GP_PIN(0, 7), -}; -static const unsigned int vin4_data18_b_mux[] = { - VI4_DATA2_B_MARK, VI4_DATA3_B_MARK, - VI4_DATA4_B_MARK, VI4_DATA5_B_MARK, - VI4_DATA6_B_MARK, VI4_DATA7_B_MARK, - VI4_DATA10_MARK, VI4_DATA11_MARK, - VI4_DATA12_MARK, VI4_DATA13_MARK, - VI4_DATA14_MARK, VI4_DATA15_MARK, - VI4_DATA18_MARK, VI4_DATA19_MARK, - VI4_DATA20_MARK, VI4_DATA21_MARK, - VI4_DATA22_MARK, VI4_DATA23_MARK, -}; -static const unsigned int vin4_data_a_pins[] = { - RCAR_GP_PIN(0, 8), RCAR_GP_PIN(0, 9), - RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11), - RCAR_GP_PIN(0, 12), RCAR_GP_PIN(0, 13), - RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15), - RCAR_GP_PIN(1, 0), RCAR_GP_PIN(1, 1), - RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), - RCAR_GP_PIN(0, 0), RCAR_GP_PIN(0, 1), - RCAR_GP_PIN(0, 2), RCAR_GP_PIN(0, 3), - RCAR_GP_PIN(0, 4), RCAR_GP_PIN(0, 5), - RCAR_GP_PIN(0, 6), RCAR_GP_PIN(0, 7), -}; -static const unsigned int vin4_data_a_mux[] = { - VI4_DATA0_A_MARK, VI4_DATA1_A_MARK, - VI4_DATA2_A_MARK, VI4_DATA3_A_MARK, - VI4_DATA4_A_MARK, VI4_DATA5_A_MARK, - VI4_DATA6_A_MARK, VI4_DATA7_A_MARK, - VI4_DATA8_MARK, VI4_DATA9_MARK, - VI4_DATA10_MARK, VI4_DATA11_MARK, - VI4_DATA12_MARK, VI4_DATA13_MARK, - VI4_DATA14_MARK, VI4_DATA15_MARK, - VI4_DATA16_MARK, VI4_DATA17_MARK, - VI4_DATA18_MARK, VI4_DATA19_MARK, - VI4_DATA20_MARK, VI4_DATA21_MARK, - VI4_DATA22_MARK, VI4_DATA23_MARK, -}; -static const unsigned int vin4_data_b_pins[] = { - RCAR_GP_PIN(2, 0), RCAR_GP_PIN(2, 1), - RCAR_GP_PIN(2, 2), RCAR_GP_PIN(2, 3), - RCAR_GP_PIN(2, 4), RCAR_GP_PIN(2, 5), - RCAR_GP_PIN(2, 6), RCAR_GP_PIN(2, 7), - RCAR_GP_PIN(1, 0), RCAR_GP_PIN(1, 1), - RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), - RCAR_GP_PIN(0, 0), RCAR_GP_PIN(0, 1), - RCAR_GP_PIN(0, 2), RCAR_GP_PIN(0, 3), - RCAR_GP_PIN(0, 4), RCAR_GP_PIN(0, 5), - RCAR_GP_PIN(0, 6), RCAR_GP_PIN(0, 7), -}; -static const unsigned int vin4_data_b_mux[] = { - VI4_DATA0_B_MARK, VI4_DATA1_B_MARK, - VI4_DATA2_B_MARK, VI4_DATA3_B_MARK, - VI4_DATA4_B_MARK, VI4_DATA5_B_MARK, - VI4_DATA6_B_MARK, VI4_DATA7_B_MARK, - VI4_DATA8_MARK, VI4_DATA9_MARK, - VI4_DATA10_MARK, VI4_DATA11_MARK, - VI4_DATA12_MARK, VI4_DATA13_MARK, - VI4_DATA14_MARK, VI4_DATA15_MARK, - VI4_DATA16_MARK, VI4_DATA17_MARK, - VI4_DATA18_MARK, VI4_DATA19_MARK, - VI4_DATA20_MARK, VI4_DATA21_MARK, - VI4_DATA22_MARK, VI4_DATA23_MARK, -}; -static const unsigned int vin4_sync_pins[] = { - /* HSYNC#, VSYNC# */ - RCAR_GP_PIN(1, 18), RCAR_GP_PIN(1, 17), -}; -static const unsigned int vin4_sync_mux[] = { - VI4_HSYNC_N_MARK, VI4_VSYNC_N_MARK, -}; -static const unsigned int vin4_field_pins[] = { - /* FIELD */ - RCAR_GP_PIN(1, 16), -}; -static const unsigned int vin4_field_mux[] = { - VI4_FIELD_MARK, -}; -static const unsigned int vin4_clkenb_pins[] = { - /* CLKENB */ - RCAR_GP_PIN(1, 19), -}; -static const unsigned int vin4_clkenb_mux[] = { - VI4_CLKENB_MARK, -}; -static const unsigned int vin4_clk_pins[] = { - /* CLK */ - RCAR_GP_PIN(1, 27), -}; -static const unsigned int vin4_clk_mux[] = { - VI4_CLK_MARK, -}; - -/* - VIN5 ------------------------------------------------------------------- */ -static const unsigned int vin5_data_pins[] = { - RCAR_GP_PIN(0, 0), RCAR_GP_PIN(0, 1), - RCAR_GP_PIN(0, 2), RCAR_GP_PIN(0, 3), - RCAR_GP_PIN(0, 4), RCAR_GP_PIN(0, 5), - RCAR_GP_PIN(0, 6), RCAR_GP_PIN(0, 7), - RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13), - RCAR_GP_PIN(1, 14), RCAR_GP_PIN(1, 15), - RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 5), - RCAR_GP_PIN(1, 6), RCAR_GP_PIN(1, 7), -}; -static const unsigned int vin5_data_mux[] = { - VI5_DATA0_MARK, VI5_DATA1_MARK, - VI5_DATA2_MARK, VI5_DATA3_MARK, - VI5_DATA4_MARK, VI5_DATA5_MARK, - VI5_DATA6_MARK, VI5_DATA7_MARK, - VI5_DATA8_MARK, VI5_DATA9_MARK, - VI5_DATA10_MARK, VI5_DATA11_MARK, - VI5_DATA12_MARK, VI5_DATA13_MARK, - VI5_DATA14_MARK, VI5_DATA15_MARK, -}; -static const unsigned int vin5_sync_pins[] = { - /* HSYNC#, VSYNC# */ - RCAR_GP_PIN(1, 10), RCAR_GP_PIN(1, 9), -}; -static const unsigned int vin5_sync_mux[] = { - VI5_HSYNC_N_MARK, VI5_VSYNC_N_MARK, -}; -static const unsigned int vin5_field_pins[] = { - RCAR_GP_PIN(1, 11), -}; -static const unsigned int vin5_field_mux[] = { - /* FIELD */ - VI5_FIELD_MARK, -}; -static const unsigned int vin5_clkenb_pins[] = { - RCAR_GP_PIN(1, 20), -}; -static const unsigned int vin5_clkenb_mux[] = { - /* CLKENB */ - VI5_CLKENB_MARK, -}; -static const unsigned int vin5_clk_pins[] = { - RCAR_GP_PIN(1, 21), -}; -static const unsigned int vin5_clk_mux[] = { - /* CLK */ - VI5_CLK_MARK, -}; - -static const struct sh_pfc_pin_group pinmux_groups[] = { - SH_PFC_PIN_GROUP(audio_clk_a_a), - SH_PFC_PIN_GROUP(audio_clk_a_b), - SH_PFC_PIN_GROUP(audio_clk_a_c), - SH_PFC_PIN_GROUP(audio_clk_b_a), - SH_PFC_PIN_GROUP(audio_clk_b_b), - SH_PFC_PIN_GROUP(audio_clk_c_a), - SH_PFC_PIN_GROUP(audio_clk_c_b), - SH_PFC_PIN_GROUP(audio_clkout_a), - SH_PFC_PIN_GROUP(audio_clkout_b), - SH_PFC_PIN_GROUP(audio_clkout_c), - SH_PFC_PIN_GROUP(audio_clkout_d), - SH_PFC_PIN_GROUP(audio_clkout1_a), - SH_PFC_PIN_GROUP(audio_clkout1_b), - SH_PFC_PIN_GROUP(audio_clkout2_a), - SH_PFC_PIN_GROUP(audio_clkout2_b), - SH_PFC_PIN_GROUP(audio_clkout3_a), - SH_PFC_PIN_GROUP(audio_clkout3_b), - SH_PFC_PIN_GROUP(avb_link), - SH_PFC_PIN_GROUP(avb_magic), - SH_PFC_PIN_GROUP(avb_phy_int), - SH_PFC_PIN_GROUP_ALIAS(avb_mdc, avb_mdio), /* Deprecated */ - SH_PFC_PIN_GROUP(avb_mdio), - SH_PFC_PIN_GROUP(avb_mii), - SH_PFC_PIN_GROUP(avb_avtp_pps), - SH_PFC_PIN_GROUP(avb_avtp_match_a), - SH_PFC_PIN_GROUP(avb_avtp_capture_a), - SH_PFC_PIN_GROUP(avb_avtp_match_b), - SH_PFC_PIN_GROUP(avb_avtp_capture_b), - SH_PFC_PIN_GROUP(can0_data_a), - SH_PFC_PIN_GROUP(can0_data_b), - SH_PFC_PIN_GROUP(can1_data), - SH_PFC_PIN_GROUP(can_clk), - SH_PFC_PIN_GROUP(canfd0_data_a), - SH_PFC_PIN_GROUP(canfd0_data_b), - SH_PFC_PIN_GROUP(canfd1_data), - SH_PFC_PIN_GROUP(drif0_ctrl_a), - SH_PFC_PIN_GROUP(drif0_data0_a), - SH_PFC_PIN_GROUP(drif0_data1_a), - SH_PFC_PIN_GROUP(drif0_ctrl_b), - SH_PFC_PIN_GROUP(drif0_data0_b), - SH_PFC_PIN_GROUP(drif0_data1_b), - SH_PFC_PIN_GROUP(drif0_ctrl_c), - SH_PFC_PIN_GROUP(drif0_data0_c), - SH_PFC_PIN_GROUP(drif0_data1_c), - SH_PFC_PIN_GROUP(drif1_ctrl_a), - SH_PFC_PIN_GROUP(drif1_data0_a), - SH_PFC_PIN_GROUP(drif1_data1_a), - SH_PFC_PIN_GROUP(drif1_ctrl_b), - SH_PFC_PIN_GROUP(drif1_data0_b), - SH_PFC_PIN_GROUP(drif1_data1_b), - SH_PFC_PIN_GROUP(drif1_ctrl_c), - SH_PFC_PIN_GROUP(drif1_data0_c), - SH_PFC_PIN_GROUP(drif1_data1_c), - SH_PFC_PIN_GROUP(drif2_ctrl_a), - SH_PFC_PIN_GROUP(drif2_data0_a), - SH_PFC_PIN_GROUP(drif2_data1_a), - SH_PFC_PIN_GROUP(drif2_ctrl_b), - SH_PFC_PIN_GROUP(drif2_data0_b), - SH_PFC_PIN_GROUP(drif2_data1_b), - SH_PFC_PIN_GROUP(drif3_ctrl_a), - SH_PFC_PIN_GROUP(drif3_data0_a), - SH_PFC_PIN_GROUP(drif3_data1_a), - SH_PFC_PIN_GROUP(drif3_ctrl_b), - SH_PFC_PIN_GROUP(drif3_data0_b), - SH_PFC_PIN_GROUP(drif3_data1_b), - SH_PFC_PIN_GROUP(du_rgb666), - SH_PFC_PIN_GROUP(du_rgb888), - SH_PFC_PIN_GROUP(du_clk_out_0), - SH_PFC_PIN_GROUP(du_clk_out_1), - SH_PFC_PIN_GROUP(du_sync), - SH_PFC_PIN_GROUP(du_oddf), - SH_PFC_PIN_GROUP(du_cde), - SH_PFC_PIN_GROUP(du_disp), - SH_PFC_PIN_GROUP(hscif0_data), - SH_PFC_PIN_GROUP(hscif0_clk), - SH_PFC_PIN_GROUP(hscif0_ctrl), - SH_PFC_PIN_GROUP(hscif1_data_a), - SH_PFC_PIN_GROUP(hscif1_clk_a), - SH_PFC_PIN_GROUP(hscif1_ctrl_a), - SH_PFC_PIN_GROUP(hscif1_data_b), - SH_PFC_PIN_GROUP(hscif1_clk_b), - SH_PFC_PIN_GROUP(hscif1_ctrl_b), - SH_PFC_PIN_GROUP(hscif2_data_a), - SH_PFC_PIN_GROUP(hscif2_clk_a), - SH_PFC_PIN_GROUP(hscif2_ctrl_a), - SH_PFC_PIN_GROUP(hscif2_data_b), - SH_PFC_PIN_GROUP(hscif2_clk_b), - SH_PFC_PIN_GROUP(hscif2_ctrl_b), - SH_PFC_PIN_GROUP(hscif3_data_a), - SH_PFC_PIN_GROUP(hscif3_clk), - SH_PFC_PIN_GROUP(hscif3_ctrl), - SH_PFC_PIN_GROUP(hscif3_data_b), - SH_PFC_PIN_GROUP(hscif3_data_c), - SH_PFC_PIN_GROUP(hscif3_data_d), - SH_PFC_PIN_GROUP(hscif4_data_a), - SH_PFC_PIN_GROUP(hscif4_clk), - SH_PFC_PIN_GROUP(hscif4_ctrl), - SH_PFC_PIN_GROUP(hscif4_data_b), - SH_PFC_PIN_GROUP(i2c0), - SH_PFC_PIN_GROUP(i2c1_a), - SH_PFC_PIN_GROUP(i2c1_b), - SH_PFC_PIN_GROUP(i2c2_a), - SH_PFC_PIN_GROUP(i2c2_b), - SH_PFC_PIN_GROUP(i2c3), - SH_PFC_PIN_GROUP(i2c5), - SH_PFC_PIN_GROUP(i2c6_a), - SH_PFC_PIN_GROUP(i2c6_b), - SH_PFC_PIN_GROUP(i2c6_c), - SH_PFC_PIN_GROUP(intc_ex_irq0), - SH_PFC_PIN_GROUP(intc_ex_irq1), - SH_PFC_PIN_GROUP(intc_ex_irq2), - SH_PFC_PIN_GROUP(intc_ex_irq3), - SH_PFC_PIN_GROUP(intc_ex_irq4), - SH_PFC_PIN_GROUP(intc_ex_irq5), - SH_PFC_PIN_GROUP(mlb_3pin), - SH_PFC_PIN_GROUP(msiof0_clk), - SH_PFC_PIN_GROUP(msiof0_sync), - SH_PFC_PIN_GROUP(msiof0_ss1), - SH_PFC_PIN_GROUP(msiof0_ss2), - SH_PFC_PIN_GROUP(msiof0_txd), - SH_PFC_PIN_GROUP(msiof0_rxd), - SH_PFC_PIN_GROUP(msiof1_clk_a), - SH_PFC_PIN_GROUP(msiof1_sync_a), - SH_PFC_PIN_GROUP(msiof1_ss1_a), - SH_PFC_PIN_GROUP(msiof1_ss2_a), - SH_PFC_PIN_GROUP(msiof1_txd_a), - SH_PFC_PIN_GROUP(msiof1_rxd_a), - SH_PFC_PIN_GROUP(msiof1_clk_b), - SH_PFC_PIN_GROUP(msiof1_sync_b), - SH_PFC_PIN_GROUP(msiof1_ss1_b), - SH_PFC_PIN_GROUP(msiof1_ss2_b), - SH_PFC_PIN_GROUP(msiof1_txd_b), - SH_PFC_PIN_GROUP(msiof1_rxd_b), - SH_PFC_PIN_GROUP(msiof1_clk_c), - SH_PFC_PIN_GROUP(msiof1_sync_c), - SH_PFC_PIN_GROUP(msiof1_ss1_c), - SH_PFC_PIN_GROUP(msiof1_ss2_c), - SH_PFC_PIN_GROUP(msiof1_txd_c), - SH_PFC_PIN_GROUP(msiof1_rxd_c), - SH_PFC_PIN_GROUP(msiof1_clk_d), - SH_PFC_PIN_GROUP(msiof1_sync_d), - SH_PFC_PIN_GROUP(msiof1_ss1_d), - SH_PFC_PIN_GROUP(msiof1_ss2_d), - SH_PFC_PIN_GROUP(msiof1_txd_d), - SH_PFC_PIN_GROUP(msiof1_rxd_d), - SH_PFC_PIN_GROUP(msiof1_clk_e), - SH_PFC_PIN_GROUP(msiof1_sync_e), - SH_PFC_PIN_GROUP(msiof1_ss1_e), - SH_PFC_PIN_GROUP(msiof1_ss2_e), - SH_PFC_PIN_GROUP(msiof1_txd_e), - SH_PFC_PIN_GROUP(msiof1_rxd_e), - SH_PFC_PIN_GROUP(msiof1_clk_f), - SH_PFC_PIN_GROUP(msiof1_sync_f), - SH_PFC_PIN_GROUP(msiof1_ss1_f), - SH_PFC_PIN_GROUP(msiof1_ss2_f), - SH_PFC_PIN_GROUP(msiof1_txd_f), - SH_PFC_PIN_GROUP(msiof1_rxd_f), - SH_PFC_PIN_GROUP(msiof1_clk_g), - SH_PFC_PIN_GROUP(msiof1_sync_g), - SH_PFC_PIN_GROUP(msiof1_ss1_g), - SH_PFC_PIN_GROUP(msiof1_ss2_g), - SH_PFC_PIN_GROUP(msiof1_txd_g), - SH_PFC_PIN_GROUP(msiof1_rxd_g), - SH_PFC_PIN_GROUP(msiof2_clk_a), - SH_PFC_PIN_GROUP(msiof2_sync_a), - SH_PFC_PIN_GROUP(msiof2_ss1_a), - SH_PFC_PIN_GROUP(msiof2_ss2_a), - SH_PFC_PIN_GROUP(msiof2_txd_a), - SH_PFC_PIN_GROUP(msiof2_rxd_a), - SH_PFC_PIN_GROUP(msiof2_clk_b), - SH_PFC_PIN_GROUP(msiof2_sync_b), - SH_PFC_PIN_GROUP(msiof2_ss1_b), - SH_PFC_PIN_GROUP(msiof2_ss2_b), - SH_PFC_PIN_GROUP(msiof2_txd_b), - SH_PFC_PIN_GROUP(msiof2_rxd_b), - SH_PFC_PIN_GROUP(msiof2_clk_c), - SH_PFC_PIN_GROUP(msiof2_sync_c), - SH_PFC_PIN_GROUP(msiof2_ss1_c), - SH_PFC_PIN_GROUP(msiof2_ss2_c), - SH_PFC_PIN_GROUP(msiof2_txd_c), - SH_PFC_PIN_GROUP(msiof2_rxd_c), - SH_PFC_PIN_GROUP(msiof2_clk_d), - SH_PFC_PIN_GROUP(msiof2_sync_d), - SH_PFC_PIN_GROUP(msiof2_ss1_d), - SH_PFC_PIN_GROUP(msiof2_ss2_d), - SH_PFC_PIN_GROUP(msiof2_txd_d), - SH_PFC_PIN_GROUP(msiof2_rxd_d), - SH_PFC_PIN_GROUP(msiof3_clk_a), - SH_PFC_PIN_GROUP(msiof3_sync_a), - SH_PFC_PIN_GROUP(msiof3_ss1_a), - SH_PFC_PIN_GROUP(msiof3_ss2_a), - SH_PFC_PIN_GROUP(msiof3_txd_a), - SH_PFC_PIN_GROUP(msiof3_rxd_a), - SH_PFC_PIN_GROUP(msiof3_clk_b), - SH_PFC_PIN_GROUP(msiof3_sync_b), - SH_PFC_PIN_GROUP(msiof3_ss1_b), - SH_PFC_PIN_GROUP(msiof3_ss2_b), - SH_PFC_PIN_GROUP(msiof3_txd_b), - SH_PFC_PIN_GROUP(msiof3_rxd_b), - SH_PFC_PIN_GROUP(msiof3_clk_c), - SH_PFC_PIN_GROUP(msiof3_sync_c), - SH_PFC_PIN_GROUP(msiof3_txd_c), - SH_PFC_PIN_GROUP(msiof3_rxd_c), - SH_PFC_PIN_GROUP(msiof3_clk_d), - SH_PFC_PIN_GROUP(msiof3_sync_d), - SH_PFC_PIN_GROUP(msiof3_ss1_d), - SH_PFC_PIN_GROUP(msiof3_txd_d), - SH_PFC_PIN_GROUP(msiof3_rxd_d), - SH_PFC_PIN_GROUP(pwm0), - SH_PFC_PIN_GROUP(pwm1_a), - SH_PFC_PIN_GROUP(pwm1_b), - SH_PFC_PIN_GROUP(pwm2_a), - SH_PFC_PIN_GROUP(pwm2_b), - SH_PFC_PIN_GROUP(pwm3_a), - SH_PFC_PIN_GROUP(pwm3_b), - SH_PFC_PIN_GROUP(pwm4_a), - SH_PFC_PIN_GROUP(pwm4_b), - SH_PFC_PIN_GROUP(pwm5_a), - SH_PFC_PIN_GROUP(pwm5_b), - SH_PFC_PIN_GROUP(pwm6_a), - SH_PFC_PIN_GROUP(pwm6_b), - SH_PFC_PIN_GROUP(qspi0_ctrl), - BUS_DATA_PIN_GROUP(qspi0_data, 2), - BUS_DATA_PIN_GROUP(qspi0_data, 4), - SH_PFC_PIN_GROUP(qspi1_ctrl), - BUS_DATA_PIN_GROUP(qspi1_data, 2), - BUS_DATA_PIN_GROUP(qspi1_data, 4), - SH_PFC_PIN_GROUP(sata0_devslp_a), - SH_PFC_PIN_GROUP(sata0_devslp_b), - SH_PFC_PIN_GROUP(scif0_data), - SH_PFC_PIN_GROUP(scif0_clk), - SH_PFC_PIN_GROUP(scif0_ctrl), - SH_PFC_PIN_GROUP(scif1_data_a), - SH_PFC_PIN_GROUP(scif1_clk), - SH_PFC_PIN_GROUP(scif1_ctrl), - SH_PFC_PIN_GROUP(scif1_data_b), - SH_PFC_PIN_GROUP(scif2_data_a), - SH_PFC_PIN_GROUP(scif2_clk), - SH_PFC_PIN_GROUP(scif2_data_b), - SH_PFC_PIN_GROUP(scif3_data_a), - SH_PFC_PIN_GROUP(scif3_clk), - SH_PFC_PIN_GROUP(scif3_ctrl), - SH_PFC_PIN_GROUP(scif3_data_b), - SH_PFC_PIN_GROUP(scif4_data_a), - SH_PFC_PIN_GROUP(scif4_clk_a), - SH_PFC_PIN_GROUP(scif4_ctrl_a), - SH_PFC_PIN_GROUP(scif4_data_b), - SH_PFC_PIN_GROUP(scif4_clk_b), - SH_PFC_PIN_GROUP(scif4_ctrl_b), - SH_PFC_PIN_GROUP(scif4_data_c), - SH_PFC_PIN_GROUP(scif4_clk_c), - SH_PFC_PIN_GROUP(scif4_ctrl_c), - SH_PFC_PIN_GROUP(scif5_data), - SH_PFC_PIN_GROUP(scif5_clk), - SH_PFC_PIN_GROUP(scif_clk_a), - SH_PFC_PIN_GROUP(scif_clk_b), - BUS_DATA_PIN_GROUP(sdhi0_data, 1), - BUS_DATA_PIN_GROUP(sdhi0_data, 4), - SH_PFC_PIN_GROUP(sdhi0_ctrl), - SH_PFC_PIN_GROUP(sdhi0_cd), - SH_PFC_PIN_GROUP(sdhi0_wp), - BUS_DATA_PIN_GROUP(sdhi1_data, 1), - BUS_DATA_PIN_GROUP(sdhi1_data, 4), - SH_PFC_PIN_GROUP(sdhi1_ctrl), - SH_PFC_PIN_GROUP(sdhi1_cd), - SH_PFC_PIN_GROUP(sdhi1_wp), - BUS_DATA_PIN_GROUP(sdhi2_data, 1), - BUS_DATA_PIN_GROUP(sdhi2_data, 4), - BUS_DATA_PIN_GROUP(sdhi2_data, 8), - SH_PFC_PIN_GROUP(sdhi2_ctrl), - SH_PFC_PIN_GROUP(sdhi2_cd_a), - SH_PFC_PIN_GROUP(sdhi2_wp_a), - SH_PFC_PIN_GROUP(sdhi2_cd_b), - SH_PFC_PIN_GROUP(sdhi2_wp_b), - SH_PFC_PIN_GROUP(sdhi2_ds), - BUS_DATA_PIN_GROUP(sdhi3_data, 1), - BUS_DATA_PIN_GROUP(sdhi3_data, 4), - BUS_DATA_PIN_GROUP(sdhi3_data, 8), - SH_PFC_PIN_GROUP(sdhi3_ctrl), - SH_PFC_PIN_GROUP(sdhi3_cd), - SH_PFC_PIN_GROUP(sdhi3_wp), - SH_PFC_PIN_GROUP(sdhi3_ds), - SH_PFC_PIN_GROUP(ssi0_data), - SH_PFC_PIN_GROUP(ssi01239_ctrl), - SH_PFC_PIN_GROUP(ssi1_data_a), - SH_PFC_PIN_GROUP(ssi1_data_b), - SH_PFC_PIN_GROUP(ssi1_ctrl_a), - SH_PFC_PIN_GROUP(ssi1_ctrl_b), - SH_PFC_PIN_GROUP(ssi2_data_a), - SH_PFC_PIN_GROUP(ssi2_data_b), - SH_PFC_PIN_GROUP(ssi2_ctrl_a), - SH_PFC_PIN_GROUP(ssi2_ctrl_b), - SH_PFC_PIN_GROUP(ssi3_data), - SH_PFC_PIN_GROUP(ssi349_ctrl), - SH_PFC_PIN_GROUP(ssi4_data), - SH_PFC_PIN_GROUP(ssi4_ctrl), - SH_PFC_PIN_GROUP(ssi5_data), - SH_PFC_PIN_GROUP(ssi5_ctrl), - SH_PFC_PIN_GROUP(ssi6_data), - SH_PFC_PIN_GROUP(ssi6_ctrl), - SH_PFC_PIN_GROUP(ssi7_data), - SH_PFC_PIN_GROUP(ssi78_ctrl), - SH_PFC_PIN_GROUP(ssi8_data), - SH_PFC_PIN_GROUP(ssi9_data_a), - SH_PFC_PIN_GROUP(ssi9_data_b), - SH_PFC_PIN_GROUP(ssi9_ctrl_a), - SH_PFC_PIN_GROUP(ssi9_ctrl_b), - SH_PFC_PIN_GROUP(tmu_tclk1_a), - SH_PFC_PIN_GROUP(tmu_tclk1_b), - SH_PFC_PIN_GROUP(tmu_tclk2_a), - SH_PFC_PIN_GROUP(tmu_tclk2_b), - SH_PFC_PIN_GROUP(tpu_to0), - SH_PFC_PIN_GROUP(tpu_to1), - SH_PFC_PIN_GROUP(tpu_to2), - SH_PFC_PIN_GROUP(tpu_to3), - SH_PFC_PIN_GROUP(usb0), - SH_PFC_PIN_GROUP(usb1), - SH_PFC_PIN_GROUP(usb2), - SH_PFC_PIN_GROUP(usb30), - SH_PFC_PIN_GROUP(usb31), - BUS_DATA_PIN_GROUP(vin4_data, 8, _a), - BUS_DATA_PIN_GROUP(vin4_data, 10, _a), - BUS_DATA_PIN_GROUP(vin4_data, 12, _a), - BUS_DATA_PIN_GROUP(vin4_data, 16, _a), - SH_PFC_PIN_GROUP(vin4_data18_a), - BUS_DATA_PIN_GROUP(vin4_data, 20, _a), - BUS_DATA_PIN_GROUP(vin4_data, 24, _a), - BUS_DATA_PIN_GROUP(vin4_data, 8, _b), - BUS_DATA_PIN_GROUP(vin4_data, 10, _b), - BUS_DATA_PIN_GROUP(vin4_data, 12, _b), - BUS_DATA_PIN_GROUP(vin4_data, 16, _b), - SH_PFC_PIN_GROUP(vin4_data18_b), - BUS_DATA_PIN_GROUP(vin4_data, 20, _b), - BUS_DATA_PIN_GROUP(vin4_data, 24, _b), - SH_PFC_PIN_GROUP_SUBSET(vin4_g8, vin4_data_a, 8, 8), - SH_PFC_PIN_GROUP(vin4_sync), - SH_PFC_PIN_GROUP(vin4_field), - SH_PFC_PIN_GROUP(vin4_clkenb), - SH_PFC_PIN_GROUP(vin4_clk), - BUS_DATA_PIN_GROUP(vin5_data, 8), - BUS_DATA_PIN_GROUP(vin5_data, 10), - BUS_DATA_PIN_GROUP(vin5_data, 12), - BUS_DATA_PIN_GROUP(vin5_data, 16), - SH_PFC_PIN_GROUP_SUBSET(vin5_high8, vin5_data, 8, 8), - SH_PFC_PIN_GROUP(vin5_sync), - SH_PFC_PIN_GROUP(vin5_field), - SH_PFC_PIN_GROUP(vin5_clkenb), - SH_PFC_PIN_GROUP(vin5_clk), -}; - -static const char * const audio_clk_groups[] = { - "audio_clk_a_a", - "audio_clk_a_b", - "audio_clk_a_c", - "audio_clk_b_a", - "audio_clk_b_b", - "audio_clk_c_a", - "audio_clk_c_b", - "audio_clkout_a", - "audio_clkout_b", - "audio_clkout_c", - "audio_clkout_d", - "audio_clkout1_a", - "audio_clkout1_b", - "audio_clkout2_a", - "audio_clkout2_b", - "audio_clkout3_a", - "audio_clkout3_b", -}; - -static const char * const avb_groups[] = { - "avb_link", - "avb_magic", - "avb_phy_int", - "avb_mdc", /* Deprecated, please use "avb_mdio" instead */ - "avb_mdio", - "avb_mii", - "avb_avtp_pps", - "avb_avtp_match_a", - "avb_avtp_capture_a", - "avb_avtp_match_b", - "avb_avtp_capture_b", -}; - -static const char * const can0_groups[] = { - "can0_data_a", - "can0_data_b", -}; - -static const char * const can1_groups[] = { - "can1_data", -}; - -static const char * const can_clk_groups[] = { - "can_clk", -}; - -static const char * const canfd0_groups[] = { - "canfd0_data_a", - "canfd0_data_b", -}; - -static const char * const canfd1_groups[] = { - "canfd1_data", -}; - -static const char * const drif0_groups[] = { - "drif0_ctrl_a", - "drif0_data0_a", - "drif0_data1_a", - "drif0_ctrl_b", - "drif0_data0_b", - "drif0_data1_b", - "drif0_ctrl_c", - "drif0_data0_c", - "drif0_data1_c", -}; - -static const char * const drif1_groups[] = { - "drif1_ctrl_a", - "drif1_data0_a", - "drif1_data1_a", - "drif1_ctrl_b", - "drif1_data0_b", - "drif1_data1_b", - "drif1_ctrl_c", - "drif1_data0_c", - "drif1_data1_c", -}; - -static const char * const drif2_groups[] = { - "drif2_ctrl_a", - "drif2_data0_a", - "drif2_data1_a", - "drif2_ctrl_b", - "drif2_data0_b", - "drif2_data1_b", -}; - -static const char * const drif3_groups[] = { - "drif3_ctrl_a", - "drif3_data0_a", - "drif3_data1_a", - "drif3_ctrl_b", - "drif3_data0_b", - "drif3_data1_b", -}; - -static const char * const du_groups[] = { - "du_rgb666", - "du_rgb888", - "du_clk_out_0", - "du_clk_out_1", - "du_sync", - "du_oddf", - "du_cde", - "du_disp", -}; - -static const char * const hscif0_groups[] = { - "hscif0_data", - "hscif0_clk", - "hscif0_ctrl", -}; - -static const char * const hscif1_groups[] = { - "hscif1_data_a", - "hscif1_clk_a", - "hscif1_ctrl_a", - "hscif1_data_b", - "hscif1_clk_b", - "hscif1_ctrl_b", -}; - -static const char * const hscif2_groups[] = { - "hscif2_data_a", - "hscif2_clk_a", - "hscif2_ctrl_a", - "hscif2_data_b", - "hscif2_clk_b", - "hscif2_ctrl_b", -}; - -static const char * const hscif3_groups[] = { - "hscif3_data_a", - "hscif3_clk", - "hscif3_ctrl", - "hscif3_data_b", - "hscif3_data_c", - "hscif3_data_d", -}; - -static const char * const hscif4_groups[] = { - "hscif4_data_a", - "hscif4_clk", - "hscif4_ctrl", - "hscif4_data_b", -}; - -static const char * const i2c0_groups[] = { - "i2c0", -}; - -static const char * const i2c1_groups[] = { - "i2c1_a", - "i2c1_b", -}; - -static const char * const i2c2_groups[] = { - "i2c2_a", - "i2c2_b", -}; - -static const char * const i2c3_groups[] = { - "i2c3", -}; - -static const char * const i2c5_groups[] = { - "i2c5", -}; - -static const char * const i2c6_groups[] = { - "i2c6_a", - "i2c6_b", - "i2c6_c", -}; - -static const char * const intc_ex_groups[] = { - "intc_ex_irq0", - "intc_ex_irq1", - "intc_ex_irq2", - "intc_ex_irq3", - "intc_ex_irq4", - "intc_ex_irq5", -}; - -static const char * const mlb_3pin_groups[] = { - "mlb_3pin", -}; - -static const char * const msiof0_groups[] = { - "msiof0_clk", - "msiof0_sync", - "msiof0_ss1", - "msiof0_ss2", - "msiof0_txd", - "msiof0_rxd", -}; - -static const char * const msiof1_groups[] = { - "msiof1_clk_a", - "msiof1_sync_a", - "msiof1_ss1_a", - "msiof1_ss2_a", - "msiof1_txd_a", - "msiof1_rxd_a", - "msiof1_clk_b", - "msiof1_sync_b", - "msiof1_ss1_b", - "msiof1_ss2_b", - "msiof1_txd_b", - "msiof1_rxd_b", - "msiof1_clk_c", - "msiof1_sync_c", - "msiof1_ss1_c", - "msiof1_ss2_c", - "msiof1_txd_c", - "msiof1_rxd_c", - "msiof1_clk_d", - "msiof1_sync_d", - "msiof1_ss1_d", - "msiof1_ss2_d", - "msiof1_txd_d", - "msiof1_rxd_d", - "msiof1_clk_e", - "msiof1_sync_e", - "msiof1_ss1_e", - "msiof1_ss2_e", - "msiof1_txd_e", - "msiof1_rxd_e", - "msiof1_clk_f", - "msiof1_sync_f", - "msiof1_ss1_f", - "msiof1_ss2_f", - "msiof1_txd_f", - "msiof1_rxd_f", - "msiof1_clk_g", - "msiof1_sync_g", - "msiof1_ss1_g", - "msiof1_ss2_g", - "msiof1_txd_g", - "msiof1_rxd_g", -}; - -static const char * const msiof2_groups[] = { - "msiof2_clk_a", - "msiof2_sync_a", - "msiof2_ss1_a", - "msiof2_ss2_a", - "msiof2_txd_a", - "msiof2_rxd_a", - "msiof2_clk_b", - "msiof2_sync_b", - "msiof2_ss1_b", - "msiof2_ss2_b", - "msiof2_txd_b", - "msiof2_rxd_b", - "msiof2_clk_c", - "msiof2_sync_c", - "msiof2_ss1_c", - "msiof2_ss2_c", - "msiof2_txd_c", - "msiof2_rxd_c", - "msiof2_clk_d", - "msiof2_sync_d", - "msiof2_ss1_d", - "msiof2_ss2_d", - "msiof2_txd_d", - "msiof2_rxd_d", -}; - -static const char * const msiof3_groups[] = { - "msiof3_clk_a", - "msiof3_sync_a", - "msiof3_ss1_a", - "msiof3_ss2_a", - "msiof3_txd_a", - "msiof3_rxd_a", - "msiof3_clk_b", - "msiof3_sync_b", - "msiof3_ss1_b", - "msiof3_ss2_b", - "msiof3_txd_b", - "msiof3_rxd_b", - "msiof3_clk_c", - "msiof3_sync_c", - "msiof3_txd_c", - "msiof3_rxd_c", - "msiof3_clk_d", - "msiof3_sync_d", - "msiof3_ss1_d", - "msiof3_txd_d", - "msiof3_rxd_d", -}; - -static const char * const pwm0_groups[] = { - "pwm0", -}; - -static const char * const pwm1_groups[] = { - "pwm1_a", - "pwm1_b", -}; - -static const char * const pwm2_groups[] = { - "pwm2_a", - "pwm2_b", -}; - -static const char * const pwm3_groups[] = { - "pwm3_a", - "pwm3_b", -}; - -static const char * const pwm4_groups[] = { - "pwm4_a", - "pwm4_b", -}; - -static const char * const pwm5_groups[] = { - "pwm5_a", - "pwm5_b", -}; - -static const char * const pwm6_groups[] = { - "pwm6_a", - "pwm6_b", -}; - -static const char * const qspi0_groups[] = { - "qspi0_ctrl", - "qspi0_data2", - "qspi0_data4", -}; - -static const char * const qspi1_groups[] = { - "qspi1_ctrl", - "qspi1_data2", - "qspi1_data4", -}; - -static const char * const sata0_groups[] = { - "sata0_devslp_a", - "sata0_devslp_b", -}; - -static const char * const scif0_groups[] = { - "scif0_data", - "scif0_clk", - "scif0_ctrl", -}; - -static const char * const scif1_groups[] = { - "scif1_data_a", - "scif1_clk", - "scif1_ctrl", - "scif1_data_b", -}; - -static const char * const scif2_groups[] = { - "scif2_data_a", - "scif2_clk", - "scif2_data_b", -}; - -static const char * const scif3_groups[] = { - "scif3_data_a", - "scif3_clk", - "scif3_ctrl", - "scif3_data_b", -}; - -static const char * const scif4_groups[] = { - "scif4_data_a", - "scif4_clk_a", - "scif4_ctrl_a", - "scif4_data_b", - "scif4_clk_b", - "scif4_ctrl_b", - "scif4_data_c", - "scif4_clk_c", - "scif4_ctrl_c", -}; - -static const char * const scif5_groups[] = { - "scif5_data", - "scif5_clk", -}; - -static const char * const scif_clk_groups[] = { - "scif_clk_a", - "scif_clk_b", -}; - -static const char * const sdhi0_groups[] = { - "sdhi0_data1", - "sdhi0_data4", - "sdhi0_ctrl", - "sdhi0_cd", - "sdhi0_wp", -}; - -static const char * const sdhi1_groups[] = { - "sdhi1_data1", - "sdhi1_data4", - "sdhi1_ctrl", - "sdhi1_cd", - "sdhi1_wp", -}; - -static const char * const sdhi2_groups[] = { - "sdhi2_data1", - "sdhi2_data4", - "sdhi2_data8", - "sdhi2_ctrl", - "sdhi2_cd_a", - "sdhi2_wp_a", - "sdhi2_cd_b", - "sdhi2_wp_b", - "sdhi2_ds", -}; - -static const char * const sdhi3_groups[] = { - "sdhi3_data1", - "sdhi3_data4", - "sdhi3_data8", - "sdhi3_ctrl", - "sdhi3_cd", - "sdhi3_wp", - "sdhi3_ds", -}; - -static const char * const ssi_groups[] = { - "ssi0_data", - "ssi01239_ctrl", - "ssi1_data_a", - "ssi1_data_b", - "ssi1_ctrl_a", - "ssi1_ctrl_b", - "ssi2_data_a", - "ssi2_data_b", - "ssi2_ctrl_a", - "ssi2_ctrl_b", - "ssi3_data", - "ssi349_ctrl", - "ssi4_data", - "ssi4_ctrl", - "ssi5_data", - "ssi5_ctrl", - "ssi6_data", - "ssi6_ctrl", - "ssi7_data", - "ssi78_ctrl", - "ssi8_data", - "ssi9_data_a", - "ssi9_data_b", - "ssi9_ctrl_a", - "ssi9_ctrl_b", -}; - -static const char * const tmu_groups[] = { - "tmu_tclk1_a", - "tmu_tclk1_b", - "tmu_tclk2_a", - "tmu_tclk2_b", -}; - -static const char * const tpu_groups[] = { - "tpu_to0", - "tpu_to1", - "tpu_to2", - "tpu_to3", -}; - -static const char * const usb0_groups[] = { - "usb0", -}; - -static const char * const usb1_groups[] = { - "usb1", -}; - -static const char * const usb2_groups[] = { - "usb2", -}; - -static const char * const usb30_groups[] = { - "usb30", -}; - -static const char * const usb31_groups[] = { - "usb31", -}; - -static const char * const vin4_groups[] = { - "vin4_data8_a", - "vin4_data10_a", - "vin4_data12_a", - "vin4_data16_a", - "vin4_data18_a", - "vin4_data20_a", - "vin4_data24_a", - "vin4_data8_b", - "vin4_data10_b", - "vin4_data12_b", - "vin4_data16_b", - "vin4_data18_b", - "vin4_data20_b", - "vin4_data24_b", - "vin4_g8", - "vin4_sync", - "vin4_field", - "vin4_clkenb", - "vin4_clk", -}; - -static const char * const vin5_groups[] = { - "vin5_data8", - "vin5_data10", - "vin5_data12", - "vin5_data16", - "vin5_high8", - "vin5_sync", - "vin5_field", - "vin5_clkenb", - "vin5_clk", -}; - -static const struct sh_pfc_function pinmux_functions[] = { - SH_PFC_FUNCTION(audio_clk), - SH_PFC_FUNCTION(avb), - SH_PFC_FUNCTION(can0), - SH_PFC_FUNCTION(can1), - SH_PFC_FUNCTION(can_clk), - SH_PFC_FUNCTION(canfd0), - SH_PFC_FUNCTION(canfd1), - SH_PFC_FUNCTION(drif0), - SH_PFC_FUNCTION(drif1), - SH_PFC_FUNCTION(drif2), - SH_PFC_FUNCTION(drif3), - SH_PFC_FUNCTION(du), - SH_PFC_FUNCTION(hscif0), - SH_PFC_FUNCTION(hscif1), - SH_PFC_FUNCTION(hscif2), - SH_PFC_FUNCTION(hscif3), - SH_PFC_FUNCTION(hscif4), - SH_PFC_FUNCTION(i2c0), - SH_PFC_FUNCTION(i2c1), - SH_PFC_FUNCTION(i2c2), - SH_PFC_FUNCTION(i2c3), - SH_PFC_FUNCTION(i2c5), - SH_PFC_FUNCTION(i2c6), - SH_PFC_FUNCTION(intc_ex), - SH_PFC_FUNCTION(mlb_3pin), - SH_PFC_FUNCTION(msiof0), - SH_PFC_FUNCTION(msiof1), - SH_PFC_FUNCTION(msiof2), - SH_PFC_FUNCTION(msiof3), - SH_PFC_FUNCTION(pwm0), - SH_PFC_FUNCTION(pwm1), - SH_PFC_FUNCTION(pwm2), - SH_PFC_FUNCTION(pwm3), - SH_PFC_FUNCTION(pwm4), - SH_PFC_FUNCTION(pwm5), - SH_PFC_FUNCTION(pwm6), - SH_PFC_FUNCTION(qspi0), - SH_PFC_FUNCTION(qspi1), - SH_PFC_FUNCTION(sata0), - SH_PFC_FUNCTION(scif0), - SH_PFC_FUNCTION(scif1), - SH_PFC_FUNCTION(scif2), - SH_PFC_FUNCTION(scif3), - SH_PFC_FUNCTION(scif4), - SH_PFC_FUNCTION(scif5), - SH_PFC_FUNCTION(scif_clk), - SH_PFC_FUNCTION(sdhi0), - SH_PFC_FUNCTION(sdhi1), - SH_PFC_FUNCTION(sdhi2), - SH_PFC_FUNCTION(sdhi3), - SH_PFC_FUNCTION(ssi), - SH_PFC_FUNCTION(tmu), - SH_PFC_FUNCTION(tpu), - SH_PFC_FUNCTION(usb0), - SH_PFC_FUNCTION(usb1), - SH_PFC_FUNCTION(usb2), - SH_PFC_FUNCTION(usb30), - SH_PFC_FUNCTION(usb31), - SH_PFC_FUNCTION(vin4), - SH_PFC_FUNCTION(vin5), -}; - -static const struct pinmux_cfg_reg pinmux_config_regs[] = { -#define F_(x, y) FN_##y -#define FM(x) FN_##x - { PINMUX_CFG_REG_VAR("GPSR0", 0xe6060100, 32, - GROUP(-16, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1), - GROUP( - /* GP0_31_16 RESERVED */ - GP_0_15_FN, GPSR0_15, - GP_0_14_FN, GPSR0_14, - GP_0_13_FN, GPSR0_13, - GP_0_12_FN, GPSR0_12, - GP_0_11_FN, GPSR0_11, - GP_0_10_FN, GPSR0_10, - GP_0_9_FN, GPSR0_9, - GP_0_8_FN, GPSR0_8, - GP_0_7_FN, GPSR0_7, - GP_0_6_FN, GPSR0_6, - GP_0_5_FN, GPSR0_5, - GP_0_4_FN, GPSR0_4, - GP_0_3_FN, GPSR0_3, - GP_0_2_FN, GPSR0_2, - GP_0_1_FN, GPSR0_1, - GP_0_0_FN, GPSR0_0, )) - }, - { PINMUX_CFG_REG("GPSR1", 0xe6060104, 32, 1, GROUP( - 0, 0, - 0, 0, - 0, 0, - 0, 0, - GP_1_27_FN, GPSR1_27, - GP_1_26_FN, GPSR1_26, - GP_1_25_FN, GPSR1_25, - GP_1_24_FN, GPSR1_24, - GP_1_23_FN, GPSR1_23, - GP_1_22_FN, GPSR1_22, - GP_1_21_FN, GPSR1_21, - GP_1_20_FN, GPSR1_20, - GP_1_19_FN, GPSR1_19, - GP_1_18_FN, GPSR1_18, - GP_1_17_FN, GPSR1_17, - GP_1_16_FN, GPSR1_16, - GP_1_15_FN, GPSR1_15, - GP_1_14_FN, GPSR1_14, - GP_1_13_FN, GPSR1_13, - GP_1_12_FN, GPSR1_12, - GP_1_11_FN, GPSR1_11, - GP_1_10_FN, GPSR1_10, - GP_1_9_FN, GPSR1_9, - GP_1_8_FN, GPSR1_8, - GP_1_7_FN, GPSR1_7, - GP_1_6_FN, GPSR1_6, - GP_1_5_FN, GPSR1_5, - GP_1_4_FN, GPSR1_4, - GP_1_3_FN, GPSR1_3, - GP_1_2_FN, GPSR1_2, - GP_1_1_FN, GPSR1_1, - GP_1_0_FN, GPSR1_0, )) - }, - { PINMUX_CFG_REG_VAR("GPSR2", 0xe6060108, 32, - GROUP(-17, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1), - GROUP( - /* GP2_31_15 RESERVED */ - GP_2_14_FN, GPSR2_14, - GP_2_13_FN, GPSR2_13, - GP_2_12_FN, GPSR2_12, - GP_2_11_FN, GPSR2_11, - GP_2_10_FN, GPSR2_10, - GP_2_9_FN, GPSR2_9, - GP_2_8_FN, GPSR2_8, - GP_2_7_FN, GPSR2_7, - GP_2_6_FN, GPSR2_6, - GP_2_5_FN, GPSR2_5, - GP_2_4_FN, GPSR2_4, - GP_2_3_FN, GPSR2_3, - GP_2_2_FN, GPSR2_2, - GP_2_1_FN, GPSR2_1, - GP_2_0_FN, GPSR2_0, )) - }, - { PINMUX_CFG_REG_VAR("GPSR3", 0xe606010c, 32, - GROUP(-16, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1), - GROUP( - /* GP3_31_16 RESERVED */ - GP_3_15_FN, GPSR3_15, - GP_3_14_FN, GPSR3_14, - GP_3_13_FN, GPSR3_13, - GP_3_12_FN, GPSR3_12, - GP_3_11_FN, GPSR3_11, - GP_3_10_FN, GPSR3_10, - GP_3_9_FN, GPSR3_9, - GP_3_8_FN, GPSR3_8, - GP_3_7_FN, GPSR3_7, - GP_3_6_FN, GPSR3_6, - GP_3_5_FN, GPSR3_5, - GP_3_4_FN, GPSR3_4, - GP_3_3_FN, GPSR3_3, - GP_3_2_FN, GPSR3_2, - GP_3_1_FN, GPSR3_1, - GP_3_0_FN, GPSR3_0, )) - }, - { PINMUX_CFG_REG_VAR("GPSR4", 0xe6060110, 32, - GROUP(-14, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1, 1, 1), - GROUP( - /* GP4_31_18 RESERVED */ - GP_4_17_FN, GPSR4_17, - GP_4_16_FN, GPSR4_16, - GP_4_15_FN, GPSR4_15, - GP_4_14_FN, GPSR4_14, - GP_4_13_FN, GPSR4_13, - GP_4_12_FN, GPSR4_12, - GP_4_11_FN, GPSR4_11, - GP_4_10_FN, GPSR4_10, - GP_4_9_FN, GPSR4_9, - GP_4_8_FN, GPSR4_8, - GP_4_7_FN, GPSR4_7, - GP_4_6_FN, GPSR4_6, - GP_4_5_FN, GPSR4_5, - GP_4_4_FN, GPSR4_4, - GP_4_3_FN, GPSR4_3, - GP_4_2_FN, GPSR4_2, - GP_4_1_FN, GPSR4_1, - GP_4_0_FN, GPSR4_0, )) - }, - { PINMUX_CFG_REG("GPSR5", 0xe6060114, 32, 1, GROUP( - 0, 0, - 0, 0, - 0, 0, - 0, 0, - 0, 0, - 0, 0, - GP_5_25_FN, GPSR5_25, - GP_5_24_FN, GPSR5_24, - GP_5_23_FN, GPSR5_23, - GP_5_22_FN, GPSR5_22, - GP_5_21_FN, GPSR5_21, - GP_5_20_FN, GPSR5_20, - GP_5_19_FN, GPSR5_19, - GP_5_18_FN, GPSR5_18, - GP_5_17_FN, GPSR5_17, - GP_5_16_FN, GPSR5_16, - GP_5_15_FN, GPSR5_15, - GP_5_14_FN, GPSR5_14, - GP_5_13_FN, GPSR5_13, - GP_5_12_FN, GPSR5_12, - GP_5_11_FN, GPSR5_11, - GP_5_10_FN, GPSR5_10, - GP_5_9_FN, GPSR5_9, - GP_5_8_FN, GPSR5_8, - GP_5_7_FN, GPSR5_7, - GP_5_6_FN, GPSR5_6, - GP_5_5_FN, GPSR5_5, - GP_5_4_FN, GPSR5_4, - GP_5_3_FN, GPSR5_3, - GP_5_2_FN, GPSR5_2, - GP_5_1_FN, GPSR5_1, - GP_5_0_FN, GPSR5_0, )) - }, - { PINMUX_CFG_REG("GPSR6", 0xe6060118, 32, 1, GROUP( - GP_6_31_FN, GPSR6_31, - GP_6_30_FN, GPSR6_30, - GP_6_29_FN, GPSR6_29, - GP_6_28_FN, GPSR6_28, - GP_6_27_FN, GPSR6_27, - GP_6_26_FN, GPSR6_26, - GP_6_25_FN, GPSR6_25, - GP_6_24_FN, GPSR6_24, - GP_6_23_FN, GPSR6_23, - GP_6_22_FN, GPSR6_22, - GP_6_21_FN, GPSR6_21, - GP_6_20_FN, GPSR6_20, - GP_6_19_FN, GPSR6_19, - GP_6_18_FN, GPSR6_18, - GP_6_17_FN, GPSR6_17, - GP_6_16_FN, GPSR6_16, - GP_6_15_FN, GPSR6_15, - GP_6_14_FN, GPSR6_14, - GP_6_13_FN, GPSR6_13, - GP_6_12_FN, GPSR6_12, - GP_6_11_FN, GPSR6_11, - GP_6_10_FN, GPSR6_10, - GP_6_9_FN, GPSR6_9, - GP_6_8_FN, GPSR6_8, - GP_6_7_FN, GPSR6_7, - GP_6_6_FN, GPSR6_6, - GP_6_5_FN, GPSR6_5, - GP_6_4_FN, GPSR6_4, - GP_6_3_FN, GPSR6_3, - GP_6_2_FN, GPSR6_2, - GP_6_1_FN, GPSR6_1, - GP_6_0_FN, GPSR6_0, )) - }, - { PINMUX_CFG_REG_VAR("GPSR7", 0xe606011c, 32, - GROUP(-28, 1, 1, 1, 1), - GROUP( - /* GP7_31_4 RESERVED */ - GP_7_3_FN, GPSR7_3, - GP_7_2_FN, GPSR7_2, - GP_7_1_FN, GPSR7_1, - GP_7_0_FN, GPSR7_0, )) - }, -#undef F_ -#undef FM - -#define F_(x, y) x, -#define FM(x) FN_##x, - { PINMUX_CFG_REG("IPSR0", 0xe6060200, 32, 4, GROUP( - IP0_31_28 - IP0_27_24 - IP0_23_20 - IP0_19_16 - IP0_15_12 - IP0_11_8 - IP0_7_4 - IP0_3_0 )) - }, - { PINMUX_CFG_REG("IPSR1", 0xe6060204, 32, 4, GROUP( - IP1_31_28 - IP1_27_24 - IP1_23_20 - IP1_19_16 - IP1_15_12 - IP1_11_8 - IP1_7_4 - IP1_3_0 )) - }, - { PINMUX_CFG_REG("IPSR2", 0xe6060208, 32, 4, GROUP( - IP2_31_28 - IP2_27_24 - IP2_23_20 - IP2_19_16 - IP2_15_12 - IP2_11_8 - IP2_7_4 - IP2_3_0 )) - }, - { PINMUX_CFG_REG("IPSR3", 0xe606020c, 32, 4, GROUP( - IP3_31_28 - IP3_27_24 - IP3_23_20 - IP3_19_16 - IP3_15_12 - IP3_11_8 - IP3_7_4 - IP3_3_0 )) - }, - { PINMUX_CFG_REG("IPSR4", 0xe6060210, 32, 4, GROUP( - IP4_31_28 - IP4_27_24 - IP4_23_20 - IP4_19_16 - IP4_15_12 - IP4_11_8 - IP4_7_4 - IP4_3_0 )) - }, - { PINMUX_CFG_REG("IPSR5", 0xe6060214, 32, 4, GROUP( - IP5_31_28 - IP5_27_24 - IP5_23_20 - IP5_19_16 - IP5_15_12 - IP5_11_8 - IP5_7_4 - IP5_3_0 )) - }, - { PINMUX_CFG_REG("IPSR6", 0xe6060218, 32, 4, GROUP( - IP6_31_28 - IP6_27_24 - IP6_23_20 - IP6_19_16 - IP6_15_12 - IP6_11_8 - IP6_7_4 - IP6_3_0 )) - }, - { PINMUX_CFG_REG("IPSR7", 0xe606021c, 32, 4, GROUP( - IP7_31_28 - IP7_27_24 - IP7_23_20 - IP7_19_16 - IP7_15_12 - IP7_11_8 - IP7_7_4 - IP7_3_0 )) - }, - { PINMUX_CFG_REG("IPSR8", 0xe6060220, 32, 4, GROUP( - IP8_31_28 - IP8_27_24 - IP8_23_20 - IP8_19_16 - IP8_15_12 - IP8_11_8 - IP8_7_4 - IP8_3_0 )) - }, - { PINMUX_CFG_REG("IPSR9", 0xe6060224, 32, 4, GROUP( - IP9_31_28 - IP9_27_24 - IP9_23_20 - IP9_19_16 - IP9_15_12 - IP9_11_8 - IP9_7_4 - IP9_3_0 )) - }, - { PINMUX_CFG_REG("IPSR10", 0xe6060228, 32, 4, GROUP( - IP10_31_28 - IP10_27_24 - IP10_23_20 - IP10_19_16 - IP10_15_12 - IP10_11_8 - IP10_7_4 - IP10_3_0 )) - }, - { PINMUX_CFG_REG("IPSR11", 0xe606022c, 32, 4, GROUP( - IP11_31_28 - IP11_27_24 - IP11_23_20 - IP11_19_16 - IP11_15_12 - IP11_11_8 - IP11_7_4 - IP11_3_0 )) - }, - { PINMUX_CFG_REG("IPSR12", 0xe6060230, 32, 4, GROUP( - IP12_31_28 - IP12_27_24 - IP12_23_20 - IP12_19_16 - IP12_15_12 - IP12_11_8 - IP12_7_4 - IP12_3_0 )) - }, - { PINMUX_CFG_REG("IPSR13", 0xe6060234, 32, 4, GROUP( - IP13_31_28 - IP13_27_24 - IP13_23_20 - IP13_19_16 - IP13_15_12 - IP13_11_8 - IP13_7_4 - IP13_3_0 )) - }, - { PINMUX_CFG_REG("IPSR14", 0xe6060238, 32, 4, GROUP( - IP14_31_28 - IP14_27_24 - IP14_23_20 - IP14_19_16 - IP14_15_12 - IP14_11_8 - IP14_7_4 - IP14_3_0 )) - }, - { PINMUX_CFG_REG("IPSR15", 0xe606023c, 32, 4, GROUP( - IP15_31_28 - IP15_27_24 - IP15_23_20 - IP15_19_16 - IP15_15_12 - IP15_11_8 - IP15_7_4 - IP15_3_0 )) - }, - { PINMUX_CFG_REG("IPSR16", 0xe6060240, 32, 4, GROUP( - IP16_31_28 - IP16_27_24 - IP16_23_20 - IP16_19_16 - IP16_15_12 - IP16_11_8 - IP16_7_4 - IP16_3_0 )) - }, - { PINMUX_CFG_REG_VAR("IPSR17", 0xe6060244, 32, - GROUP(-24, 4, 4), - GROUP( - /* IP17_31_8 RESERVED */ - IP17_7_4 - IP17_3_0 )) - }, -#undef F_ -#undef FM - -#define F_(x, y) x, -#define FM(x) FN_##x, - { PINMUX_CFG_REG_VAR("MOD_SEL0", 0xe6060500, 32, - GROUP(-1, 2, 2, 3, 1, 1, 2, 1, 1, 1, 2, 1, - 1, 1, 1, 1, 1, 1, 2, 2, 1, 2, -1), - GROUP( - /* RESERVED 31 */ - MOD_SEL0_30_29 - MOD_SEL0_28_27 - MOD_SEL0_26_25_24 - MOD_SEL0_23 - MOD_SEL0_22 - MOD_SEL0_21_20 - MOD_SEL0_19 - MOD_SEL0_18 - MOD_SEL0_17 - MOD_SEL0_16_15 - MOD_SEL0_14 - MOD_SEL0_13 - MOD_SEL0_12 - MOD_SEL0_11 - MOD_SEL0_10 - MOD_SEL0_9 - MOD_SEL0_8 - MOD_SEL0_7_6 - MOD_SEL0_5_4 - MOD_SEL0_3 - MOD_SEL0_2_1 - /* RESERVED 0 */ )) - }, - { PINMUX_CFG_REG_VAR("MOD_SEL1", 0xe6060504, 32, - GROUP(2, 3, 1, 2, 3, 1, 1, 2, 1, 2, 1, 1, - 1, 1, 1, -2, 1, 1, 1, 1, 1, 1, 1), - GROUP( - MOD_SEL1_31_30 - MOD_SEL1_29_28_27 - MOD_SEL1_26 - MOD_SEL1_25_24 - MOD_SEL1_23_22_21 - MOD_SEL1_20 - MOD_SEL1_19 - MOD_SEL1_18_17 - MOD_SEL1_16 - MOD_SEL1_15_14 - MOD_SEL1_13 - MOD_SEL1_12 - MOD_SEL1_11 - MOD_SEL1_10 - MOD_SEL1_9 - /* RESERVED 8, 7 */ - MOD_SEL1_6 - MOD_SEL1_5 - MOD_SEL1_4 - MOD_SEL1_3 - MOD_SEL1_2 - MOD_SEL1_1 - MOD_SEL1_0 )) - }, - { PINMUX_CFG_REG_VAR("MOD_SEL2", 0xe6060508, 32, - GROUP(1, 1, 1, -28, 1), - GROUP( - MOD_SEL2_31 - MOD_SEL2_30 - MOD_SEL2_29 - /* RESERVED 28-1 */ - MOD_SEL2_0 )) - }, - { }, -}; - -static const struct pinmux_drive_reg pinmux_drive_regs[] = { - { PINMUX_DRIVE_REG("DRVCTRL0", 0xe6060300) { - { PIN_QSPI0_SPCLK, 28, 2 }, /* QSPI0_SPCLK */ - { PIN_QSPI0_MOSI_IO0, 24, 2 }, /* QSPI0_MOSI_IO0 */ - { PIN_QSPI0_MISO_IO1, 20, 2 }, /* QSPI0_MISO_IO1 */ - { PIN_QSPI0_IO2, 16, 2 }, /* QSPI0_IO2 */ - { PIN_QSPI0_IO3, 12, 2 }, /* QSPI0_IO3 */ - { PIN_QSPI0_SSL, 8, 2 }, /* QSPI0_SSL */ - { PIN_QSPI1_SPCLK, 4, 2 }, /* QSPI1_SPCLK */ - { PIN_QSPI1_MOSI_IO0, 0, 2 }, /* QSPI1_MOSI_IO0 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL1", 0xe6060304) { - { PIN_QSPI1_MISO_IO1, 28, 2 }, /* QSPI1_MISO_IO1 */ - { PIN_QSPI1_IO2, 24, 2 }, /* QSPI1_IO2 */ - { PIN_QSPI1_IO3, 20, 2 }, /* QSPI1_IO3 */ - { PIN_QSPI1_SSL, 16, 2 }, /* QSPI1_SSL */ - { PIN_RPC_INT_N, 12, 2 }, /* RPC_INT# */ - { PIN_RPC_WP_N, 8, 2 }, /* RPC_WP# */ - { PIN_RPC_RESET_N, 4, 2 }, /* RPC_RESET# */ - { PIN_AVB_RX_CTL, 0, 3 }, /* AVB_RX_CTL */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL2", 0xe6060308) { - { PIN_AVB_RXC, 28, 3 }, /* AVB_RXC */ - { PIN_AVB_RD0, 24, 3 }, /* AVB_RD0 */ - { PIN_AVB_RD1, 20, 3 }, /* AVB_RD1 */ - { PIN_AVB_RD2, 16, 3 }, /* AVB_RD2 */ - { PIN_AVB_RD3, 12, 3 }, /* AVB_RD3 */ - { PIN_AVB_TX_CTL, 8, 3 }, /* AVB_TX_CTL */ - { PIN_AVB_TXC, 4, 3 }, /* AVB_TXC */ - { PIN_AVB_TD0, 0, 3 }, /* AVB_TD0 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL3", 0xe606030c) { - { PIN_AVB_TD1, 28, 3 }, /* AVB_TD1 */ - { PIN_AVB_TD2, 24, 3 }, /* AVB_TD2 */ - { PIN_AVB_TD3, 20, 3 }, /* AVB_TD3 */ - { PIN_AVB_TXCREFCLK, 16, 3 }, /* AVB_TXCREFCLK */ - { PIN_AVB_MDIO, 12, 3 }, /* AVB_MDIO */ - { RCAR_GP_PIN(2, 9), 8, 3 }, /* AVB_MDC */ - { RCAR_GP_PIN(2, 10), 4, 3 }, /* AVB_MAGIC */ - { RCAR_GP_PIN(2, 11), 0, 3 }, /* AVB_PHY_INT */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL4", 0xe6060310) { - { RCAR_GP_PIN(2, 12), 28, 3 }, /* AVB_LINK */ - { RCAR_GP_PIN(2, 13), 24, 3 }, /* AVB_AVTP_MATCH */ - { RCAR_GP_PIN(2, 14), 20, 3 }, /* AVB_AVTP_CAPTURE */ - { RCAR_GP_PIN(2, 0), 16, 3 }, /* IRQ0 */ - { RCAR_GP_PIN(2, 1), 12, 3 }, /* IRQ1 */ - { RCAR_GP_PIN(2, 2), 8, 3 }, /* IRQ2 */ - { RCAR_GP_PIN(2, 3), 4, 3 }, /* IRQ3 */ - { RCAR_GP_PIN(2, 4), 0, 3 }, /* IRQ4 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL5", 0xe6060314) { - { RCAR_GP_PIN(2, 5), 28, 3 }, /* IRQ5 */ - { RCAR_GP_PIN(2, 6), 24, 3 }, /* PWM0 */ - { RCAR_GP_PIN(2, 7), 20, 3 }, /* PWM1 */ - { RCAR_GP_PIN(2, 8), 16, 3 }, /* PWM2 */ - { RCAR_GP_PIN(1, 0), 12, 3 }, /* A0 */ - { RCAR_GP_PIN(1, 1), 8, 3 }, /* A1 */ - { RCAR_GP_PIN(1, 2), 4, 3 }, /* A2 */ - { RCAR_GP_PIN(1, 3), 0, 3 }, /* A3 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL6", 0xe6060318) { - { RCAR_GP_PIN(1, 4), 28, 3 }, /* A4 */ - { RCAR_GP_PIN(1, 5), 24, 3 }, /* A5 */ - { RCAR_GP_PIN(1, 6), 20, 3 }, /* A6 */ - { RCAR_GP_PIN(1, 7), 16, 3 }, /* A7 */ - { RCAR_GP_PIN(1, 8), 12, 3 }, /* A8 */ - { RCAR_GP_PIN(1, 9), 8, 3 }, /* A9 */ - { RCAR_GP_PIN(1, 10), 4, 3 }, /* A10 */ - { RCAR_GP_PIN(1, 11), 0, 3 }, /* A11 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL7", 0xe606031c) { - { RCAR_GP_PIN(1, 12), 28, 3 }, /* A12 */ - { RCAR_GP_PIN(1, 13), 24, 3 }, /* A13 */ - { RCAR_GP_PIN(1, 14), 20, 3 }, /* A14 */ - { RCAR_GP_PIN(1, 15), 16, 3 }, /* A15 */ - { RCAR_GP_PIN(1, 16), 12, 3 }, /* A16 */ - { RCAR_GP_PIN(1, 17), 8, 3 }, /* A17 */ - { RCAR_GP_PIN(1, 18), 4, 3 }, /* A18 */ - { RCAR_GP_PIN(1, 19), 0, 3 }, /* A19 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL8", 0xe6060320) { - { PIN_CLKOUT, 28, 3 }, /* CLKOUT */ - { RCAR_GP_PIN(1, 20), 24, 3 }, /* CS0 */ - { RCAR_GP_PIN(1, 21), 20, 3 }, /* CS1_A26 */ - { RCAR_GP_PIN(1, 22), 16, 3 }, /* BS */ - { RCAR_GP_PIN(1, 23), 12, 3 }, /* RD */ - { RCAR_GP_PIN(1, 24), 8, 3 }, /* RD_WR */ - { RCAR_GP_PIN(1, 25), 4, 3 }, /* WE0 */ - { RCAR_GP_PIN(1, 26), 0, 3 }, /* WE1 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL9", 0xe6060324) { - { RCAR_GP_PIN(1, 27), 28, 3 }, /* EX_WAIT0 */ - { PIN_PRESETOUT_N, 24, 3 }, /* PRESETOUT# */ - { RCAR_GP_PIN(0, 0), 20, 3 }, /* D0 */ - { RCAR_GP_PIN(0, 1), 16, 3 }, /* D1 */ - { RCAR_GP_PIN(0, 2), 12, 3 }, /* D2 */ - { RCAR_GP_PIN(0, 3), 8, 3 }, /* D3 */ - { RCAR_GP_PIN(0, 4), 4, 3 }, /* D4 */ - { RCAR_GP_PIN(0, 5), 0, 3 }, /* D5 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL10", 0xe6060328) { - { RCAR_GP_PIN(0, 6), 28, 3 }, /* D6 */ - { RCAR_GP_PIN(0, 7), 24, 3 }, /* D7 */ - { RCAR_GP_PIN(0, 8), 20, 3 }, /* D8 */ - { RCAR_GP_PIN(0, 9), 16, 3 }, /* D9 */ - { RCAR_GP_PIN(0, 10), 12, 3 }, /* D10 */ - { RCAR_GP_PIN(0, 11), 8, 3 }, /* D11 */ - { RCAR_GP_PIN(0, 12), 4, 3 }, /* D12 */ - { RCAR_GP_PIN(0, 13), 0, 3 }, /* D13 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL11", 0xe606032c) { - { RCAR_GP_PIN(0, 14), 28, 3 }, /* D14 */ - { RCAR_GP_PIN(0, 15), 24, 3 }, /* D15 */ - { RCAR_GP_PIN(7, 0), 20, 3 }, /* AVS1 */ - { RCAR_GP_PIN(7, 1), 16, 3 }, /* AVS2 */ - { RCAR_GP_PIN(7, 2), 12, 3 }, /* GP7_02 */ - { RCAR_GP_PIN(7, 3), 8, 3 }, /* GP7_03 */ - { PIN_DU_DOTCLKIN0, 4, 2 }, /* DU_DOTCLKIN0 */ - { PIN_DU_DOTCLKIN1, 0, 2 }, /* DU_DOTCLKIN1 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL12", 0xe6060330) { - { PIN_DU_DOTCLKIN2, 28, 2 }, /* DU_DOTCLKIN2 */ - { PIN_DU_DOTCLKIN3, 24, 2 }, /* DU_DOTCLKIN3 */ - { PIN_FSCLKST_N, 20, 2 }, /* FSCLKST# */ - { PIN_TMS, 4, 2 }, /* TMS */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL13", 0xe6060334) { - { PIN_TDO, 28, 2 }, /* TDO */ - { PIN_ASEBRK, 24, 2 }, /* ASEBRK */ - { RCAR_GP_PIN(3, 0), 20, 3 }, /* SD0_CLK */ - { RCAR_GP_PIN(3, 1), 16, 3 }, /* SD0_CMD */ - { RCAR_GP_PIN(3, 2), 12, 3 }, /* SD0_DAT0 */ - { RCAR_GP_PIN(3, 3), 8, 3 }, /* SD0_DAT1 */ - { RCAR_GP_PIN(3, 4), 4, 3 }, /* SD0_DAT2 */ - { RCAR_GP_PIN(3, 5), 0, 3 }, /* SD0_DAT3 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL14", 0xe6060338) { - { RCAR_GP_PIN(3, 6), 28, 3 }, /* SD1_CLK */ - { RCAR_GP_PIN(3, 7), 24, 3 }, /* SD1_CMD */ - { RCAR_GP_PIN(3, 8), 20, 3 }, /* SD1_DAT0 */ - { RCAR_GP_PIN(3, 9), 16, 3 }, /* SD1_DAT1 */ - { RCAR_GP_PIN(3, 10), 12, 3 }, /* SD1_DAT2 */ - { RCAR_GP_PIN(3, 11), 8, 3 }, /* SD1_DAT3 */ - { RCAR_GP_PIN(4, 0), 4, 3 }, /* SD2_CLK */ - { RCAR_GP_PIN(4, 1), 0, 3 }, /* SD2_CMD */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL15", 0xe606033c) { - { RCAR_GP_PIN(4, 2), 28, 3 }, /* SD2_DAT0 */ - { RCAR_GP_PIN(4, 3), 24, 3 }, /* SD2_DAT1 */ - { RCAR_GP_PIN(4, 4), 20, 3 }, /* SD2_DAT2 */ - { RCAR_GP_PIN(4, 5), 16, 3 }, /* SD2_DAT3 */ - { RCAR_GP_PIN(4, 6), 12, 3 }, /* SD2_DS */ - { RCAR_GP_PIN(4, 7), 8, 3 }, /* SD3_CLK */ - { RCAR_GP_PIN(4, 8), 4, 3 }, /* SD3_CMD */ - { RCAR_GP_PIN(4, 9), 0, 3 }, /* SD3_DAT0 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL16", 0xe6060340) { - { RCAR_GP_PIN(4, 10), 28, 3 }, /* SD3_DAT1 */ - { RCAR_GP_PIN(4, 11), 24, 3 }, /* SD3_DAT2 */ - { RCAR_GP_PIN(4, 12), 20, 3 }, /* SD3_DAT3 */ - { RCAR_GP_PIN(4, 13), 16, 3 }, /* SD3_DAT4 */ - { RCAR_GP_PIN(4, 14), 12, 3 }, /* SD3_DAT5 */ - { RCAR_GP_PIN(4, 15), 8, 3 }, /* SD3_DAT6 */ - { RCAR_GP_PIN(4, 16), 4, 3 }, /* SD3_DAT7 */ - { RCAR_GP_PIN(4, 17), 0, 3 }, /* SD3_DS */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL17", 0xe6060344) { - { RCAR_GP_PIN(3, 12), 28, 3 }, /* SD0_CD */ - { RCAR_GP_PIN(3, 13), 24, 3 }, /* SD0_WP */ - { RCAR_GP_PIN(3, 14), 20, 3 }, /* SD1_CD */ - { RCAR_GP_PIN(3, 15), 16, 3 }, /* SD1_WP */ - { RCAR_GP_PIN(5, 0), 12, 3 }, /* SCK0 */ - { RCAR_GP_PIN(5, 1), 8, 3 }, /* RX0 */ - { RCAR_GP_PIN(5, 2), 4, 3 }, /* TX0 */ - { RCAR_GP_PIN(5, 3), 0, 3 }, /* CTS0 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL18", 0xe6060348) { - { RCAR_GP_PIN(5, 4), 28, 3 }, /* RTS0 */ - { RCAR_GP_PIN(5, 5), 24, 3 }, /* RX1 */ - { RCAR_GP_PIN(5, 6), 20, 3 }, /* TX1 */ - { RCAR_GP_PIN(5, 7), 16, 3 }, /* CTS1 */ - { RCAR_GP_PIN(5, 8), 12, 3 }, /* RTS1 */ - { RCAR_GP_PIN(5, 9), 8, 3 }, /* SCK2 */ - { RCAR_GP_PIN(5, 10), 4, 3 }, /* TX2 */ - { RCAR_GP_PIN(5, 11), 0, 3 }, /* RX2 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL19", 0xe606034c) { - { RCAR_GP_PIN(5, 12), 28, 3 }, /* HSCK0 */ - { RCAR_GP_PIN(5, 13), 24, 3 }, /* HRX0 */ - { RCAR_GP_PIN(5, 14), 20, 3 }, /* HTX0 */ - { RCAR_GP_PIN(5, 15), 16, 3 }, /* HCTS0 */ - { RCAR_GP_PIN(5, 16), 12, 3 }, /* HRTS0 */ - { RCAR_GP_PIN(5, 17), 8, 3 }, /* MSIOF0_SCK */ - { RCAR_GP_PIN(5, 18), 4, 3 }, /* MSIOF0_SYNC */ - { RCAR_GP_PIN(5, 19), 0, 3 }, /* MSIOF0_SS1 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL20", 0xe6060350) { - { RCAR_GP_PIN(5, 20), 28, 3 }, /* MSIOF0_TXD */ - { RCAR_GP_PIN(5, 21), 24, 3 }, /* MSIOF0_SS2 */ - { RCAR_GP_PIN(5, 22), 20, 3 }, /* MSIOF0_RXD */ - { RCAR_GP_PIN(5, 23), 16, 3 }, /* MLB_CLK */ - { RCAR_GP_PIN(5, 24), 12, 3 }, /* MLB_SIG */ - { RCAR_GP_PIN(5, 25), 8, 3 }, /* MLB_DAT */ - { PIN_MLB_REF, 4, 3 }, /* MLB_REF */ - { RCAR_GP_PIN(6, 0), 0, 3 }, /* SSI_SCK01239 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL21", 0xe6060354) { - { RCAR_GP_PIN(6, 1), 28, 3 }, /* SSI_WS01239 */ - { RCAR_GP_PIN(6, 2), 24, 3 }, /* SSI_SDATA0 */ - { RCAR_GP_PIN(6, 3), 20, 3 }, /* SSI_SDATA1 */ - { RCAR_GP_PIN(6, 4), 16, 3 }, /* SSI_SDATA2 */ - { RCAR_GP_PIN(6, 5), 12, 3 }, /* SSI_SCK349 */ - { RCAR_GP_PIN(6, 6), 8, 3 }, /* SSI_WS349 */ - { RCAR_GP_PIN(6, 7), 4, 3 }, /* SSI_SDATA3 */ - { RCAR_GP_PIN(6, 8), 0, 3 }, /* SSI_SCK4 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL22", 0xe6060358) { - { RCAR_GP_PIN(6, 9), 28, 3 }, /* SSI_WS4 */ - { RCAR_GP_PIN(6, 10), 24, 3 }, /* SSI_SDATA4 */ - { RCAR_GP_PIN(6, 11), 20, 3 }, /* SSI_SCK5 */ - { RCAR_GP_PIN(6, 12), 16, 3 }, /* SSI_WS5 */ - { RCAR_GP_PIN(6, 13), 12, 3 }, /* SSI_SDATA5 */ - { RCAR_GP_PIN(6, 14), 8, 3 }, /* SSI_SCK6 */ - { RCAR_GP_PIN(6, 15), 4, 3 }, /* SSI_WS6 */ - { RCAR_GP_PIN(6, 16), 0, 3 }, /* SSI_SDATA6 */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL23", 0xe606035c) { - { RCAR_GP_PIN(6, 17), 28, 3 }, /* SSI_SCK78 */ - { RCAR_GP_PIN(6, 18), 24, 3 }, /* SSI_WS78 */ - { RCAR_GP_PIN(6, 19), 20, 3 }, /* SSI_SDATA7 */ - { RCAR_GP_PIN(6, 20), 16, 3 }, /* SSI_SDATA8 */ - { RCAR_GP_PIN(6, 21), 12, 3 }, /* SSI_SDATA9 */ - { RCAR_GP_PIN(6, 22), 8, 3 }, /* AUDIO_CLKA */ - { RCAR_GP_PIN(6, 23), 4, 3 }, /* AUDIO_CLKB */ - { RCAR_GP_PIN(6, 24), 0, 3 }, /* USB0_PWEN */ - } }, - { PINMUX_DRIVE_REG("DRVCTRL24", 0xe6060360) { - { RCAR_GP_PIN(6, 25), 28, 3 }, /* USB0_OVC */ - { RCAR_GP_PIN(6, 26), 24, 3 }, /* USB1_PWEN */ - { RCAR_GP_PIN(6, 27), 20, 3 }, /* USB1_OVC */ - { RCAR_GP_PIN(6, 28), 16, 3 }, /* USB30_PWEN */ - { RCAR_GP_PIN(6, 29), 12, 3 }, /* USB30_OVC */ - { RCAR_GP_PIN(6, 30), 8, 3 }, /* USB31_PWEN */ - { RCAR_GP_PIN(6, 31), 4, 3 }, /* USB31_OVC */ - } }, - { }, -}; - -enum ioctrl_regs { - POCCTRL, - TDSELCTRL, -}; - -static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { - [POCCTRL] = { 0xe6060380, }, - [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, -}; - -static int r8a77950_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) -{ - int bit = -EINVAL; - - *pocctrl = pinmux_ioctrl_regs[POCCTRL].reg; - - if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 11)) - bit = pin & 0x1f; - - if (pin >= RCAR_GP_PIN(4, 0) && pin <= RCAR_GP_PIN(4, 17)) - bit = (pin & 0x1f) + 12; - - return bit; -} - -static const struct pinmux_bias_reg pinmux_bias_regs[] = { - { PINMUX_BIAS_REG("PUEN0", 0xe6060400, "PUD0", 0xe6060440) { - [ 0] = PIN_QSPI0_SPCLK, /* QSPI0_SPCLK */ - [ 1] = PIN_QSPI0_MOSI_IO0, /* QSPI0_MOSI_IO0 */ - [ 2] = PIN_QSPI0_MISO_IO1, /* QSPI0_MISO_IO1 */ - [ 3] = PIN_QSPI0_IO2, /* QSPI0_IO2 */ - [ 4] = PIN_QSPI0_IO3, /* QSPI0_IO3 */ - [ 5] = PIN_QSPI0_SSL, /* QSPI0_SSL */ - [ 6] = PIN_QSPI1_SPCLK, /* QSPI1_SPCLK */ - [ 7] = PIN_QSPI1_MOSI_IO0, /* QSPI1_MOSI_IO0 */ - [ 8] = PIN_QSPI1_MISO_IO1, /* QSPI1_MISO_IO1 */ - [ 9] = PIN_QSPI1_IO2, /* QSPI1_IO2 */ - [10] = PIN_QSPI1_IO3, /* QSPI1_IO3 */ - [11] = PIN_QSPI1_SSL, /* QSPI1_SSL */ - [12] = PIN_RPC_INT_N, /* RPC_INT# */ - [13] = PIN_RPC_WP_N, /* RPC_WP# */ - [14] = PIN_RPC_RESET_N, /* RPC_RESET# */ - [15] = PIN_AVB_RX_CTL, /* AVB_RX_CTL */ - [16] = PIN_AVB_RXC, /* AVB_RXC */ - [17] = PIN_AVB_RD0, /* AVB_RD0 */ - [18] = PIN_AVB_RD1, /* AVB_RD1 */ - [19] = PIN_AVB_RD2, /* AVB_RD2 */ - [20] = PIN_AVB_RD3, /* AVB_RD3 */ - [21] = PIN_AVB_TX_CTL, /* AVB_TX_CTL */ - [22] = PIN_AVB_TXC, /* AVB_TXC */ - [23] = PIN_AVB_TD0, /* AVB_TD0 */ - [24] = PIN_AVB_TD1, /* AVB_TD1 */ - [25] = PIN_AVB_TD2, /* AVB_TD2 */ - [26] = PIN_AVB_TD3, /* AVB_TD3 */ - [27] = PIN_AVB_TXCREFCLK, /* AVB_TXCREFCLK */ - [28] = PIN_AVB_MDIO, /* AVB_MDIO */ - [29] = RCAR_GP_PIN(2, 9), /* AVB_MDC */ - [30] = RCAR_GP_PIN(2, 10), /* AVB_MAGIC */ - [31] = RCAR_GP_PIN(2, 11), /* AVB_PHY_INT */ - } }, - { PINMUX_BIAS_REG("PUEN1", 0xe6060404, "PUD1", 0xe6060444) { - [ 0] = RCAR_GP_PIN(2, 12), /* AVB_LINK */ - [ 1] = RCAR_GP_PIN(2, 13), /* AVB_AVTP_MATCH_A */ - [ 2] = RCAR_GP_PIN(2, 14), /* AVB_AVTP_CAPTURE_A */ - [ 3] = RCAR_GP_PIN(2, 0), /* IRQ0 */ - [ 4] = RCAR_GP_PIN(2, 1), /* IRQ1 */ - [ 5] = RCAR_GP_PIN(2, 2), /* IRQ2 */ - [ 6] = RCAR_GP_PIN(2, 3), /* IRQ3 */ - [ 7] = RCAR_GP_PIN(2, 4), /* IRQ4 */ - [ 8] = RCAR_GP_PIN(2, 5), /* IRQ5 */ - [ 9] = RCAR_GP_PIN(2, 6), /* PWM0 */ - [10] = RCAR_GP_PIN(2, 7), /* PWM1_A */ - [11] = RCAR_GP_PIN(2, 8), /* PWM2_A */ - [12] = RCAR_GP_PIN(1, 0), /* A0 */ - [13] = RCAR_GP_PIN(1, 1), /* A1 */ - [14] = RCAR_GP_PIN(1, 2), /* A2 */ - [15] = RCAR_GP_PIN(1, 3), /* A3 */ - [16] = RCAR_GP_PIN(1, 4), /* A4 */ - [17] = RCAR_GP_PIN(1, 5), /* A5 */ - [18] = RCAR_GP_PIN(1, 6), /* A6 */ - [19] = RCAR_GP_PIN(1, 7), /* A7 */ - [20] = RCAR_GP_PIN(1, 8), /* A8 */ - [21] = RCAR_GP_PIN(1, 9), /* A9 */ - [22] = RCAR_GP_PIN(1, 10), /* A10 */ - [23] = RCAR_GP_PIN(1, 11), /* A11 */ - [24] = RCAR_GP_PIN(1, 12), /* A12 */ - [25] = RCAR_GP_PIN(1, 13), /* A13 */ - [26] = RCAR_GP_PIN(1, 14), /* A14 */ - [27] = RCAR_GP_PIN(1, 15), /* A15 */ - [28] = RCAR_GP_PIN(1, 16), /* A16 */ - [29] = RCAR_GP_PIN(1, 17), /* A17 */ - [30] = RCAR_GP_PIN(1, 18), /* A18 */ - [31] = RCAR_GP_PIN(1, 19), /* A19 */ - } }, - { PINMUX_BIAS_REG("PUEN2", 0xe6060408, "PUD2", 0xe6060448) { - [ 0] = PIN_CLKOUT, /* CLKOUT */ - [ 1] = RCAR_GP_PIN(1, 20), /* CS0_N */ - [ 2] = RCAR_GP_PIN(1, 21), /* CS1_N_A26 */ - [ 3] = RCAR_GP_PIN(1, 22), /* BS_N */ - [ 4] = RCAR_GP_PIN(1, 23), /* RD_N */ - [ 5] = RCAR_GP_PIN(1, 24), /* RD_WR_N */ - [ 6] = RCAR_GP_PIN(1, 25), /* WE0_N */ - [ 7] = RCAR_GP_PIN(1, 26), /* WE1_N */ - [ 8] = RCAR_GP_PIN(1, 27), /* EX_WAIT0_A */ - [ 9] = PIN_PRESETOUT_N, /* PRESETOUT# */ - [10] = RCAR_GP_PIN(0, 0), /* D0 */ - [11] = RCAR_GP_PIN(0, 1), /* D1 */ - [12] = RCAR_GP_PIN(0, 2), /* D2 */ - [13] = RCAR_GP_PIN(0, 3), /* D3 */ - [14] = RCAR_GP_PIN(0, 4), /* D4 */ - [15] = RCAR_GP_PIN(0, 5), /* D5 */ - [16] = RCAR_GP_PIN(0, 6), /* D6 */ - [17] = RCAR_GP_PIN(0, 7), /* D7 */ - [18] = RCAR_GP_PIN(0, 8), /* D8 */ - [19] = RCAR_GP_PIN(0, 9), /* D9 */ - [20] = RCAR_GP_PIN(0, 10), /* D10 */ - [21] = RCAR_GP_PIN(0, 11), /* D11 */ - [22] = RCAR_GP_PIN(0, 12), /* D12 */ - [23] = RCAR_GP_PIN(0, 13), /* D13 */ - [24] = RCAR_GP_PIN(0, 14), /* D14 */ - [25] = RCAR_GP_PIN(0, 15), /* D15 */ - [26] = RCAR_GP_PIN(7, 0), /* AVS1 */ - [27] = RCAR_GP_PIN(7, 1), /* AVS2 */ - [28] = RCAR_GP_PIN(7, 2), /* GP7_02 */ - [29] = RCAR_GP_PIN(7, 3), /* GP7_03 */ - [30] = PIN_DU_DOTCLKIN0, /* DU_DOTCLKIN0 */ - [31] = PIN_DU_DOTCLKIN1, /* DU_DOTCLKIN1 */ - } }, - { PINMUX_BIAS_REG("PUEN3", 0xe606040c, "PUD3", 0xe606044c) { - [ 0] = PIN_DU_DOTCLKIN2, /* DU_DOTCLKIN2 */ - [ 1] = PIN_DU_DOTCLKIN3, /* DU_DOTCLKIN3 */ - [ 2] = PIN_FSCLKST_N, /* FSCLKST# */ - [ 3] = PIN_EXTALR, /* EXTALR*/ - [ 4] = PIN_TRST_N, /* TRST# */ - [ 5] = PIN_TCK, /* TCK */ - [ 6] = PIN_TMS, /* TMS */ - [ 7] = PIN_TDI, /* TDI */ - [ 8] = SH_PFC_PIN_NONE, - [ 9] = PIN_ASEBRK, /* ASEBRK */ - [10] = RCAR_GP_PIN(3, 0), /* SD0_CLK */ - [11] = RCAR_GP_PIN(3, 1), /* SD0_CMD */ - [12] = RCAR_GP_PIN(3, 2), /* SD0_DAT0 */ - [13] = RCAR_GP_PIN(3, 3), /* SD0_DAT1 */ - [14] = RCAR_GP_PIN(3, 4), /* SD0_DAT2 */ - [15] = RCAR_GP_PIN(3, 5), /* SD0_DAT3 */ - [16] = RCAR_GP_PIN(3, 6), /* SD1_CLK */ - [17] = RCAR_GP_PIN(3, 7), /* SD1_CMD */ - [18] = RCAR_GP_PIN(3, 8), /* SD1_DAT0 */ - [19] = RCAR_GP_PIN(3, 9), /* SD1_DAT1 */ - [20] = RCAR_GP_PIN(3, 10), /* SD1_DAT2 */ - [21] = RCAR_GP_PIN(3, 11), /* SD1_DAT3 */ - [22] = RCAR_GP_PIN(4, 0), /* SD2_CLK */ - [23] = RCAR_GP_PIN(4, 1), /* SD2_CMD */ - [24] = RCAR_GP_PIN(4, 2), /* SD2_DAT0 */ - [25] = RCAR_GP_PIN(4, 3), /* SD2_DAT1 */ - [26] = RCAR_GP_PIN(4, 4), /* SD2_DAT2 */ - [27] = RCAR_GP_PIN(4, 5), /* SD2_DAT3 */ - [28] = RCAR_GP_PIN(4, 6), /* SD2_DS */ - [29] = RCAR_GP_PIN(4, 7), /* SD3_CLK */ - [30] = RCAR_GP_PIN(4, 8), /* SD3_CMD */ - [31] = RCAR_GP_PIN(4, 9), /* SD3_DAT0 */ - } }, - { PINMUX_BIAS_REG("PUEN4", 0xe6060410, "PUD4", 0xe6060450) { - [ 0] = RCAR_GP_PIN(4, 10), /* SD3_DAT1 */ - [ 1] = RCAR_GP_PIN(4, 11), /* SD3_DAT2 */ - [ 2] = RCAR_GP_PIN(4, 12), /* SD3_DAT3 */ - [ 3] = RCAR_GP_PIN(4, 13), /* SD3_DAT4 */ - [ 4] = RCAR_GP_PIN(4, 14), /* SD3_DAT5 */ - [ 5] = RCAR_GP_PIN(4, 15), /* SD3_DAT6 */ - [ 6] = RCAR_GP_PIN(4, 16), /* SD3_DAT7 */ - [ 7] = RCAR_GP_PIN(4, 17), /* SD3_DS */ - [ 8] = RCAR_GP_PIN(3, 12), /* SD0_CD */ - [ 9] = RCAR_GP_PIN(3, 13), /* SD0_WP */ - [10] = RCAR_GP_PIN(3, 14), /* SD1_CD */ - [11] = RCAR_GP_PIN(3, 15), /* SD1_WP */ - [12] = RCAR_GP_PIN(5, 0), /* SCK0 */ - [13] = RCAR_GP_PIN(5, 1), /* RX0 */ - [14] = RCAR_GP_PIN(5, 2), /* TX0 */ - [15] = RCAR_GP_PIN(5, 3), /* CTS0_N */ - [16] = RCAR_GP_PIN(5, 4), /* RTS0_N */ - [17] = RCAR_GP_PIN(5, 5), /* RX1_A */ - [18] = RCAR_GP_PIN(5, 6), /* TX1_A */ - [19] = RCAR_GP_PIN(5, 7), /* CTS1_N */ - [20] = RCAR_GP_PIN(5, 8), /* RTS1_N */ - [21] = RCAR_GP_PIN(5, 9), /* SCK2 */ - [22] = RCAR_GP_PIN(5, 10), /* TX2_A */ - [23] = RCAR_GP_PIN(5, 11), /* RX2_A */ - [24] = RCAR_GP_PIN(5, 12), /* HSCK0 */ - [25] = RCAR_GP_PIN(5, 13), /* HRX0 */ - [26] = RCAR_GP_PIN(5, 14), /* HTX0 */ - [27] = RCAR_GP_PIN(5, 15), /* HCTS0_N */ - [28] = RCAR_GP_PIN(5, 16), /* HRTS0_N */ - [29] = RCAR_GP_PIN(5, 17), /* MSIOF0_SCK */ - [30] = RCAR_GP_PIN(5, 18), /* MSIOF0_SYNC */ - [31] = RCAR_GP_PIN(5, 19), /* MSIOF0_SS1 */ - } }, - { PINMUX_BIAS_REG("PUEN5", 0xe6060414, "PUD5", 0xe6060454) { - [ 0] = RCAR_GP_PIN(5, 20), /* MSIOF0_TXD */ - [ 1] = RCAR_GP_PIN(5, 21), /* MSIOF0_SS2 */ - [ 2] = RCAR_GP_PIN(5, 22), /* MSIOF0_RXD */ - [ 3] = RCAR_GP_PIN(5, 23), /* MLB_CLK */ - [ 4] = RCAR_GP_PIN(5, 24), /* MLB_SIG */ - [ 5] = RCAR_GP_PIN(5, 25), /* MLB_DAT */ - [ 6] = PIN_MLB_REF, /* MLB_REF */ - [ 7] = RCAR_GP_PIN(6, 0), /* SSI_SCK01239 */ - [ 8] = RCAR_GP_PIN(6, 1), /* SSI_WS01239 */ - [ 9] = RCAR_GP_PIN(6, 2), /* SSI_SDATA0 */ - [10] = RCAR_GP_PIN(6, 3), /* SSI_SDATA1_A */ - [11] = RCAR_GP_PIN(6, 4), /* SSI_SDATA2_A */ - [12] = RCAR_GP_PIN(6, 5), /* SSI_SCK349 */ - [13] = RCAR_GP_PIN(6, 6), /* SSI_WS349 */ - [14] = RCAR_GP_PIN(6, 7), /* SSI_SDATA3 */ - [15] = RCAR_GP_PIN(6, 8), /* SSI_SCK4 */ - [16] = RCAR_GP_PIN(6, 9), /* SSI_WS4 */ - [17] = RCAR_GP_PIN(6, 10), /* SSI_SDATA4 */ - [18] = RCAR_GP_PIN(6, 11), /* SSI_SCK5 */ - [19] = RCAR_GP_PIN(6, 12), /* SSI_WS5 */ - [20] = RCAR_GP_PIN(6, 13), /* SSI_SDATA5 */ - [21] = RCAR_GP_PIN(6, 14), /* SSI_SCK6 */ - [22] = RCAR_GP_PIN(6, 15), /* SSI_WS6 */ - [23] = RCAR_GP_PIN(6, 16), /* SSI_SDATA6 */ - [24] = RCAR_GP_PIN(6, 17), /* SSI_SCK78 */ - [25] = RCAR_GP_PIN(6, 18), /* SSI_WS78 */ - [26] = RCAR_GP_PIN(6, 19), /* SSI_SDATA7 */ - [27] = RCAR_GP_PIN(6, 20), /* SSI_SDATA8 */ - [28] = RCAR_GP_PIN(6, 21), /* SSI_SDATA9_A */ - [29] = RCAR_GP_PIN(6, 22), /* AUDIO_CLKA_A */ - [30] = RCAR_GP_PIN(6, 23), /* AUDIO_CLKB_B */ - [31] = RCAR_GP_PIN(6, 24), /* USB0_PWEN */ - } }, - { PINMUX_BIAS_REG("PUEN6", 0xe6060418, "PUD6", 0xe6060458) { - [ 0] = RCAR_GP_PIN(6, 25), /* USB0_OVC */ - [ 1] = RCAR_GP_PIN(6, 26), /* USB1_PWEN */ - [ 2] = RCAR_GP_PIN(6, 27), /* USB1_OVC */ - [ 3] = RCAR_GP_PIN(6, 28), /* USB30_PWEN */ - [ 4] = RCAR_GP_PIN(6, 29), /* USB30_OVC */ - [ 5] = RCAR_GP_PIN(6, 30), /* USB31_PWEN */ - [ 6] = RCAR_GP_PIN(6, 31), /* USB31_OVC */ - [ 7] = SH_PFC_PIN_NONE, - [ 8] = SH_PFC_PIN_NONE, - [ 9] = SH_PFC_PIN_NONE, - [10] = SH_PFC_PIN_NONE, - [11] = SH_PFC_PIN_NONE, - [12] = SH_PFC_PIN_NONE, - [13] = SH_PFC_PIN_NONE, - [14] = SH_PFC_PIN_NONE, - [15] = SH_PFC_PIN_NONE, - [16] = SH_PFC_PIN_NONE, - [17] = SH_PFC_PIN_NONE, - [18] = SH_PFC_PIN_NONE, - [19] = SH_PFC_PIN_NONE, - [20] = SH_PFC_PIN_NONE, - [21] = SH_PFC_PIN_NONE, - [22] = SH_PFC_PIN_NONE, - [23] = SH_PFC_PIN_NONE, - [24] = SH_PFC_PIN_NONE, - [25] = SH_PFC_PIN_NONE, - [26] = SH_PFC_PIN_NONE, - [27] = SH_PFC_PIN_NONE, - [28] = SH_PFC_PIN_NONE, - [29] = SH_PFC_PIN_NONE, - [30] = SH_PFC_PIN_NONE, - [31] = SH_PFC_PIN_NONE, - } }, - { /* sentinel */ }, -}; - -static const struct sh_pfc_soc_operations r8a77950_pfc_ops = { - .pin_to_pocctrl = r8a77950_pin_to_pocctrl, - .get_bias = rcar_pinmux_get_bias, - .set_bias = rcar_pinmux_set_bias, -}; - -const struct sh_pfc_soc_info r8a77950_pinmux_info = { - .name = "r8a77950_pfc", - .ops = &r8a77950_pfc_ops, - .unlock_reg = 0xe6060000, /* PMMR */ - - .function = { PINMUX_FUNCTION_BEGIN, PINMUX_FUNCTION_END }, - - .pins = pinmux_pins, - .nr_pins = ARRAY_SIZE(pinmux_pins), - .groups = pinmux_groups, - .nr_groups = ARRAY_SIZE(pinmux_groups), - .functions = pinmux_functions, - .nr_functions = ARRAY_SIZE(pinmux_functions), - - .cfg_regs = pinmux_config_regs, - .drive_regs = pinmux_drive_regs, - .bias_regs = pinmux_bias_regs, - .ioctrl_regs = pinmux_ioctrl_regs, - - .pinmux_data = pinmux_data, - .pinmux_data_size = ARRAY_SIZE(pinmux_data), -}; diff --git a/drivers/pinctrl/renesas/sh_pfc.h b/drivers/pinctrl/renesas/sh_pfc.h index 0fcb29ab0c84..83312fac14e5 100644 --- a/drivers/pinctrl/renesas/sh_pfc.h +++ b/drivers/pinctrl/renesas/sh_pfc.h @@ -314,7 +314,6 @@ extern const struct sh_pfc_soc_info r8a7791_pinmux_info; extern const struct sh_pfc_soc_info r8a7792_pinmux_info; extern const struct sh_pfc_soc_info r8a7793_pinmux_info; extern const struct sh_pfc_soc_info r8a7794_pinmux_info; -extern const struct sh_pfc_soc_info r8a77950_pinmux_info; extern const struct sh_pfc_soc_info r8a77951_pinmux_info; extern const struct sh_pfc_soc_info r8a77960_pinmux_info; extern const struct sh_pfc_soc_info r8a77961_pinmux_info; -- GitLab From 05777499a81298ef7e4a5e32a6f744f1f937a80c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 10 Mar 2023 15:01:26 +0100 Subject: [PATCH 0254/5631] ARM: dyndbg: allow including dyndbg.h in decompressor After a change to linux/module.h, dyndbg.h is now included indirectly from the decompressor for lz4 support, which in turn causes a build failure on 32-bit Arm: In file included from include/linux/module.h:30, from arch/arm/boot/compressed/../../../../lib/lz4/lz4_decompress.c:39, from arch/arm/boot/compressed/../../../../lib/decompress_unlz4.c:10, from arch/arm/boot/compressed/decompress.c:59: include/linux/dynamic_debug.h: In function 'ddebug_dyndbg_module_param_cb': include/linux/dynamic_debug.h:307:14: error: implicit declaration of function 'strcmp' [-Werror=implicit-function-declaration] 307 | if (!strcmp(param, "dyndbg")) { | ^~~~~~ include/linux/dynamic_debug.h:1:1: note: 'strcmp' is defined in header ''; did you forget to '#include '? +++ |+#include The decompressor has its own replacement for the linux/string.h contents, so the normal declaration is not visible here. Since the function is not actually called, it is sufficient to add a declaration, and this is in fact the correct one as it matches the definition in arch/arm/boot/compressed/string.c. Fixes: 7deabd674988 ("dyndbg: use the module notifier callbacks") Signed-off-by: Arnd Bergmann Acked-by: Jason Baron Reviewed-by: Vincenzo Palazzo Signed-off-by: Luis Chamberlain --- arch/arm/boot/compressed/decompress.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c index 74255e819831..0669851394f0 100644 --- a/arch/arm/boot/compressed/decompress.c +++ b/arch/arm/boot/compressed/decompress.c @@ -31,6 +31,7 @@ /* Not needed, but used in some headers pulled in by decompressors */ extern char * strstr(const char * s1, const char *s2); extern size_t strlen(const char *s); +extern int strcmp(const char *cs, const char *ct); extern int memcmp(const void *cs, const void *ct, size_t count); extern char * strchrnul(const char *, int); -- GitLab From 557aafac11530a283bebf2dea4cec62765d8df0f Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 10:55:59 -0800 Subject: [PATCH 0255/5631] kernel/module: add documentation for try_module_get() There is quite a bit of tribal knowledge around proper use of try_module_get() and requiring *somehow* the module to still exist to use this call in a way that is safe. Document this bit of tribal knowledge. To be clear, you should only use try_module_get() *iff* you are 100% sure the module already does exist and is not on its way out. You can be sure the module still exists and is alive through: 1) Direct protection with its refcount: you know some earlier caller called __module_get() safely 2) Implied protection: there is an implied protection against module removal Having an idea of when you are sure __module_get() might be called earlier is easy to understand however the implied protection requires an example. We use sysfs an an example for implied protection without a direct module reference count bump. kernfs / sysfs uses its own internal reference counting for files being actively used, when such file are active they completely prevent the module from being removed. kernfs protects this with its kernfs_active(). Effort has been put into verifying the kernfs implied protection works by using a currently out-of-tree test_sysfs selftest test #32 [0]: ./tools/testing/selftests/sysfs/sysfs.sh -t 0032 Without kernfs / sysfs preventing module removal through its active reference count (kernfs_active()) the write would fail or worse, a crash would happen in this test and it does not. Similar safeguards are required for other users of try_module_get() *iff* they are not ensuring the above rule 1) is followed. [0] https://lore.kernel.org/lkml/20211029184500.2821444-4-mcgrof@kernel.org/ Signed-off-by: Luis Chamberlain --- include/linux/module.h | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) diff --git a/include/linux/module.h b/include/linux/module.h index 91726444d55f..c3b357196470 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -671,10 +671,46 @@ void symbol_put_addr(void *addr); to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); -/* This is the Right Way to get a module: if it fails, it's being removed, - * so pretend it's not there. */ +/** + * try_module_get() - take module refcount unless module is being removed + * @module: the module we should check for + * + * Only try to get a module reference count if the module is not being removed. + * This call will fail if the module is already being removed. + * + * Care must also be taken to ensure the module exists and is alive prior to + * usage of this call. This can be gauranteed through two means: + * + * 1) Direct protection: you know an earlier caller must have increased the + * module reference through __module_get(). This can typically be achieved + * by having another entity other than the module itself increment the + * module reference count. + * + * 2) Implied protection: there is an implied protection against module + * removal. An example of this is the implied protection used by kernfs / + * sysfs. The sysfs store / read file operations are guaranteed to exist + * through the use of kernfs's active reference (see kernfs_active()) and a + * sysfs / kernfs file removal cannot happen unless the same file is not + * active. Therefore, if a sysfs file is being read or written to the module + * which created it must still exist. It is therefore safe to use + * try_module_get() on module sysfs store / read ops. + * + * One of the real values to try_module_get() is the module_is_live() check + * which ensures that the caller of try_module_get() can yield to userspace + * module removal requests and gracefully fail if the module is on its way out. + * + * Returns true if the reference count was successfully incremented. + */ extern bool try_module_get(struct module *module); +/** + * module_put() - release a reference count to a module + * @module: the module we should release a reference count for + * + * If you successfully bump a reference count to a module with try_module_get(), + * when you are finished you must call module_put() to release that reference + * count. + */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ -- GitLab From 8b6f18a0e20daee13be77970acf410a7fda6d0b8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Sun, 29 Jan 2023 14:20:20 +0100 Subject: [PATCH 0256/5631] iio: chemical: sps030: Reformat comment in a more readable way MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's easier to see the (lack of) difference between the lines when they are visually aligned. Signed-off-by: Jonathan Neuschäfer Link: https://lore.kernel.org/r/20230129132020.1352368-1-j.neuschaefer@gmx.net Signed-off-by: Jonathan Cameron --- drivers/iio/chemical/sps30_i2c.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/chemical/sps30_i2c.c b/drivers/iio/chemical/sps30_i2c.c index 2aed483a2fde..0cb5d9b65d62 100644 --- a/drivers/iio/chemical/sps30_i2c.c +++ b/drivers/iio/chemical/sps30_i2c.c @@ -68,10 +68,10 @@ static int sps30_i2c_command(struct sps30_state *state, u16 cmd, void *arg, size /* * Internally sensor stores measurements in a following manner: * - * PM1: upper two bytes, crc8, lower two bytes, crc8 + * PM1: upper two bytes, crc8, lower two bytes, crc8 * PM2P5: upper two bytes, crc8, lower two bytes, crc8 - * PM4: upper two bytes, crc8, lower two bytes, crc8 - * PM10: upper two bytes, crc8, lower two bytes, crc8 + * PM4: upper two bytes, crc8, lower two bytes, crc8 + * PM10: upper two bytes, crc8, lower two bytes, crc8 * * What follows next are number concentration measurements and * typical particle size measurement which we omit. -- GitLab From e932fb64c017dccbee44b7ee781584dbc65449ed Mon Sep 17 00:00:00 2001 From: Mehdi Djait Date: Sun, 29 Jan 2023 14:37:46 +0100 Subject: [PATCH 0257/5631] iio: accel: kionix-kx022a: Remove the unused member g_range The g_range member of the driver data struct is not used and should therefore be removed. Signed-off-by: Mehdi Djait Reviewed-by: Matti Vaittinen Link: https://lore.kernel.org/r/e884d53fed0d8322d8be1de2593d4f5f8975af9c.1674996464.git.mehdi.djait.k@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kionix-kx022a.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index f866859855cd..9f8c7631f098 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -162,7 +162,6 @@ struct kx022a_data { int inc_reg; int ien_reg; - unsigned int g_range; unsigned int state; unsigned int odr_ns; -- GitLab From cd62d4f39a0de0c2936ecaae938ba444d77c902a Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 24 Oct 2022 13:34:15 +0200 Subject: [PATCH 0258/5631] dt-bindings: iio: adc: renesas,rcar-gyroadc: Miscellaneous improvements Set limits on the number of power-domains and resets, and make them required. Simplify the example, and update it to match reality: - Convert from obsolete MSTP to CPG/MSSR bindings, - Examples should use #{address,size}-cells = <1>, - Add missing resets property, - Drop soc container and pinctrl properties, which are not needed in examples. Signed-off-by: Geert Uytterhoeven Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/7b7a13680fa24282c3407e12b5943a66a2ed9068.1666611184.git.geert+renesas@glider.be Signed-off-by: Jonathan Cameron --- .../iio/adc/renesas,rcar-gyroadc.yaml | 60 +++++++++---------- 1 file changed, 29 insertions(+), 31 deletions(-) diff --git a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml index c115e2e99bd9..1c7aee5ed3e0 100644 --- a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml @@ -34,9 +34,11 @@ properties: clock-names: const: fck - power-domains: true + power-domains: + maxItems: 1 - resets: true + resets: + maxItems: 1 "#address-cells": const: 1 @@ -51,6 +53,8 @@ required: - reg - clocks - clock-names + - power-domains + - resets - "#address-cells" - "#size-cells" @@ -108,36 +112,30 @@ patternProperties: examples: - | - #include + #include #include - soc { - #address-cells = <2>; - #size-cells = <2>; - - adc@e6e54000 { - compatible = "renesas,r8a7791-gyroadc", "renesas,rcar-gyroadc"; - reg = <0 0xe6e54000 0 64>; - clocks = <&mstp9_clks R8A7791_CLK_GYROADC>; - clock-names = "fck"; - power-domains = <&sysc R8A7791_PD_ALWAYS_ON>; - - pinctrl-0 = <&adc_pins>; - pinctrl-names = "default"; - - #address-cells = <1>; - #size-cells = <0>; - - adc@0 { - reg = <0>; - compatible = "maxim,max1162"; - vref-supply = <&vref_max1162>; - }; - - adc@1 { - reg = <1>; - compatible = "maxim,max1162"; - vref-supply = <&vref_max1162>; - }; + + adc@e6e54000 { + compatible = "renesas,r8a7791-gyroadc", "renesas,rcar-gyroadc"; + reg = <0xe6e54000 64>; + clocks = <&cpg CPG_MOD 901>; + clock-names = "fck"; + power-domains = <&sysc R8A7791_PD_ALWAYS_ON>; + resets = <&cpg 901>; + + #address-cells = <1>; + #size-cells = <0>; + + adc@0 { + reg = <0>; + compatible = "maxim,max1162"; + vref-supply = <&vref_max1162>; + }; + + adc@1 { + reg = <1>; + compatible = "maxim,max1162"; + vref-supply = <&vref_max1162>; }; }; ... -- GitLab From 390738596ccf565047f1db0c3c17753018da5196 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Thu, 17 Nov 2022 11:01:30 +0200 Subject: [PATCH 0259/5631] drivers: iio: dac: ad5592r: add gpio_chip names Add array of explicit gpio names for the `gpiochip` structure of ad5592r, mainly for debug purposes. Since the gpios are configurable via the dts, generic names are used. Signed-off-by: Antoniu Miclaus Link: https://lore.kernel.org/r/20221117090130.51702-1-antoniu.miclaus@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/dac/ad5592r-base.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 7a9b5fc1e579..076bc9ecfb49 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -124,6 +124,10 @@ static int ad5592r_gpio_request(struct gpio_chip *chip, unsigned offset) return 0; } +static const char * const ad5592r_gpio_names[] = { + "GPIO0", "GPIO1", "GPIO2", "GPIO3", "GPIO4", "GPIO5", "GPIO6", "GPIO7", +}; + static int ad5592r_gpio_init(struct ad5592r_state *st) { if (!st->gpio_map) @@ -140,6 +144,7 @@ static int ad5592r_gpio_init(struct ad5592r_state *st) st->gpiochip.set = ad5592r_gpio_set; st->gpiochip.request = ad5592r_gpio_request; st->gpiochip.owner = THIS_MODULE; + st->gpiochip.names = ad5592r_gpio_names; mutex_init(&st->gpio_lock); -- GitLab From f22ed8d9e804e403b204d1926138490d6ad35ed2 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 14 Jan 2023 17:29:28 +0000 Subject: [PATCH 0260/5631] iio: proximity: sx_common: Drop documentation of non existent struct element. struct sx_common_data doesn't have a num_default_regs element so drop the documentation for it. Signed-off-by: Jonathan Cameron Cc: Gwendal Grignou Cc: Stephen Boyd Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20230114172928.80414-1-jic23@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/sx_common.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iio/proximity/sx_common.h b/drivers/iio/proximity/sx_common.h index 49d4517103b0..a2bbdef200d1 100644 --- a/drivers/iio/proximity/sx_common.h +++ b/drivers/iio/proximity/sx_common.h @@ -101,7 +101,6 @@ struct sx_common_chip_info { * @client: I2C client structure. * @trig: IIO trigger object. * @regmap: Register map. - * @num_default_regs: Number of default registers to set at init. * @chan_prox_stat: Last reading of the proximity status for each channel. * We only send an event to user space when this changes. * @trigger_enabled: True when the device trigger is enabled. -- GitLab From 6d5f85de2d610d652ab7e90fea19a85c58b8df04 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 29 Jan 2023 16:08:05 +0000 Subject: [PATCH 0261/5631] staging: iio: meter: Drop ade7854 driver This driver is so far from making correct use of the IIO infrastructure and ABI that if someone wanted to make the driver suitable for moving out of staging, they would more or less be starting from scratch. As such there is little point in keeping the existing code in staging. Note this was only user of the meter.h header so that is dropped. There are no other drivers in the staging/iio/meter directory so drop the build system files as well. Signed-off-by: Jonathan Cameron Acked-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230129160805.747745-1-jic23@kernel.org --- drivers/staging/iio/Kconfig | 1 - drivers/staging/iio/Makefile | 1 - drivers/staging/iio/meter/Kconfig | 37 -- drivers/staging/iio/meter/Makefile | 8 - drivers/staging/iio/meter/ade7854-i2c.c | 153 ------- drivers/staging/iio/meter/ade7854-spi.c | 160 ------- drivers/staging/iio/meter/ade7854.c | 556 ------------------------ drivers/staging/iio/meter/ade7854.h | 173 -------- drivers/staging/iio/meter/meter.h | 398 ----------------- 9 files changed, 1487 deletions(-) delete mode 100644 drivers/staging/iio/meter/Kconfig delete mode 100644 drivers/staging/iio/meter/Makefile delete mode 100644 drivers/staging/iio/meter/ade7854-i2c.c delete mode 100644 drivers/staging/iio/meter/ade7854-spi.c delete mode 100644 drivers/staging/iio/meter/ade7854.c delete mode 100644 drivers/staging/iio/meter/ade7854.h delete mode 100644 drivers/staging/iio/meter/meter.h diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig index afd05bf3345e..d3968fe2ebb8 100644 --- a/drivers/staging/iio/Kconfig +++ b/drivers/staging/iio/Kconfig @@ -10,7 +10,6 @@ source "drivers/staging/iio/adc/Kconfig" source "drivers/staging/iio/addac/Kconfig" source "drivers/staging/iio/frequency/Kconfig" source "drivers/staging/iio/impedance-analyzer/Kconfig" -source "drivers/staging/iio/meter/Kconfig" source "drivers/staging/iio/resolver/Kconfig" endmenu diff --git a/drivers/staging/iio/Makefile b/drivers/staging/iio/Makefile index 5ed56fe57e14..c50f1019f829 100644 --- a/drivers/staging/iio/Makefile +++ b/drivers/staging/iio/Makefile @@ -8,5 +8,4 @@ obj-y += adc/ obj-y += addac/ obj-y += frequency/ obj-y += impedance-analyzer/ -obj-y += meter/ obj-y += resolver/ diff --git a/drivers/staging/iio/meter/Kconfig b/drivers/staging/iio/meter/Kconfig deleted file mode 100644 index aa6a3e7f6cdb..000000000000 --- a/drivers/staging/iio/meter/Kconfig +++ /dev/null @@ -1,37 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# IIO meter drivers configuration -# -menu "Active energy metering IC" - -config ADE7854 - tristate "Analog Devices ADE7854/58/68/78 Polyphase Multifunction Energy Metering IC Driver" - depends on SPI || I2C - help - Say yes here to build support for Analog Devices ADE7854/58/68/78 Polyphase - Multifunction Energy Metering IC Driver. - - To compile this driver as a module, choose M here: the - module will be called ade7854. - -config ADE7854_I2C - tristate "support I2C bus connection" - depends on ADE7854 && I2C - default y - help - Say Y here if you have ADE7854/58/68/78 hooked to an I2C bus. - - To compile this driver as a module, choose M here: the - module will be called ade7854-i2c. - -config ADE7854_SPI - tristate "support SPI bus connection" - depends on ADE7854 && SPI - default y - help - Say Y here if you have ADE7854/58/68/78 hooked to a SPI bus. - - To compile this driver as a module, choose M here: the - module will be called ade7854-spi. - -endmenu diff --git a/drivers/staging/iio/meter/Makefile b/drivers/staging/iio/meter/Makefile deleted file mode 100644 index ed4547e38f3a..000000000000 --- a/drivers/staging/iio/meter/Makefile +++ /dev/null @@ -1,8 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for metering ic drivers -# - -obj-$(CONFIG_ADE7854) += ade7854.o -obj-$(CONFIG_ADE7854_I2C) += ade7854-i2c.o -obj-$(CONFIG_ADE7854_SPI) += ade7854-spi.o diff --git a/drivers/staging/iio/meter/ade7854-i2c.c b/drivers/staging/iio/meter/ade7854-i2c.c deleted file mode 100644 index 572d714eb0dd..000000000000 --- a/drivers/staging/iio/meter/ade7854-i2c.c +++ /dev/null @@ -1,153 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * ADE7854/58/68/78 Polyphase Multifunction Energy Metering IC Driver (I2C Bus) - * - * Copyright 2010 Analog Devices Inc. - */ - -#include -#include -#include -#include -#include - -#include -#include "ade7854.h" - -static int ade7854_i2c_write_reg(struct device *dev, - u16 reg_address, - u32 val, - int bits) -{ - int ret; - int count; - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - mutex_lock(&st->buf_lock); - st->tx[0] = (reg_address >> 8) & 0xFF; - st->tx[1] = reg_address & 0xFF; - - switch (bits) { - case 8: - st->tx[2] = val & 0xFF; - count = 3; - break; - case 16: - st->tx[2] = (val >> 8) & 0xFF; - st->tx[3] = val & 0xFF; - count = 4; - break; - case 24: - st->tx[2] = (val >> 16) & 0xFF; - st->tx[3] = (val >> 8) & 0xFF; - st->tx[4] = val & 0xFF; - count = 5; - break; - case 32: - st->tx[2] = (val >> 24) & 0xFF; - st->tx[3] = (val >> 16) & 0xFF; - st->tx[4] = (val >> 8) & 0xFF; - st->tx[5] = val & 0xFF; - count = 6; - break; - default: - ret = -EINVAL; - goto unlock; - } - - ret = i2c_master_send(st->i2c, st->tx, count); - -unlock: - mutex_unlock(&st->buf_lock); - - if (ret < 0) - return ret; - - return 0; -} - -static int ade7854_i2c_read_reg(struct device *dev, - u16 reg_address, - u32 *val, - int bits) -{ - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - int ret; - - mutex_lock(&st->buf_lock); - st->tx[0] = (reg_address >> 8) & 0xFF; - st->tx[1] = reg_address & 0xFF; - - ret = i2c_master_send(st->i2c, st->tx, 2); - if (ret < 0) - goto unlock; - - ret = i2c_master_recv(st->i2c, st->rx, bits); - if (ret < 0) - goto unlock; - - switch (bits) { - case 8: - *val = st->rx[0]; - break; - case 16: - *val = (st->rx[0] << 8) | st->rx[1]; - break; - case 24: - *val = (st->rx[0] << 16) | (st->rx[1] << 8) | st->rx[2]; - break; - case 32: - *val = (st->rx[0] << 24) | (st->rx[1] << 16) | - (st->rx[2] << 8) | st->rx[3]; - break; - default: - ret = -EINVAL; - goto unlock; - } - -unlock: - mutex_unlock(&st->buf_lock); - return ret; -} - -static int ade7854_i2c_probe(struct i2c_client *client) -{ - struct ade7854_state *st; - struct iio_dev *indio_dev; - - indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*st)); - if (!indio_dev) - return -ENOMEM; - st = iio_priv(indio_dev); - i2c_set_clientdata(client, indio_dev); - st->read_reg = ade7854_i2c_read_reg; - st->write_reg = ade7854_i2c_write_reg; - st->i2c = client; - st->irq = client->irq; - - return ade7854_probe(indio_dev, &client->dev); -} - -static const struct i2c_device_id ade7854_id[] = { - { "ade7854", 0 }, - { "ade7858", 0 }, - { "ade7868", 0 }, - { "ade7878", 0 }, - { } -}; -MODULE_DEVICE_TABLE(i2c, ade7854_id); - -static struct i2c_driver ade7854_i2c_driver = { - .driver = { - .name = "ade7854", - }, - .probe_new = ade7854_i2c_probe, - .id_table = ade7854_id, -}; -module_i2c_driver(ade7854_i2c_driver); - -MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); -MODULE_DESCRIPTION("Analog Devices ADE7854/58/68/78 Polyphase Multifunction Energy Metering IC I2C Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/iio/meter/ade7854-spi.c b/drivers/staging/iio/meter/ade7854-spi.c deleted file mode 100644 index f12a6c8b3e88..000000000000 --- a/drivers/staging/iio/meter/ade7854-spi.c +++ /dev/null @@ -1,160 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * ADE7854/58/68/78 Polyphase Multifunction Energy Metering IC Driver (SPI Bus) - * - * Copyright 2010 Analog Devices Inc. - */ - -#include -#include -#include -#include -#include - -#include -#include "ade7854.h" - -static int ade7854_spi_write_reg(struct device *dev, - u16 reg_address, - u32 val, - int bits) -{ - int ret; - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - struct spi_transfer xfer = { - .tx_buf = st->tx, - .bits_per_word = 8, - .len = 4, - }; - - mutex_lock(&st->buf_lock); - st->tx[0] = ADE7854_WRITE_REG; - st->tx[1] = (reg_address >> 8) & 0xFF; - st->tx[2] = reg_address & 0xFF; - switch (bits) { - case 8: - st->tx[3] = val & 0xFF; - break; - case 16: - xfer.len = 5; - st->tx[3] = (val >> 8) & 0xFF; - st->tx[4] = val & 0xFF; - break; - case 24: - xfer.len = 6; - st->tx[3] = (val >> 16) & 0xFF; - st->tx[4] = (val >> 8) & 0xFF; - st->tx[5] = val & 0xFF; - break; - case 32: - xfer.len = 7; - st->tx[3] = (val >> 24) & 0xFF; - st->tx[4] = (val >> 16) & 0xFF; - st->tx[5] = (val >> 8) & 0xFF; - st->tx[6] = val & 0xFF; - break; - default: - ret = -EINVAL; - goto unlock; - } - - ret = spi_sync_transfer(st->spi, &xfer, 1); -unlock: - mutex_unlock(&st->buf_lock); - - return ret; -} - -static int ade7854_spi_read_reg(struct device *dev, - u16 reg_address, - u32 *val, - int bits) -{ - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - int ret; - struct spi_transfer xfers[] = { - { - .tx_buf = st->tx, - .bits_per_word = 8, - .len = 3, - }, { - .rx_buf = st->rx, - .bits_per_word = 8, - .len = bits, - } - }; - - mutex_lock(&st->buf_lock); - - st->tx[0] = ADE7854_READ_REG; - st->tx[1] = (reg_address >> 8) & 0xFF; - st->tx[2] = reg_address & 0xFF; - - ret = spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); - if (ret < 0) { - dev_err(&st->spi->dev, "problem when reading register 0x%02X", - reg_address); - goto unlock; - } - - switch (bits) { - case 8: - *val = st->rx[0]; - break; - case 16: - *val = be16_to_cpup((const __be16 *)st->rx); - break; - case 24: - *val = (st->rx[0] << 16) | (st->rx[1] << 8) | st->rx[2]; - break; - case 32: - *val = be32_to_cpup((const __be32 *)st->rx); - break; - } - -unlock: - mutex_unlock(&st->buf_lock); - return ret; -} - -static int ade7854_spi_probe(struct spi_device *spi) -{ - struct ade7854_state *st; - struct iio_dev *indio_dev; - - indio_dev = devm_iio_device_alloc(&spi->dev, sizeof(*st)); - if (!indio_dev) - return -ENOMEM; - st = iio_priv(indio_dev); - spi_set_drvdata(spi, indio_dev); - st->read_reg = ade7854_spi_read_reg; - st->write_reg = ade7854_spi_write_reg; - st->irq = spi->irq; - st->spi = spi; - - return ade7854_probe(indio_dev, &spi->dev); -} - -static const struct spi_device_id ade7854_id[] = { - { "ade7854", 0 }, - { "ade7858", 0 }, - { "ade7868", 0 }, - { "ade7878", 0 }, - { } -}; -MODULE_DEVICE_TABLE(spi, ade7854_id); - -static struct spi_driver ade7854_driver = { - .driver = { - .name = "ade7854", - }, - .probe = ade7854_spi_probe, - .id_table = ade7854_id, -}; -module_spi_driver(ade7854_driver); - -MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); -MODULE_DESCRIPTION("Analog Devices ADE7854/58/68/78 SPI Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/iio/meter/ade7854.c b/drivers/staging/iio/meter/ade7854.c deleted file mode 100644 index 68da6ecde6a3..000000000000 --- a/drivers/staging/iio/meter/ade7854.c +++ /dev/null @@ -1,556 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * ADE7854/58/68/78 Polyphase Multifunction Energy Metering IC Driver - * - * Copyright 2010 Analog Devices Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include "meter.h" -#include "ade7854.h" - -static ssize_t ade7854_read_8bit(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - int ret; - u32 val = 0; - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - - ret = st->read_reg(dev, this_attr->address, &val, 8); - if (ret < 0) - return ret; - - return sprintf(buf, "%u\n", val); -} - -static ssize_t ade7854_read_16bit(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - int ret; - u32 val = 0; - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - - ret = st->read_reg(dev, this_attr->address, &val, 16); - if (ret < 0) - return ret; - - return sprintf(buf, "%u\n", val); -} - -static ssize_t ade7854_read_24bit(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - int ret; - u32 val; - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - - ret = st->read_reg(dev, this_attr->address, &val, 24); - if (ret < 0) - return ret; - - return sprintf(buf, "%u\n", val); -} - -static ssize_t ade7854_read_32bit(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - int ret; - u32 val = 0; - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - ret = st->read_reg(dev, this_attr->address, &val, 32); - if (ret < 0) - return ret; - - return sprintf(buf, "%u\n", val); -} - -static ssize_t ade7854_write_8bit(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len) -{ - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - int ret; - u8 val; - - ret = kstrtou8(buf, 10, &val); - if (ret) - goto error_ret; - ret = st->write_reg(dev, this_attr->address, val, 8); - -error_ret: - return ret ? ret : len; -} - -static ssize_t ade7854_write_16bit(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len) -{ - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - int ret; - u16 val; - - ret = kstrtou16(buf, 10, &val); - if (ret) - goto error_ret; - ret = st->write_reg(dev, this_attr->address, val, 16); - -error_ret: - return ret ? ret : len; -} - -static ssize_t ade7854_write_24bit(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len) -{ - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - int ret; - u32 val; - - ret = kstrtou32(buf, 10, &val); - if (ret) - goto error_ret; - ret = st->write_reg(dev, this_attr->address, val, 24); - -error_ret: - return ret ? ret : len; -} - -static ssize_t ade7854_write_32bit(struct device *dev, - struct device_attribute *attr, - const char *buf, - size_t len) -{ - struct iio_dev_attr *this_attr = to_iio_dev_attr(attr); - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - int ret; - u32 val; - - ret = kstrtou32(buf, 10, &val); - if (ret) - goto error_ret; - ret = st->write_reg(dev, this_attr->address, val, 32); - -error_ret: - return ret ? ret : len; -} - -static int ade7854_reset(struct device *dev) -{ - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - u32 val; - - st->read_reg(dev, ADE7854_CONFIG, &val, 16); - val |= BIT(7); /* Software Chip Reset */ - - return st->write_reg(dev, ADE7854_CONFIG, val, 16); -} - -static IIO_DEV_ATTR_AIGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AIGAIN); -static IIO_DEV_ATTR_BIGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BIGAIN); -static IIO_DEV_ATTR_CIGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CIGAIN); -static IIO_DEV_ATTR_NIGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_NIGAIN); -static IIO_DEV_ATTR_AVGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AVGAIN); -static IIO_DEV_ATTR_BVGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BVGAIN); -static IIO_DEV_ATTR_CVGAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CVGAIN); -static IIO_DEV_ATTR_APPARENT_POWER_A_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AVAGAIN); -static IIO_DEV_ATTR_APPARENT_POWER_B_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BVAGAIN); -static IIO_DEV_ATTR_APPARENT_POWER_C_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CVAGAIN); -static IIO_DEV_ATTR_ACTIVE_POWER_A_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AWATTOS); -static IIO_DEV_ATTR_ACTIVE_POWER_B_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BWATTOS); -static IIO_DEV_ATTR_ACTIVE_POWER_C_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CWATTOS); -static IIO_DEV_ATTR_REACTIVE_POWER_A_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AVARGAIN); -static IIO_DEV_ATTR_REACTIVE_POWER_B_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BVARGAIN); -static IIO_DEV_ATTR_REACTIVE_POWER_C_GAIN(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CVARGAIN); -static IIO_DEV_ATTR_REACTIVE_POWER_A_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_AVAROS); -static IIO_DEV_ATTR_REACTIVE_POWER_B_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_BVAROS); -static IIO_DEV_ATTR_REACTIVE_POWER_C_OFFSET(0644, - ade7854_read_24bit, - ade7854_write_24bit, - ADE7854_CVAROS); -static IIO_DEV_ATTR_VPEAK(0644, - ade7854_read_32bit, - ade7854_write_32bit, - ADE7854_VPEAK); -static IIO_DEV_ATTR_IPEAK(0644, - ade7854_read_32bit, - ade7854_write_32bit, - ADE7854_IPEAK); -static IIO_DEV_ATTR_APHCAL(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_APHCAL); -static IIO_DEV_ATTR_BPHCAL(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_BPHCAL); -static IIO_DEV_ATTR_CPHCAL(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CPHCAL); -static IIO_DEV_ATTR_CF1DEN(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CF1DEN); -static IIO_DEV_ATTR_CF2DEN(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CF2DEN); -static IIO_DEV_ATTR_CF3DEN(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CF3DEN); -static IIO_DEV_ATTR_LINECYC(0644, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_LINECYC); -static IIO_DEV_ATTR_SAGCYC(0644, - ade7854_read_8bit, - ade7854_write_8bit, - ADE7854_SAGCYC); -static IIO_DEV_ATTR_CFCYC(0644, - ade7854_read_8bit, - ade7854_write_8bit, - ADE7854_CFCYC); -static IIO_DEV_ATTR_PEAKCYC(0644, - ade7854_read_8bit, - ade7854_write_8bit, - ADE7854_PEAKCYC); -static IIO_DEV_ATTR_CHKSUM(ade7854_read_24bit, - ADE7854_CHECKSUM); -static IIO_DEV_ATTR_ANGLE0(ade7854_read_24bit, - ADE7854_ANGLE0); -static IIO_DEV_ATTR_ANGLE1(ade7854_read_24bit, - ADE7854_ANGLE1); -static IIO_DEV_ATTR_ANGLE2(ade7854_read_24bit, - ADE7854_ANGLE2); -static IIO_DEV_ATTR_AIRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_AIRMS); -static IIO_DEV_ATTR_BIRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_BIRMS); -static IIO_DEV_ATTR_CIRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_CIRMS); -static IIO_DEV_ATTR_NIRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_NIRMS); -static IIO_DEV_ATTR_AVRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_AVRMS); -static IIO_DEV_ATTR_BVRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_BVRMS); -static IIO_DEV_ATTR_CVRMS(0444, - ade7854_read_24bit, - NULL, - ADE7854_CVRMS); -static IIO_DEV_ATTR_AIRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_AIRMSOS); -static IIO_DEV_ATTR_BIRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_BIRMSOS); -static IIO_DEV_ATTR_CIRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CIRMSOS); -static IIO_DEV_ATTR_AVRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_AVRMSOS); -static IIO_DEV_ATTR_BVRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_BVRMSOS); -static IIO_DEV_ATTR_CVRMSOS(0444, - ade7854_read_16bit, - ade7854_write_16bit, - ADE7854_CVRMSOS); -static IIO_DEV_ATTR_VOLT_A(ade7854_read_24bit, - ADE7854_VAWV); -static IIO_DEV_ATTR_VOLT_B(ade7854_read_24bit, - ADE7854_VBWV); -static IIO_DEV_ATTR_VOLT_C(ade7854_read_24bit, - ADE7854_VCWV); -static IIO_DEV_ATTR_CURRENT_A(ade7854_read_24bit, - ADE7854_IAWV); -static IIO_DEV_ATTR_CURRENT_B(ade7854_read_24bit, - ADE7854_IBWV); -static IIO_DEV_ATTR_CURRENT_C(ade7854_read_24bit, - ADE7854_ICWV); -static IIO_DEV_ATTR_AWATTHR(ade7854_read_32bit, - ADE7854_AWATTHR); -static IIO_DEV_ATTR_BWATTHR(ade7854_read_32bit, - ADE7854_BWATTHR); -static IIO_DEV_ATTR_CWATTHR(ade7854_read_32bit, - ADE7854_CWATTHR); -static IIO_DEV_ATTR_AFWATTHR(ade7854_read_32bit, - ADE7854_AFWATTHR); -static IIO_DEV_ATTR_BFWATTHR(ade7854_read_32bit, - ADE7854_BFWATTHR); -static IIO_DEV_ATTR_CFWATTHR(ade7854_read_32bit, - ADE7854_CFWATTHR); -static IIO_DEV_ATTR_AVARHR(ade7854_read_32bit, - ADE7854_AVARHR); -static IIO_DEV_ATTR_BVARHR(ade7854_read_32bit, - ADE7854_BVARHR); -static IIO_DEV_ATTR_CVARHR(ade7854_read_32bit, - ADE7854_CVARHR); -static IIO_DEV_ATTR_AVAHR(ade7854_read_32bit, - ADE7854_AVAHR); -static IIO_DEV_ATTR_BVAHR(ade7854_read_32bit, - ADE7854_BVAHR); -static IIO_DEV_ATTR_CVAHR(ade7854_read_32bit, - ADE7854_CVAHR); - -static int ade7854_set_irq(struct device *dev, bool enable) -{ - struct iio_dev *indio_dev = dev_to_iio_dev(dev); - struct ade7854_state *st = iio_priv(indio_dev); - - int ret; - u32 irqen; - - ret = st->read_reg(dev, ADE7854_MASK0, &irqen, 32); - if (ret < 0) - return ret; - - if (enable) - irqen |= BIT(17); /* 1: interrupt enabled when all periodical - * (at 8 kHz rate) DSP computations finish. - */ - else - irqen &= ~BIT(17); - - return st->write_reg(dev, ADE7854_MASK0, irqen, 32); -} - -static int ade7854_initial_setup(struct iio_dev *indio_dev) -{ - int ret; - struct device *dev = &indio_dev->dev; - - /* Disable IRQ */ - ret = ade7854_set_irq(dev, false); - if (ret) { - dev_err(dev, "disable irq failed"); - goto err_ret; - } - - ade7854_reset(dev); - usleep_range(ADE7854_STARTUP_DELAY, ADE7854_STARTUP_DELAY + 100); - -err_ret: - return ret; -} - -static IIO_CONST_ATTR_SAMP_FREQ_AVAIL("8000"); - -static IIO_CONST_ATTR(name, "ade7854"); - -static struct attribute *ade7854_attributes[] = { - &iio_dev_attr_aigain.dev_attr.attr, - &iio_dev_attr_bigain.dev_attr.attr, - &iio_dev_attr_cigain.dev_attr.attr, - &iio_dev_attr_nigain.dev_attr.attr, - &iio_dev_attr_avgain.dev_attr.attr, - &iio_dev_attr_bvgain.dev_attr.attr, - &iio_dev_attr_cvgain.dev_attr.attr, - &iio_dev_attr_linecyc.dev_attr.attr, - &iio_dev_attr_sagcyc.dev_attr.attr, - &iio_dev_attr_cfcyc.dev_attr.attr, - &iio_dev_attr_peakcyc.dev_attr.attr, - &iio_dev_attr_chksum.dev_attr.attr, - &iio_dev_attr_apparent_power_a_gain.dev_attr.attr, - &iio_dev_attr_apparent_power_b_gain.dev_attr.attr, - &iio_dev_attr_apparent_power_c_gain.dev_attr.attr, - &iio_dev_attr_active_power_a_offset.dev_attr.attr, - &iio_dev_attr_active_power_b_offset.dev_attr.attr, - &iio_dev_attr_active_power_c_offset.dev_attr.attr, - &iio_dev_attr_reactive_power_a_gain.dev_attr.attr, - &iio_dev_attr_reactive_power_b_gain.dev_attr.attr, - &iio_dev_attr_reactive_power_c_gain.dev_attr.attr, - &iio_dev_attr_reactive_power_a_offset.dev_attr.attr, - &iio_dev_attr_reactive_power_b_offset.dev_attr.attr, - &iio_dev_attr_reactive_power_c_offset.dev_attr.attr, - &iio_dev_attr_awatthr.dev_attr.attr, - &iio_dev_attr_bwatthr.dev_attr.attr, - &iio_dev_attr_cwatthr.dev_attr.attr, - &iio_dev_attr_afwatthr.dev_attr.attr, - &iio_dev_attr_bfwatthr.dev_attr.attr, - &iio_dev_attr_cfwatthr.dev_attr.attr, - &iio_dev_attr_avarhr.dev_attr.attr, - &iio_dev_attr_bvarhr.dev_attr.attr, - &iio_dev_attr_cvarhr.dev_attr.attr, - &iio_dev_attr_angle0.dev_attr.attr, - &iio_dev_attr_angle1.dev_attr.attr, - &iio_dev_attr_angle2.dev_attr.attr, - &iio_dev_attr_avahr.dev_attr.attr, - &iio_dev_attr_bvahr.dev_attr.attr, - &iio_dev_attr_cvahr.dev_attr.attr, - &iio_const_attr_sampling_frequency_available.dev_attr.attr, - &iio_const_attr_name.dev_attr.attr, - &iio_dev_attr_vpeak.dev_attr.attr, - &iio_dev_attr_ipeak.dev_attr.attr, - &iio_dev_attr_aphcal.dev_attr.attr, - &iio_dev_attr_bphcal.dev_attr.attr, - &iio_dev_attr_cphcal.dev_attr.attr, - &iio_dev_attr_cf1den.dev_attr.attr, - &iio_dev_attr_cf2den.dev_attr.attr, - &iio_dev_attr_cf3den.dev_attr.attr, - &iio_dev_attr_airms.dev_attr.attr, - &iio_dev_attr_birms.dev_attr.attr, - &iio_dev_attr_cirms.dev_attr.attr, - &iio_dev_attr_nirms.dev_attr.attr, - &iio_dev_attr_avrms.dev_attr.attr, - &iio_dev_attr_bvrms.dev_attr.attr, - &iio_dev_attr_cvrms.dev_attr.attr, - &iio_dev_attr_airmsos.dev_attr.attr, - &iio_dev_attr_birmsos.dev_attr.attr, - &iio_dev_attr_cirmsos.dev_attr.attr, - &iio_dev_attr_avrmsos.dev_attr.attr, - &iio_dev_attr_bvrmsos.dev_attr.attr, - &iio_dev_attr_cvrmsos.dev_attr.attr, - &iio_dev_attr_volt_a.dev_attr.attr, - &iio_dev_attr_volt_b.dev_attr.attr, - &iio_dev_attr_volt_c.dev_attr.attr, - &iio_dev_attr_current_a.dev_attr.attr, - &iio_dev_attr_current_b.dev_attr.attr, - &iio_dev_attr_current_c.dev_attr.attr, - NULL, -}; - -static const struct attribute_group ade7854_attribute_group = { - .attrs = ade7854_attributes, -}; - -static const struct iio_info ade7854_info = { - .attrs = &ade7854_attribute_group, -}; - -int ade7854_probe(struct iio_dev *indio_dev, struct device *dev) -{ - int ret; - struct ade7854_state *st = iio_priv(indio_dev); - /* setup the industrialio driver allocated elements */ - mutex_init(&st->buf_lock); - - indio_dev->dev.parent = dev; - indio_dev->info = &ade7854_info; - indio_dev->modes = INDIO_DIRECT_MODE; - - ret = devm_iio_device_register(dev, indio_dev); - if (ret) - return ret; - - /* Get the device into a sane initial state */ - return ade7854_initial_setup(indio_dev); -} -EXPORT_SYMBOL(ade7854_probe); - -MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>"); -MODULE_DESCRIPTION("Analog Devices ADE7854/58/68/78 Polyphase Energy Meter"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/staging/iio/meter/ade7854.h b/drivers/staging/iio/meter/ade7854.h deleted file mode 100644 index 7a49f8f1016f..000000000000 --- a/drivers/staging/iio/meter/ade7854.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ADE7854_H -#define _ADE7854_H - -#define ADE7854_AIGAIN 0x4380 -#define ADE7854_AVGAIN 0x4381 -#define ADE7854_BIGAIN 0x4382 -#define ADE7854_BVGAIN 0x4383 -#define ADE7854_CIGAIN 0x4384 -#define ADE7854_CVGAIN 0x4385 -#define ADE7854_NIGAIN 0x4386 -#define ADE7854_AIRMSOS 0x4387 -#define ADE7854_AVRMSOS 0x4388 -#define ADE7854_BIRMSOS 0x4389 -#define ADE7854_BVRMSOS 0x438A -#define ADE7854_CIRMSOS 0x438B -#define ADE7854_CVRMSOS 0x438C -#define ADE7854_NIRMSOS 0x438D -#define ADE7854_AVAGAIN 0x438E -#define ADE7854_BVAGAIN 0x438F -#define ADE7854_CVAGAIN 0x4390 -#define ADE7854_AWGAIN 0x4391 -#define ADE7854_AWATTOS 0x4392 -#define ADE7854_BWGAIN 0x4393 -#define ADE7854_BWATTOS 0x4394 -#define ADE7854_CWGAIN 0x4395 -#define ADE7854_CWATTOS 0x4396 -#define ADE7854_AVARGAIN 0x4397 -#define ADE7854_AVAROS 0x4398 -#define ADE7854_BVARGAIN 0x4399 -#define ADE7854_BVAROS 0x439A -#define ADE7854_CVARGAIN 0x439B -#define ADE7854_CVAROS 0x439C -#define ADE7854_AFWGAIN 0x439D -#define ADE7854_AFWATTOS 0x439E -#define ADE7854_BFWGAIN 0x439F -#define ADE7854_BFWATTOS 0x43A0 -#define ADE7854_CFWGAIN 0x43A1 -#define ADE7854_CFWATTOS 0x43A2 -#define ADE7854_AFVARGAIN 0x43A3 -#define ADE7854_AFVAROS 0x43A4 -#define ADE7854_BFVARGAIN 0x43A5 -#define ADE7854_BFVAROS 0x43A6 -#define ADE7854_CFVARGAIN 0x43A7 -#define ADE7854_CFVAROS 0x43A8 -#define ADE7854_VATHR1 0x43A9 -#define ADE7854_VATHR0 0x43AA -#define ADE7854_WTHR1 0x43AB -#define ADE7854_WTHR0 0x43AC -#define ADE7854_VARTHR1 0x43AD -#define ADE7854_VARTHR0 0x43AE -#define ADE7854_RSV 0x43AF -#define ADE7854_VANOLOAD 0x43B0 -#define ADE7854_APNOLOAD 0x43B1 -#define ADE7854_VARNOLOAD 0x43B2 -#define ADE7854_VLEVEL 0x43B3 -#define ADE7854_DICOEFF 0x43B5 -#define ADE7854_HPFDIS 0x43B6 -#define ADE7854_ISUMLVL 0x43B8 -#define ADE7854_ISUM 0x43BF -#define ADE7854_AIRMS 0x43C0 -#define ADE7854_AVRMS 0x43C1 -#define ADE7854_BIRMS 0x43C2 -#define ADE7854_BVRMS 0x43C3 -#define ADE7854_CIRMS 0x43C4 -#define ADE7854_CVRMS 0x43C5 -#define ADE7854_NIRMS 0x43C6 -#define ADE7854_RUN 0xE228 -#define ADE7854_AWATTHR 0xE400 -#define ADE7854_BWATTHR 0xE401 -#define ADE7854_CWATTHR 0xE402 -#define ADE7854_AFWATTHR 0xE403 -#define ADE7854_BFWATTHR 0xE404 -#define ADE7854_CFWATTHR 0xE405 -#define ADE7854_AVARHR 0xE406 -#define ADE7854_BVARHR 0xE407 -#define ADE7854_CVARHR 0xE408 -#define ADE7854_AFVARHR 0xE409 -#define ADE7854_BFVARHR 0xE40A -#define ADE7854_CFVARHR 0xE40B -#define ADE7854_AVAHR 0xE40C -#define ADE7854_BVAHR 0xE40D -#define ADE7854_CVAHR 0xE40E -#define ADE7854_IPEAK 0xE500 -#define ADE7854_VPEAK 0xE501 -#define ADE7854_STATUS0 0xE502 -#define ADE7854_STATUS1 0xE503 -#define ADE7854_OILVL 0xE507 -#define ADE7854_OVLVL 0xE508 -#define ADE7854_SAGLVL 0xE509 -#define ADE7854_MASK0 0xE50A -#define ADE7854_MASK1 0xE50B -#define ADE7854_IAWV 0xE50C -#define ADE7854_IBWV 0xE50D -#define ADE7854_ICWV 0xE50E -#define ADE7854_VAWV 0xE510 -#define ADE7854_VBWV 0xE511 -#define ADE7854_VCWV 0xE512 -#define ADE7854_AWATT 0xE513 -#define ADE7854_BWATT 0xE514 -#define ADE7854_CWATT 0xE515 -#define ADE7854_AVA 0xE519 -#define ADE7854_BVA 0xE51A -#define ADE7854_CVA 0xE51B -#define ADE7854_CHECKSUM 0xE51F -#define ADE7854_VNOM 0xE520 -#define ADE7854_PHSTATUS 0xE600 -#define ADE7854_ANGLE0 0xE601 -#define ADE7854_ANGLE1 0xE602 -#define ADE7854_ANGLE2 0xE603 -#define ADE7854_PERIOD 0xE607 -#define ADE7854_PHNOLOAD 0xE608 -#define ADE7854_LINECYC 0xE60C -#define ADE7854_ZXTOUT 0xE60D -#define ADE7854_COMPMODE 0xE60E -#define ADE7854_GAIN 0xE60F -#define ADE7854_CFMODE 0xE610 -#define ADE7854_CF1DEN 0xE611 -#define ADE7854_CF2DEN 0xE612 -#define ADE7854_CF3DEN 0xE613 -#define ADE7854_APHCAL 0xE614 -#define ADE7854_BPHCAL 0xE615 -#define ADE7854_CPHCAL 0xE616 -#define ADE7854_PHSIGN 0xE617 -#define ADE7854_CONFIG 0xE618 -#define ADE7854_MMODE 0xE700 -#define ADE7854_ACCMODE 0xE701 -#define ADE7854_LCYCMODE 0xE702 -#define ADE7854_PEAKCYC 0xE703 -#define ADE7854_SAGCYC 0xE704 -#define ADE7854_CFCYC 0xE705 -#define ADE7854_HSDC_CFG 0xE706 -#define ADE7854_CONFIG2 0xEC01 - -#define ADE7854_READ_REG 0x1 -#define ADE7854_WRITE_REG 0x0 - -#define ADE7854_MAX_TX 7 -#define ADE7854_MAX_RX 7 -#define ADE7854_STARTUP_DELAY 1000 - -#define ADE7854_SPI_SLOW (u32)(300 * 1000) -#define ADE7854_SPI_BURST (u32)(1000 * 1000) -#define ADE7854_SPI_FAST (u32)(2000 * 1000) - -/** - * struct ade7854_state - device instance specific data - * @spi: actual spi_device - * @read_reg Wrapper function for I2C and SPI read - * @write_reg Wrapper function for I2C and SPI write - * @indio_dev: industrial I/O device structure - * @buf_lock: mutex to protect tx and rx - * @tx: transmit buffer - * @rx: receive buffer - **/ -struct ade7854_state { - struct spi_device *spi; - struct i2c_client *i2c; - int (*read_reg)(struct device *dev, u16 reg_address, u32 *val, - int bits); - int (*write_reg)(struct device *dev, u16 reg_address, u32 val, - int bits); - int irq; - struct mutex buf_lock; - u8 tx[ADE7854_MAX_TX] __aligned(IIO_DMA_MINALIGN); - u8 rx[ADE7854_MAX_RX]; - -}; - -int ade7854_probe(struct iio_dev *indio_dev, struct device *dev); -int ade7854_remove(struct iio_dev *indio_dev); - -#endif diff --git a/drivers/staging/iio/meter/meter.h b/drivers/staging/iio/meter/meter.h deleted file mode 100644 index 5ed59bf30a25..000000000000 --- a/drivers/staging/iio/meter/meter.h +++ /dev/null @@ -1,398 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _METER_H -#define _METER_H - -#include - -/* metering ic types of attribute */ - -#define IIO_DEV_ATTR_CURRENT_A_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_a_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_B_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_b_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_C_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_c_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VOLT_A_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(volt_a_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VOLT_B_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(volt_b_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VOLT_C_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(volt_c_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_A_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_a_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_B_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_b_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_C_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_c_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_A_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_a_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_B_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_b_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_C_OFFSET(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_c_offset, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_A_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_a_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_B_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_b_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_C_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(current_c_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_APPARENT_POWER_A_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(apparent_power_a_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_APPARENT_POWER_B_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(apparent_power_b_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_APPARENT_POWER_C_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(apparent_power_c_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_A_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_a_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_B_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_b_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_ACTIVE_POWER_C_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(active_power_c_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_A_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_a_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_B_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_b_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_REACTIVE_POWER_C_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(reactive_power_c_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CURRENT_A(_show, _addr) \ - IIO_DEVICE_ATTR(current_a, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CURRENT_B(_show, _addr) \ - IIO_DEVICE_ATTR(current_b, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CURRENT_C(_show, _addr) \ - IIO_DEVICE_ATTR(current_c, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_VOLT_A(_show, _addr) \ - IIO_DEVICE_ATTR(volt_a, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_VOLT_B(_show, _addr) \ - IIO_DEVICE_ATTR(volt_b, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_VOLT_C(_show, _addr) \ - IIO_DEVICE_ATTR(volt_c, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_AENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(aenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_LENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(lenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_RAENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(raenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_LAENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(laenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_VAENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(vaenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_LVAENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(lvaenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_RVAENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(rvaenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_LVARENERGY(_show, _addr) \ - IIO_DEVICE_ATTR(lvarenergy, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CHKSUM(_show, _addr) \ - IIO_DEVICE_ATTR(chksum, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_ANGLE0(_show, _addr) \ - IIO_DEVICE_ATTR(angle0, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_ANGLE1(_show, _addr) \ - IIO_DEVICE_ATTR(angle1, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_ANGLE2(_show, _addr) \ - IIO_DEVICE_ATTR(angle2, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_AWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(awatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_BWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(bwatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(cwatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_AFWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(afwatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_BFWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(bfwatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CFWATTHR(_show, _addr) \ - IIO_DEVICE_ATTR(cfwatthr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_AVARHR(_show, _addr) \ - IIO_DEVICE_ATTR(avarhr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_BVARHR(_show, _addr) \ - IIO_DEVICE_ATTR(bvarhr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CVARHR(_show, _addr) \ - IIO_DEVICE_ATTR(cvarhr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_AVAHR(_show, _addr) \ - IIO_DEVICE_ATTR(avahr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_BVAHR(_show, _addr) \ - IIO_DEVICE_ATTR(bvahr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_CVAHR(_show, _addr) \ - IIO_DEVICE_ATTR(cvahr, 0444, _show, NULL, _addr) - -#define IIO_DEV_ATTR_IOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(ios, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_PHCAL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(phcal, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_APHCAL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(aphcal, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BPHCAL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bphcal, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CPHCAL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cphcal, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_APOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(apos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AAPOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(aapos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BAPOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bapos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CAPOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(capos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AVRMSGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(avrmsgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BVRMSGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bvrmsgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CVRMSGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cvrmsgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AIGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(aigain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BIGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bigain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CIGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cigain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_NIGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(nigain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AVGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(avgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BVGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bvgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CVGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cvgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_WGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(wgain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_WDIV(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(wdiv, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CFNUM(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cfnum, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CFDEN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cfden, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CF1DEN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cf1den, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CF2DEN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cf2den, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CF3DEN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cf3den, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_IRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(irms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vrms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AIRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(airms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BIRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(birms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CIRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cirms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_NIRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(nirms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AVRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(avrms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BVRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bvrms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CVRMS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cvrms, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_IRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(irmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vrmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AIRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(airmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BIRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(birmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CIRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cirmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_AVRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(avrmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_BVRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(bvrmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CVRMSOS(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cvrmsos, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VAGAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vagain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_PGA_GAIN(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(pga_gain, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VADIV(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vadiv, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_LINECYC(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(linecyc, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_SAGCYC(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(sagcyc, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_CFCYC(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(cfcyc, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_PEAKCYC(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(peakcyc, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_SAGLVL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(saglvl, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_IPKLVL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(ipklvl, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VPKLVL(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vpklvl, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_IPEAK(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(ipeak, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_RIPEAK(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(ripeak, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VPEAK(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vpeak, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_RVPEAK(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(rvpeak, _mode, _show, _store, _addr) - -#define IIO_DEV_ATTR_VPERIOD(_mode, _show, _store, _addr) \ - IIO_DEVICE_ATTR(vperiod, _mode, _show, _store, _addr) - -/* active energy register, AENERGY, is more than half full */ -#define IIO_EVENT_ATTR_AENERGY_HALF_FULL(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(aenergy_half_full, _evlist, _show, _store, _mask) - -/* a SAG on the line voltage */ -#define IIO_EVENT_ATTR_LINE_VOLT_SAG(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(line_volt_sag, _evlist, _show, _store, _mask) - -/* - * Indicates the end of energy accumulation over an integer number - * of half line cycles - */ -#define IIO_EVENT_ATTR_CYCEND(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(cycend, _evlist, _show, _store, _mask) - -/* on the rising and falling edge of the voltage waveform */ -#define IIO_EVENT_ATTR_ZERO_CROSS(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(zero_cross, _evlist, _show, _store, _mask) - -/* the active energy register has overflowed */ -#define IIO_EVENT_ATTR_AENERGY_OVERFLOW(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(aenergy_overflow, _evlist, _show, _store, _mask) - -/* the apparent energy register has overflowed */ -#define IIO_EVENT_ATTR_VAENERGY_OVERFLOW(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(vaenergy_overflow, _evlist, _show, _store, _mask) - -/* the active energy register, VAENERGY, is more than half full */ -#define IIO_EVENT_ATTR_VAENERGY_HALF_FULL(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(vaenergy_half_full, _evlist, _show, _store, _mask) - -/* the power has gone from negative to positive */ -#define IIO_EVENT_ATTR_PPOS(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(ppos, _evlist, _show, _store, _mask) - -/* the power has gone from positive to negative */ -#define IIO_EVENT_ATTR_PNEG(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(pneg, _evlist, _show, _store, _mask) - -/* waveform sample from Channel 1 has exceeded the IPKLVL value */ -#define IIO_EVENT_ATTR_IPKLVL_EXC(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(ipklvl_exc, _evlist, _show, _store, _mask) - -/* waveform sample from Channel 2 has exceeded the VPKLVL value */ -#define IIO_EVENT_ATTR_VPKLVL_EXC(_evlist, _show, _store, _mask) \ - IIO_EVENT_ATTR_SH(vpklvl_exc, _evlist, _show, _store, _mask) - -#endif /* _METER_H */ -- GitLab From e522a6f7cbeb0cdb672f3f3ed88dd1ed930a76d2 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Fri, 10 Feb 2023 16:24:21 -0800 Subject: [PATCH 0262/5631] iio: proximity: sx_common: Add old register mapping Older firmwares still send sensor configuration using a list of registers with opaque values defined during sensor tuning. sx9234 and sx9360 sensor on ACPI based devices are concerned. More schema to configure the sensors will be needed to support devices designed for windows, like Samsung Galaxy Book2. Support schema is: "<_HID>.". For instance "STH9324,reg_adv_ctrl2" in: Scope (\_SB.PCI0.I2C2) { Device (SX28) { Name (_HID, "STH9324") // _HID: Hardware ID ... Name (_DSD, Package (0x02) // _DSD: Device-Specific Data { ToUUID ("daffd814-6eba-4d8c-8a91-bc9bbf4aa301") /* Device Properties for _DSD */, Package (0x3F) { ... Package (0x02) { "STH9324,reg_adv_ctrl2", Zero },` Signed-off-by: Gwendal Grignou Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20230211002421.3447060-1-gwendal@chromium.org Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/sx9324.c | 96 ++++++++++++++++--------------- drivers/iio/proximity/sx9360.c | 32 +++++------ drivers/iio/proximity/sx_common.c | 21 +++++++ drivers/iio/proximity/sx_common.h | 5 ++ 4 files changed, 92 insertions(+), 62 deletions(-) diff --git a/drivers/iio/proximity/sx9324.c b/drivers/iio/proximity/sx9324.c index 977cf17cec52..9a40ca32bb1c 100644 --- a/drivers/iio/proximity/sx9324.c +++ b/drivers/iio/proximity/sx9324.c @@ -783,73 +783,75 @@ static int sx9324_write_raw(struct iio_dev *indio_dev, static const struct sx_common_reg_default sx9324_default_regs[] = { { SX9324_REG_IRQ_MSK, 0x00 }, - { SX9324_REG_IRQ_CFG0, 0x00 }, - { SX9324_REG_IRQ_CFG1, SX9324_REG_IRQ_CFG1_FAILCOND }, - { SX9324_REG_IRQ_CFG2, 0x00 }, - { SX9324_REG_GNRL_CTRL0, SX9324_REG_GNRL_CTRL0_SCANPERIOD_100MS }, + { SX9324_REG_IRQ_CFG0, 0x00, "irq_cfg0" }, + { SX9324_REG_IRQ_CFG1, SX9324_REG_IRQ_CFG1_FAILCOND, "irq_cfg1" }, + { SX9324_REG_IRQ_CFG2, 0x00, "irq_cfg2" }, + { SX9324_REG_GNRL_CTRL0, SX9324_REG_GNRL_CTRL0_SCANPERIOD_100MS, "gnrl_ctrl0" }, /* * The lower 4 bits should not be set as it enable sensors measurements. * Turning the detection on before the configuration values are set to * good values can cause the device to return erroneous readings. */ - { SX9324_REG_GNRL_CTRL1, SX9324_REG_GNRL_CTRL1_PAUSECTRL }, + { SX9324_REG_GNRL_CTRL1, SX9324_REG_GNRL_CTRL1_PAUSECTRL, "gnrl_ctrl1" }, - { SX9324_REG_AFE_CTRL0, SX9324_REG_AFE_CTRL0_RINT_LOWEST }, - { SX9324_REG_AFE_CTRL3, 0x00 }, + { SX9324_REG_AFE_CTRL0, SX9324_REG_AFE_CTRL0_RINT_LOWEST, "afe_ctrl0" }, + { SX9324_REG_AFE_CTRL3, 0x00, "afe_ctrl3" }, { SX9324_REG_AFE_CTRL4, SX9324_REG_AFE_CTRL4_FREQ_83_33HZ | - SX9324_REG_AFE_CTRL4_RES_100 }, - { SX9324_REG_AFE_CTRL6, 0x00 }, + SX9324_REG_AFE_CTRL4_RES_100, "afe_ctrl4" }, + { SX9324_REG_AFE_CTRL6, 0x00, "afe_ctrl6" }, { SX9324_REG_AFE_CTRL7, SX9324_REG_AFE_CTRL4_FREQ_83_33HZ | - SX9324_REG_AFE_CTRL4_RES_100 }, + SX9324_REG_AFE_CTRL4_RES_100, "afe_ctrl7" }, /* TODO(gwendal): PHx use chip default or all grounded? */ - { SX9324_REG_AFE_PH0, 0x29 }, - { SX9324_REG_AFE_PH1, 0x26 }, - { SX9324_REG_AFE_PH2, 0x1a }, - { SX9324_REG_AFE_PH3, 0x16 }, + { SX9324_REG_AFE_PH0, 0x29, "afe_ph0" }, + { SX9324_REG_AFE_PH1, 0x26, "afe_ph1" }, + { SX9324_REG_AFE_PH2, 0x1a, "afe_ph2" }, + { SX9324_REG_AFE_PH3, 0x16, "afe_ph3" }, { SX9324_REG_AFE_CTRL8, SX9324_REG_AFE_CTRL8_RESERVED | - SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM }, - { SX9324_REG_AFE_CTRL9, SX9324_REG_AFE_CTRL9_AGAIN_1 }, + SX9324_REG_AFE_CTRL8_RESFILTIN_4KOHM, "afe_ctrl8" }, + { SX9324_REG_AFE_CTRL9, SX9324_REG_AFE_CTRL9_AGAIN_1, "afe_ctrl9" }, { SX9324_REG_PROX_CTRL0, SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | - SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, + SX9324_REG_PROX_CTRL0_RAWFILT_1P50, "prox_ctrl0" }, { SX9324_REG_PROX_CTRL1, SX9324_REG_PROX_CTRL0_GAIN_1 << SX9324_REG_PROX_CTRL0_GAIN_SHIFT | - SX9324_REG_PROX_CTRL0_RAWFILT_1P50 }, - { SX9324_REG_PROX_CTRL2, SX9324_REG_PROX_CTRL2_AVGNEG_THRESH_16K }, + SX9324_REG_PROX_CTRL0_RAWFILT_1P50, "prox_ctrl1" }, + { SX9324_REG_PROX_CTRL2, SX9324_REG_PROX_CTRL2_AVGNEG_THRESH_16K, "prox_ctrl2" }, { SX9324_REG_PROX_CTRL3, SX9324_REG_PROX_CTRL3_AVGDEB_2SAMPLES | - SX9324_REG_PROX_CTRL3_AVGPOS_THRESH_16K }, + SX9324_REG_PROX_CTRL3_AVGPOS_THRESH_16K, "prox_ctrl3" }, { SX9324_REG_PROX_CTRL4, SX9324_REG_PROX_CTRL4_AVGNEG_FILT_2 | - SX9324_REG_PROX_CTRL4_AVGPOS_FILT_256 }, - { SX9324_REG_PROX_CTRL5, 0x00 }, - { SX9324_REG_PROX_CTRL6, SX9324_REG_PROX_CTRL6_PROXTHRESH_32 }, - { SX9324_REG_PROX_CTRL7, SX9324_REG_PROX_CTRL6_PROXTHRESH_32 }, - { SX9324_REG_ADV_CTRL0, 0x00 }, - { SX9324_REG_ADV_CTRL1, 0x00 }, - { SX9324_REG_ADV_CTRL2, 0x00 }, - { SX9324_REG_ADV_CTRL3, 0x00 }, - { SX9324_REG_ADV_CTRL4, 0x00 }, + SX9324_REG_PROX_CTRL4_AVGPOS_FILT_256, "prox_ctrl4" }, + { SX9324_REG_PROX_CTRL5, 0x00, "prox_ctrl5" }, + { SX9324_REG_PROX_CTRL6, SX9324_REG_PROX_CTRL6_PROXTHRESH_32, "prox_ctrl6" }, + { SX9324_REG_PROX_CTRL7, SX9324_REG_PROX_CTRL6_PROXTHRESH_32, "prox_ctrl7" }, + { SX9324_REG_ADV_CTRL0, 0x00, "adv_ctrl0" }, + { SX9324_REG_ADV_CTRL1, 0x00, "adv_ctrl1" }, + { SX9324_REG_ADV_CTRL2, 0x00, "adv_ctrl2" }, + { SX9324_REG_ADV_CTRL3, 0x00, "adv_ctrl3" }, + { SX9324_REG_ADV_CTRL4, 0x00, "adv_ctrl4" }, { SX9324_REG_ADV_CTRL5, SX9324_REG_ADV_CTRL5_STARTUP_SENSOR_1 | - SX9324_REG_ADV_CTRL5_STARTUP_METHOD_1 }, - { SX9324_REG_ADV_CTRL6, 0x00 }, - { SX9324_REG_ADV_CTRL7, 0x00 }, - { SX9324_REG_ADV_CTRL8, 0x00 }, - { SX9324_REG_ADV_CTRL9, 0x00 }, + SX9324_REG_ADV_CTRL5_STARTUP_METHOD_1, "adv_ctrl5" }, + { SX9324_REG_ADV_CTRL6, 0x00, "adv_ctrl6" }, + { SX9324_REG_ADV_CTRL7, 0x00, "adv_ctrl7" }, + { SX9324_REG_ADV_CTRL8, 0x00, "adv_ctrl8" }, + { SX9324_REG_ADV_CTRL9, 0x00, "adv_ctrl9" }, /* Body/Table threshold */ - { SX9324_REG_ADV_CTRL10, 0x00 }, - { SX9324_REG_ADV_CTRL11, 0x00 }, - { SX9324_REG_ADV_CTRL12, 0x00 }, + { SX9324_REG_ADV_CTRL10, 0x00, "adv_ctrl10" }, + { SX9324_REG_ADV_CTRL11, 0x00, "adv_ctrl11" }, + { SX9324_REG_ADV_CTRL12, 0x00, "adv_ctrl12" }, /* TODO(gwendal): SAR currenly disabled */ - { SX9324_REG_ADV_CTRL13, 0x00 }, - { SX9324_REG_ADV_CTRL14, 0x00 }, - { SX9324_REG_ADV_CTRL15, 0x00 }, - { SX9324_REG_ADV_CTRL16, 0x00 }, - { SX9324_REG_ADV_CTRL17, 0x00 }, - { SX9324_REG_ADV_CTRL18, 0x00 }, - { SX9324_REG_ADV_CTRL19, SX9324_REG_ADV_CTRL19_HIGHT_FAILURE_THRESH_SATURATION }, - { SX9324_REG_ADV_CTRL20, SX9324_REG_ADV_CTRL19_HIGHT_FAILURE_THRESH_SATURATION }, + { SX9324_REG_ADV_CTRL13, 0x00, "adv_ctrl13" }, + { SX9324_REG_ADV_CTRL14, 0x00, "adv_ctrl14" }, + { SX9324_REG_ADV_CTRL15, 0x00, "adv_ctrl15" }, + { SX9324_REG_ADV_CTRL16, 0x00, "adv_ctrl16" }, + { SX9324_REG_ADV_CTRL17, 0x00, "adv_ctrl17" }, + { SX9324_REG_ADV_CTRL18, 0x00, "adv_ctrl18" }, + { SX9324_REG_ADV_CTRL19, + SX9324_REG_ADV_CTRL19_HIGHT_FAILURE_THRESH_SATURATION, "adv_ctrl19" }, + { SX9324_REG_ADV_CTRL20, + SX9324_REG_ADV_CTRL19_HIGHT_FAILURE_THRESH_SATURATION, "adv_ctrl20" }, }; /* Activate all channels and perform an initial compensation. */ @@ -889,13 +891,15 @@ sx9324_get_default_reg(struct device *dev, int idx, const char *res; memcpy(reg_def, &sx9324_default_regs[idx], sizeof(*reg_def)); + + sx_common_get_raw_register_config(dev, reg_def); switch (reg_def->reg) { case SX9324_REG_AFE_PH0: case SX9324_REG_AFE_PH1: case SX9324_REG_AFE_PH2: case SX9324_REG_AFE_PH3: ph = reg_def->reg - SX9324_REG_AFE_PH0; - scnprintf(prop, ARRAY_SIZE(prop), "semtech,ph%d-pin", ph); + snprintf(prop, ARRAY_SIZE(prop), "semtech,ph%d-pin", ph); count = device_property_count_u32(dev, prop); if (count != ARRAY_SIZE(pin_defs)) diff --git a/drivers/iio/proximity/sx9360.c b/drivers/iio/proximity/sx9360.c index 6e19d22e6a01..a50d9176411a 100644 --- a/drivers/iio/proximity/sx9360.c +++ b/drivers/iio/proximity/sx9360.c @@ -663,37 +663,37 @@ static int sx9360_write_raw(struct iio_dev *indio_dev, static const struct sx_common_reg_default sx9360_default_regs[] = { { SX9360_REG_IRQ_MSK, 0x00 }, - { SX9360_REG_IRQ_CFG, 0x00 }, + { SX9360_REG_IRQ_CFG, 0x00, "irq_cfg" }, /* * The lower 2 bits should not be set as it enable sensors measurements. * Turning the detection on before the configuration values are set to * good values can cause the device to return erroneous readings. */ - { SX9360_REG_GNRL_CTRL0, 0x00 }, - { SX9360_REG_GNRL_CTRL1, 0x00 }, - { SX9360_REG_GNRL_CTRL2, SX9360_REG_GNRL_CTRL2_PERIOD_102MS }, + { SX9360_REG_GNRL_CTRL0, 0x00, "gnrl_ctrl0" }, + { SX9360_REG_GNRL_CTRL1, 0x00, "gnrl_ctrl1" }, + { SX9360_REG_GNRL_CTRL2, SX9360_REG_GNRL_CTRL2_PERIOD_102MS, "gnrl_ctrl2" }, - { SX9360_REG_AFE_CTRL1, SX9360_REG_AFE_CTRL1_RESFILTIN_0OHMS }, + { SX9360_REG_AFE_CTRL1, SX9360_REG_AFE_CTRL1_RESFILTIN_0OHMS, "afe_ctrl0" }, { SX9360_REG_AFE_PARAM0_PHR, SX9360_REG_AFE_PARAM0_RSVD | - SX9360_REG_AFE_PARAM0_RESOLUTION_128 }, + SX9360_REG_AFE_PARAM0_RESOLUTION_128, "afe_param0_phr" }, { SX9360_REG_AFE_PARAM1_PHR, SX9360_REG_AFE_PARAM1_AGAIN_PHM_6PF | - SX9360_REG_AFE_PARAM1_FREQ_83_33HZ }, + SX9360_REG_AFE_PARAM1_FREQ_83_33HZ, "afe_param1_phr" }, { SX9360_REG_AFE_PARAM0_PHM, SX9360_REG_AFE_PARAM0_RSVD | - SX9360_REG_AFE_PARAM0_RESOLUTION_128 }, + SX9360_REG_AFE_PARAM0_RESOLUTION_128, "afe_param0_phm" }, { SX9360_REG_AFE_PARAM1_PHM, SX9360_REG_AFE_PARAM1_AGAIN_PHM_6PF | - SX9360_REG_AFE_PARAM1_FREQ_83_33HZ }, + SX9360_REG_AFE_PARAM1_FREQ_83_33HZ, "afe_param1_phm" }, { SX9360_REG_PROX_CTRL0_PHR, SX9360_REG_PROX_CTRL0_GAIN_1 | - SX9360_REG_PROX_CTRL0_RAWFILT_1P50 }, + SX9360_REG_PROX_CTRL0_RAWFILT_1P50, "prox_ctrl0_phr" }, { SX9360_REG_PROX_CTRL0_PHM, SX9360_REG_PROX_CTRL0_GAIN_1 | - SX9360_REG_PROX_CTRL0_RAWFILT_1P50 }, - { SX9360_REG_PROX_CTRL1, SX9360_REG_PROX_CTRL1_AVGNEG_THRESH_16K }, + SX9360_REG_PROX_CTRL0_RAWFILT_1P50, "prox_ctrl0_phm" }, + { SX9360_REG_PROX_CTRL1, SX9360_REG_PROX_CTRL1_AVGNEG_THRESH_16K, "prox_ctrl1" }, { SX9360_REG_PROX_CTRL2, SX9360_REG_PROX_CTRL2_AVGDEB_2SAMPLES | - SX9360_REG_PROX_CTRL2_AVGPOS_THRESH_16K }, + SX9360_REG_PROX_CTRL2_AVGPOS_THRESH_16K, "prox_ctrl2" }, { SX9360_REG_PROX_CTRL3, SX9360_REG_PROX_CTRL3_AVGNEG_FILT_2 | - SX9360_REG_PROX_CTRL3_AVGPOS_FILT_256 }, - { SX9360_REG_PROX_CTRL4, 0x00 }, - { SX9360_REG_PROX_CTRL5, SX9360_REG_PROX_CTRL5_PROXTHRESH_32 }, + SX9360_REG_PROX_CTRL3_AVGPOS_FILT_256, "prox_ctrl3" }, + { SX9360_REG_PROX_CTRL4, 0x00, "prox_ctrl4" }, + { SX9360_REG_PROX_CTRL5, SX9360_REG_PROX_CTRL5_PROXTHRESH_32, "prox_ctrl5" }, }; /* Activate all channels and perform an initial compensation. */ diff --git a/drivers/iio/proximity/sx_common.c b/drivers/iio/proximity/sx_common.c index eba9256730ec..fe07d1444ac3 100644 --- a/drivers/iio/proximity/sx_common.c +++ b/drivers/iio/proximity/sx_common.c @@ -424,6 +424,27 @@ static const struct iio_buffer_setup_ops sx_common_buffer_setup_ops = { .postdisable = sx_common_buffer_postdisable, }; +void sx_common_get_raw_register_config(struct device *dev, + struct sx_common_reg_default *reg_def) +{ +#ifdef CONFIG_ACPI + struct acpi_device *adev = ACPI_COMPANION(dev); + u32 raw = 0, ret; + char prop[80]; + + if (!reg_def->property || !adev) + return; + + snprintf(prop, ARRAY_SIZE(prop), "%s,reg_%s", acpi_device_hid(adev), reg_def->property); + ret = device_property_read_u32(dev, prop, &raw); + if (ret) + return; + + reg_def->def = raw; +#endif +} +EXPORT_SYMBOL_NS_GPL(sx_common_get_raw_register_config, SEMTECH_PROX); + #define SX_COMMON_SOFT_RESET 0xde static int sx_common_init_device(struct device *dev, struct iio_dev *indio_dev) diff --git a/drivers/iio/proximity/sx_common.h b/drivers/iio/proximity/sx_common.h index a2bbdef200d1..101b90e52ff2 100644 --- a/drivers/iio/proximity/sx_common.h +++ b/drivers/iio/proximity/sx_common.h @@ -8,6 +8,7 @@ #ifndef IIO_SX_COMMON_H #define IIO_SX_COMMON_H +#include #include #include #include @@ -26,6 +27,7 @@ static_assert(SX_COMMON_MAX_NUM_CHANNELS < BITS_PER_LONG); struct sx_common_reg_default { u8 reg; u8 def; + const char *property; }; /** @@ -148,6 +150,9 @@ int sx_common_probe(struct i2c_client *client, const struct sx_common_chip_info *chip_info, const struct regmap_config *regmap_config); +void sx_common_get_raw_register_config(struct device *dev, + struct sx_common_reg_default *reg_def); + /* 3 is the number of events defined by a single phase. */ extern const struct iio_event_spec sx_common_events[3]; -- GitLab From e2b39db176d9d6420669aed477c949e8895d062b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 13 Feb 2023 16:32:08 +0100 Subject: [PATCH 0263/5631] iio: imu: adis16475: correct copy paste mistake in comment block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The minimal advised lower rate for adis16475 compatible devices is 1900HZ and not 4000HZ. Set that right in the comments so that it does not generate any confusion. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230213153208.1027602-1-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/imu/adis16475.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index aec55f7e1f26..3abffb01ba31 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -326,11 +326,11 @@ static int adis16475_set_freq(struct adis16475 *st, const u32 freq) /* * This is not an hard requirement but it's not advised to run the IMU - * with a sample rate lower than 4000Hz due to possible undersampling + * with a sample rate lower than 1900Hz due to possible undersampling * issues. However, there are users that might really want to take the risk. * Hence, we provide a module parameter for them. If set, we allow sample - * rates lower than 4KHz. By default, we won't allow this and we just roundup - * the rate to the next multiple of the input clock bigger than 4KHz. This + * rates lower than 1.9KHz. By default, we won't allow this and we just roundup + * the rate to the next multiple of the input clock bigger than 1.9KHz. This * is done like this as in some cases (when DEC_RATE is 0) might give * us the closest value to the one desired by the user... */ -- GitLab From 8957e5344353e9cd3f6b1e3004942e35449fa0e8 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Fri, 17 Feb 2023 15:34:03 +0000 Subject: [PATCH 0264/5631] iio: adc: axp20x_adc: Minor code cleanups The code may be clearer if parameters are not re-purposed to hold temporary results like register values, so introduce local variables as necessary to avoid that. Regroup macros based on chip type, and use the FIELD_PREP() macro instead of a hand-rolled version. Suggested-by: Jonathan Cameron Reviewed-by: Chen-Yu Tsai Reviewed-by: Andy Shevchenko Signed-off-by: Aidan MacDonald Link: https://lore.kernel.org/r/20230217153404.32481-1-aidanmacdonald.0x0@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/axp20x_adc.c | 61 +++++++++++++++++++----------------- 1 file changed, 32 insertions(+), 29 deletions(-) diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index 53bf7d4899d2..ab25e6e1ff65 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -5,6 +5,7 @@ * Quentin Schulz */ +#include #include #include #include @@ -22,20 +23,20 @@ #include #define AXP20X_ADC_EN1_MASK GENMASK(7, 0) - #define AXP20X_ADC_EN2_MASK (GENMASK(3, 2) | BIT(7)) + #define AXP22X_ADC_EN1_MASK (GENMASK(7, 5) | BIT(0)) #define AXP20X_GPIO10_IN_RANGE_GPIO0 BIT(0) #define AXP20X_GPIO10_IN_RANGE_GPIO1 BIT(1) -#define AXP20X_GPIO10_IN_RANGE_GPIO0_VAL(x) ((x) & BIT(0)) -#define AXP20X_GPIO10_IN_RANGE_GPIO1_VAL(x) (((x) & BIT(0)) << 1) #define AXP20X_ADC_RATE_MASK GENMASK(7, 6) -#define AXP813_V_I_ADC_RATE_MASK GENMASK(5, 4) -#define AXP813_ADC_RATE_MASK (AXP20X_ADC_RATE_MASK | AXP813_V_I_ADC_RATE_MASK) #define AXP20X_ADC_RATE_HZ(x) ((ilog2((x) / 25) << 6) & AXP20X_ADC_RATE_MASK) + #define AXP22X_ADC_RATE_HZ(x) ((ilog2((x) / 100) << 6) & AXP20X_ADC_RATE_MASK) + +#define AXP813_V_I_ADC_RATE_MASK GENMASK(5, 4) +#define AXP813_ADC_RATE_MASK (AXP20X_ADC_RATE_MASK | AXP813_V_I_ADC_RATE_MASK) #define AXP813_TS_GPIO0_ADC_RATE_HZ(x) AXP20X_ADC_RATE_HZ(x) #define AXP813_V_I_ADC_RATE_HZ(x) ((ilog2((x) / 100) << 4) & AXP813_V_I_ADC_RATE_MASK) #define AXP813_ADC_RATE_HZ(x) (AXP20X_ADC_RATE_HZ(x) | AXP813_V_I_ADC_RATE_HZ(x)) @@ -234,7 +235,7 @@ static int axp20x_adc_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val) { struct axp20x_adc_iio *info = iio_priv(indio_dev); - int size = 12; + int ret, size; /* * N.B.: Unlike the Chinese datasheets tell, the charging current is @@ -246,10 +247,11 @@ static int axp20x_adc_raw(struct iio_dev *indio_dev, else size = 12; - *val = axp20x_read_variable_width(info->regmap, chan->address, size); - if (*val < 0) - return *val; + ret = axp20x_read_variable_width(info->regmap, chan->address, size); + if (ret < 0) + return ret; + *val = ret; return IIO_VAL_INT; } @@ -257,11 +259,13 @@ static int axp22x_adc_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val) { struct axp20x_adc_iio *info = iio_priv(indio_dev); + int ret; - *val = axp20x_read_variable_width(info->regmap, chan->address, 12); - if (*val < 0) - return *val; + ret = axp20x_read_variable_width(info->regmap, chan->address, 12); + if (ret < 0) + return ret; + *val = ret; return IIO_VAL_INT; } @@ -269,11 +273,13 @@ static int axp813_adc_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val) { struct axp20x_adc_iio *info = iio_priv(indio_dev); + int ret; - *val = axp20x_read_variable_width(info->regmap, chan->address, 12); - if (*val < 0) - return *val; + ret = axp20x_read_variable_width(info->regmap, chan->address, 12); + if (ret < 0) + return ret; + *val = ret; return IIO_VAL_INT; } @@ -443,27 +449,27 @@ static int axp20x_adc_offset_voltage(struct iio_dev *indio_dev, int channel, int *val) { struct axp20x_adc_iio *info = iio_priv(indio_dev); + unsigned int regval; int ret; - ret = regmap_read(info->regmap, AXP20X_GPIO10_IN_RANGE, val); + ret = regmap_read(info->regmap, AXP20X_GPIO10_IN_RANGE, ®val); if (ret < 0) return ret; switch (channel) { case AXP20X_GPIO0_V: - *val &= AXP20X_GPIO10_IN_RANGE_GPIO0; + regval = FIELD_GET(AXP20X_GPIO10_IN_RANGE_GPIO0, regval); break; case AXP20X_GPIO1_V: - *val &= AXP20X_GPIO10_IN_RANGE_GPIO1; + regval = FIELD_GET(AXP20X_GPIO10_IN_RANGE_GPIO1, regval); break; default: return -EINVAL; } - *val = *val ? 700000 : 0; - + *val = regval ? 700000 : 0; return IIO_VAL_INT; } @@ -548,7 +554,7 @@ static int axp20x_write_raw(struct iio_dev *indio_dev, long mask) { struct axp20x_adc_iio *info = iio_priv(indio_dev); - unsigned int reg, regval; + unsigned int regmask, regval; /* * The AXP20X PMIC allows the user to choose between 0V and 0.7V offsets @@ -560,25 +566,22 @@ static int axp20x_write_raw(struct iio_dev *indio_dev, if (val != 0 && val != 700000) return -EINVAL; - val = val ? 1 : 0; - switch (chan->channel) { case AXP20X_GPIO0_V: - reg = AXP20X_GPIO10_IN_RANGE_GPIO0; - regval = AXP20X_GPIO10_IN_RANGE_GPIO0_VAL(val); + regmask = AXP20X_GPIO10_IN_RANGE_GPIO0; + regval = FIELD_PREP(AXP20X_GPIO10_IN_RANGE_GPIO0, !!val); break; case AXP20X_GPIO1_V: - reg = AXP20X_GPIO10_IN_RANGE_GPIO1; - regval = AXP20X_GPIO10_IN_RANGE_GPIO1_VAL(val); + regmask = AXP20X_GPIO10_IN_RANGE_GPIO1; + regval = FIELD_PREP(AXP20X_GPIO10_IN_RANGE_GPIO1, !!val); break; default: return -EINVAL; } - return regmap_update_bits(info->regmap, AXP20X_GPIO10_IN_RANGE, reg, - regval); + return regmap_update_bits(info->regmap, AXP20X_GPIO10_IN_RANGE, regmask, regval); } static const struct iio_info axp20x_adc_iio_info = { -- GitLab From c286b0472ca8d76092c1f4fb782c6745b26e74f6 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Fri, 17 Feb 2023 15:34:04 +0000 Subject: [PATCH 0265/5631] iio: adc: axp20x_adc: Replace adc_en2 flag with adc_en2_mask field The adc_en2 flag is essentially specific to axp20x-compatible devices because it hardcodes register values. Replace it with a mask field so the register value can be specified in device match data. Reviewed-by: Andy Shevchenko Signed-off-by: Aidan MacDonald Link: https://lore.kernel.org/r/20230217153404.32481-2-aidanmacdonald.0x0@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/axp20x_adc.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index ab25e6e1ff65..75bda94dbce1 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -623,9 +623,9 @@ struct axp_data { int num_channels; struct iio_chan_spec const *channels; unsigned long adc_en1_mask; + unsigned long adc_en2_mask; int (*adc_rate)(struct axp20x_adc_iio *info, int rate); - bool adc_en2; struct iio_map *maps; }; @@ -634,8 +634,8 @@ static const struct axp_data axp20x_data = { .num_channels = ARRAY_SIZE(axp20x_adc_channels), .channels = axp20x_adc_channels, .adc_en1_mask = AXP20X_ADC_EN1_MASK, + .adc_en2_mask = AXP20X_ADC_EN2_MASK, .adc_rate = axp20x_adc_rate, - .adc_en2 = true, .maps = axp20x_maps, }; @@ -645,7 +645,6 @@ static const struct axp_data axp22x_data = { .channels = axp22x_adc_channels, .adc_en1_mask = AXP22X_ADC_EN1_MASK, .adc_rate = axp22x_adc_rate, - .adc_en2 = false, .maps = axp22x_maps, }; @@ -655,7 +654,6 @@ static const struct axp_data axp813_data = { .channels = axp813_adc_channels, .adc_en1_mask = AXP22X_ADC_EN1_MASK, .adc_rate = axp813_adc_rate, - .adc_en2 = false, .maps = axp22x_maps, }; @@ -713,10 +711,10 @@ static int axp20x_probe(struct platform_device *pdev) /* Enable the ADCs on IP */ regmap_write(info->regmap, AXP20X_ADC_EN1, info->data->adc_en1_mask); - if (info->data->adc_en2) - /* Enable GPIO0/1 and internal temperature ADCs */ + if (info->data->adc_en2_mask) regmap_update_bits(info->regmap, AXP20X_ADC_EN2, - AXP20X_ADC_EN2_MASK, AXP20X_ADC_EN2_MASK); + info->data->adc_en2_mask, + info->data->adc_en2_mask); /* Configure ADCs rate */ info->data->adc_rate(info, 100); @@ -741,7 +739,7 @@ static int axp20x_probe(struct platform_device *pdev) fail_map: regmap_write(info->regmap, AXP20X_ADC_EN1, 0); - if (info->data->adc_en2) + if (info->data->adc_en2_mask) regmap_write(info->regmap, AXP20X_ADC_EN2, 0); return ret; @@ -757,7 +755,7 @@ static int axp20x_remove(struct platform_device *pdev) regmap_write(info->regmap, AXP20X_ADC_EN1, 0); - if (info->data->adc_en2) + if (info->data->adc_en2_mask) regmap_write(info->regmap, AXP20X_ADC_EN2, 0); return 0; -- GitLab From 4ab8bef1eaa534d3669852f2fe22e0f1c86c1426 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Feb 2023 21:44:39 +0100 Subject: [PATCH 0266/5631] iio: adc: meson_saradc: Better handle BL30 not releasing the hardware MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit meson_sar_adc_lock() might return an error if BL30 doesn't release its lock on the hardware. Just returning early from .remove() is wrong however as this keeps the clocks and regulators on which is never cleaned up later. Given the BL30 not giving up its lock is a strong hint for broken behaviour, and there is nothing we can do about that: Just clean up ignoring the fact that we're not holding the lock. Signed-off-by: Uwe Kleine-König Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/20230219204439.1641640-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/adc/meson_saradc.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index 85b6826cc10c..18937a262af6 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -957,14 +957,18 @@ static int meson_sar_adc_hw_enable(struct iio_dev *indio_dev) return ret; } -static int meson_sar_adc_hw_disable(struct iio_dev *indio_dev) +static void meson_sar_adc_hw_disable(struct iio_dev *indio_dev) { struct meson_sar_adc_priv *priv = iio_priv(indio_dev); int ret; + /* + * If taking the lock fails we have to assume that BL30 is broken. The + * best we can do then is to release the resources anyhow. + */ ret = meson_sar_adc_lock(indio_dev); if (ret) - return ret; + dev_err(indio_dev->dev.parent, "Failed to lock ADC (%pE)\n", ERR_PTR(ret)); clk_disable_unprepare(priv->adc_clk); @@ -977,9 +981,8 @@ static int meson_sar_adc_hw_disable(struct iio_dev *indio_dev) regulator_disable(priv->vref); - meson_sar_adc_unlock(indio_dev); - - return 0; + if (!ret) + meson_sar_adc_unlock(indio_dev); } static irqreturn_t meson_sar_adc_irq(int irq, void *data) @@ -1283,14 +1286,18 @@ static int meson_sar_adc_remove(struct platform_device *pdev) iio_device_unregister(indio_dev); - return meson_sar_adc_hw_disable(indio_dev); + meson_sar_adc_hw_disable(indio_dev); + + return 0; } static int meson_sar_adc_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); - return meson_sar_adc_hw_disable(indio_dev); + meson_sar_adc_hw_disable(indio_dev); + + return 0; } static int meson_sar_adc_resume(struct device *dev) -- GitLab From 0b0b772637cd7f35c15830bbb8e8ec66d6c34ddd Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 17:57:59 +0100 Subject: [PATCH 0267/5631] iio: pressure: bmp280: Use chip_info pointers for each chip as driver data Refactor driver I2C and SPI implementations using pointers for each variant's chip_info as the driver data. Adds the regmap configuration to the chip_info struct. Suggested-by: Andy Shevchenko Suggested-by: Jonathan Cameron Signed-off-by: Angel Iglesias Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/a48cfa756be48d61dbf656c65daff6e9a1290e6f.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 190 +++-------------------------- drivers/iio/pressure/bmp280-i2c.c | 43 +++---- drivers/iio/pressure/bmp280-spi.c | 45 +++---- drivers/iio/pressure/bmp280.h | 164 ++++++++++++++++++++++++- 4 files changed, 215 insertions(+), 227 deletions(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index c0aff78489b4..2c8773db4b73 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -49,65 +49,6 @@ */ enum { AC1, AC2, AC3, AC4, AC5, AC6, B1, B2, MB, MC, MD }; -struct bmp180_calib { - s16 AC1; - s16 AC2; - s16 AC3; - u16 AC4; - u16 AC5; - u16 AC6; - s16 B1; - s16 B2; - s16 MB; - s16 MC; - s16 MD; -}; - -/* See datasheet Section 4.2.2. */ -struct bmp280_calib { - u16 T1; - s16 T2; - s16 T3; - u16 P1; - s16 P2; - s16 P3; - s16 P4; - s16 P5; - s16 P6; - s16 P7; - s16 P8; - s16 P9; - u8 H1; - s16 H2; - u8 H3; - s16 H4; - s16 H5; - s8 H6; -}; - -/* See datasheet Section 3.11.1. */ -struct bmp380_calib { - u16 T1; - u16 T2; - s8 T3; - s16 P1; - s16 P2; - s8 P3; - s8 P4; - u16 P5; - u16 P6; - s8 P7; - s8 P8; - s16 P9; - s8 P10; - s8 P11; -}; - -static const char *const bmp280_supply_names[] = { - "vddd", "vdda" -}; - -#define BMP280_NUM_SUPPLIES ARRAY_SIZE(bmp280_supply_names) enum bmp380_odr { BMP380_ODR_200HZ, @@ -130,94 +71,6 @@ enum bmp380_odr { BMP380_ODR_0_0015HZ, }; -struct bmp280_data { - struct device *dev; - struct mutex lock; - struct regmap *regmap; - struct completion done; - bool use_eoc; - const struct bmp280_chip_info *chip_info; - union { - struct bmp180_calib bmp180; - struct bmp280_calib bmp280; - struct bmp380_calib bmp380; - } calib; - struct regulator_bulk_data supplies[BMP280_NUM_SUPPLIES]; - unsigned int start_up_time; /* in microseconds */ - - /* log of base 2 of oversampling rate */ - u8 oversampling_press; - u8 oversampling_temp; - u8 oversampling_humid; - u8 iir_filter_coeff; - - /* - * BMP380 devices introduce sampling frequency configuration. See - * datasheet sections 3.3.3. and 4.3.19 for more details. - * - * BMx280 devices allowed indirect configuration of sampling frequency - * changing the t_standby duration between measurements, as detailed on - * section 3.6.3 of the datasheet. - */ - int sampling_freq; - - /* - * Carryover value from temperature conversion, used in pressure - * calculation. - */ - s32 t_fine; - - /* - * DMA (thus cache coherency maintenance) may require the - * transfer buffers to live in their own cache lines. - */ - union { - /* Sensor data buffer */ - u8 buf[3]; - /* Calibration data buffers */ - __le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2]; - __be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2]; - u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT]; - /* Miscellaneous, endianess-aware data buffers */ - __le16 le16; - __be16 be16; - } __aligned(IIO_DMA_MINALIGN); -}; - -struct bmp280_chip_info { - unsigned int id_reg; - - const struct iio_chan_spec *channels; - int num_channels; - unsigned int start_up_time; - - const int *oversampling_temp_avail; - int num_oversampling_temp_avail; - int oversampling_temp_default; - - const int *oversampling_press_avail; - int num_oversampling_press_avail; - int oversampling_press_default; - - const int *oversampling_humid_avail; - int num_oversampling_humid_avail; - int oversampling_humid_default; - - const int *iir_filter_coeffs_avail; - int num_iir_filter_coeffs_avail; - int iir_filter_coeff_default; - - const int (*sampling_freq_avail)[2]; - int num_sampling_freq_avail; - int sampling_freq_default; - - int (*chip_config)(struct bmp280_data *); - int (*read_temp)(struct bmp280_data *, int *); - int (*read_press)(struct bmp280_data *, int *, int *); - int (*read_humid)(struct bmp280_data *, int *, int *); - int (*read_calib)(struct bmp280_data *); -}; - /* * These enums are used for indexing into the array of compensation * parameters for BMP280. @@ -905,8 +758,10 @@ static int bmp280_chip_config(struct bmp280_data *data) static const int bmp280_oversampling_avail[] = { 1, 2, 4, 8, 16 }; -static const struct bmp280_chip_info bmp280_chip_info = { +const struct bmp280_chip_info bmp280_chip_info = { .id_reg = BMP280_REG_ID, + .chip_id = BMP280_CHIP_ID, + .regmap_config = &bmp280_regmap_config, .start_up_time = 2000, .channels = bmp280_channels, .num_channels = 2, @@ -934,6 +789,7 @@ static const struct bmp280_chip_info bmp280_chip_info = { .read_press = bmp280_read_press, .read_calib = bmp280_read_calib, }; +EXPORT_SYMBOL_NS(bmp280_chip_info, IIO_BMP280); static int bme280_chip_config(struct bmp280_data *data) { @@ -953,8 +809,10 @@ static int bme280_chip_config(struct bmp280_data *data) return bmp280_chip_config(data); } -static const struct bmp280_chip_info bme280_chip_info = { +const struct bmp280_chip_info bme280_chip_info = { .id_reg = BMP280_REG_ID, + .chip_id = BME280_CHIP_ID, + .regmap_config = &bmp280_regmap_config, .start_up_time = 2000, .channels = bmp280_channels, .num_channels = 3, @@ -977,6 +835,7 @@ static const struct bmp280_chip_info bme280_chip_info = { .read_humid = bmp280_read_humid, .read_calib = bme280_read_calib, }; +EXPORT_SYMBOL_NS(bme280_chip_info, IIO_BMP280); /* * Helper function to send a command to BMP3XX sensors. @@ -1319,8 +1178,10 @@ static int bmp380_chip_config(struct bmp280_data *data) static const int bmp380_oversampling_avail[] = { 1, 2, 4, 8, 16, 32 }; static const int bmp380_iir_filter_coeffs_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128}; -static const struct bmp280_chip_info bmp380_chip_info = { +const struct bmp280_chip_info bmp380_chip_info = { .id_reg = BMP380_REG_ID, + .chip_id = BMP380_CHIP_ID, + .regmap_config = &bmp380_regmap_config, .start_up_time = 2000, .channels = bmp380_channels, .num_channels = 2, @@ -1346,6 +1207,7 @@ static const struct bmp280_chip_info bmp380_chip_info = { .read_press = bmp380_read_press, .read_calib = bmp380_read_calib, }; +EXPORT_SYMBOL_NS(bmp380_chip_info, IIO_BMP280); static int bmp180_measure(struct bmp280_data *data, u8 ctrl_meas) { @@ -1579,8 +1441,10 @@ static int bmp180_chip_config(struct bmp280_data *data) static const int bmp180_oversampling_temp_avail[] = { 1 }; static const int bmp180_oversampling_press_avail[] = { 1, 2, 4, 8 }; -static const struct bmp280_chip_info bmp180_chip_info = { +const struct bmp280_chip_info bmp180_chip_info = { .id_reg = BMP280_REG_ID, + .chip_id = BMP180_CHIP_ID, + .regmap_config = &bmp180_regmap_config, .start_up_time = 2000, .channels = bmp280_channels, .num_channels = 2, @@ -1600,6 +1464,7 @@ static const struct bmp280_chip_info bmp180_chip_info = { .read_press = bmp180_read_press, .read_calib = bmp180_read_calib, }; +EXPORT_SYMBOL_NS(bmp180_chip_info, IIO_BMP280); static irqreturn_t bmp085_eoc_irq(int irq, void *d) { @@ -1661,11 +1526,10 @@ static void bmp280_regulators_disable(void *data) int bmp280_common_probe(struct device *dev, struct regmap *regmap, - unsigned int chip, + const struct bmp280_chip_info *chip_info, const char *name, int irq) { - const struct bmp280_chip_info *chip_info; struct iio_dev *indio_dev; struct bmp280_data *data; struct gpio_desc *gpiod; @@ -1684,22 +1548,6 @@ int bmp280_common_probe(struct device *dev, indio_dev->info = &bmp280_info; indio_dev->modes = INDIO_DIRECT_MODE; - switch (chip) { - case BMP180_CHIP_ID: - chip_info = &bmp180_chip_info; - break; - case BMP280_CHIP_ID: - chip_info = &bmp280_chip_info; - break; - case BME280_CHIP_ID: - chip_info = &bme280_chip_info; - break; - case BMP380_CHIP_ID: - chip_info = &bmp380_chip_info; - break; - default: - return -EINVAL; - } data->chip_info = chip_info; /* Apply initial values from chip info structure */ @@ -1751,9 +1599,9 @@ int bmp280_common_probe(struct device *dev, ret = regmap_read(regmap, data->chip_info->id_reg, &chip_id); if (ret < 0) return ret; - if (chip_id != chip) { + if (chip_id != data->chip_info->chip_id) { dev_err(dev, "bad chip id: expected %x got %x\n", - chip, chip_id); + data->chip_info->chip_id, chip_id); return -EINVAL; } diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c index 14eab086d24a..5f908e2c9826 100644 --- a/drivers/iio/pressure/bmp280-i2c.c +++ b/drivers/iio/pressure/bmp280-i2c.c @@ -8,25 +8,14 @@ static int bmp280_i2c_probe(struct i2c_client *client) { struct regmap *regmap; - const struct regmap_config *regmap_config; + const struct bmp280_chip_info *chip_info; const struct i2c_device_id *id = i2c_client_get_device_id(client); - switch (id->driver_data) { - case BMP180_CHIP_ID: - regmap_config = &bmp180_regmap_config; - break; - case BMP280_CHIP_ID: - case BME280_CHIP_ID: - regmap_config = &bmp280_regmap_config; - break; - case BMP380_CHIP_ID: - regmap_config = &bmp380_regmap_config; - break; - default: - return -EINVAL; - } + chip_info = device_get_match_data(&client->dev); + if (!chip_info) + chip_info = (const struct bmp280_chip_info *) id->driver_data; - regmap = devm_regmap_init_i2c(client, regmap_config); + regmap = devm_regmap_init_i2c(client, chip_info->regmap_config); if (IS_ERR(regmap)) { dev_err(&client->dev, "failed to allocate register map\n"); return PTR_ERR(regmap); @@ -34,27 +23,27 @@ static int bmp280_i2c_probe(struct i2c_client *client) return bmp280_common_probe(&client->dev, regmap, - id->driver_data, + chip_info, id->name, client->irq); } static const struct of_device_id bmp280_of_i2c_match[] = { - { .compatible = "bosch,bmp085", .data = (void *)BMP180_CHIP_ID }, - { .compatible = "bosch,bmp180", .data = (void *)BMP180_CHIP_ID }, - { .compatible = "bosch,bmp280", .data = (void *)BMP280_CHIP_ID }, - { .compatible = "bosch,bme280", .data = (void *)BME280_CHIP_ID }, - { .compatible = "bosch,bmp380", .data = (void *)BMP380_CHIP_ID }, + { .compatible = "bosch,bmp085", .data = &bmp180_chip_info }, + { .compatible = "bosch,bmp180", .data = &bmp180_chip_info }, + { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, + { .compatible = "bosch,bme280", .data = &bme280_chip_info }, + { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, { }, }; MODULE_DEVICE_TABLE(of, bmp280_of_i2c_match); static const struct i2c_device_id bmp280_i2c_id[] = { - {"bmp085", BMP180_CHIP_ID }, - {"bmp180", BMP180_CHIP_ID }, - {"bmp280", BMP280_CHIP_ID }, - {"bme280", BME280_CHIP_ID }, - {"bmp380", BMP380_CHIP_ID }, + {"bmp085", (kernel_ulong_t)&bmp180_chip_info }, + {"bmp180", (kernel_ulong_t)&bmp180_chip_info }, + {"bmp280", (kernel_ulong_t)&bmp280_chip_info }, + {"bme280", (kernel_ulong_t)&bme280_chip_info }, + {"bmp380", (kernel_ulong_t)&bmp380_chip_info }, { }, }; MODULE_DEVICE_TABLE(i2c, bmp280_i2c_id); diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index 011c68e07ebf..d5a224b95185 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -47,8 +47,8 @@ static struct regmap_bus bmp280_regmap_bus = { static int bmp280_spi_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); + const struct bmp280_chip_info *chip_info; struct regmap *regmap; - const struct regmap_config *regmap_config; int ret; spi->bits_per_word = 8; @@ -58,25 +58,14 @@ static int bmp280_spi_probe(struct spi_device *spi) return ret; } - switch (id->driver_data) { - case BMP180_CHIP_ID: - regmap_config = &bmp180_regmap_config; - break; - case BMP280_CHIP_ID: - case BME280_CHIP_ID: - regmap_config = &bmp280_regmap_config; - break; - case BMP380_CHIP_ID: - regmap_config = &bmp380_regmap_config; - break; - default: - return -EINVAL; - } + chip_info = device_get_match_data(&spi->dev); + if (!chip_info) + chip_info = (const struct bmp280_chip_info *) id->driver_data; regmap = devm_regmap_init(&spi->dev, &bmp280_regmap_bus, &spi->dev, - regmap_config); + chip_info->regmap_config); if (IS_ERR(regmap)) { dev_err(&spi->dev, "failed to allocate register map\n"); return PTR_ERR(regmap); @@ -84,28 +73,28 @@ static int bmp280_spi_probe(struct spi_device *spi) return bmp280_common_probe(&spi->dev, regmap, - id->driver_data, + chip_info, id->name, spi->irq); } static const struct of_device_id bmp280_of_spi_match[] = { - { .compatible = "bosch,bmp085", }, - { .compatible = "bosch,bmp180", }, - { .compatible = "bosch,bmp181", }, - { .compatible = "bosch,bmp280", }, - { .compatible = "bosch,bme280", }, - { .compatible = "bosch,bmp380", }, + { .compatible = "bosch,bmp085", .data = &bmp180_chip_info }, + { .compatible = "bosch,bmp180", .data = &bmp180_chip_info }, + { .compatible = "bosch,bmp181", .data = &bmp180_chip_info }, + { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, + { .compatible = "bosch,bme280", .data = &bmp280_chip_info }, + { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, { }, }; MODULE_DEVICE_TABLE(of, bmp280_of_spi_match); static const struct spi_device_id bmp280_spi_id[] = { - { "bmp180", BMP180_CHIP_ID }, - { "bmp181", BMP180_CHIP_ID }, - { "bmp280", BMP280_CHIP_ID }, - { "bme280", BME280_CHIP_ID }, - { "bmp380", BMP380_CHIP_ID }, + { "bmp180", (kernel_ulong_t)&bmp180_chip_info }, + { "bmp181", (kernel_ulong_t)&bmp180_chip_info }, + { "bmp280", (kernel_ulong_t)&bmp280_chip_info }, + { "bme280", (kernel_ulong_t)&bmp280_chip_info }, + { "bmp380", (kernel_ulong_t)&bmp380_chip_info }, { } }; MODULE_DEVICE_TABLE(spi, bmp280_spi_id); diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index c791325c7416..387723fd0772 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -1,7 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include #include +#include #include +#include + /* BMP380 specific registers */ #define BMP380_REG_CMD 0x7E @@ -191,6 +194,165 @@ #define BMP280_PRESS_SKIPPED 0x80000 #define BMP280_HUMIDITY_SKIPPED 0x8000 +/* Core exported structs */ + +static const char *const bmp280_supply_names[] = { + "vddd", "vdda" +}; + +#define BMP280_NUM_SUPPLIES ARRAY_SIZE(bmp280_supply_names) + +struct bmp180_calib { + s16 AC1; + s16 AC2; + s16 AC3; + u16 AC4; + u16 AC5; + u16 AC6; + s16 B1; + s16 B2; + s16 MB; + s16 MC; + s16 MD; +}; + +/* See datasheet Section 4.2.2. */ +struct bmp280_calib { + u16 T1; + s16 T2; + s16 T3; + u16 P1; + s16 P2; + s16 P3; + s16 P4; + s16 P5; + s16 P6; + s16 P7; + s16 P8; + s16 P9; + u8 H1; + s16 H2; + u8 H3; + s16 H4; + s16 H5; + s8 H6; +}; + +/* See datasheet Section 3.11.1. */ +struct bmp380_calib { + u16 T1; + u16 T2; + s8 T3; + s16 P1; + s16 P2; + s8 P3; + s8 P4; + u16 P5; + u16 P6; + s8 P7; + s8 P8; + s16 P9; + s8 P10; + s8 P11; +}; + +struct bmp280_data { + struct device *dev; + struct mutex lock; + struct regmap *regmap; + struct completion done; + bool use_eoc; + const struct bmp280_chip_info *chip_info; + union { + struct bmp180_calib bmp180; + struct bmp280_calib bmp280; + struct bmp380_calib bmp380; + } calib; + struct regulator_bulk_data supplies[BMP280_NUM_SUPPLIES]; + unsigned int start_up_time; /* in microseconds */ + + /* log of base 2 of oversampling rate */ + u8 oversampling_press; + u8 oversampling_temp; + u8 oversampling_humid; + u8 iir_filter_coeff; + + /* + * BMP380 devices introduce sampling frequency configuration. See + * datasheet sections 3.3.3. and 4.3.19 for more details. + * + * BMx280 devices allowed indirect configuration of sampling frequency + * changing the t_standby duration between measurements, as detailed on + * section 3.6.3 of the datasheet. + */ + int sampling_freq; + + /* + * Carryover value from temperature conversion, used in pressure + * calculation. + */ + s32 t_fine; + + /* + * DMA (thus cache coherency maintenance) may require the + * transfer buffers to live in their own cache lines. + */ + union { + /* Sensor data buffer */ + u8 buf[3]; + /* Calibration data buffers */ + __le16 bmp280_cal_buf[BMP280_CONTIGUOUS_CALIB_REGS / 2]; + __be16 bmp180_cal_buf[BMP180_REG_CALIB_COUNT / 2]; + u8 bmp380_cal_buf[BMP380_CALIB_REG_COUNT]; + /* Miscellaneous, endianess-aware data buffers */ + __le16 le16; + __be16 be16; + } __aligned(IIO_DMA_MINALIGN); +}; + +struct bmp280_chip_info { + unsigned int id_reg; + const unsigned int chip_id; + + const struct regmap_config *regmap_config; + + const struct iio_chan_spec *channels; + int num_channels; + unsigned int start_up_time; + + const int *oversampling_temp_avail; + int num_oversampling_temp_avail; + int oversampling_temp_default; + + const int *oversampling_press_avail; + int num_oversampling_press_avail; + int oversampling_press_default; + + const int *oversampling_humid_avail; + int num_oversampling_humid_avail; + int oversampling_humid_default; + + const int *iir_filter_coeffs_avail; + int num_iir_filter_coeffs_avail; + int iir_filter_coeff_default; + + const int (*sampling_freq_avail)[2]; + int num_sampling_freq_avail; + int sampling_freq_default; + + int (*chip_config)(struct bmp280_data *); + int (*read_temp)(struct bmp280_data *, int *); + int (*read_press)(struct bmp280_data *, int *, int *); + int (*read_humid)(struct bmp280_data *, int *, int *); + int (*read_calib)(struct bmp280_data *); +}; + +/* Chip infos for each variant */ +extern const struct bmp280_chip_info bmp180_chip_info; +extern const struct bmp280_chip_info bmp280_chip_info; +extern const struct bmp280_chip_info bme280_chip_info; +extern const struct bmp280_chip_info bmp380_chip_info; + /* Regmap configurations */ extern const struct regmap_config bmp180_regmap_config; extern const struct regmap_config bmp280_regmap_config; @@ -199,7 +361,7 @@ extern const struct regmap_config bmp380_regmap_config; /* Probe called from different transports */ int bmp280_common_probe(struct device *dev, struct regmap *regmap, - unsigned int chip, + const struct bmp280_chip_info *, const char *name, int irq); -- GitLab From c25ea00fefa4e57a63209769fa3e4903791d05af Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 17:58:00 +0100 Subject: [PATCH 0268/5631] iio: pressure: bmp280: Add preinit callback Adds preinit callback to execute operations on probe before applying initial configuration. Signed-off-by: Angel Iglesias Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/fa9513ffad37a6a43b6d46df9d8319ccab6f5870.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 17 ++++++++++++----- drivers/iio/pressure/bmp280.h | 1 + 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 2c8773db4b73..6467034b1d3e 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1076,6 +1076,12 @@ static const int bmp380_odr_table[][2] = { [BMP380_ODR_0_0015HZ] = {0, 1526}, }; +static int bmp380_preinit(struct bmp280_data *data) +{ + /* BMP3xx requires soft-reset as part of initialization */ + return bmp380_cmd(data, BMP380_CMD_SOFT_RESET); +} + static int bmp380_chip_config(struct bmp280_data *data) { bool change = false, aux; @@ -1206,6 +1212,7 @@ const struct bmp280_chip_info bmp380_chip_info = { .read_temp = bmp380_read_temp, .read_press = bmp380_read_press, .read_calib = bmp380_read_calib, + .preinit = bmp380_preinit, }; EXPORT_SYMBOL_NS(bmp380_chip_info, IIO_BMP280); @@ -1605,11 +1612,11 @@ int bmp280_common_probe(struct device *dev, return -EINVAL; } - /* BMP3xx requires soft-reset as part of initialization */ - if (chip_id == BMP380_CHIP_ID) { - ret = bmp380_cmd(data, BMP380_CMD_SOFT_RESET); - if (ret < 0) - return ret; + if (data->chip_info->preinit) { + ret = data->chip_info->preinit(data); + if (ret) + return dev_err_probe(data->dev, ret, + "error running preinit tasks\n"); } ret = data->chip_info->chip_config(data); diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index 387723fd0772..be17104ef0a2 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -345,6 +345,7 @@ struct bmp280_chip_info { int (*read_press)(struct bmp280_data *, int *, int *); int (*read_humid)(struct bmp280_data *, int *, int *); int (*read_calib)(struct bmp280_data *); + int (*preinit)(struct bmp280_data *); }; /* Chip infos for each variant */ -- GitLab From 4d545f9649253a7defda89b44a6a2a2b1b377d9d Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 17:58:01 +0100 Subject: [PATCH 0269/5631] iio: pressure: bmp280: Make read calibration callback optional Newer models do not require read the calibration parameters and apply the compensation algorithms in the sensor. Suggested-by: Jonathan Cameron Signed-off-by: Angel Iglesias Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/bb1b95ab3f4e71d3c76543370325c5c9aaa07add.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 6467034b1d3e..22addaaa5393 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1631,10 +1631,12 @@ int bmp280_common_probe(struct device *dev, * time once. They will not change. */ - ret = data->chip_info->read_calib(data); - if (ret < 0) - return dev_err_probe(data->dev, ret, - "failed to read calibration coefficients\n"); + if (data->chip_info->read_calib) { + ret = data->chip_info->read_calib(data); + if (ret < 0) + return dev_err_probe(data->dev, ret, + "failed to read calibration coefficients\n"); + } /* * Attempt to grab an optional EOC IRQ - only the BMP085 has this -- GitLab From 42cde8808573b44e395ee8b3e22f05104afa2e74 Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 18:03:03 +0100 Subject: [PATCH 0270/5631] iio: pressure: Kconfig: Delete misleading I2C reference on bmp280 title Title entry for BMP280 called the driver an I2C implementation, when the driver supports both I2C and SPI. Signed-off-by: Angel Iglesias Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/d26fe292164ca80685f080101122b5beb564d7db.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig index c9453389e4f7..cec4b429cd64 100644 --- a/drivers/iio/pressure/Kconfig +++ b/drivers/iio/pressure/Kconfig @@ -17,7 +17,7 @@ config ABP060MG will be called abp060mg. config BMP280 - tristate "Bosch Sensortec BMP180/BMP280/BMP380 pressure sensor I2C driver" + tristate "Bosch Sensortec BMP180/BMP280/BMP380 pressure sensor driver" depends on (I2C || SPI_MASTER) select REGMAP select BMP280_I2C if (I2C) -- GitLab From 597dfb2af052f175cdd5caa7b62095c7de1ba29e Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 18:03:04 +0100 Subject: [PATCH 0271/5631] iio: pressure: bmp280: Add support for new sensor BMP580 Adds compatibility with the new sensor generation, the BMP580. The measurement and initialization codepaths are adapted from the device datasheet and the repository from manufacturer at https://github.com/boschsensortec/BMP5-Sensor-API. Signed-off-by: Angel Iglesias Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/f899fceec9b48bc173bd4b7555f0a237fa32d520.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/Kconfig | 6 +- drivers/iio/pressure/bmp280-core.c | 344 ++++++++++++++++++++++++++- drivers/iio/pressure/bmp280-i2c.c | 2 + drivers/iio/pressure/bmp280-regmap.c | 60 +++++ drivers/iio/pressure/bmp280-spi.c | 2 + drivers/iio/pressure/bmp280.h | 107 ++++++++- 6 files changed, 509 insertions(+), 12 deletions(-) diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig index cec4b429cd64..02b97e89de50 100644 --- a/drivers/iio/pressure/Kconfig +++ b/drivers/iio/pressure/Kconfig @@ -17,14 +17,14 @@ config ABP060MG will be called abp060mg. config BMP280 - tristate "Bosch Sensortec BMP180/BMP280/BMP380 pressure sensor driver" + tristate "Bosch Sensortec BMP180/BMP280/BMP380/BMP580 pressure sensor driver" depends on (I2C || SPI_MASTER) select REGMAP select BMP280_I2C if (I2C) select BMP280_SPI if (SPI_MASTER) help - Say yes here to build support for Bosch Sensortec BMP180, BMP280 and - BMP380 pressure and temperature sensors. Also supports the BME280 with + Say yes here to build support for Bosch Sensortec BMP180, BMP280, BMP380 + and BMP580 pressure and temperature sensors. Also supports the BME280 with an additional humidity sensor channel. To compile this driver as a module, choose M here: the core module diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 22addaaa5393..a7d26d81ec08 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -13,6 +13,7 @@ * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp280-ds001.pdf * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bme280-ds002.pdf * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp388-ds001.pdf + * https://www.bosch-sensortec.com/media/boschsensortec/downloads/datasheets/bst-bmp581-ds004.pdf * * Notice: * The link to the bmp180 datasheet points to an outdated version missing these changes: @@ -71,6 +72,41 @@ enum bmp380_odr { BMP380_ODR_0_0015HZ, }; +enum bmp580_odr { + BMP580_ODR_240HZ, + BMP580_ODR_218HZ, + BMP580_ODR_199HZ, + BMP580_ODR_179HZ, + BMP580_ODR_160HZ, + BMP580_ODR_149HZ, + BMP580_ODR_140HZ, + BMP580_ODR_129HZ, + BMP580_ODR_120HZ, + BMP580_ODR_110HZ, + BMP580_ODR_100HZ, + BMP580_ODR_89HZ, + BMP580_ODR_80HZ, + BMP580_ODR_70HZ, + BMP580_ODR_60HZ, + BMP580_ODR_50HZ, + BMP580_ODR_45HZ, + BMP580_ODR_40HZ, + BMP580_ODR_35HZ, + BMP580_ODR_30HZ, + BMP580_ODR_25HZ, + BMP580_ODR_20HZ, + BMP580_ODR_15HZ, + BMP580_ODR_10HZ, + BMP580_ODR_5HZ, + BMP580_ODR_4HZ, + BMP580_ODR_3HZ, + BMP580_ODR_2HZ, + BMP580_ODR_1HZ, + BMP580_ODR_0_5HZ, + BMP580_ODR_0_25HZ, + BMP580_ODR_0_125HZ, +}; + /* * These enums are used for indexing into the array of compensation * parameters for BMP280. @@ -326,7 +362,7 @@ static u32 bmp280_compensate_press(struct bmp280_data *data, } static int bmp280_read_temp(struct bmp280_data *data, - int *val) + int *val, int *val2) { s32 adc_temp, comp_temp; int ret; @@ -366,7 +402,7 @@ static int bmp280_read_press(struct bmp280_data *data, int ret; /* Read and compensate temperature so we get a reading of t_fine. */ - ret = bmp280_read_temp(data, NULL); + ret = bmp280_read_temp(data, NULL, NULL); if (ret < 0) return ret; @@ -398,7 +434,7 @@ static int bmp280_read_humid(struct bmp280_data *data, int *val, int *val2) int ret; /* Read and compensate temperature so we get a reading of t_fine. */ - ret = bmp280_read_temp(data, NULL); + ret = bmp280_read_temp(data, NULL, NULL); if (ret < 0) return ret; @@ -442,7 +478,7 @@ static int bmp280_read_raw(struct iio_dev *indio_dev, ret = data->chip_info->read_press(data, val, val2); break; case IIO_TEMP: - ret = data->chip_info->read_temp(data, val); + ret = data->chip_info->read_temp(data, val, val2); break; default: ret = -EINVAL; @@ -954,7 +990,7 @@ static u32 bmp380_compensate_press(struct bmp280_data *data, u32 adc_press) return comp_press; } -static int bmp380_read_temp(struct bmp280_data *data, int *val) +static int bmp380_read_temp(struct bmp280_data *data, int *val, int *val2) { s32 comp_temp; u32 adc_temp; @@ -994,7 +1030,7 @@ static int bmp380_read_press(struct bmp280_data *data, int *val, int *val2) int ret; /* Read and compensate for temperature so we get a reading of t_fine */ - ret = bmp380_read_temp(data, NULL); + ret = bmp380_read_temp(data, NULL, NULL); if (ret) return ret; @@ -1216,6 +1252,298 @@ const struct bmp280_chip_info bmp380_chip_info = { }; EXPORT_SYMBOL_NS(bmp380_chip_info, IIO_BMP280); +static int bmp580_soft_reset(struct bmp280_data *data) +{ + unsigned int reg; + int ret; + + ret = regmap_write(data->regmap, BMP580_REG_CMD, BMP580_CMD_SOFT_RESET); + if (ret) { + dev_err(data->dev, "failed to send reset command to device\n"); + return ret; + } + usleep_range(2000, 2500); + + /* Dummy read of chip_id */ + ret = regmap_read(data->regmap, BMP580_REG_CHIP_ID, ®); + if (ret) { + dev_err(data->dev, "failed to reestablish comms after reset\n"); + return ret; + } + + ret = regmap_read(data->regmap, BMP580_REG_INT_STATUS, ®); + if (ret) { + dev_err(data->dev, "error reading interrupt status register\n"); + return ret; + } + if (!(reg & BMP580_INT_STATUS_POR_MASK)) { + dev_err(data->dev, "error resetting sensor\n"); + return -EINVAL; + } + + return 0; +} + +/* + * Contrary to previous sensors families, compensation algorithm is builtin. + * We are only required to read the register raw data and adapt the ranges + * for what is expected on IIO ABI. + */ + +static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2) +{ + s32 raw_temp; + int ret; + + ret = regmap_bulk_read(data->regmap, BMP580_REG_TEMP_XLSB, data->buf, + sizeof(data->buf)); + if (ret) { + dev_err(data->dev, "failed to read temperature\n"); + return ret; + } + + raw_temp = get_unaligned_le24(data->buf); + if (raw_temp == BMP580_TEMP_SKIPPED) { + dev_err(data->dev, "reading temperature skipped\n"); + return -EIO; + } + + /* + * Temperature is returned in Celsius degrees in fractional + * form down 2^16. We reescale by x1000 to return milli Celsius + * to respect IIO ABI. + */ + *val = raw_temp * 1000; + *val2 = 16; + return IIO_VAL_FRACTIONAL_LOG2; +} + +static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2) +{ + u32 raw_press; + int ret; + + ret = regmap_bulk_read(data->regmap, BMP580_REG_PRESS_XLSB, data->buf, + sizeof(data->buf)); + if (ret) { + dev_err(data->dev, "failed to read pressure\n"); + return ret; + } + + raw_press = get_unaligned_le24(data->buf); + if (raw_press == BMP580_PRESS_SKIPPED) { + dev_err(data->dev, "reading pressure skipped\n"); + return -EIO; + } + /* + * Pressure is returned in Pascals in fractional form down 2^16. + * We reescale /1000 to convert to kilopascal to respect IIO ABI. + */ + *val = raw_press; + *val2 = 64000; /* 2^6 * 1000 */ + return IIO_VAL_FRACTIONAL; +} + +static const int bmp580_odr_table[][2] = { + [BMP580_ODR_240HZ] = {240, 0}, + [BMP580_ODR_218HZ] = {218, 0}, + [BMP580_ODR_199HZ] = {199, 0}, + [BMP580_ODR_179HZ] = {179, 0}, + [BMP580_ODR_160HZ] = {160, 0}, + [BMP580_ODR_149HZ] = {149, 0}, + [BMP580_ODR_140HZ] = {140, 0}, + [BMP580_ODR_129HZ] = {129, 0}, + [BMP580_ODR_120HZ] = {120, 0}, + [BMP580_ODR_110HZ] = {110, 0}, + [BMP580_ODR_100HZ] = {100, 0}, + [BMP580_ODR_89HZ] = {89, 0}, + [BMP580_ODR_80HZ] = {80, 0}, + [BMP580_ODR_70HZ] = {70, 0}, + [BMP580_ODR_60HZ] = {60, 0}, + [BMP580_ODR_50HZ] = {50, 0}, + [BMP580_ODR_45HZ] = {45, 0}, + [BMP580_ODR_40HZ] = {40, 0}, + [BMP580_ODR_35HZ] = {35, 0}, + [BMP580_ODR_30HZ] = {30, 0}, + [BMP580_ODR_25HZ] = {25, 0}, + [BMP580_ODR_20HZ] = {20, 0}, + [BMP580_ODR_15HZ] = {15, 0}, + [BMP580_ODR_10HZ] = {10, 0}, + [BMP580_ODR_5HZ] = {5, 0}, + [BMP580_ODR_4HZ] = {4, 0}, + [BMP580_ODR_3HZ] = {3, 0}, + [BMP580_ODR_2HZ] = {2, 0}, + [BMP580_ODR_1HZ] = {1, 0}, + [BMP580_ODR_0_5HZ] = {0, 500000}, + [BMP580_ODR_0_25HZ] = {0, 250000}, + [BMP580_ODR_0_125HZ] = {0, 125000}, +}; + +static int bmp580_preinit(struct bmp280_data *data) +{ + unsigned int reg; + int ret; + + /* Issue soft-reset command */ + ret = bmp580_soft_reset(data); + if (ret) + return ret; + + /* Post powerup sequence */ + ret = regmap_read(data->regmap, BMP580_REG_CHIP_ID, ®); + if (ret) + return ret; + + /* Print warn message if we don't know the chip id */ + if (reg != BMP580_CHIP_ID && reg != BMP580_CHIP_ID_ALT) + dev_warn(data->dev, "preinit: unexpected chip_id\n"); + + ret = regmap_read(data->regmap, BMP580_REG_STATUS, ®); + if (ret) + return ret; + + /* Check nvm status */ + if (!(reg & BMP580_STATUS_NVM_RDY_MASK) || (reg & BMP580_STATUS_NVM_ERR_MASK)) { + dev_err(data->dev, "preinit: nvm error on powerup sequence\n"); + return -EIO; + } + + return 0; +} + +static int bmp580_chip_config(struct bmp280_data *data) +{ + bool change = false, aux; + unsigned int tmp; + u8 reg_val; + int ret; + + /* Sets sensor in standby mode */ + ret = regmap_update_bits(data->regmap, BMP580_REG_ODR_CONFIG, + BMP580_MODE_MASK | BMP580_ODR_DEEPSLEEP_DIS, + BMP580_ODR_DEEPSLEEP_DIS | + FIELD_PREP(BMP580_MODE_MASK, BMP580_MODE_SLEEP)); + if (ret) { + dev_err(data->dev, "failed to change sensor to standby mode\n"); + return ret; + } + /* From datasheet's table 4: electrical characteristics */ + usleep_range(2500, 3000); + + /* Set default DSP mode settings */ + reg_val = FIELD_PREP(BMP580_DSP_COMP_MASK, BMP580_DSP_PRESS_TEMP_COMP_EN) | + BMP580_DSP_SHDW_IIR_TEMP_EN | BMP580_DSP_SHDW_IIR_PRESS_EN; + + ret = regmap_update_bits(data->regmap, BMP580_REG_DSP_CONFIG, + BMP580_DSP_COMP_MASK | + BMP580_DSP_SHDW_IIR_TEMP_EN | + BMP580_DSP_SHDW_IIR_PRESS_EN, reg_val); + + /* Configure oversampling */ + reg_val = FIELD_PREP(BMP580_OSR_TEMP_MASK, data->oversampling_temp) | + FIELD_PREP(BMP580_OSR_PRESS_MASK, data->oversampling_press) | + BMP580_OSR_PRESS_EN; + + ret = regmap_update_bits_check(data->regmap, BMP580_REG_OSR_CONFIG, + BMP580_OSR_TEMP_MASK | BMP580_OSR_PRESS_MASK | + BMP580_OSR_PRESS_EN, + reg_val, &aux); + if (ret) { + dev_err(data->dev, "failed to write oversampling register\n"); + return ret; + } + change = change || aux; + + /* Configure output data rate */ + ret = regmap_update_bits_check(data->regmap, BMP580_REG_ODR_CONFIG, BMP580_ODR_MASK, + FIELD_PREP(BMP580_ODR_MASK, data->sampling_freq), + &aux); + if (ret) { + dev_err(data->dev, "failed to write ODR configuration register\n"); + return ret; + } + change = change || aux; + + /* Set filter data */ + reg_val = FIELD_PREP(BMP580_DSP_IIR_PRESS_MASK, data->iir_filter_coeff) | + FIELD_PREP(BMP580_DSP_IIR_TEMP_MASK, data->iir_filter_coeff); + + ret = regmap_update_bits_check(data->regmap, BMP580_REG_DSP_IIR, + BMP580_DSP_IIR_PRESS_MASK | + BMP580_DSP_IIR_TEMP_MASK, + reg_val, &aux); + if (ret) { + dev_err(data->dev, "failed to write config register\n"); + return ret; + } + change = change || aux; + + /* Restore sensor to normal operation mode */ + ret = regmap_write_bits(data->regmap, BMP580_REG_ODR_CONFIG, + BMP580_MODE_MASK, + FIELD_PREP(BMP580_MODE_MASK, BMP580_MODE_NORMAL)); + if (ret) { + dev_err(data->dev, "failed to set normal mode\n"); + return ret; + } + /* From datasheet's table 4: electrical characteristics */ + usleep_range(3000, 3500); + + if (change) { + /* + * Check if ODR and OSR settings are valid or we are + * operating in a degraded mode. + */ + ret = regmap_read(data->regmap, BMP580_REG_EFF_OSR, &tmp); + if (ret) { + dev_err(data->dev, "error reading effective OSR register\n"); + return ret; + } + if (!(tmp & BMP580_EFF_OSR_VALID_ODR)) { + dev_warn(data->dev, "OSR and ODR incompatible settings detected\n"); + /* Set current OSR settings from data on effective OSR */ + data->oversampling_temp = FIELD_GET(BMP580_EFF_OSR_TEMP_MASK, tmp); + data->oversampling_press = FIELD_GET(BMP580_EFF_OSR_PRESS_MASK, tmp); + return -EINVAL; + } + } + + return 0; +} + +static const int bmp580_oversampling_avail[] = { 1, 2, 4, 8, 16, 32, 64, 128 }; + +const struct bmp280_chip_info bmp580_chip_info = { + .id_reg = BMP580_REG_CHIP_ID, + .chip_id = BMP580_CHIP_ID, + .regmap_config = &bmp580_regmap_config, + .start_up_time = 2000, + .channels = bmp380_channels, + .num_channels = 2, + + .oversampling_temp_avail = bmp580_oversampling_avail, + .num_oversampling_temp_avail = ARRAY_SIZE(bmp580_oversampling_avail), + .oversampling_temp_default = ilog2(1), + + .oversampling_press_avail = bmp580_oversampling_avail, + .num_oversampling_press_avail = ARRAY_SIZE(bmp580_oversampling_avail), + .oversampling_press_default = ilog2(4), + + .sampling_freq_avail = bmp580_odr_table, + .num_sampling_freq_avail = ARRAY_SIZE(bmp580_odr_table) * 2, + .sampling_freq_default = BMP580_ODR_50HZ, + + .iir_filter_coeffs_avail = bmp380_iir_filter_coeffs_avail, + .num_iir_filter_coeffs_avail = ARRAY_SIZE(bmp380_iir_filter_coeffs_avail), + .iir_filter_coeff_default = 2, + + .chip_config = bmp580_chip_config, + .read_temp = bmp580_read_temp, + .read_press = bmp580_read_press, + .preinit = bmp580_preinit, +}; +EXPORT_SYMBOL_NS(bmp580_chip_info, IIO_BMP280); + static int bmp180_measure(struct bmp280_data *data, u8 ctrl_meas) { const int conversion_time_max[] = { 4500, 7500, 13500, 25500 }; @@ -1336,7 +1664,7 @@ static s32 bmp180_compensate_temp(struct bmp280_data *data, s32 adc_temp) return (data->t_fine + 8) >> 4; } -static int bmp180_read_temp(struct bmp280_data *data, int *val) +static int bmp180_read_temp(struct bmp280_data *data, int *val, int *val2) { s32 adc_temp, comp_temp; int ret; @@ -1424,7 +1752,7 @@ static int bmp180_read_press(struct bmp280_data *data, int ret; /* Read and compensate temperature so we get a reading of t_fine. */ - ret = bmp180_read_temp(data, NULL); + ret = bmp180_read_temp(data, NULL, NULL); if (ret) return ret; diff --git a/drivers/iio/pressure/bmp280-i2c.c b/drivers/iio/pressure/bmp280-i2c.c index 5f908e2c9826..567b945e6427 100644 --- a/drivers/iio/pressure/bmp280-i2c.c +++ b/drivers/iio/pressure/bmp280-i2c.c @@ -34,6 +34,7 @@ static const struct of_device_id bmp280_of_i2c_match[] = { { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, { .compatible = "bosch,bme280", .data = &bme280_chip_info }, { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, + { .compatible = "bosch,bmp580", .data = &bmp580_chip_info }, { }, }; MODULE_DEVICE_TABLE(of, bmp280_of_i2c_match); @@ -44,6 +45,7 @@ static const struct i2c_device_id bmp280_i2c_id[] = { {"bmp280", (kernel_ulong_t)&bmp280_chip_info }, {"bme280", (kernel_ulong_t)&bme280_chip_info }, {"bmp380", (kernel_ulong_t)&bmp380_chip_info }, + {"bmp580", (kernel_ulong_t)&bmp580_chip_info }, { }, }; MODULE_DEVICE_TABLE(i2c, bmp280_i2c_id); diff --git a/drivers/iio/pressure/bmp280-regmap.c b/drivers/iio/pressure/bmp280-regmap.c index c98c67970265..3ee56720428c 100644 --- a/drivers/iio/pressure/bmp280-regmap.c +++ b/drivers/iio/pressure/bmp280-regmap.c @@ -115,6 +115,54 @@ static bool bmp380_is_volatile_reg(struct device *dev, unsigned int reg) } } +static bool bmp580_is_writeable_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case BMP580_REG_NVM_DATA_MSB: + case BMP580_REG_NVM_DATA_LSB: + case BMP580_REG_NVM_ADDR: + case BMP580_REG_ODR_CONFIG: + case BMP580_REG_OSR_CONFIG: + case BMP580_REG_INT_SOURCE: + case BMP580_REG_INT_CONFIG: + case BMP580_REG_OOR_THR_MSB: + case BMP580_REG_OOR_THR_LSB: + case BMP580_REG_OOR_CONFIG: + case BMP580_REG_OOR_RANGE: + case BMP580_REG_IF_CONFIG: + case BMP580_REG_FIFO_CONFIG: + case BMP580_REG_FIFO_SEL: + case BMP580_REG_DSP_CONFIG: + case BMP580_REG_DSP_IIR: + case BMP580_REG_CMD: + return true; + default: + return false; + } +} + +static bool bmp580_is_volatile_reg(struct device *dev, unsigned int reg) +{ + switch (reg) { + case BMP580_REG_NVM_DATA_MSB: + case BMP580_REG_NVM_DATA_LSB: + case BMP580_REG_FIFO_COUNT: + case BMP580_REG_INT_STATUS: + case BMP580_REG_PRESS_XLSB: + case BMP580_REG_PRESS_LSB: + case BMP580_REG_PRESS_MSB: + case BMP580_REG_FIFO_DATA: + case BMP580_REG_TEMP_XLSB: + case BMP580_REG_TEMP_LSB: + case BMP580_REG_TEMP_MSB: + case BMP580_REG_EFF_OSR: + case BMP580_REG_STATUS: + return true; + default: + return false; + } +} + const struct regmap_config bmp280_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -138,3 +186,15 @@ const struct regmap_config bmp380_regmap_config = { .volatile_reg = bmp380_is_volatile_reg, }; EXPORT_SYMBOL_NS(bmp380_regmap_config, IIO_BMP280); + +const struct regmap_config bmp580_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + + .max_register = BMP580_REG_CMD, + .cache_type = REGCACHE_RBTREE, + + .writeable_reg = bmp580_is_writeable_reg, + .volatile_reg = bmp580_is_volatile_reg, +}; +EXPORT_SYMBOL_NS(bmp580_regmap_config, IIO_BMP280); diff --git a/drivers/iio/pressure/bmp280-spi.c b/drivers/iio/pressure/bmp280-spi.c index d5a224b95185..1dff9bb7c4e9 100644 --- a/drivers/iio/pressure/bmp280-spi.c +++ b/drivers/iio/pressure/bmp280-spi.c @@ -85,6 +85,7 @@ static const struct of_device_id bmp280_of_spi_match[] = { { .compatible = "bosch,bmp280", .data = &bmp280_chip_info }, { .compatible = "bosch,bme280", .data = &bmp280_chip_info }, { .compatible = "bosch,bmp380", .data = &bmp380_chip_info }, + { .compatible = "bosch,bmp580", .data = &bmp580_chip_info }, { }, }; MODULE_DEVICE_TABLE(of, bmp280_of_spi_match); @@ -95,6 +96,7 @@ static const struct spi_device_id bmp280_spi_id[] = { { "bmp280", (kernel_ulong_t)&bmp280_chip_info }, { "bme280", (kernel_ulong_t)&bmp280_chip_info }, { "bmp380", (kernel_ulong_t)&bmp380_chip_info }, + { "bmp580", (kernel_ulong_t)&bmp580_chip_info }, { } }; MODULE_DEVICE_TABLE(spi, bmp280_spi_id); diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index be17104ef0a2..cd4c5be36ed7 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -6,6 +6,107 @@ #include +/* BMP580 specific registers */ +#define BMP580_REG_CMD 0x7E +#define BMP580_REG_EFF_OSR 0x38 +#define BMP580_REG_ODR_CONFIG 0x37 +#define BMP580_REG_OSR_CONFIG 0x36 +#define BMP580_REG_IF_CONFIG 0x13 +#define BMP580_REG_REV_ID 0x02 +#define BMP580_REG_CHIP_ID 0x01 +/* OOR allows to configure a pressure alarm */ +#define BMP580_REG_OOR_CONFIG 0x35 +#define BMP580_REG_OOR_RANGE 0x34 +#define BMP580_REG_OOR_THR_MSB 0x33 +#define BMP580_REG_OOR_THR_LSB 0x32 +/* DSP registers (IIR filters) */ +#define BMP580_REG_DSP_IIR 0x31 +#define BMP580_REG_DSP_CONFIG 0x30 +/* NVM access registers */ +#define BMP580_REG_NVM_DATA_MSB 0x2D +#define BMP580_REG_NVM_DATA_LSB 0x2C +#define BMP580_REG_NVM_ADDR 0x2B +/* Status registers */ +#define BMP580_REG_STATUS 0x28 +#define BMP580_REG_INT_STATUS 0x27 +#define BMP580_REG_CHIP_STATUS 0x11 +/* Data registers */ +#define BMP580_REG_FIFO_DATA 0x29 +#define BMP580_REG_PRESS_MSB 0x22 +#define BMP580_REG_PRESS_LSB 0x21 +#define BMP580_REG_PRESS_XLSB 0x20 +#define BMP580_REG_TEMP_MSB 0x1F +#define BMP580_REG_TEMP_LSB 0x1E +#define BMP580_REG_TEMP_XLSB 0x1D +/* FIFO config registers */ +#define BMP580_REG_FIFO_SEL 0x18 +#define BMP580_REG_FIFO_COUNT 0x17 +#define BMP580_REG_FIFO_CONFIG 0x16 +/* Interruptions config registers */ +#define BMP580_REG_INT_SOURCE 0x15 +#define BMP580_REG_INT_CONFIG 0x14 + +#define BMP580_CMD_NOOP 0x00 +#define BMP580_CMD_EXTMODE_SEQ_0 0x73 +#define BMP580_CMD_EXTMODE_SEQ_1 0xB4 +#define BMP580_CMD_EXTMODE_SEQ_2 0x69 +#define BMP580_CMD_NVM_OP_SEQ_0 0x5D +#define BMP580_CMD_NVM_READ_SEQ_1 0xA5 +#define BMP580_CMD_NVM_WRITE_SEQ_1 0xA0 +#define BMP580_CMD_SOFT_RESET 0xB6 + +#define BMP580_INT_STATUS_POR_MASK BIT(4) + +#define BMP580_STATUS_CORE_RDY_MASK BIT(0) +#define BMP580_STATUS_NVM_RDY_MASK BIT(1) +#define BMP580_STATUS_NVM_ERR_MASK BIT(2) +#define BMP580_STATUS_NVM_CMD_ERR_MASK BIT(3) + +#define BMP580_OSR_PRESS_MASK GENMASK(5, 3) +#define BMP580_OSR_TEMP_MASK GENMASK(2, 0) +#define BMP580_OSR_PRESS_EN BIT(6) +#define BMP580_EFF_OSR_PRESS_MASK GENMASK(5, 3) +#define BMP580_EFF_OSR_TEMP_MASK GENMASK(2, 0) +#define BMP580_EFF_OSR_VALID_ODR BIT(7) + +#define BMP580_ODR_MASK GENMASK(6, 2) +#define BMP580_MODE_MASK GENMASK(1, 0) +#define BMP580_MODE_SLEEP 0 +#define BMP580_MODE_NORMAL 1 +#define BMP580_MODE_FORCED 2 +#define BMP580_MODE_CONTINOUS 3 +#define BMP580_ODR_DEEPSLEEP_DIS BIT(7) + +#define BMP580_DSP_COMP_MASK GENMASK(1, 0) +#define BMP580_DSP_COMP_DIS 0 +#define BMP580_DSP_TEMP_COMP_EN 1 +/* + * In section 7.27 of datasheet, modes 2 and 3 are technically the same. + * Pressure compensation means also enabling temperature compensation + */ +#define BMP580_DSP_PRESS_COMP_EN 2 +#define BMP580_DSP_PRESS_TEMP_COMP_EN 3 +#define BMP580_DSP_IIR_FORCED_FLUSH BIT(2) +#define BMP580_DSP_SHDW_IIR_TEMP_EN BIT(3) +#define BMP580_DSP_FIFO_IIR_TEMP_EN BIT(4) +#define BMP580_DSP_SHDW_IIR_PRESS_EN BIT(5) +#define BMP580_DSP_FIFO_IIR_PRESS_EN BIT(6) +#define BMP580_DSP_OOR_IIR_PRESS_EN BIT(7) + +#define BMP580_DSP_IIR_PRESS_MASK GENMASK(5, 3) +#define BMP580_DSP_IIR_TEMP_MASK GENMASK(2, 0) +#define BMP580_FILTER_OFF 0 +#define BMP580_FILTER_1X 1 +#define BMP580_FILTER_3X 2 +#define BMP580_FILTER_7X 3 +#define BMP580_FILTER_15X 4 +#define BMP580_FILTER_31X 5 +#define BMP580_FILTER_63X 6 +#define BMP580_FILTER_127X 7 + +#define BMP580_TEMP_SKIPPED 0x7f7f7f +#define BMP580_PRESS_SKIPPED 0x7f7f7f + /* BMP380 specific registers */ #define BMP380_REG_CMD 0x7E #define BMP380_REG_CONFIG 0x1F @@ -184,6 +285,8 @@ #define BMP280_REG_ID 0xD0 #define BMP380_CHIP_ID 0x50 +#define BMP580_CHIP_ID 0x50 +#define BMP580_CHIP_ID_ALT 0x51 #define BMP180_CHIP_ID 0x55 #define BMP280_CHIP_ID 0x58 #define BME280_CHIP_ID 0x60 @@ -341,7 +444,7 @@ struct bmp280_chip_info { int sampling_freq_default; int (*chip_config)(struct bmp280_data *); - int (*read_temp)(struct bmp280_data *, int *); + int (*read_temp)(struct bmp280_data *, int *, int *); int (*read_press)(struct bmp280_data *, int *, int *); int (*read_humid)(struct bmp280_data *, int *, int *); int (*read_calib)(struct bmp280_data *); @@ -353,11 +456,13 @@ extern const struct bmp280_chip_info bmp180_chip_info; extern const struct bmp280_chip_info bmp280_chip_info; extern const struct bmp280_chip_info bme280_chip_info; extern const struct bmp280_chip_info bmp380_chip_info; +extern const struct bmp280_chip_info bmp580_chip_info; /* Regmap configurations */ extern const struct regmap_config bmp180_regmap_config; extern const struct regmap_config bmp280_regmap_config; extern const struct regmap_config bmp380_regmap_config; +extern const struct regmap_config bmp580_regmap_config; /* Probe called from different transports */ int bmp280_common_probe(struct device *dev, -- GitLab From 43cce95ca1396c9678c7ef8a5c065005c9fc1f11 Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 18:03:05 +0100 Subject: [PATCH 0272/5631] dt-bindings: iio: pressure: bmp085: Add BMP580 compatible string Add bosch,bmp580 to compatible string for the new family of sensors. This family includes the BMP580 and BMP581 sensors. The register map in this family presents significant departures from previous generations. Signed-off-by: Angel Iglesias Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/2510dccfd44e2225c5978bfdf4136f423326c31a.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- Documentation/devicetree/bindings/iio/pressure/bmp085.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml index 63885af6a74b..6fda887ee9d4 100644 --- a/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml +++ b/Documentation/devicetree/bindings/iio/pressure/bmp085.yaml @@ -17,6 +17,7 @@ description: | https://www.bosch-sensortec.com/bst/products/all_products/bmp280 https://www.bosch-sensortec.com/bst/products/all_products/bme280 https://www.bosch-sensortec.com/bst/products/all_products/bmp380 + https://www.bosch-sensortec.com/bst/products/all_products/bmp580 properties: compatible: @@ -26,6 +27,7 @@ properties: - bosch,bmp280 - bosch,bme280 - bosch,bmp380 + - bosch,bmp580 reg: maxItems: 1 -- GitLab From accb9d05df394c38db2a1bab416ee25d6078ca5c Mon Sep 17 00:00:00 2001 From: Angel Iglesias Date: Sun, 19 Feb 2023 18:03:06 +0100 Subject: [PATCH 0273/5631] iio: pressure: bmp280: Add nvmem operations for BMP580 The pressure sensor BMP580 contains a non-volatile memory that stores trimming and configuration params. That memory provides an programmable user range of three 2-byte words. Signed-off-by: Angel Iglesias Link: https://lore.kernel.org/r/f3f453d9b2c0f7820ca9c56e24e2165b6c39bb67.1676823250.git.ang.iglesiasg@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/pressure/bmp280-core.c | 210 ++++++++++++++++++++++++++++- drivers/iio/pressure/bmp280.h | 3 + 2 files changed, 212 insertions(+), 1 deletion(-) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index a7d26d81ec08..6089f3f9d8f4 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -1284,6 +1285,80 @@ static int bmp580_soft_reset(struct bmp280_data *data) return 0; } +/** + * bmp580_nvm_operation() - Helper function to commit NVM memory operations + * @data: sensor data struct + * @is_write: flag to signal write operation + */ +static int bmp580_nvm_operation(struct bmp280_data *data, bool is_write) +{ + unsigned long timeout, poll; + unsigned int reg; + int ret; + + /* Check NVM ready flag */ + ret = regmap_read(data->regmap, BMP580_REG_STATUS, ®); + if (ret) { + dev_err(data->dev, "failed to check nvm status\n"); + return ret; + } + if (!(reg & BMP580_STATUS_NVM_RDY_MASK)) { + dev_err(data->dev, "sensor's nvm is not ready\n"); + return -EIO; + } + + /* Start NVM operation sequence */ + ret = regmap_write(data->regmap, BMP580_REG_CMD, BMP580_CMD_NVM_OP_SEQ_0); + if (ret) { + dev_err(data->dev, "failed to send nvm operation's first sequence\n"); + return ret; + } + if (is_write) { + /* Send NVM write sequence */ + ret = regmap_write(data->regmap, BMP580_REG_CMD, + BMP580_CMD_NVM_WRITE_SEQ_1); + if (ret) { + dev_err(data->dev, "failed to send nvm write sequence\n"); + return ret; + } + /* Datasheet says on 4.8.1.2 it takes approximately 10ms */ + poll = 2000; + timeout = 12000; + } else { + /* Send NVM read sequence */ + ret = regmap_write(data->regmap, BMP580_REG_CMD, + BMP580_CMD_NVM_READ_SEQ_1); + if (ret) { + dev_err(data->dev, "failed to send nvm read sequence\n"); + return ret; + } + /* Datasheet says on 4.8.1.1 it takes approximately 200us */ + poll = 50; + timeout = 400; + } + if (ret) { + dev_err(data->dev, "failed to write command sequence\n"); + return -EIO; + } + + /* Wait until NVM is ready again */ + ret = regmap_read_poll_timeout(data->regmap, BMP580_REG_STATUS, reg, + (reg & BMP580_STATUS_NVM_RDY_MASK), + poll, timeout); + if (ret) { + dev_err(data->dev, "error checking nvm operation status\n"); + return ret; + } + + /* Check NVM error flags */ + if ((reg & BMP580_STATUS_NVM_ERR_MASK) || (reg & BMP580_STATUS_NVM_CMD_ERR_MASK)) { + dev_err(data->dev, "error processing nvm operation\n"); + return -EIO; + } + + return 0; +} + /* * Contrary to previous sensors families, compensation algorithm is builtin. * We are only required to read the register raw data and adapt the ranges @@ -1379,8 +1454,140 @@ static const int bmp580_odr_table[][2] = { [BMP580_ODR_0_125HZ] = {0, 125000}, }; +static const int bmp580_nvmem_addrs[] = { 0x20, 0x21, 0x22 }; + +static int bmp580_nvmem_read(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + struct bmp280_data *data = priv; + u16 *dst = val; + int ret, addr; + + pm_runtime_get_sync(data->dev); + mutex_lock(&data->lock); + + /* Set sensor in standby mode */ + ret = regmap_update_bits(data->regmap, BMP580_REG_ODR_CONFIG, + BMP580_MODE_MASK | BMP580_ODR_DEEPSLEEP_DIS, + BMP580_ODR_DEEPSLEEP_DIS | + FIELD_PREP(BMP580_MODE_MASK, BMP580_MODE_SLEEP)); + if (ret) { + dev_err(data->dev, "failed to change sensor to standby mode\n"); + goto exit; + } + /* Wait standby transition time */ + usleep_range(2500, 3000); + + while (bytes >= sizeof(*dst)) { + addr = bmp580_nvmem_addrs[offset / sizeof(*dst)]; + + ret = regmap_write(data->regmap, BMP580_REG_NVM_ADDR, + FIELD_PREP(BMP580_NVM_ROW_ADDR_MASK, addr)); + if (ret) { + dev_err(data->dev, "error writing nvm address\n"); + goto exit; + } + + ret = bmp580_nvm_operation(data, false); + if (ret) + goto exit; + + ret = regmap_bulk_read(data->regmap, BMP580_REG_NVM_DATA_LSB, &data->le16, + sizeof(data->le16)); + if (ret) { + dev_err(data->dev, "error reading nvm data regs\n"); + goto exit; + } + + *dst++ = le16_to_cpu(data->le16); + bytes -= sizeof(*dst); + offset += sizeof(*dst); + } +exit: + /* Restore chip config */ + data->chip_info->chip_config(data); + mutex_unlock(&data->lock); + pm_runtime_mark_last_busy(data->dev); + pm_runtime_put_autosuspend(data->dev); + return ret; +} + +static int bmp580_nvmem_write(void *priv, unsigned int offset, void *val, + size_t bytes) +{ + struct bmp280_data *data = priv; + u16 *buf = val; + int ret, addr; + + pm_runtime_get_sync(data->dev); + mutex_lock(&data->lock); + + /* Set sensor in standby mode */ + ret = regmap_update_bits(data->regmap, BMP580_REG_ODR_CONFIG, + BMP580_MODE_MASK | BMP580_ODR_DEEPSLEEP_DIS, + BMP580_ODR_DEEPSLEEP_DIS | + FIELD_PREP(BMP580_MODE_MASK, BMP580_MODE_SLEEP)); + if (ret) { + dev_err(data->dev, "failed to change sensor to standby mode\n"); + goto exit; + } + /* Wait standby transition time */ + usleep_range(2500, 3000); + + while (bytes >= sizeof(*buf)) { + addr = bmp580_nvmem_addrs[offset / sizeof(*buf)]; + + ret = regmap_write(data->regmap, BMP580_REG_NVM_ADDR, BMP580_NVM_PROG_EN | + FIELD_PREP(BMP580_NVM_ROW_ADDR_MASK, addr)); + if (ret) { + dev_err(data->dev, "error writing nvm address\n"); + goto exit; + } + data->le16 = cpu_to_le16(*buf++); + + ret = regmap_bulk_write(data->regmap, BMP580_REG_NVM_DATA_LSB, &data->le16, + sizeof(data->le16)); + if (ret) { + dev_err(data->dev, "error writing LSB NVM data regs\n"); + goto exit; + } + + ret = bmp580_nvm_operation(data, true); + if (ret) + goto exit; + + /* Disable programming mode bit */ + ret = regmap_update_bits(data->regmap, BMP580_REG_NVM_ADDR, + BMP580_NVM_PROG_EN, 0); + if (ret) { + dev_err(data->dev, "error resetting nvm write\n"); + goto exit; + } + + bytes -= sizeof(*buf); + offset += sizeof(*buf); + } +exit: + /* Restore chip config */ + data->chip_info->chip_config(data); + mutex_unlock(&data->lock); + pm_runtime_mark_last_busy(data->dev); + pm_runtime_put_autosuspend(data->dev); + return ret; +} + static int bmp580_preinit(struct bmp280_data *data) { + struct nvmem_config config = { + .dev = data->dev, + .priv = data, + .name = "bmp580_nvmem", + .word_size = sizeof(u16), + .stride = sizeof(u16), + .size = 3 * sizeof(u16), + .reg_read = bmp580_nvmem_read, + .reg_write = bmp580_nvmem_write, + }; unsigned int reg; int ret; @@ -1408,7 +1615,8 @@ static int bmp580_preinit(struct bmp280_data *data) return -EIO; } - return 0; + /* Register nvmem device */ + return PTR_ERR_OR_ZERO(devm_nvmem_register(config.dev, &config)); } static int bmp580_chip_config(struct bmp280_data *data) diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index cd4c5be36ed7..5c0563ce7572 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -104,6 +104,9 @@ #define BMP580_FILTER_63X 6 #define BMP580_FILTER_127X 7 +#define BMP580_NVM_ROW_ADDR_MASK GENMASK(5, 0) +#define BMP580_NVM_PROG_EN BIT(6) + #define BMP580_TEMP_SKIPPED 0x7f7f7f #define BMP580_PRESS_SKIPPED 0x7f7f7f -- GitLab From db3c490503bee4d0611f9fc17fcd8cfe6fcdbcad Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 27 Feb 2023 12:14:56 +0100 Subject: [PATCH 0274/5631] iio: imu: st_lsm6dsx: discard samples during filters settling time During digital filters settling time the driver is expected to drop samples since they can be corrupted. Introduce the capability to drop a given number of samples according to the configured ODR. Add sample_to_discard for LSM6DSM-like sensors since new generation devices (e.g. LSM6DSO) support DRDY mask where corrupted samples are masked in hw with values greather than 0x7ffd so the driver can easily discard them. I have not added sample_to_discard support for LSM6DS3 or LSM6DS3H since I do not have any sample for testing at the moment. Reported-by: Philippe De Muyter Tested-by: Philippe De Muyter Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/21dcd94935c147ef9b1da4984b3da6264ee9609e.1677496295.git.lorenzo@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h | 11 ++++ .../iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c | 57 ++++++++++++++++--- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 18 ++++++ 3 files changed, 78 insertions(+), 8 deletions(-) diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h index 499fcf8875b4..8e119d78730b 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h @@ -137,6 +137,13 @@ struct st_lsm6dsx_odr_table_entry { int odr_len; }; +struct st_lsm6dsx_samples_to_discard { + struct { + u32 milli_hz; + u16 samples; + } val[ST_LSM6DSX_ODR_LIST_SIZE]; +}; + struct st_lsm6dsx_fs { u32 gain; u8 val; @@ -291,6 +298,7 @@ struct st_lsm6dsx_ext_dev_settings { * @irq_config: interrupts related registers. * @drdy_mask: register info for data-ready mask (addr + mask). * @odr_table: Hw sensors odr table (Hz + val). + * @samples_to_discard: Number of samples to discard for filters settling time. * @fs_table: Hw sensors gain table (gain + val). * @decimator: List of decimator register info (addr + mask). * @batch: List of FIFO batching register info (addr + mask). @@ -323,6 +331,7 @@ struct st_lsm6dsx_settings { } irq_config; struct st_lsm6dsx_reg drdy_mask; struct st_lsm6dsx_odr_table_entry odr_table[2]; + struct st_lsm6dsx_samples_to_discard samples_to_discard[2]; struct st_lsm6dsx_fs_table_entry fs_table[2]; struct st_lsm6dsx_reg decimator[ST_LSM6DSX_MAX_ID]; struct st_lsm6dsx_reg batch[ST_LSM6DSX_MAX_ID]; @@ -353,6 +362,7 @@ enum st_lsm6dsx_fifo_mode { * @hw: Pointer to instance of struct st_lsm6dsx_hw. * @gain: Configured sensor sensitivity. * @odr: Output data rate of the sensor [Hz]. + * @samples_to_discard: Number of samples to discard for filters settling time. * @watermark: Sensor watermark level. * @decimator: Sensor decimation factor. * @sip: Number of samples in a given pattern. @@ -367,6 +377,7 @@ struct st_lsm6dsx_sensor { u32 gain; u32 odr; + u16 samples_to_discard; u16 watermark; u8 decimator; u8 sip; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 7dd5205aea5b..f6c11d6fb0b0 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -457,17 +457,31 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw) } if (gyro_sip > 0 && !(sip % gyro_sensor->decimator)) { - iio_push_to_buffers_with_timestamp( - hw->iio_devs[ST_LSM6DSX_ID_GYRO], - &hw->scan[ST_LSM6DSX_ID_GYRO], - gyro_sensor->ts_ref + ts); + /* + * We need to discards gyro samples during + * filters settling time + */ + if (gyro_sensor->samples_to_discard > 0) + gyro_sensor->samples_to_discard--; + else + iio_push_to_buffers_with_timestamp( + hw->iio_devs[ST_LSM6DSX_ID_GYRO], + &hw->scan[ST_LSM6DSX_ID_GYRO], + gyro_sensor->ts_ref + ts); gyro_sip--; } if (acc_sip > 0 && !(sip % acc_sensor->decimator)) { - iio_push_to_buffers_with_timestamp( - hw->iio_devs[ST_LSM6DSX_ID_ACC], - &hw->scan[ST_LSM6DSX_ID_ACC], - acc_sensor->ts_ref + ts); + /* + * We need to discards accel samples during + * filters settling time + */ + if (acc_sensor->samples_to_discard > 0) + acc_sensor->samples_to_discard--; + else + iio_push_to_buffers_with_timestamp( + hw->iio_devs[ST_LSM6DSX_ID_ACC], + &hw->scan[ST_LSM6DSX_ID_ACC], + acc_sensor->ts_ref + ts); acc_sip--; } if (ext_sip > 0 && !(sip % ext_sensor->decimator)) { @@ -654,6 +668,30 @@ int st_lsm6dsx_flush_fifo(struct st_lsm6dsx_hw *hw) return err; } +static void +st_lsm6dsx_update_samples_to_discard(struct st_lsm6dsx_sensor *sensor) +{ + const struct st_lsm6dsx_samples_to_discard *data; + struct st_lsm6dsx_hw *hw = sensor->hw; + int i; + + if (sensor->id != ST_LSM6DSX_ID_GYRO && + sensor->id != ST_LSM6DSX_ID_ACC) + return; + + /* check if drdy mask is supported in hw */ + if (hw->settings->drdy_mask.addr) + return; + + data = &hw->settings->samples_to_discard[sensor->id]; + for (i = 0; i < ST_LSM6DSX_ODR_LIST_SIZE; i++) { + if (data->val[i].milli_hz == sensor->odr) { + sensor->samples_to_discard = data->val[i].samples; + return; + } + } +} + int st_lsm6dsx_update_fifo(struct st_lsm6dsx_sensor *sensor, bool enable) { struct st_lsm6dsx_hw *hw = sensor->hw; @@ -673,6 +711,9 @@ int st_lsm6dsx_update_fifo(struct st_lsm6dsx_sensor *sensor, bool enable) goto out; } + if (enable) + st_lsm6dsx_update_samples_to_discard(sensor); + err = st_lsm6dsx_device_set_enable(sensor, enable); if (err < 0) goto out; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 3f6060c64f32..966df6ffe874 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -634,6 +634,24 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { .fs_len = 4, }, }, + .samples_to_discard = { + [ST_LSM6DSX_ID_ACC] = { + .val[0] = { 12500, 1 }, + .val[1] = { 26000, 1 }, + .val[2] = { 52000, 1 }, + .val[3] = { 104000, 2 }, + .val[4] = { 208000, 2 }, + .val[5] = { 416000, 2 }, + }, + [ST_LSM6DSX_ID_GYRO] = { + .val[0] = { 12500, 2 }, + .val[1] = { 26000, 5 }, + .val[2] = { 52000, 7 }, + .val[3] = { 104000, 12 }, + .val[4] = { 208000, 20 }, + .val[5] = { 416000, 36 }, + }, + }, .irq_config = { .irq1 = { .addr = 0x0d, -- GitLab From 4ad682e04c1694aba95627f60e89f83178c277c2 Mon Sep 17 00:00:00 2001 From: Mehdi Djait Date: Thu, 2 Mar 2023 14:04:35 +0100 Subject: [PATCH 0275/5631] iio: Improve the kernel-doc of iio_trigger_poll Move the kernel-doc of the function to industrialio-trigger.c Add a note on the context where the function is expected to be called. Signed-off-by: Mehdi Djait Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/bd84fc17e9d22eab998bf48720297f9a77689f45.1677761379.git.mehdi.djait.k@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-trigger.c | 6 ++++++ include/linux/iio/trigger.h | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index a2f3cc2f65ef..270ec0a9f641 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -192,6 +192,12 @@ static void iio_trigger_notify_done_atomic(struct iio_trigger *trig) schedule_work(&trig->reenable_work); } +/** + * iio_trigger_poll() - Call the IRQ trigger handler of the consumers + * @trig: trigger which occurred + * + * This function should only be called from a hard IRQ context. + */ void iio_trigger_poll(struct iio_trigger *trig) { int i; diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index f6360d9a492d..42da55dc3aa7 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -151,12 +151,6 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); -/** - * iio_trigger_poll() - called on a trigger occurring - * @trig: trigger which occurred - * - * Typically called in relevant hardware interrupt handler. - **/ void iio_trigger_poll(struct iio_trigger *trig); void iio_trigger_poll_chained(struct iio_trigger *trig); -- GitLab From f700e55ef6ef9ec723164659ed4385900981c872 Mon Sep 17 00:00:00 2001 From: Mehdi Djait Date: Thu, 2 Mar 2023 14:04:36 +0100 Subject: [PATCH 0276/5631] iio: Rename iio_trigger_poll_chained and add kernel-doc Rename the function to iio_trigger_poll_nested. Add kernel-doc with a note on the context where the function is expected to be called. Signed-off-by: Mehdi Djait Link: https://lore.kernel.org/r/841b533cba28ca25a8e87280c44e45979166e8e2.1677761379.git.mehdi.djait.k@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/bma400_core.c | 2 +- drivers/iio/accel/kionix-kx022a.c | 2 +- drivers/iio/accel/mma8452.c | 2 +- drivers/iio/accel/msa311.c | 2 +- drivers/iio/adc/ad7606.c | 2 +- drivers/iio/adc/at91-sama5d2_adc.c | 2 +- drivers/iio/adc/max11410.c | 2 +- drivers/iio/common/st_sensors/st_sensors_trigger.c | 4 ++-- drivers/iio/gyro/fxas21002c_core.c | 2 +- drivers/iio/gyro/mpu3050-core.c | 2 +- drivers/iio/humidity/hts221_buffer.c | 2 +- drivers/iio/industrialio-trigger.c | 11 +++++++++-- drivers/iio/light/acpi-als.c | 2 +- drivers/iio/light/rpr0521.c | 2 +- drivers/iio/light/st_uvis25_core.c | 2 +- drivers/iio/light/vcnl4000.c | 2 +- drivers/iio/light/vcnl4035.c | 2 +- drivers/iio/potentiostat/lmp91000.c | 2 +- drivers/iio/pressure/zpa2326.c | 2 +- drivers/iio/proximity/as3935.c | 2 +- drivers/iio/trigger/iio-trig-loop.c | 2 +- include/linux/iio/trigger.h | 2 +- 22 files changed, 31 insertions(+), 24 deletions(-) diff --git a/drivers/iio/accel/bma400_core.c b/drivers/iio/accel/bma400_core.c index 623f37cbaf50..a68b845f5b4f 100644 --- a/drivers/iio/accel/bma400_core.c +++ b/drivers/iio/accel/bma400_core.c @@ -1688,7 +1688,7 @@ static irqreturn_t bma400_interrupt(int irq, void *private) if (FIELD_GET(BMA400_INT_DRDY_MSK, le16_to_cpu(data->status))) { mutex_unlock(&data->mutex); - iio_trigger_poll_chained(data->trig); + iio_trigger_poll_nested(data->trig); return IRQ_HANDLED; } diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index 9f8c7631f098..8dac0337c249 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -899,7 +899,7 @@ static irqreturn_t kx022a_irq_thread_handler(int irq, void *private) mutex_lock(&data->mutex); if (data->trigger_enabled) { - iio_trigger_poll_chained(data->trig); + iio_trigger_poll_nested(data->trig); ret = IRQ_HANDLED; } diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index f97fb68e3a71..ea14e3aaa30a 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -1067,7 +1067,7 @@ static irqreturn_t mma8452_interrupt(int irq, void *p) return IRQ_NONE; if (src & MMA8452_INT_DRDY) { - iio_trigger_poll_chained(indio_dev->trig); + iio_trigger_poll_nested(indio_dev->trig); ret = IRQ_HANDLED; } diff --git a/drivers/iio/accel/msa311.c b/drivers/iio/accel/msa311.c index af94d3adf6d8..6690fa37da8f 100644 --- a/drivers/iio/accel/msa311.c +++ b/drivers/iio/accel/msa311.c @@ -951,7 +951,7 @@ static irqreturn_t msa311_irq_thread(int irq, void *p) } if (new_data_int_enabled) - iio_trigger_poll_chained(msa311->new_data_trig); + iio_trigger_poll_nested(msa311->new_data_trig); return IRQ_HANDLED; } diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c index dd6b603f65ea..1928d9ae5bcf 100644 --- a/drivers/iio/adc/ad7606.c +++ b/drivers/iio/adc/ad7606.c @@ -477,7 +477,7 @@ static irqreturn_t ad7606_interrupt(int irq, void *dev_id) if (iio_buffer_enabled(indio_dev)) { gpiod_set_value(st->gpio_convst, 0); - iio_trigger_poll_chained(st->trig); + iio_trigger_poll_nested(st->trig); } else { complete(&st->completion); } diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index 50d02e5fc6fc..b5d0c9ee284c 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -1194,7 +1194,7 @@ static void at91_dma_buffer_done(void *data) { struct iio_dev *indio_dev = data; - iio_trigger_poll_chained(indio_dev->trig); + iio_trigger_poll_nested(indio_dev->trig); } static int at91_adc_dma_start(struct iio_dev *indio_dev) diff --git a/drivers/iio/adc/max11410.c b/drivers/iio/adc/max11410.c index b74b689ee7de..237b2ce3f264 100644 --- a/drivers/iio/adc/max11410.c +++ b/drivers/iio/adc/max11410.c @@ -678,7 +678,7 @@ static irqreturn_t max11410_interrupt(int irq, void *dev_id) struct max11410_state *st = iio_priv(indio_dev); if (iio_buffer_enabled(indio_dev)) - iio_trigger_poll_chained(st->trig); + iio_trigger_poll_nested(st->trig); else complete(&st->completion); diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 899b640c0a70..a0df9250a69f 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -85,7 +85,7 @@ static irqreturn_t st_sensors_irq_thread(int irq, void *p) */ if (sdata->hw_irq_trigger && st_sensors_new_samples_available(indio_dev, sdata)) { - iio_trigger_poll_chained(p); + iio_trigger_poll_nested(p); } else { dev_dbg(indio_dev->dev.parent, "spurious IRQ\n"); return IRQ_NONE; @@ -110,7 +110,7 @@ static irqreturn_t st_sensors_irq_thread(int irq, void *p) dev_dbg(indio_dev->dev.parent, "more samples came in during polling\n"); sdata->hw_timestamp = iio_get_time_ns(indio_dev); - iio_trigger_poll_chained(p); + iio_trigger_poll_nested(p); } return IRQ_HANDLED; diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 3ea1d4613080..c28d17ca6f5e 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -813,7 +813,7 @@ static irqreturn_t fxas21002c_data_rdy_thread(int irq, void *private) if (!data_ready) return IRQ_NONE; - iio_trigger_poll_chained(data->dready_trig); + iio_trigger_poll_nested(data->dready_trig); return IRQ_HANDLED; } diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c index 6a6d84a3deda..a791ba3a693a 100644 --- a/drivers/iio/gyro/mpu3050-core.c +++ b/drivers/iio/gyro/mpu3050-core.c @@ -939,7 +939,7 @@ static irqreturn_t mpu3050_irq_thread(int irq, void *p) if (!(val & MPU3050_INT_STATUS_RAW_RDY)) return IRQ_NONE; - iio_trigger_poll_chained(p); + iio_trigger_poll_nested(p); return IRQ_HANDLED; } diff --git a/drivers/iio/humidity/hts221_buffer.c b/drivers/iio/humidity/hts221_buffer.c index 2a4107a79662..11ef38994a95 100644 --- a/drivers/iio/humidity/hts221_buffer.c +++ b/drivers/iio/humidity/hts221_buffer.c @@ -68,7 +68,7 @@ static irqreturn_t hts221_trigger_handler_thread(int irq, void *private) if (!(status & HTS221_RH_DRDY_MASK)) return IRQ_NONE; - iio_trigger_poll_chained(hw->trig); + iio_trigger_poll_nested(hw->trig); return IRQ_HANDLED; } diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index 270ec0a9f641..784dc1e00310 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -222,7 +222,14 @@ irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private) } EXPORT_SYMBOL(iio_trigger_generic_data_rdy_poll); -void iio_trigger_poll_chained(struct iio_trigger *trig) +/** + * iio_trigger_poll_nested() - Call the threaded trigger handler of the + * consumers + * @trig: trigger which occurred + * + * This function should only be called from a kernel thread context. + */ +void iio_trigger_poll_nested(struct iio_trigger *trig) { int i; @@ -237,7 +244,7 @@ void iio_trigger_poll_chained(struct iio_trigger *trig) } } } -EXPORT_SYMBOL(iio_trigger_poll_chained); +EXPORT_SYMBOL(iio_trigger_poll_nested); void iio_trigger_notify_done(struct iio_trigger *trig) { diff --git a/drivers/iio/light/acpi-als.c b/drivers/iio/light/acpi-als.c index e1ff6f524f4b..2d91caf24dd0 100644 --- a/drivers/iio/light/acpi-als.c +++ b/drivers/iio/light/acpi-als.c @@ -108,7 +108,7 @@ static void acpi_als_notify(struct acpi_device *device, u32 event) if (iio_buffer_enabled(indio_dev) && iio_trigger_using_own(indio_dev)) { switch (event) { case ACPI_ALS_NOTIFY_ILLUMINANCE: - iio_trigger_poll_chained(als->trig); + iio_trigger_poll_nested(als->trig); break; default: /* Unhandled event */ diff --git a/drivers/iio/light/rpr0521.c b/drivers/iio/light/rpr0521.c index 668e444f6049..9d0218b7426e 100644 --- a/drivers/iio/light/rpr0521.c +++ b/drivers/iio/light/rpr0521.c @@ -431,7 +431,7 @@ static irqreturn_t rpr0521_drdy_irq_thread(int irq, void *private) struct rpr0521_data *data = iio_priv(indio_dev); if (rpr0521_is_triggered(data)) { - iio_trigger_poll_chained(data->drdy_trigger0); + iio_trigger_poll_nested(data->drdy_trigger0); return IRQ_HANDLED; } diff --git a/drivers/iio/light/st_uvis25_core.c b/drivers/iio/light/st_uvis25_core.c index c737d3e193ae..50f95c5d2060 100644 --- a/drivers/iio/light/st_uvis25_core.c +++ b/drivers/iio/light/st_uvis25_core.c @@ -161,7 +161,7 @@ static irqreturn_t st_uvis25_trigger_handler_thread(int irq, void *private) if (!(status & ST_UVIS25_REG_UV_DA_MASK)) return IRQ_NONE; - iio_trigger_poll_chained(hw->trig); + iio_trigger_poll_nested(hw->trig); return IRQ_HANDLED; } diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c index 6bdfce9747f9..b9460c165d37 100644 --- a/drivers/iio/light/vcnl4000.c +++ b/drivers/iio/light/vcnl4000.c @@ -1078,7 +1078,7 @@ static irqreturn_t vcnl4010_irq_thread(int irq, void *p) } if (isr & VCNL4010_INT_DRDY && iio_buffer_enabled(indio_dev)) - iio_trigger_poll_chained(indio_dev->trig); + iio_trigger_poll_nested(indio_dev->trig); end: return IRQ_HANDLED; diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 84148b944000..14e29330e972 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -89,7 +89,7 @@ static irqreturn_t vcnl4035_drdy_irq_thread(int irq, void *private) IIO_EV_TYPE_THRESH, IIO_EV_DIR_EITHER), iio_get_time_ns(indio_dev)); - iio_trigger_poll_chained(data->drdy_trigger0); + iio_trigger_poll_nested(data->drdy_trigger0); return IRQ_HANDLED; } diff --git a/drivers/iio/potentiostat/lmp91000.c b/drivers/iio/potentiostat/lmp91000.c index b82f093f1e6a..0083e858c21e 100644 --- a/drivers/iio/potentiostat/lmp91000.c +++ b/drivers/iio/potentiostat/lmp91000.c @@ -118,7 +118,7 @@ static int lmp91000_read(struct lmp91000_data *data, int channel, int *val) data->chan_select = channel != LMP91000_REG_MODECN_3LEAD; - iio_trigger_poll_chained(data->trig); + iio_trigger_poll_nested(data->trig); ret = wait_for_completion_timeout(&data->completion, HZ); reinit_completion(&data->completion); diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index 67119a9b95fc..421e059d1f19 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -829,7 +829,7 @@ static irqreturn_t zpa2326_handle_threaded_irq(int irq, void *data) } /* New sample available: dispatch internal trigger consumers. */ - iio_trigger_poll_chained(priv->trigger); + iio_trigger_poll_nested(priv->trigger); if (cont) /* diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c index ebc95cf8f5f4..96fa97451cbf 100644 --- a/drivers/iio/proximity/as3935.c +++ b/drivers/iio/proximity/as3935.c @@ -257,7 +257,7 @@ static void as3935_event_work(struct work_struct *work) switch (val) { case AS3935_EVENT_INT: - iio_trigger_poll_chained(st->trig); + iio_trigger_poll_nested(st->trig); break; case AS3935_DISTURB_INT: case AS3935_NOISE_INT: diff --git a/drivers/iio/trigger/iio-trig-loop.c b/drivers/iio/trigger/iio-trig-loop.c index 96ec06bbe546..7aaed0611899 100644 --- a/drivers/iio/trigger/iio-trig-loop.c +++ b/drivers/iio/trigger/iio-trig-loop.c @@ -46,7 +46,7 @@ static int iio_loop_thread(void *data) set_freezable(); do { - iio_trigger_poll_chained(trig); + iio_trigger_poll_nested(trig); } while (likely(!kthread_freezable_should_stop(NULL))); return 0; diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 42da55dc3aa7..51f52c5c6092 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -152,7 +152,7 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); void iio_trigger_poll(struct iio_trigger *trig); -void iio_trigger_poll_chained(struct iio_trigger *trig); +void iio_trigger_poll_nested(struct iio_trigger *trig); irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private); -- GitLab From 70ed9ced1f415b4f68bfdfffc7240a79bca8e045 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 28 Feb 2023 10:05:14 +0100 Subject: [PATCH 0277/5631] dt-bindings: iio: ti,tmp117: fix documentation link Fix the broken link to point to the correct homepage. Fixes: 5e713b25d137 ("dt-bindings: iio: temperature: Add DT bindings for TMP117") Signed-off-by: Marco Felsch Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230228090518.529811-2-m.felsch@pengutronix.de Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/temperature/ti,tmp117.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml b/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml index c4f1c69f9330..b6d082995e55 100644 --- a/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml +++ b/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml @@ -9,7 +9,7 @@ title: TI TMP117 - Digital temperature sensor with integrated NV memory description: | TI TMP117 - Digital temperature sensor with integrated NV memory that supports I2C interface. - https://www.ti.com/lit/gpn/tmp1 + https://www.ti.com/lit/gpn/tmp117 maintainers: - Puranjay Mohan -- GitLab From 07cc68996d8e83f7f1caccdc588757f6df57861a Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 28 Feb 2023 10:05:15 +0100 Subject: [PATCH 0278/5631] iio: temperature: tmp117: improve fallback capabilities Don't error if the device-id found don't match the device-id for the TMP117 sensor since other TMPxxx might be compatible to the TMP117. The fallback mechanism tries to gather the required information from the of_device_id or from the i2c_client information. The commit also prepares the driver for adding new devices more easily by making use of switch-case at the relevant parts. Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20230228090518.529811-3-m.felsch@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/temperature/tmp117.c | 44 ++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 10 deletions(-) diff --git a/drivers/iio/temperature/tmp117.c b/drivers/iio/temperature/tmp117.c index f9b8f2b570f6..8a3992d9ee93 100644 --- a/drivers/iio/temperature/tmp117.c +++ b/drivers/iio/temperature/tmp117.c @@ -16,6 +16,7 @@ #include #include #include +#include #include @@ -115,23 +116,40 @@ static const struct iio_info tmp117_info = { static int tmp117_identify(struct i2c_client *client) { + const struct i2c_device_id *id; + unsigned long match_data; int dev_id; dev_id = i2c_smbus_read_word_swapped(client, TMP117_REG_DEVICE_ID); if (dev_id < 0) return dev_id; - if (dev_id != TMP117_DEVICE_ID) { - dev_err(&client->dev, "TMP117 not found\n"); - return -ENODEV; + + switch (dev_id) { + case TMP117_DEVICE_ID: + return dev_id; } - return 0; + + dev_info(&client->dev, "Unknown device id (0x%x), use fallback compatible\n", + dev_id); + + match_data = (uintptr_t)device_get_match_data(&client->dev); + if (match_data) + return match_data; + + id = i2c_client_get_device_id(client); + if (id) + return id->driver_data; + + dev_err(&client->dev, "Failed to identify unsupported device\n"); + + return -ENODEV; } static int tmp117_probe(struct i2c_client *client) { struct tmp117_data *data; struct iio_dev *indio_dev; - int ret; + int ret, dev_id; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_WORD_DATA)) return -EOPNOTSUPP; @@ -140,6 +158,8 @@ static int tmp117_probe(struct i2c_client *client) if (ret < 0) return ret; + dev_id = ret; + indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data)); if (!indio_dev) return -ENOMEM; @@ -148,24 +168,28 @@ static int tmp117_probe(struct i2c_client *client) data->client = client; data->calibbias = 0; - indio_dev->name = "tmp117"; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->info = &tmp117_info; - indio_dev->channels = tmp117_channels; - indio_dev->num_channels = ARRAY_SIZE(tmp117_channels); + switch (dev_id) { + case TMP117_DEVICE_ID: + indio_dev->channels = tmp117_channels; + indio_dev->num_channels = ARRAY_SIZE(tmp117_channels); + indio_dev->name = "tmp117"; + break; + } return devm_iio_device_register(&client->dev, indio_dev); } static const struct of_device_id tmp117_of_match[] = { - { .compatible = "ti,tmp117", }, + { .compatible = "ti,tmp117", .data = (void *)TMP117_DEVICE_ID }, { } }; MODULE_DEVICE_TABLE(of, tmp117_of_match); static const struct i2c_device_id tmp117_id[] = { - { "tmp117", 0 }, + { "tmp117", TMP117_DEVICE_ID }, { } }; MODULE_DEVICE_TABLE(i2c, tmp117_id); -- GitLab From 9225efe0806d08494e63eeecebad0b61c66d27dc Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 28 Feb 2023 10:05:16 +0100 Subject: [PATCH 0279/5631] dt-bindings: iio: ti,tmp117: add binding for the TMP116 The TMP116 is the predecessor of the TMP117. Signed-off-by: Marco Felsch Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230228090518.529811-4-m.felsch@pengutronix.de Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/temperature/ti,tmp117.yaml | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml b/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml index b6d082995e55..8c6d7735e875 100644 --- a/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml +++ b/Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml @@ -7,8 +7,9 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TI TMP117 - Digital temperature sensor with integrated NV memory description: | - TI TMP117 - Digital temperature sensor with integrated NV memory that supports - I2C interface. + TI TMP116/117 - Digital temperature sensor with integrated NV memory that + supports I2C interface. + https://www.ti.com/lit/gpn/tmp116 https://www.ti.com/lit/gpn/tmp117 maintainers: @@ -17,6 +18,7 @@ maintainers: properties: compatible: enum: + - ti,tmp116 - ti,tmp117 reg: -- GitLab From 0cd2889dc1fed57a2975521d951e1bc91088229c Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 28 Feb 2023 10:05:17 +0100 Subject: [PATCH 0280/5631] iio: temperature: tmp117: add TI TMP116 support The TMP116 is the predecessor of the TMP117. The TMP116 don't support custom offset calibration data, instead this register is used as generic EEPROM storage as well. Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20230228090518.529811-5-m.felsch@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/temperature/tmp117.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/iio/temperature/tmp117.c b/drivers/iio/temperature/tmp117.c index 8a3992d9ee93..9bfb818c3bf1 100644 --- a/drivers/iio/temperature/tmp117.c +++ b/drivers/iio/temperature/tmp117.c @@ -32,9 +32,11 @@ #define TMP117_REG_DEVICE_ID 0xF #define TMP117_RESOLUTION_10UC 78125 -#define TMP117_DEVICE_ID 0x0117 #define MICRODEGREE_PER_10MILLIDEGREE 10000 +#define TMP116_DEVICE_ID 0x1116 +#define TMP117_DEVICE_ID 0x0117 + struct tmp117_data { struct i2c_client *client; s16 calibbias; @@ -109,6 +111,14 @@ static const struct iio_chan_spec tmp117_channels[] = { }, }; +static const struct iio_chan_spec tmp116_channels[] = { + { + .type = IIO_TEMP, + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_SCALE), + }, +}; + static const struct iio_info tmp117_info = { .read_raw = tmp117_read_raw, .write_raw = tmp117_write_raw, @@ -125,6 +135,7 @@ static int tmp117_identify(struct i2c_client *client) return dev_id; switch (dev_id) { + case TMP116_DEVICE_ID: case TMP117_DEVICE_ID: return dev_id; } @@ -172,6 +183,11 @@ static int tmp117_probe(struct i2c_client *client) indio_dev->info = &tmp117_info; switch (dev_id) { + case TMP116_DEVICE_ID: + indio_dev->channels = tmp116_channels; + indio_dev->num_channels = ARRAY_SIZE(tmp116_channels); + indio_dev->name = "tmp116"; + break; case TMP117_DEVICE_ID: indio_dev->channels = tmp117_channels; indio_dev->num_channels = ARRAY_SIZE(tmp117_channels); @@ -183,12 +199,14 @@ static int tmp117_probe(struct i2c_client *client) } static const struct of_device_id tmp117_of_match[] = { + { .compatible = "ti,tmp116", .data = (void *)TMP116_DEVICE_ID }, { .compatible = "ti,tmp117", .data = (void *)TMP117_DEVICE_ID }, { } }; MODULE_DEVICE_TABLE(of, tmp117_of_match); static const struct i2c_device_id tmp117_id[] = { + { "tmp116", TMP116_DEVICE_ID }, { "tmp117", TMP117_DEVICE_ID }, { } }; -- GitLab From e94230755641d4832f28b7997755dbf0acac7b54 Mon Sep 17 00:00:00 2001 From: Marco Felsch Date: Tue, 28 Feb 2023 10:05:18 +0100 Subject: [PATCH 0281/5631] iio: temperature: tmp117: cosmetic alignment cleanup Align the code correctly if possible and align the channel bit mask to make it easier to read. Signed-off-by: Marco Felsch Link: https://lore.kernel.org/r/20230228090518.529811-6-m.felsch@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/temperature/tmp117.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/iio/temperature/tmp117.c b/drivers/iio/temperature/tmp117.c index 9bfb818c3bf1..638e3a5bd6b8 100644 --- a/drivers/iio/temperature/tmp117.c +++ b/drivers/iio/temperature/tmp117.c @@ -43,8 +43,8 @@ struct tmp117_data { }; static int tmp117_read_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *channel, int *val, - int *val2, long mask) + struct iio_chan_spec const *channel, int *val, + int *val2, long mask) { struct tmp117_data *data = iio_priv(indio_dev); s32 ret; @@ -52,7 +52,7 @@ static int tmp117_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: ret = i2c_smbus_read_word_swapped(data->client, - TMP117_REG_TEMP); + TMP117_REG_TEMP); if (ret < 0) return ret; *val = sign_extend32(ret, 15); @@ -60,7 +60,7 @@ static int tmp117_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_CALIBBIAS: ret = i2c_smbus_read_word_swapped(data->client, - TMP117_REG_TEMP_OFFSET); + TMP117_REG_TEMP_OFFSET); if (ret < 0) return ret; *val = sign_extend32(ret, 15); @@ -82,9 +82,8 @@ static int tmp117_read_raw(struct iio_dev *indio_dev, } } -static int tmp117_write_raw(struct iio_dev *indio_dev, - struct iio_chan_spec const *channel, int val, - int val2, long mask) +static int tmp117_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec + const *channel, int val, int val2, long mask) { struct tmp117_data *data = iio_priv(indio_dev); s16 off; @@ -107,7 +106,8 @@ static const struct iio_chan_spec tmp117_channels[] = { { .type = IIO_TEMP, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_CALIBBIAS) | BIT(IIO_CHAN_INFO_SCALE), + BIT(IIO_CHAN_INFO_CALIBBIAS) | + BIT(IIO_CHAN_INFO_SCALE), }, }; -- GitLab From 42d35bf6c37b9445fa39f995466d716add4b70b9 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:14:54 +0100 Subject: [PATCH 0282/5631] iio: adc: rcar-gyroadc: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/iio/adc/rcar-gyroadc.c:286:34: error: ‘rcar_gyroadc_child_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311111457.251475-1-krzysztof.kozlowski@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/adc/rcar-gyroadc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/rcar-gyroadc.c b/drivers/iio/adc/rcar-gyroadc.c index 27d9e147b4b7..b8972f673c9d 100644 --- a/drivers/iio/adc/rcar-gyroadc.c +++ b/drivers/iio/adc/rcar-gyroadc.c @@ -283,7 +283,7 @@ static const struct of_device_id rcar_gyroadc_match[] = { MODULE_DEVICE_TABLE(of, rcar_gyroadc_match); -static const struct of_device_id rcar_gyroadc_child_match[] = { +static const struct of_device_id rcar_gyroadc_child_match[] __maybe_unused = { /* Mode 1 ADCs */ { .compatible = "fujitsu,mb88101a", -- GitLab From 666cac91ae47c86c7a76fec39771123a92825134 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 10 Mar 2023 19:24:34 -0500 Subject: [PATCH 0283/5631] iio: dac: cio-dac: Fix typo in comment listing supported devices This driver supports the CIO-DAC08 device and not "CIO-DAC06". Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/20230311002434.8761-1-william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/dac/cio-dac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/dac/cio-dac.c b/drivers/iio/dac/cio-dac.c index 791dd999cf29..bb67d3340c9f 100644 --- a/drivers/iio/dac/cio-dac.c +++ b/drivers/iio/dac/cio-dac.c @@ -4,7 +4,7 @@ * Copyright (C) 2016 William Breathitt Gray * * This driver supports the following Measurement Computing devices: CIO-DAC16, - * CIO-DAC06, and PC104-DAC06. + * CIO-DAC08, and PC104-DAC06. */ #include #include -- GitLab From f8c64b146c60d60d9d35c950a854c3975034af19 Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Tue, 7 Mar 2023 07:55:33 +0100 Subject: [PATCH 0284/5631] dt-bindings: iio: adc: Add TI ADS1100 and ADS1000 The ADS1100 is a 16-bit ADC (at 8 samples per second). The ADS1000 is similar, but has a fixed data rate. Signed-off-by: Mike Looijmans Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230307065535.7927-1-mike.looijmans@topic.nl Signed-off-by: Jonathan Cameron --- .../bindings/iio/adc/ti,ads1100.yaml | 46 +++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 Documentation/devicetree/bindings/iio/adc/ti,ads1100.yaml diff --git a/Documentation/devicetree/bindings/iio/adc/ti,ads1100.yaml b/Documentation/devicetree/bindings/iio/adc/ti,ads1100.yaml new file mode 100644 index 000000000000..970ccab15e1e --- /dev/null +++ b/Documentation/devicetree/bindings/iio/adc/ti,ads1100.yaml @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iio/adc/ti,ads1100.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TI ADS1100/ADS1000 single channel I2C analog to digital converter + +maintainers: + - Mike Looijmans + +description: | + Datasheet at: https://www.ti.com/lit/gpn/ads1100 + +properties: + compatible: + enum: + - ti,ads1100 + - ti,ads1000 + + reg: + maxItems: 1 + + vdd-supply: true + + "#io-channel-cells": + const: 0 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + adc@49 { + compatible = "ti,ads1100"; + reg = <0x49>; + }; + }; +... -- GitLab From 541880542f2baa7c485b40c1ecad1855315418f6 Mon Sep 17 00:00:00 2001 From: Mike Looijmans Date: Tue, 7 Mar 2023 07:55:34 +0100 Subject: [PATCH 0285/5631] iio: adc: Add TI ADS1100 and ADS1000 The ADS1100 is a 16-bit ADC (at 8 samples per second). The ADS1000 is similar, but has a fixed data rate. Signed-off-by: Mike Looijmans Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230307065535.7927-2-mike.looijmans@topic.nl Signed-off-by: Jonathan Cameron --- drivers/iio/adc/Kconfig | 10 + drivers/iio/adc/Makefile | 1 + drivers/iio/adc/ti-ads1100.c | 445 +++++++++++++++++++++++++++++++++++ 3 files changed, 456 insertions(+) create mode 100644 drivers/iio/adc/ti-ads1100.c diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 45af2302be53..eb2b09ef5d5b 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -1229,6 +1229,16 @@ config TI_ADS7924 This driver can also be built as a module. If so, the module will be called ti-ads7924. +config TI_ADS1100 + tristate "Texas Instruments ADS1100 and ADS1000 ADC" + depends on I2C + help + If you say yes here you get support for Texas Instruments ADS1100 and + ADS1000 ADC chips. + + This driver can also be built as a module. If so, the module will be + called ti-ads1100. + config TI_ADS7950 tristate "Texas Instruments ADS7950 ADC driver" depends on SPI && GPIOLIB diff --git a/drivers/iio/adc/Makefile b/drivers/iio/adc/Makefile index 36c18177322a..e07e4a3e6237 100644 --- a/drivers/iio/adc/Makefile +++ b/drivers/iio/adc/Makefile @@ -108,6 +108,7 @@ obj-$(CONFIG_TI_ADC108S102) += ti-adc108s102.o obj-$(CONFIG_TI_ADC128S052) += ti-adc128s052.o obj-$(CONFIG_TI_ADC161S626) += ti-adc161s626.o obj-$(CONFIG_TI_ADS1015) += ti-ads1015.o +obj-$(CONFIG_TI_ADS1100) += ti-ads1100.o obj-$(CONFIG_TI_ADS7924) += ti-ads7924.o obj-$(CONFIG_TI_ADS7950) += ti-ads7950.o obj-$(CONFIG_TI_ADS8344) += ti-ads8344.o diff --git a/drivers/iio/adc/ti-ads1100.c b/drivers/iio/adc/ti-ads1100.c new file mode 100644 index 000000000000..6a478efb108b --- /dev/null +++ b/drivers/iio/adc/ti-ads1100.c @@ -0,0 +1,445 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ADS1100 - Texas Instruments Analog-to-Digital Converter + * + * Copyright (c) 2023, Topic Embedded Products + * + * Datasheet: https://www.ti.com/lit/gpn/ads1100 + * IIO driver for ADS1100 and ADS1000 ADC 16-bit I2C + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/* The ADS1100 has a single byte config register */ + +/* Conversion in progress bit */ +#define ADS1100_CFG_ST_BSY BIT(7) +/* Single conversion bit */ +#define ADS1100_CFG_SC BIT(4) +/* Data rate */ +#define ADS1100_DR_MASK GENMASK(3, 2) +/* Gain */ +#define ADS1100_PGA_MASK GENMASK(1, 0) + +#define ADS1100_CONTINUOUS 0 +#define ADS1100_SINGLESHOT ADS1100_CFG_SC + +#define ADS1100_SLEEP_DELAY_MS 2000 + +static const int ads1100_data_rate[] = { 128, 32, 16, 8 }; +static const int ads1100_data_rate_bits[] = { 12, 14, 15, 16 }; + +struct ads1100_data { + struct i2c_client *client; + struct regulator *reg_vdd; + struct mutex lock; + int scale_avail[2 * 4]; /* 4 gain settings */ + u8 config; + bool supports_data_rate; /* Only the ADS1100 can select the rate */ +}; + +static const struct iio_chan_spec ads1100_channel = { + .type = IIO_VOLTAGE, + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), + .info_mask_shared_by_all = + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_SAMP_FREQ), + .info_mask_shared_by_all_available = + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_SAMP_FREQ), + .scan_type = { + .sign = 's', + .realbits = 16, + .storagebits = 16, + .endianness = IIO_CPU, + }, + .datasheet_name = "AIN", +}; + +static int ads1100_set_config_bits(struct ads1100_data *data, u8 mask, u8 value) +{ + int ret; + u8 config = (data->config & ~mask) | (value & mask); + + if (data->config == config) + return 0; /* Already done */ + + ret = i2c_master_send(data->client, &config, 1); + if (ret < 0) + return ret; + + data->config = config; + + return 0; +}; + +static int ads1100_data_bits(struct ads1100_data *data) +{ + return ads1100_data_rate_bits[FIELD_GET(ADS1100_DR_MASK, data->config)]; +} + +static int ads1100_get_adc_result(struct ads1100_data *data, int chan, int *val) +{ + int ret; + __be16 buffer; + s16 value; + + if (chan != 0) + return -EINVAL; + + ret = pm_runtime_resume_and_get(&data->client->dev); + if (ret < 0) + return ret; + + ret = i2c_master_recv(data->client, (char *)&buffer, sizeof(buffer)); + + pm_runtime_mark_last_busy(&data->client->dev); + pm_runtime_put_autosuspend(&data->client->dev); + + if (ret < 0) { + dev_err(&data->client->dev, "I2C read fail: %d\n", ret); + return ret; + } + + /* Value is always 16-bit 2's complement */ + value = be16_to_cpu(buffer); + + /* Shift result to compensate for bit resolution vs. sample rate */ + value <<= 16 - ads1100_data_bits(data); + + *val = sign_extend32(value, 15); + + return 0; +} + +static int ads1100_set_scale(struct ads1100_data *data, int val, int val2) +{ + int microvolts; + int gain; + + /* With Vdd between 2.7 and 5V, the scale is always below 1 */ + if (val) + return -EINVAL; + + if (!val2) + return -EINVAL; + + microvolts = regulator_get_voltage(data->reg_vdd); + /* + * val2 is in 'micro' units, n = val2 / 1000000 + * result must be millivolts, d = microvolts / 1000 + * the full-scale value is d/n, corresponds to 2^15, + * hence the gain = (d / n) >> 15, factoring out the 1000 and moving the + * bitshift so everything fits in 32-bits yields this formula. + */ + gain = DIV_ROUND_CLOSEST(microvolts, BIT(15)) * MILLI / val2; + if (gain < BIT(0) || gain > BIT(3)) + return -EINVAL; + + ads1100_set_config_bits(data, ADS1100_PGA_MASK, ffs(gain) - 1); + + return 0; +} + +static int ads1100_set_data_rate(struct ads1100_data *data, int chan, int rate) +{ + unsigned int i; + unsigned int size; + + size = data->supports_data_rate ? ARRAY_SIZE(ads1100_data_rate) : 1; + for (i = 0; i < size; i++) { + if (ads1100_data_rate[i] == rate) + return ads1100_set_config_bits(data, ADS1100_DR_MASK, + FIELD_PREP(ADS1100_DR_MASK, i)); + } + + return -EINVAL; +} + +static int ads1100_get_vdd_millivolts(struct ads1100_data *data) +{ + return regulator_get_voltage(data->reg_vdd) / (MICRO / MILLI); +} + +static void ads1100_calc_scale_avail(struct ads1100_data *data) +{ + int millivolts = ads1100_get_vdd_millivolts(data); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(data->scale_avail) / 2; i++) { + data->scale_avail[i * 2 + 0] = millivolts; + data->scale_avail[i * 2 + 1] = 15 + i; + } +} + +static int ads1100_read_avail(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, + const int **vals, int *type, int *length, + long mask) +{ + struct ads1100_data *data = iio_priv(indio_dev); + + if (chan->type != IIO_VOLTAGE) + return -EINVAL; + + switch (mask) { + case IIO_CHAN_INFO_SAMP_FREQ: + *type = IIO_VAL_INT; + *vals = ads1100_data_rate; + if (data->supports_data_rate) + *length = ARRAY_SIZE(ads1100_data_rate); + else + *length = 1; + return IIO_AVAIL_LIST; + case IIO_CHAN_INFO_SCALE: + *type = IIO_VAL_FRACTIONAL_LOG2; + *vals = data->scale_avail; + *length = ARRAY_SIZE(data->scale_avail); + return IIO_AVAIL_LIST; + default: + return -EINVAL; + } +} + +static int ads1100_read_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, int *val, + int *val2, long mask) +{ + int ret; + struct ads1100_data *data = iio_priv(indio_dev); + + mutex_lock(&data->lock); + switch (mask) { + case IIO_CHAN_INFO_RAW: + ret = iio_device_claim_direct_mode(indio_dev); + if (ret) + break; + + ret = ads1100_get_adc_result(data, chan->address, val); + if (ret >= 0) + ret = IIO_VAL_INT; + iio_device_release_direct_mode(indio_dev); + break; + case IIO_CHAN_INFO_SCALE: + /* full-scale is the supply voltage in millivolts */ + *val = ads1100_get_vdd_millivolts(data); + *val2 = 15 + FIELD_GET(ADS1100_PGA_MASK, data->config); + ret = IIO_VAL_FRACTIONAL_LOG2; + break; + case IIO_CHAN_INFO_SAMP_FREQ: + *val = ads1100_data_rate[FIELD_GET(ADS1100_DR_MASK, + data->config)]; + ret = IIO_VAL_INT; + break; + default: + ret = -EINVAL; + break; + } + mutex_unlock(&data->lock); + + return ret; +} + +static int ads1100_write_raw(struct iio_dev *indio_dev, + struct iio_chan_spec const *chan, int val, + int val2, long mask) +{ + struct ads1100_data *data = iio_priv(indio_dev); + int ret; + + mutex_lock(&data->lock); + switch (mask) { + case IIO_CHAN_INFO_SCALE: + ret = ads1100_set_scale(data, val, val2); + break; + case IIO_CHAN_INFO_SAMP_FREQ: + ret = ads1100_set_data_rate(data, chan->address, val); + break; + default: + ret = -EINVAL; + break; + } + mutex_unlock(&data->lock); + + return ret; +} + +static const struct iio_info ads1100_info = { + .read_avail = ads1100_read_avail, + .read_raw = ads1100_read_raw, + .write_raw = ads1100_write_raw, +}; + +static int ads1100_setup(struct ads1100_data *data) +{ + int ret; + u8 buffer[3]; + + /* Setup continuous sampling mode at 8sps */ + buffer[0] = ADS1100_DR_MASK | ADS1100_CONTINUOUS; + ret = i2c_master_send(data->client, buffer, 1); + if (ret < 0) + return ret; + + ret = i2c_master_recv(data->client, buffer, sizeof(buffer)); + if (ret < 0) + return ret; + + /* Config register returned in third byte, strip away the busy status */ + data->config = buffer[2] & ~ADS1100_CFG_ST_BSY; + + /* Detect the sample rate capability by checking the DR bits */ + data->supports_data_rate = FIELD_GET(ADS1100_DR_MASK, buffer[2]) != 0; + + return 0; +} + +static void ads1100_reg_disable(void *reg) +{ + regulator_disable(reg); +} + +static void ads1100_disable_continuous(void *data) +{ + ads1100_set_config_bits(data, ADS1100_CFG_SC, ADS1100_SINGLESHOT); +} + +static int ads1100_probe(struct i2c_client *client) +{ + struct iio_dev *indio_dev; + struct ads1100_data *data; + struct device *dev = &client->dev; + int ret; + + indio_dev = devm_iio_device_alloc(dev, sizeof(*data)); + if (!indio_dev) + return -ENOMEM; + + data = iio_priv(indio_dev); + dev_set_drvdata(dev, data); + data->client = client; + mutex_init(&data->lock); + + indio_dev->name = "ads1100"; + indio_dev->modes = INDIO_DIRECT_MODE; + indio_dev->channels = &ads1100_channel; + indio_dev->num_channels = 1; + indio_dev->info = &ads1100_info; + + data->reg_vdd = devm_regulator_get(dev, "vdd"); + if (IS_ERR(data->reg_vdd)) + return dev_err_probe(dev, PTR_ERR(data->reg_vdd), + "Failed to get vdd regulator\n"); + + ret = regulator_enable(data->reg_vdd); + if (ret < 0) + return dev_err_probe(dev, PTR_ERR(data->reg_vdd), + "Failed to enable vdd regulator\n"); + + ret = devm_add_action_or_reset(dev, ads1100_reg_disable, data->reg_vdd); + if (ret) + return ret; + + ret = ads1100_setup(data); + if (ret) + return dev_err_probe(dev, ret, + "Failed to communicate with device\n"); + + ret = devm_add_action_or_reset(dev, ads1100_disable_continuous, data); + if (ret) + return ret; + + ads1100_calc_scale_avail(data); + + pm_runtime_set_autosuspend_delay(dev, ADS1100_SLEEP_DELAY_MS); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_active(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable pm_runtime\n"); + + ret = devm_iio_device_register(dev, indio_dev); + if (ret) + return dev_err_probe(dev, ret, + "Failed to register IIO device\n"); + + return 0; +} + +static int ads1100_runtime_suspend(struct device *dev) +{ + struct ads1100_data *data = dev_get_drvdata(dev); + + ads1100_set_config_bits(data, ADS1100_CFG_SC, ADS1100_SINGLESHOT); + regulator_disable(data->reg_vdd); + + return 0; +} + +static int ads1100_runtime_resume(struct device *dev) +{ + struct ads1100_data *data = dev_get_drvdata(dev); + int ret; + + ret = regulator_enable(data->reg_vdd); + if (ret) { + dev_err(&data->client->dev, "Failed to enable Vdd\n"); + return ret; + } + + /* + * We'll always change the mode bit in the config register, so there is + * no need here to "force" a write to the config register. If the device + * has been power-cycled, we'll re-write its config register now. + */ + return ads1100_set_config_bits(data, ADS1100_CFG_SC, + ADS1100_CONTINUOUS); +} + +static DEFINE_RUNTIME_DEV_PM_OPS(ads1100_pm_ops, + ads1100_runtime_suspend, + ads1100_runtime_resume, + NULL); + +static const struct i2c_device_id ads1100_id[] = { + { "ads1100" }, + { "ads1000" }, + { } +}; + +MODULE_DEVICE_TABLE(i2c, ads1100_id); + +static const struct of_device_id ads1100_of_match[] = { + {.compatible = "ti,ads1100" }, + {.compatible = "ti,ads1000" }, + { } +}; + +MODULE_DEVICE_TABLE(of, ads1100_of_match); + +static struct i2c_driver ads1100_driver = { + .driver = { + .name = "ads1100", + .of_match_table = ads1100_of_match, + .pm = pm_ptr(&ads1100_pm_ops), + }, + .probe_new = ads1100_probe, + .id_table = ads1100_id, +}; + +module_i2c_driver(ads1100_driver); + +MODULE_AUTHOR("Mike Looijmans "); +MODULE_DESCRIPTION("Texas Instruments ADS1100 ADC driver"); +MODULE_LICENSE("GPL"); -- GitLab From 954ea91fb68b771dba6d87cfa61b68e09cc2497f Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 6 Mar 2023 10:43:00 +0100 Subject: [PATCH 0286/5631] dt-bindings: iio: ad74413r: allow setting sink current for digital input Depending on the actual hardware wired up to a digital input channel, it may be necessary to configure the ad74413r to sink a small current. For example, in the case of a simple mechanical switch, the charge on the external 68 nF capacitor (cf. the data sheet's Figure 34) will keep the channel as reading high even after the switch is turned off again. Signed-off-by: Rasmus Villemoes Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230306094301.1357543-2-linux@rasmusvillemoes.dk Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/addac/adi,ad74413r.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/addac/adi,ad74413r.yaml b/Documentation/devicetree/bindings/iio/addac/adi,ad74413r.yaml index 9eb3ecc8bbc8..590ea7936ad7 100644 --- a/Documentation/devicetree/bindings/iio/addac/adi,ad74413r.yaml +++ b/Documentation/devicetree/bindings/iio/addac/adi,ad74413r.yaml @@ -101,6 +101,15 @@ patternProperties: When not configured as a comparator, the GPO will be treated as an output-only GPIO. + drive-strength-microamp: + description: | + For channels configured as digital input, this configures the sink + current. + minimum: 0 + maximum: 1800 + default: 0 + multipleOf: 120 + required: - reg -- GitLab From 504eb485589d146e99a53cd982b52fe1728fc19e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 6 Mar 2023 10:43:01 +0100 Subject: [PATCH 0287/5631] iio: ad74413r: wire up support for drive-strength-microamp property Use the value specified in the channel configuration node to populate the DIN_SINK field of the DIN_CONFIGx register. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20230306094301.1357543-3-linux@rasmusvillemoes.dk Signed-off-by: Jonathan Cameron --- drivers/iio/addac/ad74413r.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index f32c8c2fb26d..4395758dbaa6 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -39,6 +39,7 @@ struct ad74413r_chip_info { struct ad74413r_channel_config { u32 func; + u32 drive_strength; bool gpo_comparator; bool initialized; }; @@ -111,6 +112,7 @@ struct ad74413r_state { #define AD74413R_REG_DIN_CONFIG_X(x) (0x09 + (x)) #define AD74413R_DIN_DEBOUNCE_MASK GENMASK(4, 0) #define AD74413R_DIN_DEBOUNCE_LEN BIT(5) +#define AD74413R_DIN_SINK_MASK GENMASK(9, 6) #define AD74413R_REG_DAC_CODE_X(x) (0x16 + (x)) #define AD74413R_DAC_CODE_MAX GENMASK(12, 0) @@ -261,6 +263,18 @@ static int ad74413r_set_comp_debounce(struct ad74413r_state *st, val); } +static int ad74413r_set_comp_drive_strength(struct ad74413r_state *st, + unsigned int offset, + unsigned int strength) +{ + strength = min(strength, 1800U); + + return regmap_update_bits(st->regmap, AD74413R_REG_DIN_CONFIG_X(offset), + AD74413R_DIN_SINK_MASK, + FIELD_PREP(AD74413R_DIN_SINK_MASK, strength / 120)); +} + + static void ad74413r_gpio_set(struct gpio_chip *chip, unsigned int offset, int val) { @@ -1190,6 +1204,9 @@ static int ad74413r_parse_channel_config(struct iio_dev *indio_dev, config->gpo_comparator = fwnode_property_read_bool(channel_node, "adi,gpo-comparator"); + fwnode_property_read_u32(channel_node, "drive-strength-microamp", + &config->drive_strength); + if (!config->gpo_comparator) st->num_gpo_gpios++; @@ -1269,6 +1286,7 @@ static int ad74413r_setup_gpios(struct ad74413r_state *st) unsigned int gpo_gpio_i = 0; unsigned int i; u8 gpo_config; + u32 strength; int ret; for (i = 0; i < AD74413R_CHANNEL_MAX; i++) { @@ -1285,6 +1303,11 @@ static int ad74413r_setup_gpios(struct ad74413r_state *st) config->func == CH_FUNC_DIGITAL_INPUT_LOOP_POWER) st->comp_gpio_offsets[comp_gpio_i++] = i; + strength = config->drive_strength; + ret = ad74413r_set_comp_drive_strength(st, i, strength); + if (ret) + return ret; + ret = ad74413r_set_gpo_config(st, i, gpo_config); if (ret) return ret; -- GitLab From 0088dd6869579f7022b226d1266e6dc23789ed41 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 1 Mar 2023 12:55:11 +0100 Subject: [PATCH 0288/5631] iio: addac: ad74413r: fix Current Input, Loop Powered Mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, the driver handles CH_FUNC_CURRENT_INPUT_LOOP_POWER and CH_FUNC_CURRENT_INPUT_EXT_POWER completely identically. But that's not correct. In order for CH_FUNC_CURRENT_INPUT_LOOP_POWER to work, two changes must be made: (1) expose access to the DAC_CODE_x register so that the intended output current can be set, i.e. expose the channel as both current output and current input, and (2) per the data sheet When selecting the current input loop powered function, tie the VIOUTN_x pin to ground via the on-chip 200 kΩ resistor by enabling the CH_200K_TO_GND bit in the ADC_CONFIGx registers. Signed-off-by: Rasmus Villemoes Link: https://lore.kernel.org/r/20230301115511.849418-1-linux@rasmusvillemoes.dk Signed-off-by: Jonathan Cameron --- drivers/iio/addac/ad74413r.c | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index 4395758dbaa6..07e9f6ae16a8 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -100,6 +100,7 @@ struct ad74413r_state { #define AD74413R_REG_ADC_CONFIG_X(x) (0x05 + (x)) #define AD74413R_ADC_CONFIG_RANGE_MASK GENMASK(7, 5) #define AD74413R_ADC_CONFIG_REJECTION_MASK GENMASK(4, 3) +#define AD74413R_ADC_CONFIG_CH_200K_TO_GND BIT(2) #define AD74413R_ADC_RANGE_10V 0b000 #define AD74413R_ADC_RANGE_2P5V_EXT_POW 0b001 #define AD74413R_ADC_RANGE_2P5V_INT_POW 0b010 @@ -438,9 +439,20 @@ static int ad74413r_set_channel_dac_code(struct ad74413r_state *st, static int ad74413r_set_channel_function(struct ad74413r_state *st, unsigned int channel, u8 func) { - return regmap_update_bits(st->regmap, + int ret; + + ret = regmap_update_bits(st->regmap, AD74413R_REG_CH_FUNC_SETUP_X(channel), AD74413R_CH_FUNC_SETUP_MASK, func); + if (ret) + return ret; + + if (func == CH_FUNC_CURRENT_INPUT_LOOP_POWER) + ret = regmap_set_bits(st->regmap, + AD74413R_REG_ADC_CONFIG_X(channel), + AD74413R_ADC_CONFIG_CH_200K_TO_GND); + + return ret; } static int ad74413r_set_adc_conv_seq(struct ad74413r_state *st, @@ -1126,6 +1138,11 @@ static struct iio_chan_spec ad74413r_current_input_channels[] = { AD74413R_ADC_CURRENT_CHANNEL, }; +static struct iio_chan_spec ad74413r_current_input_loop_channels[] = { + AD74413R_DAC_CHANNEL(IIO_CURRENT, BIT(IIO_CHAN_INFO_SCALE)), + AD74413R_ADC_CURRENT_CHANNEL, +}; + static struct iio_chan_spec ad74413r_resistance_input_channels[] = { AD74413R_ADC_CHANNEL(IIO_RESISTANCE, BIT(IIO_CHAN_INFO_PROCESSED)), }; @@ -1149,7 +1166,7 @@ static const struct ad74413r_channels ad74413r_channels_map[] = { [CH_FUNC_CURRENT_OUTPUT] = AD74413R_CHANNELS(current_output), [CH_FUNC_VOLTAGE_INPUT] = AD74413R_CHANNELS(voltage_input), [CH_FUNC_CURRENT_INPUT_EXT_POWER] = AD74413R_CHANNELS(current_input), - [CH_FUNC_CURRENT_INPUT_LOOP_POWER] = AD74413R_CHANNELS(current_input), + [CH_FUNC_CURRENT_INPUT_LOOP_POWER] = AD74413R_CHANNELS(current_input_loop), [CH_FUNC_RESISTANCE_INPUT] = AD74413R_CHANNELS(resistance_input), [CH_FUNC_DIGITAL_INPUT_LOGIC] = AD74413R_CHANNELS(digital_input), [CH_FUNC_DIGITAL_INPUT_LOOP_POWER] = AD74413R_CHANNELS(digital_input), -- GitLab From 18462d080171962d5003b12a7360357fa09b6aad Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 6 Mar 2023 12:08:00 +0100 Subject: [PATCH 0289/5631] iio: imu: st_lsm6dsx: add support to ASM330LHB Add support to STM ASM330LHB (acc + gyro) automotive Mems sensor. The ASM330LHB sensor can use ASM330LHH as fallback device since it implements all the ASM330LHB features currently implemented in st_lsm6dsx. Datasheet: https://www.st.com/resource/en/datasheet/asm330lhb.pdf Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/a1d675457da7aa9e979d8cabea410e942e015e71.1678100533.git.lorenzo@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/st_lsm6dsx/Kconfig | 4 ++-- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h | 2 ++ drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c | 2 +- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 4 ++++ drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c | 5 +++++ drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_spi.c | 5 +++++ 6 files changed, 19 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig index 8c16cdacf2f2..5865a295a4df 100644 --- a/drivers/iio/imu/st_lsm6dsx/Kconfig +++ b/drivers/iio/imu/st_lsm6dsx/Kconfig @@ -14,8 +14,8 @@ config IIO_ST_LSM6DSX sensor. Supported devices: lsm6ds3, lsm6ds3h, lsm6dsl, lsm6dsm, ism330dlc, lsm6dso, lsm6dsox, asm330lhh, asm330lhhx, lsm6dsr, lsm6ds3tr-c, ism330dhcx, lsm6dsrx, lsm6ds0, lsm6dsop, lsm6dstx, - lsm6dsv, lsm6dsv16x, lsm6dso16is, ism330is, lsm6dst and the - accelerometer/gyroscope of lsm9ds1. + lsm6dsv, lsm6dsv16x, lsm6dso16is, ism330is, asm330lhb, lsm6dst + and the accelerometer/gyroscope of lsm9ds1. To compile this driver as a module, choose M here: the module will be called st_lsm6dsx. diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h index 8e119d78730b..9dfe4917a386 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h @@ -37,6 +37,7 @@ #define ST_LSM6DSV16X_DEV_NAME "lsm6dsv16x" #define ST_LSM6DSO16IS_DEV_NAME "lsm6dso16is" #define ST_ISM330IS_DEV_NAME "ism330is" +#define ST_ASM330LHB_DEV_NAME "asm330lhb" enum st_lsm6dsx_hw_id { ST_LSM6DS3_ID, @@ -61,6 +62,7 @@ enum st_lsm6dsx_hw_id { ST_LSM6DSV16X_ID, ST_LSM6DSO16IS_ID, ST_ISM330IS_ID, + ST_ASM330LHB_ID, ST_LSM6DSX_MAX_ID, }; diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index f6c11d6fb0b0..066fe561c5e8 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -15,7 +15,7 @@ * value of the decimation factor and ODR set for each FIFO data set. * * LSM6DSO/LSM6DSOX/ASM330LHH/ASM330LHHX/LSM6DSR/LSM6DSRX/ISM330DHCX/ - * LSM6DST/LSM6DSOP/LSM6DSTX/LSM6DSV: + * LSM6DST/LSM6DSOP/LSM6DSTX/LSM6DSV/ASM330LHB: * The FIFO buffer can be configured to store data from gyroscope and * accelerometer. Each sample is queued with a tag (1B) indicating data * source (gyroscope, accelerometer, hw timer). diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 966df6ffe874..455e5edd3a80 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -1032,6 +1032,10 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = { .hw_id = ST_LSM6DSOP_ID, .name = ST_LSM6DSOP_DEV_NAME, .wai = 0x6c, + }, { + .hw_id = ST_ASM330LHB_ID, + .name = ST_ASM330LHB_DEV_NAME, + .wai = 0x6b, }, }, .channels = { diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c index df5f60925260..ccdc4ceffd85 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c @@ -125,6 +125,10 @@ static const struct of_device_id st_lsm6dsx_i2c_of_match[] = { .compatible = "st,ism330is", .data = (void *)ST_ISM330IS_ID, }, + { + .compatible = "st,asm330lhb", + .data = (void *)ST_ASM330LHB_ID, + }, {}, }; MODULE_DEVICE_TABLE(of, st_lsm6dsx_i2c_of_match); @@ -152,6 +156,7 @@ static const struct i2c_device_id st_lsm6dsx_i2c_id_table[] = { { ST_LSM6DSV16X_DEV_NAME, ST_LSM6DSV16X_ID }, { ST_LSM6DSO16IS_DEV_NAME, ST_LSM6DSO16IS_ID }, { ST_ISM330IS_DEV_NAME, ST_ISM330IS_ID }, + { ST_ASM330LHB_DEV_NAME, ST_ASM330LHB_ID }, {}, }; MODULE_DEVICE_TABLE(i2c, st_lsm6dsx_i2c_id_table); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_spi.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_spi.c index 974584bda875..f56c170c41a9 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_spi.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_spi.c @@ -125,6 +125,10 @@ static const struct of_device_id st_lsm6dsx_spi_of_match[] = { .compatible = "st,ism330is", .data = (void *)ST_ISM330IS_ID, }, + { + .compatible = "st,asm330lhb", + .data = (void *)ST_ASM330LHB_ID, + }, {}, }; MODULE_DEVICE_TABLE(of, st_lsm6dsx_spi_of_match); @@ -152,6 +156,7 @@ static const struct spi_device_id st_lsm6dsx_spi_id_table[] = { { ST_LSM6DSV16X_DEV_NAME, ST_LSM6DSV16X_ID }, { ST_LSM6DSO16IS_DEV_NAME, ST_LSM6DSO16IS_ID }, { ST_ISM330IS_DEV_NAME, ST_ISM330IS_ID }, + { ST_ASM330LHB_DEV_NAME, ST_ASM330LHB_ID }, {}, }; MODULE_DEVICE_TABLE(spi, st_lsm6dsx_spi_id_table); -- GitLab From 2e467c4edc7b08c3e4ad37c5d69a372f3bc59fad Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 6 Mar 2023 12:08:01 +0100 Subject: [PATCH 0290/5631] dt-bindings: iio: imu: st_lsm6dsx: add asm330lhb Add device bindings for asm330lhb IMU sensor. Use asm330lhh as fallback device for asm330lhb since it implements all the features currently supported by asm330lhb. Signed-off-by: Lorenzo Bianconi Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/fecf1f20cc8e99fb8654cc733f14bd449ca7f87a.1678100533.git.lorenzo@kernel.org Signed-off-by: Jonathan Cameron --- Documentation/devicetree/bindings/iio/imu/st,lsm6dsx.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/imu/st,lsm6dsx.yaml b/Documentation/devicetree/bindings/iio/imu/st,lsm6dsx.yaml index decf022335d8..b39f5217d8ff 100644 --- a/Documentation/devicetree/bindings/iio/imu/st,lsm6dsx.yaml +++ b/Documentation/devicetree/bindings/iio/imu/st,lsm6dsx.yaml @@ -46,6 +46,9 @@ properties: - items: - const: st,ism330is - const: st,lsm6dso16is + - items: + - const: st,asm330lhb + - const: st,asm330lhh reg: maxItems: 1 -- GitLab From b29c49026c3c05a11f845dba17cad0b3ba06836d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 16:34:28 +0100 Subject: [PATCH 0291/5631] iio: light: max44009: add missing OF device matching MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver currently matches only via i2c_device_id, but also has of_device_id table: drivers/iio/light/max44009.c:545:34: error: ‘max44009_of_match’ defined but not used [-Werror=unused-const-variable=] Fixes: 6aef699a7d7e ("iio: light: add driver for MAX44009") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312153429.371702-2-krzysztof.kozlowski@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/light/max44009.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/iio/light/max44009.c b/drivers/iio/light/max44009.c index 3dadace09fe2..176dcad6e8e8 100644 --- a/drivers/iio/light/max44009.c +++ b/drivers/iio/light/max44009.c @@ -527,6 +527,12 @@ static int max44009_probe(struct i2c_client *client) return devm_iio_device_register(&client->dev, indio_dev); } +static const struct of_device_id max44009_of_match[] = { + { .compatible = "maxim,max44009" }, + { } +}; +MODULE_DEVICE_TABLE(of, max44009_of_match); + static const struct i2c_device_id max44009_id[] = { { "max44009", 0 }, { } @@ -536,18 +542,13 @@ MODULE_DEVICE_TABLE(i2c, max44009_id); static struct i2c_driver max44009_driver = { .driver = { .name = MAX44009_DRV_NAME, + .of_match_table = max44009_of_match, }, .probe_new = max44009_probe, .id_table = max44009_id, }; module_i2c_driver(max44009_driver); -static const struct of_device_id max44009_of_match[] = { - { .compatible = "maxim,max44009" }, - { } -}; -MODULE_DEVICE_TABLE(of, max44009_of_match); - MODULE_AUTHOR("Robert Eshleman "); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("MAX44009 ambient light sensor driver"); -- GitLab From 9ee6bc3a035a5882888d6a73a2c13e2f4e65793f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 16:34:29 +0100 Subject: [PATCH 0292/5631] iio: proximity: sx9500: Reference ACPI and OF ID data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Always reference acpi_device_id and of_device_id tables, as they is little benefit of conditional compiling and OF table could be used also for ACPI matching via PRP0001. This fixes warning: drivers/iio/proximity/sx9500.c:1039:34: error: ‘sx9500_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312153429.371702-3-krzysztof.kozlowski@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/proximity/sx9500.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/proximity/sx9500.c b/drivers/iio/proximity/sx9500.c index 8794e75e5bf9..9b2cfcade6a4 100644 --- a/drivers/iio/proximity/sx9500.c +++ b/drivers/iio/proximity/sx9500.c @@ -1051,8 +1051,8 @@ MODULE_DEVICE_TABLE(i2c, sx9500_id); static struct i2c_driver sx9500_driver = { .driver = { .name = SX9500_DRIVER_NAME, - .acpi_match_table = ACPI_PTR(sx9500_acpi_match), - .of_match_table = of_match_ptr(sx9500_of_match), + .acpi_match_table = sx9500_acpi_match, + .of_match_table = sx9500_of_match, .pm = pm_sleep_ptr(&sx9500_pm_ops), }, .probe_new = sx9500_probe, -- GitLab From e853fb1803f60da69db82d41d92e30539a859227 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:06 +0100 Subject: [PATCH 0293/5631] clk: samsung: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-25-u.kleine-koenig@pengutronix.de Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos-audss.c | 6 ++---- drivers/clk/samsung/clk-exynos-clkout.c | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index 9cc127a162ad..7626dff41f6f 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -268,7 +268,7 @@ static int exynos_audss_clk_probe(struct platform_device *pdev) return ret; } -static int exynos_audss_clk_remove(struct platform_device *pdev) +static void exynos_audss_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); @@ -277,8 +277,6 @@ static int exynos_audss_clk_remove(struct platform_device *pdev) if (!IS_ERR(epll)) clk_disable_unprepare(epll); - - return 0; } static const struct dev_pm_ops exynos_audss_clk_pm_ops = { @@ -295,7 +293,7 @@ static struct platform_driver exynos_audss_clk_driver = { .pm = &exynos_audss_clk_pm_ops, }, .probe = exynos_audss_clk_probe, - .remove = exynos_audss_clk_remove, + .remove_new = exynos_audss_clk_remove, }; module_platform_driver(exynos_audss_clk_driver); diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c index e6d6cbf8c4e6..0cff1c94c35e 100644 --- a/drivers/clk/samsung/clk-exynos-clkout.c +++ b/drivers/clk/samsung/clk-exynos-clkout.c @@ -196,15 +196,13 @@ static int exynos_clkout_probe(struct platform_device *pdev) return ret; } -static int exynos_clkout_remove(struct platform_device *pdev) +static void exynos_clkout_remove(struct platform_device *pdev) { struct exynos_clkout *clkout = platform_get_drvdata(pdev); of_clk_del_provider(clkout->np); clk_hw_unregister(clkout->data.hws[0]); iounmap(clkout->reg); - - return 0; } static int __maybe_unused exynos_clkout_suspend(struct device *dev) @@ -235,7 +233,7 @@ static struct platform_driver exynos_clkout_driver = { .pm = &exynos_clkout_pm_ops, }, .probe = exynos_clkout_probe, - .remove = exynos_clkout_remove, + .remove_new = exynos_clkout_remove, }; module_platform_driver(exynos_clkout_driver); -- GitLab From 225dc61e2fa8def14426e2a34e926a79fae6118b Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 12 Mar 2023 12:17:33 -0400 Subject: [PATCH 0294/5631] iio: adc: stm32-adc: set some stm32-adc.c variables storage-class-specifier to static smatch reports several warnings drivers/iio/adc/stm32-adc.c:2591:20: warning: symbol 'stm32_adc_min_ts_h7' was not declared. Should it be static? drivers/iio/adc/stm32-adc.c:2610:20: warning: symbol 'stm32_adc_min_ts_mp1' was not declared. Should it be static? drivers/iio/adc/stm32-adc.c:2630:20: warning: symbol 'stm32_adc_min_ts_mp13' was not declared. Should it be static? These variables are only used in stm32-adc.c, so they should be static Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230312161733.470617-1-trix@redhat.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/stm32-adc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 45d4e79f8e55..1aadb2ad2cab 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -2588,7 +2588,7 @@ static const struct stm32_adc_cfg stm32f4_adc_cfg = { .irq_clear = stm32f4_adc_irq_clear, }; -const unsigned int stm32_adc_min_ts_h7[] = { 0, 0, 0, 4300, 9000 }; +static const unsigned int stm32_adc_min_ts_h7[] = { 0, 0, 0, 4300, 9000 }; static_assert(ARRAY_SIZE(stm32_adc_min_ts_h7) == STM32_ADC_INT_CH_NB); static const struct stm32_adc_cfg stm32h7_adc_cfg = { @@ -2607,7 +2607,7 @@ static const struct stm32_adc_cfg stm32h7_adc_cfg = { .ts_int_ch = stm32_adc_min_ts_h7, }; -const unsigned int stm32_adc_min_ts_mp1[] = { 100, 100, 100, 4300, 9800 }; +static const unsigned int stm32_adc_min_ts_mp1[] = { 100, 100, 100, 4300, 9800 }; static_assert(ARRAY_SIZE(stm32_adc_min_ts_mp1) == STM32_ADC_INT_CH_NB); static const struct stm32_adc_cfg stm32mp1_adc_cfg = { @@ -2627,7 +2627,7 @@ static const struct stm32_adc_cfg stm32mp1_adc_cfg = { .ts_int_ch = stm32_adc_min_ts_mp1, }; -const unsigned int stm32_adc_min_ts_mp13[] = { 100, 0, 0, 4300, 9800 }; +static const unsigned int stm32_adc_min_ts_mp13[] = { 100, 0, 0, 4300, 9800 }; static_assert(ARRAY_SIZE(stm32_adc_min_ts_mp13) == STM32_ADC_INT_CH_NB); static const struct stm32_adc_cfg stm32mp13_adc_cfg = { -- GitLab From 66f731db6fe7e42c3b8ac843b0cab49b5bdb1bce Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:27 +0100 Subject: [PATCH 0295/5631] power: supply: rt9455_charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/rt9455_charger.c:1725:34: error: ‘rt9455_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/rt9455_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/rt9455_charger.c b/drivers/power/supply/rt9455_charger.c index 31fb6526a1fd..0149e00f2bf8 100644 --- a/drivers/power/supply/rt9455_charger.c +++ b/drivers/power/supply/rt9455_charger.c @@ -1722,7 +1722,7 @@ static const struct i2c_device_id rt9455_i2c_id_table[] = { }; MODULE_DEVICE_TABLE(i2c, rt9455_i2c_id_table); -static const struct of_device_id rt9455_of_match[] = { +static const struct of_device_id rt9455_of_match[] __maybe_unused = { { .compatible = "richtek,rt9455", }, { }, }; -- GitLab From 9e2480d437f99aa511d260d1746f596927dc633f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:28 +0100 Subject: [PATCH 0296/5631] power: supply: twl4030_charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/twl4030_charger.c:1129:34: error: ‘twl_bci_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/twl4030_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c index 53a0ea5a61da..7adfd69fe649 100644 --- a/drivers/power/supply/twl4030_charger.c +++ b/drivers/power/supply/twl4030_charger.c @@ -1126,7 +1126,7 @@ static int twl4030_bci_remove(struct platform_device *pdev) return 0; } -static const struct of_device_id twl_bci_of_match[] = { +static const struct of_device_id twl_bci_of_match[] __maybe_unused = { {.compatible = "ti,twl4030-bci", }, { } }; -- GitLab From ea66715d30ea5824290a2a4da2604d5e59fea372 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:29 +0100 Subject: [PATCH 0297/5631] power: supply: lp8727_charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/lp8727_charger.c:601:34: error: ‘lp8727_dt_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/lp8727_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/lp8727_charger.c b/drivers/power/supply/lp8727_charger.c index e6c21377d53c..dc42d354b892 100644 --- a/drivers/power/supply/lp8727_charger.c +++ b/drivers/power/supply/lp8727_charger.c @@ -598,7 +598,7 @@ static void lp8727_remove(struct i2c_client *cl) lp8727_unregister_psy(pchg); } -static const struct of_device_id lp8727_dt_ids[] = { +static const struct of_device_id lp8727_dt_ids[] __maybe_unused = { { .compatible = "ti,lp8727", }, { } }; -- GitLab From 3c904b052c3823b110412b432d0dc6414bda3760 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:30 +0100 Subject: [PATCH 0298/5631] power: supply: ltc4162-l-charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/ltc4162-l-charger.c:911:34: error: ‘ltc4162l_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/ltc4162-l-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/ltc4162-l-charger.c b/drivers/power/supply/ltc4162-l-charger.c index 0e95c65369b8..285580845e2f 100644 --- a/drivers/power/supply/ltc4162-l-charger.c +++ b/drivers/power/supply/ltc4162-l-charger.c @@ -908,7 +908,7 @@ static const struct i2c_device_id ltc4162l_i2c_id_table[] = { }; MODULE_DEVICE_TABLE(i2c, ltc4162l_i2c_id_table); -static const struct of_device_id ltc4162l_of_match[] = { +static const struct of_device_id ltc4162l_of_match[] __maybe_unused = { { .compatible = "lltc,ltc4162-l", }, { }, }; -- GitLab From 1eab6b66acdd50415fa34903dd1753bf560cdf93 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:31 +0100 Subject: [PATCH 0299/5631] power: supply: bq24257_charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/bq24257_charger.c:1143:34: error: ‘bq24257_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq24257_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/bq24257_charger.c b/drivers/power/supply/bq24257_charger.c index 103ddc2b3def..45e4ba30da98 100644 --- a/drivers/power/supply/bq24257_charger.c +++ b/drivers/power/supply/bq24257_charger.c @@ -1140,7 +1140,7 @@ static const struct i2c_device_id bq24257_i2c_ids[] = { }; MODULE_DEVICE_TABLE(i2c, bq24257_i2c_ids); -static const struct of_device_id bq24257_of_match[] = { +static const struct of_device_id bq24257_of_match[] __maybe_unused = { { .compatible = "ti,bq24250", }, { .compatible = "ti,bq24251", }, { .compatible = "ti,bq24257", }, -- GitLab From 65cc52f3a91e5734cd1653da3b02ada94cda3ff6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:15:32 +0100 Subject: [PATCH 0300/5631] power: supply: bq25890_charger: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/power/supply/bq25890_charger.c:1625:34: error: ‘bq25890_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq25890_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index bfe08d7bfaf3..22cde35eb144 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -1622,7 +1622,7 @@ static const struct i2c_device_id bq25890_i2c_ids[] = { }; MODULE_DEVICE_TABLE(i2c, bq25890_i2c_ids); -static const struct of_device_id bq25890_of_match[] = { +static const struct of_device_id bq25890_of_match[] __maybe_unused = { { .compatible = "ti,bq25890", }, { .compatible = "ti,bq25892", }, { .compatible = "ti,bq25895", }, -- GitLab From ef6d10568ca9ca622a867e5d059982251bbccd6b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 21:06:52 +0100 Subject: [PATCH 0301/5631] power: reset: qcom-pon: drop of_match_ptr for ID table The Qualcomm SoC power-on driver is specific to ARCH_QCOM which depends on OF thus the driver is OF-only. It's of_device_id table is built unconditionally, thus of_match_ptr() for ID table does not make sense. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Reviewed-by: Marijn Suijten Signed-off-by: Sebastian Reichel --- drivers/power/reset/qcom-pon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/reset/qcom-pon.c b/drivers/power/reset/qcom-pon.c index 16bc01738be9..ebdcfb28c4a0 100644 --- a/drivers/power/reset/qcom-pon.c +++ b/drivers/power/reset/qcom-pon.c @@ -91,7 +91,7 @@ static struct platform_driver pm8916_pon_driver = { .probe = pm8916_pon_probe, .driver = { .name = "pm8916-pon", - .of_match_table = of_match_ptr(pm8916_pon_id_table), + .of_match_table = pm8916_pon_id_table, }, }; module_platform_driver(pm8916_pon_driver); -- GitLab From 83425c835e7dea49576aaac5fd4bff9b38ee0c32 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:35 -0600 Subject: [PATCH 0302/5631] power: supply: charger-manager: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Sebastian Reichel --- drivers/power/supply/charger-manager.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c index c9e8450c646f..5fa6ba7f41e1 100644 --- a/drivers/power/supply/charger-manager.c +++ b/drivers/power/supply/charger-manager.c @@ -1331,7 +1331,7 @@ static struct charger_desc *of_cm_parse_desc(struct device *dev) of_property_read_string(np, "cm-thermal-zone", &desc->thermal_zone); of_property_read_u32(np, "cm-battery-cold", &desc->temp_min); - if (of_get_property(np, "cm-battery-cold-in-minus", NULL)) + if (of_property_read_bool(np, "cm-battery-cold-in-minus")) desc->temp_min *= -1; of_property_read_u32(np, "cm-battery-hot", &desc->temp_max); of_property_read_u32(np, "cm-battery-temp-diff", &desc->temp_diff); -- GitLab From 5161ec200f5a84416667da853ff822d72df507f2 Mon Sep 17 00:00:00 2001 From: Hermes Zhang Date: Thu, 9 Mar 2023 14:41:03 +0800 Subject: [PATCH 0303/5631] power: supply: bq256xx: Support to disable charger To be able to control the charging process flexible, we need to able to disable the charger. This commit will allow to disable the charger by "echo 1 > /sys/class/power_supply/bq256xx-charger/charge_type" (1 = POWER_SUPPLY_CHARGE_TYPE_NONE) and enable the charger by set it to 2/3 (POWER_SUPPLY_CHARGE_TYPE_TRICKLE/POWER_SUPPLY_CHARGE_TYPE_FAST) Signed-off-by: Hermes Zhang Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq256xx_charger.c | 40 ++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index 9cf4936440c9..e624834ae66c 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -70,6 +70,9 @@ #define BQ25611D_VBATREG_THRESH_uV 4290000 #define BQ25618_VBATREG_THRESH_uV 4300000 +#define BQ256XX_CHG_CONFIG_MASK BIT(4) +#define BQ256XX_CHG_CONFIG_BIT_SHIFT 4 + #define BQ256XX_ITERM_MASK GENMASK(3, 0) #define BQ256XX_ITERM_STEP_uA 60000 #define BQ256XX_ITERM_OFFSET_uA 60000 @@ -259,6 +262,7 @@ struct bq256xx_device { * @bq256xx_set_iterm: pointer to instance specific set_iterm function * @bq256xx_set_iprechg: pointer to instance specific set_iprechg function * @bq256xx_set_vindpm: pointer to instance specific set_vindpm function + * @bq256xx_set_charge_type: pointer to instance specific set_charge_type function * * @bq256xx_def_ichg: default ichg value in microamps * @bq256xx_def_iindpm: default iindpm value in microamps @@ -290,6 +294,7 @@ struct bq256xx_chip_info { int (*bq256xx_set_iterm)(struct bq256xx_device *bq, int iterm); int (*bq256xx_set_iprechg)(struct bq256xx_device *bq, int iprechg); int (*bq256xx_set_vindpm)(struct bq256xx_device *bq, int vindpm); + int (*bq256xx_set_charge_type)(struct bq256xx_device *bq, int type); int bq256xx_def_ichg; int bq256xx_def_iindpm; @@ -449,6 +454,27 @@ static int bq256xx_get_state(struct bq256xx_device *bq, return 0; } +static int bq256xx_set_charge_type(struct bq256xx_device *bq, int type) +{ + int chg_config = 0; + + switch (type) { + case POWER_SUPPLY_CHARGE_TYPE_NONE: + chg_config = 0x0; + break; + case POWER_SUPPLY_CHARGE_TYPE_TRICKLE: + case POWER_SUPPLY_CHARGE_TYPE_FAST: + chg_config = 0x1; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(bq->regmap, BQ256XX_CHARGER_CONTROL_0, + BQ256XX_CHG_CONFIG_MASK, + (chg_config ? 1 : 0) << BQ256XX_CHG_CONFIG_BIT_SHIFT); +} + static int bq256xx_get_ichg_curr(struct bq256xx_device *bq) { unsigned int charge_current_limit; @@ -915,6 +941,12 @@ static int bq256xx_set_charger_property(struct power_supply *psy, return ret; break; + case POWER_SUPPLY_PROP_CHARGE_TYPE: + ret = bq->chip_info->bq256xx_set_charge_type(bq, val->intval); + if (ret) + return ret; + break; + default: break; } @@ -1197,6 +1229,7 @@ static int bq256xx_property_is_writeable(struct power_supply *psy, case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: case POWER_SUPPLY_PROP_STATUS: case POWER_SUPPLY_PROP_INPUT_VOLTAGE_LIMIT: + case POWER_SUPPLY_PROP_CHARGE_TYPE: return true; default: return false; @@ -1286,6 +1319,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq256xx_set_term_curr, .bq256xx_set_iprechg = bq256xx_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ2560X_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1316,6 +1350,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq256xx_set_term_curr, .bq256xx_set_iprechg = bq256xx_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ2560X_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1346,6 +1381,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq256xx_set_term_curr, .bq256xx_set_iprechg = bq256xx_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ2560X_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1376,6 +1412,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq256xx_set_term_curr, .bq256xx_set_iprechg = bq256xx_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ2560X_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1406,6 +1443,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq256xx_set_term_curr, .bq256xx_set_iprechg = bq256xx_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ25611D_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1436,6 +1474,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq25618_619_set_term_curr, .bq256xx_set_iprechg = bq25618_619_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ25618_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, @@ -1466,6 +1505,7 @@ static const struct bq256xx_chip_info bq256xx_chip_info_tbl[] = { .bq256xx_set_iterm = bq25618_619_set_term_curr, .bq256xx_set_iprechg = bq25618_619_set_prechrg_curr, .bq256xx_set_vindpm = bq256xx_set_input_volt_lim, + .bq256xx_set_charge_type = bq256xx_set_charge_type, .bq256xx_def_ichg = BQ25618_ICHG_DEF_uA, .bq256xx_def_iindpm = BQ256XX_IINDPM_DEF_uA, -- GitLab From babb3e6a8a8e5a61a65d4463610108808139b23e Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Wed, 8 Mar 2023 17:38:19 -0600 Subject: [PATCH 0304/5631] clk: samsung: exynos850: Make PMU_ALIVE_PCLK critical PMU_ALIVE_PCLK is needed for PMU registers access, and it must be always running, as not only the kernel accesses PMU registers. Make it critical to ensure that. Signed-off-by: Sam Protsenko Link: https://lore.kernel.org/r/20230308233822.31180-5-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/clk/samsung/clk-exynos850.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/samsung/clk-exynos850.c b/drivers/clk/samsung/clk-exynos850.c index 6ab5fa8c2ef3..98b23af7324d 100644 --- a/drivers/clk/samsung/clk-exynos850.c +++ b/drivers/clk/samsung/clk-exynos850.c @@ -612,7 +612,7 @@ static const struct samsung_gate_clock apm_gate_clks[] __initconst = { CLK_CON_GAT_GOUT_APM_APBIF_GPIO_ALIVE_PCLK, 21, CLK_IGNORE_UNUSED, 0), GATE(CLK_GOUT_PMU_ALIVE_PCLK, "gout_pmu_alive_pclk", "dout_apm_bus", - CLK_CON_GAT_GOUT_APM_APBIF_PMU_ALIVE_PCLK, 21, 0, 0), + CLK_CON_GAT_GOUT_APM_APBIF_PMU_ALIVE_PCLK, 21, CLK_IS_CRITICAL, 0), GATE(CLK_GOUT_SYSREG_APM_PCLK, "gout_sysreg_apm_pclk", "dout_apm_bus", CLK_CON_GAT_GOUT_APM_SYSREG_APM_PCLK, 21, 0, 0), }; -- GitLab From fed626db8bc240678fd0fa8078aa767ad21d47fd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 28 Feb 2023 13:57:47 +0100 Subject: [PATCH 0305/5631] s390/bp: add missing BPENTER to program check handler When leaving interpretive execution because of a program check BPENTER should be called like it is done on interrupt exit as well. Acked-by: Alexander Gordeev Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/entry.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 76a06f3d3671..2af5d7602ae8 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -355,6 +355,7 @@ ENTRY(pgm_check_handler) #if IS_ENABLED(CONFIG_KVM) # cleanup critical section for program checks in __sie64a OUTSIDE %r9,.Lsie_gmap,.Lsie_done,1f + BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) SIEEXIT lghi %r10,_PIF_GUEST_FAULT #endif -- GitLab From f33f2d4c7c80c641f6ca3dfe5e7dfe1f91543780 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 28 Feb 2023 13:57:48 +0100 Subject: [PATCH 0306/5631] s390/bp: remove TIF_ISOLATE_BP TIF_ISOLATE_BP is unused since it was introduced with commit 6b73044b2b00 ("s390: run user space and KVM guests with modified branch prediction"). Given that there is no use case remove it again. Acked-by: Alexander Gordeev Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/processor.h | 1 - arch/s390/include/asm/thread_info.h | 2 -- arch/s390/kernel/entry.S | 36 +++++++++++------------------ arch/s390/kernel/processor.c | 9 -------- 4 files changed, 13 insertions(+), 35 deletions(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index e98d9650764b..ddf3adde161c 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -329,7 +329,6 @@ static __always_inline void __noreturn disabled_wait(void) #define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL -extern int s390_isolate_bp(void); extern int s390_isolate_bp_guest(void); static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index b2ffcb4fe000..f19e6f5ec367 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -70,7 +70,6 @@ void arch_setup_new_exec(void); #define TIF_PATCH_PENDING 5 /* pending live patching update */ #define TIF_PGSTE 6 /* New mm's will use 4K page tables */ #define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */ -#define TIF_ISOLATE_BP 8 /* Run process with isolated BP */ #define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ #define TIF_PER_TRAP 10 /* Need to handle PER trap on exit to usermode */ @@ -94,7 +93,6 @@ void arch_setup_new_exec(void); #define _TIF_UPROBE BIT(TIF_UPROBE) #define _TIF_GUARDED_STORAGE BIT(TIF_GUARDED_STORAGE) #define _TIF_PATCH_PENDING BIT(TIF_PATCH_PENDING) -#define _TIF_ISOLATE_BP BIT(TIF_ISOLATE_BP) #define _TIF_ISOLATE_BP_GUEST BIT(TIF_ISOLATE_BP_GUEST) #define _TIF_PER_TRAP BIT(TIF_PER_TRAP) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 2af5d7602ae8..d8890a6f5dee 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -227,7 +227,7 @@ ENTRY(__sie64a) TSTMSK __LC_CPU_FLAGS,_CIF_FPU jo .Lsie_skip # exit if fp/vx regs changed lg %r14,__SF_SIE_CONTROL_PHYS(%r15) # get sie block phys addr - BPEXIT __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + BPEXIT __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST .Lsie_entry: sie 0(%r14) # Let the next instruction be NOP to avoid triggering a machine check @@ -235,7 +235,7 @@ ENTRY(__sie64a) nopr 7 .Lsie_leave: BPOFF - BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST .Lsie_skip: lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE @@ -291,11 +291,9 @@ ENTRY(system_call) .Lsysc_per: STBEAR __LC_LAST_BREAK lctlg %c1,%c1,__LC_KERNEL_ASCE - lg %r12,__LC_CURRENT lg %r15,__LC_KERNEL_STACK xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stmg %r0,%r7,STACK_FRAME_OVERHEAD+__PT_R0(%r15) - BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP # clear user controlled register to prevent speculative use xgr %r0,%r0 xgr %r1,%r1 @@ -314,7 +312,7 @@ ENTRY(system_call) brasl %r14,__do_syscall lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) - BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + BPON LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER @@ -329,7 +327,7 @@ ENTRY(ret_from_fork) brasl %r14,__ret_from_fork lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) - BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + BPON LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER @@ -344,7 +342,6 @@ ENTRY(pgm_check_handler) stpt __LC_SYS_ENTER_TIMER BPOFF stmg %r8,%r15,__LC_SAVE_AREA_SYNC - lg %r12,__LC_CURRENT lghi %r10,0 lmg %r8,%r9,__LC_PGM_OLD_PSW tmhh %r8,0x0001 # coming from user space? @@ -355,7 +352,7 @@ ENTRY(pgm_check_handler) #if IS_ENABLED(CONFIG_KVM) # cleanup critical section for program checks in __sie64a OUTSIDE %r9,.Lsie_gmap,.Lsie_done,1f - BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST SIEEXIT lghi %r10,_PIF_GUEST_FAULT #endif @@ -367,8 +364,7 @@ ENTRY(pgm_check_handler) aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) # CHECK_VMAP_STACK branches to stack_overflow or 4f CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f -3: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP - lg %r15,__LC_KERNEL_STACK +3: lg %r15,__LC_KERNEL_STACK 4: la %r11,STACK_FRAME_OVERHEAD(%r15) stg %r10,__PT_FLAGS(%r11) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) @@ -390,7 +386,7 @@ ENTRY(pgm_check_handler) tmhh %r8,0x0001 # returning to user space? jno .Lpgm_exit_kernel lctlg %c1,%c1,__LC_USER_ASCE - BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + BPON stpt __LC_EXIT_TIMER .Lpgm_exit_kernel: mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) @@ -420,20 +416,18 @@ ENTRY(\name) STBEAR __LC_LAST_BREAK BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC - lg %r12,__LC_CURRENT lmg %r8,%r9,\lc_old_psw tmhh %r8,0x0001 # interrupting from user ? jnz 1f #if IS_ENABLED(CONFIG_KVM) OUTSIDE %r9,.Lsie_gmap,.Lsie_done,0f - BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST SIEEXIT #endif 0: CHECK_STACK __LC_SAVE_AREA_ASYNC aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f -1: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP - lctlg %c1,%c1,__LC_KERNEL_ASCE +1: lctlg %c1,%c1,__LC_KERNEL_ASCE lg %r15,__LC_KERNEL_STACK 2: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) la %r11,STACK_FRAME_OVERHEAD(%r15) @@ -457,7 +451,7 @@ ENTRY(\name) tmhh %r8,0x0001 # returning to user ? jno 2f lctlg %c1,%c1,__LC_USER_ASCE - BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + BPON stpt __LC_EXIT_TIMER 2: LBEAR __PT_LAST_BREAK(%r11) lmg %r0,%r15,__PT_R0(%r11) @@ -502,7 +496,6 @@ ENTRY(mcck_int_handler) spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer LBEAR __LC_LAST_BREAK_SAVE_AREA-4095(%r1) # validate bear lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs - lg %r12,__LC_CURRENT lmg %r8,%r9,__LC_MCK_OLD_PSW TSTMSK __LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE jo .Lmcck_panic # yes -> rest of mcck code invalid @@ -531,16 +524,13 @@ ENTRY(mcck_int_handler) TSTMSK __LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID jno .Lmcck_panic #if IS_ENABLED(CONFIG_KVM) - OUTSIDE %r9,.Lsie_gmap,.Lsie_done,.Lmcck_stack + OUTSIDE %r9,.Lsie_gmap,.Lsie_done,.Lmcck_user OUTSIDE %r9,.Lsie_entry,.Lsie_leave,4f oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST -4: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) +4: BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST SIEEXIT - j .Lmcck_stack #endif .Lmcck_user: - BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP -.Lmcck_stack: lg %r15,__LC_MCCK_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) stctg %c1,%c1,__PT_CR1(%r11) @@ -568,7 +558,7 @@ ENTRY(mcck_int_handler) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? jno 0f - BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP + BPON stpt __LC_EXIT_TIMER 0: ALTERNATIVE "nop", __stringify(lghi %r12,__LC_LAST_BREAK_SAVE_AREA),193 LBEAR 0(%r12) diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index a194611ba88c..7e2878c9a036 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -365,15 +365,6 @@ const struct seq_operations cpuinfo_op = { .show = show_cpuinfo, }; -int s390_isolate_bp(void) -{ - if (!test_facility(82)) - return -EOPNOTSUPP; - set_thread_flag(TIF_ISOLATE_BP); - return 0; -} -EXPORT_SYMBOL(s390_isolate_bp); - int s390_isolate_bp_guest(void) { if (!test_facility(82)) -- GitLab From 9b63fd2fc8526e51444de35598927e406b1bb26f Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 28 Feb 2023 13:57:49 +0100 Subject: [PATCH 0307/5631] s390/bp: remove s390_isolate_bp_guest() s390_isolate_bp_guest() is unused. Remove it. Reviewed-by: Alexander Gordeev Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/processor.h | 2 -- arch/s390/kernel/processor.c | 9 --------- 2 files changed, 11 deletions(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index ddf3adde161c..dd95fddd5dda 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -329,8 +329,6 @@ static __always_inline void __noreturn disabled_wait(void) #define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL -extern int s390_isolate_bp_guest(void); - static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return arch_irqs_disabled_flags(regs->psw.mask); diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7e2878c9a036..0a999c8226d7 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -364,12 +364,3 @@ const struct seq_operations cpuinfo_op = { .stop = c_stop, .show = show_cpuinfo, }; - -int s390_isolate_bp_guest(void) -{ - if (!test_facility(82)) - return -EOPNOTSUPP; - set_thread_flag(TIF_ISOLATE_BP_GUEST); - return 0; -} -EXPORT_SYMBOL(s390_isolate_bp_guest); -- GitLab From 69a407bf81a8d70d51e1b7787da577e67447c9ea Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 28 Feb 2023 13:57:50 +0100 Subject: [PATCH 0308/5631] s390/bp: remove __bpon() There is no point in changing branch prediction state of a cpu shortly before it enters stop state. Therefore remove __bpon(). Acked-by: Alexander Gordeev Reviewed-by: Sven Schnelle Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/processor.h | 1 - arch/s390/kernel/entry.S | 18 ++++++------------ arch/s390/kernel/ipl.c | 1 - arch/s390/kernel/smp.c | 2 -- 4 files changed, 6 insertions(+), 16 deletions(-) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index dd95fddd5dda..80ac0c1034dc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -99,7 +99,6 @@ void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; extern void execve_tail(void); -extern void __bpon(void); unsigned long vdso_size(void); /* diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index d8890a6f5dee..58b85aedca22 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -159,21 +159,15 @@ _LPP_OFFSET = __LC_LPP .section .kprobes.text, "ax" .Ldummy: /* - * This nop exists only in order to avoid that __bpon starts at - * the beginning of the kprobes text section. In that case we would - * have several symbols at the same address. E.g. objdump would take - * an arbitrary symbol name when disassembling this code. - * With the added nop in between the __bpon symbol is unique - * again. + * The following nop exists only in order to avoid that the next + * symbol starts at the beginning of the kprobes text section. + * In that case there would be several symbols at the same address. + * E.g. objdump would take an arbitrary symbol when disassembling + * the code. + * With the added nop in between this cannot happen. */ nop 0 -ENTRY(__bpon) - .globl __bpon - BPON - BR_EX %r14 -ENDPROC(__bpon) - /* * Scheduler resume function, called by switch_to * gpr2 = (task_struct *) prev diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 5f0f5c86963a..0f91cd401eef 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -649,7 +649,6 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { - __bpon(); diag308(DIAG308_LOAD_CLEAR, NULL); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index d4888453bbf8..0126c5f6b904 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -348,7 +348,6 @@ static void pcpu_delegate(struct pcpu *pcpu, abs_lc->restart_source = source_cpu; put_abs_lowcore(abs_lc); } - __bpon(); asm volatile( "0: sigp 0,%0,%2 # sigp restart to target cpu\n" " brc 2,0b # busy, try again\n" @@ -986,7 +985,6 @@ void __cpu_die(unsigned int cpu) void __noreturn cpu_die(void) { idle_task_exit(); - __bpon(); pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } -- GitLab From 72c2112ce9d72e6c40dd893f32187a3d34453113 Mon Sep 17 00:00:00 2001 From: Yu Zhe Date: Fri, 3 Mar 2023 13:21:55 +0800 Subject: [PATCH 0309/5631] s390/zcrypt: remove unnecessary (void *) conversions Pointer variables of void * type do not require type cast. Signed-off-by: Yu Zhe Reviewed-by: Muhammad Usama Anjum Link: https://lore.kernel.org/r/20230303052155.21072-1-yuzhe@nfschina.com Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_msgtype6.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 5ad251477593..a2e7fe33ba62 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -926,8 +926,7 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86x_reply *t86r; int len; @@ -982,8 +981,7 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, .type = TYPE82_RSP_CODE, .reply_code = REP82_ERROR_MACHINE_FAILURE, }; - struct response_type *resp_type = - (struct response_type *)msg->private; + struct response_type *resp_type = msg->private; struct type86_ep11_reply *t86r; int len; @@ -1157,7 +1155,7 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, struct ap_message *ap_msg) { int rc; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct CPRBX cprbx; @@ -1240,7 +1238,7 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * { int rc; unsigned int lfmt; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; struct { struct type6_hdr hdr; struct ep11_cprb cprbx; @@ -1359,7 +1357,7 @@ static long zcrypt_msgtype6_rng(struct zcrypt_queue *zq, short int verb_length; short int key_length; } __packed * msg = ap_msg->msg; - struct response_type *rtype = (struct response_type *)(ap_msg->private); + struct response_type *rtype = ap_msg->private; int rc; msg->cprbx.domain = AP_QID_QUEUE(zq->queue->qid); -- GitLab From fb77914a692d550a5bb0c7f71eac40e6da9c0e6d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 6 Mar 2023 00:55:33 +0000 Subject: [PATCH 0310/5631] s390: trim ancient junk from copy_thread() Setting and ->psw.addr in childregs of kernel thread is a rudiment of the old kernel_thread()/kernel_execve() implementation. Mainline hadn't been using them since 2012. And clarify the assignments to frame->sf.gprs - the array stores grp6..gpr15 values to be set by __switch_to(), so frame->sf.gprs[5] actually affects grp11, etc. Better spell that as frame->sf.gprs[11 - 6]... Signed-off-by: Al Viro Link: https://lore.kernel.org/r/ZAU6BYFisE8evmYf@ZenIV Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/process.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 67df64ef4839..87ca3a727604 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -136,12 +136,12 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.last_break = 1; frame->sf.back_chain = 0; - frame->sf.gprs[5] = (unsigned long)frame + sizeof(struct stack_frame); - frame->sf.gprs[6] = (unsigned long)p; + frame->sf.gprs[11 - 6] = (unsigned long)&frame->childregs; + frame->sf.gprs[12 - 6] = (unsigned long)p; /* new return point is ret_from_fork */ - frame->sf.gprs[8] = (unsigned long)ret_from_fork; + frame->sf.gprs[14 - 6] = (unsigned long)ret_from_fork; /* fake return stack for resume(), don't go back to schedule */ - frame->sf.gprs[9] = (unsigned long)frame; + frame->sf.gprs[15 - 6] = (unsigned long)frame; /* Store access registers to kernel stack of new process. */ if (unlikely(args->fn)) { @@ -149,8 +149,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) memset(&frame->childregs, 0, sizeof(struct pt_regs)); frame->childregs.psw.mask = PSW_KERNEL_BITS | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; - frame->childregs.psw.addr = - (unsigned long)__ret_from_fork; frame->childregs.gprs[9] = (unsigned long)args->fn; frame->childregs.gprs[10] = (unsigned long)args->fn_arg; frame->childregs.orig_gpr2 = -1; -- GitLab From 029a4f4b9555ddb47f38f9589fd6d43277efb9c6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 9 Mar 2023 20:12:28 +0100 Subject: [PATCH 0311/5631] s390/setup: always inline gen_lpswe() gen_lpswe() contains a BUILD_BUG_ON() statement which depends on a function parameter. If the compiler decides to generate a not inlined function this will lead to a build error, even if all call sites pass a valid parameter. To avoid this always inline gen_lpswe(). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/setup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 3a1f8825bc7d..5271bb278cfa 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -164,7 +164,7 @@ struct oldmem_data { }; extern struct oldmem_data oldmem_data; -static inline u32 gen_lpswe(unsigned long addr) +static __always_inline u32 gen_lpswe(unsigned long addr) { BUILD_BUG_ON(addr > 0xfff); return 0xb2b20000 | addr; -- GitLab From ae83707f39e1b8f2a15af3868bba25ce4fa93364 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:12 +0100 Subject: [PATCH 0312/5631] s390/pci: only add specific device in zpci_bus_scan_device() As the name suggests zpci_bus_scan_device() is used to scan a specific device and thus pci_bus_add_device() for that device is sufficient. Furthermore move this call inside the rescan/remove locking. Suggested-by: Bjorn Helgaas Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Link: https://lore.kernel.org/r/20230306151014.60913-3-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_bus.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..465399dc4a53 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -87,9 +87,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev) if (!pdev) return -ENODEV; - pci_bus_add_device(pdev); pci_lock_rescan_remove(); - pci_bus_add_devices(zdev->zbus->bus); + pci_bus_add_device(pdev); pci_unlock_rescan_remove(); return 0; -- GitLab From b881208dcdae311734f172d61cf9ae6fcb108389 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:13 +0100 Subject: [PATCH 0313/5631] s390/pci: remove redundant pci_bus_add_devices() on new bus The pci_bus_add_devices() call in zpci_bus_create_pci_bus() is without function since at this point no device could have been added to the freshly created PCI bus. Suggested-by: Bjorn Helgaas Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Link: https://lore.kernel.org/r/20230306151014.60913-4-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci_bus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 465399dc4a53..df2e27fbd376 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -212,7 +212,6 @@ static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *fr, s } zbus->bus = bus; - pci_bus_add_devices(bus); return 0; } -- GitLab From 45e5f0c017e0d0dabb952db63428e31eca6be87e Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:14 +0100 Subject: [PATCH 0314/5631] s390/pci: clean up left over special treatment for function zero Prior to commit 960ac3626487 ("s390/pci: allow zPCI zbus without a function zero") enabling and scanning a PCI function had to potentially be postponed until the function with devfn zero on that bus was plugged. While the commit removed the waiting itself extra code to scan all functions on the PCI bus once function zero appeared was missed. Remove that code and the outdated comments about waiting for function zero. Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Link: https://lore.kernel.org/r/20230306151014.60913-5-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci.c | 23 +++-------------------- arch/s390/pci/pci_bus.c | 7 ++----- 2 files changed, 5 insertions(+), 25 deletions(-) diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..ed6ff20dd0f6 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -870,32 +870,15 @@ bool zpci_is_device_configured(struct zpci_dev *zdev) * @fh: The general function handle supplied by the platform * * Given a device in the configuration state Configured, enables, scans and - * adds it to the common code PCI subsystem if possible. If the PCI device is - * parked because we can not yet create a PCI bus because we have not seen - * function 0, it is ignored but will be scanned once function 0 appears. - * If any failure occurs, the zpci_dev is left disabled. + * adds it to the common code PCI subsystem if possible. If any failure occurs, + * the zpci_dev is left disabled. * * Return: 0 on success, or an error code otherwise */ int zpci_scan_configured_device(struct zpci_dev *zdev, u32 fh) { - int rc; - zpci_update_fh(zdev, fh); - /* the PCI function will be scanned once function 0 appears */ - if (!zdev->zbus->bus) - return 0; - - /* For function 0 on a multi-function bus scan whole bus as we might - * have to pick up existing functions waiting for it to allow creating - * the PCI bus - */ - if (zdev->devfn == 0 && zdev->zbus->multifunction) - rc = zpci_bus_scan_bus(zdev->zbus); - else - rc = zpci_bus_scan_device(zdev); - - return rc; + return zpci_bus_scan_device(zdev); } /** diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index df2e27fbd376..a9875feca293 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -131,11 +131,8 @@ void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error) * @zbus: the zbus to be scanned * * Enables and scans all PCI functions on the bus making them available to the - * common PCI code. If there is no function 0 on the zbus nothing is scanned. If - * a function does not have a slot yet because it was added to the zbus before - * function 0 the slot is created. If a PCI function fails to be initialized - * an error will be returned but attempts will still be made for all other - * functions on the bus. + * common PCI code. If a PCI function fails to be initialized an error will be + * returned but attempts will still be made for all other functions on the bus. * * Return: 0 on success, an error value otherwise */ -- GitLab From 3f2d4560898bb7cf579fb78c39f7c77368560414 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:27:02 +0100 Subject: [PATCH 0315/5631] pinctrl: sx150x: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/pinctrl/pinctrl-sx150x.c:833:34: error: ‘sx150x_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312132702.352832-1-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-sx150x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-sx150x.c b/drivers/pinctrl/pinctrl-sx150x.c index 0b5ff99641e1..87fcbfbf49b7 100644 --- a/drivers/pinctrl/pinctrl-sx150x.c +++ b/drivers/pinctrl/pinctrl-sx150x.c @@ -1250,7 +1250,7 @@ static int sx150x_probe(struct i2c_client *client) static struct i2c_driver sx150x_driver = { .driver = { .name = "sx150x-pinctrl", - .of_match_table = of_match_ptr(sx150x_of_match), + .of_match_table = sx150x_of_match, }, .probe_new = sx150x_probe, .id_table = sx150x_id, -- GitLab From f7fc5768e57cc18c24783c524f4e80e680dc4fc4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 10 Mar 2023 15:02:35 +0100 Subject: [PATCH 0316/5631] pinctrl: s32cc: fix !CONFIG_PM_SLEEP build error The declaration of s32_pinctrl_suspend/s32_pinctrl_resume is hidden in an #ifdef, causing a compilation failure when CONFIG_PM_SLEEP is disabled: drivers/pinctrl/nxp/pinctrl-s32g2.c:754:38: error: 's32_pinctrl_suspend' undeclared here (not in a function); did you mean 's32_pinctrl_probe'? drivers/pinctrl/nxp/pinctrl-s32g2.c:754:9: note: in expansion of macro 'SET_LATE_SYSTEM_SLEEP_PM_OPS' 754 | SET_LATE_SYSTEM_SLEEP_PM_OPS(s32_pinctrl_suspend, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ Remove the bogus #ifdef and __maybe_unused annation on the global functions, and instead use the proper LATE_SYSTEM_SLEEP_PM_OPS() macro to pick set the function pointer. As the function definition is still in the #ifdef block, this leads to the correct code in all configurations. Fixes: fd84aaa8173d ("pinctrl: add NXP S32 SoC family support") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230310140250.359147-1-arnd@kernel.org Signed-off-by: Linus Walleij --- drivers/pinctrl/nxp/pinctrl-s32.h | 6 ++---- drivers/pinctrl/nxp/pinctrl-s32cc.c | 4 ++-- drivers/pinctrl/nxp/pinctrl-s32g2.c | 3 +-- 3 files changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/pinctrl/nxp/pinctrl-s32.h b/drivers/pinctrl/nxp/pinctrl-s32.h index b6d530a62051..545bf16b988d 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32.h +++ b/drivers/pinctrl/nxp/pinctrl-s32.h @@ -68,8 +68,6 @@ struct s32_pinctrl_soc_info { int s32_pinctrl_probe(struct platform_device *pdev, struct s32_pinctrl_soc_info *info); -#ifdef CONFIG_PM_SLEEP -int __maybe_unused s32_pinctrl_resume(struct device *dev); -int __maybe_unused s32_pinctrl_suspend(struct device *dev); -#endif +int s32_pinctrl_resume(struct device *dev); +int s32_pinctrl_suspend(struct device *dev); #endif /* __DRIVERS_PINCTRL_S32_H */ diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index 2c945523af80..e1da332433a3 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -658,7 +658,7 @@ static bool s32_pinctrl_should_save(struct s32_pinctrl *ipctl, return false; } -int __maybe_unused s32_pinctrl_suspend(struct device *dev) +int s32_pinctrl_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct s32_pinctrl *ipctl = platform_get_drvdata(pdev); @@ -685,7 +685,7 @@ int __maybe_unused s32_pinctrl_suspend(struct device *dev) return 0; } -int __maybe_unused s32_pinctrl_resume(struct device *dev) +int s32_pinctrl_resume(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct s32_pinctrl *ipctl = platform_get_drvdata(pdev); diff --git a/drivers/pinctrl/nxp/pinctrl-s32g2.c b/drivers/pinctrl/nxp/pinctrl-s32g2.c index 7dd0b4f8904d..5028f4adc389 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32g2.c +++ b/drivers/pinctrl/nxp/pinctrl-s32g2.c @@ -751,8 +751,7 @@ static int s32g_pinctrl_probe(struct platform_device *pdev) } static const struct dev_pm_ops s32g_pinctrl_pm_ops = { - SET_LATE_SYSTEM_SLEEP_PM_OPS(s32_pinctrl_suspend, - s32_pinctrl_resume) + LATE_SYSTEM_SLEEP_PM_OPS(s32_pinctrl_suspend, s32_pinctrl_resume) }; static struct platform_driver s32g_pinctrl_driver = { -- GitLab From d61955da3256d506cc201a9296723bf59f0d51ed Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 12:51:27 +0000 Subject: [PATCH 0317/5631] pinctrl: at91: Make the irqchip immutable To help gpiolib not fiddle around with the internals of the irqchip flag the chip as immutable, adding the calls into the gpiolib core required to do so. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230216-gpio-at91-immutable-v2-1-326ef362dbc7@kernel.org Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 79b7061fc8f3..1e083fc7666b 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -1526,6 +1526,20 @@ static void at91_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) #define at91_gpio_dbg_show NULL #endif +static int gpio_irq_request_resources(struct irq_data *d) +{ + struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); + + return gpiochip_lock_as_irq(&at91_gpio->chip, irqd_to_hwirq(d)); +} + +static void gpio_irq_release_resources(struct irq_data *d) +{ + struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); + + gpiochip_unlock_as_irq(&at91_gpio->chip, irqd_to_hwirq(d)); +} + /* Several AIC controller irqs are dispatched through this GPIO handler. * To use any AT91_PIN_* as an externally triggered IRQ, first call * at91_set_gpio_input() then maybe enable its glitch filter. @@ -1545,6 +1559,9 @@ static void gpio_irq_mask(struct irq_data *d) struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); void __iomem *pio = at91_gpio->regbase; unsigned mask = 1 << d->hwirq; + unsigned gpio = irqd_to_hwirq(d); + + gpiochip_disable_irq(&at91_gpio->chip, gpio); if (pio) writel_relaxed(mask, pio + PIO_IDR); @@ -1555,6 +1572,9 @@ static void gpio_irq_unmask(struct irq_data *d) struct at91_gpio_chip *at91_gpio = irq_data_get_irq_chip_data(d); void __iomem *pio = at91_gpio->regbase; unsigned mask = 1 << d->hwirq; + unsigned gpio = irqd_to_hwirq(d); + + gpiochip_enable_irq(&at91_gpio->chip, gpio); if (pio) writel_relaxed(mask, pio + PIO_IER); @@ -1721,12 +1741,15 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev, at91_gpio->pioc_hwirq = irqd_to_hwirq(d); gpio_irqchip->name = "GPIO"; + gpio_irqchip->irq_request_resources = gpio_irq_request_resources; + gpio_irqchip->irq_release_resources = gpio_irq_release_resources; gpio_irqchip->irq_ack = gpio_irq_ack; gpio_irqchip->irq_disable = gpio_irq_mask; gpio_irqchip->irq_mask = gpio_irq_mask; gpio_irqchip->irq_unmask = gpio_irq_unmask; gpio_irqchip->irq_set_wake = pm_ptr(gpio_irq_set_wake); gpio_irqchip->irq_set_type = at91_gpio->ops->irq_type; + gpio_irqchip->flags = IRQCHIP_IMMUTABLE; /* Disable irqs of this PIO controller */ writel_relaxed(~0, at91_gpio->regbase + PIO_IDR); @@ -1737,7 +1760,7 @@ static int at91_gpio_of_irq_setup(struct platform_device *pdev, * interrupt. */ girq = &at91_gpio->chip.irq; - girq->chip = gpio_irqchip; + gpio_irq_chip_set_chip(girq, gpio_irqchip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_edge_irq; -- GitLab From 5361ebe94a614c36198f26c1d006a65b367a1c3a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 12:51:28 +0000 Subject: [PATCH 0318/5631] pinctrl: at91: Remove pioc_index from struct at91_gpio_chip The pioc_idx member of struct at91_gpio_chip is write only, just remove it. Reviewed-by: Claudiu Beznea Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230216-gpio-at91-immutable-v2-2-326ef362dbc7@kernel.org Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-at91.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c index 1e083fc7666b..871209c24153 100644 --- a/drivers/pinctrl/pinctrl-at91.c +++ b/drivers/pinctrl/pinctrl-at91.c @@ -42,7 +42,6 @@ struct at91_pinctrl_mux_ops; * @next: bank sharing same clock * @pioc_hwirq: PIO bank interrupt identifier on AIC * @pioc_virq: PIO bank Linux virtual interrupt - * @pioc_idx: PIO bank index * @regbase: PIO bank virtual address * @clock: associated clock * @ops: at91 pinctrl mux ops @@ -56,7 +55,6 @@ struct at91_gpio_chip { struct at91_gpio_chip *next; int pioc_hwirq; int pioc_virq; - int pioc_idx; void __iomem *regbase; struct clk *clock; const struct at91_pinctrl_mux_ops *ops; @@ -1849,7 +1847,6 @@ static int at91_gpio_probe(struct platform_device *pdev) at91_chip->ops = of_device_get_match_data(dev); at91_chip->pioc_virq = irq; - at91_chip->pioc_idx = alias_idx; at91_chip->clock = devm_clk_get_enabled(dev, NULL); if (IS_ERR(at91_chip->clock)) -- GitLab From 29f6e7e379fd529611a365a1aaa30e9f82e6f024 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Mar 2023 22:36:51 +0100 Subject: [PATCH 0319/5631] pinctrl: qcom: msm8998: Add MPM pin mappings Add MPM <-> TLMM pin mappings to allow for waking up the AP from sleep through MPM-connected pins. Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230308213651.647098-1-konrad.dybcio@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-msm8998.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/pinctrl/qcom/pinctrl-msm8998.c b/drivers/pinctrl/qcom/pinctrl-msm8998.c index a05f41fe2706..1a061bc9b8fa 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm8998.c +++ b/drivers/pinctrl/qcom/pinctrl-msm8998.c @@ -1503,6 +1503,18 @@ static const struct msm_pingroup msm8998_groups[] = { UFS_RESET(ufs_reset, 0x19d000), }; +static const struct msm_gpio_wakeirq_map msm8998_mpm_map[] = { + { 1, 3 }, { 5, 4 }, { 9, 5 }, { 11, 6 }, { 22, 8 }, { 24, 9 }, { 26, 10 }, + { 34, 11 }, { 36, 12 }, { 37, 13 }, { 38, 14 }, { 40, 15 }, { 42, 16 }, { 46, 17 }, + { 50, 18 }, { 53, 19 }, { 54, 20 }, { 56, 21 }, { 57, 22 }, { 58, 23 }, { 59, 24 }, + { 60, 25 }, { 61, 26 }, { 62, 27 }, { 63, 28 }, { 64, 29 }, { 66, 7 }, { 71, 30 }, + { 73, 31 }, { 77, 32 }, { 78, 33 }, { 79, 34 }, { 80, 35 }, { 82, 36 }, { 86, 37 }, + { 91, 38 }, { 92, 39 }, { 95, 40 }, { 97, 41 }, { 101, 42 }, { 104, 43 }, { 106, 44 }, + { 108, 45 }, { 110, 48 }, { 112, 46 }, { 113, 47 }, { 115, 51 }, { 116, 54 }, { 117, 55 }, + { 118, 56 }, { 119, 57 }, { 120, 58 }, { 121, 59 }, { 122, 60 }, { 123, 61 }, { 124, 62 }, + { 125, 63 }, { 126, 64 }, { 127, 50 }, { 129, 65 }, { 131, 66 }, { 132, 67 }, { 133, 68 }, +}; + static const struct msm_pinctrl_soc_data msm8998_pinctrl = { .pins = msm8998_pins, .npins = ARRAY_SIZE(msm8998_pins), @@ -1511,6 +1523,8 @@ static const struct msm_pinctrl_soc_data msm8998_pinctrl = { .groups = msm8998_groups, .ngroups = ARRAY_SIZE(msm8998_groups), .ngpios = 150, + .wakeirq_map = msm8998_mpm_map, + .nwakeirq_map = ARRAY_SIZE(msm8998_mpm_map), }; static int msm8998_pinctrl_probe(struct platform_device *pdev) -- GitLab From 163bfb0cb1f6fbf961cf912cbde57399ea1ae0e8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Mar 2023 16:49:46 +0100 Subject: [PATCH 0320/5631] pinctrl: qcom: lpass-lpi: set output value before enabling output As per Hardware Programming Guide, when configuring pin as output, set the pin value before setting output-enable (OE). Similar approach is in main SoC TLMM pin controller. Cc: Fixes: 6e261d1090d6 ("pinctrl: qcom: Add sm8250 lpass lpi pinctrl driver") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230309154949.658380-1-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 87920257bb73..27fc8b671954 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -221,6 +221,15 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, } } + /* + * As per Hardware Programming Guide, when configuring pin as output, + * set the pin value before setting output-enable (OE). + */ + if (output_enabled) { + val = u32_encode_bits(value ? 1 : 0, LPI_GPIO_VALUE_OUT_MASK); + lpi_gpio_write(pctrl, group, LPI_GPIO_VALUE_REG, val); + } + val = lpi_gpio_read(pctrl, group, LPI_GPIO_CFG_REG); u32p_replace_bits(&val, pullup, LPI_GPIO_PULL_MASK); @@ -230,11 +239,6 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, lpi_gpio_write(pctrl, group, LPI_GPIO_CFG_REG, val); - if (output_enabled) { - val = u32_encode_bits(value ? 1 : 0, LPI_GPIO_VALUE_OUT_MASK); - lpi_gpio_write(pctrl, group, LPI_GPIO_VALUE_REG, val); - } - return 0; } -- GitLab From 926cf596ce3eae2150fdc5b6517f4e0d0bbe6396 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Mar 2023 16:49:47 +0100 Subject: [PATCH 0321/5631] pinctrl: qcom: lpass-lpi: use consistent name for "group" variable The set_mux callback in SoC TLMM driver (pinctrl-msm.c) uses "group", not "group_num" for the number of the pin group. Other places of lpass-lpi also use "group", so let's be consistent for code readability. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230309154949.658380-2-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 27fc8b671954..bd32556d75a5 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -84,10 +84,10 @@ static int lpi_gpio_get_function_groups(struct pinctrl_dev *pctldev, } static int lpi_gpio_set_mux(struct pinctrl_dev *pctldev, unsigned int function, - unsigned int group_num) + unsigned int group) { struct lpi_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); - const struct lpi_pingroup *g = &pctrl->data->groups[group_num]; + const struct lpi_pingroup *g = &pctrl->data->groups[group]; u32 val; int i, pin = g->pin; -- GitLab From fae1466da92d6627b5c938064ad42dac2aa88cc4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Mar 2023 16:49:48 +0100 Subject: [PATCH 0322/5631] pinctrl: qcom: lpass-lpi: allow glitch-free output GPIO When choosing GPIO function for pins, use the same glitch-free method as main TLMM pinctrl-msm.c driver in msm_pinmux_set_mux(). This replicates the commit d21f4b7ffc22 ("pinctrl: qcom: Avoid glitching lines when we first mux to output") to LPASS pin controller with same justification. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230309154949.658380-3-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-lpass-lpi.c | 28 ++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index bd32556d75a5..fdb6585a9234 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -19,6 +19,8 @@ #include "pinctrl-lpass-lpi.h" +#define MAX_NR_GPIO 23 +#define GPIO_FUNC 0 #define MAX_LPI_NUM_CLKS 2 struct lpi_pinctrl { @@ -30,6 +32,7 @@ struct lpi_pinctrl { char __iomem *slew_base; struct clk_bulk_data clks[MAX_LPI_NUM_CLKS]; struct mutex slew_access_lock; + DECLARE_BITMAP(ever_gpio, MAX_NR_GPIO); const struct lpi_pinctrl_variant_data *data; }; @@ -100,6 +103,28 @@ static int lpi_gpio_set_mux(struct pinctrl_dev *pctldev, unsigned int function, return -EINVAL; val = lpi_gpio_read(pctrl, pin, LPI_GPIO_CFG_REG); + + /* + * If this is the first time muxing to GPIO and the direction is + * output, make sure that we're not going to be glitching the pin + * by reading the current state of the pin and setting it as the + * output. + */ + if (i == GPIO_FUNC && (val & LPI_GPIO_OE_MASK) && + !test_and_set_bit(group, pctrl->ever_gpio)) { + u32 io_val = lpi_gpio_read(pctrl, group, LPI_GPIO_VALUE_REG); + + if (io_val & LPI_GPIO_VALUE_IN_MASK) { + if (!(io_val & LPI_GPIO_VALUE_OUT_MASK)) + lpi_gpio_write(pctrl, group, LPI_GPIO_VALUE_REG, + io_val | LPI_GPIO_VALUE_OUT_MASK); + } else { + if (io_val & LPI_GPIO_VALUE_OUT_MASK) + lpi_gpio_write(pctrl, group, LPI_GPIO_VALUE_REG, + io_val & ~LPI_GPIO_VALUE_OUT_MASK); + } + } + u32p_replace_bits(&val, i, LPI_GPIO_FUNCTION_MASK); lpi_gpio_write(pctrl, pin, LPI_GPIO_CFG_REG, val); @@ -394,6 +419,9 @@ int lpi_pinctrl_probe(struct platform_device *pdev) if (!data) return -EINVAL; + if (WARN_ON(data->npins > MAX_NR_GPIO)) + return -EINVAL; + pctrl->data = data; pctrl->dev = &pdev->dev; -- GitLab From 10fe4a1399d259b380dafa0f669c0a209e4f8197 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 9 Mar 2023 16:49:49 +0100 Subject: [PATCH 0323/5631] pinctrl: qcom: sm8550-lpass-lpi: allow GPIO function All LPASS pins have basic GPIO function and most of the code is ready for that. Add missing glue pieces to allow LPASS pins to work as GPIO, which is going to be used on MTP8550 and QRD8550 boards. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230309154949.658380-4-krzysztof.kozlowski@linaro.org Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c index c2bdd936d27f..db1a46fee9c6 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8550-lpass-lpi.c @@ -102,6 +102,13 @@ static const struct pinctrl_pin_desc sm8550_lpi_pins[] = { PINCTRL_PIN(22, "gpio22"), }; +static const char * const gpio_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", + "gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", + "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", + "gpio22", +}; + static const char * const dmic1_clk_groups[] = { "gpio6" }; static const char * const dmic1_data_groups[] = { "gpio7" }; static const char * const dmic2_clk_groups[] = { "gpio8" }; @@ -168,6 +175,7 @@ static const struct lpi_pingroup sm8550_groups[] = { }; static const struct lpi_function sm8550_functions[] = { + LPI_FUNCTION(gpio), LPI_FUNCTION(dmic1_clk), LPI_FUNCTION(dmic1_data), LPI_FUNCTION(dmic2_clk), -- GitLab From c874ad879c2f29ebe040a34b974389875c0d81eb Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Mon, 27 Feb 2023 18:02:12 +0800 Subject: [PATCH 0324/5631] IB/hifi1: add a null check of kzalloc_node in hfi1_ipoib_txreq_init kzalloc_node may fails, check it and do the cleanup. Fixes: b1151b74ff68 ("IB/hfi1: Fix alloc failure with larger txqueuelen") Signed-off-by: Kang Chen Link: https://lore.kernel.org/r/20230227100212.910820-1-void0red@gmail.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index 5d9a7b09ca37..349eb4139136 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -737,10 +737,13 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) txq->tx_ring.shift = ilog2(tx_item_size); txq->tx_ring.avail = hfi1_ipoib_ring_hwat(txq); tx_ring = &txq->tx_ring; - for (j = 0; j < tx_ring_size; j++) + for (j = 0; j < tx_ring_size; j++) { hfi1_txreq_from_idx(tx_ring, j)->sdma_hdr = kzalloc_node(sizeof(*tx->sdma_hdr), GFP_KERNEL, priv->dd->node); + if (!hfi1_txreq_from_idx(tx_ring, j)->sdma_hdr) + goto free_txqs; + } netif_napi_add_tx(dev, &txq->napi, hfi1_ipoib_poll_tx_ring); } -- GitLab From 271bfcfb83a9f77cbae3d6e1a16e3c14132922f0 Mon Sep 17 00:00:00 2001 From: Daniil Dulov Date: Mon, 27 Feb 2023 01:17:51 -0800 Subject: [PATCH 0325/5631] RDMA/siw: Fix potential page_array out of range access When seg is equal to MAX_ARRAY, the loop should break, otherwise it will result in out of range access. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: b9be6f18cf9e ("rdma/siw: transmit path") Signed-off-by: Daniil Dulov Link: https://lore.kernel.org/r/20230227091751.589612-1-d.dulov@aladdin.ru Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/siw/siw_qp_tx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 05052b49107f..6bb9e9e81ff4 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -558,7 +558,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) data_len -= plen; fp_off = 0; - if (++seg > (int)MAX_ARRAY) { + if (++seg >= (int)MAX_ARRAY) { siw_dbg_qp(tx_qp(c_tx), "to many fragments\n"); siw_unmap_pages(iov, kmap_mask, seg-1); wqe->processed -= c_tx->bytes_unsent; -- GitLab From f2f6e1661d38fbce6163fc321395e9de24a9529b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 18 Feb 2023 10:57:05 -0800 Subject: [PATCH 0326/5631] IB/rdmavt: Fix target union member for rvt_post_one_wr() The "cplen" result used by the memcpy() into struct rvt_swqe "wqe" may be sized to 80 for struct rvt_ud_wr (which is member "ud_wr", not "wr" which is only 40 bytes in size). Change the destination union member so the compiler can use the correct bounds check. struct rvt_swqe { union { struct ib_send_wr wr; /* don't use wr.sg_list */ struct rvt_ud_wr ud_wr; ... }; ... }; Silences false positive memcpy() run-time warning: memcpy: detected field-spanning write (size 80) of single field "&wqe->wr" at drivers/infiniband/sw/rdmavt/qp.c:2043 (size 40) Reported-by: Zhang Yi Link: https://bugzilla.kernel.org/show_bug.cgi?id=216561 Cc: Dennis Dalessandro Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: linux-rdma@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230218185701.never.779-kees@kernel.org Reviewed-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rdmavt/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 3acab569fbb9..3f707e1fa517 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -2040,7 +2040,7 @@ static int rvt_post_one_wr(struct rvt_qp *qp, wqe = rvt_get_swqe_ptr(qp, qp->s_head); /* cplen has length from above */ - memcpy(&wqe->wr, wr, cplen); + memcpy(&wqe->ud_wr, wr, cplen); wqe->length = 0; j = 0; -- GitLab From c4dc24da5286742f8cc728379f6115c9e886a8a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:04 +0100 Subject: [PATCH 0327/5631] clk: qcom: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230312161512.2715500-23-u.kleine-koenig@pengutronix.de --- drivers/clk/qcom/apcs-msm8916.c | 6 ++---- drivers/clk/qcom/apcs-sdx55.c | 6 ++---- drivers/clk/qcom/clk-rpm.c | 5 ++--- drivers/clk/qcom/gcc-msm8960.c | 6 ++---- 4 files changed, 8 insertions(+), 15 deletions(-) diff --git a/drivers/clk/qcom/apcs-msm8916.c b/drivers/clk/qcom/apcs-msm8916.c index 89e0730810ac..ce57b333ec99 100644 --- a/drivers/clk/qcom/apcs-msm8916.c +++ b/drivers/clk/qcom/apcs-msm8916.c @@ -119,18 +119,16 @@ static int qcom_apcs_msm8916_clk_probe(struct platform_device *pdev) return ret; } -static int qcom_apcs_msm8916_clk_remove(struct platform_device *pdev) +static void qcom_apcs_msm8916_clk_remove(struct platform_device *pdev) { struct clk_regmap_mux_div *a53cc = platform_get_drvdata(pdev); clk_notifier_unregister(a53cc->pclk, &a53cc->clk_nb); - - return 0; } static struct platform_driver qcom_apcs_msm8916_clk_driver = { .probe = qcom_apcs_msm8916_clk_probe, - .remove = qcom_apcs_msm8916_clk_remove, + .remove_new = qcom_apcs_msm8916_clk_remove, .driver = { .name = "qcom-apcs-msm8916-clk", }, diff --git a/drivers/clk/qcom/apcs-sdx55.c b/drivers/clk/qcom/apcs-sdx55.c index e599f862ec44..d644e6e1f8b7 100644 --- a/drivers/clk/qcom/apcs-sdx55.c +++ b/drivers/clk/qcom/apcs-sdx55.c @@ -120,20 +120,18 @@ static int qcom_apcs_sdx55_clk_probe(struct platform_device *pdev) return ret; } -static int qcom_apcs_sdx55_clk_remove(struct platform_device *pdev) +static void qcom_apcs_sdx55_clk_remove(struct platform_device *pdev) { struct device *cpu_dev = get_cpu_device(0); struct clk_regmap_mux_div *a7cc = platform_get_drvdata(pdev); clk_notifier_unregister(a7cc->pclk, &a7cc->clk_nb); dev_pm_domain_detach(cpu_dev, true); - - return 0; } static struct platform_driver qcom_apcs_sdx55_clk_driver = { .probe = qcom_apcs_sdx55_clk_probe, - .remove = qcom_apcs_sdx55_clk_remove, + .remove_new = qcom_apcs_sdx55_clk_remove, .driver = { .name = "qcom-sdx55-acps-clk", }, diff --git a/drivers/clk/qcom/clk-rpm.c b/drivers/clk/qcom/clk-rpm.c index b1be5b664bf3..e723ddb99a44 100644 --- a/drivers/clk/qcom/clk-rpm.c +++ b/drivers/clk/qcom/clk-rpm.c @@ -591,10 +591,9 @@ static int rpm_clk_probe(struct platform_device *pdev) return ret; } -static int rpm_clk_remove(struct platform_device *pdev) +static void rpm_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static struct platform_driver rpm_clk_driver = { @@ -603,7 +602,7 @@ static struct platform_driver rpm_clk_driver = { .of_match_table = rpm_clk_match_table, }, .probe = rpm_clk_probe, - .remove = rpm_clk_remove, + .remove_new = rpm_clk_remove, }; static int __init rpm_clk_init(void) diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c index 9dd4e7ffa1f8..dbc7093ab9cc 100644 --- a/drivers/clk/qcom/gcc-msm8960.c +++ b/drivers/clk/qcom/gcc-msm8960.c @@ -3754,19 +3754,17 @@ static int gcc_msm8960_probe(struct platform_device *pdev) return 0; } -static int gcc_msm8960_remove(struct platform_device *pdev) +static void gcc_msm8960_remove(struct platform_device *pdev) { struct platform_device *tsens = platform_get_drvdata(pdev); if (tsens) platform_device_unregister(tsens); - - return 0; } static struct platform_driver gcc_msm8960_driver = { .probe = gcc_msm8960_probe, - .remove = gcc_msm8960_remove, + .remove_new = gcc_msm8960_remove, .driver = { .name = "gcc-msm8960", .of_match_table = gcc_msm8960_match_table, -- GitLab From ce48f955860db841eeb4bcf9bb973ea3ef177b3a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 2 Mar 2023 18:12:06 +0200 Subject: [PATCH 0328/5631] =?UTF-8?q?i3c:=20Correct=20reference=20to=20the?= =?UTF-8?q?=20I=C2=B2C=20device=20data=20type?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I²C peripheral devices that are connected to the controller are represented in the Linux kernel as objects of the struct i2c_client. Fix this in the header file. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230302161206.38106-1-andriy.shevchenko@linux.intel.com Signed-off-by: Alexandre Belloni --- include/linux/i3c/master.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 604a126b78c8..a12cda9dc715 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -22,9 +22,10 @@ #define I3C_BROADCAST_ADDR 0x7e #define I3C_MAX_ADDR GENMASK(6, 0) +struct i2c_client; + struct i3c_master_controller; struct i3c_bus; -struct i2c_device; struct i3c_device; /** -- GitLab From 1dae3f1df7005e27a0040855ce8b3c21c262e3b2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:25:35 +0100 Subject: [PATCH 0329/5631] i3c: dw: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/i3c/master/dw-i3c-master.c:1201:34: error: ‘dw_i3c_master_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312132535.352246-1-krzysztof.kozlowski@linaro.org Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 48954d3e6571..4859dd75388d 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1209,7 +1209,7 @@ static struct platform_driver dw_i3c_driver = { .remove = dw_i3c_remove, .driver = { .name = "dw-i3c-master", - .of_match_table = of_match_ptr(dw_i3c_master_of_match), + .of_match_table = dw_i3c_master_of_match, }, }; module_platform_driver(dw_i3c_driver); -- GitLab From 07d85ba9d04e1ebd282f656a29ddf08c5b7b32a2 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 1 Mar 2023 07:04:13 -0800 Subject: [PATCH 0330/5631] perf record: Fix "read LOST count failed" msg with sample read Hundreds of "read LOST count failed" error messages may be displayed, when the below command is launched. perf record -e '{cpu/mem-loads-aux/,cpu/event=0xcd,umask=0x1/}:S' -a According to the commit 89e3106fa25fb1b6 ("libperf: Handle read format in perf_evsel__read()"), the PERF_FORMAT_GROUP is only available for the leader. However, the record__read_lost_samples() goes through every entry of an evlist, which includes both leader and member. The member event errors out and triggers the error message. Since there may be hundreds of CPUs on a server, the message will be printed hundreds of times, which is very annoying. The message itself is correct, but the pr_err is a overkill. Other error messages in the record__read_lost_samples() are all pr_debug. To make the output format consistent, change the pr_err("read LOST count failed\n"); to pr_debug("read LOST count failed\n");. User can still get the message via -v option. Fixes: e3a23261ad06d598 ("perf record: Read and inject LOST_SAMPLES events") Signed-off-by: Kan Liang Acked-by: Namhyung Kim Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230301150413.27011-1-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 8374117e66f6..be7c0c29d15b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1866,7 +1866,7 @@ static void __record__read_lost_samples(struct record *rec, struct evsel *evsel, int id_hdr_size; if (perf_evsel__read(&evsel->core, cpu_idx, thread_idx, &count) < 0) { - pr_err("read LOST count failed\n"); + pr_debug("read LOST count failed\n"); return; } -- GitLab From cb4b9e6813f9243095932c867ff16a7dffa02102 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 2 Mar 2023 11:11:45 +0800 Subject: [PATCH 0331/5631] perf record: Reuse target::initial_delay This just simply replace record_opts::initial_delay with target::initial_delay. Nothing else is changed. Signed-off-by: Changbin Du Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Hui Wang Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230302031146.2801588-3-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 12 ++++++------ tools/perf/builtin-trace.c | 8 ++++---- tools/perf/util/evlist.c | 6 +++--- tools/perf/util/evsel.c | 2 +- tools/perf/util/record.h | 1 - 5 files changed, 14 insertions(+), 15 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index be7c0c29d15b..fb8aab0cedd0 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1292,7 +1292,7 @@ static int record__open(struct record *rec) * dummy event so that we can track PERF_RECORD_MMAP to cover the delay * of waiting or event synthesis. */ - if (opts->initial_delay || target__has_cpu(&opts->target) || + if (opts->target.initial_delay || target__has_cpu(&opts->target) || perf_pmu__has_hybrid()) { pos = evlist__get_tracking_event(evlist); if (!evsel__is_dummy_event(pos)) { @@ -1307,7 +1307,7 @@ static int record__open(struct record *rec) * Enable the dummy event when the process is forked for * initial_delay, immediately for system wide. */ - if (opts->initial_delay && !pos->immediate && + if (opts->target.initial_delay && !pos->immediate && !target__has_cpu(&opts->target)) pos->core.attr.enable_on_exec = 1; else @@ -2522,7 +2522,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) * (apart from group members) have enable_on_exec=1 set, * so don't spoil it by prematurely enabling them. */ - if (!target__none(&opts->target) && !opts->initial_delay) + if (!target__none(&opts->target) && !opts->target.initial_delay) evlist__enable(rec->evlist); /* @@ -2574,10 +2574,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) evlist__start_workload(rec->evlist); } - if (opts->initial_delay) { + if (opts->target.initial_delay) { pr_info(EVLIST_DISABLED_MSG); - if (opts->initial_delay > 0) { - usleep(opts->initial_delay * USEC_PER_MSEC); + if (opts->target.initial_delay > 0) { + usleep(opts->target.initial_delay * USEC_PER_MSEC); evlist__enable(rec->evlist); pr_info(EVLIST_ENABLED_MSG); } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 610fb60b1c0d..b363c609818b 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -3993,14 +3993,14 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_mmap; - if (!target__none(&trace->opts.target) && !trace->opts.initial_delay) + if (!target__none(&trace->opts.target) && !trace->opts.target.initial_delay) evlist__enable(evlist); if (forks) evlist__start_workload(evlist); - if (trace->opts.initial_delay) { - usleep(trace->opts.initial_delay * 1000); + if (trace->opts.target.initial_delay) { + usleep(trace->opts.target.initial_delay * 1000); evlist__enable(evlist); } @@ -4788,7 +4788,7 @@ int cmd_trace(int argc, const char **argv) "per thread proc mmap processing timeout in ms"), OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only", trace__parse_cgroups), - OPT_INTEGER('D', "delay", &trace.opts.initial_delay, + OPT_INTEGER('D', "delay", &trace.opts.target.initial_delay, "ms to wait before starting measurement after program " "start"), OPTS_EVSWITCH(&trace.evswitch), diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 817df2504a1e..9e4b2bb0e6fa 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -2262,8 +2262,8 @@ int evlist__parse_event_enable_time(struct evlist *evlist, struct record_opts *o if (unset) return 0; - opts->initial_delay = str_to_delay(str); - if (opts->initial_delay) + opts->target.initial_delay = str_to_delay(str); + if (opts->target.initial_delay) return 0; ret = parse_event_enable_times(str, NULL); @@ -2306,7 +2306,7 @@ int evlist__parse_event_enable_time(struct evlist *evlist, struct record_opts *o eet->evlist = evlist; evlist->eet = eet; - opts->initial_delay = eet->times[0].start; + opts->target.initial_delay = eet->times[0].start; return 0; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 51e8ce6edddc..462cc0673cee 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1334,7 +1334,7 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts, * group leaders for traced executed by perf. */ if (target__none(&opts->target) && evsel__is_group_leader(evsel) && - !opts->initial_delay) + !opts->target.initial_delay) attr->enable_on_exec = 1; if (evsel->immediate) { diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 46212bf020cf..a6566134e09e 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -65,7 +65,6 @@ struct record_opts { const char *auxtrace_snapshot_opts; const char *auxtrace_sample_opts; bool sample_transaction; - int initial_delay; bool use_clockid; clockid_t clockid; u64 clockid_res_ns; -- GitLab From f9f60efbfc98a9b228d35a1a98fee0528c1fd3ae Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Thu, 2 Mar 2023 11:11:46 +0800 Subject: [PATCH 0332/5631] perf ftrace: Reuse target::initial_delay Replace perf_ftrace::initial_delay with target::initial_delay. Specifying a negative initial_delay is meaningless for ftrace in practice but allowed here. Signed-off-by: Changbin Du Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Hui Wang Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230302031146.2801588-4-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-ftrace.c | 10 +++++----- tools/perf/util/ftrace.h | 1 - 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index d7fe00f66b83..73d51ce84c3a 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -623,7 +623,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace) /* display column headers */ read_tracing_file_to_stdout("trace"); - if (!ftrace->initial_delay) { + if (!ftrace->target.initial_delay) { if (write_tracing_file("tracing_on", "1") < 0) { pr_err("can't enable tracing\n"); goto out_close_fd; @@ -632,8 +632,8 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace) evlist__start_workload(ftrace->evlist); - if (ftrace->initial_delay) { - usleep(ftrace->initial_delay * 1000); + if (ftrace->target.initial_delay > 0) { + usleep(ftrace->target.initial_delay * 1000); if (write_tracing_file("tracing_on", "1") < 0) { pr_err("can't enable tracing\n"); goto out_close_fd; @@ -1164,8 +1164,8 @@ int cmd_ftrace(int argc, const char **argv) "Size of per cpu buffer, needs to use a B, K, M or G suffix.", parse_buffer_size), OPT_BOOLEAN(0, "inherit", &ftrace.inherit, "Trace children processes"), - OPT_UINTEGER('D', "delay", &ftrace.initial_delay, - "Number of milliseconds to wait before starting tracing after program start"), + OPT_INTEGER('D', "delay", &ftrace.target.initial_delay, + "Number of milliseconds to wait before starting tracing after program start"), OPT_PARENT(common_options), }; const struct option latency_options[] = { diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h index a34cd15733b8..558efcb98d25 100644 --- a/tools/perf/util/ftrace.h +++ b/tools/perf/util/ftrace.h @@ -25,7 +25,6 @@ struct perf_ftrace { int graph_noirqs; int graph_verbose; int graph_thresh; - unsigned int initial_delay; }; struct filter_entry { -- GitLab From 5dd827e0fa586521416730e2bb8c3846f6dd91fc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:33 -0800 Subject: [PATCH 0333/5631] libperf evlist: Avoid a use of evsel idx Setting the leader iterates the list, so rather than use idx (which may be changed through list reordering) just count the elements and set afterwards. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evlist.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 61b637f29b82..2d6121e89ccb 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -687,15 +687,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map, void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader) { - struct perf_evsel *first, *last, *evsel; - - first = list_first_entry(list, struct perf_evsel, node); - last = list_last_entry(list, struct perf_evsel, node); - - leader->nr_members = last->idx - first->idx + 1; + struct perf_evsel *evsel; + int n = 0; - __perf_evlist__for_each_entry(list, evsel) + __perf_evlist__for_each_entry(list, evsel) { evsel->leader = leader; + n++; + } + leader->nr_members = n; } void perf_evlist__set_leader(struct perf_evlist *evlist) -- GitLab From bc6c6cdc7d927322461eb95601013524931d2ad6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:34 -0800 Subject: [PATCH 0334/5631] perf stat: Don't remove all grouped events when CPU maps disagree If the events in an evlist's CPU map differ then the entire group is removed. For example: ``` $ perf stat -e '{imc_free_running/data_read/,imc_free_running/data_write/,cs}' -a sleep 1 WARNING: grouped events cpus do not match, disabling group: anon group { imc_free_running/data_read/, imc_free_running/data_write/, cs } ``` Change the behavior so that just the events not matching the leader are removed. So in the example above, just 'cs' will be removed. Modify the warning so that it is produced once for each group, rather than once for the entire evlist. Shrink the scope and size of the warning text buffer. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cfc75517e143..7ef565ae7265 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -181,14 +181,13 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b) static void evlist__check_cpu_maps(struct evlist *evlist) { - struct evsel *evsel, *pos, *leader; - char buf[1024]; + struct evsel *evsel, *warned_leader = NULL; if (evlist__has_hybrid(evlist)) evlist__warn_hybrid_group(evlist); evlist__for_each_entry(evlist, evsel) { - leader = evsel__leader(evsel); + struct evsel *leader = evsel__leader(evsel); /* Check that leader matches cpus with each member. */ if (leader == evsel) @@ -197,19 +196,26 @@ static void evlist__check_cpu_maps(struct evlist *evlist) continue; /* If there's mismatch disable the group and warn user. */ - WARN_ONCE(1, "WARNING: grouped events cpus do not match, disabling group:\n"); - evsel__group_desc(leader, buf, sizeof(buf)); - pr_warning(" %s\n", buf); - + if (warned_leader != leader) { + char buf[200]; + + pr_warning("WARNING: grouped events cpus do not match.\n" + "Events with CPUs not matching the leader will " + "be removed from the group.\n"); + evsel__group_desc(leader, buf, sizeof(buf)); + pr_warning(" %s\n", buf); + warned_leader = leader; + } if (verbose > 0) { + char buf[200]; + cpu_map__snprint(leader->core.cpus, buf, sizeof(buf)); pr_warning(" %s: %s\n", leader->name, buf); cpu_map__snprint(evsel->core.cpus, buf, sizeof(buf)); pr_warning(" %s: %s\n", evsel->name, buf); } - for_each_group_evsel(pos, leader) - evsel__remove_from_group(pos, leader); + evsel__remove_from_group(evsel, leader); } } -- GitLab From 3c7b84d419c2a85069292d1df0695236f99c52df Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:35 -0800 Subject: [PATCH 0335/5631] perf pmu: Earlier PMU auxtrace initialization This allows event parsing to use the evsel__is_aux_event function, which is important when determining event grouping. Suggested-by: Adrian Hunter Signed-off-by: Ian Rogers Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/auxtrace.c | 4 ---- tools/perf/arch/x86/util/pmu.c | 8 ++++++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index 3da506e13f49..330d03216b0e 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -26,11 +26,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, bool found_bts = false; intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); - if (intel_pt_pmu) - intel_pt_pmu->auxtrace = true; intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); - if (intel_bts_pmu) - intel_bts_pmu->auxtrace = true; evlist__for_each_entry(evlist, evsel) { if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 358340b34243..f73b80dcd8bd 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -27,10 +27,14 @@ static bool cached_list; struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) { #ifdef HAVE_AUXTRACE_SUPPORT - if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) + if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) { + pmu->auxtrace = true; return intel_pt_pmu_default_config(pmu); - if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) + } + if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) { + pmu->auxtrace = true; pmu->selectable = true; + } #endif return NULL; } -- GitLab From ce5b85906cd6a14b00f6b2c09d066554d2c13abd Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:36 -0800 Subject: [PATCH 0336/5631] perf stat: Modify the group test Currently nr_members is 0 for an event with no group, however, they are always a leader of their own group. A later change will make that count 1 because the event is its own leader. Make the find_stat logic consistent with this, an improvement suggested by Namhyung Kim. Suggested-by: Namhyung Kim Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-shadow.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index ef85f1ae1ab2..eeccab6751d7 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -163,7 +163,7 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type continue; /* Ignore evsels that are part of different groups. */ - if (evsel->core.leader->nr_members && + if (evsel->core.leader->nr_members > 1 && evsel->core.leader != cur->core.leader) continue; /* Ignore evsels with mismatched modifiers. */ -- GitLab From 8da312d6574c7b3f58ee8dbc85afa392224b5470 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:00:59 +0100 Subject: [PATCH 0337/5631] clk: mediatek: fhctl: Add support for older fhctl register layout The Frequency Hopping Controller (FHCTL) seems to have different versions, as it has a slightly different register layout on some older SoCs like MT6795, MT8173, MT8183 (and others). This driver is indeed compatible with at least some of those older IP revisions, so all we need to do is to add a way to select the right register layout at registration time. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-2-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-fhctl.c | 26 +++++++++++++++++--- drivers/clk/mediatek/clk-fhctl.h | 9 ++++++- drivers/clk/mediatek/clk-mt8186-apmixedsys.c | 2 ++ drivers/clk/mediatek/clk-pllfh.c | 23 +++++++++++++---- drivers/clk/mediatek/clk-pllfh.h | 1 + 5 files changed, 52 insertions(+), 9 deletions(-) diff --git a/drivers/clk/mediatek/clk-fhctl.c b/drivers/clk/mediatek/clk-fhctl.c index 4f271acef5fe..45e4842cbf04 100644 --- a/drivers/clk/mediatek/clk-fhctl.c +++ b/drivers/clk/mediatek/clk-fhctl.c @@ -14,7 +14,20 @@ #define PERCENT_TO_DDSLMT(dds, percent_m10) \ ((((dds) * (percent_m10)) >> 5) / 100) -static const struct fhctl_offset fhctl_offset = { +const struct fhctl_offset fhctl_offset_v1 = { + .offset_hp_en = 0x0, + .offset_clk_con = 0x4, + .offset_rst_con = 0x8, + .offset_slope0 = 0xc, + .offset_slope1 = 0x10, + .offset_cfg = 0x0, + .offset_updnlmt = 0x4, + .offset_dds = 0x8, + .offset_dvfs = 0xc, + .offset_mon = 0x10, +}; + +const struct fhctl_offset fhctl_offset_v2 = { .offset_hp_en = 0x0, .offset_clk_con = 0x8, .offset_rst_con = 0xc, @@ -27,9 +40,16 @@ static const struct fhctl_offset fhctl_offset = { .offset_mon = 0x10, }; -const struct fhctl_offset *fhctl_get_offset_table(void) +const struct fhctl_offset *fhctl_get_offset_table(enum fhctl_variant v) { - return &fhctl_offset; + switch (v) { + case FHCTL_PLLFH_V1: + return &fhctl_offset_v1; + case FHCTL_PLLFH_V2: + return &fhctl_offset_v2; + default: + return ERR_PTR(-EINVAL); + }; } static void dump_hw(struct mtk_clk_pll *pll, struct fh_pll_regs *regs, diff --git a/drivers/clk/mediatek/clk-fhctl.h b/drivers/clk/mediatek/clk-fhctl.h index 51275febf086..bfa6d281a3ee 100644 --- a/drivers/clk/mediatek/clk-fhctl.h +++ b/drivers/clk/mediatek/clk-fhctl.h @@ -7,6 +7,13 @@ #ifndef __CLK_FHCTL_H #define __CLK_FHCTL_H +#include "clk-pllfh.h" + +enum fhctl_variant { + FHCTL_PLLFH_V1, + FHCTL_PLLFH_V2, +}; + struct fhctl_offset { u32 offset_hp_en; u32 offset_clk_con; @@ -19,7 +26,7 @@ struct fhctl_offset { u32 offset_dvfs; u32 offset_mon; }; -const struct fhctl_offset *fhctl_get_offset_table(void); +const struct fhctl_offset *fhctl_get_offset_table(enum fhctl_variant v); const struct fh_operation *fhctl_get_ops(void); void fhctl_hw_init(struct mtk_fh *fh); diff --git a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c index 1d673c6278a9..9fded5020ca4 100644 --- a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c @@ -7,6 +7,7 @@ #include #include +#include "clk-fhctl.h" #include "clk-mtk.h" #include "clk-pll.h" #include "clk-pllfh.h" @@ -98,6 +99,7 @@ enum fh_pll_id { .data = { \ .pll_id = _pllid, \ .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V2, \ .fhx_offset = _offset, \ .dds_mask = GENMASK(21, 0), \ .slope0_value = 0x6003c97, \ diff --git a/drivers/clk/mediatek/clk-pllfh.c b/drivers/clk/mediatek/clk-pllfh.c index f48780bec507..b9297726f5a0 100644 --- a/drivers/clk/mediatek/clk-pllfh.c +++ b/drivers/clk/mediatek/clk-pllfh.c @@ -104,14 +104,16 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, } } -static void pllfh_init(struct mtk_fh *fh, struct mtk_pllfh_data *pllfh_data) +static int pllfh_init(struct mtk_fh *fh, struct mtk_pllfh_data *pllfh_data) { struct fh_pll_regs *regs = &fh->regs; const struct fhctl_offset *offset; void __iomem *base = pllfh_data->state.base; void __iomem *fhx_base = base + pllfh_data->data.fhx_offset; - offset = fhctl_get_offset_table(); + offset = fhctl_get_offset_table(pllfh_data->data.fh_ver); + if (IS_ERR(offset)) + return PTR_ERR(offset); regs->reg_hp_en = base + offset->offset_hp_en; regs->reg_clk_con = base + offset->offset_clk_con; @@ -129,6 +131,8 @@ static void pllfh_init(struct mtk_fh *fh, struct mtk_pllfh_data *pllfh_data) fh->lock = &pllfh_lock; fh->ops = fhctl_get_ops(); + + return 0; } static bool fhctl_is_supported_and_enabled(const struct mtk_pllfh_data *pllfh) @@ -142,20 +146,29 @@ mtk_clk_register_pllfh(const struct mtk_pll_data *pll_data, { struct clk_hw *hw; struct mtk_fh *fh; + int ret; fh = kzalloc(sizeof(*fh), GFP_KERNEL); if (!fh) return ERR_PTR(-ENOMEM); - pllfh_init(fh, pllfh_data); + ret = pllfh_init(fh, pllfh_data); + if (ret) { + hw = ERR_PTR(ret); + goto out; + } hw = mtk_clk_register_pll_ops(&fh->clk_pll, pll_data, base, &mtk_pllfh_ops); + if (IS_ERR(hw)) + goto out; + + fhctl_hw_init(fh); + +out: if (IS_ERR(hw)) kfree(fh); - else - fhctl_hw_init(fh); return hw; } diff --git a/drivers/clk/mediatek/clk-pllfh.h b/drivers/clk/mediatek/clk-pllfh.h index c0a6e1537034..5f419c2ec01f 100644 --- a/drivers/clk/mediatek/clk-pllfh.h +++ b/drivers/clk/mediatek/clk-pllfh.h @@ -18,6 +18,7 @@ struct fh_pll_state { struct fh_pll_data { int pll_id; int fh_id; + int fh_ver; u32 fhx_offset; u32 dds_mask; u32 slope0_value; -- GitLab From 36dff04c459e809e42e35e4e99863fe5de8f4909 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:00 +0100 Subject: [PATCH 0338/5631] clk: mediatek: clk-pllfh: Export register/unregister/parse functions These functions are used by the various MediaTek apmixed clock drivers that may be built as modules: export the common functions used to parse related devicetree properties, register and unregister the PLLFH clocks. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-3-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-pllfh.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/mediatek/clk-pllfh.c b/drivers/clk/mediatek/clk-pllfh.c index b9297726f5a0..7b6e051443f4 100644 --- a/drivers/clk/mediatek/clk-pllfh.c +++ b/drivers/clk/mediatek/clk-pllfh.c @@ -103,6 +103,7 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, pllfh->state.base = base; } } +EXPORT_SYMBOL_GPL(fhctl_parse_dt); static int pllfh_init(struct mtk_fh *fh, struct mtk_pllfh_data *pllfh_data) { @@ -247,6 +248,7 @@ int mtk_clk_register_pllfhs(struct device_node *node, return PTR_ERR(hw); } +EXPORT_SYMBOL_GPL(mtk_clk_register_pllfhs); void mtk_clk_unregister_pllfhs(const struct mtk_pll_data *plls, int num_plls, struct mtk_pllfh_data *pllfhs, int num_fhs, @@ -286,3 +288,4 @@ void mtk_clk_unregister_pllfhs(const struct mtk_pll_data *plls, int num_plls, iounmap(base); } +EXPORT_SYMBOL_GPL(mtk_clk_unregister_pllfhs); -- GitLab From 4ba8590f624f66b9d33e27318c65f650f28ba760 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:01 +0100 Subject: [PATCH 0339/5631] dt-bindings: clock: mediatek,mt8186-fhctl: Support MT6795, MT8173/92/95 MT6795, MT8173, MT8192 and MT8195 support Frequency Hopping: add the compatibles for them. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-4-angelogioacchino.delregno@collabora.com Acked-by: Krzysztof Kozlowski Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/mediatek,mt8186-fhctl.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8186-fhctl.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8186-fhctl.yaml index cfd042ac1e14..d00327d12e1e 100644 --- a/Documentation/devicetree/bindings/clock/mediatek,mt8186-fhctl.yaml +++ b/Documentation/devicetree/bindings/clock/mediatek,mt8186-fhctl.yaml @@ -16,7 +16,12 @@ description: | properties: compatible: - const: mediatek,mt8186-fhctl + enum: + - mediatek,mt6795-fhctl + - mediatek,mt8173-fhctl + - mediatek,mt8186-fhctl + - mediatek,mt8192-fhctl + - mediatek,mt8195-fhctl reg: maxItems: 1 -- GitLab From f222a1baec5f2f1f1d494589a74646d1411dd8ce Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:02 +0100 Subject: [PATCH 0340/5631] clk: mediatek: mt6795: Add support for frequency hopping through FHCTL Add FHCTL parameters and register PLLs through FHCTL to add support for frequency hopping and SSC. FHCTL will be enabled only on PLLs specified in devicetree. This commit brings functional changes only upon addition of devicetree configuration. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-5-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt6795-apmixedsys.c | 63 +++++++++++++++++++- 1 file changed, 60 insertions(+), 3 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt6795-apmixedsys.c b/drivers/clk/mediatek/clk-mt6795-apmixedsys.c index 59761c72d3bc..03fa30527868 100644 --- a/drivers/clk/mediatek/clk-mt6795-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt6795-apmixedsys.c @@ -7,8 +7,10 @@ #include #include #include +#include "clk-fhctl.h" #include "clk-mtk.h" #include "clk-pll.h" +#include "clk-pllfh.h" #define REG_REF2USB 0x8 #define REG_AP_PLL_CON7 0x1c @@ -58,6 +60,56 @@ static const struct mtk_pll_data plls[] = { PLL(CLK_APMIXED_APLL2, "apll2", 0x2b4, 0x2c4, 0, 0, 31, 0x2b4, 4, 0x2bc, 0x2b8, 0), }; +enum fh_pll_id { + FH_CA53PLL_LL, + FH_CA53PLL_BL, + FH_MAINPLL, + FH_MPLL, + FH_MSDCPLL, + FH_MMPLL, + FH_VENCPLL, + FH_TVDPLL, + FH_VCODECPLL, + FH_NR_FH, +}; + +#define _FH(_pllid, _fhid, _slope, _offset) { \ + .data = { \ + .pll_id = _pllid, \ + .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V1, \ + .fhx_offset = _offset, \ + .dds_mask = GENMASK(21, 0), \ + .slope0_value = _slope, \ + .slope1_value = _slope, \ + .sfstrx_en = BIT(2), \ + .frddsx_en = BIT(1), \ + .fhctlx_en = BIT(0), \ + .tgl_org = BIT(31), \ + .dvfs_tri = BIT(31), \ + .pcwchg = BIT(31), \ + .dt_val = 0x0, \ + .df_val = 0x9, \ + .updnlmt_shft = 16, \ + .msk_frddsx_dys = GENMASK(23, 20), \ + .msk_frddsx_dts = GENMASK(19, 16), \ + }, \ + } + +#define FH(_pllid, _fhid, _offset) _FH(_pllid, _fhid, 0x6003c97, _offset) +#define FH_M(_pllid, _fhid, _offset) _FH(_pllid, _fhid, 0x6000140, _offset) + +static struct mtk_pllfh_data pllfhs[] = { + FH(CLK_APMIXED_ARMCA53PLL, FH_CA53PLL_BL, 0x38), + FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x60), + FH_M(CLK_APMIXED_MPLL, FH_MPLL, 0x74), + FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x88), + FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0x9c), + FH(CLK_APMIXED_VENCPLL, FH_VENCPLL, 0xb0), + FH(CLK_APMIXED_TVDPLL, FH_TVDPLL, 0xc4), + FH(CLK_APMIXED_VCODECPLL, FH_VCODECPLL, 0xd8), +}; + static void clk_mt6795_apmixed_setup_md1(void __iomem *base) { void __iomem *reg = base + REG_AP_PLL_CON7; @@ -85,6 +137,7 @@ static int clk_mt6795_apmixed_probe(struct platform_device *pdev) struct clk_hw_onecell_data *clk_data; struct device *dev = &pdev->dev; struct device_node *node = dev->of_node; + const u8 *fhctl_node = "mediatek,mt6795-fhctl"; void __iomem *base; struct clk_hw *hw; int ret; @@ -97,7 +150,9 @@ static int clk_mt6795_apmixed_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); + ret = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), + pllfhs, ARRAY_SIZE(pllfhs), clk_data); if (ret) goto free_clk_data; @@ -124,7 +179,8 @@ static int clk_mt6795_apmixed_probe(struct platform_device *pdev) unregister_ref2usb: mtk_clk_unregister_ref2usb_tx(clk_data->hws[CLK_APMIXED_REF2USB_TX]); unregister_plls: - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return ret; @@ -137,7 +193,8 @@ static int clk_mt6795_apmixed_remove(struct platform_device *pdev) of_clk_del_provider(node); mtk_clk_unregister_ref2usb_tx(clk_data->hws[CLK_APMIXED_REF2USB_TX]); - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); mtk_free_clk_data(clk_data); return 0; -- GitLab From 45a5cbe05d1f562b24db8ce67bd1bb3a3a9ec425 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:03 +0100 Subject: [PATCH 0341/5631] clk: mediatek: mt8173: Add support for frequency hopping through FHCTL Add FHCTL parameters and register PLLs through FHCTL to add support for frequency hopping and SSC. FHCTL will be enabled only on PLLs specified in devicetree. This commit brings functional changes only upon addition of devicetree configuration. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-6-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8173-apmixedsys.c | 65 +++++++++++++++++++- 1 file changed, 62 insertions(+), 3 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8173-apmixedsys.c b/drivers/clk/mediatek/clk-mt8173-apmixedsys.c index a56c5845d07a..0084203e67ad 100644 --- a/drivers/clk/mediatek/clk-mt8173-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8173-apmixedsys.c @@ -9,8 +9,10 @@ #include #include #include +#include "clk-fhctl.h" #include "clk-mtk.h" #include "clk-pll.h" +#include "clk-pllfh.h" #define REGOFF_REF2USB 0x8 #define REGOFF_HDMI_REF 0x40 @@ -77,6 +79,58 @@ static const struct mtk_pll_data plls[] = { PLL(CLK_APMIXED_MSDCPLL2, "msdcpll2", 0x2f0, 0x2fc, 0, 0, 21, 0x2f0, 4, 0x0, 0x2f4, 0), }; +enum fh_pll_id { + FH_ARMCA7PLL, + FH_ARMCA15PLL, + FH_MAINPLL, + FH_MPLL, + FH_MSDCPLL, + FH_MMPLL, + FH_VENCPLL, + FH_TVDPLL, + FH_VCODECPLL, + FH_LVDSPLL, + FH_MSDC2PLL, + FH_NR_FH, +}; + +#define FH(_pllid, _fhid, _offset) { \ + .data = { \ + .pll_id = _pllid, \ + .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V1, \ + .fhx_offset = _offset, \ + .dds_mask = GENMASK(21, 0), \ + .slope0_value = 0x6003c97, \ + .slope1_value = 0x6003c97, \ + .sfstrx_en = BIT(2), \ + .frddsx_en = BIT(1), \ + .fhctlx_en = BIT(0), \ + .tgl_org = BIT(31), \ + .dvfs_tri = BIT(31), \ + .pcwchg = BIT(31), \ + .dt_val = 0x0, \ + .df_val = 0x9, \ + .updnlmt_shft = 16, \ + .msk_frddsx_dys = GENMASK(23, 20), \ + .msk_frddsx_dts = GENMASK(19, 16), \ + }, \ + } + +static struct mtk_pllfh_data pllfhs[] = { + FH(CLK_APMIXED_ARMCA7PLL, FH_ARMCA7PLL, 0x38), + FH(CLK_APMIXED_ARMCA15PLL, FH_ARMCA15PLL, 0x4c), + FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x60), + FH(CLK_APMIXED_MPLL, FH_MPLL, 0x74), + FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x88), + FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0x9c), + FH(CLK_APMIXED_VENCPLL, FH_VENCPLL, 0xb0), + FH(CLK_APMIXED_TVDPLL, FH_TVDPLL, 0xc4), + FH(CLK_APMIXED_VCODECPLL, FH_VCODECPLL, 0xd8), + FH(CLK_APMIXED_LVDSPLL, FH_LVDSPLL, 0xec), + FH(CLK_APMIXED_MSDCPLL2, FH_MSDC2PLL, 0x100), +}; + static const struct of_device_id of_match_clk_mt8173_apmixed[] = { { .compatible = "mediatek,mt8173-apmixedsys" }, { /* sentinel */ } @@ -84,6 +138,7 @@ static const struct of_device_id of_match_clk_mt8173_apmixed[] = { static int clk_mt8173_apmixed_probe(struct platform_device *pdev) { + const u8 *fhctl_node = "mediatek,mt8173-fhctl"; struct device_node *node = pdev->dev.of_node; struct clk_hw_onecell_data *clk_data; void __iomem *base; @@ -98,7 +153,9 @@ static int clk_mt8173_apmixed_probe(struct platform_device *pdev) if (IS_ERR_OR_NULL(clk_data)) return -ENOMEM; - r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); + r = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), + pllfhs, ARRAY_SIZE(pllfhs), clk_data); if (r) goto free_clk_data; @@ -124,7 +181,8 @@ static int clk_mt8173_apmixed_probe(struct platform_device *pdev) unregister_ref2usb: mtk_clk_unregister_ref2usb_tx(clk_data->hws[CLK_APMIXED_REF2USB_TX]); unregister_plls: - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return r; @@ -137,7 +195,8 @@ static int clk_mt8173_apmixed_remove(struct platform_device *pdev) of_clk_del_provider(node); mtk_clk_unregister_ref2usb_tx(clk_data->hws[CLK_APMIXED_REF2USB_TX]); - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); mtk_free_clk_data(clk_data); return 0; -- GitLab From 4d586e10c428f262b167dd46eefa8b362017a9b1 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:04 +0100 Subject: [PATCH 0342/5631] clk: mediatek: mt8192: Add support for frequency hopping through FHCTL Add FHCTL parameters and register PLLs through FHCTL to add support for frequency hopping and SSC. FHCTL will be enabled only on PLLs specified in devicetree. This commit brings functional changes only upon addition of devicetree configuration. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-7-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8192.c | 67 ++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c index 61299960d28a..0f9f10172148 100644 --- a/drivers/clk/mediatek/clk-mt8192.c +++ b/drivers/clk/mediatek/clk-mt8192.c @@ -12,10 +12,12 @@ #include #include +#include "clk-fhctl.h" #include "clk-gate.h" #include "clk-mtk.h" #include "clk-mux.h" #include "clk-pll.h" +#include "clk-pllfh.h" #include #include @@ -1042,6 +1044,57 @@ static const struct mtk_pll_data plls[] = { 0, 0, 32, 0x0330, 24, 0, 0, 0, 0x0334, 0), }; +enum fh_pll_id { + FH_ARMPLL_LL, + FH_ARMPLL_BL0, + FH_ARMPLL_BL1, + FH_ARMPLL_BL2, + FH_ARMPLL_BL3, + FH_CCIPLL, + FH_MFGPLL, + FH_MEMPLL, + FH_MPLL, + FH_MMPLL, + FH_MAINPLL, + FH_MSDCPLL, + FH_ADSPPLL, + FH_APUPLL, + FH_TVDPLL, + FH_NR_FH, +}; + +#define FH(_pllid, _fhid, _offset) { \ + .data = { \ + .pll_id = _pllid, \ + .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V2, \ + .fhx_offset = _offset, \ + .dds_mask = GENMASK(21, 0), \ + .slope0_value = 0x6003c97, \ + .slope1_value = 0x6003c97, \ + .sfstrx_en = BIT(2), \ + .frddsx_en = BIT(1), \ + .fhctlx_en = BIT(0), \ + .tgl_org = BIT(31), \ + .dvfs_tri = BIT(31), \ + .pcwchg = BIT(31), \ + .dt_val = 0x0, \ + .df_val = 0x9, \ + .updnlmt_shft = 16, \ + .msk_frddsx_dys = GENMASK(23, 20), \ + .msk_frddsx_dts = GENMASK(19, 16), \ + }, \ + } + +static struct mtk_pllfh_data pllfhs[] = { + FH(CLK_APMIXED_MFGPLL, FH_MFGPLL, 0xb4), + FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0xf0), + FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x104), + FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x118), + FH(CLK_APMIXED_ADSPPLL, FH_ADSPPLL, 0x12c), + FH(CLK_APMIXED_TVDPLL, FH_TVDPLL, 0x154), +}; + /* Register mux notifier for MFG mux */ static int clk_mt8192_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) { @@ -1068,17 +1121,24 @@ static int clk_mt8192_apmixed_probe(struct platform_device *pdev) { struct clk_hw_onecell_data *clk_data; struct device_node *node = pdev->dev.of_node; + const u8 *fhctl_node = "mediatek,mt8192-fhctl"; int r; clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); if (!clk_data) return -ENOMEM; - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); + + r = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), + pllfhs, ARRAY_SIZE(pllfhs), clk_data); + if (r) + goto free_clk_data; + r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); if (r) - goto free_clk_data; + goto unregister_plls; r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) @@ -1088,6 +1148,9 @@ static int clk_mt8192_apmixed_probe(struct platform_device *pdev) unregister_gates: mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); +unregister_plls: + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); free_clk_data: mtk_free_clk_data(clk_data); return r; -- GitLab From da4a82dc67b02da854d50d342386ba3354fb7a04 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Feb 2023 11:01:05 +0100 Subject: [PATCH 0343/5631] clk: mediatek: mt8195: Add support for frequency hopping through FHCTL Add FHCTL parameters and register PLLs through FHCTL to add support for frequency hopping and SSC. FHCTL will be enabled only on PLLs specified in devicetree. This commit brings functional changes only upon addition of devicetree configuration. Signed-off-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230206100105.861720-8-angelogioacchino.delregno@collabora.com Reviewed-by: Chen-Yu Tsai Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8195-apmixedsys.c | 69 +++++++++++++++++++- 1 file changed, 66 insertions(+), 3 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c index 1bc917f2667e..c0db31ce0741 100644 --- a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c @@ -3,9 +3,11 @@ // Copyright (c) 2021 MediaTek Inc. // Author: Chun-Jie Chen +#include "clk-fhctl.h" #include "clk-gate.h" #include "clk-mtk.h" #include "clk-pll.h" +#include "clk-pllfh.h" #include #include @@ -105,6 +107,61 @@ static const struct mtk_pll_data plls[] = { 0, 0, 22, 0x0158, 24, 0, 0, 0, 0x0158, 0, 0x0158, 0, 9), }; +enum fh_pll_id { + FH_ARMPLL_LL, + FH_ARMPLL_BL, + FH_MEMPLL, + FH_ADSPPLL, + FH_NNAPLL, + FH_CCIPLL, + FH_MFGPLL, + FH_TVDPLL2, + FH_MPLL, + FH_MMPLL, + FH_MAINPLL, + FH_MSDCPLL, + FH_IMGPLL, + FH_VDECPLL, + FH_TVDPLL1, + FH_NR_FH, +}; + +#define FH(_pllid, _fhid, _offset) { \ + .data = { \ + .pll_id = _pllid, \ + .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V2, \ + .fhx_offset = _offset, \ + .dds_mask = GENMASK(21, 0), \ + .slope0_value = 0x6003c97, \ + .slope1_value = 0x6003c97, \ + .sfstrx_en = BIT(2), \ + .frddsx_en = BIT(1), \ + .fhctlx_en = BIT(0), \ + .tgl_org = BIT(31), \ + .dvfs_tri = BIT(31), \ + .pcwchg = BIT(31), \ + .dt_val = 0x0, \ + .df_val = 0x9, \ + .updnlmt_shft = 16, \ + .msk_frddsx_dys = GENMASK(23, 20), \ + .msk_frddsx_dts = GENMASK(19, 16), \ + }, \ + } + +static struct mtk_pllfh_data pllfhs[] = { + FH(CLK_APMIXED_ADSPPLL, FH_ADSPPLL, 0x78), + FH(CLK_APMIXED_NNAPLL, FH_NNAPLL, 0x8c), + FH(CLK_APMIXED_MFGPLL, FH_MFGPLL, 0xb4), + FH(CLK_APMIXED_TVDPLL2, FH_TVDPLL2, 0xc8), + FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0xf0), + FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x104), + FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x118), + FH(CLK_APMIXED_IMGPLL, FH_IMGPLL, 0x12c), + FH(CLK_APMIXED_VDECPLL, FH_VDECPLL, 0x140), + FH(CLK_APMIXED_TVDPLL2, FH_TVDPLL1, 0x154), +}; + static const struct of_device_id of_match_clk_mt8195_apmixed[] = { { .compatible = "mediatek,mt8195-apmixedsys", }, {} @@ -114,13 +171,17 @@ static int clk_mt8195_apmixed_probe(struct platform_device *pdev) { struct clk_hw_onecell_data *clk_data; struct device_node *node = pdev->dev.of_node; + const u8 *fhctl_node = "mediatek,mt8195-fhctl"; int r; clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); if (!clk_data) return -ENOMEM; - r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); + + r = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), + pllfhs, ARRAY_SIZE(pllfhs), clk_data); if (r) goto free_apmixed_data; @@ -140,7 +201,8 @@ static int clk_mt8195_apmixed_probe(struct platform_device *pdev) unregister_gates: mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); unregister_plls: - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); free_apmixed_data: mtk_free_clk_data(clk_data); return r; @@ -153,7 +215,8 @@ static int clk_mt8195_apmixed_remove(struct platform_device *pdev) of_clk_del_provider(node); mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); mtk_free_clk_data(clk_data); return 0; -- GitLab From 4b476b0f45343177c4666cec593dd1acf649bc09 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:50 +0100 Subject: [PATCH 0344/5631] clk: mediatek: clk-mtk: Switch to device_get_match_data() Instead of using of_device_get_match_data(), switch to the generic device_get_match_data(). Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-2-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mtk.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 14e8b64a32a3..f0b723372b52 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include @@ -471,7 +470,7 @@ int mtk_clk_simple_probe(struct platform_device *pdev) void __iomem *base; int num_clks, r; - mcd = of_device_get_match_data(&pdev->dev); + mcd = device_get_match_data(&pdev->dev); if (!mcd) return -EINVAL; @@ -586,7 +585,7 @@ EXPORT_SYMBOL_GPL(mtk_clk_simple_probe); int mtk_clk_simple_remove(struct platform_device *pdev) { - const struct mtk_clk_desc *mcd = of_device_get_match_data(&pdev->dev); + const struct mtk_clk_desc *mcd = device_get_match_data(&pdev->dev); struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); struct device_node *node = pdev->dev.of_node; -- GitLab From 252091242404aa7cee131a827a04b8e3d9b88daa Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:51 +0100 Subject: [PATCH 0345/5631] clk: mediatek: clk-mtk: Introduce clk_mtk_pdev_{probe,remove}() Introduce functions clk_mtk_pdev_probe() and clk_mtk_pdev_remove(): these will be useful to commonize the probe and remove handlers for multimedia (clk-mtxxxx-mm) drivers as these are registered by the mtk-mmsys driver instead of having their own devicetree compatible. In order to do this, the main logic of clk_mtk_simple{probe,remove}() was moved to new static __clk_mtk_simple_{probe,remove}() functions that take as parameter a pointer to struct device_node because when registering the clocks from mtk-mmsys we want to pass a pointer to the clock driver's parent (which is, obviously, mtk-mmsys) struct device_node instead. As for the clock driver's platform data: for the devicetree case, we keep using the standard match_data mechanism, else we retrieve it from an id_table. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-3-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mtk.c | 54 +++++++++++++++++++++++++++++----- drivers/clk/mediatek/clk-mtk.h | 2 ++ 2 files changed, 48 insertions(+), 8 deletions(-) diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index f0b723372b52..990be3d62db2 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -462,17 +462,25 @@ void mtk_clk_unregister_dividers(const struct mtk_clk_divider *mcds, int num, } EXPORT_SYMBOL_GPL(mtk_clk_unregister_dividers); -int mtk_clk_simple_probe(struct platform_device *pdev) +static int __mtk_clk_simple_probe(struct platform_device *pdev, + struct device_node *node) { + const struct platform_device_id *id; const struct mtk_clk_desc *mcd; struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; void __iomem *base; int num_clks, r; mcd = device_get_match_data(&pdev->dev); - if (!mcd) - return -EINVAL; + if (!mcd) { + /* Clock driver wasn't registered from devicetree */ + id = platform_get_device_id(pdev); + if (id) + mcd = (const struct mtk_clk_desc *)id->driver_data; + + if (!mcd) + return -EINVAL; + } /* Composite clocks needs us to pass iomem pointer */ if (mcd->composite_clks) { @@ -581,13 +589,12 @@ int mtk_clk_simple_probe(struct platform_device *pdev) iounmap(base); return r; } -EXPORT_SYMBOL_GPL(mtk_clk_simple_probe); -int mtk_clk_simple_remove(struct platform_device *pdev) +static int __mtk_clk_simple_remove(struct platform_device *pdev, + struct device_node *node) { - const struct mtk_clk_desc *mcd = device_get_match_data(&pdev->dev); struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - struct device_node *node = pdev->dev.of_node; + const struct mtk_clk_desc *mcd = device_get_match_data(&pdev->dev); of_clk_del_provider(node); if (mcd->clks) @@ -608,6 +615,37 @@ int mtk_clk_simple_remove(struct platform_device *pdev) return 0; } + +int mtk_clk_pdev_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->parent->of_node; + + return __mtk_clk_simple_probe(pdev, node); +} +EXPORT_SYMBOL_GPL(mtk_clk_pdev_probe); + +int mtk_clk_simple_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + + return __mtk_clk_simple_probe(pdev, node); +} +EXPORT_SYMBOL_GPL(mtk_clk_simple_probe); + +int mtk_clk_pdev_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->parent->of_node; + + return __mtk_clk_simple_remove(pdev, node); +} +EXPORT_SYMBOL_GPL(mtk_clk_pdev_remove); + +int mtk_clk_simple_remove(struct platform_device *pdev) +{ + return __mtk_clk_simple_remove(pdev, pdev->dev.of_node); +} EXPORT_SYMBOL_GPL(mtk_clk_simple_remove); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h index 41f4fa3b0c21..b8e0ff8f52fa 100644 --- a/drivers/clk/mediatek/clk-mtk.h +++ b/drivers/clk/mediatek/clk-mtk.h @@ -236,6 +236,8 @@ struct mtk_clk_desc { unsigned int mfg_clk_idx; }; +int mtk_clk_pdev_probe(struct platform_device *pdev); +int mtk_clk_pdev_remove(struct platform_device *pdev); int mtk_clk_simple_probe(struct platform_device *pdev); int mtk_clk_simple_remove(struct platform_device *pdev); -- GitLab From 65c10c50c9c7619637f064bbdb4d4f37556ee498 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:52 +0100 Subject: [PATCH 0346/5631] clk: mediatek: Migrate to mtk_clk_pdev_probe() for multimedia clocks Reduce duplication and simplify all MediaTek multimedia clock drivers by migrating away from defining custom probe functions for each driver and instead use mtk_clk_pdev_probe(). While at it, also add a .remove() callback to all of the multimedia clock drivers where missing. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-4-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701-mm.c | 31 +++++--------- drivers/clk/mediatek/clk-mt2712-mm.c | 31 +++++--------- drivers/clk/mediatek/clk-mt6779-mm.c | 24 +++++------ drivers/clk/mediatek/clk-mt6795-mm.c | 55 +++++------------------- drivers/clk/mediatek/clk-mt6797-mm.c | 31 +++++--------- drivers/clk/mediatek/clk-mt8167-mm.c | 47 +++++---------------- drivers/clk/mediatek/clk-mt8173-mm.c | 58 +++++--------------------- drivers/clk/mediatek/clk-mt8183-mm.c | 24 +++++------ drivers/clk/mediatek/clk-mt8186-mm.c | 56 +++++-------------------- drivers/clk/mediatek/clk-mt8192-mm.c | 29 +++++-------- drivers/clk/mediatek/clk-mt8195-vdo0.c | 55 +++++------------------- drivers/clk/mediatek/clk-mt8195-vdo1.c | 57 ++++++------------------- drivers/clk/mediatek/clk-mt8195-vpp0.c | 54 +++++------------------- drivers/clk/mediatek/clk-mt8195-vpp1.c | 54 +++++------------------- drivers/clk/mediatek/clk-mt8365-mm.c | 39 +++++------------ 15 files changed, 165 insertions(+), 480 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index 23d5ddcc1d37..a8d94ca0eefd 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -79,32 +79,23 @@ static const struct mtk_gate mm_clks[] = { GATE_DISP1(CLK_MM_TVE_FMM, "mm_tve_fmm", "mm_sel", 14), }; -static int clk_mt2701_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR); - - mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - dev_err(&pdev->dev, - "could not register clock provider: %s: %d\n", - pdev->name, r); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return r; -} +static const struct platform_device_id clk_mt2701_mm_id_table[] = { + { .name = "clk-mt2701-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt2701_mm_drv = { - .probe = clk_mt2701_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt2701-mm", }, + .id_table = clk_mt2701_mm_id_table, }; builtin_platform_driver(clk_mt2701_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index 25b8af640c12..615f6b0fe96e 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -126,32 +126,23 @@ static const struct mtk_gate mm_clks[] = { GATE_MM2(CLK_MM_DSI3_DIGITAL, "mm_dsi3_digital", "dsi1_lntc", 6), }; -static int clk_mt2712_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - - mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - - if (r != 0) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return r; -} +static const struct platform_device_id clk_mt2712_mm_id_table[] = { + { .name = "clk-mt2712-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt2712_mm_drv = { - .probe = clk_mt2712_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt2712-mm", }, + .id_table = clk_mt2712_mm_id_table, }; builtin_platform_driver(clk_mt2712_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt6779-mm.c b/drivers/clk/mediatek/clk-mt6779-mm.c index 2cccf62d3b36..219a3a7920cd 100644 --- a/drivers/clk/mediatek/clk-mt6779-mm.c +++ b/drivers/clk/mediatek/clk-mt6779-mm.c @@ -85,25 +85,23 @@ static const struct mtk_gate mm_clks[] = { GATE_MM1(CLK_MM_DISP_OVL_FBDC, "mm_disp_ovl_fbdc", "mm_sel", 16), }; -static int clk_mt6779_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - - mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} +static const struct platform_device_id clk_mt6779_mm_id_table[] = { + { .name = "clk-mt6779-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt6779_mm_drv = { - .probe = clk_mt6779_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt6779-mm", }, + .id_table = clk_mt6779_mm_id_table, }; module_platform_driver(clk_mt6779_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt6795-mm.c b/drivers/clk/mediatek/clk-mt6795-mm.c index eebb6143ada2..c0c61a08cd72 100644 --- a/drivers/clk/mediatek/clk-mt6795-mm.c +++ b/drivers/clk/mediatek/clk-mt6795-mm.c @@ -76,56 +76,23 @@ static const struct mtk_gate mm_gates[] = { GATE_MM1(CLK_MM_DPI_ENGINE, "mm_dpi_engine", "mm_sel", 9), }; -static int clk_mt6795_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int ret; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - if (!clk_data) - return -ENOMEM; - - ret = mtk_clk_register_gates(&pdev->dev, node, mm_gates, - ARRAY_SIZE(mm_gates), clk_data); - if (ret) - goto free_clk_data; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return 0; - -unregister_gates: - mtk_clk_unregister_gates(mm_gates, ARRAY_SIZE(mm_gates), clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); - return ret; -} - -static int clk_mt6795_mm_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(mm_gates, ARRAY_SIZE(mm_gates), clk_data); - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_gates, + .num_clks = ARRAY_SIZE(mm_gates), +}; - return 0; -} +static const struct platform_device_id clk_mt6795_mm_id_table[] = { + { .name = "clk-mt6795-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt6795_mm_drv = { .driver = { .name = "clk-mt6795-mm", }, - .probe = clk_mt6795_mm_probe, - .remove = clk_mt6795_mm_remove, + .id_table = clk_mt6795_mm_id_table, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, }; module_platform_driver(clk_mt6795_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index deb16a6b16a5..706c9775646d 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -92,32 +92,23 @@ static const struct mtk_gate mm_clks[] = { "clk26m", 3), }; -static int clk_mt6797_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR); - - mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - dev_err(&pdev->dev, - "could not register clock provider: %s: %d\n", - pdev->name, r); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return r; -} +static const struct platform_device_id clk_mt6797_mm_id_table[] = { + { .name = "clk-mt6797-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt6797_mm_drv = { - .probe = clk_mt6797_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt6797-mm", }, + .id_table = clk_mt6797_mm_id_table, }; builtin_platform_driver(clk_mt6797_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index c0b44104c765..78c023b0565a 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -86,47 +86,22 @@ static const struct mtk_gate mm_clks[] = { GATE_MM1(CLK_MM_HDMI_PLL, "mm_hdmi_pll", "hdmtx_dig_cts", 21), }; -struct clk_mt8167_mm_driver_data { - const struct mtk_gate *gates_clk; - int gates_num; +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), }; -static const struct clk_mt8167_mm_driver_data mt8167_mmsys_driver_data = { - .gates_clk = mm_clks, - .gates_num = ARRAY_SIZE(mm_clks), +static const struct platform_device_id clk_mt8167_mm_id_table[] = { + { .name = "clk-mt8167-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } }; -static int clk_mt8167_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - const struct clk_mt8167_mm_driver_data *data; - struct clk_hw_onecell_data *clk_data; - int ret; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - if (!clk_data) - return -ENOMEM; - - data = &mt8167_mmsys_driver_data; - - ret = mtk_clk_register_gates(&pdev->dev, node, data->gates_clk, - data->gates_num, clk_data); - if (ret) - return ret; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - return ret; - - return 0; -} - -static struct platform_driver clk_mt8173_mm_drv = { +static struct platform_driver clk_mt8167_mm_drv = { + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8167-mm", }, - .probe = clk_mt8167_mm_probe, + .id_table = clk_mt8167_mm_id_table, }; - -builtin_platform_driver(clk_mt8173_mm_drv); +builtin_platform_driver(clk_mt8167_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8173-mm.c b/drivers/clk/mediatek/clk-mt8173-mm.c index 315430ad1581..ffec2d917661 100644 --- a/drivers/clk/mediatek/clk-mt8173-mm.c +++ b/drivers/clk/mediatek/clk-mt8173-mm.c @@ -44,6 +44,7 @@ static const struct mtk_gate_regs mm1_cg_regs = { } static const struct mtk_gate mt8173_mm_clks[] = { + GATE_DUMMY(CLK_DUMMY, "mm_dummy"), /* MM0 */ GATE_MM0(CLK_MM_SMI_COMMON, "mm_smi_common", "mm_sel", 0), GATE_MM0(CLK_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 1), @@ -100,62 +101,23 @@ static const struct mtk_gate mt8173_mm_clks[] = { GATE_MM1(CLK_MM_HDMI_HDCP24M, "mm_hdmi_hdcp24m", "hdcp_24m_sel", 20), }; -struct clk_mt8173_mm_driver_data { - const struct mtk_gate *gates_clk; - int gates_num; +static const struct mtk_clk_desc mm_desc = { + .clks = mt8173_mm_clks, + .num_clks = ARRAY_SIZE(mt8173_mm_clks), }; -static const struct clk_mt8173_mm_driver_data mt8173_mmsys_driver_data = { - .gates_clk = mt8173_mm_clks, - .gates_num = ARRAY_SIZE(mt8173_mm_clks), +static const struct platform_device_id clk_mt8173_mm_id_table[] = { + { .name = "clk-mt8173-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } }; -static int clk_mt8173_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - const struct clk_mt8173_mm_driver_data *data; - struct clk_hw_onecell_data *clk_data; - int ret; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - if (!clk_data) - return -ENOMEM; - - data = &mt8173_mmsys_driver_data; - - ret = mtk_clk_register_gates(&pdev->dev, node, data->gates_clk, - data->gates_num, clk_data); - if (ret) - return ret; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - return ret; - - return 0; -} - -static int clk_mt8173_mm_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - const struct clk_mt8173_mm_driver_data *data = &mt8173_mmsys_driver_data; - - of_clk_del_provider(node); - mtk_clk_unregister_gates(data->gates_clk, data->gates_num, clk_data); - mtk_free_clk_data(clk_data); - - return 0; -} - static struct platform_driver clk_mt8173_mm_drv = { .driver = { .name = "clk-mt8173-mm", }, - .probe = clk_mt8173_mm_probe, - .remove = clk_mt8173_mm_remove, + .id_table = clk_mt8173_mm_id_table, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, }; builtin_platform_driver(clk_mt8173_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-mm.c b/drivers/clk/mediatek/clk-mt8183-mm.c index 358031530913..669dcdd66efb 100644 --- a/drivers/clk/mediatek/clk-mt8183-mm.c +++ b/drivers/clk/mediatek/clk-mt8183-mm.c @@ -82,25 +82,23 @@ static const struct mtk_gate mm_clks[] = { GATE_MM1(CLK_MM_DBI_IF, "mm_dbi_if", "dpi0_sel", 13), }; -static int clk_mt8183_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - - mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} +static const struct platform_device_id clk_mt8183_mm_id_table[] = { + { .name = "clk-mt8183-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8183_mm_drv = { - .probe = clk_mt8183_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8183-mm", }, + .id_table = clk_mt8183_mm_id_table, }; builtin_platform_driver(clk_mt8183_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-mm.c b/drivers/clk/mediatek/clk-mt8186-mm.c index 0b72607777fa..6506a8b848a9 100644 --- a/drivers/clk/mediatek/clk-mt8186-mm.c +++ b/drivers/clk/mediatek/clk-mt8186-mm.c @@ -58,55 +58,21 @@ static const struct mtk_gate mm_clks[] = { GATE_MM1(CLK_MM_DISP_26M, "mm_disp_26m_ck", "top_disp", 10), }; -static int clk_mt8186_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - if (r) - goto free_mm_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_gates: - mtk_clk_unregister_gates(mm_clks, ARRAY_SIZE(mm_clks), clk_data); -free_mm_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8186_mm_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(mm_clks, ARRAY_SIZE(mm_clks), clk_data); - mtk_free_clk_data(clk_data); - - return 0; -} +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; +static const struct platform_device_id clk_mt8186_mm_id_table[] = { + { .name = "clk-mt8186-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8186_mm_drv = { - .probe = clk_mt8186_mm_probe, - .remove = clk_mt8186_mm_remove, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8186-mm", }, + .id_table = clk_mt8186_mm_id_table, }; builtin_platform_driver(clk_mt8186_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-mm.c b/drivers/clk/mediatek/clk-mt8192-mm.c index e9eb4cf8349a..638e6faae84c 100644 --- a/drivers/clk/mediatek/clk-mt8192-mm.c +++ b/drivers/clk/mediatek/clk-mt8192-mm.c @@ -80,30 +80,23 @@ static const struct mtk_gate mm_clks[] = { GATE_MM2(CLK_MM_32KHZ, "mm_32khz", "clk32k", 25), }; -static int clk_mt8192_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(&pdev->dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - if (r) - return r; +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} +static const struct platform_device_id clk_mt8192_mm_id_table[] = { + { .name = "clk-mt8192-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8192_mm_drv = { - .probe = clk_mt8192_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8192-mm", }, + .id_table = clk_mt8192_mm_id_table, }; builtin_platform_driver(clk_mt8192_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo0.c b/drivers/clk/mediatek/clk-mt8195-vdo0.c index 839b730688ac..492c1e133d0d 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo0.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo0.c @@ -93,55 +93,22 @@ static const struct mtk_gate vdo0_clks[] = { "top_edp", 16, CLK_SET_RATE_PARENT), }; -static int clk_mt8195_vdo0_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_VDO0_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(&pdev->dev, node, vdo0_clks, - ARRAY_SIZE(vdo0_clks), clk_data); - if (r) - goto free_vdo0_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_gates: - mtk_clk_unregister_gates(vdo0_clks, ARRAY_SIZE(vdo0_clks), clk_data); -free_vdo0_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8195_vdo0_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(vdo0_clks, ARRAY_SIZE(vdo0_clks), clk_data); - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc vdo0_desc = { + .clks = vdo0_clks, + .num_clks = ARRAY_SIZE(vdo0_clks), +}; - return 0; -} +static const struct platform_device_id clk_mt8195_vdo0_id_table[] = { + { .name = "clk-mt8195-vdo0", .driver_data = (kernel_ulong_t)&vdo0_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8195_vdo0_drv = { - .probe = clk_mt8195_vdo0_probe, - .remove = clk_mt8195_vdo0_remove, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8195-vdo0", }, + .id_table = clk_mt8195_vdo0_id_table, }; builtin_platform_driver(clk_mt8195_vdo0_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo1.c b/drivers/clk/mediatek/clk-mt8195-vdo1.c index 7df695b28925..76e9f4496e43 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo1.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo1.c @@ -120,55 +120,22 @@ static const struct mtk_gate vdo1_clks[] = { GATE_VDO1_4(CLK_VDO1_DPI1_HDMI, "vdo1_dpi1_hdmi", "hdmi_txpll", 0), }; -static int clk_mt8195_vdo1_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_VDO1_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(&pdev->dev, node, vdo1_clks, - ARRAY_SIZE(vdo1_clks), clk_data); - if (r) - goto free_vdo1_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_gates: - mtk_clk_unregister_gates(vdo1_clks, ARRAY_SIZE(vdo1_clks), clk_data); -free_vdo1_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8195_vdo1_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(vdo1_clks, ARRAY_SIZE(vdo1_clks), clk_data); - mtk_free_clk_data(clk_data); - - return 0; -} +static const struct mtk_clk_desc vdo1_desc = { + .clks = vdo1_clks, + .num_clks = ARRAY_SIZE(vdo1_clks), +}; + +static const struct platform_device_id clk_mt8195_vdo1_id_table[] = { + { .name = "clk-mt8195-vdo1", .driver_data = (kernel_ulong_t)&vdo1_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8195_vdo1_drv = { - .probe = clk_mt8195_vdo1_probe, - .remove = clk_mt8195_vdo1_remove, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8195-vdo1", }, + .id_table = clk_mt8195_vdo1_id_table, }; builtin_platform_driver(clk_mt8195_vdo1_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp0.c b/drivers/clk/mediatek/clk-mt8195-vpp0.c index e19664af09b6..15f1a081358a 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp0.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp0.c @@ -86,54 +86,22 @@ static const struct mtk_gate vpp0_clks[] = { GATE_VPP0_2(CLK_VPP0_WARP1_MDP_DL_ASYNC, "vpp0_warp1_mdp_dl_async", "top_wpe_vpp", 3), }; -static int clk_mt8195_vpp0_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_VPP0_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(dev, node, vpp0_clks, ARRAY_SIZE(vpp0_clks), clk_data); - if (r) - goto free_vpp0_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_gates: - mtk_clk_unregister_gates(vpp0_clks, ARRAY_SIZE(vpp0_clks), clk_data); -free_vpp0_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8195_vpp0_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(vpp0_clks, ARRAY_SIZE(vpp0_clks), clk_data); - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc vpp0_desc = { + .clks = vpp0_clks, + .num_clks = ARRAY_SIZE(vpp0_clks), +}; - return 0; -} +static const struct platform_device_id clk_mt8195_vpp0_id_table[] = { + { .name = "clk-mt8195-vpp0", .driver_data = (kernel_ulong_t)&vpp0_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8195_vpp0_drv = { - .probe = clk_mt8195_vpp0_probe, - .remove = clk_mt8195_vpp0_remove, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8195-vpp0", }, + .id_table = clk_mt8195_vpp0_id_table, }; builtin_platform_driver(clk_mt8195_vpp0_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp1.c b/drivers/clk/mediatek/clk-mt8195-vpp1.c index e6c458fc1531..794f21cf5e65 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp1.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp1.c @@ -84,54 +84,22 @@ static const struct mtk_gate vpp1_clks[] = { GATE_VPP1_1(CLK_VPP1_VPP_SPLIT_26M, "vpp1_vpp_split_26m", "clk26m", 26), }; -static int clk_mt8195_vpp1_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_VPP1_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_gates(dev, node, vpp1_clks, ARRAY_SIZE(vpp1_clks), clk_data); - if (r) - goto free_vpp1_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_gates: - mtk_clk_unregister_gates(vpp1_clks, ARRAY_SIZE(vpp1_clks), clk_data); -free_vpp1_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8195_vpp1_remove(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - - of_clk_del_provider(node); - mtk_clk_unregister_gates(vpp1_clks, ARRAY_SIZE(vpp1_clks), clk_data); - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc vpp1_desc = { + .clks = vpp1_clks, + .num_clks = ARRAY_SIZE(vpp1_clks), +}; - return 0; -} +static const struct platform_device_id clk_mt8195_vpp1_id_table[] = { + { .name = "clk-mt8195-vpp1", .driver_data = (kernel_ulong_t)&vpp1_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8195_vpp1_drv = { - .probe = clk_mt8195_vpp1_probe, - .remove = clk_mt8195_vpp1_remove, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8195-vpp1", }, + .id_table = clk_mt8195_vpp1_id_table, }; builtin_platform_driver(clk_mt8195_vpp1_drv); diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 22c75a03a645..9569be54127c 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -72,40 +72,23 @@ static const struct mtk_gate mm_clks[] = { GATE_MM1(CLK_MM_LVDSTX_CTS, "mm_flvdstx_cts", "lvdstx_dig_cts", 3), }; -static int clk_mt8365_mm_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *node = dev->parent->of_node; - struct clk_hw_onecell_data *clk_data; - int ret; - - clk_data = mtk_alloc_clk_data(CLK_MM_NR_CLK); - - ret = mtk_clk_register_gates(dev, node, mm_clks, - ARRAY_SIZE(mm_clks), clk_data); - if (ret) - goto err_free_clk_data; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto err_unregister_gates; - - return 0; - -err_unregister_gates: - mtk_clk_unregister_gates(mm_clks, ARRAY_SIZE(mm_clks), clk_data); - -err_free_clk_data: - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc mm_desc = { + .clks = mm_clks, + .num_clks = ARRAY_SIZE(mm_clks), +}; - return ret; -} +static const struct platform_device_id clk_mt8365_mm_id_table[] = { + { .name = "clk-mt8365-mm", .driver_data = (kernel_ulong_t)&mm_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8365_mm_drv = { - .probe = clk_mt8365_mm_probe, + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, .driver = { .name = "clk-mt8365-mm", }, + .id_table = clk_mt8365_mm_id_table, }; builtin_platform_driver(clk_mt8365_mm_drv); MODULE_LICENSE("GPL"); -- GitLab From 1fe074b1f112dc873281ad8de2b2ce57a0c123ad Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:53 +0100 Subject: [PATCH 0347/5631] clk: mediatek: Add divider clocks to mtk_clk_simple_{probe,remove}() Add support for divider clocks register/unregister in the common mtk_clk_simple_probe() and mtk_clk_simple_remove() functions. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-5-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mtk.c | 19 +++++++++++++++++-- drivers/clk/mediatek/clk-mtk.h | 2 ++ 2 files changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 990be3d62db2..01224cfbcc79 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -496,7 +496,7 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, /* Calculate how many clk_hw_onecell_data entries to allocate */ num_clks = mcd->num_clks + mcd->num_composite_clks; num_clks += mcd->num_fixed_clks + mcd->num_factor_clks; - num_clks += mcd->num_mux_clks; + num_clks += mcd->num_mux_clks + mcd->num_divider_clks; clk_data = mtk_alloc_clk_data(num_clks); if (!clk_data) @@ -534,11 +534,19 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, goto unregister_muxes; } + if (mcd->divider_clks) { + r = mtk_clk_register_dividers(mcd->divider_clks, + mcd->num_divider_clks, + base, mcd->clk_lock, clk_data); + if (r) + goto unregister_composites; + } + if (mcd->clks) { r = mtk_clk_register_gates(&pdev->dev, node, mcd->clks, mcd->num_clks, clk_data); if (r) - goto unregister_composites; + goto unregister_dividers; } if (mcd->clk_notifier_func) { @@ -567,6 +575,10 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, unregister_clks: if (mcd->clks) mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); +unregister_dividers: + if (mcd->divider_clks) + mtk_clk_unregister_dividers(mcd->divider_clks, + mcd->num_divider_clks, clk_data); unregister_composites: if (mcd->composite_clks) mtk_clk_unregister_composites(mcd->composite_clks, @@ -599,6 +611,9 @@ static int __mtk_clk_simple_remove(struct platform_device *pdev, of_clk_del_provider(node); if (mcd->clks) mtk_clk_unregister_gates(mcd->clks, mcd->num_clks, clk_data); + if (mcd->divider_clks) + mtk_clk_unregister_dividers(mcd->divider_clks, + mcd->num_divider_clks, clk_data); if (mcd->composite_clks) mtk_clk_unregister_composites(mcd->composite_clks, mcd->num_composite_clks, clk_data); diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h index b8e0ff8f52fa..554aecdc1015 100644 --- a/drivers/clk/mediatek/clk-mtk.h +++ b/drivers/clk/mediatek/clk-mtk.h @@ -222,6 +222,8 @@ struct mtk_clk_desc { size_t num_clks; const struct mtk_composite *composite_clks; size_t num_composite_clks; + const struct mtk_clk_divider *divider_clks; + size_t num_divider_clks; const struct mtk_fixed_clk *fixed_clks; size_t num_fixed_clks; const struct mtk_fixed_factor *factor_clks; -- GitLab From 67798a5bf22d5164b4ae767cc488e1eb83274320 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:54 +0100 Subject: [PATCH 0348/5631] clk: mediatek: mt2712: Migrate topckgen/mcucfg to mtk_clk_simple_probe() Now that the common mtk_clk_simple_{probe,remove}() functions can deal with divider clocks it is possible to migrate more clock drivers to it: in this case, it's about topckgen. While at it, also perform a fast migration for mcucfg. Thanks to the conversion, more error handling was added to the clocks registration. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-6-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2712.c | 127 +++++------------------------- 1 file changed, 21 insertions(+), 106 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index 94f8fc2a4f7b..db20c46e088b 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -36,14 +36,11 @@ static const struct mtk_fixed_clk top_fixed_clks[] = { FIXED_CLK(CLK_TOP_CVBSPLL, "cvbspll", NULL, 108000000), }; -static const struct mtk_fixed_factor top_early_divs[] = { +static const struct mtk_fixed_factor top_divs[] = { FACTOR(CLK_TOP_SYS_26M, "sys_26m", "clk26m", 1, 1), FACTOR(CLK_TOP_CLK26M_D2, "clk26m_d2", "sys_26m", 1, 2), -}; - -static const struct mtk_fixed_factor top_divs[] = { FACTOR(CLK_TOP_ARMCA35PLL, "armca35pll_ck", "armca35pll", 1, 1), FACTOR(CLK_TOP_ARMCA35PLL_600M, "armca35pll_600m", "armca35pll_ck", 1, @@ -1295,114 +1292,30 @@ static int clk_mt2712_apmixed_probe(struct platform_device *pdev) return r; } -static struct clk_hw_onecell_data *top_clk_data; - -static void clk_mt2712_top_init_early(struct device_node *node) -{ - int r, i; - - if (!top_clk_data) { - top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - - for (i = 0; i < CLK_TOP_NR_CLK; i++) - top_clk_data->hws[i] = ERR_PTR(-EPROBE_DEFER); - } - - mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), - top_clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} - -CLK_OF_DECLARE_DRIVER(mt2712_topckgen, "mediatek,mt2712-topckgen", - clk_mt2712_top_init_early); - -static int clk_mt2712_top_probe(struct platform_device *pdev) -{ - int r, i; - struct device_node *node = pdev->dev.of_node; - void __iomem *base; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) { - pr_err("%s(): ioremap failed\n", __func__); - return PTR_ERR(base); - } - - if (!top_clk_data) { - top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - } else { - for (i = 0; i < CLK_TOP_NR_CLK; i++) { - if (top_clk_data->hws[i] == ERR_PTR(-EPROBE_DEFER)) - top_clk_data->hws[i] = ERR_PTR(-ENOENT); - } - } - - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), - top_clk_data); - mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), - top_clk_data); - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); - mtk_clk_register_composites(&pdev->dev, top_muxes, - ARRAY_SIZE(top_muxes), base, - &mt2712_clk_lock, top_clk_data); - mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, - &mt2712_clk_lock, top_clk_data); - mtk_clk_register_gates(&pdev->dev, node, top_clks, - ARRAY_SIZE(top_clks), top_clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); - - if (r != 0) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); - - return r; -} - -static int clk_mt2712_mcu_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - int r; - struct device_node *node = pdev->dev.of_node; - void __iomem *base; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) { - pr_err("%s(): ioremap failed\n", __func__); - return PTR_ERR(base); - } - - clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - - r = mtk_clk_register_composites(&pdev->dev, mcu_muxes, - ARRAY_SIZE(mcu_muxes), base, - &mt2712_clk_lock, clk_data); - if (r) - dev_err(&pdev->dev, "Could not register composites: %d\n", r); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - - if (r != 0) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct mtk_clk_desc topck_desc = { + .clks = top_clks, + .num_clks = ARRAY_SIZE(top_clks), + .fixed_clks = top_fixed_clks, + .num_fixed_clks = ARRAY_SIZE(top_fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .composite_clks = top_muxes, + .num_composite_clks = ARRAY_SIZE(top_muxes), + .divider_clks = top_adj_divs, + .num_divider_clks = ARRAY_SIZE(top_adj_divs), + .clk_lock = &mt2712_clk_lock, +}; - return r; -} +static const struct mtk_clk_desc mcu_desc = { + .composite_clks = mcu_muxes, + .num_composite_clks = ARRAY_SIZE(mcu_muxes), + .clk_lock = &mt2712_clk_lock, +}; static const struct of_device_id of_match_clk_mt2712[] = { { .compatible = "mediatek,mt2712-apmixedsys", .data = clk_mt2712_apmixed_probe, - }, { - .compatible = "mediatek,mt2712-topckgen", - .data = clk_mt2712_top_probe, - }, { - .compatible = "mediatek,mt2712-mcucfg", - .data = clk_mt2712_mcu_probe, }, { /* sentinel */ } @@ -1440,7 +1353,9 @@ static const struct mtk_clk_desc peri_desc = { static const struct of_device_id of_match_clk_mt2712_simple[] = { { .compatible = "mediatek,mt2712-infracfg", .data = &infra_desc }, + { .compatible = "mediatek,mt2712-mcucfg", .data = &mcu_desc }, { .compatible = "mediatek,mt2712-pericfg", .data = &peri_desc, }, + { .compatible = "mediatek,mt2712-topckgen", .data = &topck_desc }, { /* sentinel */ } }; -- GitLab From f8c3e0e3f31b36ed6b96e437b00fe853cd46a977 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:55 +0100 Subject: [PATCH 0349/5631] clk: mediatek: mt2712: Compress clock arrays entries to 90 columns Compress the clock arrays entries to allow a maximum of 90 columns: this greatly increases readability and also generously reduces the amount of lines. While at it, also fix some indentation here and there. This is a cosmetic change. No functional changes. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-7-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2712.c | 681 +++++++++++------------------- 1 file changed, 246 insertions(+), 435 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index db20c46e088b..ce28ee47f5cf 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -37,184 +37,95 @@ static const struct mtk_fixed_clk top_fixed_clks[] = { }; static const struct mtk_fixed_factor top_divs[] = { - FACTOR(CLK_TOP_SYS_26M, "sys_26m", "clk26m", 1, - 1), - FACTOR(CLK_TOP_CLK26M_D2, "clk26m_d2", "sys_26m", 1, - 2), - FACTOR(CLK_TOP_ARMCA35PLL, "armca35pll_ck", "armca35pll", 1, - 1), - FACTOR(CLK_TOP_ARMCA35PLL_600M, "armca35pll_600m", "armca35pll_ck", 1, - 2), - FACTOR(CLK_TOP_ARMCA35PLL_400M, "armca35pll_400m", "armca35pll_ck", 1, - 3), - FACTOR(CLK_TOP_ARMCA72PLL, "armca72pll_ck", "armca72pll", 1, - 1), - FACTOR(CLK_TOP_SYSPLL, "syspll_ck", "mainpll", 1, - 1), - FACTOR(CLK_TOP_SYSPLL_D2, "syspll_d2", "syspll_ck", 1, - 2), - FACTOR(CLK_TOP_SYSPLL1_D2, "syspll1_d2", "syspll_d2", 1, - 2), - FACTOR(CLK_TOP_SYSPLL1_D4, "syspll1_d4", "syspll_d2", 1, - 4), - FACTOR(CLK_TOP_SYSPLL1_D8, "syspll1_d8", "syspll_d2", 1, - 8), - FACTOR(CLK_TOP_SYSPLL1_D16, "syspll1_d16", "syspll_d2", 1, - 16), - FACTOR(CLK_TOP_SYSPLL_D3, "syspll_d3", "syspll_ck", 1, - 3), - FACTOR(CLK_TOP_SYSPLL2_D2, "syspll2_d2", "syspll_d3", 1, - 2), - FACTOR(CLK_TOP_SYSPLL2_D4, "syspll2_d4", "syspll_d3", 1, - 4), - FACTOR(CLK_TOP_SYSPLL_D5, "syspll_d5", "syspll_ck", 1, - 5), - FACTOR(CLK_TOP_SYSPLL3_D2, "syspll3_d2", "syspll_d5", 1, - 2), - FACTOR(CLK_TOP_SYSPLL3_D4, "syspll3_d4", "syspll_d5", 1, - 4), - FACTOR(CLK_TOP_SYSPLL_D7, "syspll_d7", "syspll_ck", 1, - 7), - FACTOR(CLK_TOP_SYSPLL4_D2, "syspll4_d2", "syspll_d7", 1, - 2), - FACTOR(CLK_TOP_SYSPLL4_D4, "syspll4_d4", "syspll_d7", 1, - 4), - FACTOR(CLK_TOP_UNIVPLL, "univpll_ck", "univpll", 1, - 1), - FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univpll_ck", 1, - 7), - FACTOR(CLK_TOP_UNIVPLL_D26, "univpll_d26", "univpll_ck", 1, - 26), - FACTOR(CLK_TOP_UNIVPLL_D52, "univpll_d52", "univpll_ck", 1, - 52), - FACTOR(CLK_TOP_UNIVPLL_D104, "univpll_d104", "univpll_ck", 1, - 104), - FACTOR(CLK_TOP_UNIVPLL_D208, "univpll_d208", "univpll_ck", 1, - 208), - FACTOR(CLK_TOP_UNIVPLL_D2, "univpll_d2", "univpll_ck", 1, - 2), - FACTOR(CLK_TOP_UNIVPLL1_D2, "univpll1_d2", "univpll_d2", 1, - 2), - FACTOR(CLK_TOP_UNIVPLL1_D4, "univpll1_d4", "univpll_d2", 1, - 4), - FACTOR(CLK_TOP_UNIVPLL1_D8, "univpll1_d8", "univpll_d2", 1, - 8), - FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univpll_ck", 1, - 3), - FACTOR(CLK_TOP_UNIVPLL2_D2, "univpll2_d2", "univpll_d3", 1, - 2), - FACTOR(CLK_TOP_UNIVPLL2_D4, "univpll2_d4", "univpll_d3", 1, - 4), - FACTOR(CLK_TOP_UNIVPLL2_D8, "univpll2_d8", "univpll_d3", 1, - 8), - FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univpll_ck", 1, - 5), - FACTOR(CLK_TOP_UNIVPLL3_D2, "univpll3_d2", "univpll_d5", 1, - 2), - FACTOR(CLK_TOP_UNIVPLL3_D4, "univpll3_d4", "univpll_d5", 1, - 4), - FACTOR(CLK_TOP_UNIVPLL3_D8, "univpll3_d8", "univpll_d5", 1, - 8), - FACTOR(CLK_TOP_F_MP0_PLL1, "f_mp0_pll1_ck", "univpll_d2", 1, - 1), - FACTOR(CLK_TOP_F_MP0_PLL2, "f_mp0_pll2_ck", "univpll1_d2", 1, - 1), - FACTOR(CLK_TOP_F_BIG_PLL1, "f_big_pll1_ck", "univpll_d2", 1, - 1), - FACTOR(CLK_TOP_F_BIG_PLL2, "f_big_pll2_ck", "univpll1_d2", 1, - 1), - FACTOR(CLK_TOP_F_BUS_PLL1, "f_bus_pll1_ck", "univpll_d2", 1, - 1), - FACTOR(CLK_TOP_F_BUS_PLL2, "f_bus_pll2_ck", "univpll1_d2", 1, - 1), - FACTOR(CLK_TOP_APLL1, "apll1_ck", "apll1", 1, - 1), - FACTOR(CLK_TOP_APLL1_D2, "apll1_d2", "apll1_ck", 1, - 2), - FACTOR(CLK_TOP_APLL1_D4, "apll1_d4", "apll1_ck", 1, - 4), - FACTOR(CLK_TOP_APLL1_D8, "apll1_d8", "apll1_ck", 1, - 8), - FACTOR(CLK_TOP_APLL1_D16, "apll1_d16", "apll1_ck", 1, - 16), - FACTOR(CLK_TOP_APLL2, "apll2_ck", "apll2", 1, - 1), - FACTOR(CLK_TOP_APLL2_D2, "apll2_d2", "apll2_ck", 1, - 2), - FACTOR(CLK_TOP_APLL2_D4, "apll2_d4", "apll2_ck", 1, - 4), - FACTOR(CLK_TOP_APLL2_D8, "apll2_d8", "apll2_ck", 1, - 8), - FACTOR(CLK_TOP_APLL2_D16, "apll2_d16", "apll2_ck", 1, - 16), - FACTOR(CLK_TOP_LVDSPLL, "lvdspll_ck", "lvdspll", 1, - 1), - FACTOR(CLK_TOP_LVDSPLL_D2, "lvdspll_d2", "lvdspll_ck", 1, - 2), - FACTOR(CLK_TOP_LVDSPLL_D4, "lvdspll_d4", "lvdspll_ck", 1, - 4), - FACTOR(CLK_TOP_LVDSPLL_D8, "lvdspll_d8", "lvdspll_ck", 1, - 8), - FACTOR(CLK_TOP_LVDSPLL2, "lvdspll2_ck", "lvdspll2", 1, - 1), - FACTOR(CLK_TOP_LVDSPLL2_D2, "lvdspll2_d2", "lvdspll2_ck", 1, - 2), - FACTOR(CLK_TOP_LVDSPLL2_D4, "lvdspll2_d4", "lvdspll2_ck", 1, - 4), - FACTOR(CLK_TOP_LVDSPLL2_D8, "lvdspll2_d8", "lvdspll2_ck", 1, - 8), - FACTOR(CLK_TOP_ETHERPLL_125M, "etherpll_125m", "etherpll", 1, - 1), - FACTOR(CLK_TOP_ETHERPLL_50M, "etherpll_50m", "etherpll", 1, - 1), - FACTOR(CLK_TOP_CVBS, "cvbs", "cvbspll", 1, - 1), - FACTOR(CLK_TOP_CVBS_D2, "cvbs_d2", "cvbs", 1, - 2), - FACTOR(CLK_TOP_MMPLL, "mmpll_ck", "mmpll", 1, - 1), - FACTOR(CLK_TOP_MMPLL_D2, "mmpll_d2", "mmpll_ck", 1, - 2), - FACTOR(CLK_TOP_VENCPLL, "vencpll_ck", "vencpll", 1, - 1), - FACTOR(CLK_TOP_VENCPLL_D2, "vencpll_d2", "vencpll_ck", 1, - 2), - FACTOR(CLK_TOP_VCODECPLL, "vcodecpll_ck", "vcodecpll", 1, - 1), - FACTOR(CLK_TOP_VCODECPLL_D2, "vcodecpll_d2", "vcodecpll_ck", 1, - 2), - FACTOR(CLK_TOP_TVDPLL, "tvdpll_ck", "tvdpll", 1, - 1), - FACTOR(CLK_TOP_TVDPLL_D2, "tvdpll_d2", "tvdpll_ck", 1, - 2), - FACTOR(CLK_TOP_TVDPLL_D4, "tvdpll_d4", "tvdpll_ck", 1, - 4), - FACTOR(CLK_TOP_TVDPLL_D8, "tvdpll_d8", "tvdpll_ck", 1, - 8), - FACTOR(CLK_TOP_TVDPLL_429M, "tvdpll_429m", "tvdpll", 1, - 1), - FACTOR(CLK_TOP_TVDPLL_429M_D2, "tvdpll_429m_d2", "tvdpll_429m", 1, - 2), - FACTOR(CLK_TOP_TVDPLL_429M_D4, "tvdpll_429m_d4", "tvdpll_429m", 1, - 4), - FACTOR(CLK_TOP_MSDCPLL, "msdcpll_ck", "msdcpll", 1, - 1), - FACTOR(CLK_TOP_MSDCPLL_D2, "msdcpll_d2", "msdcpll_ck", 1, - 2), - FACTOR(CLK_TOP_MSDCPLL_D4, "msdcpll_d4", "msdcpll_ck", 1, - 4), - FACTOR(CLK_TOP_MSDCPLL2, "msdcpll2_ck", "msdcpll2", 1, - 1), - FACTOR(CLK_TOP_MSDCPLL2_D2, "msdcpll2_d2", "msdcpll2_ck", 1, - 2), - FACTOR(CLK_TOP_MSDCPLL2_D4, "msdcpll2_d4", "msdcpll2_ck", 1, - 4), - FACTOR(CLK_TOP_D2A_ULCLK_6P5M, "d2a_ulclk_6p5m", "clk26m", 1, - 4), - FACTOR(CLK_TOP_APLL1_D3, "apll1_d3", "apll1_ck", 1, - 3), - FACTOR(CLK_TOP_APLL2_D3, "apll2_d3", "apll2_ck", 1, - 3), + FACTOR(CLK_TOP_SYS_26M, "sys_26m", "clk26m", 1, 1), + FACTOR(CLK_TOP_CLK26M_D2, "clk26m_d2", "sys_26m", 1, 2), + FACTOR(CLK_TOP_ARMCA35PLL, "armca35pll_ck", "armca35pll", 1, 1), + FACTOR(CLK_TOP_ARMCA35PLL_600M, "armca35pll_600m", "armca35pll_ck", 1, 2), + FACTOR(CLK_TOP_ARMCA35PLL_400M, "armca35pll_400m", "armca35pll_ck", 1, 3), + FACTOR(CLK_TOP_ARMCA72PLL, "armca72pll_ck", "armca72pll", 1, 1), + FACTOR(CLK_TOP_SYSPLL, "syspll_ck", "mainpll", 1, 1), + FACTOR(CLK_TOP_SYSPLL_D2, "syspll_d2", "syspll_ck", 1, 2), + FACTOR(CLK_TOP_SYSPLL1_D2, "syspll1_d2", "syspll_d2", 1, 2), + FACTOR(CLK_TOP_SYSPLL1_D4, "syspll1_d4", "syspll_d2", 1, 4), + FACTOR(CLK_TOP_SYSPLL1_D8, "syspll1_d8", "syspll_d2", 1, 8), + FACTOR(CLK_TOP_SYSPLL1_D16, "syspll1_d16", "syspll_d2", 1, 16), + FACTOR(CLK_TOP_SYSPLL_D3, "syspll_d3", "syspll_ck", 1, 3), + FACTOR(CLK_TOP_SYSPLL2_D2, "syspll2_d2", "syspll_d3", 1, 2), + FACTOR(CLK_TOP_SYSPLL2_D4, "syspll2_d4", "syspll_d3", 1, 4), + FACTOR(CLK_TOP_SYSPLL_D5, "syspll_d5", "syspll_ck", 1, 5), + FACTOR(CLK_TOP_SYSPLL3_D2, "syspll3_d2", "syspll_d5", 1, 2), + FACTOR(CLK_TOP_SYSPLL3_D4, "syspll3_d4", "syspll_d5", 1, 4), + FACTOR(CLK_TOP_SYSPLL_D7, "syspll_d7", "syspll_ck", 1, 7), + FACTOR(CLK_TOP_SYSPLL4_D2, "syspll4_d2", "syspll_d7", 1, 2), + FACTOR(CLK_TOP_SYSPLL4_D4, "syspll4_d4", "syspll_d7", 1, 4), + FACTOR(CLK_TOP_UNIVPLL, "univpll_ck", "univpll", 1, 1), + FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univpll_ck", 1, 7), + FACTOR(CLK_TOP_UNIVPLL_D26, "univpll_d26", "univpll_ck", 1, 26), + FACTOR(CLK_TOP_UNIVPLL_D52, "univpll_d52", "univpll_ck", 1, 52), + FACTOR(CLK_TOP_UNIVPLL_D104, "univpll_d104", "univpll_ck", 1, 104), + FACTOR(CLK_TOP_UNIVPLL_D208, "univpll_d208", "univpll_ck", 1, 208), + FACTOR(CLK_TOP_UNIVPLL_D2, "univpll_d2", "univpll_ck", 1, 2), + FACTOR(CLK_TOP_UNIVPLL1_D2, "univpll1_d2", "univpll_d2", 1, 2), + FACTOR(CLK_TOP_UNIVPLL1_D4, "univpll1_d4", "univpll_d2", 1, 4), + FACTOR(CLK_TOP_UNIVPLL1_D8, "univpll1_d8", "univpll_d2", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univpll_ck", 1, 3), + FACTOR(CLK_TOP_UNIVPLL2_D2, "univpll2_d2", "univpll_d3", 1, 2), + FACTOR(CLK_TOP_UNIVPLL2_D4, "univpll2_d4", "univpll_d3", 1, 4), + FACTOR(CLK_TOP_UNIVPLL2_D8, "univpll2_d8", "univpll_d3", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univpll_ck", 1, 5), + FACTOR(CLK_TOP_UNIVPLL3_D2, "univpll3_d2", "univpll_d5", 1, 2), + FACTOR(CLK_TOP_UNIVPLL3_D4, "univpll3_d4", "univpll_d5", 1, 4), + FACTOR(CLK_TOP_UNIVPLL3_D8, "univpll3_d8", "univpll_d5", 1, 8), + FACTOR(CLK_TOP_F_MP0_PLL1, "f_mp0_pll1_ck", "univpll_d2", 1, 1), + FACTOR(CLK_TOP_F_MP0_PLL2, "f_mp0_pll2_ck", "univpll1_d2", 1, 1), + FACTOR(CLK_TOP_F_BIG_PLL1, "f_big_pll1_ck", "univpll_d2", 1, 1), + FACTOR(CLK_TOP_F_BIG_PLL2, "f_big_pll2_ck", "univpll1_d2", 1, 1), + FACTOR(CLK_TOP_F_BUS_PLL1, "f_bus_pll1_ck", "univpll_d2", 1, 1), + FACTOR(CLK_TOP_F_BUS_PLL2, "f_bus_pll2_ck", "univpll1_d2", 1, 1), + FACTOR(CLK_TOP_APLL1, "apll1_ck", "apll1", 1, 1), + FACTOR(CLK_TOP_APLL1_D2, "apll1_d2", "apll1_ck", 1, 2), + FACTOR(CLK_TOP_APLL1_D4, "apll1_d4", "apll1_ck", 1, 4), + FACTOR(CLK_TOP_APLL1_D8, "apll1_d8", "apll1_ck", 1, 8), + FACTOR(CLK_TOP_APLL1_D16, "apll1_d16", "apll1_ck", 1, 16), + FACTOR(CLK_TOP_APLL2, "apll2_ck", "apll2", 1, 1), + FACTOR(CLK_TOP_APLL2_D2, "apll2_d2", "apll2_ck", 1, 2), + FACTOR(CLK_TOP_APLL2_D4, "apll2_d4", "apll2_ck", 1, 4), + FACTOR(CLK_TOP_APLL2_D8, "apll2_d8", "apll2_ck", 1, 8), + FACTOR(CLK_TOP_APLL2_D16, "apll2_d16", "apll2_ck", 1, 16), + FACTOR(CLK_TOP_LVDSPLL, "lvdspll_ck", "lvdspll", 1, 1), + FACTOR(CLK_TOP_LVDSPLL_D2, "lvdspll_d2", "lvdspll_ck", 1, 2), + FACTOR(CLK_TOP_LVDSPLL_D4, "lvdspll_d4", "lvdspll_ck", 1, 4), + FACTOR(CLK_TOP_LVDSPLL_D8, "lvdspll_d8", "lvdspll_ck", 1, 8), + FACTOR(CLK_TOP_LVDSPLL2, "lvdspll2_ck", "lvdspll2", 1, 1), + FACTOR(CLK_TOP_LVDSPLL2_D2, "lvdspll2_d2", "lvdspll2_ck", 1, 2), + FACTOR(CLK_TOP_LVDSPLL2_D4, "lvdspll2_d4", "lvdspll2_ck", 1, 4), + FACTOR(CLK_TOP_LVDSPLL2_D8, "lvdspll2_d8", "lvdspll2_ck", 1, 8), + FACTOR(CLK_TOP_ETHERPLL_125M, "etherpll_125m", "etherpll", 1, 1), + FACTOR(CLK_TOP_ETHERPLL_50M, "etherpll_50m", "etherpll", 1, 1), + FACTOR(CLK_TOP_CVBS, "cvbs", "cvbspll", 1, 1), + FACTOR(CLK_TOP_CVBS_D2, "cvbs_d2", "cvbs", 1, 2), + FACTOR(CLK_TOP_MMPLL, "mmpll_ck", "mmpll", 1, 1), + FACTOR(CLK_TOP_MMPLL_D2, "mmpll_d2", "mmpll_ck", 1, 2), + FACTOR(CLK_TOP_VENCPLL, "vencpll_ck", "vencpll", 1, 1), + FACTOR(CLK_TOP_VENCPLL_D2, "vencpll_d2", "vencpll_ck", 1, 2), + FACTOR(CLK_TOP_VCODECPLL, "vcodecpll_ck", "vcodecpll", 1, 1), + FACTOR(CLK_TOP_VCODECPLL_D2, "vcodecpll_d2", "vcodecpll_ck", 1, 2), + FACTOR(CLK_TOP_TVDPLL, "tvdpll_ck", "tvdpll", 1, 1), + FACTOR(CLK_TOP_TVDPLL_D2, "tvdpll_d2", "tvdpll_ck", 1, 2), + FACTOR(CLK_TOP_TVDPLL_D4, "tvdpll_d4", "tvdpll_ck", 1, 4), + FACTOR(CLK_TOP_TVDPLL_D8, "tvdpll_d8", "tvdpll_ck", 1, 8), + FACTOR(CLK_TOP_TVDPLL_429M, "tvdpll_429m", "tvdpll", 1, 1), + FACTOR(CLK_TOP_TVDPLL_429M_D2, "tvdpll_429m_d2", "tvdpll_429m", 1, 2), + FACTOR(CLK_TOP_TVDPLL_429M_D4, "tvdpll_429m_d4", "tvdpll_429m", 1, 4), + FACTOR(CLK_TOP_MSDCPLL, "msdcpll_ck", "msdcpll", 1, 1), + FACTOR(CLK_TOP_MSDCPLL_D2, "msdcpll_d2", "msdcpll_ck", 1, 2), + FACTOR(CLK_TOP_MSDCPLL_D4, "msdcpll_d4", "msdcpll_ck", 1, 4), + FACTOR(CLK_TOP_MSDCPLL2, "msdcpll2_ck", "msdcpll2", 1, 1), + FACTOR(CLK_TOP_MSDCPLL2_D2, "msdcpll2_d2", "msdcpll2_ck", 1, 2), + FACTOR(CLK_TOP_MSDCPLL2_D4, "msdcpll2_d4", "msdcpll2_ck", 1, 4), + FACTOR(CLK_TOP_D2A_ULCLK_6P5M, "d2a_ulclk_6p5m", "clk26m", 1, 4), + FACTOR(CLK_TOP_APLL1_D3, "apll1_d3", "apll1_ck", 1, 3), + FACTOR(CLK_TOP_APLL2_D3, "apll2_d3", "apll2_ck", 1, 3), }; static const char * const axi_parents[] = { @@ -734,169 +645,118 @@ static const char * const audull_vtx_parents[] = { static struct mtk_composite top_muxes[] = { /* CLK_CFG_0 */ MUX_GATE_FLAGS(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, 0x040, 0, 3, - 7, CLK_IS_CRITICAL), + 7, CLK_IS_CRITICAL), MUX_GATE_FLAGS(CLK_TOP_MEM_SEL, "mem_sel", mem_parents, 0x040, 8, 1, - 15, CLK_IS_CRITICAL), - MUX_GATE(CLK_TOP_MM_SEL, "mm_sel", - mm_parents, 0x040, 24, 3, 31), + 15, CLK_IS_CRITICAL), + MUX_GATE(CLK_TOP_MM_SEL, "mm_sel", mm_parents, 0x040, 24, 3, 31), /* CLK_CFG_1 */ - MUX_GATE(CLK_TOP_PWM_SEL, "pwm_sel", - pwm_parents, 0x050, 0, 2, 7), - MUX_GATE(CLK_TOP_VDEC_SEL, "vdec_sel", - vdec_parents, 0x050, 8, 4, 15), - MUX_GATE(CLK_TOP_VENC_SEL, "venc_sel", - venc_parents, 0x050, 16, 4, 23), - MUX_GATE(CLK_TOP_MFG_SEL, "mfg_sel", - mfg_parents, 0x050, 24, 4, 31), + MUX_GATE(CLK_TOP_PWM_SEL, "pwm_sel", pwm_parents, 0x050, 0, 2, 7), + MUX_GATE(CLK_TOP_VDEC_SEL, "vdec_sel", vdec_parents, 0x050, 8, 4, 15), + MUX_GATE(CLK_TOP_VENC_SEL, "venc_sel", venc_parents, 0x050, 16, 4, 23), + MUX_GATE(CLK_TOP_MFG_SEL, "mfg_sel", mfg_parents, 0x050, 24, 4, 31), /* CLK_CFG_2 */ - MUX_GATE(CLK_TOP_CAMTG_SEL, "camtg_sel", - camtg_parents, 0x060, 0, 4, 7), - MUX_GATE(CLK_TOP_UART_SEL, "uart_sel", - uart_parents, 0x060, 8, 1, 15), - MUX_GATE(CLK_TOP_SPI_SEL, "spi_sel", - spi_parents, 0x060, 16, 3, 23), - MUX_GATE(CLK_TOP_USB20_SEL, "usb20_sel", - usb20_parents, 0x060, 24, 2, 31), + MUX_GATE(CLK_TOP_CAMTG_SEL, "camtg_sel", camtg_parents, 0x060, 0, 4, 7), + MUX_GATE(CLK_TOP_UART_SEL, "uart_sel", uart_parents, 0x060, 8, 1, 15), + MUX_GATE(CLK_TOP_SPI_SEL, "spi_sel", spi_parents, 0x060, 16, 3, 23), + MUX_GATE(CLK_TOP_USB20_SEL, "usb20_sel", usb20_parents, 0x060, 24, 2, 31), /* CLK_CFG_3 */ - MUX_GATE(CLK_TOP_USB30_SEL, "usb30_sel", - usb30_parents, 0x070, 0, 2, 7), - MUX_GATE(CLK_TOP_MSDC50_0_HCLK_SEL, "msdc50_0_h_sel", - msdc50_0_h_parents, 0x070, 8, 3, 15), - MUX_GATE(CLK_TOP_MSDC50_0_SEL, "msdc50_0_sel", - msdc50_0_parents, 0x070, 16, 4, 23), - MUX_GATE(CLK_TOP_MSDC30_1_SEL, "msdc30_1_sel", - msdc30_1_parents, 0x070, 24, 3, 31), + MUX_GATE(CLK_TOP_USB30_SEL, "usb30_sel", usb30_parents, 0x070, 0, 2, 7), + MUX_GATE(CLK_TOP_MSDC50_0_HCLK_SEL, "msdc50_0_h_sel", msdc50_0_h_parents, + 0x070, 8, 3, 15), + MUX_GATE(CLK_TOP_MSDC50_0_SEL, "msdc50_0_sel", msdc50_0_parents, + 0x070, 16, 4, 23), + MUX_GATE(CLK_TOP_MSDC30_1_SEL, "msdc30_1_sel", msdc30_1_parents, + 0x070, 24, 3, 31), /* CLK_CFG_4 */ - MUX_GATE(CLK_TOP_MSDC30_2_SEL, "msdc30_2_sel", - msdc30_1_parents, 0x080, 0, 3, 7), - MUX_GATE(CLK_TOP_MSDC30_3_SEL, "msdc30_3_sel", - msdc30_3_parents, 0x080, 8, 4, 15), - MUX_GATE(CLK_TOP_AUDIO_SEL, "audio_sel", - audio_parents, 0x080, 16, 2, 23), - MUX_GATE(CLK_TOP_AUD_INTBUS_SEL, "aud_intbus_sel", - aud_intbus_parents, 0x080, 24, 3, 31), + MUX_GATE(CLK_TOP_MSDC30_2_SEL, "msdc30_2_sel", msdc30_1_parents, + 0x080, 0, 3, 7), + MUX_GATE(CLK_TOP_MSDC30_3_SEL, "msdc30_3_sel", msdc30_3_parents, + 0x080, 8, 4, 15), + MUX_GATE(CLK_TOP_AUDIO_SEL, "audio_sel", audio_parents, + 0x080, 16, 2, 23), + MUX_GATE(CLK_TOP_AUD_INTBUS_SEL, "aud_intbus_sel", aud_intbus_parents, + 0x080, 24, 3, 31), /* CLK_CFG_5 */ - MUX_GATE(CLK_TOP_PMICSPI_SEL, "pmicspi_sel", - pmicspi_parents, 0x090, 0, 3, 7), - MUX_GATE(CLK_TOP_DPILVDS1_SEL, "dpilvds1_sel", - dpilvds1_parents, 0x090, 8, 3, 15), - MUX_GATE(CLK_TOP_ATB_SEL, "atb_sel", - atb_parents, 0x090, 16, 2, 23), - MUX_GATE(CLK_TOP_NR_SEL, "nr_sel", - nr_parents, 0x090, 24, 3, 31), + MUX_GATE(CLK_TOP_PMICSPI_SEL, "pmicspi_sel", pmicspi_parents, 0x090, 0, 3, 7), + MUX_GATE(CLK_TOP_DPILVDS1_SEL, "dpilvds1_sel", dpilvds1_parents, + 0x090, 8, 3, 15), + MUX_GATE(CLK_TOP_ATB_SEL, "atb_sel", atb_parents, 0x090, 16, 2, 23), + MUX_GATE(CLK_TOP_NR_SEL, "nr_sel", nr_parents, 0x090, 24, 3, 31), /* CLK_CFG_6 */ - MUX_GATE(CLK_TOP_NFI2X_SEL, "nfi2x_sel", - nfi2x_parents, 0x0a0, 0, 4, 7), - MUX_GATE(CLK_TOP_IRDA_SEL, "irda_sel", - irda_parents, 0x0a0, 8, 2, 15), - MUX_GATE(CLK_TOP_CCI400_SEL, "cci400_sel", - cci400_parents, 0x0a0, 16, 3, 23), - MUX_GATE(CLK_TOP_AUD_1_SEL, "aud_1_sel", - aud_1_parents, 0x0a0, 24, 2, 31), + MUX_GATE(CLK_TOP_NFI2X_SEL, "nfi2x_sel", nfi2x_parents, 0x0a0, 0, 4, 7), + MUX_GATE(CLK_TOP_IRDA_SEL, "irda_sel", irda_parents, 0x0a0, 8, 2, 15), + MUX_GATE(CLK_TOP_CCI400_SEL, "cci400_sel", cci400_parents, 0x0a0, 16, 3, 23), + MUX_GATE(CLK_TOP_AUD_1_SEL, "aud_1_sel", aud_1_parents, 0x0a0, 24, 2, 31), /* CLK_CFG_7 */ - MUX_GATE(CLK_TOP_AUD_2_SEL, "aud_2_sel", - aud_2_parents, 0x0b0, 0, 2, 7), - MUX_GATE(CLK_TOP_MEM_MFG_IN_AS_SEL, "mem_mfg_sel", - mem_mfg_parents, 0x0b0, 8, 2, 15), - MUX_GATE(CLK_TOP_AXI_MFG_IN_AS_SEL, "axi_mfg_sel", - axi_mfg_parents, 0x0b0, 16, 2, 23), - MUX_GATE(CLK_TOP_SCAM_SEL, "scam_sel", - scam_parents, 0x0b0, 24, 2, 31), + MUX_GATE(CLK_TOP_AUD_2_SEL, "aud_2_sel", aud_2_parents, 0x0b0, 0, 2, 7), + MUX_GATE(CLK_TOP_MEM_MFG_IN_AS_SEL, "mem_mfg_sel", mem_mfg_parents, + 0x0b0, 8, 2, 15), + MUX_GATE(CLK_TOP_AXI_MFG_IN_AS_SEL, "axi_mfg_sel", axi_mfg_parents, + 0x0b0, 16, 2, 23), + MUX_GATE(CLK_TOP_SCAM_SEL, "scam_sel", scam_parents, 0x0b0, 24, 2, 31), /* CLK_CFG_8 */ - MUX_GATE(CLK_TOP_NFIECC_SEL, "nfiecc_sel", - nfiecc_parents, 0x0c0, 0, 3, 7), - MUX_GATE(CLK_TOP_PE2_MAC_P0_SEL, "pe2_mac_p0_sel", - pe2_mac_p0_parents, 0x0c0, 8, 3, 15), - MUX_GATE(CLK_TOP_PE2_MAC_P1_SEL, "pe2_mac_p1_sel", - pe2_mac_p0_parents, 0x0c0, 16, 3, 23), - MUX_GATE(CLK_TOP_DPILVDS_SEL, "dpilvds_sel", - dpilvds_parents, 0x0c0, 24, 3, 31), + MUX_GATE(CLK_TOP_NFIECC_SEL, "nfiecc_sel", nfiecc_parents, 0x0c0, 0, 3, 7), + MUX_GATE(CLK_TOP_PE2_MAC_P0_SEL, "pe2_mac_p0_sel", pe2_mac_p0_parents, + 0x0c0, 8, 3, 15), + MUX_GATE(CLK_TOP_PE2_MAC_P1_SEL, "pe2_mac_p1_sel", pe2_mac_p0_parents, + 0x0c0, 16, 3, 23), + MUX_GATE(CLK_TOP_DPILVDS_SEL, "dpilvds_sel", dpilvds_parents, 0x0c0, 24, 3, 31), /* CLK_CFG_9 */ - MUX_GATE(CLK_TOP_MSDC50_3_HCLK_SEL, "msdc50_3_h_sel", - msdc50_0_h_parents, 0x0d0, 0, 3, 7), - MUX_GATE(CLK_TOP_HDCP_SEL, "hdcp_sel", - hdcp_parents, 0x0d0, 8, 2, 15), - MUX_GATE(CLK_TOP_HDCP_24M_SEL, "hdcp_24m_sel", - hdcp_24m_parents, 0x0d0, 16, 2, 23), - MUX_GATE_FLAGS(CLK_TOP_RTC_SEL, "rtc_sel", rtc_parents, 0x0d0, 24, 2, - 31, CLK_IS_CRITICAL), + MUX_GATE(CLK_TOP_MSDC50_3_HCLK_SEL, "msdc50_3_h_sel", msdc50_0_h_parents, + 0x0d0, 0, 3, 7), + MUX_GATE(CLK_TOP_HDCP_SEL, "hdcp_sel", hdcp_parents, 0x0d0, 8, 2, 15), + MUX_GATE(CLK_TOP_HDCP_24M_SEL, "hdcp_24m_sel", hdcp_24m_parents, + 0x0d0, 16, 2, 23), + MUX_GATE_FLAGS(CLK_TOP_RTC_SEL, "rtc_sel", rtc_parents, + 0x0d0, 24, 2, 31, CLK_IS_CRITICAL), /* CLK_CFG_10 */ - MUX_GATE(CLK_TOP_SPINOR_SEL, "spinor_sel", - spinor_parents, 0x500, 0, 4, 7), - MUX_GATE(CLK_TOP_APLL_SEL, "apll_sel", - apll_parents, 0x500, 8, 4, 15), - MUX_GATE(CLK_TOP_APLL2_SEL, "apll2_sel", - apll_parents, 0x500, 16, 4, 23), - MUX_GATE(CLK_TOP_A1SYS_HP_SEL, "a1sys_hp_sel", - a1sys_hp_parents, 0x500, 24, 3, 31), + MUX_GATE(CLK_TOP_SPINOR_SEL, "spinor_sel", spinor_parents, 0x500, 0, 4, 7), + MUX_GATE(CLK_TOP_APLL_SEL, "apll_sel", apll_parents, 0x500, 8, 4, 15), + MUX_GATE(CLK_TOP_APLL2_SEL, "apll2_sel", apll_parents, 0x500, 16, 4, 23), + MUX_GATE(CLK_TOP_A1SYS_HP_SEL, "a1sys_hp_sel", a1sys_hp_parents, + 0x500, 24, 3, 31), /* CLK_CFG_11 */ - MUX_GATE(CLK_TOP_A2SYS_HP_SEL, "a2sys_hp_sel", - a2sys_hp_parents, 0x510, 0, 3, 7), - MUX_GATE(CLK_TOP_ASM_L_SEL, "asm_l_sel", - asm_l_parents, 0x510, 8, 2, 15), - MUX_GATE(CLK_TOP_ASM_M_SEL, "asm_m_sel", - asm_l_parents, 0x510, 16, 2, 23), - MUX_GATE(CLK_TOP_ASM_H_SEL, "asm_h_sel", - asm_l_parents, 0x510, 24, 2, 31), + MUX_GATE(CLK_TOP_A2SYS_HP_SEL, "a2sys_hp_sel", a2sys_hp_parents, 0x510, 0, 3, 7), + MUX_GATE(CLK_TOP_ASM_L_SEL, "asm_l_sel", asm_l_parents, 0x510, 8, 2, 15), + MUX_GATE(CLK_TOP_ASM_M_SEL, "asm_m_sel", asm_l_parents, 0x510, 16, 2, 23), + MUX_GATE(CLK_TOP_ASM_H_SEL, "asm_h_sel", asm_l_parents, 0x510, 24, 2, 31), /* CLK_CFG_12 */ - MUX_GATE(CLK_TOP_I2SO1_SEL, "i2so1_sel", - i2so1_parents, 0x520, 0, 2, 7), - MUX_GATE(CLK_TOP_I2SO2_SEL, "i2so2_sel", - i2so1_parents, 0x520, 8, 2, 15), - MUX_GATE(CLK_TOP_I2SO3_SEL, "i2so3_sel", - i2so1_parents, 0x520, 16, 2, 23), - MUX_GATE(CLK_TOP_TDMO0_SEL, "tdmo0_sel", - i2so1_parents, 0x520, 24, 2, 31), + MUX_GATE(CLK_TOP_I2SO1_SEL, "i2so1_sel", i2so1_parents, 0x520, 0, 2, 7), + MUX_GATE(CLK_TOP_I2SO2_SEL, "i2so2_sel", i2so1_parents, 0x520, 8, 2, 15), + MUX_GATE(CLK_TOP_I2SO3_SEL, "i2so3_sel", i2so1_parents, 0x520, 16, 2, 23), + MUX_GATE(CLK_TOP_TDMO0_SEL, "tdmo0_sel", i2so1_parents, 0x520, 24, 2, 31), /* CLK_CFG_13 */ - MUX_GATE(CLK_TOP_TDMO1_SEL, "tdmo1_sel", - i2so1_parents, 0x530, 0, 2, 7), - MUX_GATE(CLK_TOP_I2SI1_SEL, "i2si1_sel", - i2so1_parents, 0x530, 8, 2, 15), - MUX_GATE(CLK_TOP_I2SI2_SEL, "i2si2_sel", - i2so1_parents, 0x530, 16, 2, 23), - MUX_GATE(CLK_TOP_I2SI3_SEL, "i2si3_sel", - i2so1_parents, 0x530, 24, 2, 31), + MUX_GATE(CLK_TOP_TDMO1_SEL, "tdmo1_sel", i2so1_parents, 0x530, 0, 2, 7), + MUX_GATE(CLK_TOP_I2SI1_SEL, "i2si1_sel", i2so1_parents, 0x530, 8, 2, 15), + MUX_GATE(CLK_TOP_I2SI2_SEL, "i2si2_sel", i2so1_parents, 0x530, 16, 2, 23), + MUX_GATE(CLK_TOP_I2SI3_SEL, "i2si3_sel", i2so1_parents, 0x530, 24, 2, 31), /* CLK_CFG_14 */ - MUX_GATE(CLK_TOP_ETHER_125M_SEL, "ether_125m_sel", - ether_125m_parents, 0x540, 0, 2, 7), - MUX_GATE(CLK_TOP_ETHER_50M_SEL, "ether_50m_sel", - ether_50m_parents, 0x540, 8, 2, 15), - MUX_GATE(CLK_TOP_JPGDEC_SEL, "jpgdec_sel", - jpgdec_parents, 0x540, 16, 4, 23), - MUX_GATE(CLK_TOP_SPISLV_SEL, "spislv_sel", - spislv_parents, 0x540, 24, 3, 31), + MUX_GATE(CLK_TOP_ETHER_125M_SEL, "ether_125m_sel", ether_125m_parents, + 0x540, 0, 2, 7), + MUX_GATE(CLK_TOP_ETHER_50M_SEL, "ether_50m_sel", ether_50m_parents, + 0x540, 8, 2, 15), + MUX_GATE(CLK_TOP_JPGDEC_SEL, "jpgdec_sel", jpgdec_parents, 0x540, 16, 4, 23), + MUX_GATE(CLK_TOP_SPISLV_SEL, "spislv_sel", spislv_parents, 0x540, 24, 3, 31), /* CLK_CFG_15 */ - MUX_GATE(CLK_TOP_ETHER_50M_RMII_SEL, "ether_sel", - ether_parents, 0x550, 0, 2, 7), - MUX_GATE(CLK_TOP_CAM2TG_SEL, "cam2tg_sel", - camtg_parents, 0x550, 8, 4, 15), - MUX_GATE(CLK_TOP_DI_SEL, "di_sel", - di_parents, 0x550, 16, 3, 23), - MUX_GATE(CLK_TOP_TVD_SEL, "tvd_sel", - tvd_parents, 0x550, 24, 2, 31), + MUX_GATE(CLK_TOP_ETHER_50M_RMII_SEL, "ether_sel", ether_parents, 0x550, 0, 2, 7), + MUX_GATE(CLK_TOP_CAM2TG_SEL, "cam2tg_sel", camtg_parents, 0x550, 8, 4, 15), + MUX_GATE(CLK_TOP_DI_SEL, "di_sel", di_parents, 0x550, 16, 3, 23), + MUX_GATE(CLK_TOP_TVD_SEL, "tvd_sel", tvd_parents, 0x550, 24, 2, 31), /* CLK_CFG_16 */ - MUX_GATE(CLK_TOP_I2C_SEL, "i2c_sel", - i2c_parents, 0x560, 0, 3, 7), - MUX_GATE(CLK_TOP_PWM_INFRA_SEL, "pwm_infra_sel", - pwm_parents, 0x560, 8, 2, 15), - MUX_GATE(CLK_TOP_MSDC0P_AES_SEL, "msdc0p_aes_sel", - msdc0p_aes_parents, 0x560, 16, 2, 23), - MUX_GATE(CLK_TOP_CMSYS_SEL, "cmsys_sel", - cmsys_parents, 0x560, 24, 3, 31), + MUX_GATE(CLK_TOP_I2C_SEL, "i2c_sel", i2c_parents, 0x560, 0, 3, 7), + MUX_GATE(CLK_TOP_PWM_INFRA_SEL, "pwm_infra_sel", pwm_parents, 0x560, 8, 2, 15), + MUX_GATE(CLK_TOP_MSDC0P_AES_SEL, "msdc0p_aes_sel", msdc0p_aes_parents, + 0x560, 16, 2, 23), + MUX_GATE(CLK_TOP_CMSYS_SEL, "cmsys_sel", cmsys_parents, 0x560, 24, 3, 31), /* CLK_CFG_17 */ - MUX_GATE(CLK_TOP_GCPU_SEL, "gcpu_sel", - gcpu_parents, 0x570, 0, 3, 7), + MUX_GATE(CLK_TOP_GCPU_SEL, "gcpu_sel", gcpu_parents, 0x570, 0, 3, 7), /* CLK_AUDDIV_4 */ - MUX(CLK_TOP_AUD_APLL1_SEL, "aud_apll1_sel", - aud_apll1_parents, 0x134, 0, 1), - MUX(CLK_TOP_AUD_APLL2_SEL, "aud_apll2_sel", - aud_apll2_parents, 0x134, 1, 1), - MUX(CLK_TOP_DA_AUDULL_VTX_6P5M_SEL, "audull_vtx_sel", - audull_vtx_parents, 0x134, 31, 1), - MUX(CLK_TOP_APLL1_REF_SEL, "apll1_ref_sel", - apll1_ref_parents, 0x134, 4, 3), - MUX(CLK_TOP_APLL2_REF_SEL, "apll2_ref_sel", - apll1_ref_parents, 0x134, 7, 3), + MUX(CLK_TOP_AUD_APLL1_SEL, "aud_apll1_sel", aud_apll1_parents, 0x134, 0, 1), + MUX(CLK_TOP_AUD_APLL2_SEL, "aud_apll2_sel", aud_apll2_parents, 0x134, 1, 1), + MUX(CLK_TOP_DA_AUDULL_VTX_6P5M_SEL, "audull_vtx_sel", audull_vtx_parents, + 0x134, 31, 1), + MUX(CLK_TOP_APLL1_REF_SEL, "apll1_ref_sel", apll1_ref_parents, 0x134, 4, 3), + MUX(CLK_TOP_APLL2_REF_SEL, "apll2_ref_sel", apll1_ref_parents, 0x134, 7, 3), }; static const char * const mcu_mp0_parents[] = { @@ -923,13 +783,13 @@ static const char * const mcu_bus_parents[] = { static struct mtk_composite mcu_muxes[] = { /* mp0_pll_divider_cfg */ MUX_GATE_FLAGS(CLK_MCU_MP0_SEL, "mcu_mp0_sel", mcu_mp0_parents, 0x7A0, - 9, 2, -1, CLK_IS_CRITICAL), + 9, 2, -1, CLK_IS_CRITICAL), /* mp2_pll_divider_cfg */ MUX_GATE_FLAGS(CLK_MCU_MP2_SEL, "mcu_mp2_sel", mcu_mp2_parents, 0x7A8, - 9, 2, -1, CLK_IS_CRITICAL), + 9, 2, -1, CLK_IS_CRITICAL), /* bus_pll_divider_cfg */ MUX_GATE_FLAGS(CLK_MCU_BUS_SEL, "mcu_bus_sel", mcu_bus_parents, 0x7C0, - 9, 2, -1, CLK_IS_CRITICAL), + 9, 2, -1, CLK_IS_CRITICAL), }; static const struct mtk_clk_divider top_adj_divs[] = { @@ -1061,100 +921,54 @@ static const struct mtk_gate_regs peri2_cg_regs = { static const struct mtk_gate peri_clks[] = { /* PERI0 */ - GATE_PERI0(CLK_PERI_NFI, "per_nfi", - "axi_sel", 0), - GATE_PERI0(CLK_PERI_THERM, "per_therm", - "axi_sel", 1), - GATE_PERI0(CLK_PERI_PWM0, "per_pwm0", - "pwm_sel", 2), - GATE_PERI0(CLK_PERI_PWM1, "per_pwm1", - "pwm_sel", 3), - GATE_PERI0(CLK_PERI_PWM2, "per_pwm2", - "pwm_sel", 4), - GATE_PERI0(CLK_PERI_PWM3, "per_pwm3", - "pwm_sel", 5), - GATE_PERI0(CLK_PERI_PWM4, "per_pwm4", - "pwm_sel", 6), - GATE_PERI0(CLK_PERI_PWM5, "per_pwm5", - "pwm_sel", 7), - GATE_PERI0(CLK_PERI_PWM6, "per_pwm6", - "pwm_sel", 8), - GATE_PERI0(CLK_PERI_PWM7, "per_pwm7", - "pwm_sel", 9), - GATE_PERI0(CLK_PERI_PWM, "per_pwm", - "pwm_sel", 10), - GATE_PERI0(CLK_PERI_AP_DMA, "per_ap_dma", - "axi_sel", 13), - GATE_PERI0(CLK_PERI_MSDC30_0, "per_msdc30_0", - "msdc50_0_sel", 14), - GATE_PERI0(CLK_PERI_MSDC30_1, "per_msdc30_1", - "msdc30_1_sel", 15), - GATE_PERI0(CLK_PERI_MSDC30_2, "per_msdc30_2", - "msdc30_2_sel", 16), - GATE_PERI0(CLK_PERI_MSDC30_3, "per_msdc30_3", - "msdc30_3_sel", 17), - GATE_PERI0(CLK_PERI_UART0, "per_uart0", - "uart_sel", 20), - GATE_PERI0(CLK_PERI_UART1, "per_uart1", - "uart_sel", 21), - GATE_PERI0(CLK_PERI_UART2, "per_uart2", - "uart_sel", 22), - GATE_PERI0(CLK_PERI_UART3, "per_uart3", - "uart_sel", 23), - GATE_PERI0(CLK_PERI_I2C0, "per_i2c0", - "axi_sel", 24), - GATE_PERI0(CLK_PERI_I2C1, "per_i2c1", - "axi_sel", 25), - GATE_PERI0(CLK_PERI_I2C2, "per_i2c2", - "axi_sel", 26), - GATE_PERI0(CLK_PERI_I2C3, "per_i2c3", - "axi_sel", 27), - GATE_PERI0(CLK_PERI_I2C4, "per_i2c4", - "axi_sel", 28), - GATE_PERI0(CLK_PERI_AUXADC, "per_auxadc", - "ltepll_fs26m", 29), - GATE_PERI0(CLK_PERI_SPI0, "per_spi0", - "spi_sel", 30), + GATE_PERI0(CLK_PERI_NFI, "per_nfi", "axi_sel", 0), + GATE_PERI0(CLK_PERI_THERM, "per_therm", "axi_sel", 1), + GATE_PERI0(CLK_PERI_PWM0, "per_pwm0", "pwm_sel", 2), + GATE_PERI0(CLK_PERI_PWM1, "per_pwm1", "pwm_sel", 3), + GATE_PERI0(CLK_PERI_PWM2, "per_pwm2", "pwm_sel", 4), + GATE_PERI0(CLK_PERI_PWM3, "per_pwm3", "pwm_sel", 5), + GATE_PERI0(CLK_PERI_PWM4, "per_pwm4", "pwm_sel", 6), + GATE_PERI0(CLK_PERI_PWM5, "per_pwm5", "pwm_sel", 7), + GATE_PERI0(CLK_PERI_PWM6, "per_pwm6", "pwm_sel", 8), + GATE_PERI0(CLK_PERI_PWM7, "per_pwm7", "pwm_sel", 9), + GATE_PERI0(CLK_PERI_PWM, "per_pwm", "pwm_sel", 10), + GATE_PERI0(CLK_PERI_AP_DMA, "per_ap_dma", "axi_sel", 13), + GATE_PERI0(CLK_PERI_MSDC30_0, "per_msdc30_0", "msdc50_0_sel", 14), + GATE_PERI0(CLK_PERI_MSDC30_1, "per_msdc30_1", "msdc30_1_sel", 15), + GATE_PERI0(CLK_PERI_MSDC30_2, "per_msdc30_2", "msdc30_2_sel", 16), + GATE_PERI0(CLK_PERI_MSDC30_3, "per_msdc30_3", "msdc30_3_sel", 17), + GATE_PERI0(CLK_PERI_UART0, "per_uart0", "uart_sel", 20), + GATE_PERI0(CLK_PERI_UART1, "per_uart1", "uart_sel", 21), + GATE_PERI0(CLK_PERI_UART2, "per_uart2", "uart_sel", 22), + GATE_PERI0(CLK_PERI_UART3, "per_uart3", "uart_sel", 23), + GATE_PERI0(CLK_PERI_I2C0, "per_i2c0", "axi_sel", 24), + GATE_PERI0(CLK_PERI_I2C1, "per_i2c1", "axi_sel", 25), + GATE_PERI0(CLK_PERI_I2C2, "per_i2c2", "axi_sel", 26), + GATE_PERI0(CLK_PERI_I2C3, "per_i2c3", "axi_sel", 27), + GATE_PERI0(CLK_PERI_I2C4, "per_i2c4", "axi_sel", 28), + GATE_PERI0(CLK_PERI_AUXADC, "per_auxadc", "ltepll_fs26m", 29), + GATE_PERI0(CLK_PERI_SPI0, "per_spi0", "spi_sel", 30), /* PERI1 */ - GATE_PERI1(CLK_PERI_SPI, "per_spi", - "spinor_sel", 1), - GATE_PERI1(CLK_PERI_I2C5, "per_i2c5", - "axi_sel", 3), - GATE_PERI1(CLK_PERI_SPI2, "per_spi2", - "spi_sel", 5), - GATE_PERI1(CLK_PERI_SPI3, "per_spi3", - "spi_sel", 6), - GATE_PERI1(CLK_PERI_SPI5, "per_spi5", - "spi_sel", 8), - GATE_PERI1(CLK_PERI_UART4, "per_uart4", - "uart_sel", 9), - GATE_PERI1(CLK_PERI_SFLASH, "per_sflash", - "uart_sel", 11), - GATE_PERI1(CLK_PERI_GMAC, "per_gmac", - "uart_sel", 12), - GATE_PERI1(CLK_PERI_PCIE0, "per_pcie0", - "uart_sel", 14), - GATE_PERI1(CLK_PERI_PCIE1, "per_pcie1", - "uart_sel", 15), - GATE_PERI1(CLK_PERI_GMAC_PCLK, "per_gmac_pclk", - "uart_sel", 16), + GATE_PERI1(CLK_PERI_SPI, "per_spi", "spinor_sel", 1), + GATE_PERI1(CLK_PERI_I2C5, "per_i2c5", "axi_sel", 3), + GATE_PERI1(CLK_PERI_SPI2, "per_spi2", "spi_sel", 5), + GATE_PERI1(CLK_PERI_SPI3, "per_spi3", "spi_sel", 6), + GATE_PERI1(CLK_PERI_SPI5, "per_spi5", "spi_sel", 8), + GATE_PERI1(CLK_PERI_UART4, "per_uart4", "uart_sel", 9), + GATE_PERI1(CLK_PERI_SFLASH, "per_sflash", "uart_sel", 11), + GATE_PERI1(CLK_PERI_GMAC, "per_gmac", "uart_sel", 12), + GATE_PERI1(CLK_PERI_PCIE0, "per_pcie0", "uart_sel", 14), + GATE_PERI1(CLK_PERI_PCIE1, "per_pcie1", "uart_sel", 15), + GATE_PERI1(CLK_PERI_GMAC_PCLK, "per_gmac_pclk", "uart_sel", 16), /* PERI2 */ - GATE_PERI2(CLK_PERI_MSDC50_0_EN, "per_msdc50_0_en", - "msdc50_0_sel", 0), - GATE_PERI2(CLK_PERI_MSDC30_1_EN, "per_msdc30_1_en", - "msdc30_1_sel", 1), - GATE_PERI2(CLK_PERI_MSDC30_2_EN, "per_msdc30_2_en", - "msdc30_2_sel", 2), - GATE_PERI2(CLK_PERI_MSDC30_3_EN, "per_msdc30_3_en", - "msdc30_3_sel", 3), - GATE_PERI2(CLK_PERI_MSDC50_0_HCLK_EN, "per_msdc50_0_h", - "msdc50_0_h_sel", 4), - GATE_PERI2(CLK_PERI_MSDC50_3_HCLK_EN, "per_msdc50_3_h", - "msdc50_3_h_sel", 5), - GATE_PERI2(CLK_PERI_MSDC30_0_QTR_EN, "per_msdc30_0_q", - "axi_sel", 6), - GATE_PERI2(CLK_PERI_MSDC30_3_QTR_EN, "per_msdc30_3_q", - "mem_sel", 7), + GATE_PERI2(CLK_PERI_MSDC50_0_EN, "per_msdc50_0_en", "msdc50_0_sel", 0), + GATE_PERI2(CLK_PERI_MSDC30_1_EN, "per_msdc30_1_en", "msdc30_1_sel", 1), + GATE_PERI2(CLK_PERI_MSDC30_2_EN, "per_msdc30_2_en", "msdc30_2_sel", 2), + GATE_PERI2(CLK_PERI_MSDC30_3_EN, "per_msdc30_3_en", "msdc30_3_sel", 3), + GATE_PERI2(CLK_PERI_MSDC50_0_HCLK_EN, "per_msdc50_0_h", "msdc50_0_h_sel", 4), + GATE_PERI2(CLK_PERI_MSDC50_3_HCLK_EN, "per_msdc50_3_h", "msdc50_3_h_sel", 5), + GATE_PERI2(CLK_PERI_MSDC30_0_QTR_EN, "per_msdc30_0_q", "axi_sel", 6), + GATE_PERI2(CLK_PERI_MSDC30_3_QTR_EN, "per_msdc30_3_q", "mem_sel", 7), }; #define MT2712_PLL_FMAX (3000UL * MHZ) @@ -1221,38 +1035,35 @@ static const struct mtk_pll_div_table mmpll_div_table[] = { static const struct mtk_pll_data plls[] = { PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0230, 0x023C, 0xf0000100, - HAVE_RST_BAR, 31, 0x0230, 4, 0, 0, 0, 0x0234, 0), + HAVE_RST_BAR, 31, 0x0230, 4, 0, 0, 0, 0x0234, 0), PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0240, 0x024C, 0xfe000100, - HAVE_RST_BAR, 31, 0x0240, 4, 0, 0, 0, 0x0244, 0), + HAVE_RST_BAR, 31, 0x0240, 4, 0, 0, 0, 0x0244, 0), PLL(CLK_APMIXED_VCODECPLL, "vcodecpll", 0x0320, 0x032C, 0xc0000100, - 0, 31, 0x0320, 4, 0, 0, 0, 0x0324, 0), + 0, 31, 0x0320, 4, 0, 0, 0, 0x0324, 0), PLL(CLK_APMIXED_VENCPLL, "vencpll", 0x0280, 0x028C, 0x00000100, - 0, 31, 0x0280, 4, 0, 0, 0, 0x0284, 0), + 0, 31, 0x0280, 4, 0, 0, 0, 0x0284, 0), PLL(CLK_APMIXED_APLL1, "apll1", 0x0330, 0x0340, 0x00000100, - 0, 31, 0x0330, 4, 0x0338, 0x0014, 0, 0x0334, 0), + 0, 31, 0x0330, 4, 0x0338, 0x0014, 0, 0x0334, 0), PLL(CLK_APMIXED_APLL2, "apll2", 0x0350, 0x0360, 0x00000100, - 0, 31, 0x0350, 4, 0x0358, 0x0014, 1, 0x0354, 0), + 0, 31, 0x0350, 4, 0x0358, 0x0014, 1, 0x0354, 0), PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x0370, 0x037c, 0x00000100, - 0, 31, 0x0370, 4, 0, 0, 0, 0x0374, 0), + 0, 31, 0x0370, 4, 0, 0, 0, 0x0374, 0), PLL(CLK_APMIXED_LVDSPLL2, "lvdspll2", 0x0390, 0x039C, 0x00000100, - 0, 31, 0x0390, 4, 0, 0, 0, 0x0394, 0), + 0, 31, 0x0390, 4, 0, 0, 0, 0x0394, 0), PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0270, 0x027C, 0x00000100, - 0, 31, 0x0270, 4, 0, 0, 0, 0x0274, 0), + 0, 31, 0x0270, 4, 0, 0, 0, 0x0274, 0), PLL(CLK_APMIXED_MSDCPLL2, "msdcpll2", 0x0410, 0x041C, 0x00000100, - 0, 31, 0x0410, 4, 0, 0, 0, 0x0414, 0), + 0, 31, 0x0410, 4, 0, 0, 0, 0x0414, 0), PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0290, 0x029C, 0xc0000100, - 0, 31, 0x0290, 4, 0, 0, 0, 0x0294, 0), + 0, 31, 0x0290, 4, 0, 0, 0, 0x0294, 0), PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0250, 0x0260, 0x00000100, - 0, 31, 0x0250, 4, 0, 0, 0, 0x0254, 0, - mmpll_div_table), + 0, 31, 0x0250, 4, 0, 0, 0, 0x0254, 0, mmpll_div_table), PLL_B(CLK_APMIXED_ARMCA35PLL, "armca35pll", 0x0100, 0x0110, 0xf0000100, - HAVE_RST_BAR, 31, 0x0100, 4, 0, 0, 0, 0x0104, 0, - armca35pll_div_table), + HAVE_RST_BAR, 31, 0x0100, 4, 0, 0, 0, 0x0104, 0, armca35pll_div_table), PLL_B(CLK_APMIXED_ARMCA72PLL, "armca72pll", 0x0210, 0x0220, 0x00000100, - 0, 31, 0x0210, 4, 0, 0, 0, 0x0214, 0, - armca72pll_div_table), + 0, 31, 0x0210, 4, 0, 0, 0, 0x0214, 0, armca72pll_div_table), PLL(CLK_APMIXED_ETHERPLL, "etherpll", 0x0300, 0x030C, 0xc0000100, - 0, 31, 0x0300, 4, 0, 0, 0, 0x0304, 0), + 0, 31, 0x0300, 4, 0, 0, 0, 0x0304, 0), }; static u16 infrasys_rst_ofs[] = { 0x30, 0x34, }; -- GitLab From 20cace1b9d7e33f68f0ee17196bf0df618dbacbe Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:56 +0100 Subject: [PATCH 0350/5631] clk: mediatek: mt2712: Add error handling to clk_mt2712_apmixed_probe() This function was completely missing error handling: add it. Fixes: e2f744a82d72 ("clk: mediatek: Add MT2712 clock support") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-8-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2712.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index ce28ee47f5cf..8aa361f0fa13 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -1091,15 +1091,25 @@ static int clk_mt2712_apmixed_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (r) + goto free_clk_data; r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (r) { + dev_err(&pdev->dev, "Cannot register clock provider: %d\n", r); + goto unregister_plls; + } - if (r != 0) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); + return 0; +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); return r; } -- GitLab From ae567c34819536a1e7e7e5d202fabb1ce122dd79 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:57 +0100 Subject: [PATCH 0351/5631] clk: mediatek: mt2712: Move apmixedsys clock driver to its own file The only clock driver that does not support mtk_clk_simple_probe() is apmixedsys: in preparation for enabling module build of non-critical mt2712 clocks, move this to its own file. While at it, also fix some indentation issues in the PLLs table. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-9-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt2712-apmixedsys.c | 153 +++++++++++++++++ drivers/clk/mediatek/clk-mt2712.c | 164 ------------------- 3 files changed, 154 insertions(+), 165 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt2712-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index e5d018270ed0..9ba8f666221c 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -38,7 +38,7 @@ obj-$(CONFIG_COMMON_CLK_MT2701_HIFSYS) += clk-mt2701-hif.o obj-$(CONFIG_COMMON_CLK_MT2701_IMGSYS) += clk-mt2701-img.o obj-$(CONFIG_COMMON_CLK_MT2701_MMSYS) += clk-mt2701-mm.o obj-$(CONFIG_COMMON_CLK_MT2701_VDECSYS) += clk-mt2701-vdec.o -obj-$(CONFIG_COMMON_CLK_MT2712) += clk-mt2712.o +obj-$(CONFIG_COMMON_CLK_MT2712) += clk-mt2712-apmixedsys.o clk-mt2712.o obj-$(CONFIG_COMMON_CLK_MT2712_BDPSYS) += clk-mt2712-bdp.o obj-$(CONFIG_COMMON_CLK_MT2712_IMGSYS) += clk-mt2712-img.o obj-$(CONFIG_COMMON_CLK_MT2712_JPGDECSYS) += clk-mt2712-jpgdec.o diff --git a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c new file mode 100644 index 000000000000..1e1a8272a4ac --- /dev/null +++ b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017 MediaTek Inc. + * Weiyi Lu + * Copyright (c) 2023 Collabora Ltd. + * AngeloGioacchino Del Regno + */ +#include +#include +#include + +#include "clk-pll.h" +#include "clk-mtk.h" + +#include + +#define MT2712_PLL_FMAX (3000UL * MHZ) + +#define CON0_MT2712_RST_BAR BIT(24) + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift, \ + _div_table) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = CON0_MT2712_RST_BAR, \ + .fmax = MT2712_PLL_FMAX, \ + .pcwbits = _pcwbits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .tuner_en_reg = _tuner_en_reg, \ + .tuner_en_bit = _tuner_en_bit, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .div_table = _div_table, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift) \ + PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _pcwbits, _pd_reg, _pd_shift, _tuner_reg, \ + _tuner_en_reg, _tuner_en_bit, _pcw_reg, \ + _pcw_shift, NULL) + +static const struct mtk_pll_div_table armca35pll_div_table[] = { + { .div = 0, .freq = MT2712_PLL_FMAX }, + { .div = 1, .freq = 1202500000 }, + { .div = 2, .freq = 500500000 }, + { .div = 3, .freq = 315250000 }, + { .div = 4, .freq = 157625000 }, + { /* sentinel */ } +}; + +static const struct mtk_pll_div_table armca72pll_div_table[] = { + { .div = 0, .freq = MT2712_PLL_FMAX }, + { .div = 1, .freq = 994500000 }, + { .div = 2, .freq = 520000000 }, + { .div = 3, .freq = 315250000 }, + { .div = 4, .freq = 157625000 }, + { /* sentinel */ } +}; + +static const struct mtk_pll_div_table mmpll_div_table[] = { + { .div = 0, .freq = MT2712_PLL_FMAX }, + { .div = 1, .freq = 1001000000 }, + { .div = 2, .freq = 601250000 }, + { .div = 3, .freq = 250250000 }, + { .div = 4, .freq = 125125000 }, + { /* sentinel */ } +}; + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0230, 0x023C, 0xf0000100, + HAVE_RST_BAR, 31, 0x0230, 4, 0, 0, 0, 0x0234, 0), + PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0240, 0x024C, 0xfe000100, + HAVE_RST_BAR, 31, 0x0240, 4, 0, 0, 0, 0x0244, 0), + PLL(CLK_APMIXED_VCODECPLL, "vcodecpll", 0x0320, 0x032C, 0xc0000100, + 0, 31, 0x0320, 4, 0, 0, 0, 0x0324, 0), + PLL(CLK_APMIXED_VENCPLL, "vencpll", 0x0280, 0x028C, 0x00000100, + 0, 31, 0x0280, 4, 0, 0, 0, 0x0284, 0), + PLL(CLK_APMIXED_APLL1, "apll1", 0x0330, 0x0340, 0x00000100, + 0, 31, 0x0330, 4, 0x0338, 0x0014, 0, 0x0334, 0), + PLL(CLK_APMIXED_APLL2, "apll2", 0x0350, 0x0360, 0x00000100, + 0, 31, 0x0350, 4, 0x0358, 0x0014, 1, 0x0354, 0), + PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x0370, 0x037c, 0x00000100, + 0, 31, 0x0370, 4, 0, 0, 0, 0x0374, 0), + PLL(CLK_APMIXED_LVDSPLL2, "lvdspll2", 0x0390, 0x039C, 0x00000100, + 0, 31, 0x0390, 4, 0, 0, 0, 0x0394, 0), + PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0270, 0x027C, 0x00000100, + 0, 31, 0x0270, 4, 0, 0, 0, 0x0274, 0), + PLL(CLK_APMIXED_MSDCPLL2, "msdcpll2", 0x0410, 0x041C, 0x00000100, + 0, 31, 0x0410, 4, 0, 0, 0, 0x0414, 0), + PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0290, 0x029C, 0xc0000100, + 0, 31, 0x0290, 4, 0, 0, 0, 0x0294, 0), + PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0250, 0x0260, 0x00000100, + 0, 31, 0x0250, 4, 0, 0, 0, 0x0254, 0, mmpll_div_table), + PLL_B(CLK_APMIXED_ARMCA35PLL, "armca35pll", 0x0100, 0x0110, 0xf0000100, + HAVE_RST_BAR, 31, 0x0100, 4, 0, 0, 0, 0x0104, 0, armca35pll_div_table), + PLL_B(CLK_APMIXED_ARMCA72PLL, "armca72pll", 0x0210, 0x0220, 0x00000100, + 0, 31, 0x0210, 4, 0, 0, 0, 0x0214, 0, armca72pll_div_table), + PLL(CLK_APMIXED_ETHERPLL, "etherpll", 0x0300, 0x030C, 0xc0000100, + 0, 31, 0x0300, 4, 0, 0, 0, 0x0304, 0), +}; + +static int clk_mt2712_apmixed_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *clk_data; + int r; + struct device_node *node = pdev->dev.of_node; + + clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (r) + goto free_clk_data; + + r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (r) { + dev_err(&pdev->dev, "Cannot register clock provider: %d\n", r); + goto unregister_plls; + } + + return 0; + +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); + return r; +} + +static const struct of_device_id of_match_clk_mt2712_apmixed[] = { + { .compatible = "mediatek,mt2712-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt2712_apmixed_drv = { + .probe = clk_mt2712_apmixed_probe, + .driver = { + .name = "clk-mt2712-apmixed", + .of_match_table = of_match_clk_mt2712_apmixed, + }, +}; +builtin_platform_driver(clk_mt2712_apmixed_drv) diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index 8aa361f0fa13..c5fd76d1b9df 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -14,7 +14,6 @@ #include #include "clk-gate.h" -#include "clk-pll.h" #include "clk-mtk.h" #include @@ -971,101 +970,6 @@ static const struct mtk_gate peri_clks[] = { GATE_PERI2(CLK_PERI_MSDC30_3_QTR_EN, "per_msdc30_3_q", "mem_sel", 7), }; -#define MT2712_PLL_FMAX (3000UL * MHZ) - -#define CON0_MT2712_RST_BAR BIT(24) - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift, \ - _div_table) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = CON0_MT2712_RST_BAR, \ - .fmax = MT2712_PLL_FMAX, \ - .pcwbits = _pcwbits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .tuner_en_reg = _tuner_en_reg, \ - .tuner_en_bit = _tuner_en_bit, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .div_table = _div_table, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift) \ - PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _pcwbits, _pd_reg, _pd_shift, _tuner_reg, \ - _tuner_en_reg, _tuner_en_bit, _pcw_reg, \ - _pcw_shift, NULL) - -static const struct mtk_pll_div_table armca35pll_div_table[] = { - { .div = 0, .freq = MT2712_PLL_FMAX }, - { .div = 1, .freq = 1202500000 }, - { .div = 2, .freq = 500500000 }, - { .div = 3, .freq = 315250000 }, - { .div = 4, .freq = 157625000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_div_table armca72pll_div_table[] = { - { .div = 0, .freq = MT2712_PLL_FMAX }, - { .div = 1, .freq = 994500000 }, - { .div = 2, .freq = 520000000 }, - { .div = 3, .freq = 315250000 }, - { .div = 4, .freq = 157625000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_div_table mmpll_div_table[] = { - { .div = 0, .freq = MT2712_PLL_FMAX }, - { .div = 1, .freq = 1001000000 }, - { .div = 2, .freq = 601250000 }, - { .div = 3, .freq = 250250000 }, - { .div = 4, .freq = 125125000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0230, 0x023C, 0xf0000100, - HAVE_RST_BAR, 31, 0x0230, 4, 0, 0, 0, 0x0234, 0), - PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0240, 0x024C, 0xfe000100, - HAVE_RST_BAR, 31, 0x0240, 4, 0, 0, 0, 0x0244, 0), - PLL(CLK_APMIXED_VCODECPLL, "vcodecpll", 0x0320, 0x032C, 0xc0000100, - 0, 31, 0x0320, 4, 0, 0, 0, 0x0324, 0), - PLL(CLK_APMIXED_VENCPLL, "vencpll", 0x0280, 0x028C, 0x00000100, - 0, 31, 0x0280, 4, 0, 0, 0, 0x0284, 0), - PLL(CLK_APMIXED_APLL1, "apll1", 0x0330, 0x0340, 0x00000100, - 0, 31, 0x0330, 4, 0x0338, 0x0014, 0, 0x0334, 0), - PLL(CLK_APMIXED_APLL2, "apll2", 0x0350, 0x0360, 0x00000100, - 0, 31, 0x0350, 4, 0x0358, 0x0014, 1, 0x0354, 0), - PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x0370, 0x037c, 0x00000100, - 0, 31, 0x0370, 4, 0, 0, 0, 0x0374, 0), - PLL(CLK_APMIXED_LVDSPLL2, "lvdspll2", 0x0390, 0x039C, 0x00000100, - 0, 31, 0x0390, 4, 0, 0, 0, 0x0394, 0), - PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0270, 0x027C, 0x00000100, - 0, 31, 0x0270, 4, 0, 0, 0, 0x0274, 0), - PLL(CLK_APMIXED_MSDCPLL2, "msdcpll2", 0x0410, 0x041C, 0x00000100, - 0, 31, 0x0410, 4, 0, 0, 0, 0x0414, 0), - PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0290, 0x029C, 0xc0000100, - 0, 31, 0x0290, 4, 0, 0, 0, 0x0294, 0), - PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0250, 0x0260, 0x00000100, - 0, 31, 0x0250, 4, 0, 0, 0, 0x0254, 0, mmpll_div_table), - PLL_B(CLK_APMIXED_ARMCA35PLL, "armca35pll", 0x0100, 0x0110, 0xf0000100, - HAVE_RST_BAR, 31, 0x0100, 4, 0, 0, 0, 0x0104, 0, armca35pll_div_table), - PLL_B(CLK_APMIXED_ARMCA72PLL, "armca72pll", 0x0210, 0x0220, 0x00000100, - 0, 31, 0x0210, 4, 0, 0, 0, 0x0214, 0, armca72pll_div_table), - PLL(CLK_APMIXED_ETHERPLL, "etherpll", 0x0300, 0x030C, 0xc0000100, - 0, 31, 0x0300, 4, 0, 0, 0, 0x0304, 0), -}; - static u16 infrasys_rst_ofs[] = { 0x30, 0x34, }; static u16 pericfg_rst_ofs[] = { 0x0, 0x4, }; @@ -1084,35 +988,6 @@ static const struct mtk_clk_rst_desc clk_rst_desc[] = { }, }; -static int clk_mt2712_apmixed_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - int r; - struct device_node *node = pdev->dev.of_node; - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - if (!clk_data) - return -ENOMEM; - - r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - if (r) - goto free_clk_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) { - dev_err(&pdev->dev, "Cannot register clock provider: %d\n", r); - goto unregister_plls; - } - - return 0; - -unregister_plls: - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); - return r; -} - static const struct mtk_clk_desc topck_desc = { .clks = top_clks, .num_clks = ARRAY_SIZE(top_clks), @@ -1133,33 +1008,6 @@ static const struct mtk_clk_desc mcu_desc = { .clk_lock = &mt2712_clk_lock, }; -static const struct of_device_id of_match_clk_mt2712[] = { - { - .compatible = "mediatek,mt2712-apmixedsys", - .data = clk_mt2712_apmixed_probe, - }, { - /* sentinel */ - } -}; - -static int clk_mt2712_probe(struct platform_device *pdev) -{ - int (*clk_probe)(struct platform_device *); - int r; - - clk_probe = of_device_get_match_data(&pdev->dev); - if (!clk_probe) - return -EINVAL; - - r = clk_probe(pdev); - if (r != 0) - dev_err(&pdev->dev, - "could not register clock provider: %s: %d\n", - pdev->name, r); - - return r; -} - static const struct mtk_clk_desc infra_desc = { .clks = infra_clks, .num_clks = ARRAY_SIZE(infra_clks), @@ -1189,20 +1037,8 @@ static struct platform_driver clk_mt2712_simple_drv = { }, }; -static struct platform_driver clk_mt2712_drv = { - .probe = clk_mt2712_probe, - .driver = { - .name = "clk-mt2712", - .of_match_table = of_match_clk_mt2712, - }, -}; - static int __init clk_mt2712_init(void) { - int ret = platform_driver_register(&clk_mt2712_drv); - - if (ret) - return ret; return platform_driver_register(&clk_mt2712_simple_drv); } -- GitLab From c6368ce864356ffbb9a4d95bdfbfc53e55467434 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:58 +0100 Subject: [PATCH 0352/5631] clk: mediatek: mt2712-apmixedsys: Add .remove() callback for module build Add a .remove() callback to the apmixedsys driver to allow full module build; while at it, also change the usage of builtin_platform_driver() to module_platform_driver() to actually make use of the new callback. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-10-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2712-apmixedsys.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c index 1e1a8272a4ac..2f4061c9a59e 100644 --- a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c @@ -138,6 +138,18 @@ static int clk_mt2712_apmixed_probe(struct platform_device *pdev) return r; } +static int clk_mt2712_apmixed_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_free_clk_data(clk_data); + + return 0; +} + static const struct of_device_id of_match_clk_mt2712_apmixed[] = { { .compatible = "mediatek,mt2712-apmixedsys" }, { /* sentinel */ } @@ -145,9 +157,10 @@ static const struct of_device_id of_match_clk_mt2712_apmixed[] = { static struct platform_driver clk_mt2712_apmixed_drv = { .probe = clk_mt2712_apmixed_probe, + .remove = clk_mt2712_apmixed_remove, .driver = { .name = "clk-mt2712-apmixed", .of_match_table = of_match_clk_mt2712_apmixed, }, }; -builtin_platform_driver(clk_mt2712_apmixed_drv) +module_platform_driver(clk_mt2712_apmixed_drv) -- GitLab From 274bc8561a314e881507d8d99fe477b436f1f084 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:04:59 +0100 Subject: [PATCH 0353/5631] clk: mediatek: mt2712: Change to use module_platform_driver macro Now that all of the clocks in clk-mt2712.c are using the common mtk_clk_simple_{probe,remove}() callbacks we can safely migrate to module_platform_driver. While at it, also drop all references to `simple` in the specific context of mt2712 as that was used in the past only to allow us to have two platform_driver(s) in one file. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-11-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2712.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index c5fd76d1b9df..937c370d6765 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -1020,7 +1020,7 @@ static const struct mtk_clk_desc peri_desc = { .rst_desc = &clk_rst_desc[1], }; -static const struct of_device_id of_match_clk_mt2712_simple[] = { +static const struct of_device_id of_match_clk_mt2712[] = { { .compatible = "mediatek,mt2712-infracfg", .data = &infra_desc }, { .compatible = "mediatek,mt2712-mcucfg", .data = &mcu_desc }, { .compatible = "mediatek,mt2712-pericfg", .data = &peri_desc, }, @@ -1028,18 +1028,12 @@ static const struct of_device_id of_match_clk_mt2712_simple[] = { { /* sentinel */ } }; -static struct platform_driver clk_mt2712_simple_drv = { +static struct platform_driver clk_mt2712_drv = { .probe = mtk_clk_simple_probe, .remove = mtk_clk_simple_remove, .driver = { - .name = "clk-mt2712-simple", - .of_match_table = of_match_clk_mt2712_simple, + .name = "clk-mt2712", + .of_match_table = of_match_clk_mt2712, }, }; - -static int __init clk_mt2712_init(void) -{ - return platform_driver_register(&clk_mt2712_simple_drv); -} - -arch_initcall(clk_mt2712_init); +module_platform_driver(clk_mt2712_drv); -- GitLab From ab44c1a70e79d37b243ba1a202d9596a7a137b9b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:00 +0100 Subject: [PATCH 0354/5631] clk: mediatek: mt8365: Move apmixedsys clock driver to its own file In preparation for migrating all other mt8365 clocks to the common mtk_clk_simple_probe(), move apmixedsys clocks to a different file. While at it, use the builtin_platform_driver() macro for it. During the conversion, error handling was added to the apmixedsys probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-12-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8365-apmixedsys.c | 164 +++++++++++++++++++ drivers/clk/mediatek/clk-mt8365.c | 143 ---------------- 3 files changed, 165 insertions(+), 144 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8365-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 9ba8f666221c..6c898874e948 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -112,7 +112,7 @@ obj-$(CONFIG_COMMON_CLK_MT8195) += clk-mt8195-apmixedsys.o clk-mt8195-topckgen.o clk-mt8195-venc.o clk-mt8195-vpp0.o clk-mt8195-vpp1.o \ clk-mt8195-wpe.o clk-mt8195-imp_iic_wrap.o \ clk-mt8195-apusys_pll.o -obj-$(CONFIG_COMMON_CLK_MT8365) += clk-mt8365.o +obj-$(CONFIG_COMMON_CLK_MT8365) += clk-mt8365-apmixedsys.o clk-mt8365.o obj-$(CONFIG_COMMON_CLK_MT8365_APU) += clk-mt8365-apu.o obj-$(CONFIG_COMMON_CLK_MT8365_CAM) += clk-mt8365-cam.o obj-$(CONFIG_COMMON_CLK_MT8365_MFG) += clk-mt8365-mfg.o diff --git a/drivers/clk/mediatek/clk-mt8365-apmixedsys.c b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c new file mode 100644 index 000000000000..6f0fdf92bbd2 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Copyright (c) 2023 Collabora Ltd. + */ + +#include +#include +#include +#include + +#include "clk-pll.h" +#include "clk-mtk.h" + +#define MT8365_PLL_FMAX (3800UL * MHZ) +#define MT8365_PLL_FMIN (1500UL * MHZ) +#define CON0_MT8365_RST_BAR BIT(23) + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift, _div_table, \ + _rst_bar_mask, _pcw_chg_reg) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = _rst_bar_mask, \ + .fmax = MT8365_PLL_FMAX, \ + .fmin = MT8365_PLL_FMIN, \ + .pcwbits = _pcwbits, \ + .pcwibits = 8, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .tuner_en_reg = _tuner_en_reg, \ + .tuner_en_bit = _tuner_en_bit, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .pcw_chg_reg = _pcw_chg_reg, \ + .div_table = _div_table, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, \ + _tuner_en_reg, _tuner_en_bit, _pcw_reg, \ + _pcw_shift, _rst_bar_mask, _pcw_chg_reg) \ + PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _pcwbits, _pd_reg, _pd_shift, \ + _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ + _pcw_reg, _pcw_shift, NULL, _rst_bar_mask, \ + _pcw_chg_reg) \ + +static const struct mtk_pll_div_table armpll_div_table[] = { + { .div = 0, .freq = MT8365_PLL_FMAX }, + { .div = 1, .freq = 1500 * MHZ }, + { .div = 2, .freq = 750 * MHZ }, + { .div = 3, .freq = 375 * MHZ }, + { .div = 4, .freq = 182500000 }, + { } /* sentinel */ +}; + +static const struct mtk_pll_div_table mfgpll_div_table[] = { + { .div = 0, .freq = MT8365_PLL_FMAX }, + { .div = 1, .freq = 1600 * MHZ }, + { .div = 2, .freq = 800 * MHZ }, + { .div = 3, .freq = 400 * MHZ }, + { .div = 4, .freq = 200 * MHZ }, + { } /* sentinel */ +}; + +static const struct mtk_pll_div_table dsppll_div_table[] = { + { .div = 0, .freq = MT8365_PLL_FMAX }, + { .div = 1, .freq = 1600 * MHZ }, + { .div = 2, .freq = 600 * MHZ }, + { .div = 3, .freq = 400 * MHZ }, + { .div = 4, .freq = 200 * MHZ }, + { } /* sentinel */ +}; + +static const struct mtk_pll_data plls[] = { + PLL_B(CLK_APMIXED_ARMPLL, "armpll", 0x030C, 0x0318, 0x00000001, PLL_AO, + 22, 0x0310, 24, 0, 0, 0, 0x0310, 0, armpll_div_table, 0, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0228, 0x0234, 0xFF000001, + HAVE_RST_BAR, 22, 0x022C, 24, 0, 0, 0, 0x022C, 0, CON0_MT8365_RST_BAR, 0), + PLL(CLK_APMIXED_UNIVPLL, "univpll2", 0x0208, 0x0214, 0xFF000001, + HAVE_RST_BAR, 22, 0x020C, 24, 0, 0, 0, 0x020C, 0, CON0_MT8365_RST_BAR, 0), + PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0218, 0x0224, 0x00000001, 0, 22, + 0x021C, 24, 0, 0, 0, 0x021C, 0, mfgpll_div_table, 0, 0), + PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0350, 0x035C, 0x00000001, 0, 22, + 0x0354, 24, 0, 0, 0, 0x0354, 0, 0, 0), + PLL(CLK_APMIXED_MMPLL, "mmpll", 0x0330, 0x033C, 0x00000001, 0, 22, + 0x0334, 24, 0, 0, 0, 0x0334, 0, 0, 0), + PLL(CLK_APMIXED_APLL1, "apll1", 0x031C, 0x032C, 0x00000001, 0, 32, + 0x0320, 24, 0x0040, 0x000C, 0, 0x0324, 0, 0, 0x0320), + PLL(CLK_APMIXED_APLL2, "apll2", 0x0360, 0x0370, 0x00000001, 0, 32, + 0x0364, 24, 0x004C, 0x000C, 5, 0x0368, 0, 0, 0x0364), + PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x0374, 0x0380, 0x00000001, 0, 22, + 0x0378, 24, 0, 0, 0, 0x0378, 0, 0, 0), + PLL_B(CLK_APMIXED_DSPPLL, "dsppll", 0x0390, 0x039C, 0x00000001, 0, 22, + 0x0394, 24, 0, 0, 0, 0x0394, 0, dsppll_div_table, 0, 0), + PLL(CLK_APMIXED_APUPLL, "apupll", 0x03A0, 0x03AC, 0x00000001, 0, 22, + 0x03A4, 24, 0, 0, 0, 0x03A4, 0, 0, 0), +}; + +static int clk_mt8365_apmixed_probe(struct platform_device *pdev) +{ + void __iomem *base; + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + struct clk_hw *hw; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_devm_alloc_clk_data(dev, CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + hw = devm_clk_hw_register_gate(dev, "univ_en", "univpll2", 0, + base + 0x204, 0, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + clk_data->hws[CLK_APMIXED_UNIV_EN] = hw; + + hw = devm_clk_hw_register_gate(dev, "usb20_en", "univ_en", 0, + base + 0x204, 1, 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + clk_data->hws[CLK_APMIXED_USB20_EN] = hw; + + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_plls; + + return 0; + +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static const struct of_device_id of_match_clk_mt8365_apmixed[] = { + { .compatible = "mediatek,mt8365-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt8365_apmixed_drv = { + .probe = clk_mt8365_apmixed_probe, + .driver = { + .name = "clk-mt8365-apmixed", + .of_match_table = of_match_clk_mt8365_apmixed, + }, +}; +builtin_platform_driver(clk_mt8365_apmixed_drv) diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index c9faa07ec0a6..91449a7cf608 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -17,7 +17,6 @@ #include "clk-gate.h" #include "clk-mtk.h" #include "clk-mux.h" -#include "clk-pll.h" static DEFINE_SPINLOCK(mt8365_clk_lock); @@ -757,145 +756,6 @@ static const struct mtk_simple_gate peri_clks[] = { { CLK_PERIAXI, "periaxi", "axi_sel", 0x20c, 31, 0 }, }; -#define MT8365_PLL_FMAX (3800UL * MHZ) -#define MT8365_PLL_FMIN (1500UL * MHZ) -#define CON0_MT8365_RST_BAR BIT(23) - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift, _div_table, \ - _rst_bar_mask, _pcw_chg_reg) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = _rst_bar_mask, \ - .fmax = MT8365_PLL_FMAX, \ - .fmin = MT8365_PLL_FMIN, \ - .pcwbits = _pcwbits, \ - .pcwibits = 8, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .tuner_en_reg = _tuner_en_reg, \ - .tuner_en_bit = _tuner_en_bit, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .pcw_chg_reg = _pcw_chg_reg, \ - .div_table = _div_table, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, \ - _tuner_en_reg, _tuner_en_bit, _pcw_reg, \ - _pcw_shift, _rst_bar_mask, _pcw_chg_reg) \ - PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _pcwbits, _pd_reg, _pd_shift, \ - _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ - _pcw_reg, _pcw_shift, NULL, _rst_bar_mask, \ - _pcw_chg_reg) \ - -static const struct mtk_pll_div_table armpll_div_table[] = { - { .div = 0, .freq = MT8365_PLL_FMAX }, - { .div = 1, .freq = 1500 * MHZ }, - { .div = 2, .freq = 750 * MHZ }, - { .div = 3, .freq = 375 * MHZ }, - { .div = 4, .freq = 182500000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_div_table mfgpll_div_table[] = { - { .div = 0, .freq = MT8365_PLL_FMAX }, - { .div = 1, .freq = 1600 * MHZ }, - { .div = 2, .freq = 800 * MHZ }, - { .div = 3, .freq = 400 * MHZ }, - { .div = 4, .freq = 200 * MHZ }, - { } /* sentinel */ -}; - -static const struct mtk_pll_div_table dsppll_div_table[] = { - { .div = 0, .freq = MT8365_PLL_FMAX }, - { .div = 1, .freq = 1600 * MHZ }, - { .div = 2, .freq = 600 * MHZ }, - { .div = 3, .freq = 400 * MHZ }, - { .div = 4, .freq = 200 * MHZ }, - { } /* sentinel */ -}; - -static const struct mtk_pll_data plls[] = { - PLL_B(CLK_APMIXED_ARMPLL, "armpll", 0x030C, 0x0318, 0x00000001, PLL_AO, - 22, 0x0310, 24, 0, 0, 0, 0x0310, 0, armpll_div_table, 0, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0228, 0x0234, 0xFF000001, - HAVE_RST_BAR, 22, 0x022C, 24, 0, 0, 0, 0x022C, 0, - CON0_MT8365_RST_BAR, 0), - PLL(CLK_APMIXED_UNIVPLL, "univpll2", 0x0208, 0x0214, 0xFF000001, - HAVE_RST_BAR, 22, 0x020C, 24, 0, 0, 0, 0x020C, 0, - CON0_MT8365_RST_BAR, 0), - PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0218, 0x0224, 0x00000001, 0, 22, - 0x021C, 24, 0, 0, 0, 0x021C, 0, mfgpll_div_table, 0, 0), - PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0350, 0x035C, 0x00000001, 0, 22, - 0x0354, 24, 0, 0, 0, 0x0354, 0, 0, 0), - PLL(CLK_APMIXED_MMPLL, "mmpll", 0x0330, 0x033C, 0x00000001, 0, 22, - 0x0334, 24, 0, 0, 0, 0x0334, 0, 0, 0), - PLL(CLK_APMIXED_APLL1, "apll1", 0x031C, 0x032C, 0x00000001, 0, 32, - 0x0320, 24, 0x0040, 0x000C, 0, 0x0324, 0, 0, 0x0320), - PLL(CLK_APMIXED_APLL2, "apll2", 0x0360, 0x0370, 0x00000001, 0, 32, - 0x0364, 24, 0x004C, 0x000C, 5, 0x0368, 0, 0, 0x0364), - PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x0374, 0x0380, 0x00000001, 0, 22, - 0x0378, 24, 0, 0, 0, 0x0378, 0, 0, 0), - PLL_B(CLK_APMIXED_DSPPLL, "dsppll", 0x0390, 0x039C, 0x00000001, 0, 22, - 0x0394, 24, 0, 0, 0, 0x0394, 0, dsppll_div_table, 0, 0), - PLL(CLK_APMIXED_APUPLL, "apupll", 0x03A0, 0x03AC, 0x00000001, 0, 22, - 0x03A4, 24, 0, 0, 0, 0x03A4, 0, 0, 0), -}; - -static int clk_mt8365_apmixed_probe(struct platform_device *pdev) -{ - void __iomem *base; - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - struct device *dev = &pdev->dev; - struct clk_hw *hw; - int ret; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_devm_alloc_clk_data(dev, CLK_APMIXED_NR_CLK); - if (!clk_data) - return -ENOMEM; - - hw = devm_clk_hw_register_gate(dev, "univ_en", "univpll2", 0, - base + 0x204, 0, 0, NULL); - if (IS_ERR(hw)) - return PTR_ERR(hw); - clk_data->hws[CLK_APMIXED_UNIV_EN] = hw; - - hw = devm_clk_hw_register_gate(dev, "usb20_en", "univ_en", 0, - base + 0x204, 1, 0, NULL); - if (IS_ERR(hw)) - return PTR_ERR(hw); - clk_data->hws[CLK_APMIXED_USB20_EN] = hw; - - ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - if (ret) - return ret; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto unregister_plls; - - return 0; - -unregister_plls: - mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); - - return ret; -} - static int clk_mt8365_register_mtk_simple_gates(struct device *dev, void __iomem *base, struct clk_hw_onecell_data *clk_data, @@ -1104,9 +964,6 @@ static int clk_mt8365_mcu_probe(struct platform_device *pdev) static const struct of_device_id of_match_clk_mt8365[] = { { - .compatible = "mediatek,mt8365-apmixedsys", - .data = clk_mt8365_apmixed_probe, - }, { .compatible = "mediatek,mt8365-topckgen", .data = clk_mt8365_top_probe, }, { -- GitLab From 905b7430d3ccc435aec6030a622e5611704cc37c Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:01 +0100 Subject: [PATCH 0355/5631] clk: mediatek: mt8365: Convert simple_gate to mtk_gate clocks On this SoC some clocks apparently don't have different offsets for set/clr/sta registers hence they can be set, cleared and status-read on one register: this means that it was possible to use simpler gate clocks instead of custom mtk_gate ones. In preparation for converting this clock driver to the common probe mechanism for MediaTek clocks, perform a conversion from simple_gate to mtk_gate clocks since the latter does provide implicit support for simple gate clocks as well. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-13-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8365.c | 189 +++++++++++++----------------- 1 file changed, 82 insertions(+), 107 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index 91449a7cf608..85fe7586a69b 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2022 MediaTek Inc. + * Copyright (C) 2023 Collabora Ltd. + * AngeloGioacchino Del Regno */ #include @@ -393,12 +395,6 @@ static struct mtk_composite top_misc_mux_gates[] = { 0x0ec, 0, 2, 7), }; -struct mt8365_clk_audio_mux { - int id; - const char *name; - u8 shift; -}; - static struct mt8365_clk_audio_mux top_misc_muxes[] = { { CLK_TOP_APLL_I2S0_SEL, "apll_i2s0_sel", 11}, { CLK_TOP_APLL_I2S1_SEL, "apll_i2s1_sel", 12}, @@ -569,35 +565,56 @@ static const struct mtk_clk_divider top_adj_divs[] = { 0x32c, 0, 8, CLK_DIVIDER_ROUND_CLOSEST), }; -struct mtk_simple_gate { - int id; - const char *name; - const char *parent; - u32 reg; - u8 shift; - unsigned long gate_flags; -}; - -static const struct mtk_simple_gate top_clk_gates[] = { - { CLK_TOP_CONN_32K, "conn_32k", "clk32k", 0x0, 10, CLK_GATE_SET_TO_DISABLE }, - { CLK_TOP_CONN_26M, "conn_26m", "clk26m", 0x0, 11, CLK_GATE_SET_TO_DISABLE }, - { CLK_TOP_DSP_32K, "dsp_32k", "clk32k", 0x0, 16, CLK_GATE_SET_TO_DISABLE }, - { CLK_TOP_DSP_26M, "dsp_26m", "clk26m", 0x0, 17, CLK_GATE_SET_TO_DISABLE }, - { CLK_TOP_USB20_48M_EN, "usb20_48m_en", "usb20_192m_d4", 0x104, 8, 0 }, - { CLK_TOP_UNIVPLL_48M_EN, "univpll_48m_en", "usb20_192m_d4", 0x104, 9, 0 }, - { CLK_TOP_LVDSTX_CLKDIG_EN, "lvdstx_dig_en", "lvdstx_dig_cts", 0x104, 20, 0 }, - { CLK_TOP_VPLL_DPIX_EN, "vpll_dpix_en", "vpll_dpix", 0x104, 21, 0 }, - { CLK_TOP_SSUSB_TOP_CK_EN, "ssusb_top_ck_en", NULL, 0x104, 22, 0 }, - { CLK_TOP_SSUSB_PHY_CK_EN, "ssusb_phy_ck_en", NULL, 0x104, 23, 0 }, - { CLK_TOP_AUD_I2S0_M, "aud_i2s0_m_ck", "apll12_ck_div0", 0x320, 0, 0 }, - { CLK_TOP_AUD_I2S1_M, "aud_i2s1_m_ck", "apll12_ck_div1", 0x320, 1, 0 }, - { CLK_TOP_AUD_I2S2_M, "aud_i2s2_m_ck", "apll12_ck_div2", 0x320, 2, 0 }, - { CLK_TOP_AUD_I2S3_M, "aud_i2s3_m_ck", "apll12_ck_div3", 0x320, 3, 0 }, - { CLK_TOP_AUD_TDMOUT_M, "aud_tdmout_m_ck", "apll12_ck_div4", 0x320, 4, 0 }, - { CLK_TOP_AUD_TDMOUT_B, "aud_tdmout_b_ck", "apll12_ck_div4b", 0x320, 5, 0 }, - { CLK_TOP_AUD_TDMIN_M, "aud_tdmin_m_ck", "apll12_ck_div5", 0x320, 6, 0 }, - { CLK_TOP_AUD_TDMIN_B, "aud_tdmin_b_ck", "apll12_ck_div5b", 0x320, 7, 0 }, - { CLK_TOP_AUD_SPDIF_M, "aud_spdif_m_ck", "apll12_ck_div6", 0x320, 8, 0 }, +static const struct mtk_gate_regs top0_cg_regs = { + .set_ofs = 0, + .clr_ofs = 0, + .sta_ofs = 0, +}; + +static const struct mtk_gate_regs top1_cg_regs = { + .set_ofs = 0x104, + .clr_ofs = 0x104, + .sta_ofs = 0x104, +}; + +static const struct mtk_gate_regs top2_cg_regs = { + .set_ofs = 0x320, + .clr_ofs = 0x320, + .sta_ofs = 0x320, +}; + +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, \ + _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, \ + _shift, &mtk_clk_gate_ops_no_setclr) + +#define GATE_TOP2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, \ + _shift, &mtk_clk_gate_ops_no_setclr) + +static const struct mtk_gate top_clk_gates[] = { + GATE_TOP0(CLK_TOP_CONN_32K, "conn_32k", "clk32k", 10), + GATE_TOP0(CLK_TOP_CONN_26M, "conn_26m", "clk26m", 11), + GATE_TOP0(CLK_TOP_DSP_32K, "dsp_32k", "clk32k", 16), + GATE_TOP0(CLK_TOP_DSP_26M, "dsp_26m", "clk26m", 17), + GATE_TOP1(CLK_TOP_USB20_48M_EN, "usb20_48m_en", "usb20_192m_d4", 8), + GATE_TOP1(CLK_TOP_UNIVPLL_48M_EN, "univpll_48m_en", "usb20_192m_d4", 9), + GATE_TOP1(CLK_TOP_LVDSTX_CLKDIG_EN, "lvdstx_dig_en", "lvdstx_dig_cts", 20), + GATE_TOP1(CLK_TOP_VPLL_DPIX_EN, "vpll_dpix_en", "vpll_dpix", 21), + GATE_TOP1(CLK_TOP_SSUSB_TOP_CK_EN, "ssusb_top_ck_en", NULL, 22), + GATE_TOP1(CLK_TOP_SSUSB_PHY_CK_EN, "ssusb_phy_ck_en", NULL, 23), + GATE_TOP2(CLK_TOP_AUD_I2S0_M, "aud_i2s0_m_ck", "apll12_ck_div0", 0), + GATE_TOP2(CLK_TOP_AUD_I2S1_M, "aud_i2s1_m_ck", "apll12_ck_div1", 1), + GATE_TOP2(CLK_TOP_AUD_I2S2_M, "aud_i2s2_m_ck", "apll12_ck_div2", 2), + GATE_TOP2(CLK_TOP_AUD_I2S3_M, "aud_i2s3_m_ck", "apll12_ck_div3", 3), + GATE_TOP2(CLK_TOP_AUD_TDMOUT_M, "aud_tdmout_m_ck", "apll12_ck_div4", 4), + GATE_TOP2(CLK_TOP_AUD_TDMOUT_B, "aud_tdmout_b_ck", "apll12_ck_div4b", 5), + GATE_TOP2(CLK_TOP_AUD_TDMIN_M, "aud_tdmin_m_ck", "apll12_ck_div5", 6), + GATE_TOP2(CLK_TOP_AUD_TDMIN_B, "aud_tdmin_b_ck", "apll12_ck_div5b", 7), + GATE_TOP2(CLK_TOP_AUD_SPDIF_M, "aud_spdif_m_ck", "apll12_ck_div6", 8), }; static const struct mtk_gate_regs ifr2_cg_regs = { @@ -630,50 +647,24 @@ static const struct mtk_gate_regs ifr6_cg_regs = { .sta_ofs = 0xd8, }; -#define GATE_IFR2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFRX(_id, _name, _parent, _shift, _regs) \ + GATE_MTK(_id, _name, _parent, _regs, _shift, \ + &mtk_clk_gate_ops_setclr) -#define GATE_IFR3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR2(_id, _name, _parent, _shift) \ + GATE_IFRX(_id, _name, _parent, _shift, &ifr2_cg_regs) -#define GATE_IFR4(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr4_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR3(_id, _name, _parent, _shift) \ + GATE_IFRX(_id, _name, _parent, _shift, &ifr3_cg_regs) -#define GATE_IFR5(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr5_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR4(_id, _name, _parent, _shift) \ + GATE_IFRX(_id, _name, _parent, _shift, &ifr4_cg_regs) -#define GATE_IFR6(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr6_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR5(_id, _name, _parent, _shift) \ + GATE_IFRX(_id, _name, _parent, _shift, &ifr5_cg_regs) + +#define GATE_IFR6(_id, _name, _parent, _shift) \ + GATE_IFRX(_id, _name, _parent, _shift, &ifr6_cg_regs) static const struct mtk_gate ifr_clks[] = { /* IFR2 */ @@ -752,33 +743,16 @@ static const struct mtk_gate ifr_clks[] = { GATE_IFR6(CLK_IFR_SSUSB_XHCI, "ifr_ssusb_xhci", "ssusb_xhci_sel", 11), }; -static const struct mtk_simple_gate peri_clks[] = { - { CLK_PERIAXI, "periaxi", "axi_sel", 0x20c, 31, 0 }, +static const struct mtk_gate_regs peri_cg_regs = { + .set_ofs = 0x20c, + .clr_ofs = 0x20c, + .sta_ofs = 0x20c, }; -static int -clk_mt8365_register_mtk_simple_gates(struct device *dev, void __iomem *base, - struct clk_hw_onecell_data *clk_data, - const struct mtk_simple_gate *gates, - unsigned int num_gates) -{ - unsigned int i; - - for (i = 0; i != num_gates; ++i) { - const struct mtk_simple_gate *gate = &gates[i]; - struct clk_hw *hw; - - hw = devm_clk_hw_register_gate(dev, gate->name, gate->parent, 0, - base + gate->reg, gate->shift, - gate->gate_flags, NULL); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - clk_data->hws[gate->id] = hw; - } - - return 0; -} +static const struct mtk_gate peri_clks[] = { + GATE_MTK(CLK_PERIAXI, "periaxi", "axi_sel", &peri_cg_regs, 31, + &mtk_clk_gate_ops_no_setclr), +}; static int clk_mt8365_top_probe(struct platform_device *pdev) { @@ -840,17 +814,18 @@ static int clk_mt8365_top_probe(struct platform_device *pdev) if (ret) goto unregister_composites; - ret = clk_mt8365_register_mtk_simple_gates(dev, base, clk_data, - top_clk_gates, - ARRAY_SIZE(top_clk_gates)); + ret = mtk_clk_register_gates(&pdev->dev, node, top_clk_gates, + ARRAY_SIZE(top_clk_gates), clk_data); if (ret) goto unregister_dividers; ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (ret) - goto unregister_dividers; + goto unregister_gates; return 0; +unregister_gates: + mtk_clk_unregister_gates(top_clk_gates, ARRAY_SIZE(top_clk_gates), clk_data); unregister_dividers: mtk_clk_unregister_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), clk_data); @@ -915,9 +890,9 @@ static int clk_mt8365_peri_probe(struct platform_device *pdev) if (!clk_data) return -ENOMEM; - ret = clk_mt8365_register_mtk_simple_gates(dev, base, clk_data, - peri_clks, - ARRAY_SIZE(peri_clks)); + + ret = mtk_clk_register_gates(&pdev->dev, node, peri_clks, + ARRAY_SIZE(peri_clks), clk_data); if (ret) return ret; -- GitLab From ff96210073ece5b172b48b1c16a72f9c41d128e7 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:02 +0100 Subject: [PATCH 0356/5631] clk: mediatek: mt8365: Join top_misc_mux_gates and top_misc_muxes arrays In preparation for migrating this driver to the simple probe mechanism, join the audio gates to the top_misc_mux_gates array of mtk_composite clocks in one top_misc_muxes array. While at it, since the `apll_i2s0_parents` array is for all i2s clocks, rename that to `apll_i2s_parents`. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-14-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8365.c | 46 ++++++++++--------------------- 1 file changed, 14 insertions(+), 32 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index 85fe7586a69b..fef6c653c9ce 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -384,25 +384,23 @@ static const char * const mbist_diag_parents[] = { "univpll2_d8" }; -static const char * const apll_i2s0_parents[] = { +static const char * const apll_i2s_parents[] = { "aud_1_sel", "aud_2_sel" }; -static struct mtk_composite top_misc_mux_gates[] = { +static struct mtk_composite top_misc_muxes[] = { /* CLK_CFG_11 */ MUX_GATE(CLK_TOP_MBIST_DIAG_SEL, "mbist_diag_sel", mbist_diag_parents, 0x0ec, 0, 2, 7), -}; - -static struct mt8365_clk_audio_mux top_misc_muxes[] = { - { CLK_TOP_APLL_I2S0_SEL, "apll_i2s0_sel", 11}, - { CLK_TOP_APLL_I2S1_SEL, "apll_i2s1_sel", 12}, - { CLK_TOP_APLL_I2S2_SEL, "apll_i2s2_sel", 13}, - { CLK_TOP_APLL_I2S3_SEL, "apll_i2s3_sel", 14}, - { CLK_TOP_APLL_TDMOUT_SEL, "apll_tdmout_sel", 15}, - { CLK_TOP_APLL_TDMIN_SEL, "apll_tdmin_sel", 16}, - { CLK_TOP_APLL_SPDIF_SEL, "apll_spdif_sel", 17}, + /* Audio MUX */ + MUX(CLK_TOP_APLL_I2S0_SEL, "apll_i2s0_sel", apll_i2s_parents, 0x0320, 11, 1), + MUX(CLK_TOP_APLL_I2S1_SEL, "apll_i2s1_sel", apll_i2s_parents, 0x0320, 12, 1), + MUX(CLK_TOP_APLL_I2S2_SEL, "apll_i2s2_sel", apll_i2s_parents, 0x0320, 13, 1), + MUX(CLK_TOP_APLL_I2S3_SEL, "apll_i2s3_sel", apll_i2s_parents, 0x0320, 14, 1), + MUX(CLK_TOP_APLL_TDMOUT_SEL, "apll_tdmout_sel", apll_i2s_parents, 0x0320, 15, 1), + MUX(CLK_TOP_APLL_TDMIN_SEL, "apll_tdmin_sel", apll_i2s_parents, 0x0320, 16, 1), + MUX(CLK_TOP_APLL_SPDIF_SEL, "apll_spdif_sel", apll_i2s_parents, 0x0320, 17, 1), }; #define CLK_CFG_UPDATE 0x004 @@ -787,28 +785,12 @@ static int clk_mt8365_top_probe(struct platform_device *pdev) if (ret) goto unregister_factors; - ret = mtk_clk_register_composites(&pdev->dev, top_misc_mux_gates, - ARRAY_SIZE(top_misc_mux_gates), base, + ret = mtk_clk_register_composites(&pdev->dev, top_misc_muxes, + ARRAY_SIZE(top_misc_muxes), base, &mt8365_clk_lock, clk_data); if (ret) goto unregister_muxes; - for (i = 0; i != ARRAY_SIZE(top_misc_muxes); ++i) { - struct mt8365_clk_audio_mux *mux = &top_misc_muxes[i]; - struct clk_hw *hw; - - hw = devm_clk_hw_register_mux(dev, mux->name, apll_i2s0_parents, - ARRAY_SIZE(apll_i2s0_parents), - CLK_SET_RATE_PARENT, base + 0x320, - mux->shift, 1, 0, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); - goto unregister_composites; - } - - clk_data->hws[mux->id] = hw; - } - ret = mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt8365_clk_lock, clk_data); if (ret) @@ -830,8 +812,8 @@ static int clk_mt8365_top_probe(struct platform_device *pdev) mtk_clk_unregister_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), clk_data); unregister_composites: - mtk_clk_unregister_composites(top_misc_mux_gates, - ARRAY_SIZE(top_misc_mux_gates), clk_data); + mtk_clk_unregister_composites(top_misc_muxes, + ARRAY_SIZE(top_misc_muxes), clk_data); unregister_muxes: mtk_clk_unregister_muxes(top_muxes, ARRAY_SIZE(top_muxes), clk_data); unregister_factors: -- GitLab From ffe91cb28f6a923b31024dbb83a75ee9e7a269b7 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:03 +0100 Subject: [PATCH 0357/5631] clk: mediatek: mt8365: Convert to mtk_clk_simple_{probe,remove}() All clocks in this driver are supported by the common simple probe mechanism and it's now possible to migrate to it. While at it, also switch to using the module_platform_driver() macro. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-15-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8365.c | 241 +++++------------------------- 1 file changed, 37 insertions(+), 204 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index fef6c653c9ce..208cdc157918 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -752,220 +752,53 @@ static const struct mtk_gate peri_clks[] = { &mtk_clk_gate_ops_no_setclr), }; -static int clk_mt8365_top_probe(struct platform_device *pdev) -{ - void __iomem *base; - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - struct device *dev = &pdev->dev; - int ret; - int i; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - if (!clk_data) - return -ENOMEM; - - ret = mtk_clk_register_fixed_clks(top_fixed_clks, - ARRAY_SIZE(top_fixed_clks), clk_data); - if (ret) - goto free_clk_data; - - ret = mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), - clk_data); - if (ret) - goto unregister_fixed_clks; - - ret = mtk_clk_register_muxes(&pdev->dev, top_muxes, - ARRAY_SIZE(top_muxes), node, - &mt8365_clk_lock, clk_data); - if (ret) - goto unregister_factors; - - ret = mtk_clk_register_composites(&pdev->dev, top_misc_muxes, - ARRAY_SIZE(top_misc_muxes), base, - &mt8365_clk_lock, clk_data); - if (ret) - goto unregister_muxes; - - ret = mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), - base, &mt8365_clk_lock, clk_data); - if (ret) - goto unregister_composites; - - ret = mtk_clk_register_gates(&pdev->dev, node, top_clk_gates, - ARRAY_SIZE(top_clk_gates), clk_data); - if (ret) - goto unregister_dividers; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto unregister_gates; - - return 0; -unregister_gates: - mtk_clk_unregister_gates(top_clk_gates, ARRAY_SIZE(top_clk_gates), clk_data); -unregister_dividers: - mtk_clk_unregister_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), - clk_data); -unregister_composites: - mtk_clk_unregister_composites(top_misc_muxes, - ARRAY_SIZE(top_misc_muxes), clk_data); -unregister_muxes: - mtk_clk_unregister_muxes(top_muxes, ARRAY_SIZE(top_muxes), clk_data); -unregister_factors: - mtk_clk_unregister_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); -unregister_fixed_clks: - mtk_clk_unregister_fixed_clks(top_fixed_clks, - ARRAY_SIZE(top_fixed_clks), clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); - - return ret; -} - -static int clk_mt8365_infra_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - int ret; - - clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); - if (!clk_data) - return -ENOMEM; - - ret = mtk_clk_register_gates(&pdev->dev, node, ifr_clks, - ARRAY_SIZE(ifr_clks), clk_data); - if (ret) - goto free_clk_data; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto unregister_gates; - - return 0; - -unregister_gates: - mtk_clk_unregister_gates(ifr_clks, ARRAY_SIZE(ifr_clks), clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); - - return ret; -} - -static int clk_mt8365_peri_probe(struct platform_device *pdev) -{ - void __iomem *base; - struct clk_hw_onecell_data *clk_data; - struct device *dev = &pdev->dev; - struct device_node *node = dev->of_node; - int ret; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_devm_alloc_clk_data(dev, CLK_PERI_NR_CLK); - if (!clk_data) - return -ENOMEM; - - - ret = mtk_clk_register_gates(&pdev->dev, node, peri_clks, - ARRAY_SIZE(peri_clks), clk_data); - if (ret) - return ret; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - - return ret; -} - -static int clk_mt8365_mcu_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - void __iomem *base; - int ret; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - if (!clk_data) - return -ENOMEM; - - ret = mtk_clk_register_composites(&pdev->dev, mcu_muxes, - ARRAY_SIZE(mcu_muxes), base, - &mt8365_clk_lock, clk_data); - if (ret) - goto free_clk_data; - - ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (ret) - goto unregister_composites; +static const struct mtk_clk_desc topck_desc = { + .clks = top_clk_gates, + .num_clks = ARRAY_SIZE(top_clk_gates), + .fixed_clks = top_fixed_clks, + .num_fixed_clks = ARRAY_SIZE(top_fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .mux_clks = top_muxes, + .num_mux_clks = ARRAY_SIZE(top_muxes), + .composite_clks = top_misc_muxes, + .num_composite_clks = ARRAY_SIZE(top_misc_muxes), + .divider_clks = top_adj_divs, + .num_divider_clks = ARRAY_SIZE(top_adj_divs), + .clk_lock = &mt8365_clk_lock, +}; - return 0; +static const struct mtk_clk_desc infra_desc = { + .clks = ifr_clks, + .num_clks = ARRAY_SIZE(ifr_clks), +}; -unregister_composites: - mtk_clk_unregister_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), - clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); +static const struct mtk_clk_desc peri_desc = { + .clks = peri_clks, + .num_clks = ARRAY_SIZE(peri_clks), +}; - return ret; -} +static const struct mtk_clk_desc mcu_desc = { + .composite_clks = mcu_muxes, + .num_composite_clks = ARRAY_SIZE(mcu_muxes), + .clk_lock = &mt8365_clk_lock, +}; static const struct of_device_id of_match_clk_mt8365[] = { - { - .compatible = "mediatek,mt8365-topckgen", - .data = clk_mt8365_top_probe, - }, { - .compatible = "mediatek,mt8365-infracfg", - .data = clk_mt8365_infra_probe, - }, { - .compatible = "mediatek,mt8365-pericfg", - .data = clk_mt8365_peri_probe, - }, { - .compatible = "mediatek,mt8365-mcucfg", - .data = clk_mt8365_mcu_probe, - }, { - /* sentinel */ - } -}; - -static int clk_mt8365_probe(struct platform_device *pdev) -{ - int (*clk_probe)(struct platform_device *pdev); - int ret; - - clk_probe = of_device_get_match_data(&pdev->dev); - if (!clk_probe) - return -EINVAL; - - ret = clk_probe(pdev); - if (ret) - dev_err(&pdev->dev, - "%s: could not register clock provider: %d\n", - pdev->name, ret); - - return ret; -} + { .compatible = "mediatek,mt8365-topckgen", .data = &topck_desc }, + { .compatible = "mediatek,mt8365-infracfg", .data = &infra_desc }, + { .compatible = "mediatek,mt8365-pericfg", .data = &peri_desc }, + { .compatible = "mediatek,mt8365-mcucfg", .data = &mcu_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt8365_drv = { - .probe = clk_mt8365_probe, .driver = { .name = "clk-mt8365", .of_match_table = of_match_clk_mt8365, }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, }; - -static int __init clk_mt8365_init(void) -{ - return platform_driver_register(&clk_mt8365_drv); -} -arch_initcall(clk_mt8365_init); +module_platform_driver(clk_mt8365_drv); MODULE_LICENSE("GPL"); -- GitLab From c1a988f15a9203f39da37935e065c1abb61106ca Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:04 +0100 Subject: [PATCH 0358/5631] clk: mediatek: mt8167: Compress GATE_TOPx macros Use the GATE_MTK macro to compress the GATE_TOP{0..5} macros. No functional changes. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-16-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8167.c | 80 +++++++------------------------ 1 file changed, 16 insertions(+), 64 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index 91669ebafaf9..12384da4002d 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -736,77 +736,29 @@ static const struct mtk_gate_regs top5_cg_regs = { .sta_ofs = 0x44, }; -#define GATE_TOP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP0_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_TOP0_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_TOP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP2_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_TOP2_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_TOP3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top3_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP4_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top4_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_TOP4_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top4_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_TOP5(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top5_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP5(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top5_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate top_clks[] __initconst = { /* TOP0 */ -- GitLab From b27284336aa4b52129f5fd1f2e1f5b5fdccaee4b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:05 +0100 Subject: [PATCH 0359/5631] clk: mediatek: mt8167: Move apmixedsys as platform_driver in new file In preparation for migrating all other MT8167 clocks to the common mtk_clk_simple_probe(), move apmixedsys clocks to a different file. While at it, also migrate away from the legacy CLK_OF_DECLARE and convert this clock driver to be a platform_driver instead. During the conversion, error handling was added to the apmixedsys probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-17-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8167-apmixedsys.c | 143 +++++++++++++++++++ drivers/clk/mediatek/clk-mt8167.c | 102 ------------- 3 files changed, 144 insertions(+), 103 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8167-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 6c898874e948..c5778a7e8025 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -62,7 +62,7 @@ obj-$(CONFIG_COMMON_CLK_MT7986) += clk-mt7986-topckgen.o obj-$(CONFIG_COMMON_CLK_MT7986) += clk-mt7986-infracfg.o obj-$(CONFIG_COMMON_CLK_MT7986_ETHSYS) += clk-mt7986-eth.o obj-$(CONFIG_COMMON_CLK_MT8135) += clk-mt8135.o -obj-$(CONFIG_COMMON_CLK_MT8167) += clk-mt8167.o +obj-$(CONFIG_COMMON_CLK_MT8167) += clk-mt8167-apmixedsys.o clk-mt8167.o obj-$(CONFIG_COMMON_CLK_MT8167_AUDSYS) += clk-mt8167-aud.o obj-$(CONFIG_COMMON_CLK_MT8167_IMGSYS) += clk-mt8167-img.o obj-$(CONFIG_COMMON_CLK_MT8167_MFGCFG) += clk-mt8167-mfgcfg.o diff --git a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c new file mode 100644 index 000000000000..ebd90365be5f --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 MediaTek Inc. + * Copyright (c) 2020 BayLibre, SAS + * Copyright (c) 2023 Collabora, Ltd. + */ + +#include +#include +#include +#include + +#include "clk-pll.h" +#include "clk-mtk.h" + +static DEFINE_SPINLOCK(mt8167_apmixed_clk_lock); + +#define MT8167_PLL_FMAX (2500UL * MHZ) + +#define CON0_MT8167_RST_BAR BIT(27) + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift, _div_table) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = CON0_MT8167_RST_BAR, \ + .fmax = MT8167_PLL_FMAX, \ + .pcwbits = _pcwbits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .div_table = _div_table, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift) \ + PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ + NULL) + +static const struct mtk_pll_div_table mmpll_div_table[] = { + { .div = 0, .freq = MT8167_PLL_FMAX }, + { .div = 1, .freq = 1000000000 }, + { .div = 2, .freq = 604500000 }, + { .div = 3, .freq = 253500000 }, + { .div = 4, .freq = 126750000 }, + { /* sentinel */ } +}; + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0100, 0x0110, 0, 0, + 21, 0x0104, 24, 0, 0x0104, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0120, 0x0130, 0, + HAVE_RST_BAR, 21, 0x0124, 24, 0, 0x0124, 0), + PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0140, 0x0150, 0x30000000, + HAVE_RST_BAR, 7, 0x0144, 24, 0, 0x0144, 0), + PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0160, 0x0170, 0, 0, + 21, 0x0164, 24, 0, 0x0164, 0, mmpll_div_table), + PLL(CLK_APMIXED_APLL1, "apll1", 0x0180, 0x0190, 0, 0, + 31, 0x0180, 1, 0x0194, 0x0184, 0), + PLL(CLK_APMIXED_APLL2, "apll2", 0x01A0, 0x01B0, 0, 0, + 31, 0x01A0, 1, 0x01B4, 0x01A4, 0), + PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x01C0, 0x01D0, 0, 0, + 21, 0x01C4, 24, 0, 0x01C4, 0), + PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x01E0, 0x01F0, 0, 0, + 21, 0x01E4, 24, 0, 0x01E4, 0), +}; + +#define DIV_ADJ_FLAG(_id, _name, _parent, _reg, _shift, _width, _flag) { \ + .id = _id, \ + .name = _name, \ + .parent_name = _parent, \ + .div_reg = _reg, \ + .div_shift = _shift, \ + .div_width = _width, \ + .clk_divider_flags = _flag, \ +} + +static const struct mtk_clk_divider adj_divs[] = { + DIV_ADJ_FLAG(CLK_APMIXED_HDMI_REF, "hdmi_ref", "tvdpll", + 0x1c4, 24, 3, CLK_DIVIDER_POWER_OF_TWO), +}; + +static int clk_mt8167_apmixed_probe(struct platform_device *pdev) +{ + void __iomem *base; + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_devm_alloc_clk_data(dev, MT8167_CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = mtk_clk_register_dividers(adj_divs, ARRAY_SIZE(adj_divs), base, + &mt8167_apmixed_clk_lock, clk_data); + if (ret) + goto unregister_plls; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_dividers; + + return 0; + +unregister_dividers: + mtk_clk_unregister_dividers(adj_divs, ARRAY_SIZE(adj_divs), clk_data); +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static const struct of_device_id of_match_clk_mt8167_apmixed[] = { + { .compatible = "mediatek,mt8167-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt8167_apmixed_drv = { + .probe = clk_mt8167_apmixed_probe, + .driver = { + .name = "clk-mt8167-apmixed", + .of_match_table = of_match_clk_mt8167_apmixed, + }, +}; +builtin_platform_driver(clk_mt8167_apmixed_drv) diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index 12384da4002d..a4ffdac6d94d 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -14,7 +14,6 @@ #include "clk-gate.h" #include "clk-mtk.h" -#include "clk-pll.h" #include @@ -685,21 +684,6 @@ static const struct mtk_clk_divider top_adj_divs[] = { 0x0078, 0, 8), }; -#define DIV_ADJ_FLAG(_id, _name, _parent, _reg, _shift, _width, _flag) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .div_reg = _reg, \ - .div_shift = _shift, \ - .div_width = _width, \ - .clk_divider_flags = _flag, \ -} - -static const struct mtk_clk_divider apmixed_adj_divs[] = { - DIV_ADJ_FLAG(CLK_APMIXED_HDMI_REF, "hdmi_ref", "tvdpll", - 0x1c4, 24, 3, CLK_DIVIDER_POWER_OF_TWO), -}; - static const struct mtk_gate_regs top0_cg_regs = { .set_ofs = 0x50, .clr_ofs = 0x80, @@ -929,89 +913,3 @@ static void __init mtk_infracfg_init(struct device_node *node) __func__, r); } CLK_OF_DECLARE(mtk_infracfg, "mediatek,mt8167-infracfg", mtk_infracfg_init); - -#define MT8167_PLL_FMAX (2500UL * MHZ) - -#define CON0_MT8167_RST_BAR BIT(27) - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift, _div_table) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = CON0_MT8167_RST_BAR, \ - .fmax = MT8167_PLL_FMAX, \ - .pcwbits = _pcwbits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .div_table = _div_table, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift) \ - PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ - NULL) - -static const struct mtk_pll_div_table mmpll_div_table[] = { - { .div = 0, .freq = MT8167_PLL_FMAX }, - { .div = 1, .freq = 1000000000 }, - { .div = 2, .freq = 604500000 }, - { .div = 3, .freq = 253500000 }, - { .div = 4, .freq = 126750000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0100, 0x0110, 0, 0, - 21, 0x0104, 24, 0, 0x0104, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0120, 0x0130, 0, - HAVE_RST_BAR, 21, 0x0124, 24, 0, 0x0124, 0), - PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0140, 0x0150, 0x30000000, - HAVE_RST_BAR, 7, 0x0144, 24, 0, 0x0144, 0), - PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0160, 0x0170, 0, 0, - 21, 0x0164, 24, 0, 0x0164, 0, mmpll_div_table), - PLL(CLK_APMIXED_APLL1, "apll1", 0x0180, 0x0190, 0, 0, - 31, 0x0180, 1, 0x0194, 0x0184, 0), - PLL(CLK_APMIXED_APLL2, "apll2", 0x01A0, 0x01B0, 0, 0, - 31, 0x01A0, 1, 0x01B4, 0x01A4, 0), - PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x01C0, 0x01D0, 0, 0, - 21, 0x01C4, 24, 0, 0x01C4, 0), - PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x01E0, 0x01F0, 0, 0, - 21, 0x01E4, 24, 0, 0x01E4, 0), -}; - -static void __init mtk_apmixedsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - void __iomem *base; - int r; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } - - clk_data = mtk_alloc_clk_data(MT8167_CLK_APMIXED_NR_CLK); - - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - mtk_clk_register_dividers(apmixed_adj_divs, ARRAY_SIZE(apmixed_adj_divs), - base, &mt8167_clk_lock, clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); - -} -CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8167-apmixedsys", - mtk_apmixedsys_init); -- GitLab From b4bd678f27e24e5c7cb7ad87829a2f7d724fc5bb Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:06 +0100 Subject: [PATCH 0360/5631] clk: mediatek: mt8167: Remove __initconst annotation from arrays In preparation for converting the MT8167 clock drivers to be proper platform_driver(s), drop the __initconst annotation from all of the clock arrays since they will be used not only during init but also during runtime. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-18-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8167-aud.c | 2 +- drivers/clk/mediatek/clk-mt8167-img.c | 2 +- drivers/clk/mediatek/clk-mt8167-mfgcfg.c | 2 +- drivers/clk/mediatek/clk-mt8167-vdec.c | 2 +- drivers/clk/mediatek/clk-mt8167.c | 100 +++++++++++------------ 5 files changed, 54 insertions(+), 54 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index f6bea6e9e6a4..2d890a440863 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -32,7 +32,7 @@ static const struct mtk_gate_regs aud_cg_regs = { .ops = &mtk_clk_gate_ops_no_setclr, \ } -static const struct mtk_gate aud_clks[] __initconst = { +static const struct mtk_gate aud_clks[] = { GATE_AUD(CLK_AUD_AFE, "aud_afe", "clk26m_ck", 2), GATE_AUD(CLK_AUD_I2S, "aud_i2s", "i2s_infra_bck", 6), GATE_AUD(CLK_AUD_22M, "aud_22m", "rg_aud_engen1", 8), diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index 77db13b177fc..23950186ee02 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -32,7 +32,7 @@ static const struct mtk_gate_regs img_cg_regs = { .ops = &mtk_clk_gate_ops_setclr, \ } -static const struct mtk_gate img_clks[] __initconst = { +static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_LARB1_SMI, "img_larb1_smi", "smi_mm", 0), GATE_IMG(CLK_IMG_CAM_SMI, "img_cam_smi", "smi_mm", 5), GATE_IMG(CLK_IMG_CAM_CAM, "img_cam_cam", "smi_mm", 6), diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 3c23591b02f7..40b2d45f3fe3 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -32,7 +32,7 @@ static const struct mtk_gate_regs mfg_cg_regs = { .ops = &mtk_clk_gate_ops_setclr, \ } -static const struct mtk_gate mfg_clks[] __initconst = { +static const struct mtk_gate mfg_clks[] = { GATE_MFG(CLK_MFG_BAXI, "mfg_baxi", "ahb_infra_sel", 0), GATE_MFG(CLK_MFG_BMEM, "mfg_bmem", "gfmux_emi1x_sel", 1), GATE_MFG(CLK_MFG_BG3D, "mfg_bg3d", "mfg_mm", 2), diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index 759e5791599f..905529789a7c 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -47,7 +47,7 @@ static const struct mtk_gate_regs vdec1_cg_regs = { .ops = &mtk_clk_gate_ops_setclr_inv, \ } -static const struct mtk_gate vdec_clks[] __initconst = { +static const struct mtk_gate vdec_clks[] = { /* VDEC0 */ GATE_VDEC0_I(CLK_VDEC_CKEN, "vdec_cken", "rg_vdec", 0), /* VDEC1 */ diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index a4ffdac6d94d..f604add9b546 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -19,7 +19,7 @@ static DEFINE_SPINLOCK(mt8167_clk_lock); -static const struct mtk_fixed_clk fixed_clks[] __initconst = { +static const struct mtk_fixed_clk fixed_clks[] = { FIXED_CLK(CLK_TOP_CLK_NULL, "clk_null", NULL, 0), FIXED_CLK(CLK_TOP_I2S_INFRA_BCK, "i2s_infra_bck", "clk_null", 26000000), FIXED_CLK(CLK_TOP_MEMPLL, "mempll", "clk26m", 800000000), @@ -28,7 +28,7 @@ static const struct mtk_fixed_clk fixed_clks[] __initconst = { FIXED_CLK(CLK_TOP_LVDSTX_CLKDIG_CTS, "lvdstx_dig_cts", "clk26m", 52500000), }; -static const struct mtk_fixed_factor top_divs[] __initconst = { +static const struct mtk_fixed_factor top_divs[] = { FACTOR(CLK_TOP_DMPLL, "dmpll_ck", "mempll", 1, 1), FACTOR(CLK_TOP_MAINPLL_D2, "mainpll_d2", "mainpll", 1, 2), FACTOR(CLK_TOP_MAINPLL_D4, "mainpll_d4", "mainpll", 1, 4), @@ -84,22 +84,22 @@ static const struct mtk_fixed_factor top_divs[] __initconst = { FACTOR(CLK_TOP_ETH_D2, "eth_d2_ck", "eth_sel", 1, 2), }; -static const char * const uart0_parents[] __initconst = { +static const char * const uart0_parents[] = { "clk26m_ck", "univpll_d24" }; -static const char * const gfmux_emi1x_parents[] __initconst = { +static const char * const gfmux_emi1x_parents[] = { "clk26m_ck", "dmpll_ck" }; -static const char * const emi_ddrphy_parents[] __initconst = { +static const char * const emi_ddrphy_parents[] = { "gfmux_emi1x_sel", "gfmux_emi1x_sel" }; -static const char * const ahb_infra_parents[] __initconst = { +static const char * const ahb_infra_parents[] = { "clk_null", "clk26m_ck", "mainpll_d11", @@ -115,7 +115,7 @@ static const char * const ahb_infra_parents[] __initconst = { "mainpll_d10" }; -static const char * const csw_mux_mfg_parents[] __initconst = { +static const char * const csw_mux_mfg_parents[] = { "clk_null", "clk_null", "univpll_d3", @@ -126,7 +126,7 @@ static const char * const csw_mux_mfg_parents[] __initconst = { "mmpll380m" }; -static const char * const msdc0_parents[] __initconst = { +static const char * const msdc0_parents[] = { "clk26m_ck", "univpll_d6", "mainpll_d8", @@ -137,7 +137,7 @@ static const char * const msdc0_parents[] __initconst = { "mmpll_d2" }; -static const char * const camtg_mm_parents[] __initconst = { +static const char * const camtg_mm_parents[] = { "clk_null", "clk26m_ck", "usb_phy48m_ck", @@ -145,17 +145,17 @@ static const char * const camtg_mm_parents[] __initconst = { "univpll_d6" }; -static const char * const pwm_mm_parents[] __initconst = { +static const char * const pwm_mm_parents[] = { "clk26m_ck", "univpll_d12" }; -static const char * const uart1_parents[] __initconst = { +static const char * const uart1_parents[] = { "clk26m_ck", "univpll_d24" }; -static const char * const msdc1_parents[] __initconst = { +static const char * const msdc1_parents[] = { "clk26m_ck", "univpll_d6", "mainpll_d8", @@ -166,24 +166,24 @@ static const char * const msdc1_parents[] __initconst = { "mmpll_d2" }; -static const char * const spm_52m_parents[] __initconst = { +static const char * const spm_52m_parents[] = { "clk26m_ck", "univpll_d24" }; -static const char * const pmicspi_parents[] __initconst = { +static const char * const pmicspi_parents[] = { "univpll_d20", "usb_phy48m_ck", "univpll_d16", "clk26m_ck" }; -static const char * const qaxi_aud26m_parents[] __initconst = { +static const char * const qaxi_aud26m_parents[] = { "clk26m_ck", "ahb_infra_sel" }; -static const char * const aud_intbus_parents[] __initconst = { +static const char * const aud_intbus_parents[] = { "clk_null", "clk26m_ck", "mainpll_d22", @@ -191,7 +191,7 @@ static const char * const aud_intbus_parents[] __initconst = { "mainpll_d11" }; -static const char * const nfi2x_pad_parents[] __initconst = { +static const char * const nfi2x_pad_parents[] = { "clk_null", "clk_null", "clk_null", @@ -279,12 +279,12 @@ static const char * const nfi2x_pad_parents[] __initconst = { "mainpll_d5" }; -static const char * const nfi1x_pad_parents[] __initconst = { +static const char * const nfi1x_pad_parents[] = { "ahb_infra_sel", "nfi1x_ck" }; -static const char * const mfg_mm_parents[] __initconst = { +static const char * const mfg_mm_parents[] = { "clk_null", "clk_null", "clk_null", @@ -324,12 +324,12 @@ static const char * const mfg_mm_parents[] __initconst = { "mainpll_d14" }; -static const char * const ddrphycfg_parents[] __initconst = { +static const char * const ddrphycfg_parents[] = { "clk26m_ck", "mainpll_d16" }; -static const char * const smi_mm_parents[] __initconst = { +static const char * const smi_mm_parents[] = { "clk26m_ck", "clk_null", "clk_null", @@ -345,7 +345,7 @@ static const char * const smi_mm_parents[] __initconst = { "mainpll_d14" }; -static const char * const usb_78m_parents[] __initconst = { +static const char * const usb_78m_parents[] = { "clk_null", "clk26m_ck", "univpll_d16", @@ -353,7 +353,7 @@ static const char * const usb_78m_parents[] __initconst = { "mainpll_d20" }; -static const char * const scam_mm_parents[] __initconst = { +static const char * const scam_mm_parents[] = { "clk_null", "clk26m_ck", "mainpll_d14", @@ -361,7 +361,7 @@ static const char * const scam_mm_parents[] __initconst = { "mainpll_d12" }; -static const char * const spinor_parents[] __initconst = { +static const char * const spinor_parents[] = { "clk26m_d2", "clk26m_ck", "mainpll_d40", @@ -372,7 +372,7 @@ static const char * const spinor_parents[] __initconst = { "univpll_d12" }; -static const char * const msdc2_parents[] __initconst = { +static const char * const msdc2_parents[] = { "clk26m_ck", "univpll_d6", "mainpll_d8", @@ -383,7 +383,7 @@ static const char * const msdc2_parents[] __initconst = { "mmpll_d2" }; -static const char * const eth_parents[] __initconst = { +static const char * const eth_parents[] = { "clk26m_ck", "mainpll_d40", "univpll_d24", @@ -391,7 +391,7 @@ static const char * const eth_parents[] __initconst = { "mainpll_d20" }; -static const char * const vdec_mm_parents[] __initconst = { +static const char * const vdec_mm_parents[] = { "clk26m_ck", "univpll_d4", "mainpll_d4", @@ -400,7 +400,7 @@ static const char * const vdec_mm_parents[] __initconst = { "mainpll_d6" }; -static const char * const dpi0_mm_parents[] __initconst = { +static const char * const dpi0_mm_parents[] = { "clk26m_ck", "lvdspll_ck", "lvdspll_d2", @@ -408,7 +408,7 @@ static const char * const dpi0_mm_parents[] __initconst = { "lvdspll_d8" }; -static const char * const dpi1_mm_parents[] __initconst = { +static const char * const dpi1_mm_parents[] = { "clk26m_ck", "tvdpll_d2", "tvdpll_d4", @@ -416,85 +416,85 @@ static const char * const dpi1_mm_parents[] __initconst = { "tvdpll_d16" }; -static const char * const axi_mfg_in_parents[] __initconst = { +static const char * const axi_mfg_in_parents[] = { "clk26m_ck", "mainpll_d11", "univpll_d24", "mmpll380m" }; -static const char * const slow_mfg_parents[] __initconst = { +static const char * const slow_mfg_parents[] = { "clk26m_ck", "univpll_d12", "univpll_d24" }; -static const char * const aud1_parents[] __initconst = { +static const char * const aud1_parents[] = { "clk26m_ck", "apll1_ck" }; -static const char * const aud2_parents[] __initconst = { +static const char * const aud2_parents[] = { "clk26m_ck", "apll2_ck" }; -static const char * const aud_engen1_parents[] __initconst = { +static const char * const aud_engen1_parents[] = { "clk26m_ck", "rg_apll1_d2_en", "rg_apll1_d4_en", "rg_apll1_d8_en" }; -static const char * const aud_engen2_parents[] __initconst = { +static const char * const aud_engen2_parents[] = { "clk26m_ck", "rg_apll2_d2_en", "rg_apll2_d4_en", "rg_apll2_d8_en" }; -static const char * const i2c_parents[] __initconst = { +static const char * const i2c_parents[] = { "clk26m_ck", "univpll_d20", "univpll_d16", "univpll_d12" }; -static const char * const aud_i2s0_m_parents[] __initconst = { +static const char * const aud_i2s0_m_parents[] = { "rg_aud1", "rg_aud2" }; -static const char * const pwm_parents[] __initconst = { +static const char * const pwm_parents[] = { "clk26m_ck", "univpll_d12" }; -static const char * const spi_parents[] __initconst = { +static const char * const spi_parents[] = { "clk26m_ck", "univpll_d12", "univpll_d8", "univpll_d6" }; -static const char * const aud_spdifin_parents[] __initconst = { +static const char * const aud_spdifin_parents[] = { "clk26m_ck", "univpll_d2" }; -static const char * const uart2_parents[] __initconst = { +static const char * const uart2_parents[] = { "clk26m_ck", "univpll_d24" }; -static const char * const bsi_parents[] __initconst = { +static const char * const bsi_parents[] = { "clk26m_ck", "mainpll_d10", "mainpll_d12", "mainpll_d20" }; -static const char * const dbg_atclk_parents[] __initconst = { +static const char * const dbg_atclk_parents[] = { "clk_null", "clk26m_ck", "mainpll_d5", @@ -502,7 +502,7 @@ static const char * const dbg_atclk_parents[] __initconst = { "univpll_d5" }; -static const char * const csw_nfiecc_parents[] __initconst = { +static const char * const csw_nfiecc_parents[] = { "clk_null", "mainpll_d7", "mainpll_d6", @@ -510,7 +510,7 @@ static const char * const csw_nfiecc_parents[] __initconst = { "mainpll_d5" }; -static const char * const nfiecc_parents[] __initconst = { +static const char * const nfiecc_parents[] = { "clk_null", "nfi2x_pad_sel", "mainpll_d4", @@ -624,24 +624,24 @@ static struct mtk_composite top_muxes[] __initdata = { 0x07c, 13, 3), }; -static const char * const ifr_mux1_parents[] __initconst = { +static const char * const ifr_mux1_parents[] = { "clk26m_ck", "armpll", "univpll", "mainpll_d2" }; -static const char * const ifr_eth_25m_parents[] __initconst = { +static const char * const ifr_eth_25m_parents[] = { "eth_d2_ck", "rg_eth" }; -static const char * const ifr_i2c0_parents[] __initconst = { +static const char * const ifr_i2c0_parents[] = { "ahb_infra_d2", "rg_i2c" }; -static const struct mtk_composite ifr_muxes[] __initconst = { +static const struct mtk_composite ifr_muxes[] = { MUX(CLK_IFR_MUX1_SEL, "ifr_mux1_sel", ifr_mux1_parents, 0x000, 2, 2), MUX(CLK_IFR_ETH_25M_SEL, "ifr_eth_25m_sel", ifr_eth_25m_parents, 0x080, @@ -744,7 +744,7 @@ static const struct mtk_gate_regs top5_cg_regs = { #define GATE_TOP5(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top5_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -static const struct mtk_gate top_clks[] __initconst = { +static const struct mtk_gate top_clks[] = { /* TOP0 */ GATE_TOP0(CLK_TOP_PWM_MM, "pwm_mm", "pwm_mm_sel", 0), GATE_TOP0(CLK_TOP_CAM_MM, "cam_mm", "camtg_mm_sel", 1), -- GitLab From beb47f1942071b43bec84adc2fbd94e866953032 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:07 +0100 Subject: [PATCH 0361/5631] clk: mediatek: mt8167: Convert to mtk_clk_simple_{probe,remove}() Convert topckgen and infracfg clock drivers to use the common mtk_clk_simple_probe() mechanism and change this from the old "static" CLK_OF_DECLARE to be a platform driver, allowing it to eventually be built as a module. Thanks to the conversion, more error handling was added to the clocks registration. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-19-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8167-aud.c | 31 +++++---- drivers/clk/mediatek/clk-mt8167-img.c | 32 ++++----- drivers/clk/mediatek/clk-mt8167-mfgcfg.c | 32 ++++----- drivers/clk/mediatek/clk-mt8167-vdec.c | 33 ++++----- drivers/clk/mediatek/clk-mt8167.c | 86 +++++++++--------------- 5 files changed, 101 insertions(+), 113 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index 2d890a440863..eec9de190cb6 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -48,19 +48,22 @@ static const struct mtk_gate aud_clks[] = { GATE_AUD(CLK_AUD_TML, "aud_tml", "aud_afe", 27), }; -static void __init mtk_audsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_AUD_NR_CLK); - - mtk_clk_register_gates(NULL, node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); +static const struct mtk_clk_desc aud_desc = { + .clks = aud_clks, + .num_clks = ARRAY_SIZE(aud_clks), +}; - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct of_device_id of_match_clk_mt8167_audsys[] = { + { .compatible = "mediatek,mt8167-audsys", .data = &aud_desc }, + { /* sentinel */ } +}; -} -CLK_OF_DECLARE(mtk_audsys, "mediatek,mt8167-audsys", mtk_audsys_init); +static struct platform_driver clk_mt8167_audsys_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8167-audsys", + .of_match_table = of_match_clk_mt8167_audsys, + }, +}; +module_platform_driver(clk_mt8167_audsys_drv); diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index 23950186ee02..5cd51d894d32 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -41,20 +41,22 @@ static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_VENC, "img_venc", "smi_mm", 9), }; -static void __init mtk_imgsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_IMG_NR_CLK); - - mtk_clk_register_gates(NULL, node, img_clks, ARRAY_SIZE(img_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); +static const struct mtk_clk_desc img_desc = { + .clks = img_clks, + .num_clks = ARRAY_SIZE(img_clks), +}; - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct of_device_id of_match_clk_mt8167_imgsys[] = { + { .compatible = "mediatek,mt8167-imgsys", .data = &img_desc }, + { /* sentinel */ } +}; -} -CLK_OF_DECLARE(mtk_imgsys, "mediatek,mt8167-imgsys", mtk_imgsys_init); +static struct platform_driver clk_mt8167_imgsys_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8167-imgsys", + .of_match_table = of_match_clk_mt8167_imgsys, + }, +}; +module_platform_driver(clk_mt8167_imgsys_drv); diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 40b2d45f3fe3..2cf88d5d245d 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -39,20 +39,22 @@ static const struct mtk_gate mfg_clks[] = { GATE_MFG(CLK_MFG_B26M, "mfg_b26m", "clk26m_ck", 3), }; -static void __init mtk_mfgcfg_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_MFG_NR_CLK); - - mtk_clk_register_gates(NULL, node, mfg_clks, ARRAY_SIZE(mfg_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); +static const struct mtk_clk_desc mfg_desc = { + .clks = mfg_clks, + .num_clks = ARRAY_SIZE(mfg_clks), +}; - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct of_device_id of_match_clk_mt8167_mfgcfg[] = { + { .compatible = "mediatek,mt8167-mfgcfg", .data = &mfg_desc }, + { /* sentinel */ } +}; -} -CLK_OF_DECLARE(mtk_mfgcfg, "mediatek,mt8167-mfgcfg", mtk_mfgcfg_init); +static struct platform_driver clk_mt8167_mfgcfg_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8167-mfgcfg", + .of_match_table = of_match_clk_mt8167_mfgcfg, + }, +}; +module_platform_driver(clk_mt8167_mfgcfg_drv); diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index 905529789a7c..c3e2253a57d7 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -54,21 +54,22 @@ static const struct mtk_gate vdec_clks[] = { GATE_VDEC1_I(CLK_VDEC_LARB1_CKEN, "vdec_larb1_cken", "smi_mm", 0), }; -static void __init mtk_vdecsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_VDEC_NR_CLK); - - mtk_clk_register_gates(NULL, node, vdec_clks, ARRAY_SIZE(vdec_clks), - clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); +static const struct mtk_clk_desc vdec_desc = { + .clks = vdec_clks, + .num_clks = ARRAY_SIZE(vdec_clks), +}; - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static const struct of_device_id of_match_clk_mt8167_vdec[] = { + { .compatible = "mediatek,mt8167-vdecsys", .data = &vdec_desc }, + { /* sentinel */ } +}; -} -CLK_OF_DECLARE(mtk_vdecsys, "mediatek,mt8167-vdecsys", mtk_vdecsys_init); +static struct platform_driver clk_mt8167_vdec_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8167-vdecsys", + .of_match_table = of_match_clk_mt8167_vdec, + }, +}; +module_platform_driver(clk_mt8167_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index f604add9b546..507e1ebe3ba8 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "clk-gate.h" #include "clk-mtk.h" @@ -857,59 +858,38 @@ static const struct mtk_gate top_clks[] = { GATE_TOP5(CLK_TOP_APLL12_DIV6, "apll12_div6", "apll12_ck_div6", 8), }; -static void __init mtk_topckgen_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - void __iomem *base; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } - - clk_data = mtk_alloc_clk_data(MT8167_CLK_TOP_NR_CLK); +static const struct mtk_clk_desc topck_desc = { + .clks = top_clks, + .num_clks = ARRAY_SIZE(top_clks), + .fixed_clks = fixed_clks, + .num_fixed_clks = ARRAY_SIZE(fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .composite_clks = top_muxes, + .num_composite_clks = ARRAY_SIZE(top_muxes), + .divider_clks = top_adj_divs, + .num_divider_clks = ARRAY_SIZE(top_adj_divs), + .clk_lock = &mt8167_clk_lock, +}; - mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), - clk_data); - mtk_clk_register_gates(NULL, node, top_clks, ARRAY_SIZE(top_clks), clk_data); +static const struct mtk_clk_desc infra_desc = { + .composite_clks = ifr_muxes, + .num_composite_clks = ARRAY_SIZE(ifr_muxes), + .clk_lock = &mt8167_clk_lock, +}; - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(NULL, top_muxes, - ARRAY_SIZE(top_muxes), base, - &mt8167_clk_lock, clk_data); - mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), - base, &mt8167_clk_lock, clk_data); +static const struct of_device_id of_match_clk_mt8167[] = { + { .compatible = "mediatek,mt8167-topckgen", .data = &topck_desc }, + { .compatible = "mediatek,mt8167-infracfg", .data = &infra_desc }, + { /* sentinel */ } +}; - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8167-topckgen", mtk_topckgen_init); - -static void __init mtk_infracfg_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - void __iomem *base; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } - - clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); - - mtk_clk_register_composites(NULL, ifr_muxes, - ARRAY_SIZE(ifr_muxes), base, - &mt8167_clk_lock, clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_infracfg, "mediatek,mt8167-infracfg", mtk_infracfg_init); +static struct platform_driver clk_mt8167_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8167", + .of_match_table = of_match_clk_mt8167, + }, +}; +module_platform_driver(clk_mt8167_drv); -- GitLab From 127fadf7a46932646c8af2a972d301b975754697 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:08 +0100 Subject: [PATCH 0362/5631] clk: mediatek: mt8183: Move apmixedsys clock driver to its own file In preparation for migrating all other mt8183 clocks to the common mtk_clk_simple_probe(), move apmixedsys clocks to a different file. While at it, use the builtin_platform_driver() macro for it and fix some indentation issues in the PLLs table. During the conversion, error handling was added to the apmixedsys probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-20-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8183-apmixedsys.c | 193 +++++++++++++++++++ drivers/clk/mediatek/clk-mt8183.c | 153 --------------- 3 files changed, 194 insertions(+), 154 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8183-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index c5778a7e8025..33f13b8399ce 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -74,7 +74,7 @@ obj-$(CONFIG_COMMON_CLK_MT8173_IMGSYS) += clk-mt8173-img.o obj-$(CONFIG_COMMON_CLK_MT8173_MMSYS) += clk-mt8173-mm.o obj-$(CONFIG_COMMON_CLK_MT8173_VDECSYS) += clk-mt8173-vdecsys.o obj-$(CONFIG_COMMON_CLK_MT8173_VENCSYS) += clk-mt8173-vencsys.o -obj-$(CONFIG_COMMON_CLK_MT8183) += clk-mt8183.o +obj-$(CONFIG_COMMON_CLK_MT8183) += clk-mt8183-apmixedsys.o clk-mt8183.o obj-$(CONFIG_COMMON_CLK_MT8183_AUDIOSYS) += clk-mt8183-audio.o obj-$(CONFIG_COMMON_CLK_MT8183_CAMSYS) += clk-mt8183-cam.o obj-$(CONFIG_COMMON_CLK_MT8183_IMGSYS) += clk-mt8183-img.o diff --git a/drivers/clk/mediatek/clk-mt8183-apmixedsys.c b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c new file mode 100644 index 000000000000..e66e90163bb4 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 MediaTek Inc. + * Weiyi Lu + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" +#include "clk-pll.h" + +static const struct mtk_gate_regs apmixed_cg_regs = { + .set_ofs = 0x20, + .clr_ofs = 0x20, + .sta_ofs = 0x20, +}; + +#define GATE_APMIXED_FLAGS(_id, _name, _parent, _shift, _flags) \ + GATE_MTK_FLAGS(_id, _name, _parent, &apmixed_cg_regs, \ + _shift, &mtk_clk_gate_ops_no_setclr_inv, _flags) + +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_APMIXED_FLAGS(_id, _name, _parent, _shift, 0) + +/* + * CRITICAL CLOCK: + * apmixed_appll26m is the toppest clock gate of all PLLs. + */ +static const struct mtk_gate apmixed_clks[] = { + /* AUDIO0 */ + GATE_APMIXED(CLK_APMIXED_SSUSB_26M, "apmixed_ssusb26m", "f_f26m_ck", 4), + GATE_APMIXED_FLAGS(CLK_APMIXED_APPLL_26M, "apmixed_appll26m", + "f_f26m_ck", 5, CLK_IS_CRITICAL), + GATE_APMIXED(CLK_APMIXED_MIPIC0_26M, "apmixed_mipic026m", "f_f26m_ck", 6), + GATE_APMIXED(CLK_APMIXED_MDPLLGP_26M, "apmixed_mdpll26m", "f_f26m_ck", 7), + GATE_APMIXED(CLK_APMIXED_MMSYS_26M, "apmixed_mmsys26m", "f_f26m_ck", 8), + GATE_APMIXED(CLK_APMIXED_UFS_26M, "apmixed_ufs26m", "f_f26m_ck", 9), + GATE_APMIXED(CLK_APMIXED_MIPIC1_26M, "apmixed_mipic126m", "f_f26m_ck", 11), + GATE_APMIXED(CLK_APMIXED_MEMPLL_26M, "apmixed_mempll26m", "f_f26m_ck", 13), + GATE_APMIXED(CLK_APMIXED_CLKSQ_LVPLL_26M, "apmixed_lvpll26m", "f_f26m_ck", 14), + GATE_APMIXED(CLK_APMIXED_MIPID0_26M, "apmixed_mipid026m", "f_f26m_ck", 16), + GATE_APMIXED(CLK_APMIXED_MIPID1_26M, "apmixed_mipid126m", "f_f26m_ck", 17), +}; + +#define MT8183_PLL_FMAX (3800UL * MHZ) +#define MT8183_PLL_FMIN (1500UL * MHZ) + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ + _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift, \ + _pcw_chg_reg, _div_table) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = _rst_bar_mask, \ + .fmax = MT8183_PLL_FMAX, \ + .fmin = MT8183_PLL_FMIN, \ + .pcwbits = _pcwbits, \ + .pcwibits = _pcwibits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .tuner_en_reg = _tuner_en_reg, \ + .tuner_en_bit = _tuner_en_bit, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .pcw_chg_reg = _pcw_chg_reg, \ + .div_table = _div_table, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ + _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift, \ + _pcw_chg_reg) \ + PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ + _pd_shift, _tuner_reg, _tuner_en_reg, \ + _tuner_en_bit, _pcw_reg, _pcw_shift, \ + _pcw_chg_reg, NULL) + +static const struct mtk_pll_div_table armpll_div_table[] = { + { .div = 0, .freq = MT8183_PLL_FMAX }, + { .div = 1, .freq = 1500 * MHZ }, + { .div = 2, .freq = 750 * MHZ }, + { .div = 3, .freq = 375 * MHZ }, + { .div = 4, .freq = 187500000 }, + { /* sentinel */ } +}; + +static const struct mtk_pll_div_table mfgpll_div_table[] = { + { .div = 0, .freq = MT8183_PLL_FMAX }, + { .div = 1, .freq = 1600 * MHZ }, + { .div = 2, .freq = 800 * MHZ }, + { .div = 3, .freq = 400 * MHZ }, + { .div = 4, .freq = 200 * MHZ }, + { /* sentinel */ } +}; + +static const struct mtk_pll_data plls[] = { + PLL_B(CLK_APMIXED_ARMPLL_LL, "armpll_ll", 0x0200, 0x020C, 0, + HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0204, 24, 0x0, 0x0, 0, + 0x0204, 0, 0, armpll_div_table), + PLL_B(CLK_APMIXED_ARMPLL_L, "armpll_l", 0x0210, 0x021C, 0, + HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0214, 24, 0x0, 0x0, 0, + 0x0214, 0, 0, armpll_div_table), + PLL(CLK_APMIXED_CCIPLL, "ccipll", 0x0290, 0x029C, 0, + HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0294, 24, 0x0, 0x0, 0, + 0x0294, 0, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0220, 0x022C, 0, + HAVE_RST_BAR, BIT(24), 22, 8, 0x0224, 24, 0x0, 0x0, 0, + 0x0224, 0, 0), + PLL(CLK_APMIXED_UNIV2PLL, "univ2pll", 0x0230, 0x023C, 0, + HAVE_RST_BAR, BIT(24), 22, 8, 0x0234, 24, 0x0, 0x0, 0, + 0x0234, 0, 0), + PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0240, 0x024C, 0, + 0, 0, 22, 8, 0x0244, 24, 0x0, 0x0, 0, 0x0244, 0, 0, + mfgpll_div_table), + PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0250, 0x025C, 0, + 0, 0, 22, 8, 0x0254, 24, 0x0, 0x0, 0, 0x0254, 0, 0), + PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0260, 0x026C, 0, + 0, 0, 22, 8, 0x0264, 24, 0x0, 0x0, 0, 0x0264, 0, 0), + PLL(CLK_APMIXED_MMPLL, "mmpll", 0x0270, 0x027C, 0, + HAVE_RST_BAR, BIT(23), 22, 8, 0x0274, 24, 0x0, 0x0, 0, + 0x0274, 0, 0), + PLL(CLK_APMIXED_APLL1, "apll1", 0x02A0, 0x02B0, 0, + 0, 0, 32, 8, 0x02A0, 1, 0x02A8, 0x0014, 0, 0x02A4, 0, 0x02A0), + PLL(CLK_APMIXED_APLL2, "apll2", 0x02b4, 0x02c4, 0, + 0, 0, 32, 8, 0x02B4, 1, 0x02BC, 0x0014, 1, 0x02B8, 0, 0x02B4), +}; + +static int clk_mt8183_apmixed_probe(struct platform_device *pdev) +{ + void __iomem *base; + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_devm_alloc_clk_data(dev, CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); + if (ret) + goto unregister_plls; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_gates; + + return 0; + +unregister_gates: + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static const struct of_device_id of_match_clk_mt8183_apmixed[] = { + { .compatible = "mediatek,mt8183-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt8183_apmixed_drv = { + .probe = clk_mt8183_apmixed_probe, + .driver = { + .name = "clk-mt8183-apmixed", + .of_match_table = of_match_clk_mt8183_apmixed, + }, +}; +builtin_platform_driver(clk_mt8183_apmixed_drv) diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 722d913f0b4d..84b970f33316 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -14,7 +14,6 @@ #include "clk-gate.h" #include "clk-mtk.h" #include "clk-mux.h" -#include "clk-pll.h" #include @@ -941,140 +940,6 @@ static const struct mtk_gate peri_clks[] = { GATE_PERI(CLK_PERI_AXI, "peri_axi", "axi_sel", 31), }; -static const struct mtk_gate_regs apmixed_cg_regs = { - .set_ofs = 0x20, - .clr_ofs = 0x20, - .sta_ofs = 0x20, -}; - -#define GATE_APMIXED_FLAGS(_id, _name, _parent, _shift, _flags) \ - GATE_MTK_FLAGS(_id, _name, _parent, &apmixed_cg_regs, \ - _shift, &mtk_clk_gate_ops_no_setclr_inv, _flags) - -#define GATE_APMIXED(_id, _name, _parent, _shift) \ - GATE_APMIXED_FLAGS(_id, _name, _parent, _shift, 0) - -/* - * CRITICAL CLOCK: - * apmixed_appll26m is the toppest clock gate of all PLLs. - */ -static const struct mtk_gate apmixed_clks[] = { - /* AUDIO0 */ - GATE_APMIXED(CLK_APMIXED_SSUSB_26M, "apmixed_ssusb26m", - "f_f26m_ck", 4), - GATE_APMIXED_FLAGS(CLK_APMIXED_APPLL_26M, "apmixed_appll26m", - "f_f26m_ck", 5, CLK_IS_CRITICAL), - GATE_APMIXED(CLK_APMIXED_MIPIC0_26M, "apmixed_mipic026m", - "f_f26m_ck", 6), - GATE_APMIXED(CLK_APMIXED_MDPLLGP_26M, "apmixed_mdpll26m", - "f_f26m_ck", 7), - GATE_APMIXED(CLK_APMIXED_MMSYS_26M, "apmixed_mmsys26m", - "f_f26m_ck", 8), - GATE_APMIXED(CLK_APMIXED_UFS_26M, "apmixed_ufs26m", - "f_f26m_ck", 9), - GATE_APMIXED(CLK_APMIXED_MIPIC1_26M, "apmixed_mipic126m", - "f_f26m_ck", 11), - GATE_APMIXED(CLK_APMIXED_MEMPLL_26M, "apmixed_mempll26m", - "f_f26m_ck", 13), - GATE_APMIXED(CLK_APMIXED_CLKSQ_LVPLL_26M, "apmixed_lvpll26m", - "f_f26m_ck", 14), - GATE_APMIXED(CLK_APMIXED_MIPID0_26M, "apmixed_mipid026m", - "f_f26m_ck", 16), - GATE_APMIXED(CLK_APMIXED_MIPID1_26M, "apmixed_mipid126m", - "f_f26m_ck", 17), -}; - -#define MT8183_PLL_FMAX (3800UL * MHZ) -#define MT8183_PLL_FMIN (1500UL * MHZ) - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ - _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift, \ - _pcw_chg_reg, _div_table) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = _rst_bar_mask, \ - .fmax = MT8183_PLL_FMAX, \ - .fmin = MT8183_PLL_FMIN, \ - .pcwbits = _pcwbits, \ - .pcwibits = _pcwibits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .tuner_en_reg = _tuner_en_reg, \ - .tuner_en_bit = _tuner_en_bit, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .pcw_chg_reg = _pcw_chg_reg, \ - .div_table = _div_table, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ - _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift, \ - _pcw_chg_reg) \ - PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pcwibits, _pd_reg, \ - _pd_shift, _tuner_reg, _tuner_en_reg, \ - _tuner_en_bit, _pcw_reg, _pcw_shift, \ - _pcw_chg_reg, NULL) - -static const struct mtk_pll_div_table armpll_div_table[] = { - { .div = 0, .freq = MT8183_PLL_FMAX }, - { .div = 1, .freq = 1500 * MHZ }, - { .div = 2, .freq = 750 * MHZ }, - { .div = 3, .freq = 375 * MHZ }, - { .div = 4, .freq = 187500000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_div_table mfgpll_div_table[] = { - { .div = 0, .freq = MT8183_PLL_FMAX }, - { .div = 1, .freq = 1600 * MHZ }, - { .div = 2, .freq = 800 * MHZ }, - { .div = 3, .freq = 400 * MHZ }, - { .div = 4, .freq = 200 * MHZ }, - { } /* sentinel */ -}; - -static const struct mtk_pll_data plls[] = { - PLL_B(CLK_APMIXED_ARMPLL_LL, "armpll_ll", 0x0200, 0x020C, 0, - HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0204, 24, 0x0, 0x0, 0, - 0x0204, 0, 0, armpll_div_table), - PLL_B(CLK_APMIXED_ARMPLL_L, "armpll_l", 0x0210, 0x021C, 0, - HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0214, 24, 0x0, 0x0, 0, - 0x0214, 0, 0, armpll_div_table), - PLL(CLK_APMIXED_CCIPLL, "ccipll", 0x0290, 0x029C, 0, - HAVE_RST_BAR | PLL_AO, BIT(24), 22, 8, 0x0294, 24, 0x0, 0x0, 0, - 0x0294, 0, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0220, 0x022C, 0, - HAVE_RST_BAR, BIT(24), 22, 8, 0x0224, 24, 0x0, 0x0, 0, - 0x0224, 0, 0), - PLL(CLK_APMIXED_UNIV2PLL, "univ2pll", 0x0230, 0x023C, 0, - HAVE_RST_BAR, BIT(24), 22, 8, 0x0234, 24, 0x0, 0x0, 0, - 0x0234, 0, 0), - PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0240, 0x024C, 0, - 0, 0, 22, 8, 0x0244, 24, 0x0, 0x0, 0, 0x0244, 0, 0, - mfgpll_div_table), - PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0250, 0x025C, 0, - 0, 0, 22, 8, 0x0254, 24, 0x0, 0x0, 0, 0x0254, 0, 0), - PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0260, 0x026C, 0, - 0, 0, 22, 8, 0x0264, 24, 0x0, 0x0, 0, 0x0264, 0, 0), - PLL(CLK_APMIXED_MMPLL, "mmpll", 0x0270, 0x027C, 0, - HAVE_RST_BAR, BIT(23), 22, 8, 0x0274, 24, 0x0, 0x0, 0, - 0x0274, 0, 0), - PLL(CLK_APMIXED_APLL1, "apll1", 0x02A0, 0x02B0, 0, - 0, 0, 32, 8, 0x02A0, 1, 0x02A8, 0x0014, 0, 0x02A4, 0, 0x02A0), - PLL(CLK_APMIXED_APLL2, "apll2", 0x02b4, 0x02c4, 0, - 0, 0, 32, 8, 0x02B4, 1, 0x02BC, 0x0014, 1, 0x02B8, 0, 0x02B4), -}; - static u16 infra_rst_ofs[] = { INFRA_RST0_SET_OFFSET, INFRA_RST1_SET_OFFSET, @@ -1088,21 +953,6 @@ static const struct mtk_clk_rst_desc clk_rst_desc = { .rst_bank_nr = ARRAY_SIZE(infra_rst_ofs), }; -static int clk_mt8183_apmixed_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - - mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, - ARRAY_SIZE(apmixed_clks), clk_data); - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} - static struct clk_hw_onecell_data *top_clk_data; static void clk_mt8183_top_init_early(struct device_node *node) @@ -1204,9 +1054,6 @@ static int clk_mt8183_mcu_probe(struct platform_device *pdev) static const struct of_device_id of_match_clk_mt8183[] = { { - .compatible = "mediatek,mt8183-apmixedsys", - .data = clk_mt8183_apmixed_probe, - }, { .compatible = "mediatek,mt8183-topckgen", .data = clk_mt8183_top_probe, }, { -- GitLab From 2f140dabfe49745582226af4b4c371f4b248e7cf Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:09 +0100 Subject: [PATCH 0363/5631] clk: mediatek: mt8183: Compress clocks arrays entries where possible Increase human readability and decrease number of lines by compressing the clock array entries where possible, to a maximum of ~95 columns. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-21-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8183.c | 450 ++++++++++-------------------- 1 file changed, 150 insertions(+), 300 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 84b970f33316..9da193d7782d 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -448,138 +448,97 @@ static const char * const aud_2_parents[] = { static const struct mtk_mux top_muxes[] = { /* CLK_CFG_0 */ MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_MUX_AXI, "axi_sel", - axi_parents, 0x40, - 0x44, 0x48, 0, 2, 7, 0x004, 0, CLK_IS_CRITICAL), + axi_parents, 0x40, 0x44, 0x48, 0, 2, 7, 0x004, 0, CLK_IS_CRITICAL), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MM, "mm_sel", - mm_parents, 0x40, - 0x44, 0x48, 8, 3, 15, 0x004, 1), + mm_parents, 0x40, 0x44, 0x48, 8, 3, 15, 0x004, 1), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_IMG, "img_sel", - img_parents, 0x40, - 0x44, 0x48, 16, 3, 23, 0x004, 2), + img_parents, 0x40, 0x44, 0x48, 16, 3, 23, 0x004, 2), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_CAM, "cam_sel", - cam_parents, 0x40, - 0x44, 0x48, 24, 4, 31, 0x004, 3), + cam_parents, 0x40, 0x44, 0x48, 24, 4, 31, 0x004, 3), /* CLK_CFG_1 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DSP, "dsp_sel", - dsp_parents, 0x50, - 0x54, 0x58, 0, 4, 7, 0x004, 4), + dsp_parents, 0x50, 0x54, 0x58, 0, 4, 7, 0x004, 4), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DSP1, "dsp1_sel", - dsp1_parents, 0x50, - 0x54, 0x58, 8, 4, 15, 0x004, 5), + dsp1_parents, 0x50, 0x54, 0x58, 8, 4, 15, 0x004, 5), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DSP2, "dsp2_sel", - dsp2_parents, 0x50, - 0x54, 0x58, 16, 4, 23, 0x004, 6), + dsp2_parents, 0x50, 0x54, 0x58, 16, 4, 23, 0x004, 6), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_IPU_IF, "ipu_if_sel", - ipu_if_parents, 0x50, - 0x54, 0x58, 24, 4, 31, 0x004, 7), + ipu_if_parents, 0x50, 0x54, 0x58, 24, 4, 31, 0x004, 7), /* CLK_CFG_2 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MFG, "mfg_sel", - mfg_parents, 0x60, - 0x64, 0x68, 0, 2, 7, 0x004, 8), + mfg_parents, 0x60, 0x64, 0x68, 0, 2, 7, 0x004, 8), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_F52M_MFG, "f52m_mfg_sel", - f52m_mfg_parents, 0x60, - 0x64, 0x68, 8, 2, 15, 0x004, 9), + f52m_mfg_parents, 0x60, 0x64, 0x68, 8, 2, 15, 0x004, 9), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_CAMTG, "camtg_sel", - camtg_parents, 0x60, - 0x64, 0x68, 16, 3, 23, 0x004, 10), + camtg_parents, 0x60, 0x64, 0x68, 16, 3, 23, 0x004, 10), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_CAMTG2, "camtg2_sel", - camtg2_parents, 0x60, - 0x64, 0x68, 24, 3, 31, 0x004, 11), + camtg2_parents, 0x60, 0x64, 0x68, 24, 3, 31, 0x004, 11), /* CLK_CFG_3 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_CAMTG3, "camtg3_sel", - camtg3_parents, 0x70, - 0x74, 0x78, 0, 3, 7, 0x004, 12), + camtg3_parents, 0x70, 0x74, 0x78, 0, 3, 7, 0x004, 12), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_CAMTG4, "camtg4_sel", - camtg4_parents, 0x70, - 0x74, 0x78, 8, 3, 15, 0x004, 13), + camtg4_parents, 0x70, 0x74, 0x78, 8, 3, 15, 0x004, 13), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_UART, "uart_sel", - uart_parents, 0x70, - 0x74, 0x78, 16, 1, 23, 0x004, 14), + uart_parents, 0x70, 0x74, 0x78, 16, 1, 23, 0x004, 14), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SPI, "spi_sel", - spi_parents, 0x70, - 0x74, 0x78, 24, 2, 31, 0x004, 15), + spi_parents, 0x70, 0x74, 0x78, 24, 2, 31, 0x004, 15), /* CLK_CFG_4 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MSDC50_0_HCLK, "msdc50_hclk_sel", - msdc50_hclk_parents, 0x80, - 0x84, 0x88, 0, 2, 7, 0x004, 16), + msdc50_hclk_parents, 0x80, 0x84, 0x88, 0, 2, 7, 0x004, 16), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MSDC50_0, "msdc50_0_sel", - msdc50_0_parents, 0x80, - 0x84, 0x88, 8, 3, 15, 0x004, 17), + msdc50_0_parents, 0x80, 0x84, 0x88, 8, 3, 15, 0x004, 17), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MSDC30_1, "msdc30_1_sel", - msdc30_1_parents, 0x80, - 0x84, 0x88, 16, 3, 23, 0x004, 18), + msdc30_1_parents, 0x80, 0x84, 0x88, 16, 3, 23, 0x004, 18), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_MSDC30_2, "msdc30_2_sel", - msdc30_2_parents, 0x80, - 0x84, 0x88, 24, 3, 31, 0x004, 19), + msdc30_2_parents, 0x80, 0x84, 0x88, 24, 3, 31, 0x004, 19), /* CLK_CFG_5 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUDIO, "audio_sel", - audio_parents, 0x90, - 0x94, 0x98, 0, 2, 7, 0x004, 20), + audio_parents, 0x90, 0x94, 0x98, 0, 2, 7, 0x004, 20), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUD_INTBUS, "aud_intbus_sel", - aud_intbus_parents, 0x90, - 0x94, 0x98, 8, 2, 15, 0x004, 21), + aud_intbus_parents, 0x90, 0x94, 0x98, 8, 2, 15, 0x004, 21), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_PMICSPI, "pmicspi_sel", - pmicspi_parents, 0x90, - 0x94, 0x98, 16, 2, 23, 0x004, 22), + pmicspi_parents, 0x90, 0x94, 0x98, 16, 2, 23, 0x004, 22), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_FPWRAP_ULPOSC, "fpwrap_ulposc_sel", - fpwrap_ulposc_parents, 0x90, - 0x94, 0x98, 24, 2, 31, 0x004, 23), + fpwrap_ulposc_parents, 0x90, 0x94, 0x98, 24, 2, 31, 0x004, 23), /* CLK_CFG_6 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_ATB, "atb_sel", - atb_parents, 0xa0, - 0xa4, 0xa8, 0, 2, 7, 0x004, 24), + atb_parents, 0xa0, 0xa4, 0xa8, 0, 2, 7, 0x004, 24), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DPI0, "dpi0_sel", - dpi0_parents, 0xa0, - 0xa4, 0xa8, 16, 4, 23, 0x004, 26), + dpi0_parents, 0xa0, 0xa4, 0xa8, 16, 4, 23, 0x004, 26), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SCAM, "scam_sel", - scam_parents, 0xa0, - 0xa4, 0xa8, 24, 1, 31, 0x004, 27), + scam_parents, 0xa0, 0xa4, 0xa8, 24, 1, 31, 0x004, 27), /* CLK_CFG_7 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DISP_PWM, "disppwm_sel", - disppwm_parents, 0xb0, - 0xb4, 0xb8, 0, 3, 7, 0x004, 28), + disppwm_parents, 0xb0, 0xb4, 0xb8, 0, 3, 7, 0x004, 28), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_USB_TOP, "usb_top_sel", - usb_top_parents, 0xb0, - 0xb4, 0xb8, 8, 2, 15, 0x004, 29), + usb_top_parents, 0xb0, 0xb4, 0xb8, 8, 2, 15, 0x004, 29), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SSUSB_TOP_XHCI, "ssusb_top_xhci_sel", - ssusb_top_xhci_parents, 0xb0, - 0xb4, 0xb8, 16, 2, 23, 0x004, 30), + ssusb_top_xhci_parents, 0xb0, 0xb4, 0xb8, 16, 2, 23, 0x004, 30), MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_MUX_SPM, "spm_sel", - spm_parents, 0xb0, - 0xb4, 0xb8, 24, 1, 31, 0x008, 0, CLK_IS_CRITICAL), + spm_parents, 0xb0, 0xb4, 0xb8, 24, 1, 31, 0x008, 0, CLK_IS_CRITICAL), /* CLK_CFG_8 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_I2C, "i2c_sel", - i2c_parents, 0xc0, - 0xc4, 0xc8, 0, 2, 7, 0x008, 1), + i2c_parents, 0xc0, 0xc4, 0xc8, 0, 2, 7, 0x008, 1), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SCP, "scp_sel", - scp_parents, 0xc0, - 0xc4, 0xc8, 8, 3, 15, 0x008, 2), + scp_parents, 0xc0, 0xc4, 0xc8, 8, 3, 15, 0x008, 2), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_SENINF, "seninf_sel", - seninf_parents, 0xc0, - 0xc4, 0xc8, 16, 2, 23, 0x008, 3), + seninf_parents, 0xc0, 0xc4, 0xc8, 16, 2, 23, 0x008, 3), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_DXCC, "dxcc_sel", - dxcc_parents, 0xc0, - 0xc4, 0xc8, 24, 2, 31, 0x008, 4), + dxcc_parents, 0xc0, 0xc4, 0xc8, 24, 2, 31, 0x008, 4), /* CLK_CFG_9 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUD_ENG1, "aud_eng1_sel", - aud_engen1_parents, 0xd0, - 0xd4, 0xd8, 0, 2, 7, 0x008, 5), + aud_engen1_parents, 0xd0, 0xd4, 0xd8, 0, 2, 7, 0x008, 5), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUD_ENG2, "aud_eng2_sel", - aud_engen2_parents, 0xd0, - 0xd4, 0xd8, 8, 2, 15, 0x008, 6), + aud_engen2_parents, 0xd0, 0xd4, 0xd8, 8, 2, 15, 0x008, 6), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_FAES_UFSFDE, "faes_ufsfde_sel", - faes_ufsfde_parents, 0xd0, - 0xd4, 0xd8, 16, 3, 23, 0x008, 7), + faes_ufsfde_parents, 0xd0, 0xd4, 0xd8, 16, 3, 23, 0x008, 7), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_FUFS, "fufs_sel", - fufs_parents, 0xd0, - 0xd4, 0xd8, 24, 2, 31, 0x008, 8), + fufs_parents, 0xd0, 0xd4, 0xd8, 24, 2, 31, 0x008, 8), /* CLK_CFG_10 */ MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUD_1, "aud_1_sel", - aud_1_parents, 0xe0, - 0xe4, 0xe8, 0, 1, 7, 0x008, 9), + aud_1_parents, 0xe0, 0xe4, 0xe8, 0, 1, 7, 0x008, 9), MUX_GATE_CLR_SET_UPD(CLK_TOP_MUX_AUD_2, "aud_2_sel", - aud_2_parents, 0xe0, - 0xe4, 0xe8, 8, 1, 15, 0x008, 10), + aud_2_parents, 0xe0, 0xe4, 0xe8, 8, 1, 15, 0x008, 10), }; static const char * const apll_i2s0_parents[] = { @@ -643,30 +602,18 @@ static struct mtk_composite mcu_muxes[] = { }; static struct mtk_composite top_aud_comp[] = { - MUX(CLK_TOP_MUX_APLL_I2S0, "apll_i2s0_sel", apll_i2s0_parents, - 0x320, 8, 1), - MUX(CLK_TOP_MUX_APLL_I2S1, "apll_i2s1_sel", apll_i2s1_parents, - 0x320, 9, 1), - MUX(CLK_TOP_MUX_APLL_I2S2, "apll_i2s2_sel", apll_i2s2_parents, - 0x320, 10, 1), - MUX(CLK_TOP_MUX_APLL_I2S3, "apll_i2s3_sel", apll_i2s3_parents, - 0x320, 11, 1), - MUX(CLK_TOP_MUX_APLL_I2S4, "apll_i2s4_sel", apll_i2s4_parents, - 0x320, 12, 1), - MUX(CLK_TOP_MUX_APLL_I2S5, "apll_i2s5_sel", apll_i2s5_parents, - 0x328, 20, 1), - DIV_GATE(CLK_TOP_APLL12_DIV0, "apll12_div0", "apll_i2s0_sel", - 0x320, 2, 0x324, 8, 0), - DIV_GATE(CLK_TOP_APLL12_DIV1, "apll12_div1", "apll_i2s1_sel", - 0x320, 3, 0x324, 8, 8), - DIV_GATE(CLK_TOP_APLL12_DIV2, "apll12_div2", "apll_i2s2_sel", - 0x320, 4, 0x324, 8, 16), - DIV_GATE(CLK_TOP_APLL12_DIV3, "apll12_div3", "apll_i2s3_sel", - 0x320, 5, 0x324, 8, 24), - DIV_GATE(CLK_TOP_APLL12_DIV4, "apll12_div4", "apll_i2s4_sel", - 0x320, 6, 0x328, 8, 0), - DIV_GATE(CLK_TOP_APLL12_DIVB, "apll12_divb", "apll12_div4", - 0x320, 7, 0x328, 8, 8), + MUX(CLK_TOP_MUX_APLL_I2S0, "apll_i2s0_sel", apll_i2s0_parents, 0x320, 8, 1), + MUX(CLK_TOP_MUX_APLL_I2S1, "apll_i2s1_sel", apll_i2s1_parents, 0x320, 9, 1), + MUX(CLK_TOP_MUX_APLL_I2S2, "apll_i2s2_sel", apll_i2s2_parents, 0x320, 10, 1), + MUX(CLK_TOP_MUX_APLL_I2S3, "apll_i2s3_sel", apll_i2s3_parents, 0x320, 11, 1), + MUX(CLK_TOP_MUX_APLL_I2S4, "apll_i2s4_sel", apll_i2s4_parents, 0x320, 12, 1), + MUX(CLK_TOP_MUX_APLL_I2S5, "apll_i2s5_sel", apll_i2s5_parents, 0x328, 20, 1), + DIV_GATE(CLK_TOP_APLL12_DIV0, "apll12_div0", "apll_i2s0_sel", 0x320, 2, 0x324, 8, 0), + DIV_GATE(CLK_TOP_APLL12_DIV1, "apll12_div1", "apll_i2s1_sel", 0x320, 3, 0x324, 8, 8), + DIV_GATE(CLK_TOP_APLL12_DIV2, "apll12_div2", "apll_i2s2_sel", 0x320, 4, 0x324, 8, 16), + DIV_GATE(CLK_TOP_APLL12_DIV3, "apll12_div3", "apll_i2s3_sel", 0x320, 5, 0x324, 8, 24), + DIV_GATE(CLK_TOP_APLL12_DIV4, "apll12_div4", "apll_i2s4_sel", 0x320, 6, 0x328, 8, 0), + DIV_GATE(CLK_TOP_APLL12_DIVB, "apll12_divb", "apll12_div4", 0x320, 7, 0x328, 8, 8), }; static const struct mtk_gate_regs top_cg_regs = { @@ -727,203 +674,106 @@ static const struct mtk_gate_regs infra3_cg_regs = { static const struct mtk_gate infra_clks[] = { /* INFRA0 */ - GATE_INFRA0(CLK_INFRA_PMIC_TMR, "infra_pmic_tmr", - "axi_sel", 0), - GATE_INFRA0(CLK_INFRA_PMIC_AP, "infra_pmic_ap", - "axi_sel", 1), - GATE_INFRA0(CLK_INFRA_PMIC_MD, "infra_pmic_md", - "axi_sel", 2), - GATE_INFRA0(CLK_INFRA_PMIC_CONN, "infra_pmic_conn", - "axi_sel", 3), - GATE_INFRA0(CLK_INFRA_SCPSYS, "infra_scp", - "scp_sel", 4), - GATE_INFRA0(CLK_INFRA_SEJ, "infra_sej", - "f_f26m_ck", 5), - GATE_INFRA0(CLK_INFRA_APXGPT, "infra_apxgpt", - "axi_sel", 6), - GATE_INFRA0(CLK_INFRA_ICUSB, "infra_icusb", - "axi_sel", 8), - GATE_INFRA0(CLK_INFRA_GCE, "infra_gce", - "axi_sel", 9), - GATE_INFRA0(CLK_INFRA_THERM, "infra_therm", - "axi_sel", 10), - GATE_INFRA0(CLK_INFRA_I2C0, "infra_i2c0", - "i2c_sel", 11), - GATE_INFRA0(CLK_INFRA_I2C1, "infra_i2c1", - "i2c_sel", 12), - GATE_INFRA0(CLK_INFRA_I2C2, "infra_i2c2", - "i2c_sel", 13), - GATE_INFRA0(CLK_INFRA_I2C3, "infra_i2c3", - "i2c_sel", 14), - GATE_INFRA0(CLK_INFRA_PWM_HCLK, "infra_pwm_hclk", - "axi_sel", 15), - GATE_INFRA0(CLK_INFRA_PWM1, "infra_pwm1", - "i2c_sel", 16), - GATE_INFRA0(CLK_INFRA_PWM2, "infra_pwm2", - "i2c_sel", 17), - GATE_INFRA0(CLK_INFRA_PWM3, "infra_pwm3", - "i2c_sel", 18), - GATE_INFRA0(CLK_INFRA_PWM4, "infra_pwm4", - "i2c_sel", 19), - GATE_INFRA0(CLK_INFRA_PWM, "infra_pwm", - "i2c_sel", 21), - GATE_INFRA0(CLK_INFRA_UART0, "infra_uart0", - "uart_sel", 22), - GATE_INFRA0(CLK_INFRA_UART1, "infra_uart1", - "uart_sel", 23), - GATE_INFRA0(CLK_INFRA_UART2, "infra_uart2", - "uart_sel", 24), - GATE_INFRA0(CLK_INFRA_UART3, "infra_uart3", - "uart_sel", 25), - GATE_INFRA0(CLK_INFRA_GCE_26M, "infra_gce_26m", - "axi_sel", 27), - GATE_INFRA0(CLK_INFRA_CQ_DMA_FPC, "infra_cqdma_fpc", - "axi_sel", 28), - GATE_INFRA0(CLK_INFRA_BTIF, "infra_btif", - "axi_sel", 31), + GATE_INFRA0(CLK_INFRA_PMIC_TMR, "infra_pmic_tmr", "axi_sel", 0), + GATE_INFRA0(CLK_INFRA_PMIC_AP, "infra_pmic_ap", "axi_sel", 1), + GATE_INFRA0(CLK_INFRA_PMIC_MD, "infra_pmic_md", "axi_sel", 2), + GATE_INFRA0(CLK_INFRA_PMIC_CONN, "infra_pmic_conn", "axi_sel", 3), + GATE_INFRA0(CLK_INFRA_SCPSYS, "infra_scp", "scp_sel", 4), + GATE_INFRA0(CLK_INFRA_SEJ, "infra_sej", "f_f26m_ck", 5), + GATE_INFRA0(CLK_INFRA_APXGPT, "infra_apxgpt", "axi_sel", 6), + GATE_INFRA0(CLK_INFRA_ICUSB, "infra_icusb", "axi_sel", 8), + GATE_INFRA0(CLK_INFRA_GCE, "infra_gce", "axi_sel", 9), + GATE_INFRA0(CLK_INFRA_THERM, "infra_therm", "axi_sel", 10), + GATE_INFRA0(CLK_INFRA_I2C0, "infra_i2c0", "i2c_sel", 11), + GATE_INFRA0(CLK_INFRA_I2C1, "infra_i2c1", "i2c_sel", 12), + GATE_INFRA0(CLK_INFRA_I2C2, "infra_i2c2", "i2c_sel", 13), + GATE_INFRA0(CLK_INFRA_I2C3, "infra_i2c3", "i2c_sel", 14), + GATE_INFRA0(CLK_INFRA_PWM_HCLK, "infra_pwm_hclk", "axi_sel", 15), + GATE_INFRA0(CLK_INFRA_PWM1, "infra_pwm1", "i2c_sel", 16), + GATE_INFRA0(CLK_INFRA_PWM2, "infra_pwm2", "i2c_sel", 17), + GATE_INFRA0(CLK_INFRA_PWM3, "infra_pwm3", "i2c_sel", 18), + GATE_INFRA0(CLK_INFRA_PWM4, "infra_pwm4", "i2c_sel", 19), + GATE_INFRA0(CLK_INFRA_PWM, "infra_pwm", "i2c_sel", 21), + GATE_INFRA0(CLK_INFRA_UART0, "infra_uart0", "uart_sel", 22), + GATE_INFRA0(CLK_INFRA_UART1, "infra_uart1", "uart_sel", 23), + GATE_INFRA0(CLK_INFRA_UART2, "infra_uart2", "uart_sel", 24), + GATE_INFRA0(CLK_INFRA_UART3, "infra_uart3", "uart_sel", 25), + GATE_INFRA0(CLK_INFRA_GCE_26M, "infra_gce_26m", "axi_sel", 27), + GATE_INFRA0(CLK_INFRA_CQ_DMA_FPC, "infra_cqdma_fpc", "axi_sel", 28), + GATE_INFRA0(CLK_INFRA_BTIF, "infra_btif", "axi_sel", 31), /* INFRA1 */ - GATE_INFRA1(CLK_INFRA_SPI0, "infra_spi0", - "spi_sel", 1), - GATE_INFRA1(CLK_INFRA_MSDC0, "infra_msdc0", - "msdc50_hclk_sel", 2), - GATE_INFRA1(CLK_INFRA_MSDC1, "infra_msdc1", - "axi_sel", 4), - GATE_INFRA1(CLK_INFRA_MSDC2, "infra_msdc2", - "axi_sel", 5), - GATE_INFRA1(CLK_INFRA_MSDC0_SCK, "infra_msdc0_sck", - "msdc50_0_sel", 6), - GATE_INFRA1(CLK_INFRA_DVFSRC, "infra_dvfsrc", - "f_f26m_ck", 7), - GATE_INFRA1(CLK_INFRA_GCPU, "infra_gcpu", - "axi_sel", 8), - GATE_INFRA1(CLK_INFRA_TRNG, "infra_trng", - "axi_sel", 9), - GATE_INFRA1(CLK_INFRA_AUXADC, "infra_auxadc", - "f_f26m_ck", 10), - GATE_INFRA1(CLK_INFRA_CPUM, "infra_cpum", - "axi_sel", 11), - GATE_INFRA1(CLK_INFRA_CCIF1_AP, "infra_ccif1_ap", - "axi_sel", 12), - GATE_INFRA1(CLK_INFRA_CCIF1_MD, "infra_ccif1_md", - "axi_sel", 13), - GATE_INFRA1(CLK_INFRA_AUXADC_MD, "infra_auxadc_md", - "f_f26m_ck", 14), - GATE_INFRA1(CLK_INFRA_MSDC1_SCK, "infra_msdc1_sck", - "msdc30_1_sel", 16), - GATE_INFRA1(CLK_INFRA_MSDC2_SCK, "infra_msdc2_sck", - "msdc30_2_sel", 17), - GATE_INFRA1(CLK_INFRA_AP_DMA, "infra_apdma", - "axi_sel", 18), - GATE_INFRA1(CLK_INFRA_XIU, "infra_xiu", - "axi_sel", 19), - GATE_INFRA1(CLK_INFRA_DEVICE_APC, "infra_device_apc", - "axi_sel", 20), - GATE_INFRA1(CLK_INFRA_CCIF_AP, "infra_ccif_ap", - "axi_sel", 23), - GATE_INFRA1(CLK_INFRA_DEBUGSYS, "infra_debugsys", - "axi_sel", 24), - GATE_INFRA1(CLK_INFRA_AUDIO, "infra_audio", - "axi_sel", 25), - GATE_INFRA1(CLK_INFRA_CCIF_MD, "infra_ccif_md", - "axi_sel", 26), - GATE_INFRA1(CLK_INFRA_DXCC_SEC_CORE, "infra_dxcc_sec_core", - "dxcc_sel", 27), - GATE_INFRA1(CLK_INFRA_DXCC_AO, "infra_dxcc_ao", - "dxcc_sel", 28), - GATE_INFRA1(CLK_INFRA_DEVMPU_BCLK, "infra_devmpu_bclk", - "axi_sel", 30), - GATE_INFRA1(CLK_INFRA_DRAMC_F26M, "infra_dramc_f26m", - "f_f26m_ck", 31), + GATE_INFRA1(CLK_INFRA_SPI0, "infra_spi0", "spi_sel", 1), + GATE_INFRA1(CLK_INFRA_MSDC0, "infra_msdc0", "msdc50_hclk_sel", 2), + GATE_INFRA1(CLK_INFRA_MSDC1, "infra_msdc1", "axi_sel", 4), + GATE_INFRA1(CLK_INFRA_MSDC2, "infra_msdc2", "axi_sel", 5), + GATE_INFRA1(CLK_INFRA_MSDC0_SCK, "infra_msdc0_sck", "msdc50_0_sel", 6), + GATE_INFRA1(CLK_INFRA_DVFSRC, "infra_dvfsrc", "f_f26m_ck", 7), + GATE_INFRA1(CLK_INFRA_GCPU, "infra_gcpu", "axi_sel", 8), + GATE_INFRA1(CLK_INFRA_TRNG, "infra_trng", "axi_sel", 9), + GATE_INFRA1(CLK_INFRA_AUXADC, "infra_auxadc", "f_f26m_ck", 10), + GATE_INFRA1(CLK_INFRA_CPUM, "infra_cpum", "axi_sel", 11), + GATE_INFRA1(CLK_INFRA_CCIF1_AP, "infra_ccif1_ap", "axi_sel", 12), + GATE_INFRA1(CLK_INFRA_CCIF1_MD, "infra_ccif1_md", "axi_sel", 13), + GATE_INFRA1(CLK_INFRA_AUXADC_MD, "infra_auxadc_md", "f_f26m_ck", 14), + GATE_INFRA1(CLK_INFRA_MSDC1_SCK, "infra_msdc1_sck", "msdc30_1_sel", 16), + GATE_INFRA1(CLK_INFRA_MSDC2_SCK, "infra_msdc2_sck", "msdc30_2_sel", 17), + GATE_INFRA1(CLK_INFRA_AP_DMA, "infra_apdma", "axi_sel", 18), + GATE_INFRA1(CLK_INFRA_XIU, "infra_xiu", "axi_sel", 19), + GATE_INFRA1(CLK_INFRA_DEVICE_APC, "infra_device_apc", "axi_sel", 20), + GATE_INFRA1(CLK_INFRA_CCIF_AP, "infra_ccif_ap", "axi_sel", 23), + GATE_INFRA1(CLK_INFRA_DEBUGSYS, "infra_debugsys", "axi_sel", 24), + GATE_INFRA1(CLK_INFRA_AUDIO, "infra_audio", "axi_sel", 25), + GATE_INFRA1(CLK_INFRA_CCIF_MD, "infra_ccif_md", "axi_sel", 26), + GATE_INFRA1(CLK_INFRA_DXCC_SEC_CORE, "infra_dxcc_sec_core", "dxcc_sel", 27), + GATE_INFRA1(CLK_INFRA_DXCC_AO, "infra_dxcc_ao", "dxcc_sel", 28), + GATE_INFRA1(CLK_INFRA_DEVMPU_BCLK, "infra_devmpu_bclk", "axi_sel", 30), + GATE_INFRA1(CLK_INFRA_DRAMC_F26M, "infra_dramc_f26m", "f_f26m_ck", 31), /* INFRA2 */ - GATE_INFRA2(CLK_INFRA_IRTX, "infra_irtx", - "f_f26m_ck", 0), - GATE_INFRA2(CLK_INFRA_USB, "infra_usb", - "usb_top_sel", 1), - GATE_INFRA2(CLK_INFRA_DISP_PWM, "infra_disppwm", - "axi_sel", 2), - GATE_INFRA2(CLK_INFRA_CLDMA_BCLK, "infra_cldma_bclk", - "axi_sel", 3), - GATE_INFRA2(CLK_INFRA_AUDIO_26M_BCLK, "infra_audio_26m_bclk", - "f_f26m_ck", 4), - GATE_INFRA2(CLK_INFRA_SPI1, "infra_spi1", - "spi_sel", 6), - GATE_INFRA2(CLK_INFRA_I2C4, "infra_i2c4", - "i2c_sel", 7), - GATE_INFRA2(CLK_INFRA_MODEM_TEMP_SHARE, "infra_md_tmp_share", - "f_f26m_ck", 8), - GATE_INFRA2(CLK_INFRA_SPI2, "infra_spi2", - "spi_sel", 9), - GATE_INFRA2(CLK_INFRA_SPI3, "infra_spi3", - "spi_sel", 10), - GATE_INFRA2(CLK_INFRA_UNIPRO_SCK, "infra_unipro_sck", - "ssusb_top_xhci_sel", 11), - GATE_INFRA2(CLK_INFRA_UNIPRO_TICK, "infra_unipro_tick", - "fufs_sel", 12), - GATE_INFRA2(CLK_INFRA_UFS_MP_SAP_BCLK, "infra_ufs_mp_sap_bck", - "fufs_sel", 13), - GATE_INFRA2(CLK_INFRA_MD32_BCLK, "infra_md32_bclk", - "axi_sel", 14), - GATE_INFRA2(CLK_INFRA_UNIPRO_MBIST, "infra_unipro_mbist", - "axi_sel", 16), - GATE_INFRA2(CLK_INFRA_I2C5, "infra_i2c5", - "i2c_sel", 18), - GATE_INFRA2(CLK_INFRA_I2C5_ARBITER, "infra_i2c5_arbiter", - "i2c_sel", 19), - GATE_INFRA2(CLK_INFRA_I2C5_IMM, "infra_i2c5_imm", - "i2c_sel", 20), - GATE_INFRA2(CLK_INFRA_I2C1_ARBITER, "infra_i2c1_arbiter", - "i2c_sel", 21), - GATE_INFRA2(CLK_INFRA_I2C1_IMM, "infra_i2c1_imm", - "i2c_sel", 22), - GATE_INFRA2(CLK_INFRA_I2C2_ARBITER, "infra_i2c2_arbiter", - "i2c_sel", 23), - GATE_INFRA2(CLK_INFRA_I2C2_IMM, "infra_i2c2_imm", - "i2c_sel", 24), - GATE_INFRA2(CLK_INFRA_SPI4, "infra_spi4", - "spi_sel", 25), - GATE_INFRA2(CLK_INFRA_SPI5, "infra_spi5", - "spi_sel", 26), - GATE_INFRA2(CLK_INFRA_CQ_DMA, "infra_cqdma", - "axi_sel", 27), - GATE_INFRA2(CLK_INFRA_UFS, "infra_ufs", - "fufs_sel", 28), - GATE_INFRA2(CLK_INFRA_AES_UFSFDE, "infra_aes_ufsfde", - "faes_ufsfde_sel", 29), - GATE_INFRA2(CLK_INFRA_UFS_TICK, "infra_ufs_tick", - "fufs_sel", 30), + GATE_INFRA2(CLK_INFRA_IRTX, "infra_irtx", "f_f26m_ck", 0), + GATE_INFRA2(CLK_INFRA_USB, "infra_usb", "usb_top_sel", 1), + GATE_INFRA2(CLK_INFRA_DISP_PWM, "infra_disppwm", "axi_sel", 2), + GATE_INFRA2(CLK_INFRA_CLDMA_BCLK, "infra_cldma_bclk", "axi_sel", 3), + GATE_INFRA2(CLK_INFRA_AUDIO_26M_BCLK, "infra_audio_26m_bclk", "f_f26m_ck", 4), + GATE_INFRA2(CLK_INFRA_SPI1, "infra_spi1", "spi_sel", 6), + GATE_INFRA2(CLK_INFRA_I2C4, "infra_i2c4", "i2c_sel", 7), + GATE_INFRA2(CLK_INFRA_MODEM_TEMP_SHARE, "infra_md_tmp_share", "f_f26m_ck", 8), + GATE_INFRA2(CLK_INFRA_SPI2, "infra_spi2", "spi_sel", 9), + GATE_INFRA2(CLK_INFRA_SPI3, "infra_spi3", "spi_sel", 10), + GATE_INFRA2(CLK_INFRA_UNIPRO_SCK, "infra_unipro_sck", "ssusb_top_xhci_sel", 11), + GATE_INFRA2(CLK_INFRA_UNIPRO_TICK, "infra_unipro_tick", "fufs_sel", 12), + GATE_INFRA2(CLK_INFRA_UFS_MP_SAP_BCLK, "infra_ufs_mp_sap_bck", "fufs_sel", 13), + GATE_INFRA2(CLK_INFRA_MD32_BCLK, "infra_md32_bclk", "axi_sel", 14), + GATE_INFRA2(CLK_INFRA_UNIPRO_MBIST, "infra_unipro_mbist", "axi_sel", 16), + GATE_INFRA2(CLK_INFRA_I2C5, "infra_i2c5", "i2c_sel", 18), + GATE_INFRA2(CLK_INFRA_I2C5_ARBITER, "infra_i2c5_arbiter", "i2c_sel", 19), + GATE_INFRA2(CLK_INFRA_I2C5_IMM, "infra_i2c5_imm", "i2c_sel", 20), + GATE_INFRA2(CLK_INFRA_I2C1_ARBITER, "infra_i2c1_arbiter", "i2c_sel", 21), + GATE_INFRA2(CLK_INFRA_I2C1_IMM, "infra_i2c1_imm", "i2c_sel", 22), + GATE_INFRA2(CLK_INFRA_I2C2_ARBITER, "infra_i2c2_arbiter", "i2c_sel", 23), + GATE_INFRA2(CLK_INFRA_I2C2_IMM, "infra_i2c2_imm", "i2c_sel", 24), + GATE_INFRA2(CLK_INFRA_SPI4, "infra_spi4", "spi_sel", 25), + GATE_INFRA2(CLK_INFRA_SPI5, "infra_spi5", "spi_sel", 26), + GATE_INFRA2(CLK_INFRA_CQ_DMA, "infra_cqdma", "axi_sel", 27), + GATE_INFRA2(CLK_INFRA_UFS, "infra_ufs", "fufs_sel", 28), + GATE_INFRA2(CLK_INFRA_AES_UFSFDE, "infra_aes_ufsfde", "faes_ufsfde_sel", 29), + GATE_INFRA2(CLK_INFRA_UFS_TICK, "infra_ufs_tick", "fufs_sel", 30), /* INFRA3 */ - GATE_INFRA3(CLK_INFRA_MSDC0_SELF, "infra_msdc0_self", - "msdc50_0_sel", 0), - GATE_INFRA3(CLK_INFRA_MSDC1_SELF, "infra_msdc1_self", - "msdc50_0_sel", 1), - GATE_INFRA3(CLK_INFRA_MSDC2_SELF, "infra_msdc2_self", - "msdc50_0_sel", 2), - GATE_INFRA3(CLK_INFRA_UFS_AXI, "infra_ufs_axi", - "axi_sel", 5), - GATE_INFRA3(CLK_INFRA_I2C6, "infra_i2c6", - "i2c_sel", 6), - GATE_INFRA3(CLK_INFRA_AP_MSDC0, "infra_ap_msdc0", - "msdc50_hclk_sel", 7), - GATE_INFRA3(CLK_INFRA_MD_MSDC0, "infra_md_msdc0", - "msdc50_hclk_sel", 8), - GATE_INFRA3(CLK_INFRA_CCIF2_AP, "infra_ccif2_ap", - "axi_sel", 16), - GATE_INFRA3(CLK_INFRA_CCIF2_MD, "infra_ccif2_md", - "axi_sel", 17), - GATE_INFRA3(CLK_INFRA_CCIF3_AP, "infra_ccif3_ap", - "axi_sel", 18), - GATE_INFRA3(CLK_INFRA_CCIF3_MD, "infra_ccif3_md", - "axi_sel", 19), - GATE_INFRA3(CLK_INFRA_SEJ_F13M, "infra_sej_f13m", - "f_f26m_ck", 20), - GATE_INFRA3(CLK_INFRA_AES_BCLK, "infra_aes_bclk", - "axi_sel", 21), - GATE_INFRA3(CLK_INFRA_I2C7, "infra_i2c7", - "i2c_sel", 22), - GATE_INFRA3(CLK_INFRA_I2C8, "infra_i2c8", - "i2c_sel", 23), - GATE_INFRA3(CLK_INFRA_FBIST2FPC, "infra_fbist2fpc", - "msdc50_0_sel", 24), + GATE_INFRA3(CLK_INFRA_MSDC0_SELF, "infra_msdc0_self", "msdc50_0_sel", 0), + GATE_INFRA3(CLK_INFRA_MSDC1_SELF, "infra_msdc1_self", "msdc50_0_sel", 1), + GATE_INFRA3(CLK_INFRA_MSDC2_SELF, "infra_msdc2_self", "msdc50_0_sel", 2), + GATE_INFRA3(CLK_INFRA_UFS_AXI, "infra_ufs_axi", "axi_sel", 5), + GATE_INFRA3(CLK_INFRA_I2C6, "infra_i2c6", "i2c_sel", 6), + GATE_INFRA3(CLK_INFRA_AP_MSDC0, "infra_ap_msdc0", "msdc50_hclk_sel", 7), + GATE_INFRA3(CLK_INFRA_MD_MSDC0, "infra_md_msdc0", "msdc50_hclk_sel", 8), + GATE_INFRA3(CLK_INFRA_CCIF2_AP, "infra_ccif2_ap", "axi_sel", 16), + GATE_INFRA3(CLK_INFRA_CCIF2_MD, "infra_ccif2_md", "axi_sel", 17), + GATE_INFRA3(CLK_INFRA_CCIF3_AP, "infra_ccif3_ap", "axi_sel", 18), + GATE_INFRA3(CLK_INFRA_CCIF3_MD, "infra_ccif3_md", "axi_sel", 19), + GATE_INFRA3(CLK_INFRA_SEJ_F13M, "infra_sej_f13m", "f_f26m_ck", 20), + GATE_INFRA3(CLK_INFRA_AES_BCLK, "infra_aes_bclk", "axi_sel", 21), + GATE_INFRA3(CLK_INFRA_I2C7, "infra_i2c7", "i2c_sel", 22), + GATE_INFRA3(CLK_INFRA_I2C8, "infra_i2c8", "i2c_sel", 23), + GATE_INFRA3(CLK_INFRA_FBIST2FPC, "infra_fbist2fpc", "msdc50_0_sel", 24), }; static const struct mtk_gate_regs peri_cg_regs = { -- GitLab From 3f37ba7cc385ba07762ffcd7ac38af8c0f84dd3e Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:10 +0100 Subject: [PATCH 0364/5631] clk: mediatek: mt8183: Convert all remaining clocks to common probe Switch to mtk_clk_simple_{probe,remove}() for infracfg and topckgen clocks on MT8183 to allow full module build for clock drivers. Differently from other MediaTek clock drivers, it was necessary to change the name of the `clk13m` clock, as that is already declared in the SoC's devicetree as a "fixed-factor-clock" (with the same name) and redeclaring it here would obviously fail to register the entire clock controller; this clock wasn't dropped only to retain compatibility with older devicetrees As a note, the `clk13m` clock is not mentioned in any parent names array(s) as the correct one (csw_f26m_d2) is already used in place of that. Thanks to the conversion, more error handling was added to the clocks registration. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-22-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8183.c | 166 ++++++------------------------ 1 file changed, 34 insertions(+), 132 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 9da193d7782d..02176ee97cd2 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -25,11 +25,14 @@ static const struct mtk_fixed_clk top_fixed_clks[] = { FIXED_CLK(CLK_TOP_UNIVP_192M, "univpll_192m", "univpll", 192000000), }; -static const struct mtk_fixed_factor top_early_divs[] = { - FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, 2), -}; - +/* + * To retain compatibility with older devicetrees, we keep CLK_TOP_CLK13M + * valid, but renamed from "clk13m" (defined as fixed clock in the new + * devicetrees) to "clk26m_d2", satisfying the older clock assignments. + * This means that on new devicetrees "clk26m_d2" is unused. + */ static const struct mtk_fixed_factor top_divs[] = { + FACTOR(CLK_TOP_CLK13M, "clk26m_d2", "clk26m", 1, 2), FACTOR(CLK_TOP_F26M_CK_D2, "csw_f26m_ck_d2", "clk26m", 1, 2), FACTOR_FLAGS(CLK_TOP_SYSPLL_CK, "syspll_ck", "mainpll", 1, 1, 0), FACTOR_FLAGS(CLK_TOP_SYSPLL_D2, "syspll_d2", "syspll_ck", 1, 2, 0), @@ -803,26 +806,6 @@ static const struct mtk_clk_rst_desc clk_rst_desc = { .rst_bank_nr = ARRAY_SIZE(infra_rst_ofs), }; -static struct clk_hw_onecell_data *top_clk_data; - -static void clk_mt8183_top_init_early(struct device_node *node) -{ - int i; - - top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - - for (i = 0; i < CLK_TOP_NR_CLK; i++) - top_clk_data->hws[i] = ERR_PTR(-EPROBE_DEFER); - - mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), - top_clk_data); - - of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); -} - -CLK_OF_DECLARE_DRIVER(mt8183_topckgen, "mediatek,mt8183-topckgen", - clk_mt8183_top_init_early); - /* Register mux notifier for MFG mux */ static int clk_mt8183_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) { @@ -845,134 +828,53 @@ static int clk_mt8183_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) return devm_mtk_clk_mux_notifier_register(dev, clk, mfg_mux_nb); } -static int clk_mt8183_top_probe(struct platform_device *pdev) -{ - void __iomem *base; - struct device_node *node = pdev->dev.of_node; - int ret; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), - top_clk_data); - - mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs), - top_clk_data); - - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); - - mtk_clk_register_muxes(&pdev->dev, top_muxes, - ARRAY_SIZE(top_muxes), node, - &mt8183_clk_lock, top_clk_data); - - mtk_clk_register_composites(&pdev->dev, top_aud_comp, - ARRAY_SIZE(top_aud_comp), base, - &mt8183_clk_lock, top_clk_data); - - mtk_clk_register_gates(&pdev->dev, node, top_clks, - ARRAY_SIZE(top_clks), top_clk_data); - - ret = clk_mt8183_reg_mfg_mux_notifier(&pdev->dev, - top_clk_data->hws[CLK_TOP_MUX_MFG]->clk); - if (ret) - return ret; - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, - top_clk_data); -} - -static int clk_mt8183_mcu_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - void __iomem *base; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - - mtk_clk_register_composites(&pdev->dev, mcu_muxes, - ARRAY_SIZE(mcu_muxes), base, - &mt8183_clk_lock, clk_data); - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} - -static const struct of_device_id of_match_clk_mt8183[] = { - { - .compatible = "mediatek,mt8183-topckgen", - .data = clk_mt8183_top_probe, - }, { - .compatible = "mediatek,mt8183-mcucfg", - .data = clk_mt8183_mcu_probe, - }, { - /* sentinel */ - } -}; - -static int clk_mt8183_probe(struct platform_device *pdev) -{ - int (*clk_probe)(struct platform_device *pdev); - int r; - - clk_probe = of_device_get_match_data(&pdev->dev); - if (!clk_probe) - return -EINVAL; - - r = clk_probe(pdev); - if (r) - dev_err(&pdev->dev, - "could not register clock provider: %s: %d\n", - pdev->name, r); - - return r; -} - static const struct mtk_clk_desc infra_desc = { .clks = infra_clks, .num_clks = ARRAY_SIZE(infra_clks), .rst_desc = &clk_rst_desc, }; +static const struct mtk_clk_desc mcu_desc = { + .composite_clks = mcu_muxes, + .num_composite_clks = ARRAY_SIZE(mcu_muxes), + .clk_lock = &mt8183_clk_lock, +}; + static const struct mtk_clk_desc peri_desc = { .clks = peri_clks, .num_clks = ARRAY_SIZE(peri_clks), }; -static const struct of_device_id of_match_clk_mt8183_simple[] = { +static const struct mtk_clk_desc topck_desc = { + .fixed_clks = top_fixed_clks, + .num_fixed_clks = ARRAY_SIZE(top_fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .mux_clks = top_muxes, + .num_mux_clks = ARRAY_SIZE(top_muxes), + .composite_clks = top_aud_comp, + .num_composite_clks = ARRAY_SIZE(top_aud_comp), + .clks = top_clks, + .num_clks = ARRAY_SIZE(top_clks), + .clk_lock = &mt8183_clk_lock, + .clk_notifier_func = clk_mt8183_reg_mfg_mux_notifier, + .mfg_clk_idx = CLK_TOP_MUX_MFG, +}; + +static const struct of_device_id of_match_clk_mt8183[] = { { .compatible = "mediatek,mt8183-infracfg", .data = &infra_desc }, + { .compatible = "mediatek,mt8183-mcucfg", .data = &mcu_desc }, { .compatible = "mediatek,mt8183-pericfg", .data = &peri_desc, }, + { .compatible = "mediatek,mt8183-topckgen", .data = &topck_desc }, { /* sentinel */ } }; -static struct platform_driver clk_mt8183_simple_drv = { +static struct platform_driver clk_mt8183_drv = { .probe = mtk_clk_simple_probe, .remove = mtk_clk_simple_remove, - .driver = { - .name = "clk-mt8183-simple", - .of_match_table = of_match_clk_mt8183_simple, - }, -}; - -static struct platform_driver clk_mt8183_drv = { - .probe = clk_mt8183_probe, .driver = { .name = "clk-mt8183", .of_match_table = of_match_clk_mt8183, }, }; - -static int __init clk_mt8183_init(void) -{ - int ret = platform_driver_register(&clk_mt8183_drv); - - if (ret) - return ret; - return platform_driver_register(&clk_mt8183_simple_drv); -} - -arch_initcall(clk_mt8183_init); +module_platform_driver(clk_mt8183_drv) -- GitLab From 4c85e20b656607897e3bb06ff565822fa4b4de95 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:11 +0100 Subject: [PATCH 0365/5631] clk: mediatek: Consistently use GATE_MTK() macro All the various MediaTek clock drivers are, in a way or another, redefining the GATE_MTK() macro with different names: while some are doing that by actually using GATE_MTK(), others are copying it entirely (hence, entirely redefining it). Change all clock drivers to always and consistently use this macro. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai # MT8183, MT8192, MT8195 Chromebooks Link: https://lore.kernel.org/r/20230306140543.1813621-23-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701-aud.c | 40 +++-------- drivers/clk/mediatek/clk-mt2701-bdp.c | 20 ++---- drivers/clk/mediatek/clk-mt2701-eth.c | 10 +-- drivers/clk/mediatek/clk-mt2701-g3d.c | 10 +-- drivers/clk/mediatek/clk-mt2701-hif.c | 10 +-- drivers/clk/mediatek/clk-mt2701-img.c | 10 +-- drivers/clk/mediatek/clk-mt2701-mm.c | 20 ++---- drivers/clk/mediatek/clk-mt2701-vdec.c | 20 ++---- drivers/clk/mediatek/clk-mt2701.c | 40 +++-------- drivers/clk/mediatek/clk-mt2712-bdp.c | 10 +-- drivers/clk/mediatek/clk-mt2712-img.c | 10 +-- drivers/clk/mediatek/clk-mt2712-jpgdec.c | 10 +-- drivers/clk/mediatek/clk-mt2712-mfg.c | 10 +-- drivers/clk/mediatek/clk-mt2712-mm.c | 30 ++------ drivers/clk/mediatek/clk-mt2712-vdec.c | 20 ++---- drivers/clk/mediatek/clk-mt2712-venc.c | 10 +-- drivers/clk/mediatek/clk-mt2712.c | 66 ++++-------------- drivers/clk/mediatek/clk-mt6765-audio.c | 20 ++---- drivers/clk/mediatek/clk-mt6765-cam.c | 10 +-- drivers/clk/mediatek/clk-mt6765-img.c | 10 +-- drivers/clk/mediatek/clk-mt6765-mipi0a.c | 10 +-- drivers/clk/mediatek/clk-mt6765-mm.c | 10 +-- drivers/clk/mediatek/clk-mt6765-vcodec.c | 10 +-- drivers/clk/mediatek/clk-mt6765.c | 80 +++++----------------- drivers/clk/mediatek/clk-mt6797-img.c | 10 +-- drivers/clk/mediatek/clk-mt6797-mm.c | 20 ++---- drivers/clk/mediatek/clk-mt6797-vdec.c | 20 ++---- drivers/clk/mediatek/clk-mt6797-venc.c | 10 +-- drivers/clk/mediatek/clk-mt6797.c | 42 ++++-------- drivers/clk/mediatek/clk-mt7622-aud.c | 40 +++-------- drivers/clk/mediatek/clk-mt7622-eth.c | 20 ++---- drivers/clk/mediatek/clk-mt7622-hif.c | 22 ++---- drivers/clk/mediatek/clk-mt7622.c | 61 ++++------------- drivers/clk/mediatek/clk-mt7629-eth.c | 20 ++---- drivers/clk/mediatek/clk-mt7629-hif.c | 22 ++---- drivers/clk/mediatek/clk-mt7629.c | 40 +++-------- drivers/clk/mediatek/clk-mt7986-eth.c | 24 ++----- drivers/clk/mediatek/clk-mt7986-infracfg.c | 24 ++----- drivers/clk/mediatek/clk-mt8135.c | 30 ++------ drivers/clk/mediatek/clk-mt8167-aud.c | 11 +-- drivers/clk/mediatek/clk-mt8167-img.c | 10 +-- drivers/clk/mediatek/clk-mt8167-mfgcfg.c | 10 +-- drivers/clk/mediatek/clk-mt8167-mm.c | 20 ++---- drivers/clk/mediatek/clk-mt8167-vdec.c | 20 ++---- drivers/clk/mediatek/clk-mt8173-mm.c | 20 ++---- drivers/clk/mediatek/clk-mt8516-aud.c | 10 +-- drivers/clk/mediatek/clk-mt8516.c | 60 ++++------------ 47 files changed, 223 insertions(+), 839 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index 1a32d8b7db84..21f7cc106bbe 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -15,41 +15,17 @@ #include -#define GATE_AUDIO0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio2_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio3_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate_regs audio0_cg_regs = { .set_ofs = 0x0, diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c index 435ed4819d56..b0f057207945 100644 --- a/drivers/clk/mediatek/clk-mt2701-bdp.c +++ b/drivers/clk/mediatek/clk-mt2701-bdp.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs bdp1_cg_regs = { .sta_ofs = 0x0110, }; -#define GATE_BDP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &bdp0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_BDP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &bdp0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_BDP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &bdp1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_BDP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &bdp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate bdp_clks[] = { GATE_BDP0(CLK_BDP_BRG_BA, "brg_baclk", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2701-eth.c b/drivers/clk/mediatek/clk-mt2701-eth.c index f3cb78e7f6e9..4c830ebdd761 100644 --- a/drivers/clk/mediatek/clk-mt2701-eth.c +++ b/drivers/clk/mediatek/clk-mt2701-eth.c @@ -16,14 +16,8 @@ static const struct mtk_gate_regs eth_cg_regs = { .sta_ofs = 0x0030, }; -#define GATE_ETH(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = ð_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_ETH(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, ð_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate eth_clks[] = { GATE_DUMMY(CLK_DUMMY, "eth_dummy"), diff --git a/drivers/clk/mediatek/clk-mt2701-g3d.c b/drivers/clk/mediatek/clk-mt2701-g3d.c index 499a170ba5f9..ae094046890a 100644 --- a/drivers/clk/mediatek/clk-mt2701-g3d.c +++ b/drivers/clk/mediatek/clk-mt2701-g3d.c @@ -16,14 +16,8 @@ #include -#define GATE_G3D(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &g3d_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_G3D(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &g3d_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate_regs g3d_cg_regs = { .sta_ofs = 0x0, diff --git a/drivers/clk/mediatek/clk-mt2701-hif.c b/drivers/clk/mediatek/clk-mt2701-hif.c index d5465d782993..3583bd1240d5 100644 --- a/drivers/clk/mediatek/clk-mt2701-hif.c +++ b/drivers/clk/mediatek/clk-mt2701-hif.c @@ -16,14 +16,8 @@ static const struct mtk_gate_regs hif_cg_regs = { .sta_ofs = 0x0030, }; -#define GATE_HIF(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &hif_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_HIF(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &hif_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate hif_clks[] = { GATE_DUMMY(CLK_DUMMY, "hif_dummy"), diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c index 7e53deb7f990..eb172473f075 100644 --- a/drivers/clk/mediatek/clk-mt2701-img.c +++ b/drivers/clk/mediatek/clk-mt2701-img.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs img_cg_regs = { .sta_ofs = 0x0000, }; -#define GATE_IMG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &img_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IMG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_SMI_COMM, "img_smi_comm", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index a8d94ca0eefd..993d904d619f 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs disp1_cg_regs = { .sta_ofs = 0x0110, }; -#define GATE_DISP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &disp0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_DISP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &disp0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_DISP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &disp1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_DISP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &disp1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { GATE_DISP0(CLK_MM_SMI_COMMON, "mm_smi_comm", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c index d3089da0ab62..0f07c5d731df 100644 --- a/drivers/clk/mediatek/clk-mt2701-vdec.c +++ b/drivers/clk/mediatek/clk-mt2701-vdec.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs vdec1_cg_regs = { .sta_ofs = 0x0008, }; -#define GATE_VDEC0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_VDEC1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate vdec_clks[] = { GATE_VDEC0(CLK_VDEC_CKGEN, "vdec_cken", "vdec_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index 06ca81359d35..dfe328f7a44b 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -636,14 +636,8 @@ static const struct mtk_gate_regs top_aud_cg_regs = { .sta_ofs = 0x012C, }; -#define GATE_TOP_AUD(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top_aud_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP_AUD(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top_aud_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate top_clks[] = { GATE_TOP_AUD(CLK_TOP_AUD_48K_TIMING, "a1sys_hp_ck", "aud_mux1_div", @@ -702,14 +696,8 @@ static const struct mtk_gate_regs infra_cg_regs = { .sta_ofs = 0x0048, }; -#define GATE_ICG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_ICG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate infra_clks[] = { GATE_ICG(CLK_INFRA_DBG, "dbgclk", "axi_sel", 0), @@ -823,23 +811,11 @@ static const struct mtk_gate_regs peri1_cg_regs = { .sta_ofs = 0x001c, }; -#define GATE_PERI0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_PERI1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate peri_clks[] = { GATE_PERI0(CLK_PERI_USB0_MCU, "usb0_mcu_ck", "axi_sel", 31), diff --git a/drivers/clk/mediatek/clk-mt2712-bdp.c b/drivers/clk/mediatek/clk-mt2712-bdp.c index 684d03e9f6de..5e668651dd90 100644 --- a/drivers/clk/mediatek/clk-mt2712-bdp.c +++ b/drivers/clk/mediatek/clk-mt2712-bdp.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs bdp_cg_regs = { .sta_ofs = 0x100, }; -#define GATE_BDP(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &bdp_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_BDP(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &bdp_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate bdp_clks[] = { GATE_BDP(CLK_BDP_BRIDGE_B, "bdp_bridge_b", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2712-img.c b/drivers/clk/mediatek/clk-mt2712-img.c index 335049cdc856..3ffa51384e6b 100644 --- a/drivers/clk/mediatek/clk-mt2712-img.c +++ b/drivers/clk/mediatek/clk-mt2712-img.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs img_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_IMG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &img_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_IMG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_SMI_LARB2, "img_smi_larb2", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2712-jpgdec.c b/drivers/clk/mediatek/clk-mt2712-jpgdec.c index 07ba7c5e80af..8c768d5ce24d 100644 --- a/drivers/clk/mediatek/clk-mt2712-jpgdec.c +++ b/drivers/clk/mediatek/clk-mt2712-jpgdec.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs jpgdec_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_JPGDEC(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &jpgdec_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_JPGDEC(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &jpgdec_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate jpgdec_clks[] = { GATE_JPGDEC(CLK_JPGDEC_JPGDEC1, "jpgdec_jpgdec1", "jpgdec_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2712-mfg.c b/drivers/clk/mediatek/clk-mt2712-mfg.c index 42f8cf3ecf4c..8949315c2dd2 100644 --- a/drivers/clk/mediatek/clk-mt2712-mfg.c +++ b/drivers/clk/mediatek/clk-mt2712-mfg.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs mfg_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_MFG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mfg_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MFG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mfg_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mfg_clks[] = { GATE_MFG(CLK_MFG_BG3D, "mfg_bg3d", "mfg_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index 615f6b0fe96e..850cef9f2009 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -30,32 +30,14 @@ static const struct mtk_gate_regs mm2_cg_regs = { .sta_ofs = 0x220, }; -#define GATE_MM0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_MM1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_MM2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { /* MM0 */ diff --git a/drivers/clk/mediatek/clk-mt2712-vdec.c b/drivers/clk/mediatek/clk-mt2712-vdec.c index 6296ed5c5b55..572290dd43c8 100644 --- a/drivers/clk/mediatek/clk-mt2712-vdec.c +++ b/drivers/clk/mediatek/clk-mt2712-vdec.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs vdec1_cg_regs = { .sta_ofs = 0x8, }; -#define GATE_VDEC0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_VDEC1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate vdec_clks[] = { /* VDEC0 */ diff --git a/drivers/clk/mediatek/clk-mt2712-venc.c b/drivers/clk/mediatek/clk-mt2712-venc.c index b9bfc35de629..9588eb03016e 100644 --- a/drivers/clk/mediatek/clk-mt2712-venc.c +++ b/drivers/clk/mediatek/clk-mt2712-venc.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs venc_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_VENC(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &venc_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VENC(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &venc_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate venc_clks[] = { GATE_VENC(CLK_VENC_SMI_COMMON_CON, "venc_smi", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index 937c370d6765..d0e6a4fbfa99 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -814,23 +814,11 @@ static const struct mtk_gate_regs top1_cg_regs = { .sta_ofs = 0x424, }; -#define GATE_TOP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } - -#define GATE_TOP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) + +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate top_clks[] = { /* TOP0 */ @@ -854,14 +842,8 @@ static const struct mtk_gate_regs infra_cg_regs = { .sta_ofs = 0x48, }; -#define GATE_INFRA(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate infra_clks[] = { GATE_INFRA(CLK_INFRA_DBGCLK, "infra_dbgclk", "axi_sel", 0), @@ -891,32 +873,14 @@ static const struct mtk_gate_regs peri2_cg_regs = { .sta_ofs = 0x42c, }; -#define GATE_PERI0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } - -#define GATE_PERI1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } - -#define GATE_PERI2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_PERI0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_PERI1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_PERI2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri2_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate peri_clks[] = { /* PERI0 */ diff --git a/drivers/clk/mediatek/clk-mt6765-audio.c b/drivers/clk/mediatek/clk-mt6765-audio.c index 0aa6c0d352ca..5682e0302eee 100644 --- a/drivers/clk/mediatek/clk-mt6765-audio.c +++ b/drivers/clk/mediatek/clk-mt6765-audio.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs audio1_cg_regs = { .sta_ofs = 0x4, }; -#define GATE_AUDIO0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate audio_clks[] = { /* AUDIO0 */ diff --git a/drivers/clk/mediatek/clk-mt6765-cam.c b/drivers/clk/mediatek/clk-mt6765-cam.c index 25f2bef38126..6e7d192c19cb 100644 --- a/drivers/clk/mediatek/clk-mt6765-cam.c +++ b/drivers/clk/mediatek/clk-mt6765-cam.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs cam_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_CAM(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &cam_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_CAM(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &cam_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate cam_clks[] = { GATE_CAM(CLK_CAM_LARB3, "cam_larb3", "mm_ck", 0), diff --git a/drivers/clk/mediatek/clk-mt6765-img.c b/drivers/clk/mediatek/clk-mt6765-img.c index a62303ef4f41..cfbc907988af 100644 --- a/drivers/clk/mediatek/clk-mt6765-img.c +++ b/drivers/clk/mediatek/clk-mt6765-img.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs img_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_IMG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &img_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IMG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_LARB2, "img_larb2", "mm_ck", 0), diff --git a/drivers/clk/mediatek/clk-mt6765-mipi0a.c b/drivers/clk/mediatek/clk-mt6765-mipi0a.c index 25c829fc3866..f2b9dc808480 100644 --- a/drivers/clk/mediatek/clk-mt6765-mipi0a.c +++ b/drivers/clk/mediatek/clk-mt6765-mipi0a.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs mipi0a_cg_regs = { .sta_ofs = 0x80, }; -#define GATE_MIPI0A(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mipi0a_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_MIPI0A(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mipi0a_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate mipi0a_clks[] = { GATE_MIPI0A(CLK_MIPI0A_CSR_CSI_EN_0A, diff --git a/drivers/clk/mediatek/clk-mt6765-mm.c b/drivers/clk/mediatek/clk-mt6765-mm.c index bda774668a36..a4570c9dbefa 100644 --- a/drivers/clk/mediatek/clk-mt6765-mm.c +++ b/drivers/clk/mediatek/clk-mt6765-mm.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs mm_cg_regs = { .sta_ofs = 0x100, }; -#define GATE_MM(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { /* MM */ diff --git a/drivers/clk/mediatek/clk-mt6765-vcodec.c b/drivers/clk/mediatek/clk-mt6765-vcodec.c index 2bc1fbde87da..75d72b9b4032 100644 --- a/drivers/clk/mediatek/clk-mt6765-vcodec.c +++ b/drivers/clk/mediatek/clk-mt6765-vcodec.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs venc_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_VENC(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &venc_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VENC(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &venc_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate venc_clks[] = { GATE_VENC(CLK_VENC_SET0_LARB, "venc_set0_larb", "mm_ck", 0), diff --git a/drivers/clk/mediatek/clk-mt6765.c b/drivers/clk/mediatek/clk-mt6765.c index 6f5c92a7f620..0c20ce678350 100644 --- a/drivers/clk/mediatek/clk-mt6765.c +++ b/drivers/clk/mediatek/clk-mt6765.c @@ -483,32 +483,14 @@ static const struct mtk_gate_regs top2_cg_regs = { .sta_ofs = 0x320, }; -#define GATE_TOP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_TOP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) -#define GATE_TOP2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate top_clks[] = { /* TOP0 */ @@ -559,41 +541,17 @@ static const struct mtk_gate_regs ifr5_cg_regs = { .sta_ofs = 0xc8, }; -#define GATE_IFR2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ifr2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_IFR3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ifr3_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_IFR4(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr4_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR4(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ifr4_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_IFR5(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ifr5_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IFR5(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ifr5_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate ifr_clks[] = { /* INFRA_TOPAXI */ @@ -674,14 +632,8 @@ static const struct mtk_gate_regs apmixed_cg_regs = { .sta_ofs = 0x14, }; -#define GATE_APMIXED(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &apmixed_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate apmixed_clks[] = { /* AUDIO0 */ diff --git a/drivers/clk/mediatek/clk-mt6797-img.c b/drivers/clk/mediatek/clk-mt6797-img.c index 7c6a53fbb8be..06441393478f 100644 --- a/drivers/clk/mediatek/clk-mt6797-img.c +++ b/drivers/clk/mediatek/clk-mt6797-img.c @@ -16,14 +16,8 @@ static const struct mtk_gate_regs img_cg_regs = { .sta_ofs = 0x0000, }; -#define GATE_IMG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &img_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IMG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_FDVT, "img_fdvt", "mm_sel", 11), diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index 706c9775646d..e7a5a43f91f1 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -23,23 +23,11 @@ static const struct mtk_gate_regs mm1_cg_regs = { .sta_ofs = 0x0110, }; -#define GATE_MM0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ -} +#define GATE_MM0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_MM1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ -} +#define GATE_MM1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { GATE_MM0(CLK_MM_SMI_COMMON, "mm_smi_common", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt6797-vdec.c b/drivers/clk/mediatek/clk-mt6797-vdec.c index 6120fccc859f..8622ddd87a5b 100644 --- a/drivers/clk/mediatek/clk-mt6797-vdec.c +++ b/drivers/clk/mediatek/clk-mt6797-vdec.c @@ -24,23 +24,11 @@ static const struct mtk_gate_regs vdec1_cg_regs = { .sta_ofs = 0x0008, }; -#define GATE_VDEC0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ -} +#define GATE_VDEC0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_VDEC1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ -} +#define GATE_VDEC1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate vdec_clks[] = { GATE_VDEC0(CLK_VDEC_CKEN_ENG, "vdec_cken_eng", "vdec_sel", 8), diff --git a/drivers/clk/mediatek/clk-mt6797-venc.c b/drivers/clk/mediatek/clk-mt6797-venc.c index 834d3834d2bb..928d611a476e 100644 --- a/drivers/clk/mediatek/clk-mt6797-venc.c +++ b/drivers/clk/mediatek/clk-mt6797-venc.c @@ -18,14 +18,8 @@ static const struct mtk_gate_regs venc_cg_regs = { .sta_ofs = 0x0000, }; -#define GATE_VENC(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &venc_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VENC(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &venc_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate venc_clks[] = { GATE_VENC(CLK_VENC_0, "venc_0", "mm_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt6797.c b/drivers/clk/mediatek/clk-mt6797.c index 105a512857b3..17b23ee4faee 100644 --- a/drivers/clk/mediatek/clk-mt6797.c +++ b/drivers/clk/mediatek/clk-mt6797.c @@ -421,40 +421,22 @@ static const struct mtk_gate_regs infra2_cg_regs = { .sta_ofs = 0x00b0, }; -#define GATE_ICG0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ -} +#define GATE_ICG0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_ICG1(_id, _name, _parent, _shift) \ - GATE_ICG1_FLAGS(_id, _name, _parent, _shift, 0) +#define GATE_ICG1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_ICG1_FLAGS(_id, _name, _parent, _shift, _flags) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - .flags = _flags, \ -} +#define GATE_ICG1_FLAGS(_id, _name, _parent, _shift, _flags) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra1_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flags) -#define GATE_ICG2(_id, _name, _parent, _shift) \ - GATE_ICG2_FLAGS(_id, _name, _parent, _shift, 0) +#define GATE_ICG2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_ICG2_FLAGS(_id, _name, _parent, _shift, _flags) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - .flags = _flags, \ -} +#define GATE_ICG2_FLAGS(_id, _name, _parent, _shift, _flags) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra2_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flags) /* * Clock gates dramc and dramc_b are needed by the DRAM controller. diff --git a/drivers/clk/mediatek/clk-mt7622-aud.c b/drivers/clk/mediatek/clk-mt7622-aud.c index b8aabfeb1cba..27c543759f2a 100644 --- a/drivers/clk/mediatek/clk-mt7622-aud.c +++ b/drivers/clk/mediatek/clk-mt7622-aud.c @@ -16,41 +16,17 @@ #include -#define GATE_AUDIO0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio2_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_AUDIO3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &audio3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUDIO3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &audio3_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate_regs audio0_cg_regs = { .set_ofs = 0x0, diff --git a/drivers/clk/mediatek/clk-mt7622-eth.c b/drivers/clk/mediatek/clk-mt7622-eth.c index aee583fa77d0..66b163cc1633 100644 --- a/drivers/clk/mediatek/clk-mt7622-eth.c +++ b/drivers/clk/mediatek/clk-mt7622-eth.c @@ -16,14 +16,8 @@ #include -#define GATE_ETH(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = ð_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_ETH(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, ð_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate_regs eth_cg_regs = { .set_ofs = 0x30, @@ -45,14 +39,8 @@ static const struct mtk_gate_regs sgmii_cg_regs = { .sta_ofs = 0xE4, }; -#define GATE_SGMII(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &sgmii_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_SGMII(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &sgmii_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate sgmii_clks[] = { GATE_SGMII(CLK_SGMII_TX250M_EN, "sgmii_tx250m_en", diff --git a/drivers/clk/mediatek/clk-mt7622-hif.c b/drivers/clk/mediatek/clk-mt7622-hif.c index ab5cad0c2b1c..bcd1dfc6e8e0 100644 --- a/drivers/clk/mediatek/clk-mt7622-hif.c +++ b/drivers/clk/mediatek/clk-mt7622-hif.c @@ -16,23 +16,11 @@ #include -#define GATE_PCIE(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &pcie_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } - -#define GATE_SSUSB(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ssusb_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_PCIE(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &pcie_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_SSUSB(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ssusb_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate_regs pcie_cg_regs = { .set_ofs = 0x30, diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index 5a82c2270bfb..41af8d420bbf 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -50,59 +50,24 @@ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ NULL, "clkxtal") -#define GATE_APMIXED(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &apmixed_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, \ + &mtk_clk_gate_ops_no_setclr_inv) -#define GATE_INFRA(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_TOP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -#define GATE_PERI0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_PERI1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static DEFINE_SPINLOCK(mt7622_clk_lock); diff --git a/drivers/clk/mediatek/clk-mt7629-eth.c b/drivers/clk/mediatek/clk-mt7629-eth.c index a4ae7d6c7a71..719a47fef798 100644 --- a/drivers/clk/mediatek/clk-mt7629-eth.c +++ b/drivers/clk/mediatek/clk-mt7629-eth.c @@ -16,14 +16,8 @@ #include -#define GATE_ETH(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = ð_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_ETH(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, ð_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate_regs eth_cg_regs = { .set_ofs = 0x30, @@ -45,14 +39,8 @@ static const struct mtk_gate_regs sgmii_cg_regs = { .sta_ofs = 0xE4, }; -#define GATE_SGMII(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &sgmii_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_SGMII(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &sgmii_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate sgmii_clks[2][4] = { { diff --git a/drivers/clk/mediatek/clk-mt7629-hif.c b/drivers/clk/mediatek/clk-mt7629-hif.c index c3eb09ea6036..78d85542e4f1 100644 --- a/drivers/clk/mediatek/clk-mt7629-hif.c +++ b/drivers/clk/mediatek/clk-mt7629-hif.c @@ -16,23 +16,11 @@ #include -#define GATE_PCIE(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &pcie_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } - -#define GATE_SSUSB(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &ssusb_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_PCIE(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &pcie_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_SSUSB(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ssusb_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate_regs pcie_cg_regs = { .set_ofs = 0x30, diff --git a/drivers/clk/mediatek/clk-mt7629.c b/drivers/clk/mediatek/clk-mt7629.c index cf062d4a7ecc..09c85fda43d8 100644 --- a/drivers/clk/mediatek/clk-mt7629.c +++ b/drivers/clk/mediatek/clk-mt7629.c @@ -50,41 +50,17 @@ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ NULL, "clk20m") -#define GATE_APMIXED(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &apmixed_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) -#define GATE_INFRA(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_PERI0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_PERI1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static DEFINE_SPINLOCK(mt7629_clk_lock); diff --git a/drivers/clk/mediatek/clk-mt7986-eth.c b/drivers/clk/mediatek/clk-mt7986-eth.c index 703872239ecc..e04bc6845ea6 100644 --- a/drivers/clk/mediatek/clk-mt7986-eth.c +++ b/drivers/clk/mediatek/clk-mt7986-eth.c @@ -22,12 +22,8 @@ static const struct mtk_gate_regs sgmii0_cg_regs = { .sta_ofs = 0xe4, }; -#define GATE_SGMII0(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = &sgmii0_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_SGMII0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &sgmii0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate sgmii0_clks[] __initconst = { GATE_SGMII0(CLK_SGMII0_TX250M_EN, "sgmii0_tx250m_en", "top_xtal", 2), @@ -42,12 +38,8 @@ static const struct mtk_gate_regs sgmii1_cg_regs = { .sta_ofs = 0xe4, }; -#define GATE_SGMII1(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = &sgmii1_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_SGMII1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &sgmii1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate sgmii1_clks[] __initconst = { GATE_SGMII1(CLK_SGMII1_TX250M_EN, "sgmii1_tx250m_en", "top_xtal", 2), @@ -62,12 +54,8 @@ static const struct mtk_gate_regs eth_cg_regs = { .sta_ofs = 0x30, }; -#define GATE_ETH(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = ð_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr_inv, \ - } +#define GATE_ETH(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, ð_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) static const struct mtk_gate eth_clks[] __initconst = { GATE_ETH(CLK_ETH_FE_EN, "eth_fe_en", "netsys_2x_sel", 6), diff --git a/drivers/clk/mediatek/clk-mt7986-infracfg.c b/drivers/clk/mediatek/clk-mt7986-infracfg.c index e80c92167c8f..0a4bf87ee160 100644 --- a/drivers/clk/mediatek/clk-mt7986-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7986-infracfg.c @@ -87,26 +87,14 @@ static const struct mtk_gate_regs infra2_cg_regs = { .sta_ofs = 0x68, }; -#define GATE_INFRA0(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = &infra0_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_INFRA1(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = &infra1_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_INFRA2(_id, _name, _parent, _shift) \ - { \ - .id = _id, .name = _name, .parent_name = _parent, \ - .regs = &infra2_cg_regs, .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_INFRA2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate infra_clks[] = { /* INFRA0 */ diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 2b9c925c2a2b..97a115d2c3da 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -401,14 +401,8 @@ static const struct mtk_gate_regs infra_cg_regs = { .sta_ofs = 0x0048, }; -#define GATE_ICG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &infra_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_ICG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate infra_clks[] __initconst = { GATE_ICG(CLK_INFRA_PMIC_WRAP, "pmic_wrap_ck", "axi_sel", 23), @@ -438,23 +432,11 @@ static const struct mtk_gate_regs peri1_cg_regs = { .sta_ofs = 0x001c, }; -#define GATE_PERI0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_PERI1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &peri1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_PERI1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate peri_gates[] __initconst = { /* PERI0 */ diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index eec9de190cb6..8869c53da79c 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -23,14 +23,9 @@ static const struct mtk_gate_regs aud_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_AUD(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &aud_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUD(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &aud_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) + static const struct mtk_gate aud_clks[] = { GATE_AUD(CLK_AUD_AFE, "aud_afe", "clk26m_ck", 2), diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index 5cd51d894d32..6a068f2a9dce 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -23,14 +23,8 @@ static const struct mtk_gate_regs img_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_IMG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &img_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_IMG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &img_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate img_clks[] = { GATE_IMG(CLK_IMG_LARB1_SMI, "img_larb1_smi", "smi_mm", 0), diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 2cf88d5d245d..7fcb944134b6 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -23,14 +23,8 @@ static const struct mtk_gate_regs mfg_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_MFG(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mfg_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MFG(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mfg_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mfg_clks[] = { GATE_MFG(CLK_MFG_BAXI, "mfg_baxi", "ahb_infra_sel", 0), diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index 78c023b0565a..5a5192d0dc45 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -29,23 +29,11 @@ static const struct mtk_gate_regs mm1_cg_regs = { .sta_ofs = 0x110, }; -#define GATE_MM0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_MM1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mm_clks[] = { /* MM0 */ diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index c3e2253a57d7..b3eccc2eca58 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -29,23 +29,11 @@ static const struct mtk_gate_regs vdec1_cg_regs = { .sta_ofs = 0x8, }; -#define GATE_VDEC0_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC0_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_VDEC1_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &vdec1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_VDEC1_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) static const struct mtk_gate vdec_clks[] = { /* VDEC0 */ diff --git a/drivers/clk/mediatek/clk-mt8173-mm.c b/drivers/clk/mediatek/clk-mt8173-mm.c index ffec2d917661..435cfae25492 100644 --- a/drivers/clk/mediatek/clk-mt8173-mm.c +++ b/drivers/clk/mediatek/clk-mt8173-mm.c @@ -25,23 +25,11 @@ static const struct mtk_gate_regs mm1_cg_regs = { .sta_ofs = 0x0110, }; -#define GATE_MM0(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm0_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_MM1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &mm1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_MM1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &mm1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate mt8173_mm_clks[] = { GATE_DUMMY(CLK_DUMMY, "mm_dummy"), diff --git a/drivers/clk/mediatek/clk-mt8516-aud.c b/drivers/clk/mediatek/clk-mt8516-aud.c index 00f356fe7c7a..a6ae8003b9ff 100644 --- a/drivers/clk/mediatek/clk-mt8516-aud.c +++ b/drivers/clk/mediatek/clk-mt8516-aud.c @@ -22,14 +22,8 @@ static const struct mtk_gate_regs aud_cg_regs = { .sta_ofs = 0x0, }; -#define GATE_AUD(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &aud_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_AUD(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &aud_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) static const struct mtk_gate aud_clks[] __initconst = { GATE_AUD(CLK_AUD_AFE, "aud_afe", "clk26m_ck", 2), diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index 2c0cae7b3bcf..6983d3a48dc9 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -525,59 +525,23 @@ static const struct mtk_gate_regs top5_cg_regs = { .sta_ofs = 0x44, }; -#define GATE_TOP1(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top1_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP2(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP2_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top2_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_TOP2_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top2_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_TOP3(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top3_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr, \ - } +#define GATE_TOP3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top3_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -#define GATE_TOP4_I(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top4_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_setclr_inv, \ - } +#define GATE_TOP4_I(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top4_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) -#define GATE_TOP5(_id, _name, _parent, _shift) { \ - .id = _id, \ - .name = _name, \ - .parent_name = _parent, \ - .regs = &top5_cg_regs, \ - .shift = _shift, \ - .ops = &mtk_clk_gate_ops_no_setclr, \ - } +#define GATE_TOP5(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top5_cg_regs, _shift, &mtk_clk_gate_ops_setclr) static const struct mtk_gate top_clks[] __initconst = { /* TOP1 */ -- GitLab From fa8c0d01df62130ff596d560380a6f844f62639e Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:12 +0100 Subject: [PATCH 0366/5631] clk: mediatek: mt7622: Properly use CLK_IS_CRITICAL flag Instead of calling clk_prepare_enable() for clocks that shall stay enabled, use the CLK_IS_CRITICAL flag, which purpose is exactly that. Fixes: 2fc0a509e4ee ("clk: mediatek: add clock support for MT7622 SoC") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-24-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7622.c | 35 +++++++++++++------------------ 1 file changed, 15 insertions(+), 20 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index 41af8d420bbf..1c0049fbeb69 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -50,9 +50,9 @@ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ NULL, "clkxtal") -#define GATE_APMIXED(_id, _name, _parent, _shift) \ - GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, \ - &mtk_clk_gate_ops_no_setclr_inv) +#define GATE_APMIXED_AO(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &apmixed_cg_regs, _shift, \ + &mtk_clk_gate_ops_no_setclr_inv, CLK_IS_CRITICAL) #define GATE_INFRA(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) @@ -66,6 +66,10 @@ #define GATE_PERI0(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &peri0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) +#define GATE_PERI0_AO(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &peri0_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, CLK_IS_CRITICAL) + #define GATE_PERI1(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) @@ -315,7 +319,7 @@ static const struct mtk_pll_data plls[] = { }; static const struct mtk_gate apmixed_clks[] = { - GATE_APMIXED(CLK_APMIXED_MAIN_CORE_EN, "main_core_en", "mainpll", 5), + GATE_APMIXED_AO(CLK_APMIXED_MAIN_CORE_EN, "main_core_en", "mainpll", 5), }; static const struct mtk_gate infra_clks[] = { @@ -450,7 +454,7 @@ static const struct mtk_gate peri_clks[] = { GATE_PERI0(CLK_PERI_AP_DMA_PD, "peri_ap_dma_pd", "axi_sel", 12), GATE_PERI0(CLK_PERI_MSDC30_0_PD, "peri_msdc30_0", "msdc30_0_sel", 13), GATE_PERI0(CLK_PERI_MSDC30_1_PD, "peri_msdc30_1", "msdc30_1_sel", 14), - GATE_PERI0(CLK_PERI_UART0_PD, "peri_uart0_pd", "axi_sel", 17), + GATE_PERI0_AO(CLK_PERI_UART0_PD, "peri_uart0_pd", "axi_sel", 17), GATE_PERI0(CLK_PERI_UART1_PD, "peri_uart1_pd", "axi_sel", 18), GATE_PERI0(CLK_PERI_UART2_PD, "peri_uart2_pd", "axi_sel", 19), GATE_PERI0(CLK_PERI_UART3_PD, "peri_uart3_pd", "axi_sel", 20), @@ -478,12 +482,12 @@ static struct mtk_composite infra_muxes[] = { static struct mtk_composite top_muxes[] = { /* CLK_CFG_0 */ - MUX_GATE(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, - 0x040, 0, 3, 7), - MUX_GATE(CLK_TOP_MEM_SEL, "mem_sel", mem_parents, - 0x040, 8, 1, 15), - MUX_GATE(CLK_TOP_DDRPHYCFG_SEL, "ddrphycfg_sel", ddrphycfg_parents, - 0x040, 16, 1, 23), + MUX_GATE_FLAGS(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, + 0x040, 0, 3, 7, CLK_IS_CRITICAL), + MUX_GATE_FLAGS(CLK_TOP_MEM_SEL, "mem_sel", mem_parents, + 0x040, 8, 1, 15, CLK_IS_CRITICAL), + MUX_GATE_FLAGS(CLK_TOP_DDRPHYCFG_SEL, "ddrphycfg_sel", ddrphycfg_parents, + 0x040, 16, 1, 23, CLK_IS_CRITICAL), MUX_GATE(CLK_TOP_ETH_SEL, "eth_sel", eth_parents, 0x040, 24, 3, 31), @@ -621,10 +625,6 @@ static int mtk_topckgen_init(struct platform_device *pdev) mtk_clk_register_gates(&pdev->dev, node, top_clks, ARRAY_SIZE(top_clks), clk_data); - clk_prepare_enable(clk_data->hws[CLK_TOP_AXI_SEL]->clk); - clk_prepare_enable(clk_data->hws[CLK_TOP_MEM_SEL]->clk); - clk_prepare_enable(clk_data->hws[CLK_TOP_DDRPHYCFG_SEL]->clk); - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -667,9 +667,6 @@ static int mtk_apmixedsys_init(struct platform_device *pdev) mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); - clk_prepare_enable(clk_data->hws[CLK_APMIXED_ARMPLL]->clk); - clk_prepare_enable(clk_data->hws[CLK_APMIXED_MAIN_CORE_EN]->clk); - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } @@ -697,8 +694,6 @@ static int mtk_pericfg_init(struct platform_device *pdev) if (r) return r; - clk_prepare_enable(clk_data->hws[CLK_PERI_UART0_PD]->clk); - mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc[1]); return 0; -- GitLab From 9aed98adf601c02a929822526c8031003ff95a32 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:13 +0100 Subject: [PATCH 0367/5631] clk: mediatek: mt7622: Move apmixedsys clock driver to its own file In preparation for migrating mt7622 clocks to the common simple probe mechanism, move apmixedsys clocks to a different file. While at it, use the builtin_platform_driver() macro for it. During the conversion, error handling was added to the apmixedsys probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-25-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt7622-apmixedsys.c | 137 +++++++++++++++++++ drivers/clk/mediatek/clk-mt7622.c | 87 ------------ 3 files changed, 138 insertions(+), 88 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt7622-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 33f13b8399ce..4619091963a0 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -46,7 +46,7 @@ obj-$(CONFIG_COMMON_CLK_MT2712_MFGCFG) += clk-mt2712-mfg.o obj-$(CONFIG_COMMON_CLK_MT2712_MMSYS) += clk-mt2712-mm.o obj-$(CONFIG_COMMON_CLK_MT2712_VDECSYS) += clk-mt2712-vdec.o obj-$(CONFIG_COMMON_CLK_MT2712_VENCSYS) += clk-mt2712-venc.o -obj-$(CONFIG_COMMON_CLK_MT7622) += clk-mt7622.o +obj-$(CONFIG_COMMON_CLK_MT7622) += clk-mt7622-apmixedsys.o clk-mt7622.o obj-$(CONFIG_COMMON_CLK_MT7622_ETHSYS) += clk-mt7622-eth.o obj-$(CONFIG_COMMON_CLK_MT7622_HIFSYS) += clk-mt7622-hif.o obj-$(CONFIG_COMMON_CLK_MT7622_AUDSYS) += clk-mt7622-aud.o diff --git a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c new file mode 100644 index 000000000000..497fada797b9 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017 MediaTek Inc. + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" +#include "clk-pll.h" + +#define MT7622_PLL_FMAX (2500UL * MHZ) +#define CON0_MT7622_RST_BAR BIT(27) + +#define PLL_xtal(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,\ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift, _div_table, _parent_name) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = CON0_MT7622_RST_BAR, \ + .fmax = MT7622_PLL_FMAX, \ + .pcwbits = _pcwbits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .div_table = _div_table, \ + .parent_name = _parent_name, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift) \ + PLL_xtal(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,\ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ + NULL, "clkxtal") + +static const struct mtk_gate_regs apmixed_cg_regs = { + .set_ofs = 0x8, + .clr_ofs = 0x8, + .sta_ofs = 0x8, +}; + +#define GATE_APMIXED_AO(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &apmixed_cg_regs, _shift, \ + &mtk_clk_gate_ops_no_setclr_inv, CLK_IS_CRITICAL) + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0200, 0x020C, 0, + PLL_AO, 21, 0x0204, 24, 0, 0x0204, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0210, 0x021C, 0, + HAVE_RST_BAR, 21, 0x0214, 24, 0, 0x0214, 0), + PLL(CLK_APMIXED_UNIV2PLL, "univ2pll", 0x0220, 0x022C, 0, + HAVE_RST_BAR, 7, 0x0224, 24, 0, 0x0224, 14), + PLL(CLK_APMIXED_ETH1PLL, "eth1pll", 0x0300, 0x0310, 0, + 0, 21, 0x0300, 1, 0, 0x0304, 0), + PLL(CLK_APMIXED_ETH2PLL, "eth2pll", 0x0314, 0x0320, 0, + 0, 21, 0x0314, 1, 0, 0x0318, 0), + PLL(CLK_APMIXED_AUD1PLL, "aud1pll", 0x0324, 0x0330, 0, + 0, 31, 0x0324, 1, 0, 0x0328, 0), + PLL(CLK_APMIXED_AUD2PLL, "aud2pll", 0x0334, 0x0340, 0, + 0, 31, 0x0334, 1, 0, 0x0338, 0), + PLL(CLK_APMIXED_TRGPLL, "trgpll", 0x0344, 0x0354, 0, + 0, 21, 0x0344, 1, 0, 0x0348, 0), + PLL(CLK_APMIXED_SGMIPLL, "sgmipll", 0x0358, 0x0368, 0, + 0, 21, 0x0358, 1, 0, 0x035C, 0), +}; + +static const struct mtk_gate apmixed_clks[] = { + GATE_APMIXED_AO(CLK_APMIXED_MAIN_CORE_EN, "main_core_en", "mainpll", 5), +}; + +static int clk_mt7622_apmixed_probe(struct platform_device *pdev) +{ + void __iomem *base; + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_devm_alloc_clk_data(dev, CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); + if (ret) + goto unregister_plls; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_gates; + + return 0; + +unregister_gates: + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static const struct of_device_id of_match_clk_mt7622_apmixed[] = { + { .compatible = "mediatek,mt7622-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt7622_apmixed_drv = { + .probe = clk_mt7622_apmixed_probe, + .driver = { + .name = "clk-mt7622-apmixed", + .of_match_table = of_match_clk_mt7622_apmixed, + }, +}; +builtin_platform_driver(clk_mt7622_apmixed_drv) + +MODULE_DESCRIPTION("MediaTek MT7622 apmixedsys clocks driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index 1c0049fbeb69..6cf74c948ac7 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -14,46 +14,10 @@ #include "clk-cpumux.h" #include "clk-gate.h" #include "clk-mtk.h" -#include "clk-pll.h" #include #include /* for consumer */ -#define MT7622_PLL_FMAX (2500UL * MHZ) -#define CON0_MT7622_RST_BAR BIT(27) - -#define PLL_xtal(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,\ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift, _div_table, _parent_name) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = CON0_MT7622_RST_BAR, \ - .fmax = MT7622_PLL_FMAX, \ - .pcwbits = _pcwbits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .div_table = _div_table, \ - .parent_name = _parent_name, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift) \ - PLL_xtal(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits,\ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ - NULL, "clkxtal") - -#define GATE_APMIXED_AO(_id, _name, _parent, _shift) \ - GATE_MTK_FLAGS(_id, _name, _parent, &apmixed_cg_regs, _shift, \ - &mtk_clk_gate_ops_no_setclr_inv, CLK_IS_CRITICAL) - #define GATE_INFRA(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) @@ -261,12 +225,6 @@ static const char * const peribus_ck_parents[] = { "syspll1_d4" }; -static const struct mtk_gate_regs apmixed_cg_regs = { - .set_ofs = 0x8, - .clr_ofs = 0x8, - .sta_ofs = 0x8, -}; - static const struct mtk_gate_regs infra_cg_regs = { .set_ofs = 0x40, .clr_ofs = 0x44, @@ -297,31 +255,6 @@ static const struct mtk_gate_regs peri1_cg_regs = { .sta_ofs = 0x1C, }; -static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0200, 0x020C, 0, - PLL_AO, 21, 0x0204, 24, 0, 0x0204, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0210, 0x021C, 0, - HAVE_RST_BAR, 21, 0x0214, 24, 0, 0x0214, 0), - PLL(CLK_APMIXED_UNIV2PLL, "univ2pll", 0x0220, 0x022C, 0, - HAVE_RST_BAR, 7, 0x0224, 24, 0, 0x0224, 14), - PLL(CLK_APMIXED_ETH1PLL, "eth1pll", 0x0300, 0x0310, 0, - 0, 21, 0x0300, 1, 0, 0x0304, 0), - PLL(CLK_APMIXED_ETH2PLL, "eth2pll", 0x0314, 0x0320, 0, - 0, 21, 0x0314, 1, 0, 0x0318, 0), - PLL(CLK_APMIXED_AUD1PLL, "aud1pll", 0x0324, 0x0330, 0, - 0, 31, 0x0324, 1, 0, 0x0328, 0), - PLL(CLK_APMIXED_AUD2PLL, "aud2pll", 0x0334, 0x0340, 0, - 0, 31, 0x0334, 1, 0, 0x0338, 0), - PLL(CLK_APMIXED_TRGPLL, "trgpll", 0x0344, 0x0354, 0, - 0, 21, 0x0344, 1, 0, 0x0348, 0), - PLL(CLK_APMIXED_SGMIPLL, "sgmipll", 0x0358, 0x0368, 0, - 0, 21, 0x0358, 1, 0, 0x035C, 0), -}; - -static const struct mtk_gate apmixed_clks[] = { - GATE_APMIXED_AO(CLK_APMIXED_MAIN_CORE_EN, "main_core_en", "mainpll", 5), -}; - static const struct mtk_gate infra_clks[] = { GATE_INFRA(CLK_INFRA_DBGCLK_PD, "infra_dbgclk_pd", "axi_sel", 0), GATE_INFRA(CLK_INFRA_TRNG, "trng_ck", "axi_sel", 2), @@ -652,23 +585,6 @@ static int mtk_infrasys_init(struct platform_device *pdev) return 0; } -static int mtk_apmixedsys_init(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - if (!clk_data) - return -ENOMEM; - - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), - clk_data); - - mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, - ARRAY_SIZE(apmixed_clks), clk_data); - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} static int mtk_pericfg_init(struct platform_device *pdev) { @@ -701,9 +617,6 @@ static int mtk_pericfg_init(struct platform_device *pdev) static const struct of_device_id of_match_clk_mt7622[] = { { - .compatible = "mediatek,mt7622-apmixedsys", - .data = mtk_apmixedsys_init, - }, { .compatible = "mediatek,mt7622-infracfg", .data = mtk_infrasys_init, }, { -- GitLab From c50e2ea6507bcf5a4475f821fc03dd1fdcb894a7 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:14 +0100 Subject: [PATCH 0368/5631] clk: mediatek: mt7622-apmixedsys: Add .remove() callback for module build Add a .remove() callback to the apmixedsys driver to allow full module build; while at it, also change the usage of builtin_platform_driver() to module_platform_driver() to actually make use of the new callback. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-26-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7622-apmixedsys.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c index 497fada797b9..a9f3057d7080 100644 --- a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c @@ -119,6 +119,19 @@ static int clk_mt7622_apmixed_probe(struct platform_device *pdev) return ret; } +static int clk_mt7622_apmixed_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_free_clk_data(clk_data); + + return 0; +} + static const struct of_device_id of_match_clk_mt7622_apmixed[] = { { .compatible = "mediatek,mt7622-apmixedsys" }, { /* sentinel */ } @@ -126,12 +139,13 @@ static const struct of_device_id of_match_clk_mt7622_apmixed[] = { static struct platform_driver clk_mt7622_apmixed_drv = { .probe = clk_mt7622_apmixed_probe, + .remove = clk_mt7622_apmixed_remove, .driver = { .name = "clk-mt7622-apmixed", .of_match_table = of_match_clk_mt7622_apmixed, }, }; -builtin_platform_driver(clk_mt7622_apmixed_drv) +module_platform_driver(clk_mt7622_apmixed_drv) MODULE_DESCRIPTION("MediaTek MT7622 apmixedsys clocks driver"); MODULE_LICENSE("GPL"); -- GitLab From 838b86331c5e8f424b5a565e6c9c472b55768319 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:15 +0100 Subject: [PATCH 0369/5631] clk: mediatek: mt7622: Move infracfg to clk-mt7622-infracfg.c The infracfg driver cannot be converted to clk_mtk_simple_probe() as it registers cpumuxes, which is not supported on the common probing mechanism: for this reason, move it to its own file. While at it, also convert it to be a platform driver instead; to do so, also add a .remove() callback for this driver. During the conversion, error handling was added to the infracfg probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-27-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 3 +- drivers/clk/mediatek/clk-mt7622-infracfg.c | 127 +++++++++++++++++++++ drivers/clk/mediatek/clk-mt7622.c | 78 +------------ 3 files changed, 134 insertions(+), 74 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt7622-infracfg.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 4619091963a0..5dc5f9457c44 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -46,7 +46,8 @@ obj-$(CONFIG_COMMON_CLK_MT2712_MFGCFG) += clk-mt2712-mfg.o obj-$(CONFIG_COMMON_CLK_MT2712_MMSYS) += clk-mt2712-mm.o obj-$(CONFIG_COMMON_CLK_MT2712_VDECSYS) += clk-mt2712-vdec.o obj-$(CONFIG_COMMON_CLK_MT2712_VENCSYS) += clk-mt2712-venc.o -obj-$(CONFIG_COMMON_CLK_MT7622) += clk-mt7622-apmixedsys.o clk-mt7622.o +obj-$(CONFIG_COMMON_CLK_MT7622) += clk-mt7622-apmixedsys.o clk-mt7622.o \ + clk-mt7622-infracfg.o obj-$(CONFIG_COMMON_CLK_MT7622_ETHSYS) += clk-mt7622-eth.o obj-$(CONFIG_COMMON_CLK_MT7622_HIFSYS) += clk-mt7622-hif.o obj-$(CONFIG_COMMON_CLK_MT7622_AUDSYS) += clk-mt7622-aud.o diff --git a/drivers/clk/mediatek/clk-mt7622-infracfg.c b/drivers/clk/mediatek/clk-mt7622-infracfg.c new file mode 100644 index 000000000000..09d8ac4d483a --- /dev/null +++ b/drivers/clk/mediatek/clk-mt7622-infracfg.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2017 MediaTek Inc. + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include + +#include "clk-cpumux.h" +#include "clk-gate.h" +#include "clk-mtk.h" +#include "reset.h" + +#define GATE_INFRA(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate_regs infra_cg_regs = { + .set_ofs = 0x40, + .clr_ofs = 0x44, + .sta_ofs = 0x48, +}; + +static const char * const infra_mux1_parents[] = { + "clkxtal", + "armpll", + "main_core_en", + "armpll" +}; + +static const struct mtk_composite cpu_muxes[] = { + MUX(CLK_INFRA_MUX1_SEL, "infra_mux1_sel", infra_mux1_parents, 0x000, 2, 2), +}; + +static const struct mtk_gate infra_clks[] = { + GATE_INFRA(CLK_INFRA_DBGCLK_PD, "infra_dbgclk_pd", "axi_sel", 0), + GATE_INFRA(CLK_INFRA_TRNG, "trng_ck", "axi_sel", 2), + GATE_INFRA(CLK_INFRA_AUDIO_PD, "infra_audio_pd", "aud_intbus_sel", 5), + GATE_INFRA(CLK_INFRA_IRRX_PD, "infra_irrx_pd", "irrx_sel", 16), + GATE_INFRA(CLK_INFRA_APXGPT_PD, "infra_apxgpt_pd", "f10m_ref_sel", 18), + GATE_INFRA(CLK_INFRA_PMIC_PD, "infra_pmic_pd", "pmicspi_sel", 22), +}; + +static u16 infrasys_rst_ofs[] = { 0x30 }; + +static const struct mtk_clk_rst_desc clk_rst_desc = { + .version = MTK_RST_SIMPLE, + .rst_bank_ofs = infrasys_rst_ofs, + .rst_bank_nr = ARRAY_SIZE(infrasys_rst_ofs), +}; + +static const struct of_device_id of_match_clk_mt7622_infracfg[] = { + { .compatible = "mediatek,mt7622-infracfg" }, + { /* sentinel */ } +}; + +static int clk_mt7622_infracfg_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + void __iomem *base; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); + if (!clk_data) + return -ENOMEM; + + ret = mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc); + if (ret) + goto free_clk_data; + + ret = mtk_clk_register_gates(&pdev->dev, node, infra_clks, + ARRAY_SIZE(infra_clks), clk_data); + if (ret) + goto free_clk_data; + + ret = mtk_clk_register_cpumuxes(&pdev->dev, node, cpu_muxes, + ARRAY_SIZE(cpu_muxes), clk_data); + if (ret) + goto unregister_gates; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_cpumuxes; + + return 0; + +unregister_cpumuxes: + mtk_clk_unregister_cpumuxes(cpu_muxes, ARRAY_SIZE(cpu_muxes), clk_data); +unregister_gates: + mtk_clk_unregister_gates(infra_clks, ARRAY_SIZE(infra_clks), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); + return ret; +} + +static int clk_mt7622_infracfg_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_cpumuxes(cpu_muxes, ARRAY_SIZE(cpu_muxes), clk_data); + mtk_clk_unregister_gates(infra_clks, ARRAY_SIZE(infra_clks), clk_data); + mtk_free_clk_data(clk_data); + + return 0; +} + +static struct platform_driver clk_mt7622_infracfg_drv = { + .driver = { + .name = "clk-mt7622-infracfg", + .of_match_table = of_match_clk_mt7622_infracfg, + }, + .probe = clk_mt7622_infracfg_probe, + .remove = clk_mt7622_infracfg_remove, +}; +module_platform_driver(clk_mt7622_infracfg_drv); + +MODULE_DESCRIPTION("MediaTek MT7622 infracfg clocks driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index 6cf74c948ac7..fb813f8d3a7d 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -18,9 +18,6 @@ #include #include /* for consumer */ -#define GATE_INFRA(_id, _name, _parent, _shift) \ - GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) - #define GATE_TOP0(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) @@ -39,13 +36,6 @@ static DEFINE_SPINLOCK(mt7622_clk_lock); -static const char * const infra_mux1_parents[] = { - "clkxtal", - "armpll", - "main_core_en", - "armpll" -}; - static const char * const axi_parents[] = { "clkxtal", "syspll1_d2", @@ -225,12 +215,6 @@ static const char * const peribus_ck_parents[] = { "syspll1_d4" }; -static const struct mtk_gate_regs infra_cg_regs = { - .set_ofs = 0x40, - .clr_ofs = 0x44, - .sta_ofs = 0x48, -}; - static const struct mtk_gate_regs top0_cg_regs = { .set_ofs = 0x120, .clr_ofs = 0x120, @@ -255,15 +239,6 @@ static const struct mtk_gate_regs peri1_cg_regs = { .sta_ofs = 0x1C, }; -static const struct mtk_gate infra_clks[] = { - GATE_INFRA(CLK_INFRA_DBGCLK_PD, "infra_dbgclk_pd", "axi_sel", 0), - GATE_INFRA(CLK_INFRA_TRNG, "trng_ck", "axi_sel", 2), - GATE_INFRA(CLK_INFRA_AUDIO_PD, "infra_audio_pd", "aud_intbus_sel", 5), - GATE_INFRA(CLK_INFRA_IRRX_PD, "infra_irrx_pd", "irrx_sel", 16), - GATE_INFRA(CLK_INFRA_APXGPT_PD, "infra_apxgpt_pd", "f10m_ref_sel", 18), - GATE_INFRA(CLK_INFRA_PMIC_PD, "infra_pmic_pd", "pmicspi_sel", 22), -}; - static const struct mtk_fixed_clk top_fixed_clks[] = { FIXED_CLK(CLK_TOP_TO_U2_PHY, "to_u2_phy", "clkxtal", 31250000), @@ -408,11 +383,6 @@ static const struct mtk_gate peri_clks[] = { GATE_PERI1(CLK_PERI_IRTX_PD, "peri_irtx_pd", "irtx_sel", 2), }; -static struct mtk_composite infra_muxes[] = { - MUX(CLK_INFRA_MUX1_SEL, "infra_mux1_sel", infra_mux1_parents, - 0x000, 2, 2), -}; - static struct mtk_composite top_muxes[] = { /* CLK_CFG_0 */ MUX_GATE_FLAGS(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, @@ -512,22 +482,12 @@ static struct mtk_composite peri_muxes[] = { MUX(CLK_PERIBUS_SEL, "peribus_ck_sel", peribus_ck_parents, 0x05C, 0, 1), }; -static u16 infrasys_rst_ofs[] = { 0x30, }; static u16 pericfg_rst_ofs[] = { 0x0, 0x4, }; -static const struct mtk_clk_rst_desc clk_rst_desc[] = { - /* infrasys */ - { - .version = MTK_RST_SIMPLE, - .rst_bank_ofs = infrasys_rst_ofs, - .rst_bank_nr = ARRAY_SIZE(infrasys_rst_ofs), - }, - /* pericfg */ - { - .version = MTK_RST_SIMPLE, - .rst_bank_ofs = pericfg_rst_ofs, - .rst_bank_nr = ARRAY_SIZE(pericfg_rst_ofs), - }, +static const struct mtk_clk_rst_desc clk_rst_desc = { + .version = MTK_RST_SIMPLE, + .rst_bank_ofs = pericfg_rst_ofs, + .rst_bank_nr = ARRAY_SIZE(pericfg_rst_ofs), }; static int mtk_topckgen_init(struct platform_device *pdev) @@ -561,31 +521,6 @@ static int mtk_topckgen_init(struct platform_device *pdev) return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); } -static int mtk_infrasys_init(struct platform_device *pdev) -{ - struct device_node *node = pdev->dev.of_node; - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - - mtk_clk_register_gates(&pdev->dev, node, infra_clks, - ARRAY_SIZE(infra_clks), clk_data); - - mtk_clk_register_cpumuxes(&pdev->dev, node, infra_muxes, - ARRAY_SIZE(infra_muxes), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, - clk_data); - if (r) - return r; - - mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc[0]); - - return 0; -} - - static int mtk_pericfg_init(struct platform_device *pdev) { struct clk_hw_onecell_data *clk_data; @@ -610,16 +545,13 @@ static int mtk_pericfg_init(struct platform_device *pdev) if (r) return r; - mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc[1]); + mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc); return 0; } static const struct of_device_id of_match_clk_mt7622[] = { { - .compatible = "mediatek,mt7622-infracfg", - .data = mtk_infrasys_init, - }, { .compatible = "mediatek,mt7622-topckgen", .data = mtk_topckgen_init, }, { -- GitLab From 054a47fc47bd1c746ba122e2afb353f9620015b8 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:16 +0100 Subject: [PATCH 0370/5631] clk: mediatek: mt7622: Convert to platform driver and simple probe Convert the MT7622 topckgen and pericfg clock drivers to platform drivers and use the simple probe mechanism. This also allows to build these clocks as modules. Thanks to the conversion, more error handling was added to the clocks registration. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-28-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7622.c | 125 ++++++++---------------------- 1 file changed, 31 insertions(+), 94 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index fb813f8d3a7d..7a002b73fcaa 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -490,107 +490,44 @@ static const struct mtk_clk_rst_desc clk_rst_desc = { .rst_bank_nr = ARRAY_SIZE(pericfg_rst_ofs), }; -static int mtk_topckgen_init(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - void __iomem *base; - struct device_node *node = pdev->dev.of_node; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - - mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), - clk_data); - - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), - clk_data); - - mtk_clk_register_composites(&pdev->dev, top_muxes, - ARRAY_SIZE(top_muxes), base, - &mt7622_clk_lock, clk_data); - - mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), - base, &mt7622_clk_lock, clk_data); - - mtk_clk_register_gates(&pdev->dev, node, top_clks, - ARRAY_SIZE(top_clks), clk_data); - - return of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); -} - -static int mtk_pericfg_init(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - void __iomem *base; - int r; - struct device_node *node = pdev->dev.of_node; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) - return PTR_ERR(base); - - clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); - - mtk_clk_register_gates(&pdev->dev, node, peri_clks, - ARRAY_SIZE(peri_clks), clk_data); - - mtk_clk_register_composites(&pdev->dev, peri_muxes, - ARRAY_SIZE(peri_muxes), base, - &mt7622_clk_lock, clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - return r; - - mtk_register_reset_controller_with_dev(&pdev->dev, &clk_rst_desc); - - return 0; -} +static const struct mtk_clk_desc topck_desc = { + .clks = top_clks, + .num_clks = ARRAY_SIZE(top_clks), + .fixed_clks = top_fixed_clks, + .num_fixed_clks = ARRAY_SIZE(top_fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .composite_clks = top_muxes, + .num_composite_clks = ARRAY_SIZE(top_muxes), + .divider_clks = top_adj_divs, + .num_divider_clks = ARRAY_SIZE(top_adj_divs), + .clk_lock = &mt7622_clk_lock, +}; + +static const struct mtk_clk_desc peri_desc = { + .clks = peri_clks, + .num_clks = ARRAY_SIZE(peri_clks), + .composite_clks = peri_muxes, + .num_composite_clks = ARRAY_SIZE(peri_muxes), + .rst_desc = &clk_rst_desc, + .clk_lock = &mt7622_clk_lock, +}; static const struct of_device_id of_match_clk_mt7622[] = { - { - .compatible = "mediatek,mt7622-topckgen", - .data = mtk_topckgen_init, - }, { - .compatible = "mediatek,mt7622-pericfg", - .data = mtk_pericfg_init, - }, { - /* sentinel */ - } -}; - -static int clk_mt7622_probe(struct platform_device *pdev) -{ - int (*clk_init)(struct platform_device *); - int r; - - clk_init = of_device_get_match_data(&pdev->dev); - if (!clk_init) - return -EINVAL; - - r = clk_init(pdev); - if (r) - dev_err(&pdev->dev, - "could not register clock provider: %s: %d\n", - pdev->name, r); - - return r; -} + { .compatible = "mediatek,mt7622-topckgen", .data = &topck_desc }, + { .compatible = "mediatek,mt7622-pericfg", .data = &peri_desc }, + { /* sentinel */ } +}; static struct platform_driver clk_mt7622_drv = { - .probe = clk_mt7622_probe, .driver = { .name = "clk-mt7622", .of_match_table = of_match_clk_mt7622, }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, }; +module_platform_driver(clk_mt7622_drv) -static int clk_mt7622_init(void) -{ - return platform_driver_register(&clk_mt7622_drv); -} - -arch_initcall(clk_mt7622_init); +MODULE_DESCRIPTION("MediaTek MT7622 clocks driver"); +MODULE_LICENSE("GPL"); -- GitLab From f419069ad864bdb6a9ba5a38ea01224187376d6e Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:17 +0100 Subject: [PATCH 0371/5631] clk: mediatek: mt8516: Move apmixedsys clock driver to its own file In preparation for migrating mt8516 clocks to the common simple probe mechanism, convert the apmixedsys to be a separated platform driver and move it to clk-mt8516-apmixedsys.c. While at it, also fix some indentation issues. During the conversion, error handling was added to the apmixedsys probe function. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-29-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8516-apmixedsys.c | 121 +++++++++++++++++++ drivers/clk/mediatek/clk-mt8516.c | 81 ------------- 3 files changed, 122 insertions(+), 82 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8516-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 5dc5f9457c44..79244e5ccc9c 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -120,5 +120,5 @@ obj-$(CONFIG_COMMON_CLK_MT8365_MFG) += clk-mt8365-mfg.o obj-$(CONFIG_COMMON_CLK_MT8365_MMSYS) += clk-mt8365-mm.o obj-$(CONFIG_COMMON_CLK_MT8365_VDEC) += clk-mt8365-vdec.o obj-$(CONFIG_COMMON_CLK_MT8365_VENC) += clk-mt8365-venc.o -obj-$(CONFIG_COMMON_CLK_MT8516) += clk-mt8516.o +obj-$(CONFIG_COMMON_CLK_MT8516) += clk-mt8516-apmixedsys.o clk-mt8516.o obj-$(CONFIG_COMMON_CLK_MT8516_AUDSYS) += clk-mt8516-aud.o diff --git a/drivers/clk/mediatek/clk-mt8516-apmixedsys.c b/drivers/clk/mediatek/clk-mt8516-apmixedsys.c new file mode 100644 index 000000000000..5b87c9fb81f5 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8516-apmixedsys.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019 MediaTek Inc. + * James Liao + * Fabien Parent + * + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include + +#include "clk-mtk.h" +#include "clk-pll.h" + +#define MT8516_PLL_FMAX (1502UL * MHZ) + +#define CON0_MT8516_RST_BAR BIT(27) + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift, _div_table) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = CON0_MT8516_RST_BAR, \ + .fmax = MT8516_PLL_FMAX, \ + .pcwbits = _pcwbits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .div_table = _div_table, \ + } + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ + _pcw_shift) \ + PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ + _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ + NULL) + +static const struct mtk_pll_div_table mmpll_div_table[] = { + { .div = 0, .freq = MT8516_PLL_FMAX }, + { .div = 1, .freq = 1000000000 }, + { .div = 2, .freq = 604500000 }, + { .div = 3, .freq = 253500000 }, + { .div = 4, .freq = 126750000 }, + { } /* sentinel */ +}; + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0100, 0x0110, 0, 0, + 21, 0x0104, 24, 0, 0x0104, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0120, 0x0130, 0, + HAVE_RST_BAR, 21, 0x0124, 24, 0, 0x0124, 0), + PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0140, 0x0150, 0x30000000, + HAVE_RST_BAR, 7, 0x0144, 24, 0, 0x0144, 0), + PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0160, 0x0170, 0, 0, + 21, 0x0164, 24, 0, 0x0164, 0, mmpll_div_table), + PLL(CLK_APMIXED_APLL1, "apll1", 0x0180, 0x0190, 0, 0, + 31, 0x0180, 1, 0x0194, 0x0184, 0), + PLL(CLK_APMIXED_APLL2, "apll2", 0x01A0, 0x01B0, 0, 0, + 31, 0x01A0, 1, 0x01B4, 0x01A4, 0), +}; + +static int clk_mt8516_apmixed_probe(struct platform_device *pdev) +{ + void __iomem *base; + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + int ret; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + clk_data = mtk_devm_alloc_clk_data(dev, CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_plls; + + return 0; + +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static const struct of_device_id of_match_clk_mt8516_apmixed[] = { + { .compatible = "mediatek,mt8516-apmixedsys" }, + { /* sentinel */ } +}; + +static struct platform_driver clk_mt8516_apmixed_drv = { + .probe = clk_mt8516_apmixed_probe, + .driver = { + .name = "clk-mt8516-apmixed", + .of_match_table = of_match_clk_mt8516_apmixed, + }, +}; +builtin_platform_driver(clk_mt8516_apmixed_drv) + +MODULE_DESCRIPTION("MediaTek MT8516 apmixedsys clocks driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index 6983d3a48dc9..51e6948cb54b 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -13,7 +13,6 @@ #include "clk-gate.h" #include "clk-mtk.h" -#include "clk-pll.h" #include @@ -695,83 +694,3 @@ static void __init mtk_infracfg_init(struct device_node *node) __func__, r); } CLK_OF_DECLARE(mtk_infracfg, "mediatek,mt8516-infracfg", mtk_infracfg_init); - -#define MT8516_PLL_FMAX (1502UL * MHZ) - -#define CON0_MT8516_RST_BAR BIT(27) - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift, _div_table) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = CON0_MT8516_RST_BAR, \ - .fmax = MT8516_PLL_FMAX, \ - .pcwbits = _pcwbits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .div_table = _div_table, \ - } - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \ - _pcw_shift) \ - PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \ - _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \ - NULL) - -static const struct mtk_pll_div_table mmpll_div_table[] = { - { .div = 0, .freq = MT8516_PLL_FMAX }, - { .div = 1, .freq = 1000000000 }, - { .div = 2, .freq = 604500000 }, - { .div = 3, .freq = 253500000 }, - { .div = 4, .freq = 126750000 }, - { } /* sentinel */ -}; - -static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0100, 0x0110, 0, 0, - 21, 0x0104, 24, 0, 0x0104, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0120, 0x0130, 0, - HAVE_RST_BAR, 21, 0x0124, 24, 0, 0x0124, 0), - PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0140, 0x0150, 0x30000000, - HAVE_RST_BAR, 7, 0x0144, 24, 0, 0x0144, 0), - PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0160, 0x0170, 0, 0, - 21, 0x0164, 24, 0, 0x0164, 0, mmpll_div_table), - PLL(CLK_APMIXED_APLL1, "apll1", 0x0180, 0x0190, 0, 0, - 31, 0x0180, 1, 0x0194, 0x0184, 0), - PLL(CLK_APMIXED_APLL2, "apll2", 0x01A0, 0x01B0, 0, 0, - 31, 0x01A0, 1, 0x01B4, 0x01A4, 0), -}; - -static void __init mtk_apmixedsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - void __iomem *base; - int r; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); - -} -CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8516-apmixedsys", - mtk_apmixedsys_init); -- GitLab From b8390192f2755b8f58304374170341f49fe7067e Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:18 +0100 Subject: [PATCH 0372/5631] clk: mediatek: mt8516: Convert to platform driver and simple probe Convert the MT8516 clock drivers to be platform drivers and use the common probe mechanism. Thanks to the conversion, more error handling was added to the clocks registration. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-30-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8516-aud.c | 35 ++++++----- drivers/clk/mediatek/clk-mt8516.c | 88 +++++++++++---------------- 2 files changed, 57 insertions(+), 66 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8516-aud.c b/drivers/clk/mediatek/clk-mt8516-aud.c index a6ae8003b9ff..119dbbd0c3e0 100644 --- a/drivers/clk/mediatek/clk-mt8516-aud.c +++ b/drivers/clk/mediatek/clk-mt8516-aud.c @@ -3,6 +3,7 @@ * Copyright (c) 2019 MediaTek Inc. * Author: James Liao * Fabien Parent + * Copyright (c) 2023 Collabora Ltd. */ #include @@ -25,7 +26,7 @@ static const struct mtk_gate_regs aud_cg_regs = { #define GATE_AUD(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &aud_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr) -static const struct mtk_gate aud_clks[] __initconst = { +static const struct mtk_gate aud_clks[] = { GATE_AUD(CLK_AUD_AFE, "aud_afe", "clk26m_ck", 2), GATE_AUD(CLK_AUD_I2S, "aud_i2s", "i2s_infra_bck", 6), GATE_AUD(CLK_AUD_22M, "aud_22m", "rg_aud_engen1", 8), @@ -41,19 +42,25 @@ static const struct mtk_gate aud_clks[] __initconst = { GATE_AUD(CLK_AUD_TML, "aud_tml", "aud_afe", 27), }; -static void __init mtk_audsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_AUD_NR_CLK); +static const struct mtk_clk_desc aud_desc = { + .clks = aud_clks, + .num_clks = ARRAY_SIZE(aud_clks), +}; - mtk_clk_register_gates(NULL, node, aud_clks, ARRAY_SIZE(aud_clks), clk_data); +static const struct of_device_id of_match_clk_mt8516_aud[] = { + { .compatible = "mediatek,mt8516-audsys", .data = &aud_desc }, + { /* sentinel */ } +}; - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static struct platform_driver clk_mt8516_aud_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8516-aud", + .of_match_table = of_match_clk_mt8516_aud, + }, +}; +builtin_platform_driver(clk_mt8516_aud_drv); -} -CLK_OF_DECLARE(mtk_audsys, "mediatek,mt8516-audsys", mtk_audsys_init); +MODULE_DESCRIPTION("MediaTek MT8516 audiosys clocks driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index 51e6948cb54b..ad59e932d4aa 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -3,6 +3,7 @@ * Copyright (c) 2019 MediaTek Inc. * Author: James Liao * Fabien Parent + * Copyright (c) 2023 Collabora Ltd. */ #include @@ -10,6 +11,7 @@ #include #include #include +#include #include "clk-gate.h" #include "clk-mtk.h" @@ -638,59 +640,41 @@ static const struct mtk_gate top_clks[] __initconst = { GATE_TOP5(CLK_TOP_APLL12_DIV6, "apll12_div6", "apll12_ck_div6", 8), }; -static void __init mtk_topckgen_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - void __iomem *base; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } +static const struct mtk_clk_desc topck_desc = { + .clks = top_clks, + .num_clks = ARRAY_SIZE(top_clks), + .fixed_clks = fixed_clks, + .num_fixed_clks = ARRAY_SIZE(fixed_clks), + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .composite_clks = top_muxes, + .num_composite_clks = ARRAY_SIZE(top_muxes), + .divider_clks = top_adj_divs, + .num_divider_clks = ARRAY_SIZE(top_adj_divs), + .clk_lock = &mt8516_clk_lock, +}; - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); +static const struct mtk_clk_desc infra_desc = { + .composite_clks = ifr_muxes, + .num_composite_clks = ARRAY_SIZE(ifr_muxes), + .clk_lock = &mt8516_clk_lock, +}; - mtk_clk_register_fixed_clks(fixed_clks, ARRAY_SIZE(fixed_clks), - clk_data); - mtk_clk_register_gates(NULL, node, top_clks, ARRAY_SIZE(top_clks), clk_data); +static const struct of_device_id of_match_clk_mt8516[] = { + { .compatible = "mediatek,mt8516-topckgen", .data = &topck_desc }, + { .compatible = "mediatek,mt8516-infracfg", .data = &infra_desc }, + { /* sentinel */ } +}; - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(NULL, top_muxes, - ARRAY_SIZE(top_muxes), base, - &mt8516_clk_lock, clk_data); - mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), - base, &mt8516_clk_lock, clk_data); +static struct platform_driver clk_mt8516_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8516", + .of_match_table = of_match_clk_mt8516, + }, +}; +module_platform_driver(clk_mt8516_drv); - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8516-topckgen", mtk_topckgen_init); - -static void __init mtk_infracfg_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - void __iomem *base; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } - - clk_data = mtk_alloc_clk_data(CLK_IFR_NR_CLK); - - mtk_clk_register_composites(NULL, ifr_muxes, - ARRAY_SIZE(ifr_muxes), base, - &mt8516_clk_lock, clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_infracfg, "mediatek,mt8516-infracfg", mtk_infracfg_init); +MODULE_DESCRIPTION("MediaTek MT8516 clocks driver"); +MODULE_LICENSE("GPL"); -- GitLab From 876d4e21aad8b60e155dbc5bbfb8c8e75c4d9f4b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:19 +0100 Subject: [PATCH 0373/5631] clk: mediatek: mt8516: Allow building clock drivers as modules Now that all MT8516 drivers have been converted to platform driver, change the configuration options to tristate. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-31-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 2d14855dd37e..b9c0a9e21cf1 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -743,7 +743,7 @@ config COMMON_CLK_MT8365_VENC This driver supports MediaTek MT8365 venc clocks. config COMMON_CLK_MT8516 - bool "Clock driver for MediaTek MT8516" + tristate "Clock driver for MediaTek MT8516" depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK @@ -751,7 +751,7 @@ config COMMON_CLK_MT8516 This driver supports MediaTek MT8516 clocks. config COMMON_CLK_MT8516_AUDSYS - bool "Clock driver for MediaTek MT8516 audsys" + tristate "Clock driver for MediaTek MT8516 audsys" depends on COMMON_CLK_MT8516 help This driver supports MediaTek MT8516 audsys clocks. -- GitLab From 6b7daeaa7e64151df080208d6636ae433dbe07c1 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:20 +0100 Subject: [PATCH 0374/5631] clk: mediatek: Propagate struct device with mtk_clk_register_dividers() Propagate struct device for divider clocks registered through clk-mtk helpers to be able to get runtime PM support for MTK clocks. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai # MT8183, MT8192, MT8195 Chromebooks Link: https://lore.kernel.org/r/20230306140543.1813621-32-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701.c | 2 +- drivers/clk/mediatek/clk-mt8167-apmixedsys.c | 2 +- drivers/clk/mediatek/clk-mtk.c | 8 +++++--- drivers/clk/mediatek/clk-mtk.h | 3 ++- 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index dfe328f7a44b..e9c27b1364b6 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -681,7 +681,7 @@ static int mtk_topckgen_init(struct platform_device *pdev) ARRAY_SIZE(top_muxes), base, &mt2701_clk_lock, clk_data); - mtk_clk_register_dividers(top_adj_divs, ARRAY_SIZE(top_adj_divs), + mtk_clk_register_dividers(&pdev->dev, top_adj_divs, ARRAY_SIZE(top_adj_divs), base, &mt2701_clk_lock, clk_data); mtk_clk_register_gates(&pdev->dev, node, top_clks, diff --git a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c index ebd90365be5f..27597fdeb6e9 100644 --- a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c @@ -109,7 +109,7 @@ static int clk_mt8167_apmixed_probe(struct platform_device *pdev) if (ret) return ret; - ret = mtk_clk_register_dividers(adj_divs, ARRAY_SIZE(adj_divs), base, + ret = mtk_clk_register_dividers(dev, adj_divs, ARRAY_SIZE(adj_divs), base, &mt8167_apmixed_clk_lock, clk_data); if (ret) goto unregister_plls; diff --git a/drivers/clk/mediatek/clk-mtk.c b/drivers/clk/mediatek/clk-mtk.c index 01224cfbcc79..fd2214c3242f 100644 --- a/drivers/clk/mediatek/clk-mtk.c +++ b/drivers/clk/mediatek/clk-mtk.c @@ -393,7 +393,8 @@ void mtk_clk_unregister_composites(const struct mtk_composite *mcs, int num, } EXPORT_SYMBOL_GPL(mtk_clk_unregister_composites); -int mtk_clk_register_dividers(const struct mtk_clk_divider *mcds, int num, +int mtk_clk_register_dividers(struct device *dev, + const struct mtk_clk_divider *mcds, int num, void __iomem *base, spinlock_t *lock, struct clk_hw_onecell_data *clk_data) { @@ -412,7 +413,7 @@ int mtk_clk_register_dividers(const struct mtk_clk_divider *mcds, int num, continue; } - hw = clk_hw_register_divider(NULL, mcd->name, mcd->parent_name, + hw = clk_hw_register_divider(dev, mcd->name, mcd->parent_name, mcd->flags, base + mcd->div_reg, mcd->div_shift, mcd->div_width, mcd->clk_divider_flags, lock); @@ -535,7 +536,8 @@ static int __mtk_clk_simple_probe(struct platform_device *pdev, } if (mcd->divider_clks) { - r = mtk_clk_register_dividers(mcd->divider_clks, + r = mtk_clk_register_dividers(&pdev->dev, + mcd->divider_clks, mcd->num_divider_clks, base, mcd->clk_lock, clk_data); if (r) diff --git a/drivers/clk/mediatek/clk-mtk.h b/drivers/clk/mediatek/clk-mtk.h index 554aecdc1015..b7a751861fce 100644 --- a/drivers/clk/mediatek/clk-mtk.h +++ b/drivers/clk/mediatek/clk-mtk.h @@ -202,7 +202,8 @@ struct mtk_clk_divider { .div_width = _width, \ } -int mtk_clk_register_dividers(const struct mtk_clk_divider *mcds, int num, +int mtk_clk_register_dividers(struct device *dev, + const struct mtk_clk_divider *mcds, int num, void __iomem *base, spinlock_t *lock, struct clk_hw_onecell_data *clk_data); void mtk_clk_unregister_dividers(const struct mtk_clk_divider *mcds, int num, -- GitLab From 2562dc42aec84fc6f263ff4198dea85752c4f703 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:21 +0100 Subject: [PATCH 0375/5631] clk: mediatek: mt7986-apmixed: Use PLL_AO flag to set critical clock Instead of calling clk_prepare_enable() at probe time, add the PLL_AO flag to CLK_APMIXED_ARMPLL clock: this will set CLK_IS_CRITICAL. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Daniel Golle Link: https://lore.kernel.org/r/20230306140543.1813621-33-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7986-apmixed.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt7986-apmixed.c b/drivers/clk/mediatek/clk-mt7986-apmixed.c index 62080ee4dbe3..227ca572056e 100644 --- a/drivers/clk/mediatek/clk-mt7986-apmixed.c +++ b/drivers/clk/mediatek/clk-mt7986-apmixed.c @@ -42,7 +42,7 @@ "clkxtal") static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0200, 0x020C, 0x0, 0, 32, + PLL(CLK_APMIXED_ARMPLL, "armpll", 0x0200, 0x020C, 0x0, PLL_AO, 32, 0x0200, 4, 0, 0x0204, 0), PLL(CLK_APMIXED_NET2PLL, "net2pll", 0x0210, 0x021C, 0x0, 0, 32, 0x0210, 4, 0, 0x0214, 0), @@ -77,8 +77,6 @@ static int clk_mt7986_apmixed_probe(struct platform_device *pdev) mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); - clk_prepare_enable(clk_data->hws[CLK_APMIXED_ARMPLL]->clk); - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) { pr_err("%s(): could not register clock provider: %d\n", -- GitLab From 148a39560b27155906c594a60199494945ca7d81 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:22 +0100 Subject: [PATCH 0376/5631] clk: mediatek: mt7986-infracfg: Migrate to common probe mechanism Convert this driver to use the common mtk_clk_simple_probe() mechanism. While at it, also use module_platform_driver() instead, as this driver just gained a .remove() callback during the conversion. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Daniel Golle Link: https://lore.kernel.org/r/20230306140543.1813621-34-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7986-infracfg.c | 61 ++++++---------------- 1 file changed, 17 insertions(+), 44 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt7986-infracfg.c b/drivers/clk/mediatek/clk-mt7986-infracfg.c index 0a4bf87ee160..0299faad0733 100644 --- a/drivers/clk/mediatek/clk-mt7986-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7986-infracfg.c @@ -157,57 +157,30 @@ static const struct mtk_gate infra_clks[] = { GATE_INFRA2(CLK_INFRA_IPCIEB_CK, "infra_ipcieb", "sysaxi_sel", 15), }; -static int clk_mt7986_infracfg_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - int r; - void __iomem *base; - int nr = ARRAY_SIZE(infra_divs) + ARRAY_SIZE(infra_muxes) + - ARRAY_SIZE(infra_clks); - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return -ENOMEM; - } - - clk_data = mtk_alloc_clk_data(nr); - - if (!clk_data) - return -ENOMEM; - - mtk_clk_register_factors(infra_divs, ARRAY_SIZE(infra_divs), clk_data); - mtk_clk_register_muxes(&pdev->dev, infra_muxes, - ARRAY_SIZE(infra_muxes), node, - &mt7986_clk_lock, clk_data); - mtk_clk_register_gates(&pdev->dev, node, infra_clks, - ARRAY_SIZE(infra_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) { - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); - goto free_infracfg_data; - } - return r; - -free_infracfg_data: - mtk_free_clk_data(clk_data); - return r; - -} +static const struct mtk_clk_desc infra_desc = { + .clks = infra_clks, + .num_clks = ARRAY_SIZE(infra_clks), + .factor_clks = infra_divs, + .num_factor_clks = ARRAY_SIZE(infra_divs), + .mux_clks = infra_muxes, + .num_mux_clks = ARRAY_SIZE(infra_muxes), + .clk_lock = &mt7986_clk_lock, +}; static const struct of_device_id of_match_clk_mt7986_infracfg[] = { - { .compatible = "mediatek,mt7986-infracfg", }, - {} + { .compatible = "mediatek,mt7986-infracfg", .data = &infra_desc }, + { /* sentinel */ } }; static struct platform_driver clk_mt7986_infracfg_drv = { - .probe = clk_mt7986_infracfg_probe, .driver = { .name = "clk-mt7986-infracfg", .of_match_table = of_match_clk_mt7986_infracfg, }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, }; -builtin_platform_driver(clk_mt7986_infracfg_drv); +module_platform_driver(clk_mt7986_infracfg_drv); + +MODULE_DESCRIPTION("MediaTek MT7986 infracfg clocks driver"); +MODULE_LICENSE("GPL"); -- GitLab From 1d04e30065b63dfabf7627b08e6f3a2a9a9ce638 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:23 +0100 Subject: [PATCH 0377/5631] clk: mediatek: mt7986-eth: Migrate to common probe mechanism Convert this driver to use the common mtk_clk_simple_probe() mechanism. While at it, also remove __initconst annotations (as these structures are used also at runtime). Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Daniel Golle Link: https://lore.kernel.org/r/20230306140543.1813621-35-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt7986-eth.c | 83 +++++++++++---------------- 1 file changed, 32 insertions(+), 51 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt7986-eth.c b/drivers/clk/mediatek/clk-mt7986-eth.c index e04bc6845ea6..138ba0a47221 100644 --- a/drivers/clk/mediatek/clk-mt7986-eth.c +++ b/drivers/clk/mediatek/clk-mt7986-eth.c @@ -25,7 +25,7 @@ static const struct mtk_gate_regs sgmii0_cg_regs = { #define GATE_SGMII0(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &sgmii0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) -static const struct mtk_gate sgmii0_clks[] __initconst = { +static const struct mtk_gate sgmii0_clks[] = { GATE_SGMII0(CLK_SGMII0_TX250M_EN, "sgmii0_tx250m_en", "top_xtal", 2), GATE_SGMII0(CLK_SGMII0_RX250M_EN, "sgmii0_rx250m_en", "top_xtal", 3), GATE_SGMII0(CLK_SGMII0_CDR_REF, "sgmii0_cdr_ref", "top_xtal", 4), @@ -41,7 +41,7 @@ static const struct mtk_gate_regs sgmii1_cg_regs = { #define GATE_SGMII1(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &sgmii1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) -static const struct mtk_gate sgmii1_clks[] __initconst = { +static const struct mtk_gate sgmii1_clks[] = { GATE_SGMII1(CLK_SGMII1_TX250M_EN, "sgmii1_tx250m_en", "top_xtal", 2), GATE_SGMII1(CLK_SGMII1_RX250M_EN, "sgmii1_rx250m_en", "top_xtal", 3), GATE_SGMII1(CLK_SGMII1_CDR_REF, "sgmii1_cdr_ref", "top_xtal", 4), @@ -57,7 +57,7 @@ static const struct mtk_gate_regs eth_cg_regs = { #define GATE_ETH(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, ð_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) -static const struct mtk_gate eth_clks[] __initconst = { +static const struct mtk_gate eth_clks[] = { GATE_ETH(CLK_ETH_FE_EN, "eth_fe_en", "netsys_2x_sel", 6), GATE_ETH(CLK_ETH_GP2_EN, "eth_gp2_en", "sgm_325m_sel", 7), GATE_ETH(CLK_ETH_GP1_EN, "eth_gp1_en", "sgm_325m_sel", 8), @@ -65,56 +65,37 @@ static const struct mtk_gate eth_clks[] __initconst = { GATE_ETH(CLK_ETH_WOCPU0_EN, "eth_wocpu0_en", "netsys_mcu_sel", 15), }; -static void __init mtk_sgmiisys_0_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(ARRAY_SIZE(sgmii0_clks)); - - mtk_clk_register_gates(NULL, node, sgmii0_clks, - ARRAY_SIZE(sgmii0_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_sgmiisys_0, "mediatek,mt7986-sgmiisys_0", - mtk_sgmiisys_0_init); - -static void __init mtk_sgmiisys_1_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(ARRAY_SIZE(sgmii1_clks)); - - mtk_clk_register_gates(NULL, node, sgmii1_clks, - ARRAY_SIZE(sgmii1_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_sgmiisys_1, "mediatek,mt7986-sgmiisys_1", - mtk_sgmiisys_1_init); +static const struct mtk_clk_desc eth_desc = { + .clks = eth_clks, + .num_clks = ARRAY_SIZE(eth_clks), +}; -static void __init mtk_ethsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; +static const struct mtk_clk_desc sgmii0_desc = { + .clks = sgmii0_clks, + .num_clks = ARRAY_SIZE(sgmii0_clks), +}; - clk_data = mtk_alloc_clk_data(ARRAY_SIZE(eth_clks)); +static const struct mtk_clk_desc sgmii1_desc = { + .clks = sgmii1_clks, + .num_clks = ARRAY_SIZE(sgmii1_clks), +}; - mtk_clk_register_gates(NULL, node, eth_clks, ARRAY_SIZE(eth_clks), clk_data); +static const struct of_device_id of_match_clk_mt7986_eth[] = { + { .compatible = "mediatek,mt7986-ethsys", .data = ð_desc }, + { .compatible = "mediatek,mt7986-sgmiisys_0", .data = &sgmii0_desc }, + { .compatible = "mediatek,mt7986-sgmiisys_1", .data = &sgmii1_desc }, + { /* sentinel */ } +}; - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); +static struct platform_driver clk_mt7986_eth_drv = { + .driver = { + .name = "clk-mt7986-eth", + .of_match_table = of_match_clk_mt7986_eth, + }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, +}; +module_platform_driver(clk_mt7986_eth_drv); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_ethsys, "mediatek,mt7986-ethsys", mtk_ethsys_init); +MODULE_DESCRIPTION("MediaTek MT7986 Ethernet clocks driver"); +MODULE_LICENSE("GPL"); -- GitLab From c5f34f63e5140646f807e4024ee6a0dcefd15482 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:24 +0100 Subject: [PATCH 0378/5631] clk: mediatek: mt8186-mcu: Migrate to common probe mechanism Convert MT8186 MCUSYS clocks to the common mtk_clk_simple_probe(). Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-36-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8186-mcu.c | 68 +++++---------------------- 1 file changed, 13 insertions(+), 55 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8186-mcu.c b/drivers/clk/mediatek/clk-mt8186-mcu.c index e52a2d986c99..895856df95df 100644 --- a/drivers/clk/mediatek/clk-mt8186-mcu.c +++ b/drivers/clk/mediatek/clk-mt8186-mcu.c @@ -43,67 +43,25 @@ static struct mtk_composite mcu_muxes[] = { MUX(CLK_MCU_ARMPLL_BUS_SEL, "mcu_armpll_bus_sel", mcu_armpll_bus_parents, 0x2E0, 9, 2), }; -static const struct of_device_id of_match_clk_mt8186_mcu[] = { - { .compatible = "mediatek,mt8186-mcusys", }, - {} +static const struct mtk_clk_desc mcu_desc = { + .composite_clks = mcu_muxes, + .num_composite_clks = ARRAY_SIZE(mcu_muxes), }; -static int clk_mt8186_mcu_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - int r; - void __iomem *base; - - clk_data = mtk_alloc_clk_data(CLK_MCU_NR_CLK); - if (!clk_data) - return -ENOMEM; - - base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(base)) { - r = PTR_ERR(base); - goto free_mcu_data; - } - - r = mtk_clk_register_composites(&pdev->dev, mcu_muxes, - ARRAY_SIZE(mcu_muxes), base, - NULL, clk_data); - if (r) - goto free_mcu_data; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_composite_muxes; - - platform_set_drvdata(pdev, clk_data); - - return r; - -unregister_composite_muxes: - mtk_clk_unregister_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), clk_data); -free_mcu_data: - mtk_free_clk_data(clk_data); - return r; -} - -static int clk_mt8186_mcu_remove(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); - struct device_node *node = pdev->dev.of_node; - - of_clk_del_provider(node); - mtk_clk_unregister_composites(mcu_muxes, ARRAY_SIZE(mcu_muxes), clk_data); - mtk_free_clk_data(clk_data); - - return 0; -} +static const struct of_device_id of_match_clk_mt8186_mcu[] = { + { .compatible = "mediatek,mt8186-mcusys", .data = &mcu_desc }, + { /* sentinel */} +}; static struct platform_driver clk_mt8186_mcu_drv = { - .probe = clk_mt8186_mcu_probe, - .remove = clk_mt8186_mcu_remove, .driver = { .name = "clk-mt8186-mcu", .of_match_table = of_match_clk_mt8186_mcu, }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, }; -builtin_platform_driver(clk_mt8186_mcu_drv); +module_platform_driver(clk_mt8186_mcu_drv); + +MODULE_DESCRIPTION("MediaTek MT8186 mcusys clocks driver"); +MODULE_LICENSE("GPL"); -- GitLab From 164d240de9ce71e790ef325e2e465d3a7ea46e40 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:25 +0100 Subject: [PATCH 0379/5631] clk: mediatek: Switch to module_platform_driver() where possible Lots of clock drivers have got both .probe() and a .remove() callbacks: switch from builtin_platform_driver() to module_platform_driver() so that we actually register the .remove() callback. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai # MT8183, MT8192, MT8195 Chromebooks Link: https://lore.kernel.org/r/20230306140543.1813621-37-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701-aud.c | 3 +-- drivers/clk/mediatek/clk-mt2701-bdp.c | 3 +-- drivers/clk/mediatek/clk-mt2701-eth.c | 3 +-- drivers/clk/mediatek/clk-mt2701-g3d.c | 3 +-- drivers/clk/mediatek/clk-mt2701-hif.c | 3 +-- drivers/clk/mediatek/clk-mt2701-img.c | 3 +-- drivers/clk/mediatek/clk-mt2701-mm.c | 3 +-- drivers/clk/mediatek/clk-mt2701-vdec.c | 3 +-- drivers/clk/mediatek/clk-mt2712-bdp.c | 3 +-- drivers/clk/mediatek/clk-mt2712-img.c | 3 +-- drivers/clk/mediatek/clk-mt2712-jpgdec.c | 3 +-- drivers/clk/mediatek/clk-mt2712-mfg.c | 3 +-- drivers/clk/mediatek/clk-mt2712-mm.c | 3 +-- drivers/clk/mediatek/clk-mt2712-vdec.c | 3 +-- drivers/clk/mediatek/clk-mt2712-venc.c | 3 +-- drivers/clk/mediatek/clk-mt6765-audio.c | 3 +-- drivers/clk/mediatek/clk-mt6765-cam.c | 3 +-- drivers/clk/mediatek/clk-mt6765-img.c | 3 +-- drivers/clk/mediatek/clk-mt6765-mipi0a.c | 3 +-- drivers/clk/mediatek/clk-mt6765-mm.c | 3 +-- drivers/clk/mediatek/clk-mt6765-vcodec.c | 3 +-- drivers/clk/mediatek/clk-mt6797-img.c | 3 +-- drivers/clk/mediatek/clk-mt6797-mm.c | 3 +-- drivers/clk/mediatek/clk-mt6797-vdec.c | 3 +-- drivers/clk/mediatek/clk-mt6797-venc.c | 3 +-- drivers/clk/mediatek/clk-mt7622-aud.c | 3 +-- drivers/clk/mediatek/clk-mt7622-eth.c | 3 +-- drivers/clk/mediatek/clk-mt7622-hif.c | 3 +-- drivers/clk/mediatek/clk-mt7629-hif.c | 3 +-- drivers/clk/mediatek/clk-mt7981-infracfg.c | 2 +- drivers/clk/mediatek/clk-mt7981-topckgen.c | 2 +- drivers/clk/mediatek/clk-mt7986-topckgen.c | 2 +- drivers/clk/mediatek/clk-mt8167-mm.c | 2 +- drivers/clk/mediatek/clk-mt8173-mm.c | 3 +-- drivers/clk/mediatek/clk-mt8183-audio.c | 3 +-- drivers/clk/mediatek/clk-mt8183-cam.c | 3 +-- drivers/clk/mediatek/clk-mt8183-img.c | 3 +-- drivers/clk/mediatek/clk-mt8183-ipu0.c | 3 +-- drivers/clk/mediatek/clk-mt8183-ipu1.c | 3 +-- drivers/clk/mediatek/clk-mt8183-ipu_adl.c | 3 +-- drivers/clk/mediatek/clk-mt8183-ipu_conn.c | 3 +-- drivers/clk/mediatek/clk-mt8183-mfgcfg.c | 3 +-- drivers/clk/mediatek/clk-mt8183-mm.c | 3 +-- drivers/clk/mediatek/clk-mt8183-vdec.c | 3 +-- drivers/clk/mediatek/clk-mt8183-venc.c | 3 +-- drivers/clk/mediatek/clk-mt8186-apmixedsys.c | 2 +- drivers/clk/mediatek/clk-mt8186-cam.c | 2 +- drivers/clk/mediatek/clk-mt8186-img.c | 2 +- drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c | 2 +- drivers/clk/mediatek/clk-mt8186-infra_ao.c | 2 +- drivers/clk/mediatek/clk-mt8186-ipe.c | 2 +- drivers/clk/mediatek/clk-mt8186-mdp.c | 2 +- drivers/clk/mediatek/clk-mt8186-mfg.c | 2 +- drivers/clk/mediatek/clk-mt8186-mm.c | 2 +- drivers/clk/mediatek/clk-mt8186-topckgen.c | 2 +- drivers/clk/mediatek/clk-mt8186-vdec.c | 2 +- drivers/clk/mediatek/clk-mt8186-venc.c | 2 +- drivers/clk/mediatek/clk-mt8186-wpe.c | 2 +- drivers/clk/mediatek/clk-mt8192-aud.c | 3 +-- drivers/clk/mediatek/clk-mt8192-cam.c | 3 +-- drivers/clk/mediatek/clk-mt8192-img.c | 3 +-- drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c | 3 +-- drivers/clk/mediatek/clk-mt8192-ipe.c | 3 +-- drivers/clk/mediatek/clk-mt8192-mdp.c | 3 +-- drivers/clk/mediatek/clk-mt8192-mfg.c | 3 +-- drivers/clk/mediatek/clk-mt8192-mm.c | 3 +-- drivers/clk/mediatek/clk-mt8192-msdc.c | 3 +-- drivers/clk/mediatek/clk-mt8192-scp_adsp.c | 3 +-- drivers/clk/mediatek/clk-mt8192-vdec.c | 3 +-- drivers/clk/mediatek/clk-mt8192-venc.c | 3 +-- drivers/clk/mediatek/clk-mt8195-apmixedsys.c | 2 +- drivers/clk/mediatek/clk-mt8195-apusys_pll.c | 2 +- drivers/clk/mediatek/clk-mt8195-cam.c | 2 +- drivers/clk/mediatek/clk-mt8195-ccu.c | 2 +- drivers/clk/mediatek/clk-mt8195-img.c | 2 +- drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c | 2 +- drivers/clk/mediatek/clk-mt8195-infra_ao.c | 2 +- drivers/clk/mediatek/clk-mt8195-ipe.c | 2 +- drivers/clk/mediatek/clk-mt8195-mfg.c | 2 +- drivers/clk/mediatek/clk-mt8195-peri_ao.c | 2 +- drivers/clk/mediatek/clk-mt8195-scp_adsp.c | 2 +- drivers/clk/mediatek/clk-mt8195-topckgen.c | 2 +- drivers/clk/mediatek/clk-mt8195-vdec.c | 2 +- drivers/clk/mediatek/clk-mt8195-vdo0.c | 3 ++- drivers/clk/mediatek/clk-mt8195-vdo1.c | 3 ++- drivers/clk/mediatek/clk-mt8195-venc.c | 2 +- drivers/clk/mediatek/clk-mt8195-vpp0.c | 2 +- drivers/clk/mediatek/clk-mt8195-vpp1.c | 2 +- drivers/clk/mediatek/clk-mt8195-wpe.c | 2 +- drivers/clk/mediatek/clk-mt8365-apu.c | 2 +- drivers/clk/mediatek/clk-mt8365-cam.c | 2 +- drivers/clk/mediatek/clk-mt8365-mfg.c | 2 +- drivers/clk/mediatek/clk-mt8365-mm.c | 2 +- drivers/clk/mediatek/clk-mt8365-vdec.c | 2 +- drivers/clk/mediatek/clk-mt8365-venc.c | 2 +- drivers/clk/mediatek/clk-mt8516-aud.c | 2 +- 96 files changed, 98 insertions(+), 149 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index 21f7cc106bbe..cff6c3b8896f 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -163,5 +163,4 @@ static struct platform_driver clk_mt2701_aud_drv = { .of_match_table = of_match_clk_mt2701_aud, }, }; - -builtin_platform_driver(clk_mt2701_aud_drv); +module_platform_driver(clk_mt2701_aud_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c index b0f057207945..dad9a35e9310 100644 --- a/drivers/clk/mediatek/clk-mt2701-bdp.c +++ b/drivers/clk/mediatek/clk-mt2701-bdp.c @@ -104,5 +104,4 @@ static struct platform_driver clk_mt2701_bdp_drv = { .of_match_table = of_match_clk_mt2701_bdp, }, }; - -builtin_platform_driver(clk_mt2701_bdp_drv); +module_platform_driver(clk_mt2701_bdp_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-eth.c b/drivers/clk/mediatek/clk-mt2701-eth.c index 4c830ebdd761..2c4781f9141a 100644 --- a/drivers/clk/mediatek/clk-mt2701-eth.c +++ b/drivers/clk/mediatek/clk-mt2701-eth.c @@ -58,5 +58,4 @@ static struct platform_driver clk_mt2701_eth_drv = { .of_match_table = of_match_clk_mt2701_eth, }, }; - -builtin_platform_driver(clk_mt2701_eth_drv); +module_platform_driver(clk_mt2701_eth_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-g3d.c b/drivers/clk/mediatek/clk-mt2701-g3d.c index ae094046890a..2fed9f96d1e5 100644 --- a/drivers/clk/mediatek/clk-mt2701-g3d.c +++ b/drivers/clk/mediatek/clk-mt2701-g3d.c @@ -57,5 +57,4 @@ static struct platform_driver clk_mt2701_g3d_drv = { .of_match_table = of_match_clk_mt2701_g3d, }, }; - -builtin_platform_driver(clk_mt2701_g3d_drv); +module_platform_driver(clk_mt2701_g3d_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-hif.c b/drivers/clk/mediatek/clk-mt2701-hif.c index 3583bd1240d5..ac47a20047da 100644 --- a/drivers/clk/mediatek/clk-mt2701-hif.c +++ b/drivers/clk/mediatek/clk-mt2701-hif.c @@ -55,5 +55,4 @@ static struct platform_driver clk_mt2701_hif_drv = { .of_match_table = of_match_clk_mt2701_hif, }, }; - -builtin_platform_driver(clk_mt2701_hif_drv); +module_platform_driver(clk_mt2701_hif_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c index eb172473f075..776f470623ca 100644 --- a/drivers/clk/mediatek/clk-mt2701-img.c +++ b/drivers/clk/mediatek/clk-mt2701-img.c @@ -52,5 +52,4 @@ static struct platform_driver clk_mt2701_img_drv = { .of_match_table = of_match_clk_mt2701_img, }, }; - -builtin_platform_driver(clk_mt2701_img_drv); +module_platform_driver(clk_mt2701_img_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index 993d904d619f..f23208b8dcba 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -85,5 +85,4 @@ static struct platform_driver clk_mt2701_mm_drv = { }, .id_table = clk_mt2701_mm_id_table, }; - -builtin_platform_driver(clk_mt2701_mm_drv); +module_platform_driver(clk_mt2701_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c index 0f07c5d731df..57e7020aaab5 100644 --- a/drivers/clk/mediatek/clk-mt2701-vdec.c +++ b/drivers/clk/mediatek/clk-mt2701-vdec.c @@ -57,5 +57,4 @@ static struct platform_driver clk_mt2701_vdec_drv = { .of_match_table = of_match_clk_mt2701_vdec, }, }; - -builtin_platform_driver(clk_mt2701_vdec_drv); +module_platform_driver(clk_mt2701_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-bdp.c b/drivers/clk/mediatek/clk-mt2712-bdp.c index 5e668651dd90..5324544039b3 100644 --- a/drivers/clk/mediatek/clk-mt2712-bdp.c +++ b/drivers/clk/mediatek/clk-mt2712-bdp.c @@ -74,5 +74,4 @@ static struct platform_driver clk_mt2712_bdp_drv = { .of_match_table = of_match_clk_mt2712_bdp, }, }; - -builtin_platform_driver(clk_mt2712_bdp_drv); +module_platform_driver(clk_mt2712_bdp_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-img.c b/drivers/clk/mediatek/clk-mt2712-img.c index 3ffa51384e6b..c16453c6b421 100644 --- a/drivers/clk/mediatek/clk-mt2712-img.c +++ b/drivers/clk/mediatek/clk-mt2712-img.c @@ -52,5 +52,4 @@ static struct platform_driver clk_mt2712_img_drv = { .of_match_table = of_match_clk_mt2712_img, }, }; - -builtin_platform_driver(clk_mt2712_img_drv); +module_platform_driver(clk_mt2712_img_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-jpgdec.c b/drivers/clk/mediatek/clk-mt2712-jpgdec.c index 8c768d5ce24d..c1363eb5d893 100644 --- a/drivers/clk/mediatek/clk-mt2712-jpgdec.c +++ b/drivers/clk/mediatek/clk-mt2712-jpgdec.c @@ -48,5 +48,4 @@ static struct platform_driver clk_mt2712_jpgdec_drv = { .of_match_table = of_match_clk_mt2712_jpgdec, }, }; - -builtin_platform_driver(clk_mt2712_jpgdec_drv); +module_platform_driver(clk_mt2712_jpgdec_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-mfg.c b/drivers/clk/mediatek/clk-mt2712-mfg.c index 8949315c2dd2..d91d788babcf 100644 --- a/drivers/clk/mediatek/clk-mt2712-mfg.c +++ b/drivers/clk/mediatek/clk-mt2712-mfg.c @@ -47,5 +47,4 @@ static struct platform_driver clk_mt2712_mfg_drv = { .of_match_table = of_match_clk_mt2712_mfg, }, }; - -builtin_platform_driver(clk_mt2712_mfg_drv); +module_platform_driver(clk_mt2712_mfg_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index 850cef9f2009..6245b79bab90 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -126,5 +126,4 @@ static struct platform_driver clk_mt2712_mm_drv = { }, .id_table = clk_mt2712_mm_id_table, }; - -builtin_platform_driver(clk_mt2712_mm_drv); +module_platform_driver(clk_mt2712_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-vdec.c b/drivers/clk/mediatek/clk-mt2712-vdec.c index 572290dd43c8..1d3e65f60808 100644 --- a/drivers/clk/mediatek/clk-mt2712-vdec.c +++ b/drivers/clk/mediatek/clk-mt2712-vdec.c @@ -60,5 +60,4 @@ static struct platform_driver clk_mt2712_vdec_drv = { .of_match_table = of_match_clk_mt2712_vdec, }, }; - -builtin_platform_driver(clk_mt2712_vdec_drv); +module_platform_driver(clk_mt2712_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt2712-venc.c b/drivers/clk/mediatek/clk-mt2712-venc.c index 9588eb03016e..09f2683f0f13 100644 --- a/drivers/clk/mediatek/clk-mt2712-venc.c +++ b/drivers/clk/mediatek/clk-mt2712-venc.c @@ -49,5 +49,4 @@ static struct platform_driver clk_mt2712_venc_drv = { .of_match_table = of_match_clk_mt2712_venc, }, }; - -builtin_platform_driver(clk_mt2712_venc_drv); +module_platform_driver(clk_mt2712_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-audio.c b/drivers/clk/mediatek/clk-mt6765-audio.c index 5682e0302eee..712e0da78b4b 100644 --- a/drivers/clk/mediatek/clk-mt6765-audio.c +++ b/drivers/clk/mediatek/clk-mt6765-audio.c @@ -74,5 +74,4 @@ static struct platform_driver clk_mt6765_audio_drv = { .of_match_table = of_match_clk_mt6765_audio, }, }; - -builtin_platform_driver(clk_mt6765_audio_drv); +module_platform_driver(clk_mt6765_audio_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-cam.c b/drivers/clk/mediatek/clk-mt6765-cam.c index 6e7d192c19cb..0581a1f3971e 100644 --- a/drivers/clk/mediatek/clk-mt6765-cam.c +++ b/drivers/clk/mediatek/clk-mt6765-cam.c @@ -55,5 +55,4 @@ static struct platform_driver clk_mt6765_cam_drv = { .of_match_table = of_match_clk_mt6765_cam, }, }; - -builtin_platform_driver(clk_mt6765_cam_drv); +module_platform_driver(clk_mt6765_cam_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-img.c b/drivers/clk/mediatek/clk-mt6765-img.c index cfbc907988af..7c605dc155eb 100644 --- a/drivers/clk/mediatek/clk-mt6765-img.c +++ b/drivers/clk/mediatek/clk-mt6765-img.c @@ -51,5 +51,4 @@ static struct platform_driver clk_mt6765_img_drv = { .of_match_table = of_match_clk_mt6765_img, }, }; - -builtin_platform_driver(clk_mt6765_img_drv); +module_platform_driver(clk_mt6765_img_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-mipi0a.c b/drivers/clk/mediatek/clk-mt6765-mipi0a.c index f2b9dc808480..b299db047138 100644 --- a/drivers/clk/mediatek/clk-mt6765-mipi0a.c +++ b/drivers/clk/mediatek/clk-mt6765-mipi0a.c @@ -48,5 +48,4 @@ static struct platform_driver clk_mt6765_mipi0a_drv = { .of_match_table = of_match_clk_mt6765_mipi0a, }, }; - -builtin_platform_driver(clk_mt6765_mipi0a_drv); +module_platform_driver(clk_mt6765_mipi0a_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-mm.c b/drivers/clk/mediatek/clk-mt6765-mm.c index a4570c9dbefa..ec2b287cf1a3 100644 --- a/drivers/clk/mediatek/clk-mt6765-mm.c +++ b/drivers/clk/mediatek/clk-mt6765-mm.c @@ -77,5 +77,4 @@ static struct platform_driver clk_mt6765_mm_drv = { .of_match_table = of_match_clk_mt6765_mm, }, }; - -builtin_platform_driver(clk_mt6765_mm_drv); +module_platform_driver(clk_mt6765_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt6765-vcodec.c b/drivers/clk/mediatek/clk-mt6765-vcodec.c index 75d72b9b4032..17355923325e 100644 --- a/drivers/clk/mediatek/clk-mt6765-vcodec.c +++ b/drivers/clk/mediatek/clk-mt6765-vcodec.c @@ -50,5 +50,4 @@ static struct platform_driver clk_mt6765_vcodec_drv = { .of_match_table = of_match_clk_mt6765_vcodec, }, }; - -builtin_platform_driver(clk_mt6765_vcodec_drv); +module_platform_driver(clk_mt6765_vcodec_drv); diff --git a/drivers/clk/mediatek/clk-mt6797-img.c b/drivers/clk/mediatek/clk-mt6797-img.c index 06441393478f..d46a3a3ac3ad 100644 --- a/drivers/clk/mediatek/clk-mt6797-img.c +++ b/drivers/clk/mediatek/clk-mt6797-img.c @@ -48,5 +48,4 @@ static struct platform_driver clk_mt6797_img_drv = { .of_match_table = of_match_clk_mt6797_img, }, }; - -builtin_platform_driver(clk_mt6797_img_drv); +module_platform_driver(clk_mt6797_img_drv); diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index e7a5a43f91f1..899a0e6fa988 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -98,5 +98,4 @@ static struct platform_driver clk_mt6797_mm_drv = { }, .id_table = clk_mt6797_mm_id_table, }; - -builtin_platform_driver(clk_mt6797_mm_drv); +module_platform_driver(clk_mt6797_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt6797-vdec.c b/drivers/clk/mediatek/clk-mt6797-vdec.c index 8622ddd87a5b..f2b979b1ea19 100644 --- a/drivers/clk/mediatek/clk-mt6797-vdec.c +++ b/drivers/clk/mediatek/clk-mt6797-vdec.c @@ -59,5 +59,4 @@ static struct platform_driver clk_mt6797_vdec_drv = { .of_match_table = of_match_clk_mt6797_vdec, }, }; - -builtin_platform_driver(clk_mt6797_vdec_drv); +module_platform_driver(clk_mt6797_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt6797-venc.c b/drivers/clk/mediatek/clk-mt6797-venc.c index 928d611a476e..9fbf4cd5160e 100644 --- a/drivers/clk/mediatek/clk-mt6797-venc.c +++ b/drivers/clk/mediatek/clk-mt6797-venc.c @@ -50,5 +50,4 @@ static struct platform_driver clk_mt6797_venc_drv = { .of_match_table = of_match_clk_mt6797_venc, }, }; - -builtin_platform_driver(clk_mt6797_venc_drv); +module_platform_driver(clk_mt6797_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt7622-aud.c b/drivers/clk/mediatek/clk-mt7622-aud.c index 27c543759f2a..7cca52693a3f 100644 --- a/drivers/clk/mediatek/clk-mt7622-aud.c +++ b/drivers/clk/mediatek/clk-mt7622-aud.c @@ -154,5 +154,4 @@ static struct platform_driver clk_mt7622_aud_drv = { .of_match_table = of_match_clk_mt7622_aud, }, }; - -builtin_platform_driver(clk_mt7622_aud_drv); +module_platform_driver(clk_mt7622_aud_drv); diff --git a/drivers/clk/mediatek/clk-mt7622-eth.c b/drivers/clk/mediatek/clk-mt7622-eth.c index 66b163cc1633..89e68c836d40 100644 --- a/drivers/clk/mediatek/clk-mt7622-eth.c +++ b/drivers/clk/mediatek/clk-mt7622-eth.c @@ -86,5 +86,4 @@ static struct platform_driver clk_mt7622_eth_drv = { .of_match_table = of_match_clk_mt7622_eth, }, }; - -builtin_platform_driver(clk_mt7622_eth_drv); +module_platform_driver(clk_mt7622_eth_drv); diff --git a/drivers/clk/mediatek/clk-mt7622-hif.c b/drivers/clk/mediatek/clk-mt7622-hif.c index bcd1dfc6e8e0..06ade985dfe2 100644 --- a/drivers/clk/mediatek/clk-mt7622-hif.c +++ b/drivers/clk/mediatek/clk-mt7622-hif.c @@ -98,5 +98,4 @@ static struct platform_driver clk_mt7622_hif_drv = { .of_match_table = of_match_clk_mt7622_hif, }, }; - -builtin_platform_driver(clk_mt7622_hif_drv); +module_platform_driver(clk_mt7622_hif_drv); diff --git a/drivers/clk/mediatek/clk-mt7629-hif.c b/drivers/clk/mediatek/clk-mt7629-hif.c index 78d85542e4f1..79bcd91386fc 100644 --- a/drivers/clk/mediatek/clk-mt7629-hif.c +++ b/drivers/clk/mediatek/clk-mt7629-hif.c @@ -93,5 +93,4 @@ static struct platform_driver clk_mt7629_hif_drv = { .of_match_table = of_match_clk_mt7629_hif, }, }; - -builtin_platform_driver(clk_mt7629_hif_drv); +module_platform_driver(clk_mt7629_hif_drv); diff --git a/drivers/clk/mediatek/clk-mt7981-infracfg.c b/drivers/clk/mediatek/clk-mt7981-infracfg.c index 8cf5057419e8..35cd126408b6 100644 --- a/drivers/clk/mediatek/clk-mt7981-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7981-infracfg.c @@ -204,4 +204,4 @@ static struct platform_driver clk_mt7981_infracfg_drv = { .of_match_table = of_match_clk_mt7981_infracfg, }, }; -builtin_platform_driver(clk_mt7981_infracfg_drv); +module_platform_driver(clk_mt7981_infracfg_drv); diff --git a/drivers/clk/mediatek/clk-mt7981-topckgen.c b/drivers/clk/mediatek/clk-mt7981-topckgen.c index 74634d65f5f6..f4c31cb1c74e 100644 --- a/drivers/clk/mediatek/clk-mt7981-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7981-topckgen.c @@ -419,4 +419,4 @@ static struct platform_driver clk_mt7981_topckgen_drv = { .of_match_table = of_match_clk_mt7981_topckgen, }, }; -builtin_platform_driver(clk_mt7981_topckgen_drv); +module_platform_driver(clk_mt7981_topckgen_drv); diff --git a/drivers/clk/mediatek/clk-mt7986-topckgen.c b/drivers/clk/mediatek/clk-mt7986-topckgen.c index dff9976fa689..dacaf5492286 100644 --- a/drivers/clk/mediatek/clk-mt7986-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7986-topckgen.c @@ -313,4 +313,4 @@ static struct platform_driver clk_mt7986_topckgen_drv = { .of_match_table = of_match_clk_mt7986_topckgen, }, }; -builtin_platform_driver(clk_mt7986_topckgen_drv); +module_platform_driver(clk_mt7986_topckgen_drv); diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index 5a5192d0dc45..de6c2283b695 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -92,4 +92,4 @@ static struct platform_driver clk_mt8167_mm_drv = { }, .id_table = clk_mt8167_mm_id_table, }; -builtin_platform_driver(clk_mt8167_mm_drv); +module_platform_driver(clk_mt8167_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8173-mm.c b/drivers/clk/mediatek/clk-mt8173-mm.c index 435cfae25492..ba51c22cbe7a 100644 --- a/drivers/clk/mediatek/clk-mt8173-mm.c +++ b/drivers/clk/mediatek/clk-mt8173-mm.c @@ -107,8 +107,7 @@ static struct platform_driver clk_mt8173_mm_drv = { .probe = mtk_clk_pdev_probe, .remove = mtk_clk_pdev_remove, }; - -builtin_platform_driver(clk_mt8173_mm_drv); +module_platform_driver(clk_mt8173_mm_drv); MODULE_DESCRIPTION("MediaTek MT8173 MultiMedia clocks driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-audio.c b/drivers/clk/mediatek/clk-mt8183-audio.c index 3f1630290b93..24cc2178c769 100644 --- a/drivers/clk/mediatek/clk-mt8183-audio.c +++ b/drivers/clk/mediatek/clk-mt8183-audio.c @@ -106,5 +106,4 @@ static struct platform_driver clk_mt8183_audio_drv = { .of_match_table = of_match_clk_mt8183_audio, }, }; - -builtin_platform_driver(clk_mt8183_audio_drv); +module_platform_driver(clk_mt8183_audio_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-cam.c b/drivers/clk/mediatek/clk-mt8183-cam.c index 6907b1a6a824..7ff183da0075 100644 --- a/drivers/clk/mediatek/clk-mt8183-cam.c +++ b/drivers/clk/mediatek/clk-mt8183-cam.c @@ -56,5 +56,4 @@ static struct platform_driver clk_mt8183_cam_drv = { .of_match_table = of_match_clk_mt8183_cam, }, }; - -builtin_platform_driver(clk_mt8183_cam_drv); +module_platform_driver(clk_mt8183_cam_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-img.c b/drivers/clk/mediatek/clk-mt8183-img.c index 8d884425d79f..e4a9d3201e33 100644 --- a/drivers/clk/mediatek/clk-mt8183-img.c +++ b/drivers/clk/mediatek/clk-mt8183-img.c @@ -56,5 +56,4 @@ static struct platform_driver clk_mt8183_img_drv = { .of_match_table = of_match_clk_mt8183_img, }, }; - -builtin_platform_driver(clk_mt8183_img_drv); +module_platform_driver(clk_mt8183_img_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu0.c b/drivers/clk/mediatek/clk-mt8183-ipu0.c index 953a8a33d048..68d4cda89d6f 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu0.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu0.c @@ -49,5 +49,4 @@ static struct platform_driver clk_mt8183_ipu_core0_drv = { .of_match_table = of_match_clk_mt8183_ipu_core0, }, }; - -builtin_platform_driver(clk_mt8183_ipu_core0_drv); +module_platform_driver(clk_mt8183_ipu_core0_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu1.c b/drivers/clk/mediatek/clk-mt8183-ipu1.c index 221d12265974..50950bed9226 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu1.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu1.c @@ -49,5 +49,4 @@ static struct platform_driver clk_mt8183_ipu_core1_drv = { .of_match_table = of_match_clk_mt8183_ipu_core1, }, }; - -builtin_platform_driver(clk_mt8183_ipu_core1_drv); +module_platform_driver(clk_mt8183_ipu_core1_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c index 8c4fd96df821..2044d5c664b8 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c @@ -47,5 +47,4 @@ static struct platform_driver clk_mt8183_ipu_adl_drv = { .of_match_table = of_match_clk_mt8183_ipu_adl, }, }; - -builtin_platform_driver(clk_mt8183_ipu_adl_drv); +module_platform_driver(clk_mt8183_ipu_adl_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c index 14a4c3ff82a1..6e7833656c9a 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c @@ -116,5 +116,4 @@ static struct platform_driver clk_mt8183_ipu_conn_drv = { .of_match_table = of_match_clk_mt8183_ipu_conn, }, }; - -builtin_platform_driver(clk_mt8183_ipu_conn_drv); +module_platform_driver(clk_mt8183_ipu_conn_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c index 730c9ae5ea12..5a71ef094e03 100644 --- a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c @@ -48,5 +48,4 @@ static struct platform_driver clk_mt8183_mfg_drv = { .of_match_table = of_match_clk_mt8183_mfg, }, }; - -builtin_platform_driver(clk_mt8183_mfg_drv); +module_platform_driver(clk_mt8183_mfg_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-mm.c b/drivers/clk/mediatek/clk-mt8183-mm.c index 669dcdd66efb..25a04f311dc3 100644 --- a/drivers/clk/mediatek/clk-mt8183-mm.c +++ b/drivers/clk/mediatek/clk-mt8183-mm.c @@ -100,5 +100,4 @@ static struct platform_driver clk_mt8183_mm_drv = { }, .id_table = clk_mt8183_mm_id_table, }; - -builtin_platform_driver(clk_mt8183_mm_drv); +module_platform_driver(clk_mt8183_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-vdec.c b/drivers/clk/mediatek/clk-mt8183-vdec.c index c294e50b96b7..4c56d02a9d34 100644 --- a/drivers/clk/mediatek/clk-mt8183-vdec.c +++ b/drivers/clk/mediatek/clk-mt8183-vdec.c @@ -60,5 +60,4 @@ static struct platform_driver clk_mt8183_vdec_drv = { .of_match_table = of_match_clk_mt8183_vdec, }, }; - -builtin_platform_driver(clk_mt8183_vdec_drv); +module_platform_driver(clk_mt8183_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt8183-venc.c b/drivers/clk/mediatek/clk-mt8183-venc.c index 0051c5d92fc5..5b86d7d42613 100644 --- a/drivers/clk/mediatek/clk-mt8183-venc.c +++ b/drivers/clk/mediatek/clk-mt8183-venc.c @@ -52,5 +52,4 @@ static struct platform_driver clk_mt8183_venc_drv = { .of_match_table = of_match_clk_mt8183_venc, }, }; - -builtin_platform_driver(clk_mt8183_venc_drv); +module_platform_driver(clk_mt8183_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c index 9fded5020ca4..ab500b985900 100644 --- a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c @@ -192,4 +192,4 @@ static struct platform_driver clk_mt8186_apmixed_drv = { .of_match_table = of_match_clk_mt8186_apmixed, }, }; -builtin_platform_driver(clk_mt8186_apmixed_drv); +module_platform_driver(clk_mt8186_apmixed_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-cam.c b/drivers/clk/mediatek/clk-mt8186-cam.c index 9ec345a2ce66..220c8af7848e 100644 --- a/drivers/clk/mediatek/clk-mt8186-cam.c +++ b/drivers/clk/mediatek/clk-mt8186-cam.c @@ -87,4 +87,4 @@ static struct platform_driver clk_mt8186_cam_drv = { .of_match_table = of_match_clk_mt8186_cam, }, }; -builtin_platform_driver(clk_mt8186_cam_drv); +module_platform_driver(clk_mt8186_cam_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-img.c b/drivers/clk/mediatek/clk-mt8186-img.c index 08a625475aee..bac0e52bd51c 100644 --- a/drivers/clk/mediatek/clk-mt8186-img.c +++ b/drivers/clk/mediatek/clk-mt8186-img.c @@ -65,4 +65,4 @@ static struct platform_driver clk_mt8186_img_drv = { .of_match_table = of_match_clk_mt8186_img, }, }; -builtin_platform_driver(clk_mt8186_img_drv); +module_platform_driver(clk_mt8186_img_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c index 47f2e480a05e..9301dc3e86fb 100644 --- a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c @@ -64,4 +64,4 @@ static struct platform_driver clk_mt8186_imp_iic_wrap_drv = { .of_match_table = of_match_clk_mt8186_imp_iic_wrap, }, }; -builtin_platform_driver(clk_mt8186_imp_iic_wrap_drv); +module_platform_driver(clk_mt8186_imp_iic_wrap_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-infra_ao.c b/drivers/clk/mediatek/clk-mt8186-infra_ao.c index df2a6bd1aefa..e705d57032a6 100644 --- a/drivers/clk/mediatek/clk-mt8186-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8186-infra_ao.c @@ -236,4 +236,4 @@ static struct platform_driver clk_mt8186_infra_ao_drv = { .of_match_table = of_match_clk_mt8186_infra_ao, }, }; -builtin_platform_driver(clk_mt8186_infra_ao_drv); +module_platform_driver(clk_mt8186_infra_ao_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-ipe.c b/drivers/clk/mediatek/clk-mt8186-ipe.c index 8fca148effa6..36f6338f8237 100644 --- a/drivers/clk/mediatek/clk-mt8186-ipe.c +++ b/drivers/clk/mediatek/clk-mt8186-ipe.c @@ -52,4 +52,4 @@ static struct platform_driver clk_mt8186_ipe_drv = { .of_match_table = of_match_clk_mt8186_ipe, }, }; -builtin_platform_driver(clk_mt8186_ipe_drv); +module_platform_driver(clk_mt8186_ipe_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-mdp.c b/drivers/clk/mediatek/clk-mt8186-mdp.c index 05174088ef20..faf5cdc7523f 100644 --- a/drivers/clk/mediatek/clk-mt8186-mdp.c +++ b/drivers/clk/mediatek/clk-mt8186-mdp.c @@ -77,4 +77,4 @@ static struct platform_driver clk_mt8186_mdp_drv = { .of_match_table = of_match_clk_mt8186_mdp, }, }; -builtin_platform_driver(clk_mt8186_mdp_drv); +module_platform_driver(clk_mt8186_mdp_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-mfg.c b/drivers/clk/mediatek/clk-mt8186-mfg.c index 0142d741053a..468fa7e37074 100644 --- a/drivers/clk/mediatek/clk-mt8186-mfg.c +++ b/drivers/clk/mediatek/clk-mt8186-mfg.c @@ -46,4 +46,4 @@ static struct platform_driver clk_mt8186_mfg_drv = { .of_match_table = of_match_clk_mt8186_mfg, }, }; -builtin_platform_driver(clk_mt8186_mfg_drv); +module_platform_driver(clk_mt8186_mfg_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-mm.c b/drivers/clk/mediatek/clk-mt8186-mm.c index 6506a8b848a9..03dfb4d99930 100644 --- a/drivers/clk/mediatek/clk-mt8186-mm.c +++ b/drivers/clk/mediatek/clk-mt8186-mm.c @@ -75,4 +75,4 @@ static struct platform_driver clk_mt8186_mm_drv = { }, .id_table = clk_mt8186_mm_id_table, }; -builtin_platform_driver(clk_mt8186_mm_drv); +module_platform_driver(clk_mt8186_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-topckgen.c b/drivers/clk/mediatek/clk-mt8186-topckgen.c index c6786c8b315f..7f2a59347166 100644 --- a/drivers/clk/mediatek/clk-mt8186-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8186-topckgen.c @@ -730,4 +730,4 @@ static struct platform_driver clk_mt8186_topck_drv = { .of_match_table = of_match_clk_mt8186_topck, }, }; -builtin_platform_driver(clk_mt8186_topck_drv); +module_platform_driver(clk_mt8186_topck_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-vdec.c b/drivers/clk/mediatek/clk-mt8186-vdec.c index 5ad7e1ae0bac..76e226be8f72 100644 --- a/drivers/clk/mediatek/clk-mt8186-vdec.c +++ b/drivers/clk/mediatek/clk-mt8186-vdec.c @@ -85,4 +85,4 @@ static struct platform_driver clk_mt8186_vdec_drv = { .of_match_table = of_match_clk_mt8186_vdec, }, }; -builtin_platform_driver(clk_mt8186_vdec_drv); +module_platform_driver(clk_mt8186_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-venc.c b/drivers/clk/mediatek/clk-mt8186-venc.c index f5519f794c45..96c15b859e37 100644 --- a/drivers/clk/mediatek/clk-mt8186-venc.c +++ b/drivers/clk/mediatek/clk-mt8186-venc.c @@ -48,4 +48,4 @@ static struct platform_driver clk_mt8186_venc_drv = { .of_match_table = of_match_clk_mt8186_venc, }, }; -builtin_platform_driver(clk_mt8186_venc_drv); +module_platform_driver(clk_mt8186_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt8186-wpe.c b/drivers/clk/mediatek/clk-mt8186-wpe.c index 8db3e9178a1e..dbd8a81b170d 100644 --- a/drivers/clk/mediatek/clk-mt8186-wpe.c +++ b/drivers/clk/mediatek/clk-mt8186-wpe.c @@ -48,4 +48,4 @@ static struct platform_driver clk_mt8186_wpe_drv = { .of_match_table = of_match_clk_mt8186_wpe, }, }; -builtin_platform_driver(clk_mt8186_wpe_drv); +module_platform_driver(clk_mt8186_wpe_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-aud.c b/drivers/clk/mediatek/clk-mt8192-aud.c index 29affb68e854..deb292cc9da1 100644 --- a/drivers/clk/mediatek/clk-mt8192-aud.c +++ b/drivers/clk/mediatek/clk-mt8192-aud.c @@ -116,5 +116,4 @@ static struct platform_driver clk_mt8192_aud_drv = { .of_match_table = of_match_clk_mt8192_aud, }, }; - -builtin_platform_driver(clk_mt8192_aud_drv); +module_platform_driver(clk_mt8192_aud_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-cam.c b/drivers/clk/mediatek/clk-mt8192-cam.c index 90b57d46eef7..00dbd0d27fbc 100644 --- a/drivers/clk/mediatek/clk-mt8192-cam.c +++ b/drivers/clk/mediatek/clk-mt8192-cam.c @@ -104,5 +104,4 @@ static struct platform_driver clk_mt8192_cam_drv = { .of_match_table = of_match_clk_mt8192_cam, }, }; - -builtin_platform_driver(clk_mt8192_cam_drv); +module_platform_driver(clk_mt8192_cam_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-img.c b/drivers/clk/mediatek/clk-mt8192-img.c index da82d65a7650..00abbec6c666 100644 --- a/drivers/clk/mediatek/clk-mt8192-img.c +++ b/drivers/clk/mediatek/clk-mt8192-img.c @@ -67,5 +67,4 @@ static struct platform_driver clk_mt8192_img_drv = { .of_match_table = of_match_clk_mt8192_img, }, }; - -builtin_platform_driver(clk_mt8192_img_drv); +module_platform_driver(clk_mt8192_img_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c index ff8e20bb44bb..6663b70a5d47 100644 --- a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c @@ -116,5 +116,4 @@ static struct platform_driver clk_mt8192_imp_iic_wrap_drv = { .of_match_table = of_match_clk_mt8192_imp_iic_wrap, }, }; - -builtin_platform_driver(clk_mt8192_imp_iic_wrap_drv); +module_platform_driver(clk_mt8192_imp_iic_wrap_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-ipe.c b/drivers/clk/mediatek/clk-mt8192-ipe.c index 0225abe4170a..6a8d3fb7e0c5 100644 --- a/drivers/clk/mediatek/clk-mt8192-ipe.c +++ b/drivers/clk/mediatek/clk-mt8192-ipe.c @@ -54,5 +54,4 @@ static struct platform_driver clk_mt8192_ipe_drv = { .of_match_table = of_match_clk_mt8192_ipe, }, }; - -builtin_platform_driver(clk_mt8192_ipe_drv); +module_platform_driver(clk_mt8192_ipe_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-mdp.c b/drivers/clk/mediatek/clk-mt8192-mdp.c index 4675788d7816..782f83fbe97b 100644 --- a/drivers/clk/mediatek/clk-mt8192-mdp.c +++ b/drivers/clk/mediatek/clk-mt8192-mdp.c @@ -79,5 +79,4 @@ static struct platform_driver clk_mt8192_mdp_drv = { .of_match_table = of_match_clk_mt8192_mdp, }, }; - -builtin_platform_driver(clk_mt8192_mdp_drv); +module_platform_driver(clk_mt8192_mdp_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-mfg.c b/drivers/clk/mediatek/clk-mt8192-mfg.c index ec5b44ffa458..c007e561f008 100644 --- a/drivers/clk/mediatek/clk-mt8192-mfg.c +++ b/drivers/clk/mediatek/clk-mt8192-mfg.c @@ -49,5 +49,4 @@ static struct platform_driver clk_mt8192_mfg_drv = { .of_match_table = of_match_clk_mt8192_mfg, }, }; - -builtin_platform_driver(clk_mt8192_mfg_drv); +module_platform_driver(clk_mt8192_mfg_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-mm.c b/drivers/clk/mediatek/clk-mt8192-mm.c index 638e6faae84c..184d7fb82abc 100644 --- a/drivers/clk/mediatek/clk-mt8192-mm.c +++ b/drivers/clk/mediatek/clk-mt8192-mm.c @@ -98,5 +98,4 @@ static struct platform_driver clk_mt8192_mm_drv = { }, .id_table = clk_mt8192_mm_id_table, }; - -builtin_platform_driver(clk_mt8192_mm_drv); +module_platform_driver(clk_mt8192_mm_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-msdc.c b/drivers/clk/mediatek/clk-mt8192-msdc.c index a72e1b73fce8..cb21a40dfe83 100644 --- a/drivers/clk/mediatek/clk-mt8192-msdc.c +++ b/drivers/clk/mediatek/clk-mt8192-msdc.c @@ -61,5 +61,4 @@ static struct platform_driver clk_mt8192_msdc_drv = { .of_match_table = of_match_clk_mt8192_msdc, }, }; - -builtin_platform_driver(clk_mt8192_msdc_drv); +module_platform_driver(clk_mt8192_msdc_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c index 18a8679108b8..b7aa68e6c555 100644 --- a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c @@ -47,5 +47,4 @@ static struct platform_driver clk_mt8192_scp_adsp_drv = { .of_match_table = of_match_clk_mt8192_scp_adsp, }, }; - -builtin_platform_driver(clk_mt8192_scp_adsp_drv); +module_platform_driver(clk_mt8192_scp_adsp_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-vdec.c b/drivers/clk/mediatek/clk-mt8192-vdec.c index e149962dbbf9..9ddc6e99c8d7 100644 --- a/drivers/clk/mediatek/clk-mt8192-vdec.c +++ b/drivers/clk/mediatek/clk-mt8192-vdec.c @@ -91,5 +91,4 @@ static struct platform_driver clk_mt8192_vdec_drv = { .of_match_table = of_match_clk_mt8192_vdec, }, }; - -builtin_platform_driver(clk_mt8192_vdec_drv); +module_platform_driver(clk_mt8192_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt8192-venc.c b/drivers/clk/mediatek/clk-mt8192-venc.c index 80b8bb170996..67136a341d77 100644 --- a/drivers/clk/mediatek/clk-mt8192-venc.c +++ b/drivers/clk/mediatek/clk-mt8192-venc.c @@ -50,5 +50,4 @@ static struct platform_driver clk_mt8192_venc_drv = { .of_match_table = of_match_clk_mt8192_venc, }, }; - -builtin_platform_driver(clk_mt8192_venc_drv); +module_platform_driver(clk_mt8192_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c index c0db31ce0741..29124ed9398b 100644 --- a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c @@ -230,4 +230,4 @@ static struct platform_driver clk_mt8195_apmixed_drv = { .of_match_table = of_match_clk_mt8195_apmixed, }, }; -builtin_platform_driver(clk_mt8195_apmixed_drv); +module_platform_driver(clk_mt8195_apmixed_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c index 0b52f6a009c4..ca60d90e5257 100644 --- a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c +++ b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c @@ -110,4 +110,4 @@ static struct platform_driver clk_mt8195_apusys_pll_drv = { .of_match_table = of_match_clk_mt8195_apusys_pll, }, }; -builtin_platform_driver(clk_mt8195_apusys_pll_drv); +module_platform_driver(clk_mt8195_apusys_pll_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-cam.c b/drivers/clk/mediatek/clk-mt8195-cam.c index e4d00fe6e757..c0fd32270a8e 100644 --- a/drivers/clk/mediatek/clk-mt8195-cam.c +++ b/drivers/clk/mediatek/clk-mt8195-cam.c @@ -140,4 +140,4 @@ static struct platform_driver clk_mt8195_cam_drv = { .of_match_table = of_match_clk_mt8195_cam, }, }; -builtin_platform_driver(clk_mt8195_cam_drv); +module_platform_driver(clk_mt8195_cam_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-ccu.c b/drivers/clk/mediatek/clk-mt8195-ccu.c index 4e326b6301ba..9e8220bcdf9f 100644 --- a/drivers/clk/mediatek/clk-mt8195-ccu.c +++ b/drivers/clk/mediatek/clk-mt8195-ccu.c @@ -48,4 +48,4 @@ static struct platform_driver clk_mt8195_ccu_drv = { .of_match_table = of_match_clk_mt8195_ccu, }, }; -builtin_platform_driver(clk_mt8195_ccu_drv); +module_platform_driver(clk_mt8195_ccu_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-img.c b/drivers/clk/mediatek/clk-mt8195-img.c index 12f5c436d075..822efce6f79b 100644 --- a/drivers/clk/mediatek/clk-mt8195-img.c +++ b/drivers/clk/mediatek/clk-mt8195-img.c @@ -94,4 +94,4 @@ static struct platform_driver clk_mt8195_img_drv = { .of_match_table = of_match_clk_mt8195_img, }, }; -builtin_platform_driver(clk_mt8195_img_drv); +module_platform_driver(clk_mt8195_img_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c index fbc809d05072..01f8fab27c22 100644 --- a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c @@ -64,4 +64,4 @@ static struct platform_driver clk_mt8195_imp_iic_wrap_drv = { .of_match_table = of_match_clk_mt8195_imp_iic_wrap, }, }; -builtin_platform_driver(clk_mt8195_imp_iic_wrap_drv); +module_platform_driver(clk_mt8195_imp_iic_wrap_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-infra_ao.c b/drivers/clk/mediatek/clk-mt8195-infra_ao.c index fcd410461d3b..75084251ea74 100644 --- a/drivers/clk/mediatek/clk-mt8195-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-infra_ao.c @@ -238,4 +238,4 @@ static struct platform_driver clk_mt8195_infra_ao_drv = { .of_match_table = of_match_clk_mt8195_infra_ao, }, }; -builtin_platform_driver(clk_mt8195_infra_ao_drv); +module_platform_driver(clk_mt8195_infra_ao_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-ipe.c b/drivers/clk/mediatek/clk-mt8195-ipe.c index b0d745cf7752..b713fea470dd 100644 --- a/drivers/clk/mediatek/clk-mt8195-ipe.c +++ b/drivers/clk/mediatek/clk-mt8195-ipe.c @@ -49,4 +49,4 @@ static struct platform_driver clk_mt8195_ipe_drv = { .of_match_table = of_match_clk_mt8195_ipe, }, }; -builtin_platform_driver(clk_mt8195_ipe_drv); +module_platform_driver(clk_mt8195_ipe_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-mfg.c b/drivers/clk/mediatek/clk-mt8195-mfg.c index c94cb71bd9b9..fcd2d0b7e3c9 100644 --- a/drivers/clk/mediatek/clk-mt8195-mfg.c +++ b/drivers/clk/mediatek/clk-mt8195-mfg.c @@ -47,4 +47,4 @@ static struct platform_driver clk_mt8195_mfg_drv = { .of_match_table = of_match_clk_mt8195_mfg, }, }; -builtin_platform_driver(clk_mt8195_mfg_drv); +module_platform_driver(clk_mt8195_mfg_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-peri_ao.c b/drivers/clk/mediatek/clk-mt8195-peri_ao.c index 2f6b3bb657db..f66fbea2e080 100644 --- a/drivers/clk/mediatek/clk-mt8195-peri_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-peri_ao.c @@ -60,4 +60,4 @@ static struct platform_driver clk_mt8195_peri_ao_drv = { .of_match_table = of_match_clk_mt8195_peri_ao, }, }; -builtin_platform_driver(clk_mt8195_peri_ao_drv); +module_platform_driver(clk_mt8195_peri_ao_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c index e16c383f631b..1987172c98a4 100644 --- a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c @@ -45,4 +45,4 @@ static struct platform_driver clk_mt8195_scp_adsp_drv = { .of_match_table = of_match_clk_mt8195_scp_adsp, }, }; -builtin_platform_driver(clk_mt8195_scp_adsp_drv); +module_platform_driver(clk_mt8195_scp_adsp_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index cf520f85de73..a9bb7e4687ec 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1340,4 +1340,4 @@ static struct platform_driver clk_mt8195_topck_drv = { .of_match_table = of_match_clk_mt8195_topck, }, }; -builtin_platform_driver(clk_mt8195_topck_drv); +module_platform_driver(clk_mt8195_topck_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vdec.c b/drivers/clk/mediatek/clk-mt8195-vdec.c index a1446b666385..a75ea99a9a4c 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdec.c +++ b/drivers/clk/mediatek/clk-mt8195-vdec.c @@ -102,4 +102,4 @@ static struct platform_driver clk_mt8195_vdec_drv = { .of_match_table = of_match_clk_mt8195_vdec, }, }; -builtin_platform_driver(clk_mt8195_vdec_drv); +module_platform_driver(clk_mt8195_vdec_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo0.c b/drivers/clk/mediatek/clk-mt8195-vdo0.c index 492c1e133d0d..1ed152b072bd 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo0.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo0.c @@ -102,6 +102,7 @@ static const struct platform_device_id clk_mt8195_vdo0_id_table[] = { { .name = "clk-mt8195-vdo0", .driver_data = (kernel_ulong_t)&vdo0_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8195_vdo0_id_table); static struct platform_driver clk_mt8195_vdo0_drv = { .probe = mtk_clk_pdev_probe, @@ -111,4 +112,4 @@ static struct platform_driver clk_mt8195_vdo0_drv = { }, .id_table = clk_mt8195_vdo0_id_table, }; -builtin_platform_driver(clk_mt8195_vdo0_drv); +module_platform_driver(clk_mt8195_vdo0_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo1.c b/drivers/clk/mediatek/clk-mt8195-vdo1.c index 76e9f4496e43..cbd0a34884c7 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo1.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo1.c @@ -129,6 +129,7 @@ static const struct platform_device_id clk_mt8195_vdo1_id_table[] = { { .name = "clk-mt8195-vdo1", .driver_data = (kernel_ulong_t)&vdo1_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8195_vdo1_id_table); static struct platform_driver clk_mt8195_vdo1_drv = { .probe = mtk_clk_pdev_probe, @@ -138,4 +139,4 @@ static struct platform_driver clk_mt8195_vdo1_drv = { }, .id_table = clk_mt8195_vdo1_id_table, }; -builtin_platform_driver(clk_mt8195_vdo1_drv); +module_platform_driver(clk_mt8195_vdo1_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-venc.c b/drivers/clk/mediatek/clk-mt8195-venc.c index 622f57804f96..8b46cbe9ce83 100644 --- a/drivers/clk/mediatek/clk-mt8195-venc.c +++ b/drivers/clk/mediatek/clk-mt8195-venc.c @@ -67,4 +67,4 @@ static struct platform_driver clk_mt8195_venc_drv = { .of_match_table = of_match_clk_mt8195_venc, }, }; -builtin_platform_driver(clk_mt8195_venc_drv); +module_platform_driver(clk_mt8195_venc_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp0.c b/drivers/clk/mediatek/clk-mt8195-vpp0.c index 15f1a081358a..ca1288b76990 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp0.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp0.c @@ -104,4 +104,4 @@ static struct platform_driver clk_mt8195_vpp0_drv = { }, .id_table = clk_mt8195_vpp0_id_table, }; -builtin_platform_driver(clk_mt8195_vpp0_drv); +module_platform_driver(clk_mt8195_vpp0_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp1.c b/drivers/clk/mediatek/clk-mt8195-vpp1.c index 794f21cf5e65..d9a260b6ee30 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp1.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp1.c @@ -102,4 +102,4 @@ static struct platform_driver clk_mt8195_vpp1_drv = { }, .id_table = clk_mt8195_vpp1_id_table, }; -builtin_platform_driver(clk_mt8195_vpp1_drv); +module_platform_driver(clk_mt8195_vpp1_drv); diff --git a/drivers/clk/mediatek/clk-mt8195-wpe.c b/drivers/clk/mediatek/clk-mt8195-wpe.c index b483fab10e18..8878b5ef9e44 100644 --- a/drivers/clk/mediatek/clk-mt8195-wpe.c +++ b/drivers/clk/mediatek/clk-mt8195-wpe.c @@ -141,4 +141,4 @@ static struct platform_driver clk_mt8195_wpe_drv = { .of_match_table = of_match_clk_mt8195_wpe, }, }; -builtin_platform_driver(clk_mt8195_wpe_drv); +module_platform_driver(clk_mt8195_wpe_drv); diff --git a/drivers/clk/mediatek/clk-mt8365-apu.c b/drivers/clk/mediatek/clk-mt8365-apu.c index 91ffe89d9721..5a594f8eccdc 100644 --- a/drivers/clk/mediatek/clk-mt8365-apu.c +++ b/drivers/clk/mediatek/clk-mt8365-apu.c @@ -51,5 +51,5 @@ static struct platform_driver clk_mt8365_apu_drv = { .of_match_table = of_match_clk_mt8365_apu, }, }; -builtin_platform_driver(clk_mt8365_apu_drv); +module_platform_driver(clk_mt8365_apu_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-cam.c b/drivers/clk/mediatek/clk-mt8365-cam.c index 31d5b5cd6de1..ed1d8dd7043c 100644 --- a/drivers/clk/mediatek/clk-mt8365-cam.c +++ b/drivers/clk/mediatek/clk-mt8365-cam.c @@ -53,5 +53,5 @@ static struct platform_driver clk_mt8365_cam_drv = { .of_match_table = of_match_clk_mt8365_cam, }, }; -builtin_platform_driver(clk_mt8365_cam_drv); +module_platform_driver(clk_mt8365_cam_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-mfg.c b/drivers/clk/mediatek/clk-mt8365-mfg.c index 587b49128b03..b3d10b017f0d 100644 --- a/drivers/clk/mediatek/clk-mt8365-mfg.c +++ b/drivers/clk/mediatek/clk-mt8365-mfg.c @@ -59,5 +59,5 @@ static struct platform_driver clk_mt8365_mfg_drv = { .of_match_table = of_match_clk_mt8365_mfg, }, }; -builtin_platform_driver(clk_mt8365_mfg_drv); +module_platform_driver(clk_mt8365_mfg_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 9569be54127c..7ae33997ba86 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -90,5 +90,5 @@ static struct platform_driver clk_mt8365_mm_drv = { }, .id_table = clk_mt8365_mm_id_table, }; -builtin_platform_driver(clk_mt8365_mm_drv); +module_platform_driver(clk_mt8365_mm_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-vdec.c b/drivers/clk/mediatek/clk-mt8365-vdec.c index cdc678e8941c..d5caddcc5932 100644 --- a/drivers/clk/mediatek/clk-mt8365-vdec.c +++ b/drivers/clk/mediatek/clk-mt8365-vdec.c @@ -59,5 +59,5 @@ static struct platform_driver clk_mt8365_vdec_drv = { .of_match_table = of_match_clk_mt8365_vdec, }, }; -builtin_platform_driver(clk_mt8365_vdec_drv); +module_platform_driver(clk_mt8365_vdec_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-venc.c b/drivers/clk/mediatek/clk-mt8365-venc.c index 0e080c22119d..08b7c0ee52e7 100644 --- a/drivers/clk/mediatek/clk-mt8365-venc.c +++ b/drivers/clk/mediatek/clk-mt8365-venc.c @@ -48,5 +48,5 @@ static struct platform_driver clk_mt8365_venc_drv = { .of_match_table = of_match_clk_mt8365_venc, }, }; -builtin_platform_driver(clk_mt8365_venc_drv); +module_platform_driver(clk_mt8365_venc_drv); MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8516-aud.c b/drivers/clk/mediatek/clk-mt8516-aud.c index 119dbbd0c3e0..5f34487aad7e 100644 --- a/drivers/clk/mediatek/clk-mt8516-aud.c +++ b/drivers/clk/mediatek/clk-mt8516-aud.c @@ -60,7 +60,7 @@ static struct platform_driver clk_mt8516_aud_drv = { .of_match_table = of_match_clk_mt8516_aud, }, }; -builtin_platform_driver(clk_mt8516_aud_drv); +module_platform_driver(clk_mt8516_aud_drv); MODULE_DESCRIPTION("MediaTek MT8516 audiosys clocks driver"); MODULE_LICENSE("GPL"); -- GitLab From a451da86cf6d10e94372d20622ec41aac9ec00b5 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:26 +0100 Subject: [PATCH 0380/5631] clk: mediatek: Add MODULE_LICENSE() where missing In order to successfully build clock drivers as modules it is required to declare a module license: add it where missing. While at it, also change the MODULE_LICENSE text from "GPL v2" to "GPL" (which means the same) on clk-mt7981-eth.c. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai # MT8183, MT8192, MT8195 Chromebooks Link: https://lore.kernel.org/r/20230306140543.1813621-38-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701-aud.c | 1 + drivers/clk/mediatek/clk-mt2701-bdp.c | 1 + drivers/clk/mediatek/clk-mt2701-eth.c | 1 + drivers/clk/mediatek/clk-mt2701-g3d.c | 1 + drivers/clk/mediatek/clk-mt2701-hif.c | 1 + drivers/clk/mediatek/clk-mt2701-img.c | 1 + drivers/clk/mediatek/clk-mt2701-mm.c | 1 + drivers/clk/mediatek/clk-mt2701-vdec.c | 1 + drivers/clk/mediatek/clk-mt2701.c | 1 + drivers/clk/mediatek/clk-mt2712-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt2712-bdp.c | 1 + drivers/clk/mediatek/clk-mt2712-img.c | 1 + drivers/clk/mediatek/clk-mt2712-jpgdec.c | 1 + drivers/clk/mediatek/clk-mt2712-mfg.c | 1 + drivers/clk/mediatek/clk-mt2712-mm.c | 1 + drivers/clk/mediatek/clk-mt2712-vdec.c | 1 + drivers/clk/mediatek/clk-mt2712-venc.c | 1 + drivers/clk/mediatek/clk-mt2712.c | 1 + drivers/clk/mediatek/clk-mt6765-audio.c | 1 + drivers/clk/mediatek/clk-mt6765-cam.c | 1 + drivers/clk/mediatek/clk-mt6765-img.c | 1 + drivers/clk/mediatek/clk-mt6765-mipi0a.c | 1 + drivers/clk/mediatek/clk-mt6765-mm.c | 1 + drivers/clk/mediatek/clk-mt6765-vcodec.c | 1 + drivers/clk/mediatek/clk-mt6765.c | 1 + drivers/clk/mediatek/clk-mt6797-img.c | 1 + drivers/clk/mediatek/clk-mt6797-mm.c | 1 + drivers/clk/mediatek/clk-mt6797-vdec.c | 1 + drivers/clk/mediatek/clk-mt6797-venc.c | 1 + drivers/clk/mediatek/clk-mt6797.c | 1 + drivers/clk/mediatek/clk-mt7622-aud.c | 1 + drivers/clk/mediatek/clk-mt7622-eth.c | 1 + drivers/clk/mediatek/clk-mt7622-hif.c | 1 + drivers/clk/mediatek/clk-mt7629-eth.c | 1 + drivers/clk/mediatek/clk-mt7629-hif.c | 1 + drivers/clk/mediatek/clk-mt7629.c | 1 + drivers/clk/mediatek/clk-mt7981-apmixed.c | 1 + drivers/clk/mediatek/clk-mt7981-eth.c | 2 +- drivers/clk/mediatek/clk-mt7981-infracfg.c | 1 + drivers/clk/mediatek/clk-mt7981-topckgen.c | 1 + drivers/clk/mediatek/clk-mt7986-apmixed.c | 1 + drivers/clk/mediatek/clk-mt7986-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8135.c | 1 + drivers/clk/mediatek/clk-mt8167-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8167-aud.c | 1 + drivers/clk/mediatek/clk-mt8167-img.c | 1 + drivers/clk/mediatek/clk-mt8167-mfgcfg.c | 1 + drivers/clk/mediatek/clk-mt8167-mm.c | 1 + drivers/clk/mediatek/clk-mt8167-vdec.c | 1 + drivers/clk/mediatek/clk-mt8167.c | 1 + drivers/clk/mediatek/clk-mt8183-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8183-audio.c | 1 + drivers/clk/mediatek/clk-mt8183-cam.c | 1 + drivers/clk/mediatek/clk-mt8183-img.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu0.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu1.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu_adl.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu_conn.c | 1 + drivers/clk/mediatek/clk-mt8183-mfgcfg.c | 1 + drivers/clk/mediatek/clk-mt8183-mm.c | 1 + drivers/clk/mediatek/clk-mt8183-vdec.c | 1 + drivers/clk/mediatek/clk-mt8183-venc.c | 1 + drivers/clk/mediatek/clk-mt8183.c | 1 + drivers/clk/mediatek/clk-mt8186-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8186-cam.c | 1 + drivers/clk/mediatek/clk-mt8186-img.c | 1 + drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8186-infra_ao.c | 1 + drivers/clk/mediatek/clk-mt8186-ipe.c | 1 + drivers/clk/mediatek/clk-mt8186-mdp.c | 1 + drivers/clk/mediatek/clk-mt8186-mfg.c | 1 + drivers/clk/mediatek/clk-mt8186-mm.c | 1 + drivers/clk/mediatek/clk-mt8186-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8186-vdec.c | 1 + drivers/clk/mediatek/clk-mt8186-venc.c | 1 + drivers/clk/mediatek/clk-mt8186-wpe.c | 1 + drivers/clk/mediatek/clk-mt8192-aud.c | 1 + drivers/clk/mediatek/clk-mt8192-cam.c | 1 + drivers/clk/mediatek/clk-mt8192-img.c | 1 + drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8192-ipe.c | 1 + drivers/clk/mediatek/clk-mt8192-mdp.c | 1 + drivers/clk/mediatek/clk-mt8192-mfg.c | 1 + drivers/clk/mediatek/clk-mt8192-mm.c | 1 + drivers/clk/mediatek/clk-mt8192-msdc.c | 1 + drivers/clk/mediatek/clk-mt8192-scp_adsp.c | 1 + drivers/clk/mediatek/clk-mt8192-vdec.c | 1 + drivers/clk/mediatek/clk-mt8192-venc.c | 1 + drivers/clk/mediatek/clk-mt8192.c | 1 + drivers/clk/mediatek/clk-mt8195-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8195-apusys_pll.c | 1 + drivers/clk/mediatek/clk-mt8195-cam.c | 1 + drivers/clk/mediatek/clk-mt8195-ccu.c | 1 + drivers/clk/mediatek/clk-mt8195-img.c | 1 + drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8195-infra_ao.c | 1 + drivers/clk/mediatek/clk-mt8195-ipe.c | 1 + drivers/clk/mediatek/clk-mt8195-mfg.c | 1 + drivers/clk/mediatek/clk-mt8195-peri_ao.c | 1 + drivers/clk/mediatek/clk-mt8195-scp_adsp.c | 1 + drivers/clk/mediatek/clk-mt8195-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8195-vdec.c | 1 + drivers/clk/mediatek/clk-mt8195-vdo0.c | 1 + drivers/clk/mediatek/clk-mt8195-vdo1.c | 1 + drivers/clk/mediatek/clk-mt8195-venc.c | 1 + drivers/clk/mediatek/clk-mt8195-vpp0.c | 1 + drivers/clk/mediatek/clk-mt8195-vpp1.c | 1 + drivers/clk/mediatek/clk-mt8195-wpe.c | 1 + drivers/clk/mediatek/clk-mt8365-apmixedsys.c | 1 + 109 files changed, 109 insertions(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index cff6c3b8896f..113ab5b0bf8d 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -164,3 +164,4 @@ static struct platform_driver clk_mt2701_aud_drv = { }, }; module_platform_driver(clk_mt2701_aud_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c index dad9a35e9310..e7b43329d305 100644 --- a/drivers/clk/mediatek/clk-mt2701-bdp.c +++ b/drivers/clk/mediatek/clk-mt2701-bdp.c @@ -105,3 +105,4 @@ static struct platform_driver clk_mt2701_bdp_drv = { }, }; module_platform_driver(clk_mt2701_bdp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-eth.c b/drivers/clk/mediatek/clk-mt2701-eth.c index 2c4781f9141a..d30567ac4ff1 100644 --- a/drivers/clk/mediatek/clk-mt2701-eth.c +++ b/drivers/clk/mediatek/clk-mt2701-eth.c @@ -59,3 +59,4 @@ static struct platform_driver clk_mt2701_eth_drv = { }, }; module_platform_driver(clk_mt2701_eth_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-g3d.c b/drivers/clk/mediatek/clk-mt2701-g3d.c index 2fed9f96d1e5..6f881eabdc67 100644 --- a/drivers/clk/mediatek/clk-mt2701-g3d.c +++ b/drivers/clk/mediatek/clk-mt2701-g3d.c @@ -58,3 +58,4 @@ static struct platform_driver clk_mt2701_g3d_drv = { }, }; module_platform_driver(clk_mt2701_g3d_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-hif.c b/drivers/clk/mediatek/clk-mt2701-hif.c index ac47a20047da..b2ee73c4de4e 100644 --- a/drivers/clk/mediatek/clk-mt2701-hif.c +++ b/drivers/clk/mediatek/clk-mt2701-hif.c @@ -56,3 +56,4 @@ static struct platform_driver clk_mt2701_hif_drv = { }, }; module_platform_driver(clk_mt2701_hif_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c index 776f470623ca..35a5fd938a6e 100644 --- a/drivers/clk/mediatek/clk-mt2701-img.c +++ b/drivers/clk/mediatek/clk-mt2701-img.c @@ -53,3 +53,4 @@ static struct platform_driver clk_mt2701_img_drv = { }, }; module_platform_driver(clk_mt2701_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index f23208b8dcba..75611d0ab865 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -86,3 +86,4 @@ static struct platform_driver clk_mt2701_mm_drv = { .id_table = clk_mt2701_mm_id_table, }; module_platform_driver(clk_mt2701_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c index 57e7020aaab5..dca4335a52a7 100644 --- a/drivers/clk/mediatek/clk-mt2701-vdec.c +++ b/drivers/clk/mediatek/clk-mt2701-vdec.c @@ -58,3 +58,4 @@ static struct platform_driver clk_mt2701_vdec_drv = { }, }; module_platform_driver(clk_mt2701_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index e9c27b1364b6..d3097d9f0c7a 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -1032,3 +1032,4 @@ static int __init clk_mt2701_init(void) } arch_initcall(clk_mt2701_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c index 2f4061c9a59e..eade747d2812 100644 --- a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c @@ -164,3 +164,4 @@ static struct platform_driver clk_mt2712_apmixed_drv = { }, }; module_platform_driver(clk_mt2712_apmixed_drv) +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-bdp.c b/drivers/clk/mediatek/clk-mt2712-bdp.c index 5324544039b3..d4979f2fb1d3 100644 --- a/drivers/clk/mediatek/clk-mt2712-bdp.c +++ b/drivers/clk/mediatek/clk-mt2712-bdp.c @@ -75,3 +75,4 @@ static struct platform_driver clk_mt2712_bdp_drv = { }, }; module_platform_driver(clk_mt2712_bdp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-img.c b/drivers/clk/mediatek/clk-mt2712-img.c index c16453c6b421..cd2d2af6bd56 100644 --- a/drivers/clk/mediatek/clk-mt2712-img.c +++ b/drivers/clk/mediatek/clk-mt2712-img.c @@ -53,3 +53,4 @@ static struct platform_driver clk_mt2712_img_drv = { }, }; module_platform_driver(clk_mt2712_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-jpgdec.c b/drivers/clk/mediatek/clk-mt2712-jpgdec.c index c1363eb5d893..815be759e7c9 100644 --- a/drivers/clk/mediatek/clk-mt2712-jpgdec.c +++ b/drivers/clk/mediatek/clk-mt2712-jpgdec.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt2712_jpgdec_drv = { }, }; module_platform_driver(clk_mt2712_jpgdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-mfg.c b/drivers/clk/mediatek/clk-mt2712-mfg.c index d91d788babcf..9f958fadca86 100644 --- a/drivers/clk/mediatek/clk-mt2712-mfg.c +++ b/drivers/clk/mediatek/clk-mt2712-mfg.c @@ -48,3 +48,4 @@ static struct platform_driver clk_mt2712_mfg_drv = { }, }; module_platform_driver(clk_mt2712_mfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index 6245b79bab90..2649d67f2a56 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -127,3 +127,4 @@ static struct platform_driver clk_mt2712_mm_drv = { .id_table = clk_mt2712_mm_id_table, }; module_platform_driver(clk_mt2712_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-vdec.c b/drivers/clk/mediatek/clk-mt2712-vdec.c index 1d3e65f60808..1cb150fa7ab4 100644 --- a/drivers/clk/mediatek/clk-mt2712-vdec.c +++ b/drivers/clk/mediatek/clk-mt2712-vdec.c @@ -61,3 +61,4 @@ static struct platform_driver clk_mt2712_vdec_drv = { }, }; module_platform_driver(clk_mt2712_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712-venc.c b/drivers/clk/mediatek/clk-mt2712-venc.c index 09f2683f0f13..4073fa6c040f 100644 --- a/drivers/clk/mediatek/clk-mt2712-venc.c +++ b/drivers/clk/mediatek/clk-mt2712-venc.c @@ -50,3 +50,4 @@ static struct platform_driver clk_mt2712_venc_drv = { }, }; module_platform_driver(clk_mt2712_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index d0e6a4fbfa99..b2cf91622ebf 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -1001,3 +1001,4 @@ static struct platform_driver clk_mt2712_drv = { }, }; module_platform_driver(clk_mt2712_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-audio.c b/drivers/clk/mediatek/clk-mt6765-audio.c index 712e0da78b4b..c1fecf22f8ad 100644 --- a/drivers/clk/mediatek/clk-mt6765-audio.c +++ b/drivers/clk/mediatek/clk-mt6765-audio.c @@ -75,3 +75,4 @@ static struct platform_driver clk_mt6765_audio_drv = { }, }; module_platform_driver(clk_mt6765_audio_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-cam.c b/drivers/clk/mediatek/clk-mt6765-cam.c index 0581a1f3971e..15737c8f6b69 100644 --- a/drivers/clk/mediatek/clk-mt6765-cam.c +++ b/drivers/clk/mediatek/clk-mt6765-cam.c @@ -56,3 +56,4 @@ static struct platform_driver clk_mt6765_cam_drv = { }, }; module_platform_driver(clk_mt6765_cam_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-img.c b/drivers/clk/mediatek/clk-mt6765-img.c index 7c605dc155eb..7e421f4d01b8 100644 --- a/drivers/clk/mediatek/clk-mt6765-img.c +++ b/drivers/clk/mediatek/clk-mt6765-img.c @@ -52,3 +52,4 @@ static struct platform_driver clk_mt6765_img_drv = { }, }; module_platform_driver(clk_mt6765_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-mipi0a.c b/drivers/clk/mediatek/clk-mt6765-mipi0a.c index b299db047138..17186a308e94 100644 --- a/drivers/clk/mediatek/clk-mt6765-mipi0a.c +++ b/drivers/clk/mediatek/clk-mt6765-mipi0a.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt6765_mipi0a_drv = { }, }; module_platform_driver(clk_mt6765_mipi0a_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-mm.c b/drivers/clk/mediatek/clk-mt6765-mm.c index ec2b287cf1a3..af2213db17cb 100644 --- a/drivers/clk/mediatek/clk-mt6765-mm.c +++ b/drivers/clk/mediatek/clk-mt6765-mm.c @@ -78,3 +78,4 @@ static struct platform_driver clk_mt6765_mm_drv = { }, }; module_platform_driver(clk_mt6765_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765-vcodec.c b/drivers/clk/mediatek/clk-mt6765-vcodec.c index 17355923325e..48014cc71d9f 100644 --- a/drivers/clk/mediatek/clk-mt6765-vcodec.c +++ b/drivers/clk/mediatek/clk-mt6765-vcodec.c @@ -51,3 +51,4 @@ static struct platform_driver clk_mt6765_vcodec_drv = { }, }; module_platform_driver(clk_mt6765_vcodec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6765.c b/drivers/clk/mediatek/clk-mt6765.c index 0c20ce678350..61f93b6fdf8b 100644 --- a/drivers/clk/mediatek/clk-mt6765.c +++ b/drivers/clk/mediatek/clk-mt6765.c @@ -873,3 +873,4 @@ static int __init clk_mt6765_init(void) } arch_initcall(clk_mt6765_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6797-img.c b/drivers/clk/mediatek/clk-mt6797-img.c index d46a3a3ac3ad..22779829370f 100644 --- a/drivers/clk/mediatek/clk-mt6797-img.c +++ b/drivers/clk/mediatek/clk-mt6797-img.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt6797_img_drv = { }, }; module_platform_driver(clk_mt6797_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index 899a0e6fa988..8722fae10de9 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -99,3 +99,4 @@ static struct platform_driver clk_mt6797_mm_drv = { .id_table = clk_mt6797_mm_id_table, }; module_platform_driver(clk_mt6797_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6797-vdec.c b/drivers/clk/mediatek/clk-mt6797-vdec.c index f2b979b1ea19..c5a82d4a958b 100644 --- a/drivers/clk/mediatek/clk-mt6797-vdec.c +++ b/drivers/clk/mediatek/clk-mt6797-vdec.c @@ -60,3 +60,4 @@ static struct platform_driver clk_mt6797_vdec_drv = { }, }; module_platform_driver(clk_mt6797_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6797-venc.c b/drivers/clk/mediatek/clk-mt6797-venc.c index 9fbf4cd5160e..afdd288d313a 100644 --- a/drivers/clk/mediatek/clk-mt6797-venc.c +++ b/drivers/clk/mediatek/clk-mt6797-venc.c @@ -51,3 +51,4 @@ static struct platform_driver clk_mt6797_venc_drv = { }, }; module_platform_driver(clk_mt6797_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt6797.c b/drivers/clk/mediatek/clk-mt6797.c index 17b23ee4faee..4094fd75d16e 100644 --- a/drivers/clk/mediatek/clk-mt6797.c +++ b/drivers/clk/mediatek/clk-mt6797.c @@ -703,3 +703,4 @@ static int __init clk_mt6797_init(void) } arch_initcall(clk_mt6797_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7622-aud.c b/drivers/clk/mediatek/clk-mt7622-aud.c index 7cca52693a3f..4e14a4ff465a 100644 --- a/drivers/clk/mediatek/clk-mt7622-aud.c +++ b/drivers/clk/mediatek/clk-mt7622-aud.c @@ -155,3 +155,4 @@ static struct platform_driver clk_mt7622_aud_drv = { }, }; module_platform_driver(clk_mt7622_aud_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7622-eth.c b/drivers/clk/mediatek/clk-mt7622-eth.c index 89e68c836d40..4475d0846176 100644 --- a/drivers/clk/mediatek/clk-mt7622-eth.c +++ b/drivers/clk/mediatek/clk-mt7622-eth.c @@ -87,3 +87,4 @@ static struct platform_driver clk_mt7622_eth_drv = { }, }; module_platform_driver(clk_mt7622_eth_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7622-hif.c b/drivers/clk/mediatek/clk-mt7622-hif.c index 06ade985dfe2..19f394af1132 100644 --- a/drivers/clk/mediatek/clk-mt7622-hif.c +++ b/drivers/clk/mediatek/clk-mt7622-hif.c @@ -99,3 +99,4 @@ static struct platform_driver clk_mt7622_hif_drv = { }, }; module_platform_driver(clk_mt7622_hif_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7629-eth.c b/drivers/clk/mediatek/clk-mt7629-eth.c index 719a47fef798..ee84a3de7f2c 100644 --- a/drivers/clk/mediatek/clk-mt7629-eth.c +++ b/drivers/clk/mediatek/clk-mt7629-eth.c @@ -154,3 +154,4 @@ static struct platform_driver clk_mt7629_eth_drv = { }; builtin_platform_driver(clk_mt7629_eth_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7629-hif.c b/drivers/clk/mediatek/clk-mt7629-hif.c index 79bcd91386fc..464c4131d98a 100644 --- a/drivers/clk/mediatek/clk-mt7629-hif.c +++ b/drivers/clk/mediatek/clk-mt7629-hif.c @@ -94,3 +94,4 @@ static struct platform_driver clk_mt7629_hif_drv = { }, }; module_platform_driver(clk_mt7629_hif_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7629.c b/drivers/clk/mediatek/clk-mt7629.c index 09c85fda43d8..f3279f002e93 100644 --- a/drivers/clk/mediatek/clk-mt7629.c +++ b/drivers/clk/mediatek/clk-mt7629.c @@ -693,3 +693,4 @@ static int clk_mt7629_init(void) } arch_initcall(clk_mt7629_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7981-apmixed.c b/drivers/clk/mediatek/clk-mt7981-apmixed.c index 52b7123232bf..53c974c66f89 100644 --- a/drivers/clk/mediatek/clk-mt7981-apmixed.c +++ b/drivers/clk/mediatek/clk-mt7981-apmixed.c @@ -100,3 +100,4 @@ static struct platform_driver clk_mt7981_apmixed_drv = { }, }; builtin_platform_driver(clk_mt7981_apmixed_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7981-eth.c b/drivers/clk/mediatek/clk-mt7981-eth.c index 773350911be2..f27fadd6bf94 100644 --- a/drivers/clk/mediatek/clk-mt7981-eth.c +++ b/drivers/clk/mediatek/clk-mt7981-eth.c @@ -115,4 +115,4 @@ static struct platform_driver clk_mt7981_eth_drv = { }, }; module_platform_driver(clk_mt7981_eth_drv); -MODULE_LICENSE("GPL v2"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7981-infracfg.c b/drivers/clk/mediatek/clk-mt7981-infracfg.c index 35cd126408b6..d1709323d34e 100644 --- a/drivers/clk/mediatek/clk-mt7981-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7981-infracfg.c @@ -205,3 +205,4 @@ static struct platform_driver clk_mt7981_infracfg_drv = { }, }; module_platform_driver(clk_mt7981_infracfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7981-topckgen.c b/drivers/clk/mediatek/clk-mt7981-topckgen.c index f4c31cb1c74e..e09ffc22b13a 100644 --- a/drivers/clk/mediatek/clk-mt7981-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7981-topckgen.c @@ -420,3 +420,4 @@ static struct platform_driver clk_mt7981_topckgen_drv = { }, }; module_platform_driver(clk_mt7981_topckgen_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7986-apmixed.c b/drivers/clk/mediatek/clk-mt7986-apmixed.c index 227ca572056e..dc949ed1b587 100644 --- a/drivers/clk/mediatek/clk-mt7986-apmixed.c +++ b/drivers/clk/mediatek/clk-mt7986-apmixed.c @@ -98,3 +98,4 @@ static struct platform_driver clk_mt7986_apmixed_drv = { }, }; builtin_platform_driver(clk_mt7986_apmixed_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt7986-topckgen.c b/drivers/clk/mediatek/clk-mt7986-topckgen.c index dacaf5492286..af9df453d6d7 100644 --- a/drivers/clk/mediatek/clk-mt7986-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7986-topckgen.c @@ -314,3 +314,4 @@ static struct platform_driver clk_mt7986_topckgen_drv = { }, }; module_platform_driver(clk_mt7986_topckgen_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 97a115d2c3da..98165b1f7c97 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -638,3 +638,4 @@ static void __init mtk_apmixedsys_init(struct device_node *node) } CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8135-apmixedsys", mtk_apmixedsys_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c index 27597fdeb6e9..5d8b5093ed02 100644 --- a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c @@ -141,3 +141,4 @@ static struct platform_driver clk_mt8167_apmixed_drv = { }, }; builtin_platform_driver(clk_mt8167_apmixed_drv) +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index 8869c53da79c..63736642f383 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -62,3 +62,4 @@ static struct platform_driver clk_mt8167_audsys_drv = { }, }; module_platform_driver(clk_mt8167_audsys_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index 6a068f2a9dce..c2537e149aa8 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -54,3 +54,4 @@ static struct platform_driver clk_mt8167_imgsys_drv = { }, }; module_platform_driver(clk_mt8167_imgsys_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 7fcb944134b6..340c608e7ddb 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -52,3 +52,4 @@ static struct platform_driver clk_mt8167_mfgcfg_drv = { }, }; module_platform_driver(clk_mt8167_mfgcfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index de6c2283b695..0344f9c98d36 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -93,3 +93,4 @@ static struct platform_driver clk_mt8167_mm_drv = { .id_table = clk_mt8167_mm_id_table, }; module_platform_driver(clk_mt8167_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index b3eccc2eca58..35b0380f22dc 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -61,3 +61,4 @@ static struct platform_driver clk_mt8167_vdec_drv = { }, }; module_platform_driver(clk_mt8167_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index 507e1ebe3ba8..d9a837686865 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -893,3 +893,4 @@ static struct platform_driver clk_mt8167_drv = { }, }; module_platform_driver(clk_mt8167_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-apmixedsys.c b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c index e66e90163bb4..5addda17211f 100644 --- a/drivers/clk/mediatek/clk-mt8183-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c @@ -191,3 +191,4 @@ static struct platform_driver clk_mt8183_apmixed_drv = { }, }; builtin_platform_driver(clk_mt8183_apmixed_drv) +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-audio.c b/drivers/clk/mediatek/clk-mt8183-audio.c index 24cc2178c769..fe510f02dadb 100644 --- a/drivers/clk/mediatek/clk-mt8183-audio.c +++ b/drivers/clk/mediatek/clk-mt8183-audio.c @@ -107,3 +107,4 @@ static struct platform_driver clk_mt8183_audio_drv = { }, }; module_platform_driver(clk_mt8183_audio_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-cam.c b/drivers/clk/mediatek/clk-mt8183-cam.c index 7ff183da0075..7ecbfc50e8fe 100644 --- a/drivers/clk/mediatek/clk-mt8183-cam.c +++ b/drivers/clk/mediatek/clk-mt8183-cam.c @@ -57,3 +57,4 @@ static struct platform_driver clk_mt8183_cam_drv = { }, }; module_platform_driver(clk_mt8183_cam_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-img.c b/drivers/clk/mediatek/clk-mt8183-img.c index e4a9d3201e33..e75d6e6205f9 100644 --- a/drivers/clk/mediatek/clk-mt8183-img.c +++ b/drivers/clk/mediatek/clk-mt8183-img.c @@ -57,3 +57,4 @@ static struct platform_driver clk_mt8183_img_drv = { }, }; module_platform_driver(clk_mt8183_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu0.c b/drivers/clk/mediatek/clk-mt8183-ipu0.c index 68d4cda89d6f..d1dd76e7eafd 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu0.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu0.c @@ -50,3 +50,4 @@ static struct platform_driver clk_mt8183_ipu_core0_drv = { }, }; module_platform_driver(clk_mt8183_ipu_core0_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu1.c b/drivers/clk/mediatek/clk-mt8183-ipu1.c index 50950bed9226..0b4906cca119 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu1.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu1.c @@ -50,3 +50,4 @@ static struct platform_driver clk_mt8183_ipu_core1_drv = { }, }; module_platform_driver(clk_mt8183_ipu_core1_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c index 2044d5c664b8..32a82ec965ef 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c @@ -48,3 +48,4 @@ static struct platform_driver clk_mt8183_ipu_adl_drv = { }, }; module_platform_driver(clk_mt8183_ipu_adl_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c index 6e7833656c9a..1e2ebc0eab8b 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c @@ -117,3 +117,4 @@ static struct platform_driver clk_mt8183_ipu_conn_drv = { }, }; module_platform_driver(clk_mt8183_ipu_conn_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c index 5a71ef094e03..20cdbd74817f 100644 --- a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt8183_mfg_drv = { }, }; module_platform_driver(clk_mt8183_mfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-mm.c b/drivers/clk/mediatek/clk-mt8183-mm.c index 25a04f311dc3..a76e44ebf322 100644 --- a/drivers/clk/mediatek/clk-mt8183-mm.c +++ b/drivers/clk/mediatek/clk-mt8183-mm.c @@ -101,3 +101,4 @@ static struct platform_driver clk_mt8183_mm_drv = { .id_table = clk_mt8183_mm_id_table, }; module_platform_driver(clk_mt8183_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-vdec.c b/drivers/clk/mediatek/clk-mt8183-vdec.c index 4c56d02a9d34..0182745e2a18 100644 --- a/drivers/clk/mediatek/clk-mt8183-vdec.c +++ b/drivers/clk/mediatek/clk-mt8183-vdec.c @@ -61,3 +61,4 @@ static struct platform_driver clk_mt8183_vdec_drv = { }, }; module_platform_driver(clk_mt8183_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183-venc.c b/drivers/clk/mediatek/clk-mt8183-venc.c index 5b86d7d42613..c840e6ebe375 100644 --- a/drivers/clk/mediatek/clk-mt8183-venc.c +++ b/drivers/clk/mediatek/clk-mt8183-venc.c @@ -53,3 +53,4 @@ static struct platform_driver clk_mt8183_venc_drv = { }, }; module_platform_driver(clk_mt8183_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 02176ee97cd2..5ae0f1f9ca0a 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -878,3 +878,4 @@ static struct platform_driver clk_mt8183_drv = { }, }; module_platform_driver(clk_mt8183_drv) +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c index ab500b985900..e429d2cdc84a 100644 --- a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c @@ -193,3 +193,4 @@ static struct platform_driver clk_mt8186_apmixed_drv = { }, }; module_platform_driver(clk_mt8186_apmixed_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-cam.c b/drivers/clk/mediatek/clk-mt8186-cam.c index 220c8af7848e..90d91d045909 100644 --- a/drivers/clk/mediatek/clk-mt8186-cam.c +++ b/drivers/clk/mediatek/clk-mt8186-cam.c @@ -88,3 +88,4 @@ static struct platform_driver clk_mt8186_cam_drv = { }, }; module_platform_driver(clk_mt8186_cam_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-img.c b/drivers/clk/mediatek/clk-mt8186-img.c index bac0e52bd51c..11314dba4e41 100644 --- a/drivers/clk/mediatek/clk-mt8186-img.c +++ b/drivers/clk/mediatek/clk-mt8186-img.c @@ -66,3 +66,4 @@ static struct platform_driver clk_mt8186_img_drv = { }, }; module_platform_driver(clk_mt8186_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c index 9301dc3e86fb..f8d1ee294f09 100644 --- a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c @@ -65,3 +65,4 @@ static struct platform_driver clk_mt8186_imp_iic_wrap_drv = { }, }; module_platform_driver(clk_mt8186_imp_iic_wrap_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-infra_ao.c b/drivers/clk/mediatek/clk-mt8186-infra_ao.c index e705d57032a6..766c8e6bcf8d 100644 --- a/drivers/clk/mediatek/clk-mt8186-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8186-infra_ao.c @@ -237,3 +237,4 @@ static struct platform_driver clk_mt8186_infra_ao_drv = { }, }; module_platform_driver(clk_mt8186_infra_ao_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-ipe.c b/drivers/clk/mediatek/clk-mt8186-ipe.c index 36f6338f8237..0876440839df 100644 --- a/drivers/clk/mediatek/clk-mt8186-ipe.c +++ b/drivers/clk/mediatek/clk-mt8186-ipe.c @@ -53,3 +53,4 @@ static struct platform_driver clk_mt8186_ipe_drv = { }, }; module_platform_driver(clk_mt8186_ipe_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-mdp.c b/drivers/clk/mediatek/clk-mt8186-mdp.c index faf5cdc7523f..194f20f16f8c 100644 --- a/drivers/clk/mediatek/clk-mt8186-mdp.c +++ b/drivers/clk/mediatek/clk-mt8186-mdp.c @@ -78,3 +78,4 @@ static struct platform_driver clk_mt8186_mdp_drv = { }, }; module_platform_driver(clk_mt8186_mdp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-mfg.c b/drivers/clk/mediatek/clk-mt8186-mfg.c index 468fa7e37074..f16d3c44ef41 100644 --- a/drivers/clk/mediatek/clk-mt8186-mfg.c +++ b/drivers/clk/mediatek/clk-mt8186-mfg.c @@ -47,3 +47,4 @@ static struct platform_driver clk_mt8186_mfg_drv = { }, }; module_platform_driver(clk_mt8186_mfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-mm.c b/drivers/clk/mediatek/clk-mt8186-mm.c index 03dfb4d99930..9e9853a2ea91 100644 --- a/drivers/clk/mediatek/clk-mt8186-mm.c +++ b/drivers/clk/mediatek/clk-mt8186-mm.c @@ -76,3 +76,4 @@ static struct platform_driver clk_mt8186_mm_drv = { .id_table = clk_mt8186_mm_id_table, }; module_platform_driver(clk_mt8186_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-topckgen.c b/drivers/clk/mediatek/clk-mt8186-topckgen.c index 7f2a59347166..a48172d9c5ab 100644 --- a/drivers/clk/mediatek/clk-mt8186-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8186-topckgen.c @@ -731,3 +731,4 @@ static struct platform_driver clk_mt8186_topck_drv = { }, }; module_platform_driver(clk_mt8186_topck_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-vdec.c b/drivers/clk/mediatek/clk-mt8186-vdec.c index 76e226be8f72..877ca9d8ff65 100644 --- a/drivers/clk/mediatek/clk-mt8186-vdec.c +++ b/drivers/clk/mediatek/clk-mt8186-vdec.c @@ -86,3 +86,4 @@ static struct platform_driver clk_mt8186_vdec_drv = { }, }; module_platform_driver(clk_mt8186_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-venc.c b/drivers/clk/mediatek/clk-mt8186-venc.c index 96c15b859e37..a89e82285d4c 100644 --- a/drivers/clk/mediatek/clk-mt8186-venc.c +++ b/drivers/clk/mediatek/clk-mt8186-venc.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt8186_venc_drv = { }, }; module_platform_driver(clk_mt8186_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8186-wpe.c b/drivers/clk/mediatek/clk-mt8186-wpe.c index dbd8a81b170d..fba55f08129c 100644 --- a/drivers/clk/mediatek/clk-mt8186-wpe.c +++ b/drivers/clk/mediatek/clk-mt8186-wpe.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt8186_wpe_drv = { }, }; module_platform_driver(clk_mt8186_wpe_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-aud.c b/drivers/clk/mediatek/clk-mt8192-aud.c index deb292cc9da1..9b14d8514b4f 100644 --- a/drivers/clk/mediatek/clk-mt8192-aud.c +++ b/drivers/clk/mediatek/clk-mt8192-aud.c @@ -117,3 +117,4 @@ static struct platform_driver clk_mt8192_aud_drv = { }, }; module_platform_driver(clk_mt8192_aud_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-cam.c b/drivers/clk/mediatek/clk-mt8192-cam.c index 00dbd0d27fbc..321693aff33f 100644 --- a/drivers/clk/mediatek/clk-mt8192-cam.c +++ b/drivers/clk/mediatek/clk-mt8192-cam.c @@ -105,3 +105,4 @@ static struct platform_driver clk_mt8192_cam_drv = { }, }; module_platform_driver(clk_mt8192_cam_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-img.c b/drivers/clk/mediatek/clk-mt8192-img.c index 00abbec6c666..b2c148ead7f8 100644 --- a/drivers/clk/mediatek/clk-mt8192-img.c +++ b/drivers/clk/mediatek/clk-mt8192-img.c @@ -68,3 +68,4 @@ static struct platform_driver clk_mt8192_img_drv = { }, }; module_platform_driver(clk_mt8192_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c index 6663b70a5d47..fd731eb6d62e 100644 --- a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c @@ -117,3 +117,4 @@ static struct platform_driver clk_mt8192_imp_iic_wrap_drv = { }, }; module_platform_driver(clk_mt8192_imp_iic_wrap_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-ipe.c b/drivers/clk/mediatek/clk-mt8192-ipe.c index 6a8d3fb7e0c5..3fd37977ea16 100644 --- a/drivers/clk/mediatek/clk-mt8192-ipe.c +++ b/drivers/clk/mediatek/clk-mt8192-ipe.c @@ -55,3 +55,4 @@ static struct platform_driver clk_mt8192_ipe_drv = { }, }; module_platform_driver(clk_mt8192_ipe_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-mdp.c b/drivers/clk/mediatek/clk-mt8192-mdp.c index 782f83fbe97b..817e8bf4543b 100644 --- a/drivers/clk/mediatek/clk-mt8192-mdp.c +++ b/drivers/clk/mediatek/clk-mt8192-mdp.c @@ -80,3 +80,4 @@ static struct platform_driver clk_mt8192_mdp_drv = { }, }; module_platform_driver(clk_mt8192_mdp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-mfg.c b/drivers/clk/mediatek/clk-mt8192-mfg.c index c007e561f008..7f77e2d8b765 100644 --- a/drivers/clk/mediatek/clk-mt8192-mfg.c +++ b/drivers/clk/mediatek/clk-mt8192-mfg.c @@ -50,3 +50,4 @@ static struct platform_driver clk_mt8192_mfg_drv = { }, }; module_platform_driver(clk_mt8192_mfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-mm.c b/drivers/clk/mediatek/clk-mt8192-mm.c index 184d7fb82abc..3e81018a038b 100644 --- a/drivers/clk/mediatek/clk-mt8192-mm.c +++ b/drivers/clk/mediatek/clk-mt8192-mm.c @@ -99,3 +99,4 @@ static struct platform_driver clk_mt8192_mm_drv = { .id_table = clk_mt8192_mm_id_table, }; module_platform_driver(clk_mt8192_mm_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-msdc.c b/drivers/clk/mediatek/clk-mt8192-msdc.c index cb21a40dfe83..cde8c88673e4 100644 --- a/drivers/clk/mediatek/clk-mt8192-msdc.c +++ b/drivers/clk/mediatek/clk-mt8192-msdc.c @@ -62,3 +62,4 @@ static struct platform_driver clk_mt8192_msdc_drv = { }, }; module_platform_driver(clk_mt8192_msdc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c index b7aa68e6c555..df086b95d447 100644 --- a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c @@ -48,3 +48,4 @@ static struct platform_driver clk_mt8192_scp_adsp_drv = { }, }; module_platform_driver(clk_mt8192_scp_adsp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-vdec.c b/drivers/clk/mediatek/clk-mt8192-vdec.c index 9ddc6e99c8d7..2ea8b6d4d405 100644 --- a/drivers/clk/mediatek/clk-mt8192-vdec.c +++ b/drivers/clk/mediatek/clk-mt8192-vdec.c @@ -92,3 +92,4 @@ static struct platform_driver clk_mt8192_vdec_drv = { }, }; module_platform_driver(clk_mt8192_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192-venc.c b/drivers/clk/mediatek/clk-mt8192-venc.c index 67136a341d77..d73c12bc2ae9 100644 --- a/drivers/clk/mediatek/clk-mt8192-venc.c +++ b/drivers/clk/mediatek/clk-mt8192-venc.c @@ -51,3 +51,4 @@ static struct platform_driver clk_mt8192_venc_drv = { }, }; module_platform_driver(clk_mt8192_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c index 0f9f10172148..35afe496b1c1 100644 --- a/drivers/clk/mediatek/clk-mt8192.c +++ b/drivers/clk/mediatek/clk-mt8192.c @@ -1242,3 +1242,4 @@ static int __init clk_mt8192_init(void) } arch_initcall(clk_mt8192_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c index 29124ed9398b..75cc4d7a39f9 100644 --- a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c @@ -231,3 +231,4 @@ static struct platform_driver clk_mt8195_apmixed_drv = { }, }; module_platform_driver(clk_mt8195_apmixed_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c index ca60d90e5257..b167b8d31bcc 100644 --- a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c +++ b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c @@ -111,3 +111,4 @@ static struct platform_driver clk_mt8195_apusys_pll_drv = { }, }; module_platform_driver(clk_mt8195_apusys_pll_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-cam.c b/drivers/clk/mediatek/clk-mt8195-cam.c index c0fd32270a8e..c515650214bd 100644 --- a/drivers/clk/mediatek/clk-mt8195-cam.c +++ b/drivers/clk/mediatek/clk-mt8195-cam.c @@ -141,3 +141,4 @@ static struct platform_driver clk_mt8195_cam_drv = { }, }; module_platform_driver(clk_mt8195_cam_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-ccu.c b/drivers/clk/mediatek/clk-mt8195-ccu.c index 9e8220bcdf9f..a86f848a785d 100644 --- a/drivers/clk/mediatek/clk-mt8195-ccu.c +++ b/drivers/clk/mediatek/clk-mt8195-ccu.c @@ -49,3 +49,4 @@ static struct platform_driver clk_mt8195_ccu_drv = { }, }; module_platform_driver(clk_mt8195_ccu_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-img.c b/drivers/clk/mediatek/clk-mt8195-img.c index 822efce6f79b..214baa2bc974 100644 --- a/drivers/clk/mediatek/clk-mt8195-img.c +++ b/drivers/clk/mediatek/clk-mt8195-img.c @@ -95,3 +95,4 @@ static struct platform_driver clk_mt8195_img_drv = { }, }; module_platform_driver(clk_mt8195_img_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c index 01f8fab27c22..191f482186ae 100644 --- a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c @@ -65,3 +65,4 @@ static struct platform_driver clk_mt8195_imp_iic_wrap_drv = { }, }; module_platform_driver(clk_mt8195_imp_iic_wrap_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-infra_ao.c b/drivers/clk/mediatek/clk-mt8195-infra_ao.c index 75084251ea74..6ad72a320d5e 100644 --- a/drivers/clk/mediatek/clk-mt8195-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-infra_ao.c @@ -239,3 +239,4 @@ static struct platform_driver clk_mt8195_infra_ao_drv = { }, }; module_platform_driver(clk_mt8195_infra_ao_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-ipe.c b/drivers/clk/mediatek/clk-mt8195-ipe.c index b713fea470dd..b547a99b4ad9 100644 --- a/drivers/clk/mediatek/clk-mt8195-ipe.c +++ b/drivers/clk/mediatek/clk-mt8195-ipe.c @@ -50,3 +50,4 @@ static struct platform_driver clk_mt8195_ipe_drv = { }, }; module_platform_driver(clk_mt8195_ipe_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-mfg.c b/drivers/clk/mediatek/clk-mt8195-mfg.c index fcd2d0b7e3c9..75cf643ab885 100644 --- a/drivers/clk/mediatek/clk-mt8195-mfg.c +++ b/drivers/clk/mediatek/clk-mt8195-mfg.c @@ -48,3 +48,4 @@ static struct platform_driver clk_mt8195_mfg_drv = { }, }; module_platform_driver(clk_mt8195_mfg_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-peri_ao.c b/drivers/clk/mediatek/clk-mt8195-peri_ao.c index f66fbea2e080..7d65a478182d 100644 --- a/drivers/clk/mediatek/clk-mt8195-peri_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-peri_ao.c @@ -61,3 +61,4 @@ static struct platform_driver clk_mt8195_peri_ao_drv = { }, }; module_platform_driver(clk_mt8195_peri_ao_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c index 1987172c98a4..24e09339ed7d 100644 --- a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c @@ -46,3 +46,4 @@ static struct platform_driver clk_mt8195_scp_adsp_drv = { }, }; module_platform_driver(clk_mt8195_scp_adsp_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index a9bb7e4687ec..adc6bb7ce750 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1341,3 +1341,4 @@ static struct platform_driver clk_mt8195_topck_drv = { }, }; module_platform_driver(clk_mt8195_topck_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-vdec.c b/drivers/clk/mediatek/clk-mt8195-vdec.c index a75ea99a9a4c..f9e2bd402627 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdec.c +++ b/drivers/clk/mediatek/clk-mt8195-vdec.c @@ -103,3 +103,4 @@ static struct platform_driver clk_mt8195_vdec_drv = { }, }; module_platform_driver(clk_mt8195_vdec_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo0.c b/drivers/clk/mediatek/clk-mt8195-vdo0.c index 1ed152b072bd..509780750e43 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo0.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo0.c @@ -113,3 +113,4 @@ static struct platform_driver clk_mt8195_vdo0_drv = { .id_table = clk_mt8195_vdo0_id_table, }; module_platform_driver(clk_mt8195_vdo0_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-vdo1.c b/drivers/clk/mediatek/clk-mt8195-vdo1.c index cbd0a34884c7..0a5214a1ed25 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdo1.c +++ b/drivers/clk/mediatek/clk-mt8195-vdo1.c @@ -140,3 +140,4 @@ static struct platform_driver clk_mt8195_vdo1_drv = { .id_table = clk_mt8195_vdo1_id_table, }; module_platform_driver(clk_mt8195_vdo1_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-venc.c b/drivers/clk/mediatek/clk-mt8195-venc.c index 8b46cbe9ce83..d050d87bb3f2 100644 --- a/drivers/clk/mediatek/clk-mt8195-venc.c +++ b/drivers/clk/mediatek/clk-mt8195-venc.c @@ -68,3 +68,4 @@ static struct platform_driver clk_mt8195_venc_drv = { }, }; module_platform_driver(clk_mt8195_venc_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp0.c b/drivers/clk/mediatek/clk-mt8195-vpp0.c index ca1288b76990..84805a114387 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp0.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp0.c @@ -105,3 +105,4 @@ static struct platform_driver clk_mt8195_vpp0_drv = { .id_table = clk_mt8195_vpp0_id_table, }; module_platform_driver(clk_mt8195_vpp0_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-vpp1.c b/drivers/clk/mediatek/clk-mt8195-vpp1.c index d9a260b6ee30..3e91dfed2996 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp1.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp1.c @@ -103,3 +103,4 @@ static struct platform_driver clk_mt8195_vpp1_drv = { .id_table = clk_mt8195_vpp1_id_table, }; module_platform_driver(clk_mt8195_vpp1_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8195-wpe.c b/drivers/clk/mediatek/clk-mt8195-wpe.c index 8878b5ef9e44..52cebe297abf 100644 --- a/drivers/clk/mediatek/clk-mt8195-wpe.c +++ b/drivers/clk/mediatek/clk-mt8195-wpe.c @@ -142,3 +142,4 @@ static struct platform_driver clk_mt8195_wpe_drv = { }, }; module_platform_driver(clk_mt8195_wpe_drv); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8365-apmixedsys.c b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c index 6f0fdf92bbd2..55faa4e37116 100644 --- a/drivers/clk/mediatek/clk-mt8365-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c @@ -162,3 +162,4 @@ static struct platform_driver clk_mt8365_apmixed_drv = { }, }; builtin_platform_driver(clk_mt8365_apmixed_drv) +MODULE_LICENSE("GPL"); -- GitLab From 650fcdf9181e4551cd22d651a8e637c800045c97 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:27 +0100 Subject: [PATCH 0381/5631] clk: mediatek: mt2712: Change Kconfig options to allow module build All of the mt2712 drivers have been converted to platform drivers! Change the Kconfig options for all MT2712 clocks to tristate to allow building all clock drivers as modules. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-39-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index b9c0a9e21cf1..45b7aea7648d 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -75,7 +75,7 @@ config COMMON_CLK_MT2701_G3DSYS This driver supports MediaTek MT2701 g3dsys clocks. config COMMON_CLK_MT2712 - bool "Clock driver for MediaTek MT2712" + tristate "Clock driver for MediaTek MT2712" depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK && ARM64 @@ -83,43 +83,43 @@ config COMMON_CLK_MT2712 This driver supports MediaTek MT2712 basic clocks. config COMMON_CLK_MT2712_BDPSYS - bool "Clock driver for MediaTek MT2712 bdpsys" + tristate "Clock driver for MediaTek MT2712 bdpsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 bdpsys clocks. config COMMON_CLK_MT2712_IMGSYS - bool "Clock driver for MediaTek MT2712 imgsys" + tristate "Clock driver for MediaTek MT2712 imgsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 imgsys clocks. config COMMON_CLK_MT2712_JPGDECSYS - bool "Clock driver for MediaTek MT2712 jpgdecsys" + tristate "Clock driver for MediaTek MT2712 jpgdecsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 jpgdecsys clocks. config COMMON_CLK_MT2712_MFGCFG - bool "Clock driver for MediaTek MT2712 mfgcfg" + tristate "Clock driver for MediaTek MT2712 mfgcfg" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 mfgcfg clocks. config COMMON_CLK_MT2712_MMSYS - bool "Clock driver for MediaTek MT2712 mmsys" + tristate "Clock driver for MediaTek MT2712 mmsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 mmsys clocks. config COMMON_CLK_MT2712_VDECSYS - bool "Clock driver for MediaTek MT2712 vdecsys" + tristate "Clock driver for MediaTek MT2712 vdecsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 vdecsys clocks. config COMMON_CLK_MT2712_VENCSYS - bool "Clock driver for MediaTek MT2712 vencsys" + tristate "Clock driver for MediaTek MT2712 vencsys" depends on COMMON_CLK_MT2712 help This driver supports MediaTek MT2712 vencsys clocks. -- GitLab From 0f471d31e5e87ac09aeee2bd370a5c7e4f8aa925 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:28 +0100 Subject: [PATCH 0382/5631] clk: mediatek: Split MT8195 clock drivers and allow module build MT8195 clock drivers were encapsulated in one single (and big) Kconfig option: there's no reason to do that, as it is totally unnecessary to build in all or none of them. Split them out: keep boot-critical clocks as bool and allow choosing non critical clocks as tristate. As a note, the dependencies of VDEC/VENCSYS and CAM/IMG/IPE/WPESYS are not for build-time but rather for runtime, as clocks registered by those have runtime dependencies on either or both VPP and IMGSYS. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-40-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 100 ++++++++++++++++++++++++++++++++++ drivers/clk/mediatek/Makefile | 20 ++++--- 2 files changed, 113 insertions(+), 7 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 45b7aea7648d..ab47b9ec64af 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -692,6 +692,106 @@ config COMMON_CLK_MT8195 help This driver supports MediaTek MT8195 clocks. +config COMMON_CLK_MT8195_APUSYS + tristate "Clock driver for MediaTek MT8195 apusys" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 AI Processor Unit System clocks. + +config COMMON_CLK_MT8195_AUDSYS + tristate "Clock driver for MediaTek MT8195 audsys" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 audsys clocks. + +config COMMON_CLK_MT8195_IMP_IIC_WRAP + tristate "Clock driver for MediaTek MT8195 imp_iic_wrap" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 I2C/I3C clocks. + +config COMMON_CLK_MT8195_MFGCFG + tristate "Clock driver for MediaTek MT8195 mfgcfg" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 mfgcfg clocks. + +config COMMON_CLK_MT8195_MSDC + tristate "Clock driver for MediaTek MT8195 msdc" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 MMC and SD Controller's + msdc and msdc_top clocks. + +config COMMON_CLK_MT8195_SCP_ADSP + tristate "Clock driver for MediaTek MT8195 scp_adsp" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 System Companion Processor + Audio DSP clocks. + +config COMMON_CLK_MT8195_VDOSYS + tristate "Clock driver for MediaTek MT8195 vdosys" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 vdosys0/1 (multimedia) clocks. + +config COMMON_CLK_MT8195_VPPSYS + tristate "Clock driver for MediaTek MT8195 vppsys" + depends on COMMON_CLK_MT8195 + default COMMON_CLK_MT8195 + help + This driver supports MediaTek MT8195 vppsys0/1 clocks. + +config COMMON_CLK_MT8195_CAMSYS + tristate "Clock driver for MediaTek MT8195 camsys" + depends on COMMON_CLK_MT8195_VPPSYS + default COMMON_CLK_MT8195_VPPSYS + help + This driver supports MediaTek MT8195 camsys and camsys_raw clocks. + +config COMMON_CLK_MT8195_IMGSYS + tristate "Clock driver for MediaTek MT8195 imgsys" + depends on COMMON_CLK_MT8195_VPPSYS + default COMMON_CLK_MT8195_VPPSYS + help + This driver supports MediaTek MT8195 imgsys and imgsys2 clocks. + +config COMMON_CLK_MT8195_IPESYS + tristate "Clock driver for MediaTek MT8195 ipesys" + depends on COMMON_CLK_MT8195_IMGSYS + default COMMON_CLK_MT8195_IMGSYS + help + This driver supports MediaTek MT8195 ipesys clocks. + +config COMMON_CLK_MT8195_WPESYS + tristate "Clock driver for MediaTek MT8195 wpesys" + depends on COMMON_CLK_MT8195_IMGSYS + default COMMON_CLK_MT8195_IMGSYS + help + This driver supports MediaTek MT8195 Warp Engine clocks. + +config COMMON_CLK_MT8195_VDECSYS + tristate "Clock driver for MediaTek MT8195 vdecsys" + depends on COMMON_CLK_MT8195_VPPSYS + default COMMON_CLK_MT8195_VPPSYS + help + This driver supports MediaTek MT8195 vdecsys and vdecsys_soc clocks. + +config COMMON_CLK_MT8195_VENCSYS + tristate "Clock driver for MediaTek MT8195 vencsys" + depends on COMMON_CLK_MT8195_VPPSYS + default COMMON_CLK_MT8195_VPPSYS + help + This driver supports MediaTek MT8195 vencsys clocks. + config COMMON_CLK_MT8365 tristate "Clock driver for MediaTek MT8365" depends on ARCH_MEDIATEK || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 79244e5ccc9c..9ea1af2a7457 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -106,13 +106,19 @@ obj-$(CONFIG_COMMON_CLK_MT8192_SCP_ADSP) += clk-mt8192-scp_adsp.o obj-$(CONFIG_COMMON_CLK_MT8192_VDECSYS) += clk-mt8192-vdec.o obj-$(CONFIG_COMMON_CLK_MT8192_VENCSYS) += clk-mt8192-venc.o obj-$(CONFIG_COMMON_CLK_MT8195) += clk-mt8195-apmixedsys.o clk-mt8195-topckgen.o \ - clk-mt8195-peri_ao.o clk-mt8195-infra_ao.o \ - clk-mt8195-cam.o clk-mt8195-ccu.o clk-mt8195-img.o \ - clk-mt8195-ipe.o clk-mt8195-mfg.o clk-mt8195-scp_adsp.o \ - clk-mt8195-vdec.o clk-mt8195-vdo0.o clk-mt8195-vdo1.o \ - clk-mt8195-venc.o clk-mt8195-vpp0.o clk-mt8195-vpp1.o \ - clk-mt8195-wpe.o clk-mt8195-imp_iic_wrap.o \ - clk-mt8195-apusys_pll.o + clk-mt8195-peri_ao.o clk-mt8195-infra_ao.o +obj-$(CONFIG_COMMON_CLK_MT8195_APUSYS) += clk-mt8195-apusys_pll.o +obj-$(CONFIG_COMMON_CLK_MT8195_CAMSYS) += clk-mt8195-cam.o clk-mt8195-ccu.o +obj-$(CONFIG_COMMON_CLK_MT8195_IMGSYS) += clk-mt8195-img.o +obj-$(CONFIG_COMMON_CLK_MT8195_IMP_IIC_WRAP) += clk-mt8195-imp_iic_wrap.o +obj-$(CONFIG_COMMON_CLK_MT8195_IPESYS) += clk-mt8195-ipe.o +obj-$(CONFIG_COMMON_CLK_MT8195_MFGCFG) += clk-mt8195-mfg.o +obj-$(CONFIG_COMMON_CLK_MT8195_SCP_ADSP) += clk-mt8195-scp_adsp.o +obj-$(CONFIG_COMMON_CLK_MT8195_VDECSYS) += clk-mt8195-vdec.o +obj-$(CONFIG_COMMON_CLK_MT8195_VDOSYS) += clk-mt8195-vdo0.o clk-mt8195-vdo1.o +obj-$(CONFIG_COMMON_CLK_MT8195_VENCSYS) += clk-mt8195-venc.o +obj-$(CONFIG_COMMON_CLK_MT8195_VPPSYS) += clk-mt8195-vpp0.o clk-mt8195-vpp1.o +obj-$(CONFIG_COMMON_CLK_MT8195_WPESYS) += clk-mt8195-wpe.o obj-$(CONFIG_COMMON_CLK_MT8365) += clk-mt8365-apmixedsys.o clk-mt8365.o obj-$(CONFIG_COMMON_CLK_MT8365_APU) += clk-mt8365-apu.o obj-$(CONFIG_COMMON_CLK_MT8365_CAM) += clk-mt8365-cam.o -- GitLab From e55351ac27ecffcff0bfb775924629003cde8005 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:29 +0100 Subject: [PATCH 0383/5631] clk: mediatek: Allow building MT8192 non-critical clocks as modules Allow building non boot critical clocks for MT8192 SoC as modules by changing them to tristate. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-41-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index ab47b9ec64af..fc073e5be4eb 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -613,73 +613,73 @@ config COMMON_CLK_MT8192 This driver supports MediaTek MT8192 basic clocks. config COMMON_CLK_MT8192_AUDSYS - bool "Clock driver for MediaTek MT8192 audsys" + tristate "Clock driver for MediaTek MT8192 audsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 audsys clocks. config COMMON_CLK_MT8192_CAMSYS - bool "Clock driver for MediaTek MT8192 camsys" + tristate "Clock driver for MediaTek MT8192 camsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 camsys and camsys_raw clocks. config COMMON_CLK_MT8192_IMGSYS - bool "Clock driver for MediaTek MT8192 imgsys" + tristate "Clock driver for MediaTek MT8192 imgsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 imgsys and imgsys2 clocks. config COMMON_CLK_MT8192_IMP_IIC_WRAP - bool "Clock driver for MediaTek MT8192 imp_iic_wrap" + tristate "Clock driver for MediaTek MT8192 imp_iic_wrap" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 imp_iic_wrap clocks. config COMMON_CLK_MT8192_IPESYS - bool "Clock driver for MediaTek MT8192 ipesys" + tristate "Clock driver for MediaTek MT8192 ipesys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 ipesys clocks. config COMMON_CLK_MT8192_MDPSYS - bool "Clock driver for MediaTek MT8192 mdpsys" + tristate "Clock driver for MediaTek MT8192 mdpsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 mdpsys clocks. config COMMON_CLK_MT8192_MFGCFG - bool "Clock driver for MediaTek MT8192 mfgcfg" + tristate "Clock driver for MediaTek MT8192 mfgcfg" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 mfgcfg clocks. config COMMON_CLK_MT8192_MMSYS - bool "Clock driver for MediaTek MT8192 mmsys" + tristate "Clock driver for MediaTek MT8192 mmsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 mmsys clocks. config COMMON_CLK_MT8192_MSDC - bool "Clock driver for MediaTek MT8192 msdc" + tristate "Clock driver for MediaTek MT8192 msdc" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 msdc and msdc_top clocks. config COMMON_CLK_MT8192_SCP_ADSP - bool "Clock driver for MediaTek MT8192 scp_adsp" + tristate "Clock driver for MediaTek MT8192 scp_adsp" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 scp_adsp clocks. config COMMON_CLK_MT8192_VDECSYS - bool "Clock driver for MediaTek MT8192 vdecsys" + tristate "Clock driver for MediaTek MT8192 vdecsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 vdecsys and vdecsys_soc clocks. config COMMON_CLK_MT8192_VENCSYS - bool "Clock driver for MediaTek MT8192 vencsys" + tristate "Clock driver for MediaTek MT8192 vencsys" depends on COMMON_CLK_MT8192 help This driver supports MediaTek MT8192 vencsys clocks. -- GitLab From c8f0ef997329728a136d07967b7a97cba3f07f7b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:30 +0100 Subject: [PATCH 0384/5631] clk: mediatek: Allow MT7622 clocks to be built as modules Now that all drivers are using the simple probe mechanism change the MT7622 clock drivers to tristate in Kconfig to allow module build. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-42-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index fc073e5be4eb..d089806789ee 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -336,7 +336,7 @@ config COMMON_CLK_MT6797_VENCSYS This driver supports MediaTek MT6797 vencsys clocks. config COMMON_CLK_MT7622 - bool "Clock driver for MediaTek MT7622" + tristate "Clock driver for MediaTek MT7622" depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK @@ -345,21 +345,21 @@ config COMMON_CLK_MT7622 required for various periperals found on MediaTek. config COMMON_CLK_MT7622_ETHSYS - bool "Clock driver for MediaTek MT7622 ETHSYS" + tristate "Clock driver for MediaTek MT7622 ETHSYS" depends on COMMON_CLK_MT7622 help This driver add support for clocks for Ethernet and SGMII required on MediaTek MT7622 SoC. config COMMON_CLK_MT7622_HIFSYS - bool "Clock driver for MediaTek MT7622 HIFSYS" + tristate "Clock driver for MediaTek MT7622 HIFSYS" depends on COMMON_CLK_MT7622 help This driver supports MediaTek MT7622 HIFSYS clocks providing to PCI-E and USB. config COMMON_CLK_MT7622_AUDSYS - bool "Clock driver for MediaTek MT7622 AUDSYS" + tristate "Clock driver for MediaTek MT7622 AUDSYS" depends on COMMON_CLK_MT7622 help This driver supports MediaTek MT7622 AUDSYS clocks providing -- GitLab From a851b17059bc07572224045f05ee556aa4ab0303 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:31 +0100 Subject: [PATCH 0385/5631] clk: mediatek: Allow all MT8167 clocks to be built as modules Almost all MT8167 clocks have been converted to use the common probe mechanism, moreover, now all of them are platform drivers: allow building as modules. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-43-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index d089806789ee..9f81ffc0876a 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -406,7 +406,7 @@ config COMMON_CLK_MT7981_ETHSYS required on MediaTek MT7981 SoC. config COMMON_CLK_MT7986 - bool "Clock driver for MediaTek MT7986" + tristate "Clock driver for MediaTek MT7986" depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK @@ -415,7 +415,7 @@ config COMMON_CLK_MT7986 required for various peripherals found on MediaTek. config COMMON_CLK_MT7986_ETHSYS - bool "Clock driver for MediaTek MT7986 ETHSYS" + tristate "Clock driver for MediaTek MT7986 ETHSYS" depends on COMMON_CLK_MT7986 default COMMON_CLK_MT7986 help @@ -431,7 +431,7 @@ config COMMON_CLK_MT8135 This driver supports MediaTek MT8135 clocks. config COMMON_CLK_MT8167 - bool "Clock driver for MediaTek MT8167" + tristate "Clock driver for MediaTek MT8167" depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK @@ -439,35 +439,35 @@ config COMMON_CLK_MT8167 This driver supports MediaTek MT8167 basic clocks. config COMMON_CLK_MT8167_AUDSYS - bool "Clock driver for MediaTek MT8167 audsys" + tristate "Clock driver for MediaTek MT8167 audsys" depends on COMMON_CLK_MT8167 default COMMON_CLK_MT8167 help This driver supports MediaTek MT8167 audsys clocks. config COMMON_CLK_MT8167_IMGSYS - bool "Clock driver for MediaTek MT8167 imgsys" + tristate "Clock driver for MediaTek MT8167 imgsys" depends on COMMON_CLK_MT8167 default COMMON_CLK_MT8167 help This driver supports MediaTek MT8167 imgsys clocks. config COMMON_CLK_MT8167_MFGCFG - bool "Clock driver for MediaTek MT8167 mfgcfg" + tristate "Clock driver for MediaTek MT8167 mfgcfg" depends on COMMON_CLK_MT8167 default COMMON_CLK_MT8167 help This driver supports MediaTek MT8167 mfgcfg clocks. config COMMON_CLK_MT8167_MMSYS - bool "Clock driver for MediaTek MT8167 mmsys" + tristate "Clock driver for MediaTek MT8167 mmsys" depends on COMMON_CLK_MT8167 default COMMON_CLK_MT8167 help This driver supports MediaTek MT8167 mmsys clocks. config COMMON_CLK_MT8167_VDECSYS - bool "Clock driver for MediaTek MT8167 vdecsys" + tristate "Clock driver for MediaTek MT8167 vdecsys" depends on COMMON_CLK_MT8167 default COMMON_CLK_MT8167 help -- GitLab From 95ffe65437b239db3f5a570b31cd79629c851743 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:32 +0100 Subject: [PATCH 0386/5631] clk: mediatek: Allow all MT8183 clocks to be built as modules All MT8183 clocks are platform drivers now! Allow module build for all of them. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-44-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 9f81ffc0876a..a8c2d4bace9a 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -511,7 +511,7 @@ config COMMON_CLK_MT8173_VENCSYS This driver supports MediaTek MT8173 vencsys clocks. config COMMON_CLK_MT8183 - bool "Clock driver for MediaTek MT8183" + tristate "Clock driver for MediaTek MT8183" depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK && ARM64 @@ -519,77 +519,77 @@ config COMMON_CLK_MT8183 This driver supports MediaTek MT8183 basic clocks. config COMMON_CLK_MT8183_AUDIOSYS - bool "Clock driver for MediaTek MT8183 audiosys" + tristate "Clock driver for MediaTek MT8183 audiosys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 audiosys clocks. config COMMON_CLK_MT8183_CAMSYS - bool "Clock driver for MediaTek MT8183 camsys" + tristate "Clock driver for MediaTek MT8183 camsys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 camsys clocks. config COMMON_CLK_MT8183_IMGSYS - bool "Clock driver for MediaTek MT8183 imgsys" + tristate "Clock driver for MediaTek MT8183 imgsys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 imgsys clocks. config COMMON_CLK_MT8183_IPU_CORE0 - bool "Clock driver for MediaTek MT8183 ipu_core0" + tristate "Clock driver for MediaTek MT8183 ipu_core0" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 ipu_core0 clocks. config COMMON_CLK_MT8183_IPU_CORE1 - bool "Clock driver for MediaTek MT8183 ipu_core1" + tristate "Clock driver for MediaTek MT8183 ipu_core1" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 ipu_core1 clocks. config COMMON_CLK_MT8183_IPU_ADL - bool "Clock driver for MediaTek MT8183 ipu_adl" + tristate "Clock driver for MediaTek MT8183 ipu_adl" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 ipu_adl clocks. config COMMON_CLK_MT8183_IPU_CONN - bool "Clock driver for MediaTek MT8183 ipu_conn" + tristate "Clock driver for MediaTek MT8183 ipu_conn" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 ipu_conn clocks. config COMMON_CLK_MT8183_MFGCFG - bool "Clock driver for MediaTek MT8183 mfgcfg" + tristate "Clock driver for MediaTek MT8183 mfgcfg" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 mfgcfg clocks. config COMMON_CLK_MT8183_MMSYS - bool "Clock driver for MediaTek MT8183 mmsys" + tristate "Clock driver for MediaTek MT8183 mmsys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 mmsys clocks. config COMMON_CLK_MT8183_VDECSYS - bool "Clock driver for MediaTek MT8183 vdecsys" + tristate "Clock driver for MediaTek MT8183 vdecsys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help This driver supports MediaTek MT8183 vdecsys clocks. config COMMON_CLK_MT8183_VENCSYS - bool "Clock driver for MediaTek MT8183 vencsys" + tristate "Clock driver for MediaTek MT8183 vencsys" depends on COMMON_CLK_MT8183 default COMMON_CLK_MT8183 help -- GitLab From cfe2c864f0cc80ef292c0b01bb7b83b4cc393516 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:33 +0100 Subject: [PATCH 0387/5631] clk: mediatek: Allow building most MT6765 clock drivers as modules Most of the MT6765 clock drivers can be built as modules: change them to tristate to allow that. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-45-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index a8c2d4bace9a..a3260675cafc 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -133,79 +133,79 @@ config COMMON_CLK_MT6765 This driver supports MediaTek MT6765 basic clocks. config COMMON_CLK_MT6765_AUDIOSYS - bool "Clock driver for MediaTek MT6765 audiosys" + tristate "Clock driver for MediaTek MT6765 audiosys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 audiosys clocks. config COMMON_CLK_MT6765_CAMSYS - bool "Clock driver for MediaTek MT6765 camsys" + tristate "Clock driver for MediaTek MT6765 camsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 camsys clocks. config COMMON_CLK_MT6765_GCESYS - bool "Clock driver for MediaTek MT6765 gcesys" + tristate "Clock driver for MediaTek MT6765 gcesys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 gcesys clocks. config COMMON_CLK_MT6765_MMSYS - bool "Clock driver for MediaTek MT6765 mmsys" + tristate "Clock driver for MediaTek MT6765 mmsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mmsys clocks. config COMMON_CLK_MT6765_IMGSYS - bool "Clock driver for MediaTek MT6765 imgsys" + tristate "Clock driver for MediaTek MT6765 imgsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 imgsys clocks. config COMMON_CLK_MT6765_VCODECSYS - bool "Clock driver for MediaTek MT6765 vcodecsys" + tristate "Clock driver for MediaTek MT6765 vcodecsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 vcodecsys clocks. config COMMON_CLK_MT6765_MFGSYS - bool "Clock driver for MediaTek MT6765 mfgsys" + tristate "Clock driver for MediaTek MT6765 mfgsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mfgsys clocks. config COMMON_CLK_MT6765_MIPI0ASYS - bool "Clock driver for MediaTek MT6765 mipi0asys" + tristate "Clock driver for MediaTek MT6765 mipi0asys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi0asys clocks. config COMMON_CLK_MT6765_MIPI0BSYS - bool "Clock driver for MediaTek MT6765 mipi0bsys" + tristate "Clock driver for MediaTek MT6765 mipi0bsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi0bsys clocks. config COMMON_CLK_MT6765_MIPI1ASYS - bool "Clock driver for MediaTek MT6765 mipi1asys" + tristate "Clock driver for MediaTek MT6765 mipi1asys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi1asys clocks. config COMMON_CLK_MT6765_MIPI1BSYS - bool "Clock driver for MediaTek MT6765 mipi1bsys" + tristate "Clock driver for MediaTek MT6765 mipi1bsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi1bsys clocks. config COMMON_CLK_MT6765_MIPI2ASYS - bool "Clock driver for MediaTek MT6765 mipi2asys" + tristate "Clock driver for MediaTek MT6765 mipi2asys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi2asys clocks. config COMMON_CLK_MT6765_MIPI2BSYS - bool "Clock driver for MediaTek MT6765 mipi2bsys" + tristate "Clock driver for MediaTek MT6765 mipi2bsys" depends on COMMON_CLK_MT6765 help This driver supports MediaTek MT6765 mipi2bsys clocks. -- GitLab From 6f0d2e07f2dbcafdc4018839bc99971dd1a7232d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:34 +0100 Subject: [PATCH 0388/5631] clk: mediatek: Allow building most MT6797 clock drivers as modules Most of the MT6797 clock drivers can be built as modules: change them to tristate to allow that. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-46-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index a3260675cafc..0240c1039d64 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -312,25 +312,25 @@ config COMMON_CLK_MT6797 This driver supports MediaTek MT6797 basic clocks. config COMMON_CLK_MT6797_MMSYS - bool "Clock driver for MediaTek MT6797 mmsys" + tristate "Clock driver for MediaTek MT6797 mmsys" depends on COMMON_CLK_MT6797 help This driver supports MediaTek MT6797 mmsys clocks. config COMMON_CLK_MT6797_IMGSYS - bool "Clock driver for MediaTek MT6797 imgsys" + tristate "Clock driver for MediaTek MT6797 imgsys" depends on COMMON_CLK_MT6797 help This driver supports MediaTek MT6797 imgsys clocks. config COMMON_CLK_MT6797_VDECSYS - bool "Clock driver for MediaTek MT6797 vdecsys" + tristate "Clock driver for MediaTek MT6797 vdecsys" depends on COMMON_CLK_MT6797 help This driver supports MediaTek MT6797 vdecsys clocks. config COMMON_CLK_MT6797_VENCSYS - bool "Clock driver for MediaTek MT6797 vencsys" + tristate "Clock driver for MediaTek MT6797 vencsys" depends on COMMON_CLK_MT6797 help This driver supports MediaTek MT6797 vencsys clocks. -- GitLab From 5baf38e06a570a2a4ed471a996aff6d6ba69cceb Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:35 +0100 Subject: [PATCH 0389/5631] clk: mediatek: Split configuration options for MT8186 clock drivers When building clock drivers for MT8186, some may want to build in only some of them to, for example, get CPUFreq up faster, and some may want to leave out some clock drivers entirely as a machine may not need the Warp Engine or the camera ISP (hence, their clock drivers). Split the various clock drivers in their own configuration options, keeping MT8186 configuration options consistent with other MediaTek SoCs. While at it, also allow building the remaining clock drivers as modules by switching COMMON_CLK_MT8186 to tristate. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-47-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 79 ++++++++++++++++++++++++++++++++++- drivers/clk/mediatek/Makefile | 18 +++++--- 2 files changed, 91 insertions(+), 6 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 0240c1039d64..04b4be419bd0 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -596,7 +596,7 @@ config COMMON_CLK_MT8183_VENCSYS This driver supports MediaTek MT8183 vencsys clocks. config COMMON_CLK_MT8186 - bool "Clock driver for MediaTek MT8186" + tristate "Clock driver for MediaTek MT8186" depends on ARM64 || COMPILE_TEST select COMMON_CLK_MEDIATEK select COMMON_CLK_MEDIATEK_FHCTL @@ -604,6 +604,83 @@ config COMMON_CLK_MT8186 help This driver supports MediaTek MT8186 clocks. +config COMMON_CLK_MT8186_CAMSYS + tristate "Clock driver for MediaTek MT8186 camsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 camsys and camsys_raw clocks. + +config COMMON_CLK_MT8186_IMGSYS + tristate "Clock driver for MediaTek MT8186 imgsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 imgsys and imgsys2 clocks. + +config COMMON_CLK_MT8186_IPESYS + tristate "Clock driver for MediaTek MT8186 ipesys" + depends on COMMON_CLK_MT8186_IMGSYS + default COMMON_CLK_MT8186_IMGSYS + help + This driver supports MediaTek MT8186 ipesys clocks. + +config COMMON_CLK_MT8186_WPESYS + tristate "Clock driver for MediaTek MT8186 wpesys" + depends on COMMON_CLK_MT8186_IMGSYS + default COMMON_CLK_MT8186_IMGSYS + help + This driver supports MediaTek MT8186 Warp Engine clocks. + +config COMMON_CLK_MT8186_IMP_IIC_WRAP + tristate "Clock driver for MediaTek MT8186 imp_iic_wrap" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 imp_iic_wrap clocks. + +config COMMON_CLK_MT8186_MCUSYS + tristate "Clock driver for MediaTek MT8186 mcusys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 mcusys clocks. + +config COMMON_CLK_MT8186_MDPSYS + tristate "Clock driver for MediaTek MT8186 mdpsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 mdpsys clocks. + +config COMMON_CLK_MT8186_MFGCFG + tristate "Clock driver for MediaTek MT8186 mfgcfg" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 mfgcfg clocks. + +config COMMON_CLK_MT8186_MMSYS + tristate "Clock driver for MediaTek MT8186 mmsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 mmsys clocks. + +config COMMON_CLK_MT8186_VDECSYS + tristate "Clock driver for MediaTek MT8186 vdecsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 vdecsys and vdecsys_soc clocks. + +config COMMON_CLK_MT8186_VENCSYS + tristate "Clock driver for MediaTek MT8186 vencsys" + depends on COMMON_CLK_MT8186 + default COMMON_CLK_MT8186 + help + This driver supports MediaTek MT8186 vencsys clocks. + config COMMON_CLK_MT8192 bool "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 9ea1af2a7457..6186bf4a5ed9 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -87,11 +87,19 @@ obj-$(CONFIG_COMMON_CLK_MT8183_MFGCFG) += clk-mt8183-mfgcfg.o obj-$(CONFIG_COMMON_CLK_MT8183_MMSYS) += clk-mt8183-mm.o obj-$(CONFIG_COMMON_CLK_MT8183_VDECSYS) += clk-mt8183-vdec.o obj-$(CONFIG_COMMON_CLK_MT8183_VENCSYS) += clk-mt8183-venc.o -obj-$(CONFIG_COMMON_CLK_MT8186) += clk-mt8186-mcu.o clk-mt8186-topckgen.o clk-mt8186-infra_ao.o \ - clk-mt8186-apmixedsys.o clk-mt8186-imp_iic_wrap.o \ - clk-mt8186-mfg.o clk-mt8186-mm.o clk-mt8186-wpe.o \ - clk-mt8186-img.o clk-mt8186-vdec.o clk-mt8186-venc.o \ - clk-mt8186-cam.o clk-mt8186-mdp.o clk-mt8186-ipe.o +obj-$(CONFIG_COMMON_CLK_MT8186) += clk-mt8186-apmixedsys.o clk-mt8186-topckgen.o \ + clk-mt8186-infra_ao.o +obj-$(CONFIG_COMMON_CLK_MT8186_CAMSYS) += clk-mt8186-cam.o +obj-$(CONFIG_COMMON_CLK_MT8186_IMGSYS) += clk-mt8186-img.o +obj-$(CONFIG_COMMON_CLK_MT8186_IMP_IIC_WRAP) += clk-mt8186-imp_iic_wrap.o +obj-$(CONFIG_COMMON_CLK_MT8186_IPESYS) += clk-mt8186-ipe.o +obj-$(CONFIG_COMMON_CLK_MT8186_MCUSYS) += clk-mt8186-mcu.o +obj-$(CONFIG_COMMON_CLK_MT8186_MDPSYS) += clk-mt8186-mdp.o +obj-$(CONFIG_COMMON_CLK_MT8186_MFGCFG) += clk-mt8186-mfg.o +obj-$(CONFIG_COMMON_CLK_MT8186_MMSYS) += clk-mt8186-mm.o +obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o +obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o +obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o -- GitLab From 124294ff468fb3e2767473f2e317cd0ffa7eff90 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:36 +0100 Subject: [PATCH 0390/5631] clk: mediatek: mt8192: Move apmixedsys clock driver to its own file This is the last man standing in clk-mt8192.c that won't allow us to use the module_platform_driver() macro, and for *no* good reason. Move it to clk-mt8192-apmixedsys.c and while at it, also add a .remove() callback for it. Also, since the need for "clk-mt8192-simple" and "clk-mt8192" was just due to them being in the same file and probing different clocks, and since now there's just one platform_driver struct per file, it seemed natural to rename the `-simple` variant to just "clk-mt8192". Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-48-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8192-apmixedsys.c | 214 ++++++++++++++++++ drivers/clk/mediatek/clk-mt8192.c | 221 +------------------ 3 files changed, 219 insertions(+), 218 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8192-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 6186bf4a5ed9..048a150a7637 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -100,7 +100,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_MMSYS) += clk-mt8186-mm.o obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o -obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192.o +obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o obj-$(CONFIG_COMMON_CLK_MT8192_IMGSYS) += clk-mt8192-img.o diff --git a/drivers/clk/mediatek/clk-mt8192-apmixedsys.c b/drivers/clk/mediatek/clk-mt8192-apmixedsys.c new file mode 100644 index 000000000000..1e6988d5289a --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8192-apmixedsys.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 MediaTek Inc. + * Chun-Jie Chen + * Copyright (c) 2023 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include "clk-fhctl.h" +#include "clk-gate.h" +#include "clk-mtk.h" +#include "clk-pll.h" +#include "clk-pllfh.h" + +static const struct mtk_gate_regs apmixed_cg_regs = { + .set_ofs = 0x14, + .clr_ofs = 0x14, + .sta_ofs = 0x14, +}; + +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +static const struct mtk_gate apmixed_clks[] = { + GATE_APMIXED(CLK_APMIXED_MIPID26M, "mipid26m", "clk26m", 16), +}; + +#define MT8192_PLL_FMAX (3800UL * MHZ) +#define MT8192_PLL_FMIN (1500UL * MHZ) +#define MT8192_INTEGER_BITS 8 + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ + _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ + _pcw_reg, _pcw_shift, _pcw_chg_reg, \ + _en_reg, _pll_en_bit) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = _rst_bar_mask, \ + .fmax = MT8192_PLL_FMAX, \ + .fmin = MT8192_PLL_FMIN, \ + .pcwbits = _pcwbits, \ + .pcwibits = MT8192_INTEGER_BITS, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .tuner_en_reg = _tuner_en_reg, \ + .tuner_en_bit = _tuner_en_bit, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .pcw_chg_reg = _pcw_chg_reg, \ + .en_reg = _en_reg, \ + .pll_en_bit = _pll_en_bit, \ + } + +#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ + _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ + _pcw_reg, _pcw_shift) \ + PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ + _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ + _pcw_reg, _pcw_shift, 0, 0, 0) + +static const struct mtk_pll_data plls[] = { + PLL_B(CLK_APMIXED_MAINPLL, "mainpll", 0x0340, 0x034c, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0344, 24, 0, 0, 0, 0x0344, 0), + PLL_B(CLK_APMIXED_UNIVPLL, "univpll", 0x0308, 0x0314, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x030c, 24, 0, 0, 0, 0x030c, 0), + PLL(CLK_APMIXED_USBPLL, "usbpll", 0x03c4, 0x03cc, 0x00000000, + 0, 0, 22, 0x03c4, 24, 0, 0, 0, 0x03c4, 0, 0x03c4, 0x03cc, 2), + PLL_B(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0350, 0x035c, 0x00000000, + 0, 0, 22, 0x0354, 24, 0, 0, 0, 0x0354, 0), + PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0360, 0x036c, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0364, 24, 0, 0, 0, 0x0364, 0), + PLL_B(CLK_APMIXED_ADSPPLL, "adsppll", 0x0370, 0x037c, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0374, 24, 0, 0, 0, 0x0374, 0), + PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0268, 0x0274, 0x00000000, + 0, 0, 22, 0x026c, 24, 0, 0, 0, 0x026c, 0), + PLL_B(CLK_APMIXED_TVDPLL, "tvdpll", 0x0380, 0x038c, 0x00000000, + 0, 0, 22, 0x0384, 24, 0, 0, 0, 0x0384, 0), + PLL_B(CLK_APMIXED_APLL1, "apll1", 0x0318, 0x0328, 0x00000000, + 0, 0, 32, 0x031c, 24, 0x0040, 0x000c, 0, 0x0320, 0), + PLL_B(CLK_APMIXED_APLL2, "apll2", 0x032c, 0x033c, 0x00000000, + 0, 0, 32, 0x0330, 24, 0, 0, 0, 0x0334, 0), +}; + +enum fh_pll_id { + FH_ARMPLL_LL, + FH_ARMPLL_BL0, + FH_ARMPLL_BL1, + FH_ARMPLL_BL2, + FH_ARMPLL_BL3, + FH_CCIPLL, + FH_MFGPLL, + FH_MEMPLL, + FH_MPLL, + FH_MMPLL, + FH_MAINPLL, + FH_MSDCPLL, + FH_ADSPPLL, + FH_APUPLL, + FH_TVDPLL, + FH_NR_FH, +}; + +#define FH(_pllid, _fhid, _offset) { \ + .data = { \ + .pll_id = _pllid, \ + .fh_id = _fhid, \ + .fh_ver = FHCTL_PLLFH_V2, \ + .fhx_offset = _offset, \ + .dds_mask = GENMASK(21, 0), \ + .slope0_value = 0x6003c97, \ + .slope1_value = 0x6003c97, \ + .sfstrx_en = BIT(2), \ + .frddsx_en = BIT(1), \ + .fhctlx_en = BIT(0), \ + .tgl_org = BIT(31), \ + .dvfs_tri = BIT(31), \ + .pcwchg = BIT(31), \ + .dt_val = 0x0, \ + .df_val = 0x9, \ + .updnlmt_shft = 16, \ + .msk_frddsx_dys = GENMASK(23, 20), \ + .msk_frddsx_dts = GENMASK(19, 16), \ + }, \ + } + +static struct mtk_pllfh_data pllfhs[] = { + FH(CLK_APMIXED_MFGPLL, FH_MFGPLL, 0xb4), + FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0xf0), + FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x104), + FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x118), + FH(CLK_APMIXED_ADSPPLL, FH_ADSPPLL, 0x12c), + FH(CLK_APMIXED_TVDPLL, FH_TVDPLL, 0x154), +}; + +static const struct of_device_id of_match_clk_mt8192_apmixed[] = { + { .compatible = "mediatek,mt8192-apmixedsys" }, + { /* sentinel */ } +}; + +static int clk_mt8192_apmixed_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + const u8 *fhctl_node = "mediatek,mt8192-fhctl"; + int r; + + clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); + + r = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), + pllfhs, ARRAY_SIZE(pllfhs), clk_data); + if (r) + goto free_clk_data; + + r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); + if (r) + goto unregister_plls; + + r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (r) + goto unregister_gates; + + return r; + +unregister_gates: + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); +unregister_plls: + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); +free_clk_data: + mtk_free_clk_data(clk_data); + return r; +} + +static int clk_mt8192_apmixed_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); + mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, + ARRAY_SIZE(pllfhs), clk_data); + mtk_free_clk_data(clk_data); + + return 0; +} + +static struct platform_driver clk_mt8192_apmixed_drv = { + .driver = { + .name = "clk-mt8192-apmixed", + .of_match_table = of_match_clk_mt8192_apmixed, + }, + .probe = clk_mt8192_apmixed_probe, + .remove = clk_mt8192_apmixed_remove, +}; +module_platform_driver(clk_mt8192_apmixed_drv); +MODULE_DESCRIPTION("MediaTek MT8192 apmixed clocks driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c index 35afe496b1c1..45eccda51471 100644 --- a/drivers/clk/mediatek/clk-mt8192.c +++ b/drivers/clk/mediatek/clk-mt8192.c @@ -12,12 +12,9 @@ #include #include -#include "clk-fhctl.h" #include "clk-gate.h" #include "clk-mtk.h" #include "clk-mux.h" -#include "clk-pll.h" -#include "clk-pllfh.h" #include #include @@ -714,19 +711,6 @@ static struct mtk_composite top_muxes[] = { DIV_GATE(CLK_TOP_APLL12_DIV9, "apll12_div9", "apll_i2s9_m_sel", 0x320, 10, 0x338, 8, 16), }; -static const struct mtk_gate_regs apmixed_cg_regs = { - .set_ofs = 0x14, - .clr_ofs = 0x14, - .sta_ofs = 0x14, -}; - -#define GATE_APMIXED(_id, _name, _parent, _shift) \ - GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) - -static const struct mtk_gate apmixed_clks[] = { - GATE_APMIXED(CLK_APMIXED_MIPID26M, "mipid26m", "clk26m", 16), -}; - static const struct mtk_gate_regs infra0_cg_regs = { .set_ofs = 0x80, .clr_ofs = 0x84, @@ -980,121 +964,6 @@ static const struct mtk_clk_rst_desc clk_rst_desc = { .rst_idx_map_nr = ARRAY_SIZE(infra_ao_idx_map), }; -#define MT8192_PLL_FMAX (3800UL * MHZ) -#define MT8192_PLL_FMIN (1500UL * MHZ) -#define MT8192_INTEGER_BITS 8 - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ - _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ - _pcw_reg, _pcw_shift, _pcw_chg_reg, \ - _en_reg, _pll_en_bit) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = _rst_bar_mask, \ - .fmax = MT8192_PLL_FMAX, \ - .fmin = MT8192_PLL_FMIN, \ - .pcwbits = _pcwbits, \ - .pcwibits = MT8192_INTEGER_BITS, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .tuner_en_reg = _tuner_en_reg, \ - .tuner_en_bit = _tuner_en_bit, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - .pcw_chg_reg = _pcw_chg_reg, \ - .en_reg = _en_reg, \ - .pll_en_bit = _pll_en_bit, \ - } - -#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ - _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ - _pcw_reg, _pcw_shift) \ - PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ - _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ - _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ - _pcw_reg, _pcw_shift, 0, 0, 0) - -static const struct mtk_pll_data plls[] = { - PLL_B(CLK_APMIXED_MAINPLL, "mainpll", 0x0340, 0x034c, 0xff000000, - HAVE_RST_BAR, BIT(23), 22, 0x0344, 24, 0, 0, 0, 0x0344, 0), - PLL_B(CLK_APMIXED_UNIVPLL, "univpll", 0x0308, 0x0314, 0xff000000, - HAVE_RST_BAR, BIT(23), 22, 0x030c, 24, 0, 0, 0, 0x030c, 0), - PLL(CLK_APMIXED_USBPLL, "usbpll", 0x03c4, 0x03cc, 0x00000000, - 0, 0, 22, 0x03c4, 24, 0, 0, 0, 0x03c4, 0, 0x03c4, 0x03cc, 2), - PLL_B(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0350, 0x035c, 0x00000000, - 0, 0, 22, 0x0354, 24, 0, 0, 0, 0x0354, 0), - PLL_B(CLK_APMIXED_MMPLL, "mmpll", 0x0360, 0x036c, 0xff000000, - HAVE_RST_BAR, BIT(23), 22, 0x0364, 24, 0, 0, 0, 0x0364, 0), - PLL_B(CLK_APMIXED_ADSPPLL, "adsppll", 0x0370, 0x037c, 0xff000000, - HAVE_RST_BAR, BIT(23), 22, 0x0374, 24, 0, 0, 0, 0x0374, 0), - PLL_B(CLK_APMIXED_MFGPLL, "mfgpll", 0x0268, 0x0274, 0x00000000, - 0, 0, 22, 0x026c, 24, 0, 0, 0, 0x026c, 0), - PLL_B(CLK_APMIXED_TVDPLL, "tvdpll", 0x0380, 0x038c, 0x00000000, - 0, 0, 22, 0x0384, 24, 0, 0, 0, 0x0384, 0), - PLL_B(CLK_APMIXED_APLL1, "apll1", 0x0318, 0x0328, 0x00000000, - 0, 0, 32, 0x031c, 24, 0x0040, 0x000c, 0, 0x0320, 0), - PLL_B(CLK_APMIXED_APLL2, "apll2", 0x032c, 0x033c, 0x00000000, - 0, 0, 32, 0x0330, 24, 0, 0, 0, 0x0334, 0), -}; - -enum fh_pll_id { - FH_ARMPLL_LL, - FH_ARMPLL_BL0, - FH_ARMPLL_BL1, - FH_ARMPLL_BL2, - FH_ARMPLL_BL3, - FH_CCIPLL, - FH_MFGPLL, - FH_MEMPLL, - FH_MPLL, - FH_MMPLL, - FH_MAINPLL, - FH_MSDCPLL, - FH_ADSPPLL, - FH_APUPLL, - FH_TVDPLL, - FH_NR_FH, -}; - -#define FH(_pllid, _fhid, _offset) { \ - .data = { \ - .pll_id = _pllid, \ - .fh_id = _fhid, \ - .fh_ver = FHCTL_PLLFH_V2, \ - .fhx_offset = _offset, \ - .dds_mask = GENMASK(21, 0), \ - .slope0_value = 0x6003c97, \ - .slope1_value = 0x6003c97, \ - .sfstrx_en = BIT(2), \ - .frddsx_en = BIT(1), \ - .fhctlx_en = BIT(0), \ - .tgl_org = BIT(31), \ - .dvfs_tri = BIT(31), \ - .pcwchg = BIT(31), \ - .dt_val = 0x0, \ - .df_val = 0x9, \ - .updnlmt_shft = 16, \ - .msk_frddsx_dys = GENMASK(23, 20), \ - .msk_frddsx_dts = GENMASK(19, 16), \ - }, \ - } - -static struct mtk_pllfh_data pllfhs[] = { - FH(CLK_APMIXED_MFGPLL, FH_MFGPLL, 0xb4), - FH(CLK_APMIXED_MMPLL, FH_MMPLL, 0xf0), - FH(CLK_APMIXED_MAINPLL, FH_MAINPLL, 0x104), - FH(CLK_APMIXED_MSDCPLL, FH_MSDCPLL, 0x118), - FH(CLK_APMIXED_ADSPPLL, FH_ADSPPLL, 0x12c), - FH(CLK_APMIXED_TVDPLL, FH_TVDPLL, 0x154), -}; - /* Register mux notifier for MFG mux */ static int clk_mt8192_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) { @@ -1117,70 +986,6 @@ static int clk_mt8192_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) return devm_mtk_clk_mux_notifier_register(dev, clk, mfg_mux_nb); } -static int clk_mt8192_apmixed_probe(struct platform_device *pdev) -{ - struct clk_hw_onecell_data *clk_data; - struct device_node *node = pdev->dev.of_node; - const u8 *fhctl_node = "mediatek,mt8192-fhctl"; - int r; - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - if (!clk_data) - return -ENOMEM; - - fhctl_parse_dt(fhctl_node, pllfhs, ARRAY_SIZE(pllfhs)); - - r = mtk_clk_register_pllfhs(node, plls, ARRAY_SIZE(plls), - pllfhs, ARRAY_SIZE(pllfhs), clk_data); - if (r) - goto free_clk_data; - - r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, - ARRAY_SIZE(apmixed_clks), clk_data); - if (r) - goto unregister_plls; - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - goto unregister_gates; - - return r; - -unregister_gates: - mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); -unregister_plls: - mtk_clk_unregister_pllfhs(plls, ARRAY_SIZE(plls), pllfhs, - ARRAY_SIZE(pllfhs), clk_data); -free_clk_data: - mtk_free_clk_data(clk_data); - return r; -} - -static const struct of_device_id of_match_clk_mt8192[] = { - { - .compatible = "mediatek,mt8192-apmixedsys", - .data = clk_mt8192_apmixed_probe, - }, { - /* sentinel */ - } -}; - -static int clk_mt8192_probe(struct platform_device *pdev) -{ - int (*clk_probe)(struct platform_device *pdev); - int r; - - clk_probe = of_device_get_match_data(&pdev->dev); - if (!clk_probe) - return -EINVAL; - - r = clk_probe(pdev); - if (r) - dev_err(&pdev->dev, "could not register clock provider: %s: %d\n", pdev->name, r); - - return r; -} - static const struct mtk_clk_desc infra_desc = { .clks = infra_clks, .num_clks = ARRAY_SIZE(infra_clks), @@ -1208,38 +1013,20 @@ static const struct mtk_clk_desc topck_desc = { .mfg_clk_idx = CLK_TOP_MFG_PLL_SEL, }; -static const struct of_device_id of_match_clk_mt8192_simple[] = { +static const struct of_device_id of_match_clk_mt8192[] = { { .compatible = "mediatek,mt8192-infracfg", .data = &infra_desc }, { .compatible = "mediatek,mt8192-pericfg", .data = &peri_desc }, { .compatible = "mediatek,mt8192-topckgen", .data = &topck_desc }, { /* sentinel */ } }; -static struct platform_driver clk_mt8192_simple_drv = { - .probe = mtk_clk_simple_probe, - .remove = mtk_clk_simple_remove, - .driver = { - .name = "clk-mt8192-simple", - .of_match_table = of_match_clk_mt8192_simple, - }, -}; - static struct platform_driver clk_mt8192_drv = { - .probe = clk_mt8192_probe, .driver = { .name = "clk-mt8192", .of_match_table = of_match_clk_mt8192, }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, }; - -static int __init clk_mt8192_init(void) -{ - int ret = platform_driver_register(&clk_mt8192_drv); - - if (ret) - return ret; - return platform_driver_register(&clk_mt8192_simple_drv); -} - -arch_initcall(clk_mt8192_init); +module_platform_driver(clk_mt8192_drv); MODULE_LICENSE("GPL"); -- GitLab From 9bfa4fb1e0d6de678a79ec5a05fac464edcee91d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:37 +0100 Subject: [PATCH 0391/5631] clk: mediatek: Kconfig: Allow module build for core mt8192 clocks Bootloaders must in a way setup the SoC to boot Linux: this means that it will be possible to decompress a ramdisk and eventually insert the core clock driver module from there. Allow module build for all MT8192 clocks by switching to tristate. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-49-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 04b4be419bd0..02093996ccc3 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -682,7 +682,7 @@ config COMMON_CLK_MT8186_VENCSYS This driver supports MediaTek MT8186 vencsys clocks. config COMMON_CLK_MT8192 - bool "Clock driver for MediaTek MT8192" + tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARM64 -- GitLab From 65c9ad77cbc0eed78db94d80041aba675cfbdfa9 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:38 +0100 Subject: [PATCH 0392/5631] clk: mediatek: Add MODULE_DEVICE_TABLE() where appropriate Add a MODULE_DEVICE_TABLE() on all clocks that can be built as modules to allow auto-load at boot. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Tested-by: Miles Chen Tested-by: Chen-Yu Tsai # MT8183, MT8192, MT8195 Chromebooks Link: https://lore.kernel.org/r/20230306140543.1813621-50-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt2701-aud.c | 1 + drivers/clk/mediatek/clk-mt2701-bdp.c | 1 + drivers/clk/mediatek/clk-mt2701-eth.c | 1 + drivers/clk/mediatek/clk-mt2701-g3d.c | 1 + drivers/clk/mediatek/clk-mt2701-hif.c | 1 + drivers/clk/mediatek/clk-mt2701-img.c | 1 + drivers/clk/mediatek/clk-mt2701-mm.c | 1 + drivers/clk/mediatek/clk-mt2701-vdec.c | 1 + drivers/clk/mediatek/clk-mt2701.c | 1 + drivers/clk/mediatek/clk-mt2712-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt2712-bdp.c | 1 + drivers/clk/mediatek/clk-mt2712-img.c | 1 + drivers/clk/mediatek/clk-mt2712-jpgdec.c | 1 + drivers/clk/mediatek/clk-mt2712-mfg.c | 1 + drivers/clk/mediatek/clk-mt2712-mm.c | 1 + drivers/clk/mediatek/clk-mt2712-vdec.c | 1 + drivers/clk/mediatek/clk-mt2712-venc.c | 1 + drivers/clk/mediatek/clk-mt2712.c | 1 + drivers/clk/mediatek/clk-mt6765-audio.c | 1 + drivers/clk/mediatek/clk-mt6765-cam.c | 1 + drivers/clk/mediatek/clk-mt6765-img.c | 1 + drivers/clk/mediatek/clk-mt6765-mipi0a.c | 1 + drivers/clk/mediatek/clk-mt6765-mm.c | 1 + drivers/clk/mediatek/clk-mt6765-vcodec.c | 1 + drivers/clk/mediatek/clk-mt6765.c | 1 + drivers/clk/mediatek/clk-mt6779-aud.c | 1 + drivers/clk/mediatek/clk-mt6779-cam.c | 1 + drivers/clk/mediatek/clk-mt6779-img.c | 1 + drivers/clk/mediatek/clk-mt6779-ipe.c | 1 + drivers/clk/mediatek/clk-mt6779-mfg.c | 1 + drivers/clk/mediatek/clk-mt6779-mm.c | 1 + drivers/clk/mediatek/clk-mt6779-vdec.c | 1 + drivers/clk/mediatek/clk-mt6779-venc.c | 1 + drivers/clk/mediatek/clk-mt6779.c | 1 + drivers/clk/mediatek/clk-mt6795-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt6795-infracfg.c | 1 + drivers/clk/mediatek/clk-mt6795-mfg.c | 1 + drivers/clk/mediatek/clk-mt6795-mm.c | 1 + drivers/clk/mediatek/clk-mt6795-pericfg.c | 1 + drivers/clk/mediatek/clk-mt6795-topckgen.c | 1 + drivers/clk/mediatek/clk-mt6795-vdecsys.c | 1 + drivers/clk/mediatek/clk-mt6795-vencsys.c | 1 + drivers/clk/mediatek/clk-mt6797-img.c | 1 + drivers/clk/mediatek/clk-mt6797-mm.c | 1 + drivers/clk/mediatek/clk-mt6797-vdec.c | 1 + drivers/clk/mediatek/clk-mt6797-venc.c | 1 + drivers/clk/mediatek/clk-mt6797.c | 1 + drivers/clk/mediatek/clk-mt7622-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt7622-aud.c | 1 + drivers/clk/mediatek/clk-mt7622-eth.c | 1 + drivers/clk/mediatek/clk-mt7622-hif.c | 1 + drivers/clk/mediatek/clk-mt7622-infracfg.c | 1 + drivers/clk/mediatek/clk-mt7622.c | 1 + drivers/clk/mediatek/clk-mt7629-eth.c | 1 + drivers/clk/mediatek/clk-mt7629-hif.c | 1 + drivers/clk/mediatek/clk-mt7629.c | 1 + drivers/clk/mediatek/clk-mt7981-apmixed.c | 1 + drivers/clk/mediatek/clk-mt7981-eth.c | 1 + drivers/clk/mediatek/clk-mt7981-infracfg.c | 1 + drivers/clk/mediatek/clk-mt7981-topckgen.c | 1 + drivers/clk/mediatek/clk-mt7986-apmixed.c | 3 ++- drivers/clk/mediatek/clk-mt7986-eth.c | 1 + drivers/clk/mediatek/clk-mt7986-infracfg.c | 1 + drivers/clk/mediatek/clk-mt7986-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8167-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8167-aud.c | 1 + drivers/clk/mediatek/clk-mt8167-img.c | 1 + drivers/clk/mediatek/clk-mt8167-mfgcfg.c | 1 + drivers/clk/mediatek/clk-mt8167-mm.c | 1 + drivers/clk/mediatek/clk-mt8167-vdec.c | 1 + drivers/clk/mediatek/clk-mt8167.c | 1 + drivers/clk/mediatek/clk-mt8173-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8173-img.c | 1 + drivers/clk/mediatek/clk-mt8173-infracfg.c | 1 + drivers/clk/mediatek/clk-mt8173-mm.c | 1 + drivers/clk/mediatek/clk-mt8173-pericfg.c | 1 + drivers/clk/mediatek/clk-mt8173-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8173-vdecsys.c | 1 + drivers/clk/mediatek/clk-mt8173-vencsys.c | 1 + drivers/clk/mediatek/clk-mt8183-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8183-audio.c | 1 + drivers/clk/mediatek/clk-mt8183-cam.c | 1 + drivers/clk/mediatek/clk-mt8183-img.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu0.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu1.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu_adl.c | 1 + drivers/clk/mediatek/clk-mt8183-ipu_conn.c | 1 + drivers/clk/mediatek/clk-mt8183-mfgcfg.c | 1 + drivers/clk/mediatek/clk-mt8183-mm.c | 1 + drivers/clk/mediatek/clk-mt8183-vdec.c | 1 + drivers/clk/mediatek/clk-mt8183-venc.c | 1 + drivers/clk/mediatek/clk-mt8183.c | 1 + drivers/clk/mediatek/clk-mt8186-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8186-cam.c | 1 + drivers/clk/mediatek/clk-mt8186-img.c | 1 + drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8186-infra_ao.c | 1 + drivers/clk/mediatek/clk-mt8186-ipe.c | 1 + drivers/clk/mediatek/clk-mt8186-mcu.c | 1 + drivers/clk/mediatek/clk-mt8186-mdp.c | 1 + drivers/clk/mediatek/clk-mt8186-mfg.c | 1 + drivers/clk/mediatek/clk-mt8186-mm.c | 2 ++ drivers/clk/mediatek/clk-mt8186-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8186-vdec.c | 1 + drivers/clk/mediatek/clk-mt8186-venc.c | 1 + drivers/clk/mediatek/clk-mt8186-wpe.c | 1 + drivers/clk/mediatek/clk-mt8192-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8192-aud.c | 1 + drivers/clk/mediatek/clk-mt8192-cam.c | 1 + drivers/clk/mediatek/clk-mt8192-img.c | 1 + drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8192-ipe.c | 1 + drivers/clk/mediatek/clk-mt8192-mdp.c | 1 + drivers/clk/mediatek/clk-mt8192-mfg.c | 1 + drivers/clk/mediatek/clk-mt8192-mm.c | 1 + drivers/clk/mediatek/clk-mt8192-msdc.c | 1 + drivers/clk/mediatek/clk-mt8192-scp_adsp.c | 1 + drivers/clk/mediatek/clk-mt8192-vdec.c | 1 + drivers/clk/mediatek/clk-mt8192-venc.c | 1 + drivers/clk/mediatek/clk-mt8192.c | 1 + drivers/clk/mediatek/clk-mt8195-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8195-apusys_pll.c | 1 + drivers/clk/mediatek/clk-mt8195-cam.c | 1 + drivers/clk/mediatek/clk-mt8195-ccu.c | 1 + drivers/clk/mediatek/clk-mt8195-img.c | 1 + drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c | 1 + drivers/clk/mediatek/clk-mt8195-infra_ao.c | 1 + drivers/clk/mediatek/clk-mt8195-ipe.c | 1 + drivers/clk/mediatek/clk-mt8195-mfg.c | 1 + drivers/clk/mediatek/clk-mt8195-peri_ao.c | 1 + drivers/clk/mediatek/clk-mt8195-scp_adsp.c | 1 + drivers/clk/mediatek/clk-mt8195-topckgen.c | 1 + drivers/clk/mediatek/clk-mt8195-vdec.c | 1 + drivers/clk/mediatek/clk-mt8195-venc.c | 1 + drivers/clk/mediatek/clk-mt8195-vpp0.c | 1 + drivers/clk/mediatek/clk-mt8195-vpp1.c | 1 + drivers/clk/mediatek/clk-mt8195-wpe.c | 1 + drivers/clk/mediatek/clk-mt8365-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8365-apu.c | 1 + drivers/clk/mediatek/clk-mt8365-cam.c | 1 + drivers/clk/mediatek/clk-mt8365-mfg.c | 1 + drivers/clk/mediatek/clk-mt8365-mm.c | 1 + drivers/clk/mediatek/clk-mt8365-vdec.c | 1 + drivers/clk/mediatek/clk-mt8365-venc.c | 1 + drivers/clk/mediatek/clk-mt8365.c | 1 + drivers/clk/mediatek/clk-mt8516-apmixedsys.c | 1 + drivers/clk/mediatek/clk-mt8516-aud.c | 1 + drivers/clk/mediatek/clk-mt8516.c | 1 + 148 files changed, 150 insertions(+), 1 deletion(-) diff --git a/drivers/clk/mediatek/clk-mt2701-aud.c b/drivers/clk/mediatek/clk-mt2701-aud.c index 113ab5b0bf8d..5cd343b98685 100644 --- a/drivers/clk/mediatek/clk-mt2701-aud.c +++ b/drivers/clk/mediatek/clk-mt2701-aud.c @@ -124,6 +124,7 @@ static const struct of_device_id of_match_clk_mt2701_aud[] = { { .compatible = "mediatek,mt2701-audsys", .data = &audio_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_aud); static int clk_mt2701_aud_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt2701-bdp.c b/drivers/clk/mediatek/clk-mt2701-bdp.c index e7b43329d305..4c5b70d48df9 100644 --- a/drivers/clk/mediatek/clk-mt2701-bdp.c +++ b/drivers/clk/mediatek/clk-mt2701-bdp.c @@ -95,6 +95,7 @@ static const struct of_device_id of_match_clk_mt2701_bdp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_bdp); static struct platform_driver clk_mt2701_bdp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-eth.c b/drivers/clk/mediatek/clk-mt2701-eth.c index d30567ac4ff1..9a1fb0c93964 100644 --- a/drivers/clk/mediatek/clk-mt2701-eth.c +++ b/drivers/clk/mediatek/clk-mt2701-eth.c @@ -49,6 +49,7 @@ static const struct of_device_id of_match_clk_mt2701_eth[] = { { .compatible = "mediatek,mt2701-ethsys", .data = ð_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_eth); static struct platform_driver clk_mt2701_eth_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-g3d.c b/drivers/clk/mediatek/clk-mt2701-g3d.c index 6f881eabdc67..c0006861a317 100644 --- a/drivers/clk/mediatek/clk-mt2701-g3d.c +++ b/drivers/clk/mediatek/clk-mt2701-g3d.c @@ -48,6 +48,7 @@ static const struct of_device_id of_match_clk_mt2701_g3d[] = { { .compatible = "mediatek,mt2701-g3dsys", .data = &g3d_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_g3d); static struct platform_driver clk_mt2701_g3d_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-hif.c b/drivers/clk/mediatek/clk-mt2701-hif.c index b2ee73c4de4e..ff7c0b3228e4 100644 --- a/drivers/clk/mediatek/clk-mt2701-hif.c +++ b/drivers/clk/mediatek/clk-mt2701-hif.c @@ -46,6 +46,7 @@ static const struct of_device_id of_match_clk_mt2701_hif[] = { { .compatible = "mediatek,mt2701-hifsys", .data = &hif_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_hif); static struct platform_driver clk_mt2701_hif_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-img.c b/drivers/clk/mediatek/clk-mt2701-img.c index 35a5fd938a6e..baa1194eb01e 100644 --- a/drivers/clk/mediatek/clk-mt2701-img.c +++ b/drivers/clk/mediatek/clk-mt2701-img.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt2701_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_img); static struct platform_driver clk_mt2701_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-mm.c b/drivers/clk/mediatek/clk-mt2701-mm.c index 75611d0ab865..c62c56fd2b7e 100644 --- a/drivers/clk/mediatek/clk-mt2701-mm.c +++ b/drivers/clk/mediatek/clk-mt2701-mm.c @@ -76,6 +76,7 @@ static const struct platform_device_id clk_mt2701_mm_id_table[] = { { .name = "clk-mt2701-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt2701_mm_id_table); static struct platform_driver clk_mt2701_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt2701-vdec.c b/drivers/clk/mediatek/clk-mt2701-vdec.c index dca4335a52a7..b7f97bc51c16 100644 --- a/drivers/clk/mediatek/clk-mt2701-vdec.c +++ b/drivers/clk/mediatek/clk-mt2701-vdec.c @@ -48,6 +48,7 @@ static const struct of_device_id of_match_clk_mt2701_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701_vdec); static struct platform_driver clk_mt2701_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2701.c b/drivers/clk/mediatek/clk-mt2701.c index d3097d9f0c7a..4a154da8a543 100644 --- a/drivers/clk/mediatek/clk-mt2701.c +++ b/drivers/clk/mediatek/clk-mt2701.c @@ -999,6 +999,7 @@ static const struct of_device_id of_match_clk_mt2701[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2701); static int clk_mt2701_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c index eade747d2812..9d2fcda285fb 100644 --- a/drivers/clk/mediatek/clk-mt2712-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt2712-apmixedsys.c @@ -154,6 +154,7 @@ static const struct of_device_id of_match_clk_mt2712_apmixed[] = { { .compatible = "mediatek,mt2712-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_apmixed); static struct platform_driver clk_mt2712_apmixed_drv = { .probe = clk_mt2712_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-bdp.c b/drivers/clk/mediatek/clk-mt2712-bdp.c index d4979f2fb1d3..f78e01819316 100644 --- a/drivers/clk/mediatek/clk-mt2712-bdp.c +++ b/drivers/clk/mediatek/clk-mt2712-bdp.c @@ -65,6 +65,7 @@ static const struct of_device_id of_match_clk_mt2712_bdp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_bdp); static struct platform_driver clk_mt2712_bdp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-img.c b/drivers/clk/mediatek/clk-mt2712-img.c index cd2d2af6bd56..fbe7084886a0 100644 --- a/drivers/clk/mediatek/clk-mt2712-img.c +++ b/drivers/clk/mediatek/clk-mt2712-img.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt2712_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_img); static struct platform_driver clk_mt2712_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-jpgdec.c b/drivers/clk/mediatek/clk-mt2712-jpgdec.c index 815be759e7c9..7e8c2ebcdee0 100644 --- a/drivers/clk/mediatek/clk-mt2712-jpgdec.c +++ b/drivers/clk/mediatek/clk-mt2712-jpgdec.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt2712_jpgdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_jpgdec); static struct platform_driver clk_mt2712_jpgdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-mfg.c b/drivers/clk/mediatek/clk-mt2712-mfg.c index 9f958fadca86..932ea449d299 100644 --- a/drivers/clk/mediatek/clk-mt2712-mfg.c +++ b/drivers/clk/mediatek/clk-mt2712-mfg.c @@ -38,6 +38,7 @@ static const struct of_device_id of_match_clk_mt2712_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_mfg); static struct platform_driver clk_mt2712_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-mm.c b/drivers/clk/mediatek/clk-mt2712-mm.c index 2649d67f2a56..204a3eae08dc 100644 --- a/drivers/clk/mediatek/clk-mt2712-mm.c +++ b/drivers/clk/mediatek/clk-mt2712-mm.c @@ -117,6 +117,7 @@ static const struct platform_device_id clk_mt2712_mm_id_table[] = { { .name = "clk-mt2712-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt2712_mm_id_table); static struct platform_driver clk_mt2712_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-vdec.c b/drivers/clk/mediatek/clk-mt2712-vdec.c index 1cb150fa7ab4..2fc1f82ebf5d 100644 --- a/drivers/clk/mediatek/clk-mt2712-vdec.c +++ b/drivers/clk/mediatek/clk-mt2712-vdec.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt2712_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_vdec); static struct platform_driver clk_mt2712_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712-venc.c b/drivers/clk/mediatek/clk-mt2712-venc.c index 4073fa6c040f..6d053a00cf95 100644 --- a/drivers/clk/mediatek/clk-mt2712-venc.c +++ b/drivers/clk/mediatek/clk-mt2712-venc.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt2712_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712_venc); static struct platform_driver clk_mt2712_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt2712.c b/drivers/clk/mediatek/clk-mt2712.c index b2cf91622ebf..74c529f6163d 100644 --- a/drivers/clk/mediatek/clk-mt2712.c +++ b/drivers/clk/mediatek/clk-mt2712.c @@ -991,6 +991,7 @@ static const struct of_device_id of_match_clk_mt2712[] = { { .compatible = "mediatek,mt2712-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt2712); static struct platform_driver clk_mt2712_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-audio.c b/drivers/clk/mediatek/clk-mt6765-audio.c index c1fecf22f8ad..9e98d6997329 100644 --- a/drivers/clk/mediatek/clk-mt6765-audio.c +++ b/drivers/clk/mediatek/clk-mt6765-audio.c @@ -65,6 +65,7 @@ static const struct of_device_id of_match_clk_mt6765_audio[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_audio); static struct platform_driver clk_mt6765_audio_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-cam.c b/drivers/clk/mediatek/clk-mt6765-cam.c index 15737c8f6b69..6f6b29d8b29a 100644 --- a/drivers/clk/mediatek/clk-mt6765-cam.c +++ b/drivers/clk/mediatek/clk-mt6765-cam.c @@ -46,6 +46,7 @@ static const struct of_device_id of_match_clk_mt6765_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_cam); static struct platform_driver clk_mt6765_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-img.c b/drivers/clk/mediatek/clk-mt6765-img.c index 7e421f4d01b8..984201077a20 100644 --- a/drivers/clk/mediatek/clk-mt6765-img.c +++ b/drivers/clk/mediatek/clk-mt6765-img.c @@ -42,6 +42,7 @@ static const struct of_device_id of_match_clk_mt6765_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_img); static struct platform_driver clk_mt6765_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-mipi0a.c b/drivers/clk/mediatek/clk-mt6765-mipi0a.c index 17186a308e94..a47937f4efe5 100644 --- a/drivers/clk/mediatek/clk-mt6765-mipi0a.c +++ b/drivers/clk/mediatek/clk-mt6765-mipi0a.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt6765_mipi0a[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_mipi0a); static struct platform_driver clk_mt6765_mipi0a_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-mm.c b/drivers/clk/mediatek/clk-mt6765-mm.c index af2213db17cb..2b8fc052558e 100644 --- a/drivers/clk/mediatek/clk-mt6765-mm.c +++ b/drivers/clk/mediatek/clk-mt6765-mm.c @@ -68,6 +68,7 @@ static const struct of_device_id of_match_clk_mt6765_mm[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_mm); static struct platform_driver clk_mt6765_mm_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765-vcodec.c b/drivers/clk/mediatek/clk-mt6765-vcodec.c index 48014cc71d9f..36df9615b1be 100644 --- a/drivers/clk/mediatek/clk-mt6765-vcodec.c +++ b/drivers/clk/mediatek/clk-mt6765-vcodec.c @@ -41,6 +41,7 @@ static const struct of_device_id of_match_clk_mt6765_vcodec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765_vcodec); static struct platform_driver clk_mt6765_vcodec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6765.c b/drivers/clk/mediatek/clk-mt6765.c index 61f93b6fdf8b..fa7948ef1e68 100644 --- a/drivers/clk/mediatek/clk-mt6765.c +++ b/drivers/clk/mediatek/clk-mt6765.c @@ -840,6 +840,7 @@ static const struct of_device_id of_match_clk_mt6765[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6765); static int clk_mt6765_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt6779-aud.c b/drivers/clk/mediatek/clk-mt6779-aud.c index 6e473ae1fd90..6e3280d3a2e6 100644 --- a/drivers/clk/mediatek/clk-mt6779-aud.c +++ b/drivers/clk/mediatek/clk-mt6779-aud.c @@ -102,6 +102,7 @@ static const struct of_device_id of_match_clk_mt6779_aud[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_aud); static struct platform_driver clk_mt6779_aud_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-cam.c b/drivers/clk/mediatek/clk-mt6779-cam.c index 7be3db90fa4a..b4c4c7248672 100644 --- a/drivers/clk/mediatek/clk-mt6779-cam.c +++ b/drivers/clk/mediatek/clk-mt6779-cam.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt6779_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_cam); static struct platform_driver clk_mt6779_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-img.c b/drivers/clk/mediatek/clk-mt6779-img.c index 9bc51fc82dbd..b760a8af3462 100644 --- a/drivers/clk/mediatek/clk-mt6779-img.c +++ b/drivers/clk/mediatek/clk-mt6779-img.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt6779_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_img); static struct platform_driver clk_mt6779_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-ipe.c b/drivers/clk/mediatek/clk-mt6779-ipe.c index 92e9d1ade422..9285a792c59b 100644 --- a/drivers/clk/mediatek/clk-mt6779-ipe.c +++ b/drivers/clk/mediatek/clk-mt6779-ipe.c @@ -45,6 +45,7 @@ static const struct of_device_id of_match_clk_mt6779_ipe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_ipe); static struct platform_driver clk_mt6779_ipe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-mfg.c b/drivers/clk/mediatek/clk-mt6779-mfg.c index efc793a1969a..d20f32d4f827 100644 --- a/drivers/clk/mediatek/clk-mt6779-mfg.c +++ b/drivers/clk/mediatek/clk-mt6779-mfg.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt6779_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_mfg); static struct platform_driver clk_mt6779_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-mm.c b/drivers/clk/mediatek/clk-mt6779-mm.c index 219a3a7920cd..c2f700ae6c2c 100644 --- a/drivers/clk/mediatek/clk-mt6779-mm.c +++ b/drivers/clk/mediatek/clk-mt6779-mm.c @@ -94,6 +94,7 @@ static const struct platform_device_id clk_mt6779_mm_id_table[] = { { .name = "clk-mt6779-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt6779_mm_id_table); static struct platform_driver clk_mt6779_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-vdec.c b/drivers/clk/mediatek/clk-mt6779-vdec.c index 3209a6518d5b..e062ed5aa45f 100644 --- a/drivers/clk/mediatek/clk-mt6779-vdec.c +++ b/drivers/clk/mediatek/clk-mt6779-vdec.c @@ -52,6 +52,7 @@ static const struct of_device_id of_match_clk_mt6779_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_vdec); static struct platform_driver clk_mt6779_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779-venc.c b/drivers/clk/mediatek/clk-mt6779-venc.c index c25035c0f334..0ae8ac28f838 100644 --- a/drivers/clk/mediatek/clk-mt6779-venc.c +++ b/drivers/clk/mediatek/clk-mt6779-venc.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt6779_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779_venc); static struct platform_driver clk_mt6779_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6779.c b/drivers/clk/mediatek/clk-mt6779.c index 827025d127d9..1f5ea1508f61 100644 --- a/drivers/clk/mediatek/clk-mt6779.c +++ b/drivers/clk/mediatek/clk-mt6779.c @@ -1299,6 +1299,7 @@ static const struct of_device_id of_match_clk_mt6779_infra[] = { { .compatible = "mediatek,mt6779-infracfg_ao", .data = &infra_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6779); static struct platform_driver clk_mt6779_infra_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6795-apmixedsys.c b/drivers/clk/mediatek/clk-mt6795-apmixedsys.c index 03fa30527868..8b30109f253c 100644 --- a/drivers/clk/mediatek/clk-mt6795-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt6795-apmixedsys.c @@ -131,6 +131,7 @@ static const struct of_device_id of_match_clk_mt6795_apmixed[] = { { .compatible = "mediatek,mt6795-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_apmixed); static int clk_mt6795_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt6795-infracfg.c b/drivers/clk/mediatek/clk-mt6795-infracfg.c index 23d9fc057e61..086ea1438564 100644 --- a/drivers/clk/mediatek/clk-mt6795-infracfg.c +++ b/drivers/clk/mediatek/clk-mt6795-infracfg.c @@ -81,6 +81,7 @@ static const struct of_device_id of_match_clk_mt6795_infracfg[] = { { .compatible = "mediatek,mt6795-infracfg" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_infracfg); static int clk_mt6795_infracfg_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt6795-mfg.c b/drivers/clk/mediatek/clk-mt6795-mfg.c index ee7aab24eb24..1d658bb19e82 100644 --- a/drivers/clk/mediatek/clk-mt6795-mfg.c +++ b/drivers/clk/mediatek/clk-mt6795-mfg.c @@ -35,6 +35,7 @@ static const struct of_device_id of_match_clk_mt6795_mfg[] = { { .compatible = "mediatek,mt6795-mfgcfg", .data = &mfg_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_mfg); static struct platform_driver clk_mt6795_mfg_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt6795-mm.c b/drivers/clk/mediatek/clk-mt6795-mm.c index c0c61a08cd72..8acc9cad2875 100644 --- a/drivers/clk/mediatek/clk-mt6795-mm.c +++ b/drivers/clk/mediatek/clk-mt6795-mm.c @@ -85,6 +85,7 @@ static const struct platform_device_id clk_mt6795_mm_id_table[] = { { .name = "clk-mt6795-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt6795_mm_id_table); static struct platform_driver clk_mt6795_mm_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt6795-pericfg.c b/drivers/clk/mediatek/clk-mt6795-pericfg.c index 08aaa9b09c36..62cc19eee2c7 100644 --- a/drivers/clk/mediatek/clk-mt6795-pericfg.c +++ b/drivers/clk/mediatek/clk-mt6795-pericfg.c @@ -89,6 +89,7 @@ static const struct of_device_id of_match_clk_mt6795_pericfg[] = { { .compatible = "mediatek,mt6795-pericfg" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_pericfg); static int clk_mt6795_pericfg_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt6795-topckgen.c b/drivers/clk/mediatek/clk-mt6795-topckgen.c index e80fa588e309..9c6d63a80b19 100644 --- a/drivers/clk/mediatek/clk-mt6795-topckgen.c +++ b/drivers/clk/mediatek/clk-mt6795-topckgen.c @@ -539,6 +539,7 @@ static const struct of_device_id of_match_clk_mt6795_topckgen[] = { { .compatible = "mediatek,mt6795-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_topckgen); static struct platform_driver clk_mt6795_topckgen_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt6795-vdecsys.c b/drivers/clk/mediatek/clk-mt6795-vdecsys.c index d85d04e0d016..f2968f859dca 100644 --- a/drivers/clk/mediatek/clk-mt6795-vdecsys.c +++ b/drivers/clk/mediatek/clk-mt6795-vdecsys.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt6795_vdecsys[] = { { .compatible = "mediatek,mt6795-vdecsys", .data = &vdec_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_vdecsys); static struct platform_driver clk_mt6795_vdecsys_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6795-vencsys.c b/drivers/clk/mediatek/clk-mt6795-vencsys.c index de40a982ca96..2f8d48da1a85 100644 --- a/drivers/clk/mediatek/clk-mt6795-vencsys.c +++ b/drivers/clk/mediatek/clk-mt6795-vencsys.c @@ -35,6 +35,7 @@ static const struct of_device_id of_match_clk_mt6795_vencsys[] = { { .compatible = "mediatek,mt6795-vencsys", .data = &venc_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6795_vencsys); static struct platform_driver clk_mt6795_vencsys_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt6797-img.c b/drivers/clk/mediatek/clk-mt6797-img.c index 22779829370f..00fc0a03e646 100644 --- a/drivers/clk/mediatek/clk-mt6797-img.c +++ b/drivers/clk/mediatek/clk-mt6797-img.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt6797_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6797_img); static struct platform_driver clk_mt6797_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6797-mm.c b/drivers/clk/mediatek/clk-mt6797-mm.c index 8722fae10de9..caacfa40a5bc 100644 --- a/drivers/clk/mediatek/clk-mt6797-mm.c +++ b/drivers/clk/mediatek/clk-mt6797-mm.c @@ -89,6 +89,7 @@ static const struct platform_device_id clk_mt6797_mm_id_table[] = { { .name = "clk-mt6797-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt6797_mm_id_table); static struct platform_driver clk_mt6797_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt6797-vdec.c b/drivers/clk/mediatek/clk-mt6797-vdec.c index c5a82d4a958b..447fe6fa8e15 100644 --- a/drivers/clk/mediatek/clk-mt6797-vdec.c +++ b/drivers/clk/mediatek/clk-mt6797-vdec.c @@ -50,6 +50,7 @@ static const struct of_device_id of_match_clk_mt6797_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6797_vdec); static struct platform_driver clk_mt6797_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6797-venc.c b/drivers/clk/mediatek/clk-mt6797-venc.c index afdd288d313a..95b89ff8fd19 100644 --- a/drivers/clk/mediatek/clk-mt6797-venc.c +++ b/drivers/clk/mediatek/clk-mt6797-venc.c @@ -41,6 +41,7 @@ static const struct of_device_id of_match_clk_mt6797_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6797_venc); static struct platform_driver clk_mt6797_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt6797.c b/drivers/clk/mediatek/clk-mt6797.c index 4094fd75d16e..4c87c0348e5f 100644 --- a/drivers/clk/mediatek/clk-mt6797.c +++ b/drivers/clk/mediatek/clk-mt6797.c @@ -670,6 +670,7 @@ static const struct of_device_id of_match_clk_mt6797[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt6797); static int clk_mt6797_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c index a9f3057d7080..a36808d074d6 100644 --- a/drivers/clk/mediatek/clk-mt7622-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt7622-apmixedsys.c @@ -136,6 +136,7 @@ static const struct of_device_id of_match_clk_mt7622_apmixed[] = { { .compatible = "mediatek,mt7622-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622_apmixed); static struct platform_driver clk_mt7622_apmixed_drv = { .probe = clk_mt7622_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt7622-aud.c b/drivers/clk/mediatek/clk-mt7622-aud.c index 4e14a4ff465a..dd1799dd8435 100644 --- a/drivers/clk/mediatek/clk-mt7622-aud.c +++ b/drivers/clk/mediatek/clk-mt7622-aud.c @@ -145,6 +145,7 @@ static const struct of_device_id of_match_clk_mt7622_aud[] = { { .compatible = "mediatek,mt7622-audsys", .data = &audio_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622_aud); static struct platform_driver clk_mt7622_aud_drv = { .probe = clk_mt7622_aud_probe, diff --git a/drivers/clk/mediatek/clk-mt7622-eth.c b/drivers/clk/mediatek/clk-mt7622-eth.c index 4475d0846176..f96b36737029 100644 --- a/drivers/clk/mediatek/clk-mt7622-eth.c +++ b/drivers/clk/mediatek/clk-mt7622-eth.c @@ -77,6 +77,7 @@ static const struct of_device_id of_match_clk_mt7622_eth[] = { { .compatible = "mediatek,mt7622-sgmiisys", .data = &sgmii_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622_eth); static struct platform_driver clk_mt7622_eth_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7622-hif.c b/drivers/clk/mediatek/clk-mt7622-hif.c index 19f394af1132..f440943f0d46 100644 --- a/drivers/clk/mediatek/clk-mt7622-hif.c +++ b/drivers/clk/mediatek/clk-mt7622-hif.c @@ -89,6 +89,7 @@ static const struct of_device_id of_match_clk_mt7622_hif[] = { { .compatible = "mediatek,mt7622-ssusbsys", .data = &ssusb_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622_hif); static struct platform_driver clk_mt7622_hif_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7622-infracfg.c b/drivers/clk/mediatek/clk-mt7622-infracfg.c index 09d8ac4d483a..9dc05526f287 100644 --- a/drivers/clk/mediatek/clk-mt7622-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7622-infracfg.c @@ -55,6 +55,7 @@ static const struct of_device_id of_match_clk_mt7622_infracfg[] = { { .compatible = "mediatek,mt7622-infracfg" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622_infracfg); static int clk_mt7622_infracfg_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7622.c b/drivers/clk/mediatek/clk-mt7622.c index 7a002b73fcaa..274895264427 100644 --- a/drivers/clk/mediatek/clk-mt7622.c +++ b/drivers/clk/mediatek/clk-mt7622.c @@ -518,6 +518,7 @@ static const struct of_device_id of_match_clk_mt7622[] = { { .compatible = "mediatek,mt7622-pericfg", .data = &peri_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7622); static struct platform_driver clk_mt7622_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt7629-eth.c b/drivers/clk/mediatek/clk-mt7629-eth.c index ee84a3de7f2c..1e1c77cc14ba 100644 --- a/drivers/clk/mediatek/clk-mt7629-eth.c +++ b/drivers/clk/mediatek/clk-mt7629-eth.c @@ -126,6 +126,7 @@ static const struct of_device_id of_match_clk_mt7629_eth[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7629_eth); static int clk_mt7629_eth_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7629-hif.c b/drivers/clk/mediatek/clk-mt7629-hif.c index 464c4131d98a..c89036bee9a7 100644 --- a/drivers/clk/mediatek/clk-mt7629-hif.c +++ b/drivers/clk/mediatek/clk-mt7629-hif.c @@ -84,6 +84,7 @@ static const struct of_device_id of_match_clk_mt7629_hif[] = { { .compatible = "mediatek,mt7629-ssusbsys", .data = &ssusb_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7629_hif); static struct platform_driver clk_mt7629_hif_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7629.c b/drivers/clk/mediatek/clk-mt7629.c index f3279f002e93..0893fbbb68cc 100644 --- a/drivers/clk/mediatek/clk-mt7629.c +++ b/drivers/clk/mediatek/clk-mt7629.c @@ -660,6 +660,7 @@ static const struct of_device_id of_match_clk_mt7629[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7629); static int clk_mt7629_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7981-apmixed.c b/drivers/clk/mediatek/clk-mt7981-apmixed.c index 53c974c66f89..875813d8b4a9 100644 --- a/drivers/clk/mediatek/clk-mt7981-apmixed.c +++ b/drivers/clk/mediatek/clk-mt7981-apmixed.c @@ -66,6 +66,7 @@ static const struct of_device_id of_match_clk_mt7981_apmixed[] = { { .compatible = "mediatek,mt7981-apmixedsys", }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7981_apmixed); static int clk_mt7981_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7981-eth.c b/drivers/clk/mediatek/clk-mt7981-eth.c index f27fadd6bf94..b1f256b5ed4e 100644 --- a/drivers/clk/mediatek/clk-mt7981-eth.c +++ b/drivers/clk/mediatek/clk-mt7981-eth.c @@ -105,6 +105,7 @@ static const struct of_device_id of_match_clk_mt7981_eth[] = { { .compatible = "mediatek,mt7981-sgmiisys_1", .data = &sgmii1_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7981_eth); static struct platform_driver clk_mt7981_eth_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7981-infracfg.c b/drivers/clk/mediatek/clk-mt7981-infracfg.c index d1709323d34e..293261ef71e6 100644 --- a/drivers/clk/mediatek/clk-mt7981-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7981-infracfg.c @@ -195,6 +195,7 @@ static const struct of_device_id of_match_clk_mt7981_infracfg[] = { { .compatible = "mediatek,mt7981-infracfg", .data = &infracfg_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7981_infracfg); static struct platform_driver clk_mt7981_infracfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7981-topckgen.c b/drivers/clk/mediatek/clk-mt7981-topckgen.c index e09ffc22b13a..3aba1a9b9a36 100644 --- a/drivers/clk/mediatek/clk-mt7981-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7981-topckgen.c @@ -410,6 +410,7 @@ static const struct of_device_id of_match_clk_mt7981_topckgen[] = { { .compatible = "mediatek,mt7981-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7981_topckgen); static struct platform_driver clk_mt7981_topckgen_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt7986-apmixed.c b/drivers/clk/mediatek/clk-mt7986-apmixed.c index dc949ed1b587..6767e9c43886 100644 --- a/drivers/clk/mediatek/clk-mt7986-apmixed.c +++ b/drivers/clk/mediatek/clk-mt7986-apmixed.c @@ -62,8 +62,9 @@ static const struct mtk_pll_data plls[] = { static const struct of_device_id of_match_clk_mt7986_apmixed[] = { { .compatible = "mediatek,mt7986-apmixedsys", }, - {} + { } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7986_apmixed); static int clk_mt7986_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt7986-eth.c b/drivers/clk/mediatek/clk-mt7986-eth.c index 138ba0a47221..0681988960cc 100644 --- a/drivers/clk/mediatek/clk-mt7986-eth.c +++ b/drivers/clk/mediatek/clk-mt7986-eth.c @@ -86,6 +86,7 @@ static const struct of_device_id of_match_clk_mt7986_eth[] = { { .compatible = "mediatek,mt7986-sgmiisys_1", .data = &sgmii1_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7986_eth); static struct platform_driver clk_mt7986_eth_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt7986-infracfg.c b/drivers/clk/mediatek/clk-mt7986-infracfg.c index 0299faad0733..b7efa70c2d6c 100644 --- a/drivers/clk/mediatek/clk-mt7986-infracfg.c +++ b/drivers/clk/mediatek/clk-mt7986-infracfg.c @@ -171,6 +171,7 @@ static const struct of_device_id of_match_clk_mt7986_infracfg[] = { { .compatible = "mediatek,mt7986-infracfg", .data = &infra_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7986_infracfg); static struct platform_driver clk_mt7986_infracfg_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt7986-topckgen.c b/drivers/clk/mediatek/clk-mt7986-topckgen.c index af9df453d6d7..fbca3feded8f 100644 --- a/drivers/clk/mediatek/clk-mt7986-topckgen.c +++ b/drivers/clk/mediatek/clk-mt7986-topckgen.c @@ -304,6 +304,7 @@ static const struct of_device_id of_match_clk_mt7986_topckgen[] = { { .compatible = "mediatek,mt7986-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt7986_topckgen); static struct platform_driver clk_mt7986_topckgen_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c index 5d8b5093ed02..fca41f50d6ba 100644 --- a/drivers/clk/mediatek/clk-mt8167-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8167-apmixedsys.c @@ -132,6 +132,7 @@ static const struct of_device_id of_match_clk_mt8167_apmixed[] = { { .compatible = "mediatek,mt8167-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167_apmixed); static struct platform_driver clk_mt8167_apmixed_drv = { .probe = clk_mt8167_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-aud.c b/drivers/clk/mediatek/clk-mt8167-aud.c index 63736642f383..86125635c8a6 100644 --- a/drivers/clk/mediatek/clk-mt8167-aud.c +++ b/drivers/clk/mediatek/clk-mt8167-aud.c @@ -52,6 +52,7 @@ static const struct of_device_id of_match_clk_mt8167_audsys[] = { { .compatible = "mediatek,mt8167-audsys", .data = &aud_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167_audsys); static struct platform_driver clk_mt8167_audsys_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-img.c b/drivers/clk/mediatek/clk-mt8167-img.c index c2537e149aa8..315b7f64bad6 100644 --- a/drivers/clk/mediatek/clk-mt8167-img.c +++ b/drivers/clk/mediatek/clk-mt8167-img.c @@ -44,6 +44,7 @@ static const struct of_device_id of_match_clk_mt8167_imgsys[] = { { .compatible = "mediatek,mt8167-imgsys", .data = &img_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167_imgsys); static struct platform_driver clk_mt8167_imgsys_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c index 340c608e7ddb..4851f5bf3a90 100644 --- a/drivers/clk/mediatek/clk-mt8167-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8167-mfgcfg.c @@ -42,6 +42,7 @@ static const struct of_device_id of_match_clk_mt8167_mfgcfg[] = { { .compatible = "mediatek,mt8167-mfgcfg", .data = &mfg_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167_mfgcfg); static struct platform_driver clk_mt8167_mfgcfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-mm.c b/drivers/clk/mediatek/clk-mt8167-mm.c index 0344f9c98d36..4e053c61315d 100644 --- a/drivers/clk/mediatek/clk-mt8167-mm.c +++ b/drivers/clk/mediatek/clk-mt8167-mm.c @@ -83,6 +83,7 @@ static const struct platform_device_id clk_mt8167_mm_id_table[] = { { .name = "clk-mt8167-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8167_mm_id_table); static struct platform_driver clk_mt8167_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8167-vdec.c b/drivers/clk/mediatek/clk-mt8167-vdec.c index 35b0380f22dc..76900f393d31 100644 --- a/drivers/clk/mediatek/clk-mt8167-vdec.c +++ b/drivers/clk/mediatek/clk-mt8167-vdec.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt8167_vdec[] = { { .compatible = "mediatek,mt8167-vdecsys", .data = &vdec_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167_vdec); static struct platform_driver clk_mt8167_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8167.c b/drivers/clk/mediatek/clk-mt8167.c index d9a837686865..b9041f79cbbd 100644 --- a/drivers/clk/mediatek/clk-mt8167.c +++ b/drivers/clk/mediatek/clk-mt8167.c @@ -883,6 +883,7 @@ static const struct of_device_id of_match_clk_mt8167[] = { { .compatible = "mediatek,mt8167-infracfg", .data = &infra_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8167); static struct platform_driver clk_mt8167_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8173-apmixedsys.c b/drivers/clk/mediatek/clk-mt8173-apmixedsys.c index 0084203e67ad..8c2aa8b0f39e 100644 --- a/drivers/clk/mediatek/clk-mt8173-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8173-apmixedsys.c @@ -135,6 +135,7 @@ static const struct of_device_id of_match_clk_mt8173_apmixed[] = { { .compatible = "mediatek,mt8173-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_apmixed); static int clk_mt8173_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt8173-img.c b/drivers/clk/mediatek/clk-mt8173-img.c index 7b50ffb7a8a5..6db2b9ab2bc9 100644 --- a/drivers/clk/mediatek/clk-mt8173-img.c +++ b/drivers/clk/mediatek/clk-mt8173-img.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt8173_imgsys[] = { { .compatible = "mediatek,mt8173-imgsys", .data = &img_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_imgsys); static struct platform_driver clk_mt8173_vdecsys_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8173-infracfg.c b/drivers/clk/mediatek/clk-mt8173-infracfg.c index 729b3c408c7b..4ed5043076ec 100644 --- a/drivers/clk/mediatek/clk-mt8173-infracfg.c +++ b/drivers/clk/mediatek/clk-mt8173-infracfg.c @@ -74,6 +74,7 @@ static const struct of_device_id of_match_clk_mt8173_infracfg[] = { { .compatible = "mediatek,mt8173-infracfg" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_infracfg); static void clk_mt8173_infra_init_early(struct device_node *node) { diff --git a/drivers/clk/mediatek/clk-mt8173-mm.c b/drivers/clk/mediatek/clk-mt8173-mm.c index ba51c22cbe7a..18e466dbf610 100644 --- a/drivers/clk/mediatek/clk-mt8173-mm.c +++ b/drivers/clk/mediatek/clk-mt8173-mm.c @@ -98,6 +98,7 @@ static const struct platform_device_id clk_mt8173_mm_id_table[] = { { .name = "clk-mt8173-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8173_mm_id_table); static struct platform_driver clk_mt8173_mm_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8173-pericfg.c b/drivers/clk/mediatek/clk-mt8173-pericfg.c index e87294b72c2c..bebda74d0f43 100644 --- a/drivers/clk/mediatek/clk-mt8173-pericfg.c +++ b/drivers/clk/mediatek/clk-mt8173-pericfg.c @@ -107,6 +107,7 @@ static const struct of_device_id of_match_clk_mt8173_pericfg[] = { { .compatible = "mediatek,mt8173-pericfg", .data = &peri_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_pericfg); static struct platform_driver clk_mt8173_pericfg_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8173-topckgen.c b/drivers/clk/mediatek/clk-mt8173-topckgen.c index 257961528fe2..baa8fd6cb312 100644 --- a/drivers/clk/mediatek/clk-mt8173-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8173-topckgen.c @@ -638,6 +638,7 @@ static const struct of_device_id of_match_clk_mt8173_topckgen[] = { { .compatible = "mediatek,mt8173-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_topckgen); static struct platform_driver clk_mt8173_topckgen_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8173-vdecsys.c b/drivers/clk/mediatek/clk-mt8173-vdecsys.c index 5105b8e0969d..625ca0b09cc2 100644 --- a/drivers/clk/mediatek/clk-mt8173-vdecsys.c +++ b/drivers/clk/mediatek/clk-mt8173-vdecsys.c @@ -42,6 +42,7 @@ static const struct of_device_id of_match_clk_mt8173_vdecsys[] = { { .compatible = "mediatek,mt8173-vdecsys", .data = &vdec_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_vdecsys); static struct platform_driver clk_mt8173_vdecsys_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8173-vencsys.c b/drivers/clk/mediatek/clk-mt8173-vencsys.c index ff4f1cb735de..87755dd1a337 100644 --- a/drivers/clk/mediatek/clk-mt8173-vencsys.c +++ b/drivers/clk/mediatek/clk-mt8173-vencsys.c @@ -49,6 +49,7 @@ static const struct of_device_id of_match_clk_mt8173_vencsys[] = { { .compatible = "mediatek,mt8173-vencltsys", .data = &venc_lt_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8173_vencsys); static struct platform_driver clk_mt8173_vencsys_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8183-apmixedsys.c b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c index 5addda17211f..2b261c0e2b61 100644 --- a/drivers/clk/mediatek/clk-mt8183-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8183-apmixedsys.c @@ -182,6 +182,7 @@ static const struct of_device_id of_match_clk_mt8183_apmixed[] = { { .compatible = "mediatek,mt8183-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_apmixed); static struct platform_driver clk_mt8183_apmixed_drv = { .probe = clk_mt8183_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-audio.c b/drivers/clk/mediatek/clk-mt8183-audio.c index fe510f02dadb..9938c6466e76 100644 --- a/drivers/clk/mediatek/clk-mt8183-audio.c +++ b/drivers/clk/mediatek/clk-mt8183-audio.c @@ -97,6 +97,7 @@ static const struct of_device_id of_match_clk_mt8183_audio[] = { { .compatible = "mediatek,mt8183-audiosys", .data = &audio_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_audio); static struct platform_driver clk_mt8183_audio_drv = { .probe = clk_mt8183_audio_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-cam.c b/drivers/clk/mediatek/clk-mt8183-cam.c index 7ecbfc50e8fe..c0719624004f 100644 --- a/drivers/clk/mediatek/clk-mt8183-cam.c +++ b/drivers/clk/mediatek/clk-mt8183-cam.c @@ -47,6 +47,7 @@ static const struct of_device_id of_match_clk_mt8183_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_cam); static struct platform_driver clk_mt8183_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-img.c b/drivers/clk/mediatek/clk-mt8183-img.c index e75d6e6205f9..55fc80615724 100644 --- a/drivers/clk/mediatek/clk-mt8183-img.c +++ b/drivers/clk/mediatek/clk-mt8183-img.c @@ -47,6 +47,7 @@ static const struct of_device_id of_match_clk_mt8183_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_img); static struct platform_driver clk_mt8183_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-ipu0.c b/drivers/clk/mediatek/clk-mt8183-ipu0.c index d1dd76e7eafd..59255eab6fe2 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu0.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu0.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt8183_ipu_core0[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_ipu_core0); static struct platform_driver clk_mt8183_ipu_core0_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-ipu1.c b/drivers/clk/mediatek/clk-mt8183-ipu1.c index 0b4906cca119..c4baa052c809 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu1.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu1.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt8183_ipu_core1[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_ipu_core1); static struct platform_driver clk_mt8183_ipu_core1_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c index 32a82ec965ef..74866e9c50d7 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_adl.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_adl.c @@ -38,6 +38,7 @@ static const struct of_device_id of_match_clk_mt8183_ipu_adl[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_ipu_adl); static struct platform_driver clk_mt8183_ipu_adl_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c index 1e2ebc0eab8b..bd7303105357 100644 --- a/drivers/clk/mediatek/clk-mt8183-ipu_conn.c +++ b/drivers/clk/mediatek/clk-mt8183-ipu_conn.c @@ -107,6 +107,7 @@ static const struct of_device_id of_match_clk_mt8183_ipu_conn[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_ipu_conn); static struct platform_driver clk_mt8183_ipu_conn_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c index 20cdbd74817f..816ecf1191ee 100644 --- a/drivers/clk/mediatek/clk-mt8183-mfgcfg.c +++ b/drivers/clk/mediatek/clk-mt8183-mfgcfg.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt8183_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_mfg); static struct platform_driver clk_mt8183_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-mm.c b/drivers/clk/mediatek/clk-mt8183-mm.c index a76e44ebf322..2f99828bff1b 100644 --- a/drivers/clk/mediatek/clk-mt8183-mm.c +++ b/drivers/clk/mediatek/clk-mt8183-mm.c @@ -91,6 +91,7 @@ static const struct platform_device_id clk_mt8183_mm_id_table[] = { { .name = "clk-mt8183-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8183_mm_id_table); static struct platform_driver clk_mt8183_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-vdec.c b/drivers/clk/mediatek/clk-mt8183-vdec.c index 0182745e2a18..513b7956cbea 100644 --- a/drivers/clk/mediatek/clk-mt8183-vdec.c +++ b/drivers/clk/mediatek/clk-mt8183-vdec.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt8183_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_vdec); static struct platform_driver clk_mt8183_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183-venc.c b/drivers/clk/mediatek/clk-mt8183-venc.c index c840e6ebe375..532f6e12a561 100644 --- a/drivers/clk/mediatek/clk-mt8183-venc.c +++ b/drivers/clk/mediatek/clk-mt8183-venc.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt8183_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183_venc); static struct platform_driver clk_mt8183_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8183.c b/drivers/clk/mediatek/clk-mt8183.c index 5ae0f1f9ca0a..2336a1b69c09 100644 --- a/drivers/clk/mediatek/clk-mt8183.c +++ b/drivers/clk/mediatek/clk-mt8183.c @@ -868,6 +868,7 @@ static const struct of_device_id of_match_clk_mt8183[] = { { .compatible = "mediatek,mt8183-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8183); static struct platform_driver clk_mt8183_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c index e429d2cdc84a..da7950d51c64 100644 --- a/drivers/clk/mediatek/clk-mt8186-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8186-apmixedsys.c @@ -136,6 +136,7 @@ static const struct of_device_id of_match_clk_mt8186_apmixed[] = { { .compatible = "mediatek,mt8186-apmixedsys", }, {} }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_apmixed); static int clk_mt8186_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt8186-cam.c b/drivers/clk/mediatek/clk-mt8186-cam.c index 90d91d045909..656d9e6f3ee2 100644 --- a/drivers/clk/mediatek/clk-mt8186-cam.c +++ b/drivers/clk/mediatek/clk-mt8186-cam.c @@ -78,6 +78,7 @@ static const struct of_device_id of_match_clk_mt8186_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_cam); static struct platform_driver clk_mt8186_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-img.c b/drivers/clk/mediatek/clk-mt8186-img.c index 11314dba4e41..754b27f03817 100644 --- a/drivers/clk/mediatek/clk-mt8186-img.c +++ b/drivers/clk/mediatek/clk-mt8186-img.c @@ -56,6 +56,7 @@ static const struct of_device_id of_match_clk_mt8186_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_img); static struct platform_driver clk_mt8186_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c index f8d1ee294f09..7619c357b150 100644 --- a/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8186-imp_iic_wrap.c @@ -55,6 +55,7 @@ static const struct of_device_id of_match_clk_mt8186_imp_iic_wrap[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_imp_iic_wrap); static struct platform_driver clk_mt8186_imp_iic_wrap_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-infra_ao.c b/drivers/clk/mediatek/clk-mt8186-infra_ao.c index 766c8e6bcf8d..a907a5def5b8 100644 --- a/drivers/clk/mediatek/clk-mt8186-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8186-infra_ao.c @@ -227,6 +227,7 @@ static const struct of_device_id of_match_clk_mt8186_infra_ao[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_infra_ao); static struct platform_driver clk_mt8186_infra_ao_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-ipe.c b/drivers/clk/mediatek/clk-mt8186-ipe.c index 0876440839df..50e340035aa7 100644 --- a/drivers/clk/mediatek/clk-mt8186-ipe.c +++ b/drivers/clk/mediatek/clk-mt8186-ipe.c @@ -43,6 +43,7 @@ static const struct of_device_id of_match_clk_mt8186_ipe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_ipe); static struct platform_driver clk_mt8186_ipe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-mcu.c b/drivers/clk/mediatek/clk-mt8186-mcu.c index 895856df95df..d1640e4dc2ad 100644 --- a/drivers/clk/mediatek/clk-mt8186-mcu.c +++ b/drivers/clk/mediatek/clk-mt8186-mcu.c @@ -52,6 +52,7 @@ static const struct of_device_id of_match_clk_mt8186_mcu[] = { { .compatible = "mediatek,mt8186-mcusys", .data = &mcu_desc }, { /* sentinel */} }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_mcu); static struct platform_driver clk_mt8186_mcu_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8186-mdp.c b/drivers/clk/mediatek/clk-mt8186-mdp.c index 194f20f16f8c..e1d19007e375 100644 --- a/drivers/clk/mediatek/clk-mt8186-mdp.c +++ b/drivers/clk/mediatek/clk-mt8186-mdp.c @@ -68,6 +68,7 @@ static const struct of_device_id of_match_clk_mt8186_mdp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_mdp); static struct platform_driver clk_mt8186_mdp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-mfg.c b/drivers/clk/mediatek/clk-mt8186-mfg.c index f16d3c44ef41..aeb098b54585 100644 --- a/drivers/clk/mediatek/clk-mt8186-mfg.c +++ b/drivers/clk/mediatek/clk-mt8186-mfg.c @@ -37,6 +37,7 @@ static const struct of_device_id of_match_clk_mt8186_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_mfg); static struct platform_driver clk_mt8186_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-mm.c b/drivers/clk/mediatek/clk-mt8186-mm.c index 9e9853a2ea91..fc3bb6d1f714 100644 --- a/drivers/clk/mediatek/clk-mt8186-mm.c +++ b/drivers/clk/mediatek/clk-mt8186-mm.c @@ -67,6 +67,8 @@ static const struct platform_device_id clk_mt8186_mm_id_table[] = { { .name = "clk-mt8186-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8186_mm_id_table); + static struct platform_driver clk_mt8186_mm_drv = { .probe = mtk_clk_pdev_probe, .remove = mtk_clk_pdev_remove, diff --git a/drivers/clk/mediatek/clk-mt8186-topckgen.c b/drivers/clk/mediatek/clk-mt8186-topckgen.c index a48172d9c5ab..1a0340a20beb 100644 --- a/drivers/clk/mediatek/clk-mt8186-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8186-topckgen.c @@ -721,6 +721,7 @@ static const struct of_device_id of_match_clk_mt8186_topck[] = { { .compatible = "mediatek,mt8186-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_topck); static struct platform_driver clk_mt8186_topck_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-vdec.c b/drivers/clk/mediatek/clk-mt8186-vdec.c index 877ca9d8ff65..9bf3b8632870 100644 --- a/drivers/clk/mediatek/clk-mt8186-vdec.c +++ b/drivers/clk/mediatek/clk-mt8186-vdec.c @@ -76,6 +76,7 @@ static const struct of_device_id of_match_clk_mt8186_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_vdec); static struct platform_driver clk_mt8186_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-venc.c b/drivers/clk/mediatek/clk-mt8186-venc.c index a89e82285d4c..0c1bc94e84cf 100644 --- a/drivers/clk/mediatek/clk-mt8186-venc.c +++ b/drivers/clk/mediatek/clk-mt8186-venc.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt8186_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_venc); static struct platform_driver clk_mt8186_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8186-wpe.c b/drivers/clk/mediatek/clk-mt8186-wpe.c index fba55f08129c..c4727b1cb64d 100644 --- a/drivers/clk/mediatek/clk-mt8186-wpe.c +++ b/drivers/clk/mediatek/clk-mt8186-wpe.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt8186_wpe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8186_wpe); static struct platform_driver clk_mt8186_wpe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-apmixedsys.c b/drivers/clk/mediatek/clk-mt8192-apmixedsys.c index 1e6988d5289a..eafd34297b9a 100644 --- a/drivers/clk/mediatek/clk-mt8192-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8192-apmixedsys.c @@ -147,6 +147,7 @@ static const struct of_device_id of_match_clk_mt8192_apmixed[] = { { .compatible = "mediatek,mt8192-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_apmixed); static int clk_mt8192_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt8192-aud.c b/drivers/clk/mediatek/clk-mt8192-aud.c index 9b14d8514b4f..ee251492d4f1 100644 --- a/drivers/clk/mediatek/clk-mt8192-aud.c +++ b/drivers/clk/mediatek/clk-mt8192-aud.c @@ -107,6 +107,7 @@ static const struct of_device_id of_match_clk_mt8192_aud[] = { { .compatible = "mediatek,mt8192-audsys", .data = &aud_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_aud); static struct platform_driver clk_mt8192_aud_drv = { .probe = clk_mt8192_aud_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-cam.c b/drivers/clk/mediatek/clk-mt8192-cam.c index 321693aff33f..7befd6ee8c79 100644 --- a/drivers/clk/mediatek/clk-mt8192-cam.c +++ b/drivers/clk/mediatek/clk-mt8192-cam.c @@ -95,6 +95,7 @@ static const struct of_device_id of_match_clk_mt8192_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_cam); static struct platform_driver clk_mt8192_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-img.c b/drivers/clk/mediatek/clk-mt8192-img.c index b2c148ead7f8..a7505150a9d0 100644 --- a/drivers/clk/mediatek/clk-mt8192-img.c +++ b/drivers/clk/mediatek/clk-mt8192-img.c @@ -58,6 +58,7 @@ static const struct of_device_id of_match_clk_mt8192_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_img); static struct platform_driver clk_mt8192_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c index fd731eb6d62e..cd5d00a7c54b 100644 --- a/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8192-imp_iic_wrap.c @@ -107,6 +107,7 @@ static const struct of_device_id of_match_clk_mt8192_imp_iic_wrap[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_imp_iic_wrap); static struct platform_driver clk_mt8192_imp_iic_wrap_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-ipe.c b/drivers/clk/mediatek/clk-mt8192-ipe.c index 3fd37977ea16..dee671ae38e6 100644 --- a/drivers/clk/mediatek/clk-mt8192-ipe.c +++ b/drivers/clk/mediatek/clk-mt8192-ipe.c @@ -45,6 +45,7 @@ static const struct of_device_id of_match_clk_mt8192_ipe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_ipe); static struct platform_driver clk_mt8192_ipe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-mdp.c b/drivers/clk/mediatek/clk-mt8192-mdp.c index 817e8bf4543b..f7b27264e378 100644 --- a/drivers/clk/mediatek/clk-mt8192-mdp.c +++ b/drivers/clk/mediatek/clk-mt8192-mdp.c @@ -70,6 +70,7 @@ static const struct of_device_id of_match_clk_mt8192_mdp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_mdp); static struct platform_driver clk_mt8192_mdp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-mfg.c b/drivers/clk/mediatek/clk-mt8192-mfg.c index 7f77e2d8b765..85f76a2bbac4 100644 --- a/drivers/clk/mediatek/clk-mt8192-mfg.c +++ b/drivers/clk/mediatek/clk-mt8192-mfg.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt8192_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_mfg); static struct platform_driver clk_mt8192_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-mm.c b/drivers/clk/mediatek/clk-mt8192-mm.c index 3e81018a038b..47335d517714 100644 --- a/drivers/clk/mediatek/clk-mt8192-mm.c +++ b/drivers/clk/mediatek/clk-mt8192-mm.c @@ -89,6 +89,7 @@ static const struct platform_device_id clk_mt8192_mm_id_table[] = { { .name = "clk-mt8192-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8192_mm_id_table); static struct platform_driver clk_mt8192_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-msdc.c b/drivers/clk/mediatek/clk-mt8192-msdc.c index cde8c88673e4..60d65f96d39a 100644 --- a/drivers/clk/mediatek/clk-mt8192-msdc.c +++ b/drivers/clk/mediatek/clk-mt8192-msdc.c @@ -52,6 +52,7 @@ static const struct of_device_id of_match_clk_mt8192_msdc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_msdc); static struct platform_driver clk_mt8192_msdc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c index df086b95d447..6aad57797c39 100644 --- a/drivers/clk/mediatek/clk-mt8192-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8192-scp_adsp.c @@ -38,6 +38,7 @@ static const struct of_device_id of_match_clk_mt8192_scp_adsp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_scp_adsp); static struct platform_driver clk_mt8192_scp_adsp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-vdec.c b/drivers/clk/mediatek/clk-mt8192-vdec.c index 2ea8b6d4d405..473afd58495c 100644 --- a/drivers/clk/mediatek/clk-mt8192-vdec.c +++ b/drivers/clk/mediatek/clk-mt8192-vdec.c @@ -82,6 +82,7 @@ static const struct of_device_id of_match_clk_mt8192_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_vdec); static struct platform_driver clk_mt8192_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192-venc.c b/drivers/clk/mediatek/clk-mt8192-venc.c index d73c12bc2ae9..57b1b16e2310 100644 --- a/drivers/clk/mediatek/clk-mt8192-venc.c +++ b/drivers/clk/mediatek/clk-mt8192-venc.c @@ -41,6 +41,7 @@ static const struct of_device_id of_match_clk_mt8192_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192_venc); static struct platform_driver clk_mt8192_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8192.c b/drivers/clk/mediatek/clk-mt8192.c index 45eccda51471..aa11291463f7 100644 --- a/drivers/clk/mediatek/clk-mt8192.c +++ b/drivers/clk/mediatek/clk-mt8192.c @@ -1019,6 +1019,7 @@ static const struct of_device_id of_match_clk_mt8192[] = { { .compatible = "mediatek,mt8192-topckgen", .data = &topck_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8192); static struct platform_driver clk_mt8192_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c index 75cc4d7a39f9..8b9b5d820286 100644 --- a/drivers/clk/mediatek/clk-mt8195-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8195-apmixedsys.c @@ -166,6 +166,7 @@ static const struct of_device_id of_match_clk_mt8195_apmixed[] = { { .compatible = "mediatek,mt8195-apmixedsys", }, {} }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_apmixed); static int clk_mt8195_apmixed_probe(struct platform_device *pdev) { diff --git a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c index b167b8d31bcc..de04c087c8c3 100644 --- a/drivers/clk/mediatek/clk-mt8195-apusys_pll.c +++ b/drivers/clk/mediatek/clk-mt8195-apusys_pll.c @@ -101,6 +101,7 @@ static const struct of_device_id of_match_clk_mt8195_apusys_pll[] = { { .compatible = "mediatek,mt8195-apusys_pll", }, {} }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_apusys_pll); static struct platform_driver clk_mt8195_apusys_pll_drv = { .probe = clk_mt8195_apusys_pll_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-cam.c b/drivers/clk/mediatek/clk-mt8195-cam.c index c515650214bd..77e608be579a 100644 --- a/drivers/clk/mediatek/clk-mt8195-cam.c +++ b/drivers/clk/mediatek/clk-mt8195-cam.c @@ -131,6 +131,7 @@ static const struct of_device_id of_match_clk_mt8195_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_cam); static struct platform_driver clk_mt8195_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-ccu.c b/drivers/clk/mediatek/clk-mt8195-ccu.c index a86f848a785d..bdc2e6f3e9ce 100644 --- a/drivers/clk/mediatek/clk-mt8195-ccu.c +++ b/drivers/clk/mediatek/clk-mt8195-ccu.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt8195_ccu[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_ccu); static struct platform_driver clk_mt8195_ccu_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-img.c b/drivers/clk/mediatek/clk-mt8195-img.c index 214baa2bc974..d853e0e63d87 100644 --- a/drivers/clk/mediatek/clk-mt8195-img.c +++ b/drivers/clk/mediatek/clk-mt8195-img.c @@ -85,6 +85,7 @@ static const struct of_device_id of_match_clk_mt8195_img[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_img); static struct platform_driver clk_mt8195_img_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c index 191f482186ae..1d808876f5c5 100644 --- a/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8195-imp_iic_wrap.c @@ -55,6 +55,7 @@ static const struct of_device_id of_match_clk_mt8195_imp_iic_wrap[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_imp_iic_wrap); static struct platform_driver clk_mt8195_imp_iic_wrap_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-infra_ao.c b/drivers/clk/mediatek/clk-mt8195-infra_ao.c index 6ad72a320d5e..f3ee4390707d 100644 --- a/drivers/clk/mediatek/clk-mt8195-infra_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-infra_ao.c @@ -229,6 +229,7 @@ static const struct of_device_id of_match_clk_mt8195_infra_ao[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_infra_ao); static struct platform_driver clk_mt8195_infra_ao_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-ipe.c b/drivers/clk/mediatek/clk-mt8195-ipe.c index b547a99b4ad9..4c47f6521275 100644 --- a/drivers/clk/mediatek/clk-mt8195-ipe.c +++ b/drivers/clk/mediatek/clk-mt8195-ipe.c @@ -40,6 +40,7 @@ static const struct of_device_id of_match_clk_mt8195_ipe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_ipe); static struct platform_driver clk_mt8195_ipe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-mfg.c b/drivers/clk/mediatek/clk-mt8195-mfg.c index 75cf643ab885..038acf0b1167 100644 --- a/drivers/clk/mediatek/clk-mt8195-mfg.c +++ b/drivers/clk/mediatek/clk-mt8195-mfg.c @@ -38,6 +38,7 @@ static const struct of_device_id of_match_clk_mt8195_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_mfg); static struct platform_driver clk_mt8195_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-peri_ao.c b/drivers/clk/mediatek/clk-mt8195-peri_ao.c index 7d65a478182d..0de162593c01 100644 --- a/drivers/clk/mediatek/clk-mt8195-peri_ao.c +++ b/drivers/clk/mediatek/clk-mt8195-peri_ao.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt8195_peri_ao[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_peri_ao); static struct platform_driver clk_mt8195_peri_ao_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c index 24e09339ed7d..d0d3e3b09780 100644 --- a/drivers/clk/mediatek/clk-mt8195-scp_adsp.c +++ b/drivers/clk/mediatek/clk-mt8195-scp_adsp.c @@ -36,6 +36,7 @@ static const struct of_device_id of_match_clk_mt8195_scp_adsp[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_scp_adsp); static struct platform_driver clk_mt8195_scp_adsp_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index adc6bb7ce750..3c2174c3e742 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1219,6 +1219,7 @@ static const struct of_device_id of_match_clk_mt8195_topck[] = { { .compatible = "mediatek,mt8195-topckgen", }, {} }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_topck); /* Register mux notifier for MFG mux */ static int clk_mt8195_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) diff --git a/drivers/clk/mediatek/clk-mt8195-vdec.c b/drivers/clk/mediatek/clk-mt8195-vdec.c index f9e2bd402627..2bcbceb10326 100644 --- a/drivers/clk/mediatek/clk-mt8195-vdec.c +++ b/drivers/clk/mediatek/clk-mt8195-vdec.c @@ -93,6 +93,7 @@ static const struct of_device_id of_match_clk_mt8195_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_vdec); static struct platform_driver clk_mt8195_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-venc.c b/drivers/clk/mediatek/clk-mt8195-venc.c index d050d87bb3f2..0991a6968765 100644 --- a/drivers/clk/mediatek/clk-mt8195-venc.c +++ b/drivers/clk/mediatek/clk-mt8195-venc.c @@ -58,6 +58,7 @@ static const struct of_device_id of_match_clk_mt8195_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_venc); static struct platform_driver clk_mt8195_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-vpp0.c b/drivers/clk/mediatek/clk-mt8195-vpp0.c index 84805a114387..1a98fb9a25e8 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp0.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp0.c @@ -95,6 +95,7 @@ static const struct platform_device_id clk_mt8195_vpp0_id_table[] = { { .name = "clk-mt8195-vpp0", .driver_data = (kernel_ulong_t)&vpp0_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8195_vpp0_id_table); static struct platform_driver clk_mt8195_vpp0_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-vpp1.c b/drivers/clk/mediatek/clk-mt8195-vpp1.c index 3e91dfed2996..c2d5b582f53a 100644 --- a/drivers/clk/mediatek/clk-mt8195-vpp1.c +++ b/drivers/clk/mediatek/clk-mt8195-vpp1.c @@ -93,6 +93,7 @@ static const struct platform_device_id clk_mt8195_vpp1_id_table[] = { { .name = "clk-mt8195-vpp1", .driver_data = (kernel_ulong_t)&vpp1_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8195_vpp1_id_table); static struct platform_driver clk_mt8195_vpp1_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8195-wpe.c b/drivers/clk/mediatek/clk-mt8195-wpe.c index 52cebe297abf..289896cb2f6c 100644 --- a/drivers/clk/mediatek/clk-mt8195-wpe.c +++ b/drivers/clk/mediatek/clk-mt8195-wpe.c @@ -132,6 +132,7 @@ static const struct of_device_id of_match_clk_mt8195_wpe[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8195_wpe); static struct platform_driver clk_mt8195_wpe_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-apmixedsys.c b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c index 55faa4e37116..9b0bc5daeac0 100644 --- a/drivers/clk/mediatek/clk-mt8365-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8365-apmixedsys.c @@ -153,6 +153,7 @@ static const struct of_device_id of_match_clk_mt8365_apmixed[] = { { .compatible = "mediatek,mt8365-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_apmixed); static struct platform_driver clk_mt8365_apmixed_drv = { .probe = clk_mt8365_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-apu.c b/drivers/clk/mediatek/clk-mt8365-apu.c index 5a594f8eccdc..74f7fb22c87f 100644 --- a/drivers/clk/mediatek/clk-mt8365-apu.c +++ b/drivers/clk/mediatek/clk-mt8365-apu.c @@ -42,6 +42,7 @@ static const struct of_device_id of_match_clk_mt8365_apu[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_apu); static struct platform_driver clk_mt8365_apu_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-cam.c b/drivers/clk/mediatek/clk-mt8365-cam.c index ed1d8dd7043c..61516e19acd1 100644 --- a/drivers/clk/mediatek/clk-mt8365-cam.c +++ b/drivers/clk/mediatek/clk-mt8365-cam.c @@ -44,6 +44,7 @@ static const struct of_device_id of_match_clk_mt8365_cam[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_cam); static struct platform_driver clk_mt8365_cam_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-mfg.c b/drivers/clk/mediatek/clk-mt8365-mfg.c index b3d10b017f0d..4c836c69db4f 100644 --- a/drivers/clk/mediatek/clk-mt8365-mfg.c +++ b/drivers/clk/mediatek/clk-mt8365-mfg.c @@ -50,6 +50,7 @@ static const struct of_device_id of_match_clk_mt8365_mfg[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_mfg); static struct platform_driver clk_mt8365_mfg_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-mm.c b/drivers/clk/mediatek/clk-mt8365-mm.c index 7ae33997ba86..44427120846f 100644 --- a/drivers/clk/mediatek/clk-mt8365-mm.c +++ b/drivers/clk/mediatek/clk-mt8365-mm.c @@ -81,6 +81,7 @@ static const struct platform_device_id clk_mt8365_mm_id_table[] = { { .name = "clk-mt8365-mm", .driver_data = (kernel_ulong_t)&mm_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(platform, clk_mt8365_mm_id_table); static struct platform_driver clk_mt8365_mm_drv = { .probe = mtk_clk_pdev_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-vdec.c b/drivers/clk/mediatek/clk-mt8365-vdec.c index d5caddcc5932..b51571e9da00 100644 --- a/drivers/clk/mediatek/clk-mt8365-vdec.c +++ b/drivers/clk/mediatek/clk-mt8365-vdec.c @@ -50,6 +50,7 @@ static const struct of_device_id of_match_clk_mt8365_vdec[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_vdec); static struct platform_driver clk_mt8365_vdec_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365-venc.c b/drivers/clk/mediatek/clk-mt8365-venc.c index 08b7c0ee52e7..572344645c86 100644 --- a/drivers/clk/mediatek/clk-mt8365-venc.c +++ b/drivers/clk/mediatek/clk-mt8365-venc.c @@ -39,6 +39,7 @@ static const struct of_device_id of_match_clk_mt8365_venc[] = { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365_venc); static struct platform_driver clk_mt8365_venc_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8365.c b/drivers/clk/mediatek/clk-mt8365.c index 208cdc157918..6b4e193f648d 100644 --- a/drivers/clk/mediatek/clk-mt8365.c +++ b/drivers/clk/mediatek/clk-mt8365.c @@ -791,6 +791,7 @@ static const struct of_device_id of_match_clk_mt8365[] = { { .compatible = "mediatek,mt8365-mcucfg", .data = &mcu_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8365); static struct platform_driver clk_mt8365_drv = { .driver = { diff --git a/drivers/clk/mediatek/clk-mt8516-apmixedsys.c b/drivers/clk/mediatek/clk-mt8516-apmixedsys.c index 5b87c9fb81f5..edd9174d2f2f 100644 --- a/drivers/clk/mediatek/clk-mt8516-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8516-apmixedsys.c @@ -107,6 +107,7 @@ static const struct of_device_id of_match_clk_mt8516_apmixed[] = { { .compatible = "mediatek,mt8516-apmixedsys" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8516_apmixed); static struct platform_driver clk_mt8516_apmixed_drv = { .probe = clk_mt8516_apmixed_probe, diff --git a/drivers/clk/mediatek/clk-mt8516-aud.c b/drivers/clk/mediatek/clk-mt8516-aud.c index 5f34487aad7e..48340fc7430d 100644 --- a/drivers/clk/mediatek/clk-mt8516-aud.c +++ b/drivers/clk/mediatek/clk-mt8516-aud.c @@ -51,6 +51,7 @@ static const struct of_device_id of_match_clk_mt8516_aud[] = { { .compatible = "mediatek,mt8516-audsys", .data = &aud_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8516_aud); static struct platform_driver clk_mt8516_aud_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8516.c b/drivers/clk/mediatek/clk-mt8516.c index ad59e932d4aa..21eb052b0a53 100644 --- a/drivers/clk/mediatek/clk-mt8516.c +++ b/drivers/clk/mediatek/clk-mt8516.c @@ -665,6 +665,7 @@ static const struct of_device_id of_match_clk_mt8516[] = { { .compatible = "mediatek,mt8516-infracfg", .data = &infra_desc }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8516); static struct platform_driver clk_mt8516_drv = { .probe = mtk_clk_simple_probe, -- GitLab From aafcf16c9e567f7a606f28272baa35bd697508a7 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:39 +0100 Subject: [PATCH 0393/5631] clk: mediatek: mt8135: Move apmixedsys to its own file In preparation for migrating mt8135 clocks to the common simple probe mechanism, move the apmixedsys clocks to a different file. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-51-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8135-apmixedsys.c | 62 ++++++++++++++++++++ drivers/clk/mediatek/clk-mt8135.c | 46 --------------- 3 files changed, 63 insertions(+), 47 deletions(-) create mode 100644 drivers/clk/mediatek/clk-mt8135-apmixedsys.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 048a150a7637..bcd3b8c465aa 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -62,7 +62,7 @@ obj-$(CONFIG_COMMON_CLK_MT7986) += clk-mt7986-apmixed.o obj-$(CONFIG_COMMON_CLK_MT7986) += clk-mt7986-topckgen.o obj-$(CONFIG_COMMON_CLK_MT7986) += clk-mt7986-infracfg.o obj-$(CONFIG_COMMON_CLK_MT7986_ETHSYS) += clk-mt7986-eth.o -obj-$(CONFIG_COMMON_CLK_MT8135) += clk-mt8135.o +obj-$(CONFIG_COMMON_CLK_MT8135) += clk-mt8135-apmixedsys.o clk-mt8135.o obj-$(CONFIG_COMMON_CLK_MT8167) += clk-mt8167-apmixedsys.o clk-mt8167.o obj-$(CONFIG_COMMON_CLK_MT8167_AUDSYS) += clk-mt8167-aud.o obj-$(CONFIG_COMMON_CLK_MT8167_IMGSYS) += clk-mt8167-img.o diff --git a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c new file mode 100644 index 000000000000..2b4d379300fc --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2014 MediaTek Inc. + * James Liao + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno + */ + +#include +#include +#include +#include + +#include "clk-mtk.h" +#include "clk-pll.h" + +#define MT8135_PLL_FMAX (2000 * MHZ) +#define CON0_MT8135_RST_BAR BIT(27) + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = CON0_MT8135_RST_BAR, \ + .fmax = MT8135_PLL_FMAX, \ + .pcwbits = _pcwbits, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + } + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_ARMPLL1, "armpll1", 0x200, 0x218, 0x80000000, 0, 21, 0x204, 24, 0x0, 0x204, 0), + PLL(CLK_APMIXED_ARMPLL2, "armpll2", 0x2cc, 0x2e4, 0x80000000, 0, 21, 0x2d0, 24, 0x0, 0x2d0, 0), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x21c, 0x234, 0xf0000000, HAVE_RST_BAR, 21, 0x21c, 6, 0x0, 0x220, 0), + PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x238, 0x250, 0xf3000000, HAVE_RST_BAR, 7, 0x238, 6, 0x0, 0x238, 9), + PLL(CLK_APMIXED_MMPLL, "mmpll", 0x254, 0x26c, 0xf0000000, HAVE_RST_BAR, 21, 0x254, 6, 0x0, 0x258, 0), + PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x278, 0x290, 0x80000000, 0, 21, 0x278, 6, 0x0, 0x27c, 0), + PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x294, 0x2ac, 0x80000000, 0, 31, 0x294, 6, 0x0, 0x298, 0), + PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x2b0, 0x2c8, 0x80000000, 0, 21, 0x2b0, 6, 0x0, 0x2b4, 0), + PLL(CLK_APMIXED_AUDPLL, "audpll", 0x2e8, 0x300, 0x80000000, 0, 31, 0x2e8, 6, 0x2f8, 0x2ec, 0), + PLL(CLK_APMIXED_VDECPLL, "vdecpll", 0x304, 0x31c, 0x80000000, 0, 21, 0x2b0, 6, 0x0, 0x308, 0), +}; + +static void __init mtk_apmixedsys_init(struct device_node *node) +{ + struct clk_hw_onecell_data *clk_data; + + clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return; + + mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); +} +CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8135-apmixedsys", + mtk_apmixedsys_init); +MODULE_LICENSE("GPL"); diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 98165b1f7c97..2a9405b552c6 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -592,50 +592,4 @@ static void __init mtk_pericfg_init(struct device_node *node) mtk_register_reset_controller(node, &clk_rst_desc[1]); } CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8135-pericfg", mtk_pericfg_init); - -#define MT8135_PLL_FMAX (2000 * MHZ) -#define CON0_MT8135_RST_BAR BIT(27) - -#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift) { \ - .id = _id, \ - .name = _name, \ - .reg = _reg, \ - .pwr_reg = _pwr_reg, \ - .en_mask = _en_mask, \ - .flags = _flags, \ - .rst_bar_mask = CON0_MT8135_RST_BAR, \ - .fmax = MT8135_PLL_FMAX, \ - .pcwbits = _pcwbits, \ - .pd_reg = _pd_reg, \ - .pd_shift = _pd_shift, \ - .tuner_reg = _tuner_reg, \ - .pcw_reg = _pcw_reg, \ - .pcw_shift = _pcw_shift, \ - } - -static const struct mtk_pll_data plls[] = { - PLL(CLK_APMIXED_ARMPLL1, "armpll1", 0x200, 0x218, 0x80000000, 0, 21, 0x204, 24, 0x0, 0x204, 0), - PLL(CLK_APMIXED_ARMPLL2, "armpll2", 0x2cc, 0x2e4, 0x80000000, 0, 21, 0x2d0, 24, 0x0, 0x2d0, 0), - PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x21c, 0x234, 0xf0000000, HAVE_RST_BAR, 21, 0x21c, 6, 0x0, 0x220, 0), - PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x238, 0x250, 0xf3000000, HAVE_RST_BAR, 7, 0x238, 6, 0x0, 0x238, 9), - PLL(CLK_APMIXED_MMPLL, "mmpll", 0x254, 0x26c, 0xf0000000, HAVE_RST_BAR, 21, 0x254, 6, 0x0, 0x258, 0), - PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x278, 0x290, 0x80000000, 0, 21, 0x278, 6, 0x0, 0x27c, 0), - PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x294, 0x2ac, 0x80000000, 0, 31, 0x294, 6, 0x0, 0x298, 0), - PLL(CLK_APMIXED_LVDSPLL, "lvdspll", 0x2b0, 0x2c8, 0x80000000, 0, 21, 0x2b0, 6, 0x0, 0x2b4, 0), - PLL(CLK_APMIXED_AUDPLL, "audpll", 0x2e8, 0x300, 0x80000000, 0, 31, 0x2e8, 6, 0x2f8, 0x2ec, 0), - PLL(CLK_APMIXED_VDECPLL, "vdecpll", 0x304, 0x31c, 0x80000000, 0, 21, 0x2b0, 6, 0x0, 0x308, 0), -}; - -static void __init mtk_apmixedsys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - - clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); - if (!clk_data) - return; - - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); -} -CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8135-apmixedsys", - mtk_apmixedsys_init); MODULE_LICENSE("GPL"); -- GitLab From f4f9a9c003b52ea3cffda186753bfb3e37b970f8 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:40 +0100 Subject: [PATCH 0394/5631] clk: mediatek: mt8135: Properly use CLK_IS_CRITICAL flag Instead of calling clk_prepare_enable() for clocks that shall stay enabled, use the CLK_IS_CRITICAL flag, which purpose is exactly that. Fixes: a8aede794843 ("clk: mediatek: Add basic clocks for Mediatek MT8135.") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-52-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8135.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 2a9405b552c6..1c76c0003f99 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -2,6 +2,8 @@ /* * Copyright (c) 2014 MediaTek Inc. * Author: James Liao + * Copyright (c) 2023 Collabora, Ltd. + * AngeloGioacchino Del Regno */ #include @@ -390,7 +392,7 @@ static const struct mtk_composite top_muxes[] __initconst = { MUX_GATE(CLK_TOP_GCPU_SEL, "gcpu_sel", gcpu_parents, 0x0164, 24, 3, 31), /* CLK_CFG_9 */ MUX_GATE(CLK_TOP_DPI1_SEL, "dpi1_sel", dpi1_parents, 0x0168, 0, 2, 7), - MUX_GATE(CLK_TOP_CCI_SEL, "cci_sel", cci_parents, 0x0168, 8, 3, 15), + MUX_GATE_FLAGS(CLK_TOP_CCI_SEL, "cci_sel", cci_parents, 0x0168, 8, 3, 15, CLK_IS_CRITICAL), MUX_GATE(CLK_TOP_APLL_SEL, "apll_sel", apll_parents, 0x0168, 16, 3, 23), MUX_GATE(CLK_TOP_HDMIPLL_SEL, "hdmipll_sel", hdmipll_parents, 0x0168, 24, 2, 31), }; @@ -404,6 +406,10 @@ static const struct mtk_gate_regs infra_cg_regs = { #define GATE_ICG(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &infra_cg_regs, _shift, &mtk_clk_gate_ops_setclr) +#define GATE_ICG_AO(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, CLK_IS_CRITICAL) + static const struct mtk_gate infra_clks[] __initconst = { GATE_ICG(CLK_INFRA_PMIC_WRAP, "pmic_wrap_ck", "axi_sel", 23), GATE_ICG(CLK_INFRA_PMICSPI, "pmicspi_ck", "pmicspi_sel", 22), @@ -411,7 +417,7 @@ static const struct mtk_gate infra_clks[] __initconst = { GATE_ICG(CLK_INFRA_CCIF0_AP_CTRL, "ccif0_ap_ctrl", "axi_sel", 20), GATE_ICG(CLK_INFRA_KP, "kp_ck", "axi_sel", 16), GATE_ICG(CLK_INFRA_CPUM, "cpum_ck", "cpum_tck_in", 15), - GATE_ICG(CLK_INFRA_M4U, "m4u_ck", "mem_sel", 8), + GATE_ICG_AO(CLK_INFRA_M4U, "m4u_ck", "mem_sel", 8), GATE_ICG(CLK_INFRA_MFGAXI, "mfgaxi_ck", "axi_sel", 7), GATE_ICG(CLK_INFRA_DEVAPC, "devapc_ck", "axi_sel", 6), GATE_ICG(CLK_INFRA_AUDIO, "audio_ck", "aud_intbus_sel", 5), @@ -534,8 +540,6 @@ static void __init mtk_topckgen_init(struct device_node *node) ARRAY_SIZE(top_muxes), base, &mt8135_clk_lock, clk_data); - clk_prepare_enable(clk_data->hws[CLK_TOP_CCI_SEL]->clk); - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) pr_err("%s(): could not register clock provider: %d\n", @@ -553,8 +557,6 @@ static void __init mtk_infrasys_init(struct device_node *node) mtk_clk_register_gates(NULL, node, infra_clks, ARRAY_SIZE(infra_clks), clk_data); - clk_prepare_enable(clk_data->hws[CLK_INFRA_M4U]->clk); - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); if (r) pr_err("%s(): could not register clock provider: %d\n", -- GitLab From 54b7026f011e25826e1b56ea2a5ace30516bf706 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:41 +0100 Subject: [PATCH 0395/5631] clk: mediatek: mt8135-apmixedsys: Convert to platform_driver and module Convert apmixedsys clocks to be a platform driver; while at it, also add necessary error handling to the probe function, add a remove callback and provide a MODULE_DESCRIPTION(). This driver is now compatible with an eventual module build. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-53-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8135-apmixedsys.c | 53 ++++++++++++++++++-- 1 file changed, 48 insertions(+), 5 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c index 2b4d379300fc..744aae092281 100644 --- a/drivers/clk/mediatek/clk-mt8135-apmixedsys.c +++ b/drivers/clk/mediatek/clk-mt8135-apmixedsys.c @@ -47,16 +47,59 @@ static const struct mtk_pll_data plls[] = { PLL(CLK_APMIXED_VDECPLL, "vdecpll", 0x304, 0x31c, 0x80000000, 0, 21, 0x2b0, 6, 0x0, 0x308, 0), }; -static void __init mtk_apmixedsys_init(struct device_node *node) +static int clk_mt8135_apmixed_probe(struct platform_device *pdev) { struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + int ret; clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); if (!clk_data) - return; + return -ENOMEM; - mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + ret = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (ret) + return ret; + + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (ret) + goto unregister_plls; + + return 0; + +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + + return ret; +} + +static int clk_mt8135_apmixed_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_free_clk_data(clk_data); + + return 0; } -CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8135-apmixedsys", - mtk_apmixedsys_init); + +static const struct of_device_id of_match_clk_mt8135_apmixed[] = { + { .compatible = "mediatek,mt8135-apmixedsys" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8135_apmixed); + +static struct platform_driver clk_mt8135_apmixed_drv = { + .probe = clk_mt8135_apmixed_probe, + .remove = clk_mt8135_apmixed_remove, + .driver = { + .name = "clk-mt8135-apmixed", + .of_match_table = of_match_clk_mt8135_apmixed, + }, +}; +module_platform_driver(clk_mt8135_apmixed_drv) + +MODULE_DESCRIPTION("MediaTek MT8135 apmixedsys clocks driver"); MODULE_LICENSE("GPL"); -- GitLab From 139e62185668d9c5add561177ba85f5a598113da Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:42 +0100 Subject: [PATCH 0396/5631] clk: mediatek: mt8135: Join root_clk_alias and top_divs arrays In preparation for converting this driver to the common simple probe mechanism, join the root_clk_alias and top_divs mtk_fixed_factor arrays. This commit brings no functional change. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-54-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-mt8135.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 1c76c0003f99..8785d58cb3a5 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -2,8 +2,6 @@ /* * Copyright (c) 2014 MediaTek Inc. * Author: James Liao - * Copyright (c) 2023 Collabora, Ltd. - * AngeloGioacchino Del Regno */ #include @@ -19,14 +17,12 @@ static DEFINE_SPINLOCK(mt8135_clk_lock); -static const struct mtk_fixed_factor root_clk_alias[] __initconst = { +static const struct mtk_fixed_factor top_divs[] __initconst = { FACTOR(CLK_TOP_DSI0_LNTC_DSICLK, "dsi0_lntc_dsiclk", "clk_null", 1, 1), FACTOR(CLK_TOP_HDMITX_CLKDIG_CTS, "hdmitx_clkdig_cts", "clk_null", 1, 1), FACTOR(CLK_TOP_CLKPH_MCK, "clkph_mck", "clk_null", 1, 1), FACTOR(CLK_TOP_CPUM_TCK_IN, "cpum_tck_in", "clk_null", 1, 1), -}; -static const struct mtk_fixed_factor top_divs[] __initconst = { FACTOR(CLK_TOP_MAINPLL_806M, "mainpll_806m", "mainpll", 1, 2), FACTOR(CLK_TOP_MAINPLL_537P3M, "mainpll_537p3m", "mainpll", 1, 3), FACTOR(CLK_TOP_MAINPLL_322P4M, "mainpll_322p4m", "mainpll", 1, 5), @@ -534,7 +530,6 @@ static void __init mtk_topckgen_init(struct device_node *node) clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data); mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); mtk_clk_register_composites(NULL, top_muxes, ARRAY_SIZE(top_muxes), base, -- GitLab From 10966457a96d12f4b0db9c9874e07d06977255c9 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 6 Mar 2023 15:05:43 +0100 Subject: [PATCH 0397/5631] clk: mediatek: mt8135: Convert to simple probe and enable module build Convert the MT8135 clock drivers to platform_driver using the common simple probe mechanism; special note goes to the introduction of dummy clocks with ID 0 (where 0 is the first entry of a clock array) for each clock controller: this was necessary because of a mistake in the bindings for all MT8135 clock controllers, where the first clock has ID 1 (hence, array would start from element 1) instead of zero. Now that all of the MT8135 clock drivers (including apmixedsys) can be compiled as modules, change the COMMON_CLK_MT8135 configuration option to tristate to enable module build. While at it, also remove the __initconst annotation from all of the clock arrays as they are not only used during init anymore, but also during runtime. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Chen-Yu Tsai Link: https://lore.kernel.org/r/20230306140543.1813621-55-angelogioacchino.delregno@collabora.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 2 +- drivers/clk/mediatek/clk-mt8135.c | 176 +++++++++++++----------------- 2 files changed, 76 insertions(+), 102 deletions(-) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 02093996ccc3..7a12aefb1d0b 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -423,7 +423,7 @@ config COMMON_CLK_MT7986_ETHSYS required on MediaTek MT7986 SoC. config COMMON_CLK_MT8135 - bool "Clock driver for MediaTek MT8135" + tristate "Clock driver for MediaTek MT8135" depends on (ARCH_MEDIATEK && ARM) || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK && ARM diff --git a/drivers/clk/mediatek/clk-mt8135.c b/drivers/clk/mediatek/clk-mt8135.c index 8785d58cb3a5..084e48a554c2 100644 --- a/drivers/clk/mediatek/clk-mt8135.c +++ b/drivers/clk/mediatek/clk-mt8135.c @@ -5,8 +5,10 @@ */ #include +#include #include #include +#include #include #include #include @@ -17,7 +19,8 @@ static DEFINE_SPINLOCK(mt8135_clk_lock); -static const struct mtk_fixed_factor top_divs[] __initconst = { +static const struct mtk_fixed_factor top_divs[] = { + FACTOR(CLK_DUMMY, "top_divs_dummy", "clk_null", 1, 1), FACTOR(CLK_TOP_DSI0_LNTC_DSICLK, "dsi0_lntc_dsiclk", "clk_null", 1, 1), FACTOR(CLK_TOP_HDMITX_CLKDIG_CTS, "hdmitx_clkdig_cts", "clk_null", 1, 1), FACTOR(CLK_TOP_CLKPH_MCK, "clkph_mck", "clk_null", 1, 1), @@ -98,7 +101,7 @@ static const struct mtk_fixed_factor top_divs[] __initconst = { FACTOR(CLK_TOP_MEMPLL_MCK_D4, "mempll_mck_d4", "clkph_mck", 1, 4), }; -static const char * const axi_parents[] __initconst = { +static const char * const axi_parents[] = { "clk26m", "syspll_d3", "syspll_d4", @@ -108,7 +111,7 @@ static const char * const axi_parents[] __initconst = { "syspll_d3p5" }; -static const char * const smi_parents[] __initconst = { +static const char * const smi_parents[] = { "clk26m", "clkph_mck", "syspll_d2p5", @@ -126,7 +129,7 @@ static const char * const smi_parents[] __initconst = { "lvdspll" }; -static const char * const mfg_parents[] __initconst = { +static const char * const mfg_parents[] = { "clk26m", "univpll1_d4", "syspll_d2", @@ -142,13 +145,13 @@ static const char * const mfg_parents[] __initconst = { "mmpll_d7" }; -static const char * const irda_parents[] __initconst = { +static const char * const irda_parents[] = { "clk26m", "univpll2_d8", "univpll1_d6" }; -static const char * const cam_parents[] __initconst = { +static const char * const cam_parents[] = { "clk26m", "syspll_d3", "syspll_d3p5", @@ -159,13 +162,13 @@ static const char * const cam_parents[] __initconst = { "univpll1_d4" }; -static const char * const aud_intbus_parents[] __initconst = { +static const char * const aud_intbus_parents[] = { "clk26m", "syspll_d6", "univpll_d10" }; -static const char * const jpg_parents[] __initconst = { +static const char * const jpg_parents[] = { "clk26m", "syspll_d5", "syspll_d4", @@ -175,7 +178,7 @@ static const char * const jpg_parents[] __initconst = { "univpll_d5" }; -static const char * const disp_parents[] __initconst = { +static const char * const disp_parents[] = { "clk26m", "syspll_d3p5", "syspll_d3", @@ -186,7 +189,7 @@ static const char * const disp_parents[] __initconst = { "vdecpll" }; -static const char * const msdc30_parents[] __initconst = { +static const char * const msdc30_parents[] = { "clk26m", "syspll_d6", "syspll_d5", @@ -195,13 +198,13 @@ static const char * const msdc30_parents[] __initconst = { "msdcpll" }; -static const char * const usb20_parents[] __initconst = { +static const char * const usb20_parents[] = { "clk26m", "univpll2_d6", "univpll1_d10" }; -static const char * const venc_parents[] __initconst = { +static const char * const venc_parents[] = { "clk26m", "syspll_d3", "syspll_d8", @@ -212,7 +215,7 @@ static const char * const venc_parents[] __initconst = { "mmpll_d6" }; -static const char * const spi_parents[] __initconst = { +static const char * const spi_parents[] = { "clk26m", "syspll_d6", "syspll_d8", @@ -221,17 +224,17 @@ static const char * const spi_parents[] __initconst = { "univpll1_d8" }; -static const char * const uart_parents[] __initconst = { +static const char * const uart_parents[] = { "clk26m", "univpll2_d8" }; -static const char * const mem_parents[] __initconst = { +static const char * const mem_parents[] = { "clk26m", "clkph_mck" }; -static const char * const camtg_parents[] __initconst = { +static const char * const camtg_parents[] = { "clk26m", "univpll_d26", "univpll1_d6", @@ -239,12 +242,12 @@ static const char * const camtg_parents[] __initconst = { "syspll_d8" }; -static const char * const audio_parents[] __initconst = { +static const char * const audio_parents[] = { "clk26m", "syspll_d24" }; -static const char * const fix_parents[] __initconst = { +static const char * const fix_parents[] = { "rtc32k", "clk26m", "univpll_d5", @@ -255,7 +258,7 @@ static const char * const fix_parents[] __initconst = { "univpll1_d8" }; -static const char * const vdec_parents[] __initconst = { +static const char * const vdec_parents[] = { "clk26m", "vdecpll", "clkph_mck", @@ -274,13 +277,13 @@ static const char * const vdec_parents[] __initconst = { "lvdspll" }; -static const char * const ddrphycfg_parents[] __initconst = { +static const char * const ddrphycfg_parents[] = { "clk26m", "axi_sel", "syspll_d12" }; -static const char * const dpilvds_parents[] __initconst = { +static const char * const dpilvds_parents[] = { "clk26m", "lvdspll", "lvdspll_d2", @@ -288,7 +291,7 @@ static const char * const dpilvds_parents[] __initconst = { "lvdspll_d8" }; -static const char * const pmicspi_parents[] __initconst = { +static const char * const pmicspi_parents[] = { "clk26m", "univpll2_d6", "syspll_d8", @@ -299,14 +302,14 @@ static const char * const pmicspi_parents[] __initconst = { "syspll_d24" }; -static const char * const smi_mfg_as_parents[] __initconst = { +static const char * const smi_mfg_as_parents[] = { "clk26m", "smi_sel", "mfg_sel", "mem_sel" }; -static const char * const gcpu_parents[] __initconst = { +static const char * const gcpu_parents[] = { "clk26m", "syspll_d4", "univpll_d7", @@ -314,14 +317,14 @@ static const char * const gcpu_parents[] __initconst = { "syspll_d6" }; -static const char * const dpi1_parents[] __initconst = { +static const char * const dpi1_parents[] = { "clk26m", "tvhdmi_h_ck", "tvhdmi_d2", "tvhdmi_d4" }; -static const char * const cci_parents[] __initconst = { +static const char * const cci_parents[] = { "clk26m", "mainpll_537p3m", "univpll_d3", @@ -330,7 +333,7 @@ static const char * const cci_parents[] __initconst = { "syspll_d5" }; -static const char * const apll_parents[] __initconst = { +static const char * const apll_parents[] = { "clk26m", "apll_ck", "apll_d4", @@ -339,14 +342,14 @@ static const char * const apll_parents[] __initconst = { "apll_d24" }; -static const char * const hdmipll_parents[] __initconst = { +static const char * const hdmipll_parents[] = { "clk26m", "hdmitx_clkdig_cts", "hdmitx_clkdig_d2", "hdmitx_clkdig_d3" }; -static const struct mtk_composite top_muxes[] __initconst = { +static const struct mtk_composite top_muxes[] = { /* CLK_CFG_0 */ MUX_GATE(CLK_TOP_AXI_SEL, "axi_sel", axi_parents, 0x0140, 0, 3, INVALID_MUX_GATE_BIT), @@ -406,7 +409,8 @@ static const struct mtk_gate_regs infra_cg_regs = { GATE_MTK_FLAGS(_id, _name, _parent, &infra_cg_regs, _shift, \ &mtk_clk_gate_ops_setclr, CLK_IS_CRITICAL) -static const struct mtk_gate infra_clks[] __initconst = { +static const struct mtk_gate infra_clks[] = { + GATE_DUMMY(CLK_DUMMY, "infra_dummy"), GATE_ICG(CLK_INFRA_PMIC_WRAP, "pmic_wrap_ck", "axi_sel", 23), GATE_ICG(CLK_INFRA_PMICSPI, "pmicspi_ck", "pmicspi_sel", 22), GATE_ICG(CLK_INFRA_CCIF1_AP_CTRL, "ccif1_ap_ctrl", "axi_sel", 21), @@ -440,7 +444,8 @@ static const struct mtk_gate_regs peri1_cg_regs = { #define GATE_PERI1(_id, _name, _parent, _shift) \ GATE_MTK(_id, _name, _parent, &peri1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) -static const struct mtk_gate peri_gates[] __initconst = { +static const struct mtk_gate peri_gates[] = { + GATE_DUMMY(CLK_DUMMY, "peri_dummy"), /* PERI0 */ GATE_PERI0(CLK_PERI_I2C5, "i2c5_ck", "axi_sel", 31), GATE_PERI0(CLK_PERI_I2C4, "i2c4_ck", "axi_sel", 30), @@ -486,12 +491,12 @@ static const struct mtk_gate peri_gates[] __initconst = { GATE_PERI1(CLK_PERI_I2C6, "i2c6_ck", "axi_sel", 0), }; -static const char * const uart_ck_sel_parents[] __initconst = { +static const char * const uart_ck_sel_parents[] = { "clk26m", "uart_sel", }; -static const struct mtk_composite peri_clks[] __initconst = { +static const struct mtk_composite peri_clks[] = { MUX(CLK_PERI_UART0_SEL, "uart0_ck_sel", uart_ck_sel_parents, 0x40c, 0, 1), MUX(CLK_PERI_UART1_SEL, "uart1_ck_sel", uart_ck_sel_parents, 0x40c, 1, 1), MUX(CLK_PERI_UART2_SEL, "uart2_ck_sel", uart_ck_sel_parents, 0x40c, 2, 1), @@ -516,77 +521,46 @@ static const struct mtk_clk_rst_desc clk_rst_desc[] = { } }; -static void __init mtk_topckgen_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - void __iomem *base; - int r; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } +static const struct mtk_clk_desc infra_desc = { + .clks = infra_clks, + .num_clks = ARRAY_SIZE(infra_clks), + .rst_desc = &clk_rst_desc[0], +}; - clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); - - mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data); - mtk_clk_register_composites(NULL, top_muxes, - ARRAY_SIZE(top_muxes), base, - &mt8135_clk_lock, clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); -} -CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8135-topckgen", mtk_topckgen_init); - -static void __init mtk_infrasys_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - - clk_data = mtk_alloc_clk_data(CLK_INFRA_NR_CLK); - - mtk_clk_register_gates(NULL, node, infra_clks, - ARRAY_SIZE(infra_clks), clk_data); - - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); - - mtk_register_reset_controller(node, &clk_rst_desc[0]); -} -CLK_OF_DECLARE(mtk_infrasys, "mediatek,mt8135-infracfg", mtk_infrasys_init); - -static void __init mtk_pericfg_init(struct device_node *node) -{ - struct clk_hw_onecell_data *clk_data; - int r; - void __iomem *base; - - base = of_iomap(node, 0); - if (!base) { - pr_err("%s(): ioremap failed\n", __func__); - return; - } +static const struct mtk_clk_desc peri_desc = { + .clks = peri_gates, + .num_clks = ARRAY_SIZE(peri_gates), + .composite_clks = peri_clks, + .num_composite_clks = ARRAY_SIZE(peri_clks), + .clk_lock = &mt8135_clk_lock, + .rst_desc = &clk_rst_desc[1], +}; - clk_data = mtk_alloc_clk_data(CLK_PERI_NR_CLK); +static const struct mtk_clk_desc topck_desc = { + .factor_clks = top_divs, + .num_factor_clks = ARRAY_SIZE(top_divs), + .composite_clks = top_muxes, + .num_composite_clks = ARRAY_SIZE(top_muxes), + .clk_lock = &mt8135_clk_lock, +}; - mtk_clk_register_gates(NULL, node, peri_gates, - ARRAY_SIZE(peri_gates), clk_data); - mtk_clk_register_composites(NULL, peri_clks, - ARRAY_SIZE(peri_clks), base, - &mt8135_clk_lock, clk_data); +static const struct of_device_id of_match_clk_mt8135[] = { + { .compatible = "mediatek,mt8135-infracfg", .data = &infra_desc }, + { .compatible = "mediatek,mt8135-pericfg", .data = &peri_desc }, + { .compatible = "mediatek,mt8135-topckgen", .data = &topck_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8135); - r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); - if (r) - pr_err("%s(): could not register clock provider: %d\n", - __func__, r); +static struct platform_driver clk_mt8135_drv = { + .driver = { + .name = "clk-mt8135", + .of_match_table = of_match_clk_mt8135, + }, + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, +}; +module_platform_driver(clk_mt8135_drv); - mtk_register_reset_controller(node, &clk_rst_desc[1]); -} -CLK_OF_DECLARE(mtk_pericfg, "mediatek,mt8135-pericfg", mtk_pericfg_init); +MODULE_DESCRIPTION("MediaTek MT8135 clocks driver"); MODULE_LICENSE("GPL"); -- GitLab From c6d616fe10c62f528c8c52663aec338d2f4ee4c3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:37 -0800 Subject: [PATCH 0398/5631] perf evsel: Allow const evsel for certain accesses List sorting, added later to evlist, passes const elements requiring helper functions to also be const. Make the argument to evsel__find_pmu, evsel__is_aux_event and evsel__leader const. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 2 +- tools/perf/util/evsel.h | 6 +++--- tools/perf/util/pmu.c | 6 +++--- tools/perf/util/python.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 462cc0673cee..798f072b2763 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -3139,7 +3139,7 @@ bool evsel__is_hybrid(const struct evsel *evsel) return evsel->pmu_name && perf_pmu__is_hybrid(evsel->pmu_name); } -struct evsel *evsel__leader(struct evsel *evsel) +struct evsel *evsel__leader(const struct evsel *evsel) { return container_of(evsel->core.leader, struct evsel, core); } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 814a49ebb7e3..676c499323e9 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -212,8 +212,8 @@ int evsel__object_config(size_t object_size, int (*init)(struct evsel *evsel), void (*fini)(struct evsel *evsel)); -struct perf_pmu *evsel__find_pmu(struct evsel *evsel); -bool evsel__is_aux_event(struct evsel *evsel); +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel); +bool evsel__is_aux_event(const struct evsel *evsel); struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx); @@ -505,7 +505,7 @@ int evsel__store_ids(struct evsel *evsel, struct evlist *evlist); void evsel__zero_per_pkg(struct evsel *evsel); bool evsel__is_hybrid(const struct evsel *evsel); -struct evsel *evsel__leader(struct evsel *evsel); +struct evsel *evsel__leader(const struct evsel *evsel); bool evsel__has_leader(struct evsel *evsel, struct evsel *leader); bool evsel__is_leader(struct evsel *evsel); void evsel__set_leader(struct evsel *evsel, struct evsel *leader); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 43b6182d96b7..45d9b8e28e16 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -988,7 +988,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu) return NULL; } -struct perf_pmu *evsel__find_pmu(struct evsel *evsel) +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) { struct perf_pmu *pmu = NULL; @@ -1000,11 +1000,11 @@ struct perf_pmu *evsel__find_pmu(struct evsel *evsel) break; } - evsel->pmu = pmu; + ((struct evsel *)evsel)->pmu = pmu; return pmu; } -bool evsel__is_aux_event(struct evsel *evsel) +bool evsel__is_aux_event(const struct evsel *evsel) { struct perf_pmu *pmu = evsel__find_pmu(evsel); diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 42e8b813d010..ab48ffbb6448 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -83,7 +83,7 @@ const char *perf_env__arch(struct perf_env *env __maybe_unused) * far, for the perf python binding known usecases, revisit if this become * necessary. */ -struct perf_pmu *evsel__find_pmu(struct evsel *evsel __maybe_unused) +struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused) { return NULL; } -- GitLab From b594e6f6605311785171b8d4600fe96e35625530 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:31 +0100 Subject: [PATCH 0399/5631] clk: qcom: branch: Add helper functions for setting retain bits Most Qualcomm branch clocks come with a pretty usual set of bits that can enable memory retention by means of not turning off parts of the memory logic. Add them to the common header file and introduce helper functions for setting them instead of using magic writes. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-2-konrad.dybcio@linaro.org --- drivers/clk/qcom/clk-branch.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h index 17a58119165e..55b3a2c3afed 100644 --- a/drivers/clk/qcom/clk-branch.h +++ b/drivers/clk/qcom/clk-branch.h @@ -37,6 +37,32 @@ struct clk_branch { struct clk_regmap clkr; }; +/* Branch clock common bits for HLOS-owned clocks */ +#define CBCR_FORCE_MEM_CORE_ON BIT(14) +#define CBCR_FORCE_MEM_PERIPH_ON BIT(13) +#define CBCR_FORCE_MEM_PERIPH_OFF BIT(12) + +static inline void qcom_branch_set_force_mem_core(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_CORE_ON, + on ? CBCR_FORCE_MEM_CORE_ON : 0); +} + +static inline void qcom_branch_set_force_periph_on(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_PERIPH_ON, + on ? CBCR_FORCE_MEM_PERIPH_ON : 0); +} + +static inline void qcom_branch_set_force_periph_off(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_PERIPH_OFF, + on ? CBCR_FORCE_MEM_PERIPH_OFF : 0); +} + extern const struct clk_ops clk_branch_ops; extern const struct clk_ops clk_branch2_ops; extern const struct clk_ops clk_branch_simple_ops; -- GitLab From 0932e565ba7c828d5ec59f872cb3ad6b070dc003 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:32 +0100 Subject: [PATCH 0400/5631] clk: qcom: branch: Add helper functions for setting SLEEP/WAKE bits HLOS-controlled branch clocks on non-ancient Qualcomm platforms feature SLEEP and WAKE fields which can be written to to configure how long the clock hardware should wait internally before being (un)gated. Some very sensitive clocks need to have these values programmed to prevent putting the hardware in a not-exactly-good state. Add definitions of these fields and introduce helpers for setting them inside clock drivers. Reviewed-by: Dmitry Baryshkov Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-3-konrad.dybcio@linaro.org --- drivers/clk/qcom/clk-branch.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h index 55b3a2c3afed..b325f943c3e0 100644 --- a/drivers/clk/qcom/clk-branch.h +++ b/drivers/clk/qcom/clk-branch.h @@ -4,6 +4,7 @@ #ifndef __QCOM_CLK_BRANCH_H__ #define __QCOM_CLK_BRANCH_H__ +#include #include #include "clk-regmap.h" @@ -41,6 +42,8 @@ struct clk_branch { #define CBCR_FORCE_MEM_CORE_ON BIT(14) #define CBCR_FORCE_MEM_PERIPH_ON BIT(13) #define CBCR_FORCE_MEM_PERIPH_OFF BIT(12) +#define CBCR_WAKEUP GENMASK(11, 8) +#define CBCR_SLEEP GENMASK(7, 4) static inline void qcom_branch_set_force_mem_core(struct regmap *regmap, struct clk_branch clk, bool on) @@ -63,6 +66,18 @@ static inline void qcom_branch_set_force_periph_off(struct regmap *regmap, on ? CBCR_FORCE_MEM_PERIPH_OFF : 0); } +static inline void qcom_branch_set_wakeup(struct regmap *regmap, struct clk_branch clk, u32 val) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_WAKEUP, + FIELD_PREP(CBCR_WAKEUP, val)); +} + +static inline void qcom_branch_set_sleep(struct regmap *regmap, struct clk_branch clk, u32 val) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_SLEEP, + FIELD_PREP(CBCR_SLEEP, val)); +} + extern const struct clk_ops clk_branch_ops; extern const struct clk_ops clk_branch2_ops; extern const struct clk_ops clk_branch_simple_ops; -- GitLab From 5ab6561da990375b0a3cd54e12996498f6398a0f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:33 +0100 Subject: [PATCH 0401/5631] clk: qcom: branch: Move CBCR bits definitions to the header file Move the definitions of CBCR bits to the branch header file. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-4-konrad.dybcio@linaro.org --- drivers/clk/qcom/clk-branch.c | 5 ----- drivers/clk/qcom/clk-branch.h | 4 ++++ 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c index f869fc6aaed6..f2b577b07b7e 100644 --- a/drivers/clk/qcom/clk-branch.c +++ b/drivers/clk/qcom/clk-branch.c @@ -39,11 +39,6 @@ static bool clk_branch_check_halt(const struct clk_branch *br, bool enabling) return !!val == !enabling; } -#define BRANCH_CLK_OFF BIT(31) -#define BRANCH_NOC_FSM_STATUS_SHIFT 28 -#define BRANCH_NOC_FSM_STATUS_MASK 0x7 -#define BRANCH_NOC_FSM_STATUS_ON (0x2 << BRANCH_NOC_FSM_STATUS_SHIFT) - static bool clk_branch2_check_halt(const struct clk_branch *br, bool enabling) { u32 val; diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h index b325f943c3e0..9bec563ab4ee 100644 --- a/drivers/clk/qcom/clk-branch.h +++ b/drivers/clk/qcom/clk-branch.h @@ -39,6 +39,10 @@ struct clk_branch { }; /* Branch clock common bits for HLOS-owned clocks */ +#define BRANCH_CLK_OFF BIT(31) +#define BRANCH_NOC_FSM_STATUS_SHIFT 28 +#define BRANCH_NOC_FSM_STATUS_MASK 0x7 +#define BRANCH_NOC_FSM_STATUS_ON (0x2 << BRANCH_NOC_FSM_STATUS_SHIFT) #define CBCR_FORCE_MEM_CORE_ON BIT(14) #define CBCR_FORCE_MEM_PERIPH_ON BIT(13) #define CBCR_FORCE_MEM_PERIPH_OFF BIT(12) -- GitLab From b96fbb03fbc1686449e28e2edb54df5c3584ad43 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:34 +0100 Subject: [PATCH 0402/5631] clk: qcom: branch: Clean up branch enable registers Prefix the "branch enable" registers with CBCR_ to be closer to what they are actually called in Qualcomm terms, use GENMASK instead of shifting values around and adjust their usage accordingly. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-5-konrad.dybcio@linaro.org --- drivers/clk/qcom/clk-branch.c | 10 +++++----- drivers/clk/qcom/clk-branch.h | 7 +++---- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c index f2b577b07b7e..ca896ebf7e1b 100644 --- a/drivers/clk/qcom/clk-branch.c +++ b/drivers/clk/qcom/clk-branch.c @@ -44,17 +44,17 @@ static bool clk_branch2_check_halt(const struct clk_branch *br, bool enabling) u32 val; u32 mask; - mask = BRANCH_NOC_FSM_STATUS_MASK << BRANCH_NOC_FSM_STATUS_SHIFT; - mask |= BRANCH_CLK_OFF; + mask = CBCR_NOC_FSM_STATUS; + mask |= CBCR_CLK_OFF; regmap_read(br->clkr.regmap, br->halt_reg, &val); if (enabling) { val &= mask; - return (val & BRANCH_CLK_OFF) == 0 || - val == BRANCH_NOC_FSM_STATUS_ON; + return (val & CBCR_CLK_OFF) == 0 || + FIELD_GET(CBCR_NOC_FSM_STATUS, val) == FSM_STATUS_ON; } else { - return val & BRANCH_CLK_OFF; + return val & CBCR_CLK_OFF; } } diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h index 9bec563ab4ee..0cf800b9d08d 100644 --- a/drivers/clk/qcom/clk-branch.h +++ b/drivers/clk/qcom/clk-branch.h @@ -39,10 +39,9 @@ struct clk_branch { }; /* Branch clock common bits for HLOS-owned clocks */ -#define BRANCH_CLK_OFF BIT(31) -#define BRANCH_NOC_FSM_STATUS_SHIFT 28 -#define BRANCH_NOC_FSM_STATUS_MASK 0x7 -#define BRANCH_NOC_FSM_STATUS_ON (0x2 << BRANCH_NOC_FSM_STATUS_SHIFT) +#define CBCR_CLK_OFF BIT(31) +#define CBCR_NOC_FSM_STATUS GENMASK(30, 28) + #define FSM_STATUS_ON BIT(1) #define CBCR_FORCE_MEM_CORE_ON BIT(14) #define CBCR_FORCE_MEM_PERIPH_ON BIT(13) #define CBCR_FORCE_MEM_PERIPH_OFF BIT(12) -- GitLab From a6b18286810cc64419a36e3a6b5d7191f1f9b167 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:36 +0100 Subject: [PATCH 0403/5631] clk: qcom: Add GPU clock controller driver for SM6125 Add support for the GPU clock controller found on SM6125. Reviewed-by: Dmitry Baryshkov Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-7-konrad.dybcio@linaro.org --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gpucc-sm6125.c | 424 ++++++++++++++++++++++++++++++++ 3 files changed, 434 insertions(+) create mode 100644 drivers/clk/qcom/gpucc-sm6125.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 5ab4b7dfe3c2..e2875a1d0de7 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -798,6 +798,15 @@ config SM_GCC_8550 Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, SD/UFS, PCIe etc. +config SM_GPUCC_6125 + tristate "SM6125 Graphics Clock Controller" + select SM_GCC_6125 + depends on ARM64 || COMPILE_TEST + help + Support for the graphics clock controller on SM6125 devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics. + config SM_GPUCC_6350 tristate "SM6350 Graphics Clock Controller" select SM_GCC_6350 diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index c743805a9cbb..110df852fe0b 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -112,6 +112,7 @@ obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o obj-$(CONFIG_SM_GCC_8350) += gcc-sm8350.o obj-$(CONFIG_SM_GCC_8450) += gcc-sm8450.o obj-$(CONFIG_SM_GCC_8550) += gcc-sm8550.o +obj-$(CONFIG_SM_GPUCC_6125) += gpucc-sm6125.o obj-$(CONFIG_SM_GPUCC_6350) += gpucc-sm6350.o obj-$(CONFIG_SM_GPUCC_8150) += gpucc-sm8150.o obj-$(CONFIG_SM_GPUCC_8250) += gpucc-sm8250.o diff --git a/drivers/clk/qcom/gpucc-sm6125.c b/drivers/clk/qcom/gpucc-sm6125.c new file mode 100644 index 000000000000..d4f1296a48ef --- /dev/null +++ b/drivers/clk/qcom/gpucc-sm6125.c @@ -0,0 +1,424 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Linaro Limited + */ + +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_GCC_GPU_GPLL0_CLK_SRC, +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_MAIN, + P_GPU_CC_PLL0_2X_CLK, + P_GPU_CC_PLL0_OUT_AUX2, + P_GPU_CC_PLL1_OUT_AUX, + P_GPU_CC_PLL1_OUT_AUX2, +}; + +static struct pll_vco gpu_cc_pll_vco[] = { + { 1000000000, 2000000000, 0 }, + { 500000000, 1000000000, 2 }, +}; + +/* 1020MHz configuration */ +static const struct alpha_pll_config gpu_pll0_config = { + .l = 0x35, + .config_ctl_val = 0x4001055b, + .alpha_hi = 0x20, + .alpha = 0x00, + .alpha_en_mask = BIT(24), + .vco_val = 0x0 << 20, + .vco_mask = 0x3 << 20, + .aux2_output_mask = BIT(2), +}; + +/* 930MHz configuration */ +static const struct alpha_pll_config gpu_pll1_config = { + .l = 0x30, + .config_ctl_val = 0x4001055b, + .alpha_hi = 0x70, + .alpha = 0x00, + .alpha_en_mask = BIT(24), + .vco_val = 0x2 << 20, + .vco_mask = 0x3 << 20, + .aux2_output_mask = BIT(2), +}; + +static struct clk_alpha_pll gpu_cc_pll0_out_aux2 = { + .offset = 0x0, + .vco_table = gpu_cc_pll_vco, + .num_vco = ARRAY_SIZE(gpu_cc_pll_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .flags = SUPPORTS_DYNAMIC_UPDATE, + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll0_out_aux2", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll gpu_cc_pll1_out_aux2 = { + .offset = 0x100, + .vco_table = gpu_cc_pll_vco, + .num_vco = ARRAY_SIZE(gpu_cc_pll_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .flags = SUPPORTS_DYNAMIC_UPDATE, + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll1_out_aux2", + .parent_data = &(const struct clk_parent_data) { + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct parent_map gpu_cc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 5 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, +}; + +static const struct parent_map gpu_cc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_AUX2, 2 }, + { P_GPU_CC_PLL1_OUT_AUX2, 4 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpu_cc_pll0_out_aux2.clkr.hw }, + { .hw = &gpu_cc_pll1_out_aux2.clkr.hw }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gmu_clk_src = { + .cmd_rcgr = 0x1120, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_0, + .freq_tbl = ftbl_gpu_cc_gmu_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gmu_clk_src", + .parent_data = gpu_cc_parent_data_0, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gx_gfx3d_clk_src[] = { + F(320000000, P_GPU_CC_PLL1_OUT_AUX2, 2, 0, 0), + F(465000000, P_GPU_CC_PLL1_OUT_AUX2, 2, 0, 0), + F(600000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(745000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(820000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(900000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(950000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gx_gfx3d_clk_src = { + .cmd_rcgr = 0x101c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_1, + .freq_tbl = ftbl_gpu_cc_gx_gfx3d_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gx_gfx3d_clk_src", + .parent_data = gpu_cc_parent_data_1, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gpu_cc_crc_ahb_clk = { + .halt_reg = 0x107c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x107c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_crc_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_apb_clk = { + .halt_reg = 0x1088, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1088, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_apb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_gfx3d_clk = { + .halt_reg = 0x1054, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x1054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gx_gfx3d_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gfx3d_clk = { + .halt_reg = 0x10a4, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x10a4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_gfx3d_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_gx_gfx3d_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gmu_clk = { + .halt_reg = 0x1098, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1098, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_gmu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_snoc_dvm_clk = { + .halt_reg = 0x108c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x108c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_snoc_dvm_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_aon_clk = { + .halt_reg = 0x1004, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cxo_aon_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_clk = { + .halt_reg = 0x109c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x109c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cxo_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_sleep_clk = { + .halt_reg = 0x1090, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_ahb_clk = { + .halt_reg = 0x1078, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1078, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_ahb_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = { + .halt_reg = 0x5000, + .halt_check = BRANCH_VOTED, + .clkr = { + .enable_reg = 0x5000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_hlos1_vote_gpu_smmu_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gpu_cx_gdsc = { + .gdscr = 0x106c, + .gds_hw_ctrl = 0x1540, + .pd = { + .name = "gpu_cx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc gpu_gx_gdsc = { + .gdscr = 0x100c, + .pd = { + .name = "gpu_gx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct clk_regmap *gpu_cc_sm6125_clocks[] = { + [GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr, + [GPU_CC_CX_APB_CLK] = &gpu_cc_cx_apb_clk.clkr, + [GPU_CC_CX_GFX3D_CLK] = &gpu_cc_cx_gfx3d_clk.clkr, + [GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr, + [GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr, + [GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr, + [GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr, + [GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr, + [GPU_CC_PLL0_OUT_AUX2] = &gpu_cc_pll0_out_aux2.clkr, + [GPU_CC_PLL1_OUT_AUX2] = &gpu_cc_pll1_out_aux2.clkr, + [GPU_CC_SLEEP_CLK] = &gpu_cc_sleep_clk.clkr, + [GPU_CC_GX_GFX3D_CLK] = &gpu_cc_gx_gfx3d_clk.clkr, + [GPU_CC_GX_GFX3D_CLK_SRC] = &gpu_cc_gx_gfx3d_clk_src.clkr, + [GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr, + [GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK] = &gpu_cc_hlos1_vote_gpu_smmu_clk.clkr, +}; + +static struct gdsc *gpucc_sm6125_gdscs[] = { + [GPU_CX_GDSC] = &gpu_cx_gdsc, + [GPU_GX_GDSC] = &gpu_gx_gdsc, +}; + +static const struct regmap_config gpu_cc_sm6125_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9000, + .fast_io = true, +}; + +static const struct qcom_cc_desc gpu_cc_sm6125_desc = { + .config = &gpu_cc_sm6125_regmap_config, + .clks = gpu_cc_sm6125_clocks, + .num_clks = ARRAY_SIZE(gpu_cc_sm6125_clocks), + .gdscs = gpucc_sm6125_gdscs, + .num_gdscs = ARRAY_SIZE(gpucc_sm6125_gdscs), +}; + +static const struct of_device_id gpu_cc_sm6125_match_table[] = { + { .compatible = "qcom,sm6125-gpucc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpu_cc_sm6125_match_table); + +static int gpu_cc_sm6125_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + + regmap = qcom_cc_map(pdev, &gpu_cc_sm6125_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + clk_alpha_pll_configure(&gpu_cc_pll0_out_aux2, regmap, &gpu_pll0_config); + clk_alpha_pll_configure(&gpu_cc_pll1_out_aux2, regmap, &gpu_pll1_config); + + /* Set recommended WAKEUP/SLEEP settings for the gpu_cc_cx_gmu_clk */ + qcom_branch_set_wakeup(regmap, gpu_cc_cx_gmu_clk, 0xf); + qcom_branch_set_sleep(regmap, gpu_cc_cx_gmu_clk, 0xf); + + qcom_branch_set_force_mem_core(regmap, gpu_cc_gx_gfx3d_clk, true); + qcom_branch_set_force_periph_on(regmap, gpu_cc_gx_gfx3d_clk, true); + + return qcom_cc_really_probe(pdev, &gpu_cc_sm6125_desc, regmap); +} + +static struct platform_driver gpu_cc_sm6125_driver = { + .probe = gpu_cc_sm6125_probe, + .driver = { + .name = "gpucc-sm6125", + .of_match_table = gpu_cc_sm6125_match_table, + }, +}; +module_platform_driver(gpu_cc_sm6125_driver); + +MODULE_DESCRIPTION("QTI GPUCC SM6125 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 8397e24278b3690b830e5dad79169a79f63b0b43 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:38 +0100 Subject: [PATCH 0404/5631] clk: qcom: Add GPU clock controller driver for SM6375 Add support for the GPU clock controller found on SM6375. Reviewed-by: Dmitry Baryshkov Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-9-konrad.dybcio@linaro.org --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gpucc-sm6375.c | 469 ++++++++++++++++++++++++++++++++ 3 files changed, 479 insertions(+) create mode 100644 drivers/clk/qcom/gpucc-sm6375.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index e2875a1d0de7..34b436c96b77 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -807,6 +807,15 @@ config SM_GPUCC_6125 Say Y if you want to support graphics controller devices and functionality such as 3D graphics. +config SM_GPUCC_6375 + tristate "SM6375 Graphics Clock Controller" + select SM_GCC_6375 + depends on ARM64 || COMPILE_TEST + help + Support for the graphics clock controller on SM6375 devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics. + config SM_GPUCC_6350 tristate "SM6350 Graphics Clock Controller" select SM_GCC_6350 diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 110df852fe0b..00687531c7f1 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -114,6 +114,7 @@ obj-$(CONFIG_SM_GCC_8450) += gcc-sm8450.o obj-$(CONFIG_SM_GCC_8550) += gcc-sm8550.o obj-$(CONFIG_SM_GPUCC_6125) += gpucc-sm6125.o obj-$(CONFIG_SM_GPUCC_6350) += gpucc-sm6350.o +obj-$(CONFIG_SM_GPUCC_6375) += gpucc-sm6375.o obj-$(CONFIG_SM_GPUCC_8150) += gpucc-sm8150.o obj-$(CONFIG_SM_GPUCC_8250) += gpucc-sm8250.o obj-$(CONFIG_SM_GPUCC_8350) += gpucc-sm8350.o diff --git a/drivers/clk/qcom/gpucc-sm6375.c b/drivers/clk/qcom/gpucc-sm6375.c new file mode 100644 index 000000000000..eb9ffa956950 --- /dev/null +++ b/drivers/clk/qcom/gpucc-sm6375.c @@ -0,0 +1,469 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Linaro Limited + */ + +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_GCC_GPU_GPLL0_CLK_SRC, + DT_GCC_GPU_GPLL0_DIV_CLK_SRC, + DT_GCC_GPU_SNOC_DVM_GFX_CLK, +}; + +enum { + P_BI_TCXO, + P_GCC_GPU_GPLL0_CLK_SRC, + P_GCC_GPU_GPLL0_DIV_CLK_SRC, + P_GPU_CC_PLL0_OUT_EVEN, + P_GPU_CC_PLL0_OUT_MAIN, + P_GPU_CC_PLL0_OUT_ODD, + P_GPU_CC_PLL1_OUT_EVEN, + P_GPU_CC_PLL1_OUT_MAIN, + P_GPU_CC_PLL1_OUT_ODD, +}; + +static struct pll_vco lucid_vco[] = { + { 249600000, 2000000000, 0 }, +}; + +/* 532MHz Configuration */ +static const struct alpha_pll_config gpucc_pll0_config = { + .l = 0x1b, + .alpha = 0xb555, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00002261, + .config_ctl_hi1_val = 0x329a299c, + .user_ctl_val = 0x00000001, + .user_ctl_hi_val = 0x00000805, + .user_ctl_hi1_val = 0x00000000, +}; + +static struct clk_alpha_pll gpucc_pll0 = { + .offset = 0x0, + .vco_table = lucid_vco, + .num_vco = ARRAY_SIZE(lucid_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID], + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpucc_pll0", + .parent_data = &(const struct clk_parent_data){ + .index = P_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_ops, + }, + }, +}; + +/* 514MHz Configuration */ +static const struct alpha_pll_config gpucc_pll1_config = { + .l = 0x1a, + .alpha = 0xc555, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00002261, + .config_ctl_hi1_val = 0x329a299c, + .user_ctl_val = 0x00000001, + .user_ctl_hi_val = 0x00000805, + .user_ctl_hi1_val = 0x00000000, +}; + +static struct clk_alpha_pll gpucc_pll1 = { + .offset = 0x100, + .vco_table = lucid_vco, + .num_vco = ARRAY_SIZE(lucid_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID], + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpucc_pll1", + .parent_data = &(const struct clk_parent_data){ + .index = P_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_ops, + }, + }, +}; + +static const struct parent_map gpucc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_MAIN, 1 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GCC_GPU_GPLL0_CLK_SRC, 5 }, + { P_GCC_GPU_GPLL0_DIV_CLK_SRC, 6 }, +}; + +static const struct clk_parent_data gpucc_parent_data_0[] = { + { .index = P_BI_TCXO }, + { .hw = &gpucc_pll0.clkr.hw }, + { .hw = &gpucc_pll1.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct parent_map gpucc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_EVEN, 1 }, + { P_GPU_CC_PLL0_OUT_ODD, 2 }, + { P_GPU_CC_PLL1_OUT_EVEN, 3 }, + { P_GPU_CC_PLL1_OUT_ODD, 4 }, + { P_GCC_GPU_GPLL0_CLK_SRC, 5 }, +}; + +static const struct clk_parent_data gpucc_parent_data_1[] = { + { .index = P_BI_TCXO }, + { .hw = &gpucc_pll0.clkr.hw }, + { .hw = &gpucc_pll0.clkr.hw }, + { .hw = &gpucc_pll1.clkr.hw }, + { .hw = &gpucc_pll1.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, +}; + +static const struct parent_map gpucc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GCC_GPU_GPLL0_CLK_SRC, 5 }, + { P_GCC_GPU_GPLL0_DIV_CLK_SRC, 6 }, +}; + +static const struct clk_parent_data gpucc_parent_data_2[] = { + { .index = P_BI_TCXO }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct freq_tbl ftbl_gpucc_gmu_clk_src[] = { + F(200000000, P_GCC_GPU_GPLL0_DIV_CLK_SRC, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 gpucc_gmu_clk_src = { + .cmd_rcgr = 0x1120, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpucc_parent_map_0, + .freq_tbl = ftbl_gpucc_gmu_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpucc_gmu_clk_src", + .parent_data = gpucc_parent_data_0, + .num_parents = ARRAY_SIZE(gpucc_parent_data_0), + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gpucc_gx_gfx3d_clk_src[] = { + F(266000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(390000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(490000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(650000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(770000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(840000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + F(900000000, P_GPU_CC_PLL0_OUT_EVEN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gpucc_gx_gfx3d_clk_src = { + .cmd_rcgr = 0x101c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpucc_parent_map_1, + .freq_tbl = ftbl_gpucc_gx_gfx3d_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpucc_gx_gfx3d_clk_src", + .parent_data = gpucc_parent_data_1, + .num_parents = ARRAY_SIZE(gpucc_parent_data_1), + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gpucc_ahb_clk = { + .halt_reg = 0x1078, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1078, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_ahb_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cx_gfx3d_clk = { + .halt_reg = 0x10a4, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x10a4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cx_gfx3d_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpucc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cx_gfx3d_slv_clk = { + .halt_reg = 0x10a8, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x10a8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cx_gfx3d_slv_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpucc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cx_gmu_clk = { + .halt_reg = 0x1098, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1098, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cx_gmu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpucc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cx_snoc_dvm_clk = { + .halt_reg = 0x108c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x108c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cx_snoc_dvm_clk", + .parent_data = &(const struct clk_parent_data){ + .index = DT_GCC_GPU_SNOC_DVM_GFX_CLK, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cxo_aon_clk = { + .halt_reg = 0x1004, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cxo_aon_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_cxo_clk = { + .halt_reg = 0x109c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x109c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_cxo_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_gx_cxo_clk = { + .halt_reg = 0x1060, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1060, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_gx_cxo_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_gx_gfx3d_clk = { + .halt_reg = 0x1054, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_gx_gfx3d_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpucc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_gx_gmu_clk = { + .halt_reg = 0x1064, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1064, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_gx_gmu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gpucc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpucc_sleep_clk = { + .halt_reg = 0x1090, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x1090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpucc_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gpu_cx_gdsc = { + .gdscr = 0x106c, + .gds_hw_ctrl = 0x1540, + .pd = { + .name = "gpu_cx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc gpu_gx_gdsc = { + .gdscr = 0x100c, + .clamp_io_ctrl = 0x1508, + .resets = (unsigned int []){ GPU_GX_BCR, GPU_ACD_BCR, GPU_GX_ACD_MISC_BCR }, + .reset_count = 3, + .pd = { + .name = "gpu_gx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = CLAMP_IO | SW_RESET | AON_RESET, +}; + +static struct clk_regmap *gpucc_sm6375_clocks[] = { + [GPU_CC_AHB_CLK] = &gpucc_ahb_clk.clkr, + [GPU_CC_CX_GFX3D_CLK] = &gpucc_cx_gfx3d_clk.clkr, + [GPU_CC_CX_GFX3D_SLV_CLK] = &gpucc_cx_gfx3d_slv_clk.clkr, + [GPU_CC_CX_GMU_CLK] = &gpucc_cx_gmu_clk.clkr, + [GPU_CC_CX_SNOC_DVM_CLK] = &gpucc_cx_snoc_dvm_clk.clkr, + [GPU_CC_CXO_AON_CLK] = &gpucc_cxo_aon_clk.clkr, + [GPU_CC_CXO_CLK] = &gpucc_cxo_clk.clkr, + [GPU_CC_GMU_CLK_SRC] = &gpucc_gmu_clk_src.clkr, + [GPU_CC_GX_CXO_CLK] = &gpucc_gx_cxo_clk.clkr, + [GPU_CC_GX_GFX3D_CLK] = &gpucc_gx_gfx3d_clk.clkr, + [GPU_CC_GX_GFX3D_CLK_SRC] = &gpucc_gx_gfx3d_clk_src.clkr, + [GPU_CC_GX_GMU_CLK] = &gpucc_gx_gmu_clk.clkr, + [GPU_CC_PLL0] = &gpucc_pll0.clkr, + [GPU_CC_PLL1] = &gpucc_pll1.clkr, + [GPU_CC_SLEEP_CLK] = &gpucc_sleep_clk.clkr, +}; + +static const struct qcom_reset_map gpucc_sm6375_resets[] = { + [GPU_GX_BCR] = { 0x1008 }, + [GPU_ACD_BCR] = { 0x1160 }, + [GPU_GX_ACD_MISC_BCR] = { 0x8004 }, +}; + +static struct gdsc *gpucc_sm6375_gdscs[] = { + [GPU_CX_GDSC] = &gpu_cx_gdsc, + [GPU_GX_GDSC] = &gpu_gx_gdsc, +}; + +static const struct regmap_config gpucc_sm6375_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9000, + .fast_io = true, +}; + +static const struct qcom_cc_desc gpucc_sm6375_desc = { + .config = &gpucc_sm6375_regmap_config, + .clks = gpucc_sm6375_clocks, + .num_clks = ARRAY_SIZE(gpucc_sm6375_clocks), + .resets = gpucc_sm6375_resets, + .num_resets = ARRAY_SIZE(gpucc_sm6375_resets), + .gdscs = gpucc_sm6375_gdscs, + .num_gdscs = ARRAY_SIZE(gpucc_sm6375_gdscs), +}; + +static const struct of_device_id gpucc_sm6375_match_table[] = { + { .compatible = "qcom,sm6375-gpucc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpucc_sm6375_match_table); + +static int gpucc_sm6375_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + + regmap = qcom_cc_map(pdev, &gpucc_sm6375_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + clk_lucid_pll_configure(&gpucc_pll0, regmap, &gpucc_pll0_config); + clk_lucid_pll_configure(&gpucc_pll1, regmap, &gpucc_pll1_config); + + return qcom_cc_really_probe(pdev, &gpucc_sm6375_desc, regmap); +} + +static struct platform_driver gpucc_sm6375_driver = { + .probe = gpucc_sm6375_probe, + .driver = { + .name = "gpucc-sm6375", + .of_match_table = gpucc_sm6375_match_table, + }, +}; +module_platform_driver(gpucc_sm6375_driver); + +MODULE_DESCRIPTION("QTI GPUCC SM6375 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 092209f199b8fe3e7862aff2d6e45ffb388fc42a Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Feb 2023 10:13:40 +0100 Subject: [PATCH 0405/5631] clk: qcom: Add GPU clock controller driver for SM6115 Add support for the GPU clock controller found on SM6115. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230208091340.124641-11-konrad.dybcio@linaro.org --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gpucc-sm6115.c | 503 ++++++++++++++++++++++++++++++++ 3 files changed, 513 insertions(+) create mode 100644 drivers/clk/qcom/gpucc-sm6115.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 34b436c96b77..90ba20a9fa7a 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -798,6 +798,15 @@ config SM_GCC_8550 Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, SD/UFS, PCIe etc. +config SM_GPUCC_6115 + tristate "SM6115 Graphics Clock Controller" + select SM_GCC_6115 + depends on ARM64 || COMPILE_TEST + help + Support for the graphics clock controller on SM6115 devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics. + config SM_GPUCC_6125 tristate "SM6125 Graphics Clock Controller" select SM_GCC_6125 diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 00687531c7f1..441406ae404b 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -112,6 +112,7 @@ obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o obj-$(CONFIG_SM_GCC_8350) += gcc-sm8350.o obj-$(CONFIG_SM_GCC_8450) += gcc-sm8450.o obj-$(CONFIG_SM_GCC_8550) += gcc-sm8550.o +obj-$(CONFIG_SM_GPUCC_6115) += gpucc-sm6115.o obj-$(CONFIG_SM_GPUCC_6125) += gpucc-sm6125.o obj-$(CONFIG_SM_GPUCC_6350) += gpucc-sm6350.o obj-$(CONFIG_SM_GPUCC_6375) += gpucc-sm6375.o diff --git a/drivers/clk/qcom/gpucc-sm6115.c b/drivers/clk/qcom/gpucc-sm6115.c new file mode 100644 index 000000000000..c84727e8352d --- /dev/null +++ b/drivers/clk/qcom/gpucc-sm6115.c @@ -0,0 +1,503 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Linaro Limited + */ + +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_GCC_GPU_GPLL0_CLK_SRC, + DT_GCC_GPU_GPLL0_DIV_CLK_SRC, +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_MAIN, + P_GPLL0_OUT_MAIN_DIV, + P_GPU_CC_PLL0_OUT_AUX2, + P_GPU_CC_PLL0_OUT_MAIN, + P_GPU_CC_PLL1_OUT_AUX, + P_GPU_CC_PLL1_OUT_MAIN, +}; + +static struct pll_vco default_vco[] = { + { 1000000000, 2000000000, 0 }, +}; + +static struct pll_vco pll1_vco[] = { + { 500000000, 1000000000, 2 }, +}; + +static const struct alpha_pll_config gpu_cc_pll0_config = { + .l = 0x3e, + .alpha = 0, + .alpha_hi = 0x80, + .vco_val = 0x0 << 20, + .vco_mask = GENMASK(21, 20), + .alpha_en_mask = BIT(24), + .main_output_mask = BIT(0), + .aux_output_mask = BIT(1), + .aux2_output_mask = BIT(2), + .config_ctl_val = 0x4001055b, + .test_ctl_hi1_val = 0x1, +}; + +/* 1200MHz configuration */ +static struct clk_alpha_pll gpu_cc_pll0 = { + .offset = 0x0, + .vco_table = default_vco, + .num_vco = ARRAY_SIZE(default_vco), + .flags = SUPPORTS_DYNAMIC_UPDATE, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll0", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_gpu_cc_pll0_out_aux2[] = { + { 0x0, 1 }, + { } +}; + +static struct clk_alpha_pll_postdiv gpu_cc_pll0_out_aux2 = { + .offset = 0x0, + .post_div_shift = 8, + .post_div_table = post_div_table_gpu_cc_pll0_out_aux2, + .num_post_div = ARRAY_SIZE(post_div_table_gpu_cc_pll0_out_aux2), + .width = 4, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll0_out_aux2", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_pll0.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_alpha_pll_postdiv_ops, + }, +}; + +/* 640MHz configuration */ +static const struct alpha_pll_config gpu_cc_pll1_config = { + .l = 0x21, + .alpha = 0x55555555, + .alpha_hi = 0x55, + .alpha_en_mask = BIT(24), + .vco_val = 0x2 << 20, + .vco_mask = GENMASK(21, 20), + .main_output_mask = BIT(0), + .aux_output_mask = BIT(1), + .config_ctl_val = 0x4001055b, + .test_ctl_hi1_val = 0x1, +}; + +static struct clk_alpha_pll gpu_cc_pll1 = { + .offset = 0x100, + .vco_table = pll1_vco, + .num_vco = ARRAY_SIZE(pll1_vco), + .flags = SUPPORTS_DYNAMIC_UPDATE, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll1", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_gpu_cc_pll1_out_aux[] = { + { 0x0, 1 }, + { } +}; + +static struct clk_alpha_pll_postdiv gpu_cc_pll1_out_aux = { + .offset = 0x100, + .post_div_shift = 15, + .post_div_table = post_div_table_gpu_cc_pll1_out_aux, + .num_post_div = ARRAY_SIZE(post_div_table_gpu_cc_pll1_out_aux), + .width = 3, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_pll1_out_aux", + .parent_hws = (const struct clk_hw*[]) { + &gpu_cc_pll1.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_alpha_pll_postdiv_ops, + }, +}; + +static const struct parent_map gpu_cc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_MAIN, 1 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_0[] = { + { .index = P_BI_TCXO }, + { .hw = &gpu_cc_pll0.clkr.hw }, + { .hw = &gpu_cc_pll1.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct parent_map gpu_cc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_AUX2, 2 }, + { P_GPU_CC_PLL1_OUT_AUX, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_1[] = { + { .index = P_BI_TCXO }, + { .hw = &gpu_cc_pll0_out_aux2.clkr.hw }, + { .hw = &gpu_cc_pll1_out_aux.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gmu_clk_src = { + .cmd_rcgr = 0x1120, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_0, + .freq_tbl = ftbl_gpu_cc_gmu_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gmu_clk_src", + .parent_data = gpu_cc_parent_data_0, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_shared_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gx_gfx3d_clk_src[] = { + F(320000000, P_GPU_CC_PLL1_OUT_AUX, 2, 0, 0), + F(465000000, P_GPU_CC_PLL1_OUT_AUX, 2, 0, 0), + F(600000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(745000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(820000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(900000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(950000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + F(980000000, P_GPU_CC_PLL0_OUT_AUX2, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gx_gfx3d_clk_src = { + .cmd_rcgr = 0x101c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_1, + .freq_tbl = ftbl_gpu_cc_gx_gfx3d_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gx_gfx3d_clk_src", + .parent_data = gpu_cc_parent_data_1, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gpu_cc_ahb_clk = { + .halt_reg = 0x1078, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1078, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_ahb_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_crc_ahb_clk = { + .halt_reg = 0x107c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x107c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_crc_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gfx3d_clk = { + .halt_reg = 0x10a4, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x10a4, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_gfx3d_clk", + .parent_data = &(const struct clk_parent_data){ + .hw = &gpu_cc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gmu_clk = { + .halt_reg = 0x1098, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1098, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_gmu_clk", + .parent_data = &(const struct clk_parent_data){ + .hw = &gpu_cc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_snoc_dvm_clk = { + .halt_reg = 0x108c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x108c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cx_snoc_dvm_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_aon_clk = { + .halt_reg = 0x1004, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cxo_aon_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_clk = { + .halt_reg = 0x109c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x109c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_cxo_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_cxo_clk = { + .halt_reg = 0x1060, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1060, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gx_cxo_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_gx_gfx3d_clk = { + .halt_reg = 0x1054, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x1054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_gx_gfx3d_clk", + .parent_data = &(const struct clk_parent_data){ + .hw = &gpu_cc_gx_gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_sleep_clk = { + .halt_reg = 0x1090, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x1090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = { + .halt_reg = 0x5000, + .halt_check = BRANCH_VOTED, + .clkr = { + .enable_reg = 0x5000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpu_cc_hlos1_vote_gpu_smmu_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc gpu_cx_gdsc = { + .gdscr = 0x106c, + .gds_hw_ctrl = 0x1540, + .pd = { + .name = "gpu_cx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc gpu_gx_gdsc = { + .gdscr = 0x100c, + .clamp_io_ctrl = 0x1508, + .resets = (unsigned int []){ GPU_GX_BCR }, + .reset_count = 1, + .pd = { + .name = "gpu_gx_gdsc", + }, + .parent = &gpu_cx_gdsc.pd, + .pwrsts = PWRSTS_OFF_ON, + .flags = CLAMP_IO | SW_RESET | VOTABLE, +}; + +static struct clk_regmap *gpu_cc_sm6115_clocks[] = { + [GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr, + [GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr, + [GPU_CC_CX_GFX3D_CLK] = &gpu_cc_cx_gfx3d_clk.clkr, + [GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr, + [GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr, + [GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr, + [GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr, + [GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr, + [GPU_CC_GX_CXO_CLK] = &gpu_cc_gx_cxo_clk.clkr, + [GPU_CC_GX_GFX3D_CLK] = &gpu_cc_gx_gfx3d_clk.clkr, + [GPU_CC_GX_GFX3D_CLK_SRC] = &gpu_cc_gx_gfx3d_clk_src.clkr, + [GPU_CC_PLL0] = &gpu_cc_pll0.clkr, + [GPU_CC_PLL0_OUT_AUX2] = &gpu_cc_pll0_out_aux2.clkr, + [GPU_CC_PLL1] = &gpu_cc_pll1.clkr, + [GPU_CC_PLL1_OUT_AUX] = &gpu_cc_pll1_out_aux.clkr, + [GPU_CC_SLEEP_CLK] = &gpu_cc_sleep_clk.clkr, + [GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK] = &gpu_cc_hlos1_vote_gpu_smmu_clk.clkr, +}; + +static const struct qcom_reset_map gpu_cc_sm6115_resets[] = { + [GPU_GX_BCR] = { 0x1008 }, +}; + +static struct gdsc *gpu_cc_sm6115_gdscs[] = { + [GPU_CX_GDSC] = &gpu_cx_gdsc, + [GPU_GX_GDSC] = &gpu_gx_gdsc, +}; + +static const struct regmap_config gpu_cc_sm6115_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9000, + .fast_io = true, +}; + +static const struct qcom_cc_desc gpu_cc_sm6115_desc = { + .config = &gpu_cc_sm6115_regmap_config, + .clks = gpu_cc_sm6115_clocks, + .num_clks = ARRAY_SIZE(gpu_cc_sm6115_clocks), + .resets = gpu_cc_sm6115_resets, + .num_resets = ARRAY_SIZE(gpu_cc_sm6115_resets), + .gdscs = gpu_cc_sm6115_gdscs, + .num_gdscs = ARRAY_SIZE(gpu_cc_sm6115_gdscs), +}; + +static const struct of_device_id gpu_cc_sm6115_match_table[] = { + { .compatible = "qcom,sm6115-gpucc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpu_cc_sm6115_match_table); + +static int gpu_cc_sm6115_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + + regmap = qcom_cc_map(pdev, &gpu_cc_sm6115_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + clk_alpha_pll_configure(&gpu_cc_pll0, regmap, &gpu_cc_pll0_config); + clk_alpha_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll1_config); + + /* Set recommended WAKEUP/SLEEP settings for the gpu_cc_cx_gmu_clk */ + qcom_branch_set_wakeup(regmap, gpu_cc_cx_gmu_clk, 0xf); + qcom_branch_set_sleep(regmap, gpu_cc_cx_gmu_clk, 0xf); + + qcom_branch_set_force_mem_core(regmap, gpu_cc_gx_gfx3d_clk, true); + qcom_branch_set_force_periph_on(regmap, gpu_cc_gx_gfx3d_clk, true); + + return qcom_cc_really_probe(pdev, &gpu_cc_sm6115_desc, regmap); +} + +static struct platform_driver gpu_cc_sm6115_driver = { + .probe = gpu_cc_sm6115_probe, + .driver = { + .name = "sm6115-gpucc", + .of_match_table = gpu_cc_sm6115_match_table, + }, +}; +module_platform_driver(gpu_cc_sm6115_driver); + +MODULE_DESCRIPTION("QTI GPU_CC SM6115 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 7abf0bccaaec77043358ee07e694d31cf9a7dd76 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:38 -0800 Subject: [PATCH 0406/5631] perf evsel: Add function to compute group PMU name The computed name respects software events and aux event groups, such that the pmu_name is changed to be that of the aux event leader or group leader for software events. This is done as a later change will split events that are in different PMUs into different groups. Committer notes: Added a stub for this new function so that 'perf test python' passes. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 24 ++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/python.c | 5 +++++ 3 files changed, 30 insertions(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 798f072b2763..3dda8a25cf50 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -821,6 +821,30 @@ const char *evsel__name(struct evsel *evsel) return "unknown"; } +const char *evsel__group_pmu_name(const struct evsel *evsel) +{ + const struct evsel *leader; + + /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ + if (evsel->pmu_name) + return evsel->pmu_name; + /* + * Software events may be in a group with other uncore PMU events. Use + * the pmu_name of the group leader to avoid breaking the software event + * out of the group. + * + * Aux event leaders, like intel_pt, expect a group with events from + * other PMUs, so substitute the AUX event's PMU in this case. + */ + leader = evsel__leader(evsel); + if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && + leader->pmu_name) { + return leader->pmu_name; + } + + return "cpu"; +} + const char *evsel__metric_id(const struct evsel *evsel) { if (evsel->metric_id) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 676c499323e9..d26745ca6147 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -280,6 +280,7 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size); int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); +const char *evsel__group_pmu_name(const struct evsel *evsel); const char *evsel__metric_id(const struct evsel *evsel); static inline bool evsel__is_tool(const struct evsel *evsel) diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index ab48ffbb6448..be336f1b2b68 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -93,6 +93,11 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return EOF; } +bool evsel__is_aux_event(const struct evsel *evsel __maybe_unused) +{ + return false; +} + /* * Add this one here not to drag util/metricgroup.c */ -- GitLab From 4bb311b29e82c795340a6e4a5db83d8ccbe2dc49 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:39 -0800 Subject: [PATCH 0407/5631] perf parse-events: Pass ownership of the group name Pass ownership of the group name rather than copying and freeing the original. This saves a memory allocation and copy. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 3 ++- tools/perf/util/parse-events.y | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 0336ff27c15f..1be454697d57 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1761,6 +1761,7 @@ parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, handled: ret = 1; + free(name); out: free(leaders); return ret; @@ -1786,7 +1787,7 @@ void parse_events__set_leader(char *name, struct list_head *list, leader = arch_evlist__leader(list); __perf_evlist__set_leader(list, &leader->core); - leader->group_name = name ? strdup(name) : NULL; + leader->group_name = name; list_move(&leader->core.node, list); } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index be8c51770051..541b8dde2063 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -202,8 +202,8 @@ PE_NAME '{' events '}' struct list_head *list = $3; inc_group_count(list, _parse_state); + /* Takes ownership of $1. */ parse_events__set_leader($1, list, _parse_state); - free($1); $$ = list; } | -- GitLab From 347c2f0a0988c59c402148054ef54648853fa669 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:40 -0800 Subject: [PATCH 0408/5631] perf parse-events: Sort and group parsed events This change is intended to be a no-op for most current cases, the default sort order is the order the events were parsed. Where it varies is in how groups are handled. Previously an uncore and core event that are grouped would most often cause the group to be removed: ``` $ perf stat -e '{instructions,uncore_imc_free_running_0/data_total/}' -a sleep 1 WARNING: grouped events cpus do not match, disabling group: anon group { instructions, uncore_imc_free_running_0/data_total/ } ... ``` However, when wildcards are used the events should be re-sorted and re-grouped in parse_events__set_leader, but this currently fails for simple examples: ``` $ perf stat -e '{uncore_imc_free_running/data_read/,uncore_imc_free_running/data_write/}' -a sleep 1 Performance counter stats for 'system wide': MiB uncore_imc_free_running/data_read/ MiB uncore_imc_free_running/data_write/ 1.000996992 seconds time elapsed ``` A futher failure mode, fixed in this patch, is to force topdown events into a group. This change moves sorting the evsels in the evlist after parsing. It requires parsing to set up groups. First the evsels are sorted respecting the existing groupings and parse order, but also reordering to ensure evsels of the same PMU and group appear together. So that software and aux events respect groups, their pmu_name is taken from the group leader. The sorting is done with list_sort removing a memory allocation. After sorting a pass is done to correct the group leaders and for topdown events ensuring they have a group leader. This fixes the problems seen before: ``` $ perf stat -e '{uncore_imc_free_running/data_read/,uncore_imc_free_running/data_write/}' -a sleep 1 Performance counter stats for 'system wide': 727.42 MiB uncore_imc_free_running/data_read/ 81.84 MiB uncore_imc_free_running/data_write/ 1.000948615 seconds time elapsed ``` As well as making groups not fail for cases like: ``` $ perf stat -e '{imc_free_running_0/data_total/,imc_free_running_1/data_total/}' -a sleep 1 Performance counter stats for 'system wide': 256.47 MiB imc_free_running_0/data_total/ 256.48 MiB imc_free_running_1/data_total/ 1.001165442 seconds time elapsed ``` Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/evlist.c | 39 ++--- tools/perf/util/evlist.h | 2 +- tools/perf/util/parse-events.c | 240 +++++++++++++++--------------- tools/perf/util/parse-events.h | 3 +- tools/perf/util/parse-events.y | 4 +- 5 files changed, 136 insertions(+), 152 deletions(-) diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c index 8a7ae4162563..d4193479a364 100644 --- a/tools/perf/arch/x86/util/evlist.c +++ b/tools/perf/arch/x86/util/evlist.c @@ -65,29 +65,22 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, return ___evlist__add_default_attrs(evlist, attrs, nr_attrs); } -struct evsel *arch_evlist__leader(struct list_head *list) +int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) { - struct evsel *evsel, *first, *slots = NULL; - bool has_topdown = false; - - first = list_first_entry(list, struct evsel, core.node); - - if (!topdown_sys_has_perf_metrics()) - return first; - - /* If there is a slots event and a topdown event then the slots event comes first. */ - __evlist__for_each_entry(list, evsel) { - if (evsel->pmu_name && !strncmp(evsel->pmu_name, "cpu", 3) && evsel->name) { - if (strcasestr(evsel->name, "slots")) { - slots = evsel; - if (slots == first) - return first; - } - if (strcasestr(evsel->name, "topdown")) - has_topdown = true; - if (slots && has_topdown) - return slots; - } + if (topdown_sys_has_perf_metrics() && + (!lhs->pmu_name || !strncmp(lhs->pmu_name, "cpu", 3))) { + /* Ensure the topdown slots comes first. */ + if (strcasestr(lhs->name, "slots")) + return -1; + if (strcasestr(rhs->name, "slots")) + return 1; + /* Followed by topdown events. */ + if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown")) + return -1; + if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown")) + return 1; } - return first; + + /* Default ordering by insertion index. */ + return lhs->core.idx - rhs->core.idx; } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 01fa9d592c5a..d89d8f92802b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -119,7 +119,7 @@ int arch_evlist__add_default_attrs(struct evlist *evlist, #define evlist__add_default_attrs(evlist, array) \ arch_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) -struct evsel *arch_evlist__leader(struct list_head *list); +int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs); int evlist__add_dummy(struct evlist *evlist); struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 1be454697d57..394ab23089d0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -1655,125 +1656,7 @@ int parse_events__modifier_group(struct list_head *list, return parse_events__modifier_event(list, event_mod, true); } -/* - * Check if the two uncore PMUs are from the same uncore block - * The format of the uncore PMU name is uncore_#blockname_#pmuidx - */ -static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b) -{ - char *end_a, *end_b; - - end_a = strrchr(pmu_name_a, '_'); - end_b = strrchr(pmu_name_b, '_'); - - if (!end_a || !end_b) - return false; - - if ((end_a - pmu_name_a) != (end_b - pmu_name_b)) - return false; - - return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0); -} - -static int -parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list, - struct parse_events_state *parse_state) -{ - struct evsel *evsel, *leader; - uintptr_t *leaders; - bool is_leader = true; - int i, nr_pmu = 0, total_members, ret = 0; - - leader = list_first_entry(list, struct evsel, core.node); - evsel = list_last_entry(list, struct evsel, core.node); - total_members = evsel->core.idx - leader->core.idx + 1; - - leaders = calloc(total_members, sizeof(uintptr_t)); - if (WARN_ON(!leaders)) - return 0; - - /* - * Going through the whole group and doing sanity check. - * All members must use alias, and be from the same uncore block. - * Also, storing the leader events in an array. - */ - __evlist__for_each_entry(list, evsel) { - - /* Only split the uncore group which members use alias */ - if (!evsel->use_uncore_alias) - goto out; - - /* The events must be from the same uncore block */ - if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name)) - goto out; - - if (!is_leader) - continue; - /* - * If the event's PMU name starts to repeat, it must be a new - * event. That can be used to distinguish the leader from - * other members, even they have the same event name. - */ - if ((leader != evsel) && - !strcmp(leader->pmu_name, evsel->pmu_name)) { - is_leader = false; - continue; - } - - /* Store the leader event for each PMU */ - leaders[nr_pmu++] = (uintptr_t) evsel; - } - - /* only one event alias */ - if (nr_pmu == total_members) { - parse_state->nr_groups--; - goto handled; - } - - /* - * An uncore event alias is a joint name which means the same event - * runs on all PMUs of a block. - * Perf doesn't support mixed events from different PMUs in the same - * group. The big group has to be split into multiple small groups - * which only include the events from the same PMU. - * - * Here the uncore event aliases must be from the same uncore block. - * The number of PMUs must be same for each alias. The number of new - * small groups equals to the number of PMUs. - * Setting the leader event for corresponding members in each group. - */ - i = 0; - __evlist__for_each_entry(list, evsel) { - if (i >= nr_pmu) - i = 0; - evsel__set_leader(evsel, (struct evsel *) leaders[i++]); - } - - /* The number of members and group name are same for each group */ - for (i = 0; i < nr_pmu; i++) { - evsel = (struct evsel *) leaders[i]; - evsel->core.nr_members = total_members / nr_pmu; - evsel->group_name = name ? strdup(name) : NULL; - } - - /* Take the new small groups into account */ - parse_state->nr_groups += nr_pmu - 1; - -handled: - ret = 1; - free(name); -out: - free(leaders); - return ret; -} - -__weak struct evsel *arch_evlist__leader(struct list_head *list) -{ - return list_first_entry(list, struct evsel, core.node); -} - -void parse_events__set_leader(char *name, struct list_head *list, - struct parse_events_state *parse_state) +void parse_events__set_leader(char *name, struct list_head *list) { struct evsel *leader; @@ -1782,13 +1665,9 @@ void parse_events__set_leader(char *name, struct list_head *list, return; } - if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state)) - return; - - leader = arch_evlist__leader(list); + leader = list_first_entry(list, struct evsel, core.node); __perf_evlist__set_leader(list, &leader->core); leader->group_name = name; - list_move(&leader->core.node, list); } /* list_event is assumed to point to malloc'ed memory */ @@ -2245,6 +2124,117 @@ static int parse_events__with_hybrid_pmu(struct parse_events_state *parse_state, return ret; } +__weak int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs) +{ + /* Order by insertion index. */ + return lhs->core.idx - rhs->core.idx; +} + +static int evlist__cmp(void *state, const struct list_head *l, const struct list_head *r) +{ + const struct perf_evsel *lhs_core = container_of(l, struct perf_evsel, node); + const struct evsel *lhs = container_of(lhs_core, struct evsel, core); + const struct perf_evsel *rhs_core = container_of(r, struct perf_evsel, node); + const struct evsel *rhs = container_of(rhs_core, struct evsel, core); + int *leader_idx = state; + int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; + const char *lhs_pmu_name, *rhs_pmu_name; + + /* + * First sort by grouping/leader. Read the leader idx only if the evsel + * is part of a group, as -1 indicates no group. + */ + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + lhs_leader_idx = lhs_core->leader->idx; + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + rhs_leader_idx = rhs_core->leader->idx; + + if (lhs_leader_idx != rhs_leader_idx) + return lhs_leader_idx - rhs_leader_idx; + + /* Group by PMU. Groups can't span PMUs. */ + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + + /* Architecture specific sorting. */ + return arch_evlist__cmp(lhs, rhs); +} + +static void parse_events__sort_events_and_fix_groups(struct list_head *list) +{ + int idx = -1; + struct evsel *pos, *cur_leader = NULL; + struct perf_evsel *cur_leaders_grp = NULL; + + /* + * Compute index to insert ungrouped events at. Place them where the + * first ungrouped event appears. + */ + list_for_each_entry(pos, list, core.node) { + const struct evsel *pos_leader = evsel__leader(pos); + + if (pos != pos_leader || pos->core.nr_members > 1) + continue; + + idx = pos->core.idx; + break; + } + + /* Sort events. */ + list_sort(&idx, list, evlist__cmp); + + /* + * Recompute groups, splitting for PMUs and adding groups for events + * that require them. + */ + idx = 0; + list_for_each_entry(pos, list, core.node) { + const struct evsel *pos_leader = evsel__leader(pos); + const char *pos_pmu_name = evsel__group_pmu_name(pos); + const char *cur_leader_pmu_name, *pos_leader_pmu_name; + bool force_grouped = arch_evsel__must_be_in_group(pos); + + /* Reset index and nr_members. */ + pos->core.idx = idx++; + pos->core.nr_members = 0; + + /* + * Set the group leader respecting the given groupings and that + * groups can't span PMUs. + */ + if (!cur_leader) + cur_leader = pos; + + cur_leader_pmu_name = evsel__group_pmu_name(cur_leader); + if ((cur_leaders_grp != pos->core.leader && !force_grouped) || + strcmp(cur_leader_pmu_name, pos_pmu_name)) { + /* Event is for a different group/PMU than last. */ + cur_leader = pos; + /* + * Remember the leader's group before it is overwritten, + * so that later events match as being in the same + * group. + */ + cur_leaders_grp = pos->core.leader; + } + pos_leader_pmu_name = evsel__group_pmu_name(pos_leader); + if (strcmp(pos_leader_pmu_name, pos_pmu_name) || force_grouped) { + /* + * Event's PMU differs from its leader's. Groups can't + * span PMUs, so update leader from the group/PMU + * tracker. + */ + evsel__set_leader(pos, cur_leader); + } + } + list_for_each_entry(pos, list, core.node) { + pos->core.leader->nr_members++; + } +} + int __parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err, struct perf_pmu *fake_pmu) { @@ -2266,6 +2256,8 @@ int __parse_events(struct evlist *evlist, const char *str, return -1; } + parse_events__sort_events_and_fix_groups(&parse_state.list); + /* * Add list to the evlist even with errors to allow callers to clean up. */ diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 428e72eaafcc..22fc11b0bd59 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -200,8 +200,7 @@ int parse_events_copy_term_list(struct list_head *old, enum perf_pmu_event_symbol_type perf_pmu__parse_check(const char *name); -void parse_events__set_leader(char *name, struct list_head *list, - struct parse_events_state *parse_state); +void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); void parse_events_evlist_error(struct parse_events_state *parse_state, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 541b8dde2063..90d12f2bc8be 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -203,7 +203,7 @@ PE_NAME '{' events '}' inc_group_count(list, _parse_state); /* Takes ownership of $1. */ - parse_events__set_leader($1, list, _parse_state); + parse_events__set_leader($1, list); $$ = list; } | @@ -212,7 +212,7 @@ PE_NAME '{' events '}' struct list_head *list = $2; inc_group_count(list, _parse_state); - parse_events__set_leader(NULL, list, _parse_state); + parse_events__set_leader(NULL, list); $$ = list; } -- GitLab From e733f87e8c77751a00a538627eab1ac05e77cf0d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:41 -0800 Subject: [PATCH 0409/5631] perf evsel: Remove use_uncore_alias This flag used to be used when regrouping uncore events in particular due to wildcard matches. This is now handled by sorting evlist and so the flag is redundant. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 1 - tools/perf/util/evsel.h | 1 - tools/perf/util/parse-events.c | 12 +++--------- tools/perf/util/parse-events.h | 3 +-- tools/perf/util/parse-events.y | 11 +++++++---- 5 files changed, 11 insertions(+), 17 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3dda8a25cf50..a83d8cd5eb51 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -458,7 +458,6 @@ struct evsel *evsel__clone(struct evsel *orig) evsel->per_pkg = orig->per_pkg; evsel->percore = orig->percore; evsel->precise_max = orig->precise_max; - evsel->use_uncore_alias = orig->use_uncore_alias; evsel->is_libpfm_event = orig->is_libpfm_event; evsel->exclude_GH = orig->exclude_GH; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d26745ca6147..c272c06565c0 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -89,7 +89,6 @@ struct evsel { bool per_pkg; bool percore; bool precise_max; - bool use_uncore_alias; bool is_libpfm_event; bool auto_merge_stats; bool collect_stat; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 394ab23089d0..93a90651266f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1445,15 +1445,13 @@ static int parse_events__inside_hybrid_pmu(struct parse_events_state *parse_stat int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, - bool auto_merge_stats, - bool use_alias) + bool auto_merge_stats) { struct perf_event_attr attr; struct perf_pmu_info info; struct perf_pmu *pmu; struct evsel *evsel; struct parse_events_error *err = parse_state->error; - bool use_uncore_alias; LIST_HEAD(config_terms); pmu = parse_state->fake_pmu ?: perf_pmu__find(name); @@ -1488,8 +1486,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, memset(&attr, 0, sizeof(attr)); } - use_uncore_alias = (pmu->is_uncore && use_alias); - if (!head_config) { attr.type = pmu->type; evsel = __add_event(list, &parse_state->idx, &attr, @@ -1499,7 +1495,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, /*cpu_list=*/NULL); if (evsel) { evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; return 0; } else { return -ENOMEM; @@ -1560,7 +1555,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, evsel->use_config_name = true; evsel->pmu_name = name ? strdup(name) : NULL; - evsel->use_uncore_alias = use_uncore_alias; evsel->percore = config_term_percore(&evsel->config_terms); if (parse_state->fake_pmu) @@ -1622,7 +1616,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, pmu->name, orig_head, - true, true)) { + /*auto_merge_stats=*/true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; @@ -1634,7 +1628,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (parse_state->fake_pmu) { if (!parse_events_add_pmu(parse_state, list, str, head, - true, true)) { + /*auto_merge_stats=*/true)) { pr_debug("%s -> %s/%s/\n", str, "fake_pmu", str); ok++; } diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 22fc11b0bd59..fdac44dc696b 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -183,8 +183,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx, int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, char *name, struct list_head *head_config, - bool auto_merge_stats, - bool use_alias); + bool auto_merge_stats); struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, const char *name, const char *metric_id, diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 90d12f2bc8be..f1b153c72d67 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -313,7 +313,7 @@ event_pmu_name opt_pmu_config list = alloc_list(); if (!list) CLEANUP_YYABORT; - if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false)) { struct perf_pmu *pmu = NULL; int ok = 0; @@ -330,8 +330,10 @@ event_pmu_name opt_pmu_config !perf_pmu__match(pattern, pmu->alias_name, $1)) { if (parse_events_copy_term_list(orig_terms, &terms)) CLEANUP_YYABORT; - if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false)) + if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, + /*auto_merge_stats=*/true)) { ok++; + } parse_events_terms__delete(terms); } } @@ -407,7 +409,8 @@ PE_PMU_EVENT_FAKE sep_dc if (!list) YYABORT; - err = parse_events_add_pmu(_parse_state, list, $1, NULL, false, false); + err = parse_events_add_pmu(_parse_state, list, $1, /*head_config=*/NULL, + /*auto_merge_stats=*/false); free($1); if (err < 0) { free(list); @@ -425,7 +428,7 @@ PE_PMU_EVENT_FAKE opt_pmu_config if (!list) YYABORT; - err = parse_events_add_pmu(_parse_state, list, $1, $2, false, false); + err = parse_events_add_pmu(_parse_state, list, $1, $2, /*auto_merge_stats=*/false); free($1); parse_events_terms__delete($2); if (err < 0) { -- GitLab From 9d2dc632e09c0fe3a8a5890845bbd65b211fd662 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:42 -0800 Subject: [PATCH 0410/5631] perf evlist: Remove nr_groups Maintaining the number of groups during event parsing is problematic and since changing to sort/regroup events can only be computed by a linear pass over the evlist. As the value is generally only used in tests, rather than hold it in a variable compute it by passing over the evlist when necessary. This change highlights that libpfm's counting of groups with a single entry disagreed with regular event parsing. The libpfm tests are updated accordingly. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/evlist.c | 18 +++++++++++++++++- tools/lib/perf/include/internal/evlist.h | 1 - tools/lib/perf/include/perf/evlist.h | 1 + tools/perf/builtin-record.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/tests/bpf.c | 1 - tools/perf/tests/parse-events.c | 22 +++++++++++----------- tools/perf/tests/pfm.c | 12 ++++++------ tools/perf/util/evlist.c | 2 +- tools/perf/util/evlist.h | 6 ++++++ tools/perf/util/header.c | 3 +-- tools/perf/util/parse-events.c | 1 - tools/perf/util/parse-events.h | 1 - tools/perf/util/parse-events.y | 10 ---------- tools/perf/util/pfm.c | 1 - 15 files changed, 45 insertions(+), 38 deletions(-) diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index 2d6121e89ccb..81e8b5fcd8ba 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -703,7 +703,23 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) struct perf_evsel *first = list_entry(evlist->entries.next, struct perf_evsel, node); - evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; __perf_evlist__set_leader(&evlist->entries, first); } } + +int perf_evlist__nr_groups(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int nr_groups = 0; + + perf_evlist__for_each_evsel(evlist, evsel) { + /* + * evsels by default have a nr_members of 1, and they are their + * own leader. If the nr_members is >1 then this is an + * indication of a group. + */ + if (evsel->leader == evsel && evsel->nr_members > 1) + nr_groups++; + } + return nr_groups; +} diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index 850f07070036..3339bc2f1765 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -17,7 +17,6 @@ struct perf_mmap_param; struct perf_evlist { struct list_head entries; int nr_entries; - int nr_groups; bool has_user_cpus; bool needs_map_propagation; /** diff --git a/tools/lib/perf/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h index 9ca399d49bb4..e894b770779e 100644 --- a/tools/lib/perf/include/perf/evlist.h +++ b/tools/lib/perf/include/perf/evlist.h @@ -47,4 +47,5 @@ LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, (pos) = perf_evlist__next_mmap((evlist), (pos), overwrite)) LIBPERF_API void perf_evlist__set_leader(struct perf_evlist *evlist); +LIBPERF_API int perf_evlist__nr_groups(struct perf_evlist *evlist); #endif /* __LIBPERF_EVLIST_H */ diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fb8aab0cedd0..74388164a571 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -2474,7 +2474,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) rec->tool.ordered_events = false; } - if (!rec->evlist->core.nr_groups) + if (evlist__nr_groups(rec->evlist) == 0) perf_header__clear_feat(&session->header, HEADER_GROUP_DESC); if (data->is_pipe) { diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2ee2ecca208e..6400615b5e98 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1481,7 +1481,7 @@ int cmd_report(int argc, const char **argv) setup_forced_leader(&report, session->evlist); - if (symbol_conf.group_sort_idx && !session->evlist->core.nr_groups) { + if (symbol_conf.group_sort_idx && evlist__nr_groups(session->evlist) == 0) { parse_options_usage(NULL, options, "group-sort-idx", 0); ret = -EINVAL; goto error; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index ae9223f27cfb..8beb46066034 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -153,7 +153,6 @@ static int do_test(struct bpf_object *obj, int (*func)(void), } evlist__splice_list_tail(evlist, &parse_state.list); - evlist->core.nr_groups = parse_state.nr_groups; evlist__config(evlist, &opts, NULL); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 71a5cb343311..ffa6f0a90741 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -53,7 +53,7 @@ static int test__checkevent_tracepoint(struct evlist *evlist) struct evsel *evsel = evlist__first(evlist); TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist__nr_groups(evlist)); TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->core.attr.type); TEST_ASSERT_VAL("wrong sample_type", PERF_TP_SAMPLE_TYPE == evsel->core.attr.sample_type); @@ -66,7 +66,7 @@ static int test__checkevent_tracepoint_multi(struct evlist *evlist) struct evsel *evsel; TEST_ASSERT_VAL("wrong number of entries", evlist->core.nr_entries > 1); - TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 0 == evlist__nr_groups(evlist)); evlist__for_each_entry(evlist, evsel) { TEST_ASSERT_VAL("wrong type", @@ -677,7 +677,7 @@ static int test__group1(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* instructions:k */ evsel = leader = evlist__first(evlist); @@ -719,7 +719,7 @@ static int test__group2(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* faults + :ku modifier */ evsel = leader = evlist__first(evlist); @@ -775,7 +775,7 @@ static int test__group3(struct evlist *evlist __maybe_unused) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist__nr_groups(evlist)); /* group1 syscalls:sys_enter_openat:H */ evsel = leader = evlist__first(evlist); @@ -868,7 +868,7 @@ static int test__group4(struct evlist *evlist __maybe_unused) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* cycles:u + p */ evsel = leader = evlist__first(evlist); @@ -912,7 +912,7 @@ static int test__group5(struct evlist *evlist __maybe_unused) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 2 == evlist__nr_groups(evlist)); /* cycles + G */ evsel = leader = evlist__first(evlist); @@ -998,7 +998,7 @@ static int test__group_gh1(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* cycles + :H group modifier */ evsel = leader = evlist__first(evlist); @@ -1038,7 +1038,7 @@ static int test__group_gh2(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* cycles + :G group modifier */ evsel = leader = evlist__first(evlist); @@ -1078,7 +1078,7 @@ static int test__group_gh3(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* cycles:G + :u group modifier */ evsel = leader = evlist__first(evlist); @@ -1118,7 +1118,7 @@ static int test__group_gh4(struct evlist *evlist) struct evsel *evsel, *leader; TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries); - TEST_ASSERT_VAL("wrong number of groups", 1 == evlist->core.nr_groups); + TEST_ASSERT_VAL("wrong number of groups", 1 == evlist__nr_groups(evlist)); /* cycles:G + :uG group modifier */ evsel = leader = evlist__first(evlist); diff --git a/tools/perf/tests/pfm.c b/tools/perf/tests/pfm.c index 71b76deb1f92..2e38dfa34b6c 100644 --- a/tools/perf/tests/pfm.c +++ b/tools/perf/tests/pfm.c @@ -76,7 +76,7 @@ static int test__pfm_events(struct test_suite *test __maybe_unused, count_pfm_events(&evlist->core), table[i].nr_events); TEST_ASSERT_EQUAL(table[i].events, - evlist->core.nr_groups, + evlist__nr_groups(evlist), 0); evlist__delete(evlist); @@ -103,22 +103,22 @@ static int test__pfm_group(struct test_suite *test __maybe_unused, { .events = "{instructions}", .nr_events = 1, - .nr_groups = 1, + .nr_groups = 0, }, { .events = "{instructions},{}", .nr_events = 1, - .nr_groups = 1, + .nr_groups = 0, }, { .events = "{},{instructions}", .nr_events = 1, - .nr_groups = 1, + .nr_groups = 0, }, { .events = "{instructions},{instructions}", .nr_events = 2, - .nr_groups = 2, + .nr_groups = 0, }, { .events = "{instructions,cycles},{instructions,cycles}", @@ -161,7 +161,7 @@ static int test__pfm_group(struct test_suite *test __maybe_unused, count_pfm_events(&evlist->core), table[i].nr_events); TEST_ASSERT_EQUAL(table[i].events, - evlist->core.nr_groups, + evlist__nr_groups(evlist), table[i].nr_groups); evlist__delete(evlist); diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 9e4b2bb0e6fa..b74e12239aec 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1777,7 +1777,7 @@ bool evlist__exclude_kernel(struct evlist *evlist) */ void evlist__force_leader(struct evlist *evlist) { - if (!evlist->core.nr_groups) { + if (evlist__nr_groups(evlist) == 0) { struct evsel *leader = evlist__first(evlist); evlist__set_leader(evlist); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index d89d8f92802b..46cf402add93 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -9,6 +9,7 @@ #include #include #include +#include #include "events_stats.h" #include "evsel.h" #include @@ -255,6 +256,11 @@ static inline struct evsel *evlist__last(struct evlist *evlist) return container_of(evsel, struct evsel, core); } +static inline int evlist__nr_groups(struct evlist *evlist) +{ + return perf_evlist__nr_groups(&evlist->core); +} + int evlist__strerror_open(struct evlist *evlist, int err, char *buf, size_t size); int evlist__strerror_mmap(struct evlist *evlist, int err, char *buf, size_t size); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 404d816ca124..276870221ce0 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -786,7 +786,7 @@ static int write_pmu_mappings(struct feat_fd *ff, static int write_group_desc(struct feat_fd *ff, struct evlist *evlist) { - u32 nr_groups = evlist->core.nr_groups; + u32 nr_groups = evlist__nr_groups(evlist); struct evsel *evsel; int ret; @@ -2807,7 +2807,6 @@ static int process_group_desc(struct feat_fd *ff, void *data __maybe_unused) * Rebuild group relationship based on the group_desc */ session = container_of(ff->ph, struct perf_session, header); - session->evlist->core.nr_groups = nr_groups; i = nr = 0; evlist__for_each_entry(session->evlist, evsel) { diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 93a90651266f..9ec3c1dc81e0 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2260,7 +2260,6 @@ int __parse_events(struct evlist *evlist, const char *str, if (!ret) { struct evsel *last; - evlist->core.nr_groups += parse_state.nr_groups; last = evlist__last(evlist); last->cmdline_group_boundary = true; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index fdac44dc696b..767ad1729228 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -122,7 +122,6 @@ struct parse_events_error { struct parse_events_state { struct list_head list; int idx; - int nr_groups; struct parse_events_error *error; struct evlist *evlist; struct list_head *terms; diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index f1b153c72d67..3a04602d2982 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -49,14 +49,6 @@ static void free_list_evsel(struct list_head* list_evsel) free(list_evsel); } -static void inc_group_count(struct list_head *list, - struct parse_events_state *parse_state) -{ - /* Count groups only have more than 1 members */ - if (!list_is_last(list->next, list)) - parse_state->nr_groups++; -} - %} %token PE_START_EVENTS PE_START_TERMS @@ -201,7 +193,6 @@ PE_NAME '{' events '}' { struct list_head *list = $3; - inc_group_count(list, _parse_state); /* Takes ownership of $1. */ parse_events__set_leader($1, list); $$ = list; @@ -211,7 +202,6 @@ PE_NAME '{' events '}' { struct list_head *list = $2; - inc_group_count(list, _parse_state); parse_events__set_leader(NULL, list); $$ = list; } diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index b59ba825ddc9..6c11914c179f 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -112,7 +112,6 @@ int parse_libpfm_events_option(const struct option *opt, const char *str, "cannot close a non-existing event group\n"); goto error; } - evlist->core.nr_groups++; grp_leader = NULL; grp_evt = -1; } -- GitLab From a4c7d7c502b935f3a8324d954de78aecf6940897 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sat, 11 Mar 2023 18:15:43 -0800 Subject: [PATCH 0411/5631] perf parse-events: Warn when events are regrouped Use if an event is reordered or the number of groups increases to signal that regrouping has happened and warn about it. Disable the warning in the case wild card PMU names are used and for metrics. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kim Phillips Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Sean Christopherson Cc: Steinar H. Gunderson Cc: Stephane Eranian Cc: Suzuki Poulouse Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230312021543.3060328-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 2 +- tools/perf/tests/pmu-events.c | 2 +- tools/perf/util/metricgroup.c | 3 ++- tools/perf/util/parse-events.c | 39 ++++++++++++++++++++++++--------- tools/perf/util/parse-events.h | 7 +++--- tools/perf/util/parse-events.y | 1 + 6 files changed, 38 insertions(+), 16 deletions(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index ffa6f0a90741..b1c2f0a20306 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -2103,7 +2103,7 @@ static int test_event_fake_pmu(const char *str) parse_events_error__init(&err); perf_pmu__test_parse_init(); - ret = __parse_events(evlist, str, &err, &perf_pmu__fake); + ret = __parse_events(evlist, str, &err, &perf_pmu__fake, /*warn_if_reordered=*/true); if (ret) { pr_debug("failed to parse event '%s', err %d, str '%s'\n", str, ret, err.str); diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 6ccd413b5983..7f8e86452527 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -785,7 +785,7 @@ static int check_parse_id(const char *id, struct parse_events_error *error, */ perf_pmu__test_parse_init(); } - ret = __parse_events(evlist, dup, error, fake_pmu); + ret = __parse_events(evlist, dup, error, fake_pmu, /*warn_if_reordered=*/true); free(dup); evlist__delete(evlist); diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index de6dd527a2ba..5783f4c2d1ef 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1441,7 +1441,8 @@ static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu, } pr_debug("Parsing metric events '%s'\n", events.buf); parse_events_error__init(&parse_error); - ret = __parse_events(parsed_evlist, events.buf, &parse_error, fake_pmu); + ret = __parse_events(parsed_evlist, events.buf, &parse_error, fake_pmu, + /*warn_if_reordered=*/false); if (ret) { parse_events_error__print(&parse_error, events.buf); goto err_out; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9ec3c1dc81e0..3b2e5bb3e852 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2157,11 +2157,13 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list return arch_evlist__cmp(lhs, rhs); } -static void parse_events__sort_events_and_fix_groups(struct list_head *list) +static bool parse_events__sort_events_and_fix_groups(struct list_head *list) { - int idx = -1; + int idx = 0, unsorted_idx = -1; struct evsel *pos, *cur_leader = NULL; struct perf_evsel *cur_leaders_grp = NULL; + bool idx_changed = false; + int orig_num_leaders = 0, num_leaders = 0; /* * Compute index to insert ungrouped events at. Place them where the @@ -2170,15 +2172,22 @@ static void parse_events__sort_events_and_fix_groups(struct list_head *list) list_for_each_entry(pos, list, core.node) { const struct evsel *pos_leader = evsel__leader(pos); - if (pos != pos_leader || pos->core.nr_members > 1) - continue; + if (pos == pos_leader) + orig_num_leaders++; - idx = pos->core.idx; - break; + /* + * Ensure indexes are sequential, in particular for multiple + * event lists being merged. The indexes are used to detect when + * the user order is modified. + */ + pos->core.idx = idx++; + + if (unsorted_idx == -1 && pos == pos_leader && pos->core.nr_members < 2) + unsorted_idx = pos->core.idx; } /* Sort events. */ - list_sort(&idx, list, evlist__cmp); + list_sort(&unsorted_idx, list, evlist__cmp); /* * Recompute groups, splitting for PMUs and adding groups for events @@ -2192,6 +2201,8 @@ static void parse_events__sort_events_and_fix_groups(struct list_head *list) bool force_grouped = arch_evsel__must_be_in_group(pos); /* Reset index and nr_members. */ + if (pos->core.idx != idx) + idx_changed = true; pos->core.idx = idx++; pos->core.nr_members = 0; @@ -2225,12 +2236,18 @@ static void parse_events__sort_events_and_fix_groups(struct list_head *list) } } list_for_each_entry(pos, list, core.node) { - pos->core.leader->nr_members++; + struct evsel *pos_leader = evsel__leader(pos); + + if (pos == pos_leader) + num_leaders++; + pos_leader->core.nr_members++; } + return idx_changed || num_leaders != orig_num_leaders; } int __parse_events(struct evlist *evlist, const char *str, - struct parse_events_error *err, struct perf_pmu *fake_pmu) + struct parse_events_error *err, struct perf_pmu *fake_pmu, + bool warn_if_reordered) { struct parse_events_state parse_state = { .list = LIST_HEAD_INIT(parse_state.list), @@ -2250,7 +2267,9 @@ int __parse_events(struct evlist *evlist, const char *str, return -1; } - parse_events__sort_events_and_fix_groups(&parse_state.list); + if (parse_events__sort_events_and_fix_groups(&parse_state.list) && + warn_if_reordered && !parse_state.wild_card_pmus) + pr_warning("WARNING: events were regrouped to match PMUs\n"); /* * Add list to the evlist even with errors to allow callers to clean up. diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 767ad1729228..46204c1a7916 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -26,13 +26,13 @@ int parse_events_option(const struct option *opt, const char *str, int unset); int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset); __attribute__((nonnull(1, 2, 3))) int __parse_events(struct evlist *evlist, const char *str, struct parse_events_error *error, - struct perf_pmu *fake_pmu); + struct perf_pmu *fake_pmu, bool warn_if_reordered); -__attribute__((nonnull)) +__attribute__((nonnull(1, 2, 3))) static inline int parse_events(struct evlist *evlist, const char *str, struct parse_events_error *err) { - return __parse_events(evlist, str, err, NULL); + return __parse_events(evlist, str, err, /*fake_pmu=*/NULL, /*warn_if_reordered=*/true); } int parse_event(struct evlist *evlist, const char *str); @@ -128,6 +128,7 @@ struct parse_events_state { int stoken; struct perf_pmu *fake_pmu; char *hybrid_pmu_name; + bool wild_card_pmus; }; void parse_events__shrink_config_terms(void); diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 3a04602d2982..4488443e506e 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -323,6 +323,7 @@ event_pmu_name opt_pmu_config if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, /*auto_merge_stats=*/true)) { ok++; + parse_state->wild_card_pmus = true; } parse_events_terms__delete(terms); } -- GitLab From 74395567a3011a07f51cf959be96c1eecb3e6df8 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:01:56 +0100 Subject: [PATCH 0412/5631] perf vendor events s390: Add common metrics Add 3 metrics for s390 machines: - Cycles per instruction: Amount of CPU cycles used per instructions, named cpi. - Problem state ratio: Ratio of instructions executed in problem state compared to total number of instructions, named prbstate. - Level one instruction and data cache misses per 100 instructions, named l1mp. For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Output after: # ./perf stat -M cpi -- dd if=/dev/zero of=/dev/null bs=1M count=10K 10240+0 records in 10240+0 records out 10737418240 bytes (11 GB, 10 GiB) copied, 1.30151 s, 8.2 GB/s Performance counter stats for 'dd if=/dev/zero of=/dev/null .....': 6,779,778,802 CPU_CYCLES # 1.96 cpi 3,461,975,090 INSTRUCTIONS 1.306873021 seconds time elapsed 0.001034000 seconds user 1.305677000 seconds sys # Signed-off-by: Thomas Richter Acked-by: Ian Rogers Acked-By: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/s390/cf_z13/transaction.json | 15 +++++++++++++++ .../pmu-events/arch/s390/cf_z14/transaction.json | 15 +++++++++++++++ .../pmu-events/arch/s390/cf_z15/transaction.json | 15 +++++++++++++++ .../pmu-events/arch/s390/cf_z16/transaction.json | 15 +++++++++++++++ 4 files changed, 60 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json index 1a0034f79f73..86bf83b4504e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -3,5 +3,20 @@ "BriefDescription": "Transaction count", "MetricName": "transaction", "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + }, + { + "BriefDescription": "Cycles per Instruction", + "MetricName": "cpi", + "MetricExpr": "CPU_CYCLES / INSTRUCTIONS" + }, + { + "BriefDescription": "Problem State Instruction Ratio", + "MetricName": "prbstate", + "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Level One Miss per 100 Instructions", + "MetricName": "l1mp", + "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json index 1a0034f79f73..86bf83b4504e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -3,5 +3,20 @@ "BriefDescription": "Transaction count", "MetricName": "transaction", "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + }, + { + "BriefDescription": "Cycles per Instruction", + "MetricName": "cpi", + "MetricExpr": "CPU_CYCLES / INSTRUCTIONS" + }, + { + "BriefDescription": "Problem State Instruction Ratio", + "MetricName": "prbstate", + "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Level One Miss per 100 Instructions", + "MetricName": "l1mp", + "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json index 1a0034f79f73..86bf83b4504e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json @@ -3,5 +3,20 @@ "BriefDescription": "Transaction count", "MetricName": "transaction", "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + }, + { + "BriefDescription": "Cycles per Instruction", + "MetricName": "cpi", + "MetricExpr": "CPU_CYCLES / INSTRUCTIONS" + }, + { + "BriefDescription": "Problem State Instruction Ratio", + "MetricName": "prbstate", + "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Level One Miss per 100 Instructions", + "MetricName": "l1mp", + "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json index 1a0034f79f73..86bf83b4504e 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json @@ -3,5 +3,20 @@ "BriefDescription": "Transaction count", "MetricName": "transaction", "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL" + }, + { + "BriefDescription": "Cycles per Instruction", + "MetricName": "cpi", + "MetricExpr": "CPU_CYCLES / INSTRUCTIONS" + }, + { + "BriefDescription": "Problem State Instruction Ratio", + "MetricName": "prbstate", + "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Level One Miss per 100 Instructions", + "MetricName": "l1mp", + "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" } ] -- GitLab From f8a6cea4839bc8c76804b301dbb5522a6cacf6d5 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:01:57 +0100 Subject: [PATCH 0413/5631] perf vendor events s390: Add cache metrics for z16 Add metrics for s390 z16 - Percentage sourced from Level 2 cache - Percentage sourced from Level 3 on same chip cache - Percentage sourced from Level 4 Local cache on same book - Percentage sourced from Level 4 Remote cache on different book - Percentage sourced from memory For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Output after: # ./perf stat -M l4rp -- dd if=/dev/zero of=/dev/null bs=10M count=10K .... dd output deleted Performance counter stats for 'dd if=/dev/zero of=/dev/null bs=10M count=10K': 0 IDCW_OFF_DRAWER_CHIP_HIT # 0.00 l4rp 431,866 L1I_DIR_WRITES 2,395 IDCW_OFF_DRAWER_IV 0 ICW_OFF_DRAWER 0 IDCW_OFF_DRAWER_DRAWER_HIT 1,437 DCW_OFF_DRAWER 425,960,793 L1D_DIR_WRITES 12.165030699 seconds time elapsed 0.001037000 seconds user 12.162140000 seconds sys # Signed-off-by: Thomas Richter Acked-by: Ian Rogers Acked-By: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/s390/cf_z16/transaction.json | 25 +++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json index 86bf83b4504e..dde0735a7d22 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json @@ -18,5 +18,30 @@ "BriefDescription": "Level One Miss per 100 Instructions", "MetricName": "l1mp", "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 2 cache", + "MetricName": "l2p", + "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 3 on same chip cache", + "MetricName": "l3p", + "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Local cache on same book", + "MetricName": "l4lp", + "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book", + "MetricName": "l4rp", + "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from memory", + "MetricName": "memp", + "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" } ] -- GitLab From d30baf2c376f3920e99d3c2c86a1a1b805a3c74c Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 8 Mar 2023 13:53:26 +0100 Subject: [PATCH 0414/5631] perf list: Add PMU pai_ext event description for IBM z16 Add the event description for the IBM z16 pai_ext PMU released with commit c432fefe8e6262bf ("s390/pai: Add support for PAI Extension 1 NNPA counters") The document SA22-7832-13 "z/Architecture Principles of Operation", published May, 2022, contains the description of the Processor Activity Instrumentation Facility and the NNPA counter set., See Pages 5-113 to 5-116 and chapter 26 for details. Signed-off-by: Thomas Richter Acked-by: Ian Rogers Acked-by: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230308125326.2195613-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/s390/cf_z16/pai_ext.json | 178 ++++++++++++++++++ tools/perf/pmu-events/jevents.py | 1 + 2 files changed, 179 insertions(+) create mode 100644 tools/perf/pmu-events/arch/s390/cf_z16/pai_ext.json diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/pai_ext.json b/tools/perf/pmu-events/arch/s390/cf_z16/pai_ext.json new file mode 100644 index 000000000000..7ccbded95dc9 --- /dev/null +++ b/tools/perf/pmu-events/arch/s390/cf_z16/pai_ext.json @@ -0,0 +1,178 @@ +[ + { + "Unit": "PAI-EXT", + "EventCode": "6144", + "EventName": "NNPA_ALL", + "BriefDescription": "NNPA ALL Sum of all non zero counters", + "PublicDescription": "Sum of all non zero NNPA (Neural Networks Processing Assist) counters" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6145", + "EventName": "NNPA_ADD", + "BriefDescription": "NNPA ADD function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6146", + "EventName": "NNPA_SUB", + "BriefDescription": "NNPA SUB function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6147", + "EventName": "NNPA_MUL", + "BriefDescription": "NNPA MUL function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6148", + "EventName": "NNPA_DIV", + "BriefDescription": "NNPA DIV function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6149", + "EventName": "NNPA_MIN", + "BriefDescription": "NNPA MIN function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6150", + "EventName": "NNPA_MAX", + "BriefDescription": "NNPA MAX function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6151", + "EventName": "NNPA_LOG", + "BriefDescription": "NNPA LOG function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6152", + "EventName": "NNPA_EXP", + "BriefDescription": "NNPA EXP function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6153", + "EventName": "NNPA_IBM_RESERVED_9", + "BriefDescription": "Reserved for IBM use", + "PublicDescription": "Reserved for IBM use" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6154", + "EventName": "NNPA_RELU", + "BriefDescription": "NNPA RELU function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6155", + "EventName": "NNPA_TANH", + "BriefDescription": "NNPA TANH function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6156", + "EventName": "NNPA_SIGMOID", + "BriefDescription": "NNPA SIGMOID function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6157", + "EventName": "NNPA_SOFTMAX", + "BriefDescription": "NNPA SOFTMAX function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6158", + "EventName": "NNPA_BATCHNORM", + "BriefDescription": "NNPA BATCHNORM function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6159", + "EventName": "NNPA_MAXPOOL2D", + "BriefDescription": "NNPA MAXPOOL2D function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6160", + "EventName": "NNPA_AVGPOOL2D", + "BriefDescription": "NNPA AVGPOOL2D function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6161", + "EventName": "NNPA_LSTMACT", + "BriefDescription": "NNPA LSTMACT function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6162", + "EventName": "NNPA_GRUACT", + "BriefDescription": "NNPA GRUACT function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6163", + "EventName": "NNPA_CONVOLUTION", + "BriefDescription": "NNPA CONVOLUTION function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6164", + "EventName": "NNPA_MATMUL_OP", + "BriefDescription": "NNPA MATMUL OP function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6165", + "EventName": "NNPA_MATMUL_OP_BCAST23", + "BriefDescription": "NNPA NNPA MATMUL OP BCAST23 function ending with CC=0" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6166", + "EventName": "NNPA_SMALLBATCH", + "BriefDescription": "NNPA SMALLBATCH OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6167", + "EventName": "NNPA_LARGEDIM", + "BriefDescription": "NNPA LARGEDIM OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6168", + "EventName": "NNPA_SMALLTENSOR", + "BriefDescription": "NNPA SMALLTENSOR OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6169", + "EventName": "NNPA_1MFRAME", + "BriefDescription": "NNPA 1MFRAME OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6170", + "EventName": "NNPA_2GFRAME", + "BriefDescription": "NNPA 2GFRAME OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + }, + { + "Unit": "PAI-EXT", + "EventCode": "6171", + "EventName": "NNPA_ACCESSEXCEPT", + "BriefDescription": "NNPA ACCESSEXCEPT OP function ending with CC=0", + "PublicDescription": "NNPA function with conditions as described in Common Operation" + } +] diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 40b9e626fc15..533071a014d7 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -260,6 +260,7 @@ class JsonEvent: 'CPU-M-CF': 'cpum_cf', 'CPU-M-SF': 'cpum_sf', 'PAI-CRYPTO' : 'pai_crypto', + 'PAI-EXT' : 'pai_ext', 'UPI LL': 'uncore_upi', 'hisi_sicl,cpa': 'hisi_sicl,cpa', 'hisi_sccl,ddrc': 'hisi_sccl,ddrc', -- GitLab From 5f968d289b8eae1017e8d465570b444a7021212c Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 8 Mar 2023 09:48:42 +0000 Subject: [PATCH 0415/5631] perf cs-etm: Reduce verbosity of ts_source warning This is printed as a warning but it is normal behavior that users shouldn't be expected to do anything about. Reduce the warning level to debug3 so it's only seen in verbose mode to avoid confusion. Reviewed-by: Leo Yan Cc: Al Grant Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230308094843.287093-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 7f71c8a237ff..59b50dd70330 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -694,8 +694,8 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, data[CS_ETMV4_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TS_SOURCE]); else { - pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", - cpu); + pr_debug3("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", + cpu); data[CS_ETMV4_TS_SOURCE] = (__u64) -1; } } @@ -729,8 +729,8 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, in data[CS_ETE_TS_SOURCE] = (__u64) cs_etm_get_ro_signed(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TS_SOURCE]); else { - pr_warning("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", - cpu); + pr_debug3("[%03d] pmu file 'ts_source' not found. Fallback to safe value (-1)\n", + cpu); data[CS_ETE_TS_SOURCE] = (__u64) -1; } } -- GitLab From e5af139715aaf17f25bc50638a7ca67973fce2af Mon Sep 17 00:00:00 2001 From: James Clark Date: Wed, 8 Mar 2023 09:48:43 +0000 Subject: [PATCH 0416/5631] perf cs-etm: Avoid printing warning in cs_etm_is_ete() check When checking for the presence of ETE, a register is read that may not be present on older kernels or if ETE isn't available. cs_etm_get_ro() will print a warning if it doesn't exist, so check for the existence first before accessing it. Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Al Grant Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230308094843.287093-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 59b50dd70330..86b61ad74f90 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -659,8 +659,12 @@ static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; - int trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]); + int trcdevarch; + if (!cs_etm_pmu_path_exists(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH])) + return false; + + trcdevarch = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCDEVARCH]); /* * ETE if ARCHVER is 5 (ARCHVER is 4 for ETM) and ARCHPART is 0xA13. * See ETM_DEVARCH_ETE_ARCH in coresight-etm4x.h -- GitLab From 17535a33a9c1e4fb52f3db1d72a7ddbe4cea1a2e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 7 Mar 2023 16:30:20 -0800 Subject: [PATCH 0417/5631] perf lock contention: Fix compiler builtin detection __has_builtin was passed the macro rather than the actual builtin feature. The builtin test isn't sufficient and a clang version test also needs to be performed. Fixes: 1bece1351c653c3d ("perf lock contention: Support old rw_semaphore type") Reviewed-by: Namhyung Kim Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230308003020.3653271-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index e6007eaeda1a..141b36d13b19 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -182,7 +182,13 @@ static inline struct task_struct *get_lock_owner(__u64 lock, __u32 flags) struct mutex *mutex = (void *)lock; owner = BPF_CORE_READ(mutex, owner.counter); } else if (flags == LCB_F_READ || flags == LCB_F_WRITE) { -#if __has_builtin(bpf_core_type_matches) + /* + * Support for the BPF_TYPE_MATCHES argument to the + * __builtin_preserve_type_info builtin was added at some point during + * development of clang 15 and it's what is needed for + * bpf_core_type_matches. + */ +#if __has_builtin(__builtin_preserve_type_info) && __clang_major__ >= 15 if (bpf_core_type_matches(struct rw_semaphore___old)) { struct rw_semaphore___old *rwsem = (void *)lock; owner = (unsigned long)BPF_CORE_READ(rwsem, owner); -- GitLab From a7074c3eb26e0193f2c6ed79987e633b7578024e Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Sun, 12 Feb 2023 15:11:08 +0100 Subject: [PATCH 0418/5631] clk: qcom: clk-krait: switch to .determine_rate .determine_rate is meant to replace .round_rate. The former comes with a benefit which is especially relevant on 32-bit systems: since .determine_rate uses an "unsigned long" (compared to a "signed long" which is used by .round_rate) the maximum value on 32-bit systems increases from 2^31 (or approx. 2.14GHz) to 2^32 (or approx. 4.29GHz). Signed-off-by: Luca Weiss Tested-by: Christian Marangi Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230212-clk-qcom-determine_rate-v1-1-b4e447d4926e@z3ntu.xyz --- drivers/clk/qcom/clk-krait.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/clk/qcom/clk-krait.c b/drivers/clk/qcom/clk-krait.c index 293a9dfa7151..f5ce403e1e27 100644 --- a/drivers/clk/qcom/clk-krait.c +++ b/drivers/clk/qcom/clk-krait.c @@ -97,11 +97,11 @@ const struct clk_ops krait_mux_clk_ops = { EXPORT_SYMBOL_GPL(krait_mux_clk_ops); /* The divider can divide by 2, 4, 6 and 8. But we only really need div-2. */ -static long krait_div2_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int krait_div2_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - *parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), rate * 2); - return DIV_ROUND_UP(*parent_rate, 2); + req->best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), req->rate * 2); + req->rate = DIV_ROUND_UP(req->best_parent_rate, 2); + return 0; } static int krait_div2_set_rate(struct clk_hw *hw, unsigned long rate, @@ -142,7 +142,7 @@ krait_div2_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) } const struct clk_ops krait_div2_clk_ops = { - .round_rate = krait_div2_round_rate, + .determine_rate = krait_div2_determine_rate, .set_rate = krait_div2_set_rate, .recalc_rate = krait_div2_recalc_rate, }; -- GitLab From 04648b8fad219599ccc9b103188a38e72d339a3d Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Sun, 12 Feb 2023 15:11:09 +0100 Subject: [PATCH 0419/5631] clk: qcom: clk-hfpll: switch to .determine_rate .determine_rate is meant to replace .round_rate. The former comes with a benefit which is especially relevant on 32-bit systems: since .determine_rate uses an "unsigned long" (compared to a "signed long" which is used by .round_rate) the maximum value on 32-bit systems increases from 2^31 (or approx. 2.14GHz) to 2^32 (or approx. 4.29GHz). Signed-off-by: Luca Weiss Tested-by: Christian Marangi Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230212-clk-qcom-determine_rate-v1-2-b4e447d4926e@z3ntu.xyz --- drivers/clk/qcom/clk-hfpll.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/clk/qcom/clk-hfpll.c b/drivers/clk/qcom/clk-hfpll.c index 7dd17c184b69..86f728dc69e5 100644 --- a/drivers/clk/qcom/clk-hfpll.c +++ b/drivers/clk/qcom/clk-hfpll.c @@ -128,20 +128,20 @@ static void clk_hfpll_disable(struct clk_hw *hw) spin_unlock_irqrestore(&h->lock, flags); } -static long clk_hfpll_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *parent_rate) +static int clk_hfpll_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { struct clk_hfpll *h = to_clk_hfpll(hw); struct hfpll_data const *hd = h->d; unsigned long rrate; - rate = clamp(rate, hd->min_rate, hd->max_rate); + req->rate = clamp(req->rate, hd->min_rate, hd->max_rate); - rrate = DIV_ROUND_UP(rate, *parent_rate) * *parent_rate; + rrate = DIV_ROUND_UP(req->rate, req->best_parent_rate) * req->best_parent_rate; if (rrate > hd->max_rate) - rrate -= *parent_rate; + rrate -= req->best_parent_rate; - return rrate; + req->rate = rrate; + return 0; } /* @@ -241,7 +241,7 @@ const struct clk_ops clk_ops_hfpll = { .enable = clk_hfpll_enable, .disable = clk_hfpll_disable, .is_enabled = hfpll_is_enabled, - .round_rate = clk_hfpll_round_rate, + .determine_rate = clk_hfpll_determine_rate, .set_rate = clk_hfpll_set_rate, .recalc_rate = clk_hfpll_recalc_rate, .init = clk_hfpll_init, -- GitLab From bad27783c962acf837ebb3338843b1ed8272d200 Mon Sep 17 00:00:00 2001 From: Danila Tikhonov Date: Mon, 13 Feb 2023 19:53:17 +0300 Subject: [PATCH 0420/5631] dt-bindings: clock: Add SM7150 GCC clocks Add device tree bindings for global clock subsystem clock controller for Qualcomm Technology Inc's SM7150 SoCs. Co-developed-by: David Wronek Signed-off-by: David Wronek Signed-off-by: Danila Tikhonov Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230213165318.127160-2-danila@jiaxyga.com --- .../bindings/clock/qcom,sm7150-gcc.yaml | 52 +++++ include/dt-bindings/clock/qcom,sm7150-gcc.h | 186 ++++++++++++++++++ 2 files changed, 238 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/qcom,sm7150-gcc.yaml create mode 100644 include/dt-bindings/clock/qcom,sm7150-gcc.h diff --git a/Documentation/devicetree/bindings/clock/qcom,sm7150-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sm7150-gcc.yaml new file mode 100644 index 000000000000..0eb76d9d51c4 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,sm7150-gcc.yaml @@ -0,0 +1,52 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,sm7150-gcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller on SM7150 + +maintainers: + - Bjorn Andersson + - Danila Tikhonov + - David Wronek + +description: | + Qualcomm global clock control module provides the clocks, resets and power + domains on SM7150 + + See also:: include/dt-bindings/clock/qcom,sm7150-gcc.h + +properties: + compatible: + const: qcom,sm7150-gcc + + clocks: + items: + - description: Board XO source + - description: Board XO Active-Only source + - description: Sleep clock source + +required: + - compatible + - clocks + +allOf: + - $ref: qcom,gcc.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + clock-controller@100000 { + compatible = "qcom,sm7150-gcc"; + reg = <0x00100000 0x001f0000>; + clocks = <&rpmhcc RPMH_CXO_CLK>, + <&rpmhcc RPMH_CXO_CLK_A>, + <&sleep_clk>; + #clock-cells = <1>; + #reset-cells = <1>; + #power-domain-cells = <1>; + }; +... diff --git a/include/dt-bindings/clock/qcom,sm7150-gcc.h b/include/dt-bindings/clock/qcom,sm7150-gcc.h new file mode 100644 index 000000000000..7719ffc86139 --- /dev/null +++ b/include/dt-bindings/clock/qcom,sm7150-gcc.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Danila Tikhonov + * Copyright (c) 2023, David Wronek + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GCC_SM7150_H +#define _DT_BINDINGS_CLK_QCOM_GCC_SM7150_H + +/* GCC clock registers */ +#define GCC_GPLL0_MAIN_DIV_CDIV 0 +#define GPLL0 1 +#define GPLL0_OUT_EVEN 2 +#define GPLL6 3 +#define GPLL7 4 +#define GCC_AGGRE_NOC_PCIE_TBU_CLK 5 +#define GCC_AGGRE_UFS_PHY_AXI_CLK 6 +#define GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK 7 +#define GCC_AGGRE_USB3_PRIM_AXI_CLK 8 +#define GCC_APC_VS_CLK 9 +#define GCC_BOOT_ROM_AHB_CLK 10 +#define GCC_CAMERA_HF_AXI_CLK 11 +#define GCC_CAMERA_SF_AXI_CLK 12 +#define GCC_CE1_AHB_CLK 13 +#define GCC_CE1_AXI_CLK 14 +#define GCC_CE1_CLK 15 +#define GCC_CFG_NOC_USB3_PRIM_AXI_CLK 16 +#define GCC_CPUSS_AHB_CLK 17 +#define GCC_CPUSS_AHB_CLK_SRC 18 +#define GCC_CPUSS_RBCPR_CLK 19 +#define GCC_CPUSS_RBCPR_CLK_SRC 20 +#define GCC_DDRSS_GPU_AXI_CLK 21 +#define GCC_DISP_GPLL0_CLK_SRC 22 +#define GCC_DISP_GPLL0_DIV_CLK_SRC 23 +#define GCC_DISP_HF_AXI_CLK 24 +#define GCC_DISP_SF_AXI_CLK 25 +#define GCC_GP1_CLK 26 +#define GCC_GP1_CLK_SRC 27 +#define GCC_GP2_CLK 28 +#define GCC_GP2_CLK_SRC 29 +#define GCC_GP3_CLK 30 +#define GCC_GP3_CLK_SRC 31 +#define GCC_GPU_GPLL0_CLK_SRC 32 +#define GCC_GPU_GPLL0_DIV_CLK_SRC 33 +#define GCC_GPU_MEMNOC_GFX_CLK 34 +#define GCC_GPU_SNOC_DVM_GFX_CLK 35 +#define GCC_GPU_VS_CLK 36 +#define GCC_NPU_AXI_CLK 37 +#define GCC_NPU_CFG_AHB_CLK 38 +#define GCC_NPU_GPLL0_CLK_SRC 39 +#define GCC_NPU_GPLL0_DIV_CLK_SRC 40 +#define GCC_PCIE_0_AUX_CLK 41 +#define GCC_PCIE_0_AUX_CLK_SRC 42 +#define GCC_PCIE_0_CFG_AHB_CLK 43 +#define GCC_PCIE_0_CLKREF_CLK 44 +#define GCC_PCIE_0_MSTR_AXI_CLK 45 +#define GCC_PCIE_0_PIPE_CLK 46 +#define GCC_PCIE_0_SLV_AXI_CLK 47 +#define GCC_PCIE_0_SLV_Q2A_AXI_CLK 48 +#define GCC_PCIE_PHY_AUX_CLK 49 +#define GCC_PCIE_PHY_REFGEN_CLK 50 +#define GCC_PCIE_PHY_REFGEN_CLK_SRC 51 +#define GCC_PDM2_CLK 52 +#define GCC_PDM2_CLK_SRC 53 +#define GCC_PDM_AHB_CLK 54 +#define GCC_PDM_XO4_CLK 55 +#define GCC_PRNG_AHB_CLK 56 +#define GCC_QUPV3_WRAP0_CORE_2X_CLK 57 +#define GCC_QUPV3_WRAP0_CORE_CLK 58 +#define GCC_QUPV3_WRAP0_S0_CLK 59 +#define GCC_QUPV3_WRAP0_S0_CLK_SRC 60 +#define GCC_QUPV3_WRAP0_S1_CLK 61 +#define GCC_QUPV3_WRAP0_S1_CLK_SRC 62 +#define GCC_QUPV3_WRAP0_S2_CLK 63 +#define GCC_QUPV3_WRAP0_S2_CLK_SRC 64 +#define GCC_QUPV3_WRAP0_S3_CLK 65 +#define GCC_QUPV3_WRAP0_S3_CLK_SRC 66 +#define GCC_QUPV3_WRAP0_S4_CLK 67 +#define GCC_QUPV3_WRAP0_S4_CLK_SRC 68 +#define GCC_QUPV3_WRAP0_S5_CLK 69 +#define GCC_QUPV3_WRAP0_S5_CLK_SRC 70 +#define GCC_QUPV3_WRAP0_S6_CLK 71 +#define GCC_QUPV3_WRAP0_S6_CLK_SRC 72 +#define GCC_QUPV3_WRAP0_S7_CLK 73 +#define GCC_QUPV3_WRAP0_S7_CLK_SRC 74 +#define GCC_QUPV3_WRAP1_CORE_2X_CLK 75 +#define GCC_QUPV3_WRAP1_CORE_CLK 76 +#define GCC_QUPV3_WRAP1_S0_CLK 77 +#define GCC_QUPV3_WRAP1_S0_CLK_SRC 78 +#define GCC_QUPV3_WRAP1_S1_CLK 79 +#define GCC_QUPV3_WRAP1_S1_CLK_SRC 80 +#define GCC_QUPV3_WRAP1_S2_CLK 81 +#define GCC_QUPV3_WRAP1_S2_CLK_SRC 82 +#define GCC_QUPV3_WRAP1_S3_CLK 83 +#define GCC_QUPV3_WRAP1_S3_CLK_SRC 84 +#define GCC_QUPV3_WRAP1_S4_CLK 85 +#define GCC_QUPV3_WRAP1_S4_CLK_SRC 86 +#define GCC_QUPV3_WRAP1_S5_CLK 87 +#define GCC_QUPV3_WRAP1_S5_CLK_SRC 88 +#define GCC_QUPV3_WRAP1_S6_CLK 89 +#define GCC_QUPV3_WRAP1_S6_CLK_SRC 90 +#define GCC_QUPV3_WRAP1_S7_CLK 91 +#define GCC_QUPV3_WRAP1_S7_CLK_SRC 92 +#define GCC_QUPV3_WRAP_0_M_AHB_CLK 93 +#define GCC_QUPV3_WRAP_0_S_AHB_CLK 94 +#define GCC_QUPV3_WRAP_1_M_AHB_CLK 95 +#define GCC_QUPV3_WRAP_1_S_AHB_CLK 96 +#define GCC_SDCC1_AHB_CLK 97 +#define GCC_SDCC1_APPS_CLK 98 +#define GCC_SDCC1_APPS_CLK_SRC 99 +#define GCC_SDCC1_ICE_CORE_CLK 100 +#define GCC_SDCC1_ICE_CORE_CLK_SRC 101 +#define GCC_SDCC2_AHB_CLK 102 +#define GCC_SDCC2_APPS_CLK 103 +#define GCC_SDCC2_APPS_CLK_SRC 104 +#define GCC_SDCC4_AHB_CLK 105 +#define GCC_SDCC4_APPS_CLK 106 +#define GCC_SDCC4_APPS_CLK_SRC 107 +#define GCC_SYS_NOC_CPUSS_AHB_CLK 108 +#define GCC_TSIF_AHB_CLK 109 +#define GCC_TSIF_INACTIVITY_TIMERS_CLK 110 +#define GCC_TSIF_REF_CLK 111 +#define GCC_TSIF_REF_CLK_SRC 112 +#define GCC_UFS_MEM_CLKREF_CLK 113 +#define GCC_UFS_PHY_AHB_CLK 114 +#define GCC_UFS_PHY_AXI_CLK 115 +#define GCC_UFS_PHY_AXI_CLK_SRC 116 +#define GCC_UFS_PHY_AXI_HW_CTL_CLK 117 +#define GCC_UFS_PHY_ICE_CORE_CLK 118 +#define GCC_UFS_PHY_ICE_CORE_CLK_SRC 119 +#define GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK 120 +#define GCC_UFS_PHY_PHY_AUX_CLK 121 +#define GCC_UFS_PHY_PHY_AUX_CLK_SRC 122 +#define GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK 123 +#define GCC_UFS_PHY_RX_SYMBOL_0_CLK 124 +#define GCC_UFS_PHY_TX_SYMBOL_0_CLK 125 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK 126 +#define GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC 127 +#define GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK 128 +#define GCC_USB30_PRIM_MASTER_CLK 129 +#define GCC_USB30_PRIM_MASTER_CLK_SRC 130 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK 131 +#define GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC 132 +#define GCC_USB30_PRIM_SLEEP_CLK 133 +#define GCC_USB3_PRIM_CLKREF_CLK 134 +#define GCC_USB3_PRIM_PHY_AUX_CLK 135 +#define GCC_USB3_PRIM_PHY_AUX_CLK_SRC 136 +#define GCC_USB3_PRIM_PHY_COM_AUX_CLK 137 +#define GCC_USB3_PRIM_PHY_PIPE_CLK 138 +#define GCC_USB_PHY_CFG_AHB2PHY_CLK 139 +#define GCC_VDDA_VS_CLK 140 +#define GCC_VDDCX_VS_CLK 141 +#define GCC_VDDMX_VS_CLK 142 +#define GCC_VIDEO_AXI_CLK 143 +#define GCC_VS_CTRL_AHB_CLK 144 +#define GCC_VS_CTRL_CLK 145 +#define GCC_VS_CTRL_CLK_SRC 146 +#define GCC_VSENSOR_CLK_SRC 147 + +/* GCC Resets */ +#define GCC_PCIE_0_BCR 0 +#define GCC_PCIE_PHY_BCR 1 +#define GCC_PCIE_PHY_COM_BCR 2 +#define GCC_UFS_PHY_BCR 3 +#define GCC_USB30_PRIM_BCR 4 +#define GCC_USB3_DP_PHY_PRIM_BCR 5 +#define GCC_USB3_DP_PHY_SEC_BCR 6 +#define GCC_USB3_PHY_PRIM_BCR 7 +#define GCC_USB3_PHY_SEC_BCR 8 +#define GCC_QUSB2PHY_PRIM_BCR 9 +#define GCC_VIDEO_AXI_CLK_BCR 10 + +/* GCC GDSCRs */ +#define PCIE_0_GDSC 0 +#define UFS_PHY_GDSC 1 +#define USB30_PRIM_GDSC 2 +#define HLOS1_VOTE_AGGRE_NOC_MMU_AUDIO_TBU_GDSC 3 +#define HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC 4 +#define HLOS1_VOTE_AGGRE_NOC_MMU_TBU1_GDSC 5 +#define HLOS1_VOTE_AGGRE_NOC_MMU_TBU2_GDSC 6 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC 7 +#define HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC 8 +#define HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC 9 + +#endif -- GitLab From a808d58ddf29c5d593da497053bcb2af1696031b Mon Sep 17 00:00:00 2001 From: Danila Tikhonov Date: Mon, 13 Feb 2023 19:53:18 +0300 Subject: [PATCH 0421/5631] clk: qcom: Add Global Clock Controller (GCC) driver for SM7150 Add support for the global clock controller found on SM7150 based devices. This should allow most non-multimedia device drivers to probe and control their clocks. Co-developed-by: David Wronek Signed-off-by: David Wronek Signed-off-by: Danila Tikhonov Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230213165318.127160-3-danila@jiaxyga.com --- drivers/clk/qcom/Kconfig | 8 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gcc-sm7150.c | 3048 +++++++++++++++++++++++++++++++++ 3 files changed, 3057 insertions(+) create mode 100644 drivers/clk/qcom/gcc-sm7150.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 90ba20a9fa7a..1897ce5c9291 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -759,6 +759,14 @@ config SM_GCC_6375 Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, SD/UFS etc. +config SM_GCC_7150 + tristate "SM7150 Global Clock Controller" + select QCOM_GDSC + help + Support for the global clock controller on SM7150 devices. + Say Y if you want to use peripheral devices such as UART, + SPI, I2C, USB, SD/UFS, PCIe etc. + config SM_GCC_8150 tristate "SM8150 Global Clock Controller" help diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 441406ae404b..04d97a3297e2 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -107,6 +107,7 @@ obj-$(CONFIG_SM_GCC_6115) += gcc-sm6115.o obj-$(CONFIG_SM_GCC_6125) += gcc-sm6125.o obj-$(CONFIG_SM_GCC_6350) += gcc-sm6350.o obj-$(CONFIG_SM_GCC_6375) += gcc-sm6375.o +obj-$(CONFIG_SM_GCC_7150) += gcc-sm7150.o obj-$(CONFIG_SM_GCC_8150) += gcc-sm8150.o obj-$(CONFIG_SM_GCC_8250) += gcc-sm8250.o obj-$(CONFIG_SM_GCC_8350) += gcc-sm8350.o diff --git a/drivers/clk/qcom/gcc-sm7150.c b/drivers/clk/qcom/gcc-sm7150.c new file mode 100644 index 000000000000..6b628178f62c --- /dev/null +++ b/drivers/clk/qcom/gcc-sm7150.c @@ -0,0 +1,3048 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Danila Tikhonov + * Copyright (c) 2023, David Wronek + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "common.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_BI_TCXO, + DT_BI_TCXO_AO, + DT_SLEEP_CLK +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_EVEN, + P_GPLL0_OUT_MAIN, + P_GPLL6_OUT_MAIN, + P_GPLL7_OUT_MAIN, + P_SLEEP_CLK, +}; + +static struct clk_alpha_pll gpll0 = { + .offset = 0x0, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gpll0", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_fabia_ops, + }, + }, +}; + +static const struct clk_div_table post_div_table_fabia_even[] = { + { 0x0, 1 }, + { 0x1, 2 }, + { 0x3, 4 }, + { 0x7, 8 }, + { } +}; + +static struct clk_alpha_pll_postdiv gpll0_out_even = { + .offset = 0x0, + .post_div_shift = 8, + .post_div_table = post_div_table_fabia_even, + .num_post_div = ARRAY_SIZE(post_div_table_fabia_even), + .width = 4, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpll0_out_even", + .parent_hws = (const struct clk_hw*[]){ + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_fabia_ops, + }, +}; + +static struct clk_fixed_factor gcc_pll0_main_div_cdiv = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data){ + .name = "gcc_pll0_main_div_cdiv", + .parent_hws = (const struct clk_hw*[]){ + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_alpha_pll gpll6 = { + .offset = 0x13000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(6), + .hw.init = &(struct clk_init_data){ + .name = "gpll6", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_fabia_ops, + }, + }, +}; + +static struct clk_alpha_pll gpll7 = { + .offset = 0x27000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(7), + .hw.init = &(struct clk_init_data){ + .name = "gpll7", + .parent_data = &(const struct clk_parent_data){ + .index = DT_BI_TCXO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_fabia_ops, + }, + }, +}; + +static const struct parent_map gcc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_even.clkr.hw }, +}; +static const struct clk_parent_data gcc_parent_data_0_ao[] = { + { .index = DT_BI_TCXO_AO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_SLEEP_CLK, 5 }, + { P_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, + { .hw = &gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, +}; + +static const struct clk_parent_data gcc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct clk_parent_data gcc_parent_data_2_ao[] = { + { .index = DT_BI_TCXO_AO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_3[] = { + { P_BI_TCXO, 0 }, + { P_SLEEP_CLK, 5 }, +}; + +static const struct clk_parent_data gcc_parent_data_3[] = { + { .index = DT_BI_TCXO }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_4[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data gcc_parent_data_4[] = { + { .index = DT_BI_TCXO }, +}; + +static const struct parent_map gcc_parent_map_5[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL6_OUT_MAIN, 2 }, + { P_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_5[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll6.clkr.hw }, + { .hw = &gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_6[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL7_OUT_MAIN, 3 }, + { P_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_6[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll7.clkr.hw }, + { .hw = &gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_7[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL0_OUT_EVEN, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_7[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_even.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_8[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, +}; + +static const struct clk_parent_data gcc_parent_data_8[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct freq_tbl ftbl_gcc_cpuss_ahb_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { + .cmd_rcgr = 0x48014, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_ahb_clk_src", + .parent_data = gcc_parent_data_0_ao, + .num_parents = ARRAY_SIZE(gcc_parent_data_0_ao), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_cpuss_rbcpr_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_cpuss_rbcpr_clk_src = { + .cmd_rcgr = 0x4815c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_rbcpr_clk_src", + .parent_data = gcc_parent_data_2_ao, + .num_parents = ARRAY_SIZE(gcc_parent_data_2_ao), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0), + F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_gp1_clk_src = { + .cmd_rcgr = 0x64004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_gp1_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_gp2_clk_src = { + .cmd_rcgr = 0x65004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_gp2_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_gp3_clk_src = { + .cmd_rcgr = 0x66004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_gp3_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_0_aux_clk_src[] = { + F(9600000, P_BI_TCXO, 2, 0, 0), + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_0_aux_clk_src = { + .cmd_rcgr = 0x6b028, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_aux_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_phy_refgen_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_phy_refgen_clk_src = { + .cmd_rcgr = 0x6f014, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcie_phy_refgen_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_phy_refgen_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pdm2_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pdm2_clk_src = { + .cmd_rcgr = 0x33010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pdm2_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_pdm2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qupv3_wrap0_s0_clk_src[] = { + F(7372800, P_GPLL0_OUT_EVEN, 1, 384, 15625), + F(14745600, P_GPLL0_OUT_EVEN, 1, 768, 15625), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(29491200, P_GPLL0_OUT_EVEN, 1, 1536, 15625), + F(32000000, P_GPLL0_OUT_EVEN, 1, 8, 75), + F(48000000, P_GPLL0_OUT_EVEN, 1, 4, 25), + F(64000000, P_GPLL0_OUT_EVEN, 1, 16, 75), + F(80000000, P_GPLL0_OUT_EVEN, 1, 4, 15), + F(96000000, P_GPLL0_OUT_EVEN, 1, 8, 25), + F(100000000, P_GPLL0_OUT_EVEN, 3, 0, 0), + F(102400000, P_GPLL0_OUT_EVEN, 1, 128, 375), + F(112000000, P_GPLL0_OUT_EVEN, 1, 28, 75), + F(117964800, P_GPLL0_OUT_EVEN, 1, 6144, 15625), + F(120000000, P_GPLL0_OUT_EVEN, 2.5, 0, 0), + F(128000000, P_GPLL0_OUT_MAIN, 1, 16, 75), + { } +}; + +static struct clk_init_data gcc_qupv3_wrap0_s0_clk_src_init = { + .name = "gcc_qupv3_wrap0_s0_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s0_clk_src = { + .cmd_rcgr = 0x17034, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s1_clk_src_init = { + .name = "gcc_qupv3_wrap0_s1_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s1_clk_src = { + .cmd_rcgr = 0x17164, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s1_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s2_clk_src_init = { + .name = "gcc_qupv3_wrap0_s2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s2_clk_src = { + .cmd_rcgr = 0x17294, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s2_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s3_clk_src_init = { + .name = "gcc_qupv3_wrap0_s3_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s3_clk_src = { + .cmd_rcgr = 0x173c4, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s4_clk_src_init = { + .name = "gcc_qupv3_wrap0_s4_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s4_clk_src = { + .cmd_rcgr = 0x174f4, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s5_clk_src_init = { + .name = "gcc_qupv3_wrap0_s5_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s5_clk_src = { + .cmd_rcgr = 0x17624, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s5_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s6_clk_src_init = { + .name = "gcc_qupv3_wrap0_s6_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s6_clk_src = { + .cmd_rcgr = 0x17754, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s6_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap0_s7_clk_src_init = { + .name = "gcc_qupv3_wrap0_s7_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap0_s7_clk_src = { + .cmd_rcgr = 0x17884, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap0_s7_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = { + .name = "gcc_qupv3_wrap1_s0_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = { + .cmd_rcgr = 0x18018, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s0_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = { + .name = "gcc_qupv3_wrap1_s1_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = { + .cmd_rcgr = 0x18148, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s1_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = { + .name = "gcc_qupv3_wrap1_s2_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = { + .cmd_rcgr = 0x18278, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s2_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = { + .name = "gcc_qupv3_wrap1_s3_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = { + .cmd_rcgr = 0x183a8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s3_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = { + .name = "gcc_qupv3_wrap1_s4_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = { + .cmd_rcgr = 0x184d8, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s4_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = { + .name = "gcc_qupv3_wrap1_s5_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = { + .cmd_rcgr = 0x18608, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s5_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = { + .name = "gcc_qupv3_wrap1_s6_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = { + .cmd_rcgr = 0x18738, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s6_clk_src_init, +}; + +static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = { + .name = "gcc_qupv3_wrap1_s7_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, +}; + +static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = { + .cmd_rcgr = 0x18868, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_qupv3_wrap0_s0_clk_src, + .clkr.hw.init = &gcc_qupv3_wrap1_s7_clk_src_init, +}; + +static const struct freq_tbl ftbl_gcc_sdcc1_apps_clk_src[] = { + F(144000, P_BI_TCXO, 16, 3, 25), + F(400000, P_BI_TCXO, 12, 1, 4), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(20000000, P_GPLL0_OUT_EVEN, 5, 1, 3), + F(25000000, P_GPLL0_OUT_EVEN, 6, 1, 2), + F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GPLL0_OUT_EVEN, 3, 0, 0), + F(192000000, P_GPLL6_OUT_MAIN, 2, 0, 0), + F(384000000, P_GPLL6_OUT_MAIN, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { + .cmd_rcgr = 0x12028, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_5, + .freq_tbl = ftbl_gcc_sdcc1_apps_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc1_apps_clk_src", + .parent_data = gcc_parent_data_5, + .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc1_ice_core_clk_src[] = { + F(75000000, P_GPLL0_OUT_EVEN, 4, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { + .cmd_rcgr = 0x12010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_sdcc1_ice_core_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc1_ice_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { + F(400000, P_BI_TCXO, 12, 1, 4), + F(9600000, P_BI_TCXO, 2, 0, 0), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0), + F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(208000000, P_GPLL7_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { + .cmd_rcgr = 0x1400c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_6, + .freq_tbl = ftbl_gcc_sdcc2_apps_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc2_apps_clk_src", + .parent_data = gcc_parent_data_6, + .num_parents = ARRAY_SIZE(gcc_parent_data_6), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc4_apps_clk_src[] = { + F(400000, P_BI_TCXO, 12, 1, 4), + F(9600000, P_BI_TCXO, 2, 0, 0), + F(19200000, P_BI_TCXO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0), + F(33333333, P_GPLL0_OUT_EVEN, 9, 0, 0), + F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc4_apps_clk_src = { + .cmd_rcgr = 0x1600c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_sdcc4_apps_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc4_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_tsif_ref_clk_src[] = { + F(105495, P_BI_TCXO, 2, 1, 91), + { } +}; + +static struct clk_rcg2 gcc_tsif_ref_clk_src = { + .cmd_rcgr = 0x36010, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_7, + .freq_tbl = ftbl_gcc_tsif_ref_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_tsif_ref_clk_src", + .parent_data = gcc_parent_data_7, + .num_parents = ARRAY_SIZE(gcc_parent_data_7), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_axi_clk_src[] = { + F(25000000, P_GPLL0_OUT_EVEN, 12, 0, 0), + F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(240000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_axi_clk_src = { + .cmd_rcgr = 0x77020, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_axi_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_axi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_ice_core_clk_src[] = { + F(37500000, P_GPLL0_OUT_EVEN, 8, 0, 0), + F(75000000, P_GPLL0_OUT_EVEN, 4, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_ice_core_clk_src = { + .cmd_rcgr = 0x77048, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_ice_core_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_ice_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_ufs_phy_phy_aux_clk_src = { + .cmd_rcgr = 0x77098, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_pcie_0_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_phy_aux_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_ufs_phy_unipro_core_clk_src[] = { + F(37500000, P_GPLL0_OUT_EVEN, 8, 0, 0), + F(75000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_ufs_phy_unipro_core_clk_src = { + .cmd_rcgr = 0x77060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_ufs_phy_unipro_core_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_unipro_core_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb30_prim_master_clk_src[] = { + F(66666667, P_GPLL0_OUT_EVEN, 4.5, 0, 0), + F(133333333, P_GPLL0_OUT_MAIN, 4.5, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(240000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb30_prim_master_clk_src = { + .cmd_rcgr = 0xf01c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb30_prim_master_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_usb30_prim_master_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb30_prim_mock_utmi_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(20000000, P_GPLL0_OUT_EVEN, 15, 0, 0), + F(40000000, P_GPLL0_OUT_EVEN, 7.5, 0, 0), + F(60000000, P_GPLL0_OUT_MAIN, 10, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb30_prim_mock_utmi_clk_src = { + .cmd_rcgr = 0xf034, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_usb30_prim_mock_utmi_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_usb30_prim_mock_utmi_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb3_prim_phy_aux_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_usb3_prim_phy_aux_clk_src = { + .cmd_rcgr = 0xf060, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_usb3_prim_phy_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_prim_phy_aux_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_vs_ctrl_clk_src = { + .cmd_rcgr = 0x7a030, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_usb3_prim_phy_aux_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_vs_ctrl_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_vsensor_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0), + F(600000000, P_GPLL0_OUT_MAIN, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_vsensor_clk_src = { + .cmd_rcgr = 0x7a018, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_8, + .freq_tbl = ftbl_gcc_vsensor_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_vsensor_clk_src", + .parent_data = gcc_parent_data_8, + .num_parents = ARRAY_SIZE(gcc_parent_data_8), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_aggre_noc_pcie_tbu_clk = { + .halt_reg = 0x2800c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2800c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_aggre_noc_pcie_tbu_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_ufs_phy_axi_clk = { + .halt_reg = 0x82024, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x82024, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x82024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_aggre_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_ufs_phy_axi_hw_ctl_clk = { + .halt_reg = 0x82024, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x82024, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x82024, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_aggre_ufs_phy_axi_hw_ctl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_aggre_ufs_phy_axi_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch_simple_ops, + }, + }, +}; + +static struct clk_branch gcc_aggre_usb3_prim_axi_clk = { + .halt_reg = 0x8201c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8201c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_aggre_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_apc_vs_clk = { + .halt_reg = 0x7a050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_apc_vs_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vsensor_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_boot_rom_ahb_clk = { + .halt_reg = 0x38004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x38004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(10), + .hw.init = &(struct clk_init_data){ + .name = "gcc_boot_rom_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_camera_hf_axi_clk = { + .halt_reg = 0xb020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xb020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_camera_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_camera_sf_axi_clk = { + .halt_reg = 0xb06c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xb06c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_camera_sf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_ahb_clk = { + .halt_reg = 0x4100c, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x4100c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(3), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ce1_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_axi_clk = { + .halt_reg = 0x41008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ce1_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce1_clk = { + .halt_reg = 0x41004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(5), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ce1_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cfg_noc_usb3_prim_axi_clk = { + .halt_reg = 0x502c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x502c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_cfg_noc_usb3_prim_axi_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cpuss_ahb_clk = { + .halt_reg = 0x48000, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(21), + .hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_cpuss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cpuss_rbcpr_clk = { + .halt_reg = 0x48008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x48008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_cpuss_rbcpr_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_cpuss_rbcpr_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ddrss_gpu_axi_clk = { + .halt_reg = 0x4452c, + .halt_check = BRANCH_VOTED, + .clkr = { + .enable_reg = 0x4452c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ddrss_gpu_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + + +static struct clk_branch gcc_disp_gpll0_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(18), + .hw.init = &(struct clk_init_data){ + .name = "gcc_disp_gpll0_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(19), + .hw.init = &(struct clk_init_data){ + .name = "gcc_disp_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pll0_main_div_cdiv.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_hf_axi_clk = { + .halt_reg = 0xb024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xb024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_disp_hf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_disp_sf_axi_clk = { + .halt_reg = 0xb070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xb070, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_disp_sf_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + + +static struct clk_branch gcc_gp1_clk = { + .halt_reg = 0x64000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x64000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gp1_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp2_clk = { + .halt_reg = 0x65000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x65000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gp2_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_gp2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp3_clk = { + .halt_reg = 0x66000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x66000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gp3_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_gp3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(15), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gpu_gpll0_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(16), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gpu_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pll0_main_div_cdiv.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_memnoc_gfx_clk = { + .halt_reg = 0x7100c, + .halt_check = BRANCH_VOTED, + .clkr = { + .enable_reg = 0x7100c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gpu_memnoc_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_snoc_dvm_gfx_clk = { + .halt_reg = 0x71018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x71018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gpu_snoc_dvm_gfx_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gpu_vs_clk = { + .halt_reg = 0x7a04c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a04c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gpu_vs_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vsensor_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_npu_axi_clk = { + .halt_reg = 0x4d008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_npu_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_npu_cfg_ahb_clk = { + .halt_reg = 0x4d004, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x4d004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x4d004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_npu_cfg_ahb_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_npu_gpll0_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(25), + .hw.init = &(struct clk_init_data){ + .name = "gcc_npu_gpll0_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpll0.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_npu_gpll0_div_clk_src = { + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(26), + .hw.init = &(struct clk_init_data){ + .name = "gcc_npu_gpll0_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pll0_main_div_cdiv.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_aux_clk = { + .halt_reg = 0x6b01c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(3), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_aux_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pcie_0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_cfg_ahb_clk = { + .halt_reg = 0x6b018, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b018, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(2), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_cfg_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_clkref_clk = { + .halt_reg = 0x8c008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_mstr_axi_clk = { + .halt_reg = 0x6b014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_mstr_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_pipe_clk = { + .halt_reg = 0x6b020, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_pipe_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_axi_clk = { + .halt_reg = 0x6b010, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x6b010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_slv_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_0_slv_q2a_axi_clk = { + .halt_reg = 0x6b00c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(5), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_0_slv_q2a_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_phy_aux_clk = { + .halt_reg = 0x6f004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6f004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pcie_0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie_phy_refgen_clk = { + .halt_reg = 0x6f02c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x6f02c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pcie_phy_refgen_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pcie_phy_refgen_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm2_clk = { + .halt_reg = 0x3300c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3300c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pdm2_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_pdm2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_ahb_clk = { + .halt_reg = 0x33004, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x33004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x33004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pdm_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pdm_xo4_clk = { + .halt_reg = 0x33008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_pdm_xo4_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_prng_ahb_clk = { + .halt_reg = 0x34004, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x34004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(13), + .hw.init = &(struct clk_init_data){ + .name = "gcc_prng_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_core_2x_clk = { + .halt_reg = 0x17014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(9), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_core_clk = { + .halt_reg = 0x1700c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(8), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s0_clk = { + .halt_reg = 0x17030, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(10), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s0_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s1_clk = { + .halt_reg = 0x17160, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(11), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s1_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s2_clk = { + .halt_reg = 0x17290, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(12), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s2_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s3_clk = { + .halt_reg = 0x173c0, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(13), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s3_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s4_clk = { + .halt_reg = 0x174f0, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(14), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s4_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s5_clk = { + .halt_reg = 0x17620, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(15), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s5_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s6_clk = { + .halt_reg = 0x17750, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(16), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s6_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s6_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap0_s7_clk = { + .halt_reg = 0x17880, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(17), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap0_s7_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap0_s7_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_2x_clk = { + .halt_reg = 0x18004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(18), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_core_2x_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_core_clk = { + .halt_reg = 0x18008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(19), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_core_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s0_clk = { + .halt_reg = 0x18014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(22), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s0_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s0_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s1_clk = { + .halt_reg = 0x18144, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(23), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s1_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s2_clk = { + .halt_reg = 0x18274, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(24), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s2_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s3_clk = { + .halt_reg = 0x183a4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(25), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s3_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s3_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s4_clk = { + .halt_reg = 0x184d4, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(26), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s4_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s4_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s5_clk = { + .halt_reg = 0x18604, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(27), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s5_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s5_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s6_clk = { + .halt_reg = 0x18734, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(28), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s6_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s6_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap1_s7_clk = { + .halt_reg = 0x18864, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(29), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap1_s7_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_qupv3_wrap1_s7_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_0_m_ahb_clk = { + .halt_reg = 0x17004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(6), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap_0_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_0_s_ahb_clk = { + .halt_reg = 0x17008, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x17008, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(7), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap_0_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_m_ahb_clk = { + .halt_reg = 0x1800c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(20), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap_1_m_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qupv3_wrap_1_s_ahb_clk = { + .halt_reg = 0x18010, + .halt_check = BRANCH_HALT_VOTED, + .hwcg_reg = 0x18010, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x5200c, + .enable_mask = BIT(21), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qupv3_wrap_1_s_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x12008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x12008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc1_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x1200c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1200c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc1_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_sdcc1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ice_core_clk = { + .halt_reg = 0x12040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x12040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc1_ice_core_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_sdcc1_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_ahb_clk = { + .halt_reg = 0x14008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc2_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc2_apps_clk = { + .halt_reg = 0x14004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x14004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc2_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_sdcc2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc4_ahb_clk = { + .halt_reg = 0x16008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc4_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc4_apps_clk = { + .halt_reg = 0x16004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sdcc4_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_sdcc4_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_cpuss_ahb_clk = { + .halt_reg = 0x4144, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x52004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_sys_noc_cpuss_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_cpuss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_tsif_ahb_clk = { + .halt_reg = 0x36004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_tsif_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_tsif_inactivity_timers_clk = { + .halt_reg = 0x3600c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3600c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_tsif_inactivity_timers_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_tsif_ref_clk = { + .halt_reg = 0x36008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x36008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_tsif_ref_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_tsif_ref_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_mem_clkref_clk = { + .halt_reg = 0x8c000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_mem_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ahb_clk = { + .halt_reg = 0x77014, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_axi_clk = { + .halt_reg = 0x77038, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77038, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_axi_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_axi_hw_ctl_clk = { + .halt_reg = 0x77038, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77038, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77038, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_axi_hw_ctl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_axi_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch_simple_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ice_core_clk = { + .halt_reg = 0x77090, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77090, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_ice_core_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_ice_core_hw_ctl_clk = { + .halt_reg = 0x77090, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77090, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77090, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_ice_core_hw_ctl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_ice_core_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch_simple_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_phy_aux_clk = { + .halt_reg = 0x77094, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77094, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77094, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_phy_aux_hw_ctl_clk = { + .halt_reg = 0x77094, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x77094, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x77094, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_phy_aux_hw_ctl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_phy_aux_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch_simple_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_rx_symbol_0_clk = { + .halt_reg = 0x7701c, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x7701c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_rx_symbol_0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_tx_symbol_0_clk = { + .halt_reg = 0x77018, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x77018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_tx_symbol_0_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_unipro_core_clk = { + .halt_reg = 0x7708c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x7708c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x7708c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_unipro_core_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_unipro_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ufs_phy_unipro_core_hw_ctl_clk = { + .halt_reg = 0x7708c, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x7708c, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x7708c, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data){ + .name = "gcc_ufs_phy_unipro_core_hw_ctl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_ufs_phy_unipro_core_clk.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch_simple_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_master_clk = { + .halt_reg = 0xf010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb30_prim_master_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb30_prim_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_mock_utmi_clk = { + .halt_reg = 0xf018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb30_prim_mock_utmi_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb30_prim_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb30_prim_sleep_clk = { + .halt_reg = 0xf014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb30_prim_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_clkref_clk = { + .halt_reg = 0x8c010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8c010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_prim_clkref_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_aux_clk = { + .halt_reg = 0xf050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_prim_phy_aux_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_com_aux_clk = { + .halt_reg = 0xf054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xf054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_prim_phy_com_aux_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_usb3_prim_phy_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_prim_phy_pipe_clk = { + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0xf058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_prim_phy_pipe_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb_phy_cfg_ahb2phy_clk = { + .halt_reg = 0x6a004, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x6a004, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x6a004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb_phy_cfg_ahb2phy_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_vdda_vs_clk = { + .halt_reg = 0x7a00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a00c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_vdda_vs_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vsensor_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_vddcx_vs_clk = { + .halt_reg = 0x7a004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_vddcx_vs_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vsensor_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_vddmx_vs_clk = { + .halt_reg = 0x7a008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_vddmx_vs_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vsensor_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + + +static struct clk_branch gcc_video_axi_clk = { + .halt_reg = 0xb01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0xb01c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_video_axi_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_vs_ctrl_ahb_clk = { + .halt_reg = 0x7a014, + .halt_check = BRANCH_HALT, + .hwcg_reg = 0x7a014, + .hwcg_bit = 1, + .clkr = { + .enable_reg = 0x7a014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_vs_ctrl_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_vs_ctrl_clk = { + .halt_reg = 0x7a010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x7a010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_vs_ctrl_clk", + .parent_hws = (const struct clk_hw*[]){ + &gcc_vs_ctrl_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct gdsc pcie_0_gdsc = { + .gdscr = 0x6b004, + .pd = { + .name = "pcie_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc ufs_phy_gdsc = { + .gdscr = 0x77004, + .pd = { + .name = "ufs_phy_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc usb30_prim_gdsc = { + .gdscr = 0xf004, + .pd = { + .name = "usb30_prim_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc = { + .gdscr = 0x7d030, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc = { + .gdscr = 0x7d03c, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_tbu1_gdsc = { + .gdscr = 0x7d034, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_tbu1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_aggre_noc_mmu_tbu2_gdsc = { + .gdscr = 0x7d038, + .pd = { + .name = "hlos1_vote_aggre_noc_mmu_tbu2_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc = { + .gdscr = 0x7d040, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc = { + .gdscr = 0x7d048, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct gdsc hlos1_vote_mmnoc_mmu_tbu_sf_gdsc = { + .gdscr = 0x7d044, + .pd = { + .name = "hlos1_vote_mmnoc_mmu_tbu_sf_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE, +}; + +static struct clk_hw *gcc_sm7150_hws[] = { + [GCC_GPLL0_MAIN_DIV_CDIV] = &gcc_pll0_main_div_cdiv.hw, +}; + +static struct clk_regmap *gcc_sm7150_clocks[] = { + [GCC_AGGRE_NOC_PCIE_TBU_CLK] = &gcc_aggre_noc_pcie_tbu_clk.clkr, + [GCC_AGGRE_UFS_PHY_AXI_CLK] = &gcc_aggre_ufs_phy_axi_clk.clkr, + [GCC_AGGRE_UFS_PHY_AXI_HW_CTL_CLK] = + &gcc_aggre_ufs_phy_axi_hw_ctl_clk.clkr, + [GCC_AGGRE_USB3_PRIM_AXI_CLK] = &gcc_aggre_usb3_prim_axi_clk.clkr, + [GCC_APC_VS_CLK] = &gcc_apc_vs_clk.clkr, + [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, + [GCC_CAMERA_HF_AXI_CLK] = &gcc_camera_hf_axi_clk.clkr, + [GCC_CAMERA_SF_AXI_CLK] = &gcc_camera_sf_axi_clk.clkr, + [GCC_CE1_AHB_CLK] = &gcc_ce1_ahb_clk.clkr, + [GCC_CE1_AXI_CLK] = &gcc_ce1_axi_clk.clkr, + [GCC_CE1_CLK] = &gcc_ce1_clk.clkr, + [GCC_CFG_NOC_USB3_PRIM_AXI_CLK] = &gcc_cfg_noc_usb3_prim_axi_clk.clkr, + [GCC_CPUSS_AHB_CLK] = &gcc_cpuss_ahb_clk.clkr, + [GCC_CPUSS_AHB_CLK_SRC] = &gcc_cpuss_ahb_clk_src.clkr, + [GCC_CPUSS_RBCPR_CLK] = &gcc_cpuss_rbcpr_clk.clkr, + [GCC_CPUSS_RBCPR_CLK_SRC] = &gcc_cpuss_rbcpr_clk_src.clkr, + [GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr, + [GCC_DISP_GPLL0_CLK_SRC] = &gcc_disp_gpll0_clk_src.clkr, + [GCC_DISP_GPLL0_DIV_CLK_SRC] = &gcc_disp_gpll0_div_clk_src.clkr, + [GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr, + [GCC_DISP_SF_AXI_CLK] = &gcc_disp_sf_axi_clk.clkr, + [GCC_GP1_CLK] = &gcc_gp1_clk.clkr, + [GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr, + [GCC_GP2_CLK] = &gcc_gp2_clk.clkr, + [GCC_GP2_CLK_SRC] = &gcc_gp2_clk_src.clkr, + [GCC_GP3_CLK] = &gcc_gp3_clk.clkr, + [GCC_GP3_CLK_SRC] = &gcc_gp3_clk_src.clkr, + [GCC_GPU_GPLL0_CLK_SRC] = &gcc_gpu_gpll0_clk_src.clkr, + [GCC_GPU_GPLL0_DIV_CLK_SRC] = &gcc_gpu_gpll0_div_clk_src.clkr, + [GCC_GPU_MEMNOC_GFX_CLK] = &gcc_gpu_memnoc_gfx_clk.clkr, + [GCC_GPU_SNOC_DVM_GFX_CLK] = &gcc_gpu_snoc_dvm_gfx_clk.clkr, + [GCC_GPU_VS_CLK] = &gcc_gpu_vs_clk.clkr, + [GCC_NPU_AXI_CLK] = &gcc_npu_axi_clk.clkr, + [GCC_NPU_CFG_AHB_CLK] = &gcc_npu_cfg_ahb_clk.clkr, + [GCC_NPU_GPLL0_CLK_SRC] = &gcc_npu_gpll0_clk_src.clkr, + [GCC_NPU_GPLL0_DIV_CLK_SRC] = &gcc_npu_gpll0_div_clk_src.clkr, + [GCC_PCIE_0_AUX_CLK] = &gcc_pcie_0_aux_clk.clkr, + [GCC_PCIE_0_AUX_CLK_SRC] = &gcc_pcie_0_aux_clk_src.clkr, + [GCC_PCIE_0_CFG_AHB_CLK] = &gcc_pcie_0_cfg_ahb_clk.clkr, + [GCC_PCIE_0_CLKREF_CLK] = &gcc_pcie_0_clkref_clk.clkr, + [GCC_PCIE_0_MSTR_AXI_CLK] = &gcc_pcie_0_mstr_axi_clk.clkr, + [GCC_PCIE_0_PIPE_CLK] = &gcc_pcie_0_pipe_clk.clkr, + [GCC_PCIE_0_SLV_AXI_CLK] = &gcc_pcie_0_slv_axi_clk.clkr, + [GCC_PCIE_0_SLV_Q2A_AXI_CLK] = &gcc_pcie_0_slv_q2a_axi_clk.clkr, + [GCC_PCIE_PHY_AUX_CLK] = &gcc_pcie_phy_aux_clk.clkr, + [GCC_PCIE_PHY_REFGEN_CLK] = &gcc_pcie_phy_refgen_clk.clkr, + [GCC_PCIE_PHY_REFGEN_CLK_SRC] = &gcc_pcie_phy_refgen_clk_src.clkr, + [GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr, + [GCC_PDM2_CLK_SRC] = &gcc_pdm2_clk_src.clkr, + [GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr, + [GCC_PDM_XO4_CLK] = &gcc_pdm_xo4_clk.clkr, + [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + [GCC_QUPV3_WRAP0_CORE_2X_CLK] = &gcc_qupv3_wrap0_core_2x_clk.clkr, + [GCC_QUPV3_WRAP0_CORE_CLK] = &gcc_qupv3_wrap0_core_clk.clkr, + [GCC_QUPV3_WRAP0_S0_CLK] = &gcc_qupv3_wrap0_s0_clk.clkr, + [GCC_QUPV3_WRAP0_S0_CLK_SRC] = &gcc_qupv3_wrap0_s0_clk_src.clkr, + [GCC_QUPV3_WRAP0_S1_CLK] = &gcc_qupv3_wrap0_s1_clk.clkr, + [GCC_QUPV3_WRAP0_S1_CLK_SRC] = &gcc_qupv3_wrap0_s1_clk_src.clkr, + [GCC_QUPV3_WRAP0_S2_CLK] = &gcc_qupv3_wrap0_s2_clk.clkr, + [GCC_QUPV3_WRAP0_S2_CLK_SRC] = &gcc_qupv3_wrap0_s2_clk_src.clkr, + [GCC_QUPV3_WRAP0_S3_CLK] = &gcc_qupv3_wrap0_s3_clk.clkr, + [GCC_QUPV3_WRAP0_S3_CLK_SRC] = &gcc_qupv3_wrap0_s3_clk_src.clkr, + [GCC_QUPV3_WRAP0_S4_CLK] = &gcc_qupv3_wrap0_s4_clk.clkr, + [GCC_QUPV3_WRAP0_S4_CLK_SRC] = &gcc_qupv3_wrap0_s4_clk_src.clkr, + [GCC_QUPV3_WRAP0_S5_CLK] = &gcc_qupv3_wrap0_s5_clk.clkr, + [GCC_QUPV3_WRAP0_S5_CLK_SRC] = &gcc_qupv3_wrap0_s5_clk_src.clkr, + [GCC_QUPV3_WRAP0_S6_CLK] = &gcc_qupv3_wrap0_s6_clk.clkr, + [GCC_QUPV3_WRAP0_S6_CLK_SRC] = &gcc_qupv3_wrap0_s6_clk_src.clkr, + [GCC_QUPV3_WRAP0_S7_CLK] = &gcc_qupv3_wrap0_s7_clk.clkr, + [GCC_QUPV3_WRAP0_S7_CLK_SRC] = &gcc_qupv3_wrap0_s7_clk_src.clkr, + [GCC_QUPV3_WRAP1_CORE_2X_CLK] = &gcc_qupv3_wrap1_core_2x_clk.clkr, + [GCC_QUPV3_WRAP1_CORE_CLK] = &gcc_qupv3_wrap1_core_clk.clkr, + [GCC_QUPV3_WRAP1_S0_CLK] = &gcc_qupv3_wrap1_s0_clk.clkr, + [GCC_QUPV3_WRAP1_S0_CLK_SRC] = &gcc_qupv3_wrap1_s0_clk_src.clkr, + [GCC_QUPV3_WRAP1_S1_CLK] = &gcc_qupv3_wrap1_s1_clk.clkr, + [GCC_QUPV3_WRAP1_S1_CLK_SRC] = &gcc_qupv3_wrap1_s1_clk_src.clkr, + [GCC_QUPV3_WRAP1_S2_CLK] = &gcc_qupv3_wrap1_s2_clk.clkr, + [GCC_QUPV3_WRAP1_S2_CLK_SRC] = &gcc_qupv3_wrap1_s2_clk_src.clkr, + [GCC_QUPV3_WRAP1_S3_CLK] = &gcc_qupv3_wrap1_s3_clk.clkr, + [GCC_QUPV3_WRAP1_S3_CLK_SRC] = &gcc_qupv3_wrap1_s3_clk_src.clkr, + [GCC_QUPV3_WRAP1_S4_CLK] = &gcc_qupv3_wrap1_s4_clk.clkr, + [GCC_QUPV3_WRAP1_S4_CLK_SRC] = &gcc_qupv3_wrap1_s4_clk_src.clkr, + [GCC_QUPV3_WRAP1_S5_CLK] = &gcc_qupv3_wrap1_s5_clk.clkr, + [GCC_QUPV3_WRAP1_S5_CLK_SRC] = &gcc_qupv3_wrap1_s5_clk_src.clkr, + [GCC_QUPV3_WRAP1_S6_CLK] = &gcc_qupv3_wrap1_s6_clk.clkr, + [GCC_QUPV3_WRAP1_S6_CLK_SRC] = &gcc_qupv3_wrap1_s6_clk_src.clkr, + [GCC_QUPV3_WRAP1_S7_CLK] = &gcc_qupv3_wrap1_s7_clk.clkr, + [GCC_QUPV3_WRAP1_S7_CLK_SRC] = &gcc_qupv3_wrap1_s7_clk_src.clkr, + [GCC_QUPV3_WRAP_0_M_AHB_CLK] = &gcc_qupv3_wrap_0_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_0_S_AHB_CLK] = &gcc_qupv3_wrap_0_s_ahb_clk.clkr, + [GCC_QUPV3_WRAP_1_M_AHB_CLK] = &gcc_qupv3_wrap_1_m_ahb_clk.clkr, + [GCC_QUPV3_WRAP_1_S_AHB_CLK] = &gcc_qupv3_wrap_1_s_ahb_clk.clkr, + [GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr, + [GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr, + [GCC_SDCC1_APPS_CLK_SRC] = &gcc_sdcc1_apps_clk_src.clkr, + [GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr, + [GCC_SDCC1_ICE_CORE_CLK_SRC] = &gcc_sdcc1_ice_core_clk_src.clkr, + [GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr, + [GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr, + [GCC_SDCC2_APPS_CLK_SRC] = &gcc_sdcc2_apps_clk_src.clkr, + [GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr, + [GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr, + [GCC_SDCC4_APPS_CLK_SRC] = &gcc_sdcc4_apps_clk_src.clkr, + [GCC_SYS_NOC_CPUSS_AHB_CLK] = &gcc_sys_noc_cpuss_ahb_clk.clkr, + [GCC_TSIF_AHB_CLK] = &gcc_tsif_ahb_clk.clkr, + [GCC_TSIF_INACTIVITY_TIMERS_CLK] = &gcc_tsif_inactivity_timers_clk.clkr, + [GCC_TSIF_REF_CLK] = &gcc_tsif_ref_clk.clkr, + [GCC_TSIF_REF_CLK_SRC] = &gcc_tsif_ref_clk_src.clkr, + [GCC_UFS_MEM_CLKREF_CLK] = &gcc_ufs_mem_clkref_clk.clkr, + [GCC_UFS_PHY_AHB_CLK] = &gcc_ufs_phy_ahb_clk.clkr, + [GCC_UFS_PHY_AXI_CLK] = &gcc_ufs_phy_axi_clk.clkr, + [GCC_UFS_PHY_AXI_CLK_SRC] = &gcc_ufs_phy_axi_clk_src.clkr, + [GCC_UFS_PHY_AXI_HW_CTL_CLK] = &gcc_ufs_phy_axi_hw_ctl_clk.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK] = &gcc_ufs_phy_ice_core_clk.clkr, + [GCC_UFS_PHY_ICE_CORE_CLK_SRC] = &gcc_ufs_phy_ice_core_clk_src.clkr, + [GCC_UFS_PHY_ICE_CORE_HW_CTL_CLK] = + &gcc_ufs_phy_ice_core_hw_ctl_clk.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK] = &gcc_ufs_phy_phy_aux_clk.clkr, + [GCC_UFS_PHY_PHY_AUX_CLK_SRC] = &gcc_ufs_phy_phy_aux_clk_src.clkr, + [GCC_UFS_PHY_PHY_AUX_HW_CTL_CLK] = &gcc_ufs_phy_phy_aux_hw_ctl_clk.clkr, + [GCC_UFS_PHY_RX_SYMBOL_0_CLK] = &gcc_ufs_phy_rx_symbol_0_clk.clkr, + [GCC_UFS_PHY_TX_SYMBOL_0_CLK] = &gcc_ufs_phy_tx_symbol_0_clk.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK] = &gcc_ufs_phy_unipro_core_clk.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_CLK_SRC] = + &gcc_ufs_phy_unipro_core_clk_src.clkr, + [GCC_UFS_PHY_UNIPRO_CORE_HW_CTL_CLK] = + &gcc_ufs_phy_unipro_core_hw_ctl_clk.clkr, + [GCC_USB30_PRIM_MASTER_CLK] = &gcc_usb30_prim_master_clk.clkr, + [GCC_USB30_PRIM_MASTER_CLK_SRC] = &gcc_usb30_prim_master_clk_src.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK] = &gcc_usb30_prim_mock_utmi_clk.clkr, + [GCC_USB30_PRIM_MOCK_UTMI_CLK_SRC] = + &gcc_usb30_prim_mock_utmi_clk_src.clkr, + [GCC_USB30_PRIM_SLEEP_CLK] = &gcc_usb30_prim_sleep_clk.clkr, + [GCC_USB3_PRIM_CLKREF_CLK] = &gcc_usb3_prim_clkref_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK] = &gcc_usb3_prim_phy_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_AUX_CLK_SRC] = &gcc_usb3_prim_phy_aux_clk_src.clkr, + [GCC_USB3_PRIM_PHY_COM_AUX_CLK] = &gcc_usb3_prim_phy_com_aux_clk.clkr, + [GCC_USB3_PRIM_PHY_PIPE_CLK] = &gcc_usb3_prim_phy_pipe_clk.clkr, + [GCC_USB_PHY_CFG_AHB2PHY_CLK] = &gcc_usb_phy_cfg_ahb2phy_clk.clkr, + [GCC_VDDA_VS_CLK] = &gcc_vdda_vs_clk.clkr, + [GCC_VDDCX_VS_CLK] = &gcc_vddcx_vs_clk.clkr, + [GCC_VDDMX_VS_CLK] = &gcc_vddmx_vs_clk.clkr, + [GCC_VIDEO_AXI_CLK] = &gcc_video_axi_clk.clkr, + [GCC_VS_CTRL_AHB_CLK] = &gcc_vs_ctrl_ahb_clk.clkr, + [GCC_VS_CTRL_CLK] = &gcc_vs_ctrl_clk.clkr, + [GCC_VS_CTRL_CLK_SRC] = &gcc_vs_ctrl_clk_src.clkr, + [GCC_VSENSOR_CLK_SRC] = &gcc_vsensor_clk_src.clkr, + [GPLL0] = &gpll0.clkr, + [GPLL0_OUT_EVEN] = &gpll0_out_even.clkr, + [GPLL6] = &gpll6.clkr, + [GPLL7] = &gpll7.clkr, +}; + +static const struct qcom_reset_map gcc_sm7150_resets[] = { + [GCC_PCIE_0_BCR] = { 0x6b000 }, + [GCC_PCIE_PHY_BCR] = { 0x6f000 }, + [GCC_PCIE_PHY_COM_BCR] = { 0x6f010 }, + [GCC_UFS_PHY_BCR] = { 0x77000 }, + [GCC_USB30_PRIM_BCR] = { 0xf000 }, + [GCC_USB3_DP_PHY_PRIM_BCR] = { 0x50008 }, + [GCC_USB3_DP_PHY_SEC_BCR] = { 0x50014 }, + [GCC_USB3_PHY_PRIM_BCR] = { 0x50000 }, + [GCC_USB3_PHY_SEC_BCR] = { 0x5000c }, + [GCC_QUSB2PHY_PRIM_BCR] = { 0x26000 }, + [GCC_VIDEO_AXI_CLK_BCR] = { 0xb01c, 2 }, +}; + +static const struct clk_rcg_dfs_data gcc_sm7150_dfs_desc[] = { + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s2_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s5_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s6_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap0_s7_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s0_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s1_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s2_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s3_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s4_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s5_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s6_clk_src), + DEFINE_RCG_DFS(gcc_qupv3_wrap1_s7_clk_src), +}; + +static struct gdsc *gcc_sm7150_gdscs[] = { + [PCIE_0_GDSC] = &pcie_0_gdsc, + [UFS_PHY_GDSC] = &ufs_phy_gdsc, + [USB30_PRIM_GDSC] = &usb30_prim_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_AUDIO_TBU_GDSC] = + &hlos1_vote_aggre_noc_mmu_audio_tbu_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_PCIE_TBU_GDSC] = + &hlos1_vote_aggre_noc_mmu_pcie_tbu_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_TBU1_GDSC] = + &hlos1_vote_aggre_noc_mmu_tbu1_gdsc, + [HLOS1_VOTE_AGGRE_NOC_MMU_TBU2_GDSC] = + &hlos1_vote_aggre_noc_mmu_tbu2_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF0_GDSC] = + &hlos1_vote_mmnoc_mmu_tbu_hf0_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_HF1_GDSC] = + &hlos1_vote_mmnoc_mmu_tbu_hf1_gdsc, + [HLOS1_VOTE_MMNOC_MMU_TBU_SF_GDSC] = &hlos1_vote_mmnoc_mmu_tbu_sf_gdsc, +}; + +static const struct regmap_config gcc_sm7150_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x1820b0, + .fast_io = true, +}; + +static const struct qcom_cc_desc gcc_sm7150_desc = { + .config = &gcc_sm7150_regmap_config, + .clk_hws = gcc_sm7150_hws, + .num_clk_hws = ARRAY_SIZE(gcc_sm7150_hws), + .clks = gcc_sm7150_clocks, + .num_clks = ARRAY_SIZE(gcc_sm7150_clocks), + .resets = gcc_sm7150_resets, + .num_resets = ARRAY_SIZE(gcc_sm7150_resets), + .gdscs = gcc_sm7150_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_sm7150_gdscs), +}; + +static const struct of_device_id gcc_sm7150_match_table[] = { + { .compatible = "qcom,sm7150-gcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gcc_sm7150_match_table); + +static int gcc_sm7150_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + int ret; + + regmap = qcom_cc_map(pdev, &gcc_sm7150_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + /* + * Disable the GPLL0 active input to MM blocks, NPU + * and GPU via MISC registers. + */ + regmap_update_bits(regmap, 0x09ffc, 0x3, 0x3); + regmap_update_bits(regmap, 0x4d110, 0x3, 0x3); + regmap_update_bits(regmap, 0x71028, 0x3, 0x3); + + /* + * Keep the critical clocks always-ON + * GCC_CPUSS_GNOC_CLK, GCC_VIDEO_AHB_CLK, GCC_CAMERA_AHB_CLK, + * GCC_DISP_AHB_CLK, GCC_CAMERA_XO_CLK, GCC_VIDEO_XO_CLK, + * GCC_DISP_XO_CLK, GCC_GPU_CFG_AHB_CLK + */ + regmap_update_bits(regmap, 0x48004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b008, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b00c, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b02c, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b028, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x0b030, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); + + ret = qcom_cc_register_rcg_dfs(regmap, gcc_sm7150_dfs_desc, + ARRAY_SIZE(gcc_sm7150_dfs_desc)); + if (ret) + return ret; + + return qcom_cc_really_probe(pdev, &gcc_sm7150_desc, regmap); +} + +static struct platform_driver gcc_sm7150_driver = { + .probe = gcc_sm7150_probe, + .driver = { + .name = "gcc-sm7150", + .of_match_table = gcc_sm7150_match_table, + }, +}; + +static int __init gcc_sm7150_init(void) +{ + return platform_driver_register(&gcc_sm7150_driver); +} +subsys_initcall(gcc_sm7150_init); + +static void __exit gcc_sm7150_exit(void) +{ + platform_driver_unregister(&gcc_sm7150_driver); +} +module_exit(gcc_sm7150_exit); + +MODULE_DESCRIPTION("Qualcomm SM7150 Global Clock Controller"); +MODULE_LICENSE("GPL"); -- GitLab From 78b1607cb6c92c70886de7824588af9803bea3dd Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 14 Feb 2023 17:23:19 +0100 Subject: [PATCH 0422/5631] dt-bindings: clock: split qcom,gcc-ipq4019 to separate file Move schema for the GCC on IPQ4019 platform to a separate file to be able to allow passing XO and sleep clks directly to GCC. Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214162325.312057-1-robert.marko@sartura.hr --- .../bindings/clock/qcom,gcc-ipq4019.yaml | 53 +++++++++++++++++++ .../bindings/clock/qcom,gcc-other.yaml | 2 - 2 files changed, 53 insertions(+), 2 deletions(-) create mode 100644 Documentation/devicetree/bindings/clock/qcom,gcc-ipq4019.yaml diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-ipq4019.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-ipq4019.yaml new file mode 100644 index 000000000000..6ebaef2288fa --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-ipq4019.yaml @@ -0,0 +1,53 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,gcc-ipq4019.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Global Clock & Reset Controller on IPQ4019 + +maintainers: + - Stephen Boyd + - Taniya Das + - Robert Marko + +description: | + Qualcomm global clock control module provides the clocks, resets and power + domains on IPQ4019. + + See also:: include/dt-bindings/clock/qcom,gcc-ipq4019.h + +allOf: + - $ref: qcom,gcc.yaml# + +properties: + compatible: + const: qcom,gcc-ipq4019 + + clocks: + items: + - description: board XO clock + - description: sleep clock + + clock-names: + items: + - const: xo + - const: sleep_clk + +required: + - compatible + +unevaluatedProperties: false + +examples: + - | + clock-controller@1800000 { + compatible = "qcom,gcc-ipq4019"; + reg = <0x1800000 0x60000>; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + clocks = <&xo>, <&sleep_clk>; + clock-names = "xo", "sleep_clk"; + }; +... diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-other.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-other.yaml index 2e8acca64af1..ae01e7749534 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-other.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-other.yaml @@ -15,7 +15,6 @@ description: | domains. See also:: - include/dt-bindings/clock/qcom,gcc-ipq4019.h include/dt-bindings/clock/qcom,gcc-ipq6018.h include/dt-bindings/reset/qcom,gcc-ipq6018.h include/dt-bindings/clock/qcom,gcc-msm8953.h @@ -29,7 +28,6 @@ allOf: properties: compatible: enum: - - qcom,gcc-ipq4019 - qcom,gcc-ipq6018 - qcom,gcc-mdm9607 - qcom,gcc-msm8953 -- GitLab From 44740af865590320b4278589ac29f30d0e6f2ccf Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 14 Feb 2023 17:23:20 +0100 Subject: [PATCH 0423/5631] clk: qcom: gcc-ipq4019: convert XO and sleep clk to parent_data Start off IPQ4019 GCC conversion by converting XO and sleep clks to parent data in order to directly pass them. Signed-off-by: Robert Marko Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214162325.312057-2-robert.marko@sartura.hr --- drivers/clk/qcom/gcc-ipq4019.c | 75 ++++++++++++++++++++-------------- 1 file changed, 45 insertions(+), 30 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index 5675c60525a7..42a1b7f227c8 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -657,8 +657,9 @@ static struct clk_branch gcc_dcd_xo_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_dcd_xo_clk", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -954,8 +955,9 @@ static struct clk_branch gcc_usb2_sleep_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb2_sleep_clk", - .parent_names = (const char *[]){ - "gcc_sleep_clk_src", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1021,8 +1023,9 @@ static struct clk_branch gcc_usb3_sleep_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb3_sleep_clk", - .parent_names = (const char *[]){ - "gcc_sleep_clk_src", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1110,8 +1113,9 @@ static struct clk_branch gcc_wcss2g_ref_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss2g_ref_clk", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1127,8 +1131,9 @@ static struct clk_branch gcc_wcss2g_rtc_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss2g_rtc_clk", - .parent_names = (const char *[]){ - "gcc_sleep_clk_src", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1179,8 +1184,9 @@ static struct clk_branch gcc_wcss5g_ref_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss5g_ref_clk", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1196,8 +1202,9 @@ static struct clk_branch gcc_wcss5g_rtc_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss5g_rtc_clk", - .parent_names = (const char *[]){ - "gcc_sleep_clk_src", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1360,8 +1367,9 @@ static struct clk_fepll gcc_apss_cpu_plldiv_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "ddrpllapss", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_regmap_cpu_div_ops, @@ -1412,8 +1420,9 @@ static struct clk_fepll gcc_apss_sdcc_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "ddrpllsdcc", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1427,8 +1436,9 @@ static struct clk_fepll gcc_fepll125_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepll125", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1442,8 +1452,9 @@ static struct clk_fepll gcc_fepll125dly_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepll125dly", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1457,8 +1468,9 @@ static struct clk_fepll gcc_fepll200_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepll200", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1472,8 +1484,9 @@ static struct clk_fepll gcc_fepll500_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepll500", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1497,8 +1510,9 @@ static struct clk_fepll gcc_fepllwcss2g_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepllwcss2g", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, @@ -1515,8 +1529,9 @@ static struct clk_fepll gcc_fepllwcss5g_clk = { .cdiv.clkr = { .hw.init = &(struct clk_init_data){ .name = "fepllwcss5g", - .parent_names = (const char *[]){ - "xo", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", }, .num_parents = 1, .ops = &clk_fepll_div_ops, -- GitLab From 96797995e7a0012f3e2dc916af85c41f8c3ff8f3 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 14 Feb 2023 17:23:23 +0100 Subject: [PATCH 0424/5631] clk: qcom: gcc-ipq4019: move PLL clocks up Move PLL clock declarations up, before clock parent tables, so that we can use pll hw clock fields in the next commit. Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214162325.312057-5-robert.marko@sartura.hr --- drivers/clk/qcom/gcc-ipq4019.c | 1052 ++++++++++++++++---------------- 1 file changed, 526 insertions(+), 526 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index 42a1b7f227c8..45d9491198a2 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -171,6 +171,334 @@ static const char * const gcc_xo_ddr_500_200[] = { "ddrpllapss", }; +/* Calculates the VCO rate for FEPLL. */ +static u64 clk_fepll_vco_calc_rate(struct clk_fepll *pll_div, + unsigned long parent_rate) +{ + const struct clk_fepll_vco *pll_vco = pll_div->pll_vco; + u32 fdbkdiv, refclkdiv, cdiv; + u64 vco; + + regmap_read(pll_div->cdiv.clkr.regmap, pll_vco->reg, &cdiv); + refclkdiv = (cdiv >> pll_vco->refclkdiv_shift) & + (BIT(pll_vco->refclkdiv_width) - 1); + fdbkdiv = (cdiv >> pll_vco->fdbkdiv_shift) & + (BIT(pll_vco->fdbkdiv_width) - 1); + + vco = parent_rate / refclkdiv; + vco *= 2; + vco *= fdbkdiv; + + return vco; +} + +static const struct clk_fepll_vco gcc_apss_ddrpll_vco = { + .fdbkdiv_shift = 16, + .fdbkdiv_width = 8, + .refclkdiv_shift = 24, + .refclkdiv_width = 5, + .reg = 0x2e020, +}; + +static const struct clk_fepll_vco gcc_fepll_vco = { + .fdbkdiv_shift = 16, + .fdbkdiv_width = 8, + .refclkdiv_shift = 24, + .refclkdiv_width = 5, + .reg = 0x2f020, +}; + +/* + * Round rate function for APSS CPU PLL Clock divider. + * It looks up the frequency table and returns the next higher frequency + * supported in hardware. + */ +static long clk_cpu_div_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *p_rate) +{ + struct clk_fepll *pll = to_clk_fepll(hw); + struct clk_hw *p_hw; + const struct freq_tbl *f; + + f = qcom_find_freq(pll->freq_tbl, rate); + if (!f) + return -EINVAL; + + p_hw = clk_hw_get_parent_by_index(hw, f->src); + *p_rate = clk_hw_get_rate(p_hw); + + return f->freq; +}; + +/* + * Clock set rate function for APSS CPU PLL Clock divider. + * It looks up the frequency table and updates the PLL divider to corresponding + * divider value. + */ +static int clk_cpu_div_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_fepll *pll = to_clk_fepll(hw); + const struct freq_tbl *f; + u32 mask; + + f = qcom_find_freq(pll->freq_tbl, rate); + if (!f) + return -EINVAL; + + mask = (BIT(pll->cdiv.width) - 1) << pll->cdiv.shift; + regmap_update_bits(pll->cdiv.clkr.regmap, + pll->cdiv.reg, mask, + f->pre_div << pll->cdiv.shift); + /* + * There is no status bit which can be checked for successful CPU + * divider update operation so using delay for the same. + */ + udelay(1); + + return 0; +}; + +/* + * Clock frequency calculation function for APSS CPU PLL Clock divider. + * This clock divider is nonlinear so this function calculates the actual + * divider and returns the output frequency by dividing VCO Frequency + * with this actual divider value. + */ +static unsigned long +clk_cpu_div_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_fepll *pll = to_clk_fepll(hw); + u32 cdiv, pre_div; + u64 rate; + + regmap_read(pll->cdiv.clkr.regmap, pll->cdiv.reg, &cdiv); + cdiv = (cdiv >> pll->cdiv.shift) & (BIT(pll->cdiv.width) - 1); + + /* + * Some dividers have value in 0.5 fraction so multiply both VCO + * frequency(parent_rate) and pre_div with 2 to make integer + * calculation. + */ + if (cdiv > 10) + pre_div = (cdiv + 1) * 2; + else + pre_div = cdiv + 12; + + rate = clk_fepll_vco_calc_rate(pll, parent_rate) * 2; + do_div(rate, pre_div); + + return rate; +}; + +static const struct clk_ops clk_regmap_cpu_div_ops = { + .round_rate = clk_cpu_div_round_rate, + .set_rate = clk_cpu_div_set_rate, + .recalc_rate = clk_cpu_div_recalc_rate, +}; + +static const struct freq_tbl ftbl_apss_ddr_pll[] = { + { 384000000, P_XO, 0xd, 0, 0 }, + { 413000000, P_XO, 0xc, 0, 0 }, + { 448000000, P_XO, 0xb, 0, 0 }, + { 488000000, P_XO, 0xa, 0, 0 }, + { 512000000, P_XO, 0x9, 0, 0 }, + { 537000000, P_XO, 0x8, 0, 0 }, + { 565000000, P_XO, 0x7, 0, 0 }, + { 597000000, P_XO, 0x6, 0, 0 }, + { 632000000, P_XO, 0x5, 0, 0 }, + { 672000000, P_XO, 0x4, 0, 0 }, + { 716000000, P_XO, 0x3, 0, 0 }, + { 768000000, P_XO, 0x2, 0, 0 }, + { 823000000, P_XO, 0x1, 0, 0 }, + { 896000000, P_XO, 0x0, 0, 0 }, + { } +}; + +static struct clk_fepll gcc_apss_cpu_plldiv_clk = { + .cdiv.reg = 0x2e020, + .cdiv.shift = 4, + .cdiv.width = 4, + .cdiv.clkr = { + .enable_reg = 0x2e000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "ddrpllapss", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_regmap_cpu_div_ops, + }, + }, + .freq_tbl = ftbl_apss_ddr_pll, + .pll_vco = &gcc_apss_ddrpll_vco, +}; + +/* Calculates the rate for PLL divider. + * If the divider value is not fixed then it gets the actual divider value + * from divider table. Then, it calculate the clock rate by dividing the + * parent rate with actual divider value. + */ +static unsigned long +clk_regmap_clk_div_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_fepll *pll = to_clk_fepll(hw); + u32 cdiv, pre_div = 1; + u64 rate; + const struct clk_div_table *clkt; + + if (pll->fixed_div) { + pre_div = pll->fixed_div; + } else { + regmap_read(pll->cdiv.clkr.regmap, pll->cdiv.reg, &cdiv); + cdiv = (cdiv >> pll->cdiv.shift) & (BIT(pll->cdiv.width) - 1); + + for (clkt = pll->div_table; clkt->div; clkt++) { + if (clkt->val == cdiv) + pre_div = clkt->div; + } + } + + rate = clk_fepll_vco_calc_rate(pll, parent_rate); + do_div(rate, pre_div); + + return rate; +}; + +static const struct clk_ops clk_fepll_div_ops = { + .recalc_rate = clk_regmap_clk_div_recalc_rate, +}; + +static struct clk_fepll gcc_apss_sdcc_clk = { + .fixed_div = 28, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "ddrpllsdcc", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .pll_vco = &gcc_apss_ddrpll_vco, +}; + +static struct clk_fepll gcc_fepll125_clk = { + .fixed_div = 32, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepll125", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .pll_vco = &gcc_fepll_vco, +}; + +static struct clk_fepll gcc_fepll125dly_clk = { + .fixed_div = 32, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepll125dly", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .pll_vco = &gcc_fepll_vco, +}; + +static struct clk_fepll gcc_fepll200_clk = { + .fixed_div = 20, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepll200", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .pll_vco = &gcc_fepll_vco, +}; + +static struct clk_fepll gcc_fepll500_clk = { + .fixed_div = 8, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepll500", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .pll_vco = &gcc_fepll_vco, +}; + +static const struct clk_div_table fepllwcss_clk_div_table[] = { + { 0, 15 }, + { 1, 16 }, + { 2, 18 }, + { 3, 20 }, + { }, +}; + +static struct clk_fepll gcc_fepllwcss2g_clk = { + .cdiv.reg = 0x2f020, + .cdiv.shift = 8, + .cdiv.width = 2, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepllwcss2g", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .div_table = fepllwcss_clk_div_table, + .pll_vco = &gcc_fepll_vco, +}; + +static struct clk_fepll gcc_fepllwcss5g_clk = { + .cdiv.reg = 0x2f020, + .cdiv.shift = 12, + .cdiv.width = 2, + .cdiv.clkr = { + .hw.init = &(struct clk_init_data){ + .name = "fepllwcss5g", + .parent_data = &(const struct clk_parent_data){ + .fw_name = "xo", + .name = "xo", + }, + .num_parents = 1, + .ops = &clk_fepll_div_ops, + }, + }, + .div_table = fepllwcss_clk_div_table, + .pll_vco = &gcc_fepll_vco, +}; + static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = { F(48000000, P_XO, 1, 0, 0), F(200000000, P_FEPLL200, 1, 0, 0), @@ -874,248 +1202,39 @@ static struct clk_branch gcc_qpic_clk = { .hw.init = &(struct clk_init_data){ .name = "gcc_qpic_clk", .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_sdcc1_ahb_clk = { - .halt_reg = 0x18010, - .clkr = { - .enable_reg = 0x18010, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_sdcc1_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_sdcc1_apps_clk = { - .halt_reg = 0x1800c, - .clkr = { - .enable_reg = 0x1800c, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_sdcc1_apps_clk", - .parent_names = (const char *[]){ - "sdcc1_apps_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, - }, - }, -}; - -static struct clk_branch gcc_tlmm_ahb_clk = { - .halt_reg = 0x5004, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x6000, - .enable_mask = BIT(5), - .hw.init = &(struct clk_init_data){ - .name = "gcc_tlmm_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_usb2_master_clk = { - .halt_reg = 0x1e00c, - .clkr = { - .enable_reg = 0x1e00c, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb2_master_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_usb2_sleep_clk = { - .halt_reg = 0x1e010, - .clkr = { - .enable_reg = 0x1e010, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb2_sleep_clk", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "sleep_clk", - .name = "gcc_sleep_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_usb2_mock_utmi_clk = { - .halt_reg = 0x1e014, - .clkr = { - .enable_reg = 0x1e014, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb2_mock_utmi_clk", - .parent_names = (const char *[]){ - "usb30_mock_utmi_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, - }, - }, -}; - -static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk[] = { - F(2000000, P_FEPLL200, 10, 0, 0), - { } -}; - -static struct clk_rcg2 usb30_mock_utmi_clk_src = { - .cmd_rcgr = 0x1e000, - .hid_width = 5, - .parent_map = gcc_xo_200_map, - .freq_tbl = ftbl_gcc_usb30_mock_utmi_clk, - .clkr.hw.init = &(struct clk_init_data){ - .name = "usb30_mock_utmi_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, - .ops = &clk_rcg2_ops, - }, -}; - -static struct clk_branch gcc_usb3_master_clk = { - .halt_reg = 0x1e028, - .clkr = { - .enable_reg = 0x1e028, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb3_master_clk", - .parent_names = (const char *[]){ - "fepll125", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_usb3_sleep_clk = { - .halt_reg = 0x1e02C, - .clkr = { - .enable_reg = 0x1e02C, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb3_sleep_clk", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "sleep_clk", - .name = "gcc_sleep_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - }, - }, -}; - -static struct clk_branch gcc_usb3_mock_utmi_clk = { - .halt_reg = 0x1e030, - .clkr = { - .enable_reg = 0x1e030, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb3_mock_utmi_clk", - .parent_names = (const char *[]){ - "usb30_mock_utmi_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, - }, - }, -}; - -static const struct freq_tbl ftbl_gcc_fephy_dly_clk[] = { - F(125000000, P_FEPLL125DLY, 1, 0, 0), - { } -}; - -static struct clk_rcg2 fephy_125m_dly_clk_src = { - .cmd_rcgr = 0x12000, - .hid_width = 5, - .parent_map = gcc_xo_125_dly_map, - .freq_tbl = ftbl_gcc_fephy_dly_clk, - .clkr.hw.init = &(struct clk_init_data){ - .name = "fephy_125m_dly_clk_src", - .parent_names = gcc_xo_125_dly, - .num_parents = 2, - .ops = &clk_rcg2_ops, - }, -}; - - -static const struct freq_tbl ftbl_gcc_wcss2g_clk[] = { - F(48000000, P_XO, 1, 0, 0), - F(250000000, P_FEPLLWCSS2G, 1, 0, 0), - { } -}; - -static struct clk_rcg2 wcss2g_clk_src = { - .cmd_rcgr = 0x1f000, - .hid_width = 5, - .freq_tbl = ftbl_gcc_wcss2g_clk, - .parent_map = gcc_xo_wcss2g_map, - .clkr.hw.init = &(struct clk_init_data){ - .name = "wcss2g_clk_src", - .parent_names = gcc_xo_wcss2g, - .num_parents = 2, - .ops = &clk_rcg2_ops, - .flags = CLK_SET_RATE_PARENT, + "pcnoc_clk_src", + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, }, }; -static struct clk_branch gcc_wcss2g_clk = { - .halt_reg = 0x1f00C, +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x18010, .clkr = { - .enable_reg = 0x1f00C, + .enable_reg = 0x18010, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss2g_clk", + .name = "gcc_sdcc1_ahb_clk", .parent_names = (const char *[]){ - "wcss2g_clk_src", + "pcnoc_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, }, }, }; -static struct clk_branch gcc_wcss2g_ref_clk = { - .halt_reg = 0x1f00C, +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x1800c, .clkr = { - .enable_reg = 0x1f00C, + .enable_reg = 0x1800c, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss2g_ref_clk", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .name = "gcc_sdcc1_apps_clk", + .parent_names = (const char *[]){ + "sdcc1_apps_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1124,16 +1243,16 @@ static struct clk_branch gcc_wcss2g_ref_clk = { }, }; -static struct clk_branch gcc_wcss2g_rtc_clk = { - .halt_reg = 0x1f010, +static struct clk_branch gcc_tlmm_ahb_clk = { + .halt_reg = 0x5004, + .halt_check = BRANCH_HALT_VOTED, .clkr = { - .enable_reg = 0x1f010, - .enable_mask = BIT(0), + .enable_reg = 0x6000, + .enable_mask = BIT(5), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss2g_rtc_clk", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "sleep_clk", - .name = "gcc_sleep_clk_src", + .name = "gcc_tlmm_ahb_clk", + .parent_names = (const char *[]){ + "pcnoc_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1141,70 +1260,48 @@ static struct clk_branch gcc_wcss2g_rtc_clk = { }, }; -static const struct freq_tbl ftbl_gcc_wcss5g_clk[] = { - F(48000000, P_XO, 1, 0, 0), - F(250000000, P_FEPLLWCSS5G, 1, 0, 0), - { } -}; - -static struct clk_rcg2 wcss5g_clk_src = { - .cmd_rcgr = 0x20000, - .hid_width = 5, - .parent_map = gcc_xo_wcss5g_map, - .freq_tbl = ftbl_gcc_wcss5g_clk, - .clkr.hw.init = &(struct clk_init_data){ - .name = "wcss5g_clk_src", - .parent_names = gcc_xo_wcss5g, - .num_parents = 2, - .ops = &clk_rcg2_ops, - }, -}; - -static struct clk_branch gcc_wcss5g_clk = { - .halt_reg = 0x2000c, +static struct clk_branch gcc_usb2_master_clk = { + .halt_reg = 0x1e00c, .clkr = { - .enable_reg = 0x2000c, + .enable_reg = 0x1e00c, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss5g_clk", + .name = "gcc_usb2_master_clk", .parent_names = (const char *[]){ - "wcss5g_clk_src", + "pcnoc_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, }, }, }; -static struct clk_branch gcc_wcss5g_ref_clk = { - .halt_reg = 0x2000c, +static struct clk_branch gcc_usb2_sleep_clk = { + .halt_reg = 0x1e010, .clkr = { - .enable_reg = 0x2000c, + .enable_reg = 0x1e010, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss5g_ref_clk", + .name = "gcc_usb2_sleep_clk", .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, }, }, }; -static struct clk_branch gcc_wcss5g_rtc_clk = { - .halt_reg = 0x20010, +static struct clk_branch gcc_usb2_mock_utmi_clk = { + .halt_reg = 0x1e014, .clkr = { - .enable_reg = 0x20010, + .enable_reg = 0x1e014, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "gcc_wcss5g_rtc_clk", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "sleep_clk", - .name = "gcc_sleep_clk_src", + .name = "gcc_usb2_mock_utmi_clk", + .parent_names = (const char *[]){ + "usb30_mock_utmi_clk_src", }, .num_parents = 1, .ops = &clk_branch2_ops, @@ -1213,332 +1310,235 @@ static struct clk_branch gcc_wcss5g_rtc_clk = { }, }; -/* Calculates the VCO rate for FEPLL. */ -static u64 clk_fepll_vco_calc_rate(struct clk_fepll *pll_div, - unsigned long parent_rate) -{ - const struct clk_fepll_vco *pll_vco = pll_div->pll_vco; - u32 fdbkdiv, refclkdiv, cdiv; - u64 vco; - - regmap_read(pll_div->cdiv.clkr.regmap, pll_vco->reg, &cdiv); - refclkdiv = (cdiv >> pll_vco->refclkdiv_shift) & - (BIT(pll_vco->refclkdiv_width) - 1); - fdbkdiv = (cdiv >> pll_vco->fdbkdiv_shift) & - (BIT(pll_vco->fdbkdiv_width) - 1); - - vco = parent_rate / refclkdiv; - vco *= 2; - vco *= fdbkdiv; - - return vco; -} - -static const struct clk_fepll_vco gcc_apss_ddrpll_vco = { - .fdbkdiv_shift = 16, - .fdbkdiv_width = 8, - .refclkdiv_shift = 24, - .refclkdiv_width = 5, - .reg = 0x2e020, -}; - -static const struct clk_fepll_vco gcc_fepll_vco = { - .fdbkdiv_shift = 16, - .fdbkdiv_width = 8, - .refclkdiv_shift = 24, - .refclkdiv_width = 5, - .reg = 0x2f020, -}; - -/* - * Round rate function for APSS CPU PLL Clock divider. - * It looks up the frequency table and returns the next higher frequency - * supported in hardware. - */ -static long clk_cpu_div_round_rate(struct clk_hw *hw, unsigned long rate, - unsigned long *p_rate) -{ - struct clk_fepll *pll = to_clk_fepll(hw); - struct clk_hw *p_hw; - const struct freq_tbl *f; - - f = qcom_find_freq(pll->freq_tbl, rate); - if (!f) - return -EINVAL; - - p_hw = clk_hw_get_parent_by_index(hw, f->src); - *p_rate = clk_hw_get_rate(p_hw); - - return f->freq; -}; - -/* - * Clock set rate function for APSS CPU PLL Clock divider. - * It looks up the frequency table and updates the PLL divider to corresponding - * divider value. - */ -static int clk_cpu_div_set_rate(struct clk_hw *hw, unsigned long rate, - unsigned long parent_rate) -{ - struct clk_fepll *pll = to_clk_fepll(hw); - const struct freq_tbl *f; - u32 mask; - - f = qcom_find_freq(pll->freq_tbl, rate); - if (!f) - return -EINVAL; - - mask = (BIT(pll->cdiv.width) - 1) << pll->cdiv.shift; - regmap_update_bits(pll->cdiv.clkr.regmap, - pll->cdiv.reg, mask, - f->pre_div << pll->cdiv.shift); - /* - * There is no status bit which can be checked for successful CPU - * divider update operation so using delay for the same. - */ - udelay(1); - - return 0; -}; - -/* - * Clock frequency calculation function for APSS CPU PLL Clock divider. - * This clock divider is nonlinear so this function calculates the actual - * divider and returns the output frequency by dividing VCO Frequency - * with this actual divider value. - */ -static unsigned long -clk_cpu_div_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_fepll *pll = to_clk_fepll(hw); - u32 cdiv, pre_div; - u64 rate; - - regmap_read(pll->cdiv.clkr.regmap, pll->cdiv.reg, &cdiv); - cdiv = (cdiv >> pll->cdiv.shift) & (BIT(pll->cdiv.width) - 1); - - /* - * Some dividers have value in 0.5 fraction so multiply both VCO - * frequency(parent_rate) and pre_div with 2 to make integer - * calculation. - */ - if (cdiv > 10) - pre_div = (cdiv + 1) * 2; - else - pre_div = cdiv + 12; - - rate = clk_fepll_vco_calc_rate(pll, parent_rate) * 2; - do_div(rate, pre_div); - - return rate; -}; - -static const struct clk_ops clk_regmap_cpu_div_ops = { - .round_rate = clk_cpu_div_round_rate, - .set_rate = clk_cpu_div_set_rate, - .recalc_rate = clk_cpu_div_recalc_rate, +static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk[] = { + F(2000000, P_FEPLL200, 10, 0, 0), + { } }; -static const struct freq_tbl ftbl_apss_ddr_pll[] = { - { 384000000, P_XO, 0xd, 0, 0 }, - { 413000000, P_XO, 0xc, 0, 0 }, - { 448000000, P_XO, 0xb, 0, 0 }, - { 488000000, P_XO, 0xa, 0, 0 }, - { 512000000, P_XO, 0x9, 0, 0 }, - { 537000000, P_XO, 0x8, 0, 0 }, - { 565000000, P_XO, 0x7, 0, 0 }, - { 597000000, P_XO, 0x6, 0, 0 }, - { 632000000, P_XO, 0x5, 0, 0 }, - { 672000000, P_XO, 0x4, 0, 0 }, - { 716000000, P_XO, 0x3, 0, 0 }, - { 768000000, P_XO, 0x2, 0, 0 }, - { 823000000, P_XO, 0x1, 0, 0 }, - { 896000000, P_XO, 0x0, 0, 0 }, - { } +static struct clk_rcg2 usb30_mock_utmi_clk_src = { + .cmd_rcgr = 0x1e000, + .hid_width = 5, + .parent_map = gcc_xo_200_map, + .freq_tbl = ftbl_gcc_usb30_mock_utmi_clk, + .clkr.hw.init = &(struct clk_init_data){ + .name = "usb30_mock_utmi_clk_src", + .parent_names = gcc_xo_200, + .num_parents = 2, + .ops = &clk_rcg2_ops, + }, }; -static struct clk_fepll gcc_apss_cpu_plldiv_clk = { - .cdiv.reg = 0x2e020, - .cdiv.shift = 4, - .cdiv.width = 4, - .cdiv.clkr = { - .enable_reg = 0x2e000, +static struct clk_branch gcc_usb3_master_clk = { + .halt_reg = 0x1e028, + .clkr = { + .enable_reg = 0x1e028, .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "ddrpllapss", + .name = "gcc_usb3_master_clk", + .parent_names = (const char *[]){ + "fepll125", + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb3_sleep_clk = { + .halt_reg = 0x1e02C, + .clkr = { + .enable_reg = 0x1e02C, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_sleep_clk", .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, - .ops = &clk_regmap_cpu_div_ops, + .ops = &clk_branch2_ops, }, }, - .freq_tbl = ftbl_apss_ddr_pll, - .pll_vco = &gcc_apss_ddrpll_vco, }; -/* Calculates the rate for PLL divider. - * If the divider value is not fixed then it gets the actual divider value - * from divider table. Then, it calculate the clock rate by dividing the - * parent rate with actual divider value. - */ -static unsigned long -clk_regmap_clk_div_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct clk_fepll *pll = to_clk_fepll(hw); - u32 cdiv, pre_div = 1; - u64 rate; - const struct clk_div_table *clkt; +static struct clk_branch gcc_usb3_mock_utmi_clk = { + .halt_reg = 0x1e030, + .clkr = { + .enable_reg = 0x1e030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb3_mock_utmi_clk", + .parent_names = (const char *[]){ + "usb30_mock_utmi_clk_src", + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; - if (pll->fixed_div) { - pre_div = pll->fixed_div; - } else { - regmap_read(pll->cdiv.clkr.regmap, pll->cdiv.reg, &cdiv); - cdiv = (cdiv >> pll->cdiv.shift) & (BIT(pll->cdiv.width) - 1); +static const struct freq_tbl ftbl_gcc_fephy_dly_clk[] = { + F(125000000, P_FEPLL125DLY, 1, 0, 0), + { } +}; - for (clkt = pll->div_table; clkt->div; clkt++) { - if (clkt->val == cdiv) - pre_div = clkt->div; - } - } +static struct clk_rcg2 fephy_125m_dly_clk_src = { + .cmd_rcgr = 0x12000, + .hid_width = 5, + .parent_map = gcc_xo_125_dly_map, + .freq_tbl = ftbl_gcc_fephy_dly_clk, + .clkr.hw.init = &(struct clk_init_data){ + .name = "fephy_125m_dly_clk_src", + .parent_names = gcc_xo_125_dly, + .num_parents = 2, + .ops = &clk_rcg2_ops, + }, +}; - rate = clk_fepll_vco_calc_rate(pll, parent_rate); - do_div(rate, pre_div); - return rate; +static const struct freq_tbl ftbl_gcc_wcss2g_clk[] = { + F(48000000, P_XO, 1, 0, 0), + F(250000000, P_FEPLLWCSS2G, 1, 0, 0), + { } }; -static const struct clk_ops clk_fepll_div_ops = { - .recalc_rate = clk_regmap_clk_div_recalc_rate, +static struct clk_rcg2 wcss2g_clk_src = { + .cmd_rcgr = 0x1f000, + .hid_width = 5, + .freq_tbl = ftbl_gcc_wcss2g_clk, + .parent_map = gcc_xo_wcss2g_map, + .clkr.hw.init = &(struct clk_init_data){ + .name = "wcss2g_clk_src", + .parent_names = gcc_xo_wcss2g, + .num_parents = 2, + .ops = &clk_rcg2_ops, + .flags = CLK_SET_RATE_PARENT, + }, }; -static struct clk_fepll gcc_apss_sdcc_clk = { - .fixed_div = 28, - .cdiv.clkr = { +static struct clk_branch gcc_wcss2g_clk = { + .halt_reg = 0x1f00C, + .clkr = { + .enable_reg = 0x1f00C, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "ddrpllsdcc", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .name = "gcc_wcss2g_clk", + .parent_names = (const char *[]){ + "wcss2g_clk_src", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, }, }, - .pll_vco = &gcc_apss_ddrpll_vco, }; -static struct clk_fepll gcc_fepll125_clk = { - .fixed_div = 32, - .cdiv.clkr = { +static struct clk_branch gcc_wcss2g_ref_clk = { + .halt_reg = 0x1f00C, + .clkr = { + .enable_reg = 0x1f00C, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "fepll125", + .name = "gcc_wcss2g_ref_clk", .parent_data = &(const struct clk_parent_data){ .fw_name = "xo", .name = "xo", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, }, }, - .pll_vco = &gcc_fepll_vco, }; -static struct clk_fepll gcc_fepll125dly_clk = { - .fixed_div = 32, - .cdiv.clkr = { +static struct clk_branch gcc_wcss2g_rtc_clk = { + .halt_reg = 0x1f010, + .clkr = { + .enable_reg = 0x1f010, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "fepll125dly", + .name = "gcc_wcss2g_rtc_clk", .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, }, }, - .pll_vco = &gcc_fepll_vco, }; -static struct clk_fepll gcc_fepll200_clk = { - .fixed_div = 20, - .cdiv.clkr = { - .hw.init = &(struct clk_init_data){ - .name = "fepll200", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", - }, - .num_parents = 1, - .ops = &clk_fepll_div_ops, - }, +static const struct freq_tbl ftbl_gcc_wcss5g_clk[] = { + F(48000000, P_XO, 1, 0, 0), + F(250000000, P_FEPLLWCSS5G, 1, 0, 0), + { } +}; + +static struct clk_rcg2 wcss5g_clk_src = { + .cmd_rcgr = 0x20000, + .hid_width = 5, + .parent_map = gcc_xo_wcss5g_map, + .freq_tbl = ftbl_gcc_wcss5g_clk, + .clkr.hw.init = &(struct clk_init_data){ + .name = "wcss5g_clk_src", + .parent_names = gcc_xo_wcss5g, + .num_parents = 2, + .ops = &clk_rcg2_ops, }, - .pll_vco = &gcc_fepll_vco, }; -static struct clk_fepll gcc_fepll500_clk = { - .fixed_div = 8, - .cdiv.clkr = { +static struct clk_branch gcc_wcss5g_clk = { + .halt_reg = 0x2000c, + .clkr = { + .enable_reg = 0x2000c, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "fepll500", - .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .name = "gcc_wcss5g_clk", + .parent_names = (const char *[]){ + "wcss5g_clk_src", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, }, }, - .pll_vco = &gcc_fepll_vco, -}; - -static const struct clk_div_table fepllwcss_clk_div_table[] = { - { 0, 15 }, - { 1, 16 }, - { 2, 18 }, - { 3, 20 }, - { }, }; -static struct clk_fepll gcc_fepllwcss2g_clk = { - .cdiv.reg = 0x2f020, - .cdiv.shift = 8, - .cdiv.width = 2, - .cdiv.clkr = { +static struct clk_branch gcc_wcss5g_ref_clk = { + .halt_reg = 0x2000c, + .clkr = { + .enable_reg = 0x2000c, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "fepllwcss2g", + .name = "gcc_wcss5g_ref_clk", .parent_data = &(const struct clk_parent_data){ .fw_name = "xo", .name = "xo", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, }, }, - .div_table = fepllwcss_clk_div_table, - .pll_vco = &gcc_fepll_vco, }; -static struct clk_fepll gcc_fepllwcss5g_clk = { - .cdiv.reg = 0x2f020, - .cdiv.shift = 12, - .cdiv.width = 2, - .cdiv.clkr = { +static struct clk_branch gcc_wcss5g_rtc_clk = { + .halt_reg = 0x20010, + .clkr = { + .enable_reg = 0x20010, + .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ - .name = "fepllwcss5g", + .name = "gcc_wcss5g_rtc_clk", .parent_data = &(const struct clk_parent_data){ - .fw_name = "xo", - .name = "xo", + .fw_name = "sleep_clk", + .name = "gcc_sleep_clk_src", }, .num_parents = 1, - .ops = &clk_fepll_div_ops, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, }, }, - .div_table = fepllwcss_clk_div_table, - .pll_vco = &gcc_fepll_vco, }; static const struct freq_tbl ftbl_gcc_pcnoc_ahb_clk[] = { -- GitLab From fca392586c99dc0acb5a15709c2560dd4b24f6a1 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 14 Feb 2023 17:23:24 +0100 Subject: [PATCH 0425/5631] clk: qcom: gcc-ipq4019: move pcnoc clocks up Move pcnoc clocks up just after PLL-s to be able to use their HW fields. Signed-off-by: Robert Marko Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214162325.312057-6-robert.marko@sartura.hr --- drivers/clk/qcom/gcc-ipq4019.c | 74 +++++++++++++++++----------------- 1 file changed, 37 insertions(+), 37 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index 45d9491198a2..ed1330d27d85 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -499,6 +499,43 @@ static struct clk_fepll gcc_fepllwcss5g_clk = { .pll_vco = &gcc_fepll_vco, }; +static const struct freq_tbl ftbl_gcc_pcnoc_ahb_clk[] = { + F(48000000, P_XO, 1, 0, 0), + F(100000000, P_FEPLL200, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcnoc_ahb_clk_src = { + .cmd_rcgr = 0x21024, + .hid_width = 5, + .parent_map = gcc_xo_200_500_map, + .freq_tbl = ftbl_gcc_pcnoc_ahb_clk, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gcc_pcnoc_ahb_clk_src", + .parent_names = gcc_xo_200_500, + .num_parents = 3, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch pcnoc_clk_src = { + .halt_reg = 0x21030, + .clkr = { + .enable_reg = 0x21030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "pcnoc_clk_src", + .parent_names = (const char *[]){ + "gcc_pcnoc_ahb_clk_src", + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT | + CLK_IS_CRITICAL, + }, + }, +}; + static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = { F(48000000, P_XO, 1, 0, 0), F(200000000, P_FEPLL200, 1, 0, 0), @@ -1541,43 +1578,6 @@ static struct clk_branch gcc_wcss5g_rtc_clk = { }, }; -static const struct freq_tbl ftbl_gcc_pcnoc_ahb_clk[] = { - F(48000000, P_XO, 1, 0, 0), - F(100000000, P_FEPLL200, 2, 0, 0), - { } -}; - -static struct clk_rcg2 gcc_pcnoc_ahb_clk_src = { - .cmd_rcgr = 0x21024, - .hid_width = 5, - .parent_map = gcc_xo_200_500_map, - .freq_tbl = ftbl_gcc_pcnoc_ahb_clk, - .clkr.hw.init = &(struct clk_init_data){ - .name = "gcc_pcnoc_ahb_clk_src", - .parent_names = gcc_xo_200_500, - .num_parents = 3, - .ops = &clk_rcg2_ops, - }, -}; - -static struct clk_branch pcnoc_clk_src = { - .halt_reg = 0x21030, - .clkr = { - .enable_reg = 0x21030, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "pcnoc_clk_src", - .parent_names = (const char *[]){ - "gcc_pcnoc_ahb_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT | - CLK_IS_CRITICAL, - }, - }, -}; - static struct clk_regmap *gcc_ipq4019_clocks[] = { [AUDIO_CLK_SRC] = &audio_clk_src.clkr, [BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr, -- GitLab From ed8962b5e24e0a8bd5c2ed6b98fa37aba3a2ac54 Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Tue, 14 Feb 2023 17:23:25 +0100 Subject: [PATCH 0426/5631] clk: qcom: gcc-ipq4019: convert to parent data Convert the IPQ4019 GCC driver to use parent data instead of global name matching. Utilize ARRAY_SIZE for num_parents instead of hardcoding the value. Signed-off-by: Robert Marko Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230214162325.312057-7-robert.marko@sartura.hr --- drivers/clk/qcom/gcc-ipq4019.c | 480 +++++++++++++++------------------ 1 file changed, 222 insertions(+), 258 deletions(-) diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c index ed1330d27d85..5657e29464ad 100644 --- a/drivers/clk/qcom/gcc-ipq4019.c +++ b/drivers/clk/qcom/gcc-ipq4019.c @@ -77,99 +77,12 @@ struct clk_fepll { const struct freq_tbl *freq_tbl; }; -static struct parent_map gcc_xo_200_500_map[] = { - { P_XO, 0 }, - { P_FEPLL200, 1 }, - { P_FEPLL500, 2 }, -}; - -static const char * const gcc_xo_200_500[] = { - "xo", - "fepll200", - "fepll500", -}; - -static struct parent_map gcc_xo_200_map[] = { - { P_XO, 0 }, - { P_FEPLL200, 1 }, -}; - -static const char * const gcc_xo_200[] = { - "xo", - "fepll200", -}; - -static struct parent_map gcc_xo_200_spi_map[] = { - { P_XO, 0 }, - { P_FEPLL200, 2 }, -}; - -static const char * const gcc_xo_200_spi[] = { - "xo", - "fepll200", -}; - -static struct parent_map gcc_xo_sdcc1_500_map[] = { - { P_XO, 0 }, - { P_DDRPLL, 1 }, - { P_FEPLL500, 2 }, -}; - -static const char * const gcc_xo_sdcc1_500[] = { - "xo", - "ddrpllsdcc", - "fepll500", -}; - -static struct parent_map gcc_xo_wcss2g_map[] = { - { P_XO, 0 }, - { P_FEPLLWCSS2G, 1 }, -}; - -static const char * const gcc_xo_wcss2g[] = { - "xo", - "fepllwcss2g", -}; - -static struct parent_map gcc_xo_wcss5g_map[] = { - { P_XO, 0 }, - { P_FEPLLWCSS5G, 1 }, -}; - -static const char * const gcc_xo_wcss5g[] = { - "xo", - "fepllwcss5g", -}; - -static struct parent_map gcc_xo_125_dly_map[] = { - { P_XO, 0 }, - { P_FEPLL125DLY, 1 }, -}; - -static const char * const gcc_xo_125_dly[] = { - "xo", - "fepll125dly", -}; - -static struct parent_map gcc_xo_ddr_500_200_map[] = { - { P_XO, 0 }, - { P_FEPLL200, 3 }, - { P_FEPLL500, 2 }, - { P_DDRPLLAPSS, 1 }, -}; - /* * Contains index for safe clock during APSS freq change. * fepll500 is being used as safe clock so initialize it * with its index in parents list gcc_xo_ddr_500_200. */ static const int gcc_ipq4019_cpu_safe_parent = 2; -static const char * const gcc_xo_ddr_500_200[] = { - "xo", - "fepll200", - "fepll500", - "ddrpllapss", -}; /* Calculates the VCO rate for FEPLL. */ static u64 clk_fepll_vco_calc_rate(struct clk_fepll *pll_div, @@ -499,6 +412,18 @@ static struct clk_fepll gcc_fepllwcss5g_clk = { .pll_vco = &gcc_fepll_vco, }; +static struct parent_map gcc_xo_200_500_map[] = { + { P_XO, 0 }, + { P_FEPLL200, 1 }, + { P_FEPLL500, 2 }, +}; + +static const struct clk_parent_data gcc_xo_200_500[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepll200_clk.cdiv.clkr.hw }, + { .hw = &gcc_fepll500_clk.cdiv.clkr.hw }, +}; + static const struct freq_tbl ftbl_gcc_pcnoc_ahb_clk[] = { F(48000000, P_XO, 1, 0, 0), F(100000000, P_FEPLL200, 2, 0, 0), @@ -512,8 +437,8 @@ static struct clk_rcg2 gcc_pcnoc_ahb_clk_src = { .freq_tbl = ftbl_gcc_pcnoc_ahb_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_pcnoc_ahb_clk_src", - .parent_names = gcc_xo_200_500, - .num_parents = 3, + .parent_data = gcc_xo_200_500, + .num_parents = ARRAY_SIZE(gcc_xo_200_500), .ops = &clk_rcg2_ops, }, }; @@ -525,9 +450,8 @@ static struct clk_branch pcnoc_clk_src = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "pcnoc_clk_src", - .parent_names = (const char *[]){ - "gcc_pcnoc_ahb_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_pcnoc_ahb_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT | @@ -536,6 +460,16 @@ static struct clk_branch pcnoc_clk_src = { }, }; +static struct parent_map gcc_xo_200_map[] = { + { P_XO, 0 }, + { P_FEPLL200, 1 }, +}; + +static const struct clk_parent_data gcc_xo_200[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepll200_clk.cdiv.clkr.hw }, +}; + static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = { F(48000000, P_XO, 1, 0, 0), F(200000000, P_FEPLL200, 1, 0, 0), @@ -549,8 +483,8 @@ static struct clk_rcg2 audio_clk_src = { .freq_tbl = ftbl_gcc_audio_pwm_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "audio_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, @@ -563,9 +497,8 @@ static struct clk_branch gcc_audio_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_audio_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .flags = CLK_SET_RATE_PARENT, .num_parents = 1, .ops = &clk_branch2_ops, @@ -580,9 +513,8 @@ static struct clk_branch gcc_audio_pwm_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_audio_pwm_clk", - .parent_names = (const char *[]){ - "audio_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &audio_clk_src.clkr.hw }, .flags = CLK_SET_RATE_PARENT, .num_parents = 1, .ops = &clk_branch2_ops, @@ -602,8 +534,8 @@ static struct clk_rcg2 blsp1_qup1_i2c_apps_clk_src = { .freq_tbl = ftbl_gcc_blsp1_qup1_2_i2c_apps_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_qup1_i2c_apps_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; @@ -615,9 +547,8 @@ static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_qup1_i2c_apps_clk", - .parent_names = (const char *[]){ - "blsp1_qup1_i2c_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_qup1_i2c_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -632,8 +563,8 @@ static struct clk_rcg2 blsp1_qup2_i2c_apps_clk_src = { .freq_tbl = ftbl_gcc_blsp1_qup1_2_i2c_apps_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_qup2_i2c_apps_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; @@ -645,9 +576,8 @@ static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_qup2_i2c_apps_clk", - .parent_names = (const char *[]){ - "blsp1_qup2_i2c_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_qup2_i2c_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -655,6 +585,16 @@ static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = { }, }; +static struct parent_map gcc_xo_200_spi_map[] = { + { P_XO, 0 }, + { P_FEPLL200, 2 }, +}; + +static const struct clk_parent_data gcc_xo_200_spi[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepll200_clk.cdiv.clkr.hw }, +}; + static const struct freq_tbl ftbl_gcc_blsp1_qup1_2_spi_apps_clk[] = { F(960000, P_XO, 12, 1, 4), F(4800000, P_XO, 1, 1, 10), @@ -674,8 +614,8 @@ static struct clk_rcg2 blsp1_qup1_spi_apps_clk_src = { .freq_tbl = ftbl_gcc_blsp1_qup1_2_spi_apps_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_qup1_spi_apps_clk_src", - .parent_names = gcc_xo_200_spi, - .num_parents = 2, + .parent_data = gcc_xo_200_spi, + .num_parents = ARRAY_SIZE(gcc_xo_200_spi), .ops = &clk_rcg2_ops, }, }; @@ -687,9 +627,8 @@ static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_qup1_spi_apps_clk", - .parent_names = (const char *[]){ - "blsp1_qup1_spi_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_qup1_spi_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -705,8 +644,8 @@ static struct clk_rcg2 blsp1_qup2_spi_apps_clk_src = { .parent_map = gcc_xo_200_spi_map, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_qup2_spi_apps_clk_src", - .parent_names = gcc_xo_200_spi, - .num_parents = 2, + .parent_data = gcc_xo_200_spi, + .num_parents = ARRAY_SIZE(gcc_xo_200_spi), .ops = &clk_rcg2_ops, }, }; @@ -718,9 +657,8 @@ static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_qup2_spi_apps_clk", - .parent_names = (const char *[]){ - "blsp1_qup2_spi_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_qup2_spi_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -750,8 +688,8 @@ static struct clk_rcg2 blsp1_uart1_apps_clk_src = { .parent_map = gcc_xo_200_spi_map, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_uart1_apps_clk_src", - .parent_names = gcc_xo_200_spi, - .num_parents = 2, + .parent_data = gcc_xo_200_spi, + .num_parents = ARRAY_SIZE(gcc_xo_200_spi), .ops = &clk_rcg2_ops, }, }; @@ -763,9 +701,8 @@ static struct clk_branch gcc_blsp1_uart1_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_uart1_apps_clk", - .parent_names = (const char *[]){ - "blsp1_uart1_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_uart1_apps_clk_src.clkr.hw }, .flags = CLK_SET_RATE_PARENT, .num_parents = 1, .ops = &clk_branch2_ops, @@ -781,8 +718,8 @@ static struct clk_rcg2 blsp1_uart2_apps_clk_src = { .parent_map = gcc_xo_200_spi_map, .clkr.hw.init = &(struct clk_init_data){ .name = "blsp1_uart2_apps_clk_src", - .parent_names = gcc_xo_200_spi, - .num_parents = 2, + .parent_data = gcc_xo_200_spi, + .num_parents = ARRAY_SIZE(gcc_xo_200_spi), .ops = &clk_rcg2_ops, }, }; @@ -794,9 +731,8 @@ static struct clk_branch gcc_blsp1_uart2_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_uart2_apps_clk", - .parent_names = (const char *[]){ - "blsp1_uart2_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &blsp1_uart2_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -819,8 +755,8 @@ static struct clk_rcg2 gp1_clk_src = { .parent_map = gcc_xo_200_map, .clkr.hw.init = &(struct clk_init_data){ .name = "gp1_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; @@ -832,9 +768,8 @@ static struct clk_branch gcc_gp1_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_gp1_clk", - .parent_names = (const char *[]){ - "gp1_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &gp1_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -850,8 +785,8 @@ static struct clk_rcg2 gp2_clk_src = { .parent_map = gcc_xo_200_map, .clkr.hw.init = &(struct clk_init_data){ .name = "gp2_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; @@ -863,9 +798,8 @@ static struct clk_branch gcc_gp2_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_gp2_clk", - .parent_names = (const char *[]){ - "gp2_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &gp2_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -881,8 +815,8 @@ static struct clk_rcg2 gp3_clk_src = { .parent_map = gcc_xo_200_map, .clkr.hw.init = &(struct clk_init_data){ .name = "gp3_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; @@ -894,9 +828,8 @@ static struct clk_branch gcc_gp3_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_gp3_clk", - .parent_names = (const char *[]){ - "gp3_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &gp3_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -904,6 +837,18 @@ static struct clk_branch gcc_gp3_clk = { }, }; +static struct parent_map gcc_xo_sdcc1_500_map[] = { + { P_XO, 0 }, + { P_DDRPLL, 1 }, + { P_FEPLL500, 2 }, +}; + +static const struct clk_parent_data gcc_xo_sdcc1_500[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_apss_sdcc_clk.cdiv.clkr.hw }, + { .hw = &gcc_fepll500_clk.cdiv.clkr.hw }, +}; + static const struct freq_tbl ftbl_gcc_sdcc1_apps_clk[] = { F(144000, P_XO, 1, 3, 240), F(400000, P_XO, 1, 1, 0), @@ -922,8 +867,8 @@ static struct clk_rcg2 sdcc1_apps_clk_src = { .parent_map = gcc_xo_sdcc1_500_map, .clkr.hw.init = &(struct clk_init_data){ .name = "sdcc1_apps_clk_src", - .parent_names = gcc_xo_sdcc1_500, - .num_parents = 3, + .parent_data = gcc_xo_sdcc1_500, + .num_parents = ARRAY_SIZE(gcc_xo_sdcc1_500), .ops = &clk_rcg2_ops, .flags = CLK_SET_RATE_PARENT, }, @@ -947,6 +892,20 @@ static const struct freq_tbl ftbl_gcc_apps_clk[] = { { } }; +static struct parent_map gcc_xo_ddr_500_200_map[] = { + { P_XO, 0 }, + { P_FEPLL200, 3 }, + { P_FEPLL500, 2 }, + { P_DDRPLLAPSS, 1 }, +}; + +static const struct clk_parent_data gcc_xo_ddr_500_200[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepll200_clk.cdiv.clkr.hw }, + { .hw = &gcc_fepll500_clk.cdiv.clkr.hw }, + { .hw = &gcc_apss_cpu_plldiv_clk.cdiv.clkr.hw }, +}; + static struct clk_rcg2 apps_clk_src = { .cmd_rcgr = 0x1900c, .hid_width = 5, @@ -954,8 +913,8 @@ static struct clk_rcg2 apps_clk_src = { .parent_map = gcc_xo_ddr_500_200_map, .clkr.hw.init = &(struct clk_init_data){ .name = "apps_clk_src", - .parent_names = gcc_xo_ddr_500_200, - .num_parents = 4, + .parent_data = gcc_xo_ddr_500_200, + .num_parents = ARRAY_SIZE(gcc_xo_ddr_500_200), .ops = &clk_rcg2_ops, .flags = CLK_SET_RATE_PARENT, }, @@ -974,8 +933,8 @@ static struct clk_rcg2 apps_ahb_clk_src = { .freq_tbl = ftbl_gcc_apps_ahb_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "apps_ahb_clk_src", - .parent_names = gcc_xo_200_500, - .num_parents = 3, + .parent_data = gcc_xo_200_500, + .num_parents = ARRAY_SIZE(gcc_xo_200_500), .ops = &clk_rcg2_ops, }, }; @@ -988,9 +947,8 @@ static struct clk_branch gcc_apss_ahb_clk = { .enable_mask = BIT(14), .hw.init = &(struct clk_init_data){ .name = "gcc_apss_ahb_clk", - .parent_names = (const char *[]){ - "apps_ahb_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &apps_ahb_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1006,9 +964,8 @@ static struct clk_branch gcc_blsp1_ahb_clk = { .enable_mask = BIT(10), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1039,9 +996,8 @@ static struct clk_branch gcc_boot_rom_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_boot_rom_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1057,9 +1013,8 @@ static struct clk_branch gcc_crypto_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_crypto_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1074,9 +1029,8 @@ static struct clk_branch gcc_crypto_axi_clk = { .enable_mask = BIT(1), .hw.init = &(struct clk_init_data){ .name = "gcc_crypto_axi_clk", - .parent_names = (const char *[]){ - "fepll125", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll125_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1091,15 +1045,42 @@ static struct clk_branch gcc_crypto_clk = { .enable_mask = BIT(2), .hw.init = &(struct clk_init_data){ .name = "gcc_crypto_clk", - .parent_names = (const char *[]){ - "fepll125", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll125_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, }, }; +static struct parent_map gcc_xo_125_dly_map[] = { + { P_XO, 0 }, + { P_FEPLL125DLY, 1 }, +}; + +static const struct clk_parent_data gcc_xo_125_dly[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepll125dly_clk.cdiv.clkr.hw }, +}; + +static const struct freq_tbl ftbl_gcc_fephy_dly_clk[] = { + F(125000000, P_FEPLL125DLY, 1, 0, 0), + { } +}; + +static struct clk_rcg2 fephy_125m_dly_clk_src = { + .cmd_rcgr = 0x12000, + .hid_width = 5, + .parent_map = gcc_xo_125_dly_map, + .freq_tbl = ftbl_gcc_fephy_dly_clk, + .clkr.hw.init = &(struct clk_init_data){ + .name = "fephy_125m_dly_clk_src", + .parent_data = gcc_xo_125_dly, + .num_parents = ARRAY_SIZE(gcc_xo_125_dly), + .ops = &clk_rcg2_ops, + }, +}; + static struct clk_branch gcc_ess_clk = { .halt_reg = 0x12010, .clkr = { @@ -1107,9 +1088,8 @@ static struct clk_branch gcc_ess_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ess_clk", - .parent_names = (const char *[]){ - "fephy_125m_dly_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &fephy_125m_dly_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1125,9 +1105,8 @@ static struct clk_branch gcc_imem_axi_clk = { .enable_mask = BIT(17), .hw.init = &(struct clk_init_data){ .name = "gcc_imem_axi_clk", - .parent_names = (const char *[]){ - "fepll200", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll200_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1141,9 +1120,8 @@ static struct clk_branch gcc_imem_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_imem_cfg_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1157,9 +1135,8 @@ static struct clk_branch gcc_pcie_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1173,9 +1150,8 @@ static struct clk_branch gcc_pcie_axi_m_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_axi_m_clk", - .parent_names = (const char *[]){ - "fepll200", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll200_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1189,9 +1165,8 @@ static struct clk_branch gcc_pcie_axi_s_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_axi_s_clk", - .parent_names = (const char *[]){ - "fepll200", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll200_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1206,9 +1181,8 @@ static struct clk_branch gcc_prng_ahb_clk = { .enable_mask = BIT(8), .hw.init = &(struct clk_init_data){ .name = "gcc_prng_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1222,9 +1196,8 @@ static struct clk_branch gcc_qpic_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_qpic_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1238,9 +1211,8 @@ static struct clk_branch gcc_qpic_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_qpic_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1254,9 +1226,8 @@ static struct clk_branch gcc_sdcc1_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc1_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1270,9 +1241,8 @@ static struct clk_branch gcc_sdcc1_apps_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc1_apps_clk", - .parent_names = (const char *[]){ - "sdcc1_apps_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &sdcc1_apps_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1288,9 +1258,8 @@ static struct clk_branch gcc_tlmm_ahb_clk = { .enable_mask = BIT(5), .hw.init = &(struct clk_init_data){ .name = "gcc_tlmm_ahb_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1304,9 +1273,8 @@ static struct clk_branch gcc_usb2_master_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb2_master_clk", - .parent_names = (const char *[]){ - "pcnoc_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &pcnoc_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1330,23 +1298,6 @@ static struct clk_branch gcc_usb2_sleep_clk = { }, }; -static struct clk_branch gcc_usb2_mock_utmi_clk = { - .halt_reg = 0x1e014, - .clkr = { - .enable_reg = 0x1e014, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_usb2_mock_utmi_clk", - .parent_names = (const char *[]){ - "usb30_mock_utmi_clk_src", - }, - .num_parents = 1, - .ops = &clk_branch2_ops, - .flags = CLK_SET_RATE_PARENT, - }, - }, -}; - static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk[] = { F(2000000, P_FEPLL200, 10, 0, 0), { } @@ -1359,12 +1310,28 @@ static struct clk_rcg2 usb30_mock_utmi_clk_src = { .freq_tbl = ftbl_gcc_usb30_mock_utmi_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "usb30_mock_utmi_clk_src", - .parent_names = gcc_xo_200, - .num_parents = 2, + .parent_data = gcc_xo_200, + .num_parents = ARRAY_SIZE(gcc_xo_200), .ops = &clk_rcg2_ops, }, }; +static struct clk_branch gcc_usb2_mock_utmi_clk = { + .halt_reg = 0x1e014, + .clkr = { + .enable_reg = 0x1e014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb2_mock_utmi_clk", + .parent_hws = (const struct clk_hw *[]){ + &usb30_mock_utmi_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + }, + }, +}; + static struct clk_branch gcc_usb3_master_clk = { .halt_reg = 0x1e028, .clkr = { @@ -1372,9 +1339,8 @@ static struct clk_branch gcc_usb3_master_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb3_master_clk", - .parent_names = (const char *[]){ - "fepll125", - }, + .parent_hws = (const struct clk_hw *[]){ + &gcc_fepll125_clk.cdiv.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, }, @@ -1405,9 +1371,8 @@ static struct clk_branch gcc_usb3_mock_utmi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb3_mock_utmi_clk", - .parent_names = (const char *[]){ - "usb30_mock_utmi_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &usb30_mock_utmi_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1415,25 +1380,16 @@ static struct clk_branch gcc_usb3_mock_utmi_clk = { }, }; -static const struct freq_tbl ftbl_gcc_fephy_dly_clk[] = { - F(125000000, P_FEPLL125DLY, 1, 0, 0), - { } +static struct parent_map gcc_xo_wcss2g_map[] = { + { P_XO, 0 }, + { P_FEPLLWCSS2G, 1 }, }; -static struct clk_rcg2 fephy_125m_dly_clk_src = { - .cmd_rcgr = 0x12000, - .hid_width = 5, - .parent_map = gcc_xo_125_dly_map, - .freq_tbl = ftbl_gcc_fephy_dly_clk, - .clkr.hw.init = &(struct clk_init_data){ - .name = "fephy_125m_dly_clk_src", - .parent_names = gcc_xo_125_dly, - .num_parents = 2, - .ops = &clk_rcg2_ops, - }, +static const struct clk_parent_data gcc_xo_wcss2g[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepllwcss2g_clk.cdiv.clkr.hw }, }; - static const struct freq_tbl ftbl_gcc_wcss2g_clk[] = { F(48000000, P_XO, 1, 0, 0), F(250000000, P_FEPLLWCSS2G, 1, 0, 0), @@ -1447,8 +1403,8 @@ static struct clk_rcg2 wcss2g_clk_src = { .parent_map = gcc_xo_wcss2g_map, .clkr.hw.init = &(struct clk_init_data){ .name = "wcss2g_clk_src", - .parent_names = gcc_xo_wcss2g, - .num_parents = 2, + .parent_data = gcc_xo_wcss2g, + .num_parents = ARRAY_SIZE(gcc_xo_wcss2g), .ops = &clk_rcg2_ops, .flags = CLK_SET_RATE_PARENT, }, @@ -1461,9 +1417,8 @@ static struct clk_branch gcc_wcss2g_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss2g_clk", - .parent_names = (const char *[]){ - "wcss2g_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &wcss2g_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, @@ -1506,6 +1461,16 @@ static struct clk_branch gcc_wcss2g_rtc_clk = { }, }; +static struct parent_map gcc_xo_wcss5g_map[] = { + { P_XO, 0 }, + { P_FEPLLWCSS5G, 1 }, +}; + +static const struct clk_parent_data gcc_xo_wcss5g[] = { + { .fw_name = "xo", .name = "xo" }, + { .hw = &gcc_fepllwcss5g_clk.cdiv.clkr.hw }, +}; + static const struct freq_tbl ftbl_gcc_wcss5g_clk[] = { F(48000000, P_XO, 1, 0, 0), F(250000000, P_FEPLLWCSS5G, 1, 0, 0), @@ -1519,8 +1484,8 @@ static struct clk_rcg2 wcss5g_clk_src = { .freq_tbl = ftbl_gcc_wcss5g_clk, .clkr.hw.init = &(struct clk_init_data){ .name = "wcss5g_clk_src", - .parent_names = gcc_xo_wcss5g, - .num_parents = 2, + .parent_data = gcc_xo_wcss5g, + .num_parents = ARRAY_SIZE(gcc_xo_wcss5g), .ops = &clk_rcg2_ops, }, }; @@ -1532,9 +1497,8 @@ static struct clk_branch gcc_wcss5g_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_wcss5g_clk", - .parent_names = (const char *[]){ - "wcss5g_clk_src", - }, + .parent_hws = (const struct clk_hw *[]){ + &wcss5g_clk_src.clkr.hw }, .num_parents = 1, .ops = &clk_branch2_ops, .flags = CLK_SET_RATE_PARENT, -- GitLab From b73a0b80c69de77d8d4942abb37066531c0169b2 Mon Sep 17 00:00:00 2001 From: Natalia Petrova Date: Fri, 3 Mar 2023 15:44:08 +0300 Subject: [PATCH 0427/5631] RDMA/rdmavt: Delete unnecessary NULL check There is no need to check 'rdi->qp_dev' for NULL. The field 'qp_dev' is created in rvt_register_device() which will fail if the 'qp_dev' allocation fails in rvt_driver_qp_init(). Overwise this pointer doesn't changed and passed to rvt_qp_exit() by the next step. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 0acb0cc7ecc1 ("IB/rdmavt: Initialize and teardown of qpn table") Signed-off-by: Natalia Petrova Link: https://lore.kernel.org/r/20230303124408.16685-1-n.petrova@fintech.ru Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rdmavt/qp.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 3f707e1fa517..2d143a9d2027 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -464,8 +464,6 @@ void rvt_qp_exit(struct rvt_dev_info *rdi) if (qps_inuse) rvt_pr_err(rdi, "QP memory leak! %u still in use\n", qps_inuse); - if (!rdi->qp_dev) - return; kfree(rdi->qp_dev->qp_table); free_qpn_table(&rdi->qp_dev->qpn_table); -- GitLab From faa63656fc361e78ebccb288c0be638a6a4ffe35 Mon Sep 17 00:00:00 2001 From: Yixing Liu Date: Sat, 4 Mar 2023 17:15:54 +0800 Subject: [PATCH 0428/5631] RDMA/hns: Add new command to support query vf caps The current resource query for vf caps is driven by the driver, which is unreasonable. This patch adds a new command HNS_ROCE_OPC_QUERY_VF_CAPS_NUM to support obtaining vf caps information from firmware. Signed-off-by: Yixing Liu Signed-off-by: Haoyue Xu Link: https://lore.kernel.org/r/20230304091555.2241298-2-xuhaoyue1@hisilicon.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 189 ++++++--------------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 31 +--- 2 files changed, 56 insertions(+), 164 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index dbf97fe5948f..84f1167de1d9 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1960,100 +1960,6 @@ static int hns_roce_v2_set_bt(struct hns_roce_dev *hr_dev) return hns_roce_cmq_send(hr_dev, &desc, 1); } -/* Use default caps when hns_roce_query_pf_caps() failed or init VF profile */ -static void set_default_caps(struct hns_roce_dev *hr_dev) -{ - struct hns_roce_caps *caps = &hr_dev->caps; - - caps->num_qps = HNS_ROCE_V2_MAX_QP_NUM; - caps->max_wqes = HNS_ROCE_V2_MAX_WQE_NUM; - caps->num_cqs = HNS_ROCE_V2_MAX_CQ_NUM; - caps->num_srqs = HNS_ROCE_V2_MAX_SRQ_NUM; - caps->min_cqes = HNS_ROCE_MIN_CQE_NUM; - caps->max_cqes = HNS_ROCE_V2_MAX_CQE_NUM; - caps->max_sq_sg = HNS_ROCE_V2_MAX_SQ_SGE_NUM; - caps->max_rq_sg = HNS_ROCE_V2_MAX_RQ_SGE_NUM; - - caps->num_uars = HNS_ROCE_V2_UAR_NUM; - caps->phy_num_uars = HNS_ROCE_V2_PHY_UAR_NUM; - caps->num_aeq_vectors = HNS_ROCE_V2_AEQE_VEC_NUM; - caps->num_other_vectors = HNS_ROCE_V2_ABNORMAL_VEC_NUM; - caps->num_comp_vectors = 0; - - caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM; - caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; - caps->qpc_timer_bt_num = HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM; - caps->cqc_timer_bt_num = HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM; - - caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; - caps->max_qp_dest_rdma = HNS_ROCE_V2_MAX_QP_DEST_RDMA; - caps->max_sq_desc_sz = HNS_ROCE_V2_MAX_SQ_DESC_SZ; - caps->max_rq_desc_sz = HNS_ROCE_V2_MAX_RQ_DESC_SZ; - caps->irrl_entry_sz = HNS_ROCE_V2_IRRL_ENTRY_SZ; - caps->trrl_entry_sz = HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ; - caps->cqc_entry_sz = HNS_ROCE_V2_CQC_ENTRY_SZ; - caps->srqc_entry_sz = HNS_ROCE_V2_SRQC_ENTRY_SZ; - caps->mtpt_entry_sz = HNS_ROCE_V2_MTPT_ENTRY_SZ; - caps->idx_entry_sz = HNS_ROCE_V2_IDX_ENTRY_SZ; - caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; - caps->reserved_lkey = 0; - caps->reserved_pds = 0; - caps->reserved_mrws = 1; - caps->reserved_uars = 0; - caps->reserved_cqs = 0; - caps->reserved_srqs = 0; - caps->reserved_qps = HNS_ROCE_V2_RSV_QPS; - - caps->qpc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->srqc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->cqc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->mpt_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->sccc_hop_num = HNS_ROCE_SCCC_HOP_NUM; - - caps->mtt_hop_num = HNS_ROCE_MTT_HOP_NUM; - caps->wqe_sq_hop_num = HNS_ROCE_SQWQE_HOP_NUM; - caps->wqe_sge_hop_num = HNS_ROCE_EXT_SGE_HOP_NUM; - caps->wqe_rq_hop_num = HNS_ROCE_RQWQE_HOP_NUM; - caps->cqe_hop_num = HNS_ROCE_CQE_HOP_NUM; - caps->srqwqe_hop_num = HNS_ROCE_SRQWQE_HOP_NUM; - caps->idx_hop_num = HNS_ROCE_IDX_HOP_NUM; - caps->chunk_sz = HNS_ROCE_V2_TABLE_CHUNK_SIZE; - - caps->flags = HNS_ROCE_CAP_FLAG_REREG_MR | - HNS_ROCE_CAP_FLAG_ROCE_V1_V2 | - HNS_ROCE_CAP_FLAG_CQ_RECORD_DB | - HNS_ROCE_CAP_FLAG_QP_RECORD_DB; - - caps->pkey_table_len[0] = 1; - caps->ceqe_depth = HNS_ROCE_V2_COMP_EQE_NUM; - caps->aeqe_depth = HNS_ROCE_V2_ASYNC_EQE_NUM; - caps->local_ca_ack_delay = 0; - caps->max_mtu = IB_MTU_4096; - - caps->max_srq_wrs = HNS_ROCE_V2_MAX_SRQ_WR; - caps->max_srq_sges = HNS_ROCE_V2_MAX_SRQ_SGE; - - caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC | HNS_ROCE_CAP_FLAG_MW | - HNS_ROCE_CAP_FLAG_SRQ | HNS_ROCE_CAP_FLAG_FRMR | - HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL; - - caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM; - - if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) { - caps->flags |= HNS_ROCE_CAP_FLAG_STASH | - HNS_ROCE_CAP_FLAG_DIRECT_WQE | - HNS_ROCE_CAP_FLAG_XRC; - caps->max_sq_inline = HNS_ROCE_V3_MAX_SQ_INLINE; - } else { - caps->max_sq_inline = HNS_ROCE_V2_MAX_SQ_INLINE; - - /* The following configuration are only valid for HIP08 */ - caps->qpc_sz = HNS_ROCE_V2_QPC_SZ; - caps->sccc_sz = HNS_ROCE_V2_SCCC_SZ; - caps->cqe_sz = HNS_ROCE_V2_CQE_SIZE; - } -} - static void calc_pg_sz(u32 obj_num, u32 obj_size, u32 hop_num, u32 ctx_bt_num, u32 *buf_page_size, u32 *bt_page_size, u32 hem_type) { @@ -2239,7 +2145,7 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev) set_hem_page_size(hr_dev); } -static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) +static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) { struct hns_roce_cmq_desc desc[HNS_ROCE_QUERY_PF_CAPS_CMD_NUM]; struct hns_roce_caps *caps = &hr_dev->caps; @@ -2248,15 +2154,17 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) struct hns_roce_query_pf_caps_c *resp_c; struct hns_roce_query_pf_caps_d *resp_d; struct hns_roce_query_pf_caps_e *resp_e; + enum hns_roce_opcode_type cmd; int ctx_hop_num; int pbl_hop_num; int ret; int i; + cmd = hr_dev->is_vf ? HNS_ROCE_OPC_QUERY_VF_CAPS_NUM : + HNS_ROCE_OPC_QUERY_PF_CAPS_NUM; + for (i = 0; i < HNS_ROCE_QUERY_PF_CAPS_CMD_NUM; i++) { - hns_roce_cmq_setup_basic_desc(&desc[i], - HNS_ROCE_OPC_QUERY_PF_CAPS_NUM, - true); + hns_roce_cmq_setup_basic_desc(&desc[i], cmd, true); if (i < (HNS_ROCE_QUERY_PF_CAPS_CMD_NUM - 1)) desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); else @@ -2273,35 +2181,33 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) resp_d = (struct hns_roce_query_pf_caps_d *)desc[3].data; resp_e = (struct hns_roce_query_pf_caps_e *)desc[4].data; - caps->local_ca_ack_delay = resp_a->local_ca_ack_delay; - caps->max_sq_sg = le16_to_cpu(resp_a->max_sq_sg); - caps->max_sq_inline = le16_to_cpu(resp_a->max_sq_inline); - caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); + caps->local_ca_ack_delay = resp_a->local_ca_ack_delay; + caps->max_sq_sg = le16_to_cpu(resp_a->max_sq_sg); + caps->max_sq_inline = le16_to_cpu(resp_a->max_sq_inline); + caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg); - caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); + caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges); - caps->num_aeq_vectors = resp_a->num_aeq_vectors; - caps->num_other_vectors = resp_a->num_other_vectors; - caps->max_sq_desc_sz = resp_a->max_sq_desc_sz; - caps->max_rq_desc_sz = resp_a->max_rq_desc_sz; - caps->cqe_sz = resp_a->cqe_sz; - - caps->mtpt_entry_sz = resp_b->mtpt_entry_sz; - caps->irrl_entry_sz = resp_b->irrl_entry_sz; - caps->trrl_entry_sz = resp_b->trrl_entry_sz; - caps->cqc_entry_sz = resp_b->cqc_entry_sz; - caps->srqc_entry_sz = resp_b->srqc_entry_sz; - caps->idx_entry_sz = resp_b->idx_entry_sz; - caps->sccc_sz = resp_b->sccc_sz; - caps->max_mtu = resp_b->max_mtu; - caps->qpc_sz = le16_to_cpu(resp_b->qpc_sz); - caps->min_cqes = resp_b->min_cqes; - caps->min_wqes = resp_b->min_wqes; - caps->page_size_cap = le32_to_cpu(resp_b->page_size_cap); - caps->pkey_table_len[0] = resp_b->pkey_table_len; - caps->phy_num_uars = resp_b->phy_num_uars; - ctx_hop_num = resp_b->ctx_hop_num; - pbl_hop_num = resp_b->pbl_hop_num; + caps->num_aeq_vectors = resp_a->num_aeq_vectors; + caps->num_other_vectors = resp_a->num_other_vectors; + caps->max_sq_desc_sz = resp_a->max_sq_desc_sz; + caps->max_rq_desc_sz = resp_a->max_rq_desc_sz; + + caps->mtpt_entry_sz = resp_b->mtpt_entry_sz; + caps->irrl_entry_sz = resp_b->irrl_entry_sz; + caps->trrl_entry_sz = resp_b->trrl_entry_sz; + caps->cqc_entry_sz = resp_b->cqc_entry_sz; + caps->srqc_entry_sz = resp_b->srqc_entry_sz; + caps->idx_entry_sz = resp_b->idx_entry_sz; + caps->sccc_sz = resp_b->sccc_sz; + caps->max_mtu = resp_b->max_mtu; + caps->min_cqes = resp_b->min_cqes; + caps->min_wqes = resp_b->min_wqes; + caps->page_size_cap = le32_to_cpu(resp_b->page_size_cap); + caps->pkey_table_len[0] = resp_b->pkey_table_len; + caps->phy_num_uars = resp_b->phy_num_uars; + ctx_hop_num = resp_b->ctx_hop_num; + pbl_hop_num = resp_b->pbl_hop_num; caps->num_pds = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_PDS); @@ -2324,8 +2230,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->ceqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_CEQ_DEPTH); caps->num_comp_vectors = hr_reg_read(resp_d, PF_CAPS_D_NUM_CEQS); caps->aeqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_AEQ_DEPTH); - caps->default_aeq_arm_st = hr_reg_read(resp_d, PF_CAPS_D_AEQ_ARM_ST); - caps->default_ceq_arm_st = hr_reg_read(resp_d, PF_CAPS_D_CEQ_ARM_ST); caps->reserved_pds = hr_reg_read(resp_d, PF_CAPS_D_RSV_PDS); caps->num_uars = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_UARS); caps->reserved_qps = hr_reg_read(resp_d, PF_CAPS_D_RSV_QPS); @@ -2336,10 +2240,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->reserved_cqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_CQS); caps->reserved_srqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_SRQS); caps->reserved_lkey = hr_reg_read(resp_e, PF_CAPS_E_RSV_LKEYS); - caps->default_ceq_max_cnt = le16_to_cpu(resp_e->ceq_max_cnt); - caps->default_ceq_period = le16_to_cpu(resp_e->ceq_period); - caps->default_aeq_max_cnt = le16_to_cpu(resp_e->aeq_max_cnt); - caps->default_aeq_period = le16_to_cpu(resp_e->aeq_period); caps->qpc_hop_num = ctx_hop_num; caps->sccc_hop_num = ctx_hop_num; @@ -2357,6 +2257,19 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) if (!(caps->page_size_cap & PAGE_SIZE)) caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; + if (!hr_dev->is_vf) { + caps->cqe_sz = resp_a->cqe_sz; + caps->qpc_sz = le16_to_cpu(resp_b->qpc_sz); + caps->default_aeq_arm_st = + hr_reg_read(resp_d, PF_CAPS_D_AEQ_ARM_ST); + caps->default_ceq_arm_st = + hr_reg_read(resp_d, PF_CAPS_D_CEQ_ARM_ST); + caps->default_ceq_max_cnt = le16_to_cpu(resp_e->ceq_max_cnt); + caps->default_ceq_period = le16_to_cpu(resp_e->ceq_period); + caps->default_aeq_max_cnt = le16_to_cpu(resp_e->aeq_max_cnt); + caps->default_aeq_period = le16_to_cpu(resp_e->aeq_period); + } + return 0; } @@ -2404,7 +2317,11 @@ static int hns_roce_v2_vf_profile(struct hns_roce_dev *hr_dev) hr_dev->func_num = 1; - set_default_caps(hr_dev); + ret = hns_roce_query_caps(hr_dev); + if (ret) { + dev_err(dev, "failed to query VF caps, ret = %d.\n", ret); + return ret; + } ret = hns_roce_query_vf_resource(hr_dev); if (ret) { @@ -2444,9 +2361,11 @@ static int hns_roce_v2_pf_profile(struct hns_roce_dev *hr_dev) return ret; } - ret = hns_roce_query_pf_caps(hr_dev); - if (ret) - set_default_caps(hr_dev); + ret = hns_roce_query_caps(hr_dev); + if (ret) { + dev_err(dev, "failed to query PF caps, ret = %d.\n", ret); + return ret; + } ret = hns_roce_query_pf_resource(hr_dev); if (ret) { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index af9d00225cdf..1b44d2434ab4 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -35,43 +35,15 @@ #include -#define HNS_ROCE_V2_MAX_QP_NUM 0x1000 -#define HNS_ROCE_V2_MAX_WQE_NUM 0x8000 -#define HNS_ROCE_V2_MAX_SRQ_WR 0x8000 -#define HNS_ROCE_V2_MAX_SRQ_SGE 64 -#define HNS_ROCE_V2_MAX_CQ_NUM 0x100000 -#define HNS_ROCE_V2_MAX_QPC_TIMER_BT_NUM 0x100 -#define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM 0x100 -#define HNS_ROCE_V2_MAX_SRQ_NUM 0x100000 -#define HNS_ROCE_V2_MAX_CQE_NUM 0x400000 -#define HNS_ROCE_V2_MAX_RQ_SGE_NUM 64 -#define HNS_ROCE_V2_MAX_SQ_SGE_NUM 64 -#define HNS_ROCE_V2_MAX_SQ_INLINE 0x20 -#define HNS_ROCE_V3_MAX_SQ_INLINE 0x400 #define HNS_ROCE_V2_MAX_RC_INL_INN_SZ 32 -#define HNS_ROCE_V2_UAR_NUM 256 -#define HNS_ROCE_V2_PHY_UAR_NUM 1 +#define HNS_ROCE_V2_MTT_ENTRY_SZ 64 #define HNS_ROCE_V2_AEQE_VEC_NUM 1 #define HNS_ROCE_V2_ABNORMAL_VEC_NUM 1 -#define HNS_ROCE_V2_MAX_MTPT_NUM 0x100000 #define HNS_ROCE_V2_MAX_SRQWQE_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_IDX_SEGS 0x1000000 -#define HNS_ROCE_V2_MAX_PD_NUM 0x1000000 #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 -#define HNS_ROCE_V2_MAX_QP_INIT_RDMA 128 -#define HNS_ROCE_V2_MAX_QP_DEST_RDMA 128 -#define HNS_ROCE_V2_MAX_SQ_DESC_SZ 64 -#define HNS_ROCE_V2_MAX_RQ_DESC_SZ 16 -#define HNS_ROCE_V2_IRRL_ENTRY_SZ 64 -#define HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ 100 -#define HNS_ROCE_V2_CQC_ENTRY_SZ 64 -#define HNS_ROCE_V2_SRQC_ENTRY_SZ 64 -#define HNS_ROCE_V2_MTPT_ENTRY_SZ 64 -#define HNS_ROCE_V2_MTT_ENTRY_SZ 64 -#define HNS_ROCE_V2_IDX_ENTRY_SZ 4 -#define HNS_ROCE_V2_SCCC_SZ 32 #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 @@ -232,6 +204,7 @@ enum hns_roce_opcode_type { HNS_ROCE_OPC_QUERY_FUNC_INFO = 0x8407, HNS_ROCE_OPC_QUERY_PF_CAPS_NUM = 0x8408, HNS_ROCE_OPC_CFG_ENTRY_SIZE = 0x8409, + HNS_ROCE_OPC_QUERY_VF_CAPS_NUM = 0x8410, HNS_ROCE_OPC_CFG_SGID_TB = 0x8500, HNS_ROCE_OPC_CFG_SMAC_TB = 0x8501, HNS_ROCE_OPC_POST_MB = 0x8504, -- GitLab From 56d5229471ee1634bd0eb029f1aa82a8d87c6fed Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 15 Jan 2023 17:01:13 -0800 Subject: [PATCH 0429/5631] tools build: Pass libbpf feature only if libbpf 1.0+ libbpf 1.0 represented a cleanup and stabilization of APIs. Simplify development by only passing the feature test if libbpf 1.0 is installed. Committer notes: Change 'make -C tools/perf build-test' so that the LIBBPF_DYNAMIC=1 test runs only if libbpf is >= 1.0. Signed-off-by: Ian Rogers Tested-by: Jiri Olsa Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Andrii Nakryiko Cc: Christy Lee Cc: Ingo Molnar Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230116010115.490713-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/feature/test-libbpf.c | 4 ++++ tools/perf/tests/make | 7 ++++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/build/feature/test-libbpf.c b/tools/build/feature/test-libbpf.c index a508756cf4cc..cd9989f52119 100644 --- a/tools/build/feature/test-libbpf.c +++ b/tools/build/feature/test-libbpf.c @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include +#if !defined(LIBBPF_MAJOR_VERSION) || (LIBBPF_MAJOR_VERSION < 1) +#error At least libbpf 1.0 is required for Linux tools. +#endif + int main(void) { return bpf_object__open("test") ? 0 : -1; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 009d6efb673c..b4d64fdf4aef 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -150,7 +150,6 @@ run += make_no_libaudit run += make_no_libbionic run += make_no_auxtrace run += make_no_libbpf -run += make_libbpf_dynamic run += make_no_libbpf_DEBUG run += make_no_libcrypto run += make_no_sdt @@ -176,6 +175,12 @@ run += make_install_prefix_slash # run += make_install_pdf run += make_minimal +old_libbpf := $(shell echo "#include " | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}") + +ifneq ($(old_libbpf),) +run += make_libbpf_dynamic +endif + ifneq ($(call has,ctags),) run += make_tags endif -- GitLab From 76a97cf2e169851ff8e3fd9d27028168eff81e37 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 15 Jan 2023 17:01:14 -0800 Subject: [PATCH 0430/5631] perf build: Remove libbpf pre-1.0 feature tests The feature tests were necessary for libbpf pre-1.0, but as the libbpf implies at least 1.0 we can remove these now. Committer notes: Modified tools/perf/Makefile.config to better reflect the reason for failure when the libbpf present is < 1.0 and LIBBPF_DYNAMIC=1 was asked for. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Tested-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Andrii Nakryiko Cc: Christy Lee Cc: Ingo Molnar Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230116010115.490713-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/feature/Makefile | 7 --- .../feature/test-libbpf-bpf_map_create.c | 8 --- .../test-libbpf-bpf_object__next_map.c | 8 --- .../test-libbpf-bpf_object__next_program.c | 8 --- .../build/feature/test-libbpf-bpf_prog_load.c | 9 ---- .../test-libbpf-bpf_program__set_insns.c | 8 --- .../test-libbpf-btf__load_from_kernel_by_id.c | 8 --- .../build/feature/test-libbpf-btf__raw_data.c | 8 --- tools/perf/Makefile.config | 50 ++++--------------- 9 files changed, 11 insertions(+), 103 deletions(-) delete mode 100644 tools/build/feature/test-libbpf-bpf_map_create.c delete mode 100644 tools/build/feature/test-libbpf-bpf_object__next_map.c delete mode 100644 tools/build/feature/test-libbpf-bpf_object__next_program.c delete mode 100644 tools/build/feature/test-libbpf-bpf_prog_load.c delete mode 100644 tools/build/feature/test-libbpf-bpf_program__set_insns.c delete mode 100644 tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c delete mode 100644 tools/build/feature/test-libbpf-btf__raw_data.c diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 690fe97be190..dc9323e01e42 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -58,13 +58,6 @@ FILES= \ test-lzma.bin \ test-bpf.bin \ test-libbpf.bin \ - test-libbpf-btf__load_from_kernel_by_id.bin \ - test-libbpf-bpf_prog_load.bin \ - test-libbpf-bpf_map_create.bin \ - test-libbpf-bpf_object__next_program.bin \ - test-libbpf-bpf_object__next_map.bin \ - test-libbpf-bpf_program__set_insns.bin \ - test-libbpf-btf__raw_data.bin \ test-get_cpuid.bin \ test-sdt.bin \ test-cxx.bin \ diff --git a/tools/build/feature/test-libbpf-bpf_map_create.c b/tools/build/feature/test-libbpf-bpf_map_create.c deleted file mode 100644 index b9f550e332c8..000000000000 --- a/tools/build/feature/test-libbpf-bpf_map_create.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - return bpf_map_create(0 /* map_type */, NULL /* map_name */, 0, /* key_size */, - 0 /* value_size */, 0 /* max_entries */, NULL /* opts */); -} diff --git a/tools/build/feature/test-libbpf-bpf_object__next_map.c b/tools/build/feature/test-libbpf-bpf_object__next_map.c deleted file mode 100644 index 64adb519e97e..000000000000 --- a/tools/build/feature/test-libbpf-bpf_object__next_map.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - bpf_object__next_map(NULL /* obj */, NULL /* prev */); - return 0; -} diff --git a/tools/build/feature/test-libbpf-bpf_object__next_program.c b/tools/build/feature/test-libbpf-bpf_object__next_program.c deleted file mode 100644 index 8bf4fd26b545..000000000000 --- a/tools/build/feature/test-libbpf-bpf_object__next_program.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - bpf_object__next_program(NULL /* obj */, NULL /* prev */); - return 0; -} diff --git a/tools/build/feature/test-libbpf-bpf_prog_load.c b/tools/build/feature/test-libbpf-bpf_prog_load.c deleted file mode 100644 index 47f516d63ebc..000000000000 --- a/tools/build/feature/test-libbpf-bpf_prog_load.c +++ /dev/null @@ -1,9 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - return bpf_prog_load(0 /* prog_type */, NULL /* prog_name */, - NULL /* license */, NULL /* insns */, - 0 /* insn_cnt */, NULL /* opts */); -} diff --git a/tools/build/feature/test-libbpf-bpf_program__set_insns.c b/tools/build/feature/test-libbpf-bpf_program__set_insns.c deleted file mode 100644 index f3b7f18c8f49..000000000000 --- a/tools/build/feature/test-libbpf-bpf_program__set_insns.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - bpf_program__set_insns(NULL /* prog */, NULL /* new_insns */, 0 /* new_insn_cnt */); - return 0; -} diff --git a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c deleted file mode 100644 index a17647f7d5a4..000000000000 --- a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - btf__load_from_kernel_by_id(20151128); - return 0; -} diff --git a/tools/build/feature/test-libbpf-btf__raw_data.c b/tools/build/feature/test-libbpf-btf__raw_data.c deleted file mode 100644 index 57da31dd7581..000000000000 --- a/tools/build/feature/test-libbpf-btf__raw_data.c +++ /dev/null @@ -1,8 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -int main(void) -{ - btf__raw_data(NULL /* btf_ro */, NULL /* size */); - return 0; -} diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3519a0139026..b715cd4f43f4 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -565,54 +565,26 @@ ifndef NO_LIBELF # detecting libbpf without LIBBPF_DYNAMIC, so make VF=1 shows libbpf detection status $(call feature_check,libbpf) + + # Feature test requires libbpf 1.0 so we can assume the following: + CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID + CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD + CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM + CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP + CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS + CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA + CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE + ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf $(call detected,CONFIG_LIBBPF_DYNAMIC) - - $(call feature_check,libbpf-btf__load_from_kernel_by_id) - ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1) - CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID - endif - $(call feature_check,libbpf-bpf_prog_load) - ifeq ($(feature-libbpf-bpf_prog_load), 1) - CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD - endif - $(call feature_check,libbpf-bpf_object__next_program) - ifeq ($(feature-libbpf-bpf_object__next_program), 1) - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM - endif - $(call feature_check,libbpf-bpf_object__next_map) - ifeq ($(feature-libbpf-bpf_object__next_map), 1) - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP - endif - $(call feature_check,libbpf-bpf_program__set_insns) - ifeq ($(feature-libbpf-bpf_program__set_insns), 1) - CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS - else - dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources); - endif - $(call feature_check,libbpf-btf__raw_data) - ifeq ($(feature-libbpf-btf__raw_data), 1) - CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA - endif - $(call feature_check,libbpf-bpf_map_create) - ifeq ($(feature-libbpf-bpf_map_create), 1) - CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE - endif else - dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); + dummy := $(error Error: No libbpf devel library found or older than v1.0, please install/update libbpf-devel); endif else # Libbpf will be built as a static library from tools/lib/bpf. LIBBPF_STATIC := 1 - CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID - CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP - CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS - CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA - CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE endif endif -- GitLab From 6bebc06d544ddf7d4ca17ac3a1b94f4728a3cb7f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 15 Jan 2023 17:01:15 -0800 Subject: [PATCH 0431/5631] perf bpf: Remove pre libbpf 1.0 conditional logic Tests are no longer applicable as libbpf 1.0 can be assumed. Signed-off-by: Ian Rogers Acked/Tested-by: Jiri Olsa Acked/Tested-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Andrii Nakryiko Cc: Christy Lee Cc: Ingo Molnar Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230116010115.490713-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 9 ----- tools/perf/util/bpf-event.c | 66 ----------------------------------- tools/perf/util/bpf-loader.c | 18 ---------- tools/perf/util/bpf_counter.c | 18 ---------- 4 files changed, 111 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index b715cd4f43f4..51a4e26bd030 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -566,15 +566,6 @@ ifndef NO_LIBELF # detecting libbpf without LIBBPF_DYNAMIC, so make VF=1 shows libbpf detection status $(call feature_check,libbpf) - # Feature test requires libbpf 1.0 so we can assume the following: - CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID - CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM - CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP - CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS - CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA - CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE - ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index cc7c1f90cf62..025f331b3867 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -22,72 +22,6 @@ #include "record.h" #include "util/synthetic-events.h" -#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID -struct btf *btf__load_from_kernel_by_id(__u32 id) -{ - struct btf *btf; -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - int err = btf__get_from_id(id, &btf); -#pragma GCC diagnostic pop - - return err ? ERR_PTR(err) : btf; -} -#endif - -#ifndef HAVE_LIBBPF_BPF_PROG_LOAD -LIBBPF_API int bpf_load_program(enum bpf_prog_type type, - const struct bpf_insn *insns, size_t insns_cnt, - const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz); - -int bpf_prog_load(enum bpf_prog_type prog_type, - const char *prog_name __maybe_unused, - const char *license, - const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts) -{ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - return bpf_load_program(prog_type, insns, insn_cnt, license, - opts->kern_version, opts->log_buf, opts->log_size); -#pragma GCC diagnostic pop -} -#endif - -#ifndef HAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM -struct bpf_program * -bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) -{ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - return bpf_program__next(prev, obj); -#pragma GCC diagnostic pop -} -#endif - -#ifndef HAVE_LIBBPF_BPF_OBJECT__NEXT_MAP -struct bpf_map * -bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) -{ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - return bpf_map__next(prev, obj); -#pragma GCC diagnostic pop -} -#endif - -#ifndef HAVE_LIBBPF_BTF__RAW_DATA -const void * -btf__raw_data(const struct btf *btf_ro, __u32 *size) -{ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - return btf__get_raw_data(btf_ro, size); -#pragma GCC diagnostic pop -} -#endif - static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len) { int ret = 0; diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 6e9b06cf06ee..44cde27d6389 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -32,24 +32,6 @@ #include -#ifndef HAVE_LIBBPF_BPF_PROGRAM__SET_INSNS -int bpf_program__set_insns(struct bpf_program *prog __maybe_unused, - struct bpf_insn *new_insns __maybe_unused, size_t new_insn_cnt __maybe_unused) -{ - pr_err("%s: not support, update libbpf\n", __func__); - return -ENOTSUP; -} - -int libbpf_register_prog_handler(const char *sec __maybe_unused, - enum bpf_prog_type prog_type __maybe_unused, - enum bpf_attach_type exp_attach_type __maybe_unused, - const struct libbpf_prog_handler_opts *opts __maybe_unused) -{ - pr_err("%s: not support, update libbpf\n", __func__); - return -ENOTSUP; -} -#endif - /* temporarily disable libbpf deprecation warnings */ #pragma GCC diagnostic ignored "-Wdeprecated-declarations" diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index eeee899fcf34..aa78a15a6f0a 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -312,24 +312,6 @@ static bool bperf_attr_map_compatible(int attr_map_fd) (map_info.value_size == sizeof(struct perf_event_attr_map_entry)); } -#ifndef HAVE_LIBBPF_BPF_MAP_CREATE -LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags); -int -bpf_map_create(enum bpf_map_type map_type, - const char *map_name __maybe_unused, - __u32 key_size, - __u32 value_size, - __u32 max_entries, - const struct bpf_map_create_opts *opts __maybe_unused) -{ -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - return bpf_create_map(map_type, key_size, value_size, max_entries, 0); -#pragma GCC diagnostic pop -} -#endif - static int bperf_lock_attr_map(struct target *target) { char path[PATH_MAX]; -- GitLab From 7a9b223ca0761a7c7c72e569b86b84a907aa0f92 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:41 -0800 Subject: [PATCH 0432/5631] perf build: Support python/perf.so testing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a build target to echo the python/perf.so's name from Makefile.perf. Use it in tests/make so the correct target is built and tested for. Fixes: caec54705adb73b0 ("perf build: Fix python/perf.so library's name") Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 7 +++++-- tools/perf/tests/make | 5 +++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index bac9272682b7..2fcee585b225 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -647,13 +647,16 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS) # Create python binding output directory if not already present _dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python') -$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBPERF) +$(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX): $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBPERF) $(LIBSUBCMD) $(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \ CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS)' \ $(PYTHON_WORD) util/setup.py \ --quiet build_ext; \ cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/ +python_perf_target: + @echo "Target is: $(OUTPUT)python/perf$(PYTHON_EXTENSION_SUFFIX)" + please_set_SHELL_PATH_to_a_more_modern_shell: $(Q)$$(:) @@ -1152,7 +1155,7 @@ FORCE: .PHONY: all install clean config-clean strip install-gtk .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell .PHONY: .FORCE-PERF-VERSION-FILE TAGS tags cscope FORCE prepare -.PHONY: archheaders +.PHONY: archheaders python_perf_target endif # force_fixdep diff --git a/tools/perf/tests/make b/tools/perf/tests/make index b4d64fdf4aef..f9f826c0df47 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -62,10 +62,11 @@ lib = lib endif has = $(shell which $1 2>/dev/null) +python_perf_so := $(shell $(MAKE) python_perf_target|grep "Target is:"|awk '{print $$3}') # standard single make variable specified make_clean_all := clean all -make_python_perf_so := python/perf.so +make_python_perf_so := $(python_perf_so) make_debug := DEBUG=1 make_no_libperl := NO_LIBPERL=1 make_no_libpython := NO_LIBPYTHON=1 @@ -209,7 +210,7 @@ test_make_doc := $(test_ok) test_make_help_O := $(test_ok) test_make_doc_O := $(test_ok) -test_make_python_perf_so := test -f $(PERF_O)/python/perf.so +test_make_python_perf_so := test -f $(PERF_O)/$(python_perf_so) test_make_perf_o := test -f $(PERF_O)/perf.o test_make_util_map_o := test -f $(PERF_O)/util/map.o -- GitLab From a980755beb5aca9002e1c95ba519b83a44242b5b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:42 -0800 Subject: [PATCH 0433/5631] perf build: Make BUILD_BPF_SKEL default, rename to NO_BPF_SKEL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BPF skeleton support is now key to a number of perf features. Rather than making it so that BPF support must be enabled for the build, make this the default and error if the build lacks a clang and libbpf that are sufficient. To avoid the error and build without BPF skeletons the NO_BPF_SKEL=1 flag can be used. Add a build-options flag to 'perf version' to enable detection of the BPF skeleton support and use this in the offcpu shell test. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 19 ++++++++++++------- tools/perf/Makefile.perf | 8 ++++---- tools/perf/builtin-lock.c | 2 +- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-version.c | 1 + tools/perf/tests/shell/record_offcpu.sh | 2 +- 6 files changed, 20 insertions(+), 14 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 51a4e26bd030..318af7657225 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -415,6 +415,7 @@ ifdef NO_LIBELF NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 + NO_BPF_SKEL := 1 NO_JVMTI := 1 else ifeq ($(feature-libelf), 0) @@ -662,18 +663,22 @@ ifndef NO_LIBBPF msg := $(warning BPF API too old. Please install recent kernel headers. BPF support in 'perf record' is disabled.) NO_LIBBPF := 1 endif +else + NO_BPF_SKEL := 1 endif -ifdef BUILD_BPF_SKEL +ifndef NO_BPF_SKEL $(call feature_check,clang-bpf-co-re) ifeq ($(feature-clang-bpf-co-re), 0) - dummy := $(error Error: clang too old/not installed. Please install recent clang to build with BUILD_BPF_SKEL) - endif - ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(error Error: BPF skeleton support requires libbpf) + dummy := $(error: ERROR: BPF skeletons unsupported. clang too old/not installed or build with NO_BPF_SKEL=1.) + else + ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) + dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) + else + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL + endif endif - $(call detected,CONFIG_PERF_BPF_SKEL) - CFLAGS += -DHAVE_BPF_SKEL endif dwarf-post-unwind := 1 diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 2fcee585b225..283ee4f56234 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -126,7 +126,7 @@ include ../scripts/utilities.mak # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod # -# Define BUILD_BPF_SKEL to enable BPF skeletons +# Define NO_BPF_SKEL to disable BPF skeletons # # As per kernel Makefile, avoid funny character set dependencies @@ -1055,7 +1055,7 @@ SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ -ifdef BUILD_BPF_SKEL +ifndef NO_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) @@ -1088,11 +1088,11 @@ bpf-skel: $(SKELETONS) .PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o -else # BUILD_BPF_SKEL +else # NO_BPF_SKEL bpf-skel: -endif # BUILD_BPF_SKEL +endif # NO_BPF_SKEL bpf-skel-clean: $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 054997edd98b..240d49a85524 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2371,7 +2371,7 @@ int cmd_lock(int argc, const char **argv) #ifndef HAVE_BPF_SKEL set_option_nobuild(contention_options, 'b', "use-bpf", - "no BUILD_BPF_SKEL=1", false); + "NO_BPF_SKEL=1", false); #endif if (argc) { argc = parse_options(argc, argv, contention_options, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 74388164a571..33ebe42b025e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -3971,7 +3971,7 @@ int cmd_record(int argc, const char **argv) #ifndef HAVE_BPF_SKEL # define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c) - set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true); + set_nobuild('\0', "off-cpu", "NO_BPF_SKEL=1", true); # undef set_nobuild #endif diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index a886929ec6e5..0d9cda238c07 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -83,6 +83,7 @@ static void library_status(void) STATUS(HAVE_ZSTD_SUPPORT, zstd); STATUS(HAVE_LIBPFM, libpfm4); STATUS(HAVE_LIBTRACEEVENT, libtraceevent); + STATUS(HAVE_BPF_SKEL, BPF skeletons); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index e01973d4e0fb..24f81ff85793 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -28,7 +28,7 @@ test_offcpu_priv() { err=2 return fi - if perf record --off-cpu -o /dev/null --quiet true 2>&1 | grep BUILD_BPF_SKEL + if perf version --build-options 2>&1 | grep HAVE_BPF_SKEL | grep -q OFF then echo "off-cpu test [Skipped missing BPF support]" err=2 -- GitLab From 7bafa03f21a6eebfce306ce32635c3adc13815f6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:43 -0800 Subject: [PATCH 0434/5631] perf build: Remove unused HAVE_GLIBC_SUPPORT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HAVE_GLIBC_SUPPORT is only used in `perf version --build-options` but doesn't control any behavior. Remove from the build to simplify it. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 4 ---- tools/perf/builtin-version.c | 1 - 2 files changed, 5 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 318af7657225..eb7a3aa58639 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -476,10 +476,6 @@ else endif # libelf support endif # NO_LIBELF -ifeq ($(feature-glibc), 1) - CFLAGS += -DHAVE_GLIBC_SUPPORT -endif - ifeq ($(feature-libaio), 1) ifndef NO_AIO CFLAGS += -DHAVE_AIO_SUPPORT diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 0d9cda238c07..c5d03a11e565 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -59,7 +59,6 @@ static void library_status(void) { STATUS(HAVE_DWARF_SUPPORT, dwarf); STATUS(HAVE_DWARF_GETLOCATIONS_SUPPORT, dwarf_getlocations); - STATUS(HAVE_GLIBC_SUPPORT, glibc); #ifndef HAVE_SYSCALL_TABLE_SUPPORT STATUS(HAVE_LIBAUDIT_SUPPORT, libaudit); #endif -- GitLab From 0cd3142f6b238981ed4855217cfa4ee0aa899181 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:45 -0800 Subject: [PATCH 0435/5631] perf util: Remove weak sched_getcpu MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sched_getcpu may not be present and so a feature test and definition exist to workaround this in the build. The feature test is used to define HAVE_SCHED_GETCPU_SUPPORT and so this is sufficient to know whether the local sched_getcpu is needed and a weak symbol can be avoided. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cloexec.c | 13 ------------- tools/perf/util/util.c | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 13 deletions(-) diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c index fa8248aadb59..8830604c3a8d 100644 --- a/tools/perf/util/cloexec.c +++ b/tools/perf/util/cloexec.c @@ -13,19 +13,6 @@ static unsigned long flag = PERF_FLAG_FD_CLOEXEC; -int __weak sched_getcpu(void) -{ -#ifdef __NR_getcpu - unsigned cpu; - int err = syscall(__NR_getcpu, &cpu, NULL, NULL); - if (!err) - return cpu; -#else - errno = ENOSYS; -#endif - return -1; -} - static int perf_flag_probe(void) { /* use 'safest' configuration as used in evsel__fallback() */ diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 391c1e928bd7..b356c9f7f0c3 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -533,3 +533,19 @@ int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x, size_t msz, *arr_sz = new_sz; return 0; } + +#ifndef HAVE_SCHED_GETCPU_SUPPORT +int sched_getcpu(void) +{ +#ifdef __NR_getcpu + unsigned int cpu; + int err = syscall(__NR_getcpu, &cpu, NULL, NULL); + + if (!err) + return cpu; +#else + errno = ENOSYS; +#endif + return -1; +} +#endif -- GitLab From 175f9315f76345e88e3abdc947c1e0030ab99da3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:46 -0800 Subject: [PATCH 0436/5631] perf build: Error if jevents won't work and NO_JEVENTS=1 isn't set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather than disabling jevents if a sufficient python isn't present error in the build. This avoids the build progressing but the binary being degraded. The build can still succeed by specifying NO_JEVENTS=1 to the build and this is conveyed in the error message. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index eb7a3aa58639..f882ce2e25b3 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -880,14 +880,12 @@ endif ifneq ($(NO_JEVENTS),1) NO_JEVENTS := 0 ifndef PYTHON - $(warning No python interpreter disabling jevent generation) - NO_JEVENTS := 1 + $(error ERROR: No python interpreter needed for jevents generation. Install python or build with NO_JEVENTS=1.) else # jevents.py uses f-strings present in Python 3.6 released in Dec. 2016. JEVENTS_PYTHON_GOOD := $(shell $(PYTHON) -c 'import sys;print("1" if(sys.version_info.major >= 3 and sys.version_info.minor >= 6) else "0")' 2> /dev/null) ifneq ($(JEVENTS_PYTHON_GOOD), 1) - $(warning Python interpreter too old (older than 3.6) disabling jevent generation) - NO_JEVENTS := 1 + $(error ERROR: Python interpreter needed for jevents generation too old (older than 3.6). Install a newer python or build with NO_JEVENTS=1.) endif endif endif -- GitLab From dd317df072071903031ab5f91b4823858445c4a0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:47 -0800 Subject: [PATCH 0437/5631] perf build: Make binutil libraries opt in MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit binutils is GPLv3 so distributions cannot ship perf linked against libbfd and libiberty as the licenses are incompatible. Rather than defaulting the build to opting in to libbfd and libiberty support and opting out via NO_LIBBFD=1 and NO_DEMANGLE=1, make building against the libraries optional and enabled with BUILD_NONDISTRO=1. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 25 ++++++++++--------------- tools/perf/Makefile.perf | 2 ++ tools/perf/tests/make | 2 ++ 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index f882ce2e25b3..c4ae70c643b9 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -890,7 +890,7 @@ ifneq ($(NO_JEVENTS),1) endif endif -ifndef NO_LIBBFD +ifdef BUILD_NONDISTRO ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd -lopcodes else @@ -913,6 +913,7 @@ ifndef NO_LIBBFD $(call feature_check,disassembler-init-styled) endif + CFLAGS += -DHAVE_LIBBFD_SUPPORT ifeq ($(feature-libbfd-buildid), 1) CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT else @@ -923,32 +924,26 @@ endif ifdef NO_DEMANGLE CFLAGS += -DNO_DEMANGLE else - ifdef HAVE_CPLUS_DEMANGLE_SUPPORT - EXTLIBS += -liberty - else + ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) - $(call feature_check,cplus-demangle) - - # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT - # or any of 'bfd iberty z' trinity - ifeq ($(feature-cplus-demangle), 1) + ifdef HAVE_CPLUS_DEMANGLE_SUPPORT EXTLIBS += -liberty else - msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling) - CFLAGS += -DNO_DEMANGLE + $(call feature_check,cplus-demangle) + ifeq ($(feature-cplus-demangle), 1) + EXTLIBS += -liberty + endif endif endif endif ifneq ($(filter -liberty,$(EXTLIBS)),) CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT + else + CFLAGS += -DNO_DEMANGLE endif endif -ifneq ($(filter -lbfd,$(EXTLIBS)),) - CFLAGS += -DHAVE_LIBBFD_SUPPORT -endif - ifndef NO_ZLIB ifeq ($(feature-zlib), 1) CFLAGS += -DHAVE_ZLIB_SUPPORT diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 283ee4f56234..a35bc995d5d8 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -128,6 +128,8 @@ include ../scripts/utilities.mak # # Define NO_BPF_SKEL to disable BPF skeletons # +# Define BUILD_NONDISTRO to enable building an linking against libbfd and +# libiberty distribution license incompatible libraries. # As per kernel Makefile, avoid funny character set dependencies unexport LC_ALL diff --git a/tools/perf/tests/make b/tools/perf/tests/make index f9f826c0df47..52b9b6895da5 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -68,6 +68,7 @@ python_perf_so := $(shell $(MAKE) python_perf_target|grep "Target is:"|awk '{pri make_clean_all := clean all make_python_perf_so := $(python_perf_so) make_debug := DEBUG=1 +make_nondistro := BUILD_NONDISTRO=1 make_no_libperl := NO_LIBPERL=1 make_no_libpython := NO_LIBPYTHON=1 make_no_scripts := NO_LIBPYTHON=1 NO_LIBPERL=1 @@ -134,6 +135,7 @@ MAKE_F := $(MAKE) -f $(MK) endif run += make_python_perf_so run += make_debug +run += make_nondistro run += make_no_libperl run += make_no_libpython run += make_no_scripts -- GitLab From 4c72e2b35afc414140a59fb3c06ebc54e506c245 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:48 -0800 Subject: [PATCH 0438/5631] tools build: Add feature test for abi::__cxa_demangle MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cxxabi.h is part of libsdtc++ and LLVM's libcxx, providing abi::__cxa_demangle a portable C++ demangler. Add a feature test to detect that the function is available. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-cxa-demangle.cpp | 17 +++++++++++++++++ 3 files changed, 22 insertions(+) create mode 100644 tools/build/feature/test-cxa-demangle.cpp diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 38f8851bd7cb..214622d7537c 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -80,6 +80,7 @@ FEATURE_TESTS_EXTRA := \ compile-32 \ compile-x32 \ cplus-demangle \ + cxa-demangle \ gtk2 \ gtk2-infobar \ hello \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index dc9323e01e42..0a3b9281f8b0 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -23,6 +23,7 @@ FILES= \ test-libbfd-liberty.bin \ test-libbfd-liberty-z.bin \ test-cplus-demangle.bin \ + test-cxa-demangle.bin \ test-libcap.bin \ test-libelf.bin \ test-libelf-getphdrnum.bin \ @@ -262,6 +263,9 @@ $(OUTPUT)test-libbfd-liberty-z.bin: $(OUTPUT)test-cplus-demangle.bin: $(BUILD) -liberty +$(OUTPUT)test-cxa-demangle.bin: + $(BUILDXX) + $(OUTPUT)test-backtrace.bin: $(BUILD) diff --git a/tools/build/feature/test-cxa-demangle.cpp b/tools/build/feature/test-cxa-demangle.cpp new file mode 100644 index 000000000000..a3e712f65c37 --- /dev/null +++ b/tools/build/feature/test-cxa-demangle.cpp @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include + +int main(void) +{ + size_t len = 256; + char *output = (char*)malloc(len); + int status; + + output = abi::__cxa_demangle("FieldName__9ClassNameFd", output, &len, &status); + + printf("demangled symbol: {%s}\n", output); + + return 0; +} -- GitLab From 3b4e4efe88f615f160a6c9319a9392d8410f742c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:49 -0800 Subject: [PATCH 0439/5631] perf symbol: Add abi::__cxa_demangle C++ demangling support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Refactor C++ demangling out of symbol-elf into its own files similar to other languages. Add abi::__cxa_demangle support. As the other demanglers are not shippable with distributions, this brings back C++ demangling in a common case. It isn't perfect as the support for optionally demangling arguments and modifiers isn't present. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 29 +++++++++--------- tools/perf/util/Build | 1 + tools/perf/util/demangle-cxx.cpp | 50 ++++++++++++++++++++++++++++++++ tools/perf/util/demangle-cxx.h | 16 ++++++++++ tools/perf/util/symbol-elf.c | 37 +++++------------------ 5 files changed, 88 insertions(+), 45 deletions(-) create mode 100644 tools/perf/util/demangle-cxx.cpp create mode 100644 tools/perf/util/demangle-cxx.h diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c4ae70c643b9..ac8a206acf87 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -914,6 +914,7 @@ ifdef BUILD_NONDISTRO endif CFLAGS += -DHAVE_LIBBFD_SUPPORT + CXXFLAGS += -DHAVE_LIBBFD_SUPPORT ifeq ($(feature-libbfd-buildid), 1) CFLAGS += -DHAVE_LIBBFD_BUILDID_SUPPORT else @@ -921,26 +922,24 @@ ifdef BUILD_NONDISTRO endif endif -ifdef NO_DEMANGLE - CFLAGS += -DNO_DEMANGLE -else +ifndef NO_DEMANGLE + $(call feature_check,cxa-demangle) + ifeq ($(feature-cxa-demangle), 1) + EXTLIBS += -lstdc++ + CFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + CXXFLAGS += -DHAVE_CXA_DEMANGLE_SUPPORT + endif ifdef BUILD_NONDISTRO ifeq ($(filter -liberty,$(EXTLIBS)),) - ifdef HAVE_CPLUS_DEMANGLE_SUPPORT + $(call feature_check,cplus-demangle) + ifeq ($(feature-cplus-demangle), 1) EXTLIBS += -liberty - else - $(call feature_check,cplus-demangle) - ifeq ($(feature-cplus-demangle), 1) - EXTLIBS += -liberty - endif endif endif - endif - - ifneq ($(filter -liberty,$(EXTLIBS)),) - CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT - else - CFLAGS += -DNO_DEMANGLE + ifneq ($(filter -liberty,$(EXTLIBS)),) + CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT + CXXFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT + endif endif endif diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 918b501f9bd8..8607575183a9 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -211,6 +211,7 @@ perf-$(CONFIG_ZSTD) += zstd.o perf-$(CONFIG_LIBCAP) += cap.o +perf-y += demangle-cxx.o perf-y += demangle-ocaml.o perf-y += demangle-java.o perf-y += demangle-rust.o diff --git a/tools/perf/util/demangle-cxx.cpp b/tools/perf/util/demangle-cxx.cpp new file mode 100644 index 000000000000..8708bcafd370 --- /dev/null +++ b/tools/perf/util/demangle-cxx.cpp @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "demangle-cxx.h" +#include +#include +#include + +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include +#endif + +#ifdef HAVE_CXA_DEMANGLE_SUPPORT +#include +#endif + +#if defined(HAVE_LIBBFD_SUPPORT) || defined(HAVE_CPLUS_DEMANGLE_SUPPORT) +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif +#endif + +/* + * Demangle C++ function signature + * + * Note: caller is responsible for freeing demangled string + */ +extern "C" +char *cxx_demangle_sym(const char *str, bool params __maybe_unused, + bool modifiers __maybe_unused) +{ +#ifdef HAVE_LIBBFD_SUPPORT + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return bfd_demangle(NULL, str, flags); +#elif defined(HAVE_CPLUS_DEMANGLE_SUPPORT) + int flags = (params ? DMGL_PARAMS : 0) | (modifiers ? DMGL_ANSI : 0); + + return cplus_demangle(str, flags); +#elif defined(HAVE_CXA_DEMANGLE_SUPPORT) + size_t len = strlen(str); + char *output = (char*)malloc(len); + int status; + + output = abi::__cxa_demangle(str, output, &len, &status); + return output; +#else + return NULL; +#endif +} diff --git a/tools/perf/util/demangle-cxx.h b/tools/perf/util/demangle-cxx.h new file mode 100644 index 000000000000..26b5b66c0b4e --- /dev/null +++ b/tools/perf/util/demangle-cxx.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_DEMANGLE_CXX +#define __PERF_DEMANGLE_CXX 1 + +#ifdef __cplusplus +extern "C" { +#endif + +char *cxx_demangle_sym(const char *str, bool params, bool modifiers); + +#ifdef __cplusplus +} +#endif + + +#endif /* __PERF_DEMANGLE_CXX */ diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 41882ae8452e..c0a2de42c51b 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -12,6 +12,7 @@ #include "maps.h" #include "symbol.h" #include "symsrc.h" +#include "demangle-cxx.h" #include "demangle-ocaml.h" #include "demangle-java.h" #include "demangle-rust.h" @@ -25,6 +26,11 @@ #include #include +#ifdef HAVE_LIBBFD_SUPPORT +#define PACKAGE 'perf' +#include +#endif + #ifndef EM_AARCH64 #define EM_AARCH64 183 /* ARM 64 bit */ #endif @@ -45,34 +51,6 @@ typedef Elf64_Nhdr GElf_Nhdr; -#ifndef DMGL_PARAMS -#define DMGL_NO_OPTS 0 /* For readability... */ -#define DMGL_PARAMS (1 << 0) /* Include function args */ -#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ -#endif - -#ifdef HAVE_LIBBFD_SUPPORT -#define PACKAGE 'perf' -#include -#else -#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT -extern char *cplus_demangle(const char *, int); - -static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i) -{ - return cplus_demangle(c, i); -} -#else -#ifdef NO_DEMANGLE -static inline char *bfd_demangle(void __maybe_unused *v, - const char __maybe_unused *c, - int __maybe_unused i) -{ - return NULL; -} -#endif -#endif -#endif #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT static int elf_getphdrnum(Elf *elf, size_t *dst) @@ -295,7 +273,6 @@ static bool want_demangle(bool is_kernel_sym) static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) { - int demangle_flags = verbose > 0 ? (DMGL_PARAMS | DMGL_ANSI) : DMGL_NO_OPTS; char *demangled = NULL; /* @@ -306,7 +283,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name) if (!want_demangle(dso->kernel || kmodule)) return demangled; - demangled = bfd_demangle(NULL, elf_name, demangle_flags); + demangled = cxx_demangle_sym(elf_name, verbose > 0, verbose > 0); if (demangled == NULL) { demangled = ocaml_demangle_sym(elf_name); if (demangled == NULL) { -- GitLab From d7c4f89af1611530562554a237069deb2b03b312 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:50 -0800 Subject: [PATCH 0440/5631] perf build: Switch libpfm4 to opt-out rather than opt-in MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If libpfm4 passes the feature test, it would be nice to have it enabled rather than also requiring the LIBPFM4=1 build flag. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 3 +-- tools/perf/Makefile.perf | 2 +- tools/perf/tests/make | 4 ++-- 3 files changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index ac8a206acf87..2caee19e3e9a 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1138,7 +1138,7 @@ ifdef LIBCLANGLLVM endif endif -ifdef LIBPFM4 +ifndef NO_LIBPFM4 $(call feature_check,libpfm4) ifeq ($(feature-libpfm4), 1) CFLAGS += -DHAVE_LIBPFM @@ -1147,7 +1147,6 @@ ifdef LIBPFM4 $(call detected,CONFIG_LIBPFM4) else msg := $(warning libpfm4 not found, disables libpfm4 support. Please install libpfm4-dev); - NO_LIBPFM4 := 1 endif endif diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a35bc995d5d8..3e06915f6bd0 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -122,7 +122,7 @@ include ../scripts/utilities.mak # generated from the kernel .tbl or unistd.h files and use, if available, libaudit # for doing the conversions to/from strings/id. # -# Define LIBPFM4 to enable libpfm4 events extension. +# Define NO_LIBPFM4 to disable libpfm4 events extension. # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod # diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 52b9b6895da5..ba09a8b4ffb4 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -94,7 +94,7 @@ make_with_coresight := CORESIGHT=1 make_no_sdt := NO_SDT=1 make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_with_clangllvm := LIBCLANGLLVM=1 -make_with_libpfm4 := LIBPFM4=1 +make_no_libpfm4 := NO_LIBPFM4=1 make_with_gtk2 := GTK2=1 make_tags := tags make_cscope := cscope @@ -160,7 +160,7 @@ run += make_no_syscall_tbl run += make_with_babeltrace run += make_with_coresight run += make_with_clangllvm -run += make_with_libpfm4 +run += make_no_libpfm4 run += make_help run += make_doc run += make_perf_o -- GitLab From 6898e60f709b0047206110d3ec9f4612210e3ff7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:51 -0800 Subject: [PATCH 0441/5631] perf build: If libtraceevent isn't present error the build MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If libtraceevent isn't present, the build will warn and continue. This disables a number of features and so isn't desirable. This change makes the build error for this case. The build can still be made to happen by adding NO_LIBTRACEEVENT=1. Committer notes: Add NO_LIBTRACEEVENT=1 to the 'make_static' target in tools/perf/tests/make so that 'make -C tools/perf build-test' works. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 2 +- tools/perf/tests/make | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 2caee19e3e9a..da0b13e819ee 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -1164,7 +1164,7 @@ ifneq ($(NO_LIBTRACEEVENT),1) CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP) $(call detected,CONFIG_LIBTRACEEVENT) else - dummy := $(warning Warning: libtraceevent is missing limiting functionality, please install libtraceevent-dev/libtraceevent-devel) + dummy := $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel or build with NO_LIBTRACEEVENT=1) endif $(call feature_check,libtracefs) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index ba09a8b4ffb4..55d0ef3a0cae 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -112,7 +112,7 @@ make_install_info := install-info make_install_pdf := install-pdf make_install_prefix := install prefix=/tmp/krava make_install_prefix_slash := install prefix=/tmp/krava/ -make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 +make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 NO_LIBTRACEEVENT=1 # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 -- GitLab From f1925bd588cfc3ea2e8624404027958955d39121 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:53 -0800 Subject: [PATCH 0442/5631] perf build: Remove redundant NO_NEWT build option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The option controlled nothing and no code depends, conditional or otherwise, on libnewt. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 4 ---- tools/perf/Makefile.perf | 2 -- tools/perf/tests/make | 6 ++---- 3 files changed, 2 insertions(+), 10 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index da0b13e819ee..0959714a89ed 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -760,10 +760,6 @@ ifndef NO_LIBCRYPTO endif endif -ifdef NO_NEWT - NO_SLANG=1 -endif - ifndef NO_SLANG ifneq ($(feature-libslang), 1) ifneq ($(feature-libslang-include-subdir), 1) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3e06915f6bd0..dc9dda09b076 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -44,8 +44,6 @@ include ../scripts/utilities.mak # # Define WERROR=0 to disable treating any warnings as errors. # -# Define NO_NEWT if you do not want TUI support. (deprecated) -# # Define NO_SLANG if you do not want TUI support. # # Define GTK2 if you want GTK+ GUI support. diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 55d0ef3a0cae..0b92fa1863f6 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -72,10 +72,9 @@ make_nondistro := BUILD_NONDISTRO=1 make_no_libperl := NO_LIBPERL=1 make_no_libpython := NO_LIBPYTHON=1 make_no_scripts := NO_LIBPYTHON=1 NO_LIBPERL=1 -make_no_newt := NO_NEWT=1 make_no_slang := NO_SLANG=1 make_no_gtk2 := NO_GTK2=1 -make_no_ui := NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 +make_no_ui := NO_SLANG=1 NO_GTK2=1 make_no_demangle := NO_DEMANGLE=1 make_no_libelf := NO_LIBELF=1 make_no_libunwind := NO_LIBUNWIND=1 @@ -115,7 +114,7 @@ make_install_prefix_slash := install prefix=/tmp/krava/ make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 NO_LIBTRACEEVENT=1 # all the NO_* variable combined -make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 +make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_GTK2=1 make_minimal += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 make_minimal += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 make_minimal += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 @@ -139,7 +138,6 @@ run += make_nondistro run += make_no_libperl run += make_no_libpython run += make_no_scripts -run += make_no_newt run += make_no_slang run += make_no_gtk2 run += make_no_ui -- GitLab From 8d98ca5c02df13c1f750953bca2e308a41df08a9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 10 Mar 2023 22:57:44 -0800 Subject: [PATCH 0443/5631] perf build: Error if no libelf and NO_LIBELF isn't set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building without libelf support is going disable a lot of functionality. Require that the NO_LIBELF=1 build option is passed if this is intentional. Committer notes: Add NO_LIBELF=1 to the 'make_static' target in tools/perf/tests/make so that 'make -C tools/perf build-test' works. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andres Freund Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pavithra Gurushankar Cc: Peter Zijlstra Cc: Quentin Monnet Cc: Roberto Sassu Cc: Stephane Eranian Cc: Tiezhu Yang Cc: Tom Rix Cc: Yang Jihong Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230311065753.3012826-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 10 +--------- tools/perf/tests/make | 2 +- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0959714a89ed..3066d0c318c3 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -426,15 +426,7 @@ else LIBC_SUPPORT := 1 endif ifeq ($(LIBC_SUPPORT),1) - msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel); - - NO_LIBELF := 1 - NO_DWARF := 1 - NO_DEMANGLE := 1 - NO_LIBUNWIND := 1 - NO_LIBDW_DWARF_UNWIND := 1 - NO_LIBBPF := 1 - NO_JVMTI := 1 + msg := $(error ERROR: No libelf found. Disables 'probe' tool, jvmti and BPF support. Please install libelf-dev, libelf-devel, elfutils-libelf-devel or build with NO_LIBELF=1.) else ifneq ($(filter s% -fsanitize=address%,$(EXTRA_CFLAGS),),) ifneq ($(shell ldconfig -p | grep libasan >/dev/null 2>&1; echo $$?), 0) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 0b92fa1863f6..96896d498641 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -111,7 +111,7 @@ make_install_info := install-info make_install_pdf := install-pdf make_install_prefix := install prefix=/tmp/krava make_install_prefix_slash := install prefix=/tmp/krava/ -make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 NO_LIBTRACEEVENT=1 +make_static := LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 NO_LIBTRACEEVENT=1 NO_LIBELF=1 # all the NO_* variable combined make_minimal := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_GTK2=1 -- GitLab From 3ace2435bb93445e7713d69336011c46558a18af Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 13 Mar 2023 13:48:22 -0700 Subject: [PATCH 0444/5631] perf lock contention: Track and show mmap_lock with address Sometimes there are severe contentions on the mmap_lock and we want see it in the -l/--lock-addr output. However it cannot symbolize the mmap_lock because it's allocated dynamically without symbols. Stephane and Hao gave me an idea separately to display mmap_lock by following the current->mm pointer. I added a flag to mark mmap_lock after comparing the lock address so that it can show them differently. With this change it can show mmap_lock like below: $ sudo ./perf lock con -abl -- sleep 10 contended total wait max wait avg wait address symbol ... 16344 312.30 ms 2.22 ms 19.11 us ffff8cc702595640 17686 310.08 ms 1.49 ms 17.53 us ffff8cc7025952c0 3 84.14 ms 45.79 ms 28.05 ms ffff8cc78114c478 mmap_lock 3557 76.80 ms 68.75 us 21.59 us ffff8cc77ca3af58 1 68.27 ms 68.27 ms 68.27 ms ffff8cda745dfd70 9 54.53 ms 7.96 ms 6.06 ms ffff8cc7642a48b8 mmap_lock 14629 44.01 ms 60.00 us 3.01 us ffff8cc7625f9ca0 3481 42.63 ms 140.71 us 12.24 us ffffffff937906ac vmap_area_lock 16194 38.73 ms 42.15 us 2.39 us ffff8cd397cbc560 11 38.44 ms 10.39 ms 3.49 ms ffff8ccd6d12fbb8 mmap_lock 1 5.43 ms 5.43 ms 5.43 ms ffff8cd70018f0d8 1674 5.38 ms 422.93 us 3.21 us ffffffff92e06080 tasklist_lock 581 4.51 ms 130.68 us 7.75 us ffff8cc9b1259058 5 3.52 ms 1.27 ms 703.23 us ffff8cc754510070 112 3.47 ms 56.47 us 31.02 us ffff8ccee38b3120 381 3.31 ms 73.44 us 8.69 us ffffffff93790690 purge_vmap_area_lock 255 3.19 ms 36.35 us 12.49 us ffff8d053ce30c80 Note that mmap_lock was renamed some time ago and it needs to support old kernels with a different name 'mmap_sem'. Suggested-by: Hao Luo Suggested-by: Stephane Eranian Signed-off-by: Namhyung Kim Cc: Boqun Feng Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: Suren Baghdasaryan Cc: Waiman Long Cc: Will Deacon Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230313204825.2665483-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 2 +- .../perf/util/bpf_skel/lock_contention.bpf.c | 41 +++++++++++++++++++ tools/perf/util/bpf_skel/lock_data.h | 6 +++ 3 files changed, 48 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 240d49a85524..1b0dc946fe85 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1663,7 +1663,7 @@ static void print_contention_result(struct lock_contention *con) break; case LOCK_AGGR_ADDR: pr_info(" %016llx %s\n", (unsigned long long)st->addr, - st->name ? : ""); + (st->flags & LCD_F_MMAP_LOCK) ? "mmap_lock" : st->name); break; default: break; diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 141b36d13b19..40ee3dffb35a 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -92,6 +92,14 @@ struct rw_semaphore___new { atomic_long_t owner; } __attribute__((preserve_access_index)); +struct mm_struct___old { + struct rw_semaphore mmap_sem; +} __attribute__((preserve_access_index)); + +struct mm_struct___new { + struct rw_semaphore mmap_lock; +} __attribute__((preserve_access_index)); + /* control flags */ int enabled; int has_cpu; @@ -210,6 +218,36 @@ static inline struct task_struct *get_lock_owner(__u64 lock, __u32 flags) return task; } +static inline __u32 check_lock_type(__u64 lock, __u32 flags) +{ + struct task_struct *curr; + struct mm_struct___old *mm_old; + struct mm_struct___new *mm_new; + + switch (flags) { + case LCB_F_READ: /* rwsem */ + case LCB_F_WRITE: + curr = bpf_get_current_task_btf(); + if (curr->mm == NULL) + break; + mm_new = (void *)curr->mm; + if (bpf_core_field_exists(mm_new->mmap_lock)) { + if (&mm_new->mmap_lock == (void *)lock) + return LCD_F_MMAP_LOCK; + break; + } + mm_old = (void *)curr->mm; + if (bpf_core_field_exists(mm_old->mmap_sem)) { + if (&mm_old->mmap_sem == (void *)lock) + return LCD_F_MMAP_LOCK; + } + break; + default: + break; + } + return 0; +} + SEC("tp_btf/contention_begin") int contention_begin(u64 *ctx) { @@ -320,6 +358,9 @@ int contention_end(u64 *ctx) .flags = pelem->flags, }; + if (aggr_mode == LOCK_AGGR_ADDR) + first.flags |= check_lock_type(pelem->lock, pelem->flags); + bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); bpf_map_delete_elem(&tstamp, &pid); return 0; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index 3d35fd4407ac..789f20833798 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -15,6 +15,12 @@ struct contention_task_data { char comm[TASK_COMM_LEN]; }; +/* + * Upper bits of the flags in the contention_data are used to identify + * some well-known locks which do not have symbols (non-global locks). + */ +#define LCD_F_MMAP_LOCK (1U << 31) + struct contention_data { u64 total_time; u64 min_time; -- GitLab From 1811e82767dcc6ebfdb2a57877f1756f067990b8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 13 Mar 2023 13:48:23 -0700 Subject: [PATCH 0445/5631] perf lock contention: Track and show siglock with address Likewise, we can display siglock by following the pointer like current->sighand->siglock. $ sudo ./perf lock con -abl -- sleep 1 contended total wait max wait avg wait address symbol 16 2.18 ms 305.35 us 136.34 us ffffffff92e06080 tasklist_lock 28 521.78 us 31.16 us 18.63 us ffff8cc703783ec4 7 119.03 us 23.55 us 17.00 us ffff8ccb92479440 15 88.29 us 10.06 us 5.89 us ffff8cd560b5f380 siglock 7 37.67 us 9.16 us 5.38 us ffff8d053daf0c80 5 8.81 us 4.92 us 1.76 us ffff8d053d6b0c80 Signed-off-by: Namhyung Kim Cc: Boqun Feng Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Waiman Long Cc: Will Deacon Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230313204825.2665483-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 3 +-- tools/perf/util/bpf_lock_contention.c | 8 ++++++-- tools/perf/util/bpf_skel/lock_contention.bpf.c | 5 +++++ tools/perf/util/bpf_skel/lock_data.h | 3 ++- 4 files changed, 14 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 1b0dc946fe85..28fa0d0dc276 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1662,8 +1662,7 @@ static void print_contention_result(struct lock_contention *con) pid, pid == -1 ? "Unknown" : thread__comm_str(t)); break; case LOCK_AGGR_ADDR: - pr_info(" %016llx %s\n", (unsigned long long)st->addr, - (st->flags & LCD_F_MMAP_LOCK) ? "mmap_lock" : st->name); + pr_info(" %016llx %s\n", (unsigned long long)st->addr, st->name); break; default: break; diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index fadcacb9d501..51631af3b4d6 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -169,7 +169,7 @@ int lock_contention_stop(void) static const char *lock_contention_get_name(struct lock_contention *con, struct contention_key *key, - u64 *stack_trace) + u64 *stack_trace, u32 flags) { int idx = 0; u64 addr; @@ -198,6 +198,10 @@ static const char *lock_contention_get_name(struct lock_contention *con, } if (con->aggr_mode == LOCK_AGGR_ADDR) { + if (flags & LCD_F_MMAP_LOCK) + return "mmap_lock"; + if (flags & LCD_F_SIGHAND_LOCK) + return "siglock"; sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap); if (sym) name = sym->name; @@ -301,7 +305,7 @@ int lock_contention_read(struct lock_contention *con) goto next; } - name = lock_contention_get_name(con, &key, stack_trace); + name = lock_contention_get_name(con, &key, stack_trace, data.flags); st = lock_stat_findnew(ls_key, name, data.flags); if (st == NULL) break; diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 40ee3dffb35a..f76cde065c5d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -242,6 +242,11 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) return LCD_F_MMAP_LOCK; } break; + case LCB_F_SPIN: /* spinlock */ + curr = bpf_get_current_task_btf(); + if (&curr->sighand->siglock == (void *)lock) + return LCD_F_SIGHAND_LOCK; + break; default: break; } diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index 789f20833798..5ed1a0955015 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -19,7 +19,8 @@ struct contention_task_data { * Upper bits of the flags in the contention_data are used to identify * some well-known locks which do not have symbols (non-global locks). */ -#define LCD_F_MMAP_LOCK (1U << 31) +#define LCD_F_MMAP_LOCK (1U << 31) +#define LCD_F_SIGHAND_LOCK (1U << 30) struct contention_data { u64 total_time; -- GitLab From d24c0144b1dde00f6e7283df3708fcc62dddbaa9 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 13 Mar 2023 13:48:24 -0700 Subject: [PATCH 0446/5631] perf lock contention: Show per-cpu rq_lock with address Using the BPF_PROG_RUN mechanism, we can run a raw_tp BPF program to collect some semi-global locks like per-cpu locks. Let's add runqueue locks using bpf_per_cpu_ptr() helper. $ sudo ./perf lock con -abl -- sleep 1 contended total wait max wait avg wait address symbol 248 3.25 ms 32.23 us 13.10 us ffff8cc75cfd2940 siglock 60 217.91 us 9.69 us 3.63 us ffff8cc700061c00 8 70.23 us 13.86 us 8.78 us ffff8cc703629484 4 56.32 us 35.81 us 14.08 us ffff8cc78b66f778 mmap_lock 4 16.70 us 5.18 us 4.18 us ffff8cc7036a0684 3 4.99 us 2.65 us 1.66 us ffff8d053da30c80 rq_lock 2 3.44 us 2.28 us 1.72 us ffff8d053dcf0c80 rq_lock 9 2.51 us 371 ns 278 ns ffff8ccb92479440 2 2.11 us 1.24 us 1.06 us ffff8d053db30c80 rq_lock 2 2.06 us 1.69 us 1.03 us ffff8d053d970c80 rq_lock Signed-off-by: Namhyung Kim Cc: Boqun Feng Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Waiman Long Cc: Will Deacon Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230313204825.2665483-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_lock_contention.c | 27 ++++++++++++++-- .../perf/util/bpf_skel/lock_contention.bpf.c | 31 +++++++++++++++++++ tools/perf/util/bpf_skel/lock_data.h | 5 +++ 3 files changed, 61 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 51631af3b4d6..235fc7150545 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -151,6 +151,8 @@ int lock_contention_prepare(struct lock_contention *con) skel->bss->needs_callstack = con->save_callstack; skel->bss->lock_owner = con->owner; + bpf_program__set_autoload(skel->progs.collect_lock_syms, false); + lock_contention_bpf__attach(skel); return 0; } @@ -198,14 +200,26 @@ static const char *lock_contention_get_name(struct lock_contention *con, } if (con->aggr_mode == LOCK_AGGR_ADDR) { + int lock_fd = bpf_map__fd(skel->maps.lock_syms); + + /* per-process locks set upper bits of the flags */ if (flags & LCD_F_MMAP_LOCK) return "mmap_lock"; if (flags & LCD_F_SIGHAND_LOCK) return "siglock"; + + /* global locks with symbols */ sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap); if (sym) - name = sym->name; - return name; + return sym->name; + + /* try semi-global locks collected separately */ + if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr, &flags)) { + if (flags == LOCK_CLASS_RQLOCK) + return "rq_lock"; + } + + return ""; } /* LOCK_AGGR_CALLER: skip lock internal functions */ @@ -258,6 +272,15 @@ int lock_contention_read(struct lock_contention *con) thread__set_comm(idle, "swapper", /*timestamp=*/0); } + if (con->aggr_mode == LOCK_AGGR_ADDR) { + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .flags = BPF_F_TEST_RUN_ON_CPU, + ); + int prog_fd = bpf_program__fd(skel->progs.collect_lock_syms); + + bpf_prog_test_run_opts(prog_fd, &opts); + } + /* make sure it loads the kernel map */ map__load(maps__first(machine->kmaps)); diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index f76cde065c5d..ed9160999c32 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -10,6 +10,9 @@ /* default buffer size */ #define MAX_ENTRIES 10240 +/* for collect_lock_syms(). 4096 was rejected by the verifier */ +#define MAX_CPUS 1024 + /* lock contention flags from include/trace/events/lock.h */ #define LCB_F_SPIN (1U << 0) #define LCB_F_READ (1U << 1) @@ -56,6 +59,13 @@ struct { __uint(max_entries, MAX_ENTRIES); } task_data SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u32)); + __uint(max_entries, 16384); +} lock_syms SEC(".maps"); + struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(key_size, sizeof(__u32)); @@ -384,4 +394,25 @@ int contention_end(u64 *ctx) return 0; } +extern struct rq runqueues __ksym; + +SEC("raw_tp/bpf_test_finish") +int BPF_PROG(collect_lock_syms) +{ + __u64 lock_addr; + __u32 lock_flag; + + for (int i = 0; i < MAX_CPUS; i++) { + struct rq *rq = bpf_per_cpu_ptr(&runqueues, i); + + if (rq == NULL) + break; + + lock_addr = (__u64)&rq->__lock; + lock_flag = LOCK_CLASS_RQLOCK; + bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); + } + return 0; +} + char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index 5ed1a0955015..e59366f2dba3 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -36,4 +36,9 @@ enum lock_aggr_mode { LOCK_AGGR_CALLER, }; +enum lock_class_sym { + LOCK_CLASS_NONE, + LOCK_CLASS_RQLOCK, +}; + #endif /* UTIL_BPF_SKEL_LOCK_DATA_H */ -- GitLab From 4f701063bfa24ca3da050104cc757dfc3b252355 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 13 Mar 2023 13:48:25 -0700 Subject: [PATCH 0447/5631] perf lock contention: Show lock type with address Show lock type names after the symbol of locks if any. This can be useful especially when it doesn't show the lock symbols. The indentation before the lock type parenthesis is to recognize lock symbols more easily. $ sudo ./perf lock con -abl -- sleep 1 contended total wait max wait avg wait address symbol 44 6.13 ms 284.49 us 139.28 us ffffffff92e06080 tasklist_lock (rwlock) 159 983.38 us 12.38 us 6.18 us ffff8cc717c90000 siglock (spinlock) 10 679.90 us 153.35 us 67.99 us ffff8cdc2872aaf8 mmap_lock (rwsem) 9 558.11 us 180.67 us 62.01 us ffff8cd647914038 mmap_lock (rwsem) 78 228.56 us 7.82 us 2.93 us ffff8cc700061c00 (spinlock) 5 41.60 us 16.93 us 8.32 us ffffd853acb41468 (spinlock) 10 37.24 us 5.87 us 3.72 us ffff8cd560b5c200 siglock (spinlock) 4 11.17 us 3.97 us 2.79 us ffff8d053ddf0c80 rq_lock (spinlock) 1 7.86 us 7.86 us 7.86 us ffff8cd64791404c (spinlock) 1 4.13 us 4.13 us 4.13 us ffff8d053d930c80 rq_lock (spinlock) 7 3.98 us 1.67 us 568 ns ffff8ccb92479440 (mutex) 2 2.62 us 2.33 us 1.31 us ffff8cc702e6ede0 (rwlock) Signed-off-by: Namhyung Kim Cc: Boqun Feng Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Waiman Long Cc: Will Deacon Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230313204825.2665483-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 45 ++++++++++++++++++---------- tools/perf/util/bpf_skel/lock_data.h | 2 ++ 2 files changed, 32 insertions(+), 15 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 28fa0d0dc276..3c8a19ebc496 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1548,27 +1548,41 @@ static void sort_result(void) static const struct { unsigned int flags; + const char *str; const char *name; } lock_type_table[] = { - { 0, "semaphore" }, - { LCB_F_SPIN, "spinlock" }, - { LCB_F_SPIN | LCB_F_READ, "rwlock:R" }, - { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W"}, - { LCB_F_READ, "rwsem:R" }, - { LCB_F_WRITE, "rwsem:W" }, - { LCB_F_RT, "rtmutex" }, - { LCB_F_RT | LCB_F_READ, "rwlock-rt:R" }, - { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W"}, - { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R" }, - { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W" }, - { LCB_F_MUTEX, "mutex" }, - { LCB_F_MUTEX | LCB_F_SPIN, "mutex" }, + { 0, "semaphore", "semaphore" }, + { LCB_F_SPIN, "spinlock", "spinlock" }, + { LCB_F_SPIN | LCB_F_READ, "rwlock:R", "rwlock" }, + { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock" }, + { LCB_F_READ, "rwsem:R", "rwsem" }, + { LCB_F_WRITE, "rwsem:W", "rwsem" }, + { LCB_F_RT, "rt=mutex", "rt-mutex" }, + { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt" }, + { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt" }, + { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem" }, + { LCB_F_PERCPU | LCB_F_WRITE, "pcpu-sem:W", "percpu-rwsem" }, + { LCB_F_MUTEX, "mutex", "mutex" }, + { LCB_F_MUTEX | LCB_F_SPIN, "mutex", "mutex" }, /* alias for get_type_flag() */ - { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin" }, + { LCB_F_MUTEX | LCB_F_SPIN, "mutex-spin", "mutex" }, }; static const char *get_type_str(unsigned int flags) { + flags &= LCB_F_MAX_FLAGS - 1; + + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (lock_type_table[i].flags == flags) + return lock_type_table[i].str; + } + return "unknown"; +} + +static const char *get_type_name(unsigned int flags) +{ + flags &= LCB_F_MAX_FLAGS - 1; + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { if (lock_type_table[i].flags == flags) return lock_type_table[i].name; @@ -1662,7 +1676,8 @@ static void print_contention_result(struct lock_contention *con) pid, pid == -1 ? "Unknown" : thread__comm_str(t)); break; case LOCK_AGGR_ADDR: - pr_info(" %016llx %s\n", (unsigned long long)st->addr, st->name); + pr_info(" %016llx %s (%s)\n", (unsigned long long)st->addr, + st->name, get_type_name(st->flags)); break; default: break; diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index e59366f2dba3..1ba61cb4d480 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -22,6 +22,8 @@ struct contention_task_data { #define LCD_F_MMAP_LOCK (1U << 31) #define LCD_F_SIGHAND_LOCK (1U << 30) +#define LCB_F_MAX_FLAGS (1U << 7) + struct contention_data { u64 total_time; u64 min_time; -- GitLab From 07fc5921a014e227bd3b622d31a8a35ff3f19afb Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 7 Mar 2023 16:27:14 -0800 Subject: [PATCH 0448/5631] perf test: Fix "PMU event table sanity" for NO_JEVENTS=1 A table was renamed and needed to be renamed in the empty case. Fixes: 62774db2a05dc878 ("perf jevents: Generate metrics and events as separate tables") Reviewed-by: John Garry Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230308002714.1755698-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/empty-pmu-events.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index a938b74cf487..e74defb5284f 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -227,7 +227,7 @@ static const struct pmu_events_map pmu_events_map[] = { }, }; -static const struct pmu_event pme_test_soc_sys[] = { +static const struct pmu_event pmu_events__test_soc_sys[] = { { .name = "sys_ddr_pmu.write_cycles", .event = "event=0x2b", @@ -258,8 +258,8 @@ struct pmu_sys_events { static const struct pmu_sys_events pmu_sys_event_tables[] = { { - .table = { pme_test_soc_sys }, - .name = "pme_test_soc_sys", + .table = { pmu_events__test_soc_sys }, + .name = "pmu_events__test_soc_sys", }, { .table = { 0 } -- GitLab From 0e70f50e72860f84759b62dae877c48523d33255 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Mar 2023 08:41:36 -0300 Subject: [PATCH 0449/5631] perf tools bpf: Add vmlinux.h to .gitignore Now that BPF skel based tools will be built by default if the toolchain pieces that are needed are available, building directly on the source tree will produce a vmlinux.h from the BTF info that needs to get ignored. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/.gitignore | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/.gitignore b/tools/perf/util/bpf_skel/.gitignore index 5263e9e6c5d8..cd01455e1b53 100644 --- a/tools/perf/util/bpf_skel/.gitignore +++ b/tools/perf/util/bpf_skel/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only .tmp -*.skel.h \ No newline at end of file +*.skel.h +vmlinux.h -- GitLab From 1f64cfdebfe0494264271e8d7a3a47faf5f58ec7 Mon Sep 17 00:00:00 2001 From: Roman Lozko Date: Fri, 10 Mar 2023 15:04:45 +0000 Subject: [PATCH 0450/5631] perf scripts intel-pt-events.py: Fix IPC output for Python 2 Integers are not converted to floats during division in Python 2 which results in incorrect IPC values. Fix by switching to new division behavior. Fixes: a483e64c0b62e93a ("perf scripting python: intel-pt-events.py: Add --insn-trace and --src-trace") Signed-off-by: Roman Lozko Acked-by: Adrian Hunter Cc: Adrian Hunter Link: https://lore.kernel.org/r/20230310150445.2925841-1-lozko.roma@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/intel-pt-events.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py index 08862a2582f4..1c76368f13c1 100644 --- a/tools/perf/scripts/python/intel-pt-events.py +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -11,7 +11,7 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. -from __future__ import print_function +from __future__ import division, print_function import io import os -- GitLab From 9d67c94335096311c0bc7556ad1022de7385790b Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 6 Mar 2023 11:30:20 -0600 Subject: [PATCH 0451/5631] powerpc/iommu: Add "borrowing" iommu_table_group_ops PPC64 IOMMU API defines iommu_table_group_ops which handles DMA windows for PEs: control the ownership, create/set/unset a table the hardware for dynamic DMA windows (DDW). VFIO uses the API to implement support on POWER. So far only PowerNV IODA2 (POWER8 and newer machines) implemented this and other cases (POWER7 or nested KVM) did not and instead reused existing iommu_table structs. This means 1) no DDW 2) ownership transfer is done directly in the VFIO SPAPR TCE driver. Soon POWER is going to get its own iommu_ops and ownership control is going to move there. This implements spapr_tce_table_group_ops which borrows iommu_table tables. The upside is that VFIO needs to know less about POWER. The new ops returns the existing table from create_table() and only checks if the same window is already set. This is only going to work if the default DMA window starts table_group.tce32_start and as big as pe->table_group.tce32_size (not the case for IODA2+ PowerNV). This changes iommu_table_group_ops::take_ownership() to return an error if borrowing a table failed. This should not cause any visible change in behavior for PowerNV. pSeries was not that well tested/supported anyway. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Timothy Pearson Acked-by: Alex Williamson [mpe: Fix CONFIG_IOMMU_API=n build (skiroot_defconfig), & formatting] Signed-off-by: Michael Ellerman Link: https://msgid.link/525438831.16998517.1678123820075.JavaMail.zimbra@raptorengineeringinc.com --- arch/powerpc/include/asm/iommu.h | 6 +- arch/powerpc/kernel/iommu.c | 98 ++++++++++++++++++++++- arch/powerpc/platforms/powernv/pci-ioda.c | 8 +- arch/powerpc/platforms/pseries/iommu.c | 5 ++ drivers/vfio/vfio_iommu_spapr_tce.c | 94 ++++------------------ 5 files changed, 125 insertions(+), 86 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 7e29c73e3dd4..678b5bdc79b1 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -175,7 +175,7 @@ struct iommu_table_group_ops { long (*unset_window)(struct iommu_table_group *table_group, int num); /* Switch ownership from platform code to external user (e.g. VFIO) */ - void (*take_ownership)(struct iommu_table_group *table_group); + long (*take_ownership)(struct iommu_table_group *table_group); /* Switch ownership from external user (e.g. VFIO) back to core */ void (*release_ownership)(struct iommu_table_group *table_group); }; @@ -215,6 +215,8 @@ extern long iommu_tce_xchg_no_kill(struct mm_struct *mm, enum dma_data_direction *direction); extern void iommu_tce_kill(struct iommu_table *tbl, unsigned long entry, unsigned long pages); + +extern struct iommu_table_group_ops spapr_tce_table_group_ops; #else static inline void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, @@ -303,8 +305,6 @@ extern int iommu_tce_check_gpa(unsigned long page_shift, iommu_tce_check_gpa((tbl)->it_page_shift, (gpa))) extern void iommu_flush_tce(struct iommu_table *tbl); -extern int iommu_take_ownership(struct iommu_table *tbl); -extern void iommu_release_ownership(struct iommu_table *tbl); extern enum dma_data_direction iommu_tce_direction(unsigned long tce); extern unsigned long iommu_direction_to_tce_perm(enum dma_data_direction dir); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index ee95937bdaf1..4cd3d68784b6 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1086,7 +1086,7 @@ void iommu_tce_kill(struct iommu_table *tbl, } EXPORT_SYMBOL_GPL(iommu_tce_kill); -int iommu_take_ownership(struct iommu_table *tbl) +static int iommu_take_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; int ret = 0; @@ -1118,9 +1118,8 @@ int iommu_take_ownership(struct iommu_table *tbl) return ret; } -EXPORT_SYMBOL_GPL(iommu_take_ownership); -void iommu_release_ownership(struct iommu_table *tbl) +static void iommu_release_ownership(struct iommu_table *tbl) { unsigned long flags, i, sz = (tbl->it_size + 7) >> 3; @@ -1137,7 +1136,6 @@ void iommu_release_ownership(struct iommu_table *tbl) spin_unlock(&tbl->pools[i].lock); spin_unlock_irqrestore(&tbl->large_pool.lock, flags); } -EXPORT_SYMBOL_GPL(iommu_release_ownership); int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) { @@ -1179,4 +1177,96 @@ void iommu_del_device(struct device *dev) iommu_group_remove_device(dev); } EXPORT_SYMBOL_GPL(iommu_del_device); + +/* + * A simple iommu_table_group_ops which only allows reusing the existing + * iommu_table. This handles VFIO for POWER7 or the nested KVM. + * The ops does not allow creating windows and only allows reusing the existing + * one if it matches table_group->tce32_start/tce32_size/page_shift. + */ +static unsigned long spapr_tce_get_table_size(__u32 page_shift, + __u64 window_size, __u32 levels) +{ + unsigned long size; + + if (levels > 1) + return ~0U; + size = window_size >> (page_shift - 3); + return size; +} + +static long spapr_tce_create_table(struct iommu_table_group *table_group, int num, + __u32 page_shift, __u64 window_size, __u32 levels, + struct iommu_table **ptbl) +{ + struct iommu_table *tbl = table_group->tables[0]; + + if (num > 0) + return -EPERM; + + if (tbl->it_page_shift != page_shift || + tbl->it_size != (window_size >> page_shift) || + tbl->it_indirect_levels != levels - 1) + return -EINVAL; + + *ptbl = iommu_tce_table_get(tbl); + return 0; +} + +static long spapr_tce_set_window(struct iommu_table_group *table_group, + int num, struct iommu_table *tbl) +{ + return tbl == table_group->tables[num] ? 0 : -EPERM; +} + +static long spapr_tce_unset_window(struct iommu_table_group *table_group, int num) +{ + return 0; +} + +static long spapr_tce_take_ownership(struct iommu_table_group *table_group) +{ + int i, j, rc = 0; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbl = table_group->tables[i]; + + if (!tbl || !tbl->it_map) + continue; + + rc = iommu_take_ownership(tbl); + if (!rc) + continue; + for (j = 0; j < i; ++j) + iommu_release_ownership(table_group->tables[j]); + return rc; + } + return 0; +} + +static void spapr_tce_release_ownership(struct iommu_table_group *table_group) +{ + int i; + + for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { + struct iommu_table *tbl = table_group->tables[i]; + + if (!tbl) + continue; + + iommu_table_clear(tbl); + if (tbl->it_map) + iommu_release_ownership(tbl); + } +} + +struct iommu_table_group_ops spapr_tce_table_group_ops = { + .get_table_size = spapr_tce_get_table_size, + .create_table = spapr_tce_create_table, + .set_window = spapr_tce_set_window, + .unset_window = spapr_tce_unset_window, + .take_ownership = spapr_tce_take_ownership, + .release_ownership = spapr_tce_release_ownership, +}; + #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 4f6e20a35aa1..c8a5caedc4c5 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1554,6 +1554,10 @@ static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb, if (WARN_ON(!tbl)) return; +#ifdef CONFIG_IOMMU_API + pe->table_group.ops = &spapr_tce_table_group_ops; + pe->table_group.pgsizes = SZ_4K; +#endif iommu_register_group(&pe->table_group, phb->hose->global_number, pe->pe_number); pnv_pci_link_table_and_group(phb->hose->node, 0, tbl, &pe->table_group); @@ -1888,7 +1892,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) } } -static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) +static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group) { struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, table_group); @@ -1902,6 +1906,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) else if (pe->pdev) set_iommu_table_base(&pe->pdev->dev, NULL); iommu_tce_table_put(tbl); + + return 0; } static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index c74b71d4733d..8eec100a1d87 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -74,6 +74,11 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) if (!table_group) return NULL; +#ifdef CONFIG_IOMMU_API + table_group->ops = &spapr_tce_table_group_ops; + table_group->pgsizes = SZ_4K; +#endif + table_group->tables[0] = iommu_pseries_alloc_table(node); if (table_group->tables[0]) return table_group; diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 60a50ce8701e..c3f8ae102ece 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -1189,52 +1189,6 @@ static long tce_iommu_ioctl(void *iommu_data, static void tce_iommu_release_ownership(struct tce_container *container, struct iommu_table_group *table_group) -{ - int i; - - for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - struct iommu_table *tbl = container->tables[i]; - - if (!tbl) - continue; - - tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size); - if (tbl->it_map) - iommu_release_ownership(tbl); - - container->tables[i] = NULL; - } -} - -static int tce_iommu_take_ownership(struct tce_container *container, - struct iommu_table_group *table_group) -{ - int i, j, rc = 0; - - for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { - struct iommu_table *tbl = table_group->tables[i]; - - if (!tbl || !tbl->it_map) - continue; - - rc = iommu_take_ownership(tbl); - if (rc) { - for (j = 0; j < i; ++j) - iommu_release_ownership( - table_group->tables[j]); - - return rc; - } - } - - for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) - container->tables[i] = table_group->tables[i]; - - return 0; -} - -static void tce_iommu_release_ownership_ddw(struct tce_container *container, - struct iommu_table_group *table_group) { long i; @@ -1250,18 +1204,14 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container, table_group->ops->release_ownership(table_group); } -static long tce_iommu_take_ownership_ddw(struct tce_container *container, +static long tce_iommu_take_ownership(struct tce_container *container, struct iommu_table_group *table_group) { long i, ret = 0; - if (!table_group->ops->create_table || !table_group->ops->set_window || - !table_group->ops->release_ownership) { - WARN_ON_ONCE(1); - return -EFAULT; - } - - table_group->ops->take_ownership(table_group); + ret = table_group->ops->take_ownership(table_group); + if (ret) + return ret; /* Set all windows to the new group */ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { @@ -1307,9 +1257,14 @@ static int tce_iommu_attach_group(void *iommu_data, goto unlock_exit; } - if (tce_groups_attached(container) && (!table_group->ops || - !table_group->ops->take_ownership || - !table_group->ops->release_ownership)) { + /* v2 requires full support of dynamic DMA windows */ + if (container->v2 && table_group->max_dynamic_windows_supported == 0) { + ret = -EINVAL; + goto unlock_exit; + } + + /* v1 reuses TCE tables and does not share them among PEs */ + if (!container->v2 && tce_groups_attached(container)) { ret = -EBUSY; goto unlock_exit; } @@ -1344,29 +1299,15 @@ static int tce_iommu_attach_group(void *iommu_data, goto unlock_exit; } - if (!table_group->ops || !table_group->ops->take_ownership || - !table_group->ops->release_ownership) { - if (container->v2) { - ret = -EPERM; - goto free_exit; - } - ret = tce_iommu_take_ownership(container, table_group); - } else { - if (!container->v2) { - ret = -EPERM; - goto free_exit; - } - ret = tce_iommu_take_ownership_ddw(container, table_group); - if (!tce_groups_attached(container) && !container->tables[0]) - container->def_window_pending = true; - } + ret = tce_iommu_take_ownership(container, table_group); + if (!tce_groups_attached(container) && !container->tables[0]) + container->def_window_pending = true; if (!ret) { tcegrp->grp = iommu_group; list_add(&tcegrp->next, &container->group_list); } -free_exit: if (ret && tcegrp) kfree(tcegrp); @@ -1405,10 +1346,7 @@ static void tce_iommu_detach_group(void *iommu_data, table_group = iommu_group_get_iommudata(iommu_group); BUG_ON(!table_group); - if (!table_group->ops || !table_group->ops->release_ownership) - tce_iommu_release_ownership(container, table_group); - else - tce_iommu_release_ownership_ddw(container, table_group); + tce_iommu_release_ownership(container, table_group); unlock_exit: mutex_unlock(&container->lock); -- GitLab From 76f351096c4516f38b9c901a21797fa958588e3a Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 6 Mar 2023 11:30:42 -0600 Subject: [PATCH 0452/5631] powerpc/pci_64: Init pcibios subsys a bit later Subsequent patches are going to add dependency/use of iommu_ops which is initialized in subsys_initcall as well. This moves pciobios_init() to the next initcall level. This should not cause behavioral change. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Timothy Pearson Signed-off-by: Michael Ellerman Link: https://msgid.link/12303156.16998521.1678123842049.JavaMail.zimbra@raptorengineeringinc.com --- arch/powerpc/kernel/pci_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index fd42059ae2a5..e27342ef128b 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -73,7 +73,7 @@ static int __init pcibios_init(void) return 0; } -subsys_initcall(pcibios_init); +subsys_initcall_sync(pcibios_init); int pcibios_unmap_io_space(struct pci_bus *bus) { -- GitLab From a940904443e432623579245babe63e2486ff327b Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Mon, 6 Mar 2023 11:31:00 -0600 Subject: [PATCH 0453/5631] powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains Up until now PPC64 managed to avoid using iommu_ops. The VFIO driver uses a SPAPR TCE sub-driver and all iommu_ops uses were kept in the Type1 VFIO driver. Recent development added 2 uses of iommu_ops to the generic VFIO which broke POWER: - a coherency capability check; - blocking IOMMU domain - iommu_group_dma_owner_claimed()/... This adds a simple iommu_ops which reports support for cache coherency and provides a basic support for blocking domains. No other domain types are implemented so the default domain is NULL. Since now iommu_ops controls the group ownership, this takes it out of VFIO. This adds an IOMMU device into a pci_controller (=PHB) and registers it in the IOMMU subsystem, iommu_ops is registered at this point. This setup is done in postcore_initcall_sync. This replaces iommu_group_add_device() with iommu_probe_device() as the former misses necessary steps in connecting PCI devices to IOMMU devices. This adds a comment about why explicit iommu_probe_device() is still needed. The previous discussion is here: https://lore.kernel.org/r/20220707135552.3688927-1-aik@ozlabs.ru/ https://lore.kernel.org/r/20220701061751.1955857-1-aik@ozlabs.ru/ Fixes: e8ae0e140c05 ("vfio: Require that devices support DMA cache coherence") Fixes: 70693f470848 ("vfio: Set DMA ownership for VFIO devices") Signed-off-by: Alexey Kardashevskiy Signed-off-by: Timothy Pearson Acked-by: Alex Williamson [mpe: Fix CONFIG_IOMMU_API=n build] Signed-off-by: Michael Ellerman Link: https://msgid.link/2000135730.16998523.1678123860135.JavaMail.zimbra@raptorengineeringinc.com --- arch/powerpc/include/asm/pci-bridge.h | 7 + arch/powerpc/kernel/iommu.c | 148 +++++++++++++++++++++- arch/powerpc/platforms/powernv/pci-ioda.c | 34 +++++ arch/powerpc/platforms/pseries/iommu.c | 24 ++++ arch/powerpc/platforms/pseries/pseries.h | 4 + arch/powerpc/platforms/pseries/setup.c | 3 + drivers/vfio/vfio_iommu_spapr_tce.c | 8 -- 7 files changed, 218 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 71c1d26f2400..2aa3a091ef20 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -8,6 +8,7 @@ #include #include #include +#include struct device_node; @@ -44,6 +45,9 @@ struct pci_controller_ops { #endif void (*shutdown)(struct pci_controller *hose); + + struct iommu_group *(*device_group)(struct pci_controller *hose, + struct pci_dev *pdev); }; /* @@ -131,6 +135,9 @@ struct pci_controller { struct irq_domain *dev_domain; struct irq_domain *msi_domain; struct fwnode_handle *fwnode; + + /* iommu_ops support */ + struct iommu_device iommu; }; /* These are used for config access before all the PCI probing diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 4cd3d68784b6..0089dd49b4cb 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -35,6 +35,7 @@ #include #include #include +#include #define DBG(...) @@ -1156,8 +1157,14 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) pr_debug("%s: Adding %s to iommu group %d\n", __func__, dev_name(dev), iommu_group_id(table_group->group)); - - return iommu_group_add_device(table_group->group, dev); + /* + * This is still not adding devices via the IOMMU bus notifier because + * of pcibios_init() from arch/powerpc/kernel/pci_64.c which calls + * pcibios_scan_phb() first (and this guy adds devices and triggers + * the notifier) and only then it calls pci_bus_add_devices() which + * configures DMA for buses which also creates PEs and IOMMU groups. + */ + return iommu_probe_device(dev); } EXPORT_SYMBOL_GPL(iommu_add_device); @@ -1237,6 +1244,7 @@ static long spapr_tce_take_ownership(struct iommu_table_group *table_group) rc = iommu_take_ownership(tbl); if (!rc) continue; + for (j = 0; j < i; ++j) iommu_release_ownership(table_group->tables[j]); return rc; @@ -1269,4 +1277,140 @@ struct iommu_table_group_ops spapr_tce_table_group_ops = { .release_ownership = spapr_tce_release_ownership, }; +/* + * A simple iommu_ops to allow less cruft in generic VFIO code. + */ +static int spapr_tce_blocking_iommu_attach_dev(struct iommu_domain *dom, + struct device *dev) +{ + struct iommu_group *grp = iommu_group_get(dev); + struct iommu_table_group *table_group; + int ret = -EINVAL; + + if (!grp) + return -ENODEV; + + table_group = iommu_group_get_iommudata(grp); + ret = table_group->ops->take_ownership(table_group); + iommu_group_put(grp); + + return ret; +} + +static void spapr_tce_blocking_iommu_set_platform_dma(struct device *dev) +{ + struct iommu_group *grp = iommu_group_get(dev); + struct iommu_table_group *table_group; + + table_group = iommu_group_get_iommudata(grp); + table_group->ops->release_ownership(table_group); +} + +static const struct iommu_domain_ops spapr_tce_blocking_domain_ops = { + .attach_dev = spapr_tce_blocking_iommu_attach_dev, +}; + +static bool spapr_tce_iommu_capable(struct device *dev, enum iommu_cap cap) +{ + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: + return true; + default: + break; + } + + return false; +} + +static struct iommu_domain *spapr_tce_iommu_domain_alloc(unsigned int type) +{ + struct iommu_domain *dom; + + if (type != IOMMU_DOMAIN_BLOCKED) + return NULL; + + dom = kzalloc(sizeof(*dom), GFP_KERNEL); + if (!dom) + return NULL; + + dom->ops = &spapr_tce_blocking_domain_ops; + + return dom; +} + +static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev) +{ + struct pci_dev *pdev; + struct pci_controller *hose; + + if (!dev_is_pci(dev)) + return ERR_PTR(-EPERM); + + pdev = to_pci_dev(dev); + hose = pdev->bus->sysdata; + + return &hose->iommu; +} + +static void spapr_tce_iommu_release_device(struct device *dev) +{ +} + +static struct iommu_group *spapr_tce_iommu_device_group(struct device *dev) +{ + struct pci_controller *hose; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + hose = pdev->bus->sysdata; + + if (!hose->controller_ops.device_group) + return ERR_PTR(-ENOENT); + + return hose->controller_ops.device_group(hose, pdev); +} + +static const struct iommu_ops spapr_tce_iommu_ops = { + .capable = spapr_tce_iommu_capable, + .domain_alloc = spapr_tce_iommu_domain_alloc, + .probe_device = spapr_tce_iommu_probe_device, + .release_device = spapr_tce_iommu_release_device, + .device_group = spapr_tce_iommu_device_group, + .set_platform_dma_ops = spapr_tce_blocking_iommu_set_platform_dma, +}; + +static struct attribute *spapr_tce_iommu_attrs[] = { + NULL, +}; + +static struct attribute_group spapr_tce_iommu_group = { + .name = "spapr-tce-iommu", + .attrs = spapr_tce_iommu_attrs, +}; + +static const struct attribute_group *spapr_tce_iommu_groups[] = { + &spapr_tce_iommu_group, + NULL, +}; + +/* + * This registers IOMMU devices of PHBs. This needs to happen + * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and + * before subsys_initcall(iommu_subsys_init). + */ +static int __init spapr_tce_setup_phb_iommus_initcall(void) +{ + struct pci_controller *hose; + + list_for_each_entry(hose, &hose_list, list_node) { + iommu_device_sysfs_add(&hose->iommu, hose->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + hose->global_number); + iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, + hose->parent); + } + return 0; +} +postcore_initcall_sync(spapr_tce_setup_phb_iommus_initcall); + #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index c8a5caedc4c5..f851f4983423 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1899,6 +1899,13 @@ static long pnv_ioda2_take_ownership(struct iommu_table_group *table_group) /* Store @tbl as pnv_pci_ioda2_unset_window() resets it */ struct iommu_table *tbl = pe->table_group.tables[0]; + /* + * iommu_ops transfers the ownership per a device and we mode + * the group ownership with the first device in the group. + */ + if (!tbl) + return 0; + pnv_pci_ioda2_set_bypass(pe, false); pnv_pci_ioda2_unset_window(&pe->table_group, 0); if (pe->pbus) @@ -1915,6 +1922,9 @@ static void pnv_ioda2_release_ownership(struct iommu_table_group *table_group) struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, table_group); + /* See the comment about iommu_ops above */ + if (pe->table_group.tables[0]) + return; pnv_pci_ioda2_setup_default_config(pe); if (pe->pbus) pnv_ioda_setup_bus_dma(pe, pe->pbus); @@ -2921,6 +2931,27 @@ static void pnv_pci_ioda_dma_bus_setup(struct pci_bus *bus) } } +#ifdef CONFIG_IOMMU_API +static struct iommu_group *pnv_pci_device_group(struct pci_controller *hose, + struct pci_dev *pdev) +{ + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + if (WARN_ON(!phb)) + return ERR_PTR(-ENODEV); + + pe = pnv_pci_bdfn_to_pe(phb, pdev->devfn | (pdev->bus->number << 8)); + if (!pe) + return ERR_PTR(-ENODEV); + + if (!pe->table_group.group) + return ERR_PTR(-ENODEV); + + return iommu_group_ref_get(pe->table_group.group); +} +#endif + static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_ioda_dma_dev_setup, .dma_bus_setup = pnv_pci_ioda_dma_bus_setup, @@ -2931,6 +2962,9 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .setup_bridge = pnv_pci_fixup_bridge_resources, .reset_secondary_bus = pnv_pci_reset_secondary_bus, .shutdown = pnv_pci_ioda_shutdown, +#ifdef CONFIG_IOMMU_API + .device_group = pnv_pci_device_group, +#endif }; static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = { diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 8eec100a1d87..de77c8c43211 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1729,3 +1729,27 @@ static int __init tce_iommu_bus_notifier_init(void) return 0; } machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); + +#ifdef CONFIG_SPAPR_TCE_IOMMU +struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, + struct pci_dev *pdev) +{ + struct device_node *pdn, *dn = pdev->dev.of_node; + struct iommu_group *grp; + struct pci_dn *pci; + + pdn = pci_dma_find(dn, NULL); + if (!pdn || !PCI_DN(pdn)) + return ERR_PTR(-ENODEV); + + pci = PCI_DN(pdn); + if (!pci->table_group) + return ERR_PTR(-ENODEV); + + grp = pci->table_group->group; + if (!grp) + return ERR_PTR(-ENODEV); + + return iommu_group_ref_get(grp); +} +#endif diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1d75b7742ef0..f8bce40ebd0c 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -123,5 +123,9 @@ static inline void pseries_lpar_read_hblkrm_characteristics(void) { } #endif void pseries_rng_init(void); +#ifdef CONFIG_SPAPR_TCE_IOMMU +struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, + struct pci_dev *pdev); +#endif #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 4a0cec8cf623..94a7617eb044 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1118,6 +1118,9 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) struct pci_controller_ops pseries_pci_controller_ops = { .probe_mode = pSeries_pci_probe_mode, +#ifdef CONFIG_SPAPR_TCE_IOMMU + .device_group = pSeries_pci_device_group, +#endif }; define_machine(pseries) { diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index c3f8ae102ece..a94ec6225d31 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -1200,8 +1200,6 @@ static void tce_iommu_release_ownership(struct tce_container *container, for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) if (container->tables[i]) table_group->ops->unset_window(table_group, i); - - table_group->ops->release_ownership(table_group); } static long tce_iommu_take_ownership(struct tce_container *container, @@ -1209,10 +1207,6 @@ static long tce_iommu_take_ownership(struct tce_container *container, { long i, ret = 0; - ret = table_group->ops->take_ownership(table_group); - if (ret) - return ret; - /* Set all windows to the new group */ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { struct iommu_table *tbl = container->tables[i]; @@ -1231,8 +1225,6 @@ static long tce_iommu_take_ownership(struct tce_container *container, for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) table_group->ops->unset_window(table_group, i); - table_group->ops->release_ownership(table_group); - return ret; } -- GitLab From a34d2f0d79ec890b9b1b156a90016b6330173b8a Mon Sep 17 00:00:00 2001 From: Timothy Pearson Date: Mon, 6 Mar 2023 11:31:28 -0600 Subject: [PATCH 0454/5631] powerpc: Add myself to MAINTAINERS for Power VFIO support Signed-off-by: Timothy Pearson Acked-by: Alex Williamson Signed-off-by: Michael Ellerman Link: https://msgid.link/256219069.16998525.1678123888896.JavaMail.zimbra@raptorengineeringinc.com --- MAINTAINERS | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index ec57c42ed544..1893119fd9c4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9836,6 +9836,11 @@ F: drivers/crypto/vmx/ghash* F: drivers/crypto/vmx/ppc-xlate.pl F: drivers/crypto/vmx/vmx.c +IBM Power VFIO Support +M: Timothy Pearson +S: Supported +F: drivers/vfio/vfio_iommu_spapr_tce.c + IBM ServeRAID RAID DRIVER S: Orphan F: drivers/scsi/ips.* -- GitLab From 493648d6795f00b6dcd6295b2b4221871bc1b25b Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 8 Mar 2023 08:36:14 +1100 Subject: [PATCH 0455/5631] selftests/powerpc: Increase timeout for vsx_signal test On the max config P10 machine (1920 threads and 64TB) this test fails with a timeout: Sending signals to all threads 10 times...!! killing vmx_signal !! child died by signal 15 failure: vmx_signal The default timeout is 120sec so increase this 3x to 360sec. With this change the test passes on these large machines. Signed-off-by: Michael Neuling Signed-off-by: Michael Ellerman Link: https://msgid.link/20230307213614.2652059-1-mikey@neuling.org --- tools/testing/selftests/powerpc/math/vmx_signal.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/powerpc/math/vmx_signal.c b/tools/testing/selftests/powerpc/math/vmx_signal.c index b340a5c4e79d..c307dff19c12 100644 --- a/tools/testing/selftests/powerpc/math/vmx_signal.c +++ b/tools/testing/selftests/powerpc/math/vmx_signal.c @@ -151,5 +151,6 @@ int test_signal_vmx(void) int main(int argc, char *argv[]) { + test_harness_set_timeout(360); return test_harness(test_signal_vmx, "vmx_signal"); } -- GitLab From be994293544f1c0b032dabfe0832d9c1dfcea14b Mon Sep 17 00:00:00 2001 From: Bo Liu Date: Mon, 31 Oct 2022 21:54:52 -0400 Subject: [PATCH 0456/5631] powerpc: Fix a kernel-doc warning The current code provokes a kernel-doc warnings: arch/powerpc/kernel/process.c:1606: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst Signed-off-by: Bo Liu Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20221101015452.3216-1-liubo03@inspur.com --- arch/powerpc/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4b29ac5ddac6..a7f9f3f85e20 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1630,7 +1630,7 @@ void arch_setup_new_exec(void) } #ifdef CONFIG_PPC64 -/** +/* * Assign a TIDR (thread ID) for task @t and set it in the thread * structure. For now, we only support setting TIDR for 'current' task. * -- GitLab From 8a32341cf04ba05974931b4664683c2c9fb84e56 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 1 Mar 2023 22:39:17 +0530 Subject: [PATCH 0457/5631] selftests/powerpc/pmu: Fix sample field check in the mmcra_thresh_marked_sample_test The testcase verifies the setting of different fields in Monitor Mode Control Register A (MMCRA). In the current code, EV_CODE_EXTRACT macro is used to extract the "sample" field, which then needs to be further processed to fetch rand_samp_elig and rand_samp_mode bits. But the current code is not passing valid sample field to EV_CODE_EXTRACT macro. Patch addresses this by fixing the input for EV_CODE_EXTRACT. Fixes: 29cf373c5766 ("selftests/powerpc/pmu: Add interface test for mmcra register fields") Reported-by: David Binderman Link: https://lore.kernel.org/r/DB6P189MB0568CF002762C6C43AF6DF169CA89@DB6P189MB0568.EURP189.PROD.OUTLOOK.COM Signed-off-by: Kajol Jain Signed-off-by: Michael Ellerman Link: https://msgid.link/20230301170918.69176-1-kjain@linux.ibm.com --- .../pmu/sampling_tests/mmcra_thresh_marked_sample_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c index 022cc1655eb5..75527876ad3c 100644 --- a/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c +++ b/tools/testing/selftests/powerpc/pmu/sampling_tests/mmcra_thresh_marked_sample_test.c @@ -63,9 +63,9 @@ static int mmcra_thresh_marked_sample(void) get_mmcra_thd_stop(get_reg_value(intr_regs, "MMCRA"), 4)); FAIL_IF(EV_CODE_EXTRACT(event.attr.config, marked) != get_mmcra_marked(get_reg_value(intr_regs, "MMCRA"), 4)); - FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample >> 2) != + FAIL_IF((EV_CODE_EXTRACT(event.attr.config, sample) >> 2) != get_mmcra_rand_samp_elig(get_reg_value(intr_regs, "MMCRA"), 4)); - FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sample & 0x3) != + FAIL_IF((EV_CODE_EXTRACT(event.attr.config, sample) & 0x3) != get_mmcra_sample_mode(get_reg_value(intr_regs, "MMCRA"), 4)); FAIL_IF(EV_CODE_EXTRACT(event.attr.config, sm) != get_mmcra_sm(get_reg_value(intr_regs, "MMCRA"), 4)); -- GitLab From d1c5accacb234c3a9f1609a73b4b2eaa4ef07d1a Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 15 Feb 2023 11:41:15 -0700 Subject: [PATCH 0458/5631] powerpc/boot: Only use '-mabi=elfv2' with CONFIG_PPC64_BOOT_WRAPPER When CONFIG_PPC64_ELF_ABI_V2 is enabled with clang through CONFIG_PPC64_BIG_ENDIAN_ELF_ABI_V2, building the powerpc boot wrapper in 32-bit mode (i.e. with CONFIG_PPC64_BOOT_WRAPPER=n) fails with: error: unknown target ABI 'elfv2' The ABI cannot be changed with '-m32'; GCC silently accepts it but clang errors out. Only provide '-mabi=elfv2' when CONFIG_PPC64_BOOT_WRAPPER is enabled, which is the only way '-mabi=elfv2' will be useful. Tested-by: "Erhard F." Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230118-ppc64-elfv2-llvm-v1-1-b9e2ec9da11d@kernel.org --- arch/powerpc/boot/Makefile | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 295f76df13b5..08071bac056d 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -40,6 +40,9 @@ BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ ifdef CONFIG_PPC64_BOOT_WRAPPER BOOTCFLAGS += -m64 +ifdef CONFIG_PPC64_ELF_ABI_V2 +BOOTCFLAGS += $(call cc-option,-mabi=elfv2) +endif else BOOTCFLAGS += -m32 endif @@ -61,9 +64,6 @@ BOOTCFLAGS += -mbig-endian else BOOTCFLAGS += -mlittle-endian endif -ifdef CONFIG_PPC64_ELF_ABI_V2 -BOOTCFLAGS += $(call cc-option,-mabi=elfv2) -endif BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc -- GitLab From 7c3bd8362b06cff0a4044a4975adb7d71db2dfba Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 15 Feb 2023 11:41:16 -0700 Subject: [PATCH 0459/5631] powerpc: Fix use of '-mabi=elfv2' with clang '-mabi=elfv2' is not added to clang's invocations when CONFIG_PPC64_ELF_ABI_V2 is enabled, resulting in the generation of elfv1 code, as evidenced by the orphan section warnings/errors: ld.lld: error: vmlinux.a(arch/powerpc/kernel/prom_init.o):(.opd) is being placed in '.opd' ld.lld: error: vmlinux.a(init/main.o):(.opd) is being placed in '.opd' ld.lld: error: vmlinux.a(init/version.o):(.opd) is being placed in '.opd' To resolve this, add '-mabi=elfv2' to CFLAGS with clang. This uncovers an issue in the 32-bit vDSO: error: unknown target ABI 'elfv2' The ELFv2 ABI cannot be used when building code for a 32-bit target. To resolve this, just remove the '-mabi' flags from the assembler flags, as it was only needed for preprocessing (the _CALL_ELF macro) but this was cleaned up in commit 5b89492c03e5 ("powerpc: Finalise cleanup around ABI use"). Tested-by: "Erhard F." Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230118-ppc64-elfv2-llvm-v1-2-b9e2ec9da11d@kernel.org --- arch/powerpc/Makefile | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index e91d7e91347d..12447b2361e4 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -123,14 +123,12 @@ endif endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) -ifndef CONFIG_CC_IS_CLANG ifdef CONFIG_PPC64_ELF_ABI_V2 CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc)) -AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv2) else +ifndef CONFIG_CC_IS_CLANG CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) -AFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) endif endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) -- GitLab From a11334d8327b3fd7987cbfb38e956a44c722d88f Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 15 Feb 2023 11:41:17 -0700 Subject: [PATCH 0460/5631] powerpc: Allow CONFIG_PPC64_BIG_ENDIAN_ELF_ABI_V2 with ld.lld 15+ Commit 5017b4594672 ("powerpc/64: Option to build big-endian with ELFv2 ABI") restricted the ELFv2 ABI configuration such that it can only be selected when linking with ld.bfd, due to lack of testing with LLVM. ld.lld can link ELFv2 kernels without any issues; in fact, it is the only ABI that ld.lld supports, as ELFv1 is not supported in ld.lld. As this has not seen a ton of real world testing yet, be conservative and only allow this option to be selected with the latest stable release of LLVM (15.x) and newer. While in the area, remove 'default n', as it is unnecessary to specify it explicitly since all boolean/tristate configuration symbols default to n. Tested-by: "Erhard F." Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230118-ppc64-elfv2-llvm-v1-3-b9e2ec9da11d@kernel.org --- arch/powerpc/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a6c4407d3ec8..47017975fc2b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -616,8 +616,7 @@ config PPC64_BIG_ENDIAN_ELF_ABI_V2 bool "Build big-endian kernel using ELF ABI V2 (EXPERIMENTAL)" depends on PPC64 && CPU_BIG_ENDIAN depends on CC_HAS_ELFV2 - depends on LD_IS_BFD && LD_VERSION >= 22400 - default n + depends on LD_VERSION >= 22400 || LLD_VERSION >= 150000 help This builds the kernel image using the "Power Architecture 64-Bit ELF V2 ABI Specification", which has a reduced stack overhead and faster -- GitLab From 35e175bdd52e75d4f9b1a6b3cea870c728acf344 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:44 +0100 Subject: [PATCH 0461/5631] powerpc/machdep: Make machine name const Machine name in struct machdep_calls should never be modified. Mark it const. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/machdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 459736d5e511..41815168a452 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -20,7 +20,7 @@ struct kimage; struct pci_host_bridge; struct machdep_calls { - char *name; + const char *name; #ifdef CONFIG_PPC64 #ifdef CONFIG_PM void (*iommu_restore)(void); -- GitLab From 2fc39acfcacf3dc1392d8062f6d7b7d94eb2537c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:45 +0100 Subject: [PATCH 0462/5631] powerpc/machdep: Define 'compatible' property in ppc_md and use it Most probe functions do nothing else than checking whether the machine is compatible to a given string. Define that string in ppc_md structure and check it directly from probe_machine() instead of using ppc_md.probe() for that. Keep checking in ppc_md.probe() only for more complex probing. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/machdep.h | 1 + arch/powerpc/kernel/setup-common.c | 13 +++++++------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 41815168a452..4f6e7d7ee388 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -21,6 +21,7 @@ struct pci_host_bridge; struct machdep_calls { const char *name; + const char *compatible; #ifdef CONFIG_PPC64 #ifdef CONFIG_PM void (*iommu_restore)(void); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index e77734e5a127..d2a446216444 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -630,13 +630,14 @@ static __init void probe_machine(void) for (machine_id = &__machine_desc_start; machine_id < &__machine_desc_end; machine_id++) { - DBG(" %s ...", machine_id->name); + DBG(" %s ...\n", machine_id->name); + if (machine_id->compatible && !of_machine_is_compatible(machine_id->compatible)) + continue; memcpy(&ppc_md, machine_id, sizeof(struct machdep_calls)); - if (ppc_md.probe()) { - DBG(" match !\n"); - break; - } - DBG("\n"); + if (ppc_md.probe && !ppc_md.probe()) + continue; + DBG(" %s match !\n", machine_id->name); + break; } /* What can we do if we didn't find ? */ if (machine_id >= &__machine_desc_end) { -- GitLab From 1c96fcdef8c7492ecf34ed70102a1ae5253ef9d1 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:46 +0100 Subject: [PATCH 0463/5631] powerpc/platforms: Use 'compatible' property for simple cases Use the new 'compatible' property for simple cases. checkpatch complains about the new compatible being undocumented but in reality nothing is new so just ignore it for the time being. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/platforms/44x/canyonlands.c | 9 +-- arch/powerpc/platforms/44x/ebony.c | 4 +- arch/powerpc/platforms/44x/iss4xx.c | 13 +-- arch/powerpc/platforms/44x/sam440ep.c | 4 +- arch/powerpc/platforms/44x/warp.c | 10 +-- arch/powerpc/platforms/512x/mpc5121_ads.c | 4 +- arch/powerpc/platforms/512x/pdm360ng.c | 4 +- arch/powerpc/platforms/52xx/media5200.c | 16 +--- arch/powerpc/platforms/82xx/ep8248e.c | 10 +-- arch/powerpc/platforms/82xx/km82xx.c | 10 +-- arch/powerpc/platforms/82xx/mpc8272_ads.c | 10 +-- arch/powerpc/platforms/82xx/pq2fads.c | 10 +-- arch/powerpc/platforms/83xx/asp834x.c | 10 +-- arch/powerpc/platforms/83xx/mpc832x_mds.c | 10 +-- arch/powerpc/platforms/83xx/mpc832x_rdb.c | 10 +-- arch/powerpc/platforms/83xx/mpc834x_itx.c | 10 +-- arch/powerpc/platforms/83xx/mpc834x_mds.c | 10 +-- arch/powerpc/platforms/83xx/mpc836x_mds.c | 10 +-- arch/powerpc/platforms/83xx/mpc836x_rdk.c | 10 +-- arch/powerpc/platforms/83xx/mpc837x_mds.c | 10 +-- arch/powerpc/platforms/85xx/bsc913x_qds.c | 11 +-- arch/powerpc/platforms/85xx/bsc913x_rdb.c | 11 +-- arch/powerpc/platforms/85xx/c293pcie.c | 12 +-- arch/powerpc/platforms/85xx/ge_imp3a.c | 10 +-- arch/powerpc/platforms/85xx/ksi8560.c | 10 +-- arch/powerpc/platforms/85xx/mpc8536_ds.c | 10 +-- arch/powerpc/platforms/85xx/mpc85xx_ads.c | 10 +-- arch/powerpc/platforms/85xx/mpc85xx_cds.c | 11 +-- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 30 +------ arch/powerpc/platforms/85xx/mpc85xx_mds.c | 22 +---- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 81 +++---------------- arch/powerpc/platforms/85xx/mvme2500.c | 10 +-- arch/powerpc/platforms/85xx/p1022_ds.c | 10 +-- arch/powerpc/platforms/85xx/p1022_rdk.c | 10 +-- arch/powerpc/platforms/85xx/p1023_rdb.c | 8 +- arch/powerpc/platforms/85xx/ppa8548.c | 10 +-- arch/powerpc/platforms/85xx/qemu_e500.c | 10 +-- arch/powerpc/platforms/85xx/socrates.c | 13 +-- arch/powerpc/platforms/85xx/stx_gp3.c | 10 +-- arch/powerpc/platforms/85xx/twr_p102x.c | 7 +- arch/powerpc/platforms/85xx/xes_mpc85xx.c | 24 +----- arch/powerpc/platforms/86xx/gef_ppc9a.c | 18 +---- arch/powerpc/platforms/86xx/gef_sbc310.c | 18 +---- arch/powerpc/platforms/86xx/gef_sbc610.c | 18 +---- arch/powerpc/platforms/86xx/mpc8610_hpcd.c | 13 +-- arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 14 +--- arch/powerpc/platforms/8xx/adder875.c | 7 +- arch/powerpc/platforms/8xx/ep88xc.c | 7 +- arch/powerpc/platforms/8xx/mpc86xads_setup.c | 7 +- arch/powerpc/platforms/8xx/mpc885ads_setup.c | 7 +- arch/powerpc/platforms/8xx/tqm8xx_setup.c | 7 +- arch/powerpc/platforms/amigaone/setup.c | 21 +++-- arch/powerpc/platforms/embedded6xx/gamecube.c | 4 +- arch/powerpc/platforms/embedded6xx/holly.c | 12 +-- .../platforms/embedded6xx/linkstation.c | 4 +- .../platforms/embedded6xx/mpc7448_hpc2.c | 12 +-- arch/powerpc/platforms/embedded6xx/mvme5100.c | 10 +-- .../platforms/embedded6xx/storcenter.c | 7 +- arch/powerpc/platforms/embedded6xx/wii.c | 4 +- arch/powerpc/platforms/microwatt/setup.c | 7 +- arch/powerpc/platforms/powernv/setup.c | 4 +- arch/powerpc/platforms/ps3/setup.c | 4 +- 62 files changed, 88 insertions(+), 631 deletions(-) diff --git a/arch/powerpc/platforms/44x/canyonlands.c b/arch/powerpc/platforms/44x/canyonlands.c index 5b23aef8bdef..ba561ca6c25f 100644 --- a/arch/powerpc/platforms/44x/canyonlands.c +++ b/arch/powerpc/platforms/44x/canyonlands.c @@ -39,11 +39,9 @@ machine_device_initcall(canyonlands, ppc460ex_device_probe); static int __init ppc460ex_probe(void) { - if (of_machine_is_compatible("amcc,canyonlands")) { - pci_set_flags(PCI_REASSIGN_ALL_RSRC); - return 1; - } - return 0; + pci_set_flags(PCI_REASSIGN_ALL_RSRC); + + return 1; } /* USB PHY fixup code on Canyonlands kit. */ @@ -110,6 +108,7 @@ static int __init ppc460ex_canyonlands_fixup(void) machine_device_initcall(canyonlands, ppc460ex_canyonlands_fixup); define_machine(canyonlands) { .name = "Canyonlands", + .compatible = "amcc,canyonlands", .probe = ppc460ex_probe, .progress = udbg_progress, .init_IRQ = uic_init_tree, diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c index 0d8f202bc45f..5b9e57b4cd65 100644 --- a/arch/powerpc/platforms/44x/ebony.c +++ b/arch/powerpc/platforms/44x/ebony.c @@ -45,9 +45,6 @@ machine_device_initcall(ebony, ebony_device_probe); */ static int __init ebony_probe(void) { - if (!of_machine_is_compatible("ibm,ebony")) - return 0; - pci_set_flags(PCI_REASSIGN_ALL_RSRC); return 1; @@ -55,6 +52,7 @@ static int __init ebony_probe(void) define_machine(ebony) { .name = "Ebony", + .compatible = "ibm,ebony", .probe = ebony_probe, .progress = udbg_progress, .init_IRQ = uic_init_tree, diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c index c5f82591408c..e779bd3d2291 100644 --- a/arch/powerpc/platforms/44x/iss4xx.c +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -140,20 +140,9 @@ static void __init iss4xx_setup_arch(void) iss4xx_smp_init(); } -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init iss4xx_probe(void) -{ - if (!of_machine_is_compatible("ibm,iss-4xx")) - return 0; - - return 1; -} - define_machine(iss4xx) { .name = "ISS-4xx", - .probe = iss4xx_probe, + .compatible = "ibm,iss-4xx", .progress = udbg_progress, .init_IRQ = iss4xx_init_irq, .setup_arch = iss4xx_setup_arch, diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c index ed854b53877e..8b281e027477 100644 --- a/arch/powerpc/platforms/44x/sam440ep.c +++ b/arch/powerpc/platforms/44x/sam440ep.c @@ -41,9 +41,6 @@ machine_device_initcall(sam440ep, sam440ep_device_probe); static int __init sam440ep_probe(void) { - if (!of_machine_is_compatible("acube,sam440ep")) - return 0; - pci_set_flags(PCI_REASSIGN_ALL_RSRC); return 1; @@ -51,6 +48,7 @@ static int __init sam440ep_probe(void) define_machine(sam440ep) { .name = "Sam440ep", + .compatible = "acube,sam440ep", .probe = sam440ep_probe, .progress = udbg_progress, .init_IRQ = uic_init_tree, diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index cefa313c09f0..acbc356e8a19 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -41,17 +41,9 @@ static int __init warp_device_probe(void) } machine_device_initcall(warp, warp_device_probe); -static int __init warp_probe(void) -{ - if (!of_machine_is_compatible("pika,warp")) - return 0; - - return 1; -} - define_machine(warp) { .name = "Warp", - .probe = warp_probe, + .compatible = "pika,warp", .progress = udbg_progress, .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c index fc3fb999cd74..0b6a2d3fd343 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads.c @@ -53,9 +53,6 @@ static void __init mpc5121_ads_init_IRQ(void) */ static int __init mpc5121_ads_probe(void) { - if (!of_machine_is_compatible("fsl,mpc5121ads")) - return 0; - mpc512x_init_early(); return 1; @@ -63,6 +60,7 @@ static int __init mpc5121_ads_probe(void) define_machine(mpc5121_ads) { .name = "MPC5121 ADS", + .compatible = "fsl,mpc5121ads", .probe = mpc5121_ads_probe, .setup_arch = mpc5121_ads_setup_arch, .discover_phbs = mpc5121_ads_setup_pci, diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c index 1e911f42697d..d3a4eeb47bb1 100644 --- a/arch/powerpc/platforms/512x/pdm360ng.c +++ b/arch/powerpc/platforms/512x/pdm360ng.c @@ -108,9 +108,6 @@ void __init pdm360ng_init(void) static int __init pdm360ng_probe(void) { - if (!of_machine_is_compatible("ifm,pdm360ng")) - return 0; - mpc512x_init_early(); return 1; @@ -118,6 +115,7 @@ static int __init pdm360ng_probe(void) define_machine(pdm360ng) { .name = "PDM360NG", + .compatible = "ifm,pdm360ng", .probe = pdm360ng_probe, .setup_arch = mpc512x_setup_arch, .init = pdm360ng_init, diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index 33a35fff11b5..a9c92c6ccbcf 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -227,23 +227,9 @@ static void __init media5200_setup_arch(void) } -/* list of the supported boards */ -static const char * const board[] __initconst = { - "fsl,media5200", - NULL -}; - -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init media5200_probe(void) -{ - return of_device_compatible_match(of_root, board); -} - define_machine(media5200_platform) { .name = "media5200-platform", - .probe = media5200_probe, + .compatible = "fsl,media5200", .setup_arch = media5200_setup_arch, .discover_phbs = mpc52xx_setup_pci, .init = mpc52xx_declare_of_platform_devices, diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index 28e627f8a320..66defdaf816f 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -301,18 +301,10 @@ static int __init declare_of_platform_devices(void) } machine_device_initcall(ep8248e, declare_of_platform_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init ep8248e_probe(void) -{ - return of_machine_is_compatible("fsl,ep8248e"); -} - define_machine(ep8248e) { .name = "Embedded Planet EP8248E", - .probe = ep8248e_probe, + .compatible = "fsl,ep8248e", .setup_arch = ep8248e_setup_arch, .init_IRQ = ep8248e_pic_init, .get_irq = cpm2_get_irq, diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index 1c8bbf4251d9..8ab575d70080 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -188,18 +188,10 @@ static int __init declare_of_platform_devices(void) } machine_device_initcall(km82xx, declare_of_platform_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init km82xx_probe(void) -{ - return of_machine_is_compatible("keymile,km82xx"); -} - define_machine(km82xx) { .name = "Keymile km82xx", - .probe = km82xx_probe, + .compatible = "keymile,km82xx", .setup_arch = km82xx_setup_arch, .init_IRQ = km82xx_pic_init, .get_irq = cpm2_get_irq, diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c index 0b5b9dec16d5..5dd034ed2c87 100644 --- a/arch/powerpc/platforms/82xx/mpc8272_ads.c +++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c @@ -191,18 +191,10 @@ static int __init declare_of_platform_devices(void) } machine_device_initcall(mpc8272_ads, declare_of_platform_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc8272_ads_probe(void) -{ - return of_machine_is_compatible("fsl,mpc8272ads"); -} - define_machine(mpc8272_ads) { .name = "Freescale MPC8272 ADS", - .probe = mpc8272_ads_probe, + .compatible = "fsl,mpc8272ads", .setup_arch = mpc8272_ads_setup_arch, .discover_phbs = pq2_init_pci, .init_IRQ = mpc8272_ads_pic_init, diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c index ac9113d524af..d91dfdc634e9 100644 --- a/arch/powerpc/platforms/82xx/pq2fads.c +++ b/arch/powerpc/platforms/82xx/pq2fads.c @@ -154,14 +154,6 @@ static void __init pq2fads_setup_arch(void) ppc_md.progress("pq2fads_setup_arch(), finish", 0); } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init pq2fads_probe(void) -{ - return of_machine_is_compatible("fsl,pq2fads"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .name = "soc", }, { .name = "cpm", }, @@ -180,7 +172,7 @@ machine_device_initcall(pq2fads, declare_of_platform_devices); define_machine(pq2fads) { .name = "Freescale PQ2FADS", - .probe = pq2fads_probe, + .compatible = "fsl,pq2fads", .setup_arch = pq2fads_setup_arch, .discover_phbs = pq2_init_pci, .init_IRQ = pq2fads_pic_init, diff --git a/arch/powerpc/platforms/83xx/asp834x.c b/arch/powerpc/platforms/83xx/asp834x.c index 68061c2a57c1..8f3d995027fe 100644 --- a/arch/powerpc/platforms/83xx/asp834x.c +++ b/arch/powerpc/platforms/83xx/asp834x.c @@ -32,17 +32,9 @@ static void __init asp834x_setup_arch(void) machine_device_initcall(asp834x, mpc83xx_declare_of_platform_devices); -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init asp834x_probe(void) -{ - return of_machine_is_compatible("analogue-and-micro,asp8347e"); -} - define_machine(asp834x) { .name = "ASP8347E", - .probe = asp834x_probe, + .compatible = "analogue-and-micro,asp8347e", .setup_arch = asp834x_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index 435344405d2c..01035eff7d2e 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -88,17 +88,9 @@ static void __init mpc832x_sys_setup_arch(void) machine_device_initcall(mpc832x_mds, mpc83xx_declare_of_platform_devices); -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc832x_sys_probe(void) -{ - return of_machine_is_compatible("MPC832xMDS"); -} - define_machine(mpc832x_mds) { .name = "MPC832x MDS", - .probe = mpc832x_sys_probe, + .compatible = "MPC832xMDS", .setup_arch = mpc832x_sys_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index caa96edf0e72..6b7b852e48bf 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -212,17 +212,9 @@ static void __init mpc832x_rdb_setup_arch(void) machine_device_initcall(mpc832x_rdb, mpc83xx_declare_of_platform_devices); -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc832x_rdb_probe(void) -{ - return of_machine_is_compatible("MPC832xRDB"); -} - define_machine(mpc832x_rdb) { .name = "MPC832x RDB", - .probe = mpc832x_rdb_probe, + .compatible = "MPC832xRDB", .setup_arch = mpc832x_rdb_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c index 6a110f275304..92ff7be472c3 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_itx.c +++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c @@ -57,17 +57,9 @@ static void __init mpc834x_itx_setup_arch(void) mpc834x_usb_cfg(); } -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc834x_itx_probe(void) -{ - return of_machine_is_compatible("MPC834xMITX"); -} - define_machine(mpc834x_itx) { .name = "MPC834x ITX", - .probe = mpc834x_itx_probe, + .compatible = "MPC834xMITX", .setup_arch = mpc834x_itx_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c index 7dde5a75332b..8e45c034daaf 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c @@ -79,17 +79,9 @@ static void __init mpc834x_mds_setup_arch(void) machine_device_initcall(mpc834x_mds, mpc83xx_declare_of_platform_devices); -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc834x_mds_probe(void) -{ - return of_machine_is_compatible("MPC834xMDS"); -} - define_machine(mpc834x_mds) { .name = "MPC834x MDS", - .probe = mpc834x_mds_probe, + .compatible = "MPC834xMDS", .setup_arch = mpc834x_mds_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index b1e6665be5d3..4ae2b6e4b513 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -188,17 +188,9 @@ static int __init mpc836x_usb_cfg(void) machine_arch_initcall(mpc836x_mds, mpc836x_usb_cfg); #endif /* CONFIG_QE_USB */ -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc836x_mds_probe(void) -{ - return of_machine_is_compatible("MPC836xMDS"); -} - define_machine(mpc836x_mds) { .name = "MPC836x MDS", - .probe = mpc836x_mds_probe, + .compatible = "MPC836xMDS", .setup_arch = mpc836x_mds_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c index 731bc5ce726d..231a5df0399b 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c +++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c @@ -28,17 +28,9 @@ static void __init mpc836x_rdk_setup_arch(void) mpc83xx_setup_arch(); } -/* - * Called very early, MMU is off, device-tree isn't unflattened. - */ -static int __init mpc836x_rdk_probe(void) -{ - return of_machine_is_compatible("fsl,mpc8360rdk"); -} - define_machine(mpc836x_rdk) { .name = "MPC836x RDK", - .probe = mpc836x_rdk_probe, + .compatible = "fsl,mpc8360rdk", .setup_arch = mpc836x_rdk_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c index fa3538803af7..0c10100756d4 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c @@ -81,17 +81,9 @@ static void __init mpc837x_mds_setup_arch(void) machine_device_initcall(mpc837x_mds, mpc83xx_declare_of_platform_devices); -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init mpc837x_mds_probe(void) -{ - return of_machine_is_compatible("fsl,mpc837xmds"); -} - define_machine(mpc837x_mds) { .name = "MPC837x MDS", - .probe = mpc837x_mds_probe, + .compatible = "fsl,mpc837xmds", .setup_arch = mpc837x_mds_setup_arch, .discover_phbs = mpc83xx_setup_pci, .init_IRQ = mpc83xx_ipic_init_IRQ, diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c index bcbbeb5a972a..902a867352c2 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_qds.c +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -50,18 +50,9 @@ static void __init bsc913x_qds_setup_arch(void) machine_arch_initcall(bsc9132_qds, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ - -static int __init bsc9132_qds_probe(void) -{ - return of_machine_is_compatible("fsl,bsc9132qds"); -} - define_machine(bsc9132_qds) { .name = "BSC9132 QDS", - .probe = bsc9132_qds_probe, + .compatible = "fsl,bsc9132qds", .setup_arch = bsc913x_qds_setup_arch, .init_IRQ = bsc913x_qds_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c index f78e5d3deedb..58a44953b936 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c +++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c @@ -40,18 +40,9 @@ static void __init bsc913x_rdb_setup_arch(void) machine_device_initcall(bsc9131_rdb, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ - -static int __init bsc9131_rdb_probe(void) -{ - return of_machine_is_compatible("fsl,bsc9131rdb"); -} - define_machine(bsc9131_rdb) { .name = "BSC9131 RDB", - .probe = bsc9131_rdb_probe, + .compatible = "fsl,bsc9131rdb", .setup_arch = bsc913x_rdb_setup_arch, .init_IRQ = bsc913x_rdb_pic_init, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c index 58a398c89e97..fbf1875e5835 100644 --- a/arch/powerpc/platforms/85xx/c293pcie.c +++ b/arch/powerpc/platforms/85xx/c293pcie.c @@ -45,19 +45,9 @@ static void __init c293_pcie_setup_arch(void) machine_arch_initcall(c293_pcie, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init c293_pcie_probe(void) -{ - if (of_machine_is_compatible("fsl,C293PCIE")) - return 1; - return 0; -} - define_machine(c293_pcie) { .name = "C293 PCIE", - .probe = c293_pcie_probe, + .compatible = "fsl,C293PCIE", .setup_arch = c293_pcie_setup_arch, .init_IRQ = c293_pcie_pic_init, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index e3e8f18825a1..1bfd4ea13038 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -190,19 +190,11 @@ static void ge_imp3a_show_cpuinfo(struct seq_file *m) ge_imp3a_get_cpci_is_syscon() ? "yes" : "no"); } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init ge_imp3a_probe(void) -{ - return of_machine_is_compatible("ge,IMP3A"); -} - machine_arch_initcall(ge_imp3a, mpc85xx_common_publish_devices); define_machine(ge_imp3a) { .name = "GE_IMP3A", - .probe = ge_imp3a_probe, + .compatible = "ge,IMP3A", .setup_arch = ge_imp3a_setup_arch, .init_IRQ = ge_imp3a_pic_init, .show_cpuinfo = ge_imp3a_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c index a22f02b0fc77..548d478e5194 100644 --- a/arch/powerpc/platforms/85xx/ksi8560.c +++ b/arch/powerpc/platforms/85xx/ksi8560.c @@ -172,17 +172,9 @@ static void ksi8560_show_cpuinfo(struct seq_file *m) machine_device_initcall(ksi8560, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init ksi8560_probe(void) -{ - return of_machine_is_compatible("emerson,KSI8560"); -} - define_machine(ksi8560) { .name = "KSI8560", - .probe = ksi8560_probe, + .compatible = "emerson,KSI8560", .setup_arch = ksi8560_setup_arch, .init_IRQ = ksi8560_pic_init, .show_cpuinfo = ksi8560_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index e5d7386ad612..9900cf2cd392 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -52,17 +52,9 @@ static void __init mpc8536_ds_setup_arch(void) machine_arch_initcall(mpc8536_ds, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc8536_ds_probe(void) -{ - return of_machine_is_compatible("fsl,mpc8536ds"); -} - define_machine(mpc8536_ds) { .name = "MPC8536 DS", - .probe = mpc8536_ds_probe, + .compatible = "fsl,mpc8536ds", .setup_arch = mpc8536_ds_setup_arch, .init_IRQ = mpc8536_ds_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c index a34fc037957d..dd5302ab406d 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -151,17 +151,9 @@ static void mpc85xx_ads_show_cpuinfo(struct seq_file *m) machine_arch_initcall(mpc85xx_ads, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc85xx_ads_probe(void) -{ - return of_machine_is_compatible("MPC85xxADS"); -} - define_machine(mpc85xx_ads) { .name = "MPC85xx ADS", - .probe = mpc85xx_ads_probe, + .compatible = "MPC85xxADS", .setup_arch = mpc85xx_ads_setup_arch, .init_IRQ = mpc85xx_ads_pic_init, .show_cpuinfo = mpc85xx_ads_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index 0b8f2101c5fb..d7568b35ec78 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -370,20 +370,11 @@ static void mpc85xx_cds_show_cpuinfo(struct seq_file *m) seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f)); } - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc85xx_cds_probe(void) -{ - return of_machine_is_compatible("MPC85xxCDS"); -} - machine_arch_initcall(mpc85xx_cds, mpc85xx_common_publish_devices); define_machine(mpc85xx_cds) { .name = "MPC85xx CDS", - .probe = mpc85xx_cds_probe, + .compatible = "MPC85xxCDS", .setup_arch = mpc85xx_cds_setup_arch, .init_IRQ = mpc85xx_cds_pic_init, .show_cpuinfo = mpc85xx_cds_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index f8d2c97f39bd..b4feb251b57e 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -158,37 +158,13 @@ static void __init mpc85xx_ds_setup_arch(void) printk("MPC85xx DS board from Freescale Semiconductor\n"); } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc8544_ds_probe(void) -{ - return !!of_machine_is_compatible("MPC8544DS"); -} - machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices); machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices); machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc8572_ds_probe(void) -{ - return !!of_machine_is_compatible("fsl,MPC8572DS"); -} - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p2020_ds_probe(void) -{ - return !!of_machine_is_compatible("fsl,P2020DS"); -} - define_machine(mpc8544_ds) { .name = "MPC8544 DS", - .probe = mpc8544_ds_probe, + .compatible = "MPC8544DS", .setup_arch = mpc85xx_ds_setup_arch, .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI @@ -202,7 +178,7 @@ define_machine(mpc8544_ds) { define_machine(mpc8572_ds) { .name = "MPC8572 DS", - .probe = mpc8572_ds_probe, + .compatible = "fsl,MPC8572DS", .setup_arch = mpc85xx_ds_setup_arch, .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI @@ -216,7 +192,7 @@ define_machine(mpc8572_ds) { define_machine(p2020_ds) { .name = "P2020 DS", - .probe = p2020_ds_probe, + .compatible = "fsl,P2020DS", .setup_arch = mpc85xx_ds_setup_arch, .init_IRQ = mpc85xx_ds_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 3a2ac410af18..721322e04c79 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -339,14 +339,9 @@ static void __init mpc85xx_mds_pic_init(void) mpic_init(mpic); } -static int __init mpc85xx_mds_probe(void) -{ - return of_machine_is_compatible("MPC85xxMDS"); -} - define_machine(mpc8568_mds) { .name = "MPC8568 MDS", - .probe = mpc85xx_mds_probe, + .compatible = "MPC85xxMDS", .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, @@ -358,14 +353,9 @@ define_machine(mpc8568_mds) { #endif }; -static int __init mpc8569_mds_probe(void) -{ - return of_machine_is_compatible("fsl,MPC8569EMDS"); -} - define_machine(mpc8569_mds) { .name = "MPC8569 MDS", - .probe = mpc8569_mds_probe, + .compatible = "fsl,MPC8569EMDS", .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, @@ -377,15 +367,9 @@ define_machine(mpc8569_mds) { #endif }; -static int __init p1021_mds_probe(void) -{ - return of_machine_is_compatible("fsl,P1021MDS"); - -} - define_machine(p1021_mds) { .name = "P1021 MDS", - .probe = p1021_mds_probe, + .compatible = "fsl,P1021MDS", .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index d99aba158235..9754feaebcd4 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -119,70 +119,9 @@ machine_arch_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1025_rdb, mpc85xx_common_publish_devices); machine_arch_initcall(p1024_rdb, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p2020_rdb_probe(void) -{ - if (of_machine_is_compatible("fsl,P2020RDB")) - return 1; - return 0; -} - -static int __init p1020_rdb_probe(void) -{ - if (of_machine_is_compatible("fsl,P1020RDB")) - return 1; - return 0; -} - -static int __init p1020_rdb_pc_probe(void) -{ - return of_machine_is_compatible("fsl,P1020RDB-PC"); -} - -static int __init p1020_rdb_pd_probe(void) -{ - return of_machine_is_compatible("fsl,P1020RDB-PD"); -} - -static int __init p1021_rdb_pc_probe(void) -{ - if (of_machine_is_compatible("fsl,P1021RDB-PC")) - return 1; - return 0; -} - -static int __init p2020_rdb_pc_probe(void) -{ - if (of_machine_is_compatible("fsl,P2020RDB-PC")) - return 1; - return 0; -} - -static int __init p1025_rdb_probe(void) -{ - return of_machine_is_compatible("fsl,P1025RDB"); -} - -static int __init p1020_mbg_pc_probe(void) -{ - return of_machine_is_compatible("fsl,P1020MBG-PC"); -} - -static int __init p1020_utm_pc_probe(void) -{ - return of_machine_is_compatible("fsl,P1020UTM-PC"); -} - -static int __init p1024_rdb_probe(void) -{ - return of_machine_is_compatible("fsl,P1024RDB"); -} - define_machine(p2020_rdb) { .name = "P2020 RDB", - .probe = p2020_rdb_probe, + .compatible = "fsl,P2020RDB", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -196,7 +135,7 @@ define_machine(p2020_rdb) { define_machine(p1020_rdb) { .name = "P1020 RDB", - .probe = p1020_rdb_probe, + .compatible = "fsl,P1020RDB", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -210,7 +149,7 @@ define_machine(p1020_rdb) { define_machine(p1021_rdb_pc) { .name = "P1021 RDB-PC", - .probe = p1021_rdb_pc_probe, + .compatible = "fsl,P1021RDB-PC", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -224,7 +163,7 @@ define_machine(p1021_rdb_pc) { define_machine(p2020_rdb_pc) { .name = "P2020RDB-PC", - .probe = p2020_rdb_pc_probe, + .compatible = "fsl,P2020RDB-PC", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -238,7 +177,7 @@ define_machine(p2020_rdb_pc) { define_machine(p1025_rdb) { .name = "P1025 RDB", - .probe = p1025_rdb_probe, + .compatible = "fsl,P1025RDB", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -252,7 +191,7 @@ define_machine(p1025_rdb) { define_machine(p1020_mbg_pc) { .name = "P1020 MBG-PC", - .probe = p1020_mbg_pc_probe, + .compatible = "fsl,P1020MBG-PC", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -266,7 +205,7 @@ define_machine(p1020_mbg_pc) { define_machine(p1020_utm_pc) { .name = "P1020 UTM-PC", - .probe = p1020_utm_pc_probe, + .compatible = "fsl,P1020UTM-PC", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -280,7 +219,7 @@ define_machine(p1020_utm_pc) { define_machine(p1020_rdb_pc) { .name = "P1020RDB-PC", - .probe = p1020_rdb_pc_probe, + .compatible = "fsl,P1020RDB-PC", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -294,7 +233,7 @@ define_machine(p1020_rdb_pc) { define_machine(p1020_rdb_pd) { .name = "P1020RDB-PD", - .probe = p1020_rdb_pd_probe, + .compatible = "fsl,P1020RDB-PD", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI @@ -308,7 +247,7 @@ define_machine(p1020_rdb_pd) { define_machine(p1024_rdb) { .name = "P1024 RDB", - .probe = p1024_rdb_probe, + .compatible = "fsl,P1024RDB", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c index 69d5aa082a4b..ee1383e811d9 100644 --- a/arch/powerpc/platforms/85xx/mvme2500.c +++ b/arch/powerpc/platforms/85xx/mvme2500.c @@ -43,17 +43,9 @@ static void __init mvme2500_setup_arch(void) machine_arch_initcall(mvme2500, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mvme2500_probe(void) -{ - return of_machine_is_compatible("artesyn,MVME2500"); -} - define_machine(mvme2500) { .name = "MVME2500", - .probe = mvme2500_probe, + .compatible = "artesyn,MVME2500", .setup_arch = mvme2500_setup_arch, .init_IRQ = mvme2500_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 537599906146..15a684ce9201 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -549,17 +549,9 @@ static void __init p1022_ds_setup_arch(void) machine_arch_initcall(p1022_ds, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p1022_ds_probe(void) -{ - return of_machine_is_compatible("fsl,p1022ds"); -} - define_machine(p1022_ds) { .name = "P1022 DS", - .probe = p1022_ds_probe, + .compatible = "fsl,p1022ds", .setup_arch = p1022_ds_setup_arch, .init_IRQ = p1022_ds_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index bc58a99164c9..aee9ffc0eb17 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -129,17 +129,9 @@ static void __init p1022_rdk_setup_arch(void) machine_arch_initcall(p1022_rdk, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init p1022_rdk_probe(void) -{ - return of_machine_is_compatible("fsl,p1022rdk"); -} - define_machine(p1022_rdk) { .name = "P1022 RDK", - .probe = p1022_rdk_probe, + .compatible = "fsl,p1022rdk", .setup_arch = p1022_rdk_setup_arch, .init_IRQ = p1022_rdk_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index c04868eb2eb1..37e78f40d424 100644 --- a/arch/powerpc/platforms/85xx/p1023_rdb.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -94,15 +94,9 @@ static void __init mpc85xx_rdb_pic_init(void) mpic_init(mpic); } -static int __init p1023_rdb_probe(void) -{ - return of_machine_is_compatible("fsl,P1023RDB"); - -} - define_machine(p1023_rdb) { .name = "P1023 RDB", - .probe = p1023_rdb_probe, + .compatible = "fsl,P1023RDB", .setup_arch = mpc85xx_rdb_setup_arch, .init_IRQ = mpc85xx_rdb_pic_init, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c index 0faf2990bf2c..b030d0e7b06b 100644 --- a/arch/powerpc/platforms/85xx/ppa8548.c +++ b/arch/powerpc/platforms/85xx/ppa8548.c @@ -72,17 +72,9 @@ static int __init declare_of_platform_devices(void) } machine_device_initcall(ppa8548, declare_of_platform_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init ppa8548_probe(void) -{ - return of_machine_is_compatible("ppa8548"); -} - define_machine(ppa8548) { .name = "ppa8548", - .probe = ppa8548_probe, + .compatible = "ppa8548", .setup_arch = ppa8548_setup_arch, .init_IRQ = ppa8548_pic_init, .show_cpuinfo = ppa8548_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index 1639e222cc33..335815a2d121 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -46,19 +46,11 @@ static void __init qemu_e500_setup_arch(void) mpc85xx_smp_init(); } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init qemu_e500_probe(void) -{ - return !!of_machine_is_compatible("fsl,qemu-e500"); -} - machine_arch_initcall(qemu_e500, mpc85xx_common_publish_devices); define_machine(qemu_e500) { .name = "QEMU e500", - .probe = qemu_e500_probe, + .compatible = "fsl,qemu-e500", .setup_arch = qemu_e500_setup_arch, .init_IRQ = qemu_e500_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c index 09f64470c765..f603a3905801 100644 --- a/arch/powerpc/platforms/85xx/socrates.c +++ b/arch/powerpc/platforms/85xx/socrates.c @@ -69,20 +69,9 @@ static void __init socrates_setup_arch(void) machine_arch_initcall(socrates, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init socrates_probe(void) -{ - if (of_machine_is_compatible("abb,socrates")) - return 1; - - return 0; -} - define_machine(socrates) { .name = "Socrates", - .probe = socrates_probe, + .compatible = "abb,socrates", .setup_arch = socrates_setup_arch, .init_IRQ = socrates_pic_init, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c index 6b1fe7bb3a8c..9f37b25e7a82 100644 --- a/arch/powerpc/platforms/85xx/stx_gp3.c +++ b/arch/powerpc/platforms/85xx/stx_gp3.c @@ -83,17 +83,9 @@ static void stx_gp3_show_cpuinfo(struct seq_file *m) machine_arch_initcall(stx_gp3, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init stx_gp3_probe(void) -{ - return of_machine_is_compatible("stx,gp3-8560"); -} - define_machine(stx_gp3) { .name = "STX GP3", - .probe = stx_gp3_probe, + .compatible = "stx,gp3-8560", .setup_arch = stx_gp3_setup_arch, .init_IRQ = stx_gp3_pic_init, .show_cpuinfo = stx_gp3_show_cpuinfo, diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index eaec099b4077..34b1e9cf9f34 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -103,14 +103,9 @@ static void __init twr_p1025_setup_arch(void) machine_arch_initcall(twr_p1025, mpc85xx_common_publish_devices); -static int __init twr_p1025_probe(void) -{ - return of_machine_is_compatible("fsl,TWR-P1025"); -} - define_machine(twr_p1025) { .name = "TWR-P1025", - .probe = twr_p1025_probe, + .compatible = "fsl,TWR-P1025", .setup_arch = twr_p1025_setup_arch, .init_IRQ = twr_p1025_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index 5836e4ecb7a0..57c38a8f40e8 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -136,27 +136,9 @@ machine_arch_initcall(xes_mpc8572, mpc85xx_common_publish_devices); machine_arch_initcall(xes_mpc8548, mpc85xx_common_publish_devices); machine_arch_initcall(xes_mpc8540, mpc85xx_common_publish_devices); -/* - * Called very early, device-tree isn't unflattened - */ -static int __init xes_mpc8572_probe(void) -{ - return of_machine_is_compatible("xes,MPC8572"); -} - -static int __init xes_mpc8548_probe(void) -{ - return of_machine_is_compatible("xes,MPC8548"); -} - -static int __init xes_mpc8540_probe(void) -{ - return of_machine_is_compatible("xes,MPC8540"); -} - define_machine(xes_mpc8572) { .name = "X-ES MPC8572", - .probe = xes_mpc8572_probe, + .compatible = "xes,MPC8572", .setup_arch = xes_mpc85xx_setup_arch, .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI @@ -170,7 +152,7 @@ define_machine(xes_mpc8572) { define_machine(xes_mpc8548) { .name = "X-ES MPC8548", - .probe = xes_mpc8548_probe, + .compatible = "xes,MPC8548", .setup_arch = xes_mpc85xx_setup_arch, .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI @@ -184,7 +166,7 @@ define_machine(xes_mpc8548) { define_machine(xes_mpc8540) { .name = "X-ES MPC8540", - .probe = xes_mpc8540_probe, + .compatible = "xes,MPC8540", .setup_arch = xes_mpc85xx_setup_arch, .init_IRQ = xes_mpc85xx_pic_init, #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c index 8e358fa0bc41..2b656a763537 100644 --- a/arch/powerpc/platforms/86xx/gef_ppc9a.c +++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c @@ -175,27 +175,11 @@ static void gef_ppc9a_nec_fixup(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB, gef_ppc9a_nec_fixup); -/* - * Called very early, device-tree isn't unflattened - * - * This function is called to determine whether the BSP is compatible with the - * supplied device-tree, which is assumed to be the correct one for the actual - * board. It is expected that, in the future, a kernel may support multiple - * boards. - */ -static int __init gef_ppc9a_probe(void) -{ - if (of_machine_is_compatible("gef,ppc9a")) - return 1; - - return 0; -} - machine_arch_initcall(gef_ppc9a, mpc86xx_common_publish_devices); define_machine(gef_ppc9a) { .name = "GE PPC9A", - .probe = gef_ppc9a_probe, + .compatible = "gef,ppc9a", .setup_arch = gef_ppc9a_setup_arch, .init_IRQ = gef_ppc9a_init_irq, .show_cpuinfo = gef_ppc9a_show_cpuinfo, diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c index b5b2733567cb..f38ab6bdfeb5 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc310.c +++ b/arch/powerpc/platforms/86xx/gef_sbc310.c @@ -162,27 +162,11 @@ static void gef_sbc310_nec_fixup(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB, gef_sbc310_nec_fixup); -/* - * Called very early, device-tree isn't unflattened - * - * This function is called to determine whether the BSP is compatible with the - * supplied device-tree, which is assumed to be the correct one for the actual - * board. It is expected that, in the future, a kernel may support multiple - * boards. - */ -static int __init gef_sbc310_probe(void) -{ - if (of_machine_is_compatible("gef,sbc310")) - return 1; - - return 0; -} - machine_arch_initcall(gef_sbc310, mpc86xx_common_publish_devices); define_machine(gef_sbc310) { .name = "GE SBC310", - .probe = gef_sbc310_probe, + .compatible = "gef,sbc310", .setup_arch = gef_sbc310_setup_arch, .init_IRQ = gef_sbc310_init_irq, .show_cpuinfo = gef_sbc310_show_cpuinfo, diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index bb4c8e6b44d0..09d59f92eaac 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -152,27 +152,11 @@ static void gef_sbc610_nec_fixup(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_USB, gef_sbc610_nec_fixup); -/* - * Called very early, device-tree isn't unflattened - * - * This function is called to determine whether the BSP is compatible with the - * supplied device-tree, which is assumed to be the correct one for the actual - * board. It is expected that, in the future, a kernel may support multiple - * boards. - */ -static int __init gef_sbc610_probe(void) -{ - if (of_machine_is_compatible("gef,sbc610")) - return 1; - - return 0; -} - machine_arch_initcall(gef_sbc610, mpc86xx_common_publish_devices); define_machine(gef_sbc610) { .name = "GE SBC610", - .probe = gef_sbc610_probe, + .compatible = "gef,sbc610", .setup_arch = gef_sbc610_setup_arch, .init_IRQ = gef_sbc610_init_irq, .show_cpuinfo = gef_sbc610_show_cpuinfo, diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index b593b9afd30a..22ec5d7dc09d 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -307,20 +307,9 @@ static void __init mpc86xx_hpcd_setup_arch(void) printk("MPC86xx HPCD board from Freescale Semiconductor\n"); } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc86xx_hpcd_probe(void) -{ - if (of_machine_is_compatible("fsl,MPC8610HPCD")) - return 1; /* Looks good */ - - return 0; -} - define_machine(mpc86xx_hpcd) { .name = "MPC86xx HPCD", - .probe = mpc86xx_hpcd_probe, + .compatible = "fsl,MPC8610HPCD", .setup_arch = mpc86xx_hpcd_setup_arch, .init_IRQ = mpc86xx_init_irq, .get_irq = mpic_get_irq, diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 5294394c9c07..61eccb2d689d 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -85,18 +85,6 @@ mpc86xx_hpcn_show_cpuinfo(struct seq_file *m) seq_printf(m, "SVR\t\t: 0x%x\n", svid); } - -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc86xx_hpcn_probe(void) -{ - if (of_machine_is_compatible("fsl,mpc8641hpcn")) - return 1; /* Looks good */ - - return 0; -} - static const struct of_device_id of_bus_ids[] __initconst = { { .compatible = "fsl,srio", }, {}, @@ -113,7 +101,7 @@ machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices); define_machine(mpc86xx_hpcn) { .name = "MPC86xx HPCN", - .probe = mpc86xx_hpcn_probe, + .compatible = "fsl,MPC8610HPCD", .setup_arch = mpc86xx_hpcn_setup_arch, .init_IRQ = mpc86xx_init_irq, .show_cpuinfo = mpc86xx_hpcn_show_cpuinfo, diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c index 10e6e4fe77fc..68bb0da3d3ee 100644 --- a/arch/powerpc/platforms/8xx/adder875.c +++ b/arch/powerpc/platforms/8xx/adder875.c @@ -83,11 +83,6 @@ static void __init adder875_setup(void) init_ioports(); } -static int __init adder875_probe(void) -{ - return of_machine_is_compatible("analogue-and-micro,adder875"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .compatible = "simple-bus", }, {}, @@ -102,7 +97,7 @@ machine_device_initcall(adder875, declare_of_platform_devices); define_machine(adder875) { .name = "Adder MPC875", - .probe = adder875_probe, + .compatible = "analogue-and-micro,adder875", .setup_arch = adder875_setup, .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c index b3b22520b435..fc276a29d67f 100644 --- a/arch/powerpc/platforms/8xx/ep88xc.c +++ b/arch/powerpc/platforms/8xx/ep88xc.c @@ -142,11 +142,6 @@ static void __init ep88xc_setup_arch(void) BCSR8_PHY2_ENABLE | BCSR8_PHY2_POWER); } -static int __init ep88xc_probe(void) -{ - return of_machine_is_compatible("fsl,ep88xc"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .name = "soc", }, { .name = "cpm", }, @@ -165,7 +160,7 @@ machine_device_initcall(ep88xc, declare_of_platform_devices); define_machine(ep88xc) { .name = "Embedded Planet EP88xC", - .probe = ep88xc_probe, + .compatible = "fsl,ep88xc", .setup_arch = ep88xc_setup_arch, .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, diff --git a/arch/powerpc/platforms/8xx/mpc86xads_setup.c b/arch/powerpc/platforms/8xx/mpc86xads_setup.c index 03267e4a44a9..11b3d1116db1 100644 --- a/arch/powerpc/platforms/8xx/mpc86xads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc86xads_setup.c @@ -117,11 +117,6 @@ static void __init mpc86xads_setup_arch(void) iounmap(bcsr_io); } -static int __init mpc86xads_probe(void) -{ - return of_machine_is_compatible("fsl,mpc866ads"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .name = "soc", }, { .name = "cpm", }, @@ -139,7 +134,7 @@ machine_device_initcall(mpc86x_ads, declare_of_platform_devices); define_machine(mpc86x_ads) { .name = "MPC86x ADS", - .probe = mpc86xads_probe, + .compatible = "fsl,mpc866ads", .setup_arch = mpc86xads_setup_arch, .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c index b1e39f96de00..2fc7cacbcd96 100644 --- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c +++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c @@ -192,11 +192,6 @@ static void __init mpc885ads_setup_arch(void) } } -static int __init mpc885ads_probe(void) -{ - return of_machine_is_compatible("fsl,mpc885ads"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .name = "soc", }, { .name = "cpm", }, @@ -215,7 +210,7 @@ machine_device_initcall(mpc885_ads, declare_of_platform_devices); define_machine(mpc885_ads) { .name = "Freescale MPC885 ADS", - .probe = mpc885ads_probe, + .compatible = "fsl,mpc885ads", .setup_arch = mpc885ads_setup_arch, .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c index ffcfd17a5fa3..7d8eb50bb9cd 100644 --- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c +++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c @@ -121,11 +121,6 @@ static void __init tqm8xx_setup_arch(void) init_ioports(); } -static int __init tqm8xx_probe(void) -{ - return of_machine_is_compatible("tqc,tqm8xx"); -} - static const struct of_device_id of_bus_ids[] __initconst = { { .name = "soc", }, { .name = "cpm", }, @@ -144,7 +139,7 @@ machine_device_initcall(tqm8xx, declare_of_platform_devices); define_machine(tqm8xx) { .name = "TQM8xx", - .probe = tqm8xx_probe, + .compatible = "tqc,tqm8xx", .setup_arch = tqm8xx_setup_arch, .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c index 397ce6a40bd0..ba3b4a5688fb 100644 --- a/arch/powerpc/platforms/amigaone/setup.c +++ b/arch/powerpc/platforms/amigaone/setup.c @@ -143,24 +143,21 @@ void __noreturn amigaone_restart(char *cmd) static int __init amigaone_probe(void) { - if (of_machine_is_compatible("eyetech,amigaone")) { - /* - * Coherent memory access cause complete system lockup! Thus - * disable this CPU feature, even if the CPU needs it. - */ - cur_cpu_spec->cpu_features &= ~CPU_FTR_NEED_COHERENT; + /* + * Coherent memory access cause complete system lockup! Thus + * disable this CPU feature, even if the CPU needs it. + */ + cur_cpu_spec->cpu_features &= ~CPU_FTR_NEED_COHERENT; - DMA_MODE_READ = 0x44; - DMA_MODE_WRITE = 0x48; + DMA_MODE_READ = 0x44; + DMA_MODE_WRITE = 0x48; - return 1; - } - - return 0; + return 1; } define_machine(amigaone) { .name = "AmigaOne", + .compatible = "eyetech,amigaone", .probe = amigaone_probe, .setup_arch = amigaone_setup_arch, .discover_phbs = amigaone_discover_phbs, diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c index 5c2575adcc7e..4fc84ff95b5e 100644 --- a/arch/powerpc/platforms/embedded6xx/gamecube.c +++ b/arch/powerpc/platforms/embedded6xx/gamecube.c @@ -50,9 +50,6 @@ static void __noreturn gamecube_halt(void) static int __init gamecube_probe(void) { - if (!of_machine_is_compatible("nintendo,gamecube")) - return 0; - pm_power_off = gamecube_power_off; ug_udbg_init(); @@ -67,6 +64,7 @@ static void gamecube_shutdown(void) define_machine(gamecube) { .name = "gamecube", + .compatible = "nintendo,gamecube", .probe = gamecube_probe, .restart = gamecube_restart, .halt = gamecube_halt, diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index bebc5a972694..67949c85c398 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -241,16 +241,6 @@ static void __noreturn holly_restart(char *cmd) for (;;) ; } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init holly_probe(void) -{ - if (!of_machine_is_compatible("ibm,holly")) - return 0; - return 1; -} - static int ppc750_machine_check_exception(struct pt_regs *regs) { const struct exception_table_entry *entry; @@ -267,7 +257,7 @@ static int ppc750_machine_check_exception(struct pt_regs *regs) define_machine(holly){ .name = "PPC750 GX/CL TSI", - .probe = holly_probe, + .compatible = "ibm,holly", .setup_arch = holly_setup_arch, .discover_phbs = holly_init_pci, .init_IRQ = holly_init_IRQ, diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 1830e1ac1f8f..f04fd234c9ab 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -143,9 +143,6 @@ static void linkstation_show_cpuinfo(struct seq_file *m) static int __init linkstation_probe(void) { - if (!of_machine_is_compatible("linkstation")) - return 0; - pm_power_off = linkstation_power_off; return 1; @@ -153,6 +150,7 @@ static int __init linkstation_probe(void) define_machine(linkstation){ .name = "Buffalo Linkstation", + .compatible = "linkstation", .probe = linkstation_probe, .setup_arch = linkstation_setup_arch, .discover_phbs = linkstation_setup_pci, diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index ddf0c652af80..6821fb6644ac 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -159,16 +159,6 @@ static void __noreturn mpc7448_hpc2_restart(char *cmd) for (;;) ; /* Spin until reset happens */ } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mpc7448_hpc2_probe(void) -{ - if (!of_machine_is_compatible("mpc74xx")) - return 0; - return 1; -} - static int mpc7448_machine_check_exception(struct pt_regs *regs) { const struct exception_table_entry *entry; @@ -185,7 +175,7 @@ static int mpc7448_machine_check_exception(struct pt_regs *regs) define_machine(mpc7448_hpc2){ .name = "MPC7448 HPC2", - .probe = mpc7448_hpc2_probe, + .compatible = "mpc74xx", .setup_arch = mpc7448_hpc2_setup_arch, .discover_phbs = mpc7448_hpc2_setup_pci, .init_IRQ = mpc7448_hpc2_init_IRQ, diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c index 4854cc592cec..7e57de576ef7 100644 --- a/arch/powerpc/platforms/embedded6xx/mvme5100.c +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -186,14 +186,6 @@ static void __noreturn mvme5100_restart(char *cmd) ; } -/* - * Called very early, device-tree isn't unflattened - */ -static int __init mvme5100_probe(void) -{ - return of_machine_is_compatible("MVME5100"); -} - static int __init probe_of_platform_devices(void) { @@ -205,7 +197,7 @@ machine_device_initcall(mvme5100, probe_of_platform_devices); define_machine(mvme5100) { .name = "MVME5100", - .probe = mvme5100_probe, + .compatible = "MVME5100", .setup_arch = mvme5100_setup_arch, .discover_phbs = mvme5100_setup_pci, .init_IRQ = mvme5100_pic_init, diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index 5f16e80b6ed6..ab85af37117f 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -110,14 +110,9 @@ static void __noreturn storcenter_restart(char *cmd) for (;;) ; } -static int __init storcenter_probe(void) -{ - return of_machine_is_compatible("iomega,storcenter"); -} - define_machine(storcenter){ .name = "IOMEGA StorCenter", - .probe = storcenter_probe, + .compatible = "iomega,storcenter", .setup_arch = storcenter_setup_arch, .discover_phbs = storcenter_setup_pci, .init_IRQ = storcenter_init_IRQ, diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index f4e654a9d4ff..f2cc00e6f12f 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -141,9 +141,6 @@ static void __init wii_pic_probe(void) static int __init wii_probe(void) { - if (!of_machine_is_compatible("nintendo,wii")) - return 0; - pm_power_off = wii_power_off; ug_udbg_init(); @@ -174,6 +171,7 @@ device_initcall(wii_device_probe); define_machine(wii) { .name = "wii", + .compatible = "nintendo,wii", .probe = wii_probe, .setup_arch = wii_setup_arch, .restart = wii_restart, diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c index 6b32539395a4..f08edcde7bee 100644 --- a/arch/powerpc/platforms/microwatt/setup.c +++ b/arch/powerpc/platforms/microwatt/setup.c @@ -23,11 +23,6 @@ static void __init microwatt_init_IRQ(void) xics_init(); } -static int __init microwatt_probe(void) -{ - return of_machine_is_compatible("microwatt-soc"); -} - static int __init microwatt_populate(void) { return of_platform_default_populate(NULL, NULL, NULL); @@ -41,7 +36,7 @@ static void __init microwatt_setup_arch(void) define_machine(microwatt) { .name = "microwatt", - .probe = microwatt_probe, + .compatible = "microwatt-soc", .init_IRQ = microwatt_init_IRQ, .setup_arch = microwatt_setup_arch, .progress = udbg_progress, diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 61ab2d38ff4b..f89731670448 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -512,9 +512,6 @@ static void __init pnv_setup_machdep_opal(void) static int __init pnv_probe(void) { - if (!of_machine_is_compatible("ibm,powernv")) - return 0; - if (firmware_has_feature(FW_FEATURE_OPAL)) pnv_setup_machdep_opal(); @@ -578,6 +575,7 @@ static long pnv_machine_check_early(struct pt_regs *regs) define_machine(powernv) { .name = "PowerNV", + .compatible = "ibm,powernv", .probe = pnv_probe, .setup_arch = pnv_setup_arch, .init_IRQ = pnv_init_IRQ, diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index d7495785fe47..5144f11359f7 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -264,9 +264,6 @@ static int __init ps3_probe(void) { DBG(" -> %s:%d\n", __func__, __LINE__); - if (!of_machine_is_compatible("sony,ps3")) - return 0; - ps3_os_area_save_params(); pm_power_off = ps3_power_off; @@ -291,6 +288,7 @@ static void ps3_kexec_cpu_down(int crash_shutdown, int secondary) define_machine(ps3) { .name = "PS3", + .compatible = "sony,ps3", .probe = ps3_probe, .setup_arch = ps3_setup_arch, .init_IRQ = ps3_init_IRQ, -- GitLab From c8325b3227508459fab42f4f48fb232bc687f1ba Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 23 Feb 2023 15:07:42 -0600 Subject: [PATCH 0464/5631] thunderbolt: use `tb_eeprom_get_drom_offset` to discover DROM offset The static function `tb_eeprom_get_drom_offset` has more safety guards for the DROM offset fetching. Use this instead of just `tb_sw_read` No intended functional changes. Signed-off-by: Mario Limonciello Signed-off-by: Mika Westerberg --- drivers/thunderbolt/eeprom.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index c90d22f56d4e..3b96a55295a0 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -471,14 +471,13 @@ static int tb_drom_copy_efi(struct tb_switch *sw, u16 *size) static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size) { - u32 drom_offset; + u16 drom_offset; int ret; if (!sw->dma_port) return -ENODEV; - ret = tb_sw_read(sw, &drom_offset, TB_CFG_SWITCH, - sw->cap_plug_events + 12, 1); + ret = tb_eeprom_get_drom_offset(sw, &drom_offset); if (ret) return ret; -- GitLab From ebde5ba27c640e08e92c83fe30be0d9fa224eea9 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 23 Feb 2023 15:07:43 -0600 Subject: [PATCH 0465/5631] thunderbolt: Refactor DROM reading The NVM reading code has a series of gotos that potentially introduce unexpected behaviors with retries if something unexpected has failed to parse. Refactor the code to remove the gotos and drop the retry logic. Signed-off-by: Mario Limonciello [mw: renamed root switch to host router, split device handling too] Signed-off-by: Mika Westerberg --- drivers/thunderbolt/eeprom.c | 199 ++++++++++++++++++----------------- 1 file changed, 105 insertions(+), 94 deletions(-) diff --git a/drivers/thunderbolt/eeprom.c b/drivers/thunderbolt/eeprom.c index 3b96a55295a0..0f6099c18a94 100644 --- a/drivers/thunderbolt/eeprom.c +++ b/drivers/thunderbolt/eeprom.c @@ -416,7 +416,7 @@ static int tb_drom_parse_entries(struct tb_switch *sw, size_t header_size) if (pos + 1 == drom_size || pos + entry->len > drom_size || !entry->len) { tb_sw_warn(sw, "DROM buffer overrun\n"); - return -EILSEQ; + return -EIO; } switch (entry->type) { @@ -512,7 +512,7 @@ static int tb_drom_copy_nvm(struct tb_switch *sw, u16 *size) return ret; } -static int usb4_copy_host_drom(struct tb_switch *sw, u16 *size) +static int usb4_copy_drom(struct tb_switch *sw, u16 *size) { int ret; @@ -535,15 +535,40 @@ static int usb4_copy_host_drom(struct tb_switch *sw, u16 *size) return ret; } -static int tb_drom_read_n(struct tb_switch *sw, u16 offset, u8 *val, - size_t count) +static int tb_drom_bit_bang(struct tb_switch *sw, u16 *size) { - if (tb_switch_is_usb4(sw)) - return usb4_switch_drom_read(sw, offset, val, count); - return tb_eeprom_read_n(sw, offset, val, count); + int ret; + + ret = tb_eeprom_read_n(sw, 14, (u8 *)size, 2); + if (ret) + return ret; + + *size &= 0x3ff; + *size += TB_DROM_DATA_START; + + tb_sw_dbg(sw, "reading DROM (length: %#x)\n", *size); + if (*size < sizeof(struct tb_drom_header)) { + tb_sw_warn(sw, "DROM too small, aborting\n"); + return -EIO; + } + + sw->drom = kzalloc(*size, GFP_KERNEL); + if (!sw->drom) + return -ENOMEM; + + ret = tb_eeprom_read_n(sw, 0, sw->drom, *size); + if (ret) + goto err; + + return 0; + +err: + kfree(sw->drom); + sw->drom = NULL; + return ret; } -static int tb_drom_parse(struct tb_switch *sw) +static int tb_drom_parse_v1(struct tb_switch *sw) { const struct tb_drom_header *header = (const struct tb_drom_header *)sw->drom; @@ -554,7 +579,7 @@ static int tb_drom_parse(struct tb_switch *sw) tb_sw_warn(sw, "DROM UID CRC8 mismatch (expected: %#x, got: %#x)\n", header->uid_crc8, crc); - return -EILSEQ; + return -EIO; } if (!sw->uid) sw->uid = header->uid; @@ -588,85 +613,14 @@ static int usb4_drom_parse(struct tb_switch *sw) return tb_drom_parse_entries(sw, USB4_DROM_HEADER_SIZE); } -/** - * tb_drom_read() - Copy DROM to sw->drom and parse it - * @sw: Router whose DROM to read and parse - * - * This function reads router DROM and if successful parses the entries and - * populates the fields in @sw accordingly. Can be called for any router - * generation. - * - * Returns %0 in case of success and negative errno otherwise. - */ -int tb_drom_read(struct tb_switch *sw) +static int tb_drom_parse(struct tb_switch *sw, u16 size) { - u16 size; - struct tb_drom_header *header; - int res, retries = 1; - - if (sw->drom) - return 0; - - if (tb_route(sw) == 0) { - /* - * Apple's NHI EFI driver supplies a DROM for the root switch - * in a device property. Use it if available. - */ - if (tb_drom_copy_efi(sw, &size) == 0) - goto parse; - - /* Non-Apple hardware has the DROM as part of NVM */ - if (tb_drom_copy_nvm(sw, &size) == 0) - goto parse; - - /* - * USB4 hosts may support reading DROM through router - * operations. - */ - if (tb_switch_is_usb4(sw)) { - usb4_switch_read_uid(sw, &sw->uid); - if (!usb4_copy_host_drom(sw, &size)) - goto parse; - } else { - /* - * The root switch contains only a dummy drom - * (header only, no entries). Hardcode the - * configuration here. - */ - tb_drom_read_uid_only(sw, &sw->uid); - } - - return 0; - } - - res = tb_drom_read_n(sw, 14, (u8 *) &size, 2); - if (res) - return res; - size &= 0x3ff; - size += TB_DROM_DATA_START; - tb_sw_dbg(sw, "reading drom (length: %#x)\n", size); - if (size < sizeof(*header)) { - tb_sw_warn(sw, "drom too small, aborting\n"); - return -EIO; - } - - sw->drom = kzalloc(size, GFP_KERNEL); - if (!sw->drom) - return -ENOMEM; -read: - res = tb_drom_read_n(sw, 0, sw->drom, size); - if (res) - goto err; - -parse: - header = (void *) sw->drom; + const struct tb_drom_header *header = (const void *)sw->drom; + int ret; if (header->data_len + TB_DROM_DATA_START != size) { - tb_sw_warn(sw, "drom size mismatch\n"); - if (retries--) { - msleep(100); - goto read; - } + tb_sw_warn(sw, "DROM size mismatch\n"); + ret = -EIO; goto err; } @@ -674,29 +628,86 @@ int tb_drom_read(struct tb_switch *sw) switch (header->device_rom_revision) { case 3: - res = usb4_drom_parse(sw); + ret = usb4_drom_parse(sw); break; default: tb_sw_warn(sw, "DROM device_rom_revision %#x unknown\n", header->device_rom_revision); fallthrough; case 1: - res = tb_drom_parse(sw); + ret = tb_drom_parse_v1(sw); break; } - /* If the DROM parsing fails, wait a moment and retry once */ - if (res == -EILSEQ && retries--) { + if (ret) { tb_sw_warn(sw, "parsing DROM failed\n"); - msleep(100); - goto read; + goto err; } - if (!res) - return 0; + return 0; err: kfree(sw->drom); sw->drom = NULL; - return -EIO; + + return ret; +} + +static int tb_drom_host_read(struct tb_switch *sw) +{ + u16 size; + + if (tb_switch_is_usb4(sw)) { + usb4_switch_read_uid(sw, &sw->uid); + if (!usb4_copy_drom(sw, &size)) + return tb_drom_parse(sw, size); + } else { + if (!tb_drom_copy_efi(sw, &size)) + return tb_drom_parse(sw, size); + + if (!tb_drom_copy_nvm(sw, &size)) + return tb_drom_parse(sw, size); + + tb_drom_read_uid_only(sw, &sw->uid); + } + + return 0; +} + +static int tb_drom_device_read(struct tb_switch *sw) +{ + u16 size; + int ret; + + if (tb_switch_is_usb4(sw)) { + usb4_switch_read_uid(sw, &sw->uid); + ret = usb4_copy_drom(sw, &size); + } else { + ret = tb_drom_bit_bang(sw, &size); + } + + if (ret) + return ret; + + return tb_drom_parse(sw, size); +} + +/** + * tb_drom_read() - Copy DROM to sw->drom and parse it + * @sw: Router whose DROM to read and parse + * + * This function reads router DROM and if successful parses the entries and + * populates the fields in @sw accordingly. Can be called for any router + * generation. + * + * Returns %0 in case of success and negative errno otherwise. + */ +int tb_drom_read(struct tb_switch *sw) +{ + if (sw->drom) + return 0; + + if (!tb_route(sw)) + return tb_drom_host_read(sw); + return tb_drom_device_read(sw); } -- GitLab From 258d985f6eb360c9c7aacd025d0dbc080a59423f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Feb 2023 18:28:15 +0000 Subject: [PATCH 0466/5631] KVM: x86/mmu: Use EMULTYPE flag to track write #PFs to shadow pages Use a new EMULTYPE flag, EMULTYPE_WRITE_PF_TO_SP, to track page faults on self-changing writes to shadowed page tables instead of propagating that information to the emulator via a semi-persistent vCPU flag. Using a flag in "struct kvm_vcpu_arch" is confusing, especially as implemented, as it's not at all obvious that clearing the flag only when emulation actually occurs is correct. E.g. if KVM sets the flag and then retries the fault without ever getting to the emulator, the flag will be left set for future calls into the emulator. But because the flag is consumed if and only if both EMULTYPE_PF and EMULTYPE_ALLOW_RETRY_PF are set, and because EMULTYPE_ALLOW_RETRY_PF is deliberately not set for direct MMUs, emulated MMIO, or while L2 is active, KVM avoids false positives on a stale flag since FNAME(page_fault) is guaranteed to be run and refresh the flag before it's ultimately consumed by the tail end of reexecute_instruction(). Signed-off-by: Sean Christopherson Message-Id: <20230202182817.407394-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 37 ++++++++++++++++++--------------- arch/x86/kvm/mmu/mmu.c | 5 +++-- arch/x86/kvm/mmu/mmu_internal.h | 12 ++++++++++- arch/x86/kvm/mmu/paging_tmpl.h | 4 +--- arch/x86/kvm/x86.c | 15 ++----------- 5 files changed, 37 insertions(+), 36 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 808c292ad3f4..a45de1118a42 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -947,23 +947,6 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; - /* - * Indicates the guest is trying to write a gfn that contains one or - * more of the PTEs used to translate the write itself, i.e. the access - * is changing its own translation in the guest page tables. KVM exits - * to userspace if emulation of the faulting instruction fails and this - * flag is set, as KVM cannot make forward progress. - * - * If emulation fails for a write to guest page tables, KVM unprotects - * (zaps) the shadow page for the target gfn and resumes the guest to - * retry the non-emulatable instruction (on hardware). Unprotecting the - * gfn doesn't allow forward progress for a self-changing access because - * doing so also zaps the translation for the gfn, i.e. retrying the - * instruction will hit a !PRESENT fault, which results in a new shadow - * page and sends KVM back to square one. - */ - bool write_fault_to_shadow_pgtable; - /* set at EPT violation at this point */ unsigned long exit_qualification; @@ -1907,6 +1890,25 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping * an instruction (after completing userspace I/O). + * + * EMULTYPE_WRITE_PF_TO_SP - Set when emulating an intercepted page fault that + * is attempting to write a gfn that contains one or + * more of the PTEs used to translate the write itself, + * and the owning page table is being shadowed by KVM. + * If emulation of the faulting instruction fails and + * this flag is set, KVM will exit to userspace instead + * of retrying emulation as KVM cannot make forward + * progress. + * + * If emulation fails for a write to guest page tables, + * KVM unprotects (zaps) the shadow page for the target + * gfn and resumes the guest to retry the non-emulatable + * instruction (on hardware). Unprotecting the gfn + * doesn't allow forward progress for a self-changing + * access because doing so also zaps the translation for + * the gfn, i.e. retrying the instruction will hit a + * !PRESENT fault, which results in a new shadow page + * and sends KVM back to square one. */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) @@ -1916,6 +1918,7 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) +#define EMULTYPE_WRITE_PF_TO_SP (1 << 8) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c8ebe542c565..144c5a01cd77 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4203,7 +4203,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) return; - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -5664,7 +5664,8 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r == RET_PF_INVALID) { r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), false); + lower_32_bits(error_code), false, + &emulation_type); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index cc58631e2336..2cbb155c686c 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -240,6 +240,13 @@ struct kvm_page_fault { kvm_pfn_t pfn; hva_t hva; bool map_writable; + + /* + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. + */ + bool write_fault_to_shadow_pgtable; }; int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); @@ -273,7 +280,7 @@ enum { }; static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 err, bool prefetch) + u32 err, bool prefetch, int *emulation_type) { struct kvm_page_fault fault = { .addr = cr2_or_gpa, @@ -312,6 +319,9 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, else r = vcpu->arch.mmu->page_fault(vcpu, &fault); + if (fault.write_fault_to_shadow_pgtable && emulation_type) + *emulation_type |= EMULTYPE_WRITE_PF_TO_SP; + /* * Similar to above, prefetch faults aren't truly spurious, and the * async #PF path doesn't do emulation. Do count faults that are fixed diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 57f0b75c80f9..5d2958299b4f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -825,10 +825,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - vcpu->arch.write_fault_to_shadow_pgtable = false; - is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, - &walker, fault->user, &vcpu->arch.write_fault_to_shadow_pgtable); + &walker, fault->user, &fault->write_fault_to_shadow_pgtable); if (is_self_change_mapping) fault->max_level = PG_LEVEL_4K; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7713420abab0..ff7f398a0c6a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8463,7 +8463,6 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) } static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - bool write_fault_to_shadow_pgtable, int emulation_type) { gpa_t gpa = cr2_or_gpa; @@ -8534,7 +8533,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * be fixed by unprotecting shadow page and it should * be reported to userspace. */ - return !write_fault_to_shadow_pgtable; + return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, @@ -8782,20 +8781,12 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int r; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - bool write_fault_to_spt; if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; - /* - * Clear write_fault_to_shadow_pgtable here to ensure it is - * never reused. - */ - write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; - vcpu->arch.write_fault_to_shadow_pgtable = false; - if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); @@ -8816,7 +8807,6 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } if (reexecute_instruction(vcpu, cr2_or_gpa, - write_fault_to_spt, emulation_type)) return 1; @@ -8895,8 +8885,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); -- GitLab From 39fda5d873eb1f59613ce49249ee2effea9f8e06 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Feb 2023 18:28:16 +0000 Subject: [PATCH 0467/5631] KVM: x86/mmu: Detect write #PF to shadow pages during FNAME(fetch) walk Move the detection of write #PF to shadow pages, i.e. a fault on a write to a page table that is being shadowed by KVM that is used to translate the write itself, from FNAME(is_self_change_mapping) to FNAME(fetch). There is no need to detect the self-referential write before kvm_faultin_pfn() as KVM does not consume EMULTYPE_WRITE_PF_TO_SP for accesses that resolve to "error or no-slot" pfns, i.e. KVM doesn't allow retrying MMIO accesses or writes to read-only memslots. Detecting the EMULTYPE_WRITE_PF_TO_SP scenario in FNAME(fetch) will allow dropping FNAME(is_self_change_mapping) entirely, as the hugepage interaction can be deferred to kvm_mmu_hugepage_adjust(). Cc: Huang Hang Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20221213125538.81209-1-jiangshanlai@gmail.com [sean: split to separate patch, write changelog] Signed-off-by: Sean Christopherson Message-Id: <20230202182817.407394-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/paging_tmpl.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 5d2958299b4f..f57d9074fb9b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -685,6 +685,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (sp != ERR_PTR(-EEXIST)) link_shadow_page(vcpu, it.sptep, sp); + + if (fault->write && table_gfn == fault->gfn) + fault->write_fault_to_shadow_pgtable = true; } kvm_mmu_hugepage_adjust(vcpu, fault); @@ -741,17 +744,13 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, * created when kvm establishes shadow page table that stop kvm using large * page size. Do it early can avoid unnecessary #PF and emulation. * - * @write_fault_to_shadow_pgtable will return true if the fault gfn is - * currently used as its page table. - * * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok * since the PDPT is always shadowed, that means, we can not use large page * size to map the gfn which is used as PDPT. */ static bool FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, - struct guest_walker *walker, bool user_fault, - bool *write_fault_to_shadow_pgtable) + struct guest_walker *walker, bool user_fault) { int level; gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1); @@ -765,7 +764,6 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1]; self_changed |= !(gfn & mask); - *write_fault_to_shadow_pgtable |= !gfn; } return self_changed; @@ -826,7 +824,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return r; is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, - &walker, fault->user, &fault->write_fault_to_shadow_pgtable); + &walker, fault->user); if (is_self_change_mapping) fault->max_level = PG_LEVEL_4K; -- GitLab From 9a967700496feac1f006ffd97ffe2d82b6aac5ac Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 2 Feb 2023 18:28:17 +0000 Subject: [PATCH 0468/5631] KVM: x86/mmu: Remove FNAME(is_self_change_mapping) Drop FNAME(is_self_change_mapping) and instead rely on kvm_mmu_hugepage_adjust() to adjust the hugepage accordingly. Prior to commit 4cd071d13c5c ("KVM: x86/mmu: Move calls to thp_adjust() down a level"), the hugepage adjustment was done before allocating new shadow pages, i.e. failed to restrict the hugepage sizes if a new shadow page resulted in account_shadowed() changing the disallowed hugepage tracking. Removing FNAME(is_self_change_mapping) fixes a bug reported by Huang Hang where KVM unnecessarily forces a 4KiB page. FNAME(is_self_change_mapping) has a defect in that it blindly disables _all_ hugepage mappings rather than trying to reduce the size of the hugepage. If the guest is writing to a 1GiB page and the 1GiB is self-referential but a 2MiB page is not, then KVM can and should create a 2MiB mapping. Add a comment above the call to kvm_mmu_hugepage_adjust() to call out the new dependency on adjusting the hugepage size after walking indirect PTEs. Reported-by: Huang Hang Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20221213125538.81209-1-jiangshanlai@gmail.com [sean: rework changelog after separating out the emulator change] Signed-off-by: Sean Christopherson Message-Id: <20230202182817.407394-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/paging_tmpl.h | 51 +++++----------------------------- 1 file changed, 7 insertions(+), 44 deletions(-) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f57d9074fb9b..a056f2773dd9 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -690,6 +690,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, fault->write_fault_to_shadow_pgtable = true; } + /* + * Adjust the hugepage size _after_ resolving indirect shadow pages. + * KVM doesn't support mapping hugepages into the guest for gfns that + * are being shadowed by KVM, i.e. allocating a new shadow page may + * affect the allowed hugepage size. + */ kvm_mmu_hugepage_adjust(vcpu, fault); trace_kvm_mmu_spte_requested(fault); @@ -734,41 +740,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, return RET_PF_RETRY; } - /* - * To see whether the mapped gfn can write its page table in the current - * mapping. - * - * It is the helper function of FNAME(page_fault). When guest uses large page - * size to map the writable gfn which is used as current page table, we should - * force kvm to use small page size to map it because new shadow page will be - * created when kvm establishes shadow page table that stop kvm using large - * page size. Do it early can avoid unnecessary #PF and emulation. - * - * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok - * since the PDPT is always shadowed, that means, we can not use large page - * size to map the gfn which is used as PDPT. - */ -static bool -FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, - struct guest_walker *walker, bool user_fault) -{ - int level; - gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1); - bool self_changed = false; - - if (!(walker->pte_access & ACC_WRITE_MASK || - (!is_cr0_wp(vcpu->arch.mmu) && !user_fault))) - return false; - - for (level = walker->level; level <= walker->max_level; level++) { - gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1]; - - self_changed |= !(gfn & mask); - } - - return self_changed; -} - /* * Page fault handler. There are several causes for a page fault: * - there is no shadow pte for the guest pte @@ -787,7 +758,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault { struct guest_walker walker; int r; - bool is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); WARN_ON_ONCE(fault->is_tdp); @@ -812,6 +782,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault } fault->gfn = walker.gfn; + fault->max_level = walker.level; fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); if (page_fault_handle_page_track(vcpu, fault)) { @@ -823,14 +794,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, - &walker, fault->user); - - if (is_self_change_mapping) - fault->max_level = PG_LEVEL_4K; - else - fault->max_level = walker.level; - r = kvm_faultin_pfn(vcpu, fault, walker.pte_access); if (r != RET_PF_CONTINUE) return r; -- GitLab From 68ac4221497b9a54f32c452a774ae747da908a81 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 11 Feb 2023 00:35:32 +0000 Subject: [PATCH 0469/5631] KVM: nVMX: Move EVMCS1_SUPPORT_* macros to hyperv.c Move the macros that define the set of VMCS controls that are supported by eVMCS1 from hyperv.h to hyperv.c, i.e. make them "private". The macros should never be consumed directly by KVM at-large since the "final" set of supported controls depends on guest CPUID. No functional change intended. Reviewed-by: Vitaly Kuznetsov Signed-off-by: Sean Christopherson Message-Id: <20230211003534.564198-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/hyperv.c | 105 ++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/vmx/hyperv.h | 105 -------------------------------------- 2 files changed, 105 insertions(+), 105 deletions(-) diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 22daca752797..b6748055c586 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,6 +13,111 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + DEFINE_STATIC_KEY_FALSE(enable_evmcs); #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 78d17667e7ec..1299143d00df 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -22,111 +22,6 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); #define KVM_EVMCS_VERSION 1 -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - struct evmcs_field { u16 offset; u16 clean_field; -- GitLab From 19f10315fd53599d8186aa46a0363b233292eb3d Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 11 Feb 2023 00:35:33 +0000 Subject: [PATCH 0470/5631] KVM: VMX: Stub out enable_evmcs static key for CONFIG_HYPERV=n Wrap enable_evmcs in a helper and stub it out when CONFIG_HYPERV=n in order to eliminate the static branch nop placeholders. clang-14 is clever enough to elide the nop, but gcc-12 is not. Stubbing out the key reduces the size of kvm-intel.ko by ~7.5% (200KiB) when compiled with gcc-12 (there are a _lot_ of VMCS accesses throughout KVM). Reviewed-by: Vitaly Kuznetsov Signed-off-by: Sean Christopherson Message-Id: <20230211003534.564198-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/hyperv.c | 4 ++-- arch/x86/kvm/vmx/hyperv.h | 10 ++++++++-- arch/x86/kvm/vmx/vmx.c | 15 +++++++-------- arch/x86/kvm/vmx/vmx_ops.h | 22 +++++++++++----------- 4 files changed, 28 insertions(+), 23 deletions(-) diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index b6748055c586..274fbd38c64e 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -118,8 +118,6 @@ #define EVMCS1_SUPPORTED_VMFUNC (0) -DEFINE_STATIC_KEY_FALSE(enable_evmcs); - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -611,6 +609,8 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) } #if IS_ENABLED(CONFIG_HYPERV) +DEFINE_STATIC_KEY_FALSE(enable_evmcs); + /* * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption * is: in case a feature has corresponding fields in eVMCS described and it was diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 1299143d00df..a54a2fdf0a5b 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -16,8 +16,6 @@ struct vmcs_config; -DECLARE_STATIC_KEY_FALSE(enable_evmcs); - #define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) #define KVM_EVMCS_VERSION 1 @@ -69,6 +67,13 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, #if IS_ENABLED(CONFIG_HYPERV) +DECLARE_STATIC_KEY_FALSE(enable_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&enable_evmcs); +} + static __always_inline int get_evmcs_offset(unsigned long field, u16 *clean_field) { @@ -158,6 +163,7 @@ static inline void evmcs_load(u64 phys_addr) void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } static __always_inline void evmcs_write64(unsigned long field, u64 value) {} static __always_inline void evmcs_write32(unsigned long field, u32 value) {} static __always_inline void evmcs_write16(unsigned long field, u16 value) {} diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d2d6e1b6c788..09e07fb83c37 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -595,7 +595,7 @@ static void hv_reset_evmcs(void) { struct hv_vp_assist_page *vp_ap; - if (!static_branch_unlikely(&enable_evmcs)) + if (!kvm_is_using_evmcs()) return; /* @@ -2816,8 +2816,7 @@ static int vmx_hardware_enable(void) * This can happen if we hot-added a CPU but failed to allocate * VP assist page for it. */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) + if (kvm_is_using_evmcs() && !hv_get_vp_assist_page(cpu)) return -EFAULT; intel_pt_handle_vmx(1); @@ -2869,7 +2868,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) memset(vmcs, 0, vmcs_config.size); /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else vmcs->hdr.revision_id = vmcs_config.revision_id; @@ -2964,7 +2963,7 @@ static __init int alloc_kvm_area(void) * still be marked with revision_id reported by * physical CPU. */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = vmcs_config.revision_id; per_cpu(vmxarea, cpu) = vmcs; @@ -3931,7 +3930,7 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + if (kvm_is_using_evmcs()) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; if (evmcs->hv_enlightenments_control.msr_bitmap) @@ -7310,7 +7309,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) { + if (kvm_is_using_evmcs()) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; @@ -7440,7 +7439,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) * feature only for vmcs01, KVM currently isn't equipped to realize any * performance benefits from enabling it for vmcs02. */ - if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + if (kvm_is_using_evmcs() && (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index db95bde52998..ce47dc265f89 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -147,7 +147,7 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) static __always_inline u16 vmcs_read16(unsigned long field) { vmcs_check16(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read16(field); return __vmcs_readl(field); } @@ -155,7 +155,7 @@ static __always_inline u16 vmcs_read16(unsigned long field) static __always_inline u32 vmcs_read32(unsigned long field) { vmcs_check32(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read32(field); return __vmcs_readl(field); } @@ -163,7 +163,7 @@ static __always_inline u32 vmcs_read32(unsigned long field) static __always_inline u64 vmcs_read64(unsigned long field) { vmcs_check64(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read64(field); #ifdef CONFIG_X86_64 return __vmcs_readl(field); @@ -175,7 +175,7 @@ static __always_inline u64 vmcs_read64(unsigned long field) static __always_inline unsigned long vmcs_readl(unsigned long field) { vmcs_checkl(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read64(field); return __vmcs_readl(field); } @@ -222,7 +222,7 @@ static __always_inline void __vmcs_writel(unsigned long field, unsigned long val static __always_inline void vmcs_write16(unsigned long field, u16 value) { vmcs_check16(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write16(field, value); __vmcs_writel(field, value); @@ -231,7 +231,7 @@ static __always_inline void vmcs_write16(unsigned long field, u16 value) static __always_inline void vmcs_write32(unsigned long field, u32 value) { vmcs_check32(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, value); __vmcs_writel(field, value); @@ -240,7 +240,7 @@ static __always_inline void vmcs_write32(unsigned long field, u32 value) static __always_inline void vmcs_write64(unsigned long field, u64 value) { vmcs_check64(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write64(field, value); __vmcs_writel(field, value); @@ -252,7 +252,7 @@ static __always_inline void vmcs_write64(unsigned long field, u64 value) static __always_inline void vmcs_writel(unsigned long field, unsigned long value) { vmcs_checkl(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write64(field, value); __vmcs_writel(field, value); @@ -262,7 +262,7 @@ static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask) { BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, "vmcs_clear_bits does not support 64-bit fields"); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, evmcs_read32(field) & ~mask); __vmcs_writel(field, __vmcs_readl(field) & ~mask); @@ -272,7 +272,7 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) { BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, "vmcs_set_bits does not support 64-bit fields"); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, evmcs_read32(field) | mask); __vmcs_writel(field, __vmcs_readl(field) | mask); @@ -289,7 +289,7 @@ static inline void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_load(phys_addr); vmx_asm1(vmptrld, "m"(phys_addr), vmcs, phys_addr); -- GitLab From fbc722aac1ce66960de50c0f488b6ff865a41d74 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 11 Feb 2023 00:35:34 +0000 Subject: [PATCH 0471/5631] KVM: VMX: Rename "KVM is using eVMCS" static key to match its wrapper Rename enable_evmcs to __kvm_is_using_evmcs to match its wrapper, and to avoid confusion with enabling eVMCS for nested virtualization, i.e. have "enable eVMCS" be reserved for "enable eVMCS support for L1". No functional change intended. Signed-off-by: Sean Christopherson Message-Id: <20230211003534.564198-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/hyperv.c | 2 +- arch/x86/kvm/vmx/hyperv.h | 4 ++-- arch/x86/kvm/vmx/vmx.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 274fbd38c64e..79450e1ed7cf 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -609,7 +609,7 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) } #if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(enable_evmcs); +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); /* * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index a54a2fdf0a5b..9623fe1651c4 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -67,11 +67,11 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, #if IS_ENABLED(CONFIG_HYPERV) -DECLARE_STATIC_KEY_FALSE(enable_evmcs); +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); static __always_inline bool kvm_is_using_evmcs(void) { - return static_branch_unlikely(&enable_evmcs); + return static_branch_unlikely(&__kvm_is_using_evmcs); } static __always_inline int get_evmcs_offset(unsigned long field, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 09e07fb83c37..f777509ecf17 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -579,7 +579,7 @@ static __init void hv_init_evmcs(void) if (enlightened_vmcs) { pr_info("Using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); + static_branch_enable(&__kvm_is_using_evmcs); } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) -- GitLab From f7ca74904dab2f9157fb17463b4fcaf641cc370d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 27 Feb 2023 09:09:11 +0100 Subject: [PATCH 0472/5631] MIPS: BCM47XX: Add support for Huawei B593u-12 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It's a BCM5358 based home router. One of very few bcm47xx devices with cellular modems (here: LTE). Signed-off-by: Rafał Miłecki Reviewed-by: Florian Fainelli Signed-off-by: Thomas Bogendoerfer --- arch/mips/bcm47xx/board.c | 1 + arch/mips/bcm47xx/leds.c | 8 ++++++++ arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h | 1 + 3 files changed, 10 insertions(+) diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c index 90fb48b046c0..b487f687f62d 100644 --- a/arch/mips/bcm47xx/board.c +++ b/arch/mips/bcm47xx/board.c @@ -193,6 +193,7 @@ struct bcm47xx_board_type_list1 bcm47xx_board_list_board_id[] __initconst = { /* boardtype, boardnum, boardrev */ static const struct bcm47xx_board_type_list3 bcm47xx_board_list_board[] __initconst = { + {{BCM47XX_BOARD_HUAWEI_B593U_12, "Huawei B593u-12"}, "0x053d", "1234", "0x1301"}, {{BCM47XX_BOARD_HUAWEI_E970, "Huawei E970"}, "0x048e", "0x5347", "0x11"}, {{BCM47XX_BOARD_PHICOMM_M1, "Phicomm M1"}, "0x0590", "80", "0x1104"}, {{BCM47XX_BOARD_ZTE_H218N, "ZTE H218N"}, "0x053d", "1234", "0x1305"}, diff --git a/arch/mips/bcm47xx/leds.c b/arch/mips/bcm47xx/leds.c index 8e257d0896d2..64e37505b9b4 100644 --- a/arch/mips/bcm47xx/leds.c +++ b/arch/mips/bcm47xx/leds.c @@ -222,6 +222,11 @@ bcm47xx_leds_dlink_dir330[] __initconst = { /* Huawei */ +static const struct gpio_led +bcm47xx_leds_huawei_b593u_12[] __initconst = { + BCM47XX_GPIO_LED(5, "blue", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF), +}; + static const struct gpio_led bcm47xx_leds_huawei_e970[] __initconst = { BCM47XX_GPIO_LED(0, "unk", "wlan", 0, LEDS_GPIO_DEFSTATE_OFF), @@ -672,6 +677,9 @@ void __init bcm47xx_leds_register(void) bcm47xx_set_pdata(bcm47xx_leds_dlink_dir330); break; + case BCM47XX_BOARD_HUAWEI_B593U_12: + bcm47xx_set_pdata(bcm47xx_leds_huawei_b593u_12); + break; case BCM47XX_BOARD_HUAWEI_E970: bcm47xx_set_pdata(bcm47xx_leds_huawei_e970); break; diff --git a/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h b/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h index 3c401f11655e..4bd8c86ec6c3 100644 --- a/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h +++ b/arch/mips/include/asm/mach-bcm47xx/bcm47xx_board.h @@ -53,6 +53,7 @@ enum bcm47xx_board { BCM47XX_BOARD_DLINK_DIR130, BCM47XX_BOARD_DLINK_DIR330, + BCM47XX_BOARD_HUAWEI_B593U_12, BCM47XX_BOARD_HUAWEI_E970, BCM47XX_BOARD_LINKSYS_E900V1, -- GitLab From 5bd3990723bdf43333b2c268cc6644cb1961125b Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 21 Feb 2023 13:16:54 +0000 Subject: [PATCH 0473/5631] MIPS: Loongson64: Prefix ipi register address pointers with __iomem They are truely mmio pointers, so give them proper prefix. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/loongson64/smp.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index 660e1de4412a..c268c6dd1ef1 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -27,11 +27,11 @@ DEFINE_PER_CPU(int, cpu_state); #define LS_IPI_IRQ (MIPS_CPU_IRQ_BASE + 6) -static void *ipi_set0_regs[16]; -static void *ipi_clear0_regs[16]; -static void *ipi_status0_regs[16]; -static void *ipi_en0_regs[16]; -static void *ipi_mailbox_buf[16]; +static void __iomem *ipi_set0_regs[16]; +static void __iomem *ipi_clear0_regs[16]; +static void __iomem *ipi_status0_regs[16]; +static void __iomem *ipi_en0_regs[16]; +static void __iomem *ipi_mailbox_buf[16]; static uint32_t core0_c0count[NR_CPUS]; /* read a 32bit value from ipi register */ -- GitLab From ac24cc1835c8e6400230f0bf50e6ba0ab75cb09f Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 21 Feb 2023 13:16:55 +0000 Subject: [PATCH 0474/5631] MIPS: Loongson64: smp: Use nudge_writes instead of wbflush wbflush here intends to let other cores see the results ASAP, nudge_writes fits this purpose better. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/loongson64/smp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index c268c6dd1ef1..e9d91da7fe24 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -42,13 +42,13 @@ static uint32_t core0_c0count[NR_CPUS]; #define loongson3_ipi_write32(action, addr) \ do { \ writel(action, addr); \ - __wbflush(); \ + nudge_writes(); \ } while (0) /* write a 64bit value to ipi register */ #define loongson3_ipi_write64(action, addr) \ do { \ writeq(action, addr); \ - __wbflush(); \ + nudge_writes(); \ } while (0) static u32 (*ipi_read_clear)(int cpu); @@ -418,7 +418,7 @@ static irqreturn_t loongson3_ipi_interrupt(int irq, void *dev_id) c0count = c0count ? c0count : 1; for (i = 1; i < nr_cpu_ids; i++) core0_c0count[i] = c0count; - __wbflush(); /* Let others see the result ASAP */ + nudge_writes(); /* Let others see the result ASAP */ } return IRQ_HANDLED; -- GitLab From 227003cb5325298a26276f49bebbfaf39d903be4 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 21 Feb 2023 13:16:56 +0000 Subject: [PATCH 0475/5631] MIPS: Loongson64: smp: Correct nudge_writes usage Previously every write to SMP regisers are followed by nudge_writes, this incures a huge performance penalty because nudge_writes involves SYNC, which will be globalized on chip. Only set off nudge_writes when we really want other cores to see the result ASAP. Also replace read/write functions to relaxed version because we don't need extra barriers to protect against DMA. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/loongson64/smp.c | 38 ++++++++++++-------------------------- 1 file changed, 12 insertions(+), 26 deletions(-) diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index e9d91da7fe24..90c783981197 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -34,23 +34,6 @@ static void __iomem *ipi_en0_regs[16]; static void __iomem *ipi_mailbox_buf[16]; static uint32_t core0_c0count[NR_CPUS]; -/* read a 32bit value from ipi register */ -#define loongson3_ipi_read32(addr) readl(addr) -/* read a 64bit value from ipi register */ -#define loongson3_ipi_read64(addr) readq(addr) -/* write a 32bit value to ipi register */ -#define loongson3_ipi_write32(action, addr) \ - do { \ - writel(action, addr); \ - nudge_writes(); \ - } while (0) -/* write a 64bit value to ipi register */ -#define loongson3_ipi_write64(action, addr) \ - do { \ - writeq(action, addr); \ - nudge_writes(); \ - } while (0) - static u32 (*ipi_read_clear)(int cpu); static void (*ipi_write_action)(int cpu, u32 action); static void (*ipi_write_enable)(int cpu); @@ -136,26 +119,28 @@ static u32 legacy_ipi_read_clear(int cpu) u32 action; /* Load the ipi register to figure out what we're supposed to do */ - action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]); + action = readl_relaxed(ipi_status0_regs[cpu_logical_map(cpu)]); /* Clear the ipi register to clear the interrupt */ - loongson3_ipi_write32(action, ipi_clear0_regs[cpu_logical_map(cpu)]); + writel_relaxed(action, ipi_clear0_regs[cpu_logical_map(cpu)]); + nudge_writes(); return action; } static void legacy_ipi_write_action(int cpu, u32 action) { - loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu]); + writel_relaxed((u32)action, ipi_set0_regs[cpu]); + nudge_writes(); } static void legacy_ipi_write_enable(int cpu) { - loongson3_ipi_write32(0xffffffff, ipi_en0_regs[cpu_logical_map(cpu)]); + writel_relaxed(0xffffffff, ipi_en0_regs[cpu_logical_map(cpu)]); } static void legacy_ipi_clear_buf(int cpu) { - loongson3_ipi_write64(0, ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); + writeq_relaxed(0, ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); } static void legacy_ipi_write_buf(int cpu, struct task_struct *idle) @@ -171,14 +156,15 @@ static void legacy_ipi_write_buf(int cpu, struct task_struct *idle) pr_debug("CPU#%d, func_pc=%lx, sp=%lx, gp=%lx\n", cpu, startargs[0], startargs[1], startargs[2]); - loongson3_ipi_write64(startargs[3], + writeq_relaxed(startargs[3], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x18); - loongson3_ipi_write64(startargs[2], + writeq_relaxed(startargs[2], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x10); - loongson3_ipi_write64(startargs[1], + writeq_relaxed(startargs[1], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x8); - loongson3_ipi_write64(startargs[0], + writeq_relaxed(startargs[0], ipi_mailbox_buf[cpu_logical_map(cpu)] + 0x0); + nudge_writes(); } static void csr_ipi_probe(void) -- GitLab From 162e134aedcacc9ab9d5648349ceb5409f9ec880 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 21 Feb 2023 13:16:57 +0000 Subject: [PATCH 0476/5631] MIPS: Loongson64: Remove CPU_HAS_WB Q: Do we have really have write buffer A: Yes, on newer Loongson processors there is a "store fill buffer" that will collect *cached* writes, on all Loongson processors AXI crossbar will buffer all writes. Q: Then why do we want to remove CPU_HAS_WB? A: Because CPU_HAS_WB introduces wbflush, which intends to flush all write reuqests to mmio device. We won't be affected by store fill buffer because it won't buffer uncached writes. And a regular memory barrier is sufficient to flush crossbar write buffer. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 1 - arch/mips/loongson64/setup.c | 15 --------------- 2 files changed, 16 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e2f3ca73f40d..6f275ace27be 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -490,7 +490,6 @@ config MACH_LOONGSON64 select BOARD_SCACHE select CSRC_R4K select CEVT_R4K - select CPU_HAS_WB select FORCE_PCI select ISA select I8259 diff --git a/arch/mips/loongson64/setup.c b/arch/mips/loongson64/setup.c index 3cd11c2b308b..257038e18779 100644 --- a/arch/mips/loongson64/setup.c +++ b/arch/mips/loongson64/setup.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include @@ -17,20 +16,6 @@ void *loongson_fdt_blob; -static void wbflush_loongson(void) -{ - asm(".set\tpush\n\t" - ".set\tnoreorder\n\t" - ".set mips3\n\t" - "sync\n\t" - "nop\n\t" - ".set\tpop\n\t" - ".set mips0\n\t"); -} - -void (*__wbflush)(void) = wbflush_loongson; -EXPORT_SYMBOL(__wbflush); - void __init plat_mem_setup(void) { if (loongson_fdt_blob) -- GitLab From 7b76ab837522fd6aa72b25d1c5460995095fedc0 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 21 Feb 2023 13:16:58 +0000 Subject: [PATCH 0477/5631] MIPS: Loongson64: Opt-out war_io_reorder_wmb It is clearly stated on "Loongson 3A3000/3B3000 processor user manual vol 2" that "All access requests using a non-cached algorithm are executed in a blocking order. That is, before the current read request data is returned to the processor, all subsequent requests are blocked and issued; All subsequent requests are blocked until the write request data has been sent or the issued write request has not received a write reply from the final receiver." Which means uncached read/write is strongly ordered. So we won't need this workaround. This option was introduced when we add initial support for GS464E, it looks like a misinterpretation of another section in the manual saying we need barriers to ensure MMIO order against DMA requests. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h index e6d5ccaa309e..cc28d207a061 100644 --- a/arch/mips/include/asm/io.h +++ b/arch/mips/include/asm/io.h @@ -210,7 +210,7 @@ void iounmap(const volatile void __iomem *addr); #define ioremap_wc(offset, size) \ ioremap_prot((offset), (size), boot_cpu_data.writecombine) -#if defined(CONFIG_CPU_CAVIUM_OCTEON) || defined(CONFIG_CPU_LOONGSON64) +#if defined(CONFIG_CPU_CAVIUM_OCTEON) #define war_io_reorder_wmb() wmb() #else #define war_io_reorder_wmb() barrier() -- GitLab From e9a440e0923cddc0f9455dab55ae1b8b47a3e660 Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Tue, 21 Feb 2023 19:01:42 +0800 Subject: [PATCH 0478/5631] dt-bindings: mips: loongson: Add Loongson-1 based boards Add two Loongson-1 based boards: LSGZ 1B and Smartloong 1C. Signed-off-by: Keguang Zhang Reviewed-by: Rob Herring Signed-off-by: Thomas Bogendoerfer --- .../devicetree/bindings/mips/loongson/devices.yaml | 12 ++++++++++++ .../devicetree/bindings/vendor-prefixes.yaml | 2 ++ 2 files changed, 14 insertions(+) diff --git a/Documentation/devicetree/bindings/mips/loongson/devices.yaml b/Documentation/devicetree/bindings/mips/loongson/devices.yaml index f13ce386f42c..099e40e1482d 100644 --- a/Documentation/devicetree/bindings/mips/loongson/devices.yaml +++ b/Documentation/devicetree/bindings/mips/loongson/devices.yaml @@ -37,6 +37,18 @@ properties: items: - const: loongson,loongson64v-4core-virtio + - description: LS1B based boards + items: + - enum: + - loongson,lsgz-1b-dev + - const: loongson,ls1b + + - description: LS1C based boards + items: + - enum: + - loongmasses,smartloong-1c + - const: loongson,ls1c + additionalProperties: true ... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index ed64e06ecca4..06d8c326fc3d 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -769,6 +769,8 @@ patternProperties: description: Lontium Semiconductor Corporation "^loongson,.*": description: Loongson Technology Corporation Limited + "^loongmasses,.*": + description: Nanjing Loongmasses Ltd. "^lsi,.*": description: LSI Corp. (LSI Logic) "^lwn,.*": -- GitLab From 13a9d0bea9d1cb119c9ce59c95b51cbb954827cc Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:57:55 +0100 Subject: [PATCH 0479/5631] mips: ralink: rt305x: define RT305X_SYSC_BASE with __iomem So that RT305X_SYSC_BASE can be used later in multiple functions without needing to repeat this __iomem declaration each time Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ralink/rt305x.h | 3 ++- arch/mips/ralink/rt305x.c | 8 +++----- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/mips/include/asm/mach-ralink/rt305x.h b/arch/mips/include/asm/mach-ralink/rt305x.h index 4d8e8c8d83ce..ef58f7bff957 100644 --- a/arch/mips/include/asm/mach-ralink/rt305x.h +++ b/arch/mips/include/asm/mach-ralink/rt305x.h @@ -43,7 +43,8 @@ static inline int soc_is_rt5350(void) return ralink_soc == RT305X_SOC_RT5350; } -#define RT305X_SYSC_BASE 0x10000000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define RT305X_SYSC_BASE IOMEM(0x10000000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c index 8b095a9dcb15..135a46517763 100644 --- a/arch/mips/ralink/rt305x.c +++ b/arch/mips/ralink/rt305x.c @@ -21,11 +21,10 @@ static unsigned long rt5350_get_mem_size(void) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE); unsigned long ret; u32 t; - t = __raw_readl(sysc + SYSC_REG_SYSTEM_CONFIG); + t = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_SYSTEM_CONFIG); t = (t >> RT5350_SYSCFG0_DRAM_SIZE_SHIFT) & RT5350_SYSCFG0_DRAM_SIZE_MASK; @@ -142,14 +141,13 @@ void __init ralink_of_remap(void) void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT305X_SYSC_BASE); unsigned char *name; u32 n0; u32 n1; u32 id; - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); + n0 = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME0); + n1 = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME1); if (n0 == RT3052_CHIP_NAME0 && n1 == RT3052_CHIP_NAME1) { unsigned long icache_sets; -- GitLab From 0def2164c94aa504bd2a3575e74a5f7fd86f5587 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:57:56 +0100 Subject: [PATCH 0480/5631] mips: ralink: rt305x: soc queries and tests as functions Move the SoC register value queries and tests to specific functions, to remove repetition of logic. No functional changes intended Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/rt305x.c | 97 +++++++++++++++++++++++++++++++-------- 1 file changed, 77 insertions(+), 20 deletions(-) diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c index 135a46517763..a24143c739ee 100644 --- a/arch/mips/ralink/rt305x.c +++ b/arch/mips/ralink/rt305x.c @@ -139,52 +139,109 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init rt305x_get_soc_name0(void) +{ + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} + +static unsigned int __init rt305x_get_soc_name1(void) { - unsigned char *name; - u32 n0; - u32 n1; - u32 id; + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} - n0 = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_NAME1); +static bool __init rt3052_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3052_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3052_CHIP_NAME1) + return true; + else + return false; +} - if (n0 == RT3052_CHIP_NAME0 && n1 == RT3052_CHIP_NAME1) { +static bool __init rt3350_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3350_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3350_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init rt3352_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT3352_CHIP_NAME0 && + rt305x_get_soc_name1() == RT3352_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init rt5350_soc_valid(void) +{ + if (rt305x_get_soc_name0() == RT5350_CHIP_NAME0 && + rt305x_get_soc_name1() == RT5350_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt305x_get_soc_name(struct ralink_soc_info *soc_info) +{ + if (rt3052_soc_valid()) { unsigned long icache_sets; icache_sets = (read_c0_config1() >> 22) & 7; if (icache_sets == 1) { ralink_soc = RT305X_SOC_RT3050; - name = "RT3050"; soc_info->compatible = "ralink,rt3050-soc"; + return "RT3050"; } else { ralink_soc = RT305X_SOC_RT3052; - name = "RT3052"; soc_info->compatible = "ralink,rt3052-soc"; + return "RT3052"; } - } else if (n0 == RT3350_CHIP_NAME0 && n1 == RT3350_CHIP_NAME1) { + } else if (rt3350_soc_valid()) { ralink_soc = RT305X_SOC_RT3350; - name = "RT3350"; soc_info->compatible = "ralink,rt3350-soc"; - } else if (n0 == RT3352_CHIP_NAME0 && n1 == RT3352_CHIP_NAME1) { + return "RT3350"; + } else if (rt3352_soc_valid()) { ralink_soc = RT305X_SOC_RT3352; - name = "RT3352"; soc_info->compatible = "ralink,rt3352-soc"; - } else if (n0 == RT5350_CHIP_NAME0 && n1 == RT5350_CHIP_NAME1) { + return "RT3352"; + } else if (rt5350_soc_valid()) { ralink_soc = RT305X_SOC_RT5350; - name = "RT5350"; soc_info->compatible = "ralink,rt5350-soc"; + return "RT5350"; } else { - panic("rt305x: unknown SoC, n0:%08x n1:%08x", n0, n1); + panic("rt305x: unknown SoC, n0:%08x n1:%08x", + rt305x_get_soc_name0(), rt305x_get_soc_name1()); } +} + +static unsigned int __init rt305x_get_soc_id(void) +{ + return __raw_readl(RT305X_SYSC_BASE + SYSC_REG_CHIP_ID); +} + +static unsigned int __init rt305x_get_soc_ver(void) +{ + return (rt305x_get_soc_id() >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK; +} - id = __raw_readl(sysc + SYSC_REG_CHIP_ID); +static unsigned int __init rt305x_get_soc_rev(void) +{ + return (rt305x_get_soc_id() & CHIP_ID_REV_MASK); +} + +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + const char *name = rt305x_get_soc_name(soc_info); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s id:%u rev:%u", name, - (id >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK, - (id & CHIP_ID_REV_MASK)); + rt305x_get_soc_ver(), + rt305x_get_soc_rev()); soc_info->mem_base = RT305X_SDRAM_BASE; if (soc_is_rt5350()) { -- GitLab From bf27860fcabdd61d4bd33ce9488dc68bae5c7107 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:57:57 +0100 Subject: [PATCH 0481/5631] mips: ralink: rt305x: introduce 'soc_device' initialization RT305x SoCs have their own 'ralink_soc_info' structure with some information about the soc itself. In order to be able to retrieve this information from driver code and avoid architecture dependencies for retrieving these details introduce this 'soc_device'. Set 'data' pointer points to the struct 'ralink_soc_info' to be able to export also current soc information using this mechanism. We need to select 'SOC_BUS' in Kconfig configuration for these SoCs. Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/Kconfig | 1 + arch/mips/ralink/rt305x.c | 46 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 83e61e147b90..0b0459f1f83e 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -32,6 +32,7 @@ choice config SOC_RT305X bool "RT305x" + select SOC_BUS config SOC_RT3883 bool "RT3883" diff --git a/arch/mips/ralink/rt305x.c b/arch/mips/ralink/rt305x.c index a24143c739ee..d8dcc5cc66cc 100644 --- a/arch/mips/ralink/rt305x.c +++ b/arch/mips/ralink/rt305x.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include @@ -19,6 +21,8 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + static unsigned long rt5350_get_mem_size(void) { unsigned long ret; @@ -233,6 +237,46 @@ static unsigned int __init rt305x_get_soc_rev(void) return (rt305x_get_soc_id() & CHIP_ID_REV_MASK); } +static const char __init *rt305x_get_soc_id_name(void) +{ + if (soc_is_rt3050()) + return "rt3050"; + else if (soc_is_rt3052()) + return "rt3052"; + else if (soc_is_rt3350()) + return "rt3350"; + else if (soc_is_rt3352()) + return "rt3352"; + else if (soc_is_rt5350()) + return "rt5350"; + else + return "invalid"; +} + +static int __init rt305x_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt305x_get_soc_id_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(rt305x_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { const char *name = rt305x_get_soc_name(soc_info); @@ -253,4 +297,6 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) soc_info->mem_size_min = RT3352_MEM_SIZE_MIN; soc_info->mem_size_max = RT3352_MEM_SIZE_MAX; } + + soc_info_ptr = soc_info; } -- GitLab From 7edb1775846ebc5a7f4d5085ff6d712ed137a460 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:57:58 +0100 Subject: [PATCH 0482/5631] mips: ralink: rt3883: define RT3883_SYSC_BASE with __iomem So that RT3883_SYSC_BASE can be used later in multiple functions without needing to repeat this __iomem declaration each time Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ralink/rt3883.h | 4 +++- arch/mips/ralink/rt3883.c | 7 +++---- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/mips/include/asm/mach-ralink/rt3883.h b/arch/mips/include/asm/mach-ralink/rt3883.h index f250de9c055b..ad25d5e8d2dc 100644 --- a/arch/mips/include/asm/mach-ralink/rt3883.h +++ b/arch/mips/include/asm/mach-ralink/rt3883.h @@ -10,8 +10,10 @@ #include +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) + #define RT3883_SDRAM_BASE 0x00000000 -#define RT3883_SYSC_BASE 0x10000000 +#define RT3883_SYSC_BASE IOMEM(0x10000000) #define RT3883_TIMER_BASE 0x10000100 #define RT3883_INTC_BASE 0x10000200 #define RT3883_MEMC_BASE 0x10000300 diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index d9875f146d66..fa215c07558d 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -72,15 +72,14 @@ void __init ralink_of_remap(void) void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT3883_SYSC_BASE); const char *name; u32 n0; u32 n1; u32 id; - n0 = __raw_readl(sysc + RT3883_SYSC_REG_CHIPID0_3); - n1 = __raw_readl(sysc + RT3883_SYSC_REG_CHIPID4_7); - id = __raw_readl(sysc + RT3883_SYSC_REG_REVID); + n0 = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID0_3); + n1 = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID4_7); + id = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_REVID); if (n0 == RT3883_CHIP_NAME0 && n1 == RT3883_CHIP_NAME1) { soc_info->compatible = "ralink,rt3883-soc"; -- GitLab From 89f9b3041e7eddfcfa7260d7e0d2846b21f316d1 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:57:59 +0100 Subject: [PATCH 0483/5631] mips: ralink: rt3883: soc queries and tests as functions Move the SoC register value queries and tests to specific functions, to remove repetition of logic. No functional changes intended Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/rt3883.c | 64 +++++++++++++++++++++++++++++---------- 1 file changed, 48 insertions(+), 16 deletions(-) diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index fa215c07558d..6f8541a4bc8e 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -70,29 +70,61 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init rt3883_get_soc_name0(void) +{ + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID0_3); +} + +static unsigned int __init rt3883_get_soc_name1(void) +{ + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID4_7); +} + +static bool __init rt3883_soc_valid(void) +{ + if (rt3883_get_soc_name0() == RT3883_CHIP_NAME0 && + rt3883_get_soc_name1() == RT3883_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt3883_get_soc_name(void) +{ + if (rt3883_soc_valid()) + return "RT3883"; + else + return "invalid"; +} + +static unsigned int __init rt3883_get_soc_id(void) { - const char *name; - u32 n0; - u32 n1; - u32 id; + return __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_REVID); +} - n0 = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID0_3); - n1 = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_CHIPID4_7); - id = __raw_readl(RT3883_SYSC_BASE + RT3883_SYSC_REG_REVID); +static unsigned int __init rt3883_get_soc_ver(void) +{ + return (rt3883_get_soc_id() >> RT3883_REVID_VER_ID_SHIFT) & RT3883_REVID_VER_ID_MASK; +} - if (n0 == RT3883_CHIP_NAME0 && n1 == RT3883_CHIP_NAME1) { +static unsigned int __init rt3883_get_soc_rev(void) +{ + return (rt3883_get_soc_id() & RT3883_REVID_ECO_ID_MASK); +} + +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + if (rt3883_soc_valid()) soc_info->compatible = "ralink,rt3883-soc"; - name = "RT3883"; - } else { - panic("rt3883: unknown SoC, n0:%08x n1:%08x", n0, n1); - } + else + panic("rt3883: unknown SoC, n0:%08x n1:%08x", + rt3883_get_soc_name0(), rt3883_get_soc_name1()); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s ver:%u eco:%u", - name, - (id >> RT3883_REVID_VER_ID_SHIFT) & RT3883_REVID_VER_ID_MASK, - (id & RT3883_REVID_ECO_ID_MASK)); + rt3883_get_soc_name(), + rt3883_get_soc_ver(), + rt3883_get_soc_rev()); soc_info->mem_base = RT3883_SDRAM_BASE; soc_info->mem_size_min = RT3883_MEM_SIZE_MIN; -- GitLab From 2165248f68b5f3e27faac844795e6691e1ee7777 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:00 +0100 Subject: [PATCH 0484/5631] mips: ralink: rt3883: introduce 'soc_device' initialization RT3883 SoC have its own 'ralink_soc_info' structure with some information about the soc itself. In order to be able to retrieve this information from driver code and avoid architecture dependencies for retrieving these details introduce this 'soc_device'. Set 'data' pointer points to the struct 'ralink_soc_info' to be able to export also current soc information using this mechanism. We need to select 'SOC_BUS' in Kconfig configuration for these SoCs. Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/Kconfig | 1 + arch/mips/ralink/rt3883.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index 0b0459f1f83e..e2a43a59fc81 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -37,6 +37,7 @@ choice config SOC_RT3883 bool "RT3883" select HAVE_PCI + select SOC_BUS config SOC_MT7620 bool "MT7620/8" diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index 6f8541a4bc8e..cca887af378f 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include #include @@ -17,6 +19,8 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + void __init ralink_clk_init(void) { unsigned long cpu_rate, sys_rate; @@ -112,6 +116,30 @@ static unsigned int __init rt3883_get_soc_rev(void) return (rt3883_get_soc_id() & RT3883_REVID_ECO_ID_MASK); } +static int __init rt3883_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt3883_get_soc_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(rt3883_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { if (rt3883_soc_valid()) @@ -131,4 +159,5 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) soc_info->mem_size_max = RT3883_MEM_SIZE_MAX; ralink_soc = RT3883_SOC; + soc_info_ptr = soc_info; } -- GitLab From 1e688601d18d3d872ffaad70c599e8c1a1d788a0 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:01 +0100 Subject: [PATCH 0485/5631] mips: ralink: rt288x: define RT2880_SYSC_BASE with __iomem So that RT2880_SYSC_BASE can be used later in multiple functions without needing to repeat this __iomem declaration each time Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ralink/rt288x.h | 3 ++- arch/mips/ralink/rt288x.c | 7 +++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/mips/include/asm/mach-ralink/rt288x.h b/arch/mips/include/asm/mach-ralink/rt288x.h index 5f213534f0f5..66a999cd1d80 100644 --- a/arch/mips/include/asm/mach-ralink/rt288x.h +++ b/arch/mips/include/asm/mach-ralink/rt288x.h @@ -11,7 +11,8 @@ #ifndef _RT288X_REGS_H_ #define _RT288X_REGS_H_ -#define RT2880_SYSC_BASE 0x00300000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define RT2880_SYSC_BASE IOMEM(0x00300000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c index 493335db2fe1..12f339138c4c 100644 --- a/arch/mips/ralink/rt288x.c +++ b/arch/mips/ralink/rt288x.c @@ -59,15 +59,14 @@ void __init ralink_of_remap(void) void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(RT2880_SYSC_BASE); const char *name; u32 n0; u32 n1; u32 id; - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); - id = __raw_readl(sysc + SYSC_REG_CHIP_ID); + n0 = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME0); + n1 = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME1); + id = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_ID); if (n0 == RT2880_CHIP_NAME0 && n1 == RT2880_CHIP_NAME1) { soc_info->compatible = "ralink,r2880-soc"; -- GitLab From 5a5aa151bdccea934d4a84086661538b60a09a42 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:02 +0100 Subject: [PATCH 0486/5631] mips: ralink: rt288x: soc queries and tests as functions Move the SoC register value queries and tests to specific functions, to remove repetition of logic. No functional changes intended Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/rt288x.c | 63 +++++++++++++++++++++++++++++---------- 1 file changed, 47 insertions(+), 16 deletions(-) diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c index 12f339138c4c..a417b8b89b94 100644 --- a/arch/mips/ralink/rt288x.c +++ b/arch/mips/ralink/rt288x.c @@ -57,29 +57,60 @@ void __init ralink_of_remap(void) panic("Failed to remap core resources"); } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init rt2880_get_soc_name0(void) { - const char *name; - u32 n0; - u32 n1; - u32 id; + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} - n0 = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME1); - id = __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_ID); +static unsigned int __init rt2880_get_soc_name1(void) +{ + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} - if (n0 == RT2880_CHIP_NAME0 && n1 == RT2880_CHIP_NAME1) { +static bool __init rt2880_soc_valid(void) +{ + if (rt2880_get_soc_name0() == RT2880_CHIP_NAME0 && + rt2880_get_soc_name1() == RT2880_CHIP_NAME1) + return true; + else + return false; +} + +static const char __init *rt2880_get_soc_name(void) +{ + if (rt2880_soc_valid()) + return "RT2880"; + else + return "invalid"; +} + +static unsigned int __init rt2880_get_soc_id(void) +{ + return __raw_readl(RT2880_SYSC_BASE + SYSC_REG_CHIP_ID); +} + +static unsigned int __init rt2880_get_soc_ver(void) +{ + return (rt2880_get_soc_id() >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK; +} + +static unsigned int __init rt2880_get_soc_rev(void) +{ + return (rt2880_get_soc_id() & CHIP_ID_REV_MASK); +} +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + if (rt2880_soc_valid()) soc_info->compatible = "ralink,r2880-soc"; - name = "RT2880"; - } else { - panic("rt288x: unknown SoC, n0:%08x n1:%08x", n0, n1); - } + else + panic("rt288x: unknown SoC, n0:%08x n1:%08x", + rt2880_get_soc_name0(), rt2880_get_soc_name1()); snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "Ralink %s id:%u rev:%u", - name, - (id >> CHIP_ID_ID_SHIFT) & CHIP_ID_ID_MASK, - (id & CHIP_ID_REV_MASK)); + rt2880_get_soc_name(), + rt2880_get_soc_ver(), + rt2880_get_soc_rev()); soc_info->mem_base = RT2880_SDRAM_BASE; soc_info->mem_size_min = RT2880_MEM_SIZE_MIN; -- GitLab From 7a26b384c44cfa9ea65799dc375619c96608ecad Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:03 +0100 Subject: [PATCH 0487/5631] mips: ralink: rt288x: introduce 'soc_device' initialization RT288X SoCs have their own 'ralink_soc_info' structure with some information about the soc itself. In order to be able to retrieve this information from driver code and avoid architecture dependencies for retrieving these details introduce this 'soc_device'. Set 'data' pointer points to the struct 'ralink_soc_info' to be able to export also current soc information using this mechanism. We need to select 'SOC_BUS' in Kconfig configuration for these SoCs. Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/Kconfig | 1 + arch/mips/ralink/rt288x.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index e2a43a59fc81..e8b8fb35d33d 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -29,6 +29,7 @@ choice select MIPS_AUTO_PFN_OFFSET select MIPS_L1_CACHE_SHIFT_4 select HAVE_PCI + select SOC_BUS config SOC_RT305X bool "RT305x" diff --git a/arch/mips/ralink/rt288x.c b/arch/mips/ralink/rt288x.c index a417b8b89b94..456ba0b2599e 100644 --- a/arch/mips/ralink/rt288x.c +++ b/arch/mips/ralink/rt288x.c @@ -10,6 +10,8 @@ #include #include +#include +#include #include #include @@ -17,6 +19,8 @@ #include "common.h" +static struct ralink_soc_info *soc_info_ptr; + void __init ralink_clk_init(void) { unsigned long cpu_rate, wmac_rate = 40000000; @@ -98,6 +102,31 @@ static unsigned int __init rt2880_get_soc_rev(void) { return (rt2880_get_soc_id() & CHIP_ID_REV_MASK); } + +static int __init rt2880_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = rt2880_get_soc_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(rt2880_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { if (rt2880_soc_valid()) @@ -117,4 +146,5 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) soc_info->mem_size_max = RT2880_MEM_SIZE_MAX; ralink_soc = RT2880_SOC; + soc_info_ptr = soc_info; } -- GitLab From 217cf927e7c6ab41dc276442600f1309613ad417 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:04 +0100 Subject: [PATCH 0488/5631] mips: ralink: mt7620: define MT7620_SYSC_BASE with __iomem So that MT7620_SYSC_BASE can be used later in multiple functions without needing to repeat this __iomem declaration each time Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-ralink/mt7620.h | 3 ++- arch/mips/ralink/mt7620.c | 15 +++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/mips/include/asm/mach-ralink/mt7620.h b/arch/mips/include/asm/mach-ralink/mt7620.h index d51dfad8f543..3e37705ea9cf 100644 --- a/arch/mips/include/asm/mach-ralink/mt7620.h +++ b/arch/mips/include/asm/mach-ralink/mt7620.h @@ -11,7 +11,8 @@ #ifndef _MT7620_REGS_H_ #define _MT7620_REGS_H_ -#define MT7620_SYSC_BASE 0x10000000 +#define IOMEM(x) ((void __iomem *)(KSEG1ADDR(x))) +#define MT7620_SYSC_BASE IOMEM(0x10000000) #define SYSC_REG_CHIP_NAME0 0x00 #define SYSC_REG_CHIP_NAME1 0x04 diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index ae1fa0391c88..c13b73b6ee3f 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -326,7 +326,6 @@ mt7628_dram_init(struct ralink_soc_info *soc_info) void __init prom_soc_init(struct ralink_soc_info *soc_info) { - void __iomem *sysc = (void __iomem *) KSEG1ADDR(MT7620_SYSC_BASE); unsigned char *name = NULL; u32 n0; u32 n1; @@ -336,9 +335,9 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) u32 pmu1; u32 bga; - n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1); - rev = __raw_readl(sysc + SYSC_REG_CHIP_REV); + n0 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME0); + n1 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME1); + rev = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_REV); bga = (rev >> CHIP_REV_PKG_SHIFT) & CHIP_REV_PKG_MASK; if (n0 == MT7620_CHIP_NAME0 && n1 == MT7620_CHIP_NAME1) { @@ -352,7 +351,7 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) soc_info->compatible = "ralink,mt7620n-soc"; } } else if (n0 == MT7620_CHIP_NAME0 && n1 == MT7628_CHIP_NAME1) { - u32 efuse = __raw_readl(sysc + SYSC_REG_EFUSE_CFG); + u32 efuse = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_EFUSE_CFG); if (efuse & EFUSE_MT7688) { ralink_soc = MT762X_SOC_MT7688; @@ -372,7 +371,7 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) (rev >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK, (rev & CHIP_REV_ECO_MASK)); - cfg0 = __raw_readl(sysc + SYSC_REG_SYSTEM_CONFIG0); + cfg0 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_SYSTEM_CONFIG0); if (is_mt76x8()) { dram_type = cfg0 & DRAM_TYPE_MT7628_MASK; } else { @@ -388,8 +387,8 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) else mt7620_dram_init(soc_info); - pmu0 = __raw_readl(sysc + PMU0_CFG); - pmu1 = __raw_readl(sysc + PMU1_CFG); + pmu0 = __raw_readl(MT7620_SYSC_BASE + PMU0_CFG); + pmu1 = __raw_readl(MT7620_SYSC_BASE + PMU1_CFG); pr_info("Analog PMU set to %s control\n", (pmu0 & PMU_SW_SET) ? ("sw") : ("hw")); -- GitLab From 727ea3c77dd9b94d994708a148b82df76a47fa79 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:05 +0100 Subject: [PATCH 0489/5631] mips: ralink: mt7620: soc queries and tests as functions Move the SoC register value queries and tests to specific functions, to remove repetition of logic. No functional changes intended Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/mt7620.c | 94 ++++++++++++++++++++++++++++++--------- 1 file changed, 72 insertions(+), 22 deletions(-) diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index c13b73b6ee3f..8604d91f3375 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -324,34 +324,76 @@ mt7628_dram_init(struct ralink_soc_info *soc_info) } } -void __init prom_soc_init(struct ralink_soc_info *soc_info) +static unsigned int __init mt7620_get_soc_name0(void) { - unsigned char *name = NULL; - u32 n0; - u32 n1; - u32 rev; - u32 cfg0; - u32 pmu0; - u32 pmu1; - u32 bga; + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME0); +} + +static unsigned int __init mt7620_get_soc_name1(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME1); +} + +static bool __init mt7620_soc_valid(void) +{ + if (mt7620_get_soc_name0() == MT7620_CHIP_NAME0 && + mt7620_get_soc_name1() == MT7620_CHIP_NAME1) + return true; + else + return false; +} + +static bool __init mt7628_soc_valid(void) +{ + if (mt7620_get_soc_name0() == MT7620_CHIP_NAME0 && + mt7620_get_soc_name1() == MT7628_CHIP_NAME1) + return true; + else + return false; +} - n0 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME0); - n1 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_NAME1); - rev = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_REV); - bga = (rev >> CHIP_REV_PKG_SHIFT) & CHIP_REV_PKG_MASK; +static unsigned int __init mt7620_get_rev(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_CHIP_REV); +} + +static unsigned int __init mt7620_get_bga(void) +{ + return (mt7620_get_rev() >> CHIP_REV_PKG_SHIFT) & CHIP_REV_PKG_MASK; +} + +static unsigned int __init mt7620_get_efuse(void) +{ + return __raw_readl(MT7620_SYSC_BASE + SYSC_REG_EFUSE_CFG); +} + +static unsigned int __init mt7620_get_soc_ver(void) +{ + return (mt7620_get_rev() >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK; +} + +static unsigned int __init mt7620_get_soc_eco(void) +{ + return (mt7620_get_rev() & CHIP_REV_ECO_MASK); +} + +static const char __init *mt7620_get_soc_name(struct ralink_soc_info *soc_info) +{ + if (mt7620_soc_valid()) { + u32 bga = mt7620_get_bga(); - if (n0 == MT7620_CHIP_NAME0 && n1 == MT7620_CHIP_NAME1) { if (bga) { ralink_soc = MT762X_SOC_MT7620A; - name = "MT7620A"; soc_info->compatible = "ralink,mt7620a-soc"; + return "MT7620A"; } else { ralink_soc = MT762X_SOC_MT7620N; - name = "MT7620N"; soc_info->compatible = "ralink,mt7620n-soc"; + return "MT7620N"; } - } else if (n0 == MT7620_CHIP_NAME0 && n1 == MT7628_CHIP_NAME1) { - u32 efuse = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_EFUSE_CFG); + } else if (mt7628_soc_valid()) { + u32 efuse = mt7620_get_efuse(); + unsigned char *name = NULL; if (efuse & EFUSE_MT7688) { ralink_soc = MT762X_SOC_MT7688; @@ -361,15 +403,23 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) name = "MT7628AN"; } soc_info->compatible = "ralink,mt7628an-soc"; + return name; } else { - panic("mt762x: unknown SoC, n0:%08x n1:%08x\n", n0, n1); + panic("mt762x: unknown SoC, n0:%08x n1:%08x\n", + mt7620_get_soc_name0(), mt7620_get_soc_name1()); } +} + +void __init prom_soc_init(struct ralink_soc_info *soc_info) +{ + const char *name = mt7620_get_soc_name(soc_info); + u32 cfg0; + u32 pmu0; + u32 pmu1; snprintf(soc_info->sys_type, RAMIPS_SYS_TYPE_LEN, "MediaTek %s ver:%u eco:%u", - name, - (rev >> CHIP_REV_VER_SHIFT) & CHIP_REV_VER_MASK, - (rev & CHIP_REV_ECO_MASK)); + name, mt7620_get_soc_ver(), mt7620_get_soc_eco()); cfg0 = __raw_readl(MT7620_SYSC_BASE + SYSC_REG_SYSTEM_CONFIG0); if (is_mt76x8()) { -- GitLab From 83552892b772dfc4639a4f2da075bbb5d605b788 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Mon, 27 Feb 2023 11:58:06 +0100 Subject: [PATCH 0490/5631] mips: ralink: mt7620: introduce 'soc_device' initialization MT7620 SoCs have their own 'ralink_soc_info' structure with some information about the soc itself. In order to be able to retrieve this information from driver code and avoid architecture dependencies for retrieving these details introduce this 'soc_device'. Set 'data' pointer points to the struct 'ralink_soc_info' to be able to export also current soc information using this mechanism. We need to select 'SOC_BUS' in Kconfig configuration for these SoCs. Signed-off-by: Sergio Paracuellos Signed-off-by: Thomas Bogendoerfer --- arch/mips/ralink/Kconfig | 1 + arch/mips/ralink/mt7620.c | 44 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/arch/mips/ralink/Kconfig b/arch/mips/ralink/Kconfig index e8b8fb35d33d..08c012a2591f 100644 --- a/arch/mips/ralink/Kconfig +++ b/arch/mips/ralink/Kconfig @@ -44,6 +44,7 @@ choice bool "MT7620/8" select CPU_MIPSR2_IRQ_VI select HAVE_PCI + select SOC_BUS config SOC_MT7621 bool "MT7621" diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index 8604d91f3375..4435f50b8d24 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include @@ -49,6 +51,8 @@ /* does the board have sdram or ddram */ static int dram_type; +static struct ralink_soc_info *soc_info_ptr; + static __init u32 mt7620_calc_rate(u32 ref_rate, u32 mul, u32 div) { @@ -410,6 +414,44 @@ static const char __init *mt7620_get_soc_name(struct ralink_soc_info *soc_info) } } +static const char __init *mt7620_get_soc_id_name(void) +{ + if (ralink_soc == MT762X_SOC_MT7620A) + return "mt7620a"; + else if (ralink_soc == MT762X_SOC_MT7620N) + return "mt7620n"; + else if (ralink_soc == MT762X_SOC_MT7688) + return "mt7688"; + else if (ralink_soc == MT762X_SOC_MT7628AN) + return "mt7628n"; + else + return "invalid"; +} + +static int __init mt7620_soc_dev_init(void) +{ + struct soc_device *soc_dev; + struct soc_device_attribute *soc_dev_attr; + + soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL); + if (!soc_dev_attr) + return -ENOMEM; + + soc_dev_attr->family = "Ralink"; + soc_dev_attr->soc_id = mt7620_get_soc_id_name(); + + soc_dev_attr->data = soc_info_ptr; + + soc_dev = soc_device_register(soc_dev_attr); + if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr); + return PTR_ERR(soc_dev); + } + + return 0; +} +device_initcall(mt7620_soc_dev_init); + void __init prom_soc_init(struct ralink_soc_info *soc_info) { const char *name = mt7620_get_soc_name(soc_info); @@ -444,4 +486,6 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) (pmu0 & PMU_SW_SET) ? ("sw") : ("hw")); pr_info("Digital PMU set to %s control\n", (pmu1 & DIG_SW_SEL) ? ("sw") : ("hw")); + + soc_info_ptr = soc_info; } -- GitLab From 9c99b4880d178a3cc6f42634b995d526a86f746b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:46:56 -0600 Subject: [PATCH 0491/5631] mips: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Thomas Bogendoerfer --- arch/mips/pci/pci-lantiq.c | 2 +- arch/mips/pci/pci-rt3883.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c index d967e4c0cf24..79e29bf42a24 100644 --- a/arch/mips/pci/pci-lantiq.c +++ b/arch/mips/pci/pci-lantiq.c @@ -118,7 +118,7 @@ static int ltq_pci_startup(struct platform_device *pdev) /* and enable the clocks */ clk_enable(clk_pci); - if (of_find_property(node, "lantiq,external-clock", NULL)) + if (of_property_read_bool(node, "lantiq,external-clock")) clk_enable(clk_external); else clk_disable(clk_external); diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c index d59888aaed81..4ac68a534e4f 100644 --- a/arch/mips/pci/pci-rt3883.c +++ b/arch/mips/pci/pci-rt3883.c @@ -419,7 +419,7 @@ static int rt3883_pci_probe(struct platform_device *pdev) /* find the interrupt controller child node */ for_each_child_of_node(np, child) { - if (of_get_property(child, "interrupt-controller", NULL)) { + if (of_property_read_bool(child, "interrupt-controller")) { rpc->intc_of_node = child; break; } -- GitLab From b720bf90339742ef32b8add76f131f812ed1228a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 13 Mar 2023 22:33:10 -0700 Subject: [PATCH 0492/5631] perf vendor events intel: Update graniterapids events Update from 1.00 to 1.01, some event description updates. Signed-off-by: Ian Rogers Reviewed-by: Kan Liang Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230314053312.3237390-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/graniterapids/frontend.json | 2 +- tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json | 4 ++-- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json index dfd9c5ea1584..c6d5016e7337 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/frontend.json @@ -3,7 +3,7 @@ "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", "EventCode": "0x9c", "EventName": "IDQ_BUBBLES.CORE", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the nominator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json index d6aafb258708..764c0435d1d2 100644 --- a/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/graniterapids/pipeline.json @@ -72,7 +72,7 @@ "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", "EventCode": "0xa4", "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the nominator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "10000003", "UMask": "0x2" }, @@ -95,7 +95,7 @@ "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", "EventCode": "0xc2", "EventName": "UOPS_RETIRED.SLOTS", - "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the nominator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", "SampleAfterValue": "2000003", "UMask": "0x2" } diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index bb4e545fa100..210dd9b2004f 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -9,7 +9,7 @@ GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core -GenuineIntel-6-A[DE],v1.00,graniterapids,core +GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v32,haswell,core GenuineIntel-6-3F,v26,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core -- GitLab From 591530c0f5644d5fa8549ab4a738916cb6779dbf Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 13 Mar 2023 22:33:11 -0700 Subject: [PATCH 0493/5631] perf vendor events intel: Update meteorlake events Update from 1.00 to 1.01. Event description updates. Addition of IDQ_BUBBLES.CORE, TOPDOWN.BACKEND_BOUND_SLOTS, UOPS_RETIRED.SLOTS. Signed-off-by: Ian Rogers Reviewed-by: Kan Liang Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230314053312.3237390-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../pmu-events/arch/x86/meteorlake/cache.json | 8 +++++ .../arch/x86/meteorlake/frontend.json | 9 +++++ .../arch/x86/meteorlake/memory.json | 13 +++++-- .../pmu-events/arch/x86/meteorlake/other.json | 4 +-- .../arch/x86/meteorlake/pipeline.json | 36 +++++++++++++++++-- .../arch/x86/meteorlake/virtual-memory.json | 4 +++ 7 files changed, 69 insertions(+), 7 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 210dd9b2004f..34431709f7d0 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -18,7 +18,7 @@ GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core GenuineIntel-6-2D,v22,jaketown,core GenuineIntel-6-(57|85),v10,knightslanding,core -GenuineIntel-6-A[AC],v1.00,meteorlake,core +GenuineIntel-6-A[AC],v1.01,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v18,sandybridge,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index 0970724a2984..bf24d3f25a3d 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -3,6 +3,7 @@ "BriefDescription": "L2 code requests", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", "UMask": "0xe4", "Unit": "cpu_core" @@ -11,6 +12,7 @@ "BriefDescription": "Demand Data Read access L2 cache", "EventCode": "0x24", "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", "SampleAfterValue": "200003", "UMask": "0xe1", "Unit": "cpu_core" @@ -19,6 +21,7 @@ "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x41", "Unit": "cpu_atom" @@ -27,6 +30,7 @@ "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x41", "Unit": "cpu_core" @@ -35,6 +39,7 @@ "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", "SampleAfterValue": "200003", "UMask": "0x4f", "Unit": "cpu_atom" @@ -43,6 +48,7 @@ "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", "EventCode": "0x2e", "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", "SampleAfterValue": "100003", "UMask": "0x4f", "Unit": "cpu_core" @@ -53,6 +59,7 @@ "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_LOADS", "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "1000003", "UMask": "0x81", "Unit": "cpu_core" @@ -63,6 +70,7 @@ "EventCode": "0xd0", "EventName": "MEM_INST_RETIRED.ALL_STORES", "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", "SampleAfterValue": "1000003", "UMask": "0x82", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index 7de11819dd0d..66e5609699ea 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -14,5 +14,14 @@ "SampleAfterValue": "200003", "UMask": "0x2", "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index b7715cec1dbc..20c2efe70eeb 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -7,6 +7,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x80", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "1009", "UMask": "0x1", "Unit": "cpu_core" @@ -19,6 +20,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x10", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "20011", "UMask": "0x1", "Unit": "cpu_core" @@ -31,6 +33,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x100", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "503", "UMask": "0x1", "Unit": "cpu_core" @@ -43,6 +46,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x20", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100007", "UMask": "0x1", "Unit": "cpu_core" @@ -55,6 +59,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x4", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "100003", "UMask": "0x1", "Unit": "cpu_core" @@ -67,6 +72,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x200", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "101", "UMask": "0x1", "Unit": "cpu_core" @@ -79,6 +85,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x40", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "2003", "UMask": "0x1", "Unit": "cpu_core" @@ -91,6 +98,7 @@ "MSRIndex": "0x3F6", "MSRValue": "0x8", "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", "SampleAfterValue": "50021", "UMask": "0x1", "Unit": "cpu_core" @@ -101,12 +109,13 @@ "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", "PEBS": "2", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", "SampleAfterValue": "1000003", "UMask": "0x2", "Unit": "cpu_core" }, { - "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.", + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", "MSRIndex": "0x1a6,0x1a7", @@ -126,7 +135,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.", + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index ae98e3d0e149..14e648bf11c5 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "BriefDescription": "Counts demand data reads that have any type of response.", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -20,7 +20,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index 7be7e40c03ac..639789478073 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -4,6 +4,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, @@ -12,6 +13,7 @@ "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", + "PublicDescription": "Counts all branch instructions retired.", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -20,6 +22,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", "SampleAfterValue": "200003", "Unit": "cpu_atom" }, @@ -28,6 +31,7 @@ "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", "SampleAfterValue": "400009", "Unit": "cpu_core" }, @@ -39,7 +43,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of unhalted core clock cycles[This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.CORE_P", "SampleAfterValue": "2000003", @@ -55,6 +59,7 @@ { "BriefDescription": "Reference cycles when the core is not in halt state.", "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x3", "Unit": "cpu_core" @@ -63,6 +68,7 @@ "BriefDescription": "Reference cycles when the core is not in halt state.", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -77,12 +83,13 @@ { "BriefDescription": "Core cycles when the thread is not in halt state", "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", "SampleAfterValue": "2000003", "UMask": "0x2", "Unit": "cpu_core" }, { - "BriefDescription": "Counts the number of unhalted core clock cycles[This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", "SampleAfterValue": "2000003", @@ -92,6 +99,7 @@ "BriefDescription": "Thread cycles when thread is not in halt state", "EventCode": "0x3c", "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -107,6 +115,7 @@ "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", "EventName": "INST_RETIRED.ANY", "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "UMask": "0x1", "Unit": "cpu_core" @@ -124,6 +133,7 @@ "EventCode": "0xc0", "EventName": "INST_RETIRED.ANY_P", "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", "SampleAfterValue": "2000003", "Unit": "cpu_core" }, @@ -131,13 +141,24 @@ "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", "EventCode": "0x03", "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", "SampleAfterValue": "100003", "UMask": "0x82", "Unit": "cpu_core" }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, { "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", "SampleAfterValue": "10000003", "UMask": "0x4", "Unit": "cpu_core" @@ -146,6 +167,7 @@ "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", "EventCode": "0xa4", "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", "SampleAfterValue": "10000003", "UMask": "0x1", "Unit": "cpu_core" @@ -154,6 +176,7 @@ "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "SampleAfterValue": "1000003", "Unit": "cpu_atom" }, @@ -178,5 +201,14 @@ "PEBS": "1", "SampleAfterValue": "1000003", "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" } ] diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json index 0ee62378bf22..556e4292fcc8 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/virtual-memory.json @@ -3,6 +3,7 @@ "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", "EventCode": "0x12", "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -11,6 +12,7 @@ "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", "EventCode": "0x13", "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" @@ -19,6 +21,7 @@ "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", "SampleAfterValue": "200003", "UMask": "0xe", "Unit": "cpu_atom" @@ -27,6 +30,7 @@ "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", "EventCode": "0x11", "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", "SampleAfterValue": "100003", "UMask": "0xe", "Unit": "cpu_core" -- GitLab From 3da9559e4131a38ab9c38add53d496bc4c7aea27 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 13 Mar 2023 22:33:12 -0700 Subject: [PATCH 0494/5631] perf vendor events intel: Update skylake events Update from v54 to v55. Addition of OFFCORE_RESPONSE, FP_ARITH_INST_RETIRED.SCALAR, FP_ARITH_INST_RETIRED.VECTOR and INT_MISC.CLEARS_COUNT. Signed-off-by: Ian Rogers Reviewed-by: Kan Liang Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230314053312.3237390-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- tools/perf/pmu-events/arch/x86/skylake/cache.json | 8 ++++++++ .../arch/x86/skylake/floating-point.json | 15 +++++++++++++++ .../pmu-events/arch/x86/skylake/pipeline.json | 10 ++++++++++ 4 files changed, 34 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 34431709f7d0..9abebe50ae0d 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -24,7 +24,7 @@ GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v18,sandybridge,core GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core -GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v54,skylake,core +GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v55,skylake,core GenuineIntel-6-55-[01234],v1.29,skylakex,core GenuineIntel-6-86,v1.20,snowridgex,core GenuineIntel-6-8[CD],v1.10,tigerlake,core diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json index 0080ac27b899..ce592d871949 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json @@ -553,6 +553,14 @@ "SampleAfterValue": "2000003", "UMask": "0x4" }, + { + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, { "BriefDescription": "Counts all demand code reads have any response type.", "EventCode": "0xB7, 0xBB", diff --git a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json index eb83fa537e7d..4d494a5cabbf 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylake/floating-point.json @@ -31,6 +31,14 @@ "SampleAfterValue": "2000003", "UMask": "0x20" }, + { + "BriefDescription": "Counts once for most SIMD scalar computational floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Counts once for most SIMD scalar computational single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SIMD scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, { "BriefDescription": "Counts once for most SIMD scalar computational double precision floating-point instructions retired. Counts twice for DPP and FM(N)ADD/SUB instructions retired.", "EventCode": "0xC7", @@ -47,6 +55,13 @@ "SampleAfterValue": "2000003", "UMask": "0x2" }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "SampleAfterValue": "2000003", + "UMask": "0xfc" + }, { "BriefDescription": "Cycles with any input/output SSE or FP assist", "CounterMask": "1", diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json index 2c827d806554..2dfc3af08eff 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json @@ -404,6 +404,16 @@ "SampleAfterValue": "2000003", "UMask": "0x1" }, + { + "AnyThread": "1", + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, { "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "EventCode": "0x0D", -- GitLab From bdecfecac8aba6ca5e2fde8f09b4fba1d1326997 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:01:58 +0100 Subject: [PATCH 0495/5631] perf vendor events s390: Add cache metrics for z15 Add metrics for s390 z15 - Percentage sourced from Level 2 cache - Percentage sourced from Level 3 on same chip cache - Percentage sourced from Level 4 Local cache on same book - Percentage sourced from Level 4 Remote cache on different book - Percentage sourced from memory For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Outpuf after: # ./perf stat -M l4rp -- find / .... find output deleted Performance counter stats for 'find /': 5 L1I_OFFDRAWER_L4_SOURCED_WRITES # 0.01 l4rp 187 L1D_OFFDRAWER_L4_SOURCED_WRITES 0 L1I_OFFDRAWER_L3_SOURCED_WRITES 231,333,165 L1I_DIR_WRITES 3,303 L1D_OFFDRAWER_L3_SOURCED_WRITES 47,461 L1D_OFFDRAWER_L3_SOURCED_WRITES_IV 0 L1I_OFFDRAWER_L3_SOURCED_WRITES_IV 126,706,244 L1D_DIR_WRITES 27.870355461 seconds time elapsed 0.521562000 seconds user 12.494503000 seconds sys # Signed-off-by: Thomas Richter Acked-By: Sumanth Korikkar Acked-by: Ian Rogers Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-3-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/s390/cf_z15/transaction.json | 25 +++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json index 86bf83b4504e..cca237bdb7ba 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json @@ -18,5 +18,30 @@ "BriefDescription": "Level One Miss per 100 Instructions", "MetricName": "l1mp", "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 2 cache", + "MetricName": "l2p", + "MetricExpr": "((L1D_L2D_SOURCED_WRITES + L1I_L2I_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 3 on same chip cache", + "MetricName": "l3p", + "MetricExpr": "((L1D_ONCHIP_L3_SOURCED_WRITES + L1D_ONCHIP_L3_SOURCED_WRITES_IV + L1I_ONCHIP_L3_SOURCED_WRITES + L1I_ONCHIP_L3_SOURCED_WRITES_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Local cache on same book", + "MetricName": "l4lp", + "MetricExpr": "((L1D_ONCLUSTER_L3_SOURCED_WRITES + L1D_ONCLUSTER_L3_SOURCED_WRITES_IV + L1D_ONDRAWER_L4_SOURCED_WRITES + L1I_ONCLUSTER_L3_SOURCED_WRITES + L1I_ONCLUSTER_L3_SOURCED_WRITES_IV + L1I_ONDRAWER_L4_SOURCED_WRITES + L1D_OFFCLUSTER_L3_SOURCED_WRITES + L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV + L1D_ONCHIP_L3_SOURCED_WRITES_RO + L1I_OFFCLUSTER_L3_SOURCED_WRITES + L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book", + "MetricName": "l4rp", + "MetricExpr": "((L1D_OFFDRAWER_L3_SOURCED_WRITES + L1D_OFFDRAWER_L3_SOURCED_WRITES_IV + L1D_OFFDRAWER_L4_SOURCED_WRITES + L1I_OFFDRAWER_L3_SOURCED_WRITES + L1I_OFFDRAWER_L3_SOURCED_WRITES_IV + L1I_OFFDRAWER_L4_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from memory", + "MetricName": "memp", + "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" } ] -- GitLab From add7894a25d1c572b2e472557f2b1150dbc991ee Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:01:59 +0100 Subject: [PATCH 0496/5631] perf vendor events s390: Add cache metrics for z14 Add metrics for s390 z14 - Percentage sourced from Level 2 cache - Percentage sourced from Level 3 on same chip cache - Percentage sourced from Level 4 Local cache on same book - Percentage sourced from Level 4 Remote cache on different book - Percentage sourced from memory For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Output after: # ./perf stat -M l4rp -- find / .... find output deleted Performance counter stats for 'find /': 0 L1I_OFFDRAWER_L4_SOURCED_WRITES # 0.01 l4rp 84 L1D_OFFDRAWER_L4_SOURCED_WRITES 0 L1I_OFFDRAWER_L3_SOURCED_WRITES 71,535,353 L1I_DIR_WRITES 219 L1D_OFFDRAWER_L3_SOURCED_WRITES 16,436 L1D_OFFDRAWER_L3_SOURCED_WRITES_IV 0 L1I_OFFDRAWER_L3_SOURCED_WRITES_IV 46,343,940 L1D_DIR_WRITES 10.530805537 seconds time elapsed 0.774396000 seconds user 1.602714000 seconds sys # Signed-off-by: Thomas Richter Acked-by: Ian Rogers Acked-By: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-3-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/s390/cf_z14/transaction.json | 25 +++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json index 86bf83b4504e..cca237bdb7ba 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -18,5 +18,30 @@ "BriefDescription": "Level One Miss per 100 Instructions", "MetricName": "l1mp", "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 2 cache", + "MetricName": "l2p", + "MetricExpr": "((L1D_L2D_SOURCED_WRITES + L1I_L2I_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 3 on same chip cache", + "MetricName": "l3p", + "MetricExpr": "((L1D_ONCHIP_L3_SOURCED_WRITES + L1D_ONCHIP_L3_SOURCED_WRITES_IV + L1I_ONCHIP_L3_SOURCED_WRITES + L1I_ONCHIP_L3_SOURCED_WRITES_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Local cache on same book", + "MetricName": "l4lp", + "MetricExpr": "((L1D_ONCLUSTER_L3_SOURCED_WRITES + L1D_ONCLUSTER_L3_SOURCED_WRITES_IV + L1D_ONDRAWER_L4_SOURCED_WRITES + L1I_ONCLUSTER_L3_SOURCED_WRITES + L1I_ONCLUSTER_L3_SOURCED_WRITES_IV + L1I_ONDRAWER_L4_SOURCED_WRITES + L1D_OFFCLUSTER_L3_SOURCED_WRITES + L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV + L1D_ONCHIP_L3_SOURCED_WRITES_RO + L1I_OFFCLUSTER_L3_SOURCED_WRITES + L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book", + "MetricName": "l4rp", + "MetricExpr": "((L1D_OFFDRAWER_L3_SOURCED_WRITES + L1D_OFFDRAWER_L3_SOURCED_WRITES_IV + L1D_OFFDRAWER_L4_SOURCED_WRITES + L1I_OFFDRAWER_L3_SOURCED_WRITES + L1I_OFFDRAWER_L3_SOURCED_WRITES_IV + L1I_OFFDRAWER_L4_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from memory", + "MetricName": "memp", + "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" } ] -- GitLab From 850eea236f8ad4a648cb7997eed8a3c616cc0678 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:02:00 +0100 Subject: [PATCH 0497/5631] perf vendor events s390: Add cache metrics for z13 Add metrics for s390 z13 - Percentage sourced from Level 2 cache - Percentage sourced from Level 3 on same chip cache - Percentage sourced from Level 4 Local cache on same book - Percentage sourced from Level 4 Remote cache on different book - Percentage sourced from memory For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Output after: # ./perf stat -M l4rp -- find / ...find output deleted Performance counter stats for 'find /': 2 L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES # 0.02 l4rp 252 L1D_ONDRAWER_L4_SOURCED_WRITES 3,465 L1D_ONDRAWER_L3_SOURCED_WRITES_IV 80 L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES 761 L1D_ONDRAWER_L3_SOURCED_WRITES 0 L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES 131,817,067 L1I_DIR_WRITES 1 L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES 447 L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES 22 L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES 7 L1I_ONDRAWER_L4_SOURCED_WRITES 0 L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES 1,071 L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES 3 L1I_ONDRAWER_L3_SOURCED_WRITES 13,352 L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV 15,252 L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV 0 L1I_ONDRAWER_L3_SOURCED_WRITES_IV 0 L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV 57,431,083 L1D_DIR_WRITES 0 L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV 15.386502874 seconds time elapsed 0.647348000 seconds user 3.537041000 seconds sys # Signed-off-by: Thomas Richter Acked-By: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-3-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/s390/cf_z13/transaction.json | 25 +++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json index 86bf83b4504e..71e2c7fa734c 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -18,5 +18,30 @@ "BriefDescription": "Level One Miss per 100 Instructions", "MetricName": "l1mp", "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 2 cache", + "MetricName": "l2p", + "MetricExpr": "((L1D_L2D_SOURCED_WRITES + L1I_L2I_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 3 on same chip cache", + "MetricName": "l3p", + "MetricExpr": "((L1D_ONCHIP_L3_SOURCED_WRITES + L1D_ONCHIP_L3_SOURCED_WRITES_IV + L1I_ONCHIP_L3_SOURCED_WRITES + L1I_ONCHIP_L3_SOURCED_WRITES_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Local cache on same book", + "MetricName": "l4lp", + "MetricExpr": "((L1D_ONNODE_L4_SOURCED_WRITES + L1D_ONNODE_L3_SOURCED_WRITES_IV + L1D_ONNODE_L3_SOURCED_WRITES + L1I_ONNODE_L4_SOURCED_WRITES + L1I_ONNODE_L3_SOURCED_WRITES_IV + L1I_ONNODE_L3_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book", + "MetricName": "l4rp", + "MetricExpr": "((L1D_ONDRAWER_L4_SOURCED_WRITES + L1D_ONDRAWER_L3_SOURCED_WRITES_IV + L1D_ONDRAWER_L3_SOURCED_WRITES + L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES + L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV + L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES + L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES + L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV + L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES + L1I_ONDRAWER_L4_SOURCED_WRITES + L1I_ONDRAWER_L3_SOURCED_WRITES_IV + L1I_ONDRAWER_L3_SOURCED_WRITES + L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES + L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV + L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES + L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES + L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV + L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Percentage sourced from memory", + "MetricName": "memp", + "MetricExpr": "((L1D_ONNODE_MEM_SOURCED_WRITES + L1D_ONDRAWER_MEM_SOURCED_WRITES + L1D_OFFDRAWER_MEM_SOURCED_WRITES + L1D_ONCHIP_MEM_SOURCED_WRITES + L1I_ONNODE_MEM_SOURCED_WRITES + L1I_ONDRAWER_MEM_SOURCED_WRITES + L1I_OFFDRAWER_MEM_SOURCED_WRITES + L1I_ONCHIP_MEM_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" } ] -- GitLab From 4c290d4fa3aeed74e37637acaa1a787f194fe43d Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Mon, 13 Mar 2023 09:02:01 +0100 Subject: [PATCH 0498/5631] perf vendor events s390: Add metric for TLB and cache Add metrics for tlb and cache statistics: - finite_cpi: Cycles per Instructions from Finite cache/memory - est_cpi: Estimated Instruction Complexity CPI infinite Level 1 - scpl1m: Estimated Sourcing Cycles per Level 1 Miss - tlb_percent: Estimated TLB CPU percentage of Total CPU - tlb_miss: Estimated Cycles per TLB Miss For details about the formulas see this documentation: https://www.ibm.com/support/pages/system/files/inline-files/CPU%20MF%20Formulas%20including%20z16%20-%20May%202022_1.pdf Output after: # ./perf stat -M tlb_miss -- dd if=/dev/zero of=/dev/null bs=1M count=10K ... dd output removed Performance counter stats for 'dd if=/dev/zero of=/dev/null bs=1M count=10K': 667,726 DTLB2_MISSES # 440.96 tlb_miss 198 ITLB2_WRITES 795,170,260 L1C_TLB2_MISSES 9,478 ITLB2_MISSES 820 DTLB2_WRITES 1,197,126,869 L1D_PENALTY_CYCLES 2,457,447 L1I_PENALTY_CYCLES 1.249342187 seconds time elapsed 0.001030000 seconds user 1.248105000 seconds sys # Signed-off-by: Thomas Richter Acked-by: Ian Rogers Acked-By: Sumanth Korikkar Cc: Heiko Carstens Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230313080201.2440201-3-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/s390/cf_z13/transaction.json | 30 +++++++++++++++++++ .../arch/s390/cf_z14/transaction.json | 25 ++++++++++++++++ .../arch/s390/cf_z15/transaction.json | 25 ++++++++++++++++ .../arch/s390/cf_z16/transaction.json | 25 ++++++++++++++++ 4 files changed, 105 insertions(+) diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json index 71e2c7fa734c..b941a7212a4d 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json @@ -43,5 +43,35 @@ "BriefDescription": "Percentage sourced from memory", "MetricName": "memp", "MetricExpr": "((L1D_ONNODE_MEM_SOURCED_WRITES + L1D_ONDRAWER_MEM_SOURCED_WRITES + L1D_OFFDRAWER_MEM_SOURCED_WRITES + L1D_ONCHIP_MEM_SOURCED_WRITES + L1I_ONNODE_MEM_SOURCED_WRITES + L1I_ONDRAWER_MEM_SOURCED_WRITES + L1I_OFFDRAWER_MEM_SOURCED_WRITES + L1I_ONCHIP_MEM_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Cycles per Instructions from Finite cache/memory", + "MetricName": "finite_cpi", + "MetricExpr": "L1C_TLB1_MISSES / INSTRUCTIONS" + }, + { + "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1", + "MetricName": "est_cpi", + "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB1_MISSES / INSTRUCTIONS)" + }, + { + "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss", + "MetricName": "scpl1m", + "MetricExpr": "L1C_TLB1_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)" + }, + { + "BriefDescription": "Estimated TLB CPU percentage of Total CPU", + "MetricName": "tlb_percent", + "MetricExpr": "((DTLB1_MISSES + ITLB1_MISSES) / CPU_CYCLES) * (L1C_TLB1_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100" + }, + { + "BriefDescription": "Estimated Cycles per TLB Miss", + "MetricName": "tlb_miss", + "MetricExpr": "((DTLB1_MISSES + ITLB1_MISSES) / (DTLB1_WRITES + ITLB1_WRITES)) * (L1C_TLB1_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))" + }, + { + "BriefDescription": "Page Table Entry misses", + "MetricName": "pte_miss", + "MetricExpr": "(TLB2_PTE_WRITES / (DTLB1_WRITES + ITLB1_WRITES)) * 100" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json index cca237bdb7ba..ce814ea93396 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json @@ -43,5 +43,30 @@ "BriefDescription": "Percentage sourced from memory", "MetricName": "memp", "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Cycles per Instructions from Finite cache/memory", + "MetricName": "finite_cpi", + "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS" + }, + { + "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1", + "MetricName": "est_cpi", + "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)" + }, + { + "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss", + "MetricName": "scpl1m", + "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)" + }, + { + "BriefDescription": "Estimated TLB CPU percentage of Total CPU", + "MetricName": "tlb_percent", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100" + }, + { + "BriefDescription": "Estimated Cycles per TLB Miss", + "MetricName": "tlb_miss", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json index cca237bdb7ba..ce814ea93396 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json @@ -43,5 +43,30 @@ "BriefDescription": "Percentage sourced from memory", "MetricName": "memp", "MetricExpr": "((L1D_ONCHIP_MEMORY_SOURCED_WRITES + L1D_ONCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1D_OFFDRAWER_MEMORY_SOURCED_WRITES + L1I_ONCHIP_MEMORY_SOURCED_WRITES + L1I_ONCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES + L1I_OFFDRAWER_MEMORY_SOURCED_WRITES) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Cycles per Instructions from Finite cache/memory", + "MetricName": "finite_cpi", + "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS" + }, + { + "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1", + "MetricName": "est_cpi", + "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)" + }, + { + "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss", + "MetricName": "scpl1m", + "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)" + }, + { + "BriefDescription": "Estimated TLB CPU percentage of Total CPU", + "MetricName": "tlb_percent", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100" + }, + { + "BriefDescription": "Estimated Cycles per TLB Miss", + "MetricName": "tlb_miss", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))" } ] diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json index dde0735a7d22..ec2ff78e2b5f 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json @@ -43,5 +43,30 @@ "BriefDescription": "Percentage sourced from memory", "MetricName": "memp", "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100" + }, + { + "BriefDescription": "Cycles per Instructions from Finite cache/memory", + "MetricName": "finite_cpi", + "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS" + }, + { + "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1", + "MetricName": "est_cpi", + "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)" + }, + { + "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss", + "MetricName": "scpl1m", + "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)" + }, + { + "BriefDescription": "Estimated TLB CPU percentage of Total CPU", + "MetricName": "tlb_percent", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100" + }, + { + "BriefDescription": "Estimated Cycles per TLB Miss", + "MetricName": "tlb_miss", + "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))" } ] -- GitLab From d02fddf24f984b977633c56e10653a8ff19e8c7b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:01 -0600 Subject: [PATCH 0499/5631] clk: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144701.1541504-1-robh@kernel.org Acked-by: Chunyan Zhang Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 4 ++-- drivers/clk/sprd/common.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index ae07685c7588..f7528d7f8256 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4880,8 +4880,8 @@ static struct device_node *get_clk_provider_node(struct device *dev) np = dev->of_node; parent_np = dev->parent ? dev->parent->of_node : NULL; - if (!of_find_property(np, "#clock-cells", NULL)) - if (of_find_property(parent_np, "#clock-cells", NULL)) + if (!of_property_present(np, "#clock-cells")) + if (of_property_present(parent_np, "#clock-cells")) np = parent_np; return np; diff --git a/drivers/clk/sprd/common.c b/drivers/clk/sprd/common.c index ce81e4087a8f..1a3795a61f81 100644 --- a/drivers/clk/sprd/common.c +++ b/drivers/clk/sprd/common.c @@ -44,7 +44,7 @@ int sprd_clk_regmap_init(struct platform_device *pdev, struct device_node *node = dev->of_node, *np; struct regmap *regmap; - if (of_find_property(node, "sprd,syscon", NULL)) { + if (of_property_present(node, "sprd,syscon")) { regmap = syscon_regmap_lookup_by_phandle(node, "sprd,syscon"); if (IS_ERR(regmap)) { pr_err("%s: failed to get syscon regmap\n", __func__); -- GitLab From f1d97a37f975ac615e4d6875c27516150642d499 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Thu, 29 Dec 2022 17:29:46 +0800 Subject: [PATCH 0500/5631] clk: mediatek: clk-pllfh: fix missing of_node_put() in fhctl_parse_dt() The device_node pointer returned by of_find_compatible_node() with refcount incremented, when finish using it, the refcount need be decreased. Fixes: d7964de8a8ea ("clk: mediatek: Add new clock driver to handle FHCTL hardware") Signed-off-by: Yang Yingliang Link: https://lore.kernel.org/r/20221229092946.4162345-1-yangyingliang@huawei.com [sboyd@kernel.org: Also unmap on error] Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-pllfh.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mediatek/clk-pllfh.c b/drivers/clk/mediatek/clk-pllfh.c index f48780bec507..f135b32c6dbe 100644 --- a/drivers/clk/mediatek/clk-pllfh.c +++ b/drivers/clk/mediatek/clk-pllfh.c @@ -75,13 +75,13 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, base = of_iomap(node, 0); if (!base) { pr_err("%s(): ioremap failed\n", __func__); - return; + goto out_node_put; } num_clocks = of_clk_get_parent_count(node); if (!num_clocks) { pr_err("%s(): failed to get clocks property\n", __func__); - return; + goto err; } for (i = 0; i < num_clocks; i++) { @@ -102,6 +102,13 @@ void fhctl_parse_dt(const u8 *compatible_node, struct mtk_pllfh_data *pllfhs, pllfh->state.ssc_rate = ssc_rate; pllfh->state.base = base; } + +out_node_put: + of_node_put(node); + return; +err: + iounmap(base); + goto out_node_put; } static void pllfh_init(struct mtk_fh *fh, struct mtk_pllfh_data *pllfh_data) -- GitLab From 099122af4e29efb41e0db6cc2cd5a07278250e4f Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:45:56 +0100 Subject: [PATCH 0501/5631] riscv: Clarify RISCV_ALTERNATIVE help text Clarify RISCV_ALTERNATIVE's help text by pointing out that code patching is not only done at boot time, but also module load time. Also point out that this is the minimal possible overhead. Signed-off-by: Andrew Jones Link: https://lore.kernel.org/r/20230224154601.88163-2-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..04898c50ef1d 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -379,8 +379,8 @@ config RISCV_ALTERNATIVE help This Kconfig allows the kernel to automatically patch the errata required by the execution platform at run time. The - code patching is performed once in the boot stages. It means - that the overhead from this mechanism is just taken once. + code patching overhead is minimal, as it's only done once + at boot and once on each module load. config RISCV_ALTERNATIVE_EARLY bool -- GitLab From a3d095ac00faee0deb575ba053f0567b0d124d0b Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:45:57 +0100 Subject: [PATCH 0502/5631] riscv: Rename Kconfig.erratas to Kconfig.errata Errata is already plural for erratum. Rename it to make the grammar gooder. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230224154601.88163-3-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 2 +- arch/riscv/{Kconfig.erratas => Kconfig.errata} | 0 2 files changed, 1 insertion(+), 1 deletion(-) rename arch/riscv/{Kconfig.erratas => Kconfig.errata} (100%) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 04898c50ef1d..ab78f677f187 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -245,7 +245,7 @@ config AS_HAS_INSN def_bool $(as-instr,.insn r 51$(comma) 0$(comma) 0$(comma) t0$(comma) t0$(comma) zero) source "arch/riscv/Kconfig.socs" -source "arch/riscv/Kconfig.erratas" +source "arch/riscv/Kconfig.errata" menu "Platform type" diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.errata similarity index 100% rename from arch/riscv/Kconfig.erratas rename to arch/riscv/Kconfig.errata -- GitLab From ce06b42a4a96d46d4844f2b630af7d349a924a58 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:45:58 +0100 Subject: [PATCH 0503/5631] riscv: alternatives: Remove unnecessary define and unused struct A define and a struct were introduced with commit 6f4eea90465a ("riscv: Introduce alternative mechanism to apply errata solution"), which introduced alternatives to RISC-V. The define is used for an arbitrary string length, specific to sifive errata, so just use the number directly there instead. The struct has never been used, so remove it. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230224154601.88163-4-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/sifive/errata.c | 2 +- arch/riscv/include/asm/alternative.h | 7 ------- 2 files changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index da55cb247e89..69dfb38e4f06 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -14,7 +14,7 @@ #include struct errata_info_t { - char name[ERRATA_STRING_LENGTH_MAX]; + char name[32]; bool (*check_func)(unsigned long arch_id, unsigned long impid); }; diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index b8648d4f2ac1..3beef400a971 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -6,8 +6,6 @@ #ifndef __ASM_ALTERNATIVE_H #define __ASM_ALTERNATIVE_H -#define ERRATA_STRING_LENGTH_MAX 32 - #include #ifndef __ASSEMBLY__ @@ -43,11 +41,6 @@ struct alt_entry { u32 errata_id; /* The errata id */ }; -struct errata_checkfunc_id { - unsigned long vendor_id; - bool (*func)(struct alt_entry *alt); -}; - void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); -- GitLab From ff19a8dee196d757dbc32a946843260f0b784ca3 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:45:59 +0100 Subject: [PATCH 0504/5631] riscv: alternatives: Rename errata_id to patch_id Alternatives are used for both errata and cpufeatures. Use a more generic name, 'patch_id', as in "ID of code patching site", to avoid confusion when alternatives are used for cpufeatures. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230224154601.88163-5-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 6 +- arch/riscv/errata/sifive/errata.c | 6 +- arch/riscv/errata/thead/errata.c | 4 +- arch/riscv/include/asm/alternative-macros.h | 72 ++++++++++----------- arch/riscv/include/asm/alternative.h | 4 +- arch/riscv/kernel/cpufeature.c | 6 +- 6 files changed, 49 insertions(+), 49 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index ab78f677f187..69797e6eed6f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -378,9 +378,9 @@ config RISCV_ALTERNATIVE depends on !XIP_KERNEL help This Kconfig allows the kernel to automatically patch the - errata required by the execution platform at run time. The - code patching overhead is minimal, as it's only done once - at boot and once on each module load. + erratum or cpufeature required by the execution platform at run + time. The code patching overhead is minimal, as it's only done + once at boot and once on each module load. config RISCV_ALTERNATIVE_EARLY bool diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index 69dfb38e4f06..7fa7b8b6a811 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -101,12 +101,12 @@ void __init_or_module sifive_errata_patch_func(struct alt_entry *begin, for (alt = begin; alt < end; alt++) { if (alt->vendor_id != SIFIVE_VENDOR_ID) continue; - if (alt->errata_id >= ERRATA_SIFIVE_NUMBER) { - WARN(1, "This errata id:%d is not in kernel errata list", alt->errata_id); + if (alt->patch_id >= ERRATA_SIFIVE_NUMBER) { + WARN(1, "This errata id:%d is not in kernel errata list", alt->patch_id); continue; } - tmp = (1U << alt->errata_id); + tmp = (1U << alt->patch_id); if (cpu_req_errata & tmp) { mutex_lock(&text_mutex); patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 3b96a06d3c54..7e8d50ebb71a 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -93,10 +93,10 @@ void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct al for (alt = begin; alt < end; alt++) { if (alt->vendor_id != THEAD_VENDOR_ID) continue; - if (alt->errata_id >= ERRATA_THEAD_NUMBER) + if (alt->patch_id >= ERRATA_THEAD_NUMBER) continue; - tmp = (1U << alt->errata_id); + tmp = (1U << alt->patch_id); if (cpu_req_errata & tmp) { oldptr = ALT_OLD_PTR(alt); altptr = ALT_ALT_PTR(alt); diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 51c6867e02f3..993a44a8fdac 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -6,18 +6,18 @@ #ifdef __ASSEMBLY__ -.macro ALT_ENTRY oldptr newptr vendor_id errata_id new_len +.macro ALT_ENTRY oldptr newptr vendor_id patch_id new_len .4byte \oldptr - . .4byte \newptr - . .2byte \vendor_id .2byte \new_len - .4byte \errata_id + .4byte \patch_id .endm -.macro ALT_NEW_CONTENT vendor_id, errata_id, enable = 1, new_c : vararg +.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c : vararg .if \enable .pushsection .alternative, "a" - ALT_ENTRY 886b, 888f, \vendor_id, \errata_id, 889f - 888f + ALT_ENTRY 886b, 888f, \vendor_id, \patch_id, 889f - 888f .popsection .subsection 1 888 : @@ -33,7 +33,7 @@ .endif .endm -.macro ALTERNATIVE_CFG old_c, new_c, vendor_id, errata_id, enable +.macro ALTERNATIVE_CFG old_c, new_c, vendor_id, patch_id, enable 886 : .option push .option norvc @@ -41,13 +41,13 @@ \old_c .option pop 887 : - ALT_NEW_CONTENT \vendor_id, \errata_id, \enable, \new_c + ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, \new_c .endm -.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \ - new_c_2, vendor_id_2, errata_id_2, enable_2 - ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1 - ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2 +.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \ + new_c_2, vendor_id_2, patch_id_2, enable_2 + ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \patch_id_1, \enable_1 + ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, \new_c_2 .endm #define __ALTERNATIVE_CFG(...) ALTERNATIVE_CFG __VA_ARGS__ @@ -58,17 +58,17 @@ #include #include -#define ALT_ENTRY(oldptr, newptr, vendor_id, errata_id, newlen) \ +#define ALT_ENTRY(oldptr, newptr, vendor_id, patch_id, newlen) \ ".4byte ((" oldptr ") - .) \n" \ ".4byte ((" newptr ") - .) \n" \ ".2byte " vendor_id "\n" \ ".2byte " newlen "\n" \ - ".4byte " errata_id "\n" + ".4byte " patch_id "\n" -#define ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c) \ +#define ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c) \ ".if " __stringify(enable) " == 1\n" \ ".pushsection .alternative, \"a\"\n" \ - ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(errata_id), "889f - 888f") \ + ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(patch_id), "889f - 888f") \ ".popsection\n" \ ".subsection 1\n" \ "888 :\n" \ @@ -83,7 +83,7 @@ ".previous\n" \ ".endif\n" -#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, enable) \ +#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, enable) \ "886 :\n" \ ".option push\n" \ ".option norvc\n" \ @@ -91,22 +91,22 @@ old_c "\n" \ ".option pop\n" \ "887 :\n" \ - ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c) + ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c) -#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \ - new_c_2, vendor_id_2, errata_id_2, enable_2) \ - __ALTERNATIVE_CFG(old_c, new_c_1, vendor_id_1, errata_id_1, enable_1) \ - ALT_NEW_CONTENT(vendor_id_2, errata_id_2, enable_2, new_c_2) +#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \ + new_c_2, vendor_id_2, patch_id_2, enable_2) \ + __ALTERNATIVE_CFG(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1) \ + ALT_NEW_CONTENT(vendor_id_2, patch_id_2, enable_2, new_c_2) #endif /* __ASSEMBLY__ */ -#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, CONFIG_k) \ - __ALTERNATIVE_CFG(old_c, new_c, vendor_id, errata_id, IS_ENABLED(CONFIG_k)) +#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, CONFIG_k) \ + __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, IS_ENABLED(CONFIG_k)) -#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, CONFIG_k_1, \ - new_c_2, vendor_id_2, errata_id_2, CONFIG_k_2) \ - __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, errata_id_1, IS_ENABLED(CONFIG_k_1), \ - new_c_2, vendor_id_2, errata_id_2, IS_ENABLED(CONFIG_k_2)) +#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_c_2, vendor_id_2, patch_id_2, CONFIG_k_2) \ + __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, IS_ENABLED(CONFIG_k_1), \ + new_c_2, vendor_id_2, patch_id_2, IS_ENABLED(CONFIG_k_2)) #else /* CONFIG_RISCV_ALTERNATIVE */ #ifdef __ASSEMBLY__ @@ -137,19 +137,19 @@ /* * Usage: - * ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k) + * ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) * in the assembly code. Otherwise, - * asm(ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k)); + * asm(ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k)); * * old_content: The old content which is probably replaced with new content. * new_content: The new content. * vendor_id: The CPU vendor ID. - * errata_id: The errata ID. - * CONFIG_k: The Kconfig of this errata. When Kconfig is disabled, the old + * patch_id: The patch ID (erratum ID or cpufeature ID). + * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old * content will alwyas be executed. */ -#define ALTERNATIVE(old_content, new_content, vendor_id, errata_id, CONFIG_k) \ - _ALTERNATIVE_CFG(old_content, new_content, vendor_id, errata_id, CONFIG_k) +#define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \ + _ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k) /* * A vendor wants to replace an old_content, but another vendor has used @@ -158,9 +158,9 @@ * on the following sample code and then replace ALTERNATIVE() with * ALTERNATIVE_2() to append its customized content. */ -#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1, errata_id_1, CONFIG_k_1, \ - new_content_2, vendor_id_2, errata_id_2, CONFIG_k_2) \ - _ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1, errata_id_1, CONFIG_k_1, \ - new_content_2, vendor_id_2, errata_id_2, CONFIG_k_2) +#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2) \ + _ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2) #endif diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index 3beef400a971..c8dea9e94310 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -36,9 +36,9 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, struct alt_entry { s32 old_offset; /* offset relative to original instruction or data */ s32 alt_offset; /* offset relative to replacement instruction or data */ - u16 vendor_id; /* cpu vendor id */ + u16 vendor_id; /* CPU vendor ID */ u16 alt_len; /* The replacement size */ - u32 errata_id; /* The errata id */ + u32 patch_id; /* The patch ID (erratum ID or cpufeature ID) */ }; void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 59d58ee0f68d..059db20b28ca 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -282,13 +282,13 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, for (alt = begin; alt < end; alt++) { if (alt->vendor_id != 0) continue; - if (alt->errata_id >= RISCV_ISA_EXT_MAX) { + if (alt->patch_id >= RISCV_ISA_EXT_MAX) { WARN(1, "This extension id:%d is not in ISA extension list", - alt->errata_id); + alt->patch_id); continue; } - if (!__riscv_isa_extension_available(NULL, alt->errata_id)) + if (!__riscv_isa_extension_available(NULL, alt->patch_id)) continue; oldptr = ALT_OLD_PTR(alt); -- GitLab From 28ea374da1d94dfe1253b83aa2d16b5a97fb7c4e Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:46:00 +0100 Subject: [PATCH 0505/5631] riscv: lib: Include hwcap.h directly When using alternatives for cpufeatures we should include hwcap.h directly, rather than through errata_list.h. Opportunistically drop an unused include too. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230224154601.88163-6-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/lib/strcmp.S | 3 +-- arch/riscv/lib/strlen.S | 3 +-- arch/riscv/lib/strncmp.S | 3 +-- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S index c42a8412547f..687b2bea5c43 100644 --- a/arch/riscv/lib/strcmp.S +++ b/arch/riscv/lib/strcmp.S @@ -2,9 +2,8 @@ #include #include -#include #include -#include +#include /* int strcmp(const char *cs, const char *ct) */ SYM_FUNC_START(strcmp) diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S index 15bb8f3aa959..db3d42d99b78 100644 --- a/arch/riscv/lib/strlen.S +++ b/arch/riscv/lib/strlen.S @@ -2,9 +2,8 @@ #include #include -#include #include -#include +#include /* int strlen(const char *s) */ SYM_FUNC_START(strlen) diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S index 7ac2f667285a..aba5b3148621 100644 --- a/arch/riscv/lib/strncmp.S +++ b/arch/riscv/lib/strncmp.S @@ -2,9 +2,8 @@ #include #include -#include #include -#include +#include /* int strncmp(const char *cs, const char *ct, size_t count) */ SYM_FUNC_START(strncmp) -- GitLab From 816a69744102bc886edc3557d00e840e3e35e7d5 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 16:46:01 +0100 Subject: [PATCH 0506/5631] riscv: cpufeature: Drop errata_list.h and other unused includes Drop errata_list.h, since cpufeature.c includes hwcap.h directly to get cpufeature IDs. And, while there, prune the rest of the unused includes too. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230224154601.88163-7-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpufeature.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 059db20b28ca..6569d963fc7d 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -8,20 +8,15 @@ #include #include -#include #include #include #include #include #include #include -#include #include #include -#include #include -#include -#include #define NUM_ALPHA_EXTS ('z' - 'a' + 1) -- GitLab From 0b2f658f5370d9818244682c76fd8f6a91b2b1af Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:24 +0100 Subject: [PATCH 0507/5631] RISC-V: alternatives: Support patching multiple insns in assembly As pointed out in commit d374a16539b1 ("RISC-V: fix compile error from deduplicated __ALTERNATIVE_CFG_2"), we need quotes around parameters passed to macros within macros to avoid spaces being interpreted as separators. ALT_NEW_CONTENT was trying to handle this by defining new_c has a vararg, but this isn't sufficient for calling ALTERNATIVE() from assembly with multiple instructions in the new/old sequences. Remove the vararg "hack" and use quotes. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230224162631.405473-2-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/alternative-macros.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 993a44a8fdac..b8c55fb3ab2c 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -14,7 +14,7 @@ .4byte \patch_id .endm -.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c : vararg +.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c .if \enable .pushsection .alternative, "a" ALT_ENTRY 886b, 888f, \vendor_id, \patch_id, 889f - 888f @@ -41,13 +41,13 @@ \old_c .option pop 887 : - ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, \new_c + ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, "\new_c" .endm .macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \ new_c_2, vendor_id_2, patch_id_2, enable_2 ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \patch_id_1, \enable_1 - ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, \new_c_2 + ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, "\new_c_2" .endm #define __ALTERNATIVE_CFG(...) ALTERNATIVE_CFG __VA_ARGS__ -- GitLab From 8b05e7d0408ac99e2f05f3673f2f249e9a9e10ec Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:25 +0100 Subject: [PATCH 0508/5631] RISC-V: Factor out body of riscv_init_cbom_blocksize loop Refactor riscv_init_cbom_blocksize() to prepare for it to be used for both cbom block size and cboz block size. Signed-off-by: Andrew Jones Reviewed-by: Heiko Stuebner Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230224162631.405473-3-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/cacheflush.c | 45 +++++++++++++++++++++----------------- 1 file changed, 25 insertions(+), 20 deletions(-) diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index fcd6145fbead..9f37c7a330bf 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -100,34 +100,39 @@ void flush_icache_pte(pte_t pte) unsigned int riscv_cbom_block_size; EXPORT_SYMBOL_GPL(riscv_cbom_block_size); +static void cbo_get_block_size(struct device_node *node, + const char *name, u32 *block_size, + unsigned long *first_hartid) +{ + unsigned long hartid; + u32 val; + + if (riscv_of_processor_hartid(node, &hartid)) + return; + + if (of_property_read_u32(node, name, &val)) + return; + + if (!*block_size) { + *block_size = val; + *first_hartid = hartid; + } else if (*block_size != val) { + pr_warn("%s mismatched between harts %lu and %lu\n", + name, *first_hartid, hartid); + } +} + void riscv_init_cbom_blocksize(void) { struct device_node *node; unsigned long cbom_hartid; - u32 val, probed_block_size; - int ret; + u32 probed_block_size; probed_block_size = 0; for_each_of_cpu_node(node) { - unsigned long hartid; - - ret = riscv_of_processor_hartid(node, &hartid); - if (ret) - continue; - /* set block-size for cbom extension if available */ - ret = of_property_read_u32(node, "riscv,cbom-block-size", &val); - if (ret) - continue; - - if (!probed_block_size) { - probed_block_size = val; - cbom_hartid = hartid; - } else { - if (probed_block_size != val) - pr_warn("cbom-block-size mismatched between harts %lu and %lu\n", - cbom_hartid, hartid); - } + cbo_get_block_size(node, "riscv,cbom-block-size", + &probed_block_size, &cbom_hartid); } if (probed_block_size) -- GitLab From ea20f117ab99d7c7653df656ddb795e51d9f7733 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:26 +0100 Subject: [PATCH 0509/5631] dt-bindings: riscv: Document cboz-block-size The Zicboz operation (cbo.zero) operates on a block-size defined for the cpu-core. While we already have the riscv,cbom-block-size property, it only provides the block size for Zicbom operations. Even though it's likely Zicboz and Zicbom will use the same size, that's not required by the specification. Create another property specifically for Zicboz. Cc: Rob Herring Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230224162631.405473-4-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- Documentation/devicetree/bindings/riscv/cpus.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 001931d526ec..f24cf9601c6e 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -72,6 +72,11 @@ properties: description: The blocksize in bytes for the Zicbom cache operations. + riscv,cboz-block-size: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + The blocksize in bytes for the Zicboz cache operations. + riscv,isa: description: Identifies the specific RISC-V instruction set architecture -- GitLab From 7ea5a73617e931230a46150dc7c1bbfd98f24c8e Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:27 +0100 Subject: [PATCH 0510/5631] RISC-V: Add Zicboz detection and block size parsing Parse "riscv,cboz-block-size" from the DT by piggybacking on Zicbom's riscv_init_cbom_blocksize(). Additionally check the DT for the presence of the "zicboz" extension and, when it's present, validate the parsed cboz block size as we do Zicbom's cbom block size with riscv_isa_extension_check(). Signed-off-by: Andrew Jones Reviewed-by: Heiko Stuebner Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230224162631.405473-5-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/cacheflush.h | 3 ++- arch/riscv/include/asm/hwcap.h | 1 + arch/riscv/kernel/cpu.c | 1 + arch/riscv/kernel/cpufeature.c | 10 ++++++++++ arch/riscv/kernel/setup.c | 2 +- arch/riscv/mm/cacheflush.c | 23 +++++++++++++++-------- 6 files changed, 30 insertions(+), 10 deletions(-) diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 03e3b95ae6da..8091b8bf4883 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -50,7 +50,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local); #endif /* CONFIG_SMP */ extern unsigned int riscv_cbom_block_size; -void riscv_init_cbom_blocksize(void); +extern unsigned int riscv_cboz_block_size; +void riscv_init_cbo_blocksizes(void); #ifdef CONFIG_RISCV_DMA_NONCOHERENT void riscv_noncoherent_supported(void); diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index e3021b2590de..5955fbeaba86 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -42,6 +42,7 @@ #define RISCV_ISA_EXT_ZBB 30 #define RISCV_ISA_EXT_ZICBOM 31 #define RISCV_ISA_EXT_ZIHINTPAUSE 32 +#define RISCV_ISA_EXT_ZICBOZ 33 #define RISCV_ISA_EXT_MAX 64 #define RISCV_ISA_EXT_NAME_LEN_MAX 32 diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 8400f0cc9704..1b0411280141 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -186,6 +186,7 @@ arch_initcall(riscv_cpuinfo_init); */ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), + __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 6569d963fc7d..538779d03311 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -74,6 +74,15 @@ static bool riscv_isa_extension_check(int id) return false; } return true; + case RISCV_ISA_EXT_ZICBOZ: + if (!riscv_cboz_block_size) { + pr_err("Zicboz detected in ISA string, but no cboz-block-size found\n"); + return false; + } else if (!is_power_of_2(riscv_cboz_block_size)) { + pr_err("cboz-block-size present, but is not a power-of-2\n"); + return false; + } + return true; } return true; @@ -222,6 +231,7 @@ void __init riscv_fill_hwcap(void) SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB); SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM); + SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ); SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE); } #undef SET_ISA_EXT_MAP diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 376d2827e736..5d3184cbf518 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -297,7 +297,7 @@ void __init setup_arch(char **cmdline_p) setup_smp(); #endif - riscv_init_cbom_blocksize(); + riscv_init_cbo_blocksizes(); riscv_fill_hwcap(); apply_boot_alternatives(); if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 9f37c7a330bf..632d6d06148a 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -100,6 +100,9 @@ void flush_icache_pte(pte_t pte) unsigned int riscv_cbom_block_size; EXPORT_SYMBOL_GPL(riscv_cbom_block_size); +unsigned int riscv_cboz_block_size; +EXPORT_SYMBOL_GPL(riscv_cboz_block_size); + static void cbo_get_block_size(struct device_node *node, const char *name, u32 *block_size, unsigned long *first_hartid) @@ -122,19 +125,23 @@ static void cbo_get_block_size(struct device_node *node, } } -void riscv_init_cbom_blocksize(void) +void riscv_init_cbo_blocksizes(void) { + unsigned long cbom_hartid, cboz_hartid; + u32 cbom_block_size = 0, cboz_block_size = 0; struct device_node *node; - unsigned long cbom_hartid; - u32 probed_block_size; - probed_block_size = 0; for_each_of_cpu_node(node) { - /* set block-size for cbom extension if available */ + /* set block-size for cbom and/or cboz extension if available */ cbo_get_block_size(node, "riscv,cbom-block-size", - &probed_block_size, &cbom_hartid); + &cbom_block_size, &cbom_hartid); + cbo_get_block_size(node, "riscv,cboz-block-size", + &cboz_block_size, &cboz_hartid); } - if (probed_block_size) - riscv_cbom_block_size = probed_block_size; + if (cbom_block_size) + riscv_cbom_block_size = cbom_block_size; + + if (cboz_block_size) + riscv_cboz_block_size = cboz_block_size; } -- GitLab From d25f256332cc795b0fe16ba541fe0c05f0eb2c59 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:28 +0100 Subject: [PATCH 0511/5631] RISC-V: cpufeatures: Put the upper 16 bits of patch ID to work cpufeature IDs are consecutive integers starting at 26, so a 32-bit patch ID allows an aircraft carrier load of feature IDs. Repurposing the upper 16 bits still leaves a boat load of feature IDs and gains 16 bits which may be used to control patching on a per patch-site basis. This will be initially used in Zicboz's application to clear_page(), as Zicboz's block size must also be considered. In that case, the upper 16-bit value's role will be to convey the maximum block size which the Zicboz clear_page() implementation supports. cpufeature patch sites which need to check for the existence or absence of other cpufeatures may also be able to make use of this. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230224162631.405473-6-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/alternative.h | 4 +++ arch/riscv/kernel/cpufeature.c | 37 +++++++++++++++++++++++++--- 2 files changed, 37 insertions(+), 4 deletions(-) diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index c8dea9e94310..58ccd2f8cab7 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -13,10 +13,14 @@ #ifdef CONFIG_RISCV_ALTERNATIVE #include +#include #include #include #include +#define PATCH_ID_CPUFEATURE_ID(p) lower_16_bits(p) +#define PATCH_ID_CPUFEATURE_VALUE(p) upper_16_bits(p) + #define RISCV_ALTERNATIVES_BOOT 0 /* alternatives applied during regular boot */ #define RISCV_ALTERNATIVES_MODULE 1 /* alternatives applied during module-init */ #define RISCV_ALTERNATIVES_EARLY_BOOT 2 /* alternatives applied before mmu start */ diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 538779d03311..d424cd76beb1 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -274,12 +274,35 @@ void __init riscv_fill_hwcap(void) } #ifdef CONFIG_RISCV_ALTERNATIVE +/* + * Alternative patch sites consider 48 bits when determining when to patch + * the old instruction sequence with the new. These bits are broken into a + * 16-bit vendor ID and a 32-bit patch ID. A non-zero vendor ID means the + * patch site is for an erratum, identified by the 32-bit patch ID. When + * the vendor ID is zero, the patch site is for a cpufeature. cpufeatures + * further break down patch ID into two 16-bit numbers. The lower 16 bits + * are the cpufeature ID and the upper 16 bits are used for a value specific + * to the cpufeature and patch site. If the upper 16 bits are zero, then it + * implies no specific value is specified. cpufeatures that want to control + * patching on a per-site basis will provide non-zero values and implement + * checks here. The checks return true when patching should be done, and + * false otherwise. + */ +static bool riscv_cpufeature_patch_check(u16 id, u16 value) +{ + if (!value) + return true; + + return false; +} + void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned int stage) { struct alt_entry *alt; void *oldptr, *altptr; + u16 id, value; if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) return; @@ -287,13 +310,19 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, for (alt = begin; alt < end; alt++) { if (alt->vendor_id != 0) continue; - if (alt->patch_id >= RISCV_ISA_EXT_MAX) { - WARN(1, "This extension id:%d is not in ISA extension list", - alt->patch_id); + + id = PATCH_ID_CPUFEATURE_ID(alt->patch_id); + + if (id >= RISCV_ISA_EXT_MAX) { + WARN(1, "This extension id:%d is not in ISA extension list", id); continue; } - if (!__riscv_isa_extension_available(NULL, alt->patch_id)) + if (!__riscv_isa_extension_available(NULL, id)) + continue; + + value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id); + if (!riscv_cpufeature_patch_check(id, value)) continue; oldptr = ALT_OLD_PTR(alt); -- GitLab From ab0f77465e3e4ec2d2583cd770b157b16cc22844 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:29 +0100 Subject: [PATCH 0512/5631] RISC-V: Use Zicboz in clear_page when available Using memset() to zero a 4K page takes 563 total instructions, where 20 are branches. clear_page(), with Zicboz and a 64 byte block size, takes 169 total instructions, where 4 are branches and 33 are nops. Even though the block size is a variable, thanks to alternatives, we can still implement a Duff device without having to do any preliminary calculations. This is achieved by using the alternatives' cpufeature value (the upper 16 bits of patch_id). The value used is the maximum zicboz block size order accepted at the patch site. This enables us to stop patching / unrolling when 4K bytes have been zeroed (we would loop and continue after 4K if the page size would be larger) For 4K pages, unrolling 16 times allows block sizes of 64 and 128 to only loop a few times and larger block sizes to not loop at all. Since cbo.zero doesn't take an offset, we also need an 'add' after each instruction, making the loop body 112 to 160 bytes. Hopefully this is small enough to not cause icache misses. Signed-off-by: Andrew Jones Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20230224162631.405473-7-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 13 ++++++ arch/riscv/include/asm/insn-def.h | 4 ++ arch/riscv/include/asm/page.h | 6 ++- arch/riscv/kernel/cpufeature.c | 11 +++++ arch/riscv/lib/Makefile | 1 + arch/riscv/lib/clear_page.S | 74 +++++++++++++++++++++++++++++++ 6 files changed, 108 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/lib/clear_page.S diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 69797e6eed6f..275be2ee87bf 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -457,6 +457,19 @@ config RISCV_ISA_ZICBOM If you don't know what to do here, say Y. +config RISCV_ISA_ZICBOZ + bool "Zicboz extension support for faster zeroing of memory" + depends on !XIP_KERNEL && MMU + select RISCV_ALTERNATIVE + default y + help + Enable the use of the ZICBOZ extension (cbo.zero instruction) + when available. + + The Zicboz extension is used for faster zeroing of memory. + + If you don't know what to do here, say Y. + config TOOLCHAIN_HAS_ZIHINTPAUSE bool default y diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h index e01ab51f50d2..6960beb75f32 100644 --- a/arch/riscv/include/asm/insn-def.h +++ b/arch/riscv/include/asm/insn-def.h @@ -192,4 +192,8 @@ INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ RS1(base), SIMM12(2)) +#define CBO_zero(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(4)) + #endif /* __ASM_INSN_DEF_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 7fed7c431928..21fdf9527ce8 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -49,10 +49,14 @@ #ifndef __ASSEMBLY__ +#ifdef CONFIG_RISCV_ISA_ZICBOZ +void clear_page(void *page); +#else #define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE) +#endif #define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) -#define clear_user_page(pgaddr, vaddr, page) memset((pgaddr), 0, PAGE_SIZE) +#define clear_user_page(pgaddr, vaddr, page) clear_page(pgaddr) #define copy_user_page(vto, vfrom, vaddr, topg) \ memcpy((vto), (vfrom), PAGE_SIZE) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index d424cd76beb1..8e7b0d703841 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -293,6 +293,17 @@ static bool riscv_cpufeature_patch_check(u16 id, u16 value) if (!value) return true; + switch (id) { + case RISCV_ISA_EXT_ZICBOZ: + /* + * Zicboz alternative applications provide the maximum + * supported block size order, or zero when it doesn't + * matter. If the current block size exceeds the maximum, + * then the alternative cannot be applied. + */ + return riscv_cboz_block_size <= (1U << value); + } + return false; } diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 6c74b0bedd60..26cb2502ecf8 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -8,5 +8,6 @@ lib-y += strlen.o lib-y += strncmp.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o +lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S new file mode 100644 index 000000000000..d7a256eb53f4 --- /dev/null +++ b/arch/riscv/lib/clear_page.S @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define CBOZ_ALT(order, old, new) \ + ALTERNATIVE(old, new, 0, \ + ((order) << 16) | RISCV_ISA_EXT_ZICBOZ, \ + CONFIG_RISCV_ISA_ZICBOZ) + +/* void clear_page(void *page) */ +SYM_FUNC_START(clear_page) + li a2, PAGE_SIZE + + /* + * If Zicboz isn't present, or somehow has a block + * size larger than 4K, then fallback to memset. + */ + CBOZ_ALT(12, "j .Lno_zicboz", "nop") + + lw a1, riscv_cboz_block_size + add a2, a0, a2 +.Lzero_loop: + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(11, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(10, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(9, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBOZ_ALT(8, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + CBO_zero(a0) + add a0, a0, a1 + bltu a0, a2, .Lzero_loop + ret +.Lno_zicboz: + li a1, 0 + tail __memset +SYM_FUNC_END(clear_page) +EXPORT_SYMBOL(clear_page) -- GitLab From 665fd8862413f21cd924fc121eadcd32ea122c52 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:30 +0100 Subject: [PATCH 0513/5631] RISC-V: KVM: Provide UAPI for Zicboz block size We're about to allow guests to use the Zicboz extension. KVM userspace needs to know the cache block size in order to properly advertise it to the guest. Provide a virtual config register for userspace to get it with the GET_ONE_REG API, but setting it cannot be supported, so disallow SET_ONE_REG. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20230224162631.405473-8-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kvm/vcpu.c | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 92af6f3f057c..c1a1bb0fa91c 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -52,6 +52,7 @@ struct kvm_riscv_config { unsigned long mvendorid; unsigned long marchid; unsigned long mimpid; + unsigned long zicboz_block_size; }; /* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7d010b0be54e..525d785ccba2 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -283,6 +283,11 @@ static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu, return -EINVAL; reg_val = riscv_cbom_block_size; break; + case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): + if (!riscv_isa_extension_available(vcpu->arch.isa, ZICBOZ)) + return -EINVAL; + reg_val = riscv_cboz_block_size; + break; case KVM_REG_RISCV_CONFIG_REG(mvendorid): reg_val = vcpu->arch.mvendorid; break; @@ -354,6 +359,8 @@ static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, break; case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): return -EOPNOTSUPP; + case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): + return -EOPNOTSUPP; case KVM_REG_RISCV_CONFIG_REG(mvendorid): if (!vcpu->arch.ran_atleast_once) vcpu->arch.mvendorid = reg_val; -- GitLab From b20f67994f35d75758ff671cd5095ec0cfab6ff9 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 24 Feb 2023 17:26:31 +0100 Subject: [PATCH 0514/5631] RISC-V: KVM: Expose Zicboz to the guest Guests may use the cbo.zero instruction when the CPU has the Zicboz extension and the hypervisor sets henvcfg.CBZE. Add Zicboz support for KVM guests which may be enabled and disabled from KVM userspace using the ISA extension ONE_REG API. Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20230224162631.405473-9-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kvm/vcpu.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index c1a1bb0fa91c..e44c1e90eaa7 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_SVINVAL, KVM_RISCV_ISA_EXT_ZIHINTPAUSE, KVM_RISCV_ISA_EXT_ZICBOM, + KVM_RISCV_ISA_EXT_ZICBOZ, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 525d785ccba2..6adb1b6112a1 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -63,6 +63,7 @@ static const unsigned long kvm_isa_ext_arr[] = { KVM_ISA_EXT_ARR(SVPBMT), KVM_ISA_EXT_ARR(ZIHINTPAUSE), KVM_ISA_EXT_ARR(ZICBOM), + KVM_ISA_EXT_ARR(ZICBOZ), }; static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext) @@ -872,6 +873,9 @@ static void kvm_riscv_vcpu_update_config(const unsigned long *isa) if (riscv_isa_extension_available(isa, ZICBOM)) henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE); + if (riscv_isa_extension_available(isa, ZICBOZ)) + henvcfg |= ENVCFG_CBZE; + csr_write(CSR_HENVCFG, henvcfg); #ifdef CONFIG_32BIT csr_write(CSR_HENVCFGH, henvcfg >> 32); -- GitLab From 80c3a7d9f20401169283b5670dbb8d7ac07a1d55 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 15 Mar 2023 10:43:21 +0200 Subject: [PATCH 0515/5631] perf script: Fix Python support when no libtraceevent Python scripting can be used without libtraceevent. In particular, scripting for Intel PT does not use tracepoints, and so does not need libtraceevent support. Alter the build and employ conditional compilation to allow Python scripting without libtraceevent. Example: Before: $ ldd `which perf` | grep -i python $ ldd `which perf` | grep -i libtraceevent $ perf record -e intel_pt//u uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.031 MB perf.data ] $ perf script intel-pt-events.py |& head -3 Error: Couldn't find script `intel-pt-events.py' See perf script -l for available scripts. After: $ ldd `which perf` | grep -i python libpython3.10.so.1.0 => /lib/x86_64-linux-gnu/libpython3.10.so.1.0 (0x00007f4bac400000) $ ldd `which perf` | grep -i libtraceevent $ perf script intel-pt-events.py | head Intel PT Branch Trace, Power Events, Event Trace and PTWRITE Switch In 8021/8021 [000] 11234.097713404 0/0 perf-exec 8021/8021 [000] 11234.098041726 psb offset: 0x0 0 [unknown] ([unknown]) perf-exec 8021/8021 [000] 11234.098041726 cbr 45 freq: 4505 MHz (161%) 0 [unknown] ([unknown]) uname 8021/8021 [000] 11234.098082170 branches:uH tr strt 0 [unknown] ([unknown]) => 7f3a8b9422b0 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) uname 8021/8021 [000] 11234.098082379 branches:uH tr end 7f3a8b9422b0 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) => 0 [unknown] ([unknown]) uname 8021/8021 [000] 11234.098083629 branches:uH tr strt 0 [unknown] ([unknown]) => 7f3a8b9422b0 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) uname 8021/8021 [000] 11234.098083629 branches:uH call 7f3a8b9422b3 _start+0x3 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) => 7f3a8b943050 _dl_start+0x0 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) uname 8021/8021 [000] 11234.098083837 branches:uH tr end 7f3a8b943060 _dl_start+0x10 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) => 0 [unknown] ([unknown]) IPC: 0.01 (9/938) uname 8021/8021 [000] 11234.098084670 branches:uH tr strt 0 [unknown] ([unknown]) => 7f3a8b943060 _dl_start+0x10 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system") Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230315084321.14563-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Build | 2 +- tools/perf/builtin-script.c | 2 +- tools/perf/scripts/Build | 4 +- .../perf/scripts/python/Perf-Trace-Util/Build | 2 +- .../scripts/python/Perf-Trace-Util/Context.c | 4 + tools/perf/util/Build | 2 +- tools/perf/util/scripting-engines/Build | 2 +- .../scripting-engines/trace-event-python.c | 75 +++++++++++++------ tools/perf/util/trace-event-scripting.c | 9 ++- 9 files changed, 72 insertions(+), 30 deletions(-) diff --git a/tools/perf/Build b/tools/perf/Build index 6dd67e502295..aa7623622834 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -56,6 +56,6 @@ CFLAGS_builtin-report.o += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)" perf-y += util/ perf-y += arch/ perf-y += ui/ -perf-$(CONFIG_LIBTRACEEVENT) += scripts/ +perf-y += scripts/ gtk-y += ui/gtk/ diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 522226114263..976f8bfe099c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2313,8 +2313,8 @@ static void setup_scripting(void) { #ifdef HAVE_LIBTRACEEVENT setup_perl_scripting(); - setup_python_scripting(); #endif + setup_python_scripting(); } static int flush_scripting(void) diff --git a/tools/perf/scripts/Build b/tools/perf/scripts/Build index 68d4b54574ad..7d8e2e57faac 100644 --- a/tools/perf/scripts/Build +++ b/tools/perf/scripts/Build @@ -1,2 +1,4 @@ -perf-$(CONFIG_LIBPERL) += perl/Perf-Trace-Util/ +ifeq ($(CONFIG_LIBTRACEEVENT),y) + perf-$(CONFIG_LIBPERL) += perl/Perf-Trace-Util/ +endif perf-$(CONFIG_LIBPYTHON) += python/Perf-Trace-Util/ diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Build b/tools/perf/scripts/python/Perf-Trace-Util/Build index d5fed4e42617..7d0e33ce6aba 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Build +++ b/tools/perf/scripts/python/Perf-Trace-Util/Build @@ -1,3 +1,3 @@ -perf-$(CONFIG_LIBTRACEEVENT) += Context.o +perf-y += Context.o CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index 895f5fc23965..b0d449f41650 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -59,6 +59,7 @@ static struct scripting_context *get_scripting_context(PyObject *args) return get_args(args, "context", NULL); } +#ifdef HAVE_LIBTRACEEVENT static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args) { struct scripting_context *c = get_scripting_context(args); @@ -90,6 +91,7 @@ static PyObject *perf_trace_context_common_lock_depth(PyObject *obj, return Py_BuildValue("i", common_lock_depth(c)); } +#endif static PyObject *perf_sample_insn(PyObject *obj, PyObject *args) { @@ -178,12 +180,14 @@ static PyObject *perf_sample_srccode(PyObject *obj, PyObject *args) } static PyMethodDef ContextMethods[] = { +#ifdef HAVE_LIBTRACEEVENT { "common_pc", perf_trace_context_common_pc, METH_VARARGS, "Get the common preempt count event field value."}, { "common_flags", perf_trace_context_common_flags, METH_VARARGS, "Get the common flags event field value."}, { "common_lock_depth", perf_trace_context_common_lock_depth, METH_VARARGS, "Get the common lock depth event field value."}, +#endif { "perf_sample_insn", perf_sample_insn, METH_VARARGS, "Get the machine code instruction."}, { "perf_set_itrace_options", perf_set_itrace_options, diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8607575183a9..0806bc0361ad 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -78,7 +78,7 @@ perf-y += pmu-bison.o perf-y += pmu-hybrid.o perf-y += svghelper.o perf-$(CONFIG_LIBTRACEEVENT) += trace-event-info.o -perf-$(CONFIG_LIBTRACEEVENT) += trace-event-scripting.o +perf-y += trace-event-scripting.o perf-$(CONFIG_LIBTRACEEVENT) += trace-event.o perf-$(CONFIG_LIBTRACEEVENT) += trace-event-parse.o perf-$(CONFIG_LIBTRACEEVENT) += trace-event-read.o diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build index 2c96aa3cc1ec..c220fec97032 100644 --- a/tools/perf/util/scripting-engines/Build +++ b/tools/perf/util/scripting-engines/Build @@ -1,7 +1,7 @@ ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-$(CONFIG_LIBPERL) += trace-event-perl.o - perf-$(CONFIG_LIBPYTHON) += trace-event-python.o endif +perf-$(CONFIG_LIBPYTHON) += trace-event-python.o CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default -Wno-bad-function-cast -Wno-declaration-after-statement -Wno-switch-enum diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 2c2697c5d025..0f4ef61f2ffa 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -30,7 +30,9 @@ #include #include #include +#ifdef HAVE_LIBTRACEEVENT #include +#endif #include "../build-id.h" #include "../counts.h" @@ -87,18 +89,21 @@ PyMODINIT_FUNC initperf_trace_context(void); PyMODINIT_FUNC PyInit_perf_trace_context(void); #endif +#ifdef HAVE_LIBTRACEEVENT #define TRACE_EVENT_TYPE_MAX \ ((1 << (sizeof(unsigned short) * 8)) - 1) static DECLARE_BITMAP(events_defined, TRACE_EVENT_TYPE_MAX); -#define MAX_FIELDS 64 #define N_COMMON_FIELDS 7 -extern struct scripting_context *scripting_context; - static char *cur_field_name; static int zero_flag_atom; +#endif + +#define MAX_FIELDS 64 + +extern struct scripting_context *scripting_context; static PyObject *main_module, *main_dict; @@ -153,6 +158,26 @@ static PyObject *get_handler(const char *handler_name) return handler; } +static void call_object(PyObject *handler, PyObject *args, const char *die_msg) +{ + PyObject *retval; + + retval = PyObject_CallObject(handler, args); + if (retval == NULL) + handler_call_die(die_msg); + Py_DECREF(retval); +} + +static void try_call_object(const char *handler_name, PyObject *args) +{ + PyObject *handler; + + handler = get_handler(handler_name); + if (handler) + call_object(handler, args, handler_name); +} + +#ifdef HAVE_LIBTRACEEVENT static int get_argument_count(PyObject *handler) { int arg_count = 0; @@ -181,25 +206,6 @@ static int get_argument_count(PyObject *handler) return arg_count; } -static void call_object(PyObject *handler, PyObject *args, const char *die_msg) -{ - PyObject *retval; - - retval = PyObject_CallObject(handler, args); - if (retval == NULL) - handler_call_die(die_msg); - Py_DECREF(retval); -} - -static void try_call_object(const char *handler_name, PyObject *args) -{ - PyObject *handler; - - handler = get_handler(handler_name); - if (handler) - call_object(handler, args, handler_name); -} - static void define_value(enum tep_print_arg_type field_type, const char *ev_name, const char *field_name, @@ -379,6 +385,7 @@ static PyObject *get_field_numeric_entry(struct tep_event *event, obj = list; return obj; } +#endif static const char *get_dsoname(struct map *map) { @@ -906,6 +913,7 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample, return dict; } +#ifdef HAVE_LIBTRACEEVENT static void python_process_tracepoint(struct perf_sample *sample, struct evsel *evsel, struct addr_location *al, @@ -1035,6 +1043,16 @@ static void python_process_tracepoint(struct perf_sample *sample, Py_DECREF(t); } +#else +static void python_process_tracepoint(struct perf_sample *sample __maybe_unused, + struct evsel *evsel __maybe_unused, + struct addr_location *al __maybe_unused, + struct addr_location *addr_al __maybe_unused) +{ + fprintf(stderr, "Tracepoint events are not supported because " + "perf is not linked with libtraceevent.\n"); +} +#endif static PyObject *tuple_new(unsigned int sz) { @@ -1965,6 +1983,7 @@ static int python_stop_script(void) return 0; } +#ifdef HAVE_LIBTRACEEVENT static int python_generate_script(struct tep_handle *pevent, const char *outfile) { int i, not_first, count, nr_events; @@ -2155,6 +2174,18 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile return 0; } +#else +static int python_generate_script(struct tep_handle *pevent __maybe_unused, + const char *outfile __maybe_unused) +{ + fprintf(stderr, "Generating Python perf-script is not supported." + " Install libtraceevent and rebuild perf to enable it.\n" + "For example:\n # apt install libtraceevent-dev (ubuntu)" + "\n # yum install libtraceevent-devel (Fedora)" + "\n etc.\n"); + return -1; +} +#endif struct scripting_ops python_scripting_ops = { .name = "Python", diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c index 56175c53f9af..bd0000300c77 100644 --- a/tools/perf/util/trace-event-scripting.c +++ b/tools/perf/util/trace-event-scripting.c @@ -9,7 +9,9 @@ #include #include #include +#ifdef HAVE_LIBTRACEEVENT #include +#endif #include "debug.h" #include "trace-event.h" @@ -27,10 +29,11 @@ void scripting_context__update(struct scripting_context *c, struct addr_location *addr_al) { c->event_data = sample->raw_data; + c->pevent = NULL; +#ifdef HAVE_LIBTRACEEVENT if (evsel->tp_format) c->pevent = evsel->tp_format->tep; - else - c->pevent = NULL; +#endif c->event = event; c->sample = sample; c->evsel = evsel; @@ -122,6 +125,7 @@ void setup_python_scripting(void) } #endif +#ifdef HAVE_LIBTRACEEVENT static void print_perl_unsupported_msg(void) { fprintf(stderr, "Perl scripting not supported." @@ -186,3 +190,4 @@ void setup_perl_scripting(void) register_perl_scripting(&perl_scripting_ops); } #endif +#endif -- GitLab From 6e57f69f23d02b8c67d7428ee708b7d903ed22b2 Mon Sep 17 00:00:00 2001 From: liuwenyu Date: Wed, 15 Mar 2023 14:42:17 +0800 Subject: [PATCH 0516/5631] perf top: Fix rare segfault in thread__comm_len() In thread__comm_len(),strlen() is called outside of the thread->comm_lock critical section,which may cause a UAF problems if comm__free() is called by the process_thread concurrently. backtrace of the core file is as follows: (gdb) bt #0 __strlen_evex () at ../sysdeps/x86_64/multiarch/strlen-evex.S:77 #1 0x000055ad15d31de5 in thread__comm_len (thread=0x7f627d20e300) at util/thread.c:320 #2 0x000055ad15d4fade in hists__calc_col_len (h=0x7f627d295940, hists=0x55ad1772bfe0) at util/hist.c:103 #3 hists__calc_col_len (hists=0x55ad1772bfe0, h=0x7f627d295940) at util/hist.c:79 #4 0x000055ad15d52c8c in output_resort (hists=hists@entry=0x55ad1772bfe0, prog=0x0, use_callchain=false, cb=cb@entry=0x0, cb_arg=0x0) at util/hist.c:1926 #5 0x000055ad15d530a4 in evsel__output_resort_cb (evsel=evsel@entry=0x55ad1772bde0, prog=prog@entry=0x0, cb=cb@entry=0x0, cb_arg=cb_arg@entry=0x0) at util/hist.c:1945 #6 0x000055ad15d53110 in evsel__output_resort (evsel=evsel@entry=0x55ad1772bde0, prog=prog@entry=0x0) at util/hist.c:1950 #7 0x000055ad15c6ae9a in perf_top__resort_hists (t=t@entry=0x7ffcd9cbf4f0) at builtin-top.c:311 #8 0x000055ad15c6cc6d in perf_top__print_sym_table (top=0x7ffcd9cbf4f0) at builtin-top.c:346 #9 display_thread (arg=0x7ffcd9cbf4f0) at builtin-top.c:700 #10 0x00007f6282fab4fa in start_thread (arg=) at pthread_create.c:443 #11 0x00007f628302e200 in clone3 () at ../sysdeps/unix/sysv/linux/x86_64/clone3.S:81 The reason is that strlen() get a pointer to a memory that has been freed. The string pointer is stored in the structure comm_str, which corresponds to a rb_tree node,when the node is erased, the memory of the string is also freed. In thread__comm_len(),it gets the pointer within the thread->comm_lock critical section, but passed to strlen() outside of the thread->comm_lock critical section, and the perf process_thread may called comm__free() concurrently, cause this segfault problem. The process is as follows: display_thread process_thread -------------- -------------- thread__comm_len -> thread__comm_str # held the comm read lock -> __thread__comm_str(thread) # release the comm read lock thread__delete # held the comm write lock -> comm__free -> comm_str__put(comm->comm_str) -> zfree(&cs->str) # release the comm write lock # The memory of the string pointed to by comm has been free. -> thread->comm_len = strlen(comm); This patch expand the critical section range of thread->comm_lock in thread__comm_len(), to make strlen() called safe. Signed-off-by: Wenyu Liu Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Christian Brauner Cc: Feilong Lin Cc: Hewenliang Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Yunfeng Ye Link: https://lore.kernel.org/r/322bfb49-840b-f3b6-9ef1-f9ec3435b07e@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/thread.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index e3e5427e1c3c..a2490a20eb56 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -311,17 +311,30 @@ const char *thread__comm_str(struct thread *thread) return str; } +static int __thread__comm_len(struct thread *thread, const char *comm) +{ + if (!comm) + return 0; + thread->comm_len = strlen(comm); + + return thread->comm_len; +} + /* CHECKME: it should probably better return the max comm len from its comm list */ int thread__comm_len(struct thread *thread) { - if (!thread->comm_len) { - const char *comm = thread__comm_str(thread); - if (!comm) - return 0; - thread->comm_len = strlen(comm); + int comm_len = thread->comm_len; + + if (!comm_len) { + const char *comm; + + down_read(&thread->comm_lock); + comm = __thread__comm_str(thread); + comm_len = __thread__comm_len(thread, comm); + up_read(&thread->comm_lock); } - return thread->comm_len; + return comm_len; } size_t thread__fprintf(struct thread *thread, FILE *fp) -- GitLab From 990a71e904f6ec2d7d84eecb37e5127b75721985 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:28 -0700 Subject: [PATCH 0517/5631] perf bpf filter: Introduce basic BPF filter expression This implements a tiny parser for the filter expressions used for BPF. Each expression will be converted to struct perf_bpf_filter_expr and be passed to a BPF map. For now, I'd like to start with the very basic comparisons like EQ or GT. The LHS should be a term for sample data and the RHS is a number. The expressions are connected by a comma. For example, period > 10000 ip < 0x1000000000000, cpu == 3 Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/Build | 16 +++++++ tools/perf/util/bpf-filter.c | 37 ++++++++++++++++ tools/perf/util/bpf-filter.h | 36 ++++++++++++++++ tools/perf/util/bpf-filter.l | 82 ++++++++++++++++++++++++++++++++++++ tools/perf/util/bpf-filter.y | 54 ++++++++++++++++++++++++ 5 files changed, 225 insertions(+) create mode 100644 tools/perf/util/bpf-filter.c create mode 100644 tools/perf/util/bpf-filter.h create mode 100644 tools/perf/util/bpf-filter.l create mode 100644 tools/perf/util/bpf-filter.y diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 0806bc0361ad..bd18fe5f2719 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -154,6 +154,9 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-flex.o +perf-$(CONFIG_PERF_BPF_SKEL) += bpf-filter-bison.o ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o @@ -267,6 +270,16 @@ $(OUTPUT)util/pmu-bison.c $(OUTPUT)util/pmu-bison.h: util/pmu.y $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \ -o $(OUTPUT)util/pmu-bison.c -p perf_pmu_ +$(OUTPUT)util/bpf-filter-flex.c $(OUTPUT)util/bpf-filter-flex.h: util/bpf-filter.l $(OUTPUT)util/bpf-filter-bison.c + $(call rule_mkdir) + $(Q)$(call echo-cmd,flex)$(FLEX) -o $(OUTPUT)util/bpf-filter-flex.c \ + --header-file=$(OUTPUT)util/bpf-filter-flex.h $(PARSER_DEBUG_FLEX) $< + +$(OUTPUT)util/bpf-filter-bison.c $(OUTPUT)util/bpf-filter-bison.h: util/bpf-filter.y + $(call rule_mkdir) + $(Q)$(call echo-cmd,bison)$(BISON) -v $< -d $(PARSER_DEBUG_BISON) $(BISON_FILE_PREFIX_MAP) \ + -o $(OUTPUT)util/bpf-filter-bison.c -p perf_bpf_filter_ + FLEX_GE_26 := $(shell expr $(shell $(FLEX) --version | sed -e 's/flex \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 26) ifeq ($(FLEX_GE_26),1) flex_flags := -Wno-switch-enum -Wno-switch-default -Wno-unused-function -Wno-redundant-decls -Wno-sign-compare -Wno-unused-parameter -Wno-missing-prototypes -Wno-missing-declarations @@ -280,6 +293,7 @@ endif CFLAGS_parse-events-flex.o += $(flex_flags) CFLAGS_pmu-flex.o += $(flex_flags) CFLAGS_expr-flex.o += $(flex_flags) +CFLAGS_bpf-filter-flex.o += $(flex_flags) bison_flags := -DYYENABLE_NLS=0 BISON_GE_35 := $(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\)/\1\2/g') \>\= 35) @@ -291,10 +305,12 @@ endif CFLAGS_parse-events-bison.o += $(bison_flags) CFLAGS_pmu-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) CFLAGS_expr-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) +CFLAGS_bpf-filter-bison.o += -DYYLTYPE_IS_TRIVIAL=0 $(bison_flags) $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c $(OUTPUT)util/expr.o: $(OUTPUT)util/expr-flex.c $(OUTPUT)util/expr-bison.c +$(OUTPUT)util/bpf-filter.o: $(OUTPUT)util/bpf-filter-flex.c $(OUTPUT)util/bpf-filter-bison.c CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c new file mode 100644 index 000000000000..c72e35d51240 --- /dev/null +++ b/tools/perf/util/bpf-filter.c @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include + +#include "util/bpf-filter.h" +#include "util/bpf-filter-flex.h" +#include "util/bpf-filter-bison.h" + +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, + enum perf_bpf_filter_op op, + unsigned long val) +{ + struct perf_bpf_filter_expr *expr; + + expr = malloc(sizeof(*expr)); + if (expr != NULL) { + expr->sample_flags = sample_flags; + expr->op = op; + expr->val = val; + } + return expr; +} + +int perf_bpf_filter__parse(struct list_head *expr_head, const char *str) +{ + YY_BUFFER_STATE buffer; + int ret; + + buffer = perf_bpf_filter__scan_string(str); + + ret = perf_bpf_filter_parse(expr_head); + + perf_bpf_filter__flush_buffer(buffer); + perf_bpf_filter__delete_buffer(buffer); + perf_bpf_filter_lex_destroy(); + + return ret; +} diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h new file mode 100644 index 000000000000..93a0d3de038c --- /dev/null +++ b/tools/perf/util/bpf-filter.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef PERF_UTIL_BPF_FILTER_H +#define PERF_UTIL_BPF_FILTER_H + +#include + +enum perf_bpf_filter_op { + PBF_OP_EQ, + PBF_OP_NEQ, + PBF_OP_GT, + PBF_OP_GE, + PBF_OP_LT, + PBF_OP_LE, + PBF_OP_AND, +}; + +struct perf_bpf_filter_expr { + struct list_head list; + enum perf_bpf_filter_op op; + unsigned long sample_flags; + unsigned long val; +}; + +#ifdef HAVE_BPF_SKEL +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, + enum perf_bpf_filter_op op, + unsigned long val); +int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); +#else /* !HAVE_BPF_SKEL */ +static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unused, + const char *str __maybe_unused) +{ + return -ENOSYS; +} +#endif /* HAVE_BPF_SKEL*/ +#endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l new file mode 100644 index 000000000000..f6c0b74ea285 --- /dev/null +++ b/tools/perf/util/bpf-filter.l @@ -0,0 +1,82 @@ +%option prefix="perf_bpf_filter_" +%option noyywrap + +%{ +#include +#include +#include + +#include "bpf-filter.h" +#include "bpf-filter-bison.h" + +static int sample(unsigned long sample_flag) +{ + perf_bpf_filter_lval.sample = sample_flag; + return BFT_SAMPLE; +} + +static int operator(enum perf_bpf_filter_op op) +{ + perf_bpf_filter_lval.op = op; + return BFT_OP; +} + +static int value(int base) +{ + long num; + + errno = 0; + num = strtoul(perf_bpf_filter_text, NULL, base); + if (errno) + return BFT_ERROR; + + perf_bpf_filter_lval.num = num; + return BFT_NUM; +} + +static int error(const char *str) +{ + printf("perf_bpf_filter: Unexpected filter %s: %s\n", str, perf_bpf_filter_text); + return BFT_ERROR; +} + +%} + +num_dec [0-9]+ +num_hex 0[Xx][0-9a-fA-F]+ +space [ \t]+ +ident [_a-zA-Z][_a-zA-Z0-9]+ + +%% + +{num_dec} { return value(10); } +{num_hex} { return value(16); } +{space} { } + +ip { return sample(PERF_SAMPLE_IP); } +id { return sample(PERF_SAMPLE_ID); } +tid { return sample(PERF_SAMPLE_TID); } +cpu { return sample(PERF_SAMPLE_CPU); } +time { return sample(PERF_SAMPLE_TIME); } +addr { return sample(PERF_SAMPLE_ADDR); } +period { return sample(PERF_SAMPLE_PERIOD); } +txn { return sample(PERF_SAMPLE_TRANSACTION); } +weight { return sample(PERF_SAMPLE_WEIGHT); } +phys_addr { return sample(PERF_SAMPLE_PHYS_ADDR); } +code_pgsz { return sample(PERF_SAMPLE_CODE_PAGE_SIZE); } +data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); } + +"==" { return operator(PBF_OP_EQ); } +"!=" { return operator(PBF_OP_NEQ); } +">" { return operator(PBF_OP_GT); } +"<" { return operator(PBF_OP_LT); } +">=" { return operator(PBF_OP_GE); } +"<=" { return operator(PBF_OP_LE); } +"&" { return operator(PBF_OP_AND); } + +"," { return ','; } + +{ident} { return error("ident"); } +. { return error("input"); } + +%% diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y new file mode 100644 index 000000000000..13eca612ecca --- /dev/null +++ b/tools/perf/util/bpf-filter.y @@ -0,0 +1,54 @@ +%parse-param {struct list_head *expr_head} +%define parse.error verbose + +%{ + +#include +#include +#include +#include +#include "bpf-filter.h" + +static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, + char const *msg) +{ + printf("perf_bpf_filter: %s\n", msg); +} + +%} + +%union +{ + unsigned long num; + unsigned long sample; + enum perf_bpf_filter_op op; + struct perf_bpf_filter_expr *expr; +} + +%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM +%type filter_term +%destructor { free ($$); } +%type BFT_SAMPLE +%type BFT_OP +%type BFT_NUM + +%% + +filter: +filter ',' filter_term +{ + list_add_tail(&$3->list, expr_head); +} +| +filter_term +{ + list_add_tail(&$1->list, expr_head); +} + +filter_term: +BFT_SAMPLE BFT_OP BFT_NUM +{ + $$ = perf_bpf_filter_expr__new($1, $2, $3); +} + +%% -- GitLab From 56ec9457a4a20c5e07ad94bfb6e23077d54cb28e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:29 -0700 Subject: [PATCH 0518/5631] perf bpf filter: Implement event sample filtering The BPF program will be attached to a perf_event and be triggered when it overflows. It'd iterate the filters map and compare the sample value according to the expression. If any of them fails, the sample would be dropped. Also it needs to have the corresponding sample data for the expression so it compares data->sample_flags with the given value. To access the sample data, it uses the bpf_cast_to_kern_ctx() kfunc which was added in v6.2 kernel. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 +- tools/perf/util/bpf-filter.c | 64 ++++++++++ tools/perf/util/bpf-filter.h | 26 ++-- tools/perf/util/bpf_skel/sample-filter.h | 24 ++++ tools/perf/util/bpf_skel/sample_filter.bpf.c | 126 +++++++++++++++++++ tools/perf/util/evsel.h | 7 +- 6 files changed, 236 insertions(+), 13 deletions(-) create mode 100644 tools/perf/util/bpf_skel/sample-filter.h create mode 100644 tools/perf/util/bpf_skel/sample_filter.bpf.c diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index dc9dda09b076..ed6b6a070f79 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1050,7 +1050,7 @@ SKELETONS := $(SKEL_OUT)/bpf_prog_profiler.skel.h SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h -SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h +SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index c72e35d51240..f20e1bc03778 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -1,10 +1,74 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include +#include +#include + +#include "util/debug.h" +#include "util/evsel.h" + #include "util/bpf-filter.h" #include "util/bpf-filter-flex.h" #include "util/bpf-filter-bison.h" +#include "bpf_skel/sample-filter.h" +#include "bpf_skel/sample_filter.skel.h" + +#define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) + +int perf_bpf_filter__prepare(struct evsel *evsel) +{ + int i, x, y, fd; + struct sample_filter_bpf *skel; + struct bpf_program *prog; + struct bpf_link *link; + struct perf_bpf_filter_expr *expr; + + skel = sample_filter_bpf__open_and_load(); + if (!skel) { + pr_err("Failed to load perf sample-filter BPF skeleton\n"); + return -1; + } + + i = 0; + fd = bpf_map__fd(skel->maps.filters); + list_for_each_entry(expr, &evsel->bpf_filters, list) { + struct perf_bpf_filter_entry entry = { + .op = expr->op, + .flags = expr->sample_flags, + .value = expr->val, + }; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + i++; + } + + prog = skel->progs.perf_sample_filter; + for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { + for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { + link = bpf_program__attach_perf_event(prog, FD(evsel, x, y)); + if (IS_ERR(link)) { + pr_err("Failed to attach perf sample-filter program\n"); + return PTR_ERR(link); + } + } + } + evsel->bpf_skel = skel; + return 0; +} + +int perf_bpf_filter__destroy(struct evsel *evsel) +{ + struct perf_bpf_filter_expr *expr, *tmp; + + list_for_each_entry_safe(expr, tmp, &evsel->bpf_filters, list) { + list_del(&expr->list); + free(expr); + } + sample_filter_bpf__destroy(evsel->bpf_skel); + return 0; +} + struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val) diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 93a0d3de038c..eb8e1ac43cdf 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -4,15 +4,7 @@ #include -enum perf_bpf_filter_op { - PBF_OP_EQ, - PBF_OP_NEQ, - PBF_OP_GT, - PBF_OP_GE, - PBF_OP_LT, - PBF_OP_LE, - PBF_OP_AND, -}; +#include "bpf_skel/sample-filter.h" struct perf_bpf_filter_expr { struct list_head list; @@ -21,16 +13,30 @@ struct perf_bpf_filter_expr { unsigned long val; }; +struct evsel; + #ifdef HAVE_BPF_SKEL struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); +int perf_bpf_filter__prepare(struct evsel *evsel); +int perf_bpf_filter__destroy(struct evsel *evsel); + #else /* !HAVE_BPF_SKEL */ + static inline int perf_bpf_filter__parse(struct list_head *expr_head __maybe_unused, const char *str __maybe_unused) { - return -ENOSYS; + return -EOPNOTSUPP; +} +static inline int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) +{ + return -EOPNOTSUPP; +} +static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) +{ + return -EOPNOTSUPP; } #endif /* HAVE_BPF_SKEL*/ #endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h new file mode 100644 index 000000000000..862060bfda14 --- /dev/null +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -0,0 +1,24 @@ +#ifndef PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H +#define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H + +#define MAX_FILTERS 32 + +/* supported filter operations */ +enum perf_bpf_filter_op { + PBF_OP_EQ, + PBF_OP_NEQ, + PBF_OP_GT, + PBF_OP_GE, + PBF_OP_LT, + PBF_OP_LE, + PBF_OP_AND +}; + +/* BPF map entry for filtering */ +struct perf_bpf_filter_entry { + enum perf_bpf_filter_op op; + __u64 flags; + __u64 value; +}; + +#endif /* PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H */ \ No newline at end of file diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c new file mode 100644 index 000000000000..c07256279c3e --- /dev/null +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2023 Google +#include "vmlinux.h" +#include +#include +#include + +#include "sample-filter.h" + +/* BPF map that will be filled by user space */ +struct filters { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct perf_bpf_filter_entry); + __uint(max_entries, MAX_FILTERS); +} filters SEC(".maps"); + +int dropped; + +void *bpf_cast_to_kern_ctx(void *) __ksym; + +/* new kernel perf_sample_data definition */ +struct perf_sample_data___new { + __u64 sample_flags; +} __attribute__((preserve_access_index)); + +/* helper function to return the given perf sample data */ +static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, + struct perf_bpf_filter_entry *entry) +{ + struct perf_sample_data___new *data = (void *)kctx->data; + + if (!bpf_core_field_exists(data->sample_flags) || + (data->sample_flags & entry->flags) == 0) + return 0; + + switch (entry->flags) { + case PERF_SAMPLE_IP: + return kctx->data->ip; + case PERF_SAMPLE_ID: + return kctx->data->id; + case PERF_SAMPLE_TID: + return kctx->data->tid_entry.tid; + case PERF_SAMPLE_CPU: + return kctx->data->cpu_entry.cpu; + case PERF_SAMPLE_TIME: + return kctx->data->time; + case PERF_SAMPLE_ADDR: + return kctx->data->addr; + case PERF_SAMPLE_PERIOD: + return kctx->data->period; + case PERF_SAMPLE_TRANSACTION: + return kctx->data->txn; + case PERF_SAMPLE_WEIGHT: + return kctx->data->weight.full; + case PERF_SAMPLE_PHYS_ADDR: + return kctx->data->phys_addr; + case PERF_SAMPLE_CODE_PAGE_SIZE: + return kctx->data->code_page_size; + case PERF_SAMPLE_DATA_PAGE_SIZE: + return kctx->data->data_page_size; + default: + break; + } + return 0; +} + +/* BPF program to be called from perf event overflow handler */ +SEC("perf_event") +int perf_sample_filter(void *ctx) +{ + struct bpf_perf_event_data_kern *kctx; + struct perf_bpf_filter_entry *entry; + __u64 sample_data; + int i; + + kctx = bpf_cast_to_kern_ctx(ctx); + + for (i = 0; i < MAX_FILTERS; i++) { + int key = i; /* needed for verifier :( */ + + entry = bpf_map_lookup_elem(&filters, &key); + if (entry == NULL) + break; + sample_data = perf_get_sample(kctx, entry); + + switch (entry->op) { + case PBF_OP_EQ: + if (!(sample_data == entry->value)) + goto drop; + break; + case PBF_OP_NEQ: + if (!(sample_data != entry->value)) + goto drop; + break; + case PBF_OP_GT: + if (!(sample_data > entry->value)) + goto drop; + break; + case PBF_OP_GE: + if (!(sample_data >= entry->value)) + goto drop; + break; + case PBF_OP_LT: + if (!(sample_data < entry->value)) + goto drop; + break; + case PBF_OP_LE: + if (!(sample_data <= entry->value)) + goto drop; + break; + case PBF_OP_AND: + if (!(sample_data & entry->value)) + goto drop; + break; + } + } + /* generate sample data */ + return 1; + +drop: + __sync_fetch_and_add(&dropped, 1); + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index c272c06565c0..68072ec655ce 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -150,8 +150,10 @@ struct evsel { */ struct bpf_counter_ops *bpf_counter_ops; - /* for perf-stat -b */ - struct list_head bpf_counter_list; + union { + struct list_head bpf_counter_list; /* for perf-stat -b */ + struct list_head bpf_filters; /* for perf-record --filter */ + }; /* for perf-stat --use-bpf */ int bperf_leader_prog_fd; @@ -159,6 +161,7 @@ struct evsel { union { struct bperf_leader_bpf *leader_skel; struct bperf_follower_bpf *follower_skel; + void *bpf_skel; }; unsigned long open_flags; int precise_ip_original; -- GitLab From 01b33e284ca28cc977bdcfb23be2c719f2139175 Mon Sep 17 00:00:00 2001 From: Eugene Huang Date: Tue, 14 Mar 2023 17:06:18 +0800 Subject: [PATCH 0519/5631] soundwire: dmi-quirks: add remapping for Intel 'Rooks County' NUC M15 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Same DSDT problem as the HP Omen 16-k0005TX, except rt1316 amp is on link2. Link: https://github.com/thesofproject/linux/issues/4088 Signed-off-by: Eugene Huang Reviewed-by: Pierre-Louis Bossart Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314090618.498716-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/dmi-quirks.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/drivers/soundwire/dmi-quirks.c b/drivers/soundwire/dmi-quirks.c index 7969881f126d..58ea013fa918 100644 --- a/drivers/soundwire/dmi-quirks.c +++ b/drivers/soundwire/dmi-quirks.c @@ -73,6 +73,23 @@ static const struct adr_remap hp_omen_16[] = { {} }; +/* + * Intel NUC M15 LAPRC510 and LAPRC710 + */ +static const struct adr_remap intel_rooks_county[] = { + /* rt711-sdca on link0 */ + { + 0x000020025d071100ull, + 0x000030025d071101ull + }, + /* rt1316-sdca on link2 */ + { + 0x000120025d071100ull, + 0x000230025d131601ull + }, + {} +}; + static const struct dmi_system_id adr_remap_quirk_table[] = { /* TGL devices */ { @@ -98,6 +115,14 @@ static const struct dmi_system_id adr_remap_quirk_table[] = { }, .driver_data = (void *)intel_tgl_bios, }, + { + /* quirk used for NUC15 'Rooks County' LAPRC510 and LAPRC710 skews */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel(R) Client Systems"), + DMI_MATCH(DMI_PRODUCT_NAME, "LAPRC"), + }, + .driver_data = (void *)intel_rooks_county, + }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc"), -- GitLab From 4dd50aff56469bdc3638052e96e0a67d7c07dcb2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:53:55 +0800 Subject: [PATCH 0520/5631] soundwire: intel: move common definitions to header file Prepare for reused for addition of new hardware Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 32 -------------------------------- drivers/soundwire/intel.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 32 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 2651767272c7..20067f9cd128 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -19,38 +19,6 @@ #include "bus.h" #include "intel.h" - -enum intel_pdi_type { - INTEL_PDI_IN = 0, - INTEL_PDI_OUT = 1, - INTEL_PDI_BD = 2, -}; - -#define cdns_to_intel(_cdns) container_of(_cdns, struct sdw_intel, cdns) - -/* - * Read, write helpers for HW registers - */ -static inline int intel_readl(void __iomem *base, int offset) -{ - return readl(base + offset); -} - -static inline void intel_writel(void __iomem *base, int offset, int value) -{ - writel(value, base + offset); -} - -static inline u16 intel_readw(void __iomem *base, int offset) -{ - return readw(base + offset); -} - -static inline void intel_writew(void __iomem *base, int offset, u16 value) -{ - writew(value, base + offset); -} - static int intel_wait_bit(void __iomem *base, int offset, u32 mask, u32 target) { int timeout = 10; diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index de9883313c8f..089c41babfc1 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -50,6 +50,35 @@ struct sdw_intel { #endif }; +enum intel_pdi_type { + INTEL_PDI_IN = 0, + INTEL_PDI_OUT = 1, + INTEL_PDI_BD = 2, +}; + +/* + * Read, write helpers for HW registers + */ +static inline int intel_readl(void __iomem *base, int offset) +{ + return readl(base + offset); +} + +static inline void intel_writel(void __iomem *base, int offset, int value) +{ + writel(value, base + offset); +} + +static inline u16 intel_readw(void __iomem *base, int offset) +{ + return readw(base + offset); +} + +static inline void intel_writew(void __iomem *base, int offset, u16 value) +{ + writew(value, base + offset); +} + #define cdns_to_intel(_cdns) container_of(_cdns, struct sdw_intel, cdns) #define INTEL_MASTER_RESET_ITERATIONS 10 -- GitLab From a2d76b72b687e47baa41cebb9a9d44329552164a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:53:56 +0800 Subject: [PATCH 0521/5631] soundwire: intel: remove stale/misleading comment The PDIs don't really have a notion of rates and formats, only channels are relevant. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 20067f9cd128..924dff670170 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1056,7 +1056,6 @@ static int intel_create_dai(struct sdw_cdns *cdns, if (num == 0) return 0; - /* TODO: Read supported rates/formats from hardware */ for (i = off; i < (off + num); i++) { dais[i].name = devm_kasprintf(cdns->dev, GFP_KERNEL, "SDW%d Pin%d", -- GitLab From dc9256c91b722863d8ed6f0819798e000a227343 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:53:57 +0800 Subject: [PATCH 0522/5631] soundwire: intel: remove PDI-level restrictions on rates and formats This is not relevant and not aligned with hardware definitions. In addition, we've tested higher resolution formats so this is ignored at a higher level. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-4-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 924dff670170..6c17baab7923 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1066,15 +1066,11 @@ static int intel_create_dai(struct sdw_cdns *cdns, if (type == INTEL_PDI_BD || type == INTEL_PDI_OUT) { dais[i].playback.channels_min = 1; dais[i].playback.channels_max = max_ch; - dais[i].playback.rates = SNDRV_PCM_RATE_48000; - dais[i].playback.formats = SNDRV_PCM_FMTBIT_S16_LE; } if (type == INTEL_PDI_BD || type == INTEL_PDI_IN) { dais[i].capture.channels_min = 1; dais[i].capture.channels_max = max_ch; - dais[i].capture.rates = SNDRV_PCM_RATE_48000; - dais[i].capture.formats = SNDRV_PCM_FMTBIT_S16_LE; } dais[i].ops = &intel_pcm_dai_ops; -- GitLab From 59e924fe159cb441d6ff96811fde72ef0f32c094 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:53:58 +0800 Subject: [PATCH 0523/5631] soundwire: intel: remove useless abstraction PDM is supported in the hardware but never enabled: there are no known PDM-based devices. We can directly call the PCM helper. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-5-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 6c17baab7923..2c1c905f8889 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -586,13 +586,6 @@ static int intel_pdi_stream_ch_update(struct sdw_intel *sdw, return 0; } -static int intel_pdi_ch_update(struct sdw_intel *sdw) -{ - intel_pdi_stream_ch_update(sdw, &sdw->cdns.pcm); - - return 0; -} - static void intel_pdi_shim_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi) { @@ -1094,7 +1087,7 @@ static int intel_register_dai(struct sdw_intel *sdw) if (ret) return ret; - intel_pdi_ch_update(sdw); + intel_pdi_stream_ch_update(sdw, &sdw->cdns.pcm); /* DAIs are created based on total number of PDIs supported */ num_dai = cdns->pcm.num_pdi; -- GitLab From 9c49a4dd6c861bd2636094712d6d874e257787e2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:53:59 +0800 Subject: [PATCH 0524/5631] soundwire: intel: simplify sync_go sequence In the existing code, the SHIM_SYNC::SYNC_GO bit is set, and the code waits for it to return to zero. That second wait part is just wrong: the SYNC_GO bit is *write-only* so there's no way to know if it's cleared by hardware. The code works because the value for a read-only bit is zero, but that's really just luck. Simplify the sequence to a plain read-modify-write. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-6-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 2c1c905f8889..6fdb10117e59 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -475,7 +475,6 @@ static int intel_shim_sync_go_unlocked(struct sdw_intel *sdw) { void __iomem *shim = sdw->link_res->shim; u32 sync_reg; - int ret; /* Read SYNC register */ sync_reg = intel_readl(shim, SDW_SHIM_SYNC); @@ -487,13 +486,9 @@ static int intel_shim_sync_go_unlocked(struct sdw_intel *sdw) */ sync_reg |= SDW_SHIM_SYNC_SYNCGO; - ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg, - SDW_SHIM_SYNC_SYNCGO); - - if (ret < 0) - dev_err(sdw->cdns.dev, "SyncGO clear failed: %d\n", ret); + intel_writel(shim, SDW_SHIM_SYNC, sync_reg); - return ret; + return 0; } static int intel_shim_sync_go(struct sdw_intel *sdw) -- GitLab From 84706e9a75ffc3c950424bdfea06cabb4101a6b4 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:00 +0800 Subject: [PATCH 0525/5631] soundwire: intel: add sync_arm/sync_go to ops The bus start/stop sequences can be reused between platforms if we add a couple of new callbacks. In following patches the code will be moved to a shared file. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-7-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 16 ++++++++++------ drivers/soundwire/intel.h | 20 ++++++++++++++++++++ include/linux/soundwire/sdw_intel.h | 8 ++++++++ 3 files changed, 38 insertions(+), 6 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 6fdb10117e59..902934cbb27b 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -686,7 +686,7 @@ static int intel_pre_bank_switch(struct sdw_intel *sdw) if (!bus->multi_link) return 0; - intel_shim_sync_arm(sdw); + sdw_intel_sync_arm(sdw); return 0; } @@ -720,7 +720,7 @@ static int intel_post_bank_switch(struct sdw_intel *sdw) goto unlock; } - ret = intel_shim_sync_go_unlocked(sdw); + ret = sdw_intel_sync_go_unlocked(sdw); unlock: mutex_unlock(sdw->link_res->shim_lock); @@ -1140,7 +1140,7 @@ static int intel_start_bus(struct sdw_intel *sdw) * gsync is enabled */ if (bus->multi_link) - intel_shim_sync_arm(sdw); + sdw_intel_sync_arm(sdw); ret = sdw_cdns_init(cdns); if (ret < 0) { @@ -1155,7 +1155,7 @@ static int intel_start_bus(struct sdw_intel *sdw) } if (bus->multi_link) { - ret = intel_shim_sync_go(sdw); + ret = sdw_intel_sync_go(sdw); if (ret < 0) { dev_err(dev, "%s: sync go failed: %d\n", __func__, ret); goto err_interrupt; @@ -1210,7 +1210,7 @@ static int intel_start_bus_after_reset(struct sdw_intel *sdw) * timeouts when gsync is enabled */ if (bus->multi_link) - intel_shim_sync_arm(sdw); + sdw_intel_sync_arm(sdw); /* * Re-initialize the IP since it was powered-off @@ -1239,7 +1239,7 @@ static int intel_start_bus_after_reset(struct sdw_intel *sdw) } if (bus->multi_link) { - ret = intel_shim_sync_go(sdw); + ret = sdw_intel_sync_go(sdw); if (ret < 0) { dev_err(sdw->cdns.dev, "sync go failed during resume\n"); goto err_interrupt; @@ -1342,6 +1342,10 @@ const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops = { .pre_bank_switch = intel_pre_bank_switch, .post_bank_switch = intel_post_bank_switch, + + .sync_arm = intel_shim_sync_arm, + .sync_go_unlocked = intel_shim_sync_go_unlocked, + .sync_go = intel_shim_sync_go, }; EXPORT_SYMBOL_NS(sdw_intel_cnl_hw_ops, SOUNDWIRE_INTEL); diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index 089c41babfc1..28b21a92e28b 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -167,4 +167,24 @@ static inline void sdw_intel_shim_wake(struct sdw_intel *sdw, bool wake_enable) SDW_INTEL_OPS(sdw, shim_wake)(sdw, wake_enable); } +static inline void sdw_intel_sync_arm(struct sdw_intel *sdw) +{ + if (SDW_INTEL_CHECK_OPS(sdw, sync_arm)) + SDW_INTEL_OPS(sdw, sync_arm)(sdw); +} + +static inline int sdw_intel_sync_go_unlocked(struct sdw_intel *sdw) +{ + if (SDW_INTEL_CHECK_OPS(sdw, sync_go_unlocked)) + return SDW_INTEL_OPS(sdw, sync_go_unlocked)(sdw); + return -ENOTSUPP; +} + +static inline int sdw_intel_sync_go(struct sdw_intel *sdw) +{ + if (SDW_INTEL_CHECK_OPS(sdw, sync_go)) + return SDW_INTEL_OPS(sdw, sync_go)(sdw); + return -ENOTSUPP; +} + #endif /* __SDW_INTEL_LOCAL_H */ diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 91f0dc564fe5..06fa30929ebd 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -309,6 +309,10 @@ struct sdw_intel; * @shim_wake: enable/disable in-band wake management * @pre_bank_switch: helper for bus management * @post_bank_switch: helper for bus management + * @sync_arm: helper for multi-link synchronization + * @sync_go_unlocked: helper for multi-link synchronization - + * shim_lock is assumed to be locked at higher level + * @sync_go: helper for multi-link synchronization */ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); @@ -330,6 +334,10 @@ struct sdw_intel_hw_ops { int (*pre_bank_switch)(struct sdw_intel *sdw); int (*post_bank_switch)(struct sdw_intel *sdw); + + void (*sync_arm)(struct sdw_intel *sdw); + int (*sync_go_unlocked)(struct sdw_intel *sdw); + int (*sync_go)(struct sdw_intel *sdw); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; -- GitLab From 90e4632a6f6cee2a8f2ef20f47c2a5ccc7a780ea Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:01 +0800 Subject: [PATCH 0526/5631] soundwire: intel: use indirection before moving bus start/stop sequences There was no benefit to using the existing abstraction, but since we are going to move the code make sure we do use the ops. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-8-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 902934cbb27b..8395a20e5739 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1311,13 +1311,13 @@ static int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop) return ret; } - ret = intel_link_power_down(sdw); + ret = sdw_intel_link_power_down(sdw); if (ret) { dev_err(dev, "%s: Link power down failed: %d\n", __func__, ret); return ret; } - intel_shim_wake(sdw, wake_enable); + sdw_intel_shim_wake(sdw, wake_enable); return 0; } -- GitLab From 1a1a6a692e9cd58c235651fa281219dab02afeed Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:02 +0800 Subject: [PATCH 0527/5631] soundwire: intel: move bus common sequences to different file Now that the bus start/stop/clock_stop sequences use the ops, we can move them to a different file to reuse them. Note that we could in theory remove the abstraction for all those sequences and directly call the functions in intel_auxdevice.c. To allow for more flexibility and have means to special-case new platforms, we decided to keep the abstraction. If in time it becomes clear there is no benefit the abstraction will be simplified. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-9-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/Makefile | 3 +- drivers/soundwire/intel.c | 199 ------------------------- drivers/soundwire/intel.h | 7 + drivers/soundwire/intel_bus_common.c | 210 +++++++++++++++++++++++++++ 4 files changed, 219 insertions(+), 200 deletions(-) create mode 100644 drivers/soundwire/intel_bus_common.c diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile index ca97414ada70..8038e840ac5b 100644 --- a/drivers/soundwire/Makefile +++ b/drivers/soundwire/Makefile @@ -20,7 +20,8 @@ soundwire-cadence-y := cadence_master.o obj-$(CONFIG_SOUNDWIRE_CADENCE) += soundwire-cadence.o #Intel driver -soundwire-intel-y := intel.o intel_auxdevice.o intel_init.o dmi-quirks.o +soundwire-intel-y := intel.o intel_auxdevice.o intel_init.o dmi-quirks.o \ + intel_bus_common.o obj-$(CONFIG_SOUNDWIRE_INTEL) += soundwire-intel.o #Qualcomm driver diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 8395a20e5739..77d698908595 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1122,205 +1122,6 @@ static int intel_register_dai(struct sdw_intel *sdw) dais, num_dai); } -static int intel_start_bus(struct sdw_intel *sdw) -{ - struct device *dev = sdw->cdns.dev; - struct sdw_cdns *cdns = &sdw->cdns; - struct sdw_bus *bus = &cdns->bus; - int ret; - - ret = sdw_cdns_enable_interrupt(cdns, true); - if (ret < 0) { - dev_err(dev, "%s: cannot enable interrupts: %d\n", __func__, ret); - return ret; - } - - /* - * follow recommended programming flows to avoid timeouts when - * gsync is enabled - */ - if (bus->multi_link) - sdw_intel_sync_arm(sdw); - - ret = sdw_cdns_init(cdns); - if (ret < 0) { - dev_err(dev, "%s: unable to initialize Cadence IP: %d\n", __func__, ret); - goto err_interrupt; - } - - ret = sdw_cdns_exit_reset(cdns); - if (ret < 0) { - dev_err(dev, "%s: unable to exit bus reset sequence: %d\n", __func__, ret); - goto err_interrupt; - } - - if (bus->multi_link) { - ret = sdw_intel_sync_go(sdw); - if (ret < 0) { - dev_err(dev, "%s: sync go failed: %d\n", __func__, ret); - goto err_interrupt; - } - } - sdw_cdns_check_self_clearing_bits(cdns, __func__, - true, INTEL_MASTER_RESET_ITERATIONS); - - return 0; - -err_interrupt: - sdw_cdns_enable_interrupt(cdns, false); - return ret; -} - -static int intel_start_bus_after_reset(struct sdw_intel *sdw) -{ - struct device *dev = sdw->cdns.dev; - struct sdw_cdns *cdns = &sdw->cdns; - struct sdw_bus *bus = &cdns->bus; - bool clock_stop0; - int status; - int ret; - - /* - * An exception condition occurs for the CLK_STOP_BUS_RESET - * case if one or more masters remain active. In this condition, - * all the masters are powered on for they are in the same power - * domain. Master can preserve its context for clock stop0, so - * there is no need to clear slave status and reset bus. - */ - clock_stop0 = sdw_cdns_is_clock_stop(&sdw->cdns); - - if (!clock_stop0) { - - /* - * make sure all Slaves are tagged as UNATTACHED and - * provide reason for reinitialization - */ - - status = SDW_UNATTACH_REQUEST_MASTER_RESET; - sdw_clear_slave_status(bus, status); - - ret = sdw_cdns_enable_interrupt(cdns, true); - if (ret < 0) { - dev_err(dev, "cannot enable interrupts during resume\n"); - return ret; - } - - /* - * follow recommended programming flows to avoid - * timeouts when gsync is enabled - */ - if (bus->multi_link) - sdw_intel_sync_arm(sdw); - - /* - * Re-initialize the IP since it was powered-off - */ - sdw_cdns_init(&sdw->cdns); - - } else { - ret = sdw_cdns_enable_interrupt(cdns, true); - if (ret < 0) { - dev_err(dev, "cannot enable interrupts during resume\n"); - return ret; - } - } - - ret = sdw_cdns_clock_restart(cdns, !clock_stop0); - if (ret < 0) { - dev_err(dev, "unable to restart clock during resume\n"); - goto err_interrupt; - } - - if (!clock_stop0) { - ret = sdw_cdns_exit_reset(cdns); - if (ret < 0) { - dev_err(dev, "unable to exit bus reset sequence during resume\n"); - goto err_interrupt; - } - - if (bus->multi_link) { - ret = sdw_intel_sync_go(sdw); - if (ret < 0) { - dev_err(sdw->cdns.dev, "sync go failed during resume\n"); - goto err_interrupt; - } - } - } - sdw_cdns_check_self_clearing_bits(cdns, __func__, true, INTEL_MASTER_RESET_ITERATIONS); - - return 0; - -err_interrupt: - sdw_cdns_enable_interrupt(cdns, false); - return ret; -} - -static void intel_check_clock_stop(struct sdw_intel *sdw) -{ - struct device *dev = sdw->cdns.dev; - bool clock_stop0; - - clock_stop0 = sdw_cdns_is_clock_stop(&sdw->cdns); - if (!clock_stop0) - dev_err(dev, "%s: invalid configuration, clock was not stopped\n", __func__); -} - -static int intel_start_bus_after_clock_stop(struct sdw_intel *sdw) -{ - struct device *dev = sdw->cdns.dev; - struct sdw_cdns *cdns = &sdw->cdns; - int ret; - - ret = sdw_cdns_enable_interrupt(cdns, true); - if (ret < 0) { - dev_err(dev, "%s: cannot enable interrupts: %d\n", __func__, ret); - return ret; - } - - ret = sdw_cdns_clock_restart(cdns, false); - if (ret < 0) { - dev_err(dev, "%s: unable to restart clock: %d\n", __func__, ret); - sdw_cdns_enable_interrupt(cdns, false); - return ret; - } - - sdw_cdns_check_self_clearing_bits(cdns, "intel_resume_runtime no_quirks", - true, INTEL_MASTER_RESET_ITERATIONS); - - return 0; -} - -static int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop) -{ - struct device *dev = sdw->cdns.dev; - struct sdw_cdns *cdns = &sdw->cdns; - bool wake_enable = false; - int ret; - - if (clock_stop) { - ret = sdw_cdns_clock_stop(cdns, true); - if (ret < 0) - dev_err(dev, "%s: cannot stop clock: %d\n", __func__, ret); - else - wake_enable = true; - } - - ret = sdw_cdns_enable_interrupt(cdns, false); - if (ret < 0) { - dev_err(dev, "%s: cannot disable interrupts: %d\n", __func__, ret); - return ret; - } - - ret = sdw_intel_link_power_down(sdw); - if (ret) { - dev_err(dev, "%s: Link power down failed: %d\n", __func__, ret); - return ret; - } - - sdw_intel_shim_wake(sdw, wake_enable); - - return 0; -} const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops = { .debugfs_init = intel_debugfs_init, diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index 28b21a92e28b..abd1a500defa 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -187,4 +187,11 @@ static inline int sdw_intel_sync_go(struct sdw_intel *sdw) return -ENOTSUPP; } +/* common bus management */ +int intel_start_bus(struct sdw_intel *sdw); +int intel_start_bus_after_reset(struct sdw_intel *sdw); +void intel_check_clock_stop(struct sdw_intel *sdw); +int intel_start_bus_after_clock_stop(struct sdw_intel *sdw); +int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop); + #endif /* __SDW_INTEL_LOCAL_H */ diff --git a/drivers/soundwire/intel_bus_common.c b/drivers/soundwire/intel_bus_common.c new file mode 100644 index 000000000000..9a06ab58018b --- /dev/null +++ b/drivers/soundwire/intel_bus_common.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +// Copyright(c) 2015-2023 Intel Corporation. All rights reserved. + +#include +#include +#include +#include +#include "cadence_master.h" +#include "bus.h" +#include "intel.h" + +int intel_start_bus(struct sdw_intel *sdw) +{ + struct device *dev = sdw->cdns.dev; + struct sdw_cdns *cdns = &sdw->cdns; + struct sdw_bus *bus = &cdns->bus; + int ret; + + ret = sdw_cdns_enable_interrupt(cdns, true); + if (ret < 0) { + dev_err(dev, "%s: cannot enable interrupts: %d\n", __func__, ret); + return ret; + } + + /* + * follow recommended programming flows to avoid timeouts when + * gsync is enabled + */ + if (bus->multi_link) + sdw_intel_sync_arm(sdw); + + ret = sdw_cdns_init(cdns); + if (ret < 0) { + dev_err(dev, "%s: unable to initialize Cadence IP: %d\n", __func__, ret); + goto err_interrupt; + } + + ret = sdw_cdns_exit_reset(cdns); + if (ret < 0) { + dev_err(dev, "%s: unable to exit bus reset sequence: %d\n", __func__, ret); + goto err_interrupt; + } + + if (bus->multi_link) { + ret = sdw_intel_sync_go(sdw); + if (ret < 0) { + dev_err(dev, "%s: sync go failed: %d\n", __func__, ret); + goto err_interrupt; + } + } + sdw_cdns_check_self_clearing_bits(cdns, __func__, + true, INTEL_MASTER_RESET_ITERATIONS); + + return 0; + +err_interrupt: + sdw_cdns_enable_interrupt(cdns, false); + return ret; +} + +int intel_start_bus_after_reset(struct sdw_intel *sdw) +{ + struct device *dev = sdw->cdns.dev; + struct sdw_cdns *cdns = &sdw->cdns; + struct sdw_bus *bus = &cdns->bus; + bool clock_stop0; + int status; + int ret; + + /* + * An exception condition occurs for the CLK_STOP_BUS_RESET + * case if one or more masters remain active. In this condition, + * all the masters are powered on for they are in the same power + * domain. Master can preserve its context for clock stop0, so + * there is no need to clear slave status and reset bus. + */ + clock_stop0 = sdw_cdns_is_clock_stop(&sdw->cdns); + + if (!clock_stop0) { + + /* + * make sure all Slaves are tagged as UNATTACHED and + * provide reason for reinitialization + */ + + status = SDW_UNATTACH_REQUEST_MASTER_RESET; + sdw_clear_slave_status(bus, status); + + ret = sdw_cdns_enable_interrupt(cdns, true); + if (ret < 0) { + dev_err(dev, "cannot enable interrupts during resume\n"); + return ret; + } + + /* + * follow recommended programming flows to avoid + * timeouts when gsync is enabled + */ + if (bus->multi_link) + sdw_intel_sync_arm(sdw); + + /* + * Re-initialize the IP since it was powered-off + */ + sdw_cdns_init(&sdw->cdns); + + } else { + ret = sdw_cdns_enable_interrupt(cdns, true); + if (ret < 0) { + dev_err(dev, "cannot enable interrupts during resume\n"); + return ret; + } + } + + ret = sdw_cdns_clock_restart(cdns, !clock_stop0); + if (ret < 0) { + dev_err(dev, "unable to restart clock during resume\n"); + goto err_interrupt; + } + + if (!clock_stop0) { + ret = sdw_cdns_exit_reset(cdns); + if (ret < 0) { + dev_err(dev, "unable to exit bus reset sequence during resume\n"); + goto err_interrupt; + } + + if (bus->multi_link) { + ret = sdw_intel_sync_go(sdw); + if (ret < 0) { + dev_err(sdw->cdns.dev, "sync go failed during resume\n"); + goto err_interrupt; + } + } + } + sdw_cdns_check_self_clearing_bits(cdns, __func__, true, INTEL_MASTER_RESET_ITERATIONS); + + return 0; + +err_interrupt: + sdw_cdns_enable_interrupt(cdns, false); + return ret; +} + +void intel_check_clock_stop(struct sdw_intel *sdw) +{ + struct device *dev = sdw->cdns.dev; + bool clock_stop0; + + clock_stop0 = sdw_cdns_is_clock_stop(&sdw->cdns); + if (!clock_stop0) + dev_err(dev, "%s: invalid configuration, clock was not stopped\n", __func__); +} + +int intel_start_bus_after_clock_stop(struct sdw_intel *sdw) +{ + struct device *dev = sdw->cdns.dev; + struct sdw_cdns *cdns = &sdw->cdns; + int ret; + + ret = sdw_cdns_enable_interrupt(cdns, true); + if (ret < 0) { + dev_err(dev, "%s: cannot enable interrupts: %d\n", __func__, ret); + return ret; + } + + ret = sdw_cdns_clock_restart(cdns, false); + if (ret < 0) { + dev_err(dev, "%s: unable to restart clock: %d\n", __func__, ret); + sdw_cdns_enable_interrupt(cdns, false); + return ret; + } + + sdw_cdns_check_self_clearing_bits(cdns, "intel_resume_runtime no_quirks", + true, INTEL_MASTER_RESET_ITERATIONS); + + return 0; +} + +int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop) +{ + struct device *dev = sdw->cdns.dev; + struct sdw_cdns *cdns = &sdw->cdns; + bool wake_enable = false; + int ret; + + if (clock_stop) { + ret = sdw_cdns_clock_stop(cdns, true); + if (ret < 0) + dev_err(dev, "%s: cannot stop clock: %d\n", __func__, ret); + else + wake_enable = true; + } + + ret = sdw_cdns_enable_interrupt(cdns, false); + if (ret < 0) { + dev_err(dev, "%s: cannot disable interrupts: %d\n", __func__, ret); + return ret; + } + + ret = sdw_intel_link_power_down(sdw); + if (ret) { + dev_err(dev, "%s: Link power down failed: %d\n", __func__, ret); + return ret; + } + + sdw_intel_shim_wake(sdw, wake_enable); + + return 0; +} -- GitLab From 1e76de2e5dfeff17f13afe8146449fec3f5b69f7 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:03 +0800 Subject: [PATCH 0528/5631] soundwire: intel: add abstraction for cmdsync check If we add one more callback, we can have common bank switch sequences between old and new hardware: the only difference is where the CMDSYNC register is located. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-10-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 24 +++++++++++++----------- drivers/soundwire/intel.h | 7 +++++++ include/linux/soundwire/sdw_intel.h | 3 +++ 3 files changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 77d698908595..1131ecb4b5e7 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -325,6 +325,15 @@ static void intel_shim_wake(struct sdw_intel *sdw, bool wake_enable) mutex_unlock(sdw->link_res->shim_lock); } +static bool intel_check_cmdsync_unlocked(struct sdw_intel *sdw) +{ + void __iomem *shim = sdw->link_res->shim; + int sync_reg; + + sync_reg = intel_readl(shim, SDW_SHIM_SYNC); + return !!(sync_reg & SDW_SHIM_SYNC_CMDSYNC_MASK); +} + static int intel_link_power_up(struct sdw_intel *sdw) { unsigned int link_id = sdw->instance; @@ -695,8 +704,7 @@ static int intel_post_bank_switch(struct sdw_intel *sdw) { struct sdw_cdns *cdns = &sdw->cdns; struct sdw_bus *bus = &cdns->bus; - void __iomem *shim = sdw->link_res->shim; - int sync_reg, ret; + int ret = 0; /* Write to register only for multi-link */ if (!bus->multi_link) @@ -704,9 +712,6 @@ static int intel_post_bank_switch(struct sdw_intel *sdw) mutex_lock(sdw->link_res->shim_lock); - /* Read SYNC register */ - sync_reg = intel_readl(shim, SDW_SHIM_SYNC); - /* * post_bank_switch() ops is called from the bus in loop for * all the Masters in the steam with the expectation that @@ -715,13 +720,9 @@ static int intel_post_bank_switch(struct sdw_intel *sdw) * * So, set the SYNCGO bit only if CMDSYNC bit is set for any Master. */ - if (!(sync_reg & SDW_SHIM_SYNC_CMDSYNC_MASK)) { - ret = 0; - goto unlock; - } + if (sdw_intel_sync_check_cmdsync_unlocked(sdw)) + ret = sdw_intel_sync_go_unlocked(sdw); - ret = sdw_intel_sync_go_unlocked(sdw); -unlock: mutex_unlock(sdw->link_res->shim_lock); if (ret < 0) @@ -1147,6 +1148,7 @@ const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops = { .sync_arm = intel_shim_sync_arm, .sync_go_unlocked = intel_shim_sync_go_unlocked, .sync_go = intel_shim_sync_go, + .sync_check_cmdsync_unlocked = intel_check_cmdsync_unlocked, }; EXPORT_SYMBOL_NS(sdw_intel_cnl_hw_ops, SOUNDWIRE_INTEL); diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index abd1a500defa..7a69cf755954 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -187,6 +187,13 @@ static inline int sdw_intel_sync_go(struct sdw_intel *sdw) return -ENOTSUPP; } +static inline bool sdw_intel_sync_check_cmdsync_unlocked(struct sdw_intel *sdw) +{ + if (SDW_INTEL_CHECK_OPS(sdw, sync_check_cmdsync_unlocked)) + return SDW_INTEL_OPS(sdw, sync_check_cmdsync_unlocked)(sdw); + return false; +} + /* common bus management */ int intel_start_bus(struct sdw_intel *sdw); int intel_start_bus_after_reset(struct sdw_intel *sdw); diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 06fa30929ebd..207701aeeb47 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -313,6 +313,8 @@ struct sdw_intel; * @sync_go_unlocked: helper for multi-link synchronization - * shim_lock is assumed to be locked at higher level * @sync_go: helper for multi-link synchronization + * @sync_check_cmdsync_unlocked: helper for multi-link synchronization + * and bank switch - shim_lock is assumed to be locked at higher level */ struct sdw_intel_hw_ops { void (*debugfs_init)(struct sdw_intel *sdw); @@ -338,6 +340,7 @@ struct sdw_intel_hw_ops { void (*sync_arm)(struct sdw_intel *sdw); int (*sync_go_unlocked)(struct sdw_intel *sdw); int (*sync_go)(struct sdw_intel *sdw); + bool (*sync_check_cmdsync_unlocked)(struct sdw_intel *sdw); }; extern const struct sdw_intel_hw_ops sdw_intel_cnl_hw_ops; -- GitLab From fb43d62ee772fac7173bfbed3ca1bccdc508f10a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:04 +0800 Subject: [PATCH 0529/5631] soundwire: intel: move bank switch routine to common intel_bus_common.c No functionality change, just moving the routines to a common file so that they can be used for new hardware. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-11-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 49 ---------------------------- drivers/soundwire/intel.h | 4 +++ drivers/soundwire/intel_bus_common.c | 49 ++++++++++++++++++++++++++++ 3 files changed, 53 insertions(+), 49 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 1131ecb4b5e7..046c67a2a39b 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -682,55 +682,6 @@ static int intel_free_stream(struct sdw_intel *sdw, return 0; } -/* - * bank switch routines - */ - -static int intel_pre_bank_switch(struct sdw_intel *sdw) -{ - struct sdw_cdns *cdns = &sdw->cdns; - struct sdw_bus *bus = &cdns->bus; - - /* Write to register only for multi-link */ - if (!bus->multi_link) - return 0; - - sdw_intel_sync_arm(sdw); - - return 0; -} - -static int intel_post_bank_switch(struct sdw_intel *sdw) -{ - struct sdw_cdns *cdns = &sdw->cdns; - struct sdw_bus *bus = &cdns->bus; - int ret = 0; - - /* Write to register only for multi-link */ - if (!bus->multi_link) - return 0; - - mutex_lock(sdw->link_res->shim_lock); - - /* - * post_bank_switch() ops is called from the bus in loop for - * all the Masters in the steam with the expectation that - * we trigger the bankswitch for the only first Master in the list - * and do nothing for the other Masters - * - * So, set the SYNCGO bit only if CMDSYNC bit is set for any Master. - */ - if (sdw_intel_sync_check_cmdsync_unlocked(sdw)) - ret = sdw_intel_sync_go_unlocked(sdw); - - mutex_unlock(sdw->link_res->shim_lock); - - if (ret < 0) - dev_err(sdw->cdns.dev, "Post bank switch failed: %d\n", ret); - - return ret; -} - /* * DAI routines */ diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index 7a69cf755954..09d479f2c77b 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -201,4 +201,8 @@ void intel_check_clock_stop(struct sdw_intel *sdw); int intel_start_bus_after_clock_stop(struct sdw_intel *sdw); int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop); +/* common bank switch routines */ +int intel_pre_bank_switch(struct sdw_intel *sdw); +int intel_post_bank_switch(struct sdw_intel *sdw); + #endif /* __SDW_INTEL_LOCAL_H */ diff --git a/drivers/soundwire/intel_bus_common.c b/drivers/soundwire/intel_bus_common.c index 9a06ab58018b..f180e3bea989 100644 --- a/drivers/soundwire/intel_bus_common.c +++ b/drivers/soundwire/intel_bus_common.c @@ -208,3 +208,52 @@ int intel_stop_bus(struct sdw_intel *sdw, bool clock_stop) return 0; } + +/* + * bank switch routines + */ + +int intel_pre_bank_switch(struct sdw_intel *sdw) +{ + struct sdw_cdns *cdns = &sdw->cdns; + struct sdw_bus *bus = &cdns->bus; + + /* Write to register only for multi-link */ + if (!bus->multi_link) + return 0; + + sdw_intel_sync_arm(sdw); + + return 0; +} + +int intel_post_bank_switch(struct sdw_intel *sdw) +{ + struct sdw_cdns *cdns = &sdw->cdns; + struct sdw_bus *bus = &cdns->bus; + int ret = 0; + + /* Write to register only for multi-link */ + if (!bus->multi_link) + return 0; + + mutex_lock(sdw->link_res->shim_lock); + + /* + * post_bank_switch() ops is called from the bus in loop for + * all the Masters in the steam with the expectation that + * we trigger the bankswitch for the only first Master in the list + * and do nothing for the other Masters + * + * So, set the SYNCGO bit only if CMDSYNC bit is set for any Master. + */ + if (sdw_intel_sync_check_cmdsync_unlocked(sdw)) + ret = sdw_intel_sync_go_unlocked(sdw); + + mutex_unlock(sdw->link_res->shim_lock); + + if (ret < 0) + dev_err(sdw->cdns.dev, "Post bank switch failed: %d\n", ret); + + return ret; +} -- GitLab From f117e90802d6c29621f0b97dbf9e7ac8250229b9 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:05 +0800 Subject: [PATCH 0530/5631] soundwire: cadence: remove CDNS_MCP_CONFIG_SSPMOD This field is not used, and its definition is not aligned with the hardware specification. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-12-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index e835dabb516c..4f34fc72dbd5 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -33,7 +33,6 @@ MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask"); #define CDNS_MCP_CONFIG_MMASTER BIT(7) #define CDNS_MCP_CONFIG_BUS_REL BIT(6) #define CDNS_MCP_CONFIG_SNIFFER BIT(5) -#define CDNS_MCP_CONFIG_SSPMOD BIT(4) #define CDNS_MCP_CONFIG_CMD BIT(3) #define CDNS_MCP_CONFIG_OP GENMASK(2, 0) #define CDNS_MCP_CONFIG_OP_NORMAL 0 -- GitLab From 9402e25df18f806127437b9b2b3f54eee5e85182 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:06 +0800 Subject: [PATCH 0531/5631] soundwire: cadence: add helpers to access IP_MCP registers The latest Cadence IP splits some of the existing registers into two, separated by a fixed offset. The bitfields themselves remain at the same position, so we can use new helpers to dynamically add the fixed offset. For example, the existing MCP_CONFIG is now split in two with MCP_CONFIG and IP_MCP_CONFIG (the naming comes directly from the design document). This patch adds helpers to access registers with the IP_ prefix. The addition of the 'ip' prefix for helpers, registers and bitfields is intentional to help reviewers spot any mistake. For existing solutions, the offset is exactly zero so there's no functional change - the MCP_CONFIG and IP_MCP_CONFIG are aliased to the same address. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-13-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 16 ++++++++++++++++ drivers/soundwire/cadence_master.h | 3 +++ 2 files changed, 19 insertions(+) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 4f34fc72dbd5..4461a7fa4124 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -205,6 +205,16 @@ static inline void cdns_writel(struct sdw_cdns *cdns, int offset, u32 value) writel(value, cdns->registers + offset); } +static inline u32 cdns_ip_readl(struct sdw_cdns *cdns, int offset) +{ + return cdns_readl(cdns, cdns->ip_offset + offset); +} + +static inline void cdns_ip_writel(struct sdw_cdns *cdns, int offset, u32 value) +{ + return cdns_writel(cdns, cdns->ip_offset + offset, value); +} + static inline void cdns_updatel(struct sdw_cdns *cdns, int offset, u32 mask, u32 val) { @@ -215,6 +225,12 @@ static inline void cdns_updatel(struct sdw_cdns *cdns, cdns_writel(cdns, offset, tmp); } +static inline void cdns_ip_updatel(struct sdw_cdns *cdns, + int offset, u32 mask, u32 val) +{ + cdns_updatel(cdns, cdns->ip_offset + offset, mask, val); +} + static int cdns_set_wait(struct sdw_cdns *cdns, int offset, u32 mask, u32 value) { int timeout = 10; diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index dec0b4f993c1..b653734085d9 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -107,6 +107,7 @@ struct sdw_cdns_dai_runtime { * @dev: Linux device * @bus: Bus handle * @instance: instance number + * @ip_offset: version-dependent offset to access IP_MCP registers and fields * @response_buf: SoundWire response buffer * @tx_complete: Tx completion * @ports: Data ports @@ -122,6 +123,8 @@ struct sdw_cdns { struct sdw_bus bus; unsigned int instance; + u32 ip_offset; + /* * The datasheet says the RX FIFO AVAIL can be 2 entries more * than the FIFO capacity, so allow for this. -- GitLab From c5753714fa323240872a9c21381acbb88fa3325e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:07 +0800 Subject: [PATCH 0532/5631] soundwire: cadence: split access to IP_MCP_CONFIG fields The latest Cadence IP splits the MCP_CONFIG fields in two registers: MCP_CONFIG and IP_MCP_CONFIG. Rename the relevant fields and change the access methods used for those fields. For existing solutions, this is an iso-functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-14-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 47 +++++++++++++++++------------- 1 file changed, 27 insertions(+), 20 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 4461a7fa4124..f7499e126404 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -27,15 +27,17 @@ module_param_named(cnds_mcp_int_mask, interrupt_mask, int, 0444); MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask"); #define CDNS_MCP_CONFIG 0x0 - -#define CDNS_MCP_CONFIG_MCMD_RETRY GENMASK(27, 24) -#define CDNS_MCP_CONFIG_MPREQ_DELAY GENMASK(20, 16) -#define CDNS_MCP_CONFIG_MMASTER BIT(7) #define CDNS_MCP_CONFIG_BUS_REL BIT(6) -#define CDNS_MCP_CONFIG_SNIFFER BIT(5) -#define CDNS_MCP_CONFIG_CMD BIT(3) -#define CDNS_MCP_CONFIG_OP GENMASK(2, 0) -#define CDNS_MCP_CONFIG_OP_NORMAL 0 + +#define CDNS_IP_MCP_CONFIG 0x0 /* IP offset added at run-time */ + +#define CDNS_IP_MCP_CONFIG_MCMD_RETRY GENMASK(27, 24) +#define CDNS_IP_MCP_CONFIG_MPREQ_DELAY GENMASK(20, 16) +#define CDNS_IP_MCP_CONFIG_MMASTER BIT(7) +#define CDNS_IP_MCP_CONFIG_SNIFFER BIT(5) +#define CDNS_IP_MCP_CONFIG_CMD BIT(3) +#define CDNS_IP_MCP_CONFIG_OP GENMASK(2, 0) +#define CDNS_IP_MCP_CONFIG_OP_NORMAL 0 #define CDNS_MCP_CONTROL 0x4 @@ -1348,28 +1350,33 @@ int sdw_cdns_init(struct sdw_cdns *cdns) /* Configure mcp config */ val = cdns_readl(cdns, CDNS_MCP_CONFIG); + /* Disable auto bus release */ + val &= ~CDNS_MCP_CONFIG_BUS_REL; + + cdns_writel(cdns, CDNS_MCP_CONFIG, val); + + /* Configure IP mcp config */ + val = cdns_ip_readl(cdns, CDNS_IP_MCP_CONFIG); + /* enable bus operations with clock and data */ - val &= ~CDNS_MCP_CONFIG_OP; - val |= CDNS_MCP_CONFIG_OP_NORMAL; + val &= ~CDNS_IP_MCP_CONFIG_OP; + val |= CDNS_IP_MCP_CONFIG_OP_NORMAL; /* Set cmd mode for Tx and Rx cmds */ - val &= ~CDNS_MCP_CONFIG_CMD; + val &= ~CDNS_IP_MCP_CONFIG_CMD; /* Disable sniffer mode */ - val &= ~CDNS_MCP_CONFIG_SNIFFER; - - /* Disable auto bus release */ - val &= ~CDNS_MCP_CONFIG_BUS_REL; + val &= ~CDNS_IP_MCP_CONFIG_SNIFFER; if (cdns->bus.multi_link) /* Set Multi-master mode to take gsync into account */ - val |= CDNS_MCP_CONFIG_MMASTER; + val |= CDNS_IP_MCP_CONFIG_MMASTER; /* leave frame delay to hardware default of 0x1F */ /* leave command retry to hardware default of 0 */ - cdns_writel(cdns, CDNS_MCP_CONFIG, val); + cdns_ip_writel(cdns, CDNS_IP_MCP_CONFIG, val); /* changes will be committed later */ return 0; @@ -1683,9 +1690,9 @@ int sdw_cdns_clock_restart(struct sdw_cdns *cdns, bool bus_reset) if (!bus_reset) { /* enable bus operations with clock and data */ - cdns_updatel(cdns, CDNS_MCP_CONFIG, - CDNS_MCP_CONFIG_OP, - CDNS_MCP_CONFIG_OP_NORMAL); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CONFIG, + CDNS_IP_MCP_CONFIG_OP, + CDNS_IP_MCP_CONFIG_OP_NORMAL); ret = cdns_config_update(cdns); if (ret < 0) { -- GitLab From 4dc953bcad2cdd3b0fe352e362fd731807f0fbb6 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:08 +0800 Subject: [PATCH 0533/5631] soundwire: cadence: split access to IP_MCP_CONTROL fields The latest Cadence IP splits the MCP_CONTROL fields in two registers: MCP_CONTROL and IP_MCP_CONTROL. Rename the relevant fields and change the access methods used for those fields. For existing solutions, this is an iso-functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-15-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 41 ++++++++++++++++++------------ 1 file changed, 25 insertions(+), 16 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index f7499e126404..4c82712944b9 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -41,15 +41,18 @@ MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask"); #define CDNS_MCP_CONTROL 0x4 -#define CDNS_MCP_CONTROL_RST_DELAY GENMASK(10, 8) #define CDNS_MCP_CONTROL_CMD_RST BIT(7) #define CDNS_MCP_CONTROL_SOFT_RST BIT(6) -#define CDNS_MCP_CONTROL_SW_RST BIT(5) #define CDNS_MCP_CONTROL_HW_RST BIT(4) -#define CDNS_MCP_CONTROL_CLK_PAUSE BIT(3) #define CDNS_MCP_CONTROL_CLK_STOP_CLR BIT(2) -#define CDNS_MCP_CONTROL_CMD_ACCEPT BIT(1) -#define CDNS_MCP_CONTROL_BLOCK_WAKEUP BIT(0) + +#define CDNS_IP_MCP_CONTROL 0x4 /* IP offset added at run-time */ + +#define CDNS_IP_MCP_CONTROL_RST_DELAY GENMASK(10, 8) +#define CDNS_IP_MCP_CONTROL_SW_RST BIT(5) +#define CDNS_IP_MCP_CONTROL_CLK_PAUSE BIT(3) +#define CDNS_IP_MCP_CONTROL_CMD_ACCEPT BIT(1) +#define CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP BIT(0) #define CDNS_MCP_CMDCTRL 0x8 @@ -1050,6 +1053,7 @@ static void cdns_update_slave_status_work(struct work_struct *work) void sdw_cdns_check_self_clearing_bits(struct sdw_cdns *cdns, const char *string, bool initial_delay, int reset_iterations) { + u32 ip_mcp_control; u32 mcp_control; u32 mcp_config_update; int i; @@ -1057,6 +1061,12 @@ void sdw_cdns_check_self_clearing_bits(struct sdw_cdns *cdns, const char *string if (initial_delay) usleep_range(1000, 1500); + ip_mcp_control = cdns_ip_readl(cdns, CDNS_IP_MCP_CONTROL); + + /* the following bits should be cleared immediately */ + if (ip_mcp_control & CDNS_IP_MCP_CONTROL_SW_RST) + dev_err(cdns->dev, "%s failed: IP_MCP_CONTROL_SW_RST is not cleared\n", string); + mcp_control = cdns_readl(cdns, CDNS_MCP_CONTROL); /* the following bits should be cleared immediately */ @@ -1064,10 +1074,9 @@ void sdw_cdns_check_self_clearing_bits(struct sdw_cdns *cdns, const char *string dev_err(cdns->dev, "%s failed: MCP_CONTROL_CMD_RST is not cleared\n", string); if (mcp_control & CDNS_MCP_CONTROL_SOFT_RST) dev_err(cdns->dev, "%s failed: MCP_CONTROL_SOFT_RST is not cleared\n", string); - if (mcp_control & CDNS_MCP_CONTROL_SW_RST) - dev_err(cdns->dev, "%s failed: MCP_CONTROL_SW_RST is not cleared\n", string); if (mcp_control & CDNS_MCP_CONTROL_CLK_STOP_CLR) dev_err(cdns->dev, "%s failed: MCP_CONTROL_CLK_STOP_CLR is not cleared\n", string); + mcp_config_update = cdns_readl(cdns, CDNS_MCP_CONFIG_UPDATE); if (mcp_config_update & CDNS_MCP_CONFIG_UPDATE_BIT) dev_err(cdns->dev, "%s failed: MCP_CONFIG_UPDATE_BIT is not cleared\n", string); @@ -1344,8 +1353,8 @@ int sdw_cdns_init(struct sdw_cdns *cdns) CDNS_MCP_CONTROL_CMD_RST); /* Set cmd accept mode */ - cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_ACCEPT, - CDNS_MCP_CONTROL_CMD_ACCEPT); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL, CDNS_IP_MCP_CONTROL_CMD_ACCEPT, + CDNS_IP_MCP_CONTROL_CMD_ACCEPT); /* Configure mcp config */ val = cdns_readl(cdns, CDNS_MCP_CONFIG); @@ -1606,9 +1615,9 @@ int sdw_cdns_clock_stop(struct sdw_cdns *cdns, bool block_wake) * in clock stop state */ if (block_wake) - cdns_updatel(cdns, CDNS_MCP_CONTROL, - CDNS_MCP_CONTROL_BLOCK_WAKEUP, - CDNS_MCP_CONTROL_BLOCK_WAKEUP); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL, + CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP, + CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP); list_for_each_entry(slave, &cdns->bus.slaves, node) { if (slave->status == SDW_SLAVE_ATTACHED || @@ -1681,11 +1690,11 @@ int sdw_cdns_clock_restart(struct sdw_cdns *cdns, bool bus_reset) return ret; } - cdns_updatel(cdns, CDNS_MCP_CONTROL, - CDNS_MCP_CONTROL_BLOCK_WAKEUP, 0); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL, + CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP, 0); - cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_ACCEPT, - CDNS_MCP_CONTROL_CMD_ACCEPT); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CONTROL, CDNS_IP_MCP_CONTROL_CMD_ACCEPT, + CDNS_IP_MCP_CONTROL_CMD_ACCEPT); if (!bus_reset) { -- GitLab From 73a29d3f3d5b38c8ce2779bdaf3eb9a86bc6c212 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:09 +0800 Subject: [PATCH 0534/5631] soundwire: cadence: split access to IP_MCP_CMDCTRL fields The latest Cadence IP splits the MCP_CMDCTRL fields in two registers: MCP_CMDCTRL and IP_MCP_CMDCTRL. Rename the relevant fields and change the access methods used for those fields. In practice we only use the Parity error insertion in IP_CMD_CTRL. For existing solutions, this is an iso-functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-16-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 4c82712944b9..5128923f051e 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -54,9 +54,9 @@ MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask"); #define CDNS_IP_MCP_CONTROL_CMD_ACCEPT BIT(1) #define CDNS_IP_MCP_CONTROL_BLOCK_WAKEUP BIT(0) -#define CDNS_MCP_CMDCTRL 0x8 +#define CDNS_IP_MCP_CMDCTRL 0x8 /* IP offset added at run-time */ -#define CDNS_MCP_CMDCTRL_INSERT_PARITY_ERR BIT(2) +#define CDNS_IP_MCP_CMDCTRL_INSERT_PARITY_ERR BIT(2) #define CDNS_MCP_SSPSTAT 0xC #define CDNS_MCP_FRAME_SHAPE 0x10 @@ -428,9 +428,9 @@ static int cdns_parity_error_injection(void *data, u64 value) mutex_lock(&bus->bus_lock); /* program hardware to inject parity error */ - cdns_updatel(cdns, CDNS_MCP_CMDCTRL, - CDNS_MCP_CMDCTRL_INSERT_PARITY_ERR, - CDNS_MCP_CMDCTRL_INSERT_PARITY_ERR); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CMDCTRL, + CDNS_IP_MCP_CMDCTRL_INSERT_PARITY_ERR, + CDNS_IP_MCP_CMDCTRL_INSERT_PARITY_ERR); /* commit changes */ cdns_updatel(cdns, CDNS_MCP_CONFIG_UPDATE, @@ -442,9 +442,9 @@ static int cdns_parity_error_injection(void *data, u64 value) dev_info(cdns->dev, "parity error injection, read: %d\n", ret); /* program hardware to disable parity error */ - cdns_updatel(cdns, CDNS_MCP_CMDCTRL, - CDNS_MCP_CMDCTRL_INSERT_PARITY_ERR, - 0); + cdns_ip_updatel(cdns, CDNS_IP_MCP_CMDCTRL, + CDNS_IP_MCP_CMDCTRL_INSERT_PARITY_ERR, + 0); /* commit changes */ cdns_updatel(cdns, CDNS_MCP_CONFIG_UPDATE, -- GitLab From 83ae1ccba5d0549622634e35d0b3fc3a52d59772 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 14 Mar 2023 09:54:10 +0800 Subject: [PATCH 0535/5631] soundwire: cadence: change access to IP_MCP_CMD_BASE The latest Cadence IP moves MCP_CMD_BASE and MCP_CMD_RESP to the IP_MCP_CMD_BASE and IP_MCP_CMD_RESP registers located in different area and accessed with a fixed offset. Unlike other patches, the fields are not renamed to avoid a very invasive and low-value set of changes. For existing solutions, this is an iso-functionality change. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230314015410.487311-17-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 5128923f051e..39502bc75712 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -129,8 +129,8 @@ MODULE_PARM_DESC(cdns_mcp_int_mask, "Cadence MCP IntMask"); #define CDNS_MCP_FIFOSTAT 0x7C #define CDNS_MCP_RX_FIFO_AVAIL GENMASK(5, 0) -#define CDNS_MCP_CMD_BASE 0x80 -#define CDNS_MCP_RESP_BASE 0x80 +#define CDNS_IP_MCP_CMD_BASE 0x80 /* IP offset added at run-time */ +#define CDNS_IP_MCP_RESP_BASE 0x80 /* IP offset added at run-time */ /* FIFO can hold 8 commands */ #define CDNS_MCP_CMD_LEN 8 #define CDNS_MCP_CMD_WORD_LEN 0x4 @@ -590,10 +590,10 @@ static void cdns_read_response(struct sdw_cdns *cdns) num_resp = ARRAY_SIZE(cdns->response_buf); } - cmd_base = CDNS_MCP_CMD_BASE; + cmd_base = CDNS_IP_MCP_CMD_BASE; for (i = 0; i < num_resp; i++) { - cdns->response_buf[i] = cdns_readl(cdns, cmd_base); + cdns->response_buf[i] = cdns_ip_readl(cdns, cmd_base); cmd_base += CDNS_MCP_CMD_WORD_LEN; } } @@ -612,7 +612,7 @@ _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, cdns->msg_count = count; } - base = CDNS_MCP_CMD_BASE; + base = CDNS_IP_MCP_CMD_BASE; addr = msg->addr + offset; for (i = 0; i < count; i++) { @@ -625,7 +625,7 @@ _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, data |= msg->buf[i + offset]; data |= FIELD_PREP(CDNS_MCP_CMD_SSP_TAG, msg->ssp_sync); - cdns_writel(cdns, base, data); + cdns_ip_writel(cdns, base, data); base += CDNS_MCP_CMD_WORD_LEN; } @@ -673,10 +673,10 @@ cdns_program_scp_addr(struct sdw_cdns *cdns, struct sdw_msg *msg) data[0] |= msg->addr_page1; data[1] |= msg->addr_page2; - base = CDNS_MCP_CMD_BASE; - cdns_writel(cdns, base, data[0]); + base = CDNS_IP_MCP_CMD_BASE; + cdns_ip_writel(cdns, base, data[0]); base += CDNS_MCP_CMD_WORD_LEN; - cdns_writel(cdns, base, data[1]); + cdns_ip_writel(cdns, base, data[1]); time = wait_for_completion_timeout(&cdns->tx_complete, msecs_to_jiffies(CDNS_TX_TIMEOUT)); -- GitLab From d180aa56b50dd243dec89b24d23e0a59c3f0c0eb Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:30 -0700 Subject: [PATCH 0536/5631] perf record: Add BPF event filter support Use --filter option to set BPF filter for generic events other than the tracepoints or Intel PT. The BPF program will check the sample data and filter according to the expression. For example, the below is the typical perf record for frequency mode. The sample period started from 1 and increased gradually. $ sudo ./perf record -e cycles true $ sudo ./perf script perf-exec 2272336 546683.916875: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916892: 1 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916899: 3 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916905: 17 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916911: 100 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916917: 589 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916924: 3470 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) perf-exec 2272336 546683.916930: 20465 cycles: ffffffff828499b8 perf_event_exec+0x298 ([kernel.kallsyms]) true 2272336 546683.916940: 119873 cycles: ffffffff8283afdd perf_iterate_ctx+0x2d ([kernel.kallsyms]) true 2272336 546683.917003: 461349 cycles: ffffffff82892517 vma_interval_tree_insert+0x37 ([kernel.kallsyms]) true 2272336 546683.917237: 635778 cycles: ffffffff82a11400 security_mmap_file+0x20 ([kernel.kallsyms]) When you add a BPF filter to get samples having periods greater than 1000, the output would look like below: $ sudo ./perf record -e cycles --filter 'period > 1000' true $ sudo ./perf script perf-exec 2273949 546850.708501: 5029 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms]) perf-exec 2273949 546850.708508: 32409 cycles: ffffffff826f9e25 finish_wait+0x5 ([kernel.kallsyms]) perf-exec 2273949 546850.708526: 143369 cycles: ffffffff82b4cdbf xas_start+0x5f ([kernel.kallsyms]) perf-exec 2273949 546850.708600: 372650 cycles: ffffffff8286b8f7 __pagevec_lru_add+0x117 ([kernel.kallsyms]) perf-exec 2273949 546850.708791: 482953 cycles: ffffffff829190de __mod_memcg_lruvec_state+0x4e ([kernel.kallsyms]) true 2273949 546850.709036: 501985 cycles: ffffffff828add7c tlb_gather_mmu+0x4c ([kernel.kallsyms]) true 2273949 546850.709292: 503065 cycles: 7f2446d97c03 _dl_map_object_deps+0x973 (/usr/lib/x86_64-linux-gnu/ld-linux-x86-64.so.2) Committer notes: Add stubs for perf_bpf_filter__prepare() and perf_bpf_filter__destroy() to tools/perf/util/python.c to keep it building. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 15 +++++++++++--- tools/perf/util/bpf_counter.c | 3 +-- tools/perf/util/evlist.c | 25 +++++++++++++++++------- tools/perf/util/evsel.c | 2 ++ tools/perf/util/parse-events.c | 8 +++----- tools/perf/util/python.c | 14 +++++++++++++ 6 files changed, 50 insertions(+), 17 deletions(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index ff815c2f67e8..122f71726eaa 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -119,9 +119,12 @@ OPTIONS "perf report" to view group events together. --filter=:: - Event filter. This option should follow an event selector (-e) which - selects either tracepoint event(s) or a hardware trace PMU - (e.g. Intel PT or CoreSight). + Event filter. This option should follow an event selector (-e). + If the event is a tracepoint, the filter string will be parsed by + the kernel. If the event is a hardware trace PMU (e.g. Intel PT + or CoreSight), it'll be processed as an address filter. Otherwise + it means a general filter using BPF which can be applied for any + kind of event. - tracepoint filters @@ -176,6 +179,12 @@ OPTIONS Multiple filters can be separated with space or comma. + - bpf filters + + A BPF filter can access the sample data and make a decision based on the + data. Users need to set an appropriate sample type to use the BPF + filter. + --exclude-perf:: Don't record events issued by perf itself. This option should follow an event selector (-e) which selects tracepoint event(s). It adds a diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index aa78a15a6f0a..1b77436e067e 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -763,8 +763,7 @@ extern struct bpf_counter_ops bperf_cgrp_ops; static inline bool bpf_counter_skip(struct evsel *evsel) { - return list_empty(&evsel->bpf_counter_list) && - evsel->follower_skel == NULL; + return evsel->bpf_counter_ops == NULL; } int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b74e12239aec..cc491a037836 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -31,6 +31,7 @@ #include "util/evlist-hybrid.h" #include "util/pmu.h" #include "util/sample.h" +#include "util/bpf-filter.h" #include #include #include @@ -1086,17 +1087,27 @@ int evlist__apply_filters(struct evlist *evlist, struct evsel **err_evsel) int err = 0; evlist__for_each_entry(evlist, evsel) { - if (evsel->filter == NULL) - continue; - /* * filters only work for tracepoint event, which doesn't have cpu limit. * So evlist and evsel should always be same. */ - err = perf_evsel__apply_filter(&evsel->core, evsel->filter); - if (err) { - *err_evsel = evsel; - break; + if (evsel->filter) { + err = perf_evsel__apply_filter(&evsel->core, evsel->filter); + if (err) { + *err_evsel = evsel; + break; + } + } + + /* + * non-tracepoint events can have BPF filters. + */ + if (!list_empty(&evsel->bpf_filters)) { + err = perf_bpf_filter__prepare(evsel); + if (err) { + *err_evsel = evsel; + break; + } } } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a83d8cd5eb51..dc3faf005c3b 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -50,6 +50,7 @@ #include "off_cpu.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" +#include "util/bpf-filter.h" #include #include #include @@ -1517,6 +1518,7 @@ void evsel__exit(struct evsel *evsel) assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); bpf_counter__destroy(evsel); + perf_bpf_filter__destroy(evsel); evsel__free_counts(evsel); perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 3b2e5bb3e852..6c5cf5244486 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -28,6 +28,7 @@ #include "perf.h" #include "util/parse-events-hybrid.h" #include "util/pmu-hybrid.h" +#include "util/bpf-filter.h" #include "tracepoint.h" #include "thread_map.h" @@ -2542,11 +2543,8 @@ static int set_filter(struct evsel *evsel, const void *arg) perf_pmu__scan_file(pmu, "nr_addr_filters", "%d", &nr_addr_filters); - if (!nr_addr_filters) { - fprintf(stderr, - "This CPU does not support address filtering\n"); - return -1; - } + if (!nr_addr_filters) + return perf_bpf_filter__parse(&evsel->bpf_filters, str); if (evsel__append_addr_filter(evsel, str) < 0) { fprintf(stderr, diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index be336f1b2b68..0faea4c75eed 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -19,6 +19,7 @@ #include "mmap.h" #include "stat.h" #include "metricgroup.h" +#include "util/bpf-filter.h" #include "util/env.h" #include "util/pmu.h" #include @@ -135,6 +136,19 @@ int bpf_counter__disable(struct evsel *evsel __maybe_unused) return 0; } +// not to drag util/bpf-filter.c +#ifdef HAVE_BPF_SKEL +int perf_bpf_filter__prepare(struct evsel *evsel __maybe_unused) +{ + return 0; +} + +int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) +{ + return 0; +} +#endif + /* * Support debug printing even though util/debug.c is not linked. That means * implementing 'verbose' and 'eprintf'. -- GitLab From 27c6f2455b29f27c8daf209ec8bdf0ac2c567b74 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:31 -0700 Subject: [PATCH 0537/5631] perf record: Record dropped sample count When it uses bpf filters, event might drop some samples. It'd be nice if it can report how many samples it lost. As LOST_SAMPLES event can carry the similar information, let's use it for bpf filters. To indicate it's from BPF filters, add a new misc flag for that and do not display cpu load warnings. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/include/perf/event.h | 2 ++ tools/perf/builtin-record.c | 38 ++++++++++++++++++----------- tools/perf/util/bpf-filter.c | 7 ++++++ tools/perf/util/bpf-filter.h | 5 ++++ tools/perf/util/session.c | 3 ++- 5 files changed, 40 insertions(+), 15 deletions(-) diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index ad47d7b31046..51b9338f4c11 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -70,6 +70,8 @@ struct perf_record_lost { __u64 lost; }; +#define PERF_RECORD_MISC_LOST_SAMPLES_BPF (1 << 15) + struct perf_record_lost_samples { struct perf_event_header header; __u64 lost; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 33ebe42b025e..6df8b823859d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -52,6 +52,7 @@ #include "util/pmu-hybrid.h" #include "util/evlist-hybrid.h" #include "util/off_cpu.h" +#include "util/bpf-filter.h" #include "asm/bug.h" #include "perf.h" #include "cputopo.h" @@ -1856,24 +1857,16 @@ record__switch_output(struct record *rec, bool at_exit) return fd; } -static void __record__read_lost_samples(struct record *rec, struct evsel *evsel, +static void __record__save_lost_samples(struct record *rec, struct evsel *evsel, struct perf_record_lost_samples *lost, - int cpu_idx, int thread_idx) + int cpu_idx, int thread_idx, u64 lost_count, + u16 misc_flag) { - struct perf_counts_values count; struct perf_sample_id *sid; struct perf_sample sample = {}; int id_hdr_size; - if (perf_evsel__read(&evsel->core, cpu_idx, thread_idx, &count) < 0) { - pr_debug("read LOST count failed\n"); - return; - } - - if (count.lost == 0) - return; - - lost->lost = count.lost; + lost->lost = lost_count; if (evsel->core.ids) { sid = xyarray__entry(evsel->core.sample_id, cpu_idx, thread_idx); sample.id = sid->id; @@ -1882,6 +1875,7 @@ static void __record__read_lost_samples(struct record *rec, struct evsel *evsel, id_hdr_size = perf_event__synthesize_id_sample((void *)(lost + 1), evsel->core.attr.sample_type, &sample); lost->header.size = sizeof(*lost) + id_hdr_size; + lost->header.misc = misc_flag; record__write(rec, NULL, lost, lost->header.size); } @@ -1905,6 +1899,7 @@ static void record__read_lost_samples(struct record *rec) evlist__for_each_entry(session->evlist, evsel) { struct xyarray *xy = evsel->core.sample_id; + u64 lost_count; if (xy == NULL || evsel->core.fd == NULL) continue; @@ -1916,12 +1911,27 @@ static void record__read_lost_samples(struct record *rec) for (int x = 0; x < xyarray__max_x(xy); x++) { for (int y = 0; y < xyarray__max_y(xy); y++) { - __record__read_lost_samples(rec, evsel, lost, x, y); + struct perf_counts_values count; + + if (perf_evsel__read(&evsel->core, x, y, &count) < 0) { + pr_debug("read LOST count failed\n"); + goto out; + } + + if (count.lost) { + __record__save_lost_samples(rec, evsel, lost, + x, y, count.lost, 0); + } } } + + lost_count = perf_bpf_filter__lost_count(evsel); + if (lost_count) + __record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count, + PERF_RECORD_MISC_LOST_SAMPLES_BPF); } +out: free(lost); - } static volatile sig_atomic_t workload_exec_errno; diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index f20e1bc03778..7bd6f2e41513 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -69,6 +69,13 @@ int perf_bpf_filter__destroy(struct evsel *evsel) return 0; } +u64 perf_bpf_filter__lost_count(struct evsel *evsel) +{ + struct sample_filter_bpf *skel = evsel->bpf_skel; + + return skel ? skel->bss->dropped : 0; +} + struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, enum perf_bpf_filter_op op, unsigned long val) diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index eb8e1ac43cdf..f0c66764c6d0 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -22,6 +22,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); int perf_bpf_filter__prepare(struct evsel *evsel); int perf_bpf_filter__destroy(struct evsel *evsel); +u64 perf_bpf_filter__lost_count(struct evsel *evsel); #else /* !HAVE_BPF_SKEL */ @@ -38,5 +39,9 @@ static inline int perf_bpf_filter__destroy(struct evsel *evsel __maybe_unused) { return -EOPNOTSUPP; } +static inline u64 perf_bpf_filter__lost_count(struct evsel *evsel __maybe_unused) +{ + return 0; +} #endif /* HAVE_BPF_SKEL*/ #endif /* PERF_UTIL_BPF_FILTER_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 749d5b5c135b..7d8d057d1772 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1582,7 +1582,8 @@ static int machines__deliver_event(struct machines *machines, evlist->stats.total_lost += event->lost.lost; return tool->lost(tool, event, sample, machine); case PERF_RECORD_LOST_SAMPLES: - if (tool->lost_samples == perf_event__process_lost_samples) + if (tool->lost_samples == perf_event__process_lost_samples && + !(event->header.misc & PERF_RECORD_MISC_LOST_SAMPLES_BPF)) evlist->stats.total_lost_samples += event->lost_samples.lost; return tool->lost_samples(tool, event, sample, machine); case PERF_RECORD_READ: -- GitLab From 335818470f558de5dc37bbcb31f97b303605a9df Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:32 -0700 Subject: [PATCH 0538/5631] perf bpf filter: Add 'pid' sample data support The pid is special because it's saved in the PERF_SAMPLE_TID together. So it needs to differenciate tid and pid using the 'part' field in the perf bpf filter entry struct. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-filter.c | 4 +++- tools/perf/util/bpf-filter.h | 3 ++- tools/perf/util/bpf-filter.l | 11 ++++++++++- tools/perf/util/bpf-filter.y | 7 +++++-- tools/perf/util/bpf_skel/sample-filter.h | 3 ++- tools/perf/util/bpf_skel/sample_filter.bpf.c | 5 ++++- 6 files changed, 26 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 7bd6f2e41513..743c69fd6cd4 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -36,6 +36,7 @@ int perf_bpf_filter__prepare(struct evsel *evsel) list_for_each_entry(expr, &evsel->bpf_filters, list) { struct perf_bpf_filter_entry entry = { .op = expr->op, + .part = expr->part, .flags = expr->sample_flags, .value = expr->val, }; @@ -76,7 +77,7 @@ u64 perf_bpf_filter__lost_count(struct evsel *evsel) return skel ? skel->bss->dropped : 0; } -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, enum perf_bpf_filter_op op, unsigned long val) { @@ -85,6 +86,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag expr = malloc(sizeof(*expr)); if (expr != NULL) { expr->sample_flags = sample_flags; + expr->part = part; expr->op = op; expr->val = val; } diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index f0c66764c6d0..3f8827bd965f 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -9,6 +9,7 @@ struct perf_bpf_filter_expr { struct list_head list; enum perf_bpf_filter_op op; + int part; unsigned long sample_flags; unsigned long val; }; @@ -16,7 +17,7 @@ struct perf_bpf_filter_expr { struct evsel; #ifdef HAVE_BPF_SKEL -struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, +struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flags, int part, enum perf_bpf_filter_op op, unsigned long val); int perf_bpf_filter__parse(struct list_head *expr_head, const char *str); diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index f6c0b74ea285..ec12fc4d2ab8 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -11,7 +11,15 @@ static int sample(unsigned long sample_flag) { - perf_bpf_filter_lval.sample = sample_flag; + perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.part = 0; + return BFT_SAMPLE; +} + +static int sample_part(unsigned long sample_flag, int part) +{ + perf_bpf_filter_lval.sample.type = sample_flag; + perf_bpf_filter_lval.sample.part = part; return BFT_SAMPLE; } @@ -56,6 +64,7 @@ ident [_a-zA-Z][_a-zA-Z0-9]+ ip { return sample(PERF_SAMPLE_IP); } id { return sample(PERF_SAMPLE_ID); } tid { return sample(PERF_SAMPLE_TID); } +pid { return sample_part(PERF_SAMPLE_TID, 1); } cpu { return sample(PERF_SAMPLE_CPU); } time { return sample(PERF_SAMPLE_TIME); } addr { return sample(PERF_SAMPLE_ADDR); } diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 13eca612ecca..0ca6532afd8d 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -20,7 +20,10 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, %union { unsigned long num; - unsigned long sample; + struct { + unsigned long type; + int part; + } sample; enum perf_bpf_filter_op op; struct perf_bpf_filter_expr *expr; } @@ -48,7 +51,7 @@ filter_term filter_term: BFT_SAMPLE BFT_OP BFT_NUM { - $$ = perf_bpf_filter_expr__new($1, $2, $3); + $$ = perf_bpf_filter_expr__new($1.type, $1.part, $2, $3); } %% diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 862060bfda14..6b9fd554ad7b 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -17,7 +17,8 @@ enum perf_bpf_filter_op { /* BPF map entry for filtering */ struct perf_bpf_filter_entry { enum perf_bpf_filter_op op; - __u64 flags; + __u32 part; /* sub-sample type info when it has multiple values */ + __u64 flags; /* perf sample type flags */ __u64 value; }; diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index c07256279c3e..dddf38c27bb7 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -40,7 +40,10 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, case PERF_SAMPLE_ID: return kctx->data->id; case PERF_SAMPLE_TID: - return kctx->data->tid_entry.tid; + if (entry->part) + return kctx->data->tid_entry.pid; + else + return kctx->data->tid_entry.tid; case PERF_SAMPLE_CPU: return kctx->data->cpu_entry.cpu; case PERF_SAMPLE_TIME: -- GitLab From 409bcd806749f23852581f54736a6206d1601248 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:33 -0700 Subject: [PATCH 0539/5631] perf bpf filter: Add more weight sample data support The weight data consists of a couple of fields with the PERF_SAMPLE_WEIGHT_STRUCT. Add weight{1,2,3} term to select them separately. Also add their aliases like 'ins_lat', 'p_stage_cyc' and 'retire_lat'. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-filter.l | 6 ++++++ tools/perf/util/bpf_skel/sample_filter.bpf.c | 8 ++++++++ 2 files changed, 14 insertions(+) diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index ec12fc4d2ab8..419f923b35c0 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -71,6 +71,12 @@ addr { return sample(PERF_SAMPLE_ADDR); } period { return sample(PERF_SAMPLE_PERIOD); } txn { return sample(PERF_SAMPLE_TRANSACTION); } weight { return sample(PERF_SAMPLE_WEIGHT); } +weight1 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 1); } +weight2 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 2); } +weight3 { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } +ins_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 2); } /* alias for weight2 */ +p_stage_cyc { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for weight3 */ +retire_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for weight3 */ phys_addr { return sample(PERF_SAMPLE_PHYS_ADDR); } code_pgsz { return sample(PERF_SAMPLE_CODE_PAGE_SIZE); } data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); } diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index dddf38c27bb7..d930401c5bfc 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -54,6 +54,14 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, return kctx->data->period; case PERF_SAMPLE_TRANSACTION: return kctx->data->txn; + case PERF_SAMPLE_WEIGHT_STRUCT: + if (entry->part == 1) + return kctx->data->weight.var1_dw; + if (entry->part == 2) + return kctx->data->weight.var2_w; + if (entry->part == 3) + return kctx->data->weight.var3_w; + /* fall through */ case PERF_SAMPLE_WEIGHT: return kctx->data->weight.full; case PERF_SAMPLE_PHYS_ADDR: -- GitLab From ff612055fb79e24c75f682f5b0e30cfc370ee59d Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:34 -0700 Subject: [PATCH 0540/5631] perf bpf filter: Add data_src sample data support The data_src has many entries to express memory behaviors. Add each term separately so that users can combine them for their purpose. I didn't add prefix for the constants for simplicity as they are mostly distinguishable but I had to use l1_miss and l2_hit for mem_dtlb since mem_lvl has different values for the same names. Note that I decided mem_lvl to be used as an alias of mem_lvlnum as it's deprecated now. According to the comment in the UAPI header, users should use the mix of mem_lvlnum, mem_remote and mem_snoop. Also the SNOOPX bits are concatenated to mem_snoop for simplicity. The following terms are used for data_src and the corresponding perf sample data fields: * mem_op : { load, store, pfetch, exec } * mem_lvl: { l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem } * mem_snoop: { none, hit, miss, hitm, fwd, peer } * mem_remote: { remote } * mem_lock: { locked } * mem_dtlb { l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault } * mem_blk { by_data, by_addr } * mem_hops { hops0, hops1, hops2, hops3 } We can now use a filter expression like below: 'mem_op == load, mem_lvl <= l2, mem_dtlb == l1_hit' 'mem_dtlb == l2_miss, mem_hops > hops1' 'mem_lvl == ram, mem_remote == 1' Note that 'na' is shared among the terms as it has the same value except for mem_lvl. I don't have a good idea to handle that for now. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-filter.l | 61 ++++++++++++++++++++ tools/perf/util/bpf_skel/sample_filter.bpf.c | 23 ++++++++ 2 files changed, 84 insertions(+) diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index 419f923b35c0..3e66b7a0215e 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -42,6 +42,12 @@ static int value(int base) return BFT_NUM; } +static int constant(int val) +{ + perf_bpf_filter_lval.num = val; + return BFT_NUM; +} + static int error(const char *str) { printf("perf_bpf_filter: Unexpected filter %s: %s\n", str, perf_bpf_filter_text); @@ -80,6 +86,15 @@ retire_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for we phys_addr { return sample(PERF_SAMPLE_PHYS_ADDR); } code_pgsz { return sample(PERF_SAMPLE_CODE_PAGE_SIZE); } data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); } +mem_op { return sample_part(PERF_SAMPLE_DATA_SRC, 1); } +mem_lvlnum { return sample_part(PERF_SAMPLE_DATA_SRC, 2); } +mem_lvl { return sample_part(PERF_SAMPLE_DATA_SRC, 2); } /* alias for mem_lvlnum */ +mem_snoop { return sample_part(PERF_SAMPLE_DATA_SRC, 3); } /* include snoopx */ +mem_remote { return sample_part(PERF_SAMPLE_DATA_SRC, 4); } +mem_lock { return sample_part(PERF_SAMPLE_DATA_SRC, 5); } +mem_dtlb { return sample_part(PERF_SAMPLE_DATA_SRC, 6); } +mem_blk { return sample_part(PERF_SAMPLE_DATA_SRC, 7); } +mem_hops { return sample_part(PERF_SAMPLE_DATA_SRC, 8); } "==" { return operator(PBF_OP_EQ); } "!=" { return operator(PBF_OP_NEQ); } @@ -89,6 +104,52 @@ data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); } "<=" { return operator(PBF_OP_LE); } "&" { return operator(PBF_OP_AND); } +na { return constant(PERF_MEM_OP_NA); } +load { return constant(PERF_MEM_OP_LOAD); } +store { return constant(PERF_MEM_OP_STORE); } +pfetch { return constant(PERF_MEM_OP_PFETCH); } +exec { return constant(PERF_MEM_OP_EXEC); } + +l1 { return constant(PERF_MEM_LVLNUM_L1); } +l2 { return constant(PERF_MEM_LVLNUM_L2); } +l3 { return constant(PERF_MEM_LVLNUM_L3); } +l4 { return constant(PERF_MEM_LVLNUM_L4); } +cxl { return constant(PERF_MEM_LVLNUM_CXL); } +io { return constant(PERF_MEM_LVLNUM_IO); } +any_cache { return constant(PERF_MEM_LVLNUM_ANY_CACHE); } +lfb { return constant(PERF_MEM_LVLNUM_LFB); } +ram { return constant(PERF_MEM_LVLNUM_RAM); } +pmem { return constant(PERF_MEM_LVLNUM_PMEM); } + +none { return constant(PERF_MEM_SNOOP_NONE); } +hit { return constant(PERF_MEM_SNOOP_HIT); } +miss { return constant(PERF_MEM_SNOOP_MISS); } +hitm { return constant(PERF_MEM_SNOOP_HITM); } +fwd { return constant(PERF_MEM_SNOOPX_FWD); } +peer { return constant(PERF_MEM_SNOOPX_PEER); } + +remote { return constant(PERF_MEM_REMOTE_REMOTE); } + +locked { return constant(PERF_MEM_LOCK_LOCKED); } + +l1_hit { return constant(PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT); } +l1_miss { return constant(PERF_MEM_TLB_L1 | PERF_MEM_TLB_MISS); } +l2_hit { return constant(PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT); } +l2_miss { return constant(PERF_MEM_TLB_L2 | PERF_MEM_TLB_MISS); } +any_hit { return constant(PERF_MEM_TLB_HIT); } +any_miss { return constant(PERF_MEM_TLB_MISS); } +walk { return constant(PERF_MEM_TLB_WK); } +os { return constant(PERF_MEM_TLB_OS); } +fault { return constant(PERF_MEM_TLB_OS); } /* alias for os */ + +by_data { return constant(PERF_MEM_BLK_DATA); } +by_addr { return constant(PERF_MEM_BLK_ADDR); } + +hops0 { return constant(PERF_MEM_HOPS_0); } +hops1 { return constant(PERF_MEM_HOPS_1); } +hops2 { return constant(PERF_MEM_HOPS_2); } +hops3 { return constant(PERF_MEM_HOPS_3); } + "," { return ','; } {ident} { return error("ident"); } diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index d930401c5bfc..88dbc788d257 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -70,6 +70,29 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, return kctx->data->code_page_size; case PERF_SAMPLE_DATA_PAGE_SIZE: return kctx->data->data_page_size; + case PERF_SAMPLE_DATA_SRC: + if (entry->part == 1) + return kctx->data->data_src.mem_op; + if (entry->part == 2) + return kctx->data->data_src.mem_lvl_num; + if (entry->part == 3) { + __u32 snoop = kctx->data->data_src.mem_snoop; + __u32 snoopx = kctx->data->data_src.mem_snoopx; + + return (snoopx << 5) | snoop; + } + if (entry->part == 4) + return kctx->data->data_src.mem_remote; + if (entry->part == 5) + return kctx->data->data_src.mem_lock; + if (entry->part == 6) + return kctx->data->data_src.mem_dtlb; + if (entry->part == 7) + return kctx->data->data_src.mem_blk; + if (entry->part == 8) + return kctx->data->data_src.mem_hops; + /* return the whole word */ + return kctx->data->data_src.val; default: break; } -- GitLab From 46996dd7f655889a3dbbb514a0fa8bb614d6bd74 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:35 -0700 Subject: [PATCH 0541/5631] perf bpf filter: Add logical OR operator It supports two or more expressions connected as a group and the group result is considered true when one of them returns true. The new group operators (GROUP_BEGIN and GROUP_END) are added to setup and check the condition. As it doesn't allow nested groups, the condition is saved in local variables. For example, the following is to get samples only if the data source memory level is L2 cache or the weight value is greater than 30. $ sudo ./perf record -adW -e cpu/mem-loads/pp \ > --filter 'mem_lvl == l2 || weight > 30' -- sleep 1 $ sudo ./perf script -F data_src,weight 10668100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 47 11868100242 |OP LOAD|LVL LFB/MAB or LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 57 10668100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 56 10650100842 |OP LOAD|LVL L3 or L3 hit|SNP None|TLB L2 miss|LCK No|BLK N/A 144 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 16 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 20 11868100242 |OP LOAD|LVL LFB/MAB or LFB/MAB hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 189 1026a100142 |OP LOAD|LVL L1 or L1 hit|SNP None|TLB L1 or L2 hit|LCK Yes|BLK N/A 193 10468100442 |OP LOAD|LVL L2 or L2 hit|SNP None|TLB L1 or L2 hit|LCK No|BLK N/A 18 ... Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf-filter.c | 25 +++++++++++++ tools/perf/util/bpf-filter.h | 1 + tools/perf/util/bpf-filter.l | 1 + tools/perf/util/bpf-filter.y | 25 +++++++++++-- tools/perf/util/bpf_skel/sample-filter.h | 6 ++-- tools/perf/util/bpf_skel/sample_filter.bpf.c | 38 +++++++++++++------- 6 files changed, 79 insertions(+), 17 deletions(-) diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index 743c69fd6cd4..bd638737e12f 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -42,8 +42,32 @@ int perf_bpf_filter__prepare(struct evsel *evsel) }; bpf_map_update_elem(fd, &i, &entry, BPF_ANY); i++; + + if (expr->op == PBF_OP_GROUP_BEGIN) { + struct perf_bpf_filter_expr *group; + + list_for_each_entry(group, &expr->groups, list) { + struct perf_bpf_filter_entry group_entry = { + .op = group->op, + .part = group->part, + .flags = group->sample_flags, + .value = group->val, + }; + bpf_map_update_elem(fd, &i, &group_entry, BPF_ANY); + i++; + } + + memset(&entry, 0, sizeof(entry)); + entry.op = PBF_OP_GROUP_END; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); + i++; + } } + if (i > MAX_FILTERS) { + pr_err("Too many filters: %d (max = %d)\n", i, MAX_FILTERS); + return -1; + } prog = skel->progs.perf_sample_filter; for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) { for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) { @@ -89,6 +113,7 @@ struct perf_bpf_filter_expr *perf_bpf_filter_expr__new(unsigned long sample_flag expr->part = part; expr->op = op; expr->val = val; + INIT_LIST_HEAD(&expr->groups); } return expr; } diff --git a/tools/perf/util/bpf-filter.h b/tools/perf/util/bpf-filter.h index 3f8827bd965f..7afd159411b8 100644 --- a/tools/perf/util/bpf-filter.h +++ b/tools/perf/util/bpf-filter.h @@ -8,6 +8,7 @@ struct perf_bpf_filter_expr { struct list_head list; + struct list_head groups; enum perf_bpf_filter_op op; int part; unsigned long sample_flags; diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l index 3e66b7a0215e..d4ff0f1345cd 100644 --- a/tools/perf/util/bpf-filter.l +++ b/tools/perf/util/bpf-filter.l @@ -151,6 +151,7 @@ hops2 { return constant(PERF_MEM_HOPS_2); } hops3 { return constant(PERF_MEM_HOPS_3); } "," { return ','; } +"||" { return BFT_LOGICAL_OR; } {ident} { return error("ident"); } . { return error("input"); } diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 0ca6532afd8d..07d6c7926c13 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -28,8 +28,8 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused, struct perf_bpf_filter_expr *expr; } -%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM -%type filter_term +%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM BFT_LOGICAL_OR +%type filter_term filter_expr %destructor { free ($$); } %type BFT_SAMPLE %type BFT_OP @@ -49,6 +49,27 @@ filter_term } filter_term: +filter_term BFT_LOGICAL_OR filter_expr +{ + struct perf_bpf_filter_expr *expr; + + if ($1->op == PBF_OP_GROUP_BEGIN) { + expr = $1; + } else { + expr = perf_bpf_filter_expr__new(0, 0, PBF_OP_GROUP_BEGIN, 1); + list_add_tail(&$1->list, &expr->groups); + } + expr->val++; + list_add_tail(&$3->list, &expr->groups); + $$ = expr; +} +| +filter_expr +{ + $$ = $1; +} + +filter_expr: BFT_SAMPLE BFT_OP BFT_NUM { $$ = perf_bpf_filter_expr__new($1.type, $1.part, $2, $3); diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h index 6b9fd554ad7b..2e96e1ab084a 100644 --- a/tools/perf/util/bpf_skel/sample-filter.h +++ b/tools/perf/util/bpf_skel/sample-filter.h @@ -1,7 +1,7 @@ #ifndef PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H #define PERF_UTIL_BPF_SKEL_SAMPLE_FILTER_H -#define MAX_FILTERS 32 +#define MAX_FILTERS 64 /* supported filter operations */ enum perf_bpf_filter_op { @@ -11,7 +11,9 @@ enum perf_bpf_filter_op { PBF_OP_GE, PBF_OP_LT, PBF_OP_LE, - PBF_OP_AND + PBF_OP_AND, + PBF_OP_GROUP_BEGIN, + PBF_OP_GROUP_END, }; /* BPF map entry for filtering */ diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index 88dbc788d257..57e3c67d6d37 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -99,6 +99,14 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, return 0; } +#define CHECK_RESULT(data, op, val) \ + if (!(data op val)) { \ + if (!in_group) \ + goto drop; \ + } else if (in_group) { \ + group_result = 1; \ + } + /* BPF program to be called from perf event overflow handler */ SEC("perf_event") int perf_sample_filter(void *ctx) @@ -106,6 +114,8 @@ int perf_sample_filter(void *ctx) struct bpf_perf_event_data_kern *kctx; struct perf_bpf_filter_entry *entry; __u64 sample_data; + int in_group = 0; + int group_result = 0; int i; kctx = bpf_cast_to_kern_ctx(ctx); @@ -120,32 +130,34 @@ int perf_sample_filter(void *ctx) switch (entry->op) { case PBF_OP_EQ: - if (!(sample_data == entry->value)) - goto drop; + CHECK_RESULT(sample_data, ==, entry->value) break; case PBF_OP_NEQ: - if (!(sample_data != entry->value)) - goto drop; + CHECK_RESULT(sample_data, !=, entry->value) break; case PBF_OP_GT: - if (!(sample_data > entry->value)) - goto drop; + CHECK_RESULT(sample_data, >, entry->value) break; case PBF_OP_GE: - if (!(sample_data >= entry->value)) - goto drop; + CHECK_RESULT(sample_data, >=, entry->value) break; case PBF_OP_LT: - if (!(sample_data < entry->value)) - goto drop; + CHECK_RESULT(sample_data, <, entry->value) break; case PBF_OP_LE: - if (!(sample_data <= entry->value)) - goto drop; + CHECK_RESULT(sample_data, <=, entry->value) break; case PBF_OP_AND: - if (!(sample_data & entry->value)) + CHECK_RESULT(sample_data, &, entry->value) + break; + case PBF_OP_GROUP_BEGIN: + in_group = 1; + group_result = 0; + break; + case PBF_OP_GROUP_END: + if (group_result == 0) goto drop; + in_group = 0; break; } } -- GitLab From 4310551b76e0d6762abb78fc23d50dcc3c608c33 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:36 -0700 Subject: [PATCH 0542/5631] perf bpf filter: Show warning for missing sample flags For a BPF filter to work properly, users need to provide appropriate options to enable the sample types. Otherwise the BPF program would see an invalid value (i.e. always 0) and filter won't work well. Show a warning message if sample types are missing like below. $ sudo ./perf record -e cycles --filter 'addr < 100' true Error: cycles event does not have PERF_SAMPLE_ADDR Hint: please add -d option to perf record. failed to set filter "BPF" on event cycles with 22 (Invalid argument) Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 2 +- tools/perf/util/bpf-filter.c | 62 ++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 6df8b823859d..7b7e74a56346 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -1353,7 +1353,7 @@ static int record__open(struct record *rec) if (evlist__apply_filters(evlist, &pos)) { pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n", - pos->filter, evsel__name(pos), errno, + pos->filter ?: "BPF", evsel__name(pos), errno, str_error_r(errno, msg, sizeof(msg))); rc = -1; goto out; diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c index bd638737e12f..0b30688d78a7 100644 --- a/tools/perf/util/bpf-filter.c +++ b/tools/perf/util/bpf-filter.c @@ -17,6 +17,64 @@ #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) +#define __PERF_SAMPLE_TYPE(st, opt) { st, #st, opt } +#define PERF_SAMPLE_TYPE(_st, opt) __PERF_SAMPLE_TYPE(PERF_SAMPLE_##_st, opt) + +static const struct perf_sample_info { + u64 type; + const char *name; + const char *option; +} sample_table[] = { + /* default sample flags */ + PERF_SAMPLE_TYPE(IP, NULL), + PERF_SAMPLE_TYPE(TID, NULL), + PERF_SAMPLE_TYPE(PERIOD, NULL), + /* flags mostly set by default, but still have options */ + PERF_SAMPLE_TYPE(ID, "--sample-identifier"), + PERF_SAMPLE_TYPE(CPU, "--sample-cpu"), + PERF_SAMPLE_TYPE(TIME, "-T"), + /* optional sample flags */ + PERF_SAMPLE_TYPE(ADDR, "-d"), + PERF_SAMPLE_TYPE(DATA_SRC, "-d"), + PERF_SAMPLE_TYPE(PHYS_ADDR, "--phys-data"), + PERF_SAMPLE_TYPE(WEIGHT, "-W"), + PERF_SAMPLE_TYPE(WEIGHT_STRUCT, "-W"), + PERF_SAMPLE_TYPE(TRANSACTION, "--transaction"), + PERF_SAMPLE_TYPE(CODE_PAGE_SIZE, "--code-page-size"), + PERF_SAMPLE_TYPE(DATA_PAGE_SIZE, "--data-page-size"), +}; + +static const struct perf_sample_info *get_sample_info(u64 flags) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(sample_table); i++) { + if (sample_table[i].type == flags) + return &sample_table[i]; + } + return NULL; +} + +static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr *expr) +{ + const struct perf_sample_info *info; + + if (evsel->core.attr.sample_type & expr->sample_flags) + return 0; + + info = get_sample_info(expr->sample_flags); + if (info == NULL) { + pr_err("Error: %s event does not have sample flags %lx\n", + evsel__name(evsel), expr->sample_flags); + return -1; + } + + pr_err("Error: %s event does not have %s\n", evsel__name(evsel), info->name); + if (info->option) + pr_err(" Hint: please add %s option to perf record\n", info->option); + return -1; +} + int perf_bpf_filter__prepare(struct evsel *evsel) { int i, x, y, fd; @@ -40,6 +98,10 @@ int perf_bpf_filter__prepare(struct evsel *evsel) .flags = expr->sample_flags, .value = expr->val, }; + + if (check_sample_flags(evsel, expr) < 0) + return -1; + bpf_map_update_elem(fd, &i, &entry, BPF_ANY); i++; -- GitLab From c46bf3bd00167e09729f884dd479b0a8d1a63f95 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 14 Mar 2023 16:42:37 -0700 Subject: [PATCH 0543/5631] perf record: Update documentation for BPF filters Add more description and examples. Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Andi Kleen Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Song Liu Cc: Stephane Eranian Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230314234237.3008956-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 47 +++++++++++++++++++++++- 1 file changed, 46 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 122f71726eaa..680396c56bd1 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -183,7 +183,52 @@ OPTIONS A BPF filter can access the sample data and make a decision based on the data. Users need to set an appropriate sample type to use the BPF - filter. + filter. BPF filters need root privilege. + + The sample data field can be specified in lower case letter. Multiple + filters can be separated with comma. For example, + + --filter 'period > 1000, cpu == 1' + or + --filter 'mem_op == load || mem_op == store, mem_lvl > l1' + + The former filter only accept samples with period greater than 1000 AND + CPU number is 1. The latter one accepts either load and store memory + operations but it should have memory level above the L1. Since the + mem_op and mem_lvl fields come from the (memory) data_source, it'd only + work with some events which set the data_source field. + + Also user should request to collect that information (with -d option in + the above case). Otherwise, the following message will be shown. + + $ sudo perf record -e cycles --filter 'mem_op == load' + Error: cycles event does not have PERF_SAMPLE_DATA_SRC + Hint: please add -d option to perf record. + failed to set filter "BPF" on event cycles with 22 (Invalid argument) + + Essentially the BPF filter expression is: + + (("," | "||") )* + + The can be one of: + ip, id, tid, pid, cpu, time, addr, period, txn, weight, phys_addr, + code_pgsz, data_pgsz, weight1, weight2, weight3, ins_lat, retire_lat, + p_stage_cyc, mem_op, mem_lvl, mem_snoop, mem_remote, mem_lock, + mem_dtlb, mem_blk, mem_hops + + The can be one of: + ==, !=, >, >=, <, <=, & + + The can be one of: + (for any term) + na, load, store, pfetch, exec (for mem_op) + l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl) + na, none, hit, miss, hitm, fwd, peer (for mem_snoop) + remote (for mem_remote) + na, locked (for mem_locked) + na, l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault (for mem_dtlb) + na, by_data, by_addr (for mem_blk) + hops0, hops1, hops2, hops3 (for mem_hops) --exclude-perf:: Don't record events issued by perf itself. This option should follow -- GitLab From 9c3aa1f41178d75c7eabfa818bc02b698b5f152e Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:50:57 +0800 Subject: [PATCH 0544/5631] perf kvm: Refactor overall statistics Currently the tool computes overall statistics when sort the results. This patch refactors overall statistics during events processing, therefore, the function update_total_coun() is not needed anymore, an extra benefit is we can de-couple code between the statistics and the sorting. This patch is not expected any functionality changes. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 641e739c717c..0172e5b0d26e 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -278,9 +278,14 @@ static double kvm_event_rel_stddev(int vcpu_id, struct kvm_event *event) avg_stats(&kvm_stats->stats)); } -static bool update_kvm_event(struct kvm_event *event, int vcpu_id, +static bool update_kvm_event(struct perf_kvm_stat *kvm, + struct kvm_event *event, int vcpu_id, u64 time_diff) { + /* Update overall statistics */ + kvm->total_count++; + kvm->total_time += time_diff; + if (vcpu_id == -1) { kvm_update_event_stats(&event->total, time_diff); return true; @@ -399,7 +404,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, } } - return update_kvm_event(event, vcpu, time_diff); + return update_kvm_event(kvm, event, vcpu, time_diff); } static @@ -526,15 +531,6 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event, rb_insert_color(&event->rb, result); } -static void -update_total_count(struct perf_kvm_stat *kvm, struct kvm_event *event) -{ - int vcpu = kvm->trace_vcpu; - - kvm->total_count += get_event_count(event, vcpu); - kvm->total_time += get_event_time(event, vcpu); -} - static bool event_is_valid(struct kvm_event *event, int vcpu) { return !!get_event_count(event, vcpu); @@ -549,7 +545,6 @@ static void sort_result(struct perf_kvm_stat *kvm) for (i = 0; i < EVENTS_CACHE_SIZE; i++) { list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) { if (event_is_valid(event, vcpu)) { - update_total_count(kvm, event); insert_to_result(&kvm->result, event, kvm->compare, vcpu); } -- GitLab From a7d451a8733c978848ede58333be25b10889df82 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:50:58 +0800 Subject: [PATCH 0545/5631] perf kvm: Add pointer to 'perf_kvm_stat' in kvm event Sometimes, handling kvm events needs to base on global variables, e.g. when read event counts we need to know the target vcpu ID; the global variables are stored in structure perf_kvm_stat. This patch adds add a 'perf_kvm_stat' pointer in kvm event structure, it is to be used by later refactoring. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 6 ++++-- tools/perf/util/kvm-stat.h | 5 +++-- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 0172e5b0d26e..3d2560ec6b37 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -209,7 +209,8 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) return true; } -static struct kvm_event *kvm_alloc_init_event(struct event_key *key) +static struct kvm_event *kvm_alloc_init_event(struct perf_kvm_stat *kvm, + struct event_key *key) { struct kvm_event *event; @@ -219,6 +220,7 @@ static struct kvm_event *kvm_alloc_init_event(struct event_key *key) return NULL; } + event->perf_kvm = kvm; event->key = *key; init_stats(&event->total.stats); return event; @@ -238,7 +240,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, return event; } - event = kvm_alloc_init_event(key); + event = kvm_alloc_init_event(kvm, key); if (!event) return NULL; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 6f0fa05b62b6..40a4b66cfee6 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -24,10 +24,13 @@ struct kvm_event_stats { struct stats stats; }; +struct perf_kvm_stat; + struct kvm_event { struct list_head hash_entry; struct rb_node rb; + struct perf_kvm_stat *perf_kvm; struct event_key key; struct kvm_event_stats total; @@ -44,8 +47,6 @@ struct kvm_event_key { key_cmp_fun key; }; -struct perf_kvm_stat; - struct child_event_ops { void (*get_key)(struct evsel *evsel, struct perf_sample *sample, -- GitLab From f098376d16e94a0a14bd16264f28c72ee3b411c9 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:50:59 +0800 Subject: [PATCH 0546/5631] perf kvm: Move up metrics helpers This patch moves up the helper functions of event's metrics for later adding code to call them. No any functionality changes, but has a function renaming from compare_kvm_event_{metric}() to cmp_event_{metric}(). Committer notes: Those helper functions are only used if this is true: if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) So keep them enclosed with that. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 74 +++++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 36 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 3d2560ec6b37..c11f5454f35c 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -49,6 +49,44 @@ #include #include +#if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) +#define GET_EVENT_KEY(func, field) \ +static u64 get_event_ ##func(struct kvm_event *event, int vcpu) \ +{ \ + if (vcpu == -1) \ + return event->total.field; \ + \ + if (vcpu >= event->max_vcpu) \ + return 0; \ + \ + return event->vcpu[vcpu].field; \ +} + +#define COMPARE_EVENT_KEY(func, field) \ +GET_EVENT_KEY(func, field) \ +static int cmp_event_ ## func(struct kvm_event *one, \ + struct kvm_event *two, int vcpu) \ +{ \ + return get_event_ ##func(one, vcpu) > \ + get_event_ ##func(two, vcpu); \ +} + +GET_EVENT_KEY(time, time); +GET_EVENT_KEY(max, stats.max); +GET_EVENT_KEY(min, stats.min); +COMPARE_EVENT_KEY(count, stats.n); +COMPARE_EVENT_KEY(mean, stats.mean); + +#define DEF_SORT_NAME_KEY(name, compare_key) \ + { #name, cmp_event_ ## compare_key } + +static struct kvm_event_key keys[] = { + DEF_SORT_NAME_KEY(sample, count), + DEF_SORT_NAME_KEY(time, mean), + { NULL, NULL } +}; +#endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) + static const char *get_filename_for_perf_kvm(void) { const char *filename; @@ -461,42 +499,6 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, return true; } -#define GET_EVENT_KEY(func, field) \ -static u64 get_event_ ##func(struct kvm_event *event, int vcpu) \ -{ \ - if (vcpu == -1) \ - return event->total.field; \ - \ - if (vcpu >= event->max_vcpu) \ - return 0; \ - \ - return event->vcpu[vcpu].field; \ -} - -#define COMPARE_EVENT_KEY(func, field) \ -GET_EVENT_KEY(func, field) \ -static int compare_kvm_event_ ## func(struct kvm_event *one, \ - struct kvm_event *two, int vcpu)\ -{ \ - return get_event_ ##func(one, vcpu) > \ - get_event_ ##func(two, vcpu); \ -} - -GET_EVENT_KEY(time, time); -COMPARE_EVENT_KEY(count, stats.n); -COMPARE_EVENT_KEY(mean, stats.mean); -GET_EVENT_KEY(max, stats.max); -GET_EVENT_KEY(min, stats.min); - -#define DEF_SORT_NAME_KEY(name, compare_key) \ - { #name, compare_kvm_event_ ## compare_key } - -static struct kvm_event_key keys[] = { - DEF_SORT_NAME_KEY(sample, count), - DEF_SORT_NAME_KEY(time, mean), - { NULL, NULL } -}; - static bool select_key(struct perf_kvm_stat *kvm) { int i; -- GitLab From dd787ae4e8548a82350981b4b0046df6a92999f2 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:00 +0800 Subject: [PATCH 0547/5631] perf kvm: Use subtraction for comparison metrics Currently the metrics comparison uses greater operator (>), it returns the boolean value (0 or 1). This patch changes to use subtraction as comparison result, which can be used by histograms sorting. Since the subtraction result is u64 type, we change key_cmp_fun's return type to int64_t to avoid overflow. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 6 +++--- tools/perf/util/kvm-stat.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index c11f5454f35c..fbdd46d38c13 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -64,10 +64,10 @@ static u64 get_event_ ##func(struct kvm_event *event, int vcpu) \ #define COMPARE_EVENT_KEY(func, field) \ GET_EVENT_KEY(func, field) \ -static int cmp_event_ ## func(struct kvm_event *one, \ +static int64_t cmp_event_ ## func(struct kvm_event *one, \ struct kvm_event *two, int vcpu) \ { \ - return get_event_ ##func(one, vcpu) > \ + return get_event_ ##func(one, vcpu) - \ get_event_ ##func(two, vcpu); \ } @@ -525,7 +525,7 @@ static void insert_to_result(struct rb_root *result, struct kvm_event *event, p = container_of(*rb, struct kvm_event, rb); parent = *rb; - if (bigger(event, p, vcpu)) + if (bigger(event, p, vcpu) > 0) rb = &(*rb)->rb_left; else rb = &(*rb)->rb_right; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 40a4b66cfee6..0c2400d9b227 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -40,7 +40,7 @@ struct kvm_event { struct kvm_event_stats *vcpu; }; -typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); +typedef int64_t (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); struct kvm_event_key { const char *name; -- GitLab From 2d31e0bff2f3dd5369a9b45e3d8c9ee325784e60 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:01 +0800 Subject: [PATCH 0548/5631] perf kvm: Use macro to replace variable 'decode_str_len' The variable 'decode_str_len' defines the string length for KVM event name and every arch defines its own values. This introduces complexity that the variable definition are spreading in multiple source files under arch folder. This patch refactors code to use a macro KVM_EVENT_NAME_LEN to define event name length and thus remove the definitions in arch files. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/kvm-stat.c | 1 - tools/perf/arch/powerpc/util/kvm-stat.c | 3 +-- tools/perf/arch/s390/util/kvm-stat.c | 1 - tools/perf/arch/x86/util/kvm-stat.c | 7 +++---- tools/perf/builtin-kvm.c | 10 +++++----- tools/perf/util/kvm-stat.h | 3 ++- 6 files changed, 11 insertions(+), 14 deletions(-) diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 73d18e0ed6f6..72ca9bb45804 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -11,7 +11,6 @@ define_exit_reasons_table(arm64_trap_exit_reasons, kvm_arm_exception_class); const char *kvm_trap_exit_reason = "esr_ec"; const char *vcpu_id_str = "id"; -const int decode_str_len = 20; const char *kvm_exit_reason = "ret"; const char *kvm_entry_trace = "kvm:kvm_entry"; const char *kvm_exit_trace = "kvm:kvm_exit"; diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index 1a9b40ea92a5..d04a08c9fd19 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -14,7 +14,6 @@ #define NR_TPS 4 const char *vcpu_id_str = "vcpu_id"; -const int decode_str_len = 40; const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter"; const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit"; @@ -80,7 +79,7 @@ static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, { const char *hcall_reason = get_hcall_exit_reason(key->key); - scnprintf(decode, decode_str_len, "%s", hcall_reason); + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", hcall_reason); } static struct kvm_events_ops hcall_events = { diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c index 34da89ced29a..0aed92df51ba 100644 --- a/tools/perf/arch/s390/util/kvm-stat.c +++ b/tools/perf/arch/s390/util/kvm-stat.c @@ -19,7 +19,6 @@ define_exit_reasons_table(sie_diagnose_codes, diagnose_codes); define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes); const char *vcpu_id_str = "id"; -const int decode_str_len = 40; const char *kvm_exit_reason = "icptcode"; const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter"; const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit"; diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index c5dd54f6ef5e..ef513def03ba 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -18,7 +18,6 @@ static struct kvm_events_ops exit_events = { }; const char *vcpu_id_str = "vcpu_id"; -const int decode_str_len = 20; const char *kvm_exit_reason = "exit_reason"; const char *kvm_entry_trace = "kvm:kvm_entry"; const char *kvm_exit_trace = "kvm:kvm_exit"; @@ -77,7 +76,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, decode_str_len, "%#lx:%s", + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#lx:%s", (unsigned long)key->key, key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R"); } @@ -121,7 +120,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, decode_str_len, "%#llx:%s", + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#llx:%s", (unsigned long long)key->key, key->info ? "POUT" : "PIN"); } @@ -165,7 +164,7 @@ static void msr_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused, struct event_key *key, char *decode) { - scnprintf(decode, decode_str_len, "%#llx:%s", + scnprintf(decode, KVM_EVENT_NAME_LEN, "%#llx:%s", (unsigned long long)key->key, key->info ? "W" : "R"); } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index fbdd46d38c13..286faf6774ff 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -161,7 +161,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm, const char *exit_reason = get_exit_reason(kvm, key->exit_reasons, key->key); - scnprintf(decode, decode_str_len, "%s", exit_reason); + scnprintf(decode, KVM_EVENT_NAME_LEN, "%s", exit_reason); } static bool register_kvm_events_ops(struct perf_kvm_stat *kvm) @@ -434,7 +434,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, time_diff = sample->time - time_begin; if (kvm->duration && time_diff > kvm->duration) { - char decode[decode_str_len]; + char decode[KVM_EVENT_NAME_LEN]; kvm->events_ops->decode_key(kvm, &event->key, decode); if (!skip_event(decode)) { @@ -605,7 +605,7 @@ static void show_timeofday(void) static void print_result(struct perf_kvm_stat *kvm) { - char decode[decode_str_len]; + char decode[KVM_EVENT_NAME_LEN]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; @@ -616,7 +616,7 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("\n\n"); print_vcpu_info(kvm); - pr_info("%*s ", decode_str_len, kvm->events_ops->name); + pr_info("%*s ", KVM_EVENT_NAME_LEN, kvm->events_ops->name); pr_info("%10s ", "Samples"); pr_info("%9s ", "Samples%"); @@ -635,7 +635,7 @@ static void print_result(struct perf_kvm_stat *kvm) min = get_event_min(event, vcpu); kvm->events_ops->decode_key(kvm, &event->key, decode); - pr_info("%*s ", decode_str_len, decode); + pr_info("%*s ", KVM_EVENT_NAME_LEN, decode); pr_info("%10llu ", (unsigned long long)ecount); pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100); pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 0c2400d9b227..841b3174c211 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -8,6 +8,8 @@ #include "stat.h" #include "record.h" +#define KVM_EVENT_NAME_LEN 40 + struct evsel; struct evlist; struct perf_session; @@ -143,7 +145,6 @@ extern const char *kvm_events_tp[]; extern struct kvm_reg_events_ops kvm_reg_events_ops[]; extern const char * const kvm_skip_events[]; extern const char *vcpu_id_str; -extern const int decode_str_len; extern const char *kvm_exit_reason; extern const char *kvm_entry_trace; extern const char *kvm_exit_trace; -- GitLab From 2d08124b08631322303e365d422ead50ae1674b8 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:02 +0800 Subject: [PATCH 0549/5631] perf kvm: Introduce histograms data structures This is a preparation to support histograms in perf kvm tool. As first step, this patch defines histograms data structures and initialize them. Committer notes: Those are only used by functions enclosed in: #if efined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) So do this for these new functions and struct as well. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 18 ++++++++++++++++++ tools/perf/util/kvm-stat.h | 1 + 2 files changed, 19 insertions(+) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 286faf6774ff..b06c11d306a1 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -85,6 +85,20 @@ static struct kvm_event_key keys[] = { DEF_SORT_NAME_KEY(time, mean), { NULL, NULL } }; + +struct kvm_hists { + struct hists hists; + struct perf_hpp_list list; +}; + +static struct kvm_hists kvm_hists; + +static int kvm_hists__init(void) +{ + __hists__init(&kvm_hists.hists, &kvm_hists.list); + perf_hpp_list__init(&kvm_hists.list); + return 0; +} #endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) static const char *get_filename_for_perf_kvm(void) @@ -959,6 +973,8 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) set_term_quiet_input(&save); init_kvm_event_record(kvm); + kvm_hists__init(); + signal(SIGINT, sig_handler); signal(SIGTERM, sig_handler); @@ -1154,6 +1170,8 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) init_kvm_event_record(kvm); setup_pager(); + kvm_hists__init(); + ret = read_events(kvm); if (ret) goto exit; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 841b3174c211..e2c17662bac7 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -5,6 +5,7 @@ #ifdef HAVE_KVM_STAT_SUPPORT #include "tool.h" +#include "sort.h" #include "stat.h" #include "record.h" -- GitLab From 730651f7177f473345ab470db212c7b5a18466f0 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:03 +0800 Subject: [PATCH 0550/5631] perf kvm: Pass argument 'sample' to kvm_alloc_init_event() This patch adds an argument 'sample' for kvm_alloc_init_event(), and its caller functions are updated as well for passing down the 'sample' pointer. This is a preparation change to allow later patch to create histograms entries for kvm event, no any functionality changes. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index b06c11d306a1..ef502c19bc40 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -262,7 +262,8 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) } static struct kvm_event *kvm_alloc_init_event(struct perf_kvm_stat *kvm, - struct event_key *key) + struct event_key *key, + struct perf_sample *sample __maybe_unused) { struct kvm_event *event; @@ -279,7 +280,8 @@ static struct kvm_event *kvm_alloc_init_event(struct perf_kvm_stat *kvm, } static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, - struct event_key *key) + struct event_key *key, + struct perf_sample *sample) { struct kvm_event *event; struct list_head *head; @@ -292,7 +294,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, return event; } - event = kvm_alloc_init_event(kvm, key); + event = kvm_alloc_init_event(kvm, key, sample); if (!event) return NULL; @@ -302,15 +304,16 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, static bool handle_begin_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, - struct event_key *key, u64 timestamp) + struct event_key *key, + struct perf_sample *sample) { struct kvm_event *event = NULL; if (key->key != INVALID_KEY) - event = find_create_kvm_event(kvm, key); + event = find_create_kvm_event(kvm, key, sample); vcpu_record->last_event = event; - vcpu_record->start_time = timestamp; + vcpu_record->start_time = sample->time; return true; } @@ -377,12 +380,12 @@ static bool is_child_event(struct perf_kvm_stat *kvm, static bool handle_child_event(struct perf_kvm_stat *kvm, struct vcpu_event_record *vcpu_record, struct event_key *key, - struct perf_sample *sample __maybe_unused) + struct perf_sample *sample) { struct kvm_event *event = NULL; if (key->key != INVALID_KEY) - event = find_create_kvm_event(kvm, key); + event = find_create_kvm_event(kvm, key, sample); vcpu_record->last_event = event; @@ -431,7 +434,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm, return true; if (!event) - event = find_create_kvm_event(kvm, key); + event = find_create_kvm_event(kvm, key, sample); if (!event) return false; @@ -502,7 +505,7 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, return true; if (kvm->events_ops->is_begin_event(evsel, sample, &key)) - return handle_begin_event(kvm, vcpu_record, &key, sample->time); + return handle_begin_event(kvm, vcpu_record, &key, sample); if (is_child_event(kvm, evsel, sample, &key)) return handle_child_event(kvm, vcpu_record, &key, sample); -- GitLab From 001b08f4e2aab9748b5d5e49b68d5444715ffda9 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:04 +0800 Subject: [PATCH 0551/5631] perf kvm: Parse address location for samples Parse address location for samples and save it into the structure 'perf_kvm_stat', it is to be used by histograms entry. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 5 +++++ tools/perf/util/kvm-stat.h | 4 ++++ 2 files changed, 9 insertions(+) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index ef502c19bc40..17a8219a702a 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -706,6 +706,11 @@ static int process_sample_event(struct perf_tool *tool, if (skip_sample(kvm, sample)) return 0; + if (machine__resolve(machine, &kvm->al, sample) < 0) { + pr_warning("Fail to resolve address location, skip sample.\n"); + return 0; + } + thread = machine__findnew_thread(machine, sample->pid, sample->tid); if (thread == NULL) { pr_debug("problem processing %d event, skipping it.\n", diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index e2c17662bac7..3b2eab91a9be 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -7,6 +7,7 @@ #include "tool.h" #include "sort.h" #include "stat.h" +#include "symbol.h" #include "record.h" #define KVM_EVENT_NAME_LEN 40 @@ -88,6 +89,9 @@ struct perf_kvm_stat { const char *sort_key; int trace_vcpu; + /* Used when process events */ + struct addr_location al; + struct exit_reasons_table *exit_reasons; const char *exit_reasons_isa; -- GitLab From ebf39d29b985b0c0f75c2e752781a9a80daadc0e Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:05 +0800 Subject: [PATCH 0552/5631] perf hist: Add 'kvm_info' field in histograms entry __hists__add_entry() creates a temporary entry and compare it with existed histograms entries, if any existed entry equals to the temporary entry it skips to allocation to avoid duplication. The problem for support KVM event in histograms is it doesn't contain any info to identify KVM event and can be used for comparison entries. This patch adds 'kvm_info' field in the histograms entry which contains the KVM event's key, this identifier will be used for comparison histograms entries in later change. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-c2c.c | 4 ++-- tools/perf/builtin-diff.c | 4 ++-- tools/perf/tests/hists_link.c | 4 ++-- tools/perf/util/hist.c | 19 ++++++++++++------- tools/perf/util/hist.h | 3 +++ tools/perf/util/kvm-stat.h | 4 ++++ tools/perf/util/sort.h | 1 + 8 files changed, 27 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 90458ca6933f..4750fac7bf93 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -252,7 +252,7 @@ static int evsel__add_sample(struct evsel *evsel, struct perf_sample *sample, if (ann->has_br_stack && has_annotation(ann)) return process_branch_callback(evsel, sample, al, ann, machine); - he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true); + he = hists__add_entry(hists, al, NULL, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 56974eae0638..d3181fee4d3d 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -315,7 +315,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, c2c_decode_stats(&stats, mi); he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops, - &al, NULL, NULL, mi, + &al, NULL, NULL, mi, NULL, sample, true); if (he == NULL) goto free_mi; @@ -349,7 +349,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, goto free_mi; he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops, - &al, NULL, NULL, mi, + &al, NULL, NULL, mi, NULL, sample, true); if (he == NULL) goto free_mi; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index ed07cc6cca56..22b526766e14 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -423,7 +423,7 @@ static int diff__process_sample_event(struct perf_tool *tool, switch (compute) { case COMPUTE_CYCLES: if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL, - NULL, NULL, sample, true)) { + NULL, NULL, NULL, sample, true)) { pr_warning("problem incrementing symbol period, " "skipping event\n"); goto out_put; @@ -442,7 +442,7 @@ static int diff__process_sample_event(struct perf_tool *tool, break; default: - if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, + if (!hists__add_entry(hists, &al, NULL, NULL, NULL, NULL, sample, true)) { pr_warning("problem incrementing symbol period, " "skipping event\n"); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 14b2ff808b5e..e7e4ee57ce04 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -87,7 +87,7 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) goto out; he = hists__add_entry(hists, &al, NULL, - NULL, NULL, &sample, true); + NULL, NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; @@ -106,7 +106,7 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) goto out; he = hists__add_entry(hists, &al, NULL, - NULL, NULL, &sample, true); + NULL, NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b6e4b4edde43..3670136a0074 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -4,6 +4,7 @@ #include "dso.h" #include "build-id.h" #include "hist.h" +#include "kvm-stat.h" #include "map.h" #include "map_symbol.h" #include "branch.h" @@ -698,6 +699,7 @@ __hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, + struct kvm_info *ki, struct block_info *block_info, struct perf_sample *sample, bool sample_self, @@ -733,6 +735,7 @@ __hists__add_entry(struct hists *hists, .hists = hists, .branch_info = bi, .mem_info = mi, + .kvm_info = ki, .block_info = block_info, .transaction = sample->transaction, .raw_data = sample->raw_data, @@ -756,10 +759,11 @@ struct hist_entry *hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, + struct kvm_info *ki, struct perf_sample *sample, bool sample_self) { - return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL, + return __hists__add_entry(hists, al, sym_parent, bi, mi, ki, NULL, sample, sample_self, NULL); } @@ -769,10 +773,11 @@ struct hist_entry *hists__add_entry_ops(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, + struct kvm_info *ki, struct perf_sample *sample, bool sample_self) { - return __hists__add_entry(hists, al, sym_parent, bi, mi, NULL, + return __hists__add_entry(hists, al, sym_parent, bi, mi, ki, NULL, sample, sample_self, ops); } @@ -846,7 +851,7 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al */ sample->period = cost; - he = hists__add_entry(hists, al, iter->parent, NULL, mi, + he = hists__add_entry(hists, al, iter->parent, NULL, mi, NULL, sample, true); if (!he) return -ENOMEM; @@ -949,7 +954,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a sample->period = 1; sample->weight = bi->flags.cycles ? bi->flags.cycles : 1; - he = hists__add_entry(hists, al, iter->parent, &bi[i], NULL, + he = hists__add_entry(hists, al, iter->parent, &bi[i], NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; @@ -987,7 +992,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct hist_entry *he; he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample, true); + NULL, sample, true); if (he == NULL) return -ENOMEM; @@ -1047,7 +1052,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, struct hist_entry *he; int err = 0; - he = hists__add_entry(hists, al, iter->parent, NULL, NULL, + he = hists__add_entry(hists, al, iter->parent, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; @@ -1148,7 +1153,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } he = hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample, false); + NULL, sample, false); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index d93a4e510dc7..86a677954279 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -14,6 +14,7 @@ struct hist_entry_ops; struct addr_location; struct map_symbol; struct mem_info; +struct kvm_info; struct branch_info; struct branch_stack; struct block_info; @@ -150,6 +151,7 @@ struct hist_entry *hists__add_entry(struct hists *hists, struct symbol *parent, struct branch_info *bi, struct mem_info *mi, + struct kvm_info *ki, struct perf_sample *sample, bool sample_self); @@ -159,6 +161,7 @@ struct hist_entry *hists__add_entry_ops(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, + struct kvm_info *ki, struct perf_sample *sample, bool sample_self); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 3b2eab91a9be..0cf704333c4c 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -23,6 +23,10 @@ struct event_key { struct exit_reasons_table *exit_reasons; }; +struct kvm_info { + char name[KVM_EVENT_NAME_LEN]; +}; + struct kvm_event_stats { u64 time; struct stats stats; diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index d79a100e5999..22f437c3476f 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -144,6 +144,7 @@ struct hist_entry { struct hists *hists; struct mem_info *mem_info; struct block_info *block_info; + struct kvm_info *kvm_info; void *raw_data; u32 raw_size; int num_res; -- GitLab From 41f1138e5c1cf11c5b469c3f891960b4ad05e886 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:06 +0800 Subject: [PATCH 0553/5631] perf kvm: Add dimensions for KVM event statistics To support KVM event statistics, this patch firstly registers histograms columns and sorting fields; every column or field has its own format structure, the format structure is dereferenced to access the dimension, finally the dimension provides the comparison callback for sorting result. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 232 ++++++++++++++++++++++++++++++++++++- tools/perf/util/kvm-stat.h | 2 + 2 files changed, 230 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 17a8219a702a..899e331cf727 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -71,9 +71,9 @@ static int64_t cmp_event_ ## func(struct kvm_event *one, \ get_event_ ##func(two, vcpu); \ } -GET_EVENT_KEY(time, time); -GET_EVENT_KEY(max, stats.max); -GET_EVENT_KEY(min, stats.min); +COMPARE_EVENT_KEY(time, time); +COMPARE_EVENT_KEY(max, stats.max); +COMPARE_EVENT_KEY(min, stats.min); COMPARE_EVENT_KEY(count, stats.n); COMPARE_EVENT_KEY(mean, stats.mean); @@ -91,13 +91,237 @@ struct kvm_hists { struct perf_hpp_list list; }; +struct kvm_dimension { + const char *name; + int64_t (*cmp)(struct perf_hpp_fmt *fmt, struct hist_entry *left, + struct hist_entry *right); +}; + +struct kvm_fmt { + struct perf_hpp_fmt fmt; + struct kvm_dimension *dim; +}; + static struct kvm_hists kvm_hists; +static int64_t ev_name_cmp(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, + struct hist_entry *right) +{ + /* Return opposite number for sorting in alphabetical order */ + return -strcmp(left->kvm_info->name, right->kvm_info->name); +} + +static struct kvm_dimension dim_event = { + .name = "ev_name", + .cmp = ev_name_cmp, +}; + +#define EV_METRIC_CMP(metric) \ +static int64_t ev_cmp_##metric(struct perf_hpp_fmt *fmt __maybe_unused, \ + struct hist_entry *left, \ + struct hist_entry *right) \ +{ \ + struct kvm_event *event_left; \ + struct kvm_event *event_right; \ + struct perf_kvm_stat *perf_kvm; \ + \ + event_left = container_of(left, struct kvm_event, he); \ + event_right = container_of(right, struct kvm_event, he); \ + \ + perf_kvm = event_left->perf_kvm; \ + return cmp_event_##metric(event_left, event_right, \ + perf_kvm->trace_vcpu); \ +} + +EV_METRIC_CMP(time) +EV_METRIC_CMP(count) +EV_METRIC_CMP(max) +EV_METRIC_CMP(min) +EV_METRIC_CMP(mean) + +static struct kvm_dimension dim_time = { + .name = "time", + .cmp = ev_cmp_time, +}; + +static struct kvm_dimension dim_count = { + .name = "sample", + .cmp = ev_cmp_count, +}; + +static struct kvm_dimension dim_max_time = { + .name = "max_t", + .cmp = ev_cmp_max, +}; + +static struct kvm_dimension dim_min_time = { + .name = "min_t", + .cmp = ev_cmp_min, +}; + +static struct kvm_dimension dim_mean_time = { + .name = "mean_t", + .cmp = ev_cmp_mean, +}; + +static struct kvm_dimension *dimensions[] = { + &dim_event, + &dim_time, + &dim_count, + &dim_max_time, + &dim_min_time, + &dim_mean_time, + NULL, +}; + +static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) +{ + struct kvm_fmt *kvm_fmt_a = container_of(a, struct kvm_fmt, fmt); + struct kvm_fmt *kvm_fmt_b = container_of(b, struct kvm_fmt, fmt); + + return kvm_fmt_a->dim == kvm_fmt_b->dim; +} + +static void fmt_free(struct perf_hpp_fmt *fmt) +{ + struct kvm_fmt *kvm_fmt; + + kvm_fmt = container_of(fmt, struct kvm_fmt, fmt); + free(kvm_fmt); +} + +static struct kvm_dimension *get_dimension(const char *name) +{ + unsigned int i; + + for (i = 0; dimensions[i] != NULL; i++) { + if (!strcmp(dimensions[i]->name, name)) + return dimensions[i]; + } + + return NULL; +} + +static struct kvm_fmt *get_format(const char *name) +{ + struct kvm_dimension *dim = get_dimension(name); + struct kvm_fmt *kvm_fmt; + struct perf_hpp_fmt *fmt; + + if (!dim) + return NULL; + + kvm_fmt = zalloc(sizeof(*kvm_fmt)); + if (!kvm_fmt) + return NULL; + + kvm_fmt->dim = dim; + + fmt = &kvm_fmt->fmt; + INIT_LIST_HEAD(&fmt->list); + INIT_LIST_HEAD(&fmt->sort_list); + fmt->cmp = dim->cmp; + fmt->sort = dim->cmp; + fmt->color = NULL; + fmt->entry = NULL; + fmt->header = NULL; + fmt->width = NULL; + fmt->collapse = dim->cmp; + fmt->equal = fmt_equal; + fmt->free = fmt_free; + + return kvm_fmt; +} + +static int kvm_hists__init_output(struct perf_hpp_list *hpp_list, char *name) +{ + struct kvm_fmt *kvm_fmt = get_format(name); + + if (!kvm_fmt) { + pr_warning("Fail to find format for output field %s.\n", name); + return -EINVAL; + } + + perf_hpp_list__column_register(hpp_list, &kvm_fmt->fmt); + return 0; +} + +static int kvm_hists__init_sort(struct perf_hpp_list *hpp_list, char *name) +{ + struct kvm_fmt *kvm_fmt = get_format(name); + + if (!kvm_fmt) { + pr_warning("Fail to find format for sorting %s.\n", name); + return -EINVAL; + } + + perf_hpp_list__register_sort_field(hpp_list, &kvm_fmt->fmt); + return 0; +} + +static int kvm_hpp_list__init(char *list, + struct perf_hpp_list *hpp_list, + int (*fn)(struct perf_hpp_list *hpp_list, + char *name)) +{ + char *tmp, *tok; + int ret; + + if (!list || !fn) + return 0; + + for (tok = strtok_r(list, ", ", &tmp); tok; + tok = strtok_r(NULL, ", ", &tmp)) { + ret = fn(hpp_list, tok); + if (!ret) + continue; + + /* Handle errors */ + if (ret == -EINVAL) + pr_err("Invalid field key: '%s'", tok); + else if (ret == -ESRCH) + pr_err("Unknown field key: '%s'", tok); + else + pr_err("Fail to initialize for field key: '%s'", tok); + + break; + } + + return ret; +} + +static int kvm_hpp_list__parse(struct perf_hpp_list *hpp_list, + const char *output_, const char *sort_) +{ + char *output = output_ ? strdup(output_) : NULL; + char *sort = sort_ ? strdup(sort_) : NULL; + int ret; + + ret = kvm_hpp_list__init(output, hpp_list, kvm_hists__init_output); + if (ret) + goto out; + + ret = kvm_hpp_list__init(sort, hpp_list, kvm_hists__init_sort); + if (ret) + goto out; + + /* Copy sort keys to output fields */ + perf_hpp__setup_output_field(hpp_list); + + /* and then copy output fields to sort keys */ + perf_hpp__append_sort_keys(hpp_list); +out: + free(output); + free(sort); + return ret; +} + static int kvm_hists__init(void) { __hists__init(&kvm_hists.hists, &kvm_hists.list); perf_hpp_list__init(&kvm_hists.list); - return 0; + return kvm_hpp_list__parse(&kvm_hists.list, NULL, "ev_name"); } #endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 0cf704333c4c..fc30a72dfac1 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -46,6 +46,8 @@ struct kvm_event { #define DEFAULT_VCPU_NUM 8 int max_vcpu; struct kvm_event_stats *vcpu; + + struct hist_entry he; }; typedef int64_t (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); -- GitLab From f57a64142c04b6cbbfb2ce6493f0aefc237c3106 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:07 +0800 Subject: [PATCH 0554/5631] perf kvm: Use histograms list to replace cached list perf kvm tool defines its own cached list which is managed with RB tree, histograms also provide RB tree to manage data entries. Since now we have introduced histograms in the tool, it's not necessary to use the self defined list and we can directly use histograms list to manage KVM events. This patch changes to use histograms list to track KVM events, and it invokes the common function hists__output_resort_cb() to sort result, this also give us flexibility to extend more sorting key words easily. After histograms list supported, the cached list is redundant so remove the relevant code for it. Committer notes: kvm_hists__reinit() is only used by functions enclosed in: #if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) So do it with this new function as well. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 189 +++++++++++++++++++------------------ tools/perf/util/kvm-stat.h | 7 -- 2 files changed, 95 insertions(+), 101 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 899e331cf727..ae1c8c21cd1d 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -323,6 +323,12 @@ static int kvm_hists__init(void) perf_hpp_list__init(&kvm_hists.list); return kvm_hpp_list__parse(&kvm_hists.list, NULL, "ev_name"); } + +static int kvm_hists__reinit(const char *output, const char *sort) +{ + perf_hpp__reset_output_field(&kvm_hists.list); + return kvm_hpp_list__parse(&kvm_hists.list, output, sort); +} #endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) static const char *get_filename_for_perf_kvm(void) @@ -422,44 +428,37 @@ struct vcpu_event_record { struct kvm_event *last_event; }; - -static void init_kvm_event_record(struct perf_kvm_stat *kvm) -{ - unsigned int i; - - for (i = 0; i < EVENTS_CACHE_SIZE; i++) - INIT_LIST_HEAD(&kvm->kvm_events_cache[i]); -} - #ifdef HAVE_TIMERFD_SUPPORT -static void clear_events_cache_stats(struct list_head *kvm_events_cache) +static void clear_events_cache_stats(void) { - struct list_head *head; + struct rb_root_cached *root; + struct rb_node *nd; struct kvm_event *event; - unsigned int i; - int j; - - for (i = 0; i < EVENTS_CACHE_SIZE; i++) { - head = &kvm_events_cache[i]; - list_for_each_entry(event, head, hash_entry) { - /* reset stats for event */ - event->total.time = 0; - init_stats(&event->total.stats); - - for (j = 0; j < event->max_vcpu; ++j) { - event->vcpu[j].time = 0; - init_stats(&event->vcpu[j].stats); - } + int i; + + if (hists__has(&kvm_hists.hists, need_collapse)) + root = &kvm_hists.hists.entries_collapsed; + else + root = kvm_hists.hists.entries_in; + + for (nd = rb_first_cached(root); nd; nd = rb_next(nd)) { + struct hist_entry *he; + + he = rb_entry(nd, struct hist_entry, rb_node_in); + event = container_of(he, struct kvm_event, he); + + /* reset stats for event */ + event->total.time = 0; + init_stats(&event->total.stats); + + for (i = 0; i < event->max_vcpu; ++i) { + event->vcpu[i].time = 0; + init_stats(&event->vcpu[i].stats); } } } #endif -static int kvm_events_hash_fn(u64 key) -{ - return key & (EVENTS_CACHE_SIZE - 1); -} - static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) { int old_max_vcpu = event->max_vcpu; @@ -485,44 +484,64 @@ static bool kvm_event_expand(struct kvm_event *event, int vcpu_id) return true; } -static struct kvm_event *kvm_alloc_init_event(struct perf_kvm_stat *kvm, - struct event_key *key, - struct perf_sample *sample __maybe_unused) +static void *kvm_he_zalloc(size_t size) { - struct kvm_event *event; + struct kvm_event *kvm_ev; - event = zalloc(sizeof(*event)); - if (!event) { - pr_err("Not enough memory\n"); + kvm_ev = zalloc(size + sizeof(*kvm_ev)); + if (!kvm_ev) return NULL; - } - event->perf_kvm = kvm; - event->key = *key; - init_stats(&event->total.stats); - return event; + init_stats(&kvm_ev->total.stats); + hists__inc_nr_samples(&kvm_hists.hists, 0); + return &kvm_ev->he; +} + +static void kvm_he_free(void *he) +{ + struct kvm_event *kvm_ev; + + free(((struct hist_entry *)he)->kvm_info); + kvm_ev = container_of(he, struct kvm_event, he); + free(kvm_ev); } +static struct hist_entry_ops kvm_ev_entry_ops = { + .new = kvm_he_zalloc, + .free = kvm_he_free, +}; + static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, struct event_key *key, struct perf_sample *sample) { struct kvm_event *event; - struct list_head *head; + struct hist_entry *he; + struct kvm_info *ki; BUG_ON(key->key == INVALID_KEY); - head = &kvm->kvm_events_cache[kvm_events_hash_fn(key->key)]; - list_for_each_entry(event, head, hash_entry) { - if (event->key.key == key->key && event->key.info == key->info) - return event; + ki = zalloc(sizeof(*ki)); + if (!ki) { + pr_err("Failed to allocate kvm info\n"); + return NULL; } - event = kvm_alloc_init_event(kvm, key, sample); - if (!event) + kvm->events_ops->decode_key(kvm, key, ki->name); + he = hists__add_entry_ops(&kvm_hists.hists, &kvm_ev_entry_ops, + &kvm->al, NULL, NULL, NULL, ki, sample, true); + if (he == NULL) { + pr_err("Failed to allocate hist entry\n"); + free(ki); return NULL; + } + + event = container_of(he, struct kvm_event, he); + if (!event->perf_kvm) { + event->perf_kvm = kvm; + event->key = *key; + } - list_add(&event->hash_entry, head); return event; } @@ -755,58 +774,32 @@ static bool select_key(struct perf_kvm_stat *kvm) return false; } -static void insert_to_result(struct rb_root *result, struct kvm_event *event, - key_cmp_fun bigger, int vcpu) -{ - struct rb_node **rb = &result->rb_node; - struct rb_node *parent = NULL; - struct kvm_event *p; - - while (*rb) { - p = container_of(*rb, struct kvm_event, rb); - parent = *rb; - - if (bigger(event, p, vcpu) > 0) - rb = &(*rb)->rb_left; - else - rb = &(*rb)->rb_right; - } - - rb_link_node(&event->rb, parent, rb); - rb_insert_color(&event->rb, result); -} - static bool event_is_valid(struct kvm_event *event, int vcpu) { return !!get_event_count(event, vcpu); } -static void sort_result(struct perf_kvm_stat *kvm) +static int filter_cb(struct hist_entry *he, void *arg __maybe_unused) { - unsigned int i; - int vcpu = kvm->trace_vcpu; struct kvm_event *event; + struct perf_kvm_stat *perf_kvm; - for (i = 0; i < EVENTS_CACHE_SIZE; i++) { - list_for_each_entry(event, &kvm->kvm_events_cache[i], hash_entry) { - if (event_is_valid(event, vcpu)) { - insert_to_result(&kvm->result, event, - kvm->compare, vcpu); - } - } - } + event = container_of(he, struct kvm_event, he); + perf_kvm = event->perf_kvm; + if (!event_is_valid(event, perf_kvm->trace_vcpu)) + he->filtered = 1; + else + he->filtered = 0; + return 0; } -/* returns left most element of result, and erase it */ -static struct kvm_event *pop_from_result(struct rb_root *result) +static void sort_result(struct perf_kvm_stat *kvm) { - struct rb_node *node = rb_first(result); - - if (!node) - return NULL; + const char *output_columns = "ev_name,sample,time,max_t,min_t,mean_t"; - rb_erase(node, result); - return container_of(node, struct kvm_event, rb); + kvm_hists__reinit(output_columns, kvm->sort_key); + hists__collapse_resort(&kvm_hists.hists, NULL); + hists__output_resort_cb(&kvm_hists.hists, NULL, filter_cb); } static void print_vcpu_info(struct perf_kvm_stat *kvm) @@ -849,6 +842,7 @@ static void print_result(struct perf_kvm_stat *kvm) char decode[KVM_EVENT_NAME_LEN]; struct kvm_event *event; int vcpu = kvm->trace_vcpu; + struct rb_node *nd; if (kvm->live) { puts(CONSOLE_CLEAR); @@ -867,9 +861,15 @@ static void print_result(struct perf_kvm_stat *kvm) pr_info("%16s ", "Avg time"); pr_info("\n\n"); - while ((event = pop_from_result(&kvm->result))) { + for (nd = rb_first_cached(&kvm_hists.hists.entries); nd; nd = rb_next(nd)) { + struct hist_entry *he; u64 ecount, etime, max, min; + he = rb_entry(nd, struct hist_entry, rb_node); + if (he->filtered) + continue; + + event = container_of(he, struct kvm_event, he); ecount = get_event_count(event, vcpu); etime = get_event_time(event, vcpu); max = get_event_max(event, vcpu); @@ -1146,8 +1146,11 @@ static int perf_kvm__handle_timerfd(struct perf_kvm_stat *kvm) sort_result(kvm); print_result(kvm); + /* Reset sort list to "ev_name" */ + kvm_hists__reinit(NULL, "ev_name"); + /* reset counts */ - clear_events_cache_stats(kvm->kvm_events_cache); + clear_events_cache_stats(); kvm->total_count = 0; kvm->total_time = 0; kvm->lost_events = 0; @@ -1203,7 +1206,6 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) } set_term_quiet_input(&save); - init_kvm_event_record(kvm); kvm_hists__init(); @@ -1399,7 +1401,6 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) if (!register_kvm_events_ops(kvm)) goto exit; - init_kvm_event_record(kvm); setup_pager(); kvm_hists__init(); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index fc30a72dfac1..3f0cbecb862c 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -36,7 +36,6 @@ struct perf_kvm_stat; struct kvm_event { struct list_head hash_entry; - struct rb_node rb; struct perf_kvm_stat *perf_kvm; struct event_key key; @@ -81,9 +80,6 @@ struct exit_reasons_table { const char *reason; }; -#define EVENTS_BITS 12 -#define EVENTS_CACHE_SIZE (1UL << EVENTS_BITS) - struct perf_kvm_stat { struct perf_tool tool; struct record_opts opts; @@ -103,7 +99,6 @@ struct perf_kvm_stat { struct kvm_events_ops *events_ops; key_cmp_fun compare; - struct list_head kvm_events_cache[EVENTS_CACHE_SIZE]; u64 total_time; u64 total_count; @@ -112,8 +107,6 @@ struct perf_kvm_stat { struct intlist *pid_list; - struct rb_root result; - int timerfd; unsigned int display_time; bool live; -- GitLab From c695d48a33e7185cf5c7a7e44a6e8fe640ea1a71 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:08 +0800 Subject: [PATCH 0555/5631] perf kvm: Polish sorting key Since histograms supports sorting, the tool doesn't need to maintain the mapping between the sorting keys and the corresponding comparison callbacks, therefore, this patch removes structure kvm_event_key. But we still need to validate the sorting key, this patch uses an array for sorting keys and renames function select_key() to is_valid_key() to validate the sorting key passed by user. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 29 ++++++++++------------------- tools/perf/util/kvm-stat.h | 8 -------- 2 files changed, 10 insertions(+), 27 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index ae1c8c21cd1d..d102d3a146f9 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -77,15 +77,6 @@ COMPARE_EVENT_KEY(min, stats.min); COMPARE_EVENT_KEY(count, stats.n); COMPARE_EVENT_KEY(mean, stats.mean); -#define DEF_SORT_NAME_KEY(name, compare_key) \ - { #name, cmp_event_ ## compare_key } - -static struct kvm_event_key keys[] = { - DEF_SORT_NAME_KEY(sample, count), - DEF_SORT_NAME_KEY(time, mean), - { NULL, NULL } -}; - struct kvm_hists { struct hists hists; struct perf_hpp_list list; @@ -759,18 +750,18 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm, return true; } -static bool select_key(struct perf_kvm_stat *kvm) +static bool is_valid_key(struct perf_kvm_stat *kvm) { - int i; + static const char *key_array[] = { + "ev_name", "sample", "time", "max_t", "min_t", "mean_t", + }; + unsigned int i; - for (i = 0; keys[i].name; i++) { - if (!strcmp(keys[i].name, kvm->sort_key)) { - kvm->compare = keys[i].key; + for (i = 0; i < ARRAY_SIZE(key_array); i++) + if (!strcmp(key_array[i], kvm->sort_key)) return true; - } - } - pr_err("Unknown compare key:%s\n", kvm->sort_key); + pr_err("Unsupported sort key: %s\n", kvm->sort_key); return false; } @@ -1200,7 +1191,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) return ret; if (!verify_vcpu(kvm->trace_vcpu) || - !select_key(kvm) || + !is_valid_key(kvm) || !register_kvm_events_ops(kvm)) { goto out; } @@ -1395,7 +1386,7 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) if (!verify_vcpu(vcpu)) goto exit; - if (!select_key(kvm)) + if (!is_valid_key(kvm)) goto exit; if (!register_kvm_events_ops(kvm)) diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 3f0cbecb862c..35d03894fac3 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -49,13 +49,6 @@ struct kvm_event { struct hist_entry he; }; -typedef int64_t (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int); - -struct kvm_event_key { - const char *name; - key_cmp_fun key; -}; - struct child_event_ops { void (*get_key)(struct evsel *evsel, struct perf_sample *sample, @@ -98,7 +91,6 @@ struct perf_kvm_stat { const char *exit_reasons_isa; struct kvm_events_ops *events_ops; - key_cmp_fun compare; u64 total_time; u64 total_count; -- GitLab From fbb70bd3100527b9fea86c58e88a63a28f24f428 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:09 +0800 Subject: [PATCH 0556/5631] perf kvm: Support printing attributions for dimensions This patch adds header, entry callback and width for every dimension, thus in TUI mode the tool can print items with the defined attributions. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 97 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 94 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index d102d3a146f9..07f75663083a 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -84,8 +84,12 @@ struct kvm_hists { struct kvm_dimension { const char *name; + const char *header; + int width; int64_t (*cmp)(struct perf_hpp_fmt *fmt, struct hist_entry *left, struct hist_entry *right); + int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he); }; struct kvm_fmt { @@ -103,9 +107,24 @@ static int64_t ev_name_cmp(struct perf_hpp_fmt *fmt __maybe_unused, return -strcmp(left->kvm_info->name, right->kvm_info->name); } +static int fmt_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct hists *hists __maybe_unused); + +static int ev_name_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + int width = fmt_width(fmt, hpp, he->hists); + + return scnprintf(hpp->buf, hpp->size, "%*s", width, he->kvm_info->name); +} + static struct kvm_dimension dim_event = { + .header = "Event name", .name = "ev_name", .cmp = ev_name_cmp, + .entry = ev_name_entry, + .width = 40, }; #define EV_METRIC_CMP(metric) \ @@ -131,29 +150,77 @@ EV_METRIC_CMP(max) EV_METRIC_CMP(min) EV_METRIC_CMP(mean) +#define EV_METRIC_ENTRY(metric) \ +static int ev_entry_##metric(struct perf_hpp_fmt *fmt, \ + struct perf_hpp *hpp, \ + struct hist_entry *he) \ +{ \ + struct kvm_event *event; \ + int width = fmt_width(fmt, hpp, he->hists); \ + struct perf_kvm_stat *perf_kvm; \ + \ + event = container_of(he, struct kvm_event, he); \ + perf_kvm = event->perf_kvm; \ + return scnprintf(hpp->buf, hpp->size, "%*lu", width, \ + get_event_##metric(event, perf_kvm->trace_vcpu)); \ +} + +EV_METRIC_ENTRY(time) +EV_METRIC_ENTRY(count) +EV_METRIC_ENTRY(max) +EV_METRIC_ENTRY(min) + static struct kvm_dimension dim_time = { + .header = "Time (ns)", .name = "time", .cmp = ev_cmp_time, + .entry = ev_entry_time, + .width = 12, }; static struct kvm_dimension dim_count = { + .header = "Samples", .name = "sample", .cmp = ev_cmp_count, + .entry = ev_entry_count, + .width = 12, }; static struct kvm_dimension dim_max_time = { + .header = "Max Time (ns)", .name = "max_t", .cmp = ev_cmp_max, + .entry = ev_entry_max, + .width = 14, }; static struct kvm_dimension dim_min_time = { + .header = "Min Time (ns)", .name = "min_t", .cmp = ev_cmp_min, + .entry = ev_entry_min, + .width = 14, }; +static int ev_entry_mean(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct kvm_event *event; + int width = fmt_width(fmt, hpp, he->hists); + struct perf_kvm_stat *perf_kvm; + + event = container_of(he, struct kvm_event, he); + perf_kvm = event->perf_kvm; + return scnprintf(hpp->buf, hpp->size, "%*lu", width, + get_event_mean(event, perf_kvm->trace_vcpu)); +} + static struct kvm_dimension dim_mean_time = { + .header = "Mean Time (ns)", .name = "mean_t", .cmp = ev_cmp_mean, + .entry = ev_entry_mean, + .width = 14, }; static struct kvm_dimension *dimensions[] = { @@ -166,6 +233,30 @@ static struct kvm_dimension *dimensions[] = { NULL, }; +static int fmt_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct hists *hists __maybe_unused) +{ + struct kvm_fmt *kvm_fmt; + + kvm_fmt = container_of(fmt, struct kvm_fmt, fmt); + return kvm_fmt->dim->width; +} + +static int fmt_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hists *hists, int line __maybe_unused, + int *span __maybe_unused) +{ + struct kvm_fmt *kvm_fmt; + struct kvm_dimension *dim; + int width = fmt_width(fmt, hpp, hists); + + kvm_fmt = container_of(fmt, struct kvm_fmt, fmt); + dim = kvm_fmt->dim; + + return scnprintf(hpp->buf, hpp->size, "%*s", width, dim->header); +} + static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b) { struct kvm_fmt *kvm_fmt_a = container_of(a, struct kvm_fmt, fmt); @@ -215,9 +306,9 @@ static struct kvm_fmt *get_format(const char *name) fmt->cmp = dim->cmp; fmt->sort = dim->cmp; fmt->color = NULL; - fmt->entry = NULL; - fmt->header = NULL; - fmt->width = NULL; + fmt->entry = dim->entry; + fmt->header = fmt_header; + fmt->width = fmt_width; fmt->collapse = dim->cmp; fmt->equal = fmt_equal; fmt->free = fmt_free; -- GitLab From 32a5c2b84236d1eebf341ae4a90dd5e04aae97ae Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:10 +0800 Subject: [PATCH 0557/5631] perf kvm: Add dimensions for percentages Add dimensions for count and time percentages, it would be useful for user to review percentage statistics. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 98 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 97 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 07f75663083a..9bfde8b7ac65 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -223,10 +223,105 @@ static struct kvm_dimension dim_mean_time = { .width = 14, }; +#define PERC_STR(__s, __v) \ +({ \ + scnprintf(__s, sizeof(__s), "%.2F%%", __v); \ + __s; \ +}) + +static double percent(u64 st, u64 tot) +{ + return tot ? 100. * (double) st / (double) tot : 0; +} + +#define EV_METRIC_PERCENT(metric) \ +static int ev_percent_##metric(struct hist_entry *he) \ +{ \ + struct kvm_event *event; \ + struct perf_kvm_stat *perf_kvm; \ + \ + event = container_of(he, struct kvm_event, he); \ + perf_kvm = event->perf_kvm; \ + \ + return percent(get_event_##metric(event, perf_kvm->trace_vcpu), \ + perf_kvm->total_##metric); \ +} + +EV_METRIC_PERCENT(time) +EV_METRIC_PERCENT(count) + +static int ev_entry_time_precent(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + int width = fmt_width(fmt, hpp, he->hists); + double per; + char buf[10]; + + per = ev_percent_time(he); + return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per)); +} + +static int64_t +ev_cmp_time_precent(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + double per_left; + double per_right; + + per_left = ev_percent_time(left); + per_right = ev_percent_time(right); + + return per_left - per_right; +} + +static struct kvm_dimension dim_time_percent = { + .header = "Time%", + .name = "percent_time", + .cmp = ev_cmp_time_precent, + .entry = ev_entry_time_precent, + .width = 12, +}; + +static int ev_entry_count_precent(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp, + struct hist_entry *he) +{ + int width = fmt_width(fmt, hpp, he->hists); + double per; + char buf[10]; + + per = ev_percent_count(he); + return scnprintf(hpp->buf, hpp->size, "%*s", width, PERC_STR(buf, per)); +} + +static int64_t +ev_cmp_count_precent(struct perf_hpp_fmt *fmt __maybe_unused, + struct hist_entry *left, struct hist_entry *right) +{ + double per_left; + double per_right; + + per_left = ev_percent_count(left); + per_right = ev_percent_count(right); + + return per_left - per_right; +} + +static struct kvm_dimension dim_count_percent = { + .header = "Sample%", + .name = "percent_sample", + .cmp = ev_cmp_count_precent, + .entry = ev_entry_count_precent, + .width = 12, +}; + static struct kvm_dimension *dimensions[] = { &dim_event, &dim_time, + &dim_time_percent, &dim_count, + &dim_count_percent, &dim_max_time, &dim_min_time, &dim_mean_time, @@ -877,7 +972,8 @@ static int filter_cb(struct hist_entry *he, void *arg __maybe_unused) static void sort_result(struct perf_kvm_stat *kvm) { - const char *output_columns = "ev_name,sample,time,max_t,min_t,mean_t"; + const char *output_columns = "ev_name,sample,percent_sample," + "time,percent_time,max_t,min_t,mean_t"; kvm_hists__reinit(output_columns, kvm->sort_key); hists__collapse_resort(&kvm_hists.hists, NULL); -- GitLab From 984f16cd602c82451b2e910ac58d7880bcb48b1a Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:11 +0800 Subject: [PATCH 0558/5631] perf kvm: Add TUI mode for stat report Since we have supported histograms list and prepared the dimensions in the tool, this patch adds TUI mode for stat report. It also adds UI progress for sorting for better user experience. Committer notes: kvm_display() is only used by functions enclosed in: #if defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) So do it with this new function as well. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 109 ++++++++++++++++++++++++++++++++++++- tools/perf/util/kvm-stat.h | 1 + 2 files changed, 108 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 9bfde8b7ac65..4c205df5106f 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -23,6 +23,8 @@ #include "util/data.h" #include "util/ordered-events.h" #include "util/kvm-stat.h" +#include "ui/browsers/hists.h" +#include "ui/progress.h" #include "ui/ui.h" #include "util/string2.h" @@ -496,6 +498,7 @@ static int kvm_hpp_list__parse(struct perf_hpp_list *hpp_list, static int kvm_hists__init(void) { + kvm_hists.list.nr_header_lines = 1; __hists__init(&kvm_hists.hists, &kvm_hists.list); perf_hpp_list__init(&kvm_hists.list); return kvm_hpp_list__parse(&kvm_hists.list, NULL, "ev_name"); @@ -506,6 +509,93 @@ static int kvm_hists__reinit(const char *output, const char *sort) perf_hpp__reset_output_field(&kvm_hists.list); return kvm_hpp_list__parse(&kvm_hists.list, output, sort); } +static void print_result(struct perf_kvm_stat *kvm); + +#ifdef HAVE_SLANG_SUPPORT +static void kvm_browser__update_nr_entries(struct hist_browser *hb) +{ + struct rb_node *nd = rb_first_cached(&hb->hists->entries); + u64 nr_entries = 0; + + for (; nd; nd = rb_next(nd)) { + struct hist_entry *he = rb_entry(nd, struct hist_entry, + rb_node); + + if (!he->filtered) + nr_entries++; + } + + hb->nr_non_filtered_entries = nr_entries; +} + +static int kvm_browser__title(struct hist_browser *browser, + char *buf, size_t size) +{ + scnprintf(buf, size, "KVM event statistics (%lu entries)", + browser->nr_non_filtered_entries); + return 0; +} + +static struct hist_browser* +perf_kvm_browser__new(struct hists *hists) +{ + struct hist_browser *browser = hist_browser__new(hists); + + if (browser) + browser->title = kvm_browser__title; + + return browser; +} + +static int kvm__hists_browse(struct hists *hists) +{ + struct hist_browser *browser; + int key = -1; + + browser = perf_kvm_browser__new(hists); + if (browser == NULL) + return -1; + + /* reset abort key so that it can get Ctrl-C as a key */ + SLang_reset_tty(); + SLang_init_tty(0, 0, 0); + + kvm_browser__update_nr_entries(browser); + + while (1) { + key = hist_browser__run(browser, "? - help", true, 0); + + switch (key) { + case 'q': + goto out; + default: + break; + } + } + +out: + hist_browser__delete(browser); + return 0; +} + +static void kvm_display(struct perf_kvm_stat *kvm) +{ + if (!use_browser) + print_result(kvm); + else + kvm__hists_browse(&kvm_hists.hists); +} + +#else + +static void kvm_display(struct perf_kvm_stat *kvm) +{ + use_browser = 0; + print_result(kvm); +} + +#endif /* HAVE_SLANG_SUPPORT */ + #endif // defined(HAVE_KVM_STAT_SUPPORT) && defined(HAVE_LIBTRACEEVENT) static const char *get_filename_for_perf_kvm(void) @@ -972,12 +1062,15 @@ static int filter_cb(struct hist_entry *he, void *arg __maybe_unused) static void sort_result(struct perf_kvm_stat *kvm) { + struct ui_progress prog; const char *output_columns = "ev_name,sample,percent_sample," "time,percent_time,max_t,min_t,mean_t"; kvm_hists__reinit(output_columns, kvm->sort_key); + ui_progress__init(&prog, kvm_hists.hists.nr_entries, "Sorting..."); hists__collapse_resort(&kvm_hists.hists, NULL); hists__output_resort_cb(&kvm_hists.hists, NULL, filter_cb); + ui_progress__finish(); } static void print_vcpu_info(struct perf_kvm_stat *kvm) @@ -1579,7 +1672,14 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) if (!register_kvm_events_ops(kvm)) goto exit; - setup_pager(); + if (kvm->use_stdio) { + use_browser = 0; + setup_pager(); + } else { + use_browser = 1; + } + + setup_browser(false); kvm_hists__init(); @@ -1588,7 +1688,7 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) goto exit; sort_result(kvm); - print_result(kvm); + kvm_display(kvm); exit: return ret; @@ -1695,6 +1795,7 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) OPT_STRING('p', "pid", &kvm->opts.target.pid, "pid", "analyze events only for given process id(s)"), OPT_BOOLEAN('f', "force", &kvm->force, "don't complain, do it"), + OPT_BOOLEAN(0, "stdio", &kvm->use_stdio, "use the stdio interface"), OPT_END() }; @@ -1712,6 +1813,10 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv) kvm_events_report_options); } +#ifndef HAVE_SLANG_SUPPORT + kvm->use_stdio = true; +#endif + if (!kvm->opts.target.pid) kvm->opts.target.system_wide = true; diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index 35d03894fac3..bc6c8e38ef50 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -103,6 +103,7 @@ struct perf_kvm_stat { unsigned int display_time; bool live; bool force; + bool use_stdio; }; struct kvm_reg_events_ops { -- GitLab From 96d541699e5c50b1bc2d50c83cd7145994d5f071 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 15 Mar 2023 22:51:12 +0800 Subject: [PATCH 0559/5631] perf kvm: Update documentation to reflect new changes Update documentation for new sorting and option '--stdio'. Reviewed-by: James Clark Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230315145112.186603-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-kvm.txt | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt index 2ad3f5d9f72b..b66be66fe836 100644 --- a/tools/perf/Documentation/perf-kvm.txt +++ b/tools/perf/Documentation/perf-kvm.txt @@ -58,7 +58,7 @@ There are a couple of variants of perf kvm: events. 'perf kvm stat report' reports statistical data which includes events - handled time, samples, and so on. + handled sample, percent_sample, time, percent_time, max_t, min_t, mean_t. 'perf kvm stat live' reports statistical data in a live mode (similar to record + report but with statistical data updated live at a given display @@ -82,6 +82,8 @@ OPTIONS :GMEXAMPLESUBCMD: top include::guest-files.txt[] +--stdio:: Use the stdio interface. + -v:: --verbose:: Be more verbose (show counter open errors, etc). @@ -97,7 +99,10 @@ STAT REPORT OPTIONS -k:: --key=:: Sorting key. Possible values: sample (default, sort by samples - number), time (sort by average time). + number), percent_sample (sort by sample percentage), time + (sort by average time), precent_time (sort by time percentage), + max_t (sort by maximum time), min_t (sort by minimum time), mean_t + (sort by mean time). -p:: --pid=:: Analyze events only for given process ID(s) (comma separated list). -- GitLab From 357f82395cd8a0279067805841e5968f4e6dc932 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:47 +0100 Subject: [PATCH 0560/5631] powerpc/47x: Split ppc47x machine in two This machine matches two compatibles and sets .pci_irq_fixup on one of them. Split it into two machines, then the probe function can be dropped. Signed-off-by: Christophe Leroy [mpe: Drop references to ppc47x_probe() to fix build] Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/platforms/44x/ppc476.c | 37 +++++++++++++---------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 7c91ac5a5241..4641ae8c9b09 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -114,7 +114,8 @@ static int __init ppc47x_device_probe(void) return 0; } -machine_device_initcall(ppc47x, ppc47x_device_probe); +machine_device_initcall(ppc47x_akebono, ppc47x_device_probe); +machine_device_initcall(ppc47x_currituck, ppc47x_device_probe); static void __init ppc47x_init_irq(void) { @@ -249,7 +250,8 @@ static int __init ppc47x_get_board_rev(void) pr_info("%s: Unable to find board revision\n", __func__); return 0; } -machine_arch_initcall(ppc47x, ppc47x_get_board_rev); +machine_arch_initcall(ppc47x_akebono, ppc47x_get_board_rev); +machine_arch_initcall(ppc47x_currituck, ppc47x_get_board_rev); /* Use USB controller should have been hardware swizzled but it wasn't :( */ static void ppc47x_pci_irq_fixup(struct pci_dev *dev) @@ -268,27 +270,22 @@ static void ppc47x_pci_irq_fixup(struct pci_dev *dev) } } -/* - * Called very early, MMU is off, device-tree isn't unflattened - */ -static int __init ppc47x_probe(void) -{ - if (of_machine_is_compatible("ibm,akebono")) - return 1; - - if (of_machine_is_compatible("ibm,currituck")) { - ppc_md.pci_irq_fixup = ppc47x_pci_irq_fixup; - return 1; - } - - return 0; -} +define_machine(ppc47x_akebono) { + .name = "PowerPC 47x (akebono)", + .compatible = "ibm,akebono", + .progress = udbg_progress, + .init_IRQ = ppc47x_init_irq, + .setup_arch = ppc47x_setup_arch, + .restart = ppc4xx_reset_system, + .calibrate_decr = generic_calibrate_decr, +}; -define_machine(ppc47x) { - .name = "PowerPC 47x", - .probe = ppc47x_probe, +define_machine(ppc47x_currituck) { + .name = "PowerPC 47x (currituck)", + .compatible = "ibm,currituck", .progress = udbg_progress, .init_IRQ = ppc47x_init_irq, + .pci_irq_fixup = ppc47x_pci_irq_fixup, .setup_arch = ppc47x_setup_arch, .restart = ppc4xx_reset_system, .calibrate_decr = generic_calibrate_decr, -- GitLab From f47b17d51997cd47e0e6fb1b90145d516ebe6b3e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:48 +0100 Subject: [PATCH 0561/5631] powerpc/gamecube|wii : Use machine_device_initcall() Instead of checking machine type in the function, use machine_device_initcall(). Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/platforms/embedded6xx/gamecube.c | 5 +---- arch/powerpc/platforms/embedded6xx/wii.c | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c index 4fc84ff95b5e..60cdc2852c7a 100644 --- a/arch/powerpc/platforms/embedded6xx/gamecube.c +++ b/arch/powerpc/platforms/embedded6xx/gamecube.c @@ -83,11 +83,8 @@ static const struct of_device_id gamecube_of_bus[] = { static int __init gamecube_device_probe(void) { - if (!machine_is(gamecube)) - return 0; - of_platform_bus_probe(NULL, gamecube_of_bus, NULL); return 0; } -device_initcall(gamecube_device_probe); +machine_device_initcall(gamecube, gamecube_device_probe); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index f2cc00e6f12f..635c393d307a 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -161,13 +161,10 @@ static const struct of_device_id wii_of_bus[] = { static int __init wii_device_probe(void) { - if (!machine_is(wii)) - return 0; - of_platform_populate(NULL, wii_of_bus, NULL, NULL); return 0; } -device_initcall(wii_device_probe); +machine_device_initcall(wii, wii_device_probe); define_machine(wii) { .name = "wii", -- GitLab From 5a81c02d0cc5067170e49452d55a4dfd21333257 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:49 +0100 Subject: [PATCH 0562/5631] powerpc/85xx: Fix function naming for p1023_rdb platform p1023_rdb platform is a copy of mpc85xx_rdb platform and some of its functions have kept mpc85xx_rdb names. Rename the said functions. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/platforms/85xx/p1023_rdb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index 37e78f40d424..e199fc44fc2f 100644 --- a/arch/powerpc/platforms/85xx/p1023_rdb.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -37,7 +37,7 @@ * Setup the architecture * */ -static void __init mpc85xx_rdb_setup_arch(void) +static void __init p1023_rdb_setup_arch(void) { struct device_node *np; @@ -83,7 +83,7 @@ static void __init mpc85xx_rdb_setup_arch(void) machine_arch_initcall(p1023_rdb, mpc85xx_common_publish_devices); -static void __init mpc85xx_rdb_pic_init(void) +static void __init p1023_rdb_pic_init(void) { struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU, @@ -97,8 +97,8 @@ static void __init mpc85xx_rdb_pic_init(void) define_machine(p1023_rdb) { .name = "P1023 RDB", .compatible = "fsl,P1023RDB", - .setup_arch = mpc85xx_rdb_setup_arch, - .init_IRQ = mpc85xx_rdb_pic_init, + .setup_arch = p1023_rdb_setup_arch, + .init_IRQ = p1023_rdb_pic_init, .get_irq = mpic_get_irq, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, -- GitLab From 0aafbdf35c75cbfec82636d01e6dc7950bc1507c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 18 Feb 2023 10:15:50 +0100 Subject: [PATCH 0563/5631] powerpc: Make generic_calibrate_decr() the default ppc_md.calibrate_decr() is a mandatory item. Its nullity is never checked so it must be non null on all platforms. Most platforms define generic_calibrate_decr() as their ppc_md.calibrate_decr(). Have time_init() call generic_calibrate_decr() when ppc_md.calibrate_decr() is NULL, and remove default assignment from all machines. Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/6cb9865d916231c38401ba34ad1a98c249fae135.1676711562.git.christophe.leroy@csgroup.eu --- arch/powerpc/kernel/time.c | 6 +++++- arch/powerpc/platforms/40x/ppc40x_simple.c | 1 - arch/powerpc/platforms/44x/canyonlands.c | 1 - arch/powerpc/platforms/44x/ebony.c | 1 - arch/powerpc/platforms/44x/fsp2.c | 1 - arch/powerpc/platforms/44x/iss4xx.c | 1 - arch/powerpc/platforms/44x/ppc44x_simple.c | 1 - arch/powerpc/platforms/44x/ppc476.c | 2 -- arch/powerpc/platforms/44x/sam440ep.c | 1 - arch/powerpc/platforms/44x/warp.c | 1 - arch/powerpc/platforms/512x/mpc5121_ads.c | 1 - arch/powerpc/platforms/512x/mpc512x_generic.c | 1 - arch/powerpc/platforms/512x/pdm360ng.c | 1 - arch/powerpc/platforms/52xx/efika.c | 1 - arch/powerpc/platforms/52xx/lite5200.c | 1 - arch/powerpc/platforms/52xx/media5200.c | 1 - arch/powerpc/platforms/52xx/mpc5200_simple.c | 1 - arch/powerpc/platforms/82xx/ep8248e.c | 1 - arch/powerpc/platforms/82xx/km82xx.c | 1 - arch/powerpc/platforms/82xx/mpc8272_ads.c | 1 - arch/powerpc/platforms/82xx/pq2fads.c | 1 - arch/powerpc/platforms/83xx/asp834x.c | 1 - arch/powerpc/platforms/83xx/km83xx.c | 1 - arch/powerpc/platforms/83xx/mpc830x_rdb.c | 1 - arch/powerpc/platforms/83xx/mpc831x_rdb.c | 1 - arch/powerpc/platforms/83xx/mpc832x_mds.c | 1 - arch/powerpc/platforms/83xx/mpc832x_rdb.c | 1 - arch/powerpc/platforms/83xx/mpc834x_itx.c | 1 - arch/powerpc/platforms/83xx/mpc834x_mds.c | 1 - arch/powerpc/platforms/83xx/mpc836x_mds.c | 1 - arch/powerpc/platforms/83xx/mpc836x_rdk.c | 1 - arch/powerpc/platforms/83xx/mpc837x_mds.c | 1 - arch/powerpc/platforms/83xx/mpc837x_rdb.c | 1 - arch/powerpc/platforms/85xx/bsc913x_qds.c | 1 - arch/powerpc/platforms/85xx/bsc913x_rdb.c | 1 - arch/powerpc/platforms/85xx/c293pcie.c | 1 - arch/powerpc/platforms/85xx/corenet_generic.c | 1 - arch/powerpc/platforms/85xx/ge_imp3a.c | 1 - arch/powerpc/platforms/85xx/ksi8560.c | 1 - arch/powerpc/platforms/85xx/mpc8536_ds.c | 1 - arch/powerpc/platforms/85xx/mpc85xx_ads.c | 1 - arch/powerpc/platforms/85xx/mpc85xx_cds.c | 1 - arch/powerpc/platforms/85xx/mpc85xx_ds.c | 3 --- arch/powerpc/platforms/85xx/mpc85xx_mds.c | 3 --- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 10 ---------- arch/powerpc/platforms/85xx/mvme2500.c | 1 - arch/powerpc/platforms/85xx/p1010rdb.c | 1 - arch/powerpc/platforms/85xx/p1022_ds.c | 1 - arch/powerpc/platforms/85xx/p1022_rdk.c | 1 - arch/powerpc/platforms/85xx/p1023_rdb.c | 1 - arch/powerpc/platforms/85xx/ppa8548.c | 1 - arch/powerpc/platforms/85xx/qemu_e500.c | 1 - arch/powerpc/platforms/85xx/socrates.c | 1 - arch/powerpc/platforms/85xx/stx_gp3.c | 1 - arch/powerpc/platforms/85xx/tqm85xx.c | 1 - arch/powerpc/platforms/85xx/twr_p102x.c | 1 - arch/powerpc/platforms/85xx/xes_mpc85xx.c | 3 --- arch/powerpc/platforms/86xx/gef_ppc9a.c | 1 - arch/powerpc/platforms/86xx/gef_sbc310.c | 1 - arch/powerpc/platforms/86xx/gef_sbc610.c | 1 - arch/powerpc/platforms/86xx/mpc8610_hpcd.c | 1 - arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 1 - arch/powerpc/platforms/86xx/mvme7100.c | 1 - arch/powerpc/platforms/8xx/adder875.c | 1 - arch/powerpc/platforms/amigaone/setup.c | 1 - arch/powerpc/platforms/cell/setup.c | 1 - arch/powerpc/platforms/chrp/setup.c | 1 - arch/powerpc/platforms/embedded6xx/gamecube.c | 1 - arch/powerpc/platforms/embedded6xx/holly.c | 1 - arch/powerpc/platforms/embedded6xx/linkstation.c | 1 - arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c | 1 - arch/powerpc/platforms/embedded6xx/mvme5100.c | 1 - arch/powerpc/platforms/embedded6xx/storcenter.c | 1 - arch/powerpc/platforms/embedded6xx/wii.c | 1 - arch/powerpc/platforms/maple/setup.c | 1 - arch/powerpc/platforms/microwatt/setup.c | 1 - arch/powerpc/platforms/pasemi/setup.c | 1 - arch/powerpc/platforms/powernv/setup.c | 1 - arch/powerpc/platforms/pseries/setup.c | 1 - 79 files changed, 5 insertions(+), 95 deletions(-) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 9d8665910350..df20cf201f74 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -887,7 +887,11 @@ void __init time_init(void) unsigned shift; /* Normal PowerPC with timebase register */ - ppc_md.calibrate_decr(); + if (ppc_md.calibrate_decr) + ppc_md.calibrate_decr(); + else + generic_calibrate_decr(); + printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", diff --git a/arch/powerpc/platforms/40x/ppc40x_simple.c b/arch/powerpc/platforms/40x/ppc40x_simple.c index dce696c32679..e454e9d2eff1 100644 --- a/arch/powerpc/platforms/40x/ppc40x_simple.c +++ b/arch/powerpc/platforms/40x/ppc40x_simple.c @@ -74,5 +74,4 @@ define_machine(ppc40x_simple) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/canyonlands.c b/arch/powerpc/platforms/44x/canyonlands.c index ba561ca6c25f..8742a10d9e0c 100644 --- a/arch/powerpc/platforms/44x/canyonlands.c +++ b/arch/powerpc/platforms/44x/canyonlands.c @@ -114,5 +114,4 @@ define_machine(canyonlands) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/ebony.c b/arch/powerpc/platforms/44x/ebony.c index 5b9e57b4cd65..4861310c8dc0 100644 --- a/arch/powerpc/platforms/44x/ebony.c +++ b/arch/powerpc/platforms/44x/ebony.c @@ -58,5 +58,4 @@ define_machine(ebony) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c index 56d91dbef577..f6b8d02e08b0 100644 --- a/arch/powerpc/platforms/44x/fsp2.c +++ b/arch/powerpc/platforms/44x/fsp2.c @@ -313,5 +313,4 @@ define_machine(fsp2) { .init_IRQ = fsp2_irq_init, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c index e779bd3d2291..981972e8347f 100644 --- a/arch/powerpc/platforms/44x/iss4xx.c +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -147,5 +147,4 @@ define_machine(iss4xx) { .init_IRQ = iss4xx_init_irq, .setup_arch = iss4xx_setup_arch, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c index 2a0dcdf04b21..971786ff1a7b 100644 --- a/arch/powerpc/platforms/44x/ppc44x_simple.c +++ b/arch/powerpc/platforms/44x/ppc44x_simple.c @@ -82,5 +82,4 @@ define_machine(ppc44x_simple) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 4641ae8c9b09..3135e654a743 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -277,7 +277,6 @@ define_machine(ppc47x_akebono) { .init_IRQ = ppc47x_init_irq, .setup_arch = ppc47x_setup_arch, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; define_machine(ppc47x_currituck) { @@ -288,5 +287,4 @@ define_machine(ppc47x_currituck) { .pci_irq_fixup = ppc47x_pci_irq_fixup, .setup_arch = ppc47x_setup_arch, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/44x/sam440ep.c b/arch/powerpc/platforms/44x/sam440ep.c index 8b281e027477..5cdaa4068e41 100644 --- a/arch/powerpc/platforms/44x/sam440ep.c +++ b/arch/powerpc/platforms/44x/sam440ep.c @@ -54,7 +54,6 @@ define_machine(sam440ep) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; static struct i2c_board_info sam440ep_rtc_info = { diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c index acbc356e8a19..bfeb9bdc3258 100644 --- a/arch/powerpc/platforms/44x/warp.c +++ b/arch/powerpc/platforms/44x/warp.c @@ -48,7 +48,6 @@ define_machine(warp) { .init_IRQ = uic_init_tree, .get_irq = uic_get_irq, .restart = ppc4xx_reset_system, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/512x/mpc5121_ads.c b/arch/powerpc/platforms/512x/mpc5121_ads.c index 0b6a2d3fd343..80b25ce076bc 100644 --- a/arch/powerpc/platforms/512x/mpc5121_ads.c +++ b/arch/powerpc/platforms/512x/mpc5121_ads.c @@ -67,6 +67,5 @@ define_machine(mpc5121_ads) { .init = mpc512x_init, .init_IRQ = mpc5121_ads_init_IRQ, .get_irq = ipic_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = mpc512x_restart, }; diff --git a/arch/powerpc/platforms/512x/mpc512x_generic.c b/arch/powerpc/platforms/512x/mpc512x_generic.c index 364564c995bd..97dfaac8f7ff 100644 --- a/arch/powerpc/platforms/512x/mpc512x_generic.c +++ b/arch/powerpc/platforms/512x/mpc512x_generic.c @@ -47,6 +47,5 @@ define_machine(mpc512x_generic) { .setup_arch = mpc512x_setup_arch, .init_IRQ = mpc512x_init_IRQ, .get_irq = ipic_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = mpc512x_restart, }; diff --git a/arch/powerpc/platforms/512x/pdm360ng.c b/arch/powerpc/platforms/512x/pdm360ng.c index d3a4eeb47bb1..4bdec1c25de7 100644 --- a/arch/powerpc/platforms/512x/pdm360ng.c +++ b/arch/powerpc/platforms/512x/pdm360ng.c @@ -121,6 +121,5 @@ define_machine(pdm360ng) { .init = pdm360ng_init, .init_IRQ = mpc512x_init_IRQ, .get_irq = ipic_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = mpc512x_restart, }; diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 61dfec74ff85..aa82e6b437f3 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -226,7 +226,6 @@ define_machine(efika) .get_rtc_time = rtas_get_rtc_time, .progress = rtas_progress, .get_boot_time = rtas_get_boot_time, - .calibrate_decr = generic_calibrate_decr, #ifdef CONFIG_PCI .phys_mem_access_prot = pci_phys_mem_access_prot, #endif diff --git a/arch/powerpc/platforms/52xx/lite5200.c b/arch/powerpc/platforms/52xx/lite5200.c index 7ea9b6ce0591..0fd67b3ffc3e 100644 --- a/arch/powerpc/platforms/52xx/lite5200.c +++ b/arch/powerpc/platforms/52xx/lite5200.c @@ -189,5 +189,4 @@ define_machine(lite5200) { .init_IRQ = mpc52xx_init_irq, .get_irq = mpc52xx_get_irq, .restart = mpc52xx_restart, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index a9c92c6ccbcf..19626cd42406 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -236,5 +236,4 @@ define_machine(media5200_platform) { .init_IRQ = media5200_init_irq, .get_irq = mpc52xx_get_irq, .restart = mpc52xx_restart, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c index cc349d579061..f1e85e86f5e5 100644 --- a/arch/powerpc/platforms/52xx/mpc5200_simple.c +++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c @@ -76,5 +76,4 @@ define_machine(mpc5200_simple_platform) { .init_IRQ = mpc52xx_init_irq, .get_irq = mpc52xx_get_irq, .restart = mpc52xx_restart, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index 66defdaf816f..8f1856ba692e 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -308,7 +308,6 @@ define_machine(ep8248e) .setup_arch = ep8248e_setup_arch, .init_IRQ = ep8248e_pic_init, .get_irq = cpm2_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = pq2_restart, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c index 8ab575d70080..51c9bfd97592 100644 --- a/arch/powerpc/platforms/82xx/km82xx.c +++ b/arch/powerpc/platforms/82xx/km82xx.c @@ -195,7 +195,6 @@ define_machine(km82xx) .setup_arch = km82xx_setup_arch, .init_IRQ = km82xx_pic_init, .get_irq = cpm2_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = pq2_restart, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c index 5dd034ed2c87..f9b2b1617eeb 100644 --- a/arch/powerpc/platforms/82xx/mpc8272_ads.c +++ b/arch/powerpc/platforms/82xx/mpc8272_ads.c @@ -199,7 +199,6 @@ define_machine(mpc8272_ads) .discover_phbs = pq2_init_pci, .init_IRQ = mpc8272_ads_pic_init, .get_irq = cpm2_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = pq2_restart, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c index d91dfdc634e9..4080cb4253d3 100644 --- a/arch/powerpc/platforms/82xx/pq2fads.c +++ b/arch/powerpc/platforms/82xx/pq2fads.c @@ -177,7 +177,6 @@ define_machine(pq2fads) .discover_phbs = pq2_init_pci, .init_IRQ = pq2fads_pic_init, .get_irq = cpm2_get_irq, - .calibrate_decr = generic_calibrate_decr, .restart = pq2_restart, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/asp834x.c b/arch/powerpc/platforms/83xx/asp834x.c index 8f3d995027fe..6870d0c34f1d 100644 --- a/arch/powerpc/platforms/83xx/asp834x.c +++ b/arch/powerpc/platforms/83xx/asp834x.c @@ -41,6 +41,5 @@ define_machine(asp834x) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c index 907acdecc94a..26ddc7136547 100644 --- a/arch/powerpc/platforms/83xx/km83xx.c +++ b/arch/powerpc/platforms/83xx/km83xx.c @@ -184,6 +184,5 @@ define_machine(mpc83xx_km) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc830x_rdb.c b/arch/powerpc/platforms/83xx/mpc830x_rdb.c index 956d4389effa..534bb227480d 100644 --- a/arch/powerpc/platforms/83xx/mpc830x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc830x_rdb.c @@ -53,6 +53,5 @@ define_machine(mpc830x_rdb) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c index 3b578f080e3b..7b901ab3b864 100644 --- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c @@ -53,6 +53,5 @@ define_machine(mpc831x_rdb) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index 01035eff7d2e..c08f043e3963 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -97,6 +97,5 @@ define_machine(mpc832x_mds) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index 6b7b852e48bf..af6774f145e3 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -221,6 +221,5 @@ define_machine(mpc832x_rdb) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc834x_itx.c b/arch/powerpc/platforms/83xx/mpc834x_itx.c index 92ff7be472c3..e45b98ff02d8 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_itx.c +++ b/arch/powerpc/platforms/83xx/mpc834x_itx.c @@ -66,6 +66,5 @@ define_machine(mpc834x_itx) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c index 8e45c034daaf..d08974a60848 100644 --- a/arch/powerpc/platforms/83xx/mpc834x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc834x_mds.c @@ -88,6 +88,5 @@ define_machine(mpc834x_mds) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 4ae2b6e4b513..84c08fdf503c 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -197,6 +197,5 @@ define_machine(mpc836x_mds) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c index 231a5df0399b..1fc9d1235a7c 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c +++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c @@ -37,6 +37,5 @@ define_machine(mpc836x_rdk) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c index 0c10100756d4..c2055ef35b63 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c @@ -90,6 +90,5 @@ define_machine(mpc837x_mds) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c index 5d48c6842098..39e78018dd0b 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c @@ -78,6 +78,5 @@ define_machine(mpc837x_rdb) { .get_irq = ipic_get_irq, .restart = mpc83xx_restart, .time_init = mpc83xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c index 902a867352c2..a029aa090538 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_qds.c +++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c @@ -59,6 +59,5 @@ define_machine(bsc9132_qds) { .pcibios_fixup_bus = fsl_pcibios_fixup_bus, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c index 58a44953b936..361b4371d073 100644 --- a/arch/powerpc/platforms/85xx/bsc913x_rdb.c +++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c @@ -46,6 +46,5 @@ define_machine(bsc9131_rdb) { .setup_arch = bsc913x_rdb_setup_arch, .init_IRQ = bsc913x_rdb_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/c293pcie.c b/arch/powerpc/platforms/85xx/c293pcie.c index fbf1875e5835..34975708be79 100644 --- a/arch/powerpc/platforms/85xx/c293pcie.c +++ b/arch/powerpc/platforms/85xx/c293pcie.c @@ -51,6 +51,5 @@ define_machine(c293_pcie) { .setup_arch = c293_pcie_setup_arch, .init_IRQ = c293_pcie_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 2c539de2d629..bfde391c42f4 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -198,7 +198,6 @@ define_machine(corenet_generic) { #else .get_irq = mpic_get_coreint_irq, #endif - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, .power_save = e500_idle, }; diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c index 1bfd4ea13038..3678a1fbf5ad 100644 --- a/arch/powerpc/platforms/85xx/ge_imp3a.c +++ b/arch/powerpc/platforms/85xx/ge_imp3a.c @@ -203,6 +203,5 @@ define_machine(ge_imp3a) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c index 548d478e5194..af38c3aec042 100644 --- a/arch/powerpc/platforms/85xx/ksi8560.c +++ b/arch/powerpc/platforms/85xx/ksi8560.c @@ -180,5 +180,4 @@ define_machine(ksi8560) { .show_cpuinfo = ksi8560_show_cpuinfo, .get_irq = mpic_get_irq, .restart = machine_restart, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c index 9900cf2cd392..58ab3831913f 100644 --- a/arch/powerpc/platforms/85xx/mpc8536_ds.c +++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c @@ -62,6 +62,5 @@ define_machine(mpc8536_ds) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c index dd5302ab406d..7c67438e76f8 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c @@ -158,6 +158,5 @@ define_machine(mpc85xx_ads) { .init_IRQ = mpc85xx_ads_pic_init, .show_cpuinfo = mpc85xx_ads_show_cpuinfo, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c index d7568b35ec78..0e6964c7fdd6 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c @@ -383,6 +383,5 @@ define_machine(mpc85xx_cds) { .pcibios_fixup_bus = mpc85xx_cds_fixup_bus, .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index b4feb251b57e..70167b8f00a3 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -172,7 +172,6 @@ define_machine(mpc8544_ds) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -186,7 +185,6 @@ define_machine(mpc8572_ds) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -200,6 +198,5 @@ define_machine(p2020_ds) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 721322e04c79..28a04928250f 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -345,7 +345,6 @@ define_machine(mpc8568_mds) { .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, @@ -359,7 +358,6 @@ define_machine(mpc8569_mds) { .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, @@ -373,7 +371,6 @@ define_machine(p1021_mds) { .setup_arch = mpc85xx_mds_setup_arch, .init_IRQ = mpc85xx_mds_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index 9754feaebcd4..aa24793ad25c 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -129,7 +129,6 @@ define_machine(p2020_rdb) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -143,7 +142,6 @@ define_machine(p1020_rdb) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -157,7 +155,6 @@ define_machine(p1021_rdb_pc) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -171,7 +168,6 @@ define_machine(p2020_rdb_pc) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -185,7 +181,6 @@ define_machine(p1025_rdb) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -199,7 +194,6 @@ define_machine(p1020_mbg_pc) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -213,7 +207,6 @@ define_machine(p1020_utm_pc) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -227,7 +220,6 @@ define_machine(p1020_rdb_pc) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -241,7 +233,6 @@ define_machine(p1020_rdb_pd) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -255,6 +246,5 @@ define_machine(p1024_rdb) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c index ee1383e811d9..1b59e45a0c64 100644 --- a/arch/powerpc/platforms/85xx/mvme2500.c +++ b/arch/powerpc/platforms/85xx/mvme2500.c @@ -53,6 +53,5 @@ define_machine(mvme2500) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c index 8ba9306a96b6..14ec79a32746 100644 --- a/arch/powerpc/platforms/85xx/p1010rdb.c +++ b/arch/powerpc/platforms/85xx/p1010rdb.c @@ -73,6 +73,5 @@ define_machine(p1010_rdb) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 15a684ce9201..23d0926298b9 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -559,6 +559,5 @@ define_machine(p1022_ds) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c index aee9ffc0eb17..d1159150c3b5 100644 --- a/arch/powerpc/platforms/85xx/p1022_rdk.c +++ b/arch/powerpc/platforms/85xx/p1022_rdk.c @@ -139,6 +139,5 @@ define_machine(p1022_rdk) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/p1023_rdb.c b/arch/powerpc/platforms/85xx/p1023_rdb.c index e199fc44fc2f..9df0439a9382 100644 --- a/arch/powerpc/platforms/85xx/p1023_rdb.c +++ b/arch/powerpc/platforms/85xx/p1023_rdb.c @@ -100,7 +100,6 @@ define_machine(p1023_rdb) { .setup_arch = p1023_rdb_setup_arch, .init_IRQ = p1023_rdb_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/85xx/ppa8548.c b/arch/powerpc/platforms/85xx/ppa8548.c index b030d0e7b06b..acd19c52ad43 100644 --- a/arch/powerpc/platforms/85xx/ppa8548.c +++ b/arch/powerpc/platforms/85xx/ppa8548.c @@ -79,6 +79,5 @@ define_machine(ppa8548) { .init_IRQ = ppa8548_pic_init, .show_cpuinfo = ppa8548_show_cpuinfo, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index 335815a2d121..6e4b1ddf292b 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -58,7 +58,6 @@ define_machine(qemu_e500) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_coreint_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, .power_save = e500_idle, }; diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c index f603a3905801..9fa1338bc002 100644 --- a/arch/powerpc/platforms/85xx/socrates.c +++ b/arch/powerpc/platforms/85xx/socrates.c @@ -75,6 +75,5 @@ define_machine(socrates) { .setup_arch = socrates_setup_arch, .init_IRQ = socrates_pic_init, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c index 9f37b25e7a82..5e2646b4c039 100644 --- a/arch/powerpc/platforms/85xx/stx_gp3.c +++ b/arch/powerpc/platforms/85xx/stx_gp3.c @@ -90,6 +90,5 @@ define_machine(stx_gp3) { .init_IRQ = stx_gp3_pic_init, .show_cpuinfo = stx_gp3_show_cpuinfo, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c index d187f4b8bff6..80effb028bf4 100644 --- a/arch/powerpc/platforms/85xx/tqm85xx.c +++ b/arch/powerpc/platforms/85xx/tqm85xx.c @@ -127,6 +127,5 @@ define_machine(tqm85xx) { .init_IRQ = tqm85xx_pic_init, .show_cpuinfo = tqm85xx_show_cpuinfo, .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c index 34b1e9cf9f34..b88e23a334a4 100644 --- a/arch/powerpc/platforms/85xx/twr_p102x.c +++ b/arch/powerpc/platforms/85xx/twr_p102x.c @@ -112,6 +112,5 @@ define_machine(twr_p1025) { .pcibios_fixup_bus = fsl_pcibios_fixup_bus, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index 57c38a8f40e8..184013e6601e 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -146,7 +146,6 @@ define_machine(xes_mpc8572) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -160,7 +159,6 @@ define_machine(xes_mpc8548) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; @@ -174,6 +172,5 @@ define_machine(xes_mpc8540) { .pcibios_fixup_phb = fsl_pcibios_fixup_phb, #endif .get_irq = mpic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c index 2b656a763537..f0512e51300c 100644 --- a/arch/powerpc/platforms/86xx/gef_ppc9a.c +++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c @@ -185,7 +185,6 @@ define_machine(gef_ppc9a) { .show_cpuinfo = gef_ppc9a_show_cpuinfo, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c index f38ab6bdfeb5..1430b524d982 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc310.c +++ b/arch/powerpc/platforms/86xx/gef_sbc310.c @@ -172,7 +172,6 @@ define_machine(gef_sbc310) { .show_cpuinfo = gef_sbc310_show_cpuinfo, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c index 09d59f92eaac..c92af0d964e1 100644 --- a/arch/powerpc/platforms/86xx/gef_sbc610.c +++ b/arch/powerpc/platforms/86xx/gef_sbc610.c @@ -162,7 +162,6 @@ define_machine(gef_sbc610) { .show_cpuinfo = gef_sbc610_show_cpuinfo, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c index 22ec5d7dc09d..6a403705ae44 100644 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c @@ -314,7 +314,6 @@ define_machine(mpc86xx_hpcd) { .init_IRQ = mpc86xx_init_irq, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 61eccb2d689d..7b00ebd2d7f8 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -107,7 +107,6 @@ define_machine(mpc86xx_hpcn) { .show_cpuinfo = mpc86xx_hpcn_show_cpuinfo, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/86xx/mvme7100.c b/arch/powerpc/platforms/86xx/mvme7100.c index b2cc32a32d0b..c0ac40514361 100644 --- a/arch/powerpc/platforms/86xx/mvme7100.c +++ b/arch/powerpc/platforms/86xx/mvme7100.c @@ -108,7 +108,6 @@ define_machine(mvme7100) { .init_IRQ = mpc86xx_init_irq, .get_irq = mpic_get_irq, .time_init = mpc86xx_time_init, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c index 68bb0da3d3ee..7e83eb6746f4 100644 --- a/arch/powerpc/platforms/8xx/adder875.c +++ b/arch/powerpc/platforms/8xx/adder875.c @@ -102,6 +102,5 @@ define_machine(adder875) { .init_IRQ = mpc8xx_pic_init, .get_irq = mpc8xx_get_irq, .restart = mpc8xx_restart, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c index ba3b4a5688fb..6c6e714a7521 100644 --- a/arch/powerpc/platforms/amigaone/setup.c +++ b/arch/powerpc/platforms/amigaone/setup.c @@ -164,6 +164,5 @@ define_machine(amigaone) { .show_cpuinfo = amigaone_show_cpuinfo, .init_IRQ = amigaone_init_IRQ, .restart = amigaone_restart, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 47eaf75349f2..9e07d101bcee 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -265,7 +265,6 @@ define_machine(cell) { .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, .progress = cell_progress, .init_IRQ = cell_init_irq, .pci_setup_phb = cell_setup_phb, diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index d9049ceb1046..36ee3a5056a1 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -582,6 +582,5 @@ define_machine(chrp) { .time_init = chrp_time_init, .set_rtc_time = chrp_set_rtc_time, .get_rtc_time = chrp_get_rtc_time, - .calibrate_decr = generic_calibrate_decr, .phys_mem_access_prot = pci_phys_mem_access_prot, }; diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c index 60cdc2852c7a..e3b2c7464732 100644 --- a/arch/powerpc/platforms/embedded6xx/gamecube.c +++ b/arch/powerpc/platforms/embedded6xx/gamecube.c @@ -70,7 +70,6 @@ define_machine(gamecube) { .halt = gamecube_halt, .init_IRQ = flipper_pic_probe, .get_irq = flipper_pic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, .machine_shutdown = gamecube_shutdown, }; diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index 67949c85c398..a167ee88fbf9 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -264,7 +264,6 @@ define_machine(holly){ .show_cpuinfo = holly_show_cpuinfo, .get_irq = mpic_get_irq, .restart = holly_restart, - .calibrate_decr = generic_calibrate_decr, .machine_check_exception = ppc750_machine_check_exception, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index f04fd234c9ab..9c10aac40c7b 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -159,5 +159,4 @@ define_machine(linkstation){ .get_irq = mpic_get_irq, .restart = linkstation_restart, .halt = linkstation_halt, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 6821fb6644ac..ec93d69dc0ee 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -182,7 +182,6 @@ define_machine(mpc7448_hpc2){ .show_cpuinfo = mpc7448_hpc2_show_cpuinfo, .get_irq = mpic_get_irq, .restart = mpc7448_hpc2_restart, - .calibrate_decr = generic_calibrate_decr, .machine_check_exception= mpc7448_machine_check_exception, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c index 7e57de576ef7..00bec0f051be 100644 --- a/arch/powerpc/platforms/embedded6xx/mvme5100.c +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -204,6 +204,5 @@ define_machine(mvme5100) { .show_cpuinfo = mvme5100_show_cpuinfo, .get_irq = mpic_get_irq, .restart = mvme5100_restart, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, }; diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index ab85af37117f..e49880e8dab8 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -118,5 +118,4 @@ define_machine(storcenter){ .init_IRQ = storcenter_init_IRQ, .get_irq = mpic_get_irq, .restart = storcenter_restart, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 635c393d307a..b54382a8ccc6 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -175,7 +175,6 @@ define_machine(wii) { .halt = wii_halt, .init_IRQ = wii_pic_probe, .get_irq = flipper_pic_get_irq, - .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, .machine_shutdown = wii_shutdown, }; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 98c8e3603064..40618513e3f5 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -357,7 +357,6 @@ define_machine(maple) { .get_boot_time = maple_get_boot_time, .set_rtc_time = maple_set_rtc_time, .get_rtc_time = maple_get_rtc_time, - .calibrate_decr = generic_calibrate_decr, .progress = maple_progress, .power_save = power4_idle, }; diff --git a/arch/powerpc/platforms/microwatt/setup.c b/arch/powerpc/platforms/microwatt/setup.c index f08edcde7bee..5e1c0997170d 100644 --- a/arch/powerpc/platforms/microwatt/setup.c +++ b/arch/powerpc/platforms/microwatt/setup.c @@ -40,5 +40,4 @@ define_machine(microwatt) { .init_IRQ = microwatt_init_IRQ, .setup_arch = microwatt_setup_arch, .progress = udbg_progress, - .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c index 2aef49e04dd4..5c5b4a034f9e 100644 --- a/arch/powerpc/platforms/pasemi/setup.c +++ b/arch/powerpc/platforms/pasemi/setup.c @@ -449,7 +449,6 @@ define_machine(pasemi) { .get_irq = mpic_get_irq, .restart = pas_restart, .get_boot_time = pas_get_boot_time, - .calibrate_decr = generic_calibrate_decr, .progress = pas_progress, .machine_check_exception = pas_machine_check_handler, }; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index f89731670448..5e9c6b55809f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -585,7 +585,6 @@ define_machine(powernv) { .progress = pnv_progress, .machine_shutdown = pnv_shutdown, .power_save = NULL, - .calibrate_decr = generic_calibrate_decr, .machine_check_early = pnv_machine_check_early, #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 94a7617eb044..e2a57cfa6c83 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1138,7 +1138,6 @@ define_machine(pseries) { .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, - .calibrate_decr = generic_calibrate_decr, .progress = rtas_progress, .system_reset_exception = pSeries_system_reset_exception, .machine_check_early = pseries_machine_check_realmode, -- GitLab From 644f17412f5acf01a19af9d04a921937a2bc86c6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 23 Feb 2023 19:27:03 -0800 Subject: [PATCH 0564/5631] IMA: allow/fix UML builds UML supports HAS_IOMEM since 0bbadafdc49d (um: allow disabling NO_IOMEM). Current IMA build on UML fails on allmodconfig (with TCG_TPM=m): ld: security/integrity/ima/ima_queue.o: in function `ima_add_template_entry': ima_queue.c:(.text+0x2d9): undefined reference to `tpm_pcr_extend' ld: security/integrity/ima/ima_init.o: in function `ima_init': ima_init.c:(.init.text+0x43f): undefined reference to `tpm_default_chip' ld: security/integrity/ima/ima_crypto.o: in function `ima_calc_boot_aggregate_tfm': ima_crypto.c:(.text+0x1044): undefined reference to `tpm_pcr_read' ld: ima_crypto.c:(.text+0x10d8): undefined reference to `tpm_pcr_read' Modify the IMA Kconfig entry so that it selects TCG_TPM if HAS_IOMEM is set, regardless of the UML Kconfig setting. This updates TCG_TPM from =m to =y and fixes the linker errors. Fixes: f4a0391dfa91 ("ima: fix Kconfig dependencies") Cc: Stable # v5.14+ Signed-off-by: Randy Dunlap Cc: Fabio Estevam Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Cc: linux-um@lists.infradead.org Signed-off-by: Mimi Zohar --- security/integrity/ima/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 39caeca47444..60a511c6b583 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -8,7 +8,7 @@ config IMA select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_HASH_INFO - select TCG_TPM if HAS_IOMEM && !UML + select TCG_TPM if HAS_IOMEM select TCG_TIS if TCG_TPM && X86 select TCG_CRB if TCG_TPM && ACPI select TCG_IBMVTPM if TCG_TPM && PPC_PSERIES -- GitLab From 1bf088a9f0e50acd175ba8deef0db11c099fa26e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 15 Mar 2023 18:30:48 +0100 Subject: [PATCH 0565/5631] clk: qcom: gcc-qcm2290: Fix up gcc_sdcc2_apps_clk_src Add the PARENT_ENABLE flag to prevent the clock from getting stuck at boot and use floor_ops to avoid SDHCI overclocking. Fixes: 496d1a13d405 ("clk: qcom: Add Global Clock Controller driver for QCM2290") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230315173048.3497655-1-konrad.dybcio@linaro.org --- drivers/clk/qcom/gcc-qcm2290.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-qcm2290.c b/drivers/clk/qcom/gcc-qcm2290.c index 7792b8f23704..096deff2ba25 100644 --- a/drivers/clk/qcom/gcc-qcm2290.c +++ b/drivers/clk/qcom/gcc-qcm2290.c @@ -1243,7 +1243,8 @@ static struct clk_rcg2 gcc_sdcc2_apps_clk_src = { .name = "gcc_sdcc2_apps_clk_src", .parent_data = gcc_parents_12, .num_parents = ARRAY_SIZE(gcc_parents_12), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, + .flags = CLK_OPS_PARENT_ENABLE, }, }; -- GitLab From 54ed70b57623e18f6c18f510cbe1e741bca89f34 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 15 Mar 2023 11:56:30 -0400 Subject: [PATCH 0566/5631] clk: qcom: remove unused variables gpucc_parent_data,map_2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 reports these errors drivers/clk/qcom/gpucc-sm6375.c:145:37: error: ‘gpucc_parent_data_2’ defined but not used [-Werror=unused-const-variable=] 145 | static const struct clk_parent_data gpucc_parent_data_2[] = { | ^~~~~~~~~~~~~~~~~~~ drivers/clk/qcom/gpucc-sm6375.c:139:32: error: ‘gpucc_parent_map_2’ defined but not used [-Werror=unused-const-variable=] 139 | static const struct parent_map gpucc_parent_map_2[] = { | ^~~~~~~~~~~~~~~~~~ These variables are not used, so remove them. Signed-off-by: Tom Rix Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230315155630.1740065-1-trix@redhat.com --- drivers/clk/qcom/gpucc-sm6375.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/drivers/clk/qcom/gpucc-sm6375.c b/drivers/clk/qcom/gpucc-sm6375.c index eb9ffa956950..d8f4c4b59f1b 100644 --- a/drivers/clk/qcom/gpucc-sm6375.c +++ b/drivers/clk/qcom/gpucc-sm6375.c @@ -136,18 +136,6 @@ static const struct clk_parent_data gpucc_parent_data_1[] = { { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, }; -static const struct parent_map gpucc_parent_map_2[] = { - { P_BI_TCXO, 0 }, - { P_GCC_GPU_GPLL0_CLK_SRC, 5 }, - { P_GCC_GPU_GPLL0_DIV_CLK_SRC, 6 }, -}; - -static const struct clk_parent_data gpucc_parent_data_2[] = { - { .index = P_BI_TCXO }, - { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, - { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, -}; - static const struct freq_tbl ftbl_gpucc_gmu_clk_src[] = { F(200000000, P_GCC_GPU_GPLL0_DIV_CLK_SRC, 1.5, 0, 0), { } -- GitLab From 322b72e0fd10101f2da8985b31b4af70f184bf79 Mon Sep 17 00:00:00 2001 From: Peter Newman Date: Tue, 20 Dec 2022 17:41:32 +0100 Subject: [PATCH 0567/5631] x86/resctrl: Avoid redundant counter read in __mon_event_count() __mon_event_count() does the per-RMID, per-domain work for user-initiated event count reads and the initialization of new monitor groups. In the initialization case, after resctrl_arch_reset_rmid() calls __rmid_read() to record an initial count for a new monitor group, it immediately calls resctrl_arch_rmid_read(). This re-read of the hardware counter is unnecessary and the following computations are ignored by the caller during initialization. Following return from resctrl_arch_reset_rmid(), just clear the mbm_state and return. This involves moving the mbm_state lookup into the rr->first case, as it's not needed for regular event count reads: the QOS_L3_OCCUP_EVENT_ID case was redundant with the accumulating logic at the end of the function. Signed-off-by: Peter Newman Signed-off-by: Dave Hansen Reviewed-by: Reinette Chatre Tested-by: Babu Moger Link: https://lore.kernel.org/all/20221220164132.443083-2-peternewman%40google.com --- arch/x86/kernel/cpu/resctrl/monitor.c | 43 ++++++++++++--------------- 1 file changed, 19 insertions(+), 24 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 7fe51488e136..20952419be75 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -383,41 +383,36 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } +static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid, + enum resctrl_event_id evtid) +{ + switch (evtid) { + case QOS_L3_MBM_TOTAL_EVENT_ID: + return &d->mbm_total[rmid]; + case QOS_L3_MBM_LOCAL_EVENT_ID: + return &d->mbm_local[rmid]; + default: + return NULL; + } +} + static int __mon_event_count(u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 tval = 0; - if (rr->first) + if (rr->first) { resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid); + m = get_mbm_state(rr->d, rmid, rr->evtid); + if (m) + memset(m, 0, sizeof(struct mbm_state)); + return 0; + } rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval); if (rr->err) return rr->err; - switch (rr->evtid) { - case QOS_L3_OCCUP_EVENT_ID: - rr->val += tval; - return 0; - case QOS_L3_MBM_TOTAL_EVENT_ID: - m = &rr->d->mbm_total[rmid]; - break; - case QOS_L3_MBM_LOCAL_EVENT_ID: - m = &rr->d->mbm_local[rmid]; - break; - default: - /* - * Code would never reach here because an invalid - * event id would fail in resctrl_arch_rmid_read(). - */ - return -EINVAL; - } - - if (rr->first) { - memset(m, 0, sizeof(struct mbm_state)); - return 0; - } - rr->val += tval; return 0; -- GitLab From e47a4f55f240db3913317f34a9c685b5d85538f1 Mon Sep 17 00:00:00 2001 From: Varadarajan Narayanan Date: Tue, 7 Mar 2023 11:52:24 +0530 Subject: [PATCH 0568/5631] clk: qcom: clk-alpha-pll: Add support for Stromer PLLs Add programming sequence support for managing the Stromer PLLs. Reviewed-by: Stephen Boyd Co-developed-by: Sricharan R Signed-off-by: Sricharan R Signed-off-by: Varadarajan Narayanan Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307062232.4889-2-quic_kathirav@quicinc.com --- drivers/clk/qcom/clk-alpha-pll.c | 128 ++++++++++++++++++++++++++++++- drivers/clk/qcom/clk-alpha-pll.h | 13 +++- 2 files changed, 139 insertions(+), 2 deletions(-) diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index e266379427f2..14f9436b62fc 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2021, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021, 2023, Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -204,6 +204,18 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = { [PLL_OFF_CONFIG_CTL] = 0x1C, [PLL_OFF_STATUS] = 0x20, }, + [CLK_ALPHA_PLL_TYPE_STROMER] = { + [PLL_OFF_L_VAL] = 0x08, + [PLL_OFF_ALPHA_VAL] = 0x10, + [PLL_OFF_ALPHA_VAL_U] = 0x14, + [PLL_OFF_USER_CTL] = 0x18, + [PLL_OFF_USER_CTL_U] = 0x1c, + [PLL_OFF_CONFIG_CTL] = 0x20, + [PLL_OFF_CONFIG_CTL_U] = 0xff, + [PLL_OFF_TEST_CTL] = 0x30, + [PLL_OFF_TEST_CTL_U] = 0x34, + [PLL_OFF_STATUS] = 0x28, + }, }; EXPORT_SYMBOL_GPL(clk_alpha_pll_regs); @@ -215,6 +227,8 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_regs); #define ALPHA_BITWIDTH 32U #define ALPHA_SHIFT(w) min(w, ALPHA_BITWIDTH) +#define ALPHA_PLL_STATUS_REG_SHIFT 8 + #define PLL_HUAYRA_M_WIDTH 8 #define PLL_HUAYRA_M_SHIFT 8 #define PLL_HUAYRA_M_MASK 0xff @@ -2329,3 +2343,115 @@ const struct clk_ops clk_alpha_pll_rivian_evo_ops = { .round_rate = clk_rivian_evo_pll_round_rate, }; EXPORT_SYMBOL_GPL(clk_alpha_pll_rivian_evo_ops); + +void clk_stromer_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config) +{ + u32 val, val_u, mask, mask_u; + + regmap_write(regmap, PLL_L_VAL(pll), config->l); + regmap_write(regmap, PLL_ALPHA_VAL(pll), config->alpha); + regmap_write(regmap, PLL_CONFIG_CTL(pll), config->config_ctl_val); + + if (pll_has_64bit_config(pll)) + regmap_write(regmap, PLL_CONFIG_CTL_U(pll), + config->config_ctl_hi_val); + + if (pll_alpha_width(pll) > 32) + regmap_write(regmap, PLL_ALPHA_VAL_U(pll), config->alpha_hi); + + val = config->main_output_mask; + val |= config->aux_output_mask; + val |= config->aux2_output_mask; + val |= config->early_output_mask; + val |= config->pre_div_val; + val |= config->post_div_val; + val |= config->vco_val; + val |= config->alpha_en_mask; + val |= config->alpha_mode_mask; + + mask = config->main_output_mask; + mask |= config->aux_output_mask; + mask |= config->aux2_output_mask; + mask |= config->early_output_mask; + mask |= config->pre_div_mask; + mask |= config->post_div_mask; + mask |= config->vco_mask; + mask |= config->alpha_en_mask; + mask |= config->alpha_mode_mask; + + regmap_update_bits(regmap, PLL_USER_CTL(pll), mask, val); + + /* Stromer APSS PLL does not enable LOCK_DET by default, so enable it */ + val_u = config->status_val << ALPHA_PLL_STATUS_REG_SHIFT; + val_u |= config->lock_det; + + mask_u = config->status_mask; + mask_u |= config->lock_det; + + regmap_update_bits(regmap, PLL_USER_CTL_U(pll), mask_u, val_u); + regmap_write(regmap, PLL_TEST_CTL(pll), config->test_ctl_val); + regmap_write(regmap, PLL_TEST_CTL_U(pll), config->test_ctl_hi_val); + + if (pll->flags & SUPPORTS_FSM_MODE) + qcom_pll_set_fsm_mode(regmap, PLL_MODE(pll), 6, 0); +} +EXPORT_SYMBOL_GPL(clk_stromer_pll_configure); + +static int clk_alpha_pll_stromer_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + u32 l; + u64 a; + + req->rate = alpha_pll_round_rate(req->rate, req->best_parent_rate, + &l, &a, ALPHA_REG_BITWIDTH); + + return 0; +} + +static int clk_alpha_pll_stromer_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long prate) +{ + struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); + int ret; + u32 l; + u64 a; + + rate = alpha_pll_round_rate(rate, prate, &l, &a, ALPHA_REG_BITWIDTH); + + regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); + regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL_U(pll), + a >> ALPHA_BITWIDTH); + + regmap_update_bits(pll->clkr.regmap, PLL_USER_CTL(pll), + PLL_ALPHA_EN, PLL_ALPHA_EN); + + if (!clk_hw_is_enabled(hw)) + return 0; + + /* + * Stromer PLL supports Dynamic programming. + * It allows the PLL frequency to be changed on-the-fly without first + * execution of a shutdown procedure followed by a bring up procedure. + */ + regmap_update_bits(pll->clkr.regmap, PLL_MODE(pll), PLL_UPDATE, + PLL_UPDATE); + + ret = wait_for_pll_update(pll); + if (ret) + return ret; + + return wait_for_pll_enable_lock(pll); +} + +const struct clk_ops clk_alpha_pll_stromer_ops = { + .enable = clk_alpha_pll_enable, + .disable = clk_alpha_pll_disable, + .is_enabled = clk_alpha_pll_is_enabled, + .recalc_rate = clk_alpha_pll_recalc_rate, + .determine_rate = clk_alpha_pll_stromer_determine_rate, + .set_rate = clk_alpha_pll_stromer_set_rate, +}; +EXPORT_SYMBOL_GPL(clk_alpha_pll_stromer_ops); diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h index c67cfda27ecb..ff25c7f7b43e 100644 --- a/drivers/clk/qcom/clk-alpha-pll.h +++ b/drivers/clk/qcom/clk-alpha-pll.h @@ -1,5 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved. */ +/* + * Copyright (c) 2015, 2018, 2021 The Linux Foundation. All rights reserved. + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + #ifndef __QCOM_CLK_ALPHA_PLL_H__ #define __QCOM_CLK_ALPHA_PLL_H__ @@ -22,6 +26,7 @@ enum { CLK_ALPHA_PLL_TYPE_RIVIAN_EVO, CLK_ALPHA_PLL_TYPE_DEFAULT_EVO, CLK_ALPHA_PLL_TYPE_BRAMMO_EVO, + CLK_ALPHA_PLL_TYPE_STROMER, CLK_ALPHA_PLL_TYPE_MAX, }; @@ -131,6 +136,9 @@ struct alpha_pll_config { u32 post_div_mask; u32 vco_val; u32 vco_mask; + u32 status_val; + u32 status_mask; + u32 lock_det; }; extern const struct clk_ops clk_alpha_pll_ops; @@ -139,6 +147,7 @@ extern const struct clk_ops clk_alpha_pll_hwfsm_ops; extern const struct clk_ops clk_alpha_pll_postdiv_ops; extern const struct clk_ops clk_alpha_pll_huayra_ops; extern const struct clk_ops clk_alpha_pll_postdiv_ro_ops; +extern const struct clk_ops clk_alpha_pll_stromer_ops; extern const struct clk_ops clk_alpha_pll_fabia_ops; extern const struct clk_ops clk_alpha_pll_fixed_fabia_ops; @@ -188,5 +197,7 @@ void clk_lucid_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regma const struct alpha_pll_config *config); void clk_rivian_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); +void clk_stromer_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config); #endif -- GitLab From 0d6fd7f8b8f8fdb090f0ef61573f5648c19ff237 Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Tue, 7 Mar 2023 11:52:25 +0530 Subject: [PATCH 0569/5631] clk: qcom: Add STROMER PLUS PLL type for IPQ5332 Add the support for stromer plus pll, which is found on the IPQ5332 SoCs. Programming sequence is same as the stromer pll, so we can re-use the same. Reviewed-by: Stephen Boyd Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307062232.4889-3-quic_kathirav@quicinc.com --- drivers/clk/qcom/clk-alpha-pll.c | 11 +++++++++++ drivers/clk/qcom/clk-alpha-pll.h | 1 + 2 files changed, 12 insertions(+) diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index 14f9436b62fc..b9f6535a7ba7 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -216,6 +216,17 @@ const u8 clk_alpha_pll_regs[][PLL_OFF_MAX_REGS] = { [PLL_OFF_TEST_CTL_U] = 0x34, [PLL_OFF_STATUS] = 0x28, }, + [CLK_ALPHA_PLL_TYPE_STROMER_PLUS] = { + [PLL_OFF_L_VAL] = 0x04, + [PLL_OFF_USER_CTL] = 0x08, + [PLL_OFF_USER_CTL_U] = 0x0c, + [PLL_OFF_CONFIG_CTL] = 0x10, + [PLL_OFF_TEST_CTL] = 0x14, + [PLL_OFF_TEST_CTL_U] = 0x18, + [PLL_OFF_STATUS] = 0x1c, + [PLL_OFF_ALPHA_VAL] = 0x24, + [PLL_OFF_ALPHA_VAL_U] = 0x28, + }, }; EXPORT_SYMBOL_GPL(clk_alpha_pll_regs); diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h index ff25c7f7b43e..d07b17186b90 100644 --- a/drivers/clk/qcom/clk-alpha-pll.h +++ b/drivers/clk/qcom/clk-alpha-pll.h @@ -27,6 +27,7 @@ enum { CLK_ALPHA_PLL_TYPE_DEFAULT_EVO, CLK_ALPHA_PLL_TYPE_BRAMMO_EVO, CLK_ALPHA_PLL_TYPE_STROMER, + CLK_ALPHA_PLL_TYPE_STROMER_PLUS, CLK_ALPHA_PLL_TYPE_MAX, }; -- GitLab From 3d89d52970fdbeaf252d9e4f9bd067222d12641d Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Tue, 7 Mar 2023 11:52:27 +0530 Subject: [PATCH 0570/5631] clk: qcom: add Global Clock controller (GCC) driver for IPQ5332 SoC Add support for the global clock controller found on IPQ5332 SoC. PLL used on IPQ5332 is of type Stromer Plus PLL, however the programming sequence is same as Stromer PLL, so lets re-use the Stromer PLL ops. Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307062232.4889-5-quic_kathirav@quicinc.com --- drivers/clk/qcom/Kconfig | 8 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gcc-ipq5332.c | 3813 ++++++++++++++++++++++++++++++++ 3 files changed, 3822 insertions(+) create mode 100644 drivers/clk/qcom/gcc-ipq5332.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 1897ce5c9291..391e7aa35dd7 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -141,6 +141,14 @@ config IPQ_GCC_4019 Say Y if you want to use peripheral devices such as UART, SPI, i2c, USB, SD/eMMC, etc. +config IPQ_GCC_5332 + tristate "IPQ5332 Global Clock Controller" + depends on ARM64 || COMPILE_TEST + help + Support for the global clock controller on ipq5332 devices. + Say Y if you want to use peripheral devices such as UART, SPI, + i2c, USB, SD/eMMC, etc. + config IPQ_GCC_6018 tristate "IPQ6018 Global Clock Controller" help diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 04d97a3297e2..3dd4648f5093 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_CLK_GFM_LPASS_SM8250) += lpass-gfm-sm8250.o obj-$(CONFIG_IPQ_APSS_PLL) += apss-ipq-pll.o obj-$(CONFIG_IPQ_APSS_6018) += apss-ipq6018.o obj-$(CONFIG_IPQ_GCC_4019) += gcc-ipq4019.o +obj-$(CONFIG_IPQ_GCC_5332) += gcc-ipq5332.o obj-$(CONFIG_IPQ_GCC_6018) += gcc-ipq6018.o obj-$(CONFIG_IPQ_GCC_806X) += gcc-ipq806x.o obj-$(CONFIG_IPQ_GCC_8074) += gcc-ipq8074.o diff --git a/drivers/clk/qcom/gcc-ipq5332.c b/drivers/clk/qcom/gcc-ipq5332.c new file mode 100644 index 000000000000..9e4baea33937 --- /dev/null +++ b/drivers/clk/qcom/gcc-ipq5332.c @@ -0,0 +1,3813 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "reset.h" + +enum { + DT_SLEEP_CLK, + DT_XO, + DT_PCIE_2LANE_PHY_PIPE_CLK, + DT_PCIE_2LANE_PHY_PIPE_CLK_X1, + DT_USB_PCIE_WRAPPER_PIPE_CLK, +}; + +enum { + P_PCIE3X2_PIPE, + P_PCIE3X1_0_PIPE, + P_PCIE3X1_1_PIPE, + P_USB3PHY_0_PIPE, + P_CORE_BI_PLL_TEST_SE, + P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, + P_GPLL0_OUT_AUX, + P_GPLL0_OUT_MAIN, + P_GPLL2_OUT_AUX, + P_GPLL2_OUT_MAIN, + P_GPLL4_OUT_AUX, + P_GPLL4_OUT_MAIN, + P_SLEEP_CLK, + P_XO, +}; + +static const struct clk_parent_data gcc_parent_data_xo = { .index = DT_XO }; + +static struct clk_alpha_pll gpll0_main = { + .offset = 0x20000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .clkr = { + .enable_reg = 0xb000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gpll0_main", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_alpha_pll_stromer_ops, + }, + }, +}; + +static struct clk_fixed_factor gpll0_div2 = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gpll0_div2", + .parent_hws = (const struct clk_hw *[]) { + &gpll0_main.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_alpha_pll_postdiv gpll0 = { + .offset = 0x20000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll0", + .parent_hws = (const struct clk_hw *[]) { + &gpll0_main.clkr.hw }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ro_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_alpha_pll gpll2_main = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .clkr = { + .enable_reg = 0xb000, + .enable_mask = BIT(1), + .hw.init = &(const struct clk_init_data) { + .name = "gpll2", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_alpha_pll_stromer_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll2 = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll2_main", + .parent_hws = (const struct clk_hw *[]) { + &gpll2_main.clkr.hw }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ro_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_alpha_pll gpll4_main = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .clkr = { + .enable_reg = 0xb000, + .enable_mask = BIT(2), + .hw.init = &(const struct clk_init_data) { + .name = "gpll4_main", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_alpha_pll_stromer_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll4 = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll4", + .parent_hws = (const struct clk_hw *[]) { + &gpll4_main.clkr.hw }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ro_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static const struct parent_map gcc_parent_map_xo[] = { + { P_XO, 0 }, +}; + +static const struct parent_map gcc_parent_map_0[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, +}; + +static const struct clk_parent_data gcc_parent_data_0[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_div2.hw }, +}; + +static const struct parent_map gcc_parent_map_1[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, +}; + +static const struct clk_parent_data gcc_parent_data_1[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_2[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL4_OUT_MAIN, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_2[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_3[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_3[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_div2.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_4[] = { + { P_XO, 0 }, + { P_GPLL4_OUT_MAIN, 1 }, + { P_GPLL0_OUT_AUX, 2 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, +}; + +static const struct clk_parent_data gcc_parent_data_4[] = { + { .index = DT_XO }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_div2.hw }, +}; + +static const struct parent_map gcc_parent_map_5[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL2_OUT_AUX, 2 }, + { P_GPLL4_OUT_AUX, 3 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, + { P_GPLL0_OUT_AUX, 5 }, +}; + +static const struct clk_parent_data gcc_parent_data_5[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0_div2.hw }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_6[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL0_OUT_AUX, 2 }, + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_6[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_7[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL2_OUT_AUX, 2 }, + { P_GPLL4_OUT_AUX, 3 }, + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_7[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_8[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL2_OUT_AUX, 2 }, +}; + +static const struct clk_parent_data gcc_parent_data_8[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, +}; + +static const struct parent_map gcc_parent_map_9[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL2_OUT_MAIN, 2 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, +}; + +static const struct clk_parent_data gcc_parent_data_9[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, + { .hw = &gpll0_div2.hw }, +}; + +static const struct parent_map gcc_parent_map_10[] = { + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_10[] = { + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_11[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_MAIN, 1 }, + { P_GPLL4_OUT_MAIN, 2 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 3 }, +}; + +static const struct clk_parent_data gcc_parent_data_11[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0_div2.hw }, +}; + +static const struct parent_map gcc_parent_map_12[] = { + { P_XO, 0 }, + { P_GPLL0_OUT_AUX, 2 }, + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_parent_data_12[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_parent_map_13[] = { + { P_XO, 0 }, + { P_GPLL4_OUT_AUX, 1 }, + { P_GPLL0_OUT_MAIN, 3 }, + { P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 4 }, +}; + +static const struct clk_parent_data gcc_parent_data_13[] = { + { .index = DT_XO }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_div2.hw }, +}; + +static const struct freq_tbl ftbl_gcc_adss_pwm_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_adss_pwm_clk_src = { + .cmd_rcgr = 0x1c004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_adss_pwm_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_adss_pwm_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_apss_axi_clk_src[] = { + F(480000000, P_GPLL4_OUT_MAIN, 2.5, 0, 0), + F(533333333, P_GPLL0_OUT_MAIN, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_apss_axi_clk_src = { + .cmd_rcgr = 0x24004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_5, + .freq_tbl = ftbl_gcc_apss_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_apss_axi_clk_src", + .parent_data = gcc_parent_data_5, + .num_parents = ARRAY_SIZE(gcc_parent_data_5), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_blsp1_qup1_spi_apps_clk_src[] = { + F(960000, P_XO, 1, 1, 25), + F(4800000, P_XO, 5, 0, 0), + F(9600000, P_XO, 2.5, 0, 0), + F(16000000, P_GPLL0_OUT_MAIN, 10, 1, 5), + F(24000000, P_XO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_MAIN, 16, 1, 2), + F(50000000, P_GPLL0_OUT_MAIN, 16, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_blsp1_qup1_spi_apps_clk_src = { + .cmd_rcgr = 0x2004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup1_spi_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_blsp1_qup2_spi_apps_clk_src = { + .cmd_rcgr = 0x3004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup2_spi_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_blsp1_qup3_spi_apps_clk_src = { + .cmd_rcgr = 0x4004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_qup1_spi_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup3_spi_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_blsp1_uart1_apps_clk_src[] = { + F(3686400, P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 1, 144, 15625), + F(7372800, P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 1, 288, 15625), + F(14745600, P_GCC_GPLL0_OUT_MAIN_DIV_CLK_SRC, 1, 576, 15625), + F(24000000, P_XO, 1, 0, 0), + F(25000000, P_GPLL0_OUT_MAIN, 16, 1, 2), + F(32000000, P_GPLL0_OUT_MAIN, 1, 1, 25), + F(40000000, P_GPLL0_OUT_MAIN, 1, 1, 20), + F(46400000, P_GPLL0_OUT_MAIN, 1, 29, 500), + F(48000000, P_GPLL0_OUT_MAIN, 1, 3, 50), + F(51200000, P_GPLL0_OUT_MAIN, 1, 8, 125), + F(56000000, P_GPLL0_OUT_MAIN, 1, 7, 100), + F(58982400, P_GPLL0_OUT_MAIN, 1, 1152, 15625), + F(60000000, P_GPLL0_OUT_MAIN, 1, 3, 40), + F(64000000, P_GPLL0_OUT_MAIN, 12.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_blsp1_uart1_apps_clk_src = { + .cmd_rcgr = 0x202c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart1_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_blsp1_uart2_apps_clk_src = { + .cmd_rcgr = 0x302c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart2_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_blsp1_uart3_apps_clk_src = { + .cmd_rcgr = 0x402c, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_blsp1_uart1_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart3_apps_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_gp1_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_gp1_clk_src = { + .cmd_rcgr = 0x8004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_gp2_clk_src = { + .cmd_rcgr = 0x9004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_3, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk_src", + .parent_data = gcc_parent_data_3, + .num_parents = ARRAY_SIZE(gcc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_lpass_sway_clk_src[] = { + F(133333333, P_GPLL0_OUT_MAIN, 6, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_lpass_sway_clk_src = { + .cmd_rcgr = 0x27004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_lpass_sway_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_lpass_sway_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_nss_ts_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_nss_ts_clk_src = { + .cmd_rcgr = 0x17088, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_xo, + .freq_tbl = ftbl_gcc_nss_ts_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_nss_ts_clk_src", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie3x1_0_axi_clk_src[] = { + F(240000000, P_GPLL4_OUT_MAIN, 5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie3x1_0_axi_clk_src = { + .cmd_rcgr = 0x29018, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_pcie3x1_0_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_axi_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_pcie3x1_0_rchg_clk_src = { + .cmd_rcgr = 0x2907c, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_adss_pwm_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_rchg_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_rchg_clk = { + .halt_reg = 0x2907c, + .clkr = { + .enable_reg = 0x2907c, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x1_0_rchg_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_pcie3x1_0_rchg_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 gcc_pcie3x1_1_axi_clk_src = { + .cmd_rcgr = 0x2a004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_pcie3x1_0_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_axi_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_pcie3x1_1_rchg_clk_src = { + .cmd_rcgr = 0x2a078, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_adss_pwm_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_rchg_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_rchg_clk = { + .halt_reg = 0x2a078, + .clkr = { + .enable_reg = 0x2a078, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x1_1_rchg_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_pcie3x1_1_rchg_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie3x2_axi_m_clk_src[] = { + F(266666667, P_GPLL4_OUT_MAIN, 4.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie3x2_axi_m_clk_src = { + .cmd_rcgr = 0x28018, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_pcie3x2_axi_m_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_axi_m_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_pcie3x2_axi_s_clk_src = { + .cmd_rcgr = 0x28084, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_2, + .freq_tbl = ftbl_gcc_pcie3x1_0_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_axi_s_clk_src", + .parent_data = gcc_parent_data_2, + .num_parents = ARRAY_SIZE(gcc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_pcie3x2_rchg_clk_src = { + .cmd_rcgr = 0x28078, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_adss_pwm_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_rchg_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3x2_rchg_clk = { + .halt_reg = 0x28078, + .clkr = { + .enable_reg = 0x28078, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x2_rchg_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_pcie3x2_rchg_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcie_aux_clk_src[] = { + F(2000000, P_XO, 12, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcie_aux_clk_src = { + .cmd_rcgr = 0x28004, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_6, + .freq_tbl = ftbl_gcc_pcie_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie_aux_clk_src", + .parent_data = gcc_parent_data_6, + .num_parents = ARRAY_SIZE(gcc_parent_data_6), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_regmap_phy_mux gcc_pcie3x2_pipe_clk_src = { + .reg = 0x28064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x2_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE_2LANE_PHY_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux gcc_pcie3x1_0_pipe_clk_src = { + .reg = 0x29064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x1_0_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_USB_PCIE_WRAPPER_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux gcc_pcie3x1_1_pipe_clk_src = { + .reg = 0x2a064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3x1_1_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE_2LANE_PHY_PIPE_CLK_X1, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_gcc_pcnoc_bfdcd_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0_OUT_MAIN, 16, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_pcnoc_bfdcd_clk_src = { + .cmd_rcgr = 0x31004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_pcnoc_bfdcd_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_pcnoc_bfdcd_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_q6_axim_clk_src = { + .cmd_rcgr = 0x25004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_7, + .freq_tbl = ftbl_gcc_apss_axi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_axim_clk_src", + .parent_data = gcc_parent_data_7, + .num_parents = ARRAY_SIZE(gcc_parent_data_7), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qdss_at_clk_src[] = { + F(240000000, P_GPLL4_OUT_MAIN, 5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_qdss_at_clk_src = { + .cmd_rcgr = 0x2d004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_qdss_at_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_at_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qdss_tsctr_clk_src[] = { + F(600000000, P_GPLL4_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_qdss_tsctr_clk_src = { + .cmd_rcgr = 0x2d01c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_4, + .freq_tbl = ftbl_gcc_qdss_tsctr_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_tsctr_clk_src", + .parent_data = gcc_parent_data_4, + .num_parents = ARRAY_SIZE(gcc_parent_data_4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_fixed_factor gcc_qdss_tsctr_div2_clk_src = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div2_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_fixed_factor gcc_qdss_tsctr_div3_clk_src = { + .mult = 1, + .div = 3, + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div3_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_fixed_factor gcc_qdss_tsctr_div4_clk_src = { + .mult = 1, + .div = 4, + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div4_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_fixed_factor gcc_qdss_tsctr_div8_clk_src = { + .mult = 1, + .div = 8, + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div8_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_fixed_factor gcc_qdss_tsctr_div16_clk_src = { + .mult = 1, + .div = 16, + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div16_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_qpic_io_macro_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(320000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_qpic_io_macro_clk_src = { + .cmd_rcgr = 0x32004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_8, + .freq_tbl = ftbl_gcc_qpic_io_macro_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qpic_io_macro_clk_src", + .parent_data = gcc_parent_data_8, + .num_parents = ARRAY_SIZE(gcc_parent_data_8), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sdcc1_apps_clk_src[] = { + F(143713, P_XO, 1, 1, 167), + F(400000, P_XO, 1, 1, 60), + F(24000000, P_XO, 1, 0, 0), + F(48000000, P_GPLL2_OUT_MAIN, 12, 1, 2), + F(96000000, P_GPLL2_OUT_MAIN, 12, 0, 0), + F(177777778, P_GPLL0_OUT_MAIN, 4.5, 0, 0), + F(192000000, P_GPLL2_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { + .cmd_rcgr = 0x33004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_9, + .freq_tbl = ftbl_gcc_sdcc1_apps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk_src", + .parent_data = gcc_parent_data_9, + .num_parents = ARRAY_SIZE(gcc_parent_data_9), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_sleep_clk_src[] = { + F(32000, P_SLEEP_CLK, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_sleep_clk_src = { + .cmd_rcgr = 0x3400c, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_10, + .freq_tbl = ftbl_gcc_sleep_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_sleep_clk_src", + .parent_data = gcc_parent_data_10, + .num_parents = ARRAY_SIZE(gcc_parent_data_10), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_system_noc_bfdcd_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(133333333, P_GPLL0_OUT_MAIN, 6, 0, 0), + F(200000000, P_GPLL0_OUT_MAIN, 4, 0, 0), + F(266666667, P_GPLL4_OUT_MAIN, 4.5, 0, 0), + { } +}; + +static struct clk_rcg2 gcc_system_noc_bfdcd_clk_src = { + .cmd_rcgr = 0x2e004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_11, + .freq_tbl = ftbl_gcc_system_noc_bfdcd_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_system_noc_bfdcd_clk_src", + .parent_data = gcc_parent_data_11, + .num_parents = ARRAY_SIZE(gcc_parent_data_11), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_fixed_factor gcc_system_noc_bfdcd_div2_clk_src = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gcc_system_noc_bfdcd_div2_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_rcg2 gcc_uniphy_sys_clk_src = { + .cmd_rcgr = 0x16004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_xo, + .freq_tbl = ftbl_gcc_nss_ts_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_uniphy_sys_clk_src", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_usb0_aux_clk_src = { + .cmd_rcgr = 0x2c018, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_parent_map_12, + .freq_tbl = ftbl_gcc_pcie_aux_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_aux_clk_src", + .parent_data = gcc_parent_data_12, + .num_parents = ARRAY_SIZE(gcc_parent_data_12), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb0_lfps_clk_src[] = { + F(25000000, P_GPLL0_OUT_MAIN, 16, 1, 2), + { } +}; + +static struct clk_rcg2 gcc_usb0_lfps_clk_src = { + .cmd_rcgr = 0x2c07c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_usb0_lfps_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_lfps_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_usb0_master_clk_src = { + .cmd_rcgr = 0x2c004, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_0, + .freq_tbl = ftbl_gcc_gp1_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_master_clk_src", + .parent_data = gcc_parent_data_0, + .num_parents = ARRAY_SIZE(gcc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gcc_usb0_mock_utmi_clk_src[] = { + F(60000000, P_GPLL4_OUT_AUX, 10, 1, 2), + { } +}; + +static struct clk_rcg2 gcc_usb0_mock_utmi_clk_src = { + .cmd_rcgr = 0x2c02c, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_parent_map_13, + .freq_tbl = ftbl_gcc_usb0_mock_utmi_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_mock_utmi_clk_src", + .parent_data = gcc_parent_data_13, + .num_parents = ARRAY_SIZE(gcc_parent_data_13), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_regmap_phy_mux gcc_usb0_pipe_clk_src = { + .reg = 0x2c074, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_USB_PCIE_WRAPPER_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_rcg2 gcc_wcss_ahb_clk_src = { + .cmd_rcgr = 0x25030, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_1, + .freq_tbl = ftbl_gcc_lpass_sway_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_ahb_clk_src", + .parent_data = gcc_parent_data_1, + .num_parents = ARRAY_SIZE(gcc_parent_data_1), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gcc_xo_clk_src = { + .cmd_rcgr = 0x34004, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gcc_parent_map_xo, + .freq_tbl = ftbl_gcc_nss_ts_clk_src, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_xo_clk_src", + .parent_data = &gcc_parent_data_xo, + .num_parents = 1, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_fixed_factor gcc_xo_div4_clk_src = { + .mult = 1, + .div = 4, + .hw.init = &(struct clk_init_data) { + .name = "gcc_xo_div4_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_clk_src.clkr.hw }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_regmap_div gcc_qdss_dap_div_clk_src = { + .reg = 0x2d028, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_dap_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_tsctr_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div gcc_usb0_mock_utmi_div_clk_src = { + .reg = 0x2c040, + .shift = 0, + .width = 2, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_mock_utmi_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch gcc_adss_pwm_clk = { + .halt_reg = 0x1c00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1c00c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_adss_pwm_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_adss_pwm_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ahb_clk = { + .halt_reg = 0x34024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x34024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_ahb_clk = { + .halt_reg = 0x1008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb004, + .enable_mask = BIT(4), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = { + .halt_reg = 0x2024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup1_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup1_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = { + .halt_reg = 0x2020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup1_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup1_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = { + .halt_reg = 0x3024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup2_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup2_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = { + .halt_reg = 0x3020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup2_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup2_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = { + .halt_reg = 0x4024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup3_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup3_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = { + .halt_reg = 0x4020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_qup3_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_qup3_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_sleep_clk = { + .halt_reg = 0x1010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb004, + .enable_mask = BIT(5), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_sleep_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sleep_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart1_apps_clk = { + .halt_reg = 0x2040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart1_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_uart1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart2_apps_clk = { + .halt_reg = 0x3040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart2_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_uart2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart3_apps_clk = { + .halt_reg = 0x4054, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4054, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_blsp1_uart3_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_blsp1_uart3_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce_ahb_clk = { + .halt_reg = 0x25074, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25074, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_div2_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce_axi_clk = { + .halt_reg = 0x25068, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_ce_pcnoc_ahb_clk = { + .halt_reg = 0x25070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_ce_pcnoc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_ahb_clk = { + .halt_reg = 0x3a004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3a004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cmn_12gpll_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_apu_clk = { + .halt_reg = 0x3a00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3a00c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cmn_12gpll_apu_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_sys_clk = { + .halt_reg = 0x3a008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3a008, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_cmn_12gpll_sys_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_uniphy_sys_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp1_clk = { + .halt_reg = 0x8018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x8018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp2_clk = { + .halt_reg = 0x9018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_gp2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_gp2_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_lpass_core_axim_clk = { + .halt_reg = 0x27018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x27018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_lpass_core_axim_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_lpass_sway_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_lpass_sway_clk = { + .halt_reg = 0x27014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x27014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_lpass_sway_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_lpass_sway_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mdio_ahb_clk = { + .halt_reg = 0x12004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x12004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mdio_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mdio_slave_ahb_clk = { + .halt_reg = 0x1200c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1200c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mdio_slave_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_q6_axi_clk = { + .halt_reg = 0x19010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x19010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mem_noc_q6_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_q6_axim_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_ts_clk = { + .halt_reg = 0x19028, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x19028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mem_noc_ts_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_tsctr_div8_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nss_ts_clk = { + .halt_reg = 0x17018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x17018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nss_ts_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_nss_ts_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nsscc_clk = { + .halt_reg = 0x17034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17034, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nsscc_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nsscfg_clk = { + .halt_reg = 0x1702c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1702c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nsscfg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_atb_clk = { + .halt_reg = 0x17014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_atb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_nsscc_clk = { + .halt_reg = 0x17030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_nsscc_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_qosgen_ref_clk = { + .halt_reg = 0x1701c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1701c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_qosgen_ref_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_div4_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_snoc_1_clk = { + .halt_reg = 0x1707c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1707c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_snoc_1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_snoc_clk = { + .halt_reg = 0x17028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_snoc_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_timeout_ref_clk = { + .halt_reg = 0x17020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_timeout_ref_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_div4_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_xo_dcd_clk = { + .halt_reg = 0x17074, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17074, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_xo_dcd_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_ahb_clk = { + .halt_reg = 0x29030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_aux_clk = { + .halt_reg = 0x29070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_axi_m_clk = { + .halt_reg = 0x29038, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_axi_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_axi_s_bridge_clk = { + .halt_reg = 0x29048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_axi_s_clk = { + .halt_reg = 0x29040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_axi_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_0_pipe_clk = { + .halt_reg = 0x29068, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x29068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_0_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_ahb_clk = { + .halt_reg = 0x2a00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2a00c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_aux_clk = { + .halt_reg = 0x2a070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2a070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_axi_m_clk = { + .halt_reg = 0x2a014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2a014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_axi_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_axi_s_bridge_clk = { + .halt_reg = 0x2a024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2a024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_axi_s_clk = { + .halt_reg = 0x2a01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2a01c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_axi_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_1_pipe_clk = { + .halt_reg = 0x2a068, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x2a068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_1_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x1_phy_ahb_clk = { + .halt_reg = 0x29078, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x29078, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x1_phy_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_ahb_clk = { + .halt_reg = 0x28030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_aux_clk = { + .halt_reg = 0x28070, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_axi_m_clk = { + .halt_reg = 0x28038, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_axi_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_axi_m_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_axi_s_bridge_clk = { + .halt_reg = 0x28048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_axi_s_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_axi_s_clk = { + .halt_reg = 0x28040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_axi_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_axi_s_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_phy_ahb_clk = { + .halt_reg = 0x28080, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x28080, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_phy_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3x2_pipe_clk = { + .halt_reg = 0x28068, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x28068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcie3x2_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcnoc_at_clk = { + .halt_reg = 0x31024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x31024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcnoc_at_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcnoc_lpass_clk = { + .halt_reg = 0x31020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x31020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_pcnoc_lpass_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_lpass_sway_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_prng_ahb_clk = { + .halt_reg = 0x13024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb004, + .enable_mask = BIT(10), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_prng_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_ahb_clk = { + .halt_reg = 0x25014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x25014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_wcss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_ahb_s_clk = { + .halt_reg = 0x25018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x25018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_ahb_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_wcss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_axim_clk = { + .halt_reg = 0x2500c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2500c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_axim_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_q6_axim_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_axis_clk = { + .halt_reg = 0x25010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x25010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_axis_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_tsctr_1to2_clk = { + .halt_reg = 0x25020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x25020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6_tsctr_1to2_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_tsctr_div2_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6ss_atbm_clk = { + .halt_reg = 0x2501c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2501c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6ss_atbm_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6ss_pclkdbg_clk = { + .halt_reg = 0x25024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x25024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6ss_pclkdbg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_dap_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6ss_trig_clk = { + .halt_reg = 0x250a0, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x250a0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_q6ss_trig_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_dap_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_at_clk = { + .halt_reg = 0x2d038, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2d038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_at_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_cfg_ahb_clk = { + .halt_reg = 0x2d06c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2d06c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_cfg_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_dap_ahb_clk = { + .halt_reg = 0x2d068, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2d068, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_dap_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_dap_clk = { + .halt_reg = 0x2d05c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb004, + .enable_mask = BIT(2), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_dap_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_dap_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_etr_usb_clk = { + .halt_reg = 0x2d064, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2d064, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_etr_usb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor gcc_eud_at_div_clk_src = { + .mult = 1, + .div = 6, + .hw.init = &(struct clk_init_data) { + .name = "gcc_eud_at_div_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_qdss_at_clk_src.clkr.hw }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_qdss_eud_at_clk = { + .halt_reg = 0x2d070, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2d070, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qdss_eud_at_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_eud_at_div_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_ahb_clk = { + .halt_reg = 0x32010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x32010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qpic_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_clk = { + .halt_reg = 0x32014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x32014, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qpic_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_io_macro_clk = { + .halt_reg = 0x3200c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3200c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qpic_io_macro_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qpic_io_macro_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_sleep_clk = { + .halt_reg = 0x3201c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3201c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_qpic_sleep_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sleep_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x33034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x33034, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x3302c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3302c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sdcc1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_lpass_cfg_clk = { + .halt_reg = 0x2e028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e028, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_lpass_cfg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_lpass_sway_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_nssnoc_1_clk = { + .halt_reg = 0x17090, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17090, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_nssnoc_1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_nssnoc_clk = { + .halt_reg = 0x17084, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17084, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_nssnoc_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_1lane_1_m_clk = { + .halt_reg = 0x2e050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_1lane_1_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_1lane_1_s_clk = { + .halt_reg = 0x2e0ac, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e0ac, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_1lane_1_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_1_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_1lane_m_clk = { + .halt_reg = 0x2e080, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e080, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_1lane_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_1lane_s_clk = { + .halt_reg = 0x2e04c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e04c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_1lane_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x1_0_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_2lane_m_clk = { + .halt_reg = 0x2e07c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e07c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_2lane_m_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_axi_m_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_2lane_s_clk = { + .halt_reg = 0x2e048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_pcie3_2lane_s_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcie3x2_axi_s_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_usb_clk = { + .halt_reg = 0x2e058, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2e058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_usb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_at_clk = { + .halt_reg = 0x2e038, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2e038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sys_noc_at_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_wcss_ahb_clk = { + .halt_reg = 0x2e030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e030, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_sys_noc_wcss_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_wcss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy0_ahb_clk = { + .halt_reg = 0x16010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16010, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_uniphy0_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy0_sys_clk = { + .halt_reg = 0x1600c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1600c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_uniphy0_sys_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_uniphy_sys_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy1_ahb_clk = { + .halt_reg = 0x1601c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1601c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_uniphy1_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy1_sys_clk = { + .halt_reg = 0x16018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x16018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_uniphy1_sys_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_uniphy_sys_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_aux_clk = { + .halt_reg = 0x2c050, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2c050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_aux_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_aux_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_eud_at_clk = { + .halt_reg = 0x30004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x30004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_eud_at_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_eud_at_div_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_lfps_clk = { + .halt_reg = 0x2c090, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2c090, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_lfps_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_lfps_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_master_clk = { + .halt_reg = 0x2c048, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2c048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_master_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_master_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_mock_utmi_clk = { + .halt_reg = 0x2c054, + .clkr = { + .enable_reg = 0x2c054, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_mock_utmi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_mock_utmi_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_phy_cfg_ahb_clk = { + .halt_reg = 0x2c05c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2c05c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_phy_cfg_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_pipe_clk = { + .halt_reg = 0x2c078, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x2c078, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_pipe_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_usb0_pipe_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_sleep_clk = { + .halt_reg = 0x2c058, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x2c058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_usb0_sleep_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sleep_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_axim_clk = { + .halt_reg = 0x2505c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2505c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_axim_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_axis_clk = { + .halt_reg = 0x25060, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25060, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_axis_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_apb_bdg_clk = { + .halt_reg = 0x25048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25048, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_apb_bdg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_dap_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_apb_clk = { + .halt_reg = 0x25038, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25038, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_apb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_dap_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_atb_bdg_clk = { + .halt_reg = 0x2504c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2504c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_atb_bdg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_atb_clk = { + .halt_reg = 0x2503c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2503c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_atb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_at_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_nts_bdg_clk = { + .halt_reg = 0x25050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25050, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_nts_bdg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_tsctr_div2_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_nts_clk = { + .halt_reg = 0x25040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25040, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_nts_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_qdss_tsctr_div2_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_ecahb_clk = { + .halt_reg = 0x25058, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x25058, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_ecahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_wcss_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_mst_async_bdg_clk = { + .halt_reg = 0x2e0b0, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e0b0, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_mst_async_bdg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_slv_async_bdg_clk = { + .halt_reg = 0x2e0b4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x2e0b4, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_wcss_slv_async_bdg_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_system_noc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_xo_clk = { + .halt_reg = 0x34018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x34018, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_xo_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_xo_div4_clk = { + .halt_reg = 0x3401c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3401c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_xo_div4_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_div4_clk_src.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_im_sleep_clk = { + .halt_reg = 0x34020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x34020, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_im_sleep_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_sleep_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_pcnoc_1_clk = { + .halt_reg = 0x17080, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x17080, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_nssnoc_pcnoc_1_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_ahb_clk = { + .halt_reg = 0x1900c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x1900c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mem_noc_ahb_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_pcnoc_bfdcd_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_apss_axi_clk = { + .halt_reg = 0x1901c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0xb004, + .enable_mask = BIT(6), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mem_noc_apss_axi_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_apss_axi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap_div gcc_snoc_qosgen_extref_div_clk_src = { + .reg = 0x2e010, + .shift = 0, + .width = 2, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gcc_snoc_qosgen_extref_div_clk_src", + .parent_hws = (const struct clk_hw*[]) { + &gcc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch gcc_mem_noc_qosgen_extref_clk = { + .halt_reg = 0x19024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x19024, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data) { + .name = "gcc_mem_noc_qosgen_extref_clk", + .parent_hws = (const struct clk_hw*[]) { + &gcc_snoc_qosgen_extref_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap *gcc_ipq5332_clocks[] = { + [GPLL0_MAIN] = &gpll0_main.clkr, + [GPLL0] = &gpll0.clkr, + [GPLL2_MAIN] = &gpll2_main.clkr, + [GPLL2] = &gpll2.clkr, + [GPLL4_MAIN] = &gpll4_main.clkr, + [GPLL4] = &gpll4.clkr, + [GCC_ADSS_PWM_CLK] = &gcc_adss_pwm_clk.clkr, + [GCC_ADSS_PWM_CLK_SRC] = &gcc_adss_pwm_clk_src.clkr, + [GCC_AHB_CLK] = &gcc_ahb_clk.clkr, + [GCC_APSS_AXI_CLK_SRC] = &gcc_apss_axi_clk_src.clkr, + [GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr, + [GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr, + [GCC_BLSP1_QUP1_SPI_APPS_CLK_SRC] = &gcc_blsp1_qup1_spi_apps_clk_src.clkr, + [GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr, + [GCC_BLSP1_QUP2_SPI_APPS_CLK_SRC] = &gcc_blsp1_qup2_spi_apps_clk_src.clkr, + [GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr, + [GCC_BLSP1_QUP3_SPI_APPS_CLK_SRC] = &gcc_blsp1_qup3_spi_apps_clk_src.clkr, + [GCC_BLSP1_SLEEP_CLK] = &gcc_blsp1_sleep_clk.clkr, + [GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr, + [GCC_BLSP1_UART1_APPS_CLK_SRC] = &gcc_blsp1_uart1_apps_clk_src.clkr, + [GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr, + [GCC_BLSP1_UART2_APPS_CLK_SRC] = &gcc_blsp1_uart2_apps_clk_src.clkr, + [GCC_BLSP1_UART3_APPS_CLK] = &gcc_blsp1_uart3_apps_clk.clkr, + [GCC_BLSP1_UART3_APPS_CLK_SRC] = &gcc_blsp1_uart3_apps_clk_src.clkr, + [GCC_CE_AHB_CLK] = &gcc_ce_ahb_clk.clkr, + [GCC_CE_AXI_CLK] = &gcc_ce_axi_clk.clkr, + [GCC_CE_PCNOC_AHB_CLK] = &gcc_ce_pcnoc_ahb_clk.clkr, + [GCC_CMN_12GPLL_AHB_CLK] = &gcc_cmn_12gpll_ahb_clk.clkr, + [GCC_CMN_12GPLL_APU_CLK] = &gcc_cmn_12gpll_apu_clk.clkr, + [GCC_CMN_12GPLL_SYS_CLK] = &gcc_cmn_12gpll_sys_clk.clkr, + [GCC_GP1_CLK] = &gcc_gp1_clk.clkr, + [GCC_GP1_CLK_SRC] = &gcc_gp1_clk_src.clkr, + [GCC_GP2_CLK] = &gcc_gp2_clk.clkr, + [GCC_GP2_CLK_SRC] = &gcc_gp2_clk_src.clkr, + [GCC_LPASS_CORE_AXIM_CLK] = &gcc_lpass_core_axim_clk.clkr, + [GCC_LPASS_SWAY_CLK] = &gcc_lpass_sway_clk.clkr, + [GCC_LPASS_SWAY_CLK_SRC] = &gcc_lpass_sway_clk_src.clkr, + [GCC_MDIO_AHB_CLK] = &gcc_mdio_ahb_clk.clkr, + [GCC_MDIO_SLAVE_AHB_CLK] = &gcc_mdio_slave_ahb_clk.clkr, + [GCC_MEM_NOC_Q6_AXI_CLK] = &gcc_mem_noc_q6_axi_clk.clkr, + [GCC_MEM_NOC_TS_CLK] = &gcc_mem_noc_ts_clk.clkr, + [GCC_NSS_TS_CLK] = &gcc_nss_ts_clk.clkr, + [GCC_NSS_TS_CLK_SRC] = &gcc_nss_ts_clk_src.clkr, + [GCC_NSSCC_CLK] = &gcc_nsscc_clk.clkr, + [GCC_NSSCFG_CLK] = &gcc_nsscfg_clk.clkr, + [GCC_NSSNOC_ATB_CLK] = &gcc_nssnoc_atb_clk.clkr, + [GCC_NSSNOC_NSSCC_CLK] = &gcc_nssnoc_nsscc_clk.clkr, + [GCC_NSSNOC_QOSGEN_REF_CLK] = &gcc_nssnoc_qosgen_ref_clk.clkr, + [GCC_NSSNOC_SNOC_1_CLK] = &gcc_nssnoc_snoc_1_clk.clkr, + [GCC_NSSNOC_SNOC_CLK] = &gcc_nssnoc_snoc_clk.clkr, + [GCC_NSSNOC_TIMEOUT_REF_CLK] = &gcc_nssnoc_timeout_ref_clk.clkr, + [GCC_NSSNOC_XO_DCD_CLK] = &gcc_nssnoc_xo_dcd_clk.clkr, + [GCC_PCIE3X1_0_AHB_CLK] = &gcc_pcie3x1_0_ahb_clk.clkr, + [GCC_PCIE3X1_0_AUX_CLK] = &gcc_pcie3x1_0_aux_clk.clkr, + [GCC_PCIE3X1_0_AXI_CLK_SRC] = &gcc_pcie3x1_0_axi_clk_src.clkr, + [GCC_PCIE3X1_0_AXI_M_CLK] = &gcc_pcie3x1_0_axi_m_clk.clkr, + [GCC_PCIE3X1_0_AXI_S_BRIDGE_CLK] = &gcc_pcie3x1_0_axi_s_bridge_clk.clkr, + [GCC_PCIE3X1_0_AXI_S_CLK] = &gcc_pcie3x1_0_axi_s_clk.clkr, + [GCC_PCIE3X1_0_PIPE_CLK] = &gcc_pcie3x1_0_pipe_clk.clkr, + [GCC_PCIE3X1_0_RCHG_CLK] = &gcc_pcie3x1_0_rchg_clk.clkr, + [GCC_PCIE3X1_0_RCHG_CLK_SRC] = &gcc_pcie3x1_0_rchg_clk_src.clkr, + [GCC_PCIE3X1_1_AHB_CLK] = &gcc_pcie3x1_1_ahb_clk.clkr, + [GCC_PCIE3X1_1_AUX_CLK] = &gcc_pcie3x1_1_aux_clk.clkr, + [GCC_PCIE3X1_1_AXI_CLK_SRC] = &gcc_pcie3x1_1_axi_clk_src.clkr, + [GCC_PCIE3X1_1_AXI_M_CLK] = &gcc_pcie3x1_1_axi_m_clk.clkr, + [GCC_PCIE3X1_1_AXI_S_BRIDGE_CLK] = &gcc_pcie3x1_1_axi_s_bridge_clk.clkr, + [GCC_PCIE3X1_1_AXI_S_CLK] = &gcc_pcie3x1_1_axi_s_clk.clkr, + [GCC_PCIE3X1_1_PIPE_CLK] = &gcc_pcie3x1_1_pipe_clk.clkr, + [GCC_PCIE3X1_1_RCHG_CLK] = &gcc_pcie3x1_1_rchg_clk.clkr, + [GCC_PCIE3X1_1_RCHG_CLK_SRC] = &gcc_pcie3x1_1_rchg_clk_src.clkr, + [GCC_PCIE3X1_PHY_AHB_CLK] = &gcc_pcie3x1_phy_ahb_clk.clkr, + [GCC_PCIE3X2_AHB_CLK] = &gcc_pcie3x2_ahb_clk.clkr, + [GCC_PCIE3X2_AUX_CLK] = &gcc_pcie3x2_aux_clk.clkr, + [GCC_PCIE3X2_AXI_M_CLK] = &gcc_pcie3x2_axi_m_clk.clkr, + [GCC_PCIE3X2_AXI_M_CLK_SRC] = &gcc_pcie3x2_axi_m_clk_src.clkr, + [GCC_PCIE3X2_AXI_S_BRIDGE_CLK] = &gcc_pcie3x2_axi_s_bridge_clk.clkr, + [GCC_PCIE3X2_AXI_S_CLK] = &gcc_pcie3x2_axi_s_clk.clkr, + [GCC_PCIE3X2_AXI_S_CLK_SRC] = &gcc_pcie3x2_axi_s_clk_src.clkr, + [GCC_PCIE3X2_PHY_AHB_CLK] = &gcc_pcie3x2_phy_ahb_clk.clkr, + [GCC_PCIE3X2_PIPE_CLK] = &gcc_pcie3x2_pipe_clk.clkr, + [GCC_PCIE3X2_RCHG_CLK] = &gcc_pcie3x2_rchg_clk.clkr, + [GCC_PCIE3X2_RCHG_CLK_SRC] = &gcc_pcie3x2_rchg_clk_src.clkr, + [GCC_PCIE_AUX_CLK_SRC] = &gcc_pcie_aux_clk_src.clkr, + [GCC_PCNOC_AT_CLK] = &gcc_pcnoc_at_clk.clkr, + [GCC_PCNOC_BFDCD_CLK_SRC] = &gcc_pcnoc_bfdcd_clk_src.clkr, + [GCC_PCNOC_LPASS_CLK] = &gcc_pcnoc_lpass_clk.clkr, + [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + [GCC_Q6_AHB_CLK] = &gcc_q6_ahb_clk.clkr, + [GCC_Q6_AHB_S_CLK] = &gcc_q6_ahb_s_clk.clkr, + [GCC_Q6_AXIM_CLK] = &gcc_q6_axim_clk.clkr, + [GCC_Q6_AXIM_CLK_SRC] = &gcc_q6_axim_clk_src.clkr, + [GCC_Q6_AXIS_CLK] = &gcc_q6_axis_clk.clkr, + [GCC_Q6_TSCTR_1TO2_CLK] = &gcc_q6_tsctr_1to2_clk.clkr, + [GCC_Q6SS_ATBM_CLK] = &gcc_q6ss_atbm_clk.clkr, + [GCC_Q6SS_PCLKDBG_CLK] = &gcc_q6ss_pclkdbg_clk.clkr, + [GCC_Q6SS_TRIG_CLK] = &gcc_q6ss_trig_clk.clkr, + [GCC_QDSS_AT_CLK] = &gcc_qdss_at_clk.clkr, + [GCC_QDSS_AT_CLK_SRC] = &gcc_qdss_at_clk_src.clkr, + [GCC_QDSS_CFG_AHB_CLK] = &gcc_qdss_cfg_ahb_clk.clkr, + [GCC_QDSS_DAP_AHB_CLK] = &gcc_qdss_dap_ahb_clk.clkr, + [GCC_QDSS_DAP_CLK] = &gcc_qdss_dap_clk.clkr, + [GCC_QDSS_DAP_DIV_CLK_SRC] = &gcc_qdss_dap_div_clk_src.clkr, + [GCC_QDSS_ETR_USB_CLK] = &gcc_qdss_etr_usb_clk.clkr, + [GCC_QDSS_EUD_AT_CLK] = &gcc_qdss_eud_at_clk.clkr, + [GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr, + [GCC_QPIC_CLK] = &gcc_qpic_clk.clkr, + [GCC_QPIC_IO_MACRO_CLK] = &gcc_qpic_io_macro_clk.clkr, + [GCC_QPIC_IO_MACRO_CLK_SRC] = &gcc_qpic_io_macro_clk_src.clkr, + [GCC_QPIC_SLEEP_CLK] = &gcc_qpic_sleep_clk.clkr, + [GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr, + [GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr, + [GCC_SDCC1_APPS_CLK_SRC] = &gcc_sdcc1_apps_clk_src.clkr, + [GCC_SLEEP_CLK_SRC] = &gcc_sleep_clk_src.clkr, + [GCC_SNOC_LPASS_CFG_CLK] = &gcc_snoc_lpass_cfg_clk.clkr, + [GCC_SNOC_NSSNOC_1_CLK] = &gcc_snoc_nssnoc_1_clk.clkr, + [GCC_SNOC_NSSNOC_CLK] = &gcc_snoc_nssnoc_clk.clkr, + [GCC_SNOC_PCIE3_1LANE_1_M_CLK] = &gcc_snoc_pcie3_1lane_1_m_clk.clkr, + [GCC_SNOC_PCIE3_1LANE_1_S_CLK] = &gcc_snoc_pcie3_1lane_1_s_clk.clkr, + [GCC_SNOC_PCIE3_1LANE_M_CLK] = &gcc_snoc_pcie3_1lane_m_clk.clkr, + [GCC_SNOC_PCIE3_1LANE_S_CLK] = &gcc_snoc_pcie3_1lane_s_clk.clkr, + [GCC_SNOC_PCIE3_2LANE_M_CLK] = &gcc_snoc_pcie3_2lane_m_clk.clkr, + [GCC_SNOC_PCIE3_2LANE_S_CLK] = &gcc_snoc_pcie3_2lane_s_clk.clkr, + [GCC_SNOC_USB_CLK] = &gcc_snoc_usb_clk.clkr, + [GCC_SYS_NOC_AT_CLK] = &gcc_sys_noc_at_clk.clkr, + [GCC_SYS_NOC_WCSS_AHB_CLK] = &gcc_sys_noc_wcss_ahb_clk.clkr, + [GCC_SYSTEM_NOC_BFDCD_CLK_SRC] = &gcc_system_noc_bfdcd_clk_src.clkr, + [GCC_UNIPHY0_AHB_CLK] = &gcc_uniphy0_ahb_clk.clkr, + [GCC_UNIPHY0_SYS_CLK] = &gcc_uniphy0_sys_clk.clkr, + [GCC_UNIPHY1_AHB_CLK] = &gcc_uniphy1_ahb_clk.clkr, + [GCC_UNIPHY1_SYS_CLK] = &gcc_uniphy1_sys_clk.clkr, + [GCC_UNIPHY_SYS_CLK_SRC] = &gcc_uniphy_sys_clk_src.clkr, + [GCC_USB0_AUX_CLK] = &gcc_usb0_aux_clk.clkr, + [GCC_USB0_AUX_CLK_SRC] = &gcc_usb0_aux_clk_src.clkr, + [GCC_USB0_EUD_AT_CLK] = &gcc_usb0_eud_at_clk.clkr, + [GCC_USB0_LFPS_CLK] = &gcc_usb0_lfps_clk.clkr, + [GCC_USB0_LFPS_CLK_SRC] = &gcc_usb0_lfps_clk_src.clkr, + [GCC_USB0_MASTER_CLK] = &gcc_usb0_master_clk.clkr, + [GCC_USB0_MASTER_CLK_SRC] = &gcc_usb0_master_clk_src.clkr, + [GCC_USB0_MOCK_UTMI_CLK] = &gcc_usb0_mock_utmi_clk.clkr, + [GCC_USB0_MOCK_UTMI_CLK_SRC] = &gcc_usb0_mock_utmi_clk_src.clkr, + [GCC_USB0_MOCK_UTMI_DIV_CLK_SRC] = &gcc_usb0_mock_utmi_div_clk_src.clkr, + [GCC_USB0_PHY_CFG_AHB_CLK] = &gcc_usb0_phy_cfg_ahb_clk.clkr, + [GCC_USB0_PIPE_CLK] = &gcc_usb0_pipe_clk.clkr, + [GCC_USB0_SLEEP_CLK] = &gcc_usb0_sleep_clk.clkr, + [GCC_WCSS_AHB_CLK_SRC] = &gcc_wcss_ahb_clk_src.clkr, + [GCC_WCSS_AXIM_CLK] = &gcc_wcss_axim_clk.clkr, + [GCC_WCSS_AXIS_CLK] = &gcc_wcss_axis_clk.clkr, + [GCC_WCSS_DBG_IFC_APB_BDG_CLK] = &gcc_wcss_dbg_ifc_apb_bdg_clk.clkr, + [GCC_WCSS_DBG_IFC_APB_CLK] = &gcc_wcss_dbg_ifc_apb_clk.clkr, + [GCC_WCSS_DBG_IFC_ATB_BDG_CLK] = &gcc_wcss_dbg_ifc_atb_bdg_clk.clkr, + [GCC_WCSS_DBG_IFC_ATB_CLK] = &gcc_wcss_dbg_ifc_atb_clk.clkr, + [GCC_WCSS_DBG_IFC_NTS_BDG_CLK] = &gcc_wcss_dbg_ifc_nts_bdg_clk.clkr, + [GCC_WCSS_DBG_IFC_NTS_CLK] = &gcc_wcss_dbg_ifc_nts_clk.clkr, + [GCC_WCSS_ECAHB_CLK] = &gcc_wcss_ecahb_clk.clkr, + [GCC_WCSS_MST_ASYNC_BDG_CLK] = &gcc_wcss_mst_async_bdg_clk.clkr, + [GCC_WCSS_SLV_ASYNC_BDG_CLK] = &gcc_wcss_slv_async_bdg_clk.clkr, + [GCC_XO_CLK] = &gcc_xo_clk.clkr, + [GCC_XO_CLK_SRC] = &gcc_xo_clk_src.clkr, + [GCC_XO_DIV4_CLK] = &gcc_xo_div4_clk.clkr, + [GCC_IM_SLEEP_CLK] = &gcc_im_sleep_clk.clkr, + [GCC_NSSNOC_PCNOC_1_CLK] = &gcc_nssnoc_pcnoc_1_clk.clkr, + [GCC_MEM_NOC_AHB_CLK] = &gcc_mem_noc_ahb_clk.clkr, + [GCC_MEM_NOC_APSS_AXI_CLK] = &gcc_mem_noc_apss_axi_clk.clkr, + [GCC_SNOC_QOSGEN_EXTREF_DIV_CLK_SRC] = &gcc_snoc_qosgen_extref_div_clk_src.clkr, + [GCC_MEM_NOC_QOSGEN_EXTREF_CLK] = &gcc_mem_noc_qosgen_extref_clk.clkr, + [GCC_PCIE3X2_PIPE_CLK_SRC] = &gcc_pcie3x2_pipe_clk_src.clkr, + [GCC_PCIE3X1_0_PIPE_CLK_SRC] = &gcc_pcie3x1_0_pipe_clk_src.clkr, + [GCC_PCIE3X1_1_PIPE_CLK_SRC] = &gcc_pcie3x1_1_pipe_clk_src.clkr, + [GCC_USB0_PIPE_CLK_SRC] = &gcc_usb0_pipe_clk_src.clkr, +}; + +static const struct qcom_reset_map gcc_ipq5332_resets[] = { + [GCC_ADSS_BCR] = { 0x1c000 }, + [GCC_ADSS_PWM_CLK_ARES] = { 0x1c00c, 2 }, + [GCC_AHB_CLK_ARES] = { 0x34024, 2 }, + [GCC_APC0_VOLTAGE_DROOP_DETECTOR_BCR] = { 0x38000 }, + [GCC_APC0_VOLTAGE_DROOP_DETECTOR_GPLL0_CLK_ARES] = { 0x3800c, 2 }, + [GCC_APSS_AHB_CLK_ARES] = { 0x24018, 2 }, + [GCC_APSS_AXI_CLK_ARES] = { 0x2401c, 2 }, + [GCC_BLSP1_AHB_CLK_ARES] = { 0x1008, 2 }, + [GCC_BLSP1_BCR] = { 0x1000 }, + [GCC_BLSP1_QUP1_BCR] = { 0x2000 }, + [GCC_BLSP1_QUP1_I2C_APPS_CLK_ARES] = { 0x2024, 2 }, + [GCC_BLSP1_QUP1_SPI_APPS_CLK_ARES] = { 0x2020, 2 }, + [GCC_BLSP1_QUP2_BCR] = { 0x3000 }, + [GCC_BLSP1_QUP2_I2C_APPS_CLK_ARES] = { 0x3024, 2 }, + [GCC_BLSP1_QUP2_SPI_APPS_CLK_ARES] = { 0x3020, 2 }, + [GCC_BLSP1_QUP3_BCR] = { 0x4000 }, + [GCC_BLSP1_QUP3_I2C_APPS_CLK_ARES] = { 0x4024, 2 }, + [GCC_BLSP1_QUP3_SPI_APPS_CLK_ARES] = { 0x4020, 2 }, + [GCC_BLSP1_SLEEP_CLK_ARES] = { 0x1010, 2 }, + [GCC_BLSP1_UART1_APPS_CLK_ARES] = { 0x2040, 2 }, + [GCC_BLSP1_UART1_BCR] = { 0x2028 }, + [GCC_BLSP1_UART2_APPS_CLK_ARES] = { 0x3040, 2 }, + [GCC_BLSP1_UART2_BCR] = { 0x3028 }, + [GCC_BLSP1_UART3_APPS_CLK_ARES] = { 0x4054, 2 }, + [GCC_BLSP1_UART3_BCR] = { 0x4028 }, + [GCC_CE_BCR] = { 0x18008 }, + [GCC_CMN_BLK_BCR] = { 0x3a000 }, + [GCC_CMN_LDO0_BCR] = { 0x1d000 }, + [GCC_CMN_LDO1_BCR] = { 0x1d008 }, + [GCC_DCC_BCR] = { 0x35000 }, + [GCC_GP1_CLK_ARES] = { 0x8018, 2 }, + [GCC_GP2_CLK_ARES] = { 0x9018, 2 }, + [GCC_LPASS_BCR] = { 0x27000 }, + [GCC_LPASS_CORE_AXIM_CLK_ARES] = { 0x27018, 2 }, + [GCC_LPASS_SWAY_CLK_ARES] = { 0x27014, 2 }, + [GCC_MDIOM_BCR] = { 0x12000 }, + [GCC_MDIOS_BCR] = { 0x12008 }, + [GCC_NSS_BCR] = { 0x17000 }, + [GCC_NSS_TS_CLK_ARES] = { 0x17018, 2 }, + [GCC_NSSCC_CLK_ARES] = { 0x17034, 2 }, + [GCC_NSSCFG_CLK_ARES] = { 0x1702c, 2 }, + [GCC_NSSNOC_ATB_CLK_ARES] = { 0x17014, 2 }, + [GCC_NSSNOC_NSSCC_CLK_ARES] = { 0x17030, 2 }, + [GCC_NSSNOC_QOSGEN_REF_CLK_ARES] = { 0x1701c, 2 }, + [GCC_NSSNOC_SNOC_1_CLK_ARES] = { 0x1707c, 2 }, + [GCC_NSSNOC_SNOC_CLK_ARES] = { 0x17028, 2 }, + [GCC_NSSNOC_TIMEOUT_REF_CLK_ARES] = { 0x17020, 2 }, + [GCC_NSSNOC_XO_DCD_CLK_ARES] = { 0x17074, 2 }, + [GCC_PCIE3X1_0_AHB_CLK_ARES] = { 0x29030, 2 }, + [GCC_PCIE3X1_0_AUX_CLK_ARES] = { 0x29070, 2 }, + [GCC_PCIE3X1_0_AXI_M_CLK_ARES] = { 0x29038, 2 }, + [GCC_PCIE3X1_0_AXI_S_BRIDGE_CLK_ARES] = { 0x29048, 2 }, + [GCC_PCIE3X1_0_AXI_S_CLK_ARES] = { 0x29040, 2 }, + [GCC_PCIE3X1_0_BCR] = { 0x29000 }, + [GCC_PCIE3X1_0_LINK_DOWN_BCR] = { 0x29054 }, + [GCC_PCIE3X1_0_PHY_BCR] = { 0x29060 }, + [GCC_PCIE3X1_0_PHY_PHY_BCR] = { 0x2905c }, + [GCC_PCIE3X1_1_AHB_CLK_ARES] = { 0x2a00c, 2 }, + [GCC_PCIE3X1_1_AUX_CLK_ARES] = { 0x2a070, 2 }, + [GCC_PCIE3X1_1_AXI_M_CLK_ARES] = { 0x2a014, 2 }, + [GCC_PCIE3X1_1_AXI_S_BRIDGE_CLK_ARES] = { 0x2a024, 2 }, + [GCC_PCIE3X1_1_AXI_S_CLK_ARES] = { 0x2a01c, 2 }, + [GCC_PCIE3X1_1_BCR] = { 0x2a000 }, + [GCC_PCIE3X1_1_LINK_DOWN_BCR] = { 0x2a028 }, + [GCC_PCIE3X1_1_PHY_BCR] = { 0x2a030 }, + [GCC_PCIE3X1_1_PHY_PHY_BCR] = { 0x2a02c }, + [GCC_PCIE3X1_PHY_AHB_CLK_ARES] = { 0x29078, 2 }, + [GCC_PCIE3X2_AHB_CLK_ARES] = { 0x28030, 2 }, + [GCC_PCIE3X2_AUX_CLK_ARES] = { 0x28070, 2 }, + [GCC_PCIE3X2_AXI_M_CLK_ARES] = { 0x28038, 2 }, + [GCC_PCIE3X2_AXI_S_BRIDGE_CLK_ARES] = { 0x28048, 2 }, + [GCC_PCIE3X2_AXI_S_CLK_ARES] = { 0x28040, 2 }, + [GCC_PCIE3X2_BCR] = { 0x28000 }, + [GCC_PCIE3X2_LINK_DOWN_BCR] = { 0x28054 }, + [GCC_PCIE3X2_PHY_AHB_CLK_ARES] = { 0x28080, 2 }, + [GCC_PCIE3X2_PHY_BCR] = { 0x28060 }, + [GCC_PCIE3X2PHY_PHY_BCR] = { 0x2805c }, + [GCC_PCNOC_BCR] = { 0x31000 }, + [GCC_PCNOC_LPASS_CLK_ARES] = { 0x31020, 2 }, + [GCC_PRNG_AHB_CLK_ARES] = { 0x13024, 2 }, + [GCC_PRNG_BCR] = { 0x13020 }, + [GCC_Q6_AHB_CLK_ARES] = { 0x25014, 2 }, + [GCC_Q6_AHB_S_CLK_ARES] = { 0x25018, 2 }, + [GCC_Q6_AXIM_CLK_ARES] = { 0x2500c, 2 }, + [GCC_Q6_AXIS_CLK_ARES] = { 0x25010, 2 }, + [GCC_Q6_TSCTR_1TO2_CLK_ARES] = { 0x25020, 2 }, + [GCC_Q6SS_ATBM_CLK_ARES] = { 0x2501c, 2 }, + [GCC_Q6SS_PCLKDBG_CLK_ARES] = { 0x25024, 2 }, + [GCC_Q6SS_TRIG_CLK_ARES] = { 0x250a0, 2 }, + [GCC_QDSS_APB2JTAG_CLK_ARES] = { 0x2d060, 2 }, + [GCC_QDSS_AT_CLK_ARES] = { 0x2d038, 2 }, + [GCC_QDSS_BCR] = { 0x2d000 }, + [GCC_QDSS_CFG_AHB_CLK_ARES] = { 0x2d06c, 2 }, + [GCC_QDSS_DAP_AHB_CLK_ARES] = { 0x2d068, 2 }, + [GCC_QDSS_DAP_CLK_ARES] = { 0x2d05c, 2 }, + [GCC_QDSS_ETR_USB_CLK_ARES] = { 0x2d064, 2 }, + [GCC_QDSS_EUD_AT_CLK_ARES] = { 0x2d070, 2 }, + [GCC_QDSS_STM_CLK_ARES] = { 0x2d040, 2 }, + [GCC_QDSS_TRACECLKIN_CLK_ARES] = { 0x2d044, 2 }, + [GCC_QDSS_TS_CLK_ARES] = { 0x2d078, 2 }, + [GCC_QDSS_TSCTR_DIV16_CLK_ARES] = { 0x2d058, 2 }, + [GCC_QDSS_TSCTR_DIV2_CLK_ARES] = { 0x2d048, 2 }, + [GCC_QDSS_TSCTR_DIV3_CLK_ARES] = { 0x2d04c, 2 }, + [GCC_QDSS_TSCTR_DIV4_CLK_ARES] = { 0x2d050, 2 }, + [GCC_QDSS_TSCTR_DIV8_CLK_ARES] = { 0x2d054, 2 }, + [GCC_QPIC_AHB_CLK_ARES] = { 0x32010, 2 }, + [GCC_QPIC_CLK_ARES] = { 0x32014, 2 }, + [GCC_QPIC_BCR] = { 0x32000 }, + [GCC_QPIC_IO_MACRO_CLK_ARES] = { 0x3200c, 2 }, + [GCC_QPIC_SLEEP_CLK_ARES] = { 0x3201c, 2 }, + [GCC_QUSB2_0_PHY_BCR] = { 0x2c068 }, + [GCC_SDCC1_AHB_CLK_ARES] = { 0x33034, 2 }, + [GCC_SDCC1_APPS_CLK_ARES] = { 0x3302c, 2 }, + [GCC_SDCC_BCR] = { 0x33000 }, + [GCC_SNOC_BCR] = { 0x2e000 }, + [GCC_SNOC_LPASS_CFG_CLK_ARES] = { 0x2e028, 2 }, + [GCC_SNOC_NSSNOC_1_CLK_ARES] = { 0x17090, 2 }, + [GCC_SNOC_NSSNOC_CLK_ARES] = { 0x17084, 2 }, + [GCC_SYS_NOC_QDSS_STM_AXI_CLK_ARES] = { 0x2e034, 2 }, + [GCC_SYS_NOC_WCSS_AHB_CLK_ARES] = { 0x2e030, 2 }, + [GCC_UNIPHY0_AHB_CLK_ARES] = { 0x16010, 2 }, + [GCC_UNIPHY0_BCR] = { 0x16000 }, + [GCC_UNIPHY0_SYS_CLK_ARES] = { 0x1600c, 2 }, + [GCC_UNIPHY1_AHB_CLK_ARES] = { 0x1601c, 2 }, + [GCC_UNIPHY1_BCR] = { 0x16014 }, + [GCC_UNIPHY1_SYS_CLK_ARES] = { 0x16018, 2 }, + [GCC_USB0_AUX_CLK_ARES] = { 0x2c050, 2 }, + [GCC_USB0_EUD_AT_CLK_ARES] = { 0x30004, 2 }, + [GCC_USB0_LFPS_CLK_ARES] = { 0x2c090, 2 }, + [GCC_USB0_MASTER_CLK_ARES] = { 0x2c048, 2 }, + [GCC_USB0_MOCK_UTMI_CLK_ARES] = { 0x2c054, 2 }, + [GCC_USB0_PHY_BCR] = { 0x2c06c }, + [GCC_USB0_PHY_CFG_AHB_CLK_ARES] = { 0x2c05c, 2 }, + [GCC_USB0_SLEEP_CLK_ARES] = { 0x2c058, 2 }, + [GCC_USB3PHY_0_PHY_BCR] = { 0x2c070 }, + [GCC_USB_BCR] = { 0x2c000 }, + [GCC_WCSS_AXIM_CLK_ARES] = { 0x2505c, 2 }, + [GCC_WCSS_AXIS_CLK_ARES] = { 0x25060, 2 }, + [GCC_WCSS_BCR] = { 0x18004 }, + [GCC_WCSS_DBG_IFC_APB_BDG_CLK_ARES] = { 0x25048, 2 }, + [GCC_WCSS_DBG_IFC_APB_CLK_ARES] = { 0x25038, 2 }, + [GCC_WCSS_DBG_IFC_ATB_BDG_CLK_ARES] = { 0x2504c, 2 }, + [GCC_WCSS_DBG_IFC_ATB_CLK_ARES] = { 0x2503c, 2 }, + [GCC_WCSS_DBG_IFC_NTS_BDG_CLK_ARES] = { 0x25050, 2 }, + [GCC_WCSS_DBG_IFC_NTS_CLK_ARES] = { 0x25040, 2 }, + [GCC_WCSS_ECAHB_CLK_ARES] = { 0x25058, 2 }, + [GCC_WCSS_MST_ASYNC_BDG_CLK_ARES] = { 0x2e0b0, 2 }, + [GCC_WCSS_Q6_BCR] = { 0x18000 }, + [GCC_WCSS_SLV_ASYNC_BDG_CLK_ARES] = { 0x2e0b4, 2 }, + [GCC_XO_CLK_ARES] = { 0x34018, 2 }, + [GCC_XO_DIV4_CLK_ARES] = { 0x3401c, 2 }, + [GCC_Q6SS_DBG_ARES] = { 0x25094 }, + [GCC_WCSS_DBG_BDG_ARES] = { 0x25098, 0 }, + [GCC_WCSS_DBG_ARES] = { 0x25098, 1 }, + [GCC_WCSS_AXI_S_ARES] = { 0x25098, 2 }, + [GCC_WCSS_AXI_M_ARES] = { 0x25098, 3 }, + [GCC_WCSSAON_ARES] = { 0x2509C }, + [GCC_PCIE3X2_PIPE_ARES] = { 0x28058, 0 }, + [GCC_PCIE3X2_CORE_STICKY_ARES] = { 0x28058, 1 }, + [GCC_PCIE3X2_AXI_S_STICKY_ARES] = { 0x28058, 2 }, + [GCC_PCIE3X2_AXI_M_STICKY_ARES] = { 0x28058, 3 }, + [GCC_PCIE3X1_0_PIPE_ARES] = { 0x29058, 0 }, + [GCC_PCIE3X1_0_CORE_STICKY_ARES] = { 0x29058, 1 }, + [GCC_PCIE3X1_0_AXI_S_STICKY_ARES] = { 0x29058, 2 }, + [GCC_PCIE3X1_0_AXI_M_STICKY_ARES] = { 0x29058, 3 }, + [GCC_PCIE3X1_1_PIPE_ARES] = { 0x2a058, 0 }, + [GCC_PCIE3X1_1_CORE_STICKY_ARES] = { 0x2a058, 1 }, + [GCC_PCIE3X1_1_AXI_S_STICKY_ARES] = { 0x2a058, 2 }, + [GCC_PCIE3X1_1_AXI_M_STICKY_ARES] = { 0x2a058, 3 }, + [GCC_IM_SLEEP_CLK_ARES] = { 0x34020, 2 }, + [GCC_NSSNOC_PCNOC_1_CLK_ARES] = { 0x17080, 2 }, + [GCC_UNIPHY0_XPCS_ARES] = { 0x16050 }, + [GCC_UNIPHY1_XPCS_ARES] = { 0x16060 }, +}; + +static const struct regmap_config gcc_ipq5332_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x3f024, + .fast_io = true, +}; + +static struct clk_hw *gcc_ipq5332_hws[] = { + &gpll0_div2.hw, + &gcc_xo_div4_clk_src.hw, + &gcc_system_noc_bfdcd_div2_clk_src.hw, + &gcc_qdss_tsctr_div2_clk_src.hw, + &gcc_qdss_tsctr_div3_clk_src.hw, + &gcc_qdss_tsctr_div4_clk_src.hw, + &gcc_qdss_tsctr_div8_clk_src.hw, + &gcc_qdss_tsctr_div16_clk_src.hw, + &gcc_eud_at_div_clk_src.hw, +}; + +static const struct qcom_cc_desc gcc_ipq5332_desc = { + .config = &gcc_ipq5332_regmap_config, + .clks = gcc_ipq5332_clocks, + .num_clks = ARRAY_SIZE(gcc_ipq5332_clocks), + .resets = gcc_ipq5332_resets, + .num_resets = ARRAY_SIZE(gcc_ipq5332_resets), + .clk_hws = gcc_ipq5332_hws, + .num_clk_hws = ARRAY_SIZE(gcc_ipq5332_hws), +}; + +static int gcc_ipq5332_probe(struct platform_device *pdev) +{ + return qcom_cc_probe(pdev, &gcc_ipq5332_desc); +} + +static const struct of_device_id gcc_ipq5332_match_table[] = { + { .compatible = "qcom,ipq5332-gcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gcc_ipq5332_match_table); + +static struct platform_driver gcc_ipq5332_driver = { + .probe = gcc_ipq5332_probe, + .driver = { + .name = "gcc-ipq5332", + .of_match_table = gcc_ipq5332_match_table, + }, +}; + +static int __init gcc_ipq5332_init(void) +{ + return platform_driver_register(&gcc_ipq5332_driver); +} +core_initcall(gcc_ipq5332_init); + +static void __exit gcc_ipq5332_exit(void) +{ + platform_driver_unregister(&gcc_ipq5332_driver); +} +module_exit(gcc_ipq5332_exit); + +MODULE_DESCRIPTION("QTI GCC IPQ5332 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 377c0b46d8794ab4441c8c079e079dc2e367c1e1 Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Tue, 7 Mar 2023 11:52:28 +0530 Subject: [PATCH 0571/5631] clk: qcom: ipq5332: mark GPLL4 as ignore unused temporarily Clock framework disables the GPLL4 source since there are no active users for this source currently. Some of the clocks initialized by the bootloaders uses the GPLL4 as the source. Due to this, when the GPLL4 is disabled by the clock framework, system is going for the reboot. To avoid this, mark the GPLL4 as ignore unused so that clock framework doesn't disable it. Once the users of this source is enabled, we can get rid of this flag. Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307062232.4889-6-quic_kathirav@quicinc.com --- drivers/clk/qcom/gcc-ipq5332.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/clk/qcom/gcc-ipq5332.c b/drivers/clk/qcom/gcc-ipq5332.c index 9e4baea33937..bdb4a0a11d07 100644 --- a/drivers/clk/qcom/gcc-ipq5332.c +++ b/drivers/clk/qcom/gcc-ipq5332.c @@ -128,6 +128,17 @@ static struct clk_alpha_pll gpll4_main = { .parent_data = &gcc_parent_data_xo, .num_parents = 1, .ops = &clk_alpha_pll_stromer_ops, + /* + * There are no consumers for this GPLL in kernel yet, + * (will be added soon), so the clock framework + * disables this source. But some of the clocks + * initialized by boot loaders uses this source. So we + * need to keep this clock ON. Add the + * CLK_IGNORE_UNUSED flag so the clock will not be + * disabled. Once the consumer in kernel is added, we + * can get rid of this flag. + */ + .flags = CLK_IGNORE_UNUSED, }, }, }; -- GitLab From 4260ddfb649666b0da02ff9fe5d37664e447b92a Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 16 Jan 2023 21:47:46 +0100 Subject: [PATCH 0572/5631] dt-bindings: arm: msm: Convert and split kpss-acc driver Documentation to yaml Convert kpss-acc driver Documentation to yaml. The original Documentation was wrong all along. Fix it while we are converting it. The example was wrong as kpss-acc-v2 should only expose the regs but we don't have any driver that expose additional clocks. The kpss-acc driver is only specific to v1. For this exact reason, split the Documentation to 2 different schema, v1 as clock-controller and v2 for power-manager as per msm-3.10 specification, the exposed regs handle power manager. Signed-off-by: Christian Marangi Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230116204751.23045-3-ansuelsmth@gmail.com --- .../bindings/arm/msm/qcom,kpss-acc.txt | 49 ------------- .../bindings/clock/qcom,kpss-acc-v1.yaml | 72 +++++++++++++++++++ .../bindings/power/qcom,kpss-acc-v2.yaml | 42 +++++++++++ 3 files changed, 114 insertions(+), 49 deletions(-) delete mode 100644 Documentation/devicetree/bindings/arm/msm/qcom,kpss-acc.txt create mode 100644 Documentation/devicetree/bindings/clock/qcom,kpss-acc-v1.yaml create mode 100644 Documentation/devicetree/bindings/power/qcom,kpss-acc-v2.yaml diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,kpss-acc.txt b/Documentation/devicetree/bindings/arm/msm/qcom,kpss-acc.txt deleted file mode 100644 index 7f696362a4a1..000000000000 --- a/Documentation/devicetree/bindings/arm/msm/qcom,kpss-acc.txt +++ /dev/null @@ -1,49 +0,0 @@ -Krait Processor Sub-system (KPSS) Application Clock Controller (ACC) - -The KPSS ACC provides clock, power domain, and reset control to a Krait CPU. -There is one ACC register region per CPU within the KPSS remapped region as -well as an alias register region that remaps accesses to the ACC associated -with the CPU accessing the region. - -PROPERTIES - -- compatible: - Usage: required - Value type: - Definition: should be one of: - "qcom,kpss-acc-v1" - "qcom,kpss-acc-v2" - -- reg: - Usage: required - Value type: - Definition: the first element specifies the base address and size of - the register region. An optional second element specifies - the base address and size of the alias register region. - -- clocks: - Usage: required - Value type: - Definition: reference to the pll parents. - -- clock-names: - Usage: required - Value type: - Definition: must be "pll8_vote", "pxo". - -- clock-output-names: - Usage: optional - Value type: - Definition: Name of the output clock. Typically acpuX_aux where X is a - CPU number starting at 0. - -Example: - - clock-controller@2088000 { - compatible = "qcom,kpss-acc-v2"; - reg = <0x02088000 0x1000>, - <0x02008000 0x1000>; - clocks = <&gcc PLL8_VOTE>, <&gcc PXO_SRC>; - clock-names = "pll8_vote", "pxo"; - clock-output-names = "acpu0_aux"; - }; diff --git a/Documentation/devicetree/bindings/clock/qcom,kpss-acc-v1.yaml b/Documentation/devicetree/bindings/clock/qcom,kpss-acc-v1.yaml new file mode 100644 index 000000000000..a466e4e8aacd --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,kpss-acc-v1.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,kpss-acc-v1.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Krait Processor Sub-system (KPSS) Application Clock Controller (ACC) v1 + +maintainers: + - Christian Marangi + +description: + The KPSS ACC provides clock, power domain, and reset control to a Krait CPU. + There is one ACC register region per CPU within the KPSS remapped region as + well as an alias register region that remaps accesses to the ACC associated + with the CPU accessing the region. ACC v1 is currently used as a + clock-controller for enabling the cpu and hanling the aux clocks. + +properties: + compatible: + const: qcom,kpss-acc-v1 + + reg: + items: + - description: Base address and size of the register region + - description: Optional base address and size of the alias register region + minItems: 1 + + clocks: + minItems: 2 + maxItems: 2 + + clock-names: + items: + - const: pll8_vote + - const: pxo + + clock-output-names: + description: Name of the aux clock. Krait can have at most 4 cpu. + enum: + - acpu0_aux + - acpu1_aux + - acpu2_aux + - acpu3_aux + + '#clock-cells': + const: 0 + +required: + - compatible + - reg + - clocks + - clock-names + - clock-output-names + - '#clock-cells' + +additionalProperties: false + +examples: + - | + #include + + clock-controller@2088000 { + compatible = "qcom,kpss-acc-v1"; + reg = <0x02088000 0x1000>, <0x02008000 0x1000>; + clocks = <&gcc PLL8_VOTE>, <&pxo_board>; + clock-names = "pll8_vote", "pxo"; + clock-output-names = "acpu0_aux"; + #clock-cells = <0>; + }; + +... diff --git a/Documentation/devicetree/bindings/power/qcom,kpss-acc-v2.yaml b/Documentation/devicetree/bindings/power/qcom,kpss-acc-v2.yaml new file mode 100644 index 000000000000..202a5d51ee88 --- /dev/null +++ b/Documentation/devicetree/bindings/power/qcom,kpss-acc-v2.yaml @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/power/qcom,kpss-acc-v2.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Krait Processor Sub-system (KPSS) Application Clock Controller (ACC) v2 + +maintainers: + - Christian Marangi + +description: + The KPSS ACC provides clock, power manager, and reset control to a Krait CPU. + There is one ACC register region per CPU within the KPSS remapped region as + well as an alias register region that remaps accesses to the ACC associated + with the CPU accessing the region. ACC v2 is currently used as a + power-manager for enabling the cpu. + +properties: + compatible: + const: qcom,kpss-acc-v2 + + reg: + items: + - description: Base address and size of the register region + - description: Optional base address and size of the alias register region + minItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + power-manager@f9088000 { + compatible = "qcom,kpss-acc-v2"; + reg = <0xf9088000 0x1000>, + <0xf9008000 0x1000>; + }; +... -- GitLab From afd7b4d68054faef065f9526d41a1f54b58218f0 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 16 Jan 2023 21:47:47 +0100 Subject: [PATCH 0573/5631] dt-bindings: arm: msm: Rework kpss-gcc driver Documentation to yaml Rework kpss-gcc driver Documentation to yaml Documentation and move it to clock as it's a clock-controller. The current kpss-gcc Documentation have major problems and can't be converted directly. Introduce various changes to the original Documentation. Add #clock-cells additional binding as this clock outputs a static clk named acpu_l2_aux with supported compatible. Only some compatible require and outputs a clock, for the others, set only the reg as a required binding to correctly export the kpss-gcc registers. As the reg is shared also add the required syscon compatible. Signed-off-by: Christian Marangi Reviewed-by: Rob Herring Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230116204751.23045-4-ansuelsmth@gmail.com --- .../bindings/arm/msm/qcom,kpss-gcc.txt | 44 ---------- .../bindings/clock/qcom,kpss-gcc.yaml | 88 +++++++++++++++++++ 2 files changed, 88 insertions(+), 44 deletions(-) delete mode 100644 Documentation/devicetree/bindings/arm/msm/qcom,kpss-gcc.txt create mode 100644 Documentation/devicetree/bindings/clock/qcom,kpss-gcc.yaml diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,kpss-gcc.txt b/Documentation/devicetree/bindings/arm/msm/qcom,kpss-gcc.txt deleted file mode 100644 index e628758950e1..000000000000 --- a/Documentation/devicetree/bindings/arm/msm/qcom,kpss-gcc.txt +++ /dev/null @@ -1,44 +0,0 @@ -Krait Processor Sub-system (KPSS) Global Clock Controller (GCC) - -PROPERTIES - -- compatible: - Usage: required - Value type: - Definition: should be one of the following. The generic compatible - "qcom,kpss-gcc" should also be included. - "qcom,kpss-gcc-ipq8064", "qcom,kpss-gcc" - "qcom,kpss-gcc-apq8064", "qcom,kpss-gcc" - "qcom,kpss-gcc-msm8974", "qcom,kpss-gcc" - "qcom,kpss-gcc-msm8960", "qcom,kpss-gcc" - -- reg: - Usage: required - Value type: - Definition: base address and size of the register region - -- clocks: - Usage: required - Value type: - Definition: reference to the pll parents. - -- clock-names: - Usage: required - Value type: - Definition: must be "pll8_vote", "pxo". - -- clock-output-names: - Usage: required - Value type: - Definition: Name of the output clock. Typically acpu_l2_aux indicating - an L2 cache auxiliary clock. - -Example: - - l2cc: clock-controller@2011000 { - compatible = "qcom,kpss-gcc-ipq8064", "qcom,kpss-gcc"; - reg = <0x2011000 0x1000>; - clocks = <&gcc PLL8_VOTE>, <&gcc PXO_SRC>; - clock-names = "pll8_vote", "pxo"; - clock-output-names = "acpu_l2_aux"; - }; diff --git a/Documentation/devicetree/bindings/clock/qcom,kpss-gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,kpss-gcc.yaml new file mode 100644 index 000000000000..88b7672123a0 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/qcom,kpss-gcc.yaml @@ -0,0 +1,88 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/qcom,kpss-gcc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Krait Processor Sub-system (KPSS) Global Clock Controller (GCC) + +maintainers: + - Christian Marangi + +description: + Krait Processor Sub-system (KPSS) Global Clock Controller (GCC). Used + to control L2 mux (in the current implementation) and provide access + to the kpss-gcc registers. + +properties: + compatible: + items: + - enum: + - qcom,kpss-gcc-ipq8064 + - qcom,kpss-gcc-apq8064 + - qcom,kpss-gcc-msm8974 + - qcom,kpss-gcc-msm8960 + - qcom,kpss-gcc-msm8660 + - qcom,kpss-gcc-mdm9615 + - const: qcom,kpss-gcc + - const: syscon + + reg: + maxItems: 1 + + clocks: + minItems: 2 + maxItems: 2 + + clock-names: + items: + - const: pll8_vote + - const: pxo + + '#clock-cells': + const: 0 + +required: + - compatible + - reg + +if: + properties: + compatible: + contains: + enum: + - qcom,kpss-gcc-ipq8064 + - qcom,kpss-gcc-apq8064 + - qcom,kpss-gcc-msm8974 + - qcom,kpss-gcc-msm8960 +then: + required: + - clocks + - clock-names + - '#clock-cells' +else: + properties: + clock: false + clock-names: false + '#clock-cells': false + +additionalProperties: false + +examples: + - | + #include + + clock-controller@2011000 { + compatible = "qcom,kpss-gcc-ipq8064", "qcom,kpss-gcc", "syscon"; + reg = <0x2011000 0x1000>; + clocks = <&gcc PLL8_VOTE>, <&pxo_board>; + clock-names = "pll8_vote", "pxo"; + #clock-cells = <0>; + }; + + - | + clock-controller@2011000 { + compatible = "qcom,kpss-gcc-mdm9615", "qcom,kpss-gcc", "syscon"; + reg = <0x02011000 0x1000>; + }; +... -- GitLab From fe084c62aacebad46ea2f5a7f1b3183180c00a3b Mon Sep 17 00:00:00 2001 From: Rayyan Ansari Date: Sat, 21 Jan 2023 19:25:38 +0000 Subject: [PATCH 0574/5631] clk: qcom: smd: Add XO RPM clocks for MSM8226/MSM8974 Add the XO and XO_A clocks to the MSM8974 clock list, which is also used on MSM8226. Signed-off-by: Rayyan Ansari Tested-by: Luca Weiss Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230121192540.9177-2-rayyan@ansari.sh --- drivers/clk/qcom/clk-smd-rpm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 198886c1b6c8..bab96fca8916 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -610,6 +610,8 @@ static const struct rpm_smd_clk_desc rpm_clk_msm8936 = { }; static struct clk_smd_rpm *msm8974_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, [RPM_SMD_PNOC_CLK] = &clk_smd_rpm_bus_0_pcnoc_clk, [RPM_SMD_PNOC_A_CLK] = &clk_smd_rpm_bus_0_pcnoc_a_clk, [RPM_SMD_SNOC_CLK] = &clk_smd_rpm_bus_1_snoc_clk, -- GitLab From 2d1fc2d804bc1503f4e36fb97b0f6698e7769796 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Otto=20Pfl=C3=BCger?= Date: Thu, 23 Feb 2023 19:09:32 +0100 Subject: [PATCH 0575/5631] dt-bindings: clock: Add MSM8917 global clock controller MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a device tree binding to describe clocks, resets and power domains provided by the global clock controller on MSM8917 SoCs and the very similar QM215 SoCs. Add the new compatibles to qcom,gcc-msm8909.yaml. There is no need to create another YAML file because the bindings are identical (MSM8917 GCC requires the same parent clocks as the MSM8909 GCC). Signed-off-by: Otto Pflüger Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230223180935.60546-2-otto.pflueger@abscue.de --- .../bindings/clock/qcom,gcc-msm8909.yaml | 13 +- include/dt-bindings/clock/qcom,gcc-msm8917.h | 190 ++++++++++++++++++ 2 files changed, 199 insertions(+), 4 deletions(-) create mode 100644 include/dt-bindings/clock/qcom,gcc-msm8917.h diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8909.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8909.yaml index 6279a59c2e20..b91462587df5 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gcc-msm8909.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gcc-msm8909.yaml @@ -4,20 +4,25 @@ $id: http://devicetree.org/schemas/clock/qcom,gcc-msm8909.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Qualcomm Global Clock & Reset Controller on MSM8909 +title: Qualcomm Global Clock & Reset Controller on MSM8909, MSM8917 and QM215 maintainers: - Stephan Gerhold description: | Qualcomm global clock control module provides the clocks, resets and power - domains on MSM8909. + domains on MSM8909, MSM8917 or QM215. - See also:: include/dt-bindings/clock/qcom,gcc-msm8909.h + See also:: + include/dt-bindings/clock/qcom,gcc-msm8909.h + include/dt-bindings/clock/qcom,gcc-msm8917.h properties: compatible: - const: qcom,gcc-msm8909 + enum: + - qcom,gcc-msm8909 + - qcom,gcc-msm8917 + - qcom,gcc-qm215 clocks: items: diff --git a/include/dt-bindings/clock/qcom,gcc-msm8917.h b/include/dt-bindings/clock/qcom,gcc-msm8917.h new file mode 100644 index 000000000000..a371b1adc896 --- /dev/null +++ b/include/dt-bindings/clock/qcom,gcc-msm8917.h @@ -0,0 +1,190 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef _DT_BINDINGS_CLK_MSM_GCC_8917_H +#define _DT_BINDINGS_CLK_MSM_GCC_8917_H + +/* Clocks */ +#define APSS_AHB_CLK_SRC 0 +#define BLSP1_QUP2_I2C_APPS_CLK_SRC 1 +#define BLSP1_QUP2_SPI_APPS_CLK_SRC 2 +#define BLSP1_QUP3_I2C_APPS_CLK_SRC 3 +#define BLSP1_QUP3_SPI_APPS_CLK_SRC 4 +#define BLSP1_QUP4_I2C_APPS_CLK_SRC 5 +#define BLSP1_QUP4_SPI_APPS_CLK_SRC 6 +#define BLSP1_UART1_APPS_CLK_SRC 7 +#define BLSP1_UART2_APPS_CLK_SRC 8 +#define BLSP2_QUP1_I2C_APPS_CLK_SRC 9 +#define BLSP2_QUP1_SPI_APPS_CLK_SRC 10 +#define BLSP2_QUP2_I2C_APPS_CLK_SRC 11 +#define BLSP2_QUP2_SPI_APPS_CLK_SRC 12 +#define BLSP2_QUP3_I2C_APPS_CLK_SRC 13 +#define BLSP2_QUP3_SPI_APPS_CLK_SRC 14 +#define BLSP2_UART1_APPS_CLK_SRC 15 +#define BLSP2_UART2_APPS_CLK_SRC 16 +#define BYTE0_CLK_SRC 17 +#define CAMSS_GP0_CLK_SRC 18 +#define CAMSS_GP1_CLK_SRC 19 +#define CAMSS_TOP_AHB_CLK_SRC 20 +#define CCI_CLK_SRC 21 +#define CPP_CLK_SRC 22 +#define CRYPTO_CLK_SRC 23 +#define CSI0PHYTIMER_CLK_SRC 24 +#define CSI0_CLK_SRC 25 +#define CSI1PHYTIMER_CLK_SRC 26 +#define CSI1_CLK_SRC 27 +#define CSI2_CLK_SRC 28 +#define ESC0_CLK_SRC 29 +#define GCC_APSS_TCU_CLK 30 +#define GCC_BIMC_GFX_CLK 31 +#define GCC_BIMC_GPU_CLK 32 +#define GCC_BLSP1_AHB_CLK 33 +#define GCC_BLSP1_QUP2_I2C_APPS_CLK 34 +#define GCC_BLSP1_QUP2_SPI_APPS_CLK 35 +#define GCC_BLSP1_QUP3_I2C_APPS_CLK 36 +#define GCC_BLSP1_QUP3_SPI_APPS_CLK 37 +#define GCC_BLSP1_QUP4_I2C_APPS_CLK 38 +#define GCC_BLSP1_QUP4_SPI_APPS_CLK 39 +#define GCC_BLSP1_UART1_APPS_CLK 40 +#define GCC_BLSP1_UART2_APPS_CLK 41 +#define GCC_BLSP2_AHB_CLK 42 +#define GCC_BLSP2_QUP1_I2C_APPS_CLK 43 +#define GCC_BLSP2_QUP1_SPI_APPS_CLK 44 +#define GCC_BLSP2_QUP2_I2C_APPS_CLK 45 +#define GCC_BLSP2_QUP2_SPI_APPS_CLK 46 +#define GCC_BLSP2_QUP3_I2C_APPS_CLK 47 +#define GCC_BLSP2_QUP3_SPI_APPS_CLK 48 +#define GCC_BLSP2_UART1_APPS_CLK 49 +#define GCC_BLSP2_UART2_APPS_CLK 50 +#define GCC_BOOT_ROM_AHB_CLK 51 +#define GCC_CAMSS_AHB_CLK 52 +#define GCC_CAMSS_CCI_AHB_CLK 53 +#define GCC_CAMSS_CCI_CLK 54 +#define GCC_CAMSS_CPP_AHB_CLK 55 +#define GCC_CAMSS_CPP_CLK 56 +#define GCC_CAMSS_CSI0PHYTIMER_CLK 57 +#define GCC_CAMSS_CSI0PHY_CLK 58 +#define GCC_CAMSS_CSI0PIX_CLK 59 +#define GCC_CAMSS_CSI0RDI_CLK 60 +#define GCC_CAMSS_CSI0_AHB_CLK 61 +#define GCC_CAMSS_CSI0_CLK 62 +#define GCC_CAMSS_CSI1PHYTIMER_CLK 63 +#define GCC_CAMSS_CSI1PHY_CLK 64 +#define GCC_CAMSS_CSI1PIX_CLK 65 +#define GCC_CAMSS_CSI1RDI_CLK 66 +#define GCC_CAMSS_CSI1_AHB_CLK 67 +#define GCC_CAMSS_CSI1_CLK 68 +#define GCC_CAMSS_CSI2PHY_CLK 69 +#define GCC_CAMSS_CSI2PIX_CLK 70 +#define GCC_CAMSS_CSI2RDI_CLK 71 +#define GCC_CAMSS_CSI2_AHB_CLK 72 +#define GCC_CAMSS_CSI2_CLK 73 +#define GCC_CAMSS_CSI_VFE0_CLK 74 +#define GCC_CAMSS_CSI_VFE1_CLK 75 +#define GCC_CAMSS_GP0_CLK 76 +#define GCC_CAMSS_GP1_CLK 77 +#define GCC_CAMSS_ISPIF_AHB_CLK 78 +#define GCC_CAMSS_JPEG0_CLK 79 +#define GCC_CAMSS_JPEG_AHB_CLK 80 +#define GCC_CAMSS_JPEG_AXI_CLK 81 +#define GCC_CAMSS_MCLK0_CLK 82 +#define GCC_CAMSS_MCLK1_CLK 83 +#define GCC_CAMSS_MCLK2_CLK 84 +#define GCC_CAMSS_MICRO_AHB_CLK 85 +#define GCC_CAMSS_TOP_AHB_CLK 86 +#define GCC_CAMSS_VFE0_AHB_CLK 87 +#define GCC_CAMSS_VFE0_AXI_CLK 88 +#define GCC_CAMSS_VFE0_CLK 89 +#define GCC_CAMSS_VFE1_AHB_CLK 90 +#define GCC_CAMSS_VFE1_AXI_CLK 91 +#define GCC_CAMSS_VFE1_CLK 92 +#define GCC_CPP_TBU_CLK 93 +#define GCC_CRYPTO_AHB_CLK 94 +#define GCC_CRYPTO_AXI_CLK 95 +#define GCC_CRYPTO_CLK 96 +#define GCC_DCC_CLK 97 +#define GCC_GFX_TBU_CLK 98 +#define GCC_GFX_TCU_CLK 99 +#define GCC_GP1_CLK 100 +#define GCC_GP2_CLK 101 +#define GCC_GP3_CLK 102 +#define GCC_GTCU_AHB_CLK 103 +#define GCC_JPEG_TBU_CLK 104 +#define GCC_MDP_TBU_CLK 105 +#define GCC_MDSS_AHB_CLK 106 +#define GCC_MDSS_AXI_CLK 107 +#define GCC_MDSS_BYTE0_CLK 108 +#define GCC_MDSS_ESC0_CLK 109 +#define GCC_MDSS_MDP_CLK 110 +#define GCC_MDSS_PCLK0_CLK 111 +#define GCC_MDSS_VSYNC_CLK 112 +#define GCC_MSS_CFG_AHB_CLK 113 +#define GCC_MSS_Q6_BIMC_AXI_CLK 114 +#define GCC_OXILI_AHB_CLK 115 +#define GCC_OXILI_GFX3D_CLK 116 +#define GCC_PDM2_CLK 117 +#define GCC_PDM_AHB_CLK 118 +#define GCC_PRNG_AHB_CLK 119 +#define GCC_QDSS_DAP_CLK 120 +#define GCC_SDCC1_AHB_CLK 121 +#define GCC_SDCC1_APPS_CLK 122 +#define GCC_SDCC1_ICE_CORE_CLK 123 +#define GCC_SDCC2_AHB_CLK 124 +#define GCC_SDCC2_APPS_CLK 125 +#define GCC_SMMU_CFG_CLK 126 +#define GCC_USB2A_PHY_SLEEP_CLK 127 +#define GCC_USB_HS_AHB_CLK 128 +#define GCC_USB_HS_PHY_CFG_AHB_CLK 129 +#define GCC_USB_HS_SYSTEM_CLK 130 +#define GCC_VENUS0_AHB_CLK 131 +#define GCC_VENUS0_AXI_CLK 132 +#define GCC_VENUS0_CORE0_VCODEC0_CLK 133 +#define GCC_VENUS0_VCODEC0_CLK 134 +#define GCC_VENUS_TBU_CLK 135 +#define GCC_VFE1_TBU_CLK 136 +#define GCC_VFE_TBU_CLK 137 +#define GFX3D_CLK_SRC 138 +#define GP1_CLK_SRC 139 +#define GP2_CLK_SRC 140 +#define GP3_CLK_SRC 141 +#define GPLL0 142 +#define GPLL0_EARLY 143 +#define GPLL3 144 +#define GPLL3_EARLY 145 +#define GPLL4 146 +#define GPLL4_EARLY 147 +#define GPLL6 148 +#define GPLL6_EARLY 149 +#define JPEG0_CLK_SRC 150 +#define MCLK0_CLK_SRC 151 +#define MCLK1_CLK_SRC 152 +#define MCLK2_CLK_SRC 153 +#define MDP_CLK_SRC 154 +#define PCLK0_CLK_SRC 155 +#define PDM2_CLK_SRC 156 +#define SDCC1_APPS_CLK_SRC 157 +#define SDCC1_ICE_CORE_CLK_SRC 158 +#define SDCC2_APPS_CLK_SRC 159 +#define USB_HS_SYSTEM_CLK_SRC 160 +#define VCODEC0_CLK_SRC 161 +#define VFE0_CLK_SRC 162 +#define VFE1_CLK_SRC 163 +#define VSYNC_CLK_SRC 164 + +/* GCC block resets */ +#define GCC_CAMSS_MICRO_BCR 0 +#define GCC_MSS_BCR 1 +#define GCC_QUSB2_PHY_BCR 2 +#define GCC_USB_HS_BCR 3 +#define GCC_USB2_HS_PHY_ONLY_BCR 4 + +/* GDSCs */ +#define CPP_GDSC 0 +#define JPEG_GDSC 1 +#define MDSS_GDSC 2 +#define OXILI_GX_GDSC 3 +#define VENUS_CORE0_GDSC 4 +#define VENUS_GDSC 5 +#define VFE0_GDSC 6 +#define VFE1_GDSC 7 + +#endif -- GitLab From 940822566ea9759b0af71178debf67ff09ce44d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Otto=20Pfl=C3=BCger?= Date: Thu, 23 Feb 2023 19:09:34 +0100 Subject: [PATCH 0576/5631] dt-bindings: clock: qcom,rpmcc: Add MSM8917 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document the qcom,rpmcc-msm8917 compatible. Signed-off-by: Otto Pflüger Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230223180935.60546-4-otto.pflueger@abscue.de --- Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml index 2a95bf8664f9..3665dd30604a 100644 --- a/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,rpmcc.yaml @@ -31,6 +31,7 @@ properties: - qcom,rpmcc-msm8660 - qcom,rpmcc-msm8909 - qcom,rpmcc-msm8916 + - qcom,rpmcc-msm8917 - qcom,rpmcc-msm8936 - qcom,rpmcc-msm8953 - qcom,rpmcc-msm8974 @@ -107,6 +108,7 @@ allOf: - qcom,rpmcc-mdm9607 - qcom,rpmcc-msm8226 - qcom,rpmcc-msm8916 + - qcom,rpmcc-msm8917 - qcom,rpmcc-msm8936 - qcom,rpmcc-msm8953 - qcom,rpmcc-msm8974 -- GitLab From 33cc27a47d3ab6b598bf7f7dcd3a858458a4ec1d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Otto=20Pfl=C3=BCger?= Date: Thu, 23 Feb 2023 19:09:33 +0100 Subject: [PATCH 0577/5631] clk: qcom: Add global clock controller driver for MSM8917 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver provides clocks, resets and power domains needed for various components of the MSM8917 SoC and the very similar QM215 SoC. According to [1] in the downstream kernel, the GPU clock has a different source mapping on QM215 (gcc_gfx3d_map vs gcc_gfx3d_map_qm215). [1]: https://git.codelinaro.org/clo/la/kernel/msm-4.9/-/blob/LF.UM.8.6.2-28000-89xx.0/include/dt-bindings/clock/msm-clocks-hwio-8952.h#L298 Signed-off-by: Otto Pflüger Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230223180935.60546-3-otto.pflueger@abscue.de --- drivers/clk/qcom/Kconfig | 10 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gcc-msm8917.c | 3303 ++++++++++++++++++++++++++++++++ 3 files changed, 3314 insertions(+) create mode 100644 drivers/clk/qcom/gcc-msm8917.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 391e7aa35dd7..449bc8314d21 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -204,6 +204,16 @@ config MSM_GCC_8916 Say Y if you want to use devices such as UART, SPI i2c, USB, SD/eMMC, display, graphics, camera etc. +config MSM_GCC_8917 + tristate "MSM8917/QM215 Global Clock Controller" + depends on ARM64 || COMPILE_TEST + select QCOM_GDSC + help + Support for the global clock controller on msm8917 and qm215 + devices. + Say Y if you want to use devices such as UART, SPI i2c, USB, + SD/eMMC, display, graphics, camera etc. + config MSM_GCC_8939 tristate "MSM8939 Global Clock Controller" select QCOM_GDSC diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index 3dd4648f5093..c1adb427d1ef 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_MDM_LCC_9615) += lcc-mdm9615.o obj-$(CONFIG_MSM_GCC_8660) += gcc-msm8660.o obj-$(CONFIG_MSM_GCC_8909) += gcc-msm8909.o obj-$(CONFIG_MSM_GCC_8916) += gcc-msm8916.o +obj-$(CONFIG_MSM_GCC_8917) += gcc-msm8917.o obj-$(CONFIG_MSM_GCC_8939) += gcc-msm8939.o obj-$(CONFIG_MSM_GCC_8953) += gcc-msm8953.o obj-$(CONFIG_MSM_GCC_8960) += gcc-msm8960.o diff --git a/drivers/clk/qcom/gcc-msm8917.c b/drivers/clk/qcom/gcc-msm8917.c new file mode 100644 index 000000000000..a4c33a2ce61c --- /dev/null +++ b/drivers/clk/qcom/gcc-msm8917.c @@ -0,0 +1,3303 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Otto Pflüger + * + * Based on gcc-msm8953.c: + * Copyright 2021, The Linux Foundation. All rights reserved. + * with parts taken from gcc-qcs404.c: + * Copyright 2018, The Linux Foundation. All rights reserved. + * and gcc-msm8939.c: + * Copyright 2020 Linaro Limited + * adapted with data from clock-gcc-8952.c in Qualcomm's msm-4.9 release: + * Copyright (c) 2014-2020, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-pll.h" +#include "clk-rcg.h" +#include "common.h" +#include "gdsc.h" +#include "reset.h" + +enum { + DT_XO, + DT_SLEEP_CLK, + DT_DSI0PLL, + DT_DSI0PLL_BYTE, +}; + +enum { + P_XO, + P_SLEEP_CLK, + P_GPLL0, + P_GPLL3, + P_GPLL4, + P_GPLL6, + P_DSI0PLL, + P_DSI0PLL_BYTE, +}; + +static struct clk_alpha_pll gpll0_sleep_clk_src = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x45008, + .enable_mask = BIT(23), + .enable_is_inverted = true, + .hw.init = &(struct clk_init_data){ + .name = "gpll0_sleep_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_XO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll gpll0_early = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x45000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gpll0_early", + .parent_hws = (const struct clk_hw*[]){ + &gpll0_sleep_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll0 = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpll0", + .parent_hws = (const struct clk_hw*[]){ + &gpll0_early.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ro_ops, + }, +}; + +static const struct pll_vco gpll3_p_vco[] = { + { 700000000, 1400000000, 0 }, +}; + +static const struct alpha_pll_config gpll3_early_config = { + .l = 63, + .config_ctl_val = 0x4001055b, + .early_output_mask = 0, + .post_div_mask = GENMASK(11, 8), + .post_div_val = BIT(8), +}; + +static struct clk_alpha_pll gpll3_early = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .vco_table = gpll3_p_vco, + .num_vco = ARRAY_SIZE(gpll3_p_vco), + .flags = SUPPORTS_DYNAMIC_UPDATE, + .clkr = { + .hw.init = &(struct clk_init_data){ + .name = "gpll3_early", + .parent_data = &(const struct clk_parent_data) { + .index = DT_XO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll3 = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpll3", + .parent_hws = (const struct clk_hw*[]){ + &gpll3_early.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ops, + .flags = CLK_SET_RATE_PARENT, + }, +}; + +static struct clk_alpha_pll gpll4_early = { + .offset = 0x24000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x45000, + .enable_mask = BIT(5), + .hw.init = &(struct clk_init_data){ + .name = "gpll4_early", + .parent_data = &(const struct clk_parent_data) { + .index = DT_XO, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll4 = { + .offset = 0x24000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpll4", + .parent_hws = (const struct clk_hw*[]){ + &gpll4_early.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_alpha_pll_postdiv_ro_ops, + }, +}; + +static struct clk_pll gpll6_early = { + .l_reg = 0x37004, + .m_reg = 0x37008, + .n_reg = 0x3700c, + .config_reg = 0x37014, + .mode_reg = 0x37000, + .status_reg = 0x3701c, + .status_bit = 17, + .clkr.hw.init = &(struct clk_init_data){ + .name = "gpll6_early", + .parent_data = &(const struct clk_parent_data) { + .index = DT_XO, + }, + .num_parents = 1, + .ops = &clk_pll_ops, + }, +}; + +static struct clk_regmap gpll6 = { + .enable_reg = 0x45000, + .enable_mask = BIT(7), + .hw.init = &(struct clk_init_data){ + .name = "gpll6", + .parent_hws = (const struct clk_hw*[]){ + &gpll6_early.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_pll_vote_ops, + }, +}; + +static const struct parent_map gcc_xo_gpll0_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, +}; + +static const struct parent_map gcc_xo_gpll0_out_aux_map[] = { + { P_XO, 0 }, + { P_GPLL0, 2 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll6_sleep_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL6, 2 }, + { P_SLEEP_CLK, 6 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll6_sleep_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll6.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll6_gpll4_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL6, 2 }, + { P_GPLL4, 3 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll4_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll6.hw }, + { .hw = &gpll4.clkr.hw }, +}; + +static const struct freq_tbl ftbl_apss_ahb_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(133330000, P_GPLL0, 6, 0, 0), + { } +}; + +static struct clk_rcg2 apss_ahb_clk_src = { + .cmd_rcgr = 0x46000, + .hid_width = 5, + .freq_tbl = ftbl_apss_ahb_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "apss_ahb_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_blsp_i2c_apps_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + { } +}; + +static struct clk_rcg2 blsp1_qup2_i2c_apps_clk_src = { + .cmd_rcgr = 0x03000, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup2_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp1_qup3_i2c_apps_clk_src = { + .cmd_rcgr = 0x04000, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup3_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp1_qup4_i2c_apps_clk_src = { + .cmd_rcgr = 0x05000, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup4_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup1_i2c_apps_clk_src = { + .cmd_rcgr = 0x0c00c, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup1_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup2_i2c_apps_clk_src = { + .cmd_rcgr = 0x0d000, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup2_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup3_i2c_apps_clk_src = { + .cmd_rcgr = 0x0f000, + .hid_width = 5, + .freq_tbl = ftbl_blsp_i2c_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup3_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_blsp_spi_apps_clk_src[] = { + F(960000, P_XO, 10, 1, 2), + F(4800000, P_XO, 4, 0, 0), + F(9600000, P_XO, 2, 0, 0), + F(16000000, P_GPLL0, 10, 1, 5), + F(19200000, P_XO, 1, 0, 0), + F(25000000, P_GPLL0, 16, 1, 2), + F(50000000, P_GPLL0, 16, 0, 0), + { } +}; + +static struct clk_rcg2 blsp1_qup2_spi_apps_clk_src = { + .cmd_rcgr = 0x03014, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup2_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp1_qup3_spi_apps_clk_src = { + .cmd_rcgr = 0x04024, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup3_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp1_qup4_spi_apps_clk_src = { + .cmd_rcgr = 0x05024, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup4_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup1_spi_apps_clk_src = { + .cmd_rcgr = 0x0c024, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup1_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup2_spi_apps_clk_src = { + .cmd_rcgr = 0x0d014, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup2_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_qup3_spi_apps_clk_src = { + .cmd_rcgr = 0x0f024, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_blsp_spi_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_qup3_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_blsp_uart_apps_clk_src[] = { + F(3686400, P_GPLL0, 1, 72, 15625), + F(7372800, P_GPLL0, 1, 144, 15625), + F(14745600, P_GPLL0, 1, 288, 15625), + F(16000000, P_GPLL0, 10, 1, 5), + F(19200000, P_XO, 1, 0, 0), + F(24000000, P_GPLL0, 1, 3, 100), + F(25000000, P_GPLL0, 16, 1, 2), + F(32000000, P_GPLL0, 1, 1, 25), + F(40000000, P_GPLL0, 1, 1, 20), + F(46400000, P_GPLL0, 1, 29, 500), + F(48000000, P_GPLL0, 1, 3, 50), + F(51200000, P_GPLL0, 1, 8, 125), + F(56000000, P_GPLL0, 1, 7, 100), + F(58982400, P_GPLL0, 1, 1152, 15625), + F(60000000, P_GPLL0, 1, 3, 40), + F(64000000, P_GPLL0, 1, 2, 25), + { } +}; + +static struct clk_rcg2 blsp1_uart1_apps_clk_src = { + .cmd_rcgr = 0x02044, + .hid_width = 5, + .mnd_width = 16, + .freq_tbl = ftbl_blsp_uart_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart1_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp1_uart2_apps_clk_src = { + .cmd_rcgr = 0x03034, + .hid_width = 5, + .mnd_width = 16, + .freq_tbl = ftbl_blsp_uart_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart2_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_uart1_apps_clk_src = { + .cmd_rcgr = 0x0c044, + .hid_width = 5, + .mnd_width = 16, + .freq_tbl = ftbl_blsp_uart_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_uart1_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 blsp2_uart2_apps_clk_src = { + .cmd_rcgr = 0x0d034, + .hid_width = 5, + .mnd_width = 16, + .freq_tbl = ftbl_blsp_uart_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp2_uart2_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct parent_map gcc_byte0_map[] = { + { P_XO, 0 }, + { P_DSI0PLL_BYTE, 1 }, +}; + +static const struct clk_parent_data gcc_byte_data[] = { + { .index = DT_XO }, + { .index = DT_DSI0PLL_BYTE }, +}; + +static struct clk_rcg2 byte0_clk_src = { + .cmd_rcgr = 0x4d044, + .hid_width = 5, + .parent_map = gcc_byte0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "byte0_clk_src", + .parent_data = gcc_byte_data, + .num_parents = ARRAY_SIZE(gcc_byte_data), + .ops = &clk_byte2_ops, + .flags = CLK_SET_RATE_PARENT, + } +}; + +static const struct freq_tbl ftbl_camss_gp_clk_src[] = { + F(100000000, P_GPLL0, 8, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 camss_gp0_clk_src = { + .cmd_rcgr = 0x54000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_camss_gp_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "camss_gp0_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 camss_gp1_clk_src = { + .cmd_rcgr = 0x55000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_camss_gp_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "camss_gp1_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_camss_top_ahb_clk_src[] = { + F(40000000, P_GPLL0, 10, 1, 2), + F(61540000, P_GPLL0, 13, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + { } +}; + +static struct clk_rcg2 camss_top_ahb_clk_src = { + .cmd_rcgr = 0x5a000, + .hid_width = 5, + .freq_tbl = ftbl_camss_top_ahb_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "camss_top_ahb_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_cci_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(37500000, P_GPLL0, 1, 3, 64), + { } +}; + +static struct clk_rcg2 cci_clk_src = { + .cmd_rcgr = 0x51000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_cci_clk_src, + .parent_map = gcc_xo_gpll0_out_aux_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "cci_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct parent_map gcc_cpp_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL6, 3 }, +}; + +static const struct clk_parent_data gcc_cpp_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll6.hw }, +}; + +static const struct freq_tbl ftbl_cpp_clk_src[] = { + F(133330000, P_GPLL0, 6, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(308570000, P_GPLL0, 3.5, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + F(360000000, P_GPLL6, 3, 0, 0), + { } +}; + +static struct clk_rcg2 cpp_clk_src = { + .cmd_rcgr = 0x58018, + .hid_width = 5, + .freq_tbl = ftbl_cpp_clk_src, + .parent_map = gcc_cpp_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "cpp_clk_src", + .parent_data = gcc_cpp_data, + .num_parents = ARRAY_SIZE(gcc_cpp_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_crypto_clk_src[] = { + F(50000000, P_GPLL0, 16, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + { } +}; + +static struct clk_rcg2 crypto_clk_src = { + .cmd_rcgr = 0x16004, + .hid_width = 5, + .freq_tbl = ftbl_crypto_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "crypto_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_csi_clk_src[] = { + F(100000000, P_GPLL0, 8, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 csi0_clk_src = { + .cmd_rcgr = 0x4e020, + .hid_width = 5, + .freq_tbl = ftbl_csi_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "csi0_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 csi1_clk_src = { + .cmd_rcgr = 0x4f020, + .hid_width = 5, + .freq_tbl = ftbl_csi_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "csi1_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 csi2_clk_src = { + .cmd_rcgr = 0x3c020, + .hid_width = 5, + .freq_tbl = ftbl_csi_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "csi2_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_csi_phytimer_clk_src[] = { + F(100000000, P_GPLL0, 8, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + { } +}; + +static struct clk_rcg2 csi0phytimer_clk_src = { + .cmd_rcgr = 0x4e000, + .hid_width = 5, + .freq_tbl = ftbl_csi_phytimer_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "csi0phytimer_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 csi1phytimer_clk_src = { + .cmd_rcgr = 0x4f000, + .hid_width = 5, + .freq_tbl = ftbl_csi_phytimer_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "csi1phytimer_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_esc0_1_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 esc0_clk_src = { + .cmd_rcgr = 0x4d05c, + .hid_width = 5, + .freq_tbl = ftbl_esc0_1_clk_src, + .parent_map = gcc_xo_gpll0_out_aux_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "esc0_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct parent_map gcc_gfx3d_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL3, 2 }, + { P_GPLL6, 3 }, +}; + +static const struct parent_map gcc_gfx3d_map_qm215[] = { + { P_XO, 0 }, + { P_GPLL0, 5 }, + { P_GPLL3, 2 }, + { P_GPLL6, 6 }, +}; + +static const struct clk_parent_data gcc_gfx3d_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll3.clkr.hw }, + { .hw = &gpll6.hw }, +}; + +static const struct freq_tbl ftbl_gfx3d_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(228570000, P_GPLL0, 3.5, 0, 0), + F(240000000, P_GPLL6, 4.5, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(270000000, P_GPLL6, 4, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + F(400000000, P_GPLL0, 2, 0, 0), + F(465000000, P_GPLL3, 1, 0, 0), + F(484800000, P_GPLL3, 1, 0, 0), + F(500000000, P_GPLL3, 1, 0, 0), + F(523200000, P_GPLL3, 1, 0, 0), + F(550000000, P_GPLL3, 1, 0, 0), + F(598000000, P_GPLL3, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gfx3d_clk_src = { + .cmd_rcgr = 0x59000, + .hid_width = 5, + .freq_tbl = ftbl_gfx3d_clk_src, + .parent_map = gcc_gfx3d_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gfx3d_clk_src", + .parent_data = gcc_gfx3d_data, + .num_parents = ARRAY_SIZE(gcc_gfx3d_data), + .ops = &clk_rcg2_ops, + .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, + } +}; + +static const struct freq_tbl ftbl_gp_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gp1_clk_src = { + .cmd_rcgr = 0x08004, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_gp_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp1_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 gp2_clk_src = { + .cmd_rcgr = 0x09004, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_gp_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp2_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 gp3_clk_src = { + .cmd_rcgr = 0x0a004, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_gp_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp3_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_jpeg0_clk_src[] = { + F(133330000, P_GPLL0, 6, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 jpeg0_clk_src = { + .cmd_rcgr = 0x57000, + .hid_width = 5, + .freq_tbl = ftbl_jpeg0_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "jpeg0_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_mclk_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + F(24000000, P_GPLL6, 1, 1, 45), + F(66667000, P_GPLL0, 12, 0, 0), + { } +}; + +static struct clk_rcg2 mclk0_clk_src = { + .cmd_rcgr = 0x52000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_mclk_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "mclk0_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 mclk1_clk_src = { + .cmd_rcgr = 0x53000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_mclk_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "mclk1_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 mclk2_clk_src = { + .cmd_rcgr = 0x5c000, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_mclk_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "mclk2_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_sleep_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_sleep_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_mdp_clk_src[] = { + F(50000000, P_GPLL0, 16, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(145450000, P_GPLL0, 5.5, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(177780000, P_GPLL0, 4.5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 mdp_clk_src = { + .cmd_rcgr = 0x4d014, + .hid_width = 5, + .freq_tbl = ftbl_mdp_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "mdp_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct parent_map gcc_pclk_map[] = { + { P_XO, 0 }, + { P_DSI0PLL, 1 }, +}; + +static const struct clk_parent_data gcc_pclk_data[] = { + { .index = DT_XO }, + { .index = DT_DSI0PLL }, +}; + +static struct clk_rcg2 pclk0_clk_src = { + .cmd_rcgr = 0x4d000, + .hid_width = 5, + .mnd_width = 8, + .parent_map = gcc_pclk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pclk0_clk_src", + .parent_data = gcc_pclk_data, + .num_parents = ARRAY_SIZE(gcc_pclk_data), + .ops = &clk_pixel_ops, + .flags = CLK_SET_RATE_PARENT, + } +}; + +static const struct freq_tbl ftbl_pdm2_clk_src[] = { + F(64000000, P_GPLL0, 12.5, 0, 0), + { } +}; + +static struct clk_rcg2 pdm2_clk_src = { + .cmd_rcgr = 0x44010, + .hid_width = 5, + .freq_tbl = ftbl_pdm2_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pdm2_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_sdcc1_ice_core_clk_src[] = { + F(100000000, P_GPLL0, 8, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 sdcc1_ice_core_clk_src = { + .cmd_rcgr = 0x5d000, + .hid_width = 5, + .freq_tbl = ftbl_sdcc1_ice_core_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "sdcc1_ice_core_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct parent_map gcc_sdcc1_apps_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL4, 2 }, +}; + +static const struct clk_parent_data gcc_sdcc1_apss_data[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, +}; + +static const struct freq_tbl ftbl_sdcc1_apps_clk_src[] = { + F(144000, P_XO, 16, 3, 25), + F(400000, P_XO, 12, 1, 4), + F(20000000, P_GPLL0, 10, 1, 4), + F(25000000, P_GPLL0, 16, 1, 2), + F(50000000, P_GPLL0, 16, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(177770000, P_GPLL0, 4.5, 0, 0), + F(192000000, P_GPLL4, 6, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(384000000, P_GPLL4, 3, 0, 0), + { } +}; + +static struct clk_rcg2 sdcc1_apps_clk_src = { + .cmd_rcgr = 0x42004, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_sdcc1_apps_clk_src, + .parent_map = gcc_sdcc1_apps_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "sdcc1_apps_clk_src", + .parent_data = gcc_sdcc1_apss_data, + .num_parents = ARRAY_SIZE(gcc_sdcc1_apss_data), + .ops = &clk_rcg2_floor_ops, + } +}; + +static const struct freq_tbl ftbl_sdcc2_apps_clk_src[] = { + F(144000, P_XO, 16, 3, 25), + F(400000, P_XO, 12, 1, 4), + F(20000000, P_GPLL0, 10, 1, 4), + F(25000000, P_GPLL0, 16, 1, 2), + F(50000000, P_GPLL0, 16, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(177770000, P_GPLL0, 4.5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 sdcc2_apps_clk_src = { + .cmd_rcgr = 0x43004, + .hid_width = 5, + .mnd_width = 8, + .freq_tbl = ftbl_sdcc2_apps_clk_src, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "sdcc2_apps_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_floor_ops, + } +}; + +static const struct freq_tbl ftbl_usb_hs_system_clk_src[] = { + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(133330000, P_GPLL0, 6, 0, 0), + F(177780000, P_GPLL0, 4.5, 0, 0), + { } +}; + +static struct clk_rcg2 usb_hs_system_clk_src = { + .cmd_rcgr = 0x41010, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .freq_tbl = ftbl_usb_hs_system_clk_src, + .clkr.hw.init = &(struct clk_init_data){ + .name = "usb_hs_system_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_vcodec0_clk_src[] = { + F(133330000, P_GPLL0, 6, 0, 0), + F(180000000, P_GPLL6, 6, 0, 0), + F(228570000, P_GPLL0, 3.5, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(308570000, P_GPLL6, 3.5, 0, 0), + F(329140000, P_GPLL4, 3.5, 0, 0), + F(360000000, P_GPLL6, 3, 0, 0), + { } +}; + +static struct clk_rcg2 vcodec0_clk_src = { + .cmd_rcgr = 0x4c000, + .hid_width = 5, + .freq_tbl = ftbl_vcodec0_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "vcodec0_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_gpll4_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_gpll4_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_vfe_clk_src[] = { + F(50000000, P_GPLL0, 16, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(133330000, P_GPLL0, 6, 0, 0), + F(160000000, P_GPLL0, 5, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(266670000, P_GPLL0, 3, 0, 0), + F(308570000, P_GPLL6, 3.5, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + F(329140000, P_GPLL4, 3.5, 0, 0), + F(360000000, P_GPLL6, 3, 0, 0), + { } +}; + +static struct clk_rcg2 vfe0_clk_src = { + .cmd_rcgr = 0x58000, + .hid_width = 5, + .freq_tbl = ftbl_vfe_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "vfe0_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_gpll4_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_gpll4_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_rcg2 vfe1_clk_src = { + .cmd_rcgr = 0x58054, + .hid_width = 5, + .freq_tbl = ftbl_vfe_clk_src, + .parent_map = gcc_xo_gpll0_gpll6_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "vfe1_clk_src", + .parent_data = gcc_xo_gpll0_gpll6_gpll4_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll6_gpll4_data), + .ops = &clk_rcg2_ops, + } +}; + +static const struct freq_tbl ftbl_vsync_clk_src[] = { + F(19200000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 vsync_clk_src = { + .cmd_rcgr = 0x4d02c, + .hid_width = 5, + .freq_tbl = ftbl_vsync_clk_src, + .parent_map = gcc_xo_gpll0_out_aux_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "vsync_clk_src", + .parent_data = gcc_xo_gpll0_data, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_data), + .ops = &clk_rcg2_ops, + } +}; + +static struct clk_branch gcc_apss_tcu_clk = { + .halt_reg = 0x12018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_apss_tcu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_bimc_gfx_clk = { + .halt_reg = 0x59034, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x59034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_bimc_gfx_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_bimc_gpu_clk = { + .halt_reg = 0x59030, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x59030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_bimc_gpu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_blsp1_ahb_clk = { + .halt_reg = 0x01008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(10), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_blsp2_ahb_clk = { + .halt_reg = 0x0b008, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(20), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = { + .halt_reg = 0x03010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x03010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup2_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup2_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = { + .halt_reg = 0x04020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x04020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup3_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup3_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_qup4_i2c_apps_clk = { + .halt_reg = 0x05020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x05020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup4_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup4_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup1_i2c_apps_clk = { + .halt_reg = 0x0c008, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0c008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup1_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup1_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup2_i2c_apps_clk = { + .halt_reg = 0x0d010, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0d010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup2_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup2_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup3_i2c_apps_clk = { + .halt_reg = 0x0f020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0f020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup3_i2c_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup3_i2c_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = { + .halt_reg = 0x0300c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0300c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup2_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup2_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = { + .halt_reg = 0x0401c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0401c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup3_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup3_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_qup4_spi_apps_clk = { + .halt_reg = 0x0501c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0501c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup4_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_qup4_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup1_spi_apps_clk = { + .halt_reg = 0x0c004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0c004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup1_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup1_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup2_spi_apps_clk = { + .halt_reg = 0x0d00c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0d00c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup2_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup2_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_qup3_spi_apps_clk = { + .halt_reg = 0x0f01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0f01c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_qup3_spi_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_qup3_spi_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_uart1_apps_clk = { + .halt_reg = 0x0203c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0203c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart1_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_uart1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp1_uart2_apps_clk = { + .halt_reg = 0x0302c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0302c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart2_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp1_uart2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_uart1_apps_clk = { + .halt_reg = 0x0c03c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0c03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_uart1_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_uart1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_blsp2_uart2_apps_clk = { + .halt_reg = 0x0d02c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0d02c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp2_uart2_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &blsp2_uart2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_boot_rom_ahb_clk = { + .halt_reg = 0x1300c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(7), + .hw.init = &(struct clk_init_data) { + .name = "gcc_boot_rom_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_camss_ahb_clk = { + .halt_reg = 0x56004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x56004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_camss_cci_ahb_clk = { + .halt_reg = 0x5101c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5101c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_cci_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_cci_clk = { + .halt_reg = 0x51018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x51018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_cci_clk", + .parent_hws = (const struct clk_hw*[]){ + &cci_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_cpp_ahb_clk = { + .halt_reg = 0x58040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_cpp_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_cpp_clk = { + .halt_reg = 0x5803c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5803c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_cpp_clk", + .parent_hws = (const struct clk_hw*[]){ + &cpp_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0_ahb_clk = { + .halt_reg = 0x4e040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1_ahb_clk = { + .halt_reg = 0x4f040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi2_ahb_clk = { + .halt_reg = 0x3c040, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi2_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0_clk = { + .halt_reg = 0x4e03c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1_clk = { + .halt_reg = 0x4f03c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi2_clk = { + .halt_reg = 0x3c03c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi2_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0phy_clk = { + .halt_reg = 0x4e048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0phy_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1phy_clk = { + .halt_reg = 0x4f048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1phy_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi2phy_clk = { + .halt_reg = 0x3c048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi2phy_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0phytimer_clk = { + .halt_reg = 0x4e01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e01c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0phytimer_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi0phytimer_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1phytimer_clk = { + .halt_reg = 0x4f01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f01c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1phytimer_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi1phytimer_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0pix_clk = { + .halt_reg = 0x4e058, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0pix_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1pix_clk = { + .halt_reg = 0x4f058, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1pix_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi2pix_clk = { + .halt_reg = 0x3c058, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi2pix_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi0rdi_clk = { + .halt_reg = 0x4e050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4e050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi0rdi_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi1rdi_clk = { + .halt_reg = 0x4f050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4f050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi1rdi_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi2rdi_clk = { + .halt_reg = 0x3c050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x3c050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi2rdi_clk", + .parent_hws = (const struct clk_hw*[]){ + &csi2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi_vfe0_clk = { + .halt_reg = 0x58050, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi_vfe0_clk", + .parent_hws = (const struct clk_hw*[]){ + &vfe0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_csi_vfe1_clk = { + .halt_reg = 0x58074, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58074, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_csi_vfe1_clk", + .parent_hws = (const struct clk_hw*[]){ + &vfe1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_gp0_clk = { + .halt_reg = 0x54018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x54018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_gp0_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_gp0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_gp1_clk = { + .halt_reg = 0x55018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x55018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_gp1_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_ispif_ahb_clk = { + .halt_reg = 0x50004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x50004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_ispif_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_jpeg0_clk = { + .halt_reg = 0x57020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x57020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_jpeg0_clk", + .parent_hws = (const struct clk_hw*[]){ + &jpeg0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_jpeg_ahb_clk = { + .halt_reg = 0x57024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x57024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_jpeg_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_jpeg_axi_clk = { + .halt_reg = 0x57028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x57028, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_jpeg_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_camss_mclk0_clk = { + .halt_reg = 0x52018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x52018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_mclk0_clk", + .parent_hws = (const struct clk_hw*[]){ + &mclk0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_mclk1_clk = { + .halt_reg = 0x53018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x53018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_mclk1_clk", + .parent_hws = (const struct clk_hw*[]){ + &mclk1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_mclk2_clk = { + .halt_reg = 0x5c018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5c018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_mclk2_clk", + .parent_hws = (const struct clk_hw*[]){ + &mclk2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_micro_ahb_clk = { + .halt_reg = 0x5600c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5600c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_micro_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_top_ahb_clk = { + .halt_reg = 0x5a014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5a014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_top_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_vfe0_ahb_clk = { + .halt_reg = 0x58044, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58044, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe0_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_vfe0_axi_clk = { + .halt_reg = 0x58048, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe0_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_camss_vfe0_clk = { + .halt_reg = 0x58038, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe0_clk", + .parent_hws = (const struct clk_hw*[]){ + &vfe0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_vfe1_ahb_clk = { + .halt_reg = 0x58060, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58060, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe1_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &camss_top_ahb_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_camss_vfe1_axi_clk = { + .halt_reg = 0x58068, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x58068, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe1_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_camss_vfe1_clk = { + .halt_reg = 0x5805c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5805c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_camss_vfe1_clk", + .parent_hws = (const struct clk_hw*[]){ + &vfe1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_cpp_tbu_clk = { + .halt_reg = 0x12040, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(14), + .hw.init = &(struct clk_init_data) { + .name = "gcc_cpp_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_crypto_ahb_clk = { + .halt_reg = 0x16024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_crypto_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_crypto_axi_clk = { + .halt_reg = 0x16020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_crypto_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_crypto_clk = { + .halt_reg = 0x1601c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(2), + .hw.init = &(struct clk_init_data) { + .name = "gcc_crypto_clk", + .parent_hws = (const struct clk_hw*[]){ + &crypto_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_dcc_clk = { + .halt_reg = 0x77004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x77004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_dcc_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_gfx_tbu_clk = { + .halt_reg = 0x12010, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(3), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gfx_tbu_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gfx_tcu_clk = { + .halt_reg = 0x12020, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(2), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gfx_tcu_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gtcu_ahb_clk = { + .halt_reg = 0x12044, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(13), + .hw.init = &(struct clk_init_data){ + .name = "gcc_gtcu_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_gp1_clk = { + .halt_reg = 0x08000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x08000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_gp1_clk", + .parent_hws = (const struct clk_hw*[]){ + &gp1_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_gp2_clk = { + .halt_reg = 0x09000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x09000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_gp2_clk", + .parent_hws = (const struct clk_hw*[]){ + &gp2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_gp3_clk = { + .halt_reg = 0x0a000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x0a000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_gp3_clk", + .parent_hws = (const struct clk_hw*[]){ + &gp3_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_jpeg_tbu_clk = { + .halt_reg = 0x12034, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(10), + .hw.init = &(struct clk_init_data) { + .name = "gcc_jpeg_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_mdp_tbu_clk = { + .halt_reg = 0x1201c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdp_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_mdss_ahb_clk = { + .halt_reg = 0x4d07c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d07c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_mdss_axi_clk = { + .halt_reg = 0x4d080, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d080, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_mdss_byte0_clk = { + .halt_reg = 0x4d094, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d094, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_byte0_clk", + .parent_hws = (const struct clk_hw*[]){ + &byte0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_mdss_esc0_clk = { + .halt_reg = 0x4d098, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d098, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_esc0_clk", + .parent_hws = (const struct clk_hw*[]){ + &esc0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_mdss_mdp_clk = { + .halt_reg = 0x4d088, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d088, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_mdp_clk", + .parent_hws = (const struct clk_hw*[]){ + &mdp_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_mdss_pclk0_clk = { + .halt_reg = 0x4d084, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d084, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_pclk0_clk", + .parent_hws = (const struct clk_hw*[]){ + &pclk0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_mdss_vsync_clk = { + .halt_reg = 0x4d090, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4d090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdss_vsync_clk", + .parent_hws = (const struct clk_hw*[]){ + &vsync_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_mss_cfg_ahb_clk = { + .halt_reg = 0x49000, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x49000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mss_cfg_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_mss_q6_bimc_axi_clk = { + .halt_reg = 0x49004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x49004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mss_q6_bimc_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_oxili_ahb_clk = { + .halt_reg = 0x59028, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x59028, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_oxili_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_oxili_gfx3d_clk = { + .halt_reg = 0x59020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x59020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_oxili_gfx3d_clk", + .parent_hws = (const struct clk_hw*[]){ + &gfx3d_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_pdm2_clk = { + .halt_reg = 0x4400c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4400c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pdm2_clk", + .parent_hws = (const struct clk_hw*[]){ + &pdm2_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_pdm_ahb_clk = { + .halt_reg = 0x44004, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x44004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pdm_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_prng_ahb_clk = { + .halt_reg = 0x13004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(8), + .hw.init = &(struct clk_init_data) { + .name = "gcc_prng_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_qdss_dap_clk = { + .halt_reg = 0x29084, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x45004, + .enable_mask = BIT(11), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_dap_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_sdcc1_ice_core_clk = { + .halt_reg = 0x5d014, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x5d014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_ice_core_clk", + .parent_hws = (const struct clk_hw*[]){ + &sdcc1_ice_core_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x4201c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4201c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_sdcc2_ahb_clk = { + .halt_reg = 0x4301c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4301c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc2_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x42018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x42018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &sdcc1_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_sdcc2_apps_clk = { + .halt_reg = 0x43018, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x43018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc2_apps_clk", + .parent_hws = (const struct clk_hw*[]){ + &sdcc2_apps_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_smmu_cfg_clk = { + .halt_reg = 0x12038, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(12), + .hw.init = &(struct clk_init_data) { + .name = "gcc_smmu_cfg_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_usb2a_phy_sleep_clk = { + .halt_reg = 0x4102c, + .clkr = { + .enable_reg = 0x4102c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb2a_phy_sleep_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb_hs_ahb_clk = { + .halt_reg = 0x41008, + .clkr = { + .enable_reg = 0x41008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb_hs_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb_hs_phy_cfg_ahb_clk = { + .halt_reg = 0x41030, + .clkr = { + .enable_reg = 0x41030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb_hs_phy_cfg_ahb_clk", + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb_hs_system_clk = { + .halt_reg = 0x41004, + .clkr = { + .enable_reg = 0x41004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_usb_hs_system_clk", + .parent_hws = (const struct clk_hw*[]){ + &usb_hs_system_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_venus0_ahb_clk = { + .halt_reg = 0x4c020, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4c020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_venus0_ahb_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_venus0_axi_clk = { + .halt_reg = 0x4c024, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4c024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_venus0_axi_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_venus0_core0_vcodec0_clk = { + .halt_reg = 0x4c02c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4c02c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_venus0_core0_vcodec0_clk", + .parent_hws = (const struct clk_hw*[]){ + &vcodec0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_venus0_vcodec0_clk = { + .halt_reg = 0x4c01c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x4c01c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_venus0_vcodec0_clk", + .parent_hws = (const struct clk_hw*[]){ + &vcodec0_clk_src.clkr.hw, + }, + .num_parents = 1, + .ops = &clk_branch2_ops, + .flags = CLK_SET_RATE_PARENT, + } + } +}; + +static struct clk_branch gcc_venus_tbu_clk = { + .halt_reg = 0x12014, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(5), + .hw.init = &(struct clk_init_data) { + .name = "gcc_venus_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_vfe1_tbu_clk = { + .halt_reg = 0x12090, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(17), + .hw.init = &(struct clk_init_data) { + .name = "gcc_vfe1_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct clk_branch gcc_vfe_tbu_clk = { + .halt_reg = 0x1203c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x4500c, + .enable_mask = BIT(9), + .hw.init = &(struct clk_init_data) { + .name = "gcc_vfe_tbu_clk", + .ops = &clk_branch2_ops, + } + } +}; + +static struct gdsc venus_gdsc = { + .gdscr = 0x4c018, + .cxcs = (unsigned int []){ 0x4c024, 0x4c01c }, + .cxc_count = 2, + .pd = { + .name = "venus_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc venus_core0_gdsc = { + .gdscr = 0x4c028, + .cxcs = (unsigned int []){ 0x4c02c }, + .cxc_count = 1, + .pd = { + .name = "venus_core0", + }, + .flags = HW_CTRL, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc mdss_gdsc = { + .gdscr = 0x4d078, + .cxcs = (unsigned int []){ 0x4d080, 0x4d088 }, + .cxc_count = 2, + .pd = { + .name = "mdss_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc jpeg_gdsc = { + .gdscr = 0x5701c, + .cxcs = (unsigned int []){ 0x57020, 0x57028 }, + .cxc_count = 2, + .pd = { + .name = "jpeg_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc vfe0_gdsc = { + .gdscr = 0x58034, + .cxcs = (unsigned int []){ 0x58038, 0x58048, 0x5600c, 0x58050 }, + .cxc_count = 4, + .pd = { + .name = "vfe0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc vfe1_gdsc = { + .gdscr = 0x5806c, + .cxcs = (unsigned int []){ 0x5805c, 0x58068, 0x5600c, 0x58074 }, + .cxc_count = 4, + .pd = { + .name = "vfe1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc oxili_gx_gdsc = { + .gdscr = 0x5901c, + .clamp_io_ctrl = 0x5b00c, + .cxcs = (unsigned int []){ 0x59000, 0x59020 }, + .cxc_count = 2, + .pd = { + .name = "oxili_gx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = CLAMP_IO, +}; + +static struct gdsc cpp_gdsc = { + .gdscr = 0x58078, + .cxcs = (unsigned int []){ 0x5803c, 0x58064 }, + .cxc_count = 2, + .pd = { + .name = "cpp_gdsc", + }, + .flags = ALWAYS_ON, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct clk_regmap *gcc_msm8917_clocks[] = { + [GPLL0] = &gpll0.clkr, + [GPLL0_EARLY] = &gpll0_early.clkr, + [GPLL3] = &gpll3.clkr, + [GPLL3_EARLY] = &gpll3_early.clkr, + [GPLL4] = &gpll4.clkr, + [GPLL4_EARLY] = &gpll4_early.clkr, + [GPLL6] = &gpll6, + [GPLL6_EARLY] = &gpll6_early.clkr, + [APSS_AHB_CLK_SRC] = &apss_ahb_clk_src.clkr, + [BLSP1_QUP2_I2C_APPS_CLK_SRC] = &blsp1_qup2_i2c_apps_clk_src.clkr, + [BLSP1_QUP2_SPI_APPS_CLK_SRC] = &blsp1_qup2_spi_apps_clk_src.clkr, + [BLSP1_QUP3_I2C_APPS_CLK_SRC] = &blsp1_qup3_i2c_apps_clk_src.clkr, + [BLSP1_QUP3_SPI_APPS_CLK_SRC] = &blsp1_qup3_spi_apps_clk_src.clkr, + [BLSP1_QUP4_I2C_APPS_CLK_SRC] = &blsp1_qup4_i2c_apps_clk_src.clkr, + [BLSP1_QUP4_SPI_APPS_CLK_SRC] = &blsp1_qup4_spi_apps_clk_src.clkr, + [BLSP1_UART1_APPS_CLK_SRC] = &blsp1_uart1_apps_clk_src.clkr, + [BLSP1_UART2_APPS_CLK_SRC] = &blsp1_uart2_apps_clk_src.clkr, + [BLSP2_QUP1_I2C_APPS_CLK_SRC] = &blsp2_qup1_i2c_apps_clk_src.clkr, + [BLSP2_QUP1_SPI_APPS_CLK_SRC] = &blsp2_qup1_spi_apps_clk_src.clkr, + [BLSP2_QUP2_I2C_APPS_CLK_SRC] = &blsp2_qup2_i2c_apps_clk_src.clkr, + [BLSP2_QUP2_SPI_APPS_CLK_SRC] = &blsp2_qup2_spi_apps_clk_src.clkr, + [BLSP2_QUP3_I2C_APPS_CLK_SRC] = &blsp2_qup3_i2c_apps_clk_src.clkr, + [BLSP2_QUP3_SPI_APPS_CLK_SRC] = &blsp2_qup3_spi_apps_clk_src.clkr, + [BLSP2_UART1_APPS_CLK_SRC] = &blsp2_uart1_apps_clk_src.clkr, + [BLSP2_UART2_APPS_CLK_SRC] = &blsp2_uart2_apps_clk_src.clkr, + [BYTE0_CLK_SRC] = &byte0_clk_src.clkr, + [CAMSS_GP0_CLK_SRC] = &camss_gp0_clk_src.clkr, + [CAMSS_GP1_CLK_SRC] = &camss_gp1_clk_src.clkr, + [CAMSS_TOP_AHB_CLK_SRC] = &camss_top_ahb_clk_src.clkr, + [CCI_CLK_SRC] = &cci_clk_src.clkr, + [CPP_CLK_SRC] = &cpp_clk_src.clkr, + [CRYPTO_CLK_SRC] = &crypto_clk_src.clkr, + [CSI0PHYTIMER_CLK_SRC] = &csi0phytimer_clk_src.clkr, + [CSI0_CLK_SRC] = &csi0_clk_src.clkr, + [CSI1PHYTIMER_CLK_SRC] = &csi1phytimer_clk_src.clkr, + [CSI1_CLK_SRC] = &csi1_clk_src.clkr, + [CSI2_CLK_SRC] = &csi2_clk_src.clkr, + [ESC0_CLK_SRC] = &esc0_clk_src.clkr, + [GFX3D_CLK_SRC] = &gfx3d_clk_src.clkr, + [GP1_CLK_SRC] = &gp1_clk_src.clkr, + [GP2_CLK_SRC] = &gp2_clk_src.clkr, + [GP3_CLK_SRC] = &gp3_clk_src.clkr, + [JPEG0_CLK_SRC] = &jpeg0_clk_src.clkr, + [MCLK0_CLK_SRC] = &mclk0_clk_src.clkr, + [MCLK1_CLK_SRC] = &mclk1_clk_src.clkr, + [MCLK2_CLK_SRC] = &mclk2_clk_src.clkr, + [MDP_CLK_SRC] = &mdp_clk_src.clkr, + [PCLK0_CLK_SRC] = &pclk0_clk_src.clkr, + [PDM2_CLK_SRC] = &pdm2_clk_src.clkr, + [SDCC1_APPS_CLK_SRC] = &sdcc1_apps_clk_src.clkr, + [SDCC1_ICE_CORE_CLK_SRC] = &sdcc1_ice_core_clk_src.clkr, + [SDCC2_APPS_CLK_SRC] = &sdcc2_apps_clk_src.clkr, + [USB_HS_SYSTEM_CLK_SRC] = &usb_hs_system_clk_src.clkr, + [VCODEC0_CLK_SRC] = &vcodec0_clk_src.clkr, + [VFE0_CLK_SRC] = &vfe0_clk_src.clkr, + [VFE1_CLK_SRC] = &vfe1_clk_src.clkr, + [VSYNC_CLK_SRC] = &vsync_clk_src.clkr, + [GCC_APSS_TCU_CLK] = &gcc_apss_tcu_clk.clkr, + [GCC_BIMC_GFX_CLK] = &gcc_bimc_gfx_clk.clkr, + [GCC_BIMC_GPU_CLK] = &gcc_bimc_gpu_clk.clkr, + [GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr, + [GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr, + [GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr, + [GCC_BLSP1_QUP4_I2C_APPS_CLK] = &gcc_blsp1_qup4_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP4_SPI_APPS_CLK] = &gcc_blsp1_qup4_spi_apps_clk.clkr, + [GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr, + [GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr, + [GCC_BLSP2_AHB_CLK] = &gcc_blsp2_ahb_clk.clkr, + [GCC_BLSP2_QUP1_I2C_APPS_CLK] = &gcc_blsp2_qup1_i2c_apps_clk.clkr, + [GCC_BLSP2_QUP1_SPI_APPS_CLK] = &gcc_blsp2_qup1_spi_apps_clk.clkr, + [GCC_BLSP2_QUP2_I2C_APPS_CLK] = &gcc_blsp2_qup2_i2c_apps_clk.clkr, + [GCC_BLSP2_QUP2_SPI_APPS_CLK] = &gcc_blsp2_qup2_spi_apps_clk.clkr, + [GCC_BLSP2_QUP3_I2C_APPS_CLK] = &gcc_blsp2_qup3_i2c_apps_clk.clkr, + [GCC_BLSP2_QUP3_SPI_APPS_CLK] = &gcc_blsp2_qup3_spi_apps_clk.clkr, + [GCC_BLSP2_UART1_APPS_CLK] = &gcc_blsp2_uart1_apps_clk.clkr, + [GCC_BLSP2_UART2_APPS_CLK] = &gcc_blsp2_uart2_apps_clk.clkr, + [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, + [GCC_CAMSS_AHB_CLK] = &gcc_camss_ahb_clk.clkr, + [GCC_CAMSS_CCI_AHB_CLK] = &gcc_camss_cci_ahb_clk.clkr, + [GCC_CAMSS_CCI_CLK] = &gcc_camss_cci_clk.clkr, + [GCC_CAMSS_CPP_AHB_CLK] = &gcc_camss_cpp_ahb_clk.clkr, + [GCC_CAMSS_CPP_CLK] = &gcc_camss_cpp_clk.clkr, + [GCC_CAMSS_CSI0PHYTIMER_CLK] = &gcc_camss_csi0phytimer_clk.clkr, + [GCC_CAMSS_CSI0PHY_CLK] = &gcc_camss_csi0phy_clk.clkr, + [GCC_CAMSS_CSI0PIX_CLK] = &gcc_camss_csi0pix_clk.clkr, + [GCC_CAMSS_CSI0RDI_CLK] = &gcc_camss_csi0rdi_clk.clkr, + [GCC_CAMSS_CSI0_AHB_CLK] = &gcc_camss_csi0_ahb_clk.clkr, + [GCC_CAMSS_CSI0_CLK] = &gcc_camss_csi0_clk.clkr, + [GCC_CAMSS_CSI1PHYTIMER_CLK] = &gcc_camss_csi1phytimer_clk.clkr, + [GCC_CAMSS_CSI1PHY_CLK] = &gcc_camss_csi1phy_clk.clkr, + [GCC_CAMSS_CSI1PIX_CLK] = &gcc_camss_csi1pix_clk.clkr, + [GCC_CAMSS_CSI1RDI_CLK] = &gcc_camss_csi1rdi_clk.clkr, + [GCC_CAMSS_CSI1_AHB_CLK] = &gcc_camss_csi1_ahb_clk.clkr, + [GCC_CAMSS_CSI1_CLK] = &gcc_camss_csi1_clk.clkr, + [GCC_CAMSS_CSI2PHY_CLK] = &gcc_camss_csi2phy_clk.clkr, + [GCC_CAMSS_CSI2PIX_CLK] = &gcc_camss_csi2pix_clk.clkr, + [GCC_CAMSS_CSI2RDI_CLK] = &gcc_camss_csi2rdi_clk.clkr, + [GCC_CAMSS_CSI2_AHB_CLK] = &gcc_camss_csi2_ahb_clk.clkr, + [GCC_CAMSS_CSI2_CLK] = &gcc_camss_csi2_clk.clkr, + [GCC_CAMSS_CSI_VFE0_CLK] = &gcc_camss_csi_vfe0_clk.clkr, + [GCC_CAMSS_CSI_VFE1_CLK] = &gcc_camss_csi_vfe1_clk.clkr, + [GCC_CAMSS_GP0_CLK] = &gcc_camss_gp0_clk.clkr, + [GCC_CAMSS_GP1_CLK] = &gcc_camss_gp1_clk.clkr, + [GCC_CAMSS_ISPIF_AHB_CLK] = &gcc_camss_ispif_ahb_clk.clkr, + [GCC_CAMSS_JPEG0_CLK] = &gcc_camss_jpeg0_clk.clkr, + [GCC_CAMSS_JPEG_AHB_CLK] = &gcc_camss_jpeg_ahb_clk.clkr, + [GCC_CAMSS_JPEG_AXI_CLK] = &gcc_camss_jpeg_axi_clk.clkr, + [GCC_CAMSS_MCLK0_CLK] = &gcc_camss_mclk0_clk.clkr, + [GCC_CAMSS_MCLK1_CLK] = &gcc_camss_mclk1_clk.clkr, + [GCC_CAMSS_MCLK2_CLK] = &gcc_camss_mclk2_clk.clkr, + [GCC_CAMSS_MICRO_AHB_CLK] = &gcc_camss_micro_ahb_clk.clkr, + [GCC_CAMSS_TOP_AHB_CLK] = &gcc_camss_top_ahb_clk.clkr, + [GCC_CAMSS_VFE0_AHB_CLK] = &gcc_camss_vfe0_ahb_clk.clkr, + [GCC_CAMSS_VFE0_AXI_CLK] = &gcc_camss_vfe0_axi_clk.clkr, + [GCC_CAMSS_VFE0_CLK] = &gcc_camss_vfe0_clk.clkr, + [GCC_CAMSS_VFE1_AHB_CLK] = &gcc_camss_vfe1_ahb_clk.clkr, + [GCC_CAMSS_VFE1_AXI_CLK] = &gcc_camss_vfe1_axi_clk.clkr, + [GCC_CAMSS_VFE1_CLK] = &gcc_camss_vfe1_clk.clkr, + [GCC_CPP_TBU_CLK] = &gcc_cpp_tbu_clk.clkr, + [GCC_CRYPTO_AHB_CLK] = &gcc_crypto_ahb_clk.clkr, + [GCC_CRYPTO_AXI_CLK] = &gcc_crypto_axi_clk.clkr, + [GCC_CRYPTO_CLK] = &gcc_crypto_clk.clkr, + [GCC_DCC_CLK] = &gcc_dcc_clk.clkr, + [GCC_GFX_TBU_CLK] = &gcc_gfx_tbu_clk.clkr, + [GCC_GFX_TCU_CLK] = &gcc_gfx_tcu_clk.clkr, + [GCC_GP1_CLK] = &gcc_gp1_clk.clkr, + [GCC_GP2_CLK] = &gcc_gp2_clk.clkr, + [GCC_GP3_CLK] = &gcc_gp3_clk.clkr, + [GCC_GTCU_AHB_CLK] = &gcc_gtcu_ahb_clk.clkr, + [GCC_JPEG_TBU_CLK] = &gcc_jpeg_tbu_clk.clkr, + [GCC_MDP_TBU_CLK] = &gcc_mdp_tbu_clk.clkr, + [GCC_MDSS_AHB_CLK] = &gcc_mdss_ahb_clk.clkr, + [GCC_MDSS_AXI_CLK] = &gcc_mdss_axi_clk.clkr, + [GCC_MDSS_BYTE0_CLK] = &gcc_mdss_byte0_clk.clkr, + [GCC_MDSS_ESC0_CLK] = &gcc_mdss_esc0_clk.clkr, + [GCC_MDSS_MDP_CLK] = &gcc_mdss_mdp_clk.clkr, + [GCC_MDSS_PCLK0_CLK] = &gcc_mdss_pclk0_clk.clkr, + [GCC_MDSS_VSYNC_CLK] = &gcc_mdss_vsync_clk.clkr, + [GCC_MSS_CFG_AHB_CLK] = &gcc_mss_cfg_ahb_clk.clkr, + [GCC_MSS_Q6_BIMC_AXI_CLK] = &gcc_mss_q6_bimc_axi_clk.clkr, + [GCC_OXILI_AHB_CLK] = &gcc_oxili_ahb_clk.clkr, + [GCC_OXILI_GFX3D_CLK] = &gcc_oxili_gfx3d_clk.clkr, + [GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr, + [GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr, + [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + [GCC_QDSS_DAP_CLK] = &gcc_qdss_dap_clk.clkr, + [GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr, + [GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr, + [GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr, + [GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr, + [GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr, + [GCC_SMMU_CFG_CLK] = &gcc_smmu_cfg_clk.clkr, + [GCC_USB2A_PHY_SLEEP_CLK] = &gcc_usb2a_phy_sleep_clk.clkr, + [GCC_USB_HS_AHB_CLK] = &gcc_usb_hs_ahb_clk.clkr, + [GCC_USB_HS_PHY_CFG_AHB_CLK] = &gcc_usb_hs_phy_cfg_ahb_clk.clkr, + [GCC_USB_HS_SYSTEM_CLK] = &gcc_usb_hs_system_clk.clkr, + [GCC_VENUS0_AHB_CLK] = &gcc_venus0_ahb_clk.clkr, + [GCC_VENUS0_AXI_CLK] = &gcc_venus0_axi_clk.clkr, + [GCC_VENUS0_CORE0_VCODEC0_CLK] = &gcc_venus0_core0_vcodec0_clk.clkr, + [GCC_VENUS0_VCODEC0_CLK] = &gcc_venus0_vcodec0_clk.clkr, + [GCC_VENUS_TBU_CLK] = &gcc_venus_tbu_clk.clkr, + [GCC_VFE1_TBU_CLK] = &gcc_vfe1_tbu_clk.clkr, + [GCC_VFE_TBU_CLK] = &gcc_vfe_tbu_clk.clkr, +}; + +static const struct qcom_reset_map gcc_msm8917_resets[] = { + [GCC_CAMSS_MICRO_BCR] = { 0x56008 }, + [GCC_MSS_BCR] = { 0x71000 }, + [GCC_QUSB2_PHY_BCR] = { 0x4103c }, + [GCC_USB_HS_BCR] = { 0x41000 }, + [GCC_USB2_HS_PHY_ONLY_BCR] = { 0x41034 }, +}; + +static const struct regmap_config gcc_msm8917_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x80000, + .fast_io = true, +}; + +static struct gdsc *gcc_msm8917_gdscs[] = { + [CPP_GDSC] = &cpp_gdsc, + [JPEG_GDSC] = &jpeg_gdsc, + [MDSS_GDSC] = &mdss_gdsc, + [OXILI_GX_GDSC] = &oxili_gx_gdsc, + [VENUS_CORE0_GDSC] = &venus_core0_gdsc, + [VENUS_GDSC] = &venus_gdsc, + [VFE0_GDSC] = &vfe0_gdsc, + [VFE1_GDSC] = &vfe1_gdsc, +}; + +static const struct qcom_cc_desc gcc_msm8917_desc = { + .config = &gcc_msm8917_regmap_config, + .clks = gcc_msm8917_clocks, + .num_clks = ARRAY_SIZE(gcc_msm8917_clocks), + .resets = gcc_msm8917_resets, + .num_resets = ARRAY_SIZE(gcc_msm8917_resets), + .gdscs = gcc_msm8917_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_msm8917_gdscs), +}; + +static const struct qcom_cc_desc gcc_qm215_desc = { + .config = &gcc_msm8917_regmap_config, + .clks = gcc_msm8917_clocks, + .num_clks = ARRAY_SIZE(gcc_msm8917_clocks), + .resets = gcc_msm8917_resets, + .num_resets = ARRAY_SIZE(gcc_msm8917_resets), + .gdscs = gcc_msm8917_gdscs, + .num_gdscs = ARRAY_SIZE(gcc_msm8917_gdscs), +}; + +static int gcc_msm8917_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + const struct qcom_cc_desc *gcc_desc; + + gcc_desc = of_device_get_match_data(&pdev->dev); + + if (gcc_desc == &gcc_qm215_desc) + gfx3d_clk_src.parent_map = gcc_gfx3d_map_qm215; + + regmap = qcom_cc_map(pdev, gcc_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + clk_alpha_pll_configure(&gpll3_early, regmap, &gpll3_early_config); + + return qcom_cc_really_probe(pdev, gcc_desc, regmap); +} + +static const struct of_device_id gcc_msm8917_match_table[] = { + { .compatible = "qcom,gcc-msm8917", .data = &gcc_msm8917_desc }, + { .compatible = "qcom,gcc-qm215", .data = &gcc_qm215_desc }, + {}, +}; + +static struct platform_driver gcc_msm8917_driver = { + .probe = gcc_msm8917_probe, + .driver = { + .name = "gcc-msm8917", + .of_match_table = gcc_msm8917_match_table, + }, +}; + +static int __init gcc_msm8917_init(void) +{ + return platform_driver_register(&gcc_msm8917_driver); +} +core_initcall(gcc_msm8917_init); + +static void __exit gcc_msm8917_exit(void) +{ + platform_driver_unregister(&gcc_msm8917_driver); +} +module_exit(gcc_msm8917_exit); + +MODULE_DESCRIPTION("Qualcomm GCC MSM8917 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 134da70c6406184d815a491fc9535627a05e764b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Otto=20Pfl=C3=BCger?= Date: Thu, 23 Feb 2023 19:09:35 +0100 Subject: [PATCH 0578/5631] clk: qcom: smd-rpm: Add clocks for MSM8917 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit MSM8917 has mostly the same rpm clocks as MSM8953, but lacks RF_CLK3 and IPA_CLK and additionally has the BIMC_GPU clock. Signed-off-by: Otto Pflüger Reviewed-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230223180935.60546-5-otto.pflueger@abscue.de --- drivers/clk/qcom/clk-smd-rpm.c | 35 ++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index bab96fca8916..887b945a6fb7 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -573,6 +573,40 @@ static const struct rpm_smd_clk_desc rpm_clk_msm8916 = { .num_clks = ARRAY_SIZE(msm8916_clks), }; +static struct clk_smd_rpm *msm8917_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, + [RPM_SMD_PNOC_CLK] = &clk_smd_rpm_bus_0_pcnoc_clk, + [RPM_SMD_PNOC_A_CLK] = &clk_smd_rpm_bus_0_pcnoc_a_clk, + [RPM_SMD_SNOC_CLK] = &clk_smd_rpm_bus_1_snoc_clk, + [RPM_SMD_SNOC_A_CLK] = &clk_smd_rpm_bus_1_snoc_a_clk, + [RPM_SMD_BIMC_CLK] = &clk_smd_rpm_bimc_clk, + [RPM_SMD_BIMC_A_CLK] = &clk_smd_rpm_bimc_a_clk, + [RPM_SMD_BIMC_GPU_CLK] = &clk_smd_rpm_bimc_gpu_clk, + [RPM_SMD_BIMC_GPU_A_CLK] = &clk_smd_rpm_bimc_gpu_a_clk, + [RPM_SMD_SYSMMNOC_CLK] = &clk_smd_rpm_bus_2_sysmmnoc_clk, + [RPM_SMD_SYSMMNOC_A_CLK] = &clk_smd_rpm_bus_2_sysmmnoc_a_clk, + [RPM_SMD_QDSS_CLK] = &clk_smd_rpm_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &clk_smd_rpm_qdss_a_clk, + [RPM_SMD_BB_CLK1] = &clk_smd_rpm_bb_clk1, + [RPM_SMD_BB_CLK1_A] = &clk_smd_rpm_bb_clk1_a, + [RPM_SMD_BB_CLK2] = &clk_smd_rpm_bb_clk2, + [RPM_SMD_BB_CLK2_A] = &clk_smd_rpm_bb_clk2_a, + [RPM_SMD_RF_CLK2] = &clk_smd_rpm_rf_clk2, + [RPM_SMD_RF_CLK2_A] = &clk_smd_rpm_rf_clk2_a, + [RPM_SMD_DIV_CLK2] = &clk_smd_rpm_div_clk2, + [RPM_SMD_DIV_A_CLK2] = &clk_smd_rpm_div_clk2_a, + [RPM_SMD_BB_CLK1_PIN] = &clk_smd_rpm_bb_clk1_pin, + [RPM_SMD_BB_CLK1_A_PIN] = &clk_smd_rpm_bb_clk1_a_pin, + [RPM_SMD_BB_CLK2_PIN] = &clk_smd_rpm_bb_clk2_pin, + [RPM_SMD_BB_CLK2_A_PIN] = &clk_smd_rpm_bb_clk2_a_pin, +}; + +static const struct rpm_smd_clk_desc rpm_clk_msm8917 = { + .clks = msm8917_clks, + .num_clks = ARRAY_SIZE(msm8917_clks), +}; + static struct clk_smd_rpm *msm8936_clks[] = { [RPM_SMD_XO_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo, [RPM_SMD_XO_A_CLK_SRC] = &clk_smd_rpm_branch_bi_tcxo_a, @@ -1230,6 +1264,7 @@ static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8226", .data = &rpm_clk_msm8974 }, { .compatible = "qcom,rpmcc-msm8909", .data = &rpm_clk_msm8909 }, { .compatible = "qcom,rpmcc-msm8916", .data = &rpm_clk_msm8916 }, + { .compatible = "qcom,rpmcc-msm8917", .data = &rpm_clk_msm8917 }, { .compatible = "qcom,rpmcc-msm8936", .data = &rpm_clk_msm8936 }, { .compatible = "qcom,rpmcc-msm8953", .data = &rpm_clk_msm8953 }, { .compatible = "qcom,rpmcc-msm8974", .data = &rpm_clk_msm8974 }, -- GitLab From bfedee5dc406ddcd70d667be1501659f1b232b7f Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:28:49 -0800 Subject: [PATCH 0579/5631] powerpc: Simplify sysctl registration for powersave_nap_ctl_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Signed-off-by: Michael Ellerman Link: https://msgid.link/20230310232850.3960676-2-mcgrof@kernel.org --- arch/powerpc/kernel/idle.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index b9a725abc596..b1c0418b25c8 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -107,19 +107,11 @@ static struct ctl_table powersave_nap_ctl_table[] = { }, {} }; -static struct ctl_table powersave_nap_sysctl_root[] = { - { - .procname = "kernel", - .mode = 0555, - .child = powersave_nap_ctl_table, - }, - {} -}; static int __init register_powersave_nap_sysctl(void) { - register_sysctl_table(powersave_nap_sysctl_root); + register_sysctl("kernel", powersave_nap_ctl_table); return 0; } -- GitLab From eab1fd002a4f1389496a17fe8b7bcdb510c6afed Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:50:31 +0100 Subject: [PATCH 0580/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D in rtl92e_config_rf Remove unused case RF90_PATH_C and case RF90_PATH_D. The termination condition for the loop is set to priv->num_total_rf_path = RTL819X_TOTAL_RF_PATH = 2. Because of this eRFPath cannot reach the values 2 for RF90_PATH_C and 3 for RF90_PATH_D. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/3a62c8803712e7bf905886e670fe334a13d5d753.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c b/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c index 73a86e1d0701..ecbcf0d5bb68 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c @@ -74,12 +74,10 @@ bool rtl92e_config_rf(struct net_device *dev) switch (eRFPath) { case RF90_PATH_A: - case RF90_PATH_C: u4RegValue = rtl92e_get_bb_reg(dev, pPhyReg->rfintfs, bRFSI_RFENV); break; case RF90_PATH_B: - case RF90_PATH_D: u4RegValue = rtl92e_get_bb_reg(dev, pPhyReg->rfintfs, bRFSI_RFENV<<16); break; @@ -120,12 +118,10 @@ bool rtl92e_config_rf(struct net_device *dev) switch (eRFPath) { case RF90_PATH_A: - case RF90_PATH_C: rtl92e_set_bb_reg(dev, pPhyReg->rfintfs, bRFSI_RFENV, u4RegValue); break; case RF90_PATH_B: - case RF90_PATH_D: rtl92e_set_bb_reg(dev, pPhyReg->rfintfs, bRFSI_RFENV<<16, u4RegValue); break; -- GitLab From 3faa16d5217b0abb5fcc1d5e0ea7b78a0d9df003 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:50:44 +0100 Subject: [PATCH 0581/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D for rfintfs Remove unused priv->phy_reg_def[RF90_PATH_C].rfintfs and priv->phy_reg_def[RF90_PATH_D].rfintfs. The termination condition for the loop is set to priv->num_total_rf_path = RTL819X_TOTAL_RF_PATH = 2. Because of this pPhyReg = &priv->phy_reg_def[eRFPath]; pPhyReg cannot point to array element 2 for RF90_PATH_C and 3 for RF90_PATH_D. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/801d10f460acbf0601c78dee05c7b32f1628f3a8.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 1 - 2 files changed, 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index a9e83ba811b0..94b23cb53c36 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -358,8 +358,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rfintfs = rFPGA0_XAB_RFInterfaceSW; priv->phy_reg_def[RF90_PATH_B].rfintfs = rFPGA0_XAB_RFInterfaceSW; - priv->phy_reg_def[RF90_PATH_C].rfintfs = rFPGA0_XCD_RFInterfaceSW; - priv->phy_reg_def[RF90_PATH_D].rfintfs = rFPGA0_XCD_RFInterfaceSW; priv->phy_reg_def[RF90_PATH_A].rfintfi = rFPGA0_XAB_RFInterfaceRB; priv->phy_reg_def[RF90_PATH_B].rfintfi = rFPGA0_XAB_RFInterfaceRB; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index f846f109ed98..616a4b62d4b9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -69,7 +69,6 @@ #define rFPGA0_XC_RFInterfaceOE 0x868 #define rFPGA0_XD_RFInterfaceOE 0x86c #define rFPGA0_XAB_RFInterfaceSW 0x870 -#define rFPGA0_XCD_RFInterfaceSW 0x874 #define rFPGA0_XAB_RFParameter 0x878 #define rFPGA0_XCD_RFParameter 0x87c #define rFPGA0_AnalogParameter1 0x880 -- GitLab From 308e4650ea173d0e337b496cd9ea67c0ae24c572 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:50:56 +0100 Subject: [PATCH 0582/5631] staging: rtl8192e: Remove unused variable rfintfi Remove unused variable rfintfi because it is just once set and not used. Remove unused constants as well. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/f251186fe59855eee3dd465954700a1d0ec50f53.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 1 - drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 5 ----- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 3 files changed, 8 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index ac192254a4bb..adedcea5824e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -103,7 +103,6 @@ enum rf_optype { struct bb_reg_definition { u32 rfintfs; - u32 rfintfi; u32 rfintfo; u32 rfintfe; u32 rf3wireOffset; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 94b23cb53c36..19fdf56e5e91 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -359,11 +359,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rfintfs = rFPGA0_XAB_RFInterfaceSW; priv->phy_reg_def[RF90_PATH_B].rfintfs = rFPGA0_XAB_RFInterfaceSW; - priv->phy_reg_def[RF90_PATH_A].rfintfi = rFPGA0_XAB_RFInterfaceRB; - priv->phy_reg_def[RF90_PATH_B].rfintfi = rFPGA0_XAB_RFInterfaceRB; - priv->phy_reg_def[RF90_PATH_C].rfintfi = rFPGA0_XCD_RFInterfaceRB; - priv->phy_reg_def[RF90_PATH_D].rfintfi = rFPGA0_XCD_RFInterfaceRB; - priv->phy_reg_def[RF90_PATH_A].rfintfo = rFPGA0_XA_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_B].rfintfo = rFPGA0_XB_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_C].rfintfo = rFPGA0_XC_RFInterfaceOE; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 616a4b62d4b9..5a47b232945f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -80,8 +80,6 @@ #define rFPGA0_XC_LSSIReadBack 0x8a8 #define rFPGA0_XD_LSSIReadBack 0x8ac #define rFPGA0_PSDReport 0x8b4 -#define rFPGA0_XAB_RFInterfaceRB 0x8e0 -#define rFPGA0_XCD_RFInterfaceRB 0x8e4 /* Page 9 - RF mode & OFDM TxSC */ #define rFPGA1_RFMOD 0x900 -- GitLab From 0b8f11cdcb3ab3e83bc5506d6e97d95f0093647b Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:51:11 +0100 Subject: [PATCH 0583/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D for rfintfo and ..fe Remove unused priv->phy_reg_def[RF90_PATH_C].rfintfo and priv->phy_reg_def[RF90_PATH_D].rfintfo and remove unused priv->phy_reg_def[RF90_PATH_C].rfintfe and priv->phy_reg_def[RF90_PATH_D].rfintfe. The termination condition for the loop is set to priv->num_total_rf_path = RTL819X_TOTAL_RF_PATH = 2. Because of this pPhyReg = &priv->phy_reg_def[eRFPath]; pPhyReg cannot point to array element 2 for RF90_PATH_C and 3 for RF90_PATH_D. Remove unused constants as well. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/3c2237e2b4094129143594a5ab45691e9961e100.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 4 ---- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 2 files changed, 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 19fdf56e5e91..a0dd628b1bf5 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -361,13 +361,9 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rfintfo = rFPGA0_XA_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_B].rfintfo = rFPGA0_XB_RFInterfaceOE; - priv->phy_reg_def[RF90_PATH_C].rfintfo = rFPGA0_XC_RFInterfaceOE; - priv->phy_reg_def[RF90_PATH_D].rfintfo = rFPGA0_XD_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_A].rfintfe = rFPGA0_XA_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_B].rfintfe = rFPGA0_XB_RFInterfaceOE; - priv->phy_reg_def[RF90_PATH_C].rfintfe = rFPGA0_XC_RFInterfaceOE; - priv->phy_reg_def[RF90_PATH_D].rfintfe = rFPGA0_XD_RFInterfaceOE; priv->phy_reg_def[RF90_PATH_A].rf3wireOffset = rFPGA0_XA_LSSIParameter; priv->phy_reg_def[RF90_PATH_B].rf3wireOffset = rFPGA0_XB_LSSIParameter; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 5a47b232945f..ec39de9e89fe 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -66,8 +66,6 @@ #define rFPGA0_XCD_SwitchControl 0x85c #define rFPGA0_XA_RFInterfaceOE 0x860 #define rFPGA0_XB_RFInterfaceOE 0x864 -#define rFPGA0_XC_RFInterfaceOE 0x868 -#define rFPGA0_XD_RFInterfaceOE 0x86c #define rFPGA0_XAB_RFInterfaceSW 0x870 #define rFPGA0_XAB_RFParameter 0x878 #define rFPGA0_XCD_RFParameter 0x87c -- GitLab From 9272ddf969bc1656179c095b7fc683b08b1f6d5e Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:51:23 +0100 Subject: [PATCH 0584/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D for rf3wireOffset Remove unused priv->phy_reg_def[RF90_PATH_C].rf3wireOffset and priv->phy_reg_def[RF90_PATH_D].rf3wireOffset. rf3wireOffset is used in _rtl92e_phy_rf_read and _rtl92e_phy_rf_write which are used in: rtl92e_set_rf_reg and rtl92e_get_rf_reg are used in: rtl92e_set_bandwidth (eRFPath only for 0 and 1) rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_phy_switch_channel_step (eRFPath only for 0 and 1) _rtl92e_dm_check_tx_power_tracking_thermal (eRFPath only for 0) rtl92e_check_bb_and_rf is used in: rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_bb_config_para_file (eRFPath only for 0) rtl92e_config_rf_path is used in: rtl92e_config_rf (eRFPath only for 0 and 1) Remove dead code and constants. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/180723eee77f70ffda1f8f0656c2f256f005c4ef.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index a0dd628b1bf5..1013ab95bc7b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -367,8 +367,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rf3wireOffset = rFPGA0_XA_LSSIParameter; priv->phy_reg_def[RF90_PATH_B].rf3wireOffset = rFPGA0_XB_LSSIParameter; - priv->phy_reg_def[RF90_PATH_C].rf3wireOffset = rFPGA0_XC_LSSIParameter; - priv->phy_reg_def[RF90_PATH_D].rf3wireOffset = rFPGA0_XD_LSSIParameter; priv->phy_reg_def[RF90_PATH_A].rfLSSI_Select = rFPGA0_XAB_RFParameter; priv->phy_reg_def[RF90_PATH_B].rfLSSI_Select = rFPGA0_XAB_RFParameter; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index ec39de9e89fe..19acc44648e1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -58,8 +58,6 @@ #define rFPGA0_XD_HSSIParameter2 0x83c #define rFPGA0_XA_LSSIParameter 0x840 #define rFPGA0_XB_LSSIParameter 0x844 -#define rFPGA0_XC_LSSIParameter 0x848 -#define rFPGA0_XD_LSSIParameter 0x84c #define rFPGA0_RFWakeUpParameter 0x850 #define rFPGA0_RFSleepUpParameter 0x854 #define rFPGA0_XAB_SwitchControl 0x858 -- GitLab From 7358afd5bee314fc740d10c1de49a1038df478e0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:51:36 +0100 Subject: [PATCH 0585/5631] staging: rtl8192e: Remove unused variable rfLSSI_Select and rfTxGainStage Remove unused variable rfLSSI_Select and rfTxGainStage because they are just once set and not used. Remove unused constants as well. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/48f05998f4d2fe2df88ff14860cc8615dd72734d.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 10 ---------- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 3 files changed, 14 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index adedcea5824e..2236c1aaf335 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -106,8 +106,6 @@ struct bb_reg_definition { u32 rfintfo; u32 rfintfe; u32 rf3wireOffset; - u32 rfLSSI_Select; - u32 rfTxGainStage; u32 rfHSSIPara1; u32 rfHSSIPara2; u32 rfSwitchControl; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 1013ab95bc7b..87f28718e732 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -368,16 +368,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rf3wireOffset = rFPGA0_XA_LSSIParameter; priv->phy_reg_def[RF90_PATH_B].rf3wireOffset = rFPGA0_XB_LSSIParameter; - priv->phy_reg_def[RF90_PATH_A].rfLSSI_Select = rFPGA0_XAB_RFParameter; - priv->phy_reg_def[RF90_PATH_B].rfLSSI_Select = rFPGA0_XAB_RFParameter; - priv->phy_reg_def[RF90_PATH_C].rfLSSI_Select = rFPGA0_XCD_RFParameter; - priv->phy_reg_def[RF90_PATH_D].rfLSSI_Select = rFPGA0_XCD_RFParameter; - - priv->phy_reg_def[RF90_PATH_A].rfTxGainStage = rFPGA0_TxGainStage; - priv->phy_reg_def[RF90_PATH_B].rfTxGainStage = rFPGA0_TxGainStage; - priv->phy_reg_def[RF90_PATH_C].rfTxGainStage = rFPGA0_TxGainStage; - priv->phy_reg_def[RF90_PATH_D].rfTxGainStage = rFPGA0_TxGainStage; - priv->phy_reg_def[RF90_PATH_A].rfHSSIPara1 = rFPGA0_XA_HSSIParameter1; priv->phy_reg_def[RF90_PATH_B].rfHSSIPara1 = rFPGA0_XB_HSSIParameter1; priv->phy_reg_def[RF90_PATH_C].rfHSSIPara1 = rFPGA0_XC_HSSIParameter1; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 19acc44648e1..b68e84dd003f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -65,8 +65,6 @@ #define rFPGA0_XA_RFInterfaceOE 0x860 #define rFPGA0_XB_RFInterfaceOE 0x864 #define rFPGA0_XAB_RFInterfaceSW 0x870 -#define rFPGA0_XAB_RFParameter 0x878 -#define rFPGA0_XCD_RFParameter 0x87c #define rFPGA0_AnalogParameter1 0x880 #define rFPGA0_AnalogParameter2 0x884 #define rFPGA0_AnalogParameter3 0x888 -- GitLab From 37acdfa8beaa8669b0980e8ece6045047126469a Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:51:49 +0100 Subject: [PATCH 0586/5631] staging: rtl8192e: Remove unused variable rfHSSIPara1 and rfSwitchControl Remove unused variable rfHSSIPara1 and rfSwitchControl because they are just once set and not used. Remove unused constants as well. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/5f13420ce5598d447aaad0fe43b807467e0a15bb.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 10 ---------- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 6 ------ 3 files changed, 18 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index 2236c1aaf335..d42eac4b6012 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -106,9 +106,7 @@ struct bb_reg_definition { u32 rfintfo; u32 rfintfe; u32 rf3wireOffset; - u32 rfHSSIPara1; u32 rfHSSIPara2; - u32 rfSwitchControl; u32 rfAGCControl1; u32 rfAGCControl2; u32 rfRxIQImbalance; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 87f28718e732..add3de156e09 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -368,21 +368,11 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rf3wireOffset = rFPGA0_XA_LSSIParameter; priv->phy_reg_def[RF90_PATH_B].rf3wireOffset = rFPGA0_XB_LSSIParameter; - priv->phy_reg_def[RF90_PATH_A].rfHSSIPara1 = rFPGA0_XA_HSSIParameter1; - priv->phy_reg_def[RF90_PATH_B].rfHSSIPara1 = rFPGA0_XB_HSSIParameter1; - priv->phy_reg_def[RF90_PATH_C].rfHSSIPara1 = rFPGA0_XC_HSSIParameter1; - priv->phy_reg_def[RF90_PATH_D].rfHSSIPara1 = rFPGA0_XD_HSSIParameter1; - priv->phy_reg_def[RF90_PATH_A].rfHSSIPara2 = rFPGA0_XA_HSSIParameter2; priv->phy_reg_def[RF90_PATH_B].rfHSSIPara2 = rFPGA0_XB_HSSIParameter2; priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 = rFPGA0_XC_HSSIParameter2; priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2 = rFPGA0_XD_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_A].rfSwitchControl = rFPGA0_XAB_SwitchControl; - priv->phy_reg_def[RF90_PATH_B].rfSwitchControl = rFPGA0_XAB_SwitchControl; - priv->phy_reg_def[RF90_PATH_C].rfSwitchControl = rFPGA0_XCD_SwitchControl; - priv->phy_reg_def[RF90_PATH_D].rfSwitchControl = rFPGA0_XCD_SwitchControl; - priv->phy_reg_def[RF90_PATH_A].rfAGCControl1 = rOFDM0_XAAGCCore1; priv->phy_reg_def[RF90_PATH_B].rfAGCControl1 = rOFDM0_XBAGCCore1; priv->phy_reg_def[RF90_PATH_C].rfAGCControl1 = rOFDM0_XCAGCCore1; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index b68e84dd003f..5062be507a30 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -48,20 +48,14 @@ #define rFPGA0_TxGainStage 0x80c #define rFPGA0_RFTiming1 0x810 #define rFPGA0_RFTiming2 0x814 -#define rFPGA0_XA_HSSIParameter1 0x820 #define rFPGA0_XA_HSSIParameter2 0x824 -#define rFPGA0_XB_HSSIParameter1 0x828 #define rFPGA0_XB_HSSIParameter2 0x82c -#define rFPGA0_XC_HSSIParameter1 0x830 #define rFPGA0_XC_HSSIParameter2 0x834 -#define rFPGA0_XD_HSSIParameter1 0x838 #define rFPGA0_XD_HSSIParameter2 0x83c #define rFPGA0_XA_LSSIParameter 0x840 #define rFPGA0_XB_LSSIParameter 0x844 #define rFPGA0_RFWakeUpParameter 0x850 #define rFPGA0_RFSleepUpParameter 0x854 -#define rFPGA0_XAB_SwitchControl 0x858 -#define rFPGA0_XCD_SwitchControl 0x85c #define rFPGA0_XA_RFInterfaceOE 0x860 #define rFPGA0_XB_RFInterfaceOE 0x864 #define rFPGA0_XAB_RFInterfaceSW 0x870 -- GitLab From 76535902f6d4ab1b0e81894e770476da3e8b199e Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:52:02 +0100 Subject: [PATCH 0587/5631] staging: rtl8192e: Remove unused variable rfAGCControl1 and rfAGCControl2 Remove unused variable rfAGCControl1 and rfAGCControl2 because they are just once set and not used. Remove unused constants as well. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/0f191930597517cf88eb6effd4c20a46c99571ad.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 10 ---------- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 4 ---- 3 files changed, 16 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index d42eac4b6012..a5d99891688d 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -107,8 +107,6 @@ struct bb_reg_definition { u32 rfintfe; u32 rf3wireOffset; u32 rfHSSIPara2; - u32 rfAGCControl1; - u32 rfAGCControl2; u32 rfRxIQImbalance; u32 rfRxAFE; u32 rfTxIQImbalance; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index add3de156e09..32806bcc953a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -373,16 +373,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 = rFPGA0_XC_HSSIParameter2; priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2 = rFPGA0_XD_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_A].rfAGCControl1 = rOFDM0_XAAGCCore1; - priv->phy_reg_def[RF90_PATH_B].rfAGCControl1 = rOFDM0_XBAGCCore1; - priv->phy_reg_def[RF90_PATH_C].rfAGCControl1 = rOFDM0_XCAGCCore1; - priv->phy_reg_def[RF90_PATH_D].rfAGCControl1 = rOFDM0_XDAGCCore1; - - priv->phy_reg_def[RF90_PATH_A].rfAGCControl2 = rOFDM0_XAAGCCore2; - priv->phy_reg_def[RF90_PATH_B].rfAGCControl2 = rOFDM0_XBAGCCore2; - priv->phy_reg_def[RF90_PATH_C].rfAGCControl2 = rOFDM0_XCAGCCore2; - priv->phy_reg_def[RF90_PATH_D].rfAGCControl2 = rOFDM0_XDAGCCore2; - priv->phy_reg_def[RF90_PATH_A].rfRxIQImbalance = rOFDM0_XARxIQImbalance; priv->phy_reg_def[RF90_PATH_B].rfRxIQImbalance = rOFDM0_XBRxIQImbalance; priv->phy_reg_def[RF90_PATH_C].rfRxIQImbalance = rOFDM0_XCRxIQImbalance; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 5062be507a30..d0ea7e06f0f7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -117,13 +117,9 @@ #define rOFDM0_CCADropThreshold 0xc48 #define rOFDM0_ECCAThreshold 0xc4c /* Energy CCA */ #define rOFDM0_XAAGCCore1 0xc50 -#define rOFDM0_XAAGCCore2 0xc54 #define rOFDM0_XBAGCCore1 0xc58 -#define rOFDM0_XBAGCCore2 0xc5c #define rOFDM0_XCAGCCore1 0xc60 -#define rOFDM0_XCAGCCore2 0xc64 #define rOFDM0_XDAGCCore1 0xc68 -#define rOFDM0_XDAGCCore2 0xc6c #define rOFDM0_AGCParameter1 0xc70 #define rOFDM0_AGCParameter2 0xc74 #define rOFDM0_AGCRSSITable 0xc78 -- GitLab From 6362c2acfc3a2629fdbfdc130b6f54c5e63e0532 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:52:15 +0100 Subject: [PATCH 0588/5631] staging: rtl8192e: Remove unused variable rfRxIQImbalance and rfRxAFE Remove unused variable rfRxIQImbalance and rfRxAFE because they are just once set and not used. Remove unused constants with commenting line. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/1d578fc962c938e76bc0df529a3c24bba7abe049.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 10 ---------- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 9 --------- 3 files changed, 21 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index a5d99891688d..a5c2ff5b4260 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -107,8 +107,6 @@ struct bb_reg_definition { u32 rfintfe; u32 rf3wireOffset; u32 rfHSSIPara2; - u32 rfRxIQImbalance; - u32 rfRxAFE; u32 rfTxIQImbalance; u32 rfTxAFE; u32 rfLSSIReadBack; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 32806bcc953a..5b63b9eac090 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -373,16 +373,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 = rFPGA0_XC_HSSIParameter2; priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2 = rFPGA0_XD_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_A].rfRxIQImbalance = rOFDM0_XARxIQImbalance; - priv->phy_reg_def[RF90_PATH_B].rfRxIQImbalance = rOFDM0_XBRxIQImbalance; - priv->phy_reg_def[RF90_PATH_C].rfRxIQImbalance = rOFDM0_XCRxIQImbalance; - priv->phy_reg_def[RF90_PATH_D].rfRxIQImbalance = rOFDM0_XDRxIQImbalance; - - priv->phy_reg_def[RF90_PATH_A].rfRxAFE = rOFDM0_XARxAFE; - priv->phy_reg_def[RF90_PATH_B].rfRxAFE = rOFDM0_XBRxAFE; - priv->phy_reg_def[RF90_PATH_C].rfRxAFE = rOFDM0_XCRxAFE; - priv->phy_reg_def[RF90_PATH_D].rfRxAFE = rOFDM0_XDRxAFE; - priv->phy_reg_def[RF90_PATH_A].rfTxIQImbalance = rOFDM0_XATxIQImbalance; priv->phy_reg_def[RF90_PATH_B].rfTxIQImbalance = rOFDM0_XBTxIQImbalance; priv->phy_reg_def[RF90_PATH_C].rfTxIQImbalance = rOFDM0_XCTxIQImbalance; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index d0ea7e06f0f7..78e90bf5d79f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -98,15 +98,6 @@ #define rOFDM0_TRxPathEnable 0xc04 #define rOFDM0_TRMuxPar 0xc08 #define rOFDM0_TRSWIsolation 0xc0c -/* RxIQ DC offset, Rx digital filter, DC notch filter */ -#define rOFDM0_XARxAFE 0xc10 -#define rOFDM0_XARxIQImbalance 0xc14 /* RxIQ imbalance matrix */ -#define rOFDM0_XBRxAFE 0xc18 -#define rOFDM0_XBRxIQImbalance 0xc1c -#define rOFDM0_XCRxAFE 0xc20 -#define rOFDM0_XCRxIQImbalance 0xc24 -#define rOFDM0_XDRxAFE 0xc28 -#define rOFDM0_XDRxIQImbalance 0xc2c #define rOFDM0_RxDetector1 0xc30 /* PD, BW & SBD */ #define rOFDM0_RxDetector2 0xc34 /* SBD */ #define rOFDM0_RxDetector3 0xc38 /* Frame Sync */ -- GitLab From 5a828b61b8b6300384fad60aa2d7fe340ff4957d Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:52:31 +0100 Subject: [PATCH 0589/5631] staging: rtl8192e: Remove unused variable rfTxIQImbalance and rfTxAFE Remove unused variable rfTxIQImbalance and rfTxAFE because they are just once set and not used. Remove unused constants. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/62453061bcf1858c23ba57bf1f279999b37b4cc3.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8190P_def.h | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 10 ---------- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 5 ----- 3 files changed, 17 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h index a5c2ff5b4260..385cca79f484 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_def.h @@ -107,8 +107,6 @@ struct bb_reg_definition { u32 rfintfe; u32 rf3wireOffset; u32 rfHSSIPara2; - u32 rfTxIQImbalance; - u32 rfTxAFE; u32 rfLSSIReadBack; u32 rfLSSIReadBackPi; }; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 5b63b9eac090..fe12df93bc60 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -373,16 +373,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 = rFPGA0_XC_HSSIParameter2; priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2 = rFPGA0_XD_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_A].rfTxIQImbalance = rOFDM0_XATxIQImbalance; - priv->phy_reg_def[RF90_PATH_B].rfTxIQImbalance = rOFDM0_XBTxIQImbalance; - priv->phy_reg_def[RF90_PATH_C].rfTxIQImbalance = rOFDM0_XCTxIQImbalance; - priv->phy_reg_def[RF90_PATH_D].rfTxIQImbalance = rOFDM0_XDTxIQImbalance; - - priv->phy_reg_def[RF90_PATH_A].rfTxAFE = rOFDM0_XATxAFE; - priv->phy_reg_def[RF90_PATH_B].rfTxAFE = rOFDM0_XBTxAFE; - priv->phy_reg_def[RF90_PATH_C].rfTxAFE = rOFDM0_XCTxAFE; - priv->phy_reg_def[RF90_PATH_D].rfTxAFE = rOFDM0_XDTxAFE; - priv->phy_reg_def[RF90_PATH_A].rfLSSIReadBack = rFPGA0_XA_LSSIReadBack; priv->phy_reg_def[RF90_PATH_B].rfLSSIReadBack = rFPGA0_XB_LSSIReadBack; priv->phy_reg_def[RF90_PATH_C].rfLSSIReadBack = rFPGA0_XC_LSSIReadBack; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 78e90bf5d79f..fe05a94561e8 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -117,12 +117,7 @@ #define rOFDM0_HTSTFAGC 0xc7c #define rOFDM0_XATxIQImbalance 0xc80 #define rOFDM0_XATxAFE 0xc84 -#define rOFDM0_XBTxIQImbalance 0xc88 -#define rOFDM0_XBTxAFE 0xc8c #define rOFDM0_XCTxIQImbalance 0xc90 -#define rOFDM0_XCTxAFE 0xc94 -#define rOFDM0_XDTxIQImbalance 0xc98 -#define rOFDM0_XDTxAFE 0xc9c #define rOFDM0_RxHPParameter 0xce0 #define rOFDM0_TxPseudoNoiseWgt 0xce4 #define rOFDM0_FrameSync 0xcf0 -- GitLab From 9d5e2ea45b58c5180aefdf1ef5071e9af445f11b Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:52:46 +0100 Subject: [PATCH 0590/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D for rfLSSIReadBack Remove unused priv->phy_reg_def[RF90_PATH_C].rfLSSIReadBack and priv->phy_reg_def[RF90_PATH_D].rfLSSIReadBack. rfLSSIReadBack is used in: _rtl92e_phy_rf_read which is used in: rtl92e_set_rf_reg and rtl92e_get_rf_reg are used in: rtl92e_set_bandwidth (eRFPath only for 0 and 1) rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_phy_switch_channel_step (eRFPath only for 0 and 1) _rtl92e_dm_check_tx_power_tracking_thermal (eRFPath only for 0) rtl92e_check_bb_and_rf is used in: rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_bb_config_para_file (eRFPath only for 0) rtl92e_config_rf_path is used in: rtl92e_config_rf (eRFPath only for 0 and 1) Remove dead code and constants. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/622777b394a896b6db08eb7faeb455e5cbeae93f.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 3 --- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 2 files changed, 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index fe12df93bc60..b26ea8dfd871 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -375,9 +375,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rfLSSIReadBack = rFPGA0_XA_LSSIReadBack; priv->phy_reg_def[RF90_PATH_B].rfLSSIReadBack = rFPGA0_XB_LSSIReadBack; - priv->phy_reg_def[RF90_PATH_C].rfLSSIReadBack = rFPGA0_XC_LSSIReadBack; - priv->phy_reg_def[RF90_PATH_D].rfLSSIReadBack = rFPGA0_XD_LSSIReadBack; - } bool rtl92e_check_bb_and_rf(struct net_device *dev, enum hw90_block CheckBlock, diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index fe05a94561e8..28f9af71f193 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -65,8 +65,6 @@ #define rFPGA0_AnalogParameter4 0x88c #define rFPGA0_XA_LSSIReadBack 0x8a0 #define rFPGA0_XB_LSSIReadBack 0x8a4 -#define rFPGA0_XC_LSSIReadBack 0x8a8 -#define rFPGA0_XD_LSSIReadBack 0x8ac #define rFPGA0_PSDReport 0x8b4 /* Page 9 - RF mode & OFDM TxSC */ -- GitLab From 3e83b45cb66a6077300bae384b59cdd2b66b00e0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 11 Mar 2023 22:52:53 +0100 Subject: [PATCH 0591/5631] staging: rtl8192e: Remove unused RF90_PATH_C and ..D for rfHSSIPara2 Remove unused priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 and priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2. rfHSSIPara2 is used in rtl92e_set_bb_reg which is used in: rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_phy_rf_read which is used in: rtl92e_set_rf_reg and rtl92e_get_rf_reg are used in: rtl92e_set_bandwidth (eRFPath only for 0 and 1) rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_phy_switch_channel_step (eRFPath only for 0 and 1) _rtl92e_dm_check_tx_power_tracking_thermal (eRFPath only for 0) rtl92e_check_bb_and_rf is used in: rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_bb_config_para_file (eRFPath only for 0) rtl92e_config_rf_path is used in: rtl92e_config_rf (eRFPath only for 0 and 1) Remove dead code and constants. Signed-off-by: Philipp Hortmann Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/186f3e59e736de6fd2111e835cdb4b633ca41bbc.1678569965.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index b26ea8dfd871..e3886db3bfbb 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -370,8 +370,6 @@ static void _rtl92e_init_bb_rf_reg_def(struct net_device *dev) priv->phy_reg_def[RF90_PATH_A].rfHSSIPara2 = rFPGA0_XA_HSSIParameter2; priv->phy_reg_def[RF90_PATH_B].rfHSSIPara2 = rFPGA0_XB_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_C].rfHSSIPara2 = rFPGA0_XC_HSSIParameter2; - priv->phy_reg_def[RF90_PATH_D].rfHSSIPara2 = rFPGA0_XD_HSSIParameter2; priv->phy_reg_def[RF90_PATH_A].rfLSSIReadBack = rFPGA0_XA_LSSIReadBack; priv->phy_reg_def[RF90_PATH_B].rfLSSIReadBack = rFPGA0_XB_LSSIReadBack; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h index 28f9af71f193..e1b30fbdf8cc 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phyreg.h @@ -50,8 +50,6 @@ #define rFPGA0_RFTiming2 0x814 #define rFPGA0_XA_HSSIParameter2 0x824 #define rFPGA0_XB_HSSIParameter2 0x82c -#define rFPGA0_XC_HSSIParameter2 0x834 -#define rFPGA0_XD_HSSIParameter2 0x83c #define rFPGA0_XA_LSSIParameter 0x840 #define rFPGA0_XB_LSSIParameter 0x844 #define rFPGA0_RFWakeUpParameter 0x850 -- GitLab From 7c4b9278d44c567f335ef3714e201e1f2074bb9d Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 13 Mar 2023 23:46:27 +0100 Subject: [PATCH 0592/5631] staging: rtl8192e: Replace RF90_PATH_C in test expression of for loop Replace RF90_PATH_C in test expression of the for loop with the variable that is commonly used. This avoids false hits when searching for usage of RF90_PATH_C and therefore improves readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/f9af7a3d3e608206a4aa4ba2bd377b9201111b3f.1678740713.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index db26e431f8b7..fb4eede0470a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -1514,7 +1514,7 @@ static void _rtl92e_process_phyinfo(struct r8192_priv *priv, u8 *buffer, return; if (!prev_st->bIsCCK && prev_st->bPacketToSelf) { - for (rfpath = RF90_PATH_A; rfpath < RF90_PATH_C; rfpath++) { + for (rfpath = RF90_PATH_A; rfpath < priv->num_total_rf_path; rfpath++) { if (!rtl92e_is_legal_rf_path(priv->rtllib->dev, rfpath)) continue; if (priv->stats.rx_rssi_percentage[rfpath] == 0) { -- GitLab From f933c226ceae738f5e9daeb73eab304bb7e3bfcc Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 13 Mar 2023 23:46:33 +0100 Subject: [PATCH 0593/5631] staging: rtl8192e: Remove function rtl92e_is_legal_rf_path Remove function rtl92e_is_legal_rf_path that will always return 1. Reason is that the eRFPath is always 0 for RF90_PATH_A or 1 for RF90_PATH_B but never 2 or 3. In most usage cases this is easy to see but for the following functions that use rtl92e_is_legal_rf_path it is more difficult: rtl92e_set_rf_reg and rtl92e_get_rf_reg are used in: rtl92e_set_bandwidth (eRFPath only for 0 and 1) rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_phy_switch_channel_step (eRFPath only for 0 and 1) _rtl92e_dm_check_tx_power_tracking_thermal (eRFPath only for 0) rtl92e_check_bb_and_rf is used in: rtl92e_config_rf (eRFPath only for 0 and 1) _rtl92e_bb_config_para_file (eRFPath only for 0) rtl92e_config_rf_path is used in: rtl92e_config_rf (eRFPath only for 0 and 1) Remove dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/b801f1f9ff3c58aedab4e3e07b2ec0a816fdf5d9.1678740713.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8190P_rtl8256.c | 6 ------ drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 -- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 18 ------------------ drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - 4 files changed, 27 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c b/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c index ecbcf0d5bb68..bb4539e337c8 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8190P_rtl8256.c @@ -22,9 +22,6 @@ void rtl92e_set_bandwidth(struct net_device *dev, } for (eRFPath = 0; eRFPath < priv->num_total_rf_path; eRFPath++) { - if (!rtl92e_is_legal_rf_path(dev, eRFPath)) - continue; - switch (bandwidth) { case HT_CHANNEL_WIDTH_20: rtl92e_set_rf_reg(dev, (enum rf90_radio_path)eRFPath, @@ -67,9 +64,6 @@ bool rtl92e_config_rf(struct net_device *dev) for (eRFPath = (enum rf90_radio_path)RF90_PATH_A; eRFPath < priv->num_total_rf_path; eRFPath++) { - if (!rtl92e_is_legal_rf_path(dev, eRFPath)) - continue; - pPhyReg = &priv->phy_reg_def[eRFPath]; switch (eRFPath) { diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index fb4eede0470a..1e7be321721b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -1515,8 +1515,6 @@ static void _rtl92e_process_phyinfo(struct r8192_priv *priv, u8 *buffer, if (!prev_st->bIsCCK && prev_st->bPacketToSelf) { for (rfpath = RF90_PATH_A; rfpath < priv->num_total_rf_path; rfpath++) { - if (!rtl92e_is_legal_rf_path(priv->rtllib->dev, rfpath)) - continue; if (priv->stats.rx_rssi_percentage[rfpath] == 0) { priv->stats.rx_rssi_percentage[rfpath] = prev_st->RxMIMOSignalStrength[rfpath]; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index e3886db3bfbb..51a20379dca0 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -47,20 +47,6 @@ static u32 _rtl92e_calculate_bit_shift(u32 dwBitMask) return ffs(dwBitMask) - 1; } -u8 rtl92e_is_legal_rf_path(struct net_device *dev, u32 eRFPath) -{ - u8 ret = 1; - struct r8192_priv *priv = rtllib_priv(dev); - - if (priv->rf_type == RF_1T2R) { - if (eRFPath == RF90_PATH_A || eRFPath == RF90_PATH_B) - ret = 1; - else if (eRFPath == RF90_PATH_C || eRFPath == RF90_PATH_D) - ret = 0; - } - return ret; -} - void rtl92e_set_bb_reg(struct net_device *dev, u32 dwRegAddr, u32 dwBitMask, u32 dwData) { @@ -196,8 +182,6 @@ void rtl92e_set_rf_reg(struct net_device *dev, enum rf90_radio_path eRFPath, struct r8192_priv *priv = rtllib_priv(dev); u32 Original_Value, BitShift, New_Value; - if (!rtl92e_is_legal_rf_path(dev, eRFPath)) - return; if (priv->rtllib->rf_power_state != rf_on && !priv->being_init_adapter) return; @@ -233,8 +217,6 @@ u32 rtl92e_get_rf_reg(struct net_device *dev, enum rf90_radio_path eRFPath, u32 Original_Value, Readback_Value, BitShift; struct r8192_priv *priv = rtllib_priv(dev); - if (!rtl92e_is_legal_rf_path(dev, eRFPath)) - return 0; if (priv->rtllib->rf_power_state != rf_on && !priv->being_init_adapter) return 0; mutex_lock(&priv->rf_mutex); diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index ac640033e843..f1d183ed7ca4 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -49,7 +49,6 @@ enum rf90_radio_path { #define bMaskLWord 0x0000ffff #define bMaskDWord 0xffffffff -u8 rtl92e_is_legal_rf_path(struct net_device *dev, u32 eRFPath); void rtl92e_set_bb_reg(struct net_device *dev, u32 dwRegAddr, u32 dwBitMask, u32 dwData); u32 rtl92e_get_bb_reg(struct net_device *dev, u32 dwRegAddr, u32 dwBitMask); -- GitLab From 3dcf9a25d85a0e2bb619c045a64845cccdaf9fc3 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:42:56 +0100 Subject: [PATCH 0594/5631] staging: rtl8192e: Join constants AGCTAB_ArrayLength with ..LengthPciE Join constants AGCTAB_ArrayLength with AGCTAB_ArrayLengthPciE to RTL8192E_AGCTAB_ARR_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/98a7553403ef95609fbcb84e4cc653628b96c56c.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 4 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 51a20379dca0..54596982bc76 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -312,7 +312,7 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) u16 AGCTAB_ArrayLen, PHY_REGArrayLen = 0; struct r8192_priv *priv = rtllib_priv(dev); - AGCTAB_ArrayLen = AGCTAB_ArrayLength; + AGCTAB_ArrayLen = RTL8192E_AGCTAB_ARR_LEN; Rtl819XAGCTAB_Array_Table = Rtl819XAGCTAB_Array; if (priv->rf_type == RF_1T2R) { PHY_REGArrayLen = PHY_REG_1T2RArrayLength; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index f1d183ed7ca4..d984380bcca3 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define AGCTAB_ArrayLength AGCTAB_ArrayLengthPciE #define MACPHY_ArrayLength MACPHY_ArrayLengthPciE #define RadioA_ArrayLength RadioA_ArrayLengthPciE #define RadioB_ArrayLength RadioB_ArrayLengthPciE diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 7101061e3519..be6c4b7c0e0e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -347,7 +347,7 @@ u32 Rtl8192PciEMACPHY_Array_PG[] = { 0x318, 0x00000fff, 0x00000800, }; -u32 Rtl8192PciEAGCTAB_Array[AGCTAB_ArrayLengthPciE] = { +u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN] = { 0xc78, 0x7d000001, 0xc78, 0x7d010001, 0xc78, 0x7d020001, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index b6d4e9696452..439847b1f52b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -21,7 +21,7 @@ extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; extern u32 Rtl8192PciEMACPHY_Array[MACPHY_ArrayLengthPciE]; #define MACPHY_Array_PGLengthPciE 30 extern u32 Rtl8192PciEMACPHY_Array_PG[MACPHY_Array_PGLengthPciE]; -#define AGCTAB_ArrayLengthPciE 384 -extern u32 Rtl8192PciEAGCTAB_Array[AGCTAB_ArrayLengthPciE]; +#define RTL8192E_AGCTAB_ARR_LEN 384 +extern u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN]; #endif -- GitLab From 27d218e343f980a252e8d08938cbebea2563e04c Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:03 +0100 Subject: [PATCH 0595/5631] staging: rtl8192e: Join constants MACPHY_ArrayLength with ..LengthPciE Join constants MACPHY_ArrayLength with MACPHY_ArrayLengthPciE to RTL8192E_MACPHY_ARR_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/881ce5739e4237ea9a31029acaa535422d41fa5f.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 54596982bc76..29918a529f77 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -291,7 +291,7 @@ void rtl92e_config_mac(struct net_device *dev) pdwArray = Rtl819XMACPHY_Array_PG; } else { - dwArrayLen = MACPHY_ArrayLength; + dwArrayLen = RTL8192E_MACPHY_ARR_LEN; pdwArray = Rtl819XMACPHY_Array; } for (i = 0; i < dwArrayLen; i += 3) { diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index d984380bcca3..611756517ce6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define MACPHY_ArrayLength MACPHY_ArrayLengthPciE #define RadioA_ArrayLength RadioA_ArrayLengthPciE #define RadioB_ArrayLength RadioB_ArrayLengthPciE #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 439847b1f52b..cb424c8fbee0 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -17,8 +17,8 @@ extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; extern u32 Rtl8192PciERadioA_Array[RadioA_ArrayLengthPciE]; #define RadioB_ArrayLengthPciE 78 extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; -#define MACPHY_ArrayLengthPciE 18 -extern u32 Rtl8192PciEMACPHY_Array[MACPHY_ArrayLengthPciE]; +#define RTL8192E_MACPHY_ARR_LEN 18 +extern u32 Rtl8192PciEMACPHY_Array[RTL8192E_MACPHY_ARR_LEN]; #define MACPHY_Array_PGLengthPciE 30 extern u32 Rtl8192PciEMACPHY_Array_PG[MACPHY_Array_PGLengthPciE]; #define RTL8192E_AGCTAB_ARR_LEN 384 -- GitLab From 8f214347a71e0f57d80f44e2079a282c745a4dca Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:11 +0100 Subject: [PATCH 0596/5631] staging: rtl8192e: Join constants RadioA_ArrayLength with ..LengthPciE Join constants RadioA_ArrayLength with RadioA_ArrayLengthPciE to RTL8192E_RADIO_A_ARR_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/a03372c15cf1489b964d48d667f39c6e231fa190.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 4 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 29918a529f77..e4d1b7ad64ac 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -542,7 +542,7 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) switch (eRFPath) { case RF90_PATH_A: - for (i = 0; i < RadioA_ArrayLength; i += 2) { + for (i = 0; i < RTL8192E_RADIO_A_ARR_LEN; i += 2) { if (Rtl819XRadioA_Array[i] == 0xfe) { msleep(100); continue; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 611756517ce6..8f9200bed456 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define RadioA_ArrayLength RadioA_ArrayLengthPciE #define RadioB_ArrayLength RadioB_ArrayLengthPciE #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index be6c4b7c0e0e..5820c47f4e14 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -157,7 +157,7 @@ u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE] = { 0xe1c, 0x12121416, }; -u32 Rtl8192PciERadioA_Array[RadioA_ArrayLengthPciE] = { +u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN] = { 0x019, 0x00000003, 0x000, 0x000000bf, 0x001, 0x00000ee0, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index cb424c8fbee0..d177b7b17b19 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -13,8 +13,8 @@ #define PHY_REG_1T2RArrayLengthPciE 296 extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; -#define RadioA_ArrayLengthPciE 246 -extern u32 Rtl8192PciERadioA_Array[RadioA_ArrayLengthPciE]; +#define RTL8192E_RADIO_A_ARR_LEN 246 +extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; #define RadioB_ArrayLengthPciE 78 extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; #define RTL8192E_MACPHY_ARR_LEN 18 -- GitLab From ae9cb2196468e7e201d5a99c0a6f7fdb12719f59 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:18 +0100 Subject: [PATCH 0597/5631] staging: rtl8192e: Join constants RadioB_ArrayLength with ..LengthPciE Join constants RadioB_ArrayLength with RadioB_ArrayLengthPciE to RTL8192E_RADIO_B_ARR_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/1f48c0691eb4627be81fc39d08762617a6c58a08.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 4 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index e4d1b7ad64ac..e42b77f91528 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -554,7 +554,7 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) } break; case RF90_PATH_B: - for (i = 0; i < RadioB_ArrayLength; i += 2) { + for (i = 0; i < RTL8192E_RADIO_B_ARR_LEN; i += 2) { if (Rtl819XRadioB_Array[i] == 0xfe) { msleep(100); continue; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 8f9200bed456..e9ff224953f9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define RadioB_ArrayLength RadioB_ArrayLengthPciE #define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 5820c47f4e14..5c9844f4d117 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -283,7 +283,7 @@ u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN] = { 0x007, 0x00000700, }; -u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE] = { +u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN] = { 0x019, 0x00000003, 0x000, 0x000000bf, 0x001, 0x000006e0, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index d177b7b17b19..174a4dfb1855 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -15,8 +15,8 @@ extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; #define RTL8192E_RADIO_A_ARR_LEN 246 extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; -#define RadioB_ArrayLengthPciE 78 -extern u32 Rtl8192PciERadioB_Array[RadioB_ArrayLengthPciE]; +#define RTL8192E_RADIO_B_ARR_LEN 78 +extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 extern u32 Rtl8192PciEMACPHY_Array[RTL8192E_MACPHY_ARR_LEN]; #define MACPHY_Array_PGLengthPciE 30 -- GitLab From b89dd56751257a0aff2ed5af38945cdd6e318fdd Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:24 +0100 Subject: [PATCH 0598/5631] staging: rtl8192e: Join constants MACPHY_Array_PGLength with ..LengthPciE Join constants MACPHY_Array_PGLength with MACPHY_Array_PGLengthPciE to RTL8192E_MACPHY_ARR_PG_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6d86257ddf3fecbf2bb104f1eeedbf09a56e0861.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index e42b77f91528..86d51eb7af17 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -287,7 +287,7 @@ void rtl92e_config_mac(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); if (priv->tx_pwr_data_read_from_eeprom) { - dwArrayLen = MACPHY_Array_PGLength; + dwArrayLen = RTL8192E_MACPHY_ARR_PG_LEN; pdwArray = Rtl819XMACPHY_Array_PG; } else { diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index e9ff224953f9..73a532b96777 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define MACPHY_Array_PGLength MACPHY_Array_PGLengthPciE #define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE #define Rtl819XMACPHY_Array_PG Rtl8192PciEMACPHY_Array_PG diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 174a4dfb1855..70c31d56ea14 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -19,8 +19,8 @@ extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 extern u32 Rtl8192PciEMACPHY_Array[RTL8192E_MACPHY_ARR_LEN]; -#define MACPHY_Array_PGLengthPciE 30 -extern u32 Rtl8192PciEMACPHY_Array_PG[MACPHY_Array_PGLengthPciE]; +#define RTL8192E_MACPHY_ARR_PG_LEN 30 +extern u32 Rtl8192PciEMACPHY_Array_PG[RTL8192E_MACPHY_ARR_PG_LEN]; #define RTL8192E_AGCTAB_ARR_LEN 384 extern u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN]; -- GitLab From abeb432189962c0248657a92f7b13f80febe97a2 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:32 +0100 Subject: [PATCH 0599/5631] staging: rtl8192e: Join constants PHY_REG_1T2RArray.. with ..LengthPciE Join constants PHY_REG_1T2RArrayLength with PHY_REG_1T2RArrayLengthPciE to RTL8192E_PHY_REG_1T2R_ARR_LEN to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0e24d00350bd2c6d17558ea6b6667209e15073d2.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 4 ++-- 4 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 86d51eb7af17..231bd49b8892 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -315,7 +315,7 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) AGCTAB_ArrayLen = RTL8192E_AGCTAB_ARR_LEN; Rtl819XAGCTAB_Array_Table = Rtl819XAGCTAB_Array; if (priv->rf_type == RF_1T2R) { - PHY_REGArrayLen = PHY_REG_1T2RArrayLength; + PHY_REGArrayLen = RTL8192E_PHY_REG_1T2R_ARR_LEN; Rtl819XPHY_REGArray_Table = Rtl819XPHY_REG_1T2RArray; } diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 73a532b96777..96c581475ffe 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,8 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define PHY_REG_1T2RArrayLength PHY_REG_1T2RArrayLengthPciE - #define Rtl819XMACPHY_Array_PG Rtl8192PciEMACPHY_Array_PG #define Rtl819XMACPHY_Array Rtl8192PciEMACPHY_Array #define Rtl819XRadioA_Array Rtl8192PciERadioA_Array diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 5c9844f4d117..b2cf4d147c63 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -6,7 +6,7 @@ */ #include "table.h" -u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE] = { +u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN] = { 0x800, 0x00000000, 0x804, 0x00000001, 0x808, 0x0000fc00, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 70c31d56ea14..d00aa394c36a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -11,8 +11,8 @@ #include -#define PHY_REG_1T2RArrayLengthPciE 296 -extern u32 Rtl8192PciEPHY_REG_1T2RArray[PHY_REG_1T2RArrayLengthPciE]; +#define RTL8192E_PHY_REG_1T2R_ARR_LEN 296 +extern u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN]; #define RTL8192E_RADIO_A_ARR_LEN 246 extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; #define RTL8192E_RADIO_B_ARR_LEN 78 -- GitLab From 85246543066536a352d72b53dc2852fe0d3ae6a8 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:43 +0100 Subject: [PATCH 0600/5631] staging: rtl8192e: Join constants Rtl819XMACPHY_..PG with Rtl8192PciE.. Join constants Rtl819XMACPHY_Array_PG with Rtl8192PciEMACPHY_Array_PG to RTL8192E_MACPHY_ARR_PG to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/c8effbad931c1f7bcdee7245bf16bd2e85c03679.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 231bd49b8892..ef33f651f018 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -288,7 +288,7 @@ void rtl92e_config_mac(struct net_device *dev) if (priv->tx_pwr_data_read_from_eeprom) { dwArrayLen = RTL8192E_MACPHY_ARR_PG_LEN; - pdwArray = Rtl819XMACPHY_Array_PG; + pdwArray = RTL8192E_MACPHY_ARR_PG; } else { dwArrayLen = RTL8192E_MACPHY_ARR_LEN; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 96c581475ffe..694528ca7910 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XMACPHY_Array_PG Rtl8192PciEMACPHY_Array_PG #define Rtl819XMACPHY_Array Rtl8192PciEMACPHY_Array #define Rtl819XRadioA_Array Rtl8192PciERadioA_Array #define Rtl819XRadioB_Array Rtl8192PciERadioB_Array diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index b2cf4d147c63..aed1c46dedf6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -334,7 +334,7 @@ u32 Rtl8192PciEMACPHY_Array[] = { 0x318, 0x00000fff, 0x00000100, }; -u32 Rtl8192PciEMACPHY_Array_PG[] = { +u32 RTL8192E_MACPHY_ARR_PG[] = { 0x03c, 0xffff0000, 0x00000f0f, 0xe00, 0xffffffff, 0x06090909, 0xe04, 0xffffffff, 0x00030306, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index d00aa394c36a..f94975b112aa 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -20,7 +20,7 @@ extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 extern u32 Rtl8192PciEMACPHY_Array[RTL8192E_MACPHY_ARR_LEN]; #define RTL8192E_MACPHY_ARR_PG_LEN 30 -extern u32 Rtl8192PciEMACPHY_Array_PG[RTL8192E_MACPHY_ARR_PG_LEN]; +extern u32 RTL8192E_MACPHY_ARR_PG[RTL8192E_MACPHY_ARR_PG_LEN]; #define RTL8192E_AGCTAB_ARR_LEN 384 extern u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN]; -- GitLab From bfe890e59253f667b1ccccfa46051251ad513d51 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:52 +0100 Subject: [PATCH 0601/5631] staging: rtl8192e: Join constants Rtl819XMACPHY_.. with Rtl8192PciE.. Join constants Rtl819XMACPHY_Array with Rtl8192PciEMACPHY_Array to RTL8192E_MACPHY_ARR to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6e5609e6b31892671d203c9da1a947bd42b70c37.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index ef33f651f018..bf4fec83d316 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -292,7 +292,7 @@ void rtl92e_config_mac(struct net_device *dev) } else { dwArrayLen = RTL8192E_MACPHY_ARR_LEN; - pdwArray = Rtl819XMACPHY_Array; + pdwArray = RTL8192E_MACPHY_ARR; } for (i = 0; i < dwArrayLen; i += 3) { if (pdwArray[i] == 0x318) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 694528ca7910..2d2b80bc1f21 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XMACPHY_Array Rtl8192PciEMACPHY_Array #define Rtl819XRadioA_Array Rtl8192PciERadioA_Array #define Rtl819XRadioB_Array Rtl8192PciERadioB_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index aed1c46dedf6..0ab786d35682 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -325,7 +325,7 @@ u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN] = { 0x007, 0x00000700, }; -u32 Rtl8192PciEMACPHY_Array[] = { +u32 RTL8192E_MACPHY_ARR[] = { 0x03c, 0xffff0000, 0x00000f0f, 0x340, 0xffffffff, 0x161a1a1a, 0x344, 0xffffffff, 0x12121416, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index f94975b112aa..c6c7d4cd313e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -18,7 +18,7 @@ extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; #define RTL8192E_RADIO_B_ARR_LEN 78 extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 -extern u32 Rtl8192PciEMACPHY_Array[RTL8192E_MACPHY_ARR_LEN]; +extern u32 RTL8192E_MACPHY_ARR[RTL8192E_MACPHY_ARR_LEN]; #define RTL8192E_MACPHY_ARR_PG_LEN 30 extern u32 RTL8192E_MACPHY_ARR_PG[RTL8192E_MACPHY_ARR_PG_LEN]; #define RTL8192E_AGCTAB_ARR_LEN 384 -- GitLab From abb3551a4af8c16f2d478185b315258a62a13966 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:43:59 +0100 Subject: [PATCH 0602/5631] staging: rtl8192e: Join constants Rtl819XRadioA_.. with ..RadioA_.. Join constants Rtl819XRadioA_Array with Rtl8192PciERadioA_Array to RTL8192E_RADIO_A_ARR to improve readability. Fix spaces around '+' to improve coding style. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0ce85e55fd9ddd5459590d756a951809b6a1b9ee.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 6 +++--- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index bf4fec83d316..49fdaacb788a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -543,13 +543,13 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) switch (eRFPath) { case RF90_PATH_A: for (i = 0; i < RTL8192E_RADIO_A_ARR_LEN; i += 2) { - if (Rtl819XRadioA_Array[i] == 0xfe) { + if (RTL8192E_RADIO_A_ARR[i] == 0xfe) { msleep(100); continue; } - rtl92e_set_rf_reg(dev, eRFPath, Rtl819XRadioA_Array[i], + rtl92e_set_rf_reg(dev, eRFPath, RTL8192E_RADIO_A_ARR[i], bMask12Bits, - Rtl819XRadioA_Array[i+1]); + RTL8192E_RADIO_A_ARR[i + 1]); } break; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 2d2b80bc1f21..74c7850e514c 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XRadioA_Array Rtl8192PciERadioA_Array #define Rtl819XRadioB_Array Rtl8192PciERadioB_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 0ab786d35682..4f36a480f6f2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -157,7 +157,7 @@ u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN] = { 0xe1c, 0x12121416, }; -u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN] = { +u32 RTL8192E_RADIO_A_ARR[RTL8192E_RADIO_A_ARR_LEN] = { 0x019, 0x00000003, 0x000, 0x000000bf, 0x001, 0x00000ee0, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index c6c7d4cd313e..60917c95842b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -14,7 +14,7 @@ #define RTL8192E_PHY_REG_1T2R_ARR_LEN 296 extern u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN]; #define RTL8192E_RADIO_A_ARR_LEN 246 -extern u32 Rtl8192PciERadioA_Array[RTL8192E_RADIO_A_ARR_LEN]; +extern u32 RTL8192E_RADIO_A_ARR[RTL8192E_RADIO_A_ARR_LEN]; #define RTL8192E_RADIO_B_ARR_LEN 78 extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 -- GitLab From 22fc1bb4750150e3b743c51e5c5b8dc78fbe7ea4 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:44:07 +0100 Subject: [PATCH 0603/5631] staging: rtl8192e: Join constants Rtl819XRadioB_.. with ..RadioB_.. Join constants Rtl819XRadioB_Array with Rtl8192PciERadioB_Array to RTL8192E_RADIO_B_ARR to improve readability. Fix spaces around '+' to improve coding style. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/59af481400d5f7633bcaf7fcd95b7e5f0093fd3f.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 6 +++--- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 49fdaacb788a..5b9a1b78c35e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -555,13 +555,13 @@ u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) break; case RF90_PATH_B: for (i = 0; i < RTL8192E_RADIO_B_ARR_LEN; i += 2) { - if (Rtl819XRadioB_Array[i] == 0xfe) { + if (RTL8192E_RADIO_B_ARR[i] == 0xfe) { msleep(100); continue; } - rtl92e_set_rf_reg(dev, eRFPath, Rtl819XRadioB_Array[i], + rtl92e_set_rf_reg(dev, eRFPath, RTL8192E_RADIO_B_ARR[i], bMask12Bits, - Rtl819XRadioB_Array[i+1]); + RTL8192E_RADIO_B_ARR[i + 1]); } break; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 74c7850e514c..ee91d687de9b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XRadioB_Array Rtl8192PciERadioB_Array #define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 4f36a480f6f2..eeea01681e7d 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -283,7 +283,7 @@ u32 RTL8192E_RADIO_A_ARR[RTL8192E_RADIO_A_ARR_LEN] = { 0x007, 0x00000700, }; -u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN] = { +u32 RTL8192E_RADIO_B_ARR[RTL8192E_RADIO_B_ARR_LEN] = { 0x019, 0x00000003, 0x000, 0x000000bf, 0x001, 0x000006e0, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 60917c95842b..3023440db58b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -16,7 +16,7 @@ extern u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN]; #define RTL8192E_RADIO_A_ARR_LEN 246 extern u32 RTL8192E_RADIO_A_ARR[RTL8192E_RADIO_A_ARR_LEN]; #define RTL8192E_RADIO_B_ARR_LEN 78 -extern u32 Rtl8192PciERadioB_Array[RTL8192E_RADIO_B_ARR_LEN]; +extern u32 RTL8192E_RADIO_B_ARR[RTL8192E_RADIO_B_ARR_LEN]; #define RTL8192E_MACPHY_ARR_LEN 18 extern u32 RTL8192E_MACPHY_ARR[RTL8192E_MACPHY_ARR_LEN]; #define RTL8192E_MACPHY_ARR_PG_LEN 30 -- GitLab From dc756b9354b844c7a35385bf1b91cd9368feb18f Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:44:13 +0100 Subject: [PATCH 0604/5631] staging: rtl8192e: Join constants Rtl819XAGCTAB_.. with ..PciEAGCTAB.. Join constants Rtl819XAGCTAB_Array with Rtl8192PciEAGCTAB_Array to RTL8192E_AGCTAB_ARR to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/c7ca930adb5f72daa61b15b02001d09c4a1f8f46.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 5b9a1b78c35e..72ecdb9ea375 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -313,7 +313,7 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) struct r8192_priv *priv = rtllib_priv(dev); AGCTAB_ArrayLen = RTL8192E_AGCTAB_ARR_LEN; - Rtl819XAGCTAB_Array_Table = Rtl819XAGCTAB_Array; + Rtl819XAGCTAB_Array_Table = RTL8192E_AGCTAB_ARR; if (priv->rf_type == RF_1T2R) { PHY_REGArrayLen = RTL8192E_PHY_REG_1T2R_ARR_LEN; Rtl819XPHY_REGArray_Table = Rtl819XPHY_REG_1T2RArray; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index ee91d687de9b..1f9bafd6d3cc 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,7 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XAGCTAB_Array Rtl8192PciEAGCTAB_Array #define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray extern u32 rtl819XAGCTAB_Array[]; diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index eeea01681e7d..3a7656facefc 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -347,7 +347,7 @@ u32 RTL8192E_MACPHY_ARR_PG[] = { 0x318, 0x00000fff, 0x00000800, }; -u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN] = { +u32 RTL8192E_AGCTAB_ARR[RTL8192E_AGCTAB_ARR_LEN] = { 0xc78, 0x7d000001, 0xc78, 0x7d010001, 0xc78, 0x7d020001, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 3023440db58b..576228882c21 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -22,6 +22,6 @@ extern u32 RTL8192E_MACPHY_ARR[RTL8192E_MACPHY_ARR_LEN]; #define RTL8192E_MACPHY_ARR_PG_LEN 30 extern u32 RTL8192E_MACPHY_ARR_PG[RTL8192E_MACPHY_ARR_PG_LEN]; #define RTL8192E_AGCTAB_ARR_LEN 384 -extern u32 Rtl8192PciEAGCTAB_Array[RTL8192E_AGCTAB_ARR_LEN]; +extern u32 RTL8192E_AGCTAB_ARR[RTL8192E_AGCTAB_ARR_LEN]; #endif -- GitLab From 94f7d4a4641d2fc2dc4065b76914d0a37cebfd17 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 14 Mar 2023 19:44:20 +0100 Subject: [PATCH 0605/5631] staging: rtl8192e: Join constants Rtl819XPHY_REG_.. with ..PciEPHY_REG_.. Join constants Rtl819XPHY_REG_1T2RArray with Rtl8192PciEPHY_REG_1T2RArray to RTL8192E_PHY_REG_1T2R_ARR to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/2816a10a8a534014c58e0092b78443e01a67930a.1678814935.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- drivers/staging/rtl8192e/rtl8192e/table.c | 2 +- drivers/staging/rtl8192e/rtl8192e/table.h | 2 +- 4 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 72ecdb9ea375..2dbddf4ae3d6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -316,7 +316,7 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) Rtl819XAGCTAB_Array_Table = RTL8192E_AGCTAB_ARR; if (priv->rf_type == RF_1T2R) { PHY_REGArrayLen = RTL8192E_PHY_REG_1T2R_ARR_LEN; - Rtl819XPHY_REGArray_Table = Rtl819XPHY_REG_1T2RArray; + Rtl819XPHY_REGArray_Table = RTL8192E_PHY_REG_1T2R_ARR; } if (ConfigType == BB_CONFIG_PHY_REG) { diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 1f9bafd6d3cc..6723fcce8954 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,8 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -#define Rtl819XPHY_REG_1T2RArray Rtl8192PciEPHY_REG_1T2RArray - extern u32 rtl819XAGCTAB_Array[]; enum hw90_block { diff --git a/drivers/staging/rtl8192e/rtl8192e/table.c b/drivers/staging/rtl8192e/rtl8192e/table.c index 3a7656facefc..0b5cc6049232 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.c +++ b/drivers/staging/rtl8192e/rtl8192e/table.c @@ -6,7 +6,7 @@ */ #include "table.h" -u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN] = { +u32 RTL8192E_PHY_REG_1T2R_ARR[RTL8192E_PHY_REG_1T2R_ARR_LEN] = { 0x800, 0x00000000, 0x804, 0x00000001, 0x808, 0x0000fc00, diff --git a/drivers/staging/rtl8192e/rtl8192e/table.h b/drivers/staging/rtl8192e/rtl8192e/table.h index 576228882c21..82be44a9d4e8 100644 --- a/drivers/staging/rtl8192e/rtl8192e/table.h +++ b/drivers/staging/rtl8192e/rtl8192e/table.h @@ -12,7 +12,7 @@ #include #define RTL8192E_PHY_REG_1T2R_ARR_LEN 296 -extern u32 Rtl8192PciEPHY_REG_1T2RArray[RTL8192E_PHY_REG_1T2R_ARR_LEN]; +extern u32 RTL8192E_PHY_REG_1T2R_ARR[RTL8192E_PHY_REG_1T2R_ARR_LEN]; #define RTL8192E_RADIO_A_ARR_LEN 246 extern u32 RTL8192E_RADIO_A_ARR[RTL8192E_RADIO_A_ARR_LEN]; #define RTL8192E_RADIO_B_ARR_LEN 78 -- GitLab From 78c0fb1ad68ce120efafe86790e4a674c2c12ef4 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 10 Mar 2023 09:34:45 +0100 Subject: [PATCH 0606/5631] staging: rtl8723bs: MapCharToHexDigit() is not used The function MapCharToHexDigit() is not used anywhere, remove it. Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230310083449.23775-2-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_com.c | 16 ---------------- drivers/staging/rtl8723bs/include/hal_com.h | 2 -- 2 files changed, 18 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index e42556d03bce..b74817fc4316 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -859,22 +859,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num) return true; } -/* */ -/* Description: */ -/* Translate a character to hex digit. */ -/* */ -u32 MapCharToHexDigit(char chTmp) -{ - if (chTmp >= '0' && chTmp <= '9') - return chTmp - '0'; - else if (chTmp >= 'a' && chTmp <= 'f') - return 10 + (chTmp - 'a'); - else if (chTmp >= 'A' && chTmp <= 'F') - return 10 + (chTmp - 'A'); - else - return 0; -} - bool GetU1ByteIntegerFromStringInDecimal(char *Str, u8 *pInt) { u16 i = 0; diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index 6356b8c2ef81..8a7d31d1eaca 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -147,8 +147,6 @@ u8 GetHalDefVar(struct adapter *adapter, enum hal_def_variable variable, bool eqNByte(u8 *str1, u8 *str2, u32 num); -u32 MapCharToHexDigit(char chTmp); - bool ParseQualifiedString(char *In, u32 *Start, char *Out, char LeftQualifier, char RightQualifier); -- GitLab From e65df7f096d50200e7b6e0b545aeada510cbba63 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 10 Mar 2023 09:34:46 +0100 Subject: [PATCH 0607/5631] staging: rtl8723bs: ParseQualifiedString() is not used The function ParseQualifiedString() is not used anywhere, remove it. Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230310083449.23775-3-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_com.c | 24 --------------------- drivers/staging/rtl8723bs/include/hal_com.h | 3 --- 2 files changed, 27 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index b74817fc4316..ff0e41bf72b0 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -877,30 +877,6 @@ bool GetU1ByteIntegerFromStringInDecimal(char *Str, u8 *pInt) return true; } -/* <20121004, Kordan> For example, - * ParseQualifiedString(inString, 0, outString, '[', ']') gets "Kordan" from - * a string "Hello [Kordan]". - * If RightQualifier does not exist, it will hang in the while loop - */ -bool ParseQualifiedString( - char *In, u32 *Start, char *Out, char LeftQualifier, char RightQualifier -) -{ - u32 i = 0, j = 0; - char c = In[(*Start)++]; - - if (c != LeftQualifier) - return false; - - i = (*Start); - while ((c = In[(*Start)++]) != RightQualifier) - ; /* find ']' */ - j = (*Start) - 2; - strncpy((char *)Out, (const char *)(In+i), j-i+1); - - return true; -} - bool isAllSpaceOrTab(u8 *data, u8 size) { u8 cnt = 0, NumOfSpaceAndTab = 0; diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index 8a7d31d1eaca..31fdb5c45de3 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -147,9 +147,6 @@ u8 GetHalDefVar(struct adapter *adapter, enum hal_def_variable variable, bool eqNByte(u8 *str1, u8 *str2, u32 num); -bool ParseQualifiedString(char *In, u32 *Start, char *Out, char LeftQualifier, - char RightQualifier); - bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in); bool isAllSpaceOrTab(u8 *data, u8 size); -- GitLab From f89a163f1f66a9bea1222b0e61c3171b6bd0a080 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 10 Mar 2023 09:34:47 +0100 Subject: [PATCH 0608/5631] staging: rtl8723bs: isAllSpaceOrTab() is not used The function isAllSpaceOrTab() is not used anywhere, remove it. Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230310083449.23775-4-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_com.c | 15 --------------- drivers/staging/rtl8723bs/include/hal_com.h | 2 -- 2 files changed, 17 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index ff0e41bf72b0..da68557c5b20 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -877,21 +877,6 @@ bool GetU1ByteIntegerFromStringInDecimal(char *Str, u8 *pInt) return true; } -bool isAllSpaceOrTab(u8 *data, u8 size) -{ - u8 cnt = 0, NumOfSpaceAndTab = 0; - - while (size > cnt) { - if (data[cnt] == ' ' || data[cnt] == '\t' || data[cnt] == '\0') - ++NumOfSpaceAndTab; - - ++cnt; - } - - return size == NumOfSpaceAndTab; -} - - void rtw_hal_check_rxfifo_full(struct adapter *adapter) { struct dvobj_priv *psdpriv = adapter->dvobj; diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index 31fdb5c45de3..839d93d8a1df 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -149,8 +149,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num); bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in); -bool isAllSpaceOrTab(u8 *data, u8 size); - void linked_info_dump(struct adapter *padapter, u8 benable); #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA void rtw_get_raw_rssi_info(void *sel, struct adapter *padapter); -- GitLab From 1558280ca955c26bf0e13f7f17750a89c201d25b Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 10 Mar 2023 09:34:48 +0100 Subject: [PATCH 0609/5631] staging: rtl8723bs: linked_info_dump() is not used The function linked_info_dump() is not used anywhere, remove it. Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230310083449.23775-5-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_com.c | 21 --------------------- drivers/staging/rtl8723bs/include/hal_com.h | 1 - 2 files changed, 22 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index da68557c5b20..792636fe3270 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -897,27 +897,6 @@ void rtw_hal_check_rxfifo_full(struct adapter *adapter) } } -void linked_info_dump(struct adapter *padapter, u8 benable) -{ - struct pwrctrl_priv *pwrctrlpriv = adapter_to_pwrctl(padapter); - - if (padapter->bLinkInfoDump == benable) - return; - - if (benable) { - pwrctrlpriv->org_power_mgnt = pwrctrlpriv->power_mgnt;/* keep org value */ - rtw_pm_set_lps(padapter, PS_MODE_ACTIVE); - - pwrctrlpriv->ips_org_mode = pwrctrlpriv->ips_mode;/* keep org value */ - rtw_pm_set_ips(padapter, IPS_NONE); - } else { - rtw_pm_set_ips(padapter, pwrctrlpriv->ips_org_mode); - - rtw_pm_set_lps(padapter, pwrctrlpriv->ips_org_mode); - } - padapter->bLinkInfoDump = benable; -} - #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA void rtw_get_raw_rssi_info(void *sel, struct adapter *padapter) { diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index 839d93d8a1df..c1aa7f0a35f9 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -149,7 +149,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num); bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in); -void linked_info_dump(struct adapter *padapter, u8 benable); #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA void rtw_get_raw_rssi_info(void *sel, struct adapter *padapter); void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe); -- GitLab From 26269cbc7f2debf4cad98c74f14d0113672bb780 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 10 Mar 2023 09:34:49 +0100 Subject: [PATCH 0610/5631] staging: rtl8723bs: rtw_get_raw_rssi_info() is not used The function rtw_get_raw_rssi_info() is not used anywhere, remove it. Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230310083449.23775-6-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_com.c | 32 --------------------- drivers/staging/rtl8723bs/include/hal_com.h | 1 - 2 files changed, 33 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_com.c b/drivers/staging/rtl8723bs/hal/hal_com.c index 792636fe3270..852232102433 100644 --- a/drivers/staging/rtl8723bs/hal/hal_com.c +++ b/drivers/staging/rtl8723bs/hal/hal_com.c @@ -898,38 +898,6 @@ void rtw_hal_check_rxfifo_full(struct adapter *adapter) } #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA -void rtw_get_raw_rssi_info(void *sel, struct adapter *padapter) -{ - u8 isCCKrate, rf_path; - struct hal_com_data *pHalData = GET_HAL_DATA(padapter); - struct rx_raw_rssi *psample_pkt_rssi = &padapter->recvpriv.raw_rssi_info; - - netdev_dbg(padapter->pnetdev, - "RxRate = %s, PWDBALL = %d(%%), rx_pwr_all = %d(dBm)\n", - HDATA_RATE(psample_pkt_rssi->data_rate), - psample_pkt_rssi->pwdball, psample_pkt_rssi->pwr_all); - - isCCKrate = psample_pkt_rssi->data_rate <= DESC_RATE11M; - - if (isCCKrate) - psample_pkt_rssi->mimo_signal_strength[0] = psample_pkt_rssi->pwdball; - - for (rf_path = 0; rf_path < pHalData->NumTotalRFPath; rf_path++) { - netdev_dbg(padapter->pnetdev, - "RF_PATH_%d =>signal_strength:%d(%%), signal_quality:%d(%%)\n", - rf_path, - psample_pkt_rssi->mimo_signal_strength[rf_path], - psample_pkt_rssi->mimo_signal_quality[rf_path]); - - if (!isCCKrate) { - netdev_dbg(padapter->pnetdev, - "\trx_ofdm_pwr:%d(dBm), rx_ofdm_snr:%d(dB)\n", - psample_pkt_rssi->ofdm_pwr[rf_path], - psample_pkt_rssi->ofdm_snr[rf_path]); - } - } -} - void rtw_dump_raw_rssi_info(struct adapter *padapter) { u8 isCCKrate, rf_path; diff --git a/drivers/staging/rtl8723bs/include/hal_com.h b/drivers/staging/rtl8723bs/include/hal_com.h index c1aa7f0a35f9..17d5cfb66a36 100644 --- a/drivers/staging/rtl8723bs/include/hal_com.h +++ b/drivers/staging/rtl8723bs/include/hal_com.h @@ -150,7 +150,6 @@ bool eqNByte(u8 *str1, u8 *str2, u32 num); bool GetU1ByteIntegerFromStringInDecimal(char *str, u8 *in); #ifdef DBG_RX_SIGNAL_DISPLAY_RAW_DATA -void rtw_get_raw_rssi_info(void *sel, struct adapter *padapter); void rtw_store_phy_info(struct adapter *padapter, union recv_frame *prframe); void rtw_dump_raw_rssi_info(struct adapter *padapter); #endif -- GitLab From a59319660b0d2c628c3eee89c6406b48aa7d1a1e Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Wed, 15 Mar 2023 19:00:06 +0200 Subject: [PATCH 0611/5631] staging: vme_user: add space around operators Add a space before and after the operator, for readability. Reported by checkpatch script: " CHECK: spaces preferred around that '+', '<<' and '>>' ". Signed-off-by: Menna Mahmoud Link: https://lore.kernel.org/r/57006c151d4d95550b987143a6650f8b3594ddea.1678899549.git.eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme_user/vme_tsi148.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/staging/vme_user/vme_tsi148.c b/drivers/staging/vme_user/vme_tsi148.c index 482049cfc664..bfa604043355 100644 --- a/drivers/staging/vme_user/vme_tsi148.c +++ b/drivers/staging/vme_user/vme_tsi148.c @@ -737,7 +737,7 @@ static int tsi148_alloc_resource(struct vme_master_resource *image, return 0; if (!image->bus_resource.name) { - image->bus_resource.name = kmalloc(VMENAMSIZ+3, GFP_ATOMIC); + image->bus_resource.name = kmalloc(VMENAMSIZ + 3, GFP_ATOMIC); if (!image->bus_resource.name) { retval = -ENOMEM; goto err_name; @@ -983,7 +983,7 @@ static int tsi148_master_set(struct vme_master_resource *image, int enabled, goto err_aspace; } - temp_ctl &= ~(3<<4); + temp_ctl &= ~(3 << 4); if (cycle & VME_SUPER) temp_ctl |= TSI148_LCSR_OTAT_SUP; if (cycle & VME_PROG) @@ -2187,14 +2187,14 @@ static int tsi148_crcsr_init(struct vme_bridge *tsi148_bridge, /* Ensure that the CR/CSR is configured at the correct offset */ cbar = ioread32be(bridge->base + TSI148_CBAR); - cbar = (cbar & TSI148_CRCSR_CBAR_M)>>3; + cbar = (cbar & TSI148_CRCSR_CBAR_M) >> 3; vstat = tsi148_slot_get(tsi148_bridge); if (cbar != vstat) { cbar = vstat; dev_info(tsi148_bridge->parent, "Setting CR/CSR offset\n"); - iowrite32be(cbar<<3, bridge->base + TSI148_CBAR); + iowrite32be(cbar << 3, bridge->base + TSI148_CBAR); } dev_info(tsi148_bridge->parent, "CR/CSR Offset: %d\n", cbar); -- GitLab From 56d098b7fff39aa91701f8612b131c174976f910 Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Wed, 15 Mar 2023 19:00:07 +0200 Subject: [PATCH 0612/5631] staging: vme_user: remove unnecessary blank lines Remove unnecessary blank lines before a close brace as reported by checkpatch script "CHECK: Blank lines aren't necessary before a close brace '}'" Signed-off-by: Menna Mahmoud Link: https://lore.kernel.org/r/c8fedfeca9a56dba26846a5bed56642cc694bcbe.1678899549.git.eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme_user/vme_tsi148.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/staging/vme_user/vme_tsi148.c b/drivers/staging/vme_user/vme_tsi148.c index bfa604043355..2f5eafd50934 100644 --- a/drivers/staging/vme_user/vme_tsi148.c +++ b/drivers/staging/vme_user/vme_tsi148.c @@ -1023,7 +1023,6 @@ static int tsi148_master_set(struct vme_master_resource *image, int enabled, err_res: err_window: return retval; - } /* @@ -1741,7 +1740,6 @@ static int tsi148_dma_list_add(struct vme_dma_list *list, list); prev->descriptor.dnlau = cpu_to_be32(address_high); prev->descriptor.dnlal = cpu_to_be32(address_low); - } return 0; @@ -1773,7 +1771,6 @@ static int tsi148_dma_busy(struct vme_bridge *tsi148_bridge, int channel) return 0; else return 1; - } /* @@ -2220,7 +2217,6 @@ static int tsi148_crcsr_init(struct vme_bridge *tsi148_bridge, } return 0; - } static void tsi148_crcsr_exit(struct vme_bridge *tsi148_bridge, @@ -2530,7 +2526,6 @@ static int tsi148_probe(struct pci_dev *pdev, const struct pci_device_id *id) kfree(tsi148_bridge); err_struct: return retval; - } static void tsi148_remove(struct pci_dev *pdev) -- GitLab From 95a4919ab7328cb9442c0f8f1cfe5c3931f007f1 Mon Sep 17 00:00:00 2001 From: Archana Date: Sat, 11 Mar 2023 12:12:52 +0000 Subject: [PATCH 0613/5631] staging: wlan-ng: small cleanup in writeimage() It is cleaner to use "goto free_result;" as is being followed in rest of the implementation of writeimage function, and remove unnecessary kfree statements. Signed-off-by: Archana Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20230311121253.10225-1-craechal@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wlan-ng/prism2fw.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/wlan-ng/prism2fw.c b/drivers/staging/wlan-ng/prism2fw.c index 02a2191d5c4d..98ed9bb9192c 100644 --- a/drivers/staging/wlan-ng/prism2fw.c +++ b/drivers/staging/wlan-ng/prism2fw.c @@ -1008,12 +1008,11 @@ static int writeimage(struct wlandevice *wlandev, struct imgchunk *fchunk, rstmsg = kzalloc(sizeof(*rstmsg), GFP_KERNEL); rwrmsg = kzalloc(sizeof(*rwrmsg), GFP_KERNEL); if (!rstmsg || !rwrmsg) { - kfree(rstmsg); - kfree(rwrmsg); netdev_err(wlandev->netdev, "%s: no memory for firmware download, aborting download\n", __func__); - return -ENOMEM; + result = -ENOMEM; + goto free_result; } /* Initialize the messages */ -- GitLab From 238f55be3eaf73b161739a4a61ddb3291a42b909 Mon Sep 17 00:00:00 2001 From: Archana Date: Sat, 11 Mar 2023 12:12:53 +0000 Subject: [PATCH 0614/5631] staging: wlan-ng: small cleanup in plugimage() It's cleaner to set "j = -1;" before the if block and remove the else statement. Signed-off-by: Archana Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20230311121253.10225-2-craechal@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/wlan-ng/prism2fw.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/wlan-ng/prism2fw.c b/drivers/staging/wlan-ng/prism2fw.c index 98ed9bb9192c..11658865ca50 100644 --- a/drivers/staging/wlan-ng/prism2fw.c +++ b/drivers/staging/wlan-ng/prism2fw.c @@ -689,6 +689,7 @@ static int plugimage(struct imgchunk *fchunk, unsigned int nfchunks, for (i = 0; i < ns3plug; i++) { pstart = s3plug[i].addr; pend = s3plug[i].addr + s3plug[i].len; + j = -1; /* find the matching PDR (or filename) */ if (s3plug[i].itemcode != 0xffffffffUL) { /* not filename */ for (j = 0; j < pda->nrec; j++) { @@ -696,8 +697,6 @@ static int plugimage(struct imgchunk *fchunk, unsigned int nfchunks, le16_to_cpu(pda->rec[j]->code)) break; } - } else { - j = -1; } if (j >= pda->nrec && j != -1) { /* if no matching PDR, fail */ pr_warn("warning: Failed to find PDR for plugrec 0x%04x.\n", -- GitLab From 00b2c0918b1ff730b756ec4944f0ca68770d5b93 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sun, 12 Mar 2023 08:32:46 +0100 Subject: [PATCH 0615/5631] staging: rtl8192u: rtl8192_SetRFPowerState() is not used The function rtl8192_SetRFPowerState() is not used anywhere, remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230312073247.9822-2-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r819xU_phy.c | 87 --------------------------- drivers/staging/rtl8192u/r819xU_phy.h | 2 - 2 files changed, 89 deletions(-) diff --git a/drivers/staging/rtl8192u/r819xU_phy.c b/drivers/staging/rtl8192u/r819xU_phy.c index 97f4d89500ae..e6836eacc7aa 100644 --- a/drivers/staging/rtl8192u/r819xU_phy.c +++ b/drivers/staging/rtl8192u/r819xU_phy.c @@ -1044,93 +1044,6 @@ static void rtl8192_SetTxPowerLevel(struct net_device *dev, u8 channel) } } -/****************************************************************************** - * function: This function sets RF state on or off - * input: net_device *dev - * RT_RF_POWER_STATE eRFPowerState //Power State to set - * output: none - * return: none - * notice: - *****************************************************************************/ -bool rtl8192_SetRFPowerState(struct net_device *dev, - RT_RF_POWER_STATE eRFPowerState) -{ - bool bResult = true; - struct r8192_priv *priv = ieee80211_priv(dev); - - if (eRFPowerState == priv->ieee80211->eRFPowerState) - return false; - - if (priv->SetRFPowerStateInProgress) - return false; - - priv->SetRFPowerStateInProgress = true; - - switch (priv->rf_chip) { - case RF_8256: - switch (eRFPowerState) { - case eRfOn: - /* RF-A, RF-B */ - /* enable RF-Chip A/B - 0x860[4] */ - rtl8192_setBBreg(dev, rFPGA0_XA_RFInterfaceOE, BIT(4), - 0x1); - /* analog to digital on - 0x88c[9:8] */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter4, 0x300, - 0x3); - /* digital to analog on - 0x880[4:3] */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter1, 0x18, - 0x3); - /* rx antenna on - 0xc04[1:0] */ - rtl8192_setBBreg(dev, rOFDM0_TRxPathEnable, 0x3, 0x3); - /* rx antenna on - 0xd04[1:0] */ - rtl8192_setBBreg(dev, rOFDM1_TRxPathEnable, 0x3, 0x3); - /* analog to digital part2 on - 0x880[6:5] */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter1, 0x60, - 0x3); - - break; - - case eRfSleep: - - break; - - case eRfOff: - /* RF-A, RF-B */ - /* disable RF-Chip A/B - 0x860[4] */ - rtl8192_setBBreg(dev, rFPGA0_XA_RFInterfaceOE, BIT(4), - 0x0); - /* analog to digital off, for power save */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter4, 0xf00, - 0x0); /* 0x88c[11:8] */ - /* digital to analog off, for power save - 0x880[4:3] */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter1, 0x18, - 0x0); - /* rx antenna off - 0xc04[3:0] */ - rtl8192_setBBreg(dev, rOFDM0_TRxPathEnable, 0xf, 0x0); - /* rx antenna off - 0xd04[3:0] */ - rtl8192_setBBreg(dev, rOFDM1_TRxPathEnable, 0xf, 0x0); - /* analog to digital part2 off, for power save */ - rtl8192_setBBreg(dev, rFPGA0_AnalogParameter1, 0x60, - 0x0); /* 0x880[6:5] */ - - break; - - default: - bResult = false; - RT_TRACE(COMP_ERR, "%s(): unknown state to set: 0x%X\n", - __func__, eRFPowerState); - break; - } - break; - default: - RT_TRACE(COMP_ERR, "Not support rf_chip(%x)\n", priv->rf_chip); - break; - } - priv->SetRFPowerStateInProgress = false; - - return bResult; -} - /****************************************************************************** * function: This function sets command table variable (struct sw_chnl_cmd). * input: sw_chnl_cmd *CmdTable //table to be set diff --git a/drivers/staging/rtl8192u/r819xU_phy.h b/drivers/staging/rtl8192u/r819xU_phy.h index 8c2933264407..bafaa6a90c50 100644 --- a/drivers/staging/rtl8192u/r819xU_phy.h +++ b/drivers/staging/rtl8192u/r819xU_phy.h @@ -74,8 +74,6 @@ void rtl8192_SetBWMode(struct net_device *dev, enum ht_extension_chan_offset offset); void rtl8192_SwChnl_WorkItem(struct net_device *dev); void rtl8192_SetBWModeWorkItem(struct net_device *dev); -bool rtl8192_SetRFPowerState(struct net_device *dev, - RT_RF_POWER_STATE eRFPowerState); void InitialGain819xUsb(struct net_device *dev, u8 Operation); void InitialGainOperateWorkItemCallBack(struct work_struct *work); -- GitLab From 73633855a6b682a8cc36f581e52a3cea63393b66 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sun, 12 Mar 2023 08:32:47 +0100 Subject: [PATCH 0616/5631] staging: rtl8192u: dm_shadow_init() is not used The function dm_shadow_init() is not used anywhere, remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230312073247.9822-3-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r8192U_dm.c | 38 ---------------------------- drivers/staging/rtl8192u/r8192U_dm.h | 1 - 2 files changed, 39 deletions(-) diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c index 00fc8fd344db..6a33ca02c3dc 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.c +++ b/drivers/staging/rtl8192u/r8192U_dm.c @@ -2859,44 +2859,6 @@ void dm_check_fsync(struct net_device *dev) } } -/*----------------------------------------------------------------------------- - * Function: dm_shadow_init() - * - * Overview: Store all NIC MAC/BB register content. - * - * Input: NONE - * - * Output: NONE - * - * Return: NONE - * - * Revised History: - * When Who Remark - * 05/29/2008 amy Create Version 0 porting from windows code. - * - *--------------------------------------------------------------------------- - */ -void dm_shadow_init(struct net_device *dev) -{ - u8 page; - u16 offset; - - for (page = 0; page < 5; page++) - for (offset = 0; offset < 256; offset++) { - read_nic_byte(dev, offset + page * 256, &dm_shadow[page][offset]); - /*DbgPrint("P-%d/O-%02x=%02x\r\n", page, offset, DM_Shadow[page][offset]);*/ - } - - for (page = 8; page < 11; page++) - for (offset = 0; offset < 256; offset++) - read_nic_byte(dev, offset + page * 256, &dm_shadow[page][offset]); - - for (page = 12; page < 15; page++) - for (offset = 0; offset < 256; offset++) - read_nic_byte(dev, offset + page * 256, &dm_shadow[page][offset]); - -} /* dm_shadow_init */ - /*---------------------------Define function prototype------------------------*/ /*----------------------------------------------------------------------------- * Function: DM_DynamicTxPower() diff --git a/drivers/staging/rtl8192u/r8192U_dm.h b/drivers/staging/rtl8192u/r8192U_dm.h index 2159018b4e38..f4eb18216677 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.h +++ b/drivers/staging/rtl8192u/r8192U_dm.h @@ -168,7 +168,6 @@ void dm_rf_operation_test_callback(unsigned long data); void dm_rf_pathcheck_workitemcallback(struct work_struct *work); void dm_fsync_work_callback(struct work_struct *work); void dm_cck_txpower_adjust(struct net_device *dev, bool binch14); -void dm_shadow_init(struct net_device *dev); void dm_initialize_txpower_tracking(struct net_device *dev); /*--------------------------Exported Function prototype---------------------*/ -- GitLab From f20eed8bf6671de2e90b2f15cf6b616a72dd72cc Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Tue, 14 Mar 2023 05:11:52 -0700 Subject: [PATCH 0617/5631] Staging: qlge: Fix indentation in conditional statement Add tabs/spaces in conditional statements in to fix the indentation. Signed-off-by: Sumitra Sharma Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20230314121152.GA38979@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/qlge/qlge_dbg.c | 35 +++++++++++++++------------------ 1 file changed, 16 insertions(+), 19 deletions(-) diff --git a/drivers/staging/qlge/qlge_dbg.c b/drivers/staging/qlge/qlge_dbg.c index 66d28358342f..c7e865f515cf 100644 --- a/drivers/staging/qlge/qlge_dbg.c +++ b/drivers/staging/qlge/qlge_dbg.c @@ -351,26 +351,23 @@ static int qlge_get_xgmac_regs(struct qlge_adapter *qdev, u32 *buf, /* We're reading 400 xgmac registers, but we filter out * several locations that are non-responsive to reads. */ - if ((i == 0x00000114) || - (i == 0x00000118) || - (i == 0x0000013c) || - (i == 0x00000140) || - (i > 0x00000150 && i < 0x000001fc) || - (i > 0x00000278 && i < 0x000002a0) || - (i > 0x000002c0 && i < 0x000002cf) || - (i > 0x000002dc && i < 0x000002f0) || - (i > 0x000003c8 && i < 0x00000400) || - (i > 0x00000400 && i < 0x00000410) || - (i > 0x00000410 && i < 0x00000420) || - (i > 0x00000420 && i < 0x00000430) || - (i > 0x00000430 && i < 0x00000440) || - (i > 0x00000440 && i < 0x00000450) || - (i > 0x00000450 && i < 0x00000500) || - (i > 0x0000054c && i < 0x00000568) || - (i > 0x000005c8 && i < 0x00000600)) { + if ((i == 0x00000114) || (i == 0x00000118) || + (i == 0x0000013c) || (i == 0x00000140) || + (i > 0x00000150 && i < 0x000001fc) || + (i > 0x00000278 && i < 0x000002a0) || + (i > 0x000002c0 && i < 0x000002cf) || + (i > 0x000002dc && i < 0x000002f0) || + (i > 0x000003c8 && i < 0x00000400) || + (i > 0x00000400 && i < 0x00000410) || + (i > 0x00000410 && i < 0x00000420) || + (i > 0x00000420 && i < 0x00000430) || + (i > 0x00000430 && i < 0x00000440) || + (i > 0x00000440 && i < 0x00000450) || + (i > 0x00000450 && i < 0x00000500) || + (i > 0x0000054c && i < 0x00000568) || + (i > 0x000005c8 && i < 0x00000600)) { if (other_function) - status = - qlge_read_other_func_xgmac_reg(qdev, i, buf); + status = qlge_read_other_func_xgmac_reg(qdev, i, buf); else status = qlge_read_xgmac_reg(qdev, i, buf); -- GitLab From 4fa1387261e725a418066f8f46ea87a6ba0e5be1 Mon Sep 17 00:00:00 2001 From: Yalong Zou Date: Thu, 9 Mar 2023 23:08:15 +0800 Subject: [PATCH 0618/5631] usb: remove dead code in dwc3_gadget_get_irq platform_get_irq() only return non-zero irq number on success, or negative error number on failure. There is no need to check the return value of platform_get_irq() to determine the return value of dwc3_gadget_get_irq(), removing them to solve this problem. Signed-off-by: Yalong Zou Signed-off-by: Dongliang Mu Link: https://lore.kernel.org/r/20230309150815.1884260-1-yalongz@hust.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 07989c645a94..a1ebb30c15fa 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4402,11 +4402,6 @@ static int dwc3_gadget_get_irq(struct dwc3 *dwc) goto out; irq = platform_get_irq(dwc3_pdev, 0); - if (irq > 0) - goto out; - - if (!irq) - irq = -EINVAL; out: return irq; -- GitLab From a20bf02aaa6c026e81b2b15d5878c08f683517bb Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 9 Mar 2023 20:44:52 +0000 Subject: [PATCH 0619/5631] usb: musb: mpfs: convert SOC_MICROCHIP_POLARFIRE to ARCH_MICROCHIP_POLARFIRE As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the use of such symbols on other architectures, convert the Microchip FPGA usb glue layer driver to use the new symbol. Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230309204452.969574-6-conor@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig index 3a1f4bcea80c..9a8cf3de0617 100644 --- a/drivers/usb/musb/Kconfig +++ b/drivers/usb/musb/Kconfig @@ -113,7 +113,7 @@ config USB_MUSB_MEDIATEK config USB_MUSB_POLARFIRE_SOC tristate "Microchip PolarFire SoC platforms" - depends on SOC_MICROCHIP_POLARFIRE || COMPILE_TEST + depends on ARCH_MICROCHIP_POLARFIRE || COMPILE_TEST depends on NOP_USB_XCEIV select USB_MUSB_DUAL_ROLE help -- GitLab From a3927e1a9f1c3b7d71d9c8215905397e55da4da3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:27 -0600 Subject: [PATCH 0620/5631] usb: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144728.1545786-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/snps_udc_plat.c | 2 +- drivers/usb/host/fsl-mph-dr-of.c | 4 ++-- drivers/usb/musb/omap2430.c | 2 +- drivers/usb/phy/phy-mxs-usb.c | 2 +- drivers/usb/phy/phy-tegra-usb.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/usb/gadget/udc/snps_udc_plat.c b/drivers/usb/gadget/udc/snps_udc_plat.c index 8bbb89c80348..0d3e705655b9 100644 --- a/drivers/usb/gadget/udc/snps_udc_plat.c +++ b/drivers/usb/gadget/udc/snps_udc_plat.c @@ -158,7 +158,7 @@ static int udc_plat_probe(struct platform_device *pdev) } /* Register for extcon if supported */ - if (of_get_property(dev->of_node, "extcon", NULL)) { + if (of_property_present(dev->of_node, "extcon")) { udc->edev = extcon_get_edev_by_phandle(dev, 0); if (IS_ERR(udc->edev)) { if (PTR_ERR(udc->edev) == -EPROBE_DEFER) diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index 46c6a152b865..cdf71b716c2b 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -200,10 +200,10 @@ static int fsl_usb2_mph_dr_of_probe(struct platform_device *ofdev) dev_data = get_dr_mode_data(np); if (of_device_is_compatible(np, "fsl-usb2-mph")) { - if (of_get_property(np, "port0", NULL)) + if (of_property_present(np, "port0")) pdata->port_enables |= FSL_USB2_PORT0_ENABLED; - if (of_get_property(np, "port1", NULL)) + if (of_property_present(np, "port1")) pdata->port_enables |= FSL_USB2_PORT1_ENABLED; pdata->operating_mode = FSL_USB2_MPH_HOST; diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 44a21ec865fb..7f305b352591 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -334,7 +334,7 @@ static int omap2430_probe(struct platform_device *pdev) * Legacy SoCs using omap_device get confused if node is moved * because of interconnect properties mixed into the node. */ - if (of_get_property(np, "ti,hwmods", NULL)) { + if (of_property_present(np, "ti,hwmods")) { dev_warn(&pdev->dev, "please update to probe with ti-sysc\n"); populate_irqs = true; } else { diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index d2836ef5d15c..0a8e3fd699ca 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -733,7 +733,7 @@ static int mxs_phy_probe(struct platform_device *pdev) return -ENOMEM; /* Some SoCs don't have anatop registers */ - if (of_get_property(np, "fsl,anatop", NULL)) { + if (of_property_present(np, "fsl,anatop")) { mxs_phy->regmap_anatop = syscon_regmap_lookup_by_phandle (np, "fsl,anatop"); if (IS_ERR(mxs_phy->regmap_anatop)) { diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index f0240107edb1..4d207ce3ddf2 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -1375,7 +1375,7 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) tegra_phy->is_legacy_phy = of_property_read_bool(np, "nvidia,has-legacy-mode"); - if (of_find_property(np, "dr_mode", NULL)) + if (of_property_present(np, "dr_mode")) tegra_phy->mode = usb_get_dr_mode(&pdev->dev); else tegra_phy->mode = USB_DR_MODE_HOST; -- GitLab From f977caea50381e9ca38319037a2b23fe3209d647 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:28 -0600 Subject: [PATCH 0621/5631] usb: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Reviewed-by: Richard Leitner Link: https://lore.kernel.org/r/20230310144729.1545857-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/ci_hdrc_imx.c | 6 +++--- drivers/usb/chipidea/core.c | 2 +- drivers/usb/dwc2/params.c | 3 +-- drivers/usb/host/ehci-ppc-of.c | 6 +++--- drivers/usb/host/fsl-mph-dr-of.c | 7 ++----- drivers/usb/misc/usb251xb.c | 33 ++++++++++++++---------------- 6 files changed, 25 insertions(+), 32 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index 2eeccf4ec9d6..2855ac303001 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -152,12 +152,12 @@ static struct imx_usbmisc_data *usbmisc_get_init_data(struct device *dev) * Check the various over current related properties. If over current * detection is disabled we're not interested in the polarity. */ - if (of_find_property(np, "disable-over-current", NULL)) { + if (of_property_read_bool(np, "disable-over-current")) { data->disable_oc = 1; - } else if (of_find_property(np, "over-current-active-high", NULL)) { + } else if (of_property_read_bool(np, "over-current-active-high")) { data->oc_pol_active_low = 0; data->oc_pol_configured = 1; - } else if (of_find_property(np, "over-current-active-low", NULL)) { + } else if (of_property_read_bool(np, "over-current-active-low")) { data->oc_pol_active_low = 1; data->oc_pol_configured = 1; } else { diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 27c601296130..7ccb223ed53c 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -753,7 +753,7 @@ static int ci_get_platdata(struct device *dev, return ret; } - if (of_find_property(dev->of_node, "non-zero-ttctrl-ttha", NULL)) + if (of_property_read_bool(dev->of_node, "non-zero-ttctrl-ttha")) platdata->flags |= CI_HDRC_SET_NON_ZERO_TTHA; ext_id = ERR_PTR(-ENODEV); diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c index 9ed9fd956940..21d16533bd2f 100644 --- a/drivers/usb/dwc2/params.c +++ b/drivers/usb/dwc2/params.c @@ -508,8 +508,7 @@ static void dwc2_get_device_properties(struct dwc2_hsotg *hsotg) of_usb_update_otg_caps(hsotg->dev->of_node, &p->otg_caps); } - if (of_find_property(hsotg->dev->of_node, "disable-over-current", NULL)) - p->oc_disable = true; + p->oc_disable = of_property_read_bool(hsotg->dev->of_node, "disable-over-current"); } static void dwc2_check_param_otg_cap(struct dwc2_hsotg *hsotg) diff --git a/drivers/usb/host/ehci-ppc-of.c b/drivers/usb/host/ehci-ppc-of.c index 62a0a193798c..b3aa464e9d2c 100644 --- a/drivers/usb/host/ehci-ppc-of.c +++ b/drivers/usb/host/ehci-ppc-of.c @@ -151,13 +151,13 @@ static int ehci_hcd_ppc_of_probe(struct platform_device *op) of_node_put(np); } - if (of_get_property(dn, "big-endian", NULL)) { + if (of_property_read_bool(dn, "big-endian")) { ehci->big_endian_mmio = 1; ehci->big_endian_desc = 1; } - if (of_get_property(dn, "big-endian-regs", NULL)) + if (of_property_read_bool(dn, "big-endian-regs")) ehci->big_endian_mmio = 1; - if (of_get_property(dn, "big-endian-desc", NULL)) + if (of_property_read_bool(dn, "big-endian-desc")) ehci->big_endian_desc = 1; ehci->caps = hcd->regs; diff --git a/drivers/usb/host/fsl-mph-dr-of.c b/drivers/usb/host/fsl-mph-dr-of.c index cdf71b716c2b..9db909d12354 100644 --- a/drivers/usb/host/fsl-mph-dr-of.c +++ b/drivers/usb/host/fsl-mph-dr-of.c @@ -208,11 +208,8 @@ static int fsl_usb2_mph_dr_of_probe(struct platform_device *ofdev) pdata->operating_mode = FSL_USB2_MPH_HOST; } else { - if (of_get_property(np, "fsl,invert-drvvbus", NULL)) - pdata->invert_drvvbus = 1; - - if (of_get_property(np, "fsl,invert-pwr-fault", NULL)) - pdata->invert_pwr_fault = 1; + pdata->invert_drvvbus = of_property_read_bool(np, "fsl,invert-drvvbus"); + pdata->invert_pwr_fault = of_property_read_bool(np, "fsl,invert-pwr-fault"); /* setup mode selected in the device tree */ pdata->operating_mode = dev_data->op_mode; diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index e3abe67a155d..96f25c1ec113 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -410,10 +410,7 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, return -ENODEV; } - if (of_get_property(np, "skip-config", NULL)) - hub->skip_config = 1; - else - hub->skip_config = 0; + hub->skip_config = of_property_read_bool(np, "skip-config"); hub->gpio_reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(hub->gpio_reset)) @@ -431,40 +428,40 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, hub->device_id = USB251XB_DEF_DEVICE_ID; hub->conf_data1 = USB251XB_DEF_CONFIG_DATA_1; - if (of_get_property(np, "self-powered", NULL)) { + if (of_property_read_bool(np, "self-powered")) { hub->conf_data1 |= BIT(7); /* Configure Over-Current sens when self-powered */ hub->conf_data1 &= ~BIT(2); - if (of_get_property(np, "ganged-sensing", NULL)) + if (of_property_read_bool(np, "ganged-sensing")) hub->conf_data1 &= ~BIT(1); - else if (of_get_property(np, "individual-sensing", NULL)) + else if (of_property_read_bool(np, "individual-sensing")) hub->conf_data1 |= BIT(1); - } else if (of_get_property(np, "bus-powered", NULL)) { + } else if (of_property_read_bool(np, "bus-powered")) { hub->conf_data1 &= ~BIT(7); /* Disable Over-Current sense when bus-powered */ hub->conf_data1 |= BIT(2); } - if (of_get_property(np, "disable-hi-speed", NULL)) + if (of_property_read_bool(np, "disable-hi-speed")) hub->conf_data1 |= BIT(5); - if (of_get_property(np, "multi-tt", NULL)) + if (of_property_read_bool(np, "multi-tt")) hub->conf_data1 |= BIT(4); - else if (of_get_property(np, "single-tt", NULL)) + else if (of_property_read_bool(np, "single-tt")) hub->conf_data1 &= ~BIT(4); - if (of_get_property(np, "disable-eop", NULL)) + if (of_property_read_bool(np, "disable-eop")) hub->conf_data1 |= BIT(3); - if (of_get_property(np, "individual-port-switching", NULL)) + if (of_property_read_bool(np, "individual-port-switching")) hub->conf_data1 |= BIT(0); - else if (of_get_property(np, "ganged-port-switching", NULL)) + else if (of_property_read_bool(np, "ganged-port-switching")) hub->conf_data1 &= ~BIT(0); hub->conf_data2 = USB251XB_DEF_CONFIG_DATA_2; - if (of_get_property(np, "dynamic-power-switching", NULL)) + if (of_property_read_bool(np, "dynamic-power-switching")) hub->conf_data2 |= BIT(7); if (!of_property_read_u32(np, "oc-delay-us", &property_u32)) { @@ -487,17 +484,17 @@ static int usb251xb_get_ofdata(struct usb251xb *hub, } } - if (of_get_property(np, "compound-device", NULL)) + if (of_property_read_bool(np, "compound-device")) hub->conf_data2 |= BIT(3); hub->conf_data3 = USB251XB_DEF_CONFIG_DATA_3; - if (of_get_property(np, "port-mapping-mode", NULL)) + if (of_property_read_bool(np, "port-mapping-mode")) hub->conf_data3 |= BIT(3); if (data->led_support && of_get_property(np, "led-usb-mode", NULL)) hub->conf_data3 &= ~BIT(1); - if (of_get_property(np, "string-support", NULL)) + if (of_property_read_bool(np, "string-support")) hub->conf_data3 |= BIT(0); hub->non_rem_dev = USB251XB_DEF_NON_REMOVABLE_DEVICES; -- GitLab From e13a7333067e47d01f8bfcc36e300e26ab4f8bea Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 10 Mar 2023 18:41:29 +0200 Subject: [PATCH 0622/5631] usb: acpi: Switch to use acpi_evaluate_dsm_typed() The acpi_evaluate_dsm_typed() provides a way to check the type of the object evaluated by _DSM call. Use it instead of open coded variant. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230310164129.21937-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/usb-acpi.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 533baa85083c..a34b22537d7c 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -81,15 +81,11 @@ int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) return -ENODEV; } - obj = acpi_evaluate_dsm(port_handle, &guid, 0, - USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL); - - if (!obj) - return -ENODEV; - - if (obj->type != ACPI_TYPE_INTEGER) { + obj = acpi_evaluate_dsm_typed(port_handle, &guid, 0, + USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL, + ACPI_TYPE_INTEGER); + if (!obj) { dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1); - ACPI_FREE(obj); return -EINVAL; } -- GitLab From d6cfb252107d36fdddb66891c16d34a346882c36 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:18 +0100 Subject: [PATCH 0623/5631] usb: host: xhci-rcar: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/host/xhci-rcar.c:269:34: error: ‘usb_xhci_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-rcar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c index c4925f8d6b06..ad966b797b89 100644 --- a/drivers/usb/host/xhci-rcar.c +++ b/drivers/usb/host/xhci-rcar.c @@ -282,7 +282,7 @@ static struct platform_driver usb_xhci_renesas_driver = { .driver = { .name = "xhci-renesas-hcd", .pm = &xhci_plat_pm_ops, - .of_match_table = of_match_ptr(usb_xhci_of_match), + .of_match_table = usb_xhci_of_match, }, }; module_platform_driver(usb_xhci_renesas_driver); -- GitLab From 658e467b76eb41005ef0c257d0b7accf73dcd32a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:19 +0100 Subject: [PATCH 0624/5631] usb: host: max3421-hcd: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/host/max3421-hcd.c:1943:34: error: ‘max3421_of_match_table’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/max3421-hcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index 28d1524ee2fa..d152d72de126 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -1951,7 +1951,7 @@ static struct spi_driver max3421_driver = { .remove = max3421_remove, .driver = { .name = "max3421-hcd", - .of_match_table = of_match_ptr(max3421_of_match_table), + .of_match_table = max3421_of_match_table, }, }; -- GitLab From 94d1957fc361bb7efa76c25f3c78296c3c9f867f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:20 +0100 Subject: [PATCH 0625/5631] usb: renesas_usbhs: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/renesas_usbhs/common.c:535:34: error: ‘usbhs_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-3-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/renesas_usbhs/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 96f3939a65e2..fa34efabcccf 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -823,7 +823,7 @@ static struct platform_driver renesas_usbhs_driver = { .driver = { .name = "renesas_usbhs", .pm = &usbhsc_pm_ops, - .of_match_table = of_match_ptr(usbhs_of_match), + .of_match_table = usbhs_of_match, }, .probe = usbhs_probe, .remove = usbhs_remove, -- GitLab From 2df6349323f627cc1f8e076fa4a7b715f6a05e5a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:21 +0100 Subject: [PATCH 0626/5631] usb: gadget: rzv2m_usb3drd: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/gadget/udc/rzv2m_usb3drd.c:120:34: error: ‘rzv2m_usb3drd_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-4-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/rzv2m_usb3drd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/rzv2m_usb3drd.c b/drivers/usb/gadget/udc/rzv2m_usb3drd.c index 3c8bbf843038..8855d8e8d793 100644 --- a/drivers/usb/gadget/udc/rzv2m_usb3drd.c +++ b/drivers/usb/gadget/udc/rzv2m_usb3drd.c @@ -126,7 +126,7 @@ MODULE_DEVICE_TABLE(of, rzv2m_usb3drd_of_match); static struct platform_driver rzv2m_usb3drd_driver = { .driver = { .name = "rzv2m-usb3drd", - .of_match_table = of_match_ptr(rzv2m_usb3drd_of_match), + .of_match_table = rzv2m_usb3drd_of_match, }, .probe = rzv2m_usb3drd_probe, .remove = rzv2m_usb3drd_remove, -- GitLab From 4997cacd6ecb588b32c5c43bf6bbe87d311dfb1e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:22 +0100 Subject: [PATCH 0627/5631] usb: gadget: renesas_usb3: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/gadget/udc/renesas_usb3.c:2811:34: error: ‘usb3_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-5-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/renesas_usb3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index f2ac6447b748..17e765d2e093 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -3018,7 +3018,7 @@ static struct platform_driver renesas_usb3_driver = { .driver = { .name = udc_name, .pm = &renesas_usb3_pm_ops, - .of_match_table = of_match_ptr(usb3_of_match), + .of_match_table = usb3_of_match, }, }; module_platform_driver(renesas_usb3_driver); -- GitLab From f80391ddb7793dca03c0fb548acf39ee562982f0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:23 +0100 Subject: [PATCH 0628/5631] usb: gadget: max3420_udc: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/gadget/udc/max3420_udc.c:1312:34: error: ‘max3420_udc_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311173624.263189-6-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/max3420_udc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c index ddf0ed3eb4f2..12c519f32bf7 100644 --- a/drivers/usb/gadget/udc/max3420_udc.c +++ b/drivers/usb/gadget/udc/max3420_udc.c @@ -1319,7 +1319,7 @@ MODULE_DEVICE_TABLE(of, max3420_udc_of_match); static struct spi_driver max3420_driver = { .driver = { .name = "max3420-udc", - .of_match_table = of_match_ptr(max3420_udc_of_match), + .of_match_table = max3420_udc_of_match, }, .probe = max3420_probe, .remove = max3420_remove, -- GitLab From 2665eb8e20539a16d113725fdbcc2fb63fd627a5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:36:24 +0100 Subject: [PATCH 0629/5631] usb: misc: usb251xb: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/usb/misc/usb251xb.c:223:35: error: ‘usb2517i_data’ defined but not used [-Werror=unused-const-variable=] drivers/usb/misc/usb251xb.c:215:35: error: ‘usb2517_data’ defined but not used [-Werror=unused-const-variable=] drivers/usb/misc/usb251xb.c:207:35: error: ‘usb2514bi_data’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Acked-by: Richard Leitner Link: https://lore.kernel.org/r/20230311173624.263189-7-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb251xb.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c index 96f25c1ec113..ce1da80d3365 100644 --- a/drivers/usb/misc/usb251xb.c +++ b/drivers/usb/misc/usb251xb.c @@ -377,7 +377,6 @@ static int usb251xb_connect(struct usb251xb *hub) return err; } -#ifdef CONFIG_OF static void usb251xb_get_ports_field(struct usb251xb *hub, const char *prop_name, u8 port_cnt, bool ds_only, u8 *fld) @@ -623,13 +622,6 @@ static const struct of_device_id usb251xb_of_match[] = { } }; MODULE_DEVICE_TABLE(of, usb251xb_of_match); -#else /* CONFIG_OF */ -static int usb251xb_get_ofdata(struct usb251xb *hub, - const struct usb251xb_data *data) -{ - return 0; -} -#endif /* CONFIG_OF */ static void usb251xb_regulator_disable_action(void *data) { @@ -751,7 +743,7 @@ MODULE_DEVICE_TABLE(i2c, usb251xb_id); static struct i2c_driver usb251xb_i2c_driver = { .driver = { .name = DRIVER_NAME, - .of_match_table = of_match_ptr(usb251xb_of_match), + .of_match_table = usb251xb_of_match, .pm = &usb251xb_pm_ops, }, .probe_new = usb251xb_i2c_probe, -- GitLab From 45e7c9e448e345f27c4329d0395946f4a9cfd8c3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 23:29:36 +0100 Subject: [PATCH 0630/5631] usb: typec: hd3ss3220: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it is not relevant here). drivers/usb/typec/hd3ss3220.c:284:34: error: ‘dev_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230310222937.315773-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/hd3ss3220.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/hd3ss3220.c b/drivers/usb/typec/hd3ss3220.c index 746ef3a75b76..8bbeb9b1e439 100644 --- a/drivers/usb/typec/hd3ss3220.c +++ b/drivers/usb/typec/hd3ss3220.c @@ -290,7 +290,7 @@ MODULE_DEVICE_TABLE(of, dev_ids); static struct i2c_driver hd3ss3220_driver = { .driver = { .name = "hd3ss3220", - .of_match_table = of_match_ptr(dev_ids), + .of_match_table = dev_ids, }, .probe_new = hd3ss3220_probe, .remove = hd3ss3220_remove, -- GitLab From b16de6a5c70b53bee495a42ebe74ccca076a3e26 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 23:29:37 +0100 Subject: [PATCH 0631/5631] usb: typec: fusb302: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/usb/typec/tcpm/fusb302.c:1816:34: error: ‘fusb302_dt_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230310222937.315773-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/fusb302.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index 1ffce00d94b4..592b0aec782f 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -1813,7 +1813,7 @@ static int fusb302_pm_resume(struct device *dev) return 0; } -static const struct of_device_id fusb302_dt_match[] = { +static const struct of_device_id fusb302_dt_match[] __maybe_unused = { {.compatible = "fcs,fusb302"}, {}, }; -- GitLab From 34427557747cad5f599d65be894e846b31714602 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 13 Mar 2023 17:53:10 +0200 Subject: [PATCH 0632/5631] usb: gadget: aspeed: Rectify a bit a random header inclusion It looks like the driver copied'n'pasted almost random set of headers for its code. Rectify it a bit by removing of_gpio.h that is not only unused, but also will be removed in the future completely. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230313155310.80022-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/aspeed-vhub/core.c | 1 - drivers/usb/gadget/udc/aspeed-vhub/dev.c | 1 - drivers/usb/gadget/udc/aspeed-vhub/ep0.c | 1 - drivers/usb/gadget/udc/aspeed-vhub/epn.c | 1 - drivers/usb/gadget/udc/aspeed-vhub/hub.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/usb/gadget/udc/aspeed-vhub/core.c b/drivers/usb/gadget/udc/aspeed-vhub/core.c index ac3ca24f8b04..86398a04a012 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/core.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/core.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/drivers/usb/gadget/udc/aspeed-vhub/dev.c b/drivers/usb/gadget/udc/aspeed-vhub/dev.c index 4f3bc27c1c62..573109ca5b79 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/dev.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/dev.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c index b4cf46249fea..e9aa74231760 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 56e55472daa1..148d7ec3ebf4 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include diff --git a/drivers/usb/gadget/udc/aspeed-vhub/hub.c b/drivers/usb/gadget/udc/aspeed-vhub/hub.c index e2207d014620..a63e4af60a56 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/hub.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/hub.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include -- GitLab From 1239e8124714ca94dd4c882266ee4bcad3f46e73 Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Mon, 13 Mar 2023 17:50:37 +0100 Subject: [PATCH 0633/5631] dt-bindings: usb: smsc,usb3503: Add usb3803 Add support for usb3803, compared to usb3503 it uses a regular USB connection to upstream instead of HSIC, it has an additional low power mode (bypass) and an additional control signal (BYPASS_N). In bypass mode the downstream port 3 is connected to the upstream port with low switch resistance R_on. Signed-off-by: Emanuele Ghidoli Signed-off-by: Francesco Dolcini Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230313165039.255579-2-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/smsc,usb3503.yaml | 54 ++++++++++++++++++- 1 file changed, 52 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/smsc,usb3503.yaml b/Documentation/devicetree/bindings/usb/smsc,usb3503.yaml index a09f4528aea3..6156dc26e65c 100644 --- a/Documentation/devicetree/bindings/usb/smsc,usb3503.yaml +++ b/Documentation/devicetree/bindings/usb/smsc,usb3503.yaml @@ -14,6 +14,7 @@ properties: enum: - smsc,usb3503 - smsc,usb3503a + - smsc,usb3803 reg: maxItems: 1 @@ -33,6 +34,12 @@ properties: description: > GPIO for reset + bypass-gpios: + maxItems: 1 + description: > + GPIO for bypass. + Control signal to select between HUB MODE and BYPASS MODE. + disabled-ports: $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 1 @@ -46,9 +53,10 @@ properties: initial-mode: $ref: /schemas/types.yaml#/definitions/uint32 - enum: [1, 2] description: > - Specifies initial mode. 1 for Hub mode, 2 for standby mode. + Specifies initial mode. 1 for Hub mode, 2 for standby mode and 3 for bypass mode. + In bypass mode the downstream port 3 is connected to the upstream port with low + switch resistance R_on. clocks: maxItems: 1 @@ -71,6 +79,29 @@ properties: required: - compatible +allOf: + - if: + not: + properties: + compatible: + enum: + - smsc,usb3803 + then: + properties: + bypass-gpios: false + + - if: + required: + - bypass-gpios + then: + properties: + initial-mode: + enum: [1, 2, 3] + else: + properties: + initial-mode: + enum: [1, 2] + additionalProperties: false examples: @@ -92,6 +123,25 @@ examples: }; }; + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + usb-hub@8 { + compatible = "smsc,usb3803"; + reg = <0x08>; + connect-gpios = <&gpx3 0 1>; + disabled-ports = <2 3>; + intn-gpios = <&gpx3 4 1>; + reset-gpios = <&gpx3 5 1>; + bypass-gpios = <&gpx3 6 1>; + initial-mode = <3>; + clocks = <&clks 80>; + clock-names = "refclk"; + }; + }; + - | #include -- GitLab From b04b32cd67304bdda9f19fc52fc5abd95f8502ab Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Mon, 13 Mar 2023 17:50:38 +0100 Subject: [PATCH 0634/5631] usb: misc: usb3503: refactor code to prepare for usb3803 addition Refactor code to simplify adding support for USB3803 and bypass mode. Remove static usb3503_reset() and move it to usb3503_switch_mode(), with the addition of the bypass mode we need to drive the various control signals to the expected configuration, not just to assert/release the reset. In addition to that the usb3503_connect() needs to be called only for HUB mode. No functional changes expected nor intended because of this change. Signed-off-by: Emanuele Ghidoli Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230313165039.255579-3-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb3503.c | 44 ++++++++++++++++---------------------- 1 file changed, 19 insertions(+), 25 deletions(-) diff --git a/drivers/usb/misc/usb3503.c b/drivers/usb/misc/usb3503.c index bd47c4437ca4..3044db9fd8aa 100644 --- a/drivers/usb/misc/usb3503.c +++ b/drivers/usb/misc/usb3503.c @@ -52,28 +52,11 @@ struct usb3503 { bool secondary_ref_clk; }; -static int usb3503_reset(struct usb3503 *hub, int state) -{ - if (!state && hub->connect) - gpiod_set_value_cansleep(hub->connect, 0); - - if (hub->reset) - gpiod_set_value_cansleep(hub->reset, !state); - - /* Wait T_HUBINIT == 4ms for hub logic to stabilize */ - if (state) - usleep_range(4000, 10000); - - return 0; -} - static int usb3503_connect(struct usb3503 *hub) { struct device *dev = hub->dev; int err; - usb3503_reset(hub, 1); - if (hub->regmap) { /* SP_ILOCK: set connect_n, config_n for config */ err = regmap_write(hub->regmap, USB3503_SP_ILOCK, @@ -126,25 +109,36 @@ static int usb3503_connect(struct usb3503 *hub) static int usb3503_switch_mode(struct usb3503 *hub, enum usb3503_mode mode) { struct device *dev = hub->dev; - int err = 0; + int rst, conn; switch (mode) { case USB3503_MODE_HUB: - err = usb3503_connect(hub); + conn = 1; + rst = 0; break; - case USB3503_MODE_STANDBY: - usb3503_reset(hub, 0); + conn = 0; + rst = 1; dev_info(dev, "switched to STANDBY mode\n"); break; - default: dev_err(dev, "unknown mode is requested\n"); - err = -EINVAL; - break; + return -EINVAL; } - return err; + if (!conn && hub->connect) + gpiod_set_value_cansleep(hub->connect, 0); + + if (hub->reset) + gpiod_set_value_cansleep(hub->reset, rst); + + if (conn) { + /* Wait T_HUBINIT == 4ms for hub logic to stabilize */ + usleep_range(4000, 10000); + return usb3503_connect(hub); + } + + return 0; } static const struct regmap_config usb3503_regmap_config = { -- GitLab From b91e6107119f62be8b51b9955294be52c0b4fc80 Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Mon, 13 Mar 2023 17:50:39 +0100 Subject: [PATCH 0635/5631] usb: misc: usb3503: support usb3803 and bypass mode Add support for USB3803 and bypass mode, with this change is also possible to move the component out of bypass mode. In bypass mode the downstream port 3 is connected to the upstream port with low switch resistance R_on. Controlling mode of operations: | RESET_N | BYPASS_N | Mode | -------------------------------- | 0 | 0 | standby | | 1 | 0 | bypass | | 1 | 1 | hub | Datasheet: https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/DataSheets/00001691D.pdf Signed-off-by: Emanuele Ghidoli Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230313165039.255579-4-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/usb3503.c | 22 +++++++++++++++++++++- include/linux/platform_data/usb3503.h | 1 + 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/drivers/usb/misc/usb3503.c b/drivers/usb/misc/usb3503.c index 3044db9fd8aa..c6cfd1edaf76 100644 --- a/drivers/usb/misc/usb3503.c +++ b/drivers/usb/misc/usb3503.c @@ -46,6 +46,7 @@ struct usb3503 { struct device *dev; struct clk *clk; u8 port_off_mask; + struct gpio_desc *bypass; struct gpio_desc *intn; struct gpio_desc *reset; struct gpio_desc *connect; @@ -109,18 +110,25 @@ static int usb3503_connect(struct usb3503 *hub) static int usb3503_switch_mode(struct usb3503 *hub, enum usb3503_mode mode) { struct device *dev = hub->dev; - int rst, conn; + int rst, bypass, conn; switch (mode) { case USB3503_MODE_HUB: conn = 1; rst = 0; + bypass = 0; break; case USB3503_MODE_STANDBY: conn = 0; rst = 1; + bypass = 1; dev_info(dev, "switched to STANDBY mode\n"); break; + case USB3503_MODE_BYPASS: + conn = 0; + rst = 0; + bypass = 1; + break; default: dev_err(dev, "unknown mode is requested\n"); return -EINVAL; @@ -132,6 +140,9 @@ static int usb3503_switch_mode(struct usb3503 *hub, enum usb3503_mode mode) if (hub->reset) gpiod_set_value_cansleep(hub->reset, rst); + if (hub->bypass) + gpiod_set_value_cansleep(hub->bypass, bypass); + if (conn) { /* Wait T_HUBINIT == 4ms for hub logic to stabilize */ usleep_range(4000, 10000); @@ -247,6 +258,14 @@ static int usb3503_probe(struct usb3503 *hub) if (hub->connect) gpiod_set_consumer_name(hub->connect, "usb3503 connect"); + hub->bypass = devm_gpiod_get_optional(dev, "bypass", GPIOD_OUT_HIGH); + if (IS_ERR(hub->bypass)) { + err = PTR_ERR(hub->bypass); + goto err_clk; + } + if (hub->bypass) + gpiod_set_consumer_name(hub->bypass, "usb3503 bypass"); + hub->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(hub->reset)) { err = PTR_ERR(hub->reset); @@ -382,6 +401,7 @@ MODULE_DEVICE_TABLE(i2c, usb3503_id); static const struct of_device_id usb3503_of_match[] = { { .compatible = "smsc,usb3503", }, { .compatible = "smsc,usb3503a", }, + { .compatible = "smsc,usb3803", }, {}, }; MODULE_DEVICE_TABLE(of, usb3503_of_match); diff --git a/include/linux/platform_data/usb3503.h b/include/linux/platform_data/usb3503.h index d01ef97ddf36..f3c942f396f8 100644 --- a/include/linux/platform_data/usb3503.h +++ b/include/linux/platform_data/usb3503.h @@ -12,6 +12,7 @@ enum usb3503_mode { USB3503_MODE_UNKNOWN, USB3503_MODE_HUB, USB3503_MODE_STANDBY, + USB3503_MODE_BYPASS, }; struct usb3503_platform_data { -- GitLab From 55b7fa634d9f5d88f008f8b785448db40a2d5229 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 14 Mar 2023 13:53:00 +0100 Subject: [PATCH 0636/5631] dt-bindings: usb: dwc3: Add QCM2290 compatible Document the QCM2290 DWC3 controller. Signed-off-by: Konrad Dybcio Reviewed-by: Bhupesh Sharma Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230314-topic-2290_compats-v1-5-47e26c3c0365@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/qcom,dwc3.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml index 4875c5b7d5b5..a2aabdac4105 100644 --- a/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/qcom,dwc3.yaml @@ -21,6 +21,7 @@ properties: - qcom,msm8994-dwc3 - qcom,msm8996-dwc3 - qcom,msm8998-dwc3 + - qcom,qcm2290-dwc3 - qcom,qcs404-dwc3 - qcom,sc7180-dwc3 - qcom,sc7280-dwc3 @@ -300,6 +301,7 @@ allOf: compatible: contains: enum: + - qcom,qcm2290-dwc3 - qcom,sm6115-dwc3 - qcom,sm6125-dwc3 - qcom,sm8150-dwc3 -- GitLab From ef194140308776be60dd4601bd01c00c84fb8b39 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:26 -0600 Subject: [PATCH 0637/5631] serial: Use of_property_present() for testing DT property presence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230310144727.1545630-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 3 +-- drivers/tty/serial/sh-sci.c | 2 +- drivers/tty/serial/sunzilog.c | 4 ++-- 3 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 84bc0e768726..4d389e23bc01 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2264,8 +2264,7 @@ static int imx_uart_probe(struct platform_device *pdev) if (of_get_property(np, "fsl,dte-mode", NULL)) sport->dte_mode = 1; - if (of_get_property(np, "rts-gpios", NULL)) - sport->have_rtsgpio = 1; + sport->have_rtsgpio = of_property_present(np, "rts-gpios"); if (of_get_property(np, "fsl,inverted-tx", NULL)) sport->inverted_tx = 1; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 7bd080720929..a3e12e985e0d 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1573,7 +1573,7 @@ static void sci_request_dma(struct uart_port *port) * Don't request a dma channel if no channel was specified * in the device tree. */ - if (!of_find_property(port->dev->of_node, "dmas", NULL)) + if (!of_property_present(port->dev->of_node, "dmas")) return; chan = sci_request_dma_chan(port, DMA_MEM_TO_DEV); diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c index ccb809216e94..0fbeb3dbd843 100644 --- a/drivers/tty/serial/sunzilog.c +++ b/drivers/tty/serial/sunzilog.c @@ -1403,7 +1403,7 @@ static int zs_probe(struct platform_device *op) int keyboard_mouse = 0; int err; - if (of_find_property(op->dev.of_node, "keyboard", NULL)) + if (of_property_present(op->dev.of_node, "keyboard")) keyboard_mouse = 1; /* uarts must come before keyboards/mice */ @@ -1553,7 +1553,7 @@ static int __init sunzilog_init(void) for_each_node_by_name(dp, "zs") { num_sunzilog++; - if (of_find_property(dp, "keyboard", NULL)) + if (of_property_present(dp, "keyboard")) num_keybms++; } -- GitLab From 822a729af4aeb451a84863ac565bdad6f64e407e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:27 -0600 Subject: [PATCH 0638/5631] serial: Use of_property_read_bool() for boolean properties MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230310144727.1545699-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 14 +++++--------- drivers/tty/serial/mxs-auart.c | 4 ++-- drivers/tty/serial/ucc_uart.c | 2 +- 3 files changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 4d389e23bc01..0fa1bd8cdec7 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2257,20 +2257,16 @@ static int imx_uart_probe(struct platform_device *pdev) } sport->port.line = ret; - if (of_get_property(np, "uart-has-rtscts", NULL) || - of_get_property(np, "fsl,uart-has-rtscts", NULL) /* deprecated */) - sport->have_rtscts = 1; + sport->have_rtscts = of_property_read_bool(np, "uart-has-rtscts") || + of_property_read_bool(np, "fsl,uart-has-rtscts"); /* deprecated */ - if (of_get_property(np, "fsl,dte-mode", NULL)) - sport->dte_mode = 1; + sport->dte_mode = of_property_read_bool(np, "fsl,dte-mode"); sport->have_rtsgpio = of_property_present(np, "rts-gpios"); - if (of_get_property(np, "fsl,inverted-tx", NULL)) - sport->inverted_tx = 1; + sport->inverted_tx = of_property_read_bool(np, "fsl,inverted-tx"); - if (of_get_property(np, "fsl,inverted-rx", NULL)) - sport->inverted_rx = 1; + sport->inverted_rx = of_property_read_bool(np, "fsl,inverted-rx"); if (!of_property_read_u32_array(np, "fsl,dma-info", dma_buf_conf, 2)) { sport->rx_period_length = dma_buf_conf[0]; diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c index ef6e7bb6105c..a368f4293967 100644 --- a/drivers/tty/serial/mxs-auart.c +++ b/drivers/tty/serial/mxs-auart.c @@ -1587,8 +1587,8 @@ static int mxs_auart_probe(struct platform_device *pdev) } s->port.line = ret; - if (of_get_property(np, "uart-has-rtscts", NULL) || - of_get_property(np, "fsl,uart-has-rtscts", NULL) /* deprecated */) + if (of_property_read_bool(np, "uart-has-rtscts") || + of_property_read_bool(np, "fsl,uart-has-rtscts") /* deprecated */) set_bit(MXS_AUART_RTSCTS, &s->flags); if (s->port.line >= ARRAY_SIZE(auart_port)) { diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c index 32c7a5b43f8e..676840847962 100644 --- a/drivers/tty/serial/ucc_uart.c +++ b/drivers/tty/serial/ucc_uart.c @@ -1179,7 +1179,7 @@ static int soft_uart_init(struct platform_device *ofdev) struct qe_firmware_info *qe_fw_info; int ret; - if (of_find_property(np, "soft-uart", NULL)) { + if (of_property_read_bool(np, "soft-uart")) { dev_dbg(&ofdev->dev, "using Soft-UART mode\n"); soft_uart = 1; } else { -- GitLab From 88dcd07d27d1873810cd8423238f3ce4e9bd0bfc Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 23:29:56 +0100 Subject: [PATCH 0639/5631] serial: sh-sci: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/tty/serial/sh-sci.c:3144:34: error: ‘of_sci_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230310222957.315848-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index a3e12e985e0d..af4a7a865764 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -3141,7 +3141,7 @@ static int sci_remove(struct platform_device *dev) #define SCI_OF_TYPE(data) ((unsigned long)(data) >> 16) #define SCI_OF_REGTYPE(data) ((unsigned long)(data) & 0xffff) -static const struct of_device_id of_sci_match[] = { +static const struct of_device_id of_sci_match[] __maybe_unused = { /* SoC-specific types */ { .compatible = "renesas,scif-r7s72100", -- GitLab From 5406dc04884b96b8438b664d1a9b73e30e2a5517 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 23:29:57 +0100 Subject: [PATCH 0640/5631] serial: sprd: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it is not relevant here). drivers/tty/serial/sprd_serial.c:1242:34: error: ‘serial_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Baolin Wang Link: https://lore.kernel.org/r/20230310222957.315848-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sprd_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/sprd_serial.c b/drivers/tty/serial/sprd_serial.c index 492a3bdab5ba..b58f51296ace 100644 --- a/drivers/tty/serial/sprd_serial.c +++ b/drivers/tty/serial/sprd_serial.c @@ -1250,7 +1250,7 @@ static struct platform_driver sprd_platform_driver = { .remove = sprd_remove, .driver = { .name = "sprd_serial", - .of_match_table = of_match_ptr(serial_ids), + .of_match_table = serial_ids, .pm = &sprd_pm_ops, }, }; -- GitLab From a807b78ad04b2eaa348f52f5cc7702385b6de1ee Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Wed, 1 Feb 2023 08:29:03 -0500 Subject: [PATCH 0641/5631] kvm: vmx: Add IA32_FLUSH_CMD guest support Expose IA32_FLUSH_CMD to the guest if the guest CPUID enumerates support for this MSR. As with IA32_PRED_CMD, permission for unintercepted writes to this MSR will be granted to the guest after the first non-zero write. Co-developed-by: Jim Mattson Signed-off-by: Jim Mattson Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20230201132905.549148-2-eesposit@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/nested.c | 3 ++ arch/x86/kvm/vmx/vmx.c | 68 +++++++++++++++++++++++++-------------- 2 files changed, 46 insertions(+), 25 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1bc2b80273c9..f63b28f46a71 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -654,6 +654,9 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PRED_CMD, MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_FLUSH_CMD, MSR_TYPE_W); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); vmx->nested.force_msr_bitmap_recalc = false; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f777509ecf17..d7bf14abdba1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2133,6 +2133,39 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated return debugctl; } +static int vmx_set_msr_ia32_cmd(struct kvm_vcpu *vcpu, + struct msr_data *msr_info, + bool guest_has_feat, u64 cmd, + int x86_feature_bit) +{ + if (!msr_info->host_initiated && !guest_has_feat) + return 1; + + if (!(msr_info->data & ~cmd)) + return 1; + if (!boot_cpu_has(x86_feature_bit)) + return 1; + if (!msr_info->data) + return 0; + + wrmsrl(msr_info->index, cmd); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_prepare_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vcpu, msr_info->index, MSR_TYPE_W); + + return 0; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2286,31 +2319,16 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; goto find_uret_msr; case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W); + ret = vmx_set_msr_ia32_cmd(vcpu, msr_info, + guest_has_pred_cmd_msr(vcpu), + PRED_CMD_IBPB, + X86_FEATURE_IBPB); + break; + case MSR_IA32_FLUSH_CMD: + ret = vmx_set_msr_ia32_cmd(vcpu, msr_info, + guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D), + L1D_FLUSH, + X86_FEATURE_FLUSH_L1D); break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) -- GitLab From 723d5fb0ffe4c02bd4edf47ea02c02e454719f28 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Wed, 1 Feb 2023 08:29:04 -0500 Subject: [PATCH 0642/5631] kvm: svm: Add IA32_FLUSH_CMD guest support Expose IA32_FLUSH_CMD to the guest if the guest CPUID enumerates support for this MSR. As with IA32_PRED_CMD, permission for unintercepted writes to this MSR will be granted to the guest after the first non-zero write. Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20230201132905.549148-3-eesposit@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 43 +++++++++++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 252e7f37e4e2..70183d2271b5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2869,6 +2869,28 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) return 0; } +static int svm_set_msr_ia32_cmd(struct kvm_vcpu *vcpu, struct msr_data *msr, + bool guest_has_feat, u64 cmd, + int x86_feature_bit) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!msr->host_initiated && !guest_has_feat) + return 1; + + if (!(msr->data & ~cmd)) + return 1; + if (!boot_cpu_has(x86_feature_bit)) + return 1; + if (!msr->data) + return 0; + + wrmsrl(msr->index, cmd); + set_msr_interception(vcpu, svm->msrpm, msr->index, 0, 1); + + return 0; +} + static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2943,19 +2965,14 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); break; case MSR_IA32_PRED_CMD: - if (!msr->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); + r = svm_set_msr_ia32_cmd(vcpu, msr, + guest_has_pred_cmd_msr(vcpu), + PRED_CMD_IBPB, X86_FEATURE_IBPB); + break; + case MSR_IA32_FLUSH_CMD: + r = svm_set_msr_ia32_cmd(vcpu, msr, + guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D), + L1D_FLUSH, X86_FEATURE_FLUSH_L1D); break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && -- GitLab From 45cf86f26148e549c5ba4a8ab32a390e4bde216e Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Wed, 1 Feb 2023 08:29:05 -0500 Subject: [PATCH 0643/5631] kvm: x86: Advertise FLUSH_L1D to user space FLUSH_L1D was already added in 11e34e64e4103, but the feature is not visible to userspace yet. The bit definition: CPUID.(EAX=7,ECX=0):EDX[bit 28] If the feature is supported by the host, kvm should support it too so that userspace can choose whether to expose it to the guest or not. One disadvantage of not exposing it is that the guest will report a non existing vulnerability in /sys/devices/system/cpu/vulnerabilities/mmio_stale_data because the mitigation is present only if the guest supports (FLUSH_L1D and MD_CLEAR) or FB_CLEAR. Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20230201132905.549148-4-eesposit@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 599aebec2d52..9583a110cf5f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -653,7 +653,7 @@ void kvm_set_cpu_caps(void) F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | - F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) + F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ -- GitLab From 67c48662e2b5539f0ba3d4151f4e7e84c9871324 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:00 +0100 Subject: [PATCH 0644/5631] KVM: PPC: Standardize on "int" return types in the powerpc KVM code Most functions that are related to kvm_arch_vm_ioctl() already use "int" as return type to pass error values back to the caller. Some outlier functions use "long" instead for no good reason (they do not really require long values here). Let's standardize on "int" here to avoid casting the values back and forth between the two types. Reviewed-by: Nicholas Piggin Signed-off-by: Thomas Huth Message-Id: <20230208140105.655814-2-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/include/asm/kvm_ppc.h | 14 +++++++------- arch/powerpc/kvm/book3s_64_mmu_hv.c | 14 +++++++------- arch/powerpc/kvm/book3s_64_vio.c | 4 ++-- arch/powerpc/kvm/book3s_hv.c | 6 +++--- arch/powerpc/kvm/book3s_pr.c | 4 ++-- 5 files changed, 21 insertions(+), 21 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 6bef23d6d0e3..5b9f851d4035 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -156,7 +156,7 @@ extern void kvmppc_map_magic(struct kvm_vcpu *vcpu); extern int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order); extern void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info); -extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); +extern int kvmppc_alloc_reset_hpt(struct kvm *kvm, int order); extern void kvmppc_free_hpt(struct kvm_hpt_info *info); extern void kvmppc_rmap_reset(struct kvm *kvm); extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu, @@ -170,7 +170,7 @@ extern int kvmppc_switch_mmu_to_hpt(struct kvm *kvm); extern int kvmppc_switch_mmu_to_radix(struct kvm *kvm); extern void kvmppc_setup_partition_table(struct kvm *kvm); -extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, +extern int kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args); #define kvmppc_ioba_validate(stt, ioba, npages) \ (iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \ @@ -211,10 +211,10 @@ extern void kvmppc_bookehv_exit(void); extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *); -extern long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, - struct kvm_ppc_resize_hpt *rhpt); -extern long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, +extern int kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, struct kvm_ppc_resize_hpt *rhpt); +extern int kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt); int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); @@ -286,8 +286,8 @@ struct kvmppc_ops { int (*emulate_mtspr)(struct kvm_vcpu *vcpu, int sprn, ulong spr_val); int (*emulate_mfspr)(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val); void (*fast_vcpu_kick)(struct kvm_vcpu *vcpu); - long (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, - unsigned long arg); + int (*arch_vm_ioctl)(struct file *filp, unsigned int ioctl, + unsigned long arg); int (*hcall_implemented)(unsigned long hcall); int (*irq_bypass_add_producer)(struct irq_bypass_consumer *, struct irq_bypass_producer *); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7006bcbc2e37..1f4896de58ca 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -124,9 +124,9 @@ void kvmppc_set_hpt(struct kvm *kvm, struct kvm_hpt_info *info) info->virt, (long)info->order, kvm->arch.lpid); } -long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) +int kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) { - long err = -EBUSY; + int err = -EBUSY; struct kvm_hpt_info info; mutex_lock(&kvm->arch.mmu_setup_lock); @@ -1468,8 +1468,8 @@ static void resize_hpt_prepare_work(struct work_struct *work) mutex_unlock(&kvm->arch.mmu_setup_lock); } -long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, - struct kvm_ppc_resize_hpt *rhpt) +int kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) { unsigned long flags = rhpt->flags; unsigned long shift = rhpt->shift; @@ -1534,13 +1534,13 @@ static void resize_hpt_boot_vcpu(void *opaque) /* Nothing to do, just force a KVM exit */ } -long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, - struct kvm_ppc_resize_hpt *rhpt) +int kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, + struct kvm_ppc_resize_hpt *rhpt) { unsigned long flags = rhpt->flags; unsigned long shift = rhpt->shift; struct kvm_resize_hpt *resize; - long ret; + int ret; if (flags != 0 || kvm_is_radix(kvm)) return -EINVAL; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 95e738ef9062..93b695b289e9 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -288,8 +288,8 @@ static const struct file_operations kvm_spapr_tce_fops = { .release = kvm_spapr_tce_release, }; -long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, - struct kvm_create_spapr_tce_64 *args) +int kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, + struct kvm_create_spapr_tce_64 *args) { struct kvmppc_spapr_tce_table *stt = NULL; struct kvmppc_spapr_tce_table *siter; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6ba68dd6190b..cd139a1edc67 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -5779,12 +5779,12 @@ static void kvmppc_irq_bypass_del_producer_hv(struct irq_bypass_consumer *cons, } #endif -static long kvm_arch_vm_ioctl_hv(struct file *filp, - unsigned int ioctl, unsigned long arg) +static int kvm_arch_vm_ioctl_hv(struct file *filp, + unsigned int ioctl, unsigned long arg) { struct kvm *kvm __maybe_unused = filp->private_data; void __user *argp = (void __user *)arg; - long r; + int r; switch (ioctl) { diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 9fc4dd8f66eb..5908b514bfb6 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -2042,8 +2042,8 @@ static int kvmppc_core_check_processor_compat_pr(void) return 0; } -static long kvm_arch_vm_ioctl_pr(struct file *filp, - unsigned int ioctl, unsigned long arg) +static int kvm_arch_vm_ioctl_pr(struct file *filp, + unsigned int ioctl, unsigned long arg) { return -ENOTTY; } -- GitLab From 71fb165e23e3b66e68ca7baab6c317c2663c32d5 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:01 +0100 Subject: [PATCH 0645/5631] KVM: s390: Use "int" as return type for kvm_s390_get/set_skeys() These two functions only return normal integers, so it does not make sense to declare the return type as "long" here. Reviewed-by: Claudio Imbrenda Signed-off-by: Thomas Huth Message-Id: <20230208140105.655814-3-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- arch/s390/kvm/kvm-s390.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 39b36562c043..7039abda6d49 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1989,7 +1989,7 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) return ret; } -static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) { uint8_t *keys; uint64_t hva; @@ -2037,7 +2037,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) return r; } -static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) +static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) { uint8_t *keys; uint64_t hva; -- GitLab From c5edd753a0bd6243a597f5199c227a50457ee179 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:02 +0100 Subject: [PATCH 0646/5631] KVM: x86: Remove the KVM_GET_NR_MMU_PAGES ioctl The KVM_GET_NR_MMU_PAGES ioctl is quite questionable on 64-bit hosts since it fails to return the full 64 bits of the value that can be set with the corresponding KVM_SET_NR_MMU_PAGES call. Its "long" return value is truncated into an "int" in the kvm_arch_vm_ioctl() function. Since this ioctl also never has been used by userspace applications (QEMU, Google's internal VMM, kvmtool and CrosVM have been checked), it's likely the best if we remove this badly designed ioctl before anybody really tries to use it. Signed-off-by: Thomas Huth Reviewed-by: Sean Christopherson Message-Id: <20230208140105.655814-4-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 8 -------- include/uapi/linux/kvm.h | 2 +- tools/include/uapi/linux/kvm.h | 2 +- 3 files changed, 2 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ff7f398a0c6a..4282daeaee84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6021,11 +6021,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) -{ - return kvm->arch.n_max_mmu_pages; -} - static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { struct kvm_pic *pic = kvm->arch.vpic; @@ -6711,9 +6706,6 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; - case KVM_GET_NR_MMU_PAGES: - r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); - break; case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..4003a166328c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1451,7 +1451,7 @@ struct kvm_vfio_spapr_tce { #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) -#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */ #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d77aef872a0a..4003a166328c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1451,7 +1451,7 @@ struct kvm_vfio_spapr_tce { #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) -#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */ #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ struct kvm_userspace_memory_region) #define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) -- GitLab From 2def950c63e3f976af87a2606dabe0c9e21c605b Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:03 +0100 Subject: [PATCH 0647/5631] KVM: arm64: Limit length in kvm_vm_ioctl_mte_copy_tags() to INT_MAX In case of success, this function returns the amount of handled bytes. However, this does not work for large values: The function is called from kvm_arch_vm_ioctl() (which still returns a long), which in turn is called from kvm_vm_ioctl() in virt/kvm/kvm_main.c. And that function stores the return value in an "int r" variable. So the upper 32-bits of the "long" return value are lost there. KVM ioctl functions should only return "int" values, so let's limit the amount of bytes that can be requested here to INT_MAX to avoid the problem with the truncated return value. We can then also change the return type of the function to "int" to make it clearer that it is not possible to return a "long" here. Fixes: f0376edb1ddc ("KVM: arm64: Add ioctl to fetch/store tags in a guest") Signed-off-by: Thomas Huth Reviewed-by: Cornelia Huck Reviewed-by: Gavin Shan Reviewed-by: Steven Price Message-Id: <20230208140105.655814-5-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 3 ++- arch/arm64/include/asm/kvm_host.h | 4 ++-- arch/arm64/kvm/guest.c | 8 ++++++-- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 62de0768d6aa..48fad6556822 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5645,7 +5645,8 @@ with the KVM_XEN_VCPU_GET_ATTR ioctl. }; Copies Memory Tagging Extension (MTE) tags to/from guest tag memory. The -``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned. The ``addr`` +``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned. +``length`` must not be bigger than 2^31 - PAGE_SIZE bytes. The ``addr`` field must point to a buffer which the tags will be copied to or from. ``flags`` specifies the direction of copy, either ``KVM_ARM_TAGS_TO_GUEST`` or diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bcd774d74f34..6f7b218a681f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1005,8 +1005,8 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, - struct kvm_arm_copy_mte_tags *copy_tags); +int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, + struct kvm_arm_copy_mte_tags *copy_tags); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07444fa22888..26a2ebc465ea 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -1019,8 +1019,8 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, return ret; } -long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, - struct kvm_arm_copy_mte_tags *copy_tags) +int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, + struct kvm_arm_copy_mte_tags *copy_tags) { gpa_t guest_ipa = copy_tags->guest_ipa; size_t length = copy_tags->length; @@ -1041,6 +1041,10 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK) return -EINVAL; + /* Lengths above INT_MAX cannot be represented in the return value */ + if (length > INT_MAX) + return -EINVAL; + gfn = gpa_to_gfn(guest_ipa); mutex_lock(&kvm->slots_lock); -- GitLab From f15ba52bfabc3bc130053bd73d414d859162de91 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:04 +0100 Subject: [PATCH 0648/5631] KVM: Standardize on "int" return types instead of "long" in kvm_main.c KVM functions use "long" return values for functions that are wired up to "struct file_operations", but otherwise use "int" return values for functions that can return 0/-errno in order to avoid unintentional divergences between 32-bit and 64-bit kernels. Some code still uses "long" in unnecessary spots, though, which can cause a little bit of confusion and unnecessary size casts. Let's change these spots to use "int" types, too. Signed-off-by: Thomas Huth Message-Id: <20230208140105.655814-6-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d255964ec331..f40b72eb0e7b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4467,7 +4467,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return 0; } -static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) +static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: @@ -5045,7 +5045,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { - long r = -EINVAL; + int r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: -- GitLab From d8708b80fa0e6e21bc0c9e7276ad0bccef73b6e7 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Wed, 8 Feb 2023 15:01:05 +0100 Subject: [PATCH 0649/5631] KVM: Change return type of kvm_arch_vm_ioctl() to "int" All kvm_arch_vm_ioctl() implementations now only deal with "int" types as return values, so we can change the return type of these functions to use "int" instead of "long". Signed-off-by: Thomas Huth Acked-by: Anup Patel Message-Id: <20230208140105.655814-7-thuth@redhat.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arm.c | 3 +-- arch/mips/kvm/mips.c | 4 ++-- arch/powerpc/kvm/powerpc.c | 5 ++--- arch/riscv/kvm/vm.c | 3 +-- arch/s390/kvm/kvm-s390.c | 3 +-- arch/x86/kvm/x86.c | 3 +-- include/linux/kvm_host.h | 3 +-- 7 files changed, 9 insertions(+), 15 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3bd732eaf087..a43e1cb3b7e9 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1439,8 +1439,7 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, } } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 36c8991b5d39..884be4ef99dc 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -993,9 +993,9 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); } -long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { - long r; + int r; switch (ioctl) { default: diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 4c5405fc5538..c0bac9cf2d87 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -2371,12 +2371,11 @@ static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp) } #endif -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm __maybe_unused = filp->private_data; void __user *argp = (void __user *)arg; - long r; + int r; switch (ioctl) { case KVM_PPC_GET_PVINFO: { diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 65a964d7e70d..c13130ab459a 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -87,8 +87,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7039abda6d49..4c3edccb9911 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2898,8 +2898,7 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop) } } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4282daeaee84..237c483b1230 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6667,8 +6667,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) return 0; } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8ada23756b0e..90edc16d37e5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1397,8 +1397,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level, bool line_status); int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap); -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg); +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); long kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); -- GitLab From 10258bf4534bf8123b5fa620f73fe69901857f69 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Mon, 6 Feb 2023 20:58:30 +0100 Subject: [PATCH 0650/5631] backlight: qcom-wled: Add PMI8950 compatible PMI8950 contains WLED of version 4. Add support for it to the driver. Signed-off-by: Luca Weiss Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221226-msm8953-6-2-wled-v1-1-e318d4c71d05@z3ntu.xyz --- drivers/video/backlight/qcom-wled.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c index 527210e85795..5f504883aca5 100644 --- a/drivers/video/backlight/qcom-wled.c +++ b/drivers/video/backlight/qcom-wled.c @@ -1731,6 +1731,7 @@ static int wled_remove(struct platform_device *pdev) static const struct of_device_id wled_match_table[] = { { .compatible = "qcom,pm8941-wled", .data = (void *)3 }, + { .compatible = "qcom,pmi8950-wled", .data = (void *)4 }, { .compatible = "qcom,pmi8994-wled", .data = (void *)4 }, { .compatible = "qcom,pmi8998-wled", .data = (void *)4 }, { .compatible = "qcom,pm660l-wled", .data = (void *)4 }, -- GitLab From 8b339caf4255a5cfafdc743be601100c5da6c304 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:33 +0100 Subject: [PATCH 0651/5631] backlight: aat2870_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-2-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/aat2870_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/aat2870_bl.c b/drivers/video/backlight/aat2870_bl.c index 1cbb303e9c88..81fde3abb92c 100644 --- a/drivers/video/backlight/aat2870_bl.c +++ b/drivers/video/backlight/aat2870_bl.c @@ -178,7 +178,7 @@ static int aat2870_bl_probe(struct platform_device *pdev) return ret; } -static int aat2870_bl_remove(struct platform_device *pdev) +static void aat2870_bl_remove(struct platform_device *pdev) { struct aat2870_bl_driver_data *aat2870_bl = platform_get_drvdata(pdev); struct backlight_device *bd = aat2870_bl->bd; @@ -186,8 +186,6 @@ static int aat2870_bl_remove(struct platform_device *pdev) bd->props.power = FB_BLANK_POWERDOWN; bd->props.brightness = 0; backlight_update_status(bd); - - return 0; } static struct platform_driver aat2870_bl_driver = { @@ -195,7 +193,7 @@ static struct platform_driver aat2870_bl_driver = { .name = "aat2870-backlight", }, .probe = aat2870_bl_probe, - .remove = aat2870_bl_remove, + .remove_new = aat2870_bl_remove, }; static int __init aat2870_bl_init(void) -- GitLab From 6879039167ff4b6805760f1c5935e93c92dc6aa4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:34 +0100 Subject: [PATCH 0652/5631] backlight: adp5520_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Michael Hennerich Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-3-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/adp5520_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/adp5520_bl.c b/drivers/video/backlight/adp5520_bl.c index 686988c3df3a..8e0e9cfe5fe9 100644 --- a/drivers/video/backlight/adp5520_bl.c +++ b/drivers/video/backlight/adp5520_bl.c @@ -337,7 +337,7 @@ static int adp5520_bl_probe(struct platform_device *pdev) return 0; } -static int adp5520_bl_remove(struct platform_device *pdev) +static void adp5520_bl_remove(struct platform_device *pdev) { struct backlight_device *bl = platform_get_drvdata(pdev); struct adp5520_bl *data = bl_get_data(bl); @@ -347,8 +347,6 @@ static int adp5520_bl_remove(struct platform_device *pdev) if (data->pdata->en_ambl_sens) sysfs_remove_group(&bl->dev.kobj, &adp5520_bl_attr_group); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -377,7 +375,7 @@ static struct platform_driver adp5520_bl_driver = { .pm = &adp5520_bl_pm_ops, }, .probe = adp5520_bl_probe, - .remove = adp5520_bl_remove, + .remove_new = adp5520_bl_remove, }; module_platform_driver(adp5520_bl_driver); -- GitLab From f6672d7f0cff6ee8bd09851545b60e41099197ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:35 +0100 Subject: [PATCH 0653/5631] backlight: cr_bllcd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-4-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/cr_bllcd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/cr_bllcd.c b/drivers/video/backlight/cr_bllcd.c index 4ad0a72531fe..781aeecc451d 100644 --- a/drivers/video/backlight/cr_bllcd.c +++ b/drivers/video/backlight/cr_bllcd.c @@ -210,7 +210,7 @@ static int cr_backlight_probe(struct platform_device *pdev) return 0; } -static int cr_backlight_remove(struct platform_device *pdev) +static void cr_backlight_remove(struct platform_device *pdev) { struct cr_panel *crp = platform_get_drvdata(pdev); @@ -220,13 +220,11 @@ static int cr_backlight_remove(struct platform_device *pdev) cr_backlight_set_intensity(crp->cr_backlight_device); cr_lcd_set_power(crp->cr_lcd_device, FB_BLANK_POWERDOWN); pci_dev_put(lpc_dev); - - return 0; } static struct platform_driver cr_backlight_driver = { .probe = cr_backlight_probe, - .remove = cr_backlight_remove, + .remove_new = cr_backlight_remove, .driver = { .name = "cr_backlight", }, -- GitLab From 78a2bb4802071788ce2315f1c8002f10b121d33c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:36 +0100 Subject: [PATCH 0654/5631] backlight: da9052_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Adam Ward Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-5-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/da9052_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/da9052_bl.c b/drivers/video/backlight/da9052_bl.c index 882359dd288c..1cdc8543310b 100644 --- a/drivers/video/backlight/da9052_bl.c +++ b/drivers/video/backlight/da9052_bl.c @@ -135,7 +135,7 @@ static int da9052_backlight_probe(struct platform_device *pdev) return da9052_adjust_wled_brightness(wleds); } -static int da9052_backlight_remove(struct platform_device *pdev) +static void da9052_backlight_remove(struct platform_device *pdev) { struct backlight_device *bl = platform_get_drvdata(pdev); struct da9052_bl *wleds = bl_get_data(bl); @@ -143,8 +143,6 @@ static int da9052_backlight_remove(struct platform_device *pdev) wleds->brightness = 0; wleds->state = DA9052_WLEDS_OFF; da9052_adjust_wled_brightness(wleds); - - return 0; } static const struct platform_device_id da9052_wled_ids[] = { @@ -166,7 +164,7 @@ MODULE_DEVICE_TABLE(platform, da9052_wled_ids); static struct platform_driver da9052_wled_driver = { .probe = da9052_backlight_probe, - .remove = da9052_backlight_remove, + .remove_new = da9052_backlight_remove, .id_table = da9052_wled_ids, .driver = { .name = "da9052-wled", -- GitLab From 7150f8c2aa9d28a9bdc2f67180df26af5896253d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:37 +0100 Subject: [PATCH 0655/5631] backlight: hp680_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-6-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/hp680_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/hp680_bl.c b/drivers/video/backlight/hp680_bl.c index 9123c33def05..ddb7ab4df77e 100644 --- a/drivers/video/backlight/hp680_bl.c +++ b/drivers/video/backlight/hp680_bl.c @@ -119,20 +119,18 @@ static int hp680bl_probe(struct platform_device *pdev) return 0; } -static int hp680bl_remove(struct platform_device *pdev) +static void hp680bl_remove(struct platform_device *pdev) { struct backlight_device *bd = platform_get_drvdata(pdev); bd->props.brightness = 0; bd->props.power = 0; hp680bl_send_intensity(bd); - - return 0; } static struct platform_driver hp680bl_driver = { .probe = hp680bl_probe, - .remove = hp680bl_remove, + .remove_new = hp680bl_remove, .driver = { .name = "hp680-bl", .pm = &hp680bl_pm_ops, -- GitLab From c4c4fa57fd3cc00020152baa169337521f90b2ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:38 +0100 Subject: [PATCH 0656/5631] backlight: led_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-7-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/led_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/led_bl.c b/drivers/video/backlight/led_bl.c index f54d256e2d54..a1b6a2ad73a0 100644 --- a/drivers/video/backlight/led_bl.c +++ b/drivers/video/backlight/led_bl.c @@ -217,7 +217,7 @@ static int led_bl_probe(struct platform_device *pdev) return 0; } -static int led_bl_remove(struct platform_device *pdev) +static void led_bl_remove(struct platform_device *pdev) { struct led_bl_data *priv = platform_get_drvdata(pdev); struct backlight_device *bl = priv->bl_dev; @@ -228,8 +228,6 @@ static int led_bl_remove(struct platform_device *pdev) led_bl_power_off(priv); for (i = 0; i < priv->nb_leds; i++) led_sysfs_enable(priv->leds[i]); - - return 0; } static const struct of_device_id led_bl_of_match[] = { @@ -245,7 +243,7 @@ static struct platform_driver led_bl_driver = { .of_match_table = of_match_ptr(led_bl_of_match), }, .probe = led_bl_probe, - .remove = led_bl_remove, + .remove_new = led_bl_remove, }; module_platform_driver(led_bl_driver); -- GitLab From cba7dfe04f84f39e0fea353eec511b9ce8455e59 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:39 +0100 Subject: [PATCH 0657/5631] backlight: lm3533_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-8-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/lm3533_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/lm3533_bl.c b/drivers/video/backlight/lm3533_bl.c index 1df1b6643c0b..3e10d480cb7f 100644 --- a/drivers/video/backlight/lm3533_bl.c +++ b/drivers/video/backlight/lm3533_bl.c @@ -337,7 +337,7 @@ static int lm3533_bl_probe(struct platform_device *pdev) return ret; } -static int lm3533_bl_remove(struct platform_device *pdev) +static void lm3533_bl_remove(struct platform_device *pdev) { struct lm3533_bl *bl = platform_get_drvdata(pdev); struct backlight_device *bd = bl->bd; @@ -349,8 +349,6 @@ static int lm3533_bl_remove(struct platform_device *pdev) lm3533_ctrlbank_disable(&bl->cb); sysfs_remove_group(&bd->dev.kobj, &lm3533_bl_attribute_group); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -390,7 +388,7 @@ static struct platform_driver lm3533_bl_driver = { .pm = &lm3533_bl_pm_ops, }, .probe = lm3533_bl_probe, - .remove = lm3533_bl_remove, + .remove_new = lm3533_bl_remove, .shutdown = lm3533_bl_shutdown, }; module_platform_driver(lm3533_bl_driver); -- GitLab From 1c708d346c15e2cd2e0f701e6df04094d1b544ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:40 +0100 Subject: [PATCH 0658/5631] backlight: lp8788_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-9-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/lp8788_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/lp8788_bl.c b/drivers/video/backlight/lp8788_bl.c index ba42f3fe0c73..d1a14b0db265 100644 --- a/drivers/video/backlight/lp8788_bl.c +++ b/drivers/video/backlight/lp8788_bl.c @@ -298,7 +298,7 @@ static int lp8788_backlight_probe(struct platform_device *pdev) return ret; } -static int lp8788_backlight_remove(struct platform_device *pdev) +static void lp8788_backlight_remove(struct platform_device *pdev) { struct lp8788_bl *bl = platform_get_drvdata(pdev); struct backlight_device *bl_dev = bl->bl_dev; @@ -307,13 +307,11 @@ static int lp8788_backlight_remove(struct platform_device *pdev) backlight_update_status(bl_dev); sysfs_remove_group(&pdev->dev.kobj, &lp8788_attr_group); lp8788_backlight_unregister(bl); - - return 0; } static struct platform_driver lp8788_bl_driver = { .probe = lp8788_backlight_probe, - .remove = lp8788_backlight_remove, + .remove_new = lp8788_backlight_remove, .driver = { .name = LP8788_DEV_BACKLIGHT, }, -- GitLab From 519e5cc52946c62878b4b4a7ef9f79fcb8164c52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:41 +0100 Subject: [PATCH 0659/5631] backlight: mt6370-backlight: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-10-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/mt6370-backlight.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/mt6370-backlight.c b/drivers/video/backlight/mt6370-backlight.c index 623d4f2baca2..94422c956453 100644 --- a/drivers/video/backlight/mt6370-backlight.c +++ b/drivers/video/backlight/mt6370-backlight.c @@ -318,15 +318,13 @@ static int mt6370_bl_probe(struct platform_device *pdev) return 0; } -static int mt6370_bl_remove(struct platform_device *pdev) +static void mt6370_bl_remove(struct platform_device *pdev) { struct mt6370_priv *priv = platform_get_drvdata(pdev); struct backlight_device *bl_dev = priv->bl; bl_dev->props.brightness = 0; backlight_update_status(priv->bl); - - return 0; } static const struct of_device_id mt6370_bl_of_match[] = { @@ -342,7 +340,7 @@ static struct platform_driver mt6370_bl_driver = { .of_match_table = mt6370_bl_of_match, }, .probe = mt6370_bl_probe, - .remove = mt6370_bl_remove, + .remove_new = mt6370_bl_remove, }; module_platform_driver(mt6370_bl_driver); -- GitLab From 0a4606a7a4bc6f876354ff6d90b969172208eeef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:42 +0100 Subject: [PATCH 0660/5631] backlight: pwm_bl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-11-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/pwm_bl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index fb388148d98f..fce412234d10 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -625,7 +625,7 @@ static int pwm_backlight_probe(struct platform_device *pdev) return ret; } -static int pwm_backlight_remove(struct platform_device *pdev) +static void pwm_backlight_remove(struct platform_device *pdev) { struct backlight_device *bl = platform_get_drvdata(pdev); struct pwm_bl_data *pb = bl_get_data(bl); @@ -635,8 +635,6 @@ static int pwm_backlight_remove(struct platform_device *pdev) if (pb->exit) pb->exit(&pdev->dev); - - return 0; } static void pwm_backlight_shutdown(struct platform_device *pdev) @@ -690,7 +688,7 @@ static struct platform_driver pwm_backlight_driver = { .of_match_table = of_match_ptr(pwm_backlight_of_match), }, .probe = pwm_backlight_probe, - .remove = pwm_backlight_remove, + .remove_new = pwm_backlight_remove, .shutdown = pwm_backlight_shutdown, }; -- GitLab From ea379bc80231c8a86730f854e436eff19a729950 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:43 +0100 Subject: [PATCH 0661/5631] backlight: qcom-wled: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-12-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/qcom-wled.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c index 5f504883aca5..c6996aa288e6 100644 --- a/drivers/video/backlight/qcom-wled.c +++ b/drivers/video/backlight/qcom-wled.c @@ -1717,7 +1717,7 @@ static int wled_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(bl); }; -static int wled_remove(struct platform_device *pdev) +static void wled_remove(struct platform_device *pdev) { struct wled *wled = platform_get_drvdata(pdev); @@ -1725,8 +1725,6 @@ static int wled_remove(struct platform_device *pdev) cancel_delayed_work_sync(&wled->ovp_work); disable_irq(wled->short_irq); disable_irq(wled->ovp_irq); - - return 0; } static const struct of_device_id wled_match_table[] = { @@ -1743,7 +1741,7 @@ MODULE_DEVICE_TABLE(of, wled_match_table); static struct platform_driver wled_driver = { .probe = wled_probe, - .remove = wled_remove, + .remove_new = wled_remove, .driver = { .name = "qcom,wled", .of_match_table = wled_match_table, -- GitLab From 20c111d2e18c7318a9f2ae815c84ea0a9218317e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:44 +0100 Subject: [PATCH 0662/5631] backlight: rt4831-backlight: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-13-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/rt4831-backlight.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/rt4831-backlight.c b/drivers/video/backlight/rt4831-backlight.c index eb8c59e8713f..7d1af4c2ca67 100644 --- a/drivers/video/backlight/rt4831-backlight.c +++ b/drivers/video/backlight/rt4831-backlight.c @@ -203,15 +203,13 @@ static int rt4831_bl_probe(struct platform_device *pdev) return 0; } -static int rt4831_bl_remove(struct platform_device *pdev) +static void rt4831_bl_remove(struct platform_device *pdev) { struct rt4831_priv *priv = platform_get_drvdata(pdev); struct backlight_device *bl_dev = priv->bl; bl_dev->props.brightness = 0; backlight_update_status(priv->bl); - - return 0; } static const struct of_device_id __maybe_unused rt4831_bl_of_match[] = { @@ -226,7 +224,7 @@ static struct platform_driver rt4831_bl_driver = { .of_match_table = rt4831_bl_of_match, }, .probe = rt4831_bl_probe, - .remove = rt4831_bl_remove, + .remove_new = rt4831_bl_remove, }; module_platform_driver(rt4831_bl_driver); -- GitLab From 541ec23c603dcb3b9cebebe40d9a68cdc89dd36b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 08:39:45 +0100 Subject: [PATCH 0663/5631] backlight: sky81452-backlight: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308073945.2336302-14-u.kleine-koenig@pengutronix.de --- drivers/video/backlight/sky81452-backlight.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/video/backlight/sky81452-backlight.c b/drivers/video/backlight/sky81452-backlight.c index 0172438c38ce..eb18c6eb0ff0 100644 --- a/drivers/video/backlight/sky81452-backlight.c +++ b/drivers/video/backlight/sky81452-backlight.c @@ -311,7 +311,7 @@ static int sky81452_bl_probe(struct platform_device *pdev) return ret; } -static int sky81452_bl_remove(struct platform_device *pdev) +static void sky81452_bl_remove(struct platform_device *pdev) { const struct sky81452_bl_platform_data *pdata = dev_get_platdata(&pdev->dev); @@ -325,8 +325,6 @@ static int sky81452_bl_remove(struct platform_device *pdev) if (pdata->gpiod_enable) gpiod_set_value_cansleep(pdata->gpiod_enable, 0); - - return 0; } #ifdef CONFIG_OF @@ -343,7 +341,7 @@ static struct platform_driver sky81452_bl_driver = { .of_match_table = of_match_ptr(sky81452_bl_of_match), }, .probe = sky81452_bl_probe, - .remove = sky81452_bl_remove, + .remove_new = sky81452_bl_remove, }; module_platform_driver(sky81452_bl_driver); -- GitLab From a61079efc87888587e463afaed82417b162fbd69 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 25 Feb 2023 21:39:49 -0800 Subject: [PATCH 0664/5631] leds: TI_LMU_COMMON: select REGMAP instead of depending on it REGMAP is a hidden (not user visible) symbol. Users cannot set it directly thru "make *config", so drivers should select it instead of depending on it if they need it. Consistently using "select" or "depends on" can also help reduce Kconfig circular dependency issues. Therefore, change the use of "depends on REGMAP" to "select REGMAP". Fixes: 3fce8e1eb994 ("leds: TI LMU: Add common code for TI LMU devices") Signed-off-by: Randy Dunlap Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230226053953.4681-5-rdunlap@infradead.org --- drivers/leds/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 9dbce09eabac..aaa9140bc351 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -795,7 +795,7 @@ config LEDS_SPI_BYTE config LEDS_TI_LMU_COMMON tristate "LED driver for TI LMU" depends on LEDS_CLASS - depends on REGMAP + select REGMAP help Say Y to enable the LED driver for TI LMU devices. This supports common features between the TI LM3532, LM3631, LM3632, -- GitLab From 2956ad80fc56af2cb3a6bb374ebe587795abff0f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 19:04:02 +0200 Subject: [PATCH 0665/5631] leds: lp8860: Remove unused of_gpio,h of_gpio.h provides a single function, which is not used in this driver. Remove unused header. Signed-off-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230215170403.84449-1-andriy.shevchenko@linux.intel.com --- drivers/leds/leds-lp8860.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c index b66ed5ac1aa5..666f4d38214f 100644 --- a/drivers/leds/leds-lp8860.c +++ b/drivers/leds/leds-lp8860.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include -- GitLab From 6d19367b9e2f63e14bc034110f34b9a112b43ce0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 15 Feb 2023 19:04:03 +0200 Subject: [PATCH 0666/5631] leds: lp8860: Remove duplicate NULL checks for gpio_desc gpiod_*() API check already for the NULL, no need to repeat that in the driver. Signed-off-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230215170403.84449-2-andriy.shevchenko@linux.intel.com --- drivers/leds/leds-lp8860.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/leds/leds-lp8860.c b/drivers/leds/leds-lp8860.c index 666f4d38214f..221b386443bc 100644 --- a/drivers/leds/leds-lp8860.c +++ b/drivers/leds/leds-lp8860.c @@ -249,8 +249,7 @@ static int lp8860_init(struct lp8860_led *led) } } - if (led->enable_gpio) - gpiod_direction_output(led->enable_gpio, 1); + gpiod_direction_output(led->enable_gpio, 1); ret = lp8860_fault_check(led); if (ret) @@ -293,8 +292,7 @@ static int lp8860_init(struct lp8860_led *led) out: if (ret) - if (led->enable_gpio) - gpiod_direction_output(led->enable_gpio, 0); + gpiod_direction_output(led->enable_gpio, 0); if (led->regulator) { ret = regulator_disable(led->regulator); @@ -448,8 +446,7 @@ static void lp8860_remove(struct i2c_client *client) struct lp8860_led *led = i2c_get_clientdata(client); int ret; - if (led->enable_gpio) - gpiod_direction_output(led->enable_gpio, 0); + gpiod_direction_output(led->enable_gpio, 0); if (led->regulator) { ret = regulator_disable(led->regulator); -- GitLab From 8af70e202ac4ea5dd2d5561cc2675bc09b30412e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Feb 2023 17:21:21 +0000 Subject: [PATCH 0667/5631] leds: Fix reference to led_set_brightness() in doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The referenced function led_classdev_brightness_set() never existed. Fixes: 5ada28bf7675 ("led-class: always implement blinking") Signed-off-by: Thomas Weißschuh Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230218-typo-led-set-v1-1-3c35362a2f2d@weissschuh.net --- include/linux/leds.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/leds.h b/include/linux/leds.h index d71201a968b6..aedf34165354 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -256,7 +256,7 @@ struct led_classdev *__must_check devm_of_led_get(struct device *dev, * * Note that if software blinking is active, simply calling * led_cdev->brightness_set() will not stop the blinking, - * use led_classdev_brightness_set() instead. + * use led_set_brightness() instead. */ void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, unsigned long *delay_off); -- GitLab From e91a4d5deb96c496ef8e6fd8d7342515d9e64ab5 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Fri, 3 Mar 2023 17:59:25 +0530 Subject: [PATCH 0668/5631] dt-bindings: leds: Document commonly used LED triggers Document the commonly used LED triggers by the SoCs. Not all triggers are documented as some of them are very application specific. Most of the triggers documented here are currently used in devicetrees of many SoCs. While at it, add missing comments and also place the comment above the triggers (hci, mmc, wlan) to match the rest of the binding. Signed-off-by: Manivannan Sadhasivam Reviewed-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230303122925.6610-1-manivannan.sadhasivam@linaro.org --- .../devicetree/bindings/leds/common.yaml | 33 +++++++++++++++++-- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index 15e3f6645682..61e63ed81ced 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -90,22 +90,49 @@ properties: - heartbeat # LED indicates disk activity - disk-activity + # LED indicates disk read activity - disk-read + # LED indicates disk write activity - disk-write # LED flashes at a fixed, configurable rate - timer # LED alters the brightness for the specified duration with one software # timer (requires "led-pattern" property) - pattern + # LED indicates mic mute state + - audio-micmute + # LED indicates audio mute state + - audio-mute + # LED indicates bluetooth power state + - bluetooth-power + # LED indicates activity of all CPUs + - cpu + # LED indicates camera flash state + - flash + # LED indicated keyboard capslock + - kbd-capslock + # LED indicates MTD memory activity + - mtd + # LED indicates NAND memory activity (deprecated), + # in new implementations use "mtd" + - nand-disk + # No trigger assigned to the LED. This is the default mode + # if trigger is absent + - none + # LED indicates camera torch state + - torch + # LED indicates USB gadget activity - usb-gadget + # LED indicates USB host activity - usb-host + # LED is triggered by CPU activity - pattern: "^cpu[0-9]*$" - - pattern: "^hci[0-9]+-power$" # LED is triggered by Bluetooth activity - - pattern: "^mmc[0-9]+$" + - pattern: "^hci[0-9]+-power$" # LED is triggered by SD/MMC activity - - pattern: "^phy[0-9]+tx$" + - pattern: "^mmc[0-9]+$" # LED is triggered by WLAN activity + - pattern: "^phy[0-9]+tx$" led-pattern: description: | -- GitLab From e0248a258c7f5f7b0a3f2283f5cd2e472dfb7eeb Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:17:17 +0100 Subject: [PATCH 0669/5631] leds: tlc591xx: Mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/leds/leds-tlc591xx.c:138:34: error: ‘of_tlc591xx_leds_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230311111717.252019-1-krzysztof.kozlowski@linaro.org --- drivers/leds/leds-tlc591xx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/leds-tlc591xx.c b/drivers/leds/leds-tlc591xx.c index ec25e0c16bea..7e31db50036f 100644 --- a/drivers/leds/leds-tlc591xx.c +++ b/drivers/leds/leds-tlc591xx.c @@ -135,7 +135,7 @@ static const struct regmap_config tlc591xx_regmap = { .max_register = 0x1e, }; -static const struct of_device_id of_tlc591xx_leds_match[] = { +static const struct of_device_id of_tlc591xx_leds_match[] __maybe_unused = { { .compatible = "ti,tlc59116", .data = &tlc59116 }, { .compatible = "ti,tlc59108", -- GitLab From 8f0adae1cb1a3cf83e38dd435831baa38dd84b4c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 14 Mar 2023 22:00:59 +0100 Subject: [PATCH 0670/5631] leds: Mark GPIO LED trigger broken The GPIO LED trigger exposes a userspace ABI where a user can echo a GPIO number from the global GPIO numberspace into a file that will trigger a certain LED when active. This is problematic because the global GPIO numberspace is inherently instable. The trigger came about at a time when systems had one GPIO controller that defined hard-wired GPIOs numbered 0..N and this number space was stable. We have since moved to dynamic allocation of GPIO numbers and there is no real guarantee that a GPIO number will stay consistent even across a reboot: consider a USB attached GPIO controller for example. Or two. Or the effect of probe order after adding -EPROBE_DEFER to the kernel. The trigger was added to support keypad LEDs on the Nokia n810 from the GPIO event when a user slides up/down the keypad. This is arch/arm/boot/dts/omap2420-n810.dts. A userspace script is needed to activate the trigger. This will be broken unless the script was updated recently since the OMAP GPIO controller now uses dynamic GPIO number allocations. I want to know that this trigger has active users that cannot live without it if we are to continue to support it. Option if this is really needed: I can develop a new trigger that can associate GPIOs with LEDs as triggers using device tree, which should also remove the use of userspace custom scripts to achieve this and be much more trustworthy, if someone with the Nokia n810 or a device with a similar need is willing to test it. Suggested-by Pavel Machek Signed-off-by: Linus Walleij Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230314210059.419159-1-linus.walleij@linaro.org --- drivers/leds/trigger/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig index dc6816d36d06..2a57328eca20 100644 --- a/drivers/leds/trigger/Kconfig +++ b/drivers/leds/trigger/Kconfig @@ -83,6 +83,7 @@ config LEDS_TRIGGER_ACTIVITY config LEDS_TRIGGER_GPIO tristate "LED GPIO Trigger" depends on GPIOLIB || COMPILE_TEST + depends on BROKEN help This allows LEDs to be controlled by gpio events. It's good when using gpios as switches and triggering the needed LEDs -- GitLab From 96a2e242a5dcb677fe3063be38bda335c17849d3 Mon Sep 17 00:00:00 2001 From: Fenglin Wu Date: Fri, 3 Mar 2023 17:50:22 +0800 Subject: [PATCH 0671/5631] leds: flash: Add driver to support flash LED module in QCOM PMICs Add initial driver to support flash LED module found in Qualcomm Technologies, Inc. PMICs. The flash module can have 3 or 4 channels and each channel can be controlled indepedently and support full scale current up to 1.5 A. It also supports connecting two channels together to supply one LED component with full scale current up to 2 A. In that case, the current will be split on each channel symmetrically and the channels will be enabled and disabled at the same time. Signed-off-by: Fenglin Wu Tested-by: Luca Weiss # sm7225-fairphone-fp4 + pm6150l Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230303095023.538917-2-quic_fenglinw@quicinc.com --- drivers/leds/flash/Kconfig | 15 + drivers/leds/flash/Makefile | 1 + drivers/leds/flash/leds-qcom-flash.c | 773 +++++++++++++++++++++++++++ 3 files changed, 789 insertions(+) create mode 100644 drivers/leds/flash/leds-qcom-flash.c diff --git a/drivers/leds/flash/Kconfig b/drivers/leds/flash/Kconfig index d3eb689b193c..f36a60409290 100644 --- a/drivers/leds/flash/Kconfig +++ b/drivers/leds/flash/Kconfig @@ -61,6 +61,21 @@ config LEDS_MT6360 Independent current sources supply for each flash LED support torch and strobe mode. +config LEDS_QCOM_FLASH + tristate "LED support for flash module inside Qualcomm Technologies, Inc. PMIC" + depends on MFD_SPMI_PMIC || COMPILE_TEST + depends on LEDS_CLASS && OF + depends on V4L2_FLASH_LED_CLASS || !V4L2_FLASH_LED_CLASS + select REGMAP + help + This option enables support for the flash module found in Qualcomm + Technologies, Inc. PMICs. The flash module can have 3 or 4 flash LED + channels and each channel is programmable to support up to 1.5 A full + scale current. It also supports connecting two channels' output together + to supply one LED component to achieve current up to 2 A. In such case, + the total LED current will be split symmetrically on each channel and + they will be enabled/disabled at the same time. + config LEDS_RT4505 tristate "LED support for RT4505 flashlight controller" depends on I2C && OF diff --git a/drivers/leds/flash/Makefile b/drivers/leds/flash/Makefile index 0acbddc0b91b..8a60993f1a25 100644 --- a/drivers/leds/flash/Makefile +++ b/drivers/leds/flash/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_LEDS_AS3645A) += leds-as3645a.o obj-$(CONFIG_LEDS_KTD2692) += leds-ktd2692.o obj-$(CONFIG_LEDS_LM3601X) += leds-lm3601x.o obj-$(CONFIG_LEDS_MAX77693) += leds-max77693.o +obj-$(CONFIG_LEDS_QCOM_FLASH) += leds-qcom-flash.o obj-$(CONFIG_LEDS_RT4505) += leds-rt4505.o obj-$(CONFIG_LEDS_RT8515) += leds-rt8515.o obj-$(CONFIG_LEDS_SGM3140) += leds-sgm3140.o diff --git a/drivers/leds/flash/leds-qcom-flash.c b/drivers/leds/flash/leds-qcom-flash.c new file mode 100644 index 000000000000..406ed8761c78 --- /dev/null +++ b/drivers/leds/flash/leds-qcom-flash.c @@ -0,0 +1,773 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* registers definitions */ +#define FLASH_TYPE_REG 0x04 +#define FLASH_TYPE_VAL 0x18 + +#define FLASH_SUBTYPE_REG 0x05 +#define FLASH_SUBTYPE_3CH_VAL 0x04 +#define FLASH_SUBTYPE_4CH_VAL 0x07 + +#define FLASH_STS_3CH_OTST1 BIT(0) +#define FLASH_STS_3CH_OTST2 BIT(1) +#define FLASH_STS_3CH_OTST3 BIT(2) +#define FLASH_STS_3CH_BOB_THM_OVERLOAD BIT(3) +#define FLASH_STS_3CH_VPH_DROOP BIT(4) +#define FLASH_STS_3CH_BOB_ILIM_S1 BIT(5) +#define FLASH_STS_3CH_BOB_ILIM_S2 BIT(6) +#define FLASH_STS_3CH_BCL_IBAT BIT(7) + +#define FLASH_STS_4CH_VPH_LOW BIT(0) +#define FLASH_STS_4CH_BCL_IBAT BIT(1) +#define FLASH_STS_4CH_BOB_ILIM_S1 BIT(2) +#define FLASH_STS_4CH_BOB_ILIM_S2 BIT(3) +#define FLASH_STS_4CH_OTST2 BIT(4) +#define FLASH_STS_4CH_OTST1 BIT(5) +#define FLASH_STS_4CHG_BOB_THM_OVERLOAD BIT(6) + +#define FLASH_TIMER_EN_BIT BIT(7) +#define FLASH_TIMER_VAL_MASK GENMASK(6, 0) +#define FLASH_TIMER_STEP_MS 10 + +#define FLASH_STROBE_HW_SW_SEL_BIT BIT(2) +#define SW_STROBE_VAL 0 +#define HW_STROBE_VAL 1 +#define FLASH_HW_STROBE_TRIGGER_SEL_BIT BIT(1) +#define STROBE_LEVEL_TRIGGER_VAL 0 +#define STROBE_EDGE_TRIGGER_VAL 1 +#define FLASH_STROBE_POLARITY_BIT BIT(0) +#define STROBE_ACTIVE_HIGH_VAL 1 + +#define FLASH_IRES_MASK_4CH BIT(0) +#define FLASH_IRES_MASK_3CH GENMASK(1, 0) +#define FLASH_IRES_12P5MA_VAL 0 +#define FLASH_IRES_5MA_VAL_4CH 1 +#define FLASH_IRES_5MA_VAL_3CH 3 + +/* constants */ +#define FLASH_CURRENT_MAX_UA 1500000 +#define TORCH_CURRENT_MAX_UA 500000 +#define FLASH_TOTAL_CURRENT_MAX_UA 2000000 +#define FLASH_CURRENT_DEFAULT_UA 1000000 +#define TORCH_CURRENT_DEFAULT_UA 200000 + +#define TORCH_IRES_UA 5000 +#define FLASH_IRES_UA 12500 + +#define FLASH_TIMEOUT_MAX_US 1280000 +#define FLASH_TIMEOUT_STEP_US 10000 + +#define UA_PER_MA 1000 + +enum hw_type { + QCOM_MVFLASH_3CH, + QCOM_MVFLASH_4CH, +}; + +enum led_mode { + FLASH_MODE, + TORCH_MODE, +}; + +enum led_strobe { + SW_STROBE, + HW_STROBE, +}; + +enum { + REG_STATUS1, + REG_STATUS2, + REG_STATUS3, + REG_CHAN_TIMER, + REG_ITARGET, + REG_MODULE_EN, + REG_IRESOLUTION, + REG_CHAN_STROBE, + REG_CHAN_EN, + REG_MAX_COUNT, +}; + +struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = { + REG_FIELD(0x08, 0, 7), /* status1 */ + REG_FIELD(0x09, 0, 7), /* status2 */ + REG_FIELD(0x0a, 0, 7), /* status3 */ + REG_FIELD_ID(0x40, 0, 7, 3, 1), /* chan_timer */ + REG_FIELD_ID(0x43, 0, 6, 3, 1), /* itarget */ + REG_FIELD(0x46, 7, 7), /* module_en */ + REG_FIELD(0x47, 0, 5), /* iresolution */ + REG_FIELD_ID(0x49, 0, 2, 3, 1), /* chan_strobe */ + REG_FIELD(0x4c, 0, 2), /* chan_en */ +}; + +struct reg_field mvflash_4ch_regs[REG_MAX_COUNT] = { + REG_FIELD(0x06, 0, 7), /* status1 */ + REG_FIELD(0x07, 0, 6), /* status2 */ + REG_FIELD(0x09, 0, 7), /* status3 */ + REG_FIELD_ID(0x3e, 0, 7, 4, 1), /* chan_timer */ + REG_FIELD_ID(0x42, 0, 6, 4, 1), /* itarget */ + REG_FIELD(0x46, 7, 7), /* module_en */ + REG_FIELD(0x49, 0, 3), /* iresolution */ + REG_FIELD_ID(0x4a, 0, 6, 4, 1), /* chan_strobe */ + REG_FIELD(0x4e, 0, 3), /* chan_en */ +}; + +struct qcom_flash_data { + struct v4l2_flash **v4l2_flash; + struct regmap_field *r_fields[REG_MAX_COUNT]; + struct mutex lock; + enum hw_type hw_type; + u8 leds_count; + u8 max_channels; + u8 chan_en_bits; +}; + +struct qcom_flash_led { + struct qcom_flash_data *flash_data; + struct led_classdev_flash flash; + u32 max_flash_current_ma; + u32 max_torch_current_ma; + u32 max_timeout_ms; + u32 flash_current_ma; + u32 flash_timeout_ms; + u8 *chan_id; + u8 chan_count; + bool enabled; +}; + +static int set_flash_module_en(struct qcom_flash_led *led, bool en) +{ + struct qcom_flash_data *flash_data = led->flash_data; + u8 led_mask = 0, enable; + int i, rc; + + for (i = 0; i < led->chan_count; i++) + led_mask |= BIT(led->chan_id[i]); + + mutex_lock(&flash_data->lock); + if (en) + flash_data->chan_en_bits |= led_mask; + else + flash_data->chan_en_bits &= ~led_mask; + + enable = !!flash_data->chan_en_bits; + rc = regmap_field_write(flash_data->r_fields[REG_MODULE_EN], enable); + if (rc) + dev_err(led->flash.led_cdev.dev, "write module_en failed, rc=%d\n", rc); + mutex_unlock(&flash_data->lock); + + return rc; +} + +static int set_flash_current(struct qcom_flash_led *led, u32 current_ma, enum led_mode mode) +{ + struct qcom_flash_data *flash_data = led->flash_data; + u32 itarg_ua, ires_ua; + u8 shift, ires_mask = 0, ires_val = 0, chan_id; + int i, rc; + + /* + * Split the current across the channels and set the + * IRESOLUTION and ITARGET registers accordingly. + */ + itarg_ua = (current_ma * UA_PER_MA) / led->chan_count + 1; + ires_ua = (mode == FLASH_MODE) ? FLASH_IRES_UA : TORCH_IRES_UA; + + for (i = 0; i < led->chan_count; i++) { + u8 itarget = 0; + + if (itarg_ua > ires_ua) + itarget = itarg_ua / ires_ua - 1; + + chan_id = led->chan_id[i]; + + rc = regmap_fields_write(flash_data->r_fields[REG_ITARGET], chan_id, itarget); + if (rc) + return rc; + + if (flash_data->hw_type == QCOM_MVFLASH_3CH) { + shift = chan_id * 2; + ires_mask |= FLASH_IRES_MASK_3CH << shift; + ires_val |= ((mode == FLASH_MODE) ? + (FLASH_IRES_12P5MA_VAL << shift) : + (FLASH_IRES_5MA_VAL_3CH << shift)); + } else if (flash_data->hw_type == QCOM_MVFLASH_4CH) { + shift = chan_id; + ires_mask |= FLASH_IRES_MASK_4CH << shift; + ires_val |= ((mode == FLASH_MODE) ? + (FLASH_IRES_12P5MA_VAL << shift) : + (FLASH_IRES_5MA_VAL_4CH << shift)); + } else { + dev_err(led->flash.led_cdev.dev, + "HW type %d is not supported\n", flash_data->hw_type); + return -EOPNOTSUPP; + } + } + + return regmap_field_update_bits(flash_data->r_fields[REG_IRESOLUTION], ires_mask, ires_val); +} + +static int set_flash_timeout(struct qcom_flash_led *led, u32 timeout_ms) +{ + struct qcom_flash_data *flash_data = led->flash_data; + u8 timer, chan_id; + int rc, i; + + /* set SAFETY_TIMER for all the channels connected to the same LED */ + timeout_ms = min_t(u32, timeout_ms, led->max_timeout_ms); + + for (i = 0; i < led->chan_count; i++) { + chan_id = led->chan_id[i]; + + timer = timeout_ms / FLASH_TIMER_STEP_MS; + timer = clamp_t(u8, timer, 0, FLASH_TIMER_VAL_MASK); + + if (timeout_ms) + timer |= FLASH_TIMER_EN_BIT; + + rc = regmap_fields_write(flash_data->r_fields[REG_CHAN_TIMER], chan_id, timer); + if (rc) + return rc; + } + + return 0; +} + +static int set_flash_strobe(struct qcom_flash_led *led, enum led_strobe strobe, bool state) +{ + struct qcom_flash_data *flash_data = led->flash_data; + u8 strobe_sel, chan_en, chan_id, chan_mask = 0; + int rc, i; + + /* Set SW strobe config for all channels connected to the LED */ + for (i = 0; i < led->chan_count; i++) { + chan_id = led->chan_id[i]; + + if (strobe == SW_STROBE) + strobe_sel = FIELD_PREP(FLASH_STROBE_HW_SW_SEL_BIT, SW_STROBE_VAL); + else + strobe_sel = FIELD_PREP(FLASH_STROBE_HW_SW_SEL_BIT, HW_STROBE_VAL); + + strobe_sel |= + FIELD_PREP(FLASH_HW_STROBE_TRIGGER_SEL_BIT, STROBE_LEVEL_TRIGGER_VAL) | + FIELD_PREP(FLASH_STROBE_POLARITY_BIT, STROBE_ACTIVE_HIGH_VAL); + + rc = regmap_fields_write( + flash_data->r_fields[REG_CHAN_STROBE], chan_id, strobe_sel); + if (rc) + return rc; + + chan_mask |= BIT(chan_id); + } + + /* Enable/disable flash channels */ + chan_en = state ? chan_mask : 0; + rc = regmap_field_update_bits(flash_data->r_fields[REG_CHAN_EN], chan_mask, chan_en); + if (rc) + return rc; + + led->enabled = state; + return 0; +} + +static inline struct qcom_flash_led *flcdev_to_qcom_fled(struct led_classdev_flash *flcdev) +{ + return container_of(flcdev, struct qcom_flash_led, flash); +} + +static int qcom_flash_brightness_set(struct led_classdev_flash *fled_cdev, u32 brightness) +{ + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + + led->flash_current_ma = min_t(u32, led->max_flash_current_ma, brightness / UA_PER_MA); + return 0; +} + +static int qcom_flash_timeout_set(struct led_classdev_flash *fled_cdev, u32 timeout) +{ + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + + led->flash_timeout_ms = timeout / USEC_PER_MSEC; + return 0; +} + +static int qcom_flash_strobe_set(struct led_classdev_flash *fled_cdev, bool state) +{ + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + int rc; + + rc = set_flash_current(led, led->flash_current_ma, FLASH_MODE); + if (rc) + return rc; + + rc = set_flash_timeout(led, led->flash_timeout_ms); + if (rc) + return rc; + + rc = set_flash_module_en(led, state); + if (rc) + return rc; + + return set_flash_strobe(led, SW_STROBE, state); +} + +static int qcom_flash_strobe_get(struct led_classdev_flash *fled_cdev, bool *state) +{ + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + + *state = led->enabled; + return 0; +} + +static int qcom_flash_fault_get(struct led_classdev_flash *fled_cdev, u32 *fault) +{ + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + struct qcom_flash_data *flash_data = led->flash_data; + u8 shift, chan_id, chan_mask = 0; + u8 ot_mask = 0, oc_mask = 0, uv_mask = 0; + u32 val, fault_sts = 0; + int i, rc; + + rc = regmap_field_read(flash_data->r_fields[REG_STATUS1], &val); + if (rc) + return rc; + + for (i = 0; i < led->chan_count; i++) { + chan_id = led->chan_id[i]; + shift = chan_id * 2; + + if (val & BIT(shift)) + fault_sts |= LED_FAULT_SHORT_CIRCUIT; + + chan_mask |= BIT(chan_id); + } + + rc = regmap_field_read(flash_data->r_fields[REG_STATUS2], &val); + if (rc) + return rc; + + if (flash_data->hw_type == QCOM_MVFLASH_3CH) { + ot_mask = FLASH_STS_3CH_OTST1 | + FLASH_STS_3CH_OTST2 | + FLASH_STS_3CH_OTST3 | + FLASH_STS_3CH_BOB_THM_OVERLOAD; + oc_mask = FLASH_STS_3CH_BOB_ILIM_S1 | + FLASH_STS_3CH_BOB_ILIM_S2 | + FLASH_STS_3CH_BCL_IBAT; + uv_mask = FLASH_STS_3CH_VPH_DROOP; + } else if (flash_data->hw_type == QCOM_MVFLASH_4CH) { + ot_mask = FLASH_STS_4CH_OTST2 | + FLASH_STS_4CH_OTST1 | + FLASH_STS_4CHG_BOB_THM_OVERLOAD; + oc_mask = FLASH_STS_4CH_BCL_IBAT | + FLASH_STS_4CH_BOB_ILIM_S1 | + FLASH_STS_4CH_BOB_ILIM_S2; + uv_mask = FLASH_STS_4CH_VPH_LOW; + } + + if (val & ot_mask) + fault_sts |= LED_FAULT_OVER_TEMPERATURE; + + if (val & oc_mask) + fault_sts |= LED_FAULT_OVER_CURRENT; + + if (val & uv_mask) + fault_sts |= LED_FAULT_INPUT_VOLTAGE; + + rc = regmap_field_read(flash_data->r_fields[REG_STATUS3], &val); + if (rc) + return rc; + + if (flash_data->hw_type == QCOM_MVFLASH_3CH) { + if (val & chan_mask) + fault_sts |= LED_FAULT_TIMEOUT; + } else if (flash_data->hw_type == QCOM_MVFLASH_4CH) { + for (i = 0; i < led->chan_count; i++) { + chan_id = led->chan_id[i]; + shift = chan_id * 2; + + if (val & BIT(shift)) + fault_sts |= LED_FAULT_TIMEOUT; + } + } + + *fault = fault_sts; + return 0; +} + +static int qcom_flash_led_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct led_classdev_flash *fled_cdev = lcdev_to_flcdev(led_cdev); + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + u32 current_ma = brightness * led->max_torch_current_ma / LED_FULL; + bool enable = !!brightness; + int rc; + + rc = set_flash_current(led, current_ma, TORCH_MODE); + if (rc) + return rc; + + /* Disable flash timeout for torch LED */ + rc = set_flash_timeout(led, 0); + if (rc) + return rc; + + rc = set_flash_module_en(led, enable); + if (rc) + return rc; + + return set_flash_strobe(led, SW_STROBE, enable); +} + +static const struct led_flash_ops qcom_flash_ops = { + .flash_brightness_set = qcom_flash_brightness_set, + .strobe_set = qcom_flash_strobe_set, + .strobe_get = qcom_flash_strobe_get, + .timeout_set = qcom_flash_timeout_set, + .fault_get = qcom_flash_fault_get, +}; + +#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS) +static int qcom_flash_external_strobe_set(struct v4l2_flash *v4l2_flash, bool enable) +{ + struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev; + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + int rc; + + rc = set_flash_module_en(led, enable); + if (rc) + return rc; + + if (enable) + return set_flash_strobe(led, HW_STROBE, true); + else + return set_flash_strobe(led, SW_STROBE, false); +} + +static enum led_brightness +qcom_flash_intensity_to_led_brightness(struct v4l2_flash *v4l2_flash, s32 intensity) +{ + struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev; + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + u32 current_ma = intensity / UA_PER_MA; + + current_ma = min_t(u32, current_ma, led->max_torch_current_ma); + if (!current_ma) + return LED_OFF; + + return (current_ma * LED_FULL) / led->max_torch_current_ma; +} + +static s32 qcom_flash_brightness_to_led_intensity(struct v4l2_flash *v4l2_flash, + enum led_brightness brightness) +{ + struct led_classdev_flash *fled_cdev = v4l2_flash->fled_cdev; + struct qcom_flash_led *led = flcdev_to_qcom_fled(fled_cdev); + + return (brightness * led->max_torch_current_ma * UA_PER_MA) / LED_FULL; +} + +static const struct v4l2_flash_ops qcom_v4l2_flash_ops = { + .external_strobe_set = qcom_flash_external_strobe_set, + .intensity_to_led_brightness = qcom_flash_intensity_to_led_brightness, + .led_brightness_to_intensity = qcom_flash_brightness_to_led_intensity, +}; + +static int +qcom_flash_v4l2_init(struct device *dev, struct qcom_flash_led *led, struct fwnode_handle *fwnode) +{ + struct qcom_flash_data *flash_data = led->flash_data; + struct v4l2_flash_config v4l2_cfg = { 0 }; + struct led_flash_setting *intensity = &v4l2_cfg.intensity; + + if (!(led->flash.led_cdev.flags & LED_DEV_CAP_FLASH)) + return 0; + + intensity->min = intensity->step = TORCH_IRES_UA * led->chan_count; + intensity->max = led->max_torch_current_ma * UA_PER_MA; + intensity->val = min_t(u32, intensity->max, TORCH_CURRENT_DEFAULT_UA); + + strscpy(v4l2_cfg.dev_name, led->flash.led_cdev.dev->kobj.name, + sizeof(v4l2_cfg.dev_name)); + + v4l2_cfg.has_external_strobe = true; + v4l2_cfg.flash_faults = LED_FAULT_INPUT_VOLTAGE | + LED_FAULT_OVER_CURRENT | + LED_FAULT_SHORT_CIRCUIT | + LED_FAULT_OVER_TEMPERATURE | + LED_FAULT_TIMEOUT; + + flash_data->v4l2_flash[flash_data->leds_count] = + v4l2_flash_init(dev, fwnode, &led->flash, &qcom_v4l2_flash_ops, &v4l2_cfg); + return PTR_ERR_OR_ZERO(flash_data->v4l2_flash); +} +# else +static int +qcom_flash_v4l2_init(struct device *dev, struct qcom_flash_led *led, struct fwnode_handle *fwnode) +{ + return 0; +} +#endif + +static int qcom_flash_register_led_device(struct device *dev, + struct fwnode_handle *node, struct qcom_flash_led *led) +{ + struct qcom_flash_data *flash_data = led->flash_data; + struct led_init_data init_data; + struct led_classdev_flash *flash = &led->flash; + struct led_flash_setting *brightness, *timeout; + u32 count, current_ua, timeout_us; + u32 channels[4]; + int i, rc; + + count = fwnode_property_count_u32(node, "led-sources"); + if (count <= 0) { + dev_err(dev, "No led-sources specified\n"); + return -ENODEV; + } + + if (count > flash_data->max_channels) { + dev_err(dev, "led-sources count %u exceeds maximum channel count %u\n", + count, flash_data->max_channels); + return -EINVAL; + } + + rc = fwnode_property_read_u32_array(node, "led-sources", channels, count); + if (rc < 0) { + dev_err(dev, "Failed to read led-sources property, rc=%d\n", rc); + return rc; + } + + led->chan_count = count; + led->chan_id = devm_kcalloc(dev, count, sizeof(u8), GFP_KERNEL); + if (!led->chan_id) + return -ENOMEM; + + for (i = 0; i < count; i++) { + if ((channels[i] == 0) || (channels[i] > flash_data->max_channels)) { + dev_err(dev, "led-source out of HW support range [1-%u]\n", + flash_data->max_channels); + return -EINVAL; + } + + /* Make chan_id indexing from 0 */ + led->chan_id[i] = channels[i] - 1; + } + + rc = fwnode_property_read_u32(node, "led-max-microamp", ¤t_ua); + if (rc < 0) { + dev_err(dev, "Failed to read led-max-microamp property, rc=%d\n", rc); + return rc; + } + + if (current_ua == 0) { + dev_err(dev, "led-max-microamp shouldn't be 0\n"); + return -EINVAL; + } + + current_ua = min_t(u32, current_ua, TORCH_CURRENT_MAX_UA * led->chan_count); + led->max_torch_current_ma = current_ua / UA_PER_MA; + + if (fwnode_property_present(node, "flash-max-microamp")) { + flash->led_cdev.flags |= LED_DEV_CAP_FLASH; + + rc = fwnode_property_read_u32(node, "flash-max-microamp", ¤t_ua); + if (rc < 0) { + dev_err(dev, "Failed to read flash-max-microamp property, rc=%d\n", + rc); + return rc; + } + + current_ua = min_t(u32, current_ua, FLASH_CURRENT_MAX_UA * led->chan_count); + current_ua = min_t(u32, current_ua, FLASH_TOTAL_CURRENT_MAX_UA); + + /* Initialize flash class LED device brightness settings */ + brightness = &flash->brightness; + brightness->min = brightness->step = FLASH_IRES_UA * led->chan_count; + brightness->max = current_ua; + brightness->val = min_t(u32, current_ua, FLASH_CURRENT_DEFAULT_UA); + + led->max_flash_current_ma = current_ua / UA_PER_MA; + led->flash_current_ma = brightness->val / UA_PER_MA; + + rc = fwnode_property_read_u32(node, "flash-max-timeout-us", &timeout_us); + if (rc < 0) { + dev_err(dev, "Failed to read flash-max-timeout-us property, rc=%d\n", + rc); + return rc; + } + + timeout_us = min_t(u32, timeout_us, FLASH_TIMEOUT_MAX_US); + + /* Initialize flash class LED device timeout settings */ + timeout = &flash->timeout; + timeout->min = timeout->step = FLASH_TIMEOUT_STEP_US; + timeout->val = timeout->max = timeout_us; + + led->max_timeout_ms = led->flash_timeout_ms = timeout_us / USEC_PER_MSEC; + + flash->ops = &qcom_flash_ops; + } + + flash->led_cdev.brightness_set_blocking = qcom_flash_led_brightness_set; + + init_data.fwnode = node; + init_data.devicename = NULL; + init_data.default_label = NULL; + init_data.devname_mandatory = false; + + rc = devm_led_classdev_flash_register_ext(dev, flash, &init_data); + if (rc < 0) { + dev_err(dev, "Register flash LED classdev failed, rc=%d\n", rc); + return rc; + } + + return qcom_flash_v4l2_init(dev, led, node); +} + +static int qcom_flash_led_probe(struct platform_device *pdev) +{ + struct qcom_flash_data *flash_data; + struct qcom_flash_led *led; + struct fwnode_handle *child; + struct device *dev = &pdev->dev; + struct regmap *regmap; + struct reg_field *regs; + int count, i, rc; + u32 val, reg_base; + + flash_data = devm_kzalloc(dev, sizeof(*flash_data), GFP_KERNEL); + if (!flash_data) + return -ENOMEM; + + regmap = dev_get_regmap(dev->parent, NULL); + if (!regmap) { + dev_err(dev, "Failed to get parent regmap\n"); + return -EINVAL; + } + + rc = fwnode_property_read_u32(dev->fwnode, "reg", ®_base); + if (rc < 0) { + dev_err(dev, "Failed to get register base address, rc=%d\n", rc); + return rc; + } + + rc = regmap_read(regmap, reg_base + FLASH_TYPE_REG, &val); + if (rc < 0) { + dev_err(dev, "Read flash LED module type failed, rc=%d\n", rc); + return rc; + } + + if (val != FLASH_TYPE_VAL) { + dev_err(dev, "type %#x is not a flash LED module\n", val); + return -ENODEV; + } + + rc = regmap_read(regmap, reg_base + FLASH_SUBTYPE_REG, &val); + if (rc < 0) { + dev_err(dev, "Read flash LED module subtype failed, rc=%d\n", rc); + return rc; + } + + if (val == FLASH_SUBTYPE_3CH_VAL) { + flash_data->hw_type = QCOM_MVFLASH_3CH; + flash_data->max_channels = 3; + regs = mvflash_3ch_regs; + } else if (val == FLASH_SUBTYPE_4CH_VAL) { + flash_data->hw_type = QCOM_MVFLASH_4CH; + flash_data->max_channels = 4; + regs = mvflash_4ch_regs; + } else { + dev_err(dev, "flash LED subtype %#x is not yet supported\n", val); + return -ENODEV; + } + + for (i = 0; i < REG_MAX_COUNT; i++) + regs[i].reg += reg_base; + + rc = devm_regmap_field_bulk_alloc(dev, regmap, flash_data->r_fields, regs, REG_MAX_COUNT); + if (rc < 0) { + dev_err(dev, "Failed to allocate regmap field, rc=%d\n", rc); + return rc; + } + + platform_set_drvdata(pdev, flash_data); + mutex_init(&flash_data->lock); + + count = device_get_child_node_count(dev); + if (count == 0 || count > flash_data->max_channels) { + dev_err(dev, "No child or child count exceeds %d\n", flash_data->max_channels); + return -EINVAL; + } + + flash_data->v4l2_flash = devm_kcalloc(dev, count, + sizeof(*flash_data->v4l2_flash), GFP_KERNEL); + if (!flash_data->v4l2_flash) + return -ENOMEM; + + device_for_each_child_node(dev, child) { + led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL); + if (!led) { + rc = -ENOMEM; + goto release; + } + + led->flash_data = flash_data; + rc = qcom_flash_register_led_device(dev, child, led); + if (rc < 0) + goto release; + + flash_data->leds_count++; + } + + return 0; + +release: + while (flash_data->v4l2_flash[flash_data->leds_count] && flash_data->leds_count) + v4l2_flash_release(flash_data->v4l2_flash[flash_data->leds_count--]); + return rc; +} + +static int qcom_flash_led_remove(struct platform_device *pdev) +{ + struct qcom_flash_data *flash_data = platform_get_drvdata(pdev); + + while (flash_data->v4l2_flash[flash_data->leds_count] && flash_data->leds_count) + v4l2_flash_release(flash_data->v4l2_flash[flash_data->leds_count--]); + + mutex_destroy(&flash_data->lock); + return 0; +} + +static const struct of_device_id qcom_flash_led_match_table[] = { + { .compatible = "qcom,spmi-flash-led" }, + { } +}; + +MODULE_DEVICE_TABLE(of, qcom_flash_led_match_table); +static struct platform_driver qcom_flash_led_driver = { + .driver = { + .name = "leds-qcom-flash", + .of_match_table = qcom_flash_led_match_table, + }, + .probe = qcom_flash_led_probe, + .remove = qcom_flash_led_remove, +}; + +module_platform_driver(qcom_flash_led_driver); + +MODULE_DESCRIPTION("QCOM Flash LED driver"); +MODULE_LICENSE("GPL"); -- GitLab From 1aeff621689120db60cb7029e5a0fde7d01f7fb6 Mon Sep 17 00:00:00 2001 From: Fenglin Wu Date: Fri, 3 Mar 2023 17:50:23 +0800 Subject: [PATCH 0672/5631] dt-bindings: leds: Add QCOM flash LED controller Add binding document for flash LED module inside Qualcomm Technologies, Inc. PMICs. Signed-off-by: Fenglin Wu Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230303095023.538917-3-quic_fenglinw@quicinc.com --- .../bindings/leds/qcom,spmi-flash-led.yaml | 116 ++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml diff --git a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml new file mode 100644 index 000000000000..1b273aecaaec --- /dev/null +++ b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml @@ -0,0 +1,116 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/qcom,spmi-flash-led.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Flash LED device inside Qualcomm Technologies, Inc. PMICs + +maintainers: + - Fenglin Wu + +description: | + Flash LED controller is present inside some Qualcomm Technologies, Inc. PMICs. + The flash LED module can have different number of LED channels supported + e.g. 3 or 4. There are some different registers between them but they can + both support maximum current up to 1.5 A per channel and they can also support + ganging 2 channels together to supply maximum current up to 2 A. The current + will be split symmetrically on each channel and they will be enabled and + disabled at the same time. + +properties: + compatible: + items: + - enum: + - qcom,pm8150c-flash-led + - qcom,pm8150l-flash-led + - qcom,pm8350c-flash-led + - const: qcom,spmi-flash-led + + reg: + maxItems: 1 + +patternProperties: + "^led-[0-3]$": + type: object + $ref: common.yaml# + unevaluatedProperties: false + description: + Represents the physical LED components which are connected to the + flash LED channels' output. + + properties: + led-sources: + description: + The HW indices of the flash LED channels that connect to the + physical LED + allOf: + - minItems: 1 + maxItems: 2 + items: + enum: [1, 2, 3, 4] + + led-max-microamp: + anyOf: + - minimum: 5000 + maximum: 500000 + multipleOf: 5000 + - minimum: 10000 + maximum: 1000000 + multipleOf: 10000 + + flash-max-microamp: + anyOf: + - minimum: 12500 + maximum: 1500000 + multipleOf: 12500 + - minimum: 25000 + maximum: 2000000 + multipleOf: 25000 + + flash-max-timeout-us: + minimum: 10000 + maximum: 1280000 + multipleOf: 10000 + + required: + - led-sources + - led-max-microamp + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include + spmi { + #address-cells = <1>; + #size-cells = <0>; + led-controller@ee00 { + compatible = "qcom,pm8350c-flash-led", "qcom,spmi-flash-led"; + reg = <0xee00>; + + led-0 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <1>, <4>; + led-max-microamp = <300000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <0>; + }; + + led-1 { + function = LED_FUNCTION_FLASH; + color = ; + led-sources = <2>, <3>; + led-max-microamp = <300000>; + flash-max-microamp = <2000000>; + flash-max-timeout-us = <1280000>; + function-enumerator = <1>; + }; + }; + }; -- GitLab From b9da86e3aade0cd8c8b60a0f6356e7730fc90d5d Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 15 Mar 2023 16:20:54 -0700 Subject: [PATCH 0673/5631] x86/uaccess: Remove memcpy_page_flushcache() Commit 21b56c847753 ("iov_iter: get rid of separate bvec and xarray callbacks") removed the calls to memcpy_page_flushcache(). In addition, memcpy_page_flushcache() uses the deprecated kmap_atomic(). Remove the unused x86 memcpy_page_flushcache() implementation and also get rid of one more kmap_atomic() user. [ dhansen: tweak changelog ] Signed-off-by: Ira Weiny Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20221230-kmap-x86-v1-1-15f1ecccab50%40intel.com --- arch/x86/include/asm/uaccess_64.h | 2 -- arch/x86/lib/usercopy_64.c | 9 --------- 2 files changed, 11 deletions(-) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index d13d71af5cf6..c6b1dcded364 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -62,8 +62,6 @@ extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size); -extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, - size_t len); static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 6c1f8ac5e721..f515542f017f 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -136,13 +136,4 @@ void __memcpy_flushcache(void *_dst, const void *_src, size_t size) } } EXPORT_SYMBOL_GPL(__memcpy_flushcache); - -void memcpy_page_flushcache(char *to, struct page *page, size_t offset, - size_t len) -{ - char *from = kmap_atomic(page); - - memcpy_flushcache(to, from + offset, len); - kunmap_atomic(from); -} #endif -- GitLab From 820d7550a99cc09bb321fb2b890647e3669ce53f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 16 Mar 2023 14:55:46 +0100 Subject: [PATCH 0674/5631] dt-bindings: leds: Add "usbport" trigger MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Linux's "usbport" trigger is a bit specific one. It allows LED to follow state of multiple USB ports which have to be selected additionally (there isn't a single trigger for each port). Default list of USB ports to monitor can be specified using "trigger-sources" DT property. Theoretically it should be possible for Linux to deduce applicable trigger based on the references nodes in the "trigger-sources". It hasn't been implemented however (probably due to laziness). Milk spilled - we already have DT files specifying "usbport" manually - allow that value in the binding. This fixes validation of in-kernel and external DT files. Signed-off-by: Rafał Miłecki Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230316135546.9162-1-zajec5@gmail.com --- Documentation/devicetree/bindings/leds/common.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml index 61e63ed81ced..11aedf1650a1 100644 --- a/Documentation/devicetree/bindings/leds/common.yaml +++ b/Documentation/devicetree/bindings/leds/common.yaml @@ -125,6 +125,8 @@ properties: - usb-gadget # LED indicates USB host activity - usb-host + # LED indicates USB port state + - usbport # LED is triggered by CPU activity - pattern: "^cpu[0-9]*$" # LED is triggered by Bluetooth activity -- GitLab From 72cd8436ece036294322fecf91567fef3ce3e868 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:05 +0100 Subject: [PATCH 0675/5631] clk: renesas: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230312161512.2715500-24-u.kleine-koenig@pengutronix.de Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/rcar-usb2-clock-sel.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/renesas/rcar-usb2-clock-sel.c b/drivers/clk/renesas/rcar-usb2-clock-sel.c index 684d8937965e..17c110978e33 100644 --- a/drivers/clk/renesas/rcar-usb2-clock-sel.c +++ b/drivers/clk/renesas/rcar-usb2-clock-sel.c @@ -125,15 +125,13 @@ static int rcar_usb2_clock_sel_resume(struct device *dev) return 0; } -static int rcar_usb2_clock_sel_remove(struct platform_device *pdev) +static void rcar_usb2_clock_sel_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; of_clk_del_provider(dev->of_node); pm_runtime_put(dev); pm_runtime_disable(dev); - - return 0; } static int rcar_usb2_clock_sel_probe(struct platform_device *pdev) @@ -215,7 +213,7 @@ static struct platform_driver rcar_usb2_clock_sel_driver = { .pm = &rcar_usb2_clock_sel_pm_ops, }, .probe = rcar_usb2_clock_sel_probe, - .remove = rcar_usb2_clock_sel_remove, + .remove_new = rcar_usb2_clock_sel_remove, }; builtin_platform_driver(rcar_usb2_clock_sel_driver); -- GitLab From 9d7558ed8372c51cbed011cb1dc3eb1beee212cf Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 13 Mar 2023 11:49:04 +0100 Subject: [PATCH 0676/5631] pinctrl: renesas: Drop support for Renesas-specific properties The last user of the Renesas-specific properties was converted to the standard properties in commit af897250ea54c6f2 ("ARM: dts: gose: use generic pinctrl properties in SDHI nodes") in v4.10. Signed-off-by: Geert Uytterhoeven Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/ff9c14781110bbf19b56b45dd1f01e6da90319ad.1678704441.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pinctrl.c | 31 +++++-------------------------- 1 file changed, 5 insertions(+), 26 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl.c b/drivers/pinctrl/renesas/pinctrl.c index b74147800319..adaca1f7ccf8 100644 --- a/drivers/pinctrl/renesas/pinctrl.c +++ b/drivers/pinctrl/renesas/pinctrl.c @@ -40,10 +40,6 @@ struct sh_pfc_pinctrl { struct pinctrl_pin_desc *pins; struct sh_pfc_pin_config *configs; - - const char *func_prop_name; - const char *groups_prop_name; - const char *pins_prop_name; }; static int sh_pfc_get_groups_count(struct pinctrl_dev *pctldev) @@ -120,27 +116,10 @@ static int sh_pfc_dt_subnode_to_map(struct pinctrl_dev *pctldev, const char *pin; int ret; - /* Support both the old Renesas-specific properties and the new standard - * properties. Mixing old and new properties isn't allowed, neither - * inside a subnode nor across subnodes. - */ - if (!pmx->func_prop_name) { - if (of_find_property(np, "groups", NULL) || - of_find_property(np, "pins", NULL)) { - pmx->func_prop_name = "function"; - pmx->groups_prop_name = "groups"; - pmx->pins_prop_name = "pins"; - } else { - pmx->func_prop_name = "renesas,function"; - pmx->groups_prop_name = "renesas,groups"; - pmx->pins_prop_name = "renesas,pins"; - } - } - /* Parse the function and configuration properties. At least a function * or one configuration must be specified. */ - ret = of_property_read_string(np, pmx->func_prop_name, &function); + ret = of_property_read_string(np, "function", &function); if (ret < 0 && ret != -EINVAL) { dev_err(dev, "Invalid function in DT\n"); return ret; @@ -158,7 +137,7 @@ static int sh_pfc_dt_subnode_to_map(struct pinctrl_dev *pctldev, } /* Count the number of pins and groups and reallocate mappings. */ - ret = of_property_count_strings(np, pmx->pins_prop_name); + ret = of_property_count_strings(np, "pins"); if (ret == -EINVAL) { num_pins = 0; } else if (ret < 0) { @@ -168,7 +147,7 @@ static int sh_pfc_dt_subnode_to_map(struct pinctrl_dev *pctldev, num_pins = ret; } - ret = of_property_count_strings(np, pmx->groups_prop_name); + ret = of_property_count_strings(np, "groups"); if (ret == -EINVAL) { num_groups = 0; } else if (ret < 0) { @@ -199,7 +178,7 @@ static int sh_pfc_dt_subnode_to_map(struct pinctrl_dev *pctldev, *num_maps = nmaps; /* Iterate over pins and groups and create the mappings. */ - of_property_for_each_string(np, pmx->groups_prop_name, prop, group) { + of_property_for_each_string(np, "groups", prop, group) { if (function) { maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; maps[idx].data.mux.group = group; @@ -223,7 +202,7 @@ static int sh_pfc_dt_subnode_to_map(struct pinctrl_dev *pctldev, goto done; } - of_property_for_each_string(np, pmx->pins_prop_name, prop, pin) { + of_property_for_each_string(np, "pins", prop, pin) { ret = sh_pfc_map_add_config(&maps[idx], pin, PIN_MAP_TYPE_CONFIGS_PIN, configs, num_configs); -- GitLab From c857b87202bf5266b45c5b4dc0308aa603aeb262 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:35:55 +0100 Subject: [PATCH 0677/5631] backlight: lp855x: Mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/video/backlight/lp855x_bl.c:551:34: error: ‘lp855x_dt_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230311173556.263086-1-krzysztof.kozlowski@linaro.org --- drivers/video/backlight/lp855x_bl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c index 81012bf29baf..a57c9ef3b1cc 100644 --- a/drivers/video/backlight/lp855x_bl.c +++ b/drivers/video/backlight/lp855x_bl.c @@ -548,7 +548,7 @@ static void lp855x_remove(struct i2c_client *cl) sysfs_remove_group(&lp->dev->kobj, &lp855x_attr_group); } -static const struct of_device_id lp855x_dt_ids[] = { +static const struct of_device_id lp855x_dt_ids[] __maybe_unused = { { .compatible = "ti,lp8550", }, { .compatible = "ti,lp8551", }, { .compatible = "ti,lp8552", }, -- GitLab From a884cdf5dc27b489c3e9daf4c095b72e6cc38dae Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:35:56 +0100 Subject: [PATCH 0678/5631] backlight: arcxcnn_bl: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/video/backlight/arcxcnn_bl.c:378:34: error: ‘arcxcnn_dt_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230311173556.263086-2-krzysztof.kozlowski@linaro.org --- drivers/video/backlight/arcxcnn_bl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/arcxcnn_bl.c b/drivers/video/backlight/arcxcnn_bl.c index e610d7a1d13d..088bcca547dd 100644 --- a/drivers/video/backlight/arcxcnn_bl.c +++ b/drivers/video/backlight/arcxcnn_bl.c @@ -390,7 +390,7 @@ MODULE_DEVICE_TABLE(i2c, arcxcnn_ids); static struct i2c_driver arcxcnn_driver = { .driver = { .name = "arcxcnn_bl", - .of_match_table = of_match_ptr(arcxcnn_dt_ids), + .of_match_table = arcxcnn_dt_ids, }, .probe_new = arcxcnn_probe, .remove = arcxcnn_remove, -- GitLab From 796bf946c42644b047c5ad5575906ff9c397fbda Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:30 -0600 Subject: [PATCH 0679/5631] backlight: hx8357: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230310144730.1546101-1-robh@kernel.org --- drivers/video/backlight/hx8357.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/backlight/hx8357.c b/drivers/video/backlight/hx8357.c index 9b50bc96e00f..f76d2469d490 100644 --- a/drivers/video/backlight/hx8357.c +++ b/drivers/video/backlight/hx8357.c @@ -617,7 +617,7 @@ static int hx8357_probe(struct spi_device *spi) return -EINVAL; } - if (of_find_property(spi->dev.of_node, "im-gpios", NULL)) { + if (of_property_present(spi->dev.of_node, "im-gpios")) { lcd->use_im_pins = 1; for (i = 0; i < HX8357_NUM_IM_PINS; i++) { -- GitLab From fb200218b40b7864f64f1a47de61e035d8934e92 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:31 -0600 Subject: [PATCH 0680/5631] backlight: as3711: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Reviewed-by: Daniel Thompson Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230310144731.1546190-1-robh@kernel.org --- drivers/video/backlight/as3711_bl.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/video/backlight/as3711_bl.c b/drivers/video/backlight/as3711_bl.c index 3b60019cdc2b..28437c2da0f5 100644 --- a/drivers/video/backlight/as3711_bl.c +++ b/drivers/video/backlight/as3711_bl.c @@ -286,23 +286,23 @@ static int as3711_backlight_parse_dt(struct device *dev) if (ret < 0) goto err_put_bl; - if (of_find_property(bl, "su2-feedback-voltage", NULL)) { + if (of_property_read_bool(bl, "su2-feedback-voltage")) { pdata->su2_feedback = AS3711_SU2_VOLTAGE; count++; } - if (of_find_property(bl, "su2-feedback-curr1", NULL)) { + if (of_property_read_bool(bl, "su2-feedback-curr1")) { pdata->su2_feedback = AS3711_SU2_CURR1; count++; } - if (of_find_property(bl, "su2-feedback-curr2", NULL)) { + if (of_property_read_bool(bl, "su2-feedback-curr2")) { pdata->su2_feedback = AS3711_SU2_CURR2; count++; } - if (of_find_property(bl, "su2-feedback-curr3", NULL)) { + if (of_property_read_bool(bl, "su2-feedback-curr3")) { pdata->su2_feedback = AS3711_SU2_CURR3; count++; } - if (of_find_property(bl, "su2-feedback-curr-auto", NULL)) { + if (of_property_read_bool(bl, "su2-feedback-curr-auto")) { pdata->su2_feedback = AS3711_SU2_CURR_AUTO; count++; } @@ -312,19 +312,19 @@ static int as3711_backlight_parse_dt(struct device *dev) } count = 0; - if (of_find_property(bl, "su2-fbprot-lx-sd4", NULL)) { + if (of_property_read_bool(bl, "su2-fbprot-lx-sd4")) { pdata->su2_fbprot = AS3711_SU2_LX_SD4; count++; } - if (of_find_property(bl, "su2-fbprot-gpio2", NULL)) { + if (of_property_read_bool(bl, "su2-fbprot-gpio2")) { pdata->su2_fbprot = AS3711_SU2_GPIO2; count++; } - if (of_find_property(bl, "su2-fbprot-gpio3", NULL)) { + if (of_property_read_bool(bl, "su2-fbprot-gpio3")) { pdata->su2_fbprot = AS3711_SU2_GPIO3; count++; } - if (of_find_property(bl, "su2-fbprot-gpio4", NULL)) { + if (of_property_read_bool(bl, "su2-fbprot-gpio4")) { pdata->su2_fbprot = AS3711_SU2_GPIO4; count++; } @@ -334,15 +334,15 @@ static int as3711_backlight_parse_dt(struct device *dev) } count = 0; - if (of_find_property(bl, "su2-auto-curr1", NULL)) { + if (of_property_read_bool(bl, "su2-auto-curr1")) { pdata->su2_auto_curr1 = true; count++; } - if (of_find_property(bl, "su2-auto-curr2", NULL)) { + if (of_property_read_bool(bl, "su2-auto-curr2")) { pdata->su2_auto_curr2 = true; count++; } - if (of_find_property(bl, "su2-auto-curr3", NULL)) { + if (of_property_read_bool(bl, "su2-auto-curr3")) { pdata->su2_auto_curr3 = true; count++; } -- GitLab From 753b43c9d1b73337610861a6e644f8df3635d656 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:07 +0800 Subject: [PATCH 0681/5631] KVM: x86/mmu: Use 64-bit address to invalidate to fix a subtle bug FNAME(invlpg)() and kvm_mmu_invalidate_gva() take a gva_t, i.e. unsigned long, as the type of the address to invalidate. On 32-bit kernels, the upper 32 bits of the GPA will get dropped when an L2 GPA address is invalidated in the shadowed nested TDP MMU. Convert it to u64 to fix the problem. Reported-by: Sean Christopherson Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-2-jiangshanlai@gmail.com [sean: tweak changelog] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 6 +++--- arch/x86/kvm/mmu/mmu.c | 16 ++++++++-------- arch/x86/kvm/mmu/paging_tmpl.h | 7 ++++--- arch/x86/kvm/x86.c | 4 ++-- 4 files changed, 17 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a45de1118a42..214636554675 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -441,7 +441,7 @@ struct kvm_mmu { struct x86_exception *exception); int (*sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp); - void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa); + void (*invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa); struct kvm_mmu_root_info root; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; @@ -2044,8 +2044,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); -void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t gva, hpa_t root_hpa); +void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, hpa_t root_hpa); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 144c5a01cd77..edad1a4828dc 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5707,25 +5707,25 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); -void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t gva, hpa_t root_hpa) +void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, hpa_t root_hpa) { int i; /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(gva, vcpu)) + if (is_noncanonical_address(addr, vcpu)) return; - static_call(kvm_x86_flush_tlb_gva)(vcpu, gva); + static_call(kvm_x86_flush_tlb_gva)(vcpu, addr); } if (!mmu->invlpg) return; if (root_hpa == INVALID_PAGE) { - mmu->invlpg(vcpu, gva, mmu->root.hpa); + mmu->invlpg(vcpu, addr, mmu->root.hpa); /* * INVLPG is required to invalidate any global mappings for the VA, @@ -5740,15 +5740,15 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, */ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (VALID_PAGE(mmu->prev_roots[i].hpa)) - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); + mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); } else { - mmu->invlpg(vcpu, gva, root_hpa); + mmu->invlpg(vcpu, addr, root_hpa); } } void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index a056f2773dd9..0a9c11c24195 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -846,7 +846,8 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); } -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) +/* Note, @addr is a GPA when invlpg() invalidates an L2 GPA translation in shadowed TDP */ +static void FNAME(invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -854,7 +855,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) int level; u64 *sptep; - vcpu_clear_mmio_info(vcpu, gva); + vcpu_clear_mmio_info(vcpu, addr); /* * No need to check return value here, rmap_can_add() can @@ -868,7 +869,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) } write_lock(&vcpu->kvm->mmu_lock); - for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) { + for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { level = iterator.level; sptep = iterator.sptep; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..0b6b587d7914 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -802,8 +802,8 @@ void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, */ if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) - kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, - fault_mmu->root.hpa); + kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, + fault_mmu->root.hpa); fault_mmu->inject_page_fault(vcpu, fault); } -- GitLab From 90e444702a7c2e5d5806260735476d9bba0b598d Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:08 +0800 Subject: [PATCH 0682/5631] KVM: x86/mmu: Move the check in FNAME(sync_page) as kvm_sync_page_check() Prepare to check mmu->sync_page pointer before calling it. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-3-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 43 +++++++++++++++++++++++++++++++++- arch/x86/kvm/mmu/paging_tmpl.h | 27 --------------------- 2 files changed, 42 insertions(+), 28 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index edad1a4828dc..6749fa4794a4 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1914,10 +1914,51 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp) &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else +static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role; + + /* + * Ignore various flags when verifying that it's safe to sync a shadow + * page using the current MMU context. + * + * - level: not part of the overall MMU role and will never match as the MMU's + * level tracks the root level + * - access: updated based on the new guest PTE + * - quadrant: not part of the overall MMU role (similar to level) + */ + const union kvm_mmu_page_role sync_role_ign = { + .level = 0xf, + .access = 0x7, + .quadrant = 0x3, + .passthrough = 0x1, + }; + + /* + * Direct pages can never be unsync, and KVM should never attempt to + * sync a shadow page for a different MMU context, e.g. if the role + * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the + * reserved bits checks will be wrong, etc... + */ + if (WARN_ON_ONCE(sp->role.direct || + (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) + return false; + + return true; +} + +static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + if (!kvm_sync_page_check(vcpu, sp)) + return -1; + + return vcpu->arch.mmu->sync_page(vcpu, sp); +} + static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - int ret = vcpu->arch.mmu->sync_page(vcpu, sp); + int ret = __kvm_sync_page(vcpu, sp); if (ret < 0) kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0a9c11c24195..abb1d325ad30 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -943,38 +943,11 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role; int i; bool host_writable; gpa_t first_pte_gpa; bool flush = false; - /* - * Ignore various flags when verifying that it's safe to sync a shadow - * page using the current MMU context. - * - * - level: not part of the overall MMU role and will never match as the MMU's - * level tracks the root level - * - access: updated based on the new guest PTE - * - quadrant: not part of the overall MMU role (similar to level) - */ - const union kvm_mmu_page_role sync_role_ign = { - .level = 0xf, - .access = 0x7, - .quadrant = 0x3, - .passthrough = 0x1, - }; - - /* - * Direct pages can never be unsync, and KVM should never attempt to - * sync a shadow page for a different MMU context, e.g. if the role - * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the - * reserved bits checks will be wrong, etc... - */ - if (WARN_ON_ONCE(sp->role.direct || - (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) - return -1; - first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { -- GitLab From 51dddf6c49b9f60341a80c4947f3be67b3d50dc0 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:09 +0800 Subject: [PATCH 0683/5631] KVM: x86/mmu: Check mmu->sync_page pointer in kvm_sync_page_check() Assert that mmu->sync_page is non-NULL as part of the sanity checks performed before attempting to sync a shadow page. Explicitly checking mmu->sync_page is all but guaranteed to be redundant with the existing sanity check that the MMU is indirect, but the cost is negligible, and the explicit check also serves as documentation. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-4-jiangshanlai@gmail.com [sean: increase verbosity of changelog] Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6749fa4794a4..9d31724d26ad 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1940,7 +1940,7 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the * reserved bits checks will be wrong, etc... */ - if (WARN_ON_ONCE(sp->role.direct || + if (WARN_ON_ONCE(sp->role.direct || !vcpu->arch.mmu->sync_page || (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) return false; -- GitLab From 8ef228c20cae89c701c1ef7b8b8a84d6925b3575 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:10 +0800 Subject: [PATCH 0684/5631] KVM: x86/mmu: Set mmu->sync_page as NULL for direct paging mmu->sync_page for direct paging is never called. And both mmu->sync_page and mm->invlpg only make sense in shadow paging. Setting mmu->sync_page as NULL for direct paging makes it consistent with mm->invlpg which is set NULL for the case. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-5-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 9d31724d26ad..7fd824cf0a25 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1789,12 +1789,6 @@ static void mark_unsync(u64 *spte) kvm_mmu_mark_parents_unsync(sp); } -static int nonpaging_sync_page(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) -{ - return -1; -} - #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -4510,7 +4504,7 @@ static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; - context->sync_page = nonpaging_sync_page; + context->sync_page = NULL; context->invlpg = NULL; } @@ -5198,7 +5192,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->cpu_role.as_u64 = cpu_role.as_u64; context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; - context->sync_page = nonpaging_sync_page; + context->sync_page = NULL; context->invlpg = NULL; context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; -- GitLab From b19b74bc99b1501a550f4448d04d59b946dc617a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:25:56 +0300 Subject: [PATCH 0685/5631] x86/mm: Rework address range check in get_user() and put_user() The functions get_user() and put_user() check that the target address range resides in the user space portion of the virtual address space. In order to perform this check, the functions compare the end of the range against TASK_SIZE_MAX. For kernels compiled with CONFIG_X86_5LEVEL, this process requires some additional trickery using ALTERNATIVE, as TASK_SIZE_MAX depends on the paging mode in use. Linus suggested that this check could be simplified for 64-bit kernels. It is sufficient to check bit 63 of the address to ensure that the range belongs to user space. Additionally, the use of branches can be avoided by setting the target address to all ones if bit 63 is set. There's no need to check the end of the access range as there's huge gap between end of userspace range and start of the kernel range. The gap consists of canonical hole and unused ranges on both kernel and userspace sides. If an address with bit 63 set is passed down, it will trigger a #GP exception. _ASM_EXTABLE_UA() complains about this. Replace it with plain _ASM_EXTABLE() as it is expected behaviour now. The updated get_user() and put_user() checks are also compatible with Linear Address Masking, which allows user space to encode metadata in the upper bits of pointers and eliminates the need to untag the address before handling it. Suggested-by: Linus Torvalds Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-2-kirill.shutemov%40linux.intel.com --- arch/x86/lib/getuser.S | 83 ++++++++++++++++-------------------------- arch/x86/lib/putuser.S | 54 ++++++++++++--------------- 2 files changed, 55 insertions(+), 82 deletions(-) diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index b70d98d79a9d..b64a2bd1a1ef 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -37,22 +37,22 @@ #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC -#ifdef CONFIG_X86_5LEVEL -#define LOAD_TASK_SIZE_MINUS_N(n) \ - ALTERNATIVE __stringify(mov $((1 << 47) - 4096 - (n)),%rdx), \ - __stringify(mov $((1 << 56) - 4096 - (n)),%rdx), X86_FEATURE_LA57 -#else -#define LOAD_TASK_SIZE_MINUS_N(n) \ - mov $(TASK_SIZE_MAX - (n)),%_ASM_DX -#endif +.macro check_range size:req +.if IS_ENABLED(CONFIG_X86_64) + mov %rax, %rdx + sar $63, %rdx + or %rdx, %rax +.else + cmp $TASK_SIZE_MAX-\size+1, %eax + jae .Lbad_get_user + sbb %edx, %edx /* array_index_mask_nospec() */ + and %edx, %eax +.endif +.endm .text SYM_FUNC_START(__get_user_1) - LOAD_TASK_SIZE_MINUS_N(0) - cmp %_ASM_DX,%_ASM_AX - jae bad_get_user - sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ - and %_ASM_DX, %_ASM_AX + check_range size=1 ASM_STAC 1: movzbl (%_ASM_AX),%edx xor %eax,%eax @@ -62,11 +62,7 @@ SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1) SYM_FUNC_START(__get_user_2) - LOAD_TASK_SIZE_MINUS_N(1) - cmp %_ASM_DX,%_ASM_AX - jae bad_get_user - sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ - and %_ASM_DX, %_ASM_AX + check_range size=2 ASM_STAC 2: movzwl (%_ASM_AX),%edx xor %eax,%eax @@ -76,11 +72,7 @@ SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2) SYM_FUNC_START(__get_user_4) - LOAD_TASK_SIZE_MINUS_N(3) - cmp %_ASM_DX,%_ASM_AX - jae bad_get_user - sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ - and %_ASM_DX, %_ASM_AX + check_range size=4 ASM_STAC 3: movl (%_ASM_AX),%edx xor %eax,%eax @@ -90,30 +82,17 @@ SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4) SYM_FUNC_START(__get_user_8) -#ifdef CONFIG_X86_64 - LOAD_TASK_SIZE_MINUS_N(7) - cmp %_ASM_DX,%_ASM_AX - jae bad_get_user - sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ - and %_ASM_DX, %_ASM_AX + check_range size=8 ASM_STAC +#ifdef CONFIG_X86_64 4: movq (%_ASM_AX),%rdx - xor %eax,%eax - ASM_CLAC - RET #else - LOAD_TASK_SIZE_MINUS_N(7) - cmp %_ASM_DX,%_ASM_AX - jae bad_get_user_8 - sbb %_ASM_DX, %_ASM_DX /* array_index_mask_nospec() */ - and %_ASM_DX, %_ASM_AX - ASM_STAC 4: movl (%_ASM_AX),%edx 5: movl 4(%_ASM_AX),%ecx +#endif xor %eax,%eax ASM_CLAC RET -#endif SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) @@ -166,7 +145,7 @@ EXPORT_SYMBOL(__get_user_nocheck_8) SYM_CODE_START_LOCAL(.Lbad_get_user_clac) ASM_CLAC -bad_get_user: +.Lbad_get_user: xor %edx,%edx mov $(-EFAULT),%_ASM_AX RET @@ -184,23 +163,23 @@ SYM_CODE_END(.Lbad_get_user_8_clac) #endif /* get_user */ - _ASM_EXTABLE_UA(1b, .Lbad_get_user_clac) - _ASM_EXTABLE_UA(2b, .Lbad_get_user_clac) - _ASM_EXTABLE_UA(3b, .Lbad_get_user_clac) + _ASM_EXTABLE(1b, .Lbad_get_user_clac) + _ASM_EXTABLE(2b, .Lbad_get_user_clac) + _ASM_EXTABLE(3b, .Lbad_get_user_clac) #ifdef CONFIG_X86_64 - _ASM_EXTABLE_UA(4b, .Lbad_get_user_clac) + _ASM_EXTABLE(4b, .Lbad_get_user_clac) #else - _ASM_EXTABLE_UA(4b, .Lbad_get_user_8_clac) - _ASM_EXTABLE_UA(5b, .Lbad_get_user_8_clac) + _ASM_EXTABLE(4b, .Lbad_get_user_8_clac) + _ASM_EXTABLE(5b, .Lbad_get_user_8_clac) #endif /* __get_user */ - _ASM_EXTABLE_UA(6b, .Lbad_get_user_clac) - _ASM_EXTABLE_UA(7b, .Lbad_get_user_clac) - _ASM_EXTABLE_UA(8b, .Lbad_get_user_clac) + _ASM_EXTABLE(6b, .Lbad_get_user_clac) + _ASM_EXTABLE(7b, .Lbad_get_user_clac) + _ASM_EXTABLE(8b, .Lbad_get_user_clac) #ifdef CONFIG_X86_64 - _ASM_EXTABLE_UA(9b, .Lbad_get_user_clac) + _ASM_EXTABLE(9b, .Lbad_get_user_clac) #else - _ASM_EXTABLE_UA(9b, .Lbad_get_user_8_clac) - _ASM_EXTABLE_UA(10b, .Lbad_get_user_8_clac) + _ASM_EXTABLE(9b, .Lbad_get_user_8_clac) + _ASM_EXTABLE(10b, .Lbad_get_user_8_clac) #endif diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 32125224fcca..3062d09a776d 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -33,20 +33,20 @@ * as they get called from within inline assembly. */ -#ifdef CONFIG_X86_5LEVEL -#define LOAD_TASK_SIZE_MINUS_N(n) \ - ALTERNATIVE __stringify(mov $((1 << 47) - 4096 - (n)),%rbx), \ - __stringify(mov $((1 << 56) - 4096 - (n)),%rbx), X86_FEATURE_LA57 -#else -#define LOAD_TASK_SIZE_MINUS_N(n) \ - mov $(TASK_SIZE_MAX - (n)),%_ASM_BX -#endif +.macro check_range size:req +.if IS_ENABLED(CONFIG_X86_64) + mov %rcx, %rbx + sar $63, %rbx + or %rbx, %rcx +.else + cmp $TASK_SIZE_MAX-\size+1, %ecx + jae .Lbad_put_user +.endif +.endm .text SYM_FUNC_START(__put_user_1) - LOAD_TASK_SIZE_MINUS_N(0) - cmp %_ASM_BX,%_ASM_CX - jae .Lbad_put_user + check_range size=1 ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -66,9 +66,7 @@ SYM_FUNC_END(__put_user_nocheck_1) EXPORT_SYMBOL(__put_user_nocheck_1) SYM_FUNC_START(__put_user_2) - LOAD_TASK_SIZE_MINUS_N(1) - cmp %_ASM_BX,%_ASM_CX - jae .Lbad_put_user + check_range size=2 ASM_STAC 3: movw %ax,(%_ASM_CX) xor %ecx,%ecx @@ -88,9 +86,7 @@ SYM_FUNC_END(__put_user_nocheck_2) EXPORT_SYMBOL(__put_user_nocheck_2) SYM_FUNC_START(__put_user_4) - LOAD_TASK_SIZE_MINUS_N(3) - cmp %_ASM_BX,%_ASM_CX - jae .Lbad_put_user + check_range size=4 ASM_STAC 5: movl %eax,(%_ASM_CX) xor %ecx,%ecx @@ -110,9 +106,7 @@ SYM_FUNC_END(__put_user_nocheck_4) EXPORT_SYMBOL(__put_user_nocheck_4) SYM_FUNC_START(__put_user_8) - LOAD_TASK_SIZE_MINUS_N(7) - cmp %_ASM_BX,%_ASM_CX - jae .Lbad_put_user + check_range size=8 ASM_STAC 7: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 @@ -144,15 +138,15 @@ SYM_CODE_START_LOCAL(.Lbad_put_user_clac) RET SYM_CODE_END(.Lbad_put_user_clac) - _ASM_EXTABLE_UA(1b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(2b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(3b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(4b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(5b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(6b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(7b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(9b, .Lbad_put_user_clac) + _ASM_EXTABLE(1b, .Lbad_put_user_clac) + _ASM_EXTABLE(2b, .Lbad_put_user_clac) + _ASM_EXTABLE(3b, .Lbad_put_user_clac) + _ASM_EXTABLE(4b, .Lbad_put_user_clac) + _ASM_EXTABLE(5b, .Lbad_put_user_clac) + _ASM_EXTABLE(6b, .Lbad_put_user_clac) + _ASM_EXTABLE(7b, .Lbad_put_user_clac) + _ASM_EXTABLE(9b, .Lbad_put_user_clac) #ifdef CONFIG_X86_32 - _ASM_EXTABLE_UA(8b, .Lbad_put_user_clac) - _ASM_EXTABLE_UA(10b, .Lbad_put_user_clac) + _ASM_EXTABLE(8b, .Lbad_put_user_clac) + _ASM_EXTABLE(10b, .Lbad_put_user_clac) #endif -- GitLab From 5ef495e55f07aa117fdd8e187c9901cefc02fe0a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:25:57 +0300 Subject: [PATCH 0686/5631] x86: Allow atomic MM_CONTEXT flags setting So far there's no need in atomic setting of MM context flags in mm_context_t::flags. The flags set early in exec and never change after that. LAM enabling requires atomic flag setting. The upcoming flag MM_CONTEXT_FORCE_TAGGED_SVA can be set much later in the process lifetime where multiple threads exist. Convert the field to unsigned long and do MM_CONTEXT_* accesses with __set_bit() and test_bit(). No functional changes. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-3-kirill.shutemov%40linux.intel.com --- arch/x86/entry/vsyscall/vsyscall_64.c | 2 +- arch/x86/include/asm/mmu.h | 6 +++--- arch/x86/include/asm/mmu_context.h | 2 +- arch/x86/kernel/process_64.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index d234ca797e4a..e0ca8120aea8 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -317,7 +317,7 @@ static struct vm_area_struct gate_vma __ro_after_init = { struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_COMPAT - if (!mm || !(mm->context.flags & MM_CONTEXT_HAS_VSYSCALL)) + if (!mm || !test_bit(MM_CONTEXT_HAS_VSYSCALL, &mm->context.flags)) return NULL; #endif if (vsyscall_mode == NONE) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 5d7494631ea9..efa3eaee522c 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -9,9 +9,9 @@ #include /* Uprobes on this MM assume 32-bit code */ -#define MM_CONTEXT_UPROBE_IA32 BIT(0) +#define MM_CONTEXT_UPROBE_IA32 0 /* vsyscall page is accessible on this MM */ -#define MM_CONTEXT_HAS_VSYSCALL BIT(1) +#define MM_CONTEXT_HAS_VSYSCALL 1 /* * x86 has arch-specific MMU state beyond what lives in mm_struct. @@ -39,7 +39,7 @@ typedef struct { #endif #ifdef CONFIG_X86_64 - unsigned short flags; + unsigned long flags; #endif struct mutex lock; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index e01aa74a6de7..b4e4a0c04304 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -182,7 +182,7 @@ static inline void arch_exit_mmap(struct mm_struct *mm) static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || - !(mm->context.flags & MM_CONTEXT_UPROBE_IA32); + !test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags); } #else static inline bool is_64bit_mm(struct mm_struct *mm) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bb65a68b4b49..cd34bcf7f860 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -671,7 +671,7 @@ void set_personality_64bit(void) task_pt_regs(current)->orig_ax = __NR_execve; current_thread_info()->status &= ~TS_COMPAT; if (current->mm) - current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL; + __set_bit(MM_CONTEXT_HAS_VSYSCALL, ¤t->mm->context.flags); /* TBD: overwrites user setup. Should have two bits. But 64bit processes have always behaved this way, @@ -708,7 +708,7 @@ static void __set_personality_ia32(void) * uprobes applied to this MM need to know this and * cannot use user_64bit_mode() at that time. */ - current->mm->context.flags = MM_CONTEXT_UPROBE_IA32; + __set_bit(MM_CONTEXT_UPROBE_IA32, ¤t->mm->context.flags); } current->personality |= force_personality32; -- GitLab From 6449dcb0cac738219d13c618af7fd8664735f99d Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:25:58 +0300 Subject: [PATCH 0687/5631] x86: CPUID and CR3/CR4 flags for Linear Address Masking Enumerate Linear Address Masking and provide defines for CR3 and CR4 flags. The new CONFIG_ADDRESS_MASKING option enables the feature support in kernel. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Alexander Potapenko Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-4-kirill.shutemov%40linux.intel.com --- arch/x86/Kconfig | 11 +++++++++++ arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/processor-flags.h | 2 ++ arch/x86/include/uapi/asm/processor-flags.h | 6 ++++++ 4 files changed, 20 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a825bf031f49..aa9f73f5d670 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2290,6 +2290,17 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING If unsure, leave at the default value. +config ADDRESS_MASKING + bool "Linear Address Masking support" + depends on X86_64 + help + Linear Address Masking (LAM) modifies the checking that is applied + to 64-bit linear addresses, allowing software to use of the + untranslated address bits for metadata. + + The capability can be used for efficient address sanitizers (ASAN) + implementation and for optimizations in JITs. + config HOTPLUG_CPU def_bool y depends on SMP diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73c9672c123b..353b054812de 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -321,6 +321,7 @@ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index a7f3d9100adb..d8cccadc83a6 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -28,6 +28,8 @@ * On systems with SME, one bit (in a variable position!) is stolen to indicate * that the top-level paging structure is encrypted. * + * On systemms with LAM, bits 61 and 62 are used to indicate LAM mode. + * * All of the remaining bits indicate the physical address of the top-level * paging structure. * diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index c47cc7f2feeb..d898432947ff 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -82,6 +82,10 @@ #define X86_CR3_PCID_BITS 12 #define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL)) +#define X86_CR3_LAM_U57_BIT 61 /* Activate LAM for userspace, 62:57 bits masked */ +#define X86_CR3_LAM_U57 _BITULL(X86_CR3_LAM_U57_BIT) +#define X86_CR3_LAM_U48_BIT 62 /* Activate LAM for userspace, 62:48 bits masked */ +#define X86_CR3_LAM_U48 _BITULL(X86_CR3_LAM_U48_BIT) #define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ #define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) @@ -132,6 +136,8 @@ #define X86_CR4_PKE _BITUL(X86_CR4_PKE_BIT) #define X86_CR4_CET_BIT 23 /* enable Control-flow Enforcement Technology */ #define X86_CR4_CET _BITUL(X86_CR4_CET_BIT) +#define X86_CR4_LAM_SUP_BIT 28 /* LAM for supervisor pointers */ +#define X86_CR4_LAM_SUP _BITUL(X86_CR4_LAM_SUP_BIT) /* * x86-64 Task Priority Register, CR8 -- GitLab From 82721d8b25d76c5a6f4c6cf4ce4e5b33788820a1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:25:59 +0300 Subject: [PATCH 0688/5631] x86/mm: Handle LAM on context switch Linear Address Masking mode for userspace pointers encoded in CR3 bits. The mode is selected per-process and stored in mm_context_t. switch_mm_irqs_off() now respects selected LAM mode and constructs CR3 accordingly. The active LAM mode gets recorded in the tlb_state. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-5-kirill.shutemov%40linux.intel.com --- arch/x86/include/asm/mmu.h | 5 +++ arch/x86/include/asm/mmu_context.h | 24 ++++++++++++++ arch/x86/include/asm/tlbflush.h | 38 ++++++++++++++++++++- arch/x86/mm/tlb.c | 53 +++++++++++++++++++++--------- 4 files changed, 103 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index efa3eaee522c..22fc9fbf1d0a 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -42,6 +42,11 @@ typedef struct { unsigned long flags; #endif +#ifdef CONFIG_ADDRESS_MASKING + /* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */ + unsigned long lam_cr3_mask; +#endif + struct mutex lock; void __user *vdso; /* vdso base address */ const struct vdso_image *vdso_image; /* vdso image in use */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index b4e4a0c04304..0295c3863db7 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -92,6 +92,29 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) } #endif +#ifdef CONFIG_ADDRESS_MASKING +static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) +{ + return mm->context.lam_cr3_mask; +} + +static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) +{ + mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask; +} + +#else + +static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) +{ + return 0; +} + +static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) +{ +} +#endif + #define enter_lazy_tlb enter_lazy_tlb extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); @@ -169,6 +192,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); + dup_lam(oldmm, mm); return ldt_dup_context(oldmm, mm); } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index cda3118f3b27..e8b47f57bd4a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_TLBFLUSH_H #define _ASM_X86_TLBFLUSH_H -#include +#include #include #include @@ -12,6 +12,7 @@ #include #include #include +#include void __flush_tlb_all(void); @@ -101,6 +102,16 @@ struct tlb_state { */ bool invalidate_other; +#ifdef CONFIG_ADDRESS_MASKING + /* + * Active LAM mode. + * + * X86_CR3_LAM_U57/U48 shifted right by X86_CR3_LAM_U57_BIT or 0 if LAM + * disabled. + */ + u8 lam; +#endif + /* * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate * the corresponding user PCID needs a flush next time we @@ -357,6 +368,31 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) } #define huge_pmd_needs_flush huge_pmd_needs_flush +#ifdef CONFIG_ADDRESS_MASKING +static inline u64 tlbstate_lam_cr3_mask(void) +{ + u64 lam = this_cpu_read(cpu_tlbstate.lam); + + return lam << X86_CR3_LAM_U57_BIT; +} + +static inline void set_tlbstate_lam_mode(struct mm_struct *mm) +{ + this_cpu_write(cpu_tlbstate.lam, + mm->context.lam_cr3_mask >> X86_CR3_LAM_U57_BIT); +} + +#else + +static inline u64 tlbstate_lam_cr3_mask(void) +{ + return 0; +} + +static inline void set_tlbstate_lam_mode(struct mm_struct *mm) +{ +} +#endif #endif /* !MODULE */ static inline void __native_tlb_flush_global(unsigned long cr4) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 92d73ccede70..724f98d0e10f 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -154,26 +154,30 @@ static inline u16 user_pcid(u16 asid) return ret; } -static inline unsigned long build_cr3(pgd_t *pgd, u16 asid) +static inline unsigned long build_cr3(pgd_t *pgd, u16 asid, unsigned long lam) { + unsigned long cr3 = __sme_pa(pgd) | lam; + if (static_cpu_has(X86_FEATURE_PCID)) { - return __sme_pa(pgd) | kern_pcid(asid); + VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + cr3 |= kern_pcid(asid); } else { VM_WARN_ON_ONCE(asid != 0); - return __sme_pa(pgd); } + + return cr3; } -static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) +static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid, + unsigned long lam) { - VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); /* * Use boot_cpu_has() instead of this_cpu_has() as this function * might be called during early boot. This should work even after * boot because all CPU's the have same capabilities: */ VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID)); - return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH; + return build_cr3(pgd, asid, lam) | CR3_NOFLUSH; } /* @@ -274,15 +278,16 @@ static inline void invalidate_user_asid(u16 asid) (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask)); } -static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush) +static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam, + bool need_flush) { unsigned long new_mm_cr3; if (need_flush) { invalidate_user_asid(new_asid); - new_mm_cr3 = build_cr3(pgdir, new_asid); + new_mm_cr3 = build_cr3(pgdir, new_asid, lam); } else { - new_mm_cr3 = build_cr3_noflush(pgdir, new_asid); + new_mm_cr3 = build_cr3_noflush(pgdir, new_asid, lam); } /* @@ -491,6 +496,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, { struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + unsigned long new_lam = mm_lam_cr3_mask(next); bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); unsigned cpu = smp_processor_id(); u64 next_tlb_gen; @@ -520,7 +526,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid, + tlbstate_lam_cr3_mask()))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -552,9 +559,15 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * instruction. */ if (real_prev == next) { + /* Not actually switching mm's */ VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); + /* + * If this races with another thread that enables lam, 'new_lam' + * might not match tlbstate_lam_cr3_mask(). + */ + /* * Even in lazy TLB mode, the CPU should stay set in the * mm_cpumask. The TLB shootdown code can figure out from @@ -622,15 +635,16 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, barrier(); } + set_tlbstate_lam_mode(next); if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - load_new_mm_cr3(next->pgd, new_asid, true); + load_new_mm_cr3(next->pgd, new_asid, new_lam, true); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - load_new_mm_cr3(next->pgd, new_asid, false); + load_new_mm_cr3(next->pgd, new_asid, new_lam, false); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } @@ -691,6 +705,10 @@ void initialize_tlbstate_and_flush(void) /* Assert that CR3 already references the right mm. */ WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd)); + /* LAM expected to be disabled */ + WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57)); + WARN_ON(mm_lam_cr3_mask(mm)); + /* * Assert that CR4.PCIDE is set if needed. (CR4.PCIDE initialization * doesn't work like other CR4 bits because it can only be set from @@ -699,8 +717,8 @@ void initialize_tlbstate_and_flush(void) WARN_ON(boot_cpu_has(X86_FEATURE_PCID) && !(cr4_read_shadow() & X86_CR4_PCIDE)); - /* Force ASID 0 and force a TLB flush. */ - write_cr3(build_cr3(mm->pgd, 0)); + /* Disable LAM, force ASID 0 and force a TLB flush. */ + write_cr3(build_cr3(mm->pgd, 0, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT); @@ -708,6 +726,7 @@ void initialize_tlbstate_and_flush(void) this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen); + set_tlbstate_lam_mode(mm); for (i = 1; i < TLB_NR_DYN_ASIDS; i++) this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0); @@ -1071,8 +1090,10 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) */ unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd, - this_cpu_read(cpu_tlbstate.loaded_mm_asid)); + unsigned long cr3 = + build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd, + this_cpu_read(cpu_tlbstate.loaded_mm_asid), + tlbstate_lam_cr3_mask()); /* For now, be very restrictive about when this can be called. */ VM_WARN_ON(in_nmi() || preemptible()); -- GitLab From 428e106ae1ad4e45d3fd6978a753db475d0d0ec9 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:00 +0300 Subject: [PATCH 0689/5631] mm: Introduce untagged_addr_remote() untagged_addr() removes tags/metadata from the address and brings it to the canonical form. The helper is implemented on arm64 and sparc. Both of them do untagging based on global rules. However, Linear Address Masking (LAM) on x86 introduces per-process settings for untagging. As a result, untagged_addr() is now only suitable for untagging addresses for the current proccess. The new helper untagged_addr_remote() has to be used when the address targets remote process. It requires the mmap lock for target mm to be taken. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-6-kirill.shutemov%40linux.intel.com --- arch/sparc/include/asm/uaccess_64.h | 2 ++ drivers/vfio/vfio_iommu_type1.c | 2 +- fs/proc/task_mmu.c | 9 +++++++-- include/linux/mm.h | 11 ----------- include/linux/uaccess.h | 22 ++++++++++++++++++++++ mm/gup.c | 4 ++-- mm/madvise.c | 5 +++-- mm/migrate.c | 11 ++++++----- 8 files changed, 43 insertions(+), 23 deletions(-) diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index 94266a5c5b04..b825a5dd0210 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -8,8 +8,10 @@ #include #include +#include #include #include +#include #include #include diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 493c31de0edb..3d4dd9420c30 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -580,7 +580,7 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr, goto done; } - vaddr = untagged_addr(vaddr); + vaddr = untagged_addr_remote(mm, vaddr); retry: vma = vma_lookup(mm, vaddr); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6a96e1713fd5..29fd6b1f4058 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1689,8 +1689,13 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, /* watch out for wraparound */ start_vaddr = end_vaddr; - if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) - start_vaddr = untagged_addr(svpfn << PAGE_SHIFT); + if (svpfn <= (ULONG_MAX >> PAGE_SHIFT)) { + ret = mmap_read_lock_killable(mm); + if (ret) + goto out_free; + start_vaddr = untagged_addr_remote(mm, svpfn << PAGE_SHIFT); + mmap_read_unlock(mm); + } /* Ensure the address is inside the task */ if (start_vaddr > mm->task_size) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..289ae4caf878 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -96,17 +96,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #include #include -/* - * Architectures that support memory tagging (assigning tags to memory regions, - * embedding these tags into addresses that point to these memory regions, and - * checking that the memory and the pointer tags match on memory accesses) - * redefine this macro to strip tags from pointers. - * It's defined as noop for architectures that don't support memory tagging. - */ -#ifndef untagged_addr -#define untagged_addr(addr) (addr) -#endif - #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ab9728138ad6..3064314f4832 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -10,6 +10,28 @@ #include +/* + * Architectures that support memory tagging (assigning tags to memory regions, + * embedding these tags into addresses that point to these memory regions, and + * checking that the memory and the pointer tags match on memory accesses) + * redefine this macro to strip tags from pointers. + * + * Passing down mm_struct allows to define untagging rules on per-process + * basis. + * + * It's defined as noop for architectures that don't support memory tagging. + */ +#ifndef untagged_addr +#define untagged_addr(addr) (addr) +#endif + +#ifndef untagged_addr_remote +#define untagged_addr_remote(mm, addr) ({ \ + mmap_assert_locked(mm); \ + untagged_addr(addr); \ +}) +#endif + /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and diff --git a/mm/gup.c b/mm/gup.c index eab18ba045db..5ee8b682a0fe 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1085,7 +1085,7 @@ static long __get_user_pages(struct mm_struct *mm, if (!nr_pages) return 0; - start = untagged_addr(start); + start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); @@ -1259,7 +1259,7 @@ int fixup_user_fault(struct mm_struct *mm, struct vm_area_struct *vma; vm_fault_t ret; - address = untagged_addr(address); + address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; diff --git a/mm/madvise.c b/mm/madvise.c index 340125d08c03..d4b67f36f70f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -1402,8 +1402,6 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh size_t len; struct blk_plug plug; - start = untagged_addr(start); - if (!madvise_behavior_valid(behavior)) return -EINVAL; @@ -1435,6 +1433,9 @@ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int beh mmap_read_lock(mm); } + start = untagged_addr_remote(mm, start); + end = start + len; + blk_start_plug(&plug); error = madvise_walk_vmas(mm, start, end, behavior, madvise_vma_behavior); diff --git a/mm/migrate.c b/mm/migrate.c index 98f1c11197a8..8cd11bc9208f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2097,15 +2097,18 @@ static int do_move_pages_to_node(struct mm_struct *mm, * target node * 1 - when it has been queued */ -static int add_page_for_migration(struct mm_struct *mm, unsigned long addr, +static int add_page_for_migration(struct mm_struct *mm, const void __user *p, int node, struct list_head *pagelist, bool migrate_all) { struct vm_area_struct *vma; + unsigned long addr; struct page *page; int err; bool isolated; mmap_read_lock(mm); + addr = (unsigned long)untagged_addr_remote(mm, p); + err = -EFAULT; vma = vma_lookup(mm, addr); if (!vma || !vma_migratable(vma)) @@ -2211,7 +2214,6 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, for (i = start = 0; i < nr_pages; i++) { const void __user *p; - unsigned long addr; int node; err = -EFAULT; @@ -2219,7 +2221,6 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, goto out_flush; if (get_user(node, nodes + i)) goto out_flush; - addr = (unsigned long)untagged_addr(p); err = -ENODEV; if (node < 0 || node >= MAX_NUMNODES) @@ -2247,8 +2248,8 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, * Errors in the page lookup or isolation are not fatal and we simply * report them via status */ - err = add_page_for_migration(mm, addr, current_node, - &pagelist, flags & MPOL_MF_MOVE_ALL); + err = add_page_for_migration(mm, p, current_node, &pagelist, + flags & MPOL_MF_MOVE_ALL); if (err > 0) { /* The page is successfully queued for migration */ -- GitLab From 74c228d20a51ddb1354409fdbed7b72427339d7b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:01 +0300 Subject: [PATCH 0690/5631] x86/uaccess: Provide untagged_addr() and remove tags before address check untagged_addr() is a helper used by the core-mm to strip tag bits and get the address to the canonical shape based on rules of the current thread. It only handles userspace addresses. The untagging mask is stored in per-CPU variable and set on context switching to the task. The tags must not be included into check whether it's okay to access the userspace address. Strip tags in access_ok(). Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-7-kirill.shutemov%40linux.intel.com --- arch/x86/include/asm/mmu.h | 3 +++ arch/x86/include/asm/mmu_context.h | 11 +++++++++ arch/x86/include/asm/tlbflush.h | 10 ++++++++ arch/x86/include/asm/uaccess.h | 39 ++++++++++++++++++++++++++++-- arch/x86/kernel/process.c | 3 +++ arch/x86/mm/init.c | 5 ++++ 6 files changed, 69 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 22fc9fbf1d0a..9cac8c45a647 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -45,6 +45,9 @@ typedef struct { #ifdef CONFIG_ADDRESS_MASKING /* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */ unsigned long lam_cr3_mask; + + /* Significant bits of the virtual address. Excludes tag bits. */ + u64 untag_mask; #endif struct mutex lock; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 0295c3863db7..eb1387ac40fa 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -101,6 +101,12 @@ static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask; + mm->context.untag_mask = oldmm->context.untag_mask; +} + +static inline void mm_reset_untag_mask(struct mm_struct *mm) +{ + mm->context.untag_mask = -1UL; } #else @@ -113,6 +119,10 @@ static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) { } + +static inline void mm_reset_untag_mask(struct mm_struct *mm) +{ +} #endif #define enter_lazy_tlb enter_lazy_tlb @@ -139,6 +149,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.execute_only_pkey = -1; } #endif + mm_reset_untag_mask(mm); init_new_context_ldt(mm); return 0; } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index e8b47f57bd4a..75bfaa421030 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -54,6 +54,15 @@ static inline void cr4_clear_bits(unsigned long mask) local_irq_restore(flags); } +#ifdef CONFIG_ADDRESS_MASKING +DECLARE_PER_CPU(u64, tlbstate_untag_mask); + +static inline u64 current_untag_mask(void) +{ + return this_cpu_read(tlbstate_untag_mask); +} +#endif + #ifndef MODULE /* * 6 because 6 should be plenty and struct tlb_state will fit in two cache @@ -380,6 +389,7 @@ static inline void set_tlbstate_lam_mode(struct mm_struct *mm) { this_cpu_write(cpu_tlbstate.lam, mm->context.lam_cr3_mask >> X86_CR3_LAM_U57_BIT); + this_cpu_write(tlbstate_untag_mask, mm->context.untag_mask); } #else diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 1cc756eafa44..c79ebdbd6356 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -7,11 +7,13 @@ #include #include #include +#include #include #include #include #include #include +#include #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline bool pagefault_disabled(void); @@ -21,6 +23,39 @@ static inline bool pagefault_disabled(void); # define WARN_ON_IN_IRQ() #endif +#ifdef CONFIG_ADDRESS_MASKING +/* + * Mask out tag bits from the address. + * + * Magic with the 'sign' allows to untag userspace pointer without any branches + * while leaving kernel addresses intact. + */ +static inline unsigned long __untagged_addr(unsigned long addr, + unsigned long mask) +{ + long sign = addr >> 63; + + addr &= mask | sign; + return addr; +} + +#define untagged_addr(addr) ({ \ + u64 __addr = (__force u64)(addr); \ + __addr = __untagged_addr(__addr, current_untag_mask()); \ + (__force __typeof__(addr))__addr; \ +}) + +#define untagged_addr_remote(mm, addr) ({ \ + u64 __addr = (__force u64)(addr); \ + mmap_assert_locked(mm); \ + __addr = __untagged_addr(__addr, (mm)->context.untag_mask); \ + (__force __typeof__(addr))__addr; \ +}) + +#else +#define untagged_addr(addr) (addr) +#endif + /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check @@ -38,10 +73,10 @@ static inline bool pagefault_disabled(void); * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. */ -#define access_ok(addr, size) \ +#define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ - likely(__access_ok(addr, size)); \ + likely(__access_ok(untagged_addr(addr), size)); \ }) #include diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b650cde3f64d..bbc8c4c6e360 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "process.h" @@ -368,6 +369,8 @@ void arch_setup_new_exec(void) task_clear_spec_ssb_noexec(current); speculation_ctrl_update(read_thread_flags()); } + + mm_reset_untag_mask(current->mm); } #ifdef CONFIG_X86_IOPL_IOPERM diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index cb258f58fdc8..659b6c0f7910 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1048,6 +1048,11 @@ __visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; +#ifdef CONFIG_ADDRESS_MASKING +DEFINE_PER_CPU(u64, tlbstate_untag_mask); +EXPORT_PER_CPU_SYMBOL(tlbstate_untag_mask); +#endif + void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) { /* entry 0 MUST be WB (hardwired to speed up translations) */ -- GitLab From e0bddc19ba9578bc4e4c60a3f29ccc227277854c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:02 +0300 Subject: [PATCH 0691/5631] x86/mm: Reduce untagged_addr() overhead for systems without LAM Use alternatives to reduce untagged_addr() overhead. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20230312112612.31869-8-kirill.shutemov%40linux.intel.com --- arch/x86/include/asm/disabled-features.h | 8 ++++- arch/x86/include/asm/uaccess.h | 41 +++++++++++++++++------- 2 files changed, 37 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c79ebdbd6356..457e814712af 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -30,26 +31,44 @@ static inline bool pagefault_disabled(void); * Magic with the 'sign' allows to untag userspace pointer without any branches * while leaving kernel addresses intact. */ -static inline unsigned long __untagged_addr(unsigned long addr, - unsigned long mask) +static inline unsigned long __untagged_addr(unsigned long addr) { - long sign = addr >> 63; + long sign; + + /* + * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation + * in alternative instructions. The relocation gets wrong when gets + * copied to the target place. + */ + asm (ALTERNATIVE("", + "sar $63, %[sign]\n\t" /* user_ptr ? 0 : -1UL */ + "or %%gs:tlbstate_untag_mask, %[sign]\n\t" + "and %[sign], %[addr]\n\t", X86_FEATURE_LAM) + : [addr] "+r" (addr), [sign] "=r" (sign) + : "m" (tlbstate_untag_mask), "[sign]" (addr)); - addr &= mask | sign; return addr; } #define untagged_addr(addr) ({ \ - u64 __addr = (__force u64)(addr); \ - __addr = __untagged_addr(__addr, current_untag_mask()); \ - (__force __typeof__(addr))__addr; \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr(__addr); \ }) +static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, + unsigned long addr) +{ + long sign = addr >> 63; + + mmap_assert_locked(mm); + addr &= (mm)->context.untag_mask | sign; + + return addr; +} + #define untagged_addr_remote(mm, addr) ({ \ - u64 __addr = (__force u64)(addr); \ - mmap_assert_locked(mm); \ - __addr = __untagged_addr(__addr, (mm)->context.untag_mask); \ - (__force __typeof__(addr))__addr; \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ }) #else -- GitLab From 2f8794bd087e7958c8d1f0a0538856ca03e0bf3c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:03 +0300 Subject: [PATCH 0692/5631] x86/mm: Provide arch_prctl() interface for LAM Add a few of arch_prctl() handles: - ARCH_ENABLE_TAGGED_ADDR enabled LAM. The argument is required number of tag bits. It is rounded up to the nearest LAM mode that can provide it. For now only LAM_U57 is supported, with 6 tag bits. - ARCH_GET_UNTAG_MASK returns untag mask. It can indicates where tag bits located in the address. - ARCH_GET_MAX_TAG_BITS returns the maximum tag bits user can request. Zero if LAM is not supported. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-9-kirill.shutemov%40linux.intel.com --- arch/x86/include/asm/mmu.h | 2 ++ arch/x86/include/uapi/asm/prctl.h | 4 +++ arch/x86/kernel/process.c | 3 ++ arch/x86/kernel/process_64.c | 55 ++++++++++++++++++++++++++++++- 4 files changed, 63 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 9cac8c45a647..e80762e998ce 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -12,6 +12,8 @@ #define MM_CONTEXT_UPROBE_IA32 0 /* vsyscall page is accessible on this MM */ #define MM_CONTEXT_HAS_VSYSCALL 1 +/* Do not allow changing LAM mode */ +#define MM_CONTEXT_LOCK_LAM 2 /* * x86 has arch-specific MMU state beyond what lives in mm_struct. diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..a31e27b95b19 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -20,4 +20,8 @@ #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index bbc8c4c6e360..50d950771371 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -163,6 +163,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) savesegment(es, p->thread.es); savesegment(ds, p->thread.ds); + + if (p->mm && (clone_flags & (CLONE_VM | CLONE_VFORK)) == CLONE_VM) + set_bit(MM_CONTEXT_LOCK_LAM, &p->mm->context.flags); #else p->thread.sp0 = (unsigned long) (childregs + 1); savesegment(gs, p->thread.gs); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index cd34bcf7f860..186f34add865 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -743,6 +743,48 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr) } #endif +#ifdef CONFIG_ADDRESS_MASKING + +#define LAM_U57_BITS 6 + +static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) +{ + if (!cpu_feature_enabled(X86_FEATURE_LAM)) + return -ENODEV; + + /* PTRACE_ARCH_PRCTL */ + if (current->mm != mm) + return -EINVAL; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) { + mmap_write_unlock(mm); + return -EBUSY; + } + + if (!nr_bits) { + mmap_write_unlock(mm); + return -EINVAL; + } else if (nr_bits <= LAM_U57_BITS) { + mm->context.lam_cr3_mask = X86_CR3_LAM_U57; + mm->context.untag_mask = ~GENMASK(62, 57); + } else { + mmap_write_unlock(mm); + return -EINVAL; + } + + write_cr3(__read_cr3() | mm->context.lam_cr3_mask); + set_tlbstate_lam_mode(mm); + set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags); + + mmap_write_unlock(mm); + + return 0; +} +#endif + long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) { int ret = 0; @@ -830,7 +872,18 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) case ARCH_MAP_VDSO_64: return prctl_map_vdso(&vdso_image_64, arg2); #endif - +#ifdef CONFIG_ADDRESS_MASKING + case ARCH_GET_UNTAG_MASK: + return put_user(task->mm->context.untag_mask, + (unsigned long __user *)arg2); + case ARCH_ENABLE_TAGGED_ADDR: + return prctl_enable_tagged_addr(task->mm, arg2); + case ARCH_GET_MAX_TAG_BITS: + if (!cpu_feature_enabled(X86_FEATURE_LAM)) + return put_user(0, (unsigned long __user *)arg2); + else + return put_user(LAM_U57_BITS, (unsigned long __user *)arg2); +#endif default: ret = -EINVAL; break; -- GitLab From f7d304343b9d2456ffba23b99d2345408251ea45 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:04 +0300 Subject: [PATCH 0693/5631] mm: Expose untagging mask in /proc/$PID/status Add a line in /proc/$PID/status to report untag_mask. It can be used to find out LAM status of the process from the outside. It is useful for debuggers. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Catalin Marinas Acked-by: Peter Zijlstra (Intel) Tested-by: Alexander Potapenko Link: https://lore.kernel.org/all/20230312112612.31869-10-kirill.shutemov%40linux.intel.com --- arch/arm64/include/asm/mmu_context.h | 6 ++++++ arch/sparc/include/asm/mmu_context_64.h | 6 ++++++ arch/x86/include/asm/mmu_context.h | 6 ++++++ fs/proc/array.c | 7 +++++++ include/linux/mmu_context.h | 7 +++++++ 5 files changed, 32 insertions(+) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 72dbd6400549..56911691bef0 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -288,6 +288,12 @@ void post_ttbr_update_workaround(void); unsigned long arm64_mm_context_get(struct mm_struct *mm); void arm64_mm_context_put(struct mm_struct *mm); +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL >> 8; +} + #include #endif /* !__ASSEMBLY__ */ diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index 7a8380c63aab..799e797c5cdd 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -185,6 +185,12 @@ static inline void finish_arch_post_lock_switch(void) } } +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL >> adi_nbits(); +} + #include #endif /* !(__ASSEMBLY__) */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index eb1387ac40fa..06eaaf75d572 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -104,6 +104,12 @@ static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) mm->context.untag_mask = oldmm->context.untag_mask; } +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return mm->context.untag_mask; +} + static inline void mm_reset_untag_mask(struct mm_struct *mm) { mm->context.untag_mask = -1UL; diff --git a/fs/proc/array.c b/fs/proc/array.c index 9b0315d34c58..6daea628bc76 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include "internal.h" @@ -423,6 +424,11 @@ static inline void task_thp_status(struct seq_file *m, struct mm_struct *mm) seq_printf(m, "THP_enabled:\t%d\n", thp_enabled); } +static inline void task_untag_mask(struct seq_file *m, struct mm_struct *mm) +{ + seq_printf(m, "untag_mask:\t%#lx\n", mm_untag_mask(mm)); +} + int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -438,6 +444,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, task_mem(m, mm); task_core_dumping(m, task); task_thp_status(m, mm); + task_untag_mask(m, mm); mmput(mm); } task_sig(m, task); diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index b9b970f7ab45..14b9c1fa05c4 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -28,4 +28,11 @@ static inline void leave_mm(int cpu) { } # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif +#ifndef mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL; +} +#endif + #endif -- GitLab From 400b9b93441cd4e2fe824a70140f3d5a2a9c802b Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:05 +0300 Subject: [PATCH 0694/5631] iommu/sva: Replace pasid_valid() helper with mm_valid_pasid() Kernel has few users of pasid_valid() and all but one checks if the process has PASID allocated. The helper takes ioasid_t as the input. Replace the helper with mm_valid_pasid() that takes mm_struct as the argument. The only call that checks PASID that is not tied to mm_struct is open-codded now. This is preparatory patch. It helps avoid ifdeffery: no need to dereference mm->pasid in generic code to check if the process has PASID. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-11-kirill.shutemov%40linux.intel.com --- arch/x86/kernel/traps.c | 6 +++--- drivers/iommu/iommu-sva.c | 4 ++-- include/linux/ioasid.h | 9 --------- include/linux/sched/mm.h | 8 +++++++- 4 files changed, 12 insertions(+), 15 deletions(-) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d317dc3d06a3..8b83d8fbce71 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -671,15 +671,15 @@ static bool try_fixup_enqcmd_gp(void) if (!cpu_feature_enabled(X86_FEATURE_ENQCMD)) return false; - pasid = current->mm->pasid; - /* * If the mm has not been allocated a * PASID, the #GP can not be fixed up. */ - if (!pasid_valid(pasid)) + if (!mm_valid_pasid(current->mm)) return false; + pasid = current->mm->pasid; + /* * Did this thread already have its PASID activated? * If so, the #GP must be from something else. diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 24bf9b2b58aa..4ee2929f0d7a 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -34,14 +34,14 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) mutex_lock(&iommu_sva_lock); /* Is a PASID already associated with this mm? */ - if (pasid_valid(mm->pasid)) { + if (mm_valid_pasid(mm)) { if (mm->pasid < min || mm->pasid >= max) ret = -EOVERFLOW; goto out; } pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); - if (!pasid_valid(pasid)) + if (pasid == INVALID_IOASID) ret = -ENOMEM; else mm_pasid_set(mm, pasid); diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index af1c9d62e642..836ae09e92c2 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -40,10 +40,6 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -74,10 +70,5 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..b69fe7e8c0ac 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -457,6 +457,11 @@ static inline void mm_pasid_init(struct mm_struct *mm) mm->pasid = INVALID_IOASID; } +static inline bool mm_valid_pasid(struct mm_struct *mm) +{ + return mm->pasid != INVALID_IOASID; +} + /* Associate a PASID with an mm_struct: */ static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) { @@ -465,13 +470,14 @@ static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) static inline void mm_pasid_drop(struct mm_struct *mm) { - if (pasid_valid(mm->pasid)) { + if (mm_valid_pasid(mm)) { ioasid_free(mm->pasid); mm->pasid = INVALID_IOASID; } } #else static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif -- GitLab From 23e5d9ec2bab53c4e5fbac675304e699726c1ac5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:06 +0300 Subject: [PATCH 0695/5631] x86/mm/iommu/sva: Make LAM and SVA mutually exclusive IOMMU and SVA-capable devices know nothing about LAM and only expect canonical addresses. An attempt to pass down tagged pointer will lead to address translation failure. By default do not allow to enable both LAM and use SVA in the same process. The new ARCH_FORCE_TAGGED_SVA arch_prctl() overrides the limitation. By using the arch_prctl() userspace takes responsibility to never pass tagged address to the device. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Ashok Raj Reviewed-by: Jacob Pan Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-12-kirill.shutemov%40linux.intel.com --- arch/x86/include/asm/mmu.h | 2 ++ arch/x86/include/asm/mmu_context.h | 6 ++++++ arch/x86/include/uapi/asm/prctl.h | 1 + arch/x86/kernel/process_64.c | 7 +++++++ drivers/iommu/iommu-sva.c | 4 ++++ include/linux/mmu_context.h | 7 +++++++ 6 files changed, 27 insertions(+) diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index e80762e998ce..0da5c227f490 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -14,6 +14,8 @@ #define MM_CONTEXT_HAS_VSYSCALL 1 /* Do not allow changing LAM mode */ #define MM_CONTEXT_LOCK_LAM 2 +/* Allow LAM and SVA coexisting */ +#define MM_CONTEXT_FORCE_TAGGED_SVA 3 /* * x86 has arch-specific MMU state beyond what lives in mm_struct. diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 06eaaf75d572..4c396e9a384f 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -115,6 +115,12 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm) mm->context.untag_mask = -1UL; } +#define arch_pgtable_dma_compat arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return !mm_lam_cr3_mask(mm) || + test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags); +} #else static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index a31e27b95b19..eb290d89cb32 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -23,5 +23,6 @@ #define ARCH_GET_UNTAG_MASK 0x4001 #define ARCH_ENABLE_TAGGED_ADDR 0x4002 #define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 #endif /* _ASM_X86_PRCTL_H */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 186f34add865..b46924c9e46d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -756,6 +756,10 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) if (current->mm != mm) return -EINVAL; + if (mm_valid_pasid(mm) && + !test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags)) + return -EINTR; + if (mmap_write_lock_killable(mm)) return -EINTR; @@ -878,6 +882,9 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) (unsigned long __user *)arg2); case ARCH_ENABLE_TAGGED_ADDR: return prctl_enable_tagged_addr(task->mm, arg2); + case ARCH_FORCE_TAGGED_SVA: + set_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &task->mm->context.flags); + return 0; case ARCH_GET_MAX_TAG_BITS: if (!cpu_feature_enabled(X86_FEATURE_LAM)) return put_user(0, (unsigned long __user *)arg2); diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 4ee2929f0d7a..dd76a1a09cf7 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -2,6 +2,7 @@ /* * Helpers for IOMMU drivers implementing SVA */ +#include #include #include #include @@ -32,6 +33,9 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) min == 0 || max < min) return -EINVAL; + if (!arch_pgtable_dma_compat(mm)) + return -EBUSY; + mutex_lock(&iommu_sva_lock); /* Is a PASID already associated with this mm? */ if (mm_valid_pasid(mm)) { diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index 14b9c1fa05c4..f2b7a3f04099 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -35,4 +35,11 @@ static inline unsigned long mm_untag_mask(struct mm_struct *mm) } #endif +#ifndef arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return true; +} +#endif + #endif -- GitLab From 3de9745c12d6adf4ed5884b6a33a141f580ef434 Mon Sep 17 00:00:00 2001 From: Weihong Zhang Date: Sun, 12 Mar 2023 14:26:07 +0300 Subject: [PATCH 0696/5631] selftests/x86/lam: Add malloc and tag-bits test cases for linear-address masking LAM is supported only in 64-bit mode and applies only addresses used for data accesses. In 64-bit mode, linear address have 64 bits. LAM is applied to 64-bit linear address and allow software to use high bits for metadata. LAM supports configurations that differ regarding which pointer bits are masked and can be used for metadata. LAM includes following mode: - LAM_U57, pointer bits in positions 62:57 are masked (LAM width 6), allows bits 62:57 of a user pointer to be used as metadata. There are some arch_prctls: ARCH_ENABLE_TAGGED_ADDR: enable LAM mode, mask high bits of a user pointer. ARCH_GET_UNTAG_MASK: get current untagged mask. ARCH_GET_MAX_TAG_BITS: the maximum tag bits user can request. zero if LAM is not supported. The LAM mode is for pre-process, a process has only one chance to set LAM mode. But there is no API to disable LAM mode. So all of test cases are run under child process. Functions of this test: MALLOC - LAM_U57 masks bits 57:62 of a user pointer. Process on user space can dereference such pointers. - Disable LAM, dereference a pointer with metadata above 48 bit or 57 bit lead to trigger SIGSEGV. TAG_BITS - Max tag bits of LAM_U57 is 6. Signed-off-by: Weihong Zhang Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-13-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/lam.c | 326 +++++++++++++++++++++++++++ 2 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/lam.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index ca9374b56ead..598135d3162b 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -18,7 +18,7 @@ TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip syscall_numbering \ - corrupt_xstate_header amx + corrupt_xstate_header amx lam # Some selftests require 32bit support enabled also on 64bit systems TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c new file mode 100644 index 000000000000..268c1d2749af --- /dev/null +++ b/tools/testing/selftests/x86/lam.c @@ -0,0 +1,326 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +#ifndef __x86_64__ +# error This test is 64-bit only +#endif + +/* LAM modes, these definitions were copied from kernel code */ +#define LAM_NONE 0 +#define LAM_U57_BITS 6 + +#define LAM_U57_MASK (0x3fULL << 57) +/* arch prctl for LAM */ +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 + +/* Specified test function bits */ +#define FUNC_MALLOC 0x1 +#define FUNC_BITS 0x2 + +#define TEST_MASK 0x3 + +#define MALLOC_LEN 32 + +struct testcases { + unsigned int later; + int expected; /* 2: SIGSEGV Error; 1: other errors */ + unsigned long lam; + uint64_t addr; + int (*test_func)(struct testcases *test); + const char *msg; +}; + +int tests_cnt; +jmp_buf segv_env; + +static void segv_handler(int sig) +{ + ksft_print_msg("Get segmentation fault(%d).", sig); + siglongjmp(segv_env, 1); +} + +static inline int cpu_has_lam(void) +{ + unsigned int cpuinfo[4]; + + __cpuid_count(0x7, 1, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]); + + return (cpuinfo[0] & (1 << 26)); +} + +/* + * Set tagged address and read back untag mask. + * check if the untagged mask is expected. + * + * @return: + * 0: Set LAM mode successfully + * others: failed to set LAM + */ +static int set_lam(unsigned long lam) +{ + int ret = 0; + uint64_t ptr = 0; + + if (lam != LAM_U57_BITS && lam != LAM_NONE) + return -1; + + /* Skip check return */ + syscall(SYS_arch_prctl, ARCH_ENABLE_TAGGED_ADDR, lam); + + /* Get untagged mask */ + syscall(SYS_arch_prctl, ARCH_GET_UNTAG_MASK, &ptr); + + /* Check mask returned is expected */ + if (lam == LAM_U57_BITS) + ret = (ptr != ~(LAM_U57_MASK)); + else if (lam == LAM_NONE) + ret = (ptr != -1ULL); + + return ret; +} + +static unsigned long get_default_tag_bits(void) +{ + pid_t pid; + int lam = LAM_NONE; + int ret = 0; + + pid = fork(); + if (pid < 0) { + perror("Fork failed."); + } else if (pid == 0) { + /* Set LAM mode in child process */ + if (set_lam(LAM_U57_BITS) == 0) + lam = LAM_U57_BITS; + else + lam = LAM_NONE; + exit(lam); + } else { + wait(&ret); + lam = WEXITSTATUS(ret); + } + + return lam; +} + +/* According to LAM mode, set metadata in high bits */ +static uint64_t set_metadata(uint64_t src, unsigned long lam) +{ + uint64_t metadata; + + srand(time(NULL)); + + switch (lam) { + case LAM_U57_BITS: /* Set metadata in bits 62:57 */ + /* Get a random non-zero value as metadata */ + metadata = (rand() % ((1UL << LAM_U57_BITS) - 1) + 1) << 57; + metadata |= (src & ~(LAM_U57_MASK)); + break; + default: + metadata = src; + break; + } + + return metadata; +} + +/* + * Set metadata in user pointer, compare new pointer with original pointer. + * both pointers should point to the same address. + * + * @return: + * 0: value on the pointer with metadate and value on original are same + * 1: not same. + */ +static int handle_lam_test(void *src, unsigned int lam) +{ + char *ptr; + + strcpy((char *)src, "USER POINTER"); + + ptr = (char *)set_metadata((uint64_t)src, lam); + if (src == ptr) + return 0; + + /* Copy a string into the pointer with metadata */ + strcpy((char *)ptr, "METADATA POINTER"); + + return (!!strcmp((char *)src, (char *)ptr)); +} + + +int handle_max_bits(struct testcases *test) +{ + unsigned long exp_bits = get_default_tag_bits(); + unsigned long bits = 0; + + if (exp_bits != LAM_NONE) + exp_bits = LAM_U57_BITS; + + /* Get LAM max tag bits */ + if (syscall(SYS_arch_prctl, ARCH_GET_MAX_TAG_BITS, &bits) == -1) + return 1; + + return (exp_bits != bits); +} + +/* + * Test lam feature through dereference pointer get from malloc. + * @return 0: Pass test. 1: Get failure during test 2: Get SIGSEGV + */ +static int handle_malloc(struct testcases *test) +{ + char *ptr = NULL; + int ret = 0; + + if (test->later == 0 && test->lam != 0) + if (set_lam(test->lam) == -1) + return 1; + + ptr = (char *)malloc(MALLOC_LEN); + if (ptr == NULL) { + perror("malloc() failure\n"); + return 1; + } + + /* Set signal handler */ + if (sigsetjmp(segv_env, 1) == 0) { + signal(SIGSEGV, segv_handler); + ret = handle_lam_test(ptr, test->lam); + } else { + ret = 2; + } + + if (test->later != 0 && test->lam != 0) + if (set_lam(test->lam) == -1 && ret == 0) + ret = 1; + + free(ptr); + + return ret; +} + +static int fork_test(struct testcases *test) +{ + int ret, child_ret; + pid_t pid; + + pid = fork(); + if (pid < 0) { + perror("Fork failed."); + ret = 1; + } else if (pid == 0) { + ret = test->test_func(test); + exit(ret); + } else { + wait(&child_ret); + ret = WEXITSTATUS(child_ret); + } + + return ret; +} + +static void run_test(struct testcases *test, int count) +{ + int i, ret = 0; + + for (i = 0; i < count; i++) { + struct testcases *t = test + i; + + /* fork a process to run test case */ + ret = fork_test(t); + if (ret != 0) + ret = (t->expected == ret); + else + ret = !(t->expected); + + tests_cnt++; + ksft_test_result(ret, t->msg); + } +} + +static struct testcases malloc_cases[] = { + { + .later = 0, + .lam = LAM_U57_BITS, + .test_func = handle_malloc, + .msg = "MALLOC: LAM_U57. Dereferencing pointer with metadata\n", + }, + { + .later = 1, + .expected = 2, + .lam = LAM_U57_BITS, + .test_func = handle_malloc, + .msg = "MALLOC:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", + }, +}; + + +static struct testcases bits_cases[] = { + { + .test_func = handle_max_bits, + .msg = "BITS: Check default tag bits\n", + }, +}; + +static void cmd_help(void) +{ + printf("usage: lam [-h] [-t test list]\n"); + printf("\t-t test list: run tests specified in the test list, default:0x%x\n", TEST_MASK); + printf("\t\t0x1:malloc; 0x2:max_bits;\n"); + printf("\t-h: help\n"); +} + +int main(int argc, char **argv) +{ + int c = 0; + unsigned int tests = TEST_MASK; + + tests_cnt = 0; + + if (!cpu_has_lam()) { + ksft_print_msg("Unsupported LAM feature!\n"); + return -1; + } + + while ((c = getopt(argc, argv, "ht:")) != -1) { + switch (c) { + case 't': + tests = strtoul(optarg, NULL, 16); + if (!(tests & TEST_MASK)) { + ksft_print_msg("Invalid argument!\n"); + return -1; + } + break; + case 'h': + cmd_help(); + return 0; + default: + ksft_print_msg("Invalid argument\n"); + return -1; + } + } + + if (tests & FUNC_MALLOC) + run_test(malloc_cases, ARRAY_SIZE(malloc_cases)); + + if (tests & FUNC_BITS) + run_test(bits_cases, ARRAY_SIZE(bits_cases)); + + ksft_set_plan(tests_cnt); + + return ksft_exit_pass(); +} -- GitLab From e67876962ecfc5c8cb1d871d8f66ad3b21dbf065 Mon Sep 17 00:00:00 2001 From: Weihong Zhang Date: Sun, 12 Mar 2023 14:26:08 +0300 Subject: [PATCH 0697/5631] selftests/x86/lam: Add mmap and SYSCALL test cases for linear-address masking Add mmap and SYSCALL test cases. SYSCALL test cases: - LAM supports set metadata in high bits 62:57 (LAM_U57) of a user pointer, pass the pointer to SYSCALL, SYSCALL can dereference the pointer and return correct result. - Disable LAM, pass a pointer with metadata in high bits to SYSCALL, SYSCALL returns -1 (EFAULT). MMAP test cases: - Enable LAM_U57, MMAP with low address (below bits 47), set metadata in high bits of the address, dereference the address should be allowed. - Enable LAM_U57, MMAP with high address (above bits 47), set metadata in high bits of the address, dereference the address should be allowed. Signed-off-by: Weihong Zhang Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-14-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/lam.c | 144 +++++++++++++++++++++++++++++- 1 file changed, 140 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 268c1d2749af..39ebfc511685 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -29,11 +30,18 @@ /* Specified test function bits */ #define FUNC_MALLOC 0x1 #define FUNC_BITS 0x2 +#define FUNC_MMAP 0x4 +#define FUNC_SYSCALL 0x8 -#define TEST_MASK 0x3 +#define TEST_MASK 0xf + +#define LOW_ADDR (0x1UL << 30) +#define HIGH_ADDR (0x3UL << 48) #define MALLOC_LEN 32 +#define PAGE_SIZE (4 << 10) + struct testcases { unsigned int later; int expected; /* 2: SIGSEGV Error; 1: other errors */ @@ -49,6 +57,7 @@ jmp_buf segv_env; static void segv_handler(int sig) { ksft_print_msg("Get segmentation fault(%d).", sig); + siglongjmp(segv_env, 1); } @@ -61,6 +70,16 @@ static inline int cpu_has_lam(void) return (cpuinfo[0] & (1 << 26)); } +/* Check 5-level page table feature in CPUID.(EAX=07H, ECX=00H):ECX.[bit 16] */ +static inline int cpu_has_la57(void) +{ + unsigned int cpuinfo[4]; + + __cpuid_count(0x7, 0, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]); + + return (cpuinfo[2] & (1 << 16)); +} + /* * Set tagged address and read back untag mask. * check if the untagged mask is expected. @@ -213,6 +232,68 @@ static int handle_malloc(struct testcases *test) return ret; } +static int handle_mmap(struct testcases *test) +{ + void *ptr; + unsigned int flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED; + int ret = 0; + + if (test->later == 0 && test->lam != 0) + if (set_lam(test->lam) != 0) + return 1; + + ptr = mmap((void *)test->addr, PAGE_SIZE, PROT_READ | PROT_WRITE, + flags, -1, 0); + if (ptr == MAP_FAILED) { + if (test->addr == HIGH_ADDR) + if (!cpu_has_la57()) + return 3; /* unsupport LA57 */ + return 1; + } + + if (test->later != 0 && test->lam != 0) + if (set_lam(test->lam) != 0) + ret = 1; + + if (ret == 0) { + if (sigsetjmp(segv_env, 1) == 0) { + signal(SIGSEGV, segv_handler); + ret = handle_lam_test(ptr, test->lam); + } else { + ret = 2; + } + } + + munmap(ptr, PAGE_SIZE); + return ret; +} + +static int handle_syscall(struct testcases *test) +{ + struct utsname unme, *pu; + int ret = 0; + + if (test->later == 0 && test->lam != 0) + if (set_lam(test->lam) != 0) + return 1; + + if (sigsetjmp(segv_env, 1) == 0) { + signal(SIGSEGV, segv_handler); + pu = (struct utsname *)set_metadata((uint64_t)&unme, test->lam); + ret = uname(pu); + if (ret < 0) + ret = 1; + } else { + ret = 2; + } + + if (test->later != 0 && test->lam != 0) + if (set_lam(test->lam) != -1 && ret == 0) + ret = 1; + + return ret; +} + static int fork_test(struct testcases *test) { int ret, child_ret; @@ -241,13 +322,20 @@ static void run_test(struct testcases *test, int count) struct testcases *t = test + i; /* fork a process to run test case */ + tests_cnt++; ret = fork_test(t); + + /* return 3 is not support LA57, the case should be skipped */ + if (ret == 3) { + ksft_test_result_skip(t->msg); + continue; + } + if (ret != 0) ret = (t->expected == ret); else ret = !(t->expected); - tests_cnt++; ksft_test_result(ret, t->msg); } } @@ -268,7 +356,6 @@ static struct testcases malloc_cases[] = { }, }; - static struct testcases bits_cases[] = { { .test_func = handle_max_bits, @@ -276,11 +363,54 @@ static struct testcases bits_cases[] = { }, }; +static struct testcases syscall_cases[] = { + { + .later = 0, + .lam = LAM_U57_BITS, + .test_func = handle_syscall, + .msg = "SYSCALL: LAM_U57. syscall with metadata\n", + }, + { + .later = 1, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = handle_syscall, + .msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", + }, +}; + +static struct testcases mmap_cases[] = { + { + .later = 1, + .expected = 0, + .lam = LAM_U57_BITS, + .addr = HIGH_ADDR, + .test_func = handle_mmap, + .msg = "MMAP: First mmap high address, then set LAM_U57.\n", + }, + { + .later = 0, + .expected = 0, + .lam = LAM_U57_BITS, + .addr = HIGH_ADDR, + .test_func = handle_mmap, + .msg = "MMAP: First LAM_U57, then High address.\n", + }, + { + .later = 0, + .expected = 0, + .lam = LAM_U57_BITS, + .addr = LOW_ADDR, + .test_func = handle_mmap, + .msg = "MMAP: First LAM_U57, then Low address.\n", + }, +}; + static void cmd_help(void) { printf("usage: lam [-h] [-t test list]\n"); printf("\t-t test list: run tests specified in the test list, default:0x%x\n", TEST_MASK); - printf("\t\t0x1:malloc; 0x2:max_bits;\n"); + printf("\t\t0x1:malloc; 0x2:max_bits; 0x4:mmap; 0x8:syscall.\n"); printf("\t-h: help\n"); } @@ -320,6 +450,12 @@ int main(int argc, char **argv) if (tests & FUNC_BITS) run_test(bits_cases, ARRAY_SIZE(bits_cases)); + if (tests & FUNC_MMAP) + run_test(mmap_cases, ARRAY_SIZE(mmap_cases)); + + if (tests & FUNC_SYSCALL) + run_test(syscall_cases, ARRAY_SIZE(syscall_cases)); + ksft_set_plan(tests_cnt); return ksft_exit_pass(); -- GitLab From 72fd6d738c991225c1053ee5003dd45e9c04e0e6 Mon Sep 17 00:00:00 2001 From: Weihong Zhang Date: Sun, 12 Mar 2023 14:26:09 +0300 Subject: [PATCH 0698/5631] selftests/x86/lam: Add io_uring test cases for linear-address masking LAM should be supported in kernel thread, using io_uring to verify LAM feature. The test cases implement read a file through io_uring, the test cases choose an iovec array as receiving buffer, which used to receive data, according to LAM mode, set metadata in high bits of these buffer. io_uring can deal with these buffers that pointed to pointers with the metadata in high bits. Signed-off-by: Weihong Zhang Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-15-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/lam.c | 341 +++++++++++++++++++++++++++++- 1 file changed, 339 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 39ebfc511685..52750ebd0887 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -9,8 +9,12 @@ #include #include #include +#include +#include #include +#include +#include #include "../kselftest.h" #ifndef __x86_64__ @@ -32,8 +36,9 @@ #define FUNC_BITS 0x2 #define FUNC_MMAP 0x4 #define FUNC_SYSCALL 0x8 +#define FUNC_URING 0x10 -#define TEST_MASK 0xf +#define TEST_MASK 0x1f #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) @@ -42,6 +47,13 @@ #define PAGE_SIZE (4 << 10) +#define barrier() ({ \ + __asm__ __volatile__("" : : : "memory"); \ +}) + +#define URING_QUEUE_SZ 1 +#define URING_BLOCK_SZ 2048 + struct testcases { unsigned int later; int expected; /* 2: SIGSEGV Error; 1: other errors */ @@ -51,6 +63,33 @@ struct testcases { const char *msg; }; +/* Used by CQ of uring, source file handler and file's size */ +struct file_io { + int file_fd; + off_t file_sz; + struct iovec iovecs[]; +}; + +struct io_uring_queue { + unsigned int *head; + unsigned int *tail; + unsigned int *ring_mask; + unsigned int *ring_entries; + unsigned int *flags; + unsigned int *array; + union { + struct io_uring_cqe *cqes; + struct io_uring_sqe *sqes; + } queue; + size_t ring_sz; +}; + +struct io_ring { + int ring_fd; + struct io_uring_queue sq_ring; + struct io_uring_queue cq_ring; +}; + int tests_cnt; jmp_buf segv_env; @@ -294,6 +333,285 @@ static int handle_syscall(struct testcases *test) return ret; } +int sys_uring_setup(unsigned int entries, struct io_uring_params *p) +{ + return (int)syscall(__NR_io_uring_setup, entries, p); +} + +int sys_uring_enter(int fd, unsigned int to, unsigned int min, unsigned int flags) +{ + return (int)syscall(__NR_io_uring_enter, fd, to, min, flags, NULL, 0); +} + +/* Init submission queue and completion queue */ +int mmap_io_uring(struct io_uring_params p, struct io_ring *s) +{ + struct io_uring_queue *sring = &s->sq_ring; + struct io_uring_queue *cring = &s->cq_ring; + + sring->ring_sz = p.sq_off.array + p.sq_entries * sizeof(unsigned int); + cring->ring_sz = p.cq_off.cqes + p.cq_entries * sizeof(struct io_uring_cqe); + + if (p.features & IORING_FEAT_SINGLE_MMAP) { + if (cring->ring_sz > sring->ring_sz) + sring->ring_sz = cring->ring_sz; + + cring->ring_sz = sring->ring_sz; + } + + void *sq_ptr = mmap(0, sring->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, s->ring_fd, + IORING_OFF_SQ_RING); + + if (sq_ptr == MAP_FAILED) { + perror("sub-queue!"); + return 1; + } + + void *cq_ptr = sq_ptr; + + if (!(p.features & IORING_FEAT_SINGLE_MMAP)) { + cq_ptr = mmap(0, cring->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, s->ring_fd, + IORING_OFF_CQ_RING); + if (cq_ptr == MAP_FAILED) { + perror("cpl-queue!"); + munmap(sq_ptr, sring->ring_sz); + return 1; + } + } + + sring->head = sq_ptr + p.sq_off.head; + sring->tail = sq_ptr + p.sq_off.tail; + sring->ring_mask = sq_ptr + p.sq_off.ring_mask; + sring->ring_entries = sq_ptr + p.sq_off.ring_entries; + sring->flags = sq_ptr + p.sq_off.flags; + sring->array = sq_ptr + p.sq_off.array; + + /* Map a queue as mem map */ + s->sq_ring.queue.sqes = mmap(0, p.sq_entries * sizeof(struct io_uring_sqe), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + s->ring_fd, IORING_OFF_SQES); + if (s->sq_ring.queue.sqes == MAP_FAILED) { + munmap(sq_ptr, sring->ring_sz); + if (sq_ptr != cq_ptr) { + ksft_print_msg("failed to mmap uring queue!"); + munmap(cq_ptr, cring->ring_sz); + return 1; + } + } + + cring->head = cq_ptr + p.cq_off.head; + cring->tail = cq_ptr + p.cq_off.tail; + cring->ring_mask = cq_ptr + p.cq_off.ring_mask; + cring->ring_entries = cq_ptr + p.cq_off.ring_entries; + cring->queue.cqes = cq_ptr + p.cq_off.cqes; + + return 0; +} + +/* Init io_uring queues */ +int setup_io_uring(struct io_ring *s) +{ + struct io_uring_params para; + + memset(¶, 0, sizeof(para)); + s->ring_fd = sys_uring_setup(URING_QUEUE_SZ, ¶); + if (s->ring_fd < 0) + return 1; + + return mmap_io_uring(para, s); +} + +/* + * Get data from completion queue. the data buffer saved the file data + * return 0: success; others: error; + */ +int handle_uring_cq(struct io_ring *s) +{ + struct file_io *fi = NULL; + struct io_uring_queue *cring = &s->cq_ring; + struct io_uring_cqe *cqe; + unsigned int head; + off_t len = 0; + + head = *cring->head; + + do { + barrier(); + if (head == *cring->tail) + break; + /* Get the entry */ + cqe = &cring->queue.cqes[head & *s->cq_ring.ring_mask]; + fi = (struct file_io *)cqe->user_data; + if (cqe->res < 0) + break; + + int blocks = (int)(fi->file_sz + URING_BLOCK_SZ - 1) / URING_BLOCK_SZ; + + for (int i = 0; i < blocks; i++) + len += fi->iovecs[i].iov_len; + + head++; + } while (1); + + *cring->head = head; + barrier(); + + return (len != fi->file_sz); +} + +/* + * Submit squeue. specify via IORING_OP_READV. + * the buffer need to be set metadata according to LAM mode + */ +int handle_uring_sq(struct io_ring *ring, struct file_io *fi, unsigned long lam) +{ + int file_fd = fi->file_fd; + struct io_uring_queue *sring = &ring->sq_ring; + unsigned int index = 0, cur_block = 0, tail = 0, next_tail = 0; + struct io_uring_sqe *sqe; + + off_t remain = fi->file_sz; + int blocks = (int)(remain + URING_BLOCK_SZ - 1) / URING_BLOCK_SZ; + + while (remain) { + off_t bytes = remain; + void *buf; + + if (bytes > URING_BLOCK_SZ) + bytes = URING_BLOCK_SZ; + + fi->iovecs[cur_block].iov_len = bytes; + + if (posix_memalign(&buf, URING_BLOCK_SZ, URING_BLOCK_SZ)) + return 1; + + fi->iovecs[cur_block].iov_base = (void *)set_metadata((uint64_t)buf, lam); + remain -= bytes; + cur_block++; + } + + next_tail = *sring->tail; + tail = next_tail; + next_tail++; + + barrier(); + + index = tail & *ring->sq_ring.ring_mask; + + sqe = &ring->sq_ring.queue.sqes[index]; + sqe->fd = file_fd; + sqe->flags = 0; + sqe->opcode = IORING_OP_READV; + sqe->addr = (unsigned long)fi->iovecs; + sqe->len = blocks; + sqe->off = 0; + sqe->user_data = (uint64_t)fi; + + sring->array[index] = index; + tail = next_tail; + + if (*sring->tail != tail) { + *sring->tail = tail; + barrier(); + } + + if (sys_uring_enter(ring->ring_fd, 1, 1, IORING_ENTER_GETEVENTS) < 0) + return 1; + + return 0; +} + +/* + * Test LAM in async I/O and io_uring, read current binery through io_uring + * Set metadata in pointers to iovecs buffer. + */ +int do_uring(unsigned long lam) +{ + struct io_ring *ring; + struct file_io *fi; + struct stat st; + int ret = 1; + char path[PATH_MAX]; + + /* get current process path */ + if (readlink("/proc/self/exe", path, PATH_MAX) <= 0) + return 1; + + int file_fd = open(path, O_RDONLY); + + if (file_fd < 0) + return 1; + + if (fstat(file_fd, &st) < 0) + return 1; + + off_t file_sz = st.st_size; + + int blocks = (int)(file_sz + URING_BLOCK_SZ - 1) / URING_BLOCK_SZ; + + fi = malloc(sizeof(*fi) + sizeof(struct iovec) * blocks); + if (!fi) + return 1; + + fi->file_sz = file_sz; + fi->file_fd = file_fd; + + ring = malloc(sizeof(*ring)); + if (!ring) + return 1; + + memset(ring, 0, sizeof(struct io_ring)); + + if (setup_io_uring(ring)) + goto out; + + if (handle_uring_sq(ring, fi, lam)) + goto out; + + ret = handle_uring_cq(ring); + +out: + free(ring); + + for (int i = 0; i < blocks; i++) { + if (fi->iovecs[i].iov_base) { + uint64_t addr = ((uint64_t)fi->iovecs[i].iov_base); + + switch (lam) { + case LAM_U57_BITS: /* Clear bits 62:57 */ + addr = (addr & ~(0x3fULL << 57)); + break; + } + free((void *)addr); + fi->iovecs[i].iov_base = NULL; + } + } + + free(fi); + + return ret; +} + +int handle_uring(struct testcases *test) +{ + int ret = 0; + + if (test->later == 0 && test->lam != 0) + if (set_lam(test->lam) != 0) + return 1; + + if (sigsetjmp(segv_env, 1) == 0) { + signal(SIGSEGV, segv_handler); + ret = do_uring(test->lam); + } else { + ret = 2; + } + + return ret; +} + static int fork_test(struct testcases *test) { int ret, child_ret; @@ -340,6 +658,22 @@ static void run_test(struct testcases *test, int count) } } +static struct testcases uring_cases[] = { + { + .later = 0, + .lam = LAM_U57_BITS, + .test_func = handle_uring, + .msg = "URING: LAM_U57. Dereferencing pointer with metadata\n", + }, + { + .later = 1, + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = handle_uring, + .msg = "URING:[Negative] Disable LAM. Dereferencing pointer with metadata.\n", + }, +}; + static struct testcases malloc_cases[] = { { .later = 0, @@ -410,7 +744,7 @@ static void cmd_help(void) { printf("usage: lam [-h] [-t test list]\n"); printf("\t-t test list: run tests specified in the test list, default:0x%x\n", TEST_MASK); - printf("\t\t0x1:malloc; 0x2:max_bits; 0x4:mmap; 0x8:syscall.\n"); + printf("\t\t0x1:malloc; 0x2:max_bits; 0x4:mmap; 0x8:syscall; 0x10:io_uring.\n"); printf("\t-h: help\n"); } @@ -456,6 +790,9 @@ int main(int argc, char **argv) if (tests & FUNC_SYSCALL) run_test(syscall_cases, ARRAY_SIZE(syscall_cases)); + if (tests & FUNC_URING) + run_test(uring_cases, ARRAY_SIZE(uring_cases)); + ksft_set_plan(tests_cnt); return ksft_exit_pass(); -- GitLab From 833c12ce0f4307675beb60b194833c6c7cb506d7 Mon Sep 17 00:00:00 2001 From: Weihong Zhang Date: Sun, 12 Mar 2023 14:26:10 +0300 Subject: [PATCH 0699/5631] selftests/x86/lam: Add inherit test cases for linear-address masking LAM is enabled per-thread and gets inherited on fork(2)/clone(2). exec() reverts LAM status to the default disabled state. There are two test scenarios: - Fork test cases: These cases were used to test the inheritance of LAM for per-thread, Child process generated by fork() should inherit LAM feature from parent process, Child process can get the LAM mode same as parent process. - Execve test cases: Processes generated by execve() are different from processes generated by fork(), these processes revert LAM status to disabled status. Signed-off-by: Weihong Zhang Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-16-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/lam.c | 125 +++++++++++++++++++++++++++++- 1 file changed, 121 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 52750ebd0887..ebabd4333b7d 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -37,8 +37,9 @@ #define FUNC_MMAP 0x4 #define FUNC_SYSCALL 0x8 #define FUNC_URING 0x10 +#define FUNC_INHERITE 0x20 -#define TEST_MASK 0x1f +#define TEST_MASK 0x3f #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) @@ -174,6 +175,28 @@ static unsigned long get_default_tag_bits(void) return lam; } +/* + * Set tagged address and read back untag mask. + * check if the untag mask is expected. + */ +static int get_lam(void) +{ + uint64_t ptr = 0; + int ret = -1; + /* Get untagged mask */ + if (syscall(SYS_arch_prctl, ARCH_GET_UNTAG_MASK, &ptr) == -1) + return -1; + + /* Check mask returned is expected */ + if (ptr == ~(LAM_U57_MASK)) + ret = LAM_U57_BITS; + else if (ptr == -1ULL) + ret = LAM_NONE; + + + return ret; +} + /* According to LAM mode, set metadata in high bits */ static uint64_t set_metadata(uint64_t src, unsigned long lam) { @@ -581,7 +604,7 @@ int do_uring(unsigned long lam) switch (lam) { case LAM_U57_BITS: /* Clear bits 62:57 */ - addr = (addr & ~(0x3fULL << 57)); + addr = (addr & ~(LAM_U57_MASK)); break; } free((void *)addr); @@ -632,6 +655,72 @@ static int fork_test(struct testcases *test) return ret; } +static int handle_execve(struct testcases *test) +{ + int ret, child_ret; + int lam = test->lam; + pid_t pid; + + pid = fork(); + if (pid < 0) { + perror("Fork failed."); + ret = 1; + } else if (pid == 0) { + char path[PATH_MAX]; + + /* Set LAM mode in parent process */ + if (set_lam(lam) != 0) + return 1; + + /* Get current binary's path and the binary was run by execve */ + if (readlink("/proc/self/exe", path, PATH_MAX) <= 0) + exit(-1); + + /* run binary to get LAM mode and return to parent process */ + if (execlp(path, path, "-t 0x0", NULL) < 0) { + perror("error on exec"); + exit(-1); + } + } else { + wait(&child_ret); + ret = WEXITSTATUS(child_ret); + if (ret != LAM_NONE) + return 1; + } + + return 0; +} + +static int handle_inheritance(struct testcases *test) +{ + int ret, child_ret; + int lam = test->lam; + pid_t pid; + + /* Set LAM mode in parent process */ + if (set_lam(lam) != 0) + return 1; + + pid = fork(); + if (pid < 0) { + perror("Fork failed."); + return 1; + } else if (pid == 0) { + /* Set LAM mode in parent process */ + int child_lam = get_lam(); + + exit(child_lam); + } else { + wait(&child_ret); + ret = WEXITSTATUS(child_ret); + + if (lam != ret) + return 1; + } + + return 0; +} + static void run_test(struct testcases *test, int count) { int i, ret = 0; @@ -740,11 +829,26 @@ static struct testcases mmap_cases[] = { }, }; +static struct testcases inheritance_cases[] = { + { + .expected = 0, + .lam = LAM_U57_BITS, + .test_func = handle_inheritance, + .msg = "FORK: LAM_U57, child process should get LAM mode same as parent\n", + }, + { + .expected = 0, + .lam = LAM_U57_BITS, + .test_func = handle_execve, + .msg = "EXECVE: LAM_U57, child process should get disabled LAM mode\n", + }, +}; + static void cmd_help(void) { printf("usage: lam [-h] [-t test list]\n"); printf("\t-t test list: run tests specified in the test list, default:0x%x\n", TEST_MASK); - printf("\t\t0x1:malloc; 0x2:max_bits; 0x4:mmap; 0x8:syscall; 0x10:io_uring.\n"); + printf("\t\t0x1:malloc; 0x2:max_bits; 0x4:mmap; 0x8:syscall; 0x10:io_uring; 0x20:inherit;\n"); printf("\t-h: help\n"); } @@ -764,7 +868,7 @@ int main(int argc, char **argv) switch (c) { case 't': tests = strtoul(optarg, NULL, 16); - if (!(tests & TEST_MASK)) { + if (tests && !(tests & TEST_MASK)) { ksft_print_msg("Invalid argument!\n"); return -1; } @@ -778,6 +882,16 @@ int main(int argc, char **argv) } } + /* + * When tests is 0, it is not a real test case; + * the option used by test case(execve) to check the lam mode in + * process generated by execve, the process read back lam mode and + * check with lam mode in parent process. + */ + if (!tests) + return (get_lam()); + + /* Run test cases */ if (tests & FUNC_MALLOC) run_test(malloc_cases, ARRAY_SIZE(malloc_cases)); @@ -793,6 +907,9 @@ int main(int argc, char **argv) if (tests & FUNC_URING) run_test(uring_cases, ARRAY_SIZE(uring_cases)); + if (tests & FUNC_INHERITE) + run_test(inheritance_cases, ARRAY_SIZE(inheritance_cases)); + ksft_set_plan(tests_cnt); return ksft_exit_pass(); -- GitLab From 34821473deb3a56adf5e989e8cefd8bfc60ed216 Mon Sep 17 00:00:00 2001 From: Weihong Zhang Date: Sun, 12 Mar 2023 14:26:11 +0300 Subject: [PATCH 0700/5631] selftests/x86/lam: Add ARCH_FORCE_TAGGED_SVA test cases for linear-address masking By default do not allow to enable both LAM and use SVA in the same process. The new ARCH_FORCE_TAGGED_SVA arch_prctl() overrides the limitation. Add new test cases for the new arch_prctl: Before using ARCH_FORCE_TAGGED_SVA, should not allow to enable LAM/SVA coexisting. the test cases should be negative. The test depands on idxd driver and iommu. before test, need add "intel_iommu=on,sm_on" in kernel command line and insmod idxd driver. Signed-off-by: Weihong Zhang Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-17-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/lam.c | 237 +++++++++++++++++++++++++++++- 1 file changed, 235 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index ebabd4333b7d..a8c91829b616 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -30,6 +30,7 @@ #define ARCH_GET_UNTAG_MASK 0x4001 #define ARCH_ENABLE_TAGGED_ADDR 0x4002 #define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 /* Specified test function bits */ #define FUNC_MALLOC 0x1 @@ -38,8 +39,9 @@ #define FUNC_SYSCALL 0x8 #define FUNC_URING 0x10 #define FUNC_INHERITE 0x20 +#define FUNC_PASID 0x40 -#define TEST_MASK 0x3f +#define TEST_MASK 0x7f #define LOW_ADDR (0x1UL << 30) #define HIGH_ADDR (0x3UL << 48) @@ -55,11 +57,19 @@ #define URING_QUEUE_SZ 1 #define URING_BLOCK_SZ 2048 +/* Pasid test define */ +#define LAM_CMD_BIT 0x1 +#define PAS_CMD_BIT 0x2 +#define SVA_CMD_BIT 0x4 + +#define PAS_CMD(cmd1, cmd2, cmd3) (((cmd3) << 8) | ((cmd2) << 4) | ((cmd1) << 0)) + struct testcases { unsigned int later; int expected; /* 2: SIGSEGV Error; 1: other errors */ unsigned long lam; uint64_t addr; + uint64_t cmd; int (*test_func)(struct testcases *test); const char *msg; }; @@ -556,7 +566,7 @@ int do_uring(unsigned long lam) struct file_io *fi; struct stat st; int ret = 1; - char path[PATH_MAX]; + char path[PATH_MAX] = {0}; /* get current process path */ if (readlink("/proc/self/exe", path, PATH_MAX) <= 0) @@ -852,6 +862,226 @@ static void cmd_help(void) printf("\t-h: help\n"); } +/* Check for file existence */ +uint8_t file_Exists(const char *fileName) +{ + struct stat buffer; + + uint8_t ret = (stat(fileName, &buffer) == 0); + + return ret; +} + +/* Sysfs idxd files */ +const char *dsa_configs[] = { + "echo 1 > /sys/bus/dsa/devices/dsa0/wq0.1/group_id", + "echo shared > /sys/bus/dsa/devices/dsa0/wq0.1/mode", + "echo 10 > /sys/bus/dsa/devices/dsa0/wq0.1/priority", + "echo 16 > /sys/bus/dsa/devices/dsa0/wq0.1/size", + "echo 15 > /sys/bus/dsa/devices/dsa0/wq0.1/threshold", + "echo user > /sys/bus/dsa/devices/dsa0/wq0.1/type", + "echo MyApp1 > /sys/bus/dsa/devices/dsa0/wq0.1/name", + "echo 1 > /sys/bus/dsa/devices/dsa0/engine0.1/group_id", + "echo dsa0 > /sys/bus/dsa/drivers/idxd/bind", + /* bind files and devices, generated a device file in /dev */ + "echo wq0.1 > /sys/bus/dsa/drivers/user/bind", +}; + +/* DSA device file */ +const char *dsaDeviceFile = "/dev/dsa/wq0.1"; +/* file for io*/ +const char *dsaPasidEnable = "/sys/bus/dsa/devices/dsa0/pasid_enabled"; + +/* + * DSA depends on kernel cmdline "intel_iommu=on,sm_on" + * return pasid_enabled (0: disable 1:enable) + */ +int Check_DSA_Kernel_Setting(void) +{ + char command[256] = ""; + char buf[256] = ""; + char *ptr; + int rv = -1; + + snprintf(command, sizeof(command) - 1, "cat %s", dsaPasidEnable); + + FILE *cmd = popen(command, "r"); + + if (cmd) { + while (fgets(buf, sizeof(buf) - 1, cmd) != NULL); + + pclose(cmd); + rv = strtol(buf, &ptr, 16); + } + + return rv; +} + +/* + * Config DSA's sysfs files as shared DSA's WQ. + * Generated a device file /dev/dsa/wq0.1 + * Return: 0 OK; 1 Failed; 3 Skip(SVA disabled). + */ +int Dsa_Init_Sysfs(void) +{ + uint len = ARRAY_SIZE(dsa_configs); + const char **p = dsa_configs; + + if (file_Exists(dsaDeviceFile) == 1) + return 0; + + /* check the idxd driver */ + if (file_Exists(dsaPasidEnable) != 1) { + printf("Please make sure idxd driver was loaded\n"); + return 3; + } + + /* Check SVA feature */ + if (Check_DSA_Kernel_Setting() != 1) { + printf("Please enable SVA.(Add intel_iommu=on,sm_on in kernel cmdline)\n"); + return 3; + } + + /* Check the idxd device file on /dev/dsa/ */ + for (int i = 0; i < len; i++) { + if (system(p[i])) + return 1; + } + + /* After config, /dev/dsa/wq0.1 should be generated */ + return (file_Exists(dsaDeviceFile) != 1); +} + +/* + * Open DSA device file, triger API: iommu_sva_alloc_pasid + */ +void *allocate_dsa_pasid(void) +{ + int fd; + void *wq; + + fd = open(dsaDeviceFile, O_RDWR); + if (fd < 0) { + perror("open"); + return MAP_FAILED; + } + + wq = mmap(NULL, 0x1000, PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, 0); + if (wq == MAP_FAILED) + perror("mmap"); + + return wq; +} + +int set_force_svm(void) +{ + int ret = 0; + + ret = syscall(SYS_arch_prctl, ARCH_FORCE_TAGGED_SVA); + + return ret; +} + +int handle_pasid(struct testcases *test) +{ + uint tmp = test->cmd; + uint runed = 0x0; + int ret = 0; + void *wq = NULL; + + ret = Dsa_Init_Sysfs(); + if (ret != 0) + return ret; + + for (int i = 0; i < 3; i++) { + int err = 0; + + if (tmp & 0x1) { + /* run set lam mode*/ + if ((runed & 0x1) == 0) { + err = set_lam(LAM_U57_BITS); + runed = runed | 0x1; + } else + err = 1; + } else if (tmp & 0x4) { + /* run force svm */ + if ((runed & 0x4) == 0) { + err = set_force_svm(); + runed = runed | 0x4; + } else + err = 1; + } else if (tmp & 0x2) { + /* run allocate pasid */ + if ((runed & 0x2) == 0) { + runed = runed | 0x2; + wq = allocate_dsa_pasid(); + if (wq == MAP_FAILED) + err = 1; + } else + err = 1; + } + + ret = ret + err; + if (ret > 0) + break; + + tmp = tmp >> 4; + } + + if (wq != MAP_FAILED && wq != NULL) + if (munmap(wq, 0x1000)) + printf("munmap failed %d\n", errno); + + if (runed != 0x7) + ret = 1; + + return (ret != 0); +} + +/* + * Pasid test depends on idxd and SVA, kernel should enable iommu and sm. + * command line(intel_iommu=on,sm_on) + */ +static struct testcases pasid_cases[] = { + { + .expected = 1, + .cmd = PAS_CMD(LAM_CMD_BIT, PAS_CMD_BIT, SVA_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: [Negative] Execute LAM, PASID, SVA in sequence\n", + }, + { + .expected = 0, + .cmd = PAS_CMD(LAM_CMD_BIT, SVA_CMD_BIT, PAS_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: Execute LAM, SVA, PASID in sequence\n", + }, + { + .expected = 1, + .cmd = PAS_CMD(PAS_CMD_BIT, LAM_CMD_BIT, SVA_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: [Negative] Execute PASID, LAM, SVA in sequence\n", + }, + { + .expected = 0, + .cmd = PAS_CMD(PAS_CMD_BIT, SVA_CMD_BIT, LAM_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: Execute PASID, SVA, LAM in sequence\n", + }, + { + .expected = 0, + .cmd = PAS_CMD(SVA_CMD_BIT, LAM_CMD_BIT, PAS_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: Execute SVA, LAM, PASID in sequence\n", + }, + { + .expected = 0, + .cmd = PAS_CMD(SVA_CMD_BIT, PAS_CMD_BIT, LAM_CMD_BIT), + .test_func = handle_pasid, + .msg = "PASID: Execute SVA, PASID, LAM in sequence\n", + }, +}; + int main(int argc, char **argv) { int c = 0; @@ -910,6 +1140,9 @@ int main(int argc, char **argv) if (tests & FUNC_INHERITE) run_test(inheritance_cases, ARRAY_SIZE(inheritance_cases)); + if (tests & FUNC_PASID) + run_test(pasid_cases, ARRAY_SIZE(pasid_cases)); + ksft_set_plan(tests_cnt); return ksft_exit_pass(); -- GitLab From dfd7a1569e25996575a24725b64f73162155bcd6 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Sun, 12 Mar 2023 14:26:12 +0300 Subject: [PATCH 0701/5631] selftests/x86/lam: Add test cases for LAM vs thread creation LAM enabling is only allowed when the process has single thread. LAM mode is inherited into child thread. Trying to enable LAM after spawning a thread has to fail. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230312112612.31869-18-kirill.shutemov%40linux.intel.com --- tools/testing/selftests/x86/lam.c | 92 +++++++++++++++++++++++++++++++ 1 file changed, 92 insertions(+) diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index a8c91829b616..eb0e46905bf9 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE #include #include #include @@ -12,6 +13,7 @@ #include #include #include +#include #include #include @@ -50,6 +52,8 @@ #define PAGE_SIZE (4 << 10) +#define STACK_SIZE 65536 + #define barrier() ({ \ __asm__ __volatile__("" : : : "memory"); \ }) @@ -731,6 +735,75 @@ static int handle_inheritance(struct testcases *test) return 0; } +static int thread_fn_get_lam(void *arg) +{ + return get_lam(); +} + +static int thread_fn_set_lam(void *arg) +{ + struct testcases *test = arg; + + return set_lam(test->lam); +} + +static int handle_thread(struct testcases *test) +{ + char stack[STACK_SIZE]; + int ret, child_ret; + int lam = 0; + pid_t pid; + + /* Set LAM mode in parent process */ + if (!test->later) { + lam = test->lam; + if (set_lam(lam) != 0) + return 1; + } + + pid = clone(thread_fn_get_lam, stack + STACK_SIZE, + SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM, NULL); + if (pid < 0) { + perror("Clone failed."); + return 1; + } + + waitpid(pid, &child_ret, 0); + ret = WEXITSTATUS(child_ret); + + if (lam != ret) + return 1; + + if (test->later) { + if (set_lam(test->lam) != 0) + return 1; + } + + return 0; +} + +static int handle_thread_enable(struct testcases *test) +{ + char stack[STACK_SIZE]; + int ret, child_ret; + int lam = test->lam; + pid_t pid; + + pid = clone(thread_fn_set_lam, stack + STACK_SIZE, + SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM, test); + if (pid < 0) { + perror("Clone failed."); + return 1; + } + + waitpid(pid, &child_ret, 0); + ret = WEXITSTATUS(child_ret); + + if (lam != ret) + return 1; + + return 0; +} static void run_test(struct testcases *test, int count) { int i, ret = 0; @@ -846,6 +919,25 @@ static struct testcases inheritance_cases[] = { .test_func = handle_inheritance, .msg = "FORK: LAM_U57, child process should get LAM mode same as parent\n", }, + { + .expected = 0, + .lam = LAM_U57_BITS, + .test_func = handle_thread, + .msg = "THREAD: LAM_U57, child thread should get LAM mode same as parent\n", + }, + { + .expected = 1, + .lam = LAM_U57_BITS, + .test_func = handle_thread_enable, + .msg = "THREAD: [NEGATIVE] Enable LAM in child.\n", + }, + { + .expected = 1, + .later = 1, + .lam = LAM_U57_BITS, + .test_func = handle_thread, + .msg = "THREAD: [NEGATIVE] Enable LAM in parent after thread created.\n", + }, { .expected = 0, .lam = LAM_U57_BITS, -- GitLab From 5b1a1c1ab1f981b15bce778db863344f59bd1501 Mon Sep 17 00:00:00 2001 From: Yu Zhe Date: Thu, 16 Mar 2023 15:58:26 +0800 Subject: [PATCH 0702/5631] clk: remove unnecessary (void*) conversions Pointer variables of void * type do not require type cast. Signed-off-by: Yu Zhe Link: https://lore.kernel.org/r/20230316075826.22754-1-yuzhe@nfschina.com Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index ae07685c7588..9410a4e1b04b 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3194,7 +3194,7 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c, static int clk_summary_show(struct seq_file *s, void *data) { struct clk_core *c; - struct hlist_head **lists = (struct hlist_head **)s->private; + struct hlist_head **lists = s->private; seq_puts(s, " enable prepare protect duty hardware\n"); seq_puts(s, " clock count count count rate accuracy phase cycle enable\n"); @@ -3253,7 +3253,7 @@ static int clk_dump_show(struct seq_file *s, void *data) { struct clk_core *c; bool first_node = true; - struct hlist_head **lists = (struct hlist_head **)s->private; + struct hlist_head **lists = s->private; seq_putc(s, '{'); clk_prepare_lock(); -- GitLab From c3c6c9fc5d24bcafbbeda2edb521b70f5df052b7 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:11 +0800 Subject: [PATCH 0703/5631] KVM: x86/mmu: Move the code out of FNAME(sync_page)'s loop body into mmu.c Rename mmu->sync_page to mmu->sync_spte and move the code out of FNAME(sync_page)'s loop body into mmu.c. No functionalities change intended. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-6-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 4 +- arch/x86/kvm/mmu/mmu.c | 34 ++++++++-- arch/x86/kvm/mmu/paging_tmpl.h | 114 +++++++++++++------------------- 3 files changed, 76 insertions(+), 76 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 214636554675..b7526c15501e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -439,8 +439,8 @@ struct kvm_mmu { gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t gva_or_gpa, u64 access, struct x86_exception *exception); - int (*sync_page)(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp); + int (*sync_spte)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, int i); void (*invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa); struct kvm_mmu_root_info root; union kvm_cpu_role cpu_role; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7fd824cf0a25..cb01e01e0404 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1934,7 +1934,7 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the * reserved bits checks will be wrong, etc... */ - if (WARN_ON_ONCE(sp->role.direct || !vcpu->arch.mmu->sync_page || + if (WARN_ON_ONCE(sp->role.direct || !vcpu->arch.mmu->sync_spte || (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) return false; @@ -1943,10 +1943,30 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { + int flush = 0; + int i; + if (!kvm_sync_page_check(vcpu, sp)) return -1; - return vcpu->arch.mmu->sync_page(vcpu, sp); + for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { + int ret = vcpu->arch.mmu->sync_spte(vcpu, sp, i); + + if (ret < -1) + return -1; + flush |= ret; + } + + /* + * Note, any flush is purely for KVM's correctness, e.g. when dropping + * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier + * unmap or dirty logging event doesn't fail to flush. The guest is + * responsible for flushing the TLB to ensure any changes in protection + * bits are recognized, i.e. until the guest flushes or page faults on + * a relevant address, KVM is architecturally allowed to let vCPUs use + * cached translations with the old protection bits. + */ + return flush; } static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -4504,7 +4524,7 @@ static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; - context->sync_page = NULL; + context->sync_spte = NULL; context->invlpg = NULL; } @@ -5095,7 +5115,7 @@ static void paging64_init_context(struct kvm_mmu *context) { context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; - context->sync_page = paging64_sync_page; + context->sync_spte = paging64_sync_spte; context->invlpg = paging64_invlpg; } @@ -5103,7 +5123,7 @@ static void paging32_init_context(struct kvm_mmu *context) { context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; - context->sync_page = paging32_sync_page; + context->sync_spte = paging32_sync_spte; context->invlpg = paging32_invlpg; } @@ -5192,7 +5212,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->cpu_role.as_u64 = cpu_role.as_u64; context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; - context->sync_page = NULL; + context->sync_spte = NULL; context->invlpg = NULL; context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; @@ -5324,7 +5344,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; - context->sync_page = ept_sync_page; + context->sync_spte = ept_sync_spte; context->invlpg = ept_invlpg; update_permission_bitmask(context, true); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index abb1d325ad30..c07b2e7def37 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -937,87 +937,67 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * can't change unless all sptes pointing to it are nuked first. * * Returns - * < 0: the sp should be zapped - * 0: the sp is synced and no tlb flushing is required - * > 0: the sp is synced and tlb flushing is required + * < 0: failed to sync spte + * 0: the spte is synced and no tlb flushing is required + * > 0: the spte is synced and tlb flushing is required */ -static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { - int i; bool host_writable; gpa_t first_pte_gpa; - bool flush = false; - - first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); - - for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { - u64 *sptep, spte; - struct kvm_memory_slot *slot; - unsigned pte_access; - pt_element_t gpte; - gpa_t pte_gpa; - gfn_t gfn; - - if (!sp->spt[i]) - continue; + u64 *sptep, spte; + struct kvm_memory_slot *slot; + unsigned pte_access; + pt_element_t gpte; + gpa_t pte_gpa; + gfn_t gfn; - pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); + if (!sp->spt[i]) + return 0; - if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, - sizeof(pt_element_t))) - return -1; + first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); + pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - flush = true; - continue; - } + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) + return -1; - gfn = gpte_to_gfn(gpte); - pte_access = sp->role.access; - pte_access &= FNAME(gpte_access)(gpte); - FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); + if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) + return 1; - if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access)) - continue; + gfn = gpte_to_gfn(gpte); + pte_access = sp->role.access; + pte_access &= FNAME(gpte_access)(gpte); + FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - /* - * Drop the SPTE if the new protections would result in a RWX=0 - * SPTE or if the gfn is changing. The RWX=0 case only affects - * EPT with execute-only support, i.e. EPT without an effective - * "present" bit, as all other paging modes will create a - * read-only SPTE if pte_access is zero. - */ - if ((!pte_access && !shadow_present_mask) || - gfn != kvm_mmu_page_get_gfn(sp, i)) { - drop_spte(vcpu->kvm, &sp->spt[i]); - flush = true; - continue; - } + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access)) + return 0; - /* Update the shadowed access bits in case they changed. */ - kvm_mmu_page_set_access(sp, i, pte_access); + /* + * Drop the SPTE if the new protections would result in a RWX=0 + * SPTE or if the gfn is changing. The RWX=0 case only affects + * EPT with execute-only support, i.e. EPT without an effective + * "present" bit, as all other paging modes will create a + * read-only SPTE if pte_access is zero. + */ + if ((!pte_access && !shadow_present_mask) || + gfn != kvm_mmu_page_get_gfn(sp, i)) { + drop_spte(vcpu->kvm, &sp->spt[i]); + return 1; + } - sptep = &sp->spt[i]; - spte = *sptep; - host_writable = spte & shadow_host_writable_mask; - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - make_spte(vcpu, sp, slot, pte_access, gfn, - spte_to_pfn(spte), spte, true, false, - host_writable, &spte); + /* Update the shadowed access bits in case they changed. */ + kvm_mmu_page_set_access(sp, i, pte_access); - flush |= mmu_spte_update(sptep, spte); - } + sptep = &sp->spt[i]; + spte = *sptep; + host_writable = spte & shadow_host_writable_mask; + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + make_spte(vcpu, sp, slot, pte_access, gfn, + spte_to_pfn(spte), spte, true, false, + host_writable, &spte); - /* - * Note, any flush is purely for KVM's correctness, e.g. when dropping - * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier - * unmap or dirty logging event doesn't fail to flush. The guest is - * responsible for flushing the TLB to ensure any changes in protection - * bits are recognized, i.e. until the guest flushes or page faults on - * a relevant address, KVM is architecturally allowed to let vCPUs use - * cached translations with the old protection bits. - */ - return flush; + return mmu_spte_update(sptep, spte); } #undef pt_element_t -- GitLab From e6722d9211b2aa5f195267faaa6858004b4f42a0 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:12 +0800 Subject: [PATCH 0704/5631] KVM: x86/mmu: Reduce the update to the spte in FNAME(sync_spte) Sometimes when the guest updates its pagetable, it adds only new gptes to it without changing any existed one, so there is no point to update the sptes for these existed gptes. Also when the sptes for these unchanged gptes are updated, the AD bits are also removed since make_spte() is called with prefetch=true which might result unneeded TLB flushing. Just do nothing if the gpte's permissions are unchanged. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-7-jiangshanlai@gmail.com [sean: expand comment to call out A/D bits] Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/paging_tmpl.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index c07b2e7def37..4047b8ff83d6 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -985,6 +985,14 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int drop_spte(vcpu->kvm, &sp->spt[i]); return 1; } + /* + * Do nothing if the permissions are unchanged. The existing SPTE is + * still, and prefetch_invalid_gpte() has verified that the A/D bits + * are set in the "new" gPTE, i.e. there is no danger of missing an A/D + * update due to A/D bits being set in the SPTE but not the gPTE. + */ + if (kvm_mmu_page_get_access(sp, i) == pte_access) + return 0; /* Update the shadowed access bits in case they changed. */ kvm_mmu_page_set_access(sp, i, pte_access); -- GitLab From f94db0c8b9fa50296d00e236e2416aea11186e18 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 16 Feb 2023 23:41:13 +0800 Subject: [PATCH 0705/5631] KVM: x86/mmu: Sanity check input to kvm_mmu_free_roots() Tweak KVM_MMU_ROOTS_ALL to precisely cover all current+previous root flags, and add a sanity in kvm_mmu_free_roots() to verify that the set of roots to free doesn't stray outside KVM_MMU_ROOTS_ALL. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-8-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 8 ++++---- arch/x86/kvm/mmu/mmu.c | 2 ++ 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b7526c15501e..c23c49e97ce2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -420,6 +420,10 @@ struct kvm_mmu_root_info { #define KVM_MMU_NUM_PREV_ROOTS 3 +#define KVM_MMU_ROOT_CURRENT BIT(0) +#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) +#define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1) + #define KVM_HAVE_MMU_RWLOCK struct kvm_mmu_page; @@ -1997,10 +2001,6 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state, return !!(*irq_state); } -#define KVM_MMU_ROOT_CURRENT BIT(0) -#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) -#define KVM_MMU_ROOTS_ALL (~0UL) - int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index cb01e01e0404..ffc18f5a1adf 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3568,6 +3568,8 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, LIST_HEAD(invalid_list); bool free_active_root; + WARN_ON_ONCE(roots_to_free & ~KVM_MMU_ROOTS_ALL); + BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG); /* Before acquiring the MMU lock, see if we need to do any real work. */ -- GitLab From cd42853e9530fb64097cbe83abce10a34e68cdf4 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:14 +0800 Subject: [PATCH 0706/5631] kvm: x86/mmu: Use KVM_MMU_ROOT_XXX for kvm_mmu_invalidate_addr() The @root_hpa for kvm_mmu_invalidate_addr() is called with @mmu->root.hpa or INVALID_PAGE where @mmu->root.hpa is to invalidate gva for the current root (the same meaning as KVM_MMU_ROOT_CURRENT) and INVALID_PAGE is to invalidate gva for all roots (the same meaning as KVM_MMU_ROOTS_ALL). Change the argument type of kvm_mmu_invalidate_addr() and use KVM_MMU_ROOT_XXX instead so that we can reuse the function for kvm_mmu_invpcid_gva() and nested_ept_invalidate_addr() for invalidating gva for different set of roots. No fuctionalities changed. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-9-jiangshanlai@gmail.com [sean: massage comment slightly] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/mmu/mmu.c | 38 ++++++++++++++++----------------- arch/x86/kvm/x86.c | 2 +- 3 files changed, 21 insertions(+), 21 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c23c49e97ce2..9a2c5925875b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2045,7 +2045,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - u64 addr, hpa_t root_hpa); + u64 addr, unsigned long roots); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index ffc18f5a1adf..a9cbd94ea858 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5765,10 +5765,12 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - u64 addr, hpa_t root_hpa) + u64 addr, unsigned long roots) { int i; + WARN_ON_ONCE(roots & ~KVM_MMU_ROOTS_ALL); + /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ @@ -5781,31 +5783,29 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, if (!mmu->invlpg) return; - if (root_hpa == INVALID_PAGE) { + if (roots & KVM_MMU_ROOT_CURRENT) mmu->invlpg(vcpu, addr, mmu->root.hpa); - /* - * INVLPG is required to invalidate any global mappings for the VA, - * irrespective of PCID. Since it would take us roughly similar amount - * of work to determine whether any of the prev_root mappings of the VA - * is marked global, or to just sync it blindly, so we might as well - * just always sync it. - * - * Mappings not reachable via the current cr3 or the prev_roots will be - * synced when switching to that cr3, so nothing needs to be done here - * for them. - */ - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (VALID_PAGE(mmu->prev_roots[i].hpa)) - mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); - } else { - mmu->invlpg(vcpu, addr, root_hpa); + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + if ((roots & KVM_MMU_ROOT_PREVIOUS(i)) && + VALID_PAGE(mmu->prev_roots[i].hpa)) + mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); } } void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); + /* + * INVLPG is required to invalidate any global mappings for the VA, + * irrespective of PCID. Blindly sync all roots as it would take + * roughly the same amount of work/time to determine whether any of the + * previous roots have a global mapping. + * + * Mappings not reachable via the current or previous cached roots will + * be synced when switching to that new cr3, so nothing needs to be + * done here for them. + */ + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, KVM_MMU_ROOTS_ALL); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0b6b587d7914..e5a94d2228b0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -803,7 +803,7 @@ void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, - fault_mmu->root.hpa); + KVM_MMU_ROOT_CURRENT); fault_mmu->inject_page_fault(vcpu, fault); } -- GitLab From 9ebc3f51da6f526326b3d2c08c7f582e4ccabd11 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 16 Feb 2023 23:41:15 +0800 Subject: [PATCH 0707/5631] KVM: x86/mmu: Use kvm_mmu_invalidate_addr() in kvm_mmu_invpcid_gva() Use kvm_mmu_invalidate_addr() instead open calls to mmu->invlpg(). No functional change intended. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216154115.710033-10-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a9cbd94ea858..3ed8879e93ed 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5814,27 +5814,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; - bool tlb_flush = false; + unsigned long roots = 0; uint i; - if (pcid == kvm_get_active_pcid(vcpu)) { - if (mmu->invlpg) - mmu->invlpg(vcpu, gva, mmu->root.hpa); - tlb_flush = true; - } + if (pcid == kvm_get_active_pcid(vcpu)) + roots |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && - pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { - if (mmu->invlpg) - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); - tlb_flush = true; - } + pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) + roots |= KVM_MMU_ROOT_PREVIOUS(i); } - if (tlb_flush) - static_call(kvm_x86_flush_tlb_gva)(vcpu, gva); - + if (roots) + kvm_mmu_invalidate_addr(vcpu, mmu, gva, roots); ++vcpu->stat.invlpg; /* -- GitLab From 2c86c444e2751a867bfa6a059a80ba67ef9d441a Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 17 Feb 2023 07:53:17 +0800 Subject: [PATCH 0708/5631] KVM: x86/mmu: Use kvm_mmu_invalidate_addr() in nested_ept_invalidate_addr() Use kvm_mmu_invalidate_addr() instead open calls to mmu->invlpg(). No functional change intended. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216235321.735214-1-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 1 + arch/x86/kvm/vmx/nested.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3ed8879e93ed..aafa431a3533 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5792,6 +5792,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); } } +EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_addr); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f63b28f46a71..c4ede229ed82 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -358,6 +358,7 @@ static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, gpa_t addr) { + unsigned long roots = 0; uint i; struct kvm_mmu_root_info *cached_root; @@ -368,8 +369,10 @@ static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, eptp)) - vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + roots |= KVM_MMU_ROOT_PREVIOUS(i); } + if (roots) + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.mmu, addr, roots); } static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, -- GitLab From ed335278bd1282641748b2b0ca23291c457038ef Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 17 Feb 2023 07:53:18 +0800 Subject: [PATCH 0709/5631] KVM: x86/mmu: Allow the roots to be invalid in FNAME(invlpg) Don't assume the current root to be valid, just check it and remove the WARN(). Also move the code to check if the root is valid into FNAME(invlpg) to simplify the code. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216235321.735214-2-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 3 +-- arch/x86/kvm/mmu/paging_tmpl.h | 4 +--- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index aafa431a3533..32291a84fdc6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5787,8 +5787,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, mmu->invlpg(vcpu, addr, mmu->root.hpa); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { - if ((roots & KVM_MMU_ROOT_PREVIOUS(i)) && - VALID_PAGE(mmu->prev_roots[i].hpa)) + if (roots & KVM_MMU_ROOT_PREVIOUS(i)) mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); } } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4047b8ff83d6..0b4e3c9a3f05 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -863,10 +863,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa) */ mmu_topup_memory_caches(vcpu, true); - if (!VALID_PAGE(root_hpa)) { - WARN_ON(1); + if (!VALID_PAGE(root_hpa)) return; - } write_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { -- GitLab From 9fd4a4e3a3d9fc0306525d95bf3eca693d311406 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 17 Feb 2023 07:53:19 +0800 Subject: [PATCH 0710/5631] KVM: x86/mmu: Remove FNAME(invlpg) and use FNAME(sync_spte) to update vTLB instead. In hardware TLB, invalidating TLB entries means the translations are removed from the TLB. In KVM shadowed vTLB, the translations (combinations of shadow paging and hardware TLB) are generally maintained as long as they remain "clean" when the TLB of an address space (i.e. a PCID or all) is flushed with the help of write-protections, sp->unsync, and kvm_sync_page(), where "clean" in this context means that no updates to KVM's SPTEs are needed. However, FNAME(invlpg) always zaps/removes the vTLB if the shadow page is unsync, and thus triggers a remote flush even if the original vTLB entry is clean, i.e. is usable as-is. Besides this, FNAME(invlpg) is largely is a duplicate implementation of FNAME(sync_spte) to invalidate a vTLB entry. To address both issues, reuse FNAME(sync_spte) to share the code and slightly modify the semantics, i.e. keep the vTLB entry if it's "clean" and avoid remote TLB flush. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216235321.735214-3-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/mmu/mmu.c | 50 +++++++++++++++++++---------- arch/x86/kvm/mmu/paging_tmpl.h | 57 --------------------------------- 3 files changed, 33 insertions(+), 75 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9a2c5925875b..991296a2f807 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -445,7 +445,6 @@ struct kvm_mmu { struct x86_exception *exception); int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); - void (*invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa); struct kvm_mmu_root_info root; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 32291a84fdc6..5bca99e50d1a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1073,14 +1073,6 @@ static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; } -static bool rmap_can_add(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_memory_cache *mc; - - mc = &vcpu->arch.mmu_pte_list_desc_cache; - return kvm_mmu_memory_cache_nr_free_objects(mc); -} - static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_memslots *slots; @@ -4527,7 +4519,6 @@ static void nonpaging_init_context(struct kvm_mmu *context) context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_spte = NULL; - context->invlpg = NULL; } static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, @@ -5118,7 +5109,6 @@ static void paging64_init_context(struct kvm_mmu *context) context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; context->sync_spte = paging64_sync_spte; - context->invlpg = paging64_invlpg; } static void paging32_init_context(struct kvm_mmu *context) @@ -5126,7 +5116,6 @@ static void paging32_init_context(struct kvm_mmu *context) context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; context->sync_spte = paging32_sync_spte; - context->invlpg = paging32_invlpg; } static union kvm_cpu_role @@ -5215,7 +5204,6 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; context->sync_spte = NULL; - context->invlpg = NULL; context->get_guest_pgd = get_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -5347,7 +5335,6 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; context->sync_spte = ept_sync_spte; - context->invlpg = ept_invlpg; update_permission_bitmask(context, true); context->pkru_mask = 0; @@ -5388,7 +5375,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, * L2 page tables are never shadowed, so there is no need to sync * SPTEs. */ - g_context->invlpg = NULL; + g_context->sync_spte = NULL; /* * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using @@ -5764,6 +5751,35 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, hpa_t root_hpa) +{ + struct kvm_shadow_walk_iterator iterator; + + vcpu_clear_mmio_info(vcpu, addr); + + if (!VALID_PAGE(root_hpa)) + return; + + write_lock(&vcpu->kvm->mmu_lock); + for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { + struct kvm_mmu_page *sp = sptep_to_sp(iterator.sptep); + + if (sp->unsync) { + int ret = mmu->sync_spte(vcpu, sp, iterator.index); + + if (ret < 0) + mmu_page_zap_pte(vcpu->kvm, sp, iterator.sptep, NULL); + if (ret) + kvm_flush_remote_tlbs_sptep(vcpu->kvm, iterator.sptep); + } + + if (!sp->unsync_children) + break; + } + write_unlock(&vcpu->kvm->mmu_lock); +} + void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, unsigned long roots) { @@ -5780,15 +5796,15 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, static_call(kvm_x86_flush_tlb_gva)(vcpu, addr); } - if (!mmu->invlpg) + if (!mmu->sync_spte) return; if (roots & KVM_MMU_ROOT_CURRENT) - mmu->invlpg(vcpu, addr, mmu->root.hpa); + __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->root.hpa); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (roots & KVM_MMU_ROOT_PREVIOUS(i)) - mmu->invlpg(vcpu, addr, mmu->prev_roots[i].hpa); + __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->prev_roots[i].hpa); } } EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_addr); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0b4e3c9a3f05..e9d97f9b2ec3 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -846,63 +846,6 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); } -/* Note, @addr is a GPA when invlpg() invalidates an L2 GPA translation in shadowed TDP */ -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, u64 addr, hpa_t root_hpa) -{ - struct kvm_shadow_walk_iterator iterator; - struct kvm_mmu_page *sp; - u64 old_spte; - int level; - u64 *sptep; - - vcpu_clear_mmio_info(vcpu, addr); - - /* - * No need to check return value here, rmap_can_add() can - * help us to skip pte prefetch later. - */ - mmu_topup_memory_caches(vcpu, true); - - if (!VALID_PAGE(root_hpa)) - return; - - write_lock(&vcpu->kvm->mmu_lock); - for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { - level = iterator.level; - sptep = iterator.sptep; - - sp = sptep_to_sp(sptep); - old_spte = *sptep; - if (is_last_spte(old_spte, level)) { - pt_element_t gpte; - gpa_t pte_gpa; - - if (!sp->unsync) - break; - - pte_gpa = FNAME(get_level1_sp_gpa)(sp); - pte_gpa += spte_index(sptep) * sizeof(pt_element_t); - - mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL); - if (is_shadow_present_pte(old_spte)) - kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); - - if (!rmap_can_add(vcpu)) - break; - - if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, - sizeof(pt_element_t))) - break; - - FNAME(prefetch_gpte)(vcpu, sp, sptep, gpte, false); - } - - if (!sp->unsync_children) - break; - } - write_unlock(&vcpu->kvm->mmu_lock); -} - /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t addr, u64 access, -- GitLab From 91ca7672dc7386c0d181ead2e03f4e65b73ca6b8 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 17 Feb 2023 07:53:20 +0800 Subject: [PATCH 0711/5631] kvm: x86/mmu: Remove @no_dirty_log from FNAME(prefetch_gpte) FNAME(prefetch_gpte) is always called with @no_dirty_log=true. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216235321.735214-4-jiangshanlai@gmail.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/paging_tmpl.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index e9d97f9b2ec3..8ef67f76ee68 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -519,7 +519,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, pt_element_t gpte, bool no_dirty_log) + u64 *spte, pt_element_t gpte) { struct kvm_memory_slot *slot; unsigned pte_access; @@ -535,8 +535,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, - no_dirty_log && (pte_access & ACC_WRITE_MASK)); + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, pte_access & ACC_WRITE_MASK); if (!slot) return false; @@ -605,7 +604,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, if (is_shadow_present_pte(*spte)) continue; - if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true)) + if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i])) break; } } -- GitLab From 19ace7d6ca15a4395dd294286fe253a233bbf20a Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 17 Feb 2023 07:53:21 +0800 Subject: [PATCH 0712/5631] KVM: x86/mmu: Skip calling mmu->sync_spte() when the spte is 0 Sync the spte only when the spte is set and avoid the indirect branch. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230216235321.735214-5-jiangshanlai@gmail.com [sean: add wrapper instead of open coding each check] Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 12 ++++++++++-- arch/x86/kvm/mmu/paging_tmpl.h | 2 +- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5bca99e50d1a..9b036a961847 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1933,6 +1933,14 @@ static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return true; } +static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) +{ + if (!sp->spt[i]) + return 0; + + return vcpu->arch.mmu->sync_spte(vcpu, sp, i); +} + static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { int flush = 0; @@ -1942,7 +1950,7 @@ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return -1; for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { - int ret = vcpu->arch.mmu->sync_spte(vcpu, sp, i); + int ret = kvm_sync_spte(vcpu, sp, i); if (ret < -1) return -1; @@ -5766,7 +5774,7 @@ static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu struct kvm_mmu_page *sp = sptep_to_sp(iterator.sptep); if (sp->unsync) { - int ret = mmu->sync_spte(vcpu, sp, iterator.index); + int ret = kvm_sync_spte(vcpu, sp, iterator.index); if (ret < 0) mmu_page_zap_pte(vcpu->kvm, sp, iterator.sptep, NULL); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 8ef67f76ee68..03a9577329fc 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -892,7 +892,7 @@ static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int gpa_t pte_gpa; gfn_t gfn; - if (!sp->spt[i]) + if (WARN_ON_ONCE(!sp->spt[i])) return 0; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); -- GitLab From 141705b78381ab1dcb52c84ebb396e434e86b624 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 13 Jan 2023 20:29:10 +0800 Subject: [PATCH 0713/5631] KVM: x86/mmu: Track tail count in pte_list_desc to optimize guest fork() Rework "struct pte_list_desc" and pte_list_{add|remove} to track the tail count, i.e. number of PTEs in non-head descriptors, and to always keep all tail descriptors full so that adding a new entry and counting the number of entries is done in constant time instead of linear time. No visible performace is changed in tests. But pte_list_add() is no longer shown in the perf result for the COWed pages even the guest forks millions of tasks. Signed-off-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230113122910.672417-1-jiangshanlai@gmail.com [sean: reword shortlog, tweak changelog, add lots of comments, add BUG_ON()] Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 109 ++++++++++++++++++++++++----------------- 1 file changed, 65 insertions(+), 44 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 9b036a961847..9655656dce50 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -125,17 +125,31 @@ module_param(dbg, bool, 0644); #define PTE_LIST_EXT 14 /* - * Slight optimization of cacheline layout, by putting `more' and `spte_count' - * at the start; then accessing it will only use one single cacheline for - * either full (entries==PTE_LIST_EXT) case or entries<=6. + * struct pte_list_desc is the core data structure used to implement a custom + * list for tracking a set of related SPTEs, e.g. all the SPTEs that map a + * given GFN when used in the context of rmaps. Using a custom list allows KVM + * to optimize for the common case where many GFNs will have at most a handful + * of SPTEs pointing at them, i.e. allows packing multiple SPTEs into a small + * memory footprint, which in turn improves runtime performance by exploiting + * cache locality. + * + * A list is comprised of one or more pte_list_desc objects (descriptors). + * Each individual descriptor stores up to PTE_LIST_EXT SPTEs. If a descriptor + * is full and a new SPTEs needs to be added, a new descriptor is allocated and + * becomes the head of the list. This means that by definitions, all tail + * descriptors are full. + * + * Note, the meta data fields are deliberately placed at the start of the + * structure to optimize the cacheline layout; accessing the descriptor will + * touch only a single cacheline so long as @spte_count<=6 (or if only the + * descriptors metadata is accessed). */ struct pte_list_desc { struct pte_list_desc *more; - /* - * Stores number of entries stored in the pte_list_desc. No need to be - * u64 but just for easier alignment. When PTE_LIST_EXT, means full. - */ - u64 spte_count; + /* The number of PTEs stored in _this_ descriptor. */ + u32 spte_count; + /* The number of PTEs stored in all tails of this descriptor. */ + u32 tail_count; u64 *sptes[PTE_LIST_EXT]; }; @@ -929,22 +943,25 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; desc->spte_count = 2; + desc->tail_count = 0; rmap_head->val = (unsigned long)desc | 1; ++count; } else { rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->spte_count == PTE_LIST_EXT) { - count += PTE_LIST_EXT; - if (!desc->more) { - desc->more = kvm_mmu_memory_cache_alloc(cache); - desc = desc->more; - desc->spte_count = 0; - break; - } - desc = desc->more; + count = desc->tail_count + desc->spte_count; + + /* + * If the previous head is full, allocate a new head descriptor + * as tail descriptors are always kept full. + */ + if (desc->spte_count == PTE_LIST_EXT) { + desc = kvm_mmu_memory_cache_alloc(cache); + desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->spte_count = 0; + desc->tail_count = count; + rmap_head->val = (unsigned long)desc | 1; } - count += desc->spte_count; desc->sptes[desc->spte_count++] = spte; } return count; @@ -952,30 +969,44 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, - struct pte_list_desc *desc, int i, - struct pte_list_desc *prev_desc) + struct pte_list_desc *desc, int i) { - int j = desc->spte_count - 1; + struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + int j = head_desc->spte_count - 1; - desc->sptes[i] = desc->sptes[j]; - desc->sptes[j] = NULL; - desc->spte_count--; - if (desc->spte_count) + /* + * The head descriptor should never be empty. A new head is added only + * when adding an entry and the previous head is full, and heads are + * removed (this flow) when they become empty. + */ + BUG_ON(j < 0); + + /* + * Replace the to-be-freed SPTE with the last valid entry from the head + * descriptor to ensure that tail descriptors are full at all times. + * Note, this also means that tail_count is stable for each descriptor. + */ + desc->sptes[i] = head_desc->sptes[j]; + head_desc->sptes[j] = NULL; + head_desc->spte_count--; + if (head_desc->spte_count) return; - if (!prev_desc && !desc->more) + + /* + * The head descriptor is empty. If there are no tail descriptors, + * nullify the rmap head to mark the list as emtpy, else point the rmap + * head at the next descriptor, i.e. the new head. + */ + if (!head_desc->more) rmap_head->val = 0; else - if (prev_desc) - prev_desc->more = desc->more; - else - rmap_head->val = (unsigned long)desc->more | 1; - mmu_free_pte_list_desc(desc); + rmap_head->val = (unsigned long)head_desc->more | 1; + mmu_free_pte_list_desc(head_desc); } static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; - struct pte_list_desc *prev_desc; int i; if (!rmap_head->val) { @@ -991,16 +1022,13 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) } else { rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - prev_desc = NULL; while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(rmap_head, - desc, i, prev_desc); + pte_list_desc_remove_entry(rmap_head, desc, i); return; } } - prev_desc = desc; desc = desc->more; } pr_err("%s: %p many->many\n", __func__, spte); @@ -1047,7 +1075,6 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm, unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; - unsigned int count = 0; if (!rmap_head->val) return 0; @@ -1055,13 +1082,7 @@ unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) return 1; desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - - while (desc) { - count += desc->spte_count; - desc = desc->more; - } - - return count; + return desc->tail_count + desc->spte_count; } static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, -- GitLab From aae9567a74878e5bb2bc084f6dee732f8d713e6b Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 17 Mar 2023 07:48:00 +0100 Subject: [PATCH 0714/5631] staging: vt6656: remove unused vnt_get_current_tsf() function The function vnt_get_current_tsf() is not used anywhere, remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230317064800.12276-1-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vt6656/card.c | 21 --------------------- drivers/staging/vt6656/card.h | 1 - 2 files changed, 22 deletions(-) diff --git a/drivers/staging/vt6656/card.c b/drivers/staging/vt6656/card.c index 7827e579ef3d..b9dc0d13c00c 100644 --- a/drivers/staging/vt6656/card.c +++ b/drivers/staging/vt6656/card.c @@ -11,7 +11,6 @@ * vnt_add_basic_rate - Add to BasicRateSet * vnt_ofdm_min_rate - Check if any OFDM rate is in BasicRateSet * vnt_get_tsf_offset - Calculate TSFOffset - * vnt_get_current_tsf - Read Current NIC TSF counter * vnt_get_next_tbtt - Calculate Next Beacon TSF counter * vnt_reset_next_tbtt - Set NIC Beacon time * vnt_update_next_tbtt - Sync. NIC Beacon time @@ -230,26 +229,6 @@ int vnt_adjust_tsf(struct vnt_private *priv, u8 rx_rate, MESSAGE_REQUEST_TSF, 0, 8, data); } -/* - * Description: Read NIC TSF counter - * Get local TSF counter - * - * Parameters: - * In: - * priv - The adapter to be read - * Out: - * current_tsf - Current TSF counter - * - * Return Value: true if success; otherwise false - * - */ -bool vnt_get_current_tsf(struct vnt_private *priv, u64 *current_tsf) -{ - *current_tsf = priv->current_tsf; - - return true; -} - /* * Description: Clear NIC TSF counter * Clear local TSF counter diff --git a/drivers/staging/vt6656/card.h b/drivers/staging/vt6656/card.h index be32c25c95de..eb01f7cc871f 100644 --- a/drivers/staging/vt6656/card.h +++ b/drivers/staging/vt6656/card.h @@ -30,7 +30,6 @@ void vnt_update_top_rates(struct vnt_private *priv); bool vnt_ofdm_min_rate(struct vnt_private *priv); int vnt_adjust_tsf(struct vnt_private *priv, u8 rx_rate, u64 time_stamp, u64 local_tsf); -bool vnt_get_current_tsf(struct vnt_private *priv, u64 *current_tsf); bool vnt_clear_current_tsf(struct vnt_private *priv); int vnt_reset_next_tbtt(struct vnt_private *priv, u16 beacon_interval); int vnt_update_next_tbtt(struct vnt_private *priv, u64 tsf, -- GitLab From d32a62ac84c2a3169b5686715280997e76a18549 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 17 Mar 2023 07:50:40 +0100 Subject: [PATCH 0715/5631] staging: vt6655: remove unused bb_power_save_mode_on() function The function bb_power_save_mode_on() is not used anywhere, remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230317065041.16635-2-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vt6655/baseband.c | 22 ---------------------- drivers/staging/vt6655/baseband.h | 1 - 2 files changed, 23 deletions(-) diff --git a/drivers/staging/vt6655/baseband.c b/drivers/staging/vt6655/baseband.c index 6ce41983dcf4..d7c3e4bec560 100644 --- a/drivers/staging/vt6655/baseband.c +++ b/drivers/staging/vt6655/baseband.c @@ -2171,28 +2171,6 @@ bb_software_reset(struct vnt_private *priv) bb_write_embedded(priv, 0x9C, 0); } -/* - * Description: Baseband Power Save Mode ON - * - * Parameters: - * In: - * iobase - I/O base address - * Out: - * none - * - * Return Value: none - * - */ -void -bb_power_save_mode_on(struct vnt_private *priv) -{ - unsigned char by_org_data; - - bb_read_embedded(priv, 0x0D, &by_org_data); - by_org_data |= BIT(0); - bb_write_embedded(priv, 0x0D, by_org_data); -} - /* * Description: Baseband Power Save Mode OFF * diff --git a/drivers/staging/vt6655/baseband.h b/drivers/staging/vt6655/baseband.h index 15b2802ed727..d1128d050ac5 100644 --- a/drivers/staging/vt6655/baseband.h +++ b/drivers/staging/vt6655/baseband.h @@ -63,7 +63,6 @@ void bb_set_vga_gain_offset(struct vnt_private *priv, unsigned char by_data); /* VT3253 Baseband */ bool bb_vt3253_init(struct vnt_private *priv); void bb_software_reset(struct vnt_private *priv); -void bb_power_save_mode_on(struct vnt_private *priv); void bb_power_save_mode_off(struct vnt_private *priv); void bb_set_tx_antenna_mode(struct vnt_private *priv, unsigned char by_antenna_mode); -- GitLab From 5001d664e328b4a07e2377f09d7a6871ce12bc01 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 17 Mar 2023 07:50:41 +0100 Subject: [PATCH 0716/5631] staging: vt6655: remove unused bb_power_save_mode_off() function The function bb_power_save_mode_off() is not used anywhere, remove it. Signed-off-by: Michael Straube Link: https://lore.kernel.org/r/20230317065041.16635-3-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vt6655/baseband.c | 22 ---------------------- drivers/staging/vt6655/baseband.h | 1 - 2 files changed, 23 deletions(-) diff --git a/drivers/staging/vt6655/baseband.c b/drivers/staging/vt6655/baseband.c index d7c3e4bec560..0e135af8316b 100644 --- a/drivers/staging/vt6655/baseband.c +++ b/drivers/staging/vt6655/baseband.c @@ -2171,28 +2171,6 @@ bb_software_reset(struct vnt_private *priv) bb_write_embedded(priv, 0x9C, 0); } -/* - * Description: Baseband Power Save Mode OFF - * - * Parameters: - * In: - * iobase - I/O base address - * Out: - * none - * - * Return Value: none - * - */ -void -bb_power_save_mode_off(struct vnt_private *priv) -{ - unsigned char by_org_data; - - bb_read_embedded(priv, 0x0D, &by_org_data); - by_org_data &= ~(BIT(0)); - bb_write_embedded(priv, 0x0D, by_org_data); -} - /* * Description: Set Tx Antenna mode * diff --git a/drivers/staging/vt6655/baseband.h b/drivers/staging/vt6655/baseband.h index d1128d050ac5..e4a02c240a1c 100644 --- a/drivers/staging/vt6655/baseband.h +++ b/drivers/staging/vt6655/baseband.h @@ -63,7 +63,6 @@ void bb_set_vga_gain_offset(struct vnt_private *priv, unsigned char by_data); /* VT3253 Baseband */ bool bb_vt3253_init(struct vnt_private *priv); void bb_software_reset(struct vnt_private *priv); -void bb_power_save_mode_off(struct vnt_private *priv); void bb_set_tx_antenna_mode(struct vnt_private *priv, unsigned char by_antenna_mode); void bb_set_rx_antenna_mode(struct vnt_private *priv, -- GitLab From 752cbd8f191678e86aa754f795546b7f06b7f171 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Fri, 17 Mar 2023 01:09:00 +0500 Subject: [PATCH 0717/5631] staging: axis-fifo: initialize timeouts in init only Initialize the module parameters, read_timeout and write_timeout once in init(). Module parameters can only be set once and cannot be modified later, so we don't need to evaluate them again when passing the parameters to wait_event_interruptible_timeout(). Convert datatype of {read,write}_timeout from 'int' to 'long int' because implicit conversion of 'long int' to 'int' in statement '{read,write}_timeout = MAX_SCHEDULE_TIMEOUT' results in an overflow. Change format specifier for {read,write}_timeout from %i to %li. Reviewed-by: Fabio M. De Francesco Suggested-by: Greg Kroah-Hartman Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZBN3XAsItCiTk7CV@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/axis-fifo/axis-fifo.c | 28 ++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index dfd2b357f484..0a85ea667a1b 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -103,17 +103,17 @@ * globals * ---------------------------- */ -static int read_timeout = 1000; /* ms to wait before read() times out */ -static int write_timeout = 1000; /* ms to wait before write() times out */ +static long read_timeout = 1000; /* ms to wait before read() times out */ +static long write_timeout = 1000; /* ms to wait before write() times out */ /* ---------------------------- * module command-line arguments * ---------------------------- */ -module_param(read_timeout, int, 0444); +module_param(read_timeout, long, 0444); MODULE_PARM_DESC(read_timeout, "ms to wait before blocking read() timing out; set to -1 for no timeout"); -module_param(write_timeout, int, 0444); +module_param(write_timeout, long, 0444); MODULE_PARM_DESC(write_timeout, "ms to wait before blocking write() timing out; set to -1 for no timeout"); /* ---------------------------- @@ -384,9 +384,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, mutex_lock(&fifo->read_lock); ret = wait_event_interruptible_timeout(fifo->read_queue, ioread32(fifo->base_addr + XLLF_RDFO_OFFSET), - (read_timeout >= 0) ? - msecs_to_jiffies(read_timeout) : - MAX_SCHEDULE_TIMEOUT); + read_timeout); if (ret <= 0) { if (ret == 0) { @@ -528,9 +526,7 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf, ret = wait_event_interruptible_timeout(fifo->write_queue, ioread32(fifo->base_addr + XLLF_TDFV_OFFSET) >= words_to_write, - (write_timeout >= 0) ? - msecs_to_jiffies(write_timeout) : - MAX_SCHEDULE_TIMEOUT); + write_timeout); if (ret <= 0) { if (ret == 0) { @@ -948,7 +944,17 @@ static struct platform_driver axis_fifo_driver = { static int __init axis_fifo_init(void) { - pr_info("axis-fifo driver loaded with parameters read_timeout = %i, write_timeout = %i\n", + if (read_timeout >= 0) + read_timeout = msecs_to_jiffies(read_timeout); + else + read_timeout = MAX_SCHEDULE_TIMEOUT; + + if (write_timeout >= 0) + write_timeout = msecs_to_jiffies(write_timeout); + else + write_timeout = MAX_SCHEDULE_TIMEOUT; + + pr_info("axis-fifo driver loaded with parameters read_timeout = %li, write_timeout = %li\n", read_timeout, write_timeout); return platform_driver_register(&axis_fifo_driver); } -- GitLab From f4a8e711a66bd03681d61949181223c3437d5a87 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Thu, 16 Mar 2023 22:24:55 -0700 Subject: [PATCH 0718/5631] Staging: octeon: Fix line ending with '(' Since the coding style limited the code to 80 columns per line which caused splitting the function header into two lines resulted in the first line ending with a '('. This caused the checkpatch error. Place the function parameters immediately after '(' in a single line to align the function header. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230317052455.GA83442@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/octeon/octeon-stubs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/octeon/octeon-stubs.h b/drivers/staging/octeon/octeon-stubs.h index 7a02e59e283f..3e7b92cd2e35 100644 --- a/drivers/staging/octeon/octeon-stubs.h +++ b/drivers/staging/octeon/octeon-stubs.h @@ -1372,9 +1372,7 @@ static inline void cvmx_fau_async_fetch_and_add32(uint64_t scraddr, int32_t value) { } -static inline union cvmx_gmxx_rxx_rx_inbnd cvmx_spi4000_check_speed( - int interface, - int port) +static inline union cvmx_gmxx_rxx_rx_inbnd cvmx_spi4000_check_speed(int interface, int port) { union cvmx_gmxx_rxx_rx_inbnd r; -- GitLab From 1150e181a14666a77dde80252f2b5cbaea69a498 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 15 Mar 2023 14:45:48 +0100 Subject: [PATCH 0719/5631] MIPS: sibyte: remove no longer needed board_mem_region With the direct use of memblock interface board_mem_region is no longer needed. Signed-off-by: Thomas Bogendoerfer --- arch/mips/sibyte/common/cfe.c | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 1a504294d85f..2503f60271e8 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -35,11 +35,6 @@ #endif #endif -#define SIBYTE_MAX_MEM_REGIONS 8 -phys_addr_t board_mem_region_addrs[SIBYTE_MAX_MEM_REGIONS]; -phys_addr_t board_mem_region_sizes[SIBYTE_MAX_MEM_REGIONS]; -unsigned int board_mem_region_count; - int cfe_cons_handle; #ifdef CONFIG_BLK_DEV_INITRD @@ -141,16 +136,6 @@ static __init void prom_meminit(void) size -= 512; memblock_add(addr, size); } - board_mem_region_addrs[board_mem_region_count] = addr; - board_mem_region_sizes[board_mem_region_count] = size; - board_mem_region_count++; - if (board_mem_region_count == - SIBYTE_MAX_MEM_REGIONS) { - /* - * Too many regions. Need to configure more - */ - while(1); - } } } #ifdef CONFIG_BLK_DEV_INITRD -- GitLab From b984d7b56dfcf71648102e227120bdc247562d00 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 15 Mar 2023 14:55:09 +0100 Subject: [PATCH 0720/5631] MIPS: sibyte: Remove unused config option SIBYTE_BCM1x55 SIBYTE_BCM1x55 is not selected anywhere, so let's get rid of it. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kbuild.platforms | 1 - arch/mips/sibyte/Kconfig | 13 +------------ arch/mips/sibyte/Makefile | 2 -- arch/mips/sibyte/Platform | 4 ---- arch/mips/sibyte/common/bus_watcher.c | 4 ++-- arch/mips/sibyte/common/cfe.c | 2 +- arch/mips/sibyte/common/sb_tbprof.c | 10 +++++----- arch/mips/sibyte/swarm/setup.c | 6 +++--- 8 files changed, 12 insertions(+), 30 deletions(-) diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms index 5d04438ee12e..caad195ba5c1 100644 --- a/arch/mips/Kbuild.platforms +++ b/arch/mips/Kbuild.platforms @@ -29,7 +29,6 @@ platform-$(CONFIG_SGI_IP30) += sgi-ip30/ platform-$(CONFIG_SGI_IP32) += sgi-ip32/ platform-$(CONFIG_SIBYTE_BCM112X) += sibyte/ platform-$(CONFIG_SIBYTE_SB1250) += sibyte/ -platform-$(CONFIG_SIBYTE_BCM1x55) += sibyte/ platform-$(CONFIG_SIBYTE_BCM1x80) += sibyte/ platform-$(CONFIG_SNI_RM) += sni/ platform-$(CONFIG_MACH_TX49XX) += txx9/ diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig index 470d46183677..c437bc02dd08 100644 --- a/arch/mips/sibyte/Kconfig +++ b/arch/mips/sibyte/Kconfig @@ -58,16 +58,6 @@ config SIBYTE_BCM1x80 select SIBYTE_SB1xxx_SOC select SYS_SUPPORTS_SMP -config SIBYTE_BCM1x55 - bool - select CEVT_BCM1480 - select CSRC_BCM1480 - select HAVE_PCI - select IRQ_MIPS_CPU - select SIBYTE_SB1xxx_SOC - select SIBYTE_HAS_ZBUS_PROFILING - select SYS_SUPPORTS_SMP - config SIBYTE_SB1xxx_SOC bool select IRQ_MIPS_CPU @@ -143,8 +133,7 @@ config SIBYTE_CFE_CONSOLE config SIBYTE_BUS_WATCHER bool "Support for Bus Watcher statistics" depends on SIBYTE_SB1xxx_SOC && \ - (SIBYTE_BCM112X || SIBYTE_SB1250 || \ - SIBYTE_BCM1x55 || SIBYTE_BCM1x80) + (SIBYTE_BCM112X || SIBYTE_SB1250 || SIBYTE_BCM1x80) help Handle and keep statistics on the bus error interrupts (COR_ECC, BAD_ECC, IO_BUS). diff --git a/arch/mips/sibyte/Makefile b/arch/mips/sibyte/Makefile index d015c4d79c3e..ca0d57824d56 100644 --- a/arch/mips/sibyte/Makefile +++ b/arch/mips/sibyte/Makefile @@ -6,8 +6,6 @@ obj-$(CONFIG_SIBYTE_BCM112X) += sb1250/ obj-$(CONFIG_SIBYTE_BCM112X) += common/ obj-$(CONFIG_SIBYTE_SB1250) += sb1250/ obj-$(CONFIG_SIBYTE_SB1250) += common/ -obj-$(CONFIG_SIBYTE_BCM1x55) += bcm1480/ -obj-$(CONFIG_SIBYTE_BCM1x55) += common/ obj-$(CONFIG_SIBYTE_BCM1x80) += bcm1480/ obj-$(CONFIG_SIBYTE_BCM1x80) += common/ diff --git a/arch/mips/sibyte/Platform b/arch/mips/sibyte/Platform index 65b2225b76b2..304b4d16dfbf 100644 --- a/arch/mips/sibyte/Platform +++ b/arch/mips/sibyte/Platform @@ -13,10 +13,6 @@ cflags-$(CONFIG_SIBYTE_SB1250) += \ -I$(srctree)/arch/mips/include/asm/mach-sibyte \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1250_112x_ALL -cflags-$(CONFIG_SIBYTE_BCM1x55) += \ - -I$(srctree)/arch/mips/include/asm/mach-sibyte \ - -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1480_ALL - cflags-$(CONFIG_SIBYTE_BCM1x80) += \ -I$(srctree)/arch/mips/include/asm/mach-sibyte \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1480_ALL diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c index d43291473f76..a296d2c51841 100644 --- a/arch/mips/sibyte/common/bus_watcher.c +++ b/arch/mips/sibyte/common/bus_watcher.c @@ -24,7 +24,7 @@ #include #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #endif @@ -71,7 +71,7 @@ void check_bus_watcher(void) #if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250) /* Use non-destructive register */ status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS_DEBUG)); -#elif defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#elif defined(CONFIG_SIBYTE_BCM1x80) /* Use non-destructive register */ /* Same as 1250 except BUS_ERR_STATUS_DEBUG is in a different place. */ status = csr_in32(IOADDR(A_BCM1480_BUS_ERR_STATUS_DEBUG)); diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 2503f60271e8..2cb90dbbe843 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -295,7 +295,7 @@ void __init prom_init(void) #if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250) register_smp_ops(&sb_smp_ops); #endif -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 register_smp_ops(&bcm1480_smp_ops); #endif } diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c index bc47681e825a..004a08469a39 100644 --- a/arch/mips/sibyte/common/sb_tbprof.c +++ b/arch/mips/sibyte/common/sb_tbprof.c @@ -23,7 +23,7 @@ #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #include #include @@ -35,7 +35,7 @@ #error invalid SiByte UART configuration #endif -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #undef K_INT_TRACE_FREEZE #define K_INT_TRACE_FREEZE K_BCM1480_INT_TRACE_FREEZE #undef K_INT_PERF_CNT @@ -157,7 +157,7 @@ static void arm_tb(void) * a previous interrupt request. This means that bus profiling * requires ALL of the SCD perf counters. */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq((scdperfcnt & ~M_SPC_CFG_SRC1) | /* keep counters 0,2,3,4,5,6,7 as is */ V_SPC_CFG_SRC1(1), /* counter 1 counts cycles */ @@ -290,7 +290,7 @@ static int sbprof_zbprof_start(struct file *filp) * pass them through. I am exploiting my knowledge that * cp0_status masks out IP[5]. krw */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq(K_BCM1480_INT_MAP_I3, IOADDR(A_BCM1480_IMR_REGISTER(0, R_BCM1480_IMR_INTERRUPT_MAP_BASE_L) + ((K_BCM1480_INT_PERF_CNT & 0x3f) << 3))); @@ -343,7 +343,7 @@ static int sbprof_zbprof_start(struct file *filp) __raw_writeq(0, IOADDR(A_SCD_TRACE_SEQUENCE_7)); /* Now indicate the PERF_CNT interrupt as a trace-relevant interrupt */ -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 __raw_writeq(1ULL << (K_BCM1480_INT_PERF_CNT & 0x3f), IOADDR(A_BCM1480_IMR_REGISTER(0, R_BCM1480_IMR_INTERRUPT_TRACE_L))); #else diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 72a31eeeebba..9e7a1e305f61 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -24,7 +24,7 @@ #include #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 #include #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) #include @@ -34,7 +34,7 @@ #include #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 extern void bcm1480_setup(void); #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) extern void sb1250_setup(void); @@ -114,7 +114,7 @@ int update_persistent_clock64(struct timespec64 now) void __init plat_mem_setup(void) { -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#ifdef CONFIG_SIBYTE_BCM1x80 bcm1480_setup(); #elif defined(CONFIG_SIBYTE_SB1250) || defined(CONFIG_SIBYTE_BCM112X) sb1250_setup(); -- GitLab From a0136c28a2d8e03d0cb2f707cd1c837a8e0884e9 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 15 Mar 2023 15:12:02 +0100 Subject: [PATCH 0721/5631] MIPS: sibyte: Remove Sibyte CARMEL and CRHINE board support Looks like these boards were nether in active use, so let's remove them. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 18 ----------- arch/mips/include/asm/sibyte/board.h | 6 +--- arch/mips/include/asm/sibyte/carmel.h | 45 --------------------------- arch/mips/include/asm/sibyte/swarm.h | 5 --- arch/mips/sibyte/Kconfig | 9 ------ arch/mips/sibyte/Makefile | 4 --- arch/mips/sibyte/Platform | 4 --- arch/mips/sibyte/swarm/setup.c | 6 ---- 8 files changed, 1 insertion(+), 96 deletions(-) delete mode 100644 arch/mips/include/asm/sibyte/carmel.h diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 6f275ace27be..88afd252bcc3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -794,24 +794,6 @@ config SGI_IP32 help If you want this kernel to run on SGI O2 workstation, say Y here. -config SIBYTE_CRHINE - bool "Sibyte BCM91120C-CRhine" - select BOOT_ELF32 - select SIBYTE_BCM1120 - select SWAP_IO_SPACE - select SYS_HAS_CPU_SB1 - select SYS_SUPPORTS_BIG_ENDIAN - select SYS_SUPPORTS_LITTLE_ENDIAN - -config SIBYTE_CARMEL - bool "Sibyte BCM91120x-Carmel" - select BOOT_ELF32 - select SIBYTE_BCM1120 - select SWAP_IO_SPACE - select SYS_HAS_CPU_SB1 - select SYS_SUPPORTS_BIG_ENDIAN - select SYS_SUPPORTS_LITTLE_ENDIAN - config SIBYTE_CRHONE bool "Sibyte BCM91125C-CRhone" select BOOT_ELF32 diff --git a/arch/mips/include/asm/sibyte/board.h b/arch/mips/include/asm/sibyte/board.h index 20fe2f16c97e..03463faa4244 100644 --- a/arch/mips/include/asm/sibyte/board.h +++ b/arch/mips/include/asm/sibyte/board.h @@ -7,7 +7,7 @@ #define _SIBYTE_BOARD_H #if defined(CONFIG_SIBYTE_SWARM) || defined(CONFIG_SIBYTE_CRHONE) || \ - defined(CONFIG_SIBYTE_CRHINE) || defined(CONFIG_SIBYTE_LITTLESUR) + defined(CONFIG_SIBYTE_LITTLESUR) #include #endif @@ -15,10 +15,6 @@ #include #endif -#ifdef CONFIG_SIBYTE_CARMEL -#include -#endif - #ifdef CONFIG_SIBYTE_BIGSUR #include #endif diff --git a/arch/mips/include/asm/sibyte/carmel.h b/arch/mips/include/asm/sibyte/carmel.h deleted file mode 100644 index c6730d7a6392..000000000000 --- a/arch/mips/include/asm/sibyte/carmel.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2002 Broadcom Corporation - */ -#ifndef __ASM_SIBYTE_CARMEL_H -#define __ASM_SIBYTE_CARMEL_H - -#include -#include - -#define SIBYTE_BOARD_NAME "Carmel" - -#define GPIO_PHY_INTERRUPT 2 -#define GPIO_NONMASKABLE_INT 3 -#define GPIO_CF_INSERTED 6 -#define GPIO_MONTEREY_RESET 7 -#define GPIO_QUADUART_INT 8 -#define GPIO_CF_INT 9 -#define GPIO_FPGA_CCLK 10 -#define GPIO_FPGA_DOUT 11 -#define GPIO_FPGA_DIN 12 -#define GPIO_FPGA_PGM 13 -#define GPIO_FPGA_DONE 14 -#define GPIO_FPGA_INIT 15 - -#define LEDS_CS 2 -#define LEDS_PHYS 0x100C0000 -#define MLEDS_CS 3 -#define MLEDS_PHYS 0x100A0000 -#define UART_CS 4 -#define UART_PHYS 0x100D0000 -#define ARAVALI_CS 5 -#define ARAVALI_PHYS 0x11000000 -#define IDE_CS 6 -#define IDE_PHYS 0x100B0000 -#define ARAVALI2_CS 7 -#define ARAVALI2_PHYS 0x100E0000 - -#if defined(CONFIG_SIBYTE_CARMEL) -#define K_GPIO_GB_IDE 9 -#define K_INT_GB_IDE (K_INT_GPIO_0 + K_GPIO_GB_IDE) -#endif - - -#endif /* __ASM_SIBYTE_CARMEL_H */ diff --git a/arch/mips/include/asm/sibyte/swarm.h b/arch/mips/include/asm/sibyte/swarm.h index 947122f487ed..49ea7a645c15 100644 --- a/arch/mips/include/asm/sibyte/swarm.h +++ b/arch/mips/include/asm/sibyte/swarm.h @@ -24,11 +24,6 @@ #define SIBYTE_HAVE_PCMCIA 0 #define SIBYTE_HAVE_IDE 0 #endif -#ifdef CONFIG_SIBYTE_CRHINE -#define SIBYTE_BOARD_NAME "BCM91120C (CRhine)" -#define SIBYTE_HAVE_PCMCIA 0 -#define SIBYTE_HAVE_IDE 0 -#endif /* Generic bus chip selects */ #define LEDS_CS 3 diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig index c437bc02dd08..c4596d49edf1 100644 --- a/arch/mips/sibyte/Kconfig +++ b/arch/mips/sibyte/Kconfig @@ -10,15 +10,6 @@ config SIBYTE_SB1250 select SIBYTE_SB1xxx_SOC select SYS_SUPPORTS_SMP -config SIBYTE_BCM1120 - bool - select CEVT_SB1250 - select CSRC_SB1250 - select IRQ_MIPS_CPU - select SIBYTE_BCM112X - select SIBYTE_HAS_ZBUS_PROFILING - select SIBYTE_SB1xxx_SOC - config SIBYTE_BCM1125 bool select CEVT_SB1250 diff --git a/arch/mips/sibyte/Makefile b/arch/mips/sibyte/Makefile index ca0d57824d56..47078353fe8a 100644 --- a/arch/mips/sibyte/Makefile +++ b/arch/mips/sibyte/Makefile @@ -10,15 +10,11 @@ obj-$(CONFIG_SIBYTE_BCM1x80) += bcm1480/ obj-$(CONFIG_SIBYTE_BCM1x80) += common/ # -# Sibyte BCM91120x (Carmel) board -# Sibyte BCM91120C (CRhine) board # Sibyte BCM91125C (CRhone) board # Sibyte BCM91125E (Rhone) board # Sibyte SWARM board # Sibyte BCM91x80 (BigSur) board # -obj-$(CONFIG_SIBYTE_CARMEL) += swarm/ -obj-$(CONFIG_SIBYTE_CRHINE) += swarm/ obj-$(CONFIG_SIBYTE_CRHONE) += swarm/ obj-$(CONFIG_SIBYTE_RHONE) += swarm/ obj-$(CONFIG_SIBYTE_SENTOSA) += swarm/ diff --git a/arch/mips/sibyte/Platform b/arch/mips/sibyte/Platform index 304b4d16dfbf..937108e41f13 100644 --- a/arch/mips/sibyte/Platform +++ b/arch/mips/sibyte/Platform @@ -18,16 +18,12 @@ cflags-$(CONFIG_SIBYTE_BCM1x80) += \ -DSIBYTE_HDR_FEATURES=SIBYTE_HDR_FMASK_1480_ALL # -# Sibyte BCM91120x (Carmel) board -# Sibyte BCM91120C (CRhine) board # Sibyte BCM91125C (CRhone) board # Sibyte BCM91125E (Rhone) board # Sibyte BCM91250A (SWARM) board # Sibyte BCM91250C2 (LittleSur) board # Sibyte BCM91x80 (BigSur) board # -load-$(CONFIG_SIBYTE_CARMEL) := 0xffffffff80100000 -load-$(CONFIG_SIBYTE_CRHINE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_CRHONE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_RHONE) := 0xffffffff80100000 load-$(CONFIG_SIBYTE_SENTOSA) := 0xffffffff80100000 diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 9e7a1e305f61..76683993cdd3 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -146,12 +146,6 @@ void __init plat_mem_setup(void) #ifdef LEDS_PHYS -#ifdef CONFIG_SIBYTE_CARMEL -/* XXXKW need to detect Monterey/LittleSur/etc */ -#undef LEDS_PHYS -#define LEDS_PHYS MLEDS_PHYS -#endif - void setleds(char *str) { void *reg; -- GitLab From 0345234720ca5601b59f20570f71139f5ad4d229 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 15 Mar 2023 15:21:24 +0100 Subject: [PATCH 0722/5631] MIPS: sibyte: Replace BCM1125H with SB1250 option SIBYTE_BCM1125H is identical to SIBYTE_SB1250, so remove one of them. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 +- arch/mips/sibyte/Kconfig | 11 ----------- 2 files changed, 1 insertion(+), 12 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 88afd252bcc3..fd7ed68cdb91 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -807,7 +807,7 @@ config SIBYTE_CRHONE config SIBYTE_RHONE bool "Sibyte BCM91125E-Rhone" select BOOT_ELF32 - select SIBYTE_BCM1125H + select SIBYTE_SB1250 select SWAP_IO_SPACE select SYS_HAS_CPU_SB1 select SYS_SUPPORTS_BIG_ENDIAN diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig index c4596d49edf1..5fb92fe84149 100644 --- a/arch/mips/sibyte/Kconfig +++ b/arch/mips/sibyte/Kconfig @@ -20,17 +20,6 @@ config SIBYTE_BCM1125 select SIBYTE_HAS_ZBUS_PROFILING select SIBYTE_SB1xxx_SOC -config SIBYTE_BCM1125H - bool - select CEVT_SB1250 - select CSRC_SB1250 - select HAVE_PCI - select IRQ_MIPS_CPU - select SIBYTE_BCM112X - select SIBYTE_ENABLE_LDT_IF_PCI - select SIBYTE_HAS_ZBUS_PROFILING - select SIBYTE_SB1xxx_SOC - config SIBYTE_BCM112X bool select CEVT_SB1250 -- GitLab From a45e5fe792349315827b483eb23b307df47c6c6c Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 16 Mar 2023 12:49:52 +0100 Subject: [PATCH 0723/5631] MIPS: ath79: remove obsolete ATH79_DEV_* configs Commit 85b9686dae30 ("MIPS: ath79: drop platform device registration code") removes all files arch/mips/ath79/dev-*.[ch], adjusts the Makefile, but misses to adjust the Kconfig file. Hence, since then, the configs ATH79_DEV_* are really dead. Commit 3a77e0d75eed ("MIPS: ath79: drop machfiles") already removes all configs that select ATH79_DEV_* config. So at that point, they was not a way to enable them with a kernel build configuration. Remove these obsolete ATH79_DEV_* configs. Signed-off-by: Lukas Bulwahn Signed-off-by: Thomas Bogendoerfer --- arch/mips/ath79/Kconfig | 16 ---------------- 1 file changed, 16 deletions(-) diff --git a/arch/mips/ath79/Kconfig b/arch/mips/ath79/Kconfig index 7367416642cb..04154128c4de 100644 --- a/arch/mips/ath79/Kconfig +++ b/arch/mips/ath79/Kconfig @@ -29,20 +29,4 @@ config SOC_QCA955X config PCI_AR724X def_bool n -config ATH79_DEV_GPIO_BUTTONS - def_bool n - -config ATH79_DEV_LEDS_GPIO - def_bool n - -config ATH79_DEV_SPI - def_bool n - -config ATH79_DEV_USB - def_bool n - -config ATH79_DEV_WMAC - depends on (SOC_AR913X || SOC_AR933X || SOC_AR934X || SOC_QCA955X) - def_bool n - endif -- GitLab From 5af7a77acd0ff23fe06d93c3c7d0e0aa7a264fa7 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 10 Mar 2023 20:36:17 -0800 Subject: [PATCH 0724/5631] Input: hideep - clean up some inconsistent indenting Turn the space into a tab to Eliminate the follow smatch warning: drivers/input/touchscreen/hideep.c:470 hideep_program_nvm() warn: inconsistent indenting Reported-by: Abaci Robot Signed-off-by: Yang Li Link: https://lore.kernel.org/r/20220429070103.4747-1-yang.lee@linux.alibaba.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/hideep.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index bd454d93f1f7..05998e83c36a 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -467,9 +467,9 @@ static int hideep_program_nvm(struct hideep_ts *ts, u32 addr = 0; int error; - error = hideep_nvm_unlock(ts); - if (error) - return error; + error = hideep_nvm_unlock(ts); + if (error) + return error; while (ucode_len > 0) { xfer_len = min_t(size_t, ucode_len, HIDEEP_NVM_PAGE_SIZE); -- GitLab From 10b0a455f4378330de41e280ce7839997d24297d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 17 Mar 2023 03:48:07 -0700 Subject: [PATCH 0725/5631] Input: hideep - silence error in SW_RESET() On some models the first HIDEEP_SYSCON_WDT_CON write alone is enough to cause the controller to reset, causing the second write to fail: i2c-hideep_ts: write to register 0x52000014 (0x000001) failed: -121 Switch this write to a raw hideep_pgm_w_mem() to avoid an error getting logged in this case. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230311114726.182789-2-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/hideep.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index 05998e83c36a..b47feb63cfb8 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -271,9 +271,14 @@ static int hideep_pgm_w_reg(struct hideep_ts *ts, u32 addr, u32 val) #define SW_RESET_IN_PGM(clk) \ { \ + __be32 data = cpu_to_be32(0x01); \ hideep_pgm_w_reg(ts, HIDEEP_SYSCON_WDT_CNT, (clk)); \ hideep_pgm_w_reg(ts, HIDEEP_SYSCON_WDT_CON, 0x03); \ - hideep_pgm_w_reg(ts, HIDEEP_SYSCON_WDT_CON, 0x01); \ + /* \ + * The first write may already cause a reset, use a raw \ + * write for the second write to avoid error logging. \ + */ \ + hideep_pgm_w_mem(ts, HIDEEP_SYSCON_WDT_CON, &data, 1); \ } #define SET_FLASH_PIO(ce) \ -- GitLab From 007e50eb5dbe7b33a43a1449a0d9c29e8dcf1c67 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 17 Mar 2023 03:50:27 -0700 Subject: [PATCH 0726/5631] Input: hideep - optionally reset controller work mode to native HiDeep protocol The HiDeep IST940E touchscreen controller used on the Lenovo Yoga Book X90F convertible comes up in HID mode by default. This works well on the X91F Windows model where the touchscreen is correctly described in ACPI and ACPI takes care of controlling the reset GPIO and regulators. But the X90F ships with Android and the ACPI tables on this model don't describe the touchscreen. Instead this is hardcoded in the vendor kernel. The vendor kernel uses the touchscreen in native HiDeep 20 (2.0?) protocol mode and switches the controller to this mode by writing 0 to reg 0x081e. Adjusting the i2c-hid code to deal with the reset-gpio and regulators on this non devicetree (but rather broken ACPI) convertible is somewhat tricky and the native protocol reports ABS_MT_PRESSURE and ABS_MT_TOUCH_MAJOR which are not reported in HID mode, so it is preferable to use the native mode. Add support to the hideep driver to reset the work-mode to the native HiDeep protocol to allow using it on the Lenovo Yoga Book X90F. This is guarded behind a new "hideep,force-native-protocol" boolean property, to avoid changing behavior on other devices. For the record: I did test using the i2c-hid driver with some quick hacks and it does work. The I2C-HID descriptor is available from address 0x0020, just like on the X91F Windows model. So far the new "hideep,force-native-protocol" property is only used on x86/ACPI (non devicetree) devs. IOW it is not used in actual devicetree files. The devicetree-bindings maintainers have requested properties like these to not be added to the devicetree-bindings, so the new property is deliberately not added to the existing devicetree-bindings. Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230311114726.182789-3-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/hideep.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/input/touchscreen/hideep.c b/drivers/input/touchscreen/hideep.c index b47feb63cfb8..7c7020099b0f 100644 --- a/drivers/input/touchscreen/hideep.c +++ b/drivers/input/touchscreen/hideep.c @@ -35,6 +35,7 @@ #define HIDEEP_EVENT_ADDR 0x240 /* command list */ +#define HIDEEP_WORK_MODE 0x081e #define HIDEEP_RESET_CMD 0x9800 /* event bit */ @@ -964,6 +965,21 @@ static const struct attribute_group hideep_ts_attr_group = { .attrs = hideep_ts_sysfs_entries, }; +static void hideep_set_work_mode(struct hideep_ts *ts) +{ + /* + * Reset touch report format to the native HiDeep 20 protocol if requested. + * This is necessary to make touchscreens which come up in I2C-HID mode + * work with this driver. + * + * Note this is a kernel internal device-property set by x86 platform code, + * this MUST not be used in devicetree files without first adding it to + * the DT bindings. + */ + if (device_property_read_bool(&ts->client->dev, "hideep,force-native-protocol")) + regmap_write(ts->reg, HIDEEP_WORK_MODE, 0x00); +} + static int hideep_suspend(struct device *dev) { struct i2c_client *client = to_i2c_client(dev); @@ -987,6 +1003,8 @@ static int hideep_resume(struct device *dev) return error; } + hideep_set_work_mode(ts); + enable_irq(client->irq); return 0; @@ -1063,6 +1081,8 @@ static int hideep_probe(struct i2c_client *client) return error; } + hideep_set_work_mode(ts); + error = hideep_init_input(ts); if (error) return error; -- GitLab From 12c7d0aeb3beecc8b8f570d82c4d8509def71a6e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 20:27:10 -0800 Subject: [PATCH 0727/5631] Input: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to of_property_read_bool(). Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144708.1542751-1-robh@kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/matrix_keypad.c | 6 ++---- drivers/input/keyboard/omap4-keypad.c | 3 +-- drivers/input/keyboard/samsung-keypad.c | 3 +-- drivers/input/keyboard/tegra-kbc.c | 3 +-- 4 files changed, 5 insertions(+), 10 deletions(-) diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 203310727d88..a1b037891af2 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -425,14 +425,12 @@ matrix_keypad_parse_dt(struct device *dev) return ERR_PTR(-EINVAL); } - if (of_get_property(np, "linux,no-autorepeat", NULL)) - pdata->no_autorepeat = true; + pdata->no_autorepeat = of_property_read_bool(np, "linux,no-autorepeat"); pdata->wakeup = of_property_read_bool(np, "wakeup-source") || of_property_read_bool(np, "linux,wakeup"); /* legacy */ - if (of_get_property(np, "gpio-activelow", NULL)) - pdata->active_low = true; + pdata->active_low = of_property_read_bool(np, "gpio-activelow"); pdata->drive_inactive_cols = of_property_read_bool(np, "drive-inactive-cols"); diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c index 4426120398b0..9f085d5679db 100644 --- a/drivers/input/keyboard/omap4-keypad.c +++ b/drivers/input/keyboard/omap4-keypad.c @@ -274,8 +274,7 @@ static int omap4_keypad_parse_dt(struct device *dev, if (err) return err; - if (of_get_property(np, "linux,input-no-autorepeat", NULL)) - keypad_data->no_autorepeat = true; + keypad_data->no_autorepeat = of_property_read_bool(np, "linux,input-no-autorepeat"); return 0; } diff --git a/drivers/input/keyboard/samsung-keypad.c b/drivers/input/keyboard/samsung-keypad.c index 09e883ea1352..d85dd2489293 100644 --- a/drivers/input/keyboard/samsung-keypad.c +++ b/drivers/input/keyboard/samsung-keypad.c @@ -291,8 +291,7 @@ samsung_keypad_parse_dt(struct device *dev) *keymap++ = KEY(row, col, key_code); } - if (of_get_property(np, "linux,input-no-autorepeat", NULL)) - pdata->no_autorepeat = true; + pdata->no_autorepeat = of_property_read_bool(np, "linux,input-no-autorepeat"); pdata->wakeup = of_property_read_bool(np, "wakeup-source") || /* legacy name */ diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index da4019cf0c83..d5a6c7d8eb25 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -504,8 +504,7 @@ static int tegra_kbc_parse_dt(struct tegra_kbc *kbc) if (!of_property_read_u32(np, "nvidia,repeat-delay-ms", &prop)) kbc->repeat_cnt = prop; - if (of_find_property(np, "nvidia,needs-ghost-filter", NULL)) - kbc->use_ghost_filter = true; + kbc->use_ghost_filter = of_property_present(np, "nvidia,needs-ghost-filter"); if (of_property_read_bool(np, "wakeup-source") || of_property_read_bool(np, "nvidia,wakeup-source")) /* legacy */ -- GitLab From eaedf192f65fc4e3e2001b8e09940386cc494bd5 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 20:26:21 -0800 Subject: [PATCH 0728/5631] Input: zinitix - use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144708.1542682-1-robh@kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/zinitix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/zinitix.c b/drivers/input/touchscreen/zinitix.c index cdf9bcd744db..b6ece47151b8 100644 --- a/drivers/input/touchscreen/zinitix.c +++ b/drivers/input/touchscreen/zinitix.c @@ -260,7 +260,7 @@ static int zinitix_init_regulators(struct bt541_ts_data *bt541) * so check if "vddo" is present and in that case use these names. * Else use the proper supply names on the component. */ - if (of_find_property(dev->of_node, "vddo-supply", NULL)) { + if (of_property_present(dev->of_node, "vddo-supply")) { bt541->supplies[0].supply = "vdd"; bt541->supplies[1].supply = "vddo"; } else { -- GitLab From bb5e4f3e1abf0e45d2d7b96875f05fa81fa1de0f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Mar 2023 04:14:33 -0700 Subject: [PATCH 0729/5631] Input: st-keyscan - drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/input/keyboard/st-keyscan.c:251:34: error: ‘keyscan_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312131514.351603-1-krzysztof.kozlowski@linaro.org Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/st-keyscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/keyboard/st-keyscan.c b/drivers/input/keyboard/st-keyscan.c index b6e83324f97a..0d27324af809 100644 --- a/drivers/input/keyboard/st-keyscan.c +++ b/drivers/input/keyboard/st-keyscan.c @@ -259,7 +259,7 @@ static struct platform_driver keyscan_device_driver = { .driver = { .name = "st-keyscan", .pm = pm_sleep_ptr(&keyscan_dev_pm_ops), - .of_match_table = of_match_ptr(keyscan_of_match), + .of_match_table = keyscan_of_match, } }; -- GitLab From 27e54d5193b914f5c29108adffdf10a253b8b40e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Mar 2023 04:14:50 -0700 Subject: [PATCH 0730/5631] Input: tm2-touchkey - drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/input/keyboard/tm2-touchkey.c:335:34: error: ‘tm2_touchkey_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312131514.351603-2-krzysztof.kozlowski@linaro.org Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/tm2-touchkey.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/keyboard/tm2-touchkey.c b/drivers/input/keyboard/tm2-touchkey.c index 6627e65f06e5..4e20571cb4c3 100644 --- a/drivers/input/keyboard/tm2-touchkey.c +++ b/drivers/input/keyboard/tm2-touchkey.c @@ -354,7 +354,7 @@ static struct i2c_driver tm2_touchkey_driver = { .driver = { .name = TM2_TOUCHKEY_DEV_NAME, .pm = pm_sleep_ptr(&tm2_touchkey_pm_ops), - .of_match_table = of_match_ptr(tm2_touchkey_of_match), + .of_match_table = tm2_touchkey_of_match, }, .probe_new = tm2_touchkey_probe, .id_table = tm2_touchkey_id_table, -- GitLab From f92dd6d074555edfe499ef6667a25b286e312ee3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Mar 2023 04:15:11 -0700 Subject: [PATCH 0731/5631] Input: sun4i-ts - drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/input/touchscreen/sun4i-ts.c:392:34: error: ‘sun4i_ts_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230312131514.351603-3-krzysztof.kozlowski@linaro.org Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/sun4i-ts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c index 73eb8f80be6e..b990c951c486 100644 --- a/drivers/input/touchscreen/sun4i-ts.c +++ b/drivers/input/touchscreen/sun4i-ts.c @@ -400,7 +400,7 @@ MODULE_DEVICE_TABLE(of, sun4i_ts_of_match); static struct platform_driver sun4i_ts_driver = { .driver = { .name = "sun4i-ts", - .of_match_table = of_match_ptr(sun4i_ts_of_match), + .of_match_table = sun4i_ts_of_match, }, .probe = sun4i_ts_probe, .remove = sun4i_ts_remove, -- GitLab From f1e96f0617fc578f74319a5ba46473773035594f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Mar 2023 04:15:49 -0700 Subject: [PATCH 0732/5631] Input: bcm_iproc_tsc - drop of_match_ptr for ID table The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312131514.351603-4-krzysztof.kozlowski@linaro.org Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/bcm_iproc_tsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/touchscreen/bcm_iproc_tsc.c b/drivers/input/touchscreen/bcm_iproc_tsc.c index 35e2fe9911a4..9c84235327bf 100644 --- a/drivers/input/touchscreen/bcm_iproc_tsc.c +++ b/drivers/input/touchscreen/bcm_iproc_tsc.c @@ -511,7 +511,7 @@ static struct platform_driver iproc_ts_driver = { .probe = iproc_ts_probe, .driver = { .name = IPROC_TS_NAME, - .of_match_table = of_match_ptr(iproc_ts_of_match), + .of_match_table = iproc_ts_of_match, }, }; -- GitLab From eff37b5ea3d92c9d33a7e543460a565d17909ae4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:16 +0200 Subject: [PATCH 0733/5631] serial: Use ARRAY_SIZE() with iso7816 reserved array MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of a literal, size the for loop iteration based on the actual array using ARRAY_SIZE(). Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 2bd32c8ece39..ee2aabcc8943 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1491,7 +1492,7 @@ static int uart_set_iso7816_config(struct uart_port *port, * There are 5 words reserved for future use. Check that userspace * doesn't put stuff in there to prevent breakages in the future. */ - for (i = 0; i < 5; i++) + for (i = 0; i < ARRAY_SIZE(iso7816.reserved); i++) if (iso7816.reserved[i]) return -EINVAL; -- GitLab From 807fccf71939f10855a0256f0c999d665b80263f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:17 +0200 Subject: [PATCH 0734/5631] serial: Use B0 instead of implicit zero assumption MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Compare against B0 rather than assume B0 equals zero, which is true for all archs but explicit B0 makes the code more obvious. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ee2aabcc8943..296d2c33ea7a 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1662,10 +1662,10 @@ static void uart_set_termios(struct tty_struct *tty, cflag = tty->termios.c_cflag; /* Handle transition to B0 status */ - if ((old_termios->c_cflag & CBAUD) && !(cflag & CBAUD)) + if (((old_termios->c_cflag & CBAUD) != B0) && ((cflag & CBAUD) == B0)) uart_clear_mctrl(uport, TIOCM_RTS | TIOCM_DTR); /* Handle transition away from B0 status */ - else if (!(old_termios->c_cflag & CBAUD) && (cflag & CBAUD)) { + else if (((old_termios->c_cflag & CBAUD) == B0) && ((cflag & CBAUD) != B0)) { unsigned int mask = TIOCM_DTR; if (!(cflag & CRTSCTS) || !tty_throttled(tty)) -- GitLab From 6229ad9913ac794233fdb3ed20f1e899add0af6b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:18 +0200 Subject: [PATCH 0735/5631] serial: Remove extern from func prototypes in headers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove unnecessary externs from function prototypes in serial_8250.h and serial_core.h. Suggested-by: Jiri Slaby Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 41 ++++++++++++++++--------------------- include/linux/serial_core.h | 13 ++++++------ 2 files changed, 24 insertions(+), 30 deletions(-) diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 741ed4807a9c..6f78f302d272 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -151,26 +151,22 @@ void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); -extern int early_serial_setup(struct uart_port *port); - -extern int early_serial8250_setup(struct earlycon_device *device, - const char *options); -extern void serial8250_update_uartclk(struct uart_port *port, - unsigned int uartclk); -extern void serial8250_do_set_termios(struct uart_port *port, - struct ktermios *termios, const struct ktermios *old); -extern void serial8250_do_set_ldisc(struct uart_port *port, - struct ktermios *termios); -extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); -extern int serial8250_do_startup(struct uart_port *port); -extern void serial8250_do_shutdown(struct uart_port *port); -extern void serial8250_do_pm(struct uart_port *port, unsigned int state, - unsigned int oldstate); -extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); -extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, - unsigned int quot_frac); -extern int fsl8250_handle_irq(struct uart_port *port); +int early_serial_setup(struct uart_port *port); +int early_serial8250_setup(struct earlycon_device *device, const char *options); + +void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk); +void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, + const struct ktermios *old); +void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios); +unsigned int serial8250_do_get_mctrl(struct uart_port *port); +int serial8250_do_startup(struct uart_port *port); +void serial8250_do_shutdown(struct uart_port *port); +void serial8250_do_pm(struct uart_port *port, unsigned int state, + unsigned int oldstate); +void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); +void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, unsigned int quot_frac); +int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); @@ -183,9 +179,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); -extern void serial8250_set_isa_configurator(void (*v) - (int port, struct uart_port *up, - u32 *capabilities)); +void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, + u32 *capabilities)); #ifdef CONFIG_SERIAL_8250_RT288X unsigned int au_serial_in(struct uart_port *p, int offset); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9e3e5e0d11b2..05d18a145b3a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -812,9 +812,8 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) -extern int of_setup_earlycon(const struct earlycon_id *match, - unsigned long node, - const char *options); +int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, + const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; @@ -897,11 +896,11 @@ static inline bool uart_softcts_mode(struct uart_port *uport) * The following are helper functions for the low level drivers. */ -extern void uart_handle_dcd_change(struct uart_port *uport, bool active); -extern void uart_handle_cts_change(struct uart_port *uport, bool active); +void uart_handle_dcd_change(struct uart_port *uport, bool active); +void uart_handle_cts_change(struct uart_port *uport, bool active); -extern void uart_insert_char(struct uart_port *port, unsigned int status, - unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_insert_char(struct uart_port *port, unsigned int status, + unsigned int overrun, unsigned int ch, unsigned int flag); void uart_xchar_out(struct uart_port *uport, int offset); -- GitLab From 8e90cf29aef77b59ed6a6f6466add2af79621f26 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:19 +0200 Subject: [PATCH 0736/5631] serial: Move uart_change_speed() earlier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move uart_change_speed() earlier to get rid of its forward declaration. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 94 ++++++++++++++++---------------- 1 file changed, 46 insertions(+), 48 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 296d2c33ea7a..7201bbc44fa7 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -49,8 +49,6 @@ static struct lock_class_key port_lock_key; */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ -static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, - const struct ktermios *old_termios); static void uart_wait_until_sent(struct tty_struct *tty, int timeout); static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); @@ -178,6 +176,52 @@ static void uart_port_dtr_rts(struct uart_port *uport, bool active) uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } +/* Caller holds port mutex */ +static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, + const struct ktermios *old_termios) +{ + struct uart_port *uport = uart_port_check(state); + struct ktermios *termios; + int hw_stopped; + + /* + * If we have no tty, termios, or the port does not exist, + * then we can't set the parameters for this port. + */ + if (!tty || uport->type == PORT_UNKNOWN) + return; + + termios = &tty->termios; + uport->ops->set_termios(uport, termios, old_termios); + + /* + * Set modem status enables based on termios cflag + */ + spin_lock_irq(&uport->lock); + if (termios->c_cflag & CRTSCTS) + uport->status |= UPSTAT_CTS_ENABLE; + else + uport->status &= ~UPSTAT_CTS_ENABLE; + + if (termios->c_cflag & CLOCAL) + uport->status &= ~UPSTAT_DCD_ENABLE; + else + uport->status |= UPSTAT_DCD_ENABLE; + + /* reset sw-assisted CTS flow control based on (possibly) new mode */ + hw_stopped = uport->hw_stopped; + uport->hw_stopped = uart_softcts_mode(uport) && + !(uport->ops->get_mctrl(uport) & TIOCM_CTS); + if (uport->hw_stopped) { + if (!hw_stopped) + uport->ops->stop_tx(uport); + } else { + if (hw_stopped) + __uart_start(tty); + } + spin_unlock_irq(&uport->lock); +} + /* * Startup the port. This will be called once per open. All calls * will be serialised by the per-port mutex. @@ -486,52 +530,6 @@ uart_get_divisor(struct uart_port *port, unsigned int baud) } EXPORT_SYMBOL(uart_get_divisor); -/* Caller holds port mutex */ -static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, - const struct ktermios *old_termios) -{ - struct uart_port *uport = uart_port_check(state); - struct ktermios *termios; - int hw_stopped; - - /* - * If we have no tty, termios, or the port does not exist, - * then we can't set the parameters for this port. - */ - if (!tty || uport->type == PORT_UNKNOWN) - return; - - termios = &tty->termios; - uport->ops->set_termios(uport, termios, old_termios); - - /* - * Set modem status enables based on termios cflag - */ - spin_lock_irq(&uport->lock); - if (termios->c_cflag & CRTSCTS) - uport->status |= UPSTAT_CTS_ENABLE; - else - uport->status &= ~UPSTAT_CTS_ENABLE; - - if (termios->c_cflag & CLOCAL) - uport->status &= ~UPSTAT_DCD_ENABLE; - else - uport->status |= UPSTAT_DCD_ENABLE; - - /* reset sw-assisted CTS flow control based on (possibly) new mode */ - hw_stopped = uport->hw_stopped; - uport->hw_stopped = uart_softcts_mode(uport) && - !(uport->ops->get_mctrl(uport) & TIOCM_CTS); - if (uport->hw_stopped) { - if (!hw_stopped) - uport->ops->stop_tx(uport); - } else { - if (hw_stopped) - __uart_start(tty); - } - spin_unlock_irq(&uport->lock); -} - static int uart_put_char(struct tty_struct *tty, unsigned char c) { struct uart_state *state = tty->driver_data; -- GitLab From 826736a6c7c8c3185bfb10e03c10d03d53d6cf94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:20 +0200 Subject: [PATCH 0737/5631] serial: Rename uart_change_speed() to uart_change_line_settings() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit uart_change_speed() changes more than just speed so rename it to more generic uart_change_line_settings(). Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-6-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 7201bbc44fa7..ecdc5d9cdb53 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -177,8 +177,8 @@ static void uart_port_dtr_rts(struct uart_port *uport, bool active) } /* Caller holds port mutex */ -static void uart_change_speed(struct tty_struct *tty, struct uart_state *state, - const struct ktermios *old_termios) +static void uart_change_line_settings(struct tty_struct *tty, struct uart_state *state, + const struct ktermios *old_termios) { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; @@ -277,7 +277,7 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, /* * Initialise the hardware port settings. */ - uart_change_speed(tty, state, NULL); + uart_change_line_settings(tty, state, NULL); /* * Setup the RTS and DTR signals once the @@ -993,7 +993,7 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, current->comm, tty_name(port->tty)); } - uart_change_speed(tty, state, NULL); + uart_change_line_settings(tty, state, NULL); } } else { retval = uart_startup(tty, state, true); @@ -1655,7 +1655,7 @@ static void uart_set_termios(struct tty_struct *tty, goto out; } - uart_change_speed(tty, state, old_termios); + uart_change_line_settings(tty, state, old_termios); /* reload cflag from termios; port driver may have overridden flags */ cflag = tty->termios.c_cflag; @@ -2451,7 +2451,7 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) ret = ops->startup(uport); if (ret == 0) { if (tty) - uart_change_speed(tty, state, NULL); + uart_change_line_settings(tty, state, NULL); spin_lock_irq(&uport->lock); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); -- GitLab From b5def43a7b3e7e68d6b49a23166f8b886a26bb54 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:21 +0200 Subject: [PATCH 0738/5631] serial: Make hw_stopped bool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert hw_stopped in uart_port to bool because its more appropriate type for how it is used. Also convert the local variable in uart_change_line_settings() caching old hw_stopped to bool. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 6 +++--- include/linux/serial_core.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ecdc5d9cdb53..31b69e61e71d 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -182,7 +182,7 @@ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; - int hw_stopped; + bool hw_stopped; /* * If we have no tty, termios, or the port does not exist, @@ -3304,13 +3304,13 @@ void uart_handle_cts_change(struct uart_port *uport, bool active) if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { if (active) { - uport->hw_stopped = 0; + uport->hw_stopped = false; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { if (!active) { - uport->hw_stopped = 1; + uport->hw_stopped = true; uport->ops->stop_tx(uport); } } diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 05d18a145b3a..66ecec15a1bf 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -553,7 +553,7 @@ struct uart_port { #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) - int hw_stopped; /* sw-assisted CTS flow state */ + bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ -- GitLab From 1690ca513da18b1f7de89c39faf78278d302b867 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:22 +0200 Subject: [PATCH 0739/5631] serial: Rename hw_stopped to old_hw_stopped & improve logic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hw_stopped in uart_change_line_settings() stores old hw_stopped, thus rename it appropriately. Alter logic to check first if the hw_stopped was changed, and then pick which function to call if it was because the logic is more obvious that way. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-8-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 31b69e61e71d..c494cb39394b 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -182,7 +182,7 @@ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; - bool hw_stopped; + bool old_hw_stopped; /* * If we have no tty, termios, or the port does not exist, @@ -209,14 +209,13 @@ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state uport->status |= UPSTAT_DCD_ENABLE; /* reset sw-assisted CTS flow control based on (possibly) new mode */ - hw_stopped = uport->hw_stopped; + old_hw_stopped = uport->hw_stopped; uport->hw_stopped = uart_softcts_mode(uport) && !(uport->ops->get_mctrl(uport) & TIOCM_CTS); - if (uport->hw_stopped) { - if (!hw_stopped) + if (uport->hw_stopped != old_hw_stopped) { + if (!old_hw_stopped) uport->ops->stop_tx(uport); - } else { - if (hw_stopped) + else __uart_start(tty); } spin_unlock_irq(&uport->lock); -- GitLab From 044498cd89a1a580a3145b2c5fb34d5e2f3b9908 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:09:23 +0200 Subject: [PATCH 0740/5631] serial: Remove uart_wait_until_sent() forward declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove unnecessary forward declaration of uart_wait_until_sent(). Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309080923.11778-9-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index c494cb39394b..db7f6c0c39bf 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -49,7 +49,6 @@ static struct lock_class_key port_lock_key; */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ -static void uart_wait_until_sent(struct tty_struct *tty, int timeout); static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); -- GitLab From b8abba0eb1f5b8a05e864cf00f246e1c066775a2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:28 +0200 Subject: [PATCH 0741/5631] n_tty: Convert no_space_left to space_left boolean MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The no_space_left variable is only assigned with 0 and 1. Change its type to boolean and move negation from its name into the check. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index c8f56c9b1a1c..4fc5bd166e56 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -625,7 +625,7 @@ static size_t __process_echoes(struct tty_struct *tty) c = echo_buf(ldata, tail); if (c == ECHO_OP_START) { unsigned char op; - int no_space_left = 0; + bool space_left = true; /* * Since add_echo_byte() is called without holding @@ -664,7 +664,7 @@ static size_t __process_echoes(struct tty_struct *tty) num_bs = 8 - (num_chars & 7); if (num_bs > space) { - no_space_left = 1; + space_left = false; break; } space -= num_bs; @@ -690,7 +690,7 @@ static size_t __process_echoes(struct tty_struct *tty) case ECHO_OP_START: /* This is an escaped echo op start code */ if (!space) { - no_space_left = 1; + space_left = false; break; } tty_put_char(tty, ECHO_OP_START); @@ -710,7 +710,7 @@ static size_t __process_echoes(struct tty_struct *tty) * */ if (space < 2) { - no_space_left = 1; + space_left = false; break; } tty_put_char(tty, '^'); @@ -720,7 +720,7 @@ static size_t __process_echoes(struct tty_struct *tty) tail += 2; } - if (no_space_left) + if (!space_left) break; } else { if (O_OPOST(tty)) { -- GitLab From 0b05223bdf6058b96a596609c50a18c7b010224d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:29 +0200 Subject: [PATCH 0742/5631] tty_ioctl: Use BIT() for internal flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert internal flags to use BIT(). Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ioctl.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 12983ce4e43e..32ff9959b565 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -7,6 +7,7 @@ * discipline handling modules (like SLIP). */ +#include #include #include #include @@ -40,10 +41,10 @@ /* * Internal flag options for termios setting behavior */ -#define TERMIOS_FLUSH 1 -#define TERMIOS_WAIT 2 -#define TERMIOS_TERMIO 4 -#define TERMIOS_OLD 8 +#define TERMIOS_FLUSH BIT(0) +#define TERMIOS_WAIT BIT(1) +#define TERMIOS_TERMIO BIT(2) +#define TERMIOS_OLD BIT(3) /** -- GitLab From 38b6b621018ec954d6265cef23976df53f953ddb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:30 +0200 Subject: [PATCH 0743/5631] Bluetooth: hci_ldisc: Fix tty_set_termios() return value assumptions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tty_set_termios() never returns anything else than 0. Make the debug prints to look directly into the new termios instead to check CRTSCTS state. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-4-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_ldisc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 865112e96ff9..efdda2c3fce8 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -323,9 +323,9 @@ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) /* Disable hardware flow control */ ktermios = tty->termios; ktermios.c_cflag &= ~CRTSCTS; - status = tty_set_termios(tty, &ktermios); + tty_set_termios(tty, &ktermios); BT_DBG("Disabling hardware flow control: %s", - status ? "failed" : "success"); + (tty->termios.c_cflag & CRTSCTS) ? "failed" : "success"); /* Clear RTS to prevent the device from sending */ /* Most UARTs need OUT2 to enable interrupts */ @@ -357,9 +357,9 @@ void hci_uart_set_flow_control(struct hci_uart *hu, bool enable) /* Re-enable hardware flow control */ ktermios = tty->termios; ktermios.c_cflag |= CRTSCTS; - status = tty_set_termios(tty, &ktermios); + tty_set_termios(tty, &ktermios); BT_DBG("Enabling hardware flow control: %s", - status ? "failed" : "success"); + !(tty->termios.c_cflag & CRTSCTS) ? "failed" : "success"); } } -- GitLab From 9db1be84054b7445f911b9efe9bc3c924ffdb543 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:31 +0200 Subject: [PATCH 0744/5631] n_tty: Sort includes alphabetically MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sort includes in n_tty alphabetically to make it easier to see if an include is among the list or not. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-5-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 4fc5bd166e56..2cf263de1366 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -28,27 +28,28 @@ * EAGAIN */ -#include -#include +#include +#include +#include #include -#include #include -#include +#include #include -#include -#include -#include +#include #include -#include -#include -#include -#include -#include -#include -#include #include +#include #include +#include +#include +#include +#include +#include +#include +#include +#include #include + #include "tty.h" /* -- GitLab From 7e26c84d02d17e7412e6f2471916fd415654a1ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:32 +0200 Subject: [PATCH 0745/5631] n_tty: Use DIV_ROUND_UP() in room calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When PARMRK is set, a character can result in up to 3 chars in the read buffer. Receive code calculates for how many characters there (at least) is room. Convert an opencoded rounding in the calculation to use DIV_ROUND_UP(). Note: the room variable is decremented afterwards by one which ensures the characters will fit into the buffer for real so the code is okay despite rounding upwards. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-6-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 2cf263de1366..6d754fc35dce 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -1692,7 +1693,7 @@ n_tty_receive_buf_common(struct tty_struct *tty, const unsigned char *cp, room = N_TTY_BUF_SIZE - (ldata->read_head - tail); if (I_PARMRK(tty)) - room = (room + 2) / 3; + room = DIV_ROUND_UP(room, 3); room--; if (room <= 0) { overflow = ldata->icanon && ldata->canon_head == tail; -- GitLab From 8ed012d1be12c183e173c9e0933b34a7073a9c8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:33 +0200 Subject: [PATCH 0746/5631] n_tty: Cleanup includes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit n_tty uses: - bitmap_zero() from linux/bitmap.h - EXPORT_SYMBOL_GPL() from linux/export.h - jiffies, time_after() from linux/jiffies.h Add includes. n_tty uses nothing from: - linux/audit.h - linux/interrupt.h - linux/major.h - linux/mm.h - linux/module.h - linux/timer.h Remove those includes. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-7-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 6d754fc35dce..0481e57077f1 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -28,24 +28,21 @@ * EAGAIN */ -#include +#include #include #include #include +#include #include #include -#include -#include +#include #include -#include -#include #include #include #include #include #include #include -#include #include #include #include -- GitLab From 37e8b08ada22f5cd4a8e94f6e783d00cd6e6d7e6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:34 +0200 Subject: [PATCH 0747/5631] n_tty: Reindent if condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Align if condition to make it easier to read. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230309082035.14880-8-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 0481e57077f1..1c9e5d2ea7de 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1176,7 +1176,7 @@ static void n_tty_receive_overrun(struct tty_struct *tty) ldata->num_overrun++; if (time_after(jiffies, ldata->overrun_time + HZ) || - time_after(ldata->overrun_time, jiffies)) { + time_after(ldata->overrun_time, jiffies)) { tty_warn(tty, "%d input overrun(s)\n", ldata->num_overrun); ldata->overrun_time = jiffies; ldata->num_overrun = 0; -- GitLab From 035173c91c6b53144295a5b546c6bad3f40fb8a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Thu, 9 Mar 2023 10:20:35 +0200 Subject: [PATCH 0748/5631] tty: Convert hw_stopped in tty_struct to bool MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hw_stopped in tty_struct is used like bool, convert the variable type to bool. Signed-off-by: Ilpo Järvinen Acked-by: Ulf Hansson # For MMC Link: https://lore.kernel.org/r/20230309082035.14880-9-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/pcmcia/synclink_cs.c | 6 +++--- drivers/mmc/core/sdio_uart.c | 10 +++++----- drivers/tty/amiserial.c | 6 +++--- drivers/tty/mxser.c | 6 +++--- drivers/tty/synclink_gt.c | 6 +++--- include/linux/tty.h | 2 +- 6 files changed, 18 insertions(+), 18 deletions(-) diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 6ddfeb2fe98f..97c5bfb9d58a 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -1060,7 +1060,7 @@ static void cts_change(MGSLPC_INFO *info, struct tty_struct *tty) if (info->serial_signals & SerialSignal_CTS) { if (debug_level >= DEBUG_LEVEL_ISR) printk("CTS tx start..."); - tty->hw_stopped = 0; + tty->hw_stopped = false; tx_start(info, tty); info->pending_bh |= BH_TRANSMIT; return; @@ -1069,7 +1069,7 @@ static void cts_change(MGSLPC_INFO *info, struct tty_struct *tty) if (!(info->serial_signals & SerialSignal_CTS)) { if (debug_level >= DEBUG_LEVEL_ISR) printk("CTS tx stop..."); - tty->hw_stopped = 1; + tty->hw_stopped = true; tx_stop(info); } } @@ -2312,7 +2312,7 @@ static void mgslpc_set_termios(struct tty_struct *tty, /* Handle turning off CRTSCTS */ if (old_termios->c_cflag & CRTSCTS && !C_CRTSCTS(tty)) { - tty->hw_stopped = 0; + tty->hw_stopped = false; tx_release(tty); } } diff --git a/drivers/mmc/core/sdio_uart.c b/drivers/mmc/core/sdio_uart.c index 50536fe59f1a..aa659758563f 100644 --- a/drivers/mmc/core/sdio_uart.c +++ b/drivers/mmc/core/sdio_uart.c @@ -478,13 +478,13 @@ static void sdio_uart_check_modem_status(struct sdio_uart_port *port) int cts = (status & UART_MSR_CTS); if (tty->hw_stopped) { if (cts) { - tty->hw_stopped = 0; + tty->hw_stopped = false; sdio_uart_start_tx(port); tty_wakeup(tty); } } else { if (!cts) { - tty->hw_stopped = 1; + tty->hw_stopped = true; sdio_uart_stop_tx(port); } } @@ -633,7 +633,7 @@ static int sdio_uart_activate(struct tty_port *tport, struct tty_struct *tty) if (C_CRTSCTS(tty)) if (!(sdio_uart_get_mctrl(port) & TIOCM_CTS)) - tty->hw_stopped = 1; + tty->hw_stopped = true; clear_bit(TTY_IO_ERROR, &tty->flags); @@ -882,14 +882,14 @@ static void sdio_uart_set_termios(struct tty_struct *tty, /* Handle turning off CRTSCTS */ if ((old_termios->c_cflag & CRTSCTS) && !(cflag & CRTSCTS)) { - tty->hw_stopped = 0; + tty->hw_stopped = false; sdio_uart_start_tx(port); } /* Handle turning on CRTSCTS */ if (!(old_termios->c_cflag & CRTSCTS) && (cflag & CRTSCTS)) { if (!(sdio_uart_get_mctrl(port) & TIOCM_CTS)) { - tty->hw_stopped = 1; + tty->hw_stopped = true; sdio_uart_stop_tx(port); } } diff --git a/drivers/tty/amiserial.c b/drivers/tty/amiserial.c index d7515d61659e..c06ad0a0744b 100644 --- a/drivers/tty/amiserial.c +++ b/drivers/tty/amiserial.c @@ -347,7 +347,7 @@ static void check_modem_status(struct serial_state *info) #if (defined(SERIAL_DEBUG_INTR) || defined(SERIAL_DEBUG_FLOW)) printk("CTS tx start..."); #endif - port->tty->hw_stopped = 0; + port->tty->hw_stopped = false; info->IER |= UART_IER_THRI; amiga_custom.intena = IF_SETCLR | IF_TBE; mb(); @@ -362,7 +362,7 @@ static void check_modem_status(struct serial_state *info) #if (defined(SERIAL_DEBUG_INTR) || defined(SERIAL_DEBUG_FLOW)) printk("CTS tx stop..."); #endif - port->tty->hw_stopped = 1; + port->tty->hw_stopped = true; info->IER &= ~UART_IER_THRI; /* disable Tx interrupt and remove any pending interrupts */ amiga_custom.intena = IF_TBE; @@ -1197,7 +1197,7 @@ static void rs_set_termios(struct tty_struct *tty, const struct ktermios *old_te /* Handle turning off CRTSCTS */ if ((old_termios->c_cflag & CRTSCTS) && !C_CRTSCTS(tty)) { - tty->hw_stopped = 0; + tty->hw_stopped = false; rs_start(tty); } diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index ef3116e87975..10855e66fda1 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -553,7 +553,7 @@ static void mxser_handle_cts(struct tty_struct *tty, struct mxser_port *info, if (tty->hw_stopped) { if (cts) { - tty->hw_stopped = 0; + tty->hw_stopped = false; if (!mxser_16550A_or_MUST(info)) __mxser_start_tx(info); @@ -563,7 +563,7 @@ static void mxser_handle_cts(struct tty_struct *tty, struct mxser_port *info, } else if (cts) return; - tty->hw_stopped = 1; + tty->hw_stopped = true; if (!mxser_16550A_or_MUST(info)) __mxser_stop_tx(info); } @@ -1361,7 +1361,7 @@ static void mxser_set_termios(struct tty_struct *tty, spin_unlock_irqrestore(&info->slock, flags); if ((old_termios->c_cflag & CRTSCTS) && !C_CRTSCTS(tty)) { - tty->hw_stopped = 0; + tty->hw_stopped = false; mxser_start(tty); } diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 33f258d6fef9..543b3224dce9 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -730,7 +730,7 @@ static void set_termios(struct tty_struct *tty, /* Handle turning off CRTSCTS */ if ((old_termios->c_cflag & CRTSCTS) && !C_CRTSCTS(tty)) { - tty->hw_stopped = 0; + tty->hw_stopped = false; tx_release(tty); } } @@ -1953,13 +1953,13 @@ static void cts_change(struct slgt_info *info, unsigned short status) if (info->port.tty) { if (info->port.tty->hw_stopped) { if (info->signals & SerialSignal_CTS) { - info->port.tty->hw_stopped = 0; + info->port.tty->hw_stopped = false; info->pending_bh |= BH_TRANSMIT; return; } } else { if (!(info->signals & SerialSignal_CTS)) - info->port.tty->hw_stopped = 1; + info->port.tty->hw_stopped = true; } } } diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..60871a9d3212 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -227,7 +227,7 @@ struct tty_struct { unsigned long unused[0]; } __aligned(sizeof(unsigned long)) ctrl; - int hw_stopped; + bool hw_stopped; unsigned int receive_room; int flow_change; -- GitLab From 15ac1122fd6d4bf408a03e6f23c7ad4f60b22f9e Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 9 Mar 2023 11:02:24 -0800 Subject: [PATCH 0749/5631] serial: 8250_bcm7271: Fix arbitration handling The arbitration of the UART DMA is mishandled for a few exceptional cases when probing and releasing the driver. It is possible that the DMA register spaces are not defined in device tree for an instance of the driver, so attempts to access the registers in brcmuart_arbitration() would use NULL pointers. It is also possible for the probe function to return an error while still holding the UART DMA. This would prevent the UART DMA from being claimed by an instance that could use it. These errors are addressed by only releasing the UART DMA if it is held by this instance (i.e. priv->dma_enabled == 1) and directing early error paths in probe to this common release_dma handling. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20230309190224.687380-1-opendmb@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_bcm7271.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index ed5a94747692..f801b1f5b46c 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1014,14 +1014,16 @@ static int brcmuart_probe(struct platform_device *pdev) /* See if a Baud clock has been specified */ baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); if (IS_ERR(baud_mux_clk)) { - if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto release_dma; + } dev_dbg(dev, "BAUD MUX clock not specified\n"); } else { dev_dbg(dev, "BAUD MUX clock found\n"); ret = clk_prepare_enable(baud_mux_clk); if (ret) - return ret; + goto release_dma; priv->baud_mux_clk = baud_mux_clk; init_real_clk_rates(dev, priv); clk_rate = priv->default_mux_rate; @@ -1029,7 +1031,8 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); - return -EINVAL; + ret = -EINVAL; + goto release_dma; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1116,7 +1119,9 @@ static int brcmuart_probe(struct platform_device *pdev) serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); - brcmuart_arbitration(priv, 0); +release_dma: + if (priv->dma_enabled) + brcmuart_arbitration(priv, 0); return ret; } @@ -1128,7 +1133,8 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); - brcmuart_arbitration(priv, 0); + if (priv->dma_enabled) + brcmuart_arbitration(priv, 0); return 0; } -- GitLab From 410e7088e971ad656170fe9768b072b267a95310 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 13 Mar 2023 13:31:00 +0200 Subject: [PATCH 0750/5631] devres: Pass unique name of the resource to devm_add_action_or_reset() All the same as it's done in the commit e32c80bbd2f9 ("devres: Pass unique name of the resource to devm_add_action()") applies to the devm_add_action_or_reset(), which this change makes real. This helps with debug resource management. Reported-and-tested-by: Mirsad Goran Todorovac Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230313113100.59643-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/include/linux/device.h b/include/linux/device.h index 0f128520f6e5..12dc08aa5c0f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -250,17 +250,19 @@ int __devm_add_action(struct device *dev, void (*action)(void *), void *data, co #define devm_add_action(release, action, data) \ __devm_add_action(release, action, data, #action) -static inline int devm_add_action_or_reset(struct device *dev, - void (*action)(void *), void *data) +static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), + void *data, const char *name) { int ret; - ret = devm_add_action(dev, action, data); + ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } +#define devm_add_action_or_reset(release, action, data) \ + __devm_add_action_or_reset(release, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu -- GitLab From 984063339e9ec9b6d9b011169d1f330a505a7571 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 11 Mar 2023 03:14:46 +0000 Subject: [PATCH 0751/5631] kobject: define common logging prefix MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All log messages start with the prefix "kobject: ". Deduplicate this by using the pr_fmt() facility. This makes the very long log strings shorter. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230311-kobject-warning-v1-1-1ebba4f71fb5@weissschuh.net Signed-off-by: Greg Kroah-Hartman --- lib/kobject.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/lib/kobject.c b/lib/kobject.c index 6e2f0bee3560..09c81ffb8b33 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -10,6 +10,8 @@ * about using the kobject interface. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -127,7 +129,7 @@ static int fill_kobj_path(const struct kobject *kobj, char *path, int length) *(path + --length) = '/'; } - pr_debug("kobject: '%s' (%p): %s: path = '%s'\n", kobject_name(kobj), + pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; @@ -223,7 +225,7 @@ static int kobject_add_internal(struct kobject *kobj) kobj->parent = parent; } - pr_debug("kobject: '%s' (%p): %s: parent: '%s', set: '%s'\n", + pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "", kobj->kset ? kobject_name(&kobj->kset->kobj) : ""); @@ -359,7 +361,7 @@ static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { - pr_err("kobject: can not set name properly!\n"); + pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; @@ -588,7 +590,7 @@ static void __kobject_del(struct kobject *kobj) /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { - pr_debug("kobject: '%s' (%p): auto cleanup 'remove' event\n", + pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } @@ -658,16 +660,16 @@ static void kobject_cleanup(struct kobject *kobj) const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; - pr_debug("kobject: '%s' (%p): %s, parent %p\n", + pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) - pr_debug("kobject: '%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", + pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { - pr_debug("kobject: '%s' (%p): auto cleanup kobject_del\n", + pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { @@ -676,14 +678,14 @@ static void kobject_cleanup(struct kobject *kobj) } if (t && t->release) { - pr_debug("kobject: '%s' (%p): calling ktype release\n", + pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { - pr_debug("kobject: '%s': free name\n", name); + pr_debug("'%s': free name\n", name); kfree_const(name); } @@ -703,8 +705,8 @@ static void kobject_release(struct kref *kref) struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); - pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n", - kobject_name(kobj), kobj, __func__, kobj->parent, delay); + pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", + kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); @@ -733,7 +735,7 @@ EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { - pr_debug("kobject: (%p): %s\n", kobj, __func__); + pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } @@ -910,7 +912,7 @@ EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); - pr_debug("kobject: '%s' (%p): %s\n", + pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } -- GitLab From 64414da25baf3acf31350f75fdd10514bd8390b1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 11 Mar 2023 03:14:47 +0000 Subject: [PATCH 0752/5631] kobject: align stacktrace levels to logging message MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without an explicit level the stacktraces are printed at a default level. If this level does not match the one from the logging level it may happen that the stacktrace is shown without the message or vice versa. Both these cases are confusing, so make sure the user always sees both, the message and the stacktrace. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230311-kobject-warning-v1-2-1ebba4f71fb5@weissschuh.net Signed-off-by: Greg Kroah-Hartman --- lib/kobject.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/kobject.c b/lib/kobject.c index 09c81ffb8b33..f79a434e1231 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -340,7 +340,7 @@ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); - dump_stack(); + dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); @@ -349,7 +349,7 @@ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) error: pr_err("kobject (%p): %s\n", kobj, err_str); - dump_stack(); + dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); @@ -413,7 +413,7 @@ int kobject_add(struct kobject *kobj, struct kobject *parent, if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); - dump_stack(); + dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); -- GitLab From 4a46ac9d64030d9f6f18baaf115a3558880c1ae2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:32 +0100 Subject: [PATCH 0753/5631] driver core: class: specify the module owner in __class_register() There's no need to manually have to set the module owner of a class, the compiler should do it automatically for you, so add a module * to the __class_register() function and allow it to set the module owner automatically. This will let us move the module pointer out of struct class eventually, as it should not be embedded in there if we wish for it to be a read-only structure eventually. And, funny story, this module pointer isn't even being used for anything, so while we will keep it around for now, it's not like it even matters. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 6 +++--- include/linux/device/class.h | 9 +++++---- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 5983eead8391..90dc5788957a 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -154,7 +154,7 @@ static void class_remove_groups(struct class *cls, return sysfs_remove_groups(&cls->p->subsys.kobj, groups); } -int __class_register(struct class *cls, struct lock_class_key *key) +int __class_register(struct class *cls, struct module *owner, struct lock_class_key *key) { struct subsys_private *cp; int error; @@ -187,6 +187,7 @@ int __class_register(struct class *cls, struct lock_class_key *key) if (error) goto err_out; + cls->owner = owner; error = class_add_groups(class_get(cls), cls->class_groups); class_put(cls); if (error) { @@ -244,10 +245,9 @@ struct class *__class_create(struct module *owner, const char *name, } cls->name = name; - cls->owner = owner; cls->class_release = class_create_release; - retval = __class_register(cls, key); + retval = __class_register(cls, owner, key); if (retval) goto error; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 42cc3fb44a84..d1ba4ee235dc 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -85,15 +85,16 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; extern int __must_check __class_register(struct class *class, + struct module *owner, struct lock_class_key *key); extern void class_unregister(struct class *class); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ +#define class_register(class) \ +({ \ + static struct lock_class_key __key; \ + __class_register(class, THIS_MODULE, &__key); \ }) struct class_compat; -- GitLab From 10a03c36b7dd7759788ebc613091d313b60f93e0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:33 +0100 Subject: [PATCH 0754/5631] drivers: remove struct module * setting from struct class There is no need to manually set the owner of a struct class, as the registering function does it automatically, so remove all of the explicit settings from various drivers that did so as it is unneeded. This allows us to remove this pointer entirely from this structure going forward. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/vpe-mt.c | 1 - drivers/base/core.c | 1 - drivers/base/devcoredump.c | 1 - drivers/block/pktcdvd.c | 1 - drivers/block/zram/zram_drv.c | 1 - drivers/gpio/gpiolib-sysfs.c | 2 -- drivers/hwmon/hwmon.c | 1 - drivers/isdn/mISDN/core.c | 1 - drivers/media/pci/ddbridge/ddbridge-core.c | 1 - drivers/mfd/cros_ec_dev.c | 1 - drivers/misc/enclosure.c | 1 - drivers/mtd/mtdcore.c | 1 - drivers/mtd/ubi/build.c | 1 - drivers/mux/core.c | 1 - drivers/net/ipvlan/ipvtap.c | 1 - drivers/net/macvtap.c | 1 - drivers/nvme/host/fc.c | 1 - drivers/platform/chrome/wilco_ec/event.c | 1 - drivers/platform/chrome/wilco_ec/telemetry.c | 1 - drivers/platform/x86/intel/pmt/class.c | 1 - drivers/platform/x86/intel_scu_ipc.c | 1 - drivers/ptp/ptp_ocp.c | 1 - drivers/pwm/sysfs.c | 1 - drivers/rapidio/rio-driver.c | 1 - drivers/scsi/sd.c | 1 - drivers/soc/qcom/rmtfs_mem.c | 1 - drivers/spi/spi.c | 2 -- drivers/staging/fieldbus/dev_core.c | 1 - drivers/staging/greybus/loopback.c | 1 - drivers/staging/greybus/vibrator.c | 1 - drivers/usb/typec/class.c | 1 - drivers/usb/typec/mux.c | 1 - drivers/usb/typec/pd.c | 1 - drivers/usb/typec/retimer.c | 1 - drivers/watchdog/watchdog_dev.c | 1 - fs/ksmbd/server.c | 1 - net/wireless/sysfs.c | 1 - 37 files changed, 39 deletions(-) diff --git a/arch/mips/kernel/vpe-mt.c b/arch/mips/kernel/vpe-mt.c index 223d6274f2e5..667bc75f6420 100644 --- a/arch/mips/kernel/vpe-mt.c +++ b/arch/mips/kernel/vpe-mt.c @@ -316,7 +316,6 @@ static void vpe_device_release(struct device *cd) static struct class vpe_class = { .name = "vpe", - .owner = THIS_MODULE, .dev_release = vpe_device_release, .dev_groups = vpe_groups, }; diff --git a/drivers/base/core.c b/drivers/base/core.c index fe74a786e2c3..57076837b33e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -537,7 +537,6 @@ static void devlink_dev_release(struct device *dev) static struct class devlink_class = { .name = "devlink", - .owner = THIS_MODULE, .dev_groups = devlink_groups, .dev_release = devlink_dev_release, }; diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 1c06781f7114..59aaf2e1375a 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -226,7 +226,6 @@ ATTRIBUTE_GROUPS(devcd_class); static struct class devcd_class = { .name = "devcoredump", - .owner = THIS_MODULE, .dev_release = devcd_dev_release, .dev_groups = devcd_dev_groups, .class_groups = devcd_class_groups, diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 2f1a92509271..642e3377441a 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -417,7 +417,6 @@ static int pkt_sysfs_init(void) if (!class_pktcdvd) return -ENOMEM; class_pktcdvd->name = DRIVER_NAME; - class_pktcdvd->owner = THIS_MODULE; class_pktcdvd->class_release = class_pktcdvd_release; class_pktcdvd->class_groups = class_pktcdvd_groups; ret = class_register(class_pktcdvd); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index aa490da3cef2..b7bb52f8dfbd 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2481,7 +2481,6 @@ ATTRIBUTE_GROUPS(zram_control_class); static struct class zram_control_class = { .name = "zram-control", - .owner = THIS_MODULE, .class_groups = zram_control_class_groups, }; diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index cd27bf173dec..774755052618 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -523,8 +523,6 @@ ATTRIBUTE_GROUPS(gpio_class); static struct class gpio_class = { .name = "gpio", - .owner = THIS_MODULE, - .class_groups = gpio_class_groups, }; diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 33edb5c02f7d..d15ef89e5191 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -138,7 +138,6 @@ static void hwmon_dev_release(struct device *dev) static struct class hwmon_class = { .name = "hwmon", - .owner = THIS_MODULE, .dev_groups = hwmon_dev_attr_groups, .dev_release = hwmon_dev_release, }; diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index 9120be590325..f5989c9907ee 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -159,7 +159,6 @@ static void mISDN_class_release(struct class *cls) static struct class mISDN_class = { .name = "mISDN", - .owner = THIS_MODULE, .dev_uevent = mISDN_uevent, .dev_groups = mISDN_groups, .dev_release = mISDN_dev_release, diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c index ee8087f29b2c..40e6c873c36d 100644 --- a/drivers/media/pci/ddbridge/ddbridge-core.c +++ b/drivers/media/pci/ddbridge/ddbridge-core.c @@ -3117,7 +3117,6 @@ static struct device_attribute ddb_attrs_fanspeed[] = { static struct class ddb_class = { .name = "ddbridge", - .owner = THIS_MODULE, .devnode = ddb_devnode, }; diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 02d4271dfe06..92f4dfccc3cc 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -20,7 +20,6 @@ #define DRV_NAME "cros-ec-dev" static struct class cros_class = { - .owner = THIS_MODULE, .name = "chromeos", }; diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c index 4ba966529458..76511d279aff 100644 --- a/drivers/misc/enclosure.c +++ b/drivers/misc/enclosure.c @@ -451,7 +451,6 @@ ATTRIBUTE_GROUPS(enclosure_class); static struct class enclosure_class = { .name = "enclosure", - .owner = THIS_MODULE, .dev_release = enclosure_release, .dev_groups = enclosure_class_groups, }; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 0feacb9fbdac..63fca6141973 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -63,7 +63,6 @@ static SIMPLE_DEV_PM_OPS(mtd_cls_pm_ops, mtd_cls_suspend, mtd_cls_resume); static struct class mtd_class = { .name = "mtd", - .owner = THIS_MODULE, .pm = MTD_CLS_PM_OPS, }; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 0904eb40c95f..ae6d35e3da9c 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -111,7 +111,6 @@ ATTRIBUTE_GROUPS(ubi_class); /* Root UBI "class" object (corresponds to '//class/ubi/') */ struct class ubi_class = { .name = UBI_NAME_STR, - .owner = THIS_MODULE, .class_groups = ubi_class_groups, }; diff --git a/drivers/mux/core.c b/drivers/mux/core.c index 49bedbe6316c..990e7bc17c85 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -45,7 +45,6 @@ struct mux_state { static struct class mux_class = { .name = "mux", - .owner = THIS_MODULE, }; static DEFINE_IDA(mux_ida); diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index dde272586e80..60944a4beada 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -38,7 +38,6 @@ static const void *ipvtap_net_namespace(const struct device *d) static struct class ipvtap_class = { .name = "ipvtap", - .owner = THIS_MODULE, .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 031344239f27..bddcc127812e 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -43,7 +43,6 @@ static const void *macvtap_net_namespace(const struct device *d) static struct class macvtap_class = { .name = "macvtap", - .owner = THIS_MODULE, .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 456ee42a6133..2ed75923507d 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3875,7 +3875,6 @@ static const struct attribute_group *nvme_fc_attr_groups[] = { static struct class fc_class = { .name = "fc", .dev_groups = nvme_fc_attr_groups, - .owner = THIS_MODULE, }; static int __init nvme_fc_init_module(void) diff --git a/drivers/platform/chrome/wilco_ec/event.c b/drivers/platform/chrome/wilco_ec/event.c index 69ceead8cdaa..a40f60bcefb6 100644 --- a/drivers/platform/chrome/wilco_ec/event.c +++ b/drivers/platform/chrome/wilco_ec/event.c @@ -58,7 +58,6 @@ #define DRV_NAME EVENT_DEV_NAME #define EVENT_DEV_NAME_FMT (EVENT_DEV_NAME "%d") static struct class event_class = { - .owner = THIS_MODULE, .name = EVENT_CLASS_NAME, }; diff --git a/drivers/platform/chrome/wilco_ec/telemetry.c b/drivers/platform/chrome/wilco_ec/telemetry.c index 60da7a29f2ff..54708aa6c700 100644 --- a/drivers/platform/chrome/wilco_ec/telemetry.c +++ b/drivers/platform/chrome/wilco_ec/telemetry.c @@ -42,7 +42,6 @@ #define DRV_NAME TELEM_DEV_NAME #define TELEM_DEV_NAME_FMT (TELEM_DEV_NAME "%d") static struct class telem_class = { - .owner = THIS_MODULE, .name = TELEM_CLASS_NAME, }; diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 46598dcb634a..80292d21a0b4 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -155,7 +155,6 @@ ATTRIBUTE_GROUPS(intel_pmt); static struct class intel_pmt_class = { .name = "intel_pmt", - .owner = THIS_MODULE, .dev_groups = intel_pmt_groups, }; diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index e7a3e3402817..6851d10d6582 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -82,7 +82,6 @@ static DEFINE_MUTEX(ipclock); /* lock used to prevent multiple call to SCU */ static struct class intel_scu_ipc_class = { .name = "intel_scu_ipc", - .owner = THIS_MODULE, }; /** diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 4bbaccd543ad..93eba1430883 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -34,7 +34,6 @@ #define PCI_DEVICE_ID_OROLIA_ARTCARD 0xa000 static struct class timecard_class = { - .owner = THIS_MODULE, .name = "timecard", }; diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index e7db8e45001c..1a106ec32939 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -475,7 +475,6 @@ static DEFINE_SIMPLE_DEV_PM_OPS(pwm_class_pm_ops, pwm_class_suspend, pwm_class_r static struct class pwm_class = { .name = "pwm", - .owner = THIS_MODULE, .dev_groups = pwm_chip_groups, .pm = pm_sleep_ptr(&pwm_class_pm_ops), }; diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c index e60e49769bed..1b3b4c2e015d 100644 --- a/drivers/rapidio/rio-driver.c +++ b/drivers/rapidio/rio-driver.c @@ -223,7 +223,6 @@ static int rio_uevent(const struct device *dev, struct kobj_uevent_env *env) struct class rio_mport_class = { .name = "rapidio_port", - .owner = THIS_MODULE, .dev_groups = rio_mport_groups, }; EXPORT_SYMBOL_GPL(rio_mport_class); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 4f28dd617eca..f98878776204 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -587,7 +587,6 @@ ATTRIBUTE_GROUPS(sd_disk); static struct class sd_disk_class = { .name = "scsi_disk", - .owner = THIS_MODULE, .dev_release = scsi_disk_release, .dev_groups = sd_disk_groups, }; diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c index 2d3ee22b9249..5c321da7bb9d 100644 --- a/drivers/soc/qcom/rmtfs_mem.c +++ b/drivers/soc/qcom/rmtfs_mem.c @@ -126,7 +126,6 @@ static int qcom_rmtfs_mem_release(struct inode *inode, struct file *filp) } static struct class rmtfs_class = { - .owner = THIS_MODULE, .name = "rmtfs", }; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 44b85a8d47f1..4b9a17f024c0 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2776,7 +2776,6 @@ static void spi_controller_release(struct device *dev) static struct class spi_master_class = { .name = "spi_master", - .owner = THIS_MODULE, .dev_release = spi_controller_release, .dev_groups = spi_master_groups, }; @@ -2879,7 +2878,6 @@ static const struct attribute_group *spi_slave_groups[] = { static struct class spi_slave_class = { .name = "spi_slave", - .owner = THIS_MODULE, .dev_release = spi_controller_release, .dev_groups = spi_slave_groups, }; diff --git a/drivers/staging/fieldbus/dev_core.c b/drivers/staging/fieldbus/dev_core.c index 5f54f2674bd1..bf1812d8924f 100644 --- a/drivers/staging/fieldbus/dev_core.c +++ b/drivers/staging/fieldbus/dev_core.c @@ -154,7 +154,6 @@ __ATTRIBUTE_GROUPS(fieldbus); static struct class fieldbus_class = { .name = "fieldbus_dev", - .owner = THIS_MODULE, .dev_groups = fieldbus_groups, }; diff --git a/drivers/staging/greybus/loopback.c b/drivers/staging/greybus/loopback.c index 1a61fce98056..d7b39f3bb652 100644 --- a/drivers/staging/greybus/loopback.c +++ b/drivers/staging/greybus/loopback.c @@ -100,7 +100,6 @@ struct gb_loopback { static struct class loopback_class = { .name = "gb_loopback", - .owner = THIS_MODULE, }; static DEFINE_IDA(loopback_ida); diff --git a/drivers/staging/greybus/vibrator.c b/drivers/staging/greybus/vibrator.c index 0e2b188e5ca3..227e18d92a95 100644 --- a/drivers/staging/greybus/vibrator.c +++ b/drivers/staging/greybus/vibrator.c @@ -107,7 +107,6 @@ ATTRIBUTE_GROUPS(vibrator); static struct class vibrator_class = { .name = "vibrator", - .owner = THIS_MODULE, .dev_groups = vibrator_groups, }; diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index cc3182f70673..349cc2030c90 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -22,7 +22,6 @@ static DEFINE_IDA(typec_index_ida); struct class typec_class = { .name = "typec", - .owner = THIS_MODULE, }; /* ------------------------------------------------------------------------- */ diff --git a/drivers/usb/typec/mux.c b/drivers/usb/typec/mux.c index c7177ddd4f12..d9eaf9a0b0bf 100644 --- a/drivers/usb/typec/mux.c +++ b/drivers/usb/typec/mux.c @@ -514,5 +514,4 @@ EXPORT_SYMBOL_GPL(typec_mux_get_drvdata); struct class typec_mux_class = { .name = "typec_mux", - .owner = THIS_MODULE, }; diff --git a/drivers/usb/typec/pd.c b/drivers/usb/typec/pd.c index 59c537a5e600..0bcde1ff4d39 100644 --- a/drivers/usb/typec/pd.c +++ b/drivers/usb/typec/pd.c @@ -15,7 +15,6 @@ static DEFINE_IDA(pd_ida); static struct class pd_class = { .name = "usb_power_delivery", - .owner = THIS_MODULE, }; #define to_pdo(o) container_of(o, struct pdo, dev) diff --git a/drivers/usb/typec/retimer.c b/drivers/usb/typec/retimer.c index 0481e82f6bbc..4a7d1b5c4d86 100644 --- a/drivers/usb/typec/retimer.c +++ b/drivers/usb/typec/retimer.c @@ -157,5 +157,4 @@ EXPORT_SYMBOL_GPL(typec_retimer_get_drvdata); struct class retimer_class = { .name = "retimer", - .owner = THIS_MODULE, }; diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 0122e8796879..12a6f020b6b5 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -1005,7 +1005,6 @@ static struct miscdevice watchdog_miscdev = { static struct class watchdog_class = { .name = "watchdog", - .owner = THIS_MODULE, .dev_groups = wdt_groups, }; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 394b6ceac431..b5af3e43e677 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -516,7 +516,6 @@ ATTRIBUTE_GROUPS(ksmbd_control_class); static struct class ksmbd_control_class = { .name = "ksmbd-control", - .owner = THIS_MODULE, .class_groups = ksmbd_control_class_groups, }; diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index cdb638647e0b..268f670835e9 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -157,7 +157,6 @@ static const void *wiphy_namespace(const struct device *d) struct class ieee80211_class = { .name = "ieee80211", - .owner = THIS_MODULE, .dev_release = wiphy_dev_release, .dev_groups = ieee80211_groups, .pm = WIPHY_PM_OPS, -- GitLab From 6e30a66433afee90e902ced95d7136e8f7edcc7e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:34 +0100 Subject: [PATCH 0755/5631] driver core: class: remove struct module owner out of struct class The module owner field for a struct class was never actually used, so remove it as it is not doing anything at all. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 9 +++------ include/linux/device/class.h | 18 +++++++----------- 2 files changed, 10 insertions(+), 17 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 90dc5788957a..9439c6c7466f 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -154,7 +154,7 @@ static void class_remove_groups(struct class *cls, return sysfs_remove_groups(&cls->p->subsys.kobj, groups); } -int __class_register(struct class *cls, struct module *owner, struct lock_class_key *key) +int __class_register(struct class *cls, struct lock_class_key *key) { struct subsys_private *cp; int error; @@ -187,7 +187,6 @@ int __class_register(struct class *cls, struct module *owner, struct lock_class_ if (error) goto err_out; - cls->owner = owner; error = class_add_groups(class_get(cls), cls->class_groups); class_put(cls); if (error) { @@ -220,7 +219,6 @@ static void class_create_release(struct class *cls) /** * __class_create - create a struct class structure - * @owner: pointer to the module that is to "own" this struct class * @name: pointer to a string for the name of this class. * @key: the lock_class_key for this class; used by mutex lock debugging * @@ -232,8 +230,7 @@ static void class_create_release(struct class *cls) * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ -struct class *__class_create(struct module *owner, const char *name, - struct lock_class_key *key) +struct class *__class_create(const char *name, struct lock_class_key *key) { struct class *cls; int retval; @@ -247,7 +244,7 @@ struct class *__class_create(struct module *owner, const char *name, cls->name = name; cls->class_release = class_create_release; - retval = __class_register(cls, owner, key); + retval = __class_register(cls, key); if (retval) goto error; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index d1ba4ee235dc..bf736f14f0c1 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -25,7 +25,6 @@ struct fwnode_handle; /** * struct class - device classes * @name: Name of the class. - * @owner: The module owner. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. * @dev_kobj: The kobject that represents this class and links it into the hierarchy. @@ -53,7 +52,6 @@ struct fwnode_handle; */ struct class { const char *name; - struct module *owner; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; @@ -85,16 +83,15 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; extern int __must_check __class_register(struct class *class, - struct module *owner, struct lock_class_key *key); extern void class_unregister(struct class *class); /* This is a #define to keep the compiler from merging different * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, THIS_MODULE, &__key); \ +#define class_register(class) \ +({ \ + static struct lock_class_key __key; \ + __class_register(class, &__key); \ }) struct class_compat; @@ -250,8 +247,7 @@ struct class_interface { extern int __must_check class_interface_register(struct class_interface *); extern void class_interface_unregister(struct class_interface *); -extern struct class * __must_check __class_create(struct module *owner, - const char *name, +extern struct class * __must_check __class_create(const char *name, struct lock_class_key *key); extern void class_destroy(struct class *cls); @@ -260,7 +256,7 @@ extern void class_destroy(struct class *cls); /** * class_create - create a struct class structure - * @owner: pointer to the module that is to "own" this struct class + * @owner: dummy pointer, does nothing, will be removed soon. * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used @@ -274,7 +270,7 @@ extern void class_destroy(struct class *cls); #define class_create(owner, name) \ ({ \ static struct lock_class_key __key; \ - __class_create(owner, name, &__key); \ + __class_create(name, &__key); \ }) -- GitLab From 1aaba11da9aa7d7d6b52a74d45b31cac118295a1 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:35 +0100 Subject: [PATCH 0756/5631] driver core: class: remove module * from class_create() The module pointer in class_create() never actually did anything, and it shouldn't have been requred to be set as a parameter even if it did something. So just remove it and fix up all callers of the function in the kernel tree at the same time. Cc: "Rafael J. Wysocki" Acked-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20230313181843.1207845-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/mips-mt.c | 2 +- arch/mips/sibyte/common/sb_tbprof.c | 2 +- arch/powerpc/platforms/book3s/vas-api.c | 2 +- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 2 +- arch/x86/kernel/cpuid.c | 2 +- arch/x86/kernel/msr.c | 2 +- block/bsg.c | 2 +- drivers/accel/drm_accel.c | 2 +- drivers/accel/habanalabs/common/habanalabs_drv.c | 2 +- drivers/base/power/wakeup_stats.c | 2 +- drivers/block/aoe/aoechr.c | 2 +- drivers/block/rnbd/rnbd-clt-sysfs.c | 2 +- drivers/block/rnbd/rnbd-srv-sysfs.c | 2 +- drivers/block/ublk_drv.c | 2 +- drivers/char/bsr.c | 2 +- drivers/char/dsp56k.c | 2 +- drivers/char/ipmi/ipmi_devintf.c | 2 +- drivers/char/lp.c | 2 +- drivers/char/mem.c | 2 +- drivers/char/misc.c | 2 +- drivers/char/pcmcia/cm4000_cs.c | 2 +- drivers/char/pcmcia/cm4040_cs.c | 2 +- drivers/char/pcmcia/scr24x_cs.c | 2 +- drivers/char/ppdev.c | 2 +- drivers/char/tpm/tpm-interface.c | 4 ++-- drivers/char/virtio_console.c | 2 +- drivers/char/xilinx_hwicap/xilinx_hwicap.c | 2 +- drivers/char/xillybus/xillybus_class.c | 2 +- drivers/comedi/comedi_fops.c | 2 +- drivers/comedi/drivers/comedi_test.c | 2 +- drivers/crypto/qat/qat_common/adf_ctl_drv.c | 2 +- drivers/dca/dca-sysfs.c | 2 +- drivers/devfreq/devfreq-event.c | 2 +- drivers/devfreq/devfreq.c | 2 +- drivers/dma-buf/dma-heap.c | 2 +- drivers/extcon/extcon.c | 2 +- drivers/fpga/fpga-bridge.c | 2 +- drivers/fpga/fpga-mgr.c | 2 +- drivers/fpga/fpga-region.c | 2 +- drivers/gnss/core.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +- drivers/gpu/drm/display/drm_dp_aux_dev.c | 2 +- drivers/gpu/drm/drm_sysfs.c | 2 +- drivers/hid/hid-roccat-arvo.c | 2 +- drivers/hid/hid-roccat-isku.c | 2 +- drivers/hid/hid-roccat-kone.c | 2 +- drivers/hid/hid-roccat-koneplus.c | 2 +- drivers/hid/hid-roccat-konepure.c | 2 +- drivers/hid/hid-roccat-kovaplus.c | 2 +- drivers/hid/hid-roccat-pyra.c | 2 +- drivers/hid/hid-roccat-ryos.c | 2 +- drivers/hid/hid-roccat-savu.c | 2 +- drivers/hid/hidraw.c | 2 +- drivers/i2c/i2c-dev.c | 2 +- drivers/infiniband/core/uverbs_main.c | 2 +- drivers/infiniband/hw/hfi1/device.c | 4 ++-- drivers/infiniband/hw/qib/qib_file_ops.c | 2 +- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 2 +- drivers/infiniband/ulp/rtrs/rtrs-srv.c | 2 +- drivers/isdn/capi/capi.c | 2 +- drivers/isdn/mISDN/dsp_pipeline.c | 2 +- drivers/leds/led-class.c | 2 +- drivers/macintosh/adb.c | 2 +- drivers/media/dvb-core/dvbdev.c | 2 +- drivers/media/rc/lirc_dev.c | 2 +- drivers/misc/c2port/core.c | 2 +- drivers/misc/cxl/file.c | 2 +- drivers/misc/genwqe/card_base.c | 2 +- drivers/misc/hpilo.c | 2 +- drivers/misc/mei/main.c | 2 +- drivers/misc/ocxl/file.c | 2 +- drivers/misc/phantom.c | 2 +- drivers/misc/uacce/uacce.c | 2 +- drivers/most/most_cdev.c | 2 +- drivers/net/ethernet/hisilicon/hns/hnae.c | 2 +- drivers/net/ppp/ppp_generic.c | 2 +- drivers/net/wireless/mac80211_hwsim.c | 2 +- drivers/net/wwan/wwan_core.c | 2 +- drivers/net/wwan/wwan_hwsim.c | 2 +- drivers/nvdimm/bus.c | 2 +- drivers/nvme/host/core.c | 6 +++--- drivers/nvme/host/fabrics.c | 2 +- drivers/nvme/target/fcloop.c | 2 +- drivers/pci/endpoint/pci-epc-core.c | 2 +- drivers/pci/switch/switchtec.c | 2 +- drivers/phy/phy-core.c | 2 +- drivers/power/supply/power_supply_core.c | 2 +- drivers/pps/pps.c | 2 +- drivers/ptp/ptp_clock.c | 2 +- drivers/rapidio/devices/rio_mport_cdev.c | 2 +- drivers/rapidio/rio_cm.c | 2 +- drivers/rpmsg/rpmsg_core.c | 2 +- drivers/rtc/class.c | 2 +- drivers/s390/char/hmcdrv_dev.c | 2 +- drivers/s390/char/raw3270.c | 2 +- drivers/s390/char/tape_class.c | 2 +- drivers/s390/char/vmlogrdr.c | 2 +- drivers/s390/char/vmur.c | 2 +- drivers/s390/crypto/zcrypt_api.c | 2 +- drivers/sbus/char/oradax.c | 2 +- drivers/scsi/ch.c | 2 +- drivers/scsi/cxlflash/main.c | 2 +- drivers/scsi/pmcraid.c | 2 +- drivers/scsi/sg.c | 2 +- drivers/spi/spidev.c | 2 +- drivers/staging/fieldbus/anybuss/arcx-anybus.c | 2 +- drivers/staging/greybus/authentication.c | 2 +- drivers/staging/greybus/fw-management.c | 2 +- drivers/staging/greybus/raw.c | 2 +- drivers/staging/pi433/pi433_if.c | 2 +- drivers/staging/vme_user/vme_user.c | 2 +- drivers/tee/tee_core.c | 2 +- drivers/tty/tty_io.c | 2 +- drivers/tty/vt/vc_screen.c | 2 +- drivers/tty/vt/vt.c | 2 +- drivers/usb/core/file.c | 2 +- drivers/usb/gadget/function/f_hid.c | 2 +- drivers/usb/gadget/function/f_printer.c | 2 +- drivers/usb/gadget/udc/core.c | 2 +- drivers/usb/mon/mon_bin.c | 2 +- drivers/usb/roles/class.c | 2 +- drivers/vdpa/vdpa_user/vduse_dev.c | 2 +- drivers/vfio/group.c | 2 +- drivers/vfio/vfio_main.c | 2 +- drivers/video/backlight/backlight.c | 2 +- drivers/video/backlight/lcd.c | 2 +- drivers/video/fbdev/core/fbmem.c | 2 +- fs/coda/psdev.c | 2 +- fs/fuse/cuse.c | 2 +- fs/pstore/pmsg.c | 2 +- include/linux/device/class.h | 3 +-- mm/backing-dev.c | 2 +- net/bluetooth/hci_sysfs.c | 2 +- net/netfilter/xt_IDLETIMER.c | 2 +- samples/vfio-mdev/mbochs.c | 2 +- samples/vfio-mdev/mdpy.c | 2 +- samples/vfio-mdev/mtty.c | 2 +- sound/sound_core.c | 2 +- tools/testing/nvdimm/test/ndtest.c | 2 +- tools/testing/nvdimm/test/nfit.c | 2 +- 140 files changed, 144 insertions(+), 145 deletions(-) diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c index dc023a979803..f88b7919f11f 100644 --- a/arch/mips/kernel/mips-mt.c +++ b/arch/mips/kernel/mips-mt.c @@ -234,7 +234,7 @@ static int __init mips_mt_init(void) { struct class *mtc; - mtc = class_create(THIS_MODULE, "mt"); + mtc = class_create("mt"); if (IS_ERR(mtc)) return PTR_ERR(mtc); diff --git a/arch/mips/sibyte/common/sb_tbprof.c b/arch/mips/sibyte/common/sb_tbprof.c index bc47681e825a..ac376dfb4e7c 100644 --- a/arch/mips/sibyte/common/sb_tbprof.c +++ b/arch/mips/sibyte/common/sb_tbprof.c @@ -550,7 +550,7 @@ static int __init sbprof_tb_init(void) return -EIO; } - tbc = class_create(THIS_MODULE, "sb_tracebuffer"); + tbc = class_create("sb_tracebuffer"); if (IS_ERR(tbc)) { err = PTR_ERR(tbc); goto out_chrdev; diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 36c21648d19a..77ea9335fd04 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -581,7 +581,7 @@ int vas_register_coproc_api(struct module *mod, enum vas_cop_type cop_type, pr_devel("%s device allocated, dev [%i,%i]\n", name, MAJOR(coproc_device.devt), MINOR(coproc_device.devt)); - coproc_device.class = class_create(mod, name); + coproc_device.class = class_create(name); if (IS_ERR(coproc_device.class)) { rc = PTR_ERR(coproc_device.class); pr_err("Unable to create %s class %d\n", name, rc); diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 524f8ff3e69c..458cb7419502 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1580,7 +1580,7 @@ int rdt_pseudo_lock_init(void) pseudo_lock_major = ret; - pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock"); + pseudo_lock_class = class_create("pseudo_lock"); if (IS_ERR(pseudo_lock_class)) { ret = PTR_ERR(pseudo_lock_class); unregister_chrdev(pseudo_lock_major, "pseudo_lock"); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 621ba9c0f17a..bdc0d5539b57 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -154,7 +154,7 @@ static int __init cpuid_init(void) CPUID_MAJOR); return -EBUSY; } - cpuid_class = class_create(THIS_MODULE, "cpuid"); + cpuid_class = class_create("cpuid"); if (IS_ERR(cpuid_class)) { err = PTR_ERR(cpuid_class); goto out_chrdev; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 708751311786..7bb17d37db01 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -263,7 +263,7 @@ static int __init msr_init(void) pr_err("unable to get major %d for msr\n", MSR_MAJOR); return -EBUSY; } - msr_class = class_create(THIS_MODULE, "msr"); + msr_class = class_create("msr"); if (IS_ERR(msr_class)) { err = PTR_ERR(msr_class); goto out_chrdev; diff --git a/block/bsg.c b/block/bsg.c index 30fcc865ef4f..7eca43f33d7f 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -245,7 +245,7 @@ static int __init bsg_init(void) dev_t devid; int ret; - bsg_class = class_create(THIS_MODULE, "bsg"); + bsg_class = class_create("bsg"); if (IS_ERR(bsg_class)) return PTR_ERR(bsg_class); bsg_class->devnode = bsg_devnode; diff --git a/drivers/accel/drm_accel.c b/drivers/accel/drm_accel.c index 1b69824286fd..4a9baf02439e 100644 --- a/drivers/accel/drm_accel.c +++ b/drivers/accel/drm_accel.c @@ -34,7 +34,7 @@ static char *accel_devnode(const struct device *dev, umode_t *mode) static int accel_sysfs_init(void) { - accel_class = class_create(THIS_MODULE, "accel"); + accel_class = class_create("accel"); if (IS_ERR(accel_class)) return PTR_ERR(accel_class); diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 03dae57dc838..3538e89e4e5e 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -702,7 +702,7 @@ static int __init hl_init(void) hl_major = MAJOR(dev); - hl_class = class_create(THIS_MODULE, HL_NAME); + hl_class = class_create(HL_NAME); if (IS_ERR(hl_class)) { pr_err("failed to allocate class\n"); rc = PTR_ERR(hl_class); diff --git a/drivers/base/power/wakeup_stats.c b/drivers/base/power/wakeup_stats.c index 924fac493c4f..6732ed2869f9 100644 --- a/drivers/base/power/wakeup_stats.c +++ b/drivers/base/power/wakeup_stats.c @@ -210,7 +210,7 @@ void wakeup_source_sysfs_remove(struct wakeup_source *ws) static int __init wakeup_sources_sysfs_init(void) { - wakeup_class = class_create(THIS_MODULE, "wakeup"); + wakeup_class = class_create("wakeup"); return PTR_ERR_OR_ZERO(wakeup_class); } diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index 7a368c90467d..4c666f72203f 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -290,7 +290,7 @@ aoechr_init(void) } init_completion(&emsgs_comp); spin_lock_init(&emsgs_lock); - aoe_class = class_create(THIS_MODULE, "aoe"); + aoe_class = class_create("aoe"); if (IS_ERR(aoe_class)) { unregister_chrdev(AOE_MAJOR, "aoechr"); return PTR_ERR(aoe_class); diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c index e7c7d9a68168..8c6087949794 100644 --- a/drivers/block/rnbd/rnbd-clt-sysfs.c +++ b/drivers/block/rnbd/rnbd-clt-sysfs.c @@ -646,7 +646,7 @@ int rnbd_clt_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create(THIS_MODULE, "rnbd-client"); + rnbd_dev_class = class_create("rnbd-client"); if (IS_ERR(rnbd_dev_class)) return PTR_ERR(rnbd_dev_class); diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c index 297a6924ff4e..d5d9267e1fa5 100644 --- a/drivers/block/rnbd/rnbd-srv-sysfs.c +++ b/drivers/block/rnbd/rnbd-srv-sysfs.c @@ -215,7 +215,7 @@ int rnbd_srv_create_sysfs_files(void) { int err; - rnbd_dev_class = class_create(THIS_MODULE, "rnbd-server"); + rnbd_dev_class = class_create("rnbd-server"); if (IS_ERR(rnbd_dev_class)) return PTR_ERR(rnbd_dev_class); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index d1d1c8d606c8..2eb46419562b 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -2266,7 +2266,7 @@ static int __init ublk_init(void) if (ret) goto unregister_mis; - ublk_chr_class = class_create(THIS_MODULE, "ublk-char"); + ublk_chr_class = class_create("ublk-char"); if (IS_ERR(ublk_chr_class)) { ret = PTR_ERR(ublk_chr_class); goto free_chrdev_region; diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c index d5f943938427..ff429ba02fa4 100644 --- a/drivers/char/bsr.c +++ b/drivers/char/bsr.c @@ -293,7 +293,7 @@ static int __init bsr_init(void) if (!np) goto out_err; - bsr_class = class_create(THIS_MODULE, "bsr"); + bsr_class = class_create("bsr"); if (IS_ERR(bsr_class)) { printk(KERN_ERR "class_create() failed for bsr_class\n"); ret = PTR_ERR(bsr_class); diff --git a/drivers/char/dsp56k.c b/drivers/char/dsp56k.c index 06749e295ada..b3eaf3e5ef2e 100644 --- a/drivers/char/dsp56k.c +++ b/drivers/char/dsp56k.c @@ -504,7 +504,7 @@ static int __init dsp56k_init_driver(void) printk("DSP56k driver: Unable to register driver\n"); return -ENODEV; } - dsp56k_class = class_create(THIS_MODULE, "dsp56k"); + dsp56k_class = class_create("dsp56k"); if (IS_ERR(dsp56k_class)) { err = PTR_ERR(dsp56k_class); goto out_chrdev; diff --git a/drivers/char/ipmi/ipmi_devintf.c b/drivers/char/ipmi/ipmi_devintf.c index d160fa4c73fe..73e5a9e28f85 100644 --- a/drivers/char/ipmi/ipmi_devintf.c +++ b/drivers/char/ipmi/ipmi_devintf.c @@ -860,7 +860,7 @@ static int __init init_ipmi_devintf(void) pr_info("ipmi device interface\n"); - ipmi_class = class_create(THIS_MODULE, "ipmi"); + ipmi_class = class_create("ipmi"); if (IS_ERR(ipmi_class)) { pr_err("ipmi: can't register device class\n"); return PTR_ERR(ipmi_class); diff --git a/drivers/char/lp.c b/drivers/char/lp.c index 38aad99ebb61..70cfc5140c2c 100644 --- a/drivers/char/lp.c +++ b/drivers/char/lp.c @@ -1049,7 +1049,7 @@ static int __init lp_init(void) return -EIO; } - lp_class = class_create(THIS_MODULE, "printer"); + lp_class = class_create("printer"); if (IS_ERR(lp_class)) { err = PTR_ERR(lp_class); goto out_reg; diff --git a/drivers/char/mem.c b/drivers/char/mem.c index ffb101d349f0..f494d31f2b98 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -762,7 +762,7 @@ static int __init chr_dev_init(void) if (register_chrdev(MEM_MAJOR, "mem", &memory_fops)) printk("unable to get major %d for memory devs\n", MEM_MAJOR); - mem_class = class_create(THIS_MODULE, "mem"); + mem_class = class_create("mem"); if (IS_ERR(mem_class)) return PTR_ERR(mem_class); diff --git a/drivers/char/misc.c b/drivers/char/misc.c index 7a1388b0572b..1c44c29a666e 100644 --- a/drivers/char/misc.c +++ b/drivers/char/misc.c @@ -286,7 +286,7 @@ static int __init misc_init(void) struct proc_dir_entry *ret; ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops); - misc_class = class_create(THIS_MODULE, "misc"); + misc_class = class_create("misc"); err = PTR_ERR(misc_class); if (IS_ERR(misc_class)) goto fail_remove; diff --git a/drivers/char/pcmcia/cm4000_cs.c b/drivers/char/pcmcia/cm4000_cs.c index e656f42a28ac..7f96d8571a53 100644 --- a/drivers/char/pcmcia/cm4000_cs.c +++ b/drivers/char/pcmcia/cm4000_cs.c @@ -1878,7 +1878,7 @@ static int __init cmm_init(void) { int rc; - cmm_class = class_create(THIS_MODULE, "cardman_4000"); + cmm_class = class_create("cardman_4000"); if (IS_ERR(cmm_class)) return PTR_ERR(cmm_class); diff --git a/drivers/char/pcmcia/cm4040_cs.c b/drivers/char/pcmcia/cm4040_cs.c index 827711911da4..11ff59e2b963 100644 --- a/drivers/char/pcmcia/cm4040_cs.c +++ b/drivers/char/pcmcia/cm4040_cs.c @@ -650,7 +650,7 @@ static int __init cm4040_init(void) { int rc; - cmx_class = class_create(THIS_MODULE, "cardman_4040"); + cmx_class = class_create("cardman_4040"); if (IS_ERR(cmx_class)) return PTR_ERR(cmx_class); diff --git a/drivers/char/pcmcia/scr24x_cs.c b/drivers/char/pcmcia/scr24x_cs.c index 1bdce08fae3d..870781f5a08c 100644 --- a/drivers/char/pcmcia/scr24x_cs.c +++ b/drivers/char/pcmcia/scr24x_cs.c @@ -325,7 +325,7 @@ static int __init scr24x_init(void) { int ret; - scr24x_class = class_create(THIS_MODULE, "scr24x"); + scr24x_class = class_create("scr24x"); if (IS_ERR(scr24x_class)) return PTR_ERR(scr24x_class); diff --git a/drivers/char/ppdev.c b/drivers/char/ppdev.c index 38b46c7d1737..81ed58157b15 100644 --- a/drivers/char/ppdev.c +++ b/drivers/char/ppdev.c @@ -841,7 +841,7 @@ static int __init ppdev_init(void) pr_warn(CHRDEV ": unable to get major %d\n", PP_MAJOR); return -EIO; } - ppdev_class = class_create(THIS_MODULE, CHRDEV); + ppdev_class = class_create(CHRDEV); if (IS_ERR(ppdev_class)) { err = PTR_ERR(ppdev_class); goto out_chrdev; diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 7e513b771832..8763c820d1f8 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -466,13 +466,13 @@ static int __init tpm_init(void) { int rc; - tpm_class = class_create(THIS_MODULE, "tpm"); + tpm_class = class_create("tpm"); if (IS_ERR(tpm_class)) { pr_err("couldn't create tpm class\n"); return PTR_ERR(tpm_class); } - tpmrm_class = class_create(THIS_MODULE, "tpmrm"); + tpmrm_class = class_create("tpmrm"); if (IS_ERR(tpmrm_class)) { pr_err("couldn't create tpmrm class\n"); rc = PTR_ERR(tpmrm_class); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index d5ac4d955bc8..b65c809a4e97 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2244,7 +2244,7 @@ static int __init virtio_console_init(void) { int err; - pdrvdata.class = class_create(THIS_MODULE, "virtio-ports"); + pdrvdata.class = class_create("virtio-ports"); if (IS_ERR(pdrvdata.class)) { err = PTR_ERR(pdrvdata.class); pr_err("Error %d creating virtio-ports class\n", err); diff --git a/drivers/char/xilinx_hwicap/xilinx_hwicap.c b/drivers/char/xilinx_hwicap/xilinx_hwicap.c index 74a4928aea1d..a46f637da959 100644 --- a/drivers/char/xilinx_hwicap/xilinx_hwicap.c +++ b/drivers/char/xilinx_hwicap/xilinx_hwicap.c @@ -856,7 +856,7 @@ static int __init hwicap_module_init(void) dev_t devt; int retval; - icap_class = class_create(THIS_MODULE, "xilinx_config"); + icap_class = class_create("xilinx_config"); mutex_init(&icap_sem); devt = MKDEV(XHWICAP_MAJOR, XHWICAP_MINOR); diff --git a/drivers/char/xillybus/xillybus_class.c b/drivers/char/xillybus/xillybus_class.c index e9a288e61c15..89926fe9d813 100644 --- a/drivers/char/xillybus/xillybus_class.c +++ b/drivers/char/xillybus/xillybus_class.c @@ -242,7 +242,7 @@ EXPORT_SYMBOL(xillybus_find_inode); static int __init xillybus_class_init(void) { - xillybus_class = class_create(THIS_MODULE, "xillybus"); + xillybus_class = class_create("xillybus"); if (IS_ERR(xillybus_class)) { pr_warn("Failed to register xillybus class\n"); diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index b982903aaa46..8e43918d38c4 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -3383,7 +3383,7 @@ static int __init comedi_init(void) if (retval) goto out_unregister_chrdev_region; - comedi_class = class_create(THIS_MODULE, "comedi"); + comedi_class = class_create("comedi"); if (IS_ERR(comedi_class)) { retval = PTR_ERR(comedi_class); pr_err("failed to create class\n"); diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 0b5c0af1cebf..c02dc19a679b 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -795,7 +795,7 @@ static int __init comedi_test_init(void) } if (!config_mode) { - ctcls = class_create(THIS_MODULE, CLASS_NAME); + ctcls = class_create(CLASS_NAME); if (IS_ERR(ctcls)) { pr_warn("comedi_test: unable to create class\n"); goto clean3; diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 9190532b27eb..75a50fde5644 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -56,7 +56,7 @@ static int adf_chr_drv_create(void) return -EFAULT; } - adf_ctl_drv.drv_class = class_create(THIS_MODULE, DEVICE_NAME); + adf_ctl_drv.drv_class = class_create(DEVICE_NAME); if (IS_ERR(adf_ctl_drv.drv_class)) { pr_err("QAT: class_create failed for adf_ctl\n"); goto err_chrdev_unreg; diff --git a/drivers/dca/dca-sysfs.c b/drivers/dca/dca-sysfs.c index 21ebd0af268b..fcc83ede0909 100644 --- a/drivers/dca/dca-sysfs.c +++ b/drivers/dca/dca-sysfs.c @@ -74,7 +74,7 @@ int __init dca_sysfs_init(void) idr_init(&dca_idr); spin_lock_init(&dca_idr_lock); - dca_class = class_create(THIS_MODULE, "dca"); + dca_class = class_create("dca"); if (IS_ERR(dca_class)) { idr_destroy(&dca_idr); return PTR_ERR(dca_class); diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c index f041edccd107..3ebac2496679 100644 --- a/drivers/devfreq/devfreq-event.c +++ b/drivers/devfreq/devfreq-event.c @@ -469,7 +469,7 @@ ATTRIBUTE_GROUPS(devfreq_event); static int __init devfreq_event_init(void) { - devfreq_event_class = class_create(THIS_MODULE, "devfreq-event"); + devfreq_event_class = class_create("devfreq-event"); if (IS_ERR(devfreq_event_class)) { pr_err("%s: couldn't create class\n", __FILE__); return PTR_ERR(devfreq_event_class); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 817c71da391a..e36cbb920ec8 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -1988,7 +1988,7 @@ DEFINE_SHOW_ATTRIBUTE(devfreq_summary); static int __init devfreq_init(void) { - devfreq_class = class_create(THIS_MODULE, "devfreq"); + devfreq_class = class_create("devfreq"); if (IS_ERR(devfreq_class)) { pr_err("%s: couldn't create class\n", __FILE__); return PTR_ERR(devfreq_class); diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index c9e41e8a9e27..84ae708fafe7 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -314,7 +314,7 @@ static int dma_heap_init(void) if (ret) return ret; - dma_heap_class = class_create(THIS_MODULE, DEVNAME); + dma_heap_class = class_create(DEVNAME); if (IS_ERR(dma_heap_class)) { unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS); return PTR_ERR(dma_heap_class); diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index e1c71359b605..d43ba8e7260d 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -1013,7 +1013,7 @@ ATTRIBUTE_GROUPS(extcon); static int create_extcon_class(void) { if (!extcon_class) { - extcon_class = class_create(THIS_MODULE, "extcon"); + extcon_class = class_create("extcon"); if (IS_ERR(extcon_class)) return PTR_ERR(extcon_class); extcon_class->dev_groups = extcon_groups; diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 5cd40acab5bf..6a521c83a1ed 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -416,7 +416,7 @@ static void fpga_bridge_dev_release(struct device *dev) static int __init fpga_bridge_dev_init(void) { - fpga_bridge_class = class_create(THIS_MODULE, "fpga_bridge"); + fpga_bridge_class = class_create("fpga_bridge"); if (IS_ERR(fpga_bridge_class)) return PTR_ERR(fpga_bridge_class); diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index 8efa67620e21..eb583f86a0b9 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -971,7 +971,7 @@ static int __init fpga_mgr_class_init(void) { pr_info("FPGA manager framework\n"); - fpga_mgr_class = class_create(THIS_MODULE, "fpga_manager"); + fpga_mgr_class = class_create("fpga_manager"); if (IS_ERR(fpga_mgr_class)) return PTR_ERR(fpga_mgr_class); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index 27ff9dea04ae..ccf6fdab1360 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -293,7 +293,7 @@ static void fpga_region_dev_release(struct device *dev) */ static int __init fpga_region_init(void) { - fpga_region_class = class_create(THIS_MODULE, "fpga_region"); + fpga_region_class = class_create("fpga_region"); if (IS_ERR(fpga_region_class)) return PTR_ERR(fpga_region_class); diff --git a/drivers/gnss/core.c b/drivers/gnss/core.c index 77a4b280c552..48f2ee0f78c4 100644 --- a/drivers/gnss/core.c +++ b/drivers/gnss/core.c @@ -387,7 +387,7 @@ static int __init gnss_module_init(void) return ret; } - gnss_class = class_create(THIS_MODULE, "gnss"); + gnss_class = class_create("gnss"); if (IS_ERR(gnss_class)) { ret = PTR_ERR(gnss_class); pr_err("failed to create class: %d\n", ret); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a0e30f21e12e..20e75bd74bed 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -93,7 +93,7 @@ int kfd_chardev_init(void) if (err < 0) goto err_register_chrdev; - kfd_class = class_create(THIS_MODULE, kfd_dev_name); + kfd_class = class_create(kfd_dev_name); err = PTR_ERR(kfd_class); if (IS_ERR(kfd_class)) goto err_class_create; diff --git a/drivers/gpu/drm/display/drm_dp_aux_dev.c b/drivers/gpu/drm/display/drm_dp_aux_dev.c index 098e482e65a2..29555b9f03c8 100644 --- a/drivers/gpu/drm/display/drm_dp_aux_dev.c +++ b/drivers/gpu/drm/display/drm_dp_aux_dev.c @@ -330,7 +330,7 @@ int drm_dp_aux_dev_init(void) { int res; - drm_dp_aux_dev_class = class_create(THIS_MODULE, "drm_dp_aux_dev"); + drm_dp_aux_dev_class = class_create("drm_dp_aux_dev"); if (IS_ERR(drm_dp_aux_dev_class)) { return PTR_ERR(drm_dp_aux_dev_class); } diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index 183130355997..3c22a803201d 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -112,7 +112,7 @@ int drm_sysfs_init(void) { int err; - drm_class = class_create(THIS_MODULE, "drm"); + drm_class = class_create("drm"); if (IS_ERR(drm_class)) return PTR_ERR(drm_class); diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c index d94ee0539421..ea6b79b3aeeb 100644 --- a/drivers/hid/hid-roccat-arvo.c +++ b/drivers/hid/hid-roccat-arvo.c @@ -433,7 +433,7 @@ static int __init arvo_init(void) { int retval; - arvo_class = class_create(THIS_MODULE, "arvo"); + arvo_class = class_create("arvo"); if (IS_ERR(arvo_class)) return PTR_ERR(arvo_class); arvo_class->dev_groups = arvo_groups; diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c index e95d59cd8d07..3903a2cea00c 100644 --- a/drivers/hid/hid-roccat-isku.c +++ b/drivers/hid/hid-roccat-isku.c @@ -435,7 +435,7 @@ static struct hid_driver isku_driver = { static int __init isku_init(void) { int retval; - isku_class = class_create(THIS_MODULE, "isku"); + isku_class = class_create("isku"); if (IS_ERR(isku_class)) return PTR_ERR(isku_class); isku_class->dev_groups = isku_groups; diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index 76da04801ca9..945ae236fb45 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -890,7 +890,7 @@ static int __init kone_init(void) int retval; /* class name has to be same as driver name */ - kone_class = class_create(THIS_MODULE, "kone"); + kone_class = class_create("kone"); if (IS_ERR(kone_class)) return PTR_ERR(kone_class); kone_class->dev_groups = kone_groups; diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c index 1896c69ea512..97b83b6f53dd 100644 --- a/drivers/hid/hid-roccat-koneplus.c +++ b/drivers/hid/hid-roccat-koneplus.c @@ -549,7 +549,7 @@ static int __init koneplus_init(void) int retval; /* class name has to be same as driver name */ - koneplus_class = class_create(THIS_MODULE, "koneplus"); + koneplus_class = class_create("koneplus"); if (IS_ERR(koneplus_class)) return PTR_ERR(koneplus_class); koneplus_class->dev_groups = koneplus_groups; diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c index cf8eeb33a125..a297756f2410 100644 --- a/drivers/hid/hid-roccat-konepure.c +++ b/drivers/hid/hid-roccat-konepure.c @@ -207,7 +207,7 @@ static int __init konepure_init(void) { int retval; - konepure_class = class_create(THIS_MODULE, "konepure"); + konepure_class = class_create("konepure"); if (IS_ERR(konepure_class)) return PTR_ERR(konepure_class); konepure_class->dev_groups = konepure_groups; diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c index 6fb9b9563769..1a1d96e11683 100644 --- a/drivers/hid/hid-roccat-kovaplus.c +++ b/drivers/hid/hid-roccat-kovaplus.c @@ -638,7 +638,7 @@ static int __init kovaplus_init(void) { int retval; - kovaplus_class = class_create(THIS_MODULE, "kovaplus"); + kovaplus_class = class_create("kovaplus"); if (IS_ERR(kovaplus_class)) return PTR_ERR(kovaplus_class); kovaplus_class->dev_groups = kovaplus_groups; diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index 4fcc8e7d276f..15528c3b013c 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -585,7 +585,7 @@ static int __init pyra_init(void) int retval; /* class name has to be same as driver name */ - pyra_class = class_create(THIS_MODULE, "pyra"); + pyra_class = class_create("pyra"); if (IS_ERR(pyra_class)) return PTR_ERR(pyra_class); pyra_class->dev_groups = pyra_groups; diff --git a/drivers/hid/hid-roccat-ryos.c b/drivers/hid/hid-roccat-ryos.c index 5bf1971a2b14..0eb17a3b925d 100644 --- a/drivers/hid/hid-roccat-ryos.c +++ b/drivers/hid/hid-roccat-ryos.c @@ -216,7 +216,7 @@ static int __init ryos_init(void) { int retval; - ryos_class = class_create(THIS_MODULE, "ryos"); + ryos_class = class_create("ryos"); if (IS_ERR(ryos_class)) return PTR_ERR(ryos_class); ryos_class->dev_groups = ryos_groups; diff --git a/drivers/hid/hid-roccat-savu.c b/drivers/hid/hid-roccat-savu.c index a784bb4ee651..93be7acef673 100644 --- a/drivers/hid/hid-roccat-savu.c +++ b/drivers/hid/hid-roccat-savu.c @@ -204,7 +204,7 @@ static int __init savu_init(void) { int retval; - savu_class = class_create(THIS_MODULE, "savu"); + savu_class = class_create("savu"); if (IS_ERR(savu_class)) return PTR_ERR(savu_class); savu_class->dev_groups = savu_groups; diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c index 197b1e7bf029..93e62b161501 100644 --- a/drivers/hid/hidraw.c +++ b/drivers/hid/hidraw.c @@ -618,7 +618,7 @@ int __init hidraw_init(void) hidraw_major = MAJOR(dev_id); - hidraw_class = class_create(THIS_MODULE, "hidraw"); + hidraw_class = class_create("hidraw"); if (IS_ERR(hidraw_class)) { result = PTR_ERR(hidraw_class); goto error_cdev; diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 107623c4cc14..ef93064cfdb3 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -739,7 +739,7 @@ static int __init i2c_dev_init(void) if (res) goto out; - i2c_dev_class = class_create(THIS_MODULE, "i2c-dev"); + i2c_dev_class = class_create("i2c-dev"); if (IS_ERR(i2c_dev_class)) { res = PTR_ERR(i2c_dev_class); goto out_unreg_chrdev; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index bdb179a09d77..fbace69672ca 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1264,7 +1264,7 @@ static int __init ib_uverbs_init(void) goto out_alloc; } - uverbs_class = class_create(THIS_MODULE, "infiniband_verbs"); + uverbs_class = class_create("infiniband_verbs"); if (IS_ERR(uverbs_class)) { ret = PTR_ERR(uverbs_class); pr_err("user_verbs: couldn't create class infiniband_verbs\n"); diff --git a/drivers/infiniband/hw/hfi1/device.c b/drivers/infiniband/hw/hfi1/device.c index 1f4496032170..05be0d119f79 100644 --- a/drivers/infiniband/hw/hfi1/device.c +++ b/drivers/infiniband/hw/hfi1/device.c @@ -102,7 +102,7 @@ int __init dev_init(void) goto done; } - class = class_create(THIS_MODULE, class_name()); + class = class_create(class_name()); if (IS_ERR(class)) { ret = PTR_ERR(class); pr_err("Could not create device class (err %d)\n", -ret); @@ -111,7 +111,7 @@ int __init dev_init(void) } class->devnode = hfi1_devnode; - user_class = class_create(THIS_MODULE, class_name_user()); + user_class = class_create(class_name_user()); if (IS_ERR(user_class)) { ret = PTR_ERR(user_class); pr_err("Could not create device class for user accessible files (err %d)\n", diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 80fe92a21f96..c07c95fd3cfa 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -2326,7 +2326,7 @@ int __init qib_dev_init(void) goto done; } - qib_class = class_create(THIS_MODULE, "ipath"); + qib_class = class_create("ipath"); if (IS_ERR(qib_class)) { ret = PTR_ERR(qib_class); pr_err("Could not create device class (err %d)\n", -ret); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 80abf45a197a..edb2e3a25880 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -3163,7 +3163,7 @@ static int __init rtrs_client_init(void) { rtrs_rdma_dev_pd_init(0, &dev_pd); - rtrs_clt_dev_class = class_create(THIS_MODULE, "rtrs-client"); + rtrs_clt_dev_class = class_create("rtrs-client"); if (IS_ERR(rtrs_clt_dev_class)) { pr_err("Failed to create rtrs-client dev class\n"); return PTR_ERR(rtrs_clt_dev_class); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index d1703e2c0b82..c38901e2c8f4 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -2253,7 +2253,7 @@ static int __init rtrs_server_init(void) err); return err; } - rtrs_dev_class = class_create(THIS_MODULE, "rtrs-server"); + rtrs_dev_class = class_create("rtrs-server"); if (IS_ERR(rtrs_dev_class)) { err = PTR_ERR(rtrs_dev_class); goto out_err; diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 0f00be62438d..45a4043c5042 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -1393,7 +1393,7 @@ static int __init capi_init(void) kcapi_exit(); return major_ret; } - capi_class = class_create(THIS_MODULE, "capi"); + capi_class = class_create("capi"); if (IS_ERR(capi_class)) { unregister_chrdev(capi_major, "capi20"); kcapi_exit(); diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index cfbcd9e973c2..09b72f14d4b7 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -131,7 +131,7 @@ EXPORT_SYMBOL(mISDN_dsp_element_unregister); int dsp_pipeline_module_init(void) { - elements_class = class_create(THIS_MODULE, "dsp_pipeline"); + elements_class = class_create("dsp_pipeline"); if (IS_ERR(elements_class)) return PTR_ERR(elements_class); diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index a6b3adcd044a..9255bc11f99d 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -626,7 +626,7 @@ EXPORT_SYMBOL_GPL(devm_led_classdev_unregister); static int __init leds_init(void) { - leds_class = class_create(THIS_MODULE, "leds"); + leds_class = class_create("leds"); if (IS_ERR(leds_class)) return PTR_ERR(leds_class); leds_class->pm = &leds_class_dev_pm_ops; diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index 23bd0c77ac1a..57e987cf84b2 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -888,7 +888,7 @@ adbdev_init(void) return; } - adb_dev_class = class_create(THIS_MODULE, "adb"); + adb_dev_class = class_create("adb"); if (IS_ERR(adb_dev_class)) return; device_create(adb_dev_class, NULL, MKDEV(ADB_MAJOR, 0), NULL, "adb"); diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index 0ed087caf7f3..e9b3ce09e534 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -1063,7 +1063,7 @@ static int __init init_dvbdev(void) goto error; } - dvb_class = class_create(THIS_MODULE, "dvb"); + dvb_class = class_create("dvb"); if (IS_ERR(dvb_class)) { retval = PTR_ERR(dvb_class); goto error; diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 25ab61dae126..043d23aaa3cb 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -785,7 +785,7 @@ int __init lirc_dev_init(void) { int retval; - lirc_class = class_create(THIS_MODULE, "lirc"); + lirc_class = class_create("lirc"); if (IS_ERR(lirc_class)) { pr_err("class_create failed\n"); return PTR_ERR(lirc_class); diff --git a/drivers/misc/c2port/core.c b/drivers/misc/c2port/core.c index fb9a1b49ff6d..f574c83b82cf 100644 --- a/drivers/misc/c2port/core.c +++ b/drivers/misc/c2port/core.c @@ -977,7 +977,7 @@ static int __init c2port_init(void) printk(KERN_INFO "Silicon Labs C2 port support v. " DRIVER_VERSION " - (C) 2007 Rodolfo Giometti\n"); - c2port_class = class_create(THIS_MODULE, "c2port"); + c2port_class = class_create("c2port"); if (IS_ERR(c2port_class)) { printk(KERN_ERR "c2port: failed to allocate class\n"); return PTR_ERR(c2port_class); diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c index 5878329b011a..144d1f2d78ce 100644 --- a/drivers/misc/cxl/file.c +++ b/drivers/misc/cxl/file.c @@ -678,7 +678,7 @@ int __init cxl_file_init(void) pr_devel("CXL device allocated, MAJOR %i\n", MAJOR(cxl_dev)); - cxl_class = class_create(THIS_MODULE, "cxl"); + cxl_class = class_create("cxl"); if (IS_ERR(cxl_class)) { pr_err("Unable to create CXL class\n"); rc = PTR_ERR(cxl_class); diff --git a/drivers/misc/genwqe/card_base.c b/drivers/misc/genwqe/card_base.c index 5b63d179b24e..02628288cd0f 100644 --- a/drivers/misc/genwqe/card_base.c +++ b/drivers/misc/genwqe/card_base.c @@ -1363,7 +1363,7 @@ static int __init genwqe_init_module(void) { int rc; - class_genwqe = class_create(THIS_MODULE, GENWQE_DEVNAME); + class_genwqe = class_create(GENWQE_DEVNAME); if (IS_ERR(class_genwqe)) { pr_err("[%s] create class failed\n", __func__); return -ENOMEM; diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 8d00df9243c4..2c3a991d6e88 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -888,7 +888,7 @@ static int __init ilo_init(void) int error; dev_t dev; - ilo_class = class_create(THIS_MODULE, "iLO"); + ilo_class = class_create("iLO"); if (IS_ERR(ilo_class)) { error = PTR_ERR(ilo_class); goto out; diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 632d4ae21e46..76c771a424f7 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1275,7 +1275,7 @@ static int __init mei_init(void) { int ret; - mei_class = class_create(THIS_MODULE, "mei"); + mei_class = class_create("mei"); if (IS_ERR(mei_class)) { pr_err("couldn't create class\n"); ret = PTR_ERR(mei_class); diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c index 3b058654b45b..6e63f060e4cc 100644 --- a/drivers/misc/ocxl/file.c +++ b/drivers/misc/ocxl/file.c @@ -601,7 +601,7 @@ int ocxl_file_init(void) return rc; } - ocxl_class = class_create(THIS_MODULE, "ocxl"); + ocxl_class = class_create("ocxl"); if (IS_ERR(ocxl_class)) { pr_err("Unable to create ocxl class\n"); unregister_chrdev_region(ocxl_dev, OCXL_NUM_MINORS); diff --git a/drivers/misc/phantom.c b/drivers/misc/phantom.c index ce72e46a2e73..7966a6b8b5b3 100644 --- a/drivers/misc/phantom.c +++ b/drivers/misc/phantom.c @@ -503,7 +503,7 @@ static int __init phantom_init(void) int retval; dev_t dev; - phantom_class = class_create(THIS_MODULE, "phantom"); + phantom_class = class_create("phantom"); if (IS_ERR(phantom_class)) { retval = PTR_ERR(phantom_class); printk(KERN_ERR "phantom: can't register phantom class\n"); diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index 07023397afc7..346bd7cf2e94 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -620,7 +620,7 @@ static int __init uacce_init(void) { int ret; - uacce_class = class_create(THIS_MODULE, UACCE_NAME); + uacce_class = class_create(UACCE_NAME); if (IS_ERR(uacce_class)) return PTR_ERR(uacce_class); diff --git a/drivers/most/most_cdev.c b/drivers/most/most_cdev.c index 4ee536980f71..3ed8f461e01e 100644 --- a/drivers/most/most_cdev.c +++ b/drivers/most/most_cdev.c @@ -491,7 +491,7 @@ static int __init most_cdev_init(void) { int err; - comp.class = class_create(THIS_MODULE, "most_cdev"); + comp.class = class_create("most_cdev"); if (IS_ERR(comp.class)) return PTR_ERR(comp.class); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 9b26f0f2c748..8a1027ad340d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -448,7 +448,7 @@ EXPORT_SYMBOL(hnae_ae_unregister); static int __init hnae_init(void) { - hnae_class = class_create(THIS_MODULE, "hnae"); + hnae_class = class_create("hnae"); return PTR_ERR_OR_ZERO(hnae_class); } diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 1d71f5276241..a9beacd552cf 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1394,7 +1394,7 @@ static int __init ppp_init(void) goto out_net; } - ppp_class = class_create(THIS_MODULE, "ppp"); + ppp_class = class_create("ppp"); if (IS_ERR(ppp_class)) { err = PTR_ERR(ppp_class); goto out_chrdev; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 4cc4eaf80b14..68a7e09a195e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -5748,7 +5748,7 @@ static int __init init_mac80211_hwsim(void) if (err) goto out_exit_netlink; - hwsim_class = class_create(THIS_MODULE, "mac80211_hwsim"); + hwsim_class = class_create("mac80211_hwsim"); if (IS_ERR(hwsim_class)) { err = PTR_ERR(hwsim_class); goto out_exit_virtio; diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 966d0ccd2276..51bbd6bb74b5 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -1174,7 +1174,7 @@ static int __init wwan_init(void) if (err) return err; - wwan_class = class_create(THIS_MODULE, "wwan"); + wwan_class = class_create("wwan"); if (IS_ERR(wwan_class)) { err = PTR_ERR(wwan_class); goto unregister; diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index 2397a903d8f5..edb5fc803211 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -511,7 +511,7 @@ static int __init wwan_hwsim_init(void) if (!wwan_wq) return -ENOMEM; - wwan_hwsim_class = class_create(THIS_MODULE, "wwan_hwsim"); + wwan_hwsim_class = class_create("wwan_hwsim"); if (IS_ERR(wwan_hwsim_class)) { err = PTR_ERR(wwan_hwsim_class); goto err_wq_destroy; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 4976a0069e9c..954dbc105fc8 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -1320,7 +1320,7 @@ int __init nvdimm_bus_init(void) goto err_dimm_chrdev; nvdimm_major = rc; - nd_class = class_create(THIS_MODULE, "nd"); + nd_class = class_create("nd"); if (IS_ERR(nd_class)) { rc = PTR_ERR(nd_class); goto err_class; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c2730b116dc6..877a61fbd78b 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -5381,14 +5381,14 @@ static int __init nvme_core_init(void) if (result < 0) goto destroy_delete_wq; - nvme_class = class_create(THIS_MODULE, "nvme"); + nvme_class = class_create("nvme"); if (IS_ERR(nvme_class)) { result = PTR_ERR(nvme_class); goto unregister_chrdev; } nvme_class->dev_uevent = nvme_class_uevent; - nvme_subsys_class = class_create(THIS_MODULE, "nvme-subsystem"); + nvme_subsys_class = class_create("nvme-subsystem"); if (IS_ERR(nvme_subsys_class)) { result = PTR_ERR(nvme_subsys_class); goto destroy_class; @@ -5399,7 +5399,7 @@ static int __init nvme_core_init(void) if (result < 0) goto destroy_subsys_class; - nvme_ns_chr_class = class_create(THIS_MODULE, "nvme-generic"); + nvme_ns_chr_class = class_create("nvme-generic"); if (IS_ERR(nvme_ns_chr_class)) { result = PTR_ERR(nvme_ns_chr_class); goto unregister_generic_ns; diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index bbaa04a0c502..0069ebff85df 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1254,7 +1254,7 @@ static int __init nvmf_init(void) if (!nvmf_default_host) return -ENOMEM; - nvmf_class = class_create(THIS_MODULE, "nvme-fabrics"); + nvmf_class = class_create("nvme-fabrics"); if (IS_ERR(nvmf_class)) { pr_err("couldn't register class nvme-fabrics\n"); ret = PTR_ERR(nvmf_class); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 5c16372f3b53..af0d01797e5e 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -1562,7 +1562,7 @@ static int __init fcloop_init(void) { int ret; - fcloop_class = class_create(THIS_MODULE, "fcloop"); + fcloop_class = class_create("fcloop"); if (IS_ERR(fcloop_class)) { pr_err("couldn't register class fcloop\n"); ret = PTR_ERR(fcloop_class); diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index 9440d9811eea..46c9a5c3ca14 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -860,7 +860,7 @@ EXPORT_SYMBOL_GPL(__devm_pci_epc_create); static int __init pci_epc_init(void) { - pci_epc_class = class_create(THIS_MODULE, "pci_epc"); + pci_epc_class = class_create("pci_epc"); if (IS_ERR(pci_epc_class)) { pr_err("failed to create pci epc class --> %ld\n", PTR_ERR(pci_epc_class)); diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 3d6f17ff2429..d837da055921 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1804,7 +1804,7 @@ static int __init switchtec_init(void) if (rc) return rc; - switchtec_class = class_create(THIS_MODULE, "switchtec"); + switchtec_class = class_create("switchtec"); if (IS_ERR(switchtec_class)) { rc = PTR_ERR(switchtec_class); goto err_create_class; diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 9951efc03eaa..6464dcb56d56 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -1233,7 +1233,7 @@ static void phy_release(struct device *dev) static int __init phy_core_init(void) { - phy_class = class_create(THIS_MODULE, "phy"); + phy_class = class_create("phy"); if (IS_ERR(phy_class)) { pr_err("failed to create phy class --> %ld\n", PTR_ERR(phy_class)); diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index f3d7c1da299f..1bf393239d40 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1462,7 +1462,7 @@ EXPORT_SYMBOL_GPL(power_supply_get_drvdata); static int __init power_supply_class_init(void) { - power_supply_class = class_create(THIS_MODULE, "power_supply"); + power_supply_class = class_create("power_supply"); if (IS_ERR(power_supply_class)) return PTR_ERR(power_supply_class); diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 22a65ad4e46e..5d19baae6a38 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -456,7 +456,7 @@ static int __init pps_init(void) { int err; - pps_class = class_create(THIS_MODULE, "pps"); + pps_class = class_create("pps"); if (IS_ERR(pps_class)) { pr_err("failed to allocate class\n"); return PTR_ERR(pps_class); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 62d4d29e7c05..790f9250b381 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -460,7 +460,7 @@ static int __init ptp_init(void) { int err; - ptp_class = class_create(THIS_MODULE, "ptp"); + ptp_class = class_create("ptp"); if (IS_ERR(ptp_class)) { pr_err("ptp: failed to allocate class\n"); return PTR_ERR(ptp_class); diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 43db495f1986..deb96c3160a7 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2603,7 +2603,7 @@ static int __init mport_init(void) int ret; /* Create device class needed by udev */ - dev_class = class_create(THIS_MODULE, DRV_NAME); + dev_class = class_create(DRV_NAME); if (IS_ERR(dev_class)) { rmcd_error("Unable to create " DRV_NAME " class"); return PTR_ERR(dev_class); diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index db4c265287ae..acaf9cda014c 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -2297,7 +2297,7 @@ static int __init riocm_init(void) int ret; /* Create device class needed by udev */ - dev_class = class_create(THIS_MODULE, DRV_NAME); + dev_class = class_create(DRV_NAME); if (IS_ERR(dev_class)) { riocm_error("Cannot create " DRV_NAME " class"); return PTR_ERR(dev_class); diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index a2207c0cf432..5039df757127 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -694,7 +694,7 @@ static int __init rpmsg_init(void) { int ret; - rpmsg_class = class_create(THIS_MODULE, "rpmsg"); + rpmsg_class = class_create("rpmsg"); if (IS_ERR(rpmsg_class)) { pr_err("failed to create rpmsg class\n"); return PTR_ERR(rpmsg_class); diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index e5b7b48cffac..edfd942f8c54 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -475,7 +475,7 @@ EXPORT_SYMBOL_GPL(devm_rtc_device_register); static int __init rtc_init(void) { - rtc_class = class_create(THIS_MODULE, "rtc"); + rtc_class = class_create("rtc"); if (IS_ERR(rtc_class)) { pr_err("couldn't create class\n"); return PTR_ERR(rtc_class); diff --git a/drivers/s390/char/hmcdrv_dev.c b/drivers/s390/char/hmcdrv_dev.c index cb8fdf057eca..8d50c894711f 100644 --- a/drivers/s390/char/hmcdrv_dev.c +++ b/drivers/s390/char/hmcdrv_dev.c @@ -308,7 +308,7 @@ int hmcdrv_dev_init(void) * /proc/devices), but not under /dev nor /sys/devices/virtual. So * we have to create an associated class (see /sys/class). */ - hmcdrv_dev_class = class_create(THIS_MODULE, HMCDRV_DEV_CLASS); + hmcdrv_dev_class = class_create(HMCDRV_DEV_CLASS); if (IS_ERR(hmcdrv_dev_class)) { rc = PTR_ERR(hmcdrv_dev_class); diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c index 09d7570d3b7d..7115c0f85650 100644 --- a/drivers/s390/char/raw3270.c +++ b/drivers/s390/char/raw3270.c @@ -1319,7 +1319,7 @@ static int raw3270_init(void) if (rc == 0) { /* Create attributes for early (= console) device. */ mutex_lock(&raw3270_mutex); - class3270 = class_create(THIS_MODULE, "3270"); + class3270 = class_create("3270"); list_for_each_entry(rp, &raw3270_devices, list) { get_device(&rp->cdev->dev); raw3270_create_attributes(rp); diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c index c21dc68e05a0..277a0f903d11 100644 --- a/drivers/s390/char/tape_class.c +++ b/drivers/s390/char/tape_class.c @@ -117,7 +117,7 @@ EXPORT_SYMBOL(unregister_tape_dev); static int __init tape_init(void) { - tape_class = class_create(THIS_MODULE, "tape390"); + tape_class = class_create("tape390"); return 0; } diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index ed970ecfafdf..6946ba9a9de2 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -699,7 +699,7 @@ static int vmlogrdr_register_driver(void) if (ret) goto out_iucv; - vmlogrdr_class = class_create(THIS_MODULE, "vmlogrdr"); + vmlogrdr_class = class_create("vmlogrdr"); if (IS_ERR(vmlogrdr_class)) { ret = PTR_ERR(vmlogrdr_class); vmlogrdr_class = NULL; diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 131293f7f152..82efdd20ad01 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -1022,7 +1022,7 @@ static int __init ur_init(void) debug_set_level(vmur_dbf, 6); - vmur_class = class_create(THIS_MODULE, "vmur"); + vmur_class = class_create("vmur"); if (IS_ERR(vmur_class)) { rc = PTR_ERR(vmur_class); goto fail_free_dbf; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 6fe05bb82c77..582ac301d315 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -2171,7 +2171,7 @@ static int __init zcdn_init(void) int rc; /* create a new class 'zcrypt' */ - zcrypt_class = class_create(THIS_MODULE, ZCRYPT_NAME); + zcrypt_class = class_create(ZCRYPT_NAME); if (IS_ERR(zcrypt_class)) { rc = PTR_ERR(zcrypt_class); goto out_class_create_failed; diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c index e300cf26bc2a..75701b165e91 100644 --- a/drivers/sbus/char/oradax.c +++ b/drivers/sbus/char/oradax.c @@ -323,7 +323,7 @@ static int __init dax_attach(void) goto done; } - cl = class_create(THIS_MODULE, DAX_NAME); + cl = class_create(DAX_NAME); if (IS_ERR(cl)) { dax_err("class_create failed"); ret = PTR_ERR(cl); diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index 72fe6df78bc5..ac648bb8f7e7 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -995,7 +995,7 @@ static int __init init_ch_module(void) int rc; printk(KERN_INFO "SCSI Media Changer driver v" VERSION " \n"); - ch_sysfs_class = class_create(THIS_MODULE, "scsi_changer"); + ch_sysfs_class = class_create("scsi_changer"); if (IS_ERR(ch_sysfs_class)) { rc = PTR_ERR(ch_sysfs_class); return rc; diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 395b00b942f7..debd36974119 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3880,7 +3880,7 @@ static int cxlflash_class_init(void) cxlflash_major = MAJOR(devno); - cxlflash_class = class_create(THIS_MODULE, "cxlflash"); + cxlflash_class = class_create("cxlflash"); if (IS_ERR(cxlflash_class)) { rc = PTR_ERR(cxlflash_class); pr_err("%s: class_create failed rc=%d\n", __func__, rc); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 836ddc476764..7d57cc92532c 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -5346,7 +5346,7 @@ static int __init pmcraid_init(void) } pmcraid_major = MAJOR(dev); - pmcraid_class = class_create(THIS_MODULE, PMCRAID_DEVFILE); + pmcraid_class = class_create(PMCRAID_DEVFILE); if (IS_ERR(pmcraid_class)) { error = PTR_ERR(pmcraid_class); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index a91049213203..4997f880d4a4 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1677,7 +1677,7 @@ init_sg(void) SG_MAX_DEVS, "sg"); if (rc) return rc; - sg_sysfs_class = class_create(THIS_MODULE, "scsi_generic"); + sg_sysfs_class = class_create("scsi_generic"); if ( IS_ERR(sg_sysfs_class) ) { rc = PTR_ERR(sg_sysfs_class); goto err_out; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 5a038c667401..539e70c7daed 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -877,7 +877,7 @@ static int __init spidev_init(void) if (status < 0) return status; - spidev_class = class_create(THIS_MODULE, "spidev"); + spidev_class = class_create("spidev"); if (IS_ERR(spidev_class)) { unregister_chrdev(SPIDEV_MAJOR, spidev_spi_driver.driver.name); return PTR_ERR(spidev_class); diff --git a/drivers/staging/fieldbus/anybuss/arcx-anybus.c b/drivers/staging/fieldbus/anybuss/arcx-anybus.c index 9af2e63050d1..369400ec30d8 100644 --- a/drivers/staging/fieldbus/anybuss/arcx-anybus.c +++ b/drivers/staging/fieldbus/anybuss/arcx-anybus.c @@ -352,7 +352,7 @@ static int __init controller_init(void) { int err; - controller_class = class_create(THIS_MODULE, "arcx_anybus_controller"); + controller_class = class_create("arcx_anybus_controller"); if (IS_ERR(controller_class)) return PTR_ERR(controller_class); err = platform_driver_register(&controller_driver); diff --git a/drivers/staging/greybus/authentication.c b/drivers/staging/greybus/authentication.c index 297e69f011c7..7e01790a4659 100644 --- a/drivers/staging/greybus/authentication.c +++ b/drivers/staging/greybus/authentication.c @@ -402,7 +402,7 @@ int cap_init(void) { int ret; - cap_class = class_create(THIS_MODULE, "gb_authenticate"); + cap_class = class_create("gb_authenticate"); if (IS_ERR(cap_class)) return PTR_ERR(cap_class); diff --git a/drivers/staging/greybus/fw-management.c b/drivers/staging/greybus/fw-management.c index 3342b84597da..cd9141e4b794 100644 --- a/drivers/staging/greybus/fw-management.c +++ b/drivers/staging/greybus/fw-management.c @@ -696,7 +696,7 @@ int fw_mgmt_init(void) { int ret; - fw_mgmt_class = class_create(THIS_MODULE, "gb_fw_mgmt"); + fw_mgmt_class = class_create("gb_fw_mgmt"); if (IS_ERR(fw_mgmt_class)) return PTR_ERR(fw_mgmt_class); diff --git a/drivers/staging/greybus/raw.c b/drivers/staging/greybus/raw.c index 2a375f407d38..8bca8cb12cc6 100644 --- a/drivers/staging/greybus/raw.c +++ b/drivers/staging/greybus/raw.c @@ -340,7 +340,7 @@ static int raw_init(void) dev_t dev; int retval; - raw_class = class_create(THIS_MODULE, "gb_raw"); + raw_class = class_create("gb_raw"); if (IS_ERR(raw_class)) { retval = PTR_ERR(raw_class); goto error_class; diff --git a/drivers/staging/pi433/pi433_if.c b/drivers/staging/pi433/pi433_if.c index b59f6a4cb611..f08fdf06d566 100644 --- a/drivers/staging/pi433/pi433_if.c +++ b/drivers/staging/pi433/pi433_if.c @@ -1400,7 +1400,7 @@ static int __init pi433_init(void) if (status < 0) return status; - pi433_class = class_create(THIS_MODULE, "pi433"); + pi433_class = class_create("pi433"); if (IS_ERR(pi433_class)) { unregister_chrdev(MAJOR(pi433_dev), pi433_spi_driver.driver.name); diff --git a/drivers/staging/vme_user/vme_user.c b/drivers/staging/vme_user/vme_user.c index 4e533c0bfe6d..b9367b575d00 100644 --- a/drivers/staging/vme_user/vme_user.c +++ b/drivers/staging/vme_user/vme_user.c @@ -614,7 +614,7 @@ static int vme_user_probe(struct vme_dev *vdev) } /* Create sysfs entries - on udev systems this creates the dev files */ - vme_user_sysfs_class = class_create(THIS_MODULE, driver_name); + vme_user_sysfs_class = class_create(driver_name); if (IS_ERR(vme_user_sysfs_class)) { dev_err(&vdev->dev, "Error creating vme_user class.\n"); err = PTR_ERR(vme_user_sysfs_class); diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 452cbb8ad484..0eb342de0b00 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -1226,7 +1226,7 @@ static int __init tee_init(void) { int rc; - tee_class = class_create(THIS_MODULE, "tee"); + tee_class = class_create("tee"); if (IS_ERR(tee_class)) { pr_err("couldn't create class\n"); return PTR_ERR(tee_class); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 36fb945fdad4..1382d9050ce8 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3512,7 +3512,7 @@ static char *tty_devnode(const struct device *dev, umode_t *mode) static int __init tty_class_init(void) { - tty_class = class_create(THIS_MODULE, "tty"); + tty_class = class_create("tty"); if (IS_ERR(tty_class)) return PTR_ERR(tty_class); tty_class->devnode = tty_devnode; diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1dc07f9214d5..498ba9c0ee93 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -804,7 +804,7 @@ int __init vcs_init(void) if (register_chrdev(VCS_MAJOR, "vcs", &vcs_fops)) panic("unable to get major %d for vcs device", VCS_MAJOR); - vc_class = class_create(THIS_MODULE, "vc"); + vc_class = class_create("vc"); device_create(vc_class, NULL, MKDEV(VCS_MAJOR, 0), NULL, "vcs"); device_create(vc_class, NULL, MKDEV(VCS_MAJOR, 64), NULL, "vcsu"); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 57a5c23b51d4..5496bf4b76ec 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4241,7 +4241,7 @@ static int __init vtconsole_class_init(void) { int i; - vtconsole_class = class_create(THIS_MODULE, "vtconsole"); + vtconsole_class = class_create("vtconsole"); if (IS_ERR(vtconsole_class)) { pr_warn("Unable to create vt console class; errno = %ld\n", PTR_ERR(vtconsole_class)); diff --git a/drivers/usb/core/file.c b/drivers/usb/core/file.c index da7d88e069e6..c4ed3310e069 100644 --- a/drivers/usb/core/file.c +++ b/drivers/usb/core/file.c @@ -88,7 +88,7 @@ static int init_usb_class(void) } kref_init(&usb_class->kref); - usb_class->class = class_create(THIS_MODULE, "usbmisc"); + usb_class->class = class_create("usbmisc"); if (IS_ERR(usb_class->class)) { result = PTR_ERR(usb_class->class); printk(KERN_ERR "class_create failed for usb devices\n"); diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index a8da3b4a2855..9f6b10134121 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -1325,7 +1325,7 @@ int ghid_setup(struct usb_gadget *g, int count) int status; dev_t dev; - hidg_class = class_create(THIS_MODULE, "hidg"); + hidg_class = class_create("hidg"); if (IS_ERR(hidg_class)) { status = PTR_ERR(hidg_class); hidg_class = NULL; diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c index 4903d761a872..28db3e336e7d 100644 --- a/drivers/usb/gadget/function/f_printer.c +++ b/drivers/usb/gadget/function/f_printer.c @@ -1512,7 +1512,7 @@ static int gprinter_setup(int count) int status; dev_t devt; - usb_gadget_class = class_create(THIS_MODULE, "usb_printer_gadget"); + usb_gadget_class = class_create("usb_printer_gadget"); if (IS_ERR(usb_gadget_class)) { status = PTR_ERR(usb_gadget_class); usb_gadget_class = NULL; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 23b0629a8774..df930b041c33 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1758,7 +1758,7 @@ static int __init usb_udc_init(void) { int rc; - udc_class = class_create(THIS_MODULE, "udc"); + udc_class = class_create("udc"); if (IS_ERR(udc_class)) { pr_err("failed to create udc class --> %ld\n", PTR_ERR(udc_class)); diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index abb1cd35d8a6..952c56789258 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1379,7 +1379,7 @@ int __init mon_bin_init(void) { int rc; - mon_bin_class = class_create(THIS_MODULE, "usbmon"); + mon_bin_class = class_create("usbmon"); if (IS_ERR(mon_bin_class)) { rc = PTR_ERR(mon_bin_class); goto err_class; diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index 56814ef80c24..0395bd5dbd3e 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -392,7 +392,7 @@ EXPORT_SYMBOL_GPL(usb_role_switch_get_drvdata); static int __init usb_roles_init(void) { - role_class = class_create(THIS_MODULE, "usb_role"); + role_class = class_create("usb_role"); return PTR_ERR_OR_ZERO(role_class); } subsys_initcall(usb_roles_init); diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 0c3b48616a9f..c421b83f6fa2 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1793,7 +1793,7 @@ static int vduse_init(void) int ret; struct device *dev; - vduse_class = class_create(THIS_MODULE, "vduse"); + vduse_class = class_create("vduse"); if (IS_ERR(vduse_class)) return PTR_ERR(vduse_class); diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index 27d5ba7cf9dc..fc75c1000d74 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -878,7 +878,7 @@ int __init vfio_group_init(void) return ret; /* /dev/vfio/$GROUP */ - vfio.class = class_create(THIS_MODULE, "vfio"); + vfio.class = class_create("vfio"); if (IS_ERR(vfio.class)) { ret = PTR_ERR(vfio.class); goto err_group_class; diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 43bd6b76e2b6..9ae671b98592 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1408,7 +1408,7 @@ static int __init vfio_init(void) goto err_virqfd; /* /sys/class/vfio-dev/vfioX */ - vfio.device_class = class_create(THIS_MODULE, "vfio-dev"); + vfio.device_class = class_create("vfio-dev"); if (IS_ERR(vfio.device_class)) { ret = PTR_ERR(vfio.device_class); goto err_dev_class; diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c index 6eea72aa8dbf..9a885d398c22 100644 --- a/drivers/video/backlight/backlight.c +++ b/drivers/video/backlight/backlight.c @@ -751,7 +751,7 @@ static void __exit backlight_class_exit(void) static int __init backlight_class_init(void) { - backlight_class = class_create(THIS_MODULE, "backlight"); + backlight_class = class_create("backlight"); if (IS_ERR(backlight_class)) { pr_warn("Unable to create backlight class; errno = %ld\n", PTR_ERR(backlight_class)); diff --git a/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c index db56e465aaff..77c5cb2a44e2 100644 --- a/drivers/video/backlight/lcd.c +++ b/drivers/video/backlight/lcd.c @@ -323,7 +323,7 @@ static void __exit lcd_class_exit(void) static int __init lcd_class_init(void) { - lcd_class = class_create(THIS_MODULE, "lcd"); + lcd_class = class_create("lcd"); if (IS_ERR(lcd_class)) { pr_warn("Unable to create backlight class; errno = %ld\n", PTR_ERR(lcd_class)); diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 875541ff185b..b073795d99d0 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1749,7 +1749,7 @@ fbmem_init(void) goto err_chrdev; } - fb_class = class_create(THIS_MODULE, "graphics"); + fb_class = class_create("graphics"); if (IS_ERR(fb_class)) { ret = PTR_ERR(fb_class); pr_warn("Unable to create fb class; errno = %d\n", ret); diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index b39580ad4ce5..3c3148588491 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -361,7 +361,7 @@ static int __init init_coda_psdev(void) __func__, CODA_PSDEV_MAJOR); return -EIO; } - coda_psdev_class = class_create(THIS_MODULE, "coda"); + coda_psdev_class = class_create("coda"); if (IS_ERR(coda_psdev_class)) { err = PTR_ERR(coda_psdev_class); goto out_chrdev; diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 179a5c5e28fd..91e89e68177e 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -623,7 +623,7 @@ static int __init cuse_init(void) /* CUSE is not prepared for FUSE_DEV_IOC_CLONE */ cuse_channel_fops.unlocked_ioctl = NULL; - cuse_class = class_create(THIS_MODULE, "cuse"); + cuse_class = class_create("cuse"); if (IS_ERR(cuse_class)) return PTR_ERR(cuse_class); diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index ab82e5f05346..aa178304bc03 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -64,7 +64,7 @@ void pstore_register_pmsg(void) goto err; } - pmsg_class = class_create(THIS_MODULE, PMSG_NAME); + pmsg_class = class_create(PMSG_NAME); if (IS_ERR(pmsg_class)) { pr_err("device class file already in use\n"); goto err_class; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index bf736f14f0c1..cda598fc5fa0 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -256,7 +256,6 @@ extern void class_destroy(struct class *cls); /** * class_create - create a struct class structure - * @owner: dummy pointer, does nothing, will be removed soon. * @name: pointer to a string for the name of this class. * * This is used to create a struct class pointer that can then be used @@ -267,7 +266,7 @@ extern void class_destroy(struct class *cls); * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ -#define class_create(owner, name) \ +#define class_create(name) \ ({ \ static struct lock_class_key __key; \ __class_create(name, &__key); \ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index a53b9360b72e..ad011308cebe 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -347,7 +347,7 @@ ATTRIBUTE_GROUPS(bdi_dev); static __init int bdi_class_init(void) { - bdi_class = class_create(THIS_MODULE, "bdi"); + bdi_class = class_create("bdi"); if (IS_ERR(bdi_class)) return PTR_ERR(bdi_class); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 08542dfc2dc5..2934d7f4d564 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -112,7 +112,7 @@ void hci_init_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - bt_class = class_create(THIS_MODULE, "bluetooth"); + bt_class = class_create("bluetooth"); return PTR_ERR_OR_ZERO(bt_class); } diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 8d36303f3935..db720efa811d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -490,7 +490,7 @@ static int __init idletimer_tg_init(void) { int err; - idletimer_tg_class = class_create(THIS_MODULE, "xt_idletimer"); + idletimer_tg_class = class_create("xt_idletimer"); err = PTR_ERR(idletimer_tg_class); if (IS_ERR(idletimer_tg_class)) { pr_debug("couldn't register device class\n"); diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index e54eb752e1ba..a3d3249639d0 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -1418,7 +1418,7 @@ static int __init mbochs_dev_init(void) if (ret) goto err_cdev; - mbochs_class = class_create(THIS_MODULE, MBOCHS_CLASS_NAME); + mbochs_class = class_create(MBOCHS_CLASS_NAME); if (IS_ERR(mbochs_class)) { pr_err("Error: failed to register mbochs_dev class\n"); ret = PTR_ERR(mbochs_class); diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c index e8400fdab71d..ef1630fc5a91 100644 --- a/samples/vfio-mdev/mdpy.c +++ b/samples/vfio-mdev/mdpy.c @@ -705,7 +705,7 @@ static int __init mdpy_dev_init(void) if (ret) goto err_cdev; - mdpy_class = class_create(THIS_MODULE, MDPY_CLASS_NAME); + mdpy_class = class_create(MDPY_CLASS_NAME); if (IS_ERR(mdpy_class)) { pr_err("Error: failed to register mdpy_dev class\n"); ret = PTR_ERR(mdpy_class); diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index e887de672c52..0b6c386e620d 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -1316,7 +1316,7 @@ static int __init mtty_dev_init(void) if (ret) goto err_cdev; - mtty_dev.vd_class = class_create(THIS_MODULE, MTTY_CLASS_NAME); + mtty_dev.vd_class = class_create(MTTY_CLASS_NAME); if (IS_ERR(mtty_dev.vd_class)) { pr_err("Error: failed to register mtty_dev class\n"); diff --git a/sound/sound_core.c b/sound/sound_core.c index 3e7dd6fcb7cf..4f6911274d56 100644 --- a/sound/sound_core.c +++ b/sound/sound_core.c @@ -45,7 +45,7 @@ static int __init init_soundcore(void) if (rc) return rc; - sound_class = class_create(THIS_MODULE, "sound"); + sound_class = class_create("sound"); if (IS_ERR(sound_class)) { cleanup_oss_soundcore(); return PTR_ERR(sound_class); diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c index 01ceb98c15a0..3eba10c1e3e8 100644 --- a/tools/testing/nvdimm/test/ndtest.c +++ b/tools/testing/nvdimm/test/ndtest.c @@ -921,7 +921,7 @@ static __init int ndtest_init(void) nfit_test_setup(ndtest_resource_lookup, NULL); - ndtest_dimm_class = class_create(THIS_MODULE, "nfit_test_dimm"); + ndtest_dimm_class = class_create("nfit_test_dimm"); if (IS_ERR(ndtest_dimm_class)) { rc = PTR_ERR(ndtest_dimm_class); goto err_register; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c75abb497a1a..45b1c072e349 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -3282,7 +3282,7 @@ static __init int nfit_test_init(void) if (!nfit_wq) return -ENOMEM; - nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); + nfit_test_dimm = class_create("nfit_test_dimm"); if (IS_ERR(nfit_test_dimm)) { rc = PTR_ERR(nfit_test_dimm); goto err_register; -- GitLab From a2fd6e42e4fb661e183977072022b7dd8dd65d90 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:36 +0100 Subject: [PATCH 0757/5631] driver core: class: make class_dev_iter_init() options const class_dev_iter_init() does not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 4 ++-- include/linux/device/class.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 9439c6c7466f..5a60e8895165 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -284,8 +284,8 @@ EXPORT_SYMBOL_GPL(class_destroy); * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ -void class_dev_iter_init(struct class_dev_iter *iter, struct class *class, - struct device *start, const struct device_type *type) +void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, + const struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index cda598fc5fa0..1f5cfae8db88 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -103,8 +103,8 @@ void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, + const struct class *class, + const struct device *start, const struct device_type *type); extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); -- GitLab From 69df024ebbf8b1d4d8f0808b5700688fed9e45e9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:37 +0100 Subject: [PATCH 0758/5631] driver core: class: make class_for_each_device() options const class_for_each_device() does not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 +- include/linux/device/class.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 5a60e8895165..4937d660c571 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -355,7 +355,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_exit); * @fn is allowed to do anything including calling back into class * code. There's no locking restriction. */ -int class_for_each_device(struct class *class, struct device *start, +int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *, void *)) { struct class_dev_iter iter; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 1f5cfae8db88..fdbcd487e508 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -109,7 +109,7 @@ extern void class_dev_iter_init(struct class_dev_iter *iter, extern struct device *class_dev_iter_next(struct class_dev_iter *iter); extern void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(struct class *class, struct device *start, +extern int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); extern struct device *class_find_device(struct class *class, -- GitLab From cf41015ea8d3f2ae451d9b7e39ef42569caeb875 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:38 +0100 Subject: [PATCH 0759/5631] driver core: class: make class_find_device*() options const The class_find_device*() functions do not modify the struct class or the struct device passed into it, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 +- include/linux/device/class.h | 25 ++++++++++++------------- 2 files changed, 13 insertions(+), 14 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 4937d660c571..52ba0187e66d 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -402,7 +402,7 @@ EXPORT_SYMBOL_GPL(class_for_each_device); * @match is allowed to do anything including calling back into class * code. There's no locking restriction. */ -struct device *class_find_device(struct class *class, struct device *start, +struct device *class_find_device(const struct class *class, const struct device *start, const void *data, int (*match)(struct device *, const void *)) { diff --git a/include/linux/device/class.h b/include/linux/device/class.h index fdbcd487e508..dfa8958105e7 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -112,8 +112,8 @@ extern void class_dev_iter_exit(struct class_dev_iter *iter); extern int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(struct class *class, - struct device *start, const void *data, +extern struct device *class_find_device(const struct class *class, + const struct device *start, const void *data, int (*match)(struct device *, const void *)); /** @@ -122,7 +122,7 @@ extern struct device *class_find_device(struct class *class, * @class: class type * @name: name of the device to match */ -static inline struct device *class_find_device_by_name(struct class *class, +static inline struct device *class_find_device_by_name(const struct class *class, const char *name) { return class_find_device(class, NULL, name, device_match_name); @@ -134,8 +134,8 @@ static inline struct device *class_find_device_by_name(struct class *class, * @class: class type * @np: of_node of the device to match. */ -static inline struct device * -class_find_device_by_of_node(struct class *class, const struct device_node *np) +static inline struct device *class_find_device_by_of_node(const struct class *class, + const struct device_node *np) { return class_find_device(class, NULL, np, device_match_of_node); } @@ -146,9 +146,8 @@ class_find_device_by_of_node(struct class *class, const struct device_node *np) * @class: class type * @fwnode: fwnode of the device to match. */ -static inline struct device * -class_find_device_by_fwnode(struct class *class, - const struct fwnode_handle *fwnode) +static inline struct device *class_find_device_by_fwnode(const struct class *class, + const struct fwnode_handle *fwnode) { return class_find_device(class, NULL, fwnode, device_match_fwnode); } @@ -159,7 +158,7 @@ class_find_device_by_fwnode(struct class *class, * @class: class type * @devt: device type of the device to match. */ -static inline struct device *class_find_device_by_devt(struct class *class, +static inline struct device *class_find_device_by_devt(const struct class *class, dev_t devt) { return class_find_device(class, NULL, &devt, device_match_devt); @@ -173,14 +172,14 @@ struct acpi_device; * @class: class type * @adev: ACPI_COMPANION device to match. */ -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const struct acpi_device *adev) { return class_find_device(class, NULL, adev, device_match_acpi_dev); } #else -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const void *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const void *adev) { return NULL; } -- GitLab From 80842a92907bd68454591f9c7a73778f130ac38f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:39 +0100 Subject: [PATCH 0760/5631] driver core: class: make class_create/remove_file*() options const The class_create_file*() and class_remove_file*() functions do not modify the struct class at all, so mark them as const * to enforce that. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-8-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 4 ++-- include/linux/device/class.h | 10 +++++----- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 52ba0187e66d..3d65221b0dcb 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -87,7 +87,7 @@ static const struct kobj_type class_ktype = { static struct kset *class_kset; -int class_create_file_ns(struct class *cls, const struct class_attribute *attr, +int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { int error; @@ -101,7 +101,7 @@ int class_create_file_ns(struct class *cls, const struct class_attribute *attr, } EXPORT_SYMBOL_GPL(class_create_file_ns); -void class_remove_file_ns(struct class *cls, const struct class_attribute *attr, +void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { if (cls) diff --git a/include/linux/device/class.h b/include/linux/device/class.h index dfa8958105e7..75c1451fcc63 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -200,20 +200,20 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(struct class *class, +extern int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, const void *ns); -extern void class_remove_file_ns(struct class *class, +extern void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, const void *ns); -static inline int __must_check class_create_file(struct class *class, - const struct class_attribute *attr) +static inline int __must_check class_create_file(const struct class *class, + const struct class_attribute *attr) { return class_create_file_ns(class, attr, NULL); } -static inline void class_remove_file(struct class *class, +static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { return class_remove_file_ns(class, attr, NULL); -- GitLab From d2fff09656369d5465585ad2c72d8ba8ada758b5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:40 +0100 Subject: [PATCH 0761/5631] driver core: device: make device_destroy() take a const class * device_destroy() does not modify the struct class passed into it, so mark it as const to enforce this rule. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-9-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 2 +- include/linux/device.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 57076837b33e..f3b7040ef9b6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4383,7 +4383,7 @@ EXPORT_SYMBOL_GPL(device_create_with_groups); * This call unregisters and cleans up a device that was created with a * call to device_create(). */ -void device_destroy(struct class *class, dev_t devt) +void device_destroy(const struct class *class, dev_t devt) { struct device *dev; diff --git a/include/linux/device.h b/include/linux/device.h index 12dc08aa5c0f..2562451b875b 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1021,7 +1021,7 @@ __printf(6, 7) struct device * device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); -void device_destroy(struct class *cls, dev_t devt); +void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); -- GitLab From a010eb8812435015118662b23be799670f641a83 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:41 +0100 Subject: [PATCH 0762/5631] tpm: fix up the tpm_class shutdown_pre pointer when created Do not wait until long after the struct class has been created to set the shutdown_pre pointer for the tpm_class, assign it right away. This is the only in-kernel offender that tries to modify the device->class pointer contents after it has been assigned to a device, so fix that up by doing the function pointer assignment before it is matched with the device. Because of this, the patch should go through the driver core tree to allow later changes to struct device to be possible. Cc: Peter Huewe Cc: Jarkko Sakkinen Cc: Jason Gunthorpe Cc: linux-integrity@vger.kernel.org Reviewed-by: Jarkko Sakkinen Link: https://lore.kernel.org/r/20230313181843.1207845-10-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm-chip.c | 3 +-- drivers/char/tpm/tpm-interface.c | 1 + drivers/char/tpm/tpm.h | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index b99f55f2d4fd..7c444209a256 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -282,7 +282,7 @@ static void tpm_dev_release(struct device *dev) * * Return: always 0 (i.e. success) */ -static int tpm_class_shutdown(struct device *dev) +int tpm_class_shutdown(struct device *dev) { struct tpm_chip *chip = container_of(dev, struct tpm_chip, dev); @@ -337,7 +337,6 @@ struct tpm_chip *tpm_chip_alloc(struct device *pdev, device_initialize(&chip->dev); chip->dev.class = tpm_class; - chip->dev.class->shutdown_pre = tpm_class_shutdown; chip->dev.release = tpm_dev_release; chip->dev.parent = pdev; chip->dev.groups = chip->groups; diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 8763c820d1f8..43e23a04433a 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -467,6 +467,7 @@ static int __init tpm_init(void) int rc; tpm_class = class_create("tpm"); + tpm_class->shutdown_pre = tpm_class_shutdown; if (IS_ERR(tpm_class)) { pr_err("couldn't create tpm class\n"); return PTR_ERR(tpm_class); diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 24ee4e1cc452..a45eb39db0c4 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -183,6 +183,7 @@ int tpm1_get_pcr_allocation(struct tpm_chip *chip); unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm_pm_suspend(struct device *dev); int tpm_pm_resume(struct device *dev); +int tpm_class_shutdown(struct device *dev); static inline void tpm_msleep(unsigned int delay_msec) { -- GitLab From 9fa120fbd507e58af3494b8765427fdc8181e1eb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:42 +0100 Subject: [PATCH 0763/5631] driver core: device: mark struct class in struct device as constant The pointer to a struct class in a struct device should never be used to change anything in that class. So mark it as constant to enforce this requirement. This requires a few minor changes to some internal driver core functions to enforce the const * being used here now. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-11-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 10 +++++----- include/linux/device.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index f3b7040ef9b6..0970db630839 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2820,7 +2820,7 @@ EXPORT_SYMBOL_GPL(devm_device_add_groups); static int device_add_attrs(struct device *dev) { - struct class *class = dev->class; + const struct class *class = dev->class; const struct device_type *type = dev->type; int error; @@ -2887,7 +2887,7 @@ static int device_add_attrs(struct device *dev) static void device_remove_attrs(struct device *dev) { - struct class *class = dev->class; + const struct class *class = dev->class; const struct device_type *type = dev->type; if (dev->physical_location) { @@ -3120,7 +3120,7 @@ struct kobject *virtual_device_parent(struct device *dev) struct class_dir { struct kobject kobj; - struct class *class; + const struct class *class; }; #define to_class_dir(obj) container_of(obj, struct class_dir, kobj) @@ -3145,7 +3145,7 @@ static const struct kobj_type class_dir_ktype = { }; static struct kobject * -class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) +class_dir_create_and_add(const struct class *class, struct kobject *parent_kobj) { struct class_dir *dir; int retval; @@ -4580,7 +4580,7 @@ static int device_attrs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { struct kobject *kobj = &dev->kobj; - struct class *class = dev->class; + const struct class *class = dev->class; const struct device_type *type = dev->type; int error; diff --git a/include/linux/device.h b/include/linux/device.h index 2562451b875b..ea07b95b06e5 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -631,7 +631,7 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct class *class; + const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); -- GitLab From 2bd5c63978b771462da10d8771f56a1e656501d9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:18:43 +0100 Subject: [PATCH 0764/5631] driver core: device: make device_create*() take a const struct class * The functions device_create() and device_create_with_groups() do not modify the struct class passed into it, so enforce this by changing the function parameters to be struct const class. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313181843.1207845-12-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 +++--- include/linux/device.h | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 0970db630839..f1889b9cab45 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4253,7 +4253,7 @@ static void device_create_release(struct device *dev) } static __printf(6, 0) struct device * -device_create_groups_vargs(struct class *class, struct device *parent, +device_create_groups_vargs(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, va_list args) @@ -4317,7 +4317,7 @@ device_create_groups_vargs(struct class *class, struct device *parent, * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ -struct device *device_create(struct class *class, struct device *parent, +struct device *device_create(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...) { va_list vargs; @@ -4358,7 +4358,7 @@ EXPORT_SYMBOL_GPL(device_create); * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ -struct device *device_create_with_groups(struct class *class, +struct device *device_create_with_groups(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, diff --git a/include/linux/device.h b/include/linux/device.h index ea07b95b06e5..862397ae520d 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1015,10 +1015,10 @@ bool device_is_bound(struct device *dev); * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * -device_create(struct class *cls, struct device *parent, dev_t devt, +device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * -device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, +device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); -- GitLab From d7d744abc08f008f105dc7fc59805de6beeb8ec8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:12 -0600 Subject: [PATCH 0765/5631] misc/sram: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230310144713.1543544-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/sram.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/misc/sram.c b/drivers/misc/sram.c index dec92580a42c..99413310956b 100644 --- a/drivers/misc/sram.c +++ b/drivers/misc/sram.c @@ -218,14 +218,9 @@ static int sram_reserve_regions(struct sram_dev *sram, struct resource *res) block->res = child_res; list_add_tail(&block->list, &reserve_list); - if (of_find_property(child, "export", NULL)) - block->export = true; - - if (of_find_property(child, "pool", NULL)) - block->pool = true; - - if (of_find_property(child, "protect-exec", NULL)) - block->protect_exec = true; + block->export = of_property_read_bool(child, "export"); + block->pool = of_property_read_bool(child, "pool"); + block->protect_exec = of_property_read_bool(child, "protect-exec"); if ((block->export || block->pool || block->protect_exec) && block->size) { -- GitLab From 536e2fce8980c84247ee52e737d24bd1ffdb0d7f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:13 -0600 Subject: [PATCH 0766/5631] misc: lis3lv02d: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Reviewed-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230310144713.1543683-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/lis3lv02d/lis3lv02d.c | 64 +++++++++++++++--------------- 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index 3a7808b796b1..3e11f4d0b454 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -965,19 +965,19 @@ int lis3lv02d_init_dt(struct lis3lv02d *lis3) if (!pdata) return -ENOMEM; - if (of_get_property(np, "st,click-single-x", NULL)) + if (of_property_read_bool(np, "st,click-single-x")) pdata->click_flags |= LIS3_CLICK_SINGLE_X; - if (of_get_property(np, "st,click-double-x", NULL)) + if (of_property_read_bool(np, "st,click-double-x")) pdata->click_flags |= LIS3_CLICK_DOUBLE_X; - if (of_get_property(np, "st,click-single-y", NULL)) + if (of_property_read_bool(np, "st,click-single-y")) pdata->click_flags |= LIS3_CLICK_SINGLE_Y; - if (of_get_property(np, "st,click-double-y", NULL)) + if (of_property_read_bool(np, "st,click-double-y")) pdata->click_flags |= LIS3_CLICK_DOUBLE_Y; - if (of_get_property(np, "st,click-single-z", NULL)) + if (of_property_read_bool(np, "st,click-single-z")) pdata->click_flags |= LIS3_CLICK_SINGLE_Z; - if (of_get_property(np, "st,click-double-z", NULL)) + if (of_property_read_bool(np, "st,click-double-z")) pdata->click_flags |= LIS3_CLICK_DOUBLE_Z; if (!of_property_read_u32(np, "st,click-threshold-x", &val)) @@ -994,31 +994,31 @@ int lis3lv02d_init_dt(struct lis3lv02d *lis3) if (!of_property_read_u32(np, "st,click-window", &val)) pdata->click_window = val; - if (of_get_property(np, "st,irq1-disable", NULL)) + if (of_property_read_bool(np, "st,irq1-disable")) pdata->irq_cfg |= LIS3_IRQ1_DISABLE; - if (of_get_property(np, "st,irq1-ff-wu-1", NULL)) + if (of_property_read_bool(np, "st,irq1-ff-wu-1")) pdata->irq_cfg |= LIS3_IRQ1_FF_WU_1; - if (of_get_property(np, "st,irq1-ff-wu-2", NULL)) + if (of_property_read_bool(np, "st,irq1-ff-wu-2")) pdata->irq_cfg |= LIS3_IRQ1_FF_WU_2; - if (of_get_property(np, "st,irq1-data-ready", NULL)) + if (of_property_read_bool(np, "st,irq1-data-ready")) pdata->irq_cfg |= LIS3_IRQ1_DATA_READY; - if (of_get_property(np, "st,irq1-click", NULL)) + if (of_property_read_bool(np, "st,irq1-click")) pdata->irq_cfg |= LIS3_IRQ1_CLICK; - if (of_get_property(np, "st,irq2-disable", NULL)) + if (of_property_read_bool(np, "st,irq2-disable")) pdata->irq_cfg |= LIS3_IRQ2_DISABLE; - if (of_get_property(np, "st,irq2-ff-wu-1", NULL)) + if (of_property_read_bool(np, "st,irq2-ff-wu-1")) pdata->irq_cfg |= LIS3_IRQ2_FF_WU_1; - if (of_get_property(np, "st,irq2-ff-wu-2", NULL)) + if (of_property_read_bool(np, "st,irq2-ff-wu-2")) pdata->irq_cfg |= LIS3_IRQ2_FF_WU_2; - if (of_get_property(np, "st,irq2-data-ready", NULL)) + if (of_property_read_bool(np, "st,irq2-data-ready")) pdata->irq_cfg |= LIS3_IRQ2_DATA_READY; - if (of_get_property(np, "st,irq2-click", NULL)) + if (of_property_read_bool(np, "st,irq2-click")) pdata->irq_cfg |= LIS3_IRQ2_CLICK; - if (of_get_property(np, "st,irq-open-drain", NULL)) + if (of_property_read_bool(np, "st,irq-open-drain")) pdata->irq_cfg |= LIS3_IRQ_OPEN_DRAIN; - if (of_get_property(np, "st,irq-active-low", NULL)) + if (of_property_read_bool(np, "st,irq-active-low")) pdata->irq_cfg |= LIS3_IRQ_ACTIVE_LOW; if (!of_property_read_u32(np, "st,wu-duration-1", &val)) @@ -1026,32 +1026,32 @@ int lis3lv02d_init_dt(struct lis3lv02d *lis3) if (!of_property_read_u32(np, "st,wu-duration-2", &val)) pdata->duration2 = val; - if (of_get_property(np, "st,wakeup-x-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup-x-lo")) pdata->wakeup_flags |= LIS3_WAKEUP_X_LO; - if (of_get_property(np, "st,wakeup-x-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup-x-hi")) pdata->wakeup_flags |= LIS3_WAKEUP_X_HI; - if (of_get_property(np, "st,wakeup-y-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup-y-lo")) pdata->wakeup_flags |= LIS3_WAKEUP_Y_LO; - if (of_get_property(np, "st,wakeup-y-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup-y-hi")) pdata->wakeup_flags |= LIS3_WAKEUP_Y_HI; - if (of_get_property(np, "st,wakeup-z-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup-z-lo")) pdata->wakeup_flags |= LIS3_WAKEUP_Z_LO; - if (of_get_property(np, "st,wakeup-z-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup-z-hi")) pdata->wakeup_flags |= LIS3_WAKEUP_Z_HI; if (of_get_property(np, "st,wakeup-threshold", &val)) pdata->wakeup_thresh = val; - if (of_get_property(np, "st,wakeup2-x-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup2-x-lo")) pdata->wakeup_flags2 |= LIS3_WAKEUP_X_LO; - if (of_get_property(np, "st,wakeup2-x-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup2-x-hi")) pdata->wakeup_flags2 |= LIS3_WAKEUP_X_HI; - if (of_get_property(np, "st,wakeup2-y-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup2-y-lo")) pdata->wakeup_flags2 |= LIS3_WAKEUP_Y_LO; - if (of_get_property(np, "st,wakeup2-y-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup2-y-hi")) pdata->wakeup_flags2 |= LIS3_WAKEUP_Y_HI; - if (of_get_property(np, "st,wakeup2-z-lo", NULL)) + if (of_property_read_bool(np, "st,wakeup2-z-lo")) pdata->wakeup_flags2 |= LIS3_WAKEUP_Z_LO; - if (of_get_property(np, "st,wakeup2-z-hi", NULL)) + if (of_property_read_bool(np, "st,wakeup2-z-hi")) pdata->wakeup_flags2 |= LIS3_WAKEUP_Z_HI; if (of_get_property(np, "st,wakeup2-threshold", &val)) pdata->wakeup_thresh2 = val; @@ -1073,9 +1073,9 @@ int lis3lv02d_init_dt(struct lis3lv02d *lis3) } } - if (of_get_property(np, "st,hipass1-disable", NULL)) + if (of_property_read_bool(np, "st,hipass1-disable")) pdata->hipass_ctrl |= LIS3_HIPASS1_DISABLE; - if (of_get_property(np, "st,hipass2-disable", NULL)) + if (of_property_read_bool(np, "st,hipass2-disable")) pdata->hipass_ctrl |= LIS3_HIPASS2_DISABLE; if (of_property_read_s32(np, "st,axis-x", &sval) == 0) -- GitLab From 6ca8f8bf706d874090b74f811194e94ebbc560df Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:13 -0600 Subject: [PATCH 0767/5631] misc: lis3lv02d: Fix reading 'st,default-rate' property The property 'st,default-rate' is tested for presence, but the value is ignored and the 'default_rate' value is updated with a stale 'val' value. Fix this by using of_property_read_u32(). Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144713.1543613-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/misc/lis3lv02d/lis3lv02d.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c index 3e11f4d0b454..299d316f1bda 100644 --- a/drivers/misc/lis3lv02d/lis3lv02d.c +++ b/drivers/misc/lis3lv02d/lis3lv02d.c @@ -1085,7 +1085,7 @@ int lis3lv02d_init_dt(struct lis3lv02d *lis3) if (of_property_read_s32(np, "st,axis-z", &sval) == 0) pdata->axis_z = sval; - if (of_get_property(np, "st,default-rate", NULL)) + if (of_property_read_u32(np, "st,default-rate", &val) == 0) pdata->default_rate = val; if (of_property_read_s32(np, "st,min-limit-x", &sval) == 0) -- GitLab From 34320745dfc9b71234139720bc8b602cdc8c086a Mon Sep 17 00:00:00 2001 From: Phil Auld Date: Fri, 3 Mar 2023 13:37:54 -0500 Subject: [PATCH 0768/5631] sched/debug: Put sched/domains files under the verbose flag The debug files under sched/domains can take a long time to regenerate, especially when updates are done one at a time. Move these files under the sched verbose debug flag. Allow changes to verbose to trigger generation of the files. This lets a user batch the updates but still have the information available. The detailed topology printk messages are also under verbose. Discussion that lead to this approach can be found in the link below. Simplified code to maintain use of debugfs bool routines suggested by Michael Ellerman . Signed-off-by: Phil Auld Acked-by: Greg Kroah-Hartman Reviewed-by: Valentin Schneider Reviewed-by: Srikar Dronamraju Tested-by: Vishal Chourasia Cc: Michael Ellerman Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Peter Zijlstra (Intel) Cc: Srikar Dronamraju Cc: Valentin Schneider Cc: Vishal Chourasia Cc: Vincent Guittot Link: https://lore.kernel.org/all/Y01UWQL2y2r69sBX@li-05afa54c-330e-11b2-a85c-e3f3aa0db1e9.ibm.com/ Link: https://lore.kernel.org/r/20230303183754.3076321-1-pauld@redhat.com Signed-off-by: Greg Kroah-Hartman --- kernel/sched/debug.c | 52 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 49 insertions(+), 3 deletions(-) diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 1637b65ba07a..0b2340a79b65 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -280,6 +280,45 @@ static const struct file_operations sched_dynamic_fops = { __read_mostly bool sched_debug_verbose; +#ifdef CONFIG_SMP +static struct dentry *sd_dentry; + + +static ssize_t sched_verbose_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + ssize_t result; + bool orig; + + cpus_read_lock(); + mutex_lock(&sched_domains_mutex); + + orig = sched_debug_verbose; + result = debugfs_write_file_bool(filp, ubuf, cnt, ppos); + + if (sched_debug_verbose && !orig) + update_sched_domain_debugfs(); + else if (!sched_debug_verbose && orig) { + debugfs_remove(sd_dentry); + sd_dentry = NULL; + } + + mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); + + return result; +} +#else +#define sched_verbose_write debugfs_write_file_bool +#endif + +static const struct file_operations sched_verbose_fops = { + .read = debugfs_read_file_bool, + .write = sched_verbose_write, + .open = simple_open, + .llseek = default_llseek, +}; + static const struct seq_operations sched_debug_sops; static int sched_debug_open(struct inode *inode, struct file *filp) @@ -303,7 +342,7 @@ static __init int sched_init_debug(void) debugfs_sched = debugfs_create_dir("sched", NULL); debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops); - debugfs_create_bool("verbose", 0644, debugfs_sched, &sched_debug_verbose); + debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops); #ifdef CONFIG_PREEMPT_DYNAMIC debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops); #endif @@ -345,7 +384,6 @@ late_initcall(sched_init_debug); #ifdef CONFIG_SMP static cpumask_var_t sd_sysctl_cpus; -static struct dentry *sd_dentry; static int sd_flags_show(struct seq_file *m, void *v) { @@ -402,15 +440,23 @@ void update_sched_domain_debugfs(void) if (!debugfs_sched) return; + if (!sched_debug_verbose) + return; + if (!cpumask_available(sd_sysctl_cpus)) { if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL)) return; cpumask_copy(sd_sysctl_cpus, cpu_possible_mask); } - if (!sd_dentry) + if (!sd_dentry) { sd_dentry = debugfs_create_dir("domains", debugfs_sched); + /* rebuild sd_sysctl_cpus if empty since it gets cleared below */ + if (cpumask_empty(sd_sysctl_cpus)) + cpumask_copy(sd_sysctl_cpus, cpu_online_mask); + } + for_each_cpu(cpu, sd_sysctl_cpus) { struct sched_domain *sd; struct dentry *d_cpu; -- GitLab From 2744a63c1aec32eeea16330868b795ac41bcb217 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:45 +0100 Subject: [PATCH 0769/5631] cpufreq: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Viresh Kumar Cc: Srinivas Pandruvada Cc: Len Brown Cc: linux-pm@vger.kernel.org Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230313182918.1312597-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/cpufreq.c | 7 ++++++- drivers/cpufreq/intel_pstate.c | 7 +++++-- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 6d8fd3b8dcb5..6ad3119b8e15 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2932,11 +2932,16 @@ EXPORT_SYMBOL_GPL(cpufreq_unregister_driver); static int __init cpufreq_core_init(void) { struct cpufreq_governor *gov = cpufreq_default_governor(); + struct device *dev_root; if (cpufreq_disabled()) return -ENODEV; - cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + cpufreq_global_kobject = kobject_create_and_add("cpufreq", &dev_root->kobj); + put_device(dev_root); + } BUG_ON(!cpufreq_global_kobject); if (!strlen(default_governor)) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 48a4613cef1e..102cf7f0ac63 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1473,10 +1473,13 @@ static struct kobject *intel_pstate_kobject; static void __init intel_pstate_sysfs_expose_params(void) { + struct device *dev_root = bus_get_dev_root(&cpu_subsys); int rc; - intel_pstate_kobject = kobject_create_and_add("intel_pstate", - &cpu_subsys.dev_root->kobj); + if (dev_root) { + intel_pstate_kobject = kobject_create_and_add("intel_pstate", &dev_root->kobj); + put_device(dev_root); + } if (WARN_ON(!intel_pstate_kobject)) return; -- GitLab From 6644a426eb0d19220298e25ff26cde6302c60482 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:46 +0100 Subject: [PATCH 0770/5631] platform/x86: ibm_rtl: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Mark Gross Cc: platform-driver-x86@vger.kernel.org Acked-by: Hans de Goede Link: https://lore.kernel.org/r/20230313182918.1312597-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/platform/x86/ibm_rtl.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c index 5fc665f7d9b3..2ab7d9ac542d 100644 --- a/drivers/platform/x86/ibm_rtl.c +++ b/drivers/platform/x86/ibm_rtl.c @@ -199,16 +199,26 @@ static int rtl_setup_sysfs(void) { ret = subsys_system_register(&rtl_subsys, NULL); if (!ret) { - for (i = 0; rtl_attributes[i]; i ++) - device_create_file(rtl_subsys.dev_root, rtl_attributes[i]); + struct device *dev_root = bus_get_dev_root(&rtl_subsys); + + if (dev_root) { + for (i = 0; rtl_attributes[i]; i ++) + device_create_file(dev_root, rtl_attributes[i]); + put_device(dev_root); + } } return ret; } static void rtl_teardown_sysfs(void) { + struct device *dev_root = bus_get_dev_root(&rtl_subsys); int i; - for (i = 0; rtl_attributes[i]; i ++) - device_remove_file(rtl_subsys.dev_root, rtl_attributes[i]); + + if (dev_root) { + for (i = 0; rtl_attributes[i]; i ++) + device_remove_file(dev_root, rtl_attributes[i]); + put_device(dev_root); + } bus_unregister(&rtl_subsys); } -- GitLab From c8e15075b2cb58d0ff08cc8772ce259d1be6b0cd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:47 +0100 Subject: [PATCH 0771/5631] platform/x86: intel-uncore-freq: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Mark Gross Cc: platform-driver-x86@vger.kernel.org Acked-by: Hans de Goede Acked-by: Srinivas Pandruvada Link: https://lore.kernel.org/r/20230313182918.1312597-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- .../intel/uncore-frequency/uncore-frequency-common.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c index cb24de9e97dc..1a300e14f350 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c @@ -224,9 +224,15 @@ int uncore_freq_common_init(int (*read_control_freq)(struct uncore_data *data, u uncore_write = write_control_freq; uncore_read_freq = read_freq; - if (!uncore_root_kobj) - uncore_root_kobj = kobject_create_and_add("intel_uncore_frequency", - &cpu_subsys.dev_root->kobj); + if (!uncore_root_kobj) { + struct device *dev_root = bus_get_dev_root(&cpu_subsys); + + if (dev_root) { + uncore_root_kobj = kobject_create_and_add("intel_uncore_frequency", + &dev_root->kobj); + put_device(dev_root); + } + } if (uncore_root_kobj) ++uncore_instance_count; mutex_unlock(&uncore_lock); -- GitLab From db281d59e26b9aaccfd2334450099a1bc472bac6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:49 +0100 Subject: [PATCH 0772/5631] cpu/hotplug: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Thomas Gleixner Cc: Valentin Schneider Cc: Phil Auld Cc: Steven Price Cc: Juri Lelli Cc: Greg Kroah-Hartman Cc: Vincent Donnefort Cc: Kuppuswamy Sathyanarayanan Cc: "Jason A. Donenfeld" Link: https://lore.kernel.org/r/20230313182918.1312597-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- kernel/cpu.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/kernel/cpu.c b/kernel/cpu.c index 6c0a92ca6bb5..c59b73d13a3a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2569,22 +2569,33 @@ static const struct attribute_group cpuhp_smt_attr_group = { static int __init cpu_smt_sysfs_init(void) { - return sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpuhp_smt_attr_group); + struct device *dev_root; + int ret = -ENODEV; + + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); + put_device(dev_root); + } + return ret; } static int __init cpuhp_sysfs_init(void) { + struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; - ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpuhp_cpu_root_attr_group); - if (ret) - return ret; + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); + put_device(dev_root); + if (ret) + return ret; + } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); -- GitLab From 686f669780276da534e93ba769e02bdcf1f89f8d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:50 +0100 Subject: [PATCH 0773/5631] workqueue: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Lai Jiangshan Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20230313182918.1312597-8-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- kernel/workqueue.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b8b541caed48..209917792fa4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5826,13 +5826,19 @@ static struct device_attribute wq_sysfs_cpumask_attr = static int __init wq_sysfs_init(void) { + struct device *dev_root; int err; err = subsys_virtual_register(&wq_subsys, NULL); if (err) return err; - return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr); + dev_root = bus_get_dev_root(&wq_subsys); + if (dev_root) { + err = device_create_file(dev_root, &wq_sysfs_cpumask_attr); + put_device(dev_root); + } + return err; } core_initcall(wq_sysfs_init); -- GitLab From 216f58beb26e683e6d437c43e6aaf8e7b8631447 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:51 +0100 Subject: [PATCH 0774/5631] x86/microcode: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Borislav Petkov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Link: https://lore.kernel.org/r/20230313182918.1312597-9-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/microcode/core.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 7a329e561354..3afcf3de0dd4 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -632,6 +632,7 @@ static const struct attribute_group cpu_root_microcode_group = { static int __init microcode_init(void) { + struct device *dev_root; struct cpuinfo_x86 *c = &boot_cpu_data; int error; @@ -652,10 +653,14 @@ static int __init microcode_init(void) if (IS_ERR(microcode_pdev)) return PTR_ERR(microcode_pdev); - error = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpu_root_microcode_group); - if (error) { - pr_err("Error creating microcode group!\n"); - goto out_pdev; + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + error = sysfs_create_group(&dev_root->kobj, &cpu_root_microcode_group); + put_device(dev_root); + if (error) { + pr_err("Error creating microcode group!\n"); + goto out_pdev; + } } /* Do per-CPU setup */ -- GitLab From 60260272dc59ca0da233de5ff452859f2e981bdb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:52 +0100 Subject: [PATCH 0775/5631] x86/umwait: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: "H. Peter Anvin" Link: https://lore.kernel.org/r/20230313182918.1312597-10-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/umwait.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index ec8064c0ae03..2293efd6ffa6 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -232,7 +232,11 @@ static int __init umwait_init(void) * Add umwait control interface. Ignore failure, so at least the * default values are set up in case the machine manages to boot. */ - dev = cpu_subsys.dev_root; - return sysfs_create_group(&dev->kobj, &umwait_attr_group); + dev = bus_get_dev_root(&cpu_subsys); + if (dev) { + ret = sysfs_create_group(&dev->kobj, &umwait_attr_group); + put_device(dev); + } + return ret; } device_initcall(umwait_init); -- GitLab From cb6b0cba1ea9d3f71bafef4eff4e7a9547085752 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:53 +0100 Subject: [PATCH 0776/5631] arm64: cpufeature: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Brown Cc: James Morse Cc: Kristina Martsenko Cc: Marc Zyngier Cc: Ard Biesheuvel Cc: Vladimir Murzin Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230313182918.1312597-11-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/cpufeature.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 2e3e55139777..f3bab4bd0917 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1490,10 +1490,18 @@ static const DEVICE_ATTR_RO(aarch32_el0); static int __init aarch32_el0_sysfs_init(void) { + struct device *dev_root; + int ret = 0; + if (!allow_mismatched_32bit_el0) return 0; - return device_create_file(cpu_subsys.dev_root, &dev_attr_aarch32_el0); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = device_create_file(dev_root, &dev_attr_aarch32_el0); + put_device(dev_root); + } + return ret; } device_initcall(aarch32_el0_sysfs_init); -- GitLab From 1b40189691304488cd59b5f1d2ed17de89b59f93 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:54 +0100 Subject: [PATCH 0777/5631] powerpc/sysfs: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: David Hildenbrand Cc: Andrew Morton Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230313182918.1312597-12-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/kernel/sysfs.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index ef9a61718940..0f39a6b84132 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -217,13 +217,18 @@ static DEVICE_ATTR(dscr_default, 0600, static void __init sysfs_create_dscr_default(void) { if (cpu_has_feature(CPU_FTR_DSCR)) { + struct device *dev_root; int cpu; dscr_default = spr_default_dscr; for_each_possible_cpu(cpu) paca_ptrs[cpu]->dscr_default = dscr_default; - device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + device_create_file(dev_root, &dev_attr_dscr_default); + put_device(dev_root); + } } } #endif /* CONFIG_PPC64 */ @@ -746,7 +751,12 @@ static DEVICE_ATTR(svm, 0444, show_svm, NULL); static void __init create_svm_file(void) { - device_create_file(cpu_subsys.dev_root, &dev_attr_svm); + struct device *dev_root = bus_get_dev_root(&cpu_subsys); + + if (dev_root) { + device_create_file(dev_root, &dev_attr_svm); + put_device(dev_root); + } } #else static void __init create_svm_file(void) -- GitLab From 3bf88c4222d9656bdaea793a423379ab7c485324 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:55 +0100 Subject: [PATCH 0778/5631] powerpc/powernv: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Wolfram Sang Cc: Joel Stanley Cc: Liang He Cc: Greg Kroah-Hartman Cc: Julia Lawall Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230313182918.1312597-13-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/powernv/idle.c | 9 +++++++-- arch/powerpc/platforms/powernv/subcore.c | 10 ++++++++-- 2 files changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 841cb7f31f4f..6dfe8d611164 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -1464,14 +1464,19 @@ static int __init pnv_init_idle_states(void) power7_fastsleep_workaround_entry = false; power7_fastsleep_workaround_exit = false; } else { + struct device *dev_root; /* * OPAL_PM_SLEEP_ENABLED_ER1 is set. It indicates that * workaround is needed to use fastsleep. Provide sysfs * control to choose how this workaround has to be * applied. */ - device_create_file(cpu_subsys.dev_root, - &dev_attr_fastsleep_workaround_applyonce); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + device_create_file(dev_root, + &dev_attr_fastsleep_workaround_applyonce); + put_device(dev_root); + } } update_subcore_sibling_mask(); diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 7e98b00ea2e8..428532a69762 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -415,7 +415,9 @@ static DEVICE_ATTR(subcores_per_core, 0644, static int subcore_init(void) { + struct device *dev_root; unsigned pvr_ver; + int rc = 0; pvr_ver = PVR_VER(mfspr(SPRN_PVR)); @@ -435,7 +437,11 @@ static int subcore_init(void) set_subcores_per_core(1); - return device_create_file(cpu_subsys.dev_root, - &dev_attr_subcores_per_core); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + rc = device_create_file(dev_root, &dev_attr_subcores_per_core); + put_device(dev_root); + } + return rc; } machine_device_initcall(powernv, subcore_init); -- GitLab From 2a9efef85205ccd4013e947901e00c2697aa42ed Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:56 +0100 Subject: [PATCH 0779/5631] powerpc/pseries: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Greg Kroah-Hartman Cc: linuxppc-dev@lists.ozlabs.org Acked-by: Michael Ellerman (powerpc) Link: https://lore.kernel.org/r/20230313182918.1312597-14-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- .../platforms/pseries/pseries_energy.c | 28 +++++++++++-------- arch/powerpc/platforms/pseries/suspend.c | 10 +++++-- 2 files changed, 25 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index 09e98d301db0..2c661b798235 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -300,20 +300,22 @@ static struct device_attribute attr_percpu_deactivate_hint = static int __init pseries_energy_init(void) { int cpu, err; - struct device *cpu_dev; + struct device *cpu_dev, *dev_root; if (!firmware_has_feature(FW_FEATURE_BEST_ENERGY)) return 0; /* H_BEST_ENERGY hcall not supported */ /* Create the sysfs files */ - err = device_create_file(cpu_subsys.dev_root, - &attr_cpu_activate_hint_list); - if (!err) - err = device_create_file(cpu_subsys.dev_root, - &attr_cpu_deactivate_hint_list); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + err = device_create_file(dev_root, &attr_cpu_activate_hint_list); + if (!err) + err = device_create_file(dev_root, &attr_cpu_deactivate_hint_list); + put_device(dev_root); + if (err) + return err; + } - if (err) - return err; for_each_possible_cpu(cpu) { cpu_dev = get_cpu_device(cpu); err = device_create_file(cpu_dev, @@ -337,14 +339,18 @@ static int __init pseries_energy_init(void) static void __exit pseries_energy_cleanup(void) { int cpu; - struct device *cpu_dev; + struct device *cpu_dev, *dev_root; if (!sysfs_entries) return; /* Remove the sysfs files */ - device_remove_file(cpu_subsys.dev_root, &attr_cpu_activate_hint_list); - device_remove_file(cpu_subsys.dev_root, &attr_cpu_deactivate_hint_list); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + device_remove_file(dev_root, &attr_cpu_activate_hint_list); + device_remove_file(dev_root, &attr_cpu_deactivate_hint_list); + put_device(dev_root); + } for_each_possible_cpu(cpu) { cpu_dev = get_cpu_device(cpu); diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 1b902cbf85c5..5c43435472cc 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -143,6 +143,7 @@ static const struct platform_suspend_ops pseries_suspend_ops = { **/ static int pseries_suspend_sysfs_register(struct device *dev) { + struct device *dev_root; int rc; if ((rc = subsys_system_register(&suspend_subsys, NULL))) @@ -151,8 +152,13 @@ static int pseries_suspend_sysfs_register(struct device *dev) dev->id = 0; dev->bus = &suspend_subsys; - if ((rc = device_create_file(suspend_subsys.dev_root, &dev_attr_hibernate))) - goto subsys_unregister; + dev_root = bus_get_dev_root(&suspend_subsys); + if (dev_root) { + rc = device_create_file(dev_root, &dev_attr_hibernate); + put_device(dev_root); + if (rc) + goto subsys_unregister; + } return 0; -- GitLab From c93bd175414ac43d7ea6cb2a17f49eb91af03f00 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:57 +0100 Subject: [PATCH 0780/5631] powerpc/fsl: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20230313182918.1312597-15-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c index c2baa283e624..147b5d8bb904 100644 --- a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c +++ b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c @@ -116,6 +116,7 @@ static struct device_attribute mpic_attributes = __ATTR(timer_wakeup, 0644, static int __init fsl_wakeup_sys_init(void) { + struct device *dev_root; int ret; fsl_wakeup = kzalloc(sizeof(struct fsl_mpic_timer_wakeup), GFP_KERNEL); @@ -124,16 +125,26 @@ static int __init fsl_wakeup_sys_init(void) INIT_WORK(&fsl_wakeup->free_work, fsl_free_resource); - ret = device_create_file(mpic_subsys.dev_root, &mpic_attributes); - if (ret) - kfree(fsl_wakeup); + dev_root = bus_get_dev_root(&mpic_subsys); + if (dev_root) { + ret = device_create_file(dev_root, &mpic_attributes); + put_device(dev_root); + if (ret) + kfree(fsl_wakeup); + } return ret; } static void __exit fsl_wakeup_sys_exit(void) { - device_remove_file(mpic_subsys.dev_root, &mpic_attributes); + struct device *dev_root; + + dev_root = bus_get_dev_root(&mpic_subsys); + if (dev_root) { + device_remove_file(dev_root, &mpic_attributes); + put_device(dev_root); + } mutex_lock(&sysfs_lock); -- GitLab From f6d1975cd2668d239bb97ef4833ad1ddc5ffed6d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:58 +0100 Subject: [PATCH 0781/5631] sh: dma-sysfs: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Acked-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230313182918.1312597-16-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/sh/drivers/dma/dma-sysfs.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/sh/drivers/dma/dma-sysfs.c b/arch/sh/drivers/dma/dma-sysfs.c index 8ef318150f84..431bc18f0a41 100644 --- a/arch/sh/drivers/dma/dma-sysfs.c +++ b/arch/sh/drivers/dma/dma-sysfs.c @@ -45,13 +45,19 @@ static DEVICE_ATTR(devices, S_IRUGO, dma_show_devices, NULL); static int __init dma_subsys_init(void) { + struct device *dev_root; int ret; ret = subsys_system_register(&dma_subsys, NULL); if (unlikely(ret)) return ret; - return device_create_file(dma_subsys.dev_root, &dev_attr_devices); + dev_root = bus_get_dev_root(&dma_subsys); + if (dev_root) { + ret = device_create_file(dev_root, &dev_attr_devices); + put_device(dev_root); + } + return ret; } postcore_initcall(dma_subsys_init); -- GitLab From 93c42c0b0303b47fbb71cb2a633bcd45eca8b644 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:59 +0100 Subject: [PATCH 0782/5631] sh: intc: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Acked-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230313182918.1312597-17-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/sh/intc/userimask.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/sh/intc/userimask.c b/drivers/sh/intc/userimask.c index f9f043a3d90a..abe9091827cd 100644 --- a/drivers/sh/intc/userimask.c +++ b/drivers/sh/intc/userimask.c @@ -61,10 +61,18 @@ static DEVICE_ATTR(userimask, S_IRUSR | S_IWUSR, static int __init userimask_sysdev_init(void) { + struct device *dev_root; + int ret = 0; + if (unlikely(!uimask)) return -ENXIO; - return device_create_file(intc_subsys.dev_root, &dev_attr_userimask); + dev_root = bus_get_dev_root(&intc_subsys); + if (dev_root) { + ret = device_create_file(dev_root, &dev_attr_userimask); + put_device(dev_root); + } + return ret; } late_initcall(userimask_sysdev_init); -- GitLab From 9493ed19fbc302d8e3ba487b7c99a7beeddbff96 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:00 +0100 Subject: [PATCH 0783/5631] s390/topology: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: linux-s390@vger.kernel.org Acked-by: Heiko Carstens Link: https://lore.kernel.org/r/20230313182918.1312597-18-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/topology.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index c6eecd4a5302..72af753d1bba 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -649,12 +649,21 @@ static struct ctl_table topology_dir_table[] = { static int __init topology_init(void) { + struct device *dev_root; + int rc = 0; + timer_setup(&topology_timer, topology_timer_fn, TIMER_DEFERRABLE); if (MACHINE_HAS_TOPOLOGY) set_topology_timer(); else topology_update_polarization_simple(); register_sysctl_table(topology_dir_table); - return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); + + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + rc = device_create_file(dev_root, &dev_attr_dispatching); + put_device(dev_root); + } + return rc; } device_initcall(topology_init); -- GitLab From 31e7c4cc7da9d1b5ac01de9829aba53081b1b794 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:01 +0100 Subject: [PATCH 0784/5631] s390/smp: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Vasily Gorbik Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Sven Schnelle Cc: Ilya Leoshkevich Cc: linux-s390@vger.kernel.org Acked-by: Heiko Carstens Link: https://lore.kernel.org/r/20230313182918.1312597-19-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/s390/kernel/smp.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index d4888453bbf8..4df797ab8ca2 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1227,11 +1227,17 @@ static DEVICE_ATTR_WO(rescan); static int __init s390_smp_init(void) { + struct device *dev_root; int cpu, rc = 0; - rc = device_create_file(cpu_subsys.dev_root, &dev_attr_rescan); - if (rc) - return rc; + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + rc = device_create_file(dev_root, &dev_attr_rescan); + put_device(dev_root); + if (rc) + return rc; + } + for_each_present_cpu(cpu) { rc = smp_add_present_cpu(cpu); if (rc) -- GitLab From 3666062b87ec8be4b85dc475dfb54bb17e10a7f6 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:02 +0100 Subject: [PATCH 0785/5631] cpufreq: amd-pstate: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. In doing so, remove the unneded kobject structure that was only being created to cause a subdirectory for the attributes. The name of the attribute group is the correct way to do this, saving code and complexity as well as allowing the attributes to properly show up to userspace tools (the raw kobject would not allow that.) Cc: "Rafael J. Wysocki" Cc: Viresh Kumar Cc: linux-pm@vger.kernel.org Acked-by: Huang Rui Link: https://lore.kernel.org/r/20230313182918.1312597-20-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/cpufreq/amd-pstate.c | 24 ++++++++++-------------- 1 file changed, 10 insertions(+), 14 deletions(-) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 73c7643b2697..b92454c50118 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -63,7 +63,6 @@ static struct cpufreq_driver *current_pstate_driver; static struct cpufreq_driver amd_pstate_driver; static struct cpufreq_driver amd_pstate_epp_driver; static int cppc_state = AMD_PSTATE_DISABLE; -struct kobject *amd_pstate_kobj; /* * AMD Energy Preference Performance (EPP) @@ -932,6 +931,7 @@ static struct attribute *pstate_global_attributes[] = { }; static const struct attribute_group amd_pstate_global_attr_group = { + .name = "amd_pstate", .attrs = pstate_global_attributes, }; @@ -1253,6 +1253,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = { static int __init amd_pstate_init(void) { + struct device *dev_root; int ret; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) @@ -1299,24 +1300,19 @@ static int __init amd_pstate_init(void) if (ret) pr_err("failed to register with return %d\n", ret); - amd_pstate_kobj = kobject_create_and_add("amd_pstate", &cpu_subsys.dev_root->kobj); - if (!amd_pstate_kobj) { - ret = -EINVAL; - pr_err("global sysfs registration failed.\n"); - goto kobject_free; - } - - ret = sysfs_create_group(amd_pstate_kobj, &amd_pstate_global_attr_group); - if (ret) { - pr_err("sysfs attribute export failed with error %d.\n", ret); - goto global_attr_free; + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group); + put_device(dev_root); + if (ret) { + pr_err("sysfs attribute export failed with error %d.\n", ret); + goto global_attr_free; + } } return ret; global_attr_free: - kobject_put(amd_pstate_kobj); -kobject_free: cpufreq_unregister_driver(current_pstate_driver); return ret; } -- GitLab From fea087fc291b102521427c26da3d0a30c329606f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:03 +0100 Subject: [PATCH 0786/5631] irqchip/mbigen: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Thomas Gleixner Cc: Marc Zyngier Link: https://lore.kernel.org/r/20230313182918.1312597-21-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/irqchip/irq-mbigen.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index f3faf5c99770..30ca1bf7fc8b 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -245,11 +245,14 @@ static int mbigen_of_create_domain(struct platform_device *pdev, if (!of_property_read_bool(np, "interrupt-controller")) continue; - parent = platform_bus_type.dev_root; - child = of_platform_device_create(np, NULL, parent); - if (!child) { - of_node_put(np); - return -ENOMEM; + parent = bus_get_dev_root(&platform_bus_type); + if (parent) { + child = of_platform_device_create(np, NULL, parent); + put_device(parent); + if (!child) { + of_node_put(np); + return -ENOMEM; + } } if (of_property_read_u32(child->dev.of_node, "num-pins", -- GitLab From 4a69516f97bc35134f41de959000ea6cb93a1d50 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 14 Mar 2023 13:52:57 +0100 Subject: [PATCH 0787/5631] dt-bindings: dmaengine: qcom: gpi: Add QCM2290 GPI DMA Add a compatible for the single GPI DMA controller on QCM2290. It uses the same 0x10000 offset as SM6350. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Reviewed-by: Bhupesh Sharma Link: https://lore.kernel.org/r/20230314-topic-2290_compats-v1-2-47e26c3c0365@linaro.org Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/dma/qcom,gpi.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index fc5de7b6f19e..f61145c91b6d 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -24,6 +24,7 @@ properties: - qcom,sm6350-gpi-dma - items: - enum: + - qcom,qcm2290-gpi-dma - qcom,qdu1000-gpi-dma - qcom,sc7280-gpi-dma - qcom,sm6115-gpi-dma -- GitLab From d1e71a3a7ab9db0168b6885171e0576383216ac8 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 15 Mar 2023 06:45:01 +0000 Subject: [PATCH 0788/5631] dmaengine: sh: rz-dmac: Add reset support Add reset support for DMAC module found on RZ/G2L alike SoCs. For booting the board, reset release of the DMAC module is required otherwise we don't get GIC interrupts. Currently the reset release was done by the bootloader now move this to the driver instead. Signed-off-by: Biju Das Reviewed-by: Lad Prabhakar Link: https://lore.kernel.org/r/20230315064501.21491-1-biju.das.jz@bp.renesas.com Signed-off-by: Vinod Koul --- drivers/dma/sh/rz-dmac.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 476847a4916b..6b62e01ba658 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -92,6 +93,7 @@ struct rz_dmac_chan { struct rz_dmac { struct dma_device engine; struct device *dev; + struct reset_control *rstc; void __iomem *base; void __iomem *ext_base; @@ -889,6 +891,11 @@ static int rz_dmac_probe(struct platform_device *pdev) /* Initialize the channels. */ INIT_LIST_HEAD(&dmac->engine.channels); + dmac->rstc = devm_reset_control_array_get_exclusive(&pdev->dev); + if (IS_ERR(dmac->rstc)) + return dev_err_probe(&pdev->dev, PTR_ERR(dmac->rstc), + "failed to get resets\n"); + pm_runtime_enable(&pdev->dev); ret = pm_runtime_resume_and_get(&pdev->dev); if (ret < 0) { @@ -896,6 +903,10 @@ static int rz_dmac_probe(struct platform_device *pdev) goto err_pm_disable; } + ret = reset_control_deassert(dmac->rstc); + if (ret) + goto err_pm_runtime_put; + for (i = 0; i < dmac->n_channels; i++) { ret = rz_dmac_chan_probe(dmac, &dmac->channels[i], i); if (ret < 0) @@ -940,6 +951,7 @@ static int rz_dmac_probe(struct platform_device *pdev) dma_register_err: of_dma_controller_free(pdev->dev.of_node); err: + reset_control_assert(dmac->rstc); channel_num = i ? i - 1 : 0; for (i = 0; i < channel_num; i++) { struct rz_dmac_chan *channel = &dmac->channels[i]; @@ -950,6 +962,7 @@ static int rz_dmac_probe(struct platform_device *pdev) channel->lmdesc.base_dma); } +err_pm_runtime_put: pm_runtime_put(&pdev->dev); err_pm_disable: pm_runtime_disable(&pdev->dev); @@ -972,6 +985,7 @@ static int rz_dmac_remove(struct platform_device *pdev) } of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&dmac->engine); + reset_control_assert(dmac->rstc); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); -- GitLab From 5aaf9079d740ebe57f10dfefb1850011d6bb7b2a Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 15 Mar 2023 06:47:25 +0000 Subject: [PATCH 0789/5631] dt-bindings: dma: rz-dmac: Document clock-names and reset-names Document clock-names and reset-names properties as we have multiple clocks and resets. Signed-off-by: Biju Das Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230315064726.22739-1-biju.das.jz@bp.renesas.com Signed-off-by: Vinod Koul --- .../devicetree/bindings/dma/renesas,rz-dmac.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml index f638d3934e71..c284abc6784a 100644 --- a/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml +++ b/Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml @@ -54,6 +54,11 @@ properties: - description: DMA main clock - description: DMA register access clock + clock-names: + items: + - const: main + - const: register + '#dma-cells': const: 1 description: @@ -77,16 +82,23 @@ properties: - description: Reset for DMA ARESETN reset terminal - description: Reset for DMA RST_ASYNC reset terminal + reset-names: + items: + - const: arst + - const: rst_async + required: - compatible - reg - interrupts - interrupt-names - clocks + - clock-names - '#dma-cells' - dma-channels - power-domains - resets + - reset-names additionalProperties: false @@ -124,9 +136,11 @@ examples: "ch12", "ch13", "ch14", "ch15"; clocks = <&cpg CPG_MOD R9A07G044_DMAC_ACLK>, <&cpg CPG_MOD R9A07G044_DMAC_PCLK>; + clock-names = "main", "register"; power-domains = <&cpg>; resets = <&cpg R9A07G044_DMAC_ARESETN>, <&cpg R9A07G044_DMAC_RST_ASYNC>; + reset-names = "arst", "rst_async"; #dma-cells = <1>; dma-channels = <16>; }; -- GitLab From 9f7d4718211a82b2a87ae74d841d6e3938cd5c28 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 13 Mar 2023 22:52:31 +0100 Subject: [PATCH 0790/5631] dmaengine: imx-dma: Remove a redundant memset() call The desc->desc structure is already zeroed when 'desc' is kzalloc()'ed. There is no need to clear it twice. Remove the redundant memset(). Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/95a81d623bffde2e5d14e22fad7e8c9a9a7203f6.1678743528.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- drivers/dma/imx-dma.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index 80086977973f..f040751690af 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -750,7 +750,6 @@ static int imxdma_alloc_chan_resources(struct dma_chan *chan) desc = kzalloc(sizeof(*desc), GFP_KERNEL); if (!desc) break; - memset(&desc->desc, 0, sizeof(struct dma_async_tx_descriptor)); dma_async_tx_descriptor_init(&desc->desc, chan); desc->desc.tx_submit = imxdma_tx_submit; /* txd.flags will be overwritten in prep funcs */ -- GitLab From 3765af04f4fda327463e5b631a4a2d62ae7bb93f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:03 -0600 Subject: [PATCH 0791/5631] dmaengine: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144704.1541976-1-robh@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/of-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c index ac61ecda2926..775a7f408b9a 100644 --- a/drivers/dma/of-dma.c +++ b/drivers/dma/of-dma.c @@ -264,7 +264,7 @@ struct dma_chan *of_dma_request_slave_channel(struct device_node *np, } /* Silently fail if there is not even the "dmas" property */ - if (!of_find_property(np, "dmas", NULL)) + if (!of_property_present(np, "dmas")) return ERR_PTR(-ENODEV); count = of_property_count_strings(np, "dma-names"); -- GitLab From 8f6707d0773be31972768abd6e0bf7b8515b5b1a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 15:46:15 -0600 Subject: [PATCH 0792/5631] dmaengine: ioat: use PCI core macros for PCIe Capability The PCIe Capability is defined by the PCIe spec, so use the PCI_EXP_DEVCTL macros defined by the PCI core instead of defining copies in IOAT. This makes it easier to find all uses of the PCIe Device Control register. No functional change intended. Signed-off-by: Bjorn Helgaas Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230307214615.887354-1-helgaas@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/ioat/init.c | 6 +++--- drivers/dma/ioat/registers.h | 7 ------- 2 files changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index 5d707ff63554..fa7c0f9aa61d 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -1191,13 +1191,13 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca) ioat_dma->dca = ioat_dca_init(pdev, ioat_dma->reg_base); /* disable relaxed ordering */ - err = pcie_capability_read_word(pdev, IOAT_DEVCTRL_OFFSET, &val16); + err = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &val16); if (err) return pcibios_err_to_errno(err); /* clear relaxed ordering enable */ - val16 &= ~IOAT_DEVCTRL_ROE; - err = pcie_capability_write_word(pdev, IOAT_DEVCTRL_OFFSET, val16); + val16 &= ~PCI_EXP_DEVCTL_RELAX_EN; + err = pcie_capability_write_word(pdev, PCI_EXP_DEVCTL, val16); if (err) return pcibios_err_to_errno(err); diff --git a/drivers/dma/ioat/registers.h b/drivers/dma/ioat/registers.h index f55a5f92f185..54cf0ad39887 100644 --- a/drivers/dma/ioat/registers.h +++ b/drivers/dma/ioat/registers.h @@ -14,13 +14,6 @@ #define IOAT_PCI_CHANERR_INT_OFFSET 0x180 #define IOAT_PCI_CHANERRMASK_INT_OFFSET 0x184 -/* PCIe config registers */ - -/* EXPCAPID + N */ -#define IOAT_DEVCTRL_OFFSET 0x8 -/* relaxed ordering enable */ -#define IOAT_DEVCTRL_ROE 0x10 - /* MMIO Device Registers */ #define IOAT_CHANCNT_OFFSET 0x00 /* 8-bit */ -- GitLab From e32622f84ae289dc7a04e9f01cd62cb914fdc5c6 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 13:26:54 -0600 Subject: [PATCH 0793/5631] dmaengine: ioat: Drop redundant pci_enable_pcie_error_reporting() pci_enable_pcie_error_reporting() enables the device to send ERR_* Messages. Since f26e58bf6f54 ("PCI/AER: Enable error reporting when AER is native"), the PCI core does this for all devices during enumeration, so the driver doesn't need to do it itself. Remove the redundant pci_enable_pcie_error_reporting() call from the driver. Also remove the corresponding pci_disable_pcie_error_reporting() from the driver .remove() path. Note that this only controls ERR_* Messages from the device. An ERR_* Message may cause the Root Port to generate an interrupt, depending on the AER Root Error Command register managed by the AER service driver. Signed-off-by: Bjorn Helgaas Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230307192655.874008-2-helgaas@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/ioat/init.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c index fa7c0f9aa61d..c4602bfc9c74 100644 --- a/drivers/dma/ioat/init.c +++ b/drivers/dma/ioat/init.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include "dma.h" #include "registers.h" @@ -1380,15 +1379,11 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (is_skx_ioat(pdev)) device->version = IOAT_VER_3_2; err = ioat3_dma_probe(device, ioat_dca_enabled); - - if (device->version >= IOAT_VER_3_3) - pci_enable_pcie_error_reporting(pdev); } else return -ENODEV; if (err) { dev_err(dev, "Intel(R) I/OAT DMA Engine init failed\n"); - pci_disable_pcie_error_reporting(pdev); return -ENODEV; } @@ -1411,7 +1406,6 @@ static void ioat_remove(struct pci_dev *pdev) device->dca = NULL; } - pci_disable_pcie_error_reporting(pdev); ioat_dma_remove(device); } -- GitLab From 3c5cc03979b72620c31159560984f5b2c0dcba22 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 13:26:55 -0600 Subject: [PATCH 0794/5631] dmaengine: idxd: Remove unnecessary aer.h include is unused, so remove it. Signed-off-by: Bjorn Helgaas Cc: Fenghua Yu Cc: Dave Jiang Acked-by: Fenghua Yu Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230307192655.874008-3-helgaas@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/idxd/init.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 640d3048368e..a85efcda7095 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include -- GitLab From fe8f1a2e9b7c4519a145ab8110dec59fea3c532c Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Tue, 7 Mar 2023 13:10:19 +0100 Subject: [PATCH 0795/5631] dt-bindings: dma: apple,admac: Add t8112-admac compatible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The block found on Apple's M2 SoC is compatible with the existing driver so add its per-SoC compatible. Acked-by: Vinod Koul Acked-by: Martin Povišer Acked-by: Krzysztof Kozlowski Signed-off-by: Janne Grunau Link: https://lore.kernel.org/r/20230202-asahi-t8112-dt-v3-13-d1a5f6383d95@jannau.net Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/dma/apple,admac.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/dma/apple,admac.yaml b/Documentation/devicetree/bindings/dma/apple,admac.yaml index 05163d124ec3..ab193bc8bdbb 100644 --- a/Documentation/devicetree/bindings/dma/apple,admac.yaml +++ b/Documentation/devicetree/bindings/dma/apple,admac.yaml @@ -26,6 +26,7 @@ properties: - enum: - apple,t6000-admac - apple,t8103-admac + - apple,t8112-admac - const: apple,admac reg: -- GitLab From eddc63094855f411455db85b77eb8439201dc779 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 16 Mar 2023 16:11:18 -0700 Subject: [PATCH 0796/5631] clk: mediatek: Ensure fhctl code is available for COMMON_CLK_MT6795 Without this select we get linker errors when linking clk-mt6795-apmixedsys arm-linux-gnueabi-ld: drivers/clk/mediatek/clk-mt6795-apmixedsys.o: in function `clk_mt6795_apmixed_remove': clk-mt6795-apmixedsys.c:(.text+0x34): undefined reference to `mtk_clk_unregister_pllfhs' arm-linux-gnueabi-ld: drivers/clk/mediatek/clk-mt6795-apmixedsys.o: in function `clk_mt6795_apmixed_probe': clk-mt6795-apmixedsys.c:(.text+0x98): undefined reference to `fhctl_parse_dt' arm-linux-gnueabi-ld: clk-mt6795-apmixedsys.c:(.text+0xb8): undefined reference to `mtk_clk_register_pllfhs' arm-linux-gnueabi-ld: clk-mt6795-apmixedsys.c:(.text+0x1c4): undefined reference to `mtk_clk_unregister_pllfhs' Fixes: f222a1baec5f ("clk: mediatek: mt6795: Add support for frequency hopping through FHCTL") Cc: AngeloGioacchino Del Regno Cc: Chen-Yu Tsai Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230316231118.2579242-1-sboyd@kernel.org --- drivers/clk/mediatek/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 7a12aefb1d0b..c707c6fe45a3 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -270,6 +270,7 @@ config COMMON_CLK_MT6795 tristate "Clock driver for MediaTek MT6795" depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK + select COMMON_CLK_MEDIATEK_FHCTL default ARCH_MEDIATEK help This driver supports MediaTek MT6795 basic clocks and clocks -- GitLab From 2c106e156a431b9190d319f68019ebf64322bfb6 Mon Sep 17 00:00:00 2001 From: Ammar Faizi Date: Sun, 26 Feb 2023 23:53:21 +0700 Subject: [PATCH 0797/5631] MAINTAINERS: Add workqueue_internal.h to the WORKQUEUE entry This file doesn't have a maintainer. It should belong to the WORKQUEUE entry part. Add it to the WORKQUEUE entry. Signed-off-by: Ammar Faizi Reviewed-by: Lai Jiangshan Signed-off-by: Tejun Heo --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index bb08f242c242..88a2eb2249c6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22596,6 +22596,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git F: Documentation/core-api/workqueue.rst F: include/linux/workqueue.h F: kernel/workqueue.c +F: kernel/workqueue_internal.h WWAN DRIVERS M: Loic Poulain -- GitLab From a8ec5880bd82b834717770cba4596381ffd50545 Mon Sep 17 00:00:00 2001 From: Ammar Faizi Date: Sun, 26 Feb 2023 23:53:20 +0700 Subject: [PATCH 0798/5631] workqueue: Simplify a pr_warn() call in wq_select_unbound_cpu() Use pr_warn_once() to achieve the same thing. It's simpler. Signed-off-by: Ammar Faizi Reviewed-by: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b8b541caed48..3f1fabea000f 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1392,15 +1392,13 @@ static bool is_chained_work(struct workqueue_struct *wq) */ static int wq_select_unbound_cpu(int cpu) { - static bool printed_dbg_warning; int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; - } else if (!printed_dbg_warning) { - pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n"); - printed_dbg_warning = true; + } else { + pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } if (cpumask_empty(wq_unbound_cpumask)) -- GitLab From 8ef70a5ef3ed41ce4d700794d45fd9e084460a00 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:48 +0100 Subject: [PATCH 0799/5631] rtc: 88pm80x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-2-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-88pm80x.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c index 6a3f44cf6ebe..f40cc06b0979 100644 --- a/drivers/rtc/rtc-88pm80x.c +++ b/drivers/rtc/rtc-88pm80x.c @@ -317,11 +317,10 @@ static int pm80x_rtc_probe(struct platform_device *pdev) return ret; } -static int pm80x_rtc_remove(struct platform_device *pdev) +static void pm80x_rtc_remove(struct platform_device *pdev) { struct pm80x_rtc_info *info = platform_get_drvdata(pdev); pm80x_free_irq(info->chip, info->irq, info); - return 0; } static struct platform_driver pm80x_rtc_driver = { @@ -330,7 +329,7 @@ static struct platform_driver pm80x_rtc_driver = { .pm = &pm80x_rtc_pm_ops, }, .probe = pm80x_rtc_probe, - .remove = pm80x_rtc_remove, + .remove_new = pm80x_rtc_remove, }; module_platform_driver(pm80x_rtc_driver); -- GitLab From 8fbff75e2b7582fc03dbcd13e67831fb75345dcb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:49 +0100 Subject: [PATCH 0800/5631] rtc: 88pm860x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-3-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-88pm860x.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c index 2c809a1a445e..0f124ed5b3e5 100644 --- a/drivers/rtc/rtc-88pm860x.c +++ b/drivers/rtc/rtc-88pm860x.c @@ -331,7 +331,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev) return 0; } -static int pm860x_rtc_remove(struct platform_device *pdev) +static void pm860x_rtc_remove(struct platform_device *pdev) { struct pm860x_rtc_info *info = platform_get_drvdata(pdev); @@ -340,8 +340,6 @@ static int pm860x_rtc_remove(struct platform_device *pdev) /* disable measurement */ pm860x_set_bits(info->i2c, PM8607_MEAS_EN2, MEAS2_VRTC, 0); #endif /* VRTC_CALIBRATION */ - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -373,7 +371,7 @@ static struct platform_driver pm860x_rtc_driver = { .pm = &pm860x_rtc_pm_ops, }, .probe = pm860x_rtc_probe, - .remove = pm860x_rtc_remove, + .remove_new = pm860x_rtc_remove, }; module_platform_driver(pm860x_rtc_driver); -- GitLab From 8a700af1babfc0e5d34bd95264d65ea6adb0b288 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:50 +0100 Subject: [PATCH 0801/5631] rtc: ab8500: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20230304133028.2135435-4-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ab8500.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c index ea33e149d545..75bb2ac9005c 100644 --- a/drivers/rtc/rtc-ab8500.c +++ b/drivers/rtc/rtc-ab8500.c @@ -392,12 +392,10 @@ static int ab8500_rtc_probe(struct platform_device *pdev) return devm_rtc_register_device(rtc); } -static int ab8500_rtc_remove(struct platform_device *pdev) +static void ab8500_rtc_remove(struct platform_device *pdev) { dev_pm_clear_wake_irq(&pdev->dev); device_init_wakeup(&pdev->dev, false); - - return 0; } static struct platform_driver ab8500_rtc_driver = { @@ -405,7 +403,7 @@ static struct platform_driver ab8500_rtc_driver = { .name = "ab8500-rtc", }, .probe = ab8500_rtc_probe, - .remove = ab8500_rtc_remove, + .remove_new = ab8500_rtc_remove, .id_table = ab85xx_rtc_ids, }; -- GitLab From 28015e799ad9ff04d68107b7392a4884accedb0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:51 +0100 Subject: [PATCH 0802/5631] rtc: ac100: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-5-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ac100.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-ac100.c b/drivers/rtc/rtc-ac100.c index 66783cb5e711..eaf2c9ab9661 100644 --- a/drivers/rtc/rtc-ac100.c +++ b/drivers/rtc/rtc-ac100.c @@ -613,13 +613,11 @@ static int ac100_rtc_probe(struct platform_device *pdev) return devm_rtc_register_device(chip->rtc); } -static int ac100_rtc_remove(struct platform_device *pdev) +static void ac100_rtc_remove(struct platform_device *pdev) { struct ac100_rtc_dev *chip = platform_get_drvdata(pdev); ac100_rtc_unregister_clks(chip); - - return 0; } static const struct of_device_id ac100_rtc_match[] = { @@ -630,7 +628,7 @@ MODULE_DEVICE_TABLE(of, ac100_rtc_match); static struct platform_driver ac100_rtc_driver = { .probe = ac100_rtc_probe, - .remove = ac100_rtc_remove, + .remove_new = ac100_rtc_remove, .driver = { .name = "ac100-rtc", .of_match_table = of_match_ptr(ac100_rtc_match), -- GitLab From ad01bf83bfc33c53079415f02e160bf72221d7e6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:52 +0100 Subject: [PATCH 0803/5631] rtc: asm9260: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-6-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-asm9260.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-asm9260.c b/drivers/rtc/rtc-asm9260.c index de795e489f71..a83b47e0d8f5 100644 --- a/drivers/rtc/rtc-asm9260.c +++ b/drivers/rtc/rtc-asm9260.c @@ -308,14 +308,13 @@ static int asm9260_rtc_probe(struct platform_device *pdev) return ret; } -static int asm9260_rtc_remove(struct platform_device *pdev) +static void asm9260_rtc_remove(struct platform_device *pdev) { struct asm9260_rtc_priv *priv = platform_get_drvdata(pdev); /* Disable alarm matching */ iowrite32(BM_AMR_OFF, priv->iobase + HW_AMR); clk_disable_unprepare(priv->clk); - return 0; } static const struct of_device_id asm9260_dt_ids[] = { @@ -326,7 +325,7 @@ MODULE_DEVICE_TABLE(of, asm9260_dt_ids); static struct platform_driver asm9260_rtc_driver = { .probe = asm9260_rtc_probe, - .remove = asm9260_rtc_remove, + .remove_new = asm9260_rtc_remove, .driver = { .name = "asm9260-rtc", .of_match_table = asm9260_dt_ids, -- GitLab From 06e5e4a5a996aefb5d8e0c8db05b014e3bd91a28 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:53 +0100 Subject: [PATCH 0804/5631] rtc: at91sam9: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230304133028.2135435-7-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-at91sam9.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c index b7b5ea1a4e67..610f27dfc462 100644 --- a/drivers/rtc/rtc-at91sam9.c +++ b/drivers/rtc/rtc-at91sam9.c @@ -442,7 +442,7 @@ static int at91_rtc_probe(struct platform_device *pdev) /* * Disable and remove the RTC driver */ -static int at91_rtc_remove(struct platform_device *pdev) +static void at91_rtc_remove(struct platform_device *pdev) { struct sam9_rtc *rtc = platform_get_drvdata(pdev); u32 mr = rtt_readl(rtc, MR); @@ -451,8 +451,6 @@ static int at91_rtc_remove(struct platform_device *pdev) rtt_writel(rtc, MR, mr & ~(AT91_RTT_ALMIEN | AT91_RTT_RTTINCIEN)); clk_disable_unprepare(rtc->sclk); - - return 0; } static void at91_rtc_shutdown(struct platform_device *pdev) @@ -531,7 +529,7 @@ MODULE_DEVICE_TABLE(of, at91_rtc_dt_ids); static struct platform_driver at91_rtc_driver = { .probe = at91_rtc_probe, - .remove = at91_rtc_remove, + .remove_new = at91_rtc_remove, .shutdown = at91_rtc_shutdown, .driver = { .name = "rtc-at91sam9", -- GitLab From d64906b320ce6fef446ea72c6043bbec19f0da60 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:54 +0100 Subject: [PATCH 0805/5631] rtc: brcmstb-waketimer: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-8-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-brcmstb-waketimer.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-brcmstb-waketimer.c b/drivers/rtc/rtc-brcmstb-waketimer.c index 1efa81cecc27..3cdc015692ca 100644 --- a/drivers/rtc/rtc-brcmstb-waketimer.c +++ b/drivers/rtc/rtc-brcmstb-waketimer.c @@ -336,14 +336,12 @@ static int brcmstb_waketmr_probe(struct platform_device *pdev) return ret; } -static int brcmstb_waketmr_remove(struct platform_device *pdev) +static void brcmstb_waketmr_remove(struct platform_device *pdev) { struct brcmstb_waketmr *timer = dev_get_drvdata(&pdev->dev); unregister_reboot_notifier(&timer->reboot_notifier); clk_disable_unprepare(timer->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -382,7 +380,7 @@ static const __maybe_unused struct of_device_id brcmstb_waketmr_of_match[] = { static struct platform_driver brcmstb_waketmr_driver = { .probe = brcmstb_waketmr_probe, - .remove = brcmstb_waketmr_remove, + .remove_new = brcmstb_waketmr_remove, .driver = { .name = "brcmstb-waketimer", .pm = &brcmstb_waketmr_pm_ops, -- GitLab From 0b9efd82a63b31c7c2ce17a3d8ad3aeb28b3a928 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:55 +0100 Subject: [PATCH 0806/5631] rtc: cadence: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-9-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cadence.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c index 1edf7f16d73a..4ca60b519836 100644 --- a/drivers/rtc/rtc-cadence.c +++ b/drivers/rtc/rtc-cadence.c @@ -354,7 +354,7 @@ static int cdns_rtc_probe(struct platform_device *pdev) return ret; } -static int cdns_rtc_remove(struct platform_device *pdev) +static void cdns_rtc_remove(struct platform_device *pdev) { struct cdns_rtc *crtc = platform_get_drvdata(pdev); @@ -363,8 +363,6 @@ static int cdns_rtc_remove(struct platform_device *pdev) clk_disable_unprepare(crtc->pclk); clk_disable_unprepare(crtc->ref_clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -404,7 +402,7 @@ static struct platform_driver cdns_rtc_driver = { .pm = &cdns_rtc_pm_ops, }, .probe = cdns_rtc_probe, - .remove = cdns_rtc_remove, + .remove_new = cdns_rtc_remove, }; module_platform_driver(cdns_rtc_driver); -- GitLab From 63c18a079bbb5f564b30e0fa7ec292eb123b1bf6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:56 +0100 Subject: [PATCH 0807/5631] rtc: cmos: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-10-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cmos.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 00e2ca7374ec..c9416fe8542d 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -1489,10 +1489,9 @@ static int __init cmos_platform_probe(struct platform_device *pdev) return cmos_do_probe(&pdev->dev, resource, irq); } -static int cmos_platform_remove(struct platform_device *pdev) +static void cmos_platform_remove(struct platform_device *pdev) { cmos_do_remove(&pdev->dev); - return 0; } static void cmos_platform_shutdown(struct platform_device *pdev) @@ -1514,7 +1513,7 @@ static void cmos_platform_shutdown(struct platform_device *pdev) MODULE_ALIAS("platform:rtc_cmos"); static struct platform_driver cmos_platform_driver = { - .remove = cmos_platform_remove, + .remove_new = cmos_platform_remove, .shutdown = cmos_platform_shutdown, .driver = { .name = driver_name, -- GitLab From 0d8742e61098b422b1ba1458a7ce80c4f1e299bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:57 +0100 Subject: [PATCH 0808/5631] rtc: cros-ec: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Tzung-Bi Shih Link: https://lore.kernel.org/r/20230304133028.2135435-11-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cros-ec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index a3ec066d8066..998ab8606f0b 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -371,7 +371,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev) return 0; } -static int cros_ec_rtc_remove(struct platform_device *pdev) +static void cros_ec_rtc_remove(struct platform_device *pdev) { struct cros_ec_rtc *cros_ec_rtc = platform_get_drvdata(pdev); struct device *dev = &pdev->dev; @@ -382,13 +382,11 @@ static int cros_ec_rtc_remove(struct platform_device *pdev) &cros_ec_rtc->notifier); if (ret) dev_err(dev, "failed to unregister notifier\n"); - - return 0; } static struct platform_driver cros_ec_rtc_driver = { .probe = cros_ec_rtc_probe, - .remove = cros_ec_rtc_remove, + .remove_new = cros_ec_rtc_remove, .driver = { .name = DRV_NAME, .pm = &cros_ec_rtc_pm_ops, -- GitLab From de11783c9d2a4dec9e0e2c01b9a9897d72019d5f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:58 +0100 Subject: [PATCH 0809/5631] rtc: ds1685: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-By: Joshua Kinard Link: https://lore.kernel.org/r/20230304133028.2135435-12-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1685.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c index 5db9c737c022..0f707be0eb87 100644 --- a/drivers/rtc/rtc-ds1685.c +++ b/drivers/rtc/rtc-ds1685.c @@ -1322,7 +1322,7 @@ ds1685_rtc_probe(struct platform_device *pdev) * ds1685_rtc_remove - removes rtc driver. * @pdev: pointer to platform_device structure. */ -static int +static void ds1685_rtc_remove(struct platform_device *pdev) { struct ds1685_priv *rtc = platform_get_drvdata(pdev); @@ -1344,8 +1344,6 @@ ds1685_rtc_remove(struct platform_device *pdev) rtc->write(rtc, RTC_EXT_CTRL_4A, (rtc->read(rtc, RTC_EXT_CTRL_4A) & ~(RTC_CTRL_4A_RWK_MASK))); - - return 0; } /* @@ -1356,7 +1354,7 @@ static struct platform_driver ds1685_rtc_driver = { .name = "rtc-ds1685", }, .probe = ds1685_rtc_probe, - .remove = ds1685_rtc_remove, + .remove_new = ds1685_rtc_remove, }; module_platform_driver(ds1685_rtc_driver); /* ----------------------------------------------------------------------- */ -- GitLab From 43eeb707afb00579a7bb611d14fc9a056bba849e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:29:59 +0100 Subject: [PATCH 0810/5631] rtc: ftrtc010: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20230304133028.2135435-13-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ftrtc010.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-ftrtc010.c b/drivers/rtc/rtc-ftrtc010.c index 25c6e7d9570f..8bfe7378f653 100644 --- a/drivers/rtc/rtc-ftrtc010.c +++ b/drivers/rtc/rtc-ftrtc010.c @@ -191,7 +191,7 @@ static int ftrtc010_rtc_probe(struct platform_device *pdev) return ret; } -static int ftrtc010_rtc_remove(struct platform_device *pdev) +static void ftrtc010_rtc_remove(struct platform_device *pdev) { struct ftrtc010_rtc *rtc = platform_get_drvdata(pdev); @@ -199,8 +199,6 @@ static int ftrtc010_rtc_remove(struct platform_device *pdev) clk_disable_unprepare(rtc->extclk); if (!IS_ERR(rtc->pclk)) clk_disable_unprepare(rtc->pclk); - - return 0; } static const struct of_device_id ftrtc010_rtc_dt_match[] = { @@ -216,7 +214,7 @@ static struct platform_driver ftrtc010_rtc_driver = { .of_match_table = ftrtc010_rtc_dt_match, }, .probe = ftrtc010_rtc_probe, - .remove = ftrtc010_rtc_remove, + .remove_new = ftrtc010_rtc_remove, }; module_platform_driver_probe(ftrtc010_rtc_driver, ftrtc010_rtc_probe); -- GitLab From 30d5365c8dda63e31fb1fbbec446d72d0f1e5ce6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:00 +0100 Subject: [PATCH 0811/5631] rtc: hid-sensor-time: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-14-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-hid-sensor-time.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-hid-sensor-time.c b/drivers/rtc/rtc-hid-sensor-time.c index 16fdefafec5d..b81cea505ee9 100644 --- a/drivers/rtc/rtc-hid-sensor-time.c +++ b/drivers/rtc/rtc-hid-sensor-time.c @@ -296,14 +296,12 @@ static int hid_time_probe(struct platform_device *pdev) return ret; } -static int hid_time_remove(struct platform_device *pdev) +static void hid_time_remove(struct platform_device *pdev) { struct hid_sensor_hub_device *hsdev = dev_get_platdata(&pdev->dev); sensor_hub_device_close(hsdev); sensor_hub_remove_callback(hsdev, HID_USAGE_SENSOR_TIME); - - return 0; } static const struct platform_device_id hid_time_ids[] = { @@ -321,7 +319,7 @@ static struct platform_driver hid_time_platform_driver = { .name = KBUILD_MODNAME, }, .probe = hid_time_probe, - .remove = hid_time_remove, + .remove_new = hid_time_remove, }; module_platform_driver(hid_time_platform_driver); -- GitLab From 52fcb90d8cdf117ade871b01861b8a8defbf3b78 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:01 +0100 Subject: [PATCH 0812/5631] rtc: lpc24xx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-15-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-lpc24xx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-lpc24xx.c b/drivers/rtc/rtc-lpc24xx.c index eec881a81067..a4612e543f35 100644 --- a/drivers/rtc/rtc-lpc24xx.c +++ b/drivers/rtc/rtc-lpc24xx.c @@ -264,7 +264,7 @@ static int lpc24xx_rtc_probe(struct platform_device *pdev) return ret; } -static int lpc24xx_rtc_remove(struct platform_device *pdev) +static void lpc24xx_rtc_remove(struct platform_device *pdev) { struct lpc24xx_rtc *rtc = platform_get_drvdata(pdev); @@ -276,8 +276,6 @@ static int lpc24xx_rtc_remove(struct platform_device *pdev) clk_disable_unprepare(rtc->clk_rtc); clk_disable_unprepare(rtc->clk_reg); - - return 0; } static const struct of_device_id lpc24xx_rtc_match[] = { @@ -288,7 +286,7 @@ MODULE_DEVICE_TABLE(of, lpc24xx_rtc_match); static struct platform_driver lpc24xx_rtc_driver = { .probe = lpc24xx_rtc_probe, - .remove = lpc24xx_rtc_remove, + .remove_new = lpc24xx_rtc_remove, .driver = { .name = "lpc24xx-rtc", .of_match_table = lpc24xx_rtc_match, -- GitLab From bf05de01160d493d53cc289be1b1092c26b378b4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:02 +0100 Subject: [PATCH 0813/5631] rtc: max77686: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230304133028.2135435-16-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-max77686.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c index b0250d91fb00..35a6021d9ba4 100644 --- a/drivers/rtc/rtc-max77686.c +++ b/drivers/rtc/rtc-max77686.c @@ -806,14 +806,12 @@ static int max77686_rtc_probe(struct platform_device *pdev) return ret; } -static int max77686_rtc_remove(struct platform_device *pdev) +static void max77686_rtc_remove(struct platform_device *pdev) { struct max77686_rtc_info *info = platform_get_drvdata(pdev); free_irq(info->virq, info); regmap_del_irq_chip(info->rtc_irq, info->rtc_irq_data); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -877,7 +875,7 @@ static struct platform_driver max77686_rtc_driver = { .pm = &max77686_rtc_pm_ops, }, .probe = max77686_rtc_probe, - .remove = max77686_rtc_remove, + .remove_new = max77686_rtc_remove, .id_table = rtc_id, }; -- GitLab From 99c3a1367db02b6b57be54bf61da051a93e0615f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:03 +0100 Subject: [PATCH 0814/5631] rtc: mc13xxx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-17-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mc13xxx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-mc13xxx.c b/drivers/rtc/rtc-mc13xxx.c index d4234e78497e..763a42f422eb 100644 --- a/drivers/rtc/rtc-mc13xxx.c +++ b/drivers/rtc/rtc-mc13xxx.c @@ -324,7 +324,7 @@ static int __init mc13xxx_rtc_probe(struct platform_device *pdev) return ret; } -static int mc13xxx_rtc_remove(struct platform_device *pdev) +static void mc13xxx_rtc_remove(struct platform_device *pdev) { struct mc13xxx_rtc *priv = platform_get_drvdata(pdev); @@ -334,8 +334,6 @@ static int mc13xxx_rtc_remove(struct platform_device *pdev) mc13xxx_irq_free(priv->mc13xxx, MC13XXX_IRQ_RTCRST, priv); mc13xxx_unlock(priv->mc13xxx); - - return 0; } static const struct platform_device_id mc13xxx_rtc_idtable[] = { @@ -352,7 +350,7 @@ MODULE_DEVICE_TABLE(platform, mc13xxx_rtc_idtable); static struct platform_driver mc13xxx_rtc_driver = { .id_table = mc13xxx_rtc_idtable, - .remove = mc13xxx_rtc_remove, + .remove_new = mc13xxx_rtc_remove, .driver = { .name = DRIVER_NAME, }, -- GitLab From 22edbc10a514a8cf56d9c8da5cc1a2d43e6832a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:04 +0100 Subject: [PATCH 0815/5631] rtc: mpc5121: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-18-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mpc5121.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c index 6d7656a75cae..07df43e4c4d0 100644 --- a/drivers/rtc/rtc-mpc5121.c +++ b/drivers/rtc/rtc-mpc5121.c @@ -372,7 +372,7 @@ static int mpc5121_rtc_probe(struct platform_device *op) return err; } -static int mpc5121_rtc_remove(struct platform_device *op) +static void mpc5121_rtc_remove(struct platform_device *op) { struct mpc5121_rtc_data *rtc = platform_get_drvdata(op); struct mpc5121_rtc_regs __iomem *regs = rtc->regs; @@ -383,8 +383,6 @@ static int mpc5121_rtc_remove(struct platform_device *op) irq_dispose_mapping(rtc->irq); irq_dispose_mapping(rtc->irq_periodic); - - return 0; } #ifdef CONFIG_OF @@ -402,7 +400,7 @@ static struct platform_driver mpc5121_rtc_driver = { .of_match_table = of_match_ptr(mpc5121_rtc_match), }, .probe = mpc5121_rtc_probe, - .remove = mpc5121_rtc_remove, + .remove_new = mpc5121_rtc_remove, }; module_platform_driver(mpc5121_rtc_driver); -- GitLab From fa147083acf61de306e2881d91401d817de11093 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:05 +0100 Subject: [PATCH 0816/5631] rtc: mpfs: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230304133028.2135435-19-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mpfs.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-mpfs.c b/drivers/rtc/rtc-mpfs.c index 2a479d44f198..5b96a6d39210 100644 --- a/drivers/rtc/rtc-mpfs.c +++ b/drivers/rtc/rtc-mpfs.c @@ -274,11 +274,9 @@ static int mpfs_rtc_probe(struct platform_device *pdev) return devm_rtc_register_device(rtcdev->rtc); } -static int mpfs_rtc_remove(struct platform_device *pdev) +static void mpfs_rtc_remove(struct platform_device *pdev) { dev_pm_clear_wake_irq(&pdev->dev); - - return 0; } static const struct of_device_id mpfs_rtc_of_match[] = { @@ -290,7 +288,7 @@ MODULE_DEVICE_TABLE(of, mpfs_rtc_of_match); static struct platform_driver mpfs_rtc_driver = { .probe = mpfs_rtc_probe, - .remove = mpfs_rtc_remove, + .remove_new = mpfs_rtc_remove, .driver = { .name = "mpfs_rtc", .of_match_table = mpfs_rtc_of_match, -- GitLab From ae0ac71651c726c2f1d5af752d38bf40526b7026 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:06 +0100 Subject: [PATCH 0817/5631] rtc: mt7622: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-20-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mt7622.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-mt7622.c b/drivers/rtc/rtc-mt7622.c index f1e356394814..81857a457c32 100644 --- a/drivers/rtc/rtc-mt7622.c +++ b/drivers/rtc/rtc-mt7622.c @@ -357,13 +357,11 @@ static int mtk_rtc_probe(struct platform_device *pdev) return ret; } -static int mtk_rtc_remove(struct platform_device *pdev) +static void mtk_rtc_remove(struct platform_device *pdev) { struct mtk_rtc *hw = platform_get_drvdata(pdev); clk_disable_unprepare(hw->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -396,7 +394,7 @@ static SIMPLE_DEV_PM_OPS(mtk_rtc_pm_ops, mtk_rtc_suspend, mtk_rtc_resume); static struct platform_driver mtk_rtc_driver = { .probe = mtk_rtc_probe, - .remove = mtk_rtc_remove, + .remove_new = mtk_rtc_remove, .driver = { .name = MTK_RTC_DEV, .of_match_table = mtk_rtc_match, -- GitLab From 153f56f9ce99495ca4cb6d7f2047c29940aef9f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:07 +0100 Subject: [PATCH 0818/5631] rtc: mxc_v2: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-21-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mxc_v2.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c index f6d2ad91ff7a..6934bce4b29f 100644 --- a/drivers/rtc/rtc-mxc_v2.c +++ b/drivers/rtc/rtc-mxc_v2.c @@ -362,12 +362,11 @@ static int mxc_rtc_probe(struct platform_device *pdev) return ret; } -static int mxc_rtc_remove(struct platform_device *pdev) +static void mxc_rtc_remove(struct platform_device *pdev) { struct mxc_rtc_data *pdata = platform_get_drvdata(pdev); clk_disable_unprepare(pdata->clk); - return 0; } static const struct of_device_id mxc_ids[] = { @@ -382,7 +381,7 @@ static struct platform_driver mxc_rtc_driver = { .of_match_table = mxc_ids, }, .probe = mxc_rtc_probe, - .remove = mxc_rtc_remove, + .remove_new = mxc_rtc_remove, }; module_platform_driver(mxc_rtc_driver); -- GitLab From 578afdb9084ed0446060d627e7f3ecd1c4100c3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:08 +0100 Subject: [PATCH 0819/5631] rtc: omap: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-22-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-omap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index 4d4f3b1a7309..fad30b3dde46 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -910,7 +910,7 @@ static int omap_rtc_probe(struct platform_device *pdev) return ret; } -static int omap_rtc_remove(struct platform_device *pdev) +static void omap_rtc_remove(struct platform_device *pdev) { struct omap_rtc *rtc = platform_get_drvdata(pdev); u8 reg; @@ -941,8 +941,6 @@ static int omap_rtc_remove(struct platform_device *pdev) /* Disable the clock/module */ pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - - return 0; } static int __maybe_unused omap_rtc_suspend(struct device *dev) @@ -1017,7 +1015,7 @@ static void omap_rtc_shutdown(struct platform_device *pdev) static struct platform_driver omap_rtc_driver = { .probe = omap_rtc_probe, - .remove = omap_rtc_remove, + .remove_new = omap_rtc_remove, .shutdown = omap_rtc_shutdown, .driver = { .name = "omap_rtc", -- GitLab From a7f9864e4362e07e113517d647c5bc355cdee970 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:09 +0100 Subject: [PATCH 0820/5631] rtc: palmas: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-23-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-palmas.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c index 67571f7f0bbc..6971e47c6021 100644 --- a/drivers/rtc/rtc-palmas.c +++ b/drivers/rtc/rtc-palmas.c @@ -308,10 +308,9 @@ static int palmas_rtc_probe(struct platform_device *pdev) return 0; } -static int palmas_rtc_remove(struct platform_device *pdev) +static void palmas_rtc_remove(struct platform_device *pdev) { palmas_rtc_alarm_irq_enable(&pdev->dev, 0); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -347,7 +346,7 @@ MODULE_DEVICE_TABLE(of, of_palmas_rtc_match); static struct platform_driver palmas_rtc_driver = { .probe = palmas_rtc_probe, - .remove = palmas_rtc_remove, + .remove_new = palmas_rtc_remove, .driver = { .name = "palmas-rtc", .pm = &palmas_rtc_pm_ops, -- GitLab From d25f0ba97692b4a8ac63bbd2c562741525c5f5ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:10 +0100 Subject: [PATCH 0821/5631] rtc: pcf50633: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-24-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pcf50633.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-pcf50633.c b/drivers/rtc/rtc-pcf50633.c index 48951a16d65d..23edd11aa40c 100644 --- a/drivers/rtc/rtc-pcf50633.c +++ b/drivers/rtc/rtc-pcf50633.c @@ -260,14 +260,12 @@ static int pcf50633_rtc_probe(struct platform_device *pdev) return 0; } -static int pcf50633_rtc_remove(struct platform_device *pdev) +static void pcf50633_rtc_remove(struct platform_device *pdev) { struct pcf50633_rtc *rtc; rtc = platform_get_drvdata(pdev); pcf50633_free_irq(rtc->pcf, PCF50633_IRQ_ALARM); - - return 0; } static struct platform_driver pcf50633_rtc_driver = { @@ -275,7 +273,7 @@ static struct platform_driver pcf50633_rtc_driver = { .name = "pcf50633-rtc", }, .probe = pcf50633_rtc_probe, - .remove = pcf50633_rtc_remove, + .remove_new = pcf50633_rtc_remove, }; module_platform_driver(pcf50633_rtc_driver); -- GitLab From c3d12a10922dcf32a97d3c71f6a574529b061caf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:11 +0100 Subject: [PATCH 0822/5631] rtc: pic32: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-25-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pic32.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c index fa351ac20158..4f85e0c3d757 100644 --- a/drivers/rtc/rtc-pic32.c +++ b/drivers/rtc/rtc-pic32.c @@ -284,15 +284,13 @@ static void pic32_rtc_enable(struct pic32_rtc_dev *pdata, int en) clk_disable(pdata->clk); } -static int pic32_rtc_remove(struct platform_device *pdev) +static void pic32_rtc_remove(struct platform_device *pdev) { struct pic32_rtc_dev *pdata = platform_get_drvdata(pdev); pic32_rtc_setaie(&pdev->dev, 0); clk_unprepare(pdata->clk); pdata->clk = NULL; - - return 0; } static int pic32_rtc_probe(struct platform_device *pdev) @@ -373,7 +371,7 @@ MODULE_DEVICE_TABLE(of, pic32_rtc_dt_ids); static struct platform_driver pic32_rtc_driver = { .probe = pic32_rtc_probe, - .remove = pic32_rtc_remove, + .remove_new = pic32_rtc_remove, .driver = { .name = "pic32-rtc", .of_match_table = of_match_ptr(pic32_rtc_dt_ids), -- GitLab From 3fc5029a8f7d0d3c039c3649e82cc2e4eeeb46a6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:12 +0100 Subject: [PATCH 0823/5631] rtc: pm8xxx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-26-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pm8xxx.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index 372494e82f40..f6b779c12ca7 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -530,15 +530,14 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev) return 0; } -static int pm8xxx_remove(struct platform_device *pdev) +static void pm8xxx_remove(struct platform_device *pdev) { dev_pm_clear_wake_irq(&pdev->dev); - return 0; } static struct platform_driver pm8xxx_rtc_driver = { .probe = pm8xxx_rtc_probe, - .remove = pm8xxx_remove, + .remove_new = pm8xxx_remove, .driver = { .name = "rtc-pm8xxx", .of_match_table = pm8xxx_id_table, -- GitLab From ade527dd2192ddabbd4926338c31ca281098c34c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:13 +0100 Subject: [PATCH 0824/5631] rtc: rc5t583: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-27-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rc5t583.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-rc5t583.c b/drivers/rtc/rtc-rc5t583.c index 18684a7026c4..6f4bf919827a 100644 --- a/drivers/rtc/rtc-rc5t583.c +++ b/drivers/rtc/rtc-rc5t583.c @@ -262,12 +262,11 @@ static int rc5t583_rtc_probe(struct platform_device *pdev) * Disable rc5t583 RTC interrupts. * Sets status flag to free. */ -static int rc5t583_rtc_remove(struct platform_device *pdev) +static void rc5t583_rtc_remove(struct platform_device *pdev) { struct rc5t583_rtc *rc5t583_rtc = platform_get_drvdata(pdev); rc5t583_rtc_alarm_irq_enable(&rc5t583_rtc->rtc->dev, 0); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -299,7 +298,7 @@ static SIMPLE_DEV_PM_OPS(rc5t583_rtc_pm_ops, rc5t583_rtc_suspend, static struct platform_driver rc5t583_rtc_driver = { .probe = rc5t583_rtc_probe, - .remove = rc5t583_rtc_remove, + .remove_new = rc5t583_rtc_remove, .driver = { .name = "rtc-rc5t583", .pm = &rc5t583_rtc_pm_ops, -- GitLab From 0824a15b6863a19c7c8e1c16abf6090fd8ac615f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:14 +0100 Subject: [PATCH 0825/5631] rtc: rtd119x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-28-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rtd119x.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-rtd119x.c b/drivers/rtc/rtc-rtd119x.c index 8f9abd65846c..29662dfd56fe 100644 --- a/drivers/rtc/rtc-rtd119x.c +++ b/drivers/rtc/rtc-rtd119x.c @@ -216,7 +216,7 @@ static int rtd119x_rtc_probe(struct platform_device *pdev) return 0; } -static int rtd119x_rtc_remove(struct platform_device *pdev) +static void rtd119x_rtc_remove(struct platform_device *pdev) { struct rtd119x_rtc *data = platform_get_drvdata(pdev); @@ -224,13 +224,11 @@ static int rtd119x_rtc_remove(struct platform_device *pdev) clk_disable_unprepare(data->clk); clk_put(data->clk); - - return 0; } static struct platform_driver rtd119x_rtc_driver = { .probe = rtd119x_rtc_probe, - .remove = rtd119x_rtc_remove, + .remove_new = rtd119x_rtc_remove, .driver = { .name = "rtd1295-rtc", .of_match_table = rtd119x_rtc_dt_ids, -- GitLab From e55fbc80e9d2bf3ec0ec77551baa683f30e85b74 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:15 +0100 Subject: [PATCH 0826/5631] rtc: rzn1: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20230304133028.2135435-29-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-rzn1.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-rzn1.c b/drivers/rtc/rtc-rzn1.c index 0d36bc50197c..dca736caba85 100644 --- a/drivers/rtc/rtc-rzn1.c +++ b/drivers/rtc/rtc-rzn1.c @@ -391,11 +391,9 @@ static int rzn1_rtc_probe(struct platform_device *pdev) return ret; } -static int rzn1_rtc_remove(struct platform_device *pdev) +static void rzn1_rtc_remove(struct platform_device *pdev) { pm_runtime_put(&pdev->dev); - - return 0; } static const struct of_device_id rzn1_rtc_of_match[] = { @@ -406,7 +404,7 @@ MODULE_DEVICE_TABLE(of, rzn1_rtc_of_match); static struct platform_driver rzn1_rtc_driver = { .probe = rzn1_rtc_probe, - .remove = rzn1_rtc_remove, + .remove_new = rzn1_rtc_remove, .driver = { .name = "rzn1-rtc", .of_match_table = rzn1_rtc_of_match, -- GitLab From 9e6a2ad120fa3f785f013e70ae7d872abafb8318 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:16 +0100 Subject: [PATCH 0827/5631] rtc: s3c: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-30-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s3c.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 8fc5efde3e0b..70e1a18e5efd 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -385,7 +385,7 @@ static void s3c6410_rtc_disable(struct s3c_rtc *info) writew(con, info->base + S3C2410_RTCCON); } -static int s3c_rtc_remove(struct platform_device *pdev) +static void s3c_rtc_remove(struct platform_device *pdev) { struct s3c_rtc *info = platform_get_drvdata(pdev); @@ -394,8 +394,6 @@ static int s3c_rtc_remove(struct platform_device *pdev) if (info->data->needs_src_clk) clk_unprepare(info->rtc_src_clk); clk_unprepare(info->rtc_clk); - - return 0; } static int s3c_rtc_probe(struct platform_device *pdev) @@ -600,7 +598,7 @@ MODULE_DEVICE_TABLE(of, s3c_rtc_dt_match); static struct platform_driver s3c_rtc_driver = { .probe = s3c_rtc_probe, - .remove = s3c_rtc_remove, + .remove_new = s3c_rtc_remove, .driver = { .name = "s3c-rtc", .pm = &s3c_rtc_pm_ops, -- GitLab From cf407e9f1a9dc290e2088c11bd0e5542334e7ab4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:17 +0100 Subject: [PATCH 0828/5631] rtc: sa1100: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-31-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-sa1100.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 1250887e4382..0b2cfa8ca05b 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -297,7 +297,7 @@ static int sa1100_rtc_probe(struct platform_device *pdev) return sa1100_rtc_init(pdev, info); } -static int sa1100_rtc_remove(struct platform_device *pdev) +static void sa1100_rtc_remove(struct platform_device *pdev) { struct sa1100_rtc *info = platform_get_drvdata(pdev); @@ -307,8 +307,6 @@ static int sa1100_rtc_remove(struct platform_device *pdev) spin_unlock_irq(&info->lock); clk_disable_unprepare(info->clk); } - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -343,7 +341,7 @@ MODULE_DEVICE_TABLE(of, sa1100_rtc_dt_ids); static struct platform_driver sa1100_rtc_driver = { .probe = sa1100_rtc_probe, - .remove = sa1100_rtc_remove, + .remove_new = sa1100_rtc_remove, .driver = { .name = "sa1100-rtc", .pm = &sa1100_rtc_pm_ops, -- GitLab From 25ffc856b3cb1bd08a8645839aa38505469a6edd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:18 +0100 Subject: [PATCH 0829/5631] rtc: spear: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-32-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-spear.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c index 736fe535cd45..1df5c7e94198 100644 --- a/drivers/rtc/rtc-spear.c +++ b/drivers/rtc/rtc-spear.c @@ -405,15 +405,13 @@ static int spear_rtc_probe(struct platform_device *pdev) return status; } -static int spear_rtc_remove(struct platform_device *pdev) +static void spear_rtc_remove(struct platform_device *pdev) { struct spear_rtc_config *config = platform_get_drvdata(pdev); spear_rtc_disable_interrupt(config); clk_disable_unprepare(config->clk); device_init_wakeup(&pdev->dev, 0); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -477,7 +475,7 @@ MODULE_DEVICE_TABLE(of, spear_rtc_id_table); static struct platform_driver spear_rtc_driver = { .probe = spear_rtc_probe, - .remove = spear_rtc_remove, + .remove_new = spear_rtc_remove, .shutdown = spear_rtc_shutdown, .driver = { .name = "rtc-spear", -- GitLab From 54c2cb2797cd76465dae08cd9b81676ffad36b27 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:19 +0100 Subject: [PATCH 0830/5631] rtc: stm32: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-33-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-stm32.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c index ac9e228b56d0..229cb2847cc4 100644 --- a/drivers/rtc/rtc-stm32.c +++ b/drivers/rtc/rtc-stm32.c @@ -846,7 +846,7 @@ static int stm32_rtc_probe(struct platform_device *pdev) return ret; } -static int stm32_rtc_remove(struct platform_device *pdev) +static void stm32_rtc_remove(struct platform_device *pdev) { struct stm32_rtc *rtc = platform_get_drvdata(pdev); const struct stm32_rtc_registers *regs = &rtc->data->regs; @@ -869,8 +869,6 @@ static int stm32_rtc_remove(struct platform_device *pdev) dev_pm_clear_wake_irq(&pdev->dev); device_init_wakeup(&pdev->dev, false); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -917,7 +915,7 @@ static SIMPLE_DEV_PM_OPS(stm32_rtc_pm_ops, static struct platform_driver stm32_rtc_driver = { .probe = stm32_rtc_probe, - .remove = stm32_rtc_remove, + .remove_new = stm32_rtc_remove, .driver = { .name = DRIVER_NAME, .pm = &stm32_rtc_pm_ops, -- GitLab From 16324165ab1f90fa06294679e3de58cb53c0423f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:20 +0100 Subject: [PATCH 0831/5631] rtc: stmp3xxx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-34-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-stmp3xxx.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/rtc/rtc-stmp3xxx.c b/drivers/rtc/rtc-stmp3xxx.c index aae40d20d086..6f11b745f34d 100644 --- a/drivers/rtc/rtc-stmp3xxx.c +++ b/drivers/rtc/rtc-stmp3xxx.c @@ -232,17 +232,15 @@ static const struct rtc_class_ops stmp3xxx_rtc_ops = { .set_alarm = stmp3xxx_rtc_set_alarm, }; -static int stmp3xxx_rtc_remove(struct platform_device *pdev) +static void stmp3xxx_rtc_remove(struct platform_device *pdev) { struct stmp3xxx_rtc_data *rtc_data = platform_get_drvdata(pdev); if (!rtc_data) - return 0; + return; writel(STMP3XXX_RTC_CTRL_ALARM_IRQ_EN, rtc_data->io + STMP3XXX_RTC_CTRL + STMP_OFFSET_REG_CLR); - - return 0; } static int stmp3xxx_rtc_probe(struct platform_device *pdev) @@ -406,7 +404,7 @@ MODULE_DEVICE_TABLE(of, rtc_dt_ids); static struct platform_driver stmp3xxx_rtcdrv = { .probe = stmp3xxx_rtc_probe, - .remove = stmp3xxx_rtc_remove, + .remove_new = stmp3xxx_rtc_remove, .driver = { .name = "stmp3xxx-rtc", .pm = &stmp3xxx_rtc_pm_ops, -- GitLab From d6f525040eef1562327fccc4412acdb4f173e01b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:21 +0100 Subject: [PATCH 0832/5631] rtc: sunplus: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-35-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-sunplus.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index 4b578e4d44f6..44b8083603c2 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -304,15 +304,13 @@ static int sp_rtc_probe(struct platform_device *plat_dev) return ret; } -static int sp_rtc_remove(struct platform_device *plat_dev) +static void sp_rtc_remove(struct platform_device *plat_dev) { struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev); device_init_wakeup(&plat_dev->dev, 0); reset_control_assert(sp_rtc->rstc); clk_disable_unprepare(sp_rtc->rtcclk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -347,7 +345,7 @@ static SIMPLE_DEV_PM_OPS(sp_rtc_pm_ops, sp_rtc_suspend, sp_rtc_resume); static struct platform_driver sp_rtc_driver = { .probe = sp_rtc_probe, - .remove = sp_rtc_remove, + .remove_new = sp_rtc_remove, .driver = { .name = "sp7021-rtc", .of_match_table = sp_rtc_of_match, -- GitLab From 31c94505f44b47493d62c0fd43d30838326d345f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:22 +0100 Subject: [PATCH 0833/5631] rtc: tegra: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-36-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-tegra.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c index 85f7ad5d5390..441e0a66b215 100644 --- a/drivers/rtc/rtc-tegra.c +++ b/drivers/rtc/rtc-tegra.c @@ -342,13 +342,11 @@ static int tegra_rtc_probe(struct platform_device *pdev) return ret; } -static int tegra_rtc_remove(struct platform_device *pdev) +static void tegra_rtc_remove(struct platform_device *pdev) { struct tegra_rtc_info *info = platform_get_drvdata(pdev); clk_disable_unprepare(info->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -401,7 +399,7 @@ static void tegra_rtc_shutdown(struct platform_device *pdev) static struct platform_driver tegra_rtc_driver = { .probe = tegra_rtc_probe, - .remove = tegra_rtc_remove, + .remove_new = tegra_rtc_remove, .shutdown = tegra_rtc_shutdown, .driver = { .name = "tegra_rtc", -- GitLab From adebcc1c1916188c1c9ac8e8f54123b07431baf7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:23 +0100 Subject: [PATCH 0834/5631] rtc: tps6586x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-37-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-tps6586x.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c index 52093e7ba22d..9f14e2475747 100644 --- a/drivers/rtc/rtc-tps6586x.c +++ b/drivers/rtc/rtc-tps6586x.c @@ -279,13 +279,12 @@ static int tps6586x_rtc_probe(struct platform_device *pdev) return ret; }; -static int tps6586x_rtc_remove(struct platform_device *pdev) +static void tps6586x_rtc_remove(struct platform_device *pdev) { struct device *tps_dev = to_tps6586x_dev(&pdev->dev); tps6586x_update(tps_dev, RTC_CTRL, 0, RTC_ENABLE | OSC_SRC_SEL | PRE_BYPASS | CL_SEL_MASK); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -317,7 +316,7 @@ static struct platform_driver tps6586x_rtc_driver = { .pm = &tps6586x_pm_ops, }, .probe = tps6586x_rtc_probe, - .remove = tps6586x_rtc_remove, + .remove_new = tps6586x_rtc_remove, }; module_platform_driver(tps6586x_rtc_driver); -- GitLab From fff118c9e8331b9b08b69841498fbea34693a28c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:24 +0100 Subject: [PATCH 0835/5631] rtc: twl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-38-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-twl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index c24d1e18f56c..81b36948c2fa 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -586,7 +586,7 @@ static int twl_rtc_probe(struct platform_device *pdev) * Disable all TWL RTC module interrupts. * Sets status flag to free. */ -static int twl_rtc_remove(struct platform_device *pdev) +static void twl_rtc_remove(struct platform_device *pdev) { struct twl_rtc *twl_rtc = platform_get_drvdata(pdev); @@ -599,8 +599,6 @@ static int twl_rtc_remove(struct platform_device *pdev) twl6030_interrupt_mask(TWL6030_RTC_INT_MASK, REG_INT_MSK_STS_A); } - - return 0; } static void twl_rtc_shutdown(struct platform_device *pdev) @@ -642,7 +640,7 @@ MODULE_DEVICE_TABLE(of, twl_rtc_of_match); static struct platform_driver twl4030rtc_driver = { .probe = twl_rtc_probe, - .remove = twl_rtc_remove, + .remove_new = twl_rtc_remove, .shutdown = twl_rtc_shutdown, .driver = { .name = "twl_rtc", -- GitLab From 5b1064441f20fc3f397239599b1193fecb7a90e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:25 +0100 Subject: [PATCH 0836/5631] rtc: vt8500: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-39-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-vt8500.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c index 197b649cd629..ccfa76513a2c 100644 --- a/drivers/rtc/rtc-vt8500.c +++ b/drivers/rtc/rtc-vt8500.c @@ -235,14 +235,12 @@ static int vt8500_rtc_probe(struct platform_device *pdev) return devm_rtc_register_device(vt8500_rtc->rtc); } -static int vt8500_rtc_remove(struct platform_device *pdev) +static void vt8500_rtc_remove(struct platform_device *pdev) { struct vt8500_rtc *vt8500_rtc = platform_get_drvdata(pdev); /* Disable alarm matching */ writel(0, vt8500_rtc->regbase + VT8500_RTC_IS); - - return 0; } static const struct of_device_id wmt_dt_ids[] = { @@ -253,7 +251,7 @@ MODULE_DEVICE_TABLE(of, wmt_dt_ids); static struct platform_driver vt8500_rtc_driver = { .probe = vt8500_rtc_probe, - .remove = vt8500_rtc_remove, + .remove_new = vt8500_rtc_remove, .driver = { .name = "vt8500-rtc", .of_match_table = wmt_dt_ids, -- GitLab From 631aa2d919f542373892d5ef6baf13e2969a10fd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:26 +0100 Subject: [PATCH 0837/5631] rtc: wm8350: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20230304133028.2135435-40-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-wm8350.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c index 6eaa9321c074..947f8071803f 100644 --- a/drivers/rtc/rtc-wm8350.c +++ b/drivers/rtc/rtc-wm8350.c @@ -451,14 +451,12 @@ static int wm8350_rtc_probe(struct platform_device *pdev) return 0; } -static int wm8350_rtc_remove(struct platform_device *pdev) +static void wm8350_rtc_remove(struct platform_device *pdev) { struct wm8350 *wm8350 = platform_get_drvdata(pdev); wm8350_free_irq(wm8350, WM8350_IRQ_RTC_SEC, wm8350); wm8350_free_irq(wm8350, WM8350_IRQ_RTC_ALM, wm8350); - - return 0; } static SIMPLE_DEV_PM_OPS(wm8350_rtc_pm_ops, wm8350_rtc_suspend, @@ -466,7 +464,7 @@ static SIMPLE_DEV_PM_OPS(wm8350_rtc_pm_ops, wm8350_rtc_suspend, static struct platform_driver wm8350_rtc_driver = { .probe = wm8350_rtc_probe, - .remove = wm8350_rtc_remove, + .remove_new = wm8350_rtc_remove, .driver = { .name = "wm8350-rtc", .pm = &wm8350_rtc_pm_ops, -- GitLab From 257062d2679f4db5b6ebc9f4e6a77d0a45977278 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:27 +0100 Subject: [PATCH 0838/5631] rtc: xgene: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-41-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-xgene.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c index d3d0054e21fd..f78efc9760c0 100644 --- a/drivers/rtc/rtc-xgene.c +++ b/drivers/rtc/rtc-xgene.c @@ -192,14 +192,13 @@ static int xgene_rtc_probe(struct platform_device *pdev) return 0; } -static int xgene_rtc_remove(struct platform_device *pdev) +static void xgene_rtc_remove(struct platform_device *pdev) { struct xgene_rtc_dev *pdata = platform_get_drvdata(pdev); xgene_rtc_alarm_irq_enable(&pdev->dev, 0); device_init_wakeup(&pdev->dev, 0); clk_disable_unprepare(pdata->clk); - return 0; } static int __maybe_unused xgene_rtc_suspend(struct device *dev) @@ -264,7 +263,7 @@ MODULE_DEVICE_TABLE(of, xgene_rtc_of_match); static struct platform_driver xgene_rtc_driver = { .probe = xgene_rtc_probe, - .remove = xgene_rtc_remove, + .remove_new = xgene_rtc_remove, .driver = { .name = "xgene-rtc", .pm = &xgene_rtc_pm_ops, -- GitLab From f45e5cfa73f445fa3cfbb7ebac3a7e2c66a9281c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sat, 4 Mar 2023 14:30:28 +0100 Subject: [PATCH 0839/5631] rtc: zynqmp: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304133028.2135435-42-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-zynqmp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c index c9b85c838ebe..08ed171bdab4 100644 --- a/drivers/rtc/rtc-zynqmp.c +++ b/drivers/rtc/rtc-zynqmp.c @@ -342,12 +342,10 @@ static int xlnx_rtc_probe(struct platform_device *pdev) return devm_rtc_register_device(xrtcdev->rtc); } -static int xlnx_rtc_remove(struct platform_device *pdev) +static void xlnx_rtc_remove(struct platform_device *pdev) { xlnx_rtc_alarm_irq_enable(&pdev->dev, 0); device_init_wakeup(&pdev->dev, 0); - - return 0; } static int __maybe_unused xlnx_rtc_suspend(struct device *dev) @@ -384,7 +382,7 @@ MODULE_DEVICE_TABLE(of, xlnx_rtc_of_match); static struct platform_driver xlnx_rtc_driver = { .probe = xlnx_rtc_probe, - .remove = xlnx_rtc_remove, + .remove_new = xlnx_rtc_remove, .driver = { .name = KBUILD_MODNAME, .pm = &xlnx_rtc_pm_ops, -- GitLab From 335a42ebb0ca8ee9997a1731aaaae6dcd704c113 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:31 +0100 Subject: [PATCH 0840/5631] workqueue: Fix hung time report of worker pools The workqueue watchdog prints a warning when there is no progress in a worker pool. Where the progress means that the pool started processing a pending work item. Note that it is perfectly fine to process work items much longer. The progress should be guaranteed by waking up or creating idle workers. show_one_worker_pool() prints state of non-idle worker pool. It shows a delay since the last pool->watchdog_ts. The timestamp is updated when a first pending work is queued in __queue_work(). Also it is updated when a work is dequeued for processing in worker_thread() and rescuer_thread(). The delay is misleading when there is no pending work item. In this case it shows how long the last work item is being proceed. Show zero instead. There is no stall if there is no pending work. Fixes: 82607adcf9cdf40fb7b ("workqueue: implement lockup detector") Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3f1fabea000f..8c0ec21a86a2 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5000,10 +5000,16 @@ static void show_one_worker_pool(struct worker_pool *pool) struct worker *worker; bool first = true; unsigned long flags; + unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; + + /* How long the first pending work is waiting for a worker. */ + if (!list_empty(&pool->worklist)) + hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; + /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write @@ -5012,9 +5018,7 @@ static void show_one_worker_pool(struct worker_pool *pool) printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" hung=%us workers=%d", - jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000, - pool->nr_workers); + pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); -- GitLab From 3f0ea0b864562c6bd1cee892026067eaea7be242 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:32 +0100 Subject: [PATCH 0841/5631] workqueue: Warn when a new worker could not be created The workqueue watchdog reports a lockup when there was not any progress in the worker pool for a long time. The progress means that a pending work item starts being proceed. The progress is guaranteed by using idle workers or creating new workers for pending work items. There are several reasons why a new worker could not be created: + there is not enough memory + there is no free pool ID (IDR API) + the system reached PID limit + the process creating the new worker was interrupted + the last idle worker (manager) has not been scheduled for a long time. It was not able to even start creating the kthread. None of these failures is reported at the moment. The only clue is that show_one_worker_pool() prints that there is a manager. It is the last idle worker that is responsible for creating a new one. But it is not clear if create_worker() is failing and why. Make the debugging easier by printing errors in create_worker(). The error code is important, especially from kthread_create_on_node(). It helps to distinguish the various reasons. For example, reaching memory limit (-ENOMEM), other system limits (-EAGAIN), or process interrupted (-EINTR). Use pr_once() to avoid repeating the same error every CREATE_COOLDOWN for each stuck worker pool. Ratelimited printk() might be better. It would help to know if the problem remains. It would be more clear if the create_worker() errors and workqueue stalls are related. Also old messages might get lost when the internal log buffer is full. The problem is that printk() might touch the watchdog. For example, see touch_nmi_watchdog() in serial8250_console_write(). It would require synchronization of the begin and length of the ratelimit interval with the workqueue watchdog. Otherwise, the error messages might break the watchdog. This does not look worth the complexity. Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8c0ec21a86a2..9760f0fca82d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1936,12 +1936,17 @@ static struct worker *create_worker(struct worker_pool *pool) /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); - if (id < 0) + if (id < 0) { + pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", + ERR_PTR(id)); return NULL; + } worker = alloc_worker(pool->node); - if (!worker) + if (!worker) { + pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; + } worker->id = id; @@ -1953,8 +1958,11 @@ static struct worker *create_worker(struct worker_pool *pool) worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf); - if (IS_ERR(worker->task)) + if (IS_ERR(worker->task)) { + pr_err_once("workqueue: Failed to create a worker thread: %pe", + worker->task); goto fail; + } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool->attrs->cpumask); -- GitLab From 60f540389a5d2df25ddc7ad511b4fa2880dea521 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:33 +0100 Subject: [PATCH 0842/5631] workqueue: Interrupted create_worker() is not a repeated event kthread_create_on_node() might get interrupted(). It is rare but realistic. For example, when an unbound workqueue is allocated in module_init() callback. It is done in the context of the "modprobe" process. And, for example, systemd might kill pending processes when switching root from initrd to the booted system. The interrupt is a one-off event and the race might be hard to reproduce. It is always worth printing. Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9760f0fca82d..5f0ecaaaf997 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1959,8 +1959,13 @@ static struct worker *create_worker(struct worker_pool *pool) worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf); if (IS_ERR(worker->task)) { - pr_err_once("workqueue: Failed to create a worker thread: %pe", - worker->task); + if (PTR_ERR(worker->task) == -EINTR) { + pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", + id_buf); + } else { + pr_err_once("workqueue: Failed to create a worker thread: %pe", + worker->task); + } goto fail; } -- GitLab From 4c0736a76a186e5df2cd2afda3e7a04d2a427d1b Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:34 +0100 Subject: [PATCH 0843/5631] workqueue: Warn when a rescuer could not be created Rescuers are created when a workqueue with WQ_MEM_RECLAIM is allocated. It typically happens during the system boot. systemd switches the root filesystem from initrd to the booted system during boot. It kills processes that block the switch for too long. One of the process might be modprobe that tries to create a workqueue. These problems are hard to reproduce. Also alloc_workqueue() does not pass the error code. Make the debugging easier by printing an error, similar to create_worker(). Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5f0ecaaaf997..fb1eb7a3f49b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4391,13 +4391,18 @@ static int init_rescuer(struct workqueue_struct *wq) return 0; rescuer = alloc_worker(NUMA_NO_NODE); - if (!rescuer) + if (!rescuer) { + pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", + wq->name); return -ENOMEM; + } rescuer->rescue_wq = wq; rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); + pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", + wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } -- GitLab From cd2440d66fec7d1bdb4f605b64c27c63c9141989 Mon Sep 17 00:00:00 2001 From: Petr Mladek Date: Tue, 7 Mar 2023 13:53:35 +0100 Subject: [PATCH 0844/5631] workqueue: Print backtraces from CPUs with hung CPU bound workqueues The workqueue watchdog reports a lockup when there was not any progress in the worker pool for a long time. The progress means that a pending work item starts being proceed. Worker pools for unbound workqueues always wake up an idle worker and try to process the work immediately. The last idle worker has to create new worker first. The stall might happen only when a new worker could not be created in which case an error should get printed. Another problem might be too high load. In this case, workers are victims of a global system problem. Worker pools for CPU bound workqueues are designed for lightweight work items that do not need much CPU time. They are proceed one by one on a single worker. New worker is used only when a work is sleeping. It creates one additional scenario. The stall might happen when the CPU-bound workqueue is used for CPU-intensive work. More precisely, the stall is detected when a CPU-bound worker is in the TASK_RUNNING state for too long. In this case, it might be useful to see the backtrace from the problematic worker. The information how long a worker is in the running state is not available. But the CPU-bound worker pools do not have many workers in the running state by definition. And only few pools are typically blocked. It should be acceptable to print backtraces from all workers in TASK_RUNNING state in the stalled worker pools. The number of false positives should be very low. Signed-off-by: Petr Mladek Signed-off-by: Tejun Heo --- kernel/workqueue.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index fb1eb7a3f49b..044b4eee760b 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -141,6 +142,8 @@ enum { * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. + * + * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ @@ -153,6 +156,7 @@ struct worker_pool { unsigned int flags; /* X: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ + bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU @@ -5976,6 +5980,57 @@ static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; +/* + * Show workers that might prevent the processing of pending work items. + * The only candidates are CPU-bound workers in the running state. + * Pending work items should be handled by another idle worker + * in all other situations. + */ +static void show_cpu_pool_hog(struct worker_pool *pool) +{ + struct worker *worker; + unsigned long flags; + int bkt; + + raw_spin_lock_irqsave(&pool->lock, flags); + + hash_for_each(pool->busy_hash, bkt, worker, hentry) { + if (task_is_running(worker->task)) { + /* + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. + */ + printk_deferred_enter(); + + pr_info("pool %d:\n", pool->id); + sched_show_task(worker->task); + + printk_deferred_exit(); + } + } + + raw_spin_unlock_irqrestore(&pool->lock, flags); +} + +static void show_cpu_pools_hogs(void) +{ + struct worker_pool *pool; + int pi; + + pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); + + rcu_read_lock(); + + for_each_pool(pool, pi) { + if (pool->cpu_stall) + show_cpu_pool_hog(pool); + + } + + rcu_read_unlock(); +} + static void wq_watchdog_reset_touched(void) { int cpu; @@ -5989,6 +6044,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; + bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; @@ -6001,6 +6057,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; + pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; @@ -6025,11 +6082,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; + if (pool->cpu >= 0) { + pool->cpu_stall = true; + cpu_pool_stall = true; + } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } + + } rcu_read_unlock(); @@ -6037,6 +6100,9 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) if (lockup_detected) show_all_workqueues(); + if (cpu_pool_stall) + show_cpu_pools_hogs(); + wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } -- GitLab From 4cdb91b0dea7d7f59fa84a13c7753cd434fdedcf Mon Sep 17 00:00:00 2001 From: Kamalesh Babulal Date: Fri, 3 Mar 2023 15:23:10 +0530 Subject: [PATCH 0845/5631] cgroup: bpf: use cgroup_lock()/cgroup_unlock() wrappers Replace mutex_[un]lock() with cgroup_[un]lock() wrappers to stay consistent across cgroup core and other subsystem code, while operating on the cgroup_mutex. Signed-off-by: Kamalesh Babulal Acked-by: Alexei Starovoitov Reviewed-by: Christian Brauner Signed-off-by: Tejun Heo --- kernel/bpf/cgroup.c | 38 ++++++++++++------------ kernel/bpf/cgroup_iter.c | 4 +-- kernel/bpf/local_storage.c | 4 +-- kernel/cgroup/cgroup-v1.c | 16 +++++----- kernel/cgroup/cgroup.c | 60 +++++++++++++++++++------------------- 5 files changed, 61 insertions(+), 61 deletions(-) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index bf2fdb33fb31..3458701dcb28 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -173,11 +173,11 @@ void bpf_cgroup_atype_put(int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (--cgroup_lsm_atype[i].refcnt <= 0) cgroup_lsm_atype[i].attach_btf_id = 0; WARN_ON_ONCE(cgroup_lsm_atype[i].refcnt < 0); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); } #else static enum cgroup_bpf_attach_type @@ -282,7 +282,7 @@ static void cgroup_bpf_release(struct work_struct *work) unsigned int atype; - mutex_lock(&cgroup_mutex); + cgroup_lock(); for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { struct hlist_head *progs = &cgrp->bpf.progs[atype]; @@ -315,7 +315,7 @@ static void cgroup_bpf_release(struct work_struct *work) bpf_cgroup_storage_free(storage); } - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); @@ -729,9 +729,9 @@ static int cgroup_bpf_attach(struct cgroup *cgrp, { int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -831,7 +831,7 @@ static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, cg_link = container_of(link, struct bpf_cgroup_link, link); - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* link might have been auto-released by dying cgroup, so fail */ if (!cg_link->cgroup) { ret = -ENOLINK; @@ -843,7 +843,7 @@ static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, } ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); out_unlock: - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -1009,9 +1009,9 @@ static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, { int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -1120,9 +1120,9 @@ static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, { int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = __cgroup_bpf_query(cgrp, attr, uattr); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -1189,11 +1189,11 @@ static void bpf_cgroup_link_release(struct bpf_link *link) if (!cg_link->cgroup) return; - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* re-check cgroup under lock again */ if (!cg_link->cgroup) { - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return; } @@ -1205,7 +1205,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link) cg = cg_link->cgroup; cg_link->cgroup = NULL; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); cgroup_put(cg); } @@ -1232,10 +1232,10 @@ static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); seq_printf(seq, "cgroup_id:\t%llu\n" @@ -1251,10 +1251,10 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); info->cgroup.cgroup_id = cg_id; info->cgroup.attach_type = cg_link->type; diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 06989d278846..810378f04fbc 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -58,7 +58,7 @@ static void *cgroup_iter_seq_start(struct seq_file *seq, loff_t *pos) { struct cgroup_iter_priv *p = seq->private; - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* cgroup_iter doesn't support read across multiple sessions. */ if (*pos > 0) { @@ -89,7 +89,7 @@ static void cgroup_iter_seq_stop(struct seq_file *seq, void *v) { struct cgroup_iter_priv *p = seq->private; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); /* pass NULL to the prog for post-processing */ if (!v) { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index e90d9f63edc5..9bceefee14d5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -333,14 +333,14 @@ static void cgroup_storage_map_free(struct bpf_map *_map) struct list_head *storages = &map->list; struct bpf_cgroup_storage *storage, *stmp; - mutex_lock(&cgroup_mutex); + cgroup_lock(); list_for_each_entry_safe(storage, stmp, storages, list_map) { bpf_cgroup_storage_unlink(storage); bpf_cgroup_storage_free(storage); } - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); WARN_ON(!RB_EMPTY_ROOT(&map->root)); WARN_ON(!list_empty(&map->list)); diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 52bb5a74a23b..aeef06c465ef 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -58,7 +58,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) struct cgroup_root *root; int retval = 0; - mutex_lock(&cgroup_mutex); + cgroup_lock(); cgroup_attach_lock(true); for_each_root(root) { struct cgroup *from_cgrp; @@ -72,7 +72,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) break; } cgroup_attach_unlock(true); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return retval; } @@ -106,7 +106,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) if (ret) return ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); @@ -145,7 +145,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) out_err: cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -847,13 +847,13 @@ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); @@ -1119,7 +1119,7 @@ int cgroup1_reconfigure(struct fs_context *fc) trace_cgroup_remount(root); out_unlock: - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -1246,7 +1246,7 @@ int cgroup1_get_tree(struct fs_context *fc) if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); if (!ret) ret = cgroup_do_get_tree(fc); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 935e8121b21e..83ea13f2ccb1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1391,7 +1391,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); cgroup_rstat_exit(cgrp); kernfs_destroy_root(root->kf_root); @@ -1625,7 +1625,7 @@ void cgroup_kn_unlock(struct kernfs_node *kn) else cgrp = kn->parent->priv; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); @@ -1670,7 +1670,7 @@ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else - mutex_lock(&cgroup_mutex); + cgroup_lock(); if (!cgroup_is_dead(cgrp)) return cgrp; @@ -2167,13 +2167,13 @@ int cgroup_do_get_tree(struct fs_context *fc) struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; - mutex_lock(&cgroup_mutex); + cgroup_lock(); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); @@ -2356,13 +2356,13 @@ int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, { int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -2388,7 +2388,7 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) int hierarchy_id = 1; int ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); @@ -2402,7 +2402,7 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) } spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(task_cgroup_path); @@ -3111,7 +3111,7 @@ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) int ssid; restart: - mutex_lock(&cgroup_mutex); + cgroup_lock(); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { @@ -3125,7 +3125,7 @@ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait); @@ -4374,9 +4374,9 @@ int cgroup_rm_cftypes(struct cftype *cfts) if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; - mutex_lock(&cgroup_mutex); + cgroup_lock(); ret = cgroup_rm_cftypes_locked(cfts); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -4408,14 +4408,14 @@ static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) if (ret) return ret; - mutex_lock(&cgroup_mutex); + cgroup_lock(); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); return ret; } @@ -5385,7 +5385,7 @@ static void css_release_work_fn(struct work_struct *work) struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; - mutex_lock(&cgroup_mutex); + cgroup_lock(); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); @@ -5426,7 +5426,7 @@ static void css_release_work_fn(struct work_struct *work) NULL); } - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); @@ -5774,7 +5774,7 @@ static void css_killed_work_fn(struct work_struct *work) struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); - mutex_lock(&cgroup_mutex); + cgroup_lock(); do { offline_css(css); @@ -5783,7 +5783,7 @@ static void css_killed_work_fn(struct work_struct *work) css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); } /* css kill confirmation processing requires process context, bounce */ @@ -5967,7 +5967,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) pr_debug("Initializing cgroup subsys %s\n", ss->name); - mutex_lock(&cgroup_mutex); + cgroup_lock(); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); @@ -6011,7 +6011,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) BUG_ON(online_css(css)); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); } /** @@ -6071,7 +6071,7 @@ int __init cgroup_init(void) get_user_ns(init_cgroup_ns.user_ns); - mutex_lock(&cgroup_mutex); + cgroup_lock(); /* * Add init_css_set to the hash table so that dfl_root can link to @@ -6082,7 +6082,7 @@ int __init cgroup_init(void) BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); for_each_subsys(ss, ssid) { if (ss->early_init) { @@ -6134,9 +6134,9 @@ int __init cgroup_init(void) if (ss->bind) ss->bind(init_css_set.subsys[ssid]); - mutex_lock(&cgroup_mutex); + cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); } /* init_css_set.subsys[] has been updated, re-hash */ @@ -6241,7 +6241,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, if (!buf) goto out; - mutex_lock(&cgroup_mutex); + cgroup_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { @@ -6296,7 +6296,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); kfree(buf); out: return retval; @@ -6380,7 +6380,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) struct file *f; if (kargs->flags & CLONE_INTO_CGROUP) - mutex_lock(&cgroup_mutex); + cgroup_lock(); cgroup_threadgroup_change_begin(current); @@ -6455,7 +6455,7 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) err: cgroup_threadgroup_change_end(current); - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); if (f) fput(f); if (dst_cgrp) @@ -6482,7 +6482,7 @@ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; - mutex_unlock(&cgroup_mutex); + cgroup_unlock(); if (cset) { put_css_set(cset); -- GitLab From 28e4b4597d65927f8147c493d66aa0fe006e364c Mon Sep 17 00:00:00 2001 From: David Matlack Date: Thu, 26 Jan 2023 10:40:21 -0800 Subject: [PATCH 0846/5631] KVM: x86/mmu: Collapse kvm_flush_remote_tlbs_with_{range,address}() together Collapse kvm_flush_remote_tlbs_with_range() and kvm_flush_remote_tlbs_with_address() into a single function. This eliminates some lines of code and a useless NULL check on the range struct. Opportunistically switch from ENOTSUPP to EOPNOTSUPP to make checkpatch happy. Signed-off-by: David Matlack Link: https://lore.kernel.org/r/20230126184025.2294823-4-dmatlack@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 9655656dce50..ed1df733f12a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -261,27 +261,20 @@ static inline bool kvm_available_flush_tlb_with_range(void) return kvm_x86_ops.tlb_remote_flush_with_range; } -static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) -{ - int ret = -ENOTSUPP; - - if (range && kvm_x86_ops.tlb_remote_flush_with_range) - ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range); - - if (ret) - kvm_flush_remote_tlbs(kvm); -} - void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages) { struct kvm_tlb_range range; + int ret = -EOPNOTSUPP; range.start_gfn = start_gfn; range.pages = pages; - kvm_flush_remote_tlbs_with_range(kvm, &range); + if (kvm_x86_ops.tlb_remote_flush_with_range) + ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, &range); + + if (ret) + kvm_flush_remote_tlbs(kvm); } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); -- GitLab From f12f0c7da37c58da92bd4a6bdc469df7e0b2da5e Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 9 Mar 2023 20:44:51 +0000 Subject: [PATCH 0847/5631] rtc: mpfs: convert SOC_MICROCHIP_POLARFIRE to ARCH_MICROCHIP_POLARFIRE As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the use of such symbols on other architectures, convert the Microchip FPGA RTC driver to use the new symbol. Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230309204452.969574-5-conor@kernel.org Signed-off-by: Alexandre Belloni --- drivers/rtc/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 5a71579af0a1..753872408615 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1970,7 +1970,7 @@ config RTC_DRV_MSC313 config RTC_DRV_POLARFIRE_SOC tristate "Microchip PolarFire SoC built-in RTC" - depends on SOC_MICROCHIP_POLARFIRE + depends on ARCH_MICROCHIP_POLARFIRE help If you say yes here you will get support for the built-in RTC on Polarfire SoC. -- GitLab From 8c63e8c2176552d5c003d7459609383d32bf47f3 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Thu, 26 Jan 2023 10:40:22 -0800 Subject: [PATCH 0848/5631] KVM: x86/mmu: Rename kvm_flush_remote_tlbs_with_address() Rename kvm_flush_remote_tlbs_with_address() to kvm_flush_remote_tlbs_range(). This name is shorter, which reduces the number of callsites that need to be broken up across multiple lines, and more readable since it conveys a range of memory is being flushed rather than a single address. No functional change intended. Signed-off-by: David Matlack Link: https://lore.kernel.org/r/20230126184025.2294823-5-dmatlack@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 14 +++++--------- arch/x86/kvm/mmu/mmu_internal.h | 7 +++---- 2 files changed, 8 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index ed1df733f12a..b6635da53cb3 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -261,8 +261,7 @@ static inline bool kvm_available_flush_tlb_with_range(void) return kvm_x86_ops.tlb_remote_flush_with_range; } -void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, - u64 start_gfn, u64 pages) +void kvm_flush_remote_tlbs_range(struct kvm *kvm, u64 start_gfn, u64 pages) { struct kvm_tlb_range range; int ret = -EOPNOTSUPP; @@ -5922,9 +5921,8 @@ slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_with_address(kvm, - start_gfn, - iterator.gfn - start_gfn + 1); + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); flush = false; } cond_resched_rwlock_write(&kvm->mmu_lock); @@ -6279,8 +6277,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) } if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start); + kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); kvm_mmu_invalidate_end(kvm, 0, -1ul); @@ -6669,8 +6666,7 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, * is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 2cbb155c686c..4b2a1dc43db3 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -170,14 +170,13 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); -void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, - u64 start_gfn, u64 pages); +void kvm_flush_remote_tlbs_range(struct kvm *kvm, u64 start_gfn, u64 pages); /* Flush the given page (huge or not) of guest memory. */ static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) { - kvm_flush_remote_tlbs_with_address(kvm, gfn_round_for_level(gfn, level), - KVM_PAGES_PER_HPAGE(level)); + kvm_flush_remote_tlbs_range(kvm, gfn_round_for_level(gfn, level), + KVM_PAGES_PER_HPAGE(level)); } unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); -- GitLab From 4d9890ac9d43d4dfd011110ab96633caa6fa829c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:36 -0600 Subject: [PATCH 0849/5631] rtc: sun6i: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Reviewed-by: Jernej Skrabec Reviewed-by: Andre Przywara Link: https://lore.kernel.org/r/20230310144736.1547041-1-robh@kernel.org Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-sun6i.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index 7038f47d77ff..dc76537f1b62 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -260,7 +260,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node, } /* Switch to the external, more precise, oscillator, if present */ - if (of_get_property(node, "clocks", NULL)) { + if (of_property_present(node, "clocks")) { reg |= SUN6I_LOSC_CTRL_EXT_OSC; if (rtc->data->has_losc_en) reg |= SUN6I_LOSC_CTRL_EXT_LOSC_EN; -- GitLab From f69c2b5420497b7a54181ce170d682cbeb1f119f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 10:40:21 +0100 Subject: [PATCH 0850/5631] rtc: omap: include header for omap_rtc_power_off_program prototype MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Non-static functions should have a prototype: drivers/rtc/rtc-omap.c:410:5: error: no previous prototype for ‘omap_rtc_power_off_program’ [-Werror=missing-prototypes] Fixes: 6256f7f7f217 ("rtc: OMAP: Add support for rtc-only mode") Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311094021.79730-1-krzysztof.kozlowski@linaro.org Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-omap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index fad30b3dde46..8ae4d7824ec9 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -25,6 +25,7 @@ #include #include #include +#include /* * The OMAP RTC is a year/month/day/hours/minutes/seconds BCD clock -- GitLab From cca1e2f790703bb22b56d94c5efc66c1d9517b21 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:12:26 +0100 Subject: [PATCH 0851/5631] rtc: ds1390: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/rtc/rtc-ds1390.c:216:34: error: ‘ds1390_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311111226.250922-1-krzysztof.kozlowski@linaro.org Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1390.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1390.c b/drivers/rtc/rtc-ds1390.c index 93ce72b9ae59..f46428ca77cc 100644 --- a/drivers/rtc/rtc-ds1390.c +++ b/drivers/rtc/rtc-ds1390.c @@ -213,7 +213,7 @@ static int ds1390_probe(struct spi_device *spi) return res; } -static const struct of_device_id ds1390_of_match[] = { +static const struct of_device_id ds1390_of_match[] __maybe_unused = { { .compatible = "dallas,ds1390" }, {} }; -- GitLab From b48cc753c017d1f5c6e317538205d40e70d04f3c Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 15 Mar 2023 09:20:20 +0100 Subject: [PATCH 0852/5631] rtc: pcf8523: fix coding-style issues Minor modifications for coding-style correctness (tabs, spaces and blank lines before and after brackets). In total 7 errors, 3 warnings and 1 check where removed from the checkpatch output without damaging code readability. Signed-off-by: Javier Carrasco Link: https://lore.kernel.org/r/20230315082021.2104452-2-javier.carrasco@wolfvision.net Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pcf8523.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index 2e111cdb94f7..ccb5aa690433 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -21,7 +21,7 @@ #define PCF8523_CONTROL2_AF BIT(3) #define PCF8523_REG_CONTROL3 0x02 -#define PCF8523_CONTROL3_PM GENMASK(7,5) +#define PCF8523_CONTROL3_PM GENMASK(7, 5) #define PCF8523_PM_STANDBY 0x7 #define PCF8523_CONTROL3_BLF BIT(2) /* battery low bit, read-only */ #define PCF8523_CONTROL3_BSF BIT(3) @@ -234,8 +234,7 @@ static int pcf8523_param_get(struct device *dev, struct rtc_param *param) int ret; u32 value; - switch(param->param) { - + switch (param->param) { case RTC_PARAM_BACKUP_SWITCH_MODE: ret = regmap_read(pcf8523->regmap, PCF8523_REG_CONTROL3, &value); if (ret < 0) @@ -243,7 +242,7 @@ static int pcf8523_param_get(struct device *dev, struct rtc_param *param) value = FIELD_GET(PCF8523_CONTROL3_PM, value); - switch(value) { + switch (value) { case 0x0: case 0x4: param->uvalue = RTC_BSM_LEVEL; @@ -273,7 +272,7 @@ static int pcf8523_param_set(struct device *dev, struct rtc_param *param) struct pcf8523 *pcf8523 = dev_get_drvdata(dev); u8 mode; - switch(param->param) { + switch (param->param) { case RTC_PARAM_BACKUP_SWITCH_MODE: switch (param->uvalue) { case RTC_BSM_DISABLED: @@ -385,9 +384,9 @@ static const struct rtc_class_ops pcf8523_rtc_ops = { }; static const struct regmap_config regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = 0x13, + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x13, }; static int pcf8523_probe(struct i2c_client *client) -- GitLab From dc87fad6448fc574456516404469c0c2c48d642e Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 15 Mar 2023 09:20:21 +0100 Subject: [PATCH 0853/5631] rtc: pcf8523: remove unnecessary OR operation The value variable is initialized to 0 and it is not used to set any other bits rather than the one that defines the capacitor value. Setting this capacitor value is the only purpose of the function where the variable is defined and therefore the OR operation does not apply as a way to foresee functionality extensions either. Signed-off-by: Javier Carrasco Link: https://lore.kernel.org/r/20230315082021.2104452-3-javier.carrasco@wolfvision.net Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-pcf8523.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index ccb5aa690433..e7115ebef707 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -65,7 +65,7 @@ static int pcf8523_load_capacitance(struct pcf8523 *pcf8523, struct device_node load); fallthrough; case 12500: - value |= PCF8523_CONTROL1_CAP_SEL; + value = PCF8523_CONTROL1_CAP_SEL; break; case 7000: break; -- GitLab From 9d4655da1a4c17f6691a6434303d9973017bf1ca Mon Sep 17 00:00:00 2001 From: David Matlack Date: Thu, 26 Jan 2023 10:40:23 -0800 Subject: [PATCH 0854/5631] KVM: x86/mmu: Use gfn_t in kvm_flush_remote_tlbs_range() Use gfn_t instead of u64 for kvm_flush_remote_tlbs_range()'s parameters, since gfn_t is the standard type for GFNs throughout KVM. Opportunistically rename pages to nr_pages to make its role even more obvious. No functional change intended. Signed-off-by: David Matlack Link: https://lore.kernel.org/r/20230126184025.2294823-6-dmatlack@google.com [sean: convert pages to gfn_t too, and rename] Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 5 +++-- arch/x86/kvm/mmu/mmu_internal.h | 3 ++- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index b6635da53cb3..cc42fa097d5b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -261,13 +261,14 @@ static inline bool kvm_available_flush_tlb_with_range(void) return kvm_x86_ops.tlb_remote_flush_with_range; } -void kvm_flush_remote_tlbs_range(struct kvm *kvm, u64 start_gfn, u64 pages) +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, + gfn_t nr_pages) { struct kvm_tlb_range range; int ret = -EOPNOTSUPP; range.start_gfn = start_gfn; - range.pages = pages; + range.pages = nr_pages; if (kvm_x86_ops.tlb_remote_flush_with_range) ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, &range); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 4b2a1dc43db3..d39af5639ce9 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -170,7 +170,8 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); -void kvm_flush_remote_tlbs_range(struct kvm *kvm, u64 start_gfn, u64 pages); +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, + gfn_t nr_pages); /* Flush the given page (huge or not) of guest memory. */ static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) -- GitLab From 727ae377013249c05359f84975d21f3d13c70907 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Feb 2023 18:27:49 +0000 Subject: [PATCH 0855/5631] KVM: x86/mmu: Rename slot rmap walkers to add clarity and clean up code Replace "slot_handle_level" with "walk_slot_rmaps" to better capture what the helpers are doing, and to slightly shorten the function names so that each function's return type and attributes can be placed on the same line as the function declaration. No functional change intended. Link: https://lore.kernel.org/mm-commits/CAHk-=wjS-Jg7sGMwUPpDsjv392nDOOs0CtUtVkp=S6Q7JzFJRw@mail.gmail.com Signed-off-by: Ben Gardon Link: https://lore.kernel.org/r/20230202182809.1929122-2-bgardon@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 66 +++++++++++++++++++++--------------------- 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index cc42fa097d5b..88aba0d8e9e4 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5902,23 +5902,24 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot); /* The caller should hold mmu-lock before calling this function. */ -static __always_inline bool -slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield, - bool flush) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool flush_on_yield, bool flush) { struct slot_rmap_walk_iterator iterator; - for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, memslot); + flush |= fn(kvm, iterator.rmap, slot); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && flush_on_yield) { @@ -5933,23 +5934,23 @@ slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, return flush; } -static __always_inline bool -slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - bool flush_on_yield) +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) { - return slot_handle_level_range(kvm, memslot, fn, start_level, - end_level, memslot->base_gfn, - memslot->base_gfn + memslot->npages - 1, - flush_on_yield, false); + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + flush_on_yield, false); } -static __always_inline bool -slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, bool flush_on_yield) +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) { - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, - PG_LEVEL_4K, flush_on_yield); + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); } static void free_mmu_pages(struct kvm_mmu *mmu) @@ -6244,9 +6245,9 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = slot_handle_level_range(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, true, flush); } } @@ -6298,8 +6299,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, false); + walk_slot_rmaps(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, false); write_unlock(&kvm->mmu_lock); } @@ -6534,10 +6535,9 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, * all the way to the target level. There's no need to split pages * already at the target level. */ - for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) { - slot_handle_level_range(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); - } + for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) + __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, + level, level, start, end - 1, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6635,8 +6635,8 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, * Note, use KVM_MAX_HUGEPAGE_LEVEL - 1 since there's no need to zap * pages that are already mapped at the maximum hugepage level. */ - if (slot_handle_level(kvm, slot, kvm_mmu_zap_collapsible_spte, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) + if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); } @@ -6679,7 +6679,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, * Clear dirty bits only on 4k SPTEs since the legacy MMU only * support dirty logging at a 4k granularity. */ - slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); + walk_slot_rmaps_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } -- GitLab From eddd9e8302de77cea52b3b2aaa3e1db19e680dd0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Feb 2023 18:27:50 +0000 Subject: [PATCH 0856/5631] KVM: x86/mmu: Replace comment with an actual lockdep assertion on mmu_lock Assert that mmu_lock is held for write in __walk_slot_rmaps() instead of hoping the function comment will magically prevent introducing bugs. Signed-off-by: Ben Gardon Link: https://lore.kernel.org/r/20230202182809.1929122-3-bgardon@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 88aba0d8e9e4..bda2814dd158 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5906,7 +5906,6 @@ typedef bool (*slot_rmaps_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot); -/* The caller should hold mmu-lock before calling this function. */ static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, const struct kvm_memory_slot *slot, slot_rmaps_handler fn, @@ -5916,6 +5915,8 @@ static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, { struct slot_rmap_walk_iterator iterator; + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) -- GitLab From f3d90f901d18749dca096719540a075f59240051 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 2 Feb 2023 18:27:51 +0000 Subject: [PATCH 0857/5631] KVM: x86/mmu: Clean up mmu.c functions that put return type on separate line Adjust a variety of functions in mmu.c to put the function return type on the same line as the function declaration. As stated in the Linus specification: But the "on their own line" is complete garbage to begin with. That will NEVER be a kernel rule. We should never have a rule that assumes things are so long that they need to be on multiple lines. We don't put function return types on their own lines either, even if some other projects have that rule (just to get function names at the beginning of lines or some other odd reason). Leave the functions generated by BUILD_MMU_ROLE_REGS_ACCESSOR() as-is, that code is basically illegible no matter how it's formatted. No functional change intended. Link: https://lore.kernel.org/mm-commits/CAHk-=wjS-Jg7sGMwUPpDsjv392nDOOs0CtUtVkp=S6Q7JzFJRw@mail.gmail.com Signed-off-by: Ben Gardon Link: https://lore.kernel.org/r/20230202182809.1929122-4-bgardon@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 57 ++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 30 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index bda2814dd158..b2124962e5a8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -895,9 +895,9 @@ static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) untrack_possible_nx_huge_page(kvm, sp); } -static struct kvm_memory_slot * -gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, - bool no_dirty_log) +static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, + gfn_t gfn, + bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -960,9 +960,8 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, return count; } -static void -pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, - struct pte_list_desc *desc, int i) +static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, + struct pte_list_desc *desc, int i) { struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); int j = head_desc->spte_count - 1; @@ -1510,8 +1509,8 @@ struct slot_rmap_walk_iterator { struct kvm_rmap_head *end_rmap; }; -static void -rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) +static void rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, + int level) { iterator->level = level; iterator->gfn = iterator->start_gfn; @@ -1519,10 +1518,10 @@ rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot); } -static void -slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, - const struct kvm_memory_slot *slot, int start_level, - int end_level, gfn_t start_gfn, gfn_t end_gfn) +static void slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, + const struct kvm_memory_slot *slot, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn) { iterator->slot = slot; iterator->start_level = start_level; @@ -3373,9 +3372,9 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault) * Returns true if the SPTE was fixed successfully. Otherwise, * someone else modified the SPTE from its original value. */ -static bool -fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - u64 *sptep, u64 old_spte, u64 new_spte) +static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + u64 *sptep, u64 old_spte, u64 new_spte) { /* * Theoretically we could also set dirty bit (and flush TLB) here in @@ -4708,10 +4707,9 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, #include "paging_tmpl.h" #undef PTTYPE -static void -__reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, int level, bool nx, bool gbpages, - bool pse, bool amd) +static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, + u64 pa_bits_rsvd, int level, bool nx, + bool gbpages, bool pse, bool amd) { u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; @@ -4824,9 +4822,9 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, guest_cpuid_is_amd_or_hygon(vcpu)); } -static void -__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly, int huge_page_level) +static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, + u64 pa_bits_rsvd, bool execonly, + int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); u64 large_1g_rsvd = 0, large_2m_rsvd = 0; @@ -4926,8 +4924,7 @@ static inline bool boot_cpu_is_amd(void) * the direct page table on host, use as much mmu features as * possible, however, kvm currently does not do execution-protection. */ -static void -reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context) +static void reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context) { struct rsvd_bits_validate *shadow_zero_check; int i; @@ -5140,8 +5137,8 @@ static void paging32_init_context(struct kvm_mmu *context) context->sync_spte = paging32_sync_spte; } -static union kvm_cpu_role -kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) +static union kvm_cpu_role kvm_calc_cpu_role(struct kvm_vcpu *vcpu, + const struct kvm_mmu_role_regs *regs) { union kvm_cpu_role role = {0}; @@ -6750,8 +6747,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) } } -static unsigned long -mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long mmu_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct kvm *kvm; int nr_to_scan = sc->nr_to_scan; @@ -6809,8 +6806,8 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) return freed; } -static unsigned long -mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long mmu_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) { return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } -- GitLab From 30da26eacea6867353f7aa2c18f37a0a0fa82af4 Mon Sep 17 00:00:00 2001 From: Kasumov Ruslan Date: Wed, 15 Mar 2023 16:51:14 +0300 Subject: [PATCH 0858/5631] iio: adc: qcom-pm8xxx-xoadc: Remove useless condition in pm8xxx_xoadc_parse_channel() The left side of the loop condition never becomes false. hwchan cannot be NULL, because it points to elements of the hw_channels array that takes one of 4 predefined values: pm8018_xoadc_channels, pm8038_xoadc_channels, pm8058_xoadc_channels, pm8921_xoadc_channels. Found by Linux Verification Center (linuxtesting.org) with SVACE. Reviewed-by: Andi Shyti Reviewed-by: Linus Walleij Signed-off-by: Kasumov Ruslan Link: https://lore.kernel.org/r/20230315135114.22684-1-xhxgldhlpfy@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/adc/qcom-pm8xxx-xoadc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/qcom-pm8xxx-xoadc.c b/drivers/iio/adc/qcom-pm8xxx-xoadc.c index eb424496ee1d..64a3aeb6261c 100644 --- a/drivers/iio/adc/qcom-pm8xxx-xoadc.c +++ b/drivers/iio/adc/qcom-pm8xxx-xoadc.c @@ -758,7 +758,7 @@ static int pm8xxx_xoadc_parse_channel(struct device *dev, /* Find the right channel setting */ chid = 0; hwchan = &hw_channels[0]; - while (hwchan && hwchan->datasheet_name) { + while (hwchan->datasheet_name) { if (hwchan->pre_scale_mux == pre_scale_mux && hwchan->amux_channel == amux_channel) break; -- GitLab From fb37fdd02856e45e78209d32522029c9f77fe7b7 Mon Sep 17 00:00:00 2001 From: Cheng Ziqiu Date: Tue, 14 Mar 2023 15:01:30 +0800 Subject: [PATCH 0859/5631] iio: adc: at91-sama5d2_adc: remove dead code in at91_adc_probe() From the comment of platform_get_irq(), it only returns non-zero IRQ number and negative error number, other than zero. Fix this by removing the if condition. Signed-off-by: Cheng Ziqiu Reviewed-by: Dongliang Mu Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230314070130.60581-1-chengziqiu@hust.edu.cn Signed-off-by: Jonathan Cameron --- drivers/iio/adc/at91-sama5d2_adc.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index b5d0c9ee284c..30554026a7fe 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -2400,12 +2400,8 @@ static int at91_adc_probe(struct platform_device *pdev) st->dma_st.phys_addr = res->start; st->irq = platform_get_irq(pdev, 0); - if (st->irq <= 0) { - if (!st->irq) - st->irq = -ENXIO; - + if (st->irq < 0) return st->irq; - } st->per_clk = devm_clk_get(&pdev->dev, "adc_clk"); if (IS_ERR(st->per_clk)) -- GitLab From 76f2c491a0cae850ad7413e89f62673e6ef90a97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 19:53:33 +0100 Subject: [PATCH 0860/5631] iio: frequency: admv1013: Benefit from devm_clk_get_enabled() to simplify MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make use of devm_clk_get_enabled() to replace some code that effectively open codes this new function. To retain ordering move the request to a place that is executed later. This way the time of enable keeps the same. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230313185333.2776785-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jonathan Cameron --- drivers/iio/frequency/admv1013.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index ed8167271358..9bf8337806fc 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -490,11 +490,6 @@ static int admv1013_init(struct admv1013_state *st) st->input_mode); } -static void admv1013_clk_disable(void *data) -{ - clk_disable_unprepare(data); -} - static void admv1013_reg_disable(void *data) { regulator_disable(data); @@ -559,11 +554,6 @@ static int admv1013_properties_parse(struct admv1013_state *st) return dev_err_probe(&spi->dev, PTR_ERR(st->reg), "failed to get the common-mode voltage\n"); - st->clkin = devm_clk_get(&spi->dev, "lo_in"); - if (IS_ERR(st->clkin)) - return dev_err_probe(&spi->dev, PTR_ERR(st->clkin), - "failed to get the LO input clock\n"); - return 0; } @@ -601,13 +591,10 @@ static int admv1013_probe(struct spi_device *spi) if (ret) return ret; - ret = clk_prepare_enable(st->clkin); - if (ret) - return ret; - - ret = devm_add_action_or_reset(&spi->dev, admv1013_clk_disable, st->clkin); - if (ret) - return ret; + st->clkin = devm_clk_get_enabled(&spi->dev, "lo_in"); + if (IS_ERR(st->clkin)) + return dev_err_probe(&spi->dev, PTR_ERR(st->clkin), + "failed to get the LO input clock\n"); st->nb.notifier_call = admv1013_freq_change; ret = devm_clk_notifier_register(&spi->dev, st->clkin, &st->nb); -- GitLab From 87a1ff66a0e57d9022665d24793f31fc54de182d Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sat, 11 Mar 2023 09:02:18 -0500 Subject: [PATCH 0861/5631] iio: dac: cio-dac: Migrate to the regmap API The regmap API supports IO port accessors so we can take advantage of regmap abstractions rather than handling access to the device registers directly in the driver. Includes trivial header inclusion tidy up. Suggested-by: Andy Shevchenko Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/20230311140218.74920-1-william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/dac/Kconfig | 1 + drivers/iio/dac/cio-dac.c | 66 ++++++++++++++++++++++++++------------- 2 files changed, 46 insertions(+), 21 deletions(-) diff --git a/drivers/iio/dac/Kconfig b/drivers/iio/dac/Kconfig index d3f90cf86143..3acd9c3f388e 100644 --- a/drivers/iio/dac/Kconfig +++ b/drivers/iio/dac/Kconfig @@ -277,6 +277,7 @@ config CIO_DAC tristate "Measurement Computing CIO-DAC IIO driver" depends on X86 && (ISA_BUS || PC104) select ISA_BUS_API + select REGMAP_MMIO help Say yes here to build support for the Measurement Computing CIO-DAC analog output device family (CIO-DAC16, CIO-DAC08, PC104-DAC06). The diff --git a/drivers/iio/dac/cio-dac.c b/drivers/iio/dac/cio-dac.c index bb67d3340c9f..e10c26dd7cce 100644 --- a/drivers/iio/dac/cio-dac.c +++ b/drivers/iio/dac/cio-dac.c @@ -6,16 +6,15 @@ * This driver supports the following Measurement Computing devices: CIO-DAC16, * CIO-DAC08, and PC104-DAC06. */ -#include +#include #include -#include +#include #include #include -#include -#include #include #include #include +#include #include #define CIO_DAC_NUM_CHAN 16 @@ -35,25 +34,51 @@ static unsigned int num_cio_dac; module_param_hw_array(base, uint, ioport, &num_cio_dac, 0); MODULE_PARM_DESC(base, "Measurement Computing CIO-DAC base addresses"); +#define CIO_DAC_BASE 0x00 +#define CIO_DAC_CHANNEL_STRIDE 2 + +static bool cio_dac_precious_reg(struct device *dev, unsigned int reg) +{ + /* + * All registers are considered precious; if the XFER jumper is set on + * the device, then no update occurs until a DAC register is read. + */ + return true; +} + +static const struct regmap_config cio_dac_regmap_config = { + .reg_bits = 16, + .reg_stride = 2, + .val_bits = 16, + .io_port = true, + .max_register = 0x1F, + .precious_reg = cio_dac_precious_reg, +}; + /** * struct cio_dac_iio - IIO device private data structure - * @chan_out_states: channels' output states - * @base: base memory address of the DAC device + * @map: Regmap for the device */ struct cio_dac_iio { - int chan_out_states[CIO_DAC_NUM_CHAN]; - u16 __iomem *base; + struct regmap *map; }; static int cio_dac_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { struct cio_dac_iio *const priv = iio_priv(indio_dev); + const unsigned int offset = chan->channel * CIO_DAC_CHANNEL_STRIDE; + int err; + unsigned int dac_val; if (mask != IIO_CHAN_INFO_RAW) return -EINVAL; - *val = priv->chan_out_states[chan->channel]; + err = regmap_read(priv->map, CIO_DAC_BASE + offset, &dac_val); + if (err) + return err; + + *val = dac_val; return IIO_VAL_INT; } @@ -62,6 +87,7 @@ static int cio_dac_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, int val2, long mask) { struct cio_dac_iio *const priv = iio_priv(indio_dev); + const unsigned int offset = chan->channel * CIO_DAC_CHANNEL_STRIDE; if (mask != IIO_CHAN_INFO_RAW) return -EINVAL; @@ -70,10 +96,7 @@ static int cio_dac_write_raw(struct iio_dev *indio_dev, if ((unsigned int)val > 65535) return -EINVAL; - priv->chan_out_states[chan->channel] = val; - iowrite16(val, priv->base + chan->channel); - - return 0; + return regmap_write(priv->map, CIO_DAC_BASE + offset, val); } static const struct iio_info cio_dac_info = { @@ -92,7 +115,7 @@ static int cio_dac_probe(struct device *dev, unsigned int id) { struct iio_dev *indio_dev; struct cio_dac_iio *priv; - unsigned int i; + void __iomem *regs; indio_dev = devm_iio_device_alloc(dev, sizeof(*priv)); if (!indio_dev) @@ -105,21 +128,22 @@ static int cio_dac_probe(struct device *dev, unsigned int id) return -EBUSY; } - priv = iio_priv(indio_dev); - priv->base = devm_ioport_map(dev, base[id], CIO_DAC_EXTENT); - if (!priv->base) + regs = devm_ioport_map(dev, base[id], CIO_DAC_EXTENT); + if (!regs) return -ENOMEM; + priv = iio_priv(indio_dev); + priv->map = devm_regmap_init_mmio(dev, regs, &cio_dac_regmap_config); + if (IS_ERR(priv->map)) + return dev_err_probe(dev, PTR_ERR(priv->map), + "Unable to initialize register map\n"); + indio_dev->info = &cio_dac_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = cio_dac_channels; indio_dev->num_channels = CIO_DAC_NUM_CHAN; indio_dev->name = dev_name(dev); - /* initialize DAC outputs to 0V */ - for (i = 0; i < CIO_DAC_NUM_CHAN; i++) - iowrite16(0, priv->base + i); - return devm_iio_device_register(dev, indio_dev); } -- GitLab From d50b3c73f1ac20dabc53dc6e9d64ce9c79a331eb Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 7 Mar 2023 12:51:27 +0300 Subject: [PATCH 0862/5631] RDMA/mlx4: Prevent shift wrapping in set_user_sq_size() The ucmd->log_sq_bb_count variable is controlled by the user so this shift can wrap. Fix it by using check_shl_overflow() in the same way that it was done in commit 515f60004ed9 ("RDMA/hns: Prevent undefined behavior in hns_roce_set_user_sq_size()"). Fixes: 839041329fd3 ("IB/mlx4: Sanity check userspace send queue sizes") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/a8dfbd1d-c019-4556-930b-bab1ded73b10@kili.mountain Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx4/qp.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 884825b2e5f7..456656617c33 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -447,9 +447,13 @@ static int set_user_sq_size(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, struct mlx4_ib_create_qp *ucmd) { + u32 cnt; + /* Sanity check SQ size before proceeding */ - if ((1 << ucmd->log_sq_bb_count) > dev->dev->caps.max_wqes || - ucmd->log_sq_stride > + if (check_shl_overflow(1, ucmd->log_sq_bb_count, &cnt) || + cnt > dev->dev->caps.max_wqes) + return -EINVAL; + if (ucmd->log_sq_stride > ilog2(roundup_pow_of_two(dev->dev->caps.max_sq_desc_sz)) || ucmd->log_sq_stride < MLX4_IB_MIN_SQ_STRIDE) return -EINVAL; -- GitLab From 6ea0c2de314fbaed8e10526c2284e992d145171d Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Tue, 7 Mar 2023 09:15:31 -0800 Subject: [PATCH 0863/5631] RDMA/qib: Remove deprecated kmap() call kmap() has been deprecated in favor of the kmap_local_page() call. kmap_local_page() is thread local. In the sdma coalesce case the page allocated is potentially free'ed in a different context through qib_sdma_get_complete() -> qib_user_sdma_make_progress(). The use of kmap_local_page() is inappropriate in this call path. However, the page is allocated using GFP_KERNEL and will never be from highmem. Remove the use of kmap calls and use page_address() in this case. Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20230217-kmap-qib-v1-1-e5a6fde167e0@intel.com Acked-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/qib/qib_user_sdma.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c index 9fe03d6ffac1..336eb15a721f 100644 --- a/drivers/infiniband/hw/qib/qib_user_sdma.c +++ b/drivers/infiniband/hw/qib/qib_user_sdma.c @@ -320,7 +320,6 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd, unpin_user_page(page); } else { /* coalesce case */ - kunmap(page); __free_page(page); } ret = -ENOMEM; @@ -572,7 +571,7 @@ static int qib_user_sdma_coalesce(const struct qib_devdata *dd, goto done; } - mpage = kmap(page); + mpage = page_address(page); mpage_save = mpage; for (i = 0; i < niov; i++) { int cfur; @@ -581,7 +580,7 @@ static int qib_user_sdma_coalesce(const struct qib_devdata *dd, iov[i].iov_base, iov[i].iov_len); if (cfur) { ret = -EFAULT; - goto free_unmap; + goto page_free; } mpage += iov[i].iov_len; @@ -592,8 +591,7 @@ static int qib_user_sdma_coalesce(const struct qib_devdata *dd, page, 0, 0, len, mpage_save); goto done; -free_unmap: - kunmap(page); +page_free: __free_page(page); done: return ret; @@ -627,9 +625,6 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev, pkt->addr[i].dma_length, DMA_TO_DEVICE); - if (pkt->addr[i].kvaddr) - kunmap(pkt->addr[i].page); - if (pkt->addr[i].put_page) unpin_user_page(pkt->addr[i].page); else -- GitLab From 5a711e580704ac12f223fcd69a8239ccd320e075 Mon Sep 17 00:00:00 2001 From: Krzysztof Czurylo Date: Wed, 15 Mar 2023 09:53:02 -0500 Subject: [PATCH 0864/5631] RDMA/irdma: Refactor HW statistics Refactor HW statistics which, - Unifies HW statistics support for all HW generations. - Unifies support of 32- and 64-bit counters. - Removes duplicated code and simplifies implementation. - Fixes roll-over handling. - Removes unneeded last_hw_stats. With new implementation, there is no separate handling and no separate arrays for 32- and 64-bit counters (offsets, regs, values). Instead, there is a HW stats map array for each HW revision, which defines HW-specific width and location of each counter in the statistics buffer. Once the statistics are gathered (either via CQP op, or by reading HW registers), counter values are extracted from the statistics buffer using the stats map and the delta between the last and new values is computed. Finally, the counter values in rdma_hw_stats are incremented by those deltas. From the OS perspective, all the counters are 64-bit and their order in rdma_hw_stats->value[] array, as well as in irdma_hw_stat_names[], is the same for all HW gens. New statistics should always be added at the end. Signed-off-by: Krzysztof Czurylo Signed-off-by: Youvaraj Sagar Signed-off-by: Shiraz Saleem Link: https://lore.kernel.org/r/20230315145305.955-2-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/ctrl.c | 324 ++++++++---------------- drivers/infiniband/hw/irdma/defs.h | 9 +- drivers/infiniband/hw/irdma/i40iw_hw.c | 60 ++++- drivers/infiniband/hw/irdma/icrdma_hw.c | 51 ++++ drivers/infiniband/hw/irdma/irdma.h | 1 + drivers/infiniband/hw/irdma/protos.h | 8 +- drivers/infiniband/hw/irdma/type.h | 166 +++++------- drivers/infiniband/hw/irdma/utils.c | 172 ++----------- drivers/infiniband/hw/irdma/verbs.c | 151 +++++------ 9 files changed, 362 insertions(+), 580 deletions(-) diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index a41e0d21143a..d88c9184007e 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -1867,8 +1867,6 @@ void irdma_sc_vsi_init(struct irdma_sc_vsi *vsi, vsi->mtu = info->params->mtu; vsi->exception_lan_q = info->exception_lan_q; vsi->vsi_idx = info->pf_data_vsi_num; - if (vsi->dev->hw_attrs.uk_attrs.hw_rev == IRDMA_GEN_1) - vsi->fcn_id = info->dev->hmc_fn_id; irdma_set_qos_info(vsi, info->params); for (i = 0; i < IRDMA_MAX_USER_PRIORITY; i++) { @@ -1887,32 +1885,56 @@ void irdma_sc_vsi_init(struct irdma_sc_vsi *vsi, } /** - * irdma_get_fcn_id - Return the function id + * irdma_get_stats_idx - Return stats index * @vsi: pointer to the vsi */ -static u8 irdma_get_fcn_id(struct irdma_sc_vsi *vsi) +static u8 irdma_get_stats_idx(struct irdma_sc_vsi *vsi) { struct irdma_stats_inst_info stats_info = {}; struct irdma_sc_dev *dev = vsi->dev; - u8 fcn_id = IRDMA_INVALID_FCN_ID; - u8 start_idx, max_stats, i; + u8 i; - if (dev->hw_attrs.uk_attrs.hw_rev != IRDMA_GEN_1) { + if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) { if (!irdma_cqp_stats_inst_cmd(vsi, IRDMA_OP_STATS_ALLOCATE, &stats_info)) return stats_info.stats_idx; } - start_idx = 1; - max_stats = 16; - for (i = start_idx; i < max_stats; i++) - if (!dev->fcn_id_array[i]) { - fcn_id = i; - dev->fcn_id_array[i] = true; - break; + for (i = 0; i < IRDMA_MAX_STATS_COUNT_GEN_1; i++) { + if (!dev->stats_idx_array[i]) { + dev->stats_idx_array[i] = true; + return i; } + } - return fcn_id; + return IRDMA_INVALID_STATS_IDX; +} + +/** + * irdma_hw_stats_init_gen1 - Initialize stat reg table used for gen1 + * @vsi: vsi structure where hw_regs are set + * + * Populate the HW stats table + */ +static void irdma_hw_stats_init_gen1(struct irdma_sc_vsi *vsi) +{ + struct irdma_sc_dev *dev = vsi->dev; + const struct irdma_hw_stat_map *map; + u64 *stat_reg = vsi->hw_stats_regs; + u64 *regs = dev->hw_stats_regs; + u16 i, stats_reg_set = vsi->stats_idx; + + map = dev->hw_stats_map; + + /* First 4 stat instances are reserved for port level statistics. */ + stats_reg_set += vsi->stats_inst_alloc ? IRDMA_FIRST_NON_PF_STAT : 0; + + for (i = 0; i < dev->hw_attrs.max_stat_idx; i++) { + if (map[i].bitmask <= IRDMA_MAX_STATS_32) + stat_reg[i] = regs[i] + stats_reg_set * sizeof(u32); + else + stat_reg[i] = regs[i] + stats_reg_set * sizeof(u64); + } } /** @@ -1923,7 +1945,6 @@ static u8 irdma_get_fcn_id(struct irdma_sc_vsi *vsi) int irdma_vsi_stats_init(struct irdma_sc_vsi *vsi, struct irdma_vsi_stats_info *info) { - u8 fcn_id = info->fcn_id; struct irdma_dma_mem *stats_buff_mem; vsi->pestat = info->pestat; @@ -1944,26 +1965,24 @@ int irdma_vsi_stats_init(struct irdma_sc_vsi *vsi, IRDMA_GATHER_STATS_BUF_SIZE); irdma_hw_stats_start_timer(vsi); - if (info->alloc_fcn_id) - fcn_id = irdma_get_fcn_id(vsi); - if (fcn_id == IRDMA_INVALID_FCN_ID) - goto stats_error; - - vsi->stats_fcn_id_alloc = info->alloc_fcn_id; - vsi->fcn_id = fcn_id; - if (info->alloc_fcn_id) { - vsi->pestat->gather_info.use_stats_inst = true; - vsi->pestat->gather_info.stats_inst_index = fcn_id; - } - return 0; + /* when stat allocation is not required default to fcn_id. */ + vsi->stats_idx = info->fcn_id; + if (info->alloc_stats_inst) { + u8 stats_idx = irdma_get_stats_idx(vsi); -stats_error: - dma_free_coherent(vsi->pestat->hw->device, stats_buff_mem->size, - stats_buff_mem->va, stats_buff_mem->pa); - stats_buff_mem->va = NULL; + if (stats_idx != IRDMA_INVALID_STATS_IDX) { + vsi->stats_inst_alloc = true; + vsi->stats_idx = stats_idx; + vsi->pestat->gather_info.use_stats_inst = true; + vsi->pestat->gather_info.stats_inst_index = stats_idx; + } + } + + if (vsi->dev->hw_attrs.uk_attrs.hw_rev == IRDMA_GEN_1) + irdma_hw_stats_init_gen1(vsi); - return -EIO; + return 0; } /** @@ -1973,19 +1992,19 @@ int irdma_vsi_stats_init(struct irdma_sc_vsi *vsi, void irdma_vsi_stats_free(struct irdma_sc_vsi *vsi) { struct irdma_stats_inst_info stats_info = {}; - u8 fcn_id = vsi->fcn_id; struct irdma_sc_dev *dev = vsi->dev; + u8 stats_idx = vsi->stats_idx; - if (dev->hw_attrs.uk_attrs.hw_rev != IRDMA_GEN_1) { - if (vsi->stats_fcn_id_alloc) { - stats_info.stats_idx = vsi->fcn_id; + if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) { + if (vsi->stats_inst_alloc) { + stats_info.stats_idx = vsi->stats_idx; irdma_cqp_stats_inst_cmd(vsi, IRDMA_OP_STATS_FREE, &stats_info); } } else { - if (vsi->stats_fcn_id_alloc && - fcn_id < vsi->dev->hw_attrs.max_stat_inst) - vsi->dev->fcn_id_array[fcn_id] = false; + if (vsi->stats_inst_alloc && + stats_idx < vsi->dev->hw_attrs.max_stat_inst) + vsi->dev->stats_idx_array[stats_idx] = false; } if (!vsi->pestat) @@ -5297,7 +5316,8 @@ void sc_vsi_update_stats(struct irdma_sc_vsi *vsi) gather_stats = vsi->pestat->gather_info.gather_stats_va; last_gather_stats = vsi->pestat->gather_info.last_gather_stats_va; irdma_update_stats(&vsi->pestat->hw_stats, gather_stats, - last_gather_stats); + last_gather_stats, vsi->dev->hw_stats_map, + vsi->dev->hw_attrs.max_stat_idx); } /** @@ -5404,186 +5424,62 @@ int irdma_sc_dev_init(enum irdma_vers ver, struct irdma_sc_dev *dev, return ret_code; } +/** + * irdma_stat_val - Extract HW counter value from statistics buffer + * @stats_val: pointer to statistics buffer + * @byteoff: byte offset of counter value in the buffer (8B-aligned) + * @bitoff: bit offset of counter value within 8B entry + * @bitmask: maximum counter value (e.g. 0xffffff for 24-bit counter) + */ +static inline u64 irdma_stat_val(const u64 *stats_val, u16 byteoff, u8 bitoff, + u64 bitmask) +{ + u16 idx = byteoff / sizeof(*stats_val); + + return (stats_val[idx] >> bitoff) & bitmask; +} + +/** + * irdma_stat_delta - Calculate counter delta + * @new_val: updated counter value + * @old_val: last counter value + * @max_val: maximum counter value (e.g. 0xffffff for 24-bit counter) + */ +static inline u64 irdma_stat_delta(u64 new_val, u64 old_val, u64 max_val) +{ + if (new_val >= old_val) + return new_val - old_val; + + /* roll-over case */ + return max_val - old_val + new_val + 1; +} + /** * irdma_update_stats - Update statistics * @hw_stats: hw_stats instance to update * @gather_stats: updated stat counters * @last_gather_stats: last stat counters + * @map: HW stat map (hw_stats => gather_stats) + * @max_stat_idx: number of HW stats */ void irdma_update_stats(struct irdma_dev_hw_stats *hw_stats, struct irdma_gather_stats *gather_stats, - struct irdma_gather_stats *last_gather_stats) -{ - u64 *stats_val = hw_stats->stats_val_32; - - stats_val[IRDMA_HW_STAT_INDEX_RXVLANERR] += - IRDMA_STATS_DELTA(gather_stats->rxvlanerr, - last_gather_stats->rxvlanerr, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP4RXDISCARD] += - IRDMA_STATS_DELTA(gather_stats->ip4rxdiscard, - last_gather_stats->ip4rxdiscard, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP4RXTRUNC] += - IRDMA_STATS_DELTA(gather_stats->ip4rxtrunc, - last_gather_stats->ip4rxtrunc, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP4TXNOROUTE] += - IRDMA_STATS_DELTA(gather_stats->ip4txnoroute, - last_gather_stats->ip4txnoroute, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXDISCARD] += - IRDMA_STATS_DELTA(gather_stats->ip6rxdiscard, - last_gather_stats->ip6rxdiscard, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXTRUNC] += - IRDMA_STATS_DELTA(gather_stats->ip6rxtrunc, - last_gather_stats->ip6rxtrunc, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_IP6TXNOROUTE] += - IRDMA_STATS_DELTA(gather_stats->ip6txnoroute, - last_gather_stats->ip6txnoroute, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_TCPRTXSEG] += - IRDMA_STATS_DELTA(gather_stats->tcprtxseg, - last_gather_stats->tcprtxseg, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_TCPRXOPTERR] += - IRDMA_STATS_DELTA(gather_stats->tcprxopterr, - last_gather_stats->tcprxopterr, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_TCPRXPROTOERR] += - IRDMA_STATS_DELTA(gather_stats->tcprxprotoerr, - last_gather_stats->tcprxprotoerr, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED] += - IRDMA_STATS_DELTA(gather_stats->rxrpcnphandled, - last_gather_stats->rxrpcnphandled, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED] += - IRDMA_STATS_DELTA(gather_stats->rxrpcnpignored, - last_gather_stats->rxrpcnpignored, - IRDMA_MAX_STATS_32); - stats_val[IRDMA_HW_STAT_INDEX_TXNPCNPSENT] += - IRDMA_STATS_DELTA(gather_stats->txnpcnpsent, - last_gather_stats->txnpcnpsent, - IRDMA_MAX_STATS_32); - stats_val = hw_stats->stats_val_64; - stats_val[IRDMA_HW_STAT_INDEX_IP4RXOCTS] += - IRDMA_STATS_DELTA(gather_stats->ip4rxocts, - last_gather_stats->ip4rxocts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4RXPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip4rxpkts, - last_gather_stats->ip4rxpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4RXFRAGS] += - IRDMA_STATS_DELTA(gather_stats->ip4txfrag, - last_gather_stats->ip4txfrag, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4RXMCPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip4rxmcpkts, - last_gather_stats->ip4rxmcpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4TXOCTS] += - IRDMA_STATS_DELTA(gather_stats->ip4txocts, - last_gather_stats->ip4txocts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4TXPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip4txpkts, - last_gather_stats->ip4txpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4TXFRAGS] += - IRDMA_STATS_DELTA(gather_stats->ip4txfrag, - last_gather_stats->ip4txfrag, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP4TXMCPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip4txmcpkts, - last_gather_stats->ip4txmcpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXOCTS] += - IRDMA_STATS_DELTA(gather_stats->ip6rxocts, - last_gather_stats->ip6rxocts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip6rxpkts, - last_gather_stats->ip6rxpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXFRAGS] += - IRDMA_STATS_DELTA(gather_stats->ip6txfrags, - last_gather_stats->ip6txfrags, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6RXMCPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip6rxmcpkts, - last_gather_stats->ip6rxmcpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6TXOCTS] += - IRDMA_STATS_DELTA(gather_stats->ip6txocts, - last_gather_stats->ip6txocts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6TXPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip6txpkts, - last_gather_stats->ip6txpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6TXFRAGS] += - IRDMA_STATS_DELTA(gather_stats->ip6txfrags, - last_gather_stats->ip6txfrags, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_IP6TXMCPKTS] += - IRDMA_STATS_DELTA(gather_stats->ip6txmcpkts, - last_gather_stats->ip6txmcpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_TCPRXSEGS] += - IRDMA_STATS_DELTA(gather_stats->tcprxsegs, - last_gather_stats->tcprxsegs, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_TCPTXSEG] += - IRDMA_STATS_DELTA(gather_stats->tcptxsegs, - last_gather_stats->tcptxsegs, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMARXRDS] += - IRDMA_STATS_DELTA(gather_stats->rdmarxrds, - last_gather_stats->rdmarxrds, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMARXSNDS] += - IRDMA_STATS_DELTA(gather_stats->rdmarxsnds, - last_gather_stats->rdmarxsnds, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMARXWRS] += - IRDMA_STATS_DELTA(gather_stats->rdmarxwrs, - last_gather_stats->rdmarxwrs, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMATXRDS] += - IRDMA_STATS_DELTA(gather_stats->rdmatxrds, - last_gather_stats->rdmatxrds, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMATXSNDS] += - IRDMA_STATS_DELTA(gather_stats->rdmatxsnds, - last_gather_stats->rdmatxsnds, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMATXWRS] += - IRDMA_STATS_DELTA(gather_stats->rdmatxwrs, - last_gather_stats->rdmatxwrs, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMAVBND] += - IRDMA_STATS_DELTA(gather_stats->rdmavbn, - last_gather_stats->rdmavbn, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RDMAVINV] += - IRDMA_STATS_DELTA(gather_stats->rdmavinv, - last_gather_stats->rdmavinv, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_UDPRXPKTS] += - IRDMA_STATS_DELTA(gather_stats->udprxpkts, - last_gather_stats->udprxpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_UDPTXPKTS] += - IRDMA_STATS_DELTA(gather_stats->udptxpkts, - last_gather_stats->udptxpkts, - IRDMA_MAX_STATS_48); - stats_val[IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS] += - IRDMA_STATS_DELTA(gather_stats->rxnpecnmrkpkts, - last_gather_stats->rxnpecnmrkpkts, - IRDMA_MAX_STATS_48); + struct irdma_gather_stats *last_gather_stats, + const struct irdma_hw_stat_map *map, u16 max_stat_idx) +{ + u64 *stats_val = hw_stats->stats_val; + u16 i; + + for (i = 0; i < max_stat_idx; i++) { + u64 new_val = irdma_stat_val(gather_stats->val, map[i].byteoff, + map[i].bitoff, map[i].bitmask); + u64 last_val = irdma_stat_val(last_gather_stats->val, + map[i].byteoff, map[i].bitoff, + map[i].bitmask); + + stats_val[i] += + irdma_stat_delta(new_val, last_val, map[i].bitmask); + } + memcpy(last_gather_stats, gather_stats, sizeof(*last_gather_stats)); } diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h index c1906cab5c8a..6014b9d06a9b 100644 --- a/drivers/infiniband/hw/irdma/defs.h +++ b/drivers/infiniband/hw/irdma/defs.h @@ -36,6 +36,7 @@ enum irdma_protocol_used { #define IRDMA_QP_STATE_ERROR 6 #define IRDMA_MAX_TRAFFIC_CLASS 8 +#define IRDMA_MAX_STATS_COUNT_GEN_1 12 #define IRDMA_MAX_USER_PRIORITY 8 #define IRDMA_MAX_APPS 8 #define IRDMA_MAX_STATS_COUNT 128 @@ -365,9 +366,11 @@ enum irdma_cqp_op_type { #define FLD_RS_32(dev, val, field) \ ((u64)((val) & (dev)->hw_masks[field ## _M]) >> (dev)->hw_shifts[field ## _S]) -#define IRDMA_STATS_DELTA(a, b, c) ((a) >= (b) ? (a) - (b) : (a) + (c) - (b)) -#define IRDMA_MAX_STATS_32 0xFFFFFFFFULL -#define IRDMA_MAX_STATS_48 0xFFFFFFFFFFFFULL +#define IRDMA_MAX_STATS_24 0xffffffULL +#define IRDMA_MAX_STATS_32 0xffffffffULL +#define IRDMA_MAX_STATS_48 0xffffffffffffULL +#define IRDMA_MAX_STATS_56 0xffffffffffffffULL +#define IRDMA_MAX_STATS_64 0xffffffffffffffffULL #define IRDMA_MAX_CQ_READ_THRESH 0x3FFFF #define IRDMA_CQPSQ_QHASH_VLANID GENMASK_ULL(43, 32) diff --git a/drivers/infiniband/hw/irdma/i40iw_hw.c b/drivers/infiniband/hw/irdma/i40iw_hw.c index 50299f58b6b3..37a40fb4d0d7 100644 --- a/drivers/infiniband/hw/irdma/i40iw_hw.c +++ b/drivers/infiniband/hw/irdma/i40iw_hw.c @@ -32,7 +32,7 @@ static u32 i40iw_regs[IRDMA_MAX_REGS] = { 0xffffffff /* PFINT_RATEN not used in FPK */ }; -static u32 i40iw_stat_offsets_32[IRDMA_HW_STAT_INDEX_MAX_32] = { +static u32 i40iw_stat_offsets[] = { I40E_GLPES_PFIP4RXDISCARD(0), I40E_GLPES_PFIP4RXTRUNC(0), I40E_GLPES_PFIP4TXNOROUTE(0), @@ -42,10 +42,8 @@ static u32 i40iw_stat_offsets_32[IRDMA_HW_STAT_INDEX_MAX_32] = { I40E_GLPES_PFTCPRTXSEG(0), I40E_GLPES_PFTCPRXOPTERR(0), I40E_GLPES_PFTCPRXPROTOERR(0), - I40E_GLPES_PFRXVLANERR(0) -}; + I40E_GLPES_PFRXVLANERR(0), -static u32 i40iw_stat_offsets_64[IRDMA_HW_STAT_INDEX_MAX_64] = { I40E_GLPES_PFIP4RXOCTSLO(0), I40E_GLPES_PFIP4RXPKTSLO(0), I40E_GLPES_PFIP4RXFRAGSLO(0), @@ -158,6 +156,51 @@ static const struct irdma_irq_ops i40iw_irq_ops = { .irdma_en_irq = i40iw_ena_irq, }; +static const struct irdma_hw_stat_map i40iw_hw_stat_map[] = { + [IRDMA_HW_STAT_INDEX_RXVLANERR] = { 0, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_IP4RXOCTS] = { 8, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXPKTS] = { 16, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXDISCARD] = { 24, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP4RXTRUNC] = { 32, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP4RXFRAGS] = { 40, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXMCPKTS] = { 48, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXOCTS] = { 56, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXPKTS] = { 64, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXDISCARD] = { 72, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP6RXTRUNC] = { 80, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP6RXFRAGS] = { 88, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXMCPKTS] = { 96, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXOCTS] = { 104, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXPKTS] = { 112, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXFRAGS] = { 120, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXMCPKTS] = { 128, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXOCTS] = { 136, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXPKTS] = { 144, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXFRAGS] = { 152, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXMCPKTS] = { 160, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXNOROUTE] = { 168, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_IP6TXNOROUTE] = { 176, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPRXSEGS] = { 184, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_TCPRXOPTERR] = { 192, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPRXPROTOERR] = { 200, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPTXSEG] = { 208, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_TCPRTXSEG] = { 216, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_RDMARXWRS] = { 224, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMARXRDS] = { 232, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMARXSNDS] = { 240, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXWRS] = { 248, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXRDS] = { 256, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXSNDS] = { 264, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMAVBND] = { 272, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMAVINV] = { 280, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXMCOCTS] = { 288, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXMCOCTS] = { 296, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXMCOCTS] = { 304, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXMCOCTS] = { 312, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_UDPRXPKTS] = { 320, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_UDPTXPKTS] = { 328, 0, IRDMA_MAX_STATS_48 }, +}; + void i40iw_init_hw(struct irdma_sc_dev *dev) { int i; @@ -172,11 +215,8 @@ void i40iw_init_hw(struct irdma_sc_dev *dev) dev->hw_regs[i] = (u32 __iomem *)(i40iw_regs[i] + hw_addr); } - for (i = 0; i < IRDMA_HW_STAT_INDEX_MAX_32; ++i) - dev->hw_stats_regs_32[i] = i40iw_stat_offsets_32[i]; - - for (i = 0; i < IRDMA_HW_STAT_INDEX_MAX_64; ++i) - dev->hw_stats_regs_64[i] = i40iw_stat_offsets_64[i]; + for (i = 0; i < IRDMA_HW_STAT_INDEX_MAX_GEN_1; ++i) + dev->hw_stats_regs[i] = i40iw_stat_offsets[i]; dev->hw_attrs.first_hw_vf_fpm_id = I40IW_FIRST_VF_FPM_ID; dev->hw_attrs.max_hw_vf_fpm_id = IRDMA_MAX_VF_FPM_ID; @@ -195,6 +235,7 @@ void i40iw_init_hw(struct irdma_sc_dev *dev) dev->ceq_itr_mask_db = NULL; dev->aeq_itr_mask_db = NULL; dev->irq_ops = &i40iw_irq_ops; + dev->hw_stats_map = i40iw_hw_stat_map; /* Setup the hardware limits, hmc may limit further */ dev->hw_attrs.uk_attrs.max_hw_wq_frags = I40IW_MAX_WQ_FRAGMENT_COUNT; @@ -210,6 +251,7 @@ void i40iw_init_hw(struct irdma_sc_dev *dev) dev->hw_attrs.uk_attrs.max_hw_sq_chunk = I40IW_MAX_QUANTA_PER_WR; dev->hw_attrs.max_hw_pds = I40IW_MAX_PDS; dev->hw_attrs.max_stat_inst = I40IW_MAX_STATS_COUNT; + dev->hw_attrs.max_stat_idx = IRDMA_HW_STAT_INDEX_MAX_GEN_1; dev->hw_attrs.max_hw_outbound_msg_size = I40IW_MAX_OUTBOUND_MSG_SIZE; dev->hw_attrs.max_hw_inbound_msg_size = I40IW_MAX_INBOUND_MSG_SIZE; dev->hw_attrs.max_qp_wr = I40IW_MAX_QP_WRS; diff --git a/drivers/infiniband/hw/irdma/icrdma_hw.c b/drivers/infiniband/hw/irdma/icrdma_hw.c index 5986fd906308..298d14905993 100644 --- a/drivers/infiniband/hw/irdma/icrdma_hw.c +++ b/drivers/infiniband/hw/irdma/icrdma_hw.c @@ -111,6 +111,55 @@ static const struct irdma_irq_ops icrdma_irq_ops = { .irdma_en_irq = icrdma_ena_irq, }; +static const struct irdma_hw_stat_map icrdma_hw_stat_map[] = { + [IRDMA_HW_STAT_INDEX_RXVLANERR] = { 0, 32, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_IP4RXOCTS] = { 8, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXPKTS] = { 16, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXDISCARD] = { 24, 32, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP4RXTRUNC] = { 24, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP4RXFRAGS] = { 32, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXMCOCTS] = { 40, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4RXMCPKTS] = { 48, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXOCTS] = { 56, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXPKTS] = { 64, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXDISCARD] = { 72, 32, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP6RXTRUNC] = { 72, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_IP6RXFRAGS] = { 80, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXMCOCTS] = { 88, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6RXMCPKTS] = { 96, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXOCTS] = { 104, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXPKTS] = { 112, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXFRAGS] = { 120, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXMCOCTS] = { 128, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXMCPKTS] = { 136, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXOCTS] = { 144, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXPKTS] = { 152, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXFRAGS] = { 160, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXMCOCTS] = { 168, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP6TXMCPKTS] = { 176, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_IP4TXNOROUTE] = { 184, 32, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_IP6TXNOROUTE] = { 184, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPRXSEGS] = { 192, 32, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_TCPRXOPTERR] = { 200, 32, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPRXPROTOERR] = { 200, 0, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_TCPTXSEG] = { 208, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_TCPRTXSEG] = { 216, 32, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_UDPRXPKTS] = { 224, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_UDPTXPKTS] = { 232, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMARXWRS] = { 240, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMARXRDS] = { 248, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMARXSNDS] = { 256, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXWRS] = { 264, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXRDS] = { 272, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMATXSNDS] = { 280, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMAVBND] = { 288, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RDMAVINV] = { 296, 0, IRDMA_MAX_STATS_48 }, + [IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS] = { 304, 0, IRDMA_MAX_STATS_56 }, + [IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED] = { 312, 32, IRDMA_MAX_STATS_24 }, + [IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED] = { 312, 0, IRDMA_MAX_STATS_32 }, + [IRDMA_HW_STAT_INDEX_TXNPCNPSENT] = { 320, 0, IRDMA_MAX_STATS_32 }, +}; + void icrdma_init_hw(struct irdma_sc_dev *dev) { int i; @@ -140,9 +189,11 @@ void icrdma_init_hw(struct irdma_sc_dev *dev) dev->cq_ack_db = dev->hw_regs[IRDMA_CQACK]; dev->irq_ops = &icrdma_irq_ops; dev->hw_attrs.page_size_cap = SZ_4K | SZ_2M | SZ_1G; + dev->hw_stats_map = icrdma_hw_stat_map; dev->hw_attrs.max_hw_ird = ICRDMA_MAX_IRD_SIZE; dev->hw_attrs.max_hw_ord = ICRDMA_MAX_ORD_SIZE; dev->hw_attrs.max_stat_inst = ICRDMA_MAX_STATS_COUNT; + dev->hw_attrs.max_stat_idx = IRDMA_HW_STAT_INDEX_MAX_GEN_2; dev->hw_attrs.uk_attrs.max_hw_sq_chunk = IRDMA_MAX_QUANTA_PER_WR; dev->hw_attrs.uk_attrs.feature_flags |= IRDMA_FEATURE_RTS_AE | diff --git a/drivers/infiniband/hw/irdma/irdma.h b/drivers/infiniband/hw/irdma/irdma.h index 4789e85d717b..173e2dc2fc35 100644 --- a/drivers/infiniband/hw/irdma/irdma.h +++ b/drivers/infiniband/hw/irdma/irdma.h @@ -147,6 +147,7 @@ struct irdma_hw_attrs { u32 max_sleep_count; u32 max_cqp_compl_wait_time_ms; u16 max_stat_inst; + u16 max_stat_idx; }; void i40iw_init_hw(struct irdma_sc_dev *dev); diff --git a/drivers/infiniband/hw/irdma/protos.h b/drivers/infiniband/hw/irdma/protos.h index 9b6e919ae2a9..113096b60323 100644 --- a/drivers/infiniband/hw/irdma/protos.h +++ b/drivers/infiniband/hw/irdma/protos.h @@ -28,9 +28,7 @@ int irdma_cqp_gather_stats_cmd(struct irdma_sc_dev *dev, void irdma_cqp_gather_stats_gen1(struct irdma_sc_dev *dev, struct irdma_vsi_pestat *pestat); void irdma_hw_stats_read_all(struct irdma_vsi_pestat *stats, - struct irdma_dev_hw_stats *stats_values, - u64 *hw_stats_regs_32, u64 *hw_stats_regs_64, - u8 hw_rev); + const u64 *hw_stats_regs); int irdma_cqp_ws_node_cmd(struct irdma_sc_dev *dev, u8 cmd, struct irdma_ws_node_info *node_info); int irdma_cqp_ceq_cmd(struct irdma_sc_dev *dev, struct irdma_sc_ceq *sc_ceq, @@ -43,7 +41,9 @@ u16 irdma_alloc_ws_node_id(struct irdma_sc_dev *dev); void irdma_free_ws_node_id(struct irdma_sc_dev *dev, u16 node_id); void irdma_update_stats(struct irdma_dev_hw_stats *hw_stats, struct irdma_gather_stats *gather_stats, - struct irdma_gather_stats *last_gather_stats); + struct irdma_gather_stats *last_gather_stats, + const struct irdma_hw_stat_map *map, u16 max_stat_idx); + /* vsi functions */ int irdma_vsi_stats_init(struct irdma_sc_vsi *vsi, struct irdma_vsi_stats_info *info); diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h index 517d41a1c289..5ee68604e59f 100644 --- a/drivers/infiniband/hw/irdma/type.h +++ b/drivers/infiniband/hw/irdma/type.h @@ -101,7 +101,8 @@ enum irdma_qp_event_type { IRDMA_QP_EVENT_REQ_ERR, }; -enum irdma_hw_stats_index_32b { +enum irdma_hw_stats_index { + /* gen1 - 32-bit */ IRDMA_HW_STAT_INDEX_IP4RXDISCARD = 0, IRDMA_HW_STAT_INDEX_IP4RXTRUNC = 1, IRDMA_HW_STAT_INDEX_IP4TXNOROUTE = 2, @@ -111,50 +112,48 @@ enum irdma_hw_stats_index_32b { IRDMA_HW_STAT_INDEX_TCPRTXSEG = 6, IRDMA_HW_STAT_INDEX_TCPRXOPTERR = 7, IRDMA_HW_STAT_INDEX_TCPRXPROTOERR = 8, - IRDMA_HW_STAT_INDEX_MAX_32_GEN_1 = 9, /* Must be same value as next entry */ IRDMA_HW_STAT_INDEX_RXVLANERR = 9, - IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED = 10, - IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED = 11, - IRDMA_HW_STAT_INDEX_TXNPCNPSENT = 12, - IRDMA_HW_STAT_INDEX_MAX_32, /* Must be last entry */ -}; - -enum irdma_hw_stats_index_64b { - IRDMA_HW_STAT_INDEX_IP4RXOCTS = 0, - IRDMA_HW_STAT_INDEX_IP4RXPKTS = 1, - IRDMA_HW_STAT_INDEX_IP4RXFRAGS = 2, - IRDMA_HW_STAT_INDEX_IP4RXMCPKTS = 3, - IRDMA_HW_STAT_INDEX_IP4TXOCTS = 4, - IRDMA_HW_STAT_INDEX_IP4TXPKTS = 5, - IRDMA_HW_STAT_INDEX_IP4TXFRAGS = 6, - IRDMA_HW_STAT_INDEX_IP4TXMCPKTS = 7, - IRDMA_HW_STAT_INDEX_IP6RXOCTS = 8, - IRDMA_HW_STAT_INDEX_IP6RXPKTS = 9, - IRDMA_HW_STAT_INDEX_IP6RXFRAGS = 10, - IRDMA_HW_STAT_INDEX_IP6RXMCPKTS = 11, - IRDMA_HW_STAT_INDEX_IP6TXOCTS = 12, - IRDMA_HW_STAT_INDEX_IP6TXPKTS = 13, - IRDMA_HW_STAT_INDEX_IP6TXFRAGS = 14, - IRDMA_HW_STAT_INDEX_IP6TXMCPKTS = 15, - IRDMA_HW_STAT_INDEX_TCPRXSEGS = 16, - IRDMA_HW_STAT_INDEX_TCPTXSEG = 17, - IRDMA_HW_STAT_INDEX_RDMARXRDS = 18, - IRDMA_HW_STAT_INDEX_RDMARXSNDS = 19, - IRDMA_HW_STAT_INDEX_RDMARXWRS = 20, - IRDMA_HW_STAT_INDEX_RDMATXRDS = 21, - IRDMA_HW_STAT_INDEX_RDMATXSNDS = 22, - IRDMA_HW_STAT_INDEX_RDMATXWRS = 23, - IRDMA_HW_STAT_INDEX_RDMAVBND = 24, - IRDMA_HW_STAT_INDEX_RDMAVINV = 25, - IRDMA_HW_STAT_INDEX_MAX_64_GEN_1 = 26, /* Must be same value as next entry */ - IRDMA_HW_STAT_INDEX_IP4RXMCOCTS = 26, - IRDMA_HW_STAT_INDEX_IP4TXMCOCTS = 27, - IRDMA_HW_STAT_INDEX_IP6RXMCOCTS = 28, - IRDMA_HW_STAT_INDEX_IP6TXMCOCTS = 29, - IRDMA_HW_STAT_INDEX_UDPRXPKTS = 30, - IRDMA_HW_STAT_INDEX_UDPTXPKTS = 31, - IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS = 32, - IRDMA_HW_STAT_INDEX_MAX_64, /* Must be last entry */ + /* gen1 - 64-bit */ + IRDMA_HW_STAT_INDEX_IP4RXOCTS = 10, + IRDMA_HW_STAT_INDEX_IP4RXPKTS = 11, + IRDMA_HW_STAT_INDEX_IP4RXFRAGS = 12, + IRDMA_HW_STAT_INDEX_IP4RXMCPKTS = 13, + IRDMA_HW_STAT_INDEX_IP4TXOCTS = 14, + IRDMA_HW_STAT_INDEX_IP4TXPKTS = 15, + IRDMA_HW_STAT_INDEX_IP4TXFRAGS = 16, + IRDMA_HW_STAT_INDEX_IP4TXMCPKTS = 17, + IRDMA_HW_STAT_INDEX_IP6RXOCTS = 18, + IRDMA_HW_STAT_INDEX_IP6RXPKTS = 19, + IRDMA_HW_STAT_INDEX_IP6RXFRAGS = 20, + IRDMA_HW_STAT_INDEX_IP6RXMCPKTS = 21, + IRDMA_HW_STAT_INDEX_IP6TXOCTS = 22, + IRDMA_HW_STAT_INDEX_IP6TXPKTS = 23, + IRDMA_HW_STAT_INDEX_IP6TXFRAGS = 24, + IRDMA_HW_STAT_INDEX_IP6TXMCPKTS = 25, + IRDMA_HW_STAT_INDEX_TCPRXSEGS = 26, + IRDMA_HW_STAT_INDEX_TCPTXSEG = 27, + IRDMA_HW_STAT_INDEX_RDMARXRDS = 28, + IRDMA_HW_STAT_INDEX_RDMARXSNDS = 29, + IRDMA_HW_STAT_INDEX_RDMARXWRS = 30, + IRDMA_HW_STAT_INDEX_RDMATXRDS = 31, + IRDMA_HW_STAT_INDEX_RDMATXSNDS = 32, + IRDMA_HW_STAT_INDEX_RDMATXWRS = 33, + IRDMA_HW_STAT_INDEX_RDMAVBND = 34, + IRDMA_HW_STAT_INDEX_RDMAVINV = 35, + IRDMA_HW_STAT_INDEX_IP4RXMCOCTS = 36, + IRDMA_HW_STAT_INDEX_IP4TXMCOCTS = 37, + IRDMA_HW_STAT_INDEX_IP6RXMCOCTS = 38, + IRDMA_HW_STAT_INDEX_IP6TXMCOCTS = 39, + IRDMA_HW_STAT_INDEX_UDPRXPKTS = 40, + IRDMA_HW_STAT_INDEX_UDPTXPKTS = 41, + IRDMA_HW_STAT_INDEX_MAX_GEN_1 = 42, /* Must be same value as next entry */ + /* gen2 - 64-bit */ + IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS = 42, + /* gen2 - 32-bit */ + IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED = 43, + IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED = 44, + IRDMA_HW_STAT_INDEX_TXNPCNPSENT = 45, + IRDMA_HW_STAT_INDEX_MAX_GEN_2 = 46, }; enum irdma_feature_type { @@ -274,65 +273,21 @@ struct irdma_cq_shadow_area { }; struct irdma_dev_hw_stats_offsets { - u32 stats_offset_32[IRDMA_HW_STAT_INDEX_MAX_32]; - u32 stats_offset_64[IRDMA_HW_STAT_INDEX_MAX_64]; + u32 stats_offset[IRDMA_HW_STAT_INDEX_MAX_GEN_1]; }; struct irdma_dev_hw_stats { - u64 stats_val_32[IRDMA_HW_STAT_INDEX_MAX_32]; - u64 stats_val_64[IRDMA_HW_STAT_INDEX_MAX_64]; + u64 stats_val[IRDMA_GATHER_STATS_BUF_SIZE / sizeof(u64)]; }; struct irdma_gather_stats { - u32 rsvd1; - u32 rxvlanerr; - u64 ip4rxocts; - u64 ip4rxpkts; - u32 ip4rxtrunc; - u32 ip4rxdiscard; - u64 ip4rxfrags; - u64 ip4rxmcocts; - u64 ip4rxmcpkts; - u64 ip6rxocts; - u64 ip6rxpkts; - u32 ip6rxtrunc; - u32 ip6rxdiscard; - u64 ip6rxfrags; - u64 ip6rxmcocts; - u64 ip6rxmcpkts; - u64 ip4txocts; - u64 ip4txpkts; - u64 ip4txfrag; - u64 ip4txmcocts; - u64 ip4txmcpkts; - u64 ip6txocts; - u64 ip6txpkts; - u64 ip6txfrags; - u64 ip6txmcocts; - u64 ip6txmcpkts; - u32 ip6txnoroute; - u32 ip4txnoroute; - u64 tcprxsegs; - u32 tcprxprotoerr; - u32 tcprxopterr; - u64 tcptxsegs; - u32 rsvd2; - u32 tcprtxseg; - u64 udprxpkts; - u64 udptxpkts; - u64 rdmarxwrs; - u64 rdmarxrds; - u64 rdmarxsnds; - u64 rdmatxwrs; - u64 rdmatxrds; - u64 rdmatxsnds; - u64 rdmavbn; - u64 rdmavinv; - u64 rxnpecnmrkpkts; - u32 rxrpcnphandled; - u32 rxrpcnpignored; - u32 txnpcnpsent; - u32 rsvd3[88]; + u64 val[IRDMA_GATHER_STATS_BUF_SIZE / sizeof(u64)]; +}; + +struct irdma_hw_stat_map { + u16 byteoff; + u8 bitoff; + u64 bitmask; }; struct irdma_stats_gather_info { @@ -584,7 +539,7 @@ struct irdma_qos { bool valid; }; -#define IRDMA_INVALID_FCN_ID 0xff +#define IRDMA_INVALID_STATS_IDX 0xff struct irdma_sc_vsi { u16 vsi_idx; struct irdma_sc_dev *dev; @@ -598,11 +553,9 @@ struct irdma_sc_vsi { u32 exception_lan_q; u16 mtu; u16 vm_id; - u8 fcn_id; enum irdma_vm_vf_type vm_vf_type; - bool stats_fcn_id_alloc:1; + bool stats_inst_alloc:1; bool tc_change_pending:1; - struct irdma_qos qos[IRDMA_MAX_USER_PRIORITY]; struct irdma_vsi_pestat *pestat; atomic_t qp_suspend_reqs; int (*register_qset)(struct irdma_sc_vsi *vsi, @@ -611,14 +564,17 @@ struct irdma_sc_vsi { struct irdma_ws_node *tc_node); u8 qos_rel_bw; u8 qos_prio_type; + u8 stats_idx; u8 dscp_map[IIDC_MAX_DSCP_MAPPING]; + struct irdma_qos qos[IRDMA_MAX_USER_PRIORITY]; + u64 hw_stats_regs[IRDMA_HW_STAT_INDEX_MAX_GEN_1]; bool dscp_mode:1; }; struct irdma_sc_dev { struct list_head cqp_cmd_head; /* head of the CQP command list */ spinlock_t cqp_lock; /* protect CQP list access */ - bool fcn_id_array[IRDMA_MAX_STATS_COUNT]; + bool stats_idx_array[IRDMA_MAX_STATS_COUNT_GEN_1]; struct irdma_dma_mem vf_fpm_query_buf[IRDMA_MAX_PE_ENA_VF_COUNT]; u64 fpm_query_buf_pa; u64 fpm_commit_buf_pa; @@ -637,8 +593,8 @@ struct irdma_sc_dev { u32 ceq_itr; /* Interrupt throttle, usecs between interrupts: 0 disabled. 2 - 8160 */ u64 hw_masks[IRDMA_MAX_MASKS]; u64 hw_shifts[IRDMA_MAX_SHIFTS]; - u64 hw_stats_regs_32[IRDMA_HW_STAT_INDEX_MAX_32]; - u64 hw_stats_regs_64[IRDMA_HW_STAT_INDEX_MAX_64]; + const struct irdma_hw_stat_map *hw_stats_map; + u64 hw_stats_regs[IRDMA_HW_STAT_INDEX_MAX_GEN_1]; u64 feature_info[IRDMA_MAX_FEATURES]; u64 cqp_cmd_stats[IRDMA_MAX_CQP_OPS]; struct irdma_hw_attrs hw_attrs; @@ -763,7 +719,7 @@ struct irdma_vsi_init_info { struct irdma_vsi_stats_info { struct irdma_vsi_pestat *pestat; u8 fcn_id; - bool alloc_fcn_id; + bool alloc_stats_inst; }; struct irdma_device_init_info { diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 445e69e86409..0604d5e87958 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -1634,10 +1634,10 @@ static void irdma_hw_stats_timeout(struct timer_list *t) from_timer(pf_devstat, t, stats_timer); struct irdma_sc_vsi *sc_vsi = pf_devstat->vsi; - if (sc_vsi->dev->hw_attrs.uk_attrs.hw_rev == IRDMA_GEN_1) - irdma_cqp_gather_stats_gen1(sc_vsi->dev, sc_vsi->pestat); - else + if (sc_vsi->dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) irdma_cqp_gather_stats_cmd(sc_vsi->dev, sc_vsi->pestat, false); + else + irdma_cqp_gather_stats_gen1(sc_vsi->dev, sc_vsi->pestat); mod_timer(&pf_devstat->stats_timer, jiffies + msecs_to_jiffies(STATS_TIMER_DELAY)); @@ -1686,164 +1686,28 @@ void irdma_cqp_gather_stats_gen1(struct irdma_sc_dev *dev, { struct irdma_gather_stats *gather_stats = pestat->gather_info.gather_stats_va; + const struct irdma_hw_stat_map *map = dev->hw_stats_map; + u16 max_stats_idx = dev->hw_attrs.max_stat_idx; u32 stats_inst_offset_32; u32 stats_inst_offset_64; + u64 new_val; + u16 i; stats_inst_offset_32 = (pestat->gather_info.use_stats_inst) ? - pestat->gather_info.stats_inst_index : - pestat->hw->hmc.hmc_fn_id; + pestat->gather_info.stats_inst_index : + pestat->hw->hmc.hmc_fn_id; stats_inst_offset_32 *= 4; stats_inst_offset_64 = stats_inst_offset_32 * 2; - gather_stats->rxvlanerr = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_RXVLANERR] - + stats_inst_offset_32); - gather_stats->ip4rxdiscard = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP4RXDISCARD] - + stats_inst_offset_32); - gather_stats->ip4rxtrunc = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP4RXTRUNC] - + stats_inst_offset_32); - gather_stats->ip4txnoroute = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP4TXNOROUTE] - + stats_inst_offset_32); - gather_stats->ip6rxdiscard = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP6RXDISCARD] - + stats_inst_offset_32); - gather_stats->ip6rxtrunc = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP6RXTRUNC] - + stats_inst_offset_32); - gather_stats->ip6txnoroute = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_IP6TXNOROUTE] - + stats_inst_offset_32); - gather_stats->tcprtxseg = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_TCPRTXSEG] - + stats_inst_offset_32); - gather_stats->tcprxopterr = - rd32(dev->hw, - dev->hw_stats_regs_32[IRDMA_HW_STAT_INDEX_TCPRXOPTERR] - + stats_inst_offset_32); - - gather_stats->ip4rxocts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4RXOCTS] - + stats_inst_offset_64); - gather_stats->ip4rxpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4RXPKTS] - + stats_inst_offset_64); - gather_stats->ip4txfrag = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4RXFRAGS] - + stats_inst_offset_64); - gather_stats->ip4rxmcpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4RXMCPKTS] - + stats_inst_offset_64); - gather_stats->ip4txocts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4TXOCTS] - + stats_inst_offset_64); - gather_stats->ip4txpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4TXPKTS] - + stats_inst_offset_64); - gather_stats->ip4txfrag = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4TXFRAGS] - + stats_inst_offset_64); - gather_stats->ip4txmcpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP4TXMCPKTS] - + stats_inst_offset_64); - gather_stats->ip6rxocts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6RXOCTS] - + stats_inst_offset_64); - gather_stats->ip6rxpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6RXPKTS] - + stats_inst_offset_64); - gather_stats->ip6txfrags = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6RXFRAGS] - + stats_inst_offset_64); - gather_stats->ip6rxmcpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6RXMCPKTS] - + stats_inst_offset_64); - gather_stats->ip6txocts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6TXOCTS] - + stats_inst_offset_64); - gather_stats->ip6txpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6TXPKTS] - + stats_inst_offset_64); - gather_stats->ip6txfrags = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6TXFRAGS] - + stats_inst_offset_64); - gather_stats->ip6txmcpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_IP6TXMCPKTS] - + stats_inst_offset_64); - gather_stats->tcprxsegs = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_TCPRXSEGS] - + stats_inst_offset_64); - gather_stats->tcptxsegs = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_TCPTXSEG] - + stats_inst_offset_64); - gather_stats->rdmarxrds = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMARXRDS] - + stats_inst_offset_64); - gather_stats->rdmarxsnds = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMARXSNDS] - + stats_inst_offset_64); - gather_stats->rdmarxwrs = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMARXWRS] - + stats_inst_offset_64); - gather_stats->rdmatxrds = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMATXRDS] - + stats_inst_offset_64); - gather_stats->rdmatxsnds = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMATXSNDS] - + stats_inst_offset_64); - gather_stats->rdmatxwrs = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMATXWRS] - + stats_inst_offset_64); - gather_stats->rdmavbn = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMAVBND] - + stats_inst_offset_64); - gather_stats->rdmavinv = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_RDMAVINV] - + stats_inst_offset_64); - gather_stats->udprxpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_UDPRXPKTS] - + stats_inst_offset_64); - gather_stats->udptxpkts = - rd64(dev->hw, - dev->hw_stats_regs_64[IRDMA_HW_STAT_INDEX_UDPTXPKTS] - + stats_inst_offset_64); + for (i = 0; i < max_stats_idx; i++) { + if (map[i].bitmask <= IRDMA_MAX_STATS_32) + new_val = rd32(dev->hw, + dev->hw_stats_regs[i] + stats_inst_offset_32); + else + new_val = rd64(dev->hw, + dev->hw_stats_regs[i] + stats_inst_offset_64); + gather_stats->val[map[i].byteoff / sizeof(u64)] = new_val; + } irdma_process_stats(pestat); } diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 1b2e3e800c9a..ec9f4dfddd88 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3708,89 +3708,59 @@ static int irdma_iw_port_immutable(struct ib_device *ibdev, u32 port_num, return 0; } -static const struct rdma_stat_desc irdma_hw_stat_descs[] = { - /* 32bit names */ - [IRDMA_HW_STAT_INDEX_RXVLANERR].name = "rxVlanErrors", - [IRDMA_HW_STAT_INDEX_IP4RXDISCARD].name = "ip4InDiscards", - [IRDMA_HW_STAT_INDEX_IP4RXTRUNC].name = "ip4InTruncatedPkts", - [IRDMA_HW_STAT_INDEX_IP4TXNOROUTE].name = "ip4OutNoRoutes", - [IRDMA_HW_STAT_INDEX_IP6RXDISCARD].name = "ip6InDiscards", - [IRDMA_HW_STAT_INDEX_IP6RXTRUNC].name = "ip6InTruncatedPkts", - [IRDMA_HW_STAT_INDEX_IP6TXNOROUTE].name = "ip6OutNoRoutes", - [IRDMA_HW_STAT_INDEX_TCPRTXSEG].name = "tcpRetransSegs", - [IRDMA_HW_STAT_INDEX_TCPRXOPTERR].name = "tcpInOptErrors", - [IRDMA_HW_STAT_INDEX_TCPRXPROTOERR].name = "tcpInProtoErrors", - [IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED].name = "cnpHandled", - [IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED].name = "cnpIgnored", - [IRDMA_HW_STAT_INDEX_TXNPCNPSENT].name = "cnpSent", - - /* 64bit names */ - [IRDMA_HW_STAT_INDEX_IP4RXOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4InOctets", - [IRDMA_HW_STAT_INDEX_IP4RXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4InPkts", - [IRDMA_HW_STAT_INDEX_IP4RXFRAGS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4InReasmRqd", - [IRDMA_HW_STAT_INDEX_IP4RXMCOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4InMcastOctets", - [IRDMA_HW_STAT_INDEX_IP4RXMCPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4InMcastPkts", - [IRDMA_HW_STAT_INDEX_IP4TXOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4OutOctets", - [IRDMA_HW_STAT_INDEX_IP4TXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4OutPkts", - [IRDMA_HW_STAT_INDEX_IP4TXFRAGS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4OutSegRqd", - [IRDMA_HW_STAT_INDEX_IP4TXMCOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4OutMcastOctets", - [IRDMA_HW_STAT_INDEX_IP4TXMCPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip4OutMcastPkts", - [IRDMA_HW_STAT_INDEX_IP6RXOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6InOctets", - [IRDMA_HW_STAT_INDEX_IP6RXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6InPkts", - [IRDMA_HW_STAT_INDEX_IP6RXFRAGS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6InReasmRqd", - [IRDMA_HW_STAT_INDEX_IP6RXMCOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6InMcastOctets", - [IRDMA_HW_STAT_INDEX_IP6RXMCPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6InMcastPkts", - [IRDMA_HW_STAT_INDEX_IP6TXOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6OutOctets", - [IRDMA_HW_STAT_INDEX_IP6TXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6OutPkts", - [IRDMA_HW_STAT_INDEX_IP6TXFRAGS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6OutSegRqd", - [IRDMA_HW_STAT_INDEX_IP6TXMCOCTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6OutMcastOctets", - [IRDMA_HW_STAT_INDEX_IP6TXMCPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "ip6OutMcastPkts", - [IRDMA_HW_STAT_INDEX_TCPRXSEGS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "tcpInSegs", - [IRDMA_HW_STAT_INDEX_TCPTXSEG + IRDMA_HW_STAT_INDEX_MAX_32].name = - "tcpOutSegs", - [IRDMA_HW_STAT_INDEX_RDMARXRDS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwInRdmaReads", - [IRDMA_HW_STAT_INDEX_RDMARXSNDS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwInRdmaSends", - [IRDMA_HW_STAT_INDEX_RDMARXWRS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwInRdmaWrites", - [IRDMA_HW_STAT_INDEX_RDMATXRDS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwOutRdmaReads", - [IRDMA_HW_STAT_INDEX_RDMATXSNDS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwOutRdmaSends", - [IRDMA_HW_STAT_INDEX_RDMATXWRS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwOutRdmaWrites", - [IRDMA_HW_STAT_INDEX_RDMAVBND + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwRdmaBnd", - [IRDMA_HW_STAT_INDEX_RDMAVINV + IRDMA_HW_STAT_INDEX_MAX_32].name = - "iwRdmaInv", - [IRDMA_HW_STAT_INDEX_UDPRXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "RxUDP", - [IRDMA_HW_STAT_INDEX_UDPTXPKTS + IRDMA_HW_STAT_INDEX_MAX_32].name = - "TxUDP", - [IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS + IRDMA_HW_STAT_INDEX_MAX_32] - .name = "RxECNMrkd", +static const struct rdma_stat_desc irdma_hw_stat_names[] = { + /* gen1 - 32-bit */ + [IRDMA_HW_STAT_INDEX_IP4RXDISCARD].name = "ip4InDiscards", + [IRDMA_HW_STAT_INDEX_IP4RXTRUNC].name = "ip4InTruncatedPkts", + [IRDMA_HW_STAT_INDEX_IP4TXNOROUTE].name = "ip4OutNoRoutes", + [IRDMA_HW_STAT_INDEX_IP6RXDISCARD].name = "ip6InDiscards", + [IRDMA_HW_STAT_INDEX_IP6RXTRUNC].name = "ip6InTruncatedPkts", + [IRDMA_HW_STAT_INDEX_IP6TXNOROUTE].name = "ip6OutNoRoutes", + [IRDMA_HW_STAT_INDEX_TCPRTXSEG].name = "tcpRetransSegs", + [IRDMA_HW_STAT_INDEX_TCPRXOPTERR].name = "tcpInOptErrors", + [IRDMA_HW_STAT_INDEX_TCPRXPROTOERR].name = "tcpInProtoErrors", + [IRDMA_HW_STAT_INDEX_RXVLANERR].name = "rxVlanErrors", + /* gen1 - 64-bit */ + [IRDMA_HW_STAT_INDEX_IP4RXOCTS].name = "ip4InOctets", + [IRDMA_HW_STAT_INDEX_IP4RXPKTS].name = "ip4InPkts", + [IRDMA_HW_STAT_INDEX_IP4RXFRAGS].name = "ip4InReasmRqd", + [IRDMA_HW_STAT_INDEX_IP4RXMCPKTS].name = "ip4InMcastPkts", + [IRDMA_HW_STAT_INDEX_IP4TXOCTS].name = "ip4OutOctets", + [IRDMA_HW_STAT_INDEX_IP4TXPKTS].name = "ip4OutPkts", + [IRDMA_HW_STAT_INDEX_IP4TXFRAGS].name = "ip4OutSegRqd", + [IRDMA_HW_STAT_INDEX_IP4TXMCPKTS].name = "ip4OutMcastPkts", + [IRDMA_HW_STAT_INDEX_IP6RXOCTS].name = "ip6InOctets", + [IRDMA_HW_STAT_INDEX_IP6RXPKTS].name = "ip6InPkts", + [IRDMA_HW_STAT_INDEX_IP6RXFRAGS].name = "ip6InReasmRqd", + [IRDMA_HW_STAT_INDEX_IP6RXMCPKTS].name = "ip6InMcastPkts", + [IRDMA_HW_STAT_INDEX_IP6TXOCTS].name = "ip6OutOctets", + [IRDMA_HW_STAT_INDEX_IP6TXPKTS].name = "ip6OutPkts", + [IRDMA_HW_STAT_INDEX_IP6TXFRAGS].name = "ip6OutSegRqd", + [IRDMA_HW_STAT_INDEX_IP6TXMCPKTS].name = "ip6OutMcastPkts", + [IRDMA_HW_STAT_INDEX_TCPRXSEGS].name = "tcpInSegs", + [IRDMA_HW_STAT_INDEX_TCPTXSEG].name = "tcpOutSegs", + [IRDMA_HW_STAT_INDEX_RDMARXRDS].name = "iwInRdmaReads", + [IRDMA_HW_STAT_INDEX_RDMARXSNDS].name = "iwInRdmaSends", + [IRDMA_HW_STAT_INDEX_RDMARXWRS].name = "iwInRdmaWrites", + [IRDMA_HW_STAT_INDEX_RDMATXRDS].name = "iwOutRdmaReads", + [IRDMA_HW_STAT_INDEX_RDMATXSNDS].name = "iwOutRdmaSends", + [IRDMA_HW_STAT_INDEX_RDMATXWRS].name = "iwOutRdmaWrites", + [IRDMA_HW_STAT_INDEX_RDMAVBND].name = "iwRdmaBnd", + [IRDMA_HW_STAT_INDEX_RDMAVINV].name = "iwRdmaInv", + + /* gen2 - 32-bit */ + [IRDMA_HW_STAT_INDEX_RXRPCNPHANDLED].name = "cnpHandled", + [IRDMA_HW_STAT_INDEX_RXRPCNPIGNORED].name = "cnpIgnored", + [IRDMA_HW_STAT_INDEX_TXNPCNPSENT].name = "cnpSent", + /* gen2 - 64-bit */ + [IRDMA_HW_STAT_INDEX_IP4RXMCOCTS].name = "ip4InMcastOctets", + [IRDMA_HW_STAT_INDEX_IP4TXMCOCTS].name = "ip4OutMcastOctets", + [IRDMA_HW_STAT_INDEX_IP6RXMCOCTS].name = "ip6InMcastOctets", + [IRDMA_HW_STAT_INDEX_IP6TXMCOCTS].name = "ip6OutMcastOctets", + [IRDMA_HW_STAT_INDEX_UDPRXPKTS].name = "RxUDP", + [IRDMA_HW_STAT_INDEX_UDPTXPKTS].name = "TxUDP", + [IRDMA_HW_STAT_INDEX_RXNPECNMARKEDPKTS].name = "RxECNMrkd", + }; static void irdma_get_dev_fw_str(struct ib_device *dev, char *str) @@ -3810,14 +3780,13 @@ static void irdma_get_dev_fw_str(struct ib_device *dev, char *str) static struct rdma_hw_stats *irdma_alloc_hw_port_stats(struct ib_device *ibdev, u32 port_num) { - int num_counters = IRDMA_HW_STAT_INDEX_MAX_32 + - IRDMA_HW_STAT_INDEX_MAX_64; - unsigned long lifespan = RDMA_HW_STATS_DEFAULT_LIFESPAN; + struct irdma_device *iwdev = to_iwdev(ibdev); + struct irdma_sc_dev *dev = &iwdev->rf->sc_dev; - BUILD_BUG_ON(ARRAY_SIZE(irdma_hw_stat_descs) != - (IRDMA_HW_STAT_INDEX_MAX_32 + IRDMA_HW_STAT_INDEX_MAX_64)); + int num_counters = dev->hw_attrs.max_stat_idx; + unsigned long lifespan = RDMA_HW_STATS_DEFAULT_LIFESPAN; - return rdma_alloc_hw_stats_struct(irdma_hw_stat_descs, num_counters, + return rdma_alloc_hw_stats_struct(irdma_hw_stat_names, num_counters, lifespan); } @@ -3840,7 +3809,7 @@ static int irdma_get_hw_stats(struct ib_device *ibdev, else irdma_cqp_gather_stats_gen1(&iwdev->rf->sc_dev, iwdev->vsi.pestat); - memcpy(&stats->value[0], hw_stats, sizeof(*hw_stats)); + memcpy(&stats->value[0], hw_stats, sizeof(u64) * stats->num_counters); return stats->num_counters; } @@ -4054,7 +4023,7 @@ static int irdma_attach_mcast(struct ib_qp *ibqp, union ib_gid *ibgid, u16 lid) mc_qht_elem->mc_grp_ctx.vlan_id = vlan_id; if (vlan_id < VLAN_N_VID) mc_qht_elem->mc_grp_ctx.vlan_valid = true; - mc_qht_elem->mc_grp_ctx.hmc_fcn_id = iwdev->vsi.fcn_id; + mc_qht_elem->mc_grp_ctx.hmc_fcn_id = iwdev->rf->sc_dev.hmc_fn_id; mc_qht_elem->mc_grp_ctx.qs_handle = iwqp->sc_qp.vsi->qos[iwqp->sc_qp.user_pri].qs_handle; ether_addr_copy(mc_qht_elem->mc_grp_ctx.dest_mac_addr, dmac); -- GitLab From 0219ad5d3afbb59dd029d2d5630123d52c9e0cc6 Mon Sep 17 00:00:00 2001 From: Tatyana Nikolova Date: Wed, 15 Mar 2023 09:53:03 -0500 Subject: [PATCH 0865/5631] RDMA/irdma: Remove a redundant irdma_arp_table() call Remove a redundant function call in irdma_modify_qp_roce, since irdma_arp_table() with IRDMA_ARP_RESOLVE action is called after the if/else ipv check as part of irdma_add_arp(). Signed-off-by: Tatyana Nikolova Signed-off-by: Shiraz Saleem Link: https://lore.kernel.org/r/20230315145305.955-3-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/verbs.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index ec9f4dfddd88..d906f5916a11 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -1226,10 +1226,6 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr, udp_info->ipv4 = false; irdma_copy_ip_ntohl(local_ip, daddr); - udp_info->arp_idx = irdma_arp_table(iwdev->rf, - &local_ip[0], - false, NULL, - IRDMA_ARP_RESOLVE); } else if (av->net_type == RDMA_NETWORK_IPV4) { __be32 saddr = av->sgid_addr.saddr_in.sin_addr.s_addr; __be32 daddr = av->dgid_addr.saddr_in.sin_addr.s_addr; -- GitLab From 99f96b4552330d2b725974b4429fba7986635f43 Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Wed, 15 Mar 2023 09:53:04 -0500 Subject: [PATCH 0866/5631] RDMA/irdma: Change name of interrupts Add more information in interrupt names. Before this patch it was: irdma CEQ CEQ ... Now: irdma-0000:18:00.0-AEQ irdma-0000:18:00.0-CEQ-0 irdma-0000:18:00.0-CEQ-1 ... Signed-off-by: Michal Swiatkowski Suggested-by: Piotr Raczynski Reviewed-by: Shiraz Saleem Signed-off-by: Shiraz Saleem Link: https://lore.kernel.org/r/20230315145305.955-4-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/hw.c | 13 ++++++++++--- drivers/infiniband/hw/irdma/main.h | 3 +++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 2e1e2bad0401..f68353167c94 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -1089,14 +1089,19 @@ static int irdma_cfg_ceq_vector(struct irdma_pci_f *rf, struct irdma_ceq *iwceq, int status; if (rf->msix_shared && !ceq_id) { + snprintf(msix_vec->name, sizeof(msix_vec->name) - 1, + "irdma-%s-AEQCEQ-0", dev_name(&rf->pcidev->dev)); tasklet_setup(&rf->dpc_tasklet, irdma_dpc); status = request_irq(msix_vec->irq, irdma_irq_handler, 0, - "AEQCEQ", rf); + msix_vec->name, rf); } else { + snprintf(msix_vec->name, sizeof(msix_vec->name) - 1, + "irdma-%s-CEQ-%d", + dev_name(&rf->pcidev->dev), ceq_id); tasklet_setup(&iwceq->dpc_tasklet, irdma_ceq_dpc); status = request_irq(msix_vec->irq, irdma_ceq_handler, 0, - "CEQ", iwceq); + msix_vec->name, iwceq); } cpumask_clear(&msix_vec->mask); cpumask_set_cpu(msix_vec->cpu_affinity, &msix_vec->mask); @@ -1125,9 +1130,11 @@ static int irdma_cfg_aeq_vector(struct irdma_pci_f *rf) u32 ret = 0; if (!rf->msix_shared) { + snprintf(msix_vec->name, sizeof(msix_vec->name) - 1, + "irdma-%s-AEQ", dev_name(&rf->pcidev->dev)); tasklet_setup(&rf->dpc_tasklet, irdma_dpc); ret = request_irq(msix_vec->irq, irdma_irq_handler, 0, - "irdma", rf); + msix_vec->name, rf); } if (ret) { ibdev_dbg(&rf->iwdev->ibdev, "ERR: aeq irq config fail\n"); diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 65e966ad3453..def6dd58dcd4 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -115,6 +115,8 @@ extern struct auxiliary_driver i40iw_auxiliary_drv; #define IRDMA_REFLUSH BIT(2) #define IRDMA_FLUSH_WAIT BIT(3) +#define IRDMA_IRQ_NAME_STR_LEN (64) + enum init_completion_state { INVALID_STATE = 0, INITIAL_STATE, @@ -212,6 +214,7 @@ struct irdma_msix_vector { u32 cpu_affinity; u32 ceq_id; cpumask_t mask; + char name[IRDMA_IRQ_NAME_STR_LEN]; }; struct irdma_mc_table_info { -- GitLab From cc8997c94bf37005ded39bb8537549dc85776b88 Mon Sep 17 00:00:00 2001 From: Sindhu Devale Date: Wed, 15 Mar 2023 09:53:05 -0500 Subject: [PATCH 0867/5631] RDMA/irdma: Refactor PBLE functions Refactor PBLE functions using a bit mask to represent the PBLE level desired versus 2 parameters use_pble and lvl_one_only which makes the code confusing. Signed-off-by: Mustafa Ismail Signed-off-by: Sindhu Devale Link: https://lore.kernel.org/r/20230315145305.955-5-shiraz.saleem@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/irdma/pble.c | 16 +++++----- drivers/infiniband/hw/irdma/pble.h | 2 +- drivers/infiniband/hw/irdma/verbs.c | 45 ++++++++++++++--------------- 3 files changed, 31 insertions(+), 32 deletions(-) diff --git a/drivers/infiniband/hw/irdma/pble.c b/drivers/infiniband/hw/irdma/pble.c index cdc0b8a6ed48..c0bef11436b9 100644 --- a/drivers/infiniband/hw/irdma/pble.c +++ b/drivers/infiniband/hw/irdma/pble.c @@ -423,15 +423,15 @@ static int get_lvl1_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, * get_lvl1_lvl2_pble - calls get_lvl1 and get_lvl2 pble routine * @pble_rsrc: pble resources * @palloc: contains all inforamtion regarding pble (idx + pble addr) - * @level1_only: flag for a level 1 PBLE + * @lvl: Bitmask for requested pble level */ static int get_lvl1_lvl2_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, - struct irdma_pble_alloc *palloc, bool level1_only) + struct irdma_pble_alloc *palloc, u8 lvl) { int status = 0; status = get_lvl1_pble(pble_rsrc, palloc); - if (!status || level1_only || palloc->total_cnt <= PBLE_PER_PAGE) + if (!status || lvl == PBLE_LEVEL_1 || palloc->total_cnt <= PBLE_PER_PAGE) return status; status = get_lvl2_pble(pble_rsrc, palloc); @@ -444,11 +444,11 @@ static int get_lvl1_lvl2_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, * @pble_rsrc: pble resources * @palloc: contains all inforamtion regarding pble (idx + pble addr) * @pble_cnt: #of pbles requested - * @level1_only: true if only pble level 1 to acquire + * @lvl: requested pble level mask */ int irdma_get_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, struct irdma_pble_alloc *palloc, u32 pble_cnt, - bool level1_only) + u8 lvl) { int status = 0; int max_sds = 0; @@ -462,7 +462,7 @@ int irdma_get_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, /*check first to see if we can get pble's without acquiring * additional sd's */ - status = get_lvl1_lvl2_pble(pble_rsrc, palloc, level1_only); + status = get_lvl1_lvl2_pble(pble_rsrc, palloc, lvl); if (!status) goto exit; @@ -472,9 +472,9 @@ int irdma_get_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, if (status) break; - status = get_lvl1_lvl2_pble(pble_rsrc, palloc, level1_only); + status = get_lvl1_lvl2_pble(pble_rsrc, palloc, lvl); /* if level1_only, only go through it once */ - if (!status || level1_only) + if (!status || lvl) break; } diff --git a/drivers/infiniband/hw/irdma/pble.h b/drivers/infiniband/hw/irdma/pble.h index 29d295463559..b31b7c5d66fe 100644 --- a/drivers/infiniband/hw/irdma/pble.h +++ b/drivers/infiniband/hw/irdma/pble.h @@ -114,7 +114,7 @@ void irdma_free_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, struct irdma_pble_alloc *palloc); int irdma_get_pble(struct irdma_hmc_pble_rsrc *pble_rsrc, struct irdma_pble_alloc *palloc, u32 pble_cnt, - bool level1_only); + u8 lvl); int irdma_prm_add_pble_mem(struct irdma_pble_prm *pprm, struct irdma_chunk *pchunk); int irdma_prm_get_pbles(struct irdma_pble_prm *pprm, diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index d906f5916a11..ab5cdf782785 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -2325,11 +2325,10 @@ static bool irdma_check_mr_contiguous(struct irdma_pble_alloc *palloc, * irdma_setup_pbles - copy user pg address to pble's * @rf: RDMA PCI function * @iwmr: mr pointer for this memory registration - * @use_pbles: flag if to use pble's - * @lvl_1_only: request only level 1 pble if true + * @lvl: requested pble levels */ static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr, - bool use_pbles, bool lvl_1_only) + u8 lvl) { struct irdma_pbl *iwpbl = &iwmr->iwpbl; struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc; @@ -2338,9 +2337,9 @@ static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr, int status; enum irdma_pble_level level = PBLE_LEVEL_1; - if (use_pbles) { + if (lvl) { status = irdma_get_pble(rf->pble_rsrc, palloc, iwmr->page_cnt, - lvl_1_only); + lvl); if (status) return status; @@ -2355,7 +2354,7 @@ static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr, irdma_copy_user_pgaddrs(iwmr, pbl, level); - if (use_pbles) + if (lvl) iwmr->pgaddrmem[0] = *pbl; return 0; @@ -2366,11 +2365,11 @@ static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr, * @iwdev: irdma device * @req: information for q memory management * @iwpbl: pble struct - * @use_pbles: flag to use pble + * @lvl: pble level mask */ static int irdma_handle_q_mem(struct irdma_device *iwdev, struct irdma_mem_reg_req *req, - struct irdma_pbl *iwpbl, bool use_pbles) + struct irdma_pbl *iwpbl, u8 lvl) { struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc; struct irdma_mr *iwmr = iwpbl->iwmr; @@ -2383,11 +2382,11 @@ static int irdma_handle_q_mem(struct irdma_device *iwdev, bool ret = true; pg_size = iwmr->page_size; - err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles, true); + err = irdma_setup_pbles(iwdev->rf, iwmr, lvl); if (err) return err; - if (use_pbles) + if (lvl) arr = palloc->level1.addr; switch (iwmr->type) { @@ -2396,7 +2395,7 @@ static int irdma_handle_q_mem(struct irdma_device *iwdev, hmc_p = &qpmr->sq_pbl; qpmr->shadow = (dma_addr_t)arr[total]; - if (use_pbles) { + if (lvl) { ret = irdma_check_mem_contiguous(arr, req->sq_pages, pg_size); if (ret) @@ -2421,7 +2420,7 @@ static int irdma_handle_q_mem(struct irdma_device *iwdev, if (!cqmr->split) cqmr->shadow = (dma_addr_t)arr[req->cq_pages]; - if (use_pbles) + if (lvl) ret = irdma_check_mem_contiguous(arr, req->cq_pages, pg_size); @@ -2435,7 +2434,7 @@ static int irdma_handle_q_mem(struct irdma_device *iwdev, err = -EINVAL; } - if (use_pbles && ret) { + if (lvl && ret) { irdma_free_pble(iwdev->rf->pble_rsrc, palloc); iwpbl->pbl_allocated = false; } @@ -2745,17 +2744,17 @@ static int irdma_reg_user_mr_type_mem(struct irdma_mr *iwmr, int access) { struct irdma_device *iwdev = to_iwdev(iwmr->ibmr.device); struct irdma_pbl *iwpbl = &iwmr->iwpbl; - bool use_pbles; u32 stag; + u8 lvl; int err; - use_pbles = iwmr->page_cnt != 1; + lvl = iwmr->page_cnt != 1 ? PBLE_LEVEL_1 | PBLE_LEVEL_2 : PBLE_LEVEL_0; - err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles, false); + err = irdma_setup_pbles(iwdev->rf, iwmr, lvl); if (err) return err; - if (use_pbles) { + if (lvl) { err = irdma_check_mr_contiguous(&iwpbl->pble_alloc, iwmr->page_size); if (err) { @@ -2839,17 +2838,17 @@ static int irdma_reg_user_mr_type_qp(struct irdma_mem_reg_req req, struct irdma_pbl *iwpbl = &iwmr->iwpbl; struct irdma_ucontext *ucontext = NULL; unsigned long flags; - bool use_pbles; u32 total; int err; + u8 lvl; total = req.sq_pages + req.rq_pages + 1; if (total > iwmr->page_cnt) return -EINVAL; total = req.sq_pages + req.rq_pages; - use_pbles = total > 2; - err = irdma_handle_q_mem(iwdev, &req, iwpbl, use_pbles); + lvl = total > 2 ? PBLE_LEVEL_1 : PBLE_LEVEL_0; + err = irdma_handle_q_mem(iwdev, &req, iwpbl, lvl); if (err) return err; @@ -2872,9 +2871,9 @@ static int irdma_reg_user_mr_type_cq(struct irdma_mem_reg_req req, struct irdma_ucontext *ucontext = NULL; u8 shadow_pgcnt = 1; unsigned long flags; - bool use_pbles; u32 total; int err; + u8 lvl; if (iwdev->rf->sc_dev.hw_attrs.uk_attrs.feature_flags & IRDMA_FEATURE_CQ_RESIZE) shadow_pgcnt = 0; @@ -2882,8 +2881,8 @@ static int irdma_reg_user_mr_type_cq(struct irdma_mem_reg_req req, if (total > iwmr->page_cnt) return -EINVAL; - use_pbles = req.cq_pages > 1; - err = irdma_handle_q_mem(iwdev, &req, iwpbl, use_pbles); + lvl = req.cq_pages > 1 ? PBLE_LEVEL_1 : PBLE_LEVEL_0; + err = irdma_handle_q_mem(iwdev, &req, iwpbl, lvl); if (err) return err; -- GitLab From c4526fe2e4090b2d2167d36da8d9f4a866114e7a Mon Sep 17 00:00:00 2001 From: Rohit Chavan Date: Sun, 19 Mar 2023 15:38:47 +0530 Subject: [PATCH 0868/5631] RDMA/mlx5: Coding style fix reported by checkpatch Block comments should align the * on each line on line 2849 Avoid line continuations in quoted strings on line 3848 Signed-off-by: Rohit Chavan Link: https://lore.kernel.org/r/20230319100847.5566-1-roheetchavan@gmail.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/qp.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7cc3b973dec7..2bad38cb39fe 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -2846,9 +2846,9 @@ static void process_vendor_flag(struct mlx5_ib_dev *dev, int *flags, int flag, case MLX5_QP_FLAG_SCATTER_CQE: case MLX5_QP_FLAG_ALLOW_SCATTER_CQE: /* - * We don't return error if these flags were provided, - * and mlx5 doesn't have right capability. - */ + * We don't return error if these flags were provided, + * and mlx5 doesn't have right capability. + */ *flags &= ~(MLX5_QP_FLAG_SCATTER_CQE | MLX5_QP_FLAG_ALLOW_SCATTER_CQE); return; @@ -5592,8 +5592,7 @@ int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, if (wq_attr->flags_mask & IB_WQ_FLAGS_CVLAN_STRIPPING) { if (!(MLX5_CAP_GEN(dev->mdev, eth_net_offloads) && MLX5_CAP_ETH(dev->mdev, vlan_cap))) { - mlx5_ib_dbg(dev, "VLAN offloads are not " - "supported\n"); + mlx5_ib_dbg(dev, "VLAN offloads are not supported\n"); err = -EOPNOTSUPP; goto out; } -- GitLab From 512ed1199e3ee210c68a9e37a70b399fea3c2099 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 13:32:10 -0600 Subject: [PATCH 0869/5631] IB/hfi1: Drop redundant pci_enable_pcie_error_reporting() pci_enable_pcie_error_reporting() enables the device to send ERR_* Messages. Since f26e58bf6f54 ("PCI/AER: Enable error reporting when AER is native"), the PCI core does this for all devices during enumeration, so the driver doesn't need to do it itself. Remove the redundant pci_enable_pcie_error_reporting() call from the driver. Note that this only controls ERR_* Messages from the device. An ERR_* Message may cause the Root Port to generate an interrupt, depending on the AER Root Error Command register managed by the AER service driver. Signed-off-by: Bjorn Helgaas Cc: Dennis Dalessandro Reviewed-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/pcie.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index a0802332c8cb..08732e1ac966 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #include "hfi.h" @@ -65,7 +64,6 @@ int hfi1_pcie_init(struct hfi1_devdata *dd) } pci_set_master(pdev); - (void)pci_enable_pcie_error_reporting(pdev); return 0; bail: -- GitLab From 697d5cf073acd41a8ab135695bb1e2ae3fd0acb3 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 13:32:11 -0600 Subject: [PATCH 0870/5631] IB/qib: Drop redundant pci_enable_pcie_error_reporting() pci_enable_pcie_error_reporting() enables the device to send ERR_* Messages. Since f26e58bf6f54 ("PCI/AER: Enable error reporting when AER is native"), the PCI core does this for all devices during enumeration, so the driver doesn't need to do it itself. Remove the redundant pci_enable_pcie_error_reporting() call from the driver. Note that this only controls ERR_* Messages from the device. An ERR_* Message may cause the Root Port to generate an interrupt, depending on the AER Root Error Command register managed by the AER service driver. Signed-off-by: Bjorn Helgaas Cc: Dennis Dalessandro Reviewed-by: Dennis Dalessandro Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/qib/qib_pcie.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/infiniband/hw/qib/qib_pcie.c b/drivers/infiniband/hw/qib/qib_pcie.c index 692b64efad97..47bf64ace05c 100644 --- a/drivers/infiniband/hw/qib/qib_pcie.c +++ b/drivers/infiniband/hw/qib/qib_pcie.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include "qib.h" @@ -105,13 +104,6 @@ int qib_pcie_init(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - ret = pci_enable_pcie_error_reporting(pdev); - if (ret) { - qib_early_err(&pdev->dev, - "Unable to enable pcie error reporting: %d\n", - ret); - ret = 0; - } goto done; bail: -- GitLab From aec463feaca9f726a778499ed57b63ffd9c4c523 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Sat, 18 Mar 2023 14:55:03 -0400 Subject: [PATCH 0871/5631] iio: addac: stx104: Replace bitops.h header inclusion with bits.h The header is included in the stx104 driver so that we can use the BIT() macro. This macro is actually defined in the header, so replace the header inclusion with . Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/20230318185503.341914-1-william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 48a91a95e597..e45b70aa5bb7 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -3,7 +3,7 @@ * IIO driver for the Apex Embedded Systems STX104 * Copyright (C) 2016 William Breathitt Gray */ -#include +#include #include #include #include -- GitLab From f9dbd94ba8cf19f8ff76a48ba5864fd140f8a4e1 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Fri, 17 Mar 2023 11:33:19 +0100 Subject: [PATCH 0872/5631] dt-bindings: iio: st-sensors: Add IIS328DQ accelerometer The ST IIS328DQ is an accelerometer sensor, which is compatible with the already supported ST H3LIS331DL. So add the new compatible with a fallback to the ST sensor binding. Link: https://lore.kernel.org/linux-iio/2bac9ecf-9d2e-967e-9020-1c950487d781@i2se.com/ Suggested-by: Jonathan Cameron Signed-off-by: Stefan Wahren Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230317103323.7741-5-stefan.wahren@chargebyte.com Signed-off-by: Jonathan Cameron --- Documentation/devicetree/bindings/iio/st,st-sensors.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index c6201976378f..5eb71b24a7cb 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -48,6 +48,9 @@ properties: - st,lsm330d-accel - st,lsm330dl-accel - st,lsm330dlc-accel + - items: + - const: st,iis328dq + - const: st,h3lis331dl-accel - description: Silan Accelerometers enum: - silan,sc7a20 -- GitLab From 46e33707fe95a21aa9896bded0be97285b779509 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Fri, 17 Mar 2023 11:33:20 +0100 Subject: [PATCH 0873/5631] iio: accel: add support for IIS328DQ variant Since the ST IIS328DQ accelerometer is compatible to the ST LIS331DL, just add the new compatible to the st_accel framework. Link: https://www.st.com/resource/en/datasheet/iis328dq.pdf Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/20230317103323.7741-6-stefan.wahren@chargebyte.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel.h | 1 + drivers/iio/accel/st_accel_core.c | 1 + drivers/iio/accel/st_accel_i2c.c | 5 +++++ drivers/iio/accel/st_accel_spi.c | 5 +++++ 4 files changed, 12 insertions(+) diff --git a/drivers/iio/accel/st_accel.h b/drivers/iio/accel/st_accel.h index 56ed0c776d4a..e7525615712b 100644 --- a/drivers/iio/accel/st_accel.h +++ b/drivers/iio/accel/st_accel.h @@ -39,6 +39,7 @@ #define LIS302DL_ACCEL_DEV_NAME "lis302dl" #define LSM303C_ACCEL_DEV_NAME "lsm303c_accel" #define SC7A20_ACCEL_DEV_NAME "sc7a20" +#define IIS328DQ_ACCEL_DEV_NAME "iis328dq" #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 6b8562f684d5..5f7d81b44b1d 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -517,6 +517,7 @@ static const struct st_sensor_settings st_accel_sensors_settings[] = { .wai_addr = ST_SENSORS_DEFAULT_WAI_ADDRESS, .sensors_supported = { [0] = H3LIS331DL_ACCEL_DEV_NAME, + [1] = IIS328DQ_ACCEL_DEV_NAME, }, .ch = (struct iio_chan_spec *)st_accel_12bit_channels, .odr = { diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index 3f02fd5d5946..fb9e2d6f4210 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -119,6 +119,10 @@ static const struct of_device_id st_accel_of_match[] = { .compatible = "silan,sc7a20", .data = SC7A20_ACCEL_DEV_NAME, }, + { + .compatible = "st,iis328dq", + .data = IIS328DQ_ACCEL_DEV_NAME, + }, {}, }; MODULE_DEVICE_TABLE(of, st_accel_of_match); @@ -157,6 +161,7 @@ static const struct i2c_device_id st_accel_id_table[] = { { LIS302DL_ACCEL_DEV_NAME }, { LSM303C_ACCEL_DEV_NAME }, { SC7A20_ACCEL_DEV_NAME }, + { IIS328DQ_ACCEL_DEV_NAME }, {}, }; MODULE_DEVICE_TABLE(i2c, st_accel_id_table); diff --git a/drivers/iio/accel/st_accel_spi.c b/drivers/iio/accel/st_accel_spi.c index 5740dc1820bd..f72a24f45322 100644 --- a/drivers/iio/accel/st_accel_spi.c +++ b/drivers/iio/accel/st_accel_spi.c @@ -100,6 +100,10 @@ static const struct of_device_id st_accel_of_match[] = { .compatible = "st,lsm303c-accel", .data = LSM303C_ACCEL_DEV_NAME, }, + { + .compatible = "st,iis328dq", + .data = IIS328DQ_ACCEL_DEV_NAME, + }, {} }; MODULE_DEVICE_TABLE(of, st_accel_of_match); @@ -157,6 +161,7 @@ static const struct spi_device_id st_accel_id_table[] = { { LIS3DE_ACCEL_DEV_NAME }, { LIS302DL_ACCEL_DEV_NAME }, { LSM303C_ACCEL_DEV_NAME }, + { IIS328DQ_ACCEL_DEV_NAME }, {}, }; MODULE_DEVICE_TABLE(spi, st_accel_id_table); -- GitLab From 7ce93729091dff24e6a1c3578b58b36f4b1cf10a Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Fri, 10 Mar 2023 16:27:28 -0500 Subject: [PATCH 0874/5631] dyndbg: cleanup dynamic usage in ib_srp.c Currently, in dynamic_debug.h we only provide DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH() definitions if CONFIG_DYNAMIC_CORE is enabled. Thus, drivers such as infiniband srp (see: drivers/infiniband/ulp/srp/ib_srp.c) must provide their own definitions for !CONFIG_DYNAMIC_CORE. Thus, let's move this !CONFIG_DYNAMIC_CORE case into dynamic_debug.h. However, the dynamic debug interfaces should really only be defined if CONFIG_DYNAMIC_DEBUG is set or CONFIG_DYNAMIC_CORE is set along with DYNAMIC_DEBUG_MODULE, (see: Documentation/admin-guide/dynamic-debug-howto.rst). Thus, the undefined case becomes: !((CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_CORE && DYNAMIC_DEBUG_MODULE)). With those changes in place, we can remove the !CONFIG_DYNAMIC_CORE case from ib_srp.c This change was prompted by a build breakeage in ib_srp.c stemming from the inclusion of dynamic_debug.h unconditionally in module.h, due to commit 7deabd674988 ("dyndbg: use the module notifier callbacks"). In that case, if we have CONFIG_DYNAMIC_CORE=y and CONFIG_DYNAMIC_DEBUG=n then the definitions for DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH() are defined once in ib_srp.c and then again in the dynamic_debug.h. This had been working prior to the above referenced commit because dynamic_debug.h was only pulled into ib_srp.c conditinally via printk.h if CONFIG_DYNAMIC_DEBUG was set. Also, the exported functions in lib/dynamic_debug.c itself may not have a prototype if CONFIG_DYNAMIC_DEBUG=n and CONFIG_DYNAMIC_CORE=y. This would trigger the -Wmissing-prototypes warning. The exported functions are behind (include/linux/dynamic_debug.h): if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) Thus, by adding -DDYNAMIC_CONFIG_MODULE to the lib/Makefile we can ensure that the exported functions have a prototype in all cases, since lib/dynamic_debug.c is built whenever CONFIG_DYNAMIC_DEBUG_CORE=y. Fixes: 7deabd674988 ("dyndbg: use the module notifier callbacks") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303071444.sIbZTDCy-lkp@intel.com/ Signed-off-by: Jason Baron [mcgrof: adjust commit log, and remove urldefense from URL] Signed-off-by: Luis Chamberlain --- drivers/infiniband/ulp/srp/ib_srp.c | 5 --- include/linux/dynamic_debug.h | 59 ++++++++++++++++++----------- lib/Makefile | 3 ++ 3 files changed, 40 insertions(+), 27 deletions(-) diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index df21b30b7735..40ba2c6927c6 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -62,11 +62,6 @@ MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator"); MODULE_LICENSE("Dual BSD/GPL"); -#if !defined(CONFIG_DYNAMIC_DEBUG) -#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) -#define DYNAMIC_DEBUG_BRANCH(descriptor) false -#endif - static unsigned int srp_sg_tablesize; static unsigned int cmd_sg_entries; static unsigned int indirect_sg_entries; diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index f401414341fb..061dd84d09f3 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -128,14 +128,16 @@ struct ddebug_class_param { const struct ddebug_class_map *map; }; -#if defined(CONFIG_DYNAMIC_DEBUG_CORE) +/* + * pr_debug() and friends are globally enabled or modules have selectively + * enabled them. + */ +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); -extern int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname); - struct device; extern __printf(3, 4) @@ -284,10 +286,6 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -struct kernel_param; -int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); -int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); - /* for test only, generally expect drm.debug style macro wrappers */ #define __pr_debug_cls(cls, fmt, ...) do { \ BUILD_BUG_ON_MSG(!__builtin_constant_p(cls), \ @@ -295,23 +293,14 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); dynamic_pr_debug_cls(cls, fmt, ##__VA_ARGS__); \ } while (0) -#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#else /* !(CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE)) */ #include #include #include -static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname) -{ - if (!strcmp(param, "dyndbg")) { - /* avoid pr_warn(), which wants pr_fmt() fully defined */ - printk(KERN_WARNING "dyndbg param is supported only in " - "CONFIG_DYNAMIC_DEBUG builds\n"); - return 0; /* allow and ignore */ - } - return -EINVAL; -} +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) +#define DYNAMIC_DEBUG_BRANCH(descriptor) false #define dynamic_pr_debug(fmt, ...) \ do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) @@ -324,14 +313,40 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, rowsize, groupsize, buf, len, ascii); \ } while (0) +#endif /* CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE) */ + + +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + +extern int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname); +struct kernel_param; +int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); +int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); + +#else + +static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname) +{ + if (!strcmp(param, "dyndbg")) { + /* avoid pr_warn(), which wants pr_fmt() fully defined */ + printk(KERN_WARNING "dyndbg param is supported only in " + "CONFIG_DYNAMIC_DEBUG builds\n"); + return 0; /* allow and ignore */ + } + return -EINVAL; +} + struct kernel_param; static inline int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp) { return 0; } static inline int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp) { return 0; } -#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#endif + extern const struct kernel_param_ops param_ops_dyndbg_classes; -#endif +#endif /* _DYNAMIC_DEBUG_H */ diff --git a/lib/Makefile b/lib/Makefile index baf2821f7a00..7afcd85f78f6 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -231,6 +231,9 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o +#ensure exported functions have prototypes +CFLAGS_dynamic_debug.o := -DDYNAMIC_DEBUG_MODULE + obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o obj-$(CONFIG_NLATTR) += nlattr.o -- GitLab From 3703bd54cd37e7875f51ece8df8c85c184e40bba Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Wed, 8 Mar 2023 15:38:46 +0800 Subject: [PATCH 0875/5631] kallsyms: Delete an unused parameter related to {module_}kallsyms_on_each_symbol() The parameter 'struct module *' in the hook function associated with {module_}kallsyms_on_each_symbol() is no longer used. Delete it. Suggested-by: Petr Mladek Signed-off-by: Zhen Lei Reviewed-by: Vincenzo Palazzo Acked-by: Jiri Olsa Acked-by: Steven Rostedt (Google) Signed-off-by: Luis Chamberlain --- include/linux/kallsyms.h | 7 +++---- include/linux/module.h | 6 ++---- kernel/kallsyms.c | 5 ++--- kernel/kallsyms_selftest.c | 6 +++--- kernel/livepatch/core.c | 3 +-- kernel/module/kallsyms.c | 5 ++--- kernel/trace/ftrace.c | 3 +-- 7 files changed, 14 insertions(+), 21 deletions(-) diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0065209cc004..fe3c9993b5bf 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -67,8 +67,7 @@ static inline void *dereference_symbol_descriptor(void *ptr) #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); -int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data); int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data); @@ -166,8 +165,8 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), void *data) +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), + void *data) { return -EOPNOTSUPP; } diff --git a/include/linux/module.h b/include/linux/module.h index c3b357196470..d2d900077bde 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -965,13 +965,11 @@ static inline bool module_sig_ok(struct module *module) #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data); #else static inline int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 83f499182c9a..77747391f49b 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -288,8 +288,7 @@ unsigned long kallsyms_lookup_name(const char *name) * Iterate over all symbols in vmlinux. For symbols from modules use * module_kallsyms_on_each_symbol instead. */ -int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data) { char namebuf[KSYM_NAME_LEN]; @@ -299,7 +298,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, for (i = 0, off = 0; i < kallsyms_num_syms; i++) { off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); - ret = fn(data, namebuf, NULL, kallsyms_sym_address(i)); + ret = fn(data, namebuf, kallsyms_sym_address(i)); if (ret != 0) return ret; cond_resched(); diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index bfbc12da3326..a2e3745d15c4 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -95,7 +95,7 @@ static struct test_item test_items[] = { static char stub_name[KSYM_NAME_LEN]; -static int stat_symbol_len(void *data, const char *name, struct module *mod, unsigned long addr) +static int stat_symbol_len(void *data, const char *name, unsigned long addr) { *(u32 *)data += strlen(name); @@ -154,7 +154,7 @@ static void test_kallsyms_compression_ratio(void) pr_info(" ---------------------------------------------------------\n"); } -static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr) +static int lookup_name(void *data, const char *name, unsigned long addr) { u64 t0, t1, t; struct test_stat *stat = (struct test_stat *)data; @@ -207,7 +207,7 @@ static bool match_cleanup_name(const char *s, const char *name) return !strncmp(s, name, len); } -static int find_symbol(void *data, const char *name, struct module *mod, unsigned long addr) +static int find_symbol(void *data, const char *name, unsigned long addr) { struct test_stat *stat = (struct test_stat *)data; diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 4bd2d5e10f20..1de2c40cc378 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -142,8 +142,7 @@ static int klp_match_callback(void *data, unsigned long addr) return 0; } -static int klp_find_callback(void *data, const char *name, - struct module *mod, unsigned long addr) +static int klp_find_callback(void *data, const char *name, unsigned long addr) { struct klp_find_arg *args = data; diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 8e89f459ffdd..3320586584f1 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -503,8 +503,7 @@ unsigned long module_kallsyms_lookup_name(const char *name) } int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data) { struct module *mod; @@ -533,7 +532,7 @@ int module_kallsyms_on_each_symbol(const char *modname, continue; ret = fn(data, kallsyms_symbol_name(kallsyms, i), - mod, kallsyms_symbol_value(sym)); + kallsyms_symbol_value(sym)); if (ret != 0) goto out; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 29baa97d0d53..76caca8f496a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8391,8 +8391,7 @@ struct kallsyms_data { * and returns 1 in case we resolved all the requested symbols, * 0 otherwise. */ -static int kallsyms_callback(void *data, const char *name, - struct module *mod, unsigned long addr) +static int kallsyms_callback(void *data, const char *name, unsigned long addr) { struct kallsyms_data *args = data; const char **sym; -- GitLab From 7c19147d9cfc0f9328049d2e278279150d7de9ca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:51 +0300 Subject: [PATCH 0876/5631] pinctrl: ralink: reintroduce ralink,rt2880-pinmux compatible string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There have been stable releases with the ralink,rt2880-pinmux compatible string included. Having it removed breaks the ABI. Reintroduce it. Fixes: e5981cd46183 ("pinctrl: ralink: add new compatible strings for each pinctrl subdriver") Signed-off-by: Arınç ÜNAL Reviewed-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230317213011.13656-2-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- drivers/pinctrl/ralink/pinctrl-mt7620.c | 1 + drivers/pinctrl/ralink/pinctrl-mt7621.c | 1 + drivers/pinctrl/ralink/pinctrl-rt2880.c | 1 + drivers/pinctrl/ralink/pinctrl-rt305x.c | 1 + drivers/pinctrl/ralink/pinctrl-rt3883.c | 1 + 5 files changed, 5 insertions(+) diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/ralink/pinctrl-mt7620.c index 4e8d26bb3430..06b86c726839 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt7620.c +++ b/drivers/pinctrl/ralink/pinctrl-mt7620.c @@ -372,6 +372,7 @@ static int mt7620_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id mt7620_pinctrl_match[] = { { .compatible = "ralink,mt7620-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, {} }; MODULE_DEVICE_TABLE(of, mt7620_pinctrl_match); diff --git a/drivers/pinctrl/ralink/pinctrl-mt7621.c b/drivers/pinctrl/ralink/pinctrl-mt7621.c index eddc0ba6d468..fb5824922e78 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt7621.c +++ b/drivers/pinctrl/ralink/pinctrl-mt7621.c @@ -97,6 +97,7 @@ static int mt7621_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id mt7621_pinctrl_match[] = { { .compatible = "ralink,mt7621-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, {} }; MODULE_DEVICE_TABLE(of, mt7621_pinctrl_match); diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/ralink/pinctrl-rt2880.c index 3e2f1aaaf095..d7a65fcc7755 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt2880.c +++ b/drivers/pinctrl/ralink/pinctrl-rt2880.c @@ -41,6 +41,7 @@ static int rt2880_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id rt2880_pinctrl_match[] = { { .compatible = "ralink,rt2880-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, {} }; MODULE_DEVICE_TABLE(of, rt2880_pinctrl_match); diff --git a/drivers/pinctrl/ralink/pinctrl-rt305x.c b/drivers/pinctrl/ralink/pinctrl-rt305x.c index bdaee5ce1ee0..f6092c64383e 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt305x.c +++ b/drivers/pinctrl/ralink/pinctrl-rt305x.c @@ -118,6 +118,7 @@ static int rt305x_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id rt305x_pinctrl_match[] = { { .compatible = "ralink,rt305x-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, {} }; MODULE_DEVICE_TABLE(of, rt305x_pinctrl_match); diff --git a/drivers/pinctrl/ralink/pinctrl-rt3883.c b/drivers/pinctrl/ralink/pinctrl-rt3883.c index 392208662355..5f766d76bafa 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt3883.c +++ b/drivers/pinctrl/ralink/pinctrl-rt3883.c @@ -88,6 +88,7 @@ static int rt3883_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id rt3883_pinctrl_match[] = { { .compatible = "ralink,rt3883-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, {} }; MODULE_DEVICE_TABLE(of, rt3883_pinctrl_match); -- GitLab From 5465d9891254b9ebc5fedee298bd40dda9ddf6c1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:52 +0300 Subject: [PATCH 0877/5631] pinctrl: ralink: rt305x: add new compatible string for every SoC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add new compatible strings to make every SoC, or SoCs that use the same pinmux data have a unique compatible string. This ensures that the pin muxing information of every SoC, or a set of SoCs that use the same pinmux data can be properly documented. Signed-off-by: Arınç ÜNAL Reviewed-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230317213011.13656-3-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- drivers/pinctrl/ralink/pinctrl-rt305x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pinctrl/ralink/pinctrl-rt305x.c b/drivers/pinctrl/ralink/pinctrl-rt305x.c index f6092c64383e..fa3743c7680f 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt305x.c +++ b/drivers/pinctrl/ralink/pinctrl-rt305x.c @@ -118,6 +118,8 @@ static int rt305x_pinctrl_probe(struct platform_device *pdev) static const struct of_device_id rt305x_pinctrl_match[] = { { .compatible = "ralink,rt305x-pinctrl" }, + { .compatible = "ralink,rt3352-pinctrl" }, + { .compatible = "ralink,rt5350-pinctrl" }, { .compatible = "ralink,rt2880-pinmux" }, {} }; -- GitLab From f7dedad4e290e8be87b1c5a63a19a9663bcd2740 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:53 +0300 Subject: [PATCH 0878/5631] pinctrl: ralink: mt7620: split out to mt76x8 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Split the driver out to pinctrl-mt76x8.c. Remove including the unnecessary headers since is_mt76x8() is not being used anymore. Introduce a new compatible string to be able to document the pin muxing information properly. Signed-off-by: Arınç ÜNAL Reviewed-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230317213011.13656-4-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- drivers/pinctrl/ralink/Kconfig | 5 + drivers/pinctrl/ralink/Makefile | 1 + drivers/pinctrl/ralink/pinctrl-mt7620.c | 257 +-------------------- drivers/pinctrl/ralink/pinctrl-mt76x8.c | 283 ++++++++++++++++++++++++ 4 files changed, 290 insertions(+), 256 deletions(-) create mode 100644 drivers/pinctrl/ralink/pinctrl-mt76x8.c diff --git a/drivers/pinctrl/ralink/Kconfig b/drivers/pinctrl/ralink/Kconfig index 1e4c5e43d69b..c5fe4c31aaea 100644 --- a/drivers/pinctrl/ralink/Kconfig +++ b/drivers/pinctrl/ralink/Kconfig @@ -17,6 +17,11 @@ config PINCTRL_MT7621 depends on RALINK && SOC_MT7621 select PINCTRL_RALINK +config PINCTRL_MT76X8 + bool "MT76X8 pinctrl subdriver" + depends on RALINK && SOC_MT7620 + select PINCTRL_RALINK + config PINCTRL_RT2880 bool "RT2880 pinctrl subdriver" depends on RALINK && SOC_RT288X diff --git a/drivers/pinctrl/ralink/Makefile b/drivers/pinctrl/ralink/Makefile index 0ebbe552526d..be9acf2e27fd 100644 --- a/drivers/pinctrl/ralink/Makefile +++ b/drivers/pinctrl/ralink/Makefile @@ -3,6 +3,7 @@ obj-$(CONFIG_PINCTRL_RALINK) += pinctrl-ralink.o obj-$(CONFIG_PINCTRL_MT7620) += pinctrl-mt7620.o obj-$(CONFIG_PINCTRL_MT7621) += pinctrl-mt7621.o +obj-$(CONFIG_PINCTRL_MT76X8) += pinctrl-mt76x8.o obj-$(CONFIG_PINCTRL_RT2880) += pinctrl-rt2880.o obj-$(CONFIG_PINCTRL_RT305X) += pinctrl-rt305x.o obj-$(CONFIG_PINCTRL_RT3883) += pinctrl-rt3883.o diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/ralink/pinctrl-mt7620.c index 06b86c726839..3f6ffccc6882 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt7620.c +++ b/drivers/pinctrl/ralink/pinctrl-mt7620.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#include -#include #include #include #include @@ -112,262 +110,9 @@ static struct ralink_pmx_group mt7620a_pinmux_data[] = { { 0 } }; -static struct ralink_pmx_func pwm1_grp_mt76x8[] = { - FUNC("sdxc d6", 3, 19, 1), - FUNC("utif", 2, 19, 1), - FUNC("gpio", 1, 19, 1), - FUNC("pwm1", 0, 19, 1), -}; - -static struct ralink_pmx_func pwm0_grp_mt76x8[] = { - FUNC("sdxc d7", 3, 18, 1), - FUNC("utif", 2, 18, 1), - FUNC("gpio", 1, 18, 1), - FUNC("pwm0", 0, 18, 1), -}; - -static struct ralink_pmx_func uart2_grp_mt76x8[] = { - FUNC("sdxc d5 d4", 3, 20, 2), - FUNC("pwm", 2, 20, 2), - FUNC("gpio", 1, 20, 2), - FUNC("uart2", 0, 20, 2), -}; - -static struct ralink_pmx_func uart1_grp_mt76x8[] = { - FUNC("sw_r", 3, 45, 2), - FUNC("pwm", 2, 45, 2), - FUNC("gpio", 1, 45, 2), - FUNC("uart1", 0, 45, 2), -}; - -static struct ralink_pmx_func i2c_grp_mt76x8[] = { - FUNC("-", 3, 4, 2), - FUNC("debug", 2, 4, 2), - FUNC("gpio", 1, 4, 2), - FUNC("i2c", 0, 4, 2), -}; - -static struct ralink_pmx_func refclk_grp_mt76x8[] = { FUNC("refclk", 0, 37, 1) }; -static struct ralink_pmx_func perst_grp_mt76x8[] = { FUNC("perst", 0, 36, 1) }; -static struct ralink_pmx_func wdt_grp_mt76x8[] = { FUNC("wdt", 0, 38, 1) }; -static struct ralink_pmx_func spi_grp_mt76x8[] = { FUNC("spi", 0, 7, 4) }; - -static struct ralink_pmx_func sd_mode_grp_mt76x8[] = { - FUNC("jtag", 3, 22, 8), - FUNC("utif", 2, 22, 8), - FUNC("gpio", 1, 22, 8), - FUNC("sdxc", 0, 22, 8), -}; - -static struct ralink_pmx_func uart0_grp_mt76x8[] = { - FUNC("-", 3, 12, 2), - FUNC("-", 2, 12, 2), - FUNC("gpio", 1, 12, 2), - FUNC("uart0", 0, 12, 2), -}; - -static struct ralink_pmx_func i2s_grp_mt76x8[] = { - FUNC("antenna", 3, 0, 4), - FUNC("pcm", 2, 0, 4), - FUNC("gpio", 1, 0, 4), - FUNC("i2s", 0, 0, 4), -}; - -static struct ralink_pmx_func spi_cs1_grp_mt76x8[] = { - FUNC("-", 3, 6, 1), - FUNC("refclk", 2, 6, 1), - FUNC("gpio", 1, 6, 1), - FUNC("spi cs1", 0, 6, 1), -}; - -static struct ralink_pmx_func spis_grp_mt76x8[] = { - FUNC("pwm_uart2", 3, 14, 4), - FUNC("utif", 2, 14, 4), - FUNC("gpio", 1, 14, 4), - FUNC("spis", 0, 14, 4), -}; - -static struct ralink_pmx_func gpio_grp_mt76x8[] = { - FUNC("pcie", 3, 11, 1), - FUNC("refclk", 2, 11, 1), - FUNC("gpio", 1, 11, 1), - FUNC("gpio", 0, 11, 1), -}; - -static struct ralink_pmx_func p4led_kn_grp_mt76x8[] = { - FUNC("jtag", 3, 30, 1), - FUNC("utif", 2, 30, 1), - FUNC("gpio", 1, 30, 1), - FUNC("p4led_kn", 0, 30, 1), -}; - -static struct ralink_pmx_func p3led_kn_grp_mt76x8[] = { - FUNC("jtag", 3, 31, 1), - FUNC("utif", 2, 31, 1), - FUNC("gpio", 1, 31, 1), - FUNC("p3led_kn", 0, 31, 1), -}; - -static struct ralink_pmx_func p2led_kn_grp_mt76x8[] = { - FUNC("jtag", 3, 32, 1), - FUNC("utif", 2, 32, 1), - FUNC("gpio", 1, 32, 1), - FUNC("p2led_kn", 0, 32, 1), -}; - -static struct ralink_pmx_func p1led_kn_grp_mt76x8[] = { - FUNC("jtag", 3, 33, 1), - FUNC("utif", 2, 33, 1), - FUNC("gpio", 1, 33, 1), - FUNC("p1led_kn", 0, 33, 1), -}; - -static struct ralink_pmx_func p0led_kn_grp_mt76x8[] = { - FUNC("jtag", 3, 34, 1), - FUNC("rsvd", 2, 34, 1), - FUNC("gpio", 1, 34, 1), - FUNC("p0led_kn", 0, 34, 1), -}; - -static struct ralink_pmx_func wled_kn_grp_mt76x8[] = { - FUNC("rsvd", 3, 35, 1), - FUNC("rsvd", 2, 35, 1), - FUNC("gpio", 1, 35, 1), - FUNC("wled_kn", 0, 35, 1), -}; - -static struct ralink_pmx_func p4led_an_grp_mt76x8[] = { - FUNC("jtag", 3, 39, 1), - FUNC("utif", 2, 39, 1), - FUNC("gpio", 1, 39, 1), - FUNC("p4led_an", 0, 39, 1), -}; - -static struct ralink_pmx_func p3led_an_grp_mt76x8[] = { - FUNC("jtag", 3, 40, 1), - FUNC("utif", 2, 40, 1), - FUNC("gpio", 1, 40, 1), - FUNC("p3led_an", 0, 40, 1), -}; - -static struct ralink_pmx_func p2led_an_grp_mt76x8[] = { - FUNC("jtag", 3, 41, 1), - FUNC("utif", 2, 41, 1), - FUNC("gpio", 1, 41, 1), - FUNC("p2led_an", 0, 41, 1), -}; - -static struct ralink_pmx_func p1led_an_grp_mt76x8[] = { - FUNC("jtag", 3, 42, 1), - FUNC("utif", 2, 42, 1), - FUNC("gpio", 1, 42, 1), - FUNC("p1led_an", 0, 42, 1), -}; - -static struct ralink_pmx_func p0led_an_grp_mt76x8[] = { - FUNC("jtag", 3, 43, 1), - FUNC("rsvd", 2, 43, 1), - FUNC("gpio", 1, 43, 1), - FUNC("p0led_an", 0, 43, 1), -}; - -static struct ralink_pmx_func wled_an_grp_mt76x8[] = { - FUNC("rsvd", 3, 44, 1), - FUNC("rsvd", 2, 44, 1), - FUNC("gpio", 1, 44, 1), - FUNC("wled_an", 0, 44, 1), -}; - -#define MT76X8_GPIO_MODE_MASK 0x3 - -#define MT76X8_GPIO_MODE_P4LED_KN 58 -#define MT76X8_GPIO_MODE_P3LED_KN 56 -#define MT76X8_GPIO_MODE_P2LED_KN 54 -#define MT76X8_GPIO_MODE_P1LED_KN 52 -#define MT76X8_GPIO_MODE_P0LED_KN 50 -#define MT76X8_GPIO_MODE_WLED_KN 48 -#define MT76X8_GPIO_MODE_P4LED_AN 42 -#define MT76X8_GPIO_MODE_P3LED_AN 40 -#define MT76X8_GPIO_MODE_P2LED_AN 38 -#define MT76X8_GPIO_MODE_P1LED_AN 36 -#define MT76X8_GPIO_MODE_P0LED_AN 34 -#define MT76X8_GPIO_MODE_WLED_AN 32 -#define MT76X8_GPIO_MODE_PWM1 30 -#define MT76X8_GPIO_MODE_PWM0 28 -#define MT76X8_GPIO_MODE_UART2 26 -#define MT76X8_GPIO_MODE_UART1 24 -#define MT76X8_GPIO_MODE_I2C 20 -#define MT76X8_GPIO_MODE_REFCLK 18 -#define MT76X8_GPIO_MODE_PERST 16 -#define MT76X8_GPIO_MODE_WDT 14 -#define MT76X8_GPIO_MODE_SPI 12 -#define MT76X8_GPIO_MODE_SDMODE 10 -#define MT76X8_GPIO_MODE_UART0 8 -#define MT76X8_GPIO_MODE_I2S 6 -#define MT76X8_GPIO_MODE_CS1 4 -#define MT76X8_GPIO_MODE_SPIS 2 -#define MT76X8_GPIO_MODE_GPIO 0 - -static struct ralink_pmx_group mt76x8_pinmux_data[] = { - GRP_G("pwm1", pwm1_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_PWM1), - GRP_G("pwm0", pwm0_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_PWM0), - GRP_G("uart2", uart2_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_UART2), - GRP_G("uart1", uart1_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_UART1), - GRP_G("i2c", i2c_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_I2C), - GRP("refclk", refclk_grp_mt76x8, 1, MT76X8_GPIO_MODE_REFCLK), - GRP("perst", perst_grp_mt76x8, 1, MT76X8_GPIO_MODE_PERST), - GRP("wdt", wdt_grp_mt76x8, 1, MT76X8_GPIO_MODE_WDT), - GRP("spi", spi_grp_mt76x8, 1, MT76X8_GPIO_MODE_SPI), - GRP_G("sdmode", sd_mode_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_SDMODE), - GRP_G("uart0", uart0_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_UART0), - GRP_G("i2s", i2s_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_I2S), - GRP_G("spi cs1", spi_cs1_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_CS1), - GRP_G("spis", spis_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_SPIS), - GRP_G("gpio", gpio_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_GPIO), - GRP_G("wled_an", wled_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_WLED_AN), - GRP_G("p0led_an", p0led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P0LED_AN), - GRP_G("p1led_an", p1led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P1LED_AN), - GRP_G("p2led_an", p2led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P2LED_AN), - GRP_G("p3led_an", p3led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P3LED_AN), - GRP_G("p4led_an", p4led_an_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P4LED_AN), - GRP_G("wled_kn", wled_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_WLED_KN), - GRP_G("p0led_kn", p0led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P0LED_KN), - GRP_G("p1led_kn", p1led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P1LED_KN), - GRP_G("p2led_kn", p2led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P2LED_KN), - GRP_G("p3led_kn", p3led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P3LED_KN), - GRP_G("p4led_kn", p4led_kn_grp_mt76x8, MT76X8_GPIO_MODE_MASK, - 1, MT76X8_GPIO_MODE_P4LED_KN), - { 0 } -}; - static int mt7620_pinctrl_probe(struct platform_device *pdev) { - if (is_mt76x8()) - return ralink_pinctrl_init(pdev, mt76x8_pinmux_data); - else - return ralink_pinctrl_init(pdev, mt7620a_pinmux_data); + return ralink_pinctrl_init(pdev, mt7620a_pinmux_data); } static const struct of_device_id mt7620_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-mt76x8.c b/drivers/pinctrl/ralink/pinctrl-mt76x8.c new file mode 100644 index 000000000000..4283a54d2db0 --- /dev/null +++ b/drivers/pinctrl/ralink/pinctrl-mt76x8.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include "pinctrl-ralink.h" + +#define MT76X8_GPIO_MODE_MASK 0x3 + +#define MT76X8_GPIO_MODE_P4LED_KN 58 +#define MT76X8_GPIO_MODE_P3LED_KN 56 +#define MT76X8_GPIO_MODE_P2LED_KN 54 +#define MT76X8_GPIO_MODE_P1LED_KN 52 +#define MT76X8_GPIO_MODE_P0LED_KN 50 +#define MT76X8_GPIO_MODE_WLED_KN 48 +#define MT76X8_GPIO_MODE_P4LED_AN 42 +#define MT76X8_GPIO_MODE_P3LED_AN 40 +#define MT76X8_GPIO_MODE_P2LED_AN 38 +#define MT76X8_GPIO_MODE_P1LED_AN 36 +#define MT76X8_GPIO_MODE_P0LED_AN 34 +#define MT76X8_GPIO_MODE_WLED_AN 32 +#define MT76X8_GPIO_MODE_PWM1 30 +#define MT76X8_GPIO_MODE_PWM0 28 +#define MT76X8_GPIO_MODE_UART2 26 +#define MT76X8_GPIO_MODE_UART1 24 +#define MT76X8_GPIO_MODE_I2C 20 +#define MT76X8_GPIO_MODE_REFCLK 18 +#define MT76X8_GPIO_MODE_PERST 16 +#define MT76X8_GPIO_MODE_WDT 14 +#define MT76X8_GPIO_MODE_SPI 12 +#define MT76X8_GPIO_MODE_SDMODE 10 +#define MT76X8_GPIO_MODE_UART0 8 +#define MT76X8_GPIO_MODE_I2S 6 +#define MT76X8_GPIO_MODE_CS1 4 +#define MT76X8_GPIO_MODE_SPIS 2 +#define MT76X8_GPIO_MODE_GPIO 0 + +static struct ralink_pmx_func pwm1_grp[] = { + FUNC("sdxc d6", 3, 19, 1), + FUNC("utif", 2, 19, 1), + FUNC("gpio", 1, 19, 1), + FUNC("pwm1", 0, 19, 1), +}; + +static struct ralink_pmx_func pwm0_grp[] = { + FUNC("sdxc d7", 3, 18, 1), + FUNC("utif", 2, 18, 1), + FUNC("gpio", 1, 18, 1), + FUNC("pwm0", 0, 18, 1), +}; + +static struct ralink_pmx_func uart2_grp[] = { + FUNC("sdxc d5 d4", 3, 20, 2), + FUNC("pwm", 2, 20, 2), + FUNC("gpio", 1, 20, 2), + FUNC("uart2", 0, 20, 2), +}; + +static struct ralink_pmx_func uart1_grp[] = { + FUNC("sw_r", 3, 45, 2), + FUNC("pwm", 2, 45, 2), + FUNC("gpio", 1, 45, 2), + FUNC("uart1", 0, 45, 2), +}; + +static struct ralink_pmx_func i2c_grp[] = { + FUNC("-", 3, 4, 2), + FUNC("debug", 2, 4, 2), + FUNC("gpio", 1, 4, 2), + FUNC("i2c", 0, 4, 2), +}; + +static struct ralink_pmx_func refclk_grp[] = { FUNC("refclk", 0, 37, 1) }; +static struct ralink_pmx_func perst_grp[] = { FUNC("perst", 0, 36, 1) }; +static struct ralink_pmx_func wdt_grp[] = { FUNC("wdt", 0, 38, 1) }; +static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 7, 4) }; + +static struct ralink_pmx_func sd_mode_grp[] = { + FUNC("jtag", 3, 22, 8), + FUNC("utif", 2, 22, 8), + FUNC("gpio", 1, 22, 8), + FUNC("sdxc", 0, 22, 8), +}; + +static struct ralink_pmx_func uart0_grp[] = { + FUNC("-", 3, 12, 2), + FUNC("-", 2, 12, 2), + FUNC("gpio", 1, 12, 2), + FUNC("uart0", 0, 12, 2), +}; + +static struct ralink_pmx_func i2s_grp[] = { + FUNC("antenna", 3, 0, 4), + FUNC("pcm", 2, 0, 4), + FUNC("gpio", 1, 0, 4), + FUNC("i2s", 0, 0, 4), +}; + +static struct ralink_pmx_func spi_cs1_grp[] = { + FUNC("-", 3, 6, 1), + FUNC("refclk", 2, 6, 1), + FUNC("gpio", 1, 6, 1), + FUNC("spi cs1", 0, 6, 1), +}; + +static struct ralink_pmx_func spis_grp[] = { + FUNC("pwm_uart2", 3, 14, 4), + FUNC("utif", 2, 14, 4), + FUNC("gpio", 1, 14, 4), + FUNC("spis", 0, 14, 4), +}; + +static struct ralink_pmx_func gpio_grp[] = { + FUNC("pcie", 3, 11, 1), + FUNC("refclk", 2, 11, 1), + FUNC("gpio", 1, 11, 1), + FUNC("gpio", 0, 11, 1), +}; + +static struct ralink_pmx_func p4led_kn_grp[] = { + FUNC("jtag", 3, 30, 1), + FUNC("utif", 2, 30, 1), + FUNC("gpio", 1, 30, 1), + FUNC("p4led_kn", 0, 30, 1), +}; + +static struct ralink_pmx_func p3led_kn_grp[] = { + FUNC("jtag", 3, 31, 1), + FUNC("utif", 2, 31, 1), + FUNC("gpio", 1, 31, 1), + FUNC("p3led_kn", 0, 31, 1), +}; + +static struct ralink_pmx_func p2led_kn_grp[] = { + FUNC("jtag", 3, 32, 1), + FUNC("utif", 2, 32, 1), + FUNC("gpio", 1, 32, 1), + FUNC("p2led_kn", 0, 32, 1), +}; + +static struct ralink_pmx_func p1led_kn_grp[] = { + FUNC("jtag", 3, 33, 1), + FUNC("utif", 2, 33, 1), + FUNC("gpio", 1, 33, 1), + FUNC("p1led_kn", 0, 33, 1), +}; + +static struct ralink_pmx_func p0led_kn_grp[] = { + FUNC("jtag", 3, 34, 1), + FUNC("rsvd", 2, 34, 1), + FUNC("gpio", 1, 34, 1), + FUNC("p0led_kn", 0, 34, 1), +}; + +static struct ralink_pmx_func wled_kn_grp[] = { + FUNC("rsvd", 3, 35, 1), + FUNC("rsvd", 2, 35, 1), + FUNC("gpio", 1, 35, 1), + FUNC("wled_kn", 0, 35, 1), +}; + +static struct ralink_pmx_func p4led_an_grp[] = { + FUNC("jtag", 3, 39, 1), + FUNC("utif", 2, 39, 1), + FUNC("gpio", 1, 39, 1), + FUNC("p4led_an", 0, 39, 1), +}; + +static struct ralink_pmx_func p3led_an_grp[] = { + FUNC("jtag", 3, 40, 1), + FUNC("utif", 2, 40, 1), + FUNC("gpio", 1, 40, 1), + FUNC("p3led_an", 0, 40, 1), +}; + +static struct ralink_pmx_func p2led_an_grp[] = { + FUNC("jtag", 3, 41, 1), + FUNC("utif", 2, 41, 1), + FUNC("gpio", 1, 41, 1), + FUNC("p2led_an", 0, 41, 1), +}; + +static struct ralink_pmx_func p1led_an_grp[] = { + FUNC("jtag", 3, 42, 1), + FUNC("utif", 2, 42, 1), + FUNC("gpio", 1, 42, 1), + FUNC("p1led_an", 0, 42, 1), +}; + +static struct ralink_pmx_func p0led_an_grp[] = { + FUNC("jtag", 3, 43, 1), + FUNC("rsvd", 2, 43, 1), + FUNC("gpio", 1, 43, 1), + FUNC("p0led_an", 0, 43, 1), +}; + +static struct ralink_pmx_func wled_an_grp[] = { + FUNC("rsvd", 3, 44, 1), + FUNC("rsvd", 2, 44, 1), + FUNC("gpio", 1, 44, 1), + FUNC("wled_an", 0, 44, 1), +}; + +static struct ralink_pmx_group mt76x8_pinmux_data[] = { + GRP_G("pwm1", pwm1_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_PWM1), + GRP_G("pwm0", pwm0_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_PWM0), + GRP_G("uart2", uart2_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_UART2), + GRP_G("uart1", uart1_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_UART1), + GRP_G("i2c", i2c_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_I2C), + GRP("refclk", refclk_grp, 1, MT76X8_GPIO_MODE_REFCLK), + GRP("perst", perst_grp, 1, MT76X8_GPIO_MODE_PERST), + GRP("wdt", wdt_grp, 1, MT76X8_GPIO_MODE_WDT), + GRP("spi", spi_grp, 1, MT76X8_GPIO_MODE_SPI), + GRP_G("sdmode", sd_mode_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_SDMODE), + GRP_G("uart0", uart0_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_UART0), + GRP_G("i2s", i2s_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_I2S), + GRP_G("spi cs1", spi_cs1_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_CS1), + GRP_G("spis", spis_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_SPIS), + GRP_G("gpio", gpio_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_GPIO), + GRP_G("wled_an", wled_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_WLED_AN), + GRP_G("p0led_an", p0led_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P0LED_AN), + GRP_G("p1led_an", p1led_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P1LED_AN), + GRP_G("p2led_an", p2led_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P2LED_AN), + GRP_G("p3led_an", p3led_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P3LED_AN), + GRP_G("p4led_an", p4led_an_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P4LED_AN), + GRP_G("wled_kn", wled_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_WLED_KN), + GRP_G("p0led_kn", p0led_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P0LED_KN), + GRP_G("p1led_kn", p1led_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P1LED_KN), + GRP_G("p2led_kn", p2led_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P2LED_KN), + GRP_G("p3led_kn", p3led_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P3LED_KN), + GRP_G("p4led_kn", p4led_kn_grp, MT76X8_GPIO_MODE_MASK, + 1, MT76X8_GPIO_MODE_P4LED_KN), + { 0 } +}; + +static int mt76x8_pinctrl_probe(struct platform_device *pdev) +{ + return ralink_pinctrl_init(pdev, mt76x8_pinmux_data); +} + +static const struct of_device_id mt76x8_pinctrl_match[] = { + { .compatible = "ralink,mt76x8-pinctrl" }, + { .compatible = "ralink,mt7620-pinctrl" }, + { .compatible = "ralink,rt2880-pinmux" }, + {} +}; +MODULE_DEVICE_TABLE(of, mt76x8_pinctrl_match); + +static struct platform_driver mt76x8_pinctrl_driver = { + .probe = mt76x8_pinctrl_probe, + .driver = { + .name = "mt76x8-pinctrl", + .of_match_table = mt76x8_pinctrl_match, + }, +}; + +static int __init mt76x8_pinctrl_init(void) +{ + return platform_driver_register(&mt76x8_pinctrl_driver); +} +core_initcall_sync(mt76x8_pinctrl_init); -- GitLab From dc6ae2057c9cf24a4580e4c421a3cc16ade3ac21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:54 +0300 Subject: [PATCH 0879/5631] pinctrl: ralink: move to mediatek as mtmips MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This platform from Ralink was acquired by MediaTek in 2011. Then, MediaTek introduced new SoCs which utilise this platform. Move the driver to mediatek pinctrl directory. Rename the ralink core driver to mtmips. Signed-off-by: Arınç ÜNAL Link: https://lore.kernel.org/r/20230317213011.13656-5-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- drivers/pinctrl/Kconfig | 1 - drivers/pinctrl/Makefile | 1 - drivers/pinctrl/mediatek/Kconfig | 51 ++++++++++- drivers/pinctrl/mediatek/Makefile | 63 +++++++------ .../{ralink => mediatek}/pinctrl-mt7620.c | 34 +++---- .../{ralink => mediatek}/pinctrl-mt7621.c | 30 +++---- .../{ralink => mediatek}/pinctrl-mt76x8.c | 60 ++++++------- .../pinctrl-mtmips.c} | 90 +++++++++---------- .../pinctrl-mtmips.h} | 16 ++-- .../{ralink => mediatek}/pinctrl-rt2880.c | 20 ++--- .../{ralink => mediatek}/pinctrl-rt305x.c | 44 ++++----- .../{ralink => mediatek}/pinctrl-rt3883.c | 28 +++--- drivers/pinctrl/ralink/Kconfig | 40 --------- drivers/pinctrl/ralink/Makefile | 9 -- 14 files changed, 246 insertions(+), 241 deletions(-) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-mt7620.c (81%) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-mt7621.c (80%) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-mt76x8.c (81%) rename drivers/pinctrl/{ralink/pinctrl-ralink.c => mediatek/pinctrl-mtmips.c} (74%) rename drivers/pinctrl/{ralink/pinctrl-ralink.h => mediatek/pinctrl-mtmips.h} (75%) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-rt2880.c (71%) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-rt305x.c (75%) rename drivers/pinctrl/{ralink => mediatek}/pinctrl-rt3883.c (80%) delete mode 100644 drivers/pinctrl/ralink/Kconfig delete mode 100644 drivers/pinctrl/ralink/Makefile diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index 694f47fe6d11..e2a24d668e41 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -538,7 +538,6 @@ source "drivers/pinctrl/nuvoton/Kconfig" source "drivers/pinctrl/nxp/Kconfig" source "drivers/pinctrl/pxa/Kconfig" source "drivers/pinctrl/qcom/Kconfig" -source "drivers/pinctrl/ralink/Kconfig" source "drivers/pinctrl/renesas/Kconfig" source "drivers/pinctrl/samsung/Kconfig" source "drivers/pinctrl/spear/Kconfig" diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index c40397af024b..413b1e6b6933 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -67,7 +67,6 @@ obj-y += nuvoton/ obj-y += nxp/ obj-$(CONFIG_PINCTRL_PXA) += pxa/ obj-$(CONFIG_ARCH_QCOM) += qcom/ -obj-$(CONFIG_PINCTRL_RALINK) += ralink/ obj-$(CONFIG_PINCTRL_RENESAS) += renesas/ obj-$(CONFIG_PINCTRL_SAMSUNG) += samsung/ obj-$(CONFIG_PINCTRL_SPEAR) += spear/ diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index f20c28334bcb..ba21a599953c 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only menu "MediaTek pinctrl drivers" - depends on ARCH_MEDIATEK || COMPILE_TEST + depends on ARCH_MEDIATEK || RALINK || COMPILE_TEST config EINT_MTK tristate "MediaTek External Interrupt Support" @@ -22,6 +22,12 @@ config PINCTRL_MTK config PINCTRL_MTK_V2 tristate +config PINCTRL_MTK_MTMIPS + bool + depends on RALINK + select PINMUX + select GENERIC_PINCONF + config PINCTRL_MTK_MOORE bool depends on OF @@ -43,6 +49,49 @@ config PINCTRL_MTK_PARIS select OF_GPIO select PINCTRL_MTK_V2 +# For MIPS SoCs +config PINCTRL_MT7620 + bool "MediaTek MT7620 pin control" + depends on SOC_MT7620 || COMPILE_TEST + depends on RALINK + default SOC_MT7620 + select PINCTRL_MTK_MTMIPS + +config PINCTRL_MT7621 + bool "MediaTek MT7621 pin control" + depends on SOC_MT7621 || COMPILE_TEST + depends on RALINK + default SOC_MT7621 + select PINCTRL_MTK_MTMIPS + +config PINCTRL_MT76X8 + bool "MediaTek MT76X8 pin control" + depends on SOC_MT7620 || COMPILE_TEST + depends on RALINK + default SOC_MT7620 + select PINCTRL_MTK_MTMIPS + +config PINCTRL_RT2880 + bool "Ralink RT2880 pin control" + depends on SOC_RT288X || COMPILE_TEST + depends on RALINK + default SOC_RT288X + select PINCTRL_MTK_MTMIPS + +config PINCTRL_RT305X + bool "Ralink RT305X pin control" + depends on SOC_RT305X || COMPILE_TEST + depends on RALINK + default SOC_RT305X + select PINCTRL_MTK_MTMIPS + +config PINCTRL_RT3883 + bool "Ralink RT3883 pin control" + depends on SOC_RT3883 || COMPILE_TEST + depends on RALINK + default SOC_RT3883 + select PINCTRL_MTK_MTMIPS + # For ARMv7 SoCs config PINCTRL_MT2701 bool "Mediatek MT2701 pin control" diff --git a/drivers/pinctrl/mediatek/Makefile b/drivers/pinctrl/mediatek/Makefile index 44d197af516a..680f7e8526e0 100644 --- a/drivers/pinctrl/mediatek/Makefile +++ b/drivers/pinctrl/mediatek/Makefile @@ -1,32 +1,39 @@ # SPDX-License-Identifier: GPL-2.0 # Core -obj-$(CONFIG_EINT_MTK) += mtk-eint.o -obj-$(CONFIG_PINCTRL_MTK) += pinctrl-mtk-common.o -obj-$(CONFIG_PINCTRL_MTK_V2) += pinctrl-mtk-common-v2.o -obj-$(CONFIG_PINCTRL_MTK_MOORE) += pinctrl-moore.o -obj-$(CONFIG_PINCTRL_MTK_PARIS) += pinctrl-paris.o +obj-$(CONFIG_EINT_MTK) += mtk-eint.o +obj-$(CONFIG_PINCTRL_MTK) += pinctrl-mtk-common.o +obj-$(CONFIG_PINCTRL_MTK_V2) += pinctrl-mtk-common-v2.o +obj-$(CONFIG_PINCTRL_MTK_MTMIPS) += pinctrl-mtmips.o +obj-$(CONFIG_PINCTRL_MTK_MOORE) += pinctrl-moore.o +obj-$(CONFIG_PINCTRL_MTK_PARIS) += pinctrl-paris.o # SoC Drivers -obj-$(CONFIG_PINCTRL_MT2701) += pinctrl-mt2701.o -obj-$(CONFIG_PINCTRL_MT2712) += pinctrl-mt2712.o -obj-$(CONFIG_PINCTRL_MT8135) += pinctrl-mt8135.o -obj-$(CONFIG_PINCTRL_MT8127) += pinctrl-mt8127.o -obj-$(CONFIG_PINCTRL_MT6765) += pinctrl-mt6765.o -obj-$(CONFIG_PINCTRL_MT6779) += pinctrl-mt6779.o -obj-$(CONFIG_PINCTRL_MT6795) += pinctrl-mt6795.o -obj-$(CONFIG_PINCTRL_MT6797) += pinctrl-mt6797.o -obj-$(CONFIG_PINCTRL_MT7622) += pinctrl-mt7622.o -obj-$(CONFIG_PINCTRL_MT7623) += pinctrl-mt7623.o -obj-$(CONFIG_PINCTRL_MT7629) += pinctrl-mt7629.o -obj-$(CONFIG_PINCTRL_MT7981) += pinctrl-mt7981.o -obj-$(CONFIG_PINCTRL_MT7986) += pinctrl-mt7986.o -obj-$(CONFIG_PINCTRL_MT8167) += pinctrl-mt8167.o -obj-$(CONFIG_PINCTRL_MT8173) += pinctrl-mt8173.o -obj-$(CONFIG_PINCTRL_MT8183) += pinctrl-mt8183.o -obj-$(CONFIG_PINCTRL_MT8186) += pinctrl-mt8186.o -obj-$(CONFIG_PINCTRL_MT8188) += pinctrl-mt8188.o -obj-$(CONFIG_PINCTRL_MT8192) += pinctrl-mt8192.o -obj-$(CONFIG_PINCTRL_MT8195) += pinctrl-mt8195.o -obj-$(CONFIG_PINCTRL_MT8365) += pinctrl-mt8365.o -obj-$(CONFIG_PINCTRL_MT8516) += pinctrl-mt8516.o -obj-$(CONFIG_PINCTRL_MT6397) += pinctrl-mt6397.o +obj-$(CONFIG_PINCTRL_MT7620) += pinctrl-mt7620.o +obj-$(CONFIG_PINCTRL_MT7621) += pinctrl-mt7621.o +obj-$(CONFIG_PINCTRL_MT76X8) += pinctrl-mt76x8.o +obj-$(CONFIG_PINCTRL_RT2880) += pinctrl-rt2880.o +obj-$(CONFIG_PINCTRL_RT305X) += pinctrl-rt305x.o +obj-$(CONFIG_PINCTRL_RT3883) += pinctrl-rt3883.o +obj-$(CONFIG_PINCTRL_MT2701) += pinctrl-mt2701.o +obj-$(CONFIG_PINCTRL_MT2712) += pinctrl-mt2712.o +obj-$(CONFIG_PINCTRL_MT8135) += pinctrl-mt8135.o +obj-$(CONFIG_PINCTRL_MT8127) += pinctrl-mt8127.o +obj-$(CONFIG_PINCTRL_MT6765) += pinctrl-mt6765.o +obj-$(CONFIG_PINCTRL_MT6779) += pinctrl-mt6779.o +obj-$(CONFIG_PINCTRL_MT6795) += pinctrl-mt6795.o +obj-$(CONFIG_PINCTRL_MT6797) += pinctrl-mt6797.o +obj-$(CONFIG_PINCTRL_MT7622) += pinctrl-mt7622.o +obj-$(CONFIG_PINCTRL_MT7623) += pinctrl-mt7623.o +obj-$(CONFIG_PINCTRL_MT7629) += pinctrl-mt7629.o +obj-$(CONFIG_PINCTRL_MT7981) += pinctrl-mt7981.o +obj-$(CONFIG_PINCTRL_MT7986) += pinctrl-mt7986.o +obj-$(CONFIG_PINCTRL_MT8167) += pinctrl-mt8167.o +obj-$(CONFIG_PINCTRL_MT8173) += pinctrl-mt8173.o +obj-$(CONFIG_PINCTRL_MT8183) += pinctrl-mt8183.o +obj-$(CONFIG_PINCTRL_MT8186) += pinctrl-mt8186.o +obj-$(CONFIG_PINCTRL_MT8188) += pinctrl-mt8188.o +obj-$(CONFIG_PINCTRL_MT8192) += pinctrl-mt8192.o +obj-$(CONFIG_PINCTRL_MT8195) += pinctrl-mt8195.o +obj-$(CONFIG_PINCTRL_MT8365) += pinctrl-mt8365.o +obj-$(CONFIG_PINCTRL_MT8516) += pinctrl-mt8516.o +obj-$(CONFIG_PINCTRL_MT6397) += pinctrl-mt6397.o diff --git a/drivers/pinctrl/ralink/pinctrl-mt7620.c b/drivers/pinctrl/mediatek/pinctrl-mt7620.c similarity index 81% rename from drivers/pinctrl/ralink/pinctrl-mt7620.c rename to drivers/pinctrl/mediatek/pinctrl-mt7620.c index 3f6ffccc6882..d2624b9b5bc4 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt7620.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7620.c @@ -3,7 +3,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define MT7620_GPIO_MODE_UART0_SHIFT 2 #define MT7620_GPIO_MODE_UART0_MASK 0x7 @@ -52,20 +52,20 @@ #define MT7620_GPIO_MODE_EPHY 15 #define MT7620_GPIO_MODE_PA 20 -static struct ralink_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; -static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; -static struct ralink_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; -static struct ralink_pmx_func mdio_grp[] = { +static struct mtmips_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; +static struct mtmips_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; +static struct mtmips_pmx_func mdio_grp[] = { FUNC("mdio", MT7620_GPIO_MODE_MDIO, 22, 2), FUNC("refclk", MT7620_GPIO_MODE_MDIO_REFCLK, 22, 2), }; -static struct ralink_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 24, 12) }; -static struct ralink_pmx_func refclk_grp[] = { FUNC("spi refclk", 0, 37, 3) }; -static struct ralink_pmx_func ephy_grp[] = { FUNC("ephy", 0, 40, 5) }; -static struct ralink_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 60, 12) }; -static struct ralink_pmx_func wled_grp[] = { FUNC("wled", 0, 72, 1) }; -static struct ralink_pmx_func pa_grp[] = { FUNC("pa", 0, 18, 4) }; -static struct ralink_pmx_func uartf_grp[] = { +static struct mtmips_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 24, 12) }; +static struct mtmips_pmx_func refclk_grp[] = { FUNC("spi refclk", 0, 37, 3) }; +static struct mtmips_pmx_func ephy_grp[] = { FUNC("ephy", 0, 40, 5) }; +static struct mtmips_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 60, 12) }; +static struct mtmips_pmx_func wled_grp[] = { FUNC("wled", 0, 72, 1) }; +static struct mtmips_pmx_func pa_grp[] = { FUNC("pa", 0, 18, 4) }; +static struct mtmips_pmx_func uartf_grp[] = { FUNC("uartf", MT7620_GPIO_MODE_UARTF, 7, 8), FUNC("pcm uartf", MT7620_GPIO_MODE_PCM_UARTF, 7, 8), FUNC("pcm i2s", MT7620_GPIO_MODE_PCM_I2S, 7, 8), @@ -74,20 +74,20 @@ static struct ralink_pmx_func uartf_grp[] = { FUNC("gpio uartf", MT7620_GPIO_MODE_GPIO_UARTF, 7, 4), FUNC("gpio i2s", MT7620_GPIO_MODE_GPIO_I2S, 7, 4), }; -static struct ralink_pmx_func wdt_grp[] = { +static struct mtmips_pmx_func wdt_grp[] = { FUNC("wdt rst", 0, 17, 1), FUNC("wdt refclk", 0, 17, 1), }; -static struct ralink_pmx_func pcie_rst_grp[] = { +static struct mtmips_pmx_func pcie_rst_grp[] = { FUNC("pcie rst", MT7620_GPIO_MODE_PCIE_RST, 36, 1), FUNC("pcie refclk", MT7620_GPIO_MODE_PCIE_REF, 36, 1) }; -static struct ralink_pmx_func nd_sd_grp[] = { +static struct mtmips_pmx_func nd_sd_grp[] = { FUNC("nand", MT7620_GPIO_MODE_NAND, 45, 15), FUNC("sd", MT7620_GPIO_MODE_SD, 47, 13) }; -static struct ralink_pmx_group mt7620a_pinmux_data[] = { +static struct mtmips_pmx_group mt7620a_pinmux_data[] = { GRP("i2c", i2c_grp, 1, MT7620_GPIO_MODE_I2C), GRP("uartf", uartf_grp, MT7620_GPIO_MODE_UART0_MASK, MT7620_GPIO_MODE_UART0_SHIFT), @@ -112,7 +112,7 @@ static struct ralink_pmx_group mt7620a_pinmux_data[] = { static int mt7620_pinctrl_probe(struct platform_device *pdev) { - return ralink_pinctrl_init(pdev, mt7620a_pinmux_data); + return mtmips_pinctrl_init(pdev, mt7620a_pinmux_data); } static const struct of_device_id mt7620_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-mt7621.c b/drivers/pinctrl/mediatek/pinctrl-mt7621.c similarity index 80% rename from drivers/pinctrl/ralink/pinctrl-mt7621.c rename to drivers/pinctrl/mediatek/pinctrl-mt7621.c index fb5824922e78..b18c1a47bbeb 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt7621.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt7621.c @@ -3,7 +3,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define MT7621_GPIO_MODE_UART1 1 #define MT7621_GPIO_MODE_I2C 2 @@ -34,40 +34,40 @@ #define MT7621_GPIO_MODE_SDHCI_SHIFT 18 #define MT7621_GPIO_MODE_SDHCI_GPIO 1 -static struct ralink_pmx_func uart1_grp[] = { FUNC("uart1", 0, 1, 2) }; -static struct ralink_pmx_func i2c_grp[] = { FUNC("i2c", 0, 3, 2) }; -static struct ralink_pmx_func uart3_grp[] = { +static struct mtmips_pmx_func uart1_grp[] = { FUNC("uart1", 0, 1, 2) }; +static struct mtmips_pmx_func i2c_grp[] = { FUNC("i2c", 0, 3, 2) }; +static struct mtmips_pmx_func uart3_grp[] = { FUNC("uart3", 0, 5, 4), FUNC("i2s", 2, 5, 4), FUNC("spdif3", 3, 5, 4), }; -static struct ralink_pmx_func uart2_grp[] = { +static struct mtmips_pmx_func uart2_grp[] = { FUNC("uart2", 0, 9, 4), FUNC("pcm", 2, 9, 4), FUNC("spdif2", 3, 9, 4), }; -static struct ralink_pmx_func jtag_grp[] = { FUNC("jtag", 0, 13, 5) }; -static struct ralink_pmx_func wdt_grp[] = { +static struct mtmips_pmx_func jtag_grp[] = { FUNC("jtag", 0, 13, 5) }; +static struct mtmips_pmx_func wdt_grp[] = { FUNC("wdt rst", 0, 18, 1), FUNC("wdt refclk", 2, 18, 1), }; -static struct ralink_pmx_func pcie_rst_grp[] = { +static struct mtmips_pmx_func pcie_rst_grp[] = { FUNC("pcie rst", MT7621_GPIO_MODE_PCIE_RST, 19, 1), FUNC("pcie refclk", MT7621_GPIO_MODE_PCIE_REF, 19, 1) }; -static struct ralink_pmx_func mdio_grp[] = { FUNC("mdio", 0, 20, 2) }; -static struct ralink_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 22, 12) }; -static struct ralink_pmx_func spi_grp[] = { +static struct mtmips_pmx_func mdio_grp[] = { FUNC("mdio", 0, 20, 2) }; +static struct mtmips_pmx_func rgmii2_grp[] = { FUNC("rgmii2", 0, 22, 12) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 34, 7), FUNC("nand1", 2, 34, 7), }; -static struct ralink_pmx_func sdhci_grp[] = { +static struct mtmips_pmx_func sdhci_grp[] = { FUNC("sdhci", 0, 41, 8), FUNC("nand2", 2, 41, 8), }; -static struct ralink_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 49, 12) }; +static struct mtmips_pmx_func rgmii1_grp[] = { FUNC("rgmii1", 0, 49, 12) }; -static struct ralink_pmx_group mt7621_pinmux_data[] = { +static struct mtmips_pmx_group mt7621_pinmux_data[] = { GRP("uart1", uart1_grp, 1, MT7621_GPIO_MODE_UART1), GRP("i2c", i2c_grp, 1, MT7621_GPIO_MODE_I2C), GRP_G("uart3", uart3_grp, MT7621_GPIO_MODE_UART3_MASK, @@ -92,7 +92,7 @@ static struct ralink_pmx_group mt7621_pinmux_data[] = { static int mt7621_pinctrl_probe(struct platform_device *pdev) { - return ralink_pinctrl_init(pdev, mt7621_pinmux_data); + return mtmips_pinctrl_init(pdev, mt7621_pinmux_data); } static const struct of_device_id mt7621_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-mt76x8.c b/drivers/pinctrl/mediatek/pinctrl-mt76x8.c similarity index 81% rename from drivers/pinctrl/ralink/pinctrl-mt76x8.c rename to drivers/pinctrl/mediatek/pinctrl-mt76x8.c index 4283a54d2db0..e7d6ad2f62e4 100644 --- a/drivers/pinctrl/ralink/pinctrl-mt76x8.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt76x8.c @@ -3,7 +3,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define MT76X8_GPIO_MODE_MASK 0x3 @@ -35,173 +35,173 @@ #define MT76X8_GPIO_MODE_SPIS 2 #define MT76X8_GPIO_MODE_GPIO 0 -static struct ralink_pmx_func pwm1_grp[] = { +static struct mtmips_pmx_func pwm1_grp[] = { FUNC("sdxc d6", 3, 19, 1), FUNC("utif", 2, 19, 1), FUNC("gpio", 1, 19, 1), FUNC("pwm1", 0, 19, 1), }; -static struct ralink_pmx_func pwm0_grp[] = { +static struct mtmips_pmx_func pwm0_grp[] = { FUNC("sdxc d7", 3, 18, 1), FUNC("utif", 2, 18, 1), FUNC("gpio", 1, 18, 1), FUNC("pwm0", 0, 18, 1), }; -static struct ralink_pmx_func uart2_grp[] = { +static struct mtmips_pmx_func uart2_grp[] = { FUNC("sdxc d5 d4", 3, 20, 2), FUNC("pwm", 2, 20, 2), FUNC("gpio", 1, 20, 2), FUNC("uart2", 0, 20, 2), }; -static struct ralink_pmx_func uart1_grp[] = { +static struct mtmips_pmx_func uart1_grp[] = { FUNC("sw_r", 3, 45, 2), FUNC("pwm", 2, 45, 2), FUNC("gpio", 1, 45, 2), FUNC("uart1", 0, 45, 2), }; -static struct ralink_pmx_func i2c_grp[] = { +static struct mtmips_pmx_func i2c_grp[] = { FUNC("-", 3, 4, 2), FUNC("debug", 2, 4, 2), FUNC("gpio", 1, 4, 2), FUNC("i2c", 0, 4, 2), }; -static struct ralink_pmx_func refclk_grp[] = { FUNC("refclk", 0, 37, 1) }; -static struct ralink_pmx_func perst_grp[] = { FUNC("perst", 0, 36, 1) }; -static struct ralink_pmx_func wdt_grp[] = { FUNC("wdt", 0, 38, 1) }; -static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 7, 4) }; +static struct mtmips_pmx_func refclk_grp[] = { FUNC("refclk", 0, 37, 1) }; +static struct mtmips_pmx_func perst_grp[] = { FUNC("perst", 0, 36, 1) }; +static struct mtmips_pmx_func wdt_grp[] = { FUNC("wdt", 0, 38, 1) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 7, 4) }; -static struct ralink_pmx_func sd_mode_grp[] = { +static struct mtmips_pmx_func sd_mode_grp[] = { FUNC("jtag", 3, 22, 8), FUNC("utif", 2, 22, 8), FUNC("gpio", 1, 22, 8), FUNC("sdxc", 0, 22, 8), }; -static struct ralink_pmx_func uart0_grp[] = { +static struct mtmips_pmx_func uart0_grp[] = { FUNC("-", 3, 12, 2), FUNC("-", 2, 12, 2), FUNC("gpio", 1, 12, 2), FUNC("uart0", 0, 12, 2), }; -static struct ralink_pmx_func i2s_grp[] = { +static struct mtmips_pmx_func i2s_grp[] = { FUNC("antenna", 3, 0, 4), FUNC("pcm", 2, 0, 4), FUNC("gpio", 1, 0, 4), FUNC("i2s", 0, 0, 4), }; -static struct ralink_pmx_func spi_cs1_grp[] = { +static struct mtmips_pmx_func spi_cs1_grp[] = { FUNC("-", 3, 6, 1), FUNC("refclk", 2, 6, 1), FUNC("gpio", 1, 6, 1), FUNC("spi cs1", 0, 6, 1), }; -static struct ralink_pmx_func spis_grp[] = { +static struct mtmips_pmx_func spis_grp[] = { FUNC("pwm_uart2", 3, 14, 4), FUNC("utif", 2, 14, 4), FUNC("gpio", 1, 14, 4), FUNC("spis", 0, 14, 4), }; -static struct ralink_pmx_func gpio_grp[] = { +static struct mtmips_pmx_func gpio_grp[] = { FUNC("pcie", 3, 11, 1), FUNC("refclk", 2, 11, 1), FUNC("gpio", 1, 11, 1), FUNC("gpio", 0, 11, 1), }; -static struct ralink_pmx_func p4led_kn_grp[] = { +static struct mtmips_pmx_func p4led_kn_grp[] = { FUNC("jtag", 3, 30, 1), FUNC("utif", 2, 30, 1), FUNC("gpio", 1, 30, 1), FUNC("p4led_kn", 0, 30, 1), }; -static struct ralink_pmx_func p3led_kn_grp[] = { +static struct mtmips_pmx_func p3led_kn_grp[] = { FUNC("jtag", 3, 31, 1), FUNC("utif", 2, 31, 1), FUNC("gpio", 1, 31, 1), FUNC("p3led_kn", 0, 31, 1), }; -static struct ralink_pmx_func p2led_kn_grp[] = { +static struct mtmips_pmx_func p2led_kn_grp[] = { FUNC("jtag", 3, 32, 1), FUNC("utif", 2, 32, 1), FUNC("gpio", 1, 32, 1), FUNC("p2led_kn", 0, 32, 1), }; -static struct ralink_pmx_func p1led_kn_grp[] = { +static struct mtmips_pmx_func p1led_kn_grp[] = { FUNC("jtag", 3, 33, 1), FUNC("utif", 2, 33, 1), FUNC("gpio", 1, 33, 1), FUNC("p1led_kn", 0, 33, 1), }; -static struct ralink_pmx_func p0led_kn_grp[] = { +static struct mtmips_pmx_func p0led_kn_grp[] = { FUNC("jtag", 3, 34, 1), FUNC("rsvd", 2, 34, 1), FUNC("gpio", 1, 34, 1), FUNC("p0led_kn", 0, 34, 1), }; -static struct ralink_pmx_func wled_kn_grp[] = { +static struct mtmips_pmx_func wled_kn_grp[] = { FUNC("rsvd", 3, 35, 1), FUNC("rsvd", 2, 35, 1), FUNC("gpio", 1, 35, 1), FUNC("wled_kn", 0, 35, 1), }; -static struct ralink_pmx_func p4led_an_grp[] = { +static struct mtmips_pmx_func p4led_an_grp[] = { FUNC("jtag", 3, 39, 1), FUNC("utif", 2, 39, 1), FUNC("gpio", 1, 39, 1), FUNC("p4led_an", 0, 39, 1), }; -static struct ralink_pmx_func p3led_an_grp[] = { +static struct mtmips_pmx_func p3led_an_grp[] = { FUNC("jtag", 3, 40, 1), FUNC("utif", 2, 40, 1), FUNC("gpio", 1, 40, 1), FUNC("p3led_an", 0, 40, 1), }; -static struct ralink_pmx_func p2led_an_grp[] = { +static struct mtmips_pmx_func p2led_an_grp[] = { FUNC("jtag", 3, 41, 1), FUNC("utif", 2, 41, 1), FUNC("gpio", 1, 41, 1), FUNC("p2led_an", 0, 41, 1), }; -static struct ralink_pmx_func p1led_an_grp[] = { +static struct mtmips_pmx_func p1led_an_grp[] = { FUNC("jtag", 3, 42, 1), FUNC("utif", 2, 42, 1), FUNC("gpio", 1, 42, 1), FUNC("p1led_an", 0, 42, 1), }; -static struct ralink_pmx_func p0led_an_grp[] = { +static struct mtmips_pmx_func p0led_an_grp[] = { FUNC("jtag", 3, 43, 1), FUNC("rsvd", 2, 43, 1), FUNC("gpio", 1, 43, 1), FUNC("p0led_an", 0, 43, 1), }; -static struct ralink_pmx_func wled_an_grp[] = { +static struct mtmips_pmx_func wled_an_grp[] = { FUNC("rsvd", 3, 44, 1), FUNC("rsvd", 2, 44, 1), FUNC("gpio", 1, 44, 1), FUNC("wled_an", 0, 44, 1), }; -static struct ralink_pmx_group mt76x8_pinmux_data[] = { +static struct mtmips_pmx_group mt76x8_pinmux_data[] = { GRP_G("pwm1", pwm1_grp, MT76X8_GPIO_MODE_MASK, 1, MT76X8_GPIO_MODE_PWM1), GRP_G("pwm0", pwm0_grp, MT76X8_GPIO_MODE_MASK, @@ -257,7 +257,7 @@ static struct ralink_pmx_group mt76x8_pinmux_data[] = { static int mt76x8_pinctrl_probe(struct platform_device *pdev) { - return ralink_pinctrl_init(pdev, mt76x8_pinmux_data); + return mtmips_pinctrl_init(pdev, mt76x8_pinmux_data); } static const struct of_device_id mt76x8_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-ralink.c b/drivers/pinctrl/mediatek/pinctrl-mtmips.c similarity index 74% rename from drivers/pinctrl/ralink/pinctrl-ralink.c rename to drivers/pinctrl/mediatek/pinctrl-mtmips.c index 770862f45b3f..efd77b6c56a1 100644 --- a/drivers/pinctrl/ralink/pinctrl-ralink.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtmips.c @@ -19,23 +19,23 @@ #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #include "../core.h" #include "../pinctrl-utils.h" #define SYSC_REG_GPIO_MODE 0x60 #define SYSC_REG_GPIO_MODE2 0x64 -struct ralink_priv { +struct mtmips_priv { struct device *dev; struct pinctrl_pin_desc *pads; struct pinctrl_desc *desc; - struct ralink_pmx_func **func; + struct mtmips_pmx_func **func; int func_count; - struct ralink_pmx_group *groups; + struct mtmips_pmx_group *groups; const char **group_names; int group_count; @@ -43,27 +43,27 @@ struct ralink_priv { int max_pins; }; -static int ralink_get_group_count(struct pinctrl_dev *pctrldev) +static int mtmips_get_group_count(struct pinctrl_dev *pctrldev) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); return p->group_count; } -static const char *ralink_get_group_name(struct pinctrl_dev *pctrldev, +static const char *mtmips_get_group_name(struct pinctrl_dev *pctrldev, unsigned int group) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); return (group >= p->group_count) ? NULL : p->group_names[group]; } -static int ralink_get_group_pins(struct pinctrl_dev *pctrldev, +static int mtmips_get_group_pins(struct pinctrl_dev *pctrldev, unsigned int group, const unsigned int **pins, unsigned int *num_pins) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); if (group >= p->group_count) return -EINVAL; @@ -74,35 +74,35 @@ static int ralink_get_group_pins(struct pinctrl_dev *pctrldev, return 0; } -static const struct pinctrl_ops ralink_pctrl_ops = { - .get_groups_count = ralink_get_group_count, - .get_group_name = ralink_get_group_name, - .get_group_pins = ralink_get_group_pins, +static const struct pinctrl_ops mtmips_pctrl_ops = { + .get_groups_count = mtmips_get_group_count, + .get_group_name = mtmips_get_group_name, + .get_group_pins = mtmips_get_group_pins, .dt_node_to_map = pinconf_generic_dt_node_to_map_all, .dt_free_map = pinconf_generic_dt_free_map, }; -static int ralink_pmx_func_count(struct pinctrl_dev *pctrldev) +static int mtmips_pmx_func_count(struct pinctrl_dev *pctrldev) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); return p->func_count; } -static const char *ralink_pmx_func_name(struct pinctrl_dev *pctrldev, +static const char *mtmips_pmx_func_name(struct pinctrl_dev *pctrldev, unsigned int func) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); return p->func[func]->name; } -static int ralink_pmx_group_get_groups(struct pinctrl_dev *pctrldev, +static int mtmips_pmx_group_get_groups(struct pinctrl_dev *pctrldev, unsigned int func, const char * const **groups, unsigned int * const num_groups) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); if (p->func[func]->group_count == 1) *groups = &p->group_names[p->func[func]->groups[0]]; @@ -114,10 +114,10 @@ static int ralink_pmx_group_get_groups(struct pinctrl_dev *pctrldev, return 0; } -static int ralink_pmx_group_enable(struct pinctrl_dev *pctrldev, +static int mtmips_pmx_group_enable(struct pinctrl_dev *pctrldev, unsigned int func, unsigned int group) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); u32 mode = 0; u32 reg = SYSC_REG_GPIO_MODE; int i; @@ -158,11 +158,11 @@ static int ralink_pmx_group_enable(struct pinctrl_dev *pctrldev, return 0; } -static int ralink_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev, +static int mtmips_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev, struct pinctrl_gpio_range *range, unsigned int pin) { - struct ralink_priv *p = pinctrl_dev_get_drvdata(pctrldev); + struct mtmips_priv *p = pinctrl_dev_get_drvdata(pctrldev); if (!p->gpio[pin]) { dev_err(p->dev, "pin %d is not set to gpio mux\n", pin); @@ -172,28 +172,28 @@ static int ralink_pmx_group_gpio_request_enable(struct pinctrl_dev *pctrldev, return 0; } -static const struct pinmux_ops ralink_pmx_group_ops = { - .get_functions_count = ralink_pmx_func_count, - .get_function_name = ralink_pmx_func_name, - .get_function_groups = ralink_pmx_group_get_groups, - .set_mux = ralink_pmx_group_enable, - .gpio_request_enable = ralink_pmx_group_gpio_request_enable, +static const struct pinmux_ops mtmips_pmx_group_ops = { + .get_functions_count = mtmips_pmx_func_count, + .get_function_name = mtmips_pmx_func_name, + .get_function_groups = mtmips_pmx_group_get_groups, + .set_mux = mtmips_pmx_group_enable, + .gpio_request_enable = mtmips_pmx_group_gpio_request_enable, }; -static struct pinctrl_desc ralink_pctrl_desc = { +static struct pinctrl_desc mtmips_pctrl_desc = { .owner = THIS_MODULE, - .name = "ralink-pinctrl", - .pctlops = &ralink_pctrl_ops, - .pmxops = &ralink_pmx_group_ops, + .name = "mtmips-pinctrl", + .pctlops = &mtmips_pctrl_ops, + .pmxops = &mtmips_pmx_group_ops, }; -static struct ralink_pmx_func gpio_func = { +static struct mtmips_pmx_func gpio_func = { .name = "gpio", }; -static int ralink_pinctrl_index(struct ralink_priv *p) +static int mtmips_pinctrl_index(struct mtmips_priv *p) { - struct ralink_pmx_group *mux = p->groups; + struct mtmips_pmx_group *mux = p->groups; int i, j, c = 0; /* count the mux functions */ @@ -248,7 +248,7 @@ static int ralink_pinctrl_index(struct ralink_priv *p) return 0; } -static int ralink_pinctrl_pins(struct ralink_priv *p) +static int mtmips_pinctrl_pins(struct mtmips_priv *p) { int i, j; @@ -313,10 +313,10 @@ static int ralink_pinctrl_pins(struct ralink_priv *p) return 0; } -int ralink_pinctrl_init(struct platform_device *pdev, - struct ralink_pmx_group *data) +int mtmips_pinctrl_init(struct platform_device *pdev, + struct mtmips_pmx_group *data) { - struct ralink_priv *p; + struct mtmips_priv *p; struct pinctrl_dev *dev; int err; @@ -324,23 +324,23 @@ int ralink_pinctrl_init(struct platform_device *pdev, return -ENOTSUPP; /* setup the private data */ - p = devm_kzalloc(&pdev->dev, sizeof(struct ralink_priv), GFP_KERNEL); + p = devm_kzalloc(&pdev->dev, sizeof(struct mtmips_priv), GFP_KERNEL); if (!p) return -ENOMEM; p->dev = &pdev->dev; - p->desc = &ralink_pctrl_desc; + p->desc = &mtmips_pctrl_desc; p->groups = data; platform_set_drvdata(pdev, p); /* init the device */ - err = ralink_pinctrl_index(p); + err = mtmips_pinctrl_index(p); if (err) { dev_err(&pdev->dev, "failed to load index\n"); return err; } - err = ralink_pinctrl_pins(p); + err = mtmips_pinctrl_pins(p); if (err) { dev_err(&pdev->dev, "failed to load pins\n"); return err; diff --git a/drivers/pinctrl/ralink/pinctrl-ralink.h b/drivers/pinctrl/mediatek/pinctrl-mtmips.h similarity index 75% rename from drivers/pinctrl/ralink/pinctrl-ralink.h rename to drivers/pinctrl/mediatek/pinctrl-mtmips.h index e6037be1e153..a7c3dd724431 100644 --- a/drivers/pinctrl/ralink/pinctrl-ralink.h +++ b/drivers/pinctrl/mediatek/pinctrl-mtmips.h @@ -3,8 +3,8 @@ * Copyright (C) 2012 John Crispin */ -#ifndef _PINCTRL_RALINK_H__ -#define _PINCTRL_RALINK_H__ +#ifndef _PINCTRL_MTMIPS_H__ +#define _PINCTRL_MTMIPS_H__ #define FUNC(name, value, pin_first, pin_count) \ { name, value, pin_first, pin_count } @@ -19,9 +19,9 @@ .func = _func, .gpio = _gpio, \ .func_count = ARRAY_SIZE(_func) } -struct ralink_pmx_group; +struct mtmips_pmx_group; -struct ralink_pmx_func { +struct mtmips_pmx_func { const char *name; const char value; @@ -35,7 +35,7 @@ struct ralink_pmx_func { int enabled; }; -struct ralink_pmx_group { +struct mtmips_pmx_group { const char *name; int enabled; @@ -43,11 +43,11 @@ struct ralink_pmx_group { const char mask; const char gpio; - struct ralink_pmx_func *func; + struct mtmips_pmx_func *func; int func_count; }; -int ralink_pinctrl_init(struct platform_device *pdev, - struct ralink_pmx_group *data); +int mtmips_pinctrl_init(struct platform_device *pdev, + struct mtmips_pmx_group *data); #endif diff --git a/drivers/pinctrl/ralink/pinctrl-rt2880.c b/drivers/pinctrl/mediatek/pinctrl-rt2880.c similarity index 71% rename from drivers/pinctrl/ralink/pinctrl-rt2880.c rename to drivers/pinctrl/mediatek/pinctrl-rt2880.c index d7a65fcc7755..e0366721a515 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt2880.c +++ b/drivers/pinctrl/mediatek/pinctrl-rt2880.c @@ -4,7 +4,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define RT2880_GPIO_MODE_I2C BIT(0) #define RT2880_GPIO_MODE_UART0 BIT(1) @@ -15,15 +15,15 @@ #define RT2880_GPIO_MODE_SDRAM BIT(6) #define RT2880_GPIO_MODE_PCI BIT(7) -static struct ralink_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; -static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; -static struct ralink_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 7, 8) }; -static struct ralink_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; -static struct ralink_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; -static struct ralink_pmx_func sdram_grp[] = { FUNC("sdram", 0, 24, 16) }; -static struct ralink_pmx_func pci_grp[] = { FUNC("pci", 0, 40, 32) }; +static struct mtmips_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; +static struct mtmips_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 7, 8) }; +static struct mtmips_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; +static struct mtmips_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; +static struct mtmips_pmx_func sdram_grp[] = { FUNC("sdram", 0, 24, 16) }; +static struct mtmips_pmx_func pci_grp[] = { FUNC("pci", 0, 40, 32) }; -static struct ralink_pmx_group rt2880_pinmux_data_act[] = { +static struct mtmips_pmx_group rt2880_pinmux_data_act[] = { GRP("i2c", i2c_grp, 1, RT2880_GPIO_MODE_I2C), GRP("spi", spi_grp, 1, RT2880_GPIO_MODE_SPI), GRP("uartlite", uartlite_grp, 1, RT2880_GPIO_MODE_UART0), @@ -36,7 +36,7 @@ static struct ralink_pmx_group rt2880_pinmux_data_act[] = { static int rt2880_pinctrl_probe(struct platform_device *pdev) { - return ralink_pinctrl_init(pdev, rt2880_pinmux_data_act); + return mtmips_pinctrl_init(pdev, rt2880_pinmux_data_act); } static const struct of_device_id rt2880_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/pinctrl-rt305x.c b/drivers/pinctrl/mediatek/pinctrl-rt305x.c similarity index 75% rename from drivers/pinctrl/ralink/pinctrl-rt305x.c rename to drivers/pinctrl/mediatek/pinctrl-rt305x.c index fa3743c7680f..77bd4d1f6122 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt305x.c +++ b/drivers/pinctrl/mediatek/pinctrl-rt305x.c @@ -5,7 +5,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define RT305X_GPIO_MODE_UART0_SHIFT 2 #define RT305X_GPIO_MODE_UART0_MASK 0x7 @@ -31,9 +31,9 @@ #define RT3352_GPIO_MODE_LNA 18 #define RT3352_GPIO_MODE_PA 20 -static struct ralink_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; -static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; -static struct ralink_pmx_func uartf_grp[] = { +static struct mtmips_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; +static struct mtmips_pmx_func uartf_grp[] = { FUNC("uartf", RT305X_GPIO_MODE_UARTF, 7, 8), FUNC("pcm uartf", RT305X_GPIO_MODE_PCM_UARTF, 7, 8), FUNC("pcm i2s", RT305X_GPIO_MODE_PCM_I2S, 7, 8), @@ -42,28 +42,28 @@ static struct ralink_pmx_func uartf_grp[] = { FUNC("gpio uartf", RT305X_GPIO_MODE_GPIO_UARTF, 7, 4), FUNC("gpio i2s", RT305X_GPIO_MODE_GPIO_I2S, 7, 4), }; -static struct ralink_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; -static struct ralink_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; -static struct ralink_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; -static struct ralink_pmx_func rt5350_led_grp[] = { FUNC("led", 0, 22, 5) }; -static struct ralink_pmx_func rt5350_cs1_grp[] = { +static struct mtmips_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; +static struct mtmips_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; +static struct mtmips_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; +static struct mtmips_pmx_func rt5350_led_grp[] = { FUNC("led", 0, 22, 5) }; +static struct mtmips_pmx_func rt5350_cs1_grp[] = { FUNC("spi_cs1", 0, 27, 1), FUNC("wdg_cs1", 1, 27, 1), }; -static struct ralink_pmx_func sdram_grp[] = { FUNC("sdram", 0, 24, 16) }; -static struct ralink_pmx_func rt3352_rgmii_grp[] = { +static struct mtmips_pmx_func sdram_grp[] = { FUNC("sdram", 0, 24, 16) }; +static struct mtmips_pmx_func rt3352_rgmii_grp[] = { FUNC("rgmii", 0, 24, 12) }; -static struct ralink_pmx_func rgmii_grp[] = { FUNC("rgmii", 0, 40, 12) }; -static struct ralink_pmx_func rt3352_lna_grp[] = { FUNC("lna", 0, 36, 2) }; -static struct ralink_pmx_func rt3352_pa_grp[] = { FUNC("pa", 0, 38, 2) }; -static struct ralink_pmx_func rt3352_led_grp[] = { FUNC("led", 0, 40, 5) }; -static struct ralink_pmx_func rt3352_cs1_grp[] = { +static struct mtmips_pmx_func rgmii_grp[] = { FUNC("rgmii", 0, 40, 12) }; +static struct mtmips_pmx_func rt3352_lna_grp[] = { FUNC("lna", 0, 36, 2) }; +static struct mtmips_pmx_func rt3352_pa_grp[] = { FUNC("pa", 0, 38, 2) }; +static struct mtmips_pmx_func rt3352_led_grp[] = { FUNC("led", 0, 40, 5) }; +static struct mtmips_pmx_func rt3352_cs1_grp[] = { FUNC("spi_cs1", 0, 45, 1), FUNC("wdg_cs1", 1, 45, 1), }; -static struct ralink_pmx_group rt3050_pinmux_data[] = { +static struct mtmips_pmx_group rt3050_pinmux_data[] = { GRP("i2c", i2c_grp, 1, RT305X_GPIO_MODE_I2C), GRP("spi", spi_grp, 1, RT305X_GPIO_MODE_SPI), GRP("uartf", uartf_grp, RT305X_GPIO_MODE_UART0_MASK, @@ -76,7 +76,7 @@ static struct ralink_pmx_group rt3050_pinmux_data[] = { { 0 } }; -static struct ralink_pmx_group rt3352_pinmux_data[] = { +static struct mtmips_pmx_group rt3352_pinmux_data[] = { GRP("i2c", i2c_grp, 1, RT305X_GPIO_MODE_I2C), GRP("spi", spi_grp, 1, RT305X_GPIO_MODE_SPI), GRP("uartf", uartf_grp, RT305X_GPIO_MODE_UART0_MASK, @@ -92,7 +92,7 @@ static struct ralink_pmx_group rt3352_pinmux_data[] = { { 0 } }; -static struct ralink_pmx_group rt5350_pinmux_data[] = { +static struct mtmips_pmx_group rt5350_pinmux_data[] = { GRP("i2c", i2c_grp, 1, RT305X_GPIO_MODE_I2C), GRP("spi", spi_grp, 1, RT305X_GPIO_MODE_SPI), GRP("uartf", uartf_grp, RT305X_GPIO_MODE_UART0_MASK, @@ -107,11 +107,11 @@ static struct ralink_pmx_group rt5350_pinmux_data[] = { static int rt305x_pinctrl_probe(struct platform_device *pdev) { if (soc_is_rt5350()) - return ralink_pinctrl_init(pdev, rt5350_pinmux_data); + return mtmips_pinctrl_init(pdev, rt5350_pinmux_data); else if (soc_is_rt305x() || soc_is_rt3350()) - return ralink_pinctrl_init(pdev, rt3050_pinmux_data); + return mtmips_pinctrl_init(pdev, rt3050_pinmux_data); else if (soc_is_rt3352()) - return ralink_pinctrl_init(pdev, rt3352_pinmux_data); + return mtmips_pinctrl_init(pdev, rt3352_pinmux_data); else return -EINVAL; } diff --git a/drivers/pinctrl/ralink/pinctrl-rt3883.c b/drivers/pinctrl/mediatek/pinctrl-rt3883.c similarity index 80% rename from drivers/pinctrl/ralink/pinctrl-rt3883.c rename to drivers/pinctrl/mediatek/pinctrl-rt3883.c index 5f766d76bafa..eeaf344c3647 100644 --- a/drivers/pinctrl/ralink/pinctrl-rt3883.c +++ b/drivers/pinctrl/mediatek/pinctrl-rt3883.c @@ -3,7 +3,7 @@ #include #include #include -#include "pinctrl-ralink.h" +#include "pinctrl-mtmips.h" #define RT3883_GPIO_MODE_UART0_SHIFT 2 #define RT3883_GPIO_MODE_UART0_MASK 0x7 @@ -39,9 +39,9 @@ #define RT3883_GPIO_MODE_LNA_G_GPIO 0x3 #define RT3883_GPIO_MODE_LNA_G _RT3883_GPIO_MODE_LNA_G(RT3883_GPIO_MODE_LNA_G_MASK) -static struct ralink_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; -static struct ralink_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; -static struct ralink_pmx_func uartf_grp[] = { +static struct mtmips_pmx_func i2c_grp[] = { FUNC("i2c", 0, 1, 2) }; +static struct mtmips_pmx_func spi_grp[] = { FUNC("spi", 0, 3, 4) }; +static struct mtmips_pmx_func uartf_grp[] = { FUNC("uartf", RT3883_GPIO_MODE_UARTF, 7, 8), FUNC("pcm uartf", RT3883_GPIO_MODE_PCM_UARTF, 7, 8), FUNC("pcm i2s", RT3883_GPIO_MODE_PCM_I2S, 7, 8), @@ -50,21 +50,21 @@ static struct ralink_pmx_func uartf_grp[] = { FUNC("gpio uartf", RT3883_GPIO_MODE_GPIO_UARTF, 7, 4), FUNC("gpio i2s", RT3883_GPIO_MODE_GPIO_I2S, 7, 4), }; -static struct ralink_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; -static struct ralink_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; -static struct ralink_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; -static struct ralink_pmx_func lna_a_grp[] = { FUNC("lna a", 0, 32, 3) }; -static struct ralink_pmx_func lna_g_grp[] = { FUNC("lna g", 0, 35, 3) }; -static struct ralink_pmx_func pci_grp[] = { +static struct mtmips_pmx_func uartlite_grp[] = { FUNC("uartlite", 0, 15, 2) }; +static struct mtmips_pmx_func jtag_grp[] = { FUNC("jtag", 0, 17, 5) }; +static struct mtmips_pmx_func mdio_grp[] = { FUNC("mdio", 0, 22, 2) }; +static struct mtmips_pmx_func lna_a_grp[] = { FUNC("lna a", 0, 32, 3) }; +static struct mtmips_pmx_func lna_g_grp[] = { FUNC("lna g", 0, 35, 3) }; +static struct mtmips_pmx_func pci_grp[] = { FUNC("pci-dev", 0, 40, 32), FUNC("pci-host2", 1, 40, 32), FUNC("pci-host1", 2, 40, 32), FUNC("pci-fnc", 3, 40, 32) }; -static struct ralink_pmx_func ge1_grp[] = { FUNC("ge1", 0, 72, 12) }; -static struct ralink_pmx_func ge2_grp[] = { FUNC("ge2", 0, 84, 12) }; +static struct mtmips_pmx_func ge1_grp[] = { FUNC("ge1", 0, 72, 12) }; +static struct mtmips_pmx_func ge2_grp[] = { FUNC("ge2", 0, 84, 12) }; -static struct ralink_pmx_group rt3883_pinmux_data[] = { +static struct mtmips_pmx_group rt3883_pinmux_data[] = { GRP("i2c", i2c_grp, 1, RT3883_GPIO_MODE_I2C), GRP("spi", spi_grp, 1, RT3883_GPIO_MODE_SPI), GRP("uartf", uartf_grp, RT3883_GPIO_MODE_UART0_MASK, @@ -83,7 +83,7 @@ static struct ralink_pmx_group rt3883_pinmux_data[] = { static int rt3883_pinctrl_probe(struct platform_device *pdev) { - return ralink_pinctrl_init(pdev, rt3883_pinmux_data); + return mtmips_pinctrl_init(pdev, rt3883_pinmux_data); } static const struct of_device_id rt3883_pinctrl_match[] = { diff --git a/drivers/pinctrl/ralink/Kconfig b/drivers/pinctrl/ralink/Kconfig deleted file mode 100644 index c5fe4c31aaea..000000000000 --- a/drivers/pinctrl/ralink/Kconfig +++ /dev/null @@ -1,40 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -menu "Ralink pinctrl drivers" - depends on RALINK - -config PINCTRL_RALINK - bool "Ralink pinctrl driver" - select PINMUX - select GENERIC_PINCONF - -config PINCTRL_MT7620 - bool "MT7620 pinctrl subdriver" - depends on RALINK && SOC_MT7620 - select PINCTRL_RALINK - -config PINCTRL_MT7621 - bool "MT7621 pinctrl subdriver" - depends on RALINK && SOC_MT7621 - select PINCTRL_RALINK - -config PINCTRL_MT76X8 - bool "MT76X8 pinctrl subdriver" - depends on RALINK && SOC_MT7620 - select PINCTRL_RALINK - -config PINCTRL_RT2880 - bool "RT2880 pinctrl subdriver" - depends on RALINK && SOC_RT288X - select PINCTRL_RALINK - -config PINCTRL_RT305X - bool "RT305X pinctrl subdriver" - depends on RALINK && SOC_RT305X - select PINCTRL_RALINK - -config PINCTRL_RT3883 - bool "RT3883 pinctrl subdriver" - depends on RALINK && SOC_RT3883 - select PINCTRL_RALINK - -endmenu diff --git a/drivers/pinctrl/ralink/Makefile b/drivers/pinctrl/ralink/Makefile deleted file mode 100644 index be9acf2e27fd..000000000000 --- a/drivers/pinctrl/ralink/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_PINCTRL_RALINK) += pinctrl-ralink.o - -obj-$(CONFIG_PINCTRL_MT7620) += pinctrl-mt7620.o -obj-$(CONFIG_PINCTRL_MT7621) += pinctrl-mt7621.o -obj-$(CONFIG_PINCTRL_MT76X8) += pinctrl-mt76x8.o -obj-$(CONFIG_PINCTRL_RT2880) += pinctrl-rt2880.o -obj-$(CONFIG_PINCTRL_RT305X) += pinctrl-rt305x.o -obj-$(CONFIG_PINCTRL_RT3883) += pinctrl-rt3883.o -- GitLab From ea183c37312334f4d93908e0fee0835e3a441ca3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:55 +0300 Subject: [PATCH 0880/5631] pinctrl: mediatek: remove OF_GPIO as reverse dependency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The OF_GPIO option is enabled by default when GPIOLIB is enabled, and cannot be disabled. Remove it as a reverse dependency where GPIOLIB is also set as a reverse dependency. Signed-off-by: Arınç ÜNAL Reviewed-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230317213011.13656-6-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- drivers/pinctrl/mediatek/Kconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index ba21a599953c..ee04b1af36dd 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -17,7 +17,6 @@ config PINCTRL_MTK select GENERIC_PINCONF select GPIOLIB select EINT_MTK - select OF_GPIO config PINCTRL_MTK_V2 tristate @@ -35,7 +34,6 @@ config PINCTRL_MTK_MOORE select GENERIC_PINCTRL_GROUPS select GENERIC_PINMUX_FUNCTIONS select GPIOLIB - select OF_GPIO select EINT_MTK select PINCTRL_MTK_V2 @@ -46,7 +44,6 @@ config PINCTRL_MTK_PARIS select GENERIC_PINCONF select GPIOLIB select EINT_MTK - select OF_GPIO select PINCTRL_MTK_V2 # For MIPS SoCs -- GitLab From e19e35a85216ac5ac5fa74b62d2d3f4a92665a2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:56 +0300 Subject: [PATCH 0881/5631] dt-bindings: pinctrl: ralink: move additionalProperties to top MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move additionalProperties to the top. It's easier to read than after a long indented section. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-7-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml | 7 +++---- .../devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml | 7 +++---- .../devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml | 7 +++---- .../devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml | 7 +++---- .../devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml | 7 +++---- 5 files changed, 15 insertions(+), 20 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml index 1e63ea34146a..b25e0db77cb3 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml @@ -22,11 +22,14 @@ properties: patternProperties: '-pins$': type: object + additionalProperties: false + patternProperties: '^(.*-)?pinmux$': type: object description: node for pinctrl. $ref: pinmux-node.yaml# + additionalProperties: false properties: function: @@ -632,10 +635,6 @@ patternProperties: groups: enum: [i2c, spi cs1, uart0] - additionalProperties: false - - additionalProperties: false - allOf: - $ref: "pinctrl.yaml#" diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml index 1b1d37b981d9..60f6273930f5 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml @@ -22,11 +22,14 @@ properties: patternProperties: '-pins$': type: object + additionalProperties: false + patternProperties: '^(.*-)?pinmux$': type: object description: node for pinctrl. $ref: pinmux-node.yaml# + additionalProperties: false properties: function: @@ -236,10 +239,6 @@ patternProperties: groups: enum: [wdt] - additionalProperties: false - - additionalProperties: false - allOf: - $ref: "pinctrl.yaml#" diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml index 7fd0df880a76..4f3e0af7d18f 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml @@ -22,11 +22,14 @@ properties: patternProperties: '-pins$': type: object + additionalProperties: false + patternProperties: '^(.*-)?pinmux$': type: object description: node for pinctrl. $ref: pinmux-node.yaml# + additionalProperties: false properties: function: @@ -116,10 +119,6 @@ patternProperties: groups: enum: [pci] - additionalProperties: false - - additionalProperties: false - allOf: - $ref: "pinctrl.yaml#" diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 4d66ca752a30..9e45d851def6 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -23,11 +23,14 @@ properties: patternProperties: '-pins$': type: object + additionalProperties: false + patternProperties: '^(.*-)?pinmux$': type: object description: node for pinctrl. $ref: pinmux-node.yaml# + additionalProperties: false properties: function: @@ -249,10 +252,6 @@ patternProperties: groups: enum: [spi_cs1] - additionalProperties: false - - additionalProperties: false - allOf: - $ref: "pinctrl.yaml#" diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml index 008d93181aea..4bea19d4ad7b 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml @@ -22,11 +22,14 @@ properties: patternProperties: '-pins$': type: object + additionalProperties: false + patternProperties: '^(.*-)?pinmux$': type: object description: node for pinctrl. $ref: pinmux-node.yaml# + additionalProperties: false properties: function: @@ -236,10 +239,6 @@ patternProperties: groups: enum: [uartlite] - additionalProperties: false - - additionalProperties: false - allOf: - $ref: "pinctrl.yaml#" -- GitLab From 6c011cc41091625c9abbf1e711bd44c655645377 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:57 +0300 Subject: [PATCH 0882/5631] dt-bindings: pinctrl: ralink: drop quotes from referred schemas MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the quotes from the referred schemas. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-8-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml index b25e0db77cb3..cde6de77e228 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml @@ -636,7 +636,7 @@ patternProperties: enum: [i2c, spi cs1, uart0] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml index 60f6273930f5..fb8c5459ea93 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml @@ -240,7 +240,7 @@ patternProperties: enum: [wdt] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml index 4f3e0af7d18f..e51667316b2e 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml @@ -120,7 +120,7 @@ patternProperties: enum: [pci] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 9e45d851def6..8b1256af09c3 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -253,7 +253,7 @@ patternProperties: enum: [spi_cs1] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml index 4bea19d4ad7b..adc4f42a175d 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml @@ -240,7 +240,7 @@ patternProperties: enum: [uartlite] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible -- GitLab From 0b91c8aa698f29ca6880c0f4f7920782c6e9aed8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:58 +0300 Subject: [PATCH 0883/5631] dt-bindings: pinctrl: ralink: add new compatible strings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the new compatible strings for mt7620, mt76x8, and rt305x to be able to properly document the pin muxing information of each SoC, or SoCs that use the same pinmux data. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-9-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml | 4 +++- .../devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml index cde6de77e228..09ebb8ac22ac 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml @@ -17,7 +17,9 @@ description: properties: compatible: - const: ralink,mt7620-pinctrl + enum: + - ralink,mt7620-pinctrl + - ralink,mt76x8-pinctrl patternProperties: '-pins$': diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 8b1256af09c3..23fb82f9959c 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -18,7 +18,10 @@ description: properties: compatible: - const: ralink,rt305x-pinctrl + enum: + - ralink,rt305x-pinctrl + - ralink,rt3352-pinctrl + - ralink,rt5350-pinctrl patternProperties: '-pins$': -- GitLab From 9c5ade5a7304ba79a7603f0c66d2b9d6ae7b69e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:29:59 +0300 Subject: [PATCH 0884/5631] dt-bindings: pinctrl: ralink: {mt7620,mt7621}: rename to mediatek MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename schemas of pin controllers for MediaTek MT7620 and MT7621 SoCs to be on par with other pin controllers for MediaTek SoCs. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-10-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- ...ink,mt7620-pinctrl.yaml => mediatek,mt7620-pinctrl.yaml} | 6 +++--- ...ink,mt7621-pinctrl.yaml => mediatek,mt7621-pinctrl.yaml} | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) rename Documentation/devicetree/bindings/pinctrl/{ralink,mt7620-pinctrl.yaml => mediatek,mt7620-pinctrl.yaml} (98%) rename Documentation/devicetree/bindings/pinctrl/{ralink,mt7621-pinctrl.yaml => mediatek,mt7621-pinctrl.yaml} (97%) diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml similarity index 98% rename from Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml index 09ebb8ac22ac..0dcdc3788e66 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml @@ -1,17 +1,17 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/ralink,mt7620-pinctrl.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt7620-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Ralink MT7620 Pin Controller +title: MediaTek MT7620 Pin Controller maintainers: - Arınç ÜNAL - Sergio Paracuellos description: - Ralink MT7620 pin controller for MT7620, MT7628 and MT7688 SoCs. + MediaTek MT7620 pin controller for MT7620, MT7628 and MT7688 SoCs. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml similarity index 97% rename from Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml index fb8c5459ea93..32506c538459 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,mt7621-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml @@ -1,17 +1,17 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/ralink,mt7621-pinctrl.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt7621-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Ralink MT7621 Pin Controller +title: MediaTek MT7621 Pin Controller maintainers: - Arınç ÜNAL - Sergio Paracuellos description: - Ralink MT7621 pin controller for MT7621 SoC. + MediaTek MT7621 pin controller for MT7621 SoC. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. -- GitLab From a22452afa896af118e9cdea06b591e4a77309b41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:00 +0300 Subject: [PATCH 0885/5631] dt-bindings: pinctrl: mediatek: mt6795: rename to mediatek,mt6795-pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename mediatek,pinctrl-mt6795.yaml to mediatek,mt6795-pinctrl.yaml to be on par with the compatible string and other mediatek dt-binding schemas. Signed-off-by: Arınç ÜNAL Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-11-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- ...ediatek,pinctrl-mt6795.yaml => mediatek,mt6795-pinctrl.yaml} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename Documentation/devicetree/bindings/pinctrl/{mediatek,pinctrl-mt6795.yaml => mediatek,mt6795-pinctrl.yaml} (98%) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,pinctrl-mt6795.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml similarity index 98% rename from Documentation/devicetree/bindings/pinctrl/mediatek,pinctrl-mt6795.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml index 9399e0215526..c5131f053b61 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,pinctrl-mt6795.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/mediatek,pinctrl-mt6795.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt6795-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT6795 Pin Controller -- GitLab From ff01f753682b0a09ec442173669b2114c5e8fc1c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:01 +0300 Subject: [PATCH 0886/5631] dt-bindings: pinctrl: mediatek: mt8186: rename to mediatek,mt8186-pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename pinctrl-mt8186.yaml to mediatek,mt8186-pinctrl.yaml to be on par with the compatible string and other mediatek dt-binding schemas. Signed-off-by: Arınç ÜNAL Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-12-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../{pinctrl-mt8186.yaml => mediatek,mt8186-pinctrl.yaml} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename Documentation/devicetree/bindings/pinctrl/{pinctrl-mt8186.yaml => mediatek,mt8186-pinctrl.yaml} (99%) diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8186.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml similarity index 99% rename from Documentation/devicetree/bindings/pinctrl/pinctrl-mt8186.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml index 26573a793b57..32d64416eb16 100644 --- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8186.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/pinctrl-mt8186.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt8186-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT8186 Pin Controller -- GitLab From 0dcf5a56bd93f92665f9e3437843811fd4374355 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:02 +0300 Subject: [PATCH 0887/5631] dt-bindings: pinctrl: mediatek: mt8192: rename to mediatek,mt8192-pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename pinctrl-mt8192.yaml to mediatek,mt8192-pinctrl.yaml to be on par with the compatible string and other mediatek dt-binding schemas. Signed-off-by: Arınç ÜNAL Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-13-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../{pinctrl-mt8192.yaml => mediatek,mt8192-pinctrl.yaml} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename Documentation/devicetree/bindings/pinctrl/{pinctrl-mt8192.yaml => mediatek,mt8192-pinctrl.yaml} (98%) diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml similarity index 98% rename from Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml index e0e943e5b874..e764cb0f8c1a 100644 --- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8192.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/pinctrl-mt8192.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt8192-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT8192 Pin Controller -- GitLab From 1d45ecb05ab4ec878254f2a11a5af49b64020148 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:03 +0300 Subject: [PATCH 0888/5631] dt-bindings: pinctrl: mediatek: mt8195: rename to mediatek,mt8195-pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename pinctrl-mt8195.yaml to mediatek,mt8195-pinctrl.yaml to be on par with the compatible string and other mediatek dt-binding schemas. Signed-off-by: Arınç ÜNAL Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-14-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../{pinctrl-mt8195.yaml => mediatek,mt8195-pinctrl.yaml} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename Documentation/devicetree/bindings/pinctrl/{pinctrl-mt8195.yaml => mediatek,mt8195-pinctrl.yaml} (99%) diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8195.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml similarity index 99% rename from Documentation/devicetree/bindings/pinctrl/pinctrl-mt8195.yaml rename to Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml index 66fe17e9e4d3..7b3dfc14eedc 100644 --- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt8195.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/pinctrl/pinctrl-mt8195.yaml# +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt8195-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT8195 Pin Controller -- GitLab From a9d44c4cc049d9024ed05dc9a615100b019c6f93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:04 +0300 Subject: [PATCH 0889/5631] dt-bindings: pinctrl: mediatek: fix naming inconsistency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some schemas include "MediaTek", some "Mediatek". Rename all to "MediaTek" to address the naming inconsistency. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-15-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml | 4 ++-- .../devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml | 4 ++-- .../devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml | 4 ++-- .../devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml | 4 ++-- .../devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml | 4 ++-- .../devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml | 2 +- 11 files changed, 16 insertions(+), 16 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml index a55c8e4ff26e..77b1b52f5799 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml @@ -4,13 +4,13 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt65xx-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT65xx Pin Controller +title: MediaTek MT65xx Pin Controller maintainers: - Sean Wang description: |+ - The Mediatek's Pin controller is used to control SoC pins. + The MediaTek's MT65xx Pin controller is used to control SoC pins. properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml index a2141eb0854e..c2fea29fa02f 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt6779-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT6779 Pin Controller +title: MediaTek MT6779 Pin Controller maintainers: - Andy Teng diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml index c5131f053b61..a78df32e6c39 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml @@ -4,14 +4,14 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt6795-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT6795 Pin Controller +title: MediaTek MT6795 Pin Controller maintainers: - AngeloGioacchino Del Regno - Sean Wang description: | - The Mediatek's Pin controller is used to control SoC pins. + The MediaTek's MT6795 Pin controller is used to control SoC pins. properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml index ac93eb8f01a6..3531b63ca4bf 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt7622-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT7622 Pin Controller +title: MediaTek MT7622 Pin Controller maintainers: - Sean Wang diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml index 74c66fbcb2ae..c3373290a8a1 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt7981-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT7981 Pin Controller +title: MediaTek MT7981 Pin Controller maintainers: - Daniel Golle diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml index 216b356cd519..71033831d03d 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt7986-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT7986 Pin Controller +title: MediaTek MT7986 Pin Controller maintainers: - Sean Wang diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml index c30cd0d010dd..3e34b03e11fc 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt8183-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT8183 Pin Controller +title: MediaTek MT8183 Pin Controller maintainers: - Sean Wang diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml index 32d64416eb16..a0519acc92fe 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml @@ -4,13 +4,13 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt8186-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT8186 Pin Controller +title: MediaTek MT8186 Pin Controller maintainers: - Sean Wang description: | - The Mediatek's Pin controller is used to control SoC pins. + The MediaTek's MT8186 Pin controller is used to control SoC pins. properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml index e764cb0f8c1a..3c3dd142a989 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml @@ -4,13 +4,13 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt8192-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT8192 Pin Controller +title: MediaTek MT8192 Pin Controller maintainers: - Sean Wang description: | - The Mediatek's Pin controller is used to control SoC pins. + The MediaTek's MT8192 Pin controller is used to control SoC pins. properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml index 7b3dfc14eedc..d4d5357cdd1d 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml @@ -4,13 +4,13 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt8195-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT8195 Pin Controller +title: MediaTek MT8195 Pin Controller maintainers: - Sean Wang description: | - The Mediatek's Pin controller is used to control SoC pins. + The MediaTek's MT8195 Pin controller is used to control SoC pins. properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml index 4b96884a1afc..42964dfa9fdb 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/pinctrl/mediatek,mt8365-pinctrl.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Mediatek MT8365 Pin Controller +title: MediaTek MT8365 Pin Controller maintainers: - Zhiyong Tao -- GitLab From c911ad22a884795529241cf7074b5cde355741b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:05 +0300 Subject: [PATCH 0890/5631] dt-bindings: pinctrl: {mediatek,ralink}: fix formatting MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Change the style of description properties to plain style where there's no need to preserve the line endings, and vice versa. Fix capitalisation and indentation. Fit the schemas to 80 columns for each line. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-16-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../pinctrl/mediatek,mt65xx-pinctrl.yaml | 22 +++--- .../pinctrl/mediatek,mt6779-pinctrl.yaml | 33 +++++---- .../pinctrl/mediatek,mt6795-pinctrl.yaml | 41 +++++----- .../pinctrl/mediatek,mt7620-pinctrl.yaml | 2 +- .../pinctrl/mediatek,mt7621-pinctrl.yaml | 2 +- .../pinctrl/mediatek,mt7622-pinctrl.yaml | 26 +++---- .../pinctrl/mediatek,mt7981-pinctrl.yaml | 33 +++++---- .../pinctrl/mediatek,mt7986-pinctrl.yaml | 68 ++++++++--------- .../pinctrl/mediatek,mt8183-pinctrl.yaml | 26 ++++--- .../pinctrl/mediatek,mt8186-pinctrl.yaml | 47 ++++++------ .../pinctrl/mediatek,mt8188-pinctrl.yaml | 74 ++++++++++--------- .../pinctrl/mediatek,mt8192-pinctrl.yaml | 47 ++++++------ .../pinctrl/mediatek,mt8195-pinctrl.yaml | 41 +++++----- .../pinctrl/mediatek,mt8365-pinctrl.yaml | 28 +++---- .../pinctrl/ralink,rt2880-pinctrl.yaml | 2 +- .../pinctrl/ralink,rt305x-pinctrl.yaml | 2 +- .../pinctrl/ralink,rt3883-pinctrl.yaml | 2 +- 17 files changed, 258 insertions(+), 238 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml index 77b1b52f5799..5e80621800a9 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT65xx Pin Controller maintainers: - Sean Wang -description: |+ +description: The MediaTek's MT65xx Pin controller is used to control SoC pins. properties: @@ -30,7 +30,7 @@ properties: pins-are-numbered: $ref: /schemas/types.yaml#/definitions/flag - description: | + description: Specify the subnodes are using numbered pinmux to specify pins. (UNUSED) deprecated: true @@ -38,10 +38,10 @@ properties: "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. mediatek,pctl-regmap: $ref: /schemas/types.yaml#/definitions/phandle-array @@ -49,7 +49,7 @@ properties: maxItems: 1 minItems: 1 maxItems: 2 - description: | + description: Should be phandles of the syscfg node. interrupt-controller: true @@ -77,7 +77,7 @@ patternProperties: '(^pins|pins?$)': type: object additionalProperties: false - description: | + description: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer @@ -88,14 +88,14 @@ patternProperties: properties: pinmux: description: - integer array, represents gpio pin number and mux setting. + Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are defined as macros in -pinfunc.h directly. bias-disable: true bias-pull-up: - description: | + description: Besides generic pinconfig options, it can be used as the pull up settings for 2 pull resistors, R0 and R1. User can configure those special pins. Some macros have been defined for this usage, such @@ -117,7 +117,7 @@ patternProperties: input-schmitt-disable: true drive-strength: - description: | + description: Can support some arguments, such as MTK_DRIVE_4mA, MTK_DRIVE_6mA, etc. See dt-bindings/pinctrl/mt65xx.h for valid arguments. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml index c2fea29fa02f..1d038f6f8971 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml @@ -11,8 +11,8 @@ maintainers: - Sean Wang description: - The MediaTek pin controller on MT6779 is used to control pin - functions, pull up/down resistance and drive strength options. + The MediaTek pin controller on MT6779 is used to control pin functions, pull + up/down resistance and drive strength options. properties: compatible: @@ -29,22 +29,22 @@ properties: "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. gpio-ranges: minItems: 1 maxItems: 5 - description: | + description: GPIO valid number range. interrupt-controller: true interrupts: maxItems: 1 - description: | + description: Specifies the summary IRQ. "#interrupt-cells": @@ -118,19 +118,20 @@ patternProperties: patternProperties: '-pins*$': type: object - description: | + description: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. $ref: "/schemas/pinctrl/pincfg-node.yaml" properties: pinmux: description: - integer array, represents gpio pin number and mux setting. - Supported pin number and mux varies for different SoCs, and are defined - as macros in boot/dts/-pinfunc.h directly. + Integer array, represents gpio pin number and mux setting. + Supported pin number and mux varies for different SoCs, and are + defined as macros in boot/dts/-pinfunc.h directly. bias-disable: true @@ -159,7 +160,8 @@ patternProperties: mediatek,pull-up-adv: description: | Pull up setings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -170,7 +172,8 @@ patternProperties: mediatek,pull-down-adv: description: | Pull down settings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml index a78df32e6c39..c3bf98749fa4 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - AngeloGioacchino Del Regno - Sean Wang -description: | +description: The MediaTek's MT6795 Pin controller is used to control SoC pins. properties: @@ -20,10 +20,10 @@ properties: gpio-controller: true '#gpio-cells': - description: | + description: Number of cells in GPIO specifier. Since the generic GPIO binding is used, - the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. const: 2 gpio-ranges: @@ -32,7 +32,7 @@ properties: reg: description: - Physical address base for gpio base and eint registers. + Physical address base for GPIO base and eint registers. minItems: 2 reg-names: @@ -65,8 +65,8 @@ patternProperties: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and - input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. An example of using macro: pincontroller { /* GPIO0 set as multifunction GPIO0 */ @@ -86,11 +86,10 @@ patternProperties: properties: pinmux: - description: | + description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in dt-bindings/pinctrl/-pinfunc.h - directly. + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. drive-strength: enum: [2, 4, 6, 8, 10, 12, 14, 16] @@ -100,20 +99,20 @@ patternProperties: - type: boolean - enum: [100, 101, 102, 103] description: mt6795 pull down PUPD/R0/R1 type define value. - description: | - For normal pull down type, it is not necessary to specify R1R0 - values; When pull down type is PUPD/R0/R1, adding R1R0 defines - will set different resistance values. + description: + For normal pull down type, it is not necessary to specify R1R0 + values; When pull down type is PUPD/R0/R1, adding R1R0 defines + will set different resistance values. bias-pull-up: oneOf: - type: boolean - enum: [100, 101, 102, 103] description: mt6795 pull up PUPD/R0/R1 type define value. - description: | - For normal pull up type, it is not necessary to specify R1R0 - values; When pull up type is PUPD/R0/R1, adding R1R0 defines - will set different resistance values. + description: + For normal pull up type, it is not necessary to specify R1R0 + values; When pull up type is PUPD/R0/R1, adding R1R0 defines will + set different resistance values. bias-disable: true @@ -132,7 +131,8 @@ patternProperties: mediatek,pull-up-adv: description: | Pull up setings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -143,7 +143,8 @@ patternProperties: mediatek,pull-down-adv: description: | Pull down settings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml index 0dcdc3788e66..808dd8bd276f 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Arınç ÜNAL - Sergio Paracuellos -description: +description: | MediaTek MT7620 pin controller for MT7620, MT7628 and MT7688 SoCs. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml index 32506c538459..e568b9c13727 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Arınç ÜNAL - Sergio Paracuellos -description: +description: | MediaTek MT7621 pin controller for MT7621 SoC. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml index 3531b63ca4bf..38dc41c735eb 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT7622 Pin Controller maintainers: - Sean Wang -description: |+ +description: The MediaTek's MT7622 Pin controller is used to control SoC pins. properties: @@ -29,10 +29,10 @@ properties: "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. interrupt-controller: true @@ -68,18 +68,18 @@ patternProperties: '^mux(-|$)': type: object additionalProperties: false - description: | + description: pinmux configuration nodes. $ref: "/schemas/pinctrl/pinmux-node.yaml" properties: function: - description: | + description: A string containing the name of the function to mux to the group. enum: [emmc, eth, i2c, i2s, ir, led, flash, pcie, pmic, pwm, sd, spi, tdm, uart, watchdog, wifi] groups: - description: | + description: An array of strings. Each string contains the name of a group. drive-strength: @@ -247,18 +247,18 @@ patternProperties: '^conf(-|$)': type: object additionalProperties: false - description: | + description: pinconf configuration nodes. $ref: "/schemas/pinctrl/pincfg-node.yaml" properties: groups: - description: | + description: An array of strings. Each string contains the name of a group. Valid values are the same as the pinmux node. pins: - description: | + description: An array of strings. Each string contains the name of a pin. enum: [GPIO_A, I2S1_IN, I2S1_OUT, I2S_BCLK, I2S_WS, I2S_MCLK, TXD0, RXD0, SPI_WP, SPI_HOLD, SPI_CLK, SPI_MOSI, SPI_MISO, SPI_CS, @@ -315,14 +315,14 @@ patternProperties: enum: [0, 1] mediatek,tdsel: - description: | + description: An integer describing the steps for output level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 15. $ref: /schemas/types.yaml#/definitions/uint32 mediatek,rdsel: - description: | + description: An integer describing the steps for input level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 63. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml index c3373290a8a1..10717cee9058 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7981-pinctrl.yaml @@ -37,7 +37,7 @@ properties: "#gpio-cells": const: 2 - description: > + description: Number of cells in GPIO specifier. Since the generic GPIO binding is used, the amount of cells must be specified as 2. See the below mentioned gpio binding representation for description of particular cells. @@ -111,7 +111,9 @@ patternProperties: "watchdog1" "watchdog" 13 "udi" "udi" 9, 10, 11, 12, 13 "drv_vbus" "usb" 14 - "emmc_45" "flash" 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25 + "emmc_45" "flash" 15, 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25 + "snfi" "flash" 16, 17, 18, 19, 20, 21 "spi0" "spi" 16, 17, 18, 19 "spi0_wp_hold" "spi" 20, 21 @@ -148,7 +150,7 @@ patternProperties: "wf5g_led0" "led" 31 "wf5g_led1" "led" 35 "mt7531_int" "eth" 38 - "ant_sel" "ant" 14, 15, 16, 17, 18, 19, 20, 21, 22 + "ant_sel" "ant" 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 34, 35 $ref: /schemas/pinctrl/pinmux-node.yaml @@ -256,7 +258,8 @@ patternProperties: then: properties: groups: - enum: [gbe_led0, gbe_led1, wf2g_led0, wf2g_led1, wf5g_led0, wf5g_led1] + enum: [gbe_led0, gbe_led1, wf2g_led0, wf2g_led1, wf5g_led0, + wf5g_led1] - if: properties: function: @@ -275,7 +278,8 @@ patternProperties: properties: groups: items: - enum: [spi1_0, spi0, spi0_wp_hold, spi1_1, spi2, spi2_wp_hold] + enum: [spi1_0, spi0, spi0_wp_hold, spi1_1, spi2, + spi2_wp_hold] maxItems: 4 - if: properties: @@ -332,13 +336,14 @@ patternProperties: JTAG_JTDO, JTAG_JTDI, JTAG_JTMS, JTAG_JTCLK, JTAG_JTRST_N, WO_JTAG_JTDO, WO_JTAG_JTDI, WO_JTAG_JTMS, WO_JTAG_JTCLK, WO_JTAG_JTRST_N, USB_VBUS, PWM0, SPI0_CLK, SPI0_MOSI, - SPI0_MISO, SPI0_CS, SPI0_HOLD, SPI0_WP, SPI1_CLK, SPI1_MOSI, - SPI1_MISO, SPI1_CS, SPI2_CLK, SPI2_MOSI, SPI2_MISO, SPI2_CS, - SPI2_HOLD, SPI2_WP, UART0_RXD, UART0_TXD, PCIE_CLK_REQ, - PCIE_WAKE_N, SMI_MDC, SMI_MDIO, GBE_INT, GBE_RESET, - WF_DIG_RESETB, WF_CBA_RESETB, WF_XO_REQ, WF_TOP_CLK, - WF_TOP_DATA, WF_HB1, WF_HB2, WF_HB3, WF_HB4, WF_HB0, - WF_HB0_B, WF_HB5, WF_HB6, WF_HB7, WF_HB8, WF_HB9, WF_HB10] + SPI0_MISO, SPI0_CS, SPI0_HOLD, SPI0_WP, SPI1_CLK, + SPI1_MOSI, SPI1_MISO, SPI1_CS, SPI2_CLK, SPI2_MOSI, + SPI2_MISO, SPI2_CS, SPI2_HOLD, SPI2_WP, UART0_RXD, + UART0_TXD, PCIE_CLK_REQ, PCIE_WAKE_N, SMI_MDC, SMI_MDIO, + GBE_INT, GBE_RESET, WF_DIG_RESETB, WF_CBA_RESETB, + WF_XO_REQ, WF_TOP_CLK, WF_TOP_DATA, WF_HB1, WF_HB2, WF_HB3, + WF_HB4, WF_HB0, WF_HB0_B, WF_HB5, WF_HB6, WF_HB7, WF_HB8, + WF_HB9, WF_HB10] maxItems: 57 bias-disable: true @@ -348,7 +353,7 @@ patternProperties: - type: boolean description: normal pull up. - enum: [100, 101, 102, 103] - description: > + description: PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in dt-bindings/pinctrl/mt65xx.h. @@ -357,7 +362,7 @@ patternProperties: - type: boolean description: normal pull down. - enum: [100, 101, 102, 103] - description: > + description: PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in dt-bindings/pinctrl/mt65xx.h. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml index 71033831d03d..7157500a7f81 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT7986 Pin Controller maintainers: - Sean Wang -description: |+ +description: The MediaTek's MT7986 Pin controller is used to control SoC pins. properties: @@ -37,15 +37,15 @@ properties: "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. gpio-ranges: minItems: 1 maxItems: 5 - description: | + description: GPIO valid number range. interrupt-controller: true @@ -81,7 +81,7 @@ patternProperties: The following table shows the effective values of "group", "function" properties and chip pinout pins - groups function pins (in pin#) + groups function pins (in pin#) --------------------------------------------------------------------- "watchdog" "watchdog" 0 "wifi_led" "led" 1, 2 @@ -97,8 +97,9 @@ patternProperties: "pwm1_0" "pwm" 22, "snfi" "flash" 23, 24, 25, 26, 27, 28 "spi1_2" "spi" 29, 30, 31, 32 - "emmc_45" "emmc" 22, 23, 24, 25, 26, 27, 28, 29, 30, - 31, 32 + "emmc_45" "emmc" 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, + 32 + "spi1_1" "spi" 23, 24, 25, 26 "uart1_2_rx_tx" "uart" 29, 30 "uart1_2_cts_rts" "uart" 31, 32 @@ -115,8 +116,9 @@ patternProperties: "pcie_pereset" "pcie" 41 "uart1" "uart" 42, 43, 44, 45 "uart2" "uart" 46, 47, 48, 49 - "emmc_51" "emmc" 50, 51, 52, 53, 54, 55, 56, 57, 57, - 59, 60, 61 + "emmc_51" "emmc" 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, + 60, 61 + "pcm" "audio" 62, 63, 64, 65 "i2s" "audio" 62, 63, 64, 65 "switch_int" "eth" 66 @@ -129,18 +131,17 @@ patternProperties: $ref: "/schemas/pinctrl/pinmux-node.yaml" properties: function: - description: | + description: A string containing the name of the function to mux to the group. There is no "audio", "pcie" functions on mt7986b, you can only use those functions on mt7986a. enum: [audio, emmc, eth, i2c, led, flash, pcie, pwm, spi, uart, watchdog, wifi] groups: - description: | + description: An array of strings. Each string contains the name of a group. - There is no "pcie_pereset", "uart1", "uart2" "emmc_51", "pcm", - and "i2s" groups on mt7986b, you can only use those groups on - mt7986a. + There is no "pcie_pereset", "uart1", "uart2" "emmc_51", "pcm", and + "i2s" groups on mt7986b, you can only use those groups on mt7986a. required: - function - groups @@ -258,29 +259,30 @@ patternProperties: '.*conf.*': type: object additionalProperties: false - description: | + description: pinconf configuration nodes. $ref: "/schemas/pinctrl/pincfg-node.yaml" properties: pins: - description: | - An array of strings. Each string contains the name of a pin. - There is no PIN 41 to PIN 65 above on mt7686b, you can only use - those pins on mt7986a. + description: + An array of strings. Each string contains the name of a pin. There + is no PIN 41 to PIN 65 above on mt7686b, you can only use those + pins on mt7986a. items: enum: [SYS_WATCHDOG, WF2G_LED, WF5G_LED, I2C_SCL, I2C_SDA, GPIO_0, GPIO_1, GPIO_2, GPIO_3, GPIO_4, GPIO_5, GPIO_6, GPIO_7, - GPIO_8, GPIO_9, GPIO_10, GPIO_11, GPIO_12, GPIO_13, GPIO_14, - GPIO_15, PWM0, PWM1, SPI0_CLK, SPI0_MOSI, SPI0_MISO, SPI0_CS, - SPI0_HOLD, SPI0_WP, SPI1_CLK, SPI1_MOSI, SPI1_MISO, SPI1_CS, - SPI2_CLK, SPI2_MOSI, SPI2_MISO, SPI2_CS, SPI2_HOLD, SPI2_WP, - UART0_RXD, UART0_TXD, PCIE_PERESET_N, UART1_RXD, UART1_TXD, - UART1_CTS, UART1_RTS, UART2_RXD, UART2_TXD, UART2_CTS, - UART2_RTS, EMMC_DATA_0, EMMC_DATA_1, EMMC_DATA_2, - EMMC_DATA_3, EMMC_DATA_4, EMMC_DATA_5, EMMC_DATA_6, - EMMC_DATA_7, EMMC_CMD, EMMC_CK, EMMC_DSL, EMMC_RSTB, PCM_DTX, - PCM_DRX, PCM_CLK, PCM_FS, MT7531_INT, SMI_MDC, SMI_MDIO, + GPIO_8, GPIO_9, GPIO_10, GPIO_11, GPIO_12, GPIO_13, + GPIO_14, GPIO_15, PWM0, PWM1, SPI0_CLK, SPI0_MOSI, + SPI0_MISO, SPI0_CS, SPI0_HOLD, SPI0_WP, SPI1_CLK, + SPI1_MOSI, SPI1_MISO, SPI1_CS, SPI2_CLK, SPI2_MOSI, + SPI2_MISO, SPI2_CS, SPI2_HOLD, SPI2_WP, UART0_RXD, + UART0_TXD, PCIE_PERESET_N, UART1_RXD, UART1_TXD, UART1_CTS, + UART1_RTS, UART2_RXD, UART2_TXD, UART2_CTS, UART2_RTS, + EMMC_DATA_0, EMMC_DATA_1, EMMC_DATA_2, EMMC_DATA_3, + EMMC_DATA_4, EMMC_DATA_5, EMMC_DATA_6, EMMC_DATA_7, + EMMC_CMD, EMMC_CK, EMMC_DSL, EMMC_RSTB, PCM_DTX, PCM_DRX, + PCM_CLK, PCM_FS, MT7531_INT, SMI_MDC, SMI_MDIO, WF0_DIG_RESETB, WF0_CBA_RESETB, WF0_XO_REQ, WF0_TOP_CLK, WF0_TOP_DATA, WF0_HB1, WF0_HB2, WF0_HB3, WF0_HB4, WF0_HB0, WF0_HB0_B, WF0_HB5, WF0_HB6, WF0_HB7, WF0_HB8, WF0_HB9, @@ -297,7 +299,7 @@ patternProperties: - type: boolean description: normal pull up. - enum: [100, 101, 102, 103] - description: | + description: PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in dt-bindings/pinctrl/mt65xx.h. @@ -306,7 +308,7 @@ patternProperties: - type: boolean description: normal pull down. - enum: [100, 101, 102, 103] - description: | + description: PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0 defines in dt-bindings/pinctrl/mt65xx.h. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml index 3e34b03e11fc..372a3aefa937 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT8183 Pin Controller maintainers: - Sean Wang -description: |+ +description: The MediaTek's MT8183 Pin controller is used to control SoC pins. properties: @@ -37,15 +37,15 @@ properties: "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. gpio-ranges: minItems: 1 maxItems: 5 - description: | + description: GPIO valid number range. interrupt-controller: true @@ -74,7 +74,7 @@ patternProperties: '^pins': type: object additionalProperties: false - description: | + description: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer @@ -85,7 +85,7 @@ patternProperties: properties: pinmux: description: - integer array, represents gpio pin number and mux setting. + Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are defined as macros in -pinfunc.h directly. @@ -139,7 +139,8 @@ patternProperties: mediatek,pull-up-adv: description: | Pull up setings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -150,7 +151,8 @@ patternProperties: mediatek,pull-down-adv: description: | Pull down settings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -159,14 +161,14 @@ patternProperties: enum: [0, 1, 2, 3] mediatek,tdsel: - description: | + description: An integer describing the steps for output level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 15. $ref: /schemas/types.yaml#/definitions/uint32 mediatek,rdsel: - description: | + description: An integer describing the steps for input level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 63. diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml index a0519acc92fe..eb6a5cdecc6c 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT8186 Pin Controller maintainers: - Sean Wang -description: | +description: The MediaTek's MT8186 Pin controller is used to control SoC pins. properties: @@ -19,10 +19,10 @@ properties: gpio-controller: true '#gpio-cells': - description: | + description: Number of cells in GPIO specifier. Since the generic GPIO binding is used, - the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. const: 2 gpio-ranges: @@ -31,14 +31,14 @@ properties: gpio-line-names: true reg: - description: | - Physical address base for gpio base registers. There are 8 different GPIO + description: + Physical address base for GPIO base registers. There are 8 different GPIO physical address base in mt8186. maxItems: 8 reg-names: - description: | - Gpio base register names. + description: + GPIO base register names. items: - const: iocfg0 - const: iocfg_lt @@ -60,9 +60,9 @@ properties: mediatek,rsel-resistance-in-si-unit: type: boolean - description: | - Identifying i2c pins pull up/down type which is RSEL. It can support - RSEL define or si unit value(ohm) to set different resistance. + description: + Identifying i2c pins pull up/down type which is RSEL. It can support RSEL + define or si unit value(ohm) to set different resistance. # PIN CONFIGURATION NODES patternProperties: @@ -77,8 +77,8 @@ patternProperties: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and - input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. An example of using macro: pincontroller { /* GPIO0 set as multifunction GPIO0 */ @@ -98,11 +98,10 @@ patternProperties: properties: pinmux: - description: | + description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in dt-bindings/pinctrl/-pinfunc.h - directly. + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. drive-strength: enum: [2, 4, 6, 8, 10, 12, 14, 16] @@ -129,10 +128,10 @@ patternProperties: For pull down type is RSEL, it can add RSEL define & resistance value(ohm) to set different resistance by identifying property "mediatek,rsel-resistance-in-si-unit". - It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" - & "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" - define in mt8186. It can also support resistance value(ohm) - "75000" & "5000" in mt8186. + It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" & + "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" define in + mt8186. It can also support resistance value(ohm) "75000" & "5000" + in mt8186. An example of using RSEL define: pincontroller { i2c0_pin { @@ -174,10 +173,10 @@ patternProperties: For pull up type is RSEL, it can add RSEL define & resistance value(ohm) to set different resistance by identifying property "mediatek,rsel-resistance-in-si-unit". - It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" - & "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" - define in mt8186. It can also support resistance value(ohm) - "1000" & "5000" & "10000" & "75000" in mt8186. + It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" & + "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" define in + mt8186. It can also support resistance value(ohm) "1000" & "5000" + & "10000" & "75000" in mt8186. An example of using si unit resistance value(ohm): &pio { mediatek,rsel-resistance-in-si-unit; diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml index 7e750f1e643d..51b3d1247614 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT8188 Pin Controller maintainers: - Hui Liu -description: | +description: The MediaTek's MT8188 Pin controller is used to control SoC pins. properties: @@ -19,10 +19,10 @@ properties: gpio-controller: true '#gpio-cells': - description: | - Number of cells in GPIO specifier, should be two. The first cell - is the pin number, the second cell is used to specify optional - parameters which are defined in . + description: + Number of cells in GPIO specifier, should be two. The first cell is the + pin number, the second cell is used to specify optional parameters which + are defined in . const: 2 gpio-ranges: @@ -59,10 +59,11 @@ properties: mediatek,rsel-resistance-in-si-unit: type: boolean - description: | - We provide two methods to select the resistance for I2C when pull up or pull down. - The first is by RSEL definition value, another one is by resistance value(ohm). - This flag is used to identify if the method is resistance(si unit) value. + description: + We provide two methods to select the resistance for I2C when pull up or + pull down. The first is by RSEL definition value, another one is by + resistance value(ohm). This flag is used to identify if the method is + resistance(si unit) value. # PIN CONFIGURATION NODES patternProperties: @@ -75,16 +76,16 @@ patternProperties: type: object $ref: "/schemas/pinctrl/pincfg-node.yaml" additionalProperties: false - description: | + description: A pinctrl node should contain at least one subnode representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and - input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. properties: pinmux: - description: | + description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are defined as macros in dt-bindings/pinctrl/mediatek,-pinfunc.h @@ -106,18 +107,21 @@ patternProperties: - enum: [75000, 5000] description: mt8188 pull down RSEL type si unit value(ohm). description: | - For pull down type is normal, it doesn't need add RSEL & R1R0 define - and resistance value. + For pull down type is normal, it doesn't need add RSEL & R1R0 + define and resistance value. For pull down type is PUPD/R0/R1 type, it can add R1R0 define to set different resistance. It can support "MTK_PUPD_SET_R1R0_00" & - "MTK_PUPD_SET_R1R0_01" & "MTK_PUPD_SET_R1R0_10" & "MTK_PUPD_SET_R1R0_11" - define in mt8188. - For pull down type is RSEL, it can add RSEL define & resistance value(ohm) - to set different resistance by identifying property "mediatek,rsel-resistance-in-si-unit". - It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" - & "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" & "MTK_PULL_SET_RSEL_100" - & "MTK_PULL_SET_RSEL_101" & "MTK_PULL_SET_RSEL_110" & "MTK_PULL_SET_RSEL_111" - define in mt8188. It can also support resistance value(ohm) "75000" & "5000" in mt8188. + "MTK_PUPD_SET_R1R0_01" & "MTK_PUPD_SET_R1R0_10" & + "MTK_PUPD_SET_R1R0_11" define in mt8188. + For pull down type is RSEL, it can add RSEL define & resistance + value(ohm) to set different resistance by identifying property + "mediatek,rsel-resistance-in-si-unit". It can support + "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" & + "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" & + "MTK_PULL_SET_RSEL_100" & "MTK_PULL_SET_RSEL_101" & + "MTK_PULL_SET_RSEL_110" & "MTK_PULL_SET_RSEL_111" define in + mt8188. It can also support resistance value(ohm) "75000" & "5000" + in mt8188. bias-pull-up: oneOf: @@ -131,17 +135,19 @@ patternProperties: description: | For pull up type is normal, it don't need add RSEL & R1R0 define and resistance value. - For pull up type is PUPD/R0/R1 type, it can add R1R0 define to - set different resistance. It can support "MTK_PUPD_SET_R1R0_00" & - "MTK_PUPD_SET_R1R0_01" & "MTK_PUPD_SET_R1R0_10" & "MTK_PUPD_SET_R1R0_11" - define in mt8188. - For pull up type is RSEL, it can add RSEL define & resistance value(ohm) - to set different resistance by identifying property "mediatek,rsel-resistance-in-si-unit". - It can support "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" - & "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" & "MTK_PULL_SET_RSEL_100" - & "MTK_PULL_SET_RSEL_101" & "MTK_PULL_SET_RSEL_110" & "MTK_PULL_SET_RSEL_111" - define in mt8188. It can also support resistance value(ohm) - "1000" & "1500" & "2000" & "3000" & "4000" & "5000" & "10000" & "75000" in mt8188. + For pull up type is PUPD/R0/R1 type, it can add R1R0 define to set + different resistance. It can support "MTK_PUPD_SET_R1R0_00" & + "MTK_PUPD_SET_R1R0_01" & "MTK_PUPD_SET_R1R0_10" & + "MTK_PUPD_SET_R1R0_11" define in mt8188. + For pull up type is RSEL, it can add RSEL define & resistance + value(ohm) to set different resistance by identifying property + "mediatek,rsel-resistance-in-si-unit". It can support + "MTK_PULL_SET_RSEL_000" & "MTK_PULL_SET_RSEL_001" & + "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" & + "MTK_PULL_SET_RSEL_100" & "MTK_PULL_SET_RSEL_101" & + "MTK_PULL_SET_RSEL_110" & "MTK_PULL_SET_RSEL_111" define in + mt8188. It can also support resistance value(ohm) "1000" & "1500" + & "2000" & "3000" & "4000" & "5000" & "10000" & "75000" in mt8188. bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml index 3c3dd142a989..8cca1ce40f25 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT8192 Pin Controller maintainers: - Sean Wang -description: | +description: The MediaTek's MT8192 Pin controller is used to control SoC pins. properties: @@ -19,27 +19,27 @@ properties: gpio-controller: true '#gpio-cells': - description: | + description: Number of cells in GPIO specifier. Since the generic GPIO binding is used, - the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. const: 2 gpio-ranges: - description: gpio valid number range. + description: GPIO valid number range. maxItems: 1 gpio-line-names: true reg: - description: | - Physical address base for gpio base registers. There are 11 GPIO - physical address base in mt8192. + description: + Physical address base for GPIO base registers. There are 11 GPIO physical + address base in mt8192. maxItems: 11 reg-names: - description: | - Gpio base register names. + description: + GPIO base register names. maxItems: 11 interrupt-controller: true @@ -59,25 +59,26 @@ patternProperties: patternProperties: '^pins': type: object - description: | + description: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and - input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. $ref: "pinmux-node.yaml" properties: pinmux: - description: | + description: Integer array, represents gpio pin number and mux setting. - Supported pin number and mux varies for different SoCs, and are defined - as macros in dt-bindings/pinctrl/-pinfunc.h directly. + Supported pin number and mux varies for different SoCs, and are + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. drive-strength: - description: | - It can support some arguments, such as MTK_DRIVE_4mA, MTK_DRIVE_6mA, etc. See - dt-bindings/pinctrl/mt65xx.h. It can only support 2/4/6/8/10/12/14/16mA in mt8192. + description: + It can support some arguments, such as MTK_DRIVE_4mA, + MTK_DRIVE_6mA, etc. See dt-bindings/pinctrl/mt65xx.h. It can only + support 2/4/6/8/10/12/14/16mA in mt8192. enum: [2, 4, 6, 8, 10, 12, 14, 16] drive-strength-microamp: @@ -91,8 +92,8 @@ patternProperties: description: PUPD/R1/R0 pull down type. See MTK_PUPD_SET_R1R0_ defines in dt-bindings/pinctrl/mt65xx.h. - enum: [200, 201, 202, 203] - description: RSEL pull down type. See MTK_PULL_SET_RSEL_ - defines in dt-bindings/pinctrl/mt65xx.h. + description: RSEL pull down type. See MTK_PULL_SET_RSEL_ defines + in dt-bindings/pinctrl/mt65xx.h. bias-pull-up: oneOf: @@ -102,8 +103,8 @@ patternProperties: description: PUPD/R1/R0 pull up type. See MTK_PUPD_SET_R1R0_ defines in dt-bindings/pinctrl/mt65xx.h. - enum: [200, 201, 202, 203] - description: RSEL pull up type. See MTK_PULL_SET_RSEL_ - defines in dt-bindings/pinctrl/mt65xx.h. + description: RSEL pull up type. See MTK_PULL_SET_RSEL_ defines + in dt-bindings/pinctrl/mt65xx.h. bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml index d4d5357cdd1d..b8ba260d74cd 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml @@ -9,7 +9,7 @@ title: MediaTek MT8195 Pin Controller maintainers: - Sean Wang -description: | +description: The MediaTek's MT8195 Pin controller is used to control SoC pins. properties: @@ -19,27 +19,27 @@ properties: gpio-controller: true '#gpio-cells': - description: | + description: Number of cells in GPIO specifier. Since the generic GPIO binding is used, - the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. const: 2 gpio-ranges: - description: gpio valid number range. + description: GPIO valid number range. maxItems: 1 gpio-line-names: true reg: - description: | - Physical address base for gpio base registers. There are 8 GPIO - physical address base in mt8195. + description: + Physical address base for GPIO base registers. There are 8 GPIO physical + address base in mt8195. maxItems: 8 reg-names: - description: | - Gpio base register names. + description: + GPIO base register names. maxItems: 8 interrupt-controller: true @@ -53,9 +53,9 @@ properties: mediatek,rsel-resistance-in-si-unit: type: boolean - description: | - Identifying i2c pins pull up/down type which is RSEL. It can support - RSEL define or si unit value(ohm) to set different resistance. + description: + Identifying i2c pins pull up/down type which is RSEL. It can support RSEL + define or si unit value(ohm) to set different resistance. # PIN CONFIGURATION NODES patternProperties: @@ -70,8 +70,8 @@ patternProperties: A pinctrl node should contain at least one subnodes representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer - configuration, pullups, drive strength, input enable/disable and - input schmitt. + configuration, pullups, drive strength, input enable/disable and input + schmitt. An example of using macro: pincontroller { /* GPIO0 set as multifunction GPIO0 */ @@ -91,11 +91,10 @@ patternProperties: properties: pinmux: - description: | + description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in dt-bindings/pinctrl/-pinfunc.h - directly. + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. drive-strength: enum: [2, 4, 6, 8, 10, 12, 14, 16] @@ -174,9 +173,9 @@ patternProperties: & "MTK_PULL_SET_RSEL_010" & "MTK_PULL_SET_RSEL_011" & "MTK_PULL_SET_RSEL_100" & "MTK_PULL_SET_RSEL_101" & "MTK_PULL_SET_RSEL_110" & "MTK_PULL_SET_RSEL_111" - define in mt8195. It can also support resistance value(ohm) - "1000" & "1500" & "2000" & "3000" & "4000" & "5000" & "10000" & - "75000" in mt8195. + define in mt8195. It can also support resistance value(ohm) "1000" + & "1500" & "2000" & "3000" & "4000" & "5000" & "10000" & "75000" + in mt8195. An example of using RSEL define: pincontroller { i2c0-pins { diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml index 42964dfa9fdb..5aa8ba4cb547 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Zhiyong Tao - Bernhard Rosenkränzer -description: | +description: The MediaTek's MT8365 Pin controller is used to control SoC pins. properties: @@ -26,17 +26,17 @@ properties: maxItems: 1 minItems: 1 maxItems: 2 - description: | + description: Should be phandles of the syscfg node. gpio-controller: true "#gpio-cells": const: 2 - description: | - Number of cells in GPIO specifier. Since the generic GPIO - binding is used, the amount of cells must be specified as 2. See the below - mentioned gpio binding representation for description of particular cells. + description: + Number of cells in GPIO specifier. Since the generic GPIO binding is used, + the amount of cells must be specified as 2. See the below mentioned gpio + binding representation for description of particular cells. interrupt-controller: true @@ -54,7 +54,7 @@ patternProperties: "pins$": type: object additionalProperties: false - description: | + description: A pinctrl node should contain at least one subnode representing the pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer @@ -65,14 +65,14 @@ patternProperties: properties: pinmux: description: - integer array, represents gpio pin number and mux setting. + Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are defined as macros in -pinfunc.h directly. bias-disable: true bias-pull-up: - description: | + description: Besides generic pinconfig options, it can be used as the pull up settings for 2 pull resistors, R0 and R1. User can configure those special pins. @@ -120,7 +120,8 @@ patternProperties: mediatek,pull-up-adv: description: | Pull up setings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -131,7 +132,8 @@ patternProperties: mediatek,pull-down-adv: description: | Pull down settings for 2 pull resistors, R0 and R1. User can - configure those special pins. Valid arguments are described as below: + configure those special pins. Valid arguments are described as + below: 0: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. 1: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. 2: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. @@ -140,14 +142,14 @@ patternProperties: enum: [0, 1, 2, 3] mediatek,tdsel: - description: | + description: An integer describing the steps for output level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 15. $ref: /schemas/types.yaml#/definitions/uint32 mediatek,rdsel: - description: | + description: An integer describing the steps for input level shifter duty cycle when asserted (high pulse width adjustment). Valid arguments are from 0 to 63. diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml index e51667316b2e..43b33dbf115b 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Arınç ÜNAL - Sergio Paracuellos -description: +description: | Ralink RT2880 pin controller for RT2880 SoC. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 23fb82f9959c..55c6f9826e76 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Arınç ÜNAL - Sergio Paracuellos -description: +description: | Ralink RT305X pin controller for RT3050, RT3052, RT3350, RT3352 and RT5350 SoCs. The pin controller can only set the muxing of pin groups. Muxing individual diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml index adc4f42a175d..8d14e525b25e 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml @@ -10,7 +10,7 @@ maintainers: - Arınç ÜNAL - Sergio Paracuellos -description: +description: | Ralink RT3883 pin controller for RT3883 SoC. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. -- GitLab From 03af785ee25a753c6b93ef70130b97020ccfae27 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:06 +0300 Subject: [PATCH 0891/5631] dt-bindings: pinctrl: mediatek: fix pinmux header location MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix the location of the pinmux header files mentioned on the schemas. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-17-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml index 5e80621800a9..3b3d59140073 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml @@ -90,7 +90,7 @@ patternProperties: description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in -pinfunc.h directly. + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml index 1d038f6f8971..e5e7143674b5 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml @@ -131,7 +131,7 @@ patternProperties: description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in boot/dts/-pinfunc.h directly. + defined as macros in dt-bindings/pinctrl/-pinfunc.h directly. bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml index 51b3d1247614..028146fb173f 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml @@ -88,8 +88,8 @@ patternProperties: description: Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are - defined as macros in dt-bindings/pinctrl/mediatek,-pinfunc.h - directly. + defined as macros in dt-bindings/pinctrl/mediatek,mt8188-pinfunc.h + directly, for this SoC. drive-strength: enum: [2, 4, 6, 8, 10, 12, 14, 16] -- GitLab From 6a735ad501816786af9fc372eeace9ce4735bac0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:07 +0300 Subject: [PATCH 0892/5631] dt-bindings: pinctrl: mediatek: drop quotes from referred schemas MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Drop the quotes from the referred schemas. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-18-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mediatek,mt6779-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mediatek,mt6795-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mediatek,mt7622-pinctrl.yaml | 6 +++--- .../bindings/pinctrl/mediatek,mt7986-pinctrl.yaml | 6 +++--- .../bindings/pinctrl/mediatek,mt8183-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mediatek,mt8186-pinctrl.yaml | 2 +- .../bindings/pinctrl/mediatek,mt8188-pinctrl.yaml | 2 +- .../bindings/pinctrl/mediatek,mt8192-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mediatek,mt8195-pinctrl.yaml | 4 ++-- 10 files changed, 20 insertions(+), 20 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml index 3b3d59140073..bccff08a5ba3 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml @@ -67,7 +67,7 @@ required: - "#gpio-cells" allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# patternProperties: 'pins$': @@ -83,7 +83,7 @@ patternProperties: pins it needs, and how they should be configured, with regard to muxer configuration, pullups, drive strength, input enable/disable and input schmitt. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pinmux: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml index e5e7143674b5..7f0e2d6cd6d9 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml @@ -58,7 +58,7 @@ required: - "#gpio-cells" allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: properties: compatible: @@ -124,7 +124,7 @@ patternProperties: pins it needs, and how they should be configured, with regard to muxer configuration, pullups, drive strength, input enable/disable and input schmitt. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pinmux: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml index c3bf98749fa4..601d86aecdd4 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt6795-pinctrl.yaml @@ -82,7 +82,7 @@ patternProperties: } }; }; - $ref: "pinmux-node.yaml" + $ref: pinmux-node.yaml properties: pinmux: @@ -156,7 +156,7 @@ patternProperties: - pinmux allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml index 38dc41c735eb..bd72a326e6e0 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml @@ -43,7 +43,7 @@ properties: const: 2 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible @@ -70,7 +70,7 @@ patternProperties: additionalProperties: false description: pinmux configuration nodes. - $ref: "/schemas/pinctrl/pinmux-node.yaml" + $ref: /schemas/pinctrl/pinmux-node.yaml properties: function: description: @@ -249,7 +249,7 @@ patternProperties: additionalProperties: false description: pinconf configuration nodes. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: groups: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml index 7157500a7f81..31c36689438c 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml @@ -57,7 +57,7 @@ properties: const: 2 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible @@ -128,7 +128,7 @@ patternProperties: "wf_dbdc" "wifi" 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85 - $ref: "/schemas/pinctrl/pinmux-node.yaml" + $ref: /schemas/pinctrl/pinmux-node.yaml properties: function: description: @@ -261,7 +261,7 @@ patternProperties: additionalProperties: false description: pinconf configuration nodes. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pins: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml index 372a3aefa937..bf67d4672455 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml @@ -57,7 +57,7 @@ properties: const: 2 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible @@ -80,7 +80,7 @@ patternProperties: pins it needs, and how they should be configured, with regard to muxer configuration, pullups, drive strength, input enable/disable and input schmitt. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pinmux: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml index eb6a5cdecc6c..69136ddd0bbc 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8186-pinctrl.yaml @@ -94,7 +94,7 @@ patternProperties: } }; }; - $ref: "pinmux-node.yaml" + $ref: pinmux-node.yaml properties: pinmux: diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml index 028146fb173f..e994b0c70dbf 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8188-pinctrl.yaml @@ -74,7 +74,7 @@ patternProperties: patternProperties: '^pins': type: object - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml additionalProperties: false description: A pinctrl node should contain at least one subnode representing the diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml index 8cca1ce40f25..c43338cafd61 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8192-pinctrl.yaml @@ -65,7 +65,7 @@ patternProperties: pins it needs, and how they should be configured, with regard to muxer configuration, pullups, drive strength, input enable/disable and input schmitt. - $ref: "pinmux-node.yaml" + $ref: pinmux-node.yaml properties: pinmux: @@ -126,7 +126,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml index b8ba260d74cd..33cb71775db9 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8195-pinctrl.yaml @@ -87,7 +87,7 @@ patternProperties: } }; }; - $ref: "pinmux-node.yaml" + $ref: pinmux-node.yaml properties: pinmux: @@ -216,7 +216,7 @@ patternProperties: - pinmux allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible -- GitLab From 4b8efbae17e1f2762cd3799970b702bf61dfb5be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:08 +0300 Subject: [PATCH 0893/5631] dt-bindings: pinctrl: mediatek: mt7986: fix patternProperties regex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Set second level patternProperties to '^.*mux.*$' and '^.*conf.*$' on mediatek,mt7986-pinctrl.yaml to be on par with other schemas. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-19-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml index 31c36689438c..0f615ada290a 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7986-pinctrl.yaml @@ -72,7 +72,7 @@ patternProperties: additionalProperties: false patternProperties: - '.*mux.*': + '^.*mux.*$': type: object additionalProperties: false description: | @@ -256,7 +256,7 @@ patternProperties: items: enum: [wf_2g, wf_5g, wf_dbdc] maxItems: 3 - '.*conf.*': + '^.*conf.*$': type: object additionalProperties: false description: -- GitLab From 5c7daf4a06065de15e29a9a14dc22acd4b0062f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:09 +0300 Subject: [PATCH 0894/5631] dt-bindings: pinctrl: ralink: rt305x: split binding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The RT3352 and RT5350 SoCs each contain different pin muxing information, therefore, should be split. This can be done now that there are compatible strings to distinguish them from other SoCs. Split the schema out to ralink,rt3352-pinctrl.yaml and ralink,rt5350-pinctrl.yaml. Remove ralink,rt3352-pinctrl and ralink,rt5350-pinctrl from rt305x. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-20-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../pinctrl/ralink,rt305x-pinctrl.yaml | 83 +----- .../pinctrl/ralink,rt3352-pinctrl.yaml | 243 ++++++++++++++++++ .../pinctrl/ralink,rt5350-pinctrl.yaml | 206 +++++++++++++++ 3 files changed, 455 insertions(+), 77 deletions(-) create mode 100644 Documentation/devicetree/bindings/pinctrl/ralink,rt3352-pinctrl.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/ralink,rt5350-pinctrl.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml index 55c6f9826e76..95a904273009 100644 --- a/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml @@ -11,17 +11,13 @@ maintainers: - Sergio Paracuellos description: | - Ralink RT305X pin controller for RT3050, RT3052, RT3350, RT3352 and RT5350 - SoCs. + Ralink RT305X pin controller for RT3050, RT3052, and RT3350 SoCs. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. properties: compatible: - enum: - - ralink,rt305x-pinctrl - - ralink,rt3352-pinctrl - - ralink,rt5350-pinctrl + const: ralink,rt305x-pinctrl patternProperties: '-pins$': @@ -39,21 +35,9 @@ patternProperties: function: description: A string containing the name of the function to mux to the group. - anyOf: - - description: For RT3050, RT3052 and RT3350 SoCs - enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, mdio, - pcm gpio, pcm i2s, pcm uartf, rgmii, sdram, spi, uartf, - uartlite] - - - description: For RT3352 SoC - enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, - lna, mdio, pa, pcm gpio, pcm i2s, pcm uartf, rgmii, spi, - spi_cs1, uartf, uartlite, wdg_cs1] - - - description: For RT5350 SoC - enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, - pcm gpio, pcm i2s, pcm uartf, spi, spi_cs1, uartf, - uartlite, wdg_cs1] + enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, mdio, + pcm gpio, pcm i2s, pcm uartf, rgmii, sdram, spi, uartf, + uartlite] groups: description: @@ -72,17 +56,7 @@ patternProperties: then: properties: groups: - anyOf: - - description: For RT3050, RT3052 and RT3350 SoCs - enum: [i2c, jtag, mdio, rgmii, sdram, spi, uartf, - uartlite] - - - description: For RT3352 SoC - enum: [i2c, jtag, led, lna, mdio, pa, rgmii, spi, spi_cs1, - uartf, uartlite] - - - description: For RT5350 SoC - enum: [i2c, jtag, led, spi, spi_cs1, uartf, uartlite] + enum: [i2c, jtag, mdio, rgmii, sdram, spi, uartf, uartlite] - if: properties: @@ -129,24 +103,6 @@ patternProperties: groups: enum: [jtag] - - if: - properties: - function: - const: led - then: - properties: - groups: - enum: [led] - - - if: - properties: - function: - const: lna - then: - properties: - groups: - enum: [lna] - - if: properties: function: @@ -156,15 +112,6 @@ patternProperties: groups: enum: [mdio] - - if: - properties: - function: - const: pa - then: - properties: - groups: - enum: [pa] - - if: properties: function: @@ -219,15 +166,6 @@ patternProperties: groups: enum: [spi] - - if: - properties: - function: - const: spi_cs1 - then: - properties: - groups: - enum: [spi_cs1] - - if: properties: function: @@ -246,15 +184,6 @@ patternProperties: groups: enum: [uartlite] - - if: - properties: - function: - const: wdg_cs1 - then: - properties: - groups: - enum: [spi_cs1] - allOf: - $ref: pinctrl.yaml# diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt3352-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt3352-pinctrl.yaml new file mode 100644 index 000000000000..c9bc6cfd834c --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt3352-pinctrl.yaml @@ -0,0 +1,243 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/ralink,rt3352-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Ralink RT3352 Pin Controller + +maintainers: + - Arınç ÜNAL + - Sergio Paracuellos + +description: | + Ralink RT3352 pin controller for RT3352 SoC. + The pin controller can only set the muxing of pin groups. Muxing individual + pins is not supported. There is no pinconf support. + +properties: + compatible: + const: ralink,rt3352-pinctrl + +patternProperties: + '-pins$': + type: object + additionalProperties: false + + patternProperties: + '^(.*-)?pinmux$': + type: object + description: node for pinctrl. + $ref: pinmux-node.yaml# + additionalProperties: false + + properties: + function: + description: + A string containing the name of the function to mux to the group. + enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, lna, + mdio, pa, pcm gpio, pcm i2s, pcm uartf, rgmii, spi, spi_cs1, + uartf, uartlite, wdg_cs1] + + groups: + description: + An array of strings. Each string contains the name of a group. + maxItems: 1 + + required: + - groups + - function + + allOf: + - if: + properties: + function: + const: gpio + then: + properties: + groups: + enum: [i2c, jtag, led, lna, mdio, pa, rgmii, spi, spi_cs1, + uartf, uartlite] + + - if: + properties: + function: + const: gpio i2s + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: gpio uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: i2c + then: + properties: + groups: + enum: [i2c] + + - if: + properties: + function: + const: i2s uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: jtag + then: + properties: + groups: + enum: [jtag] + + - if: + properties: + function: + const: led + then: + properties: + groups: + enum: [led] + + - if: + properties: + function: + const: lna + then: + properties: + groups: + enum: [lna] + + - if: + properties: + function: + const: mdio + then: + properties: + groups: + enum: [mdio] + + - if: + properties: + function: + const: pa + then: + properties: + groups: + enum: [pa] + + - if: + properties: + function: + const: pcm gpio + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: pcm i2s + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: pcm uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: rgmii + then: + properties: + groups: + enum: [rgmii] + + - if: + properties: + function: + const: spi + then: + properties: + groups: + enum: [spi] + + - if: + properties: + function: + const: spi_cs1 + then: + properties: + groups: + enum: [spi_cs1] + + - if: + properties: + function: + const: uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: uartlite + then: + properties: + groups: + enum: [uartlite] + + - if: + properties: + function: + const: wdg_cs1 + then: + properties: + groups: + enum: [spi_cs1] + +allOf: + - $ref: pinctrl.yaml# + +required: + - compatible + +additionalProperties: false + +examples: + - | + pinctrl { + compatible = "ralink,rt3352-pinctrl"; + + i2c_pins: i2c0-pins { + pinmux { + groups = "i2c"; + function = "i2c"; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/ralink,rt5350-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ralink,rt5350-pinctrl.yaml new file mode 100644 index 000000000000..f248202ce866 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/ralink,rt5350-pinctrl.yaml @@ -0,0 +1,206 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/ralink,rt5350-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Ralink RT5350 Pin Controller + +maintainers: + - Arınç ÜNAL + - Sergio Paracuellos + +description: | + Ralink RT5350 pin controller for RT5350 SoC. + The pin controller can only set the muxing of pin groups. Muxing individual + pins is not supported. There is no pinconf support. + +properties: + compatible: + const: ralink,rt5350-pinctrl + +patternProperties: + '-pins$': + type: object + additionalProperties: false + + patternProperties: + '^(.*-)?pinmux$': + type: object + description: node for pinctrl. + $ref: pinmux-node.yaml# + additionalProperties: false + + properties: + function: + description: + A string containing the name of the function to mux to the group. + enum: [gpio, gpio i2s, gpio uartf, i2c, i2s uartf, jtag, led, + pcm gpio, pcm i2s, pcm uartf, spi, spi_cs1, uartf, uartlite, + wdg_cs1] + + groups: + description: + An array of strings. Each string contains the name of a group. + maxItems: 1 + + required: + - groups + - function + + allOf: + - if: + properties: + function: + const: gpio + then: + properties: + groups: + enum: [i2c, jtag, led, spi, spi_cs1, uartf, uartlite] + + - if: + properties: + function: + const: gpio i2s + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: gpio uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: i2c + then: + properties: + groups: + enum: [i2c] + + - if: + properties: + function: + const: i2s uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: jtag + then: + properties: + groups: + enum: [jtag] + + - if: + properties: + function: + const: led + then: + properties: + groups: + enum: [led] + + - if: + properties: + function: + const: pcm gpio + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: pcm i2s + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: pcm uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: spi + then: + properties: + groups: + enum: [spi] + + - if: + properties: + function: + const: spi_cs1 + then: + properties: + groups: + enum: [spi_cs1] + + - if: + properties: + function: + const: uartf + then: + properties: + groups: + enum: [uartf] + + - if: + properties: + function: + const: uartlite + then: + properties: + groups: + enum: [uartlite] + + - if: + properties: + function: + const: wdg_cs1 + then: + properties: + groups: + enum: [spi_cs1] + +allOf: + - $ref: pinctrl.yaml# + +required: + - compatible + +additionalProperties: false + +examples: + - | + pinctrl { + compatible = "ralink,rt5350-pinctrl"; + + i2c_pins: i2c0-pins { + pinmux { + groups = "i2c"; + function = "i2c"; + }; + }; + }; -- GitLab From 565afac7a37ab861f62edcb0683bc8d67949fc92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:10 +0300 Subject: [PATCH 0895/5631] dt-bindings: pinctrl: mediatek: mt7620: split binding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The MT7628 and MT7688 SoCs contain different pin muxing information, therefore, should be split. This can be done now that there are compatible strings to distinguish them from other SoCs. Split the schema out to mediatek,mt76x8-pinctrl.yaml. Remove mediatek,mt76x8-pinctrl from mt7620. Signed-off-by: Arınç ÜNAL Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230317213011.13656-21-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- .../pinctrl/mediatek,mt7620-pinctrl.yaml | 379 +-------------- .../pinctrl/mediatek,mt76x8-pinctrl.yaml | 450 ++++++++++++++++++ 2 files changed, 459 insertions(+), 370 deletions(-) create mode 100644 Documentation/devicetree/bindings/pinctrl/mediatek,mt76x8-pinctrl.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml index 808dd8bd276f..591bc0664ec6 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml @@ -11,15 +11,13 @@ maintainers: - Sergio Paracuellos description: | - MediaTek MT7620 pin controller for MT7620, MT7628 and MT7688 SoCs. + MediaTek MT7620 pin controller for MT7620 SoC. The pin controller can only set the muxing of pin groups. Muxing individual pins is not supported. There is no pinconf support. properties: compatible: - enum: - - ralink,mt7620-pinctrl - - ralink,mt76x8-pinctrl + const: ralink,mt7620-pinctrl patternProperties: '-pins$': @@ -37,19 +35,10 @@ patternProperties: function: description: A string containing the name of the function to mux to the group. - anyOf: - - description: For MT7620 SoC - enum: [ephy, gpio, gpio i2s, gpio uartf, i2c, i2s uartf, mdio, nand, pa, - pcie refclk, pcie rst, pcm gpio, pcm i2s, pcm uartf, refclk, - rgmii1, rgmii2, sd, spi, spi refclk, uartf, uartlite, wdt refclk, - wdt rst, wled] - - - description: For MT7628 and MT7688 SoCs - enum: [antenna, debug, gpio, i2c, i2s, jtag, p0led_an, p0led_kn, - p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, p3led_kn, - p4led_an, p4led_kn, pcie, pcm, perst, pwm, pwm0, pwm1, pwm_uart2, - refclk, rsvd, sdxc, sdxc d5 d4, sdxc d6, sdxc d7, spi, spi cs1, - spis, sw_r, uart0, uart1, uart2, utif, wdt, wled_an, wled_kn, -] + enum: [ephy, gpio, gpio i2s, gpio uartf, i2c, i2s uartf, mdio, nand, + pa, pcie refclk, pcie rst, pcm gpio, pcm i2s, pcm uartf, + refclk, rgmii1, rgmii2, sd, spi, spi refclk, uartf, uartlite, + wdt refclk, wdt rst, wled] groups: description: @@ -61,24 +50,6 @@ patternProperties: - function allOf: - - if: - properties: - function: - const: antenna - then: - properties: - groups: - enum: [i2s] - - - if: - properties: - function: - const: debug - then: - properties: - groups: - enum: [i2c] - - if: properties: function: @@ -95,17 +66,8 @@ patternProperties: then: properties: groups: - anyOf: - - description: For MT7620 SoC - enum: [ephy, i2c, mdio, nd_sd, pa, pcie, rgmii1, rgmii2, - spi, spi refclk, uartf, uartlite, wdt, wled] - - - description: For MT7628 and MT7688 SoCs - enum: [gpio, i2c, i2s, p0led_an, p0led_kn, p1led_an, - p1led_kn, p2led_an, p2led_kn, p3led_an, p3led_kn, - p4led_an, p4led_kn, perst, pwm0, pwm1, refclk, - sdmode, spi, spi cs1, spis, uart0, uart1, uart2, - wdt, wled_an, wled_kn] + enum: [ephy, i2c, mdio, nd_sd, pa, pcie, rgmii1, rgmii2, spi, + spi refclk, uartf, uartlite, wdt, wled] - if: properties: @@ -134,15 +96,6 @@ patternProperties: groups: enum: [i2c] - - if: - properties: - function: - const: i2s - then: - properties: - groups: - enum: [i2s] - - if: properties: function: @@ -152,17 +105,6 @@ patternProperties: groups: enum: [uartf] - - if: - properties: - function: - const: jtag - then: - properties: - groups: - enum: [p0led_an, p0led_kn, p1led_an, p1led_kn, p2led_an, - p2led_kn, p3led_an, p3led_kn, p4led_an, p4led_kn, - sdmode] - - if: properties: function: @@ -181,96 +123,6 @@ patternProperties: groups: enum: [nd_sd] - - if: - properties: - function: - const: p0led_an - then: - properties: - groups: - enum: [p0led_an] - - - if: - properties: - function: - const: p0led_kn - then: - properties: - groups: - enum: [p0led_kn] - - - if: - properties: - function: - const: p1led_an - then: - properties: - groups: - enum: [p1led_an] - - - if: - properties: - function: - const: p1led_kn - then: - properties: - groups: - enum: [p1led_kn] - - - if: - properties: - function: - const: p2led_an - then: - properties: - groups: - enum: [p2led_an] - - - if: - properties: - function: - const: p2led_kn - then: - properties: - groups: - enum: [p2led_kn] - - - if: - properties: - function: - const: p3led_an - then: - properties: - groups: - enum: [p3led_an] - - - if: - properties: - function: - const: p3led_kn - then: - properties: - groups: - enum: [p3led_kn] - - - if: - properties: - function: - const: p4led_an - then: - properties: - groups: - enum: [p4led_an] - - - if: - properties: - function: - const: p4led_kn - then: - properties: - groups: - enum: [p4led_kn] - - if: properties: function: @@ -280,15 +132,6 @@ patternProperties: groups: enum: [pa] - - if: - properties: - function: - const: pcie - then: - properties: - groups: - enum: [gpio] - - if: properties: function: @@ -307,15 +150,6 @@ patternProperties: groups: enum: [pcie] - - if: - properties: - function: - const: pcm - then: - properties: - groups: - enum: [i2s] - - if: properties: function: @@ -343,51 +177,6 @@ patternProperties: groups: enum: [uartf] - - if: - properties: - function: - const: perst - then: - properties: - groups: - enum: [perst] - - - if: - properties: - function: - const: pwm - then: - properties: - groups: - enum: [uart1, uart2] - - - if: - properties: - function: - const: pwm0 - then: - properties: - groups: - enum: [pwm0] - - - if: - properties: - function: - const: pwm1 - then: - properties: - groups: - enum: [pwm1] - - - if: - properties: - function: - const: pwm_uart2 - then: - properties: - groups: - enum: [spis] - - if: properties: function: @@ -395,12 +184,7 @@ patternProperties: then: properties: groups: - anyOf: - - description: For MT7620 SoC - enum: [mdio] - - - description: For MT7628 and MT7688 SoCs - enum: [gpio, refclk, spi cs1] + enum: [mdio] - if: properties: @@ -420,15 +204,6 @@ patternProperties: groups: enum: [rgmii2] - - if: - properties: - function: - const: rsvd - then: - properties: - groups: - enum: [p0led_an, p0led_kn, wled_an, wled_kn] - - if: properties: function: @@ -438,42 +213,6 @@ patternProperties: groups: enum: [nd_sd] - - if: - properties: - function: - const: sdxc - then: - properties: - groups: - enum: [sdmode] - - - if: - properties: - function: - const: sdxc d5 d4 - then: - properties: - groups: - enum: [uart2] - - - if: - properties: - function: - const: sdxc d6 - then: - properties: - groups: - enum: [pwm1] - - - if: - properties: - function: - const: sdxc d7 - then: - properties: - groups: - enum: [pwm0] - - if: properties: function: @@ -483,15 +222,6 @@ patternProperties: groups: enum: [spi] - - if: - properties: - function: - const: spi cs1 - then: - properties: - groups: - enum: [spi cs1] - - if: properties: function: @@ -501,51 +231,6 @@ patternProperties: groups: enum: [spi refclk] - - if: - properties: - function: - const: spis - then: - properties: - groups: - enum: [spis] - - - if: - properties: - function: - const: sw_r - then: - properties: - groups: - enum: [uart1] - - - if: - properties: - function: - const: uart0 - then: - properties: - groups: - enum: [uart0] - - - if: - properties: - function: - const: uart1 - then: - properties: - groups: - enum: [uart1] - - - if: - properties: - function: - const: uart2 - then: - properties: - groups: - enum: [uart2] - - if: properties: function: @@ -564,25 +249,6 @@ patternProperties: groups: enum: [uartlite] - - if: - properties: - function: - const: utif - then: - properties: - groups: - enum: [p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, - p3led_kn, p4led_an, p4led_kn, pwm0, pwm1, sdmode, spis] - - - if: - properties: - function: - const: wdt - then: - properties: - groups: - enum: [wdt] - - if: properties: function: @@ -610,33 +276,6 @@ patternProperties: groups: enum: [wled] - - if: - properties: - function: - const: wled_an - then: - properties: - groups: - enum: [wled_an] - - - if: - properties: - function: - const: wled_kn - then: - properties: - groups: - enum: [wled_kn] - - - if: - properties: - function: - const: "-" - then: - properties: - groups: - enum: [i2c, spi cs1, uart0] - allOf: - $ref: pinctrl.yaml# diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt76x8-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt76x8-pinctrl.yaml new file mode 100644 index 000000000000..31849dd5940b --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt76x8-pinctrl.yaml @@ -0,0 +1,450 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/mediatek,mt76x8-pinctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek MT76X8 Pin Controller + +maintainers: + - Arınç ÜNAL + - Sergio Paracuellos + +description: | + MediaTek MT76X8 pin controller for MT7628 and MT7688 SoCs. + The pin controller can only set the muxing of pin groups. Muxing individual + pins is not supported. There is no pinconf support. + +properties: + compatible: + const: ralink,mt76x8-pinctrl + +patternProperties: + '-pins$': + type: object + additionalProperties: false + + patternProperties: + '^(.*-)?pinmux$': + type: object + description: node for pinctrl. + $ref: pinmux-node.yaml# + additionalProperties: false + + properties: + function: + description: + A string containing the name of the function to mux to the group. + enum: [antenna, debug, gpio, i2c, i2s, jtag, p0led_an, p0led_kn, + p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, p3led_kn, + p4led_an, p4led_kn, pcie, pcm, perst, pwm, pwm0, pwm1, + pwm_uart2, refclk, rsvd, sdxc, sdxc d5 d4, sdxc d6, sdxc d7, + spi, spi cs1, spis, sw_r, uart0, uart1, uart2, utif, wdt, + wled_an, wled_kn, -] + + groups: + description: + An array of strings. Each string contains the name of a group. + maxItems: 1 + + required: + - groups + - function + + allOf: + - if: + properties: + function: + const: antenna + then: + properties: + groups: + enum: [i2s] + + - if: + properties: + function: + const: debug + then: + properties: + groups: + enum: [i2c] + + - if: + properties: + function: + const: gpio + then: + properties: + groups: + enum: [gpio, i2c, i2s, p0led_an, p0led_kn, p1led_an, p1led_kn, + p2led_an, p2led_kn, p3led_an, p3led_kn, p4led_an, + p4led_kn, perst, pwm0, pwm1, refclk, sdmode, spi, + spi cs1, spis, uart0, uart1, uart2, wdt, wled_an, + wled_kn] + + - if: + properties: + function: + const: i2c + then: + properties: + groups: + enum: [i2c] + + - if: + properties: + function: + const: i2s + then: + properties: + groups: + enum: [i2s] + + - if: + properties: + function: + const: jtag + then: + properties: + groups: + enum: [p0led_an, p0led_kn, p1led_an, p1led_kn, p2led_an, + p2led_kn, p3led_an, p3led_kn, p4led_an, p4led_kn, + sdmode] + + - if: + properties: + function: + const: p0led_an + then: + properties: + groups: + enum: [p0led_an] + + - if: + properties: + function: + const: p0led_kn + then: + properties: + groups: + enum: [p0led_kn] + + - if: + properties: + function: + const: p1led_an + then: + properties: + groups: + enum: [p1led_an] + + - if: + properties: + function: + const: p1led_kn + then: + properties: + groups: + enum: [p1led_kn] + + - if: + properties: + function: + const: p2led_an + then: + properties: + groups: + enum: [p2led_an] + + - if: + properties: + function: + const: p2led_kn + then: + properties: + groups: + enum: [p2led_kn] + + - if: + properties: + function: + const: p3led_an + then: + properties: + groups: + enum: [p3led_an] + + - if: + properties: + function: + const: p3led_kn + then: + properties: + groups: + enum: [p3led_kn] + + - if: + properties: + function: + const: p4led_an + then: + properties: + groups: + enum: [p4led_an] + + - if: + properties: + function: + const: p4led_kn + then: + properties: + groups: + enum: [p4led_kn] + + - if: + properties: + function: + const: pcie + then: + properties: + groups: + enum: [gpio] + + - if: + properties: + function: + const: pcm + then: + properties: + groups: + enum: [i2s] + + - if: + properties: + function: + const: perst + then: + properties: + groups: + enum: [perst] + + - if: + properties: + function: + const: pwm + then: + properties: + groups: + enum: [uart1, uart2] + + - if: + properties: + function: + const: pwm0 + then: + properties: + groups: + enum: [pwm0] + + - if: + properties: + function: + const: pwm1 + then: + properties: + groups: + enum: [pwm1] + + - if: + properties: + function: + const: pwm_uart2 + then: + properties: + groups: + enum: [spis] + + - if: + properties: + function: + const: refclk + then: + properties: + groups: + enum: [gpio, refclk, spi cs1] + + - if: + properties: + function: + const: rsvd + then: + properties: + groups: + enum: [p0led_an, p0led_kn, wled_an, wled_kn] + + - if: + properties: + function: + const: sdxc + then: + properties: + groups: + enum: [sdmode] + + - if: + properties: + function: + const: sdxc d5 d4 + then: + properties: + groups: + enum: [uart2] + + - if: + properties: + function: + const: sdxc d6 + then: + properties: + groups: + enum: [pwm1] + + - if: + properties: + function: + const: sdxc d7 + then: + properties: + groups: + enum: [pwm0] + + - if: + properties: + function: + const: spi + then: + properties: + groups: + enum: [spi] + + - if: + properties: + function: + const: spi cs1 + then: + properties: + groups: + enum: [spi cs1] + + - if: + properties: + function: + const: spis + then: + properties: + groups: + enum: [spis] + + - if: + properties: + function: + const: sw_r + then: + properties: + groups: + enum: [uart1] + + - if: + properties: + function: + const: uart0 + then: + properties: + groups: + enum: [uart0] + + - if: + properties: + function: + const: uart1 + then: + properties: + groups: + enum: [uart1] + + - if: + properties: + function: + const: uart2 + then: + properties: + groups: + enum: [uart2] + + - if: + properties: + function: + const: utif + then: + properties: + groups: + enum: [p1led_an, p1led_kn, p2led_an, p2led_kn, p3led_an, + p3led_kn, p4led_an, p4led_kn, pwm0, pwm1, sdmode, spis] + + - if: + properties: + function: + const: wdt + then: + properties: + groups: + enum: [wdt] + + - if: + properties: + function: + const: wled_an + then: + properties: + groups: + enum: [wled_an] + + - if: + properties: + function: + const: wled_kn + then: + properties: + groups: + enum: [wled_kn] + + - if: + properties: + function: + const: "-" + then: + properties: + groups: + enum: [i2c, spi cs1, uart0] + +allOf: + - $ref: pinctrl.yaml# + +required: + - compatible + +additionalProperties: false + +examples: + - | + pinctrl { + compatible = "ralink,mt76x8-pinctrl"; + + i2c_pins: i2c0-pins { + pinmux { + groups = "i2c"; + function = "i2c"; + }; + }; + }; -- GitLab From c7c4891bc787850a86e3c797f754bb1623e171ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Sat, 18 Mar 2023 00:30:11 +0300 Subject: [PATCH 0896/5631] MAINTAINERS: move ralink pinctrl to mediatek mips pinctrl MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Ralink pinctrl driver is now under the name of MediaTek MIPS pin controller. Move the maintainer information accordingly. Add dt-binding schema files. Add linux-mediatek@lists.infradead.org as an associated mailing list. Signed-off-by: Arınç ÜNAL Acked-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230317213011.13656-22-arinc.unal@arinc9.com Signed-off-by: Linus Walleij --- MAINTAINERS | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 6048bbe0e672..f4ee11dab1ab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16521,6 +16521,28 @@ F: Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml F: Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml F: drivers/pinctrl/mediatek/ +PIN CONTROLLER - MEDIATEK MIPS +M: Arınç ÜNAL +M: Sergio Paracuellos +L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) +L: linux-mips@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pinctrl/mediatek,mt7620-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/mediatek,mt7621-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/mediatek,mt76x8-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/ralink,rt2880-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/ralink,rt305x-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/ralink,rt3352-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/ralink,rt3883-pinctrl.yaml +F: Documentation/devicetree/bindings/pinctrl/ralink,rt5350-pinctrl.yaml +F: drivers/pinctrl/mediatek/pinctrl-mt7620.c +F: drivers/pinctrl/mediatek/pinctrl-mt7621.c +F: drivers/pinctrl/mediatek/pinctrl-mt76x8.c +F: drivers/pinctrl/mediatek/pinctrl-mtmips.* +F: drivers/pinctrl/mediatek/pinctrl-rt2880.c +F: drivers/pinctrl/mediatek/pinctrl-rt305x.c +F: drivers/pinctrl/mediatek/pinctrl-rt3883.c + PIN CONTROLLER - MICROCHIP AT91 M: Ludovic Desroches L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -17496,13 +17518,6 @@ L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/boot/dts/ralink/mt7621* -RALINK PINCTRL DRIVER -M: Arınç ÜNAL -M: Sergio Paracuellos -L: linux-mips@vger.kernel.org -S: Maintained -F: drivers/pinctrl/ralink/ - RALINK RT2X00 WIRELESS LAN DRIVER M: Stanislaw Gruszka M: Helmut Schaa -- GitLab From 709d60b5dfbfc7d2973ad6085cb1117e827cfc8d Mon Sep 17 00:00:00 2001 From: Danila Tikhonov Date: Sun, 12 Mar 2023 00:21:13 +0300 Subject: [PATCH 0897/5631] dt-bindings: pinctrl: qcom: Add SM7150 pinctrl binding Add device tree binding Documentation details for Qualcomm SM7150 TLMM device Signed-off-by: Danila Tikhonov Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311212114.108870-2-danila@jiaxyga.com Signed-off-by: Linus Walleij --- .../bindings/pinctrl/qcom,sm7150-tlmm.yaml | 162 ++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml new file mode 100644 index 000000000000..a57d44efe5bd --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm7150-tlmm.yaml @@ -0,0 +1,162 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/qcom,sm7150-tlmm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm SM7150 TLMM pin controller + +maintainers: + - Bjorn Andersson + - Danila Tikhonov + +description: + Top Level Mode Multiplexer pin controller in Qualcomm SM7150 SoC. + +allOf: + - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# + +properties: + compatible: + const: qcom,sm7150-tlmm + + reg: + maxItems: 3 + + reg-names: + items: + - const: west + - const: north + - const: south + + interrupts: + maxItems: 1 + + interrupt-controller: true + "#interrupt-cells": true + gpio-controller: true + "#gpio-cells": true + gpio-ranges: true + wakeup-parent: true + + gpio-reserved-ranges: + minItems: 1 + maxItems: 60 + + gpio-line-names: + maxItems: 119 + +patternProperties: + "-state$": + oneOf: + - $ref: "#/$defs/qcom-sm7150-tlmm-state" + - patternProperties: + "-pins$": + $ref: "#/$defs/qcom-sm7150-tlmm-state" + additionalProperties: false + +$defs: + qcom-sm7150-tlmm-state: + type: object + description: + Pinctrl node's client devices use subnodes for desired pin configuration. + Client device subnodes use below standard properties. + $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + + properties: + pins: + description: + List of gpio pins affected by the properties specified in this + subnode. + items: + oneOf: + - pattern: "^gpio([0-9]|[1-9][0-9]|10[0-9]|11[0-8])$" + - enum: [ sdc1_rclk, sdc1_clk, sdc1_cmd, sdc1_data, sdc2_clk, + sdc2_cmd, sdc2_data, ufs_reset ] + minItems: 1 + maxItems: 36 + + function: + description: + Specify the alternative function to be configured for the specified + pins. + + enum: [ gpio, adsp_ext, agera_pll, aoss_cti, atest_char, atest_tsens, + atest_tsens2, atest_usb1, atest_usb2, cam_mclk, cci_async, + cci_i2c, cci_timer0, cci_timer1, cci_timer2, cci_timer3, + cci_timer4, dbg_out, ddr_bist, ddr_pxi0, ddr_pxi1, ddr_pxi2, + ddr_pxi3, edp_hot, edp_lcd, gcc_gp1, gcc_gp2, gcc_gp3, gp_pdm0, + gp_pdm1, gp_pdm2, gps_tx, jitter_bist, ldo_en, ldo_update, + m_voc, mdp_vsync, mdp_vsync0, mdp_vsync1, mdp_vsync2, + mdp_vsync3, mss_lte, nav_pps_in, nav_pps_out, pa_indicator, + pci_e, phase_flag, pll_bist, pll_bypassnl, pll_reset, pri_mi2s, + pri_mi2s_ws, prng_rosc, qdss, qdss_cti, qlink_enable, + qlink_request, qua_mi2s, qup00, qup01, qup02, qup03, qup04, + qup10, qup11, qup12, qup13, qup14, qup15, sd_write, sdc40, + sdc41, sdc42, sdc43, sdc4_clk, sdc4_cmd, sec_mi2s, ter_mi2s, + tgu_ch0, tgu_ch1, tgu_ch2, tgu_ch3, tsif1_clk, tsif1_data, + tsif1_en, tsif1_error, tsif1_sync, tsif2_clk, tsif2_data, + tsif2_en, tsif2_error, tsif2_sync, uim1_clk, uim1_data, + uim1_present, uim1_reset, uim2_clk, uim2_data, uim2_present, + uim2_reset, uim_batt, usb_phy, vfr_1, vsense_trigger, + wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, wsa_clk, + wsa_data ] + + bias-pull-down: true + bias-pull-up: true + bias-disable: true + drive-strength: true + input-enable: true + output-high: true + output-low: true + + required: + - pins + + additionalProperties: false + +required: + - compatible + - reg + - reg-names + +additionalProperties: false + +examples: + - | + #include + + tlmm: pinctrl@3500000 { + compatible = "qcom,sm7150-tlmm"; + reg = <0x03500000 0x300000>, + <0x03900000 0x300000>, + <0x03d00000 0x300000>; + reg-names = "west", "north", "south"; + interrupts = ; + gpio-ranges = <&tlmm 0 0 120>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + wakeup-parent = <&pdc>; + + gpio-wo-state { + pins = "gpio1"; + function = "gpio"; + }; + + uart-w-state { + rx-pins { + pins = "gpio44"; + function = "qup12"; + bias-pull-up; + }; + + tx-pins { + pins = "gpio45"; + function = "qup12"; + bias-disable; + }; + }; + }; +... -- GitLab From b915395c9e04361926ec329f784a1a6fda033492 Mon Sep 17 00:00:00 2001 From: Danila Tikhonov Date: Sun, 12 Mar 2023 00:21:14 +0300 Subject: [PATCH 0898/5631] pinctrl: qcom: Add SM7150 pinctrl driver Add pinctrl driver for TLMM block found in SM7150 SoC. Signed-off-by: Danila Tikhonov Link: https://lore.kernel.org/r/20230311212114.108870-3-danila@jiaxyga.com Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/Kconfig | 10 + drivers/pinctrl/qcom/Makefile | 1 + drivers/pinctrl/qcom/pinctrl-sm7150.c | 1280 +++++++++++++++++++++++++ 3 files changed, 1291 insertions(+) create mode 100644 drivers/pinctrl/qcom/pinctrl-sm7150.c diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 62d4810cfee1..be40bcb23caf 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -417,6 +417,16 @@ config PINCTRL_SDX65 Qualcomm Technologies Inc TLMM block found on the Qualcomm Technologies Inc SDX65 platform. +config PINCTRL_SM7150 + tristate "Qualcomm Technologies Inc SM7150 pin controller driver" + depends on OF + depends on ARM64 || COMPILE_TEST + depends on PINCTRL_MSM + help + This is the pinctrl, pinmux, pinconf and gpiolib driver for the + Qualcomm Technologies Inc TLMM block found on the Qualcomm + Technologies Inc SM7150 platform. + config PINCTRL_SM8150 tristate "Qualcomm Technologies Inc SM8150 pin controller driver" depends on OF diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile index bea53b52275b..22b1286a8def 100644 --- a/drivers/pinctrl/qcom/Makefile +++ b/drivers/pinctrl/qcom/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_PINCTRL_SM6125) += pinctrl-sm6125.o obj-$(CONFIG_PINCTRL_SM6350) += pinctrl-sm6350.o obj-$(CONFIG_PINCTRL_SM6375) += pinctrl-sm6375.o obj-$(CONFIG_PINCTRL_SDX65) += pinctrl-sdx65.o +obj-$(CONFIG_PINCTRL_SM7150) += pinctrl-sm7150.o obj-$(CONFIG_PINCTRL_SM8150) += pinctrl-sm8150.o obj-$(CONFIG_PINCTRL_SM8250) += pinctrl-sm8250.o obj-$(CONFIG_PINCTRL_SM8250_LPASS_LPI) += pinctrl-sm8250-lpass-lpi.o diff --git a/drivers/pinctrl/qcom/pinctrl-sm7150.c b/drivers/pinctrl/qcom/pinctrl-sm7150.c new file mode 100644 index 000000000000..2a87e3f144fd --- /dev/null +++ b/drivers/pinctrl/qcom/pinctrl-sm7150.c @@ -0,0 +1,1280 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Danila Tikhonov + */ + +#include +#include +#include +#include + +#include "pinctrl-msm.h" + +static const char * const sm7150_tiles[] = { + "north", + "south", + "west", +}; + +enum { + NORTH, + SOUTH, + WEST +}; + +#define FUNCTION(fname) \ + [msm_mux_##fname] = { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +#define REG_SIZE 0x1000 + +#define PINGROUP(id, _tile, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ + { \ + .name = "gpio" #id, \ + .pins = gpio##id##_pins, \ + .npins = ARRAY_SIZE(gpio##id##_pins), \ + .funcs = (int[]){ \ + msm_mux_gpio, /* gpio mode */ \ + msm_mux_##f1, \ + msm_mux_##f2, \ + msm_mux_##f3, \ + msm_mux_##f4, \ + msm_mux_##f5, \ + msm_mux_##f6, \ + msm_mux_##f7, \ + msm_mux_##f8, \ + msm_mux_##f9 \ + }, \ + .nfuncs = 10, \ + .ctl_reg = REG_SIZE * id, \ + .io_reg = 0x4 + REG_SIZE * id, \ + .intr_cfg_reg = 0x8 + REG_SIZE * id, \ + .intr_status_reg = 0xc + REG_SIZE * id, \ + .intr_target_reg = 0x8 + REG_SIZE * id, \ + .tile = _tile, \ + .mux_bit = 2, \ + .pull_bit = 0, \ + .drv_bit = 6, \ + .oe_bit = 9, \ + .in_bit = 0, \ + .out_bit = 1, \ + .intr_enable_bit = 0, \ + .intr_status_bit = 0, \ + .intr_target_bit = 5, \ + .intr_target_kpss_val = 3, \ + .intr_raw_status_bit = 4, \ + .intr_polarity_bit = 1, \ + .intr_detection_bit = 2, \ + .intr_detection_width = 2, \ + } + +#define SDC_QDSD_PINGROUP(pg_name, ctl, pull, drv) \ + { \ + .name = #pg_name, \ + .pins = pg_name##_pins, \ + .npins = ARRAY_SIZE(pg_name##_pins), \ + .ctl_reg = ctl, \ + .io_reg = 0, \ + .intr_cfg_reg = 0, \ + .intr_status_reg = 0, \ + .intr_target_reg = 0, \ + .tile = SOUTH, \ + .mux_bit = -1, \ + .pull_bit = pull, \ + .drv_bit = drv, \ + .oe_bit = -1, \ + .in_bit = -1, \ + .out_bit = -1, \ + .intr_enable_bit = -1, \ + .intr_status_bit = -1, \ + .intr_target_bit = -1, \ + .intr_raw_status_bit = -1, \ + .intr_polarity_bit = -1, \ + .intr_detection_bit = -1, \ + .intr_detection_width = -1, \ + } + +#define UFS_RESET(pg_name, offset) \ + { \ + .name = #pg_name, \ + .pins = pg_name##_pins, \ + .npins = ARRAY_SIZE(pg_name##_pins), \ + .ctl_reg = offset, \ + .io_reg = offset + 0x4, \ + .intr_cfg_reg = 0, \ + .intr_status_reg = 0, \ + .intr_target_reg = 0, \ + .tile = SOUTH, \ + .mux_bit = -1, \ + .pull_bit = 3, \ + .drv_bit = 0, \ + .oe_bit = -1, \ + .in_bit = -1, \ + .out_bit = 0, \ + .intr_enable_bit = -1, \ + .intr_status_bit = -1, \ + .intr_target_bit = -1, \ + .intr_raw_status_bit = -1, \ + .intr_polarity_bit = -1, \ + .intr_detection_bit = -1, \ + .intr_detection_width = -1, \ + } + +static const struct pinctrl_pin_desc sm7150_pins[] = { + PINCTRL_PIN(0, "GPIO_0"), + PINCTRL_PIN(1, "GPIO_1"), + PINCTRL_PIN(2, "GPIO_2"), + PINCTRL_PIN(3, "GPIO_3"), + PINCTRL_PIN(4, "GPIO_4"), + PINCTRL_PIN(5, "GPIO_5"), + PINCTRL_PIN(6, "GPIO_6"), + PINCTRL_PIN(7, "GPIO_7"), + PINCTRL_PIN(8, "GPIO_8"), + PINCTRL_PIN(9, "GPIO_9"), + PINCTRL_PIN(10, "GPIO_10"), + PINCTRL_PIN(11, "GPIO_11"), + PINCTRL_PIN(12, "GPIO_12"), + PINCTRL_PIN(13, "GPIO_13"), + PINCTRL_PIN(14, "GPIO_14"), + PINCTRL_PIN(15, "GPIO_15"), + PINCTRL_PIN(16, "GPIO_16"), + PINCTRL_PIN(17, "GPIO_17"), + PINCTRL_PIN(18, "GPIO_18"), + PINCTRL_PIN(19, "GPIO_19"), + PINCTRL_PIN(20, "GPIO_20"), + PINCTRL_PIN(21, "GPIO_21"), + PINCTRL_PIN(22, "GPIO_22"), + PINCTRL_PIN(23, "GPIO_23"), + PINCTRL_PIN(24, "GPIO_24"), + PINCTRL_PIN(25, "GPIO_25"), + PINCTRL_PIN(26, "GPIO_26"), + PINCTRL_PIN(27, "GPIO_27"), + PINCTRL_PIN(28, "GPIO_28"), + PINCTRL_PIN(29, "GPIO_29"), + PINCTRL_PIN(30, "GPIO_30"), + PINCTRL_PIN(31, "GPIO_31"), + PINCTRL_PIN(32, "GPIO_32"), + PINCTRL_PIN(33, "GPIO_33"), + PINCTRL_PIN(34, "GPIO_34"), + PINCTRL_PIN(35, "GPIO_35"), + PINCTRL_PIN(36, "GPIO_36"), + PINCTRL_PIN(37, "GPIO_37"), + PINCTRL_PIN(38, "GPIO_38"), + PINCTRL_PIN(39, "GPIO_39"), + PINCTRL_PIN(40, "GPIO_40"), + PINCTRL_PIN(41, "GPIO_41"), + PINCTRL_PIN(42, "GPIO_42"), + PINCTRL_PIN(43, "GPIO_43"), + PINCTRL_PIN(44, "GPIO_44"), + PINCTRL_PIN(45, "GPIO_45"), + PINCTRL_PIN(46, "GPIO_46"), + PINCTRL_PIN(47, "GPIO_47"), + PINCTRL_PIN(48, "GPIO_48"), + PINCTRL_PIN(49, "GPIO_49"), + PINCTRL_PIN(50, "GPIO_50"), + PINCTRL_PIN(51, "GPIO_51"), + PINCTRL_PIN(52, "GPIO_52"), + PINCTRL_PIN(53, "GPIO_53"), + PINCTRL_PIN(54, "GPIO_54"), + PINCTRL_PIN(55, "GPIO_55"), + PINCTRL_PIN(56, "GPIO_56"), + PINCTRL_PIN(57, "GPIO_57"), + PINCTRL_PIN(58, "GPIO_58"), + PINCTRL_PIN(59, "GPIO_59"), + PINCTRL_PIN(60, "GPIO_60"), + PINCTRL_PIN(61, "GPIO_61"), + PINCTRL_PIN(62, "GPIO_62"), + PINCTRL_PIN(63, "GPIO_63"), + PINCTRL_PIN(64, "GPIO_64"), + PINCTRL_PIN(65, "GPIO_65"), + PINCTRL_PIN(66, "GPIO_66"), + PINCTRL_PIN(67, "GPIO_67"), + PINCTRL_PIN(68, "GPIO_68"), + PINCTRL_PIN(69, "GPIO_69"), + PINCTRL_PIN(70, "GPIO_70"), + PINCTRL_PIN(71, "GPIO_71"), + PINCTRL_PIN(72, "GPIO_72"), + PINCTRL_PIN(73, "GPIO_73"), + PINCTRL_PIN(74, "GPIO_74"), + PINCTRL_PIN(75, "GPIO_75"), + PINCTRL_PIN(76, "GPIO_76"), + PINCTRL_PIN(77, "GPIO_77"), + PINCTRL_PIN(78, "GPIO_78"), + PINCTRL_PIN(79, "GPIO_79"), + PINCTRL_PIN(80, "GPIO_80"), + PINCTRL_PIN(81, "GPIO_81"), + PINCTRL_PIN(82, "GPIO_82"), + PINCTRL_PIN(83, "GPIO_83"), + PINCTRL_PIN(84, "GPIO_84"), + PINCTRL_PIN(85, "GPIO_85"), + PINCTRL_PIN(86, "GPIO_86"), + PINCTRL_PIN(87, "GPIO_87"), + PINCTRL_PIN(88, "GPIO_88"), + PINCTRL_PIN(89, "GPIO_89"), + PINCTRL_PIN(90, "GPIO_90"), + PINCTRL_PIN(91, "GPIO_91"), + PINCTRL_PIN(92, "GPIO_92"), + PINCTRL_PIN(93, "GPIO_93"), + PINCTRL_PIN(94, "GPIO_94"), + PINCTRL_PIN(95, "GPIO_95"), + PINCTRL_PIN(96, "GPIO_96"), + PINCTRL_PIN(97, "GPIO_97"), + PINCTRL_PIN(98, "GPIO_98"), + PINCTRL_PIN(99, "GPIO_99"), + PINCTRL_PIN(100, "GPIO_100"), + PINCTRL_PIN(101, "GPIO_101"), + PINCTRL_PIN(102, "GPIO_102"), + PINCTRL_PIN(103, "GPIO_103"), + PINCTRL_PIN(104, "GPIO_104"), + PINCTRL_PIN(105, "GPIO_105"), + PINCTRL_PIN(106, "GPIO_106"), + PINCTRL_PIN(107, "GPIO_107"), + PINCTRL_PIN(108, "GPIO_108"), + PINCTRL_PIN(109, "GPIO_109"), + PINCTRL_PIN(110, "GPIO_110"), + PINCTRL_PIN(111, "GPIO_111"), + PINCTRL_PIN(112, "GPIO_112"), + PINCTRL_PIN(113, "GPIO_113"), + PINCTRL_PIN(114, "GPIO_114"), + PINCTRL_PIN(115, "GPIO_115"), + PINCTRL_PIN(116, "GPIO_116"), + PINCTRL_PIN(117, "GPIO_117"), + PINCTRL_PIN(118, "GPIO_118"), + PINCTRL_PIN(119, "UFS_RESET"), + PINCTRL_PIN(120, "SDC1_RCLK"), + PINCTRL_PIN(121, "SDC1_CLK"), + PINCTRL_PIN(122, "SDC1_CMD"), + PINCTRL_PIN(123, "SDC1_DATA"), + PINCTRL_PIN(124, "SDC2_CLK"), + PINCTRL_PIN(125, "SDC2_CMD"), + PINCTRL_PIN(126, "SDC2_DATA"), + +}; + +#define DECLARE_MSM_GPIO_PINS(pin) \ + static const unsigned int gpio##pin##_pins[] = { pin } +DECLARE_MSM_GPIO_PINS(0); +DECLARE_MSM_GPIO_PINS(1); +DECLARE_MSM_GPIO_PINS(2); +DECLARE_MSM_GPIO_PINS(3); +DECLARE_MSM_GPIO_PINS(4); +DECLARE_MSM_GPIO_PINS(5); +DECLARE_MSM_GPIO_PINS(6); +DECLARE_MSM_GPIO_PINS(7); +DECLARE_MSM_GPIO_PINS(8); +DECLARE_MSM_GPIO_PINS(9); +DECLARE_MSM_GPIO_PINS(10); +DECLARE_MSM_GPIO_PINS(11); +DECLARE_MSM_GPIO_PINS(12); +DECLARE_MSM_GPIO_PINS(13); +DECLARE_MSM_GPIO_PINS(14); +DECLARE_MSM_GPIO_PINS(15); +DECLARE_MSM_GPIO_PINS(16); +DECLARE_MSM_GPIO_PINS(17); +DECLARE_MSM_GPIO_PINS(18); +DECLARE_MSM_GPIO_PINS(19); +DECLARE_MSM_GPIO_PINS(20); +DECLARE_MSM_GPIO_PINS(21); +DECLARE_MSM_GPIO_PINS(22); +DECLARE_MSM_GPIO_PINS(23); +DECLARE_MSM_GPIO_PINS(24); +DECLARE_MSM_GPIO_PINS(25); +DECLARE_MSM_GPIO_PINS(26); +DECLARE_MSM_GPIO_PINS(27); +DECLARE_MSM_GPIO_PINS(28); +DECLARE_MSM_GPIO_PINS(29); +DECLARE_MSM_GPIO_PINS(30); +DECLARE_MSM_GPIO_PINS(31); +DECLARE_MSM_GPIO_PINS(32); +DECLARE_MSM_GPIO_PINS(33); +DECLARE_MSM_GPIO_PINS(34); +DECLARE_MSM_GPIO_PINS(35); +DECLARE_MSM_GPIO_PINS(36); +DECLARE_MSM_GPIO_PINS(37); +DECLARE_MSM_GPIO_PINS(38); +DECLARE_MSM_GPIO_PINS(39); +DECLARE_MSM_GPIO_PINS(40); +DECLARE_MSM_GPIO_PINS(41); +DECLARE_MSM_GPIO_PINS(42); +DECLARE_MSM_GPIO_PINS(43); +DECLARE_MSM_GPIO_PINS(44); +DECLARE_MSM_GPIO_PINS(45); +DECLARE_MSM_GPIO_PINS(46); +DECLARE_MSM_GPIO_PINS(47); +DECLARE_MSM_GPIO_PINS(48); +DECLARE_MSM_GPIO_PINS(49); +DECLARE_MSM_GPIO_PINS(50); +DECLARE_MSM_GPIO_PINS(51); +DECLARE_MSM_GPIO_PINS(52); +DECLARE_MSM_GPIO_PINS(53); +DECLARE_MSM_GPIO_PINS(54); +DECLARE_MSM_GPIO_PINS(55); +DECLARE_MSM_GPIO_PINS(56); +DECLARE_MSM_GPIO_PINS(57); +DECLARE_MSM_GPIO_PINS(58); +DECLARE_MSM_GPIO_PINS(59); +DECLARE_MSM_GPIO_PINS(60); +DECLARE_MSM_GPIO_PINS(61); +DECLARE_MSM_GPIO_PINS(62); +DECLARE_MSM_GPIO_PINS(63); +DECLARE_MSM_GPIO_PINS(64); +DECLARE_MSM_GPIO_PINS(65); +DECLARE_MSM_GPIO_PINS(66); +DECLARE_MSM_GPIO_PINS(67); +DECLARE_MSM_GPIO_PINS(68); +DECLARE_MSM_GPIO_PINS(69); +DECLARE_MSM_GPIO_PINS(70); +DECLARE_MSM_GPIO_PINS(71); +DECLARE_MSM_GPIO_PINS(72); +DECLARE_MSM_GPIO_PINS(73); +DECLARE_MSM_GPIO_PINS(74); +DECLARE_MSM_GPIO_PINS(75); +DECLARE_MSM_GPIO_PINS(76); +DECLARE_MSM_GPIO_PINS(77); +DECLARE_MSM_GPIO_PINS(78); +DECLARE_MSM_GPIO_PINS(79); +DECLARE_MSM_GPIO_PINS(80); +DECLARE_MSM_GPIO_PINS(81); +DECLARE_MSM_GPIO_PINS(82); +DECLARE_MSM_GPIO_PINS(83); +DECLARE_MSM_GPIO_PINS(84); +DECLARE_MSM_GPIO_PINS(85); +DECLARE_MSM_GPIO_PINS(86); +DECLARE_MSM_GPIO_PINS(87); +DECLARE_MSM_GPIO_PINS(88); +DECLARE_MSM_GPIO_PINS(89); +DECLARE_MSM_GPIO_PINS(90); +DECLARE_MSM_GPIO_PINS(91); +DECLARE_MSM_GPIO_PINS(92); +DECLARE_MSM_GPIO_PINS(93); +DECLARE_MSM_GPIO_PINS(94); +DECLARE_MSM_GPIO_PINS(95); +DECLARE_MSM_GPIO_PINS(96); +DECLARE_MSM_GPIO_PINS(97); +DECLARE_MSM_GPIO_PINS(98); +DECLARE_MSM_GPIO_PINS(99); +DECLARE_MSM_GPIO_PINS(100); +DECLARE_MSM_GPIO_PINS(101); +DECLARE_MSM_GPIO_PINS(102); +DECLARE_MSM_GPIO_PINS(103); +DECLARE_MSM_GPIO_PINS(104); +DECLARE_MSM_GPIO_PINS(105); +DECLARE_MSM_GPIO_PINS(106); +DECLARE_MSM_GPIO_PINS(107); +DECLARE_MSM_GPIO_PINS(108); +DECLARE_MSM_GPIO_PINS(109); +DECLARE_MSM_GPIO_PINS(110); +DECLARE_MSM_GPIO_PINS(111); +DECLARE_MSM_GPIO_PINS(112); +DECLARE_MSM_GPIO_PINS(113); +DECLARE_MSM_GPIO_PINS(114); +DECLARE_MSM_GPIO_PINS(115); +DECLARE_MSM_GPIO_PINS(116); +DECLARE_MSM_GPIO_PINS(117); +DECLARE_MSM_GPIO_PINS(118); + +static const unsigned int ufs_reset_pins[] = { 119 }; +static const unsigned int sdc1_rclk_pins[] = { 120 }; +static const unsigned int sdc1_clk_pins[] = { 121 }; +static const unsigned int sdc1_cmd_pins[] = { 122 }; +static const unsigned int sdc1_data_pins[] = { 123 }; +static const unsigned int sdc2_clk_pins[] = { 124 }; +static const unsigned int sdc2_cmd_pins[] = { 125 }; +static const unsigned int sdc2_data_pins[] = { 126 }; + +enum sm7150_functions { + msm_mux_gpio, + msm_mux_adsp_ext, + msm_mux_agera_pll, + msm_mux_aoss_cti, + msm_mux_atest_char, + msm_mux_atest_tsens, + msm_mux_atest_tsens2, + msm_mux_atest_usb1, + msm_mux_atest_usb2, + msm_mux_cam_mclk, + msm_mux_cci_async, + msm_mux_cci_i2c, + msm_mux_cci_timer0, + msm_mux_cci_timer1, + msm_mux_cci_timer2, + msm_mux_cci_timer3, + msm_mux_cci_timer4, + msm_mux_dbg_out, + msm_mux_ddr_bist, + msm_mux_ddr_pxi0, + msm_mux_ddr_pxi1, + msm_mux_ddr_pxi2, + msm_mux_ddr_pxi3, + msm_mux_edp_hot, + msm_mux_edp_lcd, + msm_mux_gcc_gp1, + msm_mux_gcc_gp2, + msm_mux_gcc_gp3, + msm_mux_gp_pdm0, + msm_mux_gp_pdm1, + msm_mux_gp_pdm2, + msm_mux_gps_tx, + msm_mux_jitter_bist, + msm_mux_ldo_en, + msm_mux_ldo_update, + msm_mux_m_voc, + msm_mux_mdp_vsync, + msm_mux_mdp_vsync0, + msm_mux_mdp_vsync1, + msm_mux_mdp_vsync2, + msm_mux_mdp_vsync3, + msm_mux_mss_lte, + msm_mux_nav_pps_in, + msm_mux_nav_pps_out, + msm_mux_pa_indicator, + msm_mux_pci_e, + msm_mux_phase_flag, + msm_mux_pll_bist, + msm_mux_pll_bypassnl, + msm_mux_pll_reset, + msm_mux_pri_mi2s, + msm_mux_pri_mi2s_ws, + msm_mux_prng_rosc, + msm_mux_qdss, + msm_mux_qdss_cti, + msm_mux_qlink_enable, + msm_mux_qlink_request, + msm_mux_qua_mi2s, + msm_mux_qup00, + msm_mux_qup01, + msm_mux_qup02, + msm_mux_qup03, + msm_mux_qup04, + msm_mux_qup10, + msm_mux_qup11, + msm_mux_qup12, + msm_mux_qup13, + msm_mux_qup14, + msm_mux_qup15, + msm_mux_sd_write, + msm_mux_sdc40, + msm_mux_sdc41, + msm_mux_sdc42, + msm_mux_sdc43, + msm_mux_sdc4_clk, + msm_mux_sdc4_cmd, + msm_mux_sec_mi2s, + msm_mux_ter_mi2s, + msm_mux_tgu_ch0, + msm_mux_tgu_ch1, + msm_mux_tgu_ch2, + msm_mux_tgu_ch3, + msm_mux_tsif1_clk, + msm_mux_tsif1_data, + msm_mux_tsif1_en, + msm_mux_tsif1_error, + msm_mux_tsif1_sync, + msm_mux_tsif2_clk, + msm_mux_tsif2_data, + msm_mux_tsif2_en, + msm_mux_tsif2_error, + msm_mux_tsif2_sync, + msm_mux_uim1_clk, + msm_mux_uim1_data, + msm_mux_uim1_present, + msm_mux_uim1_reset, + msm_mux_uim2_clk, + msm_mux_uim2_data, + msm_mux_uim2_present, + msm_mux_uim2_reset, + msm_mux_uim_batt, + msm_mux_usb_phy, + msm_mux_vfr_1, + msm_mux_vsense_trigger, + msm_mux_wlan1_adc0, + msm_mux_wlan1_adc1, + msm_mux_wlan2_adc0, + msm_mux_wlan2_adc1, + msm_mux_wsa_clk, + msm_mux_wsa_data, + msm_mux__, +}; + +static const char * const gpio_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", + "gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", + "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", + "gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28", + "gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35", + "gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42", + "gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49", + "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56", + "gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63", + "gpio64", "gpio65", "gpio66", "gpio67", "gpio68", "gpio69", "gpio70", + "gpio71", "gpio72", "gpio73", "gpio74", "gpio75", "gpio76", "gpio77", + "gpio78", "gpio79", "gpio80", "gpio81", "gpio82", "gpio83", "gpio84", + "gpio85", "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", "gpio91", + "gpio92", "gpio93", "gpio94", "gpio95", "gpio96", "gpio97", "gpio98", + "gpio99", "gpio100", "gpio101", "gpio102", "gpio103", "gpio104", + "gpio105", "gpio106", "gpio107", "gpio108", "gpio109", "gpio110", + "gpio111", "gpio112", "gpio113", "gpio114", "gpio115", "gpio116", + "gpio117", "gpio118", +}; + +static const char * const adsp_ext_groups[] = { + "gpio87", +}; + +static const char * const agera_pll_groups[] = { + "gpio28", +}; + +static const char * const aoss_cti_groups[] = { + "gpio85", +}; + +static const char * const atest_char_groups[] = { + "gpio86", "gpio87", "gpio88", "gpio89", "gpio90", +}; + +static const char * const atest_tsens_groups[] = { + "gpio29", +}; + +static const char * const atest_tsens2_groups[] = { + "gpio7", +}; + +static const char * const atest_usb1_groups[] = { + "gpio7", "gpio10", "gpio11", "gpio39", "gpio44", +}; + +static const char * const atest_usb2_groups[] = { + "gpio51", "gpio52", "gpio53", "gpio54", "gpio55" +}; + +static const char * const cam_mclk_groups[] = { + "gpio13", "gpio14", "gpio15", "gpio16", +}; + +static const char * const cci_async_groups[] = { + "gpio24", "gpio25", "gpio26", +}; + +static const char * const cci_i2c_groups[] = { + "gpio17", "gpio18", "gpio19", "gpio20", "gpio27", "gpio28", +}; + +static const char * const cci_timer0_groups[] = { + "gpio21", +}; + +static const char * const cci_timer1_groups[] = { + "gpio22", +}; + +static const char * const cci_timer2_groups[] = { + "gpio23", +}; + +static const char * const cci_timer3_groups[] = { + "gpio24", +}; + +static const char * const cci_timer4_groups[] = { + "gpio25", +}; + +static const char * const dbg_out_groups[] = { + "gpio3", +}; + +static const char * const ddr_bist_groups[] = { + "gpio7", "gpio8", "gpio9", "gpio10", +}; + +static const char * const ddr_pxi0_groups[] = { + "gpio6", "gpio7", +}; + +static const char * const ddr_pxi1_groups[] = { + "gpio39", "gpio44", +}; + +static const char * const ddr_pxi2_groups[] = { + "gpio10", "gpio11", +}; + +static const char * const ddr_pxi3_groups[] = { + "gpio12", "gpio13", +}; + +static const char * const edp_hot_groups[] = { + "gpio85", +}; + +static const char * const edp_lcd_groups[] = { + "gpio11", +}; + +static const char * const gcc_gp1_groups[] = { + "gpio48", "gpio56", +}; + +static const char * const gcc_gp2_groups[] = { + "gpio21", +}; + +static const char * const gcc_gp3_groups[] = { + "gpio22", +}; + +static const char * const gp_pdm0_groups[] = { + "gpio37", "gpio68", +}; + +static const char * const gp_pdm1_groups[] = { + "gpio8", "gpio50", +}; + +static const char * const gp_pdm2_groups[] = { + "gpio57", +}; + +static const char * const gps_tx_groups[] = { + "gpio83", "gpio84", "gpio107", "gpio109", +}; + +static const char * const jitter_bist_groups[] = { + "gpio26", +}; + +static const char * const ldo_en_groups[] = { + "gpio70", +}; + +static const char * const ldo_update_groups[] = { + "gpio71", +}; + +static const char * const m_voc_groups[] = { + "gpio12", +}; + +static const char * const mdp_vsync_groups[] = { + "gpio10", "gpio11", "gpio12", "gpio70", "gpio71", +}; + +static const char * const mdp_vsync0_groups[] = { + "gpio63", +}; + +static const char * const mdp_vsync1_groups[] = { + "gpio63", +}; + +static const char * const mdp_vsync2_groups[] = { + "gpio63", +}; + +static const char * const mdp_vsync3_groups[] = { + "gpio63", +}; + +static const char * const mss_lte_groups[] = { + "gpio108", "gpio109", +}; + +static const char * const nav_pps_in_groups[] = { + "gpio83", "gpio84", "gpio107", +}; + +static const char * const nav_pps_out_groups[] = { + "gpio83", "gpio84", "gpio107", +}; + +static const char * const pa_indicator_groups[] = { + "gpio99", +}; + +static const char * const pci_e_groups[] = { + "gpio66", "gpio67", "gpio68", +}; + +static const char * const phase_flag_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio6", "gpio7", "gpio10", "gpio11", + "gpio12", "gpio13", "gpio14", "gpio15", "gpio16", "gpio17", "gpio24", + "gpio25", "gpio26", "gpio27", "gpio28", "gpio29", "gpio30", "gpio35", + "gpio36", "gpio37", "gpio38", "gpio39", "gpio43", "gpio44", "gpio56", + "gpio57", "gpio60", "gpio61", "gpio62", +}; + +static const char * const pll_bist_groups[] = { + "gpio27", +}; + +static const char * const pll_bypassnl_groups[] = { + "gpio13", +}; + +static const char * const pll_reset_groups[] = { + "gpio14", +}; + +static const char * const pri_mi2s_groups[] = { + "gpio49", "gpio51", "gpio52", +}; + +static const char * const pri_mi2s_ws_groups[] = { + "gpio50", +}; + +static const char * const prng_rosc_groups[] = { + "gpio72", +}; + +static const char * const qdss_groups[] = { + "gpio13", "gpio86", "gpio14", "gpio87", "gpio15", "gpio88", "gpio16", + "gpio89", "gpio17", "gpio90", "gpio18", "gpio91", "gpio19", "gpio34", + "gpio20", "gpio35", "gpio21", "gpio53", "gpio22", "gpio30", "gpio23", + "gpio54", "gpio24", "gpio55", "gpio25", "gpio57", "gpio26", "gpio31", + "gpio27", "gpio56", "gpio28", "gpio36", "gpio29", "gpio37", "gpio93", + "gpio104", +}; + +static const char * const qdss_cti_groups[] = { + "gpio4", "gpio5", "gpio32", "gpio44", "gpio45", "gpio63", +}; + +static const char * const qlink_enable_groups[] = { + "gpio97", +}; + +static const char * const qlink_request_groups[] = { + "gpio96", +}; + +static const char * const qua_mi2s_groups[] = { + "gpio58", +}; + +static const char * const qup00_groups[] = { + "gpio49", "gpio50", "gpio51", "gpio52", "gpio57", "gpio58", +}; + +static const char * const qup01_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio12", "gpio37", +}; + +static const char * const qup02_groups[] = { + "gpio34", "gpio35", +}; + +static const char * const qup03_groups[] = { + "gpio38", "gpio39", "gpio40", "gpio41", +}; + +static const char * const qup04_groups[] = { + "gpio53", "gpio54", "gpio55", "gpio56", +}; + +static const char * const qup10_groups[] = { + "gpio59", "gpio60", "gpio61", "gpio62", "gpio63", "gpio64", "gpio65", +}; + +static const char * const qup11_groups[] = { + "gpio6", "gpio7", "gpio8", "gpio9", +}; + +static const char * const qup12_groups[] = { + "gpio42", "gpio43", "gpio44", "gpio45", +}; + +static const char * const qup13_groups[] = { + "gpio46", "gpio47", +}; + +static const char * const qup14_groups[] = { + "gpio110", "gpio111", "gpio112", "gpio113", +}; + +static const char * const qup15_groups[] = { + "gpio92", "gpio101", "gpio102", "gpio103", +}; + +static const char * const sd_write_groups[] = { + "gpio33", +}; + +static const char * const sdc40_groups[] = { + "gpio69", +}; + +static const char * const sdc41_groups[] = { + "gpio68", +}; + +static const char * const sdc42_groups[] = { + "gpio67", +}; + +static const char * const sdc43_groups[] = { + "gpio65", +}; + +static const char * const sdc4_clk_groups[] = { + "gpio66", +}; + +static const char * const sdc4_cmd_groups[] = { + "gpio64", +}; + +static const char * const sec_mi2s_groups[] = { + "gpio57", +}; + +static const char * const ter_mi2s_groups[] = { + "gpio53", "gpio54", "gpio55", "gpio56", +}; + +static const char * const tgu_ch0_groups[] = { + "gpio63", +}; + +static const char * const tgu_ch1_groups[] = { + "gpio64", +}; + +static const char * const tgu_ch2_groups[] = { + "gpio65", +}; + +static const char * const tgu_ch3_groups[] = { + "gpio62", +}; + +static const char * const tsif1_clk_groups[] = { + "gpio62", +}; + +static const char * const tsif1_data_groups[] = { + "gpio64", +}; + +static const char * const tsif1_en_groups[] = { + "gpio63", +}; + +static const char * const tsif1_error_groups[] = { + "gpio60", +}; + +static const char * const tsif1_sync_groups[] = { + "gpio61", +}; + +static const char * const tsif2_clk_groups[] = { + "gpio66", +}; + +static const char * const tsif2_data_groups[] = { + "gpio68", +}; + +static const char * const tsif2_en_groups[] = { + "gpio67", +}; + +static const char * const tsif2_error_groups[] = { + "gpio65", +}; + +static const char * const tsif2_sync_groups[] = { + "gpio69", +}; + +static const char * const uim1_clk_groups[] = { + "gpio80", +}; + +static const char * const uim1_data_groups[] = { + "gpio79", +}; + +static const char * const uim1_present_groups[] = { + "gpio82", +}; + +static const char * const uim1_reset_groups[] = { + "gpio81", +}; + +static const char * const uim2_clk_groups[] = { + "gpio76", +}; + +static const char * const uim2_data_groups[] = { + "gpio75", +}; + +static const char * const uim2_present_groups[] = { + "gpio78", +}; + +static const char * const uim2_reset_groups[] = { + "gpio77", +}; + +static const char * const uim_batt_groups[] = { + "gpio85", +}; + +static const char * const usb_phy_groups[] = { + "gpio104", +}; + +static const char * const vfr_1_groups[] = { + "gpio65", +}; + +static const char * const vsense_trigger_groups[] = { + "gpio7", +}; + +static const char * const wlan1_adc0_groups[] = { + "gpio39", +}; + +static const char * const wlan1_adc1_groups[] = { + "gpio44", +}; + +static const char * const wlan2_adc0_groups[] = { + "gpio11", +}; + +static const char * const wlan2_adc1_groups[] = { + "gpio10", +}; + +static const char * const wsa_clk_groups[] = { + "gpio49", +}; + +static const char * const wsa_data_groups[] = { + "gpio50", +}; + +static const struct msm_function sm7150_functions[] = { + FUNCTION(gpio), + FUNCTION(adsp_ext), + FUNCTION(agera_pll), + FUNCTION(aoss_cti), + FUNCTION(atest_char), + FUNCTION(atest_tsens), + FUNCTION(atest_tsens2), + FUNCTION(atest_usb1), + FUNCTION(atest_usb2), + FUNCTION(cam_mclk), + FUNCTION(cci_async), + FUNCTION(cci_i2c), + FUNCTION(cci_timer0), + FUNCTION(cci_timer1), + FUNCTION(cci_timer2), + FUNCTION(cci_timer3), + FUNCTION(cci_timer4), + FUNCTION(dbg_out), + FUNCTION(ddr_bist), + FUNCTION(ddr_pxi0), + FUNCTION(ddr_pxi1), + FUNCTION(ddr_pxi2), + FUNCTION(ddr_pxi3), + FUNCTION(edp_hot), + FUNCTION(edp_lcd), + FUNCTION(gcc_gp1), + FUNCTION(gcc_gp2), + FUNCTION(gcc_gp3), + FUNCTION(gp_pdm0), + FUNCTION(gp_pdm1), + FUNCTION(gp_pdm2), + FUNCTION(gps_tx), + FUNCTION(jitter_bist), + FUNCTION(ldo_en), + FUNCTION(ldo_update), + FUNCTION(m_voc), + FUNCTION(mdp_vsync), + FUNCTION(mdp_vsync0), + FUNCTION(mdp_vsync1), + FUNCTION(mdp_vsync2), + FUNCTION(mdp_vsync3), + FUNCTION(mss_lte), + FUNCTION(nav_pps_in), + FUNCTION(nav_pps_out), + FUNCTION(pa_indicator), + FUNCTION(pci_e), + FUNCTION(phase_flag), + FUNCTION(pll_bist), + FUNCTION(pll_bypassnl), + FUNCTION(pll_reset), + FUNCTION(pri_mi2s), + FUNCTION(pri_mi2s_ws), + FUNCTION(prng_rosc), + FUNCTION(qdss_cti), + FUNCTION(qdss), + FUNCTION(qlink_enable), + FUNCTION(qlink_request), + FUNCTION(qua_mi2s), + FUNCTION(qup00), + FUNCTION(qup01), + FUNCTION(qup02), + FUNCTION(qup03), + FUNCTION(qup04), + FUNCTION(qup10), + FUNCTION(qup11), + FUNCTION(qup12), + FUNCTION(qup13), + FUNCTION(qup14), + FUNCTION(qup15), + FUNCTION(sd_write), + FUNCTION(sdc40), + FUNCTION(sdc41), + FUNCTION(sdc42), + FUNCTION(sdc43), + FUNCTION(sdc4_clk), + FUNCTION(sdc4_cmd), + FUNCTION(sec_mi2s), + FUNCTION(ter_mi2s), + FUNCTION(tgu_ch0), + FUNCTION(tgu_ch1), + FUNCTION(tgu_ch2), + FUNCTION(tgu_ch3), + FUNCTION(tsif1_clk), + FUNCTION(tsif1_data), + FUNCTION(tsif1_en), + FUNCTION(tsif1_error), + FUNCTION(tsif1_sync), + FUNCTION(tsif2_clk), + FUNCTION(tsif2_data), + FUNCTION(tsif2_en), + FUNCTION(tsif2_error), + FUNCTION(tsif2_sync), + FUNCTION(uim1_clk), + FUNCTION(uim1_data), + FUNCTION(uim1_present), + FUNCTION(uim1_reset), + FUNCTION(uim2_clk), + FUNCTION(uim2_data), + FUNCTION(uim2_present), + FUNCTION(uim2_reset), + FUNCTION(uim_batt), + FUNCTION(usb_phy), + FUNCTION(vfr_1), + FUNCTION(vsense_trigger), + FUNCTION(wlan1_adc0), + FUNCTION(wlan1_adc1), + FUNCTION(wlan2_adc0), + FUNCTION(wlan2_adc1), + FUNCTION(wsa_clk), + FUNCTION(wsa_data), +}; + +/* + * Every pin is maintained as a single group, and missing or non-existing pin + * would be maintained as dummy group to synchronize pin group index with + * pin descriptor registered with pinctrl core. + * Clients would not be able to request these dummy pin groups. + */ +static const struct msm_pingroup sm7150_groups[] = { + [0] = PINGROUP(0, SOUTH, qup01, _, phase_flag, _, _, _, _, _, _), + [1] = PINGROUP(1, SOUTH, qup01, _, phase_flag, _, _, _, _, _, _), + [2] = PINGROUP(2, SOUTH, qup01, _, phase_flag, _, _, _, _, _, _), + [3] = PINGROUP(3, SOUTH, qup01, dbg_out, _, _, _, _, _, _, _), + [4] = PINGROUP(4, NORTH, _, qdss_cti, _, _, _, _, _, _, _), + [5] = PINGROUP(5, NORTH, _, qdss_cti, _, _, _, _, _, _, _), + [6] = PINGROUP(6, NORTH, qup11, _, phase_flag, ddr_pxi0, _, _, _, _, _), + [7] = PINGROUP(7, NORTH, qup11, ddr_bist, _, phase_flag, atest_tsens2, vsense_trigger, atest_usb1, ddr_pxi0, _), + [8] = PINGROUP(8, NORTH, qup11, gp_pdm1, ddr_bist, _, _, _, _, _, _), + [9] = PINGROUP(9, NORTH, qup11, ddr_bist, _, _, _, _, _, _, _), + [10] = PINGROUP(10, NORTH, mdp_vsync, ddr_bist, _, phase_flag, wlan2_adc1, atest_usb1, ddr_pxi2, _, _), + [11] = PINGROUP(11, NORTH, mdp_vsync, edp_lcd, _, phase_flag, wlan2_adc0, atest_usb1, ddr_pxi2, _, _), + [12] = PINGROUP(12, SOUTH, mdp_vsync, m_voc, qup01, _, phase_flag, ddr_pxi3, _, _, _), + [13] = PINGROUP(13, SOUTH, cam_mclk, pll_bypassnl, _, phase_flag, qdss, ddr_pxi3, _, _, _), + [14] = PINGROUP(14, SOUTH, cam_mclk, pll_reset, _, phase_flag, qdss, _, _, _, _), + [15] = PINGROUP(15, SOUTH, cam_mclk, _, phase_flag, qdss, _, _, _, _, _), + [16] = PINGROUP(16, SOUTH, cam_mclk, _, phase_flag, qdss, _, _, _, _, _), + [17] = PINGROUP(17, SOUTH, cci_i2c, _, phase_flag, qdss, _, _, _, _, _), + [18] = PINGROUP(18, SOUTH, cci_i2c, qdss, _, _, _, _, _, _, _), + [19] = PINGROUP(19, SOUTH, cci_i2c, qdss, _, _, _, _, _, _, _), + [20] = PINGROUP(20, SOUTH, cci_i2c, qdss, _, _, _, _, _, _, _), + [21] = PINGROUP(21, SOUTH, cci_timer0, gcc_gp2, _, qdss, _, _, _, _, _), + [22] = PINGROUP(22, SOUTH, cci_timer1, gcc_gp3, _, qdss, _, _, _, _, _), + [23] = PINGROUP(23, SOUTH, cci_timer2, qdss, _, _, _, _, _, _, _), + [24] = PINGROUP(24, SOUTH, cci_timer3, cci_async, _, phase_flag, qdss, _, _, _, _), + [25] = PINGROUP(25, SOUTH, cci_timer4, cci_async, _, phase_flag, qdss, _, _, _, _), + [26] = PINGROUP(26, SOUTH, cci_async, jitter_bist, _, phase_flag, qdss, _, _, _, _), + [27] = PINGROUP(27, SOUTH, cci_i2c, pll_bist, _, phase_flag, qdss, _, _, _, _), + [28] = PINGROUP(28, SOUTH, cci_i2c, agera_pll, _, phase_flag, qdss, _, _, _, _), + [29] = PINGROUP(29, NORTH, _, _, phase_flag, qdss, atest_tsens, _, _, _, _), + [30] = PINGROUP(30, SOUTH, _, phase_flag, qdss, _, _, _, _, _, _), + [31] = PINGROUP(31, WEST, _, qdss, _, _, _, _, _, _, _), + [32] = PINGROUP(32, NORTH, qdss_cti, _, _, _, _, _, _, _, _), + [33] = PINGROUP(33, NORTH, sd_write, _, _, _, _, _, _, _, _), + [34] = PINGROUP(34, SOUTH, qup02, qdss, _, _, _, _, _, _, _), + [35] = PINGROUP(35, SOUTH, qup02, _, phase_flag, qdss, _, _, _, _, _), + [36] = PINGROUP(36, SOUTH, _, phase_flag, qdss, _, _, _, _, _, _), + [37] = PINGROUP(37, SOUTH, qup01, gp_pdm0, _, phase_flag, qdss, _, _, _, _), + [38] = PINGROUP(38, SOUTH, qup03, _, phase_flag, _, _, _, _, _, _), + [39] = PINGROUP(39, SOUTH, qup03, _, phase_flag, _, wlan1_adc0, atest_usb1, ddr_pxi1, _, _), + [40] = PINGROUP(40, SOUTH, qup03, _, _, _, _, _, _, _, _), + [41] = PINGROUP(41, SOUTH, qup03, _, _, _, _, _, _, _, _), + [42] = PINGROUP(42, NORTH, qup12, _, _, _, _, _, _, _, _), + [43] = PINGROUP(43, NORTH, qup12, _, phase_flag, _, _, _, _, _, _), + [44] = PINGROUP(44, NORTH, qup12, _, phase_flag, qdss_cti, _, wlan1_adc1, atest_usb1, ddr_pxi1, _), + [45] = PINGROUP(45, NORTH, qup12, qdss_cti, _, _, _, _, _, _, _), + [46] = PINGROUP(46, NORTH, qup13, _, _, _, _, _, _, _, _), + [47] = PINGROUP(47, NORTH, qup13, _, _, _, _, _, _, _, _), + [48] = PINGROUP(48, WEST, gcc_gp1, _, _, _, _, _, _, _, _), + [49] = PINGROUP(49, WEST, pri_mi2s, qup00, wsa_clk, _, _, _, _, _, _), + [50] = PINGROUP(50, WEST, pri_mi2s_ws, qup00, wsa_data, gp_pdm1, _, _, _, _, _), + [51] = PINGROUP(51, WEST, pri_mi2s, qup00, atest_usb2, _, _, _, _, _, _), + [52] = PINGROUP(52, WEST, pri_mi2s, qup00, atest_usb2, _, _, _, _, _, _), + [53] = PINGROUP(53, WEST, ter_mi2s, qup04, qdss, atest_usb2, _, _, _, _, _), + [54] = PINGROUP(54, WEST, ter_mi2s, qup04, qdss, atest_usb2, _, _, _, _, _), + [55] = PINGROUP(55, WEST, ter_mi2s, qup04, qdss, atest_usb2, _, _, _, _, _), + [56] = PINGROUP(56, WEST, ter_mi2s, qup04, gcc_gp1, _, phase_flag, qdss, _, _, _), + [57] = PINGROUP(57, WEST, sec_mi2s, qup00, gp_pdm2, _, phase_flag, qdss, _, _, _), + [58] = PINGROUP(58, WEST, qua_mi2s, qup00, _, _, _, _, _, _, _), + [59] = PINGROUP(59, NORTH, qup10, _, _, _, _, _, _, _, _), + [60] = PINGROUP(60, NORTH, qup10, tsif1_error, _, phase_flag, _, _, _, _, _), + [61] = PINGROUP(61, NORTH, qup10, tsif1_sync, _, phase_flag, _, _, _, _, _), + [62] = PINGROUP(62, NORTH, qup10, tsif1_clk, tgu_ch3, _, phase_flag, _, _, _, _), + [63] = PINGROUP(63, NORTH, tsif1_en, mdp_vsync0, qup10, mdp_vsync1, mdp_vsync2, mdp_vsync3, tgu_ch0, qdss_cti, _), + [64] = PINGROUP(64, NORTH, tsif1_data, sdc4_cmd, qup10, tgu_ch1, _, _, _, _, _), + [65] = PINGROUP(65, NORTH, tsif2_error, sdc43, qup10, vfr_1, tgu_ch2, _, _, _, _), + [66] = PINGROUP(66, NORTH, tsif2_clk, sdc4_clk, pci_e, _, _, _, _, _, _), + [67] = PINGROUP(67, NORTH, tsif2_en, sdc42, pci_e, _, _, _, _, _, _), + [68] = PINGROUP(68, NORTH, tsif2_data, sdc41, pci_e, gp_pdm0, _, _, _, _, _), + [69] = PINGROUP(69, NORTH, tsif2_sync, sdc40, _, _, _, _, _, _, _), + [70] = PINGROUP(70, NORTH, _, _, mdp_vsync, ldo_en, _, _, _, _, _), + [71] = PINGROUP(71, NORTH, _, mdp_vsync, ldo_update, _, _, _, _, _, _), + [72] = PINGROUP(72, NORTH, prng_rosc, _, _, _, _, _, _, _, _), + [73] = PINGROUP(73, NORTH, _, _, _, _, _, _, _, _, _), + [74] = PINGROUP(74, WEST, _, _, _, _, _, _, _, _, _), + [75] = PINGROUP(75, WEST, uim2_data, _, _, _, _, _, _, _, _), + [76] = PINGROUP(76, WEST, uim2_clk, _, _, _, _, _, _, _, _), + [77] = PINGROUP(77, WEST, uim2_reset, _, _, _, _, _, _, _, _), + [78] = PINGROUP(78, WEST, uim2_present, _, _, _, _, _, _, _, _), + [79] = PINGROUP(79, WEST, uim1_data, _, _, _, _, _, _, _, _), + [80] = PINGROUP(80, WEST, uim1_clk, _, _, _, _, _, _, _, _), + [81] = PINGROUP(81, WEST, uim1_reset, _, _, _, _, _, _, _, _), + [82] = PINGROUP(82, WEST, uim1_present, _, _, _, _, _, _, _, _), + [83] = PINGROUP(83, WEST, _, nav_pps_in, nav_pps_out, gps_tx, _, _, _, _, _), + [84] = PINGROUP(84, WEST, _, nav_pps_in, nav_pps_out, gps_tx, _, _, _, _, _), + [85] = PINGROUP(85, WEST, uim_batt, edp_hot, aoss_cti, _, _, _, _, _, _), + [86] = PINGROUP(86, NORTH, qdss, atest_char, _, _, _, _, _, _, _), + [87] = PINGROUP(87, NORTH, adsp_ext, qdss, atest_char, _, _, _, _, _, _), + [88] = PINGROUP(88, NORTH, qdss, atest_char, _, _, _, _, _, _, _), + [89] = PINGROUP(89, NORTH, qdss, atest_char, _, _, _, _, _, _, _), + [90] = PINGROUP(90, NORTH, qdss, atest_char, _, _, _, _, _, _, _), + [91] = PINGROUP(91, NORTH, qdss, _, _, _, _, _, _, _, _), + [92] = PINGROUP(92, NORTH, _, _, qup15, _, _, _, _, _, _), + [93] = PINGROUP(93, NORTH, qdss, _, _, _, _, _, _, _, _), + [94] = PINGROUP(94, SOUTH, _, _, _, _, _, _, _, _, _), + [95] = PINGROUP(95, WEST, _, _, _, _, _, _, _, _, _), + [96] = PINGROUP(96, WEST, qlink_request, _, _, _, _, _, _, _, _), + [97] = PINGROUP(97, WEST, qlink_enable, _, _, _, _, _, _, _, _), + [98] = PINGROUP(98, WEST, _, _, _, _, _, _, _, _, _), + [99] = PINGROUP(99, WEST, _, pa_indicator, _, _, _, _, _, _, _), + [100] = PINGROUP(100, WEST, _, _, _, _, _, _, _, _, _), + [101] = PINGROUP(101, NORTH, _, _, qup15, _, _, _, _, _, _), + [102] = PINGROUP(102, NORTH, _, _, qup15, _, _, _, _, _, _), + [103] = PINGROUP(103, NORTH, _, qup15, _, _, _, _, _, _, _), + [104] = PINGROUP(104, WEST, usb_phy, _, qdss, _, _, _, _, _, _), + [105] = PINGROUP(105, NORTH, _, _, _, _, _, _, _, _, _), + [106] = PINGROUP(106, NORTH, _, _, _, _, _, _, _, _, _), + [107] = PINGROUP(107, WEST, _, nav_pps_in, nav_pps_out, gps_tx, _, _, _, _, _), + [108] = PINGROUP(108, SOUTH, mss_lte, _, _, _, _, _, _, _, _), + [109] = PINGROUP(109, SOUTH, mss_lte, gps_tx, _, _, _, _, _, _, _), + [110] = PINGROUP(110, NORTH, _, _, qup14, _, _, _, _, _, _), + [111] = PINGROUP(111, NORTH, _, _, qup14, _, _, _, _, _, _), + [112] = PINGROUP(112, NORTH, _, qup14, _, _, _, _, _, _, _), + [113] = PINGROUP(113, NORTH, _, qup14, _, _, _, _, _, _, _), + [114] = PINGROUP(114, NORTH, _, _, _, _, _, _, _, _, _), + [115] = PINGROUP(115, NORTH, _, _, _, _, _, _, _, _, _), + [116] = PINGROUP(116, NORTH, _, _, _, _, _, _, _, _, _), + [117] = PINGROUP(117, NORTH, _, _, _, _, _, _, _, _, _), + [118] = PINGROUP(118, NORTH, _, _, _, _, _, _, _, _, _), + [119] = UFS_RESET(ufs_reset, 0x9f000), + [120] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x9a000, 15, 0), + [121] = SDC_QDSD_PINGROUP(sdc1_clk, 0x9a000, 13, 6), + [122] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x9a000, 11, 3), + [123] = SDC_QDSD_PINGROUP(sdc1_data, 0x9a000, 9, 0), + [124] = SDC_QDSD_PINGROUP(sdc2_clk, 0x98000, 14, 6), + [125] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x98000, 11, 3), + [126] = SDC_QDSD_PINGROUP(sdc2_data, 0x98000, 9, 0), +}; + +static const struct msm_gpio_wakeirq_map sm7150_pdc_map[] = { + {0, 40}, {3, 50}, {4, 42}, {5, 70}, {6, 41}, {9, 57}, + {10, 80}, {11, 51}, {22, 90}, {24, 61}, {26, 52}, {30, 56}, + {31, 33}, {32, 81}, {33, 62}, {34, 43}, {36, 91}, {37, 53}, + {38, 63}, {39, 72}, {41, 101}, {42, 35}, {43, 34}, {45, 73}, + {47, 82}, {48, 36}, {49, 37}, {50, 38}, {52, 39}, {53, 102}, + {55, 92}, {56, 45}, {57, 46}, {58, 83}, {59, 47}, {62, 48}, + {64, 74}, {65, 44}, {66, 93}, {67, 49}, {68, 55}, {69, 32}, + {70, 54}, {73, 64}, {74, 71}, {78, 31}, {82, 30}, {84, 58}, + {85, 103}, {86, 59}, {87, 60}, {88, 65}, {89, 66}, {90, 67}, + {91, 68}, {92, 69}, {93, 75}, {94, 84}, {95, 94}, {96, 76}, + {98, 77}, {101, 78}, {104, 99}, {109, 104}, {110, 79}, {113, 85}, +}; + +static const struct msm_pinctrl_soc_data sm7150_tlmm = { + .pins = sm7150_pins, + .npins = ARRAY_SIZE(sm7150_pins), + .functions = sm7150_functions, + .nfunctions = ARRAY_SIZE(sm7150_functions), + .groups = sm7150_groups, + .ngroups = ARRAY_SIZE(sm7150_groups), + .ngpios = 120, + .tiles = sm7150_tiles, + .ntiles = ARRAY_SIZE(sm7150_tiles), + .wakeirq_map = sm7150_pdc_map, + .nwakeirq_map = ARRAY_SIZE(sm7150_pdc_map), + .wakeirq_dual_edge_errata = true, +}; + +static int sm7150_tlmm_probe(struct platform_device *pdev) +{ + return msm_pinctrl_probe(pdev, &sm7150_tlmm); +} + +static const struct of_device_id sm7150_tlmm_of_match[] = { + { .compatible = "qcom,sm7150-tlmm", }, + { }, +}; + +static struct platform_driver sm7150_tlmm_driver = { + .driver = { + .name = "sm7150-tlmm", + .pm = &msm_pinctrl_dev_pm_ops, + .of_match_table = sm7150_tlmm_of_match, + }, + .probe = sm7150_tlmm_probe, + .remove = msm_pinctrl_remove, +}; + +static int __init sm7150_tlmm_init(void) +{ + return platform_driver_register(&sm7150_tlmm_driver); +} +arch_initcall(sm7150_tlmm_init); + +static void __exit sm7150_tlmm_exit(void) +{ + platform_driver_unregister(&sm7150_tlmm_driver); +} +module_exit(sm7150_tlmm_exit); + +MODULE_DESCRIPTION("Qualcomm SM7150 TLMM driver"); +MODULE_LICENSE("GPL"); -- GitLab From 5b63ccb69ee8ee5ddb58d8ce105b880905678bd5 Mon Sep 17 00:00:00 2001 From: Devi Priya Date: Thu, 16 Mar 2023 12:59:37 +0530 Subject: [PATCH 0899/5631] dt-bindings: pinctrl: qcom: Add support for IPQ9574 Add new binding document for pinctrl on IPQ9574 Reviewed-by: Krzysztof Kozlowski Co-developed-by: Anusha Rao Signed-off-by: Anusha Rao Signed-off-by: Devi Priya Link: https://lore.kernel.org/r/20230316072940.29137-4-quic_devipriy@quicinc.com Signed-off-by: Linus Walleij --- .../bindings/pinctrl/qcom,ipq9574-tlmm.yaml | 130 ++++++++++++++++++ 1 file changed, 130 insertions(+) create mode 100644 Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml new file mode 100644 index 000000000000..f32239d08c32 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml @@ -0,0 +1,130 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/qcom,ipq9574-tlmm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Technologies, Inc. IPQ9574 TLMM block + +maintainers: + - Bjorn Andersson + - Krzysztof Kozlowski + +description: + Top Level Mode Multiplexer pin controller in Qualcomm IPQ9574 SoC. + +properties: + compatible: + const: qcom,ipq9574-tlmm + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + interrupt-controller: true + "#interrupt-cells": true + gpio-controller: true + "#gpio-cells": true + gpio-ranges: true + wakeup-parent: true + + gpio-reserved-ranges: + minItems: 1 + maxItems: 33 + + gpio-line-names: + maxItems: 65 + +patternProperties: + "-state$": + oneOf: + - $ref: "#/$defs/qcom-ipq9574-tlmm-state" + - patternProperties: + "-pins$": + $ref: "#/$defs/qcom-ipq9574-tlmm-state" + additionalProperties: false + +$defs: + qcom-ipq9574-tlmm-state: + type: object + description: + Pinctrl node's client devices use subnodes for desired pin configuration. + Client device subnodes use below standard properties. + $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + + properties: + pins: + description: + List of gpio pins affected by the properties specified in this + subnode. + items: + pattern: "^gpio([0-9]|[1-5][0-9]|6[0-4])$" + minItems: 1 + maxItems: 8 + + function: + description: + Specify the alternative function to be configured for the specified + pins. + + enum: [ atest_char, atest_char0, atest_char1, atest_char2, atest_char3, + audio_pdm0, audio_pdm1, audio_pri, audio_sec, blsp0_spi, blsp0_uart, + blsp1_i2c, blsp1_spi, blsp1_uart, blsp2_i2c, blsp2_spi, + blsp2_uart, blsp3_i2c, blsp3_spi, blsp3_uart, blsp4_i2c, + blsp4_spi, blsp4_uart, blsp5_i2c, blsp5_uart, cri_trng0, + cri_trng1, cri_trng3, cxc0, cxc1, dbg_out, dwc_ddrphy, + gcc_plltest, gcc_tlmm, mac, mdc, mdio, pcie0_clk, pcie0_wake, + pcie1_clk, pcie1_wake, pcie2_clk, pcie2_wake, pcie3_clk, pcie3_wake, + prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, pta, pwm, + qdss_cti_trig_in_a0, qdss_cti_trig_in_a1, qdss_cti_trig_in_b0, + qdss_cti_trig_in_b1, qdss_cti_trig_out_a0, qdss_cti_trig_out_a1, + qdss_cti_trig_out_b0, qdss_cti_trig_out_b1, qdss_traceclk_a, + qdss_traceclk_b, qdss_tracectl_a, qdss_tracectl_b, qdss_tracedata_a, + qdss_tracedata_b, qdss_tracedata_b, qspi_clk, qspi_cs, qspi_data, + rx0, rx1, sdc_clk, sdc_cmd, sdc_data, sdc_rclk, tsens_max, + wci20, wci21, wsa_swrm ] + + bias-pull-down: true + bias-pull-up: true + bias-disable: true + drive-strength: true + input-enable: true + output-high: true + output-low: true + + required: + - pins + + additionalProperties: false + +allOf: + - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include + tlmm: pinctrl@1000000 { + compatible = "qcom,ipq9574-tlmm"; + reg = <0x01000000 0x300000>; + interrupts = ; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + gpio-ranges = <&tlmm 0 0 65>; + + uart2-state { + pins = "gpio34", "gpio35"; + function = "blsp2_uart"; + drive-strength = <8>; + bias-pull-down; + }; + }; -- GitLab From c74eef68fd2d3a7821ecb57a607d597775df53ac Mon Sep 17 00:00:00 2001 From: Devi Priya Date: Thu, 16 Mar 2023 12:59:38 +0530 Subject: [PATCH 0900/5631] pinctrl: qcom: Add IPQ9574 pinctrl driver Add pinctrl definitions for the TLMM of IPQ9574 Reviewed-by: Krzysztof Kozlowski Co-developed-by: Anusha Rao Signed-off-by: Anusha Rao Signed-off-by: Devi Priya Link: https://lore.kernel.org/r/20230316072940.29137-5-quic_devipriy@quicinc.com Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/Kconfig | 11 + drivers/pinctrl/qcom/Makefile | 1 + drivers/pinctrl/qcom/pinctrl-ipq9574.c | 826 +++++++++++++++++++++++++ 3 files changed, 838 insertions(+) create mode 100644 drivers/pinctrl/qcom/pinctrl-ipq9574.c diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index be40bcb23caf..e52cfab8d5ae 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -80,6 +80,17 @@ config PINCTRL_IPQ6018 Qualcomm Technologies Inc. IPQ6018 platform. Select this for IPQ6018. +config PINCTRL_IPQ9574 + tristate "Qualcomm Technologies, Inc. IPQ9574 pin controller driver" + depends on OF || COMPILE_TEST + depends on ARM64 || COMPILE_TEST + depends on PINCTRL_MSM + help + This is the pinctrl, pinmux, pinconf and gpiolib driver for + the Qualcomm Technologies Inc. TLMM block found on the + Qualcomm Technologies Inc. IPQ9574 platform. Select this for + IPQ9574. + config PINCTRL_MSM8226 tristate "Qualcomm 8226 pin controller driver" depends on OF diff --git a/drivers/pinctrl/qcom/Makefile b/drivers/pinctrl/qcom/Makefile index 22b1286a8def..521b021b74ba 100644 --- a/drivers/pinctrl/qcom/Makefile +++ b/drivers/pinctrl/qcom/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_PINCTRL_IPQ8064) += pinctrl-ipq8064.o obj-$(CONFIG_PINCTRL_IPQ5332) += pinctrl-ipq5332.o obj-$(CONFIG_PINCTRL_IPQ8074) += pinctrl-ipq8074.o obj-$(CONFIG_PINCTRL_IPQ6018) += pinctrl-ipq6018.o +obj-$(CONFIG_PINCTRL_IPQ9574) += pinctrl-ipq9574.o obj-$(CONFIG_PINCTRL_MSM8226) += pinctrl-msm8226.o obj-$(CONFIG_PINCTRL_MSM8660) += pinctrl-msm8660.o obj-$(CONFIG_PINCTRL_MSM8960) += pinctrl-msm8960.o diff --git a/drivers/pinctrl/qcom/pinctrl-ipq9574.c b/drivers/pinctrl/qcom/pinctrl-ipq9574.c new file mode 100644 index 000000000000..7f057b62475f --- /dev/null +++ b/drivers/pinctrl/qcom/pinctrl-ipq9574.c @@ -0,0 +1,826 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (c) 2023 The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include + +#include "pinctrl-msm.h" + +#define FUNCTION(fname) \ + [msm_mux_##fname] = { \ + .name = #fname, \ + .groups = fname##_groups, \ + .ngroups = ARRAY_SIZE(fname##_groups), \ + } + +#define REG_SIZE 0x1000 +#define PINGROUP(id, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ + { \ + .name = "gpio" #id, \ + .pins = gpio##id##_pins, \ + .npins = (unsigned int)ARRAY_SIZE(gpio##id##_pins), \ + .funcs = (int[]){ \ + msm_mux_gpio, /* gpio mode */ \ + msm_mux_##f1, \ + msm_mux_##f2, \ + msm_mux_##f3, \ + msm_mux_##f4, \ + msm_mux_##f5, \ + msm_mux_##f6, \ + msm_mux_##f7, \ + msm_mux_##f8, \ + msm_mux_##f9 \ + }, \ + .nfuncs = 10, \ + .ctl_reg = REG_SIZE * id, \ + .io_reg = 0x4 + REG_SIZE * id, \ + .intr_cfg_reg = 0x8 + REG_SIZE * id, \ + .intr_status_reg = 0xc + REG_SIZE * id, \ + .intr_target_reg = 0x8 + REG_SIZE * id, \ + .mux_bit = 2, \ + .pull_bit = 0, \ + .drv_bit = 6, \ + .oe_bit = 9, \ + .in_bit = 0, \ + .out_bit = 1, \ + .intr_enable_bit = 0, \ + .intr_status_bit = 0, \ + .intr_target_bit = 5, \ + .intr_target_kpss_val = 3, \ + .intr_raw_status_bit = 4, \ + .intr_polarity_bit = 1, \ + .intr_detection_bit = 2, \ + .intr_detection_width = 2, \ + } + +static const struct pinctrl_pin_desc ipq9574_pins[] = { + PINCTRL_PIN(0, "GPIO_0"), + PINCTRL_PIN(1, "GPIO_1"), + PINCTRL_PIN(2, "GPIO_2"), + PINCTRL_PIN(3, "GPIO_3"), + PINCTRL_PIN(4, "GPIO_4"), + PINCTRL_PIN(5, "GPIO_5"), + PINCTRL_PIN(6, "GPIO_6"), + PINCTRL_PIN(7, "GPIO_7"), + PINCTRL_PIN(8, "GPIO_8"), + PINCTRL_PIN(9, "GPIO_9"), + PINCTRL_PIN(10, "GPIO_10"), + PINCTRL_PIN(11, "GPIO_11"), + PINCTRL_PIN(12, "GPIO_12"), + PINCTRL_PIN(13, "GPIO_13"), + PINCTRL_PIN(14, "GPIO_14"), + PINCTRL_PIN(15, "GPIO_15"), + PINCTRL_PIN(16, "GPIO_16"), + PINCTRL_PIN(17, "GPIO_17"), + PINCTRL_PIN(18, "GPIO_18"), + PINCTRL_PIN(19, "GPIO_19"), + PINCTRL_PIN(20, "GPIO_20"), + PINCTRL_PIN(21, "GPIO_21"), + PINCTRL_PIN(22, "GPIO_22"), + PINCTRL_PIN(23, "GPIO_23"), + PINCTRL_PIN(24, "GPIO_24"), + PINCTRL_PIN(25, "GPIO_25"), + PINCTRL_PIN(26, "GPIO_26"), + PINCTRL_PIN(27, "GPIO_27"), + PINCTRL_PIN(28, "GPIO_28"), + PINCTRL_PIN(29, "GPIO_29"), + PINCTRL_PIN(30, "GPIO_30"), + PINCTRL_PIN(31, "GPIO_31"), + PINCTRL_PIN(32, "GPIO_32"), + PINCTRL_PIN(33, "GPIO_33"), + PINCTRL_PIN(34, "GPIO_34"), + PINCTRL_PIN(35, "GPIO_35"), + PINCTRL_PIN(36, "GPIO_36"), + PINCTRL_PIN(37, "GPIO_37"), + PINCTRL_PIN(38, "GPIO_38"), + PINCTRL_PIN(39, "GPIO_39"), + PINCTRL_PIN(40, "GPIO_40"), + PINCTRL_PIN(41, "GPIO_41"), + PINCTRL_PIN(42, "GPIO_42"), + PINCTRL_PIN(43, "GPIO_43"), + PINCTRL_PIN(44, "GPIO_44"), + PINCTRL_PIN(45, "GPIO_45"), + PINCTRL_PIN(46, "GPIO_46"), + PINCTRL_PIN(47, "GPIO_47"), + PINCTRL_PIN(48, "GPIO_48"), + PINCTRL_PIN(49, "GPIO_49"), + PINCTRL_PIN(50, "GPIO_50"), + PINCTRL_PIN(51, "GPIO_51"), + PINCTRL_PIN(52, "GPIO_52"), + PINCTRL_PIN(53, "GPIO_53"), + PINCTRL_PIN(54, "GPIO_54"), + PINCTRL_PIN(55, "GPIO_55"), + PINCTRL_PIN(56, "GPIO_56"), + PINCTRL_PIN(57, "GPIO_57"), + PINCTRL_PIN(58, "GPIO_58"), + PINCTRL_PIN(59, "GPIO_59"), + PINCTRL_PIN(60, "GPIO_60"), + PINCTRL_PIN(61, "GPIO_61"), + PINCTRL_PIN(62, "GPIO_62"), + PINCTRL_PIN(63, "GPIO_63"), + PINCTRL_PIN(64, "GPIO_64"), +}; + +#define DECLARE_MSM_GPIO_PINS(pin) \ + static const unsigned int gpio##pin##_pins[] = { pin } +DECLARE_MSM_GPIO_PINS(0); +DECLARE_MSM_GPIO_PINS(1); +DECLARE_MSM_GPIO_PINS(2); +DECLARE_MSM_GPIO_PINS(3); +DECLARE_MSM_GPIO_PINS(4); +DECLARE_MSM_GPIO_PINS(5); +DECLARE_MSM_GPIO_PINS(6); +DECLARE_MSM_GPIO_PINS(7); +DECLARE_MSM_GPIO_PINS(8); +DECLARE_MSM_GPIO_PINS(9); +DECLARE_MSM_GPIO_PINS(10); +DECLARE_MSM_GPIO_PINS(11); +DECLARE_MSM_GPIO_PINS(12); +DECLARE_MSM_GPIO_PINS(13); +DECLARE_MSM_GPIO_PINS(14); +DECLARE_MSM_GPIO_PINS(15); +DECLARE_MSM_GPIO_PINS(16); +DECLARE_MSM_GPIO_PINS(17); +DECLARE_MSM_GPIO_PINS(18); +DECLARE_MSM_GPIO_PINS(19); +DECLARE_MSM_GPIO_PINS(20); +DECLARE_MSM_GPIO_PINS(21); +DECLARE_MSM_GPIO_PINS(22); +DECLARE_MSM_GPIO_PINS(23); +DECLARE_MSM_GPIO_PINS(24); +DECLARE_MSM_GPIO_PINS(25); +DECLARE_MSM_GPIO_PINS(26); +DECLARE_MSM_GPIO_PINS(27); +DECLARE_MSM_GPIO_PINS(28); +DECLARE_MSM_GPIO_PINS(29); +DECLARE_MSM_GPIO_PINS(30); +DECLARE_MSM_GPIO_PINS(31); +DECLARE_MSM_GPIO_PINS(32); +DECLARE_MSM_GPIO_PINS(33); +DECLARE_MSM_GPIO_PINS(34); +DECLARE_MSM_GPIO_PINS(35); +DECLARE_MSM_GPIO_PINS(36); +DECLARE_MSM_GPIO_PINS(37); +DECLARE_MSM_GPIO_PINS(38); +DECLARE_MSM_GPIO_PINS(39); +DECLARE_MSM_GPIO_PINS(40); +DECLARE_MSM_GPIO_PINS(41); +DECLARE_MSM_GPIO_PINS(42); +DECLARE_MSM_GPIO_PINS(43); +DECLARE_MSM_GPIO_PINS(44); +DECLARE_MSM_GPIO_PINS(45); +DECLARE_MSM_GPIO_PINS(46); +DECLARE_MSM_GPIO_PINS(47); +DECLARE_MSM_GPIO_PINS(48); +DECLARE_MSM_GPIO_PINS(49); +DECLARE_MSM_GPIO_PINS(50); +DECLARE_MSM_GPIO_PINS(51); +DECLARE_MSM_GPIO_PINS(52); +DECLARE_MSM_GPIO_PINS(53); +DECLARE_MSM_GPIO_PINS(54); +DECLARE_MSM_GPIO_PINS(55); +DECLARE_MSM_GPIO_PINS(56); +DECLARE_MSM_GPIO_PINS(57); +DECLARE_MSM_GPIO_PINS(58); +DECLARE_MSM_GPIO_PINS(59); +DECLARE_MSM_GPIO_PINS(60); +DECLARE_MSM_GPIO_PINS(61); +DECLARE_MSM_GPIO_PINS(62); +DECLARE_MSM_GPIO_PINS(63); +DECLARE_MSM_GPIO_PINS(64); + +enum ipq9574_functions { + msm_mux_atest_char, + msm_mux_atest_char0, + msm_mux_atest_char1, + msm_mux_atest_char2, + msm_mux_atest_char3, + msm_mux_audio_pdm0, + msm_mux_audio_pdm1, + msm_mux_audio_pri, + msm_mux_audio_sec, + msm_mux_blsp0_spi, + msm_mux_blsp0_uart, + msm_mux_blsp1_i2c, + msm_mux_blsp1_spi, + msm_mux_blsp1_uart, + msm_mux_blsp2_i2c, + msm_mux_blsp2_spi, + msm_mux_blsp2_uart, + msm_mux_blsp3_i2c, + msm_mux_blsp3_spi, + msm_mux_blsp3_uart, + msm_mux_blsp4_i2c, + msm_mux_blsp4_spi, + msm_mux_blsp4_uart, + msm_mux_blsp5_i2c, + msm_mux_blsp5_uart, + msm_mux_cri_trng0, + msm_mux_cri_trng1, + msm_mux_cri_trng2, + msm_mux_cri_trng3, + msm_mux_cxc0, + msm_mux_cxc1, + msm_mux_dbg_out, + msm_mux_dwc_ddrphy, + msm_mux_gcc_plltest, + msm_mux_gcc_tlmm, + msm_mux_gpio, + msm_mux_mac, + msm_mux_mdc, + msm_mux_mdio, + msm_mux_pcie0_clk, + msm_mux_pcie0_wake, + msm_mux_pcie1_clk, + msm_mux_pcie1_wake, + msm_mux_pcie2_clk, + msm_mux_pcie2_wake, + msm_mux_pcie3_clk, + msm_mux_pcie3_wake, + msm_mux_prng_rosc0, + msm_mux_prng_rosc1, + msm_mux_prng_rosc2, + msm_mux_prng_rosc3, + msm_mux_pta, + msm_mux_pwm, + msm_mux_qdss_cti_trig_in_a0, + msm_mux_qdss_cti_trig_in_a1, + msm_mux_qdss_cti_trig_in_b0, + msm_mux_qdss_cti_trig_in_b1, + msm_mux_qdss_cti_trig_out_a0, + msm_mux_qdss_cti_trig_out_a1, + msm_mux_qdss_cti_trig_out_b0, + msm_mux_qdss_cti_trig_out_b1, + msm_mux_qdss_traceclk_a, + msm_mux_qdss_traceclk_b, + msm_mux_qdss_tracectl_a, + msm_mux_qdss_tracectl_b, + msm_mux_qdss_tracedata_a, + msm_mux_qdss_tracedata_b, + msm_mux_qspi_data, + msm_mux_qspi_clk, + msm_mux_qspi_cs, + msm_mux_rx0, + msm_mux_rx1, + msm_mux_sdc_data, + msm_mux_sdc_clk, + msm_mux_sdc_cmd, + msm_mux_sdc_rclk, + msm_mux_tsens_max, + msm_mux_wci20, + msm_mux_wci21, + msm_mux_wsa_swrm, + msm_mux__, +}; + +static const char * const gpio_groups[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", + "gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", + "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", + "gpio22", "gpio23", "gpio24", "gpio25", "gpio26", "gpio27", "gpio28", + "gpio29", "gpio30", "gpio31", "gpio32", "gpio33", "gpio34", "gpio35", + "gpio36", "gpio37", "gpio38", "gpio39", "gpio40", "gpio41", "gpio42", + "gpio43", "gpio44", "gpio45", "gpio46", "gpio47", "gpio48", "gpio49", + "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", "gpio56", + "gpio57", "gpio58", "gpio59", "gpio60", "gpio61", "gpio62", "gpio63", + "gpio64", +}; + +static const char * const sdc_data_groups[] = { + "gpio0", + "gpio1", + "gpio2", + "gpio3", + "gpio6", + "gpio7", + "gpio8", + "gpio9", +}; + +static const char * const qspi_data_groups[] = { + "gpio0", + "gpio1", + "gpio2", + "gpio3", +}; + +static const char * const qdss_traceclk_b_groups[] = { + "gpio0", +}; + +static const char * const qdss_tracectl_b_groups[] = { + "gpio1", +}; + +static const char * const qdss_tracedata_b_groups[] = { + "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", "gpio8", "gpio9", + "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", "gpio15", "gpio16", + "gpio17", +}; + +static const char * const sdc_cmd_groups[] = { + "gpio4", +}; + +static const char * const qspi_cs_groups[] = { + "gpio4", +}; + +static const char * const sdc_clk_groups[] = { + "gpio5", +}; + +static const char * const qspi_clk_groups[] = { + "gpio5", +}; + +static const char * const sdc_rclk_groups[] = { + "gpio10", +}; + +static const char * const blsp0_spi_groups[] = { + "gpio11", "gpio12", "gpio13", "gpio14", +}; + +static const char * const blsp0_uart_groups[] = { + "gpio11", "gpio12", "gpio13", "gpio14", +}; + +static const char * const blsp3_spi_groups[] = { + "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", +}; + +static const char * const blsp3_i2c_groups[] = { + "gpio15", "gpio16", +}; + +static const char * const blsp3_uart_groups[] = { + "gpio15", "gpio16", "gpio17", "gpio18", +}; + +static const char * const dbg_out_groups[] = { + "gpio17", +}; + +static const char * const cri_trng0_groups[] = { + "gpio20", "gpio38", +}; + +static const char * const cri_trng1_groups[] = { + "gpio21", "gpio34", +}; + +static const char * const pcie0_clk_groups[] = { + "gpio22", +}; + +static const char * const pta_groups[] = { + "gpio22", "gpio23", "gpio24", "gpio54", "gpio55", "gpio56", "gpio61", + "gpio62", "gpio63", +}; + +static const char * const wci21_groups[] = { + "gpio23", "gpio24", +}; + +static const char * const cxc0_groups[] = { + "gpio23", "gpio24", +}; + +static const char * const pcie0_wake_groups[] = { + "gpio24", +}; + +static const char * const qdss_cti_trig_out_b0_groups[] = { + "gpio24", +}; + +static const char * const pcie1_clk_groups[] = { + "gpio25", +}; + +static const char * const qdss_cti_trig_in_b0_groups[] = { + "gpio25", +}; + +static const char * const atest_char0_groups[] = { + "gpio26", +}; + +static const char * const qdss_cti_trig_out_b1_groups[] = { + "gpio26", +}; + +static const char * const pcie1_wake_groups[] = { + "gpio27", +}; + +static const char * const atest_char1_groups[] = { + "gpio27", +}; + +static const char * const qdss_cti_trig_in_b1_groups[] = { + "gpio27", +}; + +static const char * const pcie2_clk_groups[] = { + "gpio28", +}; + +static const char * const atest_char2_groups[] = { + "gpio28", +}; + +static const char * const atest_char3_groups[] = { + "gpio29", +}; + +static const char * const pcie2_wake_groups[] = { + "gpio30", +}; + +static const char * const pwm_groups[] = { + "gpio30", "gpio31", "gpio32", "gpio33", "gpio44", "gpio45", "gpio46", + "gpio47", "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", + "gpio56", "gpio57", "gpio58", "gpio59", "gpio60", +}; + +static const char * const atest_char_groups[] = { + "gpio30", +}; + +static const char * const pcie3_clk_groups[] = { + "gpio31", +}; + +static const char * const qdss_cti_trig_in_a1_groups[] = { + "gpio31", +}; + +static const char * const qdss_cti_trig_out_a1_groups[] = { + "gpio32", +}; + +static const char * const pcie3_wake_groups[] = { + "gpio33", +}; + +static const char * const qdss_cti_trig_in_a0_groups[] = { + "gpio33", +}; + +static const char * const blsp2_uart_groups[] = { + "gpio34", "gpio35", +}; + +static const char * const blsp2_i2c_groups[] = { + "gpio34", "gpio35", +}; + +static const char * const blsp2_spi_groups[] = { + "gpio34", "gpio35", "gpio36", "gpio37", +}; + +static const char * const blsp1_uart_groups[] = { + "gpio34", "gpio35", "gpio36", "gpio37", +}; + +static const char * const qdss_cti_trig_out_a0_groups[] = { + "gpio34", +}; + +static const char * const cri_trng2_groups[] = { + "gpio35", +}; + +static const char * const blsp1_i2c_groups[] = { + "gpio36", "gpio37", +}; + +static const char * const cri_trng3_groups[] = { + "gpio36", +}; + +static const char * const dwc_ddrphy_groups[] = { + "gpio37", +}; + +static const char * const mdc_groups[] = { + "gpio38", +}; + +static const char * const mdio_groups[] = { + "gpio39", +}; + +static const char * const audio_pri_groups[] = { + "gpio40", "gpio41", "gpio42", "gpio43", "gpio61", "gpio61", +}; + +static const char * const audio_pdm0_groups[] = { + "gpio40", "gpio41", "gpio42", "gpio43", +}; + +static const char * const qdss_traceclk_a_groups[] = { + "gpio43", +}; + +static const char * const audio_sec_groups[] = { + "gpio44", "gpio45", "gpio46", "gpio47", "gpio62", "gpio62", +}; + +static const char * const wsa_swrm_groups[] = { + "gpio44", "gpio45", +}; + +static const char * const qdss_tracectl_a_groups[] = { + "gpio44", +}; + +static const char * const qdss_tracedata_a_groups[] = { + "gpio45", "gpio46", "gpio47", "gpio48", "gpio49", "gpio50", "gpio51", + "gpio52", "gpio53", "gpio54", "gpio55", "gpio56", "gpio57", "gpio58", + "gpio59", "gpio60", +}; + +static const char * const rx1_groups[] = { + "gpio46", +}; + +static const char * const mac_groups[] = { + "gpio46", "gpio47", "gpio57", "gpio58", +}; + +static const char * const blsp5_i2c_groups[] = { + "gpio48", "gpio49", +}; + +static const char * const blsp5_uart_groups[] = { + "gpio48", "gpio49", +}; + +static const char * const blsp4_uart_groups[] = { + "gpio50", "gpio51", "gpio52", "gpio53", +}; + +static const char * const blsp4_i2c_groups[] = { + "gpio50", "gpio51", +}; + +static const char * const blsp4_spi_groups[] = { + "gpio50", "gpio51", "gpio52", "gpio53", +}; + +static const char * const wci20_groups[] = { + "gpio57", "gpio58", +}; + +static const char * const cxc1_groups[] = { + "gpio57", "gpio58", +}; + +static const char * const rx0_groups[] = { + "gpio59", +}; + +static const char * const prng_rosc0_groups[] = { + "gpio60", +}; + +static const char * const gcc_plltest_groups[] = { + "gpio60", "gpio62", +}; + +static const char * const blsp1_spi_groups[] = { + "gpio61", "gpio62", "gpio63", "gpio64", +}; + +static const char * const audio_pdm1_groups[] = { + "gpio61", "gpio62", "gpio63", "gpio64", +}; + +static const char * const prng_rosc1_groups[] = { + "gpio61", +}; + +static const char * const gcc_tlmm_groups[] = { + "gpio61", +}; + +static const char * const prng_rosc2_groups[] = { + "gpio62", +}; + +static const char * const prng_rosc3_groups[] = { + "gpio63", +}; + +static const char * const tsens_max_groups[] = { + "gpio64", +}; + +static const struct msm_function ipq9574_functions[] = { + FUNCTION(atest_char), + FUNCTION(atest_char0), + FUNCTION(atest_char1), + FUNCTION(atest_char2), + FUNCTION(atest_char3), + FUNCTION(audio_pdm0), + FUNCTION(audio_pdm1), + FUNCTION(audio_pri), + FUNCTION(audio_sec), + FUNCTION(blsp0_spi), + FUNCTION(blsp0_uart), + FUNCTION(blsp1_i2c), + FUNCTION(blsp1_spi), + FUNCTION(blsp1_uart), + FUNCTION(blsp2_i2c), + FUNCTION(blsp2_spi), + FUNCTION(blsp2_uart), + FUNCTION(blsp3_i2c), + FUNCTION(blsp3_spi), + FUNCTION(blsp3_uart), + FUNCTION(blsp4_i2c), + FUNCTION(blsp4_spi), + FUNCTION(blsp4_uart), + FUNCTION(blsp5_i2c), + FUNCTION(blsp5_uart), + FUNCTION(cri_trng0), + FUNCTION(cri_trng1), + FUNCTION(cri_trng2), + FUNCTION(cri_trng3), + FUNCTION(cxc0), + FUNCTION(cxc1), + FUNCTION(dbg_out), + FUNCTION(dwc_ddrphy), + FUNCTION(gcc_plltest), + FUNCTION(gcc_tlmm), + FUNCTION(gpio), + FUNCTION(mac), + FUNCTION(mdc), + FUNCTION(mdio), + FUNCTION(pcie0_clk), + FUNCTION(pcie0_wake), + FUNCTION(pcie1_clk), + FUNCTION(pcie1_wake), + FUNCTION(pcie2_clk), + FUNCTION(pcie2_wake), + FUNCTION(pcie3_clk), + FUNCTION(pcie3_wake), + FUNCTION(prng_rosc0), + FUNCTION(prng_rosc1), + FUNCTION(prng_rosc2), + FUNCTION(prng_rosc3), + FUNCTION(pta), + FUNCTION(pwm), + FUNCTION(qdss_cti_trig_in_a0), + FUNCTION(qdss_cti_trig_in_a1), + FUNCTION(qdss_cti_trig_in_b0), + FUNCTION(qdss_cti_trig_in_b1), + FUNCTION(qdss_cti_trig_out_a0), + FUNCTION(qdss_cti_trig_out_a1), + FUNCTION(qdss_cti_trig_out_b0), + FUNCTION(qdss_cti_trig_out_b1), + FUNCTION(qdss_traceclk_a), + FUNCTION(qdss_traceclk_b), + FUNCTION(qdss_tracectl_a), + FUNCTION(qdss_tracectl_b), + FUNCTION(qdss_tracedata_a), + FUNCTION(qdss_tracedata_b), + FUNCTION(qspi_data), + FUNCTION(qspi_clk), + FUNCTION(qspi_cs), + FUNCTION(rx0), + FUNCTION(rx1), + FUNCTION(sdc_data), + FUNCTION(sdc_clk), + FUNCTION(sdc_cmd), + FUNCTION(sdc_rclk), + FUNCTION(tsens_max), + FUNCTION(wci20), + FUNCTION(wci21), + FUNCTION(wsa_swrm), +}; + +static const struct msm_pingroup ipq9574_groups[] = { + PINGROUP(0, sdc_data, qspi_data, qdss_traceclk_b, _, _, _, _, _, _), + PINGROUP(1, sdc_data, qspi_data, qdss_tracectl_b, _, _, _, _, _, _), + PINGROUP(2, sdc_data, qspi_data, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(3, sdc_data, qspi_data, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(4, sdc_cmd, qspi_cs, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(5, sdc_clk, qspi_clk, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(6, sdc_data, qdss_tracedata_b, _, _, _, _, _, _, _), + PINGROUP(7, sdc_data, qdss_tracedata_b, _, _, _, _, _, _, _), + PINGROUP(8, sdc_data, qdss_tracedata_b, _, _, _, _, _, _, _), + PINGROUP(9, sdc_data, qdss_tracedata_b, _, _, _, _, _, _, _), + PINGROUP(10, sdc_rclk, qdss_tracedata_b, _, _, _, _, _, _, _), + PINGROUP(11, blsp0_spi, blsp0_uart, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(12, blsp0_spi, blsp0_uart, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(13, blsp0_spi, blsp0_uart, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(14, blsp0_spi, blsp0_uart, qdss_tracedata_b, _, _, _, _, _, _), + PINGROUP(15, blsp3_spi, blsp3_i2c, blsp3_uart, qdss_tracedata_b, _, _, _, _, _), + PINGROUP(16, blsp3_spi, blsp3_i2c, blsp3_uart, qdss_tracedata_b, _, _, _, _, _), + PINGROUP(17, blsp3_spi, blsp3_uart, dbg_out, qdss_tracedata_b, _, _, _, _, _), + PINGROUP(18, blsp3_spi, blsp3_uart, _, _, _, _, _, _, _), + PINGROUP(19, blsp3_spi, _, _, _, _, _, _, _, _), + PINGROUP(20, blsp3_spi, _, cri_trng0, _, _, _, _, _, _), + PINGROUP(21, blsp3_spi, _, cri_trng1, _, _, _, _, _, _), + PINGROUP(22, pcie0_clk, _, pta, _, _, _, _, _, _), + PINGROUP(23, _, pta, wci21, cxc0, _, _, _, _, _), + PINGROUP(24, pcie0_wake, _, pta, wci21, cxc0, _, qdss_cti_trig_out_b0, _, _), + PINGROUP(25, pcie1_clk, _, _, qdss_cti_trig_in_b0, _, _, _, _, _), + PINGROUP(26, _, atest_char0, _, qdss_cti_trig_out_b1, _, _, _, _, _), + PINGROUP(27, pcie1_wake, _, atest_char1, qdss_cti_trig_in_b1, _, _, _, _, _), + PINGROUP(28, pcie2_clk, atest_char2, _, _, _, _, _, _, _), + PINGROUP(29, atest_char3, _, _, _, _, _, _, _, _), + PINGROUP(30, pcie2_wake, pwm, atest_char, _, _, _, _, _, _), + PINGROUP(31, pcie3_clk, pwm, _, qdss_cti_trig_in_a1, _, _, _, _, _), + PINGROUP(32, pwm, _, qdss_cti_trig_out_a1, _, _, _, _, _, _), + PINGROUP(33, pcie3_wake, pwm, _, qdss_cti_trig_in_a0, _, _, _, _, _), + PINGROUP(34, blsp2_uart, blsp2_i2c, blsp2_spi, blsp1_uart, _, cri_trng1, qdss_cti_trig_out_a0, _, _), + PINGROUP(35, blsp2_uart, blsp2_i2c, blsp2_spi, blsp1_uart, _, cri_trng2, _, _, _), + PINGROUP(36, blsp1_uart, blsp1_i2c, blsp2_spi, _, cri_trng3, _, _, _, _), + PINGROUP(37, blsp1_uart, blsp1_i2c, blsp2_spi, _, dwc_ddrphy, _, _, _, _), + PINGROUP(38, mdc, _, cri_trng0, _, _, _, _, _, _), + PINGROUP(39, mdio, _, _, _, _, _, _, _, _), + PINGROUP(40, audio_pri, audio_pdm0, _, _, _, _, _, _, _), + PINGROUP(41, audio_pri, audio_pdm0, _, _, _, _, _, _, _), + PINGROUP(42, audio_pri, audio_pdm0, _, _, _, _, _, _, _), + PINGROUP(43, audio_pri, audio_pdm0, _, qdss_traceclk_a, _, _, _, _, _), + PINGROUP(44, pwm, audio_sec, wsa_swrm, _, qdss_tracectl_a, _, _, _, _), + PINGROUP(45, pwm, audio_sec, wsa_swrm, _, qdss_tracedata_a, _, _, _, _), + PINGROUP(46, pwm, audio_sec, rx1, mac, _, qdss_tracedata_a, _, _, _), + PINGROUP(47, pwm, audio_sec, mac, _, qdss_tracedata_a, _, _, _, _), + PINGROUP(48, blsp5_i2c, blsp5_uart, _, qdss_tracedata_a, _, _, _, _, _), + PINGROUP(49, blsp5_i2c, blsp5_uart, _, qdss_tracedata_a, _, _, _, _, _), + PINGROUP(50, blsp4_uart, blsp4_i2c, blsp4_spi, pwm, qdss_tracedata_a, _, _, _, _), + PINGROUP(51, blsp4_uart, blsp4_i2c, blsp4_spi, pwm, qdss_tracedata_a, _, _, _, _), + PINGROUP(52, blsp4_uart, blsp4_spi, pwm, qdss_tracedata_a, _, _, _, _, _), + PINGROUP(53, blsp4_uart, blsp4_spi, pwm, qdss_tracedata_a, _, _, _, _, _), + PINGROUP(54, pta, pwm, qdss_tracedata_a, _, _, _, _, _, _), + PINGROUP(55, pta, pwm, qdss_tracedata_a, _, _, _, _, _, _), + PINGROUP(56, pta, pwm, qdss_tracedata_a, _, _, _, _, _, _), + PINGROUP(57, wci20, cxc1, mac, pwm, qdss_tracedata_a, _, _, _, _), + PINGROUP(58, wci20, cxc1, mac, pwm, qdss_tracedata_a, _, _, _, _), + PINGROUP(59, rx0, pwm, qdss_tracedata_a, _, _, _, _, _, _), + PINGROUP(60, pwm, prng_rosc0, qdss_tracedata_a, _, gcc_plltest, _, _, _, _), + PINGROUP(61, blsp1_spi, audio_pri, audio_pdm1, audio_pri, pta, prng_rosc1, gcc_tlmm, _, _), + PINGROUP(62, blsp1_spi, audio_sec, audio_pdm1, audio_sec, pta, prng_rosc2, gcc_plltest, _, _), + PINGROUP(63, blsp1_spi, audio_pdm1, pta, prng_rosc3, _, _, _, _, _), + PINGROUP(64, blsp1_spi, audio_pdm1, tsens_max, _, _, _, _, _, _), +}; + +/* Reserving GPIO59 for controlling the QFPROM LDO regulator */ +static const int ipq9574_reserved_gpios[] = { + 59, -1 +}; + +static const struct msm_pinctrl_soc_data ipq9574_pinctrl = { + .pins = ipq9574_pins, + .npins = ARRAY_SIZE(ipq9574_pins), + .functions = ipq9574_functions, + .nfunctions = ARRAY_SIZE(ipq9574_functions), + .groups = ipq9574_groups, + .ngroups = ARRAY_SIZE(ipq9574_groups), + .reserved_gpios = ipq9574_reserved_gpios, + .ngpios = 65, +}; + +static int ipq9574_pinctrl_probe(struct platform_device *pdev) +{ + return msm_pinctrl_probe(pdev, &ipq9574_pinctrl); +} + +static const struct of_device_id ipq9574_pinctrl_of_match[] = { + { .compatible = "qcom,ipq9574-tlmm", }, + { } +}; +MODULE_DEVICE_TABLE(of, ipq9574_pinctrl_of_match); + +static struct platform_driver ipq9574_pinctrl_driver = { + .driver = { + .name = "ipq9574-tlmm", + .of_match_table = ipq9574_pinctrl_of_match, + }, + .probe = ipq9574_pinctrl_probe, + .remove = msm_pinctrl_remove, +}; + +static int __init ipq9574_pinctrl_init(void) +{ + return platform_driver_register(&ipq9574_pinctrl_driver); +} +arch_initcall(ipq9574_pinctrl_init); + +static void __exit ipq9574_pinctrl_exit(void) +{ + platform_driver_unregister(&ipq9574_pinctrl_driver); +} +module_exit(ipq9574_pinctrl_exit); + +MODULE_DESCRIPTION("QTI IPQ9574 TLMM driver"); +MODULE_LICENSE("GPL"); -- GitLab From f1148d3491b4b76eb233e6f6b85e9811ae4c96f8 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 14 Mar 2023 23:27:05 +0100 Subject: [PATCH 0901/5631] dt-bindings: pinctrl: qcom,qcm2290-tlmm: Allow input-enable Allow the common input-enable. This was missed with the initial submission. Fixes: 5147022214db ("dt-bindings: pinctrl: qcom: Add QCM2290 pinctrl bindings") Signed-off-by: Konrad Dybcio Acked-by: Shawn Guo Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230314222705.2940258-1-konrad.dybcio@linaro.org Signed-off-by: Linus Walleij --- Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml index 6271fd15e0b6..032763649336 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcm2290-tlmm.yaml @@ -85,6 +85,7 @@ $defs: bias-pull-up: true bias-disable: true drive-strength: true + input-enable: true output-high: true output-low: true -- GitLab From cae630bf47f84d426407ff6261debfe073ce8a4b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 16 Mar 2023 11:58:00 +0100 Subject: [PATCH 0902/5631] dt-bindings: pinctrl: qcom,sc8280xp-tlmm: allow 'bias-bus-hold' The controller supports 'bias-bus-hold' so add it to the binding. Signed-off-by: Johan Hovold Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230316105800.18751-1-johan+linaro@kernel.org Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml index 97b27d6835e9..4ae39fc7894a 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8280xp-tlmm.yaml @@ -104,6 +104,7 @@ $defs: usb1_phy, usb1_sbrx, usb1_sbtx, usb1_usb4, usb2phy_ac, vsense_trigger ] + bias-bus-hold: true bias-disable: true bias-pull-down: true bias-pull-up: true -- GitLab From d11f932808dc689717e409bbc81b5093e7902fc9 Mon Sep 17 00:00:00 2001 From: Asmaa Mnebhi Date: Wed, 15 Mar 2023 17:50:27 -0400 Subject: [PATCH 0903/5631] pinctrl: mlxbf3: Add pinctrl driver support NVIDIA BlueField-3 SoC has a few pins that can be used as GPIOs or take the default hardware functionality. Add a driver for the pin muxing. Signed-off-by: Asmaa Mnebhi Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230315215027.30685-3-asmaa@nvidia.com Signed-off-by: Linus Walleij --- drivers/pinctrl/Kconfig | 13 ++ drivers/pinctrl/Makefile | 1 + drivers/pinctrl/pinctrl-mlxbf3.c | 320 +++++++++++++++++++++++++++++++ 3 files changed, 334 insertions(+) create mode 100644 drivers/pinctrl/pinctrl-mlxbf3.c diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index e2a24d668e41..fc6e2858c90c 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -523,6 +523,19 @@ config PINCTRL_ZYNQMP This driver can also be built as a module. If so, the module will be called pinctrl-zynqmp. +config PINCTRL_MLXBF3 + tristate "NVIDIA BlueField-3 SoC Pinctrl driver" + depends on (MELLANOX_PLATFORM && ARM64) || COMPILE_TEST + select PINMUX + select GPIOLIB + select GPIOLIB_IRQCHIP + select GPIO_MLXBF3 + help + Say Y to select the pinctrl driver for BlueField-3 SoCs. + This pin controller allows selecting the mux function for + each pin. This driver can also be built as a module called + pinctrl-mlxbf3. + source "drivers/pinctrl/actions/Kconfig" source "drivers/pinctrl/aspeed/Kconfig" source "drivers/pinctrl/bcm/Kconfig" diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index 413b1e6b6933..930307e248c5 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_PINCTRL_MCP23S08_I2C) += pinctrl-mcp23s08_i2c.o obj-$(CONFIG_PINCTRL_MCP23S08_SPI) += pinctrl-mcp23s08_spi.o obj-$(CONFIG_PINCTRL_MCP23S08) += pinctrl-mcp23s08.o obj-$(CONFIG_PINCTRL_MICROCHIP_SGPIO) += pinctrl-microchip-sgpio.o +obj-$(CONFIG_PINCTRL_MLXBF3) += pinctrl-mlxbf3.o obj-$(CONFIG_PINCTRL_OCELOT) += pinctrl-ocelot.o obj-$(CONFIG_PINCTRL_OXNAS) += pinctrl-oxnas.o obj-$(CONFIG_PINCTRL_PALMAS) += pinctrl-palmas.o diff --git a/drivers/pinctrl/pinctrl-mlxbf3.c b/drivers/pinctrl/pinctrl-mlxbf3.c new file mode 100644 index 000000000000..3698f7bbd88d --- /dev/null +++ b/drivers/pinctrl/pinctrl-mlxbf3.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0-only or BSD-3-Clause +/* Copyright (C) 2022 NVIDIA CORPORATION & AFFILIATES */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define MLXBF3_NGPIOS_GPIO0 32 +#define MLXBF3_MAX_GPIO_PINS 56 + +enum { + MLXBF3_GPIO_HW_MODE, + MLXBF3_GPIO_SW_MODE, +}; + +struct mlxbf3_pinctrl { + void __iomem *fw_ctrl_set0; + void __iomem *fw_ctrl_clr0; + void __iomem *fw_ctrl_set1; + void __iomem *fw_ctrl_clr1; + struct device *dev; + struct pinctrl_dev *pctl; + struct pinctrl_gpio_range gpio_range; +}; + +#define MLXBF3_GPIO_RANGE(_id, _pinbase, _gpiobase, _npins) \ + { \ + .name = "mlxbf3_gpio_range", \ + .id = _id, \ + .base = _gpiobase, \ + .pin_base = _pinbase, \ + .npins = _npins, \ + } + +static struct pinctrl_gpio_range mlxbf3_pinctrl_gpio_ranges[] = { + MLXBF3_GPIO_RANGE(0, 0, 480, 32), + MLXBF3_GPIO_RANGE(1, 32, 456, 24), +}; + +static const struct pinctrl_pin_desc mlxbf3_pins[] = { + PINCTRL_PIN(0, "gpio0"), + PINCTRL_PIN(1, "gpio1"), + PINCTRL_PIN(2, "gpio2"), + PINCTRL_PIN(3, "gpio3"), + PINCTRL_PIN(4, "gpio4"), + PINCTRL_PIN(5, "gpio5"), + PINCTRL_PIN(6, "gpio6"), + PINCTRL_PIN(7, "gpio7"), + PINCTRL_PIN(8, "gpio8"), + PINCTRL_PIN(9, "gpio9"), + PINCTRL_PIN(10, "gpio10"), + PINCTRL_PIN(11, "gpio11"), + PINCTRL_PIN(12, "gpio12"), + PINCTRL_PIN(13, "gpio13"), + PINCTRL_PIN(14, "gpio14"), + PINCTRL_PIN(15, "gpio15"), + PINCTRL_PIN(16, "gpio16"), + PINCTRL_PIN(17, "gpio17"), + PINCTRL_PIN(18, "gpio18"), + PINCTRL_PIN(19, "gpio19"), + PINCTRL_PIN(20, "gpio20"), + PINCTRL_PIN(21, "gpio21"), + PINCTRL_PIN(22, "gpio22"), + PINCTRL_PIN(23, "gpio23"), + PINCTRL_PIN(24, "gpio24"), + PINCTRL_PIN(25, "gpio25"), + PINCTRL_PIN(26, "gpio26"), + PINCTRL_PIN(27, "gpio27"), + PINCTRL_PIN(28, "gpio28"), + PINCTRL_PIN(29, "gpio29"), + PINCTRL_PIN(30, "gpio30"), + PINCTRL_PIN(31, "gpio31"), + PINCTRL_PIN(32, "gpio32"), + PINCTRL_PIN(33, "gpio33"), + PINCTRL_PIN(34, "gpio34"), + PINCTRL_PIN(35, "gpio35"), + PINCTRL_PIN(36, "gpio36"), + PINCTRL_PIN(37, "gpio37"), + PINCTRL_PIN(38, "gpio38"), + PINCTRL_PIN(39, "gpio39"), + PINCTRL_PIN(40, "gpio40"), + PINCTRL_PIN(41, "gpio41"), + PINCTRL_PIN(42, "gpio42"), + PINCTRL_PIN(43, "gpio43"), + PINCTRL_PIN(44, "gpio44"), + PINCTRL_PIN(45, "gpio45"), + PINCTRL_PIN(46, "gpio46"), + PINCTRL_PIN(47, "gpio47"), + PINCTRL_PIN(48, "gpio48"), + PINCTRL_PIN(49, "gpio49"), + PINCTRL_PIN(50, "gpio50"), + PINCTRL_PIN(51, "gpio51"), + PINCTRL_PIN(52, "gpio52"), + PINCTRL_PIN(53, "gpio53"), + PINCTRL_PIN(54, "gpio54"), + PINCTRL_PIN(55, "gpio55"), +}; + +/* + * All single-pin functions can be mapped to any GPIO, however pinmux applies + * functions to pin groups and only those groups declared as supporting that + * function. To make this work we must put each pin in its own dummy group so + * that the functions can be described as applying to all pins. + * We use the same name as in the datasheet. + */ +static const char * const mlxbf3_pinctrl_single_group_names[] = { + "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", + "gpio8", "gpio9", "gpio10", "gpio11", "gpio12", "gpio13", "gpio14", "gpio15", + "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", "gpio22", "gpio23", + "gpio24", "gpio25", "gpio26", "gpio27", "gpio28", "gpio29", "gpio30", "gpio31", + "gpio32", "gpio33", "gpio34", "gpio35", "gpio36", "gpio37", "gpio38", "gpio39", + "gpio40", "gpio41", "gpio42", "gpio43", "gpio44", "gpio45", "gpio46", "gpio47", + "gpio48", "gpio49", "gpio50", "gpio51", "gpio52", "gpio53", "gpio54", "gpio55", +}; + +static int mlxbf3_get_groups_count(struct pinctrl_dev *pctldev) +{ + /* Number single-pin groups */ + return MLXBF3_MAX_GPIO_PINS; +} + +static const char *mlxbf3_get_group_name(struct pinctrl_dev *pctldev, + unsigned int selector) +{ + return mlxbf3_pinctrl_single_group_names[selector]; +} + +static int mlxbf3_get_group_pins(struct pinctrl_dev *pctldev, + unsigned int selector, + const unsigned int **pins, + unsigned int *num_pins) +{ + /* return the dummy group for a single pin */ + *pins = &selector; + *num_pins = 1; + + return 0; +} + +static const struct pinctrl_ops mlxbf3_pinctrl_group_ops = { + .get_groups_count = mlxbf3_get_groups_count, + .get_group_name = mlxbf3_get_group_name, + .get_group_pins = mlxbf3_get_group_pins, +}; + +/* + * Only 2 functions are supported and they apply to all pins: + * 1) Default hardware functionality + * 2) Software controlled GPIO + */ +static const char * const mlxbf3_gpiofunc_group_names[] = { "swctrl" }; +static const char * const mlxbf3_hwfunc_group_names[] = { "hwctrl" }; + +struct pinfunction mlxbf3_pmx_funcs[] = { + PINCTRL_PINFUNCTION("hwfunc", mlxbf3_hwfunc_group_names, 1), + PINCTRL_PINFUNCTION("gpiofunc", mlxbf3_gpiofunc_group_names, 1), +}; + +static int mlxbf3_pmx_get_funcs_count(struct pinctrl_dev *pctldev) +{ + return ARRAY_SIZE(mlxbf3_pmx_funcs); +} + +static const char *mlxbf3_pmx_get_func_name(struct pinctrl_dev *pctldev, + unsigned int selector) +{ + return mlxbf3_pmx_funcs[selector].name; +} + +static int mlxbf3_pmx_get_groups(struct pinctrl_dev *pctldev, + unsigned int selector, + const char * const **groups, + unsigned int * const num_groups) +{ + *groups = mlxbf3_pmx_funcs[selector].groups; + *num_groups = MLXBF3_MAX_GPIO_PINS; + + return 0; +} + +static int mlxbf3_pmx_set(struct pinctrl_dev *pctldev, + unsigned int selector, + unsigned int group) +{ + struct mlxbf3_pinctrl *priv = pinctrl_dev_get_drvdata(pctldev); + + if (selector == MLXBF3_GPIO_HW_MODE) { + if (group < MLXBF3_NGPIOS_GPIO0) + writel(BIT(group), priv->fw_ctrl_clr0); + else + writel(BIT(group % MLXBF3_NGPIOS_GPIO0), priv->fw_ctrl_clr1); + } + + if (selector == MLXBF3_GPIO_SW_MODE) { + if (group < MLXBF3_NGPIOS_GPIO0) + writel(BIT(group), priv->fw_ctrl_set0); + else + writel(BIT(group % MLXBF3_NGPIOS_GPIO0), priv->fw_ctrl_set1); + } + + return 0; +} + +static int mlxbf3_gpio_request_enable(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) +{ + struct mlxbf3_pinctrl *priv = pinctrl_dev_get_drvdata(pctldev); + + if (offset < MLXBF3_NGPIOS_GPIO0) + writel(BIT(offset), priv->fw_ctrl_set0); + else + writel(BIT(offset % MLXBF3_NGPIOS_GPIO0), priv->fw_ctrl_set1); + + return 0; +} + +static void mlxbf3_gpio_disable_free(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned int offset) +{ + struct mlxbf3_pinctrl *priv = pinctrl_dev_get_drvdata(pctldev); + + /* disable GPIO functionality by giving control back to hardware */ + if (offset < MLXBF3_NGPIOS_GPIO0) + writel(BIT(offset), priv->fw_ctrl_clr0); + else + writel(BIT(offset % MLXBF3_NGPIOS_GPIO0), priv->fw_ctrl_clr1); +} + +static const struct pinmux_ops mlxbf3_pmx_ops = { + .get_functions_count = mlxbf3_pmx_get_funcs_count, + .get_function_name = mlxbf3_pmx_get_func_name, + .get_function_groups = mlxbf3_pmx_get_groups, + .set_mux = mlxbf3_pmx_set, + .gpio_request_enable = mlxbf3_gpio_request_enable, + .gpio_disable_free = mlxbf3_gpio_disable_free, +}; + +static struct pinctrl_desc mlxbf3_pin_desc = { + .name = "pinctrl-mlxbf3", + .pins = mlxbf3_pins, + .npins = ARRAY_SIZE(mlxbf3_pins), + .pctlops = &mlxbf3_pinctrl_group_ops, + .pmxops = &mlxbf3_pmx_ops, + .owner = THIS_MODULE, +}; + +static_assert(ARRAY_SIZE(mlxbf3_pinctrl_single_group_names) == MLXBF3_MAX_GPIO_PINS); + +static int mlxbf3_pinctrl_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mlxbf3_pinctrl *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = &pdev->dev; + + priv->fw_ctrl_set0 = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->fw_ctrl_set0)) + return PTR_ERR(priv->fw_ctrl_set0); + + priv->fw_ctrl_clr0 = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(priv->fw_ctrl_set0)) + return PTR_ERR(priv->fw_ctrl_set0); + + priv->fw_ctrl_set1 = devm_platform_ioremap_resource(pdev, 2); + if (IS_ERR(priv->fw_ctrl_set0)) + return PTR_ERR(priv->fw_ctrl_set0); + + priv->fw_ctrl_clr1 = devm_platform_ioremap_resource(pdev, 3); + if (IS_ERR(priv->fw_ctrl_set0)) + return PTR_ERR(priv->fw_ctrl_set0); + + ret = devm_pinctrl_register_and_init(dev, + &mlxbf3_pin_desc, + priv, + &priv->pctl); + if (ret) + return dev_err_probe(dev, ret, "Failed to register pinctrl\n"); + + ret = pinctrl_enable(priv->pctl); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable pinctrl\n"); + + pinctrl_add_gpio_ranges(priv->pctl, mlxbf3_pinctrl_gpio_ranges, 2); + + return 0; +} + +static const struct acpi_device_id mlxbf3_pinctrl_acpi_ids[] = { + { "MLNXBF34", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, mlxbf3_pinctrl_acpi_ids); + +static struct platform_driver mlxbf3_pinctrl_driver = { + .driver = { + .name = "pinctrl-mlxbf3", + .acpi_match_table = mlxbf3_pinctrl_acpi_ids, + }, + .probe = mlxbf3_pinctrl_probe, +}; +module_platform_driver(mlxbf3_pinctrl_driver); + +MODULE_DESCRIPTION("NVIDIA pinctrl driver"); +MODULE_AUTHOR("Asmaa Mnebhi "); +MODULE_LICENSE("Dual BSD/GPL"); -- GitLab From 6906f5060d39f95aa0be30e998e0cc1179ba3d04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 21:23:25 -0700 Subject: [PATCH 0904/5631] Input: iqs62x-keys - suppress duplicated error message in .remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a platform driver's remove callback returns non-zero the driver core emits an error message. In such a case however iqs62x_keys_remove() already issued a (better) message. So return zero to suppress the generic message. This patch has no other side effects as platform_remove() ignores the return value of .remove() after the warning. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230318225110.261439-1-u.kleine-koenig@pengutronix.de Signed-off-by: Dmitry Torokhov --- drivers/input/keyboard/iqs62x-keys.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/keyboard/iqs62x-keys.c b/drivers/input/keyboard/iqs62x-keys.c index db793a550c25..02ceebad7bda 100644 --- a/drivers/input/keyboard/iqs62x-keys.c +++ b/drivers/input/keyboard/iqs62x-keys.c @@ -320,7 +320,7 @@ static int iqs62x_keys_remove(struct platform_device *pdev) if (ret) dev_err(&pdev->dev, "Failed to unregister notifier: %d\n", ret); - return ret; + return 0; } static struct platform_driver iqs62x_keys_platform_driver = { -- GitLab From 69f27b45ab5e6c463656319bf94bb56be5ca7e02 Mon Sep 17 00:00:00 2001 From: "A, Rashmi" Date: Thu, 16 Mar 2023 17:35:48 +0530 Subject: [PATCH 0905/5631] phy: intel: Remove Thunder Bay eMMC PHY support Remove Thunder Bay specific code as the product got cancelled and there are no end customers or users. Signed-off-by: A, Rashmi Reviewed-by: Hunter, Adrian Link: https://lore.kernel.org/r/20230316120549.21486-4-rashmi.a@intel.com Signed-off-by: Vinod Koul --- drivers/phy/intel/Kconfig | 10 - drivers/phy/intel/Makefile | 1 - drivers/phy/intel/phy-intel-thunderbay-emmc.c | 509 ------------------ 3 files changed, 520 deletions(-) delete mode 100644 drivers/phy/intel/phy-intel-thunderbay-emmc.c diff --git a/drivers/phy/intel/Kconfig b/drivers/phy/intel/Kconfig index 18a3cc5b98c0..ac42bb2fb394 100644 --- a/drivers/phy/intel/Kconfig +++ b/drivers/phy/intel/Kconfig @@ -46,13 +46,3 @@ config PHY_INTEL_LGM_EMMC select GENERIC_PHY help Enable this to support the Intel EMMC PHY - -config PHY_INTEL_THUNDERBAY_EMMC - tristate "Intel Thunder Bay eMMC PHY driver" - depends on OF && (ARCH_THUNDERBAY || COMPILE_TEST) - select GENERIC_PHY - help - This option enables support for Intel Thunder Bay SoC eMMC PHY. - - To compile this driver as a module, choose M here: the module - will be called phy-intel-thunderbay-emmc.ko. diff --git a/drivers/phy/intel/Makefile b/drivers/phy/intel/Makefile index b7321d56b0bb..14550981a707 100644 --- a/drivers/phy/intel/Makefile +++ b/drivers/phy/intel/Makefile @@ -3,4 +3,3 @@ obj-$(CONFIG_PHY_INTEL_KEEMBAY_EMMC) += phy-intel-keembay-emmc.o obj-$(CONFIG_PHY_INTEL_KEEMBAY_USB) += phy-intel-keembay-usb.o obj-$(CONFIG_PHY_INTEL_LGM_COMBO) += phy-intel-lgm-combo.o obj-$(CONFIG_PHY_INTEL_LGM_EMMC) += phy-intel-lgm-emmc.o -obj-$(CONFIG_PHY_INTEL_THUNDERBAY_EMMC) += phy-intel-thunderbay-emmc.o diff --git a/drivers/phy/intel/phy-intel-thunderbay-emmc.c b/drivers/phy/intel/phy-intel-thunderbay-emmc.c deleted file mode 100644 index 593f6970b81e..000000000000 --- a/drivers/phy/intel/phy-intel-thunderbay-emmc.c +++ /dev/null @@ -1,509 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Intel ThunderBay eMMC PHY driver - * - * Copyright (C) 2021 Intel Corporation - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -/* eMMC/SD/SDIO core/phy configuration registers */ -#define CTRL_CFG_0 0x00 -#define CTRL_CFG_1 0x04 -#define CTRL_PRESET_0 0x08 -#define CTRL_PRESET_1 0x0c -#define CTRL_PRESET_2 0x10 -#define CTRL_PRESET_3 0x14 -#define CTRL_PRESET_4 0x18 -#define CTRL_CFG_2 0x1c -#define CTRL_CFG_3 0x20 -#define PHY_CFG_0 0x24 -#define PHY_CFG_1 0x28 -#define PHY_CFG_2 0x2c -#define PHYBIST_CTRL 0x30 -#define SDHC_STAT3 0x34 -#define PHY_STAT 0x38 -#define PHYBIST_STAT_0 0x3c -#define PHYBIST_STAT_1 0x40 -#define EMMC_AXI 0x44 - -/* CTRL_PRESET_3 */ -#define CTRL_PRESET3_MASK GENMASK(31, 0) -#define CTRL_PRESET3_SHIFT 0 - -/* CTRL_CFG_0 bit fields */ -#define SUPPORT_HS_MASK BIT(26) -#define SUPPORT_HS_SHIFT 26 - -#define SUPPORT_8B_MASK BIT(24) -#define SUPPORT_8B_SHIFT 24 - -/* CTRL_CFG_1 bit fields */ -#define SUPPORT_SDR50_MASK BIT(28) -#define SUPPORT_SDR50_SHIFT 28 -#define SLOT_TYPE_MASK GENMASK(27, 26) -#define SLOT_TYPE_OFFSET 26 -#define SUPPORT_64B_MASK BIT(24) -#define SUPPORT_64B_SHIFT 24 -#define SUPPORT_HS400_MASK BIT(2) -#define SUPPORT_HS400_SHIFT 2 -#define SUPPORT_DDR50_MASK BIT(1) -#define SUPPORT_DDR50_SHIFT 1 -#define SUPPORT_SDR104_MASK BIT(0) -#define SUPPORT_SDR104_SHIFT 0 - -/* PHY_CFG_0 bit fields */ -#define SEL_DLY_TXCLK_MASK BIT(29) -#define SEL_DLY_TXCLK_SHIFT 29 -#define SEL_DLY_RXCLK_MASK BIT(28) -#define SEL_DLY_RXCLK_SHIFT 28 - -#define OTAP_DLY_ENA_MASK BIT(27) -#define OTAP_DLY_ENA_SHIFT 27 -#define OTAP_DLY_SEL_MASK GENMASK(26, 23) -#define OTAP_DLY_SEL_SHIFT 23 -#define ITAP_CHG_WIN_MASK BIT(22) -#define ITAP_CHG_WIN_SHIFT 22 -#define ITAP_DLY_ENA_MASK BIT(21) -#define ITAP_DLY_ENA_SHIFT 21 -#define ITAP_DLY_SEL_MASK GENMASK(20, 16) -#define ITAP_DLY_SEL_SHIFT 16 -#define RET_ENB_MASK BIT(15) -#define RET_ENB_SHIFT 15 -#define RET_EN_MASK BIT(14) -#define RET_EN_SHIFT 14 -#define DLL_IFF_MASK GENMASK(13, 11) -#define DLL_IFF_SHIFT 11 -#define DLL_EN_MASK BIT(10) -#define DLL_EN_SHIFT 10 -#define DLL_TRIM_ICP_MASK GENMASK(9, 6) -#define DLL_TRIM_ICP_SHIFT 6 -#define RETRIM_EN_MASK BIT(5) -#define RETRIM_EN_SHIFT 5 -#define RETRIM_MASK BIT(4) -#define RETRIM_SHIFT 4 -#define DR_TY_MASK GENMASK(3, 1) -#define DR_TY_SHIFT 1 -#define PWR_DOWN_MASK BIT(0) -#define PWR_DOWN_SHIFT 0 - -/* PHY_CFG_1 bit fields */ -#define REN_DAT_MASK GENMASK(19, 12) -#define REN_DAT_SHIFT 12 -#define REN_CMD_MASK BIT(11) -#define REN_CMD_SHIFT 11 -#define REN_STRB_MASK BIT(10) -#define REN_STRB_SHIFT 10 -#define PU_STRB_MASK BIT(20) -#define PU_STRB_SHIFT 20 - -/* PHY_CFG_2 bit fields */ -#define CLKBUF_MASK GENMASK(24, 21) -#define CLKBUF_SHIFT 21 -#define SEL_STRB_MASK GENMASK(20, 13) -#define SEL_STRB_SHIFT 13 -#define SEL_FREQ_MASK GENMASK(12, 10) -#define SEL_FREQ_SHIFT 10 - -/* PHY_STAT bit fields */ -#define CAL_DONE BIT(6) -#define DLL_RDY BIT(5) - -#define OTAP_DLY 0x0 -#define ITAP_DLY 0x0 -#define STRB 0x33 - -/* From ACS_eMMC51_16nFFC_RO1100_Userguide_v1p0.pdf p17 */ -#define FREQSEL_200M_170M 0x0 -#define FREQSEL_170M_140M 0x1 -#define FREQSEL_140M_110M 0x2 -#define FREQSEL_110M_80M 0x3 -#define FREQSEL_80M_50M 0x4 -#define FREQSEL_275M_250M 0x5 -#define FREQSEL_250M_225M 0x6 -#define FREQSEL_225M_200M 0x7 - -/* Phy power status */ -#define PHY_UNINITIALIZED 0 -#define PHY_INITIALIZED 1 - -/* - * During init(400KHz) phy_settings will be called with 200MHZ clock - * To avoid incorrectly setting the phy for init(400KHZ) "phy_power_sts" is used. - * When actual clock is set always phy is powered off once and then powered on. - * (sdhci_arasan_set_clock). That feature will be used to identify whether the - * settings are for init phy_power_on or actual clock phy_power_on - * 0 --> init settings - * 1 --> actual settings - */ - -struct thunderbay_emmc_phy { - void __iomem *reg_base; - struct clk *emmcclk; - int phy_power_sts; -}; - -static inline void update_reg(struct thunderbay_emmc_phy *tbh_phy, u32 offset, - u32 mask, u32 shift, u32 val) -{ - u32 tmp; - - tmp = readl(tbh_phy->reg_base + offset); - tmp &= ~mask; - tmp |= val << shift; - writel(tmp, tbh_phy->reg_base + offset); -} - -static int thunderbay_emmc_phy_power(struct phy *phy, bool power_on) -{ - struct thunderbay_emmc_phy *tbh_phy = phy_get_drvdata(phy); - unsigned int freqsel = FREQSEL_200M_170M; - unsigned long rate; - static int lock; - u32 val; - int ret; - - /* Disable DLL */ - rate = clk_get_rate(tbh_phy->emmcclk); - switch (rate) { - case 200000000: - /* lock dll only when it is used, i.e only if SEL_DLY_TXCLK/RXCLK are 0 */ - update_reg(tbh_phy, PHY_CFG_0, DLL_EN_MASK, DLL_EN_SHIFT, 0x0); - break; - - /* dll lock not required for other frequencies */ - case 50000000 ... 52000000: - case 400000: - default: - break; - } - - if (!power_on) - return 0; - - rate = clk_get_rate(tbh_phy->emmcclk); - switch (rate) { - case 170000001 ... 200000000: - freqsel = FREQSEL_200M_170M; - break; - - case 140000001 ... 170000000: - freqsel = FREQSEL_170M_140M; - break; - - case 110000001 ... 140000000: - freqsel = FREQSEL_140M_110M; - break; - - case 80000001 ... 110000000: - freqsel = FREQSEL_110M_80M; - break; - - case 50000000 ... 80000000: - freqsel = FREQSEL_80M_50M; - break; - - case 250000001 ... 275000000: - freqsel = FREQSEL_275M_250M; - break; - - case 225000001 ... 250000000: - freqsel = FREQSEL_250M_225M; - break; - - case 200000001 ... 225000000: - freqsel = FREQSEL_225M_200M; - break; - default: - break; - } - /* Clock rate is checked against upper limit. It may fall low during init */ - if (rate > 200000000) - dev_warn(&phy->dev, "Unsupported rate: %lu\n", rate); - - udelay(5); - - if (lock == 0) { - /* PDB will be done only once per boot */ - update_reg(tbh_phy, PHY_CFG_0, PWR_DOWN_MASK, - PWR_DOWN_SHIFT, 0x1); - lock = 1; - /* - * According to the user manual, it asks driver to wait 5us for - * calpad busy trimming. However it is documented that this value is - * PVT(A.K.A. process, voltage and temperature) relevant, so some - * failure cases are found which indicates we should be more tolerant - * to calpad busy trimming. - */ - ret = readl_poll_timeout(tbh_phy->reg_base + PHY_STAT, - val, (val & CAL_DONE), 10, 50); - if (ret) { - dev_err(&phy->dev, "caldone failed, ret=%d\n", ret); - return ret; - } - } - rate = clk_get_rate(tbh_phy->emmcclk); - switch (rate) { - case 200000000: - /* Set frequency of the DLL operation */ - update_reg(tbh_phy, PHY_CFG_2, SEL_FREQ_MASK, SEL_FREQ_SHIFT, freqsel); - - /* Enable DLL */ - update_reg(tbh_phy, PHY_CFG_0, DLL_EN_MASK, DLL_EN_SHIFT, 0x1); - - /* - * After enabling analog DLL circuits docs say that we need 10.2 us if - * our source clock is at 50 MHz and that lock time scales linearly - * with clock speed. If we are powering on the PHY and the card clock - * is super slow (like 100kHz) this could take as long as 5.1 ms as - * per the math: 10.2 us * (50000000 Hz / 100000 Hz) => 5.1 ms - * hopefully we won't be running at 100 kHz, but we should still make - * sure we wait long enough. - * - * NOTE: There appear to be corner cases where the DLL seems to take - * extra long to lock for reasons that aren't understood. In some - * extreme cases we've seen it take up to over 10ms (!). We'll be - * generous and give it 50ms. - */ - ret = readl_poll_timeout(tbh_phy->reg_base + PHY_STAT, - val, (val & DLL_RDY), 10, 50 * USEC_PER_MSEC); - if (ret) { - dev_err(&phy->dev, "dllrdy failed, ret=%d\n", ret); - return ret; - } - break; - - default: - break; - } - return 0; -} - -static int thunderbay_emmc_phy_init(struct phy *phy) -{ - struct thunderbay_emmc_phy *tbh_phy = phy_get_drvdata(phy); - - tbh_phy->emmcclk = clk_get(&phy->dev, "emmcclk"); - - return PTR_ERR_OR_ZERO(tbh_phy->emmcclk); -} - -static int thunderbay_emmc_phy_exit(struct phy *phy) -{ - struct thunderbay_emmc_phy *tbh_phy = phy_get_drvdata(phy); - - clk_put(tbh_phy->emmcclk); - - return 0; -} - -static int thunderbay_emmc_phy_power_on(struct phy *phy) -{ - struct thunderbay_emmc_phy *tbh_phy = phy_get_drvdata(phy); - unsigned long rate; - - /* Overwrite capability bits configurable in bootloader */ - update_reg(tbh_phy, CTRL_CFG_0, - SUPPORT_HS_MASK, SUPPORT_HS_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_0, - SUPPORT_8B_MASK, SUPPORT_8B_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_1, - SUPPORT_SDR50_MASK, SUPPORT_SDR50_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_1, - SUPPORT_DDR50_MASK, SUPPORT_DDR50_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_1, - SUPPORT_SDR104_MASK, SUPPORT_SDR104_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_1, - SUPPORT_HS400_MASK, SUPPORT_HS400_SHIFT, 0x1); - update_reg(tbh_phy, CTRL_CFG_1, - SUPPORT_64B_MASK, SUPPORT_64B_SHIFT, 0x1); - - if (tbh_phy->phy_power_sts == PHY_UNINITIALIZED) { - /* Indicates initialization, settings for init, same as 400KHZ setting */ - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_TXCLK_MASK, SEL_DLY_TXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_RXCLK_MASK, SEL_DLY_RXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_ENA_MASK, ITAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_SEL_MASK, ITAP_DLY_SEL_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_ENA_MASK, OTAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_SEL_MASK, OTAP_DLY_SEL_SHIFT, 0); - update_reg(tbh_phy, PHY_CFG_0, DLL_TRIM_ICP_MASK, DLL_TRIM_ICP_SHIFT, 0); - update_reg(tbh_phy, PHY_CFG_0, DR_TY_MASK, DR_TY_SHIFT, 0x1); - - } else if (tbh_phy->phy_power_sts == PHY_INITIALIZED) { - /* Indicates actual clock setting */ - rate = clk_get_rate(tbh_phy->emmcclk); - switch (rate) { - case 200000000: - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_TXCLK_MASK, - SEL_DLY_TXCLK_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_RXCLK_MASK, - SEL_DLY_RXCLK_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_ENA_MASK, - ITAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_SEL_MASK, - ITAP_DLY_SEL_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_ENA_MASK, - OTAP_DLY_ENA_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_SEL_MASK, - OTAP_DLY_SEL_SHIFT, 2); - update_reg(tbh_phy, PHY_CFG_0, DLL_TRIM_ICP_MASK, - DLL_TRIM_ICP_SHIFT, 0x8); - update_reg(tbh_phy, PHY_CFG_0, DR_TY_MASK, - DR_TY_SHIFT, 0x1); - /* For HS400 only */ - update_reg(tbh_phy, PHY_CFG_2, SEL_STRB_MASK, - SEL_STRB_SHIFT, STRB); - break; - - case 50000000 ... 52000000: - /* For both HS and DDR52 this setting works */ - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_TXCLK_MASK, - SEL_DLY_TXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_RXCLK_MASK, - SEL_DLY_RXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_ENA_MASK, - ITAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_SEL_MASK, - ITAP_DLY_SEL_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_ENA_MASK, - OTAP_DLY_ENA_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_SEL_MASK, - OTAP_DLY_SEL_SHIFT, 4); - update_reg(tbh_phy, PHY_CFG_0, DLL_TRIM_ICP_MASK, - DLL_TRIM_ICP_SHIFT, 0x8); - update_reg(tbh_phy, PHY_CFG_0, - DR_TY_MASK, DR_TY_SHIFT, 0x1); - break; - - case 400000: - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_TXCLK_MASK, - SEL_DLY_TXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_RXCLK_MASK, - SEL_DLY_RXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_ENA_MASK, - ITAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_SEL_MASK, - ITAP_DLY_SEL_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_ENA_MASK, - OTAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_SEL_MASK, - OTAP_DLY_SEL_SHIFT, 0); - update_reg(tbh_phy, PHY_CFG_0, DLL_TRIM_ICP_MASK, - DLL_TRIM_ICP_SHIFT, 0); - update_reg(tbh_phy, PHY_CFG_0, DR_TY_MASK, DR_TY_SHIFT, 0x1); - break; - - default: - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_TXCLK_MASK, - SEL_DLY_TXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, SEL_DLY_RXCLK_MASK, - SEL_DLY_RXCLK_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_ENA_MASK, - ITAP_DLY_ENA_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, ITAP_DLY_SEL_MASK, - ITAP_DLY_SEL_SHIFT, 0x0); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_ENA_MASK, - OTAP_DLY_ENA_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, OTAP_DLY_SEL_MASK, - OTAP_DLY_SEL_SHIFT, 2); - update_reg(tbh_phy, PHY_CFG_0, DLL_TRIM_ICP_MASK, - DLL_TRIM_ICP_SHIFT, 0x8); - update_reg(tbh_phy, PHY_CFG_0, DR_TY_MASK, - DR_TY_SHIFT, 0x1); - break; - } - /* Reset, init seq called without phy_power_off, this indicates init seq */ - tbh_phy->phy_power_sts = PHY_UNINITIALIZED; - } - - update_reg(tbh_phy, PHY_CFG_0, RETRIM_EN_MASK, RETRIM_EN_SHIFT, 0x1); - update_reg(tbh_phy, PHY_CFG_0, RETRIM_MASK, RETRIM_SHIFT, 0x0); - - return thunderbay_emmc_phy_power(phy, 1); -} - -static int thunderbay_emmc_phy_power_off(struct phy *phy) -{ - struct thunderbay_emmc_phy *tbh_phy = phy_get_drvdata(phy); - - tbh_phy->phy_power_sts = PHY_INITIALIZED; - - return thunderbay_emmc_phy_power(phy, 0); -} - -static const struct phy_ops thunderbay_emmc_phy_ops = { - .init = thunderbay_emmc_phy_init, - .exit = thunderbay_emmc_phy_exit, - .power_on = thunderbay_emmc_phy_power_on, - .power_off = thunderbay_emmc_phy_power_off, - .owner = THIS_MODULE, -}; - -static const struct of_device_id thunderbay_emmc_phy_of_match[] = { - { .compatible = "intel,thunderbay-emmc-phy", - (void *)&thunderbay_emmc_phy_ops }, - {} -}; -MODULE_DEVICE_TABLE(of, thunderbay_emmc_phy_of_match); - -static int thunderbay_emmc_phy_probe(struct platform_device *pdev) -{ - struct thunderbay_emmc_phy *tbh_phy; - struct phy_provider *phy_provider; - struct device *dev = &pdev->dev; - const struct of_device_id *id; - struct phy *generic_phy; - struct resource *res; - - if (!dev->of_node) - return -ENODEV; - - tbh_phy = devm_kzalloc(dev, sizeof(*tbh_phy), GFP_KERNEL); - if (!tbh_phy) - return -ENOMEM; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - tbh_phy->reg_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(tbh_phy->reg_base)) - return PTR_ERR(tbh_phy->reg_base); - - tbh_phy->phy_power_sts = PHY_UNINITIALIZED; - id = of_match_node(thunderbay_emmc_phy_of_match, pdev->dev.of_node); - if (!id) { - dev_err(dev, "failed to get match_node\n"); - return -EINVAL; - } - - generic_phy = devm_phy_create(dev, dev->of_node, id->data); - if (IS_ERR(generic_phy)) { - dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(generic_phy); - } - - phy_set_drvdata(generic_phy, tbh_phy); - phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - - return PTR_ERR_OR_ZERO(phy_provider); -} - -static struct platform_driver thunderbay_emmc_phy_driver = { - .probe = thunderbay_emmc_phy_probe, - .driver = { - .name = "thunderbay-emmc-phy", - .of_match_table = thunderbay_emmc_phy_of_match, - }, -}; -module_platform_driver(thunderbay_emmc_phy_driver); - -MODULE_AUTHOR("Nandhini S "); -MODULE_AUTHOR("Rashmi A "); -MODULE_DESCRIPTION("Intel Thunder Bay eMMC PHY driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 64e480aaaee50513c91b5974c7a276ce2080db5e Mon Sep 17 00:00:00 2001 From: "A, Rashmi" Date: Thu, 16 Mar 2023 17:35:49 +0530 Subject: [PATCH 0906/5631] dt-bindings: phy: intel: Remove Thunder Bay eMMC PHY bindings Remove Thunder Bay specific code as the product got cancelled and there are no end customers or users. Signed-off-by: A, Rashmi Reviewed-by: Hunter, Adrian Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230316120549.21486-5-rashmi.a@intel.com Signed-off-by: Vinod Koul --- .../phy/intel,phy-thunderbay-emmc.yaml | 45 ------------------- MAINTAINERS | 7 --- 2 files changed, 52 deletions(-) delete mode 100644 Documentation/devicetree/bindings/phy/intel,phy-thunderbay-emmc.yaml diff --git a/Documentation/devicetree/bindings/phy/intel,phy-thunderbay-emmc.yaml b/Documentation/devicetree/bindings/phy/intel,phy-thunderbay-emmc.yaml deleted file mode 100644 index 361ffc35b16b..000000000000 --- a/Documentation/devicetree/bindings/phy/intel,phy-thunderbay-emmc.yaml +++ /dev/null @@ -1,45 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/phy/intel,phy-thunderbay-emmc.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: Intel Thunder Bay eMMC PHY - -maintainers: - - Srikandan Nandhini - -properties: - compatible: - const: intel,thunderbay-emmc-phy - - "#phy-cells": - const: 0 - - reg: - maxItems: 1 - - clocks: - maxItems: 1 - - clock-names: - items: - - const: emmcclk - -required: - - "#phy-cells" - - compatible - - reg - - clocks - -additionalProperties: false - -examples: - - | - mmc_phy@80440800 { - #phy-cells = <0x0>; - compatible = "intel,thunderbay-emmc-phy"; - reg = <0x80440800 0x100>; - clocks = <&emmc>; - clock-names = "emmcclk"; - }; diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..fce67b74e4a2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10442,13 +10442,6 @@ F: drivers/crypto/keembay/keembay-ocs-hcu-core.c F: drivers/crypto/keembay/ocs-hcu.c F: drivers/crypto/keembay/ocs-hcu.h -INTEL THUNDER BAY EMMC PHY DRIVER -M: Nandhini Srikandan -M: Rashmi A -S: Maintained -F: Documentation/devicetree/bindings/phy/intel,phy-thunderbay-emmc.yaml -F: drivers/phy/intel/phy-intel-thunderbay-emmc.c - INTEL MANAGEMENT ENGINE (mei) M: Tomas Winkler L: linux-kernel@vger.kernel.org -- GitLab From 0599331c3da6dbbe814262079f6b0c4f3575fd5d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:20 -0800 Subject: [PATCH 0907/5631] s390: simplify one-level sysctl registration for topology_ctl_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-2-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/topology.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index c6eecd4a5302..e5d6a1c25d13 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -637,16 +637,6 @@ static struct ctl_table topology_ctl_table[] = { { }, }; -static struct ctl_table topology_dir_table[] = { - { - .procname = "s390", - .maxlen = 0, - .mode = 0555, - .child = topology_ctl_table, - }, - { }, -}; - static int __init topology_init(void) { timer_setup(&topology_timer, topology_timer_fn, TIMER_DEFERRABLE); @@ -654,7 +644,7 @@ static int __init topology_init(void) set_topology_timer(); else topology_update_polarization_simple(); - register_sysctl_table(topology_dir_table); + register_sysctl("s390", topology_ctl_table); return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); -- GitLab From 751e24071c2e408f4b1781327756700ee4c941ab Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:21 -0800 Subject: [PATCH 0908/5631] s390: simplify one-level syctl registration for s390dbf_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-3-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/kernel/debug.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index b376f0377a2c..221c865785c2 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -981,16 +981,6 @@ static struct ctl_table s390dbf_table[] = { { } }; -static struct ctl_table s390dbf_dir_table[] = { - { - .procname = "s390dbf", - .maxlen = 0, - .mode = S_IRUGO | S_IXUGO, - .child = s390dbf_table, - }, - { } -}; - static struct ctl_table_header *s390dbf_sysctl_header; /** @@ -1574,7 +1564,7 @@ static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, */ static int __init debug_init(void) { - s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table); + s390dbf_sysctl_header = register_sysctl("s390dbf", s390dbf_table); mutex_lock(&debug_mutex); debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT, NULL); initialized = 1; -- GitLab From 71cb8c00a2eb74b6c61374366fef4fd402faa692 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:22 -0800 Subject: [PATCH 0909/5631] s390: simplify one-level sysctl registration for appldata_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-4-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/appldata/appldata_base.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index c0fd29133f27..c593f2228083 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -66,16 +66,6 @@ static struct ctl_table appldata_table[] = { { }, }; -static struct ctl_table appldata_dir_table[] = { - { - .procname = appldata_proc_name, - .maxlen = 0, - .mode = S_IRUGO | S_IXUGO, - .child = appldata_table, - }, - { }, -}; - /* * Timer */ @@ -422,7 +412,7 @@ static int __init appldata_init(void) appldata_wq = alloc_ordered_workqueue("appldata", 0); if (!appldata_wq) return -ENOMEM; - appldata_sysctl_header = register_sysctl_table(appldata_dir_table); + appldata_sysctl_header = register_sysctl(appldata_proc_name, appldata_table); return 0; } -- GitLab From 414b2a960e4373765987bdaeaafbccde6b6eb27b Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:23 -0800 Subject: [PATCH 0910/5631] s390: simplify one level sysctl registration for cmm_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-5-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/mm/cmm.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 9141ed4c52e9..5300c6867d5e 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -335,16 +335,6 @@ static struct ctl_table cmm_table[] = { { } }; -static struct ctl_table cmm_dir_table[] = { - { - .procname = "vm", - .maxlen = 0, - .mode = 0555, - .child = cmm_table, - }, - { } -}; - #ifdef CONFIG_CMM_IUCV #define SMSG_PREFIX "CMM" static void cmm_smsg_target(const char *from, char *msg) @@ -389,7 +379,7 @@ static int __init cmm_init(void) { int rc = -ENOMEM; - cmm_sysctl_header = register_sysctl_table(cmm_dir_table); + cmm_sysctl_header = register_sysctl("vm", cmm_table); if (!cmm_sysctl_header) goto out_sysctl; #ifdef CONFIG_CMM_IUCV -- GitLab From 7ddc873dcb1d05eaafceeb4a2afd53bbb31addb8 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:24 -0800 Subject: [PATCH 0911/5631] s390: simplify one-level sysctl registration for page_table_sysctl There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-6-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/mm/pgalloc.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 2de48b2c1b04..0f68b7257e08 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -33,19 +33,9 @@ static struct ctl_table page_table_sysctl[] = { { } }; -static struct ctl_table page_table_sysctl_dir[] = { - { - .procname = "vm", - .maxlen = 0, - .mode = 0555, - .child = page_table_sysctl, - }, - { } -}; - static int __init page_table_register_sysctl(void) { - return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM; + return register_sysctl("vm", page_table_sysctl) ? 0 : -ENOMEM; } __initcall(page_table_register_sysctl); -- GitLab From 7db12246306ea601809f22b26d7c2093dd80e146 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:45:25 -0800 Subject: [PATCH 0912/5631] s390: simplify dynamic sysctl registration for appldata_register_ops The routine appldata_register_ops() allocates a sysctl table with 4 entries. The firsts one, ops->ctl_table[0] is the parent directory with an empty entry following it, ops->ctl_table[1]. The next entry is for the ops->name and that is ops->ctl_table[2]. It needs an empty entry following that, and that is ops->ctl_table[3]. And so hence the kcalloc(4, sizeof(struct ctl_table), GFP_KERNEL). We can simplify this considerably since sysctl_register("foo", table) can create the parent directory for us if it does not exist. So we can just remove the first two entries and move back the ops->name to the first entry, and just use kcalloc(2, ...). [gor@linux.ibm.com: appldata_generic_handler fixup ctl_table index 2->0] Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230310234525.3986352-7-mcgrof@kernel.org Reviewed-by: Vasily Gorbik Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/appldata/appldata_base.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index c593f2228083..b07b0610950e 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -281,7 +281,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write, mutex_lock(&appldata_ops_mutex); list_for_each(lh, &appldata_ops_list) { tmp_ops = list_entry(lh, struct appldata_ops, list); - if (&tmp_ops->ctl_table[2] == ctl) { + if (&tmp_ops->ctl_table[0] == ctl) { found = 1; } } @@ -351,7 +351,8 @@ int appldata_register_ops(struct appldata_ops *ops) if (ops->size > APPLDATA_MAX_REC_SIZE) return -EINVAL; - ops->ctl_table = kcalloc(4, sizeof(struct ctl_table), GFP_KERNEL); + /* The last entry must be an empty one */ + ops->ctl_table = kcalloc(2, sizeof(struct ctl_table), GFP_KERNEL); if (!ops->ctl_table) return -ENOMEM; @@ -359,17 +360,12 @@ int appldata_register_ops(struct appldata_ops *ops) list_add(&ops->list, &appldata_ops_list); mutex_unlock(&appldata_ops_mutex); - ops->ctl_table[0].procname = appldata_proc_name; - ops->ctl_table[0].maxlen = 0; - ops->ctl_table[0].mode = S_IRUGO | S_IXUGO; - ops->ctl_table[0].child = &ops->ctl_table[2]; + ops->ctl_table[0].procname = ops->name; + ops->ctl_table[0].mode = S_IRUGO | S_IWUSR; + ops->ctl_table[0].proc_handler = appldata_generic_handler; + ops->ctl_table[0].data = ops; - ops->ctl_table[2].procname = ops->name; - ops->ctl_table[2].mode = S_IRUGO | S_IWUSR; - ops->ctl_table[2].proc_handler = appldata_generic_handler; - ops->ctl_table[2].data = ops; - - ops->sysctl_header = register_sysctl_table(ops->ctl_table); + ops->sysctl_header = register_sysctl(appldata_proc_name, ops->ctl_table); if (!ops->sysctl_header) goto out; return 0; -- GitLab From 7229ea86e0a0ed117bbc9d1677003c0bb0a5d40e Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Fri, 10 Mar 2023 03:36:48 +0100 Subject: [PATCH 0913/5631] s390/dumpstack: resolve userspace last_break report_user_fault() currently does not show which library last_break points to. Call print_vma_addr() to find out; the output now looks like this: Last Breaking-Event-Address: [<000003ffaa2a56e4>] libc.so.6[3ffaa180000+251000] For kernel it's unchanged: Last Breaking-Event-Address: [<000000000030fd06>] trace_hardirqs_on+0x56/0xc8 Signed-off-by: Ilya Leoshkevich Acked-by: Heiko Carstens Signed-off-by: Heiko Carstens --- arch/s390/kernel/dumpstack.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 1e3233eb510a..f257058d0828 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -152,7 +152,13 @@ void show_stack(struct task_struct *task, unsigned long *stack, static void show_last_breaking_event(struct pt_regs *regs) { printk("Last Breaking-Event-Address:\n"); - printk(" [<%016lx>] %pSR\n", regs->last_break, (void *)regs->last_break); + printk(" [<%016lx>] ", regs->last_break); + if (user_mode(regs)) { + print_vma_addr(KERN_CONT, regs->last_break); + pr_cont("\n"); + } else { + pr_cont("%pSR\n", (void *)regs->last_break); + } } void show_registers(struct pt_regs *regs) -- GitLab From 53fcc7dbf17691d8eac382ee315970a75286dd4b Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 15 Feb 2023 14:27:45 +0100 Subject: [PATCH 0914/5631] s390/boot: remove non-functioning image bootable check check_image_bootable() has been introduced with commit 627c9b62058e ("s390/boot: block uncompressed vmlinux booting attempts") to make sure that users don't try to boot uncompressed vmlinux ELF image in qemu. It used to be possible quite some time ago. That commit prevented confusion with uncompressed vmlinux image starting to boot and even printing kernel messages until it crashed. Users might have tried to report the problem without realizing they are doing something which was not intended. Since commit f1d3c5323772 ("s390/boot: move sclp early buffer from fixed address in asm to C") check_image_bootable() doesn't function properly anymore, as well as booting uncompressed vmlinux image in qemu doesn't really produce any output and crashes. Moving forward it doesn't make sense to fix check_image_bootable() anymore, so simply remove it. Acked-by: Alexander Gordeev Acked-by: Heiko Carstens Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/startup.c | 1 - arch/s390/include/asm/setup.h | 2 -- arch/s390/kernel/early.c | 14 -------------- 3 files changed, 17 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 11413f0baabc..16ee3469f744 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -29,7 +29,6 @@ unsigned long __bootdata_preserved(vmemmap_size); unsigned long __bootdata_preserved(MODULES_VADDR); unsigned long __bootdata_preserved(MODULES_END); unsigned long __bootdata(ident_map_size); -int __bootdata(is_full_image) = 1; struct initrd_data __bootdata(initrd_data); u64 __bootdata_preserved(stfle_fac_list[16]); diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index 3a1f8825bc7d..fc887e3e76f8 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -150,8 +150,6 @@ static inline unsigned long kaslr_offset(void) return __kaslr_offset; } -extern int is_full_image; - struct initrd_data { unsigned long start; unsigned long size; diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index d26f02495636..8225a4c1f2e2 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -34,8 +34,6 @@ #include #include "entry.h" -int __bootdata(is_full_image); - #define decompressor_handled_param(param) \ static int __init ignore_decompressor_param_##param(char *s) \ { \ @@ -288,17 +286,6 @@ static void __init setup_boot_command_line(void) strscpy(boot_command_line, early_command_line, COMMAND_LINE_SIZE); } -static void __init check_image_bootable(void) -{ - if (is_full_image) - return; - - sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n"); - sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n"); - sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n"); - disabled_wait(); -} - static void __init sort_amode31_extable(void) { sort_extable(__start_amode31_ex_table, __stop_amode31_ex_table); @@ -307,7 +294,6 @@ static void __init sort_amode31_extable(void) void __init startup_init(void) { reset_tod_clock(); - check_image_bootable(); time_early_init(); init_kernel_storage_key(); lockdep_off(); -- GitLab From 8c37cb7d4ffcc827a9484282691b018715a5ae1a Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 8 Feb 2023 18:11:25 +0100 Subject: [PATCH 0915/5631] s390/boot: rename mem_detect to physmem_info In preparation to extending mem_detect with additional information like reserved ranges rename it to more generic physmem_info. This new naming also help to avoid confusion by using more exact terms like "physmem online ranges", etc. Acked-by: Heiko Carstens Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/Makefile | 2 +- arch/s390/boot/boot.h | 2 +- arch/s390/boot/kaslr.c | 14 +-- .../boot/{mem_detect.c => physmem_info.c} | 76 +++++------ arch/s390/boot/startup.c | 6 +- arch/s390/boot/vmem.c | 6 +- arch/s390/include/asm/mem_detect.h | 117 ----------------- arch/s390/include/asm/physmem_info.h | 118 ++++++++++++++++++ arch/s390/kernel/setup.c | 28 ++--- arch/s390/mm/kasan_init.c | 6 +- drivers/s390/char/sclp_early_core.c | 8 +- 11 files changed, 192 insertions(+), 191 deletions(-) rename arch/s390/boot/{mem_detect.c => physmem_info.c} (63%) delete mode 100644 arch/s390/include/asm/mem_detect.h create mode 100644 arch/s390/include/asm/physmem_info.h diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index cebd4ca16916..c7c81e5f9218 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -35,7 +35,7 @@ endif CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char -obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o vmem.o +obj-y := head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o obj-y += version.o pgm_check_info.o ctype.o ipl_data.o machine_kexec_reloc.o obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 58ce701d6110..d39895d5796e 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -34,7 +34,7 @@ struct vmlinux_info { void startup_kernel(void); unsigned long detect_memory(unsigned long *safe_addr); -void mem_detect_set_usable_limit(unsigned long limit); +void physmem_set_usable_limit(unsigned long limit); bool is_ipl_block_dump(void); void store_ipl_parmblock(void); unsigned long read_ipl_report(unsigned long safe_addr); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 3e3d846400b4..22b7c5d8e94a 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -3,7 +3,7 @@ * Copyright IBM Corp. 2019 */ #include -#include +#include #include #include #include @@ -93,7 +93,7 @@ static int get_random(unsigned long limit, unsigned long *value) /* * To randomize kernel base address we have to consider several facts: - * 1. physical online memory might not be continuous and have holes. mem_detect + * 1. physical online memory might not be continuous and have holes. physmem * info contains list of online memory ranges we should consider. * 2. we have several memory regions which are occupied and we should not * overlap and destroy them. Currently safe_addr tells us the border below @@ -108,7 +108,7 @@ static int get_random(unsigned long limit, unsigned long *value) * (16 pages when the kernel is built with kasan enabled) * Assumptions: * 1. kernel size (including .bss size) and upper memory limit are page aligned. - * 2. mem_detect memory region start is THREAD_SIZE aligned / end is PAGE_SIZE + * 2. physmem online region start is THREAD_SIZE aligned / end is PAGE_SIZE * aligned (in practice memory configurations granularity on z/VM and LPAR * is 1mb). * @@ -132,7 +132,7 @@ static unsigned long count_valid_kernel_positions(unsigned long kernel_size, unsigned long start, end, pos = 0; int i; - for_each_mem_detect_usable_block(i, &start, &end) { + for_each_physmem_usable_range(i, &start, &end) { if (_min >= end) continue; if (start >= _max) @@ -153,7 +153,7 @@ static unsigned long position_to_address(unsigned long pos, unsigned long kernel unsigned long start, end; int i; - for_each_mem_detect_usable_block(i, &start, &end) { + for_each_physmem_usable_range(i, &start, &end) { if (_min >= end) continue; if (start >= _max) @@ -172,8 +172,8 @@ static unsigned long position_to_address(unsigned long pos, unsigned long kernel unsigned long get_random_base(unsigned long safe_addr) { - unsigned long usable_total = get_mem_detect_usable_total(); - unsigned long memory_limit = get_mem_detect_end(); + unsigned long usable_total = get_physmem_usable_total(); + unsigned long memory_limit = get_physmem_usable_end(); unsigned long base_pos, max_pos, kernel_size; int i; diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/physmem_info.c similarity index 63% rename from arch/s390/boot/mem_detect.c rename to arch/s390/boot/physmem_info.c index 35f4ba11f7fd..dc2e4d0abfab 100644 --- a/arch/s390/boot/mem_detect.c +++ b/arch/s390/boot/physmem_info.c @@ -5,44 +5,44 @@ #include #include #include -#include +#include #include #include "decompressor.h" #include "boot.h" -struct mem_detect_info __bootdata(mem_detect); +struct physmem_info __bootdata(physmem_info); /* up to 256 storage elements, 1020 subincrements each */ #define ENTRIES_EXTENDED_MAX \ - (256 * (1020 / 2) * sizeof(struct mem_detect_block)) + (256 * (1020 / 2) * sizeof(struct physmem_range)) -static struct mem_detect_block *__get_mem_detect_block_ptr(u32 n) +static struct physmem_range *__get_physmem_range_ptr(u32 n) { if (n < MEM_INLINED_ENTRIES) - return &mem_detect.entries[n]; - return &mem_detect.entries_extended[n - MEM_INLINED_ENTRIES]; + return &physmem_info.online[n]; + return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES]; } /* - * sequential calls to add_mem_detect_block with adjacent memory areas - * are merged together into single memory block. + * sequential calls to add_physmem_online_range with adjacent memory ranges + * are merged together into single memory range. */ -void add_mem_detect_block(u64 start, u64 end) +void add_physmem_online_range(u64 start, u64 end) { - struct mem_detect_block *block; + struct physmem_range *range; - if (mem_detect.count) { - block = __get_mem_detect_block_ptr(mem_detect.count - 1); - if (block->end == start) { - block->end = end; + if (physmem_info.range_count) { + range = __get_physmem_range_ptr(physmem_info.range_count - 1); + if (range->end == start) { + range->end = end; return; } } - block = __get_mem_detect_block_ptr(mem_detect.count); - block->start = start; - block->end = end; - mem_detect.count++; + range = __get_physmem_range_ptr(physmem_info.range_count); + range->start = start; + range->end = end; + physmem_info.range_count++; } static int __diag260(unsigned long rx1, unsigned long rx2) @@ -95,7 +95,7 @@ static int diag260(void) return -1; for (i = 0; i < min_t(int, rc, ARRAY_SIZE(storage_extents)); i++) - add_mem_detect_block(storage_extents[i].start, storage_extents[i].end + 1); + add_physmem_online_range(storage_extents[i].start, storage_extents[i].end + 1); return 0; } @@ -148,44 +148,44 @@ unsigned long detect_memory(unsigned long *safe_addr) unsigned long max_physmem_end = 0; sclp_early_get_memsize(&max_physmem_end); - mem_detect.entries_extended = (struct mem_detect_block *)ALIGN(*safe_addr, sizeof(u64)); + physmem_info.online_extended = (struct physmem_range *)ALIGN(*safe_addr, sizeof(u64)); if (!sclp_early_read_storage_info()) { - mem_detect.info_source = MEM_DETECT_SCLP_STOR_INFO; + physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO; } else if (!diag260()) { - mem_detect.info_source = MEM_DETECT_DIAG260; - max_physmem_end = max_physmem_end ?: get_mem_detect_end(); + physmem_info.info_source = MEM_DETECT_DIAG260; + max_physmem_end = max_physmem_end ?: get_physmem_usable_end(); } else if (max_physmem_end) { - add_mem_detect_block(0, max_physmem_end); - mem_detect.info_source = MEM_DETECT_SCLP_READ_INFO; + add_physmem_online_range(0, max_physmem_end); + physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO; } else { max_physmem_end = search_mem_end(); - add_mem_detect_block(0, max_physmem_end); - mem_detect.info_source = MEM_DETECT_BIN_SEARCH; + add_physmem_online_range(0, max_physmem_end); + physmem_info.info_source = MEM_DETECT_BIN_SEARCH; } - if (mem_detect.count > MEM_INLINED_ENTRIES) { - *safe_addr += (mem_detect.count - MEM_INLINED_ENTRIES) * - sizeof(struct mem_detect_block); + if (physmem_info.range_count > MEM_INLINED_ENTRIES) { + *safe_addr += (physmem_info.range_count - MEM_INLINED_ENTRIES) * + sizeof(struct physmem_range); } return max_physmem_end; } -void mem_detect_set_usable_limit(unsigned long limit) +void physmem_set_usable_limit(unsigned long limit) { - struct mem_detect_block *block; + struct physmem_range *range; int i; /* make sure mem_detect.usable ends up within online memory block */ - for (i = 0; i < mem_detect.count; i++) { - block = __get_mem_detect_block_ptr(i); - if (block->start >= limit) + for (i = 0; i < physmem_info.range_count; i++) { + range = __get_physmem_range_ptr(i); + if (range->start >= limit) break; - if (block->end >= limit) { - mem_detect.usable = limit; + if (range->end >= limit) { + physmem_info.usable = limit; break; } - mem_detect.usable = block->end; + physmem_info.usable = range->end; } } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 16ee3469f744..50475bf25ecd 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include "decompressor.h" #include "boot.h" #include "uv.h" @@ -139,7 +139,7 @@ static void handle_relocs(unsigned long offset) * * Consider the following factors: * 1. max_physmem_end - end of physical memory online or standby. - * Always <= end of the last online memory block (get_mem_detect_end()). + * Always >= end of the last online memory range (get_physmem_online_end()). * 2. CONFIG_MAX_PHYSMEM_BITS - the maximum size of physical memory the * kernel is able to support. * 3. "mem=" kernel command line option which limits physical memory usage. @@ -303,7 +303,7 @@ void startup_kernel(void) setup_ident_map_size(max_physmem_end); setup_vmalloc_size(); asce_limit = setup_kernel_memory_layout(); - mem_detect_set_usable_limit(ident_map_size); + physmem_set_usable_limit(ident_map_size); if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) { random_lma = get_random_base(safe_addr); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 4d1d0d8e99cb..b89a6893f398 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include "decompressor.h" @@ -51,7 +51,7 @@ static void pgtable_populate_init(void) pgalloc_low = max(pgalloc_low, initrd_end); } - pgalloc_end = round_down(get_mem_detect_end(), PAGE_SIZE); + pgalloc_end = round_down(get_physmem_usable_end(), PAGE_SIZE); pgalloc_pos = pgalloc_end; boot_check_oom(); @@ -252,7 +252,7 @@ void setup_vmem(unsigned long asce_limit) */ pgtable_populate_init(); pgtable_populate(0, sizeof(struct lowcore), POPULATE_ONE2ONE); - for_each_mem_detect_usable_block(i, &start, &end) + for_each_physmem_usable_range(i, &start, &end) pgtable_populate(start, end, POPULATE_ONE2ONE); pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore), POPULATE_ABS_LOWCORE); diff --git a/arch/s390/include/asm/mem_detect.h b/arch/s390/include/asm/mem_detect.h deleted file mode 100644 index f9e7354036d2..000000000000 --- a/arch/s390/include/asm/mem_detect.h +++ /dev/null @@ -1,117 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_S390_MEM_DETECT_H -#define _ASM_S390_MEM_DETECT_H - -#include - -enum mem_info_source { - MEM_DETECT_NONE = 0, - MEM_DETECT_SCLP_STOR_INFO, - MEM_DETECT_DIAG260, - MEM_DETECT_SCLP_READ_INFO, - MEM_DETECT_BIN_SEARCH -}; - -struct mem_detect_block { - u64 start; - u64 end; -}; - -/* - * Storage element id is defined as 1 byte (up to 256 storage elements). - * In practise only storage element id 0 and 1 are used). - * According to architecture one storage element could have as much as - * 1020 subincrements. 255 mem_detect_blocks are embedded in mem_detect_info. - * If more mem_detect_blocks are required, a block of memory from already - * known mem_detect_block is taken (entries_extended points to it). - */ -#define MEM_INLINED_ENTRIES 255 /* (PAGE_SIZE - 16) / 16 */ - -struct mem_detect_info { - u32 count; - u8 info_source; - unsigned long usable; - struct mem_detect_block entries[MEM_INLINED_ENTRIES]; - struct mem_detect_block *entries_extended; -}; -extern struct mem_detect_info mem_detect; - -void add_mem_detect_block(u64 start, u64 end); - -static inline int __get_mem_detect_block(u32 n, unsigned long *start, - unsigned long *end, bool respect_usable_limit) -{ - if (n >= mem_detect.count) { - *start = 0; - *end = 0; - return -1; - } - - if (n < MEM_INLINED_ENTRIES) { - *start = (unsigned long)mem_detect.entries[n].start; - *end = (unsigned long)mem_detect.entries[n].end; - } else { - *start = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].start; - *end = (unsigned long)mem_detect.entries_extended[n - MEM_INLINED_ENTRIES].end; - } - - if (respect_usable_limit && mem_detect.usable) { - if (*start >= mem_detect.usable) - return -1; - if (*end > mem_detect.usable) - *end = mem_detect.usable; - } - return 0; -} - -/** - * for_each_mem_detect_usable_block - early online memory range iterator - * @i: an integer used as loop variable - * @p_start: ptr to unsigned long for start address of the range - * @p_end: ptr to unsigned long for end address of the range - * - * Walks over detected online memory ranges below usable limit. - */ -#define for_each_mem_detect_usable_block(i, p_start, p_end) \ - for (i = 0; !__get_mem_detect_block(i, p_start, p_end, true); i++) - -/* Walks over all detected online memory ranges disregarding usable limit. */ -#define for_each_mem_detect_block(i, p_start, p_end) \ - for (i = 0; !__get_mem_detect_block(i, p_start, p_end, false); i++) - -static inline unsigned long get_mem_detect_usable_total(void) -{ - unsigned long start, end, total = 0; - int i; - - for_each_mem_detect_usable_block(i, &start, &end) - total += end - start; - - return total; -} - -static inline void get_mem_detect_reserved(unsigned long *start, - unsigned long *size) -{ - *start = (unsigned long)mem_detect.entries_extended; - if (mem_detect.count > MEM_INLINED_ENTRIES) - *size = (mem_detect.count - MEM_INLINED_ENTRIES) * sizeof(struct mem_detect_block); - else - *size = 0; -} - -static inline unsigned long get_mem_detect_end(void) -{ - unsigned long start; - unsigned long end; - - if (mem_detect.usable) - return mem_detect.usable; - if (mem_detect.count) { - __get_mem_detect_block(mem_detect.count - 1, &start, &end, false); - return end; - } - return 0; -} - -#endif diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h new file mode 100644 index 000000000000..d5e65a5d06e7 --- /dev/null +++ b/arch/s390/include/asm/physmem_info.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_MEM_DETECT_H +#define _ASM_S390_MEM_DETECT_H + +#include + +enum physmem_info_source { + MEM_DETECT_NONE = 0, + MEM_DETECT_SCLP_STOR_INFO, + MEM_DETECT_DIAG260, + MEM_DETECT_SCLP_READ_INFO, + MEM_DETECT_BIN_SEARCH +}; + +struct physmem_range { + u64 start; + u64 end; +}; + +/* + * Storage element id is defined as 1 byte (up to 256 storage elements). + * In practise only storage element id 0 and 1 are used). + * According to architecture one storage element could have as much as + * 1020 subincrements. 255 physmem_ranges are embedded in physmem_info. + * If more physmem_ranges are required, a block of memory from already + * known physmem_range is taken (online_extended points to it). + */ +#define MEM_INLINED_ENTRIES 255 /* (PAGE_SIZE - 16) / 16 */ + +struct physmem_info { + u32 range_count; + u8 info_source; + unsigned long usable; + struct physmem_range online[MEM_INLINED_ENTRIES]; + struct physmem_range *online_extended; +}; + +extern struct physmem_info physmem_info; + +void add_physmem_online_range(u64 start, u64 end); + +static inline int __get_physmem_range(u32 n, unsigned long *start, + unsigned long *end, bool respect_usable_limit) +{ + if (n >= physmem_info.range_count) { + *start = 0; + *end = 0; + return -1; + } + + if (n < MEM_INLINED_ENTRIES) { + *start = (unsigned long)physmem_info.online[n].start; + *end = (unsigned long)physmem_info.online[n].end; + } else { + *start = (unsigned long)physmem_info.online_extended[n - MEM_INLINED_ENTRIES].start; + *end = (unsigned long)physmem_info.online_extended[n - MEM_INLINED_ENTRIES].end; + } + + if (respect_usable_limit && physmem_info.usable) { + if (*start >= physmem_info.usable) + return -1; + if (*end > physmem_info.usable) + *end = physmem_info.usable; + } + return 0; +} + +/** + * for_each_physmem_usable_range - early online memory range iterator + * @i: an integer used as loop variable + * @p_start: ptr to unsigned long for start address of the range + * @p_end: ptr to unsigned long for end address of the range + * + * Walks over detected online memory ranges below usable limit. + */ +#define for_each_physmem_usable_range(i, p_start, p_end) \ + for (i = 0; !__get_physmem_range(i, p_start, p_end, true); i++) + +/* Walks over all detected online memory ranges disregarding usable limit. */ +#define for_each_physmem_online_range(i, p_start, p_end) \ + for (i = 0; !__get_physmem_range(i, p_start, p_end, false); i++) + +static inline unsigned long get_physmem_usable_total(void) +{ + unsigned long start, end, total = 0; + int i; + + for_each_physmem_usable_range(i, &start, &end) + total += end - start; + + return total; +} + +static inline void get_physmem_reserved(unsigned long *start, unsigned long *size) +{ + *start = (unsigned long)physmem_info.online_extended; + if (physmem_info.range_count > MEM_INLINED_ENTRIES) + *size = (physmem_info.range_count - MEM_INLINED_ENTRIES) * + sizeof(struct physmem_range); + else + *size = 0; +} + +static inline unsigned long get_physmem_usable_end(void) +{ + unsigned long start; + unsigned long end; + + if (physmem_info.usable) + return physmem_info.usable; + if (physmem_info.range_count) { + __get_physmem_range(physmem_info.range_count - 1, &start, &end, false); + return end; + } + return 0; +} + +#endif diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 8ec5cdf9dadc..f909a2dc8a5a 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -74,7 +74,7 @@ #include #include #include -#include +#include #include #include #include @@ -147,7 +147,7 @@ static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31; int __bootdata(noexec_disabled); unsigned long __bootdata(ident_map_size); -struct mem_detect_info __bootdata(mem_detect); +struct physmem_info __bootdata(physmem_info); struct initrd_data __bootdata(initrd_data); unsigned long __bootdata(pgalloc_pos); unsigned long __bootdata(pgalloc_end); @@ -730,27 +730,27 @@ static void __init reserve_certificate_list(void) memblock_reserve(ipl_cert_list_addr, ipl_cert_list_size); } -static void __init reserve_mem_detect_info(void) +static void __init reserve_physmem_info(void) { unsigned long start, size; - get_mem_detect_reserved(&start, &size); + get_physmem_reserved(&start, &size); if (size) memblock_reserve(start, size); } -static void __init free_mem_detect_info(void) +static void __init free_physmem_info(void) { unsigned long start, size; - get_mem_detect_reserved(&start, &size); + get_physmem_reserved(&start, &size); if (size) memblock_phys_free(start, size); } static const char * __init get_mem_info_source(void) { - switch (mem_detect.info_source) { + switch (physmem_info.info_source) { case MEM_DETECT_SCLP_STOR_INFO: return "sclp storage info"; case MEM_DETECT_DIAG260: @@ -763,18 +763,18 @@ static const char * __init get_mem_info_source(void) return "none"; } -static void __init memblock_add_mem_detect_info(void) +static void __init memblock_add_physmem_info(void) { unsigned long start, end; int i; pr_debug("physmem info source: %s (%hhd)\n", - get_mem_info_source(), mem_detect.info_source); + get_mem_info_source(), physmem_info.info_source); /* keep memblock lists close to the kernel */ memblock_set_bottom_up(true); - for_each_mem_detect_usable_block(i, &start, &end) + for_each_physmem_usable_range(i, &start, &end) memblock_add(start, end - start); - for_each_mem_detect_block(i, &start, &end) + for_each_physmem_online_range(i, &start, &end) memblock_physmem_add(start, end - start); memblock_set_bottom_up(false); memblock_set_node(0, ULONG_MAX, &memblock.memory, 0); @@ -997,14 +997,14 @@ void __init setup_arch(char **cmdline_p) reserve_kernel(); reserve_initrd(); reserve_certificate_list(); - reserve_mem_detect_info(); + reserve_physmem_info(); memblock_set_current_limit(ident_map_size); memblock_allow_resize(); /* Get information about *all* installed memory */ - memblock_add_mem_detect_info(); + memblock_add_physmem_info(); - free_mem_detect_info(); + free_physmem_info(); setup_memory_end(); memblock_dump_all(); setup_memory(); diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index ef89a5f26853..b0658136264f 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include @@ -244,7 +244,7 @@ void __init kasan_early_init(void) memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE); if (has_edat) { - shadow_alloc_size = get_mem_detect_usable_total() >> KASAN_SHADOW_SCALE_SHIFT; + shadow_alloc_size = get_physmem_usable_total() >> KASAN_SHADOW_SCALE_SHIFT; segment_pos = round_down(pgalloc_pos, _SEGMENT_SIZE); segment_low = segment_pos - shadow_alloc_size; segment_low = round_down(segment_low, _SEGMENT_SIZE); @@ -282,7 +282,7 @@ void __init kasan_early_init(void) * +- shadow end ----+---------+- shadow end ---+ */ /* populate kasan shadow (for identity mapping and zero page mapping) */ - for_each_mem_detect_usable_block(i, &start, &end) + for_each_physmem_usable_range(i, &start, &end) kasan_early_pgtable_populate(__sha(start), __sha(end), POPULATE_MAP); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { untracked_end = VMALLOC_START; diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c index ac1d00980fa6..dbd5c53d8edf 100644 --- a/drivers/s390/char/sclp_early_core.c +++ b/drivers/s390/char/sclp_early_core.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include "sclp.h" #include "sclp_rw.h" @@ -336,7 +336,7 @@ int __init sclp_early_get_hsa_size(unsigned long *hsa_size) #define SCLP_STORAGE_INFO_FACILITY 0x0000400000000000UL -void __weak __init add_mem_detect_block(u64 start, u64 end) {} +void __weak __init add_physmem_online_range(u64 start, u64 end) {} int __init sclp_early_read_storage_info(void) { struct read_storage_sccb *sccb = (struct read_storage_sccb *)sclp_early_sccb; @@ -369,7 +369,7 @@ int __init sclp_early_read_storage_info(void) if (!sccb->entries[sn]) continue; rn = sccb->entries[sn] >> 16; - add_mem_detect_block((rn - 1) * rzm, rn * rzm); + add_physmem_online_range((rn - 1) * rzm, rn * rzm); } break; case 0x0310: @@ -382,6 +382,6 @@ int __init sclp_early_read_storage_info(void) return 0; fail: - mem_detect.count = 0; + physmem_info.range_count = 0; return -EIO; } -- GitLab From f913a6600491d3f478ea976a9be0fb1001476c10 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 2 Feb 2023 13:59:36 +0100 Subject: [PATCH 0916/5631] s390/boot: rework decompressor reserved tracking Currently several approaches for finding unused memory in decompressor are utilized. While "safe_addr" grows towards higher addresses, vmem code allocates paging structures top down. The former requires careful ordering. In addition to that ipl report handling code verifies potential intersections with secure boot certificates on its own. Neither of two approaches are memory holes aware and consistent with each other in low memory conditions. To solve that, existing approaches are generalized and combined together, as well as online memory ranges are now taken into consideration. physmem_info has been extended to contain reserved memory ranges. New set of functions allow to handle reserves and find unused memory. All reserves and memory allocations are "typed". In case of out of memory condition decompressor fails with detailed info on current reserved ranges and usable online memory. Linux version 6.2.0 ... Kernel command line: ... mem=100M Our of memory allocating 100000 bytes 100000 aligned in range 0:5800000 Reserved memory ranges: 0000000000000000 0000000003e33000 DECOMPRESSOR 0000000003f00000 00000000057648a3 INITRD 00000000063e0000 00000000063e8000 VMEM 00000000063eb000 00000000063f4000 VMEM 00000000063f7800 0000000006400000 VMEM 0000000005800000 0000000006300000 KASAN Usable online memory ranges (info source: sclp read info [3]): 0000000000000000 0000000006400000 Usable online memory total: 6400000 Reserved: 61b10a3 Free: 24ef5d Call Trace: (sp:000000000002bd58 [<0000000000012a70>] physmem_alloc_top_down+0x60/0x14c) sp:000000000002bdc8 [<0000000000013756>] _pa+0x56/0x6a sp:000000000002bdf0 [<0000000000013bcc>] pgtable_populate+0x45c/0x65e sp:000000000002be90 [<00000000000140aa>] setup_vmem+0x2da/0x424 sp:000000000002bec8 [<0000000000011c20>] startup_kernel+0x428/0x8b4 sp:000000000002bf60 [<00000000000100f4>] startup_normal+0xd4/0xd4 physmem_alloc_range allows to find free memory in specified range. It should be used for one time allocations only like finding position for amode31 and vmlinux. physmem_alloc_top_down can be used just like physmem_alloc_range, but it also allows multiple allocations per type and tries to merge sequential allocations together. Which is useful for paging structures allocations. If sequential allocations cannot be merged together they are "chained", allowing easy per type reserved ranges enumeration and migration to memblock later. Extra "struct reserved_range" allocated for chaining are not tracked or reserved but rely on the fact that both physmem_alloc_range and physmem_alloc_top_down search for free memory only below current top down allocator position. All reserved ranges should be transferred to memblock before memblock allocations are enabled. The startup code has been reordered to delay any memory allocations until online memory ranges are detected and occupied memory ranges are marked as reserved to be excluded from follow-up allocations. Ipl report certificates are a special case, ipl report certificates list is checked together with other memory reserves until certificates are saved elsewhere. KASAN required memory for shadow memory allocation and mapping is reserved as 1 large chunk which is later passed to KASAN early initialization code. Acked-by: Heiko Carstens Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/boot.h | 30 ++++- arch/s390/boot/ipl_report.c | 106 +++++++-------- arch/s390/boot/kaslr.c | 113 ++-------------- arch/s390/boot/pgm_check_info.c | 5 +- arch/s390/boot/physmem_info.c | 188 +++++++++++++++++++++++---- arch/s390/boot/startup.c | 86 ++++++------ arch/s390/boot/vmem.c | 69 +--------- arch/s390/boot/vmlinux.lds.S | 2 + arch/s390/include/asm/physmem_info.h | 112 +++++++++++++--- arch/s390/include/asm/setup.h | 9 -- arch/s390/kernel/setup.c | 76 +++-------- arch/s390/mm/kasan_init.c | 39 +++--- 12 files changed, 430 insertions(+), 405 deletions(-) diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index d39895d5796e..2b4048106418 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -8,6 +8,8 @@ #ifndef __ASSEMBLY__ +#include + struct machine_info { unsigned char has_edat1 : 1; unsigned char has_edat2 : 1; @@ -33,21 +35,34 @@ struct vmlinux_info { }; void startup_kernel(void); -unsigned long detect_memory(unsigned long *safe_addr); +unsigned long detect_max_physmem_end(void); +void detect_physmem_online_ranges(unsigned long max_physmem_end); void physmem_set_usable_limit(unsigned long limit); +void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size); +void physmem_free(enum reserved_range_type type); +/* for continuous/multiple allocations per type */ +unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, + unsigned long align); +/* for single allocations, 1 per type */ +unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size, + unsigned long align, unsigned long min, unsigned long max, + bool die_on_oom); +bool ipl_report_certs_intersects(unsigned long addr, unsigned long size, + unsigned long *intersection_start); bool is_ipl_block_dump(void); void store_ipl_parmblock(void); -unsigned long read_ipl_report(unsigned long safe_addr); +int read_ipl_report(void); +void save_ipl_cert_comp_list(void); void setup_boot_command_line(void); void parse_boot_command_line(void); void verify_facilities(void); void print_missing_facilities(void); void sclp_early_setup_buffer(void); void print_pgm_check_info(void); -unsigned long get_random_base(unsigned long safe_addr); +unsigned long get_random_base(void); void setup_vmem(unsigned long asce_limit); -unsigned long vmem_estimate_memory_needs(unsigned long online_mem_total); void __printf(1, 2) decompressor_printk(const char *fmt, ...); +void print_stacktrace(unsigned long sp); void error(char *m); extern struct machine_info machine; @@ -62,7 +77,7 @@ extern char __boot_data_start[], __boot_data_end[]; extern char __boot_data_preserved_start[], __boot_data_preserved_end[]; extern char _decompressor_syms_start[], _decompressor_syms_end[]; extern char _stack_start[], _stack_end[]; -extern char _end[]; +extern char _end[], _decompressor_end[]; extern unsigned char _compressed_start[]; extern unsigned char _compressed_end[]; extern struct vmlinux_info _vmlinux_info; @@ -70,5 +85,10 @@ extern struct vmlinux_info _vmlinux_info; #define __abs_lowcore_pa(x) (((unsigned long)(x) - __abs_lowcore) % sizeof(struct lowcore)) +static inline bool intersects(unsigned long addr0, unsigned long size0, + unsigned long addr1, unsigned long size1) +{ + return addr0 + size0 > addr1 && addr1 + size1 > addr0; +} #endif /* __ASSEMBLY__ */ #endif /* BOOT_BOOT_H */ diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c index 74b5cd264862..1803035e68d2 100644 --- a/arch/s390/boot/ipl_report.c +++ b/arch/s390/boot/ipl_report.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include "boot.h" @@ -16,20 +17,16 @@ unsigned long __bootdata_preserved(ipl_cert_list_size); unsigned long __bootdata(early_ipl_comp_list_addr); unsigned long __bootdata(early_ipl_comp_list_size); +static struct ipl_rb_certificates *certs; +static struct ipl_rb_components *comps; +static bool ipl_report_needs_saving; + #define for_each_rb_entry(entry, rb) \ for (entry = rb->entries; \ (void *) entry + sizeof(*entry) <= (void *) rb + rb->len; \ entry++) -static inline bool intersects(unsigned long addr0, unsigned long size0, - unsigned long addr1, unsigned long size1) -{ - return addr0 + size0 > addr1 && addr1 + size1 > addr0; -} - -static unsigned long find_bootdata_space(struct ipl_rb_components *comps, - struct ipl_rb_certificates *certs, - unsigned long safe_addr) +static unsigned long get_cert_comp_list_size(void) { struct ipl_rb_certificate_entry *cert; struct ipl_rb_component_entry *comp; @@ -44,44 +41,27 @@ static unsigned long find_bootdata_space(struct ipl_rb_components *comps, ipl_cert_list_size = 0; for_each_rb_entry(cert, certs) ipl_cert_list_size += sizeof(unsigned int) + cert->len; - size = ipl_cert_list_size + early_ipl_comp_list_size; + return ipl_cert_list_size + early_ipl_comp_list_size; +} - /* - * Start from safe_addr to find a free memory area large - * enough for the IPL report boot data. This area is used - * for ipl_cert_list_addr/ipl_cert_list_size and - * early_ipl_comp_list_addr/early_ipl_comp_list_size. It must - * not overlap with any component or any certificate. - */ -repeat: - if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_data.start && initrd_data.size && - intersects(initrd_data.start, initrd_data.size, safe_addr, size)) - safe_addr = initrd_data.start + initrd_data.size; - if (intersects(safe_addr, size, (unsigned long)comps, comps->len)) { - safe_addr = (unsigned long)comps + comps->len; - goto repeat; - } - for_each_rb_entry(comp, comps) - if (intersects(safe_addr, size, comp->addr, comp->len)) { - safe_addr = comp->addr + comp->len; - goto repeat; +bool ipl_report_certs_intersects(unsigned long addr, unsigned long size, + unsigned long *intersection_start) +{ + struct ipl_rb_certificate_entry *cert; + + if (!ipl_report_needs_saving) + return false; + + for_each_rb_entry(cert, certs) { + if (intersects(addr, size, cert->addr, cert->len)) { + *intersection_start = cert->addr; + return true; } - if (intersects(safe_addr, size, (unsigned long)certs, certs->len)) { - safe_addr = (unsigned long)certs + certs->len; - goto repeat; } - for_each_rb_entry(cert, certs) - if (intersects(safe_addr, size, cert->addr, cert->len)) { - safe_addr = cert->addr + cert->len; - goto repeat; - } - early_ipl_comp_list_addr = safe_addr; - ipl_cert_list_addr = safe_addr + early_ipl_comp_list_size; - - return safe_addr + size; + return false; } -static void copy_components_bootdata(struct ipl_rb_components *comps) +static void copy_components_bootdata(void) { struct ipl_rb_component_entry *comp, *ptr; @@ -90,7 +70,7 @@ static void copy_components_bootdata(struct ipl_rb_components *comps) memcpy(ptr++, comp, sizeof(*ptr)); } -static void copy_certificates_bootdata(struct ipl_rb_certificates *certs) +static void copy_certificates_bootdata(void) { struct ipl_rb_certificate_entry *cert; void *ptr; @@ -104,10 +84,8 @@ static void copy_certificates_bootdata(struct ipl_rb_certificates *certs) } } -unsigned long read_ipl_report(unsigned long safe_addr) +int read_ipl_report(void) { - struct ipl_rb_certificates *certs; - struct ipl_rb_components *comps; struct ipl_pl_hdr *pl_hdr; struct ipl_rl_hdr *rl_hdr; struct ipl_rb_hdr *rb_hdr; @@ -120,7 +98,7 @@ unsigned long read_ipl_report(unsigned long safe_addr) */ if (!ipl_block_valid || !(ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)) - return safe_addr; + return -1; ipl_secure_flag = !!(ipl_block.hdr.flags & IPL_PL_FLAG_SIPL); /* * There is an IPL report, to find it load the pointer to the @@ -158,16 +136,30 @@ unsigned long read_ipl_report(unsigned long safe_addr) * With either the component list or the certificate list * missing the kernel will stay ignorant of secure IPL. */ - if (!comps || !certs) - return safe_addr; + if (!comps || !certs) { + certs = NULL; + return -1; + } - /* - * Copy component and certificate list to a safe area - * where the decompressed kernel can find them. - */ - safe_addr = find_bootdata_space(comps, certs, safe_addr); - copy_components_bootdata(comps); - copy_certificates_bootdata(certs); + ipl_report_needs_saving = true; + physmem_reserve(RR_IPLREPORT, (unsigned long)pl_hdr, + (unsigned long)rl_end - (unsigned long)pl_hdr); + return 0; +} + +void save_ipl_cert_comp_list(void) +{ + unsigned long size; + + if (!ipl_report_needs_saving) + return; + + size = get_cert_comp_list_size(); + early_ipl_comp_list_addr = physmem_alloc_top_down(RR_CERT_COMP_LIST, size, sizeof(int)); + ipl_cert_list_addr = early_ipl_comp_list_addr + early_ipl_comp_list_size; - return safe_addr; + copy_components_bootdata(); + copy_certificates_bootdata(); + physmem_free(RR_IPLREPORT); + ipl_report_needs_saving = false; } diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 22b7c5d8e94a..71f75f03f800 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -91,113 +91,16 @@ static int get_random(unsigned long limit, unsigned long *value) return 0; } -/* - * To randomize kernel base address we have to consider several facts: - * 1. physical online memory might not be continuous and have holes. physmem - * info contains list of online memory ranges we should consider. - * 2. we have several memory regions which are occupied and we should not - * overlap and destroy them. Currently safe_addr tells us the border below - * which all those occupied regions are. We are safe to use anything above - * safe_addr. - * 3. the upper limit might apply as well, even if memory above that limit is - * online. Currently those limitations are: - * 3.1. Limit set by "mem=" kernel command line option - * 3.2. memory reserved at the end for kasan initialization. - * 4. kernel base address must be aligned to THREAD_SIZE (kernel stack size). - * Which is required for CONFIG_CHECK_STACK. Currently THREAD_SIZE is 4 pages - * (16 pages when the kernel is built with kasan enabled) - * Assumptions: - * 1. kernel size (including .bss size) and upper memory limit are page aligned. - * 2. physmem online region start is THREAD_SIZE aligned / end is PAGE_SIZE - * aligned (in practice memory configurations granularity on z/VM and LPAR - * is 1mb). - * - * To guarantee uniform distribution of kernel base address among all suitable - * addresses we generate random value just once. For that we need to build a - * continuous range in which every value would be suitable. We can build this - * range by simply counting all suitable addresses (let's call them positions) - * which would be valid as kernel base address. To count positions we iterate - * over online memory ranges. For each range which is big enough for the - * kernel image we count all suitable addresses we can put the kernel image at - * that is - * (end - start - kernel_size) / THREAD_SIZE + 1 - * Two functions count_valid_kernel_positions and position_to_address help - * to count positions in memory range given and then convert position back - * to address. - */ -static unsigned long count_valid_kernel_positions(unsigned long kernel_size, - unsigned long _min, - unsigned long _max) -{ - unsigned long start, end, pos = 0; - int i; - - for_each_physmem_usable_range(i, &start, &end) { - if (_min >= end) - continue; - if (start >= _max) - break; - start = max(_min, start); - end = min(_max, end); - if (end - start < kernel_size) - continue; - pos += (end - start - kernel_size) / THREAD_SIZE + 1; - } - - return pos; -} - -static unsigned long position_to_address(unsigned long pos, unsigned long kernel_size, - unsigned long _min, unsigned long _max) -{ - unsigned long start, end; - int i; - - for_each_physmem_usable_range(i, &start, &end) { - if (_min >= end) - continue; - if (start >= _max) - break; - start = max(_min, start); - end = min(_max, end); - if (end - start < kernel_size) - continue; - if ((end - start - kernel_size) / THREAD_SIZE + 1 >= pos) - return start + (pos - 1) * THREAD_SIZE; - pos -= (end - start - kernel_size) / THREAD_SIZE + 1; - } - - return 0; -} - -unsigned long get_random_base(unsigned long safe_addr) +unsigned long get_random_base(void) { - unsigned long usable_total = get_physmem_usable_total(); - unsigned long memory_limit = get_physmem_usable_end(); - unsigned long base_pos, max_pos, kernel_size; - int i; + unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size; + unsigned long minimal_pos = vmlinux.default_lma + vmlinux_size; + unsigned long random; - /* - * Avoid putting kernel in the end of physical memory - * which vmem and kasan code will use for shadow memory and - * pgtable mapping allocations. - */ - memory_limit -= kasan_estimate_memory_needs(usable_total); - memory_limit -= vmem_estimate_memory_needs(usable_total); - - safe_addr = ALIGN(safe_addr, THREAD_SIZE); - kernel_size = vmlinux.image_size + vmlinux.bss_size; - if (safe_addr + kernel_size > memory_limit) + /* [vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size : physmem_info.usable] */ + if (get_random(physmem_info.usable - minimal_pos, &random)) return 0; - max_pos = count_valid_kernel_positions(kernel_size, safe_addr, memory_limit); - if (!max_pos) { - sclp_early_printk("KASLR disabled: not enough memory\n"); - return 0; - } - - /* we need a value in the range [1, base_pos] inclusive */ - if (get_random(max_pos, &base_pos)) - return 0; - return position_to_address(base_pos + 1, kernel_size, safe_addr, memory_limit); + return physmem_alloc_range(RR_VMLINUX, vmlinux_size, THREAD_SIZE, + vmlinux.default_lma, minimal_pos + random, false); } diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index c2a1defc79da..0861e3c403f8 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -123,11 +123,10 @@ void decompressor_printk(const char *fmt, ...) sclp_early_printk(buf); } -static noinline void print_stacktrace(void) +void print_stacktrace(unsigned long sp) { struct stack_info boot_stack = { STACK_TYPE_TASK, (unsigned long)_stack_start, (unsigned long)_stack_end }; - unsigned long sp = S390_lowcore.gpregs_save_area[15]; bool first = true; decompressor_printk("Call Trace:\n"); @@ -173,7 +172,7 @@ void print_pgm_check_info(void) gpregs[8], gpregs[9], gpregs[10], gpregs[11]); decompressor_printk(" %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]); - print_stacktrace(); + print_stacktrace(S390_lowcore.gpregs_save_area[15]); decompressor_printk("Last Breaking-Event-Address:\n"); decompressor_printk(" [<%016lx>] %pS\n", (unsigned long)S390_lowcore.pgm_last_break, (void *)S390_lowcore.pgm_last_break); diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index dc2e4d0abfab..4ee9b7381142 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -1,16 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include -#include -#include -#include -#include #include +#include +#include #include +#include +#include +#include +#include #include "decompressor.h" #include "boot.h" struct physmem_info __bootdata(physmem_info); +static unsigned int physmem_alloc_ranges; +static unsigned long physmem_alloc_pos; /* up to 256 storage elements, 1020 subincrements each */ #define ENTRIES_EXTENDED_MAX \ @@ -20,6 +25,11 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n) { if (n < MEM_INLINED_ENTRIES) return &physmem_info.online[n]; + if (unlikely(!physmem_info.online_extended)) { + physmem_info.online_extended = (struct physmem_range *)physmem_alloc_range( + RR_MEM_DETECT_EXTENDED, ENTRIES_EXTENDED_MAX, sizeof(long), 0, + physmem_alloc_pos, true); + } return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES]; } @@ -143,49 +153,171 @@ static unsigned long search_mem_end(void) return (offset + 1) << 20; } -unsigned long detect_memory(unsigned long *safe_addr) +unsigned long detect_max_physmem_end(void) { unsigned long max_physmem_end = 0; - sclp_early_get_memsize(&max_physmem_end); - physmem_info.online_extended = (struct physmem_range *)ALIGN(*safe_addr, sizeof(u64)); + if (!sclp_early_get_memsize(&max_physmem_end)) { + physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO; + } else { + max_physmem_end = search_mem_end(); + physmem_info.info_source = MEM_DETECT_BIN_SEARCH; + } + return max_physmem_end; +} +void detect_physmem_online_ranges(unsigned long max_physmem_end) +{ if (!sclp_early_read_storage_info()) { physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO; } else if (!diag260()) { physmem_info.info_source = MEM_DETECT_DIAG260; - max_physmem_end = max_physmem_end ?: get_physmem_usable_end(); } else if (max_physmem_end) { add_physmem_online_range(0, max_physmem_end); - physmem_info.info_source = MEM_DETECT_SCLP_READ_INFO; - } else { - max_physmem_end = search_mem_end(); - add_physmem_online_range(0, max_physmem_end); - physmem_info.info_source = MEM_DETECT_BIN_SEARCH; } +} - if (physmem_info.range_count > MEM_INLINED_ENTRIES) { - *safe_addr += (physmem_info.range_count - MEM_INLINED_ENTRIES) * - sizeof(struct physmem_range); +void physmem_set_usable_limit(unsigned long limit) +{ + physmem_info.usable = limit; + physmem_alloc_pos = limit; +} + +static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max) +{ + unsigned long start, end, total_mem = 0, total_reserved_mem = 0; + struct reserved_range *range; + enum reserved_range_type t; + int i; + + decompressor_printk("Linux version %s\n", kernel_version); + if (!is_prot_virt_guest() && early_command_line[0]) + decompressor_printk("Kernel command line: %s\n", early_command_line); + decompressor_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n", + size, align, min, max); + decompressor_printk("Reserved memory ranges:\n"); + for_each_physmem_reserved_range(t, range, &start, &end) { + decompressor_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t)); + total_reserved_mem += end - start; + } + decompressor_printk("Usable online memory ranges (info source: %s [%x]):\n", + get_physmem_info_source(), physmem_info.info_source); + for_each_physmem_usable_range(i, &start, &end) { + decompressor_printk("%016lx %016lx\n", start, end); + total_mem += end - start; } + decompressor_printk("Usable online memory total: %lx Reserved: %lx Free: %lx\n", + total_mem, total_reserved_mem, + total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); + print_stacktrace(current_frame_address()); + sclp_early_printk("\n\n -- System halted\n"); + disabled_wait(); +} - return max_physmem_end; +void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) +{ + physmem_info.reserved[type].start = addr; + physmem_info.reserved[type].end = addr + size; } -void physmem_set_usable_limit(unsigned long limit) +void physmem_free(enum reserved_range_type type) { - struct physmem_range *range; - int i; + physmem_info.reserved[type].start = 0; + physmem_info.reserved[type].end = 0; +} - /* make sure mem_detect.usable ends up within online memory block */ - for (i = 0; i < physmem_info.range_count; i++) { - range = __get_physmem_range_ptr(i); - if (range->start >= limit) - break; - if (range->end >= limit) { - physmem_info.usable = limit; +static bool __physmem_alloc_intersects(unsigned long addr, unsigned long size, + unsigned long *intersection_start) +{ + unsigned long res_addr, res_size; + int t; + + for (t = 0; t < RR_MAX; t++) { + if (!get_physmem_reserved(t, &res_addr, &res_size)) + continue; + if (intersects(addr, size, res_addr, res_size)) { + *intersection_start = res_addr; + return true; + } + } + return ipl_report_certs_intersects(addr, size, intersection_start); +} + +static unsigned long __physmem_alloc_range(unsigned long size, unsigned long align, + unsigned long min, unsigned long max, + unsigned int from_ranges, unsigned int *ranges_left, + bool die_on_oom) +{ + unsigned int nranges = from_ranges ?: physmem_info.range_count; + unsigned long range_start, range_end; + unsigned long intersection_start; + unsigned long addr, pos = max; + + align = max(align, 8UL); + while (nranges) { + __get_physmem_range(nranges - 1, &range_start, &range_end, false); + pos = min(range_end, pos); + + if (round_up(min, align) + size > pos) break; + addr = round_down(pos - size, align); + if (range_start > addr) { + nranges--; + continue; + } + if (__physmem_alloc_intersects(addr, size, &intersection_start)) { + pos = intersection_start; + continue; + } + + if (ranges_left) + *ranges_left = nranges; + return addr; + } + if (die_on_oom) + die_oom(size, align, min, max); + return 0; +} + +unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size, + unsigned long align, unsigned long min, unsigned long max, + bool die_on_oom) +{ + unsigned long addr; + + max = min(max, physmem_alloc_pos); + addr = __physmem_alloc_range(size, align, min, max, 0, NULL, die_on_oom); + if (addr) + physmem_reserve(type, addr, size); + return addr; +} + +unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, + unsigned long align) +{ + struct reserved_range *range = &physmem_info.reserved[type]; + struct reserved_range *new_range; + unsigned int ranges_left; + unsigned long addr; + + addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges, + &ranges_left, true); + /* if not a consecutive allocation of the same type or first allocation */ + if (range->start != addr + size) { + if (range->end) { + physmem_alloc_pos = __physmem_alloc_range( + sizeof(struct reserved_range), 0, 0, physmem_alloc_pos, + physmem_alloc_ranges, &ranges_left, true); + new_range = (struct reserved_range *)physmem_alloc_pos; + *new_range = *range; + range->chain = new_range; + addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, + ranges_left, &ranges_left, true); } - physmem_info.usable = range->end; + range->end = addr + size; } + range->start = addr; + physmem_alloc_pos = addr; + physmem_alloc_ranges = ranges_left; + return addr; } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 50475bf25ecd..bc07e24329b9 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -21,7 +21,6 @@ unsigned long __bootdata_preserved(__kaslr_offset); unsigned long __bootdata_preserved(__abs_lowcore); unsigned long __bootdata_preserved(__memcpy_real_area); pte_t *__bootdata_preserved(memcpy_real_ptep); -unsigned long __bootdata(__amode31_base); unsigned long __bootdata_preserved(VMALLOC_START); unsigned long __bootdata_preserved(VMALLOC_END); struct page *__bootdata_preserved(vmemmap); @@ -29,7 +28,6 @@ unsigned long __bootdata_preserved(vmemmap_size); unsigned long __bootdata_preserved(MODULES_VADDR); unsigned long __bootdata_preserved(MODULES_END); unsigned long __bootdata(ident_map_size); -struct initrd_data __bootdata(initrd_data); u64 __bootdata_preserved(stfle_fac_list[16]); u64 __bootdata_preserved(alt_stfle_fac_list[16]); @@ -75,17 +73,20 @@ unsigned long mem_safe_offset(void) } #endif -static unsigned long rescue_initrd(unsigned long safe_addr) +static void rescue_initrd(unsigned long min, unsigned long max) { + unsigned long old_addr, addr, size; + if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD)) - return safe_addr; - if (!initrd_data.start || !initrd_data.size) - return safe_addr; - if (initrd_data.start < safe_addr) { - memmove((void *)safe_addr, (void *)initrd_data.start, initrd_data.size); - initrd_data.start = safe_addr; - } - return initrd_data.start + initrd_data.size; + return; + if (!get_physmem_reserved(RR_INITRD, &addr, &size)) + return; + if (addr >= min && addr + size <= max) + return; + old_addr = addr; + physmem_free(RR_INITRD); + addr = physmem_alloc_top_down(RR_INITRD, size, 0); + memmove((void *)addr, (void *)old_addr, size); } static void copy_bootdata(void) @@ -267,46 +268,52 @@ static void offset_vmlinux_info(unsigned long offset) vmlinux.invalid_pg_dir_off += offset; } -static unsigned long reserve_amode31(unsigned long safe_addr) -{ - __amode31_base = PAGE_ALIGN(safe_addr); - return __amode31_base + vmlinux.amode31_size; -} - void startup_kernel(void) { unsigned long max_physmem_end; unsigned long random_lma; - unsigned long safe_addr; unsigned long asce_limit; + unsigned long safe_addr; void *img; psw_t psw; - initrd_data.start = parmarea.initrd_start; - initrd_data.size = parmarea.initrd_size; + setup_lpp(); + safe_addr = mem_safe_offset(); + /* + * reserve decompressor memory together with decompression heap, buffer and + * memory which might be occupied by uncompressed kernel at default 1Mb + * position (if KASLR is off or failed). + */ + physmem_reserve(RR_DECOMPRESSOR, 0, safe_addr); + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && parmarea.initrd_size) + physmem_reserve(RR_INITRD, parmarea.initrd_start, parmarea.initrd_size); oldmem_data.start = parmarea.oldmem_base; oldmem_data.size = parmarea.oldmem_size; - setup_lpp(); store_ipl_parmblock(); - safe_addr = mem_safe_offset(); - safe_addr = reserve_amode31(safe_addr); - safe_addr = read_ipl_report(safe_addr); + read_ipl_report(); uv_query_info(); - safe_addr = rescue_initrd(safe_addr); sclp_early_read_info(); setup_boot_command_line(); parse_boot_command_line(); detect_facilities(); sanitize_prot_virt_host(); - max_physmem_end = detect_memory(&safe_addr); + max_physmem_end = detect_max_physmem_end(); setup_ident_map_size(max_physmem_end); setup_vmalloc_size(); asce_limit = setup_kernel_memory_layout(); + /* got final ident_map_size, physmem allocations could be performed now */ physmem_set_usable_limit(ident_map_size); + detect_physmem_online_ranges(max_physmem_end); + save_ipl_cert_comp_list(); + rescue_initrd(safe_addr, ident_map_size); +#ifdef CONFIG_KASAN + physmem_alloc_top_down(RR_KASAN, kasan_estimate_memory_needs(get_physmem_usable_total()), + _SEGMENT_SIZE); +#endif if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) { - random_lma = get_random_base(safe_addr); + random_lma = get_random_base(); if (random_lma) { __kaslr_offset = random_lma - vmlinux.default_lma; img = (void *)vmlinux.default_lma; @@ -317,8 +324,16 @@ void startup_kernel(void) if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) { img = decompress_kernel(); memmove((void *)vmlinux.default_lma, img, vmlinux.image_size); - } else if (__kaslr_offset) + } else if (__kaslr_offset) { memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size); + memset(img, 0, vmlinux.image_size); + } + + /* vmlinux decompression is done, shrink reserved low memory */ + physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); + if (!__kaslr_offset) + physmem_reserve(RR_VMLINUX, vmlinux.default_lma, vmlinux.image_size + vmlinux.bss_size); + physmem_alloc_range(RR_AMODE31, vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G, true); /* * The order of the following operations is important: @@ -338,16 +353,11 @@ void startup_kernel(void) setup_vmem(asce_limit); copy_bootdata(); - if (__kaslr_offset) { - /* - * Save KASLR offset for early dumps, before vmcore_info is set. - * Mark as uneven to distinguish from real vmcore_info pointer. - */ - S390_lowcore.vmcore_info = __kaslr_offset | 0x1UL; - /* Clear non-relocated kernel */ - if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) - memset(img, 0, vmlinux.image_size); - } + /* + * Save KASLR offset for early dumps, before vmcore_info is set. + * Mark as uneven to distinguish from real vmcore_info pointer. + */ + S390_lowcore.vmcore_info = __kaslr_offset ? __kaslr_offset | 0x1UL : 0; /* * Jump to the decompressed kernel entry point and switch DAT mode on. diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index b89a6893f398..8f16e6f9fb20 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -10,6 +10,8 @@ #include "decompressor.h" #include "boot.h" +unsigned long __bootdata_preserved(s390_invalid_asce); + #define init_mm (*(struct mm_struct *)vmlinux.init_mm_off) #define swapper_pg_dir vmlinux.swapper_pg_dir_off #define invalid_pg_dir vmlinux.invalid_pg_dir_off @@ -22,77 +24,27 @@ static inline pte_t *__virt_to_kpte(unsigned long va) return pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va), va); } -unsigned long __bootdata_preserved(s390_invalid_asce); -unsigned long __bootdata(pgalloc_pos); -unsigned long __bootdata(pgalloc_end); -unsigned long __bootdata(pgalloc_low); - enum populate_mode { POPULATE_NONE, POPULATE_ONE2ONE, POPULATE_ABS_LOWCORE, }; -static void boot_check_oom(void) -{ - if (pgalloc_pos < pgalloc_low) - error("out of memory on boot\n"); -} - -static void pgtable_populate_init(void) -{ - unsigned long initrd_end; - unsigned long kernel_end; - - kernel_end = vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size; - pgalloc_low = round_up(kernel_end, PAGE_SIZE); - if (IS_ENABLED(CONFIG_BLK_DEV_INITRD)) { - initrd_end = round_up(initrd_data.start + initrd_data.size, _SEGMENT_SIZE); - pgalloc_low = max(pgalloc_low, initrd_end); - } - - pgalloc_end = round_down(get_physmem_usable_end(), PAGE_SIZE); - pgalloc_pos = pgalloc_end; - - boot_check_oom(); -} - -static void *boot_alloc_pages(unsigned int order) -{ - unsigned long size = PAGE_SIZE << order; - - pgalloc_pos -= size; - pgalloc_pos = round_down(pgalloc_pos, size); - - boot_check_oom(); - - return (void *)pgalloc_pos; -} - static void *boot_crst_alloc(unsigned long val) { + unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER; unsigned long *table; - table = boot_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + table = (unsigned long *)physmem_alloc_top_down(RR_VMEM, size, size); + crst_table_init(table, val); return table; } static pte_t *boot_pte_alloc(void) { - static void *pte_leftover; pte_t *pte; - BUILD_BUG_ON(_PAGE_TABLE_SIZE * 2 != PAGE_SIZE); - - if (!pte_leftover) { - pte_leftover = boot_alloc_pages(0); - pte = pte_leftover + _PAGE_TABLE_SIZE; - } else { - pte = pte_leftover; - pte_leftover = NULL; - } + pte = (pte_t *)physmem_alloc_top_down(RR_VMEM, _PAGE_TABLE_SIZE, _PAGE_TABLE_SIZE); memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); return pte; } @@ -126,7 +78,6 @@ static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end) static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next; pte_t *pte, entry; pte = pte_offset_kernel(pmd, addr); @@ -250,7 +201,6 @@ void setup_vmem(unsigned long asce_limit) * To prevent creation of a large page at address 0 first map * the lowcore and create the identity mapping only afterwards. */ - pgtable_populate_init(); pgtable_populate(0, sizeof(struct lowcore), POPULATE_ONE2ONE); for_each_physmem_usable_range(i, &start, &end) pgtable_populate(start, end, POPULATE_ONE2ONE); @@ -269,10 +219,3 @@ void setup_vmem(unsigned long asce_limit) init_mm.context.asce = S390_lowcore.kernel_asce; } - -unsigned long vmem_estimate_memory_needs(unsigned long online_mem_total) -{ - unsigned long pages = DIV_ROUND_UP(online_mem_total, PAGE_SIZE); - - return DIV_ROUND_UP(pages, _PAGE_ENTRIES) * _PAGE_TABLE_SIZE * 2; -} diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index fa9d33b01b85..389df0e0d9e5 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -93,6 +93,8 @@ SECTIONS _decompressor_syms_end = .; } + _decompressor_end = .; + #ifdef CONFIG_KERNEL_UNCOMPRESSED . = 0x100000; #else diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index d5e65a5d06e7..27234fa1da8e 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -17,6 +17,27 @@ struct physmem_range { u64 end; }; +enum reserved_range_type { + RR_DECOMPRESSOR, + RR_INITRD, + RR_VMLINUX, + RR_AMODE31, + RR_IPLREPORT, + RR_CERT_COMP_LIST, + RR_MEM_DETECT_EXTENDED, + RR_VMEM, +#ifdef CONFIG_KASAN + RR_KASAN, +#endif + RR_MAX +}; + +struct reserved_range { + unsigned long start; + unsigned long end; + struct reserved_range *chain; +}; + /* * Storage element id is defined as 1 byte (up to 256 storage elements). * In practise only storage element id 0 and 1 are used). @@ -31,6 +52,7 @@ struct physmem_info { u32 range_count; u8 info_source; unsigned long usable; + struct reserved_range reserved[RR_MAX]; struct physmem_range online[MEM_INLINED_ENTRIES]; struct physmem_range *online_extended; }; @@ -80,6 +102,70 @@ static inline int __get_physmem_range(u32 n, unsigned long *start, #define for_each_physmem_online_range(i, p_start, p_end) \ for (i = 0; !__get_physmem_range(i, p_start, p_end, false); i++) +static inline const char *get_physmem_info_source(void) +{ + switch (physmem_info.info_source) { + case MEM_DETECT_SCLP_STOR_INFO: + return "sclp storage info"; + case MEM_DETECT_DIAG260: + return "diag260"; + case MEM_DETECT_SCLP_READ_INFO: + return "sclp read info"; + case MEM_DETECT_BIN_SEARCH: + return "binary search"; + } + return "none"; +} + +#define RR_TYPE_NAME(t) case RR_ ## t: return #t +static inline const char *get_rr_type_name(enum reserved_range_type t) +{ + switch (t) { + RR_TYPE_NAME(DECOMPRESSOR); + RR_TYPE_NAME(INITRD); + RR_TYPE_NAME(VMLINUX); + RR_TYPE_NAME(AMODE31); + RR_TYPE_NAME(IPLREPORT); + RR_TYPE_NAME(CERT_COMP_LIST); + RR_TYPE_NAME(MEM_DETECT_EXTENDED); + RR_TYPE_NAME(VMEM); +#ifdef CONFIG_KASAN + RR_TYPE_NAME(KASAN); +#endif + default: + return "UNKNOWN"; + } +} + +#define for_each_physmem_reserved_type_range(t, range, p_start, p_end) \ + for (range = &physmem_info.reserved[t], *p_start = range->start, *p_end = range->end; \ + range && range->end; range = range->chain, \ + *p_start = range ? range->start : 0, *p_end = range ? range->end : 0) + +static inline struct reserved_range *__physmem_reserved_next(enum reserved_range_type *t, + struct reserved_range *range) +{ + if (!range) { + range = &physmem_info.reserved[*t]; + if (range->end) + return range; + } + if (range->chain) + return range->chain; + while (++*t < RR_MAX) { + range = &physmem_info.reserved[*t]; + if (range->end) + return range; + } + return NULL; +} + +#define for_each_physmem_reserved_range(t, range, p_start, p_end) \ + for (t = 0, range = __physmem_reserved_next(&t, NULL), \ + *p_start = range ? range->start : 0, *p_end = range ? range->end : 0; \ + range; range = __physmem_reserved_next(&t, range), \ + *p_start = range ? range->start : 0, *p_end = range ? range->end : 0) + static inline unsigned long get_physmem_usable_total(void) { unsigned long start, end, total = 0; @@ -91,28 +177,12 @@ static inline unsigned long get_physmem_usable_total(void) return total; } -static inline void get_physmem_reserved(unsigned long *start, unsigned long *size) +static inline unsigned long get_physmem_reserved(enum reserved_range_type type, + unsigned long *addr, unsigned long *size) { - *start = (unsigned long)physmem_info.online_extended; - if (physmem_info.range_count > MEM_INLINED_ENTRIES) - *size = (physmem_info.range_count - MEM_INLINED_ENTRIES) * - sizeof(struct physmem_range); - else - *size = 0; -} - -static inline unsigned long get_physmem_usable_end(void) -{ - unsigned long start; - unsigned long end; - - if (physmem_info.usable) - return physmem_info.usable; - if (physmem_info.range_count) { - __get_physmem_range(physmem_info.range_count - 1, &start, &end, false); - return end; - } - return 0; + *addr = physmem_info.reserved[type].start; + *size = physmem_info.reserved[type].end - physmem_info.reserved[type].start; + return *size; } #endif diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index fc887e3e76f8..966d569f49b7 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -74,10 +74,6 @@ extern unsigned int zlib_dfltcc_support; extern int noexec_disabled; extern unsigned long ident_map_size; -extern unsigned long pgalloc_pos; -extern unsigned long pgalloc_end; -extern unsigned long pgalloc_low; -extern unsigned long __amode31_base; /* The Write Back bit position in the physaddr is given by the SLPC PCI */ extern unsigned long mio_wb_bit_mask; @@ -150,11 +146,6 @@ static inline unsigned long kaslr_offset(void) return __kaslr_offset; } -struct initrd_data { - unsigned long start; - unsigned long size; -}; -extern struct initrd_data initrd_data; struct oldmem_data { unsigned long start; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f909a2dc8a5a..d25425b8d0c0 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -148,13 +148,8 @@ static u32 __amode31_ref *__ctl_duct = __ctl_duct_amode31; int __bootdata(noexec_disabled); unsigned long __bootdata(ident_map_size); struct physmem_info __bootdata(physmem_info); -struct initrd_data __bootdata(initrd_data); -unsigned long __bootdata(pgalloc_pos); -unsigned long __bootdata(pgalloc_end); -unsigned long __bootdata(pgalloc_low); unsigned long __bootdata_preserved(__kaslr_offset); -unsigned long __bootdata(__amode31_base); unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -635,7 +630,11 @@ static struct notifier_block kdump_mem_nb = { */ static void __init reserve_pgtables(void) { - memblock_reserve(pgalloc_pos, pgalloc_end - pgalloc_pos); + unsigned long start, end; + struct reserved_range *range; + + for_each_physmem_reserved_type_range(RR_VMEM, range, &start, &end) + memblock_reserve(start, end - start); } /* @@ -712,13 +711,13 @@ static void __init reserve_crashkernel(void) */ static void __init reserve_initrd(void) { -#ifdef CONFIG_BLK_DEV_INITRD - if (!initrd_data.start || !initrd_data.size) + unsigned long addr, size; + + if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD) || !get_physmem_reserved(RR_INITRD, &addr, &size)) return; - initrd_start = (unsigned long)__va(initrd_data.start); - initrd_end = initrd_start + initrd_data.size; - memblock_reserve(initrd_data.start, initrd_data.size); -#endif + initrd_start = (unsigned long)__va(addr); + initrd_end = initrd_start + size; + memblock_reserve(addr, size); } /* @@ -732,35 +731,18 @@ static void __init reserve_certificate_list(void) static void __init reserve_physmem_info(void) { - unsigned long start, size; + unsigned long addr, size; - get_physmem_reserved(&start, &size); - if (size) - memblock_reserve(start, size); + if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + memblock_reserve(addr, size); } static void __init free_physmem_info(void) { - unsigned long start, size; + unsigned long addr, size; - get_physmem_reserved(&start, &size); - if (size) - memblock_phys_free(start, size); -} - -static const char * __init get_mem_info_source(void) -{ - switch (physmem_info.info_source) { - case MEM_DETECT_SCLP_STOR_INFO: - return "sclp storage info"; - case MEM_DETECT_DIAG260: - return "diag260"; - case MEM_DETECT_SCLP_READ_INFO: - return "sclp read info"; - case MEM_DETECT_BIN_SEARCH: - return "binary search"; - } - return "none"; + if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + memblock_phys_free(addr, size); } static void __init memblock_add_physmem_info(void) @@ -769,7 +751,7 @@ static void __init memblock_add_physmem_info(void) int i; pr_debug("physmem info source: %s (%hhd)\n", - get_mem_info_source(), physmem_info.info_source); + get_physmem_info_source(), physmem_info.info_source); /* keep memblock lists close to the kernel */ memblock_set_bottom_up(true); for_each_physmem_usable_range(i, &start, &end) @@ -780,21 +762,6 @@ static void __init memblock_add_physmem_info(void) memblock_set_node(0, ULONG_MAX, &memblock.memory, 0); } -/* - * Check for initrd being in usable memory - */ -static void __init check_initrd(void) -{ -#ifdef CONFIG_BLK_DEV_INITRD - if (initrd_data.start && initrd_data.size && - !memblock_is_region_memory(initrd_data.start, initrd_data.size)) { - pr_err("The initial RAM disk does not fit into the memory\n"); - memblock_phys_free(initrd_data.start, initrd_data.size); - initrd_start = initrd_end = 0; - } -#endif -} - /* * Reserve memory used for lowcore/command line/kernel image. */ @@ -803,7 +770,7 @@ static void __init reserve_kernel(void) memblock_reserve(0, STARTUP_NORMAL_OFFSET); memblock_reserve(OLDMEM_BASE, sizeof(unsigned long)); memblock_reserve(OLDMEM_SIZE, sizeof(unsigned long)); - memblock_reserve(__amode31_base, __eamode31 - __samode31); + memblock_reserve(physmem_info.reserved[RR_AMODE31].start, __eamode31 - __samode31); memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP); memblock_reserve(__pa(_stext), _end - _stext); } @@ -825,13 +792,13 @@ static void __init setup_memory(void) static void __init relocate_amode31_section(void) { unsigned long amode31_size = __eamode31 - __samode31; - long amode31_offset = __amode31_base - __samode31; + long amode31_offset = physmem_info.reserved[RR_AMODE31].start - __samode31; long *ptr; pr_info("Relocating AMODE31 section of size 0x%08lx\n", amode31_size); /* Move original AMODE31 section to the new one */ - memmove((void *)__amode31_base, (void *)__samode31, amode31_size); + memmove((void *)physmem_info.reserved[RR_AMODE31].start, (void *)__samode31, amode31_size); /* Zero out the old AMODE31 section to catch invalid accesses within it */ memset((void *)__samode31, 0, amode31_size); @@ -1017,7 +984,6 @@ void __init setup_arch(char **cmdline_p) if (MACHINE_HAS_EDAT2) hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); - check_initrd(); reserve_crashkernel(); #ifdef CONFIG_CRASH_DUMP /* diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index b0658136264f..2b20382f1bd8 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -1,19 +1,15 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include +#include #include -#include -#include +#include #include #include -#include #include -#include -#include -#include +#include +#include +static unsigned long pgalloc_pos __initdata; static unsigned long segment_pos __initdata; -static unsigned long segment_low __initdata; static bool has_edat __initdata; static bool has_nx __initdata; @@ -28,19 +24,20 @@ static void __init kasan_early_panic(const char *reason) static void * __init kasan_early_alloc_segment(void) { - segment_pos -= _SEGMENT_SIZE; + unsigned long addr = segment_pos; - if (segment_pos < segment_low) + segment_pos += _SEGMENT_SIZE; + if (segment_pos > pgalloc_pos) kasan_early_panic("out of memory during initialisation\n"); - return __va(segment_pos); + return __va(addr); } static void * __init kasan_early_alloc_pages(unsigned int order) { pgalloc_pos -= (PAGE_SIZE << order); - if (pgalloc_pos < pgalloc_low) + if (segment_pos > pgalloc_pos) kasan_early_panic("out of memory during initialisation\n"); return __va(pgalloc_pos); @@ -225,8 +222,8 @@ void __init kasan_early_init(void) pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); + unsigned long pgalloc_pos_initial, segment_pos_initial; unsigned long untracked_end = MODULES_VADDR; - unsigned long shadow_alloc_size; unsigned long start, end; int i; @@ -243,13 +240,11 @@ void __init kasan_early_init(void) crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE); - if (has_edat) { - shadow_alloc_size = get_physmem_usable_total() >> KASAN_SHADOW_SCALE_SHIFT; - segment_pos = round_down(pgalloc_pos, _SEGMENT_SIZE); - segment_low = segment_pos - shadow_alloc_size; - segment_low = round_down(segment_low, _SEGMENT_SIZE); - pgalloc_pos = segment_low; - } + /* segment allocations go bottom up -> <- pgalloc go top down */ + segment_pos_initial = physmem_info.reserved[RR_KASAN].start; + segment_pos = segment_pos_initial; + pgalloc_pos_initial = physmem_info.reserved[RR_KASAN].end; + pgalloc_pos = pgalloc_pos_initial; /* * Current memory layout: * +- 0 -------------+ +- shadow start -+ @@ -298,4 +293,6 @@ void __init kasan_early_init(void) /* enable kasan */ init_task.kasan_depth = 0; sclp_early_printk("KernelAddressSanitizer initialized\n"); + memblock_reserve(segment_pos_initial, segment_pos - segment_pos_initial); + memblock_reserve(pgalloc_pos, pgalloc_pos_initial - pgalloc_pos); } -- GitLab From e4c31004d3348202d4bc0bcdf662bf9d9d3e11cb Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Tue, 14 Feb 2023 09:39:24 +0100 Subject: [PATCH 0917/5631] s390/mm,pageattr: allow KASAN shadow memory Allow changing page table attributes for KASAN shadow memory ranges. Acked-by: Heiko Carstens Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/mm/pageattr.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 85195c18b2e8..7838e9c70000 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -300,8 +300,6 @@ static int change_page_attr(unsigned long addr, unsigned long end, if (addr == end) return 0; - if (end >= MODULES_END) - return -EINVAL; mutex_lock(&cpa_mutex); pgdp = pgd_offset_k(addr); do { -- GitLab From 557b19709da97bc93ea5cf61926ca05800c15a13 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Thu, 9 Feb 2023 22:05:11 +0100 Subject: [PATCH 0918/5631] s390/kasan: move shadow mapping to decompressor Since regular paging structs are initialized in decompressor already move KASAN shadow mapping to decompressor as well. This helps to avoid allocating KASAN required memory in 1 large chunk, de-duplicate paging structs creation code and start the uncompressed kernel with KASAN instrumentation right away. This also allows to avoid all pitfalls accidentally calling KASAN instrumented code during KASAN initialization. Acked-by: Heiko Carstens Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/boot/boot.h | 7 + arch/s390/boot/startup.c | 11 +- arch/s390/boot/vmem.c | 227 +++++++++++++++++++- arch/s390/include/asm/kasan.h | 31 +-- arch/s390/include/asm/physmem_info.h | 17 -- arch/s390/kernel/early.c | 9 + arch/s390/kernel/head64.S | 3 - arch/s390/kernel/vmlinux.lds.S | 7 + arch/s390/mm/Makefile | 3 - arch/s390/mm/kasan_init.c | 298 --------------------------- arch/s390/mm/vmem.c | 11 + 11 files changed, 258 insertions(+), 366 deletions(-) delete mode 100644 arch/s390/mm/kasan_init.c diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 2b4048106418..872963c8a0ab 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -32,6 +32,13 @@ struct vmlinux_info { unsigned long init_mm_off; unsigned long swapper_pg_dir_off; unsigned long invalid_pg_dir_off; +#ifdef CONFIG_KASAN + unsigned long kasan_early_shadow_page_off; + unsigned long kasan_early_shadow_pte_off; + unsigned long kasan_early_shadow_pmd_off; + unsigned long kasan_early_shadow_pud_off; + unsigned long kasan_early_shadow_p4d_off; +#endif }; void startup_kernel(void); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index bc07e24329b9..bdf305a93987 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -266,6 +266,13 @@ static void offset_vmlinux_info(unsigned long offset) vmlinux.init_mm_off += offset; vmlinux.swapper_pg_dir_off += offset; vmlinux.invalid_pg_dir_off += offset; +#ifdef CONFIG_KASAN + vmlinux.kasan_early_shadow_page_off += offset; + vmlinux.kasan_early_shadow_pte_off += offset; + vmlinux.kasan_early_shadow_pmd_off += offset; + vmlinux.kasan_early_shadow_pud_off += offset; + vmlinux.kasan_early_shadow_p4d_off += offset; +#endif } void startup_kernel(void) @@ -307,10 +314,6 @@ void startup_kernel(void) detect_physmem_online_ranges(max_physmem_end); save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); -#ifdef CONFIG_KASAN - physmem_alloc_top_down(RR_KASAN, kasan_estimate_memory_needs(get_physmem_usable_total()), - _SEGMENT_SIZE); -#endif if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) { random_lma = get_random_base(); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 8f16e6f9fb20..b01ea2abda03 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include @@ -16,6 +17,182 @@ unsigned long __bootdata_preserved(s390_invalid_asce); #define swapper_pg_dir vmlinux.swapper_pg_dir_off #define invalid_pg_dir vmlinux.invalid_pg_dir_off +enum populate_mode { + POPULATE_NONE, + POPULATE_ONE2ONE, + POPULATE_ABS_LOWCORE, +#ifdef CONFIG_KASAN + POPULATE_KASAN_MAP_SHADOW, + POPULATE_KASAN_ZERO_SHADOW, + POPULATE_KASAN_SHALLOW +#endif +}; + +static void pgtable_populate(unsigned long addr, unsigned long end, enum populate_mode mode); + +#ifdef CONFIG_KASAN + +#define kasan_early_shadow_page vmlinux.kasan_early_shadow_page_off +#define kasan_early_shadow_pte ((pte_t *)vmlinux.kasan_early_shadow_pte_off) +#define kasan_early_shadow_pmd ((pmd_t *)vmlinux.kasan_early_shadow_pmd_off) +#define kasan_early_shadow_pud ((pud_t *)vmlinux.kasan_early_shadow_pud_off) +#define kasan_early_shadow_p4d ((p4d_t *)vmlinux.kasan_early_shadow_p4d_off) +#define __sha(x) ((unsigned long)kasan_mem_to_shadow((void *)x)) + +static pte_t pte_z; + +static void kasan_populate_shadow(void) +{ + pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); + pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); + p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); + unsigned long untracked_end; + unsigned long start, end; + int i; + + pte_z = __pte(__pa(kasan_early_shadow_page) | pgprot_val(PAGE_KERNEL_RO)); + if (!machine.has_nx) + pte_z = clear_pte_bit(pte_z, __pgprot(_PAGE_NOEXEC)); + crst_table_init((unsigned long *)kasan_early_shadow_p4d, p4d_val(p4d_z)); + crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z)); + crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); + memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE); + + /* + * Current memory layout: + * +- 0 -------------+ +- shadow start -+ + * |1:1 ident mapping| /|1/8 of ident map| + * | | / | | + * +-end of ident map+ / +----------------+ + * | ... gap ... | / | kasan | + * | | / | zero page | + * +- vmalloc area -+ / | mapping | + * | vmalloc_size | / | (untracked) | + * +- modules vaddr -+ / +----------------+ + * | 2Gb |/ | unmapped | allocated per module + * +- shadow start -+ +----------------+ + * | 1/8 addr space | | zero pg mapping| (untracked) + * +- shadow end ----+---------+- shadow end ---+ + * + * Current memory layout (KASAN_VMALLOC): + * +- 0 -------------+ +- shadow start -+ + * |1:1 ident mapping| /|1/8 of ident map| + * | | / | | + * +-end of ident map+ / +----------------+ + * | ... gap ... | / | kasan zero page| (untracked) + * | | / | mapping | + * +- vmalloc area -+ / +----------------+ + * | vmalloc_size | / |shallow populate| + * +- modules vaddr -+ / +----------------+ + * | 2Gb |/ |shallow populate| + * +- shadow start -+ +----------------+ + * | 1/8 addr space | | zero pg mapping| (untracked) + * +- shadow end ----+---------+- shadow end ---+ + */ + + for_each_physmem_usable_range(i, &start, &end) + pgtable_populate(__sha(start), __sha(end), POPULATE_KASAN_MAP_SHADOW); + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + untracked_end = VMALLOC_START; + /* shallowly populate kasan shadow for vmalloc and modules */ + pgtable_populate(__sha(VMALLOC_START), __sha(MODULES_END), POPULATE_KASAN_SHALLOW); + } else { + untracked_end = MODULES_VADDR; + } + /* populate kasan shadow for untracked memory */ + pgtable_populate(__sha(ident_map_size), __sha(untracked_end), POPULATE_KASAN_ZERO_SHADOW); + pgtable_populate(__sha(MODULES_END), __sha(_REGION1_SIZE), POPULATE_KASAN_ZERO_SHADOW); +} + +static bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + if (mode == POPULATE_KASAN_ZERO_SHADOW && + IS_ALIGNED(addr, PGDIR_SIZE) && end - addr >= PGDIR_SIZE) { + pgd_populate(&init_mm, pgd, kasan_early_shadow_p4d); + return true; + } + return false; +} + +static bool kasan_p4d_populate_zero_shadow(p4d_t *p4d, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + if (mode == POPULATE_KASAN_ZERO_SHADOW && + IS_ALIGNED(addr, P4D_SIZE) && end - addr >= P4D_SIZE) { + p4d_populate(&init_mm, p4d, kasan_early_shadow_pud); + return true; + } + return false; +} + +static bool kasan_pud_populate_zero_shadow(pud_t *pud, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + if (mode == POPULATE_KASAN_ZERO_SHADOW && + IS_ALIGNED(addr, PUD_SIZE) && end - addr >= PUD_SIZE) { + pud_populate(&init_mm, pud, kasan_early_shadow_pmd); + return true; + } + return false; +} + +static bool kasan_pmd_populate_zero_shadow(pmd_t *pmd, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + if (mode == POPULATE_KASAN_ZERO_SHADOW && + IS_ALIGNED(addr, PMD_SIZE) && end - addr >= PMD_SIZE) { + pmd_populate(&init_mm, pmd, kasan_early_shadow_pte); + return true; + } + return false; +} + +static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode) +{ + pte_t entry; + + if (mode == POPULATE_KASAN_ZERO_SHADOW) { + set_pte(pte, pte_z); + return true; + } + return false; +} +#else + +static inline void kasan_populate_shadow(void) {} + +static inline bool kasan_pgd_populate_zero_shadow(pgd_t *pgd, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + return false; +} + +static inline bool kasan_p4d_populate_zero_shadow(p4d_t *p4d, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + return false; +} + +static inline bool kasan_pud_populate_zero_shadow(pud_t *pud, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + return false; +} + +static inline bool kasan_pmd_populate_zero_shadow(pmd_t *pmd, unsigned long addr, + unsigned long end, enum populate_mode mode) +{ + return false; +} + +static bool kasan_pte_populate_zero_shadow(pte_t *pte, enum populate_mode mode) +{ + return false; +} + +#endif + /* * Mimic virt_to_kpte() in lack of init_mm symbol. Skip pmd NULL check though. */ @@ -24,12 +201,6 @@ static inline pte_t *__virt_to_kpte(unsigned long va) return pte_offset_kernel(pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va), va); } -enum populate_mode { - POPULATE_NONE, - POPULATE_ONE2ONE, - POPULATE_ABS_LOWCORE, -}; - static void *boot_crst_alloc(unsigned long val) { unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER; @@ -42,14 +213,26 @@ static void *boot_crst_alloc(unsigned long val) static pte_t *boot_pte_alloc(void) { + static void *pte_leftover; pte_t *pte; - pte = (pte_t *)physmem_alloc_top_down(RR_VMEM, _PAGE_TABLE_SIZE, _PAGE_TABLE_SIZE); + /* + * handling pte_leftovers this way helps to avoid memory fragmentation + * during POPULATE_KASAN_MAP_SHADOW when EDAT is off + */ + if (!pte_leftover) { + pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE); + pte = pte_leftover + _PAGE_TABLE_SIZE; + } else { + pte = pte_leftover; + pte_leftover = NULL; + } + memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); return pte; } -static unsigned long _pa(unsigned long addr, enum populate_mode mode) +static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_mode mode) { switch (mode) { case POPULATE_NONE: @@ -58,6 +241,12 @@ static unsigned long _pa(unsigned long addr, enum populate_mode mode) return addr; case POPULATE_ABS_LOWCORE: return __abs_lowcore_pa(addr); +#ifdef CONFIG_KASAN + case POPULATE_KASAN_MAP_SHADOW: + addr = physmem_alloc_top_down(RR_VMEM, size, size); + memset((void *)addr, 0, size); + return addr; +#endif default: return -1; } @@ -83,7 +272,9 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e pte = pte_offset_kernel(pmd, addr); for (; addr < end; addr += PAGE_SIZE, pte++) { if (pte_none(*pte)) { - entry = __pte(_pa(addr, mode)); + if (kasan_pte_populate_zero_shadow(pte, mode)) + continue; + entry = __pte(_pa(addr, PAGE_SIZE, mode)); entry = set_pte_bit(entry, PAGE_KERNEL_EXEC); set_pte(pte, entry); } @@ -101,8 +292,10 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e for (; addr < end; addr = next, pmd++) { next = pmd_addr_end(addr, end); if (pmd_none(*pmd)) { + if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode)) + continue; if (can_large_pmd(pmd, addr, next)) { - entry = __pmd(_pa(addr, mode)); + entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode)); entry = set_pmd_bit(entry, SEGMENT_KERNEL_EXEC); set_pmd(pmd, entry); continue; @@ -127,8 +320,10 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e for (; addr < end; addr = next, pud++) { next = pud_addr_end(addr, end); if (pud_none(*pud)) { + if (kasan_pud_populate_zero_shadow(pud, addr, next, mode)) + continue; if (can_large_pud(pud, addr, next)) { - entry = __pud(_pa(addr, mode)); + entry = __pud(_pa(addr, _REGION3_SIZE, mode)); entry = set_pud_bit(entry, REGION3_KERNEL_EXEC); set_pud(pud, entry); continue; @@ -153,6 +348,8 @@ static void pgtable_p4d_populate(pgd_t *pgd, unsigned long addr, unsigned long e for (; addr < end; addr = next, p4d++) { next = p4d_addr_end(addr, end); if (p4d_none(*p4d)) { + if (kasan_p4d_populate_zero_shadow(p4d, addr, next, mode)) + continue; pud = boot_crst_alloc(_REGION3_ENTRY_EMPTY); p4d_populate(&init_mm, p4d, pud); } @@ -170,9 +367,15 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat for (; addr < end; addr = next, pgd++) { next = pgd_addr_end(addr, end); if (pgd_none(*pgd)) { + if (kasan_pgd_populate_zero_shadow(pgd, addr, next, mode)) + continue; p4d = boot_crst_alloc(_REGION2_ENTRY_EMPTY); pgd_populate(&init_mm, pgd, p4d); } +#ifdef CONFIG_KASAN + if (mode == POPULATE_KASAN_SHALLOW) + continue; +#endif pgtable_p4d_populate(pgd, addr, next, mode); } } @@ -210,6 +413,8 @@ void setup_vmem(unsigned long asce_limit) POPULATE_NONE); memcpy_real_ptep = __virt_to_kpte(__memcpy_real_area); + kasan_populate_shadow(); + S390_lowcore.kernel_asce = swapper_pg_dir | asce_bits; S390_lowcore.user_asce = s390_invalid_asce; diff --git a/arch/s390/include/asm/kasan.h b/arch/s390/include/asm/kasan.h index e5cfc81d5b61..0cffead0f2f2 100644 --- a/arch/s390/include/asm/kasan.h +++ b/arch/s390/include/asm/kasan.h @@ -2,7 +2,7 @@ #ifndef __ASM_KASAN_H #define __ASM_KASAN_H -#include +#include #ifdef CONFIG_KASAN @@ -13,35 +13,6 @@ #define KASAN_SHADOW_START KASAN_SHADOW_OFFSET #define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) -extern void kasan_early_init(void); - -/* - * Estimate kasan memory requirements, which it will reserve - * at the very end of available physical memory. To estimate - * that, we take into account that kasan would require - * 1/8 of available physical memory (for shadow memory) + - * creating page tables for the shadow memory region. - * To keep page tables estimates simple take the double of - * combined ptes size. - * - * physmem parameter has to be already adjusted if not entire physical memory - * would be used (e.g. due to effect of "mem=" option). - */ -static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem) -{ - unsigned long kasan_needs; - unsigned long pages; - /* for shadow memory */ - kasan_needs = round_up(physmem / 8, PAGE_SIZE); - /* for paging structures */ - pages = DIV_ROUND_UP(kasan_needs, PAGE_SIZE); - kasan_needs += DIV_ROUND_UP(pages, _PAGE_ENTRIES) * _PAGE_TABLE_SIZE * 2; - - return kasan_needs; -} -#else -static inline void kasan_early_init(void) { } -static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem) { return 0; } #endif #endif diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index 27234fa1da8e..8e9c582592b3 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -26,9 +26,6 @@ enum reserved_range_type { RR_CERT_COMP_LIST, RR_MEM_DETECT_EXTENDED, RR_VMEM, -#ifdef CONFIG_KASAN - RR_KASAN, -#endif RR_MAX }; @@ -129,9 +126,6 @@ static inline const char *get_rr_type_name(enum reserved_range_type t) RR_TYPE_NAME(CERT_COMP_LIST); RR_TYPE_NAME(MEM_DETECT_EXTENDED); RR_TYPE_NAME(VMEM); -#ifdef CONFIG_KASAN - RR_TYPE_NAME(KASAN); -#endif default: return "UNKNOWN"; } @@ -166,17 +160,6 @@ static inline struct reserved_range *__physmem_reserved_next(enum reserved_range range; range = __physmem_reserved_next(&t, range), \ *p_start = range ? range->start : 0, *p_end = range ? range->end : 0) -static inline unsigned long get_physmem_usable_total(void) -{ - unsigned long start, end, total = 0; - int i; - - for_each_physmem_usable_range(i, &start, &end) - total += end - start; - - return total; -} - static inline unsigned long get_physmem_reserved(enum reserved_range_type type, unsigned long *addr, unsigned long *size) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 8225a4c1f2e2..2dd5976a55ac 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -51,6 +51,14 @@ decompressor_handled_param(nokaslr); decompressor_handled_param(prot_virt); #endif +static void __init kasan_early_init(void) +{ +#ifdef CONFIG_KASAN + init_task.kasan_depth = 0; + sclp_early_printk("KernelAddressSanitizer initialized\n"); +#endif +} + static void __init reset_tod_clock(void) { union tod_clock clk; @@ -293,6 +301,7 @@ static void __init sort_amode31_extable(void) void __init startup_init(void) { + kasan_early_init(); reset_tod_clock(); time_early_init(); init_kernel_storage_key(); diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 3b3bf8329e6c..f68be3951103 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -26,9 +26,6 @@ ENTRY(startup_continue) stg %r14,__LC_CURRENT larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD-__PT_SIZE brasl %r14,sclp_early_adjust_va # allow sclp_early_printk -#ifdef CONFIG_KASAN - brasl %r14,kasan_early_init -#endif brasl %r14,startup_init # s390 specific early init brasl %r14,start_kernel # common init code # diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index b653ba8d51e6..8d2288a5ba25 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -219,6 +219,13 @@ SECTIONS QUAD(init_mm) QUAD(swapper_pg_dir) QUAD(invalid_pg_dir) +#ifdef CONFIG_KASAN + QUAD(kasan_early_shadow_page) + QUAD(kasan_early_shadow_pte) + QUAD(kasan_early_shadow_pmd) + QUAD(kasan_early_shadow_pud) + QUAD(kasan_early_shadow_p4d) +#endif } :NONE /* Debugging sections. */ diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile index 57e4f3a24829..d90db06a8af5 100644 --- a/arch/s390/mm/Makefile +++ b/arch/s390/mm/Makefile @@ -10,6 +10,3 @@ obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_PTDUMP_CORE) += dump_pagetables.o obj-$(CONFIG_PGSTE) += gmap.o - -KASAN_SANITIZE_kasan_init.o := n -obj-$(CONFIG_KASAN) += kasan_init.o diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c deleted file mode 100644 index 2b20382f1bd8..000000000000 --- a/arch/s390/mm/kasan_init.c +++ /dev/null @@ -1,298 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -static unsigned long pgalloc_pos __initdata; -static unsigned long segment_pos __initdata; -static bool has_edat __initdata; -static bool has_nx __initdata; - -#define __sha(x) ((unsigned long)kasan_mem_to_shadow((void *)x)) - -static void __init kasan_early_panic(const char *reason) -{ - sclp_early_printk("The Linux kernel failed to boot with the KernelAddressSanitizer:\n"); - sclp_early_printk(reason); - disabled_wait(); -} - -static void * __init kasan_early_alloc_segment(void) -{ - unsigned long addr = segment_pos; - - segment_pos += _SEGMENT_SIZE; - if (segment_pos > pgalloc_pos) - kasan_early_panic("out of memory during initialisation\n"); - - return __va(addr); -} - -static void * __init kasan_early_alloc_pages(unsigned int order) -{ - pgalloc_pos -= (PAGE_SIZE << order); - - if (segment_pos > pgalloc_pos) - kasan_early_panic("out of memory during initialisation\n"); - - return __va(pgalloc_pos); -} - -static void * __init kasan_early_crst_alloc(unsigned long val) -{ - unsigned long *table; - - table = kasan_early_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); - return table; -} - -static pte_t * __init kasan_early_pte_alloc(void) -{ - static void *pte_leftover; - pte_t *pte; - - BUILD_BUG_ON(_PAGE_TABLE_SIZE * 2 != PAGE_SIZE); - - if (!pte_leftover) { - pte_leftover = kasan_early_alloc_pages(0); - pte = pte_leftover + _PAGE_TABLE_SIZE; - } else { - pte = pte_leftover; - pte_leftover = NULL; - } - memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); - return pte; -} - -enum populate_mode { - POPULATE_MAP, - POPULATE_ZERO_SHADOW, - POPULATE_SHALLOW -}; - -static inline pgprot_t pgprot_clear_bit(pgprot_t pgprot, unsigned long bit) -{ - return __pgprot(pgprot_val(pgprot) & ~bit); -} - -static void __init kasan_early_pgtable_populate(unsigned long address, - unsigned long end, - enum populate_mode mode) -{ - pgprot_t pgt_prot_zero = PAGE_KERNEL_RO; - pgprot_t pgt_prot = PAGE_KERNEL; - pgprot_t sgt_prot = SEGMENT_KERNEL; - pgd_t *pg_dir; - p4d_t *p4_dir; - pud_t *pu_dir; - pmd_t *pm_dir; - pte_t *pt_dir; - pmd_t pmd; - pte_t pte; - - if (!has_nx) { - pgt_prot_zero = pgprot_clear_bit(pgt_prot_zero, _PAGE_NOEXEC); - pgt_prot = pgprot_clear_bit(pgt_prot, _PAGE_NOEXEC); - sgt_prot = pgprot_clear_bit(sgt_prot, _SEGMENT_ENTRY_NOEXEC); - } - - while (address < end) { - pg_dir = pgd_offset_k(address); - if (pgd_none(*pg_dir)) { - if (mode == POPULATE_ZERO_SHADOW && - IS_ALIGNED(address, PGDIR_SIZE) && - end - address >= PGDIR_SIZE) { - pgd_populate(&init_mm, pg_dir, - kasan_early_shadow_p4d); - address = (address + PGDIR_SIZE) & PGDIR_MASK; - continue; - } - p4_dir = kasan_early_crst_alloc(_REGION2_ENTRY_EMPTY); - pgd_populate(&init_mm, pg_dir, p4_dir); - } - - if (mode == POPULATE_SHALLOW) { - address = (address + P4D_SIZE) & P4D_MASK; - continue; - } - - p4_dir = p4d_offset(pg_dir, address); - if (p4d_none(*p4_dir)) { - if (mode == POPULATE_ZERO_SHADOW && - IS_ALIGNED(address, P4D_SIZE) && - end - address >= P4D_SIZE) { - p4d_populate(&init_mm, p4_dir, - kasan_early_shadow_pud); - address = (address + P4D_SIZE) & P4D_MASK; - continue; - } - pu_dir = kasan_early_crst_alloc(_REGION3_ENTRY_EMPTY); - p4d_populate(&init_mm, p4_dir, pu_dir); - } - - pu_dir = pud_offset(p4_dir, address); - if (pud_none(*pu_dir)) { - if (mode == POPULATE_ZERO_SHADOW && - IS_ALIGNED(address, PUD_SIZE) && - end - address >= PUD_SIZE) { - pud_populate(&init_mm, pu_dir, - kasan_early_shadow_pmd); - address = (address + PUD_SIZE) & PUD_MASK; - continue; - } - pm_dir = kasan_early_crst_alloc(_SEGMENT_ENTRY_EMPTY); - pud_populate(&init_mm, pu_dir, pm_dir); - } - - pm_dir = pmd_offset(pu_dir, address); - if (pmd_none(*pm_dir)) { - if (IS_ALIGNED(address, PMD_SIZE) && - end - address >= PMD_SIZE) { - if (mode == POPULATE_ZERO_SHADOW) { - pmd_populate(&init_mm, pm_dir, kasan_early_shadow_pte); - address = (address + PMD_SIZE) & PMD_MASK; - continue; - } else if (has_edat) { - void *page = kasan_early_alloc_segment(); - - memset(page, 0, _SEGMENT_SIZE); - pmd = __pmd(__pa(page)); - pmd = set_pmd_bit(pmd, sgt_prot); - set_pmd(pm_dir, pmd); - address = (address + PMD_SIZE) & PMD_MASK; - continue; - } - } - pt_dir = kasan_early_pte_alloc(); - pmd_populate(&init_mm, pm_dir, pt_dir); - } else if (pmd_large(*pm_dir)) { - address = (address + PMD_SIZE) & PMD_MASK; - continue; - } - - pt_dir = pte_offset_kernel(pm_dir, address); - if (pte_none(*pt_dir)) { - void *page; - - switch (mode) { - case POPULATE_MAP: - page = kasan_early_alloc_pages(0); - memset(page, 0, PAGE_SIZE); - pte = __pte(__pa(page)); - pte = set_pte_bit(pte, pgt_prot); - set_pte(pt_dir, pte); - break; - case POPULATE_ZERO_SHADOW: - page = kasan_early_shadow_page; - pte = __pte(__pa(page)); - pte = set_pte_bit(pte, pgt_prot_zero); - set_pte(pt_dir, pte); - break; - case POPULATE_SHALLOW: - /* should never happen */ - break; - } - } - address += PAGE_SIZE; - } -} - -static void __init kasan_early_detect_facilities(void) -{ - if (test_facility(8)) { - has_edat = true; - __ctl_set_bit(0, 23); - } - if (!noexec_disabled && test_facility(130)) { - has_nx = true; - __ctl_set_bit(0, 20); - } -} - -void __init kasan_early_init(void) -{ - pte_t pte_z = __pte(__pa(kasan_early_shadow_page) | pgprot_val(PAGE_KERNEL_RO)); - pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); - pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); - p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); - unsigned long pgalloc_pos_initial, segment_pos_initial; - unsigned long untracked_end = MODULES_VADDR; - unsigned long start, end; - int i; - - kasan_early_detect_facilities(); - if (!has_nx) - pte_z = clear_pte_bit(pte_z, __pgprot(_PAGE_NOEXEC)); - - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, P4D_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE)); - - /* init kasan zero shadow */ - crst_table_init((unsigned long *)kasan_early_shadow_p4d, p4d_val(p4d_z)); - crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z)); - crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); - memset64((u64 *)kasan_early_shadow_pte, pte_val(pte_z), PTRS_PER_PTE); - - /* segment allocations go bottom up -> <- pgalloc go top down */ - segment_pos_initial = physmem_info.reserved[RR_KASAN].start; - segment_pos = segment_pos_initial; - pgalloc_pos_initial = physmem_info.reserved[RR_KASAN].end; - pgalloc_pos = pgalloc_pos_initial; - /* - * Current memory layout: - * +- 0 -------------+ +- shadow start -+ - * |1:1 ident mapping| /|1/8 of ident map| - * | | / | | - * +-end of ident map+ / +----------------+ - * | ... gap ... | / | kasan | - * | | / | zero page | - * +- vmalloc area -+ / | mapping | - * | vmalloc_size | / | (untracked) | - * +- modules vaddr -+ / +----------------+ - * | 2Gb |/ | unmapped | allocated per module - * +- shadow start -+ +----------------+ - * | 1/8 addr space | | zero pg mapping| (untracked) - * +- shadow end ----+---------+- shadow end ---+ - * - * Current memory layout (KASAN_VMALLOC): - * +- 0 -------------+ +- shadow start -+ - * |1:1 ident mapping| /|1/8 of ident map| - * | | / | | - * +-end of ident map+ / +----------------+ - * | ... gap ... | / | kasan zero page| (untracked) - * | | / | mapping | - * +- vmalloc area -+ / +----------------+ - * | vmalloc_size | / |shallow populate| - * +- modules vaddr -+ / +----------------+ - * | 2Gb |/ |shallow populate| - * +- shadow start -+ +----------------+ - * | 1/8 addr space | | zero pg mapping| (untracked) - * +- shadow end ----+---------+- shadow end ---+ - */ - /* populate kasan shadow (for identity mapping and zero page mapping) */ - for_each_physmem_usable_range(i, &start, &end) - kasan_early_pgtable_populate(__sha(start), __sha(end), POPULATE_MAP); - if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { - untracked_end = VMALLOC_START; - /* shallowly populate kasan shadow for vmalloc and modules */ - kasan_early_pgtable_populate(__sha(VMALLOC_START), __sha(MODULES_END), - POPULATE_SHALLOW); - } - /* populate kasan shadow for untracked memory */ - kasan_early_pgtable_populate(__sha(ident_map_size), __sha(untracked_end), - POPULATE_ZERO_SHADOW); - kasan_early_pgtable_populate(__sha(MODULES_END), __sha(_REGION1_SIZE), - POPULATE_ZERO_SHADOW); - /* enable kasan */ - init_task.kasan_depth = 0; - sclp_early_printk("KernelAddressSanitizer initialized\n"); - memblock_reserve(segment_pos_initial, segment_pos - segment_pos_initial); - memblock_reserve(pgalloc_pos, pgalloc_pos_initial - pgalloc_pos); -} diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 4113a7ffa149..242f95aa9801 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -664,6 +665,9 @@ static void __init memblock_region_swap(void *a, void *b, int size) swap(*(struct memblock_region *)a, *(struct memblock_region *)b); } +#ifdef CONFIG_KASAN +#define __sha(x) ((unsigned long)kasan_mem_to_shadow((void *)x)) +#endif /* * map whole physical memory to virtual memory (identity mapping) * we reserve enough space in the vmalloc area for vmemmap to hotplug @@ -733,6 +737,13 @@ void __init vmem_map_init(void) SET_MEMORY_RW | SET_MEMORY_NX); } +#ifdef CONFIG_KASAN + for_each_mem_range(i, &base, &end) + __set_memory(__sha(base), + (__sha(end) - __sha(base)) >> PAGE_SHIFT, + SET_MEMORY_RW | SET_MEMORY_NX); +#endif + __set_memory((unsigned long)_stext, (unsigned long)(_etext - _stext) >> PAGE_SHIFT, SET_MEMORY_RO | SET_MEMORY_X); -- GitLab From 6ef55060a1cc29dd54ff390f22cb3de266dab2b0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Mar 2023 13:50:35 +0100 Subject: [PATCH 0919/5631] s390: make use of CONFIG_FUNCTION_ALIGNMENT Make use of CONFIG_FUNCTION_ALIGNMENT which was introduced with commit d49a0626216b ("arch: Introduce CONFIG_FUNCTION_ALIGNMENT"). Select FUNCTION_ALIGNMENT_8B for gcc in order to reflect gcc's default function alignment. For all other compilers, which is only clang, select a function alignment of 16 bytes which reflects the default function alignment for clang. Also change the __ALIGN define to follow whatever the value of CONFIG_FUNCTION_ALIGNMENT is. This makes sure that the alignment of C and assembler functions is the same. In result everything still uses the default function alignment for both compilers. However in addition this is now also true for all assembly functions, so that all functions have a consistent alignment. Signed-off-by: Heiko Carstens --- arch/s390/Kconfig | 2 ++ arch/s390/include/asm/linkage.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9809c74e1240..8f1c6da2ae4d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -131,6 +131,8 @@ config S390 select CLONE_BACKWARDS2 select DMA_OPS if PCI select DYNAMIC_FTRACE if FUNCTION_TRACER + select FUNCTION_ALIGNMENT_8B if CC_IS_GCC + select FUNCTION_ALIGNMENT_16B if !CC_IS_GCC select GCC12_NO_ARRAY_BOUNDS select GENERIC_ALLOCATOR select GENERIC_CPU_AUTOPROBE diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h index c76777b15fec..df3fb7d8227b 100644 --- a/arch/s390/include/asm/linkage.h +++ b/arch/s390/include/asm/linkage.h @@ -4,7 +4,7 @@ #include -#define __ALIGN .align 16, 0x07 +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x07 #define __ALIGN_STR __stringify(__ALIGN) #endif -- GitLab From dfa2a72cdbfc3b7cda196b3389579cff88201ce6 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Mar 2023 13:50:36 +0100 Subject: [PATCH 0920/5631] s390/ftrace: move hotpatch trampolines to mcount.S Move the ftrace hotpatch trampolines to mcount.S. This allows to make use of the standard SYM_CODE macros which again makes sure that the hotpatch trampolines follow the function alignment rules of the rest of the kernel. Signed-off-by: Heiko Carstens Acked-by: Ilya Leoshkevich Signed-off-by: Heiko Carstens --- arch/s390/kernel/ftrace.c | 20 -------------------- arch/s390/kernel/mcount.S | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 20 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 416b5a94353d..6f6c44b7af89 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -49,26 +49,6 @@ struct ftrace_insn { s32 disp; } __packed; -asm( - " .align 16\n" - "ftrace_shared_hotpatch_trampoline_br:\n" - " lmg %r0,%r1,2(%r1)\n" - " br %r1\n" - "ftrace_shared_hotpatch_trampoline_br_end:\n" -); - -#ifdef CONFIG_EXPOLINE -asm( - " .align 16\n" - "ftrace_shared_hotpatch_trampoline_exrl:\n" - " lmg %r0,%r1,2(%r1)\n" - " exrl %r0,0f\n" - " j .\n" - "0: br %r1\n" - "ftrace_shared_hotpatch_trampoline_exrl_end:\n" -); -#endif /* CONFIG_EXPOLINE */ - #ifdef CONFIG_MODULES static char *ftrace_plt; #endif /* CONFIG_MODULES */ diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 43ff91073d2a..4c4ee762f515 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -135,6 +135,22 @@ SYM_FUNC_END(return_to_handler) #endif #endif /* CONFIG_FUNCTION_TRACER */ +SYM_CODE_START(ftrace_shared_hotpatch_trampoline_br) + lmg %r0,%r1,2(%r1) + br %r1 +SYM_INNER_LABEL(ftrace_shared_hotpatch_trampoline_br_end, SYM_L_GLOBAL) +SYM_CODE_END(ftrace_shared_hotpatch_trampoline_br) + +#ifdef CONFIG_EXPOLINE +SYM_CODE_START(ftrace_shared_hotpatch_trampoline_exrl) + lmg %r0,%r1,2(%r1) + exrl %r0,0f + j . +0: br %r1 +SYM_INNER_LABEL(ftrace_shared_hotpatch_trampoline_exrl_end, SYM_L_GLOBAL) +SYM_CODE_END(ftrace_shared_hotpatch_trampoline_exrl) +#endif /* CONFIG_EXPOLINE */ + #ifdef CONFIG_RETHOOK SYM_FUNC_START(arch_rethook_trampoline) -- GitLab From 91a0117dce08a635d48b6016c5af354edde2082b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Mar 2023 13:50:37 +0100 Subject: [PATCH 0921/5631] s390/expoline: use __ALIGN instead of open coded .align Use __ALIGN instead of open coded .align statement to make sure that external expoline thunks follow global function alignment rules. Signed-off-by: Heiko Carstens --- arch/s390/include/asm/nospec-insn.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h index 7e9e99523e95..7a946c42ad13 100644 --- a/arch/s390/include/asm/nospec-insn.h +++ b/arch/s390/include/asm/nospec-insn.h @@ -2,6 +2,7 @@ #ifndef _ASM_S390_NOSPEC_ASM_H #define _ASM_S390_NOSPEC_ASM_H +#include #include #ifdef __ASSEMBLY__ @@ -16,7 +17,7 @@ .macro __THUNK_PROLOG_NAME name #ifdef CONFIG_EXPOLINE_EXTERN .pushsection .text,"ax",@progbits - .align 16,0x07 + __ALIGN #else .pushsection .text.\name,"axG",@progbits,\name,comdat #endif -- GitLab From c2272b2d3b164a02929c0ce9ffed35c4fe8fbe40 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Mar 2023 13:50:38 +0100 Subject: [PATCH 0922/5631] s390/vdso: use __ALIGN instead of open coded .align Use __ALIGN instead of open coded .align statement to make sure that vdso code follows global kernel function alignment rules. Signed-off-by: Heiko Carstens --- arch/s390/kernel/vdso32/vdso_user_wrapper.S | 3 ++- arch/s390/kernel/vdso64/vdso_user_wrapper.S | 5 +++-- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/vdso32/vdso_user_wrapper.S b/arch/s390/kernel/vdso32/vdso_user_wrapper.S index 3f42f27f978c..2e645003fdaf 100644 --- a/arch/s390/kernel/vdso32/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso32/vdso_user_wrapper.S @@ -1,12 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include #include .macro vdso_syscall func,syscall .globl __kernel_compat_\func .type __kernel_compat_\func,@function - .align 8 + __ALIGN __kernel_compat_\func: CFI_STARTPROC svc \syscall diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S index 97f0c0a669a5..57f62596e53b 100644 --- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S +++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include #include #include #include @@ -16,7 +17,7 @@ .macro vdso_func func .globl __kernel_\func .type __kernel_\func,@function - .align 8 + __ALIGN __kernel_\func: CFI_STARTPROC aghi %r15,-WRAPPER_FRAME_SIZE @@ -41,7 +42,7 @@ vdso_func getcpu .macro vdso_syscall func,syscall .globl __kernel_\func .type __kernel_\func,@function - .align 8 + __ALIGN __kernel_\func: CFI_STARTPROC svc \syscall -- GitLab From 322a7ce7a62f0593160bb80f5fba52d64967b92f Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 13 Mar 2023 13:50:39 +0100 Subject: [PATCH 0923/5631] s390: enable DEBUG_FORCE_FUNCTION_ALIGN_64B Allow to enforce 64 byte function alignment like it is possible for a couple of other architectures. This may or may not be helpful for debugging performance problems, as described with the Kconfig option. Since the kernel works also with 64 byte function alignment there is no reason for not allowing to enforce this function alignment. Signed-off-by: Heiko Carstens --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c8b379e2e9ad..59d8f3080cba 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -502,7 +502,7 @@ config SECTION_MISMATCH_WARN_ONLY config DEBUG_FORCE_FUNCTION_ALIGN_64B bool "Force all function address 64B aligned" - depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC) + depends on EXPERT && (X86_64 || ARM64 || PPC32 || PPC64 || ARC || S390) select FUNCTION_ALIGNMENT_64B help There are cases that a commit from one domain changes the function -- GitLab From 003d248fee72eb8d86aefaf3b6e47fe8acfda0b6 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Sun, 29 Jan 2023 19:45:25 +0100 Subject: [PATCH 0924/5631] s390/zcrypt: make psmid unsigned long instead of long long Since s390 kernel build does not support 32 bit build any more there is no difference between long and long long. So this patch reworks all occurrences of psmid (a 64 bit value) to use unsigned long now. Signed-off-by: Harald Freudenberger Acked-by: Heiko Carstens Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 4 ++-- drivers/s390/crypto/ap_bus.h | 6 +++--- drivers/s390/crypto/ap_queue.c | 8 ++++---- drivers/s390/crypto/zcrypt_cex2c.c | 6 +++--- drivers/s390/crypto/zcrypt_msgtype50.c | 4 ++-- drivers/s390/crypto/zcrypt_msgtype6.c | 10 +++++----- 6 files changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index c699f251a464..0744a00f92a5 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -386,7 +386,7 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid, * *resgr0 is to be used instead of qid to further process this entry. */ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, - unsigned long long *psmid, + unsigned long *psmid, void *msg, size_t length, size_t *reslength, unsigned long *resgr0) @@ -429,7 +429,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, if (resgr0) *resgr0 = reg0; } else { - *psmid = (((unsigned long long)rp1.even) << 32) + rp1.odd; + *psmid = (rp1.even << 32) + rp1.odd; if (resgr0) *resgr0 = 0; } diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 0f17933954fb..4ef8e6ac6323 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -242,7 +242,7 @@ enum ap_fi_flags { struct ap_message { struct list_head list; /* Request queueing. */ - unsigned long long psmid; /* Message id. */ + unsigned long psmid; /* Message id. */ void *msg; /* Pointer to message buffer. */ unsigned int len; /* actual msg len in msg buffer */ unsigned int bufsize; /* allocated msg buffer size */ @@ -285,8 +285,8 @@ static inline void ap_release_message(struct ap_message *ap_msg) * for the first time. Otherwise the ap message queue will get * confused. */ -int ap_send(ap_qid_t, unsigned long long, void *, size_t); -int ap_recv(ap_qid_t, unsigned long long *, void *, size_t); +int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length); +int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t length); enum ap_sm_wait ap_sm_event(struct ap_queue *aq, enum ap_sm_event event); enum ap_sm_wait ap_sm_event_loop(struct ap_queue *aq, enum ap_sm_event event); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 2637fe1df727..2fe8cbf72091 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -68,7 +68,7 @@ static int ap_queue_enable_irq(struct ap_queue *aq, void *ind) * because a segment boundary was reached. The NQAP is repeated. */ static inline struct ap_queue_status -__ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length, +__ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length, int special) { if (special) @@ -76,7 +76,7 @@ __ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length, return ap_nqap(qid, psmid, msg, length); } -int ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length) +int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length) { struct ap_queue_status status; @@ -95,7 +95,7 @@ int ap_send(ap_qid_t qid, unsigned long long psmid, void *msg, size_t length) } EXPORT_SYMBOL(ap_send); -int ap_recv(ap_qid_t qid, unsigned long long *psmid, void *msg, size_t length) +int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t length) { struct ap_queue_status status; @@ -177,7 +177,7 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) break; } if (!found) { - AP_DBF_WARN("%s unassociated reply psmid=0x%016llx on 0x%02x.%04x\n", + AP_DBF_WARN("%s unassociated reply psmid=0x%016lx on 0x%02x.%04x\n", __func__, aq->reply->psmid, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); } diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index cb7849defce3..9cabe3937c9a 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -181,7 +181,7 @@ static const struct attribute_group cca_queue_attr_grp = { static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) { struct ap_message ap_msg; - unsigned long long psmid; + unsigned long psmid; unsigned int domain; struct { struct type86_hdr hdr; @@ -209,7 +209,7 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) msg = ap_msg.msg; msg->cprbx.domain = AP_QID_QUEUE(aq->qid); - rc = ap_send(aq->qid, 0x0102030405060708ULL, ap_msg.msg, ap_msg.len); + rc = ap_send(aq->qid, 0x0102030405060708UL, ap_msg.msg, ap_msg.len); if (rc) goto out_free; @@ -217,7 +217,7 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) for (i = 0; i < 2 * HZ; i++) { msleep(1000 / HZ); rc = ap_recv(aq->qid, &psmid, ap_msg.msg, 4096); - if (rc == 0 && psmid == 0x0102030405060708ULL) + if (rc == 0 && psmid == 0x0102030405060708UL) break; } diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 7d245645fdd5..1b6b60b7215b 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -476,7 +476,7 @@ static long zcrypt_cex2a_modexpo(struct zcrypt_queue *zq, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_cex2a_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &work; rc = ICAMEX_msg_to_type50MEX_msg(zq, ap_msg, mex); @@ -527,7 +527,7 @@ static long zcrypt_cex2a_modexpo_crt(struct zcrypt_queue *zq, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_cex2a_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &work; rc = ICACRT_msg_to_type50CRT_msg(zq, ap_msg, crt); diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index a2e7fe33ba62..6c874808c356 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -1034,7 +1034,7 @@ static long zcrypt_msgtype6_modexpo(struct zcrypt_queue *zq, return -ENOMEM; ap_msg->bufsize = PAGE_SIZE; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &resp_type; rc = icamex_msg_to_type6mex_msgx(zq, ap_msg, mex); @@ -1084,7 +1084,7 @@ static long zcrypt_msgtype6_modexpo_crt(struct zcrypt_queue *zq, return -ENOMEM; ap_msg->bufsize = PAGE_SIZE; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = &resp_type; rc = icacrt_msg_to_type6crt_msgx(zq, ap_msg, crt); @@ -1135,7 +1135,7 @@ int prep_cca_ap_msg(bool userspace, struct ica_xcRB *xcrb, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) @@ -1216,7 +1216,7 @@ int prep_ep11_ap_msg(bool userspace, struct ep11_urb *xcrb, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive_ep11; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) @@ -1326,7 +1326,7 @@ int prep_rng_ap_msg(struct ap_message *ap_msg, int *func_code, if (!ap_msg->msg) return -ENOMEM; ap_msg->receive = zcrypt_msgtype6_receive; - ap_msg->psmid = (((unsigned long long)current->pid) << 32) + + ap_msg->psmid = (((unsigned long)current->pid) << 32) + atomic_inc_return(&zcrypt_step); ap_msg->private = kmemdup(&resp_type, sizeof(resp_type), GFP_KERNEL); if (!ap_msg->private) -- GitLab From 8794c5961394b7fb8a69f43eaad9566e5496c0c8 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 14 Feb 2023 17:13:18 +0100 Subject: [PATCH 0925/5631] s390/zcrypt: rework length information for dqap The inline ap_dqap function does not return the number of bytes actually written into the message buffer. The calling code inspects the AP message header to figure out what kind of AP message has been received and pulls the length information from this header. This processing may not work correctly in cases where only a fragment of the reply is received. With this patch the ap_dqap inline function now returns the number of actually written bytes in the *length parameter. So the calling function has a chance to compare the number of received bytes against what the AP message header length field states. This is especially useful in cases where a message could only get partially received. The low level reply processing functions needed some rework to be able to catch this new length information and compare it the right way. The rework also deals with some situations where until now the reply length was not correctly calculated and/or set. All this has been heavily tested as the modifications on the reply length information may affect crypto load. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 18 +++++++---- drivers/s390/crypto/ap_bus.h | 8 ++--- drivers/s390/crypto/ap_queue.c | 16 +++++----- drivers/s390/crypto/zcrypt_cex2c.c | 3 +- drivers/s390/crypto/zcrypt_msgtype50.c | 11 ++++--- drivers/s390/crypto/zcrypt_msgtype6.c | 41 +++++++++++++++++--------- 6 files changed, 60 insertions(+), 37 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 0744a00f92a5..6bb536e87897 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -359,10 +359,11 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid, * ap_dqap(): Receive message from adjunct processor queue. * @qid: The AP queue number * @psmid: Pointer to program supplied message identifier - * @msg: The message text - * @length: The message length - * @reslength: Resitual length on return - * @resgr0: input: gr0 value (only used if != 0), output: resitual gr0 content + * @msg: Pointer to message buffer + * @msglen: Message buffer size + * @length: Pointer to length of actually written bytes + * @reslength: Residual length on return + * @resgr0: input: gr0 value (only used if != 0), output: residual gr0 content * * Returns AP queue status structure. * Condition code 1 on DQAP means the receive has taken place @@ -387,7 +388,8 @@ static inline struct ap_queue_status ap_nqap(ap_qid_t qid, */ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, unsigned long *psmid, - void *msg, size_t length, + void *msg, size_t msglen, + size_t *length, size_t *reslength, unsigned long *resgr0) { @@ -399,7 +401,7 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, rp1.even = 0UL; rp1.odd = 0UL; rp2.even = (unsigned long)msg; - rp2.odd = (unsigned long)length; + rp2.odd = (unsigned long)msglen; asm volatile( " lgr 0,%[reg0]\n" /* qid param into gr0 */ @@ -434,6 +436,10 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid, *resgr0 = 0; } + /* update *length with the nr of bytes stored into the msg buffer */ + if (length) + *length = msglen - rp2.odd; + return reg1.status; } diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 4ef8e6ac6323..b5d7ccbc0784 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -244,8 +244,8 @@ struct ap_message { struct list_head list; /* Request queueing. */ unsigned long psmid; /* Message id. */ void *msg; /* Pointer to message buffer. */ - unsigned int len; /* actual msg len in msg buffer */ - unsigned int bufsize; /* allocated msg buffer size */ + size_t len; /* actual msg len in msg buffer */ + size_t bufsize; /* allocated msg buffer size */ u16 flags; /* Flags, see AP_MSG_FLAG_xxx */ struct ap_fi fi; /* Failure Injection cmd */ int rc; /* Return code for this message */ @@ -285,8 +285,8 @@ static inline void ap_release_message(struct ap_message *ap_msg) * for the first time. Otherwise the ap message queue will get * confused. */ -int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length); -int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t length); +int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t msglen); +int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t msglen); enum ap_sm_wait ap_sm_event(struct ap_queue *aq, enum ap_sm_event event); enum ap_sm_wait ap_sm_event_loop(struct ap_queue *aq, enum ap_sm_event event); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 2fe8cbf72091..bbd314918a5d 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -59,7 +59,7 @@ static int ap_queue_enable_irq(struct ap_queue *aq, void *ind) * @qid: The AP queue number * @psmid: The program supplied message identifier * @msg: The message text - * @length: The message length + * @msglen: The message length * @special: Special Bit * * Returns AP queue status structure. @@ -68,19 +68,19 @@ static int ap_queue_enable_irq(struct ap_queue *aq, void *ind) * because a segment boundary was reached. The NQAP is repeated. */ static inline struct ap_queue_status -__ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length, +__ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t msglen, int special) { if (special) qid |= 0x400000UL; - return ap_nqap(qid, psmid, msg, length); + return ap_nqap(qid, psmid, msg, msglen); } -int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length) +int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t msglen) { struct ap_queue_status status; - status = __ap_send(qid, psmid, msg, length, 0); + status = __ap_send(qid, psmid, msg, msglen, 0); switch (status.response_code) { case AP_RESPONSE_NORMAL: return 0; @@ -95,13 +95,13 @@ int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t length) } EXPORT_SYMBOL(ap_send); -int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t length) +int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t msglen) { struct ap_queue_status status; if (!msg) return -EINVAL; - status = ap_dqap(qid, psmid, msg, length, NULL, NULL); + status = ap_dqap(qid, psmid, msg, msglen, NULL, NULL, NULL); switch (status.response_code) { case AP_RESPONSE_NORMAL: return 0; @@ -150,7 +150,7 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) do { status = ap_dqap(aq->qid, &aq->reply->psmid, aq->reply->msg, aq->reply->bufsize, - &reslen, &resgr0); + &aq->reply->len, &reslen, &resgr0); parts++; } while (status.response_code == 0xFF && resgr0 != 0); diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 9cabe3937c9a..4dacf5f6461f 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -203,6 +203,7 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) ap_msg.msg = (void *)get_zeroed_page(GFP_KERNEL); if (!ap_msg.msg) return -ENOMEM; + ap_msg.bufsize = PAGE_SIZE; rng_type6cprb_msgx(&ap_msg, 4, &domain); @@ -216,7 +217,7 @@ static int zcrypt_cex2c_rng_supported(struct ap_queue *aq) /* Wait for the test message to complete. */ for (i = 0; i < 2 * HZ; i++) { msleep(1000 / HZ); - rc = ap_recv(aq->qid, &psmid, ap_msg.msg, 4096); + rc = ap_recv(aq->qid, &psmid, ap_msg.msg, ap_msg.bufsize); if (rc == 0 && psmid == 0x0102030405060708UL) break; } diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 1b6b60b7215b..05ace18c12b0 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -441,14 +441,17 @@ static void zcrypt_cex2a_receive(struct ap_queue *aq, t80h = reply->msg; if (t80h->type == TYPE80_RSP_CODE) { len = t80h->len; - if (len > reply->bufsize || len > msg->bufsize) { + if (len > reply->bufsize || len > msg->bufsize || + len != reply->len) { + ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; - } else { - memcpy(msg->msg, reply->msg, len); - msg->len = len; + goto out; } + memcpy(msg->msg, reply->msg, len); + msg->len = len; } else { memcpy(msg->msg, reply->msg, sizeof(error_reply)); + msg->len = sizeof(error_reply); } out: complete((struct completion *)msg->private); diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 6c874808c356..914151c03753 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -938,28 +938,37 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, t86r->cprbx.cprb_ver_id == 0x02) { switch (resp_type->type) { case CEXXC_RESPONSE_TYPE_ICA: - len = sizeof(struct type86x_reply) + t86r->length - 2; - if (len > reply->bufsize || len > msg->bufsize) { + len = sizeof(struct type86x_reply) + t86r->length; + if (len > reply->bufsize || len > msg->bufsize || + len != reply->len) { + ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; - } else { - memcpy(msg->msg, reply->msg, len); - msg->len = len; + goto out; } + memcpy(msg->msg, reply->msg, len); + msg->len = len; break; case CEXXC_RESPONSE_TYPE_XCRB: - len = t86r->fmt2.offset2 + t86r->fmt2.count2; - if (len > reply->bufsize || len > msg->bufsize) { + if (t86r->fmt2.count2) + len = t86r->fmt2.offset2 + t86r->fmt2.count2; + else + len = t86r->fmt2.offset1 + t86r->fmt2.count1; + if (len > reply->bufsize || len > msg->bufsize || + len != reply->len) { + ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; - } else { - memcpy(msg->msg, reply->msg, len); - msg->len = len; + goto out; } + memcpy(msg->msg, reply->msg, len); + msg->len = len; break; default: memcpy(msg->msg, &error_reply, sizeof(error_reply)); + msg->len = sizeof(error_reply); } } else { memcpy(msg->msg, reply->msg, sizeof(error_reply)); + msg->len = sizeof(error_reply); } out: complete(&resp_type->work); @@ -994,18 +1003,22 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, switch (resp_type->type) { case CEXXC_RESPONSE_TYPE_EP11: len = t86r->fmt2.offset1 + t86r->fmt2.count1; - if (len > reply->bufsize || len > msg->bufsize) { + if (len > reply->bufsize || len > msg->bufsize || + len != reply->len) { + ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; - } else { - memcpy(msg->msg, reply->msg, len); - msg->len = len; + goto out; } + memcpy(msg->msg, reply->msg, len); + msg->len = len; break; default: memcpy(msg->msg, &error_reply, sizeof(error_reply)); + msg->len = sizeof(error_reply); } } else { memcpy(msg->msg, reply->msg, sizeof(error_reply)); + msg->len = sizeof(error_reply); } out: complete(&resp_type->work); -- GitLab From 964d581daf46a1e65af220786104c6db88f833aa Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 6 Feb 2023 10:53:08 +0100 Subject: [PATCH 0926/5631] s390/zcrypt: replace scnprintf with sysfs_emit Replace scnprintf() with sysfs_emit() and friends where possible. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Reviewed-by: Tony Krowiak Signed-off-by: Heiko Carstens --- drivers/s390/crypto/ap_bus.c | 75 +++++++-------- drivers/s390/crypto/ap_card.c | 23 +++-- drivers/s390/crypto/ap_queue.c | 83 ++++++++--------- drivers/s390/crypto/zcrypt_api.c | 60 ++++-------- drivers/s390/crypto/zcrypt_card.c | 6 +- drivers/s390/crypto/zcrypt_cex2c.c | 55 +++++------ drivers/s390/crypto/zcrypt_cex4.c | 141 ++++++++++++++--------------- drivers/s390/crypto/zcrypt_queue.c | 4 +- 8 files changed, 199 insertions(+), 248 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index f4cc1720156f..2bc184ee8952 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1168,7 +1168,7 @@ EXPORT_SYMBOL(ap_parse_mask_str); static ssize_t ap_domain_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", ap_domain_index); + return sysfs_emit(buf, "%d\n", ap_domain_index); } static ssize_t ap_domain_store(struct bus_type *bus, @@ -1196,14 +1196,13 @@ static BUS_ATTR_RW(ap_domain); static ssize_t ap_control_domain_mask_show(struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ - return scnprintf(buf, PAGE_SIZE, "not supported\n"); + return sysfs_emit(buf, "not supported\n"); - return scnprintf(buf, PAGE_SIZE, - "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", - ap_qci_info->adm[0], ap_qci_info->adm[1], - ap_qci_info->adm[2], ap_qci_info->adm[3], - ap_qci_info->adm[4], ap_qci_info->adm[5], - ap_qci_info->adm[6], ap_qci_info->adm[7]); + return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", + ap_qci_info->adm[0], ap_qci_info->adm[1], + ap_qci_info->adm[2], ap_qci_info->adm[3], + ap_qci_info->adm[4], ap_qci_info->adm[5], + ap_qci_info->adm[6], ap_qci_info->adm[7]); } static BUS_ATTR_RO(ap_control_domain_mask); @@ -1211,14 +1210,13 @@ static BUS_ATTR_RO(ap_control_domain_mask); static ssize_t ap_usage_domain_mask_show(struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ - return scnprintf(buf, PAGE_SIZE, "not supported\n"); + return sysfs_emit(buf, "not supported\n"); - return scnprintf(buf, PAGE_SIZE, - "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", - ap_qci_info->aqm[0], ap_qci_info->aqm[1], - ap_qci_info->aqm[2], ap_qci_info->aqm[3], - ap_qci_info->aqm[4], ap_qci_info->aqm[5], - ap_qci_info->aqm[6], ap_qci_info->aqm[7]); + return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", + ap_qci_info->aqm[0], ap_qci_info->aqm[1], + ap_qci_info->aqm[2], ap_qci_info->aqm[3], + ap_qci_info->aqm[4], ap_qci_info->aqm[5], + ap_qci_info->aqm[6], ap_qci_info->aqm[7]); } static BUS_ATTR_RO(ap_usage_domain_mask); @@ -1226,29 +1224,27 @@ static BUS_ATTR_RO(ap_usage_domain_mask); static ssize_t ap_adapter_mask_show(struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ - return scnprintf(buf, PAGE_SIZE, "not supported\n"); + return sysfs_emit(buf, "not supported\n"); - return scnprintf(buf, PAGE_SIZE, - "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", - ap_qci_info->apm[0], ap_qci_info->apm[1], - ap_qci_info->apm[2], ap_qci_info->apm[3], - ap_qci_info->apm[4], ap_qci_info->apm[5], - ap_qci_info->apm[6], ap_qci_info->apm[7]); + return sysfs_emit(buf, "0x%08x%08x%08x%08x%08x%08x%08x%08x\n", + ap_qci_info->apm[0], ap_qci_info->apm[1], + ap_qci_info->apm[2], ap_qci_info->apm[3], + ap_qci_info->apm[4], ap_qci_info->apm[5], + ap_qci_info->apm[6], ap_qci_info->apm[7]); } static BUS_ATTR_RO(ap_adapter_mask); static ssize_t ap_interrupts_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", - ap_irq_flag ? 1 : 0); + return sysfs_emit(buf, "%d\n", ap_irq_flag ? 1 : 0); } static BUS_ATTR_RO(ap_interrupts); static ssize_t config_time_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", ap_config_time); + return sysfs_emit(buf, "%d\n", ap_config_time); } static ssize_t config_time_store(struct bus_type *bus, @@ -1267,7 +1263,7 @@ static BUS_ATTR_RW(config_time); static ssize_t poll_thread_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", ap_poll_kthread ? 1 : 0); + return sysfs_emit(buf, "%d\n", ap_poll_kthread ? 1 : 0); } static ssize_t poll_thread_store(struct bus_type *bus, @@ -1291,7 +1287,7 @@ static BUS_ATTR_RW(poll_thread); static ssize_t poll_timeout_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%llu\n", poll_timeout); + return sysfs_emit(buf, "%llu\n", poll_timeout); } static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf, @@ -1320,14 +1316,14 @@ static BUS_ATTR_RW(poll_timeout); static ssize_t ap_max_domain_id_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", ap_max_domain_id); + return sysfs_emit(buf, "%d\n", ap_max_domain_id); } static BUS_ATTR_RO(ap_max_domain_id); static ssize_t ap_max_adapter_id_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%d\n", ap_max_adapter_id); + return sysfs_emit(buf, "%d\n", ap_max_adapter_id); } static BUS_ATTR_RO(ap_max_adapter_id); @@ -1338,10 +1334,9 @@ static ssize_t apmask_show(struct bus_type *bus, char *buf) if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - rc = scnprintf(buf, PAGE_SIZE, - "0x%016lx%016lx%016lx%016lx\n", - ap_perms.apm[0], ap_perms.apm[1], - ap_perms.apm[2], ap_perms.apm[3]); + rc = sysfs_emit(buf, "0x%016lx%016lx%016lx%016lx\n", + ap_perms.apm[0], ap_perms.apm[1], + ap_perms.apm[2], ap_perms.apm[3]); mutex_unlock(&ap_perms_mutex); return rc; @@ -1431,10 +1426,9 @@ static ssize_t aqmask_show(struct bus_type *bus, char *buf) if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - rc = scnprintf(buf, PAGE_SIZE, - "0x%016lx%016lx%016lx%016lx\n", - ap_perms.aqm[0], ap_perms.aqm[1], - ap_perms.aqm[2], ap_perms.aqm[3]); + rc = sysfs_emit(buf, "0x%016lx%016lx%016lx%016lx\n", + ap_perms.aqm[0], ap_perms.aqm[1], + ap_perms.aqm[2], ap_perms.aqm[3]); mutex_unlock(&ap_perms_mutex); return rc; @@ -1520,8 +1514,7 @@ static BUS_ATTR_RW(aqmask); static ssize_t scans_show(struct bus_type *bus, char *buf) { - return scnprintf(buf, PAGE_SIZE, "%llu\n", - atomic64_read(&ap_scan_bus_count)); + return sysfs_emit(buf, "%llu\n", atomic64_read(&ap_scan_bus_count)); } static ssize_t scans_store(struct bus_type *bus, const char *buf, @@ -1543,9 +1536,9 @@ static ssize_t bindings_show(struct bus_type *bus, char *buf) ap_calc_bound_apqns(&apqns, &n); if (atomic64_read(&ap_scan_bus_count) >= 1 && n == apqns) - rc = scnprintf(buf, PAGE_SIZE, "%u/%u (complete)\n", n, apqns); + rc = sysfs_emit(buf, "%u/%u (complete)\n", n, apqns); else - rc = scnprintf(buf, PAGE_SIZE, "%u/%u\n", n, apqns); + rc = sysfs_emit(buf, "%u/%u\n", n, apqns); return rc; } diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c index 6b2170cf186e..b2bd477659a7 100644 --- a/drivers/s390/crypto/ap_card.c +++ b/drivers/s390/crypto/ap_card.c @@ -24,7 +24,7 @@ static ssize_t hwtype_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", ac->ap_dev.device_type); + return sysfs_emit(buf, "%d\n", ac->ap_dev.device_type); } static DEVICE_ATTR_RO(hwtype); @@ -34,7 +34,7 @@ static ssize_t raw_hwtype_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", ac->raw_hwtype); + return sysfs_emit(buf, "%d\n", ac->raw_hwtype); } static DEVICE_ATTR_RO(raw_hwtype); @@ -44,7 +44,7 @@ static ssize_t depth_show(struct device *dev, struct device_attribute *attr, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", ac->queue_depth); + return sysfs_emit(buf, "%d\n", ac->queue_depth); } static DEVICE_ATTR_RO(depth); @@ -54,7 +54,7 @@ static ssize_t ap_functions_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "0x%08X\n", ac->functions); + return sysfs_emit(buf, "0x%08X\n", ac->functions); } static DEVICE_ATTR_RO(ap_functions); @@ -70,7 +70,7 @@ static ssize_t request_count_show(struct device *dev, spin_lock_bh(&ap_queues_lock); req_cnt = atomic64_read(&ac->total_request_count); spin_unlock_bh(&ap_queues_lock); - return scnprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); + return sysfs_emit(buf, "%llu\n", req_cnt); } static ssize_t request_count_store(struct device *dev, @@ -107,7 +107,7 @@ static ssize_t requestq_count_show(struct device *dev, if (ac == aq->card) reqq_cnt += aq->requestq_count; spin_unlock_bh(&ap_queues_lock); - return scnprintf(buf, PAGE_SIZE, "%d\n", reqq_cnt); + return sysfs_emit(buf, "%d\n", reqq_cnt); } static DEVICE_ATTR_RO(requestq_count); @@ -126,7 +126,7 @@ static ssize_t pendingq_count_show(struct device *dev, if (ac == aq->card) penq_cnt += aq->pendingq_count; spin_unlock_bh(&ap_queues_lock); - return scnprintf(buf, PAGE_SIZE, "%d\n", penq_cnt); + return sysfs_emit(buf, "%d\n", penq_cnt); } static DEVICE_ATTR_RO(pendingq_count); @@ -134,8 +134,7 @@ static DEVICE_ATTR_RO(pendingq_count); static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { - return scnprintf(buf, PAGE_SIZE, "ap:t%02X\n", - to_ap_dev(dev)->device_type); + return sysfs_emit(buf, "ap:t%02X\n", to_ap_dev(dev)->device_type); } static DEVICE_ATTR_RO(modalias); @@ -145,7 +144,7 @@ static ssize_t config_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", ac->config ? 1 : 0); + return sysfs_emit(buf, "%d\n", ac->config ? 1 : 0); } static ssize_t config_store(struct device *dev, @@ -179,7 +178,7 @@ static ssize_t chkstop_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", ac->chkstop ? 1 : 0); + return sysfs_emit(buf, "%d\n", ac->chkstop ? 1 : 0); } static DEVICE_ATTR_RO(chkstop); @@ -189,7 +188,7 @@ static ssize_t max_msg_size_show(struct device *dev, { struct ap_card *ac = to_ap_card(dev); - return scnprintf(buf, PAGE_SIZE, "%u\n", ac->maxmsgsize); + return sysfs_emit(buf, "%u\n", ac->maxmsgsize); } static DEVICE_ATTR_RO(max_msg_size); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index bbd314918a5d..57028a35be98 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -490,9 +490,9 @@ static ssize_t request_count_show(struct device *dev, spin_unlock_bh(&aq->lock); if (valid) - return scnprintf(buf, PAGE_SIZE, "%llu\n", req_cnt); + return sysfs_emit(buf, "%llu\n", req_cnt); else - return scnprintf(buf, PAGE_SIZE, "-\n"); + return sysfs_emit(buf, "-\n"); } static ssize_t request_count_store(struct device *dev, @@ -520,7 +520,7 @@ static ssize_t requestq_count_show(struct device *dev, if (aq->dev_state > AP_DEV_STATE_UNINITIATED) reqq_cnt = aq->requestq_count; spin_unlock_bh(&aq->lock); - return scnprintf(buf, PAGE_SIZE, "%d\n", reqq_cnt); + return sysfs_emit(buf, "%d\n", reqq_cnt); } static DEVICE_ATTR_RO(requestq_count); @@ -535,7 +535,7 @@ static ssize_t pendingq_count_show(struct device *dev, if (aq->dev_state > AP_DEV_STATE_UNINITIATED) penq_cnt = aq->pendingq_count; spin_unlock_bh(&aq->lock); - return scnprintf(buf, PAGE_SIZE, "%d\n", penq_cnt); + return sysfs_emit(buf, "%d\n", penq_cnt); } static DEVICE_ATTR_RO(pendingq_count); @@ -550,14 +550,14 @@ static ssize_t reset_show(struct device *dev, switch (aq->sm_state) { case AP_SM_STATE_RESET_START: case AP_SM_STATE_RESET_WAIT: - rc = scnprintf(buf, PAGE_SIZE, "Reset in progress.\n"); + rc = sysfs_emit(buf, "Reset in progress.\n"); break; case AP_SM_STATE_WORKING: case AP_SM_STATE_QUEUE_FULL: - rc = scnprintf(buf, PAGE_SIZE, "Reset Timer armed.\n"); + rc = sysfs_emit(buf, "Reset Timer armed.\n"); break; default: - rc = scnprintf(buf, PAGE_SIZE, "No Reset Timer set.\n"); + rc = sysfs_emit(buf, "No Reset Timer set.\n"); } spin_unlock_bh(&aq->lock); return rc; @@ -591,11 +591,11 @@ static ssize_t interrupt_show(struct device *dev, spin_lock_bh(&aq->lock); if (aq->sm_state == AP_SM_STATE_SETIRQ_WAIT) - rc = scnprintf(buf, PAGE_SIZE, "Enable Interrupt pending.\n"); + rc = sysfs_emit(buf, "Enable Interrupt pending.\n"); else if (aq->interrupt) - rc = scnprintf(buf, PAGE_SIZE, "Interrupts enabled.\n"); + rc = sysfs_emit(buf, "Interrupts enabled.\n"); else - rc = scnprintf(buf, PAGE_SIZE, "Interrupts disabled.\n"); + rc = sysfs_emit(buf, "Interrupts disabled.\n"); spin_unlock_bh(&aq->lock); return rc; } @@ -609,7 +609,7 @@ static ssize_t config_show(struct device *dev, int rc; spin_lock_bh(&aq->lock); - rc = scnprintf(buf, PAGE_SIZE, "%d\n", aq->config ? 1 : 0); + rc = sysfs_emit(buf, "%d\n", aq->config ? 1 : 0); spin_unlock_bh(&aq->lock); return rc; } @@ -623,7 +623,7 @@ static ssize_t chkstop_show(struct device *dev, int rc; spin_lock_bh(&aq->lock); - rc = scnprintf(buf, PAGE_SIZE, "%d\n", aq->chkstop ? 1 : 0); + rc = sysfs_emit(buf, "%d\n", aq->chkstop ? 1 : 0); spin_unlock_bh(&aq->lock); return rc; } @@ -641,50 +641,43 @@ static ssize_t states_show(struct device *dev, /* queue device state */ switch (aq->dev_state) { case AP_DEV_STATE_UNINITIATED: - rc = scnprintf(buf, PAGE_SIZE, "UNINITIATED\n"); + rc = sysfs_emit(buf, "UNINITIATED\n"); break; case AP_DEV_STATE_OPERATING: - rc = scnprintf(buf, PAGE_SIZE, "OPERATING"); + rc = sysfs_emit(buf, "OPERATING"); break; case AP_DEV_STATE_SHUTDOWN: - rc = scnprintf(buf, PAGE_SIZE, "SHUTDOWN"); + rc = sysfs_emit(buf, "SHUTDOWN"); break; case AP_DEV_STATE_ERROR: - rc = scnprintf(buf, PAGE_SIZE, "ERROR"); + rc = sysfs_emit(buf, "ERROR"); break; default: - rc = scnprintf(buf, PAGE_SIZE, "UNKNOWN"); + rc = sysfs_emit(buf, "UNKNOWN"); } /* state machine state */ if (aq->dev_state) { switch (aq->sm_state) { case AP_SM_STATE_RESET_START: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [RESET_START]\n"); + rc += sysfs_emit_at(buf, rc, " [RESET_START]\n"); break; case AP_SM_STATE_RESET_WAIT: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [RESET_WAIT]\n"); + rc += sysfs_emit_at(buf, rc, " [RESET_WAIT]\n"); break; case AP_SM_STATE_SETIRQ_WAIT: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [SETIRQ_WAIT]\n"); + rc += sysfs_emit_at(buf, rc, " [SETIRQ_WAIT]\n"); break; case AP_SM_STATE_IDLE: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [IDLE]\n"); + rc += sysfs_emit_at(buf, rc, " [IDLE]\n"); break; case AP_SM_STATE_WORKING: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [WORKING]\n"); + rc += sysfs_emit_at(buf, rc, " [WORKING]\n"); break; case AP_SM_STATE_QUEUE_FULL: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [FULL]\n"); + rc += sysfs_emit_at(buf, rc, " [FULL]\n"); break; default: - rc += scnprintf(buf + rc, PAGE_SIZE - rc, - " [UNKNOWN]\n"); + rc += sysfs_emit_at(buf, rc, " [UNKNOWN]\n"); } } spin_unlock_bh(&aq->lock); @@ -705,33 +698,33 @@ static ssize_t last_err_rc_show(struct device *dev, switch (rc) { case AP_RESPONSE_NORMAL: - return scnprintf(buf, PAGE_SIZE, "NORMAL\n"); + return sysfs_emit(buf, "NORMAL\n"); case AP_RESPONSE_Q_NOT_AVAIL: - return scnprintf(buf, PAGE_SIZE, "Q_NOT_AVAIL\n"); + return sysfs_emit(buf, "Q_NOT_AVAIL\n"); case AP_RESPONSE_RESET_IN_PROGRESS: - return scnprintf(buf, PAGE_SIZE, "RESET_IN_PROGRESS\n"); + return sysfs_emit(buf, "RESET_IN_PROGRESS\n"); case AP_RESPONSE_DECONFIGURED: - return scnprintf(buf, PAGE_SIZE, "DECONFIGURED\n"); + return sysfs_emit(buf, "DECONFIGURED\n"); case AP_RESPONSE_CHECKSTOPPED: - return scnprintf(buf, PAGE_SIZE, "CHECKSTOPPED\n"); + return sysfs_emit(buf, "CHECKSTOPPED\n"); case AP_RESPONSE_BUSY: - return scnprintf(buf, PAGE_SIZE, "BUSY\n"); + return sysfs_emit(buf, "BUSY\n"); case AP_RESPONSE_INVALID_ADDRESS: - return scnprintf(buf, PAGE_SIZE, "INVALID_ADDRESS\n"); + return sysfs_emit(buf, "INVALID_ADDRESS\n"); case AP_RESPONSE_OTHERWISE_CHANGED: - return scnprintf(buf, PAGE_SIZE, "OTHERWISE_CHANGED\n"); + return sysfs_emit(buf, "OTHERWISE_CHANGED\n"); case AP_RESPONSE_Q_FULL: - return scnprintf(buf, PAGE_SIZE, "Q_FULL/NO_PENDING_REPLY\n"); + return sysfs_emit(buf, "Q_FULL/NO_PENDING_REPLY\n"); case AP_RESPONSE_INDEX_TOO_BIG: - return scnprintf(buf, PAGE_SIZE, "INDEX_TOO_BIG\n"); + return sysfs_emit(buf, "INDEX_TOO_BIG\n"); case AP_RESPONSE_NO_FIRST_PART: - return scnprintf(buf, PAGE_SIZE, "NO_FIRST_PART\n"); + return sysfs_emit(buf, "NO_FIRST_PART\n"); case AP_RESPONSE_MESSAGE_TOO_BIG: - return scnprintf(buf, PAGE_SIZE, "MESSAGE_TOO_BIG\n"); + return sysfs_emit(buf, "MESSAGE_TOO_BIG\n"); case AP_RESPONSE_REQ_FAC_NOT_INST: - return scnprintf(buf, PAGE_SIZE, "REQ_FAC_NOT_INST\n"); + return sysfs_emit(buf, "REQ_FAC_NOT_INST\n"); default: - return scnprintf(buf, PAGE_SIZE, "response code %d\n", rc); + return sysfs_emit(buf, "response code %d\n", rc); } } static DEVICE_ATTR_RO(last_err_rc); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 6fe05bb82c77..896cb3f2a375 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -159,25 +159,20 @@ static ssize_t ioctlmask_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i, rc; struct zcdn_device *zcdndev = to_zcdn_dev(dev); + int i, n; if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - buf[0] = '0'; - buf[1] = 'x'; + n = sysfs_emit(buf, "0x"); for (i = 0; i < sizeof(zcdndev->perms.ioctlm) / sizeof(long); i++) - snprintf(buf + 2 + 2 * i * sizeof(long), - PAGE_SIZE - 2 - 2 * i * sizeof(long), - "%016lx", zcdndev->perms.ioctlm[i]); - buf[2 + 2 * i * sizeof(long)] = '\n'; - buf[2 + 2 * i * sizeof(long) + 1] = '\0'; - rc = 2 + 2 * i * sizeof(long) + 1; + n += sysfs_emit_at(buf, n, "%016lx", zcdndev->perms.ioctlm[i]); + n += sysfs_emit_at(buf, n, "\n"); mutex_unlock(&ap_perms_mutex); - return rc; + return n; } static ssize_t ioctlmask_store(struct device *dev, @@ -201,25 +196,20 @@ static ssize_t apmask_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i, rc; struct zcdn_device *zcdndev = to_zcdn_dev(dev); + int i, n; if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - buf[0] = '0'; - buf[1] = 'x'; + n = sysfs_emit(buf, "0x"); for (i = 0; i < sizeof(zcdndev->perms.apm) / sizeof(long); i++) - snprintf(buf + 2 + 2 * i * sizeof(long), - PAGE_SIZE - 2 - 2 * i * sizeof(long), - "%016lx", zcdndev->perms.apm[i]); - buf[2 + 2 * i * sizeof(long)] = '\n'; - buf[2 + 2 * i * sizeof(long) + 1] = '\0'; - rc = 2 + 2 * i * sizeof(long) + 1; + n += sysfs_emit_at(buf, n, "%016lx", zcdndev->perms.apm[i]); + n += sysfs_emit_at(buf, n, "\n"); mutex_unlock(&ap_perms_mutex); - return rc; + return n; } static ssize_t apmask_store(struct device *dev, @@ -243,25 +233,20 @@ static ssize_t aqmask_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i, rc; struct zcdn_device *zcdndev = to_zcdn_dev(dev); + int i, n; if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - buf[0] = '0'; - buf[1] = 'x'; + n = sysfs_emit(buf, "0x"); for (i = 0; i < sizeof(zcdndev->perms.aqm) / sizeof(long); i++) - snprintf(buf + 2 + 2 * i * sizeof(long), - PAGE_SIZE - 2 - 2 * i * sizeof(long), - "%016lx", zcdndev->perms.aqm[i]); - buf[2 + 2 * i * sizeof(long)] = '\n'; - buf[2 + 2 * i * sizeof(long) + 1] = '\0'; - rc = 2 + 2 * i * sizeof(long) + 1; + n += sysfs_emit_at(buf, n, "%016lx", zcdndev->perms.aqm[i]); + n += sysfs_emit_at(buf, n, "\n"); mutex_unlock(&ap_perms_mutex); - return rc; + return n; } static ssize_t aqmask_store(struct device *dev, @@ -285,25 +270,20 @@ static ssize_t admask_show(struct device *dev, struct device_attribute *attr, char *buf) { - int i, rc; struct zcdn_device *zcdndev = to_zcdn_dev(dev); + int i, n; if (mutex_lock_interruptible(&ap_perms_mutex)) return -ERESTARTSYS; - buf[0] = '0'; - buf[1] = 'x'; + n = sysfs_emit(buf, "0x"); for (i = 0; i < sizeof(zcdndev->perms.adm) / sizeof(long); i++) - snprintf(buf + 2 + 2 * i * sizeof(long), - PAGE_SIZE - 2 - 2 * i * sizeof(long), - "%016lx", zcdndev->perms.adm[i]); - buf[2 + 2 * i * sizeof(long)] = '\n'; - buf[2 + 2 * i * sizeof(long) + 1] = '\0'; - rc = 2 + 2 * i * sizeof(long) + 1; + n += sysfs_emit_at(buf, n, "%016lx", zcdndev->perms.adm[i]); + n += sysfs_emit_at(buf, n, "\n"); mutex_unlock(&ap_perms_mutex); - return rc; + return n; } static ssize_t admask_store(struct device *dev, diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c index 6ca675042416..c815722d0ac8 100644 --- a/drivers/s390/crypto/zcrypt_card.c +++ b/drivers/s390/crypto/zcrypt_card.c @@ -41,7 +41,7 @@ static ssize_t type_show(struct device *dev, { struct zcrypt_card *zc = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%s\n", zc->type_string); + return sysfs_emit(buf, "%s\n", zc->type_string); } static DEVICE_ATTR_RO(type); @@ -54,7 +54,7 @@ static ssize_t online_show(struct device *dev, struct ap_card *ac = to_ap_card(dev); int online = ac->config && zc->online ? 1 : 0; - return scnprintf(buf, PAGE_SIZE, "%d\n", online); + return sysfs_emit(buf, "%d\n", online); } static ssize_t online_store(struct device *dev, @@ -118,7 +118,7 @@ static ssize_t load_show(struct device *dev, { struct zcrypt_card *zc = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load)); + return sysfs_emit(buf, "%d\n", atomic_read(&zc->load)); } static DEVICE_ATTR_RO(load); diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 4dacf5f6461f..78f8d68ffcb2 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -75,7 +75,7 @@ static ssize_t cca_serialnr_show(struct device *dev, if (ap_domain_index >= 0) cca_get_info(ac->id, ap_domain_index, &ci, zc->online); - return scnprintf(buf, PAGE_SIZE, "%s\n", ci.serial); + return sysfs_emit(buf, "%s\n", ci.serial); } static struct device_attribute dev_attr_cca_serialnr = @@ -110,51 +110,46 @@ static ssize_t cca_mkvps_show(struct device *dev, &ci, zq->online); if (ci.new_aes_mk_state >= '1' && ci.new_aes_mk_state <= '3') - n = scnprintf(buf, PAGE_SIZE, "AES NEW: %s 0x%016llx\n", - new_state[ci.new_aes_mk_state - '1'], - ci.new_aes_mkvp); + n = sysfs_emit(buf, "AES NEW: %s 0x%016llx\n", + new_state[ci.new_aes_mk_state - '1'], + ci.new_aes_mkvp); else - n = scnprintf(buf, PAGE_SIZE, "AES NEW: - -\n"); + n = sysfs_emit(buf, "AES NEW: - -\n"); if (ci.cur_aes_mk_state >= '1' && ci.cur_aes_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "AES CUR: %s 0x%016llx\n", - cao_state[ci.cur_aes_mk_state - '1'], - ci.cur_aes_mkvp); + n += sysfs_emit_at(buf, n, "AES CUR: %s 0x%016llx\n", + cao_state[ci.cur_aes_mk_state - '1'], + ci.cur_aes_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: - -\n"); + n += sysfs_emit_at(buf, n, "AES CUR: - -\n"); if (ci.old_aes_mk_state >= '1' && ci.old_aes_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "AES OLD: %s 0x%016llx\n", - cao_state[ci.old_aes_mk_state - '1'], - ci.old_aes_mkvp); + n += sysfs_emit_at(buf, n, "AES OLD: %s 0x%016llx\n", + cao_state[ci.old_aes_mk_state - '1'], + ci.old_aes_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: - -\n"); + n += sysfs_emit_at(buf, n, "AES OLD: - -\n"); if (ci.new_apka_mk_state >= '1' && ci.new_apka_mk_state <= '3') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA NEW: %s 0x%016llx\n", - new_state[ci.new_apka_mk_state - '1'], - ci.new_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA NEW: %s 0x%016llx\n", + new_state[ci.new_apka_mk_state - '1'], + ci.new_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA NEW: - -\n"); + n += sysfs_emit_at(buf, n, "APKA NEW: - -\n"); if (ci.cur_apka_mk_state >= '1' && ci.cur_apka_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA CUR: %s 0x%016llx\n", - cao_state[ci.cur_apka_mk_state - '1'], - ci.cur_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA CUR: %s 0x%016llx\n", + cao_state[ci.cur_apka_mk_state - '1'], + ci.cur_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA CUR: - -\n"); + n += sysfs_emit_at(buf, n, "APKA CUR: - -\n"); if (ci.old_apka_mk_state >= '1' && ci.old_apka_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA OLD: %s 0x%016llx\n", - cao_state[ci.old_apka_mk_state - '1'], - ci.old_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA OLD: %s 0x%016llx\n", + cao_state[ci.old_apka_mk_state - '1'], + ci.old_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA OLD: - -\n"); + n += sysfs_emit_at(buf, n, "APKA OLD: - -\n"); return n; } diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index b03916b7538b..9cfce9ff2e65 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -88,7 +88,7 @@ static ssize_t cca_serialnr_show(struct device *dev, if (ap_domain_index >= 0) cca_get_info(ac->id, ap_domain_index, &ci, zc->online); - return scnprintf(buf, PAGE_SIZE, "%s\n", ci.serial); + return sysfs_emit(buf, "%s\n", ci.serial); } static struct device_attribute dev_attr_cca_serialnr = @@ -123,79 +123,70 @@ static ssize_t cca_mkvps_show(struct device *dev, &ci, zq->online); if (ci.new_aes_mk_state >= '1' && ci.new_aes_mk_state <= '3') - n += scnprintf(buf + n, PAGE_SIZE, - "AES NEW: %s 0x%016llx\n", - new_state[ci.new_aes_mk_state - '1'], - ci.new_aes_mkvp); + n += sysfs_emit_at(buf, n, "AES NEW: %s 0x%016llx\n", + new_state[ci.new_aes_mk_state - '1'], + ci.new_aes_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE, "AES NEW: - -\n"); + n += sysfs_emit_at(buf, n, "AES NEW: - -\n"); if (ci.cur_aes_mk_state >= '1' && ci.cur_aes_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "AES CUR: %s 0x%016llx\n", - cao_state[ci.cur_aes_mk_state - '1'], - ci.cur_aes_mkvp); + n += sysfs_emit_at(buf, n, "AES CUR: %s 0x%016llx\n", + cao_state[ci.cur_aes_mk_state - '1'], + ci.cur_aes_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "AES CUR: - -\n"); + n += sysfs_emit_at(buf, n, "AES CUR: - -\n"); if (ci.old_aes_mk_state >= '1' && ci.old_aes_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "AES OLD: %s 0x%016llx\n", - cao_state[ci.old_aes_mk_state - '1'], - ci.old_aes_mkvp); + n += sysfs_emit_at(buf, n, "AES OLD: %s 0x%016llx\n", + cao_state[ci.old_aes_mk_state - '1'], + ci.old_aes_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "AES OLD: - -\n"); + n += sysfs_emit_at(buf, n, "AES OLD: - -\n"); if (ci.new_apka_mk_state >= '1' && ci.new_apka_mk_state <= '3') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA NEW: %s 0x%016llx\n", - new_state[ci.new_apka_mk_state - '1'], - ci.new_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA NEW: %s 0x%016llx\n", + new_state[ci.new_apka_mk_state - '1'], + ci.new_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA NEW: - -\n"); + n += sysfs_emit_at(buf, n, "APKA NEW: - -\n"); if (ci.cur_apka_mk_state >= '1' && ci.cur_apka_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA CUR: %s 0x%016llx\n", - cao_state[ci.cur_apka_mk_state - '1'], - ci.cur_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA CUR: %s 0x%016llx\n", + cao_state[ci.cur_apka_mk_state - '1'], + ci.cur_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA CUR: - -\n"); + n += sysfs_emit_at(buf, n, "APKA CUR: - -\n"); if (ci.old_apka_mk_state >= '1' && ci.old_apka_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "APKA OLD: %s 0x%016llx\n", - cao_state[ci.old_apka_mk_state - '1'], - ci.old_apka_mkvp); + n += sysfs_emit_at(buf, n, "APKA OLD: %s 0x%016llx\n", + cao_state[ci.old_apka_mk_state - '1'], + ci.old_apka_mkvp); else - n += scnprintf(buf + n, PAGE_SIZE - n, "APKA OLD: - -\n"); + n += sysfs_emit_at(buf, n, "APKA OLD: - -\n"); if (ci.new_asym_mk_state >= '1' && ci.new_asym_mk_state <= '3') - n += scnprintf(buf + n, PAGE_SIZE, - "ASYM NEW: %s 0x%016llx%016llx\n", - new_state[ci.new_asym_mk_state - '1'], - *((u64 *)(ci.new_asym_mkvp)), - *((u64 *)(ci.new_asym_mkvp + sizeof(u64)))); + n += sysfs_emit_at(buf, n, "ASYM NEW: %s 0x%016llx%016llx\n", + new_state[ci.new_asym_mk_state - '1'], + *((u64 *)(ci.new_asym_mkvp)), + *((u64 *)(ci.new_asym_mkvp + sizeof(u64)))); else - n += scnprintf(buf + n, PAGE_SIZE, "ASYM NEW: - -\n"); + n += sysfs_emit_at(buf, n, "ASYM NEW: - -\n"); if (ci.cur_asym_mk_state >= '1' && ci.cur_asym_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "ASYM CUR: %s 0x%016llx%016llx\n", - cao_state[ci.cur_asym_mk_state - '1'], - *((u64 *)(ci.cur_asym_mkvp)), - *((u64 *)(ci.cur_asym_mkvp + sizeof(u64)))); + n += sysfs_emit_at(buf, n, "ASYM CUR: %s 0x%016llx%016llx\n", + cao_state[ci.cur_asym_mk_state - '1'], + *((u64 *)(ci.cur_asym_mkvp)), + *((u64 *)(ci.cur_asym_mkvp + sizeof(u64)))); else - n += scnprintf(buf + n, PAGE_SIZE - n, "ASYM CUR: - -\n"); + n += sysfs_emit_at(buf, n, "ASYM CUR: - -\n"); if (ci.old_asym_mk_state >= '1' && ci.old_asym_mk_state <= '2') - n += scnprintf(buf + n, PAGE_SIZE - n, - "ASYM OLD: %s 0x%016llx%016llx\n", - cao_state[ci.old_asym_mk_state - '1'], - *((u64 *)(ci.old_asym_mkvp)), - *((u64 *)(ci.old_asym_mkvp + sizeof(u64)))); + n += sysfs_emit_at(buf, n, "ASYM OLD: %s 0x%016llx%016llx\n", + cao_state[ci.old_asym_mk_state - '1'], + *((u64 *)(ci.old_asym_mkvp)), + *((u64 *)(ci.old_asym_mkvp + sizeof(u64)))); else - n += scnprintf(buf + n, PAGE_SIZE - n, "ASYM OLD: - -\n"); + n += sysfs_emit_at(buf, n, "ASYM OLD: - -\n"); return n; } @@ -228,9 +219,9 @@ static ssize_t ep11_api_ordinalnr_show(struct device *dev, ep11_get_card_info(ac->id, &ci, zc->online); if (ci.API_ord_nr > 0) - return scnprintf(buf, PAGE_SIZE, "%u\n", ci.API_ord_nr); + return sysfs_emit(buf, "%u\n", ci.API_ord_nr); else - return scnprintf(buf, PAGE_SIZE, "\n"); + return sysfs_emit(buf, "\n"); } static struct device_attribute dev_attr_ep11_api_ordinalnr = @@ -249,11 +240,11 @@ static ssize_t ep11_fw_version_show(struct device *dev, ep11_get_card_info(ac->id, &ci, zc->online); if (ci.FW_version > 0) - return scnprintf(buf, PAGE_SIZE, "%d.%d\n", - (int)(ci.FW_version >> 8), - (int)(ci.FW_version & 0xFF)); + return sysfs_emit(buf, "%d.%d\n", + (int)(ci.FW_version >> 8), + (int)(ci.FW_version & 0xFF)); else - return scnprintf(buf, PAGE_SIZE, "\n"); + return sysfs_emit(buf, "\n"); } static struct device_attribute dev_attr_ep11_fw_version = @@ -272,9 +263,9 @@ static ssize_t ep11_serialnr_show(struct device *dev, ep11_get_card_info(ac->id, &ci, zc->online); if (ci.serial[0]) - return scnprintf(buf, PAGE_SIZE, "%16.16s\n", ci.serial); + return sysfs_emit(buf, "%16.16s\n", ci.serial); else - return scnprintf(buf, PAGE_SIZE, "\n"); + return sysfs_emit(buf, "\n"); } static struct device_attribute dev_attr_ep11_serialnr = @@ -309,11 +300,11 @@ static ssize_t ep11_card_op_modes_show(struct device *dev, if (ci.op_mode & (1ULL << ep11_op_modes[i].mode_bit)) { if (n > 0) buf[n++] = ' '; - n += scnprintf(buf + n, PAGE_SIZE - n, - "%s", ep11_op_modes[i].mode_txt); + n += sysfs_emit_at(buf, n, "%s", + ep11_op_modes[i].mode_txt); } } - n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); + n += sysfs_emit_at(buf, n, "\n"); return n; } @@ -356,29 +347,29 @@ static ssize_t ep11_mkvps_show(struct device *dev, &di); if (di.cur_wk_state == '0') { - n = scnprintf(buf, PAGE_SIZE, "WK CUR: %s -\n", - cwk_state[di.cur_wk_state - '0']); + n = sysfs_emit(buf, "WK CUR: %s -\n", + cwk_state[di.cur_wk_state - '0']); } else if (di.cur_wk_state == '1') { - n = scnprintf(buf, PAGE_SIZE, "WK CUR: %s 0x", - cwk_state[di.cur_wk_state - '0']); + n = sysfs_emit(buf, "WK CUR: %s 0x", + cwk_state[di.cur_wk_state - '0']); bin2hex(buf + n, di.cur_wkvp, sizeof(di.cur_wkvp)); n += 2 * sizeof(di.cur_wkvp); - n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); + n += sysfs_emit_at(buf, n, "\n"); } else { - n = scnprintf(buf, PAGE_SIZE, "WK CUR: - -\n"); + n = sysfs_emit(buf, "WK CUR: - -\n"); } if (di.new_wk_state == '0') { - n += scnprintf(buf + n, PAGE_SIZE - n, "WK NEW: %s -\n", - nwk_state[di.new_wk_state - '0']); + n += sysfs_emit_at(buf, n, "WK NEW: %s -\n", + nwk_state[di.new_wk_state - '0']); } else if (di.new_wk_state >= '1' && di.new_wk_state <= '2') { - n += scnprintf(buf + n, PAGE_SIZE - n, "WK NEW: %s 0x", - nwk_state[di.new_wk_state - '0']); + n += sysfs_emit_at(buf, n, "WK NEW: %s 0x", + nwk_state[di.new_wk_state - '0']); bin2hex(buf + n, di.new_wkvp, sizeof(di.new_wkvp)); n += 2 * sizeof(di.new_wkvp); - n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); + n += sysfs_emit_at(buf, n, "\n"); } else { - n += scnprintf(buf + n, PAGE_SIZE - n, "WK NEW: - -\n"); + n += sysfs_emit_at(buf, n, "WK NEW: - -\n"); } return n; @@ -406,11 +397,11 @@ static ssize_t ep11_queue_op_modes_show(struct device *dev, if (di.op_mode & (1ULL << ep11_op_modes[i].mode_bit)) { if (n > 0) buf[n++] = ' '; - n += scnprintf(buf + n, PAGE_SIZE - n, - "%s", ep11_op_modes[i].mode_txt); + n += sysfs_emit_at(buf, n, "%s", + ep11_op_modes[i].mode_txt); } } - n += scnprintf(buf + n, PAGE_SIZE - n, "\n"); + n += sysfs_emit_at(buf, n, "\n"); return n; } diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c index cdc5a4b2c019..112a80e8e6c2 100644 --- a/drivers/s390/crypto/zcrypt_queue.c +++ b/drivers/s390/crypto/zcrypt_queue.c @@ -44,7 +44,7 @@ static ssize_t online_show(struct device *dev, struct ap_queue *aq = to_ap_queue(dev); int online = aq->config && zq->online ? 1 : 0; - return scnprintf(buf, PAGE_SIZE, "%d\n", online); + return sysfs_emit(buf, "%d\n", online); } static ssize_t online_store(struct device *dev, @@ -84,7 +84,7 @@ static ssize_t load_show(struct device *dev, { struct zcrypt_queue *zq = dev_get_drvdata(dev); - return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load)); + return sysfs_emit(buf, "%d\n", atomic_read(&zq->load)); } static DEVICE_ATTR_RO(load); -- GitLab From f6047040217babeb9655b855c83d61cb1c375ac9 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 20 Sep 2022 15:12:01 +0200 Subject: [PATCH 0927/5631] s390/ap: exploit new B bit from QCI config info This patch introduces an update to the ap_config_info struct which is filled with the QCI subfunction. There is a new bit apsb (short 'B') showing if the AP secure bind facility is available. The patch also includes a simple function ap_sb_available() wrapping this bit test. Signed-off-by: Harald Freudenberger Reviewed-by: Tony Krowiak Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 13 +++++++------ drivers/s390/crypto/ap_bus.c | 20 ++++++++++++++++---- drivers/s390/crypto/ap_bus.h | 1 + drivers/s390/crypto/vfio_ap_ops.c | 6 +++--- 4 files changed, 27 insertions(+), 13 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 6bb536e87897..5e4a88460a57 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -180,15 +180,16 @@ struct ap_config_info { unsigned int apxa : 1; /* N bit */ unsigned int qact : 1; /* C bit */ unsigned int rc8a : 1; /* R bit */ - unsigned char _reserved1 : 4; - unsigned char _reserved2[3]; - unsigned char Na; /* max # of APs - 1 */ - unsigned char Nd; /* max # of Domains - 1 */ - unsigned char _reserved3[10]; + unsigned int : 4; + unsigned int apsb : 1; /* B bit */ + unsigned int : 23; + unsigned char na; /* max # of APs - 1 */ + unsigned char nd; /* max # of Domains - 1 */ + unsigned char _reserved0[10]; unsigned int apm[8]; /* AP ID mask */ unsigned int aqm[8]; /* AP (usage) queue mask */ unsigned int adm[8]; /* AP (control) domain mask */ - unsigned char _reserved4[16]; + unsigned char _reserved1[16]; } __aligned(8); /** diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 2bc184ee8952..b3c350e9fc1d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -200,6 +200,18 @@ static inline int ap_qact_available(void) return 0; } +/* + * ap_sb_available(): Test if the AP secure binding facility is available. + * + * Returns 1 if secure binding facility is available. + */ +int ap_sb_available(void) +{ + if (ap_qci_info) + return ap_qci_info->apsb; + return 0; +} + /* * ap_fetch_qci_info(): Fetch cryptographic config info * @@ -248,13 +260,13 @@ static void __init ap_init_qci_info(void) AP_DBF_INFO("%s successful fetched initial qci info\n", __func__); if (ap_qci_info->apxa) { - if (ap_qci_info->Na) { - ap_max_adapter_id = ap_qci_info->Na; + if (ap_qci_info->na) { + ap_max_adapter_id = ap_qci_info->na; AP_DBF_INFO("%s new ap_max_adapter_id is %d\n", __func__, ap_max_adapter_id); } - if (ap_qci_info->Nd) { - ap_max_domain_id = ap_qci_info->Nd; + if (ap_qci_info->nd) { + ap_max_domain_id = ap_qci_info->nd; AP_DBF_INFO("%s new ap_max_domain_id is %d\n", __func__, ap_max_domain_id); } diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index b5d7ccbc0784..5ce020879a38 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -296,6 +296,7 @@ void ap_cancel_message(struct ap_queue *aq, struct ap_message *ap_msg); void ap_flush_queue(struct ap_queue *aq); void *ap_airq_ptr(void); +int ap_sb_available(void); void ap_wait(enum ap_sm_wait wait); void ap_request_timeout(struct timer_list *t); void ap_bus_force_rescan(void); diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 72e10abb103a..bfe995116a6a 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -599,9 +599,9 @@ static int handle_pqap(struct kvm_vcpu *vcpu) static void vfio_ap_matrix_init(struct ap_config_info *info, struct ap_matrix *matrix) { - matrix->apm_max = info->apxa ? info->Na : 63; - matrix->aqm_max = info->apxa ? info->Nd : 15; - matrix->adm_max = info->apxa ? info->Nd : 15; + matrix->apm_max = info->apxa ? info->na : 63; + matrix->aqm_max = info->apxa ? info->nd : 15; + matrix->adm_max = info->apxa ? info->nd : 15; } static void vfio_ap_mdev_update_guest_apcb(struct ap_matrix_mdev *matrix_mdev) -- GitLab From d7b1813af6a589597290cd5f720e138c0a2bf913 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Tue, 20 Sep 2022 15:18:39 +0200 Subject: [PATCH 0928/5631] s390/ap: introduce new AP bus sysfs attribute features Introduce a new AP bus sysfs attribute /sys/bus/ap/features which shows the features from the QCI information. Currently these feature bits are evaluated: - QCI S bit is shown as 'APSC' - QCI N bit is shown as 'APXA' - QCI C bit is shown as 'QACT' - QCI R bit is shown as 'RC8A' - QCI B bit is shown as 'APSB' Signed-off-by: Harald Freudenberger Reviewed-by: Tony Krowiak Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- drivers/s390/crypto/ap_bus.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index b3c350e9fc1d..4e1926cf7a3d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1557,6 +1557,31 @@ static ssize_t bindings_show(struct bus_type *bus, char *buf) static BUS_ATTR_RO(bindings); +static ssize_t features_show(struct bus_type *bus, char *buf) +{ + int n = 0; + + if (!ap_qci_info) /* QCI not supported */ + return sysfs_emit(buf, "-\n"); + + if (ap_qci_info->apsc) + n += sysfs_emit_at(buf, n, "APSC "); + if (ap_qci_info->apxa) + n += sysfs_emit_at(buf, n, "APXA "); + if (ap_qci_info->qact) + n += sysfs_emit_at(buf, n, "QACT "); + if (ap_qci_info->rc8a) + n += sysfs_emit_at(buf, n, "RC8A "); + if (ap_qci_info->apsb) + n += sysfs_emit_at(buf, n, "APSB "); + + sysfs_emit_at(buf, n == 0 ? 0 : n - 1, "\n"); + + return n; +} + +static BUS_ATTR_RO(features); + static struct attribute *ap_bus_attrs[] = { &bus_attr_ap_domain.attr, &bus_attr_ap_control_domain_mask.attr, @@ -1572,6 +1597,7 @@ static struct attribute *ap_bus_attrs[] = { &bus_attr_aqmask.attr, &bus_attr_scans.attr, &bus_attr_bindings.attr, + &bus_attr_features.attr, NULL, }; ATTRIBUTE_GROUPS(ap_bus); -- GitLab From 211c06d845a7a5d856e2a99276ceb02aaa11c618 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Mon, 12 Sep 2022 18:02:44 +0200 Subject: [PATCH 0929/5631] s390/ap: make tapq gr2 response a struct This patch introduces a new struct ap_tapq_gr2 which covers the response in GR2 on TAPQ invocation. This makes it much easier and less error-prone for the calling functions to access the right field without shifting and masking. Signed-off-by: Harald Freudenberger Reviewed-by: Tony Krowiak Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 39 ++++++++++++++++++++++++++----- drivers/s390/crypto/ap_bus.c | 23 +++++------------- drivers/s390/crypto/vfio_ap_ops.c | 8 +++---- 3 files changed, 42 insertions(+), 28 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 5e4a88460a57..ba8da3f02f35 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -86,6 +86,34 @@ static inline bool ap_instructions_available(void) return reg1 != 0; } +/* TAPQ register GR2 response struct */ +struct ap_tapq_gr2 { + union { + unsigned long value; + struct { + unsigned int fac : 32; /* facility bits */ + unsigned int apinfo : 32; /* ap type, ... */ + }; + struct { + unsigned int s : 1; /* APSC */ + unsigned int m : 1; /* AP4KM */ + unsigned int c : 1; /* AP4KC */ + unsigned int mode : 3; + unsigned int n : 1; /* APXA */ + unsigned int : 1; + unsigned int class : 8; + unsigned int bs : 2; /* SE bind/assoc */ + unsigned int : 14; + unsigned int at : 8; /* ap type */ + unsigned int nd : 8; /* nr of domains */ + unsigned int : 4; + unsigned int ml : 4; /* apxl ml */ + unsigned int : 4; + unsigned int qd : 4; /* queue depth */ + }; + }; +}; + /** * ap_tapq(): Test adjunct processor queue. * @qid: The AP queue number @@ -93,7 +121,7 @@ static inline bool ap_instructions_available(void) * * Returns AP queue status structure. */ -static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) +static inline struct ap_queue_status ap_tapq(ap_qid_t qid, struct ap_tapq_gr2 *info) { union ap_queue_status_reg reg1; unsigned long reg2; @@ -108,7 +136,7 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) : [qid] "d" (qid) : "cc", "0", "1", "2"); if (info) - *info = reg2; + info->value = reg2; return reg1.status; } @@ -116,13 +144,12 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info) * ap_test_queue(): Test adjunct processor queue. * @qid: The AP queue number * @tbit: Test facilities bit - * @info: Pointer to queue descriptor + * @info: Ptr to tapq gr2 struct * * Returns AP queue status structure. */ -static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, - int tbit, - unsigned long *info) +static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, int tbit, + struct ap_tapq_gr2 *info) { if (tbit) qid |= 1UL << 23; /* set T bit*/ diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 4e1926cf7a3d..ab37818faeab 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -343,18 +343,7 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, int *q_depth, int *q_ml, bool *q_decfg, bool *q_cstop) { struct ap_queue_status status; - union { - unsigned long value; - struct { - unsigned int fac : 32; /* facility bits */ - unsigned int at : 8; /* ap type */ - unsigned int _res1 : 8; - unsigned int _res2 : 4; - unsigned int ml : 4; /* apxl ml */ - unsigned int _res3 : 4; - unsigned int qd : 4; /* queue depth */ - } tapq_gr2; - } tapq_info; + struct ap_tapq_gr2 tapq_info; tapq_info.value = 0; @@ -364,7 +353,7 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, return false; /* call TAPQ on this APQN */ - status = ap_test_queue(qid, ap_apft_available(), &tapq_info.value); + status = ap_test_queue(qid, ap_apft_available(), &tapq_info); switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: @@ -378,10 +367,10 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, */ if (WARN_ON_ONCE(!tapq_info.value)) return false; - *q_type = tapq_info.tapq_gr2.at; - *q_fac = tapq_info.tapq_gr2.fac; - *q_depth = tapq_info.tapq_gr2.qd; - *q_ml = tapq_info.tapq_gr2.ml; + *q_type = tapq_info.at; + *q_fac = tapq_info.fac; + *q_depth = tapq_info.qd; + *q_ml = tapq_info.ml; *q_decfg = status.response_code == AP_RESPONSE_DECONFIGURED; *q_cstop = status.response_code == AP_RESPONSE_CHECKSTOPPED; switch (*q_type) { diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index bfe995116a6a..31de464e4bb2 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -2115,8 +2115,8 @@ static void vfio_ap_filter_apid_by_qtype(unsigned long *apm, unsigned long *aqm) { bool apid_cleared; struct ap_queue_status status; - unsigned long apid, apqi, info; - int qtype, qtype_mask = 0xff000000; + unsigned long apid, apqi; + struct ap_tapq_gr2 info; for_each_set_bit_inv(apid, apm, AP_DEVICES) { apid_cleared = false; @@ -2133,15 +2133,13 @@ static void vfio_ap_filter_apid_by_qtype(unsigned long *apm, unsigned long *aqm) case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: case AP_RESPONSE_BUSY: - qtype = info & qtype_mask; - /* * The vfio_ap device driver only * supports CEX4 and newer adapters, so * remove the APID if the adapter is * older than a CEX4. */ - if (qtype < AP_DEVICE_TYPE_CEX4) { + if (info.at < AP_DEVICE_TYPE_CEX4) { clear_bit_inv(apid, apm); apid_cleared = true; } -- GitLab From 088174960ebc197fab8af9b99e039bc5c0aa34e7 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 7 Sep 2022 17:25:45 +0200 Subject: [PATCH 0930/5631] s390/ap: filter ap card functions, new queue functions attribute With SE SB (Secure Binding) some currently unused and thus always zero bits in the TAPQ GR2 result are now used to show the binding state of a queue. So to check if a card has changed the comparing base is exactly this GR2 value shown as 'ap_function' in sysfs (/sys/devices/ap/cardxx/ap_functions). Now there is some queue specific info in this info and so a new mask TAPQ_CARD_FUNC_CMP_MASK is used to filter out only the relevant bits for card compare. For the same reason now the function bits (including exactly this bind/associate information) need to be exposed to user space now. So tools like lszcrypt can evaluate binding/association state on a queue base. So here comes a new sysfs attribute /sys/devices/ap/cardxx/xx.yyyy/ap_functions This sysfs attribute is similar to the already existing ap_functions attribute at ap card level. It shows the upper 32 bits of GR2 from an invocation of TAPQ for this AP queue. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- drivers/s390/crypto/ap_bus.c | 6 +++--- drivers/s390/crypto/ap_bus.h | 4 +++- drivers/s390/crypto/ap_queue.c | 21 +++++++++++++++++++++ 3 files changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ab37818faeab..05e4fe1384a8 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1999,7 +1999,6 @@ static inline void ap_scan_adapter(int ap) } return; } - if (ac) { /* Check APQN against existing card device for changes */ if (ac->raw_hwtype != type) { @@ -2008,9 +2007,10 @@ static inline void ap_scan_adapter(int ap) ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); ac = NULL; - } else if (ac->functions != func) { + } else if ((ac->functions & TAPQ_CARD_FUNC_CMP_MASK) != + (func & TAPQ_CARD_FUNC_CMP_MASK)) { AP_DBF_INFO("%s(%d) functions 0x%08x changed, rm card and queue devs\n", - __func__, ap, type); + __func__, ap, func); ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); ac = NULL; diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 5ce020879a38..f09a3fd4d7bd 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -178,7 +178,7 @@ struct ap_device { struct ap_card { struct ap_device ap_dev; int raw_hwtype; /* AP raw hardware type. */ - unsigned int functions; /* AP device function bitfield. */ + unsigned int functions; /* TAPQ GR2 upper 32 facility bits */ int queue_depth; /* AP queue depth.*/ int id; /* AP card number. */ unsigned int maxmsgsize; /* AP msg limit for this card */ @@ -187,6 +187,8 @@ struct ap_card { atomic64_t total_request_count; /* # requests ever for this AP device.*/ }; +#define TAPQ_CARD_FUNC_CMP_MASK 0xFFFF0000 + #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device) struct ap_queue { diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 57028a35be98..1c08b282987c 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -630,6 +630,26 @@ static ssize_t chkstop_show(struct device *dev, static DEVICE_ATTR_RO(chkstop); +static ssize_t ap_functions_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + struct ap_queue_status status; + struct ap_tapq_gr2 info; + + status = ap_test_queue(aq->qid, 1, &info); + if (status.response_code > AP_RESPONSE_BUSY) { + AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return -EIO; + } + + return sysfs_emit(buf, "0x%08X\n", info.fac); +} + +static DEVICE_ATTR_RO(ap_functions); + #ifdef CONFIG_ZCRYPT_DEBUG static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -738,6 +758,7 @@ static struct attribute *ap_queue_dev_attrs[] = { &dev_attr_interrupt.attr, &dev_attr_config.attr, &dev_attr_chkstop.attr, + &dev_attr_ap_functions.attr, #ifdef CONFIG_ZCRYPT_DEBUG &dev_attr_states.attr, &dev_attr_last_err_rc.attr, -- GitLab From 4bdf3c3956d863b6823daa185ee3ce3e3a432cf3 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 7 Sep 2022 18:04:03 +0200 Subject: [PATCH 0931/5631] s390/ap: provide F bit parameter for ap_rapq() and ap_zapq() Extent the ap inline functions ap_rapq() (calls PQAP(RAPQ)) and ap_zapq() (calls PQAP(ZAPQ)) with a new parameter to enable the new architectured F bit which forces an unassociate and/or unbind on a secure execution associated and/or bound queue. Signed-off-by: Harald Freudenberger Reviewed-by: Tony Krowiak Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 12 ++++++++++-- drivers/s390/crypto/ap_queue.c | 4 ++-- drivers/s390/crypto/vfio_ap_ops.c | 2 +- drivers/s390/crypto/zcrypt_cex2c.c | 2 +- 4 files changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index ba8da3f02f35..3442e76d5e3d 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -159,14 +159,18 @@ static inline struct ap_queue_status ap_test_queue(ap_qid_t qid, int tbit, /** * ap_pqap_rapq(): Reset adjunct processor queue. * @qid: The AP queue number + * @fbit: if != 0 set F bit * * Returns AP queue status structure. */ -static inline struct ap_queue_status ap_rapq(ap_qid_t qid) +static inline struct ap_queue_status ap_rapq(ap_qid_t qid, int fbit) { unsigned long reg0 = qid | (1UL << 24); /* fc 1UL is RAPQ */ union ap_queue_status_reg reg1; + if (fbit) + reg0 |= 1UL << 22; + asm volatile( " lgr 0,%[reg0]\n" /* qid arg into gr0 */ " .insn rre,0xb2af0000,0,0\n" /* PQAP(RAPQ) */ @@ -180,14 +184,18 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid) /** * ap_pqap_zapq(): Reset and zeroize adjunct processor queue. * @qid: The AP queue number + * @fbit: if != 0 set F bit * * Returns AP queue status structure. */ -static inline struct ap_queue_status ap_zapq(ap_qid_t qid) +static inline struct ap_queue_status ap_zapq(ap_qid_t qid, int fbit) { unsigned long reg0 = qid | (2UL << 24); /* fc 2UL is ZAPQ */ union ap_queue_status_reg reg1; + if (fbit) + reg0 |= 1UL << 22; + asm volatile( " lgr 0,%[reg0]\n" /* qid arg into gr0 */ " .insn rre,0xb2af0000,0,0\n" /* PQAP(ZAPQ) */ diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 1c08b282987c..8517e1c54149 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -322,7 +322,7 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) { struct ap_queue_status status; - status = ap_rapq(aq->qid); + status = ap_rapq(aq->qid, 0); switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: @@ -936,7 +936,7 @@ void ap_queue_remove(struct ap_queue *aq) * to the initial value AP_DEV_STATE_UNINITIATED. */ spin_lock_bh(&aq->lock); - ap_zapq(aq->qid); + ap_zapq(aq->qid, 0); aq->dev_state = AP_DEV_STATE_UNINITIATED; spin_unlock_bh(&aq->lock); } diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 31de464e4bb2..cfbcb864ab63 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1657,7 +1657,7 @@ static int vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q) if (!q) return 0; retry_zapq: - status = ap_zapq(q->apqn); + status = ap_zapq(q->apqn, 0); q->reset_rc = status.response_code; switch (status.response_code) { case AP_RESPONSE_NORMAL: diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 78f8d68ffcb2..251b5bd3d19c 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -338,7 +338,7 @@ static int zcrypt_cex2c_queue_probe(struct ap_device *ap_dev) zq->queue = aq; zq->online = 1; atomic_set(&zq->load, 0); - ap_rapq(aq->qid); + ap_rapq(aq->qid, 0); rc = zcrypt_cex2c_rng_supported(aq); if (rc < 0) { zcrypt_queue_free(zq); -- GitLab From c81cf436e47c34d2ff29e1b3db296f00d55b1c6f Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 7 Sep 2022 19:05:18 +0200 Subject: [PATCH 0932/5631] s390/ap: new low level inline functions ap_bapq() and ap_aapq() Introduce two new low level functions ap_bapq() (calls PQAP(BAPQ)) and ap_aapq (calls PQAP(AAPQ)). Both functions are only meant to be used in SE environment with the SE AP binding facility available. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 53 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 3442e76d5e3d..92b04d66d69a 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -354,6 +354,59 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, return reg1.status; } +/* + * ap_bapq(): SE bind AP queue. + * @qid: The AP queue number + * + * Returns AP queue status structure. + * + * Invoking this function in a non-SE environment + * may case a specification exception. + */ +static inline struct ap_queue_status ap_bapq(ap_qid_t qid) +{ + unsigned long reg0 = qid | (7UL << 24); /* fc 7 is BAPQ */ + union ap_queue_status_reg reg1; + + asm volatile( + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(BAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + : [reg1] "=&d" (reg1.value) + : [reg0] "d" (reg0) + : "cc", "0", "1"); + + return reg1.status; +} + +/* + * ap_aapq(): SE associate AP queue. + * @qid: The AP queue number + * @sec_idx: The secret index + * + * Returns AP queue status structure. + * + * Invoking this function in a non-SE environment + * may case a specification exception. + */ +static inline struct ap_queue_status ap_aapq(ap_qid_t qid, unsigned int sec_idx) +{ + unsigned long reg0 = qid | (8UL << 24); /* fc 8 is AAPQ */ + unsigned long reg2 = sec_idx; + union ap_queue_status_reg reg1; + + asm volatile( + " lgr 0,%[reg0]\n" /* qid arg into gr0 */ + " lgr 2,%[reg2]\n" /* secret index into gr2 */ + " .insn rre,0xb2af0000,0,0\n" /* PQAP(AAPQ) */ + " lgr %[reg1],1\n" /* gr1 (status) into reg1 */ + : [reg1] "=&d" (reg1.value) + : [reg0] "d" (reg0), [reg2] "d" (reg2) + : "cc", "0", "1", "2"); + + return reg1.status; +} + /** * ap_nqap(): Send message to adjunct processor queue. * @qid: The AP queue number -- GitLab From 263c8454dbffd4b878ea9bb403e157a56de98aca Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 21 Oct 2022 15:41:00 +0200 Subject: [PATCH 0933/5631] s390/ap: introduce low frequency polling possibility For some events the ap bus needs to poll. For example when an AP queue is reset until the reset is through. Also when no interrupt support is available (e.g. zVM) there is a need to poll until all requests have been processed and all replies have been delivered. Polling is done with a high resolution timer by default run with a rate of 4kHz (LPAR) or 666Hz (zVM guest). For some events (wait for reset complete, wait for irq enabled complete) this is a much too high poll rate which triggers a lot of TAPQ invocations. This patch introduces the possibility for the state machine functions to return a new wait enum AP_SM_WAIT_LOW_TIMEOUT which gives a hint to the ap_wait() function to eventually set up the timer with a more relaxed timeout value of 25Hz. This patch also includes a slight rework of the sysfs functions parsing the timer related stuff: Use of kstrtobool and kstrtoul instead of sscanf. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- drivers/s390/crypto/ap_bus.c | 44 +++++++++++++++++++++++----------- drivers/s390/crypto/ap_bus.h | 9 +++---- drivers/s390/crypto/ap_queue.c | 12 +++++----- 3 files changed, 41 insertions(+), 24 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 05e4fe1384a8..35250fd3fa91 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -122,7 +122,13 @@ static struct hrtimer ap_poll_timer; * In LPAR poll with 4kHz frequency. Poll every 250000 nanoseconds. * If z/VM change to 1500000 nanoseconds to adjust to z/VM polling. */ -static unsigned long long poll_timeout = 250000; +static unsigned long poll_high_timeout = 250000UL; + +/* + * Some state machine states only require a low frequency polling. + * We use 25 Hz frequency for these. + */ +static unsigned long poll_low_timeout = 40000000UL; /* Maximum domain id, if not given via qci */ static int ap_max_domain_id = 15; @@ -413,10 +419,13 @@ void ap_wait(enum ap_sm_wait wait) break; } fallthrough; - case AP_SM_WAIT_TIMEOUT: + case AP_SM_WAIT_LOW_TIMEOUT: + case AP_SM_WAIT_HIGH_TIMEOUT: spin_lock_bh(&ap_poll_timer_lock); if (!hrtimer_is_queued(&ap_poll_timer)) { - hr_time = poll_timeout; + hr_time = + wait == AP_SM_WAIT_LOW_TIMEOUT ? + poll_low_timeout : poll_high_timeout; hrtimer_forward_now(&ap_poll_timer, hr_time); hrtimer_restart(&ap_poll_timer); } @@ -1270,11 +1279,14 @@ static ssize_t poll_thread_show(struct bus_type *bus, char *buf) static ssize_t poll_thread_store(struct bus_type *bus, const char *buf, size_t count) { - int flag, rc; + bool value; + int rc; - if (sscanf(buf, "%d\n", &flag) != 1) - return -EINVAL; - if (flag) { + rc = kstrtobool(buf, &value); + if (rc) + return rc; + + if (value) { rc = ap_poll_thread_start(); if (rc) count = rc; @@ -1288,21 +1300,25 @@ static BUS_ATTR_RW(poll_thread); static ssize_t poll_timeout_show(struct bus_type *bus, char *buf) { - return sysfs_emit(buf, "%llu\n", poll_timeout); + return sysfs_emit(buf, "%lu\n", poll_high_timeout); } static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf, size_t count) { - unsigned long long time; + unsigned long value; ktime_t hr_time; + int rc; + + rc = kstrtoul(buf, 0, &value); + if (rc) + return rc; /* 120 seconds = maximum poll interval */ - if (sscanf(buf, "%llu\n", &time) != 1 || time < 1 || - time > 120000000000ULL) + if (value > 120000000000UL) return -EINVAL; - poll_timeout = time; - hr_time = poll_timeout; + poll_high_timeout = value; + hr_time = poll_high_timeout; spin_lock_bh(&ap_poll_timer_lock); hrtimer_cancel(&ap_poll_timer); @@ -2265,7 +2281,7 @@ static int __init ap_module_init(void) * If we are running under z/VM adjust polling to z/VM polling rate. */ if (MACHINE_IS_VM) - poll_timeout = 1500000; + poll_high_timeout = 1500000; hrtimer_init(&ap_poll_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ap_poll_timer.function = ap_poll_timeout; diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index f09a3fd4d7bd..f14323c278a3 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -108,10 +108,11 @@ enum ap_sm_event { * AP queue state wait behaviour */ enum ap_sm_wait { - AP_SM_WAIT_AGAIN = 0, /* retry immediately */ - AP_SM_WAIT_TIMEOUT, /* wait for timeout */ - AP_SM_WAIT_INTERRUPT, /* wait for thin interrupt (if available) */ - AP_SM_WAIT_NONE, /* no wait */ + AP_SM_WAIT_AGAIN = 0, /* retry immediately */ + AP_SM_WAIT_HIGH_TIMEOUT, /* poll high freq, wait for timeout */ + AP_SM_WAIT_LOW_TIMEOUT, /* poll low freq, wait for timeout */ + AP_SM_WAIT_INTERRUPT, /* wait for thin interrupt (if available) */ + AP_SM_WAIT_NONE, /* no wait */ NR_AP_SM_WAIT }; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 8517e1c54149..60dbabec25cf 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -221,7 +221,7 @@ static enum ap_sm_wait ap_sm_read(struct ap_queue *aq) case AP_RESPONSE_NO_PENDING_REPLY: if (aq->queue_count > 0) return aq->interrupt ? - AP_SM_WAIT_INTERRUPT : AP_SM_WAIT_TIMEOUT; + AP_SM_WAIT_INTERRUPT : AP_SM_WAIT_HIGH_TIMEOUT; aq->sm_state = AP_SM_STATE_IDLE; return AP_SM_WAIT_NONE; default: @@ -277,10 +277,10 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) case AP_RESPONSE_Q_FULL: aq->sm_state = AP_SM_STATE_QUEUE_FULL; return aq->interrupt ? - AP_SM_WAIT_INTERRUPT : AP_SM_WAIT_TIMEOUT; + AP_SM_WAIT_INTERRUPT : AP_SM_WAIT_HIGH_TIMEOUT; case AP_RESPONSE_RESET_IN_PROGRESS: aq->sm_state = AP_SM_STATE_RESET_WAIT; - return AP_SM_WAIT_TIMEOUT; + return AP_SM_WAIT_LOW_TIMEOUT; case AP_RESPONSE_INVALID_DOMAIN: AP_DBF_WARN("%s RESPONSE_INVALID_DOMAIN on NQAP\n", __func__); fallthrough; @@ -328,7 +328,7 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) case AP_RESPONSE_RESET_IN_PROGRESS: aq->sm_state = AP_SM_STATE_RESET_WAIT; aq->interrupt = false; - return AP_SM_WAIT_TIMEOUT; + return AP_SM_WAIT_LOW_TIMEOUT; default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; @@ -368,7 +368,7 @@ static enum ap_sm_wait ap_sm_reset_wait(struct ap_queue *aq) return AP_SM_WAIT_AGAIN; case AP_RESPONSE_BUSY: case AP_RESPONSE_RESET_IN_PROGRESS: - return AP_SM_WAIT_TIMEOUT; + return AP_SM_WAIT_LOW_TIMEOUT; case AP_RESPONSE_Q_NOT_AVAIL: case AP_RESPONSE_DECONFIGURED: case AP_RESPONSE_CHECKSTOPPED: @@ -412,7 +412,7 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq) return AP_SM_WAIT_AGAIN; fallthrough; case AP_RESPONSE_NO_PENDING_REPLY: - return AP_SM_WAIT_TIMEOUT; + return AP_SM_WAIT_LOW_TIMEOUT; default: aq->dev_state = AP_DEV_STATE_ERROR; aq->last_err_rc = status.response_code; -- GitLab From 2d72eaf036d2f2b7ec16cda2d0e7ce292537dad9 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 10 Mar 2023 17:46:49 +0100 Subject: [PATCH 0934/5631] s390/ap: implement SE AP bind, unbind and associate Implementation of the new functions for SE AP support: bind, unbind and associate. There are two new sysfs attributes for this: /sys/devices/ap/cardxx/xx.yyyy/se_bind /sys/devices/ap/cardxx/xx.yyyy/se_associate Writing a 1 into the se_bind attribute triggers the SE AP bind for this AP queue, writing a 0 into does an unbind - that's a reset (RAPQ) with the F bit enabled. The se_associate attribute needs an integer value in range 0...2^16-1 written in. This is the index into a secrets table feed into the ultravisor. For more details please see the Architecture documents. These both new ap queue attributes are only visible inside a SE guest with SB (Secure Binding) available. Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- arch/s390/include/asm/ap.h | 13 +- drivers/s390/crypto/ap_bus.h | 46 ++++-- drivers/s390/crypto/ap_queue.c | 262 ++++++++++++++++++++++++++++++++- 3 files changed, 302 insertions(+), 19 deletions(-) diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 92b04d66d69a..d5d967166bac 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -43,10 +43,11 @@ struct ap_queue_status { unsigned int queue_empty : 1; unsigned int replies_waiting : 1; unsigned int queue_full : 1; - unsigned int _pad1 : 4; + unsigned int : 3; + unsigned int async : 1; unsigned int irq_enabled : 1; unsigned int response_code : 8; - unsigned int _pad2 : 16; + unsigned int : 16; }; /* @@ -114,6 +115,14 @@ struct ap_tapq_gr2 { }; }; +/* + * Convenience defines to be used with the bs field from struct ap_tapq_gr2 + */ +#define AP_BS_Q_USABLE 0 +#define AP_BS_Q_USABLE_NO_SECURE_KEY 1 +#define AP_BS_Q_AVAIL_FOR_BINDING 2 +#define AP_BS_Q_UNUSABLE 3 + /** * ap_tapq(): Test adjunct processor queue. * @qid: The AP queue number diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index f14323c278a3..101fb324476f 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -39,22 +39,32 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr) return (*ptr & (0x80000000u >> nr)) != 0; } -#define AP_RESPONSE_NORMAL 0x00 -#define AP_RESPONSE_Q_NOT_AVAIL 0x01 -#define AP_RESPONSE_RESET_IN_PROGRESS 0x02 -#define AP_RESPONSE_DECONFIGURED 0x03 -#define AP_RESPONSE_CHECKSTOPPED 0x04 -#define AP_RESPONSE_BUSY 0x05 -#define AP_RESPONSE_INVALID_ADDRESS 0x06 -#define AP_RESPONSE_OTHERWISE_CHANGED 0x07 -#define AP_RESPONSE_INVALID_GISA 0x08 -#define AP_RESPONSE_Q_FULL 0x10 -#define AP_RESPONSE_NO_PENDING_REPLY 0x10 -#define AP_RESPONSE_INDEX_TOO_BIG 0x11 -#define AP_RESPONSE_NO_FIRST_PART 0x13 -#define AP_RESPONSE_MESSAGE_TOO_BIG 0x15 -#define AP_RESPONSE_REQ_FAC_NOT_INST 0x16 -#define AP_RESPONSE_INVALID_DOMAIN 0x42 +#define AP_RESPONSE_NORMAL 0x00 +#define AP_RESPONSE_Q_NOT_AVAIL 0x01 +#define AP_RESPONSE_RESET_IN_PROGRESS 0x02 +#define AP_RESPONSE_DECONFIGURED 0x03 +#define AP_RESPONSE_CHECKSTOPPED 0x04 +#define AP_RESPONSE_BUSY 0x05 +#define AP_RESPONSE_INVALID_ADDRESS 0x06 +#define AP_RESPONSE_OTHERWISE_CHANGED 0x07 +#define AP_RESPONSE_INVALID_GISA 0x08 +#define AP_RESPONSE_Q_BOUND_TO_ANOTHER 0x09 +#define AP_RESPONSE_STATE_CHANGE_IN_PROGRESS 0x0A +#define AP_RESPONSE_Q_NOT_BOUND 0x0B +#define AP_RESPONSE_Q_FULL 0x10 +#define AP_RESPONSE_NO_PENDING_REPLY 0x10 +#define AP_RESPONSE_INDEX_TOO_BIG 0x11 +#define AP_RESPONSE_NO_FIRST_PART 0x13 +#define AP_RESPONSE_MESSAGE_TOO_BIG 0x15 +#define AP_RESPONSE_REQ_FAC_NOT_INST 0x16 +#define AP_RESPONSE_Q_BIND_ERROR 0x30 +#define AP_RESPONSE_Q_NOT_AVAIL_FOR_ASSOC 0x31 +#define AP_RESPONSE_Q_NOT_EMPTY 0x32 +#define AP_RESPONSE_BIND_LIMIT_EXCEEDED 0x33 +#define AP_RESPONSE_INVALID_ASSOC_SECRET 0x34 +#define AP_RESPONSE_ASSOC_SECRET_NOT_UNIQUE 0x35 +#define AP_RESPONSE_ASSOC_FAILED 0x36 +#define AP_RESPONSE_INVALID_DOMAIN 0x42 /* * Known device types @@ -92,6 +102,7 @@ enum ap_sm_state { AP_SM_STATE_IDLE, AP_SM_STATE_WORKING, AP_SM_STATE_QUEUE_FULL, + AP_SM_STATE_ASSOC_WAIT, NR_AP_SM_STATES }; @@ -189,6 +200,7 @@ struct ap_card { }; #define TAPQ_CARD_FUNC_CMP_MASK 0xFFFF0000 +#define ASSOC_IDX_INVALID 0x10000 #define to_ap_card(x) container_of((x), struct ap_card, ap_dev.device) @@ -202,6 +214,7 @@ struct ap_queue { bool chkstop; /* checkstop state */ ap_qid_t qid; /* AP queue id. */ bool interrupt; /* indicate if interrupts are enabled */ + unsigned int assoc_idx; /* SE association index */ int queue_count; /* # messages currently on AP queue. */ int pendingq_count; /* # requests on pendingq list. */ int requestq_count; /* # requests on requestq list. */ @@ -212,6 +225,7 @@ struct ap_queue { struct list_head requestq; /* List of message yet to be sent. */ struct ap_message *reply; /* Per device reply message. */ enum ap_sm_state sm_state; /* ap queue state machine state */ + int rapq_fbit; /* fbit arg for next rapq invocation */ int last_err_rc; /* last error state response code */ }; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 60dbabec25cf..2be63f2554bd 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -18,6 +18,21 @@ static void __ap_flush_queue(struct ap_queue *aq); +/* + * some AP queue helper functions + */ + +static inline bool ap_q_supports_bind(struct ap_queue *aq) +{ + return ap_test_bit(&aq->card->functions, AP_FUNC_EP11) || + ap_test_bit(&aq->card->functions, AP_FUNC_ACCEL); +} + +static inline bool ap_q_supports_assoc(struct ap_queue *aq) +{ + return ap_test_bit(&aq->card->functions, AP_FUNC_EP11); +} + /** * ap_queue_enable_irq(): Enable interrupt support on this AP queue. * @aq: The AP queue @@ -322,12 +337,13 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) { struct ap_queue_status status; - status = ap_rapq(aq->qid, 0); + status = ap_rapq(aq->qid, aq->rapq_fbit); switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: aq->sm_state = AP_SM_STATE_RESET_WAIT; aq->interrupt = false; + aq->rapq_fbit = 0; return AP_SM_WAIT_LOW_TIMEOUT; default: aq->dev_state = AP_DEV_STATE_ERROR; @@ -423,6 +439,59 @@ static enum ap_sm_wait ap_sm_setirq_wait(struct ap_queue *aq) } } +/** + * ap_sm_assoc_wait(): Test queue for completion of a pending + * association request. + * @aq: pointer to the AP queue + */ +static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq) +{ + struct ap_queue_status status; + struct ap_tapq_gr2 info; + + status = ap_test_queue(aq->qid, 1, &info); + /* handle asynchronous error on this queue */ + if (status.async && status.response_code) { + aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s asynch RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return AP_SM_WAIT_NONE; + } + if (status.response_code > AP_RESPONSE_BUSY) { + aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s RC 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return AP_SM_WAIT_NONE; + } + + /* check bs bits */ + switch (info.bs) { + case AP_BS_Q_USABLE: + /* association is through */ + aq->sm_state = AP_SM_STATE_IDLE; + AP_DBF_DBG("%s queue 0x%02x.%04x associated with %u\n", + __func__, AP_QID_CARD(aq->qid), + AP_QID_QUEUE(aq->qid), aq->assoc_idx); + return AP_SM_WAIT_NONE; + case AP_BS_Q_USABLE_NO_SECURE_KEY: + /* association still pending */ + return AP_SM_WAIT_LOW_TIMEOUT; + default: + /* reset from 'outside' happened or no idea at all */ + aq->assoc_idx = ASSOC_IDX_INVALID; + aq->dev_state = AP_DEV_STATE_ERROR; + aq->last_err_rc = status.response_code; + AP_DBF_WARN("%s bs 0x%02x on 0x%02x.%04x -> AP_DEV_STATE_ERROR\n", + __func__, info.bs, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return AP_SM_WAIT_NONE; + } +} + /* * AP state machine jump table */ @@ -451,6 +520,10 @@ static ap_func_t *ap_jumptable[NR_AP_SM_STATES][NR_AP_SM_EVENTS] = { [AP_SM_EVENT_POLL] = ap_sm_read, [AP_SM_EVENT_TIMEOUT] = ap_sm_reset, }, + [AP_SM_STATE_ASSOC_WAIT] = { + [AP_SM_EVENT_POLL] = ap_sm_assoc_wait, + [AP_SM_EVENT_TIMEOUT] = ap_sm_reset, + }, }; enum ap_sm_wait ap_sm_event(struct ap_queue *aq, enum ap_sm_event event) @@ -696,6 +769,9 @@ static ssize_t states_show(struct device *dev, case AP_SM_STATE_QUEUE_FULL: rc += sysfs_emit_at(buf, rc, " [FULL]\n"); break; + case AP_SM_STATE_ASSOC_WAIT: + rc += sysfs_emit_at(buf, rc, " [ASSOC_WAIT]\n"); + break; default: rc += sysfs_emit_at(buf, rc, " [UNKNOWN]\n"); } @@ -780,6 +856,186 @@ static struct device_type ap_queue_type = { .groups = ap_queue_dev_attr_groups, }; +static ssize_t se_bind_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + struct ap_queue_status status; + struct ap_tapq_gr2 info; + + if (!ap_q_supports_bind(aq)) + return sysfs_emit(buf, "-\n"); + + status = ap_test_queue(aq->qid, 1, &info); + if (status.response_code > AP_RESPONSE_BUSY) { + AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return -EIO; + } + switch (info.bs) { + case AP_BS_Q_USABLE: + case AP_BS_Q_USABLE_NO_SECURE_KEY: + return sysfs_emit(buf, "bound\n"); + default: + return sysfs_emit(buf, "unbound\n"); + } +} + +static ssize_t se_bind_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ap_queue *aq = to_ap_queue(dev); + struct ap_queue_status status; + bool value; + int rc; + + if (!ap_q_supports_bind(aq)) + return -EINVAL; + + /* only 0 (unbind) and 1 (bind) allowed */ + rc = kstrtobool(buf, &value); + if (rc) + return rc; + + if (value) { + /* bind, do BAPQ */ + spin_lock_bh(&aq->lock); + if (aq->sm_state < AP_SM_STATE_IDLE) { + spin_unlock_bh(&aq->lock); + return -EBUSY; + } + status = ap_bapq(aq->qid); + spin_unlock_bh(&aq->lock); + if (status.response_code) { + AP_DBF_WARN("%s RC 0x%02x on bapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), + AP_QID_QUEUE(aq->qid)); + return -EIO; + } + } else { + /* unbind, set F bit arg and trigger RAPQ */ + spin_lock_bh(&aq->lock); + __ap_flush_queue(aq); + aq->rapq_fbit = 1; + aq->assoc_idx = ASSOC_IDX_INVALID; + aq->sm_state = AP_SM_STATE_RESET_START; + ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL)); + spin_unlock_bh(&aq->lock); + } + + return count; +} + +static DEVICE_ATTR_RW(se_bind); + +static ssize_t se_associate_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ap_queue *aq = to_ap_queue(dev); + struct ap_queue_status status; + struct ap_tapq_gr2 info; + + if (!ap_q_supports_assoc(aq)) + return sysfs_emit(buf, "-\n"); + + status = ap_test_queue(aq->qid, 1, &info); + if (status.response_code > AP_RESPONSE_BUSY) { + AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return -EIO; + } + + switch (info.bs) { + case AP_BS_Q_USABLE: + if (aq->assoc_idx == ASSOC_IDX_INVALID) { + AP_DBF_WARN("%s AP_BS_Q_USABLE but invalid assoc_idx\n", __func__); + return -EIO; + } + return sysfs_emit(buf, "associated %u\n", aq->assoc_idx); + case AP_BS_Q_USABLE_NO_SECURE_KEY: + if (aq->assoc_idx != ASSOC_IDX_INVALID) + return sysfs_emit(buf, "association pending\n"); + fallthrough; + default: + return sysfs_emit(buf, "unassociated\n"); + } +} + +static ssize_t se_associate_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ap_queue *aq = to_ap_queue(dev); + struct ap_queue_status status; + unsigned int value; + int rc; + + if (!ap_q_supports_assoc(aq)) + return -EINVAL; + + /* association index needs to be >= 0 */ + rc = kstrtouint(buf, 0, &value); + if (rc) + return rc; + if (value >= ASSOC_IDX_INVALID) + return -EINVAL; + + spin_lock_bh(&aq->lock); + + /* sm should be in idle state */ + if (aq->sm_state != AP_SM_STATE_IDLE) { + spin_unlock_bh(&aq->lock); + return -EBUSY; + } + + /* already associated or association pending ? */ + if (aq->assoc_idx != ASSOC_IDX_INVALID) { + spin_unlock_bh(&aq->lock); + return -EINVAL; + } + + /* trigger the asynchronous association request */ + status = ap_aapq(aq->qid, value); + switch (status.response_code) { + case AP_RESPONSE_NORMAL: + case AP_RESPONSE_STATE_CHANGE_IN_PROGRESS: + aq->sm_state = AP_SM_STATE_ASSOC_WAIT; + aq->assoc_idx = value; + ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL)); + spin_unlock_bh(&aq->lock); + break; + default: + spin_unlock_bh(&aq->lock); + AP_DBF_WARN("%s RC 0x%02x on aapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + return -EIO; + } + + return count; +} + +static DEVICE_ATTR_RW(se_associate); + +static struct attribute *ap_queue_dev_sb_attrs[] = { + &dev_attr_se_bind.attr, + &dev_attr_se_associate.attr, + NULL +}; + +static struct attribute_group ap_queue_dev_sb_attr_group = { + .attrs = ap_queue_dev_sb_attrs +}; + +static const struct attribute_group *ap_queue_dev_sb_attr_groups[] = { + &ap_queue_dev_sb_attr_group, + NULL +}; + static void ap_queue_device_release(struct device *dev) { struct ap_queue *aq = to_ap_queue(dev); @@ -801,6 +1057,9 @@ struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type) aq->ap_dev.device.release = ap_queue_device_release; aq->ap_dev.device.type = &ap_queue_type; aq->ap_dev.device_type = device_type; + // add optional SE secure binding attributes group + if (ap_sb_available() && is_prot_virt_guest()) + aq->ap_dev.device.groups = ap_queue_dev_sb_attr_groups; aq->qid = qid; aq->interrupt = false; spin_lock_init(&aq->lock); @@ -947,6 +1206,7 @@ void ap_queue_init_state(struct ap_queue *aq) aq->dev_state = AP_DEV_STATE_OPERATING; aq->sm_state = AP_SM_STATE_RESET_START; aq->last_err_rc = 0; + aq->assoc_idx = ASSOC_IDX_INVALID; ap_wait(ap_sm_event(aq, AP_SM_EVENT_POLL)); spin_unlock_bh(&aq->lock); } -- GitLab From 038c5bedbc313b55f66b26fda5a7808727c2f177 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 15 Feb 2023 15:08:15 +0100 Subject: [PATCH 0935/5631] s390/ap: add ap status asynch error support Review and extend the low level AP code to be able to deal with asynchronous reported errors on APQNs. The hypervisor and the SE guest may be confronted with an asynchronously reported error at return of an AP instruction. So all places where AP instructions are called need review and may eventually need extensions. However, not all places need rework. As together with the AP status and the enabled asynch bit there is always a response code set. The asynch error reporting comes with new response codes which may be simple handled in the default case of a switch statement. The idea behind this patch is to report asynch errors as -EPERM (read this as "Operation not permitted") which reflects the fact that only a rapq (with F bit enabled) is a valid AP instruction when an asynch error is flagged. The AP queue state machine functions return AP_SM_WAIT_NONE when a asynch error is detected to reflect the fact, that the state machine can't do anything with such an error as long as the queue is reset. Unfortunately the ap bus scan function needed some update as the ap_queue_info() now needs to return 3 states: 1 if an APQN exists and info is available, -1 if it is assumed an APQN does not exist and the new return value 0 without any info values filled. This 0 returncode is handled as "there is an APQN but we currently don't know any more hw info about this, so please use your previous info and try again later". Signed-off-by: Harald Freudenberger Reviewed-by: Holger Dengler Signed-off-by: Heiko Carstens --- drivers/s390/crypto/ap_bus.c | 62 ++++++++++++++++++++-------------- drivers/s390/crypto/ap_queue.c | 12 +++++++ 2 files changed, 49 insertions(+), 25 deletions(-) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 35250fd3fa91..70855af8c281 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -342,11 +342,14 @@ EXPORT_SYMBOL(ap_test_config_ctrl_domain); /* * ap_queue_info(): Check and get AP queue info. - * Returns true if TAPQ succeeded and the info is filled or - * false otherwise. + * Returns: 1 if APQN exists and info is filled, + * 0 if APQN seems to exit but there is no info + * available (eg. caused by an asynch pending error) + * -1 invalid APQN, TAPQ error or AP queue status which + * indicates there is no APQN. */ -static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, - int *q_depth, int *q_ml, bool *q_decfg, bool *q_cstop) +static int ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, + int *q_depth, int *q_ml, bool *q_decfg, bool *q_cstop) { struct ap_queue_status status; struct ap_tapq_gr2 tapq_info; @@ -356,10 +359,15 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, /* make sure we don't run into a specifiation exception */ if (AP_QID_CARD(qid) > ap_max_adapter_id || AP_QID_QUEUE(qid) > ap_max_domain_id) - return false; + return -1; /* call TAPQ on this APQN */ status = ap_test_queue(qid, ap_apft_available(), &tapq_info); + + /* handle pending async error with return 'no info available' */ + if (status.async) + return 0; + switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: @@ -372,7 +380,7 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, * there is at least one of the mode bits set. */ if (WARN_ON_ONCE(!tapq_info.value)) - return false; + return 0; *q_type = tapq_info.at; *q_fac = tapq_info.fac; *q_depth = tapq_info.qd; @@ -396,12 +404,12 @@ static bool ap_queue_info(ap_qid_t qid, int *q_type, unsigned int *q_fac, default: break; } - return true; + return 1; default: /* * A response code which indicates, there is no info available. */ - return false; + return -1; } } @@ -1798,12 +1806,12 @@ static inline void ap_scan_rm_card_dev_and_queue_devs(struct ap_card *ac) */ static inline void ap_scan_domains(struct ap_card *ac) { + int rc, dom, depth, type, ml; bool decfg, chkstop; - ap_qid_t qid; - unsigned int func; - struct device *dev; struct ap_queue *aq; - int rc, dom, depth, type, ml; + struct device *dev; + unsigned int func; + ap_qid_t qid; /* * Go through the configuration for the domains and compare them @@ -1822,20 +1830,24 @@ static inline void ap_scan_domains(struct ap_card *ac) AP_DBF_INFO("%s(%d,%d) not in config anymore, rm queue dev\n", __func__, ac->id, dom); device_unregister(dev); - put_device(dev); } - continue; + goto put_dev_and_continue; } /* domain is valid, get info from this APQN */ - if (!ap_queue_info(qid, &type, &func, &depth, - &ml, &decfg, &chkstop)) { - if (aq) { + rc = ap_queue_info(qid, &type, &func, &depth, + &ml, &decfg, &chkstop); + switch (rc) { + case -1: + if (dev) { AP_DBF_INFO("%s(%d,%d) queue_info() failed, rm queue dev\n", __func__, ac->id, dom); device_unregister(dev); - put_device(dev); } - continue; + fallthrough; + case 0: + goto put_dev_and_continue; + default: + break; } /* if no queue device exists, create a new one */ if (!aq) { @@ -1951,12 +1963,12 @@ static inline void ap_scan_domains(struct ap_card *ac) */ static inline void ap_scan_adapter(int ap) { + int rc, dom, depth, type, comp_type, ml; bool decfg, chkstop; - ap_qid_t qid; - unsigned int func; - struct device *dev; struct ap_card *ac; - int rc, dom, depth, type, comp_type, ml; + struct device *dev; + unsigned int func; + ap_qid_t qid; /* Is there currently a card device for this adapter ? */ dev = bus_find_device(&ap_bus_type, NULL, @@ -1986,11 +1998,11 @@ static inline void ap_scan_adapter(int ap) if (ap_test_config_usage_domain(dom)) { qid = AP_MKQID(ap, dom); if (ap_queue_info(qid, &type, &func, &depth, - &ml, &decfg, &chkstop)) + &ml, &decfg, &chkstop) > 0) break; } if (dom > ap_max_domain_id) { - /* Could not find a valid APQN for this adapter */ + /* Could not find one valid APQN for this adapter */ if (ac) { AP_DBF_INFO("%s(%d) no type info (no APQN found), rm card and queue devs\n", __func__, ap); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 2be63f2554bd..ed8f813653fe 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -50,6 +50,8 @@ static int ap_queue_enable_irq(struct ap_queue *aq, void *ind) qirqctrl.ir = 1; qirqctrl.isc = AP_ISC; status = ap_aqic(aq->qid, qirqctrl, virt_to_phys(ind)); + if (status.async) + return -EPERM; switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_OTHERWISE_CHANGED: @@ -96,6 +98,8 @@ int ap_send(ap_qid_t qid, unsigned long psmid, void *msg, size_t msglen) struct ap_queue_status status; status = __ap_send(qid, psmid, msg, msglen, 0); + if (status.async) + return -EPERM; switch (status.response_code) { case AP_RESPONSE_NORMAL: return 0; @@ -117,6 +121,8 @@ int ap_recv(ap_qid_t qid, unsigned long *psmid, void *msg, size_t msglen) if (!msg) return -EINVAL; status = ap_dqap(qid, psmid, msg, msglen, NULL, NULL, NULL); + if (status.async) + return -EPERM; switch (status.response_code) { case AP_RESPONSE_NORMAL: return 0; @@ -225,6 +231,8 @@ static enum ap_sm_wait ap_sm_read(struct ap_queue *aq) if (!aq->reply) return AP_SM_WAIT_NONE; status = ap_sm_recv(aq); + if (status.async) + return AP_SM_WAIT_NONE; switch (status.response_code) { case AP_RESPONSE_NORMAL: if (aq->queue_count > 0) { @@ -276,6 +284,8 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) status = __ap_send(qid, ap_msg->psmid, ap_msg->msg, ap_msg->len, ap_msg->flags & AP_MSG_FLAG_SPECIAL); + if (status.async) + return AP_SM_WAIT_NONE; switch (status.response_code) { case AP_RESPONSE_NORMAL: aq->queue_count = max_t(int, 1, aq->queue_count + 1); @@ -338,6 +348,8 @@ static enum ap_sm_wait ap_sm_reset(struct ap_queue *aq) struct ap_queue_status status; status = ap_rapq(aq->qid, aq->rapq_fbit); + if (status.async) + return AP_SM_WAIT_NONE; switch (status.response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_RESET_IN_PROGRESS: -- GitLab From d28d86a07dbca4b6e33032196ef4a9a7121181b4 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 17 Mar 2023 14:51:41 +0100 Subject: [PATCH 0936/5631] s390/mm: make use of atomic_fetch_xor() Make use of atomic_fetch_xor() instead of an atomic_cmpxchg() loop to implement atomic_xor_bits() (aka atomic_xor_return()). This makes the C code more readable and in addition generates better code, since for z196 and newer a single lax instruction is generated instead of a cmpxchg() loop. Signed-off-by: Heiko Carstens --- arch/s390/mm/pgalloc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 0f68b7257e08..66ab68db9842 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -133,13 +133,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits) { - unsigned int old, new; - - do { - old = atomic_read(v); - new = old ^ bits; - } while (atomic_cmpxchg(v, old, new) != old); - return new; + return atomic_fetch_xor(bits, v) ^ bits; } #ifdef CONFIG_PGSTE -- GitLab From 25b800631773163a0bbf8b761d7ea4f921f3cfba Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:54 +0100 Subject: [PATCH 0937/5631] dt-bindings: power: supply: adc-battery: add binding Add binding for a battery that is only monitored via ADC channels and simple status GPIOs. Reviewed-by: Matti Vaittinen Reviewed-by: Krzysztof Kozlowski Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- .../bindings/power/supply/adc-battery.yaml | 70 +++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 Documentation/devicetree/bindings/power/supply/adc-battery.yaml diff --git a/Documentation/devicetree/bindings/power/supply/adc-battery.yaml b/Documentation/devicetree/bindings/power/supply/adc-battery.yaml new file mode 100644 index 000000000000..ed9702caedff --- /dev/null +++ b/Documentation/devicetree/bindings/power/supply/adc-battery.yaml @@ -0,0 +1,70 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/power/supply/adc-battery.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ADC battery + +maintainers: + - Sebastian Reichel + +description: + Basic battery capacity meter, which only reports basic battery data + via ADC channels and optionally indicate that the battery is full by + polling a GPIO line. + + The voltage is expected to be measured between the battery terminals + and mandatory. The optional current/power channel is expected to + monitor the current/power flowing out of the battery. Last but not + least the temperature channel is supposed to measure the battery + temperature. + +allOf: + - $ref: power-supply.yaml# + +properties: + compatible: + const: adc-battery + + charged-gpios: + description: + GPIO which signals that the battery is fully charged. The GPIO is + often provided by charger ICs, that are not software controllable. + maxItems: 1 + + io-channels: + minItems: 1 + maxItems: 4 + + io-channel-names: + minItems: 1 + items: + - const: voltage + - enum: [ current, power, temperature ] + - enum: [ power, temperature ] + - const: temperature + + monitored-battery: true + +required: + - compatible + - io-channels + - io-channel-names + - monitored-battery + +unevaluatedProperties: false + +examples: + - | + #include + + fuel-gauge { + compatible = "adc-battery"; + charged-gpios = <&gpio 42 GPIO_ACTIVE_HIGH>; + io-channels = <&adc 13>, <&adc 37>; + io-channel-names = "voltage", "current"; + + power-supplies = <&charger>; + monitored-battery = <&battery>; + }; -- GitLab From 458aa82041ce3cd46ff5f9afd078f62a683daa28 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 8 Mar 2023 13:54:22 +0530 Subject: [PATCH 0938/5631] phy: qcom-qmp-pcie: Split out EP related init sequence for SDX55 In preparation for adding RC support, let's split out the EP related init sequence so that the common sequence could be reused by RC as well. Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230308082424.140224-12-manivannan.sadhasivam@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 42 ++++++++++++++++-------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 5182aeac43ee..35328e998699 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -1130,10 +1130,25 @@ static const struct qmp_phy_init_tbl sm8250_qmp_gen3x2_pcie_pcs_misc_tbl[] = { }; static const struct qmp_phy_init_tbl sdx55_qmp_pcie_serdes_tbl[] = { - QMP_PHY_INIT_CFG(QSERDES_V4_COM_BG_TIMER, 0x02), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIAS_EN_CLKBUFLR_EN, 0x18), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYS_CLK_CTRL, 0x07), QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_IVCO, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP_EN, 0x46), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP_CFG, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_TUNE_MAP, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_SEL, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_HS_SWITCH_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CORECLK_DIV_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MISC1, 0x88), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MISC2, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MODE, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_DC_LEVEL_CTRL, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL, 0x22), +}; + +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BG_TIMER, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYS_CLK_CTRL, 0x07), QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE0, 0x0a), QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE1, 0x0a), QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_RCTRL_MODE0, 0x19), @@ -1141,8 +1156,6 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE0, 0x03), QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE1, 0x03), QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP_EN, 0x46), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP_CFG, 0x04), QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE0, 0x7f), QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP2_MODE0, 0x02), QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE1, 0xff), @@ -1154,21 +1167,11 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_INTEGLOOP_GAIN1_MODE0, 0x01), QMP_PHY_INIT_CFG(QSERDES_V4_COM_INTEGLOOP_GAIN0_MODE1, 0xfb), QMP_PHY_INIT_CFG(QSERDES_V4_COM_INTEGLOOP_GAIN1_MODE1, 0x01), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_TUNE_MAP, 0x02), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_SEL, 0x12), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_HS_SWITCH_SEL, 0x00), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_CORECLK_DIV_MODE0, 0x05), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_CORECLK_DIV_MODE1, 0x04), QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_CONFIG, 0x04), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MISC1, 0x88), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MISC2, 0x03), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_CMN_MODE, 0x17), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_VCO_DC_LEVEL_CTRL, 0x0b), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0x56), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1d), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0x4b), QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1f), - QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL, 0x22), }; static const struct qmp_phy_init_tbl sdx55_qmp_pcie_tx_tbl[] = { @@ -1220,6 +1223,9 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_G4_RXEQEVAL_TIME, 0x13), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG2, 0x01), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02), +}; + +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; @@ -2301,6 +2307,14 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = { .pcs_misc = sdx55_qmp_pcie_pcs_misc_tbl, .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_pcs_misc_tbl), }, + + .tbls_ep = &(const struct qmp_phy_cfg_tbls) { + .serdes = sdx55_qmp_pcie_ep_serdes_tbl, + .serdes_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_serdes_tbl), + .pcs_misc = sdx55_qmp_pcie_ep_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_misc_tbl), + }, + .clk_list = sdm845_pciephy_clk_l, .num_clks = ARRAY_SIZE(sdm845_pciephy_clk_l), .reset_list = sdm845_pciephy_reset_l, -- GitLab From 364c748d5e085a4cf425bbca90482e8df77d022e Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Wed, 8 Mar 2023 13:54:23 +0530 Subject: [PATCH 0939/5631] phy: qcom-qmp-pcie: Add RC init sequence for SDX55 Add PCIe RC init sequence making use of the common init sequence. The RC mode additionally requires REFCLK_DRV_DSBL bit to set during powerup and powerdown. Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230308082424.140224-13-manivannan.sadhasivam@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 49 ++++++++++++++++++- .../qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h | 2 + 2 files changed, 50 insertions(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 35328e998699..d671748bc097 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -1146,6 +1146,41 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_HSCLK_SEL, 0x22), }; +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_rc_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_STEP_SIZE1_MODE0, 0xce), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_STEP_SIZE2_MODE0, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_STEP_SIZE1_MODE1, 0x97), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SSC_STEP_SIZE2_MODE1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CLK_ENABLE1, 0x90), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CLK_EP_DIV_MODE0, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CLK_EP_DIV_MODE1, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CP_CTRL_MODE1, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP2_MODE0, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP1_MODE1, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_LOCK_CMP2_MODE1, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DEC_START_MODE0, 0xc3), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DEC_START_MODE1, 0xd0), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DIV_FRAC_START3_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DIV_FRAC_START1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DIV_FRAC_START2_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_DIV_FRAC_START3_MODE1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_CLK_SELECT, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xca), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xd8), + QMP_PHY_INIT_CFG(QSERDES_V4_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x20), +}; + static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_BG_TIMER, 0x02), QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYS_CLK_CTRL, 0x07), @@ -1225,6 +1260,11 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02), }; +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_rc_pcs_misc_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1), + QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00), +}; + static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), @@ -2308,6 +2348,13 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = { .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_pcs_misc_tbl), }, + .tbls_rc = &(const struct qmp_phy_cfg_tbls) { + .serdes = sdx55_qmp_pcie_rc_serdes_tbl, + .serdes_num = ARRAY_SIZE(sdx55_qmp_pcie_rc_serdes_tbl), + .pcs_misc = sdx55_qmp_pcie_rc_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_rc_pcs_misc_tbl), + }, + .tbls_ep = &(const struct qmp_phy_cfg_tbls) { .serdes = sdx55_qmp_pcie_ep_serdes_tbl, .serdes_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_serdes_tbl), @@ -2323,7 +2370,7 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = { .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), .regs = pciephy_v4_regs_layout, - .pwrdn_ctrl = SW_PWRDN, + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, .phy_status = PHYSTATUS_4_20, }; diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h index af273602998e..ac872a9eff9a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h @@ -6,6 +6,8 @@ #ifndef QCOM_PHY_QMP_PCS_PCIE_V4_20_H_ #define QCOM_PHY_QMP_PCS_PCIE_V4_20_H_ +#define QPHY_V4_20_PCS_PCIE_ENDPOINT_REFCLK_DRIVE 0x01c +#define QPHY_V4_20_PCS_PCIE_OSC_DTCT_ACTIONS 0x090 #define QPHY_V4_20_PCS_PCIE_EQ_CONFIG1 0x0a0 #define QPHY_V4_20_PCS_PCIE_G3_RXEQEVAL_TIME 0x0f0 #define QPHY_V4_20_PCS_PCIE_G4_RXEQEVAL_TIME 0x0f4 -- GitLab From b4700ed86f00d1917f5219c861f425f92af1a7ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:30 +0100 Subject: [PATCH 0940/5631] phy: allwinner: phy-sun4i-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230307115900.2293120-2-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/allwinner/phy-sun4i-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index fbcd7014ab43..6a74e5ce180a 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -698,7 +698,7 @@ static struct phy *sun4i_usb_phy_xlate(struct device *dev, return data->phys[args->args[0]].phy; } -static int sun4i_usb_phy_remove(struct platform_device *pdev) +static void sun4i_usb_phy_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct sun4i_usb_phy_data *data = dev_get_drvdata(dev); @@ -711,8 +711,6 @@ static int sun4i_usb_phy_remove(struct platform_device *pdev) devm_free_irq(dev, data->vbus_det_irq, data); cancel_delayed_work_sync(&data->detect); - - return 0; } static const unsigned int sun4i_usb_phy0_cable[] = { @@ -1054,7 +1052,7 @@ MODULE_DEVICE_TABLE(of, sun4i_usb_phy_of_match); static struct platform_driver sun4i_usb_phy_driver = { .probe = sun4i_usb_phy_probe, - .remove = sun4i_usb_phy_remove, + .remove_new = sun4i_usb_phy_remove, .driver = { .of_match_table = sun4i_usb_phy_of_match, .name = "sun4i-usb-phy", -- GitLab From b762d7d39d32859728f4d847c3f3c9705833f6dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:31 +0100 Subject: [PATCH 0941/5631] phy: broadcom: phy-brcm-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Justin Chen Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20230307115900.2293120-3-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/broadcom/phy-brcm-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/broadcom/phy-brcm-usb.c b/drivers/phy/broadcom/phy-brcm-usb.c index 4de39999f43d..a4cfb777dd83 100644 --- a/drivers/phy/broadcom/phy-brcm-usb.c +++ b/drivers/phy/broadcom/phy-brcm-usb.c @@ -572,14 +572,12 @@ static int brcm_usb_phy_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(phy_provider); } -static int brcm_usb_phy_remove(struct platform_device *pdev) +static void brcm_usb_phy_remove(struct platform_device *pdev) { struct brcm_usb_phy_data *priv = dev_get_drvdata(&pdev->dev); sysfs_remove_group(&pdev->dev.kobj, &brcm_usb_phy_group); unregister_pm_notifier(&priv->pm_notifier); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -670,7 +668,7 @@ MODULE_DEVICE_TABLE(of, brcm_usb_dt_ids); static struct platform_driver brcm_usb_driver = { .probe = brcm_usb_phy_probe, - .remove = brcm_usb_phy_remove, + .remove_new = brcm_usb_phy_remove, .driver = { .name = "brcmstb-usb-phy", .pm = &brcm_usb_phy_pm_ops, -- GitLab From 7b23fd5c835298a846f3f18dfdcfa95ef34172c4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:32 +0100 Subject: [PATCH 0942/5631] phy: cadence: cdns-dphy: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-4-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/cadence/cdns-dphy.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/cadence/cdns-dphy.c b/drivers/phy/cadence/cdns-dphy.c index 3dfdfb33cd0a..6e58012b6488 100644 --- a/drivers/phy/cadence/cdns-dphy.c +++ b/drivers/phy/cadence/cdns-dphy.c @@ -456,14 +456,12 @@ static int cdns_dphy_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(phy_provider); } -static int cdns_dphy_remove(struct platform_device *pdev) +static void cdns_dphy_remove(struct platform_device *pdev) { struct cdns_dphy *dphy = dev_get_drvdata(&pdev->dev); if (dphy->ops->remove) dphy->ops->remove(dphy); - - return 0; } static const struct of_device_id cdns_dphy_of_match[] = { @@ -475,7 +473,7 @@ MODULE_DEVICE_TABLE(of, cdns_dphy_of_match); static struct platform_driver cdns_dphy_platform_driver = { .probe = cdns_dphy_probe, - .remove = cdns_dphy_remove, + .remove_new = cdns_dphy_remove, .driver = { .name = "cdns-mipi-dphy", .of_match_table = cdns_dphy_of_match, -- GitLab From e9ddb1ad98130d542c9f0d5dbfa6c833420a03ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:33 +0100 Subject: [PATCH 0943/5631] phy: cadence: phy-cadence-sierra: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-5-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/cadence/phy-cadence-sierra.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index 6e86a6517f37..294d59b9eaed 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -1513,7 +1513,7 @@ static int cdns_sierra_phy_probe(struct platform_device *pdev) return ret; } -static int cdns_sierra_phy_remove(struct platform_device *pdev) +static void cdns_sierra_phy_remove(struct platform_device *pdev) { struct cdns_sierra_phy *phy = platform_get_drvdata(pdev); int i; @@ -1533,8 +1533,6 @@ static int cdns_sierra_phy_remove(struct platform_device *pdev) } cdns_sierra_clk_unregister(phy); - - return 0; } /* QSGMII PHY PMA lane configuration */ @@ -2520,7 +2518,7 @@ MODULE_DEVICE_TABLE(of, cdns_sierra_id_table); static struct platform_driver cdns_sierra_driver = { .probe = cdns_sierra_phy_probe, - .remove = cdns_sierra_phy_remove, + .remove_new = cdns_sierra_phy_remove, .driver = { .name = "cdns-sierra-phy", .of_match_table = cdns_sierra_id_table, -- GitLab From e758fbbc0aa1014e29c0f4ca050ad09a0835197b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:34 +0100 Subject: [PATCH 0944/5631] phy: cadence: phy-cadence-torrent: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-6-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/cadence/phy-cadence-torrent.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/cadence/phy-cadence-torrent.c b/drivers/phy/cadence/phy-cadence-torrent.c index f099053c583c..3831f596d50c 100644 --- a/drivers/phy/cadence/phy-cadence-torrent.c +++ b/drivers/phy/cadence/phy-cadence-torrent.c @@ -2777,7 +2777,7 @@ static int cdns_torrent_phy_probe(struct platform_device *pdev) return ret; } -static int cdns_torrent_phy_remove(struct platform_device *pdev) +static void cdns_torrent_phy_remove(struct platform_device *pdev) { struct cdns_torrent_phy *cdns_phy = platform_get_drvdata(pdev); int i; @@ -2791,8 +2791,6 @@ static int cdns_torrent_phy_remove(struct platform_device *pdev) clk_disable_unprepare(cdns_phy->clk); cdns_torrent_clk_cleanup(cdns_phy); - - return 0; } /* Single DisplayPort(DP) link configuration */ @@ -4708,7 +4706,7 @@ MODULE_DEVICE_TABLE(of, cdns_torrent_phy_of_match); static struct platform_driver cdns_torrent_phy_driver = { .probe = cdns_torrent_phy_probe, - .remove = cdns_torrent_phy_remove, + .remove_new = cdns_torrent_phy_remove, .driver = { .name = "cdns-torrent-phy", .of_match_table = cdns_torrent_phy_of_match, -- GitLab From 780d771d7fbfcef1a554521dc86cd4d94039eee9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:35 +0100 Subject: [PATCH 0945/5631] phy: freescale: phy-fsl-imx8qm-lvds-phy: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-7-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c b/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c index e514b64bfdab..0ae052df3765 100644 --- a/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c +++ b/drivers/phy/freescale/phy-fsl-imx8qm-lvds-phy.c @@ -391,11 +391,9 @@ static int mixel_lvds_phy_probe(struct platform_device *pdev) return ret; } -static int mixel_lvds_phy_remove(struct platform_device *pdev) +static void mixel_lvds_phy_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - - return 0; } static int __maybe_unused mixel_lvds_phy_runtime_suspend(struct device *dev) @@ -436,7 +434,7 @@ MODULE_DEVICE_TABLE(of, mixel_lvds_phy_of_match); static struct platform_driver mixel_lvds_phy_driver = { .probe = mixel_lvds_phy_probe, - .remove = mixel_lvds_phy_remove, + .remove_new = mixel_lvds_phy_remove, .driver = { .pm = &mixel_lvds_phy_pm_ops, .name = "mixel-lvds-phy", -- GitLab From 2637959428c90ee99a2103d6d6a3994602cf9f85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:36 +0100 Subject: [PATCH 0946/5631] phy: intel: phy-intel-lgm-combo: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-8-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/intel/phy-intel-lgm-combo.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/phy/intel/phy-intel-lgm-combo.c b/drivers/phy/intel/phy-intel-lgm-combo.c index 6010e246d52e..c49f37e7b75d 100644 --- a/drivers/phy/intel/phy-intel-lgm-combo.c +++ b/drivers/phy/intel/phy-intel-lgm-combo.c @@ -589,13 +589,12 @@ static int intel_cbphy_probe(struct platform_device *pdev) return intel_cbphy_create(cbphy); } -static int intel_cbphy_remove(struct platform_device *pdev) +static void intel_cbphy_remove(struct platform_device *pdev) { struct intel_combo_phy *cbphy = platform_get_drvdata(pdev); intel_cbphy_rst_assert(cbphy); clk_disable_unprepare(cbphy->core_clk); - return 0; } static const struct of_device_id of_intel_cbphy_match[] = { @@ -606,7 +605,7 @@ static const struct of_device_id of_intel_cbphy_match[] = { static struct platform_driver intel_cbphy_driver = { .probe = intel_cbphy_probe, - .remove = intel_cbphy_remove, + .remove_new = intel_cbphy_remove, .driver = { .name = "intel-combo-phy", .of_match_table = of_intel_cbphy_match, -- GitLab From 30850b6e2bbd922f18a7d84666b021aa5e14af65 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:37 +0100 Subject: [PATCH 0947/5631] phy: mediatek: phy-mtk-mipi-dsi: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-9-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/mediatek/phy-mtk-mipi-dsi.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/phy/mediatek/phy-mtk-mipi-dsi.c b/drivers/phy/mediatek/phy-mtk-mipi-dsi.c index cf9c386385bb..526c05a4af5e 100644 --- a/drivers/phy/mediatek/phy-mtk-mipi-dsi.c +++ b/drivers/phy/mediatek/phy-mtk-mipi-dsi.c @@ -180,10 +180,9 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev) mipi_tx->pll); } -static int mtk_mipi_tx_remove(struct platform_device *pdev) +static void mtk_mipi_tx_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static const struct of_device_id mtk_mipi_tx_match[] = { @@ -199,7 +198,7 @@ MODULE_DEVICE_TABLE(of, mtk_mipi_tx_match); static struct platform_driver mtk_mipi_tx_driver = { .probe = mtk_mipi_tx_probe, - .remove = mtk_mipi_tx_remove, + .remove_new = mtk_mipi_tx_remove, .driver = { .name = "mediatek-mipi-tx", .of_match_table = mtk_mipi_tx_match, -- GitLab From dd5c724e09f91ba7b08054f754abe3b6e14c3e7b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:38 +0100 Subject: [PATCH 0948/5631] phy: motorola: phy-cpcap-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-10-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/motorola/phy-cpcap-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index 2f8210167b77..74333e814221 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -692,7 +692,7 @@ static int cpcap_usb_phy_probe(struct platform_device *pdev) return error; } -static int cpcap_usb_phy_remove(struct platform_device *pdev) +static void cpcap_usb_phy_remove(struct platform_device *pdev) { struct cpcap_phy_ddata *ddata = platform_get_drvdata(pdev); int error; @@ -707,13 +707,11 @@ static int cpcap_usb_phy_remove(struct platform_device *pdev) usb_remove_phy(&ddata->phy); cancel_delayed_work_sync(&ddata->detect_work); regulator_disable(ddata->vusb); - - return 0; } static struct platform_driver cpcap_usb_phy_driver = { .probe = cpcap_usb_phy_probe, - .remove = cpcap_usb_phy_remove, + .remove_new = cpcap_usb_phy_remove, .driver = { .name = "cpcap-usb-phy", .of_match_table = of_match_ptr(cpcap_usb_phy_id_table), -- GitLab From 91537c86c5203163bc671d79e941ca06eacd1a95 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:39 +0100 Subject: [PATCH 0949/5631] phy: motorola: phy-mapphone-mdm6600: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-11-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/motorola/phy-mapphone-mdm6600.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 3cd4d51c247c..1d567604b650 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -634,7 +634,7 @@ static int phy_mdm6600_probe(struct platform_device *pdev) return error; } -static int phy_mdm6600_remove(struct platform_device *pdev) +static void phy_mdm6600_remove(struct platform_device *pdev) { struct phy_mdm6600 *ddata = platform_get_drvdata(pdev); struct gpio_desc *reset_gpio = ddata->ctrl_gpios[PHY_MDM6600_RESET]; @@ -653,13 +653,11 @@ static int phy_mdm6600_remove(struct platform_device *pdev) cancel_delayed_work_sync(&ddata->modem_wake_work); cancel_delayed_work_sync(&ddata->bootup_work); cancel_delayed_work_sync(&ddata->status_work); - - return 0; } static struct platform_driver phy_mdm6600_driver = { .probe = phy_mdm6600_probe, - .remove = phy_mdm6600_remove, + .remove_new = phy_mdm6600_remove, .driver = { .name = "phy-mapphone-mdm6600", .pm = &phy_mdm6600_pm_ops, -- GitLab From cbed624f3e4d9c55fb91ec2194cab69dffd30abd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:40 +0100 Subject: [PATCH 0950/5631] phy: phy-lgm-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-12-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/phy-lgm-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/phy-lgm-usb.c b/drivers/phy/phy-lgm-usb.c index 309c8f0e0724..410729c7f513 100644 --- a/drivers/phy/phy-lgm-usb.c +++ b/drivers/phy/phy-lgm-usb.c @@ -252,13 +252,11 @@ static int phy_probe(struct platform_device *pdev) return usb_add_phy_dev(phy); } -static int phy_remove(struct platform_device *pdev) +static void phy_remove(struct platform_device *pdev) { struct tca_apb *ta = platform_get_drvdata(pdev); usb_remove_phy(&ta->phy); - - return 0; } static const struct of_device_id intel_usb_phy_dt_ids[] = { @@ -273,7 +271,7 @@ static struct platform_driver lgm_phy_driver = { .of_match_table = intel_usb_phy_dt_ids, }, .probe = phy_probe, - .remove = phy_remove, + .remove_new = phy_remove, }; module_platform_driver(lgm_phy_driver); -- GitLab From 64299241b4c014d12109866e1a0934bbd13df238 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:41 +0100 Subject: [PATCH 0951/5631] phy: qualcomm: phy-qcom-apq8064-sata: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-13-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-apq8064-sata.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c index d437a249cd73..8814f4322adf 100644 --- a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c +++ b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c @@ -243,13 +243,11 @@ static int qcom_apq8064_sata_phy_probe(struct platform_device *pdev) return 0; } -static int qcom_apq8064_sata_phy_remove(struct platform_device *pdev) +static void qcom_apq8064_sata_phy_remove(struct platform_device *pdev) { struct qcom_apq8064_sata_phy *phy = platform_get_drvdata(pdev); clk_disable_unprepare(phy->cfg_clk); - - return 0; } static const struct of_device_id qcom_apq8064_sata_phy_of_match[] = { @@ -260,7 +258,7 @@ MODULE_DEVICE_TABLE(of, qcom_apq8064_sata_phy_of_match); static struct platform_driver qcom_apq8064_sata_phy_driver = { .probe = qcom_apq8064_sata_phy_probe, - .remove = qcom_apq8064_sata_phy_remove, + .remove_new = qcom_apq8064_sata_phy_remove, .driver = { .name = "qcom-apq8064-sata-phy", .of_match_table = qcom_apq8064_sata_phy_of_match, -- GitLab From e5ce6d9d654d36329490c863645cdcd0bc36b64e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:42 +0100 Subject: [PATCH 0952/5631] phy: qualcomm: phy-qcom-eusb2-repeater: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-14-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index 3f265ac2df20..90f8543ba265 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -223,16 +223,14 @@ static int eusb2_repeater_probe(struct platform_device *pdev) return 0; } -static int eusb2_repeater_remove(struct platform_device *pdev) +static void eusb2_repeater_remove(struct platform_device *pdev) { struct eusb2_repeater *rptr = platform_get_drvdata(pdev); if (!rptr) - return 0; + return; eusb2_repeater_exit(rptr->phy); - - return 0; } static const struct of_device_id eusb2_repeater_of_match_table[] = { @@ -246,7 +244,7 @@ MODULE_DEVICE_TABLE(of, eusb2_repeater_of_match_table); static struct platform_driver eusb2_repeater_driver = { .probe = eusb2_repeater_probe, - .remove = eusb2_repeater_remove, + .remove_new = eusb2_repeater_remove, .driver = { .name = "qcom-eusb2-repeater", .of_match_table = eusb2_repeater_of_match_table, -- GitLab From de6862d1bdfafaf0369b3abb648c02a621783172 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:43 +0100 Subject: [PATCH 0953/5631] phy: qualcomm: phy-qcom-ipq806x-sata: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-15-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c index 0fc2a1ed39b3..f0a72b82c770 100644 --- a/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c +++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-sata.c @@ -170,13 +170,11 @@ static int qcom_ipq806x_sata_phy_probe(struct platform_device *pdev) return 0; } -static int qcom_ipq806x_sata_phy_remove(struct platform_device *pdev) +static void qcom_ipq806x_sata_phy_remove(struct platform_device *pdev) { struct qcom_ipq806x_sata_phy *phy = platform_get_drvdata(pdev); clk_disable_unprepare(phy->cfg_clk); - - return 0; } static const struct of_device_id qcom_ipq806x_sata_phy_of_match[] = { @@ -187,7 +185,7 @@ MODULE_DEVICE_TABLE(of, qcom_ipq806x_sata_phy_of_match); static struct platform_driver qcom_ipq806x_sata_phy_driver = { .probe = qcom_ipq806x_sata_phy_probe, - .remove = qcom_ipq806x_sata_phy_remove, + .remove_new = qcom_ipq806x_sata_phy_remove, .driver = { .name = "qcom-ipq806x-sata-phy", .of_match_table = qcom_ipq806x_sata_phy_of_match, -- GitLab From aba5c6f3eccf930dcd5c55f21b191e6f7d806c53 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:44 +0100 Subject: [PATCH 0954/5631] phy: renesas: phy-rcar-gen3-pcie: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-16-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/renesas/phy-rcar-gen3-pcie.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/renesas/phy-rcar-gen3-pcie.c b/drivers/phy/renesas/phy-rcar-gen3-pcie.c index 4dc721eb9577..9cf786a7daac 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-pcie.c +++ b/drivers/phy/renesas/phy-rcar-gen3-pcie.c @@ -126,11 +126,9 @@ static int rcar_gen3_phy_pcie_probe(struct platform_device *pdev) return error; } -static int rcar_gen3_phy_pcie_remove(struct platform_device *pdev) +static void rcar_gen3_phy_pcie_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - - return 0; }; static struct platform_driver rcar_gen3_phy_driver = { @@ -139,7 +137,7 @@ static struct platform_driver rcar_gen3_phy_driver = { .of_match_table = rcar_gen3_phy_pcie_match_table, }, .probe = rcar_gen3_phy_pcie_probe, - .remove = rcar_gen3_phy_pcie_remove, + .remove_new = rcar_gen3_phy_pcie_remove, }; module_platform_driver(rcar_gen3_phy_driver); -- GitLab From c7ac6dff31fab4ac334f3c6780286f05ea77eea4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:45 +0100 Subject: [PATCH 0955/5631] phy: renesas: phy-rcar-gen3-usb2: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230307115900.2293120-17-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/renesas/phy-rcar-gen3-usb2.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb2.c b/drivers/phy/renesas/phy-rcar-gen3-usb2.c index 9de617ca9daa..d4e2ee7e4efb 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb2.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb2.c @@ -755,7 +755,7 @@ static int rcar_gen3_phy_usb2_probe(struct platform_device *pdev) return ret; } -static int rcar_gen3_phy_usb2_remove(struct platform_device *pdev) +static void rcar_gen3_phy_usb2_remove(struct platform_device *pdev) { struct rcar_gen3_chan *channel = platform_get_drvdata(pdev); @@ -763,8 +763,6 @@ static int rcar_gen3_phy_usb2_remove(struct platform_device *pdev) device_remove_file(&pdev->dev, &dev_attr_role); pm_runtime_disable(&pdev->dev); - - return 0; }; static struct platform_driver rcar_gen3_phy_usb2_driver = { @@ -773,7 +771,7 @@ static struct platform_driver rcar_gen3_phy_usb2_driver = { .of_match_table = rcar_gen3_phy_usb2_match_table, }, .probe = rcar_gen3_phy_usb2_probe, - .remove = rcar_gen3_phy_usb2_remove, + .remove_new = rcar_gen3_phy_usb2_remove, }; module_platform_driver(rcar_gen3_phy_usb2_driver); -- GitLab From 8e593a223eadbae6b5e42b8821d1917f230b288e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:46 +0100 Subject: [PATCH 0956/5631] phy: renesas: phy-rcar-gen3-usb3: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230307115900.2293120-18-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/renesas/phy-rcar-gen3-usb3.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/renesas/phy-rcar-gen3-usb3.c b/drivers/phy/renesas/phy-rcar-gen3-usb3.c index f27d6f471629..e2d630edd992 100644 --- a/drivers/phy/renesas/phy-rcar-gen3-usb3.c +++ b/drivers/phy/renesas/phy-rcar-gen3-usb3.c @@ -199,11 +199,9 @@ static int rcar_gen3_phy_usb3_probe(struct platform_device *pdev) return ret; } -static int rcar_gen3_phy_usb3_remove(struct platform_device *pdev) +static void rcar_gen3_phy_usb3_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - - return 0; }; static struct platform_driver rcar_gen3_phy_usb3_driver = { @@ -212,7 +210,7 @@ static struct platform_driver rcar_gen3_phy_usb3_driver = { .of_match_table = rcar_gen3_phy_usb3_match_table, }, .probe = rcar_gen3_phy_usb3_probe, - .remove = rcar_gen3_phy_usb3_remove, + .remove_new = rcar_gen3_phy_usb3_remove, }; module_platform_driver(rcar_gen3_phy_usb3_driver); -- GitLab From f1c01b91e56b5716eff573bdefbb771ac1d133b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:47 +0100 Subject: [PATCH 0957/5631] phy: renesas: r8a779f0-ether-serdes: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-19-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/renesas/r8a779f0-ether-serdes.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/renesas/r8a779f0-ether-serdes.c b/drivers/phy/renesas/r8a779f0-ether-serdes.c index c5206ef9195b..55b7bdfc10d3 100644 --- a/drivers/phy/renesas/r8a779f0-ether-serdes.c +++ b/drivers/phy/renesas/r8a779f0-ether-serdes.c @@ -388,19 +388,17 @@ static int r8a779f0_eth_serdes_probe(struct platform_device *pdev) return 0; } -static int r8a779f0_eth_serdes_remove(struct platform_device *pdev) +static void r8a779f0_eth_serdes_remove(struct platform_device *pdev) { pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); platform_set_drvdata(pdev, NULL); - - return 0; } static struct platform_driver r8a779f0_eth_serdes_driver_platform = { .probe = r8a779f0_eth_serdes_probe, - .remove = r8a779f0_eth_serdes_remove, + .remove_new = r8a779f0_eth_serdes_remove, .driver = { .name = "r8a779f0_eth_serdes", .of_match_table = r8a779f0_eth_serdes_of_table, -- GitLab From b41f07b2010c65f9a3e95b0d60ae9eca6272c107 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:48 +0100 Subject: [PATCH 0958/5631] phy: rockchip: phy-rockchip-inno-csidphy: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230307115900.2293120-20-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-inno-csidphy.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c index 75f948bdea6a..98c92d6c482f 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-csidphy.c @@ -459,13 +459,11 @@ static int rockchip_inno_csidphy_probe(struct platform_device *pdev) return 0; } -static int rockchip_inno_csidphy_remove(struct platform_device *pdev) +static void rockchip_inno_csidphy_remove(struct platform_device *pdev) { struct rockchip_inno_csidphy *priv = platform_get_drvdata(pdev); pm_runtime_disable(priv->dev); - - return 0; } static struct platform_driver rockchip_inno_csidphy_driver = { @@ -474,7 +472,7 @@ static struct platform_driver rockchip_inno_csidphy_driver = { .of_match_table = rockchip_inno_csidphy_match_id, }, .probe = rockchip_inno_csidphy_probe, - .remove = rockchip_inno_csidphy_remove, + .remove_new = rockchip_inno_csidphy_remove, }; module_platform_driver(rockchip_inno_csidphy_driver); -- GitLab From 497a38322ac9830b79da97e6a2a2255d0520a5d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:49 +0100 Subject: [PATCH 0959/5631] phy: rockchip: phy-rockchip-inno-dsidphy: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230307115900.2293120-21-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c index 2c5847faff63..726928ff1273 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c @@ -755,13 +755,11 @@ static int inno_dsidphy_probe(struct platform_device *pdev) return 0; } -static int inno_dsidphy_remove(struct platform_device *pdev) +static void inno_dsidphy_remove(struct platform_device *pdev) { struct inno_dsidphy *inno = platform_get_drvdata(pdev); pm_runtime_disable(inno->dev); - - return 0; } static const struct of_device_id inno_dsidphy_of_match[] = { @@ -788,7 +786,7 @@ static struct platform_driver inno_dsidphy_driver = { .of_match_table = of_match_ptr(inno_dsidphy_of_match), }, .probe = inno_dsidphy_probe, - .remove = inno_dsidphy_remove, + .remove_new = inno_dsidphy_remove, }; module_platform_driver(inno_dsidphy_driver); -- GitLab From cb1161c0c18dc396665a83af00e5397c4895422e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:50 +0100 Subject: [PATCH 0960/5631] phy: rockchip: phy-rockchip-inno-hdmi: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230307115900.2293120-22-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-inno-hdmi.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c index 80acca4e9e14..1e1563f5fffc 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-hdmi.c @@ -1246,11 +1246,9 @@ static int inno_hdmi_phy_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(phy_provider); } -static int inno_hdmi_phy_remove(struct platform_device *pdev) +static void inno_hdmi_phy_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static const struct of_device_id inno_hdmi_phy_of_match[] = { @@ -1266,7 +1264,7 @@ MODULE_DEVICE_TABLE(of, inno_hdmi_phy_of_match); static struct platform_driver inno_hdmi_phy_driver = { .probe = inno_hdmi_phy_probe, - .remove = inno_hdmi_phy_remove, + .remove_new = inno_hdmi_phy_remove, .driver = { .name = "inno-hdmi-phy", .of_match_table = inno_hdmi_phy_of_match, -- GitLab From 1d558e55e01651e9add409a6fb652205e8dd9f92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:51 +0100 Subject: [PATCH 0961/5631] phy: rockchip: phy-rockchip-typec: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230307115900.2293120-23-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-typec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index 39db8acde61a..8b1667be4915 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -1194,11 +1194,9 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev) return 0; } -static int rockchip_typec_phy_remove(struct platform_device *pdev) +static void rockchip_typec_phy_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - - return 0; } static const struct of_device_id rockchip_typec_phy_dt_ids[] = { @@ -1213,7 +1211,7 @@ MODULE_DEVICE_TABLE(of, rockchip_typec_phy_dt_ids); static struct platform_driver rockchip_typec_phy_driver = { .probe = rockchip_typec_phy_probe, - .remove = rockchip_typec_phy_remove, + .remove_new = rockchip_typec_phy_remove, .driver = { .name = "rockchip-typec-phy", .of_match_table = rockchip_typec_phy_dt_ids, -- GitLab From 31d0d4e0222b69b33b93ee45637cc18c690449a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:52 +0100 Subject: [PATCH 0962/5631] phy: st: phy-stm32-usbphyc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-24-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/st/phy-stm32-usbphyc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 5bb9647b078f..1add3b75f92f 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -766,7 +766,7 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) return ret; } -static int stm32_usbphyc_remove(struct platform_device *pdev) +static void stm32_usbphyc_remove(struct platform_device *pdev) { struct stm32_usbphyc *usbphyc = dev_get_drvdata(&pdev->dev); int port; @@ -779,8 +779,6 @@ static int stm32_usbphyc_remove(struct platform_device *pdev) stm32_usbphyc_clk48_unregister(usbphyc); clk_disable_unprepare(usbphyc->clk); - - return 0; } static int __maybe_unused stm32_usbphyc_resume(struct device *dev) @@ -810,7 +808,7 @@ MODULE_DEVICE_TABLE(of, stm32_usbphyc_of_match); static struct platform_driver stm32_usbphyc_driver = { .probe = stm32_usbphyc_probe, - .remove = stm32_usbphyc_remove, + .remove_new = stm32_usbphyc_remove, .driver = { .of_match_table = stm32_usbphyc_of_match, .name = "stm32-usbphyc", -- GitLab From 80460691c16b74896f536067863f13b5e693dede Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:53 +0100 Subject: [PATCH 0963/5631] phy: tegra: xusb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-25-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/tegra/xusb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 78045bd6c214..ec335668563d 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1267,7 +1267,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev) return err; } -static int tegra_xusb_padctl_remove(struct platform_device *pdev) +static void tegra_xusb_padctl_remove(struct platform_device *pdev) { struct tegra_xusb_padctl *padctl = platform_get_drvdata(pdev); int err; @@ -1285,8 +1285,6 @@ static int tegra_xusb_padctl_remove(struct platform_device *pdev) dev_err(&pdev->dev, "failed to assert reset: %d\n", err); padctl->soc->ops->remove(padctl); - - return 0; } static __maybe_unused int tegra_xusb_padctl_suspend_noirq(struct device *dev) @@ -1321,7 +1319,7 @@ static struct platform_driver tegra_xusb_padctl_driver = { .pm = &tegra_xusb_padctl_pm_ops, }, .probe = tegra_xusb_padctl_probe, - .remove = tegra_xusb_padctl_remove, + .remove_new = tegra_xusb_padctl_remove, }; module_platform_driver(tegra_xusb_padctl_driver); -- GitLab From b1d9ad66587110fe35f6c2b2cd176c11a400ad24 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:54 +0100 Subject: [PATCH 0964/5631] phy: ti: phy-am654-serdes: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-26-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-am654-serdes.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index 0be727bb9f79..4ed2d951d3df 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -842,20 +842,18 @@ static int serdes_am654_probe(struct platform_device *pdev) return ret; } -static int serdes_am654_remove(struct platform_device *pdev) +static void serdes_am654_remove(struct platform_device *pdev) { struct serdes_am654 *am654_phy = platform_get_drvdata(pdev); struct device_node *node = am654_phy->of_node; pm_runtime_disable(&pdev->dev); of_clk_del_provider(node); - - return 0; } static struct platform_driver serdes_am654_driver = { .probe = serdes_am654_probe, - .remove = serdes_am654_remove, + .remove_new = serdes_am654_remove, .driver = { .name = "phy-am654", .of_match_table = serdes_am654_id_table, -- GitLab From 0196c847236a84535d92b04a79d694ae063c6f68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:55 +0100 Subject: [PATCH 0965/5631] phy: ti: phy-da8xx-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-27-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-da8xx-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-da8xx-usb.c b/drivers/phy/ti/phy-da8xx-usb.c index 83bc0a9afe12..b7a9ef3f4654 100644 --- a/drivers/phy/ti/phy-da8xx-usb.c +++ b/drivers/phy/ti/phy-da8xx-usb.c @@ -211,7 +211,7 @@ static int da8xx_usb_phy_probe(struct platform_device *pdev) return 0; } -static int da8xx_usb_phy_remove(struct platform_device *pdev) +static void da8xx_usb_phy_remove(struct platform_device *pdev) { struct da8xx_usb_phy *d_phy = platform_get_drvdata(pdev); @@ -219,8 +219,6 @@ static int da8xx_usb_phy_remove(struct platform_device *pdev) phy_remove_lookup(d_phy->usb20_phy, "usb-phy", "musb-da8xx"); phy_remove_lookup(d_phy->usb11_phy, "usb-phy", "ohci-da8xx"); } - - return 0; } static const struct of_device_id da8xx_usb_phy_ids[] = { @@ -231,7 +229,7 @@ MODULE_DEVICE_TABLE(of, da8xx_usb_phy_ids); static struct platform_driver da8xx_usb_phy_driver = { .probe = da8xx_usb_phy_probe, - .remove = da8xx_usb_phy_remove, + .remove_new = da8xx_usb_phy_remove, .driver = { .name = "da8xx-usb-phy", .of_match_table = da8xx_usb_phy_ids, -- GitLab From 13e1f73503abf52abca76843dc5050d6e4d221df Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:56 +0100 Subject: [PATCH 0966/5631] phy: ti: phy-dm816x-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-28-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-dm816x-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-dm816x-usb.c b/drivers/phy/ti/phy-dm816x-usb.c index fb619908f912..db153a55f4e1 100644 --- a/drivers/phy/ti/phy-dm816x-usb.c +++ b/drivers/phy/ti/phy-dm816x-usb.c @@ -257,20 +257,18 @@ static int dm816x_usb_phy_probe(struct platform_device *pdev) return error; } -static int dm816x_usb_phy_remove(struct platform_device *pdev) +static void dm816x_usb_phy_remove(struct platform_device *pdev) { struct dm816x_usb_phy *phy = platform_get_drvdata(pdev); usb_remove_phy(&phy->phy); pm_runtime_disable(phy->dev); clk_unprepare(phy->refclk); - - return 0; } static struct platform_driver dm816x_usb_phy_driver = { .probe = dm816x_usb_phy_probe, - .remove = dm816x_usb_phy_remove, + .remove_new = dm816x_usb_phy_remove, .driver = { .name = "dm816x-usb-phy", .pm = &dm816x_usb_phy_pm_ops, -- GitLab From db850ea9fc746090a0567d6dbf6888a9225bcfb1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:57 +0100 Subject: [PATCH 0967/5631] phy: ti: phy-j721e-wiz: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-29-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-j721e-wiz.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index 1b83c98a78f0..d2fd2143450a 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1636,7 +1636,7 @@ static int wiz_probe(struct platform_device *pdev) return ret; } -static int wiz_remove(struct platform_device *pdev) +static void wiz_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *node = dev->of_node; @@ -1650,13 +1650,11 @@ static int wiz_remove(struct platform_device *pdev) wiz_clock_cleanup(wiz, node); pm_runtime_put(dev); pm_runtime_disable(dev); - - return 0; } static struct platform_driver wiz_driver = { .probe = wiz_probe, - .remove = wiz_remove, + .remove_new = wiz_remove, .driver = { .name = "wiz", .of_match_table = wiz_id_table, -- GitLab From 5566da719432a4821bda342a314b693f2b451693 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:58 +0100 Subject: [PATCH 0968/5631] phy: ti: phy-omap-usb2: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-30-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-omap-usb2.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index 31a775877f6e..bbe5d25b0351 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -506,19 +506,17 @@ static int omap_usb2_probe(struct platform_device *pdev) return 0; } -static int omap_usb2_remove(struct platform_device *pdev) +static void omap_usb2_remove(struct platform_device *pdev) { struct omap_usb *phy = platform_get_drvdata(pdev); usb_remove_phy(&phy->phy); pm_runtime_disable(phy->dev); - - return 0; } static struct platform_driver omap_usb2_driver = { .probe = omap_usb2_probe, - .remove = omap_usb2_remove, + .remove_new = omap_usb2_remove, .driver = { .name = "omap-usb2", .of_match_table = omap_usb2_id_table, -- GitLab From c29d42577608080d83e488c6cc0b8d6835adeeb4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:58:59 +0100 Subject: [PATCH 0969/5631] phy: ti: phy-ti-pipe3: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-31-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-ti-pipe3.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index f502c36f3be5..507e1552db5e 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -841,7 +841,7 @@ static int ti_pipe3_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(phy_provider); } -static int ti_pipe3_remove(struct platform_device *pdev) +static void ti_pipe3_remove(struct platform_device *pdev) { struct ti_pipe3 *phy = platform_get_drvdata(pdev); @@ -850,8 +850,6 @@ static int ti_pipe3_remove(struct platform_device *pdev) phy->sata_refclk_enabled = false; } pm_runtime_disable(&pdev->dev); - - return 0; } static int ti_pipe3_enable_clocks(struct ti_pipe3 *phy) @@ -928,7 +926,7 @@ MODULE_DEVICE_TABLE(of, ti_pipe3_id_table); static struct platform_driver ti_pipe3_driver = { .probe = ti_pipe3_probe, - .remove = ti_pipe3_remove, + .remove_new = ti_pipe3_remove, .driver = { .name = "ti-pipe3", .of_match_table = ti_pipe3_id_table, -- GitLab From a01c9d19422e486578d7cfdf799e464025417eab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 12:59:00 +0100 Subject: [PATCH 0970/5631] phy: ti: phy-twl4030-usb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230307115900.2293120-32-u.kleine-koenig@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-twl4030-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/phy/ti/phy-twl4030-usb.c b/drivers/phy/ti/phy-twl4030-usb.c index ac71017a0bc1..da50732625d1 100644 --- a/drivers/phy/ti/phy-twl4030-usb.c +++ b/drivers/phy/ti/phy-twl4030-usb.c @@ -787,7 +787,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) return 0; } -static int twl4030_usb_remove(struct platform_device *pdev) +static void twl4030_usb_remove(struct platform_device *pdev) { struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; @@ -821,8 +821,6 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - - return 0; } #ifdef CONFIG_OF @@ -835,7 +833,7 @@ MODULE_DEVICE_TABLE(of, twl4030_usb_id_table); static struct platform_driver twl4030_usb_driver = { .probe = twl4030_usb_probe, - .remove = twl4030_usb_remove, + .remove_new = twl4030_usb_remove, .driver = { .name = "twl4030_usb", .pm = &twl4030_usb_pm_ops, -- GitLab From 8e9930e14d040bde33a11a62eee8c3c6981c7126 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:20 -0600 Subject: [PATCH 0971/5631] phy: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Reviewed-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230310144720.1544600-1-robh@kernel.org Signed-off-by: Vinod Koul --- drivers/phy/allwinner/phy-sun4i-usb.c | 2 +- drivers/phy/broadcom/phy-bcm-ns-usb2.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index 6a74e5ce180a..56d53f78d002 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -756,7 +756,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(data->vbus_det_gpio); } - if (of_find_property(np, "usb0_vbus_power-supply", NULL)) { + if (of_property_present(np, "usb0_vbus_power-supply")) { data->vbus_power_supply = devm_power_supply_get_by_phandle(dev, "usb0_vbus_power-supply"); if (IS_ERR(data->vbus_power_supply)) { diff --git a/drivers/phy/broadcom/phy-bcm-ns-usb2.c b/drivers/phy/broadcom/phy-bcm-ns-usb2.c index 6a36e187d100..269564bdf687 100644 --- a/drivers/phy/broadcom/phy-bcm-ns-usb2.c +++ b/drivers/phy/broadcom/phy-bcm-ns-usb2.c @@ -107,7 +107,7 @@ static int bcm_ns_usb2_probe(struct platform_device *pdev) return -ENOMEM; usb2->dev = dev; - if (of_find_property(dev->of_node, "brcm,syscon-clkset", NULL)) { + if (of_property_present(dev->of_node, "brcm,syscon-clkset")) { usb2->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(usb2->base)) { dev_err(dev, "Failed to map control reg\n"); -- GitLab From 8a65acdd43def7ebd9b51d21ca80bc4d4a55583f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:26:10 +0100 Subject: [PATCH 0972/5631] phy: marvell: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/phy/marvell/phy-pxa-28nm-hsic.c:192:34: error: ‘mv_hsic_phy_dt_match’ defined but not used [-Werror=unused-const-variable=] drivers/phy/marvell/phy-pxa-28nm-usb2.c:324:34: error: ‘mv_usbphy_dt_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312132611.352654-1-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/marvell/phy-pxa-28nm-hsic.c | 2 +- drivers/phy/marvell/phy-pxa-28nm-usb2.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/marvell/phy-pxa-28nm-hsic.c b/drivers/phy/marvell/phy-pxa-28nm-hsic.c index c5c100563f55..eff6dd6b2dd0 100644 --- a/drivers/phy/marvell/phy-pxa-28nm-hsic.c +++ b/drivers/phy/marvell/phy-pxa-28nm-hsic.c @@ -199,7 +199,7 @@ static struct platform_driver mv_hsic_phy_driver = { .probe = mv_hsic_phy_probe, .driver = { .name = "mv-hsic-phy", - .of_match_table = of_match_ptr(mv_hsic_phy_dt_match), + .of_match_table = mv_hsic_phy_dt_match, }, }; module_platform_driver(mv_hsic_phy_driver); diff --git a/drivers/phy/marvell/phy-pxa-28nm-usb2.c b/drivers/phy/marvell/phy-pxa-28nm-usb2.c index 0b390b9d2ae1..1b2107f80f3a 100644 --- a/drivers/phy/marvell/phy-pxa-28nm-usb2.c +++ b/drivers/phy/marvell/phy-pxa-28nm-usb2.c @@ -331,7 +331,7 @@ static struct platform_driver mv_usb2_phy_driver = { .probe = mv_usb2_phy_probe, .driver = { .name = "mv-usb2-phy", - .of_match_table = of_match_ptr(mv_usbphy_dt_match), + .of_match_table = mv_usbphy_dt_match, }, }; module_platform_driver(mv_usb2_phy_driver); -- GitLab From 5e4d267f9bc9274f8050a5ea8d4618c7f05e12eb Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:26:11 +0100 Subject: [PATCH 0973/5631] phy: st: spear: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/phy/st/phy-spear1310-miphy.c:172:34: error: ‘spear1310_miphy_of_match’ defined but not used [-Werror=unused-const-variable=] drivers/phy/st/phy-spear1340-miphy.c:182:34: error: ‘spear1340_miphy_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230312132611.352654-2-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/st/phy-spear1310-miphy.c | 2 +- drivers/phy/st/phy-spear1340-miphy.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/st/phy-spear1310-miphy.c b/drivers/phy/st/phy-spear1310-miphy.c index 8871cd186304..292413db7da4 100644 --- a/drivers/phy/st/phy-spear1310-miphy.c +++ b/drivers/phy/st/phy-spear1310-miphy.c @@ -246,7 +246,7 @@ static struct platform_driver spear1310_miphy_driver = { .probe = spear1310_miphy_probe, .driver = { .name = "spear1310-miphy", - .of_match_table = of_match_ptr(spear1310_miphy_of_match), + .of_match_table = spear1310_miphy_of_match, }, }; diff --git a/drivers/phy/st/phy-spear1340-miphy.c b/drivers/phy/st/phy-spear1340-miphy.c index ed4d0e2df053..c1d9ffa5a311 100644 --- a/drivers/phy/st/phy-spear1340-miphy.c +++ b/drivers/phy/st/phy-spear1340-miphy.c @@ -279,7 +279,7 @@ static struct platform_driver spear1340_miphy_driver = { .driver = { .name = "spear1340-miphy", .pm = &spear1340_miphy_pm_ops, - .of_match_table = of_match_ptr(spear1340_miphy_of_match), + .of_match_table = spear1340_miphy_of_match, }, }; -- GitLab From 8b798761243bf854cbf706fcfc21798726ff587a Mon Sep 17 00:00:00 2001 From: Henry Lin Date: Thu, 9 Mar 2023 14:17:08 +0800 Subject: [PATCH 0974/5631] phy: tegra: xusb: Support sleepwalk for Tegra234 Add new registers programming in sleepwalk sequence for Tegra234: MASTER_ENABLE_A/B/C/D in XUSB_AO_UTMIP_SLEEPWALK. Signed-off-by: Henry Lin Signed-off-by: Haotien Hsu Link: https://lore.kernel.org/r/20230309061708.4156383-1-haotienh@nvidia.com Signed-off-by: Vinod Koul --- drivers/phy/tegra/xusb-tegra186.c | 20 ++++++++++++++++++++ drivers/phy/tegra/xusb.h | 1 + 2 files changed, 21 insertions(+) diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index 1aae8535f452..0f60d5d1c167 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -145,6 +145,8 @@ #define MODE_HS MODE(0) #define MODE_RST MODE(1) +#define XUSB_AO_UTMIP_SLEEPWALK_STATUS(x) (0xa0 + (x) * 4) + #define XUSB_AO_UTMIP_SLEEPWALK_CFG(x) (0xd0 + (x) * 4) #define XUSB_AO_UHSIC_SLEEPWALK_CFG(x) (0xf0 + (x) * 4) #define FAKE_USBOP_VAL BIT(0) @@ -172,24 +174,30 @@ #define AP_A BIT(4) #define AN_A BIT(5) #define HIGHZ_A BIT(6) +#define MASTER_ENABLE_A BIT(7) /* phase B */ #define USBOP_RPD_B BIT(8) #define USBON_RPD_B BIT(9) #define AP_B BIT(12) #define AN_B BIT(13) #define HIGHZ_B BIT(14) +#define MASTER_ENABLE_B BIT(15) /* phase C */ #define USBOP_RPD_C BIT(16) #define USBON_RPD_C BIT(17) #define AP_C BIT(20) #define AN_C BIT(21) #define HIGHZ_C BIT(22) +#define MASTER_ENABLE_C BIT(23) /* phase D */ #define USBOP_RPD_D BIT(24) #define USBON_RPD_D BIT(25) #define AP_D BIT(28) #define AN_D BIT(29) #define HIGHZ_D BIT(30) +#define MASTER_ENABLE_D BIT(31) +#define MASTER_ENABLE_B_C_D \ + (MASTER_ENABLE_B | MASTER_ENABLE_C | MASTER_ENABLE_D) #define XUSB_AO_UHSIC_SLEEPWALK(x) (0x120 + (x) * 4) /* phase A */ @@ -417,6 +425,8 @@ static int tegra186_utmi_enable_phy_sleepwalk(struct tegra_xusb_lane *lane, value |= HIGHZ_A; value |= AP_A; value |= AN_B | AN_C | AN_D; + if (padctl->soc->supports_lp_cfg_en) + value |= MASTER_ENABLE_B_C_D; break; case USB_SPEED_LOW: @@ -424,6 +434,8 @@ static int tegra186_utmi_enable_phy_sleepwalk(struct tegra_xusb_lane *lane, value |= HIGHZ_A; value |= AN_A; value |= AP_B | AP_C | AP_D; + if (padctl->soc->supports_lp_cfg_en) + value |= MASTER_ENABLE_B_C_D; break; default: @@ -488,6 +500,13 @@ static int tegra186_utmi_disable_phy_sleepwalk(struct tegra_xusb_lane *lane) value |= WAKE_VAL_NONE; ao_writel(priv, value, XUSB_AO_UTMIP_SLEEPWALK_CFG(index)); + if (padctl->soc->supports_lp_cfg_en) { + /* disable the four stages of sleepwalk */ + value = ao_readl(priv, XUSB_AO_UTMIP_SLEEPWALK(index)); + value &= ~(MASTER_ENABLE_A | MASTER_ENABLE_B_C_D); + ao_writel(priv, value, XUSB_AO_UTMIP_SLEEPWALK(index)); + } + /* power down the line state detectors of the port */ value = ao_readl(priv, XUSB_AO_UTMIP_PAD_CFG(index)); value |= USBOP_VAL_PD | USBON_VAL_PD; @@ -1673,6 +1692,7 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = { .supports_gen2 = true, .poll_trk_completed = true, .trk_hw_mode = true, + .supports_lp_cfg_en = true, }; EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc); #endif diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h index 8bd6cd281119..6e45d194c689 100644 --- a/drivers/phy/tegra/xusb.h +++ b/drivers/phy/tegra/xusb.h @@ -434,6 +434,7 @@ struct tegra_xusb_padctl_soc { bool need_fake_usb3_port; bool poll_trk_completed; bool trk_hw_mode; + bool supports_lp_cfg_en; }; struct tegra_xusb_padctl { -- GitLab From e3be4dd2c8d8aabfd2c3127d0e2e5754d3ae82d6 Mon Sep 17 00:00:00 2001 From: Alain Volmat Date: Fri, 10 Feb 2023 23:43:08 +0100 Subject: [PATCH 0975/5631] phy: st: miphy28lp: use _poll_timeout functions for waits This commit introduces _poll_timeout functions usage instead of wait loops waiting for a status bit. Signed-off-by: Alain Volmat Reviewed-by: Patrice Chotard Link: https://lore.kernel.org/r/20230210224309.98452-1-avolmat@me.com Signed-off-by: Vinod Koul --- drivers/phy/st/phy-miphy28lp.c | 42 ++++++++-------------------------- 1 file changed, 10 insertions(+), 32 deletions(-) diff --git a/drivers/phy/st/phy-miphy28lp.c b/drivers/phy/st/phy-miphy28lp.c index 068160a34f5c..e30305b77f0d 100644 --- a/drivers/phy/st/phy-miphy28lp.c +++ b/drivers/phy/st/phy-miphy28lp.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -484,19 +485,11 @@ static inline void miphy28lp_pcie_config_gen(struct miphy28lp_phy *miphy_phy) static inline int miphy28lp_wait_compensation(struct miphy28lp_phy *miphy_phy) { - unsigned long finish = jiffies + 5 * HZ; u8 val; /* Waiting for Compensation to complete */ - do { - val = readb_relaxed(miphy_phy->base + MIPHY_COMP_FSM_6); - - if (time_after_eq(jiffies, finish)) - return -EBUSY; - cpu_relax(); - } while (!(val & COMP_DONE)); - - return 0; + return readb_relaxed_poll_timeout(miphy_phy->base + MIPHY_COMP_FSM_6, + val, val & COMP_DONE, 1, 5 * USEC_PER_SEC); } @@ -805,7 +798,6 @@ static inline void miphy28lp_configure_usb3(struct miphy28lp_phy *miphy_phy) static inline int miphy_is_ready(struct miphy28lp_phy *miphy_phy) { - unsigned long finish = jiffies + 5 * HZ; u8 mask = HFC_PLL | HFC_RDY; u8 val; @@ -816,21 +808,14 @@ static inline int miphy_is_ready(struct miphy28lp_phy *miphy_phy) if (miphy_phy->type == PHY_TYPE_SATA) mask |= PHY_RDY; - do { - val = readb_relaxed(miphy_phy->base + MIPHY_STATUS_1); - if ((val & mask) != mask) - cpu_relax(); - else - return 0; - } while (!time_after_eq(jiffies, finish)); - - return -EBUSY; + return readb_relaxed_poll_timeout(miphy_phy->base + MIPHY_STATUS_1, + val, (val & mask) == mask, 1, + 5 * USEC_PER_SEC); } static int miphy_osc_is_ready(struct miphy28lp_phy *miphy_phy) { struct miphy28lp_dev *miphy_dev = miphy_phy->phydev; - unsigned long finish = jiffies + 5 * HZ; u32 val; if (!miphy_phy->osc_rdy) @@ -839,17 +824,10 @@ static int miphy_osc_is_ready(struct miphy28lp_phy *miphy_phy) if (!miphy_phy->syscfg_reg[SYSCFG_STATUS]) return -EINVAL; - do { - regmap_read(miphy_dev->regmap, - miphy_phy->syscfg_reg[SYSCFG_STATUS], &val); - - if ((val & MIPHY_OSC_RDY) != MIPHY_OSC_RDY) - cpu_relax(); - else - return 0; - } while (!time_after_eq(jiffies, finish)); - - return -EBUSY; + return regmap_read_poll_timeout(miphy_dev->regmap, + miphy_phy->syscfg_reg[SYSCFG_STATUS], + val, val & MIPHY_OSC_RDY, 1, + 5 * USEC_PER_SEC); } static int miphy28lp_get_resource_byname(struct device_node *child, -- GitLab From 84a59a314263c21de1b308abda7f7eea92da740d Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 6 Mar 2023 17:05:35 +0000 Subject: [PATCH 0976/5631] phy: xgene: Depend on ARCH_XGENE rather than plain arm64 The X-Gene PHY driver is unlikely to be useful on a kernel without general X-Gene support enabled but currently only depends on arm64 rather than the specific platform support. Narrow the dependency to ARCH_XGENE like we do for other X-Gene specific drivers to ensure that users who have configured down the set of platforms enabled don't see the option. Signed-off-by: Mark Brown Link: https://lore.kernel.org/r/20230221-phy-build-deps-v1-1-7091bcbd16b0@kernel.org Signed-off-by: Vinod Koul --- drivers/phy/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 7bd00a11d074..f46e3148d286 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -44,7 +44,7 @@ config PHY_PISTACHIO_USB config PHY_XGENE tristate "APM X-Gene 15Gbps PHY support" - depends on HAS_IOMEM && OF && (ARM64 || COMPILE_TEST) + depends on HAS_IOMEM && OF && (ARCH_XGENE || COMPILE_TEST) select GENERIC_PHY help This option enables support for APM X-Gene SoC multi-purpose PHY. -- GitLab From 4658842abce4bebb0a0caef53f9c99f0ec4e27e3 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 9 Feb 2023 10:13:10 +0100 Subject: [PATCH 0977/5631] interconnect: qcom: Drop obsolete dependency on COMPILE_TEST Since commit 0166dc11be91 ("of: make CONFIG_OF user selectable"), it is possible to test-build any driver which depends on OF on any architecture by explicitly selecting OF. Therefore depending on COMPILE_TEST as an alternative is no longer needed. Signed-off-by: Jean Delvare Cc: Andy Gross Cc: Bjorn Andersson Cc: Konrad Dybcio Cc: Georgi Djakov Link: https://lore.kernel.org/r/20230209101310.11942cd0@endymion.delvare Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/interconnect/qcom/Kconfig b/drivers/interconnect/qcom/Kconfig index 92d65c7bda23..825b647d9169 100644 --- a/drivers/interconnect/qcom/Kconfig +++ b/drivers/interconnect/qcom/Kconfig @@ -83,7 +83,7 @@ config INTERCONNECT_QCOM_RPMH_POSSIBLE default INTERCONNECT_QCOM depends on QCOM_RPMH || (COMPILE_TEST && !QCOM_RPMH) depends on QCOM_COMMAND_DB || (COMPILE_TEST && !QCOM_COMMAND_DB) - depends on OF || COMPILE_TEST + depends on OF help Compile-testing RPMH drivers is possible on other platforms, but in order to avoid link failures, drivers must not be built-in -- GitLab From 558ea12354882bb8250be8ea09a6658af3f7d912 Mon Sep 17 00:00:00 2001 From: Vivek Aknurwar Date: Fri, 13 Jan 2023 14:07:59 -0800 Subject: [PATCH 0978/5631] interconnect: Skip call into provider if initial bw is zero Currently framework sets bw even when init bw requirements are zero during provider registration, thus resulting bulk of set bw to hw. Avoid this behaviour by skipping provider set bw calls if init bw is zero. Signed-off-by: Vivek Aknurwar Link: https://lore.kernel.org/r/1673647679-15216-1-git-send-email-quic_viveka@quicinc.com Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 7a24c1444ace..446c9d1fb486 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -981,14 +981,17 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = node->init_avg; node->peak_bw = node->init_peak; - if (provider->pre_aggregate) - provider->pre_aggregate(node); - - if (provider->aggregate) - provider->aggregate(node, 0, node->init_avg, node->init_peak, - &node->avg_bw, &node->peak_bw); + if (node->avg_bw || node->peak_bw) { + if (provider->pre_aggregate) + provider->pre_aggregate(node); + + if (provider->aggregate) + provider->aggregate(node, 0, node->init_avg, node->init_peak, + &node->avg_bw, &node->peak_bw); + if (provider->set) + provider->set(node, node); + } - provider->set(node, node); node->avg_bw = 0; node->peak_bw = 0; -- GitLab From 4c4161b4c81b632fc29002c324e996cbb79894e7 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 3 Jan 2023 06:57:17 +0200 Subject: [PATCH 0979/5631] interconnect: qcom: drop obsolete OSM_L3/EPSS defines Since Qualcomm platforms have switched to the separate OSM_L3/EPSS driver, old related defines became unused. Drop them now. Suggested-by: Bjorn Andersson Fixes: 4529992c9474 ("interconnect: qcom: osm-l3: Use platform-independent node ids") Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230103045717.1079067-1-dmitry.baryshkov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/sc7180.h | 2 -- drivers/interconnect/qcom/sc7280.h | 2 -- drivers/interconnect/qcom/sc8180x.h | 2 -- drivers/interconnect/qcom/sdm845.h | 2 -- drivers/interconnect/qcom/sm8150.h | 2 -- drivers/interconnect/qcom/sm8250.h | 2 -- 6 files changed, 12 deletions(-) diff --git a/drivers/interconnect/qcom/sc7180.h b/drivers/interconnect/qcom/sc7180.h index 7a2b3eb00923..2b718922c109 100644 --- a/drivers/interconnect/qcom/sc7180.h +++ b/drivers/interconnect/qcom/sc7180.h @@ -145,7 +145,5 @@ #define SC7180_SLAVE_SERVICE_SNOC 134 #define SC7180_SLAVE_QDSS_STM 135 #define SC7180_SLAVE_TCU 136 -#define SC7180_MASTER_OSM_L3_APPS 137 -#define SC7180_SLAVE_OSM_L3 138 #endif diff --git a/drivers/interconnect/qcom/sc7280.h b/drivers/interconnect/qcom/sc7280.h index 1fb9839b2c14..175e400305c5 100644 --- a/drivers/interconnect/qcom/sc7280.h +++ b/drivers/interconnect/qcom/sc7280.h @@ -150,7 +150,5 @@ #define SC7280_SLAVE_PCIE_1 139 #define SC7280_SLAVE_QDSS_STM 140 #define SC7280_SLAVE_TCU 141 -#define SC7280_MASTER_EPSS_L3_APPS 142 -#define SC7280_SLAVE_EPSS_L3 143 #endif diff --git a/drivers/interconnect/qcom/sc8180x.h b/drivers/interconnect/qcom/sc8180x.h index c138dcd350f1..f8d90598335a 100644 --- a/drivers/interconnect/qcom/sc8180x.h +++ b/drivers/interconnect/qcom/sc8180x.h @@ -168,8 +168,6 @@ #define SC8180X_SLAVE_EBI_CH0_DISPLAY 158 #define SC8180X_SLAVE_MNOC_SF_MEM_NOC_DISPLAY 159 #define SC8180X_SLAVE_MNOC_HF_MEM_NOC_DISPLAY 160 -#define SC8180X_MASTER_OSM_L3_APPS 161 -#define SC8180X_SLAVE_OSM_L3 162 #define SC8180X_MASTER_QUP_CORE_0 163 #define SC8180X_MASTER_QUP_CORE_1 164 diff --git a/drivers/interconnect/qcom/sdm845.h b/drivers/interconnect/qcom/sdm845.h index 776e9c2acb27..bc7e425ce985 100644 --- a/drivers/interconnect/qcom/sdm845.h +++ b/drivers/interconnect/qcom/sdm845.h @@ -136,7 +136,5 @@ #define SDM845_SLAVE_SERVICE_SNOC 128 #define SDM845_SLAVE_QDSS_STM 129 #define SDM845_SLAVE_TCU 130 -#define SDM845_MASTER_OSM_L3_APPS 131 -#define SDM845_SLAVE_OSM_L3 132 #endif /* __DRIVERS_INTERCONNECT_QCOM_SDM845_H__ */ diff --git a/drivers/interconnect/qcom/sm8150.h b/drivers/interconnect/qcom/sm8150.h index 023161681fb8..1d587c94eb06 100644 --- a/drivers/interconnect/qcom/sm8150.h +++ b/drivers/interconnect/qcom/sm8150.h @@ -148,7 +148,5 @@ #define SM8150_SLAVE_VSENSE_CTRL_CFG 137 #define SM8150_SNOC_CNOC_MAS 138 #define SM8150_SNOC_CNOC_SLV 139 -#define SM8150_MASTER_OSM_L3_APPS 140 -#define SM8150_SLAVE_OSM_L3 141 #endif diff --git a/drivers/interconnect/qcom/sm8250.h b/drivers/interconnect/qcom/sm8250.h index e3fc56bc7ca0..209ab195f21f 100644 --- a/drivers/interconnect/qcom/sm8250.h +++ b/drivers/interconnect/qcom/sm8250.h @@ -158,7 +158,5 @@ #define SM8250_SLAVE_VSENSE_CTRL_CFG 147 #define SM8250_SNOC_CNOC_MAS 148 #define SM8250_SNOC_CNOC_SLV 149 -#define SM8250_MASTER_EPSS_L3_APPS 150 -#define SM8250_SLAVE_EPSS_L3 151 #endif -- GitLab From f730038fe6a6de170268fd779b2c029aa70a928b Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Tue, 3 Jan 2023 05:11:59 +0200 Subject: [PATCH 0980/5631] interconnect: qcom: osm-l3: drop unuserd header inclusion The commit 4529992c9474 ("interconnect: qcom: osm-l3: Use platform-independent node ids") made osm-l3 driver use platform-independent IDs, removing the need to include platform headers. Fixes: 4529992c9474 ("interconnect: qcom: osm-l3: Use platform-independent node ids") Signed-off-by: Dmitry Baryshkov Reviewed-by: Bjorn Andersson Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230103031159.1060075-1-dmitry.baryshkov@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/osm-l3.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index 1bafb54f1432..a1f4f918b911 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -14,13 +14,6 @@ #include -#include "sc7180.h" -#include "sc7280.h" -#include "sc8180x.h" -#include "sdm845.h" -#include "sm8150.h" -#include "sm8250.h" - #define LUT_MAX_ENTRIES 40U #define LUT_SRC GENMASK(31, 30) #define LUT_L_VAL GENMASK(7, 0) -- GitLab From 213913ff2b89ab5ba76aceba24198b217e8e325c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:08 -0600 Subject: [PATCH 0981/5631] interconnect: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230310144709.1542841-1-robh@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 446c9d1fb486..4175a42bf748 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -451,7 +451,7 @@ struct icc_path *of_icc_get_by_index(struct device *dev, int idx) * When the consumer DT node do not have "interconnects" property * return a NULL path to skip setting constraints. */ - if (!of_find_property(np, "interconnects", NULL)) + if (!of_property_present(np, "interconnects")) return NULL; /* @@ -544,7 +544,7 @@ struct icc_path *of_icc_get(struct device *dev, const char *name) * When the consumer DT node do not have "interconnects" property * return a NULL path to skip setting constraints. */ - if (!of_find_property(np, "interconnects", NULL)) + if (!of_property_present(np, "interconnects")) return NULL; /* -- GitLab From 419405c92299d793b95053aa54d95e2d3f45a1a4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:49 +0100 Subject: [PATCH 0982/5631] interconnect: drop racy registration API Now that all interconnect drivers have been converted to the new provider registration API, the old racy interface can be removed. Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230306075651.2449-22-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 16 ---------------- include/linux/interconnect-provider.h | 11 ----------- 2 files changed, 27 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 4175a42bf748..da456329c524 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1084,22 +1084,6 @@ void icc_provider_deregister(struct icc_provider *provider) } EXPORT_SYMBOL_GPL(icc_provider_deregister); -int icc_provider_add(struct icc_provider *provider) -{ - icc_provider_init(provider); - - return icc_provider_register(provider); -} -EXPORT_SYMBOL_GPL(icc_provider_add); - -void icc_provider_del(struct icc_provider *provider) -{ - WARN_ON(!list_empty(&provider->nodes)); - - icc_provider_deregister(provider); -} -EXPORT_SYMBOL_GPL(icc_provider_del); - static const struct of_device_id __maybe_unused ignore_list[] = { { .compatible = "qcom,sc7180-ipa-virt" }, { .compatible = "qcom,sc8180x-ipa-virt" }, diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index d12cd18aab3f..b9af9016a95e 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -125,8 +125,6 @@ int icc_nodes_remove(struct icc_provider *provider); void icc_provider_init(struct icc_provider *provider); int icc_provider_register(struct icc_provider *provider); void icc_provider_deregister(struct icc_provider *provider); -int icc_provider_add(struct icc_provider *provider); -void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); void icc_sync_state(struct device *dev); @@ -179,15 +177,6 @@ static inline int icc_provider_register(struct icc_provider *provider) static inline void icc_provider_deregister(struct icc_provider *provider) { } -static inline int icc_provider_add(struct icc_provider *provider) -{ - return -ENOTSUPP; -} - -static inline void icc_provider_del(struct icc_provider *provider) -{ -} - static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) { return ERR_PTR(-ENOTSUPP); -- GitLab From c9602aa0469e19a84f9552a146ef87ec5dc7d576 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Mar 2023 20:37:49 -0700 Subject: [PATCH 0983/5631] perf symbol: Avoid memory leak from abi::__cxa_demangle MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rather than allocate memory, allow abi::__cxa_demangle to do that. This avoids a problem where on error NULL was returned triggering a memory leak. Fixes: 3b4e4efe88f615f1 ("perf symbol: Add abi::__cxa_demangle C++ demangling support") Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: André Almeida Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320033810.980165-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/demangle-cxx.cpp | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/demangle-cxx.cpp b/tools/perf/util/demangle-cxx.cpp index 8708bcafd370..85b706641837 100644 --- a/tools/perf/util/demangle-cxx.cpp +++ b/tools/perf/util/demangle-cxx.cpp @@ -38,11 +38,10 @@ char *cxx_demangle_sym(const char *str, bool params __maybe_unused, return cplus_demangle(str, flags); #elif defined(HAVE_CXA_DEMANGLE_SUPPORT) - size_t len = strlen(str); - char *output = (char*)malloc(len); + char *output; int status; - output = abi::__cxa_demangle(str, output, &len, &status); + output = abi::__cxa_demangle(str, /*output_buffer=*/NULL, /*length=*/NULL, &status); return output; #else return NULL; -- GitLab From 39b5e434fb3f06fae44c8a2df87eca036f9f9b5c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Mar 2023 20:37:50 -0700 Subject: [PATCH 0984/5631] perf bpf_counter: Use public cpumap accessors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Avoid the use of internal apis via the cpumap accessor functions. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: André Almeida Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320033810.980165-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_counter.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 1b77436e067e..76ee3e86824a 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -545,7 +545,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) filter_type == BPERF_FILTER_TGID) key = perf_thread_map__pid(evsel->core.threads, i); else if (filter_type == BPERF_FILTER_CPU) - key = evsel->core.cpus->map[i].cpu; + key = perf_cpu_map__cpu(evsel->core.cpus, i).cpu; else break; @@ -587,9 +587,9 @@ static int bperf_sync_counters(struct evsel *evsel) { int num_cpu, i, cpu; - num_cpu = all_cpu_map->nr; + num_cpu = perf_cpu_map__nr(all_cpu_map); for (i = 0; i < num_cpu; i++) { - cpu = all_cpu_map->map[i].cpu; + cpu = perf_cpu_map__cpu(all_cpu_map, i).cpu; bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); } return 0; -- GitLab From 9bb5e1f682d8391b7e9918b12d22af9492b74dad Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Mar 2023 20:37:51 -0700 Subject: [PATCH 0985/5631] perf tests: Add common error route for code-reading MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A later change will enforce that the map is put on this path regardless of success or error. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: André Almeida Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320033810.980165-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/code-reading.c | 39 +++++++++++++++++++-------------- 1 file changed, 23 insertions(+), 16 deletions(-) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index cb8cd09938d5..fb67fd5ebd9f 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -236,18 +236,19 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, const char *objdump_name; char decomp_name[KMOD_DECOMP_LEN]; bool decomp = false; - int ret; + int ret, err = 0; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); - return 0; + goto out; } pr_debug("thread__find_map failed\n"); - return -1; + err = -1; + goto out; } pr_debug("File is: %s\n", al.map->dso->long_name); @@ -255,7 +256,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(al.map->dso)) { pr_debug("Unexpected kernel address - skipping\n"); - return 0; + goto out; } pr_debug("On file address is: %#"PRIx64"\n", al.addr); @@ -272,15 +273,18 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, al.addr, buf1, len); if (ret_len != len) { pr_debug("dso__data_read_offset failed\n"); - return -1; + err = -1; + goto out; } /* * Converting addresses for use by objdump requires more information. * map__load() does that. See map__rip_2objdump() for details. */ - if (map__load(al.map)) - return -1; + if (map__load(al.map)) { + err = -1; + goto out; + } /* objdump struggles with kcore - try each map only once */ if (dso__is_kcore(al.map->dso)) { @@ -290,12 +294,12 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, if (state->done[d] == al.map->start) { pr_debug("kcore map tested already"); pr_debug(" - skipping\n"); - return 0; + goto out; } } if (state->done_cnt >= ARRAY_SIZE(state->done)) { pr_debug("Too many kcore maps - skipping\n"); - return 0; + goto out; } state->done[state->done_cnt++] = al.map->start; } @@ -306,7 +310,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, decomp_name, sizeof(decomp_name)) < 0) { pr_debug("decompression failed\n"); - return -1; + err = -1; + goto out; } decomp = true; @@ -337,15 +342,16 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, */ pr_debug("objdump failed for kcore"); pr_debug(" - skipping\n"); - return 0; } else { - return -1; + err = -1; } + goto out; } } if (ret < 0) { pr_debug("read_via_objdump failed\n"); - return -1; + err = -1; + goto out; } /* The results should be identical */ @@ -355,11 +361,12 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, dump_buf(buf1, len); pr_debug("buf2 (objdump):\n"); dump_buf(buf2, len); - return -1; + err = -1; + goto out; } pr_debug("Bytes read match those read by objdump\n"); - - return 0; +out: + return err; } static int process_sample_event(struct machine *machine, -- GitLab From 82c6d83bc1779cc306f78083fc79dc7ec7d9b18d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Mar 2023 20:37:52 -0700 Subject: [PATCH 0986/5631] perf test: Fix memory leak in symbols MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit machine__delete() doesn't delete threads. Add call to delete threads ahead of deleting the machine. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: André Almeida Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320033810.980165-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/symbols.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/tests/symbols.c b/tools/perf/tests/symbols.c index 057b16df6416..0793f8f419e2 100644 --- a/tools/perf/tests/symbols.c +++ b/tools/perf/tests/symbols.c @@ -38,6 +38,7 @@ static int init_test_info(struct test_info *ti) static void exit_test_info(struct test_info *ti) { thread__put(ti->thread); + machine__delete_threads(ti->machine); machine__delete(ti->machine); } -- GitLab From ec9640f77d199c4ed78d7a00fbbaf78773c38d9d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Sun, 19 Mar 2023 20:37:53 -0700 Subject: [PATCH 0987/5631] perf symbol: Sort names under write lock MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If finding a name doesn't find the sorted names then they are allocated and sorted. This shouldn't be done under a read lock as another reader may access it. Release the read lock and acquire the write lock, then release the write lock and reacquire the read lock. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: André Almeida Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320033810.980165-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 317c0706852f..a458aa8b87bb 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2018,6 +2018,9 @@ static int map__groups__sort_by_name_from_rbtree(struct maps *maps) if (maps_by_name == NULL) return -1; + up_read(&maps->lock); + down_write(&maps->lock); + maps->maps_by_name = maps_by_name; maps->nr_maps_allocated = maps->nr_maps; @@ -2025,6 +2028,10 @@ static int map__groups__sort_by_name_from_rbtree(struct maps *maps) maps_by_name[i++] = map; __maps__sort_by_name(maps); + + up_write(&maps->lock); + down_read(&maps->lock); + return 0; } -- GitLab From 92717003de85771cb6ee200a46521f6d1b12e3f8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Mar 2023 10:13:42 +0100 Subject: [PATCH 0988/5631] clk: mediatek: mt81xx: Ensure fhctl code is available Just like in commit eddc63094855 ("clk: mediatek: Ensure fhctl code is available for COMMON_CLK_MT6795"), these three need the shared driver code, otherwise they run into link errors such as: aarch64-linux/bin/aarch64-linux-ld: drivers/clk/mediatek/clk-mt8192-apmixedsys.o: in function `clk_mt8192_apmixed_probe': clk-mt8192-apmixedsys.c:(.text+0x134): undefined reference to `fhctl_parse_dt' Fixes: 45a5cbe05d1f ("clk: mediatek: mt8173: Add support for frequency hopping through FHCTL") Fixes: 4d586e10c428 ("clk: mediatek: mt8192: Add support for frequency hopping through FHCTL") Fixes: da4a82dc67b0 ("clk: mediatek: mt8195: Add support for frequency hopping through FHCTL") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230320091353.1918439-1-arnd@kernel.org Reviewed-by: AngeloGioacchino Del Regno Reported-by: kernel test robot Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index c707c6fe45a3..61e3266d2346 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -478,6 +478,7 @@ config COMMON_CLK_MT8173 tristate "Clock driver for MediaTek MT8173" depends on ARM64 || COMPILE_TEST select COMMON_CLK_MEDIATEK + select COMMON_CLK_MEDIATEK_FHCTL default ARCH_MEDIATEK help This driver supports MediaTek MT8173 basic clocks and clocks @@ -686,6 +687,7 @@ config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST select COMMON_CLK_MEDIATEK + select COMMON_CLK_MEDIATEK_FHCTL default ARM64 help This driver supports MediaTek MT8192 basic clocks. @@ -766,6 +768,7 @@ config COMMON_CLK_MT8195 bool "Clock driver for MediaTek MT8195" depends on ARM64 || COMPILE_TEST select COMMON_CLK_MEDIATEK + select COMMON_CLK_MEDIATEK_FHCTL default ARCH_MEDIATEK help This driver supports MediaTek MT8195 clocks. -- GitLab From d54c1fd4a51e8fbc7f9da86b0cd338a4f7cd2bb2 Mon Sep 17 00:00:00 2001 From: Qin Jian Date: Mon, 19 Dec 2022 09:51:30 +0800 Subject: [PATCH 0989/5631] clk: Add Sunplus SP7021 clock driver Add clock driver for Sunplus SP7021 SoC. Signed-off-by: Qin Jian Link: https://lore.kernel.org/r/20221219015130.42621-1-qinjian@cqplus1.com Signed-off-by: Stephen Boyd --- MAINTAINERS | 1 + drivers/clk/Kconfig | 10 + drivers/clk/Makefile | 1 + drivers/clk/clk-sp7021.c | 713 +++++++++++++++++++++++++++++++++++ include/linux/clk-provider.h | 19 + 5 files changed, 744 insertions(+) create mode 100644 drivers/clk/clk-sp7021.c diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..f72107a6e86f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2849,6 +2849,7 @@ F: Documentation/devicetree/bindings/reset/sunplus,reset.yaml F: arch/arm/boot/dts/sunplus-sp7021*.dts* F: arch/arm/configs/sp7021_*defconfig F: arch/arm/mach-sunplus/ +F: drivers/clk/clk-sp7021.c F: drivers/irqchip/irq-sp7021-intc.c F: drivers/reset/reset-sunplus.c F: include/dt-bindings/clock/sunplus,sp7021-clkc.h diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index b6c5bf69a2b2..54e01bb2f568 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -436,6 +436,16 @@ config COMMON_CLK_K210 help Support for the Canaan Kendryte K210 RISC-V SoC clocks. +config COMMON_CLK_SP7021 + tristate "Clock driver for Sunplus SP7021 SoC" + depends on SOC_SP7021 || COMPILE_TEST + default SOC_SP7021 + help + This driver supports the Sunplus SP7021 SoC clocks. + It implements SP7021 PLLs/gate. + Not all features of the PLL are currently supported + by the driver. + source "drivers/clk/actions/Kconfig" source "drivers/clk/analogbits/Kconfig" source "drivers/clk/baikal-t1/Kconfig" diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e3ca0d058a25..7bbf77acf181 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -65,6 +65,7 @@ obj-$(CONFIG_COMMON_CLK_SI5351) += clk-si5351.o obj-$(CONFIG_COMMON_CLK_SI514) += clk-si514.o obj-$(CONFIG_COMMON_CLK_SI544) += clk-si544.o obj-$(CONFIG_COMMON_CLK_SI570) += clk-si570.o +obj-$(CONFIG_COMMON_CLK_SP7021) += clk-sp7021.o obj-$(CONFIG_COMMON_CLK_STM32F) += clk-stm32f4.o obj-$(CONFIG_COMMON_CLK_STM32H7) += clk-stm32h7.o obj-$(CONFIG_COMMON_CLK_STM32MP157) += clk-stm32mp1.o diff --git a/drivers/clk/clk-sp7021.c b/drivers/clk/clk-sp7021.c new file mode 100644 index 000000000000..8fec14120105 --- /dev/null +++ b/drivers/clk/clk-sp7021.c @@ -0,0 +1,713 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (C) Sunplus Technology Co., Ltd. + * All rights reserved. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* speical div_width values for PLLTV/PLLA */ +#define DIV_TV 33 +#define DIV_A 34 + +/* PLLTV parameters */ +enum { + SEL_FRA, + SDM_MOD, + PH_SEL, + NFRA, + DIVR, + DIVN, + DIVM, + P_MAX +}; + +#define MASK_SEL_FRA GENMASK(1, 1) +#define MASK_SDM_MOD GENMASK(2, 2) +#define MASK_PH_SEL GENMASK(4, 4) +#define MASK_NFRA GENMASK(12, 6) +#define MASK_DIVR GENMASK(8, 7) +#define MASK_DIVN GENMASK(7, 0) +#define MASK_DIVM GENMASK(14, 8) + +/* HIWORD_MASK FIELD_PREP */ +#define HWM_FIELD_PREP(mask, value) \ +({ \ + u32 _m = mask; \ + (_m << 16) | FIELD_PREP(_m, value); \ +}) + +struct sp_pll { + struct clk_hw hw; + void __iomem *reg; + spinlock_t lock; /* lock for reg */ + int div_shift; + int div_width; + int pd_bit; /* power down bit idx */ + int bp_bit; /* bypass bit idx */ + unsigned long brate; /* base rate, TODO: replace brate with muldiv */ + u32 p[P_MAX]; /* for hold PLLTV/PLLA parameters */ +}; + +#define to_sp_pll(_hw) container_of(_hw, struct sp_pll, hw) + +struct sp_clk_gate_info { + u16 reg; /* reg_index_shift */ + u16 ext_parent; /* parent is extclk */ +}; + +static const struct sp_clk_gate_info sp_clk_gates[] = { + { 0x02 }, + { 0x05 }, + { 0x06 }, + { 0x07 }, + { 0x09 }, + { 0x0b, 1 }, + { 0x0f, 1 }, + { 0x14 }, + { 0x15 }, + { 0x16 }, + { 0x17 }, + { 0x18, 1 }, + { 0x19, 1 }, + { 0x1a, 1 }, + { 0x1b, 1 }, + { 0x1c, 1 }, + { 0x1d, 1 }, + { 0x1e }, + { 0x1f, 1 }, + { 0x20 }, + { 0x21 }, + { 0x22 }, + { 0x23 }, + { 0x24 }, + { 0x25 }, + { 0x26 }, + { 0x2a }, + { 0x2b }, + { 0x2d }, + { 0x2e }, + { 0x30 }, + { 0x31 }, + { 0x32 }, + { 0x33 }, + { 0x3d }, + { 0x3e }, + { 0x3f }, + { 0x42 }, + { 0x44 }, + { 0x4b }, + { 0x4c }, + { 0x4d }, + { 0x4e }, + { 0x4f }, + { 0x50 }, + { 0x55 }, + { 0x60 }, + { 0x61 }, + { 0x6a }, + { 0x73 }, + { 0x86 }, + { 0x8a }, + { 0x8b }, + { 0x8d }, + { 0x8e }, + { 0x8f }, + { 0x90 }, + { 0x92 }, + { 0x93 }, + { 0x95 }, + { 0x96 }, + { 0x97 }, + { 0x98 }, + { 0x99 }, +}; + +#define _M 1000000UL +#define F_27M (27 * _M) + +/*********************************** PLL_TV **********************************/ + +/* TODO: set proper FVCO range */ +#define FVCO_MIN (100 * _M) +#define FVCO_MAX (200 * _M) + +#define F_MIN (FVCO_MIN / 8) +#define F_MAX (FVCO_MAX) + +static long plltv_integer_div(struct sp_pll *clk, unsigned long freq) +{ + /* valid m values: 27M must be divisible by m */ + static const u32 m_table[] = { + 1, 2, 3, 4, 5, 6, 8, 9, 10, 12, 15, 16, 18, 20, 24, 25, 27, 30, 32 + }; + u32 m, n, r; + unsigned long fvco, nf; + long ret; + + freq = clamp(freq, F_MIN, F_MAX); + + /* DIVR 0~3 */ + for (r = 0; r <= 3; r++) { + fvco = freq << r; + if (fvco <= FVCO_MAX) + break; + } + + /* DIVM */ + for (m = 0; m < ARRAY_SIZE(m_table); m++) { + nf = fvco * m_table[m]; + n = nf / F_27M; + if ((n * F_27M) == nf) + break; + } + if (m >= ARRAY_SIZE(m_table)) { + ret = -EINVAL; + goto err_not_found; + } + + /* save parameters */ + clk->p[SEL_FRA] = 0; + clk->p[DIVR] = r; + clk->p[DIVN] = n; + clk->p[DIVM] = m_table[m]; + + return freq; + +err_not_found: + pr_err("%s: %s freq:%lu not found a valid setting\n", + __func__, clk_hw_get_name(&clk->hw), freq); + + return ret; +} + +/* parameters for PLLTV fractional divider */ +static const u32 pt[][5] = { + /* conventional fractional */ + { + 1, /* factor */ + 5, /* 5 * p0 (nint) */ + 1, /* 1 * p0 */ + F_27M, /* F_27M / p0 */ + 1, /* p0 / p2 */ + }, + /* phase rotation */ + { + 10, /* factor */ + 54, /* 5.4 * p0 (nint) */ + 2, /* 0.2 * p0 */ + F_27M / 10, /* F_27M / p0 */ + 5, /* p0 / p2 */ + }, +}; + +static const u32 sdm_mod_vals[] = { 91, 55 }; + +static long plltv_fractional_div(struct sp_pll *clk, unsigned long freq) +{ + u32 m, r; + u32 nint, nfra; + u32 df_quotient_min = 210000000; + u32 df_remainder_min = 0; + unsigned long fvco, nf, f, fout = 0; + int sdm, ph; + + freq = clamp(freq, F_MIN, F_MAX); + + /* DIVR 0~3 */ + for (r = 0; r <= 3; r++) { + fvco = freq << r; + if (fvco <= FVCO_MAX) + break; + } + f = F_27M >> r; + + /* PH_SEL */ + for (ph = ARRAY_SIZE(pt) - 1; ph >= 0; ph--) { + const u32 *pp = pt[ph]; + + /* SDM_MOD */ + for (sdm = 0; sdm < ARRAY_SIZE(sdm_mod_vals); sdm++) { + u32 mod = sdm_mod_vals[sdm]; + + /* DIVM 1~32 */ + for (m = 1; m <= 32; m++) { + u32 df; /* diff freq */ + u32 df_quotient, df_remainder; + + nf = fvco * m; + nint = nf / pp[3]; + + if (nint < pp[1]) + continue; + if (nint > pp[1]) + break; + + nfra = (((nf % pp[3]) * mod * pp[4]) + (F_27M / 2)) / F_27M; + if (nfra) { + u32 df0 = f * (nint + pp[2]) / pp[0]; + u32 df1 = f * (mod - nfra) / mod / pp[4]; + + df = df0 - df1; + } else { + df = f * (nint) / pp[0]; + } + + df_quotient = df / m; + df_remainder = ((df % m) * 1000) / m; + + if (freq > df_quotient) { + df_quotient = freq - df_quotient - 1; + df_remainder = 1000 - df_remainder; + } else { + df_quotient = df_quotient - freq; + } + + if (df_quotient_min > df_quotient || + (df_quotient_min == df_quotient && + df_remainder_min > df_remainder)) { + /* found a closer freq, save parameters */ + clk->p[SEL_FRA] = 1; + clk->p[SDM_MOD] = sdm; + clk->p[PH_SEL] = ph; + clk->p[NFRA] = nfra; + clk->p[DIVR] = r; + clk->p[DIVM] = m; + + fout = df / m; + df_quotient_min = df_quotient; + df_remainder_min = df_remainder; + } + } + } + } + + if (!fout) { + pr_err("%s: %s freq:%lu not found a valid setting\n", + __func__, clk_hw_get_name(&clk->hw), freq); + return -EINVAL; + } + + return fout; +} + +static long plltv_div(struct sp_pll *clk, unsigned long freq) +{ + if (freq % 100) + return plltv_fractional_div(clk, freq); + + return plltv_integer_div(clk, freq); +} + +static int plltv_set_rate(struct sp_pll *clk) +{ + unsigned long flags; + u32 r0, r1, r2; + + r0 = BIT(clk->bp_bit + 16); + r0 |= HWM_FIELD_PREP(MASK_SEL_FRA, clk->p[SEL_FRA]); + r0 |= HWM_FIELD_PREP(MASK_SDM_MOD, clk->p[SDM_MOD]); + r0 |= HWM_FIELD_PREP(MASK_PH_SEL, clk->p[PH_SEL]); + r0 |= HWM_FIELD_PREP(MASK_NFRA, clk->p[NFRA]); + + r1 = HWM_FIELD_PREP(MASK_DIVR, clk->p[DIVR]); + + r2 = HWM_FIELD_PREP(MASK_DIVN, clk->p[DIVN] - 1); + r2 |= HWM_FIELD_PREP(MASK_DIVM, clk->p[DIVM] - 1); + + spin_lock_irqsave(&clk->lock, flags); + writel(r0, clk->reg); + writel(r1, clk->reg + 4); + writel(r2, clk->reg + 8); + spin_unlock_irqrestore(&clk->lock, flags); + + return 0; +} + +/*********************************** PLL_A ***********************************/ + +/* from Q628_PLLs_REG_setting.xlsx */ +static const struct { + u32 rate; + u32 regs[5]; +} pa[] = { + { + .rate = 135475200, + .regs = { + 0x4801, + 0x02df, + 0x248f, + 0x0211, + 0x33e9 + } + }, + { + .rate = 147456000, + .regs = { + 0x4801, + 0x1adf, + 0x2490, + 0x0349, + 0x33e9 + } + }, + { + .rate = 196608000, + .regs = { + 0x4801, + 0x42ef, + 0x2495, + 0x01c6, + 0x33e9 + } + }, +}; + +static int plla_set_rate(struct sp_pll *clk) +{ + const u32 *pp = pa[clk->p[0]].regs; + unsigned long flags; + int i; + + spin_lock_irqsave(&clk->lock, flags); + for (i = 0; i < ARRAY_SIZE(pa->regs); i++) + writel(0xffff0000 | pp[i], clk->reg + (i * 4)); + spin_unlock_irqrestore(&clk->lock, flags); + + return 0; +} + +static long plla_round_rate(struct sp_pll *clk, unsigned long rate) +{ + int i = ARRAY_SIZE(pa); + + while (--i) { + if (rate >= pa[i].rate) + break; + } + clk->p[0] = i; + + return pa[i].rate; +} + +/********************************** SP_PLL ***********************************/ + +static long sp_pll_calc_div(struct sp_pll *clk, unsigned long rate) +{ + u32 fbdiv; + u32 max = 1 << clk->div_width; + + fbdiv = DIV_ROUND_CLOSEST(rate, clk->brate); + if (fbdiv > max) + fbdiv = max; + + return fbdiv; +} + +static long sp_pll_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + struct sp_pll *clk = to_sp_pll(hw); + long ret; + + if (rate == *prate) { + ret = *prate; /* bypass */ + } else if (clk->div_width == DIV_A) { + ret = plla_round_rate(clk, rate); + } else if (clk->div_width == DIV_TV) { + ret = plltv_div(clk, rate); + if (ret < 0) + ret = *prate; + } else { + ret = sp_pll_calc_div(clk, rate) * clk->brate; + } + + return ret; +} + +static unsigned long sp_pll_recalc_rate(struct clk_hw *hw, + unsigned long prate) +{ + struct sp_pll *clk = to_sp_pll(hw); + u32 reg = readl(clk->reg); + unsigned long ret; + + if (reg & BIT(clk->bp_bit)) { + ret = prate; /* bypass */ + } else if (clk->div_width == DIV_A) { + ret = pa[clk->p[0]].rate; + } else if (clk->div_width == DIV_TV) { + u32 m, r, reg2; + + r = FIELD_GET(MASK_DIVR, readl(clk->reg + 4)); + reg2 = readl(clk->reg + 8); + m = FIELD_GET(MASK_DIVM, reg2) + 1; + + if (reg & MASK_SEL_FRA) { + /* fractional divider */ + u32 sdm = FIELD_GET(MASK_SDM_MOD, reg); + u32 ph = FIELD_GET(MASK_PH_SEL, reg); + u32 nfra = FIELD_GET(MASK_NFRA, reg); + const u32 *pp = pt[ph]; + unsigned long r0, r1; + + ret = prate >> r; + r0 = ret * (pp[1] + pp[2]) / pp[0]; + r1 = ret * (sdm_mod_vals[sdm] - nfra) / sdm_mod_vals[sdm] / pp[4]; + ret = (r0 - r1) / m; + } else { + /* integer divider */ + u32 n = FIELD_GET(MASK_DIVN, reg2) + 1; + + ret = (prate / m * n) >> r; + } + } else { + u32 fbdiv = ((reg >> clk->div_shift) & ((1 << clk->div_width) - 1)) + 1; + + ret = clk->brate * fbdiv; + } + + return ret; +} + +static int sp_pll_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long prate) +{ + struct sp_pll *clk = to_sp_pll(hw); + unsigned long flags; + u32 reg; + + reg = BIT(clk->bp_bit + 16); /* HIWORD_MASK */ + + if (rate == prate) { + reg |= BIT(clk->bp_bit); /* bypass */ + } else if (clk->div_width == DIV_A) { + return plla_set_rate(clk); + } else if (clk->div_width == DIV_TV) { + return plltv_set_rate(clk); + } else if (clk->div_width) { + u32 fbdiv = sp_pll_calc_div(clk, rate); + u32 mask = GENMASK(clk->div_shift + clk->div_width - 1, clk->div_shift); + + reg |= mask << 16; + reg |= ((fbdiv - 1) << clk->div_shift) & mask; + } + + spin_lock_irqsave(&clk->lock, flags); + writel(reg, clk->reg); + spin_unlock_irqrestore(&clk->lock, flags); + + return 0; +} + +static int sp_pll_enable(struct clk_hw *hw) +{ + struct sp_pll *clk = to_sp_pll(hw); + + writel(BIT(clk->pd_bit + 16) | BIT(clk->pd_bit), clk->reg); + + return 0; +} + +static void sp_pll_disable(struct clk_hw *hw) +{ + struct sp_pll *clk = to_sp_pll(hw); + + writel(BIT(clk->pd_bit + 16), clk->reg); +} + +static int sp_pll_is_enabled(struct clk_hw *hw) +{ + struct sp_pll *clk = to_sp_pll(hw); + + return readl(clk->reg) & BIT(clk->pd_bit); +} + +static const struct clk_ops sp_pll_ops = { + .enable = sp_pll_enable, + .disable = sp_pll_disable, + .is_enabled = sp_pll_is_enabled, + .round_rate = sp_pll_round_rate, + .recalc_rate = sp_pll_recalc_rate, + .set_rate = sp_pll_set_rate +}; + +static const struct clk_ops sp_pll_sub_ops = { + .enable = sp_pll_enable, + .disable = sp_pll_disable, + .is_enabled = sp_pll_is_enabled, + .recalc_rate = sp_pll_recalc_rate, +}; + +static struct clk_hw *sp_pll_register(struct device *dev, const char *name, + const struct clk_parent_data *parent_data, + void __iomem *reg, int pd_bit, int bp_bit, + unsigned long brate, int shift, int width, + unsigned long flags) +{ + struct sp_pll *pll; + struct clk_hw *hw; + struct clk_init_data initd = { + .name = name, + .parent_data = parent_data, + .ops = (bp_bit >= 0) ? &sp_pll_ops : &sp_pll_sub_ops, + .num_parents = 1, + .flags = flags, + }; + int ret; + + pll = devm_kzalloc(dev, sizeof(*pll), GFP_KERNEL); + if (!pll) + return ERR_PTR(-ENOMEM); + + pll->hw.init = &initd; + pll->reg = reg; + pll->pd_bit = pd_bit; + pll->bp_bit = bp_bit; + pll->brate = brate; + pll->div_shift = shift; + pll->div_width = width; + spin_lock_init(&pll->lock); + + hw = &pll->hw; + ret = devm_clk_hw_register(dev, hw); + if (ret) + return ERR_PTR(ret); + + return hw; +} + +#define PLLA_CTL (pll_base + 0x1c) +#define PLLE_CTL (pll_base + 0x30) +#define PLLF_CTL (pll_base + 0x34) +#define PLLTV_CTL (pll_base + 0x38) + +static int sp7021_clk_probe(struct platform_device *pdev) +{ + static const u32 sp_clken[] = { + 0x67ef, 0x03ff, 0xff03, 0xfff0, 0x0004, /* G0.1~5 */ + 0x0000, 0x8000, 0xffff, 0x0040, 0x0000, /* G0.6~10 */ + }; + static struct clk_parent_data pd_ext, pd_sys, pd_e; + struct device *dev = &pdev->dev; + void __iomem *clk_base, *pll_base, *sys_base; + struct clk_hw_onecell_data *clk_data; + struct clk_hw **hws; + int i; + + clk_base = devm_platform_ioremap_resource(pdev, 0); + if (!clk_base) + return -ENXIO; + pll_base = devm_platform_ioremap_resource(pdev, 1); + if (!pll_base) + return -ENXIO; + sys_base = devm_platform_ioremap_resource(pdev, 2); + if (!sys_base) + return -ENXIO; + + /* enable default clks */ + for (i = 0; i < ARRAY_SIZE(sp_clken); i++) + writel((sp_clken[i] << 16) | sp_clken[i], clk_base + i * 4); + + clk_data = devm_kzalloc(dev, struct_size(clk_data, hws, CLK_MAX), + GFP_KERNEL); + if (!clk_data) + return -ENOMEM; + + hws = clk_data->hws; + pd_ext.index = 0; + + /* PLLs */ + hws[PLL_A] = sp_pll_register(dev, "plla", &pd_ext, PLLA_CTL, + 11, 12, 27000000, 0, DIV_A, 0); + if (IS_ERR(hws[PLL_A])) + return PTR_ERR(hws[PLL_A]); + + hws[PLL_E] = sp_pll_register(dev, "plle", &pd_ext, PLLE_CTL, + 6, 2, 50000000, 0, 0, 0); + if (IS_ERR(hws[PLL_E])) + return PTR_ERR(hws[PLL_E]); + pd_e.hw = hws[PLL_E]; + hws[PLL_E_2P5] = sp_pll_register(dev, "plle_2p5", &pd_e, PLLE_CTL, + 13, -1, 2500000, 0, 0, 0); + if (IS_ERR(hws[PLL_E_2P5])) + return PTR_ERR(hws[PLL_E_2P5]); + hws[PLL_E_25] = sp_pll_register(dev, "plle_25", &pd_e, PLLE_CTL, + 12, -1, 25000000, 0, 0, 0); + if (IS_ERR(hws[PLL_E_25])) + return PTR_ERR(hws[PLL_E_25]); + hws[PLL_E_112P5] = sp_pll_register(dev, "plle_112p5", &pd_e, PLLE_CTL, + 11, -1, 112500000, 0, 0, 0); + if (IS_ERR(hws[PLL_E_112P5])) + return PTR_ERR(hws[PLL_E_112P5]); + + hws[PLL_F] = sp_pll_register(dev, "pllf", &pd_ext, PLLF_CTL, + 0, 10, 13500000, 1, 4, 0); + if (IS_ERR(hws[PLL_F])) + return PTR_ERR(hws[PLL_F]); + + hws[PLL_TV] = sp_pll_register(dev, "plltv", &pd_ext, PLLTV_CTL, + 0, 15, 27000000, 0, DIV_TV, 0); + if (IS_ERR(hws[PLL_TV])) + return PTR_ERR(hws[PLL_TV]); + hws[PLL_TV_A] = devm_clk_hw_register_divider(dev, "plltv_a", "plltv", 0, + PLLTV_CTL + 4, 5, 1, + CLK_DIVIDER_POWER_OF_TWO, + &to_sp_pll(hws[PLL_TV])->lock); + if (IS_ERR(hws[PLL_TV_A])) + return PTR_ERR(hws[PLL_TV_A]); + + /* system clock, should not be disabled */ + hws[PLL_SYS] = sp_pll_register(dev, "pllsys", &pd_ext, sys_base, + 10, 9, 13500000, 0, 4, CLK_IS_CRITICAL); + if (IS_ERR(hws[PLL_SYS])) + return PTR_ERR(hws[PLL_SYS]); + pd_sys.hw = hws[PLL_SYS]; + + /* gates */ + for (i = 0; i < ARRAY_SIZE(sp_clk_gates); i++) { + char name[10]; + u32 j = sp_clk_gates[i].reg; + struct clk_parent_data *pd = sp_clk_gates[i].ext_parent ? &pd_ext : &pd_sys; + + sprintf(name, "%02d_0x%02x", i, j); + hws[i] = devm_clk_hw_register_gate_parent_data(dev, name, pd, 0, + clk_base + (j >> 4) * 4, + j & 0x0f, + CLK_GATE_HIWORD_MASK, + NULL); + if (IS_ERR(hws[i])) + return PTR_ERR(hws[i]); + } + + clk_data->num = CLK_MAX; + + return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_data); +} + +static const struct of_device_id sp7021_clk_dt_ids[] = { + { .compatible = "sunplus,sp7021-clkc" }, + { } +}; +MODULE_DEVICE_TABLE(of, sp7021_clk_dt_ids); + +static struct platform_driver sp7021_clk_driver = { + .probe = sp7021_clk_probe, + .driver = { + .name = "sp7021-clk", + .of_match_table = sp7021_clk_dt_ids, + }, +}; +module_platform_driver(sp7021_clk_driver); + +MODULE_AUTHOR("Sunplus Technology"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Clock driver for Sunplus SP7021 SoC"); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..0e3bc3eb9911 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate_parent_data - register a gate clock with the + * clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- GitLab From 34f576c95d1bd1be3f123c2d1f3db084e5e72583 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 20 Mar 2023 20:35:16 +0200 Subject: [PATCH 0990/5631] perf intel-pt: Add event type names UINTR and UIRET UINTR and UIRET are listed in table 32-50 "CFE Packet Type and Vector Fields Details" in the Intel Processor Trace chapter of The Intel SDM Volume 3 version 078. The codes are for "User interrupt delivered" and "Exiting from user interrupt routine" respectively. Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230320183517.15099-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 976f8bfe099c..c9296d8b33c0 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1906,7 +1906,7 @@ static int perf_sample__fprintf_synth_evt(struct perf_sample *sample, FILE *fp) struct perf_synth_intel_evt *data = perf_sample__synth_ptr(sample); const char *cfe[32] = {NULL, "INTR", "IRET", "SMI", "RSM", "SIPI", "INIT", "VMENTRY", "VMEXIT", "VMEXIT_INTR", - "SHUTDOWN"}; + "SHUTDOWN", NULL, "UINTR", "UIRET"}; const char *evd[64] = {"PFA", "VMXQ", "VMXR"}; const char *s; int len, i; -- GitLab From 052072f69f28864cebaeb6ca9dc2c9825b72c834 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 20 Mar 2023 20:35:17 +0200 Subject: [PATCH 0991/5631] perf intel-pt: Add support for new branch instructions ERETS and ERETU Intel Flexible Return and Event Delivery (FRED) adds instructions ERETS (return to supervisor) and ERETU (return to user). Intel PT instruction decoder needs to know about these instructions because they are branch instructions. Similar to IRET instructions, when the decoder encounters one of these instructions it will match it to a TIP (target instruction pointer) packet that informs what the branch destination is. The existing "x86 instruction decoder - new instructions" test can be used to test the result e.g. $ perf test -v ins |& grep eret Decoded ok: f2 0f 01 ca erets Decoded ok: f3 0f 01 ca eretu Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230320183517.15099-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/insn-x86.c | 4 ++++ .../intel-pt-decoder/intel-pt-insn-decoder.c | 18 ++++++++++++++++++ .../intel-pt-decoder/intel-pt-insn-decoder.h | 2 ++ 3 files changed, 24 insertions(+) diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index 94b490c434d0..735257d205b5 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -29,6 +29,8 @@ struct test_data test_data_64[] = { #include "insn-x86-dat-64.c" {{0x0f, 0x01, 0xee}, 3, 0, NULL, NULL, "0f 01 ee \trdpkru"}, {{0x0f, 0x01, 0xef}, 3, 0, NULL, NULL, "0f 01 ef \twrpkru"}, + {{0xf2, 0x0f, 0x01, 0xca}, 4, 0, "erets", "indirect", "f2 0f 01 ca \terets"}, + {{0xf3, 0x0f, 0x01, 0xca}, 4, 0, "eretu", "indirect", "f3 0f 01 ca \teretu"}, {{0}, 0, 0, NULL, NULL, NULL}, }; @@ -49,6 +51,8 @@ static int get_op(const char *op_str) {"syscall", INTEL_PT_OP_SYSCALL}, {"sysret", INTEL_PT_OP_SYSRET}, {"vmentry", INTEL_PT_OP_VMENTRY}, + {"erets", INTEL_PT_OP_ERETS}, + {"eretu", INTEL_PT_OP_ERETU}, {NULL, 0}, }; struct val_data *val; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c index 22308dd93010..c5d57027ec23 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c @@ -52,6 +52,20 @@ static void intel_pt_insn_decoder(struct insn *insn, op = INTEL_PT_OP_VMENTRY; branch = INTEL_PT_BR_INDIRECT; break; + case 0xca: + switch (insn->prefixes.bytes[3]) { + case 0xf2: /* erets */ + op = INTEL_PT_OP_ERETS; + branch = INTEL_PT_BR_INDIRECT; + break; + case 0xf3: /* eretu */ + op = INTEL_PT_OP_ERETU; + branch = INTEL_PT_BR_INDIRECT; + break; + default: + break; + } + break; default: break; } @@ -230,6 +244,8 @@ const char *branch_name[] = { [INTEL_PT_OP_SYSCALL] = "Syscall", [INTEL_PT_OP_SYSRET] = "Sysret", [INTEL_PT_OP_VMENTRY] = "VMentry", + [INTEL_PT_OP_ERETS] = "Erets", + [INTEL_PT_OP_ERETU] = "Eretu", }; const char *intel_pt_insn_name(enum intel_pt_insn_op op) @@ -273,6 +289,8 @@ int intel_pt_insn_type(enum intel_pt_insn_op op) case INTEL_PT_OP_LOOP: return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL; case INTEL_PT_OP_IRET: + case INTEL_PT_OP_ERETS: + case INTEL_PT_OP_ERETU: return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT; case INTEL_PT_OP_INT: diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h index e3338b56a75f..7fb7fe3a1566 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h @@ -25,6 +25,8 @@ enum intel_pt_insn_op { INTEL_PT_OP_SYSCALL, INTEL_PT_OP_SYSRET, INTEL_PT_OP_VMENTRY, + INTEL_PT_OP_ERETS, + INTEL_PT_OP_ERETU, }; enum intel_pt_insn_branch { -- GitLab From f43cc1a9a8612ca591e4c205b9f503d63380eccc Mon Sep 17 00:00:00 2001 From: German Gomez Date: Mon, 20 Mar 2023 15:15:05 +0000 Subject: [PATCH 0992/5631] perf event: Add 'simd_flags' field to 'struct perf_sample' Add new field to 'struct perf_sample' to store flags related to SIMD ops. It will be used to store SIMD information from SVE and NEON when profiling using ARM SPE. Signed-off-by: German Gomez Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Anshuman.Khandual@arm.com Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230320151509.1137462-2-james.clark@arm.com Signed-off-by: James Clark Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sample.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h index 33b08e0ac746..c92ad0f51ecd 100644 --- a/tools/perf/util/sample.h +++ b/tools/perf/util/sample.h @@ -66,6 +66,18 @@ struct aux_sample { void *data; }; +struct simd_flags { + u64 arch:1, /* architecture (isa) */ + pred:2; /* predication */ +}; + +/* simd architecture flags */ +#define SIMD_OP_FLAGS_ARCH_SVE 0x01 /* ARM SVE */ + +/* simd predicate flags */ +#define SIMD_OP_FLAGS_PRED_PARTIAL 0x01 /* partial predicate */ +#define SIMD_OP_FLAGS_PRED_EMPTY 0x02 /* empty predicate */ + struct perf_sample { u64 ip; u32 pid, tid; @@ -106,6 +118,7 @@ struct perf_sample { struct stack_dump user_stack; struct sample_read read; struct aux_sample aux_sample; + struct simd_flags simd_flags; }; /* -- GitLab From 0066015a3d8f9c01a17eb04579edba7dac9510af Mon Sep 17 00:00:00 2001 From: German Gomez Date: Mon, 20 Mar 2023 15:15:06 +0000 Subject: [PATCH 0993/5631] perf arm-spe: Refactor arm-spe to support operation packet type Extend the decoder of Arm SPE records to support more fields from the operation packet type. Not all fields are being decoded by this commit. Only those needed to support the use-case SVE load/store/other operations. Suggested-by: Leo Yan Signed-off-by: German Gomez Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Anshuman.Khandual@arm.com Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230320151509.1137462-2-james.clark@arm.com Signed-off-by: James Clark Signed-off-by: Arnaldo Carvalho de Melo --- .../util/arm-spe-decoder/arm-spe-decoder.c | 30 ++++++++++-- .../util/arm-spe-decoder/arm-spe-decoder.h | 47 +++++++++++++++---- tools/perf/util/arm-spe.c | 8 ++-- 3 files changed, 67 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 40dcedfd75cd..f3918f290df5 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -190,11 +190,27 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) decoder->record.context_id = payload; break; case ARM_SPE_OP_TYPE: - if (idx == SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC) { - if (payload & 0x1) - decoder->record.op = ARM_SPE_ST; + switch (idx) { + case SPE_OP_PKT_HDR_CLASS_LD_ST_ATOMIC: + decoder->record.op |= ARM_SPE_OP_LDST; + if (payload & SPE_OP_PKT_ST) + decoder->record.op |= ARM_SPE_OP_ST; else - decoder->record.op = ARM_SPE_LD; + decoder->record.op |= ARM_SPE_OP_LD; + if (SPE_OP_PKT_IS_LDST_SVE(payload)) + decoder->record.op |= ARM_SPE_OP_SVE_LDST; + break; + case SPE_OP_PKT_HDR_CLASS_OTHER: + decoder->record.op |= ARM_SPE_OP_OTHER; + if (SPE_OP_PKT_IS_OTHER_SVE_OP(payload)) + decoder->record.op |= ARM_SPE_OP_SVE_OTHER; + break; + case SPE_OP_PKT_HDR_CLASS_BR_ERET: + decoder->record.op |= ARM_SPE_OP_BRANCH_ERET; + break; + default: + pr_err("Get packet error!\n"); + return -1; } break; case ARM_SPE_EVENTS: @@ -222,6 +238,12 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder) if (payload & BIT(EV_MISPRED)) decoder->record.type |= ARM_SPE_BRANCH_MISS; + if (payload & BIT(EV_PARTIAL_PREDICATE)) + decoder->record.type |= ARM_SPE_SVE_PARTIAL_PRED; + + if (payload & BIT(EV_EMPTY_PREDICATE)) + decoder->record.type |= ARM_SPE_SVE_EMPTY_PRED; + break; case ARM_SPE_DATA_SOURCE: decoder->record.source = payload; diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h index 46a61df1145b..1443c28545a9 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -14,19 +14,46 @@ #include "arm-spe-pkt-decoder.h" enum arm_spe_sample_type { - ARM_SPE_L1D_ACCESS = 1 << 0, - ARM_SPE_L1D_MISS = 1 << 1, - ARM_SPE_LLC_ACCESS = 1 << 2, - ARM_SPE_LLC_MISS = 1 << 3, - ARM_SPE_TLB_ACCESS = 1 << 4, - ARM_SPE_TLB_MISS = 1 << 5, - ARM_SPE_BRANCH_MISS = 1 << 6, - ARM_SPE_REMOTE_ACCESS = 1 << 7, + ARM_SPE_L1D_ACCESS = 1 << 0, + ARM_SPE_L1D_MISS = 1 << 1, + ARM_SPE_LLC_ACCESS = 1 << 2, + ARM_SPE_LLC_MISS = 1 << 3, + ARM_SPE_TLB_ACCESS = 1 << 4, + ARM_SPE_TLB_MISS = 1 << 5, + ARM_SPE_BRANCH_MISS = 1 << 6, + ARM_SPE_REMOTE_ACCESS = 1 << 7, + ARM_SPE_SVE_PARTIAL_PRED = 1 << 8, + ARM_SPE_SVE_EMPTY_PRED = 1 << 9, }; enum arm_spe_op_type { - ARM_SPE_LD = 1 << 0, - ARM_SPE_ST = 1 << 1, + /* First level operation type */ + ARM_SPE_OP_OTHER = 1 << 0, + ARM_SPE_OP_LDST = 1 << 1, + ARM_SPE_OP_BRANCH_ERET = 1 << 2, + + /* Second level operation type for OTHER */ + ARM_SPE_OP_SVE_OTHER = 1 << 16, + ARM_SPE_OP_SVE_FP = 1 << 17, + ARM_SPE_OP_SVE_PRED_OTHER = 1 << 18, + + /* Second level operation type for LDST */ + ARM_SPE_OP_LD = 1 << 16, + ARM_SPE_OP_ST = 1 << 17, + ARM_SPE_OP_ATOMIC = 1 << 18, + ARM_SPE_OP_EXCL = 1 << 19, + ARM_SPE_OP_AR = 1 << 20, + ARM_SPE_OP_SIMD_FP = 1 << 21, + ARM_SPE_OP_GP_REG = 1 << 22, + ARM_SPE_OP_UNSPEC_REG = 1 << 23, + ARM_SPE_OP_NV_SYSREG = 1 << 24, + ARM_SPE_OP_SVE_LDST = 1 << 25, + ARM_SPE_OP_SVE_PRED_LDST = 1 << 26, + ARM_SPE_OP_SVE_SG = 1 << 27, + + /* Second level operation type for BRANCH_ERET */ + ARM_SPE_OP_BR_COND = 1 << 16, + ARM_SPE_OP_BR_INDIRECT = 1 << 17, }; enum arm_spe_neoverse_data_source { diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 906476a839e1..bfae4731a47a 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -411,7 +411,7 @@ static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *rec * We have no data on the hit level or data source for stores in the * Neoverse SPE records. */ - if (record->op & ARM_SPE_ST) { + if (record->op & ARM_SPE_OP_ST) { data_src->mem_lvl = PERF_MEM_LVL_NA; data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA; data_src->mem_snoop = PERF_MEM_SNOOP_NA; @@ -497,12 +497,12 @@ static void arm_spe__synth_data_source_generic(const struct arm_spe_record *reco static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr) { - union perf_mem_data_src data_src = { 0 }; + union perf_mem_data_src data_src = { .mem_op = PERF_MEM_OP_NA }; bool is_neoverse = is_midr_in_range_list(midr, neoverse_spe); - if (record->op == ARM_SPE_LD) + if (record->op & ARM_SPE_OP_LD) data_src.mem_op = PERF_MEM_OP_LOAD; - else if (record->op == ARM_SPE_ST) + else if (record->op & ARM_SPE_OP_ST) data_src.mem_op = PERF_MEM_OP_STORE; else return 0; -- GitLab From 03a6c16ebf0162b57acd16c2dd2baa79d8db2a97 Mon Sep 17 00:00:00 2001 From: German Gomez Date: Mon, 20 Mar 2023 15:15:07 +0000 Subject: [PATCH 0994/5631] perf arm-spe: Add SVE flags to the SPE samples Add flags from the Scalable Vector Extension (SVE) to the SPE samples which are available from Armv8.3 (FEAT_SPEv1p1). These will be displayed in a new SIMD sort field in a later commit. Signed-off-by: German Gomez Signed-off-by: James Clark Acked-by: Ian Rogers Link: https://lore.kernel.org/r/20230320151509.1137462-2-james.clark@arm.com Cc: Anshuman.Khandual@arm.com Cc: Mark Rutland Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Cc: Will Deacon Cc: Leo Yan Cc: Mike Leach Cc: Alexander Shishkin Cc: linux-arm-kernel@lists.infradead.org Cc: John Garry Cc: Ingo Molnar Cc: linux-kernel@vger.kernel.org Cc: linux-perf-users@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/arm-spe.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index bfae4731a47a..7b36ba6b4079 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -273,6 +273,25 @@ static int arm_spe_set_tid(struct arm_spe_queue *speq, pid_t tid) return 0; } +static struct simd_flags arm_spe__synth_simd_flags(const struct arm_spe_record *record) +{ + struct simd_flags simd_flags = {}; + + if ((record->op & ARM_SPE_OP_LDST) && (record->op & ARM_SPE_OP_SVE_LDST)) + simd_flags.arch |= SIMD_OP_FLAGS_ARCH_SVE; + + if ((record->op & ARM_SPE_OP_OTHER) && (record->op & ARM_SPE_OP_SVE_OTHER)) + simd_flags.arch |= SIMD_OP_FLAGS_ARCH_SVE; + + if (record->type & ARM_SPE_SVE_PARTIAL_PRED) + simd_flags.pred |= SIMD_OP_FLAGS_PRED_PARTIAL; + + if (record->type & ARM_SPE_SVE_EMPTY_PRED) + simd_flags.pred |= SIMD_OP_FLAGS_PRED_EMPTY; + + return simd_flags; +} + static void arm_spe_prep_sample(struct arm_spe *spe, struct arm_spe_queue *speq, union perf_event *event, @@ -289,6 +308,7 @@ static void arm_spe_prep_sample(struct arm_spe *spe, sample->tid = speq->tid; sample->period = 1; sample->cpu = speq->cpu; + sample->simd_flags = arm_spe__synth_simd_flags(record); event->sample.header.type = PERF_RECORD_SAMPLE; event->sample.header.misc = sample->cpumode; -- GitLab From ea15483e7c55f73809cd9e208fff511966539ee5 Mon Sep 17 00:00:00 2001 From: German Gomez Date: Mon, 20 Mar 2023 15:15:08 +0000 Subject: [PATCH 0995/5631] perf report: Add 'simd' sort field Add 'simd' sort field to visualize SIMD ops in 'perf report'. Rows are labeled with the SIMD ISA, and the type of predicate (if any): - [p] partial predicate - [e] empty predicate (no elements in the vector being used) Example with Arm SPE and SVE (Scalable Vector Extension): #include double src[1025], dst[1025]; int main(void) { svfloat64_t vc = svdup_f64(1); for(;;) for(int i = 0; i < 1025; i += svcntd()) { svbool_t pg = svwhilelt_b64(i, 1025); svfloat64_t vsrc = svld1(pg, &src[i]); svfloat64_t vdst = svadd_x(pg, vsrc, vc); svst1(pg, &dst[i], vdst); } return 0; } ... compiled using "gcc-11 -march=armv8-a+sve -O3" Profiling on a platform that implements FEAT_SVE and FEAT_SPEv1p1: $ perf record -e arm_spe_0// -- ./a.out $ perf report --itrace=i1i -s overhead,pid,simd,sym Overhead Pid:Command Simd Symbol ........ ................ ....... ...................... 53.76% 10758:program [.] main 46.14% 10758:program [.] SVE [.] main 0.09% 10758:program [p] SVE [.] main The report shows 0.09% of the sampled SVE operations use partial predicates due to src and dst arrays not being multiples of the vector register lengths. Signed-off-by: German Gomez Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Anshuman.Khandual@arm.com Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230320151509.1137462-2-james.clark@arm.com Signed-off-by: James Clark Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 1 + tools/perf/util/hist.c | 1 + tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 47 ++++++++++++++++++++++++ tools/perf/util/sort.h | 2 + 5 files changed, 52 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index c242e8da6b1a..cfd502f7e6da 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,7 @@ OPTIONS - addr: (Full) virtual address of the sampled instruction - retire_lat: On X86, this reports pipeline stall of this instruction compared to the previous instruction in cycles. And currently supported only on X86 + - simd: Flags describing a SIMD operation. "e" for empty Arm SVE predicate. "p" for partial Arm SVE predicate By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 3670136a0074..0c11f50abfec 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -745,6 +745,7 @@ __hists__add_entry(struct hists *hists, .weight = sample->weight, .ins_lat = sample->ins_lat, .p_stage_cyc = sample->p_stage_cyc, + .simd_flags = sample->simd_flags, }, *he = hists__findnew_entry(hists, &entry, al, sample_self); if (!hists->has_callchains && he && he->callchain_size != 0) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 86a677954279..afc9f1c7f4dc 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -81,6 +81,7 @@ enum hist_column { HISTC_ADDR_FROM, HISTC_ADDR_TO, HISTC_ADDR, + HISTC_SIMD, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 093a0c8b2e3d..e11e68ecf0a2 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -139,6 +139,52 @@ struct sort_entry sort_thread = { .se_width_idx = HISTC_THREAD, }; +/* --sort simd */ + +static int64_t +sort__simd_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (left->simd_flags.arch != right->simd_flags.arch) + return (int64_t) left->simd_flags.arch - right->simd_flags.arch; + + return (int64_t) left->simd_flags.pred - right->simd_flags.pred; +} + +static const char *hist_entry__get_simd_name(struct simd_flags *simd_flags) +{ + u64 arch = simd_flags->arch; + + if (arch & SIMD_OP_FLAGS_ARCH_SVE) + return "SVE"; + else + return "n/a"; +} + +static int hist_entry__simd_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width __maybe_unused) +{ + const char *name; + + if (!he->simd_flags.arch) + return repsep_snprintf(bf, size, ""); + + name = hist_entry__get_simd_name(&he->simd_flags); + + if (he->simd_flags.pred & SIMD_OP_FLAGS_PRED_EMPTY) + return repsep_snprintf(bf, size, "[e] %s", name); + else if (he->simd_flags.pred & SIMD_OP_FLAGS_PRED_PARTIAL) + return repsep_snprintf(bf, size, "[p] %s", name); + + return repsep_snprintf(bf, size, "[.] %s", name); +} + +struct sort_entry sort_simd = { + .se_header = "Simd ", + .se_cmp = sort__simd_cmp, + .se_snprintf = hist_entry__simd_snprintf, + .se_width_idx = HISTC_SIMD, +}; + /* --sort comm */ /* @@ -2142,6 +2188,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_ADDR, "addr", sort_addr), DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc), DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc), + DIM(SORT_SIMD, "simd", sort_simd) }; #undef DIM diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 22f437c3476f..ecfb7f1359d5 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -111,6 +111,7 @@ struct hist_entry { u64 p_stage_cyc; u8 cpumode; u8 depth; + struct simd_flags simd_flags; /* We are added by hists__add_dummy_entry. */ bool dummy; @@ -241,6 +242,7 @@ enum sort_type { SORT_ADDR, SORT_LOCAL_RETIRE_LAT, SORT_GLOBAL_RETIRE_LAT, + SORT_SIMD, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, -- GitLab From 2d337b7158f8c38dacf8394028ab87b8a25ed707 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Wed, 1 Mar 2023 10:06:27 +0000 Subject: [PATCH 0996/5631] userfaultfd: move unprivileged_userfaultfd sysctl to its own file The sysctl_unprivileged_userfaultfd is part of userfaultfd, move it to its own file. Signed-off-by: ZhangPeng Signed-off-by: Luis Chamberlain --- fs/userfaultfd.c | 20 +++++++++++++++++++- include/linux/userfaultfd_k.h | 2 -- kernel/sysctl.c | 11 ----------- 3 files changed, 19 insertions(+), 14 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 44d1ee429eb0..d01f803a6b11 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -32,7 +32,22 @@ #include #include -int sysctl_unprivileged_userfaultfd __read_mostly; +static int sysctl_unprivileged_userfaultfd __read_mostly; + +#ifdef CONFIG_SYSCTL +static struct ctl_table vm_userfaultfd_table[] = { + { + .procname = "unprivileged_userfaultfd", + .data = &sysctl_unprivileged_userfaultfd, + .maxlen = sizeof(sysctl_unprivileged_userfaultfd), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; +#endif static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; @@ -2178,6 +2193,9 @@ static int __init userfaultfd_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); +#ifdef CONFIG_SYSCTL + register_sysctl_init("vm", vm_userfaultfd_table); +#endif return 0; } __initcall(userfaultfd_init); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..fff49fec0258 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,8 +36,6 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int sysctl_unprivileged_userfaultfd; - extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1c240d2c99bc..c14552a662ae 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2438,17 +2438,6 @@ static struct ctl_table vm_table[] = { .extra1 = (void *)&mmap_rnd_compat_bits_min, .extra2 = (void *)&mmap_rnd_compat_bits_max, }, -#endif -#ifdef CONFIG_USERFAULTFD - { - .procname = "unprivileged_userfaultfd", - .data = &sysctl_unprivileged_userfaultfd, - .maxlen = sizeof(sysctl_unprivileged_userfaultfd), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { } }; -- GitLab From 962de54828c5bb100eb8de881b79ed9c8b7468c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 9 Mar 2023 20:20:11 +0800 Subject: [PATCH 0997/5631] mm: hugetlb: move hugeltb sysctls to its own file This moves all hugetlb sysctls to its own file, also kill an useless hugetlb_treat_movable_handler() defination. Signed-off-by: Kefeng Wang Reviewed-by: Luis Chamberlain Reviewed-by: Mike Kravetz Reviewed-by: Muchun Song Signed-off-by: Luis Chamberlain --- include/linux/hugetlb.h | 8 ------- kernel/sysctl.c | 32 -------------------------- mm/hugetlb.c | 51 ++++++++++++++++++++++++++++++++++++++--- 3 files changed, 48 insertions(+), 43 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..4056b05d81ed 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); - int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c14552a662ae..ce0297acf97c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,38 +2140,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, -#endif -#ifdef CONFIG_HUGETLB_PAGE - { - .procname = "nr_hugepages", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_sysctl_handler, - }, -#ifdef CONFIG_NUMA - { - .procname = "nr_hugepages_mempolicy", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = &hugetlb_mempolicy_sysctl_handler, - }, -#endif - { - .procname = "hugetlb_shm_group", - .data = &sysctl_hugetlb_shm_group, - .maxlen = sizeof(gid_t), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nr_overcommit_hugepages", - .data = NULL, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = hugetlb_overcommit_handler, - }, #endif { .procname = "lowmem_reserve_ratio", diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 07abcb6eb203..0ee77c55e44e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4202,6 +4202,12 @@ static void __init hugetlb_sysfs_init(void) hugetlb_register_all_nodes(); } +#ifdef CONFIG_SYSCTL +static void hugetlb_sysctl_init(void); +#else +static inline void hugetlb_sysctl_init(void) { } +#endif + static int __init hugetlb_init(void) { int i; @@ -4257,6 +4263,7 @@ static int __init hugetlb_init(void) hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); + hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); @@ -4588,7 +4595,7 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, return ret; } -int hugetlb_sysctl_handler(struct ctl_table *table, int write, +static int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { @@ -4597,7 +4604,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write, } #ifdef CONFIG_NUMA -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, +static int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, @@ -4605,7 +4612,7 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, } #endif /* CONFIG_NUMA */ -int hugetlb_overcommit_handler(struct ctl_table *table, int write, +static int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; @@ -4634,6 +4641,44 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, return ret; } +static struct ctl_table hugetlb_table[] = { + { + .procname = "nr_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_sysctl_handler, + }, +#ifdef CONFIG_NUMA + { + .procname = "nr_hugepages_mempolicy", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &hugetlb_mempolicy_sysctl_handler, + }, +#endif + { + .procname = "hugetlb_shm_group", + .data = &sysctl_hugetlb_shm_group, + .maxlen = sizeof(gid_t), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "nr_overcommit_hugepages", + .data = NULL, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = hugetlb_overcommit_handler, + }, + { } +}; + +static void hugetlb_sysctl_init(void) +{ + register_sysctl_init("vm", hugetlb_table); +} #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) -- GitLab From 6b301ded45a6d9538f5f579a2e9f4b6c45fa988b Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Mon, 20 Mar 2023 23:14:15 -0700 Subject: [PATCH 0998/5631] tpm: Fix a possible dereference of ERR_PTR in tpm_init() Smatch reports: drivers/char/tpm/tpm-interface.c:470 tpm_init() error: 'tpm_class' dereferencing possible ERR_PTR() If class_create() returns error pointer, we are dereferencing a possible error pointer. Fix this by moving the dereference post error handling. Fixes: a010eb881243 ("tpm: fix up the tpm_class shutdown_pre pointer when created") Signed-off-by: Harshit Mogalapalli Link: https://lore.kernel.org/r/20230321061416.626561-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Greg Kroah-Hartman --- drivers/char/tpm/tpm-interface.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 43e23a04433a..4463d0018290 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -467,12 +467,13 @@ static int __init tpm_init(void) int rc; tpm_class = class_create("tpm"); - tpm_class->shutdown_pre = tpm_class_shutdown; if (IS_ERR(tpm_class)) { pr_err("couldn't create tpm class\n"); return PTR_ERR(tpm_class); } + tpm_class->shutdown_pre = tpm_class_shutdown; + tpmrm_class = class_create("tpmrm"); if (IS_ERR(tpmrm_class)) { pr_err("couldn't create tpmrm class\n"); -- GitLab From 9e67955322838b93e37f3902cabde0ee712dd2ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 11:19:10 +0100 Subject: [PATCH 0999/5631] usb: host: u132-hcd: Various style improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Don't break strings over two (or more) lines - Put the , separating function args at the end of line - Replace if (cond) {} else { ... } by if (!cond) { ... } - Consistently use curly braces in all blocks belonging to the same if if at least one block needs them. - Don't start a new line just for ); There are no semantic changes. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321101911.342538-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/u132-hcd.c | 398 +++++++++++++++++++----------------- 1 file changed, 208 insertions(+), 190 deletions(-) diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 95240c9c45bd..f5433993c76e 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -71,8 +71,8 @@ INT_MODULE_PARM(testing, 0); /* Some boards misreport power switching/overcurrent*/ static bool distrust_firmware = true; module_param(distrust_firmware, bool, 0); -MODULE_PARM_DESC(distrust_firmware, "true to distrust firmware power/overcurrent" - "t setup"); +MODULE_PARM_DESC(distrust_firmware, + "true to distrust firmware power/overcurrentt setup"); static DECLARE_WAIT_QUEUE_HEAD(u132_hcd_wait); /* * u132_module_lock exists to protect access to global variables @@ -254,8 +254,9 @@ static void u132_hcd_delete(struct kref *kref) mutex_lock(&u132_module_lock); u132_instances -= 1; mutex_unlock(&u132_module_lock); - dev_warn(&u132->platform_dev->dev, "FREEING the hcd=%p and thus the u13" - "2=%p going=%d pdev=%p\n", hcd, u132, u132->going, pdev); + dev_warn(&u132->platform_dev->dev, + "FREEING the hcd=%p and thus the u132=%p going=%d pdev=%p\n", + hcd, u132, u132->going, pdev); usb_put_hcd(hcd); } @@ -346,8 +347,9 @@ static void u132_endp_delete(struct kref *kref) ring->curr_endp = next_endp; list_del(head); } - } else + } else { list_del(head); + } if (endp->input) { udev->endp_number_in[usb_endp] = 0; u132_udev_put_kref(u132, udev); @@ -419,35 +421,32 @@ static int read_roothub_info(struct u132 *u132) { u32 revision; int retval; + struct device *dev = &u132->platform_dev->dev; + retval = u132_read_pcimem(u132, revision, &revision); if (retval) { - dev_err(&u132->platform_dev->dev, "error %d accessing device co" - "ntrol\n", retval); + dev_err(dev, "error %d accessing device control\n", retval); return retval; } else if ((revision & 0xFF) == 0x10) { } else if ((revision & 0xFF) == 0x11) { } else { - dev_err(&u132->platform_dev->dev, "device revision is not valid" - " %08X\n", revision); + dev_err(dev, "device revision is not valid %08X\n", revision); return -ENODEV; } retval = u132_read_pcimem(u132, control, &u132->hc_control); if (retval) { - dev_err(&u132->platform_dev->dev, "error %d accessing device co" - "ntrol\n", retval); + dev_err(dev, "error %d accessing device control\n", retval); return retval; } retval = u132_read_pcimem(u132, roothub.status, &u132->hc_roothub_status); if (retval) { - dev_err(&u132->platform_dev->dev, "error %d accessing device re" - "g roothub.status\n", retval); + dev_err(dev, "error %d accessing device reg roothub.status\n", retval); return retval; } retval = u132_read_pcimem(u132, roothub.a, &u132->hc_roothub_a); if (retval) { - dev_err(&u132->platform_dev->dev, "error %d accessing device re" - "g roothub.a\n", retval); + dev_err(dev, "error %d accessing device reg roothub.a\n", retval); return retval; } { @@ -457,12 +456,12 @@ static int read_roothub_info(struct u132 *u132) retval = u132_read_pcimem(u132, roothub.portstatus[i], &u132->hc_roothub_portstatus[i]); if (retval) { - dev_err(&u132->platform_dev->dev, "error %d acc" - "essing device roothub.portstatus[%d]\n" - , retval, i); + dev_err(dev, "error %d accessing device roothub.portstatus[%d]\n", + retval, i); return retval; - } else + } else { i += 1; + } } } return 0; @@ -472,8 +471,8 @@ static void u132_hcd_monitor_work(struct work_struct *work) { struct u132 *u132 = container_of(work, struct u132, monitor.work); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, "device has been removed %d\n", + u132->going); u132_monitor_put_kref(u132); return; } else if (u132->going > 0) { @@ -622,8 +621,8 @@ static void u132_hcd_interrupt_recv(void *data, struct urb *urb, u8 *buf, struct u132_udev *udev = &u132->udev[address]; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, "device has been removed %d\n", + u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -633,8 +632,8 @@ static void u132_hcd_interrupt_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -694,9 +693,8 @@ static void u132_hcd_interrupt_recv(void *data, struct urb *urb, u8 *buf, endp->toggle_bits = 0x2; usb_settoggle(udev->usb_device, endp->usb_endp, 0, 0); - dev_err(&u132->platform_dev->dev, "urb=%p givin" - "g back INTERRUPT %s\n", urb, - cc_to_text[condition_code]); + dev_err(&u132->platform_dev->dev, "urb=%p giving back INTERRUPT %s\n", + urb, cc_to_text[condition_code]); } mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, @@ -704,8 +702,8 @@ static void u132_hcd_interrupt_recv(void *data, struct urb *urb, u8 *buf, return; } } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -721,8 +719,8 @@ static void u132_hcd_bulk_output_sent(void *data, struct urb *urb, u8 *buf, u8 address = u132->addr[endp->usb_addr].address; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, "device has been removed %d\n", + u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -732,8 +730,8 @@ static void u132_hcd_bulk_output_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -755,8 +753,8 @@ static void u132_hcd_bulk_output_sent(void *data, struct urb *urb, u8 *buf, return; } } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -773,8 +771,8 @@ static void u132_hcd_bulk_input_recv(void *data, struct urb *urb, u8 *buf, struct u132_udev *udev = &u132->udev[address]; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -784,8 +782,8 @@ static void u132_hcd_bulk_input_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -833,9 +831,9 @@ static void u132_hcd_bulk_input_recv(void *data, struct urb *urb, u8 *buf, endp->toggle_bits = toggle_bits; usb_settoggle(udev->usb_device, endp->usb_endp, 0, 1 & toggle_bits); - dev_warn(&u132->platform_dev->dev, "urb=%p(SHORT NOT OK" - ") giving back BULK IN %s\n", urb, - cc_to_text[condition_code]); + dev_warn(&u132->platform_dev->dev, + "urb=%p(SHORT NOT OK) giving back BULK IN %s\n", + urb, cc_to_text[condition_code]); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -849,17 +847,18 @@ static void u132_hcd_bulk_input_recv(void *data, struct urb *urb, u8 *buf, } else { endp->toggle_bits = 0x2; usb_settoggle(udev->usb_device, endp->usb_endp, 0, 0); - dev_err(&u132->platform_dev->dev, "urb=%p giving back B" - "ULK IN code=%d %s\n", urb, condition_code, - cc_to_text[condition_code]); + dev_err(&u132->platform_dev->dev, + "urb=%p giving back BULK IN code=%d %s\n", + urb, condition_code, cc_to_text[condition_code]); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, cc_to_error[condition_code]); return; } } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -874,8 +873,8 @@ static void u132_hcd_configure_empty_sent(void *data, struct urb *urb, u8 *buf, struct u132 *u132 = endp->u132; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -885,8 +884,8 @@ static void u132_hcd_configure_empty_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -895,8 +894,9 @@ static void u132_hcd_configure_empty_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, 0); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -912,8 +912,8 @@ static void u132_hcd_configure_input_recv(void *data, struct urb *urb, u8 *buf, u8 address = u132->addr[endp->usb_addr].address; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -923,8 +923,8 @@ static void u132_hcd_configure_input_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -952,23 +952,24 @@ static void u132_hcd_configure_input_recv(void *data, struct urb *urb, u8 *buf, return; } else if (condition_code == TD_CC_STALL) { mutex_unlock(&u132->scheduler_lock); - dev_warn(&u132->platform_dev->dev, "giving back SETUP I" - "NPUT STALL urb %p\n", urb); + dev_warn(&u132->platform_dev->dev, + "giving back SETUP INPUT STALL urb %p\n", urb); u132_hcd_giveback_urb(u132, endp, urb, cc_to_error[condition_code]); return; } else { mutex_unlock(&u132->scheduler_lock); - dev_err(&u132->platform_dev->dev, "giving back SETUP IN" - "PUT %s urb %p\n", cc_to_text[condition_code], - urb); + dev_err(&u132->platform_dev->dev, + "giving back SETUP INPUT %s urb %p\n", + cc_to_text[condition_code], urb); u132_hcd_giveback_urb(u132, endp, urb, cc_to_error[condition_code]); return; } } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -983,8 +984,8 @@ static void u132_hcd_configure_empty_recv(void *data, struct urb *urb, u8 *buf, struct u132 *u132 = endp->u132; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, "device has been removed %d\n", + u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -994,8 +995,8 @@ static void u132_hcd_configure_empty_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1004,8 +1005,9 @@ static void u132_hcd_configure_empty_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, 0); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1021,8 +1023,8 @@ static void u132_hcd_configure_setup_sent(void *data, struct urb *urb, u8 *buf, u8 address = u132->addr[endp->usb_addr].address; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, "device has been removed %d\n", + u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1032,8 +1034,8 @@ static void u132_hcd_configure_setup_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1062,8 +1064,9 @@ static void u132_hcd_configure_setup_sent(void *data, struct urb *urb, u8 *buf, return; } } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1080,8 +1083,8 @@ static void u132_hcd_enumeration_empty_recv(void *data, struct urb *urb, struct u132_udev *udev = &u132->udev[address]; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1091,8 +1094,8 @@ static void u132_hcd_enumeration_empty_recv(void *data, struct urb *urb, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1103,8 +1106,9 @@ static void u132_hcd_enumeration_empty_recv(void *data, struct urb *urb, u132_hcd_giveback_urb(u132, endp, urb, 0); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1119,8 +1123,8 @@ static void u132_hcd_enumeration_address_sent(void *data, struct urb *urb, struct u132 *u132 = endp->u132; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1130,8 +1134,7 @@ static void u132_hcd_enumeration_address_sent(void *data, struct urb *urb, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1146,8 +1149,9 @@ static void u132_hcd_enumeration_address_sent(void *data, struct urb *urb, u132_hcd_giveback_urb(u132, endp, urb, retval); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1162,8 +1166,8 @@ static void u132_hcd_initial_empty_sent(void *data, struct urb *urb, u8 *buf, struct u132 *u132 = endp->u132; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1173,8 +1177,8 @@ static void u132_hcd_initial_empty_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1183,8 +1187,9 @@ static void u132_hcd_initial_empty_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, 0); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1200,8 +1205,8 @@ static void u132_hcd_initial_input_recv(void *data, struct urb *urb, u8 *buf, u8 address = u132->addr[endp->usb_addr].address; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1211,8 +1216,8 @@ static void u132_hcd_initial_input_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1235,8 +1240,9 @@ static void u132_hcd_initial_input_recv(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, retval); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1252,8 +1258,8 @@ static void u132_hcd_initial_setup_sent(void *data, struct urb *urb, u8 *buf, u8 address = u132->addr[endp->usb_addr].address; mutex_lock(&u132->scheduler_lock); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); mutex_unlock(&u132->scheduler_lock); u132_hcd_forget_urb(u132, endp, urb, -ENODEV); return; @@ -1263,8 +1269,8 @@ static void u132_hcd_initial_setup_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, -EINTR); return; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); return; @@ -1279,8 +1285,9 @@ static void u132_hcd_initial_setup_sent(void *data, struct urb *urb, u8 *buf, u132_hcd_giveback_urb(u132, endp, urb, retval); return; } else { - dev_err(&u132->platform_dev->dev, "CALLBACK called urb=%p " - "unlinked=%d\n", urb, urb->unlinked); + dev_err(&u132->platform_dev->dev, + "CALLBACK called urb=%p unlinked=%d\n", + urb, urb->unlinked); mutex_unlock(&u132->scheduler_lock); u132_hcd_giveback_urb(u132, endp, urb, 0); return; @@ -1462,8 +1469,7 @@ static void u132_hcd_endp_work_scheduler(struct work_struct *work) retval = edset_input(u132, ring, endp, urb, address, endp->toggle_bits, u132_hcd_bulk_input_recv); - if (retval == 0) { - } else + if (retval != 0) u132_hcd_giveback_urb(u132, endp, urb, retval); return; @@ -1485,8 +1491,7 @@ static void u132_hcd_endp_work_scheduler(struct work_struct *work) retval = edset_output(u132, ring, endp, urb, address, endp->toggle_bits, u132_hcd_bulk_output_sent); - if (retval == 0) { - } else + if (retval != 0) u132_hcd_giveback_urb(u132, endp, urb, retval); return; @@ -1608,8 +1613,9 @@ static int u132_run(struct u132 *u132) retval = u132_read_pcimem(u132, control, &u132->hc_control); if (retval) return retval; - dev_info(&u132->platform_dev->dev, "resetting from state '%s', control " - "= %08X\n", hcfs2string(u132->hc_control & OHCI_CTRL_HCFS), + dev_info(&u132->platform_dev->dev, + "resetting from state '%s', control = %08X\n", + hcfs2string(u132->hc_control & OHCI_CTRL_HCFS), u132->hc_control); switch (u132->hc_control & OHCI_CTRL_HCFS) { case OHCI_USB_OPER: @@ -1662,8 +1668,8 @@ extra: { return retval; if (0 != (status & OHCI_HCR)) { if (--reset_timeout == 0) { - dev_err(&u132->platform_dev->dev, "USB HC reset" - " timed out!\n"); + dev_err(&u132->platform_dev->dev, + "USB HC reset timed out!\n"); return -ENODEV; } else { msleep(5); @@ -1701,9 +1707,11 @@ extra: { if (!(u132->flags & OHCI_QUIRK_INITRESET)) { u132->flags |= OHCI_QUIRK_INITRESET; goto retry; - } else - dev_err(&u132->platform_dev->dev, "init err(%08x %04x)" - "\n", fminterval, periodicstart); + } else { + dev_err(&u132->platform_dev->dev, + "init err(%08x %04x)\n", + fminterval, periodicstart); + } } /* start controller operations */ u132->hc_control &= OHCI_CTRL_RWC; u132->hc_control |= OHCI_CONTROL_INIT | OHCI_CTRL_BLE | OHCI_USB_OPER; @@ -1767,11 +1775,12 @@ static void u132_hcd_stop(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "u132 device %p(hcd=%p) has b" - "een removed %d\n", u132, hcd, u132->going); + dev_err(&u132->platform_dev->dev, + "u132 device %p(hcd=%p) has been removed %d\n", + u132, hcd, u132->going); } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device hcd=%p is being remov" - "ed\n", hcd); + dev_err(&u132->platform_dev->dev, + "device hcd=%p is being removed\n", hcd); } else { mutex_lock(&u132->sw_lock); msleep(100); @@ -1784,8 +1793,8 @@ static int u132_hcd_start(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); @@ -1803,8 +1812,8 @@ static int u132_hcd_start(struct usb_hcd *hcd) if (vendor == PCI_VENDOR_ID_AMD && device == 0x740c) { u132->flags = OHCI_QUIRK_AMD756; } else if (vendor == PCI_VENDOR_ID_OPTI && device == 0xc861) { - dev_err(&u132->platform_dev->dev, "WARNING: OPTi workar" - "ounds unavailable\n"); + dev_err(&u132->platform_dev->dev, + "WARNING: OPTi workarounds unavailable\n"); } else if (vendor == PCI_VENDOR_ID_COMPAQ && device == 0xa0f8) u132->flags |= OHCI_QUIRK_ZFMICRO; retval = u132_run(u132); @@ -1825,8 +1834,8 @@ static int u132_hcd_reset(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); @@ -2181,8 +2190,8 @@ static int queue_control_on_old_endpoint(struct u132 *u132, } } if (I == 0) { - dev_err(&u132->platform_dev->dev, "run out of d" - "evice space\n"); + dev_err(&u132->platform_dev->dev, + "run out of device space\n"); return -EINVAL; } urb->hcpriv = u132; @@ -2239,12 +2248,12 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } } if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed " - "urb=%p\n", urb); + dev_err(&u132->platform_dev->dev, + "device is being removed urb=%p\n", urb); return -ESHUTDOWN; } else { u8 usb_addr = usb_pipedevice(urb->pipe); @@ -2289,8 +2298,8 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, usb_endp, address, mem_flags); } } else if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { - dev_err(&u132->platform_dev->dev, "the hardware does no" - "t support PIPE_ISOCHRONOUS\n"); + dev_err(&u132->platform_dev->dev, + "the hardware does not support PIPE_ISOCHRONOUS\n"); return -EINVAL; } else if (usb_pipetype(urb->pipe) == PIPE_BULK) { u8 address = u132->addr[usb_addr].address; @@ -2323,10 +2332,11 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } } else if (u132->num_endpoints == MAX_U132_ENDPS) { return -EINVAL; - } else + } else { return create_endpoint_and_queue_bulk(u132, udev, urb, usb_dev, usb_addr, usb_endp, address, mem_flags); + } } else { struct u132_endp *endp = urb->ep->hcpriv; u16 urb_size = 8; @@ -2343,8 +2353,9 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, int w = sprintf(d, " %02X", *b++); d += w; l += w; - } else + } else { d += sprintf(d, " .."); + } } if (endp) { unsigned long irqs; @@ -2371,10 +2382,11 @@ static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, } } else if (u132->num_endpoints == MAX_U132_ENDPS) { return -EINVAL; - } else + } else { return create_endpoint_and_queue_control(u132, urb, usb_dev, usb_addr, usb_endp, mem_flags); + } } } } @@ -2394,9 +2406,9 @@ static int dequeue_from_overflow_chain(struct u132 *u132, return 0; } } - dev_err(&u132->platform_dev->dev, "urb=%p not found in endp[%d]=%p ring" - "[%d] %c%c usb_endp=%d usb_addr=%d size=%d next=%04X last=%04X" - "\n", urb, endp->endp_number, endp, endp->ring->number, + dev_err(&u132->platform_dev->dev, + "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d size=%d next=%04X last=%04X\n", + urb, endp->endp_number, endp, endp->ring->number, endp->input ? 'I' : ' ', endp->output ? 'O' : ' ', endp->usb_endp, endp->usb_addr, endp->queue_size, endp->queue_next, endp->queue_last); @@ -2416,9 +2428,9 @@ static int u132_endp_urb_dequeue(struct u132 *u132, struct u132_endp *endp, return rc; } if (endp->queue_size == 0) { - dev_err(&u132->platform_dev->dev, "urb=%p not found in endp[%d]" - "=%p ring[%d] %c%c usb_endp=%d usb_addr=%d\n", urb, - endp->endp_number, endp, endp->ring->number, + dev_err(&u132->platform_dev->dev, + "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d\n", + urb, endp->endp_number, endp, endp->ring->number, endp->input ? 'I' : ' ', endp->output ? 'O' : ' ', endp->usb_endp, endp->usb_addr); spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); @@ -2477,10 +2489,9 @@ static int u132_endp_urb_dequeue(struct u132 *u132, struct u132_endp *endp, usb_hcd_giveback_urb(hcd, urb, status); return 0; } else if (list_empty(&endp->urb_more)) { - dev_err(&u132->platform_dev->dev, "urb=%p not found in " - "endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr" - "=%d size=%d next=%04X last=%04X\n", urb, - endp->endp_number, endp, endp->ring->number, + dev_err(&u132->platform_dev->dev, + "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d size=%d next=%04X last=%04X\n", + urb, endp->endp_number, endp, endp->ring->number, endp->input ? 'I' : ' ', endp->output ? 'O' : ' ', endp->usb_endp, endp->usb_addr, endp->queue_size, @@ -2503,8 +2514,8 @@ static int u132_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 2) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else { u8 usb_addr = usb_pipedevice(urb->pipe); @@ -2528,9 +2539,9 @@ static void u132_endpoint_disable(struct usb_hcd *hcd, { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 2) { - dev_err(&u132->platform_dev->dev, "u132 device %p(hcd=%p hep=%p" - ") has been removed %d\n", u132, hcd, hep, - u132->going); + dev_err(&u132->platform_dev->dev, + "u132 device %p(hcd=%p hep=%p) has been removed %d\n", + u132, hcd, hep, u132->going); } else { struct u132_endp *endp = hep->hcpriv; if (endp) @@ -2542,8 +2553,8 @@ static int u132_get_frame(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); @@ -2590,8 +2601,9 @@ static int u132_roothub_descriptor(struct u132 *u132, if (u132->num_ports > 7) { desc->u.hs.DeviceRemovable[1] = (rh_b & RH_B_DR) >> 8; desc->u.hs.DeviceRemovable[2] = 0xff; - } else + } else { desc->u.hs.DeviceRemovable[1] = 0xff; + } return 0; } @@ -2614,8 +2626,8 @@ static int u132_roothub_portstatus(struct u132 *u132, __le32 *desc, u16 wIndex) roothub.portstatus[port], &rh_portstatus); *desc = cpu_to_le32(rh_portstatus); if (*(u16 *) (desc + 2)) { - dev_info(&u132->platform_dev->dev, "Port %d Status Chan" - "ge = %08X\n", port, *desc); + dev_info(&u132->platform_dev->dev, + "Port %d Status Change = %08X\n", port, *desc); } return ret_portstatus; } @@ -2660,9 +2672,10 @@ static int u132_roothub_portreset(struct u132 *u132, int port_index) if (retval) return retval; } - } else + } else { break; /* start the next reset, sleep till it's probably done */ + } retval = u132_write_pcimem(u132, roothub.portstatus[port_index], RH_PS_PRS); if (retval) @@ -2721,8 +2734,8 @@ static int u132_roothub_clearportfeature(struct u132 *u132, u16 wValue, temp = RH_PS_POCI; if ((u132->hc_control & OHCI_CTRL_HCFS) != OHCI_USB_OPER) { - dev_err(&u132->platform_dev->dev, "TODO resume_" - "root_hub\n"); + dev_err(&u132->platform_dev->dev, + "TODO resume_root_hub\n"); } break; case USB_PORT_FEAT_C_SUSPEND: @@ -2754,19 +2767,20 @@ static int u132_hub_status_data(struct usb_hcd *hcd, char *buf) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device hcd=%p has been remov" - "ed %d\n", hcd, u132->going); + dev_err(&u132->platform_dev->dev, + "device hcd=%p has been removed %d\n", + hcd, u132->going); return -ENODEV; } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device hcd=%p is being remov" - "ed\n", hcd); + dev_err(&u132->platform_dev->dev, + "device hcd=%p is being removed\n", hcd); return -ESHUTDOWN; } else { int i, changed = 0, length = 1; if (u132->flags & OHCI_QUIRK_AMD756) { if ((u132->hc_roothub_a & RH_A_NDP) > MAX_ROOT_PORTS) { - dev_err(&u132->platform_dev->dev, "bogus NDP, r" - "ereads as NDP=%d\n", + dev_err(&u132->platform_dev->dev, + "bogus NDP, rereads as NDP=%d\n", u132->hc_roothub_a & RH_A_NDP); goto done; } @@ -2806,8 +2820,8 @@ static int u132_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); @@ -2888,14 +2902,15 @@ static int u132_start_port_reset(struct usb_hcd *hcd, unsigned port_num) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); return -ESHUTDOWN; - } else + } else { return 0; + } } @@ -2904,28 +2919,30 @@ static int u132_bus_suspend(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); return -ESHUTDOWN; - } else + } else { return 0; + } } static int u132_bus_resume(struct usb_hcd *hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); return -ESHUTDOWN; - } else + } else { return 0; + } } #else @@ -2963,14 +2980,15 @@ static int u132_remove(struct platform_device *pdev) if (hcd) { struct u132 *u132 = hcd_to_u132(hcd); if (u132->going++ > 1) { - dev_err(&u132->platform_dev->dev, "already being remove" - "d\n"); + dev_err(&u132->platform_dev->dev, + "already being removed\n"); return -ENODEV; } else { int rings = MAX_U132_RINGS; int endps = MAX_U132_ENDPS; - dev_err(&u132->platform_dev->dev, "removing device u132" - ".%d\n", u132->sequence_num); + dev_err(&u132->platform_dev->dev, + "removing device u132.%d\n", + u132->sequence_num); msleep(100); mutex_lock(&u132->sw_lock); u132_monitor_cancel_work(u132); @@ -2991,8 +3009,9 @@ static int u132_remove(struct platform_device *pdev) u132_u132_put_kref(u132); return 0; } - } else + } else { return 0; + } } static void u132_initialise(struct u132 *u132, struct platform_device *pdev) @@ -3075,8 +3094,7 @@ static int u132_probe(struct platform_device *pdev) hcd = usb_create_hcd(&u132_hc_driver, &pdev->dev, dev_name(&pdev->dev)); if (!hcd) { - printk(KERN_ERR "failed to create the usb hcd struct for U132\n" - ); + printk(KERN_ERR "failed to create the usb hcd struct for U132\n"); ftdi_elan_gone_away(pdev); return -ENOMEM; } else { @@ -3114,8 +3132,8 @@ static int u132_suspend(struct platform_device *pdev, pm_message_t state) struct usb_hcd *hcd = platform_get_drvdata(pdev); struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); @@ -3144,8 +3162,8 @@ static int u132_resume(struct platform_device *pdev) struct usb_hcd *hcd = platform_get_drvdata(pdev); struct u132 *u132 = hcd_to_u132(hcd); if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n" - , u132->going); + dev_err(&u132->platform_dev->dev, + "device has been removed %d\n", u132->going); return -ENODEV; } else if (u132->going > 0) { dev_err(&u132->platform_dev->dev, "device is being removed\n"); -- GitLab From ee2f38b3c6f2c68a0e6f5945aae91d607bc9a7c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 11:19:11 +0100 Subject: [PATCH 1000/5631] usb: host: u132-hcd: Drop if with an always true condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A platform device's .remove() callback is only ever called after .probe() successfully completed. After such a successful call, platform_get_drvdata() doesn't return NULL. Simplify accordingly. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321101911.342538-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/u132-hcd.c | 66 +++++++++++++++++++------------------ 1 file changed, 34 insertions(+), 32 deletions(-) diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index f5433993c76e..45244c791bcb 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2977,39 +2977,36 @@ static const struct hc_driver u132_hc_driver = { static int u132_remove(struct platform_device *pdev) { struct usb_hcd *hcd = platform_get_drvdata(pdev); - if (hcd) { - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going++ > 1) { - dev_err(&u132->platform_dev->dev, - "already being removed\n"); - return -ENODEV; - } else { - int rings = MAX_U132_RINGS; - int endps = MAX_U132_ENDPS; - dev_err(&u132->platform_dev->dev, - "removing device u132.%d\n", - u132->sequence_num); - msleep(100); - mutex_lock(&u132->sw_lock); - u132_monitor_cancel_work(u132); - while (rings-- > 0) { - struct u132_ring *ring = &u132->ring[rings]; - u132_ring_cancel_work(u132, ring); - } - while (endps-- > 0) { - struct u132_endp *endp = u132->endp[endps]; - if (endp) - u132_endp_cancel_work(u132, endp); - } - u132->going += 1; - printk(KERN_INFO "removing device u132.%d\n", - u132->sequence_num); - mutex_unlock(&u132->sw_lock); - usb_remove_hcd(hcd); - u132_u132_put_kref(u132); - return 0; - } + struct u132 *u132 = hcd_to_u132(hcd); + + if (u132->going++ > 1) { + dev_err(&u132->platform_dev->dev, + "already being removed\n"); + return -ENODEV; } else { + int rings = MAX_U132_RINGS; + int endps = MAX_U132_ENDPS; + dev_err(&u132->platform_dev->dev, + "removing device u132.%d\n", + u132->sequence_num); + msleep(100); + mutex_lock(&u132->sw_lock); + u132_monitor_cancel_work(u132); + while (rings-- > 0) { + struct u132_ring *ring = &u132->ring[rings]; + u132_ring_cancel_work(u132, ring); + } + while (endps-- > 0) { + struct u132_endp *endp = u132->endp[endps]; + if (endp) + u132_endp_cancel_work(u132, endp); + } + u132->going += 1; + printk(KERN_INFO "removing device u132.%d\n", + u132->sequence_num); + mutex_unlock(&u132->sw_lock); + usb_remove_hcd(hcd); + u132_u132_put_kref(u132); return 0; } } @@ -3092,6 +3089,11 @@ static int u132_probe(struct platform_device *pdev) if (retval) return retval; + /* + * Note that after a successful call of usb_create_hcd(), + * dev_set_drvdata() was called such that platform_get_drvdata(pdev) + * returns hcd later on. + */ hcd = usb_create_hcd(&u132_hc_driver, &pdev->dev, dev_name(&pdev->dev)); if (!hcd) { printk(KERN_ERR "failed to create the usb hcd struct for U132\n"); -- GitLab From 653b131a897e67c65a0fb2ddbfba29b6daec76e2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 20 Mar 2023 18:39:02 -0500 Subject: [PATCH 1001/5631] dt-bindings: usb: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230320233904.2920197-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- .../bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml | 4 ++-- .../devicetree/bindings/usb/brcm,bcm7445-ehci.yaml | 2 +- Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml | 4 ++-- Documentation/devicetree/bindings/usb/generic-ehci.yaml | 2 +- Documentation/devicetree/bindings/usb/generic-xhci.yaml | 2 +- Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml | 4 ++-- Documentation/devicetree/bindings/usb/maxim,max33359.yaml | 4 ++-- .../devicetree/bindings/usb/mediatek,mt6360-tcpc.yaml | 4 ++-- .../devicetree/bindings/usb/mediatek,mt6370-tcpc.yaml | 4 ++-- .../devicetree/bindings/usb/mediatek,mtk-xhci.yaml | 2 +- Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml | 8 ++++---- Documentation/devicetree/bindings/usb/mediatek,musb.yaml | 4 ++-- .../devicetree/bindings/usb/nvidia,tegra-xudc.yaml | 4 ++-- .../devicetree/bindings/usb/realtek,rts5411.yaml | 2 +- .../devicetree/bindings/usb/richtek,rt1711h.yaml | 4 ++-- Documentation/devicetree/bindings/usb/richtek,rt1719.yaml | 4 ++-- Documentation/devicetree/bindings/usb/st,stusb160x.yaml | 4 ++-- Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml | 4 ++-- Documentation/devicetree/bindings/usb/ti,tps6598x.yaml | 4 ++-- Documentation/devicetree/bindings/usb/usb-xhci.yaml | 2 +- 20 files changed, 36 insertions(+), 36 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml index f38a2be07eda..da757c1155d4 100644 --- a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml +++ b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml @@ -2,8 +2,8 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/amlogic,meson-g12a-usb-ctrl.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/amlogic,meson-g12a-usb-ctrl.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic Meson G12A DWC3 USB SoC Controller Glue diff --git a/Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml b/Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml index ad075407d85e..1536cbec6334 100644 --- a/Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml +++ b/Documentation/devicetree/bindings/usb/brcm,bcm7445-ehci.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Broadcom STB USB EHCI Controller allOf: - - $ref: "usb-hcd.yaml" + - $ref: usb-hcd.yaml maintainers: - Al Cooper diff --git a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml index 51120fe90322..f6e7a5c1ff0b 100644 --- a/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml +++ b/Documentation/devicetree/bindings/usb/fcs,fsa4480.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/fcs,fsa4480.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/fcs,fsa4480.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: ON Semiconductor Analog Audio Switch diff --git a/Documentation/devicetree/bindings/usb/generic-ehci.yaml b/Documentation/devicetree/bindings/usb/generic-ehci.yaml index 050cfd5acdaa..9445764bd8de 100644 --- a/Documentation/devicetree/bindings/usb/generic-ehci.yaml +++ b/Documentation/devicetree/bindings/usb/generic-ehci.yaml @@ -10,7 +10,7 @@ maintainers: - Greg Kroah-Hartman allOf: - - $ref: "usb-hcd.yaml" + - $ref: usb-hcd.yaml - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/generic-xhci.yaml b/Documentation/devicetree/bindings/usb/generic-xhci.yaml index db841589fc33..594ebb3ee432 100644 --- a/Documentation/devicetree/bindings/usb/generic-xhci.yaml +++ b/Documentation/devicetree/bindings/usb/generic-xhci.yaml @@ -10,7 +10,7 @@ maintainers: - Mathias Nyman allOf: - - $ref: "usb-xhci.yaml#" + - $ref: usb-xhci.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml index bf4b1d016e1f..f196beb826d8 100644 --- a/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml +++ b/Documentation/devicetree/bindings/usb/gpio-sbu-mux.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/gpio-sbu-mux.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/gpio-sbu-mux.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: GPIO-based SBU mux diff --git a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml index 8e513a6af378..beccbd1d4d0e 100644 --- a/Documentation/devicetree/bindings/usb/maxim,max33359.yaml +++ b/Documentation/devicetree/bindings/usb/maxim,max33359.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/maxim,max33359.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/maxim,max33359.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Maxim TCPCI Type-C PD controller diff --git a/Documentation/devicetree/bindings/usb/mediatek,mt6360-tcpc.yaml b/Documentation/devicetree/bindings/usb/mediatek,mt6360-tcpc.yaml index c72257c19220..4f6018aadc8c 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mt6360-tcpc.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mt6360-tcpc.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/mediatek,mt6360-tcpc.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/mediatek,mt6360-tcpc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek MT6360 Type-C Port Switch and Power Delivery controller diff --git a/Documentation/devicetree/bindings/usb/mediatek,mt6370-tcpc.yaml b/Documentation/devicetree/bindings/usb/mediatek,mt6370-tcpc.yaml index 72f56cc88457..747d0f16d9b6 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mt6370-tcpc.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mt6370-tcpc.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/mediatek,mt6370-tcpc.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/mediatek,mt6370-tcpc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: MediatTek MT6370 Type-C Port Switch and Power Delivery controller diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml index c119caa9ad16..556bedb96165 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml @@ -11,7 +11,7 @@ maintainers: - Chunfeng Yun allOf: - - $ref: "usb-xhci.yaml" + - $ref: usb-xhci.yaml description: | There are two scenarios: diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml index d2655173e108..5b908c457e3d 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml @@ -11,7 +11,7 @@ maintainers: - Chunfeng Yun allOf: - - $ref: "usb-drd.yaml" + - $ref: usb-drd.yaml description: | The DRD controller has a glue layer IPPC (IP Port Control), and its host is @@ -204,9 +204,9 @@ patternProperties: example if the host mode is enabled. dependencies: - connector: [ 'usb-role-switch' ] - port: [ 'usb-role-switch' ] - role-switch-default-mode: [ 'usb-role-switch' ] + connector: [ usb-role-switch ] + port: [ usb-role-switch ] + role-switch-default-mode: [ usb-role-switch ] wakeup-source: [ 'mediatek,syscon-wakeup' ] required: diff --git a/Documentation/devicetree/bindings/usb/mediatek,musb.yaml b/Documentation/devicetree/bindings/usb/mediatek,musb.yaml index f16ab30a95d2..a39d38db7714 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,musb.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,musb.yaml @@ -68,8 +68,8 @@ properties: type: object dependencies: - usb-role-switch: [ 'connector' ] - connector: [ 'usb-role-switch' ] + usb-role-switch: [ connector ] + connector: [ usb-role-switch ] required: - compatible diff --git a/Documentation/devicetree/bindings/usb/nvidia,tegra-xudc.yaml b/Documentation/devicetree/bindings/usb/nvidia,tegra-xudc.yaml index e638f77658fc..e2270ce0c56b 100644 --- a/Documentation/devicetree/bindings/usb/nvidia,tegra-xudc.yaml +++ b/Documentation/devicetree/bindings/usb/nvidia,tegra-xudc.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/nvidia,tegra-xudc.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/nvidia,tegra-xudc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: NVIDIA Tegra XUSB device mode controller (XUDC) diff --git a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml index 623d04a88a81..9309f003cd07 100644 --- a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml +++ b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml @@ -26,7 +26,7 @@ properties: phandle to the regulator that provides power to the hub. peer-hub: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle to the peer hub on the controller. diff --git a/Documentation/devicetree/bindings/usb/richtek,rt1711h.yaml b/Documentation/devicetree/bindings/usb/richtek,rt1711h.yaml index 1999f614c89b..3bec824ec446 100644 --- a/Documentation/devicetree/bindings/usb/richtek,rt1711h.yaml +++ b/Documentation/devicetree/bindings/usb/richtek,rt1711h.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/richtek,rt1711h.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/richtek,rt1711h.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Richtek RT1711H Type-C Port Switch and Power Delivery controller diff --git a/Documentation/devicetree/bindings/usb/richtek,rt1719.yaml b/Documentation/devicetree/bindings/usb/richtek,rt1719.yaml index e3e87e4d3292..43562041b646 100644 --- a/Documentation/devicetree/bindings/usb/richtek,rt1719.yaml +++ b/Documentation/devicetree/bindings/usb/richtek,rt1719.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/richtek,rt1719.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/richtek,rt1719.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Richtek RT1719 sink-only Type-C PD controller diff --git a/Documentation/devicetree/bindings/usb/st,stusb160x.yaml b/Documentation/devicetree/bindings/usb/st,stusb160x.yaml index ffcd9897ea38..edfebb813f77 100644 --- a/Documentation/devicetree/bindings/usb/st,stusb160x.yaml +++ b/Documentation/devicetree/bindings/usb/st,stusb160x.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/st,stusb160x.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/st,stusb160x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: STMicroelectronics STUSB160x Type-C controller diff --git a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml index f81ba3e90297..fd36dd02fe74 100644 --- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml +++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/ti,j721e-usb.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/ti,j721e-usb.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: TI wrapper module for the Cadence USBSS-DRD controller diff --git a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml index 348a715d61f4..7d9c5e786e42 100644 --- a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml +++ b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/usb/ti,tps6598x.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/usb/ti,tps6598x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Texas Instruments 6598x Type-C Port Switch and Power Delivery controller diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.yaml b/Documentation/devicetree/bindings/usb/usb-xhci.yaml index f2139a9f35fb..180a261c3e8f 100644 --- a/Documentation/devicetree/bindings/usb/usb-xhci.yaml +++ b/Documentation/devicetree/bindings/usb/usb-xhci.yaml @@ -10,7 +10,7 @@ maintainers: - Mathias Nyman allOf: - - $ref: "usb-hcd.yaml#" + - $ref: usb-hcd.yaml# properties: usb2-lpm-disable: -- GitLab From f1e8f25980968f7c18f1eb977bd1d5fd716325a5 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 20 Mar 2023 14:16:18 +0800 Subject: [PATCH 1002/5631] perf kvm: Reference count 'struct kvm_info' hists__add_entry_ops() doesn't allocate a new histogram entry if it has an existing entry for a KVM event, in this case, find_create_kvm_event() allocates a 'struct kvm_info' but it's not used by any histograms and never freed. To fix the memory leak, this patch first introduces a refcnt and a set of functions for refcnt operations on 'struct kvm_info'. When the data structure is not anymore used (the refcnt hits zero) kvm_info__zput() will free the memory used. Committer: Provide a nop version of kvm_info__zput() to be used when HAVE_KVM_STAT_SUPPORT isn't defined as it is used unconditionally in hists__findnew_entry() and hist_entry__delete(). Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230320061619.29520-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 3 +-- tools/perf/util/hist.c | 5 +++++ tools/perf/util/kvm-stat.h | 40 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 4c205df5106f..1e1cb5a9d0a2 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -768,7 +768,6 @@ static void kvm_he_free(void *he) { struct kvm_event *kvm_ev; - free(((struct hist_entry *)he)->kvm_info); kvm_ev = container_of(he, struct kvm_event, he); free(kvm_ev); } @@ -788,7 +787,7 @@ static struct kvm_event *find_create_kvm_event(struct perf_kvm_stat *kvm, BUG_ON(key->key == INVALID_KEY); - ki = zalloc(sizeof(*ki)); + ki = kvm_info__new(); if (!ki) { pr_err("Failed to allocate kvm info\n"); return NULL; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 0c11f50abfec..b339ff863fe2 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -628,6 +628,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists, block_info__zput(entry->block_info); + kvm_info__zput(entry->kvm_info); + /* If the map of an existing hist_entry has * become out-of-date due to an exec() or * similar, update it. Otherwise we will @@ -1324,6 +1326,9 @@ void hist_entry__delete(struct hist_entry *he) if (he->block_info) block_info__zput(he->block_info); + if (he->kvm_info) + kvm_info__zput(he->kvm_info); + zfree(&he->res_samples); zfree(&he->stat_acc); free_srcline(he->srcline); diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h index bc6c8e38ef50..3e9ac754c3d1 100644 --- a/tools/perf/util/kvm-stat.h +++ b/tools/perf/util/kvm-stat.h @@ -10,6 +10,9 @@ #include "symbol.h" #include "record.h" +#include +#include + #define KVM_EVENT_NAME_LEN 40 struct evsel; @@ -25,6 +28,7 @@ struct event_key { struct kvm_info { char name[KVM_EVENT_NAME_LEN]; + refcount_t refcnt; }; struct kvm_event_stats { @@ -145,6 +149,42 @@ extern const char *vcpu_id_str; extern const char *kvm_exit_reason; extern const char *kvm_entry_trace; extern const char *kvm_exit_trace; + +static inline struct kvm_info *kvm_info__get(struct kvm_info *ki) +{ + if (ki) + refcount_inc(&ki->refcnt); + return ki; +} + +static inline void kvm_info__put(struct kvm_info *ki) +{ + if (ki && refcount_dec_and_test(&ki->refcnt)) + free(ki); +} + +static inline void __kvm_info__zput(struct kvm_info **ki) +{ + kvm_info__put(*ki); + *ki = NULL; +} + +#define kvm_info__zput(ki) __kvm_info__zput(&ki) + +static inline struct kvm_info *kvm_info__new(void) +{ + struct kvm_info *ki; + + ki = zalloc(sizeof(*ki)); + if (ki) + refcount_set(&ki->refcnt, 1); + + return ki; +} + +#else /* HAVE_KVM_STAT_SUPPORT */ +// We use this unconditionally in hists__findnew_entry() and hist_entry__delete() +#define kvm_info__zput(ki) do { } while (0) #endif /* HAVE_KVM_STAT_SUPPORT */ extern int kvm_add_default_arch_event(int *argc, const char **argv); -- GitLab From 51b02a964728115761acc5baa5e67c8d0a9bc222 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Mon, 20 Mar 2023 14:16:19 +0800 Subject: [PATCH 1003/5631] perf kvm: Delete histograms entries before exiting It's good not to release resources for a program when kernel cleans up memory space, this patch explicitly releases histograms entries with hists__delete_entries(). Committer notice: This helps with memory leak checkers, but may delay exiting a tool by doing needless linked list traversals freeing lots of objects. Signed-off-by: Leo Yan Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230320061619.29520-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kvm.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 1e1cb5a9d0a2..fb9dc0dc46f9 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -1528,6 +1528,8 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm) } out: + hists__delete_entries(&kvm_hists.hists); + if (kvm->timerfd >= 0) close(kvm->timerfd); @@ -1690,6 +1692,7 @@ static int kvm_events_report_vcpu(struct perf_kvm_stat *kvm) kvm_display(kvm); exit: + hists__delete_entries(&kvm_hists.hists); return ret; } -- GitLab From 636203670716c2a8d76791d6b8f4c4cd76e8c701 Mon Sep 17 00:00:00 2001 From: "Bernhard M. Wiedemann" Date: Tue, 21 Mar 2023 07:30:32 +0100 Subject: [PATCH 1004/5631] perf jevents: Sort list of input files Without this, pmu-events.c would be generated with variations in ordering depending on non-deterministic filesystem readdir order. I tested that pmu-events.c still has the same number of lines and that perf list output works. This patch was done while working on reproducible builds for openSUSE, but also solves issues in Debian [1] and other distributions. [1] https://tests.reproducible-builds.org/debian/rb-pkg/unstable/i386/linux.html Signed-off-by: Bernhard M. Wiedemann Cc: Ian Rogers Link: https://lore.kernel.org/r/20230321063032.19804-1-bwiedemann@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/jevents.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 533071a014d7..ca99b9cfe4ad 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -922,7 +922,7 @@ def main() -> None: def ftw(path: str, parents: Sequence[str], action: Callable[[Sequence[str], os.DirEntry], None]) -> None: """Replicate the directory/file walking behavior of C's file tree walk.""" - for item in os.scandir(path): + for item in sorted(os.scandir(path), key=lambda e: e.name): if _args.model != 'all' and item.is_dir(): # Check if the model matches one in _args.model. if len(parents) == _args.model.split(',')[0].count('/'): -- GitLab From 7effbd18e496a954540fb6319db0d87d28a70496 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 20 Mar 2023 11:45:59 +0000 Subject: [PATCH 1005/5631] perf vendor events arm64: Add N1 metrics Generated from the telemetry solution repo[1] with this command: ./generate.py /tools/perf/ --telemetry-files \ ../../data/pmu/cpu/neoverse/neoverse-n1.json Since this data source now includes the SPE events for N1, it has diverged from A76 which means the folder has to be split. The new data also uses more fine grained grouping, but this will be consistent for all future products. Long PublicDescriptions are now included even for common events because this can include product specific details. For non verbose mode the common BriefDescriptions remain the same. [1]: https://gitlab.arm.com/telemetry-solution/telemetry-solution Signed-off-by: James Clark Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: renyu.zj@linux.alibaba.com Link: https://lore.kernel.org/r/20230320114601.524958-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- .../{cortex-a76-n1 => cortex-a76}/branch.json | 0 .../{cortex-a76-n1 => cortex-a76}/bus.json | 0 .../{cortex-a76-n1 => cortex-a76}/cache.json | 0 .../exception.json | 0 .../instruction.json | 0 .../{cortex-a76-n1 => cortex-a76}/memory.json | 0 .../pipeline.json | 0 .../arch/arm64/arm/neoverse-n1/bus.json | 18 ++ .../arch/arm64/arm/neoverse-n1/exception.json | 62 +++++ .../arch/arm64/arm/neoverse-n1/general.json | 6 + .../arch/arm64/arm/neoverse-n1/l1d_cache.json | 50 ++++ .../arch/arm64/arm/neoverse-n1/l1i_cache.json | 10 + .../arch/arm64/arm/neoverse-n1/l2_cache.json | 46 ++++ .../arch/arm64/arm/neoverse-n1/l3_cache.json | 18 ++ .../arch/arm64/arm/neoverse-n1/ll_cache.json | 10 + .../arch/arm64/arm/neoverse-n1/memory.json | 22 ++ .../arch/arm64/arm/neoverse-n1/metrics.json | 219 ++++++++++++++++++ .../arch/arm64/arm/neoverse-n1/retired.json | 26 +++ .../arch/arm64/arm/neoverse-n1/spe.json | 18 ++ .../arm64/arm/neoverse-n1/spec_operation.json | 102 ++++++++ .../arch/arm64/arm/neoverse-n1/stall.json | 10 + .../arch/arm64/arm/neoverse-n1/tlb.json | 66 ++++++ tools/perf/pmu-events/arch/arm64/mapfile.csv | 4 +- 23 files changed, 685 insertions(+), 2 deletions(-) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/branch.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/bus.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/cache.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/exception.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/instruction.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/memory.json (100%) rename tools/perf/pmu-events/arch/arm64/arm/{cortex-a76-n1 => cortex-a76}/pipeline.json (100%) create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/bus.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/exception.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/general.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1d_cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1i_cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l2_cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l3_cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/ll_cache.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/memory.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/metrics.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/retired.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spe.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spec_operation.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/stall.json create mode 100644 tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/tlb.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/branch.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/branch.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/branch.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/bus.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/bus.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/bus.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/cache.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/cache.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/cache.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/exception.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/exception.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/exception.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/instruction.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/instruction.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/instruction.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/memory.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/memory.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/memory.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a76/pipeline.json similarity index 100% rename from tools/perf/pmu-events/arch/arm64/arm/cortex-a76-n1/pipeline.json rename to tools/perf/pmu-events/arch/arm64/arm/cortex-a76/pipeline.json diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/bus.json new file mode 100644 index 000000000000..2e11a8c4a484 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/bus.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "BUS_ACCESS", + "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES." + }, + { + "ArchStdEvent": "BUS_ACCESS_RD", + "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually." + }, + { + "ArchStdEvent": "BUS_ACCESS_WR", + "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/exception.json new file mode 100644 index 000000000000..4404b8e91690 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/exception.json @@ -0,0 +1,62 @@ +[ + { + "ArchStdEvent": "EXC_TAKEN", + "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally." + }, + { + "ArchStdEvent": "EXC_RETURN", + "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET" + }, + { + "ArchStdEvent": "EXC_UNDEF", + "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1." + }, + { + "ArchStdEvent": "EXC_SVC", + "PublicDescription": "Counts SVC exceptions taken locally." + }, + { + "ArchStdEvent": "EXC_PABORT", + "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts." + }, + { + "ArchStdEvent": "EXC_DABORT", + "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_FIQ", + "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally." + }, + { + "ArchStdEvent": "EXC_SMC", + "PublicDescription": "Counts SMC exceptions take to EL3." + }, + { + "ArchStdEvent": "EXC_HVC", + "PublicDescription": "Counts HVC exceptions taken to EL2." + }, + { + "ArchStdEvent": "EXC_TRAP_PABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC." + }, + { + "ArchStdEvent": "EXC_TRAP_DABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors." + }, + { + "ArchStdEvent": "EXC_TRAP_OTHER", + "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts." + }, + { + "ArchStdEvent": "EXC_TRAP_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally." + }, + { + "ArchStdEvent": "EXC_TRAP_FIQ", + "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/general.json new file mode 100644 index 000000000000..20fada95ef97 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/general.json @@ -0,0 +1,6 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1d_cache.json new file mode 100644 index 000000000000..6cd0b3ba5010 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1d_cache.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching." + }, + { + "ArchStdEvent": "L1D_CACHE", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1i_cache.json new file mode 100644 index 000000000000..e719b6e7fa77 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l1i_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l2_cache.json new file mode 100644 index 000000000000..2f6099889de1 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l2_cache.json @@ -0,0 +1,46 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line." + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "PublicDescription": "TBD" + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request." + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l3_cache.json new file mode 100644 index 000000000000..f93e0c9f309a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/l3_cache.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE", + "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores." + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL", + "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache." + }, + { + "ArchStdEvent": "L3D_CACHE", + "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "PublicDescription": "TBD" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/ll_cache.json new file mode 100644 index 000000000000..bb712d57d58a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/memory.json new file mode 100644 index 000000000000..9041f6e0befb --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/memory.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "MEM_ACCESS", + "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions." + }, + { + "ArchStdEvent": "MEMORY_ERROR", + "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation." + }, + { + "ArchStdEvent": "REMOTE_ACCESS", + "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated." + }, + { + "ArchStdEvent": "MEM_ACCESS_RD", + "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + }, + { + "ArchStdEvent": "MEM_ACCESS_WR", + "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/metrics.json new file mode 100644 index 000000000000..dc0f8638f8f5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/metrics.json @@ -0,0 +1,219 @@ +[ + { + "MetricName": "backend_stalled_cycles", + "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "branch_misprediction_ratio", + "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)", + "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", + "MetricGroup": "Miss_Ratio;Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_mpki", + "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", + "MetricGroup": "MPKI;Branch_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "branch_percentage", + "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)", + "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "crypto_percentage", + "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "dtlb_mpki", + "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "frontend_stalled_cycles", + "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "integer_dp_percentage", + "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "itlb_mpki", + "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "itlb_walk_ratio", + "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1d_cache_mpki", + "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1D_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1d_tlb_miss_ratio", + "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1d_tlb_mpki", + "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1i_cache_mpki", + "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1I_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_tlb_miss_ratio", + "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1i_tlb_mpki", + "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l2_cache_mpki", + "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "MPKI;L2_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_tlb_miss_ratio", + "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)", + "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l2_tlb_mpki", + "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "ll_cache_read_hit_ratio", + "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "ll_cache_read_miss_ratio", + "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "ll_cache_read_mpki", + "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;LL_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "load_percentage", + "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "scalar_fp_percentage", + "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "simd_percentage", + "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "store_percentage", + "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/retired.json new file mode 100644 index 000000000000..0c7692ad5108 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/retired.json @@ -0,0 +1,26 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "PublicDescription": "Counts instructions that have been architecturally executed." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace." + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED", + "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications." + }, + { + "ArchStdEvent": "BR_RETIRED", + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spe.json new file mode 100644 index 000000000000..5de8b0f3a440 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spe.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP", + "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FEED", + "PublicDescription": "Counts statistical profiling samples taken for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE", + "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering." + }, + { + "ArchStdEvent": "SAMPLE_COLLISION", + "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spec_operation.json new file mode 100644 index 000000000000..be8c0667f1d9 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/spec_operation.json @@ -0,0 +1,102 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "PublicDescription": "Counts branches which are speculatively executed and mispredicted." + }, + { + "ArchStdEvent": "BR_PRED", + "PublicDescription": "Counts branches speculatively executed and were predicted right." + }, + { + "ArchStdEvent": "INST_SPEC", + "PublicDescription": "Counts operations that have been speculatively executed." + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + "PublicDescription": "Counts unaligned memory read operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses. The event does not count preload operations (PLD, PLI)." + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + "PublicDescription": "Counts unaligned memory write operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + "PublicDescription": "Counts unaligned memory operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed." + }, + { + "ArchStdEvent": "LD_SPEC", + "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations." + }, + { + "ArchStdEvent": "ST_SPEC", + "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations." + }, + { + "ArchStdEvent": "DP_SPEC", + "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations." + }, + { + "ArchStdEvent": "ASE_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers." + }, + { + "ArchStdEvent": "VFP_SPEC", + "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "PublicDescription": "Counts immediate branch operations which are speculatively executed." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations. Eg: BR Xn, RET" + }, + { + "ArchStdEvent": "ISB_SPEC", + "PublicDescription": "Counts ISB operations that are executed." + }, + { + "ArchStdEvent": "DSB_SPEC", + "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU." + }, + { + "ArchStdEvent": "DMB_SPEC", + "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations." + }, + { + "ArchStdEvent": "RC_LD_SPEC", + "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB" + }, + { + "ArchStdEvent": "RC_ST_SPEC", + "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/stall.json new file mode 100644 index 000000000000..688afd8a4061 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/stall.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/tlb.json new file mode 100644 index 000000000000..b550af1831f5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n1/tlb.json @@ -0,0 +1,66 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction." + }, + { + "ArchStdEvent": "L1D_TLB", + "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB", + "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB", + "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK", + "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK", + "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + "PublicDescription": "Counts level 1 data TLB refills caused by memory read operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + "PublicDescription": "Counts level 1 data TLB refills caused by data side memory write operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count with an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_RD", + "PublicDescription": "Counts level 1 data TLB accesses caused by memory read operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_WR", + "PublicDescription": "Counts any L1 data side TLB accesses caused by memory write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + "PublicDescription": "Counts level 2 TLB refills caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations or hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + "PublicDescription": "Counts level 2 TLB refills caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_RD", + "PublicDescription": "Counts level 2 TLB accesses caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_WR", + "PublicDescription": "Counts level 2 TLB accesses caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index f134e833c069..9d400785d195 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -23,8 +23,8 @@ 0x00000000410fd080,v1,arm/cortex-a57-a72,core 0x00000000410fd090,v1,arm/cortex-a73,core 0x00000000410fd0a0,v1,arm/cortex-a75,core -0x00000000410fd0b0,v1,arm/cortex-a76-n1,core -0x00000000410fd0c0,v1,arm/cortex-a76-n1,core +0x00000000410fd0b0,v1,arm/cortex-a76,core +0x00000000410fd0c0,v1,arm/neoverse-n1,core 0x00000000410fd0d0,v1,arm/cortex-a77,core 0x00000000410fd400,v1,arm/neoverse-v1,core 0x00000000410fd410,v1,arm/cortex-a78,core -- GitLab From 204e7c499f5fa7732144ef9765c195982be72f31 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 17 Feb 2023 16:32:11 -0600 Subject: [PATCH 1006/5631] perf tools: Add support for perf_event_attr::config3 perf_event_attr has gained a new field, config3, so add support for it extending the existing configN support. Signed-off-by: Rob Herring Cc: Alexander Shishkin Cc: James Clark Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20220914-arm-perf-tool-spe1-2-v2-v5-2-2cf5210b2f77@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/parse-events.c | 13 ++++++++++++- tools/perf/util/parse-events.c | 6 ++++++ tools/perf/util/parse-events.h | 1 + tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 3 +++ tools/perf/util/pmu.h | 1 + 6 files changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index b1c2f0a20306..6eb1400443ad 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -449,6 +449,7 @@ static int test__checkevent_pmu(struct evlist *evlist) TEST_ASSERT_VAL("wrong config", 10 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong config1", 1 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", 3 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); /* * The period value gets configured within evlist__config, * while this test executes only parse events method. @@ -470,6 +471,7 @@ static int test__checkevent_list(struct evlist *evlist) TEST_ASSERT_VAL("wrong config", 1 == evsel->core.attr.config); TEST_ASSERT_VAL("wrong config1", 0 == evsel->core.attr.config1); TEST_ASSERT_VAL("wrong config2", 0 == evsel->core.attr.config2); + TEST_ASSERT_VAL("wrong config3", 0 == evsel->core.attr.config3); TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user); TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel); TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv); @@ -632,6 +634,15 @@ static int test__checkterms_simple(struct list_head *terms) TEST_ASSERT_VAL("wrong val", term->val.num == 3); TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config2")); + /* config3=4 */ + term = list_entry(term->list.next, struct parse_events_term, list); + TEST_ASSERT_VAL("wrong type term", + term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG3); + TEST_ASSERT_VAL("wrong type val", + term->type_val == PARSE_EVENTS__TERM_TYPE_NUM); + TEST_ASSERT_VAL("wrong val", term->val.num == 4); + TEST_ASSERT_VAL("wrong config", !strcmp(term->config, "config3")); + /* umask=1*/ term = list_entry(term->list.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", @@ -2004,7 +2015,7 @@ struct terms_test { static const struct terms_test test__terms[] = { [0] = { - .str = "config=10,config1,config2=3,umask=1,read,r0xead", + .str = "config=10,config1,config2=3,config3=4,umask=1,read,r0xead", .check = test__checkterms_simple, }, }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 6c5cf5244486..cc8e8766ca30 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -949,6 +949,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = { [PARSE_EVENTS__TERM_TYPE_CONFIG] = "config", [PARSE_EVENTS__TERM_TYPE_CONFIG1] = "config1", [PARSE_EVENTS__TERM_TYPE_CONFIG2] = "config2", + [PARSE_EVENTS__TERM_TYPE_CONFIG3] = "config3", [PARSE_EVENTS__TERM_TYPE_NAME] = "name", [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD] = "period", [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ] = "freq", @@ -988,6 +989,7 @@ config_term_avail(int term_type, struct parse_events_error *err) case PARSE_EVENTS__TERM_TYPE_CONFIG: case PARSE_EVENTS__TERM_TYPE_CONFIG1: case PARSE_EVENTS__TERM_TYPE_CONFIG2: + case PARSE_EVENTS__TERM_TYPE_CONFIG3: case PARSE_EVENTS__TERM_TYPE_NAME: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: @@ -1033,6 +1035,10 @@ do { \ CHECK_TYPE_VAL(NUM); attr->config2 = term->val.num; break; + case PARSE_EVENTS__TERM_TYPE_CONFIG3: + CHECK_TYPE_VAL(NUM); + attr->config3 = term->val.num; + break; case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: CHECK_TYPE_VAL(NUM); break; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 46204c1a7916..86ad4438a2aa 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -59,6 +59,7 @@ enum { PARSE_EVENTS__TERM_TYPE_CONFIG, PARSE_EVENTS__TERM_TYPE_CONFIG1, PARSE_EVENTS__TERM_TYPE_CONFIG2, + PARSE_EVENTS__TERM_TYPE_CONFIG3, PARSE_EVENTS__TERM_TYPE_NAME, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 3a9ce96c8bce..51fe0a9fb3de 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -285,6 +285,7 @@ modifier_bp [rwx]{1,3} config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); } config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } +config3 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG3); } name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 45d9b8e28e16..e3aae731bd6f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1209,6 +1209,9 @@ static int pmu_config_term(const char *pmu_name, case PERF_PMU_FORMAT_VALUE_CONFIG2: vp = &attr->config2; break; + case PERF_PMU_FORMAT_VALUE_CONFIG3: + vp = &attr->config3; + break; default: return -EINVAL; } diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 6b770f17eb86..24cf69ab32cd 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -19,6 +19,7 @@ enum { PERF_PMU_FORMAT_VALUE_CONFIG, PERF_PMU_FORMAT_VALUE_CONFIG1, PERF_PMU_FORMAT_VALUE_CONFIG2, + PERF_PMU_FORMAT_VALUE_CONFIG3, PERF_PMU_FORMAT_VALUE_CONFIG_END, }; -- GitLab From 213acadd21a080fc8cda8eebe6d14cc2d4ad1332 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 11:36:38 +0100 Subject: [PATCH 1007/5631] usb: host: u132-hcd: Delete driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver got its last actual change in 2006 and is probably unused as nowbody should use a cardbus to USB adapter any more. If it were still used, the driver was in urgent need for maintainer love. (Explicit kref handling, underdocumented locking, .remove() can return errors ...) Also the link in the (now removed) help text doesn't look actively maintained. According to archive.org it forwarded to http://www.copenhagen-hotel.net/ already back in 2018. So don't waste more time on this driver and just delete it. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321103638.343886-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/mips/configs/mtx1_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - drivers/usb/Makefile | 1 - drivers/usb/host/Kconfig | 27 - drivers/usb/host/Makefile | 1 - drivers/usb/host/u132-hcd.c | 3239 ------------------------- drivers/usb/misc/Kconfig | 2 - 7 files changed, 3272 deletions(-) delete mode 100644 drivers/usb/host/u132-hcd.c diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 89a1511d2ee4..7b6a2a9daa10 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -497,7 +497,6 @@ CONFIG_USB_EHCI_ROOT_HUB_TT=y CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PLATFORM=m CONFIG_USB_UHCI_HCD=m -CONFIG_USB_U132_HCD=m CONFIG_USB_SL811_HCD=m CONFIG_USB_SL811_CS=m CONFIG_USB_ACM=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 110258277959..fd5cc93c4a99 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -845,7 +845,6 @@ CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PPC_OF_BE=y CONFIG_USB_OHCI_HCD_PPC_OF_LE=y CONFIG_USB_UHCI_HCD=m -CONFIG_USB_U132_HCD=m CONFIG_USB_SL811_HCD=m CONFIG_USB_ACM=m CONFIG_USB_PRINTER=m diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile index a81e6ef293af..3a9a0dd4be70 100644 --- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -31,7 +31,6 @@ obj-$(CONFIG_USB_FHCI_HCD) += host/ obj-$(CONFIG_USB_XHCI_HCD) += host/ obj-$(CONFIG_USB_SL811_HCD) += host/ obj-$(CONFIG_USB_ISP1362_HCD) += host/ -obj-$(CONFIG_USB_U132_HCD) += host/ obj-$(CONFIG_USB_R8A66597_HCD) += host/ obj-$(CONFIG_USB_FSL_USB2) += host/ obj-$(CONFIG_USB_FOTG210_HCD) += host/ diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig index eacb603ad1b2..c170672f847e 100644 --- a/drivers/usb/host/Kconfig +++ b/drivers/usb/host/Kconfig @@ -622,33 +622,6 @@ config FHCI_DEBUG Say "y" to see some FHCI debug information and statistics through debugfs. -config USB_U132_HCD - tristate "Elan U132 Adapter Host Controller" - depends on USB_FTDI_ELAN - help - The U132 adapter is a USB to CardBus adapter specifically designed - for PC cards that contain an OHCI host controller. Typical PC cards - are the Orange Mobile 3G Option GlobeTrotter Fusion card. The U132 - adapter will *NOT* work with PC cards that do not contain an OHCI - controller. - - For those PC cards that contain multiple OHCI controllers only the - first one is used. - - The driver consists of two modules, the "ftdi-elan" module is a - USB client driver that interfaces to the FTDI chip within ELAN's - USB-to-PCMCIA adapter, and this "u132-hcd" module is a USB host - controller driver that talks to the OHCI controller within the - CardBus cards that are inserted in the U132 adapter. - - This driver has been tested with a CardBus OHCI USB adapter, and - worked with a USB PEN Drive inserted into the first USB port of - the PCCARD. A rather pointless thing to do, but useful for testing. - - It is safe to say M here. - - See also - config USB_SL811_HCD tristate "SL811HS HCD support" depends on HAS_IOMEM diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile index 5a13712f367d..be4e5245c52f 100644 --- a/drivers/usb/host/Makefile +++ b/drivers/usb/host/Makefile @@ -76,7 +76,6 @@ obj-$(CONFIG_USB_XHCI_MTK) += xhci-mtk-hcd.o obj-$(CONFIG_USB_XHCI_TEGRA) += xhci-tegra.o obj-$(CONFIG_USB_SL811_HCD) += sl811-hcd.o obj-$(CONFIG_USB_SL811_CS) += sl811_cs.o -obj-$(CONFIG_USB_U132_HCD) += u132-hcd.o obj-$(CONFIG_USB_R8A66597_HCD) += r8a66597-hcd.o obj-$(CONFIG_USB_FSL_USB2) += fsl-mph-dr-of.o obj-$(CONFIG_USB_EHCI_FSL) += fsl-mph-dr-of.o diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c deleted file mode 100644 index 45244c791bcb..000000000000 --- a/drivers/usb/host/u132-hcd.c +++ /dev/null @@ -1,3239 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* -* Host Controller Driver for the Elan Digital Systems U132 adapter -* -* Copyright(C) 2006 Elan Digital Systems Limited -* http://www.elandigitalsystems.com -* -* Author and Maintainer - Tony Olech - Elan Digital Systems -* tony.olech@elandigitalsystems.com -* -* This driver was written by Tony Olech(tony.olech@elandigitalsystems.com) -* based on various USB host drivers in the 2.6.15 linux kernel -* with constant reference to the 3rd Edition of Linux Device Drivers -* published by O'Reilly -* -* The U132 adapter is a USB to CardBus adapter specifically designed -* for PC cards that contain an OHCI host controller. Typical PC cards -* are the Orange Mobile 3G Option GlobeTrotter Fusion card. -* -* The U132 adapter will *NOT *work with PC cards that do not contain -* an OHCI controller. A simple way to test whether a PC card has an -* OHCI controller as an interface is to insert the PC card directly -* into a laptop(or desktop) with a CardBus slot and if "lspci" shows -* a new USB controller and "lsusb -v" shows a new OHCI Host Controller -* then there is a good chance that the U132 adapter will support the -* PC card.(you also need the specific client driver for the PC card) -* -* Please inform the Author and Maintainer about any PC cards that -* contain OHCI Host Controller and work when directly connected to -* an embedded CardBus slot but do not work when they are connected -* via an ELAN U132 adapter. -* -*/ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - - /* FIXME ohci.h is ONLY for internal use by the OHCI driver. - * If you're going to try stuff like this, you need to split - * out shareable stuff (register declarations?) into its own - * file, maybe name - */ - -#include "ohci.h" -#define OHCI_CONTROL_INIT OHCI_CTRL_CBSR -#define OHCI_INTR_INIT (OHCI_INTR_MIE | OHCI_INTR_UE | OHCI_INTR_RD | \ - OHCI_INTR_WDH) -MODULE_AUTHOR("Tony Olech - Elan Digital Systems Limited"); -MODULE_DESCRIPTION("U132 USB Host Controller Driver"); -MODULE_LICENSE("GPL"); -#define INT_MODULE_PARM(n, v) static int n = v;module_param(n, int, 0444) -INT_MODULE_PARM(testing, 0); -/* Some boards misreport power switching/overcurrent*/ -static bool distrust_firmware = true; -module_param(distrust_firmware, bool, 0); -MODULE_PARM_DESC(distrust_firmware, - "true to distrust firmware power/overcurrentt setup"); -static DECLARE_WAIT_QUEUE_HEAD(u132_hcd_wait); -/* -* u132_module_lock exists to protect access to global variables -* -*/ -static DEFINE_MUTEX(u132_module_lock); -static int u132_exiting; -static int u132_instances; -/* -* end of the global variables protected by u132_module_lock -*/ -static struct workqueue_struct *workqueue; -#define MAX_U132_PORTS 7 -#define MAX_U132_ADDRS 128 -#define MAX_U132_UDEVS 4 -#define MAX_U132_ENDPS 100 -#define MAX_U132_RINGS 4 -static const char *cc_to_text[16] = { - "No Error ", - "CRC Error ", - "Bit Stuff ", - "Data Togg ", - "Stall ", - "DevNotResp ", - "PIDCheck ", - "UnExpPID ", - "DataOver ", - "DataUnder ", - "(for hw) ", - "(for hw) ", - "BufferOver ", - "BuffUnder ", - "(for HCD) ", - "(for HCD) " -}; -struct u132_port { - struct u132 *u132; - int reset; - int enable; - int power; - int Status; -}; -struct u132_addr { - u8 address; -}; -struct u132_udev { - struct kref kref; - struct usb_device *usb_device; - u8 enumeration; - u8 udev_number; - u8 usb_addr; - u8 portnumber; - u8 endp_number_in[16]; - u8 endp_number_out[16]; -}; -#define ENDP_QUEUE_SHIFT 3 -#define ENDP_QUEUE_SIZE (1<platform_dev, offsetof(struct \ - ohci_regs, member), 0, data) -#define u132_write_pcimem(u132, member, data) \ - usb_ftdi_elan_write_pcimem(u132->platform_dev, offsetof(struct \ - ohci_regs, member), 0, data) -static inline struct u132 *udev_to_u132(struct u132_udev *udev) -{ - u8 udev_number = udev->udev_number; - return container_of(udev, struct u132, udev[udev_number]); -} - -static inline struct u132 *hcd_to_u132(struct usb_hcd *hcd) -{ - return (struct u132 *)(hcd->hcd_priv); -} - -static inline struct usb_hcd *u132_to_hcd(struct u132 *u132) -{ - return container_of((void *)u132, struct usb_hcd, hcd_priv); -} - -static inline void u132_disable(struct u132 *u132) -{ - u132_to_hcd(u132)->state = HC_STATE_HALT; -} - - -#define kref_to_u132(d) container_of(d, struct u132, kref) -#define kref_to_u132_endp(d) container_of(d, struct u132_endp, kref) -#define kref_to_u132_udev(d) container_of(d, struct u132_udev, kref) -#include "../misc/usb_u132.h" -static const char hcd_name[] = "u132_hcd"; -#define PORT_C_MASK ((USB_PORT_STAT_C_CONNECTION | USB_PORT_STAT_C_ENABLE | \ - USB_PORT_STAT_C_SUSPEND | USB_PORT_STAT_C_OVERCURRENT | \ - USB_PORT_STAT_C_RESET) << 16) -static void u132_hcd_delete(struct kref *kref) -{ - struct u132 *u132 = kref_to_u132(kref); - struct platform_device *pdev = u132->platform_dev; - struct usb_hcd *hcd = u132_to_hcd(u132); - u132->going += 1; - mutex_lock(&u132_module_lock); - u132_instances -= 1; - mutex_unlock(&u132_module_lock); - dev_warn(&u132->platform_dev->dev, - "FREEING the hcd=%p and thus the u132=%p going=%d pdev=%p\n", - hcd, u132, u132->going, pdev); - usb_put_hcd(hcd); -} - -static inline void u132_u132_put_kref(struct u132 *u132) -{ - kref_put(&u132->kref, u132_hcd_delete); -} - -static inline void u132_u132_init_kref(struct u132 *u132) -{ - kref_init(&u132->kref); -} - -static void u132_udev_delete(struct kref *kref) -{ - struct u132_udev *udev = kref_to_u132_udev(kref); - udev->udev_number = 0; - udev->usb_device = NULL; - udev->usb_addr = 0; - udev->enumeration = 0; -} - -static inline void u132_udev_put_kref(struct u132 *u132, struct u132_udev *udev) -{ - kref_put(&udev->kref, u132_udev_delete); -} - -static inline void u132_udev_get_kref(struct u132 *u132, struct u132_udev *udev) -{ - kref_get(&udev->kref); -} - -static inline void u132_udev_init_kref(struct u132 *u132, - struct u132_udev *udev) -{ - kref_init(&udev->kref); -} - -static inline void u132_ring_put_kref(struct u132 *u132, struct u132_ring *ring) -{ - kref_put(&u132->kref, u132_hcd_delete); -} - -static void u132_ring_requeue_work(struct u132 *u132, struct u132_ring *ring, - unsigned int delta) -{ - if (delta > 0) { - if (queue_delayed_work(workqueue, &ring->scheduler, delta)) - return; - } else if (queue_delayed_work(workqueue, &ring->scheduler, 0)) - return; - kref_put(&u132->kref, u132_hcd_delete); -} - -static void u132_ring_queue_work(struct u132 *u132, struct u132_ring *ring, - unsigned int delta) -{ - kref_get(&u132->kref); - u132_ring_requeue_work(u132, ring, delta); -} - -static void u132_ring_cancel_work(struct u132 *u132, struct u132_ring *ring) -{ - if (cancel_delayed_work(&ring->scheduler)) - kref_put(&u132->kref, u132_hcd_delete); -} - -static void u132_endp_delete(struct kref *kref) -{ - struct u132_endp *endp = kref_to_u132_endp(kref); - struct u132 *u132 = endp->u132; - u8 usb_addr = endp->usb_addr; - u8 usb_endp = endp->usb_endp; - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - u8 endp_number = endp->endp_number; - struct usb_host_endpoint *hep = endp->hep; - struct u132_ring *ring = endp->ring; - struct list_head *head = &endp->endp_ring; - ring->length -= 1; - if (endp == ring->curr_endp) { - if (list_empty(head)) { - ring->curr_endp = NULL; - list_del(head); - } else { - struct u132_endp *next_endp = list_entry(head->next, - struct u132_endp, endp_ring); - ring->curr_endp = next_endp; - list_del(head); - } - } else { - list_del(head); - } - if (endp->input) { - udev->endp_number_in[usb_endp] = 0; - u132_udev_put_kref(u132, udev); - } - if (endp->output) { - udev->endp_number_out[usb_endp] = 0; - u132_udev_put_kref(u132, udev); - } - u132->endp[endp_number - 1] = NULL; - hep->hcpriv = NULL; - kfree(endp); - u132_u132_put_kref(u132); -} - -static inline void u132_endp_put_kref(struct u132 *u132, struct u132_endp *endp) -{ - kref_put(&endp->kref, u132_endp_delete); -} - -static inline void u132_endp_get_kref(struct u132 *u132, struct u132_endp *endp) -{ - kref_get(&endp->kref); -} - -static inline void u132_endp_init_kref(struct u132 *u132, - struct u132_endp *endp) -{ - kref_init(&endp->kref); - kref_get(&u132->kref); -} - -static void u132_endp_queue_work(struct u132 *u132, struct u132_endp *endp, - unsigned int delta) -{ - if (queue_delayed_work(workqueue, &endp->scheduler, delta)) - kref_get(&endp->kref); -} - -static void u132_endp_cancel_work(struct u132 *u132, struct u132_endp *endp) -{ - if (cancel_delayed_work(&endp->scheduler)) - kref_put(&endp->kref, u132_endp_delete); -} - -static inline void u132_monitor_put_kref(struct u132 *u132) -{ - kref_put(&u132->kref, u132_hcd_delete); -} - -static void u132_monitor_queue_work(struct u132 *u132, unsigned int delta) -{ - if (queue_delayed_work(workqueue, &u132->monitor, delta)) - kref_get(&u132->kref); -} - -static void u132_monitor_requeue_work(struct u132 *u132, unsigned int delta) -{ - if (!queue_delayed_work(workqueue, &u132->monitor, delta)) - kref_put(&u132->kref, u132_hcd_delete); -} - -static void u132_monitor_cancel_work(struct u132 *u132) -{ - if (cancel_delayed_work(&u132->monitor)) - kref_put(&u132->kref, u132_hcd_delete); -} - -static int read_roothub_info(struct u132 *u132) -{ - u32 revision; - int retval; - struct device *dev = &u132->platform_dev->dev; - - retval = u132_read_pcimem(u132, revision, &revision); - if (retval) { - dev_err(dev, "error %d accessing device control\n", retval); - return retval; - } else if ((revision & 0xFF) == 0x10) { - } else if ((revision & 0xFF) == 0x11) { - } else { - dev_err(dev, "device revision is not valid %08X\n", revision); - return -ENODEV; - } - retval = u132_read_pcimem(u132, control, &u132->hc_control); - if (retval) { - dev_err(dev, "error %d accessing device control\n", retval); - return retval; - } - retval = u132_read_pcimem(u132, roothub.status, - &u132->hc_roothub_status); - if (retval) { - dev_err(dev, "error %d accessing device reg roothub.status\n", retval); - return retval; - } - retval = u132_read_pcimem(u132, roothub.a, &u132->hc_roothub_a); - if (retval) { - dev_err(dev, "error %d accessing device reg roothub.a\n", retval); - return retval; - } - { - int I = u132->num_ports; - int i = 0; - while (I-- > 0) { - retval = u132_read_pcimem(u132, roothub.portstatus[i], - &u132->hc_roothub_portstatus[i]); - if (retval) { - dev_err(dev, "error %d accessing device roothub.portstatus[%d]\n", - retval, i); - return retval; - } else { - i += 1; - } - } - } - return 0; -} - -static void u132_hcd_monitor_work(struct work_struct *work) -{ - struct u132 *u132 = container_of(work, struct u132, monitor.work); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n", - u132->going); - u132_monitor_put_kref(u132); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - u132_monitor_put_kref(u132); - return; - } else { - int retval; - mutex_lock(&u132->sw_lock); - retval = read_roothub_info(u132); - if (retval) { - struct usb_hcd *hcd = u132_to_hcd(u132); - u132_disable(u132); - u132->going = 1; - mutex_unlock(&u132->sw_lock); - usb_hc_died(hcd); - ftdi_elan_gone_away(u132->platform_dev); - u132_monitor_put_kref(u132); - return; - } else { - u132_monitor_requeue_work(u132, 500); - mutex_unlock(&u132->sw_lock); - return; - } - } -} - -static void u132_hcd_giveback_urb(struct u132 *u132, struct u132_endp *endp, - struct urb *urb, int status) -{ - struct u132_ring *ring; - unsigned long irqs; - struct usb_hcd *hcd = u132_to_hcd(u132); - urb->error_count = 0; - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - usb_hcd_unlink_urb_from_ep(hcd, urb); - endp->queue_next += 1; - if (ENDP_QUEUE_SIZE > --endp->queue_size) { - endp->active = 0; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - } else { - struct list_head *next = endp->urb_more.next; - struct u132_urbq *urbq = list_entry(next, struct u132_urbq, - urb_more); - list_del(next); - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = - urbq->urb; - endp->active = 0; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - kfree(urbq); - } - mutex_lock(&u132->scheduler_lock); - ring = endp->ring; - ring->in_use = 0; - u132_ring_cancel_work(u132, ring); - u132_ring_queue_work(u132, ring, 0); - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - usb_hcd_giveback_urb(hcd, urb, status); -} - -static void u132_hcd_forget_urb(struct u132 *u132, struct u132_endp *endp, - struct urb *urb, int status) -{ - u132_endp_put_kref(u132, endp); -} - -static void u132_hcd_abandon_urb(struct u132 *u132, struct u132_endp *endp, - struct urb *urb, int status) -{ - unsigned long irqs; - struct usb_hcd *hcd = u132_to_hcd(u132); - urb->error_count = 0; - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - usb_hcd_unlink_urb_from_ep(hcd, urb); - endp->queue_next += 1; - if (ENDP_QUEUE_SIZE > --endp->queue_size) { - endp->active = 0; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - } else { - struct list_head *next = endp->urb_more.next; - struct u132_urbq *urbq = list_entry(next, struct u132_urbq, - urb_more); - list_del(next); - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = - urbq->urb; - endp->active = 0; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - kfree(urbq); - } - usb_hcd_giveback_urb(hcd, urb, status); -} - -static inline int edset_input(struct u132 *u132, struct u132_ring *ring, - struct u132_endp *endp, struct urb *urb, u8 address, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - return usb_ftdi_elan_edset_input(u132->platform_dev, ring->number, endp, - urb, address, endp->usb_endp, toggle_bits, callback); -} - -static inline int edset_setup(struct u132 *u132, struct u132_ring *ring, - struct u132_endp *endp, struct urb *urb, u8 address, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - return usb_ftdi_elan_edset_setup(u132->platform_dev, ring->number, endp, - urb, address, endp->usb_endp, toggle_bits, callback); -} - -static inline int edset_single(struct u132 *u132, struct u132_ring *ring, - struct u132_endp *endp, struct urb *urb, u8 address, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - return usb_ftdi_elan_edset_single(u132->platform_dev, ring->number, - endp, urb, address, endp->usb_endp, toggle_bits, callback); -} - -static inline int edset_output(struct u132 *u132, struct u132_ring *ring, - struct u132_endp *endp, struct urb *urb, u8 address, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - return usb_ftdi_elan_edset_output(u132->platform_dev, ring->number, - endp, urb, address, endp->usb_endp, toggle_bits, callback); -} - - -/* -* must not LOCK sw_lock -* -*/ -static void u132_hcd_interrupt_recv(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n", - u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - struct u132_ring *ring = endp->ring; - u8 *u = urb->transfer_buffer + urb->actual_length; - u8 *b = buf; - int L = len; - - while (L-- > 0) - *u++ = *b++; - - urb->actual_length += len; - if ((condition_code == TD_CC_NOERROR) && - (urb->transfer_buffer_length > urb->actual_length)) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - if (urb->actual_length > 0) { - int retval; - mutex_unlock(&u132->scheduler_lock); - retval = edset_single(u132, ring, endp, urb, - address, endp->toggle_bits, - u132_hcd_interrupt_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, - retval); - } else { - ring->in_use = 0; - endp->active = 0; - endp->jiffies = jiffies + - msecs_to_jiffies(urb->interval); - u132_ring_cancel_work(u132, ring); - u132_ring_queue_work(u132, ring, 0); - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - } - return; - } else if ((condition_code == TD_DATAUNDERRUN) && - ((urb->transfer_flags & URB_SHORT_NOT_OK) == 0)) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else { - if (condition_code == TD_CC_NOERROR) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, - 0, 1 & toggle_bits); - } else if (condition_code == TD_CC_STALL) { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, endp->usb_endp, - 0, 0); - } else { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, endp->usb_endp, - 0, 0); - dev_err(&u132->platform_dev->dev, "urb=%p giving back INTERRUPT %s\n", - urb, cc_to_text[condition_code]); - } - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_bulk_output_sent(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n", - u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - struct u132_ring *ring = endp->ring; - urb->actual_length += len; - endp->toggle_bits = toggle_bits; - if (urb->transfer_buffer_length > urb->actual_length) { - int retval; - mutex_unlock(&u132->scheduler_lock); - retval = edset_output(u132, ring, endp, urb, address, - endp->toggle_bits, u132_hcd_bulk_output_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_bulk_input_recv(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - struct u132_ring *ring = endp->ring; - u8 *u = urb->transfer_buffer + urb->actual_length; - u8 *b = buf; - int L = len; - - while (L-- > 0) - *u++ = *b++; - - urb->actual_length += len; - if ((condition_code == TD_CC_NOERROR) && - (urb->transfer_buffer_length > urb->actual_length)) { - int retval; - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_input(u132->platform_dev, - ring->number, endp, urb, address, - endp->usb_endp, endp->toggle_bits, - u132_hcd_bulk_input_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else if (condition_code == TD_CC_NOERROR) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } else if ((condition_code == TD_DATAUNDERRUN) && - ((urb->transfer_flags & URB_SHORT_NOT_OK) == 0)) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else if (condition_code == TD_DATAUNDERRUN) { - endp->toggle_bits = toggle_bits; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, - 1 & toggle_bits); - dev_warn(&u132->platform_dev->dev, - "urb=%p(SHORT NOT OK) giving back BULK IN %s\n", - urb, cc_to_text[condition_code]); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else if (condition_code == TD_CC_STALL) { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, 0); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } else { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, endp->usb_endp, 0, 0); - dev_err(&u132->platform_dev->dev, - "urb=%p giving back BULK IN code=%d %s\n", - urb, condition_code, cc_to_text[condition_code]); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_configure_empty_sent(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_configure_input_recv(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - struct u132_ring *ring = endp->ring; - u8 *u = urb->transfer_buffer; - u8 *b = buf; - int L = len; - - while (L-- > 0) - *u++ = *b++; - - urb->actual_length = len; - if ((condition_code == TD_CC_NOERROR) || ((condition_code == - TD_DATAUNDERRUN) && ((urb->transfer_flags & - URB_SHORT_NOT_OK) == 0))) { - int retval; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_empty(u132->platform_dev, - ring->number, endp, urb, address, - endp->usb_endp, 0x3, - u132_hcd_configure_empty_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else if (condition_code == TD_CC_STALL) { - mutex_unlock(&u132->scheduler_lock); - dev_warn(&u132->platform_dev->dev, - "giving back SETUP INPUT STALL urb %p\n", urb); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } else { - mutex_unlock(&u132->scheduler_lock); - dev_err(&u132->platform_dev->dev, - "giving back SETUP INPUT %s urb %p\n", - cc_to_text[condition_code], urb); - u132_hcd_giveback_urb(u132, endp, urb, - cc_to_error[condition_code]); - return; - } - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_configure_empty_recv(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n", - u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_configure_setup_sent(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, "device has been removed %d\n", - u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - if (usb_pipein(urb->pipe)) { - int retval; - struct u132_ring *ring = endp->ring; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_input(u132->platform_dev, - ring->number, endp, urb, address, - endp->usb_endp, 0, - u132_hcd_configure_input_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - int retval; - struct u132_ring *ring = endp->ring; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_input(u132->platform_dev, - ring->number, endp, urb, address, - endp->usb_endp, 0, - u132_hcd_configure_empty_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_enumeration_empty_recv(void *data, struct urb *urb, - u8 *buf, int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - u132->addr[0].address = 0; - endp->usb_addr = udev->usb_addr; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_enumeration_address_sent(void *data, struct urb *urb, - u8 *buf, int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - int retval; - struct u132_ring *ring = endp->ring; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_input(u132->platform_dev, - ring->number, endp, urb, 0, endp->usb_endp, 0, - u132_hcd_enumeration_empty_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_initial_empty_sent(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_initial_input_recv(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - int retval; - struct u132_ring *ring = endp->ring; - u8 *u = urb->transfer_buffer; - u8 *b = buf; - int L = len; - - while (L-- > 0) - *u++ = *b++; - - urb->actual_length = len; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_empty(u132->platform_dev, - ring->number, endp, urb, address, endp->usb_endp, 0x3, - u132_hcd_initial_empty_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -static void u132_hcd_initial_setup_sent(void *data, struct urb *urb, u8 *buf, - int len, int toggle_bits, int error_count, int condition_code, - int repeat_number, int halted, int skipped, int actual, int non_null) -{ - struct u132_endp *endp = data; - struct u132 *u132 = endp->u132; - u8 address = u132->addr[endp->usb_addr].address; - mutex_lock(&u132->scheduler_lock); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_forget_urb(u132, endp, urb, -ENODEV); - return; - } else if (endp->dequeueing) { - endp->dequeueing = 0; - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -EINTR); - return; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, -ENODEV); - return; - } else if (!urb->unlinked) { - int retval; - struct u132_ring *ring = endp->ring; - mutex_unlock(&u132->scheduler_lock); - retval = usb_ftdi_elan_edset_input(u132->platform_dev, - ring->number, endp, urb, address, endp->usb_endp, 0, - u132_hcd_initial_input_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - dev_err(&u132->platform_dev->dev, - "CALLBACK called urb=%p unlinked=%d\n", - urb, urb->unlinked); - mutex_unlock(&u132->scheduler_lock); - u132_hcd_giveback_urb(u132, endp, urb, 0); - return; - } -} - -/* -* this work function is only executed from the work queue -* -*/ -static void u132_hcd_ring_work_scheduler(struct work_struct *work) -{ - struct u132_ring *ring = - container_of(work, struct u132_ring, scheduler.work); - struct u132 *u132 = ring->u132; - mutex_lock(&u132->scheduler_lock); - if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_ring_put_kref(u132, ring); - return; - } else if (ring->curr_endp) { - struct u132_endp *endp, *last_endp = ring->curr_endp; - unsigned long wakeup = 0; - list_for_each_entry(endp, &last_endp->endp_ring, endp_ring) { - if (endp->queue_next == endp->queue_last) { - } else if ((endp->delayed == 0) - || time_after_eq(jiffies, endp->jiffies)) { - ring->curr_endp = endp; - u132_endp_cancel_work(u132, last_endp); - u132_endp_queue_work(u132, last_endp, 0); - mutex_unlock(&u132->scheduler_lock); - u132_ring_put_kref(u132, ring); - return; - } else { - unsigned long delta = endp->jiffies - jiffies; - if (delta > wakeup) - wakeup = delta; - } - } - if (last_endp->queue_next == last_endp->queue_last) { - } else if ((last_endp->delayed == 0) || time_after_eq(jiffies, - last_endp->jiffies)) { - u132_endp_cancel_work(u132, last_endp); - u132_endp_queue_work(u132, last_endp, 0); - mutex_unlock(&u132->scheduler_lock); - u132_ring_put_kref(u132, ring); - return; - } else { - unsigned long delta = last_endp->jiffies - jiffies; - if (delta > wakeup) - wakeup = delta; - } - if (wakeup > 0) { - u132_ring_requeue_work(u132, ring, wakeup); - mutex_unlock(&u132->scheduler_lock); - return; - } else { - mutex_unlock(&u132->scheduler_lock); - u132_ring_put_kref(u132, ring); - return; - } - } else { - mutex_unlock(&u132->scheduler_lock); - u132_ring_put_kref(u132, ring); - return; - } -} - -static void u132_hcd_endp_work_scheduler(struct work_struct *work) -{ - struct u132_ring *ring; - struct u132_endp *endp = - container_of(work, struct u132_endp, scheduler.work); - struct u132 *u132 = endp->u132; - mutex_lock(&u132->scheduler_lock); - ring = endp->ring; - if (endp->edset_flush) { - endp->edset_flush = 0; - if (endp->dequeueing) - usb_ftdi_elan_edset_flush(u132->platform_dev, - ring->number, endp); - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else if (endp->active) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else if (endp->queue_next == endp->queue_last) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else if (endp->pipetype == PIPE_INTERRUPT) { - u8 address = u132->addr[endp->usb_addr].address; - if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else { - int retval; - struct urb *urb = endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_next]; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_single(u132, ring, endp, urb, address, - endp->toggle_bits, u132_hcd_interrupt_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } - } else if (endp->pipetype == PIPE_CONTROL) { - u8 address = u132->addr[endp->usb_addr].address; - if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else if (address == 0) { - int retval; - struct urb *urb = endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_next]; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_setup(u132, ring, endp, urb, address, - 0x2, u132_hcd_initial_setup_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else if (endp->usb_addr == 0) { - int retval; - struct urb *urb = endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_next]; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_setup(u132, ring, endp, urb, 0, 0x2, - u132_hcd_enumeration_address_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } else { - int retval; - struct urb *urb = endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_next]; - address = u132->addr[endp->usb_addr].address; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_setup(u132, ring, endp, urb, address, - 0x2, u132_hcd_configure_setup_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, retval); - return; - } - } else { - if (endp->input) { - u8 address = u132->addr[endp->usb_addr].address; - if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else { - int retval; - struct urb *urb = endp->urb_list[ - ENDP_QUEUE_MASK & endp->queue_next]; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_input(u132, ring, endp, urb, - address, endp->toggle_bits, - u132_hcd_bulk_input_recv); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, - retval); - return; - } - } else { /* output pipe */ - u8 address = u132->addr[endp->usb_addr].address; - if (ring->in_use) { - mutex_unlock(&u132->scheduler_lock); - u132_endp_put_kref(u132, endp); - return; - } else { - int retval; - struct urb *urb = endp->urb_list[ - ENDP_QUEUE_MASK & endp->queue_next]; - endp->active = 1; - ring->curr_endp = endp; - ring->in_use = 1; - mutex_unlock(&u132->scheduler_lock); - retval = edset_output(u132, ring, endp, urb, - address, endp->toggle_bits, - u132_hcd_bulk_output_sent); - if (retval != 0) - u132_hcd_giveback_urb(u132, endp, urb, - retval); - return; - } - } - } -} -#ifdef CONFIG_PM - -static void port_power(struct u132 *u132, int pn, int is_on) -{ - u132->port[pn].power = is_on; -} - -#endif - -static void u132_power(struct u132 *u132, int is_on) -{ - struct usb_hcd *hcd = u132_to_hcd(u132) - ; /* hub is inactive unless the port is powered */ - if (is_on) { - if (u132->power) - return; - u132->power = 1; - } else { - u132->power = 0; - hcd->state = HC_STATE_HALT; - } -} - -static int u132_periodic_reinit(struct u132 *u132) -{ - int retval; - u32 fi = u132->hc_fminterval & 0x03fff; - u32 fit; - u32 fminterval; - retval = u132_read_pcimem(u132, fminterval, &fminterval); - if (retval) - return retval; - fit = fminterval & FIT; - retval = u132_write_pcimem(u132, fminterval, - (fit ^ FIT) | u132->hc_fminterval); - if (retval) - return retval; - return u132_write_pcimem(u132, periodicstart, - ((9 * fi) / 10) & 0x3fff); -} - -static char *hcfs2string(int state) -{ - switch (state) { - case OHCI_USB_RESET: - return "reset"; - case OHCI_USB_RESUME: - return "resume"; - case OHCI_USB_OPER: - return "operational"; - case OHCI_USB_SUSPEND: - return "suspend"; - } - return "?"; -} - -static int u132_init(struct u132 *u132) -{ - int retval; - u32 control; - u132_disable(u132); - u132->next_statechange = jiffies; - retval = u132_write_pcimem(u132, intrdisable, OHCI_INTR_MIE); - if (retval) - return retval; - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; - if (u132->num_ports == 0) { - u32 rh_a = -1; - retval = u132_read_pcimem(u132, roothub.a, &rh_a); - if (retval) - return retval; - u132->num_ports = rh_a & RH_A_NDP; - retval = read_roothub_info(u132); - if (retval) - return retval; - } - if (u132->num_ports > MAX_U132_PORTS) - return -EINVAL; - - return 0; -} - - -/* Start an OHCI controller, set the BUS operational -* resets USB and controller -* enable interrupts -*/ -static int u132_run(struct u132 *u132) -{ - int retval; - u32 control; - u32 status; - u32 fminterval; - u32 periodicstart; - u32 cmdstatus; - u32 roothub_a; - int mask = OHCI_INTR_INIT; - int first = u132->hc_fminterval == 0; - int sleep_time = 0; - int reset_timeout = 30; /* ... allow extra time */ - u132_disable(u132); - if (first) { - u32 temp; - retval = u132_read_pcimem(u132, fminterval, &temp); - if (retval) - return retval; - u132->hc_fminterval = temp & 0x3fff; - u132->hc_fminterval |= FSMP(u132->hc_fminterval) << 16; - } - retval = u132_read_pcimem(u132, control, &u132->hc_control); - if (retval) - return retval; - dev_info(&u132->platform_dev->dev, - "resetting from state '%s', control = %08X\n", - hcfs2string(u132->hc_control & OHCI_CTRL_HCFS), - u132->hc_control); - switch (u132->hc_control & OHCI_CTRL_HCFS) { - case OHCI_USB_OPER: - sleep_time = 0; - break; - case OHCI_USB_SUSPEND: - case OHCI_USB_RESUME: - u132->hc_control &= OHCI_CTRL_RWC; - u132->hc_control |= OHCI_USB_RESUME; - sleep_time = 10; - break; - default: - u132->hc_control &= OHCI_CTRL_RWC; - u132->hc_control |= OHCI_USB_RESET; - sleep_time = 50; - break; - } - retval = u132_write_pcimem(u132, control, u132->hc_control); - if (retval) - return retval; - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; - msleep(sleep_time); - retval = u132_read_pcimem(u132, roothub.a, &roothub_a); - if (retval) - return retval; - if (!(roothub_a & RH_A_NPS)) { - int temp; /* power down each port */ - for (temp = 0; temp < u132->num_ports; temp++) { - retval = u132_write_pcimem(u132, - roothub.portstatus[temp], RH_PS_LSDA); - if (retval) - return retval; - } - } - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; -retry: - retval = u132_read_pcimem(u132, cmdstatus, &status); - if (retval) - return retval; - retval = u132_write_pcimem(u132, cmdstatus, OHCI_HCR); - if (retval) - return retval; -extra: { - retval = u132_read_pcimem(u132, cmdstatus, &status); - if (retval) - return retval; - if (0 != (status & OHCI_HCR)) { - if (--reset_timeout == 0) { - dev_err(&u132->platform_dev->dev, - "USB HC reset timed out!\n"); - return -ENODEV; - } else { - msleep(5); - goto extra; - } - } - } - if (u132->flags & OHCI_QUIRK_INITRESET) { - retval = u132_write_pcimem(u132, control, u132->hc_control); - if (retval) - return retval; - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; - } - retval = u132_write_pcimem(u132, ed_controlhead, 0x00000000); - if (retval) - return retval; - retval = u132_write_pcimem(u132, ed_bulkhead, 0x11000000); - if (retval) - return retval; - retval = u132_write_pcimem(u132, hcca, 0x00000000); - if (retval) - return retval; - retval = u132_periodic_reinit(u132); - if (retval) - return retval; - retval = u132_read_pcimem(u132, fminterval, &fminterval); - if (retval) - return retval; - retval = u132_read_pcimem(u132, periodicstart, &periodicstart); - if (retval) - return retval; - if (0 == (fminterval & 0x3fff0000) || 0 == periodicstart) { - if (!(u132->flags & OHCI_QUIRK_INITRESET)) { - u132->flags |= OHCI_QUIRK_INITRESET; - goto retry; - } else { - dev_err(&u132->platform_dev->dev, - "init err(%08x %04x)\n", - fminterval, periodicstart); - } - } /* start controller operations */ - u132->hc_control &= OHCI_CTRL_RWC; - u132->hc_control |= OHCI_CONTROL_INIT | OHCI_CTRL_BLE | OHCI_USB_OPER; - retval = u132_write_pcimem(u132, control, u132->hc_control); - if (retval) - return retval; - retval = u132_write_pcimem(u132, cmdstatus, OHCI_BLF); - if (retval) - return retval; - retval = u132_read_pcimem(u132, cmdstatus, &cmdstatus); - if (retval) - return retval; - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; - u132_to_hcd(u132)->state = HC_STATE_RUNNING; - retval = u132_write_pcimem(u132, roothub.status, RH_HS_DRWE); - if (retval) - return retval; - retval = u132_write_pcimem(u132, intrstatus, mask); - if (retval) - return retval; - retval = u132_write_pcimem(u132, intrdisable, - OHCI_INTR_MIE | OHCI_INTR_OC | OHCI_INTR_RHSC | OHCI_INTR_FNO | - OHCI_INTR_UE | OHCI_INTR_RD | OHCI_INTR_SF | OHCI_INTR_WDH | - OHCI_INTR_SO); - if (retval) - return retval; /* handle root hub init quirks ... */ - retval = u132_read_pcimem(u132, roothub.a, &roothub_a); - if (retval) - return retval; - roothub_a &= ~(RH_A_PSM | RH_A_OCPM); - if (u132->flags & OHCI_QUIRK_SUPERIO) { - roothub_a |= RH_A_NOCP; - roothub_a &= ~(RH_A_POTPGT | RH_A_NPS); - retval = u132_write_pcimem(u132, roothub.a, roothub_a); - if (retval) - return retval; - } else if ((u132->flags & OHCI_QUIRK_AMD756) || distrust_firmware) { - roothub_a |= RH_A_NPS; - retval = u132_write_pcimem(u132, roothub.a, roothub_a); - if (retval) - return retval; - } - retval = u132_write_pcimem(u132, roothub.status, RH_HS_LPSC); - if (retval) - return retval; - retval = u132_write_pcimem(u132, roothub.b, - (roothub_a & RH_A_NPS) ? 0 : RH_B_PPCM); - if (retval) - return retval; - retval = u132_read_pcimem(u132, control, &control); - if (retval) - return retval; - mdelay((roothub_a >> 23) & 0x1fe); - u132_to_hcd(u132)->state = HC_STATE_RUNNING; - return 0; -} - -static void u132_hcd_stop(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "u132 device %p(hcd=%p) has been removed %d\n", - u132, hcd, u132->going); - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device hcd=%p is being removed\n", hcd); - } else { - mutex_lock(&u132->sw_lock); - msleep(100); - u132_power(u132, 0); - mutex_unlock(&u132->sw_lock); - } -} - -static int u132_hcd_start(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else if (hcd->self.controller) { - int retval; - struct platform_device *pdev = - to_platform_device(hcd->self.controller); - u16 vendor = ((struct u132_platform_data *) - dev_get_platdata(&pdev->dev))->vendor; - u16 device = ((struct u132_platform_data *) - dev_get_platdata(&pdev->dev))->device; - mutex_lock(&u132->sw_lock); - msleep(10); - if (vendor == PCI_VENDOR_ID_AMD && device == 0x740c) { - u132->flags = OHCI_QUIRK_AMD756; - } else if (vendor == PCI_VENDOR_ID_OPTI && device == 0xc861) { - dev_err(&u132->platform_dev->dev, - "WARNING: OPTi workarounds unavailable\n"); - } else if (vendor == PCI_VENDOR_ID_COMPAQ && device == 0xa0f8) - u132->flags |= OHCI_QUIRK_ZFMICRO; - retval = u132_run(u132); - if (retval) { - u132_disable(u132); - u132->going = 1; - } - msleep(100); - mutex_unlock(&u132->sw_lock); - return retval; - } else { - dev_err(&u132->platform_dev->dev, "platform_device missing\n"); - return -ENODEV; - } -} - -static int u132_hcd_reset(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - int retval; - mutex_lock(&u132->sw_lock); - retval = u132_init(u132); - if (retval) { - u132_disable(u132); - u132->going = 1; - } - mutex_unlock(&u132->sw_lock); - return retval; - } -} - -static int create_endpoint_and_queue_int(struct u132 *u132, - struct u132_udev *udev, struct urb *urb, - struct usb_device *usb_dev, u8 usb_addr, u8 usb_endp, u8 address, - gfp_t mem_flags) -{ - struct u132_ring *ring; - unsigned long irqs; - int rc; - u8 endp_number; - struct u132_endp *endp = kmalloc(sizeof(struct u132_endp), mem_flags); - - if (!endp) - return -ENOMEM; - - spin_lock_init(&endp->queue_lock.slock); - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - rc = usb_hcd_link_urb_to_ep(u132_to_hcd(u132), urb); - if (rc) { - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - kfree(endp); - return rc; - } - - endp_number = ++u132->num_endpoints; - urb->ep->hcpriv = u132->endp[endp_number - 1] = endp; - INIT_DELAYED_WORK(&endp->scheduler, u132_hcd_endp_work_scheduler); - INIT_LIST_HEAD(&endp->urb_more); - ring = endp->ring = &u132->ring[0]; - if (ring->curr_endp) { - list_add_tail(&endp->endp_ring, &ring->curr_endp->endp_ring); - } else { - INIT_LIST_HEAD(&endp->endp_ring); - ring->curr_endp = endp; - } - ring->length += 1; - endp->dequeueing = 0; - endp->edset_flush = 0; - endp->active = 0; - endp->delayed = 0; - endp->endp_number = endp_number; - endp->u132 = u132; - endp->hep = urb->ep; - endp->pipetype = usb_pipetype(urb->pipe); - u132_endp_init_kref(u132, endp); - if (usb_pipein(urb->pipe)) { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, usb_endp, 0, 0); - endp->input = 1; - endp->output = 0; - udev->endp_number_in[usb_endp] = endp_number; - u132_udev_get_kref(u132, udev); - } else { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, usb_endp, 1, 0); - endp->input = 0; - endp->output = 1; - udev->endp_number_out[usb_endp] = endp_number; - u132_udev_get_kref(u132, udev); - } - urb->hcpriv = u132; - endp->delayed = 1; - endp->jiffies = jiffies + msecs_to_jiffies(urb->interval); - endp->udev_number = address; - endp->usb_addr = usb_addr; - endp->usb_endp = usb_endp; - endp->queue_size = 1; - endp->queue_last = 0; - endp->queue_next = 0; - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - u132_endp_queue_work(u132, endp, msecs_to_jiffies(urb->interval)); - return 0; -} - -static int queue_int_on_old_endpoint(struct u132 *u132, - struct u132_udev *udev, struct urb *urb, - struct usb_device *usb_dev, struct u132_endp *endp, u8 usb_addr, - u8 usb_endp, u8 address) -{ - urb->hcpriv = u132; - endp->delayed = 1; - endp->jiffies = jiffies + msecs_to_jiffies(urb->interval); - if (endp->queue_size++ < ENDP_QUEUE_SIZE) { - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - } else { - struct u132_urbq *urbq = kmalloc(sizeof(struct u132_urbq), - GFP_ATOMIC); - if (urbq == NULL) { - endp->queue_size -= 1; - return -ENOMEM; - } else { - list_add_tail(&urbq->urb_more, &endp->urb_more); - urbq->urb = urb; - } - } - return 0; -} - -static int create_endpoint_and_queue_bulk(struct u132 *u132, - struct u132_udev *udev, struct urb *urb, - struct usb_device *usb_dev, u8 usb_addr, u8 usb_endp, u8 address, - gfp_t mem_flags) -{ - int ring_number; - struct u132_ring *ring; - unsigned long irqs; - int rc; - u8 endp_number; - struct u132_endp *endp = kmalloc(sizeof(struct u132_endp), mem_flags); - - if (!endp) - return -ENOMEM; - - spin_lock_init(&endp->queue_lock.slock); - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - rc = usb_hcd_link_urb_to_ep(u132_to_hcd(u132), urb); - if (rc) { - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - kfree(endp); - return rc; - } - - endp_number = ++u132->num_endpoints; - urb->ep->hcpriv = u132->endp[endp_number - 1] = endp; - INIT_DELAYED_WORK(&endp->scheduler, u132_hcd_endp_work_scheduler); - INIT_LIST_HEAD(&endp->urb_more); - endp->dequeueing = 0; - endp->edset_flush = 0; - endp->active = 0; - endp->delayed = 0; - endp->endp_number = endp_number; - endp->u132 = u132; - endp->hep = urb->ep; - endp->pipetype = usb_pipetype(urb->pipe); - u132_endp_init_kref(u132, endp); - if (usb_pipein(urb->pipe)) { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, usb_endp, 0, 0); - ring_number = 3; - endp->input = 1; - endp->output = 0; - udev->endp_number_in[usb_endp] = endp_number; - u132_udev_get_kref(u132, udev); - } else { - endp->toggle_bits = 0x2; - usb_settoggle(udev->usb_device, usb_endp, 1, 0); - ring_number = 2; - endp->input = 0; - endp->output = 1; - udev->endp_number_out[usb_endp] = endp_number; - u132_udev_get_kref(u132, udev); - } - ring = endp->ring = &u132->ring[ring_number - 1]; - if (ring->curr_endp) { - list_add_tail(&endp->endp_ring, &ring->curr_endp->endp_ring); - } else { - INIT_LIST_HEAD(&endp->endp_ring); - ring->curr_endp = endp; - } - ring->length += 1; - urb->hcpriv = u132; - endp->udev_number = address; - endp->usb_addr = usb_addr; - endp->usb_endp = usb_endp; - endp->queue_size = 1; - endp->queue_last = 0; - endp->queue_next = 0; - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - u132_endp_queue_work(u132, endp, 0); - return 0; -} - -static int queue_bulk_on_old_endpoint(struct u132 *u132, struct u132_udev *udev, - struct urb *urb, - struct usb_device *usb_dev, struct u132_endp *endp, u8 usb_addr, - u8 usb_endp, u8 address) -{ - urb->hcpriv = u132; - if (endp->queue_size++ < ENDP_QUEUE_SIZE) { - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - } else { - struct u132_urbq *urbq = kmalloc(sizeof(struct u132_urbq), - GFP_ATOMIC); - if (urbq == NULL) { - endp->queue_size -= 1; - return -ENOMEM; - } else { - list_add_tail(&urbq->urb_more, &endp->urb_more); - urbq->urb = urb; - } - } - return 0; -} - -static int create_endpoint_and_queue_control(struct u132 *u132, - struct urb *urb, - struct usb_device *usb_dev, u8 usb_addr, u8 usb_endp, - gfp_t mem_flags) -{ - struct u132_ring *ring; - unsigned long irqs; - int rc; - u8 endp_number; - struct u132_endp *endp = kmalloc(sizeof(struct u132_endp), mem_flags); - - if (!endp) - return -ENOMEM; - - spin_lock_init(&endp->queue_lock.slock); - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - rc = usb_hcd_link_urb_to_ep(u132_to_hcd(u132), urb); - if (rc) { - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - kfree(endp); - return rc; - } - - endp_number = ++u132->num_endpoints; - urb->ep->hcpriv = u132->endp[endp_number - 1] = endp; - INIT_DELAYED_WORK(&endp->scheduler, u132_hcd_endp_work_scheduler); - INIT_LIST_HEAD(&endp->urb_more); - ring = endp->ring = &u132->ring[0]; - if (ring->curr_endp) { - list_add_tail(&endp->endp_ring, &ring->curr_endp->endp_ring); - } else { - INIT_LIST_HEAD(&endp->endp_ring); - ring->curr_endp = endp; - } - ring->length += 1; - endp->dequeueing = 0; - endp->edset_flush = 0; - endp->active = 0; - endp->delayed = 0; - endp->endp_number = endp_number; - endp->u132 = u132; - endp->hep = urb->ep; - u132_endp_init_kref(u132, endp); - u132_endp_get_kref(u132, endp); - if (usb_addr == 0) { - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - endp->udev_number = address; - endp->usb_addr = usb_addr; - endp->usb_endp = usb_endp; - endp->input = 1; - endp->output = 1; - endp->pipetype = usb_pipetype(urb->pipe); - u132_udev_init_kref(u132, udev); - u132_udev_get_kref(u132, udev); - udev->endp_number_in[usb_endp] = endp_number; - udev->endp_number_out[usb_endp] = endp_number; - urb->hcpriv = u132; - endp->queue_size = 1; - endp->queue_last = 0; - endp->queue_next = 0; - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - u132_endp_queue_work(u132, endp, 0); - return 0; - } else { /*(usb_addr > 0) */ - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - endp->udev_number = address; - endp->usb_addr = usb_addr; - endp->usb_endp = usb_endp; - endp->input = 1; - endp->output = 1; - endp->pipetype = usb_pipetype(urb->pipe); - u132_udev_get_kref(u132, udev); - udev->enumeration = 2; - udev->endp_number_in[usb_endp] = endp_number; - udev->endp_number_out[usb_endp] = endp_number; - urb->hcpriv = u132; - endp->queue_size = 1; - endp->queue_last = 0; - endp->queue_next = 0; - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = urb; - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - u132_endp_queue_work(u132, endp, 0); - return 0; - } -} - -static int queue_control_on_old_endpoint(struct u132 *u132, - struct urb *urb, - struct usb_device *usb_dev, struct u132_endp *endp, u8 usb_addr, - u8 usb_endp) -{ - if (usb_addr == 0) { - if (usb_pipein(urb->pipe)) { - urb->hcpriv = u132; - if (endp->queue_size++ < ENDP_QUEUE_SIZE) { - endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_last++] = urb; - } else { - struct u132_urbq *urbq = - kmalloc(sizeof(struct u132_urbq), - GFP_ATOMIC); - if (urbq == NULL) { - endp->queue_size -= 1; - return -ENOMEM; - } else { - list_add_tail(&urbq->urb_more, - &endp->urb_more); - urbq->urb = urb; - } - } - return 0; - } else { /* usb_pipeout(urb->pipe) */ - struct u132_addr *addr = &u132->addr[usb_dev->devnum]; - int I = MAX_U132_UDEVS; - int i = 0; - while (--I > 0) { - struct u132_udev *udev = &u132->udev[++i]; - if (udev->usb_device) { - continue; - } else { - udev->enumeration = 1; - u132->addr[0].address = i; - endp->udev_number = i; - udev->udev_number = i; - udev->usb_addr = usb_dev->devnum; - u132_udev_init_kref(u132, udev); - udev->endp_number_in[usb_endp] = - endp->endp_number; - u132_udev_get_kref(u132, udev); - udev->endp_number_out[usb_endp] = - endp->endp_number; - udev->usb_device = usb_dev; - ((u8 *) (urb->setup_packet))[2] = - addr->address = i; - u132_udev_get_kref(u132, udev); - break; - } - } - if (I == 0) { - dev_err(&u132->platform_dev->dev, - "run out of device space\n"); - return -EINVAL; - } - urb->hcpriv = u132; - if (endp->queue_size++ < ENDP_QUEUE_SIZE) { - endp->urb_list[ENDP_QUEUE_MASK & - endp->queue_last++] = urb; - } else { - struct u132_urbq *urbq = - kmalloc(sizeof(struct u132_urbq), - GFP_ATOMIC); - if (urbq == NULL) { - endp->queue_size -= 1; - return -ENOMEM; - } else { - list_add_tail(&urbq->urb_more, - &endp->urb_more); - urbq->urb = urb; - } - } - return 0; - } - } else { /*(usb_addr > 0) */ - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - urb->hcpriv = u132; - if (udev->enumeration != 2) - udev->enumeration = 2; - if (endp->queue_size++ < ENDP_QUEUE_SIZE) { - endp->urb_list[ENDP_QUEUE_MASK & endp->queue_last++] = - urb; - } else { - struct u132_urbq *urbq = - kmalloc(sizeof(struct u132_urbq), GFP_ATOMIC); - if (urbq == NULL) { - endp->queue_size -= 1; - return -ENOMEM; - } else { - list_add_tail(&urbq->urb_more, &endp->urb_more); - urbq->urb = urb; - } - } - return 0; - } -} - -static int u132_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, - gfp_t mem_flags) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (irqs_disabled()) { - if (gfpflags_allow_blocking(mem_flags)) { - printk(KERN_ERR "invalid context for function that might sleep\n"); - return -EINVAL; - } - } - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device is being removed urb=%p\n", urb); - return -ESHUTDOWN; - } else { - u8 usb_addr = usb_pipedevice(urb->pipe); - u8 usb_endp = usb_pipeendpoint(urb->pipe); - struct usb_device *usb_dev = urb->dev; - if (usb_pipetype(urb->pipe) == PIPE_INTERRUPT) { - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - struct u132_endp *endp = urb->ep->hcpriv; - urb->actual_length = 0; - if (endp) { - unsigned long irqs; - int retval; - spin_lock_irqsave(&endp->queue_lock.slock, - irqs); - retval = usb_hcd_link_urb_to_ep(hcd, urb); - if (retval == 0) { - retval = queue_int_on_old_endpoint( - u132, udev, urb, - usb_dev, endp, - usb_addr, usb_endp, - address); - if (retval) - usb_hcd_unlink_urb_from_ep( - hcd, urb); - } - spin_unlock_irqrestore(&endp->queue_lock.slock, - irqs); - if (retval) { - return retval; - } else { - u132_endp_queue_work(u132, endp, - msecs_to_jiffies(urb->interval)) - ; - return 0; - } - } else if (u132->num_endpoints == MAX_U132_ENDPS) { - return -EINVAL; - } else { /*(endp == NULL) */ - return create_endpoint_and_queue_int(u132, udev, - urb, usb_dev, usb_addr, - usb_endp, address, mem_flags); - } - } else if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) { - dev_err(&u132->platform_dev->dev, - "the hardware does not support PIPE_ISOCHRONOUS\n"); - return -EINVAL; - } else if (usb_pipetype(urb->pipe) == PIPE_BULK) { - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - struct u132_endp *endp = urb->ep->hcpriv; - urb->actual_length = 0; - if (endp) { - unsigned long irqs; - int retval; - spin_lock_irqsave(&endp->queue_lock.slock, - irqs); - retval = usb_hcd_link_urb_to_ep(hcd, urb); - if (retval == 0) { - retval = queue_bulk_on_old_endpoint( - u132, udev, urb, - usb_dev, endp, - usb_addr, usb_endp, - address); - if (retval) - usb_hcd_unlink_urb_from_ep( - hcd, urb); - } - spin_unlock_irqrestore(&endp->queue_lock.slock, - irqs); - if (retval) { - return retval; - } else { - u132_endp_queue_work(u132, endp, 0); - return 0; - } - } else if (u132->num_endpoints == MAX_U132_ENDPS) { - return -EINVAL; - } else { - return create_endpoint_and_queue_bulk(u132, - udev, urb, usb_dev, usb_addr, - usb_endp, address, mem_flags); - } - } else { - struct u132_endp *endp = urb->ep->hcpriv; - u16 urb_size = 8; - u8 *b = urb->setup_packet; - int i = 0; - char data[30 * 3 + 4]; - char *d = data; - int m = (sizeof(data) - 1) / 3; - int l = 0; - data[0] = 0; - while (urb_size-- > 0) { - if (i > m) { - } else if (i++ < m) { - int w = sprintf(d, " %02X", *b++); - d += w; - l += w; - } else { - d += sprintf(d, " .."); - } - } - if (endp) { - unsigned long irqs; - int retval; - spin_lock_irqsave(&endp->queue_lock.slock, - irqs); - retval = usb_hcd_link_urb_to_ep(hcd, urb); - if (retval == 0) { - retval = queue_control_on_old_endpoint( - u132, urb, usb_dev, - endp, usb_addr, - usb_endp); - if (retval) - usb_hcd_unlink_urb_from_ep( - hcd, urb); - } - spin_unlock_irqrestore(&endp->queue_lock.slock, - irqs); - if (retval) { - return retval; - } else { - u132_endp_queue_work(u132, endp, 0); - return 0; - } - } else if (u132->num_endpoints == MAX_U132_ENDPS) { - return -EINVAL; - } else { - return create_endpoint_and_queue_control(u132, - urb, usb_dev, usb_addr, usb_endp, - mem_flags); - } - } - } -} - -static int dequeue_from_overflow_chain(struct u132 *u132, - struct u132_endp *endp, struct urb *urb) -{ - struct u132_urbq *urbq; - - list_for_each_entry(urbq, &endp->urb_more, urb_more) { - if (urbq->urb == urb) { - struct usb_hcd *hcd = u132_to_hcd(u132); - list_del(&urbq->urb_more); - endp->queue_size -= 1; - urb->error_count = 0; - usb_hcd_giveback_urb(hcd, urb, 0); - return 0; - } - } - dev_err(&u132->platform_dev->dev, - "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d size=%d next=%04X last=%04X\n", - urb, endp->endp_number, endp, endp->ring->number, - endp->input ? 'I' : ' ', endp->output ? 'O' : ' ', - endp->usb_endp, endp->usb_addr, endp->queue_size, - endp->queue_next, endp->queue_last); - return -EINVAL; -} - -static int u132_endp_urb_dequeue(struct u132 *u132, struct u132_endp *endp, - struct urb *urb, int status) -{ - unsigned long irqs; - int rc; - - spin_lock_irqsave(&endp->queue_lock.slock, irqs); - rc = usb_hcd_check_unlink_urb(u132_to_hcd(u132), urb, status); - if (rc) { - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - return rc; - } - if (endp->queue_size == 0) { - dev_err(&u132->platform_dev->dev, - "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d\n", - urb, endp->endp_number, endp, endp->ring->number, - endp->input ? 'I' : ' ', endp->output ? 'O' : ' ', - endp->usb_endp, endp->usb_addr); - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - return -EINVAL; - } - if (urb == endp->urb_list[ENDP_QUEUE_MASK & endp->queue_next]) { - if (endp->active) { - endp->dequeueing = 1; - endp->edset_flush = 1; - u132_endp_queue_work(u132, endp, 0); - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - return 0; - } else { - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - u132_hcd_abandon_urb(u132, endp, urb, status); - return 0; - } - } else { - u16 queue_list = 0; - u16 queue_size = endp->queue_size; - u16 queue_scan = endp->queue_next; - struct urb **urb_slot = NULL; - while (++queue_list < ENDP_QUEUE_SIZE && --queue_size > 0) { - if (urb == endp->urb_list[ENDP_QUEUE_MASK & - ++queue_scan]) { - urb_slot = &endp->urb_list[ENDP_QUEUE_MASK & - queue_scan]; - break; - } - } - while (++queue_list < ENDP_QUEUE_SIZE && --queue_size > 0) { - *urb_slot = endp->urb_list[ENDP_QUEUE_MASK & - ++queue_scan]; - urb_slot = &endp->urb_list[ENDP_QUEUE_MASK & - queue_scan]; - } - if (urb_slot) { - struct usb_hcd *hcd = u132_to_hcd(u132); - - usb_hcd_unlink_urb_from_ep(hcd, urb); - endp->queue_size -= 1; - if (list_empty(&endp->urb_more)) { - spin_unlock_irqrestore(&endp->queue_lock.slock, - irqs); - } else { - struct list_head *next = endp->urb_more.next; - struct u132_urbq *urbq = list_entry(next, - struct u132_urbq, urb_more); - list_del(next); - *urb_slot = urbq->urb; - spin_unlock_irqrestore(&endp->queue_lock.slock, - irqs); - kfree(urbq); - } - urb->error_count = 0; - usb_hcd_giveback_urb(hcd, urb, status); - return 0; - } else if (list_empty(&endp->urb_more)) { - dev_err(&u132->platform_dev->dev, - "urb=%p not found in endp[%d]=%p ring[%d] %c%c usb_endp=%d usb_addr=%d size=%d next=%04X last=%04X\n", - urb, endp->endp_number, endp, endp->ring->number, - endp->input ? 'I' : ' ', - endp->output ? 'O' : ' ', endp->usb_endp, - endp->usb_addr, endp->queue_size, - endp->queue_next, endp->queue_last); - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - return -EINVAL; - } else { - int retval; - - usb_hcd_unlink_urb_from_ep(u132_to_hcd(u132), urb); - retval = dequeue_from_overflow_chain(u132, endp, - urb); - spin_unlock_irqrestore(&endp->queue_lock.slock, irqs); - return retval; - } - } -} - -static int u132_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 2) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else { - u8 usb_addr = usb_pipedevice(urb->pipe); - u8 usb_endp = usb_pipeendpoint(urb->pipe); - u8 address = u132->addr[usb_addr].address; - struct u132_udev *udev = &u132->udev[address]; - if (usb_pipein(urb->pipe)) { - u8 endp_number = udev->endp_number_in[usb_endp]; - struct u132_endp *endp = u132->endp[endp_number - 1]; - return u132_endp_urb_dequeue(u132, endp, urb, status); - } else { - u8 endp_number = udev->endp_number_out[usb_endp]; - struct u132_endp *endp = u132->endp[endp_number - 1]; - return u132_endp_urb_dequeue(u132, endp, urb, status); - } - } -} - -static void u132_endpoint_disable(struct usb_hcd *hcd, - struct usb_host_endpoint *hep) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 2) { - dev_err(&u132->platform_dev->dev, - "u132 device %p(hcd=%p hep=%p) has been removed %d\n", - u132, hcd, hep, u132->going); - } else { - struct u132_endp *endp = hep->hcpriv; - if (endp) - u132_endp_put_kref(u132, endp); - } -} - -static int u132_get_frame(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - dev_err(&u132->platform_dev->dev, "TODO: u132_get_frame\n"); - mdelay(100); - return 0; - } -} - -static int u132_roothub_descriptor(struct u132 *u132, - struct usb_hub_descriptor *desc) -{ - int retval; - u16 temp; - u32 rh_a = -1; - u32 rh_b = -1; - retval = u132_read_pcimem(u132, roothub.a, &rh_a); - if (retval) - return retval; - desc->bDescriptorType = USB_DT_HUB; - desc->bPwrOn2PwrGood = (rh_a & RH_A_POTPGT) >> 24; - desc->bHubContrCurrent = 0; - desc->bNbrPorts = u132->num_ports; - temp = 1 + (u132->num_ports / 8); - desc->bDescLength = 7 + 2 * temp; - temp = HUB_CHAR_COMMON_LPSM | HUB_CHAR_COMMON_OCPM; - if (rh_a & RH_A_NPS) - temp |= HUB_CHAR_NO_LPSM; - if (rh_a & RH_A_PSM) - temp |= HUB_CHAR_INDV_PORT_LPSM; - if (rh_a & RH_A_NOCP) - temp |= HUB_CHAR_NO_OCPM; - else if (rh_a & RH_A_OCPM) - temp |= HUB_CHAR_INDV_PORT_OCPM; - desc->wHubCharacteristics = cpu_to_le16(temp); - retval = u132_read_pcimem(u132, roothub.b, &rh_b); - if (retval) - return retval; - memset(desc->u.hs.DeviceRemovable, 0xff, - sizeof(desc->u.hs.DeviceRemovable)); - desc->u.hs.DeviceRemovable[0] = rh_b & RH_B_DR; - if (u132->num_ports > 7) { - desc->u.hs.DeviceRemovable[1] = (rh_b & RH_B_DR) >> 8; - desc->u.hs.DeviceRemovable[2] = 0xff; - } else { - desc->u.hs.DeviceRemovable[1] = 0xff; - } - return 0; -} - -static int u132_roothub_status(struct u132 *u132, __le32 *desc) -{ - u32 rh_status = -1; - int ret_status = u132_read_pcimem(u132, roothub.status, &rh_status); - *desc = cpu_to_le32(rh_status); - return ret_status; -} - -static int u132_roothub_portstatus(struct u132 *u132, __le32 *desc, u16 wIndex) -{ - if (wIndex == 0 || wIndex > u132->num_ports) { - return -EINVAL; - } else { - int port = wIndex - 1; - u32 rh_portstatus = -1; - int ret_portstatus = u132_read_pcimem(u132, - roothub.portstatus[port], &rh_portstatus); - *desc = cpu_to_le32(rh_portstatus); - if (*(u16 *) (desc + 2)) { - dev_info(&u132->platform_dev->dev, - "Port %d Status Change = %08X\n", port, *desc); - } - return ret_portstatus; - } -} - - -/* this timer value might be vendor-specific ... */ -#define PORT_RESET_HW_MSEC 10 -#define PORT_RESET_MSEC 10 -/* wrap-aware logic morphed from */ -#define tick_before(t1, t2) ((s16)(((s16)(t1))-((s16)(t2))) < 0) -static int u132_roothub_portreset(struct u132 *u132, int port_index) -{ - int retval; - u32 fmnumber; - u16 now; - u16 reset_done; - retval = u132_read_pcimem(u132, fmnumber, &fmnumber); - if (retval) - return retval; - now = fmnumber; - reset_done = now + PORT_RESET_MSEC; - do { - u32 portstat; - do { - retval = u132_read_pcimem(u132, - roothub.portstatus[port_index], &portstat); - if (retval) - return retval; - if (RH_PS_PRS & portstat) - continue; - else - break; - } while (tick_before(now, reset_done)); - if (RH_PS_PRS & portstat) - return -ENODEV; - if (RH_PS_CCS & portstat) { - if (RH_PS_PRSC & portstat) { - retval = u132_write_pcimem(u132, - roothub.portstatus[port_index], - RH_PS_PRSC); - if (retval) - return retval; - } - } else { - break; /* start the next reset, - sleep till it's probably done */ - } - retval = u132_write_pcimem(u132, roothub.portstatus[port_index], - RH_PS_PRS); - if (retval) - return retval; - msleep(PORT_RESET_HW_MSEC); - retval = u132_read_pcimem(u132, fmnumber, &fmnumber); - if (retval) - return retval; - now = fmnumber; - } while (tick_before(now, reset_done)); - return 0; -} - -static int u132_roothub_setportfeature(struct u132 *u132, u16 wValue, - u16 wIndex) -{ - if (wIndex == 0 || wIndex > u132->num_ports) { - return -EINVAL; - } else { - int port_index = wIndex - 1; - struct u132_port *port = &u132->port[port_index]; - port->Status &= ~(1 << wValue); - switch (wValue) { - case USB_PORT_FEAT_SUSPEND: - return u132_write_pcimem(u132, - roothub.portstatus[port_index], RH_PS_PSS); - case USB_PORT_FEAT_POWER: - return u132_write_pcimem(u132, - roothub.portstatus[port_index], RH_PS_PPS); - case USB_PORT_FEAT_RESET: - return u132_roothub_portreset(u132, port_index); - default: - return -EPIPE; - } - } -} - -static int u132_roothub_clearportfeature(struct u132 *u132, u16 wValue, - u16 wIndex) -{ - if (wIndex == 0 || wIndex > u132->num_ports) { - return -EINVAL; - } else { - int port_index = wIndex - 1; - u32 temp; - struct u132_port *port = &u132->port[port_index]; - port->Status &= ~(1 << wValue); - switch (wValue) { - case USB_PORT_FEAT_ENABLE: - temp = RH_PS_CCS; - break; - case USB_PORT_FEAT_C_ENABLE: - temp = RH_PS_PESC; - break; - case USB_PORT_FEAT_SUSPEND: - temp = RH_PS_POCI; - if ((u132->hc_control & OHCI_CTRL_HCFS) - != OHCI_USB_OPER) { - dev_err(&u132->platform_dev->dev, - "TODO resume_root_hub\n"); - } - break; - case USB_PORT_FEAT_C_SUSPEND: - temp = RH_PS_PSSC; - break; - case USB_PORT_FEAT_POWER: - temp = RH_PS_LSDA; - break; - case USB_PORT_FEAT_C_CONNECTION: - temp = RH_PS_CSC; - break; - case USB_PORT_FEAT_C_OVER_CURRENT: - temp = RH_PS_OCIC; - break; - case USB_PORT_FEAT_C_RESET: - temp = RH_PS_PRSC; - break; - default: - return -EPIPE; - } - return u132_write_pcimem(u132, roothub.portstatus[port_index], - temp); - } -} - - -/* the virtual root hub timer IRQ checks for hub status*/ -static int u132_hub_status_data(struct usb_hcd *hcd, char *buf) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device hcd=%p has been removed %d\n", - hcd, u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, - "device hcd=%p is being removed\n", hcd); - return -ESHUTDOWN; - } else { - int i, changed = 0, length = 1; - if (u132->flags & OHCI_QUIRK_AMD756) { - if ((u132->hc_roothub_a & RH_A_NDP) > MAX_ROOT_PORTS) { - dev_err(&u132->platform_dev->dev, - "bogus NDP, rereads as NDP=%d\n", - u132->hc_roothub_a & RH_A_NDP); - goto done; - } - } - if (u132->hc_roothub_status & (RH_HS_LPSC | RH_HS_OCIC)) - buf[0] = changed = 1; - else - buf[0] = 0; - if (u132->num_ports > 7) { - buf[1] = 0; - length++; - } - for (i = 0; i < u132->num_ports; i++) { - if (u132->hc_roothub_portstatus[i] & (RH_PS_CSC | - RH_PS_PESC | RH_PS_PSSC | RH_PS_OCIC | - RH_PS_PRSC)) { - changed = 1; - if (i < 7) - buf[0] |= 1 << (i + 1); - else - buf[1] |= 1 << (i - 7); - continue; - } - if (!(u132->hc_roothub_portstatus[i] & RH_PS_CCS)) - continue; - - if ((u132->hc_roothub_portstatus[i] & RH_PS_PSS)) - continue; - } -done: - return changed ? length : 0; - } -} - -static int u132_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, - u16 wIndex, char *buf, u16 wLength) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - int retval = 0; - mutex_lock(&u132->sw_lock); - switch (typeReq) { - case ClearHubFeature: - switch (wValue) { - case C_HUB_OVER_CURRENT: - case C_HUB_LOCAL_POWER: - break; - default: - goto stall; - } - break; - case SetHubFeature: - switch (wValue) { - case C_HUB_OVER_CURRENT: - case C_HUB_LOCAL_POWER: - break; - default: - goto stall; - } - break; - case ClearPortFeature:{ - retval = u132_roothub_clearportfeature(u132, - wValue, wIndex); - if (retval) - goto error; - break; - } - case GetHubDescriptor:{ - retval = u132_roothub_descriptor(u132, - (struct usb_hub_descriptor *)buf); - if (retval) - goto error; - break; - } - case GetHubStatus:{ - retval = u132_roothub_status(u132, - (__le32 *) buf); - if (retval) - goto error; - break; - } - case GetPortStatus:{ - retval = u132_roothub_portstatus(u132, - (__le32 *) buf, wIndex); - if (retval) - goto error; - break; - } - case SetPortFeature:{ - retval = u132_roothub_setportfeature(u132, - wValue, wIndex); - if (retval) - goto error; - break; - } - default: - goto stall; - error: - u132_disable(u132); - u132->going = 1; - break; - stall: - retval = -EPIPE; - break; - } - mutex_unlock(&u132->sw_lock); - return retval; - } -} - -static int u132_start_port_reset(struct usb_hcd *hcd, unsigned port_num) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - return 0; - } -} - - -#ifdef CONFIG_PM -static int u132_bus_suspend(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - return 0; - } -} - -static int u132_bus_resume(struct usb_hcd *hcd) -{ - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - return 0; - } -} - -#else -#define u132_bus_suspend NULL -#define u132_bus_resume NULL -#endif -static const struct hc_driver u132_hc_driver = { - .description = hcd_name, - .hcd_priv_size = sizeof(struct u132), - .irq = NULL, - .flags = HCD_USB11 | HCD_MEMORY, - .reset = u132_hcd_reset, - .start = u132_hcd_start, - .stop = u132_hcd_stop, - .urb_enqueue = u132_urb_enqueue, - .urb_dequeue = u132_urb_dequeue, - .endpoint_disable = u132_endpoint_disable, - .get_frame_number = u132_get_frame, - .hub_status_data = u132_hub_status_data, - .hub_control = u132_hub_control, - .bus_suspend = u132_bus_suspend, - .bus_resume = u132_bus_resume, - .start_port_reset = u132_start_port_reset, -}; - -/* -* This function may be called by the USB core whilst the "usb_all_devices_rwsem" -* is held for writing, thus this module must not call usb_remove_hcd() -* synchronously - but instead should immediately stop activity to the -* device and asynchronously call usb_remove_hcd() -*/ -static int u132_remove(struct platform_device *pdev) -{ - struct usb_hcd *hcd = platform_get_drvdata(pdev); - struct u132 *u132 = hcd_to_u132(hcd); - - if (u132->going++ > 1) { - dev_err(&u132->platform_dev->dev, - "already being removed\n"); - return -ENODEV; - } else { - int rings = MAX_U132_RINGS; - int endps = MAX_U132_ENDPS; - dev_err(&u132->platform_dev->dev, - "removing device u132.%d\n", - u132->sequence_num); - msleep(100); - mutex_lock(&u132->sw_lock); - u132_monitor_cancel_work(u132); - while (rings-- > 0) { - struct u132_ring *ring = &u132->ring[rings]; - u132_ring_cancel_work(u132, ring); - } - while (endps-- > 0) { - struct u132_endp *endp = u132->endp[endps]; - if (endp) - u132_endp_cancel_work(u132, endp); - } - u132->going += 1; - printk(KERN_INFO "removing device u132.%d\n", - u132->sequence_num); - mutex_unlock(&u132->sw_lock); - usb_remove_hcd(hcd); - u132_u132_put_kref(u132); - return 0; - } -} - -static void u132_initialise(struct u132 *u132, struct platform_device *pdev) -{ - int rings = MAX_U132_RINGS; - int ports = MAX_U132_PORTS; - int addrs = MAX_U132_ADDRS; - int udevs = MAX_U132_UDEVS; - int endps = MAX_U132_ENDPS; - u132->board = dev_get_platdata(&pdev->dev); - u132->platform_dev = pdev; - u132->power = 0; - u132->reset = 0; - mutex_init(&u132->sw_lock); - mutex_init(&u132->scheduler_lock); - while (rings-- > 0) { - struct u132_ring *ring = &u132->ring[rings]; - ring->u132 = u132; - ring->number = rings + 1; - ring->length = 0; - ring->curr_endp = NULL; - INIT_DELAYED_WORK(&ring->scheduler, - u132_hcd_ring_work_scheduler); - } - mutex_lock(&u132->sw_lock); - INIT_DELAYED_WORK(&u132->monitor, u132_hcd_monitor_work); - while (ports-- > 0) { - struct u132_port *port = &u132->port[ports]; - port->u132 = u132; - port->reset = 0; - port->enable = 0; - port->power = 0; - port->Status = 0; - } - while (addrs-- > 0) { - struct u132_addr *addr = &u132->addr[addrs]; - addr->address = 0; - } - while (udevs-- > 0) { - struct u132_udev *udev = &u132->udev[udevs]; - int i = ARRAY_SIZE(udev->endp_number_in); - int o = ARRAY_SIZE(udev->endp_number_out); - udev->usb_device = NULL; - udev->udev_number = 0; - udev->usb_addr = 0; - udev->portnumber = 0; - while (i-- > 0) - udev->endp_number_in[i] = 0; - - while (o-- > 0) - udev->endp_number_out[o] = 0; - - } - while (endps-- > 0) - u132->endp[endps] = NULL; - - mutex_unlock(&u132->sw_lock); -} - -static int u132_probe(struct platform_device *pdev) -{ - struct usb_hcd *hcd; - int retval; - u32 control; - u32 rh_a = -1; - - msleep(100); - if (u132_exiting > 0) - return -ENODEV; - - retval = ftdi_write_pcimem(pdev, intrdisable, OHCI_INTR_MIE); - if (retval) - return retval; - retval = ftdi_read_pcimem(pdev, control, &control); - if (retval) - return retval; - retval = ftdi_read_pcimem(pdev, roothub.a, &rh_a); - if (retval) - return retval; - - /* - * Note that after a successful call of usb_create_hcd(), - * dev_set_drvdata() was called such that platform_get_drvdata(pdev) - * returns hcd later on. - */ - hcd = usb_create_hcd(&u132_hc_driver, &pdev->dev, dev_name(&pdev->dev)); - if (!hcd) { - printk(KERN_ERR "failed to create the usb hcd struct for U132\n"); - ftdi_elan_gone_away(pdev); - return -ENOMEM; - } else { - struct u132 *u132 = hcd_to_u132(hcd); - retval = 0; - hcd->rsrc_start = 0; - mutex_lock(&u132_module_lock); - u132->sequence_num = ++u132_instances; - mutex_unlock(&u132_module_lock); - u132_u132_init_kref(u132); - u132_initialise(u132, pdev); - hcd->product_desc = "ELAN U132 Host Controller"; - retval = usb_add_hcd(hcd, 0, 0); - if (retval != 0) { - dev_err(&u132->platform_dev->dev, "init error %d\n", - retval); - u132_u132_put_kref(u132); - return retval; - } else { - device_wakeup_enable(hcd->self.controller); - u132_monitor_queue_work(u132, 100); - return 0; - } - } -} - - -#ifdef CONFIG_PM -/* - * for this device there's no useful distinction between the controller - * and its root hub. - */ -static int u132_suspend(struct platform_device *pdev, pm_message_t state) -{ - struct usb_hcd *hcd = platform_get_drvdata(pdev); - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - int retval = 0, ports; - - switch (state.event) { - case PM_EVENT_FREEZE: - retval = u132_bus_suspend(hcd); - break; - case PM_EVENT_SUSPEND: - case PM_EVENT_HIBERNATE: - ports = MAX_U132_PORTS; - while (ports-- > 0) { - port_power(u132, ports, 0); - } - break; - } - return retval; - } -} - -static int u132_resume(struct platform_device *pdev) -{ - struct usb_hcd *hcd = platform_get_drvdata(pdev); - struct u132 *u132 = hcd_to_u132(hcd); - if (u132->going > 1) { - dev_err(&u132->platform_dev->dev, - "device has been removed %d\n", u132->going); - return -ENODEV; - } else if (u132->going > 0) { - dev_err(&u132->platform_dev->dev, "device is being removed\n"); - return -ESHUTDOWN; - } else { - int retval = 0; - if (!u132->port[0].power) { - int ports = MAX_U132_PORTS; - while (ports-- > 0) { - port_power(u132, ports, 1); - } - retval = 0; - } else { - retval = u132_bus_resume(hcd); - } - return retval; - } -} - -#else -#define u132_suspend NULL -#define u132_resume NULL -#endif -/* -* this driver is loaded explicitly by ftdi_u132 -* -* the platform_driver struct is static because it is per type of module -*/ -static struct platform_driver u132_platform_driver = { - .probe = u132_probe, - .remove = u132_remove, - .suspend = u132_suspend, - .resume = u132_resume, - .driver = { - .name = hcd_name, - }, -}; -static int __init u132_hcd_init(void) -{ - int retval; - u132_instances = 0; - u132_exiting = 0; - if (usb_disabled()) - return -ENODEV; - workqueue = create_singlethread_workqueue("u132"); - if (!workqueue) - return -ENOMEM; - retval = platform_driver_register(&u132_platform_driver); - if (retval) - destroy_workqueue(workqueue); - - return retval; -} - - -module_init(u132_hcd_init); -static void __exit u132_hcd_exit(void) -{ - mutex_lock(&u132_module_lock); - u132_exiting += 1; - mutex_unlock(&u132_module_lock); - platform_driver_unregister(&u132_platform_driver); - printk(KERN_INFO "u132-hcd driver deregistered\n"); - wait_event(u132_hcd_wait, u132_instances == 0); - destroy_workqueue(workqueue); -} - - -module_exit(u132_hcd_exit); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform:u132_hcd"); diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig index a5f7652db7da..c873cfd4ee86 100644 --- a/drivers/usb/misc/Kconfig +++ b/drivers/usb/misc/Kconfig @@ -126,8 +126,6 @@ config USB_FTDI_ELAN worked with a USB PEN Drive inserted into the first USB port of the PCCARD. A rather pointless thing to do, but useful for testing. - See also the USB_U132_HCD entry "Elan U132 Adapter Host Controller" - It is safe to say M here. config USB_APPLEDISPLAY -- GitLab From bc4000fdb009a531fc5b94339f8531eee64bc232 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 14 Mar 2023 10:00:39 -0700 Subject: [PATCH 1008/5631] perf/x86/intel: Add Granite Rapids From core PMU's perspective, Granite Rapids is similar to the Sapphire Rapids. The key differences include: - Doesn't need the AUX event workaround for the mem load event. (Implement in this patch). - Support Retire Latency (Has been implemented in the commit c87a31093c70 ("perf/x86: Support Retire Latency")) - The event list, which will be supported in the perf tool later. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230314170041.2967712-1-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a3fb996a86a1..070cc4ef2672 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -5469,6 +5469,15 @@ pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i) return x86_pmu.pebs ? attr->mode : 0; } +static umode_t +mem_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + if (attr == &event_attr_mem_ld_aux.attr.attr) + return x86_pmu.flags & PMU_FL_MEM_LOADS_AUX ? attr->mode : 0; + + return pebs_is_visible(kobj, attr, i); +} + static umode_t lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) { @@ -5496,7 +5505,7 @@ static struct attribute_group group_events_td = { static struct attribute_group group_events_mem = { .name = "events", - .is_visible = pebs_is_visible, + .is_visible = mem_is_visible, }; static struct attribute_group group_events_tsx = { @@ -6486,6 +6495,10 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: + x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + fallthrough; + case INTEL_FAM6_GRANITERAPIDS_X: + case INTEL_FAM6_GRANITERAPIDS_D: pmem = true; x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6502,7 +6515,6 @@ __init int intel_pmu_init(void) x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = spr_get_event_constraints; -- GitLab From 5a796d5cb5d11f5aad4893a59f22715810769928 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Tue, 14 Mar 2023 10:00:40 -0700 Subject: [PATCH 1009/5631] perf/x86/msr: Add Granite Rapids The same as Sapphire Rapids, the SMI_COUNT MSR is also supported on Granite Rapids. Add Granite Rapids model. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230314170041.2967712-2-kan.liang@linux.intel.com --- arch/x86/events/msr.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index c65d8906cbcf..0feaaa571303 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -70,6 +70,8 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: + case INTEL_FAM6_GRANITERAPIDS_X: + case INTEL_FAM6_GRANITERAPIDS_D: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: -- GitLab From 872d28001be56b205bd9b3f97cea1571a1bde317 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 14 Mar 2023 10:00:41 -0700 Subject: [PATCH 1010/5631] perf/x86/cstate: Add Granite Rapids support Granite Rapids Xeon is successor or Emerald Rapids Xeon, and it will use the same C-state residency counters as Emerald Rapids (and previous Xeons, all the way back to Ice Lake Xeon). Add Granite Rapids Xeon support. Signed-off-by: Artem Bityutskiy Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230314170041.2967712-3-kan.liang@linux.intel.com --- arch/x86/events/intel/cstate.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 551741e79e03..835862c548cc 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -678,6 +678,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), -- GitLab From 8be174835f07b2c106b9961c0775486d06112a3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 16:09:19 +0100 Subject: [PATCH 1011/5631] usb: ftdi-elan: Delete driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver didn't see real maintainance since several years. It has several trivial issues (check $(scripts/checkpatch.pl -f drivers/usb/misc/ftdi-elan.c)) and some harder ones (difficult locking, explict kref handling, ...). Also today it's hard to find hardware to make actually use of such a card and I suspect the driver is completely unused. So remove it. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321150919.351947-1-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- arch/mips/configs/mtx1_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - drivers/usb/misc/Kconfig | 20 - drivers/usb/misc/Makefile | 1 - drivers/usb/misc/ftdi-elan.c | 2780 ------------------------- 5 files changed, 2803 deletions(-) delete mode 100644 drivers/usb/misc/ftdi-elan.c diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index 7b6a2a9daa10..c0c61c37d0b1 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -553,7 +553,6 @@ CONFIG_USB_LCD=m CONFIG_USB_CYPRESS_CY7C63=m CONFIG_USB_CYTHERM=m CONFIG_USB_IDMOUSE=m -CONFIG_USB_FTDI_ELAN=m CONFIG_USB_APPLEDISPLAY=m CONFIG_USB_SISUSBVGA=m CONFIG_USB_LD=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index fd5cc93c4a99..b6366e501f9a 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -907,7 +907,6 @@ CONFIG_USB_SEVSEG=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m CONFIG_USB_IDMOUSE=m -CONFIG_USB_FTDI_ELAN=m CONFIG_USB_APPLEDISPLAY=m CONFIG_USB_SISUSBVGA=m CONFIG_USB_LD=m diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig index c873cfd4ee86..08e3cf9efb38 100644 --- a/drivers/usb/misc/Kconfig +++ b/drivers/usb/misc/Kconfig @@ -108,26 +108,6 @@ config USB_IDMOUSE See also . -config USB_FTDI_ELAN - tristate "Elan PCMCIA CardBus Adapter USB Client" - help - ELAN's Uxxx series of adapters are USB to PCMCIA CardBus adapters. - Currently only the U132 adapter is available. - - The U132 is specifically designed for CardBus PC cards that contain - an OHCI host controller. Typical PC cards are the Orange Mobile 3G - Option GlobeTrotter Fusion card. The U132 adapter will *NOT* work - with PC cards that do not contain an OHCI controller. To use a U132 - adapter you will need this "ftdi-elan" module as well as the "u132-hcd" - module which is a USB host controller driver that talks to the OHCI - controller within CardBus card that are inserted in the U132 adapter. - - This driver has been tested with a CardBus OHCI USB adapter, and - worked with a USB PEN Drive inserted into the first USB port of - the PCCARD. A rather pointless thing to do, but useful for testing. - - It is safe to say M here. - config USB_APPLEDISPLAY tristate "Apple Cinema Display support" select BACKLIGHT_CLASS_DEVICE diff --git a/drivers/usb/misc/Makefile b/drivers/usb/misc/Makefile index 93581baec3a8..1992cc284d8a 100644 --- a/drivers/usb/misc/Makefile +++ b/drivers/usb/misc/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_USB_CYTHERM) += cytherm.o obj-$(CONFIG_USB_EMI26) += emi26.o obj-$(CONFIG_USB_EMI62) += emi62.o obj-$(CONFIG_USB_EZUSB_FX2) += ezusb.o -obj-$(CONFIG_USB_FTDI_ELAN) += ftdi-elan.o obj-$(CONFIG_APPLE_MFI_FASTCHARGE) += apple-mfi-fastcharge.o obj-$(CONFIG_USB_IDMOUSE) += idmouse.o obj-$(CONFIG_USB_IOWARRIOR) += iowarrior.o diff --git a/drivers/usb/misc/ftdi-elan.c b/drivers/usb/misc/ftdi-elan.c deleted file mode 100644 index 8ce191e3a4c0..000000000000 --- a/drivers/usb/misc/ftdi-elan.c +++ /dev/null @@ -1,2780 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * USB FTDI client driver for Elan Digital Systems's Uxxx adapters - * - * Copyright(C) 2006 Elan Digital Systems Limited - * http://www.elandigitalsystems.com - * - * Author and Maintainer - Tony Olech - Elan Digital Systems - * tony.olech@elandigitalsystems.com - * - * This driver was written by Tony Olech(tony.olech@elandigitalsystems.com) - * based on various USB client drivers in the 2.6.15 linux kernel - * with constant reference to the 3rd Edition of Linux Device Drivers - * published by O'Reilly - * - * The U132 adapter is a USB to CardBus adapter specifically designed - * for PC cards that contain an OHCI host controller. Typical PC cards - * are the Orange Mobile 3G Option GlobeTrotter Fusion card. - * - * The U132 adapter will *NOT *work with PC cards that do not contain - * an OHCI controller. A simple way to test whether a PC card has an - * OHCI controller as an interface is to insert the PC card directly - * into a laptop(or desktop) with a CardBus slot and if "lspci" shows - * a new USB controller and "lsusb -v" shows a new OHCI Host Controller - * then there is a good chance that the U132 adapter will support the - * PC card.(you also need the specific client driver for the PC card) - * - * Please inform the Author and Maintainer about any PC cards that - * contain OHCI Host Controller and work when directly connected to - * an embedded CardBus slot but do not work when they are connected - * via an ELAN U132 adapter. - * - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -MODULE_AUTHOR("Tony Olech"); -MODULE_DESCRIPTION("FTDI ELAN driver"); -MODULE_LICENSE("GPL"); -#define INT_MODULE_PARM(n, v) static int n = v;module_param(n, int, 0444) -static bool distrust_firmware = 1; -module_param(distrust_firmware, bool, 0); -MODULE_PARM_DESC(distrust_firmware, - "true to distrust firmware power/overcurrent setup"); -extern struct platform_driver u132_platform_driver; -/* - * ftdi_module_lock exists to protect access to global variables - * - */ -static struct mutex ftdi_module_lock; -static int ftdi_instances = 0; -static struct list_head ftdi_static_list; -/* - * end of the global variables protected by ftdi_module_lock - */ -#include "usb_u132.h" -#include -#include - -/* FIXME ohci.h is ONLY for internal use by the OHCI driver. - * If you're going to try stuff like this, you need to split - * out shareable stuff (register declarations?) into its own - * file, maybe name - */ - -#include "../host/ohci.h" -/* Define these values to match your devices*/ -#define USB_FTDI_ELAN_VENDOR_ID 0x0403 -#define USB_FTDI_ELAN_PRODUCT_ID 0xd6ea -/* table of devices that work with this driver*/ -static const struct usb_device_id ftdi_elan_table[] = { - {USB_DEVICE(USB_FTDI_ELAN_VENDOR_ID, USB_FTDI_ELAN_PRODUCT_ID)}, - { /* Terminating entry */ } -}; - -MODULE_DEVICE_TABLE(usb, ftdi_elan_table); -/* only the jtag(firmware upgrade device) interface requires - * a device file and corresponding minor number, but the - * interface is created unconditionally - I suppose it could - * be configured or not according to a module parameter. - * But since we(now) require one interface per device, - * and since it unlikely that a normal installation would - * require more than a couple of elan-ftdi devices, 8 seems - * like a reasonable limit to have here, and if someone - * really requires more than 8 devices, then they can frig the - * code and recompile - */ -#define USB_FTDI_ELAN_MINOR_BASE 192 -#define COMMAND_BITS 5 -#define COMMAND_SIZE (1<udev->dev, "FREEING ftdi=%p\n", ftdi); - usb_put_dev(ftdi->udev); - ftdi->disconnected += 1; - mutex_lock(&ftdi_module_lock); - list_del_init(&ftdi->ftdi_list); - ftdi_instances -= 1; - mutex_unlock(&ftdi_module_lock); - kfree(ftdi->bulk_in_buffer); - ftdi->bulk_in_buffer = NULL; - kfree(ftdi); -} - -static void ftdi_elan_put_kref(struct usb_ftdi *ftdi) -{ - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_elan_get_kref(struct usb_ftdi *ftdi) -{ - kref_get(&ftdi->kref); -} - -static void ftdi_elan_init_kref(struct usb_ftdi *ftdi) -{ - kref_init(&ftdi->kref); -} - -static void ftdi_status_requeue_work(struct usb_ftdi *ftdi, unsigned int delta) -{ - if (!schedule_delayed_work(&ftdi->status_work, delta)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_status_queue_work(struct usb_ftdi *ftdi, unsigned int delta) -{ - if (schedule_delayed_work(&ftdi->status_work, delta)) - kref_get(&ftdi->kref); -} - -static void ftdi_status_cancel_work(struct usb_ftdi *ftdi) -{ - if (cancel_delayed_work_sync(&ftdi->status_work)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_command_requeue_work(struct usb_ftdi *ftdi, unsigned int delta) -{ - if (!schedule_delayed_work(&ftdi->command_work, delta)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_command_queue_work(struct usb_ftdi *ftdi, unsigned int delta) -{ - if (schedule_delayed_work(&ftdi->command_work, delta)) - kref_get(&ftdi->kref); -} - -static void ftdi_command_cancel_work(struct usb_ftdi *ftdi) -{ - if (cancel_delayed_work_sync(&ftdi->command_work)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_response_requeue_work(struct usb_ftdi *ftdi, - unsigned int delta) -{ - if (!schedule_delayed_work(&ftdi->respond_work, delta)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -static void ftdi_respond_queue_work(struct usb_ftdi *ftdi, unsigned int delta) -{ - if (schedule_delayed_work(&ftdi->respond_work, delta)) - kref_get(&ftdi->kref); -} - -static void ftdi_response_cancel_work(struct usb_ftdi *ftdi) -{ - if (cancel_delayed_work_sync(&ftdi->respond_work)) - kref_put(&ftdi->kref, ftdi_elan_delete); -} - -void ftdi_elan_gone_away(struct platform_device *pdev) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - ftdi->gone_away += 1; - ftdi_elan_put_kref(ftdi); -} - - -EXPORT_SYMBOL_GPL(ftdi_elan_gone_away); -static void ftdi_release_platform_dev(struct device *dev) -{ - dev->parent = NULL; -} - -static void ftdi_elan_do_callback(struct usb_ftdi *ftdi, - struct u132_target *target, u8 *buffer, int length); -static void ftdi_elan_kick_command_queue(struct usb_ftdi *ftdi); -static void ftdi_elan_kick_respond_queue(struct usb_ftdi *ftdi); -static int ftdi_elan_setupOHCI(struct usb_ftdi *ftdi); -static int ftdi_elan_checkingPCI(struct usb_ftdi *ftdi); -static int ftdi_elan_enumeratePCI(struct usb_ftdi *ftdi); -static int ftdi_elan_synchronize(struct usb_ftdi *ftdi); -static int ftdi_elan_stuck_waiting(struct usb_ftdi *ftdi); -static int ftdi_elan_command_engine(struct usb_ftdi *ftdi); -static int ftdi_elan_respond_engine(struct usb_ftdi *ftdi); -static int ftdi_elan_hcd_init(struct usb_ftdi *ftdi) -{ - if (ftdi->platform_dev.dev.parent) - return -EBUSY; - - ftdi_elan_get_kref(ftdi); - ftdi->platform_data.potpg = 100; - ftdi->platform_data.reset = NULL; - ftdi->platform_dev.id = ftdi->sequence_num; - ftdi->platform_dev.resource = ftdi->resources; - ftdi->platform_dev.num_resources = ARRAY_SIZE(ftdi->resources); - ftdi->platform_dev.dev.platform_data = &ftdi->platform_data; - ftdi->platform_dev.dev.parent = NULL; - ftdi->platform_dev.dev.release = ftdi_release_platform_dev; - ftdi->platform_dev.dev.dma_mask = NULL; - snprintf(ftdi->device_name, sizeof(ftdi->device_name), "u132_hcd"); - ftdi->platform_dev.name = ftdi->device_name; - dev_info(&ftdi->udev->dev, "requesting module '%s'\n", "u132_hcd"); - request_module("u132_hcd"); - dev_info(&ftdi->udev->dev, "registering '%s'\n", - ftdi->platform_dev.name); - - return platform_device_register(&ftdi->platform_dev); -} - -static void ftdi_elan_abandon_completions(struct usb_ftdi *ftdi) -{ - mutex_lock(&ftdi->u132_lock); - while (ftdi->respond_next > ftdi->respond_head) { - struct u132_respond *respond = &ftdi->respond[RESPOND_MASK & - ftdi->respond_head++]; - *respond->result = -ESHUTDOWN; - *respond->value = 0; - complete(&respond->wait_completion); - } - mutex_unlock(&ftdi->u132_lock); -} - -static void ftdi_elan_abandon_targets(struct usb_ftdi *ftdi) -{ - int ed_number = 4; - mutex_lock(&ftdi->u132_lock); - while (ed_number-- > 0) { - struct u132_target *target = &ftdi->target[ed_number]; - if (target->active == 1) { - target->condition_code = TD_DEVNOTRESP; - mutex_unlock(&ftdi->u132_lock); - ftdi_elan_do_callback(ftdi, target, NULL, 0); - mutex_lock(&ftdi->u132_lock); - } - } - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - mutex_unlock(&ftdi->u132_lock); -} - -static void ftdi_elan_flush_targets(struct usb_ftdi *ftdi) -{ - int ed_number = 4; - mutex_lock(&ftdi->u132_lock); - while (ed_number-- > 0) { - struct u132_target *target = &ftdi->target[ed_number]; - target->abandoning = 1; - wait_1:if (target->active == 1) { - int command_size = ftdi->command_next - - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x80 | (ed_number << 5) | 0x4; - command->length = 0x00; - command->address = 0x00; - command->width = 0x00; - command->follows = 0; - command->value = 0; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - mutex_lock(&ftdi->u132_lock); - goto wait_1; - } - } - wait_2:if (target->active == 1) { - int command_size = ftdi->command_next - - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x90 | (ed_number << 5); - command->length = 0x00; - command->address = 0x00; - command->width = 0x00; - command->follows = 0; - command->value = 0; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - mutex_lock(&ftdi->u132_lock); - goto wait_2; - } - } - } - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - mutex_unlock(&ftdi->u132_lock); -} - -static void ftdi_elan_cancel_targets(struct usb_ftdi *ftdi) -{ - int ed_number = 4; - mutex_lock(&ftdi->u132_lock); - while (ed_number-- > 0) { - struct u132_target *target = &ftdi->target[ed_number]; - target->abandoning = 1; - wait:if (target->active == 1) { - int command_size = ftdi->command_next - - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x80 | (ed_number << 5) | 0x4; - command->length = 0x00; - command->address = 0x00; - command->width = 0x00; - command->follows = 0; - command->value = 0; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - mutex_lock(&ftdi->u132_lock); - goto wait; - } - } - } - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - mutex_unlock(&ftdi->u132_lock); -} - -static void ftdi_elan_kick_command_queue(struct usb_ftdi *ftdi) -{ - ftdi_command_queue_work(ftdi, 0); -} - -static void ftdi_elan_command_work(struct work_struct *work) -{ - struct usb_ftdi *ftdi = - container_of(work, struct usb_ftdi, command_work.work); - - if (ftdi->disconnected > 0) { - ftdi_elan_put_kref(ftdi); - return; - } else { - int retval = ftdi_elan_command_engine(ftdi); - if (retval == -ESHUTDOWN) { - ftdi->disconnected += 1; - } else if (retval == -ENODEV) { - ftdi->disconnected += 1; - } else if (retval) - dev_err(&ftdi->udev->dev, "command error %d\n", retval); - ftdi_command_requeue_work(ftdi, msecs_to_jiffies(10)); - return; - } -} - -static void ftdi_elan_kick_respond_queue(struct usb_ftdi *ftdi) -{ - ftdi_respond_queue_work(ftdi, 0); -} - -static void ftdi_elan_respond_work(struct work_struct *work) -{ - struct usb_ftdi *ftdi = - container_of(work, struct usb_ftdi, respond_work.work); - if (ftdi->disconnected > 0) { - ftdi_elan_put_kref(ftdi); - return; - } else { - int retval = ftdi_elan_respond_engine(ftdi); - if (retval == 0) { - } else if (retval == -ESHUTDOWN) { - ftdi->disconnected += 1; - } else if (retval == -ENODEV) { - ftdi->disconnected += 1; - } else if (retval == -EILSEQ) { - ftdi->disconnected += 1; - } else { - ftdi->disconnected += 1; - dev_err(&ftdi->udev->dev, "respond error %d\n", retval); - } - if (ftdi->disconnected > 0) { - ftdi_elan_abandon_completions(ftdi); - ftdi_elan_abandon_targets(ftdi); - } - ftdi_response_requeue_work(ftdi, msecs_to_jiffies(10)); - return; - } -} - - -/* - * the sw_lock is initially held and will be freed - * after the FTDI has been synchronized - * - */ -static void ftdi_elan_status_work(struct work_struct *work) -{ - struct usb_ftdi *ftdi = - container_of(work, struct usb_ftdi, status_work.work); - int work_delay_in_msec = 0; - if (ftdi->disconnected > 0) { - ftdi_elan_put_kref(ftdi); - return; - } else if (ftdi->synchronized == 0) { - down(&ftdi->sw_lock); - if (ftdi_elan_synchronize(ftdi) == 0) { - ftdi->synchronized = 1; - ftdi_command_queue_work(ftdi, 1); - ftdi_respond_queue_work(ftdi, 1); - up(&ftdi->sw_lock); - work_delay_in_msec = 100; - } else { - dev_err(&ftdi->udev->dev, "synchronize failed\n"); - up(&ftdi->sw_lock); - work_delay_in_msec = 10 *1000; - } - } else if (ftdi->stuck_status > 0) { - if (ftdi_elan_stuck_waiting(ftdi) == 0) { - ftdi->stuck_status = 0; - ftdi->synchronized = 0; - } else if ((ftdi->stuck_status++ % 60) == 1) { - dev_err(&ftdi->udev->dev, "WRONG type of card inserted - please remove\n"); - } else - dev_err(&ftdi->udev->dev, "WRONG type of card inserted - checked %d times\n", - ftdi->stuck_status); - work_delay_in_msec = 100; - } else if (ftdi->enumerated == 0) { - if (ftdi_elan_enumeratePCI(ftdi) == 0) { - ftdi->enumerated = 1; - work_delay_in_msec = 250; - } else - work_delay_in_msec = 1000; - } else if (ftdi->initialized == 0) { - if (ftdi_elan_setupOHCI(ftdi) == 0) { - ftdi->initialized = 1; - work_delay_in_msec = 500; - } else { - dev_err(&ftdi->udev->dev, "initialized failed - trying again in 10 seconds\n"); - work_delay_in_msec = 1 *1000; - } - } else if (ftdi->registered == 0) { - work_delay_in_msec = 10; - if (ftdi_elan_hcd_init(ftdi) == 0) { - ftdi->registered = 1; - } else - dev_err(&ftdi->udev->dev, "register failed\n"); - work_delay_in_msec = 250; - } else { - if (ftdi_elan_checkingPCI(ftdi) == 0) { - work_delay_in_msec = 250; - } else if (ftdi->controlreg & 0x00400000) { - if (ftdi->gone_away > 0) { - dev_err(&ftdi->udev->dev, "PCI device eject confirmed platform_dev.dev.parent=%p platform_dev.dev=%p\n", - ftdi->platform_dev.dev.parent, - &ftdi->platform_dev.dev); - platform_device_unregister(&ftdi->platform_dev); - ftdi->platform_dev.dev.parent = NULL; - ftdi->registered = 0; - ftdi->enumerated = 0; - ftdi->card_ejected = 0; - ftdi->initialized = 0; - ftdi->gone_away = 0; - } else - ftdi_elan_flush_targets(ftdi); - work_delay_in_msec = 250; - } else { - dev_err(&ftdi->udev->dev, "PCI device has disappeared\n"); - ftdi_elan_cancel_targets(ftdi); - work_delay_in_msec = 500; - ftdi->enumerated = 0; - ftdi->initialized = 0; - } - } - if (ftdi->disconnected > 0) { - ftdi_elan_put_kref(ftdi); - return; - } else { - ftdi_status_requeue_work(ftdi, - msecs_to_jiffies(work_delay_in_msec)); - return; - } -} - - -/* - * file_operations for the jtag interface - * - * the usage count for the device is incremented on open() - * and decremented on release() - */ -static int ftdi_elan_open(struct inode *inode, struct file *file) -{ - int subminor; - struct usb_interface *interface; - - subminor = iminor(inode); - interface = usb_find_interface(&ftdi_elan_driver, subminor); - - if (!interface) { - pr_err("can't find device for minor %d\n", subminor); - return -ENODEV; - } else { - struct usb_ftdi *ftdi = usb_get_intfdata(interface); - if (!ftdi) { - return -ENODEV; - } else { - if (down_interruptible(&ftdi->sw_lock)) { - return -EINTR; - } else { - ftdi_elan_get_kref(ftdi); - file->private_data = ftdi; - return 0; - } - } - } -} - -static int ftdi_elan_release(struct inode *inode, struct file *file) -{ - struct usb_ftdi *ftdi = file->private_data; - if (ftdi == NULL) - return -ENODEV; - up(&ftdi->sw_lock); /* decrement the count on our device */ - ftdi_elan_put_kref(ftdi); - return 0; -} - - -/* - * - * blocking bulk reads are used to get data from the device - * - */ -static ssize_t ftdi_elan_read(struct file *file, char __user *buffer, - size_t count, loff_t *ppos) -{ - char data[30 *3 + 4]; - char *d = data; - int m = (sizeof(data) - 1) / 3 - 1; - int bytes_read = 0; - int retry_on_empty = 10; - int retry_on_timeout = 5; - struct usb_ftdi *ftdi = file->private_data; - if (ftdi->disconnected > 0) { - return -ENODEV; - } - data[0] = 0; -have:if (ftdi->bulk_in_left > 0) { - if (count-- > 0) { - char *p = ++ftdi->bulk_in_last + ftdi->bulk_in_buffer; - ftdi->bulk_in_left -= 1; - if (bytes_read < m) { - d += sprintf(d, " %02X", 0x000000FF & *p); - } else if (bytes_read > m) { - } else - d += sprintf(d, " .."); - if (copy_to_user(buffer++, p, 1)) { - return -EFAULT; - } else { - bytes_read += 1; - goto have; - } - } else - return bytes_read; - } -more:if (count > 0) { - int packet_bytes = 0; - int retval = usb_bulk_msg(ftdi->udev, - usb_rcvbulkpipe(ftdi->udev, ftdi->bulk_in_endpointAddr), - ftdi->bulk_in_buffer, ftdi->bulk_in_size, - &packet_bytes, 50); - if (packet_bytes > 2) { - ftdi->bulk_in_left = packet_bytes - 2; - ftdi->bulk_in_last = 1; - goto have; - } else if (retval == -ETIMEDOUT) { - if (retry_on_timeout-- > 0) { - goto more; - } else if (bytes_read > 0) { - return bytes_read; - } else - return retval; - } else if (retval == 0) { - if (retry_on_empty-- > 0) { - goto more; - } else - return bytes_read; - } else - return retval; - } else - return bytes_read; -} - -static void ftdi_elan_write_bulk_callback(struct urb *urb) -{ - struct usb_ftdi *ftdi = urb->context; - int status = urb->status; - - if (status && !(status == -ENOENT || status == -ECONNRESET || - status == -ESHUTDOWN)) { - dev_err(&ftdi->udev->dev, - "urb=%p write bulk status received: %d\n", urb, status); - } - usb_free_coherent(urb->dev, urb->transfer_buffer_length, - urb->transfer_buffer, urb->transfer_dma); -} - -static int fill_buffer_with_all_queued_commands(struct usb_ftdi *ftdi, - char *buf, int command_size, int total_size) -{ - int ed_commands = 0; - int b = 0; - int I = command_size; - int i = ftdi->command_head; - while (I-- > 0) { - struct u132_command *command = &ftdi->command[COMMAND_MASK & - i++]; - int F = command->follows; - u8 *f = command->buffer; - if (command->header & 0x80) { - ed_commands |= 1 << (0x3 & (command->header >> 5)); - } - buf[b++] = command->header; - buf[b++] = (command->length >> 0) & 0x00FF; - buf[b++] = (command->length >> 8) & 0x00FF; - buf[b++] = command->address; - buf[b++] = command->width; - while (F-- > 0) { - buf[b++] = *f++; - } - } - return ed_commands; -} - -static int ftdi_elan_total_command_size(struct usb_ftdi *ftdi, int command_size) -{ - int total_size = 0; - int I = command_size; - int i = ftdi->command_head; - while (I-- > 0) { - struct u132_command *command = &ftdi->command[COMMAND_MASK & - i++]; - total_size += 5 + command->follows; - } - return total_size; -} - -static int ftdi_elan_command_engine(struct usb_ftdi *ftdi) -{ - int retval; - char *buf; - int ed_commands; - int total_size; - struct urb *urb; - int command_size = ftdi->command_next - ftdi->command_head; - if (command_size == 0) - return 0; - total_size = ftdi_elan_total_command_size(ftdi, command_size); - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; - buf = usb_alloc_coherent(ftdi->udev, total_size, GFP_KERNEL, - &urb->transfer_dma); - if (!buf) { - dev_err(&ftdi->udev->dev, "could not get a buffer to write %d commands totaling %d bytes to the Uxxx\n", - command_size, total_size); - usb_free_urb(urb); - return -ENOMEM; - } - ed_commands = fill_buffer_with_all_queued_commands(ftdi, buf, - command_size, total_size); - usb_fill_bulk_urb(urb, ftdi->udev, usb_sndbulkpipe(ftdi->udev, - ftdi->bulk_out_endpointAddr), buf, total_size, - ftdi_elan_write_bulk_callback, ftdi); - urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - if (ed_commands) { - char diag[40 *3 + 4]; - char *d = diag; - int m = total_size; - u8 *c = buf; - int s = (sizeof(diag) - 1) / 3; - diag[0] = 0; - while (s-- > 0 && m-- > 0) { - if (s > 0 || m == 0) { - d += sprintf(d, " %02X", *c++); - } else - d += sprintf(d, " .."); - } - } - retval = usb_submit_urb(urb, GFP_KERNEL); - if (retval) { - dev_err(&ftdi->udev->dev, "failed %d to submit urb %p to write %d commands totaling %d bytes to the Uxxx\n", - retval, urb, command_size, total_size); - usb_free_coherent(ftdi->udev, total_size, buf, urb->transfer_dma); - usb_free_urb(urb); - return retval; - } - usb_free_urb(urb); /* release our reference to this urb, - the USB core will eventually free it entirely */ - ftdi->command_head += command_size; - ftdi_elan_kick_respond_queue(ftdi); - return 0; -} - -static void ftdi_elan_do_callback(struct usb_ftdi *ftdi, - struct u132_target *target, u8 *buffer, int length) -{ - struct urb *urb = target->urb; - int halted = target->halted; - int skipped = target->skipped; - int actual = target->actual; - int non_null = target->non_null; - int toggle_bits = target->toggle_bits; - int error_count = target->error_count; - int condition_code = target->condition_code; - int repeat_number = target->repeat_number; - void (*callback) (void *, struct urb *, u8 *, int, int, int, int, int, - int, int, int, int) = target->callback; - target->active -= 1; - target->callback = NULL; - (*callback) (target->endp, urb, buffer, length, toggle_bits, - error_count, condition_code, repeat_number, halted, skipped, - actual, non_null); -} - -static char *have_ed_set_response(struct usb_ftdi *ftdi, - struct u132_target *target, u16 ed_length, int ed_number, int ed_type, - char *b) -{ - int payload = (ed_length >> 0) & 0x07FF; - mutex_lock(&ftdi->u132_lock); - target->actual = 0; - target->non_null = (ed_length >> 15) & 0x0001; - target->repeat_number = (ed_length >> 11) & 0x000F; - if (ed_type == 0x02 || ed_type == 0x03) { - if (payload == 0 || target->abandoning > 0) { - target->abandoning = 0; - mutex_unlock(&ftdi->u132_lock); - ftdi_elan_do_callback(ftdi, target, 4 + ftdi->response, - payload); - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - return ftdi->response; - } else { - ftdi->expected = 4 + payload; - ftdi->ed_found = 1; - mutex_unlock(&ftdi->u132_lock); - return b; - } - } else { - target->abandoning = 0; - mutex_unlock(&ftdi->u132_lock); - ftdi_elan_do_callback(ftdi, target, 4 + ftdi->response, - payload); - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - return ftdi->response; - } -} - -static char *have_ed_get_response(struct usb_ftdi *ftdi, - struct u132_target *target, u16 ed_length, int ed_number, int ed_type, - char *b) -{ - mutex_lock(&ftdi->u132_lock); - target->condition_code = TD_DEVNOTRESP; - target->actual = (ed_length >> 0) & 0x01FF; - target->non_null = (ed_length >> 15) & 0x0001; - target->repeat_number = (ed_length >> 11) & 0x000F; - mutex_unlock(&ftdi->u132_lock); - if (target->active) - ftdi_elan_do_callback(ftdi, target, NULL, 0); - target->abandoning = 0; - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - return ftdi->response; -} - - -/* - * The engine tries to empty the FTDI fifo - * - * all responses found in the fifo data are dispatched thus - * the response buffer can only ever hold a maximum sized - * response from the Uxxx. - * - */ -static int ftdi_elan_respond_engine(struct usb_ftdi *ftdi) -{ - u8 *b = ftdi->response + ftdi->received; - int bytes_read = 0; - int retry_on_empty = 1; - int retry_on_timeout = 3; -read:{ - int packet_bytes = 0; - int retval = usb_bulk_msg(ftdi->udev, - usb_rcvbulkpipe(ftdi->udev, ftdi->bulk_in_endpointAddr), - ftdi->bulk_in_buffer, ftdi->bulk_in_size, - &packet_bytes, 500); - char diag[30 *3 + 4]; - char *d = diag; - int m = packet_bytes; - u8 *c = ftdi->bulk_in_buffer; - int s = (sizeof(diag) - 1) / 3; - diag[0] = 0; - while (s-- > 0 && m-- > 0) { - if (s > 0 || m == 0) { - d += sprintf(d, " %02X", *c++); - } else - d += sprintf(d, " .."); - } - if (packet_bytes > 2) { - ftdi->bulk_in_left = packet_bytes - 2; - ftdi->bulk_in_last = 1; - goto have; - } else if (retval == -ETIMEDOUT) { - if (retry_on_timeout-- > 0) { - dev_err(&ftdi->udev->dev, "TIMED OUT with packet_bytes = %d with total %d bytes%s\n", - packet_bytes, bytes_read, diag); - goto more; - } else if (bytes_read > 0) { - dev_err(&ftdi->udev->dev, "ONLY %d bytes%s\n", - bytes_read, diag); - return -ENOMEM; - } else { - dev_err(&ftdi->udev->dev, "TIMED OUT with packet_bytes = %d with total %d bytes%s\n", - packet_bytes, bytes_read, diag); - return -ENOMEM; - } - } else if (retval == -EILSEQ) { - dev_err(&ftdi->udev->dev, "error = %d with packet_bytes = %d with total %d bytes%s\n", - retval, packet_bytes, bytes_read, diag); - return retval; - } else if (retval) { - dev_err(&ftdi->udev->dev, "error = %d with packet_bytes = %d with total %d bytes%s\n", - retval, packet_bytes, bytes_read, diag); - return retval; - } else { - if (retry_on_empty-- > 0) { - goto more; - } else - return 0; - } - } -more:{ - goto read; - } -have:if (ftdi->bulk_in_left > 0) { - u8 c = ftdi->bulk_in_buffer[++ftdi->bulk_in_last]; - bytes_read += 1; - ftdi->bulk_in_left -= 1; - if (ftdi->received == 0 && c == 0xFF) { - goto have; - } else - *b++ = c; - if (++ftdi->received < ftdi->expected) { - goto have; - } else if (ftdi->ed_found) { - int ed_number = (ftdi->response[0] >> 5) & 0x03; - u16 ed_length = (ftdi->response[2] << 8) | - ftdi->response[1]; - struct u132_target *target = &ftdi->target[ed_number]; - int payload = (ed_length >> 0) & 0x07FF; - char diag[30 *3 + 4]; - char *d = diag; - int m = payload; - u8 *c = 4 + ftdi->response; - int s = (sizeof(diag) - 1) / 3; - diag[0] = 0; - while (s-- > 0 && m-- > 0) { - if (s > 0 || m == 0) { - d += sprintf(d, " %02X", *c++); - } else - d += sprintf(d, " .."); - } - ftdi_elan_do_callback(ftdi, target, 4 + ftdi->response, - payload); - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - b = ftdi->response; - goto have; - } else if (ftdi->expected == 8) { - u8 buscmd; - int respond_head = ftdi->respond_head++; - struct u132_respond *respond = &ftdi->respond[ - RESPOND_MASK & respond_head]; - u32 data = ftdi->response[7]; - data <<= 8; - data |= ftdi->response[6]; - data <<= 8; - data |= ftdi->response[5]; - data <<= 8; - data |= ftdi->response[4]; - *respond->value = data; - *respond->result = 0; - complete(&respond->wait_completion); - ftdi->received = 0; - ftdi->expected = 4; - ftdi->ed_found = 0; - b = ftdi->response; - buscmd = (ftdi->response[0] >> 0) & 0x0F; - if (buscmd == 0x00) { - } else if (buscmd == 0x02) { - } else if (buscmd == 0x06) { - } else if (buscmd == 0x0A) { - } else - dev_err(&ftdi->udev->dev, "Uxxx unknown(%0X) value = %08X\n", - buscmd, data); - goto have; - } else { - if ((ftdi->response[0] & 0x80) == 0x00) { - ftdi->expected = 8; - goto have; - } else { - int ed_number = (ftdi->response[0] >> 5) & 0x03; - int ed_type = (ftdi->response[0] >> 0) & 0x03; - u16 ed_length = (ftdi->response[2] << 8) | - ftdi->response[1]; - struct u132_target *target = &ftdi->target[ - ed_number]; - target->halted = (ftdi->response[0] >> 3) & - 0x01; - target->skipped = (ftdi->response[0] >> 2) & - 0x01; - target->toggle_bits = (ftdi->response[3] >> 6) - & 0x03; - target->error_count = (ftdi->response[3] >> 4) - & 0x03; - target->condition_code = (ftdi->response[ - 3] >> 0) & 0x0F; - if ((ftdi->response[0] & 0x10) == 0x00) { - b = have_ed_set_response(ftdi, target, - ed_length, ed_number, ed_type, - b); - goto have; - } else { - b = have_ed_get_response(ftdi, target, - ed_length, ed_number, ed_type, - b); - goto have; - } - } - } - } else - goto more; -} - - -/* - * create a urb, and a buffer for it, and copy the data to the urb - * - */ -static ssize_t ftdi_elan_write(struct file *file, - const char __user *user_buffer, size_t count, - loff_t *ppos) -{ - int retval = 0; - struct urb *urb; - char *buf; - struct usb_ftdi *ftdi = file->private_data; - - if (ftdi->disconnected > 0) { - return -ENODEV; - } - if (count == 0) { - goto exit; - } - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) { - retval = -ENOMEM; - goto error_1; - } - buf = usb_alloc_coherent(ftdi->udev, count, GFP_KERNEL, - &urb->transfer_dma); - if (!buf) { - retval = -ENOMEM; - goto error_2; - } - if (copy_from_user(buf, user_buffer, count)) { - retval = -EFAULT; - goto error_3; - } - usb_fill_bulk_urb(urb, ftdi->udev, usb_sndbulkpipe(ftdi->udev, - ftdi->bulk_out_endpointAddr), buf, count, - ftdi_elan_write_bulk_callback, ftdi); - urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - retval = usb_submit_urb(urb, GFP_KERNEL); - if (retval) { - dev_err(&ftdi->udev->dev, - "failed submitting write urb, error %d\n", retval); - goto error_3; - } - usb_free_urb(urb); - -exit: - return count; -error_3: - usb_free_coherent(ftdi->udev, count, buf, urb->transfer_dma); -error_2: - usb_free_urb(urb); -error_1: - return retval; -} - -static const struct file_operations ftdi_elan_fops = { - .owner = THIS_MODULE, - .llseek = no_llseek, - .read = ftdi_elan_read, - .write = ftdi_elan_write, - .open = ftdi_elan_open, - .release = ftdi_elan_release, -}; - -/* - * usb class driver info in order to get a minor number from the usb core, - * and to have the device registered with the driver core - */ -static struct usb_class_driver ftdi_elan_jtag_class = { - .name = "ftdi-%d-jtag", - .fops = &ftdi_elan_fops, - .minor_base = USB_FTDI_ELAN_MINOR_BASE, -}; - -/* - * the following definitions are for the - * ELAN FPGA state machgine processor that - * lies on the other side of the FTDI chip - */ -#define cPCIu132rd 0x0 -#define cPCIu132wr 0x1 -#define cPCIiord 0x2 -#define cPCIiowr 0x3 -#define cPCImemrd 0x6 -#define cPCImemwr 0x7 -#define cPCIcfgrd 0xA -#define cPCIcfgwr 0xB -#define cPCInull 0xF -#define cU132cmd_status 0x0 -#define cU132flash 0x1 -#define cPIDsetup 0x0 -#define cPIDout 0x1 -#define cPIDin 0x2 -#define cPIDinonce 0x3 -#define cCCnoerror 0x0 -#define cCCcrc 0x1 -#define cCCbitstuff 0x2 -#define cCCtoggle 0x3 -#define cCCstall 0x4 -#define cCCnoresp 0x5 -#define cCCbadpid1 0x6 -#define cCCbadpid2 0x7 -#define cCCdataoverrun 0x8 -#define cCCdataunderrun 0x9 -#define cCCbuffoverrun 0xC -#define cCCbuffunderrun 0xD -#define cCCnotaccessed 0xF -static int ftdi_elan_write_reg(struct usb_ftdi *ftdi, u32 data) -{ -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x00 | cPCIu132wr; - command->length = 0x04; - command->address = 0x00; - command->width = 0x00; - command->follows = 4; - command->value = data; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -static int ftdi_elan_write_config(struct usb_ftdi *ftdi, int config_offset, - u8 width, u32 data) -{ - u8 addressofs = config_offset / 4; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x00 | (cPCIcfgwr & 0x0F); - command->length = 0x04; - command->address = addressofs; - command->width = 0x00 | (width & 0x0F); - command->follows = 4; - command->value = data; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -static int ftdi_elan_write_pcimem(struct usb_ftdi *ftdi, int mem_offset, - u8 width, u32 data) -{ - u8 addressofs = mem_offset / 4; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x00 | (cPCImemwr & 0x0F); - command->length = 0x04; - command->address = addressofs; - command->width = 0x00 | (width & 0x0F); - command->follows = 4; - command->value = data; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_write_pcimem(struct platform_device *pdev, int mem_offset, - u8 width, u32 data) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_write_pcimem(ftdi, mem_offset, width, data); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_write_pcimem); -static int ftdi_elan_read_reg(struct usb_ftdi *ftdi, u32 *data) -{ -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - int respond_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - respond_size = ftdi->respond_next - ftdi->respond_head; - if (command_size < COMMAND_SIZE && respond_size < RESPOND_SIZE) - { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - struct u132_respond *respond = &ftdi->respond[ - RESPOND_MASK & ftdi->respond_next]; - int result = -ENODEV; - respond->result = &result; - respond->header = command->header = 0x00 | cPCIu132rd; - command->length = 0x04; - respond->address = command->address = cU132cmd_status; - command->width = 0x00; - command->follows = 0; - command->value = 0; - command->buffer = NULL; - respond->value = data; - init_completion(&respond->wait_completion); - ftdi->command_next += 1; - ftdi->respond_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - wait_for_completion(&respond->wait_completion); - return result; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -static int ftdi_elan_read_config(struct usb_ftdi *ftdi, int config_offset, - u8 width, u32 *data) -{ - u8 addressofs = config_offset / 4; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - int respond_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - respond_size = ftdi->respond_next - ftdi->respond_head; - if (command_size < COMMAND_SIZE && respond_size < RESPOND_SIZE) - { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - struct u132_respond *respond = &ftdi->respond[ - RESPOND_MASK & ftdi->respond_next]; - int result = -ENODEV; - respond->result = &result; - respond->header = command->header = 0x00 | (cPCIcfgrd & - 0x0F); - command->length = 0x04; - respond->address = command->address = addressofs; - command->width = 0x00 | (width & 0x0F); - command->follows = 0; - command->value = 0; - command->buffer = NULL; - respond->value = data; - init_completion(&respond->wait_completion); - ftdi->command_next += 1; - ftdi->respond_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - wait_for_completion(&respond->wait_completion); - return result; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -static int ftdi_elan_read_pcimem(struct usb_ftdi *ftdi, int mem_offset, - u8 width, u32 *data) -{ - u8 addressofs = mem_offset / 4; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else { - int command_size; - int respond_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - respond_size = ftdi->respond_next - ftdi->respond_head; - if (command_size < COMMAND_SIZE && respond_size < RESPOND_SIZE) - { - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - struct u132_respond *respond = &ftdi->respond[ - RESPOND_MASK & ftdi->respond_next]; - int result = -ENODEV; - respond->result = &result; - respond->header = command->header = 0x00 | (cPCImemrd & - 0x0F); - command->length = 0x04; - respond->address = command->address = addressofs; - command->width = 0x00 | (width & 0x0F); - command->follows = 0; - command->value = 0; - command->buffer = NULL; - respond->value = data; - init_completion(&respond->wait_completion); - ftdi->command_next += 1; - ftdi->respond_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - wait_for_completion(&respond->wait_completion); - return result; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_read_pcimem(struct platform_device *pdev, int mem_offset, - u8 width, u32 *data) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - if (ftdi->initialized == 0) { - return -ENODEV; - } else - return ftdi_elan_read_pcimem(ftdi, mem_offset, width, data); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_read_pcimem); -static int ftdi_elan_edset_setup(struct usb_ftdi *ftdi, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - u8 ed = ed_number - 1; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_target *target = &ftdi->target[ed]; - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x80 | (ed << 5); - command->length = 0x8007; - command->address = (toggle_bits << 6) | (ep_number << 2) - | (address << 0); - command->width = usb_maxpacket(urb->dev, urb->pipe); - command->follows = 8; - command->value = 0; - command->buffer = urb->setup_packet; - target->callback = callback; - target->endp = endp; - target->urb = urb; - target->active = 1; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_edset_setup(struct platform_device *pdev, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_setup(ftdi, ed_number, endp, urb, address, - ep_number, toggle_bits, callback); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_setup); -static int ftdi_elan_edset_input(struct usb_ftdi *ftdi, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - u8 ed = ed_number - 1; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_target *target = &ftdi->target[ed]; - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - u32 remaining_length = urb->transfer_buffer_length - - urb->actual_length; - command->header = 0x82 | (ed << 5); - if (remaining_length == 0) { - command->length = 0x0000; - } else if (remaining_length > 1024) { - command->length = 0x8000 | 1023; - } else - command->length = 0x8000 | (remaining_length - - 1); - command->address = (toggle_bits << 6) | (ep_number << 2) - | (address << 0); - command->width = usb_maxpacket(urb->dev, urb->pipe); - command->follows = 0; - command->value = 0; - command->buffer = NULL; - target->callback = callback; - target->endp = endp; - target->urb = urb; - target->active = 1; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_edset_input(struct platform_device *pdev, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_input(ftdi, ed_number, endp, urb, address, - ep_number, toggle_bits, callback); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_input); -static int ftdi_elan_edset_empty(struct usb_ftdi *ftdi, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - u8 ed = ed_number - 1; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_target *target = &ftdi->target[ed]; - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x81 | (ed << 5); - command->length = 0x0000; - command->address = (toggle_bits << 6) | (ep_number << 2) - | (address << 0); - command->width = usb_maxpacket(urb->dev, urb->pipe); - command->follows = 0; - command->value = 0; - command->buffer = NULL; - target->callback = callback; - target->endp = endp; - target->urb = urb; - target->active = 1; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_edset_empty(struct platform_device *pdev, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_empty(ftdi, ed_number, endp, urb, address, - ep_number, toggle_bits, callback); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_empty); -static int ftdi_elan_edset_output(struct usb_ftdi *ftdi, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - u8 ed = ed_number - 1; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - u8 *b; - u16 urb_size; - int i = 0; - char data[30 *3 + 4]; - char *d = data; - int m = (sizeof(data) - 1) / 3 - 1; - struct u132_target *target = &ftdi->target[ed]; - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x81 | (ed << 5); - command->address = (toggle_bits << 6) | (ep_number << 2) - | (address << 0); - command->width = usb_maxpacket(urb->dev, urb->pipe); - command->follows = min_t(u32, 1024, - urb->transfer_buffer_length - - urb->actual_length); - command->value = 0; - command->buffer = urb->transfer_buffer + - urb->actual_length; - command->length = 0x8000 | (command->follows - 1); - b = command->buffer; - urb_size = command->follows; - data[0] = 0; - while (urb_size-- > 0) { - if (i > m) { - } else if (i++ < m) { - int w = sprintf(d, " %02X", *b++); - d += w; - } else - d += sprintf(d, " .."); - } - target->callback = callback; - target->endp = endp; - target->urb = urb; - target->active = 1; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_edset_output(struct platform_device *pdev, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_output(ftdi, ed_number, endp, urb, address, - ep_number, toggle_bits, callback); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_output); -static int ftdi_elan_edset_single(struct usb_ftdi *ftdi, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - u8 ed = ed_number - 1; -wait:if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - int command_size; - mutex_lock(&ftdi->u132_lock); - command_size = ftdi->command_next - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - u32 remaining_length = urb->transfer_buffer_length - - urb->actual_length; - struct u132_target *target = &ftdi->target[ed]; - struct u132_command *command = &ftdi->command[ - COMMAND_MASK & ftdi->command_next]; - command->header = 0x83 | (ed << 5); - if (remaining_length == 0) { - command->length = 0x0000; - } else if (remaining_length > 1024) { - command->length = 0x8000 | 1023; - } else - command->length = 0x8000 | (remaining_length - - 1); - command->address = (toggle_bits << 6) | (ep_number << 2) - | (address << 0); - command->width = usb_maxpacket(urb->dev, urb->pipe); - command->follows = 0; - command->value = 0; - command->buffer = NULL; - target->callback = callback; - target->endp = endp; - target->urb = urb; - target->active = 1; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - goto wait; - } - } -} - -int usb_ftdi_elan_edset_single(struct platform_device *pdev, u8 ed_number, - void *endp, struct urb *urb, u8 address, u8 ep_number, u8 toggle_bits, - void (*callback) (void *endp, struct urb *urb, u8 *buf, int len, - int toggle_bits, int error_count, int condition_code, int repeat_number, - int halted, int skipped, int actual, int non_null)) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_single(ftdi, ed_number, endp, urb, address, - ep_number, toggle_bits, callback); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_single); -static int ftdi_elan_edset_flush(struct usb_ftdi *ftdi, u8 ed_number, - void *endp) -{ - u8 ed = ed_number - 1; - if (ftdi->disconnected > 0) { - return -ENODEV; - } else if (ftdi->initialized == 0) { - return -ENODEV; - } else { - struct u132_target *target = &ftdi->target[ed]; - mutex_lock(&ftdi->u132_lock); - if (target->abandoning > 0) { - mutex_unlock(&ftdi->u132_lock); - return 0; - } else { - target->abandoning = 1; - wait_1:if (target->active == 1) { - int command_size = ftdi->command_next - - ftdi->command_head; - if (command_size < COMMAND_SIZE) { - struct u132_command *command = - &ftdi->command[COMMAND_MASK & - ftdi->command_next]; - command->header = 0x80 | (ed << 5) | - 0x4; - command->length = 0x00; - command->address = 0x00; - command->width = 0x00; - command->follows = 0; - command->value = 0; - command->buffer = &command->value; - ftdi->command_next += 1; - ftdi_elan_kick_command_queue(ftdi); - } else { - mutex_unlock(&ftdi->u132_lock); - msleep(100); - mutex_lock(&ftdi->u132_lock); - goto wait_1; - } - } - mutex_unlock(&ftdi->u132_lock); - return 0; - } - } -} - -int usb_ftdi_elan_edset_flush(struct platform_device *pdev, u8 ed_number, - void *endp) -{ - struct usb_ftdi *ftdi = platform_device_to_usb_ftdi(pdev); - return ftdi_elan_edset_flush(ftdi, ed_number, endp); -} - - -EXPORT_SYMBOL_GPL(usb_ftdi_elan_edset_flush); -static int ftdi_elan_flush_input_fifo(struct usb_ftdi *ftdi) -{ - int retry_on_empty = 10; - int retry_on_timeout = 5; - int retry_on_status = 20; -more:{ - int packet_bytes = 0; - int retval = usb_bulk_msg(ftdi->udev, - usb_rcvbulkpipe(ftdi->udev, ftdi->bulk_in_endpointAddr), - ftdi->bulk_in_buffer, ftdi->bulk_in_size, - &packet_bytes, 100); - if (packet_bytes > 2) { - char diag[30 *3 + 4]; - char *d = diag; - int m = (sizeof(diag) - 1) / 3 - 1; - char *b = ftdi->bulk_in_buffer; - int bytes_read = 0; - diag[0] = 0; - while (packet_bytes-- > 0) { - char c = *b++; - if (bytes_read < m) { - d += sprintf(d, " %02X", - 0x000000FF & c); - } else if (bytes_read > m) { - } else - d += sprintf(d, " .."); - bytes_read += 1; - continue; - } - goto more; - } else if (packet_bytes > 1) { - char s1 = ftdi->bulk_in_buffer[0]; - char s2 = ftdi->bulk_in_buffer[1]; - if (s1 == 0x31 && s2 == 0x60) { - return 0; - } else if (retry_on_status-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "STATUS ERROR retry limit reached\n"); - return -EFAULT; - } - } else if (packet_bytes > 0) { - char b1 = ftdi->bulk_in_buffer[0]; - dev_err(&ftdi->udev->dev, "only one byte flushed from FTDI = %02X\n", - b1); - if (retry_on_status-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "STATUS ERROR retry limit reached\n"); - return -EFAULT; - } - } else if (retval == -ETIMEDOUT) { - if (retry_on_timeout-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "TIMED OUT retry limit reached\n"); - return -ENOMEM; - } - } else if (retval == 0) { - if (retry_on_empty-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "empty packet retry limit reached\n"); - return -ENOMEM; - } - } else { - dev_err(&ftdi->udev->dev, "error = %d\n", retval); - return retval; - } - } - return -1; -} - - -/* - * send the long flush sequence - * - */ -static int ftdi_elan_synchronize_flush(struct usb_ftdi *ftdi) -{ - int retval; - struct urb *urb; - char *buf; - int I = 257; - int i = 0; - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; - buf = usb_alloc_coherent(ftdi->udev, I, GFP_KERNEL, &urb->transfer_dma); - if (!buf) { - dev_err(&ftdi->udev->dev, "could not get a buffer for flush sequence\n"); - usb_free_urb(urb); - return -ENOMEM; - } - while (I-- > 0) - buf[i++] = 0x55; - usb_fill_bulk_urb(urb, ftdi->udev, usb_sndbulkpipe(ftdi->udev, - ftdi->bulk_out_endpointAddr), buf, i, - ftdi_elan_write_bulk_callback, ftdi); - urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - retval = usb_submit_urb(urb, GFP_KERNEL); - if (retval) { - dev_err(&ftdi->udev->dev, "failed to submit urb containing the flush sequence\n"); - usb_free_coherent(ftdi->udev, i, buf, urb->transfer_dma); - usb_free_urb(urb); - return -ENOMEM; - } - usb_free_urb(urb); - return 0; -} - - -/* - * send the reset sequence - * - */ -static int ftdi_elan_synchronize_reset(struct usb_ftdi *ftdi) -{ - int retval; - struct urb *urb; - char *buf; - int I = 4; - int i = 0; - urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; - buf = usb_alloc_coherent(ftdi->udev, I, GFP_KERNEL, &urb->transfer_dma); - if (!buf) { - dev_err(&ftdi->udev->dev, "could not get a buffer for the reset sequence\n"); - usb_free_urb(urb); - return -ENOMEM; - } - buf[i++] = 0x55; - buf[i++] = 0xAA; - buf[i++] = 0x5A; - buf[i++] = 0xA5; - usb_fill_bulk_urb(urb, ftdi->udev, usb_sndbulkpipe(ftdi->udev, - ftdi->bulk_out_endpointAddr), buf, i, - ftdi_elan_write_bulk_callback, ftdi); - urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; - retval = usb_submit_urb(urb, GFP_KERNEL); - if (retval) { - dev_err(&ftdi->udev->dev, "failed to submit urb containing the reset sequence\n"); - usb_free_coherent(ftdi->udev, i, buf, urb->transfer_dma); - usb_free_urb(urb); - return -ENOMEM; - } - usb_free_urb(urb); - return 0; -} - -static int ftdi_elan_synchronize(struct usb_ftdi *ftdi) -{ - int retval; - int long_stop = 10; - int retry_on_timeout = 5; - int retry_on_empty = 10; - retval = ftdi_elan_flush_input_fifo(ftdi); - if (retval) - return retval; - ftdi->bulk_in_left = 0; - ftdi->bulk_in_last = -1; - while (long_stop-- > 0) { - int read_stop; - int read_stuck; - retval = ftdi_elan_synchronize_flush(ftdi); - if (retval) - return retval; - retval = ftdi_elan_flush_input_fifo(ftdi); - if (retval) - return retval; - reset:retval = ftdi_elan_synchronize_reset(ftdi); - if (retval) - return retval; - read_stop = 100; - read_stuck = 10; - read:{ - int packet_bytes = 0; - retval = usb_bulk_msg(ftdi->udev, - usb_rcvbulkpipe(ftdi->udev, - ftdi->bulk_in_endpointAddr), - ftdi->bulk_in_buffer, ftdi->bulk_in_size, - &packet_bytes, 500); - if (packet_bytes > 2) { - char diag[30 *3 + 4]; - char *d = diag; - int m = (sizeof(diag) - 1) / 3 - 1; - char *b = ftdi->bulk_in_buffer; - int bytes_read = 0; - unsigned char c = 0; - diag[0] = 0; - while (packet_bytes-- > 0) { - c = *b++; - if (bytes_read < m) { - d += sprintf(d, " %02X", c); - } else if (bytes_read > m) { - } else - d += sprintf(d, " .."); - bytes_read += 1; - continue; - } - if (c == 0x7E) { - return 0; - } else { - if (c == 0x55) { - goto read; - } else if (read_stop-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "retry limit reached\n"); - continue; - } - } - } else if (packet_bytes > 1) { - unsigned char s1 = ftdi->bulk_in_buffer[0]; - unsigned char s2 = ftdi->bulk_in_buffer[1]; - if (s1 == 0x31 && s2 == 0x00) { - if (read_stuck-- > 0) { - goto read; - } else - goto reset; - } else { - if (read_stop-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "retry limit reached\n"); - continue; - } - } - } else if (packet_bytes > 0) { - if (read_stop-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "retry limit reached\n"); - continue; - } - } else if (retval == -ETIMEDOUT) { - if (retry_on_timeout-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "TIMED OUT retry limit reached\n"); - continue; - } - } else if (retval == 0) { - if (retry_on_empty-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "empty packet retry limit reached\n"); - continue; - } - } else { - dev_err(&ftdi->udev->dev, "error = %d\n", - retval); - if (read_stop-- > 0) { - goto read; - } else { - dev_err(&ftdi->udev->dev, "retry limit reached\n"); - continue; - } - } - } - } - dev_err(&ftdi->udev->dev, "failed to synchronize\n"); - return -EFAULT; -} - -static int ftdi_elan_stuck_waiting(struct usb_ftdi *ftdi) -{ - int retry_on_empty = 10; - int retry_on_timeout = 5; - int retry_on_status = 50; -more:{ - int packet_bytes = 0; - int retval = usb_bulk_msg(ftdi->udev, - usb_rcvbulkpipe(ftdi->udev, ftdi->bulk_in_endpointAddr), - ftdi->bulk_in_buffer, ftdi->bulk_in_size, - &packet_bytes, 1000); - if (packet_bytes > 2) { - char diag[30 *3 + 4]; - char *d = diag; - int m = (sizeof(diag) - 1) / 3 - 1; - char *b = ftdi->bulk_in_buffer; - int bytes_read = 0; - diag[0] = 0; - while (packet_bytes-- > 0) { - char c = *b++; - if (bytes_read < m) { - d += sprintf(d, " %02X", - 0x000000FF & c); - } else if (bytes_read > m) { - } else - d += sprintf(d, " .."); - bytes_read += 1; - } - goto more; - } else if (packet_bytes > 1) { - char s1 = ftdi->bulk_in_buffer[0]; - char s2 = ftdi->bulk_in_buffer[1]; - if (s1 == 0x31 && s2 == 0x60) { - return 0; - } else if (retry_on_status-- > 0) { - msleep(5); - goto more; - } else - return -EFAULT; - } else if (packet_bytes > 0) { - char b1 = ftdi->bulk_in_buffer[0]; - dev_err(&ftdi->udev->dev, "only one byte flushed from FTDI = %02X\n", b1); - if (retry_on_status-- > 0) { - msleep(5); - goto more; - } else { - dev_err(&ftdi->udev->dev, "STATUS ERROR retry limit reached\n"); - return -EFAULT; - } - } else if (retval == -ETIMEDOUT) { - if (retry_on_timeout-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "TIMED OUT retry limit reached\n"); - return -ENOMEM; - } - } else if (retval == 0) { - if (retry_on_empty-- > 0) { - goto more; - } else { - dev_err(&ftdi->udev->dev, "empty packet retry limit reached\n"); - return -ENOMEM; - } - } else { - dev_err(&ftdi->udev->dev, "error = %d\n", retval); - return -ENOMEM; - } - } - return -1; -} - -static int ftdi_elan_checkingPCI(struct usb_ftdi *ftdi) -{ - int UxxxStatus = ftdi_elan_read_reg(ftdi, &ftdi->controlreg); - if (UxxxStatus) - return UxxxStatus; - if (ftdi->controlreg & 0x00400000) { - if (ftdi->card_ejected) { - } else { - ftdi->card_ejected = 1; - dev_err(&ftdi->udev->dev, "CARD EJECTED - controlreg = %08X\n", - ftdi->controlreg); - } - return -ENODEV; - } else { - u8 fn = ftdi->function - 1; - int activePCIfn = fn << 8; - u32 pcidata; - u32 pciVID; - u32 pciPID; - int reg = 0; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - pciVID = pcidata & 0xFFFF; - pciPID = (pcidata >> 16) & 0xFFFF; - if (pciVID == ftdi->platform_data.vendor && pciPID == - ftdi->platform_data.device) { - return 0; - } else { - dev_err(&ftdi->udev->dev, "vendor=%04X pciVID=%04X device=%04X pciPID=%04X\n", - ftdi->platform_data.vendor, pciVID, - ftdi->platform_data.device, pciPID); - return -ENODEV; - } - } -} - - -#define ftdi_read_pcimem(ftdi, member, data) ftdi_elan_read_pcimem(ftdi, \ - offsetof(struct ohci_regs, member), 0, data); -#define ftdi_write_pcimem(ftdi, member, data) ftdi_elan_write_pcimem(ftdi, \ - offsetof(struct ohci_regs, member), 0, data); - -#define OHCI_CONTROL_INIT OHCI_CTRL_CBSR -#define OHCI_INTR_INIT (OHCI_INTR_MIE | OHCI_INTR_UE | OHCI_INTR_RD | \ - OHCI_INTR_WDH) -static int ftdi_elan_check_controller(struct usb_ftdi *ftdi, int quirk) -{ - int devices = 0; - int retval; - u32 hc_control; - int num_ports; - u32 control; - u32 rh_a = -1; - u32 status; - u32 fminterval; - u32 hc_fminterval; - u32 periodicstart; - u32 cmdstatus; - u32 roothub_a; - int mask = OHCI_INTR_INIT; - int sleep_time = 0; - int reset_timeout = 30; /* ... allow extra time */ - int temp; - retval = ftdi_write_pcimem(ftdi, intrdisable, OHCI_INTR_MIE); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, roothub.a, &rh_a); - if (retval) - return retval; - num_ports = rh_a & RH_A_NDP; - retval = ftdi_read_pcimem(ftdi, fminterval, &hc_fminterval); - if (retval) - return retval; - hc_fminterval &= 0x3fff; - if (hc_fminterval != FI) { - } - hc_fminterval |= FSMP(hc_fminterval) << 16; - retval = ftdi_read_pcimem(ftdi, control, &hc_control); - if (retval) - return retval; - switch (hc_control & OHCI_CTRL_HCFS) { - case OHCI_USB_OPER: - sleep_time = 0; - break; - case OHCI_USB_SUSPEND: - case OHCI_USB_RESUME: - hc_control &= OHCI_CTRL_RWC; - hc_control |= OHCI_USB_RESUME; - sleep_time = 10; - break; - default: - hc_control &= OHCI_CTRL_RWC; - hc_control |= OHCI_USB_RESET; - sleep_time = 50; - break; - } - retval = ftdi_write_pcimem(ftdi, control, hc_control); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; - msleep(sleep_time); - retval = ftdi_read_pcimem(ftdi, roothub.a, &roothub_a); - if (retval) - return retval; - if (!(roothub_a & RH_A_NPS)) { /* power down each port */ - for (temp = 0; temp < num_ports; temp++) { - retval = ftdi_write_pcimem(ftdi, - roothub.portstatus[temp], RH_PS_LSDA); - if (retval) - return retval; - } - } - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; -retry:retval = ftdi_read_pcimem(ftdi, cmdstatus, &status); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, cmdstatus, OHCI_HCR); - if (retval) - return retval; -extra:{ - retval = ftdi_read_pcimem(ftdi, cmdstatus, &status); - if (retval) - return retval; - if (0 != (status & OHCI_HCR)) { - if (--reset_timeout == 0) { - dev_err(&ftdi->udev->dev, "USB HC reset timed out!\n"); - return -ENODEV; - } else { - msleep(5); - goto extra; - } - } - } - if (quirk & OHCI_QUIRK_INITRESET) { - retval = ftdi_write_pcimem(ftdi, control, hc_control); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; - } - retval = ftdi_write_pcimem(ftdi, ed_controlhead, 0x00000000); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, ed_bulkhead, 0x11000000); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, hcca, 0x00000000); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, fminterval, &fminterval); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, fminterval, - ((fminterval & FIT) ^ FIT) | hc_fminterval); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, periodicstart, - ((9 *hc_fminterval) / 10) & 0x3fff); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, fminterval, &fminterval); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, periodicstart, &periodicstart); - if (retval) - return retval; - if (0 == (fminterval & 0x3fff0000) || 0 == periodicstart) { - if (!(quirk & OHCI_QUIRK_INITRESET)) { - quirk |= OHCI_QUIRK_INITRESET; - goto retry; - } else - dev_err(&ftdi->udev->dev, "init err(%08x %04x)\n", - fminterval, periodicstart); - } /* start controller operations */ - hc_control &= OHCI_CTRL_RWC; - hc_control |= OHCI_CONTROL_INIT | OHCI_CTRL_BLE | OHCI_USB_OPER; - retval = ftdi_write_pcimem(ftdi, control, hc_control); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, cmdstatus, OHCI_BLF); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, cmdstatus, &cmdstatus); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, roothub.status, RH_HS_DRWE); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, intrstatus, mask); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, intrdisable, - OHCI_INTR_MIE | OHCI_INTR_OC | OHCI_INTR_RHSC | OHCI_INTR_FNO | - OHCI_INTR_UE | OHCI_INTR_RD | OHCI_INTR_SF | OHCI_INTR_WDH | - OHCI_INTR_SO); - if (retval) - return retval; /* handle root hub init quirks ... */ - retval = ftdi_read_pcimem(ftdi, roothub.a, &roothub_a); - if (retval) - return retval; - roothub_a &= ~(RH_A_PSM | RH_A_OCPM); - if (quirk & OHCI_QUIRK_SUPERIO) { - roothub_a |= RH_A_NOCP; - roothub_a &= ~(RH_A_POTPGT | RH_A_NPS); - retval = ftdi_write_pcimem(ftdi, roothub.a, roothub_a); - if (retval) - return retval; - } else if ((quirk & OHCI_QUIRK_AMD756) || distrust_firmware) { - roothub_a |= RH_A_NPS; - retval = ftdi_write_pcimem(ftdi, roothub.a, roothub_a); - if (retval) - return retval; - } - retval = ftdi_write_pcimem(ftdi, roothub.status, RH_HS_LPSC); - if (retval) - return retval; - retval = ftdi_write_pcimem(ftdi, roothub.b, - (roothub_a & RH_A_NPS) ? 0 : RH_B_PPCM); - if (retval) - return retval; - retval = ftdi_read_pcimem(ftdi, control, &control); - if (retval) - return retval; - mdelay((roothub_a >> 23) & 0x1fe); - for (temp = 0; temp < num_ports; temp++) { - u32 portstatus; - retval = ftdi_read_pcimem(ftdi, roothub.portstatus[temp], - &portstatus); - if (retval) - return retval; - if (1 & portstatus) - devices += 1; - } - return devices; -} - -static int ftdi_elan_setup_controller(struct usb_ftdi *ftdi, int fn) -{ - u32 latence_timer; - int UxxxStatus; - u32 pcidata; - int reg = 0; - int activePCIfn = fn << 8; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000025FL | 0x2800); - if (UxxxStatus) - return UxxxStatus; - reg = 16; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0, - 0xFFFFFFFF); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0, - 0xF0000000); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - reg = 12; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &latence_timer); - if (UxxxStatus) - return UxxxStatus; - latence_timer &= 0xFFFF00FF; - latence_timer |= 0x00001600; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0x00, - latence_timer); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - reg = 4; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0x00, - 0x06); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - for (reg = 0; reg <= 0x54; reg += 4) { - UxxxStatus = ftdi_elan_read_pcimem(ftdi, reg, 0, &pcidata); - if (UxxxStatus) - return UxxxStatus; - } - return 0; -} - -static int ftdi_elan_close_controller(struct usb_ftdi *ftdi, int fn) -{ - u32 latence_timer; - int UxxxStatus; - u32 pcidata; - int reg = 0; - int activePCIfn = fn << 8; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000025FL | 0x2800); - if (UxxxStatus) - return UxxxStatus; - reg = 16; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0, - 0xFFFFFFFF); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0, - 0x00000000); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - reg = 12; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &latence_timer); - if (UxxxStatus) - return UxxxStatus; - latence_timer &= 0xFFFF00FF; - latence_timer |= 0x00001600; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0x00, - latence_timer); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - reg = 4; - UxxxStatus = ftdi_elan_write_config(ftdi, activePCIfn | reg, 0x00, - 0x00); - if (UxxxStatus) - return UxxxStatus; - return ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, &pcidata); -} - -static int ftdi_elan_found_controller(struct usb_ftdi *ftdi, int fn, int quirk) -{ - int result; - int UxxxStatus; - UxxxStatus = ftdi_elan_setup_controller(ftdi, fn); - if (UxxxStatus) - return UxxxStatus; - result = ftdi_elan_check_controller(ftdi, quirk); - UxxxStatus = ftdi_elan_close_controller(ftdi, fn); - if (UxxxStatus) - return UxxxStatus; - return result; -} - -static int ftdi_elan_enumeratePCI(struct usb_ftdi *ftdi) -{ - u32 controlreg; - u8 sensebits; - int UxxxStatus; - UxxxStatus = ftdi_elan_read_reg(ftdi, &controlreg); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x00000000L); - if (UxxxStatus) - return UxxxStatus; - msleep(750); - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x00000200L | 0x100); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x00000200L | 0x500); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_reg(ftdi, &controlreg); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000020CL | 0x000); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000020DL | 0x000); - if (UxxxStatus) - return UxxxStatus; - msleep(250); - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000020FL | 0x000); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_reg(ftdi, &controlreg); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_write_reg(ftdi, 0x0000025FL | 0x800); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_reg(ftdi, &controlreg); - if (UxxxStatus) - return UxxxStatus; - UxxxStatus = ftdi_elan_read_reg(ftdi, &controlreg); - if (UxxxStatus) - return UxxxStatus; - msleep(1000); - sensebits = (controlreg >> 16) & 0x000F; - if (0x0D == sensebits) - return 0; - else - return - ENXIO; -} - -static int ftdi_elan_setupOHCI(struct usb_ftdi *ftdi) -{ - int UxxxStatus; - u32 pcidata; - int reg = 0; - u8 fn; - int activePCIfn = 0; - int max_devices = 0; - int controllers = 0; - int unrecognized = 0; - ftdi->function = 0; - for (fn = 0; (fn < 4); fn++) { - u32 pciVID = 0; - u32 pciPID = 0; - int devices = 0; - activePCIfn = fn << 8; - UxxxStatus = ftdi_elan_read_config(ftdi, activePCIfn | reg, 0, - &pcidata); - if (UxxxStatus) - return UxxxStatus; - pciVID = pcidata & 0xFFFF; - pciPID = (pcidata >> 16) & 0xFFFF; - if ((pciVID == PCI_VENDOR_ID_OPTI) && (pciPID == 0xc861)) { - devices = ftdi_elan_found_controller(ftdi, fn, 0); - controllers += 1; - } else if ((pciVID == PCI_VENDOR_ID_NEC) && (pciPID == 0x0035)) - { - devices = ftdi_elan_found_controller(ftdi, fn, 0); - controllers += 1; - } else if ((pciVID == PCI_VENDOR_ID_AL) && (pciPID == 0x5237)) { - devices = ftdi_elan_found_controller(ftdi, fn, 0); - controllers += 1; - } else if ((pciVID == PCI_VENDOR_ID_ATT) && (pciPID == 0x5802)) - { - devices = ftdi_elan_found_controller(ftdi, fn, 0); - controllers += 1; - } else if (pciVID == PCI_VENDOR_ID_AMD && pciPID == 0x740c) { - devices = ftdi_elan_found_controller(ftdi, fn, - OHCI_QUIRK_AMD756); - controllers += 1; - } else if (pciVID == PCI_VENDOR_ID_COMPAQ && pciPID == 0xa0f8) { - devices = ftdi_elan_found_controller(ftdi, fn, - OHCI_QUIRK_ZFMICRO); - controllers += 1; - } else if (0 == pcidata) { - } else - unrecognized += 1; - if (devices > max_devices) { - max_devices = devices; - ftdi->function = fn + 1; - ftdi->platform_data.vendor = pciVID; - ftdi->platform_data.device = pciPID; - } - } - if (ftdi->function > 0) { - return ftdi_elan_setup_controller(ftdi, ftdi->function - 1); - } else if (controllers > 0) { - return -ENXIO; - } else if (unrecognized > 0) { - return -ENXIO; - } else { - ftdi->enumerated = 0; - return -ENXIO; - } -} - - -/* - * we use only the first bulk-in and bulk-out endpoints - */ -static int ftdi_elan_probe(struct usb_interface *interface, - const struct usb_device_id *id) -{ - struct usb_host_interface *iface_desc; - struct usb_endpoint_descriptor *bulk_in, *bulk_out; - int retval; - struct usb_ftdi *ftdi; - - ftdi = kzalloc(sizeof(struct usb_ftdi), GFP_KERNEL); - if (!ftdi) - return -ENOMEM; - - mutex_lock(&ftdi_module_lock); - list_add_tail(&ftdi->ftdi_list, &ftdi_static_list); - ftdi->sequence_num = ++ftdi_instances; - mutex_unlock(&ftdi_module_lock); - ftdi_elan_init_kref(ftdi); - sema_init(&ftdi->sw_lock, 1); - ftdi->udev = usb_get_dev(interface_to_usbdev(interface)); - ftdi->interface = interface; - mutex_init(&ftdi->u132_lock); - ftdi->expected = 4; - - iface_desc = interface->cur_altsetting; - retval = usb_find_common_endpoints(iface_desc, - &bulk_in, &bulk_out, NULL, NULL); - if (retval) { - dev_err(&ftdi->udev->dev, "Could not find both bulk-in and bulk-out endpoints\n"); - goto error; - } - - ftdi->bulk_in_size = usb_endpoint_maxp(bulk_in); - ftdi->bulk_in_endpointAddr = bulk_in->bEndpointAddress; - ftdi->bulk_in_buffer = kmalloc(ftdi->bulk_in_size, GFP_KERNEL); - if (!ftdi->bulk_in_buffer) { - retval = -ENOMEM; - goto error; - } - - ftdi->bulk_out_endpointAddr = bulk_out->bEndpointAddress; - - dev_info(&ftdi->udev->dev, "interface %d has I=%02X O=%02X\n", - iface_desc->desc.bInterfaceNumber, ftdi->bulk_in_endpointAddr, - ftdi->bulk_out_endpointAddr); - usb_set_intfdata(interface, ftdi); - if (iface_desc->desc.bInterfaceNumber == 0 && - ftdi->bulk_in_endpointAddr == 0x81 && - ftdi->bulk_out_endpointAddr == 0x02) { - retval = usb_register_dev(interface, &ftdi_elan_jtag_class); - if (retval) { - dev_err(&ftdi->udev->dev, "Not able to get a minor for this device\n"); - usb_set_intfdata(interface, NULL); - retval = -ENOMEM; - goto error; - } else { - ftdi->class = &ftdi_elan_jtag_class; - dev_info(&ftdi->udev->dev, "USB FDTI=%p JTAG interface %d now attached to ftdi%d\n", - ftdi, iface_desc->desc.bInterfaceNumber, - interface->minor); - return 0; - } - } else if (iface_desc->desc.bInterfaceNumber == 1 && - ftdi->bulk_in_endpointAddr == 0x83 && - ftdi->bulk_out_endpointAddr == 0x04) { - ftdi->class = NULL; - dev_info(&ftdi->udev->dev, "USB FDTI=%p ELAN interface %d now activated\n", - ftdi, iface_desc->desc.bInterfaceNumber); - INIT_DELAYED_WORK(&ftdi->status_work, ftdi_elan_status_work); - INIT_DELAYED_WORK(&ftdi->command_work, ftdi_elan_command_work); - INIT_DELAYED_WORK(&ftdi->respond_work, ftdi_elan_respond_work); - ftdi_status_queue_work(ftdi, msecs_to_jiffies(3 *1000)); - return 0; - } else { - dev_err(&ftdi->udev->dev, - "Could not find ELAN's U132 device\n"); - retval = -ENODEV; - goto error; - } -error:if (ftdi) { - ftdi_elan_put_kref(ftdi); - } - return retval; -} - -static void ftdi_elan_disconnect(struct usb_interface *interface) -{ - struct usb_ftdi *ftdi = usb_get_intfdata(interface); - ftdi->disconnected += 1; - if (ftdi->class) { - int minor = interface->minor; - struct usb_class_driver *class = ftdi->class; - usb_set_intfdata(interface, NULL); - usb_deregister_dev(interface, class); - dev_info(&ftdi->udev->dev, "USB FTDI U132 jtag interface on minor %d now disconnected\n", - minor); - } else { - ftdi_status_cancel_work(ftdi); - ftdi_command_cancel_work(ftdi); - ftdi_response_cancel_work(ftdi); - ftdi_elan_abandon_completions(ftdi); - ftdi_elan_abandon_targets(ftdi); - if (ftdi->registered) { - platform_device_unregister(&ftdi->platform_dev); - ftdi->synchronized = 0; - ftdi->enumerated = 0; - ftdi->initialized = 0; - ftdi->registered = 0; - } - ftdi->disconnected += 1; - usb_set_intfdata(interface, NULL); - dev_info(&ftdi->udev->dev, "USB FTDI U132 host controller interface now disconnected\n"); - } - ftdi_elan_put_kref(ftdi); -} - -static struct usb_driver ftdi_elan_driver = { - .name = "ftdi-elan", - .probe = ftdi_elan_probe, - .disconnect = ftdi_elan_disconnect, - .id_table = ftdi_elan_table, -}; -static int __init ftdi_elan_init(void) -{ - int result; - pr_info("driver %s\n", ftdi_elan_driver.name); - mutex_init(&ftdi_module_lock); - INIT_LIST_HEAD(&ftdi_static_list); - result = usb_register(&ftdi_elan_driver); - if (result) { - pr_err("usb_register failed. Error number %d\n", result); - } - return result; - -} - -static void __exit ftdi_elan_exit(void) -{ - struct usb_ftdi *ftdi; - struct usb_ftdi *temp; - usb_deregister(&ftdi_elan_driver); - pr_info("ftdi_u132 driver deregistered\n"); - list_for_each_entry_safe(ftdi, temp, &ftdi_static_list, ftdi_list) { - ftdi_status_cancel_work(ftdi); - ftdi_command_cancel_work(ftdi); - ftdi_response_cancel_work(ftdi); - } -} - - -module_init(ftdi_elan_init); -module_exit(ftdi_elan_exit); -- GitLab From ad36aab37ae4f2ca898a809454020c5acc23b47c Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 19 Jan 2023 22:19:45 +0800 Subject: [PATCH 1012/5631] KVM: nVMX: Remove outdated comments in nested_vmx_setup_ctls_msrs() nested_vmx_setup_ctls_msrs() initializes the vmcs_conf.nested, which stores the global VMX MSR configurations when nested is supported, regardless of any particular CPUID settings for one VM. Commit 6defc591846d ("KVM: nVMX: include conditional controls in /dev/kvm KVM_GET_MSRS") added the some feature flags for secondary proc-based controls, so that those features can be available in KVM_GET_MSRS. Yet this commit did not remove the obsolete comments in nested_vmx_setup_ctls_msrs(). Just fix the comments, and no functional change intended. Fixes: 6defc591846d ("KVM: nVMX: include conditional controls in /dev/kvm KVM_GET_MSRS") Signed-off-by: Yu Zhang Link: https://lore.kernel.org/r/20230119141946.585610-1-yu.c.zhang@linux.intel.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/nested.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f63b28f46a71..d778fa304f51 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6866,11 +6866,6 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) msrs->procbased_ctls_low &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); - /* - * secondary cpu-based controls. Do not include those that - * depend on CPUID bits, they are added later by - * vmx_vcpu_after_set_cpuid. - */ msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; -- GitLab From f6cde92083dec5cf424504d7029acdffbe5beed8 Mon Sep 17 00:00:00 2001 From: Yu Zhang Date: Thu, 19 Jan 2023 22:19:46 +0800 Subject: [PATCH 1013/5631] KVM: nVMX: Add helpers to setup VMX control msr configs nested_vmx_setup_ctls_msrs() is used to set up the various VMX MSR controls for nested VMX. But it is a bit lengthy, just add helpers to setup the configuration of VMX MSRs. Suggested-by: Sean Christopherson Signed-off-by: Yu Zhang Link: https://lore.kernel.org/r/20230119141946.585610-2-yu.c.zhang@linux.intel.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/nested.c | 107 ++++++++++++++++++++++++++------------ 1 file changed, 74 insertions(+), 33 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d778fa304f51..dab529cd799c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6753,36 +6753,9 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; } -/* - * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be - * returned for the various VMX controls MSRs when nested VMX is enabled. - * The same values should also be used to verify that vmcs12 control fields are - * valid during nested entry from L1 to L2. - * Each of these control msrs has a low and high 32-bit half: A low bit is on - * if the corresponding bit in the (32-bit) control field *must* be on, and a - * bit in the high half is on if the corresponding bit in the control field - * may be on. See also vmx_control_verify(). - */ -void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) +static void nested_vmx_setup_pinbased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) { - struct nested_vmx_msrs *msrs = &vmcs_conf->nested; - - /* - * Note that as a general rule, the high half of the MSRs (bits in - * the control fields which may be 1) should be initialized by the - * intersection of the underlying hardware's MSR (i.e., features which - * can be supported) and the list of features we want to expose - - * because they are known to be properly supported in our code. - * Also, usually, the low half of the MSRs (bits which must be 1) can - * be set to 0, meaning that L1 may turn off any of these bits. The - * reason is that if one of these bits is necessary, it will appear - * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control - * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_l1_wants_exit() will not pass related exits to L1. - * These rules have exceptions below. - */ - - /* pin-based controls */ msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6795,8 +6768,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; +} - /* exit controls */ +static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6815,8 +6791,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; +} - /* entry controls */ +static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6832,8 +6811,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; +} - /* cpu-based controls */ +static void nested_vmx_setup_cpubased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6865,7 +6847,12 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of CR3 access interception. */ msrs->procbased_ctls_low &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); +} +static void nested_vmx_setup_secondary_ctls(u32 ept_caps, + struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; @@ -6943,8 +6930,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (enable_sgx) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; +} - /* miscellaneous data */ +static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | @@ -6952,7 +6942,10 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; msrs->misc_high = 0; +} +static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) +{ /* * This MSR reports some information about VMX support. We * should return information about the VMX we emulate for the @@ -6967,7 +6960,10 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; +} +static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) +{ /* * These MSRs specify bits which the guest must keep fixed on * while L1 is in VMXON mode (in L1's root mode, or running an L2). @@ -6984,6 +6980,51 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (vmx_umip_emulated()) msrs->cr4_fixed1 |= X86_CR4_UMIP; +} + +/* + * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be + * returned for the various VMX controls MSRs when nested VMX is enabled. + * The same values should also be used to verify that vmcs12 control fields are + * valid during nested entry from L1 to L2. + * Each of these control msrs has a low and high 32-bit half: A low bit is on + * if the corresponding bit in the (32-bit) control field *must* be on, and a + * bit in the high half is on if the corresponding bit in the control field + * may be on. See also vmx_control_verify(). + */ +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) +{ + struct nested_vmx_msrs *msrs = &vmcs_conf->nested; + + /* + * Note that as a general rule, the high half of the MSRs (bits in + * the control fields which may be 1) should be initialized by the + * intersection of the underlying hardware's MSR (i.e., features which + * can be supported) and the list of features we want to expose - + * because they are known to be properly supported in our code. + * Also, usually, the low half of the MSRs (bits which must be 1) can + * be set to 0, meaning that L1 may turn off any of these bits. The + * reason is that if one of these bits is necessary, it will appear + * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control + * fields of vmcs01 and vmcs02, will turn these bits off - and + * nested_vmx_l1_wants_exit() will not pass related exits to L1. + * These rules have exceptions below. + */ + nested_vmx_setup_pinbased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_exit_ctls(vmcs_conf, msrs); + + nested_vmx_setup_entry_ctls(vmcs_conf, msrs); + + nested_vmx_setup_cpubased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_secondary_ctls(ept_caps, vmcs_conf, msrs); + + nested_vmx_setup_misc_data(vmcs_conf, msrs); + + nested_vmx_setup_basic(msrs); + + nested_vmx_setup_cr_fixed(msrs); msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } -- GitLab From b4b55dfd965057232abd317fbbfa31d8a2c16a49 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 5 Mar 2023 16:55:30 +0100 Subject: [PATCH 1014/5631] ring_buffer: Change some static functions to void The results of some static functions are not used. Change the type of these function to void and remove unnecessary returns. No functional change intended. Link: https://lkml.kernel.org/r/20230305155532.5549-2-ubizjak@gmail.com Signed-off-by: Uros Bizjak Reviewed-by: Masami Hiramatsu Reviewed-by: Mukesh Ojha Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c6f47b6cfd5f..b45915dd67b9 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1565,15 +1565,12 @@ static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer, } } -static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, +static void rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, struct buffer_page *bpage) { unsigned long val = (unsigned long)bpage; - if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK)) - return 1; - - return 0; + RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK); } /** @@ -1583,30 +1580,28 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, * As a safety measure we check to make sure the data pages have not * been corrupted. */ -static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) +static void rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *head = rb_list_head(cpu_buffer->pages); struct list_head *tmp; if (RB_WARN_ON(cpu_buffer, rb_list_head(rb_list_head(head->next)->prev) != head)) - return -1; + return; if (RB_WARN_ON(cpu_buffer, rb_list_head(rb_list_head(head->prev)->next) != head)) - return -1; + return; for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) { if (RB_WARN_ON(cpu_buffer, rb_list_head(rb_list_head(tmp->next)->prev) != tmp)) - return -1; + return; if (RB_WARN_ON(cpu_buffer, rb_list_head(rb_list_head(tmp->prev)->next) != tmp)) - return -1; + return; } - - return 0; } static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, @@ -4496,7 +4491,6 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, default: RB_WARN_ON(cpu_buffer, 1); } - return; } static void @@ -4527,7 +4521,6 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, default: RB_WARN_ON(iter->cpu_buffer, 1); } - return; } static struct buffer_page * @@ -4942,7 +4935,6 @@ rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked) { if (likely(locked)) raw_spin_unlock(&cpu_buffer->reader_lock); - return; } /** -- GitLab From bc92b9562abc831a65e505d2e675b51528d22d8b Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 5 Mar 2023 16:55:31 +0100 Subject: [PATCH 1015/5631] ring_buffer: Change some static functions to bool The return values of some functions are of boolean type. Change the type of these function to bool and adjust their return values. Also change type of some internal varibles to bool. No functional change intended. Link: https://lkml.kernel.org/r/20230305155532.5549-3-ubizjak@gmail.com Cc: Masami Hiramatsu Signed-off-by: Uros Bizjak Reviewed-by: Mukesh Ojha Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 47 +++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 24 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b45915dd67b9..93f854433d89 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -163,7 +163,7 @@ enum { #define extended_time(event) \ (event->type_len >= RINGBUF_TYPE_TIME_EXTEND) -static inline int rb_null_event(struct ring_buffer_event *event) +static inline bool rb_null_event(struct ring_buffer_event *event) { return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta; } @@ -363,11 +363,9 @@ static void free_buffer_page(struct buffer_page *bpage) /* * We need to fit the time_stamp delta into 27 bits. */ -static inline int test_time_stamp(u64 delta) +static inline bool test_time_stamp(u64 delta) { - if (delta & TS_DELTA_TEST) - return 1; - return 0; + return !!(delta & TS_DELTA_TEST); } #define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE) @@ -696,7 +694,7 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) return ret == expect; } -static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) +static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) { unsigned long cnt, top, bottom, msb; unsigned long cnt2, top2, bottom2, msb2; @@ -1486,7 +1484,7 @@ rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer) return NULL; } -static int rb_head_page_replace(struct buffer_page *old, +static bool rb_head_page_replace(struct buffer_page *old, struct buffer_page *new) { unsigned long *ptr = (unsigned long *)&old->list.prev->next; @@ -1913,7 +1911,7 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage) return local_read(&bpage->write) & RB_WRITE_MASK; } -static int +static bool rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) { struct list_head *tail_page, *to_remove, *next_page; @@ -2026,12 +2024,13 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) return nr_removed == 0; } -static int +static bool rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *pages = &cpu_buffer->new_pages; - int retries, success; unsigned long flags; + bool success; + int retries; /* Can be called at early boot up, where interrupts must not been enabled */ raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); @@ -2050,7 +2049,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) * spinning. */ retries = 10; - success = 0; + success = false; while (retries--) { struct list_head *head_page, *prev_page, *r; struct list_head *last_page, *first_page; @@ -2079,7 +2078,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) * pointer to point to end of list */ head_page->prev = last_page; - success = 1; + success = true; break; } } @@ -2107,7 +2106,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer) { - int success; + bool success; if (cpu_buffer->nr_pages_to_update > 0) success = rb_insert_pages(cpu_buffer); @@ -2990,7 +2989,7 @@ static u64 rb_time_delta(struct ring_buffer_event *event) } } -static inline int +static inline bool rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) { @@ -3011,7 +3010,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, delta = rb_time_delta(event); if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) - return 0; + return false; /* Make sure the write stamp is read before testing the location */ barrier(); @@ -3024,7 +3023,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, /* Something came in, can't discard */ if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, write_stamp, write_stamp - delta)) - return 0; + return false; /* * It's possible that the event time delta is zero @@ -3057,12 +3056,12 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, if (index == old_index) { /* update counters */ local_sub(event_length, &cpu_buffer->entries_bytes); - return 1; + return true; } } /* could not discard */ - return 0; + return false; } static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer) @@ -3277,7 +3276,7 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * Note: The TRANSITION bit only handles a single transition between context. */ -static __always_inline int +static __always_inline bool trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { unsigned int val = cpu_buffer->current_context; @@ -3294,14 +3293,14 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = RB_CTX_TRANSITION; if (val & (1 << (bit + cpu_buffer->nest))) { do_ring_buffer_record_recursion(); - return 1; + return true; } } val |= (1 << (bit + cpu_buffer->nest)); cpu_buffer->current_context = val; - return 0; + return false; } static __always_inline void @@ -4530,7 +4529,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) unsigned long overwrite; unsigned long flags; int nr_loops = 0; - int ret; + bool ret; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); @@ -5405,8 +5404,8 @@ bool ring_buffer_empty(struct trace_buffer *buffer) struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; bool dolock; + bool ret; int cpu; - int ret; /* yes this is racy, but if you don't like the race, lock the buffer */ for_each_buffer_cpu(buffer, cpu) { @@ -5435,7 +5434,7 @@ bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu) struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; bool dolock; - int ret; + bool ret; if (!cpumask_test_cpu(cpu, buffer->cpumask)) return true; -- GitLab From 8328e36da9cd8cb051394630e910cbb461f7e3ec Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Sun, 5 Mar 2023 16:55:32 +0100 Subject: [PATCH 1016/5631] ring_buffer: Use try_cmpxchg instead of cmpxchg Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old. x86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails. There is no need to re-read the value in the loop. No functional change intended. Link: https://lkml.kernel.org/r/20230305155532.5549-4-ubizjak@gmail.com Cc: Masami Hiramatsu Signed-off-by: Uros Bizjak Acked-by: Mukesh Ojha Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 93f854433d89..2d5c3caff32d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4057,10 +4057,10 @@ void ring_buffer_record_off(struct trace_buffer *buffer) unsigned int rd; unsigned int new_rd; + rd = atomic_read(&buffer->record_disabled); do { - rd = atomic_read(&buffer->record_disabled); new_rd = rd | RB_BUFFER_OFF; - } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); + } while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd)); } EXPORT_SYMBOL_GPL(ring_buffer_record_off); @@ -4080,10 +4080,10 @@ void ring_buffer_record_on(struct trace_buffer *buffer) unsigned int rd; unsigned int new_rd; + rd = atomic_read(&buffer->record_disabled); do { - rd = atomic_read(&buffer->record_disabled); new_rd = rd & ~RB_BUFFER_OFF; - } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd); + } while (!atomic_try_cmpxchg(&buffer->record_disabled, &rd, new_rd)); } EXPORT_SYMBOL_GPL(ring_buffer_record_on); -- GitLab From e11b521a7b69c2621bb2e5920bb96f6d2facdc7e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 24 Jan 2023 09:56:53 -0500 Subject: [PATCH 1017/5631] ftrace: Show a list of all functions that have ever been enabled When debugging a crash that appears to be related to ftrace, but not for sure, it is useful to know if a function was ever enabled by ftrace or not. It could be that a BPF program was attached to it, or possibly a live patch. We are having crashes in the field where this information is not always known. But having ftrace set a flag if a function has ever been attached since boot up helps tremendously in trying to know if a crash had to do with something using ftrace. For analyzing crashes, the use of a kdump image can have access to the flags. When looking at issues where the kernel did not panic, the touched_functions file can simply be used. Link: https://lore.kernel.org/linux-trace-kernel/20230124095653.6fd1640e@gandalf.local.home Cc: Masami Hiramatsu Cc: Catalin Marinas Tested-by: Mark Rutland Tested-by: Chris Li Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 5 ++++- kernel/trace/ftrace.c | 51 +++++++++++++++++++++++++++++++++++++----- 2 files changed, 50 insertions(+), 6 deletions(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 931f3d904529..327046f1278d 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -548,6 +548,7 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops + * TOUCHED - A callback was added since boot up * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -567,9 +568,10 @@ enum { FTRACE_FL_DIRECT_EN = (1UL << 23), FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), + FTRACE_FL_TOUCHED = (1UL << 20), }; -#define FTRACE_REF_MAX_SHIFT 21 +#define FTRACE_REF_MAX_SHIFT 20 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) @@ -628,6 +630,7 @@ enum { FTRACE_ITER_PROBE = (1 << 4), FTRACE_ITER_MOD = (1 << 5), FTRACE_ITER_ENABLED = (1 << 6), + FTRACE_ITER_TOUCHED = (1 << 7), }; void arch_ftrace_update_code(int command); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3b46dba3f69b..db8532a4d5c8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -45,6 +45,9 @@ #include "trace_output.h" #include "trace_stat.h" +/* Flags that do not get reset */ +#define FTRACE_NOCLEAR_FLAGS (FTRACE_FL_DISABLED | FTRACE_FL_TOUCHED) + #define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__" #define FTRACE_WARN_ON(cond) \ @@ -2256,7 +2259,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) flag ^= rec->flags & FTRACE_FL_ENABLED; if (update) { - rec->flags |= FTRACE_FL_ENABLED; + rec->flags |= FTRACE_FL_ENABLED | FTRACE_FL_TOUCHED; if (flag & FTRACE_FL_REGS) { if (rec->flags & FTRACE_FL_REGS) rec->flags |= FTRACE_FL_REGS_EN; @@ -2326,7 +2329,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) if (update) { /* If there's no more users, clear all flags */ if (!ftrace_rec_count(rec)) - rec->flags &= FTRACE_FL_DISABLED; + rec->flags &= FTRACE_NOCLEAR_FLAGS; else /* * Just disable the record, but keep the ops TRAMP @@ -3147,7 +3150,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) struct dyn_ftrace *rec; do_for_each_ftrace_rec(pg, rec) { - if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_FL_DISABLED)) + if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_NOCLEAR_FLAGS)) pr_warn(" %pS flags:%lx\n", (void *)rec->ip, rec->flags); } while_for_each_ftrace_rec(); @@ -3598,7 +3601,10 @@ t_func_next(struct seq_file *m, loff_t *pos) !ftrace_lookup_ip(iter->hash, rec->ip)) || ((iter->flags & FTRACE_ITER_ENABLED) && - !(rec->flags & FTRACE_FL_ENABLED))) { + !(rec->flags & FTRACE_FL_ENABLED)) || + + ((iter->flags & FTRACE_ITER_TOUCHED) && + !(rec->flags & FTRACE_FL_TOUCHED))) { rec = NULL; goto retry; @@ -3857,7 +3863,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } - if (iter->flags & FTRACE_ITER_ENABLED) { + if (iter->flags & (FTRACE_ITER_ENABLED | FTRACE_ITER_TOUCHED)) { struct ftrace_ops *ops; seq_printf(m, " (%ld)%s%s%s%s", @@ -3959,6 +3965,31 @@ ftrace_enabled_open(struct inode *inode, struct file *file) return 0; } +static int +ftrace_touched_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + + /* + * This shows us what functions have ever been enabled + * (traced, direct, patched, etc). Not sure if we want lockdown + * to hide such critical information for an admin. + * Although, perhaps it can show information we don't + * want people to see, but if something had traced + * something, we probably want to know about it. + */ + + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); + if (!iter) + return -ENOMEM; + + iter->pg = ftrace_pages_start; + iter->flags = FTRACE_ITER_TOUCHED; + iter->ops = &global_ops; + + return 0; +} + /** * ftrace_regex_open - initialize function tracer filter files * @ops: The ftrace_ops that hold the hash filters @@ -5872,6 +5903,13 @@ static const struct file_operations ftrace_enabled_fops = { .release = seq_release_private, }; +static const struct file_operations ftrace_touched_fops = { + .open = ftrace_touched_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, +}; + static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, @@ -6336,6 +6374,9 @@ static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer) trace_create_file("enabled_functions", TRACE_MODE_READ, d_tracer, NULL, &ftrace_enabled_fops); + trace_create_file("touched_functions", TRACE_MODE_READ, + d_tracer, NULL, &ftrace_touched_fops); + ftrace_create_filter_files(&global_ops, d_tracer); #ifdef CONFIG_FUNCTION_GRAPH_TRACER -- GitLab From 0f74f8b6675cc36d689abb4d9b3d75ab4049b7d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:07 +0100 Subject: [PATCH 1018/5631] i3c: Make i3c_master_unregister() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function returned zero unconditionally. Switch the return type to void and simplify the callers accordingly. Signed-off-by: Uwe Kleine-König Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20230318233311.265186-2-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 6 +----- drivers/i3c/master/dw-i3c-master.c | 5 +---- drivers/i3c/master/i3c-master-cdns.c | 5 +---- drivers/i3c/master/mipi-i3c-hci/core.c | 4 +++- drivers/i3c/master/svc-i3c-master.c | 5 +---- include/linux/i3c/master.h | 2 +- 6 files changed, 8 insertions(+), 19 deletions(-) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 54e4c34b4a22..04d6d54d2ab8 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -2695,17 +2695,13 @@ EXPORT_SYMBOL_GPL(i3c_master_register); * @master: master used to send frames on the bus * * Basically undo everything done in i3c_master_register(). - * - * Return: 0 in case of success, a negative error code otherwise. */ -int i3c_master_unregister(struct i3c_master_controller *master) +void i3c_master_unregister(struct i3c_master_controller *master) { i3c_master_i2c_adapter_cleanup(master); i3c_master_unregister_i3c_devs(master); i3c_master_bus_cleanup(master); device_unregister(&master->dev); - - return 0; } EXPORT_SYMBOL_GPL(i3c_master_unregister); diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 4859dd75388d..8d04b3c72b0e 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1185,11 +1185,8 @@ static int dw_i3c_probe(struct platform_device *pdev) static int dw_i3c_remove(struct platform_device *pdev) { struct dw_i3c_master *master = platform_get_drvdata(pdev); - int ret; - ret = i3c_master_unregister(&master->base); - if (ret) - return ret; + i3c_master_unregister(&master->base); reset_control_assert(master->core_rst); diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 5b37ffe5ad5b..454925c5e097 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -1665,11 +1665,8 @@ static int cdns_i3c_master_probe(struct platform_device *pdev) static int cdns_i3c_master_remove(struct platform_device *pdev) { struct cdns_i3c_master *master = platform_get_drvdata(pdev); - int ret; - ret = i3c_master_unregister(&master->base); - if (ret) - return ret; + i3c_master_unregister(&master->base); clk_disable_unprepare(master->sysclk); clk_disable_unprepare(master->pclk); diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index 6aef5ce43cc1..f9bc58366a72 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -769,7 +769,9 @@ static int i3c_hci_remove(struct platform_device *pdev) { struct i3c_hci *hci = platform_get_drvdata(pdev); - return i3c_master_unregister(&hci->master); + i3c_master_unregister(&hci->master); + + return 0; } static const __maybe_unused struct of_device_id i3c_hci_of_match[] = { diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index d6e9ed74cdcf..e5476d04b403 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -1572,11 +1572,8 @@ static int svc_i3c_master_probe(struct platform_device *pdev) static int svc_i3c_master_remove(struct platform_device *pdev) { struct svc_i3c_master *master = platform_get_drvdata(pdev); - int ret; - ret = i3c_master_unregister(&master->base); - if (ret) - return ret; + i3c_master_unregister(&master->base); pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index a12cda9dc715..0b52da4f2346 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -542,7 +542,7 @@ int i3c_master_register(struct i3c_master_controller *master, struct device *parent, const struct i3c_master_controller_ops *ops, bool secondary); -int i3c_master_unregister(struct i3c_master_controller *master); +void i3c_master_unregister(struct i3c_master_controller *master); /** * i3c_dev_get_master_data() - get master private data attached to an I3C -- GitLab From 04b5f1be2673a035b0218c6e0369cfd1460d63a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:08 +0100 Subject: [PATCH 1019/5631] i3c: dw: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230318233311.265186-3-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 8d04b3c72b0e..61ad03c4c2c9 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1182,7 +1182,7 @@ static int dw_i3c_probe(struct platform_device *pdev) return ret; } -static int dw_i3c_remove(struct platform_device *pdev) +static void dw_i3c_remove(struct platform_device *pdev) { struct dw_i3c_master *master = platform_get_drvdata(pdev); @@ -1191,8 +1191,6 @@ static int dw_i3c_remove(struct platform_device *pdev) reset_control_assert(master->core_rst); clk_disable_unprepare(master->core_clk); - - return 0; } static const struct of_device_id dw_i3c_master_of_match[] = { @@ -1203,7 +1201,7 @@ MODULE_DEVICE_TABLE(of, dw_i3c_master_of_match); static struct platform_driver dw_i3c_driver = { .probe = dw_i3c_probe, - .remove = dw_i3c_remove, + .remove_new = dw_i3c_remove, .driver = { .name = "dw-i3c-master", .of_match_table = dw_i3c_master_of_match, -- GitLab From 3f8ad583590f7bfeb3b8ee1ddd1cca5f7f9a5a75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:09 +0100 Subject: [PATCH 1020/5631] i3c: cdns: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230318233311.265186-4-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/i3c/master/i3c-master-cdns.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 454925c5e097..01610fa5b0cc 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -1662,7 +1662,7 @@ static int cdns_i3c_master_probe(struct platform_device *pdev) return ret; } -static int cdns_i3c_master_remove(struct platform_device *pdev) +static void cdns_i3c_master_remove(struct platform_device *pdev) { struct cdns_i3c_master *master = platform_get_drvdata(pdev); @@ -1670,13 +1670,11 @@ static int cdns_i3c_master_remove(struct platform_device *pdev) clk_disable_unprepare(master->sysclk); clk_disable_unprepare(master->pclk); - - return 0; } static struct platform_driver cdns_i3c_master = { .probe = cdns_i3c_master_probe, - .remove = cdns_i3c_master_remove, + .remove_new = cdns_i3c_master_remove, .driver = { .name = "cdns-i3c-master", .of_match_table = cdns_i3c_master_of_ids, -- GitLab From f959ec617521bab177758b7c71b0d56a65615079 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:10 +0100 Subject: [PATCH 1021/5631] i3c: mipi-i3c-hci: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230318233311.265186-5-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/i3c/master/mipi-i3c-hci/core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c index f9bc58366a72..837af83c85f4 100644 --- a/drivers/i3c/master/mipi-i3c-hci/core.c +++ b/drivers/i3c/master/mipi-i3c-hci/core.c @@ -765,13 +765,11 @@ static int i3c_hci_probe(struct platform_device *pdev) return 0; } -static int i3c_hci_remove(struct platform_device *pdev) +static void i3c_hci_remove(struct platform_device *pdev) { struct i3c_hci *hci = platform_get_drvdata(pdev); i3c_master_unregister(&hci->master); - - return 0; } static const __maybe_unused struct of_device_id i3c_hci_of_match[] = { @@ -782,7 +780,7 @@ MODULE_DEVICE_TABLE(of, i3c_hci_of_match); static struct platform_driver i3c_hci_driver = { .probe = i3c_hci_probe, - .remove = i3c_hci_remove, + .remove_new = i3c_hci_remove, .driver = { .name = "mipi-i3c-hci", .of_match_table = of_match_ptr(i3c_hci_of_match), -- GitLab From 2810f1de814adb7728b1068586bebcf733cf1992 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 00:33:11 +0100 Subject: [PATCH 1022/5631] i3c: svc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Miquel Raynal Link: https://lore.kernel.org/r/20230318233311.265186-6-u.kleine-koenig@pengutronix.de Signed-off-by: Alexandre Belloni --- drivers/i3c/master/svc-i3c-master.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index e5476d04b403..e3f454123805 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -1569,7 +1569,7 @@ static int svc_i3c_master_probe(struct platform_device *pdev) return ret; } -static int svc_i3c_master_remove(struct platform_device *pdev) +static void svc_i3c_master_remove(struct platform_device *pdev) { struct svc_i3c_master *master = platform_get_drvdata(pdev); @@ -1577,8 +1577,6 @@ static int svc_i3c_master_remove(struct platform_device *pdev) pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_disable(&pdev->dev); - - return 0; } static int __maybe_unused svc_i3c_runtime_suspend(struct device *dev) @@ -1616,7 +1614,7 @@ MODULE_DEVICE_TABLE(of, svc_i3c_master_of_match_tbl); static struct platform_driver svc_i3c_master = { .probe = svc_i3c_master_probe, - .remove = svc_i3c_master_remove, + .remove_new = svc_i3c_master_remove, .driver = { .name = "silvaco-i3c-master", .of_match_table = svc_i3c_master_of_match_tbl, -- GitLab From ab0fccc373d505c9a09bf459557768ab3177e0d2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 17 Mar 2023 18:36:33 -0500 Subject: [PATCH 1023/5631] dt-bindings: rtc: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Acked-by: Florian Fainelli Acked-by: Nicolas Ferre Reviewed-by: Linus Walleij Reviewed-by: Krzysztof Kozlowski Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230317233634.3968656-1-robh@kernel.org Signed-off-by: Alexandre Belloni --- .../devicetree/bindings/rtc/allwinner,sun4i-a10-rtc.yaml | 2 +- .../devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml | 2 +- .../devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml | 2 +- .../devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml | 2 +- .../devicetree/bindings/rtc/brcm,brcmstb-waketimer.yaml | 2 +- Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml | 4 ++-- .../devicetree/bindings/rtc/microcrystal,rv3032.yaml | 2 +- Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml | 2 +- Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml | 2 +- Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml | 2 +- Documentation/devicetree/bindings/rtc/rtc-mxc.yaml | 2 +- Documentation/devicetree/bindings/rtc/rtc-mxc_v2.yaml | 2 +- Documentation/devicetree/bindings/rtc/sa1100-rtc.yaml | 4 ++-- Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml | 2 +- Documentation/devicetree/bindings/rtc/ti,k3-rtc.yaml | 2 +- Documentation/devicetree/bindings/rtc/trivial-rtc.yaml | 2 +- 16 files changed, 18 insertions(+), 18 deletions(-) diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun4i-a10-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun4i-a10-rtc.yaml index dede49431733..054e1e397fc8 100644 --- a/Documentation/devicetree/bindings/rtc/allwinner,sun4i-a10-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun4i-a10-rtc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner A10 RTC allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Chen-Yu Tsai diff --git a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml index 04947e166cef..4531eec568a6 100644 --- a/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/allwinner,sun6i-a31-rtc.yaml @@ -61,7 +61,7 @@ properties: - the Internal Oscillator, at index 2. allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml index 0e5f0fcc26b0..4d2bef15fb7a 100644 --- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel AT91 RTC allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Alexandre Belloni diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml index b5cd20e89daf..b80b85c394ac 100644 --- a/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml +++ b/Documentation/devicetree/bindings/rtc/atmel,at91sam9260-rtt.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel AT91 RTT allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Alexandre Belloni diff --git a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.yaml b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.yaml index c6c57636c729..c5e5c5aec74e 100644 --- a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.yaml +++ b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.yaml @@ -15,7 +15,7 @@ description: optionally generate RTC alarm interrupts. allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml index 056d42daae06..b1c1a0e21318 100644 --- a/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml +++ b/Documentation/devicetree/bindings/rtc/faraday,ftrtc010.yaml @@ -38,8 +38,8 @@ properties: clock-names: items: - - const: "PCLK" - - const: "EXTCLK" + - const: PCLK + - const: EXTCLK required: - compatible diff --git a/Documentation/devicetree/bindings/rtc/microcrystal,rv3032.yaml b/Documentation/devicetree/bindings/rtc/microcrystal,rv3032.yaml index dd6eebf06ea6..27a9de10f0af 100644 --- a/Documentation/devicetree/bindings/rtc/microcrystal,rv3032.yaml +++ b/Documentation/devicetree/bindings/rtc/microcrystal,rv3032.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip RV-3032 RTC allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Alexandre Belloni diff --git a/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml b/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml index 585c185d1eb3..af4a31cd0954 100644 --- a/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/mstar,msc313-rtc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mstar MSC313e RTC allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Daniel Palmer diff --git a/Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml b/Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml index 7a1857f5caa8..4f9b5604acd9 100644 --- a/Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml +++ b/Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NUVOTON NCT3018Y Real Time Clock allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Medad CChien diff --git a/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml b/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml index a1148eb22c24..bcb230027622 100644 --- a/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml +++ b/Documentation/devicetree/bindings/rtc/nxp,pcf2127.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP PCF2127 Real Time Clock allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Alexandre Belloni diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml index 4f263fa6fd0d..a14b52178c4b 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Real Time Clock of the i.MX SoCs allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Philippe Reynes diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc_v2.yaml b/Documentation/devicetree/bindings/rtc/rtc-mxc_v2.yaml index 2d1a30663d72..e50131c26dc6 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-mxc_v2.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc-mxc_v2.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: i.MX53 Secure Real Time Clock (SRTC) allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# maintainers: - Patrick Bruenn diff --git a/Documentation/devicetree/bindings/rtc/sa1100-rtc.yaml b/Documentation/devicetree/bindings/rtc/sa1100-rtc.yaml index b04b87ef6f33..a16c355dcd11 100644 --- a/Documentation/devicetree/bindings/rtc/sa1100-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/sa1100-rtc.yaml @@ -34,8 +34,8 @@ properties: interrupt-names: items: - - const: 'rtc 1Hz' - - const: 'rtc alarm' + - const: rtc 1Hz + - const: rtc alarm required: - compatible diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml index 9e66ed33cda4..4703083d1f11 100644 --- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 st,syscfg: - $ref: "/schemas/types.yaml#/definitions/phandle-array" + $ref: /schemas/types.yaml#/definitions/phandle-array items: minItems: 3 maxItems: 3 diff --git a/Documentation/devicetree/bindings/rtc/ti,k3-rtc.yaml b/Documentation/devicetree/bindings/rtc/ti,k3-rtc.yaml index d995ef04a6eb..df5b4f77f6fb 100644 --- a/Documentation/devicetree/bindings/rtc/ti,k3-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/ti,k3-rtc.yaml @@ -13,7 +13,7 @@ description: | This RTC appears in the AM62x family of SoCs. allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml index eb75861c28c3..a3603e638c37 100644 --- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml @@ -15,7 +15,7 @@ description: | possibly an interrupt line. allOf: - - $ref: "rtc.yaml#" + - $ref: rtc.yaml# properties: compatible: -- GitLab From 0e6255fa3f649170da6bd1a544680589cfae1131 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 20 Mar 2023 22:21:42 +0100 Subject: [PATCH 1024/5631] rtc: meson-vrtc: Use ktime_get_real_ts64() to get the current time The VRTC alarm register can be programmed with an amount of seconds after which the SoC will be woken up by the VRTC timer again. We are already converting the alarm time from meson_vrtc_set_alarm() to "seconds since 1970". This means we also need to use "seconds since 1970" for the current time. This fixes a problem where setting the alarm to one minute in the future results in the firmware (which handles wakeup) to output (on the serial console) that the system will be woken up in billions of seconds. ktime_get_raw_ts64() returns the time since boot, not since 1970. Switch to ktime_get_real_ts64() to fix the calculation of the alarm time and to make the SoC wake up at the specified date/time. Also the firmware (which manages suspend) now prints either 59 or 60 seconds until wakeup (depending on how long it takes for the system to enter suspend). Fixes: 6ef35398e827 ("rtc: Add Amlogic Virtual Wake RTC") Signed-off-by: Martin Blumenstingl Reviewed-by: Neil Armstrong Reviewed-by: Kevin Hilman Link: https://lore.kernel.org/r/20230320212142.2355062-1-martin.blumenstingl@googlemail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-meson-vrtc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c index 1463c8621561..648fa362ec44 100644 --- a/drivers/rtc/rtc-meson-vrtc.c +++ b/drivers/rtc/rtc-meson-vrtc.c @@ -23,7 +23,7 @@ static int meson_vrtc_read_time(struct device *dev, struct rtc_time *tm) struct timespec64 time; dev_dbg(dev, "%s\n", __func__); - ktime_get_raw_ts64(&time); + ktime_get_real_ts64(&time); rtc_time64_to_tm(time.tv_sec, tm); return 0; @@ -96,7 +96,7 @@ static int __maybe_unused meson_vrtc_suspend(struct device *dev) long alarm_secs; struct timespec64 time; - ktime_get_raw_ts64(&time); + ktime_get_real_ts64(&time); local_time = time.tv_sec; dev_dbg(dev, "alarm_time = %lus, local_time=%lus\n", -- GitLab From 12de2f50244efdbc8e98f89a340255c3c847e1dc Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Tue, 21 Mar 2023 19:18:14 +0800 Subject: [PATCH 1025/5631] dt-bindings: clock: Add Loongson-1 clock Add devicetree binding document and related header file for the Loongson-1 clock. Signed-off-by: Keguang Zhang Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230321111817.71756-2-keguang.zhang@gmail.com Signed-off-by: Stephen Boyd --- .../bindings/clock/loongson,ls1x-clk.yaml | 45 +++++++++++++++++++ include/dt-bindings/clock/loongson,ls1x-clk.h | 19 ++++++++ 2 files changed, 64 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/loongson,ls1x-clk.yaml create mode 100644 include/dt-bindings/clock/loongson,ls1x-clk.h diff --git a/Documentation/devicetree/bindings/clock/loongson,ls1x-clk.yaml b/Documentation/devicetree/bindings/clock/loongson,ls1x-clk.yaml new file mode 100644 index 000000000000..01561a0f35d5 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/loongson,ls1x-clk.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/loongson,ls1x-clk.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Loongson-1 Clock Controller + +maintainers: + - Keguang Zhang + +properties: + compatible: + enum: + - loongson,ls1b-clk + - loongson,ls1c-clk + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + "#clock-cells": + const: 1 + +required: + - compatible + - reg + - clocks + - "#clock-cells" + +additionalProperties: false + +examples: + - | + clkc: clock-controller@1fe78030 { + compatible = "loongson,ls1b-clk"; + reg = <0x1fe78030 0x8>; + + clocks = <&xtal>; + #clock-cells = <1>; + }; + +... diff --git a/include/dt-bindings/clock/loongson,ls1x-clk.h b/include/dt-bindings/clock/loongson,ls1x-clk.h new file mode 100644 index 000000000000..d400e9ac6002 --- /dev/null +++ b/include/dt-bindings/clock/loongson,ls1x-clk.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Loongson-1 clock tree IDs + * + * Copyright (C) 2023 Keguang Zhang + */ + +#ifndef __DT_BINDINGS_CLOCK_LS1X_CLK_H__ +#define __DT_BINDINGS_CLOCK_LS1X_CLK_H__ + +#define LS1X_CLKID_PLL 0 +#define LS1X_CLKID_CPU 1 +#define LS1X_CLKID_DC 2 +#define LS1X_CLKID_AHB 3 +#define LS1X_CLKID_APB 4 + +#define CLK_NR_CLKS (LS1X_CLKID_APB + 1) + +#endif /* __DT_BINDINGS_CLOCK_LS1X_CLK_H__ */ -- GitLab From c46496119ed07be49537fcb61fa07a34e9a726b2 Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Tue, 21 Mar 2023 19:18:15 +0800 Subject: [PATCH 1026/5631] clk: loongson1: Remove the outdated driver Remove the outdated driver due to the following aspects. - no DT support - duplicate code across LS1B and LS1C - does not fit into the current clock framework Signed-off-by: Keguang Zhang Link: https://lore.kernel.org/r/20230321111817.71756-3-keguang.zhang@gmail.com Signed-off-by: Stephen Boyd --- drivers/clk/Makefile | 1 - drivers/clk/loongson1/Makefile | 4 - drivers/clk/loongson1/clk-loongson1b.c | 118 ------------------------- drivers/clk/loongson1/clk-loongson1c.c | 95 -------------------- drivers/clk/loongson1/clk.c | 41 --------- drivers/clk/loongson1/clk.h | 15 ---- 6 files changed, 274 deletions(-) delete mode 100644 drivers/clk/loongson1/Makefile delete mode 100644 drivers/clk/loongson1/clk-loongson1b.c delete mode 100644 drivers/clk/loongson1/clk-loongson1c.c delete mode 100644 drivers/clk/loongson1/clk.c delete mode 100644 drivers/clk/loongson1/clk.h diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e3ca0d058a25..b7b2c6d64636 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -93,7 +93,6 @@ obj-y += imx/ obj-y += ingenic/ obj-$(CONFIG_ARCH_K3) += keystone/ obj-$(CONFIG_ARCH_KEYSTONE) += keystone/ -obj-$(CONFIG_MACH_LOONGSON32) += loongson1/ obj-y += mediatek/ obj-$(CONFIG_ARCH_MESON) += meson/ obj-y += microchip/ diff --git a/drivers/clk/loongson1/Makefile b/drivers/clk/loongson1/Makefile deleted file mode 100644 index 251d0fe9dcd1..000000000000 --- a/drivers/clk/loongson1/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-y += clk.o -obj-$(CONFIG_LOONGSON1_LS1B) += clk-loongson1b.o -obj-$(CONFIG_LOONGSON1_LS1C) += clk-loongson1c.o diff --git a/drivers/clk/loongson1/clk-loongson1b.c b/drivers/clk/loongson1/clk-loongson1b.c deleted file mode 100644 index 13a2ca23a159..000000000000 --- a/drivers/clk/loongson1/clk-loongson1b.c +++ /dev/null @@ -1,118 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2012-2016 Zhang, Keguang - */ - -#include -#include -#include -#include - -#include -#include "clk.h" - -#define OSC (33 * 1000000) -#define DIV_APB 2 - -static DEFINE_SPINLOCK(_lock); - -static unsigned long ls1x_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - u32 pll, rate; - - pll = __raw_readl(LS1X_CLK_PLL_FREQ); - rate = 12 + (pll & GENMASK(5, 0)); - rate *= OSC; - rate >>= 1; - - return rate; -} - -static const struct clk_ops ls1x_pll_clk_ops = { - .recalc_rate = ls1x_pll_recalc_rate, -}; - -static const char *const cpu_parents[] = { "cpu_clk_div", "osc_clk", }; -static const char *const ahb_parents[] = { "ahb_clk_div", "osc_clk", }; -static const char *const dc_parents[] = { "dc_clk_div", "osc_clk", }; - -void __init ls1x_clk_init(void) -{ - struct clk_hw *hw; - - hw = clk_hw_register_fixed_rate(NULL, "osc_clk", NULL, 0, OSC); - clk_hw_register_clkdev(hw, "osc_clk", NULL); - - /* clock derived from 33 MHz OSC clk */ - hw = clk_hw_register_pll(NULL, "pll_clk", "osc_clk", - &ls1x_pll_clk_ops, 0); - clk_hw_register_clkdev(hw, "pll_clk", NULL); - - /* clock derived from PLL clk */ - /* _____ - * _______________________| | - * OSC ___/ | MUX |___ CPU CLK - * \___ PLL ___ CPU DIV ___| | - * |_____| - */ - hw = clk_hw_register_divider(NULL, "cpu_clk_div", "pll_clk", - CLK_GET_RATE_NOCACHE, LS1X_CLK_PLL_DIV, - DIV_CPU_SHIFT, DIV_CPU_WIDTH, - CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ROUND_CLOSEST, &_lock); - clk_hw_register_clkdev(hw, "cpu_clk_div", NULL); - hw = clk_hw_register_mux(NULL, "cpu_clk", cpu_parents, - ARRAY_SIZE(cpu_parents), - CLK_SET_RATE_NO_REPARENT, LS1X_CLK_PLL_DIV, - BYPASS_CPU_SHIFT, BYPASS_CPU_WIDTH, 0, &_lock); - clk_hw_register_clkdev(hw, "cpu_clk", NULL); - - /* _____ - * _______________________| | - * OSC ___/ | MUX |___ DC CLK - * \___ PLL ___ DC DIV ___| | - * |_____| - */ - hw = clk_hw_register_divider(NULL, "dc_clk_div", "pll_clk", - 0, LS1X_CLK_PLL_DIV, DIV_DC_SHIFT, - DIV_DC_WIDTH, CLK_DIVIDER_ONE_BASED, &_lock); - clk_hw_register_clkdev(hw, "dc_clk_div", NULL); - hw = clk_hw_register_mux(NULL, "dc_clk", dc_parents, - ARRAY_SIZE(dc_parents), - CLK_SET_RATE_NO_REPARENT, LS1X_CLK_PLL_DIV, - BYPASS_DC_SHIFT, BYPASS_DC_WIDTH, 0, &_lock); - clk_hw_register_clkdev(hw, "dc_clk", NULL); - - /* _____ - * _______________________| | - * OSC ___/ | MUX |___ DDR CLK - * \___ PLL ___ DDR DIV ___| | - * |_____| - */ - hw = clk_hw_register_divider(NULL, "ahb_clk_div", "pll_clk", - 0, LS1X_CLK_PLL_DIV, DIV_DDR_SHIFT, - DIV_DDR_WIDTH, CLK_DIVIDER_ONE_BASED, - &_lock); - clk_hw_register_clkdev(hw, "ahb_clk_div", NULL); - hw = clk_hw_register_mux(NULL, "ahb_clk", ahb_parents, - ARRAY_SIZE(ahb_parents), - CLK_SET_RATE_NO_REPARENT, LS1X_CLK_PLL_DIV, - BYPASS_DDR_SHIFT, BYPASS_DDR_WIDTH, 0, &_lock); - clk_hw_register_clkdev(hw, "ahb_clk", NULL); - clk_hw_register_clkdev(hw, "ls1x-dma", NULL); - clk_hw_register_clkdev(hw, "stmmaceth", NULL); - - /* clock derived from AHB clk */ - /* APB clk is always half of the AHB clk */ - hw = clk_hw_register_fixed_factor(NULL, "apb_clk", "ahb_clk", 0, 1, - DIV_APB); - clk_hw_register_clkdev(hw, "apb_clk", NULL); - clk_hw_register_clkdev(hw, "ls1x-ac97", NULL); - clk_hw_register_clkdev(hw, "ls1x-i2c", NULL); - clk_hw_register_clkdev(hw, "ls1x-nand", NULL); - clk_hw_register_clkdev(hw, "ls1x-pwmtimer", NULL); - clk_hw_register_clkdev(hw, "ls1x-spi", NULL); - clk_hw_register_clkdev(hw, "ls1x-wdt", NULL); - clk_hw_register_clkdev(hw, "serial8250", NULL); -} diff --git a/drivers/clk/loongson1/clk-loongson1c.c b/drivers/clk/loongson1/clk-loongson1c.c deleted file mode 100644 index 1ebf740380ef..000000000000 --- a/drivers/clk/loongson1/clk-loongson1c.c +++ /dev/null @@ -1,95 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2016 Yang Ling - */ - -#include -#include -#include - -#include -#include "clk.h" - -#define OSC (24 * 1000000) -#define DIV_APB 1 - -static DEFINE_SPINLOCK(_lock); - -static unsigned long ls1x_pll_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - u32 pll, rate; - - pll = __raw_readl(LS1X_CLK_PLL_FREQ); - rate = ((pll >> 8) & 0xff) + ((pll >> 16) & 0xff); - rate *= OSC; - rate >>= 2; - - return rate; -} - -static const struct clk_ops ls1x_pll_clk_ops = { - .recalc_rate = ls1x_pll_recalc_rate, -}; - -static const struct clk_div_table ahb_div_table[] = { - [0] = { .val = 0, .div = 2 }, - [1] = { .val = 1, .div = 4 }, - [2] = { .val = 2, .div = 3 }, - [3] = { .val = 3, .div = 3 }, - [4] = { /* sentinel */ } -}; - -void __init ls1x_clk_init(void) -{ - struct clk_hw *hw; - - hw = clk_hw_register_fixed_rate(NULL, "osc_clk", NULL, 0, OSC); - clk_hw_register_clkdev(hw, "osc_clk", NULL); - - /* clock derived from 24 MHz OSC clk */ - hw = clk_hw_register_pll(NULL, "pll_clk", "osc_clk", - &ls1x_pll_clk_ops, 0); - clk_hw_register_clkdev(hw, "pll_clk", NULL); - - hw = clk_hw_register_divider(NULL, "cpu_clk_div", "pll_clk", - CLK_GET_RATE_NOCACHE, LS1X_CLK_PLL_DIV, - DIV_CPU_SHIFT, DIV_CPU_WIDTH, - CLK_DIVIDER_ONE_BASED | - CLK_DIVIDER_ROUND_CLOSEST, &_lock); - clk_hw_register_clkdev(hw, "cpu_clk_div", NULL); - hw = clk_hw_register_fixed_factor(NULL, "cpu_clk", "cpu_clk_div", - 0, 1, 1); - clk_hw_register_clkdev(hw, "cpu_clk", NULL); - - hw = clk_hw_register_divider(NULL, "dc_clk_div", "pll_clk", - 0, LS1X_CLK_PLL_DIV, DIV_DC_SHIFT, - DIV_DC_WIDTH, CLK_DIVIDER_ONE_BASED, &_lock); - clk_hw_register_clkdev(hw, "dc_clk_div", NULL); - hw = clk_hw_register_fixed_factor(NULL, "dc_clk", "dc_clk_div", - 0, 1, 1); - clk_hw_register_clkdev(hw, "dc_clk", NULL); - - hw = clk_hw_register_divider_table(NULL, "ahb_clk_div", "cpu_clk_div", - 0, LS1X_CLK_PLL_FREQ, DIV_DDR_SHIFT, - DIV_DDR_WIDTH, CLK_DIVIDER_ALLOW_ZERO, - ahb_div_table, &_lock); - clk_hw_register_clkdev(hw, "ahb_clk_div", NULL); - hw = clk_hw_register_fixed_factor(NULL, "ahb_clk", "ahb_clk_div", - 0, 1, 1); - clk_hw_register_clkdev(hw, "ahb_clk", NULL); - clk_hw_register_clkdev(hw, "ls1x-dma", NULL); - clk_hw_register_clkdev(hw, "stmmaceth", NULL); - - /* clock derived from AHB clk */ - hw = clk_hw_register_fixed_factor(NULL, "apb_clk", "ahb_clk", 0, 1, - DIV_APB); - clk_hw_register_clkdev(hw, "apb_clk", NULL); - clk_hw_register_clkdev(hw, "ls1x-ac97", NULL); - clk_hw_register_clkdev(hw, "ls1x-i2c", NULL); - clk_hw_register_clkdev(hw, "ls1x-nand", NULL); - clk_hw_register_clkdev(hw, "ls1x-pwmtimer", NULL); - clk_hw_register_clkdev(hw, "ls1x-spi", NULL); - clk_hw_register_clkdev(hw, "ls1x-wdt", NULL); - clk_hw_register_clkdev(hw, "serial8250", NULL); -} diff --git a/drivers/clk/loongson1/clk.c b/drivers/clk/loongson1/clk.c deleted file mode 100644 index f336a3126d31..000000000000 --- a/drivers/clk/loongson1/clk.c +++ /dev/null @@ -1,41 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (c) 2012-2016 Zhang, Keguang - */ - -#include -#include - -#include "clk.h" - -struct clk_hw *__init clk_hw_register_pll(struct device *dev, - const char *name, - const char *parent_name, - const struct clk_ops *ops, - unsigned long flags) -{ - int ret; - struct clk_hw *hw; - struct clk_init_data init; - - /* allocate the divider */ - hw = kzalloc(sizeof(*hw), GFP_KERNEL); - if (!hw) - return ERR_PTR(-ENOMEM); - - init.name = name; - init.ops = ops; - init.flags = flags; - init.parent_names = parent_name ? &parent_name : NULL; - init.num_parents = parent_name ? 1 : 0; - hw->init = &init; - - /* register the clock */ - ret = clk_hw_register(dev, hw); - if (ret) { - kfree(hw); - hw = ERR_PTR(ret); - } - - return hw; -} diff --git a/drivers/clk/loongson1/clk.h b/drivers/clk/loongson1/clk.h deleted file mode 100644 index 124642302b12..000000000000 --- a/drivers/clk/loongson1/clk.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (c) 2012-2016 Zhang, Keguang - */ - -#ifndef __LOONGSON1_CLK_H -#define __LOONGSON1_CLK_H - -struct clk_hw *clk_hw_register_pll(struct device *dev, - const char *name, - const char *parent_name, - const struct clk_ops *ops, - unsigned long flags); - -#endif /* __LOONGSON1_CLK_H */ -- GitLab From fbdb1873656be002df069b7a235c202aefcfdf2e Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Tue, 21 Mar 2023 19:18:16 +0800 Subject: [PATCH 1027/5631] clk: loongson1: Re-implement the clock driver Re-implement the clock driver for Loongson-1 to add devicetree support and fit into the clock framework. Signed-off-by: Keguang Zhang Link: https://lore.kernel.org/r/20230321111817.71756-4-keguang.zhang@gmail.com Signed-off-by: Stephen Boyd --- drivers/clk/Makefile | 1 + drivers/clk/clk-loongson1.c | 303 ++++++++++++++++++++++++++++++++++++ 2 files changed, 304 insertions(+) create mode 100644 drivers/clk/clk-loongson1.c diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index b7b2c6d64636..417bc27ab6e8 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -43,6 +43,7 @@ obj-$(CONFIG_COMMON_CLK_K210) += clk-k210.o obj-$(CONFIG_LMK04832) += clk-lmk04832.o obj-$(CONFIG_COMMON_CLK_LAN966X) += clk-lan966x.o obj-$(CONFIG_COMMON_CLK_LOCHNAGAR) += clk-lochnagar.o +obj-$(CONFIG_MACH_LOONGSON32) += clk-loongson1.o obj-$(CONFIG_COMMON_CLK_MAX77686) += clk-max77686.o obj-$(CONFIG_COMMON_CLK_MAX9485) += clk-max9485.o obj-$(CONFIG_ARCH_MILBEAUT_M10V) += clk-milbeaut.o diff --git a/drivers/clk/clk-loongson1.c b/drivers/clk/clk-loongson1.c new file mode 100644 index 000000000000..a3467aa6790f --- /dev/null +++ b/drivers/clk/clk-loongson1.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Clock driver for Loongson-1 SoC + * + * Copyright (C) 2012-2023 Keguang Zhang + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* Loongson 1 Clock Register Definitions */ +#define CLK_PLL_FREQ 0x0 +#define CLK_PLL_DIV 0x4 + +static DEFINE_SPINLOCK(ls1x_clk_div_lock); + +struct ls1x_clk_pll_data { + u32 fixed; + u8 shift; + u8 int_shift; + u8 int_width; + u8 frac_shift; + u8 frac_width; +}; + +struct ls1x_clk_div_data { + u8 shift; + u8 width; + unsigned long flags; + const struct clk_div_table *table; + u8 bypass_shift; + u8 bypass_inv; + spinlock_t *lock; /* protect access to DIV registers */ +}; + +struct ls1x_clk { + void __iomem *reg; + unsigned int offset; + struct clk_hw hw; + const void *data; +}; + +#define to_ls1x_clk(_hw) container_of(_hw, struct ls1x_clk, hw) + +static inline unsigned long ls1x_pll_rate_part(unsigned int val, + unsigned int shift, + unsigned int width) +{ + return (val & GENMASK(shift + width, shift)) >> shift; +} + +static unsigned long ls1x_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct ls1x_clk *ls1x_clk = to_ls1x_clk(hw); + const struct ls1x_clk_pll_data *d = ls1x_clk->data; + u32 val, rate; + + val = readl(ls1x_clk->reg); + rate = d->fixed; + rate += ls1x_pll_rate_part(val, d->int_shift, d->int_width); + if (d->frac_width) + rate += ls1x_pll_rate_part(val, d->frac_shift, d->frac_width); + rate *= parent_rate; + rate >>= d->shift; + + return rate; +} + +static const struct clk_ops ls1x_pll_clk_ops = { + .recalc_rate = ls1x_pll_recalc_rate, +}; + +static unsigned long ls1x_divider_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct ls1x_clk *ls1x_clk = to_ls1x_clk(hw); + const struct ls1x_clk_div_data *d = ls1x_clk->data; + unsigned int val; + + val = readl(ls1x_clk->reg) >> d->shift; + val &= clk_div_mask(d->width); + + return divider_recalc_rate(hw, parent_rate, val, d->table, + d->flags, d->width); +} + +static long ls1x_divider_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + struct ls1x_clk *ls1x_clk = to_ls1x_clk(hw); + const struct ls1x_clk_div_data *d = ls1x_clk->data; + + return divider_round_rate(hw, rate, prate, d->table, + d->width, d->flags); +} + +static int ls1x_divider_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct ls1x_clk *ls1x_clk = to_ls1x_clk(hw); + const struct ls1x_clk_div_data *d = ls1x_clk->data; + int val, div_val; + unsigned long flags = 0; + + div_val = divider_get_val(rate, parent_rate, d->table, + d->width, d->flags); + if (div_val < 0) + return div_val; + + spin_lock_irqsave(d->lock, flags); + + /* Bypass the clock */ + val = readl(ls1x_clk->reg); + if (d->bypass_inv) + val &= ~BIT(d->bypass_shift); + else + val |= BIT(d->bypass_shift); + writel(val, ls1x_clk->reg); + + val = readl(ls1x_clk->reg); + val &= ~(clk_div_mask(d->width) << d->shift); + val |= (u32)div_val << d->shift; + writel(val, ls1x_clk->reg); + + /* Restore the clock */ + val = readl(ls1x_clk->reg); + if (d->bypass_inv) + val |= BIT(d->bypass_shift); + else + val &= ~BIT(d->bypass_shift); + writel(val, ls1x_clk->reg); + + spin_unlock_irqrestore(d->lock, flags); + + return 0; +} + +static const struct clk_ops ls1x_clk_divider_ops = { + .recalc_rate = ls1x_divider_recalc_rate, + .round_rate = ls1x_divider_round_rate, + .set_rate = ls1x_divider_set_rate, +}; + +#define LS1X_CLK_PLL(_name, _offset, _fixed, _shift, \ + f_shift, f_width, i_shift, i_width) \ +struct ls1x_clk _name = { \ + .offset = (_offset), \ + .data = &(const struct ls1x_clk_pll_data) { \ + .fixed = (_fixed), \ + .shift = (_shift), \ + .int_shift = (i_shift), \ + .int_width = (i_width), \ + .frac_shift = (f_shift), \ + .frac_width = (f_width), \ + }, \ + .hw.init = &(const struct clk_init_data) { \ + .name = #_name, \ + .ops = &ls1x_pll_clk_ops, \ + .parent_data = &(const struct clk_parent_data) { \ + .fw_name = "xtal", \ + .name = "xtal", \ + .index = -1, \ + }, \ + .num_parents = 1, \ + }, \ +} + +#define LS1X_CLK_DIV(_name, _pname, _offset, _shift, _width, \ + _table, _bypass_shift, _bypass_inv, _flags) \ +struct ls1x_clk _name = { \ + .offset = (_offset), \ + .data = &(const struct ls1x_clk_div_data){ \ + .shift = (_shift), \ + .width = (_width), \ + .table = (_table), \ + .flags = (_flags), \ + .bypass_shift = (_bypass_shift), \ + .bypass_inv = (_bypass_inv), \ + .lock = &ls1x_clk_div_lock, \ + }, \ + .hw.init = &(const struct clk_init_data) { \ + .name = #_name, \ + .ops = &ls1x_clk_divider_ops, \ + .parent_hws = (const struct clk_hw *[]) { _pname }, \ + .num_parents = 1, \ + .flags = CLK_GET_RATE_NOCACHE, \ + }, \ +} + +static LS1X_CLK_PLL(ls1b_clk_pll, CLK_PLL_FREQ, 12, 1, 0, 5, 0, 0); +static LS1X_CLK_DIV(ls1b_clk_cpu, &ls1b_clk_pll.hw, CLK_PLL_DIV, + 20, 4, NULL, 8, 0, + CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ROUND_CLOSEST); +static LS1X_CLK_DIV(ls1b_clk_dc, &ls1b_clk_pll.hw, CLK_PLL_DIV, + 26, 4, NULL, 12, 0, CLK_DIVIDER_ONE_BASED); +static LS1X_CLK_DIV(ls1b_clk_ahb, &ls1b_clk_pll.hw, CLK_PLL_DIV, + 14, 4, NULL, 10, 0, CLK_DIVIDER_ONE_BASED); +static CLK_FIXED_FACTOR(ls1b_clk_apb, "ls1b_clk_apb", "ls1b_clk_ahb", 2, 1, + CLK_SET_RATE_PARENT); + +static struct clk_hw_onecell_data ls1b_clk_hw_data = { + .hws = { + [LS1X_CLKID_PLL] = &ls1b_clk_pll.hw, + [LS1X_CLKID_CPU] = &ls1b_clk_cpu.hw, + [LS1X_CLKID_DC] = &ls1b_clk_dc.hw, + [LS1X_CLKID_AHB] = &ls1b_clk_ahb.hw, + [LS1X_CLKID_APB] = &ls1b_clk_apb.hw, + }, + .num = CLK_NR_CLKS, +}; + +static const struct clk_div_table ls1c_ahb_div_table[] = { + [0] = { .val = 0, .div = 2 }, + [1] = { .val = 1, .div = 4 }, + [2] = { .val = 2, .div = 3 }, + [3] = { .val = 3, .div = 3 }, + [4] = { /* sentinel */ } +}; + +static LS1X_CLK_PLL(ls1c_clk_pll, CLK_PLL_FREQ, 0, 2, 8, 8, 16, 8); +static LS1X_CLK_DIV(ls1c_clk_cpu, &ls1c_clk_pll.hw, CLK_PLL_DIV, + 8, 7, NULL, 0, 1, + CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ROUND_CLOSEST); +static LS1X_CLK_DIV(ls1c_clk_dc, &ls1c_clk_pll.hw, CLK_PLL_DIV, + 24, 7, NULL, 4, 1, CLK_DIVIDER_ONE_BASED); +static LS1X_CLK_DIV(ls1c_clk_ahb, &ls1c_clk_cpu.hw, CLK_PLL_FREQ, + 0, 2, ls1c_ahb_div_table, 0, 0, CLK_DIVIDER_ALLOW_ZERO); +static CLK_FIXED_FACTOR(ls1c_clk_apb, "ls1c_clk_apb", "ls1c_clk_ahb", 1, 1, + CLK_SET_RATE_PARENT); + +static struct clk_hw_onecell_data ls1c_clk_hw_data = { + .hws = { + [LS1X_CLKID_PLL] = &ls1c_clk_pll.hw, + [LS1X_CLKID_CPU] = &ls1c_clk_cpu.hw, + [LS1X_CLKID_DC] = &ls1c_clk_dc.hw, + [LS1X_CLKID_AHB] = &ls1c_clk_ahb.hw, + [LS1X_CLKID_APB] = &ls1c_clk_apb.hw, + }, + .num = CLK_NR_CLKS, +}; + +static void __init ls1x_clk_init(struct device_node *np, + struct clk_hw_onecell_data *hw_data) +{ + struct ls1x_clk *ls1x_clk; + void __iomem *reg; + int i, ret; + + reg = of_iomap(np, 0); + if (!reg) { + pr_err("Unable to map base for %pOF\n", np); + return; + } + + for (i = 0; i < hw_data->num; i++) { + /* array might be sparse */ + if (!hw_data->hws[i]) + continue; + + if (i != LS1X_CLKID_APB) { + ls1x_clk = to_ls1x_clk(hw_data->hws[i]); + ls1x_clk->reg = reg + ls1x_clk->offset; + } + + ret = of_clk_hw_register(np, hw_data->hws[i]); + if (ret) + goto err; + } + + ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, hw_data); + if (!ret) + return; + +err: + pr_err("Failed to register %pOF\n", np); + + while (--i >= 0) + clk_hw_unregister(hw_data->hws[i]); + + iounmap(reg); +} + +static void __init ls1b_clk_init(struct device_node *np) +{ + return ls1x_clk_init(np, &ls1b_clk_hw_data); +} + +static void __init ls1c_clk_init(struct device_node *np) +{ + return ls1x_clk_init(np, &ls1c_clk_hw_data); +} + +CLK_OF_DECLARE(ls1b_clk, "loongson,ls1b-clk", ls1b_clk_init); +CLK_OF_DECLARE(ls1c_clk, "loongson,ls1c-clk", ls1c_clk_init); -- GitLab From b927c76c805432cc66e1cee67e1209514868c873 Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Tue, 21 Mar 2023 19:18:17 +0800 Subject: [PATCH 1028/5631] MIPS: loongson32: Update the clock initialization The Loongson-1 clock driver is under re-implementation to add DT support. As a result, ls1x_clk_init() will be dropped soon. Therefore, call of_clk_init() for clock initialization instead. Signed-off-by: Keguang Zhang Acked-by: Stephen Boyd Acked-by: Thomas Bogendoerfer Link: https://lore.kernel.org/r/20230321111817.71756-5-keguang.zhang@gmail.com Signed-off-by: Stephen Boyd --- arch/mips/include/asm/mach-loongson32/platform.h | 1 - arch/mips/loongson32/common/time.c | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/mach-loongson32/platform.h b/arch/mips/include/asm/mach-loongson32/platform.h index 86e1a6aab4e5..2cdcfb5f6012 100644 --- a/arch/mips/include/asm/mach-loongson32/platform.h +++ b/arch/mips/include/asm/mach-loongson32/platform.h @@ -20,7 +20,6 @@ extern struct platform_device ls1x_gpio1_pdev; extern struct platform_device ls1x_rtc_pdev; extern struct platform_device ls1x_wdt_pdev; -void __init ls1x_clk_init(void); void __init ls1x_rtc_set_extclk(struct platform_device *pdev); void __init ls1x_serial_set_uartclk(struct platform_device *pdev); diff --git a/arch/mips/loongson32/common/time.c b/arch/mips/loongson32/common/time.c index 459b15c96d3b..965c04aa56fd 100644 --- a/arch/mips/loongson32/common/time.c +++ b/arch/mips/loongson32/common/time.c @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -211,7 +212,7 @@ void __init plat_time_init(void) struct clk *clk = NULL; /* initialize LS1X clocks */ - ls1x_clk_init(); + of_clk_init(NULL); #ifdef CONFIG_CEVT_CSRC_LS1X /* setup LS1X PWM timer */ -- GitLab From 488018957c72498e9a30db6258d48dbd6c4ceb57 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:08 +0100 Subject: [PATCH 1029/5631] clk: socfpga: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The indentation of the init function parameters has been aligned to match open parenthesis, as suggested by checkpatch, and the __init macro moved before the function name, as specified in init.h. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-2-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-periph.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/drivers/clk/socfpga/clk-periph.c b/drivers/clk/socfpga/clk-periph.c index 43707e2d7248..6a4075147b9c 100644 --- a/drivers/clk/socfpga/clk-periph.c +++ b/drivers/clk/socfpga/clk-periph.c @@ -47,8 +47,8 @@ static const struct clk_ops periclk_ops = { .get_parent = clk_periclk_get_parent, }; -static __init void __socfpga_periph_init(struct device_node *node, - const struct clk_ops *ops) +static void __init __socfpga_periph_init(struct device_node *node, + const struct clk_ops *ops) { u32 reg; struct clk_hw *hw_clk; @@ -96,11 +96,25 @@ static __init void __socfpga_periph_init(struct device_node *node, periph_clk->hw.hw.init = &init; hw_clk = &periph_clk->hw.hw; - if (clk_hw_register(NULL, hw_clk)) { - kfree(periph_clk); - return; + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; + } + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { + pr_err("Could not register clock provider for node:%s\n", + clk_name); + goto err_of_clk_add_hw_provider; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); + + return; + +err_of_clk_add_hw_provider: + clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(periph_clk); } void __init socfpga_periph_init(struct device_node *node) -- GitLab From da939f6d8080ad12415240c584de03816fd575b8 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:09 +0100 Subject: [PATCH 1030/5631] clk: socfpga: arria10: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The indentation of the init function parameters has been aligned to match open parenthesis, as suggested by checkpatch, and the __init macro moved before the function name, as specified in init.h. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-3-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-periph-a10.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/clk/socfpga/clk-periph-a10.c b/drivers/clk/socfpga/clk-periph-a10.c index b9cdde4b8441..64cc70b970b7 100644 --- a/drivers/clk/socfpga/clk-periph-a10.c +++ b/drivers/clk/socfpga/clk-periph-a10.c @@ -57,8 +57,8 @@ static const struct clk_ops periclk_ops = { .get_parent = clk_periclk_get_parent, }; -static __init void __socfpga_periph_init(struct device_node *node, - const struct clk_ops *ops) +static void __init __socfpga_periph_init(struct device_node *node, + const struct clk_ops *ops) { u32 reg; struct clk_hw *hw_clk; @@ -106,21 +106,25 @@ static __init void __socfpga_periph_init(struct device_node *node, hw_clk = &periph_clk->hw.hw; - if (clk_hw_register(NULL, hw_clk)) { - kfree(periph_clk); - return; + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); - if (rc < 0) { + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { pr_err("Could not register clock provider for node:%s\n", clk_name); - goto err_clk; + goto err_of_clk_add_hw_provider; } return; -err_clk: +err_of_clk_add_hw_provider: clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(periph_clk); } void __init socfpga_a10_periph_init(struct device_node *node) -- GitLab From 85f1b574059d88f4b7f5dc0401f3745b305476f9 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:10 +0100 Subject: [PATCH 1031/5631] clk: socfpga: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The err variable unnecessarily duplicates the functionality of the rc variable, so it has been removed. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-4-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-gate.c | 35 +++++++++++++++++++++------------- 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c index 0c18c55edf8c..32ccda960f28 100644 --- a/drivers/clk/socfpga/clk-gate.c +++ b/drivers/clk/socfpga/clk-gate.c @@ -126,17 +126,14 @@ void __init socfpga_gate_init(struct device_node *node) struct clk_init_data init; struct clk_ops *ops; int rc; - int err; socfpga_clk = kzalloc(sizeof(*socfpga_clk), GFP_KERNEL); if (WARN_ON(!socfpga_clk)) return; ops = kmemdup(&gateclk_ops, sizeof(gateclk_ops), GFP_KERNEL); - if (WARN_ON(!ops)) { - kfree(socfpga_clk); - return; - } + if (WARN_ON(!ops)) + goto err_kmemdup; rc = of_property_read_u32_array(node, "clk-gate", clk_gate, 2); if (rc) @@ -182,13 +179,25 @@ void __init socfpga_gate_init(struct device_node *node) hw_clk = &socfpga_clk->hw.hw; - err = clk_hw_register(NULL, hw_clk); - if (err) { - kfree(ops); - kfree(socfpga_clk); - return; + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); - if (WARN_ON(rc)) - return; + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { + pr_err("Could not register clock provider for node:%s\n", + clk_name); + goto err_of_clk_add_hw_provider; + } + + return; + +err_of_clk_add_hw_provider: + clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(ops); +err_kmemdup: + kfree(socfpga_clk); } -- GitLab From 6e83bd71c0cf196b52e3cb69c26b0cc579fe4c6c Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:11 +0100 Subject: [PATCH 1032/5631] clk: socfpga: arria10: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The indentation of the init function parameters has been aligned to match open parenthesis as suggested by checkpatch. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-5-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-gate-a10.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/clk/socfpga/clk-gate-a10.c b/drivers/clk/socfpga/clk-gate-a10.c index 7cdf2f07c79b..06f129c160bc 100644 --- a/drivers/clk/socfpga/clk-gate-a10.c +++ b/drivers/clk/socfpga/clk-gate-a10.c @@ -40,7 +40,7 @@ static struct clk_ops gateclk_ops = { }; static void __init __socfpga_gate_init(struct device_node *node, - const struct clk_ops *ops) + const struct clk_ops *ops) { u32 clk_gate[2]; u32 div_reg[3]; @@ -94,13 +94,25 @@ static void __init __socfpga_gate_init(struct device_node *node, socfpga_clk->hw.hw.init = &init; hw_clk = &socfpga_clk->hw.hw; - if (clk_hw_register(NULL, hw_clk)) { - kfree(socfpga_clk); - return; + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; } - rc = of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); - if (WARN_ON(rc)) - return; + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { + pr_err("Could not register clock provider for node:%s\n", + clk_name); + goto err_of_clk_add_hw_provider; + } + + return; + +err_of_clk_add_hw_provider: + clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(socfpga_clk); } void __init socfpga_a10_gate_init(struct device_node *node) -- GitLab From 00720a904877bb7e5f16e5ca409391bdd64ea5c4 Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:12 +0100 Subject: [PATCH 1033/5631] clk: socfpga: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The return type of the init function has been changed to void since the return value was not used, and the indentation of the parameters has been aligned to match open parenthesis, as suggested by checkpatch. The err variable has been renamed rc for consistency. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-6-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-pll.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c index 127cc849c5ee..9dcc1b2d2cc0 100644 --- a/drivers/clk/socfpga/clk-pll.c +++ b/drivers/clk/socfpga/clk-pll.c @@ -70,8 +70,8 @@ static const struct clk_ops clk_pll_ops = { .get_parent = clk_pll_get_parent, }; -static __init struct clk_hw *__socfpga_pll_init(struct device_node *node, - const struct clk_ops *ops) +static void __init __socfpga_pll_init(struct device_node *node, + const struct clk_ops *ops) { u32 reg; struct clk_hw *hw_clk; @@ -80,13 +80,13 @@ static __init struct clk_hw *__socfpga_pll_init(struct device_node *node, const char *parent_name[SOCFPGA_MAX_PARENTS]; struct clk_init_data init; struct device_node *clkmgr_np; - int err; + int rc; of_property_read_u32(node, "reg", ®); pll_clk = kzalloc(sizeof(*pll_clk), GFP_KERNEL); if (WARN_ON(!pll_clk)) - return NULL; + return; clkmgr_np = of_find_compatible_node(NULL, NULL, "altr,clk-mgr"); clk_mgr_base_addr = of_iomap(clkmgr_np, 0); @@ -108,13 +108,25 @@ static __init struct clk_hw *__socfpga_pll_init(struct device_node *node, hw_clk = &pll_clk->hw.hw; - err = clk_hw_register(NULL, hw_clk); - if (err) { - kfree(pll_clk); - return ERR_PTR(err); + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; } - of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); - return hw_clk; + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { + pr_err("Could not register clock provider for node:%s\n", + clk_name); + goto err_of_clk_add_hw_provider; + } + + return; + +err_of_clk_add_hw_provider: + clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(pll_clk); } void __init socfpga_pll_init(struct device_node *node) -- GitLab From 3dc6faa3ab0260c1d2058d45f0a93928f917348a Mon Sep 17 00:00:00 2001 From: Marco Pagani Date: Fri, 9 Dec 2022 16:29:13 +0100 Subject: [PATCH 1034/5631] clk: socfpga: arria10: use of_clk_add_hw_provider and improve error handling The function of_clk_add_provider() has been deprecated, so use its suggested replacement of_clk_add_hw_provider() instead. Since of_clk_add_hw_provider() can fail, like of_clk_add_provider(), check its return value and do the error handling. The return type of the init function has been changed to void since the return value was not used, and the indentation of the parameters has been aligned to match open parenthesis, as suggested by checkpatch. Signed-off-by: Marco Pagani Link: https://lore.kernel.org/r/20221209152913.1335068-7-marpagan@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/socfpga/clk-pll-a10.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/drivers/clk/socfpga/clk-pll-a10.c b/drivers/clk/socfpga/clk-pll-a10.c index bee0f7da5b6e..b028f25c658a 100644 --- a/drivers/clk/socfpga/clk-pll-a10.c +++ b/drivers/clk/socfpga/clk-pll-a10.c @@ -63,8 +63,8 @@ static const struct clk_ops clk_pll_ops = { .get_parent = clk_pll_get_parent, }; -static struct clk_hw * __init __socfpga_pll_init(struct device_node *node, - const struct clk_ops *ops) +static void __init __socfpga_pll_init(struct device_node *node, + const struct clk_ops *ops) { u32 reg; struct clk_hw *hw_clk; @@ -73,13 +73,14 @@ static struct clk_hw * __init __socfpga_pll_init(struct device_node *node, const char *parent_name[SOCFGPA_MAX_PARENTS]; struct clk_init_data init; struct device_node *clkmgr_np; + int rc; int i = 0; of_property_read_u32(node, "reg", ®); pll_clk = kzalloc(sizeof(*pll_clk), GFP_KERNEL); if (WARN_ON(!pll_clk)) - return NULL; + return; clkmgr_np = of_find_compatible_node(NULL, NULL, "altr,clk-mgr"); clk_mgr_a10_base_addr = of_iomap(clkmgr_np, 0); @@ -103,12 +104,25 @@ static struct clk_hw * __init __socfpga_pll_init(struct device_node *node, pll_clk->hw.bit_idx = SOCFPGA_PLL_EXT_ENA; hw_clk = &pll_clk->hw.hw; - if (clk_hw_register(NULL, hw_clk)) { - kfree(pll_clk); - return NULL; + rc = clk_hw_register(NULL, hw_clk); + if (rc) { + pr_err("Could not register clock:%s\n", clk_name); + goto err_clk_hw_register; } - of_clk_add_provider(node, of_clk_src_simple_get, hw_clk); - return hw_clk; + + rc = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw_clk); + if (rc) { + pr_err("Could not register clock provider for node:%s\n", + clk_name); + goto err_of_clk_add_hw_provider; + } + + return; + +err_of_clk_add_hw_provider: + clk_hw_unregister(hw_clk); +err_clk_hw_register: + kfree(pll_clk); } void __init socfpga_a10_pll_init(struct device_node *node) -- GitLab From 03b49487130ed907db787dc7b4e39392f077861b Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 7 Mar 2023 13:31:57 +0100 Subject: [PATCH 1035/5631] clk: qcom: gcc-sm6375: Update the .pwrsts for usb gdsc The USB controller on sm6375 doesn't retain its state when the system goes into low power state and the GDSCs are turned off. This can be observed by the USB connection not coming back alive after putting the device into suspend, essentially breaking USB. Work around this by updating the .pwrsts for the USB GDSCs so they only transition to retention state in low power. This change should be reverted when a proper suspend sequence is implemented in the USB drivers. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307123159.3797551-1-konrad.dybcio@linaro.org --- drivers/clk/qcom/gcc-sm6375.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-sm6375.c b/drivers/clk/qcom/gcc-sm6375.c index ad3c4833990d..417a0fd242ec 100644 --- a/drivers/clk/qcom/gcc-sm6375.c +++ b/drivers/clk/qcom/gcc-sm6375.c @@ -3534,7 +3534,8 @@ static struct gdsc usb30_prim_gdsc = { .pd = { .name = "usb30_prim_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + /* TODO: Change to OFF_ON when USB drivers get proper suspend support */ + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc ufs_phy_gdsc = { -- GitLab From 78a2f2a04fb5f1182f03f2ed1f9433982f66346f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 7 Mar 2023 13:31:58 +0100 Subject: [PATCH 1036/5631] clk: qcom: gcc-msm8996: Update the .pwrsts for usb gdsc The USB controller on MSM8996 doesn't retain its state when the system goes into low power state and the GDSCs are turned off. This can be observed by the USB connection not coming back alive after putting the device into suspend, essentially breaking USB. Work around this by updating the .pwrsts for the USB GDSCs so they only transition to retention state in low power. This change should be reverted when a proper suspend sequence is implemented in the USB drivers. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307123159.3797551-2-konrad.dybcio@linaro.org --- drivers/clk/qcom/gcc-msm8996.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index e16163706735..5e44d1bcca9e 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -3455,7 +3455,8 @@ static struct gdsc usb30_gdsc = { .pd = { .name = "usb30", }, - .pwrsts = PWRSTS_OFF_ON, + /* TODO: Change to OFF_ON when USB drivers get proper suspend support */ + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie0_gdsc = { -- GitLab From 83fddbcc833766d02d8bcdb3a3866f0c20b02349 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 7 Mar 2023 13:31:59 +0100 Subject: [PATCH 1037/5631] clk: qcom: gcc-msm8998: Update the .pwrsts for usb gdsc The USB controller on msm8998 doesn't retain its state when the system goes into low power state and the GDSCs are turned off. This can be observed by the USB connection not coming back alive after putting the device into suspend, essentially breaking USB. Work around this by updating the .pwrsts for the USB GDSCs so they only transition to retention state in low power. This change should be reverted when a proper suspend sequence is implemented in the USB drivers. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230307123159.3797551-3-konrad.dybcio@linaro.org --- drivers/clk/qcom/gcc-msm8998.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/gcc-msm8998.c b/drivers/clk/qcom/gcc-msm8998.c index 908e996841c2..be024f8093c5 100644 --- a/drivers/clk/qcom/gcc-msm8998.c +++ b/drivers/clk/qcom/gcc-msm8998.c @@ -2898,7 +2898,8 @@ static struct gdsc usb_30_gdsc = { .pd = { .name = "usb_30_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + /* TODO: Change to OFF_ON when USB drivers get proper suspend support */ + .pwrsts = PWRSTS_RET_ON, .flags = VOTABLE, }; -- GitLab From cb4a0bec0bb982991b27d6826f3372890cebb8ab Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:28:43 +0100 Subject: [PATCH 1038/5631] EDAC/sysfs: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Borislav Petkov Cc: Tony Luck Cc: James Morse Cc: Mauro Carvalho Chehab Cc: Robert Richter Cc: linux-edac@vger.kernel.org Link: https://lore.kernel.org/r/20230313182918.1312597-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/edac/edac_device_sysfs.c | 16 +++++++++------- drivers/edac/edac_pci_sysfs.c | 14 +++++++++----- 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c index ac678b4a21fc..010c26be5846 100644 --- a/drivers/edac/edac_device_sysfs.c +++ b/drivers/edac/edac_device_sysfs.c @@ -228,8 +228,9 @@ static struct kobj_type ktype_device_ctrl = { */ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev) { + struct device *dev_root; struct bus_type *edac_subsys; - int err; + int err = -ENODEV; edac_dbg(1, "\n"); @@ -247,15 +248,16 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev) */ edac_dev->owner = THIS_MODULE; - if (!try_module_get(edac_dev->owner)) { - err = -ENODEV; + if (!try_module_get(edac_dev->owner)) goto err_out; - } /* register */ - err = kobject_init_and_add(&edac_dev->kobj, &ktype_device_ctrl, - &edac_subsys->dev_root->kobj, - "%s", edac_dev->name); + dev_root = bus_get_dev_root(edac_subsys); + if (dev_root) { + err = kobject_init_and_add(&edac_dev->kobj, &ktype_device_ctrl, + &dev_root->kobj, "%s", edac_dev->name); + put_device(dev_root); + } if (err) { edac_dbg(1, "Failed to register '.../edac/%s'\n", edac_dev->name); diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c index 888d5728ecef..287cc51dbc86 100644 --- a/drivers/edac/edac_pci_sysfs.c +++ b/drivers/edac/edac_pci_sysfs.c @@ -337,8 +337,9 @@ static struct kobj_type ktype_edac_pci_main_kobj = { */ static int edac_pci_main_kobj_setup(void) { - int err; + int err = -ENODEV; struct bus_type *edac_subsys; + struct device *dev_root; edac_dbg(0, "\n"); @@ -357,7 +358,6 @@ static int edac_pci_main_kobj_setup(void) */ if (!try_module_get(THIS_MODULE)) { edac_dbg(1, "try_module_get() failed\n"); - err = -ENODEV; goto decrement_count_fail; } @@ -369,9 +369,13 @@ static int edac_pci_main_kobj_setup(void) } /* Instanstiate the pci object */ - err = kobject_init_and_add(edac_pci_top_main_kobj, - &ktype_edac_pci_main_kobj, - &edac_subsys->dev_root->kobj, "pci"); + dev_root = bus_get_dev_root(edac_subsys); + if (dev_root) { + err = kobject_init_and_add(edac_pci_top_main_kobj, + &ktype_edac_pci_main_kobj, + &dev_root->kobj, "pci"); + put_device(dev_root); + } if (err) { edac_dbg(1, "Failed to register '.../edac/pci'\n"); goto kobject_init_and_add_fail; -- GitLab From dc467faa2305cca067d24315c71d4e12d4e2d679 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Sun, 19 Mar 2023 09:45:20 -0700 Subject: [PATCH 1039/5631] Staging: greybus: Fix lines ending with '(' The coding style used to limit lines to 80 characters, which led to splitting of these function headers into multiple lines and ends the first line with a '('. Such splits causes checks reported by the checkpatch. Place the function parameters of each function immediately after '(' in a single line to align the function headers. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230319164520.GA125117@sumitra.com Signed-off-by: Greg Kroah-Hartman --- .../staging/greybus/audio_manager_module.c | 40 +++++++++---------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/drivers/staging/greybus/audio_manager_module.c b/drivers/staging/greybus/audio_manager_module.c index 0a0f0a394c84..81b4ba607a0e 100644 --- a/drivers/staging/greybus/audio_manager_module.c +++ b/drivers/staging/greybus/audio_manager_module.c @@ -70,9 +70,8 @@ static void gb_audio_module_release(struct kobject *kobj) kfree(module); } -static ssize_t gb_audio_module_name_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_name_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, char *buf) { return sprintf(buf, "%s", module->desc.name); } @@ -80,9 +79,8 @@ static ssize_t gb_audio_module_name_show( static struct gb_audio_manager_module_attribute gb_audio_module_name_attribute = __ATTR(name, 0664, gb_audio_module_name_show, NULL); -static ssize_t gb_audio_module_vid_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_vid_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, char *buf) { return sprintf(buf, "%d", module->desc.vid); } @@ -90,9 +88,8 @@ static ssize_t gb_audio_module_vid_show( static struct gb_audio_manager_module_attribute gb_audio_module_vid_attribute = __ATTR(vid, 0664, gb_audio_module_vid_show, NULL); -static ssize_t gb_audio_module_pid_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_pid_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, char *buf) { return sprintf(buf, "%d", module->desc.pid); } @@ -100,9 +97,9 @@ static ssize_t gb_audio_module_pid_show( static struct gb_audio_manager_module_attribute gb_audio_module_pid_attribute = __ATTR(pid, 0664, gb_audio_module_pid_show, NULL); -static ssize_t gb_audio_module_intf_id_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_intf_id_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, + char *buf) { return sprintf(buf, "%d", module->desc.intf_id); } @@ -111,9 +108,9 @@ static struct gb_audio_manager_module_attribute gb_audio_module_intf_id_attribute = __ATTR(intf_id, 0664, gb_audio_module_intf_id_show, NULL); -static ssize_t gb_audio_module_ip_devices_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_ip_devices_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, + char *buf) { return sprintf(buf, "0x%X", module->desc.ip_devices); } @@ -122,9 +119,9 @@ static struct gb_audio_manager_module_attribute gb_audio_module_ip_devices_attribute = __ATTR(ip_devices, 0664, gb_audio_module_ip_devices_show, NULL); -static ssize_t gb_audio_module_op_devices_show( - struct gb_audio_manager_module *module, - struct gb_audio_manager_module_attribute *attr, char *buf) +static ssize_t gb_audio_module_op_devices_show(struct gb_audio_manager_module *module, + struct gb_audio_manager_module_attribute *attr, + char *buf) { return sprintf(buf, "0x%X", module->desc.op_devices); } @@ -181,10 +178,9 @@ static void send_add_uevent(struct gb_audio_manager_module *module) kobject_uevent_env(&module->kobj, KOBJ_ADD, envp); } -int gb_audio_manager_module_create( - struct gb_audio_manager_module **module, - struct kset *manager_kset, - int id, struct gb_audio_manager_module_descriptor *desc) +int gb_audio_manager_module_create(struct gb_audio_manager_module **module, + struct kset *manager_kset, + int id, struct gb_audio_manager_module_descriptor *desc) { int err; struct gb_audio_manager_module *m; -- GitLab From ba32601bdb189c13e5fab0f060d67a46805d6e5f Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Mon, 20 Mar 2023 17:10:34 +0500 Subject: [PATCH 1040/5631] staging: greybus: fix line ending with '(' Splitting function header to multiple lines because of 80 characters per line limit, results in ending the function call line with '('. This leads to CHECK reported by checkpatch.pl Move the first parameter right after the '(' in the function call line. Align the rest of the parameters to the opening parenthesis. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZBhNOkQbG4ygNF98@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/audio_topology.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/greybus/audio_topology.c b/drivers/staging/greybus/audio_topology.c index 62d7674852be..08e6a807c132 100644 --- a/drivers/staging/greybus/audio_topology.c +++ b/drivers/staging/greybus/audio_topology.c @@ -24,9 +24,8 @@ struct gbaudio_ctl_pvt { struct gb_audio_ctl_elem_info *info; }; -static struct gbaudio_module_info *find_gb_module( - struct gbaudio_codec_info *codec, - char const *name) +static struct gbaudio_module_info *find_gb_module(struct gbaudio_codec_info *codec, + char const *name) { int dev_id; char begin[NAME_SIZE]; -- GitLab From d91e15a21d4b3823ce93a42b05f0d171689f4e6a Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 14 Mar 2023 10:48:18 -0400 Subject: [PATCH 1041/5631] sched/topology: Make sched_energy_mutex,update static smatch reports kernel/sched/topology.c:212:1: warning: symbol 'sched_energy_mutex' was not declared. Should it be static? kernel/sched/topology.c:213:6: warning: symbol 'sched_energy_update' was not declared. Should it be static? These variables are only used in topology.c, so should be static Signed-off-by: Tom Rix Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Link: https://lore.kernel.org/r/20230314144818.1453523-1-trix@redhat.com --- kernel/sched/topology.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 051aaf65c749..6682535e37c8 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -209,8 +209,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) DEFINE_STATIC_KEY_FALSE(sched_energy_present); static unsigned int sysctl_sched_energy_aware = 1; -DEFINE_MUTEX(sched_energy_mutex); -bool sched_energy_update; +static DEFINE_MUTEX(sched_energy_mutex); +static bool sched_energy_update; void rebuild_sched_domains_energy(void) { -- GitLab From 530bfad1d53d103f98cec66a3e491a36d397884d Mon Sep 17 00:00:00 2001 From: Hao Jia Date: Thu, 16 Mar 2023 16:18:06 +0800 Subject: [PATCH 1042/5631] sched/core: Avoid selecting the task that is throttled to run when core-sched enable When {rt, cfs}_rq or dl task is throttled, since cookied tasks are not dequeued from the core tree, So sched_core_find() and sched_core_next() may return throttled task, which may cause throttled task to run on the CPU. So we add checks in sched_core_find() and sched_core_next() to make sure that the return is a runnable task that is not throttled. Co-developed-by: Cruz Zhao Signed-off-by: Cruz Zhao Signed-off-by: Hao Jia Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230316081806.69544-1-jiahao.os@bytedance.com --- kernel/sched/core.c | 60 ++++++++++++++++++++++++++++------------- kernel/sched/deadline.c | 10 +++++++ kernel/sched/fair.c | 16 +++++++++++ kernel/sched/rt.c | 19 +++++++++++++ kernel/sched/sched.h | 4 +++ 5 files changed, 90 insertions(+), 19 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 488655f2319f..9140a33bcc97 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -261,36 +261,51 @@ void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) resched_curr(rq); } -/* - * Find left-most (aka, highest priority) task matching @cookie. - */ -static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie) +static int sched_task_is_throttled(struct task_struct *p, int cpu) { - struct rb_node *node; - - node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp); - /* - * The idle task always matches any cookie! - */ - if (!node) - return idle_sched_class.pick_task(rq); + if (p->sched_class->task_is_throttled) + return p->sched_class->task_is_throttled(p, cpu); - return __node_2_sc(node); + return 0; } static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie) { struct rb_node *node = &p->core_node; + int cpu = task_cpu(p); + + do { + node = rb_next(node); + if (!node) + return NULL; + + p = __node_2_sc(node); + if (p->core_cookie != cookie) + return NULL; + + } while (sched_task_is_throttled(p, cpu)); + + return p; +} + +/* + * Find left-most (aka, highest priority) and unthrottled task matching @cookie. + * If no suitable task is found, NULL will be returned. + */ +static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie) +{ + struct task_struct *p; + struct rb_node *node; - node = rb_next(node); + node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp); if (!node) return NULL; - p = container_of(node, struct task_struct, core_node); - if (p->core_cookie != cookie) - return NULL; + p = __node_2_sc(node); + if (!sched_task_is_throttled(p, rq->cpu)) + return p; - return p; + return sched_core_next(p, cookie); } /* @@ -6236,7 +6251,7 @@ static bool try_steal_cookie(int this, int that) goto unlock; p = sched_core_find(src, cookie); - if (p == src->idle) + if (!p) goto unlock; do { @@ -6248,6 +6263,13 @@ static bool try_steal_cookie(int this, int that) if (p->core_occupation > dst->idle->core_occupation) goto next; + /* + * sched_core_find() and sched_core_next() will ensure that task @p + * is not throttled now, we also need to check whether the runqueue + * of the destination CPU is being throttled. + */ + if (sched_task_is_throttled(p, this)) + goto next; deactivate_task(src, p, 0); set_task_cpu(p, this); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 71b24371a6f7..4cc7e1ca066d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2704,6 +2704,13 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, #endif } +#ifdef CONFIG_SCHED_CORE +static int task_is_throttled_dl(struct task_struct *p, int cpu) +{ + return p->dl.dl_throttled; +} +#endif + DEFINE_SCHED_CLASS(dl) = { .enqueue_task = enqueue_task_dl, @@ -2736,6 +2743,9 @@ DEFINE_SCHED_CLASS(dl) = { .switched_to = switched_to_dl, .update_curr = update_curr_dl, +#ifdef CONFIG_SCHED_CORE + .task_is_throttled = task_is_throttled_dl, +#endif }; /* Used for dl_bw check and update, used under sched_rt_handler()::mutex */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7a1b1f855b96..b572367249f0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11933,6 +11933,18 @@ bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b, return delta > 0; } + +static int task_is_throttled_fair(struct task_struct *p, int cpu) +{ + struct cfs_rq *cfs_rq; + +#ifdef CONFIG_FAIR_GROUP_SCHED + cfs_rq = task_group(p)->cfs_rq[cpu]; +#else + cfs_rq = &cpu_rq(cpu)->cfs; +#endif + return throttled_hierarchy(cfs_rq); +} #else static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {} #endif @@ -12559,6 +12571,10 @@ DEFINE_SCHED_CLASS(fair) = { .task_change_group = task_change_group_fair, #endif +#ifdef CONFIG_SCHED_CORE + .task_is_throttled = task_is_throttled_fair, +#endif + #ifdef CONFIG_UCLAMP_TASK .uclamp_enabled = 1, #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 0a11f44adee5..9d67dfbf1000 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2677,6 +2677,21 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) return 0; } +#ifdef CONFIG_SCHED_CORE +static int task_is_throttled_rt(struct task_struct *p, int cpu) +{ + struct rt_rq *rt_rq; + +#ifdef CONFIG_RT_GROUP_SCHED + rt_rq = task_group(p)->rt_rq[cpu]; +#else + rt_rq = &cpu_rq(cpu)->rt; +#endif + + return rt_rq_throttled(rt_rq); +} +#endif + DEFINE_SCHED_CLASS(rt) = { .enqueue_task = enqueue_task_rt, @@ -2710,6 +2725,10 @@ DEFINE_SCHED_CLASS(rt) = { .update_curr = update_curr_rt, +#ifdef CONFIG_SCHED_CORE + .task_is_throttled = task_is_throttled_rt, +#endif + #ifdef CONFIG_UCLAMP_TASK .uclamp_enabled = 1, #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3e8df6d31c1e..060616944d7a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2224,6 +2224,10 @@ struct sched_class { #ifdef CONFIG_FAIR_GROUP_SCHED void (*task_change_group)(struct task_struct *p); #endif + +#ifdef CONFIG_SCHED_CORE + int (*task_is_throttled)(struct task_struct *p, int cpu); +#endif }; static inline void put_prev_task(struct rq *rq, struct task_struct *prev) -- GitLab From eff6c8ce8d4d7faef75f66614dd20bb50595d261 Mon Sep 17 00:00:00 2001 From: wuchi Date: Tue, 21 Mar 2023 14:44:59 +0800 Subject: [PATCH 1043/5631] sched/core: Reduce cost of sched_move_task when config autogroup Some sched_move_task calls are useless because that task_struct->sched_task_group maybe not changed (equals task_group of cpu_cgroup) when system enable autogroup. So do some checks in sched_move_task. sched_move_task eg: task A belongs to cpu_cgroup0 and autogroup0, it will always belong to cpu_cgroup0 when do_exit. So there is no need to do {de|en}queue. The call graph is as follow. do_exit sched_autogroup_exit_task sched_move_task dequeue_task sched_change_group A.sched_task_group = sched_get_task_group (=cpu_cgroup0) enqueue_task Performance results: =========================== 1. env cpu: bogomips=4600.00 kernel: 6.3.0-rc3 cpu_cgroup: 6:cpu,cpuacct:/user.slice 2. cmds do_exit script: for i in {0..10000}; do sleep 0 & done wait Run the above script, then use the following bpftrace cmd to get the cost of sched_move_task: bpftrace -e 'k:sched_move_task { @ts[tid] = nsecs; } kr:sched_move_task /@ts[tid]/ { @ns += nsecs - @ts[tid]; delete(@ts[tid]); }' 3. cost time(ns): without patch: 43528033 with patch: 18541416 diff:-24986617 -57.4% As the result show, the patch will save 57.4% in the scenario. Signed-off-by: wuchi Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230321064459.39421-1-wuchi.zero@gmail.com --- kernel/sched/core.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9140a33bcc97..5ddd9610be56 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -10351,7 +10351,7 @@ void sched_release_group(struct task_group *tg) spin_unlock_irqrestore(&task_group_lock, flags); } -static void sched_change_group(struct task_struct *tsk) +static struct task_group *sched_get_task_group(struct task_struct *tsk) { struct task_group *tg; @@ -10363,7 +10363,13 @@ static void sched_change_group(struct task_struct *tsk) tg = container_of(task_css_check(tsk, cpu_cgrp_id, true), struct task_group, css); tg = autogroup_task_group(tsk, tg); - tsk->sched_task_group = tg; + + return tg; +} + +static void sched_change_group(struct task_struct *tsk, struct task_group *group) +{ + tsk->sched_task_group = group; #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_change_group) @@ -10384,10 +10390,19 @@ void sched_move_task(struct task_struct *tsk) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; + struct task_group *group; struct rq_flags rf; struct rq *rq; rq = task_rq_lock(tsk, &rf); + /* + * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous + * group changes. + */ + group = sched_get_task_group(tsk); + if (group == tsk->sched_task_group) + goto unlock; + update_rq_clock(rq); running = task_current(rq, tsk); @@ -10398,7 +10413,7 @@ void sched_move_task(struct task_struct *tsk) if (running) put_prev_task(rq, tsk); - sched_change_group(tsk); + sched_change_group(tsk, group); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -10412,6 +10427,7 @@ void sched_move_task(struct task_struct *tsk) resched_curr(rq); } +unlock: task_rq_unlock(rq, tsk, &rf); } -- GitLab From 41abdba9374734b743019fc1cc05e3225c82ba6b Mon Sep 17 00:00:00 2001 From: Shrikanth Hegde Date: Fri, 24 Feb 2023 00:21:53 +0530 Subject: [PATCH 1044/5631] sched: Interleave cfs bandwidth timers for improved single thread performance at low utilization CPU cfs bandwidth controller uses hrtimer. Currently there is no initial value set. Hence all period timers would align at expiry. This happens when there are multiple CPU cgroup's. There is a performance gain that can be achieved here if the timers are interleaved when the utilization of each CPU cgroup is low and total utilization of all the CPU cgroup's is less than 50%. If the timers are interleaved, then the unthrottled cgroup can run freely without many context switches and can also benefit from SMT Folding. This effect will be further amplified in SPLPAR environment. This commit adds a random offset after initializing each hrtimer. This would result in interleaving the timers at expiry, which helps in achieving the said performance gain. This was tested on powerpc platform with 8 core SMT=8. Socket power was measured when the workload. Benchmarked the stress-ng with power information. Throughput oriented benchmarks show significant gain up to 25% while power consumption increases up to 15%. Workload: stress-ng --cpu=32 --cpu-ops=50000. 1CG - 1 cgroup is running. 2CG - 2 cgroups are running together. Time taken to complete stress-ng in seconds and power is in watts. each cgroup is throttled at 25% with 100ms as the period value. 6.2-rc6 | with patch 8 core 1CG power 2CG power | 1CG power 2 CG power 27.5 80.6 40 90 | 27.3 82 32.3 104 27.5 81 40.2 91 | 27.5 81 38.7 96 27.7 80 40.1 89 | 27.6 80 29.7 106 27.7 80.1 40.3 94 | 27.6 80 31.5 105 Latency might be affected by this change. That could happen if the CPU was in a deep idle state which is possible if we interleave the timers. Used schbench for measuring the latency. Each cgroup is throttled at 25% with period value is set to 100ms. Numbers are when both the cgroups are running simultaneously. Latency values don't degrade much. Some improvement is seen in tail latencies. 6.2-rc6 with patch Groups: 16 50.0th: 39.5 42.5 75.0th: 924.0 922.0 90.0th: 972.0 968.0 95.0th: 1005.5 994.0 99.0th: 4166.0 2287.0 99.5th: 7314.0 7448.0 99.9th: 15024.0 13600.0 Groups: 32 50.0th: 819.0 463.0 75.0th: 1596.0 918.0 90.0th: 5992.0 1281.5 95.0th: 13184.0 2765.0 99.0th: 21792.0 14240.0 99.5th: 25696.0 18920.0 99.9th: 33280.0 35776.0 Groups: 64 50.0th: 4806.0 3440.0 75.0th: 31136.0 33664.0 90.0th: 54144.0 58752.0 95.0th: 66176.0 67200.0 99.0th: 84736.0 91520.0 99.5th: 97408.0 114048.0 99.9th: 136448.0 140032.0 Initial RFC PATCH, discussions and details on the problem: Link1: https://lore.kernel.org/lkml/5ae3cb09-8c9a-11e8-75a7-cc774d9bc283@linux.vnet.ibm.com/ Link2: https://lore.kernel.org/lkml/9c57c92c-3e0c-b8c5-4be9-8f4df344a347@linux.vnet.ibm.com/ Suggested-by: Peter Zijlstra Suggested-by: Thomas Gleixner Signed-off-by: Shrikanth Hegde Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ben Segall Reviewed-by: Vincent Guittot Link: https://lore.kernel.org/r/20230223185153.1499710-1-sshegde@linux.vnet.ibm.com --- kernel/sched/fair.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b572367249f0..bc358dc4faeb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5923,6 +5923,10 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); cfs_b->period_timer.function = sched_cfs_period_timer; + + /* Add a random offset so that timers interleave */ + hrtimer_set_expires(&cfs_b->period_timer, + get_random_u32_below(cfs_b->period)); hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; cfs_b->slack_started = false; -- GitLab From 72a456de903389aa9d484ee0127af3352f156e1c Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Fri, 17 Mar 2023 20:13:13 +0100 Subject: [PATCH 1045/5631] staging: rtl8192e: Remove unused variable rtl819XAGCTAB_Array Remove unused variable rtl819XAGCTAB_Array. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0733800b195d4f63cce2ef2ac114943c8c30f587.1679077522.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 6723fcce8954..fd34756e450f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -9,8 +9,6 @@ #define MAX_DOZE_WAITING_TIMES_9x 64 -extern u32 rtl819XAGCTAB_Array[]; - enum hw90_block { HW90_BLOCK_MAC = 0, HW90_BLOCK_PHY0 = 1, -- GitLab From 8f51a66a629b67a11250f555b89aa8d91137ed94 Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Mon, 20 Mar 2023 12:33:56 +0200 Subject: [PATCH 1046/5631] staging: most: use inline functions for to_hdm Convert `to_hdm` macro into a static inline function. it is not great to have macro that use `container_of` macro, because from looking at the definition one cannot tell what type it applies to. One can get the same benefit from an efficiency point of view by making an inline function. Suggested-by: Julia Lawall Signed-off-by: Menna Mahmoud Link: https://lore.kernel.org/r/20230320103356.6498-1-eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/i2c/i2c.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/staging/most/i2c/i2c.c b/drivers/staging/most/i2c/i2c.c index df53a4c4f850..4e85e681922f 100644 --- a/drivers/staging/most/i2c/i2c.c +++ b/drivers/staging/most/i2c/i2c.c @@ -44,7 +44,10 @@ struct hdm_i2c { char name[64]; }; -#define to_hdm(iface) container_of(iface, struct hdm_i2c, most_iface) +static inline struct hdm_i2c *to_hdm(struct most_interface *iface) +{ + return container_of(iface, struct hdm_i2c, most_iface); +} static irqreturn_t most_irq_handler(int, void *); static void pending_rx_work(struct work_struct *); -- GitLab From c388adce927c302dc740a550e79236f4dc9864b7 Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Mon, 20 Mar 2023 23:22:39 +0200 Subject: [PATCH 1047/5631] staging: most: define iface_to_hdm as an inline function Convert `iface_to_hdm` macro into a static inline function. it is not great to have macro that use `container_of` macro, because from looking at the definition one cannot tell what type it applies to. One can get the same benefit from an efficiency point of view by making an inline function. Suggested-by: Julia Lawall Signed-off-by: Menna Mahmoud Link: https://lore.kernel.org/r/20230320212239.22452-1-eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/dim2/dim2.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/staging/most/dim2/dim2.c b/drivers/staging/most/dim2/dim2.c index b8bd01ca1f11..21d1c9f24c3d 100644 --- a/drivers/staging/most/dim2/dim2.c +++ b/drivers/staging/most/dim2/dim2.c @@ -108,7 +108,10 @@ struct dim2_platform_data { u8 fcnt; }; -#define iface_to_hdm(iface) container_of(iface, struct dim2_hdm, most_iface) +static inline struct dim2_hdm *iface_to_hdm(struct most_interface *iface) +{ + return container_of(iface, struct dim2_hdm, most_iface); +} /* Macro to identify a network status message */ #define PACKET_IS_NET_INFO(p) \ -- GitLab From 288dee556536f07f51df4b0d265c83be73991fb1 Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Sun, 19 Mar 2023 22:11:34 +0200 Subject: [PATCH 1048/5631] staging: rtl8723bs: use inline functions for dvobj_to_dev Convert `dvobj_to_dev` macro into a static inline function. it is not great to have macro that use `container_of` macro, because from looking at the definition one cannot tell what type it applies to. One can get the same benefit from an efficiency point of view by making an inline function. Suggested-by: Julia Lawall Signed-off-by: Menna Mahmoud Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230319201134.253839-1-eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/include/drv_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8723bs/include/drv_types.h b/drivers/staging/rtl8723bs/include/drv_types.h index 82159e1c7f9b..ea6bb44c5e1d 100644 --- a/drivers/staging/rtl8723bs/include/drv_types.h +++ b/drivers/staging/rtl8723bs/include/drv_types.h @@ -305,7 +305,11 @@ struct sdio_data intf_data; }; #define dvobj_to_pwrctl(dvobj) (&(dvobj->pwrctl_priv)) -#define pwrctl_to_dvobj(pwrctl) container_of(pwrctl, struct dvobj_priv, pwrctl_priv) + +static inline struct dvobj_priv *pwrctl_to_dvobj(struct pwrctrl_priv *pwrctl_priv) +{ + return container_of(pwrctl_priv, struct dvobj_priv, pwrctl_priv); +} static inline struct device *dvobj_to_dev(struct dvobj_priv *dvobj) { -- GitLab From 7045b31e1b8f6a3ebd3023d69834666e48a2eb9c Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 21 Mar 2023 15:01:27 -0400 Subject: [PATCH 1049/5631] staging: rts5208: remove unused xd_check_err_code function clang with W=1 reports drivers/staging/rts5208/xd.c:34:19: error: unused function 'xd_check_err_code' [-Werror,-Wunused-function] static inline int xd_check_err_code(struct rtsx_chip *chip, u8 err_code) ^ This function is not used, so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230321190127.1827703-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rts5208/xd.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/staging/rts5208/xd.c b/drivers/staging/rts5208/xd.c index 42cab93982c0..c0af378ada71 100644 --- a/drivers/staging/rts5208/xd.c +++ b/drivers/staging/rts5208/xd.c @@ -31,13 +31,6 @@ static inline void xd_set_err_code(struct rtsx_chip *chip, u8 err_code) xd_card->err_code = err_code; } -static inline int xd_check_err_code(struct rtsx_chip *chip, u8 err_code) -{ - struct xd_info *xd_card = &chip->xd_card; - - return (xd_card->err_code == err_code); -} - static int xd_set_init_para(struct rtsx_chip *chip) { struct xd_info *xd_card = &chip->xd_card; -- GitLab From 1bd51241bde49f134d3631ebbcc3d5ce4f8b143a Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Tue, 21 Mar 2023 22:40:51 -0700 Subject: [PATCH 1050/5631] Staging: nvec: Remove macro definition to_nvec_led Remove definition 'to_nvec_led' because it is only used once. Rewrite the code directly in the calling function 'nvec_led_brightness_set'. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230322054051.GA150453@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/nvec_paz00.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/staging/nvec/nvec_paz00.c b/drivers/staging/nvec/nvec_paz00.c index 8b4da95081c8..55d59840fca4 100644 --- a/drivers/staging/nvec/nvec_paz00.c +++ b/drivers/staging/nvec/nvec_paz00.c @@ -14,9 +14,6 @@ #include #include "nvec.h" -#define to_nvec_led(led_cdev) \ - container_of(led_cdev, struct nvec_led, cdev) - #define NVEC_LED_REQ {'\x0d', '\x10', '\x45', '\x10', '\x00'} #define NVEC_LED_MAX 8 @@ -29,7 +26,7 @@ struct nvec_led { static void nvec_led_brightness_set(struct led_classdev *led_cdev, enum led_brightness value) { - struct nvec_led *led = to_nvec_led(led_cdev); + struct nvec_led *led = container_of(led_cdev, struct nvec_led, cdev); unsigned char buf[] = NVEC_LED_REQ; buf[4] = value; -- GitLab From de19ec778c7a4ee2fe2112126c5d05a10db2d582 Mon Sep 17 00:00:00 2001 From: Cheng Xu Date: Wed, 22 Mar 2023 17:33:17 +0800 Subject: [PATCH 1051/5631] RDMA/erdma: Unify byte ordering APIs usage Replace __be32_to_cpu/__cpu_to_be16 with be32_to_cpu/cpu_to_be16. And use be32_to_cpu_array to copy and swap byte order to hide the loop. Signed-off-by: Cheng Xu Link: https://lore.kernel.org/r/20230322093319.84045-2-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/erdma/erdma_cm.h | 10 +++++----- drivers/infiniband/hw/erdma/erdma_cmdq.c | 12 +++++------- drivers/infiniband/hw/erdma/erdma_cq.c | 2 +- 3 files changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/erdma/erdma_cm.h b/drivers/infiniband/hw/erdma/erdma_cm.h index 8a3f998fec9b..a26d80770188 100644 --- a/drivers/infiniband/hw/erdma/erdma_cm.h +++ b/drivers/infiniband/hw/erdma/erdma_cm.h @@ -33,11 +33,11 @@ struct mpa_rr_params { * MPA request/response Hdr bits & fields */ enum { - MPA_RR_FLAG_MARKERS = __cpu_to_be16(0x8000), - MPA_RR_FLAG_CRC = __cpu_to_be16(0x4000), - MPA_RR_FLAG_REJECT = __cpu_to_be16(0x2000), - MPA_RR_RESERVED = __cpu_to_be16(0x1f00), - MPA_RR_MASK_REVISION = __cpu_to_be16(0x00ff) + MPA_RR_FLAG_MARKERS = cpu_to_be16(0x8000), + MPA_RR_FLAG_CRC = cpu_to_be16(0x4000), + MPA_RR_FLAG_REJECT = cpu_to_be16(0x2000), + MPA_RR_RESERVED = cpu_to_be16(0x1f00), + MPA_RR_MASK_REVISION = cpu_to_be16(0x00ff) }; /* diff --git a/drivers/infiniband/hw/erdma/erdma_cmdq.c b/drivers/infiniband/hw/erdma/erdma_cmdq.c index 6ebfa6989b11..3fd33b85c15a 100644 --- a/drivers/infiniband/hw/erdma/erdma_cmdq.c +++ b/drivers/infiniband/hw/erdma/erdma_cmdq.c @@ -283,7 +283,7 @@ static void *get_next_valid_cmdq_cqe(struct erdma_cmdq *cmdq) __be32 *cqe = get_queue_entry(cmdq->cq.qbuf, cmdq->cq.ci, cmdq->cq.depth, CQE_SHIFT); u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK, - __be32_to_cpu(READ_ONCE(*cqe))); + be32_to_cpu(READ_ONCE(*cqe))); return owner ^ !!(cmdq->cq.ci & cmdq->cq.depth) ? cqe : NULL; } @@ -319,7 +319,6 @@ static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq) __be32 *cqe; u16 ctx_id; u64 *sqe; - int i; cqe = get_next_valid_cmdq_cqe(cmdq); if (!cqe) @@ -328,8 +327,8 @@ static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq) cmdq->cq.ci++; dma_rmb(); - hdr0 = __be32_to_cpu(*cqe); - sqe_idx = __be32_to_cpu(*(cqe + 1)); + hdr0 = be32_to_cpu(*cqe); + sqe_idx = be32_to_cpu(*(cqe + 1)); sqe = get_queue_entry(cmdq->sq.qbuf, sqe_idx, cmdq->sq.depth, SQEBB_SHIFT); @@ -341,9 +340,8 @@ static int erdma_poll_single_cmd_completion(struct erdma_cmdq *cmdq) comp_wait->cmd_status = ERDMA_CMD_STATUS_FINISHED; comp_wait->comp_status = FIELD_GET(ERDMA_CQE_HDR_SYNDROME_MASK, hdr0); cmdq->sq.ci += cmdq->sq.wqebb_cnt; - - for (i = 0; i < 4; i++) - comp_wait->comp_data[i] = __be32_to_cpu(*(cqe + 2 + i)); + /* Copy 16B comp data after cqe hdr to outer */ + be32_to_cpu_array(comp_wait->comp_data, cqe + 2, 4); if (cmdq->use_event) complete(&comp_wait->wait_event); diff --git a/drivers/infiniband/hw/erdma/erdma_cq.c b/drivers/infiniband/hw/erdma/erdma_cq.c index cabd8678b355..7e2bfa6ed86f 100644 --- a/drivers/infiniband/hw/erdma/erdma_cq.c +++ b/drivers/infiniband/hw/erdma/erdma_cq.c @@ -11,7 +11,7 @@ static void *get_next_valid_cqe(struct erdma_cq *cq) __be32 *cqe = get_queue_entry(cq->kern_cq.qbuf, cq->kern_cq.ci, cq->depth, CQE_SHIFT); u32 owner = FIELD_GET(ERDMA_CQE_HDR_OWNER_MASK, - __be32_to_cpu(READ_ONCE(*cqe))); + be32_to_cpu(READ_ONCE(*cqe))); return owner ^ !!(cq->kern_cq.ci & cq->depth) ? cqe : NULL; } -- GitLab From 72769dba6dc0b8ac5793f94a83add4ce0108c44c Mon Sep 17 00:00:00 2001 From: Cheng Xu Date: Wed, 22 Mar 2023 17:33:18 +0800 Subject: [PATCH 1052/5631] RDMA/erdma: Eliminate unnecessary casting of EQ doorbells Using void * to define EQ doorbell pointer can eliminate unnecessary casting when performing assignment. Also rename *db_addr* to *db* for a shorter name. Signed-off-by: Cheng Xu Link: https://lore.kernel.org/r/20230322093319.84045-3-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/erdma/erdma.h | 2 +- drivers/infiniband/hw/erdma/erdma_cmdq.c | 3 +-- drivers/infiniband/hw/erdma/erdma_eq.c | 9 ++++----- 3 files changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/erdma/erdma.h b/drivers/infiniband/hw/erdma/erdma.h index 3d8c11aa23a2..e819e4032490 100644 --- a/drivers/infiniband/hw/erdma/erdma.h +++ b/drivers/infiniband/hw/erdma/erdma.h @@ -32,7 +32,7 @@ struct erdma_eq { atomic64_t event_num; atomic64_t notify_num; - u64 __iomem *db_addr; + void __iomem *db; u64 *db_record; }; diff --git a/drivers/infiniband/hw/erdma/erdma_cmdq.c b/drivers/infiniband/hw/erdma/erdma_cmdq.c index 3fd33b85c15a..eb6aaf7e28f5 100644 --- a/drivers/infiniband/hw/erdma/erdma_cmdq.c +++ b/drivers/infiniband/hw/erdma/erdma_cmdq.c @@ -166,8 +166,7 @@ static int erdma_cmdq_eq_init(struct erdma_dev *dev) spin_lock_init(&eq->lock); atomic64_set(&eq->event_num, 0); - eq->db_addr = - (u64 __iomem *)(dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG); + eq->db = dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG; eq->db_record = (u64 *)(eq->qbuf + buf_size); erdma_reg_write32(dev, ERDMA_REGS_CMDQ_EQ_ADDR_H_REG, diff --git a/drivers/infiniband/hw/erdma/erdma_eq.c b/drivers/infiniband/hw/erdma/erdma_eq.c index ed54130d924b..ea47cb21fdb8 100644 --- a/drivers/infiniband/hw/erdma/erdma_eq.c +++ b/drivers/infiniband/hw/erdma/erdma_eq.c @@ -14,7 +14,7 @@ void notify_eq(struct erdma_eq *eq) FIELD_PREP(ERDMA_EQDB_ARM_MASK, 1); *eq->db_record = db_data; - writeq(db_data, eq->db_addr); + writeq(db_data, eq->db); atomic64_inc(&eq->notify_num); } @@ -98,7 +98,7 @@ int erdma_aeq_init(struct erdma_dev *dev) atomic64_set(&eq->event_num, 0); atomic64_set(&eq->notify_num, 0); - eq->db_addr = (u64 __iomem *)(dev->func_bar + ERDMA_REGS_AEQ_DB_REG); + eq->db = dev->func_bar + ERDMA_REGS_AEQ_DB_REG; eq->db_record = (u64 *)(eq->qbuf + buf_size); erdma_reg_write32(dev, ERDMA_REGS_AEQ_ADDR_H_REG, @@ -243,9 +243,8 @@ static int erdma_ceq_init_one(struct erdma_dev *dev, u16 ceqn) atomic64_set(&eq->notify_num, 0); eq->depth = ERDMA_DEFAULT_EQ_DEPTH; - eq->db_addr = - (u64 __iomem *)(dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG + - (ceqn + 1) * ERDMA_DB_SIZE); + eq->db = dev->func_bar + ERDMA_REGS_CEQ_DB_BASE_REG + + (ceqn + 1) * ERDMA_DB_SIZE; eq->db_record = (u64 *)(eq->qbuf + buf_size); eq->ci = 0; dev->ceqs[ceqn].dev = dev; -- GitLab From 901d9d62416baec3979fd9d768249b8a9e8e56ee Mon Sep 17 00:00:00 2001 From: Cheng Xu Date: Wed, 22 Mar 2023 17:33:19 +0800 Subject: [PATCH 1053/5631] RDMA/erdma: Minor refactor of device init flow After necessary configuration, driver should wait hardware finishing initialization. The wait sets at CMDQ related function though it has nothing to do with CMDQ. Refactor this part to make code cleaner. Signed-off-by: Cheng Xu Link: https://lore.kernel.org/r/20230322093319.84045-4-chengyou@linux.alibaba.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/erdma/erdma_cmdq.c | 27 +--------------- drivers/infiniband/hw/erdma/erdma_main.c | 39 ++++++++++++++++++++---- 2 files changed, 34 insertions(+), 32 deletions(-) diff --git a/drivers/infiniband/hw/erdma/erdma_cmdq.c b/drivers/infiniband/hw/erdma/erdma_cmdq.c index eb6aaf7e28f5..a151a7bdd504 100644 --- a/drivers/infiniband/hw/erdma/erdma_cmdq.c +++ b/drivers/infiniband/hw/erdma/erdma_cmdq.c @@ -182,9 +182,8 @@ static int erdma_cmdq_eq_init(struct erdma_dev *dev) int erdma_cmdq_init(struct erdma_dev *dev) { - int err, i; struct erdma_cmdq *cmdq = &dev->cmdq; - u32 sts, ctrl; + int err; cmdq->max_outstandings = ERDMA_CMDQ_MAX_OUTSTANDING; cmdq->use_event = false; @@ -207,34 +206,10 @@ int erdma_cmdq_init(struct erdma_dev *dev) if (err) goto err_destroy_cq; - ctrl = FIELD_PREP(ERDMA_REG_DEV_CTRL_INIT_MASK, 1); - erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG, ctrl); - - for (i = 0; i < ERDMA_WAIT_DEV_DONE_CNT; i++) { - sts = erdma_reg_read32_filed(dev, ERDMA_REGS_DEV_ST_REG, - ERDMA_REG_DEV_ST_INIT_DONE_MASK); - if (sts) - break; - - msleep(ERDMA_REG_ACCESS_WAIT_MS); - } - - if (i == ERDMA_WAIT_DEV_DONE_CNT) { - dev_err(&dev->pdev->dev, "wait init done failed.\n"); - err = -ETIMEDOUT; - goto err_destroy_eq; - } - set_bit(ERDMA_CMDQ_STATE_OK_BIT, &cmdq->state); return 0; -err_destroy_eq: - dma_free_coherent(&dev->pdev->dev, - (cmdq->eq.depth << EQE_SHIFT) + - ERDMA_EXTRA_BUFFER_SIZE, - cmdq->eq.qbuf, cmdq->eq.qbuf_dma_addr); - err_destroy_cq: dma_free_coherent(&dev->pdev->dev, (cmdq->cq.depth << CQE_SHIFT) + diff --git a/drivers/infiniband/hw/erdma/erdma_main.c b/drivers/infiniband/hw/erdma/erdma_main.c index 5dc31e5df5cb..2c8fd00b0816 100644 --- a/drivers/infiniband/hw/erdma/erdma_main.c +++ b/drivers/infiniband/hw/erdma/erdma_main.c @@ -211,13 +211,36 @@ static int erdma_device_init(struct erdma_dev *dev, struct pci_dev *pdev) return 0; } -static void erdma_device_uninit(struct erdma_dev *dev) +static void erdma_hw_reset(struct erdma_dev *dev) { u32 ctrl = FIELD_PREP(ERDMA_REG_DEV_CTRL_RESET_MASK, 1); erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG, ctrl); } +static int erdma_wait_hw_init_done(struct erdma_dev *dev) +{ + int i; + + erdma_reg_write32(dev, ERDMA_REGS_DEV_CTRL_REG, + FIELD_PREP(ERDMA_REG_DEV_CTRL_INIT_MASK, 1)); + + for (i = 0; i < ERDMA_WAIT_DEV_DONE_CNT; i++) { + if (erdma_reg_read32_filed(dev, ERDMA_REGS_DEV_ST_REG, + ERDMA_REG_DEV_ST_INIT_DONE_MASK)) + break; + + msleep(ERDMA_REG_ACCESS_WAIT_MS); + } + + if (i == ERDMA_WAIT_DEV_DONE_CNT) { + dev_err(&dev->pdev->dev, "wait init done failed.\n"); + return -ETIMEDOUT; + } + + return 0; +} + static const struct pci_device_id erdma_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_ALIBABA, 0x107f) }, {} @@ -293,16 +316,22 @@ static int erdma_probe_dev(struct pci_dev *pdev) if (err) goto err_uninit_aeq; - err = erdma_ceqs_init(dev); + err = erdma_wait_hw_init_done(dev); if (err) goto err_uninit_cmdq; + err = erdma_ceqs_init(dev); + if (err) + goto err_reset_hw; + erdma_finish_cmdq_init(dev); return 0; +err_reset_hw: + erdma_hw_reset(dev); + err_uninit_cmdq: - erdma_device_uninit(dev); erdma_cmdq_destroy(dev); err_uninit_aeq: @@ -334,9 +363,7 @@ static void erdma_remove_dev(struct pci_dev *pdev) struct erdma_dev *dev = pci_get_drvdata(pdev); erdma_ceqs_uninit(dev); - - erdma_device_uninit(dev); - + erdma_hw_reset(dev); erdma_cmdq_destroy(dev); erdma_aeq_destroy(dev); erdma_comm_irq_uninit(dev); -- GitLab From e83ca8cfa286c9fc78b585b0e66df7f542bcbcf2 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 8 Mar 2023 15:24:37 -0800 Subject: [PATCH 1054/5631] KVM: PPC: booke: Mark three local functions "static" Tag a few functions that are local and don't have a previous prototype as "static". No functional change intended. Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303031630.ntvIuYqo-lkp@intel.com Signed-off-by: Sean Christopherson Signed-off-by: Michael Ellerman Link: https://msgid.link/20230308232437.500031-1-seanjc@google.com --- arch/powerpc/kvm/booke.c | 5 +++-- arch/powerpc/kvm/e500mc.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 01adffb24667..ce37d282be6d 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -623,7 +623,7 @@ static void arm_next_watchdog(struct kvm_vcpu *vcpu) spin_unlock_irqrestore(&vcpu->arch.wdt_lock, flags); } -void kvmppc_watchdog_func(struct timer_list *t) +static void kvmppc_watchdog_func(struct timer_list *t) { struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.wdt_timer); u32 tsr, new_tsr; @@ -1946,7 +1946,8 @@ static int kvmppc_booke_add_watchpoint(struct debug_reg *dbg_reg, uint64_t addr, dbg_reg->dbcr0 |= DBCR0_IDM; return 0; } -void kvm_guest_protect_msr(struct kvm_vcpu *vcpu, ulong prot_bitmap, bool set) +static void kvm_guest_protect_msr(struct kvm_vcpu *vcpu, ulong prot_bitmap, + bool set) { /* XXX: Add similar MSR protection for BookE-PR */ #ifdef CONFIG_KVM_BOOKE_HV diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index a309138927ff..d58df71ace58 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -168,7 +168,7 @@ static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu) kvmppc_booke_vcpu_put(vcpu); } -int kvmppc_e500mc_check_processor_compat(void) +static int kvmppc_e500mc_check_processor_compat(void) { int r; -- GitLab From 3a713753d3cb52e4e3039cdb906ef00f0b574219 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:28:50 -0800 Subject: [PATCH 1055/5631] powerpc: Simplify sysctl registration for nmi_wd_lpm_factor_ctl_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Signed-off-by: Michael Ellerman Link: https://msgid.link/20230310232850.3960676-3-mcgrof@kernel.org --- arch/powerpc/platforms/pseries/mobility.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 643d309d1bd0..7564e5d4253b 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -62,18 +62,10 @@ static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { }, {} }; -static struct ctl_table nmi_wd_lpm_factor_sysctl_root[] = { - { - .procname = "kernel", - .mode = 0555, - .child = nmi_wd_lpm_factor_ctl_table, - }, - {} -}; static int __init register_nmi_wd_lpm_factor_sysctl(void) { - register_sysctl_table(nmi_wd_lpm_factor_sysctl_root); + register_sysctl("kernel", nmi_wd_lpm_factor_ctl_table); return 0; } -- GitLab From aa977833dee5de583ac5dbc902e39983ec6302ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 14 Feb 2023 03:25:53 +0000 Subject: [PATCH 1056/5631] iommu: Make kobj_type structure constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230214-kobj_type-iommu-v1-1-e7392834b9d0@weissschuh.net Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 10db680acaed..ace9d418a115 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -739,7 +739,7 @@ static void iommu_group_release(struct kobject *kobj) kfree(group); } -static struct kobj_type iommu_group_ktype = { +static const struct kobj_type iommu_group_ktype = { .sysfs_ops = &iommu_group_sysfs_ops, .release = iommu_group_release, }; -- GitLab From 08632365b274e4be6c43053eba7589c811e6e572 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Fri, 24 Feb 2023 15:07:51 +0000 Subject: [PATCH 1057/5631] iommu/sun50i: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Joerg Roedel Cc: Will Deacon Cc: Chen-Yu Tsai Cc: Jernej Skrabec Cc: Samuel Holland Cc: Philipp Zabel Cc: iommu@lists.linux.dev Cc: linux-arm-kernel@lists.infradead.org Cc: linux-sunxi@lists.linux.dev Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230224150811.80316-8-nick.alcock@oracle.com Signed-off-by: Joerg Roedel --- drivers/iommu/sun50i-iommu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 2d993d0cea7d..74c5cb93e900 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -1076,4 +1076,3 @@ builtin_platform_driver_probe(sun50i_iommu_driver, sun50i_iommu_probe); MODULE_DESCRIPTION("Allwinner H6 IOMMU driver"); MODULE_AUTHOR("Maxime Ripard "); MODULE_AUTHOR("zhuxianbin "); -MODULE_LICENSE("Dual BSD/GPL"); -- GitLab From efe37fda9d52c59ac7b5837a877353486d8cb45c Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Tue, 7 Mar 2023 17:30:29 +0100 Subject: [PATCH 1058/5631] iommu/ipmmu-vmsa: remove R-Car H3 ES1.* handling R-Car H3 ES1.* was only available to an internal development group and needed a lot of quirks and workarounds. These become a maintenance burden now, so our development group decided to remove upstream support and disable booting for this SoC. Public users only have ES2 onwards. Reviewed-by: Laurent Pinchart Reviewed-by: Geert Uytterhoeven Signed-off-by: Wolfram Sang Link: https://lore.kernel.org/r/20230307163041.3815-2-wsa+renesas@sang-engineering.com Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index bdf1a4e5eae0..ba42001a6f57 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -697,7 +697,6 @@ static const struct soc_device_attribute soc_needs_opt_in[] = { static const struct soc_device_attribute soc_denylist[] = { { .soc_id = "r8a774a1", }, - { .soc_id = "r8a7795", .revision = "ES1.*" }, { .soc_id = "r8a7795", .revision = "ES2.*" }, { .soc_id = "r8a7796", }, { /* sentinel */ } -- GitLab From 829a79556fc983f2d4a3d687d4bc60fe8deb56fd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 7 Mar 2023 19:45:04 -0800 Subject: [PATCH 1059/5631] iommu/fsl: fix all kernel-doc warnings in fsl_pamu.c Fix kernel-doc warnings as reported by the kernel test robot: fsl_pamu.c:192: warning: expecting prototype for pamu_config_paace(). Prototype was for pamu_config_ppaace() instead fsl_pamu.c:239: warning: Function parameter or member 'omi_index' not described in 'get_ome_index' fsl_pamu.c:239: warning: Function parameter or member 'dev' not described in 'get_ome_index' fsl_pamu.c:332: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Setup operation mapping and stash destinations for QMAN and QMAN portal. fsl_pamu.c:361: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Setup the operation mapping table for various devices. This is a static Fixes: 695093e38c3e ("iommu/fsl: Freescale PAMU driver and iommu implementation.") Fixes: cd70d4659ff3 ("iommu/fsl: Various cleanups") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: lore.kernel.org/r/202302281151.B1WtZvSC-lkp@intel.com Cc: Aditya Srivastava Cc: Joerg Roedel Cc: Will Deacon Cc: Robin Murphy Cc: iommu@lists.linux.dev Cc: Timur Tabi Cc: Varun Sethi Cc: Emil Medve Reviewed-by: Lu Baolu Acked-by: Timur Tabi Link: https://lore.kernel.org/r/20230308034504.9985-1-rdunlap@infradead.org Signed-off-by: Joerg Roedel --- drivers/iommu/fsl_pamu.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index 05d820fb1d0b..f37d3b044131 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -178,7 +178,7 @@ int pamu_update_paace_stash(int liodn, u32 value) } /** - * pamu_config_paace() - Sets up PPAACE entry for specified liodn + * pamu_config_ppaace() - Sets up PPAACE entry for specified liodn * * @liodn: Logical IO device number * @omi: Operation mapping index -- if ~omi == 0 then omi not defined @@ -232,7 +232,8 @@ int pamu_config_ppaace(int liodn, u32 omi, u32 stashid, int prot) /** * get_ome_index() - Returns the index in the operation mapping table * for device. - * @*omi_index: pointer for storing the index value + * @omi_index: pointer for storing the index value + * @dev: target device * */ void get_ome_index(u32 *omi_index, struct device *dev) @@ -328,7 +329,7 @@ u32 get_stash_id(u32 stash_dest_hint, u32 vcpu) #define QMAN_PORTAL_PAACE 2 #define BMAN_PAACE 3 -/** +/* * Setup operation mapping and stash destinations for QMAN and QMAN portal. * Memory accesses to QMAN and BMAN private memory need not be coherent, so * clear the PAACE entry coherency attribute for them. @@ -357,7 +358,7 @@ static void setup_qbman_paace(struct paace *ppaace, int paace_type) } } -/** +/* * Setup the operation mapping table for various devices. This is a static * table where each table index corresponds to a particular device. PAMU uses * this table to translate device transaction to appropriate corenet -- GitLab From 1b0b5f50dc83351fa2d2158a183cbe258178cb3f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 18:17:08 +0100 Subject: [PATCH 1060/5631] iommu: Spelling s/cpmxchg64/cmpxchg64/ Fix misspellings of "cmpxchg64" Fixes: d286a58bc8f4d5cf ("iommu: Tidy up io-pgtable dependencies") Signed-off-by: Geert Uytterhoeven Acked-by: Robin Murphy Link: https://lore.kernel.org/r/eab156858147249d44463662eb9192202c39ab9f.1678295792.git.geert+renesas@glider.be Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 889c7efd050b..c4928514e5e2 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -33,7 +33,7 @@ config IOMMU_IO_PGTABLE_LPAE bool "ARMv7/v8 Long Descriptor Format" select IOMMU_IO_PGTABLE depends on ARM || ARM64 || COMPILE_TEST - depends on !GENERIC_ATOMIC64 # for cpmxchg64() + depends on !GENERIC_ATOMIC64 # for cmpxchg64() help Enable support for the ARM long descriptor pagetable format. This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page @@ -72,7 +72,7 @@ config IOMMU_IO_PGTABLE_DART bool "Apple DART Formats" select IOMMU_IO_PGTABLE depends on ARM64 || COMPILE_TEST - depends on !GENERIC_ATOMIC64 # for cpmxchg64() + depends on !GENERIC_ATOMIC64 # for cmpxchg64() help Enable support for the Apple DART pagetable formats. These include the t8020 and t6000/t8110 DART formats used in Apple M1/M2 family -- GitLab From a6c9e3874e5759af089c07ab80c87105babc9727 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:09 -0600 Subject: [PATCH 1061/5631] iommu: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20230310144709.1542910-1-robh@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 2 +- drivers/iommu/ipmmu-vmsa.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 2ff7a72cf377..d0843caf8760 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -139,7 +139,7 @@ static int arm_smmu_register_legacy_master(struct device *dev, int err; np = dev_get_dev_node(dev); - if (!np || !of_find_property(np, "#stream-id-cells", NULL)) { + if (!np || !of_property_present(np, "#stream-id-cells")) { of_node_put(np); return -ENODEV; } diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index bdf1a4e5eae0..f4470303d906 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1014,7 +1014,7 @@ static int ipmmu_probe(struct platform_device *pdev) * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property. */ if (!mmu->features->has_cache_leaf_nodes || - !of_find_property(pdev->dev.of_node, "renesas,ipmmu-main", NULL)) + !of_property_present(pdev->dev.of_node, "renesas,ipmmu-main")) mmu->root = mmu; else mmu->root = ipmmu_find_root(); -- GitLab From 0c0431646116b4fbba75c4784e1bda0781dc8073 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:09 -0600 Subject: [PATCH 1062/5631] iommu/omap: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to of_property_read_bool(). Signed-off-by: Rob Herring Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20230310144709.1542980-1-robh@kernel.org Signed-off-by: Joerg Roedel --- drivers/iommu/omap-iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 3ab078112a7c..baafd6211ac4 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1191,7 +1191,7 @@ static int omap_iommu_probe(struct platform_device *pdev) return err; if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8) return -EINVAL; - if (of_find_property(of, "ti,iommu-bus-err-back", NULL)) + if (of_property_read_bool(of, "ti,iommu-bus-err-back")) obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN; obj->dev = &pdev->dev; -- GitLab From b67ab6fb63bbbe6d2c0edebd28c27ea425c8b55b Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Mon, 13 Mar 2023 21:40:26 +0900 Subject: [PATCH 1063/5631] dt-bindings: iommu: renesas, ipmmu-vmsa: Update for R-Car Gen4 Since R-Car Gen4 does not have the main IPMMU IMSSTR register, update the bindings to drop the interrupt bit number from the renesas,ipmmu-main property. Signed-off-by: Yoshihiro Shimoda [geert: Re-add removed items level, add minItems/maxItems constraints] Signed-off-by: Geert Uytterhoeven Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230313124026.954514-1-yoshihiro.shimoda.uh@renesas.com Signed-off-by: Joerg Roedel --- .../bindings/iommu/renesas,ipmmu-vmsa.yaml | 32 ++++++++++++++----- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml index 72308a4c14e7..be90f68c11d1 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.yaml @@ -74,16 +74,16 @@ properties: renesas,ipmmu-main: $ref: /schemas/types.yaml#/definitions/phandle-array items: - - items: + - minItems: 1 + items: - description: phandle to main IPMMU - - description: the interrupt bit number associated with the particular - cache IPMMU device. The interrupt bit number needs to match the main - IPMMU IMSSTR register. Only used by cache IPMMU instances. + - description: + The interrupt bit number associated with the particular cache + IPMMU device. If present, the interrupt bit number needs to match + the main IPMMU IMSSTR register. Only used by cache IPMMU + instances. description: - Reference to the main IPMMU phandle plus 1 cell. The cell is - the interrupt bit number associated with the particular cache IPMMU - device. The interrupt bit number needs to match the main IPMMU IMSSTR - register. Only used by cache IPMMU instances. + Reference to the main IPMMU. required: - compatible @@ -109,6 +109,22 @@ allOf: required: - power-domains + - if: + properties: + compatible: + contains: + const: renesas,rcar-gen4-ipmmu-vmsa + then: + properties: + renesas,ipmmu-main: + items: + - maxItems: 1 + else: + properties: + renesas,ipmmu-main: + items: + - minItems: 2 + examples: - | #include -- GitLab From 0d571dcbe7c6d36dcfcb8e04a49cc01fe462d171 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Tue, 21 Mar 2023 09:23:47 +0000 Subject: [PATCH 1064/5631] iommu/amd: Allocate page table using numa locality info Introduce 'struct protection_domain->nid' variable. It will contain IOMMU NUMA node ID. And allocate page table pages using IOMMU numa locality info. This optimizes page table walk by IOMMU. Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20230321092348.6127-2-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 8 ++++++++ drivers/iommu/amd/amd_iommu_types.h | 1 + drivers/iommu/amd/io_pgtable.c | 4 ++-- drivers/iommu/amd/io_pgtable_v2.c | 16 ++++++---------- drivers/iommu/amd/iommu.c | 6 ++++++ 5 files changed, 23 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index c160a332ce33..20a142b54498 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -122,6 +122,14 @@ static inline int get_pci_sbdf_id(struct pci_dev *pdev) return PCI_SEG_DEVID_TO_SBDF(seg, devid); } +static inline void *alloc_pgtable_page(int nid, gfp_t gfp) +{ + struct page *page; + + page = alloc_pages_node(nid, gfp | __GFP_ZERO, 0); + return page ? page_address(page) : NULL; +} + extern bool translation_pre_enabled(struct amd_iommu *iommu); extern bool amd_iommu_is_attach_deferred(struct device *dev); extern int __init add_special_device(u8 type, u8 id, u32 *devid, diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 3d684190b4d5..e5cfdeaaad48 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -549,6 +549,7 @@ struct protection_domain { spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ int glx; /* Number of levels for GCR3 table */ + int nid; /* Node ID */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ unsigned dev_cnt; /* devices assigned to this domain */ diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index ace0e9b8b913..1b67116882be 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -156,7 +156,7 @@ static bool increase_address_space(struct protection_domain *domain, bool ret = true; u64 *pte; - pte = (void *)get_zeroed_page(gfp); + pte = alloc_pgtable_page(domain->nid, gfp); if (!pte) return false; @@ -250,7 +250,7 @@ static u64 *alloc_pte(struct protection_domain *domain, if (!IOMMU_PTE_PRESENT(__pte) || pte_level == PAGE_MODE_NONE) { - page = (u64 *)get_zeroed_page(gfp); + page = alloc_pgtable_page(domain->nid, gfp); if (!page) return NULL; diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index 8638ddf6fb3b..9f8b423f7630 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -46,11 +46,6 @@ static inline bool is_large_pte(u64 pte) return (pte & IOMMU_PAGE_PSE); } -static inline void *alloc_pgtable_page(void) -{ - return (void *)get_zeroed_page(GFP_KERNEL); -} - static inline u64 set_pgtable_attr(u64 *page) { u64 prot; @@ -138,8 +133,8 @@ static void free_pgtable(u64 *pt, int level) } /* Allocate page table */ -static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova, - unsigned long pg_size, bool *updated) +static u64 *v2_alloc_pte(int nid, u64 *pgd, unsigned long iova, + unsigned long pg_size, gfp_t gfp, bool *updated) { u64 *pte, *page; int level, end_level; @@ -162,7 +157,7 @@ static u64 *v2_alloc_pte(u64 *pgd, unsigned long iova, } if (!IOMMU_PTE_PRESENT(__pte)) { - page = alloc_pgtable_page(); + page = alloc_pgtable_page(nid, gfp); if (!page) return NULL; @@ -262,7 +257,8 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova, while (mapped_size < size) { map_size = get_alloc_page_size(pgsize); - pte = v2_alloc_pte(pdom->iop.pgd, iova, map_size, &updated); + pte = v2_alloc_pte(pdom->nid, pdom->iop.pgd, + iova, map_size, gfp, &updated); if (!pte) { ret = -EINVAL; goto out; @@ -384,7 +380,7 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo struct protection_domain *pdom = (struct protection_domain *)cookie; int ret; - pgtable->pgd = alloc_pgtable_page(); + pgtable->pgd = alloc_pgtable_page(pdom->nid, GFP_ATOMIC); if (!pgtable->pgd) return NULL; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5a505ba5467e..5452d0dd6569 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1662,6 +1662,10 @@ static void do_attach(struct iommu_dev_data *dev_data, dev_data->domain = domain; list_add(&dev_data->list, &domain->dev_list); + /* Update NUMA Node ID */ + if (domain->nid == NUMA_NO_NODE) + domain->nid = dev_to_node(dev_data->dev); + /* Do reference counting */ domain->dev_iommu[iommu->index] += 1; domain->dev_cnt += 1; @@ -2097,6 +2101,8 @@ static struct protection_domain *protection_domain_alloc(unsigned int type) if (type == IOMMU_DOMAIN_IDENTITY) return domain; + domain->nid = NUMA_NO_NODE; + pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain); if (!pgtbl_ops) { domain_id_free(domain->id); -- GitLab From 4d4a0dbab2b998692f54fa6f7a9d2eb675110743 Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Tue, 21 Mar 2023 09:23:48 +0000 Subject: [PATCH 1065/5631] iommu/amd: Allocate IOMMU irqs using numa locality info Use numa information to allocate irq resources and also to set irq affinity. This optimizes the IOMMU interrupt handling. Reviewed-by: Suravee Suthikulpanit Reviewed-by: Alexey Kardashevskiy Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20230321092348.6127-3-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 19a46b9f7357..141eca29c951 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2383,6 +2383,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu) struct irq_domain *domain; struct irq_alloc_info info; int irq, ret; + int node = dev_to_node(&iommu->dev->dev); domain = iommu_get_irqdomain(); if (!domain) @@ -2392,7 +2393,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu) info.type = X86_IRQ_ALLOC_TYPE_AMDVI; info.data = iommu; - irq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); + irq = irq_domain_alloc_irqs(domain, 1, node, &info); if (irq < 0) { irq_domain_remove(domain); return irq; -- GitLab From 24dfb197c3b7d274e5f78fce5e63392526a933e9 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:51 +0800 Subject: [PATCH 1066/5631] iommu/ipmmu-vmsa: Call arm_iommu_release_mapping() in release path In the iommu driver's release_device operation, the driver should detach the device from any attached domain and release the resources allocated in the probe_device and probe_finalize paths. Replace arm_iommu_detach_device() with arm_iommu_release_mapping() in the release path of the ipmmu-vmsa driver. The device_release callback is called in device_del(), this device is not coming back. Zeroing out pointers and testing for a condition which cannot be true by construction is simply a waste of time and code. The bonus is that it also removes a obstacle of arm_iommu_detach_device() re-entering the iommu core during release_device. With this removed, the iommu core code could be simplified a lot. Signed-off-by: Jason Gunthorpe Suggested-by: Robin Murphy Link: https://lore.kernel.org/linux-iommu/7b248ba1-3967-5cd8-82e9-0268c706d320@arm.com/ Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index f4470303d906..7fcbef8802de 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -30,7 +30,6 @@ #define arm_iommu_create_mapping(...) NULL #define arm_iommu_attach_device(...) -ENODEV #define arm_iommu_release_mapping(...) do {} while (0) -#define arm_iommu_detach_device(...) do {} while (0) #endif #define IPMMU_CTX_MAX 16U @@ -820,7 +819,18 @@ static void ipmmu_probe_finalize(struct device *dev) static void ipmmu_release_device(struct device *dev) { - arm_iommu_detach_device(dev); + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct ipmmu_vmsa_device *mmu = to_ipmmu(dev); + unsigned int i; + + for (i = 0; i < fwspec->num_ids; ++i) { + unsigned int utlb = fwspec->ids[i]; + + ipmmu_imuctr_write(mmu, utlb, 0); + mmu->utlb_ctx[utlb] = IPMMU_CTX_INVALID; + } + + arm_iommu_release_mapping(mmu->mapping); } static struct iommu_group *ipmmu_find_group(struct device *dev) -- GitLab From 293f2564f3dd76b749fc31ae4226bd818f860e4f Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:52 +0800 Subject: [PATCH 1067/5631] iommu: Split iommu_group_remove_device() into helpers So that code could be re-used by iommu_release_device() in the subsequent change. No intention for functionality change. Signed-off-by: Jason Gunthorpe Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 64 +++++++++++++++++++++++++++++-------------- 1 file changed, 44 insertions(+), 20 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index ace9d418a115..942bab8b9798 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -453,6 +453,46 @@ int iommu_probe_device(struct device *dev) } +/* + * Remove a device from a group's device list and return the group device + * if successful. + */ +static struct group_device * +__iommu_group_remove_device(struct iommu_group *group, struct device *dev) +{ + struct group_device *device; + + lockdep_assert_held(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + if (device->dev == dev) { + list_del(&device->list); + return device; + } + } + + return NULL; +} + +/* + * Release a device from its group and decrements the iommu group reference + * count. + */ +static void __iommu_group_release_device(struct iommu_group *group, + struct group_device *grp_dev) +{ + struct device *dev = grp_dev->dev; + + sysfs_remove_link(group->devices_kobj, grp_dev->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + trace_remove_device_from_group(group->id, dev); + + kfree(grp_dev->name); + kfree(grp_dev); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +} + void iommu_release_device(struct device *dev) { const struct iommu_ops *ops; @@ -1068,7 +1108,7 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device); void iommu_group_remove_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; - struct group_device *tmp_device, *device = NULL; + struct group_device *device; if (!group) return; @@ -1076,27 +1116,11 @@ void iommu_group_remove_device(struct device *dev) dev_info(dev, "Removing from iommu group %d\n", group->id); mutex_lock(&group->mutex); - list_for_each_entry(tmp_device, &group->devices, list) { - if (tmp_device->dev == dev) { - device = tmp_device; - list_del(&device->list); - break; - } - } + device = __iommu_group_remove_device(group, dev); mutex_unlock(&group->mutex); - if (!device) - return; - - sysfs_remove_link(group->devices_kobj, device->name); - sysfs_remove_link(&dev->kobj, "iommu_group"); - - trace_remove_device_from_group(group->id, dev); - - kfree(device->name); - kfree(device); - dev->iommu_group = NULL; - kobject_put(group->devices_kobj); + if (device) + __iommu_group_release_device(group, device); } EXPORT_SYMBOL_GPL(iommu_group_remove_device); -- GitLab From dba9ca9d41f5266194a5e8007db50985d271d0a4 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:53 +0800 Subject: [PATCH 1068/5631] iommu: Same critical region for device release and removal In a non-driver context, it is crucial to ensure the consistency of a device's iommu ops. Otherwise, it may result in a situation where a device is released but it's iommu ops are still used. Put the ops->release_device and __iommu_group_remove_device() in a same group->mutext critical region, so that, as long as group->mutex is held and the device is in its group's device list, its iommu ops are always consistent. Add check of group ownership if the released device is the last one. Signed-off-by: Jason Gunthorpe Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 942bab8b9798..419d5655ce61 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -495,18 +495,44 @@ static void __iommu_group_release_device(struct iommu_group *group, void iommu_release_device(struct device *dev) { + struct iommu_group *group = dev->iommu_group; + struct group_device *device; const struct iommu_ops *ops; - if (!dev->iommu) + if (!dev->iommu || !group) return; iommu_device_unlink(dev->iommu->iommu_dev, dev); + mutex_lock(&group->mutex); + device = __iommu_group_remove_device(group, dev); + + /* + * If the group has become empty then ownership must have been released, + * and the current domain must be set back to NULL or the default + * domain. + */ + if (list_empty(&group->devices)) + WARN_ON(group->owner_cnt || + group->domain != group->default_domain); + + /* + * release_device() must stop using any attached domain on the device. + * If there are still other devices in the group they are not effected + * by this callback. + * + * The IOMMU driver must set the device to either an identity or + * blocking translation and stop using any domain pointer, as it is + * going to be freed. + */ ops = dev_iommu_ops(dev); if (ops->release_device) ops->release_device(dev); + mutex_unlock(&group->mutex); + + if (device) + __iommu_group_release_device(group, device); - iommu_group_remove_device(dev); module_put(ops->owner); dev_iommu_free(dev); } -- GitLab From 33793748de8fde338c11277d3d16dadc79ba65bf Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:54 +0800 Subject: [PATCH 1069/5631] iommu: Move lock from iommu_change_dev_def_domain() to its caller The intention is to make it possible to put group ownership check and default domain change in a same critical region protected by the group's mutex lock. No intentional functional change. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 419d5655ce61..32c51e6a3491 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2889,7 +2889,7 @@ static int iommu_change_dev_def_domain(struct iommu_group *group, int ret, dev_def_dom; struct device *dev; - mutex_lock(&group->mutex); + lockdep_assert_held(&group->mutex); if (group->default_domain != group->domain) { dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n"); @@ -2978,28 +2978,15 @@ static int iommu_change_dev_def_domain(struct iommu_group *group, goto free_new_domain; group->domain = group->default_domain; - - /* - * Release the mutex here because ops->probe_finalize() call-back of - * some vendor IOMMU drivers calls arm_iommu_attach_device() which - * in-turn might call back into IOMMU core code, where it tries to take - * group->mutex, resulting in a deadlock. - */ - mutex_unlock(&group->mutex); - - /* Make sure dma_ops is appropriatley set */ - iommu_group_do_probe_finalize(dev, group->default_domain); iommu_domain_free(prev_dom); + return 0; free_new_domain: iommu_domain_free(group->default_domain); group->default_domain = prev_dom; group->domain = prev_dom; - out: - mutex_unlock(&group->mutex); - return ret; } @@ -3089,7 +3076,19 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, goto out; } + mutex_lock(&group->mutex); ret = iommu_change_dev_def_domain(group, dev, req_type); + /* + * Release the mutex here because ops->probe_finalize() call-back of + * some vendor IOMMU drivers calls arm_iommu_attach_device() which + * in-turn might call back into IOMMU core code, where it tries to take + * group->mutex, resulting in a deadlock. + */ + mutex_unlock(&group->mutex); + + /* Make sure dma_ops is appropriatley set */ + if (!ret) + iommu_group_do_probe_finalize(dev, group->default_domain); ret = ret ?: count; out: -- GitLab From 49a22aae7d9cfd1e8060b7ea4e0a1537f60dd39d Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:55 +0800 Subject: [PATCH 1070/5631] iommu: Replace device_lock() with group->mutex device_lock() was used in iommu_group_store_type() to prevent the devices in an iommu group from being attached by any device driver. On the other hand, in order to avoid lock race between group->mutex and device_lock(), it limited the usage scenario to the singleton groups. We already have the DMA ownership scheme to avoid driver attachment and group->mutex ensures that device ops are always valid, there's no need for device_lock() anymore. Remove device_lock() and the singleton group limitation. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 81 ++++++++++--------------------------------- 1 file changed, 18 insertions(+), 63 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 32c51e6a3491..6538c72b5ae1 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2956,14 +2956,6 @@ static int iommu_change_dev_def_domain(struct iommu_group *group, goto out; } - /* We can bring up a flush queue without tearing down the domain */ - if (type == IOMMU_DOMAIN_DMA_FQ && prev_dom->type == IOMMU_DOMAIN_DMA) { - ret = iommu_dma_init_fq(prev_dom); - if (!ret) - prev_dom->type = IOMMU_DOMAIN_DMA_FQ; - goto out; - } - /* Sets group->default_domain to the newly allocated domain */ ret = iommu_group_alloc_default_domain(dev->bus, group, type); if (ret) @@ -2996,7 +2988,7 @@ static int iommu_change_dev_def_domain(struct iommu_group *group, * transition. Return failure if this isn't met. * * We need to consider the race between this and the device release path. - * device_lock(dev) is used here to guarantee that the device release path + * group->mutex is used here to guarantee that the device release path * will not be entered at the same time. */ static ssize_t iommu_group_store_type(struct iommu_group *group, @@ -3023,61 +3015,29 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, else return -EINVAL; - /* - * Lock/Unlock the group mutex here before device lock to - * 1. Make sure that the iommu group has only one device (this is a - * prerequisite for step 2) - * 2. Get struct *dev which is needed to lock device - */ mutex_lock(&group->mutex); - if (iommu_group_device_count(group) != 1) { + /* We can bring up a flush queue without tearing down the domain. */ + if (req_type == IOMMU_DOMAIN_DMA_FQ && + group->default_domain->type == IOMMU_DOMAIN_DMA) { + ret = iommu_dma_init_fq(group->default_domain); + if (!ret) + group->default_domain->type = IOMMU_DOMAIN_DMA_FQ; mutex_unlock(&group->mutex); - pr_err_ratelimited("Cannot change default domain: Group has more than one device\n"); - return -EINVAL; + + return ret ?: count; + } + + /* Otherwise, ensure that device exists and no driver is bound. */ + if (list_empty(&group->devices) || group->owner_cnt) { + mutex_unlock(&group->mutex); + return -EPERM; } - /* Since group has only one device */ grp_dev = list_first_entry(&group->devices, struct group_device, list); dev = grp_dev->dev; - get_device(dev); - /* - * Don't hold the group mutex because taking group mutex first and then - * the device lock could potentially cause a deadlock as below. Assume - * two threads T1 and T2. T1 is trying to change default domain of an - * iommu group and T2 is trying to hot unplug a device or release [1] VF - * of a PCIe device which is in the same iommu group. T1 takes group - * mutex and before it could take device lock assume T2 has taken device - * lock and is yet to take group mutex. Now, both the threads will be - * waiting for the other thread to release lock. Below, lock order was - * suggested. - * device_lock(dev); - * mutex_lock(&group->mutex); - * iommu_change_dev_def_domain(); - * mutex_unlock(&group->mutex); - * device_unlock(dev); - * - * [1] Typical device release path - * device_lock() from device/driver core code - * -> bus_notifier() - * -> iommu_bus_notifier() - * -> iommu_release_device() - * -> ops->release_device() vendor driver calls back iommu core code - * -> mutex_lock() from iommu core code - */ - mutex_unlock(&group->mutex); - - /* Check if the device in the group still has a driver bound to it */ - device_lock(dev); - if (device_is_bound(dev) && !(req_type == IOMMU_DOMAIN_DMA_FQ && - group->default_domain->type == IOMMU_DOMAIN_DMA)) { - pr_err_ratelimited("Device is still bound to driver\n"); - ret = -EBUSY; - goto out; - } - - mutex_lock(&group->mutex); ret = iommu_change_dev_def_domain(group, dev, req_type); + /* * Release the mutex here because ops->probe_finalize() call-back of * some vendor IOMMU drivers calls arm_iommu_attach_device() which @@ -3088,14 +3048,9 @@ static ssize_t iommu_group_store_type(struct iommu_group *group, /* Make sure dma_ops is appropriatley set */ if (!ret) - iommu_group_do_probe_finalize(dev, group->default_domain); - ret = ret ?: count; - -out: - device_unlock(dev); - put_device(dev); + __iommu_group_dma_finalize(group); - return ret; + return ret ?: count; } static bool iommu_is_default_domain(struct iommu_group *group) -- GitLab From 4c8444f19ed05971c91cd93252f4a8e3dcb37995 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 14:49:56 +0800 Subject: [PATCH 1071/5631] iommu: Cleanup iommu_change_dev_def_domain() As the singleton group limitation has been removed, cleanup the code in iommu_change_dev_def_domain() accordingly. Documentation is also updated. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322064956.263419-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- .../ABI/testing/sysfs-kernel-iommu_groups | 1 - drivers/iommu/iommu.c | 83 +++++-------------- 2 files changed, 21 insertions(+), 63 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups index b15af6a5bc08..a42d4383d999 100644 --- a/Documentation/ABI/testing/sysfs-kernel-iommu_groups +++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups @@ -53,7 +53,6 @@ Description: /sys/kernel/iommu_groups//type shows the type of default The default domain type of a group may be modified only when - - The group has only one device. - The device in the group is not bound to any device driver. So, the users must unbind the appropriate driver before changing the default domain type. diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6538c72b5ae1..9fccfc69e4c5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2867,11 +2867,10 @@ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); /* - * Changes the default domain of an iommu group that has *only* one device + * Changes the default domain of an iommu group * * @group: The group for which the default domain should be changed - * @prev_dev: The device in the group (this is used to make sure that the device - * hasn't changed after the caller has called this function) + * @dev: The first device in the group * @type: The type of the new default domain that gets associated with the group * * Returns 0 on success and error code on failure @@ -2882,103 +2881,63 @@ EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); * Please take a closer look if intended to use for other purposes. */ static int iommu_change_dev_def_domain(struct iommu_group *group, - struct device *prev_dev, int type) + struct device *dev, int type) { + struct __group_domain_type gtype = {NULL, 0}; struct iommu_domain *prev_dom; - struct group_device *grp_dev; - int ret, dev_def_dom; - struct device *dev; + int ret; lockdep_assert_held(&group->mutex); - if (group->default_domain != group->domain) { - dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n"); - ret = -EBUSY; - goto out; - } - - /* - * iommu group wasn't locked while acquiring device lock in - * iommu_group_store_type(). So, make sure that the device count hasn't - * changed while acquiring device lock. - * - * Changing default domain of an iommu group with two or more devices - * isn't supported because there could be a potential deadlock. Consider - * the following scenario. T1 is trying to acquire device locks of all - * the devices in the group and before it could acquire all of them, - * there could be another thread T2 (from different sub-system and use - * case) that has already acquired some of the device locks and might be - * waiting for T1 to release other device locks. - */ - if (iommu_group_device_count(group) != 1) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Group has more than one device\n"); - ret = -EINVAL; - goto out; - } - - /* Since group has only one device */ - grp_dev = list_first_entry(&group->devices, struct group_device, list); - dev = grp_dev->dev; - - if (prev_dev != dev) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Device has been changed\n"); - ret = -EBUSY; - goto out; - } - prev_dom = group->default_domain; - if (!prev_dom) { - ret = -EINVAL; - goto out; - } - - dev_def_dom = iommu_get_def_domain_type(dev); + __iommu_group_for_each_dev(group, >ype, + probe_get_default_domain_type); if (!type) { /* * If the user hasn't requested any specific type of domain and * if the device supports both the domains, then default to the * domain the device was booted with */ - type = dev_def_dom ? : iommu_def_domain_type; - } else if (dev_def_dom && type != dev_def_dom) { - dev_err_ratelimited(prev_dev, "Device cannot be in %s domain\n", + type = gtype.type ? : iommu_def_domain_type; + } else if (gtype.type && type != gtype.type) { + dev_err_ratelimited(dev, "Device cannot be in %s domain\n", iommu_domain_type_str(type)); - ret = -EINVAL; - goto out; + return -EINVAL; } /* * Switch to a new domain only if the requested domain type is different * from the existing default domain type */ - if (prev_dom->type == type) { - ret = 0; - goto out; - } + if (prev_dom->type == type) + return 0; + + group->default_domain = NULL; + group->domain = NULL; /* Sets group->default_domain to the newly allocated domain */ ret = iommu_group_alloc_default_domain(dev->bus, group, type); if (ret) - goto out; + goto restore_old_domain; - ret = iommu_create_device_direct_mappings(group, dev); + ret = iommu_group_create_direct_mappings(group); if (ret) goto free_new_domain; - ret = __iommu_attach_device(group->default_domain, dev); + ret = __iommu_attach_group(group->default_domain, group); if (ret) goto free_new_domain; - group->domain = group->default_domain; iommu_domain_free(prev_dom); return 0; free_new_domain: iommu_domain_free(group->default_domain); +restore_old_domain: group->default_domain = prev_dom; group->domain = prev_dom; -out: + return ret; } -- GitLab From 2fdcc1b324189b5fb20655baebd40cd82e2bdf0c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 22 Mar 2023 02:37:26 +0100 Subject: [PATCH 1072/5631] KVM: x86/mmu: Avoid indirect call for get_cr3 Most of the time, calls to get_guest_pgd result in calling kvm_read_cr3 (the exception is only nested TDP). Hardcode the default instead of using the get_cr3 function, avoiding a retpoline if they are enabled. Signed-off-by: Paolo Bonzini Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-2-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/mmu.c | 31 ++++++++++++++++++++----------- arch/x86/kvm/mmu/paging_tmpl.h | 2 +- 2 files changed, 21 insertions(+), 12 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index b2124962e5a8..4c874d4ec68f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -256,6 +256,20 @@ static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu) return regs; } +static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) +{ + return kvm_read_cr3(vcpu); +} + +static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + return kvm_read_cr3(vcpu); + + return mmu->get_guest_pgd(vcpu); +} + static inline bool kvm_available_flush_tlb_with_range(void) { return kvm_x86_ops.tlb_remote_flush_with_range; @@ -3801,7 +3815,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) int quadrant, i, r; hpa_t root; - root_pgd = mmu->get_guest_pgd(vcpu); + root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); root_gfn = root_pgd >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) @@ -4251,7 +4265,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->root_role.direct; - arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); + arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -4270,7 +4284,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return; if (!vcpu->arch.mmu->root_role.direct && - work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) + work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); @@ -4673,11 +4687,6 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); -static unsigned long get_cr3(struct kvm_vcpu *vcpu) -{ - return kvm_read_cr3(vcpu); -} - static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { @@ -5223,7 +5232,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; context->sync_spte = NULL; - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -5372,7 +5381,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu, kvm_init_shadow_mmu(vcpu, cpu_role); - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -5386,7 +5395,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, return; g_context->cpu_role.as_u64 = new_mode.as_u64; - g_context->get_guest_pgd = get_cr3; + g_context->get_guest_pgd = get_guest_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 03a9577329fc..0662e0278e70 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -324,7 +324,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->cpu_role.base.level; - pte = mmu->get_guest_pgd(vcpu); + pte = kvm_mmu_get_guest_pgd(vcpu, mmu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 -- GitLab From 50f13998451effea5c5fdc70fe576f8b435d6224 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 22 Mar 2023 02:37:30 +0100 Subject: [PATCH 1073/5631] KVM: x86/mmu: Fix comment typo Fix a small comment typo in make_spte(). Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-6-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/spte.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c15bfca3ed15..cf2c6426a6fc 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -164,7 +164,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, /* * For simplicity, enforce the NX huge page mitigation even if not * strictly necessary. KVM could ignore the mitigation if paging is - * disabled in the guest, as the guest doesn't have an page tables to + * disabled in the guest, as the guest doesn't have any page tables to * abuse. But to safely ignore the mitigation, KVM would have to * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG * is toggled on, and that's a net negative for performance when TDP is -- GitLab From c33fcc13ee0d02efe5729588e8fba8b899c8879a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 22 Mar 2023 20:34:21 +0800 Subject: [PATCH 1074/5631] iommu: Use sysfs_emit() for sysfs show Use sysfs_emit() instead of the sprintf() for sysfs entries. sysfs_emit() knows the maximum of the temporary buffer used for outputting sysfs content and avoids overrunning the buffer length. Prefer 'long long' over 'long long int' as suggested by checkpatch.pl. Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230322123421.278852-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/init.c | 4 ++-- drivers/iommu/intel/iommu.c | 17 +++++++++-------- drivers/iommu/iommu.c | 31 +++++++++++++++---------------- 3 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 19a46b9f7357..a98202018140 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1941,7 +1941,7 @@ static ssize_t amd_iommu_show_cap(struct device *dev, char *buf) { struct amd_iommu *iommu = dev_to_amd_iommu(dev); - return sprintf(buf, "%x\n", iommu->cap); + return sysfs_emit(buf, "%x\n", iommu->cap); } static DEVICE_ATTR(cap, S_IRUGO, amd_iommu_show_cap, NULL); @@ -1950,7 +1950,7 @@ static ssize_t amd_iommu_show_features(struct device *dev, char *buf) { struct amd_iommu *iommu = dev_to_amd_iommu(dev); - return sprintf(buf, "%llx:%llx\n", iommu->features2, iommu->features); + return sysfs_emit(buf, "%llx:%llx\n", iommu->features2, iommu->features); } static DEVICE_ATTR(features, S_IRUGO, amd_iommu_show_features, NULL); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7c2f4bd33582..a366790fb781 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3760,8 +3760,8 @@ static ssize_t version_show(struct device *dev, { struct intel_iommu *iommu = dev_to_intel_iommu(dev); u32 ver = readl(iommu->reg + DMAR_VER_REG); - return sprintf(buf, "%d:%d\n", - DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); + return sysfs_emit(buf, "%d:%d\n", + DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver)); } static DEVICE_ATTR_RO(version); @@ -3769,7 +3769,7 @@ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->reg_phys); + return sysfs_emit(buf, "%llx\n", iommu->reg_phys); } static DEVICE_ATTR_RO(address); @@ -3777,7 +3777,7 @@ static ssize_t cap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->cap); + return sysfs_emit(buf, "%llx\n", iommu->cap); } static DEVICE_ATTR_RO(cap); @@ -3785,7 +3785,7 @@ static ssize_t ecap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%llx\n", iommu->ecap); + return sysfs_emit(buf, "%llx\n", iommu->ecap); } static DEVICE_ATTR_RO(ecap); @@ -3793,7 +3793,7 @@ static ssize_t domains_supported_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%ld\n", cap_ndoms(iommu->cap)); + return sysfs_emit(buf, "%ld\n", cap_ndoms(iommu->cap)); } static DEVICE_ATTR_RO(domains_supported); @@ -3801,8 +3801,9 @@ static ssize_t domains_used_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids, - cap_ndoms(iommu->cap))); + return sysfs_emit(buf, "%d\n", + bitmap_weight(iommu->domain_ids, + cap_ndoms(iommu->cap))); } static DEVICE_ATTR_RO(domains_used); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 9fccfc69e4c5..7abee83610b6 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -616,7 +616,7 @@ static void iommu_group_remove_file(struct iommu_group *group, static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) { - return sprintf(buf, "%s\n", group->name); + return sysfs_emit(buf, "%s\n", group->name); } /** @@ -729,52 +729,51 @@ static ssize_t iommu_group_show_resv_regions(struct iommu_group *group, { struct iommu_resv_region *region, *next; struct list_head group_resv_regions; - char *str = buf; + int offset = 0; INIT_LIST_HEAD(&group_resv_regions); iommu_get_group_resv_regions(group, &group_resv_regions); list_for_each_entry_safe(region, next, &group_resv_regions, list) { - str += sprintf(str, "0x%016llx 0x%016llx %s\n", - (long long int)region->start, - (long long int)(region->start + - region->length - 1), - iommu_group_resv_type_string[region->type]); + offset += sysfs_emit_at(buf, offset, "0x%016llx 0x%016llx %s\n", + (long long)region->start, + (long long)(region->start + + region->length - 1), + iommu_group_resv_type_string[region->type]); kfree(region); } - return (str - buf); + return offset; } static ssize_t iommu_group_show_type(struct iommu_group *group, char *buf) { - char *type = "unknown\n"; + char *type = "unknown"; mutex_lock(&group->mutex); if (group->default_domain) { switch (group->default_domain->type) { case IOMMU_DOMAIN_BLOCKED: - type = "blocked\n"; + type = "blocked"; break; case IOMMU_DOMAIN_IDENTITY: - type = "identity\n"; + type = "identity"; break; case IOMMU_DOMAIN_UNMANAGED: - type = "unmanaged\n"; + type = "unmanaged"; break; case IOMMU_DOMAIN_DMA: - type = "DMA\n"; + type = "DMA"; break; case IOMMU_DOMAIN_DMA_FQ: - type = "DMA-FQ\n"; + type = "DMA-FQ"; break; } } mutex_unlock(&group->mutex); - strcpy(buf, type); - return strlen(type); + return sysfs_emit(buf, "%s\n", type); } static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); -- GitLab From 01b31714bd90be2784f7145bf93b7f78f3d081e1 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 22 Mar 2023 02:37:27 +0100 Subject: [PATCH 1075/5631] KVM: x86: Do not unload MMU roots when only toggling CR0.WP with TDP enabled There is no need to unload the MMU roots with TDP enabled when only CR0.WP has changed -- the paging structures are still valid, only the permission bitmap needs to be updated. One heavy user of toggling CR0.WP is grsecurity's KERNEXEC feature to implement kernel W^X. The optimization brings a huge performance gain for this case as the following micro-benchmark running 'ssdd 10 50000' from rt-tests[1] on a grsecurity L1 VM shows (runtime in seconds, lower is better): legacy TDP shadow kvm-x86/next@d8708b 8.43s 9.45s 70.3s +patch 5.39s 5.63s 70.2s For legacy MMU this is ~36% faster, for TDP MMU even ~40% faster. Also TDP and legacy MMU now both have a similar runtime which vanishes the need to disable TDP MMU for grsecurity. Shadow MMU sees no measurable difference and is still slow, as expected. [1] https://git.kernel.org/pub/scm/utils/rt-tests/rt-tests.git Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-3-minipli@grsecurity.net Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..c6d909778b2c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -906,6 +906,18 @@ EXPORT_SYMBOL_GPL(load_pdptrs); void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { + /* + * CR0.WP is incorporated into the MMU role, but only for non-nested, + * indirect shadow MMUs. If TDP is enabled, the MMU's metadata needs + * to be updated, e.g. so that emulating guest translations does the + * right thing, but there's no need to unload the root as CR0.WP + * doesn't affect SPTEs. + */ + if (tdp_enabled && (cr0 ^ old_cr0) == X86_CR0_WP) { + kvm_init_mmu(vcpu); + return; + } + if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); -- GitLab From e40bcf9f3a187126ce74a05d3b177fc16874446f Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 22 Mar 2023 02:37:28 +0100 Subject: [PATCH 1076/5631] KVM: x86: Ignore CR0.WP toggles in non-paging mode If paging is disabled, there are no permission bits to emulate. Micro-optimize this case to avoid unnecessary work. Suggested-by: Sean Christopherson Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-4-minipli@grsecurity.net Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c6d909778b2c..8a66ac7a4878 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -908,14 +908,20 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon { /* * CR0.WP is incorporated into the MMU role, but only for non-nested, - * indirect shadow MMUs. If TDP is enabled, the MMU's metadata needs - * to be updated, e.g. so that emulating guest translations does the - * right thing, but there's no need to unload the root as CR0.WP - * doesn't affect SPTEs. + * indirect shadow MMUs. If paging is disabled, no updates are needed + * as there are no permission bits to emulate. If TDP is enabled, the + * MMU's metadata needs to be updated, e.g. so that emulating guest + * translations does the right thing, but there's no need to unload the + * root as CR0.WP doesn't affect SPTEs. */ - if (tdp_enabled && (cr0 ^ old_cr0) == X86_CR0_WP) { - kvm_init_mmu(vcpu); - return; + if ((cr0 ^ old_cr0) == X86_CR0_WP) { + if (!(cr0 & X86_CR0_PG)) + return; + + if (tdp_enabled) { + kvm_init_mmu(vcpu); + return; + } } if ((cr0 ^ old_cr0) & X86_CR0_PG) { -- GitLab From 74cdc836919bf34684ef66f995273f35e2189daf Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 22 Mar 2023 02:37:29 +0100 Subject: [PATCH 1077/5631] KVM: x86: Make use of kvm_read_cr*_bits() when testing bits Make use of the kvm_read_cr{0,4}_bits() helper functions when we only want to know the state of certain bits instead of the whole register. This not only makes the intent cleaner, it also avoids a potential VMREAD in case the tested bits aren't guest owned. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-5-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 612e6c70ce2e..f4aa170b5b97 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -540,9 +540,9 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (!pmc) return 1; - if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) && + if (!(kvm_read_cr4_bits(vcpu, X86_CR4_PCE)) && (static_call(kvm_x86_get_cpl)(vcpu) != 0) && - (kvm_read_cr0(vcpu) & X86_CR0_PE)) + (kvm_read_cr0_bits(vcpu, X86_CR0_PE))) return 1; *data = pmc_read_counter(pmc) & mask; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7bf14abdba1..8fc1a0c7856f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5517,7 +5517,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); + trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -7575,7 +7575,7 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else -- GitLab From fb509f76acc8d42bed11bca308404f81c2be856a Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Wed, 22 Mar 2023 02:37:31 +0100 Subject: [PATCH 1078/5631] KVM: VMX: Make CR0.WP a guest owned bit Guests like grsecurity that make heavy use of CR0.WP to implement kernel level W^X will suffer from the implied VMEXITs. With EPT there is no need to intercept a guest change of CR0.WP, so simply make it a guest owned bit if we can do so. This implies that a read of a guest's CR0.WP bit might need a VMREAD. However, the only potentially affected user seems to be kvm_init_mmu() which is a heavy operation to begin with. But also most callers already cache the full value of CR0 anyway, so no additional VMREAD is needed. The only exception is nested_vmx_load_cr3(). This change is VMX-specific, as SVM has no such fine grained control register intercept control. Suggested-by: Sean Christopherson Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230322013731.102955-7-minipli@grsecurity.net Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- arch/x86/kvm/kvm_cache_regs.h | 2 +- arch/x86/kvm/vmx/nested.c | 4 ++-- arch/x86/kvm/vmx/vmx.c | 2 +- arch/x86/kvm/vmx/vmx.h | 18 ++++++++++++++++++ 4 files changed, 22 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 4c91f626c058..e50d353b5c1c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -4,7 +4,7 @@ #include -#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS +#define KVM_POSSIBLE_CR0_GUEST_BITS (X86_CR0_TS | X86_CR0_WP) #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f63b28f46a71..61d940fc91ba 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4481,7 +4481,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4632,7 +4632,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 8fc1a0c7856f..e501f6864a72 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4790,7 +4790,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 2acdc54bc34b..423e9d3c9c40 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -640,6 +640,24 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) +static inline unsigned long vmx_l1_guest_owned_cr0_bits(void) +{ + unsigned long bits = KVM_POSSIBLE_CR0_GUEST_BITS; + + /* + * CR0.WP needs to be intercepted when KVM is shadowing legacy paging + * in order to construct shadow PTEs with the correct protections. + * Note! CR0.WP technically can be passed through to the guest if + * paging is disabled, but checking CR0.PG would generate a cyclical + * dependency of sorts due to forcing the caller to ensure CR0 holds + * the correct value prior to determining which CR0 bits can be owned + * by L1. Keep it simple and limit the optimization to EPT. + */ + if (!enable_ept) + bits &= ~X86_CR0_WP; + return bits; +} + static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); -- GitLab From e92606fa172f63a26054885b9715be86c643229d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 13 Mar 2023 16:33:46 -0700 Subject: [PATCH 1079/5631] livepatch: Convert stack entries array to percpu The entries array in klp_check_stack() is static local because it's too big to be reasonably allocated on the stack. Serialized access is enforced by the klp_mutex. In preparation for calling klp_check_stack() without the mutex (from cond_resched), convert it to a percpu variable. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230313233346.kayh4t2lpicjkpsv@treble --- kernel/livepatch/transition.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index f1b25ec581e0..135fc73e2e5d 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -14,6 +14,8 @@ #include "transition.h" #define MAX_STACK_ENTRIES 100 +DEFINE_PER_CPU(unsigned long[MAX_STACK_ENTRIES], klp_stack_entries); + #define STACK_ERR_BUF_SIZE 128 #define SIGNALS_TIMEOUT 15 @@ -240,12 +242,15 @@ static int klp_check_stack_func(struct klp_func *func, unsigned long *entries, */ static int klp_check_stack(struct task_struct *task, const char **oldname) { - static unsigned long entries[MAX_STACK_ENTRIES]; + unsigned long *entries = this_cpu_ptr(klp_stack_entries); struct klp_object *obj; struct klp_func *func; int ret, nr_entries; - ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries)); + /* Protect 'klp_stack_entries' */ + lockdep_assert_preemption_disabled(); + + ret = stack_trace_save_tsk_reliable(task, entries, MAX_STACK_ENTRIES); if (ret < 0) return -EINVAL; nr_entries = ret; -- GitLab From 383439d3d400d4c5a7ffb4495124adc6be6a05e2 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 24 Feb 2023 08:49:59 -0800 Subject: [PATCH 1080/5631] livepatch: Skip task_call_func() for current task The current task doesn't need the scheduler's protection to unwind its own stack. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Mladek Tested-by: Seth Forshee (DigitalOcean) Link: https://lore.kernel.org/r/4b92e793462d532a05f03767151fa29db3e68e13.1677257135.git.jpoimboe@kernel.org --- kernel/livepatch/transition.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 135fc73e2e5d..824e2e3f07dd 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -312,7 +312,11 @@ static bool klp_try_switch_task(struct task_struct *task) * functions. If all goes well, switch the task to the target patch * state. */ - ret = task_call_func(task, klp_check_and_switch_task, &old_name); + if (task == current) + ret = klp_check_and_switch_task(current, &old_name); + else + ret = task_call_func(task, klp_check_and_switch_task, &old_name); + switch (ret) { case 0: /* success */ break; -- GitLab From e3ff7c609f39671d1aaff4fb4a8594e14f3e03f8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 24 Feb 2023 08:50:00 -0800 Subject: [PATCH 1081/5631] livepatch,sched: Add livepatch task switching to cond_resched() There have been reports [1][2] of live patches failing to complete within a reasonable amount of time due to CPU-bound kthreads. Fix it by patching tasks in cond_resched(). There are four different flavors of cond_resched(), depending on the kernel configuration. Hook into all of them. A more elegant solution might be to use a preempt notifier. However, non-ORC unwinders can't unwind a preempted task reliably. [1] https://lore.kernel.org/lkml/20220507174628.2086373-1-song@kernel.org/ [2] https://lkml.kernel.org/lkml/20230120-vhost-klp-switching-v1-0-7c2b65519c43@kernel.org Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Mladek Tested-by: Seth Forshee (DigitalOcean) Link: https://lore.kernel.org/r/4ae981466b7814ec221014fc2554b2f86f3fb70b.1677257135.git.jpoimboe@kernel.org --- include/linux/livepatch.h | 1 + include/linux/livepatch_sched.h | 29 +++++++++ include/linux/sched.h | 20 ++++-- kernel/livepatch/core.c | 1 + kernel/livepatch/transition.c | 107 +++++++++++++++++++++++++++----- kernel/sched/core.c | 64 ++++++++++++++++--- 6 files changed, 194 insertions(+), 28 deletions(-) create mode 100644 include/linux/livepatch_sched.h diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 293e29960c6e..9b9b38e89563 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_LIVEPATCH) diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h new file mode 100644 index 000000000000..013794fb5da0 --- /dev/null +++ b/include/linux/livepatch_sched.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_LIVEPATCH_SCHED_H_ +#define _LINUX_LIVEPATCH_SCHED_H_ + +#include +#include + +#ifdef CONFIG_LIVEPATCH + +void __klp_sched_try_switch(void); + +#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + +DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key); + +static __always_inline void klp_sched_try_switch(void) +{ + if (static_branch_unlikely(&klp_sched_try_switch_key)) + __klp_sched_try_switch(); +} + +#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + +#else /* !CONFIG_LIVEPATCH */ +static inline void klp_sched_try_switch(void) {} +static inline void __klp_sched_try_switch(void) {} +#endif /* CONFIG_LIVEPATCH */ + +#endif /* _LINUX_LIVEPATCH_SCHED_H_ */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..6d654eb4cabd 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -36,6 +36,7 @@ #include #include #include +#include #include /* task_struct member predeclarations (sorted alphabetically): */ @@ -2070,6 +2071,9 @@ extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +void sched_dynamic_klp_enable(void); +void sched_dynamic_klp_disable(void); + DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) @@ -2078,6 +2082,7 @@ static __always_inline int _cond_resched(void) } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) @@ -2085,20 +2090,25 @@ static __always_inline int _cond_resched(void) return dynamic_cond_resched(); } -#else +#else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { + klp_sched_try_switch(); return __cond_resched(); } -#endif /* CONFIG_PREEMPT_DYNAMIC */ +#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ -#else +#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ -static inline int _cond_resched(void) { return 0; } +static inline int _cond_resched(void) +{ + klp_sched_try_switch(); + return 0; +} -#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ +#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 4bd2d5e10f20..eea7c8ec6e05 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -33,6 +33,7 @@ * * - klp_ftrace_handler() * - klp_update_patch_state() + * - __klp_sched_try_switch() */ DEFINE_MUTEX(klp_mutex); diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 824e2e3f07dd..e9fd83a02228 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -9,6 +9,7 @@ #include #include +#include #include "core.h" #include "patch.h" #include "transition.h" @@ -26,6 +27,25 @@ static int klp_target_state = KLP_UNDEFINED; static unsigned int klp_signals_cnt; +/* + * When a livepatch is in progress, enable klp stack checking in + * cond_resched(). This helps CPU-bound kthreads get patched. + */ +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + +#define klp_cond_resched_enable() sched_dynamic_klp_enable() +#define klp_cond_resched_disable() sched_dynamic_klp_disable() + +#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + +DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key); +EXPORT_SYMBOL(klp_sched_try_switch_key); + +#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key) +#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key) + +#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + /* * This work can be performed periodically to finish patching or unpatching any * "straggler" tasks which failed to transition in the first attempt. @@ -174,8 +194,8 @@ void klp_update_patch_state(struct task_struct *task) * barrier (smp_rmb) for two cases: * * 1) Enforce the order of the TIF_PATCH_PENDING read and the - * klp_target_state read. The corresponding write barrier is in - * klp_init_transition(). + * klp_target_state read. The corresponding write barriers are in + * klp_init_transition() and klp_reverse_transition(). * * 2) Enforce the order of the TIF_PATCH_PENDING read and a future read * of func->transition, if klp_ftrace_handler() is called later on @@ -343,6 +363,44 @@ static bool klp_try_switch_task(struct task_struct *task) return !ret; } +void __klp_sched_try_switch(void) +{ + if (likely(!klp_patch_pending(current))) + return; + + /* + * This function is called from cond_resched() which is called in many + * places throughout the kernel. Using the klp_mutex here might + * deadlock. + * + * Instead, disable preemption to prevent racing with other callers of + * klp_try_switch_task(). Thanks to task_call_func() they won't be + * able to switch this task while it's running. + */ + preempt_disable(); + + /* + * Make sure current didn't get patched between the above check and + * preempt_disable(). + */ + if (unlikely(!klp_patch_pending(current))) + goto out; + + /* + * Enforce the order of the TIF_PATCH_PENDING read above and the + * klp_target_state read in klp_try_switch_task(). The corresponding + * write barriers are in klp_init_transition() and + * klp_reverse_transition(). + */ + smp_rmb(); + + klp_try_switch_task(current); + +out: + preempt_enable(); +} +EXPORT_SYMBOL(__klp_sched_try_switch); + /* * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set. * Kthreads with TIF_PATCH_PENDING set are woken up. @@ -449,7 +507,8 @@ void klp_try_complete_transition(void) return; } - /* we're done, now cleanup the data structures */ + /* Done! Now cleanup the data structures. */ + klp_cond_resched_disable(); patch = klp_transition_patch; klp_complete_transition(); @@ -501,6 +560,8 @@ void klp_start_transition(void) set_tsk_thread_flag(task, TIF_PATCH_PENDING); } + klp_cond_resched_enable(); + klp_signals_cnt = 0; } @@ -556,8 +617,9 @@ void klp_init_transition(struct klp_patch *patch, int state) * see a func in transition with a task->patch_state of KLP_UNDEFINED. * * Also enforce the order of the klp_target_state write and future - * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() doesn't - * set a task->patch_state to KLP_UNDEFINED. + * TIF_PATCH_PENDING writes to ensure klp_update_patch_state() and + * __klp_sched_try_switch() don't set a task->patch_state to + * KLP_UNDEFINED. */ smp_wmb(); @@ -593,14 +655,10 @@ void klp_reverse_transition(void) klp_target_state == KLP_PATCHED ? "patching to unpatching" : "unpatching to patching"); - klp_transition_patch->enabled = !klp_transition_patch->enabled; - - klp_target_state = !klp_target_state; - /* * Clear all TIF_PATCH_PENDING flags to prevent races caused by - * klp_update_patch_state() running in parallel with - * klp_start_transition(). + * klp_update_patch_state() or __klp_sched_try_switch() running in + * parallel with the reverse transition. */ read_lock(&tasklist_lock); for_each_process_thread(g, task) @@ -610,9 +668,28 @@ void klp_reverse_transition(void) for_each_possible_cpu(cpu) clear_tsk_thread_flag(idle_task(cpu), TIF_PATCH_PENDING); - /* Let any remaining calls to klp_update_patch_state() complete */ + /* + * Make sure all existing invocations of klp_update_patch_state() and + * __klp_sched_try_switch() see the cleared TIF_PATCH_PENDING before + * starting the reverse transition. + */ klp_synchronize_transition(); + /* + * All patching has stopped, now re-initialize the global variables to + * prepare for the reverse transition. + */ + klp_transition_patch->enabled = !klp_transition_patch->enabled; + klp_target_state = !klp_target_state; + + /* + * Enforce the order of the klp_target_state write and the + * TIF_PATCH_PENDING writes in klp_start_transition() to ensure + * klp_update_patch_state() and __klp_sched_try_switch() don't set + * task->patch_state to the wrong value. + */ + smp_wmb(); + klp_start_transition(); } @@ -626,9 +703,9 @@ void klp_copy_process(struct task_struct *child) * the task flag up to date with the parent here. * * The operation is serialized against all klp_*_transition() - * operations by the tasklist_lock. The only exception is - * klp_update_patch_state(current), but we cannot race with - * that because we are current. + * operations by the tasklist_lock. The only exceptions are + * klp_update_patch_state(current) and __klp_sched_try_switch(), but we + * cannot race with them because we are current. */ if (test_tsk_thread_flag(current, TIF_PATCH_PENDING)) set_tsk_thread_flag(child, TIF_PATCH_PENDING); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5ddd9610be56..b9616f153946 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8525,6 +8525,7 @@ EXPORT_STATIC_CALL_TRAMP(might_resched); static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched); int __sched dynamic_cond_resched(void) { + klp_sched_try_switch(); if (!static_branch_unlikely(&sk_dynamic_cond_resched)) return 0; return __cond_resched(); @@ -8673,13 +8674,17 @@ int sched_dynamic_mode(const char *str) #error "Unsupported PREEMPT_DYNAMIC mechanism" #endif -void sched_dynamic_update(int mode) +DEFINE_MUTEX(sched_dynamic_mutex); +static bool klp_override; + +static void __sched_dynamic_update(int mode) { /* * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in * the ZERO state, which is invalid. */ - preempt_dynamic_enable(cond_resched); + if (!klp_override) + preempt_dynamic_enable(cond_resched); preempt_dynamic_enable(might_resched); preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); @@ -8687,36 +8692,79 @@ void sched_dynamic_update(int mode) switch (mode) { case preempt_dynamic_none: - preempt_dynamic_enable(cond_resched); + if (!klp_override) + preempt_dynamic_enable(cond_resched); preempt_dynamic_disable(might_resched); preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: none\n"); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: none\n"); break; case preempt_dynamic_voluntary: - preempt_dynamic_enable(cond_resched); + if (!klp_override) + preempt_dynamic_enable(cond_resched); preempt_dynamic_enable(might_resched); preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: voluntary\n"); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: voluntary\n"); break; case preempt_dynamic_full: - preempt_dynamic_disable(cond_resched); + if (!klp_override) + preempt_dynamic_disable(cond_resched); preempt_dynamic_disable(might_resched); preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); preempt_dynamic_enable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: full\n"); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: full\n"); break; } preempt_dynamic_mode = mode; } +void sched_dynamic_update(int mode) +{ + mutex_lock(&sched_dynamic_mutex); + __sched_dynamic_update(mode); + mutex_unlock(&sched_dynamic_mutex); +} + +#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL + +static int klp_cond_resched(void) +{ + __klp_sched_try_switch(); + return __cond_resched(); +} + +void sched_dynamic_klp_enable(void) +{ + mutex_lock(&sched_dynamic_mutex); + + klp_override = true; + static_call_update(cond_resched, klp_cond_resched); + + mutex_unlock(&sched_dynamic_mutex); +} + +void sched_dynamic_klp_disable(void) +{ + mutex_lock(&sched_dynamic_mutex); + + klp_override = false; + __sched_dynamic_update(preempt_dynamic_mode); + + mutex_unlock(&sched_dynamic_mutex); +} + +#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + static int __init setup_preempt_mode(char *str) { int mode = sched_dynamic_mode(str); -- GitLab From 05bfb338fa8dd40b008ce443e397fc374f6bd107 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 24 Feb 2023 08:50:01 -0800 Subject: [PATCH 1082/5631] vhost: Fix livepatch timeouts in vhost_worker() Livepatch timeouts were reported due to busy vhost_worker() kthreads. Now that cond_resched() can do livepatch task switching, use cond_resched() in vhost_worker(). That's the better way to conditionally call schedule() anyway. Reported-by: Seth Forshee (DigitalOcean) Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Mladek Tested-by: Seth Forshee (DigitalOcean) Link: https://lore.kernel.org/r/509f6ea6fe6505f0a75a66026ba531c765ef922f.1677257135.git.jpoimboe@kernel.org --- drivers/vhost/vhost.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f11bdbe4c2c5..822fbdb54c4f 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -363,8 +363,7 @@ static int vhost_worker(void *data) kcov_remote_start_common(dev->kcov_handle); work->fn(work); kcov_remote_stop(); - if (need_resched()) - schedule(); + cond_resched(); } } kthread_unuse_mm(dev->mm); -- GitLab From 0c928ff26bd68d9638444601c0cbf4e4f978b752 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 22 Mar 2023 09:55:20 -0700 Subject: [PATCH 1083/5631] KVM: SVM: Fix benign "bool vs. int" comparison in svm_set_cr0() Explicitly convert the return from is_paging() to a bool when comparing against old_paging, which is also a boolean. is_paging() sneakily uses kvm_read_cr0_bits() and returns an int, i.e. returns X86_CR0_PG or 0, not 1 or 0. Luckily, the bug is benign as it only results in a false positive, not a false negative, i.e. only causes a spurious refresh of CR4 when paging is enabled in both the old and new. Cc: Maxim Levitsky Fixes: c53bbe2145f5 ("KVM: x86: SVM: don't passthrough SMAP/SMEP/PKE bits in !NPT && !gCR0.PG case") Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 70183d2271b5..19794a8ea28c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1802,7 +1802,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; - if (old_paging != is_paging(vcpu)) + if (old_paging != !!is_paging(vcpu)) svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); } -- GitLab From 607475cfa0f753862c0030de836875fe4ac5cf8a Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Wed, 22 Mar 2023 12:58:21 +0800 Subject: [PATCH 1084/5631] KVM: x86: Add helpers to query individual CR0/CR4 bits Add helpers to check if a specific CR0/CR4 bit is set to avoid a plethora of implicit casts from the "unsigned long" return of kvm_read_cr*_bits(), and to make each caller's intent more obvious. Defer converting helpers that do truly ugly casts from "unsigned long" to "int", e.g. is_pse(), to a future commit so that their conversion is more isolated. Opportunistically drop the superfluous pcid_enabled from kvm_set_cr3(); the local variable is used only once, immediately after its declaration. Suggested-by: Sean Christopherson Signed-off-by: Binbin Wu Link: https://lore.kernel.org/r/20230322045824.22970-2-binbin.wu@linux.intel.com [sean: move "obvious" conversions to this commit, massage changelog] Signed-off-by: Sean Christopherson --- arch/x86/kvm/cpuid.c | 4 ++-- arch/x86/kvm/kvm_cache_regs.h | 16 ++++++++++++++++ arch/x86/kvm/mmu.h | 2 +- arch/x86/kvm/pmu.c | 4 ++-- arch/x86/kvm/vmx/nested.c | 2 +- arch/x86/kvm/vmx/vmx.c | 2 +- arch/x86/kvm/x86.c | 22 ++++++++++------------ arch/x86/kvm/x86.h | 4 ++-- 8 files changed, 35 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9583a110cf5f..1ad3bde72526 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -266,7 +266,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e /* Update OSXSAVE bit */ if (boot_cpu_has(X86_FEATURE_XSAVE)) cpuid_entry_change(best, X86_FEATURE_OSXSAVE, - kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)); + kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); cpuid_entry_change(best, X86_FEATURE_APIC, vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); @@ -275,7 +275,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e best = cpuid_entry2_find(entries, nent, 7, 0); if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) cpuid_entry_change(best, X86_FEATURE_OSPKE, - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)); + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); best = cpuid_entry2_find(entries, nent, 0xD, 0); if (best) diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index e50d353b5c1c..75eae9c4998a 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -157,6 +157,14 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) return vcpu->arch.cr0 & mask; } +static __always_inline bool kvm_is_cr0_bit_set(struct kvm_vcpu *vcpu, + unsigned long cr0_bit) +{ + BUILD_BUG_ON(!is_power_of_2(cr0_bit)); + + return !!kvm_read_cr0_bits(vcpu, cr0_bit); +} + static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu) { return kvm_read_cr0_bits(vcpu, ~0UL); @@ -171,6 +179,14 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) return vcpu->arch.cr4 & mask; } +static __always_inline bool kvm_is_cr4_bit_set(struct kvm_vcpu *vcpu, + unsigned long cr4_bit) +{ + BUILD_BUG_ON(!is_power_of_2(cr4_bit)); + + return !!kvm_read_cr4_bits(vcpu, cr4_bit); +} + static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 168c46fd8dd1..89f532516a45 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -132,7 +132,7 @@ static inline unsigned long kvm_get_pcid(struct kvm_vcpu *vcpu, gpa_t cr3) { BUILD_BUG_ON((X86_CR3_PCID_MASK & PAGE_MASK) != 0); - return kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE) + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE) ? cr3 & X86_CR3_PCID_MASK : 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f4aa170b5b97..bb1733bb5bf9 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -540,9 +540,9 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (!pmc) return 1; - if (!(kvm_read_cr4_bits(vcpu, X86_CR4_PCE)) && + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCE) && (static_call(kvm_x86_get_cpl)(vcpu) != 0) && - (kvm_read_cr0_bits(vcpu, X86_CR0_PE))) + kvm_is_cr0_bit_set(vcpu, X86_CR0_PE)) return 1; *data = pmc_read_counter(pmc) & mask; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 61d940fc91ba..06b2c24d5a74 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5154,7 +5154,7 @@ static int handle_vmxon(struct kvm_vcpu *vcpu) * does force CR0.PE=1, but only to also force VM86 in order to emulate * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e501f6864a72..c3ef74562158 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5180,7 +5180,7 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; - return vmx_get_cpl(vcpu) == 3 && kvm_read_cr0_bits(vcpu, X86_CR0_AM) && + return vmx_get_cpl(vcpu) == 3 && kvm_is_cr0_bit_set(vcpu, X86_CR0_AM) && (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8a66ac7a4878..3fab192862d4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -841,7 +841,7 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { - if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE)) return true; kvm_queue_exception(vcpu, UD_VECTOR); @@ -983,7 +983,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) return 1; if (!(cr0 & X86_CR0_PG) && - (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) + (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -1005,7 +1005,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return; - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); @@ -1019,7 +1019,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (static_cpu_has(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || - kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) write_pkru(vcpu->arch.pkru); #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ } @@ -1033,14 +1033,14 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (static_cpu_has(X86_FEATURE_PKU) && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || - kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) { + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) write_pkru(vcpu->arch.host_pkru); } #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); @@ -1245,7 +1245,7 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB * with PCIDE=0. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) return; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) @@ -1260,9 +1260,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) bool skip_tlb_flush = false; unsigned long pcid = 0; #ifdef CONFIG_X86_64 - bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - - if (pcid_enabled) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; pcid = cr3 & X86_CR3_PCID_MASK; @@ -5051,7 +5049,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || - !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { + !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } @@ -13254,7 +13252,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } - pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); + pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE); switch (type) { case INVPCID_TYPE_INDIV_ADDR: diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a8167b47b8c8..6d68c6772105 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -123,7 +123,7 @@ static inline bool kvm_exception_is_soft(unsigned int nr) static inline bool is_protmode(struct kvm_vcpu *vcpu) { - return kvm_read_cr0_bits(vcpu, X86_CR0_PE); + return kvm_is_cr0_bit_set(vcpu, X86_CR0_PE); } static inline int is_long_mode(struct kvm_vcpu *vcpu) @@ -193,7 +193,7 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu) static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; + return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48; } static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) -- GitLab From bede6eb4db19424477c36dace426ae12255f4a0d Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Wed, 22 Mar 2023 12:58:22 +0800 Subject: [PATCH 1085/5631] KVM: x86: Use boolean return value for is_{pae,pse,paging}() Convert is_{pae,pse,paging}() to use kvm_is_cr{0,4}_bit_set() and return bools. Returning an "int" requires not one, but two implicit casts, first from "unsigned long" to "int", and then again to a "bool". Both casts are more than a bit dangerous; the ulong=>int casts would drop a bit on 64-bit kernels _if_ the bits in question weren't in the lower 32 bits, and the int=>bool cast can result in false negatives/positives, e.g. see commit 0c928ff26bd6 ("KVM: SVM: Fix benign "bool vs. int" comparison in svm_set_cr0()"). Suggested-by: Sean Christopherson Signed-off-by: Binbin Wu Link: https://lore.kernel.org/r/20230322045824.22970-3-binbin.wu@linux.intel.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/svm.c | 2 +- arch/x86/kvm/x86.h | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 19794a8ea28c..70183d2271b5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1802,7 +1802,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; - if (old_paging != !!is_paging(vcpu)) + if (old_paging != is_paging(vcpu)) svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 6d68c6772105..577b82358529 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -171,19 +171,19 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline int is_pae(struct kvm_vcpu *vcpu) +static inline bool is_pae(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PAE); } -static inline int is_pse(struct kvm_vcpu *vcpu) +static inline bool is_pse(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_PSE); + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PSE); } -static inline int is_paging(struct kvm_vcpu *vcpu) +static inline bool is_paging(struct kvm_vcpu *vcpu) { - return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG)); + return likely(kvm_is_cr0_bit_set(vcpu, X86_CR0_PG)); } static inline bool is_pae_paging(struct kvm_vcpu *vcpu) -- GitLab From 627778bfcfa1ff81acfe863dcc4316edd0a51276 Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Wed, 22 Mar 2023 12:58:23 +0800 Subject: [PATCH 1086/5631] KVM: SVM: Use kvm_is_cr4_bit_set() to query SMAP/SMEP in "can emulate" Use kvm_is_cr4_bit_set() to query SMAP and SMEP when determining whether or not AMD's SMAP+SEV errata prevents KVM from emulating an instruction. This eliminates an implicit cast from ulong to bool and makes the code slightly more readable. Note, any overhead from making multiple calls to kvm_read_cr4_bits() is negligible, not to mention the code is question is encountered only in rare situations, i.e. is not a remotely hot path. Suggested-by: Sean Christopherson Signed-off-by: Binbin Wu Link: https://lore.kernel.org/r/20230322045824.22970-4-binbin.wu@linux.intel.com [sean: keep local smap/smep variables, massage changelog] Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/svm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 70183d2271b5..9c707dd7349a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4545,7 +4545,6 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { bool smep, smap, is_user; - unsigned long cr4; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ @@ -4637,9 +4636,8 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) goto resume_guest; - cr4 = kvm_read_cr4(vcpu); - smep = cr4 & X86_CR4_SMEP; - smap = cr4 & X86_CR4_SMAP; + smep = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMEP); + smap = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMAP); is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); -- GitLab From 6dddd93938b3651cfeba7158ac179b4e6d3c1553 Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Sun, 19 Feb 2023 08:13:28 +0000 Subject: [PATCH 1087/5631] RDMA/efa: Add data polling capability feature bit Add feature bit to existing device caps field. EFA supports data polling of 128 bytes blocks. The flag indicates that the NIC guarentees that a 128 byte aligned block is written in order, ie that observing the last 8 bits of the block mean the prior 127 bytes are also written. It is useful for "last data polling" acceleration techniques. Link: https://lore.kernel.org/r/20230219081328.10419-1-mrgolin@amazon.com Reviewed-by: Yehuda Yitschak Reviewed-by: Yossi Leybovich Signed-off-by: Yonatan Nachum Signed-off-by: Michael Margolin Acked-by: Gal Pressman Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/efa/efa_admin_cmds_defs.h | 7 +++++-- drivers/infiniband/hw/efa/efa_verbs.c | 5 ++++- include/uapi/rdma/efa-abi.h | 3 ++- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h index d4b9226088bd..3db791e6c030 100644 --- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h +++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_ADMIN_CMDS_H_ @@ -618,7 +618,9 @@ struct efa_admin_feature_device_attr_desc { * TX queues * 1 : rnr_retry - If set, RNR retry is supported on * modify QP command - * 31:2 : reserved - MBZ + * 2 : data_polling_128 - If set, 128 bytes data + * polling is supported + * 31:3 : reserved - MBZ */ u32 device_caps; @@ -991,6 +993,7 @@ struct efa_admin_host_info { /* feature_device_attr_desc */ #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK BIT(0) #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK BIT(1) +#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_DATA_POLLING_128_MASK BIT(2) /* create_eq_cmd */ #define EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS_MASK GENMASK(4, 0) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 31454643f8c5..c20136e9d3d1 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include @@ -250,6 +250,9 @@ int efa_query_device(struct ib_device *ibdev, if (EFA_DEV_CAP(dev, RNR_RETRY)) resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RNR_RETRY; + if (EFA_DEV_CAP(dev, DATA_POLLING_128)) + resp.device_caps |= EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128; + if (dev->neqs) resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS; diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 163ac79556d6..74406b4817ce 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) */ /* - * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef EFA_ABI_USER_H @@ -120,6 +120,7 @@ enum { EFA_QUERY_DEVICE_CAPS_RNR_RETRY = 1 << 1, EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2, EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID = 1 << 3, + EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4, }; struct efa_ibv_ex_query_device_resp { -- GitLab From b72d6965eeac4503445ab64bc0aede4934e0a7a6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 16 Feb 2023 21:39:58 +0200 Subject: [PATCH 1088/5631] x86/platform/intel-mid: Remove unused definitions from intel-mid.h After a few rounds of removal and refactoring Intel MID related code some artifacts are left untouched. However, they are not used anywhere. Remove them. Signed-off-by: Andy Shevchenko Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20230216193958.2971-1-andriy.shevchenko%40linux.intel.com --- arch/x86/include/asm/intel-mid.h | 21 --------------------- 1 file changed, 21 deletions(-) diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index c201083b34f6..a3abdcd89a32 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -20,25 +20,4 @@ extern void intel_mid_pwr_power_off(void); extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); -#ifdef CONFIG_X86_INTEL_MID - -extern void intel_scu_devices_create(void); -extern void intel_scu_devices_destroy(void); - -#else /* !CONFIG_X86_INTEL_MID */ - -static inline void intel_scu_devices_create(void) { } -static inline void intel_scu_devices_destroy(void) { } - -#endif /* !CONFIG_X86_INTEL_MID */ - -/* Bus Select SoC Fuse value */ -#define BSEL_SOC_FUSE_MASK 0x7 -/* FSB 133MHz */ -#define BSEL_SOC_FUSE_001 0x1 -/* FSB 100MHz */ -#define BSEL_SOC_FUSE_101 0x5 -/* FSB 83MHz */ -#define BSEL_SOC_FUSE_111 0x7 - #endif /* _ASM_X86_INTEL_MID_H */ -- GitLab From 7a3a401874bea02f568aa416ac29170d8cde0dc2 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 21 Mar 2023 03:35:11 +0300 Subject: [PATCH 1089/5631] x86/tdx: Drop flags from __tdx_hypercall() After TDX_HCALL_ISSUE_STI got dropped, the only flag left is TDX_HCALL_HAS_OUTPUT. The flag indicates if the caller wants to see tdx_hypercall_args updated based on the hypercall output. Drop the flags and provide __tdx_hypercall_ret() that matches TDX_HCALL_HAS_OUTPUT semantics. Suggested-by: Peter Zijlstra Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20230321003511.9469-1-kirill.shutemov%40linux.intel.com --- arch/x86/boot/compressed/tdx.c | 4 +- arch/x86/coco/tdx/tdcall.S | 66 ++++++++++++++++++------------- arch/x86/coco/tdx/tdx.c | 18 ++++----- arch/x86/include/asm/shared/tdx.h | 5 +-- 4 files changed, 51 insertions(+), 42 deletions(-) diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c index 918a7606f53c..2d81d3cc72a1 100644 --- a/arch/x86/boot/compressed/tdx.c +++ b/arch/x86/boot/compressed/tdx.c @@ -26,7 +26,7 @@ static inline unsigned int tdx_io_in(int size, u16 port) .r14 = port, }; - if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + if (__tdx_hypercall_ret(&args)) return UINT_MAX; return args.r11; @@ -43,7 +43,7 @@ static inline void tdx_io_out(int size, u16 port, u32 value) .r15 = value, }; - __tdx_hypercall(&args, 0); + __tdx_hypercall(&args); } static inline u8 tdx_inb(u16 port) diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S index 6a255e6809bc..b193c0a1d8db 100644 --- a/arch/x86/coco/tdx/tdcall.S +++ b/arch/x86/coco/tdx/tdcall.S @@ -85,12 +85,12 @@ SYM_FUNC_START(__tdx_module_call) SYM_FUNC_END(__tdx_module_call) /* - * __tdx_hypercall() - Make hypercalls to a TDX VMM using TDVMCALL leaf - * of TDCALL instruction + * TDX_HYPERCALL - Make hypercalls to a TDX VMM using TDVMCALL leaf of TDCALL + * instruction * * Transforms values in function call argument struct tdx_hypercall_args @args * into the TDCALL register ABI. After TDCALL operation, VMM output is saved - * back in @args. + * back in @args, if \ret is 1. * *------------------------------------------------------------------------- * TD VMCALL ABI: @@ -105,26 +105,18 @@ SYM_FUNC_END(__tdx_module_call) * specification. Non zero value indicates vendor * specific ABI. * R11 - VMCALL sub function number - * RBX, RBP, RDI, RSI - Used to pass VMCALL sub function specific arguments. + * RBX, RDX, RDI, RSI - Used to pass VMCALL sub function specific arguments. * R8-R9, R12-R15 - Same as above. * * Output Registers: * * RAX - TDCALL instruction status (Not related to hypercall * output). - * R10 - Hypercall output error code. - * R11-R15 - Hypercall sub function specific output values. + * RBX, RDX, RDI, RSI - Hypercall sub function specific output values. + * R8-R15 - Same as above. * - *------------------------------------------------------------------------- - * - * __tdx_hypercall() function ABI: - * - * @args (RDI) - struct tdx_hypercall_args for input and output - * @flags (RSI) - TDX_HCALL_* flags - * - * On successful completion, return the hypercall error code. */ -SYM_FUNC_START(__tdx_hypercall) +.macro TDX_HYPERCALL ret:req FRAME_BEGIN /* Save callee-saved GPRs as mandated by the x86_64 ABI */ @@ -134,9 +126,8 @@ SYM_FUNC_START(__tdx_hypercall) push %r12 push %rbx - /* Free RDI and RSI to be used as TDVMCALL arguments */ + /* Free RDI to be used as TDVMCALL arguments */ movq %rdi, %rax - push %rsi /* Copy hypercall registers from arg struct: */ movq TDX_HYPERCALL_r8(%rax), %r8 @@ -171,14 +162,11 @@ SYM_FUNC_START(__tdx_hypercall) * and are handled by callers. */ testq %rax, %rax - jne .Lpanic + jne .Lpanic\@ pop %rax - /* Copy hypercall result registers to arg struct if needed */ - testq $TDX_HCALL_HAS_OUTPUT, (%rsp) - jz .Lout - + .if \ret movq %r8, TDX_HYPERCALL_r8(%rax) movq %r9, TDX_HYPERCALL_r9(%rax) movq %r10, TDX_HYPERCALL_r10(%rax) @@ -191,7 +179,8 @@ SYM_FUNC_START(__tdx_hypercall) movq %rsi, TDX_HYPERCALL_rsi(%rax) movq %rbx, TDX_HYPERCALL_rbx(%rax) movq %rdx, TDX_HYPERCALL_rdx(%rax) -.Lout: + .endif + /* TDVMCALL leaf return code is in R10 */ movq %r10, %rax @@ -208,9 +197,6 @@ SYM_FUNC_START(__tdx_hypercall) xor %rdi, %rdi xor %rdx, %rdx - /* Remove TDX_HCALL_* flags from the stack */ - pop %rsi - /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ pop %rbx pop %r12 @@ -221,9 +207,33 @@ SYM_FUNC_START(__tdx_hypercall) FRAME_END RET -.Lpanic: +.Lpanic\@: call __tdx_hypercall_failed /* __tdx_hypercall_failed never returns */ REACHABLE - jmp .Lpanic + jmp .Lpanic\@ +.endm + +/* + * + * __tdx_hypercall() function ABI: + * + * @args (RDI) - struct tdx_hypercall_args for input + * + * On successful completion, return the hypercall error code. + */ +SYM_FUNC_START(__tdx_hypercall) + TDX_HYPERCALL ret=0 SYM_FUNC_END(__tdx_hypercall) + +/* + * + * __tdx_hypercall_ret() function ABI: + * + * @args (RDI) - struct tdx_hypercall_args for input and output + * + * On successful completion, return the hypercall error code. + */ +SYM_FUNC_START(__tdx_hypercall_ret) + TDX_HYPERCALL ret=1 +SYM_FUNC_END(__tdx_hypercall_ret) diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 055300e08fb3..e146b599260f 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -66,7 +66,7 @@ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) .r15 = r15, }; - return __tdx_hypercall(&args, 0); + return __tdx_hypercall(&args); } /* Called from __tdx_hypercall() for unrecoverable failure */ @@ -99,7 +99,7 @@ long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, .r14 = p4, }; - return __tdx_hypercall(&args, 0); + return __tdx_hypercall(&args); } EXPORT_SYMBOL_GPL(tdx_kvm_hypercall); #endif @@ -179,7 +179,7 @@ static void __noreturn tdx_panic(const char *msg) * happens to return. */ while (1) - __tdx_hypercall(&args, 0); + __tdx_hypercall(&args); } static void tdx_parse_tdinfo(u64 *cc_mask) @@ -289,7 +289,7 @@ static u64 __cpuidle __halt(const bool irq_disabled) * can keep the vCPU in virtual HLT, even if an IRQ is * pending, without hanging/breaking the guest. */ - return __tdx_hypercall(&args, 0); + return __tdx_hypercall(&args); } static int handle_halt(struct ve_info *ve) @@ -326,7 +326,7 @@ static int read_msr(struct pt_regs *regs, struct ve_info *ve) * can be found in TDX Guest-Host-Communication Interface * (GHCI), section titled "TDG.VP.VMCALL". */ - if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + if (__tdx_hypercall_ret(&args)) return -EIO; regs->ax = lower_32_bits(args.r11); @@ -348,7 +348,7 @@ static int write_msr(struct pt_regs *regs, struct ve_info *ve) * can be found in TDX Guest-Host-Communication Interface * (GHCI) section titled "TDG.VP.VMCALL". */ - if (__tdx_hypercall(&args, 0)) + if (__tdx_hypercall(&args)) return -EIO; return ve_instr_len(ve); @@ -380,7 +380,7 @@ static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) * ABI can be found in TDX Guest-Host-Communication Interface * (GHCI), section titled "VP.VMCALL". */ - if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + if (__tdx_hypercall_ret(&args)) return -EIO; /* @@ -407,7 +407,7 @@ static bool mmio_read(int size, unsigned long addr, unsigned long *val) .r15 = *val, }; - if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) + if (__tdx_hypercall_ret(&args)) return false; *val = args.r11; return true; @@ -541,7 +541,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port) * in TDX Guest-Host-Communication Interface (GHCI) section titled * "TDG.VP.VMCALL". */ - success = !__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT); + success = !__tdx_hypercall_ret(&args); /* Update part of the register affected by the emulated instruction */ regs->ax &= ~mask; diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 4a03993e0785..2631e01f6e0f 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -7,8 +7,6 @@ #define TDX_HYPERCALL_STANDARD 0 -#define TDX_HCALL_HAS_OUTPUT BIT(0) - #define TDX_CPUID_LEAF_ID 0x21 #define TDX_IDENT "IntelTDX " @@ -36,7 +34,8 @@ struct tdx_hypercall_args { }; /* Used to request services from the VMM */ -u64 __tdx_hypercall(struct tdx_hypercall_args *args, unsigned long flags); +u64 __tdx_hypercall(struct tdx_hypercall_args *args); +u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args); /* Called from __tdx_hypercall() for unrecoverable failure */ void __tdx_hypercall_failed(void); -- GitLab From 3f6cc47f5eb40d96ce8cf443282a2c29fd629a76 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:32:47 -0800 Subject: [PATCH 1090/5631] x86: Simplify one-level sysctl registration for abi_table2 There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20230310233248.3965389-2-mcgrof%40kernel.org --- arch/x86/entry/vdso/vdso32-setup.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 3b300a773c7e..f3b3cacbcbb0 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -70,18 +70,9 @@ static struct ctl_table abi_table2[] = { {} }; -static struct ctl_table abi_root_table2[] = { - { - .procname = "abi", - .mode = 0555, - .child = abi_table2 - }, - {} -}; - static __init int ia32_binfmt_init(void) { - register_sysctl_table(abi_root_table2); + register_sysctl("abi", abi_table2); return 0; } __initcall(ia32_binfmt_init); -- GitLab From 89d7971eb2318595bc3b6ab7c5caede112c302ff Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 15:32:48 -0800 Subject: [PATCH 1091/5631] x86: Simplify one-level sysctl registration for itmt_kern_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20230310233248.3965389-3-mcgrof%40kernel.org --- arch/x86/kernel/itmt.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 9ff480e94511..670eb08b972a 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -77,15 +77,6 @@ static struct ctl_table itmt_kern_table[] = { {} }; -static struct ctl_table itmt_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = itmt_kern_table, - }, - {} -}; - static struct ctl_table_header *itmt_sysctl_header; /** @@ -114,7 +105,7 @@ int sched_set_itmt_support(void) return 0; } - itmt_sysctl_header = register_sysctl_table(itmt_root_table); + itmt_sysctl_header = register_sysctl("kernel", itmt_kern_table); if (!itmt_sysctl_header) { mutex_unlock(&itmt_update_mutex); return -ENOMEM; -- GitLab From 5faaffab5ba8cd4f3781b90cccd47440b54aea5b Mon Sep 17 00:00:00 2001 From: Santosh Shukla Date: Mon, 27 Feb 2023 14:10:06 +0530 Subject: [PATCH 1092/5631] KVM: nSVM: Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting VINTR Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting virtual interrupts in order to request an interrupt window, as KVM has usurped vmcb02's int_ctl. If an interrupt window opens before the next VM-Exit, svm_clear_vintr() will restore vmcb12's int_ctl. If no window opens, V_IRQ will be correctly preserved in vmcb12's int_ctl (because it was never recognized while L2 was running). Suggested-by: Sean Christopherson Link: https://lkml.kernel.org/r/Y9hybI65So5X2LFg%40google.com Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-2-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/nested.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 05d38944a6c0..a77055d96e31 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -416,18 +416,17 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm) /* Only a few fields of int_ctl are written by the processor. */ mask = V_IRQ_MASK | V_TPR_MASK; - if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) && - svm_is_intercept(svm, INTERCEPT_VINTR)) { - /* - * In order to request an interrupt window, L0 is usurping - * svm->vmcb->control.int_ctl and possibly setting V_IRQ - * even if it was clear in L1's VMCB. Restoring it would be - * wrong. However, in this case V_IRQ will remain true until - * interrupt_window_interception calls svm_clear_vintr and - * restores int_ctl. We can just leave it aside. - */ + /* + * Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting + * virtual interrupts in order to request an interrupt window, as KVM + * has usurped vmcb02's int_ctl. If an interrupt window opens before + * the next VM-Exit, svm_clear_vintr() will restore vmcb12's int_ctl. + * If no window opens, V_IRQ will be correctly preserved in vmcb12's + * int_ctl (because it was never recognized while L2 was running). + */ + if (svm_is_intercept(svm, INTERCEPT_VINTR) && + !test_bit(INTERCEPT_VINTR, (unsigned long *)svm->nested.ctl.intercepts)) mask &= ~V_IRQ_MASK; - } if (nested_vgif_enabled(svm)) mask |= V_GIF_MASK; -- GitLab From 7334ede457c6f1f7a26344ed25928f63f9a53a8d Mon Sep 17 00:00:00 2001 From: Santosh Shukla Date: Mon, 27 Feb 2023 14:10:07 +0530 Subject: [PATCH 1093/5631] KVM: nSVM: Disable intercept of VINTR if saved L1 host RFLAGS.IF is 0 Disable intercept of virtual interrupts (used to detect interrupt windows) if the saved host (L1) RFLAGS.IF is '0', as the effective RFLAGS.IF for L1 interrupts will never be set while L2 is running (L2's RFLAGS.IF doesn't affect L1 IRQs when virtual interrupts are enabled). Suggested-by: Sean Christopherson Link: https://lkml.kernel.org/r/Y9hybI65So5X2LFg%40google.com Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-3-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/nested.c | 15 ++++++++++----- arch/x86/kvm/svm/svm.c | 10 ++++++++++ 2 files changed, 20 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index a77055d96e31..a0a525758ed9 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -139,13 +139,18 @@ void recalc_intercepts(struct vcpu_svm *svm) if (g->int_ctl & V_INTR_MASKING_MASK) { /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8 - * does not affect any interrupt we may want to inject; - * therefore, writes to CR8 are irrelevant to L0, as are - * interrupt window vmexits. + * If L2 is active and V_INTR_MASKING is enabled in vmcb12, + * disable intercept of CR8 writes as L2's CR8 does not affect + * any interrupt KVM may want to inject. + * + * Similarly, disable intercept of virtual interrupts (used to + * detect interrupt windows) if the saved RFLAGS.IF is '0', as + * the effective RFLAGS.IF for L1 interrupts will never be set + * while L2 is running (L2's RFLAGS.IF doesn't affect L1 IRQs). */ vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); - vmcb_clr_intercept(c, INTERCEPT_VINTR); + if (!(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)) + vmcb_clr_intercept(c, INTERCEPT_VINTR); } /* diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 70183d2271b5..e347225b3914 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1583,6 +1583,16 @@ static void svm_set_vintr(struct vcpu_svm *svm) svm_set_intercept(svm, INTERCEPT_VINTR); + /* + * Recalculating intercepts may have cleared the VINTR intercept. If + * V_INTR_MASKING is enabled in vmcb12, then the effective RFLAGS.IF + * for L1 physical interrupts is L1's RFLAGS.IF at the time of VMRUN. + * Requesting an interrupt window if save.RFLAGS.IF=0 is pointless as + * interrupts will never be unblocked while L2 is running. + */ + if (!svm_is_intercept(svm, INTERCEPT_VINTR)) + return; + /* * This is just a dummy VINTR to actually cause a vmexit to happen. * Actual injection of virtual interrupts happens through EVENTINJ. -- GitLab From af48ab8b39ee9e4c4593a5da6e2501ebb8f99b12 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Mar 2023 09:36:46 +0100 Subject: [PATCH 1094/5631] ACPI: LPIT: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. Cc: Len Brown Cc: linux-acpi@vger.kernel.org Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230322083646.2937580-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/acpi_lpit.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index 3843d2576d3f..c5598b6d5db8 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -98,6 +98,12 @@ EXPORT_SYMBOL_GPL(lpit_read_residency_count_address); static void lpit_update_residency(struct lpit_residency_info *info, struct acpi_lpit_native *lpit_native) { + struct device *dev_root = bus_get_dev_root(&cpu_subsys); + + /* Silently fail, if cpuidle attribute group is not present */ + if (!dev_root) + return; + info->frequency = lpit_native->counter_frequency ? lpit_native->counter_frequency : tsc_khz * 1000; if (!info->frequency) @@ -108,18 +114,18 @@ static void lpit_update_residency(struct lpit_residency_info *info, info->iomem_addr = ioremap(info->gaddr.address, info->gaddr.bit_width / 8); if (!info->iomem_addr) - return; + goto exit; - /* Silently fail, if cpuidle attribute group is not present */ - sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, + sysfs_add_file_to_group(&dev_root->kobj, &dev_attr_low_power_idle_system_residency_us.attr, "cpuidle"); } else if (info->gaddr.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) { - /* Silently fail, if cpuidle attribute group is not present */ - sysfs_add_file_to_group(&cpu_subsys.dev_root->kobj, + sysfs_add_file_to_group(&dev_root->kobj, &dev_attr_low_power_idle_cpu_residency_us.attr, "cpuidle"); } +exit: + put_device(dev_root); } static void lpit_process(u64 begin, u64 end) -- GitLab From bf6479dbe743ca343fa122aaffbe9dcb1de80a51 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 22 Mar 2023 10:05:57 +0100 Subject: [PATCH 1095/5631] cpuidle: move to use bus_get_dev_root() Direct access to the struct bus_type dev_root pointer is going away soon so replace that with a call to bus_get_dev_root() instead, which is what it is there for. This allows us to clean up the cpuidle_add_interface() call a bit as it was only called in one place, with the same argument so just put that into the function itself. Note that cpuidle_remove_interface() should also probably be removed in the future as there are no callers of it for some reason. Cc: Daniel Lezcano Cc: linux-pm@vger.kernel.org Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230322090557.2943479-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/cpuidle/cpuidle.c | 2 +- drivers/cpuidle/cpuidle.h | 2 +- drivers/cpuidle/sysfs.c | 13 ++++++++++--- 3 files changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0b00f21cefe3..8e929f6602ce 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -808,7 +808,7 @@ static int __init cpuidle_init(void) if (cpuidle_disabled()) return -ENODEV; - return cpuidle_add_interface(cpu_subsys.dev_root); + return cpuidle_add_interface(); } module_param(off, int, 0444); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index 9f336af17fa6..52701d9588f1 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -30,7 +30,7 @@ extern int cpuidle_switch_governor(struct cpuidle_governor *gov); struct device; -extern int cpuidle_add_interface(struct device *dev); +extern int cpuidle_add_interface(void); extern void cpuidle_remove_interface(struct device *dev); extern int cpuidle_add_device_sysfs(struct cpuidle_device *device); extern void cpuidle_remove_device_sysfs(struct cpuidle_device *device); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index 48948b171749..d6f5da61cb7d 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -119,11 +119,18 @@ static struct attribute_group cpuidle_attr_group = { /** * cpuidle_add_interface - add CPU global sysfs attributes - * @dev: the target device */ -int cpuidle_add_interface(struct device *dev) +int cpuidle_add_interface(void) { - return sysfs_create_group(&dev->kobj, &cpuidle_attr_group); + struct device *dev_root = bus_get_dev_root(&cpu_subsys); + int retval; + + if (!dev_root) + return -EINVAL; + + retval = sysfs_create_group(&dev_root->kobj, &cpuidle_attr_group); + put_device(dev_root); + return retval; } /** -- GitLab From 5d1ec4565200f461943990f0988932ca86823087 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 27 Feb 2023 14:10:08 +0530 Subject: [PATCH 1096/5631] KVM: nSVM: Raise event on nested VM exit if L1 doesn't intercept IRQs If L1 doesn't intercept interrupts, then KVM will use vmcb02's V_IRQ to detect an interrupt window for L1 IRQs. On a subsequent nested VM-Exit, KVM might need to copy the current V_IRQ from vmcb02 to vmcb01 to continue waiting for an interrupt window, i.e. if there is still a pending IRQ for L1. Raise KVM_REQ_EVENT on nested exit if L1 isn't intercepting IRQs to ensure that KVM will re-enable interrupt window detection if needed. Note that this is a theoretical bug because KVM already raises KVM_REQ_EVENT on each nested VM exit, because the nested VM exit resets RFLAGS and kvm_set_rflags() raises the KVM_REQ_EVENT unconditionally. Explicitly raise KVM_REQ_EVENT for the interrupt window case to avoid having an unnecessary dependency on kvm_set_rflags(), and to document the scenario. Signed-off-by: Maxim Levitsky [santosh: reworded description as per Sean's v2 comment] Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-4-santosh.shukla@amd.com [sean: further massage changelog and comment] Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/nested.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index a0a525758ed9..8300fd31878d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1025,6 +1025,28 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm_switch_vmcb(svm, &svm->vmcb01); + /* + * Rules for synchronizing int_ctl bits from vmcb02 to vmcb01: + * + * V_IRQ, V_IRQ_VECTOR, V_INTR_PRIO_MASK, V_IGN_TPR: If L1 doesn't + * intercept interrupts, then KVM will use vmcb02's V_IRQ (and related + * flags) to detect interrupt windows for L1 IRQs (even if L1 uses + * virtual interrupt masking). Raise KVM_REQ_EVENT to ensure that + * KVM re-requests an interrupt window if necessary, which implicitly + * copies this bits from vmcb02 to vmcb01. + * + * V_TPR: If L1 doesn't use virtual interrupt masking, then L1's vTPR + * is stored in vmcb02, but its value doesn't need to be copied from/to + * vmcb01 because it is copied from/to the virtual APIC's TPR register + * on each VM entry/exit. + * + * V_GIF: If nested vGIF is not used, KVM uses vmcb02's V_GIF for L1's + * V_GIF. However, GIF is architecturally clear on each VM exit, thus + * there is no need to copy V_GIF from vmcb02 to vmcb01. + */ + if (!nested_exit_on_intr(svm)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); -- GitLab From 772f254d4d5687ee349cbe443959bc01304880d6 Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Mon, 27 Feb 2023 14:10:09 +0530 Subject: [PATCH 1097/5631] KVM: SVM: add wrappers to enable/disable IRET interception SEV-ES guests don't use IRET interception for the detection of an end of a NMI. Therefore it makes sense to create a wrapper to avoid repeating the check for the SEV-ES. No functional change is intended. Suggested-by: Sean Christopherson Signed-off-by: Maxim Levitsky [Renamed iret intercept API of style svm_{clr,set}_iret_intercept()] Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-5-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/svm.c | 28 +++++++++++++++++++--------- 1 file changed, 19 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e347225b3914..69ace08ab1e4 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2490,16 +2490,29 @@ static int task_switch_interception(struct kvm_vcpu *vcpu) has_error_code, error_code); } +static void svm_clr_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_clr_intercept(svm, INTERCEPT_IRET); +} + +static void svm_set_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_IRET); +} + static int iret_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); ++vcpu->stat.nmi_window_exits; svm->awaiting_iret_completion = true; - if (!sev_es_guest(vcpu->kvm)) { - svm_clr_intercept(svm, INTERCEPT_IRET); + + svm_clr_iret_intercept(svm); + if (!sev_es_guest(vcpu->kvm)) svm->nmi_iret_rip = kvm_rip_read(vcpu); - } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } @@ -3508,8 +3521,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) return; svm->nmi_masked = true; - if (!sev_es_guest(vcpu->kvm)) - svm_set_intercept(svm, INTERCEPT_IRET); + svm_set_iret_intercept(svm); ++vcpu->stat.nmi_injections; } @@ -3649,12 +3661,10 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) if (masked) { svm->nmi_masked = true; - if (!sev_es_guest(vcpu->kvm)) - svm_set_intercept(svm, INTERCEPT_IRET); + svm_set_iret_intercept(svm); } else { svm->nmi_masked = false; - if (!sev_es_guest(vcpu->kvm)) - svm_clr_intercept(svm, INTERCEPT_IRET); + svm_clr_iret_intercept(svm); } } -- GitLab From 2cb9317377caaec647d7485bc53ab33a0b54f27c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 27 Feb 2023 14:10:10 +0530 Subject: [PATCH 1098/5631] KVM: x86: Raise an event request when processing NMIs if an NMI is pending Don't raise KVM_REQ_EVENT if no NMIs are pending at the end of process_nmi(). Finishing process_nmi() without a pending NMI will become much more likely when KVM gains support for AMD's vNMI, which allows pending vNMIs in hardware, i.e. doesn't require explicit injection. Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-6-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..3c995483b405 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10150,7 +10150,9 @@ static void process_nmi(struct kvm_vcpu *vcpu) vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); - kvm_make_request(KVM_REQ_EVENT, vcpu); + + if (vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); } void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, -- GitLab From 400fee8c9b2df61721de8103a4054247bea79fd0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 27 Feb 2023 14:10:11 +0530 Subject: [PATCH 1099/5631] KVM: x86: Tweak the code and comment related to handling concurrent NMIs Tweak the code and comment that deals with concurrent NMIs to explicitly call out that x86 allows exactly one pending NMI, but that KVM needs to temporarily allow two pending NMIs in order to workaround the fact that the target vCPU cannot immediately recognize an incoming NMI, unlike bare metal. No functional change intended. Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-7-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3c995483b405..e317559df489 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10138,15 +10138,22 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, static void process_nmi(struct kvm_vcpu *vcpu) { - unsigned limit = 2; + unsigned int limit; /* - * x86 is limited to one NMI running, and one NMI pending after it. - * If an NMI is already in progress, limit further NMIs to just one. - * Otherwise, allow two (and we'll inject the first one immediately). + * x86 is limited to one NMI pending, but because KVM can't react to + * incoming NMIs as quickly as bare metal, e.g. if the vCPU is + * scheduled out, KVM needs to play nice with two queued NMIs showing + * up at the same time. To handle this scenario, allow two NMIs to be + * (temporarily) pending so long as NMIs are not blocked and KVM is not + * waiting for a previous NMI injection to complete (which effectively + * blocks NMIs). KVM will immediately inject one of the two NMIs, and + * will request an NMI window to handle the second NMI. */ if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; + else + limit = 2; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); -- GitLab From ab2ee212a57bf136b896a47ce37da38a1fdbdc36 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 27 Feb 2023 14:10:12 +0530 Subject: [PATCH 1100/5631] KVM: x86: Save/restore all NMIs when multiple NMIs are pending Save all pending NMIs in KVM_GET_VCPU_EVENTS, and queue KVM_REQ_NMI if one or more NMIs are pending after KVM_SET_VCPU_EVENTS in order to re-evaluate pending NMIs with respect to NMI blocking. KVM allows multiple NMIs to be pending in order to faithfully emulate bare metal handling of simultaneous NMIs (on bare metal, truly simultaneous NMIs are impossible, i.e. one will always arrive first and be consumed). Support for simultaneous NMIs botched the save/restore though. KVM only saves one pending NMI, but allows userspace to restore 255 pending NMIs as kvm_vcpu_events.nmi.pending is a u8, and KVM's internal state is stored in an unsigned int. Fixes: 7460fb4a3400 ("KVM: Fix simultaneous NMIs") Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-8-santosh.shukla@amd.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e317559df489..f18f740f75d8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5125,7 +5125,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending != 0; + events->nmi.pending = vcpu->arch.nmi_pending; events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ @@ -5212,8 +5212,11 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; - if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { vcpu->arch.nmi_pending = events->nmi.pending; + if (vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_NMI, vcpu); + } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && -- GitLab From 3763bf58029f3459d7187f687eadfc8eb08e5ca8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 22 Mar 2023 11:33:08 -0700 Subject: [PATCH 1101/5631] x86/cpufeatures: Redefine synthetic virtual NMI bit as AMD's "real" vNMI The existing X86_FEATURE_VNMI is a synthetic feature flag that exists purely to maintain /proc/cpuinfo's ABI, the "real" Intel vNMI feature flag is tracked as VMX_FEATURE_VIRTUAL_NMIS, as the feature is enumerated through VMX MSRs, not CPUID. AMD is also gaining virtual NMI support, but in true VMX vs. SVM form, enumerates support through CPUID, i.e. wants to add real feature flag for vNMI. Redefine the syntheic X86_FEATURE_VNMI to AMD's real CPUID bit to avoid having both X86_FEATURE_VNMI and e.g. X86_FEATURE_AMD_VNMI. Signed-off-by: Sean Christopherson --- arch/x86/include/asm/cpufeatures.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73c9672c123b..ced9e1832589 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -369,6 +368,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ -- GitLab From ad9c29f3c29197aa25d26a5f258a98e4cb901996 Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Fri, 20 Jan 2023 16:18:57 -0800 Subject: [PATCH 1102/5631] Documentation/x86: Explain the purpose for dynamic features This summary will help to guide the proper use of the enabling model. Signed-off-by: Chang S. Bae Signed-off-by: Dave Hansen Reviewed-by: Tony Luck Link: https://lore.kernel.org/all/20230121001900.14900-2-chang.seok.bae%40intel.com --- Documentation/x86/xstate.rst | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst index 5cec7fb558d6..e954e79af4ce 100644 --- a/Documentation/x86/xstate.rst +++ b/Documentation/x86/xstate.rst @@ -11,6 +11,22 @@ are enabled by XCR0 as well, but the first use of related instruction is trapped by the kernel because by default the required large XSTATE buffers are not allocated automatically. +The purpose for dynamic features +-------------------------------- + +Legacy userspace libraries often have hard-coded, static sizes for +alternate signal stacks, often using MINSIGSTKSZ which is typically 2KB. +That stack must be able to store at *least* the signal frame that the +kernel sets up before jumping into the signal handler. That signal frame +must include an XSAVE buffer defined by the CPU. + +However, that means that the size of signal stacks is dynamic, not static, +because different CPUs have differently-sized XSAVE buffers. A compiled-in +size of 2KB with existing applications is too small for new CPU features +like AMX. Instead of universally requiring larger stack, with the dynamic +enabling, the kernel can enforce userspace applications to have +properly-sized altstacks. + Using dynamically enabled XSTATE features in user space applications -------------------------------------------------------------------- -- GitLab From a03c376ebaf38394a63a75292329f38a47520c2c Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Fri, 20 Jan 2023 16:18:58 -0800 Subject: [PATCH 1103/5631] x86/arch_prctl: Add AMX feature numbers as ABI constants Each distinct XSAVE feature has a number assigned to it. Among other things, the number determines the ordering of features in the XSAVE buffer and is also used to generate XSAVE bitmasks like the value for XCR0. AMX state is dynamically enabled by the architecture-specific prctl(). This prctl() takes one XSAVE feature number as an argument. However, the feature numbers are not defined in any readily available userspace headers. The means that each userspace app trying to use dynamic feature prctl()s will likely end up defining their own constants for each feature. Since these feature numbers are a part of the uabi, expose them in the prctl() uabi header. Save everyone the trouble of looking them up and defining their own. [ dhansen: expand changelog a bit ] Signed-off-by: Chang S. Bae Signed-off-by: Dave Hansen Reviewed-by: Tony Luck Link: https://lore.kernel.org/all/20230121001900.14900-3-chang.seok.bae%40intel.com --- arch/x86/include/uapi/asm/prctl.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..f298c778f856 100644 --- a/arch/x86/include/uapi/asm/prctl.h +++ b/arch/x86/include/uapi/asm/prctl.h @@ -16,6 +16,9 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 -- GitLab From 7f9daaf59e14d62b29b6f4ca743e17bf96ff42ae Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Fri, 20 Jan 2023 16:18:59 -0800 Subject: [PATCH 1104/5631] Documentation/x86: Add the AMX enabling example Explain steps to enable the dynamic feature with a code example. Signed-off-by: Chang S. Bae Signed-off-by: Dave Hansen Reviewed-by: Thiago Macieira Reviewed-by: Bagas Sanjaya Reviewed-by: Tony Luck Link: https://lore.kernel.org/all/20230121001900.14900-4-chang.seok.bae%40intel.com --- Documentation/x86/xstate.rst | 55 ++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst index e954e79af4ce..23b1c9f3efb2 100644 --- a/Documentation/x86/xstate.rst +++ b/Documentation/x86/xstate.rst @@ -80,6 +80,61 @@ the handler allocates a larger xstate buffer for the task so the large state can be context switched. In the unlikely cases that the allocation fails, the kernel sends SIGSEGV. +AMX TILE_DATA enabling example +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Below is the example of how userspace applications enable +TILE_DATA dynamically: + + 1. The application first needs to query the kernel for AMX + support:: + + #include + #include + #include + #include + + #ifndef ARCH_GET_XCOMP_SUPP + #define ARCH_GET_XCOMP_SUPP 0x1021 + #endif + + #ifndef ARCH_XCOMP_TILECFG + #define ARCH_XCOMP_TILECFG 17 + #endif + + #ifndef ARCH_XCOMP_TILEDATA + #define ARCH_XCOMP_TILEDATA 18 + #endif + + #define MASK_XCOMP_TILE ((1 << ARCH_XCOMP_TILECFG) | \ + (1 << ARCH_XCOMP_TILEDATA)) + + unsigned long features; + long rc; + + ... + + rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_SUPP, &features); + + if (!rc && (features & MASK_XCOMP_TILE) == MASK_XCOMP_TILE) + printf("AMX is available.\n"); + + 2. After that, determining support for AMX, an application must + explicitly ask permission to use it:: + + #ifndef ARCH_REQ_XCOMP_PERM + #define ARCH_REQ_XCOMP_PERM 0x1023 + #endif + + ... + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_PERM, ARCH_XCOMP_TILEDATA); + + if (!rc) + printf("AMX is ready for use.\n"); + +Note this example does not include the sigaltstack preparation. + Dynamic features in signal frames --------------------------------- -- GitLab From 5fbff260755750559aa12a30f6fa7f8a863666f1 Mon Sep 17 00:00:00 2001 From: "Chang S. Bae" Date: Fri, 20 Jan 2023 16:19:00 -0800 Subject: [PATCH 1105/5631] Documentation/x86: Explain the state component permission for guests Commit 980fe2fddcff ("x86/fpu: Extend fpu_xstate_prctl() with guest permissions") extends a couple of arch_prctl(2) options for VCPU threads. Add description for them. Signed-off-by: Chang S. Bae Signed-off-by: Dave Hansen Reviewed-by: Thiago Macieira Reviewed-by: Yang Zhong Reviewed-by: Tony Luck Link: https://lore.kernel.org/all/20230121001900.14900-5-chang.seok.bae%40intel.com --- Documentation/x86/xstate.rst | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/Documentation/x86/xstate.rst b/Documentation/x86/xstate.rst index 23b1c9f3efb2..ae5c69e48b11 100644 --- a/Documentation/x86/xstate.rst +++ b/Documentation/x86/xstate.rst @@ -143,3 +143,32 @@ entry if the feature is in its initial configuration. This differs from non-dynamic features which are always written regardless of their configuration. Signal handlers can examine the XSAVE buffer's XSTATE_BV field to determine if a features was written. + +Dynamic features for virtual machines +------------------------------------- + +The permission for the guest state component needs to be managed separately +from the host, as they are exclusive to each other. A coupled of options +are extended to control the guest permission: + +-ARCH_GET_XCOMP_GUEST_PERM + + arch_prctl(ARCH_GET_XCOMP_GUEST_PERM, &features); + + ARCH_GET_XCOMP_GUEST_PERM is a variant of ARCH_GET_XCOMP_PERM. So it + provides the same semantics and functionality but for the guest + components. + +-ARCH_REQ_XCOMP_GUEST_PERM + + arch_prctl(ARCH_REQ_XCOMP_GUEST_PERM, feature_nr); + + ARCH_REQ_XCOMP_GUEST_PERM is a variant of ARCH_REQ_XCOMP_PERM. It has the + same semantics for the guest permission. While providing a similar + functionality, this comes with a constraint. Permission is frozen when the + first VCPU is created. Any attempt to change permission after that point + is going to be rejected. So, the permission has to be requested before the + first VCPU creation. + +Note that some VMMs may have already established a set of supported state +components. These options are not presumed to support any particular VMM. -- GitLab From 68f7c82ab1b8c7057b0c241907ff7906c7407e6d Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Wed, 22 Mar 2023 12:58:24 +0800 Subject: [PATCH 1106/5631] KVM: x86: Change return type of is_long_mode() to bool Change return type of is_long_mode() to bool to avoid implicit cast, as literally every user of is_long_mode() treats its return value as a boolean. Signed-off-by: Binbin Wu Link: https://lore.kernel.org/r/20230322045824.22970-5-binbin.wu@linux.intel.com Reviewed-by: Kai Huang Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 577b82358529..203fb6640b5b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -126,12 +126,12 @@ static inline bool is_protmode(struct kvm_vcpu *vcpu) return kvm_is_cr0_bit_set(vcpu, X86_CR0_PE); } -static inline int is_long_mode(struct kvm_vcpu *vcpu) +static inline bool is_long_mode(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 - return vcpu->arch.efer & EFER_LMA; + return !!(vcpu->arch.efer & EFER_LMA); #else - return 0; + return false; #endif } -- GitLab From 3c17655ab13704582fe25e8ea3200a9b2f8bf20a Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Wed, 15 Mar 2023 13:52:56 +0100 Subject: [PATCH 1107/5631] module/decompress: Never use kunmap() for local un-mappings Use kunmap_local() to unmap pages locally mapped with kmap_local_page(). kunmap_local() must be called on the kernel virtual address returned by kmap_local_page(), differently from how we use kunmap() which instead expects the mapped page as its argument. In module_zstd_decompress() we currently map with kmap_local_page() and unmap with kunmap(). This breaks the code and so it should be fixed. Cc: Piotr Gorski Cc: Dmitry Torokhov Cc: Luis Chamberlain Cc: Stephen Boyd Cc: Ira Weiny Fixes: 169a58ad824d ("module/decompress: Support zstd in-kernel decompression") Signed-off-by: Fabio M. De Francesco Reviewed-by: Stephen Boyd Reviewed-by: Ira Weiny Reviewed-by: Piotr Gorski Signed-off-by: Luis Chamberlain --- kernel/module/decompress.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index bb79ac1a6d8f..7ddc87bee274 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -267,7 +267,7 @@ static ssize_t module_zstd_decompress(struct load_info *info, zstd_dec.size = PAGE_SIZE; ret = zstd_decompress_stream(dstream, &zstd_dec, &zstd_buf); - kunmap(page); + kunmap_local(zstd_dec.dst); retval = zstd_get_error_code(ret); if (retval) break; -- GitLab From 1c4522ab13b163173971d8b0c0eb0b253b1b7f28 Mon Sep 17 00:00:00 2001 From: Santosh Shukla Date: Mon, 27 Feb 2023 14:10:14 +0530 Subject: [PATCH 1108/5631] KVM: SVM: Add definitions for new bits in VMCB::int_ctrl related to vNMI Add defines for three new bits in VMVC::int_ctrl that are part of SVM's Virtual NMI (vNMI) support: V_NMI_PENDING_MASK(11) - Virtual NMI is pending V_NMI_BLOCKING_MASK(12) - Virtual NMI is masked V_NMI_ENABLE_MASK(26) - Enable NMI virtualization To "inject" an NMI, the hypervisor (KVM) sets V_NMI_PENDING. When the CPU services the pending vNMI, hardware clears V_NMI_PENDING and sets V_NMI_BLOCKING, e.g. to indicate that the vCPU is handling an NMI. Hardware clears V_NMI_BLOCKING upon successful execution of IRET, or if a VM-Exit occurs while delivering the virtual NMI. Reviewed-by: Maxim Levitsky Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-10-santosh.shukla@amd.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/svm.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 770dcf75eaa9..25306a420b84 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -183,6 +183,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define V_GIF_SHIFT 9 #define V_GIF_MASK (1 << V_GIF_SHIFT) +#define V_NMI_PENDING_SHIFT 11 +#define V_NMI_PENDING_MASK (1 << V_NMI_PENDING_SHIFT) + +#define V_NMI_BLOCKING_SHIFT 12 +#define V_NMI_BLOCKING_MASK (1 << V_NMI_BLOCKING_SHIFT) + #define V_INTR_PRIO_SHIFT 16 #define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) @@ -197,6 +203,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define V_GIF_ENABLE_SHIFT 25 #define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT) +#define V_NMI_ENABLE_SHIFT 26 +#define V_NMI_ENABLE_MASK (1 << V_NMI_ENABLE_SHIFT) + #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) -- GitLab From bdedff263132c862924f5cad96f0e82eeeb4e2e6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 22 Mar 2023 17:40:16 -0700 Subject: [PATCH 1109/5631] KVM: x86: Route pending NMIs from userspace through process_nmi() Use the asynchronous NMI queue to handle pending NMIs coming in from userspace during KVM_SET_VCPU_EVENTS so that all of KVM's logic for handling multiple NMIs goes through process_nmi(). This will simplify supporting SVM's upcoming "virtual NMI" functionality, which will need changes KVM manages pending NMIs. Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f18f740f75d8..befabb4678f9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5213,9 +5213,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { - vcpu->arch.nmi_pending = events->nmi.pending; - if (vcpu->arch.nmi_pending) - kvm_make_request(KVM_REQ_NMI, vcpu); + vcpu->arch.nmi_pending = 0; + atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); + kvm_make_request(KVM_REQ_NMI, vcpu); } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); -- GitLab From fa4c027a7956f5e07697bfcb580d25eeb8471257 Mon Sep 17 00:00:00 2001 From: Santosh Shukla Date: Mon, 27 Feb 2023 14:10:15 +0530 Subject: [PATCH 1110/5631] KVM: x86: Add support for SVM's Virtual NMI Add support for SVM's Virtual NMIs implementation, which adds proper tracking of virtual NMI blocking, and an intr_ctrl flag that software can set to mark a virtual NMI as pending. Pending virtual NMIs are serviced by hardware if/when virtual NMIs become unblocked, i.e. act more or less like real NMIs. Introduce two new kvm_x86_ops callbacks so to support SVM's vNMI, as KVM needs to treat a pending vNMI as partially injected. Specifically, if two NMIs (for L1) arrive concurrently in KVM's software model, KVM's ABI is to inject one and pend the other. Without vNMI, KVM manually tracks the pending NMI and uses NMI windows to detect when the NMI should be injected. With vNMI, the pending NMI is simply stuffed into the VMCB and handed off to hardware. This means that KVM needs to be able to set a vNMI pending on-demand, and also query if a vNMI is pending, e.g. to honor the "at most one NMI pending" rule and to preserve all NMIs across save and restore. Warn if KVM attempts to open an NMI window when vNMI is fully enabled, as the above logic should prevent KVM from ever getting to kvm_check_and_inject_events() with two NMIs pending _in software_, and the "at most one NMI pending" logic should prevent having an NMI pending in hardware and an NMI pending in software if NMIs are also blocked, i.e. if KVM can't immediately inject the second NMI. Signed-off-by: Santosh Shukla Co-developed-by: Maxim Levitsky Signed-off-by: Maxim Levitsky Link: https://lore.kernel.org/r/20230227084016.3368-11-santosh.shukla@amd.com [sean: rewrite shortlog and changelog, massage code comments] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm-x86-ops.h | 2 + arch/x86/include/asm/kvm_host.h | 11 ++- arch/x86/kvm/svm/svm.c | 114 +++++++++++++++++++++++------ arch/x86/kvm/svm/svm.h | 22 ++++++ arch/x86/kvm/x86.c | 20 ++++- 5 files changed, 146 insertions(+), 23 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 8dc345cc6318..092ef2398857 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -68,6 +68,8 @@ KVM_X86_OP(get_interrupt_shadow) KVM_X86_OP(patch_hypercall) KVM_X86_OP(inject_irq) KVM_X86_OP(inject_nmi) +KVM_X86_OP_OPTIONAL_RET0(is_vnmi_pending) +KVM_X86_OP_OPTIONAL_RET0(set_vnmi_pending) KVM_X86_OP(inject_exception) KVM_X86_OP(cancel_injection) KVM_X86_OP(interrupt_allowed) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a45de1118a42..3edb8b3e3ef5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -876,7 +876,8 @@ struct kvm_vcpu_arch { u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ - unsigned nmi_pending; /* NMI queued after currently running handler */ + /* Number of NMIs pending injection, not including hardware vNMIs. */ + unsigned int nmi_pending; bool nmi_injected; /* Trying to inject an NMI this entry */ bool smi_pending; /* SMI queued after currently running handler */ u8 handling_intr_from_guest; @@ -1621,6 +1622,13 @@ struct kvm_x86_ops { int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); + /* Whether or not a virtual NMI is pending in hardware. */ + bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); + /* + * Attempt to pend a virtual NMI in harware. Returns %true on success + * to allow using static_call_ret0 as the fallback. + */ + bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); @@ -2005,6 +2013,7 @@ int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); +int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 69ace08ab1e4..7a14c937a36d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -230,6 +230,8 @@ module_param(dump_invalid_vmcb, bool, 0644); bool intercept_smi = true; module_param(intercept_smi, bool, 0444); +bool vnmi = true; +module_param(vnmi, bool, 0444); static bool svm_gp_erratum_intercept = true; @@ -1311,6 +1313,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu) if (kvm_vcpu_apicv_active(vcpu)) avic_init_vmcb(svm, vmcb); + if (vnmi) + svm->vmcb->control.int_ctl |= V_NMI_ENABLE_MASK; + if (vgif) { svm_clr_intercept(svm, INTERCEPT_STGI); svm_clr_intercept(svm, INTERCEPT_CLGI); @@ -3525,6 +3530,39 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) ++vcpu->stat.nmi_injections; } +static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + return !!(svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK); +} + +static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + if (svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK) + return false; + + svm->vmcb->control.int_ctl |= V_NMI_PENDING_MASK; + vmcb_mark_dirty(svm->vmcb, VMCB_INTR); + + /* + * Because the pending NMI is serviced by hardware, KVM can't know when + * the NMI is "injected", but for all intents and purposes, passing the + * NMI off to hardware counts as injection. + */ + ++vcpu->stat.nmi_injections; + + return true; +} + static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3620,6 +3658,35 @@ static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) svm_set_intercept(svm, INTERCEPT_CR8_WRITE); } +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) + return svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK; + else + return svm->nmi_masked; +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) { + if (masked) + svm->vmcb->control.int_ctl |= V_NMI_BLOCKING_MASK; + else + svm->vmcb->control.int_ctl &= ~V_NMI_BLOCKING_MASK; + + } else { + svm->nmi_masked = masked; + if (masked) + svm_set_iret_intercept(svm); + else + svm_clr_iret_intercept(svm); + } +} + bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3631,8 +3698,10 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return false; - return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - svm->nmi_masked; + if (svm_get_nmi_mask(vcpu)) + return true; + + return vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -3650,24 +3719,6 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return 1; } -static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) -{ - return to_svm(vcpu)->nmi_masked; -} - -static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (masked) { - svm->nmi_masked = true; - svm_set_iret_intercept(svm); - } else { - svm->nmi_masked = false; - svm_clr_iret_intercept(svm); - } -} - bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3748,7 +3799,16 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->nmi_masked && !svm->awaiting_iret_completion) + /* + * KVM should never request an NMI window when vNMI is enabled, as KVM + * allows at most one to-be-injected NMI and one pending NMI, i.e. if + * two NMIs arrive simultaneously, KVM will inject one and set + * V_NMI_PENDING for the other. WARN, but continue with the standard + * single-step approach to try and salvage the pending NMI. + */ + WARN_ON_ONCE(is_vnmi_enabled(svm)); + + if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { @@ -4797,6 +4857,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .patch_hypercall = svm_patch_hypercall, .inject_irq = svm_inject_irq, .inject_nmi = svm_inject_nmi, + .is_vnmi_pending = svm_is_vnmi_pending, + .set_vnmi_pending = svm_set_vnmi_pending, .inject_exception = svm_inject_exception, .cancel_injection = svm_cancel_injection, .interrupt_allowed = svm_interrupt_allowed, @@ -5090,6 +5152,16 @@ static __init int svm_hardware_setup(void) pr_info("Virtual GIF supported\n"); } + vnmi = vgif && vnmi && boot_cpu_has(X86_FEATURE_VNMI); + if (vnmi) + pr_info("Virtual NMI enabled\n"); + + if (!vnmi) { + svm_x86_ops.is_vnmi_pending = NULL; + svm_x86_ops.set_vnmi_pending = NULL; + } + + if (lbrv) { if (!boot_cpu_has(X86_FEATURE_LBRV)) lbrv = false; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 839809972da1..fb48c347bbe0 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -36,6 +36,7 @@ extern bool npt_enabled; extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; +extern bool vnmi; /* * Clean bits in VMCB. @@ -548,6 +549,27 @@ static inline bool is_x2apic_msrpm_offset(u32 offset) (msr < (APIC_BASE_MSR + 0x100)); } +static inline struct vmcb *get_vnmi_vmcb_l1(struct vcpu_svm *svm) +{ + if (!vnmi) + return NULL; + + if (is_guest_mode(&svm->vcpu)) + return NULL; + else + return svm->vmcb01.ptr; +} + +static inline bool is_vnmi_enabled(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vnmi_vmcb_l1(svm); + + if (vmcb) + return !!(vmcb->control.int_ctl & V_NMI_ENABLE_MASK); + else + return false; +} + /* svm.c */ #define MSR_INVALID 0xffffffffU diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index befabb4678f9..f32c2b51c157 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5125,7 +5125,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ @@ -10158,13 +10158,31 @@ static void process_nmi(struct kvm_vcpu *vcpu) else limit = 2; + /* + * Adjust the limit to account for pending virtual NMIs, which aren't + * tracked in vcpu->arch.nmi_pending. + */ + if (static_call(kvm_x86_is_vnmi_pending)(vcpu)) + limit--; + vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); + if (vcpu->arch.nmi_pending && + (static_call(kvm_x86_set_vnmi_pending)(vcpu))) + vcpu->arch.nmi_pending--; + if (vcpu->arch.nmi_pending) kvm_make_request(KVM_REQ_EVENT, vcpu); } +/* Return total number of NMIs pending injection to the VM */ +int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.nmi_pending + + static_call(kvm_x86_is_vnmi_pending)(vcpu); +} + void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { -- GitLab From 0977cfac6e76fa976618129a4585bcf53784cc87 Mon Sep 17 00:00:00 2001 From: Santosh Shukla Date: Mon, 27 Feb 2023 14:10:16 +0530 Subject: [PATCH 1111/5631] KVM: nSVM: Implement support for nested VNMI Allow L1 to use vNMI to accelerate its injection of NMI to L2 by propagating vNMI int_ctl bits from/to vmcb12 to/from vmcb02. To handle both the case where vNMI is enabled for L1 and L2, and where vNMI is enabled for L1 but _not_ L2, move pending L1 vNMIs to nmi_pending on nested VM-Entry and raise KVM_REQ_EVENT, i.e. rely on existing code to route the NMI to the correct domain. On nested VM-Exit, reverse the process and set/clear V_NMI_PENDING for L1 based one whether nmi_pending is zero or non-zero. There is no need to consider vmcb02 in this case, as V_NMI_PENDING can be set in vmcb02 if vNMI is disabled for L2, and if vNMI is enabled for L2, then L1 and L2 have different NMI contexts. Co-developed-by: Maxim Levitsky Signed-off-by: Maxim Levitsky Signed-off-by: Santosh Shukla Link: https://lore.kernel.org/r/20230227084016.3368-12-santosh.shukla@amd.com [sean: massage changelog to match the code] Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/nested.c | 33 +++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 5 +++++ arch/x86/kvm/svm/svm.h | 7 +++++++ 3 files changed, 45 insertions(+) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 8300fd31878d..96936ddf1b3c 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -281,6 +281,11 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) return false; + if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && + !vmcb12_is_intercept(control, INTERCEPT_NMI))) { + return false; + } + return true; } @@ -436,6 +441,9 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm) if (nested_vgif_enabled(svm)) mask |= V_GIF_MASK; + if (nested_vnmi_enabled(svm)) + mask |= V_NMI_BLOCKING_MASK | V_NMI_PENDING_MASK; + svm->nested.ctl.int_ctl &= ~mask; svm->nested.ctl.int_ctl |= svm->vmcb->control.int_ctl & mask; } @@ -655,6 +663,17 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, else int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); + if (vnmi) { + if (vmcb01->control.int_ctl & V_NMI_PENDING_MASK) { + svm->vcpu.arch.nmi_pending++; + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + } + if (nested_vnmi_enabled(svm)) + int_ctl_vmcb12_bits |= (V_NMI_PENDING_MASK | + V_NMI_ENABLE_MASK | + V_NMI_BLOCKING_MASK); + } + /* Copied from vmcb01. msrpm_base can be overwritten later. */ vmcb02->control.nested_ctl = vmcb01->control.nested_ctl; vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa; @@ -1055,6 +1074,20 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm_update_lbrv(vcpu); } + if (vnmi) { + if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK) + vmcb01->control.int_ctl |= V_NMI_BLOCKING_MASK; + else + vmcb01->control.int_ctl &= ~V_NMI_BLOCKING_MASK; + + if (vcpu->arch.nmi_pending) { + vcpu->arch.nmi_pending--; + vmcb01->control.int_ctl |= V_NMI_PENDING_MASK; + } else { + vmcb01->control.int_ctl &= ~V_NMI_PENDING_MASK; + } + } + /* * On vmexit the GIF is set to false and * no event can be injected in L1. diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7a14c937a36d..e0ec95f1f068 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4246,6 +4246,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF); + svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI); + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ @@ -5001,6 +5003,9 @@ static __init void svm_set_cpu_caps(void) if (vgif) kvm_cpu_cap_set(X86_FEATURE_VGIF); + if (vnmi) + kvm_cpu_cap_set(X86_FEATURE_VNMI); + /* Nested VM can receive #VMEXIT instead of triggering #GP */ kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index fb48c347bbe0..f44751dd8d5d 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -266,6 +266,7 @@ struct vcpu_svm { bool pause_filter_enabled : 1; bool pause_threshold_enabled : 1; bool vgif_enabled : 1; + bool vnmi_enabled : 1; u32 ldr_reg; u32 dfr_reg; @@ -540,6 +541,12 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; } +static inline bool nested_vnmi_enabled(struct vcpu_svm *svm) +{ + return svm->vnmi_enabled && + (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK); +} + static inline bool is_x2apic_msrpm_offset(u32 offset) { /* 4 msrs per u8, and 4 u8 in u32 */ -- GitLab From 6e2a3a324aab9d76e6b864eb6ebc60b197b5141a Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Sun, 19 Mar 2023 14:59:30 +0200 Subject: [PATCH 1112/5631] net/mlx5: Expose bits for enabling out-of-order by default Add needed HW bits for enabling out-of-order by default and use go_back_n when out-of-order is not needed. Signed-off-by: Or Har-Toov Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/75d6dfe263989a05c08c43406132b336ea12d00a.1679230449.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66d76e97a087..62039b147432 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1077,7 +1077,9 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x17]; + u8 reserved_at_7[0x1]; + u8 qp_ooo_transmit_default[0x1]; + u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1493,7 +1495,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0x7]; + u8 reserved_at_b3[0x6]; + u8 go_back_n[0x1]; u8 shampo[0x1]; u8 reserved_at_bb[0x5]; @@ -3261,7 +3264,8 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x3]; + u8 reserved_at_55[0x1]; + u8 retry_mode[0x2]; u8 ts_format[0x2]; u8 reserved_at_5a[0x1]; u8 rlky[0x1]; -- GitLab From 742948cc02d5230ef81546556502a05a90f89bbb Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Sun, 19 Mar 2023 14:59:31 +0200 Subject: [PATCH 1113/5631] RDMA/mlx5: Disable out-of-order in integrity enabled QPs Set retry_mode to GO_BACK_N when qp is created with INTEGRITY_EN flag because out-of-order is not supported when doing HW offload of signature operations. Signed-off-by: Or Har-Toov Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/362de42cdc7a541afa5b1fd0ec6ae706061764a2.1679230449.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/qp.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7cc3b973dec7..0fdbf79a3e81 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -60,6 +60,10 @@ enum raw_qp_set_mask_map { MLX5_RAW_QP_RATE_LIMIT = 1UL << 1, }; +enum { + MLX5_QP_RM_GO_BACK_N = 0x1, +}; + struct mlx5_modify_raw_qp_param { u16 operation; @@ -2519,6 +2523,10 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd, if (qp->flags & IB_QP_CREATE_IPOIB_UD_LSO) MLX5_SET(qpc, qpc, ulp_stateless_offload_mode, 1); + if (qp->flags & IB_QP_CREATE_INTEGRITY_EN && + MLX5_CAP_GEN(mdev, go_back_n)) + MLX5_SET(qpc, qpc, retry_mode, MLX5_QP_RM_GO_BACK_N); + err = mlx5_qpc_create_qp(dev, &base->mqp, in, inlen, out); kvfree(in); if (err) -- GitLab From f4244e55e4c3a14374ea319b680f33d97cf6ba7e Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Sun, 19 Mar 2023 14:59:32 +0200 Subject: [PATCH 1114/5631] net/mlx5: Set out of order (ooo) by default When FW supports ooo by default, enable the cap. Signed-off-by: Or Har-Toov Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/00bd14bfb002ed2338de3296bcd9af27d4770b70.1679230449.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f1de152a6113..9194f031a7be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -684,6 +684,9 @@ static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) MLX5_ST_SZ_BYTES(roce_cap)); MLX5_SET(roce_cap, set_hca_cap, sw_r_roce_src_udp_port, 1); + if (MLX5_CAP_ROCE_MAX(dev, qp_ooo_transmit_default)) + MLX5_SET(roce_cap, set_hca_cap, qp_ooo_transmit_default, 1); + err = set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ROCE); return err; } -- GitLab From e0e8fbf84628f3aa80a01ba28db7921224f5d7b9 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:20 -0600 Subject: [PATCH 1115/5631] pinctrl: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Reviewed-by: Geert Uytterhoeven Reviewed-by: Jernej Skrabec Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230310144721.1544669-1-robh@kernel.org [Dropped hunk hitting drivers/pinctrl/renesas/pinctrl.c] Signed-off-by: Linus Walleij --- drivers/pinctrl/mediatek/pinctrl-moore.c | 2 +- drivers/pinctrl/pinctrl-single.c | 4 ++-- drivers/pinctrl/pinctrl-stmfx.c | 2 +- drivers/pinctrl/stm32/pinctrl-stm32.c | 2 +- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 20 ++++++++++---------- 5 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.c b/drivers/pinctrl/mediatek/pinctrl-moore.c index 007b98ce5631..8649a2f9d324 100644 --- a/drivers/pinctrl/mediatek/pinctrl-moore.c +++ b/drivers/pinctrl/mediatek/pinctrl-moore.c @@ -586,7 +586,7 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw) * Documentation/devicetree/bindings/gpio/gpio.txt on how to * bind pinctrl and gpio drivers via the "gpio-ranges" property. */ - if (!of_find_property(hw->dev->of_node, "gpio-ranges", NULL)) { + if (!of_property_present(hw->dev->of_node, "gpio-ranges")) { ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0, chip->ngpio); if (ret < 0) { diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index 190923757cda..0dabbcf68b9f 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -939,11 +939,11 @@ static int pcs_parse_pinconf(struct pcs_device *pcs, struct device_node *np, /* cacluate how much properties are supported in current node */ for (i = 0; i < ARRAY_SIZE(prop2); i++) { - if (of_find_property(np, prop2[i].name, NULL)) + if (of_property_present(np, prop2[i].name)) nconfs++; } for (i = 0; i < ARRAY_SIZE(prop4); i++) { - if (of_find_property(np, prop4[i].name, NULL)) + if (of_property_present(np, prop4[i].name)) nconfs++; } if (!nconfs) diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 1181c4b506b1..3c031692e44d 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -632,7 +632,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) pctl->dev = &pdev->dev; pctl->stmfx = stmfx; - if (!of_find_property(np, "gpio-ranges", NULL)) { + if (!of_property_present(np, "gpio-ranges")) { dev_err(pctl->dev, "missing required gpio-ranges property\n"); return -EINVAL; } diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index cb33a23ab0c1..66a25becd8f5 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1374,7 +1374,7 @@ static struct irq_domain *stm32_pctrl_get_irq_domain(struct platform_device *pde struct device_node *parent; struct irq_domain *domain; - if (!of_find_property(np, "interrupt-parent", NULL)) + if (!of_property_present(np, "interrupt-parent")) return NULL; parent = of_irq_find_parent(np); diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index f35179eceb4e..1dc1882cbdd7 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -224,16 +224,16 @@ static int sunxi_pctrl_get_group_pins(struct pinctrl_dev *pctldev, static bool sunxi_pctrl_has_bias_prop(struct device_node *node) { - return of_find_property(node, "bias-pull-up", NULL) || - of_find_property(node, "bias-pull-down", NULL) || - of_find_property(node, "bias-disable", NULL) || - of_find_property(node, "allwinner,pull", NULL); + return of_property_present(node, "bias-pull-up") || + of_property_present(node, "bias-pull-down") || + of_property_present(node, "bias-disable") || + of_property_present(node, "allwinner,pull"); } static bool sunxi_pctrl_has_drive_prop(struct device_node *node) { - return of_find_property(node, "drive-strength", NULL) || - of_find_property(node, "allwinner,drive", NULL); + return of_property_present(node, "drive-strength") || + of_property_present(node, "allwinner,drive"); } static int sunxi_pctrl_parse_bias_prop(struct device_node *node) @@ -241,13 +241,13 @@ static int sunxi_pctrl_parse_bias_prop(struct device_node *node) u32 val; /* Try the new style binding */ - if (of_find_property(node, "bias-pull-up", NULL)) + if (of_property_present(node, "bias-pull-up")) return PIN_CONFIG_BIAS_PULL_UP; - if (of_find_property(node, "bias-pull-down", NULL)) + if (of_property_present(node, "bias-pull-down")) return PIN_CONFIG_BIAS_PULL_DOWN; - if (of_find_property(node, "bias-disable", NULL)) + if (of_property_present(node, "bias-disable")) return PIN_CONFIG_BIAS_DISABLE; /* And fall back to the old binding */ @@ -1424,7 +1424,7 @@ static int sunxi_pinctrl_setup_debounce(struct sunxi_pinctrl *pctl, return 0; /* If we don't have any setup, bail out */ - if (!of_find_property(node, "input-debounce", NULL)) + if (!of_property_present(node, "input-debounce")) return 0; losc = devm_clk_get(pctl->dev, "losc"); -- GitLab From 68c37f917ed97e0b0e6a2be9f6be3eba39b8ea4b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:31 -0800 Subject: [PATCH 1116/5631] sh: SH2007: drop the bad URL info This URL provided is no longer functional, so drop it. Fixes: 3a598264436e ("sh: SH-2007 board support.") Signed-off-by: Randy Dunlap Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Cc: Geert Uytterhoeven Cc: Hitoshi Mitake Cc: linux-sh@vger.kernel.org Reviewed-by: Geert Uytterhoeven Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-2-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/boards/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 83bcb6d2daca..fafe15d3ba1d 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -358,7 +358,6 @@ config SH_SH2007 intended for embedded applications. It has an Ethernet interface (SMC9118), direct connected Compact Flash socket, two serial ports and PC-104 bus. - More information at . config SH_APSH4A3A bool "AP-SH4A-3A" -- GitLab From d1155e4132de712a9d3066e2667ceaad39a539c5 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:32 -0800 Subject: [PATCH 1117/5631] sh: nmi_debug: fix return value of __setup handler __setup() handlers should return 1 to obsolete_checksetup() in init/main.c to indicate that the boot option has been handled. A return of 0 causes the boot option/value to be listed as an Unknown kernel parameter and added to init's (limited) argument or environment strings. Also, error return codes don't mean anything to obsolete_checksetup() -- only non-zero (usually 1) or zero. So return 1 from nmi_debug_setup(). Fixes: 1e1030dccb10 ("sh: nmi_debug support.") Signed-off-by: Randy Dunlap Reported-by: Igor Zhbanov Link: lore.kernel.org/r/64644a2f-4a20-bab3-1e15-3b2cdd0defe3@omprussia.ru Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-3-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/kernel/nmi_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/sh/kernel/nmi_debug.c b/arch/sh/kernel/nmi_debug.c index 11777867c6f5..a212b645b4cf 100644 --- a/arch/sh/kernel/nmi_debug.c +++ b/arch/sh/kernel/nmi_debug.c @@ -49,7 +49,7 @@ static int __init nmi_debug_setup(char *str) register_die_notifier(&nmi_debug_nb); if (*str != '=') - return 0; + return 1; for (p = str + 1; *p; p = sep + 1) { sep = strchr(p, ','); @@ -70,6 +70,6 @@ static int __init nmi_debug_setup(char *str) break; } - return 0; + return 1; } __setup("nmi_debug", nmi_debug_setup); -- GitLab From 6cba655543c7959f8a6d2979b9d40a6a66b7ed4f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:33 -0800 Subject: [PATCH 1118/5631] sh: init: use OF_EARLY_FLATTREE for early init When CONFIG_OF_EARLY_FLATTREE and CONFIG_SH_DEVICE_TREE are not set, SH3 build fails with a call to early_init_dt_scan(), so in arch/sh/kernel/setup.c and arch/sh/kernel/head_32.S, use CONFIG_OF_EARLY_FLATTREE instead of CONFIG_OF_FLATTREE. Fixes this build error: ../arch/sh/kernel/setup.c: In function 'sh_fdt_init': ../arch/sh/kernel/setup.c:262:26: error: implicit declaration of function 'early_init_dt_scan' [-Werror=implicit-function-declaration] 262 | if (!dt_virt || !early_init_dt_scan(dt_virt)) { Fixes: 03767daa1387 ("sh: fix build regression with CONFIG_OF && !CONFIG_OF_FLATTREE") Fixes: eb6b6930a70f ("sh: fix memory corruption of unflattened device tree") Signed-off-by: Randy Dunlap Suggested-by: Rob Herring Cc: Frank Rowand Cc: devicetree@vger.kernel.org Cc: Rich Felker Cc: Yoshinori Sato Cc: Geert Uytterhoeven Cc: John Paul Adrian Glaubitz Cc: linux-sh@vger.kernel.org Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-4-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/kernel/head_32.S | 6 +++--- arch/sh/kernel/setup.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/sh/kernel/head_32.S b/arch/sh/kernel/head_32.S index 4adbd4ade319..b603b7968b38 100644 --- a/arch/sh/kernel/head_32.S +++ b/arch/sh/kernel/head_32.S @@ -64,7 +64,7 @@ ENTRY(_stext) ldc r0, r6_bank #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov r4, r12 ! Store device tree blob pointer in r12 #endif @@ -315,7 +315,7 @@ ENTRY(_stext) 10: #endif -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE mov.l 8f, r0 ! Make flat device tree available early. jsr @r0 mov r12, r4 @@ -346,7 +346,7 @@ ENTRY(stack_start) 5: .long start_kernel 6: .long cpu_init 7: .long init_thread_union -#if defined(CONFIG_OF_FLATTREE) +#if defined(CONFIG_OF_EARLY_FLATTREE) 8: .long sh_fdt_init #endif diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 1fcb6659822a..af977ec4ca5e 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -244,7 +244,7 @@ void __init __weak plat_early_device_setup(void) { } -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE void __ref sh_fdt_init(phys_addr_t dt_phys) { static int done = 0; @@ -326,7 +326,7 @@ void __init setup_arch(char **cmdline_p) /* Let earlyprintk output early console messages */ sh_early_platform_driver_probe("earlyprintk", 1, 1); -#ifdef CONFIG_OF_FLATTREE +#ifdef CONFIG_OF_EARLY_FLATTREE #ifdef CONFIG_USE_BUILTIN_DTB unflatten_and_copy_device_tree(); #else -- GitLab From 58a49ad90939386a8682e842c474a0d2c00ec39c Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:34 -0800 Subject: [PATCH 1119/5631] sh: math-emu: fix macro redefined warning Fix a warning that was reported by the kernel test robot: In file included from ../include/math-emu/soft-fp.h:27, from ../arch/sh/math-emu/math.c:22: ../arch/sh/include/asm/sfp-machine.h:17: warning: "__BYTE_ORDER" redefined 17 | #define __BYTE_ORDER __BIG_ENDIAN In file included from ../arch/sh/math-emu/math.c:21: ../arch/sh/math-emu/sfp-util.h:71: note: this is the location of the previous definition 71 | #define __BYTE_ORDER __LITTLE_ENDIAN Fixes: b929926f01f2 ("sh: define __BIG_ENDIAN for math-emu") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Link: lore.kernel.org/r/202111121827.6v6SXtVv-lkp@intel.com Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Cc: linux-sh@vger.kernel.org Reviewed-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-5-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/math-emu/sfp-util.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/sh/math-emu/sfp-util.h b/arch/sh/math-emu/sfp-util.h index 784f541344f3..bda50762b3d3 100644 --- a/arch/sh/math-emu/sfp-util.h +++ b/arch/sh/math-emu/sfp-util.h @@ -67,7 +67,3 @@ } while (0) #define abort() return 0 - -#define __BYTE_ORDER __LITTLE_ENDIAN - - -- GitLab From 644a9cf0d2a8340121fa8107a5fa6f27782bb080 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:35 -0800 Subject: [PATCH 1120/5631] sh: remove sh5/sh64 last fragments A previous patch removed most of the sh5 (sh64) support from the kernel tree. Now remove the last stragglers. Fixes: 37744feebc08 ("sh: remove sh5 support") Signed-off-by: Randy Dunlap Cc: Geert Uytterhoeven Cc: Arnd Bergmann Cc: Rich Felker Cc: Yoshinori Sato Cc: John Paul Adrian Glaubitz Cc: linux-sh@vger.kernel.org Acked-by: John Paul Adrian Glaubitz Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-6-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- Documentation/kbuild/kbuild.rst | 1 - Documentation/scheduler/sched-arch.rst | 2 -- Documentation/translations/zh_CN/scheduler/sched-arch.rst | 2 -- scripts/checkstack.pl | 7 ------- tools/perf/arch/common.c | 2 -- tools/scripts/Makefile.arch | 5 ----- tools/testing/selftests/mm/Makefile | 2 +- tools/testing/selftests/mm/run_vmtests.sh | 2 +- 8 files changed, 2 insertions(+), 21 deletions(-) diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index 5202186728b4..e22621f4af0b 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -160,7 +160,6 @@ directory name found in the arch/ directory. But some architectures such as x86 and sparc have aliases. - x86: i386 for 32 bit, x86_64 for 64 bit -- sh: sh for 32 bit, sh64 for 64 bit - sparc: sparc32 for 32 bit, sparc64 for 64 bit CROSS_COMPILE diff --git a/Documentation/scheduler/sched-arch.rst b/Documentation/scheduler/sched-arch.rst index 0eaec669790a..505cd27f9a92 100644 --- a/Documentation/scheduler/sched-arch.rst +++ b/Documentation/scheduler/sched-arch.rst @@ -70,7 +70,5 @@ Possible arch problems I found (and either tried to fix or didn't): ia64 - is safe_halt call racy vs interrupts? (does it sleep?) (See #4a) -sh64 - Is sleeping racy vs interrupts? (See #4a) - sparc - IRQs on at this point(?), change local_irq_save to _disable. - TODO: needs secondary CPUs to disable preempt (See #1) diff --git a/Documentation/translations/zh_CN/scheduler/sched-arch.rst b/Documentation/translations/zh_CN/scheduler/sched-arch.rst index 754a15c6b60f..ce3f39d9b3cb 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-arch.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-arch.rst @@ -70,7 +70,5 @@ arch/x86/kernel/process.c有轮询和睡眠空闲函数的例子。 ia64 - safe_halt的调用与中断相比，是否很荒谬？ (它睡眠了吗) (参考 #4a) -sh64 - 睡眠与中断相比，是否很荒谬？ (参考 #4a) - sparc - 在这一点上，IRQ是开着的（？），把local_irq_save改为_disable。 - 待办事项: 需要第二个CPU来禁用抢占 (参考 #1) diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl index d48dfed6d3db..84f5fb7f1cec 100755 --- a/scripts/checkstack.pl +++ b/scripts/checkstack.pl @@ -10,7 +10,6 @@ # Mips port by Juan Quintela # IA64 port via Andreas Dilger # Arm port by Holger Schurig -# sh64 port by Paul Mundt # Random bits by Matt Mackall # M68k port by Geert Uytterhoeven and Andreas Schwab # AArch64, PARISC ports by Kyle McMartin @@ -100,12 +99,6 @@ my (@stack, $re, $dre, $sub, $x, $xs, $funcre, $min_stack); # 100092: e3 f0 ff c8 ff 71 lay %r15,-56(%r15) $re = qr/.*(?:lay|ag?hi).*\%r15,-(([0-9]{2}|[3-9])[0-9]{2}) (?:\(\%r15\))?$/ox; - } elsif ($arch =~ /^sh64$/) { - #XXX: we only check for the immediate case presently, - # though we will want to check for the movi/sub - # pair for larger users. -- PFM. - #a00048e0: d4fc40f0 addi.l r15,-240,r15 - $re = qr/.*addi\.l.*r15,-(([0-9]{2}|[3-9])[0-9]{2}),r15/o; } elsif ($arch eq 'sparc' || $arch eq 'sparc64') { # f0019d10: 9d e3 bf 90 save %sp, -112, %sp $re = qr/.*save.*%sp, -(([0-9]{2}|[3-9])[0-9]{2}), %sp/o; diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 59dd875fd5e4..cfe63dfab03a 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -51,9 +51,7 @@ const char *const s390_triplets[] = { const char *const sh_triplets[] = { "sh-unknown-linux-gnu-", - "sh64-unknown-linux-gnu-", "sh-linux-gnu-", - "sh64-linux-gnu-", NULL }; diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 1c72d07cb9fe..f6a50f06dfc4 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -29,11 +29,6 @@ ifeq ($(ARCH),sparc64) SRCARCH := sparc endif -# Additional ARCH settings for sh -ifeq ($(ARCH),sh64) - SRCARCH := sh -endif - # Additional ARCH settings for loongarch ifeq ($(ARCH),loongarch32) SRCARCH := loongarch diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index c31d952cff68..fc35050b5542 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -90,7 +90,7 @@ endif endif -ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) +ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..a9d6d52596f2 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -132,7 +132,7 @@ else fi # filter 64bit architectures -ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" +ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sparc64 x86_64" if [ -z "$ARCH" ]; then ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi -- GitLab From c2bd1e18c6f85c0027da2e5e7753b9bfd9f8e6dc Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Mar 2023 20:00:37 -0800 Subject: [PATCH 1121/5631] sh: mcount.S: fix build error when PRINTK is not enabled Fix a build error in mcount.S when CONFIG_PRINTK is not enabled. Fixes this build error: sh2-linux-ld: arch/sh/lib/mcount.o: in function `stack_panic': (.text+0xec): undefined reference to `dump_stack' Fixes: e460ab27b6c3 ("sh: Fix up stack overflow check with ftrace disabled.") Signed-off-by: Randy Dunlap Cc: John Paul Adrian Glaubitz Cc: Yoshinori Sato Cc: Rich Felker Suggested-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230306040037.20350-8-rdunlap@infradead.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug index 10290e5c1f43..c449e7c1b20f 100644 --- a/arch/sh/Kconfig.debug +++ b/arch/sh/Kconfig.debug @@ -15,7 +15,7 @@ config SH_STANDARD_BIOS config STACK_DEBUG bool "Check for stack overflows" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && PRINTK help This option will cause messages to be printed if free stack space drops below a certain limit. Saying Y here will add overhead to -- GitLab From d31d7300ebc0c43021ec48c0e6a3a427386f4617 Mon Sep 17 00:00:00 2001 From: Dhruva Gole Date: Thu, 23 Mar 2023 14:29:04 +0530 Subject: [PATCH 1122/5631] rtc: k3: handle errors while enabling wake irq Due to the potential failure of enable_irq_wake(), it would be better to return error if it fails. Fixes: b09d633575e5 ("rtc: Introduce ti-k3-rtc") Cc: Nishanth Menon Signed-off-by: Dhruva Gole Link: https://lore.kernel.org/r/20230323085904.957999-1-d-gole@ti.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ti-k3.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ti-k3.c b/drivers/rtc/rtc-ti-k3.c index ba23163cc042..0d90fe923355 100644 --- a/drivers/rtc/rtc-ti-k3.c +++ b/drivers/rtc/rtc-ti-k3.c @@ -632,7 +632,8 @@ static int __maybe_unused ti_k3_rtc_suspend(struct device *dev) struct ti_k3_rtc *priv = dev_get_drvdata(dev); if (device_may_wakeup(dev)) - enable_irq_wake(priv->irq); + return enable_irq_wake(priv->irq); + return 0; } -- GitLab From aa4d540b4150052ae3b36d286b9c833a961ce291 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 21 Mar 2023 17:47:03 -0600 Subject: [PATCH 1123/5631] RDMA/core: Fix multiple -Warray-bounds warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit GCC-13 (and Clang)[1] does not like to access a partially allocated object, since it cannot reason about it for bounds checking. In this case 140 bytes are allocated for an object of type struct ib_umad_packet: packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); However, notice that sizeof(*packet) is only 104 bytes: struct ib_umad_packet { struct ib_mad_send_buf * msg; /* 0 8 */ struct ib_mad_recv_wc * recv_wc; /* 8 8 */ struct list_head list; /* 16 16 */ int length; /* 32 4 */ /* XXX 4 bytes hole, try to pack */ struct ib_user_mad mad __attribute__((__aligned__(8))); /* 40 64 */ /* size: 104, cachelines: 2, members: 5 */ /* sum members: 100, holes: 1, sum holes: 4 */ /* forced alignments: 1, forced holes: 1, sum forced holes: 4 */ /* last cacheline: 40 bytes */ } __attribute__((__aligned__(8))); and 36 bytes extra bytes are allocated for a flexible-array member in struct ib_user_mad: include/rdma/ib_mad.h: 120 enum { ... 123 IB_MGMT_RMPP_HDR = 36, ... } struct ib_user_mad { struct ib_user_mad_hdr hdr; /* 0 64 */ /* --- cacheline 1 boundary (64 bytes) --- */ __u64 data[] __attribute__((__aligned__(8))); /* 64 0 */ /* size: 64, cachelines: 1, members: 2 */ /* forced alignments: 1 */ } __attribute__((__aligned__(8))); So we have sizeof(*packet) + IB_MGMT_RMPP_HDR == 140 bytes Then the address of the flex-array member (for which only 36 bytes were allocated) is casted and copied into a pointer to struct ib_rmpp_mad, which, in turn, is of size 256 bytes: rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; struct ib_rmpp_mad { struct ib_mad_hdr mad_hdr; /* 0 24 */ struct ib_rmpp_hdr rmpp_hdr; /* 24 12 */ u8 data[220]; /* 36 220 */ /* size: 256, cachelines: 4, members: 3 */ }; The thing is that those 36 bytes allocated for flex-array member data in struct ib_user_mad onlly account for the size of both struct ib_mad_hdr and struct ib_rmpp_hdr, but nothing is left for array u8 data[220]. So, the compiler is legitimately complaining about accessing an object for which not enough memory was allocated. Apparently, the only members of struct ib_rmpp_mad that are relevant (that are actually being used) in function ib_umad_write() are mad_hdr and rmpp_hdr. So, instead of casting packet->mad.data to (struct ib_rmpp_mad *) create a new structure struct ib_rmpp_mad_hdr { struct ib_mad_hdr mad_hdr; struct ib_rmpp_hdr rmpp_hdr; } __packed; and cast packet->mad.data to (struct ib_rmpp_mad_hdr *). Notice that IB_MGMT_RMPP_HDR == sizeof(struct ib_rmpp_mad_hdr) == 36 bytes Refactor the rest of the code, accordingly. Fix the following warnings seen under GCC-13 and -Warray-bounds: drivers/infiniband/core/user_mad.c:564:50: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:566:42: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:618:25: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] drivers/infiniband/core/user_mad.c:622:44: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=] Link: https://github.com/KSPP/linux/issues/273 Link: https://godbolt.org/z/oYWaGM4Yb [1] Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/ZBpB91qQcB10m3Fw@work Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/user_mad.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f83954180a33..d21c0a042f0a 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -131,6 +131,11 @@ struct ib_umad_packet { struct ib_user_mad mad; }; +struct ib_rmpp_mad_hdr { + struct ib_mad_hdr mad_hdr; + struct ib_rmpp_hdr rmpp_hdr; +} __packed; + #define CREATE_TRACE_POINTS #include @@ -494,11 +499,11 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_umad_file *file = filp->private_data; + struct ib_rmpp_mad_hdr *rmpp_mad_hdr; struct ib_umad_packet *packet; struct ib_mad_agent *agent; struct rdma_ah_attr ah_attr; struct ib_ah *ah; - struct ib_rmpp_mad *rmpp_mad; __be64 *tid; int ret, data_len, hdr_len, copy_offset, rmpp_active; u8 base_version; @@ -506,7 +511,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, if (count < hdr_size(file) + IB_MGMT_RMPP_HDR) return -EINVAL; - packet = kzalloc(sizeof *packet + IB_MGMT_RMPP_HDR, GFP_KERNEL); + packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL); if (!packet) return -ENOMEM; @@ -560,13 +565,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, goto err_up; } - rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data; - hdr_len = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class); + rmpp_mad_hdr = (struct ib_rmpp_mad_hdr *)packet->mad.data; + hdr_len = ib_get_mad_data_offset(rmpp_mad_hdr->mad_hdr.mgmt_class); - if (ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) + if (ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) && ib_mad_kernel_rmpp_agent(agent)) { copy_offset = IB_MGMT_RMPP_HDR; - rmpp_active = ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & + rmpp_active = ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE; } else { copy_offset = IB_MGMT_MAD_HDR; @@ -615,12 +620,12 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf, tid = &((struct ib_mad_hdr *) packet->msg->mad)->tid; *tid = cpu_to_be64(((u64) agent->hi_tid) << 32 | (be64_to_cpup(tid) & 0xffffffff)); - rmpp_mad->mad_hdr.tid = *tid; + rmpp_mad_hdr->mad_hdr.tid = *tid; } if (!ib_mad_kernel_rmpp_agent(agent) - && ib_is_mad_class_rmpp(rmpp_mad->mad_hdr.mgmt_class) - && (ib_get_rmpp_flags(&rmpp_mad->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { + && ib_is_mad_class_rmpp(rmpp_mad_hdr->mad_hdr.mgmt_class) + && (ib_get_rmpp_flags(&rmpp_mad_hdr->rmpp_hdr) & IB_MGMT_RMPP_FLAG_ACTIVE)) { spin_lock_irq(&file->send_lock); list_add_tail(&packet->list, &file->send_list); spin_unlock_irq(&file->send_lock); -- GitLab From 9cc61e5fbd619eea0401f519e7bac72fe3d4d1e8 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:04 +0100 Subject: [PATCH 1124/5631] driver core: bus: move dev_root out of struct bus_type Now that all accesses of dev_root is through the bus_get_dev_root() call, move the pointer out of struct bus_type and into the private dynamic structure, subsys_private. With this change, there is no modifiable portions of struct bus_type so it can be marked as a constant structure and moved to read-only memory. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-22-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 ++ drivers/base/bus.c | 28 ++++++++++++++++++++++------ include/linux/device/bus.h | 2 -- 3 files changed, 24 insertions(+), 8 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index b055eba1ec30..f1034e27e651 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -27,6 +27,7 @@ * on this bus. * @bus - pointer back to the struct bus_type that this structure is associated * with. + * @dev_root: Default device to use as the parent. * * @glue_dirs - "glue" directory to put in-between the parent device to * avoid namespace conflicts @@ -49,6 +50,7 @@ struct subsys_private { struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; struct bus_type *bus; + struct device *dev_root; struct kset glue_dirs; struct class *class; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index dd4b82d7510f..91a6b6b1fc49 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -935,8 +935,8 @@ void bus_unregister(const struct bus_type *bus) return; pr_debug("bus: '%s': unregistering\n", bus->name); - if (bus->dev_root) - device_unregister(bus->dev_root); + if (sp->dev_root) + device_unregister(sp->dev_root); bus_kobj = &sp->subsys.kobj; sysfs_remove_groups(bus_kobj, bus->bus_groups); @@ -1198,6 +1198,7 @@ static int subsys_register(struct bus_type *subsys, const struct attribute_group **groups, struct kobject *parent_of_root) { + struct subsys_private *sp; struct device *dev; int err; @@ -1205,6 +1206,12 @@ static int subsys_register(struct bus_type *subsys, if (err < 0) return err; + sp = bus_to_subsys(subsys); + if (!sp) { + err = -EINVAL; + goto err_sp; + } + dev = kzalloc(sizeof(struct device), GFP_KERNEL); if (!dev) { err = -ENOMEM; @@ -1223,7 +1230,8 @@ static int subsys_register(struct bus_type *subsys, if (err < 0) goto err_dev_reg; - subsys->dev_root = dev; + sp->dev_root = dev; + subsys_put(sp); return 0; err_dev_reg: @@ -1232,6 +1240,8 @@ static int subsys_register(struct bus_type *subsys, err_name: kfree(dev); err_dev: + subsys_put(sp); +err_sp: bus_unregister(subsys); return err; } @@ -1349,9 +1359,15 @@ bool bus_is_registered(const struct bus_type *bus) */ struct device *bus_get_dev_root(const struct bus_type *bus) { - if (bus) - return get_device(bus->dev_root); - return NULL; + struct subsys_private *sp = bus_to_subsys(bus); + struct device *dev_root; + + if (!sp) + return NULL; + + dev_root = get_device(sp->dev_root); + subsys_put(sp); + return dev_root; } EXPORT_SYMBOL_GPL(bus_get_dev_root); diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 6ce32ef4b8fd..c258e8770285 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -26,7 +26,6 @@ struct fwnode_handle; * * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). - * @dev_root: Default device to use as the parent. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -82,7 +81,6 @@ struct fwnode_handle; struct bus_type { const char *name; const char *dev_name; - struct device *dev_root; const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; -- GitLab From 75cff725d9566699a670a02b3cfd1c6e9e9ed53e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:05 +0100 Subject: [PATCH 1125/5631] driver core: bus: mark the struct bus_type for sysfs callbacks as constant struct bus_type should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct bus_type to be moved to read-only memory. Cc: "David S. Miller" Cc: "James E.J. Bottomley" Cc: "K. Y. Srinivasan" Cc: Alexander Gordeev Cc: Alexandre Bounine Cc: Alison Schofield Cc: Ben Widawsky Cc: Dexuan Cui Cc: Eric Dumazet Cc: Haiyang Zhang Cc: Hannes Reinecke Cc: Harald Freudenberger Cc: Heiko Carstens Cc: Hu Haowen Cc: Jakub Kicinski Cc: Jens Axboe Cc: Jonathan Corbet Cc: Laurentiu Tudor Cc: Matt Porter Cc: Michael Ellerman Cc: Paolo Abeni Cc: Stuart Yoder Cc: Vasily Gorbik Cc: Vishal Verma Cc: Yanteng Si Acked-by: Ilya Dryomov # rbd Acked-by: Ira Weiny # cxl Reviewed-by: Alex Shi Acked-by: Iwona Winiarska Acked-by: Dan Williams Acked-by: Bjorn Helgaas # pci Acked-by: Wei Liu Acked-by: Martin K. Petersen # scsi Link: https://lore.kernel.org/r/20230313182918.1312597-23-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/driver-model/bus.rst | 4 +- Documentation/filesystems/sysfs.rst | 4 +- .../translations/zh_CN/filesystems/sysfs.txt | 4 +- .../translations/zh_TW/filesystems/sysfs.txt | 4 +- arch/powerpc/platforms/pseries/ibmebus.c | 4 +- arch/powerpc/platforms/pseries/vio.c | 8 ++-- drivers/ata/pata_parport/pata_parport.c | 6 +-- drivers/base/bus.c | 8 ++-- drivers/block/rbd.c | 34 +++++++-------- drivers/bus/fsl-mc/fsl-mc-bus.c | 6 +-- drivers/cxl/core/port.c | 2 +- drivers/hv/vmbus_drv.c | 2 +- drivers/net/netdevsim/bus.c | 4 +- drivers/pci/pci-sysfs.c | 2 +- drivers/pci/pci.c | 4 +- drivers/peci/sysfs.c | 2 +- drivers/rapidio/rio-sysfs.c | 2 +- drivers/s390/crypto/ap_bus.c | 42 +++++++++---------- drivers/scsi/fcoe/fcoe_sysfs.c | 8 ++-- drivers/scsi/fcoe/fcoe_transport.c | 6 +-- include/linux/device/bus.h | 4 +- include/scsi/libfcoe.h | 6 +-- 22 files changed, 78 insertions(+), 88 deletions(-) diff --git a/Documentation/driver-api/driver-model/bus.rst b/Documentation/driver-api/driver-model/bus.rst index 016b15a6e8ea..9709ab62a468 100644 --- a/Documentation/driver-api/driver-model/bus.rst +++ b/Documentation/driver-api/driver-model/bus.rst @@ -125,8 +125,8 @@ Exporting Attributes struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + ssize_t (*show)(const struct bus_type *, char * buf); + ssize_t (*store)(const struct bus_type *, const char * buf, size_t count); }; Bus drivers can export attributes using the BUS_ATTR_RW macro that works diff --git a/Documentation/filesystems/sysfs.rst b/Documentation/filesystems/sysfs.rst index f8187d466b97..c32993bc83c7 100644 --- a/Documentation/filesystems/sysfs.rst +++ b/Documentation/filesystems/sysfs.rst @@ -373,8 +373,8 @@ Structure:: struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + ssize_t (*show)(const struct bus_type *, char * buf); + ssize_t (*store)(const struct bus_type *, const char * buf, size_t count); }; Declaring:: diff --git a/Documentation/translations/zh_CN/filesystems/sysfs.txt b/Documentation/translations/zh_CN/filesystems/sysfs.txt index 046cc1d52058..547062759e60 100644 --- a/Documentation/translations/zh_CN/filesystems/sysfs.txt +++ b/Documentation/translations/zh_CN/filesystems/sysfs.txt @@ -329,8 +329,8 @@ void device_remove_file(struct device *dev, const struct device_attribute * attr struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + ssize_t (*show)(const struct bus_type *, char * buf); + ssize_t (*store)(const struct bus_type *, const char * buf, size_t count); }; 声明: diff --git a/Documentation/translations/zh_TW/filesystems/sysfs.txt b/Documentation/translations/zh_TW/filesystems/sysfs.txt index acd677f19d4f..280824cc7e5d 100644 --- a/Documentation/translations/zh_TW/filesystems/sysfs.txt +++ b/Documentation/translations/zh_TW/filesystems/sysfs.txt @@ -332,8 +332,8 @@ void device_remove_file(struct device *dev, const struct device_attribute * attr struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *, char * buf); - ssize_t (*store)(struct bus_type *, const char * buf, size_t count); + ssize_t (*show)(const struct bus_type *, char * buf); + ssize_t (*store)(const struct bus_type *, const char * buf, size_t count); }; 聲明: diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index bb9c18682783..44703f13985b 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -267,7 +267,7 @@ static char *ibmebus_chomp(const char *in, size_t count) return out; } -static ssize_t probe_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t probe_store(const struct bus_type *bus, const char *buf, size_t count) { struct device_node *dn = NULL; struct device *dev; @@ -305,7 +305,7 @@ static ssize_t probe_store(struct bus_type *bus, const char *buf, size_t count) } static BUS_ATTR_WO(probe); -static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t remove_store(const struct bus_type *bus, const char *buf, size_t count) { struct device *dev; char *path; diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 770df9351aaa..bf7aff6390be 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1006,7 +1006,7 @@ ATTRIBUTE_GROUPS(vio_cmo_dev); /* sysfs bus functions and data structures for CMO */ #define viobus_cmo_rd_attr(name) \ -static ssize_t cmo_bus_##name##_show(struct bus_type *bt, char *buf) \ +static ssize_t cmo_bus_##name##_show(const struct bus_type *bt, char *buf) \ { \ return sprintf(buf, "%lu\n", vio_cmo.name); \ } \ @@ -1015,7 +1015,7 @@ static struct bus_attribute bus_attr_cmo_bus_##name = \ #define viobus_cmo_pool_rd_attr(name, var) \ static ssize_t \ -cmo_##name##_##var##_show(struct bus_type *bt, char *buf) \ +cmo_##name##_##var##_show(const struct bus_type *bt, char *buf) \ { \ return sprintf(buf, "%lu\n", vio_cmo.name.var); \ } \ @@ -1030,12 +1030,12 @@ viobus_cmo_pool_rd_attr(reserve, size); viobus_cmo_pool_rd_attr(excess, size); viobus_cmo_pool_rd_attr(excess, free); -static ssize_t cmo_high_show(struct bus_type *bt, char *buf) +static ssize_t cmo_high_show(const struct bus_type *bt, char *buf) { return sprintf(buf, "%lu\n", vio_cmo.high); } -static ssize_t cmo_high_store(struct bus_type *bt, const char *buf, +static ssize_t cmo_high_store(const struct bus_type *bt, const char *buf, size_t count) { unsigned long flags; diff --git a/drivers/ata/pata_parport/pata_parport.c b/drivers/ata/pata_parport/pata_parport.c index 294a266a0dda..64d1bde26940 100644 --- a/drivers/ata/pata_parport/pata_parport.c +++ b/drivers/ata/pata_parport/pata_parport.c @@ -554,8 +554,7 @@ void pata_parport_unregister_driver(struct pi_protocol *pr) } EXPORT_SYMBOL_GPL(pata_parport_unregister_driver); -static ssize_t new_device_store(struct bus_type *bus, const char *buf, - size_t count) +static ssize_t new_device_store(const struct bus_type *bus, const char *buf, size_t count) { char port[12] = "auto"; char protocol[8] = "auto"; @@ -630,8 +629,7 @@ static void pi_remove_one(struct device *dev) /* pata_parport_dev_release will do kfree(pi) */ } -static ssize_t delete_device_store(struct bus_type *bus, const char *buf, - size_t count) +static ssize_t delete_device_store(const struct bus_type *bus, const char *buf, size_t count) { struct device *dev; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 91a6b6b1fc49..819ab745fa9f 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -274,7 +274,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf, } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store); -static ssize_t drivers_autoprobe_show(struct bus_type *bus, char *buf) +static ssize_t drivers_autoprobe_show(const struct bus_type *bus, char *buf) { struct subsys_private *sp = bus_to_subsys(bus); int ret; @@ -287,7 +287,7 @@ static ssize_t drivers_autoprobe_show(struct bus_type *bus, char *buf) return ret; } -static ssize_t drivers_autoprobe_store(struct bus_type *bus, +static ssize_t drivers_autoprobe_store(const struct bus_type *bus, const char *buf, size_t count) { struct subsys_private *sp = bus_to_subsys(bus); @@ -304,7 +304,7 @@ static ssize_t drivers_autoprobe_store(struct bus_type *bus, return count; } -static ssize_t drivers_probe_store(struct bus_type *bus, +static ssize_t drivers_probe_store(const struct bus_type *bus, const char *buf, size_t count) { struct device *dev; @@ -808,7 +808,7 @@ static void klist_devices_put(struct klist_node *n) put_device(dev); } -static ssize_t bus_uevent_store(struct bus_type *bus, +static ssize_t bus_uevent_store(const struct bus_type *bus, const char *buf, size_t count) { struct subsys_private *sp = bus_to_subsys(bus); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 5cb008b9700a..84ad3b17956f 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -491,12 +491,12 @@ static bool single_major = true; module_param(single_major, bool, 0444); MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)"); -static ssize_t add_store(struct bus_type *bus, const char *buf, size_t count); -static ssize_t remove_store(struct bus_type *bus, const char *buf, +static ssize_t add_store(const struct bus_type *bus, const char *buf, size_t count); +static ssize_t remove_store(const struct bus_type *bus, const char *buf, size_t count); -static ssize_t add_single_major_store(struct bus_type *bus, const char *buf, +static ssize_t add_single_major_store(const struct bus_type *bus, const char *buf, size_t count); -static ssize_t remove_single_major_store(struct bus_type *bus, const char *buf, +static ssize_t remove_single_major_store(const struct bus_type *bus, const char *buf, size_t count); static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth); @@ -538,7 +538,7 @@ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) return is_lock_owner; } -static ssize_t supported_features_show(struct bus_type *bus, char *buf) +static ssize_t supported_features_show(const struct bus_type *bus, char *buf) { return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED); } @@ -6967,9 +6967,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth) return ret; } -static ssize_t do_rbd_add(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t do_rbd_add(const char *buf, size_t count) { struct rbd_device *rbd_dev = NULL; struct ceph_options *ceph_opts = NULL; @@ -7081,18 +7079,18 @@ static ssize_t do_rbd_add(struct bus_type *bus, goto out; } -static ssize_t add_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t add_store(const struct bus_type *bus, const char *buf, size_t count) { if (single_major) return -EINVAL; - return do_rbd_add(bus, buf, count); + return do_rbd_add(buf, count); } -static ssize_t add_single_major_store(struct bus_type *bus, const char *buf, +static ssize_t add_single_major_store(const struct bus_type *bus, const char *buf, size_t count) { - return do_rbd_add(bus, buf, count); + return do_rbd_add(buf, count); } static void rbd_dev_remove_parent(struct rbd_device *rbd_dev) @@ -7122,9 +7120,7 @@ static void rbd_dev_remove_parent(struct rbd_device *rbd_dev) } } -static ssize_t do_rbd_remove(struct bus_type *bus, - const char *buf, - size_t count) +static ssize_t do_rbd_remove(const char *buf, size_t count) { struct rbd_device *rbd_dev = NULL; struct list_head *tmp; @@ -7196,18 +7192,18 @@ static ssize_t do_rbd_remove(struct bus_type *bus, return count; } -static ssize_t remove_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t remove_store(const struct bus_type *bus, const char *buf, size_t count) { if (single_major) return -EINVAL; - return do_rbd_remove(bus, buf, count); + return do_rbd_remove(buf, count); } -static ssize_t remove_single_major_store(struct bus_type *bus, const char *buf, +static ssize_t remove_single_major_store(const struct bus_type *bus, const char *buf, size_t count) { - return do_rbd_remove(bus, buf, count); + return do_rbd_remove(buf, count); } /* diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 36cb091a33b4..653e2d4c116f 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -231,7 +231,7 @@ static int scan_fsl_mc_bus(struct device *dev, void *data) return 0; } -static ssize_t rescan_store(struct bus_type *bus, +static ssize_t rescan_store(const struct bus_type *bus, const char *buf, size_t count) { unsigned long val; @@ -284,7 +284,7 @@ static int fsl_mc_bus_get_autorescan(struct device *dev, void *data) return 0; } -static ssize_t autorescan_store(struct bus_type *bus, +static ssize_t autorescan_store(const struct bus_type *bus, const char *buf, size_t count) { bus_for_each_dev(bus, NULL, (void *)buf, fsl_mc_bus_set_autorescan); @@ -292,7 +292,7 @@ static ssize_t autorescan_store(struct bus_type *bus, return count; } -static ssize_t autorescan_show(struct bus_type *bus, char *buf) +static ssize_t autorescan_show(const struct bus_type *bus, char *buf) { bus_for_each_dev(bus, NULL, (void *)buf, fsl_mc_bus_get_autorescan); return strlen(buf); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 8ee6b6e2e2a4..66333cd6248e 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1927,7 +1927,7 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL); /* for user tooling to ensure port disable work has completed */ -static ssize_t flush_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t flush_store(const struct bus_type *bus, const char *buf, size_t count) { if (sysfs_streq(buf, "1")) { flush_workqueue(cxl_bus_wq); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index d24dd65b33d4..513adba09f56 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -684,7 +684,7 @@ static const struct attribute_group vmbus_dev_group = { __ATTRIBUTE_GROUPS(vmbus_dev); /* Set up the attribute for /sys/bus/vmbus/hibernation */ -static ssize_t hibernation_show(struct bus_type *bus, char *buf) +static ssize_t hibernation_show(const struct bus_type *bus, char *buf) { return sprintf(buf, "%d\n", !!hv_is_hibernation_supported()); } diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 0052968e881e..0787ad252dd9 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -132,7 +132,7 @@ static struct nsim_bus_dev * nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues); static ssize_t -new_device_store(struct bus_type *bus, const char *buf, size_t count) +new_device_store(const struct bus_type *bus, const char *buf, size_t count) { unsigned int id, port_count, num_queues; struct nsim_bus_dev *nsim_bus_dev; @@ -186,7 +186,7 @@ static BUS_ATTR_WO(new_device); static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev); static ssize_t -del_device_store(struct bus_type *bus, const char *buf, size_t count) +del_device_store(const struct bus_type *bus, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev, *tmp; unsigned int id; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index dd0d9d9bc509..ab32a91f287b 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -428,7 +428,7 @@ static ssize_t msi_bus_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RW(msi_bus); -static ssize_t rescan_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t rescan_store(const struct bus_type *bus, const char *buf, size_t count) { unsigned long val; struct pci_bus *b = NULL; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7a67611dc5f4..45c3bb039f21 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -6679,7 +6679,7 @@ void pci_reassigndev_resource_alignment(struct pci_dev *dev) } } -static ssize_t resource_alignment_show(struct bus_type *bus, char *buf) +static ssize_t resource_alignment_show(const struct bus_type *bus, char *buf) { size_t count = 0; @@ -6691,7 +6691,7 @@ static ssize_t resource_alignment_show(struct bus_type *bus, char *buf) return count; } -static ssize_t resource_alignment_store(struct bus_type *bus, +static ssize_t resource_alignment_store(const struct bus_type *bus, const char *buf, size_t count) { char *param, *old, *end; diff --git a/drivers/peci/sysfs.c b/drivers/peci/sysfs.c index db9ef05776e3..c04244075794 100644 --- a/drivers/peci/sysfs.c +++ b/drivers/peci/sysfs.c @@ -15,7 +15,7 @@ static int rescan_controller(struct device *dev, void *data) return peci_controller_scan_devices(to_peci_controller(dev)); } -static ssize_t rescan_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t rescan_store(const struct bus_type *bus, const char *buf, size_t count) { bool res; int ret; diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c index f7679602498e..90d391210533 100644 --- a/drivers/rapidio/rio-sysfs.c +++ b/drivers/rapidio/rio-sysfs.c @@ -286,7 +286,7 @@ const struct attribute_group *rio_dev_groups[] = { NULL, }; -static ssize_t scan_store(struct bus_type *bus, const char *buf, size_t count) +static ssize_t scan_store(const struct bus_type *bus, const char *buf, size_t count) { long val; int rc; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index f4cc1720156f..5a99e0b18289 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1166,12 +1166,12 @@ EXPORT_SYMBOL(ap_parse_mask_str); * AP bus attributes. */ -static ssize_t ap_domain_show(struct bus_type *bus, char *buf) +static ssize_t ap_domain_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_domain_index); } -static ssize_t ap_domain_store(struct bus_type *bus, +static ssize_t ap_domain_store(const struct bus_type *bus, const char *buf, size_t count) { int domain; @@ -1193,7 +1193,7 @@ static ssize_t ap_domain_store(struct bus_type *bus, static BUS_ATTR_RW(ap_domain); -static ssize_t ap_control_domain_mask_show(struct bus_type *bus, char *buf) +static ssize_t ap_control_domain_mask_show(const struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ return scnprintf(buf, PAGE_SIZE, "not supported\n"); @@ -1208,7 +1208,7 @@ static ssize_t ap_control_domain_mask_show(struct bus_type *bus, char *buf) static BUS_ATTR_RO(ap_control_domain_mask); -static ssize_t ap_usage_domain_mask_show(struct bus_type *bus, char *buf) +static ssize_t ap_usage_domain_mask_show(const struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ return scnprintf(buf, PAGE_SIZE, "not supported\n"); @@ -1223,7 +1223,7 @@ static ssize_t ap_usage_domain_mask_show(struct bus_type *bus, char *buf) static BUS_ATTR_RO(ap_usage_domain_mask); -static ssize_t ap_adapter_mask_show(struct bus_type *bus, char *buf) +static ssize_t ap_adapter_mask_show(const struct bus_type *bus, char *buf) { if (!ap_qci_info) /* QCI not supported */ return scnprintf(buf, PAGE_SIZE, "not supported\n"); @@ -1238,7 +1238,7 @@ static ssize_t ap_adapter_mask_show(struct bus_type *bus, char *buf) static BUS_ATTR_RO(ap_adapter_mask); -static ssize_t ap_interrupts_show(struct bus_type *bus, char *buf) +static ssize_t ap_interrupts_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_irq_flag ? 1 : 0); @@ -1246,12 +1246,12 @@ static ssize_t ap_interrupts_show(struct bus_type *bus, char *buf) static BUS_ATTR_RO(ap_interrupts); -static ssize_t config_time_show(struct bus_type *bus, char *buf) +static ssize_t config_time_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_config_time); } -static ssize_t config_time_store(struct bus_type *bus, +static ssize_t config_time_store(const struct bus_type *bus, const char *buf, size_t count) { int time; @@ -1265,12 +1265,12 @@ static ssize_t config_time_store(struct bus_type *bus, static BUS_ATTR_RW(config_time); -static ssize_t poll_thread_show(struct bus_type *bus, char *buf) +static ssize_t poll_thread_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_poll_kthread ? 1 : 0); } -static ssize_t poll_thread_store(struct bus_type *bus, +static ssize_t poll_thread_store(const struct bus_type *bus, const char *buf, size_t count) { int flag, rc; @@ -1289,12 +1289,12 @@ static ssize_t poll_thread_store(struct bus_type *bus, static BUS_ATTR_RW(poll_thread); -static ssize_t poll_timeout_show(struct bus_type *bus, char *buf) +static ssize_t poll_timeout_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%llu\n", poll_timeout); } -static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf, +static ssize_t poll_timeout_store(const struct bus_type *bus, const char *buf, size_t count) { unsigned long long time; @@ -1318,21 +1318,21 @@ static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf, static BUS_ATTR_RW(poll_timeout); -static ssize_t ap_max_domain_id_show(struct bus_type *bus, char *buf) +static ssize_t ap_max_domain_id_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_max_domain_id); } static BUS_ATTR_RO(ap_max_domain_id); -static ssize_t ap_max_adapter_id_show(struct bus_type *bus, char *buf) +static ssize_t ap_max_adapter_id_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%d\n", ap_max_adapter_id); } static BUS_ATTR_RO(ap_max_adapter_id); -static ssize_t apmask_show(struct bus_type *bus, char *buf) +static ssize_t apmask_show(const struct bus_type *bus, char *buf) { int rc; @@ -1393,7 +1393,7 @@ static int apmask_commit(unsigned long *newapm) return 0; } -static ssize_t apmask_store(struct bus_type *bus, const char *buf, +static ssize_t apmask_store(const struct bus_type *bus, const char *buf, size_t count) { int rc, changes = 0; @@ -1425,7 +1425,7 @@ static ssize_t apmask_store(struct bus_type *bus, const char *buf, static BUS_ATTR_RW(apmask); -static ssize_t aqmask_show(struct bus_type *bus, char *buf) +static ssize_t aqmask_show(const struct bus_type *bus, char *buf) { int rc; @@ -1486,7 +1486,7 @@ static int aqmask_commit(unsigned long *newaqm) return 0; } -static ssize_t aqmask_store(struct bus_type *bus, const char *buf, +static ssize_t aqmask_store(const struct bus_type *bus, const char *buf, size_t count) { int rc, changes = 0; @@ -1518,13 +1518,13 @@ static ssize_t aqmask_store(struct bus_type *bus, const char *buf, static BUS_ATTR_RW(aqmask); -static ssize_t scans_show(struct bus_type *bus, char *buf) +static ssize_t scans_show(const struct bus_type *bus, char *buf) { return scnprintf(buf, PAGE_SIZE, "%llu\n", atomic64_read(&ap_scan_bus_count)); } -static ssize_t scans_store(struct bus_type *bus, const char *buf, +static ssize_t scans_store(const struct bus_type *bus, const char *buf, size_t count) { AP_DBF_INFO("%s force AP bus rescan\n", __func__); @@ -1536,7 +1536,7 @@ static ssize_t scans_store(struct bus_type *bus, const char *buf, static BUS_ATTR_RW(scans); -static ssize_t bindings_show(struct bus_type *bus, char *buf) +static ssize_t bindings_show(const struct bus_type *bus, char *buf) { int rc; unsigned int apqns, n; diff --git a/drivers/scsi/fcoe/fcoe_sysfs.c b/drivers/scsi/fcoe/fcoe_sysfs.c index 6260aa5ea6af..e17957f8085c 100644 --- a/drivers/scsi/fcoe/fcoe_sysfs.c +++ b/drivers/scsi/fcoe/fcoe_sysfs.c @@ -659,17 +659,17 @@ static const struct device_type fcoe_fcf_device_type = { .release = fcoe_fcf_device_release, }; -static ssize_t ctlr_create_store(struct bus_type *bus, const char *buf, +static ssize_t ctlr_create_store(const struct bus_type *bus, const char *buf, size_t count) { - return fcoe_ctlr_create_store(bus, buf, count); + return fcoe_ctlr_create_store(buf, count); } static BUS_ATTR_WO(ctlr_create); -static ssize_t ctlr_destroy_store(struct bus_type *bus, const char *buf, +static ssize_t ctlr_destroy_store(const struct bus_type *bus, const char *buf, size_t count) { - return fcoe_ctlr_destroy_store(bus, buf, count); + return fcoe_ctlr_destroy_store(buf, count); } static BUS_ATTR_WO(ctlr_destroy); diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c index 62341c6353a7..46b0bf237be1 100644 --- a/drivers/scsi/fcoe/fcoe_transport.c +++ b/drivers/scsi/fcoe/fcoe_transport.c @@ -745,8 +745,7 @@ static int libfcoe_device_notification(struct notifier_block *notifier, return NOTIFY_OK; } -ssize_t fcoe_ctlr_create_store(struct bus_type *bus, - const char *buf, size_t count) +ssize_t fcoe_ctlr_create_store(const char *buf, size_t count) { struct net_device *netdev = NULL; struct fcoe_transport *ft = NULL; @@ -808,8 +807,7 @@ ssize_t fcoe_ctlr_create_store(struct bus_type *bus, return count; } -ssize_t fcoe_ctlr_destroy_store(struct bus_type *bus, - const char *buf, size_t count) +ssize_t fcoe_ctlr_destroy_store(const char *buf, size_t count) { int rc = -ENODEV; struct net_device *netdev = NULL; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index c258e8770285..78c875386c06 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -118,8 +118,8 @@ extern int __must_check bus_rescan_devices(struct bus_type *bus); struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *bus, char *buf); - ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); + ssize_t (*show)(const struct bus_type *bus, char *buf); + ssize_t (*store)(const struct bus_type *bus, const char *buf, size_t count); }; #define BUS_ATTR_RW(_name) \ diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index 279782156373..8300ef1a982e 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -397,10 +397,8 @@ int fcoe_transport_attach(struct fcoe_transport *ft); int fcoe_transport_detach(struct fcoe_transport *ft); /* sysfs store handler for ctrl_control interface */ -ssize_t fcoe_ctlr_create_store(struct bus_type *bus, - const char *buf, size_t count); -ssize_t fcoe_ctlr_destroy_store(struct bus_type *bus, - const char *buf, size_t count); +ssize_t fcoe_ctlr_create_store(const char *buf, size_t count); +ssize_t fcoe_ctlr_destroy_store(const char *buf, size_t count); #endif /* _LIBFCOE_H */ -- GitLab From 00c4a3c47da761b4ba5d09c46b6fc77af5759081 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:06 +0100 Subject: [PATCH 1126/5631] driver core: bus: constantify bus_register() bus_register() is now safe to take a constant * to bus_type, so make that change and mark the subsys_private bus_type * constant as well. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-24-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 +- drivers/base/bus.c | 2 +- include/linux/device/bus.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index f1034e27e651..09c6682d16b5 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -49,7 +49,7 @@ struct subsys_private { struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; - struct bus_type *bus; + const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 819ab745fa9f..f739a2a79e59 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -841,7 +841,7 @@ static struct bus_attribute bus_attr_uevent = __ATTR(uevent, 0200, NULL, * infrastructure, then register the children subsystems it has: * the devices and drivers that belong to the subsystem. */ -int bus_register(struct bus_type *bus) +int bus_register(const struct bus_type *bus) { int retval; struct subsys_private *priv; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 78c875386c06..c30c4748c170 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -110,7 +110,7 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(struct bus_type *bus); +extern int __must_check bus_register(const struct bus_type *bus); extern void bus_unregister(const struct bus_type *bus); -- GitLab From 9622b9f282e0f0d37683b21575b683039169e397 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:07 +0100 Subject: [PATCH 1127/5631] driver core: bus: constify bus_rescan_devices() The bus_rescan_devices() function was missed in the previous change of the bus_for_each* constant pointer changes, so fix it up now to take a const * to struct bus_type. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-25-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 2 +- include/linux/device/bus.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f739a2a79e59..ced61fad390e 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -769,7 +769,7 @@ static int __must_check bus_rescan_devices_helper(struct device *dev, * attached and rescan it against existing drivers to see if it matches * any by calling device_attach() for the unbound devices. */ -int bus_rescan_devices(struct bus_type *bus) +int bus_rescan_devices(const struct bus_type *bus) { return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper); } diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index c30c4748c170..b517b82d4723 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -114,7 +114,7 @@ extern int __must_check bus_register(const struct bus_type *bus); extern void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(struct bus_type *bus); +extern int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; -- GitLab From 7c06be04251a0b3349868622a2111a54cbfad8d4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:08 +0100 Subject: [PATCH 1128/5631] driver core: bus: constify driver_find() The driver_find() function can now take a const * to bus_type, not just a * so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-26-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 2 +- include/linux/device/driver.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index ced61fad390e..8fea26c22521 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -1307,7 +1307,7 @@ EXPORT_SYMBOL_GPL(subsys_virtual_register); * from being unregistered or unloaded while the caller is using it. * The caller is responsible for preventing this. */ -struct device_driver *driver_find(const char *name, struct bus_type *bus) +struct device_driver *driver_find(const char *name, const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kobject *k; diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 50d0a416a5e7..ceb0e477c2c8 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -126,7 +126,7 @@ extern int __must_check driver_register(struct device_driver *drv); extern void driver_unregister(struct device_driver *drv); extern struct device_driver *driver_find(const char *name, - struct bus_type *bus); + const struct bus_type *bus); extern int driver_probe_done(void); extern void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); -- GitLab From 38370c4e25af7f5670787a1bb1861b289f2ad770 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:09 +0100 Subject: [PATCH 1129/5631] driver core: bus: constify bus_get() It's funny to think about getting a reference count of a constant structure pointer, but this locks into place the private data "underneath" the struct bus_type() which is important to not go away while we are working with the bus structure for some callbacks. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-27-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/bus.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 8fea26c22521..84a21084d67d 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -84,7 +84,7 @@ static struct subsys_private *bus_to_subsys(const struct bus_type *bus) return sp; } -static struct bus_type *bus_get(struct bus_type *bus) +static const struct bus_type *bus_get(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); @@ -233,7 +233,7 @@ static const struct kset_uevent_ops bus_uevent_ops = { static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t count) { - struct bus_type *bus = bus_get(drv->bus); + const struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; @@ -256,7 +256,7 @@ static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t count) { - struct bus_type *bus = bus_get(drv->bus); + const struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; -- GitLab From c28dd08ef713d2127c5bad3f3e0e93d6ec0309a2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:10 +0100 Subject: [PATCH 1130/5631] driver core: make the bus_type in struct device_driver constant The pointer to struct bus_type in struct device_driver should only be pointing to something that can never change now that the driver core has fixed up the previously writable fields. So mark it as a constant pointer to enforce this and move forward with the goal of moving bus_type into read-only memory. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-28-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index ceb0e477c2c8..0f22a6f46f8c 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -95,7 +95,7 @@ enum probe_type { */ struct device_driver { const char *name; - struct bus_type *bus; + const struct bus_type *bus; struct module *owner; const char *mod_name; /* used for built-in modules */ -- GitLab From 550fac229e469b75ab4609b617146314786c62b3 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:11 +0100 Subject: [PATCH 1131/5631] crypto: hisilicon/qm - make struct bus_type * const In the function, qm_get_qos_value(), a struct bus_type * is used, but it really should be a const pointer as it is not modified anywhere in the function, and the driver core function it is used in expects a constant pointer. Cc: Weili Qian Cc: Zhou Wang Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Acked-by: Herbert Xu Link: https://lore.kernel.org/r/20230313182918.1312597-29-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/crypto/hisilicon/qm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index e4c84433a88a..fd1a38ee55f8 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3691,7 +3691,7 @@ static ssize_t qm_get_qos_value(struct hisi_qm *qm, const char *buf, unsigned long *val, unsigned int *fun_index) { - struct bus_type *bus_type = qm->pdev->dev.bus; + const struct bus_type *bus_type = qm->pdev->dev.bus; char tbuf_bdf[QM_DBG_READ_LEN] = {0}; char val_buf[QM_DBG_READ_LEN] = {0}; struct pci_dev *pdev; -- GitLab From c9a9f18d3ad8acb9f9d6b52b5e1922a70b48dc35 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:12 +0100 Subject: [PATCH 1132/5631] drm/i915/huc: use const struct bus_type pointers The struct bus_type pointers in the functions intel_huc_register_gsc_notifier() and intel_huc_unregister_gsc_notifier() should be a const pointer, as the structure is not modified anywhere in the functions, and the pointer they are passed will be a const * in the near future. Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: David Airlie Cc: Daniel Vetter Cc: Daniele Ceraolo Spurio Cc: Alan Previn Cc: John Harrison Cc: Greg Kroah-Hartman Cc: Tony Ye Cc: Vitaly Lubart Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Acked-by: Tvrtko Ursulin Link: https://lore.kernel.org/r/20230313182918.1312597-30-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/gpu/drm/i915/gt/uc/intel_huc.c | 4 ++-- drivers/gpu/drm/i915/gt/uc/intel_huc.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 410905da8e97..8b453bd7c953 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -183,7 +183,7 @@ static int gsc_notifier(struct notifier_block *nb, unsigned long action, void *d return 0; } -void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus) +void intel_huc_register_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus) { int ret; @@ -200,7 +200,7 @@ void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus } } -void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus) +void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus) { if (!huc->delayed_load.nb.notifier_call) return; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h index 52db03620c60..05d4832f8461 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h @@ -51,8 +51,8 @@ int intel_huc_check_status(struct intel_huc *huc); void intel_huc_update_auth_status(struct intel_huc *huc); bool intel_huc_is_authenticated(struct intel_huc *huc); -void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); -void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus); +void intel_huc_register_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus); +void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus); static inline int intel_huc_sanitize(struct intel_huc *huc) { -- GitLab From 94a1150421940ff2e8113b5fa6837774777d5b3d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:13 +0100 Subject: [PATCH 1133/5631] vhost-vdpa: vhost_vdpa_alloc_domain() should be using a const struct bus_type * The function, vhost_vdpa_alloc_domain(), has a pointer to a struct bus_type, but it should be constant as the function it passes it to expects it to be const, and the vhost code does not modify it in any way. Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/20230313182918.1312597-31-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/vhost/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index dc12dbd5b43b..08c7cb3399fc 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1140,7 +1140,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) struct vdpa_device *vdpa = v->vdpa; const struct vdpa_config_ops *ops = vdpa->config; struct device *dma_dev = vdpa_get_dma_dev(vdpa); - struct bus_type *bus; + const struct bus_type *bus; int ret; /* Device want to do DMA by itself */ -- GitLab From 790f3b60ac78efb339c7ef2f4d2dba63c804110a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:14 +0100 Subject: [PATCH 1134/5631] dmaengine: idxd: use const struct bus_type * In the functions unbind_store() and bind_store(), a struct bus_type * should be a const one, as the driver core bus functions used by this variable are expecting the pointer to be constant, and these functions do not modify the pointer at all. Cc: dmaengine@vger.kernel.org Acked-by: Vinod Koul Acked-by: Fenghua Yu Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230313182918.1312597-32-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/dma/idxd/compat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/idxd/compat.c b/drivers/dma/idxd/compat.c index 3df21615f888..5fd38d1b9d28 100644 --- a/drivers/dma/idxd/compat.c +++ b/drivers/dma/idxd/compat.c @@ -16,7 +16,7 @@ extern void device_driver_detach(struct device *dev); static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t count) { - struct bus_type *bus = drv->bus; + const struct bus_type *bus = drv->bus; struct device *dev; int rc = -ENODEV; @@ -32,7 +32,7 @@ static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t count) { - struct bus_type *bus = drv->bus; + const struct bus_type *bus = drv->bus; struct device *dev; struct device_driver *alt_drv = NULL; int rc = -ENODEV; -- GitLab From a3ea9fbc822f9ae9402ffc0954751d7a11f672ea Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:15 +0100 Subject: [PATCH 1135/5631] ARM/dma-mapping: const a pointer to bus_type in arm_iommu_create_mapping() Change the function arm_iommu_create_mapping() to take a pointer to a const bus_type as the function does not modify the variable the pointer points to at all, and the driver core bus functions it calls all expect a const * type. Cc: Russell King Cc: Greg Kroah-Hartman Cc: "Russell King (Oracle)" Cc: Arnd Bergmann Cc: Robin Murphy Cc: Kees Cook Cc: Lukas Bulwahn Cc: Ben Dooks Cc: Linus Walleij Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230313182918.1312597-33-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/dma-iommu.h | 2 +- arch/arm/mm/dma-mapping.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h index fe9ef6f79e9c..82ec1ccf1fee 100644 --- a/arch/arm/include/asm/dma-iommu.h +++ b/arch/arm/include/asm/dma-iommu.h @@ -24,7 +24,7 @@ struct dma_iommu_mapping { }; struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size); +arm_iommu_create_mapping(const struct bus_type *bus, dma_addr_t base, u64 size); void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping); diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 8bc01071474a..b4a33358d2e9 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1543,7 +1543,7 @@ static const struct dma_map_ops iommu_ops = { * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size) +arm_iommu_create_mapping(const struct bus_type *bus, dma_addr_t base, u64 size) { unsigned int bits = size >> PAGE_SHIFT; unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); -- GitLab From b18d0a0f92a8fe9e56d812808184c8c4b9f18f92 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:16 +0100 Subject: [PATCH 1136/5631] iommu: make the pointer to struct bus_type constant A number of iommu functions take a struct bus_type * and never modify the data passed in, so make them all const * as that is what the driver core is expecting to have passed into as well. This is a step toward making all struct bus_type pointers constant in the kernel. Cc: Will Deacon Cc: Robin Murphy Cc: iommu@lists.linux.dev Acked-by: Joerg Roedel Link: https://lore.kernel.org/r/20230313182918.1312597-34-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/iommu.c | 14 +++++++------- include/linux/iommu.h | 10 +++++----- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 10db680acaed..0b5e181998c9 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -89,7 +89,7 @@ static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data); static int iommu_alloc_default_domain(struct iommu_group *group, struct device *dev); -static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, +static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus, unsigned type); static int __iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -1631,7 +1631,7 @@ static int iommu_get_def_domain_type(struct device *dev) return 0; } -static int iommu_group_alloc_default_domain(struct bus_type *bus, +static int iommu_group_alloc_default_domain(const struct bus_type *bus, struct iommu_group *group, unsigned int type) { @@ -1777,7 +1777,7 @@ static int probe_get_default_domain_type(struct device *dev, void *data) return 0; } -static void probe_alloc_default_domain(struct bus_type *bus, +static void probe_alloc_default_domain(const struct bus_type *bus, struct iommu_group *group) { struct __group_domain_type gtype; @@ -1832,7 +1832,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group) iommu_do_create_direct_mappings); } -int bus_iommu_probe(struct bus_type *bus) +int bus_iommu_probe(const struct bus_type *bus) { struct iommu_group *group, *next; LIST_HEAD(group_list); @@ -1876,7 +1876,7 @@ int bus_iommu_probe(struct bus_type *bus) return ret; } -bool iommu_present(struct bus_type *bus) +bool iommu_present(const struct bus_type *bus) { return bus->iommu_ops != NULL; } @@ -1951,7 +1951,7 @@ void iommu_set_fault_handler(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_set_fault_handler); -static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, +static struct iommu_domain *__iommu_domain_alloc(const struct bus_type *bus, unsigned type) { struct iommu_domain *domain; @@ -1976,7 +1976,7 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, return domain; } -struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) +struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED); } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..0fd4e6734d5b 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -455,11 +455,11 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_iommu_probe(struct bus_type *bus); -extern bool iommu_present(struct bus_type *bus); +extern int bus_iommu_probe(const struct bus_type *bus); +extern bool iommu_present(const struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); -extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); +extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus); extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, @@ -732,7 +732,7 @@ struct iommu_device {}; struct iommu_fault_param {}; struct iommu_iotlb_gather {}; -static inline bool iommu_present(struct bus_type *bus) +static inline bool iommu_present(const struct bus_type *bus) { return false; } @@ -742,7 +742,7 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) +static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { return NULL; } -- GitLab From d492cc2573a08352c48a66d3e3f312a15fb3f363 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:17 +0100 Subject: [PATCH 1137/5631] driver core: device.h: make struct bus_type a const * Now that all users who accessed the bus_type structure in struct device are properly using it as a const *, mark it as such so that no one can modify it going forward anymore. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230313182918.1312597-35-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/device.h b/include/linux/device.h index 862397ae520d..3b23772d3bbb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -566,7 +566,7 @@ struct device { const char *init_name; /* initial name of the device */ const struct device_type *type; - struct bus_type *bus; /* type of bus device is on */ + const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device -- GitLab From 9d11b13402d1b80f7f3ca5061d75f15cf8002555 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 13 Mar 2023 19:29:18 +0100 Subject: [PATCH 1138/5631] USB: mark all struct bus_type as const Now that the driver core can properly handle constant struct bus_type, move all of the USB subsystem struct bus_type structures as const, placing them into read-only memory which can not be modified at runtime. Cc: Johan Hovold Cc: Evan Green Cc: Alan Stern Cc: linux-usb@vger.kernel.org Acked-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230313182918.1312597-36-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/ulpi.c | 2 +- drivers/usb/core/driver.c | 2 +- drivers/usb/core/usb.h | 2 +- drivers/usb/gadget/udc/core.c | 4 ++-- drivers/usb/serial/bus.c | 2 +- drivers/usb/typec/bus.c | 2 +- drivers/usb/typec/bus.h | 2 +- include/linux/usb/serial.h | 2 +- 8 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index a98b2108376a..8305a5dfb910 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -90,7 +90,7 @@ static void ulpi_remove(struct device *dev) drv->remove(to_ulpi_dev(dev)); } -static struct bus_type ulpi_bus = { +static const struct bus_type ulpi_bus = { .name = "ulpi", .match = ulpi_match, .uevent = ulpi_uevent, diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index a0e076c6f3a4..f58a0299fb3b 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -2025,7 +2025,7 @@ int usb_disable_usb2_hardware_lpm(struct usb_device *udev) #endif /* CONFIG_PM */ -struct bus_type usb_bus_type = { +const struct bus_type usb_bus_type = { .name = "usb", .match = usb_device_match, .uevent = usb_uevent, diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index 0eac7d4285d1..cd434af259c3 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -140,7 +140,7 @@ static inline int usb_disable_usb2_hardware_lpm(struct usb_device *udev) #endif -extern struct bus_type usb_bus_type; +extern const struct bus_type usb_bus_type; extern struct mutex usb_port_peer_mutex; extern struct device_type usb_device_type; extern struct device_type usb_if_device_type; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index df930b041c33..d919f0743a0a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -26,7 +26,7 @@ static DEFINE_IDA(gadget_id_numbers); -static struct bus_type gadget_bus_type; +static const struct bus_type gadget_bus_type; /** * struct usb_udc - describes one usb device controller @@ -1747,7 +1747,7 @@ static int usb_udc_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -static struct bus_type gadget_bus_type = { +static const struct bus_type gadget_bus_type = { .name = "gadget", .probe = gadget_bind_driver, .remove = gadget_unbind_driver, diff --git a/drivers/usb/serial/bus.c b/drivers/usb/serial/bus.c index 9e38142acd38..3eb8dc3a1a8f 100644 --- a/drivers/usb/serial/bus.c +++ b/drivers/usb/serial/bus.c @@ -144,7 +144,7 @@ static void free_dynids(struct usb_serial_driver *drv) spin_unlock(&drv->dynids.lock); } -struct bus_type usb_serial_bus_type = { +const struct bus_type usb_serial_bus_type = { .name = "usb-serial", .match = usb_serial_device_match, .probe = usb_serial_device_probe, diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 098f0efaa58d..fe5b9a2e61f5 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -431,7 +431,7 @@ static void typec_remove(struct device *dev) adev->ops = NULL; } -struct bus_type typec_bus = { +const struct bus_type typec_bus = { .name = "typec", .dev_groups = typec_groups, .match = typec_match, diff --git a/drivers/usb/typec/bus.h b/drivers/usb/typec/bus.h index c89168857417..643b8c81786d 100644 --- a/drivers/usb/typec/bus.h +++ b/drivers/usb/typec/bus.h @@ -28,7 +28,7 @@ struct altmode { #define to_altmode(d) container_of(d, struct altmode, adev) -extern struct bus_type typec_bus; +extern const struct bus_type typec_bus; extern const struct device_type typec_altmode_dev_type; #define is_typec_altmode(_dev_) (_dev_->type == &typec_altmode_dev_type) diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index f7bfedb740f5..7eeb5f9c4f0d 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -378,7 +378,7 @@ void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, int usb_serial_bus_register(struct usb_serial_driver *device); void usb_serial_bus_deregister(struct usb_serial_driver *device); -extern struct bus_type usb_serial_bus_type; +extern const struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; static inline void usb_serial_debug_data(struct device *dev, -- GitLab From 8504fa9baf8bdc5f333f24077b54df1d16173d99 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 22 Mar 2023 18:35:58 +0100 Subject: [PATCH 1139/5631] dt-bindings: mailbox: qcom,apcs-kpss-global: correct SDX55 clocks SDX55 and SDX65 DTS takes clocks in a bit different order. Adjust bindings to the DTS. Fixes: 0d17014e9189 ("dt-bindings: mailbox: Add binding for SDX55 APCS") Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Acked-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230322173559.809805-1-krzysztof.kozlowski@linaro.org --- .../devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index d888ead09282..2992227631c4 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -97,14 +97,14 @@ allOf: properties: clocks: items: + - description: reference clock - description: primary pll parent of the clock driver - description: auxiliary parent - - description: reference clock clock-names: items: + - const: ref - const: pll - const: aux - - const: ref - if: properties: compatible: -- GitLab From 22ead09ba40745e50970565af1996c2c1cc4e909 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 22 Mar 2023 18:35:59 +0100 Subject: [PATCH 1140/5631] dt-bindings: mailbox: qcom,apcs-kpss-global: fix SDX55 'if' match The qcom,sdx55-apcs-gcc is followed by another compatible (syscon), thus the 'if' clause must match by contains. Fixes: 0d17014e9189 ("dt-bindings: mailbox: Add binding for SDX55 APCS") Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Acked-by: Manivannan Sadhasivam Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230322173559.809805-2-krzysztof.kozlowski@linaro.org --- .../devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index 2992227631c4..4d2f408a5efb 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -91,8 +91,9 @@ allOf: - if: properties: compatible: - enum: - - qcom,sdx55-apcs-gcc + contains: + enum: + - qcom,sdx55-apcs-gcc then: properties: clocks: -- GitLab From 1d83f18be5ad3054636322925f6614e62cb5ff91 Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Fri, 17 Feb 2023 14:03:04 +0530 Subject: [PATCH 1141/5631] clk: qcom: apss-ipq-pll: refactor the driver to accommodate different PLL types APSS PLL found on the IPQ8074 and IPQ6018 are of type Huayra PLL. But, IPQ5332 APSS PLL is of type Stromer Plus. To accommodate both these PLLs, refactor the driver to take the clk_alpha_pll, alpha_pll_config via driver data. Reviewed-by: Konrad Dybcio Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230217083308.12017-2-quic_kathirav@quicinc.com --- drivers/clk/qcom/apss-ipq-pll.c | 60 ++++++++++++++++++++++----------- 1 file changed, 41 insertions(+), 19 deletions(-) diff --git a/drivers/clk/qcom/apss-ipq-pll.c b/drivers/clk/qcom/apss-ipq-pll.c index a5aea27eb867..4f2a147e9fb2 100644 --- a/drivers/clk/qcom/apss-ipq-pll.c +++ b/drivers/clk/qcom/apss-ipq-pll.c @@ -8,20 +8,27 @@ #include "clk-alpha-pll.h" -static const u8 ipq_pll_offsets[] = { - [PLL_OFF_L_VAL] = 0x08, - [PLL_OFF_ALPHA_VAL] = 0x10, - [PLL_OFF_USER_CTL] = 0x18, - [PLL_OFF_CONFIG_CTL] = 0x20, - [PLL_OFF_CONFIG_CTL_U] = 0x24, - [PLL_OFF_STATUS] = 0x28, - [PLL_OFF_TEST_CTL] = 0x30, - [PLL_OFF_TEST_CTL_U] = 0x34, +/* + * Even though APSS PLL type is of existing one (like Huayra), its offsets + * are different from the one mentioned in the clk-alpha-pll.c, since the + * PLL is specific to APSS, so lets the define the same. + */ +static const u8 ipq_pll_offsets[][PLL_OFF_MAX_REGS] = { + [CLK_ALPHA_PLL_TYPE_HUAYRA] = { + [PLL_OFF_L_VAL] = 0x08, + [PLL_OFF_ALPHA_VAL] = 0x10, + [PLL_OFF_USER_CTL] = 0x18, + [PLL_OFF_CONFIG_CTL] = 0x20, + [PLL_OFF_CONFIG_CTL_U] = 0x24, + [PLL_OFF_STATUS] = 0x28, + [PLL_OFF_TEST_CTL] = 0x30, + [PLL_OFF_TEST_CTL_U] = 0x34, + }, }; -static struct clk_alpha_pll ipq_pll = { +static struct clk_alpha_pll ipq_pll_huayra = { .offset = 0x0, - .regs = ipq_pll_offsets, + .regs = ipq_pll_offsets[CLK_ALPHA_PLL_TYPE_HUAYRA], .flags = SUPPORTS_DYNAMIC_UPDATE, .clkr = { .enable_reg = 0x0, @@ -61,6 +68,21 @@ static const struct alpha_pll_config ipq8074_pll_config = { .test_ctl_hi_val = 0x4000, }; +struct apss_pll_data { + struct clk_alpha_pll *pll; + const struct alpha_pll_config *pll_config; +}; + +static struct apss_pll_data ipq8074_pll_data = { + .pll = &ipq_pll_huayra, + .pll_config = &ipq8074_pll_config, +}; + +static struct apss_pll_data ipq6018_pll_data = { + .pll = &ipq_pll_huayra, + .pll_config = &ipq6018_pll_config, +}; + static const struct regmap_config ipq_pll_regmap_config = { .reg_bits = 32, .reg_stride = 4, @@ -71,7 +93,7 @@ static const struct regmap_config ipq_pll_regmap_config = { static int apss_ipq_pll_probe(struct platform_device *pdev) { - const struct alpha_pll_config *ipq_pll_config; + const struct apss_pll_data *data; struct device *dev = &pdev->dev; struct regmap *regmap; void __iomem *base; @@ -85,23 +107,23 @@ static int apss_ipq_pll_probe(struct platform_device *pdev) if (IS_ERR(regmap)) return PTR_ERR(regmap); - ipq_pll_config = of_device_get_match_data(&pdev->dev); - if (!ipq_pll_config) + data = of_device_get_match_data(&pdev->dev); + if (!data) return -ENODEV; - clk_alpha_pll_configure(&ipq_pll, regmap, ipq_pll_config); + clk_alpha_pll_configure(data->pll, regmap, data->pll_config); - ret = devm_clk_register_regmap(dev, &ipq_pll.clkr); + ret = devm_clk_register_regmap(dev, &data->pll->clkr); if (ret) return ret; return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, - &ipq_pll.clkr.hw); + &data->pll->clkr.hw); } static const struct of_device_id apss_ipq_pll_match_table[] = { - { .compatible = "qcom,ipq6018-a53pll", .data = &ipq6018_pll_config }, - { .compatible = "qcom,ipq8074-a53pll", .data = &ipq8074_pll_config }, + { .compatible = "qcom,ipq6018-a53pll", .data = &ipq6018_pll_data }, + { .compatible = "qcom,ipq8074-a53pll", .data = &ipq8074_pll_data }, { } }; MODULE_DEVICE_TABLE(of, apss_ipq_pll_match_table); -- GitLab From 102262767edefbe2560c1111b19b193fcfd9de5d Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Fri, 17 Feb 2023 14:03:05 +0530 Subject: [PATCH 1142/5631] dt-bindings: clock: qcom,a53pll: add IPQ5332 compatible Add IPQ5332 compatible to A53 PLL bindings. Acked-by: Krzysztof Kozlowski Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230217083308.12017-3-quic_kathirav@quicinc.com --- Documentation/devicetree/bindings/clock/qcom,a53pll.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/clock/qcom,a53pll.yaml b/Documentation/devicetree/bindings/clock/qcom,a53pll.yaml index 525ebaa93c85..3b6169f30154 100644 --- a/Documentation/devicetree/bindings/clock/qcom,a53pll.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,a53pll.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,ipq5332-a53pll - qcom,ipq6018-a53pll - qcom,ipq8074-a53pll - qcom,msm8916-a53pll -- GitLab From c7ef7fbb1ccfc8b25f3b5382b70274189ba75bcc Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Fri, 17 Feb 2023 14:03:06 +0530 Subject: [PATCH 1143/5631] clk: qcom: apss-ipq-pll: add support for IPQ5332 IPQ5332 APSS PLL is of type Stromer Plus. Add support for the same. To configure the stromer plus PLL separate API (clock_stromer_pll_configure) to be used. To achieve this, introduce the new member pll_type in device data structure and call the appropriate function based on this. Reviewed-by: Konrad Dybcio Signed-off-by: Kathiravan T Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230217083308.12017-4-quic_kathirav@quicinc.com --- drivers/clk/qcom/apss-ipq-pll.c | 58 ++++++++++++++++++++++++++++++++- 1 file changed, 57 insertions(+), 1 deletion(-) diff --git a/drivers/clk/qcom/apss-ipq-pll.c b/drivers/clk/qcom/apss-ipq-pll.c index 4f2a147e9fb2..cf4f0d340cbf 100644 --- a/drivers/clk/qcom/apss-ipq-pll.c +++ b/drivers/clk/qcom/apss-ipq-pll.c @@ -24,6 +24,17 @@ static const u8 ipq_pll_offsets[][PLL_OFF_MAX_REGS] = { [PLL_OFF_TEST_CTL] = 0x30, [PLL_OFF_TEST_CTL_U] = 0x34, }, + [CLK_ALPHA_PLL_TYPE_STROMER_PLUS] = { + [PLL_OFF_L_VAL] = 0x08, + [PLL_OFF_ALPHA_VAL] = 0x10, + [PLL_OFF_ALPHA_VAL_U] = 0x14, + [PLL_OFF_USER_CTL] = 0x18, + [PLL_OFF_USER_CTL_U] = 0x1c, + [PLL_OFF_CONFIG_CTL] = 0x20, + [PLL_OFF_STATUS] = 0x28, + [PLL_OFF_TEST_CTL] = 0x30, + [PLL_OFF_TEST_CTL_U] = 0x34, + }, }; static struct clk_alpha_pll ipq_pll_huayra = { @@ -44,6 +55,38 @@ static struct clk_alpha_pll ipq_pll_huayra = { }, }; +static struct clk_alpha_pll ipq_pll_stromer_plus = { + .offset = 0x0, + .regs = ipq_pll_offsets[CLK_ALPHA_PLL_TYPE_STROMER_PLUS], + .flags = SUPPORTS_DYNAMIC_UPDATE, + .clkr = { + .enable_reg = 0x0, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "a53pll", + .parent_data = &(const struct clk_parent_data) { + .fw_name = "xo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_stromer_ops, + }, + }, +}; + +static const struct alpha_pll_config ipq5332_pll_config = { + .l = 0x3e, + .config_ctl_val = 0x4001075b, + .config_ctl_hi_val = 0x304, + .main_output_mask = BIT(0), + .aux_output_mask = BIT(1), + .early_output_mask = BIT(3), + .alpha_en_mask = BIT(24), + .status_val = 0x3, + .status_mask = GENMASK(10, 8), + .lock_det = BIT(2), + .test_ctl_hi_val = 0x00400003, +}; + static const struct alpha_pll_config ipq6018_pll_config = { .l = 0x37, .config_ctl_val = 0x240d4828, @@ -69,16 +112,25 @@ static const struct alpha_pll_config ipq8074_pll_config = { }; struct apss_pll_data { + int pll_type; struct clk_alpha_pll *pll; const struct alpha_pll_config *pll_config; }; +static struct apss_pll_data ipq5332_pll_data = { + .pll_type = CLK_ALPHA_PLL_TYPE_STROMER_PLUS, + .pll = &ipq_pll_stromer_plus, + .pll_config = &ipq5332_pll_config, +}; + static struct apss_pll_data ipq8074_pll_data = { + .pll_type = CLK_ALPHA_PLL_TYPE_HUAYRA, .pll = &ipq_pll_huayra, .pll_config = &ipq8074_pll_config, }; static struct apss_pll_data ipq6018_pll_data = { + .pll_type = CLK_ALPHA_PLL_TYPE_HUAYRA, .pll = &ipq_pll_huayra, .pll_config = &ipq6018_pll_config, }; @@ -111,7 +163,10 @@ static int apss_ipq_pll_probe(struct platform_device *pdev) if (!data) return -ENODEV; - clk_alpha_pll_configure(data->pll, regmap, data->pll_config); + if (data->pll_type == CLK_ALPHA_PLL_TYPE_HUAYRA) + clk_alpha_pll_configure(data->pll, regmap, data->pll_config); + else if (data->pll_type == CLK_ALPHA_PLL_TYPE_STROMER_PLUS) + clk_stromer_pll_configure(data->pll, regmap, data->pll_config); ret = devm_clk_register_regmap(dev, &data->pll->clkr); if (ret) @@ -122,6 +177,7 @@ static int apss_ipq_pll_probe(struct platform_device *pdev) } static const struct of_device_id apss_ipq_pll_match_table[] = { + { .compatible = "qcom,ipq5332-a53pll", .data = &ipq5332_pll_data }, { .compatible = "qcom,ipq6018-a53pll", .data = &ipq6018_pll_data }, { .compatible = "qcom,ipq8074-a53pll", .data = &ipq8074_pll_data }, { } -- GitLab From d4856dccdac9cd742a7c8c6dd0ff9de165b62fa2 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Fri, 9 Dec 2022 14:54:06 +0100 Subject: [PATCH 1144/5631] dt-bindings: leds: spmi-flash-led: Add pm6150l compatible Add the compatible for the flash-led block found on pm6150l PMIC. Signed-off-by: Luca Weiss Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20221209-fp4-pm6150l-flash-v1-1-531521eb2a72@fairphone.com --- Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml index 1b273aecaaec..ffacf703d9f9 100644 --- a/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml +++ b/Documentation/devicetree/bindings/leds/qcom,spmi-flash-led.yaml @@ -22,6 +22,7 @@ properties: compatible: items: - enum: + - qcom,pm6150l-flash-led - qcom,pm8150c-flash-led - qcom,pm8150l-flash-led - qcom,pm8350c-flash-led -- GitLab From 5c38376ef5b46d3091cc9485b95dd70db20f0089 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Fri, 10 Mar 2023 14:55:55 +0800 Subject: [PATCH 1145/5631] leds: rgb: mt6370: Add MediaTek MT6370 current sink type LED Indicator support The MediaTek MT6370 is a highly-integrated smart power management IC, which includes a single cell Li-Ion/Li-Polymer switching battery charger, a USB Type-C & Power Delivery (PD) controller, dual Flash LED current sources, a RGB LED driver, a backlight WLED driver, a display bias driver and a general LDO for portable devices. Add support for the MediaTek MT6370 Current Sink Type LED Indicator driver. It can control four channels current-sink RGB LEDs with 3 modes: constant current, PWM, and breath mode. Co-developed-by: Alice Chen Signed-off-by: Alice Chen Signed-off-by: ChiYuan Huang Signed-off-by: ChiaEn Wu Acked-by: Jacek Anaszewski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1df93a583c3f508a7158b83b95857e9bce235e1b.1678430444.git.chiaen_wu@richtek.com --- drivers/leds/rgb/Kconfig | 13 + drivers/leds/rgb/Makefile | 1 + drivers/leds/rgb/leds-mt6370-rgb.c | 1010 ++++++++++++++++++++++++++++ 3 files changed, 1024 insertions(+) create mode 100644 drivers/leds/rgb/leds-mt6370-rgb.c diff --git a/drivers/leds/rgb/Kconfig b/drivers/leds/rgb/Kconfig index 204cf470beae..7d86bb26c54b 100644 --- a/drivers/leds/rgb/Kconfig +++ b/drivers/leds/rgb/Kconfig @@ -26,4 +26,17 @@ config LEDS_QCOM_LPG If compiled as a module, the module will be named leds-qcom-lpg. +config LEDS_MT6370_RGB + tristate "LED Support for MediaTek MT6370 PMIC" + depends on MFD_MT6370 + select LINEAR_RANGE + help + Say Y here to enable support for MT6370_RGB LED device. + In MT6370, there are four channel current-sink LED drivers that + support hardware pattern for constant current, PWM, and breath mode. + Isink4 channel can also be used as a CHG_VIN power good indicator. + + This driver can also be built as a module. If so, the module + will be called "leds-mt6370-rgb". + endif # LEDS_CLASS_MULTICOLOR diff --git a/drivers/leds/rgb/Makefile b/drivers/leds/rgb/Makefile index 0675bc0f6e18..8c01daf63f61 100644 --- a/drivers/leds/rgb/Makefile +++ b/drivers/leds/rgb/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_LEDS_PWM_MULTICOLOR) += leds-pwm-multicolor.o obj-$(CONFIG_LEDS_QCOM_LPG) += leds-qcom-lpg.o +obj-$(CONFIG_LEDS_MT6370_RGB) += leds-mt6370-rgb.o diff --git a/drivers/leds/rgb/leds-mt6370-rgb.c b/drivers/leds/rgb/leds-mt6370-rgb.c new file mode 100644 index 000000000000..9c1e6d566f11 --- /dev/null +++ b/drivers/leds/rgb/leds-mt6370-rgb.c @@ -0,0 +1,1010 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Richtek Technology Corp. + * + * Authors: + * ChiYuan Huang + * Alice Chen + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +enum { + MT6370_LED_ISNK1 = 0, + MT6370_LED_ISNK2, + MT6370_LED_ISNK3, + MT6370_LED_ISNK4, + MT6370_MAX_LEDS +}; + +enum mt6370_led_mode { + MT6370_LED_PWM_MODE = 0, + MT6370_LED_BREATH_MODE, + MT6370_LED_REG_MODE, + MT6370_LED_MAX_MODE +}; + +enum mt6370_led_field { + F_RGB_EN = 0, + F_CHGIND_EN, + F_LED1_CURR, + F_LED2_CURR, + F_LED3_CURR, + F_LED4_CURR, + F_LED1_MODE, + F_LED2_MODE, + F_LED3_MODE, + F_LED4_MODE, + F_LED1_DUTY, + F_LED2_DUTY, + F_LED3_DUTY, + F_LED4_DUTY, + F_LED1_FREQ, + F_LED2_FREQ, + F_LED3_FREQ, + F_LED4_FREQ, + F_MAX_FIELDS +}; + +enum mt6370_led_ranges { + R_LED123_CURR = 0, + R_LED4_CURR, + R_LED_TRFON, + R_LED_TOFF, + R_MAX_RANGES +}; + +enum mt6370_pattern { + P_LED_TR1 = 0, + P_LED_TR2, + P_LED_TF1, + P_LED_TF2, + P_LED_TON, + P_LED_TOFF, + P_MAX_PATTERNS +}; + +#define MT6370_REG_DEV_INFO 0x100 +#define MT6370_REG_RGB1_DIM 0x182 +#define MT6370_REG_RGB2_DIM 0x183 +#define MT6370_REG_RGB3_DIM 0x184 +#define MT6370_REG_RGB_EN 0x185 +#define MT6370_REG_RGB1_ISNK 0x186 +#define MT6370_REG_RGB2_ISNK 0x187 +#define MT6370_REG_RGB3_ISNK 0x188 +#define MT6370_REG_RGB1_TR 0x189 +#define MT6370_REG_RGB_CHRIND_DIM 0x192 +#define MT6370_REG_RGB_CHRIND_CTRL 0x193 +#define MT6370_REG_RGB_CHRIND_TR 0x194 + +#define MT6372_REG_RGB_EN 0x182 +#define MT6372_REG_RGB1_ISNK 0x183 +#define MT6372_REG_RGB2_ISNK 0x184 +#define MT6372_REG_RGB3_ISNK 0x185 +#define MT6372_REG_RGB4_ISNK 0x186 +#define MT6372_REG_RGB1_DIM 0x187 +#define MT6372_REG_RGB2_DIM 0x188 +#define MT6372_REG_RGB3_DIM 0x189 +#define MT6372_REG_RGB4_DIM 0x18A +#define MT6372_REG_RGB12_FREQ 0x18B +#define MT6372_REG_RGB34_FREQ 0x18C +#define MT6372_REG_RGB1_TR 0x18D + +#define MT6370_VENDOR_ID_MASK GENMASK(7, 4) +#define MT6372_VENDOR_ID 0x9 +#define MT6372C_VENDOR_ID 0xb +#define MT6370_CHEN_BIT(id) BIT(MT6370_LED_ISNK4 - id) +#define MT6370_VIRTUAL_MULTICOLOR 5 +#define MC_CHANNEL_NUM 3 +#define MT6370_PWM_DUTY (BIT(5) - 1) +#define MT6372_PWM_DUTY (BIT(8) - 1) + +struct mt6370_led { + /* + * If the color of the LED in DT is set to + * - 'LED_COLOR_ID_RGB' + * - 'LED_COLOR_ID_MULTI' + * The member 'index' of this struct will be set to + * 'MT6370_VIRTUAL_MULTICOLOR'. + * If so, this LED will choose 'struct led_classdev_mc mc' to use. + * Instead, if the member 'index' of this struct is set to + * 'MT6370_LED_ISNK1' ~ 'MT6370_LED_ISNK4', then this LED will choose + * 'struct led_classdev isink' to use. + */ + union { + struct led_classdev isink; + struct led_classdev_mc mc; + }; + struct mt6370_priv *priv; + enum led_default_state default_state; + u32 index; +}; + +struct mt6370_pdata { + const unsigned int *tfreq; + unsigned int tfreq_len; + u16 reg_rgb1_tr; + s16 reg_rgb_chrind_tr; + u8 pwm_duty; +}; + +struct mt6370_priv { + /* Per LED access lock */ + struct mutex lock; + struct regmap *regmap; + struct regmap_field *fields[F_MAX_FIELDS]; + const struct reg_field *reg_fields; + const struct linear_range *ranges; + struct reg_cfg *reg_cfgs; + const struct mt6370_pdata *pdata; + unsigned int leds_count; + unsigned int leds_active; + struct mt6370_led leds[]; +}; + +static const struct reg_field common_reg_fields[F_MAX_FIELDS] = { + [F_RGB_EN] = REG_FIELD(MT6370_REG_RGB_EN, 4, 7), + [F_CHGIND_EN] = REG_FIELD(MT6370_REG_RGB_CHRIND_DIM, 7, 7), + [F_LED1_CURR] = REG_FIELD(MT6370_REG_RGB1_ISNK, 0, 2), + [F_LED2_CURR] = REG_FIELD(MT6370_REG_RGB2_ISNK, 0, 2), + [F_LED3_CURR] = REG_FIELD(MT6370_REG_RGB3_ISNK, 0, 2), + [F_LED4_CURR] = REG_FIELD(MT6370_REG_RGB_CHRIND_CTRL, 0, 1), + [F_LED1_MODE] = REG_FIELD(MT6370_REG_RGB1_DIM, 5, 6), + [F_LED2_MODE] = REG_FIELD(MT6370_REG_RGB2_DIM, 5, 6), + [F_LED3_MODE] = REG_FIELD(MT6370_REG_RGB3_DIM, 5, 6), + [F_LED4_MODE] = REG_FIELD(MT6370_REG_RGB_CHRIND_DIM, 5, 6), + [F_LED1_DUTY] = REG_FIELD(MT6370_REG_RGB1_DIM, 0, 4), + [F_LED2_DUTY] = REG_FIELD(MT6370_REG_RGB2_DIM, 0, 4), + [F_LED3_DUTY] = REG_FIELD(MT6370_REG_RGB3_DIM, 0, 4), + [F_LED4_DUTY] = REG_FIELD(MT6370_REG_RGB_CHRIND_DIM, 0, 4), + [F_LED1_FREQ] = REG_FIELD(MT6370_REG_RGB1_ISNK, 3, 5), + [F_LED2_FREQ] = REG_FIELD(MT6370_REG_RGB2_ISNK, 3, 5), + [F_LED3_FREQ] = REG_FIELD(MT6370_REG_RGB3_ISNK, 3, 5), + [F_LED4_FREQ] = REG_FIELD(MT6370_REG_RGB_CHRIND_CTRL, 2, 4), +}; + +static const struct reg_field mt6372_reg_fields[F_MAX_FIELDS] = { + [F_RGB_EN] = REG_FIELD(MT6372_REG_RGB_EN, 4, 7), + [F_CHGIND_EN] = REG_FIELD(MT6372_REG_RGB_EN, 3, 3), + [F_LED1_CURR] = REG_FIELD(MT6372_REG_RGB1_ISNK, 0, 3), + [F_LED2_CURR] = REG_FIELD(MT6372_REG_RGB2_ISNK, 0, 3), + [F_LED3_CURR] = REG_FIELD(MT6372_REG_RGB3_ISNK, 0, 3), + [F_LED4_CURR] = REG_FIELD(MT6372_REG_RGB4_ISNK, 0, 3), + [F_LED1_MODE] = REG_FIELD(MT6372_REG_RGB1_ISNK, 6, 7), + [F_LED2_MODE] = REG_FIELD(MT6372_REG_RGB2_ISNK, 6, 7), + [F_LED3_MODE] = REG_FIELD(MT6372_REG_RGB3_ISNK, 6, 7), + [F_LED4_MODE] = REG_FIELD(MT6372_REG_RGB4_ISNK, 6, 7), + [F_LED1_DUTY] = REG_FIELD(MT6372_REG_RGB1_DIM, 0, 7), + [F_LED2_DUTY] = REG_FIELD(MT6372_REG_RGB2_DIM, 0, 7), + [F_LED3_DUTY] = REG_FIELD(MT6372_REG_RGB3_DIM, 0, 7), + [F_LED4_DUTY] = REG_FIELD(MT6372_REG_RGB4_DIM, 0, 7), + [F_LED1_FREQ] = REG_FIELD(MT6372_REG_RGB12_FREQ, 5, 7), + [F_LED2_FREQ] = REG_FIELD(MT6372_REG_RGB12_FREQ, 2, 4), + [F_LED3_FREQ] = REG_FIELD(MT6372_REG_RGB34_FREQ, 5, 7), + [F_LED4_FREQ] = REG_FIELD(MT6372_REG_RGB34_FREQ, 2, 4), +}; + +/* Current unit: microamp, time unit: millisecond */ +static const struct linear_range common_led_ranges[R_MAX_RANGES] = { + [R_LED123_CURR] = { 4000, 1, 6, 4000 }, + [R_LED4_CURR] = { 2000, 1, 3, 2000 }, + [R_LED_TRFON] = { 125, 0, 15, 200 }, + [R_LED_TOFF] = { 250, 0, 15, 400 }, +}; + +static const struct linear_range mt6372_led_ranges[R_MAX_RANGES] = { + [R_LED123_CURR] = { 2000, 1, 14, 2000 }, + [R_LED4_CURR] = { 2000, 1, 14, 2000 }, + [R_LED_TRFON] = { 125, 0, 15, 250 }, + [R_LED_TOFF] = { 250, 0, 15, 500 }, +}; + +static const unsigned int common_tfreqs[] = { + 10000, 5000, 2000, 1000, 500, 200, 5, 1, +}; + +static const unsigned int mt6372_tfreqs[] = { + 8000, 4000, 2000, 1000, 500, 250, 8, 4, +}; + +static const struct mt6370_pdata common_pdata = { + .tfreq = common_tfreqs, + .tfreq_len = ARRAY_SIZE(common_tfreqs), + .pwm_duty = MT6370_PWM_DUTY, + .reg_rgb1_tr = MT6370_REG_RGB1_TR, + .reg_rgb_chrind_tr = MT6370_REG_RGB_CHRIND_TR, +}; + +static const struct mt6370_pdata mt6372_pdata = { + .tfreq = mt6372_tfreqs, + .tfreq_len = ARRAY_SIZE(mt6372_tfreqs), + .pwm_duty = MT6372_PWM_DUTY, + .reg_rgb1_tr = MT6372_REG_RGB1_TR, + .reg_rgb_chrind_tr = -1, +}; + +static enum mt6370_led_field mt6370_get_led_current_field(unsigned int led_no) +{ + switch (led_no) { + case MT6370_LED_ISNK1: + return F_LED1_CURR; + case MT6370_LED_ISNK2: + return F_LED2_CURR; + case MT6370_LED_ISNK3: + return F_LED3_CURR; + default: + return F_LED4_CURR; + } +} + +static int mt6370_set_led_brightness(struct mt6370_priv *priv, unsigned int led_no, + unsigned int level) +{ + enum mt6370_led_field sel_field; + + sel_field = mt6370_get_led_current_field(led_no); + + return regmap_field_write(priv->fields[sel_field], level); +} + +static int mt6370_get_led_brightness(struct mt6370_priv *priv, unsigned int led_no, + unsigned int *level) +{ + enum mt6370_led_field sel_field; + + sel_field = mt6370_get_led_current_field(led_no); + + return regmap_field_read(priv->fields[sel_field], level); +} + +static int mt6370_set_led_duty(struct mt6370_priv *priv, unsigned int led_no, unsigned int ton, + unsigned int toff) +{ + const struct mt6370_pdata *pdata = priv->pdata; + enum mt6370_led_field sel_field; + unsigned int divisor, ratio; + + divisor = pdata->pwm_duty; + ratio = ton * divisor / (ton + toff); + + switch (led_no) { + case MT6370_LED_ISNK1: + sel_field = F_LED1_DUTY; + break; + case MT6370_LED_ISNK2: + sel_field = F_LED2_DUTY; + break; + case MT6370_LED_ISNK3: + sel_field = F_LED3_DUTY; + break; + default: + sel_field = F_LED4_DUTY; + break; + } + + return regmap_field_write(priv->fields[sel_field], ratio); +} + +static int mt6370_set_led_freq(struct mt6370_priv *priv, unsigned int led_no, unsigned int ton, + unsigned int toff) +{ + const struct mt6370_pdata *pdata = priv->pdata; + enum mt6370_led_field sel_field; + unsigned int tfreq_len = pdata->tfreq_len; + unsigned int tsum, sel; + + tsum = ton + toff; + + if (tsum > pdata->tfreq[0] || tsum < pdata->tfreq[tfreq_len - 1]) + return -EOPNOTSUPP; + + sel = find_closest_descending(tsum, pdata->tfreq, tfreq_len); + + switch (led_no) { + case MT6370_LED_ISNK1: + sel_field = F_LED1_FREQ; + break; + case MT6370_LED_ISNK2: + sel_field = F_LED2_FREQ; + break; + case MT6370_LED_ISNK3: + sel_field = F_LED3_FREQ; + break; + default: + sel_field = F_LED4_FREQ; + break; + } + + return regmap_field_write(priv->fields[sel_field], sel); +} + +static void mt6370_get_breath_reg_base(struct mt6370_priv *priv, unsigned int led_no, + unsigned int *base) +{ + const struct mt6370_pdata *pdata = priv->pdata; + + if (pdata->reg_rgb_chrind_tr < 0) { + *base = pdata->reg_rgb1_tr + led_no * 3; + return; + } + + switch (led_no) { + case MT6370_LED_ISNK1: + case MT6370_LED_ISNK2: + case MT6370_LED_ISNK3: + *base = pdata->reg_rgb1_tr + led_no * 3; + break; + default: + *base = pdata->reg_rgb_chrind_tr; + break; + } +} + +static int mt6370_gen_breath_pattern(struct mt6370_priv *priv, struct led_pattern *pattern, u32 len, + u8 *pattern_val, u32 val_len) +{ + enum mt6370_led_ranges sel_range; + struct led_pattern *curr; + unsigned int sel; + u32 val = 0; + int i; + + if (len < P_MAX_PATTERNS && val_len < P_MAX_PATTERNS / 2) + return -EINVAL; + + /* + * Pattern list + * tr1: byte 0, b'[7:4] + * tr2: byte 0, b'[3:0] + * tf1: byte 1, b'[7:4] + * tf2: byte 1, b'[3:0] + * ton: byte 2, b'[7:4] + * toff: byte 2, b'[3:0] + */ + for (i = 0; i < P_MAX_PATTERNS; i++) { + curr = pattern + i; + + sel_range = i == P_LED_TOFF ? R_LED_TOFF : R_LED_TRFON; + + linear_range_get_selector_within(priv->ranges + sel_range, curr->delta_t, &sel); + + if (i % 2) { + val |= sel; + } else { + val <<= 8; + val |= sel << 4; + } + } + + put_unaligned_be24(val, pattern_val); + + return 0; +} + +static int mt6370_set_led_mode(struct mt6370_priv *priv, unsigned int led_no, + enum mt6370_led_mode mode) +{ + enum mt6370_led_field sel_field; + + switch (led_no) { + case MT6370_LED_ISNK1: + sel_field = F_LED1_MODE; + break; + case MT6370_LED_ISNK2: + sel_field = F_LED2_MODE; + break; + case MT6370_LED_ISNK3: + sel_field = F_LED3_MODE; + break; + default: + sel_field = F_LED4_MODE; + break; + } + + return regmap_field_write(priv->fields[sel_field], mode); +} + +static int mt6370_mc_brightness_set(struct led_classdev *lcdev, enum led_brightness level) +{ + struct led_classdev_mc *mccdev = lcdev_to_mccdev(lcdev); + struct mt6370_led *led = container_of(mccdev, struct mt6370_led, mc); + struct mt6370_priv *priv = led->priv; + struct mc_subled *subled; + unsigned int enable, disable; + int i, ret; + + mutex_lock(&priv->lock); + + led_mc_calc_color_components(mccdev, level); + + ret = regmap_field_read(priv->fields[F_RGB_EN], &enable); + if (ret) + goto out_unlock; + + disable = enable; + + for (i = 0; i < mccdev->num_colors; i++) { + u32 brightness; + + subled = mccdev->subled_info + i; + brightness = min(subled->brightness, lcdev->max_brightness); + disable &= ~MT6370_CHEN_BIT(subled->channel); + + if (level == 0) { + enable &= ~MT6370_CHEN_BIT(subled->channel); + + ret = mt6370_set_led_mode(priv, subled->channel, MT6370_LED_REG_MODE); + if (ret) + goto out_unlock; + + continue; + } + + if (brightness == 0) { + enable &= ~MT6370_CHEN_BIT(subled->channel); + continue; + } + + enable |= MT6370_CHEN_BIT(subled->channel); + + ret = mt6370_set_led_brightness(priv, subled->channel, brightness); + if (ret) + goto out_unlock; + } + + ret = regmap_field_write(priv->fields[F_RGB_EN], disable); + if (ret) + goto out_unlock; + + ret = regmap_field_write(priv->fields[F_RGB_EN], enable); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static int mt6370_mc_blink_set(struct led_classdev *lcdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct led_classdev_mc *mccdev = lcdev_to_mccdev(lcdev); + struct mt6370_led *led = container_of(mccdev, struct mt6370_led, mc); + struct mt6370_priv *priv = led->priv; + struct mc_subled *subled; + unsigned int enable, disable; + int i, ret; + + mutex_lock(&priv->lock); + + if (!*delay_on && !*delay_off) + *delay_on = *delay_off = 500; + + ret = regmap_field_read(priv->fields[F_RGB_EN], &enable); + if (ret) + goto out_unlock; + + disable = enable; + + for (i = 0; i < mccdev->num_colors; i++) { + subled = mccdev->subled_info + i; + + disable &= ~MT6370_CHEN_BIT(subled->channel); + + ret = mt6370_set_led_duty(priv, subled->channel, *delay_on, *delay_off); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_freq(priv, subled->channel, *delay_on, *delay_off); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_mode(priv, subled->channel, MT6370_LED_PWM_MODE); + if (ret) + goto out_unlock; + } + + /* Toggle to make pattern timing the same */ + ret = regmap_field_write(priv->fields[F_RGB_EN], disable); + if (ret) + goto out_unlock; + + ret = regmap_field_write(priv->fields[F_RGB_EN], enable); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static int mt6370_mc_pattern_set(struct led_classdev *lcdev, struct led_pattern *pattern, u32 len, + int repeat) +{ + struct led_classdev_mc *mccdev = lcdev_to_mccdev(lcdev); + struct mt6370_led *led = container_of(mccdev, struct mt6370_led, mc); + struct mt6370_priv *priv = led->priv; + struct mc_subled *subled; + unsigned int reg_base, enable, disable; + u8 params[P_MAX_PATTERNS / 2]; + int i, ret; + + mutex_lock(&priv->lock); + + ret = mt6370_gen_breath_pattern(priv, pattern, len, params, sizeof(params)); + if (ret) + goto out_unlock; + + ret = regmap_field_read(priv->fields[F_RGB_EN], &enable); + if (ret) + goto out_unlock; + + disable = enable; + + for (i = 0; i < mccdev->num_colors; i++) { + subled = mccdev->subled_info + i; + + mt6370_get_breath_reg_base(priv, subled->channel, ®_base); + disable &= ~MT6370_CHEN_BIT(subled->channel); + + ret = regmap_raw_write(priv->regmap, reg_base, params, sizeof(params)); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_mode(priv, subled->channel, MT6370_LED_BREATH_MODE); + if (ret) + goto out_unlock; + } + + /* Toggle to make pattern timing be the same */ + ret = regmap_field_write(priv->fields[F_RGB_EN], disable); + if (ret) + goto out_unlock; + + ret = regmap_field_write(priv->fields[F_RGB_EN], enable); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static inline int mt6370_mc_pattern_clear(struct led_classdev *lcdev) +{ + struct led_classdev_mc *mccdev = lcdev_to_mccdev(lcdev); + struct mt6370_led *led = container_of(mccdev, struct mt6370_led, mc); + struct mt6370_priv *priv = led->priv; + struct mc_subled *subled; + int i, ret; + + mutex_lock(&led->priv->lock); + + for (i = 0; i < mccdev->num_colors; i++) { + subled = mccdev->subled_info + i; + + ret = mt6370_set_led_mode(priv, subled->channel, MT6370_LED_REG_MODE); + if (ret) + break; + } + + mutex_unlock(&led->priv->lock); + + return ret; +} + +static int mt6370_isnk_brightness_set(struct led_classdev *lcdev, + enum led_brightness level) +{ + struct mt6370_led *led = container_of(lcdev, struct mt6370_led, isink); + struct mt6370_priv *priv = led->priv; + unsigned int enable; + int ret; + + mutex_lock(&priv->lock); + + ret = regmap_field_read(priv->fields[F_RGB_EN], &enable); + if (ret) + goto out_unlock; + + if (level == 0) { + enable &= ~MT6370_CHEN_BIT(led->index); + + ret = mt6370_set_led_mode(priv, led->index, MT6370_LED_REG_MODE); + if (ret) + goto out_unlock; + } else { + enable |= MT6370_CHEN_BIT(led->index); + + ret = mt6370_set_led_brightness(priv, led->index, level); + if (ret) + goto out_unlock; + } + + ret = regmap_field_write(priv->fields[F_RGB_EN], enable); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static int mt6370_isnk_blink_set(struct led_classdev *lcdev, unsigned long *delay_on, + unsigned long *delay_off) +{ + struct mt6370_led *led = container_of(lcdev, struct mt6370_led, isink); + struct mt6370_priv *priv = led->priv; + int ret; + + mutex_lock(&priv->lock); + + if (!*delay_on && !*delay_off) + *delay_on = *delay_off = 500; + + ret = mt6370_set_led_duty(priv, led->index, *delay_on, *delay_off); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_freq(priv, led->index, *delay_on, *delay_off); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_mode(priv, led->index, MT6370_LED_PWM_MODE); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static int mt6370_isnk_pattern_set(struct led_classdev *lcdev, struct led_pattern *pattern, u32 len, + int repeat) +{ + struct mt6370_led *led = container_of(lcdev, struct mt6370_led, isink); + struct mt6370_priv *priv = led->priv; + unsigned int reg_base; + u8 params[P_MAX_PATTERNS / 2]; + int ret; + + mutex_lock(&priv->lock); + + ret = mt6370_gen_breath_pattern(priv, pattern, len, params, sizeof(params)); + if (ret) + goto out_unlock; + + mt6370_get_breath_reg_base(priv, led->index, ®_base); + + ret = regmap_raw_write(priv->regmap, reg_base, params, sizeof(params)); + if (ret) + goto out_unlock; + + ret = mt6370_set_led_mode(priv, led->index, MT6370_LED_BREATH_MODE); + +out_unlock: + mutex_unlock(&priv->lock); + + return ret; +} + +static inline int mt6370_isnk_pattern_clear(struct led_classdev *lcdev) +{ + struct mt6370_led *led = container_of(lcdev, struct mt6370_led, isink); + struct mt6370_priv *priv = led->priv; + int ret; + + mutex_lock(&led->priv->lock); + ret = mt6370_set_led_mode(priv, led->index, MT6370_LED_REG_MODE); + mutex_unlock(&led->priv->lock); + + return ret; +} + +static int mt6370_assign_multicolor_info(struct device *dev, struct mt6370_led *led, + struct fwnode_handle *fwnode) +{ + struct mt6370_priv *priv = led->priv; + struct fwnode_handle *child; + struct mc_subled *sub_led; + u32 num_color = 0; + int ret; + + sub_led = devm_kcalloc(dev, MC_CHANNEL_NUM, sizeof(*sub_led), GFP_KERNEL); + if (!sub_led) + return -ENOMEM; + + fwnode_for_each_child_node(fwnode, child) { + u32 reg, color; + + ret = fwnode_property_read_u32(child, "reg", ®); + if (ret || reg > MT6370_LED_ISNK3 || priv->leds_active & BIT(reg)) { + fwnode_handle_put(child); + return -EINVAL; + } + + ret = fwnode_property_read_u32(child, "color", &color); + if (ret) { + fwnode_handle_put(child); + return dev_err_probe(dev, ret, "LED %d, no color specified\n", led->index); + } + + priv->leds_active |= BIT(reg); + sub_led[num_color].color_index = color; + sub_led[num_color].channel = reg; + sub_led[num_color].intensity = 0; + num_color++; + } + + if (num_color < 2) + return dev_err_probe(dev, -EINVAL, + "Multicolor must include 2 or more LED channels\n"); + + led->mc.num_colors = num_color; + led->mc.subled_info = sub_led; + + return 0; +} + +static int mt6370_init_led_properties(struct device *dev, struct mt6370_led *led, + struct led_init_data *init_data) +{ + struct mt6370_priv *priv = led->priv; + struct led_classdev *lcdev; + enum mt6370_led_ranges sel_range; + u32 max_uA, max_level; + int ret; + + if (led->index == MT6370_VIRTUAL_MULTICOLOR) { + ret = mt6370_assign_multicolor_info(dev, led, init_data->fwnode); + if (ret) + return ret; + + lcdev = &led->mc.led_cdev; + lcdev->brightness_set_blocking = mt6370_mc_brightness_set; + lcdev->blink_set = mt6370_mc_blink_set; + lcdev->pattern_set = mt6370_mc_pattern_set; + lcdev->pattern_clear = mt6370_mc_pattern_clear; + } else { + lcdev = &led->isink; + lcdev->brightness_set_blocking = mt6370_isnk_brightness_set; + lcdev->blink_set = mt6370_isnk_blink_set; + lcdev->pattern_set = mt6370_isnk_pattern_set; + lcdev->pattern_clear = mt6370_isnk_pattern_clear; + } + + ret = fwnode_property_read_u32(init_data->fwnode, "led-max-microamp", &max_uA); + if (ret) { + dev_warn(dev, "Not specified led-max-microamp, config to the minimum\n"); + max_uA = 0; + } + + if (led->index == MT6370_LED_ISNK4) + sel_range = R_LED4_CURR; + else + sel_range = R_LED123_CURR; + + linear_range_get_selector_within(priv->ranges + sel_range, max_uA, &max_level); + + lcdev->max_brightness = max_level; + + led->default_state = led_init_default_state_get(init_data->fwnode); + + return 0; +} + +static int mt6370_isnk_init_default_state(struct mt6370_led *led) +{ + struct mt6370_priv *priv = led->priv; + unsigned int enable, level; + int ret; + + ret = mt6370_get_led_brightness(priv, led->index, &level); + if (ret) + return ret; + + ret = regmap_field_read(priv->fields[F_RGB_EN], &enable); + if (ret) + return ret; + + if (!(enable & MT6370_CHEN_BIT(led->index))) + level = 0; + + switch (led->default_state) { + case LEDS_DEFSTATE_ON: + led->isink.brightness = led->isink.max_brightness; + break; + case LEDS_DEFSTATE_KEEP: + led->isink.brightness = min(level, led->isink.max_brightness); + break; + default: + led->isink.brightness = 0; + break; + } + + return mt6370_isnk_brightness_set(&led->isink, led->isink.brightness); +} + +static int mt6370_multicolor_led_register(struct device *dev, struct mt6370_led *led, + struct led_init_data *init_data) +{ + int ret; + + ret = mt6370_mc_brightness_set(&led->mc.led_cdev, 0); + if (ret) + return dev_err_probe(dev, ret, "Couldn't set multicolor brightness\n"); + + ret = devm_led_classdev_multicolor_register_ext(dev, &led->mc, init_data); + if (ret) + return dev_err_probe(dev, ret, "Couldn't register multicolor\n"); + + return 0; +} + +static int mt6370_led_register(struct device *dev, struct mt6370_led *led, + struct led_init_data *init_data) +{ + struct mt6370_priv *priv = led->priv; + int ret; + + if (led->index == MT6370_VIRTUAL_MULTICOLOR) + return mt6370_multicolor_led_register(dev, led, init_data); + + /* If ISNK4 is declared, change its mode from HW auto to SW control */ + if (led->index == MT6370_LED_ISNK4) { + ret = regmap_field_write(priv->fields[F_CHGIND_EN], 1); + if (ret) + return dev_err_probe(dev, ret, "Failed to set CHRIND to SW\n"); + } + + ret = mt6370_isnk_init_default_state(led); + if (ret) + return dev_err_probe(dev, ret, "Failed to init %d isnk state\n", led->index); + + ret = devm_led_classdev_register_ext(dev, &led->isink, init_data); + if (ret) + return dev_err_probe(dev, ret, "Couldn't register isink %d\n", led->index); + + return 0; +} + +static int mt6370_check_vendor_info(struct mt6370_priv *priv) +{ + unsigned int devinfo, vid; + int ret; + + ret = regmap_read(priv->regmap, MT6370_REG_DEV_INFO, &devinfo); + if (ret) + return ret; + + vid = FIELD_GET(MT6370_VENDOR_ID_MASK, devinfo); + if (vid == MT6372_VENDOR_ID || vid == MT6372C_VENDOR_ID) { + priv->reg_fields = mt6372_reg_fields; + priv->ranges = mt6372_led_ranges; + priv->pdata = &mt6372_pdata; + } else { + /* Common for MT6370/71 */ + priv->reg_fields = common_reg_fields; + priv->ranges = common_led_ranges; + priv->pdata = &common_pdata; + } + + return 0; +} + +static int mt6370_leds_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mt6370_priv *priv; + struct fwnode_handle *child; + size_t count; + unsigned int i = 0; + int ret; + + count = device_get_child_node_count(dev); + if (!count || count > MT6370_MAX_LEDS) + return dev_err_probe(dev, -EINVAL, + "No child node or node count over max LED number %zu\n", + count); + + priv = devm_kzalloc(dev, struct_size(priv, leds, count), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->leds_count = count; + mutex_init(&priv->lock); + + priv->regmap = dev_get_regmap(dev->parent, NULL); + if (!priv->regmap) + return dev_err_probe(dev, -ENODEV, "Failed to get parent regmap\n"); + + ret = mt6370_check_vendor_info(priv); + if (ret) + return dev_err_probe(dev, ret, "Failed to check vendor info\n"); + + ret = devm_regmap_field_bulk_alloc(dev, priv->regmap, priv->fields, priv->reg_fields, + F_MAX_FIELDS); + if (ret) + return dev_err_probe(dev, ret, "Failed to allocate regmap field\n"); + + device_for_each_child_node(dev, child) { + struct mt6370_led *led = priv->leds + i++; + struct led_init_data init_data = { .fwnode = child }; + u32 reg, color; + + ret = fwnode_property_read_u32(child, "reg", ®); + if (ret) { + dev_err(dev, "Failed to parse reg property\n"); + goto fwnode_release; + } + + if (reg >= MT6370_MAX_LEDS) { + ret = -EINVAL; + dev_err(dev, "Error reg property number\n"); + goto fwnode_release; + } + + ret = fwnode_property_read_u32(child, "color", &color); + if (ret) { + dev_err(dev, "Failed to parse color property\n"); + goto fwnode_release; + } + + if (color == LED_COLOR_ID_RGB || color == LED_COLOR_ID_MULTI) + reg = MT6370_VIRTUAL_MULTICOLOR; + + if (priv->leds_active & BIT(reg)) { + ret = -EINVAL; + dev_err(dev, "Duplicate reg property\n"); + goto fwnode_release; + } + + priv->leds_active |= BIT(reg); + + led->index = reg; + led->priv = priv; + + ret = mt6370_init_led_properties(dev, led, &init_data); + if (ret) + goto fwnode_release; + + ret = mt6370_led_register(dev, led, &init_data); + if (ret) + goto fwnode_release; + } + + return 0; + +fwnode_release: + fwnode_handle_put(child); + return ret; +} + +static const struct of_device_id mt6370_rgbled_device_table[] = { + { .compatible = "mediatek,mt6370-indicator" }, + {} +}; +MODULE_DEVICE_TABLE(of, mt6370_rgbled_device_table); + +static struct platform_driver mt6370_rgbled_driver = { + .driver = { + .name = "mt6370-indicator", + .of_match_table = mt6370_rgbled_device_table, + }, + .probe = mt6370_leds_probe, +}; +module_platform_driver(mt6370_rgbled_driver); + +MODULE_AUTHOR("Alice Chen "); +MODULE_AUTHOR("ChiYuan Huang "); +MODULE_DESCRIPTION("MediaTek MT6370 RGB LED Driver"); +MODULE_LICENSE("GPL"); -- GitLab From fa31e4221c65b205e18c82c459c3bcd68404a1c6 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Fri, 10 Mar 2023 14:55:56 +0800 Subject: [PATCH 1146/5631] leds: flash: mt6370: Add MediaTek MT6370 flashlight support The MediaTek MT6370 is a highly-integrated smart power management IC, which includes a single cell Li-Ion/Li-Polymer switching battery charger, a USB Type-C & Power Delivery (PD) controller, dual Flash LED current sources, a RGB LED driver, a backlight WLED driver, a display bias driver and a general LDO for portable devices. Add support for the MT6370 Flash LED driver. Flash LED in MT6370 has 2 channels and support torch/strobe mode. Co-developed-by: Alice Chen Signed-off-by: Alice Chen Signed-off-by: ChiYuan Huang Signed-off-by: ChiaEn Wu Acked-by: Jacek Anaszewski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/52480420a160e5a4c71715fbbf105e684a16e7c2.1678430444.git.chiaen_wu@richtek.com --- drivers/leds/flash/Kconfig | 13 + drivers/leds/flash/Makefile | 1 + drivers/leds/flash/leds-mt6370-flash.c | 573 +++++++++++++++++++++++++ 3 files changed, 587 insertions(+) create mode 100644 drivers/leds/flash/leds-mt6370-flash.c diff --git a/drivers/leds/flash/Kconfig b/drivers/leds/flash/Kconfig index f36a60409290..4ed2efc65434 100644 --- a/drivers/leds/flash/Kconfig +++ b/drivers/leds/flash/Kconfig @@ -61,6 +61,19 @@ config LEDS_MT6360 Independent current sources supply for each flash LED support torch and strobe mode. +config LEDS_MT6370_FLASH + tristate "Flash LED Support for MediaTek MT6370 PMIC" + depends on LEDS_CLASS + depends on V4L2_FLASH_LED_CLASS || !V4L2_FLASH_LED_CLASS + depends on MFD_MT6370 + help + Support 2 channels and torch/strobe mode. + Say Y here to enable support for + MT6370_FLASH_LED device. + + This driver can also be built as a module. If so, the module + will be called "leds-mt6370-flash". + config LEDS_QCOM_FLASH tristate "LED support for flash module inside Qualcomm Technologies, Inc. PMIC" depends on MFD_SPMI_PMIC || COMPILE_TEST diff --git a/drivers/leds/flash/Makefile b/drivers/leds/flash/Makefile index 8a60993f1a25..91d60a4b7952 100644 --- a/drivers/leds/flash/Makefile +++ b/drivers/leds/flash/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_LEDS_MT6360) += leds-mt6360.o +obj-$(CONFIG_LEDS_MT6370_FLASH) += leds-mt6370-flash.o obj-$(CONFIG_LEDS_AAT1290) += leds-aat1290.o obj-$(CONFIG_LEDS_AS3645A) += leds-as3645a.o obj-$(CONFIG_LEDS_KTD2692) += leds-ktd2692.o diff --git a/drivers/leds/flash/leds-mt6370-flash.c b/drivers/leds/flash/leds-mt6370-flash.c new file mode 100644 index 000000000000..931067c8a75f --- /dev/null +++ b/drivers/leds/flash/leds-mt6370-flash.c @@ -0,0 +1,573 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Richtek Technology Corp. + * + * Authors: + * Alice Chen + * ChiYuan Huang + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +enum { + MT6370_LED_FLASH1 = 0, + MT6370_LED_FLASH2, + MT6370_MAX_LEDS +}; + +/* Virtual definition for multicolor */ + +#define MT6370_REG_FLEDEN 0x17E +#define MT6370_REG_STRBTO 0x173 +#define MT6370_REG_CHGSTAT2 0x1D1 +#define MT6370_REG_FLEDSTAT1 0x1D9 +#define MT6370_REG_FLEDISTRB(_id) (0x174 + 4 * (_id)) +#define MT6370_REG_FLEDITOR(_id) (0x175 + 4 * (_id)) +#define MT6370_ITORCH_MASK GENMASK(4, 0) +#define MT6370_ISTROBE_MASK GENMASK(6, 0) +#define MT6370_STRBTO_MASK GENMASK(6, 0) +#define MT6370_TORCHEN_MASK BIT(3) +#define MT6370_STROBEN_MASK BIT(2) +#define MT6370_FLCSEN_MASK(_id) BIT(MT6370_LED_FLASH2 - (_id)) +#define MT6370_FLCSEN_MASK_ALL GENMASK(1, 0) +#define MT6370_FLEDCHGVINOVP_MASK BIT(3) +#define MT6370_FLED1STRBTO_MASK BIT(11) +#define MT6370_FLED2STRBTO_MASK BIT(10) +#define MT6370_FLED1STRB_MASK BIT(9) +#define MT6370_FLED2STRB_MASK BIT(8) +#define MT6370_FLED1SHORT_MASK BIT(7) +#define MT6370_FLED2SHORT_MASK BIT(6) +#define MT6370_FLEDLVF_MASK BIT(3) + +#define MT6370_LED_JOINT 2 +#define MT6370_RANGE_FLED_REG 4 +#define MT6370_ITORCH_MIN_uA 25000 +#define MT6370_ITORCH_STEP_uA 12500 +#define MT6370_ITORCH_MAX_uA 400000 +#define MT6370_ITORCH_DOUBLE_MAX_uA 800000 +#define MT6370_ISTRB_MIN_uA 50000 +#define MT6370_ISTRB_STEP_uA 12500 +#define MT6370_ISTRB_MAX_uA 1500000 +#define MT6370_ISTRB_DOUBLE_MAX_uA 3000000 +#define MT6370_STRBTO_MIN_US 64000 +#define MT6370_STRBTO_STEP_US 32000 +#define MT6370_STRBTO_MAX_US 2432000 + +#define to_mt6370_led(ptr, member) container_of(ptr, struct mt6370_led, member) + +struct mt6370_led { + struct led_classdev_flash flash; + struct v4l2_flash *v4l2_flash; + struct mt6370_priv *priv; + u8 led_no; +}; + +struct mt6370_priv { + struct regmap *regmap; + struct mutex lock; + unsigned int fled_strobe_used; + unsigned int fled_torch_used; + unsigned int leds_active; + unsigned int leds_count; + struct mt6370_led leds[]; +}; + +static int mt6370_torch_brightness_set(struct led_classdev *lcdev, enum led_brightness level) +{ + struct mt6370_led *led = to_mt6370_led(lcdev, flash.led_cdev); + struct mt6370_priv *priv = led->priv; + u32 led_enable_mask = led->led_no == MT6370_LED_JOINT ? MT6370_FLCSEN_MASK_ALL : + MT6370_FLCSEN_MASK(led->led_no); + u32 enable_mask = MT6370_TORCHEN_MASK | led_enable_mask; + u32 val = level ? led_enable_mask : 0; + u32 curr; + int ret, i; + + mutex_lock(&priv->lock); + + /* + * There is only one set of flash control logic, and this flag is used to check if 'strobe' + * is currently being used. + */ + if (priv->fled_strobe_used) { + dev_warn(lcdev->dev, "Please disable strobe first [%d]\n", priv->fled_strobe_used); + ret = -EBUSY; + goto unlock; + } + + if (level) + curr = priv->fled_torch_used | BIT(led->led_no); + else + curr = priv->fled_torch_used & ~BIT(led->led_no); + + if (curr) + val |= MT6370_TORCHEN_MASK; + + if (level) { + level -= 1; + if (led->led_no == MT6370_LED_JOINT) { + u32 flevel[MT6370_MAX_LEDS]; + + /* + * There're two flash channels in MT6370. If joint flash output is used, + * torch current will be averaged output from both channels. + */ + flevel[0] = level / 2; + flevel[1] = level - flevel[0]; + for (i = 0; i < MT6370_MAX_LEDS; i++) { + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDITOR(i), + MT6370_ITORCH_MASK, flevel[i]); + if (ret) + goto unlock; + } + } else { + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDITOR(led->led_no), + MT6370_ITORCH_MASK, level); + if (ret) + goto unlock; + } + } + + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDEN, enable_mask, val); + if (ret) + goto unlock; + + priv->fled_torch_used = curr; + +unlock: + mutex_unlock(&priv->lock); + return ret; +} + +static int mt6370_flash_brightness_set(struct led_classdev_flash *fl_cdev, u32 brightness) +{ + /* + * Because of the current spikes when turning on the flash, the brightness should be kept + * by the LED framework. This empty function is used to prevent checking failure when + * led_classdev_flash registers ops. + */ + return 0; +} + +static int _mt6370_flash_brightness_set(struct led_classdev_flash *fl_cdev, u32 brightness) +{ + struct mt6370_led *led = to_mt6370_led(fl_cdev, flash); + struct mt6370_priv *priv = led->priv; + struct led_flash_setting *setting = &fl_cdev->brightness; + u32 val = (brightness - setting->min) / setting->step; + int ret, i; + + if (led->led_no == MT6370_LED_JOINT) { + u32 flevel[MT6370_MAX_LEDS]; + + /* + * There're two flash channels in MT6370. If joint flash output is used, storbe + * current will be averaged output from both channels. + */ + flevel[0] = val / 2; + flevel[1] = val - flevel[0]; + for (i = 0; i < MT6370_MAX_LEDS; i++) { + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDISTRB(i), + MT6370_ISTROBE_MASK, flevel[i]); + if (ret) + break; + } + } else { + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDISTRB(led->led_no), + MT6370_ISTROBE_MASK, val); + } + + return ret; +} + +static int mt6370_strobe_set(struct led_classdev_flash *fl_cdev, bool state) +{ + struct mt6370_led *led = to_mt6370_led(fl_cdev, flash); + struct mt6370_priv *priv = led->priv; + struct led_classdev *lcdev = &fl_cdev->led_cdev; + struct led_flash_setting *s = &fl_cdev->brightness; + u32 led_enable_mask = led->led_no == MT6370_LED_JOINT ? MT6370_FLCSEN_MASK_ALL : + MT6370_FLCSEN_MASK(led->led_no); + u32 enable_mask = MT6370_STROBEN_MASK | led_enable_mask; + u32 val = state ? led_enable_mask : 0; + u32 curr; + int ret; + + mutex_lock(&priv->lock); + + /* + * There is only one set of flash control logic, and this flag is used to check if 'torch' + * is currently being used. + */ + if (priv->fled_torch_used) { + dev_warn(lcdev->dev, "Please disable torch first [0x%x]\n", priv->fled_torch_used); + ret = -EBUSY; + goto unlock; + } + + if (state) + curr = priv->fled_strobe_used | BIT(led->led_no); + else + curr = priv->fled_strobe_used & ~BIT(led->led_no); + + if (curr) + val |= MT6370_STROBEN_MASK; + + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDEN, enable_mask, val); + if (ret) { + dev_err(lcdev->dev, "[%d] control current source %d fail\n", led->led_no, state); + goto unlock; + } + + /* + * If the flash needs to turn on, configure the flash current to ramp up to the setting + * value. Otherwise, always revert to the minimum one. + */ + ret = _mt6370_flash_brightness_set(fl_cdev, state ? s->val : s->min); + if (ret) { + dev_err(lcdev->dev, "[%d] Failed to set brightness\n", led->led_no); + goto unlock; + } + + /* + * For the flash to turn on/off, we must wait for HW ramping up/down time 5ms/500us to + * prevent the unexpected problem. + */ + if (!priv->fled_strobe_used && curr) + usleep_range(5000, 6000); + else if (priv->fled_strobe_used && !curr) + usleep_range(500, 600); + + priv->fled_strobe_used = curr; + +unlock: + mutex_unlock(&priv->lock); + return ret; +} + +static int mt6370_strobe_get(struct led_classdev_flash *fl_cdev, bool *state) +{ + struct mt6370_led *led = to_mt6370_led(fl_cdev, flash); + struct mt6370_priv *priv = led->priv; + + mutex_lock(&priv->lock); + *state = !!(priv->fled_strobe_used & BIT(led->led_no)); + mutex_unlock(&priv->lock); + + return 0; +} + +static int mt6370_timeout_set(struct led_classdev_flash *fl_cdev, u32 timeout) +{ + struct mt6370_led *led = to_mt6370_led(fl_cdev, flash); + struct mt6370_priv *priv = led->priv; + struct led_flash_setting *s = &fl_cdev->timeout; + u32 val = (timeout - s->min) / s->step; + + return regmap_update_bits(priv->regmap, MT6370_REG_STRBTO, MT6370_STRBTO_MASK, val); +} + +static int mt6370_fault_get(struct led_classdev_flash *fl_cdev, u32 *fault) +{ + struct mt6370_led *led = to_mt6370_led(fl_cdev, flash); + struct mt6370_priv *priv = led->priv; + u16 fled_stat; + unsigned int chg_stat, strobe_timeout_mask, fled_short_mask; + u32 rfault = 0; + int ret; + + ret = regmap_read(priv->regmap, MT6370_REG_CHGSTAT2, &chg_stat); + if (ret) + return ret; + + ret = regmap_raw_read(priv->regmap, MT6370_REG_FLEDSTAT1, &fled_stat, sizeof(fled_stat)); + if (ret) + return ret; + + switch (led->led_no) { + case MT6370_LED_FLASH1: + strobe_timeout_mask = MT6370_FLED1STRBTO_MASK; + fled_short_mask = MT6370_FLED1SHORT_MASK; + break; + + case MT6370_LED_FLASH2: + strobe_timeout_mask = MT6370_FLED2STRBTO_MASK; + fled_short_mask = MT6370_FLED2SHORT_MASK; + break; + + case MT6370_LED_JOINT: + strobe_timeout_mask = MT6370_FLED1STRBTO_MASK | MT6370_FLED2STRBTO_MASK; + fled_short_mask = MT6370_FLED1SHORT_MASK | MT6370_FLED2SHORT_MASK; + break; + default: + return -EINVAL; + } + + if (chg_stat & MT6370_FLEDCHGVINOVP_MASK) + rfault |= LED_FAULT_INPUT_VOLTAGE; + + if (fled_stat & strobe_timeout_mask) + rfault |= LED_FAULT_TIMEOUT; + + if (fled_stat & fled_short_mask) + rfault |= LED_FAULT_SHORT_CIRCUIT; + + if (fled_stat & MT6370_FLEDLVF_MASK) + rfault |= LED_FAULT_UNDER_VOLTAGE; + + *fault = rfault; + return ret; +} + +static const struct led_flash_ops mt6370_flash_ops = { + .flash_brightness_set = mt6370_flash_brightness_set, + .strobe_set = mt6370_strobe_set, + .strobe_get = mt6370_strobe_get, + .timeout_set = mt6370_timeout_set, + .fault_get = mt6370_fault_get, +}; + +#if IS_ENABLED(CONFIG_V4L2_FLASH_LED_CLASS) +static int mt6370_flash_external_strobe_set(struct v4l2_flash *v4l2_flash, + bool enable) +{ + struct led_classdev_flash *flash = v4l2_flash->fled_cdev; + struct mt6370_led *led = to_mt6370_led(flash, flash); + struct mt6370_priv *priv = led->priv; + u32 mask = led->led_no == MT6370_LED_JOINT ? MT6370_FLCSEN_MASK_ALL : + MT6370_FLCSEN_MASK(led->led_no); + u32 val = enable ? mask : 0; + int ret; + + mutex_lock(&priv->lock); + + ret = regmap_update_bits(priv->regmap, MT6370_REG_FLEDEN, mask, val); + if (ret) + goto unlock; + + if (enable) + priv->fled_strobe_used |= BIT(led->led_no); + else + priv->fled_strobe_used &= ~BIT(led->led_no); + +unlock: + mutex_unlock(&priv->lock); + return ret; +} + +static const struct v4l2_flash_ops v4l2_flash_ops = { + .external_strobe_set = mt6370_flash_external_strobe_set, +}; + +static void mt6370_init_v4l2_flash_config(struct mt6370_led *led, struct v4l2_flash_config *cfg) +{ + struct led_classdev *lcdev; + struct led_flash_setting *s = &cfg->intensity; + + lcdev = &led->flash.led_cdev; + + s->min = MT6370_ITORCH_MIN_uA; + s->step = MT6370_ITORCH_STEP_uA; + s->val = s->max = s->min + (lcdev->max_brightness - 1) * s->step; + + cfg->has_external_strobe = 1; + strscpy(cfg->dev_name, dev_name(lcdev->dev), sizeof(cfg->dev_name)); + + cfg->flash_faults = LED_FAULT_SHORT_CIRCUIT | LED_FAULT_TIMEOUT | + LED_FAULT_INPUT_VOLTAGE | LED_FAULT_UNDER_VOLTAGE; +} +#else +static const struct v4l2_flash_ops v4l2_flash_ops; +static void mt6370_init_v4l2_flash_config(struct mt6370_led *led, struct v4l2_flash_config *cfg) +{ +} +#endif + +static void mt6370_v4l2_flash_release(void *v4l2_flash) +{ + v4l2_flash_release(v4l2_flash); +} + +static int mt6370_led_register(struct device *parent, struct mt6370_led *led, + struct fwnode_handle *fwnode) +{ + struct led_init_data init_data = { .fwnode = fwnode }; + struct v4l2_flash_config v4l2_config = {}; + int ret; + + ret = devm_led_classdev_flash_register_ext(parent, &led->flash, &init_data); + if (ret) + return dev_err_probe(parent, ret, "Couldn't register flash %d\n", led->led_no); + + mt6370_init_v4l2_flash_config(led, &v4l2_config); + led->v4l2_flash = v4l2_flash_init(parent, fwnode, &led->flash, &v4l2_flash_ops, + &v4l2_config); + if (IS_ERR(led->v4l2_flash)) + return dev_err_probe(parent, PTR_ERR(led->v4l2_flash), + "Failed to register %d v4l2 sd\n", led->led_no); + + return devm_add_action_or_reset(parent, mt6370_v4l2_flash_release, led->v4l2_flash); +} + +static u32 mt6370_clamp(u32 val, u32 min, u32 max, u32 step) +{ + u32 retval; + + retval = clamp_val(val, min, max); + if (step > 1) + retval = rounddown(retval - min, step) + min; + + return retval; +} + +static int mt6370_init_flash_properties(struct device *dev, struct mt6370_led *led, + struct fwnode_handle *fwnode) +{ + struct led_classdev_flash *flash = &led->flash; + struct led_classdev *lcdev = &flash->led_cdev; + struct mt6370_priv *priv = led->priv; + struct led_flash_setting *s; + u32 sources[MT6370_MAX_LEDS]; + u32 max_ua, val; + int i, ret, num; + + num = fwnode_property_count_u32(fwnode, "led-sources"); + if (num < 1) + return dev_err_probe(dev, -EINVAL, + "Not specified or wrong number of led-sources\n"); + + ret = fwnode_property_read_u32_array(fwnode, "led-sources", sources, num); + if (ret) + return ret; + + for (i = 0; i < num; i++) { + if (sources[i] >= MT6370_MAX_LEDS) + return -EINVAL; + if (priv->leds_active & BIT(sources[i])) + return -EINVAL; + priv->leds_active |= BIT(sources[i]); + } + + /* If both channels are specified in 'led-sources', joint flash output mode is used */ + led->led_no = num == 2 ? MT6370_LED_JOINT : sources[0]; + + max_ua = num == 2 ? MT6370_ITORCH_DOUBLE_MAX_uA : MT6370_ITORCH_MAX_uA; + val = MT6370_ITORCH_MIN_uA; + ret = fwnode_property_read_u32(fwnode, "led-max-microamp", &val); + if (!ret) + val = mt6370_clamp(val, MT6370_ITORCH_MIN_uA, max_ua, MT6370_ITORCH_STEP_uA); + + lcdev->max_brightness = (val - MT6370_ITORCH_MIN_uA) / MT6370_ITORCH_STEP_uA + 1; + lcdev->brightness_set_blocking = mt6370_torch_brightness_set; + lcdev->flags |= LED_DEV_CAP_FLASH; + + max_ua = num == 2 ? MT6370_ISTRB_DOUBLE_MAX_uA : MT6370_ISTRB_MAX_uA; + val = MT6370_ISTRB_MIN_uA; + ret = fwnode_property_read_u32(fwnode, "flash-max-microamp", &val); + if (!ret) + val = mt6370_clamp(val, MT6370_ISTRB_MIN_uA, max_ua, MT6370_ISTRB_STEP_uA); + + s = &flash->brightness; + s->min = MT6370_ISTRB_MIN_uA; + s->step = MT6370_ISTRB_STEP_uA; + s->val = s->max = val; + + /* Always configure to the minimum level when off to prevent flash current spikes. */ + ret = _mt6370_flash_brightness_set(flash, s->min); + if (ret) + return ret; + + val = MT6370_STRBTO_MIN_US; + ret = fwnode_property_read_u32(fwnode, "flash-max-timeout-us", &val); + if (!ret) + val = mt6370_clamp(val, MT6370_STRBTO_MIN_US, MT6370_STRBTO_MAX_US, + MT6370_STRBTO_STEP_US); + + s = &flash->timeout; + s->min = MT6370_STRBTO_MIN_US; + s->step = MT6370_STRBTO_STEP_US; + s->val = s->max = val; + + flash->ops = &mt6370_flash_ops; + + return 0; +} + +static int mt6370_led_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mt6370_priv *priv; + struct fwnode_handle *child; + size_t count; + int i = 0, ret; + + count = device_get_child_node_count(dev); + if (!count || count > MT6370_MAX_LEDS) + return dev_err_probe(dev, -EINVAL, + "No child node or node count over max led number %zu\n", count); + + priv = devm_kzalloc(dev, struct_size(priv, leds, count), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->leds_count = count; + mutex_init(&priv->lock); + + priv->regmap = dev_get_regmap(dev->parent, NULL); + if (!priv->regmap) + return dev_err_probe(dev, -ENODEV, "Failed to get parent regmap\n"); + + device_for_each_child_node(dev, child) { + struct mt6370_led *led = priv->leds + i; + + led->priv = priv; + + ret = mt6370_init_flash_properties(dev, led, child); + if (ret) { + fwnode_handle_put(child); + return ret; + } + + ret = mt6370_led_register(dev, led, child); + if (ret) { + fwnode_handle_put(child); + return ret; + } + + i++; + } + + return 0; +} + +static const struct of_device_id mt6370_led_of_id[] = { + { .compatible = "mediatek,mt6370-flashlight" }, + {} +}; +MODULE_DEVICE_TABLE(of, mt6370_led_of_id); + +static struct platform_driver mt6370_led_driver = { + .driver = { + .name = "mt6370-flashlight", + .of_match_table = mt6370_led_of_id, + }, + .probe = mt6370_led_probe, +}; +module_platform_driver(mt6370_led_driver); + +MODULE_AUTHOR("Alice Chen "); +MODULE_AUTHOR("ChiYuan Huang "); +MODULE_DESCRIPTION("MT6370 FLASH LED Driver"); +MODULE_LICENSE("GPL"); -- GitLab From f797dbf9a1ac1c50de6c1fac7110e7f8213b6848 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Fri, 10 Mar 2023 14:55:57 +0800 Subject: [PATCH 1147/5631] docs: leds: Add MT6370 RGB LED pattern document Document the MT6370 RGB LED pattern trigger. This simply describe how the pattern works, each timing period, and the pattern diagram for MT6370 RGB LED. Signed-off-by: ChiYuan Huang Signed-off-by: ChiaEn Wu Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/38f1e863b0f099158a63fb6f95056a1cb30d80a0.1678430444.git.chiaen_wu@richtek.com --- Documentation/leds/leds-mt6370-rgb.rst | 64 ++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) create mode 100644 Documentation/leds/leds-mt6370-rgb.rst diff --git a/Documentation/leds/leds-mt6370-rgb.rst b/Documentation/leds/leds-mt6370-rgb.rst new file mode 100644 index 000000000000..abf739e44842 --- /dev/null +++ b/Documentation/leds/leds-mt6370-rgb.rst @@ -0,0 +1,64 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================================= +The device for Mediatek MT6370 RGB LED +========================================= + +Description +----------- + +The MT6370 integrates a four-channel RGB LED driver, designed to provide a +variety of lighting effect for mobile device applications. The RGB LED devices +includes a smart LED string controller and it can drive 3 channels of LEDs with +a sink current up to 24mA and a CHG_VIN power good indicator LED with sink +current up to 6mA. It provides three operation modes for RGB LEDs: +PWM Dimming mode, breath pattern mode, and constant current mode. The device +can increase or decrease the brightness of the RGB LED via an I2C interface. + +The breath pattern for a channel can be programmed using the "pattern" trigger, +using the hw_pattern attribute. + +/sys/class/leds//hw_pattern +-------------------------------- + +Specify a hardware breath pattern for a MT6370 RGB LED. + +The breath pattern is a series of timing pairs, with the hold-time expressed in +milliseconds. And the brightness is controlled by +'/sys/class/leds//brightness'. The pattern doesn't include the brightness +setting. Hardware pattern only controls the timing for each pattern stage +depending on the current brightness setting. + +Pattern diagram:: + + "0 Tr1 0 Tr2 0 Tf1 0 Tf2 0 Ton 0 Toff" --> '0' for dummy brightness code + + ^ + | ============ + | / \ / +Icurr | / \ / + | / \ / + | / \ / .....repeat + | / \ / + | --- --- --- + |--- --- --- + +----------------------------------============------------> Time + < Tr1>< Ton >< Toff >< Tr1> + +Timing description:: + +Tr1: First rising time for duty 0 to 30%. +Tr2: Second rising time for duty 31% to 100%. +Ton: On time for duty 100%. +Tf1: First falling time for duty 100% to 31%. +Tf2: Second falling time for duty 30% to 0%. +Toff: Off time for duty 0%. + +Tr1/Tr2/Tf1/Tf2/Ton: 125ms to 3125ms, 200ms per step. +Toff: 250ms to 6250ms, 400ms per step. + +Pattern example:: + + "0 125 0 125 0 125 0 125 0 625 0 1050" + +This Will configure Tr1/Tr2/Tf1/Tf2 to 125m, Ton to 625ms, and Toff to 1050ms. -- GitLab From 4793b19ef0dc40b4b8fdae9a48f73c818e490046 Mon Sep 17 00:00:00 2001 From: ChiYuan Huang Date: Fri, 17 Mar 2023 23:42:40 +0800 Subject: [PATCH 1148/5631] leds: rgb: mt6370: Fix implicit declaration for FIELD_GET 0-DAY CI Kernel Test Service reported the implicit declaration error below: drivers/leds/rgb/leds-mt6370-rgb.c: In function'mt6370_check_vendor_info': >> drivers/leds/rgb/leds-mt6370-rgb.c:889:15: error: implicit declaration of function 'FIELD_GET' [-Werror=implicit-function-declaration] 889 | vid = FIELD_GET(MT6370_VENDOR_ID_MASK, devinfo); | Add the missing header 'bitfield.h' to fix it. Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303171729.CcgyFx17-lkp@intel.com/ Fixes: 55a8a5c16eb3 ("leds: rgb: mt6370: Add MediaTek MT6370 current sink type LED Indicator support") Signed-off-by: ChiYuan Huang Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1679067760-19098-1-git-send-email-cy_huang@richtek.com --- drivers/leds/rgb/leds-mt6370-rgb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/leds/rgb/leds-mt6370-rgb.c b/drivers/leds/rgb/leds-mt6370-rgb.c index 9c1e6d566f11..bb62431efe83 100644 --- a/drivers/leds/rgb/leds-mt6370-rgb.c +++ b/drivers/leds/rgb/leds-mt6370-rgb.c @@ -7,6 +7,7 @@ * Alice Chen */ +#include #include #include #include -- GitLab From 1d105d6cddd03f97303fd4cbcf62834d6ed820c3 Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Sun, 19 Mar 2023 14:49:01 +0700 Subject: [PATCH 1149/5631] Documentation: leds: Add MT6370 doc to the toctree Commit 4ba9df04b7ac66 ("docs: leds: Add MT6370 RGB LED pattern document") adds documentation for Mediatek MT6370 RGB LED device, but forgets to include it to leds toctree index. Add the missing entry. Link: https://lore.kernel.org/oe-kbuild-all/202303182310.tB1mUzU7-lkp@intel.com/ Fixes: 4ba9df04b7ac66 ("docs: leds: Add MT6370 RGB LED pattern document") Reported-by: kernel test robot Signed-off-by: Bagas Sanjaya Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230319074903.13075-2-bagasdotme@gmail.com --- Documentation/leds/index.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/leds/index.rst b/Documentation/leds/index.rst index b9ca081fac71..ce57254cb871 100644 --- a/Documentation/leds/index.rst +++ b/Documentation/leds/index.rst @@ -25,5 +25,6 @@ LEDs leds-lp5562 leds-lp55xx leds-mlxcpld + leds-mt6370-rgb leds-sc27xx leds-qcom-lpg -- GitLab From cc087c0b137e9e86457f84a7b5b1416938101a14 Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Sun, 19 Mar 2023 14:49:02 +0700 Subject: [PATCH 1150/5631] Documentation: leds: mt6370: Properly wrap hw_pattern chart The pattern diagram (chart) of /sys/class/leds//hw_pattern is wrapped in literal code block. However, the block indentation is interrupted by Icurr axis label, hence below warnings: Documentation/leds/leds-mt6370-rgb.rst:39: WARNING: Literal block ends without a blank line; unexpected unindent. Documentation/leds/leds-mt6370-rgb.rst:41: WARNING: Line block ends without a blank line. Documentation/leds/leds-mt6370-rgb.rst:46: WARNING: Unexpected indentation. Documentation/leds/leds-mt6370-rgb.rst:44: WARNING: Inline substitution_reference start-string without end-string. Fix the chart indentation by adding 4 more spaces so that the axis label is in the code block. Link: https://lore.kernel.org/oe-kbuild-all/202303182310.tB1mUzU7-lkp@intel.com/ Fixes: 4ba9df04b7ac66 ("docs: leds: Add MT6370 RGB LED pattern document") Reported-by: kernel test robot Signed-off-by: Bagas Sanjaya Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230319074903.13075-3-bagasdotme@gmail.com --- Documentation/leds/leds-mt6370-rgb.rst | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/leds/leds-mt6370-rgb.rst b/Documentation/leds/leds-mt6370-rgb.rst index abf739e44842..ea782797a06d 100644 --- a/Documentation/leds/leds-mt6370-rgb.rst +++ b/Documentation/leds/leds-mt6370-rgb.rst @@ -31,19 +31,19 @@ depending on the current brightness setting. Pattern diagram:: - "0 Tr1 0 Tr2 0 Tf1 0 Tf2 0 Ton 0 Toff" --> '0' for dummy brightness code - - ^ - | ============ - | / \ / -Icurr | / \ / - | / \ / - | / \ / .....repeat - | / \ / - | --- --- --- - |--- --- --- - +----------------------------------============------------> Time - < Tr1>< Ton >< Toff >< Tr1> + "0 Tr1 0 Tr2 0 Tf1 0 Tf2 0 Ton 0 Toff" --> '0' for dummy brightness code + + ^ + | ============ + | / \ / + Icurr | / \ / + | / \ / + | / \ / .....repeat + | / \ / + | --- --- --- + |--- --- --- + +----------------------------------============------------> Time + < Tr1>< Ton >< Toff >< Tr1> Timing description:: -- GitLab From 8574bf8d0ddd46f0bc393381563f59a6f4418a3e Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 21 Feb 2023 22:30:16 -0500 Subject: [PATCH 1151/5631] riscv: ptrace: Remove duplicate operation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The TIF_SYSCALL_TRACE is controlled by a common code, see kernel/ptrace.c and include/linux/thread_info.h. clear_task_syscall_work(child, SYSCALL_TRACE); Signed-off-by: Guo Ren Signed-off-by: Guo Ren Reviewed-by: Oleg Nesterov Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230222033021.983168-3-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/ptrace.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 2ae8280ae475..44f4b1ca315d 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -212,7 +212,6 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) void ptrace_disable(struct task_struct *child) { - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); } long arch_ptrace(struct task_struct *child, long request, -- GitLab From d0db02c628793e389538c0e5c3f6491141ea6200 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 21 Feb 2023 22:30:17 -0500 Subject: [PATCH 1152/5631] riscv: entry: Add noinstr to prevent instrumentation inserted MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without noinstr the compiler is free to insert instrumentation (think all the k*SAN, KCov, GCov, ftrace etc..) which can call code we're not yet ready to run this early in the entry path, for instance it could rely on RCU which isn't on yet, or expect lockdep state. (by peterz) Link: https://lore.kernel.org/linux-riscv/YxcQ6NoPf3AH0EXe@hirez.programming.kicks-ass.net/ Reviewed-by: Björn Töpel Suggested-by: Peter Zijlstra Tested-by: Jisheng Zhang Signed-off-by: Guo Ren Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20230222033021.983168-4-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/traps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index f6fda94e8e59..02727a4fe8be 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -119,9 +119,9 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } #if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_RISCV_ALTERNATIVE) -#define __trap_section __section(".xip.traps") +#define __trap_section __noinstr_section(".xip.traps") #else -#define __trap_section +#define __trap_section noinstr #endif #define DO_ERROR_INFO(name, signo, code, str) \ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ -- GitLab From f0bddf50586da81360627a772be0e355b62f071e Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Tue, 21 Feb 2023 22:30:18 -0500 Subject: [PATCH 1153/5631] riscv: entry: Convert to generic entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch converts riscv to use the generic entry infrastructure from kernel/entry/*. The generic entry makes maintainers' work easier and codes more elegant. Here are the changes: - More clear entry.S with handle_exception and ret_from_exception - Get rid of complex custom signal implementation - Move syscall procedure from assembly to C, which is much more readable. - Connect ret_from_fork & ret_from_kernel_thread to generic entry. - Wrap with irqentry_enter/exit and syscall_enter/exit_from_user_mode - Use the standard preemption code instead of custom Suggested-by: Huacai Chen Reviewed-by: Björn Töpel Tested-by: Yipeng Zou Tested-by: Jisheng Zhang Signed-off-by: Guo Ren Signed-off-by: Guo Ren Cc: Ben Hutchings Link: https://lore.kernel.org/r/20230222033021.983168-5-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + arch/riscv/include/asm/asm-prototypes.h | 2 + arch/riscv/include/asm/csr.h | 1 - arch/riscv/include/asm/entry-common.h | 11 ++ arch/riscv/include/asm/ptrace.h | 10 +- arch/riscv/include/asm/stacktrace.h | 5 + arch/riscv/include/asm/syscall.h | 21 ++ arch/riscv/include/asm/thread_info.h | 13 +- arch/riscv/kernel/entry.S | 242 ++++-------------------- arch/riscv/kernel/head.h | 1 - arch/riscv/kernel/ptrace.c | 43 ----- arch/riscv/kernel/signal.c | 29 +-- arch/riscv/kernel/traps.c | 140 ++++++++++++-- arch/riscv/mm/fault.c | 6 +- 14 files changed, 210 insertions(+), 315 deletions(-) create mode 100644 arch/riscv/include/asm/entry-common.h diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..41a9a0d5afa5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -60,6 +60,7 @@ config RISCV select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_EARLY_IOREMAP + select GENERIC_ENTRY select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO select GENERIC_IDLE_POLL_SETUP select GENERIC_IOREMAP if MMU diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index ef386fcf3939..61ba8ed43d8f 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -27,5 +27,7 @@ DECLARE_DO_ERROR_INFO(do_trap_break); asmlinkage unsigned long get_overflow_stack(void); asmlinkage void handle_bad_stack(struct pt_regs *regs); +asmlinkage void do_page_fault(struct pt_regs *regs); +asmlinkage void do_irq(struct pt_regs *regs); #endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 0e571f6483d9..7c2b8cdb7b77 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -40,7 +40,6 @@ #define SR_UXL _AC(0x300000000, UL) /* XLEN mask for U-mode */ #define SR_UXL_32 _AC(0x100000000, UL) /* XLEN = 32 for U-mode */ #define SR_UXL_64 _AC(0x200000000, UL) /* XLEN = 64 for U-mode */ -#define SR_UXL_SHIFT 32 #endif /* SATP flags */ diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h new file mode 100644 index 000000000000..6e4dee49d84b --- /dev/null +++ b/arch/riscv/include/asm/entry-common.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_ENTRY_COMMON_H +#define _ASM_RISCV_ENTRY_COMMON_H + +#include + +void handle_page_fault(struct pt_regs *regs); +void handle_break(struct pt_regs *regs); + +#endif /* _ASM_RISCV_ENTRY_COMMON_H */ diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index 6ecd461129d2..b5b0adcc85c1 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -53,6 +53,9 @@ struct pt_regs { unsigned long orig_a0; }; +#define PTRACE_SYSEMU 0x1f +#define PTRACE_SYSEMU_SINGLESTEP 0x20 + #ifdef CONFIG_64BIT #define REG_FMT "%016lx" #else @@ -121,8 +124,6 @@ extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long frame_pointer); -int do_syscall_trace_enter(struct pt_regs *regs); -void do_syscall_trace_exit(struct pt_regs *regs); /** * regs_get_register() - get register value from its offset @@ -172,6 +173,11 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, return 0; } +static inline int regs_irqs_disabled(struct pt_regs *regs) +{ + return !(regs->status & SR_PIE); +} + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h index 3450c1912afd..f7e8ef2418b9 100644 --- a/arch/riscv/include/asm/stacktrace.h +++ b/arch/riscv/include/asm/stacktrace.h @@ -16,4 +16,9 @@ extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *re extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task, const char *loglvl); +static inline bool on_thread_stack(void) +{ + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); +} + #endif /* _ASM_RISCV_STACKTRACE_H */ diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 384a63b86420..736110e1fd78 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -74,5 +74,26 @@ static inline int syscall_get_arch(struct task_struct *task) #endif } +typedef long (*syscall_t)(ulong, ulong, ulong, ulong, ulong, ulong, ulong); +static inline void syscall_handler(struct pt_regs *regs, ulong syscall) +{ + syscall_t fn; + +#ifdef CONFIG_COMPAT + if ((regs->status & SR_UXL) == SR_UXL_32) + fn = compat_sys_call_table[syscall]; + else +#endif + fn = sys_call_table[syscall]; + + regs->a0 = fn(regs->orig_a0, regs->a1, regs->a2, + regs->a3, regs->a4, regs->a5, regs->a6); +} + +static inline bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) +{ + return false; +} + asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); #endif /* _ASM_RISCV_SYSCALL_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index f704c8dd57e0..e0d202134b44 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -67,6 +67,7 @@ struct thread_info { long kernel_sp; /* Kernel stack pointer */ long user_sp; /* User stack pointer */ int cpu; + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ }; /* @@ -89,26 +90,18 @@ struct thread_info { * - pending work-to-be-done flags are in lowest half-word * - other flags in upper half-word(s) */ -#define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_RESTORE_SIGMASK 4 /* restore signal mask in do_signal() */ #define TIF_MEMDIE 5 /* is terminating due to OOM killer */ -#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ -#define TIF_SYSCALL_AUDIT 7 /* syscall auditing */ -#define TIF_SECCOMP 8 /* syscall secure computing */ #define TIF_NOTIFY_SIGNAL 9 /* signal notifications exist */ #define TIF_UPROBE 10 /* uprobe breakpoint or singlestep */ #define TIF_32BIT 11 /* compat-mode 32bit process */ -#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) -#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) -#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) -#define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_UPROBE (1 << TIF_UPROBE) @@ -116,8 +109,4 @@ struct thread_info { (_TIF_NOTIFY_RESUME | _TIF_SIGPENDING | _TIF_NEED_RESCHED | \ _TIF_NOTIFY_SIGNAL | _TIF_UPROBE) -#define _TIF_SYSCALL_WORK \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT | \ - _TIF_SECCOMP) - #endif /* _ASM_RISCV_THREAD_INFO_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 99d38fdf8b18..bc322f92ba34 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -14,11 +14,7 @@ #include #include -#if !IS_ENABLED(CONFIG_PREEMPTION) -.set resume_kernel, restore_all -#endif - -ENTRY(handle_exception) +SYM_CODE_START(handle_exception) /* * If coming from userspace, preserve the user thread pointer and load * the kernel thread pointer. If we came from the kernel, the scratch @@ -106,19 +102,8 @@ _save_context: .option norelax la gp, __global_pointer$ .option pop - -#ifdef CONFIG_TRACE_IRQFLAGS - call __trace_hardirqs_off -#endif - -#ifdef CONFIG_CONTEXT_TRACKING_USER - /* If previous state is in user mode, call user_exit_callable(). */ - li a0, SR_PP - and a0, s1, a0 - bnez a0, skip_context_tracking - call user_exit_callable -skip_context_tracking: -#endif + move a0, sp /* pt_regs */ + la ra, ret_from_exception /* * MSB of cause differentiates between @@ -126,38 +111,13 @@ skip_context_tracking: */ bge s4, zero, 1f - la ra, ret_from_exception - /* Handle interrupts */ - move a0, sp /* pt_regs */ - la a1, generic_handle_arch_irq - jr a1 -1: - /* - * Exceptions run with interrupts enabled or disabled depending on the - * state of SR_PIE in m/sstatus. - */ - andi t0, s1, SR_PIE - beqz t0, 1f - /* kprobes, entered via ebreak, must have interrupts disabled. */ - li t0, EXC_BREAKPOINT - beq s4, t0, 1f -#ifdef CONFIG_TRACE_IRQFLAGS - call __trace_hardirqs_on -#endif - csrs CSR_STATUS, SR_IE - + tail do_irq 1: - la ra, ret_from_exception - /* Handle syscalls */ - li t0, EXC_SYSCALL - beq s4, t0, handle_syscall - /* Handle other exceptions */ slli t0, s4, RISCV_LGPTR la t1, excp_vect_table la t2, excp_vect_table_end - move a0, sp /* pt_regs */ add t0, t1, t0 /* Check if exception code lies within bounds */ bgeu t0, t2, 1f @@ -165,95 +125,17 @@ skip_context_tracking: jr t0 1: tail do_trap_unknown +SYM_CODE_END(handle_exception) -handle_syscall: -#ifdef CONFIG_RISCV_M_MODE - /* - * When running is M-Mode (no MMU config), MPIE does not get set. - * As a result, we need to force enable interrupts here because - * handle_exception did not do set SR_IE as it always sees SR_PIE - * being cleared. - */ - csrs CSR_STATUS, SR_IE -#endif -#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER) - /* Recover a0 - a7 for system calls */ - REG_L a0, PT_A0(sp) - REG_L a1, PT_A1(sp) - REG_L a2, PT_A2(sp) - REG_L a3, PT_A3(sp) - REG_L a4, PT_A4(sp) - REG_L a5, PT_A5(sp) - REG_L a6, PT_A6(sp) - REG_L a7, PT_A7(sp) -#endif - /* save the initial A0 value (needed in signal handlers) */ - REG_S a0, PT_ORIG_A0(sp) - /* - * Advance SEPC to avoid executing the original - * scall instruction on sret - */ - addi s2, s2, 0x4 - REG_S s2, PT_EPC(sp) - /* Trace syscalls, but only if requested by the user. */ - REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_WORK - bnez t0, handle_syscall_trace_enter -check_syscall_nr: - /* Check to make sure we don't jump to a bogus syscall number. */ - li t0, __NR_syscalls - la s0, sys_ni_syscall - /* - * Syscall number held in a7. - * If syscall number is above allowed value, redirect to ni_syscall. - */ - bgeu a7, t0, 3f -#ifdef CONFIG_COMPAT - REG_L s0, PT_STATUS(sp) - srli s0, s0, SR_UXL_SHIFT - andi s0, s0, (SR_UXL >> SR_UXL_SHIFT) - li t0, (SR_UXL_32 >> SR_UXL_SHIFT) - sub t0, s0, t0 - bnez t0, 1f - - /* Call compat_syscall */ - la s0, compat_sys_call_table - j 2f -1: -#endif - /* Call syscall */ - la s0, sys_call_table -2: - slli t0, a7, RISCV_LGPTR - add s0, s0, t0 - REG_L s0, 0(s0) -3: - jalr s0 - -ret_from_syscall: - /* Set user a0 to kernel a0 */ - REG_S a0, PT_A0(sp) - /* - * We didn't execute the actual syscall. - * Seccomp already set return value for the current task pt_regs. - * (If it was configured with SECCOMP_RET_ERRNO/TRACE) - */ -ret_from_syscall_rejected: -#ifdef CONFIG_DEBUG_RSEQ - move a0, sp - call rseq_syscall -#endif - /* Trace syscalls, but only if requested by the user. */ - REG_L t0, TASK_TI_FLAGS(tp) - andi t0, t0, _TIF_SYSCALL_WORK - bnez t0, handle_syscall_trace_exit - +/* + * The ret_from_exception must be called with interrupt disabled. Here is the + * caller list: + * - handle_exception + * - ret_from_fork + * - ret_from_kernel_thread + */ SYM_CODE_START_NOALIGN(ret_from_exception) REG_L s0, PT_STATUS(sp) - csrc CSR_STATUS, SR_IE -#ifdef CONFIG_TRACE_IRQFLAGS - call __trace_hardirqs_off -#endif #ifdef CONFIG_RISCV_M_MODE /* the MPP value is too large to be used as an immediate arg for addi */ li t0, SR_MPP @@ -261,17 +143,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else andi s0, s0, SR_SPP #endif - bnez s0, resume_kernel -SYM_CODE_END(ret_from_exception) - - /* Interrupts must be disabled here so flags are checked atomically */ - REG_L s0, TASK_TI_FLAGS(tp) /* current_thread_info->flags */ - andi s1, s0, _TIF_WORK_MASK - bnez s1, resume_userspace_slow -resume_userspace: -#ifdef CONFIG_CONTEXT_TRACKING_USER - call user_enter_callable -#endif + bnez s0, 1f /* Save unwound kernel stack pointer in thread_info */ addi s0, sp, PT_SIZE_ON_STACK @@ -282,18 +154,7 @@ resume_userspace: * structures again. */ csrw CSR_SCRATCH, tp - -restore_all: -#ifdef CONFIG_TRACE_IRQFLAGS - REG_L s1, PT_STATUS(sp) - andi t0, s1, SR_PIE - beqz t0, 1f - call __trace_hardirqs_on - j 2f 1: - call __trace_hardirqs_off -2: -#endif REG_L a0, PT_STATUS(sp) /* * The current load reservation is effectively part of the processor's @@ -356,47 +217,10 @@ restore_all: #else sret #endif - -#if IS_ENABLED(CONFIG_PREEMPTION) -resume_kernel: - REG_L s0, TASK_TI_PREEMPT_COUNT(tp) - bnez s0, restore_all - REG_L s0, TASK_TI_FLAGS(tp) - andi s0, s0, _TIF_NEED_RESCHED - beqz s0, restore_all - call preempt_schedule_irq - j restore_all -#endif - -resume_userspace_slow: - /* Enter slow path for supplementary processing */ - move a0, sp /* pt_regs */ - move a1, s0 /* current_thread_info->flags */ - call do_work_pending - j resume_userspace - -/* Slow paths for ptrace. */ -handle_syscall_trace_enter: - move a0, sp - call do_syscall_trace_enter - move t0, a0 - REG_L a0, PT_A0(sp) - REG_L a1, PT_A1(sp) - REG_L a2, PT_A2(sp) - REG_L a3, PT_A3(sp) - REG_L a4, PT_A4(sp) - REG_L a5, PT_A5(sp) - REG_L a6, PT_A6(sp) - REG_L a7, PT_A7(sp) - bnez t0, ret_from_syscall_rejected - j check_syscall_nr -handle_syscall_trace_exit: - move a0, sp - call do_syscall_trace_exit - j ret_from_exception +SYM_CODE_END(ret_from_exception) #ifdef CONFIG_VMAP_STACK -handle_kernel_stack_overflow: +SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) /* * Takes the psuedo-spinlock for the shadow stack, in case multiple * harts are concurrently overflowing their kernel stacks. We could @@ -505,23 +329,25 @@ restore_caller_reg: REG_S s5, PT_TP(sp) move a0, sp tail handle_bad_stack +SYM_CODE_END(handle_kernel_stack_overflow) #endif -END(handle_exception) - -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) + call schedule_tail + move a0, sp /* pt_regs */ la ra, ret_from_exception - tail schedule_tail -ENDPROC(ret_from_fork) + tail syscall_exit_to_user_mode +SYM_CODE_END(ret_from_fork) -ENTRY(ret_from_kernel_thread) +SYM_CODE_START(ret_from_kernel_thread) call schedule_tail /* Call fn(arg) */ - la ra, ret_from_exception move a0, s1 - jr s0 -ENDPROC(ret_from_kernel_thread) - + jalr s0 + move a0, sp /* pt_regs */ + la ra, ret_from_exception + tail syscall_exit_to_user_mode +SYM_CODE_END(ret_from_kernel_thread) /* * Integer register context switch @@ -533,7 +359,7 @@ ENDPROC(ret_from_kernel_thread) * The value of a0 and a1 must be preserved by this function, as that's how * arguments are passed to schedule_tail. */ -ENTRY(__switch_to) +SYM_FUNC_START(__switch_to) /* Save context into prev->thread */ li a4, TASK_THREAD_RA add a3, a0, a4 @@ -570,7 +396,7 @@ ENTRY(__switch_to) /* The offset of thread_info in task_struct is zero. */ move tp, a1 ret -ENDPROC(__switch_to) +SYM_FUNC_END(__switch_to) #ifndef CONFIG_MMU #define do_page_fault do_trap_unknown @@ -579,7 +405,7 @@ ENDPROC(__switch_to) .section ".rodata" .align LGREG /* Exception vector table */ -ENTRY(excp_vect_table) +SYM_CODE_START(excp_vect_table) RISCV_PTR do_trap_insn_misaligned ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault) RISCV_PTR do_trap_insn_illegal @@ -588,7 +414,7 @@ ENTRY(excp_vect_table) RISCV_PTR do_trap_load_fault RISCV_PTR do_trap_store_misaligned RISCV_PTR do_trap_store_fault - RISCV_PTR do_trap_ecall_u /* system call, gets intercepted */ + RISCV_PTR do_trap_ecall_u /* system call */ RISCV_PTR do_trap_ecall_s RISCV_PTR do_trap_unknown RISCV_PTR do_trap_ecall_m @@ -598,11 +424,11 @@ ENTRY(excp_vect_table) RISCV_PTR do_trap_unknown RISCV_PTR do_page_fault /* store page fault */ excp_vect_table_end: -END(excp_vect_table) +SYM_CODE_END(excp_vect_table) #ifndef CONFIG_MMU -ENTRY(__user_rt_sigreturn) +SYM_CODE_START(__user_rt_sigreturn) li a7, __NR_rt_sigreturn scall -END(__user_rt_sigreturn) +SYM_CODE_END(__user_rt_sigreturn) #endif diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h index 726731ada534..a556fdaafed9 100644 --- a/arch/riscv/kernel/head.h +++ b/arch/riscv/kernel/head.h @@ -10,7 +10,6 @@ extern atomic_t hart_lottery; -asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void __init setup_vm(uintptr_t dtb_pa); #ifdef CONFIG_XIP_KERNEL asmlinkage void __init __copy_data(void); diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 44f4b1ca315d..23c48b14a0e7 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -19,9 +19,6 @@ #include #include -#define CREATE_TRACE_POINTS -#include - enum riscv_regset { REGSET_X, #ifdef CONFIG_FPU @@ -228,46 +225,6 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -/* - * Allows PTRACE_SYSCALL to work. These are called from entry.S in - * {handle,ret_from}_syscall. - */ -__visible int do_syscall_trace_enter(struct pt_regs *regs) -{ - if (test_thread_flag(TIF_SYSCALL_TRACE)) - if (ptrace_report_syscall_entry(regs)) - return -1; - - /* - * Do the secure computing after ptrace; failures should be fast. - * If this fails we might have return value in a0 from seccomp - * (via SECCOMP_RET_ERRNO/TRACE). - */ - if (secure_computing() == -1) - return -1; - -#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) - trace_sys_enter(regs, syscall_get_nr(current, regs)); -#endif - - audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3); - return 0; -} - -__visible void do_syscall_trace_exit(struct pt_regs *regs) -{ - audit_syscall_exit(regs); - - if (test_thread_flag(TIF_SYSCALL_TRACE)) - ptrace_report_syscall_exit(regs, 0); - -#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) - trace_sys_exit(regs, regs_return_value(regs)); -#endif -} - #ifdef CONFIG_COMPAT static int compat_riscv_gpr_get(struct task_struct *target, const struct user_regset *regset, diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index bfb2afa4135f..2e365084417e 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -274,7 +275,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) signal_setup_done(ret, ksig, 0); } -static void do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs) { struct ksignal ksig; @@ -311,29 +312,3 @@ static void do_signal(struct pt_regs *regs) */ restore_saved_sigmask(); } - -/* - * Handle any pending work on the resume-to-userspace path, as indicated by - * _TIF_WORK_MASK. Entered from assembly with IRQs off. - */ -asmlinkage __visible void do_work_pending(struct pt_regs *regs, - unsigned long thread_info_flags) -{ - do { - if (thread_info_flags & _TIF_NEED_RESCHED) { - schedule(); - } else { - local_irq_enable(); - if (thread_info_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - /* Handle pending signal delivery */ - if (thread_info_flags & (_TIF_SIGPENDING | - _TIF_NOTIFY_SIGNAL)) - do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) - resume_user_mode_work(regs); - } - local_irq_disable(); - thread_info_flags = read_thread_flags(); - } while (thread_info_flags & _TIF_WORK_MASK); -} diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 02727a4fe8be..1f4e37be7eb3 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -17,12 +17,14 @@ #include #include #include +#include #include #include #include #include #include +#include #include int show_unhandled_signals = 1; @@ -123,10 +125,18 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, #else #define __trap_section noinstr #endif -#define DO_ERROR_INFO(name, signo, code, str) \ -asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ -{ \ - do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ +#define DO_ERROR_INFO(name, signo, code, str) \ +asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ +{ \ + if (user_mode(regs)) { \ + irqentry_enter_from_user_mode(regs); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + irqentry_exit_to_user_mode(regs); \ + } else { \ + irqentry_state_t state = irqentry_nmi_enter(regs); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + irqentry_nmi_exit(regs, state); \ + } \ } DO_ERROR_INFO(do_trap_unknown, @@ -148,26 +158,50 @@ DO_ERROR_INFO(do_trap_store_misaligned, int handle_misaligned_load(struct pt_regs *regs); int handle_misaligned_store(struct pt_regs *regs); -asmlinkage void __trap_section do_trap_load_misaligned(struct pt_regs *regs) +asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) { - if (!handle_misaligned_load(regs)) - return; - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - load address misaligned"); + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + if (handle_misaligned_load(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + "Oops - load address misaligned"); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + if (handle_misaligned_load(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + "Oops - load address misaligned"); + + irqentry_nmi_exit(regs, state); + } } -asmlinkage void __trap_section do_trap_store_misaligned(struct pt_regs *regs) +asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) { - if (!handle_misaligned_store(regs)) - return; - do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, - "Oops - store (or AMO) address misaligned"); + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + if (handle_misaligned_store(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + "Oops - store (or AMO) address misaligned"); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + if (handle_misaligned_store(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + "Oops - store (or AMO) address misaligned"); + + irqentry_nmi_exit(regs, state); + } } #endif DO_ERROR_INFO(do_trap_store_fault, SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault"); -DO_ERROR_INFO(do_trap_ecall_u, - SIGILL, ILL_ILLTRP, "environment call from U-mode"); DO_ERROR_INFO(do_trap_ecall_s, SIGILL, ILL_ILLTRP, "environment call from S-mode"); DO_ERROR_INFO(do_trap_ecall_m, @@ -183,7 +217,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) return GET_INSN_LENGTH(insn); } -asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) +void handle_break(struct pt_regs *regs) { #ifdef CONFIG_KPROBES if (kprobe_single_step_handler(regs)) @@ -213,7 +247,77 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) else die(regs, "Kernel BUG"); } -NOKPROBE_SYMBOL(do_trap_break); + +asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + handle_break(regs); + + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + handle_break(regs); + + irqentry_nmi_exit(regs, state); + } +} + +asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) +{ + if (user_mode(regs)) { + ulong syscall = regs->a7; + + syscall = syscall_enter_from_user_mode(regs, syscall); + + regs->epc += 4; + regs->orig_a0 = regs->a0; + + if (syscall < NR_syscalls) + syscall_handler(regs, syscall); + else + regs->a0 = -ENOSYS; + + syscall_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLTRP, regs->epc, + "Oops - environment call from U-mode"); + + irqentry_nmi_exit(regs, state); + } + +} + +#ifdef CONFIG_MMU +asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); + + handle_page_fault(regs); + + local_irq_disable(); + + irqentry_exit(regs, state); +} +#endif + +asmlinkage __visible noinstr void do_irq(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + irqentry_state_t state = irqentry_enter(regs); + + irq_enter_rcu(); + old_regs = set_irq_regs(regs); + handle_arch_irq(regs); + set_irq_regs(old_regs); + irq_exit_rcu(); + + irqentry_exit(regs, state); +} #ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long pc) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 460f785f6e09..3aba72ec1742 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -204,7 +205,7 @@ static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) * This routine handles page faults. It determines the address and the * problem, and then passes it off to one of the appropriate routines. */ -asmlinkage void do_page_fault(struct pt_regs *regs) +void handle_page_fault(struct pt_regs *regs) { struct task_struct *tsk; struct vm_area_struct *vma; @@ -251,7 +252,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs) } #endif /* Enable interrupts if they were enabled in the parent context. */ - if (likely(regs->status & SR_PIE)) + if (!regs_irqs_disabled(regs)) local_irq_enable(); /* @@ -356,4 +357,3 @@ asmlinkage void do_page_fault(struct pt_regs *regs) } return; } -NOKPROBE_SYMBOL(do_page_fault); -- GitLab From 0bf298ad2b61ae69d38826f3513e5fffc3fe3a53 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 21 Feb 2023 22:30:19 -0500 Subject: [PATCH 1154/5631] riscv: entry: Remove extra level wrappers of trace_hardirqs_{on,off} MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since riscv is converted to generic entry, there's no need for the extra wrappers of trace_hardirqs_{on,off}. Signed-off-by: Jisheng Zhang Reviewed-by: Guo Ren Reviewed-by: Björn Töpel Tested-by: Guo Ren Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20230222033021.983168-6-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/Makefile | 2 -- arch/riscv/kernel/trace_irq.c | 27 --------------------------- arch/riscv/kernel/trace_irq.h | 11 ----------- 3 files changed, 40 deletions(-) delete mode 100644 arch/riscv/kernel/trace_irq.c delete mode 100644 arch/riscv/kernel/trace_irq.h diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 4cf303a779ab..392fa6e35d4a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -68,8 +68,6 @@ obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irq.o - obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o obj-$(CONFIG_RISCV_SBI) += sbi.o diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c deleted file mode 100644 index 095ac976d7da..000000000000 --- a/arch/riscv/kernel/trace_irq.c +++ /dev/null @@ -1,27 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2022 Changbin Du - */ - -#include -#include -#include "trace_irq.h" - -/* - * trace_hardirqs_on/off require the caller to setup frame pointer properly. - * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel. - * Here we add one extra level so they can be safely called by low - * level entry code which $fp is used for other purpose. - */ - -void __trace_hardirqs_on(void) -{ - trace_hardirqs_on(); -} -NOKPROBE_SYMBOL(__trace_hardirqs_on); - -void __trace_hardirqs_off(void) -{ - trace_hardirqs_off(); -} -NOKPROBE_SYMBOL(__trace_hardirqs_off); diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h deleted file mode 100644 index 99fe67377e5e..000000000000 --- a/arch/riscv/kernel/trace_irq.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2022 Changbin Du - */ -#ifndef __TRACE_IRQ_H -#define __TRACE_IRQ_H - -void __trace_hardirqs_on(void); -void __trace_hardirqs_off(void); - -#endif /* __TRACE_IRQ_H */ -- GitLab From ab9164dae27334415537ccf1c3fbabf56b7793b2 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 21 Feb 2023 22:30:20 -0500 Subject: [PATCH 1155/5631] riscv: entry: Consolidate ret_from_kernel_thread into ret_from_fork MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The ret_from_kernel_thread() behaves similarly with ret_from_fork(), the only difference is whether call the fn(arg) or not, this can be achieved by testing fn is NULL or not, I.E s0 is 0 or not. Many architectures have done the same thing, it makes entry.S more clean. Signed-off-by: Jisheng Zhang Reviewed-by: Björn Töpel Reviewed-by: Guo Ren Tested-by: Guo Ren Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20230222033021.983168-7-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/entry.S | 12 +++--------- arch/riscv/kernel/process.c | 5 ++--- 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index bc322f92ba34..5ccef259498d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -132,7 +132,6 @@ SYM_CODE_END(handle_exception) * caller list: * - handle_exception * - ret_from_fork - * - ret_from_kernel_thread */ SYM_CODE_START_NOALIGN(ret_from_exception) REG_L s0, PT_STATUS(sp) @@ -334,20 +333,15 @@ SYM_CODE_END(handle_kernel_stack_overflow) SYM_CODE_START(ret_from_fork) call schedule_tail - move a0, sp /* pt_regs */ - la ra, ret_from_exception - tail syscall_exit_to_user_mode -SYM_CODE_END(ret_from_fork) - -SYM_CODE_START(ret_from_kernel_thread) - call schedule_tail + beqz s0, 1f /* not from kernel thread */ /* Call fn(arg) */ move a0, s1 jalr s0 +1: move a0, sp /* pt_regs */ la ra, ret_from_exception tail syscall_exit_to_user_mode -SYM_CODE_END(ret_from_kernel_thread) +SYM_CODE_END(ret_from_fork) /* * Integer register context switch diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 774ffde386ab..e2a060066730 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -34,7 +34,6 @@ EXPORT_SYMBOL(__stack_chk_guard); #endif extern asmlinkage void ret_from_fork(void); -extern asmlinkage void ret_from_kernel_thread(void); void arch_cpu_idle(void) { @@ -173,7 +172,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* Supervisor/Machine, irqs on: */ childregs->status = SR_PP | SR_PIE; - p->thread.ra = (unsigned long)ret_from_kernel_thread; p->thread.s[0] = (unsigned long)args->fn; p->thread.s[1] = (unsigned long)args->fn_arg; } else { @@ -183,8 +181,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (clone_flags & CLONE_SETTLS) childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ - p->thread.ra = (unsigned long)ret_from_fork; + p->thread.s[0] = 0; } + p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ return 0; } -- GitLab From 45b32b946a97bb4553bab30c2519bbaac55f39db Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Tue, 21 Feb 2023 22:30:21 -0500 Subject: [PATCH 1156/5631] riscv: entry: Consolidate general regs saving/restoring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Consolidate the saving/restoring GPs (except zero, ra, sp, gp, tp and t0) into save_from_x6_to_x31/restore_from_x6_to_x31 macros. No functional change intended. Signed-off-by: Jisheng Zhang Reviewed-by: Guo Ren Reviewed-by: Björn Töpel Tested-by: Guo Ren Signed-off-by: Guo Ren Link: https://lore.kernel.org/r/20230222033021.983168-8-guoren@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/asm.h | 61 +++++++++++++++++++++++++ arch/riscv/kernel/entry.S | 81 ++-------------------------------- arch/riscv/kernel/mcount-dyn.S | 57 ++---------------------- 3 files changed, 68 insertions(+), 131 deletions(-) diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 816e753de636..114bbadaef41 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -69,6 +69,7 @@ #endif #ifdef __ASSEMBLY__ +#include /* Common assembly source macros */ @@ -81,6 +82,66 @@ .endr .endm + /* save all GPs except x1 ~ x5 */ + .macro save_from_x6_to_x31 + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + .endm + + /* restore all GPs except x1 ~ x5 */ + .macro restore_from_x6_to_x31 + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + .endm + #endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_ASM_H */ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 5ccef259498d..3fbb100bc9e4 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -42,32 +42,7 @@ _save_context: REG_S x1, PT_RA(sp) REG_S x3, PT_GP(sp) REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x8, PT_S0(sp) - REG_S x9, PT_S1(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x18, PT_S2(sp) - REG_S x19, PT_S3(sp) - REG_S x20, PT_S4(sp) - REG_S x21, PT_S5(sp) - REG_S x22, PT_S6(sp) - REG_S x23, PT_S7(sp) - REG_S x24, PT_S8(sp) - REG_S x25, PT_S9(sp) - REG_S x26, PT_S10(sp) - REG_S x27, PT_S11(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) + save_from_x6_to_x31 /* * Disable user-mode memory access as it should only be set in the @@ -182,32 +157,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) REG_L x3, PT_GP(sp) REG_L x4, PT_TP(sp) REG_L x5, PT_T0(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x8, PT_S0(sp) - REG_L x9, PT_S1(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x18, PT_S2(sp) - REG_L x19, PT_S3(sp) - REG_L x20, PT_S4(sp) - REG_L x21, PT_S5(sp) - REG_L x22, PT_S6(sp) - REG_L x23, PT_S7(sp) - REG_L x24, PT_S8(sp) - REG_L x25, PT_S9(sp) - REG_L x26, PT_S10(sp) - REG_L x27, PT_S11(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) + restore_from_x6_to_x31 REG_L x2, PT_SP(sp) @@ -287,32 +237,7 @@ restore_caller_reg: REG_S x1, PT_RA(sp) REG_S x3, PT_GP(sp) REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x8, PT_S0(sp) - REG_S x9, PT_S1(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x18, PT_S2(sp) - REG_S x19, PT_S3(sp) - REG_S x20, PT_S4(sp) - REG_S x21, PT_S5(sp) - REG_S x22, PT_S6(sp) - REG_S x23, PT_S7(sp) - REG_S x24, PT_S8(sp) - REG_S x25, PT_S9(sp) - REG_S x26, PT_S10(sp) - REG_S x27, PT_S11(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) + save_from_x6_to_x31 REG_L s0, TASK_TI_KERNEL_SP(tp) csrr s1, CSR_STATUS diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 125de818d1ba..669b8697aa38 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -66,66 +66,17 @@ REG_S x3, PT_GP(sp) REG_S x4, PT_TP(sp) REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x8, PT_S0(sp) - REG_S x9, PT_S1(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x18, PT_S2(sp) - REG_S x19, PT_S3(sp) - REG_S x20, PT_S4(sp) - REG_S x21, PT_S5(sp) - REG_S x22, PT_S6(sp) - REG_S x23, PT_S7(sp) - REG_S x24, PT_S8(sp) - REG_S x25, PT_S9(sp) - REG_S x26, PT_S10(sp) - REG_S x27, PT_S11(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) + save_from_x6_to_x31 .endm .macro RESTORE_ALL - REG_L t0, PT_EPC(sp) REG_L x1, PT_RA(sp) REG_L x2, PT_SP(sp) REG_L x3, PT_GP(sp) REG_L x4, PT_TP(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x8, PT_S0(sp) - REG_L x9, PT_S1(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x18, PT_S2(sp) - REG_L x19, PT_S3(sp) - REG_L x20, PT_S4(sp) - REG_L x21, PT_S5(sp) - REG_L x22, PT_S6(sp) - REG_L x23, PT_S7(sp) - REG_L x24, PT_S8(sp) - REG_L x25, PT_S9(sp) - REG_L x26, PT_S10(sp) - REG_L x27, PT_S11(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) + /* Restore t0 with PT_EPC */ + REG_L x5, PT_EPC(sp) + restore_from_x6_to_x31 addi sp, sp, PT_SIZE_ON_STACK .endm -- GitLab From 347284984f415e52590373253c6943bbdc806ebf Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:02 +0200 Subject: [PATCH 1157/5631] xhci: mem: Carefully calculate size for memory allocations Carefully calculate size for memory allocations, i.e. with help of size_mul() macro from overflow.h. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index d0a9467aa5fc..c385513ad00b 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -9,6 +9,7 @@ */ #include +#include #include #include #include @@ -568,7 +569,7 @@ static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, gfp_t mem_flags) { struct device *dev = xhci_to_hcd(xhci)->self.sysdev; - size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs; + size_t size = size_mul(sizeof(struct xhci_stream_ctx), num_stream_ctxs); if (size > MEDIUM_STREAM_ARRAY_SIZE) return dma_alloc_coherent(dev, size, @@ -1660,7 +1661,7 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags) goto fail_sp; xhci->scratchpad->sp_array = dma_alloc_coherent(dev, - num_sp * sizeof(u64), + size_mul(sizeof(u64), num_sp), &xhci->scratchpad->sp_dma, flags); if (!xhci->scratchpad->sp_array) goto fail_sp2; @@ -1799,7 +1800,7 @@ int xhci_alloc_erst(struct xhci_hcd *xhci, struct xhci_segment *seg; struct xhci_erst_entry *entry; - size = sizeof(struct xhci_erst_entry) * evt_ring->num_segs; + size = size_mul(sizeof(struct xhci_erst_entry), evt_ring->num_segs); erst->entries = dma_alloc_coherent(xhci_to_hcd(xhci)->self.sysdev, size, &erst->erst_dma_addr, flags); if (!erst->entries) @@ -1830,7 +1831,7 @@ xhci_free_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir) if (!ir) return; - erst_size = sizeof(struct xhci_erst_entry) * (ir->erst.num_entries); + erst_size = sizeof(struct xhci_erst_entry) * ir->erst.num_entries; if (ir->erst.entries) dma_free_coherent(dev, erst_size, ir->erst.entries, -- GitLab From 53ee2663f0df536ccb37d559c4f4c53c4511db7a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:03 +0200 Subject: [PATCH 1158/5631] xhci: mem: Use dma_poll_zalloc() instead of explicit memset() Use dma_poll_zalloc() instead of explicit memset() call in xhci_alloc_stream_ctx(). Note, that dma_alloc_coherent() is always issues zeroed memory chunk. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index c385513ad00b..4ffa6495878d 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -575,10 +575,10 @@ static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, return dma_alloc_coherent(dev, size, dma, mem_flags); else if (size <= SMALL_STREAM_ARRAY_SIZE) - return dma_pool_alloc(xhci->small_streams_pool, + return dma_pool_zalloc(xhci->small_streams_pool, mem_flags, dma); else - return dma_pool_alloc(xhci->medium_streams_pool, + return dma_pool_zalloc(xhci->medium_streams_pool, mem_flags, dma); } @@ -643,8 +643,6 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, mem_flags); if (!stream_info->stream_ctx_array) goto cleanup_ring_array; - memset(stream_info->stream_ctx_array, 0, - sizeof(struct xhci_stream_ctx)*num_stream_ctxs); /* Allocate everything needed to free the stream rings later */ stream_info->free_streams_command = -- GitLab From 85052fdb40a0eb2278d10f016ce12de00672bba9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:04 +0200 Subject: [PATCH 1159/5631] xhci: mem: Get rid of redundant 'else' In the snippets like the following if (...) return / goto / break / continue ...; else ... the 'else' is redundant. Get rid of it. While at it, make if-chain sorted from testing bigger values to smaller. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-4-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 4ffa6495878d..357883256a5a 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -572,14 +572,11 @@ static struct xhci_stream_ctx *xhci_alloc_stream_ctx(struct xhci_hcd *xhci, size_t size = size_mul(sizeof(struct xhci_stream_ctx), num_stream_ctxs); if (size > MEDIUM_STREAM_ARRAY_SIZE) - return dma_alloc_coherent(dev, size, - dma, mem_flags); - else if (size <= SMALL_STREAM_ARRAY_SIZE) - return dma_pool_zalloc(xhci->small_streams_pool, - mem_flags, dma); + return dma_alloc_coherent(dev, size, dma, mem_flags); + if (size > SMALL_STREAM_ARRAY_SIZE) + return dma_pool_zalloc(xhci->medium_streams_pool, mem_flags, dma); else - return dma_pool_zalloc(xhci->medium_streams_pool, - mem_flags, dma); + return dma_pool_zalloc(xhci->small_streams_pool, mem_flags, dma); } struct xhci_ring *xhci_dma_to_transfer_ring( @@ -1399,8 +1396,9 @@ static u32 xhci_get_max_esit_payload(struct usb_device *udev, if ((udev->speed >= USB_SPEED_SUPER_PLUS) && USB_SS_SSP_ISOC_COMP(ep->ss_ep_comp.bmAttributes)) return le32_to_cpu(ep->ssp_isoc_ep_comp.dwBytesPerInterval); + /* SuperSpeed or SuperSpeedPlus Isoc ep with less than 48k per esit */ - else if (udev->speed >= USB_SPEED_SUPER) + if (udev->speed >= USB_SPEED_SUPER) return le16_to_cpu(ep->ss_ep_comp.wBytesPerInterval); max_packet = usb_endpoint_maxp(&ep->desc); -- GitLab From 3056a5cafa3cf83c7c83d3fb4029707888d4bb63 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:05 +0200 Subject: [PATCH 1160/5631] xhci: mem: Drop useless return:s When function returns void and we have if-else-if chain, there is no need to explicitly call return. Drop them and indent lines better. While at it, make if-chain sorted from testing bigger values to smaller. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-5-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 357883256a5a..fa0c4ac2ca7f 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -544,14 +544,11 @@ static void xhci_free_stream_ctx(struct xhci_hcd *xhci, size_t size = sizeof(struct xhci_stream_ctx) * num_stream_ctxs; if (size > MEDIUM_STREAM_ARRAY_SIZE) - dma_free_coherent(dev, size, - stream_ctx, dma); - else if (size <= SMALL_STREAM_ARRAY_SIZE) - return dma_pool_free(xhci->small_streams_pool, - stream_ctx, dma); + dma_free_coherent(dev, size, stream_ctx, dma); + else if (size > SMALL_STREAM_ARRAY_SIZE) + dma_pool_free(xhci->medium_streams_pool, stream_ctx, dma); else - return dma_pool_free(xhci->medium_streams_pool, - stream_ctx, dma); + dma_pool_free(xhci->small_streams_pool, stream_ctx, dma); } /* -- GitLab From 76dc910af13c677b504ac8606352c791891166b1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:06 +0200 Subject: [PATCH 1161/5631] xhci: mem: Use while (i--) pattern to clean up Use more natural while (i--) patter to clean up allocated resources. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-6-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index fa0c4ac2ca7f..b8c1465f8d23 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1679,11 +1679,10 @@ static int scratchpad_alloc(struct xhci_hcd *xhci, gfp_t flags) return 0; fail_sp4: - for (i = i - 1; i >= 0; i--) { + while (i--) dma_free_coherent(dev, xhci->page_size, xhci->scratchpad->sp_buffers[i], xhci->scratchpad->sp_array[i]); - } kfree(xhci->scratchpad->sp_buffers); -- GitLab From 96be93a8c8272d20d20476ba8324e580b6e8a08f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:07 +0200 Subject: [PATCH 1162/5631] xhci: mem: Replace explicit castings with appropriate specifiers There is no need to have explicit castings when we have specific pointer extensions. Replace the explicit castings with appropriate specifiers. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-7-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index b8c1465f8d23..67ac02d177b5 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -666,8 +666,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, cur_ring->cycle_state; stream_info->stream_ctx_array[cur_stream].stream_ring = cpu_to_le64(addr); - xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n", - cur_stream, (unsigned long long) addr); + xhci_dbg(xhci, "Setting stream %d ring ptr to 0x%08llx\n", cur_stream, addr); ret = xhci_update_stream_mapping(cur_ring, mem_flags); if (ret) { @@ -977,16 +976,14 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, if (!dev->out_ctx) goto fail; - xhci_dbg(xhci, "Slot %d output ctx = 0x%llx (dma)\n", slot_id, - (unsigned long long)dev->out_ctx->dma); + xhci_dbg(xhci, "Slot %d output ctx = 0x%pad (dma)\n", slot_id, &dev->out_ctx->dma); /* Allocate the (input) device context for address device command */ dev->in_ctx = xhci_alloc_container_ctx(xhci, XHCI_CTX_TYPE_INPUT, flags); if (!dev->in_ctx) goto fail; - xhci_dbg(xhci, "Slot %d input ctx = 0x%llx (dma)\n", slot_id, - (unsigned long long)dev->in_ctx->dma); + xhci_dbg(xhci, "Slot %d input ctx = 0x%pad (dma)\n", slot_id, &dev->in_ctx->dma); /* Initialize the cancellation and bandwidth list for each ep */ for (i = 0; i < 31; i++) { @@ -2351,8 +2348,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) goto fail; xhci->dcbaa->dma = dma; xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "// Device context base array address = 0x%llx (DMA), %p (virt)", - (unsigned long long)xhci->dcbaa->dma, xhci->dcbaa); + "// Device context base array address = 0x%pad (DMA), %p (virt)", + &xhci->dcbaa->dma, xhci->dcbaa); xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr); /* @@ -2393,8 +2390,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) goto fail; xhci_dbg_trace(xhci, trace_xhci_dbg_init, "Allocated command ring at %p", xhci->cmd_ring); - xhci_dbg_trace(xhci, trace_xhci_dbg_init, "First segment DMA is 0x%llx", - (unsigned long long)xhci->cmd_ring->first_seg->dma); + xhci_dbg_trace(xhci, trace_xhci_dbg_init, "First segment DMA is 0x%pad", + &xhci->cmd_ring->first_seg->dma); /* Set the address in the Command Ring Control register */ val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); -- GitLab From 4feb07d0ada339f7edc0dc3b24581f201848a65b Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 17 Mar 2023 17:47:08 +0200 Subject: [PATCH 1163/5631] xhci: mem: Join string literals back For easy grepping on debug purposes join string literals back in the messages. No functional change. Signed-off-by: Andy Shevchenko Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-8-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mem.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 67ac02d177b5..7e106bd804ca 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -607,8 +607,7 @@ struct xhci_stream_info *xhci_alloc_stream_info(struct xhci_hcd *xhci, int ret; struct device *dev = xhci_to_hcd(xhci)->self.sysdev; - xhci_dbg(xhci, "Allocating %u streams and %u " - "stream context array entries.\n", + xhci_dbg(xhci, "Allocating %u streams and %u stream context array entries.\n", num_streams, num_stream_ctxs); if (xhci->cmd_ring_reserved_trbs == MAX_RSVD_CMD_TRBS) { xhci_dbg(xhci, "Command ring has no reserved TRBs available\n"); @@ -1950,8 +1949,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci, struct xhci_interrupter deq = xhci_trb_virt_to_dma(ir->event_ring->deq_seg, ir->event_ring->dequeue); if (!deq) - xhci_warn(xhci, "WARN something wrong with SW event ring " - "dequeue ptr.\n"); + xhci_warn(xhci, "WARN something wrong with SW event ring dequeue ptr.\n"); /* Update HC event ring dequeue pointer */ temp = xhci_read_64(xhci, &ir->ir_set->erst_dequeue); temp &= ERST_PTR_MASK; @@ -1960,8 +1958,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci, struct xhci_interrupter */ temp &= ~ERST_EHB; xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "// Write event ring dequeue pointer, " - "preserving EHB bit"); + "// Write event ring dequeue pointer, preserving EHB bit"); xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp, &ir->ir_set->erst_dequeue); } @@ -1994,8 +1991,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, } else if (major_revision <= 0x02) { rhub = &xhci->usb2_rhub; } else { - xhci_warn(xhci, "Ignoring unknown port speed, " - "Ext Cap %p, revision = 0x%x\n", + xhci_warn(xhci, "Ignoring unknown port speed, Ext Cap %p, revision = 0x%x\n", addr, major_revision); /* Ignoring port protocol we can't understand. FIXME */ return; @@ -2010,9 +2006,8 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, port_offset = XHCI_EXT_PORT_OFF(temp); port_count = XHCI_EXT_PORT_COUNT(temp); xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "Ext Cap %p, port offset = %u, " - "count = %u, revision = 0x%x", - addr, port_offset, port_count, major_revision); + "Ext Cap %p, port offset = %u, count = %u, revision = 0x%x", + addr, port_offset, port_count, major_revision); /* Port count includes the current port offset */ if (port_offset == 0 || (port_offset + port_count - 1) > num_ports) /* WTF? "Valid values are ‘1’ to MaxPorts" */ @@ -2069,10 +2064,8 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports, struct xhci_port *hw_port = &xhci->hw_ports[i]; /* Duplicate entry. Ignore the port if the revisions differ. */ if (hw_port->rhub) { - xhci_warn(xhci, "Duplicate port entry, Ext Cap %p," - " port %u\n", addr, i); - xhci_warn(xhci, "Port was marked as USB %u, " - "duplicated as USB %u\n", + xhci_warn(xhci, "Duplicate port entry, Ext Cap %p, port %u\n", addr, i); + xhci_warn(xhci, "Port was marked as USB %u, duplicated as USB %u\n", hw_port->rhub->maj_rev, major_revision); /* Only adjust the roothub port counts if we haven't * found a similar duplicate. @@ -2411,8 +2404,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) val = readl(&xhci->cap_regs->db_off); val &= DBOFF_MASK; xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "// Doorbell array is located at offset 0x%x" - " from cap regs base addr", val); + "// Doorbell array is located at offset 0x%x from cap regs base addr", + val); xhci->dba = (void __iomem *) xhci->cap_regs + val; /* Set ir_set to interrupt register set 0 */ -- GitLab From edf1664f3249a091a2b91182fc087b3253b0b4c2 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Fri, 17 Mar 2023 17:47:09 +0200 Subject: [PATCH 1164/5631] xhci: dbc: Provide sysfs option to configure dbc descriptors When DbC is enabled the first port on the xHC host acts as a usb device. xHC provides the descriptors automatically when the DbC device is enumerated. Most of the values are hardcoded, but some fields such as idProduct, idVendor, bcdDevice and bInterfaceProtocol can be modified. Add sysfs entries that allow userspace to change these. User can only change them before dbc is enabled, i.e. before writing "enable" to dbc sysfs file as we don't want these values to change while device is connected, or during enumeration. Add documentation for these entries in Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-9-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- .../testing/sysfs-bus-pci-drivers-xhci_hcd | 52 +++++ drivers/usb/host/xhci-dbgcap.c | 191 +++++++++++++++++- drivers/usb/host/xhci-dbgcap.h | 4 + 3 files changed, 243 insertions(+), 4 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd index 0088aba4caa8..5a775b8f6543 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd +++ b/Documentation/ABI/testing/sysfs-bus-pci-drivers-xhci_hcd @@ -23,3 +23,55 @@ Description: Reading this attribute gives the state of the DbC. It can be one of the following states: disabled, enabled, initialized, connected, configured and stalled. + +What: /sys/bus/pci/drivers/xhci_hcd/.../dbc_idVendor +Date: March 2023 +Contact: Mathias Nyman +Description: + This dbc_idVendor attribute lets us change the idVendor field + presented in the USB device descriptor by this xhci debug + device. + Value can only be changed while debug capability (DbC) is in + disabled state to prevent USB device descriptor change while + connected to a USB host. + The default value is 0x1d6b (Linux Foundation). + It can be any 16-bit integer. + +What: /sys/bus/pci/drivers/xhci_hcd/.../dbc_idProduct +Date: March 2023 +Contact: Mathias Nyman +Description: + This dbc_idProduct attribute lets us change the idProduct field + presented in the USB device descriptor by this xhci debug + device. + Value can only be changed while debug capability (DbC) is in + disabled state to prevent USB device descriptor change while + connected to a USB host. + The default value is 0x0010. It can be any 16-bit integer. + +What: /sys/bus/pci/drivers/xhci_hcd/.../dbc_bcdDevice +Date: March 2023 +Contact: Mathias Nyman +Description: + This dbc_bcdDevice attribute lets us change the bcdDevice field + presented in the USB device descriptor by this xhci debug + device. + Value can only be changed while debug capability (DbC) is in + disabled state to prevent USB device descriptor change while + connected to a USB host. + The default value is 0x0010. (device rev 0.10) + It can be any 16-bit integer. + +What: /sys/bus/pci/drivers/xhci_hcd/.../dbc_bInterfaceProtocol +Date: March 2023 +Contact: Mathias Nyman +Description: + This attribute lets us change the bInterfaceProtocol field + presented in the USB Interface descriptor by the xhci debug + device. + Value can only be changed while debug capability (DbC) is in + disabled state to prevent USB descriptor change while + connected to a USB host. + The default value is 1 (GNU Remote Debug command). + Other permissible value is 0 which is for vendor defined debug + target. diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index f1367b53b260..b40d9238d447 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -124,10 +124,10 @@ static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length) /* Set DbC context and info registers: */ lo_hi_writeq(dbc->ctx->dma, &dbc->regs->dccp); - dev_info = cpu_to_le32((DBC_VENDOR_ID << 16) | DBC_PROTOCOL); + dev_info = (dbc->idVendor << 16) | dbc->bInterfaceProtocol; writel(dev_info, &dbc->regs->devinfo1); - dev_info = cpu_to_le32((DBC_DEVICE_REV << 16) | DBC_PRODUCT_ID); + dev_info = (dbc->bcdDevice << 16) | dbc->idProduct; writel(dev_info, &dbc->regs->devinfo2); } @@ -971,7 +971,186 @@ static ssize_t dbc_store(struct device *dev, return count; } +static ssize_t dbc_idVendor_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + + return sprintf(buf, "%04x\n", dbc->idVendor); +} + +static ssize_t dbc_idVendor_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + void __iomem *ptr; + u16 value; + u32 dev_info; + + if (kstrtou16(buf, 0, &value)) + return -EINVAL; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + if (dbc->state != DS_DISABLED) + return -EBUSY; + + dbc->idVendor = value; + ptr = &dbc->regs->devinfo1; + dev_info = readl(ptr); + dev_info = (dev_info & ~(0xffffu << 16)) | (value << 16); + writel(dev_info, ptr); + + return size; +} + +static ssize_t dbc_idProduct_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + + return sprintf(buf, "%04x\n", dbc->idProduct); +} + +static ssize_t dbc_idProduct_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + void __iomem *ptr; + u32 dev_info; + u16 value; + + if (kstrtou16(buf, 0, &value)) + return -EINVAL; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + if (dbc->state != DS_DISABLED) + return -EBUSY; + + dbc->idProduct = value; + ptr = &dbc->regs->devinfo2; + dev_info = readl(ptr); + dev_info = (dev_info & ~(0xffffu)) | value; + writel(dev_info, ptr); + return size; +} + +static ssize_t dbc_bcdDevice_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + + return sprintf(buf, "%04x\n", dbc->bcdDevice); +} + +static ssize_t dbc_bcdDevice_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + void __iomem *ptr; + u32 dev_info; + u16 value; + + if (kstrtou16(buf, 0, &value)) + return -EINVAL; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + if (dbc->state != DS_DISABLED) + return -EBUSY; + + dbc->bcdDevice = value; + ptr = &dbc->regs->devinfo2; + dev_info = readl(ptr); + dev_info = (dev_info & ~(0xffffu << 16)) | (value << 16); + writel(dev_info, ptr); + + return size; +} + +static ssize_t dbc_bInterfaceProtocol_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + + return sprintf(buf, "%02x\n", dbc->bInterfaceProtocol); +} + +static ssize_t dbc_bInterfaceProtocol_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct xhci_dbc *dbc; + struct xhci_hcd *xhci; + void __iomem *ptr; + u32 dev_info; + u8 value; + int ret; + + /* bInterfaceProtocol is 8 bit, but xhci only supports values 0 and 1 */ + ret = kstrtou8(buf, 0, &value); + if (ret || value > 1) + return -EINVAL; + + xhci = hcd_to_xhci(dev_get_drvdata(dev)); + dbc = xhci->dbc; + if (dbc->state != DS_DISABLED) + return -EBUSY; + + dbc->bInterfaceProtocol = value; + ptr = &dbc->regs->devinfo1; + dev_info = readl(ptr); + dev_info = (dev_info & ~(0xffu)) | value; + writel(dev_info, ptr); + + return size; +} + static DEVICE_ATTR_RW(dbc); +static DEVICE_ATTR_RW(dbc_idVendor); +static DEVICE_ATTR_RW(dbc_idProduct); +static DEVICE_ATTR_RW(dbc_bcdDevice); +static DEVICE_ATTR_RW(dbc_bInterfaceProtocol); + +static struct attribute *dbc_dev_attributes[] = { + &dev_attr_dbc.attr, + &dev_attr_dbc_idVendor.attr, + &dev_attr_dbc_idProduct.attr, + &dev_attr_dbc_bcdDevice.attr, + &dev_attr_dbc_bInterfaceProtocol.attr, + NULL +}; + +static const struct attribute_group dbc_dev_attrib_grp = { + .attrs = dbc_dev_attributes, +}; struct xhci_dbc * xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver *driver) @@ -986,6 +1165,10 @@ xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver * dbc->regs = base; dbc->dev = dev; dbc->driver = driver; + dbc->idProduct = DBC_PRODUCT_ID; + dbc->idVendor = DBC_VENDOR_ID; + dbc->bcdDevice = DBC_DEVICE_REV; + dbc->bInterfaceProtocol = DBC_PROTOCOL; if (readl(&dbc->regs->control) & DBC_CTRL_DBC_ENABLE) goto err; @@ -993,7 +1176,7 @@ xhci_alloc_dbc(struct device *dev, void __iomem *base, const struct dbc_driver * INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events); spin_lock_init(&dbc->lock); - ret = device_create_file(dev, &dev_attr_dbc); + ret = sysfs_create_group(&dev->kobj, &dbc_dev_attrib_grp); if (ret) goto err; @@ -1012,7 +1195,7 @@ void xhci_dbc_remove(struct xhci_dbc *dbc) xhci_dbc_stop(dbc); /* remove sysfs files */ - device_remove_file(dbc->dev, &dev_attr_dbc); + sysfs_remove_group(&dbc->dev->kobj, &dbc_dev_attrib_grp); kfree(dbc); } diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index ca04192fdab1..51a7ab3ba0ca 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -132,6 +132,10 @@ struct xhci_dbc { struct dbc_str_descs *string; dma_addr_t string_dma; size_t string_size; + u16 idVendor; + u16 idProduct; + u16 bcdDevice; + u8 bInterfaceProtocol; enum dbc_state state; struct delayed_work event_work; -- GitLab From 944e7deb4238d10cd16905474574236ac8a8e847 Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:10 +0200 Subject: [PATCH 1165/5631] xhci: Avoid PCI MSI/MSIX interrupt reinitialization at resume xhci MSI setup is currently done at the same time as xHC host is started in xhci_run(). This couples the generic xhci code with PCI, and will reconfigure MSI/MSIX interrupts every time xHC is started. Decouple MSI/MSIX configuration from generic xhci code by moving MSI/MSIX part to a PCI specific xhci_pci_run() function overriding xhci_run(). This allows us to remove unnecessay MSI/MSIX reconfiguration done every time PCI xhci resumes from suspend. i.e. remove the xhci_cleanup_msix() call from xhci_resume() and the xhci_try_enale_msi() call in xhci_run() called a bit later by xhci_resume() [minor changes and commit message rewrite -Mathias] Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-10-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 15 +++++++++++++++ drivers/usb/host/xhci.c | 8 ++------ drivers/usb/host/xhci.h | 1 + 3 files changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index fb988e4ea924..5f006d199cd6 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -78,14 +78,29 @@ static const char hcd_name[] = "xhci_hcd"; static struct hc_driver __read_mostly xhci_pci_hc_driver; static int xhci_pci_setup(struct usb_hcd *hcd); +static int xhci_pci_run(struct usb_hcd *hcd); static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags); static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .reset = xhci_pci_setup, + .start = xhci_pci_run, .update_hub_device = xhci_pci_update_hub_device, }; +static int xhci_pci_run(struct usb_hcd *hcd) +{ + int ret; + + if (usb_hcd_is_primary_hcd(hcd)) { + ret = xhci_try_enable_msi(hcd); + if (ret) + return ret; + } + + return xhci_run(hcd); +} + /* called after powerup, by probe or system-pm "wakeup" */ static int xhci_pci_reinit(struct xhci_hcd *xhci, struct pci_dev *pdev) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 6183ce8574b1..d08e2ba744f8 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -432,7 +432,7 @@ static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) } } -static int xhci_try_enable_msi(struct usb_hcd *hcd) +int xhci_try_enable_msi(struct usb_hcd *hcd) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct pci_dev *pdev; @@ -486,6 +486,7 @@ static int xhci_try_enable_msi(struct usb_hcd *hcd) hcd->irq = pdev->irq; return 0; } +EXPORT_SYMBOL_GPL(xhci_try_enable_msi); #else @@ -701,10 +702,6 @@ int xhci_run(struct usb_hcd *hcd) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_run"); - ret = xhci_try_enable_msi(hcd); - if (ret) - return ret; - temp_64 = xhci_read_64(xhci, &ir->ir_set->erst_dequeue); temp_64 &= ~ERST_PTR_MASK; xhci_dbg_trace(xhci, trace_xhci_dbg_init, @@ -1246,7 +1243,6 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) spin_unlock_irq(&xhci->lock); if (retval) return retval; - xhci_cleanup_msix(xhci); xhci_dbg(xhci, "// Disabling event ring interrupts\n"); temp = readl(&xhci->op_regs->status); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 786002bb35db..26fccc8d9055 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2143,6 +2143,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated); irqreturn_t xhci_irq(struct usb_hcd *hcd); irqreturn_t xhci_msi_irq(int irq, void *hcd); +int xhci_try_enable_msi(struct usb_hcd *hcd); int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev); int xhci_alloc_tt_info(struct xhci_hcd *xhci, struct xhci_virt_device *virt_dev, -- GitLab From fabbd95cc47cc412e68d03476367046f4cdbd838 Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:11 +0200 Subject: [PATCH 1166/5631] xhci: Move functions to setup msi to xhci-pci Move functions to setup msi from xhci.c to xhci-pci.c to decouple PCI specific code from generic xhci code. No functional changes, functions are an exact copy [commit message rewording -Mathias] Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-11-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 129 ++++++++++++++++++++++++++++++++ drivers/usb/host/xhci-ring.c | 1 + drivers/usb/host/xhci-trace.c | 1 + drivers/usb/host/xhci.c | 134 ---------------------------------- drivers/usb/host/xhci.h | 1 - 5 files changed, 131 insertions(+), 135 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 5f006d199cd6..2d56b7477fcd 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -88,6 +88,135 @@ static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .update_hub_device = xhci_pci_update_hub_device, }; +/* + * Set up MSI + */ +static int xhci_setup_msi(struct xhci_hcd *xhci) +{ + int ret; + /* + * TODO:Check with MSI Soc for sysdev + */ + struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + xhci_dbg_trace(xhci, trace_xhci_dbg_init, + "failed to allocate MSI entry"); + return ret; + } + + ret = request_irq(pdev->irq, xhci_msi_irq, + 0, "xhci_hcd", xhci_to_hcd(xhci)); + if (ret) { + xhci_dbg_trace(xhci, trace_xhci_dbg_init, + "disable MSI interrupt"); + pci_free_irq_vectors(pdev); + } + + return ret; +} + +/* + * Set up MSI-X + */ +static int xhci_setup_msix(struct xhci_hcd *xhci) +{ + int i, ret; + struct usb_hcd *hcd = xhci_to_hcd(xhci); + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + + /* + * calculate number of msi-x vectors supported. + * - HCS_MAX_INTRS: the max number of interrupts the host can handle, + * with max number of interrupters based on the xhci HCSPARAMS1. + * - num_online_cpus: maximum msi-x vectors per CPUs core. + * Add additional 1 vector to ensure always available interrupt. + */ + xhci->msix_count = min(num_online_cpus() + 1, + HCS_MAX_INTRS(xhci->hcs_params1)); + + ret = pci_alloc_irq_vectors(pdev, xhci->msix_count, xhci->msix_count, + PCI_IRQ_MSIX); + if (ret < 0) { + xhci_dbg_trace(xhci, trace_xhci_dbg_init, + "Failed to enable MSI-X"); + return ret; + } + + for (i = 0; i < xhci->msix_count; i++) { + ret = request_irq(pci_irq_vector(pdev, i), xhci_msi_irq, 0, + "xhci_hcd", xhci_to_hcd(xhci)); + if (ret) + goto disable_msix; + } + + hcd->msix_enabled = 1; + return ret; + +disable_msix: + xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt"); + while (--i >= 0) + free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci)); + pci_free_irq_vectors(pdev); + return ret; +} + +static int xhci_try_enable_msi(struct usb_hcd *hcd) +{ + struct xhci_hcd *xhci = hcd_to_xhci(hcd); + struct pci_dev *pdev; + int ret; + + /* The xhci platform device has set up IRQs through usb_add_hcd. */ + if (xhci->quirks & XHCI_PLAT) + return 0; + + pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); + /* + * Some Fresco Logic host controllers advertise MSI, but fail to + * generate interrupts. Don't even try to enable MSI. + */ + if (xhci->quirks & XHCI_BROKEN_MSI) + goto legacy_irq; + + /* unregister the legacy interrupt */ + if (hcd->irq) + free_irq(hcd->irq, hcd); + hcd->irq = 0; + + ret = xhci_setup_msix(xhci); + if (ret) + /* fall back to msi*/ + ret = xhci_setup_msi(xhci); + + if (!ret) { + hcd->msi_enabled = 1; + return 0; + } + + if (!pdev->irq) { + xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n"); + return -EINVAL; + } + + legacy_irq: + if (!strlen(hcd->irq_descr)) + snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d", + hcd->driver->description, hcd->self.busnum); + + /* fall back to legacy interrupt*/ + ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED, + hcd->irq_descr, hcd); + if (ret) { + xhci_err(xhci, "request interrupt %d failed\n", + pdev->irq); + return ret; + } + hcd->irq = pdev->irq; + return 0; +} + static int xhci_pci_run(struct usb_hcd *hcd) { int ret; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index eb788c60c1c0..1ad12d5a4857 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3106,6 +3106,7 @@ irqreturn_t xhci_msi_irq(int irq, void *hcd) { return xhci_irq(hcd); } +EXPORT_SYMBOL_GPL(xhci_msi_irq); /**** Endpoint Ring Operations ****/ diff --git a/drivers/usb/host/xhci-trace.c b/drivers/usb/host/xhci-trace.c index d0070814d1ea..062662d23241 100644 --- a/drivers/usb/host/xhci-trace.c +++ b/drivers/usb/host/xhci-trace.c @@ -12,3 +12,4 @@ #include "xhci-trace.h" EXPORT_TRACEPOINT_SYMBOL_GPL(xhci_dbg_quirks); +EXPORT_TRACEPOINT_SYMBOL_GPL(xhci_dbg_init); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index d08e2ba744f8..9be84e635e1b 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -319,79 +319,6 @@ static int xhci_disable_interrupter(struct xhci_interrupter *ir) } #ifdef CONFIG_USB_PCI -/* - * Set up MSI - */ -static int xhci_setup_msi(struct xhci_hcd *xhci) -{ - int ret; - /* - * TODO:Check with MSI Soc for sysdev - */ - struct pci_dev *pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); - - ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); - if (ret < 0) { - xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "failed to allocate MSI entry"); - return ret; - } - - ret = request_irq(pdev->irq, xhci_msi_irq, - 0, "xhci_hcd", xhci_to_hcd(xhci)); - if (ret) { - xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "disable MSI interrupt"); - pci_free_irq_vectors(pdev); - } - - return ret; -} - -/* - * Set up MSI-X - */ -static int xhci_setup_msix(struct xhci_hcd *xhci) -{ - int i, ret; - struct usb_hcd *hcd = xhci_to_hcd(xhci); - struct pci_dev *pdev = to_pci_dev(hcd->self.controller); - - /* - * calculate number of msi-x vectors supported. - * - HCS_MAX_INTRS: the max number of interrupts the host can handle, - * with max number of interrupters based on the xhci HCSPARAMS1. - * - num_online_cpus: maximum msi-x vectors per CPUs core. - * Add additional 1 vector to ensure always available interrupt. - */ - xhci->msix_count = min(num_online_cpus() + 1, - HCS_MAX_INTRS(xhci->hcs_params1)); - - ret = pci_alloc_irq_vectors(pdev, xhci->msix_count, xhci->msix_count, - PCI_IRQ_MSIX); - if (ret < 0) { - xhci_dbg_trace(xhci, trace_xhci_dbg_init, - "Failed to enable MSI-X"); - return ret; - } - - for (i = 0; i < xhci->msix_count; i++) { - ret = request_irq(pci_irq_vector(pdev, i), xhci_msi_irq, 0, - "xhci_hcd", xhci_to_hcd(xhci)); - if (ret) - goto disable_msix; - } - - hcd->msix_enabled = 1; - return ret; - -disable_msix: - xhci_dbg_trace(xhci, trace_xhci_dbg_init, "disable MSI-X interrupt"); - while (--i >= 0) - free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci)); - pci_free_irq_vectors(pdev); - return ret; -} /* Free any IRQs and disable MSI-X */ static void xhci_cleanup_msix(struct xhci_hcd *xhci) @@ -432,69 +359,8 @@ static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) } } -int xhci_try_enable_msi(struct usb_hcd *hcd) -{ - struct xhci_hcd *xhci = hcd_to_xhci(hcd); - struct pci_dev *pdev; - int ret; - - /* The xhci platform device has set up IRQs through usb_add_hcd. */ - if (xhci->quirks & XHCI_PLAT) - return 0; - - pdev = to_pci_dev(xhci_to_hcd(xhci)->self.controller); - /* - * Some Fresco Logic host controllers advertise MSI, but fail to - * generate interrupts. Don't even try to enable MSI. - */ - if (xhci->quirks & XHCI_BROKEN_MSI) - goto legacy_irq; - - /* unregister the legacy interrupt */ - if (hcd->irq) - free_irq(hcd->irq, hcd); - hcd->irq = 0; - - ret = xhci_setup_msix(xhci); - if (ret) - /* fall back to msi*/ - ret = xhci_setup_msi(xhci); - - if (!ret) { - hcd->msi_enabled = 1; - return 0; - } - - if (!pdev->irq) { - xhci_err(xhci, "No msi-x/msi found and no IRQ in BIOS\n"); - return -EINVAL; - } - - legacy_irq: - if (!strlen(hcd->irq_descr)) - snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d", - hcd->driver->description, hcd->self.busnum); - - /* fall back to legacy interrupt*/ - ret = request_irq(pdev->irq, &usb_hcd_irq, IRQF_SHARED, - hcd->irq_descr, hcd); - if (ret) { - xhci_err(xhci, "request interrupt %d failed\n", - pdev->irq); - return ret; - } - hcd->irq = pdev->irq; - return 0; -} -EXPORT_SYMBOL_GPL(xhci_try_enable_msi); - #else -static inline int xhci_try_enable_msi(struct usb_hcd *hcd) -{ - return 0; -} - static inline void xhci_cleanup_msix(struct xhci_hcd *xhci) { } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 26fccc8d9055..786002bb35db 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2143,7 +2143,6 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated); irqreturn_t xhci_irq(struct usb_hcd *hcd); irqreturn_t xhci_msi_irq(int irq, void *hcd); -int xhci_try_enable_msi(struct usb_hcd *hcd); int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev); int xhci_alloc_tt_info(struct xhci_hcd *xhci, struct xhci_virt_device *virt_dev, -- GitLab From ed526ba2ecdfb77bcdbcf4331b8380b646252c20 Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:12 +0200 Subject: [PATCH 1167/5631] xhci: move PCI specific MSI/MSIX cleanup away from generic xhci functions Call the PCI specific MSI/MSIX interrupt freeing code from the xhci-pci callbacks instead of generic xhci code, decoupling PCI parts from generic xhci functions. Adds xhci_pci_stop() that overrides xhci_stop() for PCI xHC controllers. This will free MSIX interrupts a bit later in the hc_driver stop callback, but is still earlier than usb core frees "legacy" interrupts, or interrupts for other hosts. Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-12-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 12 ++++++++++++ drivers/usb/host/xhci.c | 10 ++++------ drivers/usb/host/xhci.h | 2 ++ 3 files changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 2d56b7477fcd..b6cfc028f8f7 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -230,6 +230,16 @@ static int xhci_pci_run(struct usb_hcd *hcd) return xhci_run(hcd); } +static void xhci_pci_stop(struct usb_hcd *hcd) +{ + struct xhci_hcd *xhci = hcd_to_xhci(hcd); + + xhci_stop(hcd); + + if (usb_hcd_is_primary_hcd(hcd)) + xhci_cleanup_msix(xhci); +} + /* called after powerup, by probe or system-pm "wakeup" */ static int xhci_pci_reinit(struct xhci_hcd *xhci, struct pci_dev *pdev) { @@ -868,6 +878,7 @@ static void xhci_pci_shutdown(struct usb_hcd *hcd) struct pci_dev *pdev = to_pci_dev(hcd->self.controller); xhci_shutdown(hcd); + xhci_cleanup_msix(xhci); /* Yet another workaround for spurious wakeups at shutdown with HSW */ if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) @@ -932,6 +943,7 @@ static int __init xhci_pci_init(void) xhci_pci_hc_driver.pci_poweroff_late = xhci_pci_poweroff_late; xhci_pci_hc_driver.shutdown = xhci_pci_shutdown; #endif + xhci_pci_hc_driver.stop = xhci_pci_stop; return pci_register_driver(&xhci_pci_driver); } module_init(xhci_pci_init); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 9be84e635e1b..cf90751125ed 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -321,7 +321,7 @@ static int xhci_disable_interrupter(struct xhci_interrupter *ir) #ifdef CONFIG_USB_PCI /* Free any IRQs and disable MSI-X */ -static void xhci_cleanup_msix(struct xhci_hcd *xhci) +void xhci_cleanup_msix(struct xhci_hcd *xhci) { struct usb_hcd *hcd = xhci_to_hcd(xhci); struct pci_dev *pdev = to_pci_dev(hcd->self.controller); @@ -345,6 +345,7 @@ static void xhci_cleanup_msix(struct xhci_hcd *xhci) pci_free_irq_vectors(pdev); hcd->msix_enabled = 0; } +EXPORT_SYMBOL_GPL(xhci_cleanup_msix); static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) { @@ -617,7 +618,7 @@ EXPORT_SYMBOL_GPL(xhci_run); * Disable device contexts, disable IRQs, and quiesce the HC. * Reset the HC, finish any completed transactions, and cleanup memory. */ -static void xhci_stop(struct usb_hcd *hcd) +void xhci_stop(struct usb_hcd *hcd) { u32 temp; struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -640,8 +641,6 @@ static void xhci_stop(struct usb_hcd *hcd) xhci_reset(xhci, XHCI_RESET_SHORT_USEC); spin_unlock_irq(&xhci->lock); - xhci_cleanup_msix(xhci); - /* Deleting Compliance Mode Recovery Timer */ if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && (!(xhci_all_ports_seen_u0(xhci)))) { @@ -668,6 +667,7 @@ static void xhci_stop(struct usb_hcd *hcd) readl(&xhci->op_regs->status)); mutex_unlock(&xhci->mutex); } +EXPORT_SYMBOL_GPL(xhci_stop); /* * Shutdown HC (not bus-specific) @@ -709,8 +709,6 @@ void xhci_shutdown(struct usb_hcd *hcd) spin_unlock_irq(&xhci->lock); - xhci_cleanup_msix(xhci); - xhci_dbg_trace(xhci, trace_xhci_dbg_init, "xhci_shutdown completed - status = %x", readl(&xhci->op_regs->status)); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 786002bb35db..a9111260632c 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2125,6 +2125,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us); int xhci_run(struct usb_hcd *hcd); int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks); void xhci_shutdown(struct usb_hcd *hcd); +void xhci_stop(struct usb_hcd *hcd); void xhci_init_driver(struct hc_driver *drv, const struct xhci_driver_overrides *over); int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, @@ -2143,6 +2144,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated); irqreturn_t xhci_irq(struct usb_hcd *hcd); irqreturn_t xhci_msi_irq(int irq, void *hcd); +void xhci_cleanup_msix(struct xhci_hcd *xhci); int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev); int xhci_alloc_tt_info(struct xhci_hcd *xhci, struct xhci_virt_device *virt_dev, -- GitLab From ba47b1aa7640cb98bb3e4c06f37afdbeb5c5d9ba Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:13 +0200 Subject: [PATCH 1168/5631] xhci: Move functions to cleanup MSI to xhci-pci Move function to cleanup MSI from xhci.c to xhci-pci.c This is to decouple PCI specific code from generic xhci code. No functional changes, function is an exact copy Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-13-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 26 ++++++++++++++++++++++++++ drivers/usb/host/xhci.c | 31 ------------------------------- drivers/usb/host/xhci.h | 1 - 3 files changed, 26 insertions(+), 32 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index b6cfc028f8f7..1e84a842e2a9 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -88,6 +88,32 @@ static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .update_hub_device = xhci_pci_update_hub_device, }; +/* Free any IRQs and disable MSI-X */ +static void xhci_cleanup_msix(struct xhci_hcd *xhci) +{ + struct usb_hcd *hcd = xhci_to_hcd(xhci); + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + + if (xhci->quirks & XHCI_PLAT) + return; + + /* return if using legacy interrupt */ + if (hcd->irq > 0) + return; + + if (hcd->msix_enabled) { + int i; + + for (i = 0; i < xhci->msix_count; i++) + free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci)); + } else { + free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci)); + } + + pci_free_irq_vectors(pdev); + hcd->msix_enabled = 0; +} + /* * Set up MSI */ diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index cf90751125ed..874dca6dec69 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -320,33 +320,6 @@ static int xhci_disable_interrupter(struct xhci_interrupter *ir) #ifdef CONFIG_USB_PCI -/* Free any IRQs and disable MSI-X */ -void xhci_cleanup_msix(struct xhci_hcd *xhci) -{ - struct usb_hcd *hcd = xhci_to_hcd(xhci); - struct pci_dev *pdev = to_pci_dev(hcd->self.controller); - - if (xhci->quirks & XHCI_PLAT) - return; - - /* return if using legacy interrupt */ - if (hcd->irq > 0) - return; - - if (hcd->msix_enabled) { - int i; - - for (i = 0; i < xhci->msix_count; i++) - free_irq(pci_irq_vector(pdev, i), xhci_to_hcd(xhci)); - } else { - free_irq(pci_irq_vector(pdev, 0), xhci_to_hcd(xhci)); - } - - pci_free_irq_vectors(pdev); - hcd->msix_enabled = 0; -} -EXPORT_SYMBOL_GPL(xhci_cleanup_msix); - static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) { struct usb_hcd *hcd = xhci_to_hcd(xhci); @@ -362,10 +335,6 @@ static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) #else -static inline void xhci_cleanup_msix(struct xhci_hcd *xhci) -{ -} - static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci) { } diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index a9111260632c..08d721921b7b 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -2144,7 +2144,6 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated); irqreturn_t xhci_irq(struct usb_hcd *hcd); irqreturn_t xhci_msi_irq(int irq, void *hcd); -void xhci_cleanup_msix(struct xhci_hcd *xhci); int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev); int xhci_alloc_tt_info(struct xhci_hcd *xhci, struct xhci_virt_device *virt_dev, -- GitLab From 0c540438c632005ce57f45436a25cafa499d977f Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:14 +0200 Subject: [PATCH 1169/5631] xhci: Call MSI sync function from xhci-pci instead of generic xhci code Call function to sync MSI interrupts from pci specific xhci_pci_suspend() function in xhci-pci.c instead of from generic xhci_suspend() [commit message rewording -Mathias] Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-14-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 5 +++++ drivers/usb/host/xhci.c | 7 ++----- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 1e84a842e2a9..ef55cadc8d14 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -779,6 +779,7 @@ static void xhci_sparse_control_quirk(struct usb_hcd *hcd) writel(reg, hcd->regs + SPARSE_CNTL_ENABLE); } +extern void xhci_msix_sync_irqs(struct xhci_hcd *xhci); static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -802,6 +803,10 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) xhci_sparse_control_quirk(hcd); ret = xhci_suspend(xhci, do_wakeup); + + /* synchronize irq when using MSI-X */ + xhci_msix_sync_irqs(xhci); + if (ret && (xhci->quirks & XHCI_SSIC_PORT_UNUSED)) xhci_ssic_port_unused_quirk(hcd, false); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 874dca6dec69..c0fb34ccd187 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -320,7 +320,7 @@ static int xhci_disable_interrupter(struct xhci_interrupter *ir) #ifdef CONFIG_USB_PCI -static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) +void xhci_msix_sync_irqs(struct xhci_hcd *xhci) { struct usb_hcd *hcd = xhci_to_hcd(xhci); @@ -332,6 +332,7 @@ static void __maybe_unused xhci_msix_sync_irqs(struct xhci_hcd *xhci) synchronize_irq(pci_irq_vector(pdev, i)); } } +EXPORT_SYMBOL_GPL(xhci_msix_sync_irqs); #else @@ -969,10 +970,6 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup) __func__); } - /* step 5: remove core well power */ - /* synchronize irq when using MSI-X */ - xhci_msix_sync_irqs(xhci); - return rc; } EXPORT_SYMBOL_GPL(xhci_suspend); -- GitLab From 9abe15d55dccec92d361705741ee80f13b4d0888 Mon Sep 17 00:00:00 2001 From: Josue David Hernandez Gutierrez Date: Fri, 17 Mar 2023 17:47:15 +0200 Subject: [PATCH 1170/5631] xhci: Move xhci MSI sync function to to xhci-pci Move function to sync MSI from xhci.c to xhci-pci.c to decouple PCI specific code from generic xhci code. No functional changes, function is an exact copy [commit message rewording -Mathias] Signed-off-by: Josue David Hernandez Gutierrez Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230317154715.535523-15-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 14 +++++++++++++- drivers/usb/host/xhci.c | 24 ------------------------ 2 files changed, 13 insertions(+), 25 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ef55cadc8d14..a53ecc8ff8c5 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -88,6 +88,19 @@ static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .update_hub_device = xhci_pci_update_hub_device, }; +static void xhci_msix_sync_irqs(struct xhci_hcd *xhci) +{ + struct usb_hcd *hcd = xhci_to_hcd(xhci); + + if (hcd->msix_enabled) { + struct pci_dev *pdev = to_pci_dev(hcd->self.controller); + int i; + + for (i = 0; i < xhci->msix_count; i++) + synchronize_irq(pci_irq_vector(pdev, i)); + } +} + /* Free any IRQs and disable MSI-X */ static void xhci_cleanup_msix(struct xhci_hcd *xhci) { @@ -779,7 +792,6 @@ static void xhci_sparse_control_quirk(struct usb_hcd *hcd) writel(reg, hcd->regs + SPARSE_CNTL_ENABLE); } -extern void xhci_msix_sync_irqs(struct xhci_hcd *xhci); static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index c0fb34ccd187..cc9fde8cba78 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -318,30 +318,6 @@ static int xhci_disable_interrupter(struct xhci_interrupter *ir) return 0; } -#ifdef CONFIG_USB_PCI - -void xhci_msix_sync_irqs(struct xhci_hcd *xhci) -{ - struct usb_hcd *hcd = xhci_to_hcd(xhci); - - if (hcd->msix_enabled) { - struct pci_dev *pdev = to_pci_dev(hcd->self.controller); - int i; - - for (i = 0; i < xhci->msix_count; i++) - synchronize_irq(pci_irq_vector(pdev, i)); - } -} -EXPORT_SYMBOL_GPL(xhci_msix_sync_irqs); - -#else - -static inline void xhci_msix_sync_irqs(struct xhci_hcd *xhci) -{ -} - -#endif - static void compliance_mode_recovery(struct timer_list *t) { struct xhci_hcd *xhci; -- GitLab From 1fb1ea0d9cb8359ae9d6f67f22666c74d5b9f47d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 10 Mar 2023 19:07:47 +0200 Subject: [PATCH 1171/5631] mei: Move uuid.h to the MEI namespace There is only a single user of the UUID uAPI, let's make it part of that user. The way it's done is to prevent compilation time breakage for the user space that does #include In the future MEI user space tools can switch over to use mei_uuid.h. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230310170747.22782-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 1 + drivers/misc/mei/bus-fixup.c | 2 +- drivers/misc/mei/hdcp/mei_hdcp.c | 2 +- drivers/misc/mei/hw.h | 2 +- drivers/misc/mei/main.c | 1 - drivers/misc/mei/pxp/mei_pxp.c | 2 +- include/linux/mod_devicetable.h | 1 + include/linux/uuid.h | 3 --- include/uapi/linux/mei.h | 2 +- include/uapi/linux/mei_uuid.h | 29 +++++++++++++++++++++++++++++ include/uapi/linux/uuid.h | 31 +------------------------------ 11 files changed, 37 insertions(+), 39 deletions(-) create mode 100644 include/uapi/linux/mei_uuid.h diff --git a/MAINTAINERS b/MAINTAINERS index 7ee30a356e89..619c30ec36dc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10459,6 +10459,7 @@ F: drivers/watchdog/mei_wdt.c F: include/linux/mei_aux.h F: include/linux/mei_cl_bus.h F: include/uapi/linux/mei.h +F: include/uapi/linux/mei_uuid.h F: include/uapi/linux/uuid.h F: samples/mei/* diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index 211536109308..31e3c74ca1f1 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -9,8 +9,8 @@ #include #include #include -#include +#include #include #include "mei_dev.h" diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c index e0dcd5c114db..45e3d4d27797 100644 --- a/drivers/misc/mei/hdcp/mei_hdcp.c +++ b/drivers/misc/mei/hdcp/mei_hdcp.c @@ -18,7 +18,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index 319418ddf4fb..e910302fcd1f 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -7,7 +7,7 @@ #ifndef _MEI_HW_TYPES_H_ #define _MEI_HW_TYPES_H_ -#include +#include /* * Timeouts in Seconds diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 632d4ae21e46..c64291741d73 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/misc/mei/pxp/mei_pxp.c b/drivers/misc/mei/pxp/mei_pxp.c index 7ee1fa7b1cb3..3bf560bbdee0 100644 --- a/drivers/misc/mei/pxp/mei_pxp.c +++ b/drivers/misc/mei/pxp/mei_pxp.c @@ -13,7 +13,7 @@ #include #include -#include +#include #include #include #include diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 549590e9c644..35203ca3fc37 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -9,6 +9,7 @@ #define LINUX_MOD_DEVICETABLE_H #ifdef __KERNEL__ +#include #include #include typedef unsigned long kernel_ulong_t; diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 6b1a3efa1e0b..43d4a79b273d 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -107,7 +107,4 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* MEI UUID type, don't use anywhere else */ -#include - #endif diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 4f3638489d01..6e57743628c0 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -7,7 +7,7 @@ #ifndef _LINUX_MEI_H #define _LINUX_MEI_H -#include +#include /* * This IOCTL is used to associate the current file descriptor with a diff --git a/include/uapi/linux/mei_uuid.h b/include/uapi/linux/mei_uuid.h new file mode 100644 index 000000000000..676ebe12d623 --- /dev/null +++ b/include/uapi/linux/mei_uuid.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * MEI UUID definition + * + * Copyright (C) 2010, Intel Corp. + * Huang Ying + */ + +#ifndef _UAPI_LINUX_MEI_UUID_H_ +#define _UAPI_LINUX_MEI_UUID_H_ + +#include + +typedef struct { + __u8 b[16]; +} uuid_le; + +#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ +((uuid_le) \ +{{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ + (b) & 0xff, ((b) >> 8) & 0xff, \ + (c) & 0xff, ((c) >> 8) & 0xff, \ + (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) + +#define NULL_UUID_LE \ + UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x00, 0x00, 0x00) + +#endif /* _UAPI_LINUX_MEI_UUID_H_ */ diff --git a/include/uapi/linux/uuid.h b/include/uapi/linux/uuid.h index 96ac684a4b2f..8443738f4bb2 100644 --- a/include/uapi/linux/uuid.h +++ b/include/uapi/linux/uuid.h @@ -1,30 +1 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* DO NOT USE in new code! This is solely for MEI due to legacy reasons */ -/* - * MEI UUID definition - * - * Copyright (C) 2010, Intel Corp. - * Huang Ying - */ - -#ifndef _UAPI_LINUX_UUID_H_ -#define _UAPI_LINUX_UUID_H_ - -#include - -typedef struct { - __u8 b[16]; -} uuid_le; - -#define UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ -((uuid_le) \ -{{ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ - (b) & 0xff, ((b) >> 8) & 0xff, \ - (c) & 0xff, ((c) >> 8) & 0xff, \ - (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) }}) - -#define NULL_UUID_LE \ - UUID_LE(0x00000000, 0x0000, 0x0000, 0x00, 0x00, 0x00, 0x00, \ - 0x00, 0x00, 0x00, 0x00) - -#endif /* _UAPI_LINUX_UUID_H_ */ +#include -- GitLab From a0c7f9f659825e9761f8db423001de4e5147b60c Mon Sep 17 00:00:00 2001 From: Xu Yang Date: Fri, 17 Mar 2023 14:16:51 +0800 Subject: [PATCH 1172/5631] usb: chipidea: debug: remove redundant 'role' debug file Two 'role' file exist in different position but with totally same function. 1. /sys/devices/platform/soc@0/xxxxxxxx.usb/ci_hdrc.0/role 2. /sys/kernel/debug/usb/ci_hdrc.0/role This will remove the 2rd redundant 'role' debug file (under debugfs) and keep the one which is more closer to user. Acked-by: Peter Chen Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20230317061651.2457567-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/debug.c | 55 ------------------------------------ 1 file changed, 55 deletions(-) diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index bbc610e5bd69..e72c43615d77 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -247,60 +247,6 @@ static int ci_otg_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(ci_otg); -static int ci_role_show(struct seq_file *s, void *data) -{ - struct ci_hdrc *ci = s->private; - - if (ci->role != CI_ROLE_END) - seq_printf(s, "%s\n", ci_role(ci)->name); - - return 0; -} - -static ssize_t ci_role_write(struct file *file, const char __user *ubuf, - size_t count, loff_t *ppos) -{ - struct seq_file *s = file->private_data; - struct ci_hdrc *ci = s->private; - enum ci_role role; - char buf[8]; - int ret; - - if (copy_from_user(buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) - return -EFAULT; - - for (role = CI_ROLE_HOST; role < CI_ROLE_END; role++) - if (ci->roles[role] && - !strncmp(buf, ci->roles[role]->name, - strlen(ci->roles[role]->name))) - break; - - if (role == CI_ROLE_END || role == ci->role) - return -EINVAL; - - pm_runtime_get_sync(ci->dev); - disable_irq(ci->irq); - ci_role_stop(ci); - ret = ci_role_start(ci, role); - enable_irq(ci->irq); - pm_runtime_put_sync(ci->dev); - - return ret ? ret : count; -} - -static int ci_role_open(struct inode *inode, struct file *file) -{ - return single_open(file, ci_role_show, inode->i_private); -} - -static const struct file_operations ci_role_fops = { - .open = ci_role_open, - .write = ci_role_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int ci_registers_show(struct seq_file *s, void *unused) { struct ci_hdrc *ci = s->private; @@ -354,7 +300,6 @@ void dbg_create_files(struct ci_hdrc *ci) if (ci_otg_is_fsm_mode(ci)) debugfs_create_file("otg", S_IRUGO, dir, ci, &ci_otg_fops); - debugfs_create_file("role", S_IRUGO | S_IWUSR, dir, ci, &ci_role_fops); debugfs_create_file("registers", S_IRUGO, dir, ci, &ci_registers_fops); } -- GitLab From 1ad715857018893776fd61706da5b2188d67c650 Mon Sep 17 00:00:00 2001 From: Yu Zhe Date: Thu, 16 Mar 2023 16:23:38 +0800 Subject: [PATCH 1173/5631] usb: typec: tcpm: remove unnecessary (void*) conversions Pointer variables of void * type do not require type cast. Signed-off-by: Yu Zhe Acked-by: Heikki Krogerus Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230316082338.18388-1-yuzhe@nfschina.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/fusb302.c | 2 +- drivers/usb/typec/tcpm/tcpm.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index 592b0aec782f..62ba53357612 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -190,7 +190,7 @@ static void fusb302_log(struct fusb302_chip *chip, const char *fmt, ...) static int fusb302_debug_show(struct seq_file *s, void *v) { - struct fusb302_chip *chip = (struct fusb302_chip *)s->private; + struct fusb302_chip *chip = s->private; int tail; mutex_lock(&chip->logbuffer_lock); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index a0d943d78580..e8bfe3f57ab4 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -737,7 +737,7 @@ static void tcpm_log_source_caps(struct tcpm_port *port) static int tcpm_debug_show(struct seq_file *s, void *v) { - struct tcpm_port *port = (struct tcpm_port *)s->private; + struct tcpm_port *port = s->private; int tail; mutex_lock(&port->logbuffer_lock); -- GitLab From a88b3c9eef83b605ef7016471a56db9129ae2529 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 19 Mar 2023 11:59:10 -0400 Subject: [PATCH 1174/5631] usb: gadget: udc: remove unused usbf_ep_dma_reg_clrset function clang with W=1 reports drivers/usb/gadget/udc/renesas_usbf.c:548:20: error: unused function 'usbf_ep_dma_reg_clrset' [-Werror,-Wunused-function] static inline void usbf_ep_dma_reg_clrset(struct usbf_ep *ep, uint offset, ^ This function is not used, so remove it. Signed-off-by: Tom Rix Acked-by: Herve Codina Link: https://lore.kernel.org/r/20230319155910.1706294-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/renesas_usbf.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/usb/gadget/udc/renesas_usbf.c b/drivers/usb/gadget/udc/renesas_usbf.c index cb23e62e8a87..84ac9fe4ce7f 100644 --- a/drivers/usb/gadget/udc/renesas_usbf.c +++ b/drivers/usb/gadget/udc/renesas_usbf.c @@ -545,17 +545,6 @@ static inline void usbf_ep_dma_reg_bitclr(struct usbf_ep *ep, uint offset, usbf_ep_dma_reg_writel(ep, offset, tmp); } -static inline void usbf_ep_dma_reg_clrset(struct usbf_ep *ep, uint offset, - u32 clr, u32 set) -{ - u32 tmp; - - tmp = usbf_ep_dma_reg_readl(ep, offset); - tmp &= ~clr; - tmp |= set; - usbf_ep_dma_reg_writel(ep, offset, tmp); -} - static void usbf_ep0_send_null(struct usbf_ep *ep0, bool is_data1) { u32 set; -- GitLab From 2271b2727aeca2e09d07f63bc61dc9757c3a5a3c Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 19 Mar 2023 10:10:53 -0400 Subject: [PATCH 1175/5631] usb: typec: tcpci_mt6360: remove unused mt6360_tcpc_read16 function clang with W=1 reports drivers/usb/typec/tcpm/tcpci_mt6360.c:46:19: error: unused function 'mt6360_tcpc_read16' [-Werror,-Wunused-function] static inline int mt6360_tcpc_read16(struct regmap *regmap, ^ This function is not used, so remove it. Signed-off-by: Tom Rix Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230319141053.1703937-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpci_mt6360.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpci_mt6360.c b/drivers/usb/typec/tcpm/tcpci_mt6360.c index 1b7c31278ebb..6fa8fd5c8041 100644 --- a/drivers/usb/typec/tcpm/tcpci_mt6360.c +++ b/drivers/usb/typec/tcpm/tcpci_mt6360.c @@ -43,12 +43,6 @@ struct mt6360_tcpc_info { int irq; }; -static inline int mt6360_tcpc_read16(struct regmap *regmap, - unsigned int reg, u16 *val) -{ - return regmap_raw_read(regmap, reg, val, sizeof(u16)); -} - static inline int mt6360_tcpc_write16(struct regmap *regmap, unsigned int reg, u16 val) { -- GitLab From 766eae980611f5377ee54518f58da11b4d866f59 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 19 Mar 2023 09:37:32 -0400 Subject: [PATCH 1176/5631] usb: typec: tipd: remove unused tps6598x_write16,32 functions clang with W=1 reports drivers/usb/typec/tipd/core.c:180:19: error: unused function 'tps6598x_write16' [-Werror,-Wunused-function] static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val) ^ drivers/usb/typec/tipd/core.c:185:19: error: unused function 'tps6598x_write32' [-Werror,-Wunused-function] static inline int tps6598x_write32(struct tps6598x *tps, u8 reg, u32 val) ^ These static functions are not used, so remove them. Signed-off-by: Tom Rix Reviewed-by: Heikki Krogerus Reviewed-by: Jun Nie Link: https://lore.kernel.org/r/20230319133732.1702841-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 485b90c13078..af6ecb54b52c 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -177,16 +177,6 @@ static inline int tps6598x_read64(struct tps6598x *tps, u8 reg, u64 *val) return tps6598x_block_read(tps, reg, val, sizeof(u64)); } -static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val) -{ - return tps6598x_block_write(tps, reg, &val, sizeof(u16)); -} - -static inline int tps6598x_write32(struct tps6598x *tps, u8 reg, u32 val) -{ - return tps6598x_block_write(tps, reg, &val, sizeof(u32)); -} - static inline int tps6598x_write64(struct tps6598x *tps, u8 reg, u64 val) { return tps6598x_block_write(tps, reg, &val, sizeof(u64)); -- GitLab From 8c1b63b3c2358024181674e0ada901d50b919d3e Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 21 Mar 2023 14:12:55 -0400 Subject: [PATCH 1177/5631] USB: serial: quatech2: remove unused qt2_setdevice function clang with W=1 reports drivers/usb/serial/quatech2.c:179:19: error: unused function 'qt2_setdevice' [-Werror,-Wunused-function] static inline int qt2_setdevice(struct usb_device *dev, u8 *data) ^ This function is not used, so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230321181255.1825963-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/serial/quatech2.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index 6fca40ace83a..fee581409bf6 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -176,14 +176,6 @@ static inline int qt2_control_msg(struct usb_device *dev, NULL, 0, QT2_USB_TIMEOUT); } -static inline int qt2_setdevice(struct usb_device *dev, u8 *data) -{ - u16 x = ((u16) (data[1] << 8) | (u16) (data[0])); - - return qt2_control_msg(dev, QT_SET_GET_DEVICE, x, 0); -} - - static inline int qt2_getregister(struct usb_device *dev, u8 uart, u8 reg, -- GitLab From 092a2a78e618ee8ebd5c86cac61a404d0bec3310 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 23 Mar 2023 11:55:30 +0800 Subject: [PATCH 1178/5631] dt-bindings: usb: snps,dwc3: correct i.MX8MQ support The previous i.MX8MQ support breaks rockchip,dwc3 support, so use select to restrict i.MX8MQ support and avoid break others. Fixes: 3754c41c7686 ("dt-bindings: usb: snps,dwc3: support i.MX8MQ") Signed-off-by: Peng Fan Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230323035531.3808192-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- .../bindings/usb/fsl,imx8mq-dwc3.yaml | 48 +++++++++++++++++++ .../devicetree/bindings/usb/snps,dwc3.yaml | 12 ++--- 2 files changed, 53 insertions(+), 7 deletions(-) create mode 100644 Documentation/devicetree/bindings/usb/fsl,imx8mq-dwc3.yaml diff --git a/Documentation/devicetree/bindings/usb/fsl,imx8mq-dwc3.yaml b/Documentation/devicetree/bindings/usb/fsl,imx8mq-dwc3.yaml new file mode 100644 index 000000000000..50569d3ee767 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/fsl,imx8mq-dwc3.yaml @@ -0,0 +1,48 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/fsl,imx8mq-dwc3.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP iMX8MQ Soc USB Controller + +maintainers: + - Li Jun + - Peng Fan + +select: + properties: + compatible: + contains: + enum: + - fsl,imx8mq-dwc3 + required: + - compatible + +properties: + compatible: + items: + - const: fsl,imx8mq-dwc3 + - const: snps,dwc3 + +allOf: + - $ref: snps,dwc3.yaml# + +unevaluatedProperties: false + +examples: + - | + #include + #include + + usb_dwc3_1: usb@38200000 { + compatible = "fsl,imx8mq-dwc3", "snps,dwc3"; + reg = <0x38200000 0x10000>; + clocks = <&clk IMX8MQ_CLK_USB2_CTRL_ROOT>, + <&clk IMX8MQ_CLK_USB_CORE_REF>, + <&clk IMX8MQ_CLK_32K>; + clock-names = "bus_early", "ref", "suspend"; + interrupts = ; + phys = <&usb3_phy1>, <&usb3_phy1>; + phy-names = "usb2-phy", "usb3-phy"; + }; diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index 16c7d06c9172..c167fd577cae 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -30,13 +30,11 @@ allOf: properties: compatible: - oneOf: - - items: - - const: fsl,imx8mq-dwc3 - - const: snps,dwc3 - - const: snps,dwc3 - - const: synopsys,dwc3 - deprecated: true + contains: + oneOf: + - const: snps,dwc3 + - const: synopsys,dwc3 + deprecated: true reg: maxItems: 1 -- GitLab From fcd3f50845be909c9e0f8ac402874a2fb4b09c6c Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 23 Mar 2023 11:55:31 +0800 Subject: [PATCH 1179/5631] arm64: dts: imx8mq: drop usb3-resume-missing-cas from usb The property is NXP downstream property that there is no user in upstream, drop it. Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230323035531.3808192-2-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8mq.dtsi | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 98fbba4c99a9..aa4f4f28ca9f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -1445,7 +1445,6 @@ phys = <&usb3_phy0>, <&usb3_phy0>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg1>; - usb3-resume-missing-cas; status = "disabled"; }; @@ -1477,7 +1476,6 @@ phys = <&usb3_phy1>, <&usb3_phy1>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg2>; - usb3-resume-missing-cas; status = "disabled"; }; -- GitLab From fe70f2c83e28df6b18e77a4de092b5313e26ca62 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:18 +0100 Subject: [PATCH 1180/5631] usb: phy: ab8500: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-ab8500-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-ab8500-usb.c b/drivers/usb/phy/phy-ab8500-usb.c index 4c52ba96f17e..408f47e39025 100644 --- a/drivers/usb/phy/phy-ab8500-usb.c +++ b/drivers/usb/phy/phy-ab8500-usb.c @@ -965,7 +965,7 @@ static int ab8500_usb_probe(struct platform_device *pdev) return 0; } -static int ab8500_usb_remove(struct platform_device *pdev) +static void ab8500_usb_remove(struct platform_device *pdev) { struct ab8500_usb *ab = platform_get_drvdata(pdev); @@ -977,8 +977,6 @@ static int ab8500_usb_remove(struct platform_device *pdev) ab8500_usb_host_phy_dis(ab); else if (ab->mode == USB_PERIPHERAL) ab8500_usb_peri_phy_dis(ab); - - return 0; } static const struct platform_device_id ab8500_usb_devtype[] = { @@ -989,7 +987,7 @@ MODULE_DEVICE_TABLE(platform, ab8500_usb_devtype); static struct platform_driver ab8500_usb_driver = { .probe = ab8500_usb_probe, - .remove = ab8500_usb_remove, + .remove_new = ab8500_usb_remove, .id_table = ab8500_usb_devtype, .driver = { .name = "abx5x0-usb", -- GitLab From c123905f5c563c1b43ef5a745b8f403e5e8e1879 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:19 +0100 Subject: [PATCH 1181/5631] usb: phy: am335x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-am335x.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c index 8524475d942d..e39665cf4b4a 100644 --- a/drivers/usb/phy/phy-am335x.c +++ b/drivers/usb/phy/phy-am335x.c @@ -82,12 +82,11 @@ static int am335x_phy_probe(struct platform_device *pdev) return usb_add_phy_dev(&am_phy->usb_phy_gen.phy); } -static int am335x_phy_remove(struct platform_device *pdev) +static void am335x_phy_remove(struct platform_device *pdev) { struct am335x_phy *am_phy = platform_get_drvdata(pdev); usb_remove_phy(&am_phy->usb_phy_gen.phy); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -134,7 +133,7 @@ MODULE_DEVICE_TABLE(of, am335x_phy_ids); static struct platform_driver am335x_phy_driver = { .probe = am335x_phy_probe, - .remove = am335x_phy_remove, + .remove_new = am335x_phy_remove, .driver = { .name = "am335x-phy-driver", .pm = &am335x_pm_ops, -- GitLab From ba1e43522f3290165ef9e881c3db7b0adcc3a1f0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:20 +0100 Subject: [PATCH 1182/5631] usb: phy: fsl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-4-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-fsl-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 972704262b02..79617bb0a70e 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -983,7 +983,7 @@ static int fsl_otg_probe(struct platform_device *pdev) return ret; } -static int fsl_otg_remove(struct platform_device *pdev) +static void fsl_otg_remove(struct platform_device *pdev) { struct fsl_usb2_platform_data *pdata = dev_get_platdata(&pdev->dev); @@ -998,13 +998,11 @@ static int fsl_otg_remove(struct platform_device *pdev) if (pdata->exit) pdata->exit(pdev); - - return 0; } struct platform_driver fsl_otg_driver = { .probe = fsl_otg_probe, - .remove = fsl_otg_remove, + .remove_new = fsl_otg_remove, .driver = { .name = driver_name, .owner = THIS_MODULE, -- GitLab From a8095f9c5238070366e8813f6c6e330de9d2d32b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:21 +0100 Subject: [PATCH 1183/5631] usb: phy: generic: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-generic.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index c1309ea24a52..770081b828a4 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -330,13 +330,11 @@ static int usb_phy_generic_probe(struct platform_device *pdev) return 0; } -static int usb_phy_generic_remove(struct platform_device *pdev) +static void usb_phy_generic_remove(struct platform_device *pdev) { struct usb_phy_generic *nop = platform_get_drvdata(pdev); usb_remove_phy(&nop->phy); - - return 0; } static const struct of_device_id nop_xceiv_dt_ids[] = { @@ -348,7 +346,7 @@ MODULE_DEVICE_TABLE(of, nop_xceiv_dt_ids); static struct platform_driver usb_phy_generic_driver = { .probe = usb_phy_generic_probe, - .remove = usb_phy_generic_remove, + .remove_new = usb_phy_generic_remove, .driver = { .name = "usb_phy_generic", .of_match_table = nop_xceiv_dt_ids, -- GitLab From 399d011772afb910fbf60bc0cea93fccd44d1ecb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:22 +0100 Subject: [PATCH 1184/5631] usb: phy: gpio-vbus: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20230319092428.283054-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-gpio-vbus-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-gpio-vbus-usb.c b/drivers/usb/phy/phy-gpio-vbus-usb.c index 12dfeff7de3d..817c242a76ca 100644 --- a/drivers/usb/phy/phy-gpio-vbus-usb.c +++ b/drivers/usb/phy/phy-gpio-vbus-usb.c @@ -325,7 +325,7 @@ static int gpio_vbus_probe(struct platform_device *pdev) return 0; } -static int gpio_vbus_remove(struct platform_device *pdev) +static void gpio_vbus_remove(struct platform_device *pdev) { struct gpio_vbus_data *gpio_vbus = platform_get_drvdata(pdev); @@ -333,8 +333,6 @@ static int gpio_vbus_remove(struct platform_device *pdev) cancel_delayed_work_sync(&gpio_vbus->work); usb_remove_phy(&gpio_vbus->phy); - - return 0; } #ifdef CONFIG_PM @@ -386,7 +384,7 @@ static struct platform_driver gpio_vbus_driver = { .of_match_table = gpio_vbus_of_match, }, .probe = gpio_vbus_probe, - .remove = gpio_vbus_remove, + .remove_new = gpio_vbus_remove, }; module_platform_driver(gpio_vbus_driver); -- GitLab From 744e004bf2be5daf56332369c8f95da77195550a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:23 +0100 Subject: [PATCH 1185/5631] usb: phy: keystone: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-7-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-keystone.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-keystone.c b/drivers/usb/phy/phy-keystone.c index f75912279b39..bd9a98ad1b30 100644 --- a/drivers/usb/phy/phy-keystone.c +++ b/drivers/usb/phy/phy-keystone.c @@ -88,13 +88,11 @@ static int keystone_usbphy_probe(struct platform_device *pdev) return usb_add_phy_dev(&k_phy->usb_phy_gen.phy); } -static int keystone_usbphy_remove(struct platform_device *pdev) +static void keystone_usbphy_remove(struct platform_device *pdev) { struct keystone_usbphy *k_phy = platform_get_drvdata(pdev); usb_remove_phy(&k_phy->usb_phy_gen.phy); - - return 0; } static const struct of_device_id keystone_usbphy_ids[] = { @@ -105,7 +103,7 @@ MODULE_DEVICE_TABLE(of, keystone_usbphy_ids); static struct platform_driver keystone_usbphy_driver = { .probe = keystone_usbphy_probe, - .remove = keystone_usbphy_remove, + .remove_new = keystone_usbphy_remove, .driver = { .name = "keystone-usbphy", .of_match_table = keystone_usbphy_ids, -- GitLab From 25b979e46f0bda69e100b9cb01ac63bfbd373111 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:24 +0100 Subject: [PATCH 1186/5631] usb: phy: mv: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-8-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-mv-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-mv-usb.c b/drivers/usb/phy/phy-mv-usb.c index 86503b7d695c..df7c27474a75 100644 --- a/drivers/usb/phy/phy-mv-usb.c +++ b/drivers/usb/phy/phy-mv-usb.c @@ -644,7 +644,7 @@ static const struct attribute_group *mv_otg_groups[] = { NULL, }; -static int mv_otg_remove(struct platform_device *pdev) +static void mv_otg_remove(struct platform_device *pdev) { struct mv_otg *mvotg = platform_get_drvdata(pdev); @@ -654,8 +654,6 @@ static int mv_otg_remove(struct platform_device *pdev) mv_otg_disable(mvotg); usb_remove_phy(&mvotg->phy); - - return 0; } static int mv_otg_probe(struct platform_device *pdev) @@ -869,7 +867,7 @@ static int mv_otg_resume(struct platform_device *pdev) static struct platform_driver mv_otg_driver = { .probe = mv_otg_probe, - .remove = mv_otg_remove, + .remove_new = mv_otg_remove, .driver = { .name = driver_name, .dev_groups = mv_otg_groups, -- GitLab From 8471b0fa61947f27eeba1b012a8bfbf78bd6ab59 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:25 +0100 Subject: [PATCH 1187/5631] usb: phy: mxs: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20230319092428.283054-9-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-mxs-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c index 0a8e3fd699ca..e1a2b2ea098b 100644 --- a/drivers/usb/phy/phy-mxs-usb.c +++ b/drivers/usb/phy/phy-mxs-usb.c @@ -801,13 +801,11 @@ static int mxs_phy_probe(struct platform_device *pdev) return usb_add_phy_dev(&mxs_phy->phy); } -static int mxs_phy_remove(struct platform_device *pdev) +static void mxs_phy_remove(struct platform_device *pdev) { struct mxs_phy *mxs_phy = platform_get_drvdata(pdev); usb_remove_phy(&mxs_phy->phy); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -853,7 +851,7 @@ static SIMPLE_DEV_PM_OPS(mxs_phy_pm, mxs_phy_system_suspend, static struct platform_driver mxs_phy_driver = { .probe = mxs_phy_probe, - .remove = mxs_phy_remove, + .remove_new = mxs_phy_remove, .driver = { .name = DRIVER_NAME, .of_match_table = mxs_phy_dt_ids, -- GitLab From e5c1b349efc132553b7e7542f7296a31184f4233 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:26 +0100 Subject: [PATCH 1188/5631] usb: phy: tahvo: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-10-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-tahvo.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-tahvo.c b/drivers/usb/phy/phy-tahvo.c index f2d2cc586c5b..47562d49dfc1 100644 --- a/drivers/usb/phy/phy-tahvo.c +++ b/drivers/usb/phy/phy-tahvo.c @@ -412,7 +412,7 @@ static int tahvo_usb_probe(struct platform_device *pdev) return ret; } -static int tahvo_usb_remove(struct platform_device *pdev) +static void tahvo_usb_remove(struct platform_device *pdev) { struct tahvo_usb *tu = platform_get_drvdata(pdev); @@ -420,13 +420,11 @@ static int tahvo_usb_remove(struct platform_device *pdev) usb_remove_phy(&tu->phy); if (!IS_ERR(tu->ick)) clk_disable(tu->ick); - - return 0; } static struct platform_driver tahvo_usb_driver = { .probe = tahvo_usb_probe, - .remove = tahvo_usb_remove, + .remove_new = tahvo_usb_remove, .driver = { .name = "tahvo-usb", .dev_groups = tahvo_groups, -- GitLab From d95a0ce2fc03322440f404a2971ec528a56af345 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:27 +0100 Subject: [PATCH 1189/5631] usb: phy: tegra: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-11-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-tegra-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index 4d207ce3ddf2..8b2ff3a8882d 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -1486,18 +1486,16 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return usb_add_phy_dev(&tegra_phy->u_phy); } -static int tegra_usb_phy_remove(struct platform_device *pdev) +static void tegra_usb_phy_remove(struct platform_device *pdev) { struct tegra_usb_phy *tegra_phy = platform_get_drvdata(pdev); usb_remove_phy(&tegra_phy->u_phy); - - return 0; } static struct platform_driver tegra_usb_phy_driver = { .probe = tegra_usb_phy_probe, - .remove = tegra_usb_phy_remove, + .remove_new = tegra_usb_phy_remove, .driver = { .name = "tegra-phy", .of_match_table = tegra_usb_phy_id_table, -- GitLab From 17eb81908084047c8b08ae99863dccada5efd5e2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 19 Mar 2023 10:24:28 +0100 Subject: [PATCH 1190/5631] usb: phy: twl6030: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230319092428.283054-12-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-twl6030-usb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c index ab3c38a7d8ac..c3ce6b1054f1 100644 --- a/drivers/usb/phy/phy-twl6030-usb.c +++ b/drivers/usb/phy/phy-twl6030-usb.c @@ -409,7 +409,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) return status; } -static int twl6030_usb_remove(struct platform_device *pdev) +static void twl6030_usb_remove(struct platform_device *pdev) { struct twl6030_usb *twl = platform_get_drvdata(pdev); @@ -422,8 +422,6 @@ static int twl6030_usb_remove(struct platform_device *pdev) free_irq(twl->irq2, twl); regulator_put(twl->usb3v3); cancel_work_sync(&twl->set_vbus_work); - - return 0; } static const struct of_device_id twl6030_usb_id_table[] = { @@ -434,7 +432,7 @@ MODULE_DEVICE_TABLE(of, twl6030_usb_id_table); static struct platform_driver twl6030_usb_driver = { .probe = twl6030_usb_probe, - .remove = twl6030_usb_remove, + .remove_new = twl6030_usb_remove, .driver = { .name = "twl6030_usb", .of_match_table = of_match_ptr(twl6030_usb_id_table), -- GitLab From 62b5412b1f4afab27d8df90ddcabb8e1e11a00ad Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 21 Mar 2023 14:21:41 +0100 Subject: [PATCH 1191/5631] usb: typec: ucsi: add PMIC Glink UCSI driver Introduce the UCSI PMIC Glink aux driver that communicates with the aDSP firmware with the UCSI protocol which handles the USB-C Port(s) Power Delivery. The UCSI messaging is necessary on newer Qualcomm SoCs to provide USB role switch and altmode notifications. Reviewed-by: Heikki Krogerus Signed-off-by: Neil Armstrong Reviewed-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230130-topic-sm8450-upstream-pmic-glink-v5-1-552f3b721f9e@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/Kconfig | 10 + drivers/usb/typec/ucsi/Makefile | 1 + drivers/usb/typec/ucsi/ucsi_glink.c | 345 ++++++++++++++++++++++++++++ 3 files changed, 356 insertions(+) create mode 100644 drivers/usb/typec/ucsi/ucsi_glink.c diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index 8f9c4b9f31f7..b3bb0191987e 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -58,4 +58,14 @@ config UCSI_STM32G0 To compile the driver as a module, choose M here: the module will be called ucsi_stm32g0. +config UCSI_PMIC_GLINK + tristate "UCSI Qualcomm PMIC GLINK Interface Driver" + depends on QCOM_PMIC_GLINK + help + This driver enables UCSI support on platforms that expose UCSI + interface as PMIC GLINK device. + + To compile the driver as a module, choose M here: the module will be + called ucsi_glink. + endif diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index 480d533d762f..77f09e136956 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -18,3 +18,4 @@ endif obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o obj-$(CONFIG_UCSI_STM32G0) += ucsi_stm32g0.o +obj-$(CONFIG_UCSI_PMIC_GLINK) += ucsi_glink.o diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c new file mode 100644 index 000000000000..b454a5159896 --- /dev/null +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Linaro Ltd + */ +#include +#include +#include +#include +#include +#include +#include +#include "ucsi.h" + +#define UCSI_BUF_SIZE 48 + +#define MSG_TYPE_REQ_RESP 1 +#define UCSI_BUF_SIZE 48 + +#define UC_NOTIFY_RECEIVER_UCSI 0x0 +#define UC_UCSI_READ_BUF_REQ 0x11 +#define UC_UCSI_WRITE_BUF_REQ 0x12 +#define UC_UCSI_USBC_NOTIFY_IND 0x13 + +struct ucsi_read_buf_req_msg { + struct pmic_glink_hdr hdr; +}; + +struct ucsi_read_buf_resp_msg { + struct pmic_glink_hdr hdr; + u8 buf[UCSI_BUF_SIZE]; + u32 ret_code; +}; + +struct ucsi_write_buf_req_msg { + struct pmic_glink_hdr hdr; + u8 buf[UCSI_BUF_SIZE]; + u32 reserved; +}; + +struct ucsi_write_buf_resp_msg { + struct pmic_glink_hdr hdr; + u32 ret_code; +}; + +struct ucsi_notify_ind_msg { + struct pmic_glink_hdr hdr; + u32 notification; + u32 receiver; + u32 reserved; +}; + +struct pmic_glink_ucsi { + struct device *dev; + + struct pmic_glink_client *client; + + struct ucsi *ucsi; + struct completion read_ack; + struct completion write_ack; + struct completion sync_ack; + bool sync_pending; + struct mutex lock; /* protects concurrent access to PMIC Glink interface */ + + int sync_val; + + struct work_struct notify_work; + struct work_struct register_work; + + u8 read_buf[UCSI_BUF_SIZE]; +}; + +static int pmic_glink_ucsi_read(struct ucsi *__ucsi, unsigned int offset, + void *val, size_t val_len) +{ + struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(__ucsi); + struct ucsi_read_buf_req_msg req = {}; + unsigned long left; + int ret; + + req.hdr.owner = PMIC_GLINK_OWNER_USBC; + req.hdr.type = MSG_TYPE_REQ_RESP; + req.hdr.opcode = UC_UCSI_READ_BUF_REQ; + + mutex_lock(&ucsi->lock); + memset(ucsi->read_buf, 0, sizeof(ucsi->read_buf)); + reinit_completion(&ucsi->read_ack); + + ret = pmic_glink_send(ucsi->client, &req, sizeof(req)); + if (ret < 0) { + dev_err(ucsi->dev, "failed to send UCSI read request: %d\n", ret); + goto out_unlock; + } + + left = wait_for_completion_timeout(&ucsi->read_ack, 5 * HZ); + if (!left) { + dev_err(ucsi->dev, "timeout waiting for UCSI read response\n"); + ret = -ETIMEDOUT; + goto out_unlock; + } + + memcpy(val, &ucsi->read_buf[offset], val_len); + ret = 0; + +out_unlock: + mutex_unlock(&ucsi->lock); + + return ret; +} + +static int pmic_glink_ucsi_locked_write(struct pmic_glink_ucsi *ucsi, unsigned int offset, + const void *val, size_t val_len) +{ + struct ucsi_write_buf_req_msg req = {}; + unsigned long left; + int ret; + + req.hdr.owner = PMIC_GLINK_OWNER_USBC; + req.hdr.type = MSG_TYPE_REQ_RESP; + req.hdr.opcode = UC_UCSI_WRITE_BUF_REQ; + memcpy(&req.buf[offset], val, val_len); + + reinit_completion(&ucsi->write_ack); + + ret = pmic_glink_send(ucsi->client, &req, sizeof(req)); + if (ret < 0) { + dev_err(ucsi->dev, "failed to send UCSI write request: %d\n", ret); + return ret; + } + + left = wait_for_completion_timeout(&ucsi->write_ack, 5 * HZ); + if (!left) { + dev_err(ucsi->dev, "timeout waiting for UCSI write response\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int pmic_glink_ucsi_async_write(struct ucsi *__ucsi, unsigned int offset, + const void *val, size_t val_len) +{ + struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(__ucsi); + int ret; + + mutex_lock(&ucsi->lock); + ret = pmic_glink_ucsi_locked_write(ucsi, offset, val, val_len); + mutex_unlock(&ucsi->lock); + + return ret; +} + +static int pmic_glink_ucsi_sync_write(struct ucsi *__ucsi, unsigned int offset, + const void *val, size_t val_len) +{ + struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(__ucsi); + unsigned long left; + int ret; + + /* TOFIX: Downstream forces recipient to CON when UCSI_GET_ALTERNATE_MODES command */ + + mutex_lock(&ucsi->lock); + ucsi->sync_val = 0; + reinit_completion(&ucsi->sync_ack); + ucsi->sync_pending = true; + ret = pmic_glink_ucsi_locked_write(ucsi, offset, val, val_len); + mutex_unlock(&ucsi->lock); + + left = wait_for_completion_timeout(&ucsi->sync_ack, 5 * HZ); + if (!left) { + dev_err(ucsi->dev, "timeout waiting for UCSI sync write response\n"); + ret = -ETIMEDOUT; + } else if (ucsi->sync_val) { + dev_err(ucsi->dev, "sync write returned: %d\n", ucsi->sync_val); + } + + ucsi->sync_pending = false; + + return ret; +} + +static const struct ucsi_operations pmic_glink_ucsi_ops = { + .read = pmic_glink_ucsi_read, + .sync_write = pmic_glink_ucsi_sync_write, + .async_write = pmic_glink_ucsi_async_write +}; + +static void pmic_glink_ucsi_read_ack(struct pmic_glink_ucsi *ucsi, const void *data, int len) +{ + const struct ucsi_read_buf_resp_msg *resp = data; + + if (resp->ret_code) + return; + + memcpy(ucsi->read_buf, resp->buf, UCSI_BUF_SIZE); + complete(&ucsi->read_ack); +} + +static void pmic_glink_ucsi_write_ack(struct pmic_glink_ucsi *ucsi, const void *data, int len) +{ + const struct ucsi_write_buf_resp_msg *resp = data; + + if (resp->ret_code) + return; + + ucsi->sync_val = resp->ret_code; + complete(&ucsi->write_ack); +} + +static void pmic_glink_ucsi_notify(struct work_struct *work) +{ + struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, notify_work); + unsigned int con_num; + u32 cci; + int ret; + + ret = pmic_glink_ucsi_read(ucsi->ucsi, UCSI_CCI, &cci, sizeof(cci)); + if (ret) { + dev_err(ucsi->dev, "failed to read CCI on notification\n"); + return; + } + + con_num = UCSI_CCI_CONNECTOR(cci); + if (con_num) + ucsi_connector_change(ucsi->ucsi, con_num); + + if (ucsi->sync_pending && cci & UCSI_CCI_BUSY) { + ucsi->sync_val = -EBUSY; + complete(&ucsi->sync_ack); + } else if (ucsi->sync_pending && + (cci & (UCSI_CCI_ACK_COMPLETE | UCSI_CCI_COMMAND_COMPLETE))) { + complete(&ucsi->sync_ack); + } +} + +static void pmic_glink_ucsi_register(struct work_struct *work) +{ + struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, register_work); + + ucsi_register(ucsi->ucsi); +} + +static void pmic_glink_ucsi_callback(const void *data, size_t len, void *priv) +{ + struct pmic_glink_ucsi *ucsi = priv; + const struct pmic_glink_hdr *hdr = data; + + switch (hdr->opcode) { + case UC_UCSI_READ_BUF_REQ: + pmic_glink_ucsi_read_ack(ucsi, data, len); + break; + case UC_UCSI_WRITE_BUF_REQ: + pmic_glink_ucsi_write_ack(ucsi, data, len); + break; + case UC_UCSI_USBC_NOTIFY_IND: + schedule_work(&ucsi->notify_work); + break; + }; +} + +static void pmic_glink_ucsi_pdr_notify(void *priv, int state) +{ + struct pmic_glink_ucsi *ucsi = priv; + + if (state == SERVREG_SERVICE_STATE_UP) + schedule_work(&ucsi->register_work); + else if (state == SERVREG_SERVICE_STATE_DOWN) + ucsi_unregister(ucsi->ucsi); +} + +static void pmic_glink_ucsi_destroy(void *data) +{ + struct pmic_glink_ucsi *ucsi = data; + + /* Protect to make sure we're not in a middle of a transaction from a glink callback */ + mutex_lock(&ucsi->lock); + ucsi_destroy(ucsi->ucsi); + mutex_unlock(&ucsi->lock); +} + +static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct pmic_glink_ucsi *ucsi; + struct device *dev = &adev->dev; + int ret; + + ucsi = devm_kzalloc(dev, sizeof(*ucsi), GFP_KERNEL); + if (!ucsi) + return -ENOMEM; + + ucsi->dev = dev; + dev_set_drvdata(dev, ucsi); + + INIT_WORK(&ucsi->notify_work, pmic_glink_ucsi_notify); + INIT_WORK(&ucsi->register_work, pmic_glink_ucsi_register); + init_completion(&ucsi->read_ack); + init_completion(&ucsi->write_ack); + init_completion(&ucsi->sync_ack); + mutex_init(&ucsi->lock); + + ucsi->ucsi = ucsi_create(dev, &pmic_glink_ucsi_ops); + if (IS_ERR(ucsi->ucsi)) + return PTR_ERR(ucsi->ucsi); + + /* Make sure we destroy *after* pmic_glink unregister */ + ret = devm_add_action_or_reset(dev, pmic_glink_ucsi_destroy, ucsi); + if (ret) + return ret; + + ucsi_set_drvdata(ucsi->ucsi, ucsi); + + ucsi->client = devm_pmic_glink_register_client(dev, + PMIC_GLINK_OWNER_USBC, + pmic_glink_ucsi_callback, + pmic_glink_ucsi_pdr_notify, + ucsi); + return PTR_ERR_OR_ZERO(ucsi->client); +} + +static void pmic_glink_ucsi_remove(struct auxiliary_device *adev) +{ + struct pmic_glink_ucsi *ucsi = dev_get_drvdata(&adev->dev); + + /* Unregister first to stop having read & writes */ + ucsi_unregister(ucsi->ucsi); +} + +static const struct auxiliary_device_id pmic_glink_ucsi_id_table[] = { + { .name = "pmic_glink.ucsi", }, + {}, +}; +MODULE_DEVICE_TABLE(auxiliary, pmic_glink_ucsi_id_table); + +static struct auxiliary_driver pmic_glink_ucsi_driver = { + .name = "pmic_glink_ucsi", + .probe = pmic_glink_ucsi_probe, + .remove = pmic_glink_ucsi_remove, + .id_table = pmic_glink_ucsi_id_table, +}; + +module_auxiliary_driver(pmic_glink_ucsi_driver); + +MODULE_DESCRIPTION("Qualcomm PMIC GLINK UCSI driver"); +MODULE_LICENSE("GPL"); -- GitLab From a33113f7369395a70de8b52d6e9fda17aa548aad Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 21 Mar 2023 14:21:45 +0100 Subject: [PATCH 1192/5631] dt-bindings: usb: snps,dwc3: document HS & SS OF graph ports Document the optional ports subnode to describe the High-Speed and Super-Speed connections as separate OF graph links. The ports property is an alternative to the already documented single port subnode property. Reviewed-by: Rob Herring Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20230130-topic-sm8450-upstream-pmic-glink-v5-5-552f3b721f9e@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/snps,dwc3.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index c167fd577cae..eb58ba96b850 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -377,6 +377,22 @@ properties: This port is used with the 'usb-role-switch' property to connect the dwc3 to type C connector. + ports: + $ref: /schemas/graph.yaml#/properties/ports + description: + Those ports should be used with any connector to the data bus of this + controller using the OF graph bindings specified if the "usb-role-switch" + property is used. + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: High Speed (HS) data bus. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: Super Speed (SS) data bus. + wakeup-source: $ref: /schemas/types.yaml#/definitions/flag description: -- GitLab From 84364a00b264885a97f83c328df8e63d3ec7aefa Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Thu, 16 Mar 2023 15:12:24 +0200 Subject: [PATCH 1193/5631] usb: dwc3-am62: Add support for system wakeup based on USB events The USB2SS IP in TI's AM62 SoC is capable of supporting wakeup from deep sleep based on the following events, 1) VBUS state change 2) Overcurrent detection 3) Line state change Wakeup from these events can enabled by setting their corresponding bits in the WAKEUP_CONFIG register. The events to be enabled are decided based on the current role of the controller. When the role of the controller is host, the comparators for detecting VBUS state change are disabled while entering low power mode. This is done as VBUS state is not used in host mode and disabling the comparators helps in reducing the power consumption. So, wakeup from VBUS state change should be disabled in host mode. While operating in peripheral mode all the wakeup events can be enabled. Therefore, add support for the same in the suspend/resume hooks. Signed-off-by: Aswath Govindraju Signed-off-by: Roger Quadros Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230316131226.89540-2-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-am62.c | 39 ++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 173cf3579c55..867bfa1252b8 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -17,6 +17,8 @@ #include #include +#include "core.h" + /* USB WRAPPER register offsets */ #define USBSS_PID 0x0 #define USBSS_OVERCURRENT_CTRL 0x4 @@ -45,6 +47,10 @@ #define USBSS_PHY_VBUS_SEL_SHIFT 1 #define USBSS_PHY_LANE_REVERSE BIT(0) +/* CORE STAT register bits */ +#define USBSS_CORE_OPERATIONAL_MODE_MASK GENMASK(13, 12) +#define USBSS_CORE_OPERATIONAL_MODE_SHIFT 12 + /* MODE CONTROL register bits */ #define USBSS_MODE_VALID BIT(0) @@ -233,6 +239,9 @@ static int dwc3_ti_probe(struct platform_device *pdev) reg |= USBSS_MODE_VALID; dwc3_ti_writel(data, USBSS_MODE_CONTROL, reg); + /* Device has capability to wakeup system from sleep */ + device_set_wakeup_capable(dev, true); + /* Setting up autosuspend */ pm_runtime_set_autosuspend_delay(dev, DWC3_AM62_AUTOSUSPEND_DELAY); pm_runtime_use_autosuspend(dev); @@ -281,6 +290,22 @@ static int dwc3_ti_remove(struct platform_device *pdev) static int dwc3_ti_suspend_common(struct device *dev) { struct dwc3_data *data = dev_get_drvdata(dev); + u32 reg, current_prtcap_dir; + + if (device_may_wakeup(dev)) { + reg = dwc3_ti_readl(data, USBSS_CORE_STAT); + current_prtcap_dir = (reg & USBSS_CORE_OPERATIONAL_MODE_MASK) + >> USBSS_CORE_OPERATIONAL_MODE_SHIFT; + /* Set wakeup config enable bits */ + reg = dwc3_ti_readl(data, USBSS_WAKEUP_CONFIG); + if (current_prtcap_dir == DWC3_GCTL_PRTCAP_HOST) { + reg |= USBSS_WAKEUP_CFG_LINESTATE_EN | USBSS_WAKEUP_CFG_OVERCURRENT_EN; + } else { + reg |= USBSS_WAKEUP_CFG_OVERCURRENT_EN | USBSS_WAKEUP_CFG_LINESTATE_EN | + USBSS_WAKEUP_CFG_VBUSVALID_EN; + } + dwc3_ti_writel(data, USBSS_WAKEUP_CONFIG, reg); + } clk_disable_unprepare(data->usb2_refclk); @@ -290,9 +315,23 @@ static int dwc3_ti_suspend_common(struct device *dev) static int dwc3_ti_resume_common(struct device *dev) { struct dwc3_data *data = dev_get_drvdata(dev); + u32 reg; clk_prepare_enable(data->usb2_refclk); + if (device_may_wakeup(dev)) { + /* Clear wakeup config enable bits */ + reg = dwc3_ti_readl(data, USBSS_WAKEUP_CONFIG); + reg &= ~(USBSS_WAKEUP_CFG_OVERCURRENT_EN | USBSS_WAKEUP_CFG_LINESTATE_EN | + USBSS_WAKEUP_CFG_VBUSVALID_EN); + dwc3_ti_writel(data, USBSS_WAKEUP_CONFIG, reg); + } + + reg = dwc3_ti_readl(data, USBSS_WAKEUP_STAT); + /* Clear the wakeup status with wakeup clear bit */ + reg |= USBSS_WAKEUP_STAT_CLR; + dwc3_ti_writel(data, USBSS_WAKEUP_STAT, reg); + return 0; } -- GitLab From 4e3972b589da0519bf57ed386974b64b9c8572fd Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Thu, 16 Mar 2023 15:12:25 +0200 Subject: [PATCH 1194/5631] usb: dwc3-am62: Enable as a wakeup source by default USB module can wakeup system. Enable it as a wakeup source by default. Finer grain wakeup enable/disable can be done from the power/wakeup system control file of the respective USB device. Signed-off-by: Roger Quadros Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230316131226.89540-3-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-am62.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 867bfa1252b8..859b48279658 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -241,6 +241,9 @@ static int dwc3_ti_probe(struct platform_device *pdev) /* Device has capability to wakeup system from sleep */ device_set_wakeup_capable(dev, true); + ret = device_wakeup_enable(dev); + if (ret) + dev_err(dev, "couldn't enable device as a wakeup source: %d\n", ret); /* Setting up autosuspend */ pm_runtime_set_autosuspend_delay(dev, DWC3_AM62_AUTOSUSPEND_DELAY); -- GitLab From 8c4853c48d6cd56611446ec767c5e8365bdd964b Mon Sep 17 00:00:00 2001 From: Li Jun Date: Fri, 17 Mar 2023 16:55:28 +0800 Subject: [PATCH 1195/5631] usb: dwc3: add several registers dump for debugfs Add 5 missing register dump for debugfs as they are in use now. Signed-off-by: Li Jun Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/1679043328-13425-1-git-send-email-jun.li@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/debugfs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index 850df0e6bcab..e4a2560b9dc0 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -88,6 +88,9 @@ static const struct debugfs_reg32 dwc3_regs[] = { dump_register(GPRTBIMAP_HS1), dump_register(GPRTBIMAP_FS0), dump_register(GPRTBIMAP_FS1), + dump_register(GUCTL2), + dump_register(VER_NUMBER), + dump_register(VER_TYPE), dump_register(GUSB2PHYCFG(0)), dump_register(GUSB2PHYCFG(1)), @@ -229,6 +232,8 @@ static const struct debugfs_reg32 dwc3_regs[] = { dump_register(GEVNTCOUNT(0)), dump_register(GHWPARAMS8), + dump_register(GUCTL3), + dump_register(GFLADJ), dump_register(DCFG), dump_register(DCTL), dump_register(DEVTEN), -- GitLab From 2b947f8769be8b8181dc795fd292d3e7120f5204 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Mon, 20 Mar 2023 14:29:31 +0800 Subject: [PATCH 1196/5631] usb: gadget: udc: renesas_usb3: Fix use after free bug in renesas_usb3_remove due to race condition In renesas_usb3_probe, role_work is bound with renesas_usb3_role_work. renesas_usb3_start will be called to start the work. If we remove the driver which will call usbhs_remove, there may be an unfinished work. The possible sequence is as follows: CPU0 CPU1 renesas_usb3_role_work renesas_usb3_remove usb_role_switch_unregister device_unregister kfree(sw) //free usb3->role_sw usb_role_switch_set_role //use usb3->role_sw The usb3->role_sw could be freed under such circumstance and then used in usb_role_switch_set_role. This bug was found by static analysis. And note that removing a driver is a root-only operation, and should never happen in normal case. But the root user may directly remove the device which will also trigger the remove function. Fix it by canceling the work before cleanup in the renesas_usb3_remove. Fixes: 39facfa01c9f ("usb: gadget: udc: renesas_usb3: Add register of usb role switch") Signed-off-by: Zheng Wang Reviewed-by: Yoshihiro Shimoda Link: https://lore.kernel.org/r/20230320062931.505170-1-zyytlz.wz@163.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/renesas_usb3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 17e765d2e093..aac8bc185afa 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -2660,6 +2660,7 @@ static int renesas_usb3_remove(struct platform_device *pdev) debugfs_remove_recursive(usb3->dentry); device_remove_file(&pdev->dev, &dev_attr_role); + cancel_work_sync(&usb3->role_work); usb_role_switch_unregister(usb3->role_sw); usb_del_gadget_udc(&usb3->gadget); -- GitLab From f7515d9fe8fc4b80754cd4d98a5fcaee84adeebb Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:07 -0800 Subject: [PATCH 1197/5631] objtool: Add objtool_types.h Reduce the amount of header sync churn by splitting the shared objtool.h types into a new file. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/dec622720851210ceafa12d4f4c5f9e73c832152.1677683419.git.jpoimboe@kernel.org --- MAINTAINERS | 2 +- include/linux/objtool.h | 42 +----- include/linux/objtool_types.h | 48 +++++++ tools/include/linux/objtool.h | 200 ---------------------------- tools/include/linux/objtool_types.h | 48 +++++++ tools/objtool/check.c | 2 +- tools/objtool/orc_dump.c | 2 +- tools/objtool/orc_gen.c | 2 +- tools/objtool/sync-check.sh | 2 +- 9 files changed, 102 insertions(+), 246 deletions(-) create mode 100644 include/linux/objtool_types.h delete mode 100644 tools/include/linux/objtool.h create mode 100644 tools/include/linux/objtool_types.h diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..36e9e642c05e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15090,8 +15090,8 @@ OBJTOOL M: Josh Poimboeuf M: Peter Zijlstra S: Supported +F: include/linux/objtool*.h F: tools/objtool/ -F: include/linux/objtool.h OCELOT ETHERNET SWITCH DRIVER M: Vladimir Oltean diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 9ac3df3fccf0..8375792acfc0 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -2,47 +2,7 @@ #ifndef _LINUX_OBJTOOL_H #define _LINUX_OBJTOOL_H -#ifndef __ASSEMBLY__ - -#include - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#include #ifdef CONFIG_OBJTOOL diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h new file mode 100644 index 000000000000..8513537a30ed --- /dev/null +++ b/include/linux/objtool_types.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; + u8 end; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + */ +#define UNWIND_HINT_TYPE_CALL 0 +#define UNWIND_HINT_TYPE_REGS 1 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h deleted file mode 100644 index 9ac3df3fccf0..000000000000 --- a/tools/include/linux/objtool.h +++ /dev/null @@ -1,200 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_OBJTOOL_H -#define _LINUX_OBJTOOL_H - -#ifndef __ASSEMBLY__ - -#include - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 - -#ifdef CONFIG_OBJTOOL - -#include - -#ifndef __ASSEMBLY__ - -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "987: \n\t" \ - ".pushsection .discard.unwind_hints\n\t" \ - /* struct unwind_hint */ \ - ".long 987b - .\n\t" \ - ".short " __stringify(sp_offset) "\n\t" \ - ".byte " __stringify(sp_reg) "\n\t" \ - ".byte " __stringify(type) "\n\t" \ - ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ - ".balign 4 \n\t" \ - ".popsection\n\t" - -/* - * This macro marks the given function's stack frame as "non-standard", which - * tells objtool to ignore the function when doing stack metadata validation. - * It should only be used in special cases where you're 100% sure it won't - * affect the reliability of frame pointers and kernel stack traces. - * - * For more information, see tools/objtool/Documentation/objtool.txt. - */ -#define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(".discard.func_stack_frame_non_standard") \ - *__func_stack_frame_non_standard_##func = func - -/* - * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore - * for the case where a function is intentionally missing frame pointer setup, - * but otherwise needs objtool/ORC coverage when frame pointers are disabled. - */ -#ifdef CONFIG_FRAME_POINTER -#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func) -#else -#define STACK_FRAME_NON_STANDARD_FP(func) -#endif - -#define ANNOTATE_NOENDBR \ - "986: \n\t" \ - ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ - ".popsection\n\t" - -#define ASM_REACHABLE \ - "998:\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long 998b - .\n\t" \ - ".popsection\n\t" - -#else /* __ASSEMBLY__ */ - -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL \ - 999: \ - .pushsection .discard.intra_function_calls; \ - .long 999b; \ - .popsection; - -/* - * In asm, there are two kinds of code: normal C-type callable functions and - * the rest. The normal callable functions can be called by other code, and - * don't do anything unusual with the stack. Such normal callable functions - * are annotated with the ENTRY/ENDPROC macros. Most asm code falls in this - * category. In this case, no special debugging annotations are needed because - * objtool can automatically generate the ORC data for the ORC unwinder to read - * at runtime. - * - * Anything which doesn't fall into the above category, such as syscall and - * interrupt handlers, tends to not be called directly by other functions, and - * often does unusual non-C-function-type things with the stack pointer. Such - * code needs to be annotated such that objtool can understand it. The - * following CFI hint macros are for this type of code. - * - * These macros provide hints to objtool about the state of the stack at each - * instruction. Objtool starts from the hints and follows the code flow, - * making automatic CFI adjustments when it sees pushes and pops, filling out - * the debuginfo as necessary. It will also warn if it sees any - * inconsistencies. - */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: - .pushsection .discard.unwind_hints - /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . - .short \sp_offset - .byte \sp_reg - .byte \type - .byte \signal - .byte \end - .balign 4 - .popsection -.endm - -.macro STACK_FRAME_NON_STANDARD func:req - .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func - .popsection -.endm - -.macro STACK_FRAME_NON_STANDARD_FP func:req -#ifdef CONFIG_FRAME_POINTER - STACK_FRAME_NON_STANDARD \func -#endif -.endm - -.macro ANNOTATE_NOENDBR -.Lhere_\@: - .pushsection .discard.noendbr - .quad .Lhere_\@ - .popsection -.endm - -.macro REACHABLE -.Lhere_\@: - .pushsection .discard.reachable - .long .Lhere_\@ - . - .popsection -.endm - -#endif /* __ASSEMBLY__ */ - -#else /* !CONFIG_OBJTOOL */ - -#ifndef __ASSEMBLY__ - -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" -#define STACK_FRAME_NON_STANDARD(func) -#define STACK_FRAME_NON_STANDARD_FP(func) -#define ANNOTATE_NOENDBR -#define ASM_REACHABLE -#else -#define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.endm -.macro STACK_FRAME_NON_STANDARD func:req -.endm -.macro ANNOTATE_NOENDBR -.endm -.macro REACHABLE -.endm -#endif - -#endif /* CONFIG_OBJTOOL */ - -#endif /* _LINUX_OBJTOOL_H */ diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h new file mode 100644 index 000000000000..8513537a30ed --- /dev/null +++ b/tools/include/linux/objtool_types.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; + u8 end; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + */ +#define UNWIND_HINT_TYPE_CALL 0 +#define UNWIND_HINT_TYPE_REGS 1 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4 +#define UNWIND_HINT_TYPE_SAVE 5 +#define UNWIND_HINT_TYPE_RESTORE 6 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 37c36dc1d868..efc2baa02883 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -17,7 +17,7 @@ #include #include -#include +#include #include #include #include diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 2d8ebdcd1db3..9f6c528c26f2 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -4,7 +4,7 @@ */ #include -#include +#include #include #include #include diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 57a4527d5988..f49630a21e0f 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include diff --git a/tools/objtool/sync-check.sh b/tools/objtool/sync-check.sh index 105a291ff8e7..81d120d05442 100755 --- a/tools/objtool/sync-check.sh +++ b/tools/objtool/sync-check.sh @@ -6,7 +6,7 @@ if [ -z "$SRCARCH" ]; then exit 1 fi -FILES="include/linux/objtool.h" +FILES="include/linux/objtool_types.h" if [ "$SRCARCH" = "x86" ]; then FILES="$FILES -- GitLab From 1c0c1faf5692c18c127d044ecc0cc92c7bab3477 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:08 -0800 Subject: [PATCH 1198/5631] objtool: Use relative pointers for annotations They produce the needed relocations while using half the space. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/bed05c64e28200220c9b1754a2f3ce71f73076ea.1677683419.git.jpoimboe@kernel.org --- arch/x86/include/asm/nospec-branch.h | 6 +++--- include/linux/objtool.h | 12 ++++++------ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 3ef70e54a858..78ed1546b775 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -194,9 +194,9 @@ * builds. */ .macro ANNOTATE_RETPOLINE_SAFE - .Lannotate_\@: +.Lhere_\@: .pushsection .discard.retpoline_safe - _ASM_PTR .Lannotate_\@ + .long .Lhere_\@ - . .popsection .endm @@ -318,7 +318,7 @@ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ - _ASM_PTR " 999b\n\t" \ + ".long 999b - .\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 8375792acfc0..2b0258d273fc 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -49,7 +49,7 @@ #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ + ".long 986b - .\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ @@ -67,7 +67,7 @@ #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b; \ + .long 999b - .; \ .popsection; /* @@ -92,10 +92,10 @@ * inconsistencies. */ .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: +.Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . + .long .Lhere_\@ - . .short \sp_offset .byte \sp_reg .byte \type @@ -107,7 +107,7 @@ .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func + .long \func - . .popsection .endm @@ -120,7 +120,7 @@ .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .quad .Lhere_\@ + .long .Lhere_\@ - . .popsection .endm -- GitLab From d88ebba45dfe67114a6ac8c6514f2c65b6ed64c7 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:09 -0800 Subject: [PATCH 1199/5631] objtool: Change UNWIND_HINT() argument order The most important argument is 'type', make that one first. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/d994f8c29376c5618c75698df28fc03b52d3a868.1677683419.git.jpoimboe@kernel.org --- arch/x86/include/asm/unwind_hints.h | 2 +- include/linux/objtool.h | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index e7c71750b309..97b392217c0f 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -67,7 +67,7 @@ #else #define UNWIND_HINT_FUNC \ - UNWIND_HINT(ORC_REG_SP, 8, UNWIND_HINT_TYPE_FUNC, 0, 0) + UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0, 0) #endif /* __ASSEMBLY__ */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 2b0258d273fc..725d7f0b6748 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -10,7 +10,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -137,8 +137,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR -- GitLab From f902cfdd46aedd2afb3e8033223312dbf5fbb675 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:10 -0800 Subject: [PATCH 1200/5631] x86,objtool: Introduce ORC_TYPE_* Unwind hints and ORC entry types are two distinct things. Separate them out more explicitly. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/cc879d38fff8a43f8f7beb2fd56e35a5a384d7cd.1677683419.git.jpoimboe@kernel.org --- arch/x86/include/asm/orc_types.h | 4 ++++ arch/x86/kernel/unwind_orc.c | 12 ++++++------ include/linux/objtool_types.h | 1 + tools/arch/x86/include/asm/orc_types.h | 4 ++++ tools/include/linux/objtool_types.h | 1 + tools/objtool/orc_dump.c | 7 +++---- tools/objtool/orc_gen.c | 19 +++++++++++++++++-- 7 files changed, 36 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index 1343a62106de..b4d4ec78589e 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -39,6 +39,10 @@ #define ORC_REG_SP_INDIRECT 9 #define ORC_REG_MAX 15 +#define ORC_TYPE_CALL 0 +#define ORC_TYPE_REGS 1 +#define ORC_TYPE_REGS_PARTIAL 2 + #ifndef __ASSEMBLY__ #include diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 37307b40f8da..8348ac581de3 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -133,7 +133,7 @@ static struct orc_entry null_orc_entry = { .sp_offset = sizeof(long), .sp_reg = ORC_REG_SP, .bp_reg = ORC_REG_UNDEFINED, - .type = UNWIND_HINT_TYPE_CALL + .type = ORC_TYPE_CALL }; #ifdef CONFIG_CALL_THUNKS @@ -153,7 +153,7 @@ static struct orc_entry *orc_callthunk_find(unsigned long ip) /* Fake frame pointer entry -- used as a fallback for generated code */ static struct orc_entry orc_fp_entry = { - .type = UNWIND_HINT_TYPE_CALL, + .type = ORC_TYPE_CALL, .sp_reg = ORC_REG_BP, .sp_offset = 16, .bp_reg = ORC_REG_PREV_SP, @@ -554,7 +554,7 @@ bool unwind_next_frame(struct unwind_state *state) /* Find IP, SP and possibly regs: */ switch (orc->type) { - case UNWIND_HINT_TYPE_CALL: + case ORC_TYPE_CALL: ip_p = sp - sizeof(long); if (!deref_stack_reg(state, ip_p, &state->ip)) @@ -567,7 +567,7 @@ bool unwind_next_frame(struct unwind_state *state) state->prev_regs = NULL; break; - case UNWIND_HINT_TYPE_REGS: + case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn_current("can't access registers at %pB\n", (void *)orig_ip); @@ -590,13 +590,13 @@ bool unwind_next_frame(struct unwind_state *state) state->full_regs = true; break; - case UNWIND_HINT_TYPE_REGS_PARTIAL: + case ORC_TYPE_REGS_PARTIAL: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn_current("can't access iret registers at %pB\n", (void *)orig_ip); goto err; } - /* See UNWIND_HINT_TYPE_REGS case comment. */ + /* See ORC_TYPE_REGS case comment. */ state->ip = unwind_recover_rethook(state, state->ip, (unsigned long *)(state->sp - sizeof(long))); diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 8513537a30ed..9a83468c0039 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -40,6 +40,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +/* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 #define UNWIND_HINT_TYPE_ENTRY 4 #define UNWIND_HINT_TYPE_SAVE 5 diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h index 1343a62106de..b4d4ec78589e 100644 --- a/tools/arch/x86/include/asm/orc_types.h +++ b/tools/arch/x86/include/asm/orc_types.h @@ -39,6 +39,10 @@ #define ORC_REG_SP_INDIRECT 9 #define ORC_REG_MAX 15 +#define ORC_TYPE_CALL 0 +#define ORC_TYPE_REGS 1 +#define ORC_TYPE_REGS_PARTIAL 2 + #ifndef __ASSEMBLY__ #include diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h index 8513537a30ed..9a83468c0039 100644 --- a/tools/include/linux/objtool_types.h +++ b/tools/include/linux/objtool_types.h @@ -40,6 +40,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +/* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 #define UNWIND_HINT_TYPE_ENTRY 4 #define UNWIND_HINT_TYPE_SAVE 5 diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 9f6c528c26f2..97ecbb8b9034 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -4,7 +4,6 @@ */ #include -#include #include #include #include @@ -39,11 +38,11 @@ static const char *reg_name(unsigned int reg) static const char *orc_type_name(unsigned int type) { switch (type) { - case UNWIND_HINT_TYPE_CALL: + case ORC_TYPE_CALL: return "call"; - case UNWIND_HINT_TYPE_REGS: + case ORC_TYPE_REGS: return "regs"; - case UNWIND_HINT_TYPE_REGS_PARTIAL: + case ORC_TYPE_REGS_PARTIAL: return "regs (partial)"; default: return "?"; diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index f49630a21e0f..e85bbb996f6c 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -26,6 +26,22 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, return 0; } + switch (cfi->type) { + case UNWIND_HINT_TYPE_CALL: + orc->type = ORC_TYPE_CALL; + break; + case UNWIND_HINT_TYPE_REGS: + orc->type = ORC_TYPE_REGS; + break; + case UNWIND_HINT_TYPE_REGS_PARTIAL: + orc->type = ORC_TYPE_REGS_PARTIAL; + break; + default: + WARN_FUNC("unknown unwind hint type %d", + insn->sec, insn->offset, cfi->type); + return -1; + } + orc->end = cfi->end; orc->signal = cfi->signal; @@ -83,7 +99,6 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->sp_offset = cfi->cfa.offset; orc->bp_offset = bp->offset; - orc->type = cfi->type; return 0; } @@ -151,7 +166,7 @@ int orc_create(struct objtool_file *file) struct orc_entry null = { .sp_reg = ORC_REG_UNDEFINED, .bp_reg = ORC_REG_UNDEFINED, - .type = UNWIND_HINT_TYPE_CALL, + .type = ORC_TYPE_CALL, }; /* Build a deduplicated list of ORC entries: */ -- GitLab From 4708ea14bef314fc901857eefd65678236a9f2d9 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:11 -0800 Subject: [PATCH 1201/5631] x86,objtool: Separate unret validation from unwind hints The ENTRY unwind hint type is serving double duty as both an empty unwind hint and an unret validation annotation. Unret validation is unrelated to unwinding. Separate it out into its own annotation. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/ff7448d492ea21b86d8a90264b105fbd0d751077.1677683419.git.jpoimboe@kernel.org --- arch/x86/entry/entry_64.S | 14 +++--- arch/x86/include/asm/nospec-branch.h | 8 ++-- arch/x86/include/asm/unwind_hints.h | 8 +++- arch/x86/kernel/head_64.S | 5 --- include/linux/objtool.h | 16 +++++++ include/linux/objtool_types.h | 5 +-- tools/include/linux/objtool_types.h | 5 +-- tools/objtool/check.c | 65 ++++++++++++++++++--------- tools/objtool/include/objtool/check.h | 4 +- 9 files changed, 85 insertions(+), 45 deletions(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index eccc3431e515..5b93eb7db0ab 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -388,9 +388,9 @@ SYM_CODE_START(\asmsym) .if \vector == X86_TRAP_BP /* #BP advances %rip to the next instruction */ - UNWIND_HINT_IRET_REGS offset=\has_error_code*8 signal=0 + UNWIND_HINT_IRET_ENTRY offset=\has_error_code*8 signal=0 .else - UNWIND_HINT_IRET_REGS offset=\has_error_code*8 + UNWIND_HINT_IRET_ENTRY offset=\has_error_code*8 .endif ENDBR @@ -461,7 +461,7 @@ SYM_CODE_END(\asmsym) */ .macro idtentry_mce_db vector asmsym cfunc SYM_CODE_START(\asmsym) - UNWIND_HINT_IRET_REGS + UNWIND_HINT_IRET_ENTRY ENDBR ASM_CLAC cld @@ -518,7 +518,7 @@ SYM_CODE_END(\asmsym) */ .macro idtentry_vc vector asmsym cfunc SYM_CODE_START(\asmsym) - UNWIND_HINT_IRET_REGS + UNWIND_HINT_IRET_ENTRY ENDBR ASM_CLAC cld @@ -582,7 +582,7 @@ SYM_CODE_END(\asmsym) */ .macro idtentry_df vector asmsym cfunc SYM_CODE_START(\asmsym) - UNWIND_HINT_IRET_REGS offset=8 + UNWIND_HINT_IRET_ENTRY offset=8 ENDBR ASM_CLAC cld @@ -1107,7 +1107,7 @@ SYM_CODE_START(error_entry) FENCE_SWAPGS_KERNEL_ENTRY CALL_DEPTH_ACCOUNT leaq 8(%rsp), %rax /* return pt_regs pointer */ - ANNOTATE_UNRET_END + VALIDATE_UNRET_END RET .Lbstep_iret: @@ -1153,7 +1153,7 @@ SYM_CODE_END(error_return) * when PAGE_TABLE_ISOLATION is in use. Do not clobber. */ SYM_CODE_START(asm_exc_nmi) - UNWIND_HINT_IRET_REGS + UNWIND_HINT_IRET_ENTRY ENDBR /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 78ed1546b775..edb2b0cb8efe 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -210,8 +210,8 @@ * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into it's own annotation. */ -.macro ANNOTATE_UNRET_END -#ifdef CONFIG_DEBUG_ENTRY +.macro VALIDATE_UNRET_END +#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -286,7 +286,7 @@ .macro UNTRAIN_RET #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CALL_DEPTH_TRACKING) - ANNOTATE_UNRET_END + VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ @@ -297,7 +297,7 @@ .macro UNTRAIN_RET_FROM_CALL #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ defined(CONFIG_CALL_DEPTH_TRACKING) - ANNOTATE_UNRET_END + VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 97b392217c0f..4c0f28d665eb 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -12,7 +12,8 @@ .endm .macro UNWIND_HINT_ENTRY - UNWIND_HINT type=UNWIND_HINT_TYPE_ENTRY end=1 + VALIDATE_UNRET_BEGIN + UNWIND_HINT_EMPTY .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1 @@ -52,6 +53,11 @@ UNWIND_HINT_REGS base=\base offset=\offset partial=1 signal=\signal .endm +.macro UNWIND_HINT_IRET_ENTRY base=%rsp offset=0 signal=1 + VALIDATE_UNRET_BEGIN + UNWIND_HINT_IRET_REGS base=\base offset=\offset signal=\signal +.endm + .macro UNWIND_HINT_FUNC UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC .endm diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 222efd4a09bc..ee3ed15ee1f8 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -390,8 +390,6 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR - ANNOTATE_UNRET_END - /* Build pt_regs */ PUSH_AND_CLEAR_REGS @@ -451,7 +449,6 @@ SYM_CODE_END(early_idt_handler_array) SYM_CODE_START_LOCAL(early_idt_handler_common) UNWIND_HINT_IRET_REGS offset=16 - ANNOTATE_UNRET_END /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -501,8 +498,6 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8 ENDBR - ANNOTATE_UNRET_END - /* Build pt_regs */ PUSH_AND_CLEAR_REGS diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 725d7f0b6748..5aa475118820 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -124,6 +124,22 @@ .popsection .endm +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +.macro VALIDATE_UNRET_BEGIN +#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +.Lhere_\@: + .pushsection .discard.validate_unret + .long .Lhere_\@ - . + .popsection +#endif +.endm + .macro REACHABLE .Lhere_\@: .pushsection .discard.reachable diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 9a83468c0039..9787ad0f2ef4 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -42,8 +42,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 /* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#define UNWIND_HINT_TYPE_SAVE 4 +#define UNWIND_HINT_TYPE_RESTORE 5 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h index 9a83468c0039..9787ad0f2ef4 100644 --- a/tools/include/linux/objtool_types.h +++ b/tools/include/linux/objtool_types.h @@ -42,8 +42,7 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 /* The below hint types don't have corresponding ORC types */ #define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#define UNWIND_HINT_TYPE_SAVE 4 +#define UNWIND_HINT_TYPE_RESTORE 5 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index efc2baa02883..10be80b3fe67 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2307,16 +2307,9 @@ static int read_unwind_hints(struct objtool_file *file) WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", insn->sec, insn->offset); } - - insn->entry = 1; } } - if (hint->type == UNWIND_HINT_TYPE_ENTRY) { - hint->type = UNWIND_HINT_TYPE_CALL; - insn->entry = 1; - } - if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -2449,6 +2442,34 @@ static int read_instr_hints(struct objtool_file *file) return 0; } +static int read_validate_unret_hints(struct objtool_file *file) +{ + struct section *sec; + struct instruction *insn; + struct reloc *reloc; + + sec = find_section_by_name(file->elf, ".rela.discard.validate_unret"); + if (!sec) + return 0; + + list_for_each_entry(reloc, &sec->reloc_list, list) { + if (reloc->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, reloc->sym->sec, reloc->addend); + if (!insn) { + WARN("bad .discard.instr_end entry"); + return -1; + } + insn->unret = 1; + } + + return 0; +} + + static int read_intra_function_calls(struct objtool_file *file) { struct instruction *insn; @@ -2667,6 +2688,10 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret; + ret = read_validate_unret_hints(file); + if (ret) + return ret; + return 0; } @@ -3863,10 +3888,10 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) /* * Validate rethunk entry constraint: must untrain RET before the first RET. * - * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * Follow every branch (intra-function) and ensure VALIDATE_UNRET_END comes * before an actual RET instruction. */ -static int validate_entry(struct objtool_file *file, struct instruction *insn) +static int validate_unret(struct objtool_file *file, struct instruction *insn) { struct instruction *next, *dest; int ret, warnings = 0; @@ -3874,10 +3899,10 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) for (;;) { next = next_insn_to_validate(file, insn); - if (insn->visited & VISITED_ENTRY) + if (insn->visited & VISITED_UNRET) return 0; - insn->visited |= VISITED_ENTRY; + insn->visited |= VISITED_UNRET; if (!insn->ignore_alts && insn->alts) { struct alternative *alt; @@ -3887,7 +3912,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) if (alt->skip_orig) skip_orig = true; - ret = validate_entry(file, alt->insn); + ret = validate_unret(file, alt->insn); if (ret) { if (opts.backtrace) BT_FUNC("(alt)", insn); @@ -3915,7 +3940,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) insn->sec, insn->offset); return -1; } - ret = validate_entry(file, insn->jump_dest); + ret = validate_unret(file, insn->jump_dest); if (ret) { if (opts.backtrace) { BT_FUNC("(branch%s)", insn, @@ -3940,7 +3965,7 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) return -1; } - ret = validate_entry(file, dest); + ret = validate_unret(file, dest); if (ret) { if (opts.backtrace) BT_FUNC("(call)", insn); @@ -3976,19 +4001,19 @@ static int validate_entry(struct objtool_file *file, struct instruction *insn) } /* - * Validate that all branches starting at 'insn->entry' encounter UNRET_END - * before RET. + * Validate that all branches starting at VALIDATE_UNRET_BEGIN encounter + * VALIDATE_UNRET_END before RET. */ -static int validate_unret(struct objtool_file *file) +static int validate_unrets(struct objtool_file *file) { struct instruction *insn; int ret, warnings = 0; for_each_insn(file, insn) { - if (!insn->entry) + if (!insn->unret) continue; - ret = validate_entry(file, insn); + ret = validate_unret(file, insn); if (ret < 0) { WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); return ret; @@ -4607,7 +4632,7 @@ int check(struct objtool_file *file) * Must be after validate_branch() and friends, it plays * further games with insn->visited. */ - ret = validate_unret(file); + ret = validate_unrets(file); if (ret < 0) return ret; warnings += ret; diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h index 3e7c7004f7df..daa46f1f0965 100644 --- a/tools/objtool/include/objtool/check.h +++ b/tools/objtool/include/objtool/check.h @@ -61,7 +61,7 @@ struct instruction { restore : 1, retpoline_safe : 1, noendbr : 1, - entry : 1, + unret : 1, visited : 4, no_reloc : 1; /* 10 bit hole */ @@ -92,7 +92,7 @@ static inline struct symbol *insn_func(struct instruction *insn) #define VISITED_BRANCH 0x01 #define VISITED_BRANCH_UACCESS 0x02 #define VISITED_BRANCH_MASK 0x03 -#define VISITED_ENTRY 0x04 +#define VISITED_UNRET 0x04 static inline bool is_static_jump(struct instruction *insn) { -- GitLab From fb799447ae2974a07907906dff5bd4b9e47b7123 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 1 Mar 2023 07:13:12 -0800 Subject: [PATCH 1202/5631] x86,objtool: Split UNWIND_HINT_EMPTY in two Mark reported that the ORC unwinder incorrectly marks an unwind as reliable when the unwind terminates prematurely in the dark corners of return_to_handler() due to lack of information about the next frame. The problem is UNWIND_HINT_EMPTY is used in two different situations: 1) The end of the kernel stack unwind before hitting user entry, boot code, or fork entry 2) A blind spot in ORC coverage where the unwinder has to bail due to lack of information about the next frame The ORC unwinder has no way to tell the difference between the two. When it encounters an undefined stack state with 'end=1', it blindly marks the stack reliable, which can break the livepatch consistency model. Fix it by splitting UNWIND_HINT_EMPTY into UNWIND_HINT_UNDEFINED and UNWIND_HINT_END_OF_STACK. Reported-by: Mark Rutland Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Acked-by: Steven Rostedt (Google) Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/fd6212c8b450d3564b855e1cb48404d6277b4d9f.1677683419.git.jpoimboe@kernel.org --- .../livepatch/reliable-stacktrace.rst | 2 +- arch/x86/entry/entry_64.S | 12 ++++----- arch/x86/include/asm/orc_types.h | 14 +++++----- arch/x86/include/asm/unwind_hints.h | 12 ++++++--- arch/x86/kernel/ftrace_64.S | 2 +- arch/x86/kernel/head_64.S | 12 ++++----- arch/x86/kernel/relocate_kernel_64.S | 10 +++---- arch/x86/kernel/unwind_orc.c | 15 +++++------ arch/x86/lib/retpoline.S | 6 ++--- arch/x86/platform/pvh/head.S | 2 +- arch/x86/xen/xen-asm.S | 4 +-- arch/x86/xen/xen-head.S | 4 +-- include/linux/objtool.h | 10 +++---- include/linux/objtool_types.h | 27 ++++++++++++------- scripts/sorttable.h | 2 +- tools/arch/x86/include/asm/orc_types.h | 14 +++++----- tools/include/linux/objtool_types.h | 27 ++++++++++++------- tools/objtool/check.c | 2 +- tools/objtool/orc_dump.c | 8 ++++-- tools/objtool/orc_gen.c | 26 +++++++++--------- 20 files changed, 116 insertions(+), 95 deletions(-) diff --git a/Documentation/livepatch/reliable-stacktrace.rst b/Documentation/livepatch/reliable-stacktrace.rst index 67459d2ca2af..d56bb706172f 100644 --- a/Documentation/livepatch/reliable-stacktrace.rst +++ b/Documentation/livepatch/reliable-stacktrace.rst @@ -183,7 +183,7 @@ trampoline or return trampoline. For example, considering the x86_64 .. code-block:: none SYM_CODE_START(return_to_handler) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED subq $24, %rsp /* Save the return values */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 5b93eb7db0ab..45e135be2a9f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -205,7 +205,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -286,7 +286,7 @@ SYM_FUNC_END(__switch_to_asm) .pushsection .text, "ax" __FUNC_ALIGN SYM_CODE_START_NOALIGN(ret_from_fork) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR // copy_thread CALL_DEPTH_ACCOUNT movq %rax, %rdi @@ -303,7 +303,7 @@ SYM_CODE_START_NOALIGN(ret_from_fork) 1: /* kernel thread */ - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK movq %r12, %rdi CALL_NOSPEC rbx /* @@ -643,7 +643,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -869,7 +869,7 @@ SYM_CODE_END(exc_xen_hypervisor_callback) */ __FUNC_ALIGN SYM_CODE_START_NOALIGN(xen_failsafe_callback) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ENDBR movl %ds, %ecx cmpw %cx, 0x10(%rsp) @@ -1520,7 +1520,7 @@ SYM_CODE_END(asm_exc_nmi) * MSRs to fully disable 32-bit SYSCALL. */ SYM_CODE_START(ignore_sysret) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax sysretl diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h index b4d4ec78589e..46d7e06763c9 100644 --- a/arch/x86/include/asm/orc_types.h +++ b/arch/x86/include/asm/orc_types.h @@ -39,9 +39,11 @@ #define ORC_REG_SP_INDIRECT 9 #define ORC_REG_MAX 15 -#define ORC_TYPE_CALL 0 -#define ORC_TYPE_REGS 1 -#define ORC_TYPE_REGS_PARTIAL 2 +#define ORC_TYPE_UNDEFINED 0 +#define ORC_TYPE_END_OF_STACK 1 +#define ORC_TYPE_CALL 2 +#define ORC_TYPE_REGS 3 +#define ORC_TYPE_REGS_PARTIAL 4 #ifndef __ASSEMBLY__ #include @@ -60,16 +62,14 @@ struct orc_entry { #if defined(__LITTLE_ENDIAN_BITFIELD) unsigned sp_reg:4; unsigned bp_reg:4; - unsigned type:2; + unsigned type:3; unsigned signal:1; - unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; unsigned unused:4; - unsigned end:1; unsigned signal:1; - unsigned type:2; + unsigned type:3; #endif } __packed; diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 4c0f28d665eb..01cb9692b160 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -7,13 +7,17 @@ #ifdef __ASSEMBLY__ -.macro UNWIND_HINT_EMPTY - UNWIND_HINT type=UNWIND_HINT_TYPE_CALL end=1 +.macro UNWIND_HINT_END_OF_STACK + UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK +.endm + +.macro UNWIND_HINT_UNDEFINED + UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED .endm .macro UNWIND_HINT_ENTRY VALIDATE_UNRET_BEGIN - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK .endm .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1 @@ -73,7 +77,7 @@ #else #define UNWIND_HINT_FUNC \ - UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0, 0) + UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1265ad519249..0387732e9c3f 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -340,7 +340,7 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__) #ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_CODE_START(return_to_handler) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR subq $16, %rsp diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ee3ed15ee1f8..8d8d25c64827 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -42,7 +42,7 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map) __HEAD .code64 SYM_CODE_START_NOALIGN(startup_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, * and someone has loaded an identity mapped page table @@ -105,7 +105,7 @@ SYM_CODE_START_NOALIGN(startup_64) lretq .Lon_kernel_cs: - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK /* Sanitize CPU configuration */ call verify_cpu @@ -127,7 +127,7 @@ SYM_CODE_START_NOALIGN(startup_64) SYM_CODE_END(startup_64) SYM_CODE_START(secondary_startup_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR /* * At this point the CPU runs in 64bit mode CS.L = 1 CS.D = 0, @@ -156,7 +156,7 @@ SYM_CODE_START(secondary_startup_64) * verify_cpu() above to make sure NX is enabled. */ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR /* @@ -238,7 +238,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) ANNOTATE_RETPOLINE_SAFE jmp *%rax 1: - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR // above /* @@ -371,7 +371,7 @@ SYM_CODE_END(secondary_startup_64) */ SYM_CODE_START(start_cpu0) ANNOTATE_NOENDBR - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK movq initial_stack(%rip), %rsp jmp .Ljump_to_C_code SYM_CODE_END(start_cpu0) diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 4a73351f87f8..56cab1bb25f5 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -43,7 +43,7 @@ .code64 SYM_CODE_START_NOALIGN(relocate_range) SYM_CODE_START_NOALIGN(relocate_kernel) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR /* * %rdi indirection_page @@ -113,7 +113,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) SYM_CODE_END(relocate_kernel) SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK /* set return address to 0 if not preserving context */ pushq $0 /* store the start address on the stack */ @@ -231,7 +231,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) SYM_CODE_END(identity_mapped) SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR // RET target, above movq RSP(%r8), %rsp movq CR4(%r8), %rax @@ -256,8 +256,8 @@ SYM_CODE_END(virtual_mapped) /* Do the copies */ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) - UNWIND_HINT_EMPTY - movq %rdi, %rcx /* Put the page_list in %rcx */ + UNWIND_HINT_END_OF_STACK + movq %rdi, %rcx /* Put the page_list in %rcx */ xorl %edi, %edi xorl %esi, %esi jmp 1f diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 8348ac581de3..3ac50b7298d1 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -158,7 +158,6 @@ static struct orc_entry orc_fp_entry = { .sp_offset = 16, .bp_reg = ORC_REG_PREV_SP, .bp_offset = -16, - .end = 0, }; static struct orc_entry *orc_find(unsigned long ip) @@ -250,13 +249,13 @@ static int orc_sort_cmp(const void *_a, const void *_b) return -1; /* - * The "weak" section terminator entries need to always be on the left + * The "weak" section terminator entries need to always be first * to ensure the lookup code skips them in favor of real entries. * These terminator entries exist to handle any gaps created by * whitelisted .o files which didn't get objtool generation. */ orc_a = cur_orc_table + (a - cur_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, @@ -474,14 +473,12 @@ bool unwind_next_frame(struct unwind_state *state) */ orc = &orc_fp_entry; state->error = true; - } - - /* End-of-stack check for kernel threads: */ - if (orc->sp_reg == ORC_REG_UNDEFINED) { - if (!orc->end) + } else { + if (orc->type == ORC_TYPE_UNDEFINED) goto err; - goto the_end; + if (orc->type == ORC_TYPE_END_OF_STACK) + goto the_end; } state->signal = orc->signal; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f61c65322be..27ef53fab6bd 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -33,7 +33,7 @@ .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR ALTERNATIVE_2 __stringify(RETPOLINE \reg), \ @@ -75,7 +75,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_call_thunk_\reg, SYM_L_GLOBAL) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR CALL_DEPTH_ACCOUNT @@ -103,7 +103,7 @@ SYM_CODE_END(__x86_indirect_call_thunk_array) .align RETPOLINE_THUNK_SIZE SYM_INNER_LABEL(__x86_indirect_jump_thunk_\reg, SYM_L_GLOBAL) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR POLINE \reg ANNOTATE_UNRET_SAFE diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index 7fe564eaf228..c4365a05ab83 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -50,7 +50,7 @@ #define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8) SYM_CODE_START_LOCAL(pvh_start_xen) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK cld lgdt (_pa(gdt)) diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 4a184f6e4e4d..08f1ceb9eb81 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -165,7 +165,7 @@ xen_pv_trap asm_exc_xen_hypervisor_callback SYM_CODE_START(xen_early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ENDBR pop %rcx pop %r11 @@ -193,7 +193,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * rsp->rax } */ SYM_CODE_START(xen_iret) - UNWIND_HINT_EMPTY + UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR pushq $0 jmp hypercall_iret diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index e36ea4268bd2..6eafdd17c242 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -45,7 +45,7 @@ SYM_CODE_END(hypercall_page) #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR cld @@ -71,7 +71,7 @@ SYM_CODE_END(startup_xen) #ifdef CONFIG_XEN_PV_SMP .pushsection .text SYM_CODE_START(asm_cpu_bringup_and_idle) - UNWIND_HINT_EMPTY + UNWIND_HINT_END_OF_STACK ENDBR call cpu_bringup_and_idle diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 5aa475118820..03f82c2c2ebf 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -10,7 +10,7 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -19,7 +19,6 @@ ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -91,7 +90,7 @@ * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ @@ -100,7 +99,6 @@ .byte \sp_reg .byte \type .byte \signal - .byte \end .balign 4 .popsection .endm @@ -153,14 +151,14 @@ #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal, end) "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index 9787ad0f2ef4..453a4f4ef39d 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -16,12 +16,18 @@ struct unwind_hint { u8 sp_reg; u8 type; u8 signal; - u8 end; }; #endif /* __ASSEMBLY__ */ /* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP * (the caller's SP right before it made the call). Used for all callable * functions, i.e. all C code and all callable asm functions. @@ -32,17 +38,20 @@ struct unwind_hint { * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 /* The below hint types don't have corresponding ORC types */ -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_SAVE 4 -#define UNWIND_HINT_TYPE_RESTORE 5 +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/scripts/sorttable.h b/scripts/sorttable.h index deb7c1d3e979..7bd0184380d3 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -128,7 +128,7 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = g_orc_table + (a - g_orc_ip_table); - return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; + return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } static void *sort_orctable(void *arg) diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h index b4d4ec78589e..46d7e06763c9 100644 --- a/tools/arch/x86/include/asm/orc_types.h +++ b/tools/arch/x86/include/asm/orc_types.h @@ -39,9 +39,11 @@ #define ORC_REG_SP_INDIRECT 9 #define ORC_REG_MAX 15 -#define ORC_TYPE_CALL 0 -#define ORC_TYPE_REGS 1 -#define ORC_TYPE_REGS_PARTIAL 2 +#define ORC_TYPE_UNDEFINED 0 +#define ORC_TYPE_END_OF_STACK 1 +#define ORC_TYPE_CALL 2 +#define ORC_TYPE_REGS 3 +#define ORC_TYPE_REGS_PARTIAL 4 #ifndef __ASSEMBLY__ #include @@ -60,16 +62,14 @@ struct orc_entry { #if defined(__LITTLE_ENDIAN_BITFIELD) unsigned sp_reg:4; unsigned bp_reg:4; - unsigned type:2; + unsigned type:3; unsigned signal:1; - unsigned end:1; #elif defined(__BIG_ENDIAN_BITFIELD) unsigned bp_reg:4; unsigned sp_reg:4; unsigned unused:4; - unsigned end:1; unsigned signal:1; - unsigned type:2; + unsigned type:3; #endif } __packed; diff --git a/tools/include/linux/objtool_types.h b/tools/include/linux/objtool_types.h index 9787ad0f2ef4..453a4f4ef39d 100644 --- a/tools/include/linux/objtool_types.h +++ b/tools/include/linux/objtool_types.h @@ -16,12 +16,18 @@ struct unwind_hint { u8 sp_reg; u8 type; u8 signal; - u8 end; }; #endif /* __ASSEMBLY__ */ /* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP * (the caller's SP right before it made the call). Used for all callable * functions, i.e. all C code and all callable asm functions. @@ -32,17 +38,20 @@ struct unwind_hint { * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that * sp_reg+sp_offset points to the iret return frame. * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 /* The below hint types don't have corresponding ORC types */ -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_SAVE 4 -#define UNWIND_HINT_TYPE_RESTORE 5 +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 10be80b3fe67..cae6ac6ff246 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2243,6 +2243,7 @@ static void set_func_state(struct cfi_state *state) memcpy(&state->regs, &initial_func_cfi.regs, CFI_NUM_REGS * sizeof(struct cfi_reg)); state->stack_size = initial_func_cfi.cfa.offset; + state->type = UNWIND_HINT_TYPE_CALL; } static int read_unwind_hints(struct objtool_file *file) @@ -2327,7 +2328,6 @@ static int read_unwind_hints(struct objtool_file *file) cfi.cfa.offset = bswap_if_needed(file->elf, hint->sp_offset); cfi.type = hint->type; cfi.signal = hint->signal; - cfi.end = hint->end; insn->cfi = cfi_hash_find_or_add(&cfi); } diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c index 97ecbb8b9034..0e183bb1c720 100644 --- a/tools/objtool/orc_dump.c +++ b/tools/objtool/orc_dump.c @@ -38,6 +38,10 @@ static const char *reg_name(unsigned int reg) static const char *orc_type_name(unsigned int type) { switch (type) { + case ORC_TYPE_UNDEFINED: + return "(und)"; + case ORC_TYPE_END_OF_STACK: + return "end"; case ORC_TYPE_CALL: return "call"; case ORC_TYPE_REGS: @@ -201,6 +205,7 @@ int orc_dump(const char *_objname) printf("%llx:", (unsigned long long)(orc_ip_addr + (i * sizeof(int)) + orc_ip[i])); } + printf("type:%s", orc_type_name(orc[i].type)); printf(" sp:"); @@ -210,8 +215,7 @@ int orc_dump(const char *_objname) print_reg(orc[i].bp_reg, bswap_if_needed(&dummy_elf, orc[i].bp_offset)); - printf(" type:%s signal:%d end:%d\n", - orc_type_name(orc[i].type), orc[i].signal, orc[i].end); + printf(" signal:%d\n", orc[i].signal); } elf_end(elf); diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e85bbb996f6c..b327f9ccfe73 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -21,12 +21,22 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, memset(orc, 0, sizeof(*orc)); if (!cfi) { - orc->end = 0; - orc->sp_reg = ORC_REG_UNDEFINED; + /* + * This is usually either unreachable nops/traps (which don't + * trigger unreachable instruction warnings), or + * STACK_FRAME_NON_STANDARD functions. + */ + orc->type = ORC_TYPE_UNDEFINED; return 0; } switch (cfi->type) { + case UNWIND_HINT_TYPE_UNDEFINED: + orc->type = ORC_TYPE_UNDEFINED; + return 0; + case UNWIND_HINT_TYPE_END_OF_STACK: + orc->type = ORC_TYPE_END_OF_STACK; + return 0; case UNWIND_HINT_TYPE_CALL: orc->type = ORC_TYPE_CALL; break; @@ -42,14 +52,8 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, return -1; } - orc->end = cfi->end; orc->signal = cfi->signal; - if (cfi->cfa.base == CFI_UNDEFINED) { - orc->sp_reg = ORC_REG_UNDEFINED; - return 0; - } - switch (cfi->cfa.base) { case CFI_SP: orc->sp_reg = ORC_REG_SP; @@ -163,11 +167,7 @@ int orc_create(struct objtool_file *file) struct orc_list_entry *entry; struct list_head orc_list; - struct orc_entry null = { - .sp_reg = ORC_REG_UNDEFINED, - .bp_reg = ORC_REG_UNDEFINED, - .type = ORC_TYPE_CALL, - }; + struct orc_entry null = { .type = ORC_TYPE_UNDEFINED }; /* Build a deduplicated list of ORC entries: */ INIT_LIST_HEAD(&orc_list); -- GitLab From 3d8f61bf8bcd69bcd397276d53aa18f7ca8347f9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 24 Jan 2023 19:45:19 +0000 Subject: [PATCH 1203/5631] x86: KVM: Add common feature flag for AMD's PSFD Use a common X86_FEATURE_* flag for AMD's PSFD, and suppress it from /proc/cpuinfo via the standard method of an empty string instead of hacking in a one-off "private" #define in KVM. The request that led to KVM defining its own flag was really just that the feature not show up in /proc/cpuinfo, and additional patches+discussions in the interim have clarified that defining flags in cpufeatures.h purely so that KVM can advertise features to userspace is ok so long as the kernel already uses a word to track the associated CPUID leaf. No functional change intended. Link: https://lore.kernel.org/all/d1b1e0da-29f0-c443-6c86-9549bbe1c79d@redhat.como Link: https://lore.kernel.org/all/YxGZH7aOXQF7Pu5q@nazgul.tnic Link: https://lore.kernel.org/all/Y3O7UYWfOLfJkwM%2F@zn.tnic Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20230124194519.2893234-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kvm/cpuid.c | 8 +------- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 73c9672c123b..42abcd3db7a7 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -337,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1ad3bde72526..6972e0be60fa 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -60,12 +60,6 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -/* - * This one is tied to SSB in the user API, and not - * visible in /proc/cpuinfo. - */ -#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ - #define F feature_bit /* Scattered Flag - For features that are scattered by cpufeatures.h. */ @@ -715,7 +709,7 @@ void kvm_set_cpu_caps(void) F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | - __feature_bit(KVM_X86_FEATURE_AMD_PSFD) + F(AMD_PSFD) ); /* -- GitLab From 65966aaca18a5cbf42ac22234cb9cbbf60a4d33c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 16 Feb 2023 12:22:54 -0800 Subject: [PATCH 1204/5631] KVM: x86: Assert that the emulator doesn't load CS with garbage in !RM Yell loudly if KVM attempts to load CS outside of Real Mode without an accompanying control transfer type, i.e. on X86_TRANSFER_NONE. KVM uses X86_TRANSFER_NONE when emulating IRET and exceptions/interrupts for Real Mode, but IRET emulation for Protected Mode is non-existent. WARN instead of trying to pass in a less-wrong type, e.g. X86_TRANSFER_RET, as emulating IRET goes even beyond emulating FAR RET (which KVM also doesn't fully support). Reported-by: Hou Wenlong Link: https://lore.kernel.org/r/20230216202254.671772-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/emulate.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a20bec931764..936a397a08cd 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1640,6 +1640,14 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; break; case VCPU_SREG_CS: + /* + * KVM uses "none" when loading CS as part of emulating Real + * Mode exceptions and IRET (handled above). In all other + * cases, loading CS without a control transfer is a KVM bug. + */ + if (WARN_ON_ONCE(transfer == X86_TRANSFER_NONE)) + goto exception; + if (!(seg_desc.type & 8)) goto exception; -- GitLab From 99b30869804ea59d9596cdbefa5cc3aabd588521 Mon Sep 17 00:00:00 2001 From: Robert Hoo Date: Wed, 8 Mar 2023 15:29:36 +0800 Subject: [PATCH 1205/5631] KVM: x86: Remove a redundant guest cpuid check in kvm_set_cr4() If !guest_cpuid_has(vcpu, X86_FEATURE_PCID), CR4.PCIDE would have been in vcpu->arch.cr4_guest_rsvd_bits and failed earlier kvm_is_valid_cr4() check. Remove this meaningless check. Reviewed-by: Xiaoyao Li Signed-off-by: Robert Hoo Fixes: 4683d758f48e ("KVM: x86: Supplement __cr4_reserved_bits() with X86_FEATURE_PCID check") Link: https://lore.kernel.org/r/20230308072936.1293101-1-robert.hu@intel.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3fab192862d4..2e0933f510ee 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1196,9 +1196,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - return 1; - /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) return 1; -- GitLab From 14aa40a1d05ef27c42fdfacd5a81f5df6a49ee39 Mon Sep 17 00:00:00 2001 From: Li kunyu Date: Tue, 13 Dec 2022 16:02:36 +0800 Subject: [PATCH 1206/5631] kvm: kvm_main: Remove unnecessary (void*) conversions void * pointer assignment does not require a forced replacement. Signed-off-by: Li kunyu Link: https://lore.kernel.org/r/20221213080236.3969-1-kunyu@nfschina.com Signed-off-by: Sean Christopherson --- virt/kvm/kvm_main.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f40b72eb0e7b..8f0a7da37e32 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3866,7 +3866,7 @@ static int create_vcpu_fd(struct kvm_vcpu *vcpu) #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS static int vcpu_get_pid(void *data, u64 *val) { - struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data; + struct kvm_vcpu *vcpu = data; *val = pid_nr(rcu_access_pointer(vcpu->pid)); return 0; } @@ -5572,8 +5572,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, const char *fmt) { int ret; - struct kvm_stat_data *stat_data = (struct kvm_stat_data *) - inode->i_private; + struct kvm_stat_data *stat_data = inode->i_private; /* * The debugfs files are a reference to the kvm struct which @@ -5594,8 +5593,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, static int kvm_debugfs_release(struct inode *inode, struct file *file) { - struct kvm_stat_data *stat_data = (struct kvm_stat_data *) - inode->i_private; + struct kvm_stat_data *stat_data = inode->i_private; simple_attr_release(inode, file); kvm_put_kvm(stat_data->kvm); @@ -5644,7 +5642,7 @@ static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) static int kvm_stat_data_get(void *data, u64 *val) { int r = -EFAULT; - struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; + struct kvm_stat_data *stat_data = data; switch (stat_data->kind) { case KVM_STAT_VM: @@ -5663,7 +5661,7 @@ static int kvm_stat_data_get(void *data, u64 *val) static int kvm_stat_data_clear(void *data, u64 val) { int r = -EFAULT; - struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data; + struct kvm_stat_data *stat_data = data; if (val) return -EINVAL; -- GitLab From 12aad9164763bb4890277d3b2a4664f443a48e3f Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 17 Feb 2023 20:33:35 +0100 Subject: [PATCH 1207/5631] KVM: x86: Shrink struct kvm_pmu Move the 'version' member to the beginning of the structure to reuse an existing hole instead of introducing another one. This allows us to save 8 bytes for 64 bit builds. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230217193336.15278-2-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a45de1118a42..a440ceae06fb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -515,6 +515,7 @@ struct kvm_pmc { #define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { + u8 version; unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; unsigned available_event_types; @@ -527,7 +528,6 @@ struct kvm_pmu { u64 global_ovf_ctrl_mask; u64 reserved_bits; u64 raw_event_mask; - u8 version; struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; struct irq_work irq_work; -- GitLab From f530b531fb9e05eb134cfc334242799ea974d111 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Fri, 17 Feb 2023 20:33:36 +0100 Subject: [PATCH 1208/5631] KVM: Shrink struct kvm_mmu_memory_cache Move the 'capacity' member around to make use of the padding hole on 64 bit systems instead of introducing yet another one. This allows us to save 8 bytes per instance for 64 bit builds of which, e.g., x86's struct kvm_vcpu_arch has a few. Signed-off-by: Mathias Krause Link: https://lore.kernel.org/r/20230217193336.15278-3-minipli@grsecurity.net Signed-off-by: Sean Christopherson --- include/linux/kvm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2728d49bbdf6..6f4737d5046a 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -91,11 +91,11 @@ struct gfn_to_pfn_cache { * is topped up (__kvm_mmu_topup_memory_cache()). */ struct kvm_mmu_memory_cache { - int nobjs; gfp_t gfp_zero; gfp_t gfp_custom; struct kmem_cache *kmem_cache; int capacity; + int nobjs; void **objects; }; #endif -- GitLab From 752b8a9b4d98da55ab84cfb0d37adca8cd3d17b1 Mon Sep 17 00:00:00 2001 From: Shaoqin Huang Date: Mon, 20 Feb 2023 11:49:09 +0800 Subject: [PATCH 1209/5631] KVM: Add the missed title format The 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 now is not a title, make it as a title to keep the format consistent. Signed-off-by: Shaoqin Huang Fixes: 106ee47dc633 ("docs: kvm: Convert api.txt to ReST format") Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20230220034910.11024-1-shahuang@redhat.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/api.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 48fad6556822..a69e91088d76 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -7267,6 +7267,7 @@ and injected exceptions. will clear DR6.RTM. 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 +-------------------------------------- :Architectures: x86, arm64, mips :Parameters: args[0] whether feature should be enabled or not -- GitLab From 7ffc2e89518a3ad9b81faad67254737d87073f44 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 24 Feb 2023 11:28:32 -0800 Subject: [PATCH 1210/5631] KVM: MIPS: Make kvm_mips_callbacks const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make kvm_mips_callbacks fully const as it's now hardcoded to point at kvm_vz_callbacks, the only remaining the set of callbacks. Link: https://lore.kernel.org/all/beb697c2-dfad-780e-4638-76b229f28731@linaro.org Suggested-by: Philippe Mathieu-Daudé Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/20230224192832.1286267-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/mips/include/asm/kvm_host.h | 2 +- arch/mips/kvm/vz.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 2803c9c21ef9..957121a495f0 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -757,7 +757,7 @@ struct kvm_mips_callbacks { int (*vcpu_run)(struct kvm_vcpu *vcpu); void (*vcpu_reenter)(struct kvm_vcpu *vcpu); }; -extern struct kvm_mips_callbacks *kvm_mips_callbacks; +extern const struct kvm_mips_callbacks * const kvm_mips_callbacks; int kvm_mips_emulation_init(void); /* Debug: dump vcpu state */ diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index dafab003ea0d..3d21cbfa7443 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -3305,7 +3305,7 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { }; /* FIXME: Get rid of the callbacks now that trap-and-emulate is gone. */ -struct kvm_mips_callbacks *kvm_mips_callbacks = &kvm_vz_callbacks; +const struct kvm_mips_callbacks * const kvm_mips_callbacks = &kvm_vz_callbacks; int kvm_mips_emulation_init(void) { -- GitLab From 907d73bc0b0a00a9cc3254d14351fc239899473f Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 23 Mar 2023 18:31:40 -0700 Subject: [PATCH 1211/5631] Input: xpad - remove unused field in VID/PID table The list of specific VID/PID combinations for various controllers recently added a new field "xtype". However, this field isn't used, nor filled in the table itself, and was likely added by mistake and overlooked during review. Since this field isn't used, it's safe to remove. Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230225012147.276489-3-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index f642ec8e92dd..a1f23da7d72c 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -126,7 +126,6 @@ static const struct xpad_device { char *name; u8 mapping; u8 xtype; - u8 packet_type; } xpad_device[] = { { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 }, -- GitLab From 1999a6b12a3b5c8953fc9ec74863ebc75a1b851d Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 23 Mar 2023 18:32:43 -0700 Subject: [PATCH 1212/5631] Input: xpad - add VID for Turtle Beach controllers This adds support for the Turtle Beach REACT-R and Recon Xbox controllers Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230225012147.276489-4-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index a1f23da7d72c..49ae963e5f9d 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -474,6 +474,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x0f0d), /* Hori Controllers */ XPAD_XBOXONE_VENDOR(0x0f0d), /* Hori Controllers */ XPAD_XBOX360_VENDOR(0x1038), /* SteelSeries Controllers */ + XPAD_XBOXONE_VENDOR(0x10f5), /* Turtle Beach Controllers */ XPAD_XBOX360_VENDOR(0x11c9), /* Nacon GC100XF */ XPAD_XBOX360_VENDOR(0x1209), /* Ardwiino Controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* X-Box 360 dance pads */ -- GitLab From 77987b872fcfeaf36b4760fe5d77a0cf9ac7fdbe Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 21 Mar 2023 11:54:15 -0700 Subject: [PATCH 1213/5631] dt-bindings: input: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Reviewed-by: Mattijs Korpershoek # for mediatek,mt6779-keypad.yaml Link: https://lore.kernel.org/r/20230320234718.2930154-1-robh@kernel.org Signed-off-by: Dmitry Torokhov --- Documentation/devicetree/bindings/input/adc-joystick.yaml | 4 ++-- .../devicetree/bindings/input/google,cros-ec-keyb.yaml | 2 +- Documentation/devicetree/bindings/input/imx-keypad.yaml | 2 +- Documentation/devicetree/bindings/input/matrix-keymap.yaml | 2 +- .../devicetree/bindings/input/mediatek,mt6779-keypad.yaml | 2 +- .../devicetree/bindings/input/microchip,cap11xx.yaml | 4 ++-- Documentation/devicetree/bindings/input/pwm-vibrator.yaml | 4 ++-- Documentation/devicetree/bindings/input/regulator-haptic.yaml | 4 ++-- .../bindings/input/touchscreen/elan,elants_i2c.yaml | 4 ++-- 9 files changed, 14 insertions(+), 14 deletions(-) diff --git a/Documentation/devicetree/bindings/input/adc-joystick.yaml b/Documentation/devicetree/bindings/input/adc-joystick.yaml index da0f8dfca8bf..6c244d66f8ce 100644 --- a/Documentation/devicetree/bindings/input/adc-joystick.yaml +++ b/Documentation/devicetree/bindings/input/adc-joystick.yaml @@ -2,8 +2,8 @@ # Copyright 2019-2020 Artur Rojek %YAML 1.2 --- -$id: "http://devicetree.org/schemas/input/adc-joystick.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/input/adc-joystick.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: ADC attached joystick diff --git a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml index a8abdb39623b..fefaaf46a240 100644 --- a/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml +++ b/Documentation/devicetree/bindings/input/google,cros-ec-keyb.yaml @@ -57,7 +57,7 @@ if: contains: const: google,cros-ec-keyb then: - $ref: "/schemas/input/matrix-keymap.yaml#" + $ref: /schemas/input/matrix-keymap.yaml# required: - keypad,num-rows - keypad,num-columns diff --git a/Documentation/devicetree/bindings/input/imx-keypad.yaml b/Documentation/devicetree/bindings/input/imx-keypad.yaml index 7514df62b592..b110eb1f3358 100644 --- a/Documentation/devicetree/bindings/input/imx-keypad.yaml +++ b/Documentation/devicetree/bindings/input/imx-keypad.yaml @@ -10,7 +10,7 @@ maintainers: - Liu Ying allOf: - - $ref: "/schemas/input/matrix-keymap.yaml#" + - $ref: /schemas/input/matrix-keymap.yaml# description: | The KPP is designed to interface with a keypad matrix with 2-point contact diff --git a/Documentation/devicetree/bindings/input/matrix-keymap.yaml b/Documentation/devicetree/bindings/input/matrix-keymap.yaml index 4d6dbe91646d..a715c2a773fe 100644 --- a/Documentation/devicetree/bindings/input/matrix-keymap.yaml +++ b/Documentation/devicetree/bindings/input/matrix-keymap.yaml @@ -21,7 +21,7 @@ description: | properties: linux,keymap: - $ref: '/schemas/types.yaml#/definitions/uint32-array' + $ref: /schemas/types.yaml#/definitions/uint32-array description: | An array of packed 1-cell entries containing the equivalent of row, column and linux key-code. The 32-bit big endian cell is packed as: diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index d768c30f48fb..47aac8794b68 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -10,7 +10,7 @@ maintainers: - Mattijs Korpershoek allOf: - - $ref: "/schemas/input/matrix-keymap.yaml#" + - $ref: /schemas/input/matrix-keymap.yaml# description: | Mediatek's Keypad controller is used to interface a SoC with a matrix-type diff --git a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml index 5fa625b5c5fb..5b5d4f7d3482 100644 --- a/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml +++ b/Documentation/devicetree/bindings/input/microchip,cap11xx.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/input/microchip,cap11xx.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/input/microchip,cap11xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Microchip CAP11xx based capacitive touch sensors diff --git a/Documentation/devicetree/bindings/input/pwm-vibrator.yaml b/Documentation/devicetree/bindings/input/pwm-vibrator.yaml index a70a636ee112..d32716c604fe 100644 --- a/Documentation/devicetree/bindings/input/pwm-vibrator.yaml +++ b/Documentation/devicetree/bindings/input/pwm-vibrator.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/input/pwm-vibrator.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/input/pwm-vibrator.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: PWM vibrator diff --git a/Documentation/devicetree/bindings/input/regulator-haptic.yaml b/Documentation/devicetree/bindings/input/regulator-haptic.yaml index 627891e1ef55..cf63f834dd7d 100644 --- a/Documentation/devicetree/bindings/input/regulator-haptic.yaml +++ b/Documentation/devicetree/bindings/input/regulator-haptic.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: "http://devicetree.org/schemas/input/regulator-haptic.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/input/regulator-haptic.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Regulator Haptic diff --git a/Documentation/devicetree/bindings/input/touchscreen/elan,elants_i2c.yaml b/Documentation/devicetree/bindings/input/touchscreen/elan,elants_i2c.yaml index f9053e5e9b24..3255c2c8951a 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/elan,elants_i2c.yaml +++ b/Documentation/devicetree/bindings/input/touchscreen/elan,elants_i2c.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/input/touchscreen/elan,elants_i2c.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/input/touchscreen/elan,elants_i2c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Elantech I2C Touchscreen -- GitLab From 704bc669e1dda3eb8f6d5cb462b21e85558a3912 Mon Sep 17 00:00:00 2001 From: Jungseung Lee Date: Mon, 20 Mar 2023 12:29:05 +0900 Subject: [PATCH 1214/5631] workqueue: Introduce show_freezable_workqueues Currently show_all_workqueue is called if freeze fails at the time of freeze the workqueues, which shows the status of all workqueues and of all worker pools. In this cases we may only need to dump state of only workqueues that are freezable and busy. This patch defines show_freezable_workqueues, which uses show_one_workqueue, a granular function that shows the state of individual workqueues, so that dump only the state of freezable workqueues at that time. tj: Minor message adjustment. Signed-off-by: Jungseung Lee Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 1 + kernel/power/process.c | 2 +- kernel/workqueue.c | 26 ++++++++++++++++++++++++-- 3 files changed, 26 insertions(+), 3 deletions(-) diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ac551b8ee7d9..3992c994787f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -472,6 +472,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); +extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); diff --git a/kernel/power/process.c b/kernel/power/process.c index 6c1c7e566d35..cae81a87cc91 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -93,7 +93,7 @@ static int try_to_freeze_tasks(bool user_only) todo - wq_busy, wq_busy); if (wq_busy) - show_all_workqueues(); + show_freezable_workqueues(); if (!wakeup || pm_debug_messages_on) { read_lock(&tasklist_lock); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 044b4eee760b..d78935e4fb5d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5065,8 +5065,7 @@ static void show_one_worker_pool(struct worker_pool *pool) /** * show_all_workqueues - dump workqueue state * - * Called from a sysrq handler or try_to_freeze_tasks() and prints out - * all busy workqueues and pools. + * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { @@ -5087,6 +5086,29 @@ void show_all_workqueues(void) rcu_read_unlock(); } +/** + * show_freezable_workqueues - dump freezable workqueue state + * + * Called from try_to_freeze_tasks() and prints out all freezable workqueues + * still busy. + */ +void show_freezable_workqueues(void) +{ + struct workqueue_struct *wq; + + rcu_read_lock(); + + pr_info("Showing freezable workqueues that are still busy:\n"); + + list_for_each_entry_rcu(wq, &workqueues, list) { + if (!(wq->flags & WQ_FREEZABLE)) + continue; + show_one_workqueue(wq); + } + + rcu_read_unlock(); +} + /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { -- GitLab From 8e4645226b4931e96d55546a1fb3863aa50b5e62 Mon Sep 17 00:00:00 2001 From: Haifeng Xu Date: Tue, 28 Feb 2023 08:35:37 +0000 Subject: [PATCH 1215/5631] cpuset: Clean up cpuset_node_allowed Commit 002f290627c2 ("cpuset: use static key better and convert to new API") has used __cpuset_node_allowed() instead of cpuset_node_allowed() to check whether we can allocate on a memory node. Now this function isn't used by anyone, so we can do the follow things to clean up it. 1. remove unused codes 2. rename __cpuset_node_allowed() to cpuset_node_allowed() 3. update comments in mm/page_alloc.c Suggested-by: Waiman Long Signed-off-by: Haifeng Xu Acked-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cpuset.h | 16 ++-------------- kernel/cgroup/cpuset.c | 4 ++-- mm/page_alloc.c | 4 ++-- 3 files changed, 6 insertions(+), 18 deletions(-) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..980b76a1237e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -80,18 +80,11 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); - -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - if (cpusets_enabled()) - return __cpuset_node_allowed(node, gfp_mask); - return true; -} +extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { - return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); + return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -223,11 +216,6 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - return true; -} - static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 636f1c682ac0..0241b07d6f21 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3831,7 +3831,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) } /* - * __cpuset_node_allowed - Can we allocate on a memory node? + * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * @@ -3870,7 +3870,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ -bool __cpuset_node_allowed(int node, gfp_t gfp_mask) +bool cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ bool allowed; /* is allocation in zone z allowed? */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ac1fc986af44..ea4e39b06475 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4217,7 +4217,7 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, retry: /* * Scan zonelist, looking for a zone with enough free. - * See also __cpuset_node_allowed() comment in kernel/cgroup/cpuset.c. + * See also cpuset_node_allowed() comment in kernel/cgroup/cpuset.c. */ no_fallback = alloc_flags & ALLOC_NOFRAGMENT; z = ac->preferred_zoneref; @@ -4891,7 +4891,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) /* * Ignore cpuset mems for non-blocking __GFP_HIGH (probably * GFP_ATOMIC) rather than fail, see the comment for - * __cpuset_node_allowed(). + * cpuset_node_allowed(). */ if (alloc_flags & ALLOC_MIN_RESERVE) alloc_flags &= ~ALLOC_CPUSET; -- GitLab From c52198601695851622f361d3f16456e9fc857629 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 20 Mar 2023 17:55:13 -0700 Subject: [PATCH 1216/5631] locking/csd_lock: Add Kconfig option for csd_debug default The csd_debug kernel parameter works well, but is inconvenient in cases where it is more closely associated with boot loaders or automation than with a particular kernel version or release. Thererfore, provide a new CSD_LOCK_WAIT_DEBUG_DEFAULT Kconfig option that defaults csd_debug to 1 when selected and 0 otherwise, with this latter being the default. Signed-off-by: Paul E. McKenney Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230321005516.50558-1-paulmck@kernel.org --- Documentation/admin-guide/kernel-parameters.txt | 6 ++++-- kernel/smp.c | 2 +- lib/Kconfig.debug | 9 +++++++++ 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..ce70777f5999 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -893,8 +893,10 @@ handling. When switched on, additional debug data is printed to the console in case a hanging CPU is detected, and that CPU is pinged again in order to try - to resolve the hang situation. - 0: disable csdlock debugging (default) + to resolve the hang situation. The default value of + this option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT + Kconfig option. + 0: disable csdlock debugging 1: enable basic csdlock debugging (minor impact) ext: enable extended csdlock debugging (more impact, but more data) diff --git a/kernel/smp.c b/kernel/smp.c index 06a413987a14..e2d558f5cef8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -158,7 +158,7 @@ void __init call_function_init(void) #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG -static DEFINE_STATIC_KEY_FALSE(csdlock_debug_enabled); +static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); static DEFINE_STATIC_KEY_FALSE(csdlock_debug_extended); static int __init csdlock_debug(char *str) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c8b379e2e9ad..e1b160a0474d 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1480,6 +1480,15 @@ config CSD_LOCK_WAIT_DEBUG include the IPI handler function currently executing (if any) and relevant stack traces. +config CSD_LOCK_WAIT_DEBUG_DEFAULT + bool "Default csd_lock_wait() debugging on at boot time" + depends on CSD_LOCK_WAIT_DEBUG + depends on 64BIT + default n + help + This option causes the csdlock_debug= kernel boot parameter to + default to 1 (basic debugging) instead of 0 (no debugging). + endmenu # lock debugging config TRACE_IRQFLAGS -- GitLab From 1771257cb447a7b27a15ed9aaf332726c47fcbcf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 20 Mar 2023 17:55:14 -0700 Subject: [PATCH 1217/5631] locking/csd_lock: Remove added data from CSD lock debugging The diagnostics added by this commit were extremely useful in one instance: a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") However, they have not seen much action since, and there have been some concerns expressed that the complexity is not worth the benefit. Therefore, manually revert this commit, but leave a comment telling people where to find these diagnostics. [ paulmck: Apply Juergen Gross feedback. ] Signed-off-by: Paul E. McKenney Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230321005516.50558-2-paulmck@kernel.org --- .../admin-guide/kernel-parameters.txt | 4 - kernel/smp.c | 233 +----------------- 2 files changed, 12 insertions(+), 225 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index ce70777f5999..b15198a85acb 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -896,10 +896,6 @@ to resolve the hang situation. The default value of this option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT Kconfig option. - 0: disable csdlock debugging - 1: enable basic csdlock debugging (minor impact) - ext: enable extended csdlock debugging (more impact, - but more data) dasd= [HW,NET] See header of drivers/s390/block/dasd_devmap.c. diff --git a/kernel/smp.c b/kernel/smp.c index e2d558f5cef8..038d666f327b 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -31,59 +31,8 @@ #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) -#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG -union cfd_seq_cnt { - u64 val; - struct { - u64 src:16; - u64 dst:16; -#define CFD_SEQ_NOCPU 0xffff - u64 type:4; -#define CFD_SEQ_QUEUE 0 -#define CFD_SEQ_IPI 1 -#define CFD_SEQ_NOIPI 2 -#define CFD_SEQ_PING 3 -#define CFD_SEQ_PINGED 4 -#define CFD_SEQ_HANDLE 5 -#define CFD_SEQ_DEQUEUE 6 -#define CFD_SEQ_IDLE 7 -#define CFD_SEQ_GOTIPI 8 -#define CFD_SEQ_HDLEND 9 - u64 cnt:28; - } u; -}; - -static char *seq_type[] = { - [CFD_SEQ_QUEUE] = "queue", - [CFD_SEQ_IPI] = "ipi", - [CFD_SEQ_NOIPI] = "noipi", - [CFD_SEQ_PING] = "ping", - [CFD_SEQ_PINGED] = "pinged", - [CFD_SEQ_HANDLE] = "handle", - [CFD_SEQ_DEQUEUE] = "dequeue (src CPU 0 == empty)", - [CFD_SEQ_IDLE] = "idle", - [CFD_SEQ_GOTIPI] = "gotipi", - [CFD_SEQ_HDLEND] = "hdlend (src CPU 0 == early)", -}; - -struct cfd_seq_local { - u64 ping; - u64 pinged; - u64 handle; - u64 dequeue; - u64 idle; - u64 gotipi; - u64 hdlend; -}; -#endif - struct cfd_percpu { call_single_data_t csd; -#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG - u64 seq_queue; - u64 seq_ipi; - u64 seq_noipi; -#endif }; struct call_function_data { @@ -159,18 +108,21 @@ void __init call_function_init(void) #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); -static DEFINE_STATIC_KEY_FALSE(csdlock_debug_extended); +/* + * Parse the csdlock_debug= kernel boot parameter. + * + * If you need to restore the old "ext" value that once provided + * additional debugging information, reapply the following commits: + * + * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") + * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") + */ static int __init csdlock_debug(char *str) { unsigned int val = 0; - if (str && !strcmp(str, "ext")) { - val = 1; - static_branch_enable(&csdlock_debug_extended); - } else - get_option(&str, &val); - + get_option(&str, &val); if (val) static_branch_enable(&csdlock_debug_enabled); @@ -181,36 +133,11 @@ __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); -static DEFINE_PER_CPU(struct cfd_seq_local, cfd_seq_local); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); -static u64 cfd_seq; - -#define CFD_SEQ(s, d, t, c) \ - (union cfd_seq_cnt){ .u.src = s, .u.dst = d, .u.type = t, .u.cnt = c } - -static u64 cfd_seq_inc(unsigned int src, unsigned int dst, unsigned int type) -{ - union cfd_seq_cnt new, old; - - new = CFD_SEQ(src, dst, type, 0); - - do { - old.val = READ_ONCE(cfd_seq); - new.u.cnt = old.u.cnt + 1; - } while (cmpxchg(&cfd_seq, old.val, new.val) != old.val); - - return old.val; -} - -#define cfd_seq_store(var, src, dst, type) \ - do { \ - if (static_branch_unlikely(&csdlock_debug_extended)) \ - var = cfd_seq_inc(src, dst, type); \ - } while (0) /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(struct __call_single_data *csd) @@ -244,80 +171,6 @@ static int csd_lock_wait_getcpu(struct __call_single_data *csd) return -1; } -static void cfd_seq_data_add(u64 val, unsigned int src, unsigned int dst, - unsigned int type, union cfd_seq_cnt *data, - unsigned int *n_data, unsigned int now) -{ - union cfd_seq_cnt new[2]; - unsigned int i, j, k; - - new[0].val = val; - new[1] = CFD_SEQ(src, dst, type, new[0].u.cnt + 1); - - for (i = 0; i < 2; i++) { - if (new[i].u.cnt <= now) - new[i].u.cnt |= 0x80000000U; - for (j = 0; j < *n_data; j++) { - if (new[i].u.cnt == data[j].u.cnt) { - /* Direct read value trumps generated one. */ - if (i == 0) - data[j].val = new[i].val; - break; - } - if (new[i].u.cnt < data[j].u.cnt) { - for (k = *n_data; k > j; k--) - data[k].val = data[k - 1].val; - data[j].val = new[i].val; - (*n_data)++; - break; - } - } - if (j == *n_data) { - data[j].val = new[i].val; - (*n_data)++; - } - } -} - -static const char *csd_lock_get_type(unsigned int type) -{ - return (type >= ARRAY_SIZE(seq_type)) ? "?" : seq_type[type]; -} - -static void csd_lock_print_extended(struct __call_single_data *csd, int cpu) -{ - struct cfd_seq_local *seq = &per_cpu(cfd_seq_local, cpu); - unsigned int srccpu = csd->node.src; - struct call_function_data *cfd = per_cpu_ptr(&cfd_data, srccpu); - struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu); - unsigned int now; - union cfd_seq_cnt data[2 * ARRAY_SIZE(seq_type)]; - unsigned int n_data = 0, i; - - data[0].val = READ_ONCE(cfd_seq); - now = data[0].u.cnt; - - cfd_seq_data_add(pcpu->seq_queue, srccpu, cpu, CFD_SEQ_QUEUE, data, &n_data, now); - cfd_seq_data_add(pcpu->seq_ipi, srccpu, cpu, CFD_SEQ_IPI, data, &n_data, now); - cfd_seq_data_add(pcpu->seq_noipi, srccpu, cpu, CFD_SEQ_NOIPI, data, &n_data, now); - - cfd_seq_data_add(per_cpu(cfd_seq_local.ping, srccpu), srccpu, CFD_SEQ_NOCPU, CFD_SEQ_PING, data, &n_data, now); - cfd_seq_data_add(per_cpu(cfd_seq_local.pinged, srccpu), srccpu, CFD_SEQ_NOCPU, CFD_SEQ_PINGED, data, &n_data, now); - - cfd_seq_data_add(seq->idle, CFD_SEQ_NOCPU, cpu, CFD_SEQ_IDLE, data, &n_data, now); - cfd_seq_data_add(seq->gotipi, CFD_SEQ_NOCPU, cpu, CFD_SEQ_GOTIPI, data, &n_data, now); - cfd_seq_data_add(seq->handle, CFD_SEQ_NOCPU, cpu, CFD_SEQ_HANDLE, data, &n_data, now); - cfd_seq_data_add(seq->dequeue, CFD_SEQ_NOCPU, cpu, CFD_SEQ_DEQUEUE, data, &n_data, now); - cfd_seq_data_add(seq->hdlend, CFD_SEQ_NOCPU, cpu, CFD_SEQ_HDLEND, data, &n_data, now); - - for (i = 0; i < n_data; i++) { - pr_alert("\tcsd: cnt(%07x): %04x->%04x %s\n", - data[i].u.cnt & ~0x80000000U, data[i].u.src, - data[i].u.dst, csd_lock_get_type(data[i].u.type)); - } - pr_alert("\tcsd: cnt now: %07x\n", now); -} - /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, @@ -368,8 +221,6 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { - if (static_branch_unlikely(&csdlock_debug_extended)) - csd_lock_print_extended(csd, cpu); dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); @@ -412,27 +263,7 @@ static __always_inline void csd_lock_wait(struct __call_single_data *csd) smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } - -static void __smp_call_single_queue_debug(int cpu, struct llist_node *node) -{ - unsigned int this_cpu = smp_processor_id(); - struct cfd_seq_local *seq = this_cpu_ptr(&cfd_seq_local); - struct call_function_data *cfd = this_cpu_ptr(&cfd_data); - struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu); - - cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE); - if (llist_add(node, &per_cpu(call_single_queue, cpu))) { - cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI); - cfd_seq_store(seq->ping, this_cpu, cpu, CFD_SEQ_PING); - send_call_function_single_ipi(cpu); - cfd_seq_store(seq->pinged, this_cpu, cpu, CFD_SEQ_PINGED); - } else { - cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI); - } -} #else -#define cfd_seq_store(var, src, dst, type) - static void csd_lock_record(struct __call_single_data *csd) { } @@ -470,19 +301,6 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { -#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG - if (static_branch_unlikely(&csdlock_debug_extended)) { - unsigned int type; - - type = CSD_TYPE(container_of(node, call_single_data_t, - node.llist)); - if (type == CSD_TYPE_SYNC || type == CSD_TYPE_ASYNC) { - __smp_call_single_queue_debug(cpu, node); - return; - } - } -#endif - /* * The list addition should be visible before sending the IPI * handler locks the list to pull the entry off it because of @@ -541,8 +359,6 @@ static int generic_exec_single(int cpu, struct __call_single_data *csd) */ void generic_smp_call_function_single_interrupt(void) { - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->gotipi, CFD_SEQ_NOCPU, - smp_processor_id(), CFD_SEQ_GOTIPI); __flush_smp_call_function_queue(true); } @@ -570,13 +386,7 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) lockdep_assert_irqs_disabled(); head = this_cpu_ptr(&call_single_queue); - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->handle, CFD_SEQ_NOCPU, - smp_processor_id(), CFD_SEQ_HANDLE); entry = llist_del_all(head); - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->dequeue, - /* Special meaning of source cpu: 0 == queue empty */ - entry ? CFD_SEQ_NOCPU : 0, - smp_processor_id(), CFD_SEQ_DEQUEUE); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ @@ -635,12 +445,8 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) } } - if (!entry) { - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->hdlend, - 0, smp_processor_id(), - CFD_SEQ_HDLEND); + if (!entry) return; - } /* * Second; run all !SYNC callbacks. @@ -678,9 +484,6 @@ static void __flush_smp_call_function_queue(bool warn_cpu_offline) */ if (entry) sched_ttwu_pending(entry); - - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->hdlend, CFD_SEQ_NOCPU, - smp_processor_id(), CFD_SEQ_HDLEND); } @@ -704,8 +507,6 @@ void flush_smp_call_function_queue(void) if (llist_empty(this_cpu_ptr(&call_single_queue))) return; - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->idle, CFD_SEQ_NOCPU, - smp_processor_id(), CFD_SEQ_IDLE); local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); @@ -929,8 +730,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { - struct cfd_percpu *pcpu = per_cpu_ptr(cfd->pcpu, cpu); - call_single_data_t *csd = &pcpu->csd; + call_single_data_t *csd = &per_cpu_ptr(cfd->pcpu, cpu)->csd; if (cond_func && !cond_func(cpu, info)) continue; @@ -944,20 +744,13 @@ static void smp_call_function_many_cond(const struct cpumask *mask, csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif - cfd_seq_store(pcpu->seq_queue, this_cpu, cpu, CFD_SEQ_QUEUE); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; - - cfd_seq_store(pcpu->seq_ipi, this_cpu, cpu, CFD_SEQ_IPI); - } else { - cfd_seq_store(pcpu->seq_noipi, this_cpu, cpu, CFD_SEQ_NOIPI); } } - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->ping, this_cpu, CFD_SEQ_NOCPU, CFD_SEQ_PING); - /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the @@ -967,8 +760,6 @@ static void smp_call_function_many_cond(const struct cpumask *mask, send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) arch_send_call_function_ipi_mask(cfd->cpumask_ipi); - - cfd_seq_store(this_cpu_ptr(&cfd_seq_local)->pinged, this_cpu, CFD_SEQ_NOCPU, CFD_SEQ_PINGED); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { -- GitLab From 6366d062e7f97499409979f23f4107a6c45edb04 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 20 Mar 2023 17:55:15 -0700 Subject: [PATCH 1218/5631] locking/csd_lock: Remove per-CPU data indirection from CSD lock debugging The diagnostics added by this commit were extremely useful in one instance: a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") However, they have not seen much action since, and there have been some concerns expressed that the complexity is not worth the benefit. Therefore, manually revert the following commit preparatory commit: de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") Signed-off-by: Paul E. McKenney Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230321005516.50558-3-paulmck@kernel.org --- kernel/smp.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/kernel/smp.c b/kernel/smp.c index 038d666f327b..7a85bcddd9dc 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -31,12 +31,8 @@ #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) -struct cfd_percpu { - call_single_data_t csd; -}; - struct call_function_data { - struct cfd_percpu __percpu *pcpu; + call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; @@ -59,8 +55,8 @@ int smpcfd_prepare_cpu(unsigned int cpu) free_cpumask_var(cfd->cpumask); return -ENOMEM; } - cfd->pcpu = alloc_percpu(struct cfd_percpu); - if (!cfd->pcpu) { + cfd->csd = alloc_percpu(call_single_data_t); + if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; @@ -75,7 +71,7 @@ int smpcfd_dead_cpu(unsigned int cpu) free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); - free_percpu(cfd->pcpu); + free_percpu(cfd->csd); return 0; } @@ -730,7 +726,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { - call_single_data_t *csd = &per_cpu_ptr(cfd->pcpu, cpu)->csd; + call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) continue; @@ -774,7 +770,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; - csd = &per_cpu_ptr(cfd->pcpu, cpu)->csd; + csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } -- GitLab From 203e435844734cfa503cd1755f35db2514db5cca Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 20 Mar 2023 17:55:16 -0700 Subject: [PATCH 1219/5631] kernel/smp: Make csdlock_debug= resettable It is currently possible to set the csdlock_debug_enabled static branch, but not to reset it. This is an issue when several different entities supply kernel boot parameters and also for kernels built with CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT=y. Therefore, make the csdlock_debug=0 kernel boot parameter turn off debugging. Last one wins! Reported-by: Jes Sorensen Signed-off-by: Paul E. McKenney Signed-off-by: Peter Zijlstra (Intel) Acked-by: Juergen Gross Link: https://lore.kernel.org/r/20230321005516.50558-4-paulmck@kernel.org --- Documentation/admin-guide/kernel-parameters.txt | 13 +++++++------ kernel/smp.c | 11 ++++++++--- 2 files changed, 15 insertions(+), 9 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b15198a85acb..5f2ec4b0f927 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -889,12 +889,13 @@ cs89x0_media= [HW,NET] Format: { rj45 | aui | bnc } - csdlock_debug= [KNL] Enable debug add-ons of cross-CPU function call - handling. When switched on, additional debug data is - printed to the console in case a hanging CPU is - detected, and that CPU is pinged again in order to try - to resolve the hang situation. The default value of - this option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT + csdlock_debug= [KNL] Enable or disable debug add-ons of cross-CPU + function call handling. When switched on, + additional debug data is printed to the console + in case a hanging CPU is detected, and that + CPU is pinged again in order to try to resolve + the hang situation. The default value of this + option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT Kconfig option. dasd= [HW,NET] diff --git a/kernel/smp.c b/kernel/smp.c index 7a85bcddd9dc..298ba7570621 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -116,11 +116,16 @@ static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug */ static int __init csdlock_debug(char *str) { + int ret; unsigned int val = 0; - get_option(&str, &val); - if (val) - static_branch_enable(&csdlock_debug_enabled); + ret = get_option(&str, &val); + if (ret) { + if (val) + static_branch_enable(&csdlock_debug_enabled); + else + static_branch_disable(&csdlock_debug_enabled); + } return 1; } -- GitLab From 56eb0598c7a30c76009a082d3213486d6a013df0 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:52 +0000 Subject: [PATCH 1220/5631] trace: Add trace_ipi_send_cpumask() trace_ipi_raise() is unsuitable for generically tracing IPI sources due to its "reason" argument being an uninformative string (on arm64 all you get is "Function call interrupts" for SMP calls). Add a variant of it that exports a target cpumask, a callsite and a callback. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20230307143558.294354-2-vschneid@redhat.com --- include/trace/events/ipi.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h index 0be71dad6ec0..b1125dc27682 100644 --- a/include/trace/events/ipi.h +++ b/include/trace/events/ipi.h @@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise, TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); +TRACE_EVENT(ipi_send_cpumask, + + TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), + + TP_ARGS(cpumask, callsite, callback), + + TP_STRUCT__entry( + __cpumask(cpumask) + __field(void *, callsite) + __field(void *, callback) + ), + + TP_fast_assign( + __assign_cpumask(cpumask, cpumask_bits(cpumask)); + __entry->callsite = (void *)callsite; + __entry->callback = callback; + ), + + TP_printk("cpumask=%s callsite=%pS callback=%pS", + __get_cpumask(cpumask), __entry->callsite, __entry->callback) +); + DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), -- GitLab From cc9cb0a71725aa8dd8d8f534a9b562bbf7981f75 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:53 +0000 Subject: [PATCH 1221/5631] sched, smp: Trace IPIs sent via send_call_function_single_ipi() send_call_function_single_ipi() is the thing that sends IPIs at the bottom of smp_call_function*() via either generic_exec_single() or smp_call_function_many_cond(). Give it an IPI-related tracepoint. Note that this ends up tracing any IPI sent via __smp_call_single_queue(), which covers __ttwu_queue_wakelist() and irq_work_queue_on() "for free". Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Acked-by: Ingo Molnar Link: https://lore.kernel.org/r/20230307143558.294354-3-vschneid@redhat.com --- arch/arm/kernel/smp.c | 1 - arch/arm64/kernel/smp.c | 1 - kernel/sched/core.c | 9 +++++++-- kernel/smp.c | 2 ++ 4 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 0b8c25763adc..5edf09237b2f 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -48,7 +48,6 @@ #include #include -#define CREATE_TRACE_POINTS #include /* diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 4e8327264255..438c16fc4463 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -51,7 +51,6 @@ #include #include -#define CREATE_TRACE_POINTS #include DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 488655f2319f..c26a2cd99ec7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -80,6 +80,7 @@ #define CREATE_TRACE_POINTS #include #include +#include #undef CREATE_TRACE_POINTS #include "sched.h" @@ -95,6 +96,8 @@ #include "../../io_uring/io-wq.h" #include "../smpboot.h" +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); + /* * Export tracepoints that act as a bare tracehook (ie: have no trace event * associated with them) to allow external modules to probe them. @@ -3830,10 +3833,12 @@ void send_call_function_single_ipi(int cpu) { struct rq *rq = cpu_rq(cpu); - if (!set_nr_if_polling(rq->idle)) + if (!set_nr_if_polling(rq->idle)) { + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); arch_send_call_function_single_ipi(cpu); - else + } else { trace_sched_wake_idle_without_ipi(cpu); + } } /* diff --git a/kernel/smp.c b/kernel/smp.c index 298ba7570621..770e879a7274 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -26,6 +26,8 @@ #include #include +#include + #include "smpboot.h" #include "sched/smp.h" -- GitLab From 08407b5f61c1bbd4ebb26a76474df4354fd76fb7 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:54 +0000 Subject: [PATCH 1222/5631] smp: Trace IPIs sent via arch_send_call_function_ipi_mask() This simply wraps around the arch function and prepends it with a tracepoint, similar to send_call_function_single_ipi(). Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20230307143558.294354-4-vschneid@redhat.com --- kernel/smp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/kernel/smp.c b/kernel/smp.c index 770e879a7274..03e6d576295d 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -103,6 +103,13 @@ void __init call_function_init(void) smpcfd_prepare_cpu(smp_processor_id()); } +static __always_inline void +send_call_function_ipi_mask(struct cpumask *mask) +{ + trace_ipi_send_cpumask(mask, _RET_IP_, NULL); + arch_send_call_function_ipi_mask(mask); +} + #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); @@ -762,7 +769,7 @@ static void smp_call_function_many_cond(const struct cpumask *mask, if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) - arch_send_call_function_ipi_mask(cfd->cpumask_ipi); + send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { -- GitLab From 4468161a5ca2ea239c92de7c0a0dca61854ec4da Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:55 +0000 Subject: [PATCH 1223/5631] irq_work: Trace self-IPIs sent via arch_irq_work_raise() IPIs sent to remote CPUs via irq_work_queue_on() are now covered by trace_ipi_send_cpumask(), add another instance of the tracepoint to cover self-IPIs. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Link: https://lore.kernel.org/r/20230307143558.294354-5-vschneid@redhat.com --- kernel/irq_work.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 7afa40fe5cc4..c33e88e32a67 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -22,6 +22,8 @@ #include #include +#include + static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); @@ -74,6 +76,16 @@ void __weak arch_irq_work_raise(void) */ } +static __always_inline void irq_work_raise(struct irq_work *work) +{ + if (trace_ipi_send_cpumask_enabled() && arch_irq_work_has_interrupt()) + trace_ipi_send_cpumask(cpumask_of(smp_processor_id()), + _RET_IP_, + work->func); + + arch_irq_work_raise(); +} + /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { @@ -99,7 +111,7 @@ static void __irq_work_queue_local(struct irq_work *work) /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) - arch_irq_work_raise(); + irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ -- GitLab From 4c8c3c7f70a6779d30f5492acbc9978f4636fe7a Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:56 +0000 Subject: [PATCH 1224/5631] treewide: Trace IPIs sent via smp_send_reschedule() To be able to trace invocations of smp_send_reschedule(), rename the arch-specific definitions of it to arch_smp_send_reschedule() and wrap it into an smp_send_reschedule() that contains a tracepoint. Changes to include the declaration of the tracepoint were driven by the following coccinelle script: @func_use@ @@ smp_send_reschedule(...); @include@ @@ #include @no_include depends on func_use && !include@ @@ #include <...> + + #include [csky bits] [riscv bits] Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Acked-by: Guo Ren Acked-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230307143558.294354-6-vschneid@redhat.com --- arch/alpha/kernel/smp.c | 2 +- arch/arc/kernel/smp.c | 2 +- arch/arm/kernel/smp.c | 2 +- arch/arm/mach-actions/platsmp.c | 2 ++ arch/arm64/kernel/smp.c | 2 +- arch/csky/kernel/smp.c | 2 +- arch/hexagon/kernel/smp.c | 2 +- arch/ia64/kernel/smp.c | 4 ++-- arch/loongarch/kernel/smp.c | 4 ++-- arch/mips/include/asm/smp.h | 2 +- arch/mips/kernel/rtlx-cmp.c | 2 ++ arch/openrisc/kernel/smp.c | 2 +- arch/parisc/kernel/smp.c | 4 ++-- arch/powerpc/kernel/smp.c | 6 ++++-- arch/powerpc/kvm/book3s_hv.c | 3 +++ arch/powerpc/platforms/powernv/subcore.c | 2 ++ arch/riscv/kernel/smp.c | 4 ++-- arch/s390/kernel/smp.c | 2 +- arch/sh/kernel/smp.c | 2 +- arch/sparc/kernel/smp_32.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/x86/include/asm/smp.h | 2 +- arch/x86/kvm/svm/svm.c | 4 ++++ arch/x86/kvm/x86.c | 2 ++ arch/xtensa/kernel/smp.c | 2 +- include/linux/smp.h | 11 +++++++++-- virt/kvm/kvm_main.c | 3 +++ 27 files changed, 53 insertions(+), 26 deletions(-) diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 0ede4b044e86..7439b2377df5 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -562,7 +562,7 @@ handle_ipi(struct pt_regs *regs) } void -smp_send_reschedule(int cpu) +arch_smp_send_reschedule(int cpu) { #ifdef DEBUG_IPI_MSG if (cpu == hard_smp_processor_id()) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index ad93fe6e4b77..409cfa4675b4 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -292,7 +292,7 @@ static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg) ipi_send_msg_one(cpu, msg); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { ipi_send_msg_one(cpu, IPI_RESCHEDULE); } diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 5edf09237b2f..b350bfc9d1f8 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -746,7 +746,7 @@ void __init set_smp_ipi_range(int ipi_base, int n) ipi_setup(smp_processor_id()); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/arm/mach-actions/platsmp.c b/arch/arm/mach-actions/platsmp.c index f26618b43514..7b208e96fbb6 100644 --- a/arch/arm/mach-actions/platsmp.c +++ b/arch/arm/mach-actions/platsmp.c @@ -20,6 +20,8 @@ #include #include +#include + #define OWL_CPU1_ADDR 0x50 #define OWL_CPU1_FLAG 0x5c diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 438c16fc4463..66f2745062dd 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -976,7 +976,7 @@ void __init set_smp_ipi_range(int ipi_base, int n) ipi_setup(smp_processor_id()); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index b45d1073307f..be77383acb5f 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -140,7 +140,7 @@ void smp_send_stop(void) on_each_cpu(ipi_stop, NULL, 1); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index 4ba93e59370c..4e8bee25b8c6 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -217,7 +217,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { send_ipi(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index e2cc59db86bc..ea4f009a232b 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -220,11 +220,11 @@ kdump_smp_send_init(void) * Called with preemption disabled. */ void -smp_send_reschedule (int cpu) +arch_smp_send_reschedule (int cpu) { ia64_send_ipi(cpu, IA64_IPI_RESCHEDULE, IA64_IPI_DM_INT, 0); } -EXPORT_SYMBOL_GPL(smp_send_reschedule); +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); /* * Called with preemption disabled. diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 8c6e227cb29d..83225610a148 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -155,11 +155,11 @@ void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) * it goes straight through and wastes no time serializing * anything. Worst case is that we lose a reschedule ... */ -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { loongson_send_ipi_single(cpu, SMP_RESCHEDULE); } -EXPORT_SYMBOL_GPL(smp_send_reschedule); +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); irqreturn_t loongson_ipi_interrupt(int irq, void *dev) { diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 5d9ff61004ca..9806e79895d9 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -66,7 +66,7 @@ extern void calculate_cpu_foreign_map(void); * it goes straight through and wastes no time serializing * anything. Worst case is that we lose a reschedule ... */ -static inline void smp_send_reschedule(int cpu) +static inline void arch_smp_send_reschedule(int cpu) { extern const struct plat_smp_ops *mp_ops; /* private */ diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c index d26dcc4b46e7..e991cc936c1c 100644 --- a/arch/mips/kernel/rtlx-cmp.c +++ b/arch/mips/kernel/rtlx-cmp.c @@ -17,6 +17,8 @@ #include #include +#include + static int major; static void rtlx_interrupt(void) diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c index e1419095a6f0..0a7a059e2dff 100644 --- a/arch/openrisc/kernel/smp.c +++ b/arch/openrisc/kernel/smp.c @@ -173,7 +173,7 @@ void handle_IPI(unsigned int ipi_msg) } } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 7dbd92cafae3..b7fc859fa87d 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -246,8 +246,8 @@ void kgdb_roundup_cpus(void) inline void smp_send_stop(void) { send_IPI_allbutself(IPI_CPU_STOP); } -void -smp_send_reschedule(int cpu) { send_IPI_single(cpu, IPI_RESCHEDULE); } +void +arch_smp_send_reschedule(int cpu) { send_IPI_single(cpu, IPI_RESCHEDULE); } void smp_send_all_nop(void) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6b90f10a6c81..35f101ccb540 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -61,6 +61,8 @@ #include #include +#include + #ifdef DEBUG #include #define DBG(fmt...) udbg_printf(fmt) @@ -364,12 +366,12 @@ static inline void do_message_pass(int cpu, int msg) #endif } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { if (likely(smp_ops)) do_message_pass(cpu, PPC_MSG_RESCHEDULE); } -EXPORT_SYMBOL_GPL(smp_send_reschedule); +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); void arch_send_call_function_single_ipi(int cpu) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6ba68dd6190b..3b70b5f80bd5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -80,6 +81,8 @@ #include #include +#include + #include "book3s.h" #include "book3s_hv.h" diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c index 7e98b00ea2e8..c53c4c797768 100644 --- a/arch/powerpc/platforms/powernv/subcore.c +++ b/arch/powerpc/platforms/powernv/subcore.c @@ -20,6 +20,8 @@ #include #include +#include + #include "subcore.h" #include "powernv.h" diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 8c3b59f1f9b8..42e9656a1db2 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -328,8 +328,8 @@ bool smp_crash_stop_failed(void) } #endif -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { send_ipi_single(cpu, IPI_RESCHEDULE); } -EXPORT_SYMBOL_GPL(smp_send_reschedule); +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index d4888453bbf8..a710319f97e9 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -553,7 +553,7 @@ void arch_send_call_function_single_ipi(int cpu) * it goes straight through and wastes no time serializing * anything. Worst case is that we lose a reschedule ... */ -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { pcpu_ec_call(pcpu_devices + cpu, ec_schedule); } diff --git a/arch/sh/kernel/smp.c b/arch/sh/kernel/smp.c index 65924d9ec245..5cf35a774dc7 100644 --- a/arch/sh/kernel/smp.c +++ b/arch/sh/kernel/smp.c @@ -256,7 +256,7 @@ void __init smp_cpus_done(unsigned int max_cpus) (bogosum / (5000/HZ)) % 100); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { mp_ops->send_ipi(cpu, SMP_MSG_RESCHEDULE); } diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index ad8094d955eb..87eaa7719fa2 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -120,7 +120,7 @@ void cpu_panic(void) struct linux_prom_registers smp_penguin_ctable = { 0 }; -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { /* * CPU model dependent way of implementing IPI generation targeting diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index a55295d1b924..e5964d1d8b37 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1430,7 +1430,7 @@ static unsigned long send_cpu_poke(int cpu) return hv_err; } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { if (cpu == smp_processor_id()) { WARN_ON_ONCE(preemptible()); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index b4dbb20dab1a..f9757123d8fa 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -98,7 +98,7 @@ static inline void play_dead(void) smp_ops.play_dead(); } -static inline void smp_send_reschedule(int cpu) +static inline void arch_smp_send_reschedule(int cpu) { smp_ops.smp_send_reschedule(cpu); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 252e7f37e4e2..424fcdba4c78 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -41,6 +42,9 @@ #include #include + +#include + #include "trace.h" #include "svm.h" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7713420abab0..07ba937bdb6f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -60,7 +60,9 @@ #include #include #include +#include +#include #include #include diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 4dc109dd6214..d95907b8e4d3 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -389,7 +389,7 @@ void arch_send_call_function_single_ipi(int cpu) send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..c036a2228d8d 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -125,8 +125,15 @@ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ -extern void smp_send_reschedule(int cpu); - +extern void arch_smp_send_reschedule(int cpu); +/* + * scheduler_ipi() is inline so can't be passed as callback reason, but the + * callsite IP should be sufficient for root-causing IPIs sent from here. + */ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ +}) /* * Prepare machine for booting other CPUs. diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d255964ec331..7d1889629bfe 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -62,11 +62,14 @@ #include "kvm_mm.h" #include "vfio.h" +#include + #define CREATE_TRACE_POINTS #include #include + /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 -- GitLab From 253a0fb4c62827cdcaf43afcea5d675507eaf7a3 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:57 +0000 Subject: [PATCH 1225/5631] smp: reword smp call IPI comment Accessing the call_single_queue hasn't involved a spinlock since 2014: 6897fc22ea01 ("kernel: use lockless list for smp_call_function_single") The llist operations (namely cmpxchg() and xchg()) provide similar ordering guarantees, update the comment to lessen confusion. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230307143558.294354-7-vschneid@redhat.com --- kernel/smp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/kernel/smp.c b/kernel/smp.c index 03e6d576295d..6bbfabbe62fc 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -312,9 +312,10 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* - * The list addition should be visible before sending the IPI - * handler locks the list to pull the entry off it because of - * normal cache coherency rules implied by spinlocks. + * The list addition should be visible to the target CPU when it pops + * the head of the list to pull the entry off it in the IPI handler + * because of normal cache coherency rules implied by the underlying + * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added -- GitLab From 68f4ff04dbada18dad79659c266a8e5e29e458cd Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Tue, 7 Mar 2023 14:35:58 +0000 Subject: [PATCH 1226/5631] sched, smp: Trace smp callback causing an IPI Context ======= The newly-introduced ipi_send_cpumask tracepoint has a "callback" parameter which so far has only been fed with NULL. While CSD_TYPE_SYNC/ASYNC and CSD_TYPE_IRQ_WORK share a similar backing struct layout (meaning their callback func can be accessed without caring about the actual CSD type), CSD_TYPE_TTWU doesn't even have a function attached to its struct. This means we need to check the type of a CSD before eventually dereferencing its associated callback. This isn't as trivial as it sounds: the CSD type is stored in __call_single_node.u_flags, which get cleared right before the callback is executed via csd_unlock(). This implies checking the CSD type before it is enqueued on the call_single_queue, as the target CPU's queue can be flushed before we get to sending an IPI. Furthermore, send_call_function_single_ipi() only has a CPU parameter, and would need to have an additional argument to trickle down the invoked function. This is somewhat silly, as the extra argument will always be pushed down to the function even when nothing is being traced, which is unnecessary overhead. Changes ======= send_call_function_single_ipi() is only used by smp.c, and is defined in sched/core.c as it contains scheduler-specific ops (set_nr_if_polling() of a CPU's idle task). Split it into two parts: the scheduler bits remain in sched/core.c, and the actual IPI emission is moved into smp.c. This lets us define an __always_inline helper function that can take the related callback as parameter without creating useless register pressure in the non-traced path which only gains a (disabled) static branch. Do the same thing for the multi IPI case. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20230307143558.294354-8-vschneid@redhat.com --- kernel/sched/core.c | 18 ++++++++++------- kernel/sched/smp.h | 2 +- kernel/smp.c | 49 +++++++++++++++++++++++++++++++++++++-------- 3 files changed, 53 insertions(+), 16 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c26a2cd99ec7..b0a48cfc0a22 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3829,16 +3829,20 @@ void sched_ttwu_pending(void *arg) rq_unlock_irqrestore(rq, &rf); } -void send_call_function_single_ipi(int cpu) +/* + * Prepare the scene for sending an IPI for a remote smp_call + * + * Returns true if the caller can proceed with sending the IPI. + * Returns false otherwise. + */ +bool call_function_single_prep_ipi(int cpu) { - struct rq *rq = cpu_rq(cpu); - - if (!set_nr_if_polling(rq->idle)) { - trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); - arch_send_call_function_single_ipi(cpu); - } else { + if (set_nr_if_polling(cpu_rq(cpu)->idle)) { trace_sched_wake_idle_without_ipi(cpu); + return false; } + + return true; } /* diff --git a/kernel/sched/smp.h b/kernel/sched/smp.h index 2eb23dd0f285..21ac44428bb0 100644 --- a/kernel/sched/smp.h +++ b/kernel/sched/smp.h @@ -6,7 +6,7 @@ extern void sched_ttwu_pending(void *arg); -extern void send_call_function_single_ipi(int cpu); +extern bool call_function_single_prep_ipi(int cpu); #ifdef CONFIG_SMP extern void flush_smp_call_function_queue(void); diff --git a/kernel/smp.c b/kernel/smp.c index 6bbfabbe62fc..37e9613a0889 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -104,9 +104,18 @@ void __init call_function_init(void) } static __always_inline void -send_call_function_ipi_mask(struct cpumask *mask) +send_call_function_single_ipi(int cpu, smp_call_func_t func) { - trace_ipi_send_cpumask(mask, _RET_IP_, NULL); + if (call_function_single_prep_ipi(cpu)) { + trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, func); + arch_send_call_function_single_ipi(cpu); + } +} + +static __always_inline void +send_call_function_ipi_mask(struct cpumask *mask, smp_call_func_t func) +{ + trace_ipi_send_cpumask(mask, _RET_IP_, func); arch_send_call_function_ipi_mask(mask); } @@ -307,9 +316,8 @@ static __always_inline void csd_unlock(struct __call_single_data *csd) smp_store_release(&csd->node.u_flags, 0); } -static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); - -void __smp_call_single_queue(int cpu, struct llist_node *node) +static __always_inline void +raw_smp_call_single_queue(int cpu, struct llist_node *node, smp_call_func_t func) { /* * The list addition should be visible to the target CPU when it pops @@ -324,7 +332,32 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) - send_call_function_single_ipi(cpu); + send_call_function_single_ipi(cpu, func); +} + +static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); + +void __smp_call_single_queue(int cpu, struct llist_node *node) +{ + /* + * We have to check the type of the CSD before queueing it, because + * once queued it can have its flags cleared by + * flush_smp_call_function_queue() + * even if we haven't sent the smp_call IPI yet (e.g. the stopper + * executes migration_cpu_stop() on the remote CPU). + */ + if (trace_ipi_send_cpumask_enabled()) { + call_single_data_t *csd; + smp_call_func_t func; + + csd = container_of(node, call_single_data_t, node.llist); + func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? + sched_ttwu_pending : csd->func; + + raw_smp_call_single_queue(cpu, node, func); + } else { + raw_smp_call_single_queue(cpu, node, NULL); + } } /* @@ -768,9 +801,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask, * provided mask. */ if (nr_cpus == 1) - send_call_function_single_ipi(last_cpu); + send_call_function_single_ipi(last_cpu, func); else if (likely(nr_cpus > 1)) - send_call_function_ipi_mask(cfd->cpumask_ipi); + send_call_function_ipi_mask(cfd->cpumask_ipi, func); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { -- GitLab From 68e2d17c9eb311ab59aeb6d0c38aad8985fa2596 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2023 11:28:36 +0100 Subject: [PATCH 1227/5631] trace: Add trace_ipi_send_cpu() Because copying cpumasks around when targeting a single CPU is a bit daft... Tested-and-reviewed-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230322103004.GA571242%40hirez.programming.kicks-ass.net --- include/linux/smp.h | 6 +++--- include/trace/events/ipi.h | 22 ++++++++++++++++++++++ kernel/irq_work.c | 6 ++---- kernel/sched/core.c | 1 + kernel/smp.c | 4 ++-- 5 files changed, 30 insertions(+), 9 deletions(-) diff --git a/include/linux/smp.h b/include/linux/smp.h index c036a2228d8d..ed8f344ba627 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -130,9 +130,9 @@ extern void arch_smp_send_reschedule(int cpu); * scheduler_ipi() is inline so can't be passed as callback reason, but the * callsite IP should be sufficient for root-causing IPIs sent from here. */ -#define smp_send_reschedule(cpu) ({ \ - trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, NULL); \ - arch_smp_send_reschedule(cpu); \ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ }) /* diff --git a/include/trace/events/ipi.h b/include/trace/events/ipi.h index b1125dc27682..3de9bfc982ce 100644 --- a/include/trace/events/ipi.h +++ b/include/trace/events/ipi.h @@ -35,6 +35,28 @@ TRACE_EVENT(ipi_raise, TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); +TRACE_EVENT(ipi_send_cpu, + + TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), + + TP_ARGS(cpu, callsite, callback), + + TP_STRUCT__entry( + __field(unsigned int, cpu) + __field(void *, callsite) + __field(void *, callback) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->callsite = (void *)callsite; + __entry->callback = callback; + ), + + TP_printk("cpu=%u callsite=%pS callback=%pS", + __entry->cpu, __entry->callsite, __entry->callback) +); + TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), diff --git a/kernel/irq_work.c b/kernel/irq_work.c index c33e88e32a67..2f4fb336dda1 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -78,10 +78,8 @@ void __weak arch_irq_work_raise(void) static __always_inline void irq_work_raise(struct irq_work *work) { - if (trace_ipi_send_cpumask_enabled() && arch_irq_work_has_interrupt()) - trace_ipi_send_cpumask(cpumask_of(smp_processor_id()), - _RET_IP_, - work->func); + if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) + trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b0a48cfc0a22..ad40755ddc11 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -96,6 +96,7 @@ #include "../../io_uring/io-wq.h" #include "../smpboot.h" +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu); EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); /* diff --git a/kernel/smp.c b/kernel/smp.c index 37e9613a0889..43f0796ecdb2 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -107,7 +107,7 @@ static __always_inline void send_call_function_single_ipi(int cpu, smp_call_func_t func) { if (call_function_single_prep_ipi(cpu)) { - trace_ipi_send_cpumask(cpumask_of(cpu), _RET_IP_, func); + trace_ipi_send_cpu(cpu, _RET_IP_, func); arch_send_call_function_single_ipi(cpu); } } @@ -346,7 +346,7 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ - if (trace_ipi_send_cpumask_enabled()) { + if (trace_ipi_send_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; -- GitLab From 5c3124975e15c1fadd5af1c61e4d627cf6d97ba2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 22 Mar 2023 14:58:36 +0100 Subject: [PATCH 1228/5631] trace,smp: Trace all smp_function_call*() invocations (Ab)use the trace_ipi_send_cpu*() family to trace all smp_function_call*() invocations, not only those that result in an actual IPI. The queued entries log their callback function while the actual IPIs are traced on generic_smp_call_function_single_interrupt(). Signed-off-by: Peter Zijlstra (Intel) --- kernel/smp.c | 66 ++++++++++++++++++++++++++++------------------------ 1 file changed, 36 insertions(+), 30 deletions(-) diff --git a/kernel/smp.c b/kernel/smp.c index 43f0796ecdb2..ab3e5dad6cfe 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -104,18 +104,20 @@ void __init call_function_init(void) } static __always_inline void -send_call_function_single_ipi(int cpu, smp_call_func_t func) +send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { - trace_ipi_send_cpu(cpu, _RET_IP_, func); + trace_ipi_send_cpu(cpu, _RET_IP_, + generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void -send_call_function_ipi_mask(struct cpumask *mask, smp_call_func_t func) +send_call_function_ipi_mask(struct cpumask *mask) { - trace_ipi_send_cpumask(mask, _RET_IP_, func); + trace_ipi_send_cpumask(mask, _RET_IP_, + generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } @@ -316,25 +318,6 @@ static __always_inline void csd_unlock(struct __call_single_data *csd) smp_store_release(&csd->node.u_flags, 0); } -static __always_inline void -raw_smp_call_single_queue(int cpu, struct llist_node *node, smp_call_func_t func) -{ - /* - * The list addition should be visible to the target CPU when it pops - * the head of the list to pull the entry off it in the IPI handler - * because of normal cache coherency rules implied by the underlying - * llist ops. - * - * If IPIs can go out of order to the cache coherency protocol - * in an architecture, sufficient synchronisation should be added - * to arch code to make it appear to obey cache coherency WRT - * locking and barrier primitives. Generic code isn't really - * equipped to do the right thing... - */ - if (llist_add(node, &per_cpu(call_single_queue, cpu))) - send_call_function_single_ipi(cpu, func); -} - static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) @@ -354,10 +337,23 @@ void __smp_call_single_queue(int cpu, struct llist_node *node) func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; - raw_smp_call_single_queue(cpu, node, func); - } else { - raw_smp_call_single_queue(cpu, node, NULL); + trace_ipi_send_cpu(cpu, _RET_IP_, func); } + + /* + * The list addition should be visible to the target CPU when it pops + * the head of the list to pull the entry off it in the IPI handler + * because of normal cache coherency rules implied by the underlying + * llist ops. + * + * If IPIs can go out of order to the cache coherency protocol + * in an architecture, sufficient synchronisation should be added + * to arch code to make it appear to obey cache coherency WRT + * locking and barrier primitives. Generic code isn't really + * equipped to do the right thing... + */ + if (llist_add(node, &per_cpu(call_single_queue, cpu))) + send_call_function_single_ipi(cpu); } /* @@ -732,9 +728,9 @@ static void smp_call_function_many_cond(const struct cpumask *mask, int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; + int nr_cpus = 0, nr_queued = 0; bool run_remote = false; bool run_local = false; - int nr_cpus = 0; lockdep_assert_preemption_disabled(); @@ -776,8 +772,10 @@ static void smp_call_function_many_cond(const struct cpumask *mask, for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); - if (cond_func && !cond_func(cpu, info)) + if (cond_func && !cond_func(cpu, info)) { + __cpumask_clear_cpu(cpu, cfd->cpumask); continue; + } csd_lock(csd); if (wait) @@ -793,17 +791,25 @@ static void smp_call_function_many_cond(const struct cpumask *mask, nr_cpus++; last_cpu = cpu; } + nr_queued++; } + /* + * Trace each smp_function_call_*() as an IPI, actual IPIs + * will be traced with func==generic_smp_call_function_single_ipi(). + */ + if (nr_queued) + trace_ipi_send_cpumask(cfd->cpumask, _RET_IP_, func); + /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) - send_call_function_single_ipi(last_cpu, func); + send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) - send_call_function_ipi_mask(cfd->cpumask_ipi, func); + send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { -- GitLab From 0a392354dbc3ff748e0856a75592fe8d0fdc7674 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 24 Mar 2023 09:26:47 +0000 Subject: [PATCH 1229/5631] device property: constify fwnode_get_phy_mode() argument fwnode_get_phy_mode() does not modify the fwnode argument, merely using it to obtain the phy-mode property value. Therefore, it can be made const. Signed-off-by: Russell King (Oracle) Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/E1pfdh9-00EQ8t-HB@rmk-PC.armlinux.org.uk Signed-off-by: Greg Kroah-Hartman --- drivers/base/property.c | 2 +- include/linux/property.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/property.c b/drivers/base/property.c index 3fc25e568598..35b8f3a4e24b 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -935,7 +935,7 @@ EXPORT_SYMBOL_GPL(device_get_dma_attr); * 'phy-connection-type', and return its index in phy_modes table, or errno in * error case. */ -int fwnode_get_phy_mode(struct fwnode_handle *fwnode) +int fwnode_get_phy_mode(const struct fwnode_handle *fwnode) { const char *pm; int err, i; diff --git a/include/linux/property.h b/include/linux/property.h index 0a29db15ff34..110634f5db2e 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -396,7 +396,7 @@ enum dev_dma_attr device_get_dma_attr(const struct device *dev); const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); -int fwnode_get_phy_mode(struct fwnode_handle *fwnode); +int fwnode_get_phy_mode(const struct fwnode_handle *fwnode); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); -- GitLab From 5b9ff0ba11042096bfb396e506fa9038e6a61de7 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 24 Mar 2023 13:27:20 +0200 Subject: [PATCH 1230/5631] device property: Constify a few fwnode APIs The fwnode parameter is not altered in the following APIs: - fwnode_get_next_parent_dev() - fwnode_is_ancestor_of() - fwnode_graph_get_endpoint_count() so constify them. Reported-by: Russell King (Oracle) Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230324112720.71315-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/property.c | 6 +++--- include/linux/property.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/base/property.c b/drivers/base/property.c index 35b8f3a4e24b..6a908e9c30f8 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -648,7 +648,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_parent); * * Return: a pointer to the device of the @fwnode's closest ancestor. */ -struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode) +struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; struct device *dev; @@ -718,7 +718,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_nth_parent); * * Return: true if @ancestor is an ancestor of @child. Otherwise, returns false. */ -bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child) +bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child) { struct fwnode_handle *parent; @@ -1235,7 +1235,7 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_by_id); * If FWNODE_GRAPH_DEVICE_DISABLED flag is specified, also unconnected endpoints * and endpoints connected to disabled devices are counted. */ -unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, +unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags) { struct fwnode_handle *ep; diff --git a/include/linux/property.h b/include/linux/property.h index 110634f5db2e..4a536548606b 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -105,11 +105,11 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); for (parent = fwnode_get_parent(fwnode); parent; \ parent = fwnode_get_next_parent(parent)) -struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); +struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); +bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( @@ -433,7 +433,7 @@ static inline bool fwnode_graph_is_endpoint(const struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); -unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, +unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ -- GitLab From d703e5a6ffa73fba8e9023190c53d4458cc09a06 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 24 Mar 2023 11:08:48 +0100 Subject: [PATCH 1231/5631] mips: Remove obsolete configs IRQ_MSP_CIC and IRQ_MSP_SLP Commit 1b00767fd8e1 ("MIPS: Remove PMC MSP71xx platform") removes all uses of the config IRQ_MSP_CIC and IRQ_MSP_SLP. Remove these two obsolete configs IRQ_MSP_CIC and IRQ_MSP_SLP. Signed-off-by: Lukas Bulwahn Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index fd7ed68cdb91..b91086b0ae22 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1164,12 +1164,6 @@ config SYS_SUPPORTS_LITTLE_ENDIAN config MIPS_HUGE_TLB_SUPPORT def_bool HUGETLB_PAGE || TRANSPARENT_HUGEPAGE -config IRQ_MSP_SLP - bool - -config IRQ_MSP_CIC - bool - config IRQ_TXX9 bool -- GitLab From ed6a0b6e9fd78e167d0488331d1695c6c84192be Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 19 Mar 2023 11:31:48 -0500 Subject: [PATCH 1232/5631] MIPS: octeon: Use of_address_to_resource() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace of_get_address() and of_translate_address() calls with single call to of_address_to_resource(). Signed-off-by: Rob Herring Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/octeon-irq.c | 35 ++++++++++++---------------- 1 file changed, 15 insertions(+), 20 deletions(-) diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index fd8043f6ff8a..064e2409377a 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2290,7 +2290,7 @@ static irqreturn_t octeon_irq_cib_handler(int my_irq, void *data) static int __init octeon_irq_init_cib(struct device_node *ciu_node, struct device_node *parent) { - const __be32 *addr; + struct resource res; u32 val; struct octeon_irq_cib_host_data *host_data; int parent_irq; @@ -2309,21 +2309,19 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node, return -ENOMEM; raw_spin_lock_init(&host_data->lock); - addr = of_get_address(ciu_node, 0, NULL, NULL); - if (!addr) { + r = of_address_to_resource(ciu_node, 0, &res); + if (r) { pr_err("ERROR: Couldn't acquire reg(0) %pOFn\n", ciu_node); - return -EINVAL; + return r; } - host_data->raw_reg = (u64)phys_to_virt( - of_translate_address(ciu_node, addr)); + host_data->raw_reg = (u64)phys_to_virt(res.start); - addr = of_get_address(ciu_node, 1, NULL, NULL); - if (!addr) { + r = of_address_to_resource(ciu_node, 1, &res); + if (r) { pr_err("ERROR: Couldn't acquire reg(1) %pOFn\n", ciu_node); - return -EINVAL; + return r; } - host_data->en_reg = (u64)phys_to_virt( - of_translate_address(ciu_node, addr)); + host_data->en_reg = (u64)phys_to_virt(res.start); r = of_property_read_u32(ciu_node, "cavium,max-bits", &val); if (r) { @@ -2874,11 +2872,11 @@ static struct irq_chip octeon_irq_chip_ciu3_mbox = { static int __init octeon_irq_init_ciu3(struct device_node *ciu_node, struct device_node *parent) { - int i; + int i, ret; int node; struct irq_domain *domain; struct octeon_ciu3_info *ciu3_info; - const __be32 *zero_addr; + struct resource res; u64 base_addr; union cvmx_ciu3_const consts; @@ -2888,14 +2886,11 @@ static int __init octeon_irq_init_ciu3(struct device_node *ciu_node, if (!ciu3_info) return -ENOMEM; - zero_addr = of_get_address(ciu_node, 0, NULL, NULL); - if (WARN_ON(!zero_addr)) - return -EINVAL; - - base_addr = of_translate_address(ciu_node, zero_addr); - base_addr = (u64)phys_to_virt(base_addr); + ret = of_address_to_resource(ciu_node, 0, &res); + if (WARN_ON(ret)) + return ret; - ciu3_info->ciu3_addr = base_addr; + ciu3_info->ciu3_addr = base_addr = phys_to_virt(res.start); ciu3_info->node = node; consts.u64 = cvmx_read_csr(base_addr + CIU3_CONST); -- GitLab From 6be87d61c427e63c33d9cea8dc2e20cd06700882 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Wed, 22 Feb 2023 13:24:23 +0000 Subject: [PATCH 1233/5631] MIPS: Always select ARCH_HAS_SETUP_DMA_OPS arch_setup_dma_ops on MIPS sets coherency information in struct device. It's essential for per-device coherency to work. Select it for all non-coherent platforms. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index b91086b0ae22..fa72d906916f 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -134,7 +134,6 @@ choice config MIPS_GENERIC_KERNEL bool "Generic board-agnostic MIPS kernel" - select ARCH_HAS_SETUP_DMA_OPS select MIPS_GENERIC select BOOT_RAW select BUILTIN_DTB @@ -1069,6 +1068,7 @@ config DMA_NONCOHERENT # by pgprot_writcombine can be mixed, and the latter sometimes provides # significant advantages. # + select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_DMA_WRITE_COMBINE select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_DEVICE -- GitLab From e0b7fd1207a8ec47091439fb62dd87ca6f5b4ad3 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Wed, 22 Feb 2023 13:24:24 +0000 Subject: [PATCH 1234/5631] MIPS: Always select ARCH_HAS_SYNC_DMA_FOR_CPU for noncoherent platforms As now we are telling the necessity of post DMA flush per CPU type, there is no need to select ARCH_HAS_SYNC_DMA_FOR_CPU on per platform bias, just select it unconditionally and we can sort it at runtime. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index fa72d906916f..2082efdb411b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -115,7 +115,6 @@ config MACH_INGENIC select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_ZBOOT select DMA_NONCOHERENT - select ARCH_HAS_SYNC_DMA_FOR_CPU select IRQ_MIPS_CPU select PINCTRL select GPIOLIB @@ -1071,6 +1070,7 @@ config DMA_NONCOHERENT select ARCH_HAS_SETUP_DMA_OPS select ARCH_HAS_DMA_WRITE_COMBINE select ARCH_HAS_DMA_PREP_COHERENT + select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_DMA_SET_UNCACHED select DMA_NONCOHERENT_MMAP @@ -1828,11 +1828,9 @@ config SYS_HAS_CPU_MIPS32_R3_5 config SYS_HAS_CPU_MIPS32_R5 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS32_R6 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS64_R1 bool @@ -1842,15 +1840,12 @@ config SYS_HAS_CPU_MIPS64_R2 config SYS_HAS_CPU_MIPS64_R5 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_MIPS64_R6 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_P5600 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_R3000 bool @@ -1875,7 +1870,6 @@ config SYS_HAS_CPU_NEVADA config SYS_HAS_CPU_R10000 bool - select ARCH_HAS_SYNC_DMA_FOR_CPU if DMA_NONCOHERENT config SYS_HAS_CPU_RM7000 bool @@ -1904,7 +1898,6 @@ config SYS_HAS_CPU_BMIPS4380 config SYS_HAS_CPU_BMIPS5000 bool select SYS_HAS_CPU_BMIPS - select ARCH_HAS_SYNC_DMA_FOR_CPU # # CPU may reorder R->R, R->W, W->R, W->W -- GitLab From 600efe35d54961dd026f04c6ea5b4074b3284c87 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Wed, 22 Feb 2023 13:24:25 +0000 Subject: [PATCH 1235/5631] MIPS: c-r4k: Always install dma flush functions As nowadays DMA coherence is managed per device, it is possible to have a system that is defaulted to coherent dma but still have noncoherent device that needs to use those flush functions. Just install them unconditionally. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/mm/c-r4k.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index a549fa98c2f4..7d447050a20b 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1867,15 +1867,9 @@ void r4k_cache_init(void) __local_flush_icache_user_range = local_r4k_flush_icache_user_range; #ifdef CONFIG_DMA_NONCOHERENT - if (dma_default_coherent) { - _dma_cache_wback_inv = (void *)cache_noop; - _dma_cache_wback = (void *)cache_noop; - _dma_cache_inv = (void *)cache_noop; - } else { - _dma_cache_wback_inv = r4k_dma_cache_wback_inv; - _dma_cache_wback = r4k_dma_cache_wback_inv; - _dma_cache_inv = r4k_dma_cache_inv; - } + _dma_cache_wback_inv = r4k_dma_cache_wback_inv; + _dma_cache_wback = r4k_dma_cache_wback_inv; + _dma_cache_inv = r4k_dma_cache_inv; #endif /* CONFIG_DMA_NONCOHERENT */ build_clear_page(); -- GitLab From 9168d125ea032ad199275193493c13cb077da5cc Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 3 Mar 2023 16:16:21 -0600 Subject: [PATCH 1236/5631] RDMA/rxe: Replace exists by rxe in rxe.c 'exists' looks like a boolean. This patch replaces it by the normal name used for the rxe device, 'rxe', which should be a little less confusing. The second rxe_dbg() message is incorrect since rxe is known to be NULL and this will cause a seg fault if this message were ever sent. Replace it by pr_debug for the moment. Fixes: c6aba5ea0055 ("RDMA/rxe: Replace pr_xxx by rxe_dbg_xxx in rxe.c") Link: https://lore.kernel.org/r/20230303221623.8053-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 136c2efe3466..a3f05fdd9fac 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -175,7 +175,7 @@ int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name) static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) { - struct rxe_dev *exists; + struct rxe_dev *rxe; int err = 0; if (is_vlan_dev(ndev)) { @@ -184,17 +184,17 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) goto err; } - exists = rxe_get_dev_from_net(ndev); - if (exists) { - ib_device_put(&exists->ib_dev); - rxe_dbg(exists, "already configured on %s\n", ndev->name); + rxe = rxe_get_dev_from_net(ndev); + if (rxe) { + ib_device_put(&rxe->ib_dev); + rxe_dbg(rxe, "already configured on %s\n", ndev->name); err = -EEXIST; goto err; } err = rxe_net_add(ibdev_name, ndev); if (err) { - rxe_dbg(exists, "failed to add %s\n", ndev->name); + pr_debug("failed to add %s\n", ndev->name); goto err; } err: -- GitLab From a9fb3287211e64b94ceb2b6b4791cc2b829d0d56 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 3 Mar 2023 16:16:22 -0600 Subject: [PATCH 1237/5631] RDMA/rxe: Change rxe_dbg to rxe_dbg_dev Replace the name rxe_dbg with rxe_dbg_dev which better matches the remaining rxe_dbg_xxx macros for debug messages with a rxe device parameter. Reuse the name rxe_dbg for debug messages which do not have a rxe device parameter. Link: https://lore.kernel.org/r/20230303221623.8053-3-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe.c | 2 +- drivers/infiniband/sw/rxe/rxe.h | 3 ++- drivers/infiniband/sw/rxe/rxe_cq.c | 6 +++--- drivers/infiniband/sw/rxe/rxe_icrc.c | 4 ++-- drivers/infiniband/sw/rxe/rxe_mmap.c | 6 +++--- drivers/infiniband/sw/rxe/rxe_net.c | 4 ++-- drivers/infiniband/sw/rxe/rxe_qp.c | 16 ++++++++-------- drivers/infiniband/sw/rxe/rxe_srq.c | 6 +++--- drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +- 9 files changed, 25 insertions(+), 24 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index a3f05fdd9fac..d57ba7a5964b 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -187,7 +187,7 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) rxe = rxe_get_dev_from_net(ndev); if (rxe) { ib_device_put(&rxe->ib_dev); - rxe_dbg(rxe, "already configured on %s\n", ndev->name); + rxe_dbg_dev(rxe, "already configured on %s\n", ndev->name); err = -EEXIST; goto err; } diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index 2415f3704f57..0757acc38103 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -38,7 +38,8 @@ #define RXE_ROCE_V2_SPORT (0xc000) -#define rxe_dbg(rxe, fmt, ...) ibdev_dbg(&(rxe)->ib_dev, \ +#define rxe_dbg(fmt, ...) pr_debug("%s: " fmt "\n", __func__, ##__VA_ARGS__) +#define rxe_dbg_dev(rxe, fmt, ...) ibdev_dbg(&(rxe)->ib_dev, \ "%s: " fmt, __func__, ##__VA_ARGS__) #define rxe_dbg_uc(uc, fmt, ...) ibdev_dbg((uc)->ibuc.device, \ "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index 1df186534639..22fbc198e5d1 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -14,12 +14,12 @@ int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq, int count; if (cqe <= 0) { - rxe_dbg(rxe, "cqe(%d) <= 0\n", cqe); + rxe_dbg_dev(rxe, "cqe(%d) <= 0\n", cqe); goto err1; } if (cqe > rxe->attr.max_cqe) { - rxe_dbg(rxe, "cqe(%d) > max_cqe(%d)\n", + rxe_dbg_dev(rxe, "cqe(%d) > max_cqe(%d)\n", cqe, rxe->attr.max_cqe); goto err1; } @@ -65,7 +65,7 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, cq->queue = rxe_queue_init(rxe, &cqe, sizeof(struct rxe_cqe), type); if (!cq->queue) { - rxe_dbg(rxe, "unable to create cq\n"); + rxe_dbg_dev(rxe, "unable to create cq\n"); return -ENOMEM; } diff --git a/drivers/infiniband/sw/rxe/rxe_icrc.c b/drivers/infiniband/sw/rxe/rxe_icrc.c index 71bc2c189588..fdf5f08cd8f1 100644 --- a/drivers/infiniband/sw/rxe/rxe_icrc.c +++ b/drivers/infiniband/sw/rxe/rxe_icrc.c @@ -21,7 +21,7 @@ int rxe_icrc_init(struct rxe_dev *rxe) tfm = crypto_alloc_shash("crc32", 0, 0); if (IS_ERR(tfm)) { - rxe_dbg(rxe, "failed to init crc32 algorithm err: %ld\n", + rxe_dbg_dev(rxe, "failed to init crc32 algorithm err: %ld\n", PTR_ERR(tfm)); return PTR_ERR(tfm); } @@ -51,7 +51,7 @@ static __be32 rxe_crc32(struct rxe_dev *rxe, __be32 crc, void *next, size_t len) *(__be32 *)shash_desc_ctx(shash) = crc; err = crypto_shash_update(shash, next, len); if (unlikely(err)) { - rxe_dbg(rxe, "failed crc calculation, err: %d\n", err); + rxe_dbg_dev(rxe, "failed crc calculation, err: %d\n", err); return (__force __be32)crc32_le((__force u32)crc, next, len); } diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c index a47d72dbc537..6b7f2bd69879 100644 --- a/drivers/infiniband/sw/rxe/rxe_mmap.c +++ b/drivers/infiniband/sw/rxe/rxe_mmap.c @@ -79,7 +79,7 @@ int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) /* Don't allow a mmap larger than the object. */ if (size > ip->info.size) { - rxe_dbg(rxe, "mmap region is larger than the object!\n"); + rxe_dbg_dev(rxe, "mmap region is larger than the object!\n"); spin_unlock_bh(&rxe->pending_lock); ret = -EINVAL; goto done; @@ -87,7 +87,7 @@ int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) goto found_it; } - rxe_dbg(rxe, "unable to find pending mmap info\n"); + rxe_dbg_dev(rxe, "unable to find pending mmap info\n"); spin_unlock_bh(&rxe->pending_lock); ret = -EINVAL; goto done; @@ -98,7 +98,7 @@ int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma) ret = remap_vmalloc_range(vma, ip->obj, 0); if (ret) { - rxe_dbg(rxe, "err %d from remap_vmalloc_range\n", ret); + rxe_dbg_dev(rxe, "err %d from remap_vmalloc_range\n", ret); goto done; } diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index e02e1624bcf4..a2ace42e9536 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -596,7 +596,7 @@ static int rxe_notify(struct notifier_block *not_blk, rxe_port_down(rxe); break; case NETDEV_CHANGEMTU: - rxe_dbg(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); + rxe_dbg_dev(rxe, "%s changed mtu to %d\n", ndev->name, ndev->mtu); rxe_set_mtu(rxe, ndev->mtu); break; case NETDEV_CHANGE: @@ -608,7 +608,7 @@ static int rxe_notify(struct notifier_block *not_blk, case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: default: - rxe_dbg(rxe, "ignoring netdev event = %ld for %s\n", + rxe_dbg_dev(rxe, "ignoring netdev event = %ld for %s\n", event, ndev->name); break; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index ab72db68b58f..c954dd9394ba 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -19,33 +19,33 @@ static int rxe_qp_chk_cap(struct rxe_dev *rxe, struct ib_qp_cap *cap, int has_srq) { if (cap->max_send_wr > rxe->attr.max_qp_wr) { - rxe_dbg(rxe, "invalid send wr = %u > %d\n", + rxe_dbg_dev(rxe, "invalid send wr = %u > %d\n", cap->max_send_wr, rxe->attr.max_qp_wr); goto err1; } if (cap->max_send_sge > rxe->attr.max_send_sge) { - rxe_dbg(rxe, "invalid send sge = %u > %d\n", + rxe_dbg_dev(rxe, "invalid send sge = %u > %d\n", cap->max_send_sge, rxe->attr.max_send_sge); goto err1; } if (!has_srq) { if (cap->max_recv_wr > rxe->attr.max_qp_wr) { - rxe_dbg(rxe, "invalid recv wr = %u > %d\n", + rxe_dbg_dev(rxe, "invalid recv wr = %u > %d\n", cap->max_recv_wr, rxe->attr.max_qp_wr); goto err1; } if (cap->max_recv_sge > rxe->attr.max_recv_sge) { - rxe_dbg(rxe, "invalid recv sge = %u > %d\n", + rxe_dbg_dev(rxe, "invalid recv sge = %u > %d\n", cap->max_recv_sge, rxe->attr.max_recv_sge); goto err1; } } if (cap->max_inline_data > rxe->max_inline_data) { - rxe_dbg(rxe, "invalid max inline data = %u > %d\n", + rxe_dbg_dev(rxe, "invalid max inline data = %u > %d\n", cap->max_inline_data, rxe->max_inline_data); goto err1; } @@ -73,7 +73,7 @@ int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init) } if (!init->recv_cq || !init->send_cq) { - rxe_dbg(rxe, "missing cq\n"); + rxe_dbg_dev(rxe, "missing cq\n"); goto err1; } @@ -82,14 +82,14 @@ int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init) if (init->qp_type == IB_QPT_GSI) { if (!rdma_is_port_valid(&rxe->ib_dev, port_num)) { - rxe_dbg(rxe, "invalid port = %d\n", port_num); + rxe_dbg_dev(rxe, "invalid port = %d\n", port_num); goto err1; } port = &rxe->port; if (init->qp_type == IB_QPT_GSI && port->qp_gsi_index) { - rxe_dbg(rxe, "GSI QP exists for port %d\n", port_num); + rxe_dbg_dev(rxe, "GSI QP exists for port %d\n", port_num); goto err1; } } diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c index 82e37a41ced4..27ca82ec0826 100644 --- a/drivers/infiniband/sw/rxe/rxe_srq.c +++ b/drivers/infiniband/sw/rxe/rxe_srq.c @@ -13,13 +13,13 @@ int rxe_srq_chk_init(struct rxe_dev *rxe, struct ib_srq_init_attr *init) struct ib_srq_attr *attr = &init->attr; if (attr->max_wr > rxe->attr.max_srq_wr) { - rxe_dbg(rxe, "max_wr(%d) > max_srq_wr(%d)\n", + rxe_dbg_dev(rxe, "max_wr(%d) > max_srq_wr(%d)\n", attr->max_wr, rxe->attr.max_srq_wr); goto err1; } if (attr->max_wr <= 0) { - rxe_dbg(rxe, "max_wr(%d) <= 0\n", attr->max_wr); + rxe_dbg_dev(rxe, "max_wr(%d) <= 0\n", attr->max_wr); goto err1; } @@ -27,7 +27,7 @@ int rxe_srq_chk_init(struct rxe_dev *rxe, struct ib_srq_init_attr *init) attr->max_wr = RXE_MIN_SRQ_WR; if (attr->max_sge > rxe->attr.max_srq_sge) { - rxe_dbg(rxe, "max_sge(%d) > max_srq_sge(%d)\n", + rxe_dbg_dev(rxe, "max_sge(%d) > max_srq_sge(%d)\n", attr->max_sge, rxe->attr.max_srq_sge); goto err1; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index e14050a69276..f178d0773ff2 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1095,7 +1095,7 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) err = ib_register_device(dev, ibdev_name, NULL); if (err) - rxe_dbg(rxe, "failed with error %d\n", err); + rxe_dbg_dev(rxe, "failed with error %d\n", err); /* * Note that rxe may be invalid at this point if another thread -- GitLab From 9ac01f434a1eb56ea94611bd75cf62fa276b41f4 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 3 Mar 2023 16:16:23 -0600 Subject: [PATCH 1238/5631] RDMA/rxe: Extend dbg log messages to err and info Extend the dbg log messages (e.g. rxe_dbg_xxx) to include err and info types. rxe.c is modified to use these new log messages as examples. Link: https://lore.kernel.org/r/20230303221623.8053-4-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe.c | 8 ++++--- drivers/infiniband/sw/rxe/rxe.h | 42 +++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index d57ba7a5964b..7a7e713de52d 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -160,6 +160,8 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu) port->attr.active_mtu = mtu; port->mtu_cap = ib_mtu_enum_to_int(mtu); + + rxe_info_dev(rxe, "Set mtu to %d", port->mtu_cap); } /* called by ifc layer to create new rxe device. @@ -179,7 +181,7 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) int err = 0; if (is_vlan_dev(ndev)) { - pr_err("rxe creation allowed on top of a real device only\n"); + rxe_err("rxe creation allowed on top of a real device only"); err = -EPERM; goto err; } @@ -187,14 +189,14 @@ static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) rxe = rxe_get_dev_from_net(ndev); if (rxe) { ib_device_put(&rxe->ib_dev); - rxe_dbg_dev(rxe, "already configured on %s\n", ndev->name); + rxe_err_dev(rxe, "already configured on %s", ndev->name); err = -EEXIST; goto err; } err = rxe_net_add(ibdev_name, ndev); if (err) { - pr_debug("failed to add %s\n", ndev->name); + rxe_err("failed to add %s\n", ndev->name); goto err; } err: diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index 0757acc38103..bd8a8ea4ea8f 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -58,6 +58,48 @@ #define rxe_dbg_mw(mw, fmt, ...) ibdev_dbg((mw)->ibmw.device, \ "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err(fmt, ...) pr_err_ratelimited("%s: " fmt "\n", __func__, \ + ##__VA_ARGS__) +#define rxe_err_dev(rxe, fmt, ...) ibdev_err_ratelimited(&(rxe)->ib_dev, \ + "%s: " fmt, __func__, ##__VA_ARGS__) +#define rxe_err_uc(uc, fmt, ...) ibdev_err_ratelimited((uc)->ibuc.device, \ + "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_pd(pd, fmt, ...) ibdev_err_ratelimited((pd)->ibpd.device, \ + "pd#%d %s: " fmt, (pd)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_ah(ah, fmt, ...) ibdev_err_ratelimited((ah)->ibah.device, \ + "ah#%d %s: " fmt, (ah)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_srq(srq, fmt, ...) ibdev_err_ratelimited((srq)->ibsrq.device, \ + "srq#%d %s: " fmt, (srq)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_qp(qp, fmt, ...) ibdev_err_ratelimited((qp)->ibqp.device, \ + "qp#%d %s: " fmt, (qp)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_cq(cq, fmt, ...) ibdev_err_ratelimited((cq)->ibcq.device, \ + "cq#%d %s: " fmt, (cq)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_mr(mr, fmt, ...) ibdev_err_ratelimited((mr)->ibmr.device, \ + "mr#%d %s: " fmt, (mr)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_err_mw(mw, fmt, ...) ibdev_err_ratelimited((mw)->ibmw.device, \ + "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) + +#define rxe_info(fmt, ...) pr_info_ratelimited("%s: " fmt "\n", __func__, \ + ##__VA_ARGS__) +#define rxe_info_dev(rxe, fmt, ...) ibdev_info_ratelimited(&(rxe)->ib_dev, \ + "%s: " fmt, __func__, ##__VA_ARGS__) +#define rxe_info_uc(uc, fmt, ...) ibdev_info_ratelimited((uc)->ibuc.device, \ + "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_pd(pd, fmt, ...) ibdev_info_ratelimited((pd)->ibpd.device, \ + "pd#%d %s: " fmt, (pd)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_ah(ah, fmt, ...) ibdev_info_ratelimited((ah)->ibah.device, \ + "ah#%d %s: " fmt, (ah)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_srq(srq, fmt, ...) ibdev_info_ratelimited((srq)->ibsrq.device, \ + "srq#%d %s: " fmt, (srq)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_qp(qp, fmt, ...) ibdev_info_ratelimited((qp)->ibqp.device, \ + "qp#%d %s: " fmt, (qp)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_cq(cq, fmt, ...) ibdev_info_ratelimited((cq)->ibcq.device, \ + "cq#%d %s: " fmt, (cq)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_mr(mr, fmt, ...) ibdev_info_ratelimited((mr)->ibmr.device, \ + "mr#%d %s: " fmt, (mr)->elem.index, __func__, ##__VA_ARGS__) +#define rxe_info_mw(mw, fmt, ...) ibdev_info_ratelimited((mw)->ibmw.device, \ + "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) + /* responder states */ enum resp_states { RESPST_NONE, -- GitLab From 5bf944f24129cbc4b5828348bdce2db94ca9fbd6 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Fri, 3 Mar 2023 16:16:24 -0600 Subject: [PATCH 1239/5631] RDMA/rxe: Add error messages This patch adds error and debug messages so that every interaction with rdma-core through a verbs API call or a completion error return will generate at least one error message backed up by debug messages with more detail. With dynamic debugging one can follow up after seeing an error message by turning on the appropriate debug messages. Link: https://lore.kernel.org/r/20230303221623.8053-5-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 4 + drivers/infiniband/sw/rxe/rxe_loc.h | 1 - drivers/infiniband/sw/rxe/rxe_mr.c | 13 - drivers/infiniband/sw/rxe/rxe_resp.c | 4 + drivers/infiniband/sw/rxe/rxe_verbs.c | 828 +++++++++++++++++++------- 5 files changed, 609 insertions(+), 241 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 20737fec392b..876057e3ee3c 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -428,6 +428,10 @@ static void make_send_cqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe, uwc->wc_flags = IB_WC_WITH_IMM; uwc->byte_len = wqe->dma.length; } + } else { + if (wqe->status != IB_WC_WR_FLUSH_ERR) + rxe_err_qp(qp, "non-flush error status = %d", + wqe->status); } } diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index 1bb0cb479eb1..839de34cf4c9 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -80,7 +80,6 @@ int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length); int advance_dma_data(struct rxe_dma_info *dma, unsigned int length); int rxe_invalidate_mr(struct rxe_qp *qp, u32 key); int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe); -int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata); void rxe_mr_cleanup(struct rxe_pool_elem *elem); /* rxe_mw.c */ diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index b10aa1580a64..1e17f8086d59 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -722,19 +722,6 @@ int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe) return 0; } -int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) -{ - struct rxe_mr *mr = to_rmr(ibmr); - - /* See IBA 10.6.7.2.6 */ - if (atomic_read(&mr->num_mw) > 0) - return -EINVAL; - - rxe_cleanup(mr); - kfree_rcu(mr); - return 0; -} - void rxe_mr_cleanup(struct rxe_pool_elem *elem) { struct rxe_mr *mr = container_of(elem, typeof(*mr), elem); diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 0cc1ba91d48c..4217eec03a94 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1151,6 +1151,10 @@ static enum resp_states do_complete(struct rxe_qp *qp, wc->port_num = qp->attr.port_num; } + } else { + if (wc->status != IB_WC_WR_FLUSH_ERR) + rxe_err_qp(qp, "non-flush error status = %d", + wc->status); } /* have copy for srq and reference for !srq */ diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index f178d0773ff2..84b53c070fc5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -12,31 +12,48 @@ #include "rxe_queue.h" #include "rxe_hw_counters.h" -static int rxe_query_device(struct ib_device *dev, +static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr); + +/* dev */ +static int rxe_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, - struct ib_udata *uhw) + struct ib_udata *udata) { - struct rxe_dev *rxe = to_rdev(dev); + struct rxe_dev *rxe = to_rdev(ibdev); + int err; + + if (udata->inlen || udata->outlen) { + rxe_dbg_dev(rxe, "malformed udata"); + err = -EINVAL; + goto err_out; + } - if (uhw->inlen || uhw->outlen) - return -EINVAL; + memcpy(attr, &rxe->attr, sizeof(*attr)); - *attr = rxe->attr; return 0; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_query_port(struct ib_device *dev, +static int rxe_query_port(struct ib_device *ibdev, u32 port_num, struct ib_port_attr *attr) { - struct rxe_dev *rxe = to_rdev(dev); - int rc; + struct rxe_dev *rxe = to_rdev(ibdev); + int err, ret; - /* *attr being zeroed by the caller, avoid zeroing it here */ - *attr = rxe->port.attr; + if (port_num != 1) { + err = -EINVAL; + rxe_dbg_dev(rxe, "bad port_num = %d", port_num); + goto err_out; + } + + memcpy(attr, &rxe->port.attr, sizeof(*attr)); mutex_lock(&rxe->usdev_lock); - rc = ib_get_eth_speed(dev, port_num, &attr->active_speed, - &attr->active_width); + ret = ib_get_eth_speed(ibdev, port_num, &attr->active_speed, + &attr->active_width); if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; @@ -47,27 +64,45 @@ static int rxe_query_port(struct ib_device *dev, mutex_unlock(&rxe->usdev_lock); - return rc; + return ret; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_query_pkey(struct ib_device *device, +static int rxe_query_pkey(struct ib_device *ibdev, u32 port_num, u16 index, u16 *pkey) { - if (index > 0) - return -EINVAL; + struct rxe_dev *rxe = to_rdev(ibdev); + int err; + + if (index != 0) { + err = -EINVAL; + rxe_dbg_dev(rxe, "bad pkey index = %d", index); + goto err_out; + } *pkey = IB_DEFAULT_PKEY_FULL; return 0; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_modify_device(struct ib_device *dev, +static int rxe_modify_device(struct ib_device *ibdev, int mask, struct ib_device_modify *attr) { - struct rxe_dev *rxe = to_rdev(dev); + struct rxe_dev *rxe = to_rdev(ibdev); + int err; if (mask & ~(IB_DEVICE_MODIFY_SYS_IMAGE_GUID | - IB_DEVICE_MODIFY_NODE_DESC)) - return -EOPNOTSUPP; + IB_DEVICE_MODIFY_NODE_DESC)) { + err = -EOPNOTSUPP; + rxe_dbg_dev(rxe, "unsupported mask = 0x%x", mask); + goto err_out; + } if (mask & IB_DEVICE_MODIFY_SYS_IMAGE_GUID) rxe->attr.sys_image_guid = cpu_to_be64(attr->sys_image_guid); @@ -78,16 +113,33 @@ static int rxe_modify_device(struct ib_device *dev, } return 0; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_modify_port(struct ib_device *dev, - u32 port_num, int mask, struct ib_port_modify *attr) +static int rxe_modify_port(struct ib_device *ibdev, u32 port_num, + int mask, struct ib_port_modify *attr) { - struct rxe_dev *rxe = to_rdev(dev); + struct rxe_dev *rxe = to_rdev(ibdev); struct rxe_port *port; + int err; - port = &rxe->port; + if (port_num != 1) { + err = -EINVAL; + rxe_dbg_dev(rxe, "bad port_num = %d", port_num); + goto err_out; + } + //TODO is shutdown useful + if (mask & ~(IB_PORT_RESET_QKEY_CNTR)) { + err = -EOPNOTSUPP; + rxe_dbg_dev(rxe, "unsupported mask = 0x%x", mask); + goto err_out; + } + + port = &rxe->port; port->attr.port_cap_flags |= attr->set_port_cap_mask; port->attr.port_cap_flags &= ~attr->clr_port_cap_mask; @@ -95,73 +147,125 @@ static int rxe_modify_port(struct ib_device *dev, port->attr.qkey_viol_cntr = 0; return 0; -} -static enum rdma_link_layer rxe_get_link_layer(struct ib_device *dev, - u32 port_num) -{ - return IB_LINK_LAYER_ETHERNET; +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_alloc_ucontext(struct ib_ucontext *ibuc, struct ib_udata *udata) +static enum rdma_link_layer rxe_get_link_layer(struct ib_device *ibdev, + u32 port_num) { - struct rxe_dev *rxe = to_rdev(ibuc->device); - struct rxe_ucontext *uc = to_ruc(ibuc); + struct rxe_dev *rxe = to_rdev(ibdev); + int err; - return rxe_add_to_pool(&rxe->uc_pool, uc); -} + if (port_num != 1) { + err = -EINVAL; + rxe_dbg_dev(rxe, "bad port_num = %d", port_num); + goto err_out; + } -static void rxe_dealloc_ucontext(struct ib_ucontext *ibuc) -{ - struct rxe_ucontext *uc = to_ruc(ibuc); + return IB_LINK_LAYER_ETHERNET; - rxe_cleanup(uc); +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } -static int rxe_port_immutable(struct ib_device *dev, u32 port_num, +static int rxe_port_immutable(struct ib_device *ibdev, u32 port_num, struct ib_port_immutable *immutable) { + struct rxe_dev *rxe = to_rdev(ibdev); + struct ib_port_attr attr = {}; int err; - struct ib_port_attr attr; - immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; + if (port_num != 1) { + err = -EINVAL; + rxe_dbg_dev(rxe, "bad port_num = %d", port_num); + goto err_out; + } - err = ib_query_port(dev, port_num, &attr); + err = ib_query_port(ibdev, port_num, &attr); if (err) - return err; + goto err_out; + immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP; immutable->pkey_tbl_len = attr.pkey_tbl_len; immutable->gid_tbl_len = attr.gid_tbl_len; immutable->max_mad_size = IB_MGMT_MAD_SIZE; return 0; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } +/* uc */ +static int rxe_alloc_ucontext(struct ib_ucontext *ibuc, struct ib_udata *udata) +{ + struct rxe_dev *rxe = to_rdev(ibuc->device); + struct rxe_ucontext *uc = to_ruc(ibuc); + int err; + + err = rxe_add_to_pool(&rxe->uc_pool, uc); + if (err) + rxe_err_dev(rxe, "unable to create uc"); + + return err; +} + +static void rxe_dealloc_ucontext(struct ib_ucontext *ibuc) +{ + struct rxe_ucontext *uc = to_ruc(ibuc); + int err; + + err = rxe_cleanup(uc); + if (err) + rxe_err_uc(uc, "cleanup failed, err = %d", err); +} + +/* pd */ static int rxe_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata) { struct rxe_dev *rxe = to_rdev(ibpd->device); struct rxe_pd *pd = to_rpd(ibpd); + int err; + + err = rxe_add_to_pool(&rxe->pd_pool, pd); + if (err) { + rxe_dbg_dev(rxe, "unable to alloc pd"); + goto err_out; + } - return rxe_add_to_pool(&rxe->pd_pool, pd); + return 0; + +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } static int rxe_dealloc_pd(struct ib_pd *ibpd, struct ib_udata *udata) { struct rxe_pd *pd = to_rpd(ibpd); + int err; + + err = rxe_cleanup(pd); + if (err) + rxe_err_pd(pd, "cleanup failed, err = %d", err); - rxe_cleanup(pd); return 0; } +/* ah */ static int rxe_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, struct ib_udata *udata) - { struct rxe_dev *rxe = to_rdev(ibah->device); struct rxe_ah *ah = to_rah(ibah); struct rxe_create_ah_resp __user *uresp = NULL; - int err; + int err, cleanup_err; if (udata) { /* test if new user provider */ @@ -174,16 +278,18 @@ static int rxe_create_ah(struct ib_ah *ibah, err = rxe_add_to_pool_ah(&rxe->ah_pool, ah, init_attr->flags & RDMA_CREATE_AH_SLEEPABLE); - if (err) - return err; + if (err) { + rxe_dbg_dev(rxe, "unable to create ah"); + goto err_out; + } /* create index > 0 */ ah->ah_num = ah->elem.index; err = rxe_ah_chk_attr(ah, init_attr->ah_attr); if (err) { - rxe_cleanup(ah); - return err; + rxe_dbg_ah(ah, "bad attr"); + goto err_cleanup; } if (uresp) { @@ -191,8 +297,9 @@ static int rxe_create_ah(struct ib_ah *ibah, err = copy_to_user(&uresp->ah_num, &ah->ah_num, sizeof(uresp->ah_num)); if (err) { - rxe_cleanup(ah); - return -EFAULT; + err = -EFAULT; + rxe_dbg_ah(ah, "unable to copy to user"); + goto err_cleanup; } } else if (ah->is_user) { /* only if old user provider */ @@ -203,19 +310,34 @@ static int rxe_create_ah(struct ib_ah *ibah, rxe_finalize(ah); return 0; + +err_cleanup: + cleanup_err = rxe_cleanup(ah); + if (cleanup_err) + rxe_err_ah(ah, "cleanup failed, err = %d", cleanup_err); +err_out: + rxe_err_ah(ah, "returned err = %d", err); + return err; } static int rxe_modify_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr) { - int err; struct rxe_ah *ah = to_rah(ibah); + int err; err = rxe_ah_chk_attr(ah, attr); - if (err) - return err; + if (err) { + rxe_dbg_ah(ah, "bad attr"); + goto err_out; + } rxe_init_av(attr, &ah->av); + return 0; + +err_out: + rxe_err_ah(ah, "returned err = %d", err); + return err; } static int rxe_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr) @@ -225,92 +347,77 @@ static int rxe_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *attr) memset(attr, 0, sizeof(*attr)); attr->type = ibah->type; rxe_av_to_attr(&ah->av, attr); + return 0; } static int rxe_destroy_ah(struct ib_ah *ibah, u32 flags) { struct rxe_ah *ah = to_rah(ibah); + int err; - rxe_cleanup_ah(ah, flags & RDMA_DESTROY_AH_SLEEPABLE); - - return 0; -} - -static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) -{ - int i; - u32 length; - struct rxe_recv_wqe *recv_wqe; - int num_sge = ibwr->num_sge; - int full; - - full = queue_full(rq->queue, QUEUE_TYPE_FROM_ULP); - if (unlikely(full)) - return -ENOMEM; - - if (unlikely(num_sge > rq->max_sge)) - return -EINVAL; - - length = 0; - for (i = 0; i < num_sge; i++) - length += ibwr->sg_list[i].length; - - recv_wqe = queue_producer_addr(rq->queue, QUEUE_TYPE_FROM_ULP); - recv_wqe->wr_id = ibwr->wr_id; - - memcpy(recv_wqe->dma.sge, ibwr->sg_list, - num_sge * sizeof(struct ib_sge)); - - recv_wqe->dma.length = length; - recv_wqe->dma.resid = length; - recv_wqe->dma.num_sge = num_sge; - recv_wqe->dma.cur_sge = 0; - recv_wqe->dma.sge_offset = 0; - - queue_advance_producer(rq->queue, QUEUE_TYPE_FROM_ULP); + err = rxe_cleanup_ah(ah, flags & RDMA_DESTROY_AH_SLEEPABLE); + if (err) + rxe_err_ah(ah, "cleanup failed, err = %d", err); return 0; } +/* srq */ static int rxe_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init, struct ib_udata *udata) { - int err; struct rxe_dev *rxe = to_rdev(ibsrq->device); struct rxe_pd *pd = to_rpd(ibsrq->pd); struct rxe_srq *srq = to_rsrq(ibsrq); struct rxe_create_srq_resp __user *uresp = NULL; + int err, cleanup_err; if (udata) { - if (udata->outlen < sizeof(*uresp)) - return -EINVAL; + if (udata->outlen < sizeof(*uresp)) { + err = -EINVAL; + rxe_err_dev(rxe, "malformed udata"); + goto err_out; + } uresp = udata->outbuf; } - if (init->srq_type != IB_SRQT_BASIC) - return -EOPNOTSUPP; + if (init->srq_type != IB_SRQT_BASIC) { + err = -EOPNOTSUPP; + rxe_dbg_dev(rxe, "srq type = %d, not supported", + init->srq_type); + goto err_out; + } err = rxe_srq_chk_init(rxe, init); - if (err) - return err; + if (err) { + rxe_dbg_dev(rxe, "invalid init attributes"); + goto err_out; + } err = rxe_add_to_pool(&rxe->srq_pool, srq); - if (err) - return err; + if (err) { + rxe_dbg_dev(rxe, "unable to create srq, err = %d", err); + goto err_out; + } rxe_get(pd); srq->pd = pd; err = rxe_srq_from_init(rxe, srq, init, udata, uresp); - if (err) + if (err) { + rxe_dbg_srq(srq, "create srq failed, err = %d", err); goto err_cleanup; + } return 0; err_cleanup: - rxe_cleanup(srq); - + cleanup_err = rxe_cleanup(srq); + if (cleanup_err) + rxe_err_srq(srq, "cleanup failed, err = %d", cleanup_err); +err_out: + rxe_err_dev(rxe, "returned err = %d", err); return err; } @@ -318,46 +425,64 @@ static int rxe_modify_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr, enum ib_srq_attr_mask mask, struct ib_udata *udata) { - int err; struct rxe_srq *srq = to_rsrq(ibsrq); struct rxe_dev *rxe = to_rdev(ibsrq->device); - struct rxe_modify_srq_cmd ucmd = {}; + struct rxe_modify_srq_cmd cmd = {}; + int err; if (udata) { - if (udata->inlen < sizeof(ucmd)) - return -EINVAL; + if (udata->inlen < sizeof(cmd)) { + err = -EINVAL; + rxe_dbg_srq(srq, "malformed udata"); + goto err_out; + } - err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); - if (err) - return err; + err = ib_copy_from_udata(&cmd, udata, sizeof(cmd)); + if (err) { + err = -EFAULT; + rxe_dbg_srq(srq, "unable to read udata"); + goto err_out; + } } err = rxe_srq_chk_attr(rxe, srq, attr, mask); - if (err) - return err; + if (err) { + rxe_dbg_srq(srq, "bad init attributes"); + goto err_out; + } + + err = rxe_srq_from_attr(rxe, srq, attr, mask, &cmd, udata); + if (err) { + rxe_dbg_srq(srq, "bad attr"); + goto err_out; + } + + return 0; - return rxe_srq_from_attr(rxe, srq, attr, mask, &ucmd, udata); +err_out: + rxe_err_srq(srq, "returned err = %d", err); + return err; } static int rxe_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr) { struct rxe_srq *srq = to_rsrq(ibsrq); + int err; - if (srq->error) - return -EINVAL; + if (srq->error) { + err = -EINVAL; + rxe_dbg_srq(srq, "srq in error state"); + goto err_out; + } attr->max_wr = srq->rq.queue->buf->index_mask; attr->max_sge = srq->rq.max_sge; attr->srq_limit = srq->limit; return 0; -} - -static int rxe_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata) -{ - struct rxe_srq *srq = to_rsrq(ibsrq); - rxe_cleanup(srq); - return 0; +err_out: + rxe_err_srq(srq, "returned err = %d", err); + return err; } static int rxe_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, @@ -378,76 +503,116 @@ static int rxe_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&srq->rq.producer_lock, flags); - if (err) + if (err) { *bad_wr = wr; + rxe_err_srq(srq, "returned err = %d", err); + } return err; } +static int rxe_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata) +{ + struct rxe_srq *srq = to_rsrq(ibsrq); + int err; + + err = rxe_cleanup(srq); + if (err) + rxe_err_srq(srq, "cleanup failed, err = %d", err); + + return 0; +} + +/* qp */ static int rxe_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init, struct ib_udata *udata) { - int err; struct rxe_dev *rxe = to_rdev(ibqp->device); struct rxe_pd *pd = to_rpd(ibqp->pd); struct rxe_qp *qp = to_rqp(ibqp); struct rxe_create_qp_resp __user *uresp = NULL; + int err, cleanup_err; if (udata) { - if (udata->outlen < sizeof(*uresp)) - return -EINVAL; - uresp = udata->outbuf; - } - - if (init->create_flags) - return -EOPNOTSUPP; - - err = rxe_qp_chk_init(rxe, init); - if (err) - return err; + if (udata->inlen) { + err = -EINVAL; + rxe_dbg_dev(rxe, "malformed udata, err = %d", err); + goto err_out; + } - if (udata) { - if (udata->inlen) - return -EINVAL; + if (udata->outlen < sizeof(*uresp)) { + err = -EINVAL; + rxe_dbg_dev(rxe, "malformed udata, err = %d", err); + goto err_out; + } qp->is_user = true; + uresp = udata->outbuf; } else { qp->is_user = false; } + if (init->create_flags) { + err = -EOPNOTSUPP; + rxe_dbg_dev(rxe, "unsupported create_flags, err = %d", err); + goto err_out; + } + + err = rxe_qp_chk_init(rxe, init); + if (err) { + rxe_dbg_dev(rxe, "bad init attr, err = %d", err); + goto err_out; + } + err = rxe_add_to_pool(&rxe->qp_pool, qp); - if (err) - return err; + if (err) { + rxe_dbg_dev(rxe, "unable to create qp, err = %d", err); + goto err_out; + } err = rxe_qp_from_init(rxe, qp, pd, init, uresp, ibqp->pd, udata); - if (err) - goto qp_init; + if (err) { + rxe_dbg_qp(qp, "create qp failed, err = %d", err); + goto err_cleanup; + } rxe_finalize(qp); return 0; -qp_init: - rxe_cleanup(qp); +err_cleanup: + cleanup_err = rxe_cleanup(qp); + if (cleanup_err) + rxe_err_qp(qp, "cleanup failed, err = %d", cleanup_err); +err_out: + rxe_err_dev(rxe, "returned err = %d", err); return err; } static int rxe_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int mask, struct ib_udata *udata) { - int err; struct rxe_dev *rxe = to_rdev(ibqp->device); struct rxe_qp *qp = to_rqp(ibqp); + int err; - if (mask & ~IB_QP_ATTR_STANDARD_BITS) - return -EOPNOTSUPP; + if (mask & ~IB_QP_ATTR_STANDARD_BITS) { + err = -EOPNOTSUPP; + rxe_dbg_qp(qp, "unsupported mask = 0x%x, err = %d", + mask, err); + goto err_out; + } err = rxe_qp_chk_attr(rxe, qp, attr, mask); - if (err) - return err; + if (err) { + rxe_dbg_qp(qp, "bad mask/attr, err = %d", err); + goto err_out; + } err = rxe_qp_from_attr(qp, attr, mask, udata); - if (err) - return err; + if (err) { + rxe_dbg_qp(qp, "modify qp failed, err = %d", err); + goto err_out; + } if ((mask & IB_QP_AV) && (attr->ah_attr.ah_flags & IB_AH_GRH)) qp->src_port = rdma_get_udp_sport(attr->ah_attr.grh.flow_label, @@ -455,6 +620,10 @@ static int rxe_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, qp->attr.dest_qp_num); return 0; + +err_out: + rxe_err_qp(qp, "returned err = %d", err); + return err; } static int rxe_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, @@ -471,38 +640,59 @@ static int rxe_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, static int rxe_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) { struct rxe_qp *qp = to_rqp(ibqp); - int ret; + int err; + + err = rxe_qp_chk_destroy(qp); + if (err) { + rxe_dbg_qp(qp, "unable to destroy qp, err = %d", err); + goto err_out; + } - ret = rxe_qp_chk_destroy(qp); - if (ret) - return ret; + err = rxe_cleanup(qp); + if (err) + rxe_err_qp(qp, "cleanup failed, err = %d", err); - rxe_cleanup(qp); return 0; + +err_out: + rxe_err_qp(qp, "returned err = %d", err); + return err; } +/* send wr */ static int validate_send_wr(struct rxe_qp *qp, const struct ib_send_wr *ibwr, unsigned int mask, unsigned int length) { int num_sge = ibwr->num_sge; struct rxe_sq *sq = &qp->sq; - if (unlikely(num_sge > sq->max_sge)) - return -EINVAL; + if (unlikely(num_sge > sq->max_sge)) { + rxe_dbg_qp(qp, "num_sge > max_sge"); + goto err_out; + } if (unlikely(mask & WR_ATOMIC_MASK)) { - if (length < 8) - return -EINVAL; + if (length != 8) { + rxe_dbg_qp(qp, "atomic length != 8"); + goto err_out; + } - if (atomic_wr(ibwr)->remote_addr & 0x7) - return -EINVAL; + if (atomic_wr(ibwr)->remote_addr & 0x7) { + rxe_dbg_qp(qp, "misaligned atomic address"); + goto err_out; + } } if (unlikely((ibwr->send_flags & IB_SEND_INLINE) && - (length > sq->max_inline))) - return -EINVAL; + (length > sq->max_inline))) { + rxe_dbg_qp(qp, "inline length too big"); + goto err_out; + } return 0; + +err_out: + return -EINVAL; } static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, @@ -550,12 +740,12 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, break; case IB_WR_LOCAL_INV: wr->ex.invalidate_rkey = ibwr->ex.invalidate_rkey; - break; + break; case IB_WR_REG_MR: wr->wr.reg.mr = reg_wr(ibwr)->mr; wr->wr.reg.key = reg_wr(ibwr)->key; wr->wr.reg.access = reg_wr(ibwr)->access; - break; + break; default: break; } @@ -624,9 +814,9 @@ static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr, spin_lock_irqsave(&qp->sq.sq_lock, flags); full = queue_full(sq->queue, QUEUE_TYPE_FROM_ULP); - if (unlikely(full)) { spin_unlock_irqrestore(&qp->sq.sq_lock, flags); + rxe_dbg_qp(qp, "queue full"); return -ENOMEM; } @@ -652,6 +842,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, while (wr) { mask = wr_opcode_mask(wr->opcode, qp); if (unlikely(!mask)) { + rxe_dbg_qp(qp, "bad wr opcode for qp"); err = -EINVAL; *bad_wr = wr; break; @@ -659,6 +850,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, if (unlikely((wr->send_flags & IB_SEND_INLINE) && !(mask & WR_INLINE_MASK))) { + rxe_dbg_qp(qp, "opcode doesn't support inline data"); err = -EINVAL; *bad_wr = wr; break; @@ -669,17 +861,26 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, length = 0; for (i = 0; i < wr->num_sge; i++) length += wr->sg_list[i].length; + if (length > 1<<31) { + err = -EINVAL; + rxe_dbg_qp(qp, "message length too long"); + *bad_wr = wr; + break; + } err = post_one_send(qp, wr, mask, length); - if (err) { *bad_wr = wr; break; } + wr = next; } - rxe_sched_task(&qp->req.task); + /* if we didn't post anything there's nothing to do */ + if (!err) + rxe_sched_task(&qp->req.task); + if (unlikely(qp->req.state == QP_STATE_ERROR)) rxe_sched_task(&qp->comp.task); @@ -690,23 +891,90 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { struct rxe_qp *qp = to_rqp(ibqp); + int err; if (unlikely(!qp->valid)) { *bad_wr = wr; - return -EINVAL; + err = -EINVAL; + rxe_dbg_qp(qp, "qp destroyed"); + goto err_out; } if (unlikely(qp->req.state < QP_STATE_READY)) { *bad_wr = wr; - return -EINVAL; + err = -EINVAL; + rxe_dbg_qp(qp, "qp not ready to send"); + goto err_out; } if (qp->is_user) { /* Utilize process context to do protocol processing */ rxe_run_task(&qp->req.task); - return 0; - } else - return rxe_post_send_kernel(qp, wr, bad_wr); + } else { + err = rxe_post_send_kernel(qp, wr, bad_wr); + if (err) + goto err_out; + } + + return 0; + +err_out: + rxe_err_qp(qp, "returned err = %d", err); + return err; +} + +/* recv wr */ +static int post_one_recv(struct rxe_rq *rq, const struct ib_recv_wr *ibwr) +{ + int i; + unsigned long length; + struct rxe_recv_wqe *recv_wqe; + int num_sge = ibwr->num_sge; + int full; + int err; + + full = queue_full(rq->queue, QUEUE_TYPE_FROM_ULP); + if (unlikely(full)) { + err = -ENOMEM; + rxe_dbg("queue full"); + goto err_out; + } + + if (unlikely(num_sge > rq->max_sge)) { + err = -EINVAL; + rxe_dbg("bad num_sge > max_sge"); + goto err_out; + } + + length = 0; + for (i = 0; i < num_sge; i++) + length += ibwr->sg_list[i].length; + + /* IBA max message size is 2^31 */ + if (length >= (1UL<<31)) { + err = -EINVAL; + rxe_dbg("message length too long"); + goto err_out; + } + + recv_wqe = queue_producer_addr(rq->queue, QUEUE_TYPE_FROM_ULP); + + recv_wqe->wr_id = ibwr->wr_id; + recv_wqe->dma.length = length; + recv_wqe->dma.resid = length; + recv_wqe->dma.num_sge = num_sge; + recv_wqe->dma.cur_sge = 0; + recv_wqe->dma.sge_offset = 0; + memcpy(recv_wqe->dma.sge, ibwr->sg_list, + num_sge * sizeof(struct ib_sge)); + + queue_advance_producer(rq->queue, QUEUE_TYPE_FROM_ULP); + + return 0; + +err_out: + rxe_dbg("returned err = %d", err); + return err; } static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, @@ -719,12 +987,16 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, if (unlikely((qp_state(qp) < IB_QPS_INIT) || !qp->valid)) { *bad_wr = wr; - return -EINVAL; + err = -EINVAL; + rxe_dbg_qp(qp, "qp destroyed or not ready to post recv"); + goto err_out; } if (unlikely(qp->srq)) { *bad_wr = wr; - return -EINVAL; + err = -EINVAL; + rxe_dbg_qp(qp, "use post_srq_recv instead"); + goto err_out; } spin_lock_irqsave(&rq->producer_lock, flags); @@ -743,73 +1015,101 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, if (qp->resp.state == QP_STATE_ERROR) rxe_sched_task(&qp->resp.task); +err_out: + if (err) + rxe_err_qp(qp, "returned err = %d", err); + return err; } +/* cq */ static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata) { - int err; struct ib_device *dev = ibcq->device; struct rxe_dev *rxe = to_rdev(dev); struct rxe_cq *cq = to_rcq(ibcq); struct rxe_create_cq_resp __user *uresp = NULL; + int err, cleanup_err; if (udata) { - if (udata->outlen < sizeof(*uresp)) - return -EINVAL; + if (udata->outlen < sizeof(*uresp)) { + err = -EINVAL; + rxe_dbg_dev(rxe, "malformed udata, err = %d", err); + goto err_out; + } uresp = udata->outbuf; } - if (attr->flags) - return -EOPNOTSUPP; + if (attr->flags) { + err = -EOPNOTSUPP; + rxe_dbg_dev(rxe, "bad attr->flags, err = %d", err); + goto err_out; + } err = rxe_cq_chk_attr(rxe, NULL, attr->cqe, attr->comp_vector); - if (err) - return err; + if (err) { + rxe_dbg_dev(rxe, "bad init attributes, err = %d", err); + goto err_out; + } + + err = rxe_add_to_pool(&rxe->cq_pool, cq); + if (err) { + rxe_dbg_dev(rxe, "unable to create cq, err = %d", err); + goto err_out; + } err = rxe_cq_from_init(rxe, cq, attr->cqe, attr->comp_vector, udata, uresp); - if (err) - return err; - - return rxe_add_to_pool(&rxe->cq_pool, cq); -} - -static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) -{ - struct rxe_cq *cq = to_rcq(ibcq); - - /* See IBA C11-17: The CI shall return an error if this Verb is - * invoked while a Work Queue is still associated with the CQ. - */ - if (atomic_read(&cq->num_wq)) - return -EINVAL; - - rxe_cq_disable(cq); + if (err) { + rxe_dbg_cq(cq, "create cq failed, err = %d", err); + goto err_cleanup; + } - rxe_cleanup(cq); return 0; + +err_cleanup: + cleanup_err = rxe_cleanup(cq); + if (cleanup_err) + rxe_err_cq(cq, "cleanup failed, err = %d", cleanup_err); +err_out: + rxe_err_dev(rxe, "returned err = %d", err); + return err; } static int rxe_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata) { - int err; struct rxe_cq *cq = to_rcq(ibcq); struct rxe_dev *rxe = to_rdev(ibcq->device); struct rxe_resize_cq_resp __user *uresp = NULL; + int err; if (udata) { - if (udata->outlen < sizeof(*uresp)) - return -EINVAL; + if (udata->outlen < sizeof(*uresp)) { + err = -EINVAL; + rxe_dbg_cq(cq, "malformed udata"); + goto err_out; + } uresp = udata->outbuf; } err = rxe_cq_chk_attr(rxe, cq, cqe, 0); - if (err) - return err; + if (err) { + rxe_dbg_cq(cq, "bad attr, err = %d", err); + goto err_out; + } - return rxe_cq_resize_queue(cq, cqe, uresp, udata); + err = rxe_cq_resize_queue(cq, cqe, uresp, udata); + if (err) { + rxe_dbg_cq(cq, "resize cq failed, err = %d", err); + goto err_out; + } + + return 0; + +err_out: + rxe_err_cq(cq, "returned err = %d", err); + return err; } static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) @@ -823,7 +1123,7 @@ static int rxe_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) for (i = 0; i < num_entries; i++) { cqe = queue_head(cq->queue, QUEUE_TYPE_TO_ULP); if (!cqe) - break; + break; /* queue empty */ memcpy(wc++, &cqe->ibwc, sizeof(*wc)); queue_advance_consumer(cq->queue, QUEUE_TYPE_TO_ULP); @@ -864,6 +1164,34 @@ static int rxe_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) return ret; } +static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) +{ + struct rxe_cq *cq = to_rcq(ibcq); + int err; + + /* See IBA C11-17: The CI shall return an error if this Verb is + * invoked while a Work Queue is still associated with the CQ. + */ + if (atomic_read(&cq->num_wq)) { + err = -EINVAL; + rxe_dbg_cq(cq, "still in use"); + goto err_out; + } + + rxe_cq_disable(cq); + + err = rxe_cleanup(cq); + if (err) + rxe_err_cq(cq, "cleanup failed, err = %d", err); + + return 0; + +err_out: + rxe_err_cq(cq, "returned err = %d", err); + return err; +} + +/* mr */ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) { struct rxe_dev *rxe = to_rdev(ibpd->device); @@ -874,12 +1202,15 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { err = -ENOMEM; + rxe_dbg_dev(rxe, "no memory for mr"); goto err_out; } err = rxe_add_to_pool(&rxe->mr_pool, mr); - if (err) + if (err) { + rxe_dbg_dev(rxe, "unable to create mr"); goto err_free; + } rxe_get(pd); mr->ibmr.pd = ibpd; @@ -892,46 +1223,53 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) err_free: kfree(mr); err_out: + rxe_err_pd(pd, "returned err = %d", err); return ERR_PTR(err); } -static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, - u64 start, - u64 length, - u64 iova, - int access, struct ib_udata *udata) +static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start, + u64 length, u64 iova, int access, + struct ib_udata *udata) { - int err; struct rxe_dev *rxe = to_rdev(ibpd->device); struct rxe_pd *pd = to_rpd(ibpd); struct rxe_mr *mr; + int err, cleanup_err; mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { err = -ENOMEM; + rxe_dbg_pd(pd, "no memory for mr"); goto err_out; } err = rxe_add_to_pool(&rxe->mr_pool, mr); - if (err) + if (err) { + rxe_dbg_pd(pd, "unable to create mr"); goto err_free; + } rxe_get(pd); mr->ibmr.pd = ibpd; mr->ibmr.device = ibpd->device; err = rxe_mr_init_user(rxe, start, length, iova, access, mr); - if (err) + if (err) { + rxe_dbg_mr(mr, "reg_user_mr failed, err = %d", err); goto err_cleanup; + } rxe_finalize(mr); return &mr->ibmr; err_cleanup: - rxe_cleanup(mr); + cleanup_err = rxe_cleanup(mr); + if (cleanup_err) + rxe_err_mr(mr, "cleanup failed, err = %d", cleanup_err); err_free: kfree(mr); err_out: + rxe_err_pd(pd, "returned err = %d", err); return ERR_PTR(err); } @@ -941,40 +1279,76 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type, struct rxe_dev *rxe = to_rdev(ibpd->device); struct rxe_pd *pd = to_rpd(ibpd); struct rxe_mr *mr; - int err; + int err, cleanup_err; - if (mr_type != IB_MR_TYPE_MEM_REG) - return ERR_PTR(-EINVAL); + if (mr_type != IB_MR_TYPE_MEM_REG) { + err = -EINVAL; + rxe_dbg_pd(pd, "mr type %d not supported, err = %d", + mr_type, err); + goto err_out; + } mr = kzalloc(sizeof(*mr), GFP_KERNEL); if (!mr) { err = -ENOMEM; + rxe_dbg_mr(mr, "no memory for mr"); goto err_out; } err = rxe_add_to_pool(&rxe->mr_pool, mr); - if (err) + if (err) { + rxe_dbg_mr(mr, "unable to create mr, err = %d", err); goto err_free; + } rxe_get(pd); mr->ibmr.pd = ibpd; mr->ibmr.device = ibpd->device; err = rxe_mr_init_fast(max_num_sg, mr); - if (err) + if (err) { + rxe_dbg_mr(mr, "alloc_mr failed, err = %d", err); goto err_cleanup; + } rxe_finalize(mr); return &mr->ibmr; err_cleanup: - rxe_cleanup(mr); + cleanup_err = rxe_cleanup(mr); + if (cleanup_err) + rxe_err_mr(mr, "cleanup failed, err = %d", err); err_free: kfree(mr); err_out: + rxe_err_pd(pd, "returned err = %d", err); return ERR_PTR(err); } +static int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) +{ + struct rxe_mr *mr = to_rmr(ibmr); + int err, cleanup_err; + + /* See IBA 10.6.7.2.6 */ + if (atomic_read(&mr->num_mw) > 0) { + err = -EINVAL; + rxe_dbg_mr(mr, "mr has mw's bound"); + goto err_out; + } + + cleanup_err = rxe_cleanup(mr); + if (cleanup_err) + rxe_err_mr(mr, "cleanup failed, err = %d", cleanup_err); + + kfree_rcu(mr); + return 0; + +err_out: + rxe_err_mr(mr, "returned err = %d", err); + return err; +} + static ssize_t parent_show(struct device *device, struct device_attribute *attr, char *buf) { -- GitLab From 3946fc2a42b18cf0b675121158a2625825ce27b5 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:27 -0600 Subject: [PATCH 1240/5631] RDMA/rxe: Convert tasklet args to queue pairs Originally is was thought that the tasklet machinery in rxe_task.c would be used in other applications but that has not happened for years. This patch replaces the 'void *arg' by struct 'rxe_qp *qp' in the parameters to the tasklet calls. This change will have no affect on performance but may make the code a little clearer. Link: https://lore.kernel.org/r/20230304174533.11296-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 3 +-- drivers/infiniband/sw/rxe/rxe_loc.h | 6 +++--- drivers/infiniband/sw/rxe/rxe_req.c | 3 +-- drivers/infiniband/sw/rxe/rxe_resp.c | 3 +-- drivers/infiniband/sw/rxe/rxe_task.c | 11 ++++++----- drivers/infiniband/sw/rxe/rxe_task.h | 9 +++++---- 6 files changed, 17 insertions(+), 18 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 876057e3ee3c..cbfa16b3a490 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -575,9 +575,8 @@ static void free_pkt(struct rxe_pkt_info *pkt) ib_device_put(dev); } -int rxe_completer(void *arg) +int rxe_completer(struct rxe_qp *qp) { - struct rxe_qp *qp = (struct rxe_qp *)arg; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_send_wqe *wqe = NULL; struct sk_buff *skb = NULL; diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h index 839de34cf4c9..804b15e929dd 100644 --- a/drivers/infiniband/sw/rxe/rxe_loc.h +++ b/drivers/infiniband/sw/rxe/rxe_loc.h @@ -170,9 +170,9 @@ void rxe_srq_cleanup(struct rxe_pool_elem *elem); void rxe_dealloc(struct ib_device *ib_dev); -int rxe_completer(void *arg); -int rxe_requester(void *arg); -int rxe_responder(void *arg); +int rxe_completer(struct rxe_qp *qp); +int rxe_requester(struct rxe_qp *qp); +int rxe_responder(struct rxe_qp *qp); /* rxe_icrc.c */ int rxe_icrc_init(struct rxe_dev *rxe); diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 899c8779f800..f2dc2d191e16 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -635,9 +635,8 @@ static int rxe_do_local_ops(struct rxe_qp *qp, struct rxe_send_wqe *wqe) return 0; } -int rxe_requester(void *arg) +int rxe_requester(struct rxe_qp *qp) { - struct rxe_qp *qp = (struct rxe_qp *)arg; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); struct rxe_pkt_info pkt; struct sk_buff *skb; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 4217eec03a94..7cb1b962d665 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1443,9 +1443,8 @@ static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify) queue_advance_consumer(q, q->type); } -int rxe_responder(void *arg) +int rxe_responder(struct rxe_qp *qp) { - struct rxe_qp *qp = (struct rxe_qp *)arg; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); enum resp_states state; struct rxe_pkt_info *pkt = NULL; diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 60b90e33a884..959cc6229a34 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -11,7 +11,7 @@ int __rxe_do_task(struct rxe_task *task) { int ret; - while ((ret = task->func(task->arg)) == 0) + while ((ret = task->func(task->qp)) == 0) ; task->ret = ret; @@ -29,7 +29,7 @@ static void do_task(struct tasklet_struct *t) int cont; int ret; struct rxe_task *task = from_tasklet(task, t, tasklet); - struct rxe_qp *qp = (struct rxe_qp *)task->arg; + struct rxe_qp *qp = (struct rxe_qp *)task->qp; unsigned int iterations = RXE_MAX_ITERATIONS; spin_lock_bh(&task->lock); @@ -54,7 +54,7 @@ static void do_task(struct tasklet_struct *t) do { cont = 0; - ret = task->func(task->arg); + ret = task->func(task->qp); spin_lock_bh(&task->lock); switch (task->state) { @@ -91,9 +91,10 @@ static void do_task(struct tasklet_struct *t) task->ret = ret; } -int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *)) +int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, + int (*func)(struct rxe_qp *)) { - task->arg = arg; + task->qp = qp; task->func = func; task->destroyed = false; diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index 7b88129702ac..41efd5fd49b0 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -22,18 +22,19 @@ struct rxe_task { struct tasklet_struct tasklet; int state; spinlock_t lock; - void *arg; - int (*func)(void *arg); + struct rxe_qp *qp; + int (*func)(struct rxe_qp *qp); int ret; bool destroyed; }; /* * init rxe_task structure - * arg => parameter to pass to fcn + * qp => parameter to pass to func * func => function to call until it returns != 0 */ -int rxe_init_task(struct rxe_task *task, void *arg, int (*func)(void *)); +int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, + int (*func)(struct rxe_qp *)); /* cleanup task */ void rxe_cleanup_task(struct rxe_task *task); -- GitLab From 49dc9c1f0c7e396654a31a480328fffd902fa494 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:29 -0600 Subject: [PATCH 1241/5631] RDMA/rxe: Cleanup reset state handling in rxe_resp.c Cleanup the handling of qp in the error state, reset state and during rxe_qp_do_cleanup. The error state does about the same thing as the others but has code spread all over. This patch combines them in a cleaner way. Link: https://lore.kernel.org/r/20230304174533.11296-4-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe.h | 1 - drivers/infiniband/sw/rxe/rxe_resp.c | 107 ++++++++++++++------------- 2 files changed, 57 insertions(+), 51 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index bd8a8ea4ea8f..d33dd6cf83d3 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -133,7 +133,6 @@ enum resp_states { RESPST_ERR_LENGTH, RESPST_ERR_CQ_OVERFLOW, RESPST_ERROR, - RESPST_RESET, RESPST_DONE, RESPST_EXIT, }; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 7cb1b962d665..8f9bbb14fa7a 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -42,7 +42,6 @@ static char *resp_state_name[] = { [RESPST_ERR_LENGTH] = "ERR_LENGTH", [RESPST_ERR_CQ_OVERFLOW] = "ERR_CQ_OVERFLOW", [RESPST_ERROR] = "ERROR", - [RESPST_RESET] = "RESET", [RESPST_DONE] = "DONE", [RESPST_EXIT] = "EXIT", }; @@ -69,17 +68,6 @@ static inline enum resp_states get_req(struct rxe_qp *qp, { struct sk_buff *skb; - if (qp->resp.state == QP_STATE_ERROR) { - while ((skb = skb_dequeue(&qp->req_pkts))) { - rxe_put(qp); - kfree_skb(skb); - ib_device_put(qp->ibqp.device); - } - - /* go drain recv wr queue */ - return RESPST_CHK_RESOURCE; - } - skb = skb_peek(&qp->req_pkts); if (!skb) return RESPST_EXIT; @@ -334,24 +322,6 @@ static enum resp_states check_resource(struct rxe_qp *qp, { struct rxe_srq *srq = qp->srq; - if (qp->resp.state == QP_STATE_ERROR) { - if (qp->resp.wqe) { - qp->resp.status = IB_WC_WR_FLUSH_ERR; - return RESPST_COMPLETE; - } else if (!srq) { - qp->resp.wqe = queue_head(qp->rq.queue, - QUEUE_TYPE_FROM_CLIENT); - if (qp->resp.wqe) { - qp->resp.status = IB_WC_WR_FLUSH_ERR; - return RESPST_COMPLETE; - } else { - return RESPST_EXIT; - } - } else { - return RESPST_EXIT; - } - } - if (pkt->mask & (RXE_READ_OR_ATOMIC_MASK | RXE_ATOMIC_WRITE_MASK)) { /* it is the requesters job to not send * too many read/atomic ops, we just @@ -1425,22 +1395,66 @@ static enum resp_states do_class_d1e_error(struct rxe_qp *qp) } } -static void rxe_drain_req_pkts(struct rxe_qp *qp, bool notify) +/* drain incoming request packet queue */ +static void rxe_drain_req_pkts(struct rxe_qp *qp) { struct sk_buff *skb; - struct rxe_queue *q = qp->rq.queue; while ((skb = skb_dequeue(&qp->req_pkts))) { rxe_put(qp); kfree_skb(skb); ib_device_put(qp->ibqp.device); } +} + +/* complete receive wqe with flush error */ +static int complete_flush(struct rxe_qp *qp, struct rxe_recv_wqe *wqe) +{ + struct rxe_cqe cqe = {}; + struct ib_wc *wc = &cqe.ibwc; + struct ib_uverbs_wc *uwc = &cqe.uibwc; + + if (qp->rcq->is_user) { + uwc->status = IB_WC_WR_FLUSH_ERR; + uwc->qp_num = qp_num(qp); + uwc->wr_id = wqe->wr_id; + } else { + wc->status = IB_WC_WR_FLUSH_ERR; + wc->qp = &qp->ibqp; + wc->wr_id = wqe->wr_id; + } + + if (rxe_cq_post(qp->rcq, &cqe, 0)) + return -ENOMEM; + + return 0; +} + +/* drain and optionally complete the recive queue + * if unable to complete a wqe stop completing and + * just flush the remaining wqes + */ +static void rxe_drain_recv_queue(struct rxe_qp *qp, bool notify) +{ + struct rxe_queue *q = qp->rq.queue; + struct rxe_recv_wqe *wqe; + int err; - if (notify) + if (qp->srq) return; - while (!qp->srq && q && queue_head(q, q->type)) + while ((wqe = queue_head(q, q->type))) { + if (notify) { + err = complete_flush(qp, wqe); + if (err) { + rxe_dbg_qp(qp, "complete failed for recv wqe"); + notify = 0; + } + } queue_advance_consumer(q, q->type); + } + + qp->resp.wqe = NULL; } int rxe_responder(struct rxe_qp *qp) @@ -1453,20 +1467,18 @@ int rxe_responder(struct rxe_qp *qp) if (!rxe_get(qp)) return -EAGAIN; - qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; - - if (!qp->valid) + if (!qp->valid || qp->resp.state == QP_STATE_ERROR || + qp->resp.state == QP_STATE_RESET) { + bool notify = qp->valid && + (qp->resp.state == QP_STATE_ERROR); + rxe_drain_req_pkts(qp); + rxe_drain_recv_queue(qp, notify); goto exit; + } - switch (qp->resp.state) { - case QP_STATE_RESET: - state = RESPST_RESET; - break; + qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; - default: - state = RESPST_GET_REQ; - break; - } + state = RESPST_GET_REQ; while (1) { rxe_dbg_qp(qp, "state = %s\n", resp_state_name[state]); @@ -1625,11 +1637,6 @@ int rxe_responder(struct rxe_qp *qp) goto exit; - case RESPST_RESET: - rxe_drain_req_pkts(qp, false); - qp->resp.wqe = NULL; - goto exit; - case RESPST_ERROR: qp->resp.goto_error = 0; rxe_dbg_qp(qp, "moved to error state\n"); -- GitLab From fbdeb828a21ff8de045a27ddcfc6ee66201b9a94 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:30 -0600 Subject: [PATCH 1242/5631] RDMA/rxe: Cleanup error state handling in rxe_comp.c Cleanup the handling of qp in the error state, reset state and during rxe_qp_do_cleanup. Make the same as rxe_resp.c Link: https://lore.kernel.org/r/20230304174533.11296-5-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 55 +++++++++++++++++++++++----- drivers/infiniband/sw/rxe/rxe_cq.c | 1 + drivers/infiniband/sw/rxe/rxe_resp.c | 28 +++++++------- 3 files changed, 61 insertions(+), 23 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index cbfa16b3a490..f7ab0dfe1034 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -542,25 +542,60 @@ static inline enum comp_state complete_wqe(struct rxe_qp *qp, return COMPST_GET_WQE; } -static void rxe_drain_resp_pkts(struct rxe_qp *qp, bool notify) +/* drain incoming response packet queue */ +static void drain_resp_pkts(struct rxe_qp *qp) { struct sk_buff *skb; - struct rxe_send_wqe *wqe; - struct rxe_queue *q = qp->sq.queue; while ((skb = skb_dequeue(&qp->resp_pkts))) { rxe_put(qp); kfree_skb(skb); ib_device_put(qp->ibqp.device); } +} + +/* complete send wqe with flush error */ +static int flush_send_wqe(struct rxe_qp *qp, struct rxe_send_wqe *wqe) +{ + struct rxe_cqe cqe = {}; + struct ib_wc *wc = &cqe.ibwc; + struct ib_uverbs_wc *uwc = &cqe.uibwc; + int err; + + if (qp->is_user) { + uwc->wr_id = wqe->wr.wr_id; + uwc->status = IB_WC_WR_FLUSH_ERR; + uwc->qp_num = qp->ibqp.qp_num; + } else { + wc->wr_id = wqe->wr.wr_id; + wc->status = IB_WC_WR_FLUSH_ERR; + wc->qp = &qp->ibqp; + } + + err = rxe_cq_post(qp->scq, &cqe, 0); + if (err) + rxe_dbg_cq(qp->scq, "post cq failed, err = %d", err); + + return err; +} + +/* drain and optionally complete the send queue + * if unable to complete a wqe, i.e. cq is full, stop + * completing and flush the remaining wqes + */ +static void flush_send_queue(struct rxe_qp *qp, bool notify) +{ + struct rxe_send_wqe *wqe; + struct rxe_queue *q = qp->sq.queue; + int err; while ((wqe = queue_head(q, q->type))) { if (notify) { - wqe->status = IB_WC_WR_FLUSH_ERR; - do_complete(qp, wqe); - } else { - queue_advance_consumer(q, q->type); + err = flush_send_wqe(qp, wqe); + if (err) + notify = 0; } + queue_advance_consumer(q, q->type); } } @@ -589,8 +624,10 @@ int rxe_completer(struct rxe_qp *qp) if (!qp->valid || qp->comp.state == QP_STATE_ERROR || qp->comp.state == QP_STATE_RESET) { - rxe_drain_resp_pkts(qp, qp->valid && - qp->comp.state == QP_STATE_ERROR); + bool notify = qp->valid && + (qp->comp.state == QP_STATE_ERROR); + drain_resp_pkts(qp); + flush_send_queue(qp, notify); goto exit; } diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index 22fbc198e5d1..66a13c935d50 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -114,6 +114,7 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) full = queue_full(cq->queue, QUEUE_TYPE_TO_CLIENT); if (unlikely(full)) { + rxe_err_cq(cq, "queue full"); spin_unlock_irqrestore(&cq->cq_lock, flags); if (cq->ibcq.event_handler) { ev.device = cq->ibcq.device; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 8f9bbb14fa7a..2f71183449f9 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1396,7 +1396,7 @@ static enum resp_states do_class_d1e_error(struct rxe_qp *qp) } /* drain incoming request packet queue */ -static void rxe_drain_req_pkts(struct rxe_qp *qp) +static void drain_req_pkts(struct rxe_qp *qp) { struct sk_buff *skb; @@ -1408,33 +1408,35 @@ static void rxe_drain_req_pkts(struct rxe_qp *qp) } /* complete receive wqe with flush error */ -static int complete_flush(struct rxe_qp *qp, struct rxe_recv_wqe *wqe) +static int flush_recv_wqe(struct rxe_qp *qp, struct rxe_recv_wqe *wqe) { struct rxe_cqe cqe = {}; struct ib_wc *wc = &cqe.ibwc; struct ib_uverbs_wc *uwc = &cqe.uibwc; + int err; if (qp->rcq->is_user) { + uwc->wr_id = wqe->wr_id; uwc->status = IB_WC_WR_FLUSH_ERR; uwc->qp_num = qp_num(qp); - uwc->wr_id = wqe->wr_id; } else { + wc->wr_id = wqe->wr_id; wc->status = IB_WC_WR_FLUSH_ERR; wc->qp = &qp->ibqp; - wc->wr_id = wqe->wr_id; } - if (rxe_cq_post(qp->rcq, &cqe, 0)) - return -ENOMEM; + err = rxe_cq_post(qp->rcq, &cqe, 0); + if (err) + rxe_dbg_cq(qp->rcq, "post cq failed err = %d", err); - return 0; + return err; } /* drain and optionally complete the recive queue * if unable to complete a wqe stop completing and * just flush the remaining wqes */ -static void rxe_drain_recv_queue(struct rxe_qp *qp, bool notify) +static void flush_recv_queue(struct rxe_qp *qp, bool notify) { struct rxe_queue *q = qp->rq.queue; struct rxe_recv_wqe *wqe; @@ -1445,11 +1447,9 @@ static void rxe_drain_recv_queue(struct rxe_qp *qp, bool notify) while ((wqe = queue_head(q, q->type))) { if (notify) { - err = complete_flush(qp, wqe); - if (err) { - rxe_dbg_qp(qp, "complete failed for recv wqe"); + err = flush_recv_wqe(qp, wqe); + if (err) notify = 0; - } } queue_advance_consumer(q, q->type); } @@ -1471,8 +1471,8 @@ int rxe_responder(struct rxe_qp *qp) qp->resp.state == QP_STATE_RESET) { bool notify = qp->valid && (qp->resp.state == QP_STATE_ERROR); - rxe_drain_req_pkts(qp); - rxe_drain_recv_queue(qp, notify); + drain_req_pkts(qp); + flush_recv_queue(qp, notify); goto exit; } -- GitLab From a246aa2e8a6d8919462b7ffe550cbe51d2894152 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:31 -0600 Subject: [PATCH 1243/5631] RDMA/rxe: Remove qp reference counting in tasks Currently each of the three tasklets requester, completer and responder in the rxe driver take and release a reference to the qp argument at the beginning and end of the subroutines. The caller passing in the qp argument should be responsible for holding a reference to qp so these are not required. Further doing so breaks the qp cleanup code in rxe_qp_do_cleanup which calls these routines after all the references have been dropped so they cannot drain the packet and work request queues as intended. In fact if these routines are deferred by calling tasklet_schedule there is no guarantee that the calling code does have a qp reference. That is a bug in rxe_task.c which will be fixed later in this series. Link: https://lore.kernel.org/r/20230304174533.11296-6-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 5 ----- drivers/infiniband/sw/rxe/rxe_req.c | 5 ----- drivers/infiniband/sw/rxe/rxe_resp.c | 4 ---- 3 files changed, 14 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index f7ab0dfe1034..7aa8e90bdfe4 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -619,9 +619,6 @@ int rxe_completer(struct rxe_qp *qp) enum comp_state state; int ret; - if (!rxe_get(qp)) - return -EAGAIN; - if (!qp->valid || qp->comp.state == QP_STATE_ERROR || qp->comp.state == QP_STATE_RESET) { bool notify = qp->valid && @@ -824,7 +821,5 @@ int rxe_completer(struct rxe_qp *qp) out: if (pkt) free_pkt(pkt); - rxe_put(qp); - return ret; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index f2dc2d191e16..abc65c54bfd6 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -653,9 +653,6 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_ah *ah; struct rxe_av *av; - if (!rxe_get(qp)) - return -EAGAIN; - if (unlikely(!qp->valid)) goto exit; @@ -844,7 +841,5 @@ int rxe_requester(struct rxe_qp *qp) exit: ret = -EAGAIN; out: - rxe_put(qp); - return ret; } diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 2f71183449f9..01e3cbea8445 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1464,9 +1464,6 @@ int rxe_responder(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; int ret; - if (!rxe_get(qp)) - return -EAGAIN; - if (!qp->valid || qp->resp.state == QP_STATE_ERROR || qp->resp.state == QP_STATE_RESET) { bool notify = qp->valid && @@ -1658,6 +1655,5 @@ int rxe_responder(struct rxe_qp *qp) exit: ret = -EAGAIN; out: - rxe_put(qp); return ret; } -- GitLab From 960ebe97e5238565d15063c8f4d1b2108efe2e65 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:32 -0600 Subject: [PATCH 1244/5631] RDMA/rxe: Remove __rxe_do_task() The subroutine __rxe_do_task is not thread safe and it has no way to guarantee that the tasks, which are designed with the assumption that they are non-reentrant, are not reentered. All of its uses are non-performance critical. This patch replaces calls to __rxe_do_task with calls to rxe_sched_task. It also removes irrelevant or unneeded if tests. Instead of calling the task machinery a single call to the tasklet function (rxe_requester, etc.) is sufficient to draing the queues if task execution has been disabled or stopped. Together these changes allow the removal of __rxe_do_task. Link: https://lore.kernel.org/r/20230304174533.11296-7-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_qp.c | 56 +++++++++------------------- drivers/infiniband/sw/rxe/rxe_task.c | 13 ------- drivers/infiniband/sw/rxe/rxe_task.h | 6 --- 3 files changed, 17 insertions(+), 58 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index c954dd9394ba..49891f8ed4e6 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -473,29 +473,23 @@ static void rxe_qp_reset(struct rxe_qp *qp) { /* stop tasks from running */ rxe_disable_task(&qp->resp.task); - - /* stop request/comp */ - if (qp->sq.queue) { - if (qp_type(qp) == IB_QPT_RC) - rxe_disable_task(&qp->comp.task); - rxe_disable_task(&qp->req.task); - } + rxe_disable_task(&qp->comp.task); + rxe_disable_task(&qp->req.task); /* move qp to the reset state */ qp->req.state = QP_STATE_RESET; qp->comp.state = QP_STATE_RESET; qp->resp.state = QP_STATE_RESET; - /* let state machines reset themselves drain work and packet queues - * etc. - */ - __rxe_do_task(&qp->resp.task); + /* drain work and packet queuesc */ + rxe_requester(qp); + rxe_completer(qp); + rxe_responder(qp); - if (qp->sq.queue) { - __rxe_do_task(&qp->comp.task); - __rxe_do_task(&qp->req.task); + if (qp->rq.queue) + rxe_queue_reset(qp->rq.queue); + if (qp->sq.queue) rxe_queue_reset(qp->sq.queue); - } /* cleanup attributes */ atomic_set(&qp->ssn, 0); @@ -518,13 +512,8 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* reenable tasks */ rxe_enable_task(&qp->resp.task); - - if (qp->sq.queue) { - if (qp_type(qp) == IB_QPT_RC) - rxe_enable_task(&qp->comp.task); - - rxe_enable_task(&qp->req.task); - } + rxe_enable_task(&qp->comp.task); + rxe_enable_task(&qp->req.task); } /* drain the send queue */ @@ -533,10 +522,7 @@ static void rxe_qp_drain(struct rxe_qp *qp) if (qp->sq.queue) { if (qp->req.state != QP_STATE_DRAINED) { qp->req.state = QP_STATE_DRAIN; - if (qp_type(qp) == IB_QPT_RC) - rxe_sched_task(&qp->comp.task); - else - __rxe_do_task(&qp->comp.task); + rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); } } @@ -552,11 +538,7 @@ void rxe_qp_error(struct rxe_qp *qp) /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); - - if (qp_type(qp) == IB_QPT_RC) - rxe_sched_task(&qp->comp.task); - else - __rxe_do_task(&qp->comp.task); + rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); } @@ -773,24 +755,20 @@ static void rxe_qp_do_cleanup(struct work_struct *work) qp->valid = 0; qp->qp_timeout_jiffies = 0; - rxe_cleanup_task(&qp->resp.task); if (qp_type(qp) == IB_QPT_RC) { del_timer_sync(&qp->retrans_timer); del_timer_sync(&qp->rnr_nak_timer); } + rxe_cleanup_task(&qp->resp.task); rxe_cleanup_task(&qp->req.task); rxe_cleanup_task(&qp->comp.task); /* flush out any receive wr's or pending requests */ - if (qp->req.task.func) - __rxe_do_task(&qp->req.task); - - if (qp->sq.queue) { - __rxe_do_task(&qp->comp.task); - __rxe_do_task(&qp->req.task); - } + rxe_requester(qp); + rxe_completer(qp); + rxe_responder(qp); if (qp->sq.queue) rxe_queue_cleanup(qp->sq.queue); diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index 959cc6229a34..a67f48545443 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -6,19 +6,6 @@ #include "rxe.h" -int __rxe_do_task(struct rxe_task *task) - -{ - int ret; - - while ((ret = task->func(task->qp)) == 0) - ; - - task->ret = ret; - - return ret; -} - /* * this locking is due to a potential race where * a second caller finds the task already running diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index 41efd5fd49b0..99585e40cef9 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -39,12 +39,6 @@ int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, /* cleanup task */ void rxe_cleanup_task(struct rxe_task *task); -/* - * raw call to func in loop without any checking - * can call when tasklets are disabled - */ -int __rxe_do_task(struct rxe_task *task); - void rxe_run_task(struct rxe_task *task); void rxe_sched_task(struct rxe_task *task); -- GitLab From f455a1bc972cefc4bf2dbf1bf37a36bb51a5f7e7 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:33 -0600 Subject: [PATCH 1245/5631] RDMA/rxe: Make tasks schedule each other Replace rxe_run_task() by rxe_sched_task() when tasks call each other. These are not performance critical and mainly involve error paths but they run the risk of causing deadlocks. Link: https://lore.kernel.org/r/20230304174533.11296-8-rpearsonhpe@gmail.com Signed-off-by: Ian Ziemba Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 8 ++++---- drivers/infiniband/sw/rxe/rxe_req.c | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 7aa8e90bdfe4..2c70cdcd55dc 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -322,7 +322,7 @@ static inline enum comp_state check_ack(struct rxe_qp *qp, qp->comp.psn = pkt->psn; if (qp->req.wait_psn) { qp->req.wait_psn = 0; - rxe_run_task(&qp->req.task); + rxe_sched_task(&qp->req.task); } } return COMPST_ERROR_RETRY; @@ -473,7 +473,7 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) */ if (qp->req.wait_fence) { qp->req.wait_fence = 0; - rxe_run_task(&qp->req.task); + rxe_sched_task(&qp->req.task); } } @@ -487,7 +487,7 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp, if (qp->req.need_rd_atomic) { qp->comp.timeout_retry = 0; qp->req.need_rd_atomic = 0; - rxe_run_task(&qp->req.task); + rxe_sched_task(&qp->req.task); } } @@ -767,7 +767,7 @@ int rxe_completer(struct rxe_qp *qp) RXE_CNT_COMP_RETRY); qp->req.need_retry = 1; qp->comp.started_retry = 1; - rxe_run_task(&qp->req.task); + rxe_sched_task(&qp->req.task); } goto done; diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index abc65c54bfd6..745731140a54 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -753,7 +753,7 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wqe_index); wqe->state = wqe_state_done; wqe->status = IB_WC_SUCCESS; - rxe_run_task(&qp->comp.task); + rxe_sched_task(&qp->comp.task); goto done; } payload = mtu; @@ -837,7 +837,7 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); wqe->state = wqe_state_error; qp->req.state = QP_STATE_ERROR; - rxe_run_task(&qp->comp.task); + rxe_sched_task(&qp->comp.task); exit: ret = -EAGAIN; out: -- GitLab From d94671632572813e90bcf475bb4c7d51fbf20173 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Sat, 4 Mar 2023 11:45:34 -0600 Subject: [PATCH 1246/5631] RDMA/rxe: Rewrite rxe_task.c This patch is a major rewrite of the tasklet routines in rxe_task.c. The main motivation for this is the realization that the code violates the safety of the qp pointer by correct reference counting. When a tasklet is scheduled from a verbs API the calling thread has a valid reference to the qp and schedules the tasklet to run at a later time carrying a pointer to the qp. Once the calling code returns however the qp can be destroyed at any time. In order to correct this a reference to the qp must be taken when the task is scheduled and held until it finishes running. This is complicated by the tasklet library not alwys running a task that is scheduled depending on whether someone else has scheduled it. This patch moves the logic for deciding whether to run or schedule a task outside of do_task() and guarantees that there is only one copy of the task scheduled or running at a time. Secondly the separate flags controlling teardown and draining of the task are included in the task state machine and all references to the state are protected by spinlocks to avoid consistency and memory barrier issues. Link: https://lore.kernel.org/r/20230304174533.11296-9-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_task.c | 266 +++++++++++++++++++++------ drivers/infiniband/sw/rxe/rxe_task.h | 8 +- 2 files changed, 218 insertions(+), 56 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index a67f48545443..fea9a517c8d9 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -6,56 +6,128 @@ #include "rxe.h" -/* - * this locking is due to a potential race where - * a second caller finds the task already running - * but looks just after the last call to func +/* Check if task is idle i.e. not running, not scheduled in + * tasklet queue and not draining. If so move to busy to + * reserve a slot in do_task() by setting to busy and taking + * a qp reference to cover the gap from now until the task finishes. + * state will move out of busy if task returns a non zero value + * in do_task(). If state is already busy it is raised to armed + * to indicate to do_task that additional pass should be made + * over the task. + * Context: caller should hold task->lock. + * Returns: true if state transitioned from idle to busy else false. + */ +static bool __reserve_if_idle(struct rxe_task *task) +{ + WARN_ON(rxe_read(task->qp) <= 0); + + if (task->tasklet.state & TASKLET_STATE_SCHED) + return false; + + if (task->state == TASK_STATE_IDLE) { + rxe_get(task->qp); + task->state = TASK_STATE_BUSY; + task->num_sched++; + return true; + } + + if (task->state == TASK_STATE_BUSY) + task->state = TASK_STATE_ARMED; + + return false; +} + +/* check if task is idle or drained and not currently + * scheduled in the tasklet queue. This routine is + * called by rxe_cleanup_task or rxe_disable_task to + * see if the queue is empty. + * Context: caller should hold task->lock. + * Returns true if done else false. + */ +static bool __is_done(struct rxe_task *task) +{ + if (task->tasklet.state & TASKLET_STATE_SCHED) + return false; + + if (task->state == TASK_STATE_IDLE || + task->state == TASK_STATE_DRAINED) { + return true; + } + + return false; +} + +/* a locked version of __is_done */ +static bool is_done(struct rxe_task *task) +{ + unsigned long flags; + int done; + + spin_lock_irqsave(&task->lock, flags); + done = __is_done(task); + spin_unlock_irqrestore(&task->lock, flags); + + return done; +} + +/* do_task is a wrapper for the three tasks (requester, + * completer, responder) and calls them in a loop until + * they return a non-zero value. It is called either + * directly by rxe_run_task or indirectly if rxe_sched_task + * schedules the task. They must call __reserve_if_idle to + * move the task to busy before calling or scheduling. + * The task can also be moved to drained or invalid + * by calls to rxe-cleanup_task or rxe_disable_task. + * In that case tasks which get here are not executed but + * just flushed. The tasks are designed to look to see if + * there is work to do and do part of it before returning + * here with a return value of zero until all the work + * has been consumed then it retuens a non-zero value. + * The number of times the task can be run is limited by + * max iterations so one task cannot hold the cpu forever. */ static void do_task(struct tasklet_struct *t) { int cont; int ret; struct rxe_task *task = from_tasklet(task, t, tasklet); - struct rxe_qp *qp = (struct rxe_qp *)task->qp; - unsigned int iterations = RXE_MAX_ITERATIONS; + unsigned int iterations; + unsigned long flags; + int resched = 0; - spin_lock_bh(&task->lock); - switch (task->state) { - case TASK_STATE_START: - task->state = TASK_STATE_BUSY; - spin_unlock_bh(&task->lock); - break; - - case TASK_STATE_BUSY: - task->state = TASK_STATE_ARMED; - fallthrough; - case TASK_STATE_ARMED: - spin_unlock_bh(&task->lock); - return; + WARN_ON(rxe_read(task->qp) <= 0); - default: - spin_unlock_bh(&task->lock); - rxe_dbg_qp(qp, "failed with bad state %d\n", task->state); + spin_lock_irqsave(&task->lock, flags); + if (task->state >= TASK_STATE_DRAINED) { + rxe_put(task->qp); + task->num_done++; + spin_unlock_irqrestore(&task->lock, flags); return; } + spin_unlock_irqrestore(&task->lock, flags); do { + iterations = RXE_MAX_ITERATIONS; cont = 0; - ret = task->func(task->qp); - spin_lock_bh(&task->lock); + do { + ret = task->func(task->qp); + } while (ret == 0 && iterations-- > 0); + + spin_lock_irqsave(&task->lock, flags); switch (task->state) { case TASK_STATE_BUSY: if (ret) { - task->state = TASK_STATE_START; - } else if (iterations--) { - cont = 1; + task->state = TASK_STATE_IDLE; } else { - /* reschedule the tasklet and exit + /* This can happen if the client + * can add work faster than the + * tasklet can finish it. + * Reschedule the tasklet and exit * the loop to give up the cpu */ - tasklet_schedule(&task->tasklet); - task->state = TASK_STATE_START; + task->state = TASK_STATE_IDLE; + resched = 1; } break; @@ -68,72 +140,158 @@ static void do_task(struct tasklet_struct *t) cont = 1; break; + case TASK_STATE_DRAINING: + if (ret) + task->state = TASK_STATE_DRAINED; + else + cont = 1; + break; + default: - rxe_dbg_qp(qp, "failed with bad state %d\n", - task->state); + WARN_ON(1); + rxe_info_qp(task->qp, "unexpected task state = %d", task->state); + } + + if (!cont) { + task->num_done++; + if (WARN_ON(task->num_done != task->num_sched)) + rxe_err_qp(task->qp, "%ld tasks scheduled, %ld tasks done", + task->num_sched, task->num_done); } - spin_unlock_bh(&task->lock); + spin_unlock_irqrestore(&task->lock, flags); } while (cont); task->ret = ret; + + if (resched) + rxe_sched_task(task); + + rxe_put(task->qp); } int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, int (*func)(struct rxe_qp *)) { - task->qp = qp; - task->func = func; - task->destroyed = false; + WARN_ON(rxe_read(qp) <= 0); + + task->qp = qp; + task->func = func; tasklet_setup(&task->tasklet, do_task); - task->state = TASK_STATE_START; + task->state = TASK_STATE_IDLE; spin_lock_init(&task->lock); return 0; } +/* rxe_cleanup_task is only called from rxe_do_qp_cleanup in + * process context. The qp is already completed with no + * remaining references. Once the queue is drained the + * task is moved to invalid and returns. The qp cleanup + * code then calls the task functions directly without + * using the task struct to drain any late arriving packets + * or work requests. + */ void rxe_cleanup_task(struct rxe_task *task) { - bool idle; + unsigned long flags; - /* - * Mark the task, then wait for it to finish. It might be - * running in a non-tasklet (direct call) context. - */ - task->destroyed = true; + spin_lock_irqsave(&task->lock, flags); + if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { + task->state = TASK_STATE_DRAINING; + } else { + task->state = TASK_STATE_INVALID; + spin_unlock_irqrestore(&task->lock, flags); + return; + } + spin_unlock_irqrestore(&task->lock, flags); - do { - spin_lock_bh(&task->lock); - idle = (task->state == TASK_STATE_START); - spin_unlock_bh(&task->lock); - } while (!idle); + /* now the task cannot be scheduled or run just wait + * for the previously scheduled tasks to finish. + */ + while (!is_done(task)) + cond_resched(); tasklet_kill(&task->tasklet); + + spin_lock_irqsave(&task->lock, flags); + task->state = TASK_STATE_INVALID; + spin_unlock_irqrestore(&task->lock, flags); } +/* run the task inline if it is currently idle + * cannot call do_task holding the lock + */ void rxe_run_task(struct rxe_task *task) { - if (task->destroyed) - return; + unsigned long flags; + int run; + + WARN_ON(rxe_read(task->qp) <= 0); - do_task(&task->tasklet); + spin_lock_irqsave(&task->lock, flags); + run = __reserve_if_idle(task); + spin_unlock_irqrestore(&task->lock, flags); + + if (run) + do_task(&task->tasklet); } +/* schedule the task to run later as a tasklet. + * the tasklet)schedule call can be called holding + * the lock. + */ void rxe_sched_task(struct rxe_task *task) { - if (task->destroyed) - return; + unsigned long flags; + + WARN_ON(rxe_read(task->qp) <= 0); - tasklet_schedule(&task->tasklet); + spin_lock_irqsave(&task->lock, flags); + if (__reserve_if_idle(task)) + tasklet_schedule(&task->tasklet); + spin_unlock_irqrestore(&task->lock, flags); } +/* rxe_disable/enable_task are only called from + * rxe_modify_qp in process context. Task is moved + * to the drained state by do_task. + */ void rxe_disable_task(struct rxe_task *task) { + unsigned long flags; + + WARN_ON(rxe_read(task->qp) <= 0); + + spin_lock_irqsave(&task->lock, flags); + if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { + task->state = TASK_STATE_DRAINING; + } else { + task->state = TASK_STATE_DRAINED; + spin_unlock_irqrestore(&task->lock, flags); + return; + } + spin_unlock_irqrestore(&task->lock, flags); + + while (!is_done(task)) + cond_resched(); + tasklet_disable(&task->tasklet); } void rxe_enable_task(struct rxe_task *task) { + unsigned long flags; + + WARN_ON(rxe_read(task->qp) <= 0); + + spin_lock_irqsave(&task->lock, flags); + if (task->state == TASK_STATE_INVALID) { + spin_unlock_irqrestore(&task->lock, flags); + return; + } + task->state = TASK_STATE_IDLE; tasklet_enable(&task->tasklet); + spin_unlock_irqrestore(&task->lock, flags); } diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h index 99585e40cef9..facb7c8e3729 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.h +++ b/drivers/infiniband/sw/rxe/rxe_task.h @@ -8,9 +8,12 @@ #define RXE_TASK_H enum { - TASK_STATE_START = 0, + TASK_STATE_IDLE = 0, TASK_STATE_BUSY = 1, TASK_STATE_ARMED = 2, + TASK_STATE_DRAINING = 3, + TASK_STATE_DRAINED = 4, + TASK_STATE_INVALID = 5, }; /* @@ -25,7 +28,8 @@ struct rxe_task { struct rxe_qp *qp; int (*func)(struct rxe_qp *qp); int ret; - bool destroyed; + long num_sched; + long num_done; }; /* -- GitLab From d649c638dc26f3501da510cf7fceb5c15ca54258 Mon Sep 17 00:00:00 2001 From: Cheng Xu Date: Tue, 7 Mar 2023 18:29:23 +0800 Subject: [PATCH 1247/5631] RDMA/erdma: Use fixed hardware page size Hardware's page size is 4096, but the kernel's page size may vary. Driver should use hardware's page size when communicating with hardware. Fixes: 155055771704 ("RDMA/erdma: Add verbs implementation") Link: https://lore.kernel.org/r/20230307102924.70577-2-chengyou@linux.alibaba.com Signed-off-by: Cheng Xu Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/erdma/erdma_hw.h | 4 ++++ drivers/infiniband/hw/erdma/erdma_verbs.c | 17 +++++++++-------- 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h index 4c38d99c73f1..56e0c7a3e8f8 100644 --- a/drivers/infiniband/hw/erdma/erdma_hw.h +++ b/drivers/infiniband/hw/erdma/erdma_hw.h @@ -112,6 +112,10 @@ #define ERDMA_PAGE_SIZE_SUPPORT 0x7FFFF000 +/* Hardware page size definition */ +#define ERDMA_HW_PAGE_SHIFT 12 +#define ERDMA_HW_PAGE_SIZE 4096 + /* WQE related. */ #define EQE_SIZE 16 #define EQE_SHIFT 4 diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c index 9c30d78730aa..83e1b0d55977 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.c +++ b/drivers/infiniband/hw/erdma/erdma_verbs.c @@ -38,7 +38,7 @@ static int create_qp_cmd(struct erdma_dev *dev, struct erdma_qp *qp) FIELD_PREP(ERDMA_CMD_CREATE_QP_PD_MASK, pd->pdn); if (rdma_is_kernel_res(&qp->ibqp.res)) { - u32 pgsz_range = ilog2(SZ_1M) - PAGE_SHIFT; + u32 pgsz_range = ilog2(SZ_1M) - ERDMA_HW_PAGE_SHIFT; req.sq_cqn_mtt_cfg = FIELD_PREP(ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK, @@ -66,13 +66,13 @@ static int create_qp_cmd(struct erdma_dev *dev, struct erdma_qp *qp) user_qp = &qp->user_qp; req.sq_cqn_mtt_cfg = FIELD_PREP( ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK, - ilog2(user_qp->sq_mtt.page_size) - PAGE_SHIFT); + ilog2(user_qp->sq_mtt.page_size) - ERDMA_HW_PAGE_SHIFT); req.sq_cqn_mtt_cfg |= FIELD_PREP(ERDMA_CMD_CREATE_QP_CQN_MASK, qp->scq->cqn); req.rq_cqn_mtt_cfg = FIELD_PREP( ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK, - ilog2(user_qp->rq_mtt.page_size) - PAGE_SHIFT); + ilog2(user_qp->rq_mtt.page_size) - ERDMA_HW_PAGE_SHIFT); req.rq_cqn_mtt_cfg |= FIELD_PREP(ERDMA_CMD_CREATE_QP_CQN_MASK, qp->rcq->cqn); @@ -162,7 +162,7 @@ static int create_cq_cmd(struct erdma_dev *dev, struct erdma_cq *cq) if (rdma_is_kernel_res(&cq->ibcq.res)) { page_size = SZ_32M; req.cfg0 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK, - ilog2(page_size) - PAGE_SHIFT); + ilog2(page_size) - ERDMA_HW_PAGE_SHIFT); req.qbuf_addr_l = lower_32_bits(cq->kern_cq.qbuf_dma_addr); req.qbuf_addr_h = upper_32_bits(cq->kern_cq.qbuf_dma_addr); @@ -175,8 +175,9 @@ static int create_cq_cmd(struct erdma_dev *dev, struct erdma_cq *cq) cq->kern_cq.qbuf_dma_addr + (cq->depth << CQE_SHIFT); } else { mtt = &cq->user_cq.qbuf_mtt; - req.cfg0 |= FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK, - ilog2(mtt->page_size) - PAGE_SHIFT); + req.cfg0 |= + FIELD_PREP(ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK, + ilog2(mtt->page_size) - ERDMA_HW_PAGE_SHIFT); if (mtt->mtt_nents == 1) { req.qbuf_addr_l = lower_32_bits(*(u64 *)mtt->mtt_buf); req.qbuf_addr_h = upper_32_bits(*(u64 *)mtt->mtt_buf); @@ -636,7 +637,7 @@ static int init_user_qp(struct erdma_qp *qp, struct erdma_ucontext *uctx, u32 rq_offset; int ret; - if (len < (PAGE_ALIGN(qp->attrs.sq_size * SQEBB_SIZE) + + if (len < (ALIGN(qp->attrs.sq_size * SQEBB_SIZE, ERDMA_HW_PAGE_SIZE) + qp->attrs.rq_size * RQE_SIZE)) return -EINVAL; @@ -646,7 +647,7 @@ static int init_user_qp(struct erdma_qp *qp, struct erdma_ucontext *uctx, if (ret) return ret; - rq_offset = PAGE_ALIGN(qp->attrs.sq_size << SQEBB_SHIFT); + rq_offset = ALIGN(qp->attrs.sq_size << SQEBB_SHIFT, ERDMA_HW_PAGE_SIZE); qp->user_qp.rq_offset = rq_offset; ret = get_mtt_entries(qp->dev, &qp->user_qp.rq_mtt, va + rq_offset, -- GitLab From dcfbb67e48a2becfce7990386e985b9c45098ee5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 11:01:31 +0100 Subject: [PATCH 1248/5631] driver core: class: use lock_class_key already present in struct subsys_private In commit 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure"), we moved the lock_class_key into the internal structure shared by busses and classes, but only used it for buses. Move the class code to use this structure as it is already present and being allocated, instead of the statically allocated on-the-stack variable that class_create() was using as part of a macro wrapper around the core function call. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324100132.1633647-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 15 +++++++++------ include/linux/device/class.h | 36 ++---------------------------------- 2 files changed, 11 insertions(+), 40 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 3d65221b0dcb..dbaeb79ae917 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -154,9 +154,10 @@ static void class_remove_groups(struct class *cls, return sysfs_remove_groups(&cls->p->subsys.kobj, groups); } -int __class_register(struct class *cls, struct lock_class_key *key) +int class_register(struct class *cls) { struct subsys_private *cp; + struct lock_class_key *key; int error; pr_debug("device class '%s': registering\n", cls->name); @@ -167,6 +168,8 @@ int __class_register(struct class *cls, struct lock_class_key *key) klist_init(&cp->klist_devices, klist_class_dev_get, klist_class_dev_put); INIT_LIST_HEAD(&cp->interfaces); kset_init(&cp->glue_dirs); + key = &cp->lock_key; + lockdep_register_key(key); __mutex_init(&cp->mutex, "subsys mutex", key); error = kobject_set_name(&cp->subsys.kobj, "%s", cls->name); if (error) { @@ -201,7 +204,7 @@ int __class_register(struct class *cls, struct lock_class_key *key) cls->p = NULL; return error; } -EXPORT_SYMBOL_GPL(__class_register); +EXPORT_SYMBOL_GPL(class_register); void class_unregister(struct class *cls) { @@ -218,7 +221,7 @@ static void class_create_release(struct class *cls) } /** - * __class_create - create a struct class structure + * class_create - create a struct class structure * @name: pointer to a string for the name of this class. * @key: the lock_class_key for this class; used by mutex lock debugging * @@ -230,7 +233,7 @@ static void class_create_release(struct class *cls) * Note, the pointer created here is to be destroyed when finished by * making a call to class_destroy(). */ -struct class *__class_create(const char *name, struct lock_class_key *key) +struct class *class_create(const char *name) { struct class *cls; int retval; @@ -244,7 +247,7 @@ struct class *__class_create(const char *name, struct lock_class_key *key) cls->name = name; cls->class_release = class_create_release; - retval = __class_register(cls, key); + retval = class_register(cls); if (retval) goto error; @@ -254,7 +257,7 @@ struct class *__class_create(const char *name, struct lock_class_key *key) kfree(cls); return ERR_PTR(retval); } -EXPORT_SYMBOL_GPL(__class_create); +EXPORT_SYMBOL_GPL(class_create); /** * class_destroy - destroys a struct class structure diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 75c1451fcc63..03d2f99f84c5 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,18 +82,9 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check __class_register(struct class *class, - struct lock_class_key *key); +extern int __must_check class_register(struct class *class); extern void class_unregister(struct class *class); -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ -}) - struct class_compat; struct class_compat *class_compat_register(const char *name); void class_compat_unregister(struct class_compat *cls); @@ -246,30 +237,7 @@ struct class_interface { extern int __must_check class_interface_register(struct class_interface *); extern void class_interface_unregister(struct class_interface *); -extern struct class * __must_check __class_create(const char *name, - struct lock_class_key *key); +extern struct class * __must_check class_create(const char *name); extern void class_destroy(struct class *cls); -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ - -/** - * class_create - create a struct class structure - * @name: pointer to a string for the name of this class. - * - * This is used to create a struct class pointer that can then be used - * in calls to device_create(). - * - * Returns &struct class pointer on success, or ERR_PTR() on error. - * - * Note, the pointer created here is to be destroyed when finished by - * making a call to class_destroy(). - */ -#define class_create(name) \ -({ \ - static struct lock_class_key __key; \ - __class_create(name, &__key); \ -}) - - #endif /* _DEVICE_CLASS_H_ */ -- GitLab From 43718dca48429b9eb5b82cdd41e2a1f162a02fb9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 11:01:32 +0100 Subject: [PATCH 1249/5631] driver core: class.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/class.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324100132.1633647-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/class.h | 46 ++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 26 deletions(-) diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 03d2f99f84c5..1dc7706cb42d 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -82,8 +82,9 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check class_register(struct class *class); -extern void class_unregister(struct class *class); + +int __must_check class_register(struct class *class); +void class_unregister(struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -93,19 +94,15 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - const struct class *class, - const struct device *start, - const struct device_type *type); -extern struct device *class_dev_iter_next(struct class_dev_iter *iter); -extern void class_dev_iter_exit(struct class_dev_iter *iter); +void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, + const struct device *start, const struct device_type *type); +struct device *class_dev_iter_next(struct class_dev_iter *iter); +void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(const struct class *class, const struct device *start, - void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(const struct class *class, - const struct device *start, const void *data, - int (*match)(struct device *, const void *)); +int class_for_each_device(const struct class *class, const struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *class_find_device(const struct class *class, const struct device *start, + const void *data, int (*match)(struct device *, const void *)); /** * class_find_device_by_name - device iterator for locating a particular device @@ -191,12 +188,10 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(const struct class *class, - const struct class_attribute *attr, - const void *ns); -extern void class_remove_file_ns(const struct class *class, - const struct class_attribute *attr, - const void *ns); +int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); +void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); static inline int __must_check class_create_file(const struct class *class, const struct class_attribute *attr) @@ -223,8 +218,7 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, - char *buf); +ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf); struct class_interface { struct list_head node; @@ -234,10 +228,10 @@ struct class_interface { void (*remove_dev) (struct device *, struct class_interface *); }; -extern int __must_check class_interface_register(struct class_interface *); -extern void class_interface_unregister(struct class_interface *); +int __must_check class_interface_register(struct class_interface *); +void class_interface_unregister(struct class_interface *); -extern struct class * __must_check class_create(const char *name); -extern void class_destroy(struct class *cls); +struct class * __must_check class_create(const char *name); +void class_destroy(struct class *cls); #endif /* _DEVICE_CLASS_H_ */ -- GitLab From f43243c66e5e9ad839d235f82a58e73a7e7612af Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:06 +0100 Subject: [PATCH 1250/5631] driver core: device.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/include/linux/device.h b/include/linux/device.h index 3b23772d3bbb..472dd24d4823 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1088,8 +1088,7 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); -extern __printf(3, 4) -int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- GitLab From 0d62b79fd8083ae2400f31e38f8d63db3bd59bff Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:07 +0100 Subject: [PATCH 1251/5631] driver core: bus.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/bus.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/bus.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index b517b82d4723..65a5e2c0f04d 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -110,11 +110,11 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(const struct bus_type *bus); +int __must_check bus_register(const struct bus_type *bus); -extern void bus_unregister(const struct bus_type *bus); +void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(const struct bus_type *bus); +int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; @@ -244,10 +244,8 @@ void bus_sort_breadthfirst(struct bus_type *bus, */ struct notifier_block; -extern int bus_register_notifier(const struct bus_type *bus, - struct notifier_block *nb); -extern int bus_unregister_notifier(const struct bus_type *bus, - struct notifier_block *nb); +int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb); +int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb); /** * enum bus_notifier_event - Bus Notifier events that have happened @@ -279,7 +277,7 @@ enum bus_notifier_event { BUS_NOTIFY_DRIVER_NOT_BOUND, }; -extern struct kset *bus_get_kset(const struct bus_type *bus); +struct kset *bus_get_kset(const struct bus_type *bus); struct device *bus_get_dev_root(const struct bus_type *bus); #endif -- GitLab From 8a2b9c84c708cf2a99499d5a685a642af7b68c37 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:08 +0100 Subject: [PATCH 1252/5631] driver core: driver.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/device/driver.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/device/driver.h | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 0f22a6f46f8c..c244267a6744 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -122,13 +122,12 @@ struct device_driver { }; -extern int __must_check driver_register(struct device_driver *drv); -extern void driver_unregister(struct device_driver *drv); +int __must_check driver_register(struct device_driver *drv); +void driver_unregister(struct device_driver *drv); -extern struct device_driver *driver_find(const char *name, - const struct bus_type *bus); -extern int driver_probe_done(void); -extern void wait_for_device_probe(void); +struct device_driver *driver_find(const char *name, const struct bus_type *bus); +int driver_probe_done(void); +void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); /* sysfs interface for exporting driver attributes */ @@ -147,18 +146,15 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -extern int __must_check driver_create_file(struct device_driver *driver, - const struct driver_attribute *attr); -extern void driver_remove_file(struct device_driver *driver, - const struct driver_attribute *attr); +int __must_check driver_create_file(struct device_driver *driver, + const struct driver_attribute *attr); +void driver_remove_file(struct device_driver *driver, + const struct driver_attribute *attr); int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); -extern int __must_check driver_for_each_device(struct device_driver *drv, - struct device *start, - void *data, - int (*fn)(struct device *dev, - void *)); +int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, + void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); -- GitLab From 8da5b970aaec41ed11c3165f5c25878cd9849517 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:09 +0100 Subject: [PATCH 1253/5631] driver core: base.h: remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from drivers/base/base.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 88 ++++++++++++++++++++++----------------------- 1 file changed, 42 insertions(+), 46 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index 09c6682d16b5..a2d3a1d0fa9b 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -124,42 +124,40 @@ struct device_private { container_of(obj, struct device_private, knode_class) /* initialisation functions */ -extern int devices_init(void); -extern int buses_init(void); -extern int classes_init(void); -extern int firmware_init(void); +int devices_init(void); +int buses_init(void); +int classes_init(void); +int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR -extern int hypervisor_init(void); +int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif -extern int platform_bus_init(void); -extern void cpu_dev_init(void); -extern void container_dev_init(void); +int platform_bus_init(void); +void cpu_dev_init(void); +void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS -extern void auxiliary_bus_init(void); +void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(struct device *dev); -extern int bus_add_device(struct device *dev); -extern void bus_probe_device(struct device *dev); -extern void bus_remove_device(struct device *dev); +int bus_add_device(struct device *dev); +void bus_probe_device(struct device *dev); +void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); -extern int bus_add_driver(struct device_driver *drv); -extern void bus_remove_driver(struct device_driver *drv); -extern void device_release_driver_internal(struct device *dev, - struct device_driver *drv, - struct device *parent); +int bus_add_driver(struct device_driver *drv); +void bus_remove_driver(struct device_driver *drv); +void device_release_driver_internal(struct device *dev, struct device_driver *drv, + struct device *parent); -extern void driver_detach(struct device_driver *drv); -extern void driver_deferred_probe_del(struct device *dev); -extern void device_set_deferred_probe_reason(const struct device *dev, - struct va_format *vaf); +void driver_detach(struct device_driver *drv); +void driver_deferred_probe_del(struct device *dev); +void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(struct device_driver *drv, struct device *dev) { @@ -174,27 +172,25 @@ static inline void dev_sync_state(struct device *dev) dev->driver->sync_state(dev); } -extern int driver_add_groups(struct device_driver *drv, - const struct attribute_group **groups); -extern void driver_remove_groups(struct device_driver *drv, - const struct attribute_group **groups); +int driver_add_groups(struct device_driver *drv, const struct attribute_group **groups); +void driver_remove_groups(struct device_driver *drv, const struct attribute_group **groups); void device_driver_detach(struct device *dev); -extern int devres_release_all(struct device *dev); -extern void device_block_probing(void); -extern void device_unblock_probing(void); -extern void deferred_probe_extend_timeout(void); -extern void driver_deferred_probe_trigger(void); +int devres_release_all(struct device *dev); +void device_block_probing(void); +void device_unblock_probing(void); +void deferred_probe_extend_timeout(void); +void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; -extern void devices_kset_move_last(struct device *dev); +void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) -extern void module_add_driver(struct module *mod, struct device_driver *drv); -extern void module_remove_driver(struct device_driver *drv); +void module_add_driver(struct module *mod, struct device_driver *drv); +void module_remove_driver(struct device_driver *drv); #else static inline void module_add_driver(struct module *mod, struct device_driver *drv) { } @@ -202,24 +198,24 @@ static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS -extern int devtmpfs_init(void); +int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif /* Device links support */ -extern int device_links_read_lock(void); -extern void device_links_read_unlock(int idx); -extern int device_links_read_lock_held(void); -extern int device_links_check_suppliers(struct device *dev); -extern void device_links_force_bind(struct device *dev); -extern void device_links_driver_bound(struct device *dev); -extern void device_links_driver_cleanup(struct device *dev); -extern void device_links_no_driver(struct device *dev); -extern bool device_links_busy(struct device *dev); -extern void device_links_unbind_consumers(struct device *dev); -extern void fw_devlink_drivers_done(void); -extern void fw_devlink_probing_done(void); +int device_links_read_lock(void); +void device_links_read_unlock(int idx); +int device_links_read_lock_held(void); +int device_links_check_suppliers(struct device *dev); +void device_links_force_bind(struct device *dev); +void device_links_driver_bound(struct device *dev); +void device_links_driver_cleanup(struct device *dev); +void device_links_no_driver(struct device *dev); +bool device_links_busy(struct device *dev); +void device_links_unbind_consumers(struct device *dev); +void fw_devlink_drivers_done(void); +void fw_devlink_probing_done(void); /* device pm support */ void device_pm_move_to_tail(struct device *dev); -- GitLab From 3e44d5c9e987c32e5bdc9de2c166f622cc81e15d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:10 +0100 Subject: [PATCH 1254/5631] driver core: physical_location.h remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from drivers/base/physical_location.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/physical_location.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/physical_location.h b/drivers/base/physical_location.h index 82cde9f1b161..3f3f61307998 100644 --- a/drivers/base/physical_location.h +++ b/drivers/base/physical_location.h @@ -8,7 +8,7 @@ #include #ifdef CONFIG_ACPI -extern bool dev_add_physical_location(struct device *dev); +bool dev_add_physical_location(struct device *dev); extern const struct attribute_group dev_attr_physical_location_group; #else static inline bool dev_add_physical_location(struct device *dev) { return false; }; -- GitLab From 44650f33d3bd76dd968cb8880c8eedd465030cd5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 13:27:11 +0100 Subject: [PATCH 1255/5631] kobject.h remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from include/linux/kobject.h as they are not needed. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230324122711.2664537-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 59 ++++++++++++++++++----------------------- 1 file changed, 26 insertions(+), 33 deletions(-) diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bdab370a24f4..c392c811d9ad 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,43 +79,37 @@ struct kobject { unsigned int uevent_suppress:1; }; -extern __printf(2, 3) -int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern __printf(2, 0) -int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +__printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); +__printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } -extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); -extern __printf(3, 4) __must_check -int kobject_add(struct kobject *kobj, struct kobject *parent, - const char *fmt, ...); -extern __printf(4, 5) __must_check -int kobject_init_and_add(struct kobject *kobj, - const struct kobj_type *ktype, struct kobject *parent, - const char *fmt, ...); +void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); +__printf(3, 4) __must_check int kobject_add(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); +__printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, + const struct kobj_type *ktype, + struct kobject *parent, + const char *fmt, ...); -extern void kobject_del(struct kobject *kobj); +void kobject_del(struct kobject *kobj); -extern struct kobject * __must_check kobject_create_and_add(const char *name, - struct kobject *parent); +struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); -extern int __must_check kobject_rename(struct kobject *, const char *new_name); -extern int __must_check kobject_move(struct kobject *, struct kobject *); +int __must_check kobject_rename(struct kobject *, const char *new_name); +int __must_check kobject_move(struct kobject *, struct kobject *); -extern struct kobject *kobject_get(struct kobject *kobj); -extern struct kobject * __must_check kobject_get_unless_zero( - struct kobject *kobj); -extern void kobject_put(struct kobject *kobj); +struct kobject *kobject_get(struct kobject *kobj); +struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); +void kobject_put(struct kobject *kobj); -extern const void *kobject_namespace(const struct kobject *kobj); -extern void kobject_get_ownership(const struct kobject *kobj, - kuid_t *uid, kgid_t *gid); -extern char *kobject_get_path(const struct kobject *kobj, gfp_t flag); +const void *kobject_namespace(const struct kobject *kobj); +void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); +char *kobject_get_path(const struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); @@ -176,12 +170,11 @@ struct kset { const struct kset_uevent_ops *uevent_ops; } __randomize_layout; -extern void kset_init(struct kset *kset); -extern int __must_check kset_register(struct kset *kset); -extern void kset_unregister(struct kset *kset); -extern struct kset * __must_check kset_create_and_add(const char *name, - const struct kset_uevent_ops *u, - struct kobject *parent_kobj); +void kset_init(struct kset *kset); +int __must_check kset_register(struct kset *kset); +void kset_unregister(struct kset *kset); +struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, + struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { @@ -203,7 +196,7 @@ static inline const struct kobj_type *get_ktype(const struct kobject *kobj) return kobj->ktype; } -extern struct kobject *kset_find_obj(struct kset *, const char *); +struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; -- GitLab From b0d237087c674c43df76c1a0bc2737592f3038f4 Mon Sep 17 00:00:00 2001 From: Jun Miao Date: Thu, 23 Feb 2023 13:28:51 +0800 Subject: [PATCH 1256/5631] KVM: Fix comments that refer to the non-existent install_new_memslots() Fix stale comments that were left behind when install_new_memslots() was replaced by kvm_swap_active_memslots() as part of the scalable memslots rework. Fixes: a54d806688fe ("KVM: Keep memslots in tree-based structures instead of array-based ones") Signed-off-by: Jun Miao Link: https://lore.kernel.org/r/20230223052851.1054799-1-jun.miao@intel.com Signed-off-by: Sean Christopherson --- Documentation/virt/kvm/locking.rst | 2 +- include/linux/kvm_host.h | 4 ++-- virt/kvm/kvm_main.c | 14 +++++++------- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 14c4e9fa501d..8c77554e4896 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -21,7 +21,7 @@ The acquisition orders for mutexes are as follows: - kvm->mn_active_invalidate_count ensures that pairs of invalidate_range_start() and invalidate_range_end() callbacks use the same memslots array. kvm->slots_lock and kvm->slots_arch_lock - are taken on the waiting side in install_new_memslots, so MMU notifiers + are taken on the waiting side when modifying memslots, so MMU notifiers must not take either kvm->slots_lock or kvm->slots_arch_lock. For SRCU: diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 90edc16d37e5..9696c2fb30e9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -58,7 +58,7 @@ /* * Bit 63 of the memslot generation number is an "update in-progress flag", - * e.g. is temporarily set for the duration of install_new_memslots(). + * e.g. is temporarily set for the duration of kvm_swap_active_memslots(). * This flag effectively creates a unique generation number that is used to * mark cached memslot data, e.g. MMIO accesses, as potentially being stale, * i.e. may (or may not) have come from the previous memslots generation. @@ -713,7 +713,7 @@ struct kvm { * use by the VM. To be used under the slots_lock (above) or in a * kvm->srcu critical section where acquiring the slots_lock would * lead to deadlock with the synchronize_srcu in - * install_new_memslots. + * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8f0a7da37e32..d1abb331ea68 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1298,7 +1298,7 @@ static void kvm_destroy_vm(struct kvm *kvm) * At this point, pending calls to invalidate_range_start() * have completed but no more MMU notifiers will run, so * mn_active_invalidate_count may remain unbalanced. - * No threads can be waiting in install_new_memslots as the + * No threads can be waiting in kvm_swap_active_memslots() as the * last reference on KVM has been dropped, but freeing * memslots would deadlock without this manual intervention. */ @@ -1742,13 +1742,13 @@ static void kvm_invalidate_memslot(struct kvm *kvm, kvm_arch_flush_shadow_memslot(kvm, old); kvm_arch_guest_memory_reclaimed(kvm); - /* Was released by kvm_swap_active_memslots, reacquire. */ + /* Was released by kvm_swap_active_memslots(), reacquire. */ mutex_lock(&kvm->slots_arch_lock); /* * Copy the arch-specific field of the newly-installed slot back to the * old slot as the arch data could have changed between releasing - * slots_arch_lock in install_new_memslots() and re-acquiring the lock + * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock * above. Writers are required to retrieve memslots *after* acquiring * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. */ @@ -1810,11 +1810,11 @@ static int kvm_set_memslot(struct kvm *kvm, int r; /* - * Released in kvm_swap_active_memslots. + * Released in kvm_swap_active_memslots(). * - * Must be held from before the current memslots are copied until - * after the new memslots are installed with rcu_assign_pointer, - * then released before the synchronize srcu in kvm_swap_active_memslots. + * Must be held from before the current memslots are copied until after + * the new memslots are installed with rcu_assign_pointer, then + * released before the synchronize srcu in kvm_swap_active_memslots(). * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all -- GitLab From f6baabdcadd1080893aa5e49e6959cb070244703 Mon Sep 17 00:00:00 2001 From: Anish Moorthy Date: Thu, 23 Feb 2023 00:18:05 +0000 Subject: [PATCH 1257/5631] KVM: selftests: Fix nsec to sec conversion in demand_paging_test demand_paging_test uses 1E8 as the denominator to convert nanoseconds to seconds, which is wrong. Use NSEC_PER_SEC instead to fix the issue and make the conversion obvious. Reported-by: James Houghton Signed-off-by: Anish Moorthy Reviewed-by: Oliver Upton Reviewed-by: Sean Christopherson Link: https://lore.kernel.org/r/20230223001805.2971237-1-amoorthy@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/demand_paging_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index b0e1fc4de9e2..2439c4043fed 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -194,7 +194,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", memstress_args.vcpu_args[0].pages * nr_vcpus / - ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC)); memstress_destroy_vm(vm); -- GitLab From d14d9139c023042e63dc869a9a1be4e4eb317396 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Tue, 14 Feb 2023 16:49:19 +0800 Subject: [PATCH 1258/5631] KVM: selftests: Add a helper to read kvm boolean module parameters Add a helper function for reading kvm boolean module parameters values. No functional change intended. Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230214084920.59787-2-likexu@tencent.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/include/kvm_util_base.h | 1 + tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index fbc2a79369b8..a089c356f354 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -213,6 +213,7 @@ extern const struct vm_guest_mode_params vm_guest_mode_params[]; int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); +bool get_kvm_param_bool(const char *param); bool get_kvm_intel_param_bool(const char *param); bool get_kvm_amd_param_bool(const char *param); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8ec20ac33de0..298c4372fb1a 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -80,6 +80,11 @@ static bool get_module_param_bool(const char *module_name, const char *param) TEST_FAIL("Unrecognized value '%c' for boolean module param", value); } +bool get_kvm_param_bool(const char *param) +{ + return get_module_param_bool("kvm", param); +} + bool get_kvm_intel_param_bool(const char *param) { return get_module_param_bool("kvm_intel", param); -- GitLab From 9f33a88c0a820681a4cbabfc912ac5569a9de330 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 24 Mar 2023 15:40:41 +0000 Subject: [PATCH 1259/5631] kernel/ksysfs.c: use sysfs_emit for sysfs show handlers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit sysfs_emit() is the recommended way to format strings for sysfs as per Documentation/filesystems/sysfs.rst. Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20230324-ksysfs-sysfs_emit-v1-1-67c03cddc8a6@weissschuh.net Signed-off-by: Greg Kroah-Hartman --- kernel/ksysfs.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 0408aab80941..aad7a3bfd846 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -39,7 +39,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static ssize_t uevent_seqnum_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum); + return sysfs_emit(buf, "%llu\n", (unsigned long long)uevent_seqnum); } KERNEL_ATTR_RO(uevent_seqnum); @@ -64,7 +64,7 @@ KERNEL_ATTR_RO(address_bits); static ssize_t uevent_helper_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%s\n", uevent_helper); + return sysfs_emit(buf, "%s\n", uevent_helper); } static ssize_t uevent_helper_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -85,7 +85,7 @@ KERNEL_ATTR_RW(uevent_helper); static ssize_t profiling_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", prof_on); + return sysfs_emit(buf, "%d\n", prof_on); } static ssize_t profiling_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -116,14 +116,14 @@ KERNEL_ATTR_RW(profiling); static ssize_t kexec_loaded_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", !!kexec_image); + return sysfs_emit(buf, "%d\n", !!kexec_image); } KERNEL_ATTR_RO(kexec_loaded); static ssize_t kexec_crash_loaded_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", kexec_crash_loaded()); + return sysfs_emit(buf, "%d\n", kexec_crash_loaded()); } KERNEL_ATTR_RO(kexec_crash_loaded); @@ -135,7 +135,7 @@ static ssize_t kexec_crash_size_show(struct kobject *kobj, if (size < 0) return size; - return sprintf(buf, "%zd\n", size); + return sysfs_emit(buf, "%zd\n", size); } static ssize_t kexec_crash_size_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -160,8 +160,8 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { phys_addr_t vmcore_base = paddr_vmcoreinfo_note(); - return sprintf(buf, "%pa %x\n", &vmcore_base, - (unsigned int)VMCOREINFO_NOTE_SIZE); + return sysfs_emit(buf, "%pa %x\n", &vmcore_base, + (unsigned int)VMCOREINFO_NOTE_SIZE); } KERNEL_ATTR_RO(vmcoreinfo); @@ -171,7 +171,7 @@ KERNEL_ATTR_RO(vmcoreinfo); static ssize_t fscaps_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", file_caps_enabled); + return sysfs_emit(buf, "%d\n", file_caps_enabled); } KERNEL_ATTR_RO(fscaps); @@ -180,7 +180,7 @@ int rcu_expedited; static ssize_t rcu_expedited_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited)); + return sysfs_emit(buf, "%d\n", READ_ONCE(rcu_expedited)); } static ssize_t rcu_expedited_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -197,7 +197,7 @@ int rcu_normal; static ssize_t rcu_normal_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", READ_ONCE(rcu_normal)); + return sysfs_emit(buf, "%d\n", READ_ONCE(rcu_normal)); } static ssize_t rcu_normal_store(struct kobject *kobj, struct kobj_attribute *attr, -- GitLab From b66973b82d4426b318f78a20c6b39ddd977a508a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:35 -0700 Subject: [PATCH 1260/5631] module: move get_modinfo() helpers all above Instead of forward declaring routines for get_modinfo() just move everything up. This makes no functional changes. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 100 +++++++++++++++++++++---------------------- 1 file changed, 48 insertions(+), 52 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index b4759f1695b7..1e739f534100 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1016,9 +1016,55 @@ int try_to_force_load(struct module *mod, const char *reason) #endif } -static char *get_modinfo(const struct load_info *info, const char *tag); +/* Parse tag=value strings from .modinfo section */ +static char *next_string(char *string, unsigned long *secsize) +{ + /* Skip non-zero chars */ + while (string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + + /* Skip any zero padding. */ + while (!string[0]) { + string++; + if ((*secsize)-- <= 1) + return NULL; + } + return string; +} + static char *get_next_modinfo(const struct load_info *info, const char *tag, - char *prev); + char *prev) +{ + char *p; + unsigned int taglen = strlen(tag); + Elf_Shdr *infosec = &info->sechdrs[info->index.info]; + unsigned long size = infosec->sh_size; + + /* + * get_modinfo() calls made before rewrite_section_headers() + * must use sh_offset, as sh_addr isn't set! + */ + char *modinfo = (char *)info->hdr + infosec->sh_offset; + + if (prev) { + size -= prev - modinfo; + modinfo = next_string(prev, &size); + } + + for (p = modinfo; p; p = next_string(p, &size)) { + if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') + return p + taglen + 1; + } + return NULL; +} + +static char *get_modinfo(const struct load_info *info, const char *tag) +{ + return get_next_modinfo(info, tag, NULL); +} static int verify_namespace_is_imported(const struct load_info *info, const struct kernel_symbol *sym, @@ -1544,56 +1590,6 @@ static void set_license(struct module *mod, const char *license) } } -/* Parse tag=value strings from .modinfo section */ -static char *next_string(char *string, unsigned long *secsize) -{ - /* Skip non-zero chars */ - while (string[0]) { - string++; - if ((*secsize)-- <= 1) - return NULL; - } - - /* Skip any zero padding. */ - while (!string[0]) { - string++; - if ((*secsize)-- <= 1) - return NULL; - } - return string; -} - -static char *get_next_modinfo(const struct load_info *info, const char *tag, - char *prev) -{ - char *p; - unsigned int taglen = strlen(tag); - Elf_Shdr *infosec = &info->sechdrs[info->index.info]; - unsigned long size = infosec->sh_size; - - /* - * get_modinfo() calls made before rewrite_section_headers() - * must use sh_offset, as sh_addr isn't set! - */ - char *modinfo = (char *)info->hdr + infosec->sh_offset; - - if (prev) { - size -= prev - modinfo; - modinfo = next_string(prev, &size); - } - - for (p = modinfo; p; p = next_string(p, &size)) { - if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') - return p + taglen + 1; - } - return NULL; -} - -static char *get_modinfo(const struct load_info *info, const char *tag) -{ - return get_next_modinfo(info, tag, NULL); -} - static void setup_modinfo(struct module *mod, struct load_info *info) { struct module_attribute *attr; -- GitLab From feb5b784a26363b690f618213450faf244c1c58e Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:36 -0700 Subject: [PATCH 1261/5631] module: rename next_string() to module_next_tag_pair() This makes it clearer what it is doing. While at it, make it available to other code other than main.c. This will be used in the subsequent patch and make the changes easier to read. Signed-off-by: Luis Chamberlain --- kernel/module/internal.h | 2 ++ kernel/module/main.c | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/kernel/module/internal.h b/kernel/module/internal.h index e3883b7d4840..1fa2328636ec 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -96,6 +96,8 @@ long module_get_offset_and_type(struct module *mod, enum mod_mem_type type, char *module_flags(struct module *mod, char *buf, bool show_state); size_t module_flags_taint(unsigned long taints, char *buf); +char *module_next_tag_pair(char *string, unsigned long *secsize); + static inline void module_assert_mutex_or_preempt(void) { #ifdef CONFIG_LOCKDEP diff --git a/kernel/module/main.c b/kernel/module/main.c index 1e739f534100..ebb5e6b92a48 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1017,7 +1017,7 @@ int try_to_force_load(struct module *mod, const char *reason) } /* Parse tag=value strings from .modinfo section */ -static char *next_string(char *string, unsigned long *secsize) +char *module_next_tag_pair(char *string, unsigned long *secsize) { /* Skip non-zero chars */ while (string[0]) { @@ -1051,10 +1051,10 @@ static char *get_next_modinfo(const struct load_info *info, const char *tag, if (prev) { size -= prev - modinfo; - modinfo = next_string(prev, &size); + modinfo = module_next_tag_pair(prev, &size); } - for (p = modinfo; p; p = next_string(p, &size)) { + for (p = modinfo; p; p = module_next_tag_pair(p, &size)) { if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') return p + taglen + 1; } -- GitLab From 1e684172358453df1cb783d7c101a09ff08ceee1 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:37 -0700 Subject: [PATCH 1262/5631] module: add a for_each_modinfo_entry() Add a for_each_modinfo_entry() to make it easier to read and use. This produces no functional changes but makes this code easiert to read as we are used to with loops in the kernel and trims more lines of code. Signed-off-by: Luis Chamberlain --- kernel/module/internal.h | 3 +++ kernel/module/main.c | 5 +---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/module/internal.h b/kernel/module/internal.h index 1fa2328636ec..6ae29bb8836f 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -98,6 +98,9 @@ size_t module_flags_taint(unsigned long taints, char *buf); char *module_next_tag_pair(char *string, unsigned long *secsize); +#define for_each_modinfo_entry(entry, info, name) \ + for (entry = get_modinfo(info, name); entry; entry = get_next_modinfo(info, name, entry)) + static inline void module_assert_mutex_or_preempt(void) { #ifdef CONFIG_LOCKDEP diff --git a/kernel/module/main.c b/kernel/module/main.c index ebb5e6b92a48..427284ab31f1 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1075,12 +1075,9 @@ static int verify_namespace_is_imported(const struct load_info *info, namespace = kernel_symbol_namespace(sym); if (namespace && namespace[0]) { - imported_namespace = get_modinfo(info, "import_ns"); - while (imported_namespace) { + for_each_modinfo_entry(imported_namespace, info, "import_ns") { if (strcmp(namespace, imported_namespace) == 0) return 0; - imported_namespace = get_next_modinfo( - info, "import_ns", imported_namespace); } #ifdef CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS pr_warn( -- GitLab From 85e6f61c134f111232d27d3f63667c1bccbbc12d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:38 -0700 Subject: [PATCH 1263/5631] module: move early sanity checks into a helper Move early sanity checkers for the module into a helper. This let's us make it clear when we are working with the local copy of the module prior to allocation. This produces no functional changes, it just makes subsequent changes easier to read. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 43 ++++++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 427284ab31f1..22596cb46dc8 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2668,6 +2668,31 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname, return 0; } +/* Module within temporary copy, this doesn't do any allocation */ +static int early_mod_check(struct load_info *info, int flags) +{ + int err; + + /* + * Now that we know we have the correct module name, check + * if it's blacklisted. + */ + if (blacklisted(info->name)) { + pr_err("Module %s is blacklisted\n", info->name); + return -EPERM; + } + + err = rewrite_section_headers(info, flags); + if (err) + return err; + + /* Check module struct version now, before we try to use module. */ + if (!check_modstruct_version(info, info->mod)) + return -ENOEXEC; + + return 0; +} + /* * Allocate and load the module: note that size of section 0 is always * zero, and we rely on this for optional sections. @@ -2711,26 +2736,10 @@ static int load_module(struct load_info *info, const char __user *uargs, if (err) goto free_copy; - /* - * Now that we know we have the correct module name, check - * if it's blacklisted. - */ - if (blacklisted(info->name)) { - err = -EPERM; - pr_err("Module %s is blacklisted\n", info->name); - goto free_copy; - } - - err = rewrite_section_headers(info, flags); + err = early_mod_check(info, flags); if (err) goto free_copy; - /* Check module struct version now, before we try to use module. */ - if (!check_modstruct_version(info, info->mod)) { - err = -ENOEXEC; - goto free_copy; - } - /* Figure out module layout, and allocate all the memory. */ mod = layout_and_allocate(info, flags); if (IS_ERR(mod)) { -- GitLab From 02da2cbab452a236fa67abc9fc9e47430934e652 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:39 -0700 Subject: [PATCH 1264/5631] module: move check_modinfo() early to early_mod_check() This moves check_modinfo() to early_mod_check(). This doesn't make any functional changes either, as check_modinfo() was the first call on layout_and_allocate(), so we're just moving it back one routine and at the end. This let's us keep separate the checkers from the allocator. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 22596cb46dc8..95fd705328ac 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2273,10 +2273,6 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) unsigned int ndx; int err; - err = check_modinfo(info->mod, info, flags); - if (err) - return ERR_PTR(err); - /* Allow arches to frob section contents and sizes. */ err = module_frob_arch_sections(info->hdr, info->sechdrs, info->secstrings, info->mod); @@ -2690,6 +2686,10 @@ static int early_mod_check(struct load_info *info, int flags) if (!check_modstruct_version(info, info->mod)) return -ENOEXEC; + err = check_modinfo(info->mod, info, flags); + if (err) + return err; + return 0; } -- GitLab From ad8d3a36e981064f8a646531cddca30516894457 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:40 -0700 Subject: [PATCH 1265/5631] module: rename set_license() to module_license_taint_check() The set_license() routine would seem to a reader to do some sort of setting, but it does not. It just adds a taint if the license is not set or proprietary. This makes what the code is doing clearer, so much we can remove the comment about it. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 95fd705328ac..5e64485ac05a 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1573,7 +1573,7 @@ static void layout_sections(struct module *mod, struct load_info *info) __layout_sections(mod, info, true); } -static void set_license(struct module *mod, const char *license) +static void module_license_taint_check(struct module *mod, const char *license) { if (!license) license = "unspecified"; @@ -1993,8 +1993,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) if (err) return err; - /* Set up license info based on the info section */ - set_license(mod, get_modinfo(info, "license")); + module_license_taint_check(mod, get_modinfo(info, "license")); if (get_modinfo(info, "test")) { if (!test_taint(TAINT_TEST)) -- GitLab From ed52cabecb7a7e4242cee9c370c2622a47177d5d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:41 -0700 Subject: [PATCH 1266/5631] module: split taint work out of check_modinfo_livepatch() The work to taint the kernel due to a module should be split up eventually. To aid with this, split up the tainting on check_modinfo_livepatch(). This let's us bring more early checks together which do return a value, and makes changes easier to read later where we stuff all the work to do the taints in one single routine. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 5e64485ac05a..cfb2ff5185fe 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1808,12 +1808,8 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info) /* Nothing more to do */ return 0; - if (set_livepatch_module(mod)) { - add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK); - pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n", - mod->name); + if (set_livepatch_module(mod)) return 0; - } pr_err("%s: module is marked as livepatch module, but livepatch support is disabled", mod->name); @@ -1993,6 +1989,11 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) if (err) return err; + if (is_livepatch_module(mod)) { + add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK); + pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n", + mod->name); + } module_license_taint_check(mod, get_modinfo(info, "license")); if (get_modinfo(info, "test")) { -- GitLab From 437c1f9cc61fd37829eaf12d8ae2f7dcc5dddce0 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:42 -0700 Subject: [PATCH 1267/5631] module: split taint adding with info checking check_modinfo() actually does two things: a) sanity checks, some of which are fatal, and so we prevent the user from completing trying to load a module b) taints the kernel The taints are pretty heavy handed because we're tainting the kernel *before* we ever even get to load the module into the modules linked list. That is, it it can fail for other reasons later as we review the module's structure. But this commit makes no functional changes, it just makes the intent clearer and splits the code up where needed to make that happen. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 62 ++++++++++++++++++++++++++++---------------- 1 file changed, 40 insertions(+), 22 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index cfb2ff5185fe..a3953ca18090 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1951,25 +1951,10 @@ static int setup_load_info(struct load_info *info, int flags) return 0; } -static int check_modinfo(struct module *mod, struct load_info *info, int flags) +/* + * These calls taint the kernel depending certain module circumstances */ +static void module_augment_kernel_taints(struct module *mod, struct load_info *info) { - const char *modmagic = get_modinfo(info, "vermagic"); - int err; - - if (flags & MODULE_INIT_IGNORE_VERMAGIC) - modmagic = NULL; - - /* This is allowed: modprobe --force will invalidate it. */ - if (!modmagic) { - err = try_to_force_load(mod, "bad vermagic"); - if (err) - return err; - } else if (!same_magic(modmagic, vermagic, info->index.vers)) { - pr_err("%s: version magic '%s' should be '%s'\n", - info->name, modmagic, vermagic); - return -ENOEXEC; - } - if (!get_modinfo(info, "intree")) { if (!test_taint(TAINT_OOT_MODULE)) pr_warn("%s: loading out-of-tree module taints kernel.\n", @@ -1985,15 +1970,12 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) "is unknown, you have been warned.\n", mod->name); } - err = check_modinfo_livepatch(mod, info); - if (err) - return err; - if (is_livepatch_module(mod)) { add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK); pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n", mod->name); } + module_license_taint_check(mod, get_modinfo(info, "license")); if (get_modinfo(info, "test")) { @@ -2002,6 +1984,42 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) mod->name); add_taint_module(mod, TAINT_TEST, LOCKDEP_STILL_OK); } +} + +static int check_modinfo(struct module *mod, struct load_info *info, int flags) +{ + const char *modmagic = get_modinfo(info, "vermagic"); + int err; + + if (flags & MODULE_INIT_IGNORE_VERMAGIC) + modmagic = NULL; + + /* This is allowed: modprobe --force will invalidate it. */ + if (!modmagic) { + err = try_to_force_load(mod, "bad vermagic"); + if (err) + return err; + } else if (!same_magic(modmagic, vermagic, info->index.vers)) { + pr_err("%s: version magic '%s' should be '%s'\n", + info->name, modmagic, vermagic); + return -ENOEXEC; + } + + err = check_modinfo_livepatch(mod, info); + if (err) + return err; + + /* + * We are tainting your kernel *even* if you try to load + * modules with possible taints and we fail to load these + * modules for other reasons. + * + * We have a descrepancy though, see the other taints for + * signature and those in check_module_license_and_versions(). + * + * We should compromise and converge. + */ + module_augment_kernel_taints(mod, info); return 0; } -- GitLab From a12b94511cf36855cd731c16005bd535e2007552 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:43 -0700 Subject: [PATCH 1268/5631] module: move tainting until after a module hits our linked list It is silly to have taints spread out all over, we can just compromise and add them if the module ever hit our linked list. Our sanity checkers should just prevent crappy drivers / bogus ELF modules / etc and kconfig options should be enough to let you *not* load things you don't want. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index a3953ca18090..1aa71f82aca2 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2009,18 +2009,6 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) if (err) return err; - /* - * We are tainting your kernel *even* if you try to load - * modules with possible taints and we fail to load these - * modules for other reasons. - * - * We have a descrepancy though, see the other taints for - * signature and those in check_module_license_and_versions(). - * - * We should compromise and converge. - */ - module_augment_kernel_taints(mod, info); - return 0; } @@ -2772,6 +2760,16 @@ static int load_module(struct load_info *info, const char __user *uargs, if (err) goto free_module; + /* + * We are tainting your kernel if your module gets into + * the modules linked list somehow. + * + * We have a descrepancy though, see the other taints for + * signature and those in check_module_license_and_versions(). + * + * We should compromise and converge. + */ + module_augment_kernel_taints(mod, info); #ifdef CONFIG_MODULE_SIG mod->sig_ok = info->sig_ok; if (!mod->sig_ok) { -- GitLab From c3bbf62ebf8c9e87cea875cfa146f44f46af4145 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:44 -0700 Subject: [PATCH 1269/5631] module: move signature taint to module_augment_kernel_taints() Just move the signature taint into the helper: module_augment_kernel_taints() Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 1aa71f82aca2..2f1988137965 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1984,6 +1984,15 @@ static void module_augment_kernel_taints(struct module *mod, struct load_info *i mod->name); add_taint_module(mod, TAINT_TEST, LOCKDEP_STILL_OK); } +#ifdef CONFIG_MODULE_SIG + mod->sig_ok = info->sig_ok; + if (!mod->sig_ok) { + pr_notice_once("%s: module verification failed: signature " + "and/or required key missing - tainting " + "kernel\n", mod->name); + add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); + } +#endif } static int check_modinfo(struct module *mod, struct load_info *info, int flags) @@ -2770,15 +2779,6 @@ static int load_module(struct load_info *info, const char __user *uargs, * We should compromise and converge. */ module_augment_kernel_taints(mod, info); -#ifdef CONFIG_MODULE_SIG - mod->sig_ok = info->sig_ok; - if (!mod->sig_ok) { - pr_notice_once("%s: module verification failed: signature " - "and/or required key missing - tainting " - "kernel\n", mod->name); - add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); - } -#endif /* To avoid stressing percpu allocator, do this once we're unique. */ err = percpu_modalloc(mod, info); -- GitLab From 72f08b3cc631f4ebcaa9f373d18fc0b877fb6458 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:45 -0700 Subject: [PATCH 1270/5631] module: converge taint work together Converge on a compromise: so long as we have a module hit our linked list of modules we taint. That is, the module was about to become live. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 52 ++++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 28 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 2f1988137965..f165d93a4ef9 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1955,6 +1955,8 @@ static int setup_load_info(struct load_info *info, int flags) * These calls taint the kernel depending certain module circumstances */ static void module_augment_kernel_taints(struct module *mod, struct load_info *info) { + int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE); + if (!get_modinfo(info, "intree")) { if (!test_taint(TAINT_OOT_MODULE)) pr_warn("%s: loading out-of-tree module taints kernel.\n", @@ -1993,6 +1995,28 @@ static void module_augment_kernel_taints(struct module *mod, struct load_info *i add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK); } #endif + + /* + * ndiswrapper is under GPL by itself, but loads proprietary modules. + * Don't use add_taint_module(), as it would prevent ndiswrapper from + * using GPL-only symbols it needs. + */ + if (strcmp(mod->name, "ndiswrapper") == 0) + add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); + + /* driverloader was caught wrongly pretending to be under GPL */ + if (strcmp(mod->name, "driverloader") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + + /* lve claims to be GPL but upstream won't provide source */ + if (strcmp(mod->name, "lve") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE, + LOCKDEP_NOW_UNRELIABLE); + + if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE)) + pr_warn("%s: module license taints kernel.\n", mod->name); + } static int check_modinfo(struct module *mod, struct load_info *info, int flags) @@ -2198,29 +2222,6 @@ static int move_module(struct module *mod, struct load_info *info) static int check_module_license_and_versions(struct module *mod) { - int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE); - - /* - * ndiswrapper is under GPL by itself, but loads proprietary modules. - * Don't use add_taint_module(), as it would prevent ndiswrapper from - * using GPL-only symbols it needs. - */ - if (strcmp(mod->name, "ndiswrapper") == 0) - add_taint(TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); - - /* driverloader was caught wrongly pretending to be under GPL */ - if (strcmp(mod->name, "driverloader") == 0) - add_taint_module(mod, TAINT_PROPRIETARY_MODULE, - LOCKDEP_NOW_UNRELIABLE); - - /* lve claims to be GPL but upstream won't provide source */ - if (strcmp(mod->name, "lve") == 0) - add_taint_module(mod, TAINT_PROPRIETARY_MODULE, - LOCKDEP_NOW_UNRELIABLE); - - if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE)) - pr_warn("%s: module license taints kernel.\n", mod->name); - #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs)) { @@ -2772,11 +2773,6 @@ static int load_module(struct load_info *info, const char __user *uargs, /* * We are tainting your kernel if your module gets into * the modules linked list somehow. - * - * We have a descrepancy though, see the other taints for - * signature and those in check_module_license_and_versions(). - * - * We should compromise and converge. */ module_augment_kernel_taints(mod, info); -- GitLab From 419e1a20f7bdef5380fde5ed73f05c98c28a598b Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:27:46 -0700 Subject: [PATCH 1271/5631] module: rename check_module_license_and_versions() to check_export_symbol_versions() This makes the routine easier to understand what the check its checking for. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index f165d93a4ef9..cf097ffe6a4a 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2220,7 +2220,7 @@ static int move_module(struct module *mod, struct load_info *info) return -ENOMEM; } -static int check_module_license_and_versions(struct module *mod) +static int check_export_symbol_versions(struct module *mod) { #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || @@ -2796,7 +2796,7 @@ static int load_module(struct load_info *info, const char __user *uargs, if (err) goto free_unload; - err = check_module_license_and_versions(mod); + err = check_export_symbol_versions(mod); if (err) goto free_unload; -- GitLab From 46752820f9abc013b6bd8172562b642376723313 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:35:38 -0700 Subject: [PATCH 1272/5631] module: add sanity check for ELF module section The ELF ".gnu.linkonce.this_module" section is special, it is what we use to construct the struct module __this_module, which THIS_MODULE points to. When userspace loads a module we always deal first with a copy of the userspace buffer, and twiddle with the userspace copy's version of the struct module. Eventually we allocate memory to do a memcpy() of that struct module, under the assumption that the module size is right. But we have no validity checks against the size or the requirements for the section. Add some validity checks for the special module section early and while at it, cache the module section index early, so we don't have to do that later. While at it, just move over the assigment of the info->mod to make the code clearer. The validity checker also adds an explicit size check to ensure the module section size matches the kernel's run time size for sizeof(struct module). This should prevent sloppy loads of modules which are built today *without* actually increasing the size of the struct module. A developer today can for example expand the size of struct module, rebuild a directoroy 'make fs/xfs/' for example and then try to insmode the driver there. That module would in effect have an incorrect size. This new size check would put a stop gap against such mistakes. This also makes the entire goal of ".gnu.linkonce.this_module" pretty clear. Before this patch verification of the goal / intent required some Indian Jones whips, torches and cleaning up big old spider webs. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 62 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 53 insertions(+), 9 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index cf097ffe6a4a..e1a9dd51c036 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2002 Richard Henderson * Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. + * Copyright (C) 2023 Luis Chamberlain */ #define INCLUDE_VERMAGIC @@ -1656,6 +1657,7 @@ static int elf_validity_check(struct load_info *info) unsigned int i; Elf_Shdr *shdr, *strhdr; int err; + unsigned int num_mod_secs = 0, mod_idx; if (info->len < sizeof(*(info->hdr))) { pr_err("Invalid ELF header len %lu\n", info->len); @@ -1767,6 +1769,11 @@ static int elf_validity_check(struct load_info *info) i, shdr->sh_type); return err; } + if (strcmp(info->secstrings + shdr->sh_name, + ".gnu.linkonce.this_module") == 0) { + num_mod_secs++; + mod_idx = i; + } if (shdr->sh_flags & SHF_ALLOC) { if (shdr->sh_name >= strhdr->sh_size) { @@ -1779,6 +1786,52 @@ static int elf_validity_check(struct load_info *info) } } + /* + * The ".gnu.linkonce.this_module" ELF section is special. It is + * what modpost uses to refer to __this_module and let's use rely + * on THIS_MODULE to point to &__this_module properly. The kernel's + * modpost declares it on each modules's *.mod.c file. If the struct + * module of the kernel changes a full kernel rebuild is required. + * + * We have a few expectaions for this special section, the following + * code validates all this for us: + * + * o Only one section must exist + * o We expect the kernel to always have to allocate it: SHF_ALLOC + * o The section size must match the kernel's run time's struct module + * size + */ + if (num_mod_secs != 1) { + pr_err("Only one .gnu.linkonce.this_module section must exist.\n"); + goto no_exec; + } + + shdr = &info->sechdrs[mod_idx]; + + /* + * This is already implied on the switch above, however let's be + * pedantic about it. + */ + if (shdr->sh_type == SHT_NOBITS) { + pr_err(".gnu.linkonce.this_module section must have a size set\n"); + goto no_exec; + } + + if (!(shdr->sh_flags & SHF_ALLOC)) { + pr_err(".gnu.linkonce.this_module must occupy memory during process execution\n"); + goto no_exec; + } + + if (shdr->sh_size != sizeof(struct module)) { + pr_err(".gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n"); + goto no_exec; + } + + info->index.mod = mod_idx; + + /* This is temporary: point mod into copy of data. */ + info->mod = (void *)info->hdr + shdr->sh_offset; + return 0; no_exec: @@ -1925,15 +1978,6 @@ static int setup_load_info(struct load_info *info, int flags) return -ENOEXEC; } - info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); - if (!info->index.mod) { - pr_warn("%s: No module found in object\n", - info->name ?: "(missing .modinfo section or name field)"); - return -ENOEXEC; - } - /* This is temporary: point mod into copy of data. */ - info->mod = (void *)info->hdr + info->sechdrs[info->index.mod].sh_offset; - /* * If we didn't load the .modinfo 'name' field earlier, fall back to * on-disk struct mod 'name' field. -- GitLab From c7ee8aebf6c0588c0aab76538aff395c3abf811c Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:35:39 -0700 Subject: [PATCH 1273/5631] module: add stop-grap sanity check on module memcpy() The integrity of the struct module we load is important, and although our ELF validator already checks that the module section must match struct module, add a stop-gap check before we memcpy() the final minted module. This also makes those inspecting the code what the goal is. While at it, clarify the goal behind updating the sh_addr address. The current comment is pretty misleading. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index e1a9dd51c036..fbe62d1625bc 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2213,7 +2213,8 @@ static int move_module(struct module *mod, struct load_info *info) { int i; void *ptr; - enum mod_mem_type t; + enum mod_mem_type t = 0; + int ret = -ENOMEM; for_each_mod_mem_type(type) { if (!mod->mem[type].size) { @@ -2249,9 +2250,26 @@ static int move_module(struct module *mod, struct load_info *info) dest = mod->mem[type].base + (shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK); - if (shdr->sh_type != SHT_NOBITS) + if (shdr->sh_type != SHT_NOBITS) { + /* + * Our ELF checker already validated this, but let's + * be pedantic and make the goal clearer. We actually + * end up copying over all modifications made to the + * userspace copy of the entire struct module. + */ + if (i == info->index.mod && + (WARN_ON_ONCE(shdr->sh_size != sizeof(struct module)))) { + ret = -ENOEXEC; + goto out_enomem; + } memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); - /* Update sh_addr to point to copy in image. */ + } + /* + * Update the userspace copy's ELF section address to point to + * our newly allocated memory as a pure convenience so that + * users of info can keep taking advantage and using the newly + * minted official memory area. + */ shdr->sh_addr = (unsigned long)dest; pr_debug("\t0x%lx %s\n", (long)shdr->sh_addr, info->secstrings + shdr->sh_name); @@ -2261,7 +2279,7 @@ static int move_module(struct module *mod, struct load_info *info) out_enomem: for (t--; t >= 0; t--) module_memory_free(mod->mem[t].base, t); - return -ENOMEM; + return ret; } static int check_export_symbol_versions(struct module *mod) -- GitLab From 1bb49db9919a4d4186cba288930e7026d8f7ec96 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:35:40 -0700 Subject: [PATCH 1274/5631] module: move more elf validity checks to elf_validity_check() The symbol and strings section validation currently happen in setup_load_info() but since they are also doing validity checks move this to elf_validity_check(). Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 79 ++++++++++++++++++++++++-------------------- 1 file changed, 44 insertions(+), 35 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index fbe62d1625bc..84a7f96cf35a 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1658,6 +1658,8 @@ static int elf_validity_check(struct load_info *info) Elf_Shdr *shdr, *strhdr; int err; unsigned int num_mod_secs = 0, mod_idx; + unsigned int num_info_secs = 0, info_idx; + unsigned int num_sym_secs = 0, sym_idx; if (info->len < sizeof(*(info->hdr))) { pr_err("Invalid ELF header len %lu\n", info->len); @@ -1761,6 +1763,8 @@ static int elf_validity_check(struct load_info *info) info->hdr->e_shnum); goto no_exec; } + num_sym_secs++; + sym_idx = i; fallthrough; default: err = validate_section_offset(info, shdr); @@ -1773,6 +1777,10 @@ static int elf_validity_check(struct load_info *info) ".gnu.linkonce.this_module") == 0) { num_mod_secs++; mod_idx = i; + } else if (strcmp(info->secstrings + shdr->sh_name, + ".modinfo") == 0) { + num_info_secs++; + info_idx = i; } if (shdr->sh_flags & SHF_ALLOC) { @@ -1786,6 +1794,27 @@ static int elf_validity_check(struct load_info *info) } } + if (num_info_secs > 1) { + pr_err("Only one .modinfo section must exist.\n"); + goto no_exec; + } else if (num_info_secs == 1) { + /* Try to find a name early so we can log errors with a module name */ + info->index.info = info_idx; + info->name = get_modinfo(info, "name"); + } + + if (num_sym_secs != 1) { + pr_warn("%s: module has no symbols (stripped?)\n", + info->name ?: "(missing .modinfo section or name field)"); + goto no_exec; + } + + /* Sets internal symbols and strings. */ + info->index.sym = sym_idx; + shdr = &info->sechdrs[sym_idx]; + info->index.str = shdr->sh_link; + info->strtab = (char *)info->hdr + info->sechdrs[info->index.str].sh_offset; + /* * The ".gnu.linkonce.this_module" ELF section is special. It is * what modpost uses to refer to __this_module and let's use rely @@ -1802,7 +1831,8 @@ static int elf_validity_check(struct load_info *info) * size */ if (num_mod_secs != 1) { - pr_err("Only one .gnu.linkonce.this_module section must exist.\n"); + pr_err("module %s: Only one .gnu.linkonce.this_module section must exist.\n", + info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } @@ -1813,17 +1843,20 @@ static int elf_validity_check(struct load_info *info) * pedantic about it. */ if (shdr->sh_type == SHT_NOBITS) { - pr_err(".gnu.linkonce.this_module section must have a size set\n"); + pr_err("module %s: .gnu.linkonce.this_module section must have a size set\n", + info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } if (!(shdr->sh_flags & SHF_ALLOC)) { - pr_err(".gnu.linkonce.this_module must occupy memory during process execution\n"); + pr_err("module %s: .gnu.linkonce.this_module must occupy memory during process execution\n", + info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } if (shdr->sh_size != sizeof(struct module)) { - pr_err(".gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n"); + pr_err("module %s: .gnu.linkonce.this_module section size must match the kernel's built struct module size at run time\n", + info->name ?: "(missing .modinfo section or name field)"); goto no_exec; } @@ -1832,6 +1865,13 @@ static int elf_validity_check(struct load_info *info) /* This is temporary: point mod into copy of data. */ info->mod = (void *)info->hdr + shdr->sh_offset; + /* + * If we didn't load the .modinfo 'name' field earlier, fall back to + * on-disk struct mod 'name' field. + */ + if (!info->name) + info->name = info->mod->name; + return 0; no_exec: @@ -1954,37 +1994,6 @@ static int rewrite_section_headers(struct load_info *info, int flags) */ static int setup_load_info(struct load_info *info, int flags) { - unsigned int i; - - /* Try to find a name early so we can log errors with a module name */ - info->index.info = find_sec(info, ".modinfo"); - if (info->index.info) - info->name = get_modinfo(info, "name"); - - /* Find internal symbols and strings. */ - for (i = 1; i < info->hdr->e_shnum; i++) { - if (info->sechdrs[i].sh_type == SHT_SYMTAB) { - info->index.sym = i; - info->index.str = info->sechdrs[i].sh_link; - info->strtab = (char *)info->hdr - + info->sechdrs[info->index.str].sh_offset; - break; - } - } - - if (info->index.sym == 0) { - pr_warn("%s: module has no symbols (stripped?)\n", - info->name ?: "(missing .modinfo section or name field)"); - return -ENOEXEC; - } - - /* - * If we didn't load the .modinfo 'name' field earlier, fall back to - * on-disk struct mod 'name' field. - */ - if (!info->name) - info->name = info->mod->name; - if (flags & MODULE_INIT_IGNORE_MODVERSIONS) info->index.vers = 0; /* Pretend no __versions section! */ else -- GitLab From 3d40bb903ed1f654707d34bdd61ee2c332000e4b Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:35:41 -0700 Subject: [PATCH 1275/5631] module: merge remnants of setup_load_info() to elf validation The setup_load_info() was actually had ELF validation checks of its own. To later cache useful variables as an secondary step just means looping again over the ELF sections we just validated. We can simply keep tabs of the key sections of interest as we validate the module ELF section in one swoop, so do that and merge the two routines together. Expand a bit on the documentation / intent / goals. Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 60 ++++++++++++++++++++------------------------ 1 file changed, 27 insertions(+), 33 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 84a7f96cf35a..929644d79d38 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1647,12 +1647,26 @@ static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr) } /* - * Sanity checks against invalid binaries, wrong arch, weird elf version. + * Check userspace passed ELF module against our expectations, and cache + * useful variables for further processing as we go. * - * Also do basic validity checks against section offsets and sizes, the + * This does basic validity checks against section offsets and sizes, the * section name string table, and the indices used for it (sh_name). + * + * As a last step, since we're already checking the ELF sections we cache + * useful variables which will be used later for our convenience: + * + * o pointers to section headers + * o cache the modinfo symbol section + * o cache the string symbol section + * o cache the module section + * + * As a last step we set info->mod to the temporary copy of the module in + * info->hdr. The final one will be allocated in move_module(). Any + * modifications we make to our copy of the module will be carried over + * to the final minted module. */ -static int elf_validity_check(struct load_info *info) +static int elf_validity_cache_copy(struct load_info *info, int flags) { unsigned int i; Elf_Shdr *shdr, *strhdr; @@ -1872,6 +1886,13 @@ static int elf_validity_check(struct load_info *info) if (!info->name) info->name = info->mod->name; + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) + info->index.vers = 0; /* Pretend no __versions section! */ + else + info->index.vers = find_sec(info, "__versions"); + + info->index.pcpu = find_pcpusec(info); + return 0; no_exec: @@ -1984,26 +2005,6 @@ static int rewrite_section_headers(struct load_info *info, int flags) return 0; } -/* - * Set up our basic convenience variables (pointers to section headers, - * search for module section index etc), and do some basic section - * verification. - * - * Set info->mod to the temporary copy of the module in info->hdr. The final one - * will be allocated in move_module(). - */ -static int setup_load_info(struct load_info *info, int flags) -{ - if (flags & MODULE_INIT_IGNORE_MODVERSIONS) - info->index.vers = 0; /* Pretend no __versions section! */ - else - info->index.vers = find_sec(info, "__versions"); - - info->index.pcpu = find_pcpusec(info); - - return 0; -} - /* * These calls taint the kernel depending certain module circumstances */ static void module_augment_kernel_taints(struct module *mod, struct load_info *info) @@ -2809,17 +2810,10 @@ static int load_module(struct load_info *info, const char __user *uargs, /* * Do basic sanity checks against the ELF header and - * sections. - */ - err = elf_validity_check(info); - if (err) - goto free_copy; - - /* - * Everything checks out, so set up the section info - * in the info structure. + * sections. Cache useful sections and set the + * info->mod to the userspace passed struct module. */ - err = setup_load_info(info, flags); + err = elf_validity_cache_copy(info, flags); if (err) goto free_copy; -- GitLab From 25be451aa4c0e9a96c59a626ab0e93d5cb7f6f48 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sun, 19 Mar 2023 14:35:42 -0700 Subject: [PATCH 1276/5631] module: fold usermode helper kmod into modules directory The kernel/kmod.c is already only built if we enabled modules, so just stuff it under kernel/module/kmod.c and unify the MAINTAINERS file for it. Signed-off-by: Luis Chamberlain --- MAINTAINERS | 13 +++---------- kernel/Makefile | 1 - kernel/module/Makefile | 4 +++- kernel/{ => module}/kmod.c | 0 4 files changed, 6 insertions(+), 12 deletions(-) rename kernel/{ => module}/kmod.c (100%) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..1ca0e26aa9f8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11522,16 +11522,6 @@ F: include/linux/kmemleak.h F: mm/kmemleak.c F: samples/kmemleak/kmemleak-test.c -KMOD KERNEL MODULE LOADER - USERMODE HELPER -M: Luis Chamberlain -L: linux-kernel@vger.kernel.org -L: linux-modules@vger.kernel.org -S: Maintained -F: include/linux/kmod.h -F: kernel/kmod.c -F: lib/test_kmod.c -F: tools/testing/selftests/kmod/ - KMSAN M: Alexander Potapenko R: Marco Elver @@ -14083,8 +14073,11 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git modules-next F: include/linux/module.h +F: include/linux/kmod.h F: kernel/module/ F: scripts/module* +F: lib/test_kmod.c +F: tools/testing/selftests/kmod/ MONOLITHIC POWER SYSTEM PMIC DRIVER M: Saravanan Sekar diff --git a/kernel/Makefile b/kernel/Makefile index 10ef068f598d..3dd4ea433ee9 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -13,7 +13,6 @@ obj-y = fork.o exec_domain.o panic.o \ async.o range.o smpboot.o ucount.o regset.o obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o -obj-$(CONFIG_MODULES) += kmod.o obj-$(CONFIG_MULTIUSER) += groups.o ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/module/Makefile b/kernel/module/Makefile index 948efea81e85..5b1d26b53b8d 100644 --- a/kernel/module/Makefile +++ b/kernel/module/Makefile @@ -7,7 +7,9 @@ # and produce insane amounts of uninteresting coverage. KCOV_INSTRUMENT_module.o := n -obj-y += main.o strict_rwx.o +obj-y += main.o +obj-y += strict_rwx.o +obj-y += kmod.o obj-$(CONFIG_MODULE_DECOMPRESS) += decompress.o obj-$(CONFIG_MODULE_SIG) += signing.o obj-$(CONFIG_LIVEPATCH) += livepatch.o diff --git a/kernel/kmod.c b/kernel/module/kmod.c similarity index 100% rename from kernel/kmod.c rename to kernel/module/kmod.c -- GitLab From 6ed81802d4d1b037ad2d1657511ff0c2e9aeda14 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Tue, 21 Mar 2023 19:36:20 -0600 Subject: [PATCH 1277/5631] module: in layout_sections, move_module: add the modname layout_sections() and move_module() each issue ~50 messages for each module loaded. Add mod-name into their 2 header lines, to help the reader find his module. no functional changes. Signed-off-by: Jim Cromie Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 929644d79d38..3bea679837e0 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1567,10 +1567,10 @@ static void layout_sections(struct module *mod, struct load_info *info) for (i = 0; i < info->hdr->e_shnum; i++) info->sechdrs[i].sh_entsize = ~0UL; - pr_debug("Core section allocation order:\n"); + pr_debug("Core section allocation order for %s:\n", mod->name); __layout_sections(mod, info, false); - pr_debug("Init section allocation order:\n"); + pr_debug("Init section allocation order for %s:\n", mod->name); __layout_sections(mod, info, true); } @@ -2249,7 +2249,7 @@ static int move_module(struct module *mod, struct load_info *info) } /* Transfer each section which specifies SHF_ALLOC */ - pr_debug("final section addresses:\n"); + pr_debug("Final section addresses for %s:\n", mod->name); for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; Elf_Shdr *shdr = &info->sechdrs[i]; -- GitLab From b10addf37bbcaee66672eb54c15532266c8daea6 Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Tue, 21 Mar 2023 19:36:21 -0600 Subject: [PATCH 1278/5631] module: add symbol-name to pr_debug Absolute symbol The pr_debug("Absolute symbol" ..) reports value, (which is usually 0), but not the name, which is more informative. So add it. no functional changes Signed-off-by: Jim Cromie Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 3bea679837e0..6567d5a156ae 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1394,8 +1394,8 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) case SHN_ABS: /* Don't need to do anything */ - pr_debug("Absolute symbol: 0x%08lx\n", - (long)sym[i].st_value); + pr_debug("Absolute symbol: 0x%08lx %s\n", + (long)sym[i].st_value, name); break; case SHN_LIVEPATCH: -- GitLab From 66a2301edf313d630c2ece4f3721c5b3402653ee Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Tue, 21 Mar 2023 19:36:22 -0600 Subject: [PATCH 1279/5631] module: add section-size to move_module pr_debug move_module() pr_debug's "Final section addresses for $modname". Add section addresses to the message, for anyone looking at these. no functional changes. Signed-off-by: Jim Cromie Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 6567d5a156ae..1d587e5e9cc6 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2281,8 +2281,8 @@ static int move_module(struct module *mod, struct load_info *info) * minted official memory area. */ shdr->sh_addr = (unsigned long)dest; - pr_debug("\t0x%lx %s\n", - (long)shdr->sh_addr, info->secstrings + shdr->sh_name); + pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr, + (long)shdr->sh_size, info->secstrings + shdr->sh_name); } return 0; -- GitLab From 33c951f62920d144ca89daa0560180a49afb6f1e Mon Sep 17 00:00:00 2001 From: Jim Cromie Date: Tue, 21 Mar 2023 19:36:23 -0600 Subject: [PATCH 1280/5631] module: already_uses() - reduce pr_debug output volume already_uses() is unnecessarily chatty. `modprobe i915` yields 491 messages like: [ 64.108744] i915 uses drm! This is a normal situation, and isn't worth all the log entries. NOTE: I've preserved the "does not use %s" messages, which happens less often, but does happen. Its not clear to me what it tells a reader, or what info might improve the pr_debug's utility. [ 6847.584999] main:already_uses:569: amdgpu does not use ttm! [ 6847.585001] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585014] main:already_uses:569: amdgpu does not use drm! [ 6847.585016] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585024] main:already_uses:569: amdgpu does not use drm_display_helper! [ 6847.585025] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585084] main:already_uses:569: amdgpu does not use drm_kms_helper! [ 6847.585086] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585175] main:already_uses:569: amdgpu does not use drm_buddy! [ 6847.585176] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585202] main:already_uses:569: amdgpu does not use i2c_algo_bit! [ 6847.585204] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585249] main:already_uses:569: amdgpu does not use gpu_sched! [ 6847.585250] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585314] main:already_uses:569: amdgpu does not use video! [ 6847.585315] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585409] main:already_uses:569: amdgpu does not use iommu_v2! [ 6847.585410] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6847.585816] main:already_uses:569: amdgpu does not use drm_ttm_helper! [ 6847.585818] main:add_module_usage:584: Allocating new usage for amdgpu. [ 6848.762268] dyndbg: add-module: amdgpu.2533 sites no functional changes. Signed-off-by: Jim Cromie Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 1d587e5e9cc6..5cc21083af04 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -564,10 +564,8 @@ static int already_uses(struct module *a, struct module *b) struct module_use *use; list_for_each_entry(use, &b->source_list, source_list) { - if (use->source == a) { - pr_debug("%s uses %s!\n", a->name, b->name); + if (use->source == a) return 1; - } } pr_debug("%s does not use %s!\n", a->name, b->name); return 0; -- GitLab From 3edf091d5c1241fa191a1d860a3930411fc81d79 Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Fri, 24 Mar 2023 15:53:10 +0700 Subject: [PATCH 1281/5631] Documentation: core-api: update kernel-doc reference to kmod.c Commit d6f819908f8aac ("module: fold usermode helper kmod into modules directory") moves kmod helper implementation (kmod.c) to kernel/module/ directory but forgets to update its reference on kernel api doc, hence: WARNING: kernel-doc './scripts/kernel-doc -rst -enable-lineno -sphinx-version 2.4.4 -export ./kernel/kmod.c' failed with return code 2 Update the reference. Fixes: d6f819908f8aac ("module: fold usermode helper kmod into modules directory") Reported-by: Stephen Rothwell Link: https://lore.kernel.org/linux-next/20230324154413.19cc78be@canb.auug.org.au/ Signed-off-by: Bagas Sanjaya Reviewed-by: Liam Beguin Signed-off-by: Luis Chamberlain --- Documentation/core-api/kernel-api.rst | 2 +- Documentation/translations/zh_CN/core-api/kernel-api.rst | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 62f961610773..e27728596008 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -223,7 +223,7 @@ Module Support Module Loading -------------- -.. kernel-doc:: kernel/kmod.c +.. kernel-doc:: kernel/module/kmod.c :export: Inter Module support diff --git a/Documentation/translations/zh_CN/core-api/kernel-api.rst b/Documentation/translations/zh_CN/core-api/kernel-api.rst index a4b373c48c0c..a1ea7081077c 100644 --- a/Documentation/translations/zh_CN/core-api/kernel-api.rst +++ b/Documentation/translations/zh_CN/core-api/kernel-api.rst @@ -226,7 +226,7 @@ kernel/relay.c 该API在以下内核代码中: -kernel/kmod.c +kernel/module/kmod.c 模块接口支持 ------------ -- GitLab From 5b1abc285a083f76e9987efa9e78ecc18d5d202f Mon Sep 17 00:00:00 2001 From: Like Xu Date: Mon, 13 Mar 2023 16:53:11 +0800 Subject: [PATCH 1282/5631] KVM: selftests: Report enable_pmu module value when test is skipped Running x86_64/pmu_event_filter_test or x86_64/vmx_pmu_caps_test with enable_pmu globally disabled will report the following into: 1..0 # SKIP - Requirement not met: use_intel_pmu() || use_amd_pmu() or 1..0 # SKIP - Requirement not met: kvm_cpu_has(X86_FEATURE_PDCM) this can be confusing, so add a check on kvm.enable_pmu. Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230313085311.25327-3-likexu@tencent.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c | 1 + tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c | 1 + 2 files changed, 2 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2feef25ba691..1f60dfae69e0 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -764,6 +764,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; + TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index c280ba1e6572..2933b1bd754e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -55,6 +55,7 @@ int main(int argc, char *argv[]) /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); + TEST_REQUIRE(get_kvm_param_bool("enable_pmu")); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); -- GitLab From 8264e85560e5fae942ca42aae1df7daeb5aaa30e Mon Sep 17 00:00:00 2001 From: Ackerley Tng Date: Mon, 27 Feb 2023 18:06:01 +0000 Subject: [PATCH 1283/5631] KVM: selftests: Adjust VM's initial stack address to align with SysV ABI spec Align the guest stack to match calling sequence requirements in section "The Stack Frame" of the System V ABI AMD64 Architecture Processor Supplement, which requires the value (%rsp + 8), NOT %rsp, to be a multiple of 16 when control is transferred to the function entry point. I.e. in a normal function call, %rsp needs to be 16-byte aligned _before_ CALL, not after. This fixes unexpected #GPs in guest code when the compiler uses SSE instructions, e.g. to initialize memory, as many SSE instructions require memory operands (including those on the stack) to be 16-byte-aligned. Signed-off-by: Ackerley Tng Link: https://lore.kernel.org/r/20230227180601.104318-1-ackerleytng@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/lib/x86_64/processor.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c39a4353ba19..c09cd151fbe0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -5,6 +5,7 @@ * Copyright (C) 2018, Google LLC. */ +#include "linux/bitmap.h" #include "test_util.h" #include "kvm_util.h" #include "processor.h" @@ -573,6 +574,21 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, DEFAULT_GUEST_STACK_VADDR_MIN, MEM_REGION_DATA); + stack_vaddr += DEFAULT_STACK_PGS * getpagesize(); + + /* + * Align stack to match calling sequence requirements in section "The + * Stack Frame" of the System V ABI AMD64 Architecture Processor + * Supplement, which requires the value (%rsp + 8) to be a multiple of + * 16 when control is transferred to the function entry point. + * + * If this code is ever used to launch a vCPU with 32-bit entry point it + * may need to subtract 4 bytes instead of 8 bytes. + */ + TEST_ASSERT(IS_ALIGNED(stack_vaddr, PAGE_SIZE), + "__vm_vaddr_alloc() did not provide a page-aligned address"); + stack_vaddr -= 8; + vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); vcpu_setup(vm, vcpu); @@ -580,7 +596,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); regs.rflags = regs.rflags | 0x2; - regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize()); + regs.rsp = stack_vaddr; regs.rip = (unsigned long) guest_code; vcpu_regs_set(vcpu, ®s); -- GitLab From 735b0e0f2d001b7ed9486db84453fb860e764a4d Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Wed, 22 Mar 2023 18:45:28 +0400 Subject: [PATCH 1284/5631] KVM: selftests: Add 'malloc' failure check in vcpu_save_state There is a 'malloc' call in vcpu_save_state function, which can be unsuccessful. This patch will add the malloc failure checking to avoid possible null dereference and give more information about test fail reasons. Signed-off-by: Ivan Orlov Link: https://lore.kernel.org/r/20230322144528.704077-1-ivan.orlov0322@gmail.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/lib/x86_64/processor.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index c09cd151fbe0..a12b21a2ef37 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -970,6 +970,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu) vcpu_run_complete_io(vcpu); state = malloc(sizeof(*state) + msr_list->nmsrs * sizeof(state->msrs.entries[0])); + TEST_ASSERT(state, "-ENOMEM when allocating kvm state"); vcpu_events_get(vcpu, &state->events); vcpu_mp_state_get(vcpu, &state->mp_state); -- GitLab From 5de4a3765b7e703374aa955662bba67475a7ac92 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:44 +0000 Subject: [PATCH 1285/5631] KVM: selftests: Add a fully functional "struct xstate" for x86 Add a working xstate data structure for the usage of AMX and potential future usage on other xstate components. AMX selftest requires checking both the xstate_bv and xcomp_bv. Existing code relies on pointer arithmetics to fetch xstate_bv and does not support xcomp_bv. So, add a working xstate data structure into processor.h for x86. Suggested-by: Sean Christopherson Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-3-mizhang@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 12 +++++++ tools/testing/selftests/kvm/x86_64/amx_test.c | 36 ++++++------------- 2 files changed, 23 insertions(+), 25 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 90387ddcb2a9..44b6c23d08f7 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -48,6 +48,18 @@ extern bool host_cpu_is_amd; #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +struct xstate_header { + u64 xstate_bv; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +struct xstate { + u8 i387[512]; + struct xstate_header header; + u8 extended_state_area[0]; +} __attribute__ ((packed, aligned (64))); + /* Note, these are ordered alphabetically to match kvm_cpuid_entry2. Eww. */ enum cpuid_output_regs { KVM_CPUID_EAX, diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index b646cdb5055a..59e0a573652d 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -41,10 +41,6 @@ #define XSAVE_HDR_OFFSET 512 -struct xsave_data { - u8 area[XSAVE_SIZE]; -} __aligned(64); - struct tile_config { u8 palette_id; u8 start_row; @@ -103,13 +99,13 @@ static inline void __tilerelease(void) asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::); } -static inline void __xsavec(struct xsave_data *data, uint64_t rfbm) +static inline void __xsavec(struct xstate *xstate, uint64_t rfbm) { uint32_t rfbm_lo = rfbm; uint32_t rfbm_hi = rfbm >> 32; asm volatile("xsavec (%%rdi)" - : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi) + : : "D" (xstate), "a" (rfbm_lo), "d" (rfbm_hi) : "memory"); } @@ -158,16 +154,6 @@ static void set_tilecfg(struct tile_config *cfg) } } -static void set_xstatebv(void *data, uint64_t bv) -{ - *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv; -} - -static u64 get_xstatebv(void *data) -{ - return *(u64 *)(data + XSAVE_HDR_OFFSET); -} - static void init_regs(void) { uint64_t cr4, xcr0; @@ -184,7 +170,7 @@ static void init_regs(void) static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct tile_data *tiledata, - struct xsave_data *xsave_data) + struct xstate *xstate) { init_regs(); check_cpuid_xsave(); @@ -205,9 +191,9 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, __tilerelease(); GUEST_SYNC(5); /* bit 18 not in the XCOMP_BV after xsavec() */ - set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA); - __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0); + xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; + __xsavec(xstate, XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); @@ -243,7 +229,7 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; struct kvm_x86_state *state; int xsave_restore_size; - vm_vaddr_t amx_cfg, tiledata, xsavedata; + vm_vaddr_t amx_cfg, tiledata, xstate; struct ucall uc; u32 amx_offset; int stage, ret; @@ -282,10 +268,10 @@ int main(int argc, char *argv[]) tiledata = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize()); - /* xsave data for guest_code */ - xsavedata = vm_vaddr_alloc_pages(vm, 3); - memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize()); - vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xsavedata); + /* XSAVE state for guest_code */ + xstate = vm_vaddr_alloc_pages(vm, DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + memset(addr_gva2hva(vm, xstate), 0, PAGE_SIZE * DIV_ROUND_UP(XSAVE_SIZE, PAGE_SIZE)); + vcpu_args_set(vcpu, 3, amx_cfg, tiledata, xstate); for (stage = 1; ; stage++) { vcpu_run(vcpu); -- GitLab From bec357a4af5579a60eaba6d42f7d3662d4323767 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:45 +0000 Subject: [PATCH 1286/5631] KVM: selftests: Fix an error in comment of amx_test After the execution of __tilerelease(), AMX component will be in INIT state. Therefore, execution of XSAVEC saving the AMX state into memory will cause the xstate_bv[18] cleared in xheader. However, the xcomp_bv[18] will remain set. Fix the error in comment. Also, update xsavec() to XSAVEC because xcomp_bv[18] is set due to the instruction, not the function. Finally, use XTILEDATA instead 'bit 18' in comments. Cc: Jim Mattson Cc: Venkatesh Srinivas Cc: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-4-mizhang@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 59e0a573652d..c59d7ff0b01d 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -190,7 +190,10 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, GUEST_SYNC(4); __tilerelease(); GUEST_SYNC(5); - /* bit 18 not in the XCOMP_BV after xsavec() */ + /* + * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in + * the xcomp_bv. + */ xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; __xsavec(xstate, XFEATURE_MASK_XTILEDATA); GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); -- GitLab From 48ad4222c43ceb5ce303758ff26e1d8c881502ac Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:46 +0000 Subject: [PATCH 1287/5631] KVM: selftests: Enable checking on xcomp_bv in amx_test After tilerelease instruction, AMX tiles are in INIT state. According to Intel SDM vol 1. 13.10: "If RFBM[i] = 1, XSTATE_BV[i] is set to the value of XINUSE[i].", XSTATE_BV[18] should be cleared after xsavec. On the other hand, according to Intel SDM vol 1. 13.4.3: "If XCOMP_BV[i] = 1, state component i is located at a byte offset locationI from the base address of the XSAVE area". Since at the time of xsavec, XCR0[18] is set indicating AMX tile data component is still enabled, xcomp_bv[18] should be set. Complete the checks by adding the assert to xcomp_bv[18] after xsavec. Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-5-mizhang@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index c59d7ff0b01d..34cf6f253c13 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -197,6 +197,7 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; __xsavec(xstate, XFEATURE_MASK_XTILEDATA); GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); + GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILEDATA); /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); -- GitLab From 0aeb9729486a32fab168114b00006b2643aa8a41 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:47 +0000 Subject: [PATCH 1288/5631] KVM: selftests: Add check of CR0.TS in the #NM handler in amx_test Be extra paranoid and assert that CR0.TS is clear when verifying the #NM in the AMX test is due to the expected XFeature Disable error, i.e. that the #NM isn't due to CR0.TS=1. Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-6-mizhang@google.com [sean: reword changelog to make it clear this is pure paranoia] Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 34cf6f253c13..95a30611e03e 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -216,6 +216,7 @@ void guest_nm_handler(struct ex_regs *regs) { /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ GUEST_SYNC(7); + GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); GUEST_SYNC(8); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); -- GitLab From 9cbd9aaa670f7be61ba569f5c3ebafc2e0aabeb6 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:48 +0000 Subject: [PATCH 1289/5631] KVM: selftests: Assert that XTILE_DATA is set in IA32_XFD on #NM Add an extra check to IA32_XFD to ensure that XTILE_DATA is actually set, i.e. is consistent with the AMX architecture. In addition, repeat the checks after the guest/host world switch to ensure the values of IA32_XFD and IA32_XFD_ERR are well preserved. Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-7-mizhang@google.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 95a30611e03e..cd0491cc7c8c 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -218,8 +218,10 @@ void guest_nm_handler(struct ex_regs *regs) GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); GUEST_SYNC(8); GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ -- GitLab From bfc5afc37c9dba85f8c057fb85109a72e72d64a5 Mon Sep 17 00:00:00 2001 From: Mingwei Zhang Date: Tue, 21 Feb 2023 16:36:50 +0000 Subject: [PATCH 1290/5631] KVM: selftests: Verify XTILE_DATA in XSTATE isn't affected by IA32_XFD Add asserts to verify the XSTATE metadata for XTILE_DATA isn't affected by disabling AMX tile data via IA32_XFD. XFD doesn't intercept XSAVE, it only prevents setting bits in XCR0, i.e. regardless of XFD, AMX state is managed by XSAVE/XRSTOR as long as the corresponding bits are set XCR0. Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-9-mizhang@google.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index cd0491cc7c8c..e6bc6cd108dc 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -201,6 +201,16 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, /* xfd=0x40000, disable amx tiledata */ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + + /* + * XTILEDATA is cleared in xstate_bv but set in xcomp_bv, this property + * remains the same even when amx tiledata is disabled by IA32_XFD. + */ + xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; + __xsavec(xstate, XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); + GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILEDATA)); + GUEST_SYNC(6); GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); set_tilecfg(amx_cfg); -- GitLab From 7e1075f050782c4d1249ebb15f63836bc2a94a97 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 21 Feb 2023 16:36:51 +0000 Subject: [PATCH 1291/5631] KVM: selftests: Assert that XTILE is XSAVE-enabled Assert that XTILE is XSAVE-enabled. check_xsave_supports_xtile() doesn't actually check anything since its return value is not used. Add the intended assert. Opportunistically, move the assert to a more appropriate location: immediately after XSETBV and remove check_xsave_supports_xtile(). Fixes: 5dc19f1c7dd3 ("KVM: selftests: Convert AMX test to use X86_PROPRETY_XXX") Signed-off-by: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-10-mizhang@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index e6bc6cd108dc..6f788e6d8a8d 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -115,11 +115,6 @@ static inline void check_cpuid_xsave(void) GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); } -static bool check_xsave_supports_xtile(void) -{ - return __xgetbv(0) & XFEATURE_MASK_XTILE; -} - static void check_xtile_info(void) { GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0)); @@ -166,6 +161,7 @@ static void init_regs(void) xcr0 = __xgetbv(0); xcr0 |= XFEATURE_MASK_XTILE; __xsetbv(0x0, xcr0); + GUEST_ASSERT(__xgetbv(0) & XFEATURE_MASK_XTILE); } static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, @@ -174,7 +170,6 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, { init_regs(); check_cpuid_xsave(); - check_xsave_supports_xtile(); check_xtile_info(); GUEST_SYNC(1); -- GitLab From 2ab3991b0b9b57affd26ab116c6e1aab5c1bf8c3 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 21 Feb 2023 16:36:52 +0000 Subject: [PATCH 1292/5631] KVM: selftests: Assert that both XTILE{CFG,DATA} are XSAVE-enabled Assert that both XTILE{CFG,DATA} are written and read back via XSETBV and XGETBV respectively. The original check in amx_test only ensures at least one of the XTILE bits are set, XTILECFG or XTILEDATA, when it really should be checking that both are set. Fixes: bf70636d9443 ("selftest: kvm: Add amx selftest") Signed-off-by: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-11-mizhang@google.com [sean: massage changelog] Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 6f788e6d8a8d..e9d31f443192 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -161,7 +161,7 @@ static void init_regs(void) xcr0 = __xgetbv(0); xcr0 |= XFEATURE_MASK_XTILE; __xsetbv(0x0, xcr0); - GUEST_ASSERT(__xgetbv(0) & XFEATURE_MASK_XTILE); + GUEST_ASSERT((__xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE); } static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, -- GitLab From d01d4a4f7bd2197208b904378debf3331eec936e Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 21 Feb 2023 16:36:53 +0000 Subject: [PATCH 1293/5631] KVM: selftests: Move XSAVE and OSXSAVE CPUID checks into AMX's init_regs() Move the checks on XSAVE and OSXSAVE into init_regs() so that the XSAVE check is done before setting CR4.OSXSAVE, i.e. before a potential #GP, and so that the OSXSAVE check is performend immediately after enabling XSAVE in CR4. Signed-off-by: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-12-mizhang@google.com [sean: keep XSAVE check, rewrite changelog accordingly] Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/amx_test.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index e9d31f443192..d1838d5ad9d7 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -109,12 +109,6 @@ static inline void __xsavec(struct xstate *xstate, uint64_t rfbm) : "memory"); } -static inline void check_cpuid_xsave(void) -{ - GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); - GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); -} - static void check_xtile_info(void) { GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0)); @@ -153,10 +147,13 @@ static void init_regs(void) { uint64_t cr4, xcr0; + GUEST_ASSERT(this_cpu_has(X86_FEATURE_XSAVE)); + /* turn on CR4.OSXSAVE */ cr4 = get_cr4(); cr4 |= X86_CR4_OSXSAVE; set_cr4(cr4); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); xcr0 = __xgetbv(0); xcr0 |= XFEATURE_MASK_XTILE; @@ -169,7 +166,6 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, struct xstate *xstate) { init_regs(); - check_cpuid_xsave(); check_xtile_info(); GUEST_SYNC(1); -- GitLab From d32fb071429360f5f597c284087c845b2f748ebe Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 21 Feb 2023 16:36:54 +0000 Subject: [PATCH 1294/5631] KVM: selftests: Check that the palette table exists before using it Check that the palette table exists before using it. The maximum number of AMX palette tables is enumerated by CPUID.1DH:EAX. Assert that the palette used in amx_test, CPUID.1DH.1H, does not exceed that maximum. Signed-off-by: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-13-mizhang@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/include/x86_64/processor.h | 1 + tools/testing/selftests/kvm/x86_64/amx_test.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 44b6c23d08f7..f108fae5d29e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -227,6 +227,7 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_XSTATE_MAX_SIZE KVM_X86_CPU_PROPERTY(0xd, 0, ECX, 0, 31) #define X86_PROPERTY_XSTATE_TILE_SIZE KVM_X86_CPU_PROPERTY(0xd, 18, EAX, 0, 31) #define X86_PROPERTY_XSTATE_TILE_OFFSET KVM_X86_CPU_PROPERTY(0xd, 18, EBX, 0, 31) +#define X86_PROPERTY_AMX_MAX_PALETTE_TABLES KVM_X86_CPU_PROPERTY(0x1d, 0, EAX, 0, 31) #define X86_PROPERTY_AMX_TOTAL_TILE_BYTES KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 0, 15) #define X86_PROPERTY_AMX_BYTES_PER_TILE KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 16, 31) #define X86_PROPERTY_AMX_BYTES_PER_ROW KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 0, 15) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index d1838d5ad9d7..8e8f26d715d6 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -30,6 +30,7 @@ #define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE) /* Tile configuration associated: */ +#define PALETTE_TABLE_INDEX 1 #define MAX_TILES 16 #define RESERVED_BYTES 14 @@ -120,6 +121,10 @@ static void check_xtile_info(void) GUEST_ASSERT(xtile.xsave_size == 8192); GUEST_ASSERT(sizeof(struct tile_data) >= xtile.xsave_size); + GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_AMX_MAX_PALETTE_TABLES)); + GUEST_ASSERT(this_cpu_property(X86_PROPERTY_AMX_MAX_PALETTE_TABLES) >= + PALETTE_TABLE_INDEX); + GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_AMX_NR_TILE_REGS)); xtile.max_names = this_cpu_property(X86_PROPERTY_AMX_NR_TILE_REGS); GUEST_ASSERT(xtile.max_names == 8); -- GitLab From d563164eaeb1a995c2a10ace6fdb0a730b41c167 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 21 Feb 2023 16:36:55 +0000 Subject: [PATCH 1295/5631] KVM: selftests: Check that XTILEDATA supports XFD Check that XTILEDATA supports XFD. In amx_test, add the requirement that the guest allows the xfeature, XTILEDATA, to be set in XFD. Otherwise, the test may fail. Signed-off-by: Aaron Lewis Signed-off-by: Mingwei Zhang Link: https://lore.kernel.org/r/20230221163655.920289-14-mizhang@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/include/x86_64/processor.h | 1 + tools/testing/selftests/kvm/x86_64/amx_test.c | 1 + 2 files changed, 2 insertions(+) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index f108fae5d29e..3538fa6db72d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -143,6 +143,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_XTILEDATA KVM_X86_CPU_FEATURE(0xD, 0, EAX, 18) #define X86_FEATURE_XSAVES KVM_X86_CPU_FEATURE(0xD, 1, EAX, 3) #define X86_FEATURE_XFD KVM_X86_CPU_FEATURE(0xD, 1, EAX, 4) +#define X86_FEATURE_XTILEDATA_XFD KVM_X86_CPU_FEATURE(0xD, 18, ECX, 2) /* * Extended Leafs, a.k.a. AMD defined diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 8e8f26d715d6..5c82d7e6f552 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -258,6 +258,7 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_AMX_TILE)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA)); + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA_XFD)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); -- GitLab From b69edab47f1da8edd8e7bfdf8c70f51a2a5d89fb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 2 Mar 2023 14:49:50 -0800 Subject: [PATCH 1296/5631] kheaders: Use array declaration instead of char Under CONFIG_FORTIFY_SOURCE, memcpy() will check the size of destination and source buffers. Defining kernel_headers_data as "char" would trip this check. Since these addresses are treated as byte arrays, define them as arrays (as done everywhere else). This was seen with: $ cat /sys/kernel/kheaders.tar.xz >> /dev/null detected buffer overflow in memcpy kernel BUG at lib/string_helpers.c:1027! ... RIP: 0010:fortify_panic+0xf/0x20 [...] Call Trace: ikheaders_read+0x45/0x50 [kheaders] kernfs_fop_read_iter+0x1a4/0x2f0 ... Reported-by: Jakub Kicinski Link: https://lore.kernel.org/bpf/20230302112130.6e402a98@kernel.org/ Acked-by: Joel Fernandes (Google) Reviewed-by: Alexander Lobakin Tested-by: Jakub Kicinski Fixes: 43d8ce9d65a5 ("Provide in-kernel headers to make extending kernel easier") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20230302224946.never.243-kees@kernel.org --- kernel/kheaders.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/kheaders.c b/kernel/kheaders.c index 8f69772af77b..42163c9e94e5 100644 --- a/kernel/kheaders.c +++ b/kernel/kheaders.c @@ -26,15 +26,15 @@ asm ( " .popsection \n" ); -extern char kernel_headers_data; -extern char kernel_headers_data_end; +extern char kernel_headers_data[]; +extern char kernel_headers_data_end[]; static ssize_t ikheaders_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { - memcpy(buf, &kernel_headers_data + off, len); + memcpy(buf, &kernel_headers_data[off], len); return len; } @@ -48,8 +48,8 @@ static struct bin_attribute kheaders_attr __ro_after_init = { static int __init ikheaders_init(void) { - kheaders_attr.size = (&kernel_headers_data_end - - &kernel_headers_data); + kheaders_attr.size = (kernel_headers_data_end - + kernel_headers_data); return sysfs_create_bin_file(kernel_kobj, &kheaders_attr); } -- GitLab From 009455205e68ef017a429dc818b92c4a84b867c4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 24 Mar 2023 10:08:14 +0100 Subject: [PATCH 1297/5631] driver core: bus: move documentation for lock_key to proper location. In commit 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure"), the lock_key variable moved out of struct bus_type and into struct subsys_private, yet the documentation for it did not move. Fix that up and place the documentation comment in the correct location. Cc: "Rafael J. Wysocki" Fixes: 37e98d9bedb5 ("driver core: bus: move lock_class_key into dynamic structure") Link: https://lore.kernel.org/r/20230324090814.386654-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 1 + include/linux/device/bus.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index a2d3a1d0fa9b..d3e081dc4b13 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -33,6 +33,7 @@ * avoid namespace conflicts * @class - pointer back to the struct class that this structure is associated * with. + * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 65a5e2c0f04d..ae10c4322754 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -65,7 +65,6 @@ struct fwnode_handle; * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU * driver implementations to a bus and allow the driver to do * bus-specific setup - * @lock_key: Lock class key for use by the lock validator * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * -- GitLab From 1acaceb1a43b86a3a8d340c37444214f4bbf0cdd Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Wed, 22 Mar 2023 19:22:50 +0500 Subject: [PATCH 1298/5631] staging: most: remove extra blank line Remove extra blank line reported by checkpatch script. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZBsPOk3TgQTfNAAK@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/dim2/dim2.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/staging/most/dim2/dim2.c b/drivers/staging/most/dim2/dim2.c index 21d1c9f24c3d..9fa665c4038f 100644 --- a/drivers/staging/most/dim2/dim2.c +++ b/drivers/staging/most/dim2/dim2.c @@ -989,7 +989,6 @@ static int rcar_gen2_enable(struct platform_device *pdev) writel(0x04, dev->io_base + 0x600); } - /* BBCR = 0b11 */ writel(0x03, dev->io_base + 0x500); writel(0x0002FF02, dev->io_base + 0x508); -- GitLab From c35cc254f34503a53d58560367a1eb4ac0a430cc Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Fri, 24 Mar 2023 00:49:44 +0500 Subject: [PATCH 1299/5631] staging: most: fix line ending with '(' in video/ Splitting function header to multiple lines because of 80 characters per line limit, results in ending the function call line with '('. This leads to CHECK reported by checkpatch.pl Move the function parameters right after the '(' in the function call line. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZBytWDocM7XbXkRx@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/video/video.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/most/video/video.c b/drivers/staging/most/video/video.c index ffa97ef21ea5..6254a5df2502 100644 --- a/drivers/staging/most/video/video.c +++ b/drivers/staging/most/video/video.c @@ -365,8 +365,7 @@ static const struct video_device comp_videodev_template = { /**************************************************************************/ -static struct most_video_dev *get_comp_dev( - struct most_interface *iface, int channel_idx) +static struct most_video_dev *get_comp_dev(struct most_interface *iface, int channel_idx) { struct most_video_dev *mdev; unsigned long flags; -- GitLab From bb75546bb630d2fccd39dfcf691a9cb73cfbc7d9 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Fri, 24 Mar 2023 00:56:11 +0500 Subject: [PATCH 1300/5631] staging: most: fix line ending with '(' in dim2/ Splitting function header to multiple lines because of 80 characters per line limit, results in ending the function call line with '('. This leads to CHECK reported by checkpatch.pl Move the function parameters right after the '(' in the function call line. Align the rest of the parameters to the opening parenthesis. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZByu29jb1mE3KOsn@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/dim2/hal.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/most/dim2/hal.c b/drivers/staging/most/dim2/hal.c index a5d40b5b138a..6abe3ab2b2cf 100644 --- a/drivers/staging/most/dim2/hal.c +++ b/drivers/staging/most/dim2/hal.c @@ -346,9 +346,8 @@ static void dim2_clear_ctram(void) dim2_clear_ctr(ctr_addr); } -static void dim2_configure_channel( - u8 ch_addr, u8 type, u8 is_tx, u16 dbr_address, u16 hw_buffer_size, - u16 packet_length) +static void dim2_configure_channel(u8 ch_addr, u8 type, u8 is_tx, u16 dbr_address, + u16 hw_buffer_size, u16 packet_length) { dim2_configure_cdt(ch_addr, dbr_address, hw_buffer_size, packet_length); dim2_configure_cat(MLB_CAT, ch_addr, type, is_tx ? 1 : 0); -- GitLab From d24927f43b9f3f3994ddf075caee531391c56559 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Wed, 22 Mar 2023 18:36:03 +0500 Subject: [PATCH 1301/5631] staging: ks7010: fix line ending with '(' Splitting function header to multiple lines because of 80 characters per line limit, results in ending the function call line with '('. This leads to CHECK reported by checkpatch.pl Move the first parameter right after the '(' in the function call line. Align the rest of the parameters to the opening parenthesis. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZBsEQzL3Oidsmg/L@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/ks7010/ks_hostif.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c index 9429ee155910..af3825578d85 100644 --- a/drivers/staging/ks7010/ks_hostif.c +++ b/drivers/staging/ks7010/ks_hostif.c @@ -75,9 +75,8 @@ static void ks_wlan_hw_wakeup_task(struct work_struct *work) if (ps_status == PS_SNOOZE) { ks_wlan_hw_wakeup_request(priv); - time_left = wait_for_completion_interruptible_timeout( - &priv->psstatus.wakeup_wait, - msecs_to_jiffies(20)); + time_left = wait_for_completion_interruptible_timeout(&priv->psstatus.wakeup_wait, + msecs_to_jiffies(20)); if (time_left <= 0) { netdev_dbg(priv->net_dev, "wake up timeout or interrupted !!!\n"); schedule_work(&priv->wakeup_work); -- GitLab From 09d0c43a094a9b86e1de22894f17cab38b1f12a2 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:14:48 +0100 Subject: [PATCH 1302/5631] staging: rtl8192e: Remove double defined constants bMaskBytex and more Remove double defined constants. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/3f31664d8751ebb8b78cbd7d019f002fb2ba4c3c.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index fd34756e450f..498da6be3e4e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -25,14 +25,6 @@ enum rf90_radio_path { RF90_PATH_MAX }; -#define bMaskByte0 0xff -#define bMaskByte1 0xff00 -#define bMaskByte2 0xff0000 -#define bMaskByte3 0xff000000 -#define bMaskHWord 0xffff0000 -#define bMaskLWord 0x0000ffff -#define bMaskDWord 0xffffffff - void rtl92e_set_bb_reg(struct net_device *dev, u32 dwRegAddr, u32 dwBitMask, u32 dwData); u32 rtl92e_get_bb_reg(struct net_device *dev, u32 dwRegAddr, u32 dwBitMask); -- GitLab From f6dcdc1b1b6f9730901fb91eb742ff50b5b5211d Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:14:53 +0100 Subject: [PATCH 1303/5631] staging: rtl8192e: Replace macro skb_tail_pointer_rsl with standard function Replace macro skb_tail_pointer_rsl with function skb_tail_pointer to increase readablility. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6885112850b48c0f9ff16655f7d9efe085ccc001.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 4 ++-- drivers/staging/rtl8192e/rtllib.h | 2 -- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 47feb4248d25..2ec47c367c5f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -1653,7 +1653,7 @@ static short _rtl92e_alloc_rx_ring(struct net_device *dev) priv->rx_buf[rx_queue_idx][i] = skb; mapping = (dma_addr_t *)skb->cb; *mapping = dma_map_single(&priv->pdev->dev, - skb_tail_pointer_rsl(skb), + skb_tail_pointer(skb), priv->rxbuffersize, DMA_FROM_DEVICE); if (dma_mapping_error(&priv->pdev->dev, *mapping)) { dev_kfree_skb_any(skb); @@ -1909,7 +1909,7 @@ static void _rtl92e_rx_normal(struct net_device *dev) priv->rx_buf[rx_queue_idx][priv->rx_idx[rx_queue_idx]] = skb; *((dma_addr_t *)skb->cb) = dma_map_single(&priv->pdev->dev, - skb_tail_pointer_rsl(skb), + skb_tail_pointer(skb), priv->rxbuffersize, DMA_FROM_DEVICE); if (dma_mapping_error(&priv->pdev->dev, *((dma_addr_t *)skb->cb))) { dev_kfree_skb_any(skb); diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 8e5e29ce8f0d..cb904fc4f574 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -62,8 +62,6 @@ #define IW_CUSTOM_MAX 256 /* In bytes */ #endif -#define skb_tail_pointer_rsl(skb) skb_tail_pointer(skb) - #define queue_delayed_work_rsl(x, y, z) queue_delayed_work(x, y, z) #define INIT_DELAYED_WORK_RSL(x, y, z) INIT_DELAYED_WORK(x, y) -- GitLab From 3443454f749d8663adfa46e018625c061c85efa4 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:00 +0100 Subject: [PATCH 1304/5631] staging: rtl8192e: Remove unused macro queue_delayed_work_rsl and more Remove unused macro queue_delayed_work_rsl and queue_work_rsl to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/3ed738a5d67a999ad42454fcb0d6668bfa706205.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index cb904fc4f574..8965bb605eaa 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -62,10 +62,8 @@ #define IW_CUSTOM_MAX 256 /* In bytes */ #endif -#define queue_delayed_work_rsl(x, y, z) queue_delayed_work(x, y, z) #define INIT_DELAYED_WORK_RSL(x, y, z) INIT_DELAYED_WORK(x, y) -#define queue_work_rsl(x, y) queue_work(x, y) #define INIT_WORK_RSL(x, y, z) INIT_WORK(x, y) #define container_of_work_rsl(x, y, z) container_of(x, y, z) -- GitLab From 9c9c9f8e3e93e09e0208413d310a0b9475c561ab Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:06 +0100 Subject: [PATCH 1305/5631] staging: rtl8192e: Replace macro INIT_DELAYED_WORK_RSL with standard macro Replace macro INIT_DELAYED_WORK_RSL with standard macro INIT_DELAYED_WORK to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/61b589012a5efb4b68a76e52eb84ad19093013b3.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 18 ++++++------------ drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 3 +-- drivers/staging/rtl8192e/rtllib.h | 2 -- drivers/staging/rtl8192e/rtllib_softmac.c | 15 +++++---------- 4 files changed, 12 insertions(+), 26 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 2ec47c367c5f..a2263c41c6c8 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -893,19 +893,13 @@ static void _rtl92e_init_priv_task(struct net_device *dev) INIT_WORK_RSL(&priv->reset_wq, (void *)_rtl92e_restart, dev); INIT_WORK_RSL(&priv->rtllib->ips_leave_wq, (void *)rtl92e_ips_leave_wq, dev); - INIT_DELAYED_WORK_RSL(&priv->watch_dog_wq, - (void *)_rtl92e_watchdog_wq_cb, dev); - INIT_DELAYED_WORK_RSL(&priv->txpower_tracking_wq, - (void *)rtl92e_dm_txpower_tracking_wq, dev); - INIT_DELAYED_WORK_RSL(&priv->rfpath_check_wq, - (void *)rtl92e_dm_rf_pathcheck_wq, dev); - INIT_DELAYED_WORK_RSL(&priv->update_beacon_wq, - (void *)_rtl92e_update_beacon, dev); + INIT_DELAYED_WORK(&priv->watch_dog_wq, (void *)_rtl92e_watchdog_wq_cb); + INIT_DELAYED_WORK(&priv->txpower_tracking_wq, (void *)rtl92e_dm_txpower_tracking_wq); + INIT_DELAYED_WORK(&priv->rfpath_check_wq, (void *)rtl92e_dm_rf_pathcheck_wq); + INIT_DELAYED_WORK(&priv->update_beacon_wq, (void *)_rtl92e_update_beacon); INIT_WORK_RSL(&priv->qos_activate, (void *)_rtl92e_qos_activate, dev); - INIT_DELAYED_WORK_RSL(&priv->rtllib->hw_wakeup_wq, - (void *)rtl92e_hw_wakeup_wq, dev); - INIT_DELAYED_WORK_RSL(&priv->rtllib->hw_sleep_wq, - (void *)rtl92e_hw_sleep_wq, dev); + INIT_DELAYED_WORK(&priv->rtllib->hw_wakeup_wq, (void *)rtl92e_hw_wakeup_wq); + INIT_DELAYED_WORK(&priv->rtllib->hw_sleep_wq, (void *)rtl92e_hw_sleep_wq); tasklet_setup(&priv->irq_rx_tasklet, _rtl92e_irq_rx_tasklet); tasklet_setup(&priv->irq_tx_tasklet, _rtl92e_irq_tx_tasklet); tasklet_setup(&priv->irq_prepare_beacon_tasklet, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index eb54f8cbee76..b745b73eedea 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -217,8 +217,7 @@ void rtl92e_dm_init(struct net_device *dev) if (IS_HARDWARE_TYPE_8192SE(dev)) _rtl92e_dm_init_wa_broadcom_iot(dev); - INIT_DELAYED_WORK_RSL(&priv->gpio_change_rf_wq, - (void *)_rtl92e_dm_check_rf_ctrl_gpio, dev); + INIT_DELAYED_WORK(&priv->gpio_change_rf_wq, (void *)_rtl92e_dm_check_rf_ctrl_gpio); } void rtl92e_dm_deinit(struct net_device *dev) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 8965bb605eaa..8cbefa6dfd6e 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -62,8 +62,6 @@ #define IW_CUSTOM_MAX 256 /* In bytes */ #endif -#define INIT_DELAYED_WORK_RSL(x, y, z) INIT_DELAYED_WORK(x, y) - #define INIT_WORK_RSL(x, y, z) INIT_WORK(x, y) #define container_of_work_rsl(x, y, z) container_of(x, y, z) diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index 4923423aa85b..c442fc98283d 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -2996,18 +2996,13 @@ int rtllib_softmac_init(struct rtllib_device *ieee) timer_setup(&ieee->beacon_timer, rtllib_send_beacon_cb, 0); - INIT_DELAYED_WORK_RSL(&ieee->link_change_wq, - (void *)rtllib_link_change_wq, ieee); - INIT_DELAYED_WORK_RSL(&ieee->start_ibss_wq, - (void *)rtllib_start_ibss_wq, ieee); + INIT_DELAYED_WORK(&ieee->link_change_wq, (void *)rtllib_link_change_wq); + INIT_DELAYED_WORK(&ieee->start_ibss_wq, (void *)rtllib_start_ibss_wq); INIT_WORK_RSL(&ieee->associate_complete_wq, (void *)rtllib_associate_complete_wq, ieee); - INIT_DELAYED_WORK_RSL(&ieee->associate_procedure_wq, - (void *)rtllib_associate_procedure_wq, ieee); - INIT_DELAYED_WORK_RSL(&ieee->softmac_scan_wq, - (void *)rtllib_softmac_scan_wq, ieee); - INIT_DELAYED_WORK_RSL(&ieee->associate_retry_wq, - (void *)rtllib_associate_retry_wq, ieee); + INIT_DELAYED_WORK(&ieee->associate_procedure_wq, (void *)rtllib_associate_procedure_wq); + INIT_DELAYED_WORK(&ieee->softmac_scan_wq, (void *)rtllib_softmac_scan_wq); + INIT_DELAYED_WORK(&ieee->associate_retry_wq, (void *)rtllib_associate_retry_wq); INIT_WORK_RSL(&ieee->wx_sync_scan_wq, (void *)rtllib_wx_sync_scan_wq, ieee); -- GitLab From 8c385e3f53d47b6a1e6add1b02afdb6ae70b27f3 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:12 +0100 Subject: [PATCH 1306/5631] staging: rtl8192e: Replace macro INIT_WORK_RSL with standard macro Replace macro INIT_WORK_RSL with standard macro INIT_WORK to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/71879ccda54d57078f47c70cdba90ae2234adc91.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 7 +++---- drivers/staging/rtl8192e/rtllib.h | 2 -- drivers/staging/rtl8192e/rtllib_softmac.c | 6 ++---- 3 files changed, 5 insertions(+), 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index a2263c41c6c8..ea07b350b62a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -890,14 +890,13 @@ static void _rtl92e_init_priv_task(struct net_device *dev) { struct r8192_priv *priv = rtllib_priv(dev); - INIT_WORK_RSL(&priv->reset_wq, (void *)_rtl92e_restart, dev); - INIT_WORK_RSL(&priv->rtllib->ips_leave_wq, (void *)rtl92e_ips_leave_wq, - dev); + INIT_WORK(&priv->reset_wq, (void *)_rtl92e_restart); + INIT_WORK(&priv->rtllib->ips_leave_wq, (void *)rtl92e_ips_leave_wq); INIT_DELAYED_WORK(&priv->watch_dog_wq, (void *)_rtl92e_watchdog_wq_cb); INIT_DELAYED_WORK(&priv->txpower_tracking_wq, (void *)rtl92e_dm_txpower_tracking_wq); INIT_DELAYED_WORK(&priv->rfpath_check_wq, (void *)rtl92e_dm_rf_pathcheck_wq); INIT_DELAYED_WORK(&priv->update_beacon_wq, (void *)_rtl92e_update_beacon); - INIT_WORK_RSL(&priv->qos_activate, (void *)_rtl92e_qos_activate, dev); + INIT_WORK(&priv->qos_activate, (void *)_rtl92e_qos_activate); INIT_DELAYED_WORK(&priv->rtllib->hw_wakeup_wq, (void *)rtl92e_hw_wakeup_wq); INIT_DELAYED_WORK(&priv->rtllib->hw_sleep_wq, (void *)rtl92e_hw_sleep_wq); tasklet_setup(&priv->irq_rx_tasklet, _rtl92e_irq_rx_tasklet); diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 8cbefa6dfd6e..aa39f8b2bf09 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -62,8 +62,6 @@ #define IW_CUSTOM_MAX 256 /* In bytes */ #endif -#define INIT_WORK_RSL(x, y, z) INIT_WORK(x, y) - #define container_of_work_rsl(x, y, z) container_of(x, y, z) #define container_of_dwork_rsl(x, y, z) \ container_of(to_delayed_work(x), y, z) diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index c442fc98283d..91fb5f150a00 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -2998,13 +2998,11 @@ int rtllib_softmac_init(struct rtllib_device *ieee) INIT_DELAYED_WORK(&ieee->link_change_wq, (void *)rtllib_link_change_wq); INIT_DELAYED_WORK(&ieee->start_ibss_wq, (void *)rtllib_start_ibss_wq); - INIT_WORK_RSL(&ieee->associate_complete_wq, - (void *)rtllib_associate_complete_wq, ieee); + INIT_WORK(&ieee->associate_complete_wq, (void *)rtllib_associate_complete_wq); INIT_DELAYED_WORK(&ieee->associate_procedure_wq, (void *)rtllib_associate_procedure_wq); INIT_DELAYED_WORK(&ieee->softmac_scan_wq, (void *)rtllib_softmac_scan_wq); INIT_DELAYED_WORK(&ieee->associate_retry_wq, (void *)rtllib_associate_retry_wq); - INIT_WORK_RSL(&ieee->wx_sync_scan_wq, (void *)rtllib_wx_sync_scan_wq, - ieee); + INIT_WORK(&ieee->wx_sync_scan_wq, (void *)rtllib_wx_sync_scan_wq); mutex_init(&ieee->wx_mutex); mutex_init(&ieee->scan_mutex); -- GitLab From 861a6a82b37516fbcefc60ba967c017e9f0f42fb Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:18 +0100 Subject: [PATCH 1307/5631] staging: rtl8192e: Replace macro container_of_work_rsl with standard macro Replace macro container_of_work_rsl with standard macro container_of to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/d75688b6f884c526f6046fac522b8ed87db1ca2f.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 9 +++------ drivers/staging/rtl8192e/rtl8192e/rtl_ps.c | 3 +-- drivers/staging/rtl8192e/rtllib.h | 1 - drivers/staging/rtl8192e/rtllib_softmac.c | 2 +- drivers/staging/rtl8192e/rtllib_softmac_wx.c | 3 +-- 5 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index ea07b350b62a..3244aef12c05 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -311,8 +311,7 @@ static const struct rtllib_qos_parameters def_qos_parameters = { static void _rtl92e_update_beacon(void *data) { - struct r8192_priv *priv = container_of_work_rsl(data, struct r8192_priv, - update_beacon_wq.work); + struct r8192_priv *priv = container_of(data, struct r8192_priv, update_beacon_wq.work); struct net_device *dev = priv->rtllib->dev; struct rtllib_device *ieee = priv->rtllib; struct rtllib_network *net = &ieee->current_network; @@ -326,8 +325,7 @@ static void _rtl92e_update_beacon(void *data) static void _rtl92e_qos_activate(void *data) { - struct r8192_priv *priv = container_of_work_rsl(data, struct r8192_priv, - qos_activate); + struct r8192_priv *priv = container_of(data, struct r8192_priv, qos_activate); struct net_device *dev = priv->rtllib->dev; int i; @@ -2033,8 +2031,7 @@ void rtl92e_commit(struct net_device *dev) static void _rtl92e_restart(void *data) { - struct r8192_priv *priv = container_of_work_rsl(data, struct r8192_priv, - reset_wq); + struct r8192_priv *priv = container_of(data, struct r8192_priv, reset_wq); struct net_device *dev = priv->rtllib->dev; mutex_lock(&priv->wx_mutex); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_ps.c b/drivers/staging/rtl8192e/rtl8192e/rtl_ps.c index ef4f736ce325..5a1cd22f5e25 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_ps.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_ps.c @@ -142,8 +142,7 @@ void rtl92e_ips_leave(struct net_device *dev) void rtl92e_ips_leave_wq(void *data) { - struct rtllib_device *ieee = container_of_work_rsl(data, - struct rtllib_device, ips_leave_wq); + struct rtllib_device *ieee = container_of(data, struct rtllib_device, ips_leave_wq); struct net_device *dev = ieee->dev; struct r8192_priv *priv = (struct r8192_priv *)rtllib_priv(dev); diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index aa39f8b2bf09..669a9d9a5d18 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -62,7 +62,6 @@ #define IW_CUSTOM_MAX 256 /* In bytes */ #endif -#define container_of_work_rsl(x, y, z) container_of(x, y, z) #define container_of_dwork_rsl(x, y, z) \ container_of(to_delayed_work(x), y, z) diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index 91fb5f150a00..b9886e83a6dc 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -1498,7 +1498,7 @@ static void rtllib_associate_step2(struct rtllib_device *ieee) static void rtllib_associate_complete_wq(void *data) { struct rtllib_device *ieee = (struct rtllib_device *) - container_of_work_rsl(data, + container_of(data, struct rtllib_device, associate_complete_wq); struct rt_pwr_save_ctrl *psc = &ieee->pwr_save_ctrl; diff --git a/drivers/staging/rtl8192e/rtllib_softmac_wx.c b/drivers/staging/rtl8192e/rtllib_softmac_wx.c index 06f1d6de5cc7..1f2fa711e60b 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac_wx.c +++ b/drivers/staging/rtl8192e/rtllib_softmac_wx.c @@ -326,8 +326,7 @@ EXPORT_SYMBOL(rtllib_wx_set_mode); void rtllib_wx_sync_scan_wq(void *data) { - struct rtllib_device *ieee = container_of_work_rsl(data, - struct rtllib_device, wx_sync_scan_wq); + struct rtllib_device *ieee = container_of(data, struct rtllib_device, wx_sync_scan_wq); short chan; enum ht_extchnl_offset chan_offset = 0; enum ht_channel_width bandwidth = 0; -- GitLab From 27e99d0327c26edb287b28ab11d46de710a65c3e Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:24 +0100 Subject: [PATCH 1308/5631] staging: rtl8192e: Replace macro iwe_stream_add_event_rsl with standard function Replace macro iwe_stream_add_event_rsl with standard function iwe_stream_add_event to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/00a8057acc994c139530a070974694b999a8f96a.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 3 --- drivers/staging/rtl8192e/rtllib_wx.c | 16 ++++++---------- 2 files changed, 6 insertions(+), 13 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 669a9d9a5d18..81d630cf7e52 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -65,9 +65,6 @@ #define container_of_dwork_rsl(x, y, z) \ container_of(to_delayed_work(x), y, z) -#define iwe_stream_add_event_rsl(info, start, stop, iwe, len) \ - iwe_stream_add_event(info, start, stop, iwe, len) - #define iwe_stream_add_point_rsl(info, start, stop, iwe, p) \ iwe_stream_add_point(info, start, stop, iwe, p) diff --git a/drivers/staging/rtl8192e/rtllib_wx.c b/drivers/staging/rtl8192e/rtllib_wx.c index 217426ee2e92..e580cd01c201 100644 --- a/drivers/staging/rtl8192e/rtllib_wx.c +++ b/drivers/staging/rtl8192e/rtllib_wx.c @@ -41,8 +41,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.cmd = SIOCGIWAP; iwe.u.ap_addr.sa_family = ARPHRD_ETHER; ether_addr_copy(iwe.u.ap_addr.sa_data, network->bssid); - start = iwe_stream_add_event_rsl(info, start, stop, - &iwe, IW_EV_ADDR_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_ADDR_LEN); /* Remaining entries will be displayed in the order we provide them */ /* Add the ESSID */ @@ -71,8 +70,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, } *pname = '\0'; snprintf(iwe.u.name, IFNAMSIZ, "IEEE802.11%s", proto_name); - start = iwe_stream_add_event_rsl(info, start, stop, - &iwe, IW_EV_CHAR_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_CHAR_LEN); /* Add mode */ iwe.cmd = SIOCGIWMODE; if (network->capability & @@ -81,8 +79,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.u.mode = IW_MODE_MASTER; else iwe.u.mode = IW_MODE_ADHOC; - start = iwe_stream_add_event_rsl(info, start, stop, - &iwe, IW_EV_UINT_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_UINT_LEN); } /* Add frequency/channel */ @@ -90,8 +87,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.u.freq.m = network->channel; iwe.u.freq.e = 0; iwe.u.freq.i = 0; - start = iwe_stream_add_event_rsl(info, start, stop, &iwe, - IW_EV_FREQ_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_FREQ_LEN); /* Add encryption capability */ iwe.cmd = SIOCGIWENCODE; @@ -152,7 +148,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.u.bitrate.disabled = 0; iwe.u.bitrate.fixed = 0; iwe.u.bitrate.value = max_rate * 500000; - start = iwe_stream_add_event_rsl(info, start, stop, &iwe, IW_EV_PARAM_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_PARAM_LEN); iwe.cmd = IWEVCUSTOM; iwe.u.data.length = p - custom; if (iwe.u.data.length) @@ -172,7 +168,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, if (!(network->stats.mask & RTLLIB_STATMASK_SIGNAL)) iwe.u.qual.updated |= IW_QUAL_QUAL_INVALID; iwe.u.qual.updated = 7; - start = iwe_stream_add_event_rsl(info, start, stop, &iwe, IW_EV_QUAL_LEN); + start = iwe_stream_add_event(info, start, stop, &iwe, IW_EV_QUAL_LEN); iwe.cmd = IWEVCUSTOM; p = custom; -- GitLab From 4f3db2e2a97bb04e49cf2840dcde8a813b2ece2a Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Wed, 22 Mar 2023 18:15:32 +0100 Subject: [PATCH 1309/5631] staging: rtl8192e: Replace macro iwe_stream_add_point_rsl with standard function Replace macro iwe_stream_add_point_rsl with standard function iwe_stream_add_point to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/563af664b3186e73d99f73a6396f8ebcd3c52be2.1679504314.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 3 --- drivers/staging/rtl8192e/rtllib_wx.c | 26 ++++++++++---------------- 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 81d630cf7e52..1ce4c29dab13 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -65,9 +65,6 @@ #define container_of_dwork_rsl(x, y, z) \ container_of(to_delayed_work(x), y, z) -#define iwe_stream_add_point_rsl(info, start, stop, iwe, p) \ - iwe_stream_add_point(info, start, stop, iwe, p) - static inline void *netdev_priv_rsl(struct net_device *dev) { return netdev_priv(dev); diff --git a/drivers/staging/rtl8192e/rtllib_wx.c b/drivers/staging/rtl8192e/rtllib_wx.c index e580cd01c201..d6691f3c7c70 100644 --- a/drivers/staging/rtl8192e/rtllib_wx.c +++ b/drivers/staging/rtl8192e/rtllib_wx.c @@ -49,16 +49,13 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.u.data.flags = 1; if (network->ssid_len > 0) { iwe.u.data.length = min_t(u8, network->ssid_len, 32); - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, - network->ssid); + start = iwe_stream_add_point(info, start, stop, &iwe, network->ssid); } else if (network->hidden_ssid_len == 0) { iwe.u.data.length = sizeof(""); - start = iwe_stream_add_point_rsl(info, start, stop, - &iwe, ""); + start = iwe_stream_add_point(info, start, stop, &iwe, ""); } else { iwe.u.data.length = min_t(u8, network->hidden_ssid_len, 32); - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, - network->hidden_ssid); + start = iwe_stream_add_point(info, start, stop, &iwe, network->hidden_ssid); } /* Add the protocol name */ iwe.cmd = SIOCGIWNAME; @@ -96,8 +93,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, else iwe.u.data.flags = IW_ENCODE_DISABLED; iwe.u.data.length = 0; - start = iwe_stream_add_point_rsl(info, start, stop, - &iwe, network->ssid); + start = iwe_stream_add_point(info, start, stop, &iwe, network->ssid); /* Add basic and extended rates */ max_rate = 0; p = custom; @@ -152,8 +148,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, iwe.cmd = IWEVCUSTOM; iwe.u.data.length = p - custom; if (iwe.u.data.length) - start = iwe_stream_add_point_rsl(info, start, stop, - &iwe, custom); + start = iwe_stream_add_point(info, start, stop, &iwe, custom); /* Add quality statistics */ /* TODO: Fix these values... */ iwe.cmd = IWEVQUAL; @@ -174,7 +169,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, p = custom; iwe.u.data.length = p - custom; if (iwe.u.data.length) - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, custom); + start = iwe_stream_add_point(info, start, stop, &iwe, custom); memset(&iwe, 0, sizeof(iwe)); if (network->wpa_ie_len) { @@ -183,7 +178,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, memcpy(buf, network->wpa_ie, network->wpa_ie_len); iwe.cmd = IWEVGENIE; iwe.u.data.length = network->wpa_ie_len; - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, buf); + start = iwe_stream_add_point(info, start, stop, &iwe, buf); } memset(&iwe, 0, sizeof(iwe)); if (network->rsn_ie_len) { @@ -192,7 +187,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, memcpy(buf, network->rsn_ie, network->rsn_ie_len); iwe.cmd = IWEVGENIE; iwe.u.data.length = network->rsn_ie_len; - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, buf); + start = iwe_stream_add_point(info, start, stop, &iwe, buf); } /* add info for WZC */ @@ -203,7 +198,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, memcpy(buf, network->wzc_ie, network->wzc_ie_len); iwe.cmd = IWEVGENIE; iwe.u.data.length = network->wzc_ie_len; - start = iwe_stream_add_point_rsl(info, start, stop, &iwe, buf); + start = iwe_stream_add_point(info, start, stop, &iwe, buf); } /* Add EXTRA: Age to display seconds since last beacon/probe response @@ -216,8 +211,7 @@ static inline char *rtl819x_translate_scan(struct rtllib_device *ieee, (100 * (jiffies - network->last_scanned)) / HZ); iwe.u.data.length = p - custom; if (iwe.u.data.length) - start = iwe_stream_add_point_rsl(info, start, stop, - &iwe, custom); + start = iwe_stream_add_point(info, start, stop, &iwe, custom); return start; } -- GitLab From 6bfafec3faf7ab20d72bb2063058591e55b68f8e Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Thu, 23 Mar 2023 12:59:31 -0400 Subject: [PATCH 1310/5631] staging: rtl8192u: remove unused ieee80211_SignalStrengthTranslate function clang with W=1 reports drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c:1961:18: error: unused function 'ieee80211_SignalStrengthTranslate' [-Werror,-Wunused-function] static inline u8 ieee80211_SignalStrengthTranslate( ^ This function is not used so remove it. It may have been used in the past but that has been commented out. Also remove the comment. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230323165931.2634587-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192u/ieee80211/ieee80211_rx.c | 38 ------------------- 1 file changed, 38 deletions(-) diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c index 5c73e3f8541a..ca09367005e1 100644 --- a/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c +++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_rx.c @@ -1958,43 +1958,6 @@ int ieee80211_parse_info_param(struct ieee80211_device *ieee, return 0; } -static inline u8 ieee80211_SignalStrengthTranslate( - u8 CurrSS - ) -{ - u8 RetSS; - - // Step 1. Scale mapping. - if (CurrSS >= 71 && CurrSS <= 100) { - RetSS = 90 + ((CurrSS - 70) / 3); - } else if (CurrSS >= 41 && CurrSS <= 70) { - RetSS = 78 + ((CurrSS - 40) / 3); - } else if (CurrSS >= 31 && CurrSS <= 40) { - RetSS = 66 + (CurrSS - 30); - } else if (CurrSS >= 21 && CurrSS <= 30) { - RetSS = 54 + (CurrSS - 20); - } else if (CurrSS >= 5 && CurrSS <= 20) { - RetSS = 42 + (((CurrSS - 5) * 2) / 3); - } else if (CurrSS == 4) { - RetSS = 36; - } else if (CurrSS == 3) { - RetSS = 27; - } else if (CurrSS == 2) { - RetSS = 18; - } else if (CurrSS == 1) { - RetSS = 9; - } else { - RetSS = CurrSS; - } - //RT_TRACE(COMP_DBG, DBG_LOUD, ("##### After Mapping: LastSS: %d, CurrSS: %d, RetSS: %d\n", LastSS, CurrSS, RetSS)); - - // Step 2. Smoothing. - - //RT_TRACE(COMP_DBG, DBG_LOUD, ("$$$$$ After Smoothing: LastSS: %d, CurrSS: %d, RetSS: %d\n", LastSS, CurrSS, RetSS)); - - return RetSS; -} - /* 0-100 index */ static long ieee80211_translate_todbm(u8 signal_strength_index) { @@ -2095,7 +2058,6 @@ static inline int ieee80211_network_init( network->flags |= NETWORK_EMPTY_ESSID; stats->signal = 30 + (stats->SignalStrength * 70) / 100; - //stats->signal = ieee80211_SignalStrengthTranslate(stats->signal); stats->noise = ieee80211_translate_todbm((u8)(100 - stats->signal)) - 25; memcpy(&network->stats, stats, sizeof(network->stats)); -- GitLab From 336af4bb239a7c95657e6e83784cf3e5e4a44c3e Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sat, 25 Mar 2023 03:31:28 +0500 Subject: [PATCH 1311/5631] staging: rtl8192e: remove extra blank lines Remove the extra blank line in accordance with the Linux kernel coding-style regulations. These issues were reported by checkpatch.pl "CHECK: Please don't use multiple blank lines" Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/6d7388f944e8296227269c7472a462ea7c94149c.1679696777.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index c394c21beefb..c6114d99829b 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -154,7 +154,6 @@ rtllib_frag_cache_get(struct rtllib_device *ieee, return skb; } - /* Called only as a tasklet (software IRQ) */ static int rtllib_frag_cache_invalidate(struct rtllib_device *ieee, struct rtllib_hdr_4addr *hdr) @@ -318,7 +317,6 @@ rtllib_rx_frame_decrypt(struct rtllib_device *ieee, struct sk_buff *skb, return res; } - /* Called only as a tasklet (software IRQ), by rtllib_rx */ static inline int rtllib_rx_frame_decrypt_msdu(struct rtllib_device *ieee, struct sk_buff *skb, @@ -355,7 +353,6 @@ rtllib_rx_frame_decrypt_msdu(struct rtllib_device *ieee, struct sk_buff *skb, return 0; } - /* this function is stolen from ipw2200 driver*/ #define IEEE_PACKET_RETRY_TIME (5*HZ) static int is_duplicate_packet(struct rtllib_device *ieee, @@ -887,7 +884,6 @@ static u8 parse_subframe(struct rtllib_device *ieee, struct sk_buff *skb, return rxb->nr_subframes; } - static size_t rtllib_rx_get_hdrlen(struct rtllib_device *ieee, struct sk_buff *skb, struct rtllib_rx_stats *rx_stats) @@ -1569,7 +1565,6 @@ static int rtllib_verify_qos_info(struct rtllib_qos_information_element return 0; } - /* Parse a QoS parameter element */ static int rtllib_read_qos_param_element( struct rtllib_qos_parameter_info *element_param, @@ -1599,7 +1594,6 @@ static int rtllib_read_qos_info_element( return rtllib_verify_qos_info(element_info, QOS_OUI_INFO_SUB_TYPE); } - /* Write QoS parameters from the ac parameters. */ static int rtllib_qos_convert_ac_to_parameters(struct rtllib_qos_parameter_info *param_elm, struct rtllib_qos_data *qos_data) @@ -1843,7 +1837,6 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee, } } - if (*tmp_htinfo_len == 0) { if (info_element->len >= 4 && info_element->data[0] == 0x00 && @@ -1932,7 +1925,6 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee, info_element->data[2] == 0x96) network->cisco_cap_exist = true; - if (info_element->len >= 3 && info_element->data[0] == 0x00 && info_element->data[1] == 0x0a && @@ -2142,13 +2134,11 @@ int rtllib_parse_info_param(struct rtllib_device *ieee, network->dtim_data = RTLLIB_DTIM_VALID; - if (info_element->data[2] & 1) network->dtim_data |= RTLLIB_DTIM_MBCAST; offset = (info_element->data[2] >> 1)*2; - if (ieee->assoc_id < 8*offset || ieee->assoc_id > 8*(offset + info_element->len - 3)) break; @@ -2203,7 +2193,6 @@ int rtllib_parse_info_param(struct rtllib_device *ieee, &tmp_htcap_len); break; - case MFIE_TYPE_HT_INFO: netdev_dbg(ieee->dev, "MFIE_TYPE_HT_INFO: %d bytes\n", info_element->len); @@ -2392,7 +2381,6 @@ static inline int is_same_network(struct rtllib_network *src, (dst->capability & WLAN_CAPABILITY_ESS))); } - static inline void update_network(struct rtllib_device *ieee, struct rtllib_network *dst, struct rtllib_network *src) @@ -2580,7 +2568,6 @@ static inline void rtllib_process_probe_response( goto free_network; } - if (!rtllib_legal_channel(ieee, network->channel)) goto free_network; -- GitLab From 6ca4e57aade709dd4d918c4d385330fcd0b08b11 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sat, 25 Mar 2023 03:31:29 +0500 Subject: [PATCH 1312/5631] staging: rtl8192e: add blank lines after declarations Add blank lines after declarations to adhere to the Linux kernel coding-style guidelines. These issues are reported by checkpatch.pl "CHECK: Please use a blank line after function/struct/union/enum declarations" Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/d8a5e738046ffdc1b257e1935eacb8e16af34d5e.1679696777.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index c6114d99829b..7144a0630ea6 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -231,10 +231,12 @@ rtllib_rx_frame_mgmt(struct rtllib_device *ieee, struct sk_buff *skb, static unsigned char rfc1042_header[] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; + /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ static unsigned char bridge_tunnel_header[] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; + /* No encapsulation header if EtherType < 0x600 (=length) */ /* Called by rtllib_rx_frame_decrypt */ -- GitLab From 2ac74cf1fc0508486d5fb7d88d24eae924eae6e9 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sat, 25 Mar 2023 03:31:30 +0500 Subject: [PATCH 1313/5631] staging: rtl8192e: add spaces around binary operators Use spaces around binary operators as suggested by Linux kernel coding style guidelines. Issues reported by checkpatch.pl for the following binary operators: + , - , * , | , << Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/44a545cf8e99ebfdbfc3f5bb314f3828abe98558.1679696777.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 54 ++++++++++++++-------------- 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 7144a0630ea6..f627dfe66d90 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -356,7 +356,7 @@ rtllib_rx_frame_decrypt_msdu(struct rtllib_device *ieee, struct sk_buff *skb, } /* this function is stolen from ipw2200 driver*/ -#define IEEE_PACKET_RETRY_TIME (5*HZ) +#define IEEE_PACKET_RETRY_TIME (5 * HZ) static int is_duplicate_packet(struct rtllib_device *ieee, struct rtllib_hdr_4addr *header) { @@ -936,7 +936,7 @@ static int rtllib_rx_check_duplicate(struct rtllib_device *ieee, if (GetTs(ieee, (struct ts_common_info **)&pRxTS, hdr->addr2, (u8)Frame_QoSTID((u8 *)(skb->data)), RX_DIR, true)) { - if ((fc & (1<<11)) && (frag == pRxTS->rx_last_frag_num) && + if ((fc & (1 << 11)) && (frag == pRxTS->rx_last_frag_num) && (WLAN_GET_SEQ_SEQ(sc) == pRxTS->rx_last_seq_num)) return -1; pRxTS->rx_last_frag_num = frag; @@ -1619,23 +1619,23 @@ static int rtllib_qos_convert_ac_to_parameters(struct rtllib_qos_parameter_info case 1: /* BIT(0) | BIT(3) */ if (acm) - qos_data->wmm_acm |= (0x01<<0)|(0x01<<3); + qos_data->wmm_acm |= (0x01 << 0) | (0x01 << 3); break; case 2: /* BIT(4) | BIT(5) */ if (acm) - qos_data->wmm_acm |= (0x01<<4)|(0x01<<5); + qos_data->wmm_acm |= (0x01 << 4) | (0x01 << 5); break; case 3: /* BIT(6) | BIT(7) */ if (acm) - qos_data->wmm_acm |= (0x01<<6)|(0x01<<7); + qos_data->wmm_acm |= (0x01 << 6) | (0x01 << 7); break; case 0: default: /* BIT(1) | BIT(2) */ if (acm) - qos_data->wmm_acm |= (0x01<<1)|(0x01<<2); + qos_data->wmm_acm |= (0x01 << 1) | (0x01 << 2); break; } @@ -1979,7 +1979,7 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee, info_element->data[3] == 0x04) { netdev_dbg(ieee->dev, "MFIE_TYPE_WZC: %d bytes\n", info_element->len); - network->wzc_ie_len = min(info_element->len+2, MAX_WZC_IE_LEN); + network->wzc_ie_len = min(info_element->len + 2, MAX_WZC_IE_LEN); memcpy(network->wzc_ie, info_element, network->wzc_ie_len); } } @@ -2139,10 +2139,10 @@ int rtllib_parse_info_param(struct rtllib_device *ieee, if (info_element->data[2] & 1) network->dtim_data |= RTLLIB_DTIM_MBCAST; - offset = (info_element->data[2] >> 1)*2; + offset = (info_element->data[2] >> 1) * 2; - if (ieee->assoc_id < 8*offset || - ieee->assoc_id > 8*(offset + info_element->len - 3)) + if (ieee->assoc_id < 8 * offset || + ieee->assoc_id > 8 * (offset + info_element->len - 3)) break; offset = (ieee->assoc_id / 8) - offset; @@ -2357,7 +2357,7 @@ static inline int rtllib_network_init( if (rtllib_is_empty_essid(network->ssid, network->ssid_len)) network->flags |= NETWORK_EMPTY_ESSID; stats->signal = 30 + (stats->SignalStrength * 70) / 100; - stats->noise = rtllib_translate_todbm((u8)(100-stats->signal)) - 25; + stats->noise = rtllib_translate_todbm((u8)(100 - stats->signal)) - 25; memcpy(&network->stats, stats, sizeof(network->stats)); @@ -2545,22 +2545,22 @@ static inline void rtllib_process_probe_response( "'%s' ( %pM ): %c%c%c%c %c%c%c%c-%c%c%c%c %c%c%c%c\n", escape_essid(info_element->data, info_element->len), beacon->header.addr3, - (le16_to_cpu(beacon->capability) & (1<<0xf)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0xe)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0xd)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0xc)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0xb)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0xa)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x9)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x8)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x7)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x6)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x5)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x4)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x3)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x2)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x1)) ? '1' : '0', - (le16_to_cpu(beacon->capability) & (1<<0x0)) ? '1' : '0'); + (le16_to_cpu(beacon->capability) & (1 << 0xf)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0xe)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0xd)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0xc)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0xb)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0xa)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x9)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x8)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x7)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x6)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x5)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x4)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x3)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x2)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x1)) ? '1' : '0', + (le16_to_cpu(beacon->capability) & (1 << 0x0)) ? '1' : '0'); if (rtllib_network_init(ieee, beacon, network, stats)) { netdev_dbg(ieee->dev, "Dropped '%s' ( %pM) via %s.\n", -- GitLab From 6e1ce577876250dbbfa95caaad9e51826f452166 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sat, 25 Mar 2023 03:31:31 +0500 Subject: [PATCH 1314/5631] staging: rtl8192e: remove blank lines after '{' Remove unnecessary blank lines after an open brace to adhere to the Linux kernel coding-style guidelines. These issues are reported by checkpatch.pl "CHECK: Blank lines aren't necessary after an open brace '{'" Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/e7cd8152e6986d361f81289868040889224bd1bf.1679696777.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_rx.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index f627dfe66d90..b649d02dc5c8 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -1167,7 +1167,6 @@ static int rtllib_rx_decrypt(struct rtllib_device *ieee, struct sk_buff *skb, if (crypt && !(fc & RTLLIB_FCTL_WEP) && !ieee->open_wep) { if (/*ieee->ieee802_1x &&*/ rtllib_is_eapol_frame(ieee, skb, hdrlen)) { - /* pass unencrypted EAPOL frames even if encryption is * configured */ @@ -1207,7 +1206,6 @@ static void rtllib_rx_check_leave_lps(struct rtllib_device *ieee, u8 unicast, u8 nr_subframes) { if (unicast) { - if (ieee->state == RTLLIB_LINKED) { if (((ieee->link_detect_info.NumRxUnicastOkInPeriod + ieee->link_detect_info.NumTxOkInPeriod) > 8) || @@ -1552,7 +1550,6 @@ static u8 qos_oui[QOS_OUI_LEN] = { 0x00, 0x50, 0xF2 }; static int rtllib_verify_qos_info(struct rtllib_qos_information_element *info_element, int sub_type) { - if (info_element->elementID != QOS_ELEMENT_ID) return -1; if (info_element->qui_subtype != sub_type) @@ -2696,7 +2693,6 @@ static void rtllib_rx_mgt(struct rtllib_device *ieee, ieee->last_rx_ps_time = jiffies; switch (WLAN_FC_GET_STYPE(le16_to_cpu(header->frame_ctl))) { - case RTLLIB_STYPE_BEACON: netdev_dbg(ieee->dev, "received BEACON (%d)\n", WLAN_FC_GET_STYPE(le16_to_cpu(header->frame_ctl))); -- GitLab From fe730bfda640bc7b64f458bb35007225b640bcb0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:35:13 +0100 Subject: [PATCH 1315/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_phy_rf_read priv->rf_chip is initialized to RF_8256 and never changed. Remove conditions in function _rtl92e_phy_rf_read as those are dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/c3b2e2a41cc450c1cb9ac41b8ed19b090d9627a6.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 43 ++++++++----------- 1 file changed, 18 insertions(+), 25 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 2dbddf4ae3d6..c4fd412cf3d6 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -82,24 +82,20 @@ static u32 _rtl92e_phy_rf_read(struct net_device *dev, Offset &= 0x3f; - if (priv->rf_chip == RF_8256) { - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0xf00, 0x0); - if (Offset >= 31) { - priv->rf_reg_0value[eRFPath] |= 0x140; - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, - bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); - NewOffset = Offset - 30; - } else if (Offset >= 16) { - priv->rf_reg_0value[eRFPath] |= 0x100; - priv->rf_reg_0value[eRFPath] &= (~0x40); - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, - bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); - - NewOffset = Offset - 15; - } else - NewOffset = Offset; + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0xf00, 0x0); + if (Offset >= 31) { + priv->rf_reg_0value[eRFPath] |= 0x140; + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, + bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); + NewOffset = Offset - 30; + } else if (Offset >= 16) { + priv->rf_reg_0value[eRFPath] |= 0x100; + priv->rf_reg_0value[eRFPath] &= (~0x40); + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, + bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); + NewOffset = Offset - 15; } else { NewOffset = Offset; } @@ -113,15 +109,12 @@ static u32 _rtl92e_phy_rf_read(struct net_device *dev, ret = rtl92e_get_bb_reg(dev, pPhyReg->rfLSSIReadBack, bLSSIReadBackData); - if (priv->rf_chip == RF_8256) { - priv->rf_reg_0value[eRFPath] &= 0xebf; - - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); + priv->rf_reg_0value[eRFPath] &= 0xebf; - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0x300, 0x3); - } + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0x300, 0x3); return ret; -- GitLab From 1200384754b6ecce28e075efd256cfd654a91d04 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:35:28 +0100 Subject: [PATCH 1316/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_phy_rf_write priv->rf_chip is initialized to RF_8256 and never changed. Remove conditions in function _rtl92e_phy_rf_write as those are dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/77628b7ecade212401d7da5e3c0b79f8ef55b5c1.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 46 +++++++++---------- 1 file changed, 21 insertions(+), 25 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index c4fd412cf3d6..acd1e1869d78 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -129,24 +129,22 @@ static void _rtl92e_phy_rf_write(struct net_device *dev, struct bb_reg_definition *pPhyReg = &priv->phy_reg_def[eRFPath]; Offset &= 0x3f; - if (priv->rf_chip == RF_8256) { - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0xf00, 0x0); - if (Offset >= 31) { - priv->rf_reg_0value[eRFPath] |= 0x140; - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, - bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); - NewOffset = Offset - 30; - } else if (Offset >= 16) { - priv->rf_reg_0value[eRFPath] |= 0x100; - priv->rf_reg_0value[eRFPath] &= (~0x40); - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, - bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); - NewOffset = Offset - 15; - } else - NewOffset = Offset; + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0xf00, 0x0); + + if (Offset >= 31) { + priv->rf_reg_0value[eRFPath] |= 0x140; + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, + bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); + NewOffset = Offset - 30; + } else if (Offset >= 16) { + priv->rf_reg_0value[eRFPath] |= 0x100; + priv->rf_reg_0value[eRFPath] &= (~0x40); + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, + bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); + NewOffset = Offset - 15; } else { NewOffset = Offset; } @@ -158,15 +156,13 @@ static void _rtl92e_phy_rf_write(struct net_device *dev, if (Offset == 0x0) priv->rf_reg_0value[eRFPath] = Data; - if (priv->rf_chip == RF_8256) { - if (Offset != 0) { - priv->rf_reg_0value[eRFPath] &= 0xebf; - rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, - bMaskDWord, - (priv->rf_reg_0value[eRFPath] << 16)); - } - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0x300, 0x3); + if (Offset != 0) { + priv->rf_reg_0value[eRFPath] &= 0xebf; + rtl92e_set_bb_reg(dev, pPhyReg->rf3wireOffset, + bMaskDWord, + (priv->rf_reg_0value[eRFPath] << 16)); } + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, 0x300, 0x3); } void rtl92e_set_rf_reg(struct net_device *dev, enum rf90_radio_path eRFPath, -- GitLab From 846fc62b9c3a1d322f3d7cd988aef5c9d88aa613 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:35:45 +0100 Subject: [PATCH 1317/5631] staging: rtl8192e: Remove priv->rf_chip in rtl92e_set_tx_power priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function rtl92e_set_tx_power as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/190d0a77602cb89bc24512c99b72f25f4ca5d5e2.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index acd1e1869d78..6579c7b81bfd 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -485,19 +485,8 @@ void rtl92e_set_tx_power(struct net_device *dev, u8 channel) powerlevelOFDM24G = priv->tx_pwr_level_ofdm_24g[channel - 1]; } - switch (priv->rf_chip) { - case RF_8225: - break; - case RF_8256: - rtl92e_set_cck_tx_power(dev, powerlevel); - rtl92e_set_ofdm_tx_power(dev, powerlevelOFDM24G); - break; - case RF_8258: - break; - default: - netdev_err(dev, "Invalid RF Chip ID.\n"); - break; - } + rtl92e_set_cck_tx_power(dev, powerlevel); + rtl92e_set_ofdm_tx_power(dev, powerlevelOFDM24G); } bool rtl92e_config_phy(struct net_device *dev) -- GitLab From ade42a46b293436433a10de77003afa205d7dde5 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:00 +0100 Subject: [PATCH 1318/5631] staging: rtl8192e: Remove priv->rf_chip in rtl92e_config_phy priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function rtl92e_config_phy as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/c0d4e98308c9198776d8d04d1c2910f089f45a90.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 6579c7b81bfd..e35085253e70 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -491,25 +491,10 @@ void rtl92e_set_tx_power(struct net_device *dev, u8 channel) bool rtl92e_config_phy(struct net_device *dev) { - struct r8192_priv *priv = rtllib_priv(dev); bool rtStatus = true; - switch (priv->rf_chip) { - case RF_8225: - break; - case RF_8256: - rtStatus = rtl92e_config_rf(dev); - break; - - case RF_8258: - break; - case RF_PSEUDO_11N: - break; + rtStatus = rtl92e_config_rf(dev); - default: - netdev_err(dev, "Invalid RF Chip ID.\n"); - break; - } return rtStatus; } -- GitLab From 592630558d93a6416987e48a56ec41233fa9bd0b Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:13 +0100 Subject: [PATCH 1319/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_set_tx_power_level priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function _rtl92e_set_tx_power_level as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/465a789243287c1420fdce68f9a861784a164140.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index e35085253e70..b528b8ab4b2b 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -542,21 +542,8 @@ static void _rtl92e_set_tx_power_level(struct net_device *dev, u8 channel) u8 powerlevel = priv->tx_pwr_level_cck[channel - 1]; u8 powerlevelOFDM24G = priv->tx_pwr_level_ofdm_24g[channel - 1]; - switch (priv->rf_chip) { - case RF_8225: - break; - - case RF_8256: - rtl92e_set_cck_tx_power(dev, powerlevel); - rtl92e_set_ofdm_tx_power(dev, powerlevelOFDM24G); - break; - - case RF_8258: - break; - default: - netdev_warn(dev, "%s(): Invalid RF Chip ID\n", __func__); - break; - } + rtl92e_set_cck_tx_power(dev, powerlevel); + rtl92e_set_ofdm_tx_power(dev, powerlevelOFDM24G); } static u8 _rtl92e_phy_set_sw_chnl_cmd_array(struct net_device *dev, -- GitLab From 0c0b33680ad2e21819786f817ed22c2bc1801601 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:23 +0100 Subject: [PATCH 1320/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_phy_switch_channel_step priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function _rtl92e_phy_switch_channel_step as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/1b9e10de4f539aa24150275c80ec4bbd925c853d.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 83 ++++--------------- 1 file changed, 16 insertions(+), 67 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index b528b8ab4b2b..73e426e052b0 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -14,24 +14,6 @@ #include "table.h" -static u32 RF_CHANNEL_TABLE_ZEBRA[] = { - 0, - 0x085c, - 0x08dc, - 0x095c, - 0x09dc, - 0x0a5c, - 0x0adc, - 0x0b5c, - 0x0bdc, - 0x0c5c, - 0x0cdc, - 0x0d5c, - 0x0ddc, - 0x0e5c, - 0x0f72, -}; - /*************************Define local function prototype**********************/ static u32 _rtl92e_phy_rf_fw_read(struct net_device *dev, @@ -608,58 +590,25 @@ static u8 _rtl92e_phy_switch_channel_step(struct net_device *dev, u8 channel, 0, 0, 0); RfDependCmdCnt = 0; - switch (priv->rf_chip) { - case RF_8225: - if (!(channel >= 1 && channel <= 14)) { - netdev_err(dev, - "Invalid channel requested for 8225: %d\n", - channel); - return false; - } - _rtl92e_phy_set_sw_chnl_cmd_array(dev, - ieee->RfDependCmd, - RfDependCmdCnt++, - MAX_RFDEPENDCMD_CNT, - CmdID_RF_WriteReg, - rZebra1_Channel, - RF_CHANNEL_TABLE_ZEBRA[channel], - 10); - _rtl92e_phy_set_sw_chnl_cmd_array(dev, - ieee->RfDependCmd, - RfDependCmdCnt++, - MAX_RFDEPENDCMD_CNT, - CmdID_End, 0, 0, 0); - break; - - case RF_8256: - if (!(channel >= 1 && channel <= 14)) { - netdev_err(dev, - "Invalid channel requested for 8256: %d\n", - channel); - return false; - } - _rtl92e_phy_set_sw_chnl_cmd_array(dev, - ieee->RfDependCmd, - RfDependCmdCnt++, - MAX_RFDEPENDCMD_CNT, - CmdID_RF_WriteReg, - rZebra1_Channel, - channel, 10); - _rtl92e_phy_set_sw_chnl_cmd_array(dev, - ieee->RfDependCmd, - RfDependCmdCnt++, - MAX_RFDEPENDCMD_CNT, - CmdID_End, 0, 0, 0); - break; - - case RF_8258: - break; - default: - netdev_warn(dev, "Unknown RF Chip ID\n"); + if (!(channel >= 1 && channel <= 14)) { + netdev_err(dev, + "Invalid channel requested for 8256: %d\n", + channel); return false; } - + _rtl92e_phy_set_sw_chnl_cmd_array(dev, + ieee->RfDependCmd, + RfDependCmdCnt++, + MAX_RFDEPENDCMD_CNT, + CmdID_RF_WriteReg, + rZebra1_Channel, + channel, 10); + _rtl92e_phy_set_sw_chnl_cmd_array(dev, + ieee->RfDependCmd, + RfDependCmdCnt++, + MAX_RFDEPENDCMD_CNT, + CmdID_End, 0, 0, 0); do { switch (*stage) { -- GitLab From 5d020fd58cb132c197079ab7bc1459d1e8cdfde3 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:34 +0100 Subject: [PATCH 1321/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_set_bw_mode_work_item priv->rf_chip is initialized to RF_8256 and never changed. Remove conditions in function _rtl92e_set_bw_mode_work_item as those are dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/a872bb67f71b9992740d5f9b154f794604a2dbb0.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 24 +------------------ 1 file changed, 1 insertion(+), 23 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 73e426e052b0..1f0d3654c6a0 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -849,10 +849,6 @@ static void _rtl92e_set_bw_mode_work_item(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); u8 regBwOpMode; - if (priv->rf_chip == RF_PSEUDO_11N) { - priv->set_bw_mode_in_progress = false; - return; - } if (!priv->up) { netdev_err(dev, "%s(): Driver is not initialized\n", __func__); return; @@ -918,25 +914,7 @@ static void _rtl92e_set_bw_mode_work_item(struct net_device *dev) } - switch (priv->rf_chip) { - case RF_8225: - break; - - case RF_8256: - rtl92e_set_bandwidth(dev, priv->current_chnl_bw); - break; - - case RF_8258: - break; - - case RF_PSEUDO_11N: - break; - - default: - netdev_info(dev, "%s(): Unknown RFChipID: %d\n", __func__, - priv->rf_chip); - break; - } + rtl92e_set_bandwidth(dev, priv->current_chnl_bw); atomic_dec(&(priv->rtllib->atm_swbw)); priv->set_bw_mode_in_progress = false; -- GitLab From ec69d872eb6fccc0e271f2d7ca283796c215a776 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:43 +0100 Subject: [PATCH 1322/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_set_rf_power_state priv->rf_chip is initialized to RF_8256 and never changed. Remove conditions in function _rtl92e_set_rf_power_state as those are dead code. Removed unnecessary blank lines to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/a83b95c68697e6eade68bfd0bf8e22a1340c1457.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 186 +++++++----------- 1 file changed, 76 insertions(+), 110 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 1f0d3654c6a0..b1c297d2ae36 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -1040,129 +1040,95 @@ static bool _rtl92e_set_rf_power_state(struct net_device *dev, return false; priv->set_rf_pwr_state_in_progress = true; - switch (priv->rf_chip) { - case RF_8256: - switch (rf_power_state) { - case rf_on: - if ((priv->rtllib->rf_power_state == rf_off) && - RT_IN_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC)) { - bool rtstatus; - u32 InitilizeCount = 3; - - do { - InitilizeCount--; - rtstatus = rtl92e_enable_nic(dev); - } while (!rtstatus && (InitilizeCount > 0)); - - if (!rtstatus) { - netdev_err(dev, - "%s(): Failed to initialize Adapter.\n", - __func__); - priv->set_rf_pwr_state_in_progress = false; - return false; - } - - RT_CLEAR_PS_LEVEL(psc, - RT_RF_OFF_LEVL_HALT_NIC); - } else { - rtl92e_writeb(dev, ANAPAR, 0x37); - mdelay(1); - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, - 0x4, 0x1); - priv->hw_rf_off_action = 0; - - rtl92e_set_bb_reg(dev, rFPGA0_XA_RFInterfaceOE, - BIT4, 0x1); - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, - 0x300, 0x3); - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, - 0x18, 0x3); - rtl92e_set_bb_reg(dev, rOFDM0_TRxPathEnable, - 0x3, 0x3); - rtl92e_set_bb_reg(dev, rOFDM1_TRxPathEnable, - 0x3, 0x3); - rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, - 0x60, 0x3); - + switch (rf_power_state) { + case rf_on: + if ((priv->rtllib->rf_power_state == rf_off) && + RT_IN_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC)) { + bool rtstatus; + u32 InitilizeCount = 3; + + do { + InitilizeCount--; + rtstatus = rtl92e_enable_nic(dev); + } while (!rtstatus && (InitilizeCount > 0)); + if (!rtstatus) { + netdev_err(dev, + "%s(): Failed to initialize Adapter.\n", + __func__); + priv->set_rf_pwr_state_in_progress = false; + return false; } - + RT_CLEAR_PS_LEVEL(psc, + RT_RF_OFF_LEVL_HALT_NIC); + } else { + rtl92e_writeb(dev, ANAPAR, 0x37); + mdelay(1); + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, + 0x4, 0x1); + priv->hw_rf_off_action = 0; + rtl92e_set_bb_reg(dev, rFPGA0_XA_RFInterfaceOE, + BIT4, 0x1); + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter4, + 0x300, 0x3); + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, + 0x18, 0x3); + rtl92e_set_bb_reg(dev, rOFDM0_TRxPathEnable, + 0x3, 0x3); + rtl92e_set_bb_reg(dev, rOFDM1_TRxPathEnable, + 0x3, 0x3); + rtl92e_set_bb_reg(dev, rFPGA0_AnalogParameter1, + 0x60, 0x3); + } + break; + case rf_sleep: + if (priv->rtllib->rf_power_state == rf_off) break; - - case rf_sleep: - if (priv->rtllib->rf_power_state == rf_off) + for (QueueID = 0, i = 0; QueueID < MAX_TX_QUEUE; ) { + ring = &priv->tx_ring[QueueID]; + if (skb_queue_len(&ring->queue) == 0) { + QueueID++; + continue; + } else { + udelay(10); + i++; + } + if (i >= MAX_DOZE_WAITING_TIMES_9x) break; - - - for (QueueID = 0, i = 0; QueueID < MAX_TX_QUEUE; ) { - ring = &priv->tx_ring[QueueID]; - - if (skb_queue_len(&ring->queue) == 0) { - QueueID++; - continue; - } else { - udelay(10); - i++; - } - - if (i >= MAX_DOZE_WAITING_TIMES_9x) - break; + } + rtl92e_set_rf_off(dev); + break; + case rf_off: + for (QueueID = 0, i = 0; QueueID < MAX_TX_QUEUE; ) { + ring = &priv->tx_ring[QueueID]; + if (skb_queue_len(&ring->queue) == 0) { + QueueID++; + continue; + } else { + udelay(10); + i++; } + if (i >= MAX_DOZE_WAITING_TIMES_9x) + break; + } + if (psc->RegRfPsLevel & RT_RF_OFF_LEVL_HALT_NIC && + !RT_IN_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC)) { + rtl92e_disable_nic(dev); + RT_SET_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC); + } else if (!(psc->RegRfPsLevel & + RT_RF_OFF_LEVL_HALT_NIC)) { rtl92e_set_rf_off(dev); - break; - - case rf_off: - for (QueueID = 0, i = 0; QueueID < MAX_TX_QUEUE; ) { - ring = &priv->tx_ring[QueueID]; - - if (skb_queue_len(&ring->queue) == 0) { - QueueID++; - continue; - } else { - udelay(10); - i++; - } - - if (i >= MAX_DOZE_WAITING_TIMES_9x) - break; - } - - if (psc->RegRfPsLevel & RT_RF_OFF_LEVL_HALT_NIC && - !RT_IN_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC)) { - rtl92e_disable_nic(dev); - RT_SET_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC); - } else if (!(psc->RegRfPsLevel & - RT_RF_OFF_LEVL_HALT_NIC)) { - rtl92e_set_rf_off(dev); - } - - break; - - default: - bResult = false; - netdev_warn(dev, - "%s(): Unknown state requested: 0x%X.\n", - __func__, rf_power_state); - break; } - break; - default: - netdev_warn(dev, "%s(): Unknown RF type\n", __func__); + bResult = false; + netdev_warn(dev, + "%s(): Unknown state requested: 0x%X.\n", + __func__, rf_power_state); break; } if (bResult) { priv->rtllib->rf_power_state = rf_power_state; - - switch (priv->rf_chip) { - case RF_8256: - break; - - default: - netdev_warn(dev, "%s(): Unknown RF type\n", __func__); - break; - } } priv->set_rf_pwr_state_in_progress = false; -- GitLab From 25e99c453b6d4797be3606d4debeabc9e7f28ef9 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:36:54 +0100 Subject: [PATCH 1323/5631] staging: rtl8192e: Remove rf_chip in _rtl92e_get_supported_wireless_mode priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function _rtl92e_get_supported_wireless_mode as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/e2db309dea3208560337376fec26fa5cfba93848.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 3244aef12c05..8e4e939d7617 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -595,23 +595,9 @@ static void _rtl92e_refresh_support_rate(struct r8192_priv *priv) static u8 _rtl92e_get_supported_wireless_mode(struct net_device *dev) { - struct r8192_priv *priv = rtllib_priv(dev); u8 ret = 0; - switch (priv->rf_chip) { - case RF_8225: - case RF_8256: - case RF_6052: - case RF_PSEUDO_11N: - ret = (WIRELESS_MODE_N_24G | WIRELESS_MODE_G | WIRELESS_MODE_B); - break; - case RF_8258: - ret = (WIRELESS_MODE_A | WIRELESS_MODE_N_5G); - break; - default: - ret = WIRELESS_MODE_B; - break; - } + ret = (WIRELESS_MODE_N_24G | WIRELESS_MODE_G | WIRELESS_MODE_B); return ret; } -- GitLab From 1d907c886f1c955fe805563bd6b08c733d903eb8 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:37:02 +0100 Subject: [PATCH 1324/5631] staging: rtl8192e: Remove priv->rf_chip in _rtl92e_get_channel_map priv->rf_chip is initialized to RF_8256 and never changed. Remove condition in function _rtl92e_get_channel_map as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/b8c5a719c6f8930adb87a4ad9bd5d368ba5f348b.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 8e4e939d7617..ecc3f0c6c267 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -895,13 +895,6 @@ static short _rtl92e_get_channel_map(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); - if ((priv->rf_chip != RF_8225) && (priv->rf_chip != RF_8256) && - (priv->rf_chip != RF_6052)) { - netdev_err(dev, "%s: unknown rf chip, can't set channel map\n", - __func__); - return -1; - } - if (priv->chnl_plan >= COUNTRY_CODE_MAX) { netdev_info(dev, "rtl819x_init:Error channel plan! Set to default.\n"); -- GitLab From d6e10084a19f6a0aec81f5823514736f4a990023 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sat, 25 Mar 2023 09:37:10 +0100 Subject: [PATCH 1325/5631] staging: rtl8192e: Remove priv->rf_chip priv->rf_chip is initialized to RF_8256 and not used. Remove initialization, variable and enum as it is dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/2ce85c1a159ae376d82c19c61e694924f07d1093.1679732276.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 -- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 10 ---------- 2 files changed, 12 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 1e7be321721b..a67927f0c5e3 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -432,8 +432,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) rtl92e_init_adaptive_rate(dev); - priv->rf_chip = RF_8256; - if (priv->reg_chnl_plan == 0xf) priv->chnl_plan = priv->eeprom_chnl_plan; else diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index c8816c44ca51..68ec0aeb2dd9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -129,15 +129,6 @@ enum dcmg_txcmd_op { TXCMD_XXXX_CTRL, }; -enum rt_rf_type_819xu { - RF_TYPE_MIN = 0, - RF_8225, - RF_8256, - RF_8258, - RF_6052 = 4, - RF_PSEUDO_11N = 5, -}; - enum rt_customer_id { RT_CID_DEFAULT = 0, RT_CID_819x_CAMEO = 6, @@ -221,7 +212,6 @@ struct r8192_priv { enum rt_customer_id customer_id; - enum rt_rf_type_819xu rf_chip; enum ht_channel_width current_chnl_bw; struct bb_reg_definition phy_reg_def[4]; struct rate_adaptive rate_adaptive; -- GitLab From f8a0457a0f8dd76a65fbdbed7175efbd3f8d0f78 Mon Sep 17 00:00:00 2001 From: Menna Mahmoud Date: Wed, 22 Mar 2023 13:37:34 +0200 Subject: [PATCH 1326/5631] staging: greybus: remove unnecessary blank line MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove unnecessary blank line before struct as reported by checkpatch: " CHECK: Please don't use multiple blank lines " Signed-off-by: Menna Mahmoud Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230322113735.31214-1-eng.mennamahmoud.mm@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/greybus_authentication.h | 1 - drivers/staging/greybus/pwm.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/staging/greybus/greybus_authentication.h b/drivers/staging/greybus/greybus_authentication.h index 7edc7295b7ab..48b4a9794d3c 100644 --- a/drivers/staging/greybus/greybus_authentication.h +++ b/drivers/staging/greybus/greybus_authentication.h @@ -41,7 +41,6 @@ #define CAP_AUTH_RESULT_CR_NO_KEY 0x03 #define CAP_AUTH_RESULT_CR_SIG_FAIL 0x04 - /* IOCTL support */ struct cap_ioc_get_endpoint_uid { __u8 uid[8]; diff --git a/drivers/staging/greybus/pwm.c b/drivers/staging/greybus/pwm.c index 3fda172239d2..26d39e08c3b6 100644 --- a/drivers/staging/greybus/pwm.c +++ b/drivers/staging/greybus/pwm.c @@ -24,7 +24,6 @@ struct gb_pwm_chip { #define pwm_chip_to_gb_pwm_chip(chip) \ container_of(chip, struct gb_pwm_chip, chip) - static int gb_pwm_count_operation(struct gb_pwm_chip *pwmc) { struct gb_pwm_count_response response; -- GitLab From 016227800e3b085d90638312bf79d40add8da1e4 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Fri, 24 Mar 2023 09:43:34 +0100 Subject: [PATCH 1327/5631] staging: rtl8723bs: remove hal_btcoex_SetChipType() Remove the function hal_btcoex_SetChipType() as it does nothing and produces the following gcc warning when compiling with W=1. drivers/staging/rtl8723bs/hal/hal_btcoex.c:1182:30: warning: variable 'pHalData' set but not used [-Wunused-but-set-variable] 1182 | struct hal_com_data *pHalData; | ^~~~~~~~ Signed-off-by: Michael Straube Reviewed-by: Hans de Goede Link: https://lore.kernel.org/r/20230324084334.12183-1-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/hal/hal_btcoex.c | 8 -------- drivers/staging/rtl8723bs/hal/rtl8723b_hal_init.c | 1 - drivers/staging/rtl8723bs/include/hal_btcoex.h | 1 - 3 files changed, 10 deletions(-) diff --git a/drivers/staging/rtl8723bs/hal/hal_btcoex.c b/drivers/staging/rtl8723bs/hal/hal_btcoex.c index e36f8c369a04..e26b789b9cdd 100644 --- a/drivers/staging/rtl8723bs/hal/hal_btcoex.c +++ b/drivers/staging/rtl8723bs/hal/hal_btcoex.c @@ -1177,14 +1177,6 @@ bool hal_btcoex_IsBtDisabled(struct adapter *padapter) return false; } -void hal_btcoex_SetChipType(struct adapter *padapter, u8 chipType) -{ - struct hal_com_data *pHalData; - - - pHalData = GET_HAL_DATA(padapter); -} - void hal_btcoex_SetPgAntNum(struct adapter *padapter, u8 antNum) { struct hal_com_data *pHalData; diff --git a/drivers/staging/rtl8723bs/hal/rtl8723b_hal_init.c b/drivers/staging/rtl8723bs/hal/rtl8723b_hal_init.c index 0fcae6871108..c3c1b49674d3 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723b_hal_init.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723b_hal_init.c @@ -2304,7 +2304,6 @@ void Hal_EfuseParseBTCoexistInfo_8723B( } hal_btcoex_SetBTCoexist(padapter, pHalData->EEPROMBluetoothCoexist); - hal_btcoex_SetChipType(padapter, pHalData->EEPROMBluetoothType); hal_btcoex_SetPgAntNum(padapter, pHalData->EEPROMBluetoothAntNum == Ant_x2 ? 2 : 1); if (pHalData->EEPROMBluetoothAntNum == Ant_x1) hal_btcoex_SetSingleAntPath(padapter, pHalData->ant_path); diff --git a/drivers/staging/rtl8723bs/include/hal_btcoex.h b/drivers/staging/rtl8723bs/include/hal_btcoex.h index fb167642da01..525cce3574fe 100644 --- a/drivers/staging/rtl8723bs/include/hal_btcoex.h +++ b/drivers/staging/rtl8723bs/include/hal_btcoex.h @@ -23,7 +23,6 @@ struct bt_coexist { void hal_btcoex_SetBTCoexist(struct adapter *padapter, u8 bBtExist); bool hal_btcoex_IsBtExist(struct adapter *padapter); bool hal_btcoex_IsBtDisabled(struct adapter *); -void hal_btcoex_SetChipType(struct adapter *padapter, u8 chipType); void hal_btcoex_SetPgAntNum(struct adapter *padapter, u8 antNum); void hal_btcoex_SetSingleAntPath(struct adapter *padapter, u8 singleAntPath); -- GitLab From f48198232d605a0d29f1e11235a6f6142b074b39 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Sat, 25 Mar 2023 01:23:33 -0700 Subject: [PATCH 1328/5631] staging: greybus: Inline gpio_chip_to_gb_gpio_controller() Convert 'gpio_chip_to_gb_gpio_controller' from a macro to a static inline function, to make the relevant types apparent in the definition and to benefit from the type checking performed by the compiler at call sites. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/3fc5d84a99574ac4a76d26427ac544de375adeb4.1679732179.git.sumitraartsy@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/gpio.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/staging/greybus/gpio.c b/drivers/staging/greybus/gpio.c index d729b922a750..2a115a8fc263 100644 --- a/drivers/staging/greybus/gpio.c +++ b/drivers/staging/greybus/gpio.c @@ -41,8 +41,11 @@ struct gb_gpio_controller { struct irq_chip irqc; struct mutex irq_lock; }; -#define gpio_chip_to_gb_gpio_controller(chip) \ - container_of(chip, struct gb_gpio_controller, chip) + +static inline struct gb_gpio_controller *gpio_chip_to_gb_gpio_controller(struct gpio_chip *chip) +{ + return container_of(chip, struct gb_gpio_controller, chip); +} static struct gpio_chip *irq_data_to_gpio_chip(struct irq_data *d) { -- GitLab From f5aca1a63e83178374195d3a26790091fdf2ed05 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Sat, 25 Mar 2023 01:31:06 -0700 Subject: [PATCH 1329/5631] staging: greybus: Inline gb_audio_manager_module() Convert 'gb_audio_manager_module' from a macro to a static inline function, to make the relevant types apparent in the definition and to benefit from the type checking performed by the compiler at call sites. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/7470bf9d9a57e8bf27e55bd5e3791c5e0ee31385.1679732179.git.sumitraartsy@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/audio_manager_module.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/staging/greybus/audio_manager_module.c b/drivers/staging/greybus/audio_manager_module.c index 81b4ba607a0e..5f9dcbdbc191 100644 --- a/drivers/staging/greybus/audio_manager_module.c +++ b/drivers/staging/greybus/audio_manager_module.c @@ -12,8 +12,11 @@ #define to_gb_audio_module_attr(x) \ container_of(x, struct gb_audio_manager_module_attribute, attr) -#define to_gb_audio_module(x) \ - container_of(x, struct gb_audio_manager_module, kobj) + +static inline struct gb_audio_manager_module *to_gb_audio_module(struct kobject *kobj) +{ + return container_of(kobj, struct gb_audio_manager_module, kobj); +} struct gb_audio_manager_module_attribute { struct attribute attr; -- GitLab From 01bc9ff2749b1aee1eab70d98c5313361add336c Mon Sep 17 00:00:00 2001 From: Abhirup Deb Date: Tue, 21 Mar 2023 00:12:50 +0530 Subject: [PATCH 1330/5631] staging: vme_user: Replace "<<" with BIT macro Replace the "<<" operator with BIT macro, in accordance to the checkpatch.pl script and Linux kernel coding-style guidelines. Signed-off-by: Abhirup Deb Link: https://lore.kernel.org/r/ZBipKh/e2lK3YcQr@li-27defe4c-32e1-11b2-a85c-e202e9981075.ibm.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme_user/vme_tsi148.h | 534 +++++++++++++------------- 1 file changed, 267 insertions(+), 267 deletions(-) diff --git a/drivers/staging/vme_user/vme_tsi148.h b/drivers/staging/vme_user/vme_tsi148.h index b3cb4a089cc8..63f726e1811a 100644 --- a/drivers/staging/vme_user/vme_tsi148.h +++ b/drivers/staging/vme_user/vme_tsi148.h @@ -536,22 +536,22 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * PFCS Register Set */ -#define TSI148_PCFS_CMMD_SERR (1<<8) /* SERR_L out pin ssys err */ -#define TSI148_PCFS_CMMD_PERR (1<<6) /* PERR_L out pin parity */ -#define TSI148_PCFS_CMMD_MSTR (1<<2) /* PCI bus master */ -#define TSI148_PCFS_CMMD_MEMSP (1<<1) /* PCI mem space access */ -#define TSI148_PCFS_CMMD_IOSP (1<<0) /* PCI I/O space enable */ - -#define TSI148_PCFS_STAT_RCPVE (1<<15) /* Detected Parity Error */ -#define TSI148_PCFS_STAT_SIGSE (1<<14) /* Signalled System Error */ -#define TSI148_PCFS_STAT_RCVMA (1<<13) /* Received Master Abort */ -#define TSI148_PCFS_STAT_RCVTA (1<<12) /* Received Target Abort */ -#define TSI148_PCFS_STAT_SIGTA (1<<11) /* Signalled Target Abort */ +#define TSI148_PCFS_CMMD_SERR BIT(8) /* SERR_L out pin ssys err */ +#define TSI148_PCFS_CMMD_PERR BIT(6) /* PERR_L out pin parity */ +#define TSI148_PCFS_CMMD_MSTR BIT(2) /* PCI bus master */ +#define TSI148_PCFS_CMMD_MEMSP BIT(1) /* PCI mem space access */ +#define TSI148_PCFS_CMMD_IOSP BIT(0) /* PCI I/O space enable */ + +#define TSI148_PCFS_STAT_RCPVE BIT(15) /* Detected Parity Error */ +#define TSI148_PCFS_STAT_SIGSE BIT(14) /* Signalled System Error */ +#define TSI148_PCFS_STAT_RCVMA BIT(13) /* Received Master Abort */ +#define TSI148_PCFS_STAT_RCVTA BIT(12) /* Received Target Abort */ +#define TSI148_PCFS_STAT_SIGTA BIT(11) /* Signalled Target Abort */ #define TSI148_PCFS_STAT_SELTIM (3<<9) /* DELSEL Timing */ -#define TSI148_PCFS_STAT_DPAR (1<<8) /* Data Parity Err Reported */ -#define TSI148_PCFS_STAT_FAST (1<<7) /* Fast back-to-back Cap */ -#define TSI148_PCFS_STAT_P66M (1<<5) /* 66 MHz Capable */ -#define TSI148_PCFS_STAT_CAPL (1<<4) /* Capab List - address $34 */ +#define TSI148_PCFS_STAT_DPAR BIT(8) /* Data Parity Err Reported */ +#define TSI148_PCFS_STAT_FAST BIT(7) /* Fast back-to-back Cap */ +#define TSI148_PCFS_STAT_P66M BIT(5) /* 66 MHz Capable */ +#define TSI148_PCFS_STAT_CAPL BIT(4) /* Capab List - address $34 */ /* * Revision ID/Class Code Registers (CRG +$008) @@ -572,17 +572,17 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, * Memory Base Address Lower Reg (CRG + $010) */ #define TSI148_PCFS_MBARL_BASEL_M (0xFFFFF<<12) /* Base Addr Lower Mask */ -#define TSI148_PCFS_MBARL_PRE (1<<3) /* Prefetch */ +#define TSI148_PCFS_MBARL_PRE BIT(3) /* Prefetch */ #define TSI148_PCFS_MBARL_MTYPE_M (3<<1) /* Memory Type Mask */ -#define TSI148_PCFS_MBARL_IOMEM (1<<0) /* I/O Space Indicator */ +#define TSI148_PCFS_MBARL_IOMEM BIT(0) /* I/O Space Indicator */ /* * Message Signaled Interrupt Capabilities Register (CRG + $040) */ -#define TSI148_PCFS_MSICAP_64BAC (1<<7) /* 64-bit Address Capable */ +#define TSI148_PCFS_MSICAP_64BAC BIT(7) /* 64-bit Address Capable */ #define TSI148_PCFS_MSICAP_MME_M (7<<4) /* Multiple Msg Enable Mask */ #define TSI148_PCFS_MSICAP_MMC_M (7<<1) /* Multiple Msg Capable Mask */ -#define TSI148_PCFS_MSICAP_MSIEN (1<<0) /* Msg signaled INT Enable */ +#define TSI148_PCFS_MSICAP_MSIEN BIT(0) /* Msg signaled INT Enable */ /* * Message Address Lower Register (CRG +$044) @@ -599,22 +599,22 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, */ #define TSI148_PCFS_PCIXCAP_MOST_M (7<<4) /* Max outstanding Split Tran */ #define TSI148_PCFS_PCIXCAP_MMRBC_M (3<<2) /* Max Mem Read byte cnt */ -#define TSI148_PCFS_PCIXCAP_ERO (1<<1) /* Enable Relaxed Ordering */ -#define TSI148_PCFS_PCIXCAP_DPERE (1<<0) /* Data Parity Recover Enable */ +#define TSI148_PCFS_PCIXCAP_ERO BIT(1) /* Enable Relaxed Ordering */ +#define TSI148_PCFS_PCIXCAP_DPERE BIT(0) /* Data Parity Recover Enable */ /* * PCI-X Status Register (CRG +$054) */ -#define TSI148_PCFS_PCIXSTAT_RSCEM (1<<29) /* Received Split Comp Error */ +#define TSI148_PCFS_PCIXSTAT_RSCEM BIT(29) /* Received Split Comp Error */ #define TSI148_PCFS_PCIXSTAT_DMCRS_M (7<<26) /* max Cumulative Read Size */ #define TSI148_PCFS_PCIXSTAT_DMOST_M (7<<23) /* max outstanding Split Trans */ #define TSI148_PCFS_PCIXSTAT_DMMRC_M (3<<21) /* max mem read byte count */ -#define TSI148_PCFS_PCIXSTAT_DC (1<<20) /* Device Complexity */ -#define TSI148_PCFS_PCIXSTAT_USC (1<<19) /* Unexpected Split comp */ -#define TSI148_PCFS_PCIXSTAT_SCD (1<<18) /* Split completion discard */ -#define TSI148_PCFS_PCIXSTAT_133C (1<<17) /* 133MHz capable */ -#define TSI148_PCFS_PCIXSTAT_64D (1<<16) /* 64 bit device */ +#define TSI148_PCFS_PCIXSTAT_DC BIT(20) /* Device Complexity */ +#define TSI148_PCFS_PCIXSTAT_USC BIT(19) /* Unexpected Split comp */ +#define TSI148_PCFS_PCIXSTAT_SCD BIT(18) /* Split completion discard */ +#define TSI148_PCFS_PCIXSTAT_133C BIT(17) /* 133MHz capable */ +#define TSI148_PCFS_PCIXSTAT_64D BIT(16) /* 64 bit device */ #define TSI148_PCFS_PCIXSTAT_BN_M (0xFF<<8) /* Bus number */ #define TSI148_PCFS_PCIXSTAT_DN_M (0x1F<<3) /* Device number */ #define TSI148_PCFS_PCIXSTAT_FN_M (7<<0) /* Function Number */ @@ -646,23 +646,23 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * Outbound Translation Attribute */ -#define TSI148_LCSR_OTAT_EN (1<<31) /* Window Enable */ -#define TSI148_LCSR_OTAT_MRPFD (1<<18) /* Prefetch Disable */ +#define TSI148_LCSR_OTAT_EN BIT(31) /* Window Enable */ +#define TSI148_LCSR_OTAT_MRPFD BIT(18) /* Prefetch Disable */ #define TSI148_LCSR_OTAT_PFS_M (3<<16) /* Prefetch Size Mask */ #define TSI148_LCSR_OTAT_PFS_2 (0<<16) /* 2 Cache Lines P Size */ -#define TSI148_LCSR_OTAT_PFS_4 (1<<16) /* 4 Cache Lines P Size */ +#define TSI148_LCSR_OTAT_PFS_4 BIT(16) /* 4 Cache Lines P Size */ #define TSI148_LCSR_OTAT_PFS_8 (2<<16) /* 8 Cache Lines P Size */ #define TSI148_LCSR_OTAT_PFS_16 (3<<16) /* 16 Cache Lines P Size */ #define TSI148_LCSR_OTAT_2eSSTM_M (7<<11) /* 2eSST Xfer Rate Mask */ #define TSI148_LCSR_OTAT_2eSSTM_160 (0<<11) /* 160MB/s 2eSST Xfer Rate */ -#define TSI148_LCSR_OTAT_2eSSTM_267 (1<<11) /* 267MB/s 2eSST Xfer Rate */ +#define TSI148_LCSR_OTAT_2eSSTM_267 BIT(11) /* 267MB/s 2eSST Xfer Rate */ #define TSI148_LCSR_OTAT_2eSSTM_320 (2<<11) /* 320MB/s 2eSST Xfer Rate */ #define TSI148_LCSR_OTAT_TM_M (7<<8) /* Xfer Protocol Mask */ #define TSI148_LCSR_OTAT_TM_SCT (0<<8) /* SCT Xfer Protocol */ -#define TSI148_LCSR_OTAT_TM_BLT (1<<8) /* BLT Xfer Protocol */ +#define TSI148_LCSR_OTAT_TM_BLT BIT(8) /* BLT Xfer Protocol */ #define TSI148_LCSR_OTAT_TM_MBLT (2<<8) /* MBLT Xfer Protocol */ #define TSI148_LCSR_OTAT_TM_2eVME (3<<8) /* 2eVME Xfer Protocol */ #define TSI148_LCSR_OTAT_TM_2eSST (4<<8) /* 2eSST Xfer Protocol */ @@ -670,14 +670,14 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, #define TSI148_LCSR_OTAT_DBW_M (3<<6) /* Max Data Width */ #define TSI148_LCSR_OTAT_DBW_16 (0<<6) /* 16-bit Data Width */ -#define TSI148_LCSR_OTAT_DBW_32 (1<<6) /* 32-bit Data Width */ +#define TSI148_LCSR_OTAT_DBW_32 BIT(6) /* 32-bit Data Width */ -#define TSI148_LCSR_OTAT_SUP (1<<5) /* Supervisory Access */ -#define TSI148_LCSR_OTAT_PGM (1<<4) /* Program Access */ +#define TSI148_LCSR_OTAT_SUP BIT(5) /* Supervisory Access */ +#define TSI148_LCSR_OTAT_PGM BIT(4) /* Program Access */ #define TSI148_LCSR_OTAT_AMODE_M (0xf<<0) /* Address Mode Mask */ #define TSI148_LCSR_OTAT_AMODE_A16 (0<<0) /* A16 Address Space */ -#define TSI148_LCSR_OTAT_AMODE_A24 (1<<0) /* A24 Address Space */ +#define TSI148_LCSR_OTAT_AMODE_A24 BIT(0) /* A24 Address Space */ #define TSI148_LCSR_OTAT_AMODE_A32 (2<<0) /* A32 Address Space */ #define TSI148_LCSR_OTAT_AMODE_A64 (4<<0) /* A32 Address Space */ #define TSI148_LCSR_OTAT_AMODE_CRCSR (5<<0) /* CR/CSR Address Space */ @@ -689,17 +689,17 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * VME Master Control Register CRG+$234 */ -#define TSI148_LCSR_VMCTRL_VSA (1<<27) /* VMEbus Stop Ack */ -#define TSI148_LCSR_VMCTRL_VS (1<<26) /* VMEbus Stop */ -#define TSI148_LCSR_VMCTRL_DHB (1<<25) /* Device Has Bus */ -#define TSI148_LCSR_VMCTRL_DWB (1<<24) /* Device Wants Bus */ +#define TSI148_LCSR_VMCTRL_VSA BIT(27) /* VMEbus Stop Ack */ +#define TSI148_LCSR_VMCTRL_VS BIT(26) /* VMEbus Stop */ +#define TSI148_LCSR_VMCTRL_DHB BIT(25) /* Device Has Bus */ +#define TSI148_LCSR_VMCTRL_DWB BIT(24) /* Device Wants Bus */ -#define TSI148_LCSR_VMCTRL_RMWEN (1<<20) /* RMW Enable */ +#define TSI148_LCSR_VMCTRL_RMWEN BIT(20) /* RMW Enable */ #define TSI148_LCSR_VMCTRL_ATO_M (7<<16) /* Master Access Time-out Mask */ #define TSI148_LCSR_VMCTRL_ATO_32 (0<<16) /* 32 us */ -#define TSI148_LCSR_VMCTRL_ATO_128 (1<<16) /* 128 us */ +#define TSI148_LCSR_VMCTRL_ATO_128 BIT(16) /* 128 us */ #define TSI148_LCSR_VMCTRL_ATO_512 (2<<16) /* 512 us */ #define TSI148_LCSR_VMCTRL_ATO_2M (3<<16) /* 2 ms */ #define TSI148_LCSR_VMCTRL_ATO_8M (4<<16) /* 8 ms */ @@ -709,7 +709,7 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, #define TSI148_LCSR_VMCTRL_VTOFF_M (7<<12) /* VMEbus Master Time off */ #define TSI148_LCSR_VMCTRL_VTOFF_0 (0<<12) /* 0us */ -#define TSI148_LCSR_VMCTRL_VTOFF_1 (1<<12) /* 1us */ +#define TSI148_LCSR_VMCTRL_VTOFF_1 BIT(12) /* 1us */ #define TSI148_LCSR_VMCTRL_VTOFF_2 (2<<12) /* 2us */ #define TSI148_LCSR_VMCTRL_VTOFF_4 (3<<12) /* 4us */ #define TSI148_LCSR_VMCTRL_VTOFF_8 (4<<12) /* 8us */ @@ -719,7 +719,7 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, #define TSI148_LCSR_VMCTRL_VTON_M (7<<8) /* VMEbus Master Time On */ #define TSI148_LCSR_VMCTRL_VTON_4 (0<<8) /* 8us */ -#define TSI148_LCSR_VMCTRL_VTON_8 (1<<8) /* 8us */ +#define TSI148_LCSR_VMCTRL_VTON_8 BIT(8) /* 8us */ #define TSI148_LCSR_VMCTRL_VTON_16 (2<<8) /* 16us */ #define TSI148_LCSR_VMCTRL_VTON_32 (3<<8) /* 32us */ #define TSI148_LCSR_VMCTRL_VTON_64 (4<<8) /* 64us */ @@ -730,22 +730,22 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, #define TSI148_LCSR_VMCTRL_VREL_M (3<<3) /* VMEbus Master Rel Mode Mask */ #define TSI148_LCSR_VMCTRL_VREL_T_D (0<<3) /* Time on or Done */ -#define TSI148_LCSR_VMCTRL_VREL_T_R_D (1<<3) /* Time on and REQ or Done */ +#define TSI148_LCSR_VMCTRL_VREL_T_R_D BIT(3) /* Time on and REQ or Done */ #define TSI148_LCSR_VMCTRL_VREL_T_B_D (2<<3) /* Time on and BCLR or Done */ #define TSI148_LCSR_VMCTRL_VREL_T_D_R (3<<3) /* Time on or Done and REQ */ -#define TSI148_LCSR_VMCTRL_VFAIR (1<<2) /* VMEbus Master Fair Mode */ +#define TSI148_LCSR_VMCTRL_VFAIR BIT(2) /* VMEbus Master Fair Mode */ #define TSI148_LCSR_VMCTRL_VREQL_M (3<<0) /* VMEbus Master Req Level Mask */ /* * VMEbus Control Register CRG+$238 */ -#define TSI148_LCSR_VCTRL_LRE (1<<31) /* Late Retry Enable */ +#define TSI148_LCSR_VCTRL_LRE BIT(31) /* Late Retry Enable */ #define TSI148_LCSR_VCTRL_DLT_M (0xF<<24) /* Deadlock Timer */ #define TSI148_LCSR_VCTRL_DLT_OFF (0<<24) /* Deadlock Timer Off */ -#define TSI148_LCSR_VCTRL_DLT_16 (1<<24) /* 16 VCLKS */ +#define TSI148_LCSR_VCTRL_DLT_16 BIT(24) /* 16 VCLKS */ #define TSI148_LCSR_VCTRL_DLT_32 (2<<24) /* 32 VCLKS */ #define TSI148_LCSR_VCTRL_DLT_64 (3<<24) /* 64 VCLKS */ #define TSI148_LCSR_VCTRL_DLT_128 (4<<24) /* 128 VCLKS */ @@ -758,22 +758,22 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, #define TSI148_LCSR_VCTRL_DLT_16384 (0xB<<24) /* 16384 VCLKS */ #define TSI148_LCSR_VCTRL_DLT_32768 (0xC<<24) /* 32768 VCLKS */ -#define TSI148_LCSR_VCTRL_NERBB (1<<20) /* No Early Release of Bus Busy +#define TSI148_LCSR_VCTRL_NERBB BIT(20) /* No Early Release of Bus Busy */ -#define TSI148_LCSR_VCTRL_SRESET (1<<17) /* System Reset */ -#define TSI148_LCSR_VCTRL_LRESET (1<<16) /* Local Reset */ +#define TSI148_LCSR_VCTRL_SRESET BIT(17) /* System Reset */ +#define TSI148_LCSR_VCTRL_LRESET BIT(16) /* Local Reset */ -#define TSI148_LCSR_VCTRL_SFAILAI (1<<15) /* SYSFAIL Auto Slot ID */ +#define TSI148_LCSR_VCTRL_SFAILAI BIT(15) /* SYSFAIL Auto Slot ID */ #define TSI148_LCSR_VCTRL_BID_M (0x1F<<8) /* Broadcast ID Mask */ -#define TSI148_LCSR_VCTRL_ATOEN (1<<7) /* Arbiter Time-out Enable */ -#define TSI148_LCSR_VCTRL_ROBIN (1<<6) /* VMEbus Round Robin */ +#define TSI148_LCSR_VCTRL_ATOEN BIT(7) /* Arbiter Time-out Enable */ +#define TSI148_LCSR_VCTRL_ROBIN BIT(6) /* VMEbus Round Robin */ #define TSI148_LCSR_VCTRL_GTO_M (7<<0) /* VMEbus Global Time-out Mask */ #define TSI148_LCSR_VCTRL_GTO_8 (0<<0) /* 8 us */ -#define TSI148_LCSR_VCTRL_GTO_16 (1<<0) /* 16 us */ +#define TSI148_LCSR_VCTRL_GTO_16 BIT(0) /* 16 us */ #define TSI148_LCSR_VCTRL_GTO_32 (2<<0) /* 32 us */ #define TSI148_LCSR_VCTRL_GTO_64 (3<<0) /* 64 us */ #define TSI148_LCSR_VCTRL_GTO_128 (4<<0) /* 128 us */ @@ -784,48 +784,48 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * VMEbus Status Register CRG + $23C */ -#define TSI148_LCSR_VSTAT_CPURST (1<<15) /* Clear power up reset */ -#define TSI148_LCSR_VSTAT_BRDFL (1<<14) /* Board fail */ -#define TSI148_LCSR_VSTAT_PURSTS (1<<12) /* Power up reset status */ -#define TSI148_LCSR_VSTAT_BDFAILS (1<<11) /* Board Fail Status */ -#define TSI148_LCSR_VSTAT_SYSFAILS (1<<10) /* System Fail Status */ -#define TSI148_LCSR_VSTAT_ACFAILS (1<<9) /* AC fail status */ -#define TSI148_LCSR_VSTAT_SCONS (1<<8) /* System Cont Status */ -#define TSI148_LCSR_VSTAT_GAP (1<<5) /* Geographic Addr Parity */ +#define TSI148_LCSR_VSTAT_CPURST BIT(15) /* Clear power up reset */ +#define TSI148_LCSR_VSTAT_BRDFL BIT(14) /* Board fail */ +#define TSI148_LCSR_VSTAT_PURSTS BIT(12) /* Power up reset status */ +#define TSI148_LCSR_VSTAT_BDFAILS BIT(11) /* Board Fail Status */ +#define TSI148_LCSR_VSTAT_SYSFAILS BIT(10) /* System Fail Status */ +#define TSI148_LCSR_VSTAT_ACFAILS BIT(9) /* AC fail status */ +#define TSI148_LCSR_VSTAT_SCONS BIT(8) /* System Cont Status */ +#define TSI148_LCSR_VSTAT_GAP BIT(5) /* Geographic Addr Parity */ #define TSI148_LCSR_VSTAT_GA_M (0x1F<<0) /* Geographic Addr Mask */ /* * PCI Configuration Status Register CRG+$240 */ -#define TSI148_LCSR_PSTAT_REQ64S (1<<6) /* Request 64 status set */ -#define TSI148_LCSR_PSTAT_M66ENS (1<<5) /* M66ENS 66Mhz enable */ -#define TSI148_LCSR_PSTAT_FRAMES (1<<4) /* Frame Status */ -#define TSI148_LCSR_PSTAT_IRDYS (1<<3) /* IRDY status */ -#define TSI148_LCSR_PSTAT_DEVSELS (1<<2) /* DEVL status */ -#define TSI148_LCSR_PSTAT_STOPS (1<<1) /* STOP status */ -#define TSI148_LCSR_PSTAT_TRDYS (1<<0) /* TRDY status */ +#define TSI148_LCSR_PSTAT_REQ64S BIT(6) /* Request 64 status set */ +#define TSI148_LCSR_PSTAT_M66ENS BIT(5) /* M66ENS 66Mhz enable */ +#define TSI148_LCSR_PSTAT_FRAMES BIT(4) /* Frame Status */ +#define TSI148_LCSR_PSTAT_IRDYS BIT(3) /* IRDY status */ +#define TSI148_LCSR_PSTAT_DEVSELS BIT(2) /* DEVL status */ +#define TSI148_LCSR_PSTAT_STOPS BIT(1) /* STOP status */ +#define TSI148_LCSR_PSTAT_TRDYS BIT(0) /* TRDY status */ /* * VMEbus Exception Attributes Register CRG + $268 */ -#define TSI148_LCSR_VEAT_VES (1<<31) /* Status */ -#define TSI148_LCSR_VEAT_VEOF (1<<30) /* Overflow */ -#define TSI148_LCSR_VEAT_VESCL (1<<29) /* Status Clear */ -#define TSI148_LCSR_VEAT_2EOT (1<<21) /* 2e Odd Termination */ -#define TSI148_LCSR_VEAT_2EST (1<<20) /* 2e Slave terminated */ -#define TSI148_LCSR_VEAT_BERR (1<<19) /* Bus Error */ -#define TSI148_LCSR_VEAT_LWORD (1<<18) /* LWORD_ signal state */ -#define TSI148_LCSR_VEAT_WRITE (1<<17) /* WRITE_ signal state */ -#define TSI148_LCSR_VEAT_IACK (1<<16) /* IACK_ signal state */ -#define TSI148_LCSR_VEAT_DS1 (1<<15) /* DS1_ signal state */ -#define TSI148_LCSR_VEAT_DS0 (1<<14) /* DS0_ signal state */ +#define TSI148_LCSR_VEAT_VES BIT(31) /* Status */ +#define TSI148_LCSR_VEAT_VEOF BIT(30) /* Overflow */ +#define TSI148_LCSR_VEAT_VESCL BIT(29) /* Status Clear */ +#define TSI148_LCSR_VEAT_2EOT BIT(21) /* 2e Odd Termination */ +#define TSI148_LCSR_VEAT_2EST BIT(20) /* 2e Slave terminated */ +#define TSI148_LCSR_VEAT_BERR BIT(19) /* Bus Error */ +#define TSI148_LCSR_VEAT_LWORD BIT(18) /* LWORD_ signal state */ +#define TSI148_LCSR_VEAT_WRITE BIT(17) /* WRITE_ signal state */ +#define TSI148_LCSR_VEAT_IACK BIT(16) /* IACK_ signal state */ +#define TSI148_LCSR_VEAT_DS1 BIT(15) /* DS1_ signal state */ +#define TSI148_LCSR_VEAT_DS0 BIT(14) /* DS0_ signal state */ #define TSI148_LCSR_VEAT_AM_M (0x3F<<8) /* Address Mode Mask */ #define TSI148_LCSR_VEAT_XAM_M (0xFF<<0) /* Master AMode Mask */ /* * VMEbus PCI Error Diagnostics PCI/X Attributes Register CRG + $280 */ -#define TSI148_LCSR_EDPAT_EDPCL (1<<29) +#define TSI148_LCSR_EDPAT_EDPCL BIT(29) /* * Inbound Translation Starting Address Lower @@ -851,36 +851,36 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * Inbound Translation Attribute */ -#define TSI148_LCSR_ITAT_EN (1<<31) /* Window Enable */ -#define TSI148_LCSR_ITAT_TH (1<<18) /* Prefetch Threshold */ +#define TSI148_LCSR_ITAT_EN BIT(31) /* Window Enable */ +#define TSI148_LCSR_ITAT_TH BIT(18) /* Prefetch Threshold */ #define TSI148_LCSR_ITAT_VFS_M (3<<16) /* Virtual FIFO Size Mask */ #define TSI148_LCSR_ITAT_VFS_64 (0<<16) /* 64 bytes Virtual FIFO Size */ -#define TSI148_LCSR_ITAT_VFS_128 (1<<16) /* 128 bytes Virtual FIFO Sz */ +#define TSI148_LCSR_ITAT_VFS_128 BIT(16) /* 128 bytes Virtual FIFO Sz */ #define TSI148_LCSR_ITAT_VFS_256 (2<<16) /* 256 bytes Virtual FIFO Sz */ #define TSI148_LCSR_ITAT_VFS_512 (3<<16) /* 512 bytes Virtual FIFO Sz */ #define TSI148_LCSR_ITAT_2eSSTM_M (7<<12) /* 2eSST Xfer Rate Mask */ #define TSI148_LCSR_ITAT_2eSSTM_160 (0<<12) /* 160MB/s 2eSST Xfer Rate */ -#define TSI148_LCSR_ITAT_2eSSTM_267 (1<<12) /* 267MB/s 2eSST Xfer Rate */ +#define TSI148_LCSR_ITAT_2eSSTM_267 BIT(12) /* 267MB/s 2eSST Xfer Rate */ #define TSI148_LCSR_ITAT_2eSSTM_320 (2<<12) /* 320MB/s 2eSST Xfer Rate */ -#define TSI148_LCSR_ITAT_2eSSTB (1<<11) /* 2eSST Bcast Xfer Protocol */ -#define TSI148_LCSR_ITAT_2eSST (1<<10) /* 2eSST Xfer Protocol */ -#define TSI148_LCSR_ITAT_2eVME (1<<9) /* 2eVME Xfer Protocol */ -#define TSI148_LCSR_ITAT_MBLT (1<<8) /* MBLT Xfer Protocol */ -#define TSI148_LCSR_ITAT_BLT (1<<7) /* BLT Xfer Protocol */ +#define TSI148_LCSR_ITAT_2eSSTB BIT(11) /* 2eSST Bcast Xfer Protocol */ +#define TSI148_LCSR_ITAT_2eSST BIT(10) /* 2eSST Xfer Protocol */ +#define TSI148_LCSR_ITAT_2eVME BIT(9) /* 2eVME Xfer Protocol */ +#define TSI148_LCSR_ITAT_MBLT BIT(8) /* MBLT Xfer Protocol */ +#define TSI148_LCSR_ITAT_BLT BIT(7) /* BLT Xfer Protocol */ #define TSI148_LCSR_ITAT_AS_M (7<<4) /* Address Space Mask */ #define TSI148_LCSR_ITAT_AS_A16 (0<<4) /* A16 Address Space */ -#define TSI148_LCSR_ITAT_AS_A24 (1<<4) /* A24 Address Space */ +#define TSI148_LCSR_ITAT_AS_A24 BIT(4) /* A24 Address Space */ #define TSI148_LCSR_ITAT_AS_A32 (2<<4) /* A32 Address Space */ #define TSI148_LCSR_ITAT_AS_A64 (4<<4) /* A64 Address Space */ -#define TSI148_LCSR_ITAT_SUPR (1<<3) /* Supervisor Access */ -#define TSI148_LCSR_ITAT_NPRIV (1<<2) /* Non-Priv (User) Access */ -#define TSI148_LCSR_ITAT_PGM (1<<1) /* Program Access */ -#define TSI148_LCSR_ITAT_DATA (1<<0) /* Data Access */ +#define TSI148_LCSR_ITAT_SUPR BIT(3) /* Supervisor Access */ +#define TSI148_LCSR_ITAT_NPRIV BIT(2) /* Non-Priv (User) Access */ +#define TSI148_LCSR_ITAT_PGM BIT(1) /* Program Access */ +#define TSI148_LCSR_ITAT_DATA BIT(0) /* Data Access */ /* * GCSR Base Address Lower Address CRG +$404 @@ -890,18 +890,18 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * GCSR Attribute Register CRG + $408 */ -#define TSI148_LCSR_GCSRAT_EN (1<<7) /* Enable access to GCSR */ +#define TSI148_LCSR_GCSRAT_EN BIT(7) /* Enable access to GCSR */ #define TSI148_LCSR_GCSRAT_AS_M (7<<4) /* Address Space Mask */ #define TSI148_LCSR_GCSRAT_AS_A16 (0<<4) /* Address Space 16 */ -#define TSI148_LCSR_GCSRAT_AS_A24 (1<<4) /* Address Space 24 */ +#define TSI148_LCSR_GCSRAT_AS_A24 BIT(4) /* Address Space 24 */ #define TSI148_LCSR_GCSRAT_AS_A32 (2<<4) /* Address Space 32 */ #define TSI148_LCSR_GCSRAT_AS_A64 (4<<4) /* Address Space 64 */ -#define TSI148_LCSR_GCSRAT_SUPR (1<<3) /* Sup set -GCSR decoder */ -#define TSI148_LCSR_GCSRAT_NPRIV (1<<2) /* Non-Privliged set - CGSR */ -#define TSI148_LCSR_GCSRAT_PGM (1<<1) /* Program set - GCSR decoder */ -#define TSI148_LCSR_GCSRAT_DATA (1<<0) /* DATA set GCSR decoder */ +#define TSI148_LCSR_GCSRAT_SUPR BIT(3) /* Sup set -GCSR decoder */ +#define TSI148_LCSR_GCSRAT_NPRIV BIT(2) /* Non-Privliged set - CGSR */ +#define TSI148_LCSR_GCSRAT_PGM BIT(1) /* Program set - GCSR decoder */ +#define TSI148_LCSR_GCSRAT_DATA BIT(0) /* DATA set GCSR decoder */ /* * CRG Base Address Lower Address CRG + $410 @@ -911,18 +911,18 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * CRG Attribute Register CRG + $414 */ -#define TSI148_LCSR_CRGAT_EN (1<<7) /* Enable PRG Access */ +#define TSI148_LCSR_CRGAT_EN BIT(7) /* Enable PRG Access */ #define TSI148_LCSR_CRGAT_AS_M (7<<4) /* Address Space */ #define TSI148_LCSR_CRGAT_AS_A16 (0<<4) /* Address Space 16 */ -#define TSI148_LCSR_CRGAT_AS_A24 (1<<4) /* Address Space 24 */ +#define TSI148_LCSR_CRGAT_AS_A24 BIT(4) /* Address Space 24 */ #define TSI148_LCSR_CRGAT_AS_A32 (2<<4) /* Address Space 32 */ #define TSI148_LCSR_CRGAT_AS_A64 (4<<4) /* Address Space 64 */ -#define TSI148_LCSR_CRGAT_SUPR (1<<3) /* Supervisor Access */ -#define TSI148_LCSR_CRGAT_NPRIV (1<<2) /* Non-Privliged(User) Access */ -#define TSI148_LCSR_CRGAT_PGM (1<<1) /* Program Access */ -#define TSI148_LCSR_CRGAT_DATA (1<<0) /* Data Access */ +#define TSI148_LCSR_CRGAT_SUPR BIT(3) /* Supervisor Access */ +#define TSI148_LCSR_CRGAT_NPRIV BIT(2) /* Non-Privliged(User) Access */ +#define TSI148_LCSR_CRGAT_PGM BIT(1) /* Program Access */ +#define TSI148_LCSR_CRGAT_DATA BIT(0) /* Data Access */ /* * CR/CSR Offset Lower Register CRG + $41C @@ -932,7 +932,7 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * CR/CSR Attribute register CRG + $420 */ -#define TSI148_LCSR_CRAT_EN (1<<7) /* Enable access to CR/CSR */ +#define TSI148_LCSR_CRAT_EN BIT(7) /* Enable access to CR/CSR */ /* * Location Monitor base address lower register CRG + $428 @@ -942,18 +942,18 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, /* * Location Monitor Attribute Register CRG + $42C */ -#define TSI148_LCSR_LMAT_EN (1<<7) /* Enable Location Monitor */ +#define TSI148_LCSR_LMAT_EN BIT(7) /* Enable Location Monitor */ #define TSI148_LCSR_LMAT_AS_M (7<<4) /* Address Space MASK */ #define TSI148_LCSR_LMAT_AS_A16 (0<<4) /* A16 */ -#define TSI148_LCSR_LMAT_AS_A24 (1<<4) /* A24 */ +#define TSI148_LCSR_LMAT_AS_A24 BIT(4) /* A24 */ #define TSI148_LCSR_LMAT_AS_A32 (2<<4) /* A32 */ #define TSI148_LCSR_LMAT_AS_A64 (4<<4) /* A64 */ -#define TSI148_LCSR_LMAT_SUPR (1<<3) /* Supervisor Access */ -#define TSI148_LCSR_LMAT_NPRIV (1<<2) /* Non-Priv (User) Access */ -#define TSI148_LCSR_LMAT_PGM (1<<1) /* Program Access */ -#define TSI148_LCSR_LMAT_DATA (1<<0) /* Data Access */ +#define TSI148_LCSR_LMAT_SUPR BIT(3) /* Supervisor Access */ +#define TSI148_LCSR_LMAT_NPRIV BIT(2) /* Non-Priv (User) Access */ +#define TSI148_LCSR_LMAT_PGM BIT(1) /* Program Access */ +#define TSI148_LCSR_LMAT_DATA BIT(0) /* Data Access */ /* * Broadcast Pulse Generator Timer Register CRG + $438 @@ -969,34 +969,34 @@ static const int TSI148_GCSR_MBOX[4] = { TSI148_GCSR_MBOX0, * VMEbus Interrupt Control Register CRG + $43C */ #define TSI148_LCSR_VICR_CNTS_M (3<<22) /* Cntr Source MASK */ -#define TSI148_LCSR_VICR_CNTS_DIS (1<<22) /* Cntr Disable */ +#define TSI148_LCSR_VICR_CNTS_DIS BIT(22) /* Cntr Disable */ #define TSI148_LCSR_VICR_CNTS_IRQ1 (2<<22) /* IRQ1 to Cntr */ #define TSI148_LCSR_VICR_CNTS_IRQ2 (3<<22) /* IRQ2 to Cntr */ #define TSI148_LCSR_VICR_EDGIS_M (3<<20) /* Edge interrupt MASK */ -#define TSI148_LCSR_VICR_EDGIS_DIS (1<<20) /* Edge interrupt Disable */ +#define TSI148_LCSR_VICR_EDGIS_DIS BIT(20) /* Edge interrupt Disable */ #define TSI148_LCSR_VICR_EDGIS_IRQ1 (2<<20) /* IRQ1 to Edge */ #define TSI148_LCSR_VICR_EDGIS_IRQ2 (3<<20) /* IRQ2 to Edge */ #define TSI148_LCSR_VICR_IRQIF_M (3<<18) /* IRQ1* Function MASK */ -#define TSI148_LCSR_VICR_IRQIF_NORM (1<<18) /* Normal */ +#define TSI148_LCSR_VICR_IRQIF_NORM BIT(18) /* Normal */ #define TSI148_LCSR_VICR_IRQIF_PULSE (2<<18) /* Pulse Generator */ #define TSI148_LCSR_VICR_IRQIF_PROG (3<<18) /* Programmable Clock */ #define TSI148_LCSR_VICR_IRQIF_1U (4<<18) /* 1us Clock */ #define TSI148_LCSR_VICR_IRQ2F_M (3<<16) /* IRQ2* Function MASK */ -#define TSI148_LCSR_VICR_IRQ2F_NORM (1<<16) /* Normal */ +#define TSI148_LCSR_VICR_IRQ2F_NORM BIT(16) /* Normal */ #define TSI148_LCSR_VICR_IRQ2F_PULSE (2<<16) /* Pulse Generator */ #define TSI148_LCSR_VICR_IRQ2F_PROG (3<<16) /* Programmable Clock */ #define TSI148_LCSR_VICR_IRQ2F_1U (4<<16) /* 1us Clock */ -#define TSI148_LCSR_VICR_BIP (1<<15) /* Broadcast Interrupt Pulse */ +#define TSI148_LCSR_VICR_BIP BIT(15) /* Broadcast Interrupt Pulse */ -#define TSI148_LCSR_VICR_IRQC (1<<12) /* VMEbus IRQ Clear */ -#define TSI148_LCSR_VICR_IRQS (1<<11) /* VMEbus IRQ Status */ +#define TSI148_LCSR_VICR_IRQC BIT(12) /* VMEbus IRQ Clear */ +#define TSI148_LCSR_VICR_IRQS BIT(11) /* VMEbus IRQ Status */ #define TSI148_LCSR_VICR_IRQL_M (7<<8) /* VMEbus SW IRQ Level Mask */ -#define TSI148_LCSR_VICR_IRQL_1 (1<<8) /* VMEbus SW IRQ Level 1 */ +#define TSI148_LCSR_VICR_IRQL_1 BIT(8) /* VMEbus SW IRQ Level 1 */ #define TSI148_LCSR_VICR_IRQL_2 (2<<8) /* VMEbus SW IRQ Level 2 */ #define TSI148_LCSR_VICR_IRQL_3 (3<<8) /* VMEbus SW IRQ Level 3 */ #define TSI148_LCSR_VICR_IRQL_4 (4<<8) /* VMEbus SW IRQ Level 4 */ @@ -1014,29 +1014,29 @@ static const int TSI148_LCSR_VICR_IRQL[8] = { 0, TSI148_LCSR_VICR_IRQL_1, /* * Interrupt Enable Register CRG + $440 */ -#define TSI148_LCSR_INTEN_DMA1EN (1<<25) /* DMAC 1 */ -#define TSI148_LCSR_INTEN_DMA0EN (1<<24) /* DMAC 0 */ -#define TSI148_LCSR_INTEN_LM3EN (1<<23) /* Location Monitor 3 */ -#define TSI148_LCSR_INTEN_LM2EN (1<<22) /* Location Monitor 2 */ -#define TSI148_LCSR_INTEN_LM1EN (1<<21) /* Location Monitor 1 */ -#define TSI148_LCSR_INTEN_LM0EN (1<<20) /* Location Monitor 0 */ -#define TSI148_LCSR_INTEN_MB3EN (1<<19) /* Mail Box 3 */ -#define TSI148_LCSR_INTEN_MB2EN (1<<18) /* Mail Box 2 */ -#define TSI148_LCSR_INTEN_MB1EN (1<<17) /* Mail Box 1 */ -#define TSI148_LCSR_INTEN_MB0EN (1<<16) /* Mail Box 0 */ -#define TSI148_LCSR_INTEN_PERREN (1<<13) /* PCI/X Error */ -#define TSI148_LCSR_INTEN_VERREN (1<<12) /* VMEbus Error */ -#define TSI148_LCSR_INTEN_VIEEN (1<<11) /* VMEbus IRQ Edge */ -#define TSI148_LCSR_INTEN_IACKEN (1<<10) /* IACK */ -#define TSI148_LCSR_INTEN_SYSFLEN (1<<9) /* System Fail */ -#define TSI148_LCSR_INTEN_ACFLEN (1<<8) /* AC Fail */ -#define TSI148_LCSR_INTEN_IRQ7EN (1<<7) /* IRQ7 */ -#define TSI148_LCSR_INTEN_IRQ6EN (1<<6) /* IRQ6 */ -#define TSI148_LCSR_INTEN_IRQ5EN (1<<5) /* IRQ5 */ -#define TSI148_LCSR_INTEN_IRQ4EN (1<<4) /* IRQ4 */ -#define TSI148_LCSR_INTEN_IRQ3EN (1<<3) /* IRQ3 */ -#define TSI148_LCSR_INTEN_IRQ2EN (1<<2) /* IRQ2 */ -#define TSI148_LCSR_INTEN_IRQ1EN (1<<1) /* IRQ1 */ +#define TSI148_LCSR_INTEN_DMA1EN BIT(25) /* DMAC 1 */ +#define TSI148_LCSR_INTEN_DMA0EN BIT(24) /* DMAC 0 */ +#define TSI148_LCSR_INTEN_LM3EN BIT(23) /* Location Monitor 3 */ +#define TSI148_LCSR_INTEN_LM2EN BIT(22) /* Location Monitor 2 */ +#define TSI148_LCSR_INTEN_LM1EN BIT(21) /* Location Monitor 1 */ +#define TSI148_LCSR_INTEN_LM0EN BIT(20) /* Location Monitor 0 */ +#define TSI148_LCSR_INTEN_MB3EN BIT(19) /* Mail Box 3 */ +#define TSI148_LCSR_INTEN_MB2EN BIT(18) /* Mail Box 2 */ +#define TSI148_LCSR_INTEN_MB1EN BIT(17) /* Mail Box 1 */ +#define TSI148_LCSR_INTEN_MB0EN BIT(16) /* Mail Box 0 */ +#define TSI148_LCSR_INTEN_PERREN BIT(13) /* PCI/X Error */ +#define TSI148_LCSR_INTEN_VERREN BIT(12) /* VMEbus Error */ +#define TSI148_LCSR_INTEN_VIEEN BIT(11) /* VMEbus IRQ Edge */ +#define TSI148_LCSR_INTEN_IACKEN BIT(10) /* IACK */ +#define TSI148_LCSR_INTEN_SYSFLEN BIT(9) /* System Fail */ +#define TSI148_LCSR_INTEN_ACFLEN BIT(8) /* AC Fail */ +#define TSI148_LCSR_INTEN_IRQ7EN BIT(7) /* IRQ7 */ +#define TSI148_LCSR_INTEN_IRQ6EN BIT(6) /* IRQ6 */ +#define TSI148_LCSR_INTEN_IRQ5EN BIT(5) /* IRQ5 */ +#define TSI148_LCSR_INTEN_IRQ4EN BIT(4) /* IRQ4 */ +#define TSI148_LCSR_INTEN_IRQ3EN BIT(3) /* IRQ3 */ +#define TSI148_LCSR_INTEN_IRQ2EN BIT(2) /* IRQ2 */ +#define TSI148_LCSR_INTEN_IRQ1EN BIT(1) /* IRQ1 */ static const int TSI148_LCSR_INTEN_LMEN[4] = { TSI148_LCSR_INTEN_LM0EN, TSI148_LCSR_INTEN_LM1EN, @@ -1054,29 +1054,29 @@ static const int TSI148_LCSR_INTEN_IRQEN[7] = { TSI148_LCSR_INTEN_IRQ1EN, /* * Interrupt Enable Out Register CRG + $444 */ -#define TSI148_LCSR_INTEO_DMA1EO (1<<25) /* DMAC 1 */ -#define TSI148_LCSR_INTEO_DMA0EO (1<<24) /* DMAC 0 */ -#define TSI148_LCSR_INTEO_LM3EO (1<<23) /* Loc Monitor 3 */ -#define TSI148_LCSR_INTEO_LM2EO (1<<22) /* Loc Monitor 2 */ -#define TSI148_LCSR_INTEO_LM1EO (1<<21) /* Loc Monitor 1 */ -#define TSI148_LCSR_INTEO_LM0EO (1<<20) /* Location Monitor 0 */ -#define TSI148_LCSR_INTEO_MB3EO (1<<19) /* Mail Box 3 */ -#define TSI148_LCSR_INTEO_MB2EO (1<<18) /* Mail Box 2 */ -#define TSI148_LCSR_INTEO_MB1EO (1<<17) /* Mail Box 1 */ -#define TSI148_LCSR_INTEO_MB0EO (1<<16) /* Mail Box 0 */ -#define TSI148_LCSR_INTEO_PERREO (1<<13) /* PCI/X Error */ -#define TSI148_LCSR_INTEO_VERREO (1<<12) /* VMEbus Error */ -#define TSI148_LCSR_INTEO_VIEEO (1<<11) /* VMEbus IRQ Edge */ -#define TSI148_LCSR_INTEO_IACKEO (1<<10) /* IACK */ -#define TSI148_LCSR_INTEO_SYSFLEO (1<<9) /* System Fail */ -#define TSI148_LCSR_INTEO_ACFLEO (1<<8) /* AC Fail */ -#define TSI148_LCSR_INTEO_IRQ7EO (1<<7) /* IRQ7 */ -#define TSI148_LCSR_INTEO_IRQ6EO (1<<6) /* IRQ6 */ -#define TSI148_LCSR_INTEO_IRQ5EO (1<<5) /* IRQ5 */ -#define TSI148_LCSR_INTEO_IRQ4EO (1<<4) /* IRQ4 */ -#define TSI148_LCSR_INTEO_IRQ3EO (1<<3) /* IRQ3 */ -#define TSI148_LCSR_INTEO_IRQ2EO (1<<2) /* IRQ2 */ -#define TSI148_LCSR_INTEO_IRQ1EO (1<<1) /* IRQ1 */ +#define TSI148_LCSR_INTEO_DMA1EO BIT(25) /* DMAC 1 */ +#define TSI148_LCSR_INTEO_DMA0EO BIT(24) /* DMAC 0 */ +#define TSI148_LCSR_INTEO_LM3EO BIT(23) /* Loc Monitor 3 */ +#define TSI148_LCSR_INTEO_LM2EO BIT(22) /* Loc Monitor 2 */ +#define TSI148_LCSR_INTEO_LM1EO BIT(21) /* Loc Monitor 1 */ +#define TSI148_LCSR_INTEO_LM0EO BIT(20) /* Location Monitor 0 */ +#define TSI148_LCSR_INTEO_MB3EO BIT(19) /* Mail Box 3 */ +#define TSI148_LCSR_INTEO_MB2EO BIT(18) /* Mail Box 2 */ +#define TSI148_LCSR_INTEO_MB1EO BIT(17) /* Mail Box 1 */ +#define TSI148_LCSR_INTEO_MB0EO BIT(16) /* Mail Box 0 */ +#define TSI148_LCSR_INTEO_PERREO BIT(13) /* PCI/X Error */ +#define TSI148_LCSR_INTEO_VERREO BIT(12) /* VMEbus Error */ +#define TSI148_LCSR_INTEO_VIEEO BIT(11) /* VMEbus IRQ Edge */ +#define TSI148_LCSR_INTEO_IACKEO BIT(10) /* IACK */ +#define TSI148_LCSR_INTEO_SYSFLEO BIT(9) /* System Fail */ +#define TSI148_LCSR_INTEO_ACFLEO BIT(8) /* AC Fail */ +#define TSI148_LCSR_INTEO_IRQ7EO BIT(7) /* IRQ7 */ +#define TSI148_LCSR_INTEO_IRQ6EO BIT(6) /* IRQ6 */ +#define TSI148_LCSR_INTEO_IRQ5EO BIT(5) /* IRQ5 */ +#define TSI148_LCSR_INTEO_IRQ4EO BIT(4) /* IRQ4 */ +#define TSI148_LCSR_INTEO_IRQ3EO BIT(3) /* IRQ3 */ +#define TSI148_LCSR_INTEO_IRQ2EO BIT(2) /* IRQ2 */ +#define TSI148_LCSR_INTEO_IRQ1EO BIT(1) /* IRQ1 */ static const int TSI148_LCSR_INTEO_LMEO[4] = { TSI148_LCSR_INTEO_LM0EO, TSI148_LCSR_INTEO_LM1EO, @@ -1094,29 +1094,29 @@ static const int TSI148_LCSR_INTEO_IRQEO[7] = { TSI148_LCSR_INTEO_IRQ1EO, /* * Interrupt Status Register CRG + $448 */ -#define TSI148_LCSR_INTS_DMA1S (1<<25) /* DMA 1 */ -#define TSI148_LCSR_INTS_DMA0S (1<<24) /* DMA 0 */ -#define TSI148_LCSR_INTS_LM3S (1<<23) /* Location Monitor 3 */ -#define TSI148_LCSR_INTS_LM2S (1<<22) /* Location Monitor 2 */ -#define TSI148_LCSR_INTS_LM1S (1<<21) /* Location Monitor 1 */ -#define TSI148_LCSR_INTS_LM0S (1<<20) /* Location Monitor 0 */ -#define TSI148_LCSR_INTS_MB3S (1<<19) /* Mail Box 3 */ -#define TSI148_LCSR_INTS_MB2S (1<<18) /* Mail Box 2 */ -#define TSI148_LCSR_INTS_MB1S (1<<17) /* Mail Box 1 */ -#define TSI148_LCSR_INTS_MB0S (1<<16) /* Mail Box 0 */ -#define TSI148_LCSR_INTS_PERRS (1<<13) /* PCI/X Error */ -#define TSI148_LCSR_INTS_VERRS (1<<12) /* VMEbus Error */ -#define TSI148_LCSR_INTS_VIES (1<<11) /* VMEbus IRQ Edge */ -#define TSI148_LCSR_INTS_IACKS (1<<10) /* IACK */ -#define TSI148_LCSR_INTS_SYSFLS (1<<9) /* System Fail */ -#define TSI148_LCSR_INTS_ACFLS (1<<8) /* AC Fail */ -#define TSI148_LCSR_INTS_IRQ7S (1<<7) /* IRQ7 */ -#define TSI148_LCSR_INTS_IRQ6S (1<<6) /* IRQ6 */ -#define TSI148_LCSR_INTS_IRQ5S (1<<5) /* IRQ5 */ -#define TSI148_LCSR_INTS_IRQ4S (1<<4) /* IRQ4 */ -#define TSI148_LCSR_INTS_IRQ3S (1<<3) /* IRQ3 */ -#define TSI148_LCSR_INTS_IRQ2S (1<<2) /* IRQ2 */ -#define TSI148_LCSR_INTS_IRQ1S (1<<1) /* IRQ1 */ +#define TSI148_LCSR_INTS_DMA1S BIT(25) /* DMA 1 */ +#define TSI148_LCSR_INTS_DMA0S BIT(24) /* DMA 0 */ +#define TSI148_LCSR_INTS_LM3S BIT(23) /* Location Monitor 3 */ +#define TSI148_LCSR_INTS_LM2S BIT(22) /* Location Monitor 2 */ +#define TSI148_LCSR_INTS_LM1S BIT(21) /* Location Monitor 1 */ +#define TSI148_LCSR_INTS_LM0S BIT(20) /* Location Monitor 0 */ +#define TSI148_LCSR_INTS_MB3S BIT(19) /* Mail Box 3 */ +#define TSI148_LCSR_INTS_MB2S BIT(18) /* Mail Box 2 */ +#define TSI148_LCSR_INTS_MB1S BIT(17) /* Mail Box 1 */ +#define TSI148_LCSR_INTS_MB0S BIT(16) /* Mail Box 0 */ +#define TSI148_LCSR_INTS_PERRS BIT(13) /* PCI/X Error */ +#define TSI148_LCSR_INTS_VERRS BIT(12) /* VMEbus Error */ +#define TSI148_LCSR_INTS_VIES BIT(11) /* VMEbus IRQ Edge */ +#define TSI148_LCSR_INTS_IACKS BIT(10) /* IACK */ +#define TSI148_LCSR_INTS_SYSFLS BIT(9) /* System Fail */ +#define TSI148_LCSR_INTS_ACFLS BIT(8) /* AC Fail */ +#define TSI148_LCSR_INTS_IRQ7S BIT(7) /* IRQ7 */ +#define TSI148_LCSR_INTS_IRQ6S BIT(6) /* IRQ6 */ +#define TSI148_LCSR_INTS_IRQ5S BIT(5) /* IRQ5 */ +#define TSI148_LCSR_INTS_IRQ4S BIT(4) /* IRQ4 */ +#define TSI148_LCSR_INTS_IRQ3S BIT(3) /* IRQ3 */ +#define TSI148_LCSR_INTS_IRQ2S BIT(2) /* IRQ2 */ +#define TSI148_LCSR_INTS_IRQ1S BIT(1) /* IRQ1 */ static const int TSI148_LCSR_INTS_LMS[4] = { TSI148_LCSR_INTS_LM0S, TSI148_LCSR_INTS_LM1S, @@ -1131,22 +1131,22 @@ static const int TSI148_LCSR_INTS_MBS[4] = { TSI148_LCSR_INTS_MB0S, /* * Interrupt Clear Register CRG + $44C */ -#define TSI148_LCSR_INTC_DMA1C (1<<25) /* DMA 1 */ -#define TSI148_LCSR_INTC_DMA0C (1<<24) /* DMA 0 */ -#define TSI148_LCSR_INTC_LM3C (1<<23) /* Location Monitor 3 */ -#define TSI148_LCSR_INTC_LM2C (1<<22) /* Location Monitor 2 */ -#define TSI148_LCSR_INTC_LM1C (1<<21) /* Location Monitor 1 */ -#define TSI148_LCSR_INTC_LM0C (1<<20) /* Location Monitor 0 */ -#define TSI148_LCSR_INTC_MB3C (1<<19) /* Mail Box 3 */ -#define TSI148_LCSR_INTC_MB2C (1<<18) /* Mail Box 2 */ -#define TSI148_LCSR_INTC_MB1C (1<<17) /* Mail Box 1 */ -#define TSI148_LCSR_INTC_MB0C (1<<16) /* Mail Box 0 */ -#define TSI148_LCSR_INTC_PERRC (1<<13) /* VMEbus Error */ -#define TSI148_LCSR_INTC_VERRC (1<<12) /* VMEbus Access Time-out */ -#define TSI148_LCSR_INTC_VIEC (1<<11) /* VMEbus IRQ Edge */ -#define TSI148_LCSR_INTC_IACKC (1<<10) /* IACK */ -#define TSI148_LCSR_INTC_SYSFLC (1<<9) /* System Fail */ -#define TSI148_LCSR_INTC_ACFLC (1<<8) /* AC Fail */ +#define TSI148_LCSR_INTC_DMA1C BIT(25) /* DMA 1 */ +#define TSI148_LCSR_INTC_DMA0C BIT(24) /* DMA 0 */ +#define TSI148_LCSR_INTC_LM3C BIT(23) /* Location Monitor 3 */ +#define TSI148_LCSR_INTC_LM2C BIT(22) /* Location Monitor 2 */ +#define TSI148_LCSR_INTC_LM1C BIT(21) /* Location Monitor 1 */ +#define TSI148_LCSR_INTC_LM0C BIT(20) /* Location Monitor 0 */ +#define TSI148_LCSR_INTC_MB3C BIT(19) /* Mail Box 3 */ +#define TSI148_LCSR_INTC_MB2C BIT(18) /* Mail Box 2 */ +#define TSI148_LCSR_INTC_MB1C BIT(17) /* Mail Box 1 */ +#define TSI148_LCSR_INTC_MB0C BIT(16) /* Mail Box 0 */ +#define TSI148_LCSR_INTC_PERRC BIT(13) /* VMEbus Error */ +#define TSI148_LCSR_INTC_VERRC BIT(12) /* VMEbus Access Time-out */ +#define TSI148_LCSR_INTC_VIEC BIT(11) /* VMEbus IRQ Edge */ +#define TSI148_LCSR_INTC_IACKC BIT(10) /* IACK */ +#define TSI148_LCSR_INTC_SYSFLC BIT(9) /* System Fail */ +#define TSI148_LCSR_INTC_ACFLC BIT(8) /* AC Fail */ static const int TSI148_LCSR_INTC_LMC[4] = { TSI148_LCSR_INTC_LM0C, TSI148_LCSR_INTC_LM1C, @@ -1192,15 +1192,15 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, /* * DMA Control (0-1) Registers CRG + $500 */ -#define TSI148_LCSR_DCTL_ABT (1<<27) /* Abort */ -#define TSI148_LCSR_DCTL_PAU (1<<26) /* Pause */ -#define TSI148_LCSR_DCTL_DGO (1<<25) /* DMA Go */ +#define TSI148_LCSR_DCTL_ABT BIT(27) /* Abort */ +#define TSI148_LCSR_DCTL_PAU BIT(26) /* Pause */ +#define TSI148_LCSR_DCTL_DGO BIT(25) /* DMA Go */ -#define TSI148_LCSR_DCTL_MOD (1<<23) /* Mode */ +#define TSI148_LCSR_DCTL_MOD BIT(23) /* Mode */ #define TSI148_LCSR_DCTL_VBKS_M (7<<12) /* VMEbus block Size MASK */ #define TSI148_LCSR_DCTL_VBKS_32 (0<<12) /* VMEbus block Size 32 */ -#define TSI148_LCSR_DCTL_VBKS_64 (1<<12) /* VMEbus block Size 64 */ +#define TSI148_LCSR_DCTL_VBKS_64 BIT(12) /* VMEbus block Size 64 */ #define TSI148_LCSR_DCTL_VBKS_128 (2<<12) /* VMEbus block Size 128 */ #define TSI148_LCSR_DCTL_VBKS_256 (3<<12) /* VMEbus block Size 256 */ #define TSI148_LCSR_DCTL_VBKS_512 (4<<12) /* VMEbus block Size 512 */ @@ -1210,7 +1210,7 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, #define TSI148_LCSR_DCTL_VBOT_M (7<<8) /* VMEbus back-off MASK */ #define TSI148_LCSR_DCTL_VBOT_0 (0<<8) /* VMEbus back-off 0us */ -#define TSI148_LCSR_DCTL_VBOT_1 (1<<8) /* VMEbus back-off 1us */ +#define TSI148_LCSR_DCTL_VBOT_1 BIT(8) /* VMEbus back-off 1us */ #define TSI148_LCSR_DCTL_VBOT_2 (2<<8) /* VMEbus back-off 2us */ #define TSI148_LCSR_DCTL_VBOT_4 (3<<8) /* VMEbus back-off 4us */ #define TSI148_LCSR_DCTL_VBOT_8 (4<<8) /* VMEbus back-off 8us */ @@ -1220,7 +1220,7 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, #define TSI148_LCSR_DCTL_PBKS_M (7<<4) /* PCI block size MASK */ #define TSI148_LCSR_DCTL_PBKS_32 (0<<4) /* PCI block size 32 bytes */ -#define TSI148_LCSR_DCTL_PBKS_64 (1<<4) /* PCI block size 64 bytes */ +#define TSI148_LCSR_DCTL_PBKS_64 BIT(4) /* PCI block size 64 bytes */ #define TSI148_LCSR_DCTL_PBKS_128 (2<<4) /* PCI block size 128 bytes */ #define TSI148_LCSR_DCTL_PBKS_256 (3<<4) /* PCI block size 256 bytes */ #define TSI148_LCSR_DCTL_PBKS_512 (4<<4) /* PCI block size 512 bytes */ @@ -1230,7 +1230,7 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, #define TSI148_LCSR_DCTL_PBOT_M (7<<0) /* PCI back off MASK */ #define TSI148_LCSR_DCTL_PBOT_0 (0<<0) /* PCI back off 0us */ -#define TSI148_LCSR_DCTL_PBOT_1 (1<<0) /* PCI back off 1us */ +#define TSI148_LCSR_DCTL_PBOT_1 BIT(0) /* PCI back off 1us */ #define TSI148_LCSR_DCTL_PBOT_2 (2<<0) /* PCI back off 2us */ #define TSI148_LCSR_DCTL_PBOT_4 (3<<0) /* PCI back off 3us */ #define TSI148_LCSR_DCTL_PBOT_8 (4<<0) /* PCI back off 4us */ @@ -1241,14 +1241,14 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, /* * DMA Status Registers (0-1) CRG + $504 */ -#define TSI148_LCSR_DSTA_SMA (1<<31) /* PCI Signalled Master Abt */ -#define TSI148_LCSR_DSTA_RTA (1<<30) /* PCI Received Target Abt */ -#define TSI148_LCSR_DSTA_MRC (1<<29) /* PCI Max Retry Count */ -#define TSI148_LCSR_DSTA_VBE (1<<28) /* VMEbus error */ -#define TSI148_LCSR_DSTA_ABT (1<<27) /* Abort */ -#define TSI148_LCSR_DSTA_PAU (1<<26) /* Pause */ -#define TSI148_LCSR_DSTA_DON (1<<25) /* Done */ -#define TSI148_LCSR_DSTA_BSY (1<<24) /* Busy */ +#define TSI148_LCSR_DSTA_SMA BIT(31) /* PCI Signalled Master Abt */ +#define TSI148_LCSR_DSTA_RTA BIT(30) /* PCI Received Target Abt */ +#define TSI148_LCSR_DSTA_MRC BIT(29) /* PCI Max Retry Count */ +#define TSI148_LCSR_DSTA_VBE BIT(28) /* VMEbus error */ +#define TSI148_LCSR_DSTA_ABT BIT(27) /* Abort */ +#define TSI148_LCSR_DSTA_PAU BIT(26) /* Pause */ +#define TSI148_LCSR_DSTA_DON BIT(25) /* Done */ +#define TSI148_LCSR_DSTA_BSY BIT(24) /* Busy */ /* * DMA Current Link Address Lower (0-1) @@ -1260,20 +1260,20 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, */ #define TSI148_LCSR_DSAT_TYP_M (3<<28) /* Source Bus Type */ #define TSI148_LCSR_DSAT_TYP_PCI (0<<28) /* PCI Bus */ -#define TSI148_LCSR_DSAT_TYP_VME (1<<28) /* VMEbus */ +#define TSI148_LCSR_DSAT_TYP_VME BIT(28) /* VMEbus */ #define TSI148_LCSR_DSAT_TYP_PAT (2<<28) /* Data Pattern */ -#define TSI148_LCSR_DSAT_PSZ (1<<25) /* Pattern Size */ -#define TSI148_LCSR_DSAT_NIN (1<<24) /* No Increment */ +#define TSI148_LCSR_DSAT_PSZ BIT(25) /* Pattern Size */ +#define TSI148_LCSR_DSAT_NIN BIT(24) /* No Increment */ #define TSI148_LCSR_DSAT_2eSSTM_M (3<<11) /* 2eSST Trans Rate Mask */ #define TSI148_LCSR_DSAT_2eSSTM_160 (0<<11) /* 160 MB/s */ -#define TSI148_LCSR_DSAT_2eSSTM_267 (1<<11) /* 267 MB/s */ +#define TSI148_LCSR_DSAT_2eSSTM_267 BIT(11) /* 267 MB/s */ #define TSI148_LCSR_DSAT_2eSSTM_320 (2<<11) /* 320 MB/s */ #define TSI148_LCSR_DSAT_TM_M (7<<8) /* Bus Transfer Protocol Mask */ #define TSI148_LCSR_DSAT_TM_SCT (0<<8) /* SCT */ -#define TSI148_LCSR_DSAT_TM_BLT (1<<8) /* BLT */ +#define TSI148_LCSR_DSAT_TM_BLT BIT(8) /* BLT */ #define TSI148_LCSR_DSAT_TM_MBLT (2<<8) /* MBLT */ #define TSI148_LCSR_DSAT_TM_2eVME (3<<8) /* 2eVME */ #define TSI148_LCSR_DSAT_TM_2eSST (4<<8) /* 2eSST */ @@ -1281,14 +1281,14 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, #define TSI148_LCSR_DSAT_DBW_M (3<<6) /* Max Data Width MASK */ #define TSI148_LCSR_DSAT_DBW_16 (0<<6) /* 16 Bits */ -#define TSI148_LCSR_DSAT_DBW_32 (1<<6) /* 32 Bits */ +#define TSI148_LCSR_DSAT_DBW_32 BIT(6) /* 32 Bits */ -#define TSI148_LCSR_DSAT_SUP (1<<5) /* Supervisory Mode */ -#define TSI148_LCSR_DSAT_PGM (1<<4) /* Program Mode */ +#define TSI148_LCSR_DSAT_SUP BIT(5) /* Supervisory Mode */ +#define TSI148_LCSR_DSAT_PGM BIT(4) /* Program Mode */ #define TSI148_LCSR_DSAT_AMODE_M (0xf<<0) /* Address Space Mask */ #define TSI148_LCSR_DSAT_AMODE_A16 (0<<0) /* A16 */ -#define TSI148_LCSR_DSAT_AMODE_A24 (1<<0) /* A24 */ +#define TSI148_LCSR_DSAT_AMODE_A24 BIT(0) /* A24 */ #define TSI148_LCSR_DSAT_AMODE_A32 (2<<0) /* A32 */ #define TSI148_LCSR_DSAT_AMODE_A64 (4<<0) /* A64 */ #define TSI148_LCSR_DSAT_AMODE_CRCSR (5<<0) /* CR/CSR */ @@ -1301,16 +1301,16 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, * DMA Destination Attribute Registers (0-1) */ #define TSI148_LCSR_DDAT_TYP_PCI (0<<28) /* Destination PCI Bus */ -#define TSI148_LCSR_DDAT_TYP_VME (1<<28) /* Destination VMEbus */ +#define TSI148_LCSR_DDAT_TYP_VME BIT(28) /* Destination VMEbus */ #define TSI148_LCSR_DDAT_2eSSTM_M (3<<11) /* 2eSST Transfer Rate Mask */ #define TSI148_LCSR_DDAT_2eSSTM_160 (0<<11) /* 160 MB/s */ -#define TSI148_LCSR_DDAT_2eSSTM_267 (1<<11) /* 267 MB/s */ +#define TSI148_LCSR_DDAT_2eSSTM_267 BIT(11) /* 267 MB/s */ #define TSI148_LCSR_DDAT_2eSSTM_320 (2<<11) /* 320 MB/s */ #define TSI148_LCSR_DDAT_TM_M (7<<8) /* Bus Transfer Protocol Mask */ #define TSI148_LCSR_DDAT_TM_SCT (0<<8) /* SCT */ -#define TSI148_LCSR_DDAT_TM_BLT (1<<8) /* BLT */ +#define TSI148_LCSR_DDAT_TM_BLT BIT(8) /* BLT */ #define TSI148_LCSR_DDAT_TM_MBLT (2<<8) /* MBLT */ #define TSI148_LCSR_DDAT_TM_2eVME (3<<8) /* 2eVME */ #define TSI148_LCSR_DDAT_TM_2eSST (4<<8) /* 2eSST */ @@ -1318,14 +1318,14 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, #define TSI148_LCSR_DDAT_DBW_M (3<<6) /* Max Data Width MASK */ #define TSI148_LCSR_DDAT_DBW_16 (0<<6) /* 16 Bits */ -#define TSI148_LCSR_DDAT_DBW_32 (1<<6) /* 32 Bits */ +#define TSI148_LCSR_DDAT_DBW_32 BIT(6) /* 32 Bits */ -#define TSI148_LCSR_DDAT_SUP (1<<5) /* Supervisory/User Access */ -#define TSI148_LCSR_DDAT_PGM (1<<4) /* Program/Data Access */ +#define TSI148_LCSR_DDAT_SUP BIT(5) /* Supervisory/User Access */ +#define TSI148_LCSR_DDAT_PGM BIT(4) /* Program/Data Access */ #define TSI148_LCSR_DDAT_AMODE_M (0xf<<0) /* Address Space Mask */ #define TSI148_LCSR_DDAT_AMODE_A16 (0<<0) /* A16 */ -#define TSI148_LCSR_DDAT_AMODE_A24 (1<<0) /* A24 */ +#define TSI148_LCSR_DDAT_AMODE_A24 BIT(0) /* A24 */ #define TSI148_LCSR_DDAT_AMODE_A32 (2<<0) /* A32 */ #define TSI148_LCSR_DDAT_AMODE_A64 (4<<0) /* A64 */ #define TSI148_LCSR_DDAT_AMODE_CRCSR (5<<0) /* CRC/SR */ @@ -1338,7 +1338,7 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, * DMA Next Link Address Lower */ #define TSI148_LCSR_DNLAL_DNLAL_M (0x3FFFFFF<<6) /* Address Mask */ -#define TSI148_LCSR_DNLAL_LLA (1<<0) /* Last Link Address Indicator */ +#define TSI148_LCSR_DNLAL_LLA BIT(0) /* Last Link Address Indicator */ /* * DMA 2eSST Broadcast Select @@ -1352,22 +1352,22 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, /* * GCSR Control and Status Register CRG + $604 */ -#define TSI148_GCSR_GCTRL_LRST (1<<15) /* Local Reset */ -#define TSI148_GCSR_GCTRL_SFAILEN (1<<14) /* System Fail enable */ -#define TSI148_GCSR_GCTRL_BDFAILS (1<<13) /* Board Fail Status */ -#define TSI148_GCSR_GCTRL_SCON (1<<12) /* System Copntroller */ -#define TSI148_GCSR_GCTRL_MEN (1<<11) /* Module Enable (READY) */ - -#define TSI148_GCSR_GCTRL_LMI3S (1<<7) /* Loc Monitor 3 Int Status */ -#define TSI148_GCSR_GCTRL_LMI2S (1<<6) /* Loc Monitor 2 Int Status */ -#define TSI148_GCSR_GCTRL_LMI1S (1<<5) /* Loc Monitor 1 Int Status */ -#define TSI148_GCSR_GCTRL_LMI0S (1<<4) /* Loc Monitor 0 Int Status */ -#define TSI148_GCSR_GCTRL_MBI3S (1<<3) /* Mail box 3 Int Status */ -#define TSI148_GCSR_GCTRL_MBI2S (1<<2) /* Mail box 2 Int Status */ -#define TSI148_GCSR_GCTRL_MBI1S (1<<1) /* Mail box 1 Int Status */ -#define TSI148_GCSR_GCTRL_MBI0S (1<<0) /* Mail box 0 Int Status */ - -#define TSI148_GCSR_GAP (1<<5) /* Geographic Addr Parity */ +#define TSI148_GCSR_GCTRL_LRST BIT(15) /* Local Reset */ +#define TSI148_GCSR_GCTRL_SFAILEN BIT(14) /* System Fail enable */ +#define TSI148_GCSR_GCTRL_BDFAILS BIT(13) /* Board Fail Status */ +#define TSI148_GCSR_GCTRL_SCON BIT(12) /* System Copntroller */ +#define TSI148_GCSR_GCTRL_MEN BIT(11) /* Module Enable (READY) */ + +#define TSI148_GCSR_GCTRL_LMI3S BIT(7) /* Loc Monitor 3 Int Status */ +#define TSI148_GCSR_GCTRL_LMI2S BIT(6) /* Loc Monitor 2 Int Status */ +#define TSI148_GCSR_GCTRL_LMI1S BIT(5) /* Loc Monitor 1 Int Status */ +#define TSI148_GCSR_GCTRL_LMI0S BIT(4) /* Loc Monitor 0 Int Status */ +#define TSI148_GCSR_GCTRL_MBI3S BIT(3) /* Mail box 3 Int Status */ +#define TSI148_GCSR_GCTRL_MBI2S BIT(2) /* Mail box 2 Int Status */ +#define TSI148_GCSR_GCTRL_MBI1S BIT(1) /* Mail box 1 Int Status */ +#define TSI148_GCSR_GCTRL_MBI0S BIT(0) /* Mail box 0 Int Status */ + +#define TSI148_GCSR_GAP BIT(5) /* Geographic Addr Parity */ #define TSI148_GCSR_GA_M (0x1F<<0) /* Geographic Address Mask */ /* @@ -1377,20 +1377,20 @@ static const int TSI148_LCSR_INTC_MBC[4] = { TSI148_LCSR_INTC_MB0C, /* * CR/CSR Bit Clear Register CRG + $FF4 */ -#define TSI148_CRCSR_CSRBCR_LRSTC (1<<7) /* Local Reset Clear */ -#define TSI148_CRCSR_CSRBCR_SFAILC (1<<6) /* System Fail Enable Clear */ -#define TSI148_CRCSR_CSRBCR_BDFAILS (1<<5) /* Board Fail Status */ -#define TSI148_CRCSR_CSRBCR_MENC (1<<4) /* Module Enable Clear */ -#define TSI148_CRCSR_CSRBCR_BERRSC (1<<3) /* Bus Error Status Clear */ +#define TSI148_CRCSR_CSRBCR_LRSTC BIT(7) /* Local Reset Clear */ +#define TSI148_CRCSR_CSRBCR_SFAILC BIT(6) /* System Fail Enable Clear */ +#define TSI148_CRCSR_CSRBCR_BDFAILS BIT(5) /* Board Fail Status */ +#define TSI148_CRCSR_CSRBCR_MENC BIT(4) /* Module Enable Clear */ +#define TSI148_CRCSR_CSRBCR_BERRSC BIT(3) /* Bus Error Status Clear */ /* * CR/CSR Bit Set Register CRG+$FF8 */ -#define TSI148_CRCSR_CSRBSR_LISTS (1<<7) /* Local Reset Clear */ -#define TSI148_CRCSR_CSRBSR_SFAILS (1<<6) /* System Fail Enable Clear */ -#define TSI148_CRCSR_CSRBSR_BDFAILS (1<<5) /* Board Fail Status */ -#define TSI148_CRCSR_CSRBSR_MENS (1<<4) /* Module Enable Clear */ -#define TSI148_CRCSR_CSRBSR_BERRS (1<<3) /* Bus Error Status Clear */ +#define TSI148_CRCSR_CSRBSR_LISTS BIT(7) /* Local Reset Clear */ +#define TSI148_CRCSR_CSRBSR_SFAILS BIT(6) /* System Fail Enable Clear */ +#define TSI148_CRCSR_CSRBSR_BDFAILS BIT(5) /* Board Fail Status */ +#define TSI148_CRCSR_CSRBSR_MENS BIT(4) /* Module Enable Clear */ +#define TSI148_CRCSR_CSRBSR_BERRS BIT(3) /* Bus Error Status Clear */ /* * CR/CSR Base Address Register CRG + FFC -- GitLab From b4474375481fbdd6f8568aadc5ccf6acf09cf997 Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sat, 25 Mar 2023 14:28:20 +0100 Subject: [PATCH 1331/5631] staging: rtl8192e: remove RTL819X_DEFAULT_RF_TYPE Remove RTL819X_DEFAULT_RF_TYPE and use RF_1T2R directly to make follow up patches, which will remove priv->rf_type, easier to review. Signed-off-by: Michael Straube Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230325132823.22872-2-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index a67927f0c5e3..3027d43cb362 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -343,7 +343,7 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) else priv->tx_pwr_data_read_from_eeprom = false; - priv->rf_type = RTL819X_DEFAULT_RF_TYPE; + priv->rf_type = RF_1T2R; if (priv->card_8192_version > VERSION_8190_BD) { if (!priv->autoload_fail_flag) { diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 68ec0aeb2dd9..914cd28897a5 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -61,8 +61,6 @@ #define HAL_HW_PCI_REVISION_ID_8192PCIE 0x01 #define HAL_HW_PCI_REVISION_ID_8192SE 0x10 -#define RTL819X_DEFAULT_RF_TYPE RF_1T2R - #define RTLLIB_WATCH_DOG_TIME 2000 #define MAX_DEV_ADDR_SIZE 8 /*support till 64 bit bus width OS*/ -- GitLab From a3ed769cc229e7d395f9c772e5db72ded643169d Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sat, 25 Mar 2023 14:28:21 +0100 Subject: [PATCH 1332/5631] staging: rtl8192e: remove redundant setting of rf_type At this point the value of priv->rf_type is RF_1T2R already. Setting it again is redundant and can be removed. Signed-off-by: Michael Straube Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230325132823.22872-3-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 3027d43cb362..0e0096ef4943 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -350,10 +350,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) tempval = (rtl92e_eeprom_read(dev, (EEPROM_RFInd_PowerDiff >> 1))) & 0xff; priv->eeprom_legacy_ht_tx_pwr_diff = tempval & 0xf; - - if (tempval&0x80) - priv->rf_type = RF_1T2R; - } else { priv->eeprom_legacy_ht_tx_pwr_diff = 0x04; } -- GitLab From 2fd65482d923ee09a6e133dcc15f988a4a44420b Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sat, 25 Mar 2023 14:28:22 +0100 Subject: [PATCH 1333/5631] staging: rtl8192e: priv->rf_type is always RF_1T2R The value of priv->rf_type is always RF_1T2R. Remove if statements that check for priv->rf_type == RF_1T2R and remove resulting dead code. Signed-off-by: Michael Straube Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230325132823.22872-4-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- .../staging/rtl8192e/rtl8192e/r8192E_dev.c | 13 ++++------- .../staging/rtl8192e/rtl8192e/r8192E_phy.c | 7 ++---- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 23 +++++++------------ 3 files changed, 14 insertions(+), 29 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 0e0096ef4943..b237970ecf85 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -540,8 +540,7 @@ static void _rtl92e_hwconfig(struct net_device *dev) u32 ratr_value; ratr_value = regRATR; - if (priv->rf_type == RF_1T2R) - ratr_value &= ~(RATE_ALL_OFDM_2SS); + ratr_value &= ~(RATE_ALL_OFDM_2SS); rtl92e_writel(dev, RATR0, ratr_value); rtl92e_writeb(dev, UFWP, 1); } @@ -1886,14 +1885,10 @@ void rtl92e_update_ratr_table(struct net_device *dev) break; case IEEE_N_24G: case IEEE_N_5G: - if (ieee->ht_info->peer_mimo_ps == 0) { + if (ieee->ht_info->peer_mimo_ps == 0) ratr_value &= 0x0007F007; - } else { - if (priv->rf_type == RF_1T2R) - ratr_value &= 0x000FF007; - else - ratr_value &= 0x0F81F007; - } + else + ratr_value &= 0x000FF007; break; default: break; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index b1c297d2ae36..bd302f5cb356 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -281,14 +281,11 @@ static void _rtl92e_phy_config_bb(struct net_device *dev, u8 ConfigType) u32 *Rtl819XPHY_REGArray_Table = NULL; u32 *Rtl819XAGCTAB_Array_Table = NULL; u16 AGCTAB_ArrayLen, PHY_REGArrayLen = 0; - struct r8192_priv *priv = rtllib_priv(dev); AGCTAB_ArrayLen = RTL8192E_AGCTAB_ARR_LEN; Rtl819XAGCTAB_Array_Table = RTL8192E_AGCTAB_ARR; - if (priv->rf_type == RF_1T2R) { - PHY_REGArrayLen = RTL8192E_PHY_REG_1T2R_ARR_LEN; - Rtl819XPHY_REGArray_Table = RTL8192E_PHY_REG_1T2R_ARR; - } + PHY_REGArrayLen = RTL8192E_PHY_REG_1T2R_ARR_LEN; + Rtl819XPHY_REGArray_Table = RTL8192E_PHY_REG_1T2R_ARR; if (ConfigType == BB_CONFIG_PHY_REG) { for (i = 0; i < PHY_REGArrayLen; i += 2) { diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index b745b73eedea..46be638677d9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -272,19 +272,14 @@ void rtl92e_init_adaptive_rate(struct net_device *dev) pra->ping_rssi_enable = 0; pra->ping_rssi_thresh_for_ra = 15; - - if (priv->rf_type == RF_1T2R) { - pra->upper_rssi_threshold_ratr = 0x000fc000; - pra->middle_rssi_threshold_ratr = 0x000ff000; - pra->low_rssi_threshold_ratr = 0x000ff001; - pra->low_rssi_threshold_ratr_40M = 0x000ff005; - pra->low_rssi_threshold_ratr_20M = 0x000ff001; - pra->ping_rssi_ratr = 0x0000000d; - } - + pra->upper_rssi_threshold_ratr = 0x000fc000; + pra->middle_rssi_threshold_ratr = 0x000ff000; + pra->low_rssi_threshold_ratr = 0x000ff001; + pra->low_rssi_threshold_ratr_40M = 0x000ff005; + pra->low_rssi_threshold_ratr_20M = 0x000ff001; + pra->ping_rssi_ratr = 0x0000000d; } - static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev) { struct r8192_priv *priv = rtllib_priv(dev); @@ -383,8 +378,7 @@ static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev) u32 ratr_value; ratr_value = targetRATR; - if (priv->rf_type == RF_1T2R) - ratr_value &= ~(RATE_ALL_OFDM_2SS); + ratr_value &= ~(RATE_ALL_OFDM_2SS); rtl92e_writel(dev, RATR0, ratr_value); rtl92e_writeb(dev, UFWP, 1); @@ -981,8 +975,7 @@ void rtl92e_dm_restore_state(struct net_device *dev) priv->rtllib->mode == WIRELESS_MODE_N_5G)) return; ratr_value = reg_ratr; - if (priv->rf_type == RF_1T2R) - ratr_value &= ~(RATE_ALL_OFDM_2SS); + ratr_value &= ~(RATE_ALL_OFDM_2SS); rtl92e_writel(dev, RATR0, ratr_value); rtl92e_writeb(dev, UFWP, 1); if (priv->tx_pwr_tracking_init && priv->btxpower_tracking) -- GitLab From 91de7cdc784f28655eb97de3e66ede0ada94b6eb Mon Sep 17 00:00:00 2001 From: Michael Straube Date: Sat, 25 Mar 2023 14:28:23 +0100 Subject: [PATCH 1334/5631] staging: rtl8192e: remove rf_type from struct r8192_priv The field rf_type of struct r8192_priv is always RF_1T2R and only used in one place. Use RF_1T2R directly there and remove rf_type from struct r8192_priv. Signed-off-by: Michael Straube Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230325132823.22872-5-straube.linux@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 -- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 2 +- 3 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index b237970ecf85..1eb063fe660a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -343,8 +343,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) else priv->tx_pwr_data_read_from_eeprom = false; - priv->rf_type = RF_1T2R; - if (priv->card_8192_version > VERSION_8190_BD) { if (!priv->autoload_fail_flag) { tempval = (rtl92e_eeprom_read(dev, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 914cd28897a5..1e99eb833405 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -289,7 +289,6 @@ struct r8192_priv { enum nic_t card_8192; u8 card_8192_version; - u8 rf_type; u8 ic_cut; char nick[IW_ESSID_MAX_SIZE + 1]; u8 check_roaming_cnt; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 46be638677d9..d45808760638 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -532,7 +532,7 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) priv->rtllib->bdynamic_txpower_enable = false; powerlevelOFDM24G = priv->pwr_track >> 24; - RF_Type = priv->rf_type; + RF_Type = RF_1T2R; Value = (RF_Type<<8) | powerlevelOFDM24G; for (j = 0; j <= 30; j++) { -- GitLab From b07c8ef8c60a4714fad3d7c95a8e464ad83ca715 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Sat, 25 Mar 2023 23:45:19 -0700 Subject: [PATCH 1335/5631] staging: greybus: Inline pwm_chip_to_gb_pwm_chip() Convert 'pwm_chip_to_gb_pwm_chip' from a macro to a static inline function, to make the relevant types apparent in the definition and to benefit from the type checking performed by the compiler at call sites. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230326064519.GA179449@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/pwm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/staging/greybus/pwm.c b/drivers/staging/greybus/pwm.c index 26d39e08c3b6..88da1d796f13 100644 --- a/drivers/staging/greybus/pwm.c +++ b/drivers/staging/greybus/pwm.c @@ -21,8 +21,11 @@ struct gb_pwm_chip { struct pwm_chip chip; struct pwm_chip *pwm; }; -#define pwm_chip_to_gb_pwm_chip(chip) \ - container_of(chip, struct gb_pwm_chip, chip) + +static inline struct gb_pwm_chip *pwm_chip_to_gb_pwm_chip(struct pwm_chip *chip) +{ + return container_of(chip, struct gb_pwm_chip, chip); +} static int gb_pwm_count_operation(struct gb_pwm_chip *pwmc) { -- GitLab From d9bc0d11e33bd7b6bfeedc570cd5738e5b4c7ca8 Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Thu, 8 Dec 2022 02:40:37 +0000 Subject: [PATCH 1336/5631] fs/9p: Consolidate file operations and add readahead and writeback We had 3 different sets of file operations across 2 different protocol variants differentiated by cache which really only changed 3 functions. But the real problem is that certain file modes, mount options, and other factors weren't being considered when we decided whether or not to use caches. This consolidates all the operations and switches to conditionals within a common set to decide whether or not to do different aspects of caching. Signed-off-by: Eric Van Hensbergen Reviewed-by: Dominique Martinet --- fs/9p/v9fs.c | 30 ++++------ fs/9p/v9fs.h | 2 + fs/9p/v9fs_vfs.h | 4 -- fs/9p/vfs_dir.c | 10 +++- fs/9p/vfs_file.c | 131 +++++++---------------------------------- fs/9p/vfs_inode.c | 44 +++++++------- fs/9p/vfs_inode_dotl.c | 30 ++++++++-- 7 files changed, 89 insertions(+), 162 deletions(-) diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 61a51b90600d..a46bf9121f11 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -39,8 +39,6 @@ enum { Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag, /* Options that take no arguments */ Opt_nodevmap, - /* Cache options */ - Opt_cache_loose, Opt_fscache, Opt_mmap, /* Access options */ Opt_access, Opt_posixacl, /* Lock timeout option */ @@ -58,9 +56,6 @@ static const match_table_t tokens = { {Opt_remotename, "aname=%s"}, {Opt_nodevmap, "nodevmap"}, {Opt_cache, "cache=%s"}, - {Opt_cache_loose, "loose"}, - {Opt_fscache, "fscache"}, - {Opt_mmap, "mmap"}, {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, @@ -69,10 +64,12 @@ static const match_table_t tokens = { }; static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { - [CACHE_NONE] = "none", - [CACHE_MMAP] = "mmap", - [CACHE_LOOSE] = "loose", - [CACHE_FSCACHE] = "fscache", + [CACHE_NONE] = "none", + [CACHE_READAHEAD] = "readahead", + [CACHE_WRITEBACK] = "writeback", + [CACHE_MMAP] = "mmap", + [CACHE_LOOSE] = "loose", + [CACHE_FSCACHE] = "fscache", }; /* Interpret mount options for cache mode */ @@ -89,6 +86,12 @@ static int get_cache_mode(char *s) } else if (!strcmp(s, "mmap")) { version = CACHE_MMAP; p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n"); + } else if (!strcmp(s, "writeback")) { + version = CACHE_WRITEBACK; + p9_debug(P9_DEBUG_9P, "Cache mode: writeback\n"); + } else if (!strcmp(s, "readahead")) { + version = CACHE_READAHEAD; + p9_debug(P9_DEBUG_9P, "Cache mode: readahead\n"); } else if (!strcmp(s, "none")) { version = CACHE_NONE; p9_debug(P9_DEBUG_9P, "Cache mode: none\n"); @@ -266,15 +269,6 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) case Opt_nodevmap: v9ses->nodev = 1; break; - case Opt_cache_loose: - v9ses->cache = CACHE_LOOSE; - break; - case Opt_fscache: - v9ses->cache = CACHE_FSCACHE; - break; - case Opt_mmap: - v9ses->cache = CACHE_MMAP; - break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index f3f74d197b5d..e5d41804b3cd 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -50,6 +50,8 @@ enum p9_session_flags { enum p9_cache_modes { CACHE_NONE, + CACHE_READAHEAD, + CACHE_WRITEBACK, CACHE_MMAP, CACHE_LOOSE, CACHE_FSCACHE, diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 75106b9f293d..cdf441f22e07 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -36,10 +36,6 @@ extern const struct file_operations v9fs_dir_operations; extern const struct file_operations v9fs_dir_operations_dotl; extern const struct dentry_operations v9fs_dentry_operations; extern const struct dentry_operations v9fs_cached_dentry_operations; -extern const struct file_operations v9fs_cached_file_operations; -extern const struct file_operations v9fs_cached_file_operations_dotl; -extern const struct file_operations v9fs_mmap_file_operations; -extern const struct file_operations v9fs_mmap_file_operations_dotl; extern struct kmem_cache *v9fs_inode_cache; struct inode *v9fs_alloc_inode(struct super_block *sb); diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 3d74b04fe0de..289b58cb896e 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -197,9 +197,9 @@ static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx) /** - * v9fs_dir_release - called on a close of a file or directory - * @inode: inode of the directory - * @filp: file pointer to a directory + * v9fs_dir_release - close a directory or a file + * @inode: inode of the directory or file + * @filp: file pointer to a directory or file * */ @@ -214,7 +214,11 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) fid = filp->private_data; p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n", inode, filp, fid ? fid->fid : -1); + if (fid) { + if ((S_ISREG(inode->i_mode)) && (filp->f_mode & FMODE_WRITE)) + retval = filemap_fdatawrite(inode->i_mapping); + spin_lock(&inode->i_lock); hlist_del(&fid->ilist); spin_unlock(&inode->i_lock); diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 44c15eb2b908..cd1f3f4079d7 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -29,7 +29,6 @@ #include "fid.h" #include "cache.h" -static const struct vm_operations_struct v9fs_file_vm_ops; static const struct vm_operations_struct v9fs_mmap_file_vm_ops; /** @@ -74,7 +73,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) } mutex_lock(&v9inode->v_mutex); - if ((v9ses->cache) && !v9inode->writeback_fid && + if ((v9ses->cache >= CACHE_WRITEBACK) && !v9inode->writeback_fid && ((file->f_flags & O_ACCMODE) != O_RDONLY)) { /* * clone a fid and add it to writeback_fid @@ -368,10 +367,15 @@ v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct p9_fid *fid = iocb->ki_filp->private_data; int ret, err = 0; + struct inode *inode = file_inode(iocb->ki_filp); + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", iov_iter_count(to), iocb->ki_pos); + if (v9ses->cache > CACHE_MMAP) + return generic_file_read_iter(iocb, to); + if (iocb->ki_filp->f_flags & O_NONBLOCK) ret = p9_client_read_once(fid, iocb->ki_pos, to, &err); else @@ -396,6 +400,11 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t retval; loff_t origin; int err = 0; + struct inode *inode = file_inode(iocb->ki_filp); + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); + + if (v9ses->cache >= CACHE_WRITEBACK) + return generic_file_write_iter(iocb, from); retval = generic_write_checks(iocb, from); if (retval <= 0) @@ -478,25 +487,16 @@ static int v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) { int retval; - - - retval = generic_file_mmap(filp, vma); - if (!retval) - vma->vm_ops = &v9fs_file_vm_ops; - - return retval; -} - -static int -v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) -{ - int retval; - struct inode *inode; - struct v9fs_inode *v9inode; + struct inode *inode = file_inode(filp); + struct v9fs_inode *v9inode = V9FS_I(inode); + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); struct p9_fid *fid; - inode = file_inode(filp); - v9inode = V9FS_I(inode); + if (v9ses->cache < CACHE_MMAP) { + invalidate_inode_pages2(filp->f_mapping); + return generic_file_readonly_mmap(filp, vma); + } + mutex_lock(&v9inode->v_mutex); if (!v9inode->writeback_fid && (vma->vm_flags & VM_SHARED) && @@ -564,35 +564,6 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) return VM_FAULT_NOPAGE; } -/** - * v9fs_mmap_file_read_iter - read from a file - * @iocb: The operation parameters - * @to: The buffer to read into - * - */ -static ssize_t -v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to) -{ - /* TODO: Check if there are dirty pages */ - return v9fs_file_read_iter(iocb, to); -} - -/** - * v9fs_mmap_file_write_iter - write to a file - * @iocb: The operation parameters - * @from: The data to write - * - */ -static ssize_t -v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from) -{ - /* - * TODO: invalidate mmaps on filp's inode between - * offset and offset+count - */ - return v9fs_file_write_iter(iocb, from); -} - static void v9fs_mmap_vm_close(struct vm_area_struct *vma) { struct inode *inode; @@ -615,13 +586,6 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) filemap_fdatawrite_wbc(inode->i_mapping, &wbc); } - -static const struct vm_operations_struct v9fs_file_vm_ops = { - .fault = filemap_fault, - .map_pages = filemap_map_pages, - .page_mkwrite = v9fs_vm_page_mkwrite, -}; - static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .close = v9fs_mmap_vm_close, .fault = filemap_fault, @@ -629,34 +593,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .page_mkwrite = v9fs_vm_page_mkwrite, }; - -const struct file_operations v9fs_cached_file_operations = { - .llseek = generic_file_llseek, - .read_iter = generic_file_read_iter, - .write_iter = generic_file_write_iter, - .open = v9fs_file_open, - .release = v9fs_dir_release, - .lock = v9fs_file_lock, - .mmap = v9fs_file_mmap, - .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, - .fsync = v9fs_file_fsync, -}; - -const struct file_operations v9fs_cached_file_operations_dotl = { - .llseek = generic_file_llseek, - .read_iter = generic_file_read_iter, - .write_iter = generic_file_write_iter, - .open = v9fs_file_open, - .release = v9fs_dir_release, - .lock = v9fs_file_lock_dotl, - .flock = v9fs_file_flock_dotl, - .mmap = v9fs_file_mmap, - .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, - .fsync = v9fs_file_fsync_dotl, -}; - const struct file_operations v9fs_file_operations = { .llseek = generic_file_llseek, .read_iter = v9fs_file_read_iter, @@ -678,34 +614,7 @@ const struct file_operations v9fs_file_operations_dotl = { .release = v9fs_dir_release, .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, - .mmap = generic_file_readonly_mmap, - .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, - .fsync = v9fs_file_fsync_dotl, -}; - -const struct file_operations v9fs_mmap_file_operations = { - .llseek = generic_file_llseek, - .read_iter = v9fs_mmap_file_read_iter, - .write_iter = v9fs_mmap_file_write_iter, - .open = v9fs_file_open, - .release = v9fs_dir_release, - .lock = v9fs_file_lock, - .mmap = v9fs_mmap_file_mmap, - .splice_read = generic_file_splice_read, - .splice_write = iter_file_splice_write, - .fsync = v9fs_file_fsync, -}; - -const struct file_operations v9fs_mmap_file_operations_dotl = { - .llseek = generic_file_llseek, - .read_iter = v9fs_mmap_file_read_iter, - .write_iter = v9fs_mmap_file_write_iter, - .open = v9fs_file_open, - .release = v9fs_dir_release, - .lock = v9fs_file_lock_dotl, - .flock = v9fs_file_flock_dotl, - .mmap = v9fs_mmap_file_mmap, + .mmap = v9fs_file_mmap, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 1d523bec0a94..63590f55363b 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -287,24 +287,10 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, case S_IFREG: if (v9fs_proto_dotl(v9ses)) { inode->i_op = &v9fs_file_inode_operations_dotl; - if (v9ses->cache == CACHE_LOOSE || - v9ses->cache == CACHE_FSCACHE) - inode->i_fop = - &v9fs_cached_file_operations_dotl; - else if (v9ses->cache == CACHE_MMAP) - inode->i_fop = &v9fs_mmap_file_operations_dotl; - else - inode->i_fop = &v9fs_file_operations_dotl; + inode->i_fop = &v9fs_file_operations_dotl; } else { inode->i_op = &v9fs_file_inode_operations; - if (v9ses->cache == CACHE_LOOSE || - v9ses->cache == CACHE_FSCACHE) - inode->i_fop = - &v9fs_cached_file_operations; - else if (v9ses->cache == CACHE_MMAP) - inode->i_fop = &v9fs_mmap_file_operations; - else - inode->i_fop = &v9fs_file_operations; + inode->i_fop = &v9fs_file_operations; } break; @@ -843,7 +829,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, inode = d_inode(dentry); v9inode = V9FS_I(inode); mutex_lock(&v9inode->v_mutex); - if ((v9ses->cache) && !v9inode->writeback_fid && + if ((v9ses->cache >= CACHE_WRITEBACK) && !v9inode->writeback_fid && ((flags & O_ACCMODE) != O_RDONLY)) { /* * clone a fid and add it to writeback_fid @@ -1030,6 +1016,7 @@ v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); struct v9fs_session_info *v9ses; struct p9_fid *fid; struct p9_wstat *st; @@ -1039,6 +1026,14 @@ v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); return 0; + } else if (v9ses->cache >= CACHE_WRITEBACK) { + if (S_ISREG(inode->i_mode)) { + int retval = filemap_fdatawrite(inode->i_mapping); + + if (retval) + p9_debug(P9_DEBUG_ERROR, + "flushing writeback during getattr returned %d\n", retval); + } } fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) @@ -1115,8 +1110,12 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, } /* Write all dirty data */ - if (d_is_reg(dentry)) - filemap_write_and_wait(inode->i_mapping); + if (d_is_reg(dentry)) { + retval = filemap_fdatawrite(inode->i_mapping); + if (retval) + p9_debug(P9_DEBUG_ERROR, + "flushing writeback during setattr returned %d\n", retval); + } retval = p9_client_wstat(fid, &wstat); @@ -1127,9 +1126,12 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, return retval; if ((iattr->ia_valid & ATTR_SIZE) && - iattr->ia_size != i_size_read(inode)) { + iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); - fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); + if (v9ses->cache == CACHE_FSCACHE) + fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); + else + invalidate_mapping_pages(&inode->i_data, 0, -1); } v9fs_invalidate_inode_attr(inode); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 331ed60d8fcb..a28eb3aeab29 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -458,6 +458,7 @@ v9fs_vfs_getattr_dotl(struct mnt_idmap *idmap, struct dentry *dentry = path->dentry; struct v9fs_session_info *v9ses; struct p9_fid *fid; + struct inode *inode = d_inode(dentry); struct p9_stat_dotl *st; p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); @@ -465,6 +466,14 @@ v9fs_vfs_getattr_dotl(struct mnt_idmap *idmap, if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); return 0; + } else if (v9ses->cache >= CACHE_WRITEBACK) { + if (S_ISREG(inode->i_mode)) { + int retval = filemap_fdatawrite(inode->i_mapping); + + if (retval) + p9_debug(P9_DEBUG_ERROR, + "flushing writeback during getattr returned %d\n", retval); + } } fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) @@ -540,12 +549,14 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; + struct inode *inode = d_inode(dentry); + struct v9fs_inode *v9inode = V9FS_I(inode); + struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_iattr_dotl p9attr = { .uid = INVALID_UID, .gid = INVALID_GID, }; - struct inode *inode = d_inode(dentry); p9_debug(P9_DEBUG_VFS, "\n"); @@ -553,6 +564,8 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, if (retval) return retval; + v9ses = v9fs_dentry2v9ses(dentry); + p9attr.valid = v9fs_mapped_iattr_valid(iattr->ia_valid); if (iattr->ia_valid & ATTR_MODE) p9attr.mode = iattr->ia_mode; @@ -583,8 +596,12 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, return PTR_ERR(fid); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) - filemap_write_and_wait(inode->i_mapping); + if (S_ISREG(inode->i_mode)) { + retval = filemap_fdatawrite(inode->i_mapping); + if (retval < 0) + p9_debug(P9_DEBUG_ERROR, + "Flushing file prior to setattr failed: %d\n", retval); + } retval = p9_client_setattr(fid, &p9attr); if (retval < 0) { @@ -593,9 +610,12 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, return retval; } - if ((iattr->ia_valid & ATTR_SIZE) && - iattr->ia_size != i_size_read(inode)) + if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != + i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); + if (v9ses->cache == CACHE_FSCACHE) + fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); + } v9fs_invalidate_inode_attr(inode); setattr_copy(&nop_mnt_idmap, inode, iattr); -- GitLab From 740b8bf87322701b4607b77346477cbc764f5c56 Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Sat, 17 Dec 2022 17:05:47 +0000 Subject: [PATCH 1337/5631] fs/9p: Remove unnecessary superblock flags These flags just add unnecessary extra operations. When 9p is run without cache, it inherently implements these options so we don't need them in the superblock (which ends up sending extraneous fsyncs, etc.). User can still request these options on mount, but we don't need to set them as default. Signed-off-by: Eric Van Hensbergen --- fs/9p/vfs_super.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 266c4693e20c..65d96fa94ba2 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -84,9 +84,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_bdi->io_pages = v9ses->maxdata >> PAGE_SHIFT; } - sb->s_flags |= SB_ACTIVE | SB_DIRSYNC; - if (!v9ses->cache) - sb->s_flags |= SB_SYNCHRONOUS; + sb->s_flags |= SB_ACTIVE; #ifdef CONFIG_9P_FS_POSIX_ACL if ((v9ses->flags & V9FS_ACL_MASK) == V9FS_POSIX_ACL) -- GitLab From 8142db4f2792717837b97e219e5f5203dde17abb Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Sat, 17 Dec 2022 17:19:34 +0000 Subject: [PATCH 1338/5631] fs/9p: allow disable of xattr support on mount xattr creates a lot of additional messages for 9p in the current implementation. This allows users to conditionalize xattr support on 9p mount if they are on a connection with bad latency. Using this flag is also useful when debugging other aspects of 9p as it reduces the noise in the trace files. Signed-off-by: Eric Van Hensbergen Reviewed-by: Dominique Martinet --- Documentation/filesystems/9p.rst | 2 ++ fs/9p/v9fs.c | 9 ++++++++- fs/9p/v9fs.h | 3 ++- fs/9p/vfs_super.c | 3 ++- 4 files changed, 14 insertions(+), 3 deletions(-) diff --git a/Documentation/filesystems/9p.rst b/Documentation/filesystems/9p.rst index 7b5964bc8865..0e800b8f73cc 100644 --- a/Documentation/filesystems/9p.rst +++ b/Documentation/filesystems/9p.rst @@ -137,6 +137,8 @@ Options This can be used to share devices/named pipes/sockets between hosts. This functionality will be expanded in later versions. + noxattr do not offer xattr functions on this mount. + access there are four access modes. user if a user tries to access a file on v9fs diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index a46bf9121f11..f8e952c013f9 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -38,7 +38,7 @@ enum { /* String options */ Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag, /* Options that take no arguments */ - Opt_nodevmap, + Opt_nodevmap, Opt_noxattr, /* Access options */ Opt_access, Opt_posixacl, /* Lock timeout option */ @@ -55,6 +55,7 @@ static const match_table_t tokens = { {Opt_uname, "uname=%s"}, {Opt_remotename, "aname=%s"}, {Opt_nodevmap, "nodevmap"}, + {Opt_noxattr, "noxattr"}, {Opt_cache, "cache=%s"}, {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, @@ -149,6 +150,9 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) if (v9ses->flags & V9FS_POSIX_ACL) seq_puts(m, ",posixacl"); + if (v9ses->flags & V9FS_NO_XATTR) + seq_puts(m, ",noxattr"); + return p9_show_client_options(m, v9ses->clnt); } @@ -269,6 +273,9 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) case Opt_nodevmap: v9ses->nodev = 1; break; + case Opt_noxattr: + v9ses->flags |= V9FS_NO_XATTR; + break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index e5d41804b3cd..8cd63782a25c 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -36,7 +36,8 @@ enum p9_session_flags { V9FS_ACCESS_SINGLE = 0x04, V9FS_ACCESS_USER = 0x08, V9FS_ACCESS_CLIENT = 0x10, - V9FS_POSIX_ACL = 0x20 + V9FS_POSIX_ACL = 0x20, + V9FS_NO_XATTR = 0x40 }; /* possible values of ->cache */ diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 65d96fa94ba2..5fc6a945bfff 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -64,7 +64,8 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_magic = V9FS_MAGIC; if (v9fs_proto_dotl(v9ses)) { sb->s_op = &v9fs_super_ops_dotl; - sb->s_xattr = v9fs_xattr_handlers; + if (!(v9ses->flags & V9FS_NO_XATTR)) + sb->s_xattr = v9fs_xattr_handlers; } else { sb->s_op = &v9fs_super_ops; sb->s_time_max = U32_MAX; -- GitLab From 46c30cb8f5393586c6ebc7b53a235c85bfac1de8 Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Sun, 18 Dec 2022 18:03:54 +0000 Subject: [PATCH 1339/5631] 9p: Add additional debug flags and open modes Add some additional debug flags to assist with debugging cache changes. Also add some additional open modes so we can track cache state in fids more directly. Signed-off-by: Eric Van Hensbergen --- include/net/9p/9p.h | 6 ++++++ net/9p/client.c | 8 ++++---- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h index 429adf6be29c..60cad0d200a4 100644 --- a/include/net/9p/9p.h +++ b/include/net/9p/9p.h @@ -42,6 +42,8 @@ enum p9_debug_flags { P9_DEBUG_PKT = (1<<10), P9_DEBUG_FSC = (1<<11), P9_DEBUG_VPKT = (1<<12), + P9_DEBUG_CACHE = (1<<13), + P9_DEBUG_MMAP = (1<<14), }; #ifdef CONFIG_NET_9P_DEBUG @@ -213,6 +215,10 @@ enum p9_open_mode_t { P9_ORCLOSE = 0x40, P9_OAPPEND = 0x80, P9_OEXCL = 0x1000, + P9L_MODE_MASK = 0x1FFF, /* don't send anything under this to server */ + P9L_DIRECT = 0x2000, /* cache disabled */ + P9L_NOWRITECACHE = 0x4000, /* no write caching */ + P9L_LOOSE = 0x8000, /* loose cache */ }; /** diff --git a/net/9p/client.c b/net/9p/client.c index 2adcb5e7b0e2..a3340268ec8d 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1230,9 +1230,9 @@ int p9_client_open(struct p9_fid *fid, int mode) return -EINVAL; if (p9_is_proto_dotl(clnt)) - req = p9_client_rpc(clnt, P9_TLOPEN, "dd", fid->fid, mode); + req = p9_client_rpc(clnt, P9_TLOPEN, "dd", fid->fid, mode & P9L_MODE_MASK); else - req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode); + req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode & P9L_MODE_MASK); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; @@ -1277,7 +1277,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, return -EINVAL; req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags, - mode, gid); + mode & P9L_MODE_MASK, gid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; @@ -1321,7 +1321,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, return -EINVAL; req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm, - mode, extension); + mode & P9L_MODE_MASK, extension); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; -- GitLab From 6deffc8924b59df173da5fc7a9c96d3717cd9e96 Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Sun, 18 Dec 2022 20:34:45 +0000 Subject: [PATCH 1340/5631] fs/9p: Add new mount modes Add some additional mount modes for cache management including specifying directio as a mount option and an option for ignore qid.version for determining whether or not a file is cacheable. Signed-off-by: Eric Van Hensbergen --- fs/9p/v9fs.c | 16 ++++++++++++++-- fs/9p/v9fs.h | 5 ++++- 2 files changed, 18 insertions(+), 3 deletions(-) diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index f8e952c013f9..43d3806150a9 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -38,7 +38,7 @@ enum { /* String options */ Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag, /* Options that take no arguments */ - Opt_nodevmap, Opt_noxattr, + Opt_nodevmap, Opt_noxattr, Opt_directio, Opt_ignoreqv, /* Access options */ Opt_access, Opt_posixacl, /* Lock timeout option */ @@ -56,6 +56,8 @@ static const match_table_t tokens = { {Opt_remotename, "aname=%s"}, {Opt_nodevmap, "nodevmap"}, {Opt_noxattr, "noxattr"}, + {Opt_directio, "directio"}, + {Opt_ignoreqv, "ignoreqv"}, {Opt_cache, "cache=%s"}, {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, @@ -125,7 +127,7 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) if (v9ses->nodev) seq_puts(m, ",nodevmap"); if (v9ses->cache) - seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]); + seq_printf(m, ",cache=%s", v9fs_cache_modes[v9ses->cache]); #ifdef CONFIG_9P_FSCACHE if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) seq_printf(m, ",cachetag=%s", v9ses->cachetag); @@ -147,6 +149,10 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) break; } + if (v9ses->flags & V9FS_IGNORE_QV) + seq_puts(m, ",ignoreqv"); + if (v9ses->flags & V9FS_DIRECT_IO) + seq_puts(m, ",directio"); if (v9ses->flags & V9FS_POSIX_ACL) seq_puts(m, ",posixacl"); @@ -276,6 +282,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) case Opt_noxattr: v9ses->flags |= V9FS_NO_XATTR; break; + case Opt_directio: + v9ses->flags |= V9FS_DIRECT_IO; + break; + case Opt_ignoreqv: + v9ses->flags |= V9FS_IGNORE_QV; + break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 8cd63782a25c..12401f1be5d6 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -37,7 +37,10 @@ enum p9_session_flags { V9FS_ACCESS_USER = 0x08, V9FS_ACCESS_CLIENT = 0x10, V9FS_POSIX_ACL = 0x20, - V9FS_NO_XATTR = 0x40 + V9FS_NO_XATTR = 0x40, + V9FS_IGNORE_QV = 0x80, /* ignore qid.version for cache hints */ + V9FS_DIRECT_IO = 0x100, + V9FS_SYNC = 0x200 }; /* possible values of ->cache */ -- GitLab From 1543b4c5071c54d76aad7a7a26a6e43082269b0c Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Mon, 27 Mar 2023 02:06:37 +0000 Subject: [PATCH 1341/5631] fs/9p: remove writeback fid and fix per-file modes This patch removes the creating of an additional writeback_fid for opened files. The patch addresses problems when files were opened write-only or getattr on files with dirty caches. This patch also incorporates information about cache behavior in the fid for every file. This allows us to reflect cache behavior from mount flags, open mode, and information from the server to inform readahead and writeback behavior. This includes adding support for a 9p semantic that qid.version==0 is used to mark a file as non-cachable which is important for synthetic files. This may have a side-effect of not supporting caching on certain legacy file servers that do not properly set qid.version. There is also now a mount flag which can disable the qid.version behavior. Signed-off-by: Eric Van Hensbergen --- fs/9p/fid.c | 48 +++++++++------------- fs/9p/fid.h | 33 ++++++++++++++- fs/9p/v9fs.h | 1 - fs/9p/vfs_addr.c | 22 +++++----- fs/9p/vfs_file.c | 91 ++++++++++++++---------------------------- fs/9p/vfs_inode.c | 45 +++++++-------------- fs/9p/vfs_inode_dotl.c | 48 +++++++++------------- fs/9p/vfs_super.c | 33 ++++----------- 8 files changed, 135 insertions(+), 186 deletions(-) diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 805151114e96..de009a33e0e2 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -41,14 +41,24 @@ void v9fs_fid_add(struct dentry *dentry, struct p9_fid **pfid) *pfid = NULL; } +static bool v9fs_is_writeable(int mode) +{ + if (mode & (P9_OWRITE|P9_ORDWR)) + return true; + else + return false; +} + /** * v9fs_fid_find_inode - search for an open fid off of the inode list * @inode: return a fid pointing to a specific inode + * @want_writeable: only consider fids which are writeable * @uid: return a fid belonging to the specified user + * @any: ignore uid as a selection criteria * */ - -static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) +struct p9_fid *v9fs_fid_find_inode(struct inode *inode, bool want_writeable, + kuid_t uid, bool any) { struct hlist_head *h; struct p9_fid *fid, *ret = NULL; @@ -58,7 +68,12 @@ static struct p9_fid *v9fs_fid_find_inode(struct inode *inode, kuid_t uid) spin_lock(&inode->i_lock); h = (struct hlist_head *)&inode->i_private; hlist_for_each_entry(fid, h, ilist) { - if (uid_eq(fid->uid, uid)) { + if (any || uid_eq(fid->uid, uid)) { + if (want_writeable && !v9fs_is_writeable(fid->mode)) { + p9_debug(P9_DEBUG_VFS, " mode: %x not writeable?\n", + fid->mode); + continue; + } p9_fid_get(fid); ret = fid; break; @@ -118,7 +133,7 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any) spin_unlock(&dentry->d_lock); } else { if (dentry->d_inode) - ret = v9fs_fid_find_inode(dentry->d_inode, uid); + ret = v9fs_fid_find_inode(dentry->d_inode, false, uid, any); } return ret; @@ -299,28 +314,3 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) return v9fs_fid_lookup_with_uid(dentry, uid, any); } -struct p9_fid *v9fs_writeback_fid(struct dentry *dentry) -{ - int err; - struct p9_fid *fid, *ofid; - - ofid = v9fs_fid_lookup_with_uid(dentry, GLOBAL_ROOT_UID, 0); - fid = clone_fid(ofid); - if (IS_ERR(fid)) - goto error_out; - p9_fid_put(ofid); - /* - * writeback fid will only be used to write back the - * dirty pages. We always request for the open fid in read-write - * mode so that a partial page write which result in page - * read can work. - */ - err = p9_client_open(fid, O_RDWR); - if (err < 0) { - p9_fid_put(fid); - fid = ERR_PTR(err); - goto error_out; - } -error_out: - return fid; -} diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 8a4e8cd12ca2..11576e1364bf 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -7,14 +7,16 @@ #ifndef FS_9P_FID_H #define FS_9P_FID_H #include +#include "v9fs.h" +struct p9_fid *v9fs_fid_find_inode(struct inode *inode, bool want_writeable, + kuid_t uid, bool any); struct p9_fid *v9fs_fid_lookup(struct dentry *dentry); static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry) { return v9fs_fid_lookup(dentry->d_parent); } void v9fs_fid_add(struct dentry *dentry, struct p9_fid **fid); -struct p9_fid *v9fs_writeback_fid(struct dentry *dentry); void v9fs_open_fid_add(struct inode *inode, struct p9_fid **fid); static inline struct p9_fid *clone_fid(struct p9_fid *fid) { @@ -32,4 +34,33 @@ static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) p9_fid_put(fid); return nfid; } +/** + * v9fs_fid_addmodes - add cache flags to fid mode (for client use only) + * @fid: fid to augment + * @s_flags: session info mount flags + * @s_cache: session info cache flags + * @f_flags: unix open flags + * + * make sure mode reflects flags of underlying mounts + * also qid.version == 0 reflects a synthetic or legacy file system + * NOTE: these are set after open so only reflect 9p client not + * underlying file system on server. + */ +static inline void v9fs_fid_add_modes(struct p9_fid *fid, int s_flags, + int s_cache, unsigned int f_flags) +{ + if (fid->qid.type != P9_QTFILE) + return; + + if ((!s_cache) || + ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || + (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { + fid->mode |= P9L_DIRECT; /* no read or write cache */ + } else if ((s_cache < CACHE_WRITEBACK) || + (f_flags & O_DSYNC) | (s_flags & V9FS_SYNC)) { + fid->mode |= P9L_NOWRITECACHE; + } else if (s_cache == CACHE_LOOSE) { + fid->mode |= P9L_LOOSE; /* noncoherent cache */ + } +} #endif diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 12401f1be5d6..999cdbcbfed9 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -118,7 +118,6 @@ struct v9fs_inode { struct netfs_inode netfs; /* Netfslib context and vfs inode */ struct p9_qid qid; unsigned int cache_validity; - struct p9_fid *writeback_fid; struct mutex v_mutex; }; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 6f46d7e4c750..211165430a8a 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,8 +57,6 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) */ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) { - struct inode *inode = file_inode(file); - struct v9fs_inode *v9inode = V9FS_I(inode); struct p9_fid *fid = file->private_data; BUG_ON(!fid); @@ -66,11 +64,8 @@ static int v9fs_init_request(struct netfs_io_request *rreq, struct file *file) /* we might need to read from a fid that was opened write-only * for read-modify-write of page cache, use the writeback fid * for that */ - if (rreq->origin == NETFS_READ_FOR_WRITE && - (fid->mode & O_ACCMODE) == O_WRONLY) { - fid = v9inode->writeback_fid; - BUG_ON(!fid); - } + WARN_ON(rreq->origin == NETFS_READ_FOR_WRITE && + !(fid->mode & P9_ORDWR)); p9_fid_get(fid); rreq->netfs_priv = fid; @@ -164,6 +159,7 @@ static int v9fs_vfs_write_folio_locked(struct folio *folio) loff_t i_size = i_size_read(inode); struct iov_iter from; size_t len = folio_size(folio); + struct p9_fid *writeback_fid; int err; if (start >= i_size) @@ -173,13 +169,17 @@ static int v9fs_vfs_write_folio_locked(struct folio *folio) iov_iter_xarray(&from, ITER_SOURCE, &folio_mapping(folio)->i_pages, start, len); - /* We should have writeback_fid always set */ - BUG_ON(!v9inode->writeback_fid); + writeback_fid = v9fs_fid_find_inode(inode, true, INVALID_UID, true); + if (!writeback_fid) { + WARN_ONCE(1, "folio expected an open fid inode->i_private=%p\n", + inode->i_private); + return -EINVAL; + } folio_wait_fscache(folio); folio_start_writeback(folio); - p9_client_write(v9inode->writeback_fid, start, &from, &err); + p9_client_write(writeback_fid, start, &from, &err); if (err == 0 && fscache_cookie_enabled(cookie) && @@ -192,6 +192,8 @@ static int v9fs_vfs_write_folio_locked(struct folio *folio) } folio_end_writeback(folio); + p9_fid_put(writeback_fid); + return err; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index cd1f3f4079d7..9f1d464bc1b5 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -43,7 +43,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) int err; struct v9fs_inode *v9inode; struct v9fs_session_info *v9ses; - struct p9_fid *fid, *writeback_fid; + struct p9_fid *fid; int omode; p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file); @@ -60,7 +60,19 @@ int v9fs_file_open(struct inode *inode, struct file *file) if (IS_ERR(fid)) return PTR_ERR(fid); - err = p9_client_open(fid, omode); + if ((v9ses->cache >= CACHE_WRITEBACK) && (omode & P9_OWRITE)) { + int writeback_omode = (omode & ~P9_OWRITE) | P9_ORDWR; + + p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, try opening O_RDWR\n"); + err = p9_client_open(fid, writeback_omode); + if (err < 0) { + p9_debug(P9_DEBUG_CACHE, "could not open O_RDWR, disabling caches\n"); + err = p9_client_open(fid, omode); + fid->mode |= P9L_DIRECT; + } + } else { + err = p9_client_open(fid, omode); + } if (err < 0) { p9_fid_put(fid); return err; @@ -72,36 +84,14 @@ int v9fs_file_open(struct inode *inode, struct file *file) file->private_data = fid; } - mutex_lock(&v9inode->v_mutex); - if ((v9ses->cache >= CACHE_WRITEBACK) && !v9inode->writeback_fid && - ((file->f_flags & O_ACCMODE) != O_RDONLY)) { - /* - * clone a fid and add it to writeback_fid - * we do it during open time instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - writeback_fid = v9fs_writeback_fid(file_dentry(file)); - if (IS_ERR(writeback_fid)) { - err = PTR_ERR(writeback_fid); - mutex_unlock(&v9inode->v_mutex); - goto out_error; - } - v9inode->writeback_fid = (void *) writeback_fid; - } - mutex_unlock(&v9inode->v_mutex); #ifdef CONFIG_9P_FSCACHE if (v9ses->cache == CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); #endif + v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags); v9fs_open_fid_add(inode, &fid); return 0; -out_error: - p9_fid_put(file->private_data); - file->private_data = NULL; - return err; } /** @@ -367,14 +357,14 @@ v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct p9_fid *fid = iocb->ki_filp->private_data; int ret, err = 0; - struct inode *inode = file_inode(iocb->ki_filp); - struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); - p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", - iov_iter_count(to), iocb->ki_pos); + p9_debug(P9_DEBUG_VFS, "fid %d count %zu offset %lld\n", + fid->fid, iov_iter_count(to), iocb->ki_pos); - if (v9ses->cache > CACHE_MMAP) + if (!(fid->mode & P9L_DIRECT)) { + p9_debug(P9_DEBUG_VFS, "(cached)\n"); return generic_file_read_iter(iocb, to); + } if (iocb->ki_filp->f_flags & O_NONBLOCK) ret = p9_client_read_once(fid, iocb->ki_pos, to, &err); @@ -397,14 +387,17 @@ static ssize_t v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; + struct p9_fid *fid = file->private_data; ssize_t retval; loff_t origin; int err = 0; - struct inode *inode = file_inode(iocb->ki_filp); - struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); - if (v9ses->cache >= CACHE_WRITEBACK) + p9_debug(P9_DEBUG_VFS, "fid %d\n", fid->fid); + + if (!(fid->mode & (P9L_DIRECT | P9L_NOWRITECACHE))) { + p9_debug(P9_DEBUG_CACHE, "(cached)\n"); return generic_file_write_iter(iocb, from); + } retval = generic_write_checks(iocb, from); if (retval <= 0) @@ -488,36 +481,18 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) { int retval; struct inode *inode = file_inode(filp); - struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); - struct p9_fid *fid; + + p9_debug(P9_DEBUG_MMAP, "filp :%p\n", filp); if (v9ses->cache < CACHE_MMAP) { + p9_debug(P9_DEBUG_CACHE, "(no mmap mode)"); + if (vma->vm_flags & VM_MAYSHARE) + return -ENODEV; invalidate_inode_pages2(filp->f_mapping); return generic_file_readonly_mmap(filp, vma); } - mutex_lock(&v9inode->v_mutex); - if (!v9inode->writeback_fid && - (vma->vm_flags & VM_SHARED) && - (vma->vm_flags & VM_WRITE)) { - /* - * clone a fid and add it to writeback_fid - * we do it during mmap instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - fid = v9fs_writeback_fid(file_dentry(filp)); - if (IS_ERR(fid)) { - retval = PTR_ERR(fid); - mutex_unlock(&v9inode->v_mutex); - return retval; - } - v9inode->writeback_fid = (void *) fid; - } - mutex_unlock(&v9inode->v_mutex); - retval = generic_file_mmap(filp, vma); if (!retval) vma->vm_ops = &v9fs_mmap_file_vm_ops; @@ -528,7 +503,6 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) static vm_fault_t v9fs_vm_page_mkwrite(struct vm_fault *vmf) { - struct v9fs_inode *v9inode; struct folio *folio = page_folio(vmf->page); struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); @@ -537,8 +511,6 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", folio, (unsigned long)filp->private_data); - v9inode = V9FS_I(inode); - /* Wait for the page to be written to the cache before we allow it to * be modified. We then assume the entire page will need writing back. */ @@ -551,7 +523,6 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) /* Update file times before taking page lock */ file_update_time(filp); - BUG_ON(!v9inode->writeback_fid); if (folio_lock_killable(folio) < 0) return VM_FAULT_RETRY; if (folio_mapping(folio) != inode->i_mapping) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 63590f55363b..fb5e5c0e41e4 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -230,7 +230,6 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) v9inode = alloc_inode_sb(sb, v9fs_inode_cache, GFP_KERNEL); if (!v9inode) return NULL; - v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; mutex_init(&v9inode->v_mutex); return &v9inode->netfs.inode; @@ -383,9 +382,6 @@ void v9fs_evict_inode(struct inode *inode) filemap_fdatawrite(&inode->i_data); fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); - /* clunk the fid stashed in writeback_fid */ - p9_fid_put(v9inode->writeback_fid); - v9inode->writeback_fid = NULL; } static int v9fs_test_inode(struct inode *inode, void *data) @@ -796,9 +792,10 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, u32 perm; struct v9fs_inode *v9inode; struct v9fs_session_info *v9ses; - struct p9_fid *fid, *inode_fid; + struct p9_fid *fid; struct dentry *res = NULL; struct inode *inode; + int p9_omode; if (d_in_lookup(dentry)) { res = v9fs_vfs_lookup(dir, dentry, 0); @@ -817,9 +814,14 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, v9ses = v9fs_inode2v9ses(dir); perm = unixmode2p9mode(v9ses, mode); - fid = v9fs_create(v9ses, dir, dentry, NULL, perm, - v9fs_uflags2omode(flags, - v9fs_proto_dotu(v9ses))); + p9_omode = v9fs_uflags2omode(flags, v9fs_proto_dotu(v9ses)); + + if ((v9ses->cache >= CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { + p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; + p9_debug(P9_DEBUG_CACHE, + "write-only file with writeback enabled, creating w/ O_RDWR\n"); + } + fid = v9fs_create(v9ses, dir, dentry, NULL, perm, p9_omode); if (IS_ERR(fid)) { err = PTR_ERR(fid); goto error; @@ -828,25 +830,6 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, v9fs_invalidate_inode_attr(dir); inode = d_inode(dentry); v9inode = V9FS_I(inode); - mutex_lock(&v9inode->v_mutex); - if ((v9ses->cache >= CACHE_WRITEBACK) && !v9inode->writeback_fid && - ((flags & O_ACCMODE) != O_RDONLY)) { - /* - * clone a fid and add it to writeback_fid - * we do it during open time instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - inode_fid = v9fs_writeback_fid(dentry); - if (IS_ERR(inode_fid)) { - err = PTR_ERR(inode_fid); - mutex_unlock(&v9inode->v_mutex); - goto error; - } - v9inode->writeback_fid = (void *) inode_fid; - } - mutex_unlock(&v9inode->v_mutex); err = finish_open(file, dentry, generic_file_open); if (err) goto error; @@ -855,6 +838,8 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); + + v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags); v9fs_open_fid_add(inode, &fid); file->f_mode |= FMODE_CREATED; @@ -1024,7 +1009,7 @@ v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } else if (v9ses->cache >= CACHE_WRITEBACK) { if (S_ISREG(inode->i_mode)) { @@ -1128,10 +1113,10 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); + truncate_pagecache(inode, iattr->ia_size); + if (v9ses->cache == CACHE_FSCACHE) fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); - else - invalidate_mapping_pages(&inode->i_data, 0, -1); } v9fs_invalidate_inode_attr(inode); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a28eb3aeab29..4b9488cb7a56 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -232,12 +232,12 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, int err = 0; kgid_t gid; umode_t mode; + int p9_omode = v9fs_open_to_dotl_flags(flags); const unsigned char *name = NULL; struct p9_qid qid; struct inode *inode; struct p9_fid *fid = NULL; - struct v9fs_inode *v9inode; - struct p9_fid *dfid = NULL, *ofid = NULL, *inode_fid = NULL; + struct p9_fid *dfid = NULL, *ofid = NULL; struct v9fs_session_info *v9ses; struct posix_acl *pacl = NULL, *dacl = NULL; struct dentry *res = NULL; @@ -282,14 +282,19 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, /* Update mode based on ACL value */ err = v9fs_acl_mode(dir, &mode, &dacl, &pacl); if (err) { - p9_debug(P9_DEBUG_VFS, "Failed to get acl values in creat %d\n", + p9_debug(P9_DEBUG_VFS, "Failed to get acl values in create %d\n", err); goto out; } - err = p9_client_create_dotl(ofid, name, v9fs_open_to_dotl_flags(flags), - mode, gid, &qid); + + if ((v9ses->cache >= CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { + p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; + p9_debug(P9_DEBUG_CACHE, + "write-only file with writeback enabled, creating w/ O_RDWR\n"); + } + err = p9_client_create_dotl(ofid, name, p9_omode, mode, gid, &qid); if (err < 0) { - p9_debug(P9_DEBUG_VFS, "p9_client_open_dotl failed in creat %d\n", + p9_debug(P9_DEBUG_VFS, "p9_client_open_dotl failed in create %d\n", err); goto out; } @@ -314,36 +319,19 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, v9fs_fid_add(dentry, &fid); d_instantiate(dentry, inode); - v9inode = V9FS_I(inode); - mutex_lock(&v9inode->v_mutex); - if ((v9ses->cache) && !v9inode->writeback_fid && - ((flags & O_ACCMODE) != O_RDONLY)) { - /* - * clone a fid and add it to writeback_fid - * we do it during open time instead of - * page dirty time via write_begin/page_mkwrite - * because we want write after unlink usecase - * to work. - */ - inode_fid = v9fs_writeback_fid(dentry); - if (IS_ERR(inode_fid)) { - err = PTR_ERR(inode_fid); - mutex_unlock(&v9inode->v_mutex); - goto out; - } - v9inode->writeback_fid = (void *) inode_fid; - } - mutex_unlock(&v9inode->v_mutex); /* Since we are opening a file, assign the open fid to the file */ err = finish_open(file, dentry, generic_file_open); if (err) goto out; file->private_data = ofid; #ifdef CONFIG_9P_FSCACHE - if (v9ses->cache == CACHE_FSCACHE) + if (v9ses->cache == CACHE_FSCACHE) { + struct v9fs_inode *v9inode = V9FS_I(inode); fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); + } #endif + v9fs_fid_add_modes(ofid, v9ses->flags, v9ses->cache, flags); v9fs_open_fid_add(inode, &ofid); file->f_mode |= FMODE_CREATED; out: @@ -464,9 +452,9 @@ v9fs_vfs_getattr_dotl(struct mnt_idmap *idmap, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { - generic_fillattr(&nop_mnt_idmap, d_inode(dentry), stat); + generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; - } else if (v9ses->cache >= CACHE_WRITEBACK) { + } else if (v9ses->cache) { if (S_ISREG(inode->i_mode)) { int retval = filemap_fdatawrite(inode->i_mapping); @@ -613,6 +601,8 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { truncate_setsize(inode, iattr->ia_size); + truncate_pagecache(inode, iattr->ia_size); + if (v9ses->cache == CACHE_FSCACHE) fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); } diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 5fc6a945bfff..af83b39e340c 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -290,49 +290,30 @@ static int v9fs_drop_inode(struct inode *inode) static int v9fs_write_inode(struct inode *inode, struct writeback_control *wbc) { - int ret; - struct p9_wstat wstat; struct v9fs_inode *v9inode; + /* * send an fsync request to server irrespective of * wbc->sync_mode. */ p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); - v9inode = V9FS_I(inode); - if (!v9inode->writeback_fid) - return 0; - v9fs_blank_wstat(&wstat); - ret = p9_client_wstat(v9inode->writeback_fid, &wstat); - if (ret < 0) { - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - return ret; - } + v9inode = V9FS_I(inode); fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); + return 0; } static int v9fs_write_inode_dotl(struct inode *inode, struct writeback_control *wbc) { - int ret; struct v9fs_inode *v9inode; - /* - * send an fsync request to server irrespective of - * wbc->sync_mode. - */ + v9inode = V9FS_I(inode); - p9_debug(P9_DEBUG_VFS, "%s: inode %p, writeback_fid %p\n", - __func__, inode, v9inode->writeback_fid); - if (!v9inode->writeback_fid) - return 0; - - ret = p9_client_fsync(v9inode->writeback_fid, 0); - if (ret < 0) { - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); - return ret; - } + p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode); + fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); + return 0; } -- GitLab From 101f26c72825c5dba1dfe826e4202a9a04b435c6 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 27 Mar 2023 10:35:22 +0200 Subject: [PATCH 1342/5631] MIPS: octeon: Fix compile error Commit ed6a0b6e9fd7 ("MIPS: octeon: Use of_address_to_resource()") lost a cast, which causes a compile error. Fixes: ed6a0b6e9fd7 ("MIPS: octeon: Use of_address_to_resource()") Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/octeon-irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 064e2409377a..8425a6b38aa2 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -2890,7 +2890,7 @@ static int __init octeon_irq_init_ciu3(struct device_node *ciu_node, if (WARN_ON(ret)) return ret; - ciu3_info->ciu3_addr = base_addr = phys_to_virt(res.start); + ciu3_info->ciu3_addr = base_addr = (u64)phys_to_virt(res.start); ciu3_info->node = node; consts.u64 = cvmx_read_csr(base_addr + CIU3_CONST); -- GitLab From 7f061c19f6521ef2b3e6f784ae344ebb562a5343 Mon Sep 17 00:00:00 2001 From: Abel Vesa Date: Wed, 8 Feb 2023 10:13:58 +0100 Subject: [PATCH 1343/5631] dt-bindings: arm-smmu: Add compatible for SM8550 SoC Add the SoC specific compatible for SM8550 implementing arm,mmu-500. Signed-off-by: Abel Vesa Signed-off-by: Neil Armstrong Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230207-topic-sm8550-upstream-smmu-bindings-v3-1-cb15a7123cfe@linaro.org Signed-off-by: Will Deacon --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index 807cb511fe18..ea81e9b1860c 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -53,6 +53,7 @@ properties: - qcom,sm8250-smmu-500 - qcom,sm8350-smmu-500 - qcom,sm8450-smmu-500 + - qcom,sm8550-smmu-500 - const: qcom,smmu-500 - const: arm,mmu-500 @@ -389,6 +390,7 @@ allOf: - qcom,sm6375-smmu-500 - qcom,sm8350-smmu-500 - qcom,sm8450-smmu-500 + - qcom,sm8550-smmu-500 then: properties: clock-names: false -- GitLab From 5c3686616b1840b3143b227eb58fb1c1621d204e Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 13 Mar 2023 17:44:16 +0100 Subject: [PATCH 1344/5631] dt-bindings: arm-smmu: Use qcom,smmu compatible for MMU500 adreno SMMUs qcom,smmu-500 was introduced to prevent people from adding new compatibles for what seems to roughly be the same hardware. Use it for qcom,adreno-smmu-compatible targets as well. While at it, fix the "arm,smmu-500" -> "arm,mmu-500" typo in the comment. Acked-by: Krzysztof Kozlowski Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230313-topic-gpu_smmu_bindings-v3-1-66ab655fbfd5@linaro.org Signed-off-by: Will Deacon --- .../devicetree/bindings/iommu/arm,smmu.yaml | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index ea81e9b1860c..b3a8f5864648 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -76,9 +76,19 @@ properties: - qcom,sm8350-smmu-500 - qcom,sm8450-smmu-500 - const: arm,mmu-500 - - - description: Qcom Adreno GPUs implementing "arm,smmu-500" + - description: Qcom Adreno GPUs implementing "qcom,smmu-500" and "arm,mmu-500" + items: + - enum: + - qcom,sc7280-smmu-500 + - qcom,sm8150-smmu-500 + - qcom,sm8250-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 + - description: Qcom Adreno GPUs implementing "arm,mmu-500" (legacy binding) + deprecated: true items: + # Do not add additional SoC to this list. Instead use previous list. - enum: - qcom,sc7280-smmu-500 - qcom,sm8150-smmu-500 -- GitLab From 16d1646871fbe800c9751f0816a970f9126a6586 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 13 Mar 2023 17:44:17 +0100 Subject: [PATCH 1345/5631] dt-bindings: arm-smmu: Add SM8350 Adreno SMMU Document the Adreno SMMU present on SM8350. Acked-by: Krzysztof Kozlowski Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230313-topic-gpu_smmu_bindings-v3-2-66ab655fbfd5@linaro.org Signed-off-by: Will Deacon --- Documentation/devicetree/bindings/iommu/arm,smmu.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index b3a8f5864648..f45e4296a5ea 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -82,6 +82,7 @@ properties: - qcom,sc7280-smmu-500 - qcom,sm8150-smmu-500 - qcom,sm8250-smmu-500 + - qcom,sm8350-smmu-500 - const: qcom,adreno-smmu - const: qcom,smmu-500 - const: arm,mmu-500 -- GitLab From 3ad6585509dc8157e598dbd06b71efed2e45fee8 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 15 Mar 2023 11:52:08 +0100 Subject: [PATCH 1346/5631] dt-bindings: arm-smmu: Document SM61[12]5 GPU SMMU Both of these SoCs have a Qualcomm MMU500 implementation of SMMU in front of their GPUs that expect 3 clocks. Both of them also have an APPS SMMU that expects no clocks. Remove qcom,sm61[12]5-smmu-500 from the "no clocks" list (intentionally 'breaking' the schema checks of APPS SMMU, as now it *can* accept clocks - with the current structure of this file it would have taken a wastefully-long time to sort this out properly..) and add necessary yaml to describe the clocks required by the GPU SMMUs. Signed-off-by: Konrad Dybcio Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230315-topic-kamorta_adrsmmu-v1-1-d1c0dea90bd9@linaro.org Signed-off-by: Will Deacon --- .../devicetree/bindings/iommu/arm,smmu.yaml | 28 +++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml index f45e4296a5ea..ba677d401e24 100644 --- a/Documentation/devicetree/bindings/iommu/arm,smmu.yaml +++ b/Documentation/devicetree/bindings/iommu/arm,smmu.yaml @@ -80,6 +80,8 @@ properties: items: - enum: - qcom,sc7280-smmu-500 + - qcom,sm6115-smmu-500 + - qcom,sm6125-smmu-500 - qcom,sm8150-smmu-500 - qcom,sm8250-smmu-500 - qcom,sm8350-smmu-500 @@ -376,6 +378,30 @@ allOf: - description: interface clock required to access smmu's registers through the TCU's programming interface. + - if: + properties: + compatible: + items: + - enum: + - qcom,sm6115-smmu-500 + - qcom,sm6125-smmu-500 + - const: qcom,adreno-smmu + - const: qcom,smmu-500 + - const: arm,mmu-500 + then: + properties: + clock-names: + items: + - const: mem + - const: hlos + - const: iface + + clocks: + items: + - description: GPU memory bus clock + - description: Voter clock required for HLOS SMMU access + - description: Interface clock required for register access + # Disallow clocks for all other platforms with specific compatibles - if: properties: @@ -395,8 +421,6 @@ allOf: - qcom,sdm845-smmu-500 - qcom,sdx55-smmu-500 - qcom,sdx65-smmu-500 - - qcom,sm6115-smmu-500 - - qcom,sm6125-smmu-500 - qcom,sm6350-smmu-500 - qcom,sm6375-smmu-500 - qcom,sm8350-smmu-500 -- GitLab From 5f4f53d28cde2cc7be96f657229c8603da578500 Mon Sep 17 00:00:00 2001 From: Kautuk Consul Date: Mon, 27 Mar 2023 07:33:20 -0400 Subject: [PATCH 1347/5631] KVM: PPC: Book3S HV: kvmppc_hv_entry: remove .global scope kvmppc_hv_entry isn't called from anywhere other than book3s_hv_rmhandlers.S itself. Remove .global scope for this function and annotate it with SYM_CODE_START_LOCAL and SYM_CODE_END. Signed-off-by: Kautuk Consul Signed-off-by: Michael Ellerman Link: https://msgid.link/20230327113320.3407491-1-kconsul@linux.vnet.ibm.com --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index acf80915f406..0a9781192b86 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -502,8 +502,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) * * *****************************************************************************/ -.global kvmppc_hv_entry -kvmppc_hv_entry: +SYM_CODE_START_LOCAL(kvmppc_hv_entry) /* Required state: * @@ -940,6 +939,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r4, VCPU_GPR(R4)(r4) HRFI_TO_GUEST b . +SYM_CODE_END(kvmppc_hv_entry) secondary_too_late: li r12, 0 -- GitLab From 8c153645fa402ee96ec3c2fef9db3a087b3667ac Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 21 Mar 2023 10:06:00 +0000 Subject: [PATCH 1348/5631] iommu/arm-smmu-v3: Explain why ATS stays disabled with bypass The SMMU does not support enabling ATS for a bypass stream. Add a comment. Signed-off-by: Jean-Philippe Brucker Link: https://lore.kernel.org/r/20230321100559.341981-1-jean-philippe@linaro.org Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index f2425b0f0cd6..a8410c132f1e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2447,6 +2447,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) master->domain = smmu_domain; + /* + * The SMMU does not support enabling ATS with bypass. When the STE is + * in bypass (STE.Config[2:0] == 0b100), ATS Translation Requests and + * Translated transactions are denied as though ATS is disabled for the + * stream (STE.EATS == 0b00), causing F_BAD_ATS_TREQ and + * F_TRANSL_FORBIDDEN events (IHI0070Ea 5.2 Stream Table Entry). + */ if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS) master->ats_enabled = arm_smmu_ats_supported(master); -- GitLab From 170848d4060d40220194c0af19f977a582f08922 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Mar 2023 10:18:28 +0200 Subject: [PATCH 1349/5631] driver core: class: fix documentation for class_create() In commit dcfbb67e48a2 ("driver core: class: use lock_class_key already present in struct subsys_private") we removed the key parameter to the function class_create() but forgot to remove it from the kerneldoc, which causes a build warning. Fix that up by removing the key parameter from the documentation as it is now gone. Reported-by: Stephen Rothwell Fixes: dcfbb67e48a2 ("driver core: class: use lock_class_key already present in struct subsys_private") Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327081828.1087364-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index dbaeb79ae917..0f8938a17144 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -223,7 +223,6 @@ static void class_create_release(struct class *cls) /** * class_create - create a struct class structure * @name: pointer to a string for the name of this class. - * @key: the lock_class_key for this class; used by mutex lock debugging * * This is used to create a struct class pointer that can then be used * in calls to device_create(). -- GitLab From 12261134732689b7e30c59db9978f81230965181 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Mon, 27 Mar 2023 13:30:29 +0530 Subject: [PATCH 1350/5631] iommu/arm-smmu-qcom: Limit the SMR groups to 128 Some platforms support more than 128 stream matching groups than what is defined by the ARM SMMU architecture specification. But due to some unknown reasons, those additional groups don't exhibit the same behavior as the architecture supported ones. For instance, the additional groups will not detect the quirky behavior of some firmware versions intercepting writes to S2CR register, thus skipping the quirk implemented in the driver and causing boot crash. So let's limit the groups to 128 for now until the issue with those groups are fixed and issue a notice to users in that case. Reviewed-by: Johan Hovold Tested-by: Johan Hovold Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20230327080029.11584-1-manivannan.sadhasivam@linaro.org [will: Reworded the comment slightly] Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d1b296b95c86..ae09c627bc84 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -268,12 +268,26 @@ static int qcom_smmu_init_context(struct arm_smmu_domain *smmu_domain, static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu) { - unsigned int last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); struct qcom_smmu *qsmmu = to_qcom_smmu(smmu); + unsigned int last_s2cr; u32 reg; u32 smr; int i; + /* + * Some platforms support more than the Arm SMMU architected maximum of + * 128 stream matching groups. For unknown reasons, the additional + * groups don't exhibit the same behavior as the architected registers, + * so limit the groups to 128 until the behavior is fixed for the other + * groups. + */ + if (smmu->num_mapping_groups > 128) { + dev_notice(smmu->dev, "\tLimiting the stream matching groups to 128\n"); + smmu->num_mapping_groups = 128; + } + + last_s2cr = ARM_SMMU_GR0_S2CR(smmu->num_mapping_groups - 1); + /* * With some firmware versions writes to S2CR of type FAULT are * ignored, and writing BYPASS will end up written as FAULT in the -- GitLab From 0203471df1d5242ab63692ddd9e95f37f0cddadc Mon Sep 17 00:00:00 2001 From: Daniel Pinto Date: Tue, 15 Nov 2022 08:17:32 +0000 Subject: [PATCH 1351/5631] fs/ntfs3: Fix wrong cast in xattr.c cpu_to_be32 and be32_to_cpu respectively return and receive __be32, change the cast to the correct types. Fixes the following sparse warnings: fs/ntfs3/xattr.c:811:48: sparse: sparse: incorrect type in assignment (different base types) fs/ntfs3/xattr.c:901:34: sparse: sparse: cast to restricted __be32 Reported-by: kernel test robot Signed-off-by: Daniel Pinto Signed-off-by: Konstantin Komarov --- fs/ntfs3/xattr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index ff64302e87e5..f8043838eb92 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -780,7 +780,7 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de, err = sizeof(u32); *(u32 *)buffer = le32_to_cpu(ni->std_fa); if (!strcmp(name, SYSTEM_NTFS_ATTRIB_BE)) - *(u32 *)buffer = cpu_to_be32(*(u32 *)buffer); + *(__be32 *)buffer = cpu_to_be32(*(u32 *)buffer); } goto out; } @@ -857,7 +857,7 @@ static noinline int ntfs_setxattr(const struct xattr_handler *handler, if (size != sizeof(u32)) goto out; if (!strcmp(name, SYSTEM_NTFS_ATTRIB_BE)) - new_fa = cpu_to_le32(be32_to_cpu(*(u32 *)value)); + new_fa = cpu_to_le32(be32_to_cpu(*(__be32 *)value)); else new_fa = cpu_to_le32(*(u32 *)value); -- GitLab From bfa434c60157c9793e9b12c9b68ade02aff9f803 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Tue, 22 Nov 2022 17:24:14 +0800 Subject: [PATCH 1352/5631] fs/ntfs3: Fix memory leak if ntfs_read_mft failed Label ATTR_ROOT in ntfs_read_mft() sets is_root = true and ni->ni_flags |= NI_FLAG_DIR, then next attr will goto label ATTR_ALLOC and alloc ni->dir.alloc_run. However two states are not always consistent and can make memory leak. 1) attr_name in ATTR_ROOT does not fit the condition it will set is_root = true but NI_FLAG_DIR is not set. 2) next attr_name in ATTR_ALLOC fits the condition and alloc ni->dir.alloc_run 3) in cleanup function ni_clear(), when NI_FLAG_DIR is set, it frees ni->dir.alloc_run, otherwise it frees ni->file.run 4) because NI_FLAG_DIR is not set in this case, ni->dir.alloc_run is leaked as kmemleak reported: unreferenced object 0xffff888003bc5480 (size 64): backtrace: [<000000003d42e6b0>] __kmalloc_node+0x4e/0x1c0 [<00000000d8e19b8a>] kvmalloc_node+0x39/0x1f0 [<00000000fc3eb5b8>] run_add_entry+0x18a/0xa40 [ntfs3] [<0000000011c9f978>] run_unpack+0x75d/0x8e0 [ntfs3] [<00000000e7cf1819>] run_unpack_ex+0xbc/0x500 [ntfs3] [<00000000bbf0a43d>] ntfs_iget5+0xb25/0x2dd0 [ntfs3] [<00000000a6e50693>] ntfs_fill_super+0x218d/0x3580 [ntfs3] [<00000000b9170608>] get_tree_bdev+0x3fb/0x710 [<000000004833798a>] vfs_get_tree+0x8e/0x280 [<000000006e20b8e6>] path_mount+0xf3c/0x1930 [<000000007bf15a5f>] do_mount+0xf3/0x110 ... Fix this by always setting is_root and NI_FLAG_DIR together. Fixes: 82cae269cfa9 ("fs/ntfs3: Add initialization of super block") Signed-off-by: Chen Zhongjin Signed-off-by: Konstantin Komarov --- fs/ntfs3/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 309d9b46b5d5..ce6bb3bd86b6 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -259,7 +259,6 @@ static struct inode *ntfs_read_mft(struct inode *inode, goto out; root = Add2Ptr(attr, roff); - is_root = true; if (attr->name_len != ARRAY_SIZE(I30_NAME) || memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) @@ -272,6 +271,7 @@ static struct inode *ntfs_read_mft(struct inode *inode, if (!is_dir) goto next_attr; + is_root = true; ni->ni_flags |= NI_FLAG_DIR; err = indx_init(&ni->dir, sbi, attr, INDEX_MUTEX_I30); -- GitLab From e6c3cef24cb0d045f99d5cb039b344874e3cfd74 Mon Sep 17 00:00:00 2001 From: Jiasheng Jiang Date: Wed, 23 Nov 2022 16:48:46 +0800 Subject: [PATCH 1353/5631] fs/ntfs3: Add check for kmemdup Since the kmemdup may return NULL pointer, it should be better to add check for the return value in order to avoid NULL pointer dereference. Fixes: b46acd6a6a62 ("fs/ntfs3: Add NTFS journal") Signed-off-by: Jiasheng Jiang Signed-off-by: Konstantin Komarov --- fs/ntfs3/fslog.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index c6eb371a3695..dc723f03d6bb 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -4256,6 +4256,10 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) rec_len -= t32; attr_names = kmemdup(Add2Ptr(lrh, t32), rec_len, GFP_NOFS); + if (!attr_names) { + err = -ENOMEM; + goto out; + } lcb_put(lcb); lcb = NULL; -- GitLab From 254e69f284d7270e0abdc023ee53b71401c3ba0c Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Fri, 25 Nov 2022 10:21:59 +0000 Subject: [PATCH 1354/5631] fs/ntfs3: Fix null-ptr-deref on inode->i_op in ntfs_lookup() Syzbot reported a null-ptr-deref bug: ntfs3: loop0: Different NTFS' sector size (1024) and media sector size (512) ntfs3: loop0: Mark volume as dirty due to NTFS errors general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] RIP: 0010:d_flags_for_inode fs/dcache.c:1980 [inline] RIP: 0010:__d_add+0x5ce/0x800 fs/dcache.c:2796 Call Trace: d_splice_alias+0x122/0x3b0 fs/dcache.c:3191 lookup_open fs/namei.c:3391 [inline] open_last_lookups fs/namei.c:3481 [inline] path_openat+0x10e6/0x2df0 fs/namei.c:3688 do_filp_open+0x264/0x4f0 fs/namei.c:3718 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_open fs/open.c:1334 [inline] __se_sys_open fs/open.c:1330 [inline] __x64_sys_open+0x221/0x270 fs/open.c:1330 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd If the MFT record of ntfs inode is not a base record, inode->i_op can be NULL. And a null-ptr-deref may happen: ntfs_lookup() dir_search_u() # inode->i_op is set to NULL d_splice_alias() __d_add() d_flags_for_inode() # inode->i_op->get_link null-ptr-deref Fix this by adding a Check on inode->i_op before calling the d_splice_alias() function. Fixes: 4342306f0f0d ("fs/ntfs3: Add file operations and implementation") Reported-by: syzbot+a8f26a403c169b7593fe@syzkaller.appspotmail.com Signed-off-by: ZhangPeng Signed-off-by: Konstantin Komarov --- fs/ntfs3/namei.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 407fe92394e2..8d206770d8c6 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -88,6 +88,16 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry, __putname(uni); } + /* + * Check for a null pointer + * If the MFT record of ntfs inode is not a base record, inode->i_op can be NULL. + * This causes null pointer dereference in d_splice_alias(). + */ + if (!IS_ERR(inode) && inode->i_op == NULL) { + iput(inode); + inode = ERR_PTR(-EINVAL); + } + return d_splice_alias(inode, dentry); } -- GitLab From db2a3cc6a3481076da6344cc62a80a4e2525f36f Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 17 Nov 2022 17:19:12 +0800 Subject: [PATCH 1355/5631] fs/ntfs3: Fix NULL pointer dereference in 'ni_write_inode' Syzbot found the following issue: Unable to handle kernel NULL pointer dereference at virtual address 0000000000000016 Mem abort info: ESR = 0x0000000096000006 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x06: level 2 translation fault Data abort info: ISV = 0, ISS = 0x00000006 CM = 0, WnR = 0 user pgtable: 4k pages, 48-bit VAs, pgdp=000000010af56000 [0000000000000016] pgd=08000001090da003, p4d=08000001090da003, pud=08000001090ce003, pmd=0000000000000000 Internal error: Oops: 0000000096000006 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 3036 Comm: syz-executor206 Not tainted 6.0.0-rc6-syzkaller-17739-g16c9f284e746 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : is_rec_inuse fs/ntfs3/ntfs.h:313 [inline] pc : ni_write_inode+0xac/0x798 fs/ntfs3/frecord.c:3232 lr : ni_write_inode+0xa0/0x798 fs/ntfs3/frecord.c:3226 sp : ffff8000126c3800 x29: ffff8000126c3860 x28: 0000000000000000 x27: ffff0000c8b02000 x26: ffff0000c7502320 x25: ffff0000c7502288 x24: 0000000000000000 x23: ffff80000cbec91c x22: ffff0000c8b03000 x21: ffff0000c8b02000 x20: 0000000000000001 x19: ffff0000c75024d8 x18: 00000000000000c0 x17: ffff80000dd1b198 x16: ffff80000db59158 x15: ffff0000c4b6b500 x14: 00000000000000b8 x13: 0000000000000000 x12: ffff0000c4b6b500 x11: ff80800008be1b60 x10: 0000000000000000 x9 : ffff0000c4b6b500 x8 : 0000000000000000 x7 : ffff800008be1b50 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000001 x3 : 0000000000000000 x2 : 0000000000000008 x1 : 0000000000000001 x0 : 0000000000000000 Call trace: is_rec_inuse fs/ntfs3/ntfs.h:313 [inline] ni_write_inode+0xac/0x798 fs/ntfs3/frecord.c:3232 ntfs_evict_inode+0x54/0x84 fs/ntfs3/inode.c:1744 evict+0xec/0x334 fs/inode.c:665 iput_final fs/inode.c:1748 [inline] iput+0x2c4/0x324 fs/inode.c:1774 ntfs_new_inode+0x7c/0xe0 fs/ntfs3/fsntfs.c:1660 ntfs_create_inode+0x20c/0xe78 fs/ntfs3/inode.c:1278 ntfs_create+0x54/0x74 fs/ntfs3/namei.c:100 lookup_open fs/namei.c:3413 [inline] open_last_lookups fs/namei.c:3481 [inline] path_openat+0x804/0x11c4 fs/namei.c:3688 do_filp_open+0xdc/0x1b8 fs/namei.c:3718 do_sys_openat2+0xb8/0x22c fs/open.c:1311 do_sys_open fs/open.c:1327 [inline] __do_sys_openat fs/open.c:1343 [inline] __se_sys_openat fs/open.c:1338 [inline] __arm64_sys_openat+0xb0/0xe0 fs/open.c:1338 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline] invoke_syscall arch/arm64/kernel/syscall.c:52 [inline] el0_svc_common+0x138/0x220 arch/arm64/kernel/syscall.c:142 do_el0_svc+0x48/0x164 arch/arm64/kernel/syscall.c:206 el0_svc+0x58/0x150 arch/arm64/kernel/entry-common.c:636 el0t_64_sync_handler+0x84/0xf0 arch/arm64/kernel/entry-common.c:654 el0t_64_sync+0x18c/0x190 Code: 97dafee4 340001b4 f9401328 2a1f03e0 (79402d14) ---[ end trace 0000000000000000 ]--- Above issue may happens as follows: ntfs_new_inode mi_init mi->mrec = kmalloc(sbi->record_size, GFP_NOFS); -->failed to allocate memory if (!mi->mrec) return -ENOMEM; iput iput_final evict ntfs_evict_inode ni_write_inode is_rec_inuse(ni->mi.mrec)-> As 'ni->mi.mrec' is NULL trigger NULL-ptr-deref To solve above issue if new inode failed make inode bad before call 'iput()' in 'ntfs_new_inode()'. Reported-by: syzbot+f45957555ed4a808cc7a@syzkaller.appspotmail.com Signed-off-by: Ye Bin Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 567563771bf8..8de861ddec60 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1683,6 +1683,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) out: if (err) { + make_bad_inode(inode); iput(inode); ni = ERR_PTR(err); } -- GitLab From b8c44949044e5f7f864525fdffe8e95135ce9ce5 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Wed, 7 Dec 2022 09:46:10 +0000 Subject: [PATCH 1356/5631] fs/ntfs3: Fix OOB read in indx_insert_into_buffer Syzbot reported a OOB read bug: BUG: KASAN: slab-out-of-bounds in indx_insert_into_buffer+0xaa3/0x13b0 fs/ntfs3/index.c:1755 Read of size 17168 at addr ffff8880255e06c0 by task syz-executor308/3630 Call Trace: memmove+0x25/0x60 mm/kasan/shadow.c:54 indx_insert_into_buffer+0xaa3/0x13b0 fs/ntfs3/index.c:1755 indx_insert_entry+0x446/0x6b0 fs/ntfs3/index.c:1863 ntfs_create_inode+0x1d3f/0x35c0 fs/ntfs3/inode.c:1548 ntfs_create+0x3e/0x60 fs/ntfs3/namei.c:100 lookup_open fs/namei.c:3413 [inline] If the member struct INDEX_BUFFER *index of struct indx_node is incorrect, that is, the value of __le32 used is greater than the value of __le32 total in struct INDEX_HDR. Therefore, OOB read occurs when memmove is called in indx_insert_into_buffer(). Fix this by adding a check in hdr_find_e(). Fixes: 82cae269cfa9 ("fs/ntfs3: Add initialization of super block") Reported-by: syzbot+d882d57193079e379309@syzkaller.appspotmail.com Signed-off-by: ZhangPeng Signed-off-by: Konstantin Komarov --- fs/ntfs3/index.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 51ab75954640..ae9616becec1 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -725,9 +725,13 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, u32 e_size, e_key_len; u32 end = le32_to_cpu(hdr->used); u32 off = le32_to_cpu(hdr->de_off); + u32 total = le32_to_cpu(hdr->total); u16 offs[128]; fill_table: + if (end > total) + return NULL; + if (off + sizeof(struct NTFS_DE) > end) return NULL; -- GitLab From 4f082a7531223a438c757bb20e304f4c941c67a8 Mon Sep 17 00:00:00 2001 From: Edward Lo Date: Thu, 27 Oct 2022 23:33:37 +0800 Subject: [PATCH 1357/5631] fs/ntfs3: Enhance the attribute size check This combines the overflow and boundary check so that all attribute size will be properly examined while enumerating them. [ 169.181521] BUG: KASAN: slab-out-of-bounds in run_unpack+0x2e3/0x570 [ 169.183161] Read of size 1 at addr ffff8880094b6240 by task mount/247 [ 169.184046] [ 169.184925] CPU: 0 PID: 247 Comm: mount Not tainted 6.0.0-rc7+ #3 [ 169.185908] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 169.187066] Call Trace: [ 169.187492] [ 169.188049] dump_stack_lvl+0x49/0x63 [ 169.188495] print_report.cold+0xf5/0x689 [ 169.188964] ? run_unpack+0x2e3/0x570 [ 169.189331] kasan_report+0xa7/0x130 [ 169.189714] ? run_unpack+0x2e3/0x570 [ 169.190079] __asan_load1+0x51/0x60 [ 169.190634] run_unpack+0x2e3/0x570 [ 169.191290] ? run_pack+0x840/0x840 [ 169.191569] ? run_lookup_entry+0xb3/0x1f0 [ 169.192443] ? mi_enum_attr+0x20a/0x230 [ 169.192886] run_unpack_ex+0xad/0x3e0 [ 169.193276] ? run_unpack+0x570/0x570 [ 169.193557] ? ni_load_mi+0x80/0x80 [ 169.193889] ? debug_smp_processor_id+0x17/0x20 [ 169.194236] ? mi_init+0x4a/0x70 [ 169.194496] attr_load_runs_vcn+0x166/0x1c0 [ 169.194851] ? attr_data_write_resident+0x250/0x250 [ 169.195188] mi_read+0x133/0x2c0 [ 169.195481] ntfs_iget5+0x277/0x1780 [ 169.196017] ? call_rcu+0x1c7/0x330 [ 169.196392] ? ntfs_get_block_bmap+0x70/0x70 [ 169.196708] ? evict+0x223/0x280 [ 169.197014] ? __kmalloc+0x33/0x540 [ 169.197305] ? wnd_init+0x15b/0x1b0 [ 169.197599] ntfs_fill_super+0x1026/0x1ba0 [ 169.197994] ? put_ntfs+0x1d0/0x1d0 [ 169.198299] ? vsprintf+0x20/0x20 [ 169.198583] ? mutex_unlock+0x81/0xd0 [ 169.198930] ? set_blocksize+0x95/0x150 [ 169.199269] get_tree_bdev+0x232/0x370 [ 169.199750] ? put_ntfs+0x1d0/0x1d0 [ 169.200094] ntfs_fs_get_tree+0x15/0x20 [ 169.200431] vfs_get_tree+0x4c/0x130 [ 169.200714] path_mount+0x654/0xfe0 [ 169.201067] ? putname+0x80/0xa0 [ 169.201358] ? finish_automount+0x2e0/0x2e0 [ 169.201965] ? putname+0x80/0xa0 [ 169.202445] ? kmem_cache_free+0x1c4/0x440 [ 169.203075] ? putname+0x80/0xa0 [ 169.203414] do_mount+0xd6/0xf0 [ 169.203719] ? path_mount+0xfe0/0xfe0 [ 169.203977] ? __kasan_check_write+0x14/0x20 [ 169.204382] __x64_sys_mount+0xca/0x110 [ 169.204711] do_syscall_64+0x3b/0x90 [ 169.205059] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 169.205571] RIP: 0033:0x7f67a80e948a [ 169.206327] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 169.208296] RSP: 002b:00007ffddf020f58 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 [ 169.209253] RAX: ffffffffffffffda RBX: 000055e2547a6060 RCX: 00007f67a80e948a [ 169.209777] RDX: 000055e2547a6260 RSI: 000055e2547a62e0 RDI: 000055e2547aeaf0 [ 169.210342] RBP: 0000000000000000 R08: 000055e2547a6280 R09: 0000000000000020 [ 169.210843] R10: 00000000c0ed0000 R11: 0000000000000202 R12: 000055e2547aeaf0 [ 169.211307] R13: 000055e2547a6260 R14: 0000000000000000 R15: 00000000ffffffff [ 169.211913] [ 169.212304] [ 169.212680] Allocated by task 0: [ 169.212963] (stack is not available) [ 169.213200] [ 169.213472] The buggy address belongs to the object at ffff8880094b5e00 [ 169.213472] which belongs to the cache UDP of size 1152 [ 169.214095] The buggy address is located 1088 bytes inside of [ 169.214095] 1152-byte region [ffff8880094b5e00, ffff8880094b6280) [ 169.214639] [ 169.215004] The buggy address belongs to the physical page: [ 169.215766] page:000000002e324c8c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x94b4 [ 169.218412] head:000000002e324c8c order:2 compound_mapcount:0 compound_pincount:0 [ 169.219078] flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) [ 169.220272] raw: 000fffffc0010200 0000000000000000 dead000000000122 ffff888002409b40 [ 169.221006] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000 [ 169.222320] page dumped because: kasan: bad access detected [ 169.222922] [ 169.223119] Memory state around the buggy address: [ 169.224056] ffff8880094b6100: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 169.224908] ffff8880094b6180: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 169.225677] >ffff8880094b6200: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 169.226445] ^ [ 169.227055] ffff8880094b6280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 169.227638] ffff8880094b6300: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Signed-off-by: Edward Lo Signed-off-by: Konstantin Komarov --- fs/ntfs3/record.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index defce6a5c8e1..abfe004774c0 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -220,11 +220,6 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* overflow check */ - return NULL; - } - attr = Add2Ptr(attr, asize); off += asize; } @@ -247,8 +242,8 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if ((t32 & 0xf) || (t32 > 0x100)) return NULL; - /* Check boundary. */ - if (off + asize > used) + /* Check overflow and boundary. */ + if (off + asize < off || off + asize > used) return NULL; /* Check size of attribute. */ -- GitLab From 8dae4f6341e335a09575be60b4fdf697c732a470 Mon Sep 17 00:00:00 2001 From: Abdun Nihaal Date: Sun, 30 Oct 2022 12:32:51 +0530 Subject: [PATCH 1358/5631] fs/ntfs3: Fix NULL dereference in ni_write_inode Syzbot reports a NULL dereference in ni_write_inode. When creating a new inode, if allocation fails in mi_init function (called in mi_format_new function), mi->mrec is set to NULL. In the error path of this inode creation, mi->mrec is later dereferenced in ni_write_inode. Add a NULL check to prevent NULL dereference. Link: https://syzkaller.appspot.com/bug?extid=f45957555ed4a808cc7a Reported-and-tested-by: syzbot+f45957555ed4a808cc7a@syzkaller.appspotmail.com Signed-off-by: Abdun Nihaal Signed-off-by: Konstantin Komarov --- fs/ntfs3/frecord.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index f1df52dfab74..912eeb3d3471 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -3258,6 +3258,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) return 0; } + if (!ni->mi.mrec) + goto out; + if (is_rec_inuse(ni->mi.mrec) && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { bool modified = false; -- GitLab From 98bea253aa28ad8be2ce565a9ca21beb4a9419e5 Mon Sep 17 00:00:00 2001 From: Edward Lo Date: Sat, 5 Nov 2022 23:39:44 +0800 Subject: [PATCH 1359/5631] fs/ntfs3: Validate MFT flags before replaying logs Log load and replay is part of the metadata handle flow during mount operation. The $MFT record will be loaded and used while replaying logs. However, a malformed $MFT record, say, has RECORD_FLAG_DIR flag set and contains an ATTR_ROOT attribute will misguide kernel to treat it as a directory, and try to free the allocated resources when the corresponding inode is freed, which will cause an invalid kfree because the memory hasn't actually been allocated. [ 101.368647] BUG: KASAN: invalid-free in kvfree+0x2c/0x40 [ 101.369457] [ 101.369986] CPU: 0 PID: 198 Comm: mount Not tainted 6.0.0-rc7+ #5 [ 101.370529] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 101.371362] Call Trace: [ 101.371795] [ 101.372157] dump_stack_lvl+0x49/0x63 [ 101.372658] print_report.cold+0xf5/0x689 [ 101.373022] ? ni_write_inode+0x754/0xd90 [ 101.373378] ? kvfree+0x2c/0x40 [ 101.373698] kasan_report_invalid_free+0x77/0xf0 [ 101.374058] ? kvfree+0x2c/0x40 [ 101.374352] ? kvfree+0x2c/0x40 [ 101.374668] __kasan_slab_free+0x189/0x1b0 [ 101.374992] ? kvfree+0x2c/0x40 [ 101.375271] kfree+0x168/0x3b0 [ 101.375717] kvfree+0x2c/0x40 [ 101.376002] indx_clear+0x26/0x60 [ 101.376316] ni_clear+0xc5/0x290 [ 101.376661] ntfs_evict_inode+0x45/0x70 [ 101.377001] evict+0x199/0x280 [ 101.377432] iput.part.0+0x286/0x320 [ 101.377819] iput+0x32/0x50 [ 101.378166] ntfs_loadlog_and_replay+0x143/0x320 [ 101.378656] ? ntfs_bio_fill_1+0x510/0x510 [ 101.378968] ? iput.part.0+0x286/0x320 [ 101.379367] ntfs_fill_super+0xecb/0x1ba0 [ 101.379729] ? put_ntfs+0x1d0/0x1d0 [ 101.380046] ? vsprintf+0x20/0x20 [ 101.380542] ? mutex_unlock+0x81/0xd0 [ 101.380914] ? set_blocksize+0x95/0x150 [ 101.381597] get_tree_bdev+0x232/0x370 [ 101.382254] ? put_ntfs+0x1d0/0x1d0 [ 101.382699] ntfs_fs_get_tree+0x15/0x20 [ 101.383094] vfs_get_tree+0x4c/0x130 [ 101.383675] path_mount+0x654/0xfe0 [ 101.384203] ? putname+0x80/0xa0 [ 101.384540] ? finish_automount+0x2e0/0x2e0 [ 101.384943] ? putname+0x80/0xa0 [ 101.385362] ? kmem_cache_free+0x1c4/0x440 [ 101.385968] ? putname+0x80/0xa0 [ 101.386666] do_mount+0xd6/0xf0 [ 101.387228] ? path_mount+0xfe0/0xfe0 [ 101.387585] ? __kasan_check_write+0x14/0x20 [ 101.387979] __x64_sys_mount+0xca/0x110 [ 101.388436] do_syscall_64+0x3b/0x90 [ 101.388757] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 101.389289] RIP: 0033:0x7fa0f70e948a [ 101.390048] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 101.391297] RSP: 002b:00007ffc24fdecc8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 [ 101.391988] RAX: ffffffffffffffda RBX: 000055932c183060 RCX: 00007fa0f70e948a [ 101.392494] RDX: 000055932c183260 RSI: 000055932c1832e0 RDI: 000055932c18bce0 [ 101.393053] RBP: 0000000000000000 R08: 000055932c183280 R09: 0000000000000020 [ 101.393577] R10: 00000000c0ed0000 R11: 0000000000000202 R12: 000055932c18bce0 [ 101.394044] R13: 000055932c183260 R14: 0000000000000000 R15: 00000000ffffffff [ 101.394747] [ 101.395402] [ 101.396047] Allocated by task 198: [ 101.396724] kasan_save_stack+0x26/0x50 [ 101.397400] __kasan_slab_alloc+0x6d/0x90 [ 101.397974] kmem_cache_alloc_lru+0x192/0x5a0 [ 101.398524] ntfs_alloc_inode+0x23/0x70 [ 101.399137] alloc_inode+0x3b/0xf0 [ 101.399534] iget5_locked+0x54/0xa0 [ 101.400026] ntfs_iget5+0xaf/0x1780 [ 101.400414] ntfs_loadlog_and_replay+0xe5/0x320 [ 101.400883] ntfs_fill_super+0xecb/0x1ba0 [ 101.401313] get_tree_bdev+0x232/0x370 [ 101.401774] ntfs_fs_get_tree+0x15/0x20 [ 101.402224] vfs_get_tree+0x4c/0x130 [ 101.402673] path_mount+0x654/0xfe0 [ 101.403160] do_mount+0xd6/0xf0 [ 101.403537] __x64_sys_mount+0xca/0x110 [ 101.404058] do_syscall_64+0x3b/0x90 [ 101.404333] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 101.404816] [ 101.405067] The buggy address belongs to the object at ffff888008cc9ea0 [ 101.405067] which belongs to the cache ntfs_inode_cache of size 992 [ 101.406171] The buggy address is located 232 bytes inside of [ 101.406171] 992-byte region [ffff888008cc9ea0, ffff888008cca280) [ 101.406995] [ 101.408559] The buggy address belongs to the physical page: [ 101.409320] page:00000000dccf19dd refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x8cc8 [ 101.410654] head:00000000dccf19dd order:2 compound_mapcount:0 compound_pincount:0 [ 101.411533] flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) [ 101.412665] raw: 000fffffc0010200 0000000000000000 dead000000000122 ffff888003695140 [ 101.413209] raw: 0000000000000000 00000000800e000e 00000001ffffffff 0000000000000000 [ 101.413799] page dumped because: kasan: bad access detected [ 101.414213] [ 101.414427] Memory state around the buggy address: [ 101.414991] ffff888008cc9e80: fc fc fc fc 00 00 00 00 00 00 00 00 00 00 00 00 [ 101.415785] ffff888008cc9f00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 101.416933] >ffff888008cc9f80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 101.417857] ^ [ 101.418566] ffff888008cca000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 101.419704] ffff888008cca080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Signed-off-by: Edward Lo Signed-off-by: Konstantin Komarov --- fs/ntfs3/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index ce6bb3bd86b6..059f28878458 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -100,6 +100,12 @@ static struct inode *ntfs_read_mft(struct inode *inode, /* Record should contain $I30 root. */ is_dir = rec->flags & RECORD_FLAG_DIR; + /* MFT_REC_MFT is not a dir */ + if (is_dir && ino == MFT_REC_MFT) { + err = -EINVAL; + goto out; + } + inode->i_generation = le16_to_cpu(rec->seq); /* Enumerate all struct Attributes MFT. */ -- GitLab From ab84eee4c7ab929996602eda7832854c35a6dda2 Mon Sep 17 00:00:00 2001 From: Zeng Heng Date: Mon, 12 Dec 2022 09:31:34 +0800 Subject: [PATCH 1360/5631] fs/ntfs3: Fix slab-out-of-bounds read in hdr_delete_de() Here is a BUG report from syzbot: BUG: KASAN: slab-out-of-bounds in hdr_delete_de+0xe0/0x150 fs/ntfs3/index.c:806 Read of size 16842960 at addr ffff888079cc0600 by task syz-executor934/3631 Call Trace: memmove+0x25/0x60 mm/kasan/shadow.c:54 hdr_delete_de+0xe0/0x150 fs/ntfs3/index.c:806 indx_delete_entry+0x74f/0x3670 fs/ntfs3/index.c:2193 ni_remove_name+0x27a/0x980 fs/ntfs3/frecord.c:2910 ntfs_unlink_inode+0x3d4/0x720 fs/ntfs3/inode.c:1712 ntfs_rename+0x41a/0xcb0 fs/ntfs3/namei.c:276 Before using the meta-data in struct INDEX_HDR, we need to check index header valid or not. Otherwise, the corruptedi (or malicious) fs image can cause out-of-bounds access which could make kernel panic. Fixes: 82cae269cfa9 ("fs/ntfs3: Add initialization of super block") Reported-by: syzbot+9c2811fd56591639ff5f@syzkaller.appspotmail.com Signed-off-by: Zeng Heng Signed-off-by: Konstantin Komarov --- fs/ntfs3/fslog.c | 2 +- fs/ntfs3/index.c | 4 ++++ fs/ntfs3/ntfs_fs.h | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index dc723f03d6bb..bf7396447284 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -2575,7 +2575,7 @@ static int read_next_log_rec(struct ntfs_log *log, struct lcb *lcb, u64 *lsn) return find_log_rec(log, *lsn, lcb); } -static inline bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes) +bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes) { __le16 mask; u32 min_de, de_off, used, total; diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index ae9616becec1..7a1e01a2ed9a 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -848,6 +848,10 @@ static inline struct NTFS_DE *hdr_delete_de(struct INDEX_HDR *hdr, u32 off = PtrOffset(hdr, re); int bytes = used - (off + esize); + /* check INDEX_HDR valid before using INDEX_HDR */ + if (!check_index_header(hdr, le32_to_cpu(hdr->total))) + return NULL; + if (off >= used || esize < sizeof(struct NTFS_DE) || bytes < sizeof(struct NTFS_DE)) return NULL; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 80072e5f96f7..15296f5690b5 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -581,6 +581,7 @@ int ni_rename(struct ntfs_inode *dir_ni, struct ntfs_inode *new_dir_ni, bool ni_is_dirty(struct inode *inode); /* Globals from fslog.c */ +bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ -- GitLab From 08e8cf5f2d9ec383a2e339a2711b62a54ff3fba0 Mon Sep 17 00:00:00 2001 From: Edward Lo Date: Tue, 4 Oct 2022 23:15:06 +0800 Subject: [PATCH 1361/5631] fs/ntfs3: Add length check in indx_get_root This adds a length check to guarantee the retrieved index root is legit. [ 162.459513] BUG: KASAN: use-after-free in hdr_find_e.isra.0+0x10c/0x320 [ 162.460176] Read of size 2 at addr ffff8880037bca99 by task mount/243 [ 162.460851] [ 162.461252] CPU: 0 PID: 243 Comm: mount Not tainted 6.0.0-rc7 #42 [ 162.461744] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 162.462609] Call Trace: [ 162.462954] [ 162.463276] dump_stack_lvl+0x49/0x63 [ 162.463822] print_report.cold+0xf5/0x689 [ 162.464608] ? unwind_get_return_address+0x3a/0x60 [ 162.465766] ? hdr_find_e.isra.0+0x10c/0x320 [ 162.466975] kasan_report+0xa7/0x130 [ 162.467506] ? _raw_spin_lock_irq+0xc0/0xf0 [ 162.467998] ? hdr_find_e.isra.0+0x10c/0x320 [ 162.468536] __asan_load2+0x68/0x90 [ 162.468923] hdr_find_e.isra.0+0x10c/0x320 [ 162.469282] ? cmp_uints+0xe0/0xe0 [ 162.469557] ? cmp_sdh+0x90/0x90 [ 162.469864] ? ni_find_attr+0x214/0x300 [ 162.470217] ? ni_load_mi+0x80/0x80 [ 162.470479] ? entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 162.470931] ? ntfs_bread_run+0x190/0x190 [ 162.471307] ? indx_get_root+0xe4/0x190 [ 162.471556] ? indx_get_root+0x140/0x190 [ 162.471833] ? indx_init+0x1e0/0x1e0 [ 162.472069] ? fnd_clear+0x115/0x140 [ 162.472363] ? _raw_spin_lock_irqsave+0x100/0x100 [ 162.472731] indx_find+0x184/0x470 [ 162.473461] ? sysvec_apic_timer_interrupt+0x57/0xc0 [ 162.474429] ? indx_find_buffer+0x2d0/0x2d0 [ 162.474704] ? do_syscall_64+0x3b/0x90 [ 162.474962] dir_search_u+0x196/0x2f0 [ 162.475381] ? ntfs_nls_to_utf16+0x450/0x450 [ 162.475661] ? ntfs_security_init+0x3d6/0x440 [ 162.475906] ? is_sd_valid+0x180/0x180 [ 162.476191] ntfs_extend_init+0x13f/0x2c0 [ 162.476496] ? ntfs_fix_post_read+0x130/0x130 [ 162.476861] ? iput.part.0+0x286/0x320 [ 162.477325] ntfs_fill_super+0x11e0/0x1b50 [ 162.477709] ? put_ntfs+0x1d0/0x1d0 [ 162.477970] ? vsprintf+0x20/0x20 [ 162.478258] ? set_blocksize+0x95/0x150 [ 162.478538] get_tree_bdev+0x232/0x370 [ 162.478789] ? put_ntfs+0x1d0/0x1d0 [ 162.479038] ntfs_fs_get_tree+0x15/0x20 [ 162.479374] vfs_get_tree+0x4c/0x130 [ 162.479729] path_mount+0x654/0xfe0 [ 162.480124] ? putname+0x80/0xa0 [ 162.480484] ? finish_automount+0x2e0/0x2e0 [ 162.480894] ? putname+0x80/0xa0 [ 162.481467] ? kmem_cache_free+0x1c4/0x440 [ 162.482280] ? putname+0x80/0xa0 [ 162.482714] do_mount+0xd6/0xf0 [ 162.483264] ? path_mount+0xfe0/0xfe0 [ 162.484782] ? __kasan_check_write+0x14/0x20 [ 162.485593] __x64_sys_mount+0xca/0x110 [ 162.486024] do_syscall_64+0x3b/0x90 [ 162.486543] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 162.487141] RIP: 0033:0x7f9d374e948a [ 162.488324] Code: 48 8b 0d 11 fa 2a 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 008 [ 162.489728] RSP: 002b:00007ffe30e73d18 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 162.490971] RAX: ffffffffffffffda RBX: 0000561cdb43a060 RCX: 00007f9d374e948a [ 162.491669] RDX: 0000561cdb43a260 RSI: 0000561cdb43a2e0 RDI: 0000561cdb442af0 [ 162.492050] RBP: 0000000000000000 R08: 0000561cdb43a280 R09: 0000000000000020 [ 162.492459] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 0000561cdb442af0 [ 162.493183] R13: 0000561cdb43a260 R14: 0000000000000000 R15: 00000000ffffffff [ 162.493644] [ 162.493908] [ 162.494214] The buggy address belongs to the physical page: [ 162.494761] page:000000003e38a3d5 refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x37bc [ 162.496064] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff) [ 162.497278] raw: 000fffffc0000000 ffffea00000df1c8 ffffea00000df008 0000000000000000 [ 162.498928] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 162.500542] page dumped because: kasan: bad access detected [ 162.501057] [ 162.501242] Memory state around the buggy address: [ 162.502230] ffff8880037bc980: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.502977] ffff8880037bca00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.503522] >ffff8880037bca80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.503963] ^ [ 162.504370] ffff8880037bcb00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 162.504766] ffff8880037bcb80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Signed-off-by: Edward Lo Signed-off-by: Konstantin Komarov --- fs/ntfs3/index.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 7a1e01a2ed9a..f716487ec8a0 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -994,6 +994,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *a; const struct INDEX_NAMES *in = &s_index_names[indx->type]; + struct INDEX_ROOT *root = NULL; a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, mi); @@ -1003,7 +1004,15 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, if (attr) *attr = a; - return resident_data_ex(a, sizeof(struct INDEX_ROOT)); + root = resident_data_ex(a, sizeof(struct INDEX_ROOT)); + + /* length check */ + if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > + le32_to_cpu(a->res.data_size)) { + return NULL; + } + + return root; } static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni, -- GitLab From e479f0a62a2a4358f25d0d0b60c333e6d881d7c6 Mon Sep 17 00:00:00 2001 From: Yu Zhe Date: Thu, 10 Nov 2022 15:46:40 +0800 Subject: [PATCH 1362/5631] fs/ntfs3: fix spelling mistake "attibute" -> "attribute" There is a spelling mistake in comment. Fix it. Signed-off-by: Yu Zhe Signed-off-by: Konstantin Komarov --- fs/ntfs3/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index f8043838eb92..4746959af964 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -410,7 +410,7 @@ static noinline int ntfs_set_ea(struct inode *inode, const char *name, /* * 1. Check ea_info.size_pack for overflow. - * 2. New attibute size must fit value from $AttrDef + * 2. New attribute size must fit value from $AttrDef */ if (new_pack > 0xffff || size > sbi->ea_max_size) { ntfs_inode_warn( -- GitLab From fc4992458e0aa2d2e82a25c922e6ac36c2d91083 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Thu, 29 Dec 2022 15:44:43 +0400 Subject: [PATCH 1363/5631] fs/ntfs3: Add null pointer checks Added null pointer checks in function ntfs_security_init. Also added le32_to_cpu in functions ntfs_security_init and indx_read. Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 16 ++++++++++------ fs/ntfs3/index.c | 3 ++- 2 files changed, 12 insertions(+), 7 deletions(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 8de861ddec60..1f36e89dcff7 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -1876,10 +1876,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sdh->type != ATTR_ZERO || + if(!(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || - offsetof(struct INDEX_ROOT, ihdr) + root_sdh->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sdh->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } @@ -1895,10 +1897,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sii->type != ATTR_ZERO || + if(!(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || - offsetof(struct INDEX_ROOT, ihdr) + root_sii->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sii->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index f716487ec8a0..8718df791a55 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1102,7 +1102,8 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, } /* check for index header length */ - if (offsetof(struct INDEX_BUFFER, ihdr) + ib->ihdr.used > bytes) { + if (offsetof(struct INDEX_BUFFER, ihdr) + le32_to_cpu(ib->ihdr.used) > + bytes) { err = -EINVAL; goto out; } -- GitLab From 0addfb1c2281b5ca2ac02e7dbf6f5a7dbfbc71b9 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Thu, 29 Dec 2022 15:50:41 +0400 Subject: [PATCH 1364/5631] fs/ntfs3: Improved checking of attribute's name length Added comment, added null pointer checking. Signed-off-by: Konstantin Komarov --- fs/ntfs3/inode.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 059f28878458..3d2e4c1270e4 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -137,7 +137,13 @@ static struct inode *ntfs_read_mft(struct inode *inode, rsize = attr->non_res ? 0 : le32_to_cpu(attr->res.data_size); asize = le32_to_cpu(attr->size); - if (le16_to_cpu(attr->name_off) + attr->name_len > asize) + /* + * Really this check was done in 'ni_enum_attr_ex' -> ... 'mi_enum_attr'. + * There not critical to check this case again + */ + if (attr->name_len && + sizeof(short) * attr->name_len + le16_to_cpu(attr->name_off) > + asize) goto out; if (attr->non_res) { -- GitLab From 318d016e423054c143e5e58644ac93ef553013b9 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Thu, 29 Dec 2022 15:58:56 +0400 Subject: [PATCH 1365/5631] fs/ntfs3: Check for extremely large size of $AttrDef Added additional checking for size of $AttrDef. Added comment. Signed-off-by: Konstantin Komarov --- fs/ntfs3/super.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index ef4ea3f21905..0967035146ce 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1185,10 +1185,18 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto out; } - if (inode->i_size < sizeof(struct ATTR_DEF_ENTRY)) { + /* + * Typical $AttrDef contains up to 20 entries. + * Check for extremely large size. + */ + if (inode->i_size < sizeof(struct ATTR_DEF_ENTRY) || + inode->i_size > 100 * sizeof(struct ATTR_DEF_ENTRY)) { + ntfs_err(sb, "Looks like $AttrDef is corrupted (size=%llu).", + inode->i_size); err = -EINVAL; goto put_inode_out; } + bytes = inode->i_size; sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN); if (!t) { -- GitLab From 30200ef8d1368f0dee424d5926bd7af0cdc87b54 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 30 Dec 2022 14:09:44 +0400 Subject: [PATCH 1366/5631] fs/ntfs3: Restore overflow checking for attr size in mi_enum_attr Fixed comment. Removed explicit initialization for INDEX_ROOT. Signed-off-by: Konstantin Komarov --- fs/ntfs3/index.c | 7 ++++--- fs/ntfs3/record.c | 5 +++++ fs/ntfs3/super.c | 2 +- 3 files changed, 10 insertions(+), 4 deletions(-) diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 8718df791a55..9fefeac5fe7e 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -994,7 +994,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *a; const struct INDEX_NAMES *in = &s_index_names[indx->type]; - struct INDEX_ROOT *root = NULL; + struct INDEX_ROOT *root; a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, mi); @@ -1007,8 +1007,9 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, root = resident_data_ex(a, sizeof(struct INDEX_ROOT)); /* length check */ - if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > - le32_to_cpu(a->res.data_size)) { + if (root && + offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > + le32_to_cpu(a->res.data_size)) { return NULL; } diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index abfe004774c0..0603169ee8a0 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -220,6 +220,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } + if (off + asize < off) { + /* Overflow check. */ + return NULL; + } + attr = Add2Ptr(attr, asize); off += asize; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 0967035146ce..19d0889b131f 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1187,7 +1187,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* * Typical $AttrDef contains up to 20 entries. - * Check for extremely large size. + * Check for extremely large/small size. */ if (inode->i_size < sizeof(struct ATTR_DEF_ENTRY) || inode->i_size > 100 * sizeof(struct ATTR_DEF_ENTRY)) { -- GitLab From 6827d50b2c430c329af442b64c9176d174f56521 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Fri, 30 Dec 2022 14:58:25 +0400 Subject: [PATCH 1367/5631] fs/ntfs3: Refactoring of various minor issues Removed unused macro. Changed null pointer checking. Fixed inconsistent indenting. Signed-off-by: Konstantin Komarov --- fs/ntfs3/bitmap.c | 3 ++- fs/ntfs3/frecord.c | 2 +- fs/ntfs3/fsntfs.c | 6 ++++-- fs/ntfs3/namei.c | 2 +- fs/ntfs3/ntfs.h | 3 --- 5 files changed, 8 insertions(+), 8 deletions(-) diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 723fb64e6531..393c726ef17a 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -658,7 +658,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) if (!wnd->bits_last) wnd->bits_last = wbits; - wnd->free_bits = kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN); + wnd->free_bits = + kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN); if (!wnd->free_bits) return -ENOMEM; diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 912eeb3d3471..1103d4d9a497 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -1645,7 +1645,7 @@ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, { struct ATTRIB *attr = NULL; struct ATTR_FILE_NAME *fname; - struct le_str *fns; + struct le_str *fns; if (le) *le = NULL; diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 1f36e89dcff7..342938704cfd 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -2599,8 +2599,10 @@ static inline bool is_reserved_name(struct ntfs_sb_info *sbi, if (len == 4 || (len > 4 && le16_to_cpu(name[4]) == '.')) { port_digit = le16_to_cpu(name[3]); if (port_digit >= '1' && port_digit <= '9') - if (!ntfs_cmp_names(name, 3, COM_NAME, 3, upcase, false) || - !ntfs_cmp_names(name, 3, LPT_NAME, 3, upcase, false)) + if (!ntfs_cmp_names(name, 3, COM_NAME, 3, upcase, + false) || + !ntfs_cmp_names(name, 3, LPT_NAME, 3, upcase, + false)) return true; } diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 8d206770d8c6..92bbc8ee83ca 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -93,7 +93,7 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry, * If the MFT record of ntfs inode is not a base record, inode->i_op can be NULL. * This causes null pointer dereference in d_splice_alias(). */ - if (!IS_ERR(inode) && inode->i_op == NULL) { + if (!IS_ERR_OR_NULL(inode) && !inode->i_op) { iput(inode); inode = ERR_PTR(-EINVAL); } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 86ea1826d099..90151e56c122 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -435,9 +435,6 @@ static inline u64 attr_svcn(const struct ATTRIB *attr) return attr->non_res ? le64_to_cpu(attr->nres.svcn) : 0; } -/* The size of resident attribute by its resident size. */ -#define BYTES_PER_RESIDENT(b) (0x18 + (b)) - static_assert(sizeof(struct ATTRIB) == 0x48); static_assert(sizeof(((struct ATTRIB *)NULL)->res) == 0x08); static_assert(sizeof(((struct ATTRIB *)NULL)->nres) == 0x38); -- GitLab From ec275bf9693d19cc0fdce8436f4c425ced86f6e7 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Wed, 11 Jan 2023 16:59:43 +0800 Subject: [PATCH 1368/5631] fs/ntfs3: Fix a possible null-pointer dereference in ni_clear() In a previous commit c1006bd13146, ni->mi.mrec in ni_write_inode() could be NULL, and thus a NULL check is added for this variable. However, in the same call stack, ni->mi.mrec can be also dereferenced in ni_clear(): ntfs_evict_inode(inode) ni_write_inode(inode, ...) ni = ntfs_i(inode); is_rec_inuse(ni->mi.mrec) -> Add a NULL check by previous commit ni_clear(ntfs_i(inode)) is_rec_inuse(ni->mi.mrec) -> No check Thus, a possible null-pointer dereference may exist in ni_clear(). To fix it, a NULL check is added in this function. Signed-off-by: Jia-Ju Bai Reported-by: TOTE Robot Signed-off-by: Konstantin Komarov --- fs/ntfs3/frecord.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 1103d4d9a497..9e7dfee303e8 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -102,7 +102,7 @@ void ni_clear(struct ntfs_inode *ni) { struct rb_node *node; - if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec)) + if (!ni->vfs_inode.i_nlink && ni->mi.mrec && is_rec_inuse(ni->mi.mrec)) ni_delete_all(ni); al_destroy(ni); -- GitLab From c20bc9c6d8eb13ab1c3f8e5f8ad91466ae717d7f Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 16 Jan 2023 11:41:41 +0400 Subject: [PATCH 1369/5631] fs/ntfs3: Use bh_read to simplify code The duplicating code is replaced by a generic function bh_read() Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 10 ++-------- fs/ntfs3/inode.c | 1 + 2 files changed, 3 insertions(+), 8 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index e9bdc1ff08c9..b3b72673fa5e 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -223,16 +223,10 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - lock_buffer(bh); - bh->b_end_io = end_buffer_read_sync; - get_bh(bh); - submit_bh(REQ_OP_READ, bh); - - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) { + err = bh_read(bh, 0); + if (err < 0) { unlock_page(page); put_page(page); - err = -EIO; goto out; } } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 3d2e4c1270e4..bb004e476563 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -648,6 +648,7 @@ static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, bh->b_size = block_size; off = vbo & (PAGE_SIZE - 1); set_bh_page(bh, page, off); + err = bh_read(bh, 0); if (err < 0) goto out; -- GitLab From 267a36ba30a7425ad59d20e7e7e33bbdcc9cfb0a Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 16 Jan 2023 12:52:10 +0400 Subject: [PATCH 1370/5631] fs/ntfs3: Remove noacsrules Currently, this option does not work properly. Its use leads to unstable results. If we figure out how to implement it without errors, we will add it later. Signed-off-by: Konstantin Komarov --- Documentation/filesystems/ntfs3.rst | 11 ----------- fs/ntfs3/file.c | 11 ----------- fs/ntfs3/inode.c | 1 - fs/ntfs3/namei.c | 1 - fs/ntfs3/ntfs_fs.h | 3 --- fs/ntfs3/super.c | 9 +-------- fs/ntfs3/xattr.c | 14 -------------- 7 files changed, 1 insertion(+), 49 deletions(-) diff --git a/Documentation/filesystems/ntfs3.rst b/Documentation/filesystems/ntfs3.rst index 5aa102bd72c2..f0cf05cad2ba 100644 --- a/Documentation/filesystems/ntfs3.rst +++ b/Documentation/filesystems/ntfs3.rst @@ -61,17 +61,6 @@ this table marked with no it means default is without **no**. directories, fmask applies only to files and dmask only to directories. * - fmask= - * - noacsrules - - "No access rules" mount option sets access rights for files/folders to - 777 and owner/group to root. This mount option absorbs all other - permissions. - - - Permissions change for files/folders will be reported as successful, - but they will remain 777. - - - Owner/group change will be reported as successful, butthey will stay - as root. - * - nohidden - Files with the Windows-specific HIDDEN (FILE_ATTRIBUTE_HIDDEN) attribute will not be shown under Linux. diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index b3b72673fa5e..e4b54d6bcda5 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -654,22 +654,12 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { - struct super_block *sb = dentry->d_sb; - struct ntfs_sb_info *sbi = sb->s_fs_info; struct inode *inode = d_inode(dentry); struct ntfs_inode *ni = ntfs_i(inode); u32 ia_valid = attr->ia_valid; umode_t mode = inode->i_mode; int err; - if (sbi->options->noacsrules) { - /* "No access rules" - Force any changes of time etc. */ - attr->ia_valid |= ATTR_FORCE; - /* and disable for editing some attributes. */ - attr->ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE); - ia_valid = attr->ia_valid; - } - err = setattr_prepare(idmap, dentry, attr); if (err) goto out; @@ -1153,7 +1143,6 @@ const struct inode_operations ntfs_file_inode_operations = { .getattr = ntfs_getattr, .setattr = ntfs3_setattr, .listxattr = ntfs_listxattr, - .permission = ntfs_permission, .get_inode_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, .fiemap = ntfs_fiemap, diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index bb004e476563..31f7e97fa43e 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -2070,7 +2070,6 @@ const struct inode_operations ntfs_link_inode_operations = { .get_link = ntfs_get_link, .setattr = ntfs3_setattr, .listxattr = ntfs_listxattr, - .permission = ntfs_permission, }; const struct address_space_operations ntfs_aops = { diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 92bbc8ee83ca..fdd11f2a1883 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -607,7 +607,6 @@ const struct inode_operations ntfs_dir_inode_operations = { .rmdir = ntfs_rmdir, .mknod = ntfs_mknod, .rename = ntfs_rename, - .permission = ntfs_permission, .get_inode_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, .setattr = ntfs3_setattr, diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 15296f5690b5..85efb34d211c 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -100,7 +100,6 @@ struct ntfs_mount_options { unsigned hide_dot_files : 1; /* Set hidden flag on dot files. */ unsigned windows_names : 1; /* Disallow names forbidden by Windows. */ unsigned force : 1; /* RW mount dirty volume. */ - unsigned noacsrules : 1; /* Exclude acs rules. */ unsigned prealloc : 1; /* Preallocate space when file is growing. */ unsigned nocase : 1; /* case insensitive. */ }; @@ -870,8 +869,6 @@ int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, #endif int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); -int ntfs_permission(struct mnt_idmap *idmap, struct inode *inode, - int mask); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); extern const struct xattr_handler *ntfs_xattr_handlers[]; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 19d0889b131f..10c019ef7da3 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -253,7 +253,6 @@ enum Opt { Opt_acl, Opt_iocharset, Opt_prealloc, - Opt_noacsrules, Opt_nocase, Opt_err, }; @@ -274,7 +273,6 @@ static const struct fs_parameter_spec ntfs_fs_parameters[] = { fsparam_flag_no("acl", Opt_acl), fsparam_flag_no("showmeta", Opt_showmeta), fsparam_flag_no("prealloc", Opt_prealloc), - fsparam_flag_no("acsrules", Opt_noacsrules), fsparam_flag_no("nocase", Opt_nocase), fsparam_string("iocharset", Opt_iocharset), {} @@ -387,9 +385,6 @@ static int ntfs_fs_parse_param(struct fs_context *fc, case Opt_prealloc: opts->prealloc = result.negated ? 0 : 1; break; - case Opt_noacsrules: - opts->noacsrules = result.negated ? 1 : 0; - break; case Opt_nocase: opts->nocase = result.negated ? 1 : 0; break; @@ -572,8 +567,6 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",hide_dot_files"); if (opts->force) seq_puts(m, ",force"); - if (opts->noacsrules) - seq_puts(m, ",noacsrules"); if (opts->prealloc) seq_puts(m, ",prealloc"); if (sb->s_flags & SB_POSIXACL) @@ -791,7 +784,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, if (boot_sector_size != sector_size) { ntfs_warn( sb, - "Different NTFS' sector size (%u) and media sector size (%u)", + "Different NTFS sector size (%u) and media sector size (%u)", boot_sector_size, sector_size); dev_size += sector_size - 1; } diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 4746959af964..4cab20d70c79 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -711,20 +711,6 @@ int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry) return posix_acl_chmod(idmap, dentry, inode->i_mode); } -/* - * ntfs_permission - inode_operations::permission - */ -int ntfs_permission(struct mnt_idmap *idmap, struct inode *inode, - int mask) -{ - if (ntfs_sb(inode->i_sb)->options->noacsrules) { - /* "No access rules" mode - Allow all changes. */ - return 0; - } - - return generic_permission(idmap, inode, mask); -} - /* * ntfs_listxattr - inode_operations::listxattr */ -- GitLab From 1842fbc8d25e629e54080fe3c5928d4ce8ccf55a Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 16 Jan 2023 13:03:24 +0400 Subject: [PATCH 1371/5631] fs/ntfs3: Fix ntfs_create_inode() Previous variant creates an inode that requires update the parent directory (ea_packed_size). Operations in ntfs_create_inode have been rearranged so we insert new directory entry with correct ea_packed_size and new created inode does not require update it's parent directory. Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 2 +- fs/ntfs3/inode.c | 83 ++++++++++++++++++++++++---------------------- fs/ntfs3/ntfs_fs.h | 2 +- fs/ntfs3/xattr.c | 20 ++++++----- 4 files changed, 58 insertions(+), 49 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index e4b54d6bcda5..1e8d6a3c9fec 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -703,7 +703,7 @@ int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } if (ia_valid & (ATTR_UID | ATTR_GID | ATTR_MODE)) - ntfs_save_wsl_perm(inode); + ntfs_save_wsl_perm(inode, NULL); mark_inode_dirty(inode); out: return err; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 31f7e97fa43e..a7ca8183b91d 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -1320,8 +1320,7 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, inode_init_owner(idmap, inode, dir, mode); mode = inode->i_mode; - inode->i_atime = inode->i_mtime = inode->i_ctime = ni->i_crtime = - current_time(inode); + ni->i_crtime = current_time(inode); rec = ni->mi.mrec; rec->hard_links = cpu_to_le16(1); @@ -1362,10 +1361,9 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, attr->res.data_size = cpu_to_le32(dsize); std5->cr_time = std5->m_time = std5->c_time = std5->a_time = - kernel2nt(&inode->i_atime); + kernel2nt(&ni->i_crtime); - ni->std_fa = fa; - std5->fa = fa; + std5->fa = ni->std_fa = fa; attr = Add2Ptr(attr, asize); @@ -1564,11 +1562,15 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, } asize = SIZEOF_NONRESIDENT + ALIGN(err, 8); + /* Write non resident data. */ + err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rp, + nsize, 0); + if (err) + goto out5; } else { attr->res.data_off = SIZEOF_RESIDENT_LE; attr->res.data_size = cpu_to_le32(nsize); memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), rp, nsize); - nsize = 0; } /* Size of symlink equals the length of input string. */ inode->i_size = size; @@ -1589,19 +1591,8 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, rec->used = cpu_to_le32(PtrOffset(rec, attr) + 8); rec->next_attr_id = cpu_to_le16(aid); - /* Step 2: Add new name in index. */ - err = indx_insert_entry(&dir_ni->dir, dir_ni, new_de, sbi, fnd, 0); - if (err) - goto out6; - - /* Unlock parent directory before ntfs_init_acl. */ - if (!fnd) - ni_unlock(dir_ni); - inode->i_generation = le16_to_cpu(rec->seq); - dir->i_mtime = dir->i_ctime = inode->i_atime; - if (S_ISDIR(mode)) { inode->i_op = &ntfs_dir_inode_operations; inode->i_fop = &ntfs_dir_operations; @@ -1626,41 +1617,58 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, if (!S_ISLNK(mode) && (sb->s_flags & SB_POSIXACL)) { err = ntfs_init_acl(idmap, inode, dir); if (err) - goto out7; + goto out5; } else #endif { inode->i_flags |= S_NOSEC; } - /* Write non resident data. */ - if (nsize) { - err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rp, nsize, 0); - if (err) - goto out7; + /* + * ntfs_init_acl and ntfs_save_wsl_perm update extended attribute. + * The packed size of extended attribute is stored in direntry too. + * 'fname' here points to inside new_de. + */ + ntfs_save_wsl_perm(inode, &fname->dup.ea_size); + + /* + * update ea_size in file_name attribute too. + * Use ni_find_attr cause layout of MFT record may be changed + * in ntfs_init_acl and ntfs_save_wsl_perm. + */ + attr = ni_find_attr(ni, NULL, NULL, ATTR_NAME, NULL, 0, NULL, NULL); + if (attr) { + struct ATTR_FILE_NAME *fn; + + fn = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); + if (fn) + fn->dup.ea_size = fname->dup.ea_size; } + /* We do not need to update parent directory later */ + ni->ni_flags &= ~NI_FLAG_UPDATE_PARENT; + + /* Step 2: Add new name in index. */ + err = indx_insert_entry(&dir_ni->dir, dir_ni, new_de, sbi, fnd, 0); + if (err) + goto out6; + /* * Call 'd_instantiate' after inode->i_op is set * but before finish_open. */ d_instantiate(dentry, inode); - ntfs_save_wsl_perm(inode); + /* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */ + inode->i_atime = inode->i_mtime = inode->i_ctime = dir->i_mtime = + dir->i_ctime = ni->i_crtime; + mark_inode_dirty(dir); mark_inode_dirty(inode); /* Normal exit. */ goto out2; -out7: - - /* Undo 'indx_insert_entry'. */ - if (!fnd) - ni_lock_dir(dir_ni); - indx_delete_entry(&dir_ni->dir, dir_ni, new_de + 1, - le16_to_cpu(new_de->key_size), sbi); - /* ni_unlock(dir_ni); will be called later. */ out6: if (rp_inserted) ntfs_remove_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref); @@ -1682,11 +1690,11 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, kfree(rp); out1: - if (err) { - if (!fnd) - ni_unlock(dir_ni); + if (!fnd) + ni_unlock(dir_ni); + + if (err) return ERR_PTR(err); - } unlock_new_inode(inode); @@ -1783,9 +1791,6 @@ void ntfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); - if (inode->i_nlink) - _ni_write_inode(inode, inode_needs_sync(inode)); - invalidate_inode_buffers(inode); clear_inode(inode); diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 85efb34d211c..50b7fb71ca26 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -872,7 +872,7 @@ int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); extern const struct xattr_handler *ntfs_xattr_handlers[]; -int ntfs_save_wsl_perm(struct inode *inode); +int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size); void ntfs_get_wsl_perm(struct inode *inode); /* globals from lznt.c */ diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 4cab20d70c79..9fbeaa7bbc00 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -296,7 +296,8 @@ static int ntfs_get_ea(struct inode *inode, const char *name, size_t name_len, static noinline int ntfs_set_ea(struct inode *inode, const char *name, size_t name_len, const void *value, - size_t val_size, int flags, bool locked) + size_t val_size, int flags, bool locked, + __le16 *ea_size) { struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_sb_info *sbi = ni->mi.sbi; @@ -504,6 +505,8 @@ static noinline int ntfs_set_ea(struct inode *inode, const char *name, if (ea_info.size_pack != size_pack) ni->ni_flags |= NI_FLAG_UPDATE_PARENT; + if (ea_size) + *ea_size = ea_info.size_pack; mark_inode_dirty(&ni->vfs_inode); out: @@ -633,7 +636,7 @@ static noinline int ntfs_set_acl_ex(struct mnt_idmap *idmap, flags = 0; } - err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0); + err = ntfs_set_ea(inode, name, name_len, value, size, flags, 0, NULL); if (err == -ENODATA && !size) err = 0; /* Removing non existed xattr. */ if (!err) { @@ -923,7 +926,8 @@ static noinline int ntfs_setxattr(const struct xattr_handler *handler, } /* Deal with NTFS extended attribute. */ - err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0); + err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0, + NULL); out: inode->i_ctime = current_time(inode); @@ -937,7 +941,7 @@ static noinline int ntfs_setxattr(const struct xattr_handler *handler, * * save uid/gid/mode in xattr */ -int ntfs_save_wsl_perm(struct inode *inode) +int ntfs_save_wsl_perm(struct inode *inode, __le16 *ea_size) { int err; __le32 value; @@ -946,26 +950,26 @@ int ntfs_save_wsl_perm(struct inode *inode) ni_lock(ni); value = cpu_to_le32(i_uid_read(inode)); err = ntfs_set_ea(inode, "$LXUID", sizeof("$LXUID") - 1, &value, - sizeof(value), 0, true); /* true == already locked. */ + sizeof(value), 0, true, ea_size); if (err) goto out; value = cpu_to_le32(i_gid_read(inode)); err = ntfs_set_ea(inode, "$LXGID", sizeof("$LXGID") - 1, &value, - sizeof(value), 0, true); + sizeof(value), 0, true, ea_size); if (err) goto out; value = cpu_to_le32(inode->i_mode); err = ntfs_set_ea(inode, "$LXMOD", sizeof("$LXMOD") - 1, &value, - sizeof(value), 0, true); + sizeof(value), 0, true, ea_size); if (err) goto out; if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { value = cpu_to_le32(inode->i_rdev); err = ntfs_set_ea(inode, "$LXDEV", sizeof("$LXDEV") - 1, &value, - sizeof(value), 0, true); + sizeof(value), 0, true, ea_size); if (err) goto out; } -- GitLab From 625602487a03203a732dc0d4b63da895f45def86 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 16 Jan 2023 14:23:38 +0400 Subject: [PATCH 1372/5631] fs/ntfs3: Optimization in ntfs_set_state() The current volume flags are updated only if VOLUME_FLAG_DIRTY has been changed. Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 342938704cfd..d888ba14237f 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -925,6 +925,7 @@ int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty) struct VOLUME_INFO *info; struct mft_inode *mi; struct ntfs_inode *ni; + __le16 info_flags; /* * Do not change state if fs was real_dirty. @@ -957,6 +958,8 @@ int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty) goto out; } + info_flags = info->flags; + switch (dirty) { case NTFS_DIRTY_ERROR: ntfs_notice(sbi->sb, "Mark volume as dirty due to NTFS errors"); @@ -970,8 +973,10 @@ int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty) break; } /* Cache current volume flags. */ - sbi->volume.flags = info->flags; - mi->dirty = true; + if (info_flags != info->flags) { + sbi->volume.flags = info->flags; + mi->dirty = true; + } err = 0; out: -- GitLab From e483783c7bca4169a5ed284acc01a9577c875407 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 14 Feb 2023 13:44:22 +0400 Subject: [PATCH 1373/5631] fs/ntfs3: Undo endian changes sbi->mft.reserved_bitmap is in-memory (not on-disk!) bitmap. Assumed cpu endian is faster than fixed endian. Signed-off-by: Konstantin Komarov --- fs/ntfs3/fsntfs.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index d888ba14237f..9ed9dd0d8edf 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -646,13 +646,13 @@ int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, NULL, 0, NULL, NULL)) goto next; - __clear_bit_le(ir - MFT_REC_RESERVED, + __clear_bit(ir - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); } } /* Scan 5 bits for zero. Bit 0 == MFT_REC_RESERVED */ - zbit = find_next_zero_bit_le(&sbi->mft.reserved_bitmap, + zbit = find_next_zero_bit(&sbi->mft.reserved_bitmap, MFT_REC_FREE, MFT_REC_RESERVED); if (zbit >= MFT_REC_FREE) { sbi->mft.next_reserved = MFT_REC_FREE; @@ -720,7 +720,7 @@ int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, if (*rno >= MFT_REC_FREE) wnd_set_used(wnd, *rno, 1); else if (*rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) - __set_bit_le(*rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); + __set_bit(*rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); out: if (!mft) @@ -748,7 +748,7 @@ void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft) else wnd_set_free(wnd, rno, 1); } else if (rno >= MFT_REC_RESERVED && sbi->mft.reserved_bitmap_inited) { - __clear_bit_le(rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); + __clear_bit(rno - MFT_REC_RESERVED, &sbi->mft.reserved_bitmap); } if (rno < wnd_zone_bit(wnd)) @@ -846,9 +846,8 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) { int err; struct super_block *sb = sbi->sb; - u32 blocksize; + u32 blocksize, bytes; sector_t block1, block2; - u32 bytes; if (!sb) return; -- GitLab From 63e92a0c5a0d5816803907a3e30a91ef72c903a5 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 14 Feb 2023 13:57:09 +0400 Subject: [PATCH 1374/5631] fs/ntfs3: Undo critial modificatins to keep directory consistency Affect xfstest 320. Signed-off-by: Konstantin Komarov --- fs/ntfs3/index.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 9fefeac5fe7e..5d1ec0124137 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1778,10 +1778,11 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, struct indx_node *n1 = fnd->nodes[level]; struct INDEX_HDR *hdr1 = &n1->index->ihdr; struct INDEX_HDR *hdr2; - u32 to_copy, used; + u32 to_copy, used, used1; CLST new_vbn; __le64 t_vbn, *sub_vbn; u16 sp_size; + void *hdr1_saved = NULL; /* Try the most easy case. */ e = fnd->level - 1 == level ? fnd->de[level] : NULL; @@ -1814,6 +1815,13 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, return -ENOMEM; memcpy(up_e, sp, sp_size); + used1 = le32_to_cpu(hdr1->used); + hdr1_saved = kmemdup(hdr1, used1, GFP_NOFS); + if (!hdr1_saved) { + err = -ENOMEM; + goto out; + } + if (!hdr1->flags) { up_e->flags |= NTFS_IE_HAS_SUBNODES; up_e->size = cpu_to_le16(sp_size + sizeof(u64)); @@ -1846,7 +1854,7 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, hdr_insert_head(hdr2, de_t, to_copy); /* Remove all entries (sp including) from hdr1. */ - used = le32_to_cpu(hdr1->used) - to_copy - sp_size; + used = used1 - to_copy - sp_size; memmove(de_t, Add2Ptr(sp, sp_size), used - le32_to_cpu(hdr1->de_off)); hdr1->used = cpu_to_le32(used); @@ -1876,8 +1884,6 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, if (!level) { /* Insert in root. */ err = indx_insert_into_root(indx, ni, up_e, NULL, ctx, fnd, 0); - if (err) - goto out; } else { /* * The target buffer's parent is another index buffer. @@ -1885,12 +1891,20 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, */ err = indx_insert_into_buffer(indx, ni, root, up_e, ctx, level - 1, fnd); - if (err) - goto out; + } + + if (err) { + /* + * Undo critical operations. + */ + indx_mark_free(indx, ni, new_vbn >> indx->idx2vbn_bits); + memcpy(hdr1, hdr1_saved, used1); + indx_write(indx, ni, n1, 0); } out: kfree(up_e); + kfree(hdr1_saved); return err; } @@ -1949,16 +1963,12 @@ int indx_insert_entry(struct ntfs_index *indx, struct ntfs_inode *ni, */ err = indx_insert_into_root(indx, ni, new_de, fnd->root_de, ctx, fnd, undo); - if (err) - goto out; } else { /* * Found a leaf buffer, so we'll insert the new entry into it. */ err = indx_insert_into_buffer(indx, ni, root, new_de, ctx, fnd->level - 1, fnd); - if (err) - goto out; } out: -- GitLab From 1a6be5fb156a1a7e1c81d30ca4ca48bca99b7ca1 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 14 Feb 2023 14:00:04 +0400 Subject: [PATCH 1375/5631] fs/ntfs3: Remove field sbi->used.bitmap.set_tail This field is not used in driver. Signed-off-by: Konstantin Komarov --- fs/ntfs3/ntfs_fs.h | 1 - fs/ntfs3/super.c | 2 -- 2 files changed, 3 deletions(-) diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 50b7fb71ca26..7845c627a761 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -163,7 +163,6 @@ struct wnd_bitmap { size_t zone_bit; size_t zone_end; - bool set_tail; // Not necessary in driver. bool inited; }; diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 10c019ef7da3..d7bec9b28a42 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1117,8 +1117,6 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto put_inode_out; } - /* Not necessary. */ - sbi->used.bitmap.set_tail = true; err = wnd_init(&sbi->used.bitmap, sb, tt); if (err) goto put_inode_out; -- GitLab From 75c5e0c9e5cad34deeec7c131c2b1368df5a8c75 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 14 Feb 2023 15:06:27 +0400 Subject: [PATCH 1376/5631] fs/ntfs3: Changed ntfs_get_acl() to use dentry ntfs_get_acl changed to match new interface in struct inode_operations. Signed-off-by: Konstantin Komarov --- fs/ntfs3/file.c | 2 +- fs/ntfs3/namei.c | 4 ++-- fs/ntfs3/ntfs_fs.h | 5 +++-- fs/ntfs3/xattr.c | 26 +++++++++----------------- 4 files changed, 15 insertions(+), 22 deletions(-) diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 1e8d6a3c9fec..56185bd1a03e 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1143,7 +1143,7 @@ const struct inode_operations ntfs_file_inode_operations = { .getattr = ntfs_getattr, .setattr = ntfs3_setattr, .listxattr = ntfs_listxattr, - .get_inode_acl = ntfs_get_acl, + .get_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, .fiemap = ntfs_fiemap, }; diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index fdd11f2a1883..447a241fe02c 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -607,7 +607,7 @@ const struct inode_operations ntfs_dir_inode_operations = { .rmdir = ntfs_rmdir, .mknod = ntfs_mknod, .rename = ntfs_rename, - .get_inode_acl = ntfs_get_acl, + .get_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, .setattr = ntfs3_setattr, .getattr = ntfs_getattr, @@ -620,7 +620,7 @@ const struct inode_operations ntfs_special_inode_operations = { .setattr = ntfs3_setattr, .getattr = ntfs_getattr, .listxattr = ntfs_listxattr, - .get_inode_acl = ntfs_get_acl, + .get_acl = ntfs_get_acl, .set_acl = ntfs_set_acl, }; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 7845c627a761..15df110f561f 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -857,11 +857,12 @@ unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase, /* globals from xattr.c */ #ifdef CONFIG_NTFS3_FS_POSIX_ACL -struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu); +struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, + struct dentry *dentry, int type); int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, - struct inode *dir); + struct inode *dir); #else #define ntfs_get_acl NULL #define ntfs_set_acl NULL diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 9fbeaa7bbc00..d2746803f032 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -520,9 +520,14 @@ static noinline int ntfs_set_ea(struct inode *inode, const char *name, } #ifdef CONFIG_NTFS3_FS_POSIX_ACL -static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, - int locked) + +/* + * ntfs_get_acl - inode_operations::get_acl + */ +struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, + struct dentry *dentry, int type) { + struct inode *inode = d_inode(dentry); struct ntfs_inode *ni = ntfs_i(inode); const char *name; size_t name_len; @@ -545,13 +550,11 @@ static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, name_len = sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1; } - if (!locked) - ni_lock(ni); + ni_lock(ni); err = ntfs_get_ea(inode, name, name_len, buf, PATH_MAX, &req); - if (!locked) - ni_unlock(ni); + ni_unlock(ni); /* Translate extended attribute to acl. */ if (err >= 0) { @@ -570,17 +573,6 @@ static struct posix_acl *ntfs_get_acl_ex(struct inode *inode, int type, return acl; } -/* - * ntfs_get_acl - inode_operations::get_acl - */ -struct posix_acl *ntfs_get_acl(struct inode *inode, int type, bool rcu) -{ - if (rcu) - return ERR_PTR(-ECHILD); - - return ntfs_get_acl_ex(inode, type, 0); -} - static noinline int ntfs_set_acl_ex(struct mnt_idmap *idmap, struct inode *inode, struct posix_acl *acl, int type, bool init_acl) -- GitLab From 96de65a9413e0422233b285368e8a9a64e461187 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Tue, 17 Jan 2023 15:01:00 +0400 Subject: [PATCH 1377/5631] fs/ntfs3: Code formatting and refactoring Added minor refactoring. Added and fixed some comments. In some places, the code has been reformatted to fit into 80 columns. clang-format-12 was used to format code according kernel's .clang-format. Signed-off-by: Konstantin Komarov --- fs/ntfs3/attrib.c | 17 +++++----- fs/ntfs3/bitmap.c | 22 ++++++------- fs/ntfs3/file.c | 25 ++++++++------- fs/ntfs3/frecord.c | 37 ++++++++++------------ fs/ntfs3/fslog.c | 77 +++++++++++++++++++++++----------------------- fs/ntfs3/fsntfs.c | 13 ++++---- fs/ntfs3/index.c | 28 +++++++++-------- fs/ntfs3/inode.c | 33 ++++++++++---------- fs/ntfs3/lznt.c | 10 +++--- fs/ntfs3/namei.c | 4 +-- fs/ntfs3/ntfs_fs.h | 9 +++--- fs/ntfs3/record.c | 9 +++--- fs/ntfs3/run.c | 6 ++-- fs/ntfs3/super.c | 70 ++++++++++++++++++++++------------------- fs/ntfs3/xattr.c | 4 +-- 15 files changed, 186 insertions(+), 178 deletions(-) diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 5e6bafb10f42..0b8bc66377db 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -405,8 +405,8 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, int err = 0; struct ntfs_sb_info *sbi = ni->mi.sbi; u8 cluster_bits = sbi->cluster_bits; - bool is_mft = - ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && !name_len; + bool is_mft = ni->mi.rno == MFT_REC_MFT && type == ATTR_DATA && + !name_len; u64 old_valid, old_size, old_alloc, new_alloc, new_alloc_tmp; struct ATTRIB *attr = NULL, *attr_b; struct ATTR_LIST_ENTRY *le, *le_b; @@ -531,11 +531,10 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, pre_alloc = 0; if (type == ATTR_DATA && !name_len && sbi->options->prealloc) { - pre_alloc = - bytes_to_cluster( - sbi, - get_pre_allocated(new_size)) - - new_alen; + pre_alloc = bytes_to_cluster( + sbi, get_pre_allocated( + new_size)) - + new_alen; } /* Get the last LCN to allocate from. */ @@ -573,8 +572,8 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, err = attr_allocate_clusters( sbi, run, vcn, lcn, to_allocate, &pre_alloc, is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, - is_mft ? 0 - : (sbi->record_size - + is_mft ? 0 : + (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 393c726ef17a..9a6c6a09d70c 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -40,9 +40,9 @@ static struct kmem_cache *ntfs_enode_cachep; int __init ntfs3_init_bitmap(void) { - ntfs_enode_cachep = - kmem_cache_create("ntfs3_enode_cache", sizeof(struct e_node), 0, - SLAB_RECLAIM_ACCOUNT, NULL); + ntfs_enode_cachep = kmem_cache_create("ntfs3_enode_cache", + sizeof(struct e_node), 0, + SLAB_RECLAIM_ACCOUNT, NULL); return ntfs_enode_cachep ? 0 : -ENOMEM; } @@ -286,9 +286,9 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, if (wnd->uptodated != 1) { /* Check bits before 'bit'. */ ib = wnd->zone_bit == wnd->zone_end || - bit < wnd->zone_end - ? 0 - : wnd->zone_end; + bit < wnd->zone_end ? + 0 : + wnd->zone_end; while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) { bit -= 1; @@ -297,9 +297,9 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, /* Check bits after 'end_in'. */ ib = wnd->zone_bit == wnd->zone_end || - end_in > wnd->zone_bit - ? wnd->nbits - : wnd->zone_bit; + end_in > wnd->zone_bit ? + wnd->nbits : + wnd->zone_bit; while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) { end_in += 1; @@ -417,8 +417,8 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len) return; n3 = rb_first(&wnd->count_tree); wnd->extent_max = - n3 ? rb_entry(n3, struct e_node, count.node)->count.key - : 0; + n3 ? rb_entry(n3, struct e_node, count.node)->count.key : + 0; return; } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 56185bd1a03e..9a3d55c367d9 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -22,20 +22,21 @@ static int ntfs_ioctl_fitrim(struct ntfs_sb_info *sbi, unsigned long arg) { struct fstrim_range __user *user_range; struct fstrim_range range; + struct block_device *dev; int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!bdev_max_discard_sectors(sbi->sb->s_bdev)) + dev = sbi->sb->s_bdev; + if (!bdev_max_discard_sectors(dev)) return -EOPNOTSUPP; user_range = (struct fstrim_range __user *)arg; if (copy_from_user(&range, user_range, sizeof(range))) return -EFAULT; - range.minlen = max_t(u32, range.minlen, - bdev_discard_granularity(sbi->sb->s_bdev)); + range.minlen = max_t(u32, range.minlen, bdev_discard_granularity(dev)); err = ntfs_trim_fs(sbi, &range); if (err < 0) @@ -190,8 +191,8 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) for (; idx < idx_end; idx += 1, from = 0) { page_off = (loff_t)idx << PAGE_SHIFT; - to = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) - : PAGE_SIZE; + to = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) : + PAGE_SIZE; iblock = page_off >> inode->i_blkbits; page = find_or_create_page(mapping, idx, @@ -564,13 +565,14 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) ni_unlock(ni); } else { /* Check new size. */ + u8 cluster_bits = sbi->cluster_bits; /* generic/213: expected -ENOSPC instead of -EFBIG. */ if (!is_supported_holes) { loff_t to_alloc = new_size - inode_get_bytes(inode); if (to_alloc > 0 && - (to_alloc >> sbi->cluster_bits) > + (to_alloc >> cluster_bits) > wnd_zeroes(&sbi->used.bitmap)) { err = -ENOSPC; goto out; @@ -591,7 +593,7 @@ static long ntfs_fallocate(struct file *file, int mode, loff_t vbo, loff_t len) } if (is_supported_holes) { - CLST vcn = vbo >> sbi->cluster_bits; + CLST vcn = vbo >> cluster_bits; CLST cend = bytes_to_cluster(sbi, end); CLST cend_v = bytes_to_cluster(sbi, ni->i_valid); CLST lcn, clen; @@ -1049,8 +1051,8 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret) goto out; - ret = is_compressed(ni) ? ntfs_compress_write(iocb, from) - : __generic_file_write_iter(iocb, from); + ret = is_compressed(ni) ? ntfs_compress_write(iocb, from) : + __generic_file_write_iter(iocb, from); out: inode_unlock(inode); @@ -1102,8 +1104,9 @@ static int ntfs_file_release(struct inode *inode, struct file *file) int err = 0; /* If we are last writer on the inode, drop the block reservation. */ - if (sbi->options->prealloc && ((file->f_mode & FMODE_WRITE) && - atomic_read(&inode->i_writecount) == 1)) { + if (sbi->options->prealloc && + ((file->f_mode & FMODE_WRITE) && + atomic_read(&inode->i_writecount) == 1)) { ni_lock(ni); down_write(&ni->file.run_lock); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 9e7dfee303e8..481219f2a7cf 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -76,8 +76,8 @@ struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni) const struct ATTRIB *attr; attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); - return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) - : NULL; + return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) : + NULL; } /* @@ -91,8 +91,8 @@ struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni) attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); - return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) - : NULL; + return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) : + NULL; } /* @@ -1439,8 +1439,8 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, int err; CLST plen; struct ATTRIB *attr; - bool is_ext = - (flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED)) && !svcn; + bool is_ext = (flags & (ATTR_FLAG_SPARSED | ATTR_FLAG_COMPRESSED)) && + !svcn; u32 name_size = ALIGN(name_len * sizeof(short), 8); u32 name_off = is_ext ? SIZEOF_NONRESIDENT_EX : SIZEOF_NONRESIDENT; u32 run_off = name_off + name_size; @@ -1756,9 +1756,9 @@ int ni_new_attr_flags(struct ntfs_inode *ni, enum FILE_ATTRIBUTE new_fa) } /* Resize nonresident empty attribute in-place only. */ - new_asize = (new_aflags & (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) - ? (SIZEOF_NONRESIDENT_EX + 8) - : (SIZEOF_NONRESIDENT + 8); + new_asize = (new_aflags & (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) ? + (SIZEOF_NONRESIDENT_EX + 8) : + (SIZEOF_NONRESIDENT + 8); if (!mi_resize_attr(mi, attr, new_asize - le32_to_cpu(attr->size))) return -EOPNOTSUPP; @@ -2965,14 +2965,14 @@ bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, { struct ntfs_sb_info *sbi = ni->mi.sbi; struct ATTRIB *attr; - u16 de_key_size = de2 ? le16_to_cpu(de2->key_size) : 0; + u16 de_key_size; switch (undo_step) { case 4: + de_key_size = le16_to_cpu(de2->key_size); if (ni_insert_resident(ni, de_key_size, ATTR_NAME, NULL, 0, - &attr, NULL, NULL)) { + &attr, NULL, NULL)) return false; - } memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), de2 + 1, de_key_size); mi_get_ref(&ni->mi, &de2->ref); @@ -2981,19 +2981,16 @@ bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, de2->flags = 0; de2->res = 0; - if (indx_insert_entry(&dir_ni->dir, dir_ni, de2, sbi, NULL, - 1)) { + if (indx_insert_entry(&dir_ni->dir, dir_ni, de2, sbi, NULL, 1)) return false; - } fallthrough; case 2: de_key_size = le16_to_cpu(de->key_size); if (ni_insert_resident(ni, de_key_size, ATTR_NAME, NULL, 0, - &attr, NULL, NULL)) { + &attr, NULL, NULL)) return false; - } memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), de + 1, de_key_size); mi_get_ref(&ni->mi, &de->ref); @@ -3162,9 +3159,9 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, u64 data_size = le64_to_cpu(attr->nres.data_size); __le64 valid_le; - dup->alloc_size = is_attr_ext(attr) - ? attr->nres.total_size - : attr->nres.alloc_size; + dup->alloc_size = is_attr_ext(attr) ? + attr->nres.total_size : + attr->nres.alloc_size; dup->data_size = attr->nres.data_size; if (new_valid > data_size) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index bf7396447284..57762c5fe68b 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -827,10 +827,10 @@ static inline struct RESTART_TABLE *extend_rsttbl(struct RESTART_TABLE *tbl, memcpy(rt + 1, tbl + 1, esize * used); - rt->free_goal = free_goal == ~0u - ? cpu_to_le32(~0u) - : cpu_to_le32(sizeof(struct RESTART_TABLE) + - free_goal * esize); + rt->free_goal = free_goal == ~0u ? + cpu_to_le32(~0u) : + cpu_to_le32(sizeof(struct RESTART_TABLE) + + free_goal * esize); if (tbl->first_free) { rt->first_free = tbl->first_free; @@ -1089,9 +1089,9 @@ static inline u64 base_lsn(struct ntfs_log *log, (lsn < (lsn_to_vbo(log, h_lsn) & ~log->page_mask) ? 1 : 0)) << log->file_data_bits) + ((((is_log_record_end(hdr) && - h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn)) - ? le16_to_cpu(hdr->record_hdr.next_record_off) - : log->page_size) + + h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn)) ? + le16_to_cpu(hdr->record_hdr.next_record_off) : + log->page_size) + lsn) >> 3); @@ -1298,9 +1298,9 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size, if (!log->clst_per_page) log->clst_per_page = 1; - log->first_page = major_ver >= 2 - ? 0x22 * page_size - : ((sys_page_size << 1) + (page_size << 1)); + log->first_page = major_ver >= 2 ? + 0x22 * page_size : + ((sys_page_size << 1) + (page_size << 1)); log->major_ver = major_ver; log->minor_ver = minor_ver; } @@ -1512,20 +1512,19 @@ static u32 current_log_avail(struct ntfs_log *log) * have to compute the free range. * If there is no oldest lsn then start at the first page of the file. */ - oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN) - ? log->first_page - : (log->oldest_lsn_off & ~log->sys_page_mask); + oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN) ? + log->first_page : + (log->oldest_lsn_off & ~log->sys_page_mask); /* * We will use the next log page offset to compute the next free page. * If we are going to reuse this page go to the next page. * If we are at the first page then use the end of the file. */ - next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL) - ? log->next_page + log->page_size - : log->next_page == log->first_page - ? log->l_size - : log->next_page; + next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL) ? + log->next_page + log->page_size : + log->next_page == log->first_page ? log->l_size : + log->next_page; /* If the two offsets are the same then there is no available space. */ if (oldest_off == next_free_off) @@ -1535,9 +1534,9 @@ static u32 current_log_avail(struct ntfs_log *log) * this range from the total available pages. */ free_bytes = - oldest_off < next_free_off - ? log->total_avail_pages - (next_free_off - oldest_off) - : oldest_off - next_free_off; + oldest_off < next_free_off ? + log->total_avail_pages - (next_free_off - oldest_off) : + oldest_off - next_free_off; free_bytes >>= log->page_bits; return free_bytes * log->reserved; @@ -1671,8 +1670,8 @@ static int last_log_lsn(struct ntfs_log *log) } best_lsn1 = first_tail ? base_lsn(log, first_tail, first_file_off) : 0; - best_lsn2 = - second_tail ? base_lsn(log, second_tail, second_file_off) : 0; + best_lsn2 = second_tail ? base_lsn(log, second_tail, second_file_off) : + 0; if (first_tail && second_tail) { if (best_lsn1 > best_lsn2) { @@ -1767,8 +1766,8 @@ static int last_log_lsn(struct ntfs_log *log) page_cnt = page_pos = 1; - curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off) - : log->next_page; + curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off) : + log->next_page; wrapped_file = curpage_off == log->first_page && @@ -1826,9 +1825,9 @@ static int last_log_lsn(struct ntfs_log *log) le64_to_cpu(cur_page->record_hdr.last_end_lsn) && ((lsn_cur >> log->file_data_bits) + ((curpage_off < - (lsn_to_vbo(log, lsn_cur) & ~log->page_mask)) - ? 1 - : 0)) != expected_seq) { + (lsn_to_vbo(log, lsn_cur) & ~log->page_mask)) ? + 1 : + 0)) != expected_seq) { goto check_tail; } @@ -2642,9 +2641,10 @@ static inline bool check_index_root(const struct ATTRIB *attr, { bool ret; const struct INDEX_ROOT *root = resident_data(attr); - u8 index_bits = le32_to_cpu(root->index_block_size) >= sbi->cluster_size - ? sbi->cluster_bits - : SECTOR_SHIFT; + u8 index_bits = le32_to_cpu(root->index_block_size) >= + sbi->cluster_size ? + sbi->cluster_bits : + SECTOR_SHIFT; u8 block_clst = root->index_block_clst; if (le32_to_cpu(attr->res.data_size) < sizeof(struct INDEX_ROOT) || @@ -3683,7 +3683,8 @@ static int do_action(struct ntfs_log *log, struct OPEN_ATTR_ENRTY *oe, if (a_dirty) { attr = oa->attr; - err = ntfs_sb_write_run(sbi, oa->run1, vbo, buffer_le, bytes, 0); + err = ntfs_sb_write_run(sbi, oa->run1, vbo, buffer_le, bytes, + 0); if (err) goto out; } @@ -3768,11 +3769,10 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) if (!log) return -ENOMEM; - memset(&rst_info, 0, sizeof(struct restart_info)); - log->ni = ni; log->l_size = l_size; log->one_page_buf = kmalloc(page_size, GFP_NOFS); + if (!log->one_page_buf) { err = -ENOMEM; goto out; @@ -3783,6 +3783,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) log->page_bits = blksize_bits(page_size); /* Look for a restart area on the disk. */ + memset(&rst_info, 0, sizeof(struct restart_info)); err = log_read_rst(log, l_size, true, &rst_info); if (err) goto out; @@ -3859,10 +3860,10 @@ int log_replay(struct ntfs_inode *ni, bool *initialized) log->init_ra = !!rst_info.vbo; /* If we have a valid page then grab a pointer to the restart area. */ - ra2 = rst_info.valid_page - ? Add2Ptr(rst_info.r_page, - le16_to_cpu(rst_info.r_page->ra_off)) - : NULL; + ra2 = rst_info.valid_page ? + Add2Ptr(rst_info.r_page, + le16_to_cpu(rst_info.r_page->ra_off)) : + NULL; if (rst_info.chkdsk_was_run || (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) { diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 9ed9dd0d8edf..0a82b1bf3ec2 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -172,8 +172,8 @@ int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, u16 sample, fo, fn; fo = le16_to_cpu(rhdr->fix_off); - fn = simple ? ((bytes >> SECTOR_SHIFT) + 1) - : le16_to_cpu(rhdr->fix_num); + fn = simple ? ((bytes >> SECTOR_SHIFT) + 1) : + le16_to_cpu(rhdr->fix_num); /* Check errors. */ if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || @@ -849,14 +849,13 @@ void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait) u32 blocksize, bytes; sector_t block1, block2; - if (!sb) + /* + * sb can be NULL here. In this case sbi->flags should be 0 too. + */ + if (!sb || !(sbi->flags & NTFS_FLAGS_MFTMIRR)) return; blocksize = sb->s_blocksize; - - if (!(sbi->flags & NTFS_FLAGS_MFTMIRR)) - return; - bytes = sbi->mft.recs_mirr << sbi->record_bits; block1 = sbi->mft.lbo >> sb->s_blocksize_bits; block2 = sbi->mft.lbo2 >> sb->s_blocksize_bits; diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 5d1ec0124137..0a48d2d67219 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -431,8 +431,9 @@ static int scan_nres_bitmap(struct ntfs_inode *ni, struct ATTRIB *bitmap, if (vbo + blocksize > data_size) nbits = 8 * (data_size - vbo); - ok = nbits > from ? (*fn)((ulong *)bh->b_data, from, nbits, ret) - : false; + ok = nbits > from ? + (*fn)((ulong *)bh->b_data, from, nbits, ret) : + false; put_bh(bh); if (ok) { @@ -764,8 +765,7 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, return NULL; max_idx = 0; - table_size = min(table_size * 2, - (int)ARRAY_SIZE(offs)); + table_size = min(table_size * 2, (int)ARRAY_SIZE(offs)); goto fill_table; } } else if (diff2 < 0) { @@ -1170,8 +1170,10 @@ int indx_find(struct ntfs_index *indx, struct ntfs_inode *ni, /* Read next level. */ err = indx_read(indx, ni, de_get_vbn(e), &node); - if (err) + if (err) { + /* io error? */ return err; + } /* Lookup entry that is <= to the search value. */ e = hdr_find_e(indx, &node->index->ihdr, key, key_len, ctx, @@ -1673,9 +1675,9 @@ static int indx_insert_into_root(struct ntfs_index *indx, struct ntfs_inode *ni, mi->dirty = true; /* Create alloc and bitmap attributes (if not). */ - err = run_is_empty(&indx->alloc_run) - ? indx_create_allocate(indx, ni, &new_vbn) - : indx_add_allocate(indx, ni, &new_vbn); + err = run_is_empty(&indx->alloc_run) ? + indx_create_allocate(indx, ni, &new_vbn) : + indx_add_allocate(indx, ni, &new_vbn); /* Layout of record may be changed, so rescan root. */ root = indx_get_root(indx, ni, &attr, &mi); @@ -1865,9 +1867,9 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, hdr_insert_de(indx, (*indx->cmp)(new_de + 1, le16_to_cpu(new_de->key_size), up_e + 1, le16_to_cpu(up_e->key_size), - ctx) < 0 - ? hdr2 - : hdr1, + ctx) < 0 ? + hdr2 : + hdr1, new_de, NULL, ctx); indx_mark_used(indx, ni, new_vbn >> indx->idx2vbn_bits); @@ -2337,8 +2339,8 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, err = level ? indx_insert_into_buffer(indx, ni, root, re, ctx, fnd->level - 1, - fnd) - : indx_insert_into_root(indx, ni, re, e, + fnd) : + indx_insert_into_root(indx, ni, re, e, ctx, fnd, 0); kfree(re); diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index a7ca8183b91d..6c560245eef4 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -262,8 +262,8 @@ static struct inode *ntfs_read_mft(struct inode *inode, if (!attr->nres.alloc_size) goto next_attr; - run = ino == MFT_REC_BITMAP ? &sbi->used.bitmap.run - : &ni->file.run; + run = ino == MFT_REC_BITMAP ? &sbi->used.bitmap.run : + &ni->file.run; break; case ATTR_ROOT: @@ -290,9 +290,9 @@ static struct inode *ntfs_read_mft(struct inode *inode, if (err) goto out; - mode = sb->s_root - ? (S_IFDIR | (0777 & sbi->options->fs_dmask_inv)) - : (S_IFDIR | 0777); + mode = sb->s_root ? + (S_IFDIR | (0777 & sbi->options->fs_dmask_inv)) : + (S_IFDIR | 0777); goto next_attr; case ATTR_ALLOC: @@ -449,8 +449,8 @@ static struct inode *ntfs_read_mft(struct inode *inode, ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; inode->i_op = &ntfs_file_inode_operations; inode->i_fop = &ntfs_file_operations; - inode->i_mapping->a_ops = - is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; + inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : + &ntfs_aops; if (ino != MFT_REC_MFT) init_rwsem(&ni->file.run_lock); } else if (S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || @@ -786,8 +786,8 @@ static ssize_t ntfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } ret = blockdev_direct_IO(iocb, inode, iter, - wr ? ntfs_get_block_direct_IO_W - : ntfs_get_block_direct_IO_R); + wr ? ntfs_get_block_direct_IO_W : + ntfs_get_block_direct_IO_R); if (ret > 0) end = vbo + ret; @@ -846,7 +846,7 @@ int ntfs_set_size(struct inode *inode, u64 new_size) } static int ntfs_resident_writepage(struct folio *folio, - struct writeback_control *wbc, void *data) + struct writeback_control *wbc, void *data) { struct address_space *mapping = data; struct ntfs_inode *ni = ntfs_i(mapping->host); @@ -887,8 +887,8 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, *pagep = NULL; if (is_resident(ni)) { - struct page *page = grab_cache_page_write_begin( - mapping, pos >> PAGE_SHIFT); + struct page *page = + grab_cache_page_write_begin(mapping, pos >> PAGE_SHIFT); if (!page) { err = -ENOMEM; @@ -920,9 +920,8 @@ int ntfs_write_begin(struct file *file, struct address_space *mapping, /* * ntfs_write_end - Address_space_operations::write_end. */ -int ntfs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, u32 copied, struct page *page, - void *fsdata) +int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, + u32 len, u32 copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); @@ -1605,8 +1604,8 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, } else if (S_ISREG(mode)) { inode->i_op = &ntfs_file_inode_operations; inode->i_fop = &ntfs_file_operations; - inode->i_mapping->a_ops = - is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; + inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : + &ntfs_aops; init_rwsem(&ni->file.run_lock); } else { inode->i_op = &ntfs_special_inode_operations; diff --git a/fs/ntfs3/lznt.c b/fs/ntfs3/lznt.c index 28f654561f27..61e161c7c567 100644 --- a/fs/ntfs3/lznt.c +++ b/fs/ntfs3/lznt.c @@ -296,8 +296,8 @@ static inline ssize_t decompress_chunk(u8 *unc, u8 *unc_end, const u8 *cmpr, */ struct lznt *get_lznt_ctx(int level) { - struct lznt *r = kzalloc(level ? offsetof(struct lznt, hash) - : sizeof(struct lznt), + struct lznt *r = kzalloc(level ? offsetof(struct lznt, hash) : + sizeof(struct lznt), GFP_NOFS); if (r) @@ -392,9 +392,9 @@ ssize_t decompress_lznt(const void *cmpr, size_t cmpr_size, void *unc, unc_use = err; } else { /* This chunk does not contain compressed data. */ - unc_use = unc_chunk + LZNT_CHUNK_SIZE > unc_end - ? unc_end - unc_chunk - : LZNT_CHUNK_SIZE; + unc_use = unc_chunk + LZNT_CHUNK_SIZE > unc_end ? + unc_end - unc_chunk : + LZNT_CHUNK_SIZE; if (cmpr_chunk + sizeof(chunk_hdr) + unc_use > cmpr_end) { diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 447a241fe02c..9736b1e4a0f6 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -433,8 +433,8 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, inode = ntfs_create_inode(&nop_mnt_idmap, dir, dentry, uni, mode, 0, NULL, 0, fnd); - err = IS_ERR(inode) ? PTR_ERR(inode) - : finish_open(file, dentry, ntfs_file_open); + err = IS_ERR(inode) ? PTR_ERR(inode) : + finish_open(file, dentry, ntfs_file_open); dput(d); out2: diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 15df110f561f..eb01f7e76479 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -338,7 +338,7 @@ enum ntfs_inode_mutex_lock_class { }; /* - * sturct ntfs_inode + * struct ntfs_inode * * Ntfs inode - extends linux inode. consists of one or more MFT inodes. */ @@ -699,9 +699,8 @@ int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create); int ntfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, u32 len, struct page **pagep, void **fsdata); -int ntfs_write_end(struct file *file, struct address_space *mapping, - loff_t pos, u32 len, u32 copied, struct page *page, - void *fsdata); +int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, + u32 len, u32 copied, struct page *page, void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, @@ -858,7 +857,7 @@ unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase, /* globals from xattr.c */ #ifdef CONFIG_NTFS3_FS_POSIX_ACL struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, - struct dentry *dentry, int type); + struct dentry *dentry, int type); int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 0603169ee8a0..2a281cead2bc 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -419,10 +419,9 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, struct ntfs_sb_info *sbi = mi->sbi; u32 used = le32_to_cpu(rec->used); const u16 *upcase = sbi->upcase; - int diff; /* Can we insert mi attribute? */ - if (used + asize > mi->sbi->record_size) + if (used + asize > sbi->record_size) return NULL; /* @@ -431,7 +430,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, */ attr = NULL; while ((attr = mi_enum_attr(mi, attr))) { - diff = compare_attr(attr, type, name, name_len, upcase); + int diff = compare_attr(attr, type, name, name_len, upcase); if (diff < 0) continue; @@ -442,9 +441,11 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, } if (!attr) { - tail = 8; /* Not used, just to suppress warning. */ + /* Append. */ + tail = 8; attr = Add2Ptr(rec, used - 8); } else { + /* Insert before 'attr'. */ tail = used - PtrOffset(rec, attr); } diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c index a5af71cd8d14..47612d16c027 100644 --- a/fs/ntfs3/run.c +++ b/fs/ntfs3/run.c @@ -433,9 +433,9 @@ bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, should_add_tail = Tovcn < r->len; if (should_add_tail) { - tail_lcn = r->lcn == SPARSE_LCN - ? SPARSE_LCN - : (r->lcn + Tovcn); + tail_lcn = r->lcn == SPARSE_LCN ? + SPARSE_LCN : + (r->lcn + Tovcn); tail_vcn = r->vcn + Tovcn; tail_len = r->len - Tovcn; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index d7bec9b28a42..6a412826b43d 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -39,10 +39,10 @@ * To mount large volumes as ntfs one should use large cluster size (up to 2M) * The maximum volume size in this case is 2^32 * 2^21 = 2^53 = 8P * - * ntfs limits, cluster size is 2M (2^31) + * ntfs limits, cluster size is 2M (2^21) * ----------------------------------------------------------------------------- - * | < 8P, 2^54 | < 2^32 | yes | yes | yes | yes | yes | - * | > 8P, 2^54 | > 2^32 | no | no | yes | yes | yes | + * | < 8P, 2^53 | < 2^32 | yes | yes | yes | yes | yes | + * | > 8P, 2^53 | > 2^32 | no | no | yes | yes | yes | * ----------------------------------------------------------|------------------ * */ @@ -115,9 +115,9 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...) return; /* Use static allocated buffer, if possible. */ - name = atomic_dec_and_test(&s_name_buf_cnt) - ? s_name_buf - : kmalloc(sizeof(s_name_buf), GFP_NOFS); + name = atomic_dec_and_test(&s_name_buf_cnt) ? + s_name_buf : + kmalloc(sizeof(s_name_buf), GFP_NOFS); if (name) { struct dentry *de = d_find_alias(inode); @@ -369,7 +369,8 @@ static int ntfs_fs_parse_param(struct fs_context *fc, #ifdef CONFIG_NTFS3_FS_POSIX_ACL fc->sb_flags |= SB_POSIXACL; #else - return invalf(fc, "ntfs3: Support for ACL not compiled in!"); + return invalf( + fc, "ntfs3: Support for ACL not compiled in!"); #endif else fc->sb_flags &= ~SB_POSIXACL; @@ -404,24 +405,29 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) ro_rw = sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY); if (ro_rw && (sbi->flags & NTFS_FLAGS_NEED_REPLAY)) { - errorf(fc, "ntfs3: Couldn't remount rw because journal is not replayed. Please umount/remount instead\n"); + errorf(fc, + "ntfs3: Couldn't remount rw because journal is not replayed. Please umount/remount instead\n"); return -EINVAL; } new_opts->nls = ntfs_load_nls(new_opts->nls_name); if (IS_ERR(new_opts->nls)) { new_opts->nls = NULL; - errorf(fc, "ntfs3: Cannot load iocharset %s", new_opts->nls_name); + errorf(fc, "ntfs3: Cannot load iocharset %s", + new_opts->nls_name); return -EINVAL; } if (new_opts->nls != sbi->options->nls) - return invalf(fc, "ntfs3: Cannot use different iocharset when remounting!"); + return invalf( + fc, + "ntfs3: Cannot use different iocharset when remounting!"); sync_filesystem(sb); if (ro_rw && (sbi->volume.flags & VOLUME_FLAG_DIRTY) && !new_opts->force) { - errorf(fc, "ntfs3: Volume is dirty and \"force\" flag is not set!"); + errorf(fc, + "ntfs3: Volume is dirty and \"force\" flag is not set!"); return -EINVAL; } @@ -539,10 +545,8 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root) struct ntfs_mount_options *opts = sbi->options; struct user_namespace *user_ns = seq_user_ns(m); - seq_printf(m, ",uid=%u", - from_kuid_munged(user_ns, opts->fs_uid)); - seq_printf(m, ",gid=%u", - from_kgid_munged(user_ns, opts->fs_gid)); + seq_printf(m, ",uid=%u", from_kuid_munged(user_ns, opts->fs_uid)); + seq_printf(m, ",gid=%u", from_kgid_munged(user_ns, opts->fs_gid)); if (opts->fmask) seq_printf(m, ",fmask=%04o", opts->fs_fmask_inv ^ 0xffff); if (opts->dmask) @@ -699,7 +703,7 @@ static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot) if (boot->sectors_per_clusters <= 0x80) return boot->sectors_per_clusters; if (boot->sectors_per_clusters >= 0xf4) /* limit shift to 2MB max */ - return 1U << -(s8)boot->sectors_per_clusters; + return 1U << (-(s8)boot->sectors_per_clusters); return -EINVAL; } @@ -717,6 +721,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, struct buffer_head *bh; struct MFT_REC *rec; u16 fn, ao; + u8 cluster_bits; sbi->volume.blocks = dev_size >> PAGE_SHIFT; @@ -784,7 +789,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, if (boot_sector_size != sector_size) { ntfs_warn( sb, - "Different NTFS sector size (%u) and media sector size (%u)", + "Different NTFS sector size (%u) and media sector size (%u).", boot_sector_size, sector_size); dev_size += sector_size - 1; } @@ -792,8 +797,8 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->cluster_size = boot_sector_size * sct_per_clst; sbi->cluster_bits = blksize_bits(sbi->cluster_size); - sbi->mft.lbo = mlcn << sbi->cluster_bits; - sbi->mft.lbo2 = mlcn2 << sbi->cluster_bits; + sbi->mft.lbo = mlcn << cluster_bits; + sbi->mft.lbo2 = mlcn2 << cluster_bits; /* Compare boot's cluster and sector. */ if (sbi->cluster_size < boot_sector_size) @@ -804,7 +809,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, /* No way to use ntfs_get_block in this case. */ ntfs_err( sb, - "Failed to mount 'cause NTFS's cluster size (%u) is less than media sector size (%u)", + "Failed to mount 'cause NTFS's cluster size (%u) is less than media sector size (%u).", sbi->cluster_size, sector_size); goto out; } @@ -840,18 +845,18 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, gb0 = format_size_gb(dev_size, &mb0); ntfs_warn( sb, - "RAW NTFS volume: Filesystem size %u.%02u Gb > volume size %u.%02u Gb. Mount in read-only", + "RAW NTFS volume: Filesystem size %u.%02u Gb > volume size %u.%02u Gb. Mount in read-only.", gb, mb, gb0, mb0); sb->s_flags |= SB_RDONLY; } - clusters = sbi->volume.size >> sbi->cluster_bits; + clusters = sbi->volume.size >> cluster_bits; #ifndef CONFIG_NTFS3_64BIT_CLUSTER /* 32 bits per cluster. */ if (clusters >> 32) { ntfs_notice( sb, - "NTFS %u.%02u Gb is too big to use 32 bits per cluster", + "NTFS %u.%02u Gb is too big to use 32 bits per cluster.", gb, mb); goto out; } @@ -885,17 +890,17 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->volume.blocks = sbi->volume.size >> sb->s_blocksize_bits; /* Maximum size for normal files. */ - sbi->maxbytes = (clusters << sbi->cluster_bits) - 1; + sbi->maxbytes = (clusters << cluster_bits) - 1; #ifdef CONFIG_NTFS3_64BIT_CLUSTER - if (clusters >= (1ull << (64 - sbi->cluster_bits))) + if (clusters >= (1ull << (64 - cluster_bits))) sbi->maxbytes = -1; sbi->maxbytes_sparse = -1; sb->s_maxbytes = MAX_LFS_FILESIZE; #else /* Maximum size for sparse file. */ - sbi->maxbytes_sparse = (1ull << (sbi->cluster_bits + 32)) - 1; - sb->s_maxbytes = 0xFFFFFFFFull << sbi->cluster_bits; + sbi->maxbytes_sparse = (1ull << (cluster_bits + 32)) - 1; + sb->s_maxbytes = 0xFFFFFFFFull << cluster_bits; #endif /* @@ -903,7 +908,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, * It would be nice if we are able to allocate 1/8 of * total clusters for MFT but not more then 512 MB. */ - sbi->zone_max = min_t(CLST, 0x20000000 >> sbi->cluster_bits, clusters >> 3); + sbi->zone_max = min_t(CLST, 0x20000000 >> cluster_bits, clusters >> 3); err = 0; @@ -1433,7 +1438,7 @@ static const struct fs_context_operations ntfs_context_ops = { }; /* - * ntfs_init_fs_context - Initialize spi and opts + * ntfs_init_fs_context - Initialize sbi and opts * * This will called when mount/remount. We will first initialize * options so that if remount we can use just that. @@ -1506,7 +1511,8 @@ static int __init init_ntfs_fs(void) if (IS_ENABLED(CONFIG_NTFS3_FS_POSIX_ACL)) pr_info("ntfs3: Enabled Linux POSIX ACLs support\n"); if (IS_ENABLED(CONFIG_NTFS3_64BIT_CLUSTER)) - pr_notice("ntfs3: Warning: Activated 64 bits per cluster. Windows does not support this\n"); + pr_notice( + "ntfs3: Warning: Activated 64 bits per cluster. Windows does not support this\n"); if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS)) pr_info("ntfs3: Read-only LZX/Xpress compression included\n"); @@ -1549,7 +1555,9 @@ MODULE_DESCRIPTION("ntfs3 read/write filesystem"); MODULE_INFO(behaviour, "Enabled Linux POSIX ACLs support"); #endif #ifdef CONFIG_NTFS3_64BIT_CLUSTER -MODULE_INFO(cluster, "Warning: Activated 64 bits per cluster. Windows does not support this"); +MODULE_INFO( + cluster, + "Warning: Activated 64 bits per cluster. Windows does not support this"); #endif #ifdef CONFIG_NTFS3_LZX_XPRESS MODULE_INFO(compression, "Read-only lzx/xpress compression included"); diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index d2746803f032..4ad78ceb0088 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -23,8 +23,8 @@ static inline size_t unpacked_ea_size(const struct EA_FULL *ea) { - return ea->size ? le32_to_cpu(ea->size) - : ALIGN(struct_size(ea, name, + return ea->size ? le32_to_cpu(ea->size) : + ALIGN(struct_size(ea, name, 1 + ea->name_len + le16_to_cpu(ea->elength)), 4); -- GitLab From 16b3dbfb5d5cdfb0fcb66a5065369c935500a437 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Wed, 15 Feb 2023 13:24:23 +0400 Subject: [PATCH 1378/5631] fs/ntfs3: Add missed "nocase" in ntfs_show_options Sort processing ntfs3's mount options in same order they declared. Signed-off-by: Konstantin Komarov --- fs/ntfs3/super.c | 40 +++++++++++++++++++++------------------- 1 file changed, 21 insertions(+), 19 deletions(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 6a412826b43d..521ce31d67a1 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -270,11 +270,11 @@ static const struct fs_parameter_spec ntfs_fs_parameters[] = { fsparam_flag_no("hidden", Opt_nohidden), fsparam_flag_no("hide_dot_files", Opt_hide_dot_files), fsparam_flag_no("windows_names", Opt_windows_names), - fsparam_flag_no("acl", Opt_acl), fsparam_flag_no("showmeta", Opt_showmeta), + fsparam_flag_no("acl", Opt_acl), + fsparam_string("iocharset", Opt_iocharset), fsparam_flag_no("prealloc", Opt_prealloc), fsparam_flag_no("nocase", Opt_nocase), - fsparam_string("iocharset", Opt_iocharset), {} }; @@ -364,6 +364,9 @@ static int ntfs_fs_parse_param(struct fs_context *fc, case Opt_windows_names: opts->windows_names = result.negated ? 0 : 1; break; + case Opt_showmeta: + opts->showmeta = result.negated ? 0 : 1; + break; case Opt_acl: if (!result.negated) #ifdef CONFIG_NTFS3_FS_POSIX_ACL @@ -375,9 +378,6 @@ static int ntfs_fs_parse_param(struct fs_context *fc, else fc->sb_flags &= ~SB_POSIXACL; break; - case Opt_showmeta: - opts->showmeta = result.negated ? 0 : 1; - break; case Opt_iocharset: kfree(opts->nls_name); opts->nls_name = param->string; @@ -547,34 +547,36 @@ static int ntfs_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",uid=%u", from_kuid_munged(user_ns, opts->fs_uid)); seq_printf(m, ",gid=%u", from_kgid_munged(user_ns, opts->fs_gid)); - if (opts->fmask) - seq_printf(m, ",fmask=%04o", opts->fs_fmask_inv ^ 0xffff); if (opts->dmask) seq_printf(m, ",dmask=%04o", opts->fs_dmask_inv ^ 0xffff); - if (opts->nls) - seq_printf(m, ",iocharset=%s", opts->nls->charset); - else - seq_puts(m, ",iocharset=utf8"); + if (opts->fmask) + seq_printf(m, ",fmask=%04o", opts->fs_fmask_inv ^ 0xffff); if (opts->sys_immutable) seq_puts(m, ",sys_immutable"); if (opts->discard) seq_puts(m, ",discard"); + if (opts->force) + seq_puts(m, ",force"); if (opts->sparse) seq_puts(m, ",sparse"); - if (opts->showmeta) - seq_puts(m, ",showmeta"); if (opts->nohidden) seq_puts(m, ",nohidden"); - if (opts->windows_names) - seq_puts(m, ",windows_names"); if (opts->hide_dot_files) seq_puts(m, ",hide_dot_files"); - if (opts->force) - seq_puts(m, ",force"); - if (opts->prealloc) - seq_puts(m, ",prealloc"); + if (opts->windows_names) + seq_puts(m, ",windows_names"); + if (opts->showmeta) + seq_puts(m, ",showmeta"); if (sb->s_flags & SB_POSIXACL) seq_puts(m, ",acl"); + if (opts->nls) + seq_printf(m, ",iocharset=%s", opts->nls->charset); + else + seq_puts(m, ",iocharset=utf8"); + if (opts->prealloc) + seq_puts(m, ",prealloc"); + if (opts->nocase) + seq_puts(m, ",nocase"); return 0; } -- GitLab From e43f6ec224c1b428260e161f0300afbe2e1194fe Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Wed, 15 Feb 2023 16:06:56 +0400 Subject: [PATCH 1379/5631] fs/ntfs3: Print details about mount fails Added error mesages with error codes. Minor refactoring and code formatting. Signed-off-by: Konstantin Komarov --- fs/ntfs3/frecord.c | 2 +- fs/ntfs3/fsntfs.c | 40 +++++------ fs/ntfs3/super.c | 172 +++++++++++++++++++++++++++------------------ 3 files changed, 122 insertions(+), 92 deletions(-) diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 481219f2a7cf..2bfcf1a989c9 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -3360,7 +3360,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) ni_unlock(ni); if (err) { - ntfs_err(sb, "%s r=%lx failed, %d.", hint, inode->i_ino, err); + ntfs_inode_err(inode, "%s failed, %d.", hint, err); ntfs_set_state(sbi, NTFS_DIRTY_ERROR); return err; } diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 0a82b1bf3ec2..28cc421102e5 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -223,7 +223,7 @@ int ntfs_extend_init(struct ntfs_sb_info *sbi) inode = ntfs_iget5(sb, &ref, &NAME_EXTEND); if (IS_ERR(inode)) { err = PTR_ERR(inode); - ntfs_err(sb, "Failed to load $Extend."); + ntfs_err(sb, "Failed to load $Extend (%d).", err); inode = NULL; goto out; } @@ -282,7 +282,7 @@ int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi) /* Check for 4GB. */ if (ni->vfs_inode.i_size >= 0x100000000ull) { - ntfs_err(sb, "\x24LogFile is too big"); + ntfs_err(sb, "\x24LogFile is large than 4G."); err = -EINVAL; goto out; } @@ -1863,7 +1863,7 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) inode = ntfs_iget5(sb, &ref, &NAME_SECURE); if (IS_ERR(inode)) { err = PTR_ERR(inode); - ntfs_err(sb, "Failed to load $Secure."); + ntfs_err(sb, "Failed to load $Secure (%d).", err); inode = NULL; goto out; } @@ -1874,45 +1874,43 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) attr = ni_find_attr(ni, NULL, &le, ATTR_ROOT, SDH_NAME, ARRAY_SIZE(SDH_NAME), NULL, NULL); - if (!attr) { - err = -EINVAL; - goto out; - } - - if(!(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + if (!attr || + !(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || offsetof(struct INDEX_ROOT, ihdr) + - le32_to_cpu(root_sdh->ihdr.used) > - le32_to_cpu(attr->res.data_size)) { + le32_to_cpu(root_sdh->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { + ntfs_err(sb, "$Secure::$SDH is corrupted."); err = -EINVAL; goto out; } err = indx_init(indx_sdh, sbi, attr, INDEX_MUTEX_SDH); - if (err) + if (err) { + ntfs_err(sb, "Failed to initialize $Secure::$SDH (%d).", err); goto out; + } attr = ni_find_attr(ni, attr, &le, ATTR_ROOT, SII_NAME, ARRAY_SIZE(SII_NAME), NULL, NULL); - if (!attr) { - err = -EINVAL; - goto out; - } - - if(!(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + if (!attr || + !(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || offsetof(struct INDEX_ROOT, ihdr) + - le32_to_cpu(root_sii->ihdr.used) > - le32_to_cpu(attr->res.data_size)) { + le32_to_cpu(root_sii->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { + ntfs_err(sb, "$Secure::$SII is corrupted."); err = -EINVAL; goto out; } err = indx_init(indx_sii, sbi, attr, INDEX_MUTEX_SII); - if (err) + if (err) { + ntfs_err(sb, "Failed to initialize $Secure::$SII (%d).", err); goto out; + } fnd_sii = fnd_get(); if (!fnd_sii) { diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 521ce31d67a1..e0f78b306f15 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -734,48 +734,81 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, err = -EINVAL; boot = (struct NTFS_BOOT *)bh->b_data; - if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) + if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) { + ntfs_err(sb, "Boot's signature is not NTFS."); goto out; + } /* 0x55AA is not mandaroty. Thanks Maxim Suhanov*/ /*if (0x55 != boot->boot_magic[0] || 0xAA != boot->boot_magic[1]) * goto out; */ - boot_sector_size = (u32)boot->bytes_per_sector[1] << 8; - if (boot->bytes_per_sector[0] || boot_sector_size < SECTOR_SIZE || + boot_sector_size = ((u32)boot->bytes_per_sector[1] << 8) | + boot->bytes_per_sector[0]; + if (boot_sector_size < SECTOR_SIZE || !is_power_of_2(boot_sector_size)) { + ntfs_err(sb, "Invalid bytes per sector %u.", boot_sector_size); goto out; } /* cluster size: 512, 1K, 2K, 4K, ... 2M */ sct_per_clst = true_sectors_per_clst(boot); - if ((int)sct_per_clst < 0) - goto out; - if (!is_power_of_2(sct_per_clst)) + if ((int)sct_per_clst < 0 || !is_power_of_2(sct_per_clst)) { + ntfs_err(sb, "Invalid sectors per cluster %u.", sct_per_clst); goto out; + } + + sbi->cluster_size = boot_sector_size * sct_per_clst; + sbi->cluster_bits = cluster_bits = blksize_bits(sbi->cluster_size); + sbi->cluster_mask = sbi->cluster_size - 1; + sbi->cluster_mask_inv = ~(u64)sbi->cluster_mask; mlcn = le64_to_cpu(boot->mft_clst); mlcn2 = le64_to_cpu(boot->mft2_clst); sectors = le64_to_cpu(boot->sectors_per_volume); - if (mlcn * sct_per_clst >= sectors) + if (mlcn * sct_per_clst >= sectors || mlcn2 * sct_per_clst >= sectors) { + ntfs_err( + sb, + "Start of MFT 0x%llx (0x%llx) is out of volume 0x%llx.", + mlcn, mlcn2, sectors); goto out; + } - if (mlcn2 * sct_per_clst >= sectors) - goto out; + sbi->record_size = record_size = + boot->record_size < 0 ? 1 << (-boot->record_size) : + (u32)boot->record_size << cluster_bits; + sbi->record_bits = blksize_bits(record_size); + sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes /* Check MFT record size. */ - if ((boot->record_size < 0 && - SECTOR_SIZE > (2U << (-boot->record_size))) || - (boot->record_size >= 0 && !is_power_of_2(boot->record_size))) { + if (record_size < SECTOR_SIZE || !is_power_of_2(record_size)) { + ntfs_err(sb, "Invalid bytes per MFT record %u (%d).", + record_size, boot->record_size); + goto out; + } + + if (record_size > MAXIMUM_BYTES_PER_MFT) { + ntfs_err(sb, "Unsupported bytes per MFT record %u.", + record_size); goto out; } + sbi->index_size = boot->index_size < 0 ? + 1u << (-boot->index_size) : + (u32)boot->index_size << cluster_bits; + /* Check index record size. */ - if ((boot->index_size < 0 && - SECTOR_SIZE > (2U << (-boot->index_size))) || - (boot->index_size >= 0 && !is_power_of_2(boot->index_size))) { + if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) { + ntfs_err(sb, "Invalid bytes per index %u(%d).", sbi->index_size, + boot->index_size); + goto out; + } + + if (sbi->index_size > MAXIMUM_BYTES_PER_INDEX) { + ntfs_err(sb, "Unsupported bytes per index %u.", + sbi->index_size); goto out; } @@ -796,15 +829,15 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, dev_size += sector_size - 1; } - sbi->cluster_size = boot_sector_size * sct_per_clst; - sbi->cluster_bits = blksize_bits(sbi->cluster_size); - sbi->mft.lbo = mlcn << cluster_bits; sbi->mft.lbo2 = mlcn2 << cluster_bits; /* Compare boot's cluster and sector. */ - if (sbi->cluster_size < boot_sector_size) + if (sbi->cluster_size < boot_sector_size) { + ntfs_err(sb, "Invalid bytes per cluster (%u).", + sbi->cluster_size); goto out; + } /* Compare boot's cluster and media sector. */ if (sbi->cluster_size < sector_size) { @@ -816,28 +849,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, goto out; } - sbi->cluster_mask = sbi->cluster_size - 1; - sbi->cluster_mask_inv = ~(u64)sbi->cluster_mask; - sbi->record_size = record_size = boot->record_size < 0 - ? 1 << (-boot->record_size) - : (u32)boot->record_size - << sbi->cluster_bits; - - if (record_size > MAXIMUM_BYTES_PER_MFT || record_size < SECTOR_SIZE) - goto out; - - sbi->record_bits = blksize_bits(record_size); - sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes - sbi->max_bytes_per_attr = record_size - ALIGN(MFTRECORD_FIXUP_OFFSET_1, 8) - ALIGN(((record_size >> SECTOR_SHIFT) * sizeof(short)), 8) - ALIGN(sizeof(enum ATTR_TYPE), 8); - sbi->index_size = boot->index_size < 0 - ? 1u << (-boot->index_size) - : (u32)boot->index_size << sbi->cluster_bits; - sbi->volume.ser_num = le64_to_cpu(boot->serial_num); /* Warning if RAW volume. */ @@ -928,6 +944,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) int err; struct ntfs_sb_info *sbi = sb->s_fs_info; struct block_device *bdev = sb->s_bdev; + struct ntfs_mount_options *options; struct inode *inode; struct ntfs_inode *ni; size_t i, tt, bad_len, bad_frags; @@ -942,7 +959,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.high = 0; sbi->sb = sb; - sbi->options = fc->fs_private; + sbi->options = options = fc->fs_private; fc->fs_private = NULL; sb->s_flags |= SB_NODIRATIME; sb->s_magic = 0x7366746e; // "ntfs" @@ -950,12 +967,12 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_export_op = &ntfs_export_ops; sb->s_time_gran = NTFS_TIME_GRAN; // 100 nsec sb->s_xattr = ntfs_xattr_handlers; - sb->s_d_op = sbi->options->nocase ? &ntfs_dentry_ops : NULL; + sb->s_d_op = options->nocase ? &ntfs_dentry_ops : NULL; - sbi->options->nls = ntfs_load_nls(sbi->options->nls_name); - if (IS_ERR(sbi->options->nls)) { - sbi->options->nls = NULL; - errorf(fc, "Cannot load nls %s", sbi->options->nls_name); + options->nls = ntfs_load_nls(options->nls_name); + if (IS_ERR(options->nls)) { + options->nls = NULL; + errorf(fc, "Cannot load nls %s", options->nls_name); err = -EINVAL; goto out; } @@ -980,8 +997,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_VOL); inode = ntfs_iget5(sb, &ref, &NAME_VOLUME); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $Volume."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Volume (%d).", err); goto out; } @@ -1007,13 +1024,9 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } attr = ni_find_attr(ni, attr, NULL, ATTR_VOL_INFO, NULL, 0, NULL, NULL); - if (!attr || is_attr_ext(attr)) { - err = -EINVAL; - goto put_inode_out; - } - - info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO); - if (!info) { + if (!attr || is_attr_ext(attr) || + !(info = resident_data_ex(attr, SIZEOF_ATTRIBUTE_VOLUME_INFO))) { + ntfs_err(sb, "$Volume is corrupted."); err = -EINVAL; goto put_inode_out; } @@ -1028,13 +1041,13 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_MIRR); inode = ntfs_iget5(sb, &ref, &NAME_MIRROR); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $MFTMirr."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $MFTMirr (%d).", err); goto out; } - sbi->mft.recs_mirr = - ntfs_up_cluster(sbi, inode->i_size) >> sbi->record_bits; + sbi->mft.recs_mirr = ntfs_up_cluster(sbi, inode->i_size) >> + sbi->record_bits; iput(inode); @@ -1043,8 +1056,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_LOG); inode = ntfs_iget5(sb, &ref, &NAME_LOGFILE); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load \x24LogFile."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load \x24LogFile (%d).", err); goto out; } @@ -1064,7 +1077,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto out; } } else if (sbi->volume.flags & VOLUME_FLAG_DIRTY) { - if (!sb_rdonly(sb) && !sbi->options->force) { + if (!sb_rdonly(sb) && !options->force) { ntfs_warn( sb, "volume is dirty and \"force\" flag is not set!"); @@ -1079,8 +1092,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) inode = ntfs_iget5(sb, &ref, &NAME_MFT); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $MFT."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $MFT (%d).", err); goto out; } @@ -1095,8 +1108,10 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) goto put_inode_out; err = ni_load_all_mi(ni); - if (err) + if (err) { + ntfs_err(sb, "Failed to load $MFT's subrecords (%d).", err); goto put_inode_out; + } sbi->mft.ni = ni; @@ -1105,8 +1120,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_BITMAP); inode = ntfs_iget5(sb, &ref, &NAME_BITMAP); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $Bitmap."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $Bitmap (%d).", err); goto out; } @@ -1120,20 +1135,25 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* Check bitmap boundary. */ tt = sbi->used.bitmap.nbits; if (inode->i_size < bitmap_size(tt)) { + ntfs_err(sb, "$Bitmap is corrupted."); err = -EINVAL; goto put_inode_out; } err = wnd_init(&sbi->used.bitmap, sb, tt); - if (err) + if (err) { + ntfs_err(sb, "Failed to initialize $Bitmap (%d).", err); goto put_inode_out; + } iput(inode); /* Compute the MFT zone. */ err = ntfs_refresh_zone(sbi); - if (err) + if (err) { + ntfs_err(sb, "Failed to initialize MFT zone (%d).", err); goto out; + } /* Load $BadClus. */ ref.low = cpu_to_le32(MFT_REC_BADCLUST); @@ -1178,8 +1198,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_ATTR); inode = ntfs_iget5(sb, &ref, &NAME_ATTRDEF); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $AttrDef -> %d", err); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $AttrDef (%d)", err); goto out; } @@ -1208,6 +1228,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) if (IS_ERR(page)) { err = PTR_ERR(page); + ntfs_err(sb, "Failed to read $AttrDef (%d).", err); goto put_inode_out; } memcpy(Add2Ptr(t, done), page_address(page), @@ -1215,6 +1236,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ntfs_unmap_page(page); if (!idx && ATTR_STD != t->type) { + ntfs_err(sb, "$AttrDef is corrupted."); err = -EINVAL; goto put_inode_out; } @@ -1249,13 +1271,14 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_UPCASE); inode = ntfs_iget5(sb, &ref, &NAME_UPCASE); if (IS_ERR(inode)) { - ntfs_err(sb, "Failed to load $UpCase."); err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load $UpCase (%d).", err); goto out; } if (inode->i_size != 0x10000 * sizeof(short)) { err = -EINVAL; + ntfs_err(sb, "$UpCase is corrupted."); goto put_inode_out; } @@ -1266,6 +1289,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) if (IS_ERR(page)) { err = PTR_ERR(page); + ntfs_err(sb, "Failed to read $UpCase (%d).", err); goto put_inode_out; } @@ -1291,23 +1315,31 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) if (is_ntfs3(sbi)) { /* Load $Secure. */ err = ntfs_security_init(sbi); - if (err) + if (err) { + ntfs_err(sb, "Failed to initialize $Secure (%d).", err); goto out; + } /* Load $Extend. */ err = ntfs_extend_init(sbi); - if (err) + if (err) { + ntfs_warn(sb, "Failed to initialize $Extend."); goto load_root; + } - /* Load $Extend\$Reparse. */ + /* Load $Extend/$Reparse. */ err = ntfs_reparse_init(sbi); - if (err) + if (err) { + ntfs_warn(sb, "Failed to initialize $Extend/$Reparse."); goto load_root; + } - /* Load $Extend\$ObjId. */ + /* Load $Extend/$ObjId. */ err = ntfs_objid_init(sbi); - if (err) + if (err) { + ntfs_warn(sb, "Failed to initialize $Extend/$ObjId."); goto load_root; + } } load_root: @@ -1316,8 +1348,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.seq = cpu_to_le16(MFT_REC_ROOT); inode = ntfs_iget5(sb, &ref, &NAME_ROOT); if (IS_ERR(inode) || !inode->i_op) { - ntfs_err(sb, "Failed to load root."); - err = IS_ERR(inode) ? PTR_ERR(inode) : -EINVAL; + err = PTR_ERR(inode); + ntfs_err(sb, "Failed to load root (%d).", err); goto out; } -- GitLab From 788ee1605c2e9feed39c3a749fb3e47c6e15c1b9 Mon Sep 17 00:00:00 2001 From: Konstantin Komarov Date: Mon, 20 Feb 2023 09:39:35 +0400 Subject: [PATCH 1380/5631] fs/ntfs3: Fix root inode checking Separate checking inode->i_op and inode itself. Reported-by: kernel test robot Reported-by: Dan Carpenter Link: https://lore.kernel.org/r/202302162319.bDJOuyfy-lkp@intel.com/ Signed-off-by: Konstantin Komarov --- fs/ntfs3/super.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index e0f78b306f15..5158dd31fd97 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -1347,12 +1347,21 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) ref.low = cpu_to_le32(MFT_REC_ROOT); ref.seq = cpu_to_le16(MFT_REC_ROOT); inode = ntfs_iget5(sb, &ref, &NAME_ROOT); - if (IS_ERR(inode) || !inode->i_op) { + if (IS_ERR(inode)) { err = PTR_ERR(inode); ntfs_err(sb, "Failed to load root (%d).", err); goto out; } + /* + * Final check. Looks like this case should never occurs. + */ + if (!inode->i_op) { + err = -EINVAL; + ntfs_err(sb, "Failed to load root (%d).", err); + goto put_inode_out; + } + sb->s_root = d_make_root(inode); if (!sb->s_root) { err = -ENOMEM; -- GitLab From af90d7b69c69b9b8ab91acc2ceab3706a2798373 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 16 Mar 2023 16:34:46 +0100 Subject: [PATCH 1381/5631] s390/cpum_sf: remove flag PERF_CPUM_SF_FULL_BLOCKS This flag is used to process only fully populated sampling buffers when an sampling event is stopped on a CPU. By default the last sampling buffer is also scanned for samples even if the sampling block full indicator is not set in the trailer entry of a sampling buffer page. This flag can be set via perf_event_attr::config1 field. It was never used and never documented. It is useless now. With PERF_CPUM_SF_FULL_BLOCKS: When a process is scheduled off the CPU, the sampling is stopped and the samples are copied to the perf ring buffer and marked invalid. When stopped at the last full sample buffer page (which is achieved with the PERF_CPUM_SF_FULL_BLOCKS options), the hardware sampling will resume at the first free sample entry in the current, partially filled sample buffer. Without PERF_CPUM_SF_FULL_BLOCKS (default behavior): The partially filled last sample buffer is scanned and valid samples are saved to the perf ring buffer. The valid samples are marked invalid. The sampling is resumed when the process is scheduled on this CPU. Again the hardware sampling will resume at the first free sample entry in the current, partially filled sample buffer. Now the next interrupt handler invocation scans the full sample block and saves the valid samples to the ring buffer. It omits the invalid samples at the top of the buffer. The default behavior is fully sufficient, therefore remove this feature. Signed-off-by: Thomas Richter Acked-by: Hendrik Brueckner Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/perf_event.h | 2 -- arch/s390/kernel/perf_cpum_sf.c | 14 ++------------ 2 files changed, 2 insertions(+), 14 deletions(-) diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index b9da71632827..9917e2717b2b 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -60,7 +60,6 @@ struct perf_sf_sde_regs { #define PERF_CPUM_SF_DIAG_MODE 0x0002 /* Diagnostic-sampling flag */ #define PERF_CPUM_SF_MODE_MASK (PERF_CPUM_SF_BASIC_MODE| \ PERF_CPUM_SF_DIAG_MODE) -#define PERF_CPUM_SF_FULL_BLOCKS 0x0004 /* Process full SDBs only */ #define PERF_CPUM_SF_FREQ_MODE 0x0008 /* Sampling with frequency */ #define REG_NONE 0 @@ -71,7 +70,6 @@ struct perf_sf_sde_regs { #define SAMPL_RATE(hwc) ((hwc)->event_base) #define SAMPL_FLAGS(hwc) ((hwc)->config_base) #define SAMPL_DIAG_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE) -#define SDB_FULL_BLOCKS(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS) #define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE) #define perf_arch_fetch_caller_regs(regs, __ip) do { \ diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index e7b867e2f73f..7ef72f5ff52e 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -882,10 +882,6 @@ static int __hw_perf_event_init(struct perf_event *event) SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE; } - /* Check and set other sampling flags */ - if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS) - SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS; - err = __hw_perf_event_init_rate(event, &si); if (err) goto out; @@ -1293,11 +1289,8 @@ static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t * The sampling buffer position are retrieved and saved in the TEAR_REG * register of the specified perf event. * - * Only full sample-data-blocks are processed. Specify the flash_all flag - * to also walk through partially filled sample-data-blocks. It is ignored - * if PERF_CPUM_SF_FULL_BLOCKS is set. The PERF_CPUM_SF_FULL_BLOCKS flag - * enforces the processing of full sample-data-blocks only (trailer entries - * with the block-full-indicator bit set). + * Only full sample-data-blocks are processed. Specify the flush_all flag + * to also walk through partially filled sample-data-blocks. */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { @@ -1315,9 +1308,6 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) if (SAMPL_DIAG_MODE(&event->hw)) return; - if (flush_all && SDB_FULL_BLOCKS(hwc)) - flush_all = 0; - sdbt = (unsigned long *) TEAR_REG(hwc); done = event_overflow = sampl_overflow = num_sdb = 0; while (!done) { -- GitLab From e7615c9225d7c7562d1cd95ba8cc2cbf38c3d29e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 17 Mar 2023 10:31:40 +0100 Subject: [PATCH 1382/5631] s390: enable ARCH_HAS_MEMBARRIER_SYNC_CORE s390 trivially supports the ARCH_HAS_MEMBARRIER_SYNC_CORE requirements since the used lpswe(y) instruction to return from any kernel context to user space performs CPU serialization. This is very similar to arm, arm64 and powerpc. See commit 70216e18e519 ("membarrier: Provide core serializing command, *_SYNC_CORE") for further details. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- .../features/sched/membarrier-sync-core/arch-support.txt | 4 ++-- arch/s390/Kconfig | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt index 1e51614c136e..23260ca44946 100644 --- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt +++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt @@ -5,7 +5,7 @@ # # Architecture requirements # -# * arm/arm64/powerpc +# * arm/arm64/powerpc/s390 # # Rely on implicit context synchronization as a result of exception return # when returning from IPI handler, and when returning to user-space. @@ -45,7 +45,7 @@ | parisc: | TODO | | powerpc: | ok | | riscv: | TODO | - | s390: | TODO | + | s390: | ok | | sh: | TODO | | sparc: | TODO | | um: | TODO | diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8f1c6da2ae4d..d610f911677e 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -76,6 +76,7 @@ config S390 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL -- GitLab From 85206bf95313c33a244d6ea4304b01ade95b8b05 Mon Sep 17 00:00:00 2001 From: Lizhe Date: Sun, 19 Mar 2023 12:19:41 +0800 Subject: [PATCH 1383/5631] s390/vfio-ap: remove redundant driver match function If there is no driver match function, the driver core assumes that each candidate pair (driver, device) matches, see driver_match_device(). Drop the matrix bus's match function that always returned 1 and so implements the same behaviour as when there is no match function Signed-off-by: Lizhe Reviewed-by: Tony Krowiak Link: https://lore.kernel.org/r/20230319041941.259830-1-sensor1010@163.com Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/vfio_ap_drv.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 997b524bdd2b..9341c000da41 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -59,14 +59,8 @@ static void vfio_ap_matrix_dev_release(struct device *dev) kfree(matrix_dev); } -static int matrix_bus_match(struct device *dev, struct device_driver *drv) -{ - return 1; -} - static struct bus_type matrix_bus = { .name = "matrix", - .match = &matrix_bus_match, }; static struct device_driver matrix_driver = { -- GitLab From 386af3bdb53585405c22dae58ad99b72ed5895f5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 16:01:49 +0300 Subject: [PATCH 1384/5631] device property: Add headers to the Driver Core entry in MAINTAINERS The header files (fwnode.h and property.h) are part of the device property API, which in its turn is part of driver core. Add the missed headers to the corresponding record in the MAINTAINERS database. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327130150.84114-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..b088fceaff39 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6318,7 +6318,9 @@ F: drivers/base/ F: fs/debugfs/ F: fs/sysfs/ F: include/linux/debugfs.h +F: include/linux/fwnode.h F: include/linux/kobj* +F: include/linux/property.h F: lib/kobj* DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS) -- GitLab From 579d472b379983498a6a7d9f7b1dd74c20afdc50 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 16:01:50 +0300 Subject: [PATCH 1385/5631] device property: Remove unused struct net_device forward declaration There is no users in the property.h for the struct net_device. Remove the latter for good. Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327130150.84114-2-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/property.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/property.h b/include/linux/property.h index 4a536548606b..59f452198c64 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -16,7 +16,6 @@ #include struct device; -struct net_device; enum dev_prop_type { DEV_PROP_U8, -- GitLab From 5c9a27df4eb9a402770d5547af255a765e1c10ac Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Mar 2023 18:03:19 +0200 Subject: [PATCH 1386/5631] driver core: move sysfs_dev_char_kobj out of class.h The structure sysfs_dev_char_kobj is local only to the driver core code, so move it out of the global class.h file and into the internal base.h file as no one else should be touching this symbol. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230327160319.513974-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 3 +++ include/linux/device/class.h | 1 - 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index d3e081dc4b13..2867ca4ee4ce 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -189,6 +189,9 @@ const char *device_get_devnode(const struct device *dev, umode_t *mode, extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); +/* /sys/dev/char directory */ +extern struct kobject *sysfs_dev_char_kobj; + #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) void module_add_driver(struct module *mod, struct device_driver *drv); void module_remove_driver(struct device_driver *drv); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 1dc7706cb42d..d3960733c0fa 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -81,7 +81,6 @@ struct class_dev_iter { }; extern struct kobject *sysfs_dev_block_kobj; -extern struct kobject *sysfs_dev_char_kobj; int __must_check class_register(struct class *class); void class_unregister(struct class *class); -- GitLab From 81fe523af79f50e27647f6f18ed683e379a40d29 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 19 Mar 2023 11:32:17 -0500 Subject: [PATCH 1387/5631] clk: ti: Use of_address_to_resource() Replace of_get_address() and of_translate_address() calls with single call to of_address_to_resource(). Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230319163217.226144-1-robh@kernel.org Reviewed-by: Tony Lindgren Signed-off-by: Stephen Boyd --- drivers/clk/ti/clkctrl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index f73f402ff7de..b6fce916967c 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -512,16 +512,16 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) struct clk_hw_omap *hw; struct clk *clk; struct omap_clkctrl_clk *clkctrl_clk = NULL; - const __be32 *addrp; bool legacy_naming; const char *clkctrl_name; u32 addr; int ret; char *c; u16 soc_mask = 0; + struct resource res; - addrp = of_get_address(node, 0, NULL, NULL); - addr = (u32)of_translate_address(node, addrp); + of_address_to_resource(node, 0, &res); + addr = (u32)res.start; #ifdef CONFIG_ARCH_OMAP4 if (of_machine_is_compatible("ti,omap4")) -- GitLab From 8048bb4579cfd17deb73aa0d8a02124f42ad5ff6 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 23 Mar 2023 13:14:37 +0100 Subject: [PATCH 1388/5631] MAINTAINERS: remove obsolete file entry in MIPS/LOONGSON1 ARCHITECTURE Commit c46496119ed0 ("clk: loongson1: Remove the outdated driver") removes all files matching the pattern drivers/*/*/*loongson1*, but misses to adjust the file entry for MIPS/LOONGSON1 ARCHITECTURE in MAINTAINERS. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken reference. Remove this file entry in MIPS/LOONGSON1 ARCHITECTURE. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230323121437.28239-1-lukas.bulwahn@gmail.com Acked-by: Keguang Zhang Signed-off-by: Stephen Boyd --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..1695009c1296 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14000,7 +14000,6 @@ L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/include/asm/mach-loongson32/ F: arch/mips/loongson32/ -F: drivers/*/*/*loongson1* F: drivers/*/*loongson1* MIPS/LOONGSON2EF ARCHITECTURE -- GitLab From 66a20af59e83977c0faea08f7bebe9e812aab487 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 18 Jan 2023 20:15:20 +0100 Subject: [PATCH 1389/5631] dt-bindings: clk: si521xx: Add Skyworks Si521xx I2C PCIe clock generators Add binding for Skyworks Si521xx PCIe clock generators. This binding is designed to support Si52144/Si52146/Si52147 series I2C PCIe clock generators, tested model is Si52144. It should be possible to add Si5213x series as well. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20230118191521.15544-1-marex@denx.de Signed-off-by: Stephen Boyd --- .../bindings/clock/skyworks,si521xx.yaml | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/skyworks,si521xx.yaml diff --git a/Documentation/devicetree/bindings/clock/skyworks,si521xx.yaml b/Documentation/devicetree/bindings/clock/skyworks,si521xx.yaml new file mode 100644 index 000000000000..9e35e0e51ce8 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/skyworks,si521xx.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/skyworks,si521xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Skyworks Si521xx I2C PCIe clock generators + +description: | + The Skyworks Si521xx are I2C PCIe clock generators providing + from 4 to 9 output clocks. + +maintainers: + - Marek Vasut + +properties: + compatible: + enum: + - skyworks,si52144 + - skyworks,si52146 + - skyworks,si52147 + + reg: + const: 0x6b + + '#clock-cells': + const: 1 + + clocks: + items: + - description: XTal input clock + + skyworks,out-amplitude-microvolt: + enum: [ 300000, 400000, 500000, 600000, 700000, 800000, 900000, 1000000 ] + description: Output clock signal amplitude + +required: + - compatible + - reg + - clocks + - '#clock-cells' + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + clock-generator@6b { + compatible = "skyworks,si52144"; + reg = <0x6b>; + #clock-cells = <1>; + clocks = <&ref25m>; + }; + }; + +... -- GitLab From edc12763a3a29836b23c4fc97a1207baea1d11e8 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 18 Jan 2023 20:15:21 +0100 Subject: [PATCH 1390/5631] clk: si521xx: Clock driver for Skyworks Si521xx I2C PCIe clock generators Add driver for the Skyworks Si521xx PCIe clock generators. Supported models are Si52144/Si52146/Si52147, tested model is Si52144. It should be possible to add Si5213x series as well. Signed-off-by: Marek Vasut Link: https://lore.kernel.org/r/20230118191521.15544-2-marex@denx.de [sboyd@kernel.org: Make clk_ops const] Signed-off-by: Stephen Boyd --- drivers/clk/Kconfig | 9 + drivers/clk/Makefile | 1 + drivers/clk/clk-si521xx.c | 395 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 405 insertions(+) create mode 100644 drivers/clk/clk-si521xx.c diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index b6c5bf69a2b2..4b77f3e2ba88 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -367,6 +367,15 @@ config COMMON_CLK_RS9_PCIE This driver supports the Renesas 9-series PCIe clock generator models 9FGV/9DBV/9DMV/9FGL/9DML/9QXL/9SQ. +config COMMON_CLK_SI521XX + tristate "Clock driver for SkyWorks Si521xx PCIe clock generators" + depends on I2C + depends on OF + select REGMAP_I2C + help + This driver supports the SkyWorks Si521xx PCIe clock generator + models Si52144/Si52146/Si52147. + config COMMON_CLK_VC5 tristate "Clock driver for IDT VersaClock 5,6 devices" depends on I2C diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e3ca0d058a25..5e2c225f040c 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -72,6 +72,7 @@ obj-$(CONFIG_COMMON_CLK_TPS68470) += clk-tps68470.o obj-$(CONFIG_CLK_TWL6040) += clk-twl6040.o obj-$(CONFIG_ARCH_VT8500) += clk-vt8500.o obj-$(CONFIG_COMMON_CLK_RS9_PCIE) += clk-renesas-pcie.o +obj-$(CONFIG_COMMON_CLK_SI521XX) += clk-si521xx.o obj-$(CONFIG_COMMON_CLK_VC5) += clk-versaclock5.o obj-$(CONFIG_COMMON_CLK_VC7) += clk-versaclock7.o obj-$(CONFIG_COMMON_CLK_WM831X) += clk-wm831x.o diff --git a/drivers/clk/clk-si521xx.c b/drivers/clk/clk-si521xx.c new file mode 100644 index 000000000000..ac8d4c59cd3d --- /dev/null +++ b/drivers/clk/clk-si521xx.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Skyworks Si521xx PCIe clock generator driver + * + * The following series can be supported: + * - Si52144 - 4x DIFF + * - Si52146 - 6x DIFF + * - Si52147 - 9x DIFF + * Currently tested: + * - Si52144 + * + * Copyright (C) 2022 Marek Vasut + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* OE1 and OE2 register */ +#define SI521XX_REG_OE(n) (((n) & 0x1) + 1) +#define SI521XX_REG_ID 0x3 +#define SI521XX_REG_ID_PROG GENMASK(7, 4) +#define SI521XX_REG_ID_VENDOR GENMASK(3, 0) +#define SI521XX_REG_BC 0x4 +#define SI521XX_REG_DA 0x5 +#define SI521XX_REG_DA_AMP_SEL BIT(7) +#define SI521XX_REG_DA_AMP_MASK GENMASK(6, 4) +#define SI521XX_REG_DA_AMP_MIN 300000 +#define SI521XX_REG_DA_AMP_DEFAULT 800000 +#define SI521XX_REG_DA_AMP_MAX 1000000 +#define SI521XX_REG_DA_AMP_STEP 100000 +#define SI521XX_REG_DA_AMP(UV) \ + FIELD_PREP(SI521XX_REG_DA_AMP_MASK, \ + ((UV) - SI521XX_REG_DA_AMP_MIN) / SI521XX_REG_DA_AMP_STEP) +#define SI521XX_REG_DA_UNKNOWN BIT(3) /* Always set */ + +/* Count of populated OE bits in control register ref, 1 and 2 */ +#define SI521XX_OE_MAP(cr1, cr2) (((cr2) << 8) | (cr1)) +#define SI521XX_OE_MAP_GET_OE(oe, map) (((map) >> (((oe) - 1) * 8)) & 0xff) + +#define SI521XX_DIFF_MULT 4 +#define SI521XX_DIFF_DIV 1 + +/* Supported Skyworks Si521xx models. */ +enum si521xx_model { + SI52144 = 0x44, + SI52146 = 0x46, + SI52147 = 0x47, +}; + +struct si521xx; + +struct si_clk { + struct clk_hw hw; + struct si521xx *si; + u8 reg; + u8 bit; +}; + +struct si521xx { + struct i2c_client *client; + struct regmap *regmap; + struct si_clk clk_dif[9]; + u16 chip_info; + u8 pll_amplitude; +}; + +/* + * Si521xx i2c regmap + */ +static const struct regmap_range si521xx_readable_ranges[] = { + regmap_reg_range(SI521XX_REG_OE(0), SI521XX_REG_DA), +}; + +static const struct regmap_access_table si521xx_readable_table = { + .yes_ranges = si521xx_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(si521xx_readable_ranges), +}; + +static const struct regmap_range si521xx_writeable_ranges[] = { + regmap_reg_range(SI521XX_REG_OE(0), SI521XX_REG_OE(1)), + regmap_reg_range(SI521XX_REG_BC, SI521XX_REG_DA), +}; + +static const struct regmap_access_table si521xx_writeable_table = { + .yes_ranges = si521xx_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(si521xx_writeable_ranges), +}; + +static int si521xx_regmap_i2c_write(void *context, unsigned int reg, + unsigned int val) +{ + struct i2c_client *i2c = context; + const u8 data[3] = { reg, 1, val }; + const int count = ARRAY_SIZE(data); + int ret; + + ret = i2c_master_send(i2c, data, count); + if (ret == count) + return 0; + else if (ret < 0) + return ret; + else + return -EIO; +} + +static int si521xx_regmap_i2c_read(void *context, unsigned int reg, + unsigned int *val) +{ + struct i2c_client *i2c = context; + struct i2c_msg xfer[2]; + u8 txdata = reg; + u8 rxdata[2]; + int ret; + + xfer[0].addr = i2c->addr; + xfer[0].flags = 0; + xfer[0].len = 1; + xfer[0].buf = (void *)&txdata; + + xfer[1].addr = i2c->addr; + xfer[1].flags = I2C_M_RD; + xfer[1].len = 2; + xfer[1].buf = (void *)rxdata; + + ret = i2c_transfer(i2c->adapter, xfer, 2); + if (ret < 0) + return ret; + if (ret != 2) + return -EIO; + + /* + * Byte 0 is transfer length, which is always 1 due + * to BCP register programming to 1 in si521xx_probe(), + * ignore it and use data from Byte 1. + */ + *val = rxdata[1]; + return 0; +} + +static const struct regmap_config si521xx_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .cache_type = REGCACHE_NONE, + .max_register = SI521XX_REG_DA, + .rd_table = &si521xx_readable_table, + .wr_table = &si521xx_writeable_table, + .reg_write = si521xx_regmap_i2c_write, + .reg_read = si521xx_regmap_i2c_read, +}; + +static unsigned long si521xx_diff_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + unsigned long long rate; + + rate = (unsigned long long)parent_rate * SI521XX_DIFF_MULT; + do_div(rate, SI521XX_DIFF_DIV); + return (unsigned long)rate; +} + +static long si521xx_diff_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + unsigned long best_parent; + + best_parent = (rate / SI521XX_DIFF_MULT) * SI521XX_DIFF_DIV; + *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent); + + return (*prate / SI521XX_DIFF_DIV) * SI521XX_DIFF_MULT; +} + +static int si521xx_diff_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + /* + * We must report success but we can do so unconditionally because + * si521xx_diff_round_rate returns values that ensure this call is a + * nop. + */ + + return 0; +} + +#define to_si521xx_clk(_hw) container_of(_hw, struct si_clk, hw) + +static int si521xx_diff_prepare(struct clk_hw *hw) +{ + struct si_clk *si_clk = to_si521xx_clk(hw); + struct si521xx *si = si_clk->si; + + regmap_set_bits(si->regmap, SI521XX_REG_OE(si_clk->reg), si_clk->bit); + + return 0; +} + +static void si521xx_diff_unprepare(struct clk_hw *hw) +{ + struct si_clk *si_clk = to_si521xx_clk(hw); + struct si521xx *si = si_clk->si; + + regmap_clear_bits(si->regmap, SI521XX_REG_OE(si_clk->reg), si_clk->bit); +} + +static const struct clk_ops si521xx_diff_clk_ops = { + .round_rate = si521xx_diff_round_rate, + .set_rate = si521xx_diff_set_rate, + .recalc_rate = si521xx_diff_recalc_rate, + .prepare = si521xx_diff_prepare, + .unprepare = si521xx_diff_unprepare, +}; + +static int si521xx_get_common_config(struct si521xx *si) +{ + struct i2c_client *client = si->client; + struct device_node *np = client->dev.of_node; + unsigned int amp; + int ret; + + /* Set defaults */ + si->pll_amplitude = SI521XX_REG_DA_AMP(SI521XX_REG_DA_AMP_DEFAULT); + + /* Output clock amplitude */ + ret = of_property_read_u32(np, "skyworks,out-amplitude-microvolt", + &); + if (!ret) { + if (amp < SI521XX_REG_DA_AMP_MIN || amp > SI521XX_REG_DA_AMP_MAX || + amp % SI521XX_REG_DA_AMP_STEP) { + return dev_err_probe(&client->dev, -EINVAL, + "Invalid skyworks,out-amplitude-microvolt value\n"); + } + si->pll_amplitude = SI521XX_REG_DA_AMP(amp); + } + + return 0; +} + +static void si521xx_update_config(struct si521xx *si) +{ + /* If amplitude is non-default, update it. */ + if (si->pll_amplitude == SI521XX_REG_DA_AMP(SI521XX_REG_DA_AMP_DEFAULT)) + return; + + regmap_update_bits(si->regmap, SI521XX_REG_DA, + SI521XX_REG_DA_AMP_MASK, si->pll_amplitude); +} + +static void si521xx_diff_idx_to_reg_bit(const u16 chip_info, const int idx, + struct si_clk *clk) +{ + unsigned long mask; + int oe, b, ctr = 0; + + for (oe = 1; oe <= 2; oe++) { + mask = bitrev8(SI521XX_OE_MAP_GET_OE(oe, chip_info)); + for_each_set_bit(b, &mask, 8) { + if (ctr++ != idx) + continue; + clk->reg = SI521XX_REG_OE(oe); + clk->bit = 7 - b; + return; + } + } +} + +static struct clk_hw * +si521xx_of_clk_get(struct of_phandle_args *clkspec, void *data) +{ + struct si521xx *si = data; + unsigned int idx = clkspec->args[0]; + + return &si->clk_dif[idx].hw; +} + +static int si521xx_probe(struct i2c_client *client) +{ + const u16 chip_info = (u16)(uintptr_t)device_get_match_data(&client->dev); + const struct clk_parent_data clk_parent_data = { .index = 0 }; + struct si521xx *si; + unsigned char name[6] = "DIFF0"; + struct clk_init_data init = {}; + int i, ret; + + if (!chip_info) + return -EINVAL; + + si = devm_kzalloc(&client->dev, sizeof(*si), GFP_KERNEL); + if (!si) + return -ENOMEM; + + i2c_set_clientdata(client, si); + si->client = client; + + /* Fetch common configuration from DT (if specified) */ + ret = si521xx_get_common_config(si); + if (ret) + return ret; + + si->regmap = devm_regmap_init(&client->dev, NULL, client, + &si521xx_regmap_config); + if (IS_ERR(si->regmap)) + return dev_err_probe(&client->dev, PTR_ERR(si->regmap), + "Failed to allocate register map\n"); + + /* Always read back 1 Byte via I2C */ + ret = regmap_write(si->regmap, SI521XX_REG_BC, 1); + if (ret < 0) + return ret; + + /* Register clock */ + for (i = 0; i < hweight16(chip_info); i++) { + memset(&init, 0, sizeof(init)); + snprintf(name, 6, "DIFF%d", i); + init.name = name; + init.ops = &si521xx_diff_clk_ops; + init.parent_data = &clk_parent_data; + init.num_parents = 1; + init.flags = CLK_SET_RATE_PARENT; + + si->clk_dif[i].hw.init = &init; + si->clk_dif[i].si = si; + + si521xx_diff_idx_to_reg_bit(chip_info, i, &si->clk_dif[i]); + + ret = devm_clk_hw_register(&client->dev, &si->clk_dif[i].hw); + if (ret) + return ret; + } + + ret = devm_of_clk_add_hw_provider(&client->dev, si521xx_of_clk_get, si); + if (!ret) + si521xx_update_config(si); + + return ret; +} + +static int __maybe_unused si521xx_suspend(struct device *dev) +{ + struct si521xx *si = dev_get_drvdata(dev); + + regcache_cache_only(si->regmap, true); + regcache_mark_dirty(si->regmap); + + return 0; +} + +static int __maybe_unused si521xx_resume(struct device *dev) +{ + struct si521xx *si = dev_get_drvdata(dev); + int ret; + + regcache_cache_only(si->regmap, false); + ret = regcache_sync(si->regmap); + if (ret) + dev_err(dev, "Failed to restore register map: %d\n", ret); + return ret; +} + +static const struct i2c_device_id si521xx_id[] = { + { "si52144", .driver_data = SI521XX_OE_MAP(0x5, 0xc0) }, + { "si52146", .driver_data = SI521XX_OE_MAP(0x15, 0xe0) }, + { "si52147", .driver_data = SI521XX_OE_MAP(0x17, 0xf8) }, + { } +}; +MODULE_DEVICE_TABLE(i2c, si521xx_id); + +static const struct of_device_id clk_si521xx_of_match[] = { + { .compatible = "skyworks,si52144", .data = (void *)SI521XX_OE_MAP(0x5, 0xc0) }, + { .compatible = "skyworks,si52146", .data = (void *)SI521XX_OE_MAP(0x15, 0xe0) }, + { .compatible = "skyworks,si52147", .data = (void *)SI521XX_OE_MAP(0x15, 0xf8) }, + { } +}; +MODULE_DEVICE_TABLE(of, clk_si521xx_of_match); + +static SIMPLE_DEV_PM_OPS(si521xx_pm_ops, si521xx_suspend, si521xx_resume); + +static struct i2c_driver si521xx_driver = { + .driver = { + .name = "clk-si521xx", + .pm = &si521xx_pm_ops, + .of_match_table = clk_si521xx_of_match, + }, + .probe_new = si521xx_probe, + .id_table = si521xx_id, +}; +module_i2c_driver(si521xx_driver); + +MODULE_AUTHOR("Marek Vasut "); +MODULE_DESCRIPTION("Skyworks Si521xx PCIe clock generator driver"); +MODULE_LICENSE("GPL"); -- GitLab From da751726ff2ad2322d81316ebf6aadb22dfad0d8 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 10 Mar 2023 08:55:32 +0100 Subject: [PATCH 1391/5631] clk: rs9: Check for vendor/device ID This is in preparation to support additional devices which have different IDs as well as a slightly different register layout. Signed-off-by: Alexander Stein Reviewed-by: Marek Vasut Link: https://lore.kernel.org/r/20230310075535.3476580-1-alexander.stein@ew.tq-group.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-renesas-pcie.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index f91f30560820..3873c52ad3b0 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -45,6 +45,13 @@ #define RS9_REG_DID 0x6 #define RS9_REG_BCP 0x7 +#define RS9_REG_VID_IDT 0x01 + +#define RS9_REG_DID_TYPE_FGV (0x0 << RS9_REG_DID_TYPE_SHIFT) +#define RS9_REG_DID_TYPE_DBV (0x1 << RS9_REG_DID_TYPE_SHIFT) +#define RS9_REG_DID_TYPE_DMV (0x2 << RS9_REG_DID_TYPE_SHIFT) +#define RS9_REG_DID_TYPE_SHIFT 0x6 + /* Supported Renesas 9-series models. */ enum rs9_model { RENESAS_9FGV0241, @@ -54,6 +61,7 @@ enum rs9_model { struct rs9_chip_info { const enum rs9_model model; unsigned int num_clks; + u8 did; }; struct rs9_driver_data { @@ -269,6 +277,7 @@ static int rs9_probe(struct i2c_client *client) { unsigned char name[5] = "DIF0"; struct rs9_driver_data *rs9; + unsigned int vid, did; struct clk_hw *hw; int i, ret; @@ -305,6 +314,20 @@ static int rs9_probe(struct i2c_client *client) if (ret < 0) return ret; + ret = regmap_read(rs9->regmap, RS9_REG_VID, &vid); + if (ret < 0) + return ret; + + ret = regmap_read(rs9->regmap, RS9_REG_DID, &did); + if (ret < 0) + return ret; + + if (vid != RS9_REG_VID_IDT || did != rs9->chip_info->did) + return dev_err_probe(&client->dev, -ENODEV, + "Incorrect VID/DID: %#02x, %#02x. Expected %#02x, %#02x\n", + vid, did, RS9_REG_VID_IDT, + rs9->chip_info->did); + /* Register clock */ for (i = 0; i < rs9->chip_info->num_clks; i++) { snprintf(name, 5, "DIF%d", i); @@ -348,6 +371,7 @@ static int __maybe_unused rs9_resume(struct device *dev) static const struct rs9_chip_info renesas_9fgv0241_info = { .model = RENESAS_9FGV0241, .num_clks = 2, + .did = RS9_REG_DID_TYPE_FGV | 0x02, }; static const struct i2c_device_id rs9_id[] = { -- GitLab From 51f2be462f70d9c3ef06f6028c21ac8ca00fed1d Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 10 Mar 2023 08:55:33 +0100 Subject: [PATCH 1392/5631] dt-bindings: clk: rs9: Add 9FGV0441 This is a 4-channel variant of 9FGV series. Signed-off-by: Alexander Stein Acked-by: Krzysztof Kozlowski Reviewed-by: Marek Vasut Link: https://lore.kernel.org/r/20230310075535.3476580-2-alexander.stein@ew.tq-group.com Signed-off-by: Stephen Boyd --- .../devicetree/bindings/clock/renesas,9series.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/clock/renesas,9series.yaml b/Documentation/devicetree/bindings/clock/renesas,9series.yaml index 6b6cec3fba52..3afdebdb52ad 100644 --- a/Documentation/devicetree/bindings/clock/renesas,9series.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,9series.yaml @@ -16,6 +16,11 @@ description: | - 9FGV0241: 0 -- DIF0 1 -- DIF1 + - 9FGV0441: + 0 -- DIF0 + 1 -- DIF1 + 2 -- DIF2 + 3 -- DIF3 maintainers: - Marek Vasut @@ -24,6 +29,7 @@ properties: compatible: enum: - renesas,9fgv0241 + - renesas,9fgv0441 reg: description: I2C device address -- GitLab From 603df193ec5174ff81c32cf1a78b7819ce984b8c Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 10 Mar 2023 08:55:34 +0100 Subject: [PATCH 1393/5631] clk: rs9: Support device specific dif bit calculation The calculation DIFx is BIT(n) +1 is only true for 9FGV0241. With additional devices this is getting more complicated. Support a base bit for the DIF calculation, currently only devices with consecutive bits are supported, e.g. the 6-channel device needs additional logic. Signed-off-by: Alexander Stein Reviewed-by: Marek Vasut Link: https://lore.kernel.org/r/20230310075535.3476580-3-alexander.stein@ew.tq-group.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-renesas-pcie.c | 32 +++++++++++++++++++------------- 1 file changed, 19 insertions(+), 13 deletions(-) diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 3873c52ad3b0..0036bd18c559 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -18,7 +18,6 @@ #include #define RS9_REG_OE 0x0 -#define RS9_REG_OE_DIF_OE(n) BIT((n) + 1) #define RS9_REG_SS 0x1 #define RS9_REG_SS_AMP_0V6 0x0 #define RS9_REG_SS_AMP_0V7 0x1 @@ -31,9 +30,6 @@ #define RS9_REG_SS_SSC_MASK (3 << 3) #define RS9_REG_SS_SSC_LOCK BIT(5) #define RS9_REG_SR 0x2 -#define RS9_REG_SR_2V0_DIF(n) 0 -#define RS9_REG_SR_3V0_DIF(n) BIT((n) + 1) -#define RS9_REG_SR_DIF_MASK(n) BIT((n) + 1) #define RS9_REG_REF 0x3 #define RS9_REG_REF_OE BIT(4) #define RS9_REG_REF_OD BIT(5) @@ -159,17 +155,27 @@ static const struct regmap_config rs9_regmap_config = { .reg_read = rs9_regmap_i2c_read, }; +static u8 rs9_calc_dif(const struct rs9_driver_data *rs9, int idx) +{ + enum rs9_model model = rs9->chip_info->model; + + if (model == RENESAS_9FGV0241) + return BIT(idx) + 1; + + return 0; +} + static int rs9_get_output_config(struct rs9_driver_data *rs9, int idx) { struct i2c_client *client = rs9->client; + u8 dif = rs9_calc_dif(rs9, idx); unsigned char name[5] = "DIF0"; struct device_node *np; int ret; u32 sr; /* Set defaults */ - rs9->clk_dif_sr &= ~RS9_REG_SR_DIF_MASK(idx); - rs9->clk_dif_sr |= RS9_REG_SR_3V0_DIF(idx); + rs9->clk_dif_sr |= dif; snprintf(name, 5, "DIF%d", idx); np = of_get_child_by_name(client->dev.of_node, name); @@ -181,11 +187,9 @@ static int rs9_get_output_config(struct rs9_driver_data *rs9, int idx) of_node_put(np); if (!ret) { if (sr == 2000000) { /* 2V/ns */ - rs9->clk_dif_sr &= ~RS9_REG_SR_DIF_MASK(idx); - rs9->clk_dif_sr |= RS9_REG_SR_2V0_DIF(idx); + rs9->clk_dif_sr &= ~dif; } else if (sr == 3000000) { /* 3V/ns (default) */ - rs9->clk_dif_sr &= ~RS9_REG_SR_DIF_MASK(idx); - rs9->clk_dif_sr |= RS9_REG_SR_3V0_DIF(idx); + rs9->clk_dif_sr |= dif; } else ret = dev_err_probe(&client->dev, -EINVAL, "Invalid renesas,slew-rate value\n"); @@ -256,11 +260,13 @@ static void rs9_update_config(struct rs9_driver_data *rs9) } for (i = 0; i < rs9->chip_info->num_clks; i++) { - if (rs9->clk_dif_sr & RS9_REG_SR_3V0_DIF(i)) + u8 dif = rs9_calc_dif(rs9, i); + + if (rs9->clk_dif_sr & dif) continue; - regmap_update_bits(rs9->regmap, RS9_REG_SR, RS9_REG_SR_3V0_DIF(i), - rs9->clk_dif_sr & RS9_REG_SR_3V0_DIF(i)); + regmap_update_bits(rs9->regmap, RS9_REG_SR, dif, + rs9->clk_dif_sr & dif); } } -- GitLab From e44fdd114cc3c872aa5157c6b3a190bcf92a9ffb Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Fri, 10 Mar 2023 08:55:35 +0100 Subject: [PATCH 1394/5631] clk: rs9: Add support for 9FGV0441 This model is similar to 9FGV0241, but the DIFx bits start at bit 0. Signed-off-by: Alexander Stein Reviewed-by: Marek Vasut Link: https://lore.kernel.org/r/20230310075535.3476580-4-alexander.stein@ew.tq-group.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-renesas-pcie.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 0036bd18c559..6799fb0fa2d3 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -6,6 +6,7 @@ * - 9FGV/9DBV/9DMV/9FGL/9DML/9QXL/9SQ * Currently supported: * - 9FGV0241 + * - 9FGV0441 * * Copyright (C) 2022 Marek Vasut */ @@ -51,6 +52,7 @@ /* Supported Renesas 9-series models. */ enum rs9_model { RENESAS_9FGV0241, + RENESAS_9FGV0441, }; /* Structure to describe features of a particular 9-series model */ @@ -64,7 +66,7 @@ struct rs9_driver_data { struct i2c_client *client; struct regmap *regmap; const struct rs9_chip_info *chip_info; - struct clk_hw *clk_dif[2]; + struct clk_hw *clk_dif[4]; u8 pll_amplitude; u8 pll_ssc; u8 clk_dif_sr; @@ -161,6 +163,8 @@ static u8 rs9_calc_dif(const struct rs9_driver_data *rs9, int idx) if (model == RENESAS_9FGV0241) return BIT(idx) + 1; + else if (model == RENESAS_9FGV0441) + return BIT(idx); return 0; } @@ -380,14 +384,22 @@ static const struct rs9_chip_info renesas_9fgv0241_info = { .did = RS9_REG_DID_TYPE_FGV | 0x02, }; +static const struct rs9_chip_info renesas_9fgv0441_info = { + .model = RENESAS_9FGV0441, + .num_clks = 4, + .did = RS9_REG_DID_TYPE_FGV | 0x04, +}; + static const struct i2c_device_id rs9_id[] = { { "9fgv0241", .driver_data = RENESAS_9FGV0241 }, + { "9fgv0441", .driver_data = RENESAS_9FGV0441 }, { } }; MODULE_DEVICE_TABLE(i2c, rs9_id); static const struct of_device_id clk_rs9_of_match[] = { { .compatible = "renesas,9fgv0241", .data = &renesas_9fgv0241_info }, + { .compatible = "renesas,9fgv0441", .data = &renesas_9fgv0441_info }, { } }; MODULE_DEVICE_TABLE(of, clk_rs9_of_match); -- GitLab From 57e3bbd2cb8f98dfd78298998d42d6c4cd414083 Mon Sep 17 00:00:00 2001 From: Shubhrajyoti Datta Date: Fri, 24 Mar 2023 16:19:58 +0530 Subject: [PATCH 1395/5631] clk: zynqmp: pll: Remove the limit The range is taken care in the zynqmp_pll_round_rate. Remove the rate range in the zynqmp_clk_register_pll() to prevent the early truncation of the frequencies and also allow multiple combinations of child and parent to get more accurate rates. Signed-off-by: Shubhrajyoti Datta Link: https://lore.kernel.org/r/20230324104958.25099-1-shubhrajyoti.datta@amd.com Signed-off-by: Stephen Boyd --- drivers/clk/zynqmp/pll.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/zynqmp/pll.c b/drivers/clk/zynqmp/pll.c index 0d3e1377b092..7411a7fd50ac 100644 --- a/drivers/clk/zynqmp/pll.c +++ b/drivers/clk/zynqmp/pll.c @@ -341,7 +341,5 @@ struct clk_hw *zynqmp_clk_register_pll(const char *name, u32 clk_id, return ERR_PTR(ret); } - clk_hw_set_rate_range(hw, PS_PLL_VCO_MIN, PS_PLL_VCO_MAX); - return hw; } -- GitLab From 595c88cda65d30c6b36277c232193295a45406dc Mon Sep 17 00:00:00 2001 From: Shubhrajyoti Datta Date: Mon, 27 Mar 2023 11:56:37 +0530 Subject: [PATCH 1396/5631] clocking-wizard: Support higher frequency accuracy Change the multipliers and divisors to support a higher frequency accuracy if there is only one output. Currently only O is changed now we are changing M, D and O. For multiple output case the earlier behavior is retained. Signed-off-by: Shubhrajyoti Datta Link: https://lore.kernel.org/r/20230327062637.22237-1-shubhrajyoti.datta@amd.com Signed-off-by: Stephen Boyd --- drivers/clk/xilinx/clk-xlnx-clock-wizard.c | 228 ++++++++++++++++++--- 1 file changed, 204 insertions(+), 24 deletions(-) diff --git a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c index eb1dfe7ecc1b..b7591ae019e7 100644 --- a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c +++ b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c @@ -8,12 +8,14 @@ * */ +#include #include #include #include #include #include #include +#include #include #include #include @@ -37,6 +39,7 @@ #define WZRD_CLKOUT_DIVIDE_MASK (0xff << WZRD_DIVCLK_DIVIDE_SHIFT) #define WZRD_CLKOUT_FRAC_SHIFT 8 #define WZRD_CLKOUT_FRAC_MASK 0x3ff +#define WZRD_CLKOUT0_FRAC_MASK GENMASK(17, 8) #define WZRD_DR_MAX_INT_DIV_VALUE 255 #define WZRD_DR_STATUS_REG_OFFSET 0x04 @@ -49,6 +52,22 @@ #define WZRD_USEC_POLL 10 #define WZRD_TIMEOUT_POLL 1000 + +/* Divider limits, from UG572 Table 3-4 for Ultrascale+ */ +#define DIV_O 0x01 +#define DIV_ALL 0x03 + +#define WZRD_M_MIN 2 +#define WZRD_M_MAX 128 +#define WZRD_D_MIN 1 +#define WZRD_D_MAX 106 +#define WZRD_VCO_MIN 800000000 +#define WZRD_VCO_MAX 1600000000 +#define WZRD_O_MIN 1 +#define WZRD_O_MAX 128 +#define WZRD_MIN_ERR 20000 +#define WZRD_FRAC_POINTS 1000 + /* Get the mask from width */ #define div_mask(width) ((1 << (width)) - 1) @@ -97,6 +116,9 @@ struct clk_wzrd { * @width: width of the divider bit field * @flags: clk_wzrd divider flags * @table: array of value/divider pairs, last entry should have div = 0 + * @m: value of the multiplier + * @d: value of the common divider + * @o: value of the leaf divider * @lock: register lock */ struct clk_wzrd_divider { @@ -107,6 +129,9 @@ struct clk_wzrd_divider { u8 width; u8 flags; const struct clk_div_table *table; + u32 m; + u32 d; + u32 o; spinlock_t *lock; /* divider lock */ }; @@ -198,12 +223,155 @@ static long clk_wzrd_round_rate(struct clk_hw *hw, unsigned long rate, return *prate / div; } +static int clk_wzrd_get_divisors(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + unsigned long vco_freq, freq, diff; + u32 m, d, o; + + for (m = WZRD_M_MIN; m <= WZRD_M_MAX; m++) { + for (d = WZRD_D_MIN; d <= WZRD_D_MAX; d++) { + vco_freq = DIV_ROUND_CLOSEST((parent_rate * m), d); + if (vco_freq >= WZRD_VCO_MIN && vco_freq <= WZRD_VCO_MAX) { + for (o = WZRD_O_MIN; o <= WZRD_O_MAX; o++) { + freq = DIV_ROUND_CLOSEST_ULL(vco_freq, o); + diff = abs(freq - rate); + + if (diff < WZRD_MIN_ERR) { + divider->m = m; + divider->d = d; + divider->o = o; + return 0; + } + } + } + } + } + return -EBUSY; +} + +static int clk_wzrd_dynamic_all_nolock(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + unsigned long vco_freq, rate_div, clockout0_div; + u32 reg, pre, value, f; + int err; + + err = clk_wzrd_get_divisors(hw, rate, parent_rate); + if (err) + return err; + + vco_freq = DIV_ROUND_CLOSEST(parent_rate * divider->m, divider->d); + rate_div = DIV_ROUND_CLOSEST_ULL((vco_freq * WZRD_FRAC_POINTS), rate); + + clockout0_div = div_u64(rate_div, WZRD_FRAC_POINTS); + + pre = DIV_ROUND_CLOSEST_ULL(vco_freq * WZRD_FRAC_POINTS, rate); + f = (pre - (clockout0_div * WZRD_FRAC_POINTS)); + f &= WZRD_CLKOUT_FRAC_MASK; + + reg = FIELD_PREP(WZRD_CLKOUT_DIVIDE_MASK, clockout0_div) | + FIELD_PREP(WZRD_CLKOUT0_FRAC_MASK, f); + + writel(reg, divider->base + WZRD_CLK_CFG_REG(2)); + /* Set divisor and clear phase offset */ + reg = FIELD_PREP(WZRD_CLKFBOUT_MULT_MASK, divider->m) | + FIELD_PREP(WZRD_DIVCLK_DIVIDE_MASK, divider->d); + writel(reg, divider->base + WZRD_CLK_CFG_REG(0)); + writel(divider->o, divider->base + WZRD_CLK_CFG_REG(2)); + writel(0, divider->base + WZRD_CLK_CFG_REG(3)); + /* Check status register */ + err = readl_poll_timeout(divider->base + WZRD_DR_STATUS_REG_OFFSET, value, + value & WZRD_DR_LOCK_BIT_MASK, + WZRD_USEC_POLL, WZRD_TIMEOUT_POLL); + if (err) + return -ETIMEDOUT; + + /* Initiate reconfiguration */ + writel(WZRD_DR_BEGIN_DYNA_RECONF, + divider->base + WZRD_DR_INIT_REG_OFFSET); + + /* Check status register */ + return readl_poll_timeout(divider->base + WZRD_DR_STATUS_REG_OFFSET, value, + value & WZRD_DR_LOCK_BIT_MASK, + WZRD_USEC_POLL, WZRD_TIMEOUT_POLL); +} + +static int clk_wzrd_dynamic_all(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + unsigned long flags = 0; + int ret; + + spin_lock_irqsave(divider->lock, flags); + + ret = clk_wzrd_dynamic_all_nolock(hw, rate, parent_rate); + + spin_unlock_irqrestore(divider->lock, flags); + + return ret; +} + +static unsigned long clk_wzrd_recalc_rate_all(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + u32 m, d, o, div, reg, f; + + reg = readl(divider->base + WZRD_CLK_CFG_REG(0)); + d = FIELD_GET(WZRD_DIVCLK_DIVIDE_MASK, reg); + m = FIELD_GET(WZRD_CLKFBOUT_MULT_MASK, reg); + reg = readl(divider->base + WZRD_CLK_CFG_REG(2)); + o = FIELD_GET(WZRD_DIVCLK_DIVIDE_MASK, reg); + f = FIELD_GET(WZRD_CLKOUT0_FRAC_MASK, reg); + + div = DIV_ROUND_CLOSEST(d * (WZRD_FRAC_POINTS * o + f), WZRD_FRAC_POINTS); + return divider_recalc_rate(hw, parent_rate * m, div, divider->table, + divider->flags, divider->width); +} + +static long clk_wzrd_round_rate_all(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + struct clk_wzrd_divider *divider = to_clk_wzrd_divider(hw); + unsigned long int_freq; + u32 m, d, o, div, f; + int err; + + err = clk_wzrd_get_divisors(hw, rate, *prate); + if (err) + return err; + + m = divider->m; + d = divider->d; + o = divider->o; + + div = d * o; + int_freq = divider_recalc_rate(hw, *prate * m, div, divider->table, + divider->flags, divider->width); + + if (rate > int_freq) { + f = DIV_ROUND_CLOSEST_ULL(rate * WZRD_FRAC_POINTS, int_freq); + rate = DIV_ROUND_CLOSEST(int_freq * f, WZRD_FRAC_POINTS); + } + return rate; +} + static const struct clk_ops clk_wzrd_clk_divider_ops = { .round_rate = clk_wzrd_round_rate, .set_rate = clk_wzrd_dynamic_reconfig, .recalc_rate = clk_wzrd_recalc_rate, }; +static const struct clk_ops clk_wzrd_clk_div_all_ops = { + .round_rate = clk_wzrd_round_rate_all, + .set_rate = clk_wzrd_dynamic_all, + .recalc_rate = clk_wzrd_recalc_rate_all, +}; + static unsigned long clk_wzrd_recalc_ratef(struct clk_hw *hw, unsigned long parent_rate) { @@ -280,7 +448,7 @@ static struct clk *clk_wzrd_register_divf(struct device *dev, void __iomem *base, u16 offset, u8 shift, u8 width, u8 clk_divider_flags, - const struct clk_div_table *table, + u32 div_type, spinlock_t *lock) { struct clk_wzrd_divider *div; @@ -307,7 +475,6 @@ static struct clk *clk_wzrd_register_divf(struct device *dev, div->flags = clk_divider_flags; div->lock = lock; div->hw.init = &init; - div->table = table; hw = &div->hw; ret = devm_clk_hw_register(dev, hw); @@ -324,7 +491,7 @@ static struct clk *clk_wzrd_register_divider(struct device *dev, void __iomem *base, u16 offset, u8 shift, u8 width, u8 clk_divider_flags, - const struct clk_div_table *table, + u32 div_type, spinlock_t *lock) { struct clk_wzrd_divider *div; @@ -337,7 +504,12 @@ static struct clk *clk_wzrd_register_divider(struct device *dev, return ERR_PTR(-ENOMEM); init.name = name; - init.ops = &clk_wzrd_clk_divider_ops; + if (clk_divider_flags & CLK_DIVIDER_READ_ONLY) + init.ops = &clk_divider_ro_ops; + else if (div_type == DIV_O) + init.ops = &clk_wzrd_clk_divider_ops; + else + init.ops = &clk_wzrd_clk_div_all_ops; init.flags = flags; init.parent_names = &parent_name; init.num_parents = 1; @@ -349,7 +521,6 @@ static struct clk *clk_wzrd_register_divider(struct device *dev, div->flags = clk_divider_flags; div->lock = lock; div->hw.init = &init; - div->table = table; hw = &div->hw; ret = devm_clk_hw_register(dev, hw); @@ -425,6 +596,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) const char *clk_name; void __iomem *ctrl_reg; struct clk_wzrd *clk_wzrd; + const char *clkout_name; struct device_node *np = pdev->dev.of_node; int nr_outputs; unsigned long flags = 0; @@ -469,6 +641,26 @@ static int clk_wzrd_probe(struct platform_device *pdev) goto err_disable_clk; } + ret = of_property_read_u32(np, "xlnx,nr-outputs", &nr_outputs); + if (ret || nr_outputs > WZRD_NUM_OUTPUTS) { + ret = -EINVAL; + goto err_disable_clk; + } + + clkout_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_out0", dev_name(&pdev->dev)); + if (nr_outputs == 1) { + clk_wzrd->clkout[0] = clk_wzrd_register_divider + (&pdev->dev, clkout_name, + __clk_get_name(clk_wzrd->clk_in1), 0, + clk_wzrd->base, WZRD_CLK_CFG_REG(3), + WZRD_CLKOUT_DIVIDE_SHIFT, + WZRD_CLKOUT_DIVIDE_WIDTH, + CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, + DIV_ALL, &clkwzrd_lock); + + goto out; + } + reg = readl(clk_wzrd->base + WZRD_CLK_CFG_REG(0)); reg_f = reg & WZRD_CLKFBOUT_FRAC_MASK; reg_f = reg_f >> WZRD_CLKFBOUT_FRAC_SHIFT; @@ -476,20 +668,11 @@ static int clk_wzrd_probe(struct platform_device *pdev) reg = reg & WZRD_CLKFBOUT_MULT_MASK; reg = reg >> WZRD_CLKFBOUT_MULT_SHIFT; mult = (reg * 1000) + reg_f; - clk_name = kasprintf(GFP_KERNEL, "%s_mul", dev_name(&pdev->dev)); + clk_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_mul", dev_name(&pdev->dev)); if (!clk_name) { ret = -ENOMEM; goto err_disable_clk; } - - ret = of_property_read_u32(np, "xlnx,nr-outputs", &nr_outputs); - if (ret || nr_outputs > WZRD_NUM_OUTPUTS) { - ret = -EINVAL; - goto err_disable_clk; - } - if (nr_outputs == 1) - flags = CLK_SET_RATE_PARENT; - clk_wzrd->clks_internal[wzrd_clk_mul] = clk_register_fixed_factor (&pdev->dev, clk_name, __clk_get_name(clk_wzrd->clk_in1), @@ -500,7 +683,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) goto err_disable_clk; } - clk_name = kasprintf(GFP_KERNEL, "%s_mul_div", dev_name(&pdev->dev)); + clk_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s_mul_div", dev_name(&pdev->dev)); if (!clk_name) { ret = -ENOMEM; goto err_rm_int_clk; @@ -521,9 +704,8 @@ static int clk_wzrd_probe(struct platform_device *pdev) /* register div per output */ for (i = nr_outputs - 1; i >= 0 ; i--) { - const char *clkout_name; - - clkout_name = kasprintf(GFP_KERNEL, "%s_out%d", dev_name(&pdev->dev), i); + clkout_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "%s_out%d", dev_name(&pdev->dev), i); if (!clkout_name) { ret = -ENOMEM; goto err_rm_int_clk; @@ -537,7 +719,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) WZRD_CLKOUT_DIVIDE_SHIFT, WZRD_CLKOUT_DIVIDE_WIDTH, CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, - NULL, &clkwzrd_lock); + DIV_O, &clkwzrd_lock); else clk_wzrd->clkout[i] = clk_wzrd_register_divider (&pdev->dev, clkout_name, @@ -546,7 +728,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) WZRD_CLKOUT_DIVIDE_SHIFT, WZRD_CLKOUT_DIVIDE_WIDTH, CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO, - NULL, &clkwzrd_lock); + DIV_O, &clkwzrd_lock); if (IS_ERR(clk_wzrd->clkout[i])) { int j; @@ -559,8 +741,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) } } - kfree(clk_name); - +out: clk_wzrd->clk_data.clks = clk_wzrd->clkout; clk_wzrd->clk_data.clk_num = ARRAY_SIZE(clk_wzrd->clkout); of_clk_add_provider(np, of_clk_src_onecell_get, &clk_wzrd->clk_data); @@ -585,7 +766,6 @@ static int clk_wzrd_probe(struct platform_device *pdev) err_rm_int_clks: clk_unregister(clk_wzrd->clks_internal[1]); err_rm_int_clk: - kfree(clk_name); clk_unregister(clk_wzrd->clks_internal[0]); err_disable_clk: clk_disable_unprepare(clk_wzrd->axi_clk); -- GitLab From d8c0ee307a6086299157ce8eddec9aef478ef475 Mon Sep 17 00:00:00 2001 From: Yinbo Zhu Date: Thu, 23 Mar 2023 10:52:28 +0800 Subject: [PATCH 1397/5631] dt-bindings: clock: add loongson-2 boot clock index The Loongson-2 boot clock was used to spi and lio peripheral and this patch was to add boot clock index number. Signed-off-by: Yinbo Zhu Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230323025229.2971-1-zhuyinbo@loongson.cn Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/loongson,ls2k-clk.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/dt-bindings/clock/loongson,ls2k-clk.h b/include/dt-bindings/clock/loongson,ls2k-clk.h index db1e27e792ff..3bc4dfc193c2 100644 --- a/include/dt-bindings/clock/loongson,ls2k-clk.h +++ b/include/dt-bindings/clock/loongson,ls2k-clk.h @@ -24,6 +24,7 @@ #define LOONGSON2_SATA_CLK 14 #define LOONGSON2_PIX0_CLK 15 #define LOONGSON2_PIX1_CLK 16 -#define LOONGSON2_CLK_END 17 +#define LOONGSON2_BOOT_CLK 17 +#define LOONGSON2_CLK_END 18 #endif -- GitLab From acc0ccffec502be0d64f477d4341957a897e4283 Mon Sep 17 00:00:00 2001 From: Yinbo Zhu Date: Thu, 23 Mar 2023 10:52:29 +0800 Subject: [PATCH 1398/5631] clk: clk-loongson2: add clock controller driver support This driver provides support for clock controller on Loongson-2 SoC, the Loongson-2 SoC uses a 100MHz clock as the PLL reference clock, there are five independent PLLs inside, each of which PLL can provide up to three sets of frequency dependent clock outputs. Signed-off-by: Yinbo Zhu Link: https://lore.kernel.org/r/20230323025229.2971-2-zhuyinbo@loongson.cn Signed-off-by: Stephen Boyd --- MAINTAINERS | 1 + drivers/clk/Kconfig | 9 + drivers/clk/Makefile | 1 + drivers/clk/clk-loongson2.c | 341 ++++++++++++++++++++++++++++++++++++ 4 files changed, 352 insertions(+) create mode 100644 drivers/clk/clk-loongson2.c diff --git a/MAINTAINERS b/MAINTAINERS index 1695009c1296..2f676da6b1d3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12121,6 +12121,7 @@ M: Yinbo Zhu L: linux-clk@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/clock/loongson,ls2k-clk.yaml +F: drivers/clk/clk-loongson2.c F: include/dt-bindings/clock/loongson,ls2k-clk.h LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index b6c5bf69a2b2..44c08b30c34d 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -325,6 +325,15 @@ config COMMON_CLK_LOCHNAGAR This driver supports the clocking features of the Cirrus Logic Lochnagar audio development board. +config COMMON_CLK_LOONGSON2 + bool "Clock driver for Loongson-2 SoC" + depends on LOONGARCH || COMPILE_TEST + help + This driver provides support for clock controller on Loongson-2 SoC. + The clock controller can generates and supplies clock to various + peripherals within the SoC. + Say Y here to support Loongson-2 SoC clock driver. + config COMMON_CLK_NXP def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX) select REGMAP_MMIO if ARCH_LPC32XX diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index 417bc27ab6e8..fd9d0d51190d 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_LMK04832) += clk-lmk04832.o obj-$(CONFIG_COMMON_CLK_LAN966X) += clk-lan966x.o obj-$(CONFIG_COMMON_CLK_LOCHNAGAR) += clk-lochnagar.o obj-$(CONFIG_MACH_LOONGSON32) += clk-loongson1.o +obj-$(CONFIG_COMMON_CLK_LOONGSON2) += clk-loongson2.o obj-$(CONFIG_COMMON_CLK_MAX77686) += clk-max77686.o obj-$(CONFIG_COMMON_CLK_MAX9485) += clk-max9485.o obj-$(CONFIG_ARCH_MILBEAUT_M10V) += clk-milbeaut.o diff --git a/drivers/clk/clk-loongson2.c b/drivers/clk/clk-loongson2.c new file mode 100644 index 000000000000..70ae1dd2e474 --- /dev/null +++ b/drivers/clk/clk-loongson2.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Author: Yinbo Zhu + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define LOONGSON2_PLL_MULT_SHIFT 32 +#define LOONGSON2_PLL_MULT_WIDTH 10 +#define LOONGSON2_PLL_DIV_SHIFT 26 +#define LOONGSON2_PLL_DIV_WIDTH 6 +#define LOONGSON2_APB_FREQSCALE_SHIFT 20 +#define LOONGSON2_APB_FREQSCALE_WIDTH 3 +#define LOONGSON2_USB_FREQSCALE_SHIFT 16 +#define LOONGSON2_USB_FREQSCALE_WIDTH 3 +#define LOONGSON2_SATA_FREQSCALE_SHIFT 12 +#define LOONGSON2_SATA_FREQSCALE_WIDTH 3 +#define LOONGSON2_BOOT_FREQSCALE_SHIFT 8 +#define LOONGSON2_BOOT_FREQSCALE_WIDTH 3 + +static void __iomem *loongson2_pll_base; + +static const struct clk_parent_data pdata[] = { + { .fw_name = "ref_100m",}, +}; + +static struct clk_hw *loongson2_clk_register(struct device *dev, + const char *name, + const char *parent_name, + const struct clk_ops *ops, + unsigned long flags) +{ + int ret; + struct clk_hw *hw; + struct clk_init_data init; + + hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); + if (!hw) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = ops; + init.flags = flags; + init.num_parents = 1; + + if (!parent_name) + init.parent_data = pdata; + else + init.parent_names = &parent_name; + + hw->init = &init; + + ret = devm_clk_hw_register(dev, hw); + if (ret) + hw = ERR_PTR(ret); + + return hw; +} + +static unsigned long loongson2_calc_pll_rate(int offset, unsigned long rate) +{ + u64 val; + u32 mult, div; + + val = readq(loongson2_pll_base + offset); + + mult = (val >> LOONGSON2_PLL_MULT_SHIFT) & + clk_div_mask(LOONGSON2_PLL_MULT_WIDTH); + div = (val >> LOONGSON2_PLL_DIV_SHIFT) & + clk_div_mask(LOONGSON2_PLL_DIV_WIDTH); + + return div_u64((u64)rate * mult, div); +} + +static unsigned long loongson2_node_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_pll_rate(0x0, parent_rate); +} + +static const struct clk_ops loongson2_node_clk_ops = { + .recalc_rate = loongson2_node_recalc_rate, +}; + +static unsigned long loongson2_ddr_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_pll_rate(0x10, parent_rate); +} + +static const struct clk_ops loongson2_ddr_clk_ops = { + .recalc_rate = loongson2_ddr_recalc_rate, +}; + +static unsigned long loongson2_dc_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_pll_rate(0x20, parent_rate); +} + +static const struct clk_ops loongson2_dc_clk_ops = { + .recalc_rate = loongson2_dc_recalc_rate, +}; + +static unsigned long loongson2_pix0_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_pll_rate(0x30, parent_rate); +} + +static const struct clk_ops loongson2_pix0_clk_ops = { + .recalc_rate = loongson2_pix0_recalc_rate, +}; + +static unsigned long loongson2_pix1_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_pll_rate(0x40, parent_rate); +} + +static const struct clk_ops loongson2_pix1_clk_ops = { + .recalc_rate = loongson2_pix1_recalc_rate, +}; + +static unsigned long loongson2_calc_rate(unsigned long rate, + int shift, int width) +{ + u64 val; + u32 mult; + + val = readq(loongson2_pll_base + 0x50); + + mult = (val >> shift) & clk_div_mask(width); + + return div_u64((u64)rate * (mult + 1), 8); +} + +static unsigned long loongson2_boot_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_rate(parent_rate, + LOONGSON2_BOOT_FREQSCALE_SHIFT, + LOONGSON2_BOOT_FREQSCALE_WIDTH); +} + +static const struct clk_ops loongson2_boot_clk_ops = { + .recalc_rate = loongson2_boot_recalc_rate, +}; + +static unsigned long loongson2_apb_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_rate(parent_rate, + LOONGSON2_APB_FREQSCALE_SHIFT, + LOONGSON2_APB_FREQSCALE_WIDTH); +} + +static const struct clk_ops loongson2_apb_clk_ops = { + .recalc_rate = loongson2_apb_recalc_rate, +}; + +static unsigned long loongson2_usb_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_rate(parent_rate, + LOONGSON2_USB_FREQSCALE_SHIFT, + LOONGSON2_USB_FREQSCALE_WIDTH); +} + +static const struct clk_ops loongson2_usb_clk_ops = { + .recalc_rate = loongson2_usb_recalc_rate, +}; + +static unsigned long loongson2_sata_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + return loongson2_calc_rate(parent_rate, + LOONGSON2_SATA_FREQSCALE_SHIFT, + LOONGSON2_SATA_FREQSCALE_WIDTH); +} + +static const struct clk_ops loongson2_sata_clk_ops = { + .recalc_rate = loongson2_sata_recalc_rate, +}; + +static inline int loongson2_check_clk_hws(struct clk_hw *clks[], unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) + if (IS_ERR(clks[i])) { + pr_err("Loongson2 clk %u: register failed with %ld\n", + i, PTR_ERR(clks[i])); + return PTR_ERR(clks[i]); + } + + return 0; +} + +static int loongson2_clk_probe(struct platform_device *pdev) +{ + int ret; + struct clk_hw **hws; + struct clk_hw_onecell_data *clk_hw_data; + spinlock_t loongson2_clk_lock; + struct device *dev = &pdev->dev; + + loongson2_pll_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(loongson2_pll_base)) + return PTR_ERR(loongson2_pll_base); + + clk_hw_data = devm_kzalloc(dev, struct_size(clk_hw_data, hws, LOONGSON2_CLK_END), + GFP_KERNEL); + if (WARN_ON(!clk_hw_data)) + return -ENOMEM; + + clk_hw_data->num = LOONGSON2_CLK_END; + hws = clk_hw_data->hws; + + hws[LOONGSON2_NODE_PLL] = loongson2_clk_register(dev, "node_pll", + NULL, + &loongson2_node_clk_ops, 0); + + hws[LOONGSON2_DDR_PLL] = loongson2_clk_register(dev, "ddr_pll", + NULL, + &loongson2_ddr_clk_ops, 0); + + hws[LOONGSON2_DC_PLL] = loongson2_clk_register(dev, "dc_pll", + NULL, + &loongson2_dc_clk_ops, 0); + + hws[LOONGSON2_PIX0_PLL] = loongson2_clk_register(dev, "pix0_pll", + NULL, + &loongson2_pix0_clk_ops, 0); + + hws[LOONGSON2_PIX1_PLL] = loongson2_clk_register(dev, "pix1_pll", + NULL, + &loongson2_pix1_clk_ops, 0); + + hws[LOONGSON2_BOOT_CLK] = loongson2_clk_register(dev, "boot", + NULL, + &loongson2_boot_clk_ops, 0); + + hws[LOONGSON2_NODE_CLK] = devm_clk_hw_register_divider(dev, "node", + "node_pll", 0, + loongson2_pll_base + 0x8, 0, + 6, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + /* + * The hda clk divisor in the upper 32bits and the clk-prodiver + * layer code doesn't support 64bit io operation thus a conversion + * is required that subtract shift by 32 and add 4byte to the hda + * address + */ + hws[LOONGSON2_HDA_CLK] = devm_clk_hw_register_divider(dev, "hda", + "ddr_pll", 0, + loongson2_pll_base + 0x22, 12, + 7, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_GPU_CLK] = devm_clk_hw_register_divider(dev, "gpu", + "ddr_pll", 0, + loongson2_pll_base + 0x18, 22, + 6, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_DDR_CLK] = devm_clk_hw_register_divider(dev, "ddr", + "ddr_pll", 0, + loongson2_pll_base + 0x18, 0, + 6, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_GMAC_CLK] = devm_clk_hw_register_divider(dev, "gmac", + "dc_pll", 0, + loongson2_pll_base + 0x28, 22, + 6, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_DC_CLK] = devm_clk_hw_register_divider(dev, "dc", + "dc_pll", 0, + loongson2_pll_base + 0x28, 0, + 6, CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_APB_CLK] = loongson2_clk_register(dev, "apb", + "gmac", + &loongson2_apb_clk_ops, 0); + + hws[LOONGSON2_USB_CLK] = loongson2_clk_register(dev, "usb", + "gmac", + &loongson2_usb_clk_ops, 0); + + hws[LOONGSON2_SATA_CLK] = loongson2_clk_register(dev, "sata", + "gmac", + &loongson2_sata_clk_ops, 0); + + hws[LOONGSON2_PIX0_CLK] = clk_hw_register_divider(NULL, "pix0", + "pix0_pll", 0, + loongson2_pll_base + 0x38, 0, 6, + CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + hws[LOONGSON2_PIX1_CLK] = clk_hw_register_divider(NULL, "pix1", + "pix1_pll", 0, + loongson2_pll_base + 0x48, 0, 6, + CLK_DIVIDER_ONE_BASED, + &loongson2_clk_lock); + + ret = loongson2_check_clk_hws(hws, LOONGSON2_CLK_END); + if (ret) + return ret; + + return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_hw_data); +} + +static const struct of_device_id loongson2_clk_match_table[] = { + { .compatible = "loongson,ls2k-clk" }, + { } +}; +MODULE_DEVICE_TABLE(of, loongson2_clk_match_table); + +static struct platform_driver loongson2_clk_driver = { + .probe = loongson2_clk_probe, + .driver = { + .name = "loongson2-clk", + .of_match_table = loongson2_clk_match_table, + }, +}; +module_platform_driver(loongson2_clk_driver); + +MODULE_DESCRIPTION("Loongson2 clock driver"); +MODULE_LICENSE("GPL"); -- GitLab From 0ca6a0970073a14f5608f0add0e431697316cbca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 22 Mar 2023 18:15:12 +0100 Subject: [PATCH 1399/5631] dt-bindings: clk: add BCM63268 timer clock definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing timer clock definitions for BCM63268. Signed-off-by: Álvaro Fernández Rojas Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230322171515.120353-2-noltari@gmail.com Signed-off-by: Stephen Boyd --- include/dt-bindings/clock/bcm63268-clock.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/include/dt-bindings/clock/bcm63268-clock.h b/include/dt-bindings/clock/bcm63268-clock.h index da23e691d359..dea8adc8510e 100644 --- a/include/dt-bindings/clock/bcm63268-clock.h +++ b/include/dt-bindings/clock/bcm63268-clock.h @@ -27,4 +27,17 @@ #define BCM63268_CLK_TBUS 27 #define BCM63268_CLK_ROBOSW250 31 +#define BCM63268_TCLK_EPHY1 0 +#define BCM63268_TCLK_EPHY2 1 +#define BCM63268_TCLK_EPHY3 2 +#define BCM63268_TCLK_GPHY1 3 +#define BCM63268_TCLK_DSL 4 +#define BCM63268_TCLK_WAKEON_EPHY 6 +#define BCM63268_TCLK_WAKEON_DSL 7 +#define BCM63268_TCLK_FAP1 11 +#define BCM63268_TCLK_FAP2 15 +#define BCM63268_TCLK_UTO_50 16 +#define BCM63268_TCLK_UTO_EXTIN 17 +#define BCM63268_TCLK_USB_REF 18 + #endif /* __DT_BINDINGS_CLOCK_BCM63268_H */ -- GitLab From 2a67e196bb5197bdca89332d2a71e708ee4d897d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 22 Mar 2023 18:15:13 +0100 Subject: [PATCH 1400/5631] dt-bindings: reset: add BCM63268 timer reset definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing timer reset definitions for BCM63268. Signed-off-by: Álvaro Fernández Rojas Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230322171515.120353-3-noltari@gmail.com Signed-off-by: Stephen Boyd --- include/dt-bindings/reset/bcm63268-reset.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/dt-bindings/reset/bcm63268-reset.h b/include/dt-bindings/reset/bcm63268-reset.h index 6a6403a4c2d5..d87a7882782a 100644 --- a/include/dt-bindings/reset/bcm63268-reset.h +++ b/include/dt-bindings/reset/bcm63268-reset.h @@ -23,4 +23,8 @@ #define BCM63268_RST_PCIE_HARD 17 #define BCM63268_RST_GPHY 18 +#define BCM63268_TRST_SW 29 +#define BCM63268_TRST_HW 30 +#define BCM63268_TRST_POR 31 + #endif /* __DT_BINDINGS_RESET_BCM63268_H */ -- GitLab From cd04bbb9247c5aec393b51ce1e2a6eb3cac2e27e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 22 Mar 2023 18:15:14 +0100 Subject: [PATCH 1401/5631] dt-bindings: clock: Add BCM63268 timer binding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Document the Broadcom BCM63268 Clock and Reset controller. Signed-off-by: Álvaro Fernández Rojas Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230322171515.120353-4-noltari@gmail.com Signed-off-by: Stephen Boyd --- .../clock/brcm,bcm63268-timer-clocks.yaml | 40 +++++++++++++++++++ 1 file changed, 40 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/brcm,bcm63268-timer-clocks.yaml diff --git a/Documentation/devicetree/bindings/clock/brcm,bcm63268-timer-clocks.yaml b/Documentation/devicetree/bindings/clock/brcm,bcm63268-timer-clocks.yaml new file mode 100644 index 000000000000..199818b2fb6d --- /dev/null +++ b/Documentation/devicetree/bindings/clock/brcm,bcm63268-timer-clocks.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/brcm,bcm63268-timer-clocks.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Broadcom BCM63268 Timer Clock and Reset Device Tree Bindings + +maintainers: + - Álvaro Fernández Rojas + +properties: + compatible: + const: brcm,bcm63268-timer-clocks + + reg: + maxItems: 1 + + "#clock-cells": + const: 1 + + "#reset-cells": + const: 1 + +required: + - compatible + - reg + - "#clock-cells" + - "#reset-cells" + +additionalProperties: false + +examples: + - | + timer_clk: clock-controller@100000ac { + compatible = "brcm,bcm63268-timer-clocks"; + reg = <0x100000ac 0x4>; + #clock-cells = <1>; + #reset-cells = <1>; + }; -- GitLab From ba7c8d2700adf594540046d63da9a84eb92272c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C3=81lvaro=20Fern=C3=A1ndez=20Rojas?= Date: Wed, 22 Mar 2023 18:15:15 +0100 Subject: [PATCH 1402/5631] clk: bcm: Add BCM63268 timer clock and reset driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add driver for BCM63268 timer clock and reset controller. Signed-off-by: Álvaro Fernández Rojas Link: https://lore.kernel.org/r/20230322171515.120353-5-noltari@gmail.com [sboyd@kernel.org: Mark reset ops const, fixup includes] Signed-off-by: Stephen Boyd --- drivers/clk/bcm/Kconfig | 9 ++ drivers/clk/bcm/Makefile | 1 + drivers/clk/bcm/clk-bcm63268-timer.c | 216 +++++++++++++++++++++++++++ 3 files changed, 226 insertions(+) create mode 100644 drivers/clk/bcm/clk-bcm63268-timer.c diff --git a/drivers/clk/bcm/Kconfig b/drivers/clk/bcm/Kconfig index 77266afb1c79..a972d763eb77 100644 --- a/drivers/clk/bcm/Kconfig +++ b/drivers/clk/bcm/Kconfig @@ -37,6 +37,15 @@ config CLK_BCM_63XX_GATE Enable common clock framework support for Broadcom BCM63xx DSL SoCs based on the MIPS architecture +config CLK_BCM63268_TIMER + bool "Broadcom BCM63268 timer clock and reset support" + depends on BMIPS_GENERIC || COMPILE_TEST + default BMIPS_GENERIC + select RESET_CONTROLLER + help + Enable timer clock and reset support for Broadcom BCM63268 DSL SoCs + based on the MIPS architecture. + config CLK_BCM_KONA bool "Broadcom Kona CCU clock support" depends on ARCH_BCM_MOBILE || COMPILE_TEST diff --git a/drivers/clk/bcm/Makefile b/drivers/clk/bcm/Makefile index edb66b44cb27..d0b6f4b1fb08 100644 --- a/drivers/clk/bcm/Makefile +++ b/drivers/clk/bcm/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_CLK_BCM_63XX) += clk-bcm63xx.o obj-$(CONFIG_CLK_BCM_63XX_GATE) += clk-bcm63xx-gate.o +obj-$(CONFIG_CLK_BCM63268_TIMER) += clk-bcm63268-timer.o obj-$(CONFIG_CLK_BCM_KONA) += clk-kona.o obj-$(CONFIG_CLK_BCM_KONA) += clk-kona-setup.o obj-$(CONFIG_CLK_BCM_KONA) += clk-bcm281xx.o diff --git a/drivers/clk/bcm/clk-bcm63268-timer.c b/drivers/clk/bcm/clk-bcm63268-timer.c new file mode 100644 index 000000000000..463710d272a1 --- /dev/null +++ b/drivers/clk/bcm/clk-bcm63268-timer.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BCM63268 Timer Clock and Reset Controller Driver + * + * Copyright (C) 2023 Álvaro Fernández Rojas + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define BCM63268_TIMER_RESET_SLEEP_MIN_US 10000 +#define BCM63268_TIMER_RESET_SLEEP_MAX_US 20000 + +struct bcm63268_tclkrst_hw { + void __iomem *regs; + spinlock_t lock; + + struct reset_controller_dev rcdev; + struct clk_hw_onecell_data data; +}; + +struct bcm63268_tclk_table_entry { + const char * const name; + u8 bit; +}; + +static const struct bcm63268_tclk_table_entry bcm63268_timer_clocks[] = { + { + .name = "ephy1", + .bit = BCM63268_TCLK_EPHY1, + }, { + .name = "ephy2", + .bit = BCM63268_TCLK_EPHY2, + }, { + .name = "ephy3", + .bit = BCM63268_TCLK_EPHY3, + }, { + .name = "gphy1", + .bit = BCM63268_TCLK_GPHY1, + }, { + .name = "dsl", + .bit = BCM63268_TCLK_DSL, + }, { + .name = "wakeon_ephy", + .bit = BCM63268_TCLK_WAKEON_EPHY, + }, { + .name = "wakeon_dsl", + .bit = BCM63268_TCLK_WAKEON_DSL, + }, { + .name = "fap1_pll", + .bit = BCM63268_TCLK_FAP1, + }, { + .name = "fap2_pll", + .bit = BCM63268_TCLK_FAP2, + }, { + .name = "uto_50", + .bit = BCM63268_TCLK_UTO_50, + }, { + .name = "uto_extin", + .bit = BCM63268_TCLK_UTO_EXTIN, + }, { + .name = "usb_ref", + .bit = BCM63268_TCLK_USB_REF, + }, { + /* sentinel */ + } +}; + +static inline struct bcm63268_tclkrst_hw * +to_bcm63268_timer_reset(struct reset_controller_dev *rcdev) +{ + return container_of(rcdev, struct bcm63268_tclkrst_hw, rcdev); +} + +static int bcm63268_timer_reset_update(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) +{ + struct bcm63268_tclkrst_hw *reset = to_bcm63268_timer_reset(rcdev); + unsigned long flags; + uint32_t val; + + spin_lock_irqsave(&reset->lock, flags); + val = __raw_readl(reset->regs); + if (assert) + val &= ~BIT(id); + else + val |= BIT(id); + __raw_writel(val, reset->regs); + spin_unlock_irqrestore(&reset->lock, flags); + + return 0; +} + +static int bcm63268_timer_reset_assert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + return bcm63268_timer_reset_update(rcdev, id, true); +} + +static int bcm63268_timer_reset_deassert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + return bcm63268_timer_reset_update(rcdev, id, false); +} + +static int bcm63268_timer_reset_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + bcm63268_timer_reset_update(rcdev, id, true); + usleep_range(BCM63268_TIMER_RESET_SLEEP_MIN_US, + BCM63268_TIMER_RESET_SLEEP_MAX_US); + + bcm63268_timer_reset_update(rcdev, id, false); + /* + * Ensure component is taken out reset state by sleeping also after + * deasserting the reset. Otherwise, the component may not be ready + * for operation. + */ + usleep_range(BCM63268_TIMER_RESET_SLEEP_MIN_US, + BCM63268_TIMER_RESET_SLEEP_MAX_US); + + return 0; +} + +static int bcm63268_timer_reset_status(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct bcm63268_tclkrst_hw *reset = to_bcm63268_timer_reset(rcdev); + + return !(__raw_readl(reset->regs) & BIT(id)); +} + +static const struct reset_control_ops bcm63268_timer_reset_ops = { + .assert = bcm63268_timer_reset_assert, + .deassert = bcm63268_timer_reset_deassert, + .reset = bcm63268_timer_reset_reset, + .status = bcm63268_timer_reset_status, +}; + +static int bcm63268_tclk_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct bcm63268_tclk_table_entry *entry; + struct bcm63268_tclkrst_hw *hw; + struct clk_hw *clk; + u8 maxbit = 0; + int i, ret; + + for (entry = bcm63268_timer_clocks; entry->name; entry++) + maxbit = max(maxbit, entry->bit); + maxbit++; + + hw = devm_kzalloc(&pdev->dev, struct_size(hw, data.hws, maxbit), + GFP_KERNEL); + if (!hw) + return -ENOMEM; + + platform_set_drvdata(pdev, hw); + + spin_lock_init(&hw->lock); + + hw->data.num = maxbit; + for (i = 0; i < maxbit; i++) + hw->data.hws[i] = ERR_PTR(-ENODEV); + + hw->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(hw->regs)) + return PTR_ERR(hw->regs); + + for (entry = bcm63268_timer_clocks; entry->name; entry++) { + clk = devm_clk_hw_register_gate(dev, entry->name, NULL, 0, + hw->regs, entry->bit, + CLK_GATE_BIG_ENDIAN, + &hw->lock); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + hw->data.hws[entry->bit] = clk; + } + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, + &hw->data); + if (ret) + return ret; + + hw->rcdev.of_node = dev->of_node; + hw->rcdev.ops = &bcm63268_timer_reset_ops; + + ret = devm_reset_controller_register(dev, &hw->rcdev); + if (ret) + dev_err(dev, "Failed to register reset controller\n"); + + return 0; +} + +static const struct of_device_id bcm63268_tclk_dt_ids[] = { + { .compatible = "brcm,bcm63268-timer-clocks" }, + { /* sentinel */ } +}; + +static struct platform_driver bcm63268_tclk = { + .probe = bcm63268_tclk_probe, + .driver = { + .name = "bcm63268-timer-clock", + .of_match_table = bcm63268_tclk_dt_ids, + }, +}; +builtin_platform_driver(bcm63268_tclk); -- GitLab From 08b71a71f315bbb25608abc924ac209d1e079683 Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 27 Mar 2023 14:27:50 +0800 Subject: [PATCH 1403/5631] pinctrl: s32: refine error/return/config checks and simplify driver codes Improve error/return code handlings and config checks in order to have better reliability and simplify driver codes such as removing/changing improper macros, blanks, print formats and helper calls. Signed-off-by: Chester Lin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230327062754.3326-2-clin@suse.com Signed-off-by: Linus Walleij --- drivers/pinctrl/nxp/pinctrl-s32cc.c | 141 +++++++++++++++------------- drivers/pinctrl/nxp/pinctrl-s32g2.c | 4 +- 2 files changed, 76 insertions(+), 69 deletions(-) diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index e1da332433a3..f698e1a240ef 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -28,7 +28,8 @@ #include "../pinctrl-utils.h" #include "pinctrl-s32.h" -#define S32_PIN_ID_MASK GENMASK(31, 4) +#define S32_PIN_ID_SHIFT 4 +#define S32_PIN_ID_MASK GENMASK(31, S32_PIN_ID_SHIFT) #define S32_MSCR_SSS_MASK GENMASK(2, 0) #define S32_MSCR_PUS BIT(12) @@ -46,7 +47,7 @@ static struct regmap_config s32_regmap_config = { static u32 get_pin_no(u32 pinmux) { - return (pinmux & S32_PIN_ID_MASK) >> __ffs(S32_PIN_ID_MASK); + return (pinmux & S32_PIN_ID_MASK) >> S32_PIN_ID_SHIFT; } static u32 get_pin_func(u32 pinmux) @@ -108,7 +109,7 @@ s32_get_region(struct pinctrl_dev *pctldev, unsigned int pin) unsigned int mem_regions = ipctl->info->mem_regions; unsigned int i; - for (i = 0; i < mem_regions; ++i) { + for (i = 0; i < mem_regions; i++) { pin_range = ipctl->regions[i].pin_range; if (pin >= pin_range->start && pin <= pin_range->end) return &ipctl->regions[i]; @@ -224,8 +225,7 @@ static int s32_dt_group_node_to_map(struct pinctrl_dev *pctldev, n_pins = of_property_count_elems_of_size(np, "pinmux", sizeof(u32)); if (n_pins < 0) { - dev_warn(dev, "Unable to find 'pinmux' property in node %s.\n", - np->name); + dev_warn(dev, "Can't find 'pinmux' property in node %pOFn\n", np); } else if (!n_pins) { return -EINVAL; } @@ -317,20 +317,25 @@ static int s32_pmx_set(struct pinctrl_dev *pctldev, unsigned int selector, info->functions[selector].name, grp->name); /* Check beforehand so we don't have a partial config. */ - for (i = 0; i < grp->npins; ++i) { + for (i = 0; i < grp->npins; i++) { if (s32_check_pin(pctldev, grp->pin_ids[i]) != 0) { - dev_err(info->dev, "invalid pin: %d in group: %d\n", + dev_err(info->dev, "invalid pin: %u in group: %u\n", grp->pin_ids[i], group); return -EINVAL; } } - for (i = 0, ret = 0; i < grp->npins && !ret; ++i) { + for (i = 0, ret = 0; i < grp->npins && !ret; i++) { ret = s32_regmap_update(pctldev, grp->pin_ids[i], S32_MSCR_SSS_MASK, grp->pin_sss[i]); + if (ret) { + dev_err(info->dev, "Failed to set pin %u\n", + grp->pin_ids[i]); + return ret; + } } - return ret; + return 0; } static int s32_pmx_get_funcs_count(struct pinctrl_dev *pctldev) @@ -375,8 +380,8 @@ static int s32_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, int ret; ret = s32_regmap_read(pctldev, offset, &config); - if (ret != 0) - return -EINVAL; + if (ret) + return ret; /* Save current configuration */ gpio_pin = kmalloc(sizeof(*gpio_pin), GFP_KERNEL); @@ -387,7 +392,7 @@ static int s32_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, gpio_pin->config = config; spin_lock_irqsave(&ipctl->gpio_configs_lock, flags); - list_add(&(gpio_pin->list), &(ipctl->gpio_configs)); + list_add(&gpio_pin->list, &ipctl->gpio_configs); spin_unlock_irqrestore(&ipctl->gpio_configs_lock, flags); /* GPIO pin means SSS = 0 */ @@ -401,23 +406,20 @@ static void s32_pmx_gpio_disable_free(struct pinctrl_dev *pctldev, unsigned int offset) { struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); - struct list_head *pos, *tmp; - struct gpio_pin_config *gpio_pin; + struct gpio_pin_config *gpio_pin, *tmp; unsigned long flags; int ret; spin_lock_irqsave(&ipctl->gpio_configs_lock, flags); - list_for_each_safe(pos, tmp, &ipctl->gpio_configs) { - gpio_pin = list_entry(pos, struct gpio_pin_config, list); - + list_for_each_entry_safe(gpio_pin, tmp, &ipctl->gpio_configs, list) { if (gpio_pin->pin_id == offset) { ret = s32_regmap_write(pctldev, gpio_pin->pin_id, gpio_pin->config); if (ret != 0) goto unlock; - list_del(pos); + list_del(&gpio_pin->list); kfree(gpio_pin); break; } @@ -461,7 +463,8 @@ static const int support_slew[] = {208, -1, -1, -1, 166, 150, 133, 83}; static int s32_get_slew_regval(int arg) { - int i; + unsigned int i; + /* Translate a real slew rate (MHz) to a register value */ for (i = 0; i < ARRAY_SIZE(support_slew); i++) { if (arg == support_slew[i]) @@ -542,10 +545,11 @@ static int s32_pinconf_mscr_update(struct pinctrl_dev *pctldev, unsigned int config = 0, mask = 0; int i, ret; - if (s32_check_pin(pctldev, pin_id) != 0) - return -EINVAL; + ret = s32_check_pin(pctldev, pin_id); + if (ret) + return ret; - dev_dbg(ipctl->dev, "pinconf set pin %s with %d configs\n", + dev_dbg(ipctl->dev, "pinconf set pin %s with %u configs\n", pin_get_name(pctldev, pin_id), num_configs); for (i = 0; i < num_configs; i++) { @@ -559,11 +563,9 @@ static int s32_pinconf_mscr_update(struct pinctrl_dev *pctldev, if (!config && !mask) return 0; - ret = s32_regmap_update(pctldev, pin_id, mask, config); + dev_dbg(ipctl->dev, "update: pin %u cfg 0x%x\n", pin_id, config); - dev_dbg(ipctl->dev, "update: pin %d cfg 0x%x\n", pin_id, config); - - return ret; + return s32_regmap_update(pctldev, pin_id, mask, config); } static int s32_pinconf_get(struct pinctrl_dev *pctldev, @@ -604,10 +606,13 @@ static void s32_pinconf_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s, unsigned int pin_id) { unsigned int config; - int ret = s32_regmap_read(pctldev, pin_id, &config); + int ret; - if (!ret) - seq_printf(s, "0x%x", config); + ret = s32_regmap_read(pctldev, pin_id, &config); + if (ret) + return; + + seq_printf(s, "0x%x", config); } static void s32_pinconf_group_dbg_show(struct pinctrl_dev *pctldev, @@ -710,7 +715,7 @@ int s32_pinctrl_resume(struct device *dev) } #endif -static void s32_pinctrl_parse_groups(struct device_node *np, +static int s32_pinctrl_parse_groups(struct device_node *np, struct s32_pin_group *grp, struct s32_pinctrl_soc_info *info) { @@ -722,21 +727,20 @@ static void s32_pinctrl_parse_groups(struct device_node *np, dev = info->dev; - dev_dbg(dev, "group: %s\n", np->name); + dev_dbg(dev, "group: %pOFn\n", np); /* Initialise group */ grp->name = np->name; npins = of_property_count_elems_of_size(np, "pinmux", sizeof(u32)); - if (npins < 0) { dev_err(dev, "Failed to read 'pinmux' property in node %s.\n", - np->name); - return; + grp->name); + return -EINVAL; } if (!npins) { - dev_err(dev, "The group %s has no pins.\n", np->name); - return; + dev_err(dev, "The group %s has no pins.\n", grp->name); + return -EINVAL; } grp->npins = npins; @@ -745,12 +749,8 @@ static void s32_pinctrl_parse_groups(struct device_node *np, sizeof(unsigned int), GFP_KERNEL); grp->pin_sss = devm_kcalloc(info->dev, grp->npins, sizeof(unsigned int), GFP_KERNEL); - - if (!grp->pin_ids || !grp->pin_sss) { - dev_err(dev, "Failed to allocate memory for the group %s.\n", - np->name); - return; - } + if (!grp->pin_ids || !grp->pin_sss) + return -ENOMEM; i = 0; of_property_for_each_u32(np, "pinmux", prop, p, pinmux) { @@ -761,9 +761,11 @@ static void s32_pinctrl_parse_groups(struct device_node *np, grp->pin_ids[i], grp->pin_sss[i]); i++; } + + return 0; } -static void s32_pinctrl_parse_functions(struct device_node *np, +static int s32_pinctrl_parse_functions(struct device_node *np, struct s32_pinctrl_soc_info *info, u32 index) { @@ -771,8 +773,9 @@ static void s32_pinctrl_parse_functions(struct device_node *np, struct s32_pmx_func *func; struct s32_pin_group *grp; u32 i = 0; + int ret = 0; - dev_dbg(info->dev, "parse function(%d): %s\n", index, np->name); + dev_dbg(info->dev, "parse function(%u): %pOFn\n", index, np); func = &info->functions[index]; @@ -780,18 +783,24 @@ static void s32_pinctrl_parse_functions(struct device_node *np, func->name = np->name; func->num_groups = of_get_child_count(np); if (func->num_groups == 0) { - dev_err(info->dev, "no groups defined in %s\n", np->full_name); - return; + dev_err(info->dev, "no groups defined in %pOF\n", np); + return -EINVAL; } - func->groups = devm_kzalloc(info->dev, - func->num_groups * sizeof(char *), GFP_KERNEL); + func->groups = devm_kcalloc(info->dev, func->num_groups, + sizeof(*func->groups), GFP_KERNEL); + if (!func->groups) + return -ENOMEM; for_each_child_of_node(np, child) { func->groups[i] = child->name; grp = &info->groups[info->grp_index++]; - s32_pinctrl_parse_groups(child, grp, info); + ret = s32_pinctrl_parse_groups(child, grp, info); + if (ret) + return ret; i++; } + + return 0; } static int s32_pinctrl_probe_dt(struct platform_device *pdev, @@ -804,6 +813,7 @@ static int s32_pinctrl_probe_dt(struct platform_device *pdev, struct regmap *map; void __iomem *base; int mem_regions = info->mem_regions; + int ret; u32 nfuncs = 0; u32 i = 0; @@ -815,13 +825,12 @@ static int s32_pinctrl_probe_dt(struct platform_device *pdev, return -EINVAL; } - ipctl->regions = devm_kzalloc(&pdev->dev, - mem_regions * sizeof(*(ipctl->regions)), - GFP_KERNEL); + ipctl->regions = devm_kcalloc(&pdev->dev, mem_regions, + sizeof(*ipctl->regions), GFP_KERNEL); if (!ipctl->regions) return -ENOMEM; - for (i = 0; i < mem_regions; ++i) { + for (i = 0; i < mem_regions; i++) { base = devm_platform_get_and_ioremap_resource(pdev, i, &res); if (IS_ERR(base)) return PTR_ERR(base); @@ -851,24 +860,26 @@ static int s32_pinctrl_probe_dt(struct platform_device *pdev, } info->nfunctions = nfuncs; - info->functions = devm_kzalloc(&pdev->dev, - nfuncs * sizeof(struct s32_pmx_func), - GFP_KERNEL); + info->functions = devm_kcalloc(&pdev->dev, nfuncs, + sizeof(*info->functions), GFP_KERNEL); if (!info->functions) return -ENOMEM; info->ngroups = 0; for_each_child_of_node(np, child) info->ngroups += of_get_child_count(child); - info->groups = devm_kzalloc(&pdev->dev, - info->ngroups * sizeof(struct s32_pin_group), - GFP_KERNEL); + + info->groups = devm_kcalloc(&pdev->dev, info->ngroups, + sizeof(*info->groups), GFP_KERNEL); if (!info->groups) return -ENOMEM; i = 0; - for_each_child_of_node(np, child) - s32_pinctrl_parse_functions(child, info, i++); + for_each_child_of_node(np, child) { + ret = s32_pinctrl_parse_functions(child, info, i++); + if (ret) + return ret; + } return 0; } @@ -923,11 +934,9 @@ int s32_pinctrl_probe(struct platform_device *pdev, ipctl->pctl = devm_pinctrl_register(&pdev->dev, s32_pinctrl_desc, ipctl); - - if (IS_ERR(ipctl->pctl)) { - dev_err(&pdev->dev, "could not register s32 pinctrl driver\n"); - return PTR_ERR(ipctl->pctl); - } + if (IS_ERR(ipctl->pctl)) + return dev_err_probe(&pdev->dev, PTR_ERR(ipctl->pctl), + "could not register s32 pinctrl driver\n"); #ifdef CONFIG_PM_SLEEP saved_context = &ipctl->saved_context; diff --git a/drivers/pinctrl/nxp/pinctrl-s32g2.c b/drivers/pinctrl/nxp/pinctrl-s32g2.c index 5028f4adc389..d9f3ff6794ea 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32g2.c +++ b/drivers/pinctrl/nxp/pinctrl-s32g2.c @@ -757,14 +757,12 @@ static const struct dev_pm_ops s32g_pinctrl_pm_ops = { static struct platform_driver s32g_pinctrl_driver = { .driver = { .name = "s32g-siul2-pinctrl", - .owner = THIS_MODULE, .of_match_table = s32_pinctrl_of_match, - .pm = &s32g_pinctrl_pm_ops, + .pm = pm_sleep_ptr(&s32g_pinctrl_pm_ops), .suppress_bind_attrs = true, }, .probe = s32g_pinctrl_probe, }; - builtin_platform_driver(s32g_pinctrl_driver); MODULE_AUTHOR("Matthew Nunez "); -- GitLab From 48b016cbb2f48ce4cbefd91f63a0d0dded975932 Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 27 Mar 2023 14:27:51 +0800 Subject: [PATCH 1404/5631] pinctrl: s32cc: refactor pin config parsing Move common codes into smaller inline functions and remove argument checks that are not actually used by pull up/down bits in the S32 MSCR register. Signed-off-by: Chester Lin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230327062754.3326-3-clin@suse.com Signed-off-by: Linus Walleij --- drivers/pinctrl/nxp/pinctrl-s32cc.c | 52 ++++++++++++++++++----------- 1 file changed, 33 insertions(+), 19 deletions(-) diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index f698e1a240ef..36f323f87785 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -474,11 +474,38 @@ static int s32_get_slew_regval(int arg) return -EINVAL; } -static int s32_get_pin_conf(enum pin_config_param param, u32 arg, - unsigned int *mask, unsigned int *config) +static inline void s32_pin_set_pull(enum pin_config_param param, + unsigned int *mask, unsigned int *config) { + switch (param) { + case PIN_CONFIG_BIAS_DISABLE: + case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: + *config &= ~(S32_MSCR_PUS | S32_MSCR_PUE); + break; + case PIN_CONFIG_BIAS_PULL_UP: + *config |= S32_MSCR_PUS | S32_MSCR_PUE; + break; + case PIN_CONFIG_BIAS_PULL_DOWN: + *config &= ~S32_MSCR_PUS; + *config |= S32_MSCR_PUE; + break; + default: + return; + } + + *mask |= S32_MSCR_PUS | S32_MSCR_PUE; +} + +static int s32_parse_pincfg(unsigned long pincfg, unsigned int *mask, + unsigned int *config) +{ + enum pin_config_param param; + u32 arg; int ret; + param = pinconf_to_config_param(pincfg); + arg = pinconf_to_config_argument(pincfg); + switch (param) { /* All pins are persistent over suspend */ case PIN_CONFIG_PERSIST_STATE: @@ -508,26 +535,15 @@ static int s32_get_pin_conf(enum pin_config_param param, u32 arg, *config |= S32_MSCR_SRE((u32)ret); *mask |= S32_MSCR_SRE(~0); break; + case PIN_CONFIG_BIAS_DISABLE: case PIN_CONFIG_BIAS_PULL_UP: - if (arg) - *config |= S32_MSCR_PUS; - else - *config &= ~S32_MSCR_PUS; - fallthrough; case PIN_CONFIG_BIAS_PULL_DOWN: - if (arg) - *config |= S32_MSCR_PUE; - else - *config &= ~S32_MSCR_PUE; - *mask |= S32_MSCR_PUE | S32_MSCR_PUS; + s32_pin_set_pull(param, mask, config); break; case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: *config &= ~(S32_MSCR_ODE | S32_MSCR_OBE | S32_MSCR_IBE); *mask |= S32_MSCR_ODE | S32_MSCR_OBE | S32_MSCR_IBE; - fallthrough; - case PIN_CONFIG_BIAS_DISABLE: - *config &= ~(S32_MSCR_PUS | S32_MSCR_PUE); - *mask |= S32_MSCR_PUS | S32_MSCR_PUE; + s32_pin_set_pull(param, mask, config); break; default: return -EOPNOTSUPP; @@ -553,9 +569,7 @@ static int s32_pinconf_mscr_update(struct pinctrl_dev *pctldev, pin_get_name(pctldev, pin_id), num_configs); for (i = 0; i < num_configs; i++) { - ret = s32_get_pin_conf(pinconf_to_config_param(configs[i]), - pinconf_to_config_argument(configs[i]), - &mask, &config); + ret = s32_parse_pincfg(configs[i], &mask, &config); if (ret) return ret; } -- GitLab From 8ff169e8448ccbc569f2cc8767a4f34f3dbbc160 Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 27 Mar 2023 14:27:52 +0800 Subject: [PATCH 1405/5631] pinctrl: s32cc: embed generic struct pingroup Use generic data structure to describe pin control groups in S32 SoC family and drop duplicated struct members. Suggested-by: Andy Shevchenko Signed-off-by: Chester Lin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230327062754.3326-4-clin@suse.com Signed-off-by: Linus Walleij --- drivers/pinctrl/nxp/pinctrl-s32.h | 12 ++---- drivers/pinctrl/nxp/pinctrl-s32cc.c | 57 +++++++++++++++-------------- 2 files changed, 33 insertions(+), 36 deletions(-) diff --git a/drivers/pinctrl/nxp/pinctrl-s32.h b/drivers/pinctrl/nxp/pinctrl-s32.h index 545bf16b988d..850cd668f406 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32.h +++ b/drivers/pinctrl/nxp/pinctrl-s32.h @@ -15,16 +15,12 @@ struct platform_device; /** * struct s32_pin_group - describes an S32 pin group - * @name: the name of this specific pin group - * @npins: the number of pins in this group array, i.e. the number of - * elements in pin_ids and pin_sss so we can iterate over that array - * @pin_ids: an array of pin IDs in this group - * @pin_sss: an array of source signal select configs paired with pin_ids + * @data: generic data describes group name, number of pins, and a pin array in + this group. + * @pin_sss: an array of source signal select configs paired with pin array. */ struct s32_pin_group { - const char *name; - unsigned int npins; - unsigned int *pin_ids; + struct pingroup data; unsigned int *pin_sss; }; diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index 36f323f87785..e65c88162d7f 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -188,7 +188,7 @@ static const char *s32_get_group_name(struct pinctrl_dev *pctldev, struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); const struct s32_pinctrl_soc_info *info = ipctl->info; - return info->groups[selector].name; + return info->groups[selector].data.name; } static int s32_get_group_pins(struct pinctrl_dev *pctldev, @@ -198,8 +198,8 @@ static int s32_get_group_pins(struct pinctrl_dev *pctldev, struct s32_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev); const struct s32_pinctrl_soc_info *info = ipctl->info; - *pins = info->groups[selector].pin_ids; - *npins = info->groups[selector].npins; + *pins = info->groups[selector].data.pins; + *npins = info->groups[selector].data.npins; return 0; } @@ -314,23 +314,23 @@ static int s32_pmx_set(struct pinctrl_dev *pctldev, unsigned int selector, grp = &info->groups[group]; dev_dbg(ipctl->dev, "set mux for function %s group %s\n", - info->functions[selector].name, grp->name); + info->functions[selector].name, grp->data.name); /* Check beforehand so we don't have a partial config. */ - for (i = 0; i < grp->npins; i++) { - if (s32_check_pin(pctldev, grp->pin_ids[i]) != 0) { + for (i = 0; i < grp->data.npins; i++) { + if (s32_check_pin(pctldev, grp->data.pins[i]) != 0) { dev_err(info->dev, "invalid pin: %u in group: %u\n", - grp->pin_ids[i], group); + grp->data.pins[i], group); return -EINVAL; } } - for (i = 0, ret = 0; i < grp->npins && !ret; i++) { - ret = s32_regmap_update(pctldev, grp->pin_ids[i], + for (i = 0, ret = 0; i < grp->data.npins && !ret; i++) { + ret = s32_regmap_update(pctldev, grp->data.pins[i], S32_MSCR_SSS_MASK, grp->pin_sss[i]); if (ret) { dev_err(info->dev, "Failed to set pin %u\n", - grp->pin_ids[i]); + grp->data.pins[i]); return ret; } } @@ -606,8 +606,8 @@ static int s32_pconf_group_set(struct pinctrl_dev *pctldev, unsigned int selecto int i, ret; grp = &info->groups[selector]; - for (i = 0; i < grp->npins; i++) { - ret = s32_pinconf_mscr_update(pctldev, grp->pin_ids[i], + for (i = 0; i < grp->data.npins; i++) { + ret = s32_pinconf_mscr_update(pctldev, grp->data.pins[i], configs, num_configs); if (ret) return ret; @@ -641,9 +641,9 @@ static void s32_pinconf_group_dbg_show(struct pinctrl_dev *pctldev, seq_puts(s, "\n"); grp = &info->groups[selector]; - for (i = 0; i < grp->npins; i++) { - name = pin_get_name(pctldev, grp->pin_ids[i]); - ret = s32_regmap_read(pctldev, grp->pin_ids[i], &config); + for (i = 0; i < grp->data.npins; i++) { + name = pin_get_name(pctldev, grp->data.pins[i]); + ret = s32_regmap_read(pctldev, grp->data.pins[i], &config); if (ret) return; seq_printf(s, "%s: 0x%x\n", name, config); @@ -736,6 +736,7 @@ static int s32_pinctrl_parse_groups(struct device_node *np, const __be32 *p; struct device *dev; struct property *prop; + unsigned int *pins, *sss; int i, npins; u32 pinmux; @@ -744,38 +745,38 @@ static int s32_pinctrl_parse_groups(struct device_node *np, dev_dbg(dev, "group: %pOFn\n", np); /* Initialise group */ - grp->name = np->name; + grp->data.name = np->name; npins = of_property_count_elems_of_size(np, "pinmux", sizeof(u32)); if (npins < 0) { dev_err(dev, "Failed to read 'pinmux' property in node %s.\n", - grp->name); + grp->data.name); return -EINVAL; } if (!npins) { - dev_err(dev, "The group %s has no pins.\n", grp->name); + dev_err(dev, "The group %s has no pins.\n", grp->data.name); return -EINVAL; } - grp->npins = npins; + grp->data.npins = npins; - grp->pin_ids = devm_kcalloc(info->dev, grp->npins, - sizeof(unsigned int), GFP_KERNEL); - grp->pin_sss = devm_kcalloc(info->dev, grp->npins, - sizeof(unsigned int), GFP_KERNEL); - if (!grp->pin_ids || !grp->pin_sss) + pins = devm_kcalloc(info->dev, npins, sizeof(*pins), GFP_KERNEL); + sss = devm_kcalloc(info->dev, npins, sizeof(*sss), GFP_KERNEL); + if (!pins || !sss) return -ENOMEM; i = 0; of_property_for_each_u32(np, "pinmux", prop, p, pinmux) { - grp->pin_ids[i] = get_pin_no(pinmux); - grp->pin_sss[i] = get_pin_func(pinmux); + pins[i] = get_pin_no(pinmux); + sss[i] = get_pin_func(pinmux); - dev_dbg(info->dev, "pin-id: 0x%x, sss: 0x%x", - grp->pin_ids[i], grp->pin_sss[i]); + dev_dbg(info->dev, "pin: 0x%x, sss: 0x%x", pins[i], sss[i]); i++; } + grp->data.pins = pins; + grp->pin_sss = sss; + return 0; } -- GitLab From 966b0e64b6891aa785d9e44abad069d515f6cb8f Mon Sep 17 00:00:00 2001 From: Chester Lin Date: Mon, 27 Mar 2023 14:27:53 +0800 Subject: [PATCH 1406/5631] pinctrl: s32cc: Use generic struct data to describe pin function Replace struct s32_pmx_func with generic struct pinfunction since they have the same data fields. Suggested-by: Andy Shevchenko Signed-off-by: Chester Lin Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230327062754.3326-5-clin@suse.com Signed-off-by: Linus Walleij --- drivers/pinctrl/nxp/pinctrl-s32.h | 14 +------------- drivers/pinctrl/nxp/pinctrl-s32cc.c | 18 +++++++++++------- 2 files changed, 12 insertions(+), 20 deletions(-) diff --git a/drivers/pinctrl/nxp/pinctrl-s32.h b/drivers/pinctrl/nxp/pinctrl-s32.h index 850cd668f406..2f7aecd462e4 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32.h +++ b/drivers/pinctrl/nxp/pinctrl-s32.h @@ -24,18 +24,6 @@ struct s32_pin_group { unsigned int *pin_sss; }; -/** - * struct s32_pmx_func - describes S32 pinmux functions - * @name: the name of this specific function - * @groups: corresponding pin groups - * @num_groups: the number of groups - */ -struct s32_pmx_func { - const char *name; - const char **groups; - unsigned int num_groups; -}; - /** * struct s32_pin_range - pin ID range for each memory region. * @start: start pin ID @@ -52,7 +40,7 @@ struct s32_pinctrl_soc_info { unsigned int npins; struct s32_pin_group *groups; unsigned int ngroups; - struct s32_pmx_func *functions; + struct pinfunction *functions; unsigned int nfunctions; unsigned int grp_index; const struct s32_pin_range *mem_pin_ranges; diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index e65c88162d7f..8373468719b6 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -364,7 +364,7 @@ static int s32_pmx_get_groups(struct pinctrl_dev *pctldev, const struct s32_pinctrl_soc_info *info = ipctl->info; *groups = info->functions[selector].groups; - *num_groups = info->functions[selector].num_groups; + *num_groups = info->functions[selector].ngroups; return 0; } @@ -785,8 +785,9 @@ static int s32_pinctrl_parse_functions(struct device_node *np, u32 index) { struct device_node *child; - struct s32_pmx_func *func; + struct pinfunction *func; struct s32_pin_group *grp; + const char **groups; u32 i = 0; int ret = 0; @@ -796,18 +797,19 @@ static int s32_pinctrl_parse_functions(struct device_node *np, /* Initialise function */ func->name = np->name; - func->num_groups = of_get_child_count(np); - if (func->num_groups == 0) { + func->ngroups = of_get_child_count(np); + if (func->ngroups == 0) { dev_err(info->dev, "no groups defined in %pOF\n", np); return -EINVAL; } - func->groups = devm_kcalloc(info->dev, func->num_groups, + + groups = devm_kcalloc(info->dev, func->ngroups, sizeof(*func->groups), GFP_KERNEL); - if (!func->groups) + if (!groups) return -ENOMEM; for_each_child_of_node(np, child) { - func->groups[i] = child->name; + groups[i] = child->name; grp = &info->groups[info->grp_index++]; ret = s32_pinctrl_parse_groups(child, grp, info); if (ret) @@ -815,6 +817,8 @@ static int s32_pinctrl_parse_functions(struct device_node *np, i++; } + func->groups = groups; + return 0; } -- GitLab From 94df03a4527611bfa7b461f2ba45370341e763b8 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sat, 25 Mar 2023 12:54:40 +0100 Subject: [PATCH 1407/5631] dt-bindings: pinctrl: Convert Amlogic Meson pinctrl binding Convert Amlogic Meson pin controller binding to yaml. Reviewed-by: Rob Herring Signed-off-by: Heiner Kallweit Link: https://lore.kernel.org/r/dd29c1b7-05db-dd98-df40-20a238d89a96@gmail.com Signed-off-by: Linus Walleij --- .../pinctrl/amlogic,meson-pinctrl-a1.yaml | 67 +++++++++++++ .../pinctrl/amlogic,meson-pinctrl-common.yaml | 57 +++++++++++ .../amlogic,meson-pinctrl-g12a-aobus.yaml | 68 ++++++++++++++ .../amlogic,meson-pinctrl-g12a-periphs.yaml | 72 ++++++++++++++ .../pinctrl/amlogic,meson8-pinctrl-aobus.yaml | 76 +++++++++++++++ .../pinctrl/amlogic,meson8-pinctrl-cbus.yaml | 78 +++++++++++++++ .../bindings/pinctrl/meson,pinctrl.txt | 94 ------------------- 7 files changed, 418 insertions(+), 94 deletions(-) create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-a1.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-common.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-aobus.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-periphs.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-aobus.yaml create mode 100644 Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml delete mode 100644 Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-a1.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-a1.yaml new file mode 100644 index 000000000000..99080c9eaac3 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-a1.yaml @@ -0,0 +1,67 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson-pinctrl-a1.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson A1 pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: amlogic,meson-pinctrl-common.yaml# + +properties: + compatible: + enum: + - amlogic,meson-a1-periphs-pinctrl + - amlogic,meson-s4-periphs-pinctrl + +required: + - compatible + +patternProperties: + "^bank@[0-9a-z]+$": + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-gpio + + unevaluatedProperties: false + + properties: + reg: + maxItems: 2 + + reg-names: + items: + - const: mux + - const: gpio + +unevaluatedProperties: + type: object + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-pins + +examples: + - | + periphs_pinctrl: pinctrl { + compatible = "amlogic,meson-a1-periphs-pinctrl"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + bank@400 { + reg = <0x0400 0x003c>, + <0x0480 0x0118>; + reg-names = "mux", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&periphs_pinctrl 0 0 62>; + }; + + cec_ao_a_h_pins: cec_ao_a_h { + mux { + groups = "cec_ao_a_h"; + function = "cec_ao_a_h"; + bias-disable; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-common.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-common.yaml new file mode 100644 index 000000000000..a7b29ef0bab6 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-common.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson-pinctrl-common.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: pinctrl.yaml# + +properties: + ranges: true + + "#address-cells": + enum: [1, 2] + + "#size-cells": + enum: [1, 2] + +required: + - ranges + - "#address-cells" + - "#size-cells" + +additionalProperties: true + +$defs: + meson-gpio: + type: object + + properties: + gpio-controller: true + + "#gpio-cells": + const: 2 + + gpio-ranges: + maxItems: 1 + + required: + - reg + - reg-names + - gpio-controller + - "#gpio-cells" + - gpio-ranges + + meson-pins: + type: object + additionalProperties: + type: object + allOf: + - $ref: pincfg-node.yaml# + - $ref: pinmux-node.yaml# diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-aobus.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-aobus.yaml new file mode 100644 index 000000000000..7c9c94ec5b7b --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-aobus.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson-pinctrl-g12a-aobus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson G12 AOBUS pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: amlogic,meson-pinctrl-common.yaml# + +properties: + compatible: + enum: + - amlogic,meson-g12a-aobus-pinctrl + +required: + - compatible + +patternProperties: + "^bank@[0-9a-z]+$": + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-gpio + + unevaluatedProperties: false + + properties: + reg: + maxItems: 3 + + reg-names: + items: + - const: mux + - const: ds + - const: gpio + +unevaluatedProperties: + type: object + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-pins + +examples: + - | + ao_pinctrl: pinctrl { + compatible = "amlogic,meson-g12a-aobus-pinctrl"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + bank@14 { + reg = <0x14 0x8>, + <0x1c 0x8>, + <0x24 0x14>; + reg-names = "mux", "ds", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&ao_pinctrl 0 0 15>; + }; + + cec_ao_a_h_pins: cec_ao_a_h { + mux { + groups = "cec_ao_a_h"; + function = "cec_ao_a_h"; + bias-disable; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-periphs.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-periphs.yaml new file mode 100644 index 000000000000..4bcb8b60420f --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson-pinctrl-g12a-periphs.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson-pinctrl-g12a-periphs.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson G12 PERIPHS pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: amlogic,meson-pinctrl-common.yaml# + +properties: + compatible: + enum: + - amlogic,meson-g12a-periphs-pinctrl + +required: + - compatible + +patternProperties: + "^bank@[0-9a-z]+$": + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-gpio + + unevaluatedProperties: false + + properties: + reg: + maxItems: 5 + + reg-names: + items: + - const: gpio + - const: pull + - const: pull-enable + - const: mux + - const: ds + +unevaluatedProperties: + type: object + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-pins + +examples: + - | + periphs_pinctrl: pinctrl { + compatible = "amlogic,meson-g12a-periphs-pinctrl"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + bank@40 { + reg = <0x40 0x4c>, + <0xe8 0x18>, + <0x120 0x18>, + <0x2c0 0x40>, + <0x340 0x1c>; + reg-names = "gpio", "pull", "pull-enable", "mux", "ds"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&periphs_pinctrl 0 0 86>; + }; + + cec_ao_a_h_pins: cec_ao_a_h { + mux { + groups = "cec_ao_a_h"; + function = "cec_ao_a_h"; + bias-disable; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-aobus.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-aobus.yaml new file mode 100644 index 000000000000..32d99c9b6afc --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-aobus.yaml @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson8-pinctrl-aobus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson8 AOBUS pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: amlogic,meson-pinctrl-common.yaml# + +properties: + compatible: + oneOf: + - enum: + - amlogic,meson8-aobus-pinctrl + - amlogic,meson8b-aobus-pinctrl + - amlogic,meson-gxbb-aobus-pinctrl + - amlogic,meson-gxl-aobus-pinctrl + - amlogic,meson-axg-aobus-pinctrl + - items: + - const: amlogic,meson8m2-aobus-pinctrl + - const: amlogic,meson8-aobus-pinctrl + +required: + - compatible + +patternProperties: + "^bank@[0-9a-z]+$": + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-gpio + + unevaluatedProperties: false + + properties: + reg: + maxItems: 3 + + reg-names: + items: + - const: mux + - const: pull + - const: gpio + +unevaluatedProperties: + type: object + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-pins + +examples: + - | + pinctrl_aobus: pinctrl { + compatible = "amlogic,meson8-aobus-pinctrl"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + bank@14 { + reg = <0x14 0x4>, + <0x2c 0x4>, + <0x24 0x8>; + reg-names = "mux", "pull", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_aobus 0 0 16>; + }; + + cec_ao_a_h_pins: cec_ao_a_h { + mux { + groups = "cec_ao_a_h"; + function = "cec_ao_a_h"; + bias-disable; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml new file mode 100644 index 000000000000..d0441051f34a --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/amlogic,meson8-pinctrl-cbus.yaml @@ -0,0 +1,78 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pinctrl/amlogic,meson8-pinctrl-cbus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson8 CBUS pinmux controller + +maintainers: + - Neil Armstrong + +allOf: + - $ref: amlogic,meson-pinctrl-common.yaml# + +properties: + compatible: + oneOf: + - enum: + - amlogic,meson8-cbus-pinctrl + - amlogic,meson8b-cbus-pinctrl + - amlogic,meson-gxbb-periphs-pinctrl + - amlogic,meson-gxl-periphs-pinctrl + - amlogic,meson-axg-periphs-pinctrl + - items: + - const: amlogic,meson8m2-cbus-pinctrl + - const: amlogic,meson8-cbus-pinctrl + +required: + - compatible + +patternProperties: + "^bank@[0-9a-z]+$": + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-gpio + + unevaluatedProperties: false + + properties: + reg: + maxItems: 4 + + reg-names: + items: + - const: mux + - const: pull + - const: pull-enable + - const: gpio + +unevaluatedProperties: + type: object + $ref: amlogic,meson-pinctrl-common.yaml#/$defs/meson-pins + +examples: + - | + pinctrl_cbus: pinctrl { + compatible = "amlogic,meson8-cbus-pinctrl"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + bank@80b0 { + reg = <0x80b0 0x28>, + <0x80e8 0x18>, + <0x8120 0x18>, + <0x8030 0x30>; + reg-names = "mux", "pull", "pull-enable", "gpio"; + gpio-controller; + #gpio-cells = <2>; + gpio-ranges = <&pinctrl_cbus 0 0 120>; + }; + + cec_ao_a_h_pins: cec_ao_a_h { + mux { + groups = "cec_ao_a_h"; + function = "cec_ao_a_h"; + bias-disable; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt deleted file mode 100644 index 8146193bd8ac..000000000000 --- a/Documentation/devicetree/bindings/pinctrl/meson,pinctrl.txt +++ /dev/null @@ -1,94 +0,0 @@ -== Amlogic Meson pinmux controller == - -Required properties for the root node: - - compatible: one of "amlogic,meson8-cbus-pinctrl" - "amlogic,meson8b-cbus-pinctrl" - "amlogic,meson8m2-cbus-pinctrl" - "amlogic,meson8-aobus-pinctrl" - "amlogic,meson8b-aobus-pinctrl" - "amlogic,meson8m2-aobus-pinctrl" - "amlogic,meson-gxbb-periphs-pinctrl" - "amlogic,meson-gxbb-aobus-pinctrl" - "amlogic,meson-gxl-periphs-pinctrl" - "amlogic,meson-gxl-aobus-pinctrl" - "amlogic,meson-axg-periphs-pinctrl" - "amlogic,meson-axg-aobus-pinctrl" - "amlogic,meson-g12a-periphs-pinctrl" - "amlogic,meson-g12a-aobus-pinctrl" - "amlogic,meson-a1-periphs-pinctrl" - "amlogic,meson-s4-periphs-pinctrl" - - reg: address and size of registers controlling irq functionality - -=== GPIO sub-nodes === - -The GPIO bank for the controller is represented as a sub-node and it acts as a -GPIO controller. - -Required properties for sub-nodes are: - - reg: should contain a list of address and size, one tuple for each entry - in reg-names. - - reg-names: an array of strings describing the "reg" entries. - Must contain "mux" and "gpio". - May contain "pull", "pull-enable" and "ds" when appropriate. - - gpio-controller: identifies the node as a gpio controller - - #gpio-cells: must be 2 - -=== Other sub-nodes === - -Child nodes without the "gpio-controller" represent some desired -configuration for a pin or a group. Those nodes can be pinmux nodes or -configuration nodes. - -Required properties for pinmux nodes are: - - groups: a list of pinmux groups. The list of all available groups - depends on the SoC and can be found in driver sources. - - function: the name of a function to activate for the specified set - of groups. The list of all available functions depends on the SoC - and can be found in driver sources. - -Required properties for configuration nodes: - - pins: a list of pin names - -Configuration nodes support the following generic properties, as -described in file pinctrl-bindings.txt: - - "bias-disable" - - "bias-pull-up" - - "bias-pull-down" - - "output-enable" - - "output-disable" - - "output-low" - - "output-high" - -Optional properties : - - drive-strength-microamp: Drive strength for the specified pins in uA. - This property is only valid for G12A and newer. - -=== Example === - - pinctrl: pinctrl@c1109880 { - compatible = "amlogic,meson8-cbus-pinctrl"; - reg = <0xc1109880 0x10>; - #address-cells = <1>; - #size-cells = <1>; - ranges; - - gpio: banks@c11080b0 { - reg = <0xc11080b0 0x28>, - <0xc11080e8 0x18>, - <0xc1108120 0x18>, - <0xc1108030 0x30>; - reg-names = "mux", "pull", "pull-enable", "gpio"; - gpio-controller; - #gpio-cells = <2>; - }; - - nand { - mux { - groups = "nand_io", "nand_io_ce0", "nand_io_ce1", - "nand_io_rb0", "nand_ale", "nand_cle", - "nand_wen_clk", "nand_ren_clk", "nand_dqs", - "nand_ce2", "nand_ce3"; - function = "nand"; - }; - }; - }; -- GitLab From b5e2c507b06c9d36411845149162a804ae7b04a9 Mon Sep 17 00:00:00 2001 From: Yimin Gu Date: Tue, 28 Feb 2023 19:26:56 -0500 Subject: [PATCH 1408/5631] riscv: Kconfig: Allow RV32 to build with no MMU Some RISC-V 32bit cores do not have an MMU, and the kernel should be able to build for them. This patch enables the RV32 to be built with no MMU support. Signed-off-by: Yimin Gu CC: Jesse Taube Tested-by: Waldemar Brodkorb Signed-off-by: Jesse Taube Reviewed-by: Damien Le Moal Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230301002657.352637-3-Mr.Bossman075@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..d1f661425790 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -177,8 +177,8 @@ config MMU config PAGE_OFFSET hex - default 0xC0000000 if 32BIT - default 0x80000000 if 64BIT && !MMU + default 0xC0000000 if 32BIT && MMU + default 0x80000000 if !MMU default 0xff60000000000000 if 64BIT config KASAN_SHADOW_OFFSET @@ -279,7 +279,6 @@ config ARCH_RV32I select GENERIC_LIB_ASHRDI3 select GENERIC_LIB_LSHRDI3 select GENERIC_LIB_UCMPDI2 - select MMU config ARCH_RV64I bool "RV64I" -- GitLab From 77c0c966719f07f14c82f358745f77582580cdcd Mon Sep 17 00:00:00 2001 From: Jesse Taube Date: Tue, 28 Feb 2023 19:26:57 -0500 Subject: [PATCH 1409/5631] riscv: configs: Add nommu PHONY defconfig for RV32 32bit risc-v can be configured to run without MMU. Introduce rv32_nommu_virt_defconfig .PHONY target, that is based on nommu_virt_defconfig. This is similar to how rv32_defconfig is based on "defconfig". Suggested-by: Conor Dooley Signed-off-by: Jesse Taube Cc: Yimin Gu Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230301002657.352637-4-Mr.Bossman075@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Makefile | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6203c3378922..1b276f62f22b 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -174,3 +174,7 @@ rv64_randconfig: PHONY += rv32_defconfig rv32_defconfig: $(Q)$(MAKE) -f $(srctree)/Makefile defconfig 32-bit.config + +PHONY += rv32_nommu_virt_defconfig +rv32_nommu_virt_defconfig: + $(Q)$(MAKE) -f $(srctree)/Makefile nommu_virt_defconfig 32-bit.config -- GitLab From 25a4ce564921db0973b74c04e0ea23bd2ee12a3a Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Mon, 20 Feb 2023 16:06:22 +0100 Subject: [PATCH 1410/5631] dma-direct: cleanup parameters to dma_direct_optimal_gfp_mask Since both callers of dma_direct_optimal_gfp_mask() pass dev->coherent_dma_mask as the second argument, it is better to remove that parameter altogether. Not only is reducing number of parameters good for readability, but the new function signature is also more logical: The optimal flags depend only on data contained in struct device. While touching this code, let's also rename phys_mask to phys_limit in dma_direct_alloc_from_pool(), because it is indeed a limit. Signed-off-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- kernel/dma/direct.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 63859a101ed8..5595d1d5cdcc 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -44,10 +44,11 @@ u64 dma_direct_get_required_mask(struct device *dev) return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } -static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_limit) +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 *phys_limit) { - u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); + u64 dma_limit = min_not_zero( + dev->coherent_dma_mask, + dev->bus_dma_limit); /* * Optimistically try the zone that the physical address mask falls @@ -126,8 +127,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, if (is_swiotlb_for_alloc(dev)) return dma_direct_alloc_swiotlb(dev, size); - gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_limit); + gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit); page = dma_alloc_contiguous(dev, size, gfp); if (page) { if (!dma_coherent_ok(dev, page_to_phys(page), size) || @@ -172,14 +172,13 @@ static void *dma_direct_alloc_from_pool(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { struct page *page; - u64 phys_mask; + u64 phys_limit; void *ret; if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))) return NULL; - gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); + gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit); page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok); if (!page) return NULL; -- GitLab From 479623fd0c5ad86a43ae11670f7da2a7c462acd4 Mon Sep 17 00:00:00 2001 From: Desnes Nunes Date: Thu, 16 Mar 2023 11:09:10 -0300 Subject: [PATCH 1411/5631] dma-debug: small dma_debug_entry's comment and variable name updates Small update on dma_debug_entry's struct commentary and also standardize the usage of 'dma_addr' variable name from debug_dma_map_page() on debug_dma_unmap_page(), and similarly on debug_dma_free_coherent() Signed-off-by: Desnes Nunes Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 18c93c2276ca..9aa5100d0d7e 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -53,6 +53,7 @@ enum map_err_types { * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping * @list: node on pre-allocated free_entries list * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent + * @dev_addr: dma address * @size: length of the mapping * @type: single, page, sg, coherent * @direction: enum dma_data_direction @@ -1262,13 +1263,13 @@ void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) } EXPORT_SYMBOL(debug_dma_mapping_error); -void debug_dma_unmap_page(struct device *dev, dma_addr_t addr, +void debug_dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, int direction) { struct dma_debug_entry ref = { .type = dma_debug_single, .dev = dev, - .dev_addr = addr, + .dev_addr = dma_addr, .size = size, .direction = direction, }; @@ -1403,13 +1404,13 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, } void debug_dma_free_coherent(struct device *dev, size_t size, - void *virt, dma_addr_t addr) + void *virt, dma_addr_t dma_addr) { struct dma_debug_entry ref = { .type = dma_debug_coherent, .dev = dev, .offset = offset_in_page(virt), - .dev_addr = addr, + .dev_addr = dma_addr, .size = size, .direction = DMA_BIDIRECTIONAL, }; -- GitLab From bd89d69a529fbef3559a16dbe4cee4b04225136a Mon Sep 17 00:00:00 2001 From: Desnes Nunes Date: Thu, 16 Mar 2023 11:09:11 -0300 Subject: [PATCH 1412/5631] dma-debug: add cacheline to user/kernel space dump messages Having the cacheline also printed on the debug_dma_dump_mappings() and dump_show() is useful for debugging. Furthermore, this also standardizes the messages shown on both dump functions. Signed-off-by: Desnes Nunes Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 122 ++++++++++++++++++++++++--------------------- 1 file changed, 64 insertions(+), 58 deletions(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 9aa5100d0d7e..676142072d99 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -396,37 +396,6 @@ static unsigned long long phys_addr(struct dma_debug_entry *entry) return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset; } -/* - * Dump mapping entries for debugging purposes - */ -void debug_dma_dump_mappings(struct device *dev) -{ - int idx; - - for (idx = 0; idx < HASH_SIZE; idx++) { - struct hash_bucket *bucket = &dma_entry_hash[idx]; - struct dma_debug_entry *entry; - unsigned long flags; - - spin_lock_irqsave(&bucket->lock, flags); - - list_for_each_entry(entry, &bucket->list, list) { - if (!dev || dev == entry->dev) { - dev_info(entry->dev, - "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n", - type2name[entry->type], idx, - phys_addr(entry), entry->pfn, - entry->dev_addr, entry->size, - dir2name[entry->direction], - maperr2str[entry->map_err_type]); - } - } - - spin_unlock_irqrestore(&bucket->lock, flags); - cond_resched(); - } -} - /* * For each mapping (initial cacheline in the case of * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a @@ -547,6 +516,70 @@ static void active_cacheline_remove(struct dma_debug_entry *entry) spin_unlock_irqrestore(&radix_lock, flags); } +/* + * Dump mappings entries on kernel space for debugging purposes + */ +void debug_dma_dump_mappings(struct device *dev) +{ + int idx; + phys_addr_t cln; + + for (idx = 0; idx < HASH_SIZE; idx++) { + struct hash_bucket *bucket = &dma_entry_hash[idx]; + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&bucket->lock, flags); + list_for_each_entry(entry, &bucket->list, list) { + if (!dev || dev == entry->dev) { + cln = to_cacheline_number(entry); + dev_info(entry->dev, + "%s idx %d P=%llx N=%lx D=%llx L=%llx cln=%llx %s %s\n", + type2name[entry->type], idx, + phys_addr(entry), entry->pfn, + entry->dev_addr, entry->size, + cln, dir2name[entry->direction], + maperr2str[entry->map_err_type]); + } + } + spin_unlock_irqrestore(&bucket->lock, flags); + + cond_resched(); + } +} + +/* + * Dump mappings entries on user space via debugfs + */ +static int dump_show(struct seq_file *seq, void *v) +{ + int idx; + phys_addr_t cln; + + for (idx = 0; idx < HASH_SIZE; idx++) { + struct hash_bucket *bucket = &dma_entry_hash[idx]; + struct dma_debug_entry *entry; + unsigned long flags; + + spin_lock_irqsave(&bucket->lock, flags); + list_for_each_entry(entry, &bucket->list, list) { + cln = to_cacheline_number(entry); + seq_printf(seq, + "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx cln=%llx %s %s\n", + dev_driver_string(entry->dev), + dev_name(entry->dev), + type2name[entry->type], idx, + phys_addr(entry), entry->pfn, + entry->dev_addr, entry->size, + cln, dir2name[entry->direction], + maperr2str[entry->map_err_type]); + } + spin_unlock_irqrestore(&bucket->lock, flags); + } + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dump); + /* * Wrapper function for adding an entry to the hash. * This function takes care of locking itself. @@ -765,33 +798,6 @@ static const struct file_operations filter_fops = { .llseek = default_llseek, }; -static int dump_show(struct seq_file *seq, void *v) -{ - int idx; - - for (idx = 0; idx < HASH_SIZE; idx++) { - struct hash_bucket *bucket = &dma_entry_hash[idx]; - struct dma_debug_entry *entry; - unsigned long flags; - - spin_lock_irqsave(&bucket->lock, flags); - list_for_each_entry(entry, &bucket->list, list) { - seq_printf(seq, - "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx %s %s\n", - dev_name(entry->dev), - dev_driver_string(entry->dev), - type2name[entry->type], idx, - phys_addr(entry), entry->pfn, - entry->dev_addr, entry->size, - dir2name[entry->direction], - maperr2str[entry->map_err_type]); - } - spin_unlock_irqrestore(&bucket->lock, flags); - } - return 0; -} -DEFINE_SHOW_ATTRIBUTE(dump); - static int __init dma_debug_fs_init(void) { struct dentry *dentry = debugfs_create_dir("dma-api", NULL); -- GitLab From cf34b880a66e3581300b997df25a7c12f7cfe7d7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Mar 2023 20:16:06 +0200 Subject: [PATCH 1413/5631] powerpc/fsl: fix compiler warning in fsl_wakeup_sys_init() Commit c93bd175414a ("powerpc/fsl: move to use bus_get_dev_root()") changed to use bus_get_dev_root() but didn't consider that the function can fail and return an uninitialized value of ret (hint, the function can never fail, but the compiler doesn't know that.) Fix this up by setting ret to -EINVAL just in case something really goes wrong with the call to bus_get_dev_root(). Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: linuxppc-dev@lists.ozlabs.org Fixes: c93bd175414a ("powerpc/fsl: move to use bus_get_dev_root()") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303280045.4oaaezcn-lkp@intel.com/ Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230327181606.1424846-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c index 147b5d8bb904..ce6c739c51e5 100644 --- a/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c +++ b/arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c @@ -117,7 +117,7 @@ static struct device_attribute mpic_attributes = __ATTR(timer_wakeup, 0644, static int __init fsl_wakeup_sys_init(void) { struct device *dev_root; - int ret; + int ret = -EINVAL; fsl_wakeup = kzalloc(sizeof(struct fsl_mpic_timer_wakeup), GFP_KERNEL); if (!fsl_wakeup) -- GitLab From 2f9e87f5a2941b259336c7ea6c5a1499ede4554a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 23 Mar 2023 20:26:40 +0200 Subject: [PATCH 1414/5631] driver core: Add a comment to set_primary_fwnode() on nullifying Explain what parent && fn == parent->fwnode conditional does. With this refactor the code a bit. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230323182640.61085-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index f1889b9cab45..b59692a4d809 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4982,9 +4982,13 @@ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) } else { if (fwnode_is_primary(fn)) { dev->fwnode = fn->secondary; + + /* Skip nullifying fn->secondary if the primary is shared */ + if (parent && fn == parent->fwnode) + return; + /* Set fn->secondary = NULL, so fn remains the primary fwnode */ - if (!(parent && fn == parent->fwnode)) - fn->secondary = NULL; + fn->secondary = NULL; } else { dev->fwnode = NULL; } -- GitLab From 517d4927aabe488144863e72b52bb3e506fecd34 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 09:45:26 +0100 Subject: [PATCH 1415/5631] driver core: bus: constify class_unregister/destroy() The class_unregister() and class_destroy() function should be taking a const * to struct class, not just a *, so fix that up. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230325084526.3622123-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 8 ++++---- include/linux/device/class.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 0f8938a17144..8ae91e118827 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -142,13 +142,13 @@ static void klist_class_dev_put(struct klist_node *n) put_device(dev); } -static int class_add_groups(struct class *cls, +static int class_add_groups(const struct class *cls, const struct attribute_group **groups) { return sysfs_create_groups(&cls->p->subsys.kobj, groups); } -static void class_remove_groups(struct class *cls, +static void class_remove_groups(const struct class *cls, const struct attribute_group **groups) { return sysfs_remove_groups(&cls->p->subsys.kobj, groups); @@ -206,7 +206,7 @@ int class_register(struct class *cls) } EXPORT_SYMBOL_GPL(class_register); -void class_unregister(struct class *cls) +void class_unregister(const struct class *cls) { pr_debug("device class '%s': unregistering\n", cls->name); class_remove_groups(cls, cls->class_groups); @@ -265,7 +265,7 @@ EXPORT_SYMBOL_GPL(class_create); * Note, the pointer to be destroyed must have been created with a call * to class_create(). */ -void class_destroy(struct class *cls) +void class_destroy(const struct class *cls) { if (IS_ERR_OR_NULL(cls)) return; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index d3960733c0fa..73436c578d37 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -83,7 +83,7 @@ struct class_dev_iter { extern struct kobject *sysfs_dev_block_kobj; int __must_check class_register(struct class *class); -void class_unregister(struct class *class); +void class_unregister(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -231,6 +231,6 @@ int __must_check class_interface_register(struct class_interface *); void class_interface_unregister(struct class_interface *); struct class * __must_check class_create(const char *name); -void class_destroy(struct class *cls); +void class_destroy(const struct class *cls); #endif /* _DEVICE_CLASS_H_ */ -- GitLab From 16313403d873ff17a587818b61f84c8cb4971cef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 27 Mar 2023 16:54:14 +0200 Subject: [PATCH 1416/5631] staging: iio: resolver: ads1210: fix config mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As stated in the device datasheet [1], bits a0 and a1 have to be set to 1 for the configuration mode. [1]: https://www.analog.com/media/en/technical-documentation/data-sheets/ad2s1210.pdf Fixes: b19e9ad5e2cb9 ("staging:iio:resolver:ad2s1210 general driver cleanup") Cc: stable Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230327145414.1505537-1-nuno.sa@analog.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/iio/resolver/ad2s1210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c index e4cf42438487..636c45b12843 100644 --- a/drivers/staging/iio/resolver/ad2s1210.c +++ b/drivers/staging/iio/resolver/ad2s1210.c @@ -101,7 +101,7 @@ struct ad2s1210_state { static const int ad2s1210_mode_vals[4][2] = { [MOD_POS] = { 0, 0 }, [MOD_VEL] = { 0, 1 }, - [MOD_CONFIG] = { 1, 0 }, + [MOD_CONFIG] = { 1, 1 }, }; static inline void ad2s1210_set_mode(enum ad2s1210_mode mode, -- GitLab From 1068d4e910cc8e8d06dc04512287a59737292f40 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Mon, 27 Mar 2023 10:13:51 -0700 Subject: [PATCH 1417/5631] staging: rtl8192e: fix line ending with '(' Splitting function header to multiple lines because of 80 characters per line limit, results in ending the function call line with '('. This leads to CHECK reported by checkpatch.pl Move the first parameter right after the '(' in the function call line. Align the rest of the parameters to the opening parenthesis. Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230327171351.GA188288@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 1ce4c29dab13..155b54e93b1e 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -1910,10 +1910,9 @@ struct net_device *alloc_rtllib(int sizeof_priv); /* rtllib_tx.c */ -int rtllib_encrypt_fragment( - struct rtllib_device *ieee, - struct sk_buff *frag, - int hdr_len); +int rtllib_encrypt_fragment(struct rtllib_device *ieee, + struct sk_buff *frag, + int hdr_len); netdev_tx_t rtllib_xmit(struct sk_buff *skb, struct net_device *dev); void rtllib_txb_free(struct rtllib_txb *txb); -- GitLab From 5ceb51dae50666635d6e5dcd4cca9582e0826bf8 Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Mon, 27 Mar 2023 10:16:53 -0700 Subject: [PATCH 1418/5631] staging: rtl8192e: remove extra blank lines Remove the extra blank line in accordance with the Linux kernel coding-style regulations. These issues were reported by checkpatch.pl "CHECK: Please don't use multiple blank lines" Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230327171653.GA188371@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 155b54e93b1e..197c0a44ebd6 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -308,7 +308,6 @@ enum rt_op_mode { RT_OP_MODE_NO_LINK, }; - #define aSifsTime \ (((priv->rtllib->current_network.mode == IEEE_A) \ || (priv->rtllib->current_network.mode == IEEE_N_24G) \ @@ -653,7 +652,6 @@ struct rtllib_security { u16 flags; } __packed; - /* 802.11 data frame from AP * ,-------------------------------------------------------------------. * Bytes | 2 | 2 | 6 | 6 | 6 | 2 | 0..2312 | 4 | @@ -984,7 +982,6 @@ static inline u8 Frame_QoSTID(u8 *buf) (fc & RTLLIB_FCTL_FROMDS)) ? 30 : 24)))->field.tid; } - struct eapol { u8 snap[6]; u16 ethertype; @@ -1199,8 +1196,6 @@ struct bandwidth_autoswitch { bool bautoswitch_enable; }; - - #define REORDER_WIN_SIZE 128 #define REORDER_ENTRY_NUM 128 struct rx_reorder_entry { @@ -1372,7 +1367,6 @@ struct rt_intel_promisc_mode { bool fltr_src_sta_frame; }; - /*************** DRIVER STATUS *****/ #define STATUS_SCANNING 0 /*************** DRIVER STATUS *****/ @@ -1441,7 +1435,6 @@ struct rtllib_device { struct rx_reorder_entry RxReorderEntry[128]; struct list_head RxReorder_Unused_List; - /* Bookkeeping structures */ struct net_device_stats stats; struct rtllib_softmac_stats softmac_stats; @@ -1738,7 +1731,6 @@ struct rtllib_device { struct rtllib_assoc_response_frame *resp, struct rtllib_network *network); - /* check whether Tx hw resource available */ short (*check_nic_enough_desc)(struct net_device *dev, int queue_index); void (*SetBWModeHandler)(struct net_device *dev, @@ -1811,7 +1803,6 @@ struct rtllib_device { */ #define IEEE_SOFTMAC_BEACONS (1<<6) - static inline void *rtllib_priv(struct net_device *dev) { return ((struct rtllib_device *)netdev_priv(dev))->priv; @@ -1903,7 +1894,6 @@ static inline int rtllib_is_cck_rate(u8 rate) return 0; } - /* rtllib.c */ void free_rtllib(struct net_device *dev); struct net_device *alloc_rtllib(int sizeof_priv); @@ -2112,7 +2102,6 @@ static inline const char *escape_essid(const char *essid, u8 essid_len) /* fun with the built-in rtllib stack... */ bool rtllib_MgntDisconnect(struct rtllib_device *rtllib, u8 asRsn); - /* For the function is more related to hardware setting, it's better to use the * ieee handler to refer to it. */ -- GitLab From bf8d1ecccb297b81bcca980dcd04fc1fb74d4209 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:02:19 +0200 Subject: [PATCH 1419/5631] staging: rtl8192e: Remove rtl92e_config_phy Remove rtl92e_config_phy to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/5c433417b4e8e96a70c23a03bec30d26e45791d0.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 2 +- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 9 --------- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h | 1 - 3 files changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 1eb063fe660a..f4fdaeff2917 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -691,7 +691,7 @@ bool rtl92e_start_adapter(struct net_device *dev) } if (priv->rst_progress == RESET_TYPE_NORESET) { - rtStatus = rtl92e_config_phy(dev); + rtStatus = rtl92e_config_rf(dev); if (!rtStatus) { netdev_info(dev, "RF Config failed\n"); return rtStatus; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index bd302f5cb356..139d8268c8dc 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -468,15 +468,6 @@ void rtl92e_set_tx_power(struct net_device *dev, u8 channel) rtl92e_set_ofdm_tx_power(dev, powerlevelOFDM24G); } -bool rtl92e_config_phy(struct net_device *dev) -{ - bool rtStatus = true; - - rtStatus = rtl92e_config_rf(dev); - - return rtStatus; -} - u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath) { diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h index 498da6be3e4e..6c4c33ded6a9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.h @@ -39,7 +39,6 @@ bool rtl92e_check_bb_and_rf(struct net_device *dev, bool rtl92e_config_bb(struct net_device *dev); void rtl92e_get_tx_power(struct net_device *dev); void rtl92e_set_tx_power(struct net_device *dev, u8 channel); -bool rtl92e_config_phy(struct net_device *dev); u8 rtl92e_config_rf_path(struct net_device *dev, enum rf90_radio_path eRFPath); u8 rtl92e_set_channel(struct net_device *dev, u8 channel); -- GitLab From f57a7f1515828cb493efb0628537e98d0747da71 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:02:37 +0200 Subject: [PATCH 1420/5631] staging: rtl8192e: Remove _rtl92e_get_supported_wireless_mode Remove _rtl92e_get_supported_wireless_mode to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/f8470fff23d5870cbcda3d6f4978ba17016a8fe8.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index ecc3f0c6c267..12e5132fa788 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -593,18 +593,10 @@ static void _rtl92e_refresh_support_rate(struct r8192_priv *priv) } } -static u8 _rtl92e_get_supported_wireless_mode(struct net_device *dev) -{ - u8 ret = 0; - - ret = (WIRELESS_MODE_N_24G | WIRELESS_MODE_G | WIRELESS_MODE_B); - return ret; -} - void rtl92e_set_wireless_mode(struct net_device *dev, u8 wireless_mode) { struct r8192_priv *priv = rtllib_priv(dev); - u8 support_mode = _rtl92e_get_supported_wireless_mode(dev); + u8 support_mode = (WIRELESS_MODE_N_24G | WIRELESS_MODE_G | WIRELESS_MODE_B); if ((wireless_mode == WIRELESS_MODE_AUTO) || ((wireless_mode & support_mode) == 0)) { -- GitLab From 1b4217b400aedad80512c389c8aef4fe7bbc0119 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:02:45 +0200 Subject: [PATCH 1421/5631] staging: rtl8192e: Remove 5G wireless_mode in rtl92e_set_wireless_mode Remove wireless_mode == WIRELESS_MODE_N_5G as 5G is not supported by hardware and to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/693a34b187f21d9d48accd3b0b953dff2f0795eb.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 12e5132fa788..c03978353a90 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -624,12 +624,11 @@ void rtl92e_set_wireless_mode(struct net_device *dev, u8 wireless_mode) priv->rtllib->mode = wireless_mode; - if ((wireless_mode == WIRELESS_MODE_N_24G) || - (wireless_mode == WIRELESS_MODE_N_5G)) { + if (wireless_mode == WIRELESS_MODE_N_24G) priv->rtllib->ht_info->enable_ht = 1; - } else { + else priv->rtllib->ht_info->enable_ht = 0; - } + _rtl92e_refresh_support_rate(priv); } -- GitLab From 4648ac046624d7d59d51122277f50fed84923629 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:02:51 +0200 Subject: [PATCH 1422/5631] staging: rtl8192e: Remove unused if clauses in rtl92e_set_wireless_mode Equation (support_mode & WIRELESS_MODE_N_24G) will always be true. Remove resulting dead code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/359ed203ab08afe5c2f449f40d2958868b4e55b4.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 21 ++------------------ 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index c03978353a90..689a5e16eb4d 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -598,25 +598,8 @@ void rtl92e_set_wireless_mode(struct net_device *dev, u8 wireless_mode) struct r8192_priv *priv = rtllib_priv(dev); u8 support_mode = (WIRELESS_MODE_N_24G | WIRELESS_MODE_G | WIRELESS_MODE_B); - if ((wireless_mode == WIRELESS_MODE_AUTO) || - ((wireless_mode & support_mode) == 0)) { - if (support_mode & WIRELESS_MODE_N_24G) { - wireless_mode = WIRELESS_MODE_N_24G; - } else if (support_mode & WIRELESS_MODE_N_5G) { - wireless_mode = WIRELESS_MODE_N_5G; - } else if ((support_mode & WIRELESS_MODE_A)) { - wireless_mode = WIRELESS_MODE_A; - } else if ((support_mode & WIRELESS_MODE_G)) { - wireless_mode = WIRELESS_MODE_G; - } else if ((support_mode & WIRELESS_MODE_B)) { - wireless_mode = WIRELESS_MODE_B; - } else { - netdev_info(dev, - "%s(): Unsupported mode requested. Fallback to 802.11b\n", - __func__); - wireless_mode = WIRELESS_MODE_B; - } - } + if ((wireless_mode == WIRELESS_MODE_AUTO) || ((wireless_mode & support_mode) == 0)) + wireless_mode = WIRELESS_MODE_N_24G; if ((wireless_mode & (WIRELESS_MODE_B | WIRELESS_MODE_G)) == (WIRELESS_MODE_G | WIRELESS_MODE_B)) -- GitLab From 1bfa151cc0e10b717921630330dfd53f15b28b77 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:02:57 +0200 Subject: [PATCH 1423/5631] staging: rtl8192e: Remove wireless modes A, N_5G from _rtl92e_hwconfig Remove WIRELESS_MODE_N_5G and WIRELESS_MODE_A as those are not supported by hardware and to improve readability. Combine WIRELESS_MODE_G with default to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/ab96af426f090ac2fe4a2536b052fcf8a2e38aa8.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index f4fdaeff2917..1da14e737aa4 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -503,16 +503,6 @@ static void _rtl92e_hwconfig(struct net_device *dev) regRATR = RATE_ALL_CCK; regRRSR = RATE_ALL_CCK; break; - case WIRELESS_MODE_A: - regBwOpMode = BW_OPMODE_5G | BW_OPMODE_20MHZ; - regRATR = RATE_ALL_OFDM_AG; - regRRSR = RATE_ALL_OFDM_AG; - break; - case WIRELESS_MODE_G: - regBwOpMode = BW_OPMODE_20MHZ; - regRATR = RATE_ALL_CCK | RATE_ALL_OFDM_AG; - regRRSR = RATE_ALL_CCK | RATE_ALL_OFDM_AG; - break; case WIRELESS_MODE_AUTO: case WIRELESS_MODE_N_24G: regBwOpMode = BW_OPMODE_20MHZ; @@ -520,12 +510,7 @@ static void _rtl92e_hwconfig(struct net_device *dev) RATE_ALL_OFDM_1SS | RATE_ALL_OFDM_2SS; regRRSR = RATE_ALL_CCK | RATE_ALL_OFDM_AG; break; - case WIRELESS_MODE_N_5G: - regBwOpMode = BW_OPMODE_5G; - regRATR = RATE_ALL_OFDM_AG | RATE_ALL_OFDM_1SS | - RATE_ALL_OFDM_2SS; - regRRSR = RATE_ALL_OFDM_AG; - break; + case WIRELESS_MODE_G: default: regBwOpMode = BW_OPMODE_20MHZ; regRATR = RATE_ALL_CCK | RATE_ALL_OFDM_AG; -- GitLab From a993465cd1e3499bd1f5841dadfae354b8a95f06 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:03:06 +0200 Subject: [PATCH 1424/5631] staging: rtl8192e: Remove wireless modes A, N_5G from rtl92e_set_channel Remove WIRELESS_MODE_N_5G and WIRELESS_MODE_A as those are not supported by hardware and to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/aaaf832fe5f90ad2c618bef22c1bdbd5209c4359.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index 139d8268c8dc..dd666701138e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -696,15 +696,6 @@ u8 rtl92e_set_channel(struct net_device *dev, u8 channel) switch (priv->rtllib->mode) { - case WIRELESS_MODE_A: - case WIRELESS_MODE_N_5G: - if (channel <= 14) { - netdev_warn(dev, - "Channel %d not available in 802.11a.\n", - channel); - return false; - } - break; case WIRELESS_MODE_B: if (channel > 14) { netdev_warn(dev, -- GitLab From 35c2274d3417b837097d87901705abae4e121f7a Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 27 Mar 2023 23:03:14 +0200 Subject: [PATCH 1425/5631] staging: rtl8192e: Remove wireless mode WIRELESS_MODE_N_5G Remove WIRELESS_MODE_N_5G from equations as it is not supported by hardware and to improve readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/fdefd4d706493fa3f080550d31eb5bea3f4e1a7e.1679949171.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 +-- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 6 ++---- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 689a5e16eb4d..7506d7eb7b4c 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -581,8 +581,7 @@ static void _rtl92e_refresh_support_rate(struct r8192_priv *priv) { struct rtllib_device *ieee = priv->rtllib; - if (ieee->mode == WIRELESS_MODE_N_24G || - ieee->mode == WIRELESS_MODE_N_5G) { + if (ieee->mode == WIRELESS_MODE_N_24G) { memcpy(ieee->reg_dot11ht_oper_rate_set, ieee->reg_ht_supp_rate_set, 16); memcpy(ieee->reg_dot11tx_ht_oper_rate_set, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index d45808760638..b5f4d0230da7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -296,8 +296,7 @@ static void _rtl92e_dm_check_rate_adaptive(struct net_device *dev) if (pra->rate_adaptive_disabled) return; - if (!(priv->rtllib->mode == WIRELESS_MODE_N_24G || - priv->rtllib->mode == WIRELESS_MODE_N_5G)) + if (priv->rtllib->mode != WIRELESS_MODE_N_24G) return; if (priv->rtllib->state == RTLLIB_LINKED) { @@ -971,8 +970,7 @@ void rtl92e_dm_restore_state(struct net_device *dev) if (priv->rate_adaptive.rate_adaptive_disabled) return; - if (!(priv->rtllib->mode == WIRELESS_MODE_N_24G || - priv->rtllib->mode == WIRELESS_MODE_N_5G)) + if (priv->rtllib->mode != WIRELESS_MODE_N_24G) return; ratr_value = reg_ratr; ratr_value &= ~(RATE_ALL_OFDM_2SS); -- GitLab From c7177ef36c743923a093d6b0ffd73f1002fc7cd6 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Tue, 28 Mar 2023 00:49:06 +0500 Subject: [PATCH 1426/5631] staging: rtl8192u: remove change history from comments Remove the change history information as it is not required in the comments. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/95fff39231ebb2bb683c2a8f252a93f4845fffb1.1679945728.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r8192U_dm.c | 45 ---------------------------- 1 file changed, 45 deletions(-) diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c index 6a33ca02c3dc..b1ebb776fc42 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.c +++ b/drivers/staging/rtl8192u/r8192U_dm.c @@ -7,12 +7,6 @@ Module Name: Abstract: HW dynamic mechanism. - -Major Change History: - When Who What - ---------- --------------- ------------------------------- - 2008-05-14 amy create version 0 porting from windows code. - --*/ #include "r8192U.h" #include "r8192U_dm.h" @@ -274,11 +268,6 @@ void init_rate_adaptive(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/26/08 amy Create version 0 porting from windows code. - * *---------------------------------------------------------------------------*/ static void dm_check_rate_adaptive(struct net_device *dev) { @@ -1589,11 +1578,6 @@ static void dm_bb_initialgain_backup(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/15/2008 amy Create Version 0 porting from windows code. - * *---------------------------------------------------------------------------*/ static void dm_dig_init(struct net_device *dev) { @@ -1634,10 +1618,6 @@ static void dm_dig_init(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/27/2008 amy Create Version 0 porting from windows code. *---------------------------------------------------------------------------*/ static void dm_ctrl_initgain_byrssi(struct net_device *dev) { @@ -1850,11 +1830,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/28/2008 amy Create Version 0 porting from windows code. - * *---------------------------------------------------------------------------*/ static void dm_ctrl_initgain_byrssi_highpwr( struct net_device *dev) @@ -2269,11 +2244,6 @@ static void dm_ctstoself(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/28/2008 amy Create Version 0 porting from windows code. - * *---------------------------------------------------------------------------*/ static void dm_check_pbc_gpio(struct net_device *dev) { @@ -2303,11 +2273,6 @@ static void dm_check_pbc_gpio(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 01/30/2008 MHC Create Version 0. - * *---------------------------------------------------------------------------*/ void dm_rf_pathcheck_workitemcallback(struct work_struct *work) { @@ -2552,11 +2517,6 @@ static void dm_rxpath_sel_byrssi(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 05/28/2008 amy Create Version 0 porting from windows code. - * *---------------------------------------------------------------------------*/ static void dm_check_rx_path_selection(struct net_device *dev) { @@ -2871,11 +2831,6 @@ void dm_check_fsync(struct net_device *dev) * Output: NONE * * Return: NONE - * - * Revised History: - * When Who Remark - * 03/06/2008 Jacken Create Version 0. - * *--------------------------------------------------------------------------- */ static void dm_init_dynamic_txpower(struct net_device *dev) -- GitLab From a430e7757debd2c0ac096a808e4363eace287773 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Tue, 28 Mar 2023 00:49:07 +0500 Subject: [PATCH 1427/5631] staging: rtl8192u: remove commented out code Remove all of the commented out code lines as they are not being used and can be brought back in the future if they are ever needed again. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/e5e2fabde70d497cc8b683ff444854299180812b.1679945728.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r8192U_dm.c | 123 --------------------------- 1 file changed, 123 deletions(-) diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c index b1ebb776fc42..e5c0bece4bb4 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.c +++ b/drivers/staging/rtl8192u/r8192U_dm.c @@ -48,12 +48,8 @@ static void dm_init_bandwidth_autoswitch(struct net_device *dev); static void dm_bandwidth_autoswitch(struct net_device *dev); /* DM --> TX power control */ -/*static void dm_initialize_txpower_tracking(struct net_device *dev);*/ - static void dm_check_txpower_tracking(struct net_device *dev); -/*static void dm_txpower_reset_recovery(struct net_device *dev);*/ - /* DM --> Dynamic Init Gain by RSSI */ static void dm_dig_init(struct net_device *dev); static void dm_ctrl_initgain_byrssi(struct net_device *dev); @@ -68,7 +64,6 @@ static void dm_init_ctstoself(struct net_device *dev); /* DM --> EDCA turbo mode control */ static void dm_check_edca_turbo(struct net_device *dev); -/*static void dm_gpio_change_rf(struct net_device *dev);*/ /* DM --> Check PBC */ static void dm_check_pbc_gpio(struct net_device *dev); @@ -115,7 +110,6 @@ void init_hal_dm(struct net_device *dev) /* Initial TX Power Control for near/far range , add by amy 2008/05/15, porting from windows code. */ dm_init_dynamic_txpower(dev); init_rate_adaptive(dev); - /*dm_initialize_txpower_tracking(dev);*/ dm_dig_init(dev); dm_init_edca_turbo(dev); dm_init_bandwidth_autoswitch(dev); @@ -140,21 +134,6 @@ void dm_CheckRxAggregation(struct net_device *dev) unsigned long curTxOkCnt = 0; unsigned long curRxOkCnt = 0; -/* - if (pHalData->bForcedUsbRxAggr) { - if (pHalData->ForcedUsbRxAggrInfo == 0) { - if (pHalData->bCurrentRxAggrEnable) { - Adapter->HalFunc.HalUsbRxAggrHandler(Adapter, FALSE); - } - } else { - if (!pHalData->bCurrentRxAggrEnable || (pHalData->ForcedUsbRxAggrInfo != pHalData->LastUsbRxAggrInfoSetting)) { - Adapter->HalFunc.HalUsbRxAggrHandler(Adapter, TRUE); - } - } - return; - } - -*/ curTxOkCnt = priv->stats.txbytesunicast - lastTxOkCnt; curRxOkCnt = priv->stats.rxbytesunicast - lastRxOkCnt; @@ -188,10 +167,6 @@ void dm_CheckRxAggregation(struct net_device *dev) void hal_dm_watchdog(struct net_device *dev) { - /*struct r8192_priv *priv = ieee80211_priv(dev);*/ - - /*static u8 previous_bssid[6] ={0};*/ - /*Add by amy 2008/05/15 ,porting from windows code.*/ dm_check_rate_adaptive(dev); dm_dynamic_txpower(dev); @@ -293,7 +268,6 @@ static void dm_check_rate_adaptive(struct net_device *dev) return; if (priv->ieee80211->state == IEEE80211_LINKED) { - /*RT_TRACE(COMP_RATE, "dm_CheckRateAdaptive(): \t");*/ /* Check whether Short GI is enabled */ bshort_gi_enabled = (pHTInfo->bCurTxBW40MHz && pHTInfo->bCurShortGI40MHz) || @@ -340,36 +314,27 @@ static void dm_check_rate_adaptive(struct net_device *dev) (pra->low_rssi_thresh_for_ra40M):(pra->low_rssi_thresh_for_ra20M); } - /*DbgPrint("[DM] THresh H/L=%d/%d\n\r", RATR.HighRSSIThreshForRA, RATR.LowRSSIThreshForRA);*/ if (priv->undecorated_smoothed_pwdb >= (long)HighRSSIThreshForRA) { - /*DbgPrint("[DM] RSSI=%d STA=HIGH\n\r", pHalData->UndecoratedSmoothedPWDB);*/ pra->ratr_state = DM_RATR_STA_HIGH; targetRATR = pra->upper_rssi_threshold_ratr; } else if (priv->undecorated_smoothed_pwdb >= (long)LowRSSIThreshForRA) { - /*DbgPrint("[DM] RSSI=%d STA=Middle\n\r", pHalData->UndecoratedSmoothedPWDB);*/ pra->ratr_state = DM_RATR_STA_MIDDLE; targetRATR = pra->middle_rssi_threshold_ratr; } else { - /*DbgPrint("[DM] RSSI=%d STA=LOW\n\r", pHalData->UndecoratedSmoothedPWDB);*/ pra->ratr_state = DM_RATR_STA_LOW; targetRATR = pra->low_rssi_threshold_ratr; } /* cosa add for test */ if (pra->ping_rssi_enable) { - /*pHalData->UndecoratedSmoothedPWDB = 19;*/ if (priv->undecorated_smoothed_pwdb < (long)(pra->ping_rssi_thresh_for_ra+5)) { if ((priv->undecorated_smoothed_pwdb < (long)pra->ping_rssi_thresh_for_ra) || ping_rssi_state) { - /*DbgPrint("TestRSSI = %d, set RATR to 0x%x\n", pHalData->UndecoratedSmoothedPWDB, pRA->TestRSSIRATR);*/ pra->ratr_state = DM_RATR_STA_LOW; targetRATR = pra->ping_rssi_ratr; ping_rssi_state = 1; } - /*else - DbgPrint("TestRSSI is between the range.\n");*/ } else { - /*DbgPrint("TestRSSI Recover to 0x%x\n", targetRATR);*/ ping_rssi_state = 0; } } @@ -491,7 +456,6 @@ static void dm_TXPowerTrackingCallback_TSSI(struct net_device *dev) u32 Value; u8 Pwr_Flag; u16 Avg_TSSI_Meas, TSSI_13dBm, Avg_TSSI_Meas_from_driver = 0; - /*RT_STATUS rtStatus = RT_STATUS_SUCCESS;*/ bool rtStatus = true; u32 delta = 0; @@ -513,7 +477,6 @@ static void dm_TXPowerTrackingCallback_TSSI(struct net_device *dev) if (rtStatus == RT_STATUS_FAILURE) RT_TRACE(COMP_POWER_TRACKING, "Set configuration with tx cmd queue fail!\n"); usleep_range(1000, 2000); - /*DbgPrint("hi, vivi, strange\n");*/ for (i = 0; i <= 30; i++) { read_nic_byte(dev, 0x1ba, &Pwr_Flag); @@ -559,8 +522,6 @@ static void dm_TXPowerTrackingCallback_TSSI(struct net_device *dev) TSSI_13dBm = priv->TSSI_13dBm; RT_TRACE(COMP_POWER_TRACKING, "TSSI_13dBm = %d\n", TSSI_13dBm); - /*if (abs(Avg_TSSI_Meas_from_driver - TSSI_13dBm) <= E_FOR_TX_POWER_TRACK)*/ - /* For MacOS-compatible */ if (Avg_TSSI_Meas_from_driver > TSSI_13dBm) delta = Avg_TSSI_Meas_from_driver - TSSI_13dBm; else @@ -664,7 +625,6 @@ static void dm_TXPowerTrackingCallback_ThermalMeter(struct net_device *dev) } } priv->btxpower_trackingInit = true; - /*pHalData->TXPowercount = 0;*/ return; } @@ -708,9 +668,6 @@ static void dm_TXPowerTrackingCallback_ThermalMeter(struct net_device *dev) } tmpCCK40Mindex = 0; } - /*DbgPrint("%ddb, tmpOFDMindex = %d, tmpCCK20Mindex = %d, tmpCCK40Mindex = %d", - ((u1Byte)tmpRegA - pHalData->ThermalMeter[0]), - tmpOFDMindex, tmpCCK20Mindex, tmpCCK40Mindex);*/ if (priv->CurrentChannelBW != HT_CHANNEL_WIDTH_20) /* 40M */ tmpCCKindex = tmpCCK40Mindex; else @@ -730,7 +687,6 @@ static void dm_TXPowerTrackingCallback_ThermalMeter(struct net_device *dev) } if (CCKSwingNeedUpdate) { - /*DbgPrint("Update CCK Swing, CCK_index = %d\n", pHalData->CCK_index);*/ dm_cck_txpower_adjust(dev, priv->bcck_in_ch14); } if (priv->OFDM_index != tmpOFDMindex) { @@ -1301,7 +1257,6 @@ static void dm_CheckTXPowerTracking_ThermalMeter(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); static u8 TM_Trigger; - /*DbgPrint("dm_CheckTXPowerTracking()\n");*/ if (!priv->btxpower_tracking) return; if (priv->txpower_count <= 2) { @@ -1321,7 +1276,6 @@ static void dm_CheckTXPowerTracking_ThermalMeter(struct net_device *dev) TM_Trigger = 1; return; } - /*DbgPrint("Schedule TxPowerTrackingWorkItem\n");*/ queue_delayed_work(priv->priv_wq, &priv->txpower_tracking_wq, 0); TM_Trigger = 0; } @@ -1329,7 +1283,6 @@ static void dm_CheckTXPowerTracking_ThermalMeter(struct net_device *dev) static void dm_check_txpower_tracking(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); - /*static u32 tx_power_track_counter = 0;*/ #ifdef RTL8190P dm_CheckTXPowerTracking_TSSI(dev); @@ -1414,7 +1367,6 @@ static void dm_CCKTxPowerAdjust_ThermalMeter(struct net_device *dev, bool bInCH RT_TRACE(COMP_POWER_TRACKING, "CCK not chnl 14, reg 0x%x = 0x%x\n", rCCK0_DebugPort, TempVal); } else { - /*priv->CCKTxPowerAdjustCntNotCh14++; cosa add for debug.*/ /* Write 0xa22 0xa23 */ TempVal = CCKSwingTable_Ch14[priv->CCK_index][0] + (CCKSwingTable_Ch14[priv->CCK_index][1]<<8); @@ -1497,10 +1449,7 @@ void dm_restore_dynamic_mechanism_state(struct net_device *dev) ratr_value = reg_ratr; if (priv->rf_type == RF_1T2R) { /* 1T2R, Spatial Stream 2 should be disabled */ ratr_value &= ~(RATE_ALL_OFDM_2SS); - /*DbgPrint("HW_VAR_TATR_0 from 0x%x ==> 0x%x\n", ((pu4Byte)(val))[0], ratr_value);*/ } - /*DbgPrint("set HW_VAR_TATR_0 = 0x%x\n", ratr_value);*/ - /*cosa PlatformEFIOWrite4Byte(Adapter, RATR0, ((pu4Byte)(val))[0]);*/ write_nic_dword(dev, RATR0, ratr_value); write_nic_byte(dev, UFWP, 1); } @@ -1522,7 +1471,6 @@ static void dm_bb_initialgain_restore(struct net_device *dev) return; /* Disable Initial Gain */ - /*PHY_SetBBReg(Adapter, UFWP, bMaskLWord, 0x800);*/ rtl8192_setBBreg(dev, UFWP, bMaskByte1, 0x8); /* Only clear byte 1 and rewrite. */ rtl8192_setBBreg(dev, rOFDM0_XAAGCCore1, bit_mask, (u32)priv->initgain_backup.xaagccore1); rtl8192_setBBreg(dev, rOFDM0_XBAGCCore1, bit_mask, (u32)priv->initgain_backup.xbagccore1); @@ -1537,7 +1485,6 @@ static void dm_bb_initialgain_restore(struct net_device *dev) RT_TRACE(COMP_DIG, "dm_BBInitialGainRestore 0xc68 is %x\n", priv->initgain_backup.xdagccore1); RT_TRACE(COMP_DIG, "dm_BBInitialGainRestore 0xa0a is %x\n", priv->initgain_backup.cca); /* Enable Initial Gain */ - /*PHY_SetBBReg(Adapter, UFWP, bMaskLWord, 0x100);*/ rtl8192_setBBreg(dev, UFWP, bMaskByte1, 0x1); /* Only clear byte 1 and rewrite. */ } /* dm_BBInitialGainRestore */ @@ -1550,7 +1497,6 @@ static void dm_bb_initialgain_backup(struct net_device *dev) if (dm_digtable.dig_algorithm == DIG_ALGO_BY_RSSI) return; - /*PHY_SetBBReg(Adapter, UFWP, bMaskLWord, 0x800);*/ rtl8192_setBBreg(dev, UFWP, bMaskByte1, 0x8); /* Only clear byte 1 and rewrite. */ priv->initgain_backup.xaagccore1 = (u8)rtl8192_QueryBBReg(dev, rOFDM0_XAAGCCore1, bit_mask); priv->initgain_backup.xbagccore1 = (u8)rtl8192_QueryBBReg(dev, rOFDM0_XBAGCCore1, bit_mask); @@ -1643,7 +1589,6 @@ static void dm_ctrl_initgain_byrssi_by_driverrssi( if (!dm_digtable.dig_enable_flag) return; - /*DbgPrint("Dig by Sw Rssi\n");*/ if (dm_digtable.dig_algorithm_switch) /* if switched algorithm, we have to disable FW Dig. */ fw_dig = 0; @@ -1660,11 +1605,7 @@ static void dm_ctrl_initgain_byrssi_by_driverrssi( else dm_digtable.cur_connect_state = DIG_DISCONNECT; - /*DbgPrint("DM_DigTable.PreConnectState = %d, DM_DigTable.CurConnectState = %d\n", - DM_DigTable.PreConnectState, DM_DigTable.CurConnectState);*/ - dm_digtable.rssi_val = priv->undecorated_smoothed_pwdb; - /*DbgPrint("DM_DigTable.Rssi_val = %d\n", DM_DigTable.Rssi_val);*/ dm_initial_gain(dev); dm_pd_th(dev); dm_cs_ratio(dev); @@ -1700,11 +1641,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( (priv->undecorated_smoothed_pwdb < dm_digtable.rssi_high_thresh)) return; - /*DbgPrint("Dig by Fw False Alarm\n");*/ - /*if (DM_DigTable.Dig_State == DM_STA_DIG_OFF)*/ - /*DbgPrint("DIG Check\n\r RSSI=%d LOW=%d HIGH=%d STATE=%d", - pHalData->UndecoratedSmoothedPWDB, DM_DigTable.RssiLowThresh, - DM_DigTable.RssiHighThresh, DM_DigTable.Dig_State);*/ /* 1. When RSSI decrease, We have to judge if it is smaller than a threshold * and then execute the step below. */ @@ -1737,12 +1673,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( * 2008/02/05 MH SD3-Jerry 92U/92E PD_TH are the same. */ write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x00); - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(pAdapter, rOFDM0_RxDetector1, 0x40); - else if (pAdapter->HardwareType == HARDWARE_TYPE_RTL8192E) - else - PlatformEFIOWrite1Byte(pAdapter, rOFDM0_RxDetector1, 0x40); - */ } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x42); @@ -1750,7 +1680,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( write_nic_byte(dev, 0xa0a, 0x08); /* 1.5 Higher EDCCA. */ - /*PlatformEFIOWrite4Byte(pAdapter, rOFDM0_ECCAThreshold, 0x325);*/ return; } @@ -1771,7 +1700,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( reset_cnt = priv->reset_count; dm_digtable.dig_state = DM_STA_DIG_ON; - /*DbgPrint("DIG ON\n\r");*/ /* 2.1 Set initial gain. * 2008/02/26 MH SD3-Jerry suggest to prevent dirty environment. @@ -1794,13 +1722,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( * 2008/02/05 MH SD3-Jerry 92U/92E PD_TH are the same. */ write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x20); - /* - else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x42); - else if (pAdapter->HardwareType == HARDWARE_TYPE_RTL8192E) - else - PlatformEFIOWrite1Byte(pAdapter, rOFDM0_RxDetector1, 0x42); - */ } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x44); @@ -1810,7 +1731,6 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( /* 2.4 Lower EDCCA. * 2008/01/11 MH 90/92 series are the same. */ - /*PlatformEFIOWrite4Byte(pAdapter, rOFDM0_ECCAThreshold, 0x346);*/ /* 2.5 DIG On. */ rtl8192_setBBreg(dev, UFWP, bMaskByte1, 0x1); /* Only clear byte 1 and rewrite. */ @@ -1856,11 +1776,6 @@ static void dm_ctrl_initgain_byrssi_highpwr( /* 3.1 Higher PD_TH for OFDM for high power state. */ if (priv->CurrentChannelBW != HT_CHANNEL_WIDTH_20) { write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x10); - - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x41); - */ - } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x43); } else { @@ -1874,10 +1789,6 @@ static void dm_ctrl_initgain_byrssi_highpwr( /* 3.2 Recover PD_TH for OFDM for normal power region. */ if (priv->CurrentChannelBW != HT_CHANNEL_WIDTH_20) { write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x20); - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x42); - */ - } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x44); } @@ -1919,7 +1830,6 @@ static void dm_initial_gain( dm_digtable.cur_ig_value = priv->DefaultInitialGain[0]; dm_digtable.pre_ig_value = 0; } - /*DbgPrint("DM_DigTable.CurIGValue = 0x%x, DM_DigTable.PreIGValue = 0x%x\n", DM_DigTable.CurIGValue, DM_DigTable.PreIGValue);*/ /* if silent reset happened, we should rewrite the values back */ if (priv->reset_count != reset_cnt) { @@ -1935,7 +1845,6 @@ static void dm_initial_gain( if ((dm_digtable.pre_ig_value != dm_digtable.cur_ig_value) || !initialized || force_write) { initial_gain = (u8)dm_digtable.cur_ig_value; - /*DbgPrint("Write initial gain = 0x%x\n", initial_gain);*/ /* Set initial gain. */ write_nic_byte(dev, rOFDM0_XAAGCCore1, initial_gain); write_nic_byte(dev, rOFDM0_XBAGCCore1, initial_gain); @@ -1987,7 +1896,6 @@ static void dm_pd_th( { if ((dm_digtable.prepd_thstate != dm_digtable.curpd_thstate) || (initialized <= 3) || force_write) { - /*DbgPrint("Write PD_TH state = %d\n", DM_DigTable.CurPD_THState);*/ if (dm_digtable.curpd_thstate == DIG_PD_AT_LOW_POWER) { /* Lower PD_TH for OFDM. */ if (priv->CurrentChannelBW != HT_CHANNEL_WIDTH_20) { @@ -1995,9 +1903,6 @@ static void dm_pd_th( * 2008/02/05 MH SD3-Jerry 92U/92E PD_TH are the same. */ write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x00); - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x40); - */ } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x42); } else if (dm_digtable.curpd_thstate == DIG_PD_AT_NORMAL_POWER) { @@ -2007,18 +1912,12 @@ static void dm_pd_th( * 2008/02/05 MH SD3-Jerry 92U/92E PD_TH are the same. */ write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x20); - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x42); - */ } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x44); } else if (dm_digtable.curpd_thstate == DIG_PD_AT_HIGH_POWER) { /* Higher PD_TH for OFDM for high power state. */ if (priv->CurrentChannelBW != HT_CHANNEL_WIDTH_20) { write_nic_byte(dev, (rOFDM0_XATxAFE+3), 0x10); - /*else if (priv->card_8192 == HARDWARE_TYPE_RTL8190P) - write_nic_byte(dev, rOFDM0_RxDetector1, 0x41); - */ } else write_nic_byte(dev, rOFDM0_RxDetector1, 0x43); } @@ -2065,7 +1964,6 @@ static void dm_cs_ratio( { if ((dm_digtable.precs_ratio_state != dm_digtable.curcs_ratio_state) || !initialized || force_write) { - /*DbgPrint("Write CS_ratio state = %d\n", DM_DigTable.CurCS_ratioState);*/ if (dm_digtable.curcs_ratio_state == DIG_CS_RATIO_LOWER) { /* Lower CS ratio for CCK. */ write_nic_byte(dev, 0xa0a, 0x08); @@ -2094,7 +1992,6 @@ static void dm_check_edca_turbo( { struct r8192_priv *priv = ieee80211_priv(dev); PRT_HIGH_THROUGHPUT pHTInfo = priv->ieee80211->pHTInfo; - /*PSTA_QOS pStaQos = pMgntInfo->pStaQos;*/ /* Keep past Tx/Rx packet count for RT-to-RT EDCA turbo. */ static unsigned long lastTxOkCnt; @@ -2111,20 +2008,16 @@ static void dm_check_edca_turbo( if (priv->ieee80211->pHTInfo->IOTAction & HT_IOT_ACT_DISABLE_EDCA_TURBO) goto dm_CheckEdcaTurbo_EXIT; - /*printk("========>%s():bis_any_nonbepkts is %d\n", __func__, priv->bis_any_nonbepkts);*/ - /* Check the status for current condition. */ if (!priv->ieee80211->bis_any_nonbepkts) { curTxOkCnt = priv->stats.txbytesunicast - lastTxOkCnt; curRxOkCnt = priv->stats.rxbytesunicast - lastRxOkCnt; /* For RT-AP, we needs to turn it on when Rx>Tx */ if (curRxOkCnt > 4*curTxOkCnt) { - /*printk("%s():curRxOkCnt > 4*curTxOkCnt\n");*/ if (!priv->bis_cur_rdlstate || !priv->bcurrent_turbo_EDCA) { write_nic_dword(dev, EDCAPARA_BE, edca_setting_DL[pHTInfo->IOTPeer]); priv->bis_cur_rdlstate = true; } } else { - /*printk("%s():curRxOkCnt < 4*curTxOkCnt\n");*/ if (priv->bis_cur_rdlstate || !priv->bcurrent_turbo_EDCA) { write_nic_dword(dev, EDCAPARA_BE, edca_setting_UL[pHTInfo->IOTPeer]); priv->bis_cur_rdlstate = false; @@ -2224,7 +2117,6 @@ static void dm_ctstoself(struct net_device *dev) curRxOkCnt = priv->stats.rxbytesunicast - lastRxOkCnt; if (curRxOkCnt > 4*curTxOkCnt) { /* downlink, disable CTS to self */ pHTInfo->IOTAction &= ~HT_IOT_ACT_FORCED_CTS2SELF; - /*DbgPrint("dm_CTSToSelf() ==> CTS to self disabled -- downlink\n");*/ } else { /* uplink */ pHTInfo->IOTAction |= HT_IOT_ACT_FORCED_CTS2SELF; } @@ -2279,7 +2171,6 @@ void dm_rf_pathcheck_workitemcallback(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct r8192_priv *priv = container_of(dwork, struct r8192_priv, rfpath_check_wq); struct net_device *dev = priv->ieee80211->dev; - /*bool bactually_set = false;*/ u8 rfpath = 0, i; /* 2008/01/30 MH After discussing with SD3 Jerry, 0xc04/0xd04 register will @@ -2343,7 +2234,6 @@ static void dm_rxpath_sel_byrssi(struct net_device *dev) if (priv->ieee80211->mode == WIRELESS_MODE_B) { DM_RxPathSelTable.cck_method = CCK_RX_VERSION_2; /* pure B mode, fixed cck version2 */ - /*DbgPrint("Pure B mode, use cck rx version2\n");*/ } /* decide max/sec/min rssi index */ @@ -2496,7 +2386,6 @@ static void dm_rxpath_sel_byrssi(struct net_device *dev) if ((DM_RxPathSelTable.disabled_rf >> i) & 0x1) { /* disabled rf */ if (tmp_max_rssi >= DM_RxPathSelTable.rf_enable_rssi_th[i]) { /* enable the BB Rx path */ - /*DbgPrint("RF-%d is enabled.\n", 0x1<framesync); reg_c38_State = RegC38_Default; - /*DbgPrint("Fsync is idle, rssi>=40, write 0xc38 = 0x%x\n", pHalData->framesync);*/ } } } else { if (reg_c38_State) { write_nic_byte(dev, rOFDM0_RxDetector3, priv->framesync); reg_c38_State = RegC38_Default; - /*DbgPrint("Fsync is idle, not connected, write 0xc38 = 0x%x\n", pHalData->framesync);*/ } } } @@ -2808,13 +2694,11 @@ void dm_check_fsync(struct net_device *dev) write_nic_byte(dev, rOFDM0_RxDetector3, priv->framesync); reg_c38_State = RegC38_Default; reset_cnt = priv->reset_count; - /*DbgPrint("reg_c38_State = 0 for silent reset.\n");*/ } } else { if (reg_c38_State) { write_nic_byte(dev, rOFDM0_RxDetector3, priv->framesync); reg_c38_State = RegC38_Default; - /*DbgPrint("framesync no monitor, write 0xc38 = 0x%x\n", pHalData->framesync);*/ } } } @@ -2856,7 +2740,6 @@ static void dm_dynamic_txpower(struct net_device *dev) priv->bDynamicTxLowPower = false; return; } - /*printk("priv->ieee80211->current_network.unknown_cap_exist is %d , priv->ieee80211->current_network.broadcom_cap_exist is %d\n", priv->ieee80211->current_network.unknown_cap_exist, priv->ieee80211->current_network.broadcom_cap_exist);*/ if ((priv->ieee80211->current_network.atheros_cap_exist) && (priv->ieee80211->mode == IEEE_G)) { txhipower_threshold = TX_POWER_ATHEROAP_THRESH_HIGH; txlowpower_threshold = TX_POWER_ATHEROAP_THRESH_LOW; @@ -2865,7 +2748,6 @@ static void dm_dynamic_txpower(struct net_device *dev) txlowpower_threshold = TX_POWER_NEAR_FIELD_THRESH_LOW; } - /*printk("=======>%s(): txhipower_threshold is %d, txlowpower_threshold is %d\n", __func__, txhipower_threshold, txlowpower_threshold);*/ RT_TRACE(COMP_TXAGC, "priv->undecorated_smoothed_pwdb = %ld\n", priv->undecorated_smoothed_pwdb); if (priv->ieee80211->state == IEEE80211_LINKED) { @@ -2884,7 +2766,6 @@ static void dm_dynamic_txpower(struct net_device *dev) priv->bDynamicTxLowPower = false; } } else { - /*pHalData->bTXPowerCtrlforNearFarRange = !pHalData->bTXPowerCtrlforNearFarRange;*/ priv->bDynamicTxHighPower = false; priv->bDynamicTxLowPower = false; } @@ -2911,14 +2792,10 @@ static void dm_check_txrateandretrycount(struct net_device *dev) struct r8192_priv *priv = ieee80211_priv(dev); struct ieee80211_device *ieee = priv->ieee80211; /* for 11n tx rate */ - /*priv->stats.CurrentShowTxate = read_nic_byte(dev, CURRENT_TX_RATE_REG);*/ read_nic_byte(dev, CURRENT_TX_RATE_REG, &ieee->softmac_stats.CurrentShowTxate); - /*printk("=============>tx_rate_reg:%x\n", ieee->softmac_stats.CurrentShowTxate);*/ /* for initial tx rate */ - /*priv->stats.last_packet_rate = read_nic_byte(dev, INITIAL_TX_RATE_REG);*/ read_nic_byte(dev, INITIAL_TX_RATE_REG, &ieee->softmac_stats.last_packet_rate); /* for tx retry count */ - /*priv->stats.txretrycount = read_nic_dword(dev, TX_RETRY_COUNT_REG);*/ read_nic_dword(dev, TX_RETRY_COUNT_REG, &ieee->softmac_stats.txretrycount); } -- GitLab From ba25552a58b4e463c6716aaa775936bbb66022c5 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Tue, 28 Mar 2023 00:49:08 +0500 Subject: [PATCH 1428/5631] staging: rtl8192u: add '*' on subsequent lines in block comment Linux kernel coding style for block comments uses a column of '*' on the left side. Fix block comment by adding '*' on subsequent lines as reported by checkatch.pl script. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/3a581aae65a152ce41fdd2db667574eba1783113.1679945728.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r8192U_dm.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c index e5c0bece4bb4..dd9903719c20 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.c +++ b/drivers/staging/rtl8192u/r8192U_dm.c @@ -1,13 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /*++ -Copyright-c Realtek Semiconductor Corp. All rights reserved. - -Module Name: - r8192U_dm.c - -Abstract: - HW dynamic mechanism. ---*/ + * Copyright-c Realtek Semiconductor Corp. All rights reserved. + * + * Module Name: + * r8192U_dm.c + * + * Abstract: + * HW dynamic mechanism. + *-- + */ #include "r8192U.h" #include "r8192U_dm.h" #include "r8192U_hw.h" -- GitLab From 63ff870ce0e54f34c4c7a3b95883c30916801400 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Tue, 28 Mar 2023 00:49:09 +0500 Subject: [PATCH 1429/5631] staging: rtl8192u: add '*/' on separate line in block comments Linux kernel coding style uses '*/' on a separate line at the end of multi line comments. Fix block comments by moving '*/' at the end of block comments on a separate line as reported by checkpatch.pl script. Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/140e0928531e61dc7396271a5b16a6be17514c76.1679945728.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192u/r8192U_dm.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192u/r8192U_dm.c b/drivers/staging/rtl8192u/r8192U_dm.c index dd9903719c20..cbae852478ea 100644 --- a/drivers/staging/rtl8192u/r8192U_dm.c +++ b/drivers/staging/rtl8192u/r8192U_dm.c @@ -244,7 +244,8 @@ void init_rate_adaptive(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_check_rate_adaptive(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); @@ -1525,7 +1526,8 @@ static void dm_bb_initialgain_backup(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_dig_init(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); @@ -1565,7 +1567,8 @@ static void dm_dig_init(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_ctrl_initgain_byrssi(struct net_device *dev) { if (!dm_digtable.dig_enable_flag) @@ -1751,7 +1754,8 @@ static void dm_ctrl_initgain_byrssi_by_fwfalse_alarm( * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_ctrl_initgain_byrssi_highpwr( struct net_device *dev) { @@ -2137,7 +2141,8 @@ static void dm_ctstoself(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_check_pbc_gpio(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); @@ -2166,7 +2171,8 @@ static void dm_check_pbc_gpio(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ void dm_rf_pathcheck_workitemcallback(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); @@ -2407,7 +2413,8 @@ static void dm_rxpath_sel_byrssi(struct net_device *dev) * Output: NONE * * Return: NONE - *---------------------------------------------------------------------------*/ + *--------------------------------------------------------------------------- + */ static void dm_check_rx_path_selection(struct net_device *dev) { struct r8192_priv *priv = ieee80211_priv(dev); -- GitLab From 0cda003f1d9e662e55660c657e37f6f1e66437b6 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Tue, 28 Mar 2023 03:00:57 +0500 Subject: [PATCH 1430/5631] staging: rtl8192e: fix unbalanced braces around else Balance if/else braces as recommended by checkpatch.pl Signed-off-by: Khadija Kamran Link: https://lore.kernel.org/r/ZCISGaFELBfDyGRT@khadija-virtual-machine Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl819x_TSProc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtl819x_TSProc.c b/drivers/staging/rtl8192e/rtl819x_TSProc.c index 68c131afc2ba..c61fdf73c572 100644 --- a/drivers/staging/rtl8192e/rtl819x_TSProc.c +++ b/drivers/staging/rtl8192e/rtl819x_TSProc.c @@ -517,6 +517,7 @@ void TsStartAddBaProcess(struct rtllib_device *ieee, struct tx_ts_record *pTxTS) netdev_dbg(ieee->dev, "Immediately Start ADDBA\n"); mod_timer(&pTxTS->TsAddBaTimer, jiffies + 10); } - } else + } else { netdev_dbg(ieee->dev, "BA timer is already added\n"); + } } -- GitLab From f045e9df6537175d02565f21616ac1a9dd59b61c Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Thu, 16 Mar 2023 18:14:45 +0800 Subject: [PATCH 1431/5631] iommu/mediatek: Set dma_mask for PGTABLE_PA_35_EN When we enable PGTABLE_PA_35_EN, the PA for pgtable may be 35bits. Thus add dma_mask for it. Fixes: 301c3ca12576 ("iommu/mediatek: Allow page table PA up to 35bit") Signed-off-by: Chengci.Xu Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230316101445.12443-1-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index d5a4955910ff..6a00ce208dc2 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1258,6 +1258,14 @@ static int mtk_iommu_probe(struct platform_device *pdev) return PTR_ERR(data->bclk); } + if (MTK_IOMMU_HAS_FLAG(data->plat_data, PGTABLE_PA_35_EN)) { + ret = dma_set_mask(dev, DMA_BIT_MASK(35)); + if (ret) { + dev_err(dev, "Failed to set dma_mask 35.\n"); + return ret; + } + } + pm_runtime_enable(dev); if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) { -- GitLab From f594496403fa383259aa7dfad92f383a2ee07e1b Mon Sep 17 00:00:00 2001 From: Vasant Hegde Date: Fri, 10 Mar 2023 09:00:00 +0000 Subject: [PATCH 1432/5631] iommu/amd: Add 5 level guest page table support Newer AMD IOMMU supports 5 level guest page table (v2 page table). If both processor and IOMMU supports 5 level page table then enable it. Otherwise fall back to 4 level page table. Co-developed-by: Wei Huang Signed-off-by: Wei Huang Reviewed-by: Suravee Suthikulpanit Signed-off-by: Vasant Hegde Link: https://lore.kernel.org/r/20230310090000.1117786-1-vasant.hegde@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu.h | 1 + drivers/iommu/amd/amd_iommu_types.h | 7 +++++++ drivers/iommu/amd/init.c | 23 +++++++++++++++++++++-- drivers/iommu/amd/io_pgtable_v2.c | 9 ++++++--- drivers/iommu/amd/iommu.c | 5 +++++ 5 files changed, 40 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 20a142b54498..e98f20a9bdd8 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -34,6 +34,7 @@ extern int amd_iommu_reenable(int); extern int amd_iommu_enable_faulting(void); extern int amd_iommu_guest_ir; extern enum io_pgtable_fmt amd_iommu_pgtable; +extern int amd_iommu_gpt_level; /* IOMMUv2 specific functions */ struct iommu_domain; diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index e5cfdeaaad48..3cda781b6c7f 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -93,6 +93,8 @@ #define FEATURE_GA (1ULL<<7) #define FEATURE_HE (1ULL<<8) #define FEATURE_PC (1ULL<<9) +#define FEATURE_GATS_SHIFT (12) +#define FEATURE_GATS_MASK (3ULL) #define FEATURE_GAM_VAPIC (1ULL<<21) #define FEATURE_GIOSUP (1ULL<<48) #define FEATURE_EPHSUP (1ULL<<50) @@ -305,6 +307,9 @@ #define PAGE_MODE_6_LEVEL 0x06 #define PAGE_MODE_7_LEVEL 0x07 +#define GUEST_PGTABLE_4_LEVEL 0x00 +#define GUEST_PGTABLE_5_LEVEL 0x01 + #define PM_LEVEL_SHIFT(x) (12 + ((x) * 9)) #define PM_LEVEL_SIZE(x) (((x) < 6) ? \ ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \ @@ -398,6 +403,8 @@ #define DTE_GCR3_SHIFT_B 16 #define DTE_GCR3_SHIFT_C 43 +#define DTE_GPT_LEVEL_SHIFT 54 + #define GCR3_VALID 0x01ULL #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 141eca29c951..c46ee218d387 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -153,6 +153,8 @@ bool amd_iommu_dump; bool amd_iommu_irq_remap __read_mostly; enum io_pgtable_fmt amd_iommu_pgtable = AMD_IOMMU_V1; +/* Guest page table level */ +int amd_iommu_gpt_level = PAGE_MODE_4_LEVEL; int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC; static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; @@ -306,6 +308,11 @@ static bool check_feature_on_all_iommus(u64 mask) return !!(amd_iommu_efr & mask); } +static inline int check_feature_gpt_level(void) +{ + return ((amd_iommu_efr >> FEATURE_GATS_SHIFT) & FEATURE_GATS_MASK); +} + /* * For IVHD type 0x11/0x40, EFR is also available via IVHD. * Default to IVHD EFR since it is available sooner @@ -2155,8 +2162,10 @@ static void print_iommu_info(void) if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) pr_info("X2APIC enabled\n"); } - if (amd_iommu_pgtable == AMD_IOMMU_V2) - pr_info("V2 page table enabled\n"); + if (amd_iommu_pgtable == AMD_IOMMU_V2) { + pr_info("V2 page table enabled (Paging mode : %d level)\n", + amd_iommu_gpt_level); + } } static int __init amd_iommu_init_pci(void) @@ -3026,6 +3035,11 @@ static int __init early_amd_iommu_init(void) if (ret) goto out; + /* 5 level guest page table */ + if (cpu_feature_enabled(X86_FEATURE_LA57) && + check_feature_gpt_level() == GUEST_PGTABLE_5_LEVEL) + amd_iommu_gpt_level = PAGE_MODE_5_LEVEL; + /* Disable any previously enabled IOMMUs */ if (!is_kdump_kernel() || amd_iommu_disabled) disable_iommus(); @@ -3557,6 +3571,11 @@ __setup("ivrs_acpihid", parse_ivrs_acpihid); bool amd_iommu_v2_supported(void) { + /* CPU page table size should match IOMMU guest page table size */ + if (cpu_feature_enabled(X86_FEATURE_LA57) && + amd_iommu_gpt_level != PAGE_MODE_5_LEVEL) + return false; + /* * Since DTE[Mode]=0 is prohibited on SNP-enabled system * (i.e. EFR[SNPSup]=1), IOMMUv2 page table cannot be used without diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c index 9f8b423f7630..27c3015947e6 100644 --- a/drivers/iommu/amd/io_pgtable_v2.c +++ b/drivers/iommu/amd/io_pgtable_v2.c @@ -37,8 +37,7 @@ static inline int get_pgtable_level(void) { - /* 5 level page table is not supported */ - return PAGE_MODE_4_LEVEL; + return amd_iommu_gpt_level; } static inline bool is_large_pte(u64 pte) @@ -379,6 +378,7 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg); struct protection_domain *pdom = (struct protection_domain *)cookie; int ret; + int ias = IOMMU_IN_ADDR_BIT_SIZE; pgtable->pgd = alloc_pgtable_page(pdom->nid, GFP_ATOMIC); if (!pgtable->pgd) @@ -388,12 +388,15 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo if (ret) goto err_free_pgd; + if (get_pgtable_level() == PAGE_MODE_5_LEVEL) + ias = 57; + pgtable->iop.ops.map_pages = iommu_v2_map_pages; pgtable->iop.ops.unmap_pages = iommu_v2_unmap_pages; pgtable->iop.ops.iova_to_phys = iommu_v2_iova_to_phys; cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES_V2, - cfg->ias = IOMMU_IN_ADDR_BIT_SIZE, + cfg->ias = ias, cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE, cfg->tlb = &v2_flush_ops; diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5452d0dd6569..e290f2034252 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1611,6 +1611,11 @@ static void set_dte_entry(struct amd_iommu *iommu, u16 devid, tmp = DTE_GCR3_VAL_C(gcr3) << DTE_GCR3_SHIFT_C; flags |= tmp; + if (amd_iommu_gpt_level == PAGE_MODE_5_LEVEL) { + dev_table[devid].data[2] |= + ((u64)GUEST_PGTABLE_5_LEVEL << DTE_GPT_LEVEL_SHIFT); + } + if (domain->flags & PD_GIOV_MASK) pte_root |= DTE_FLAG_GIOV; } -- GitLab From 8ad266d133b005e88953b08d988fac86f74a0665 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 17 Mar 2023 13:51:33 -0700 Subject: [PATCH 1433/5631] driver core: Add CONFIG_FW_DEVLINK_SYNC_STATE_TIMEOUT Add a build time equivalent of fw_devlink.sync_state=timeout so that board specific kernels could enable it and not have to deal with setting or cluttering the kernel commandline. Cc: Doug Anderson Signed-off-by: Saravana Kannan Reviewed-by: Douglas Anderson Link: https://lore.kernel.org/r/20230317205134.964098-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/Kconfig | 12 ++++++++++++ drivers/base/core.c | 5 +++++ 2 files changed, 17 insertions(+) diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 6f04b831a5c0..2b8fd6bb7da0 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -230,4 +230,16 @@ config GENERIC_ARCH_NUMA Enable support for generic NUMA implementation. Currently, RISC-V and ARM64 use it. +config FW_DEVLINK_SYNC_STATE_TIMEOUT + bool "sync_state() behavior defaults to timeout instead of strict" + help + This is build time equivalent of adding kernel command line parameter + "fw_devlink.sync_state=timeout". Give up waiting on consumers and + call sync_state() on any devices that haven't yet received their + sync_state() calls after deferred_probe_timeout has expired or by + late_initcall() if !CONFIG_MODULES. You should almost always want to + select N here unless you have already successfully tested with the + command line option on every system/board your kernel is expected to + work on. + endmenu diff --git a/drivers/base/core.c b/drivers/base/core.c index b59692a4d809..89249be22161 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1671,7 +1671,12 @@ early_param("fw_devlink.strict", fw_devlink_strict_setup); #define FW_DEVLINK_SYNC_STATE_STRICT 0 #define FW_DEVLINK_SYNC_STATE_TIMEOUT 1 +#ifndef CONFIG_FW_DEVLINK_SYNC_STATE_TIMEOUT static int fw_devlink_sync_state; +#else +static int fw_devlink_sync_state = FW_DEVLINK_SYNC_STATE_TIMEOUT; +#endif + static int __init fw_devlink_sync_state_setup(char *arg) { if (!arg) -- GitLab From 76d0de5729c0569c4071e7f21fcab394e502f03a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:01 +0900 Subject: [PATCH 1434/5631] fprobe: Pass entry_data to handlers Pass the private entry_data to the entry and exit handlers so that they can share the context data, something like saved function arguments etc. User must specify the private entry_data size by @entry_data_size field before registering the fprobe. Link: https://lkml.kernel.org/r/167526696173.433354.17408372048319432574.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 8 ++++++-- kernel/trace/bpf_trace.c | 2 +- kernel/trace/fprobe.c | 21 ++++++++++++++------- lib/test_fprobe.c | 6 ++++-- samples/fprobe/fprobe_example.c | 6 ++++-- 5 files changed, 29 insertions(+), 14 deletions(-) diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 1c2bde0ead73..e0d4e6136249 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -13,6 +13,7 @@ * @nmissed: The counter for missing events. * @flags: The status flag. * @rethook: The rethook data structure. (internal data) + * @entry_data_size: The private data storage size. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -29,9 +30,12 @@ struct fprobe { unsigned long nmissed; unsigned int flags; struct rethook *rethook; + size_t entry_data_size; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); }; /* This fprobe is soft-disabled. */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e8da032bb6fc..fa403c323501 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2646,7 +2646,7 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, static void kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, - struct pt_regs *regs) + struct pt_regs *regs, void *data) { struct bpf_kprobe_multi_link *link; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index e8143e368074..fa25d09c9d57 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,14 +17,16 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + char data[]; }; static void fprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; - struct rethook_node *rh; + struct rethook_node *rh = NULL; struct fprobe *fp; + void *entry_data = NULL; int bit; fp = container_of(ops, struct fprobe, ops); @@ -37,9 +39,6 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, return; } - if (fp->entry_handler) - fp->entry_handler(fp, ip, ftrace_get_regs(fregs)); - if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { @@ -48,9 +47,16 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; - rethook_hook(rh, ftrace_get_regs(fregs), true); + if (fp->entry_data_size) + entry_data = fpr->data; } + if (fp->entry_handler) + fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data); + + if (rh) + rethook_hook(rh, ftrace_get_regs(fregs), true); + out: ftrace_test_recursion_unlock(bit); } @@ -81,7 +87,8 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, fpr = container_of(rh, struct fprobe_rethook_node, node); - fp->exit_handler(fp, fpr->entry_ip, regs); + fp->exit_handler(fp, fpr->entry_ip, regs, + fp->entry_data_size ? (void *)fpr->data : NULL); } NOKPROBE_SYMBOL(fprobe_exit_handler); @@ -146,7 +153,7 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) for (i = 0; i < size; i++) { struct fprobe_rethook_node *node; - node = kzalloc(sizeof(*node), GFP_KERNEL); + node = kzalloc(sizeof(*node) + fp->entry_data_size, GFP_KERNEL); if (!node) { rethook_free(fp->rethook); fp->rethook = NULL; diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 1fb56cf5e5ce..e4f65d114ed2 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -30,7 +30,8 @@ static noinline u32 fprobe_selftest_target2(u32 value) return (value / div_factor) + 1; } -static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs) +static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); /* This can be called on the fprobe_selftest_target and the fprobe_selftest_target2 */ @@ -39,7 +40,8 @@ static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, struct entry_val = (rand1 / div_factor); } -static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs) +static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) { unsigned long ret = regs_return_value(regs); diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index e22da8573116..dd794990ad7e 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -48,7 +48,8 @@ static void show_backtrace(void) stack_trace_print(stacks, len, 24); } -static void sample_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs) +static void sample_entry_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) { if (use_trace) /* @@ -63,7 +64,8 @@ static void sample_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_ show_backtrace(); } -static void sample_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs) +static void sample_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs, + void *data) { unsigned long rip = instruction_pointer(regs); -- GitLab From 34cabf8fd18f31c773b489d4113fbf6cb5b964c9 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:10 +0900 Subject: [PATCH 1435/5631] lib/test_fprobe: Add private entry_data testcases Add test cases for checking whether private entry_data is correctly passed or not. Link: https://lkml.kernel.org/r/167526697074.433354.17790288501657876219.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- lib/test_fprobe.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index e4f65d114ed2..6c7ef5acea21 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -38,6 +38,12 @@ static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, if (ip != target_ip) KUNIT_EXPECT_EQ(current_test, ip, target2_ip); entry_val = (rand1 / div_factor); + if (fp->entry_data_size) { + KUNIT_EXPECT_NOT_NULL(current_test, data); + if (data) + *(u32 *)data = entry_val; + } else + KUNIT_EXPECT_NULL(current_test, data); } static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, @@ -53,6 +59,12 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_EQ(current_test, ret, (rand1 / div_factor)); KUNIT_EXPECT_EQ(current_test, entry_val, (rand1 / div_factor)); exit_val = entry_val + div_factor; + if (fp->entry_data_size) { + KUNIT_EXPECT_NOT_NULL(current_test, data); + if (data) + KUNIT_EXPECT_EQ(current_test, *(u32 *)data, entry_val); + } else + KUNIT_EXPECT_NULL(current_test, data); } /* Test entry only (no rethook) */ @@ -134,6 +146,23 @@ static void test_fprobe_syms(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } +/* Test private entry_data */ +static void test_fprobe_data(struct kunit *test) +{ + struct fprobe fp = { + .entry_handler = fp_entry_handler, + .exit_handler = fp_exit_handler, + .entry_data_size = sizeof(u32), + }; + + current_test = test; + KUNIT_EXPECT_EQ(test, 0, register_fprobe(&fp, "fprobe_selftest_target", NULL)); + + target(rand1); + + KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); +} + static unsigned long get_ftrace_location(void *func) { unsigned long size, addr = (unsigned long)func; @@ -159,6 +188,7 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe_entry), KUNIT_CASE(test_fprobe), KUNIT_CASE(test_fprobe_syms), + KUNIT_CASE(test_fprobe_data), {} }; -- GitLab From 59a7a298565aa0ce44ce8e4fbcbb89a19730013a Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:19 +0900 Subject: [PATCH 1436/5631] fprobe: Add nr_maxactive to specify rethook_node pool size Add nr_maxactive to specify rethook_node pool size. This means the maximum number of actively running target functions concurrently for probing by exit_handler. Note that if the running function is preempted or sleep, it is still counted as 'active'. Link: https://lkml.kernel.org/r/167526697917.433354.17779774988245113106.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 2 ++ kernel/trace/fprobe.c | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index e0d4e6136249..678f741a7b33 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -14,6 +14,7 @@ * @flags: The status flag. * @rethook: The rethook data structure. (internal data) * @entry_data_size: The private data storage size. + * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -31,6 +32,7 @@ struct fprobe { unsigned int flags; struct rethook *rethook; size_t entry_data_size; + int nr_maxactive; void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index fa25d09c9d57..f222848571f2 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -143,7 +143,10 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) } /* Initialize rethook if needed */ - size = num * num_possible_cpus() * 2; + if (fp->nr_maxactive) + size = fp->nr_maxactive; + else + size = num * num_possible_cpus() * 2; if (size < 0) return -E2BIG; -- GitLab From 7e7ef1bfe5522faab6f245ced7b6749e9ac410d8 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:28 +0900 Subject: [PATCH 1437/5631] lib/test_fprobe: Add a test case for nr_maxactive Add a test case for nr_maxactive. If the number of active functions is more than nr_maxactive, it must be skipped. Link: https://lkml.kernel.org/r/167526698856.433354.4430007340787176666.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- lib/test_fprobe.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 6c7ef5acea21..4b37d7022f35 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -17,8 +17,10 @@ static u32 rand1, entry_val, exit_val; /* Use indirect calls to avoid inlining the target functions */ static u32 (*target)(u32 value); static u32 (*target2)(u32 value); +static u32 (*target_nest)(u32 value, u32 (*nest)(u32)); static unsigned long target_ip; static unsigned long target2_ip; +static unsigned long target_nest_ip; static noinline u32 fprobe_selftest_target(u32 value) { @@ -30,6 +32,11 @@ static noinline u32 fprobe_selftest_target2(u32 value) return (value / div_factor) + 1; } +static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) +{ + return nest(value + 2); +} + static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs, void *data) { @@ -67,6 +74,19 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_NULL(current_test, data); } +static notrace void nest_entry_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) +{ + KUNIT_EXPECT_FALSE(current_test, preemptible()); +} + +static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) +{ + KUNIT_EXPECT_FALSE(current_test, preemptible()); + KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip); +} + /* Test entry only (no rethook) */ static void test_fprobe_entry(struct kunit *test) { @@ -163,6 +183,25 @@ static void test_fprobe_data(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } +/* Test nr_maxactive */ +static void test_fprobe_nest(struct kunit *test) +{ + static const char *syms[] = {"fprobe_selftest_target", "fprobe_selftest_nest_target"}; + struct fprobe fp = { + .entry_handler = nest_entry_handler, + .exit_handler = nest_exit_handler, + .nr_maxactive = 1, + }; + + current_test = test; + KUNIT_EXPECT_EQ(test, 0, register_fprobe_syms(&fp, syms, 2)); + + target_nest(rand1, target); + KUNIT_EXPECT_EQ(test, 1, fp.nmissed); + + KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); +} + static unsigned long get_ftrace_location(void *func) { unsigned long size, addr = (unsigned long)func; @@ -178,8 +217,10 @@ static int fprobe_test_init(struct kunit *test) rand1 = get_random_u32_above(div_factor); target = fprobe_selftest_target; target2 = fprobe_selftest_target2; + target_nest = fprobe_selftest_nest_target; target_ip = get_ftrace_location(target); target2_ip = get_ftrace_location(target2); + target_nest_ip = get_ftrace_location(target_nest); return 0; } @@ -189,6 +230,7 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe), KUNIT_CASE(test_fprobe_syms), KUNIT_CASE(test_fprobe_data), + KUNIT_CASE(test_fprobe_nest), {} }; -- GitLab From 39d954200bf6ad503c722e44d0be80c7b826fa42 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:38 +0900 Subject: [PATCH 1438/5631] fprobe: Skip exit_handler if entry_handler returns !0 Skip hooking function return and calling exit_handler if the entry_handler() returns !0. Link: https://lkml.kernel.org/r/167526699798.433354.10998365726830117303.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/fprobe.h | 4 ++-- kernel/trace/bpf_trace.c | 15 +++++++++++++-- kernel/trace/fprobe.c | 14 +++++++++----- lib/test_fprobe.c | 7 +++++-- samples/fprobe/fprobe_example.c | 5 +++-- 5 files changed, 32 insertions(+), 13 deletions(-) diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 678f741a7b33..47fefc7f363b 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -34,8 +34,8 @@ struct fprobe { size_t entry_data_size; int nr_maxactive; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, - struct pt_regs *regs, void *entry_data); + int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); }; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fa403c323501..d804172b709c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2644,12 +2644,23 @@ kprobe_multi_link_prog_run(struct bpf_kprobe_multi_link *link, return err; } -static void +static int kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip, struct pt_regs *regs, void *data) { struct bpf_kprobe_multi_link *link; + link = container_of(fp, struct bpf_kprobe_multi_link, fp); + kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); + return 0; +} + +static void +kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip, + struct pt_regs *regs, void *data) +{ + struct bpf_kprobe_multi_link *link; + link = container_of(fp, struct bpf_kprobe_multi_link, fp); kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs); } @@ -2848,7 +2859,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error; if (flags & BPF_F_KPROBE_MULTI_RETURN) - link->fp.exit_handler = kprobe_multi_link_handler; + link->fp.exit_handler = kprobe_multi_link_exit_handler; else link->fp.entry_handler = kprobe_multi_link_handler; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index f222848571f2..9abb3905bc8e 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -27,7 +27,7 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit; + int bit, ret; fp = container_of(ops, struct fprobe, ops); if (fprobe_disabled(fp)) @@ -52,11 +52,15 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, } if (fp->entry_handler) - fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data); - - if (rh) - rethook_hook(rh, ftrace_get_regs(fregs), true); + ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data); + /* If entry_handler returns !0, nmissed is not counted. */ + if (rh) { + if (ret) + rethook_recycle(rh); + else + rethook_hook(rh, ftrace_get_regs(fregs), true); + } out: ftrace_test_recursion_unlock(bit); } diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 4b37d7022f35..9fa2ac9eda83 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -37,7 +37,7 @@ static noinline u32 fprobe_selftest_nest_target(u32 value, u32 (*nest)(u32)) return nest(value + 2); } -static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, +static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); @@ -51,6 +51,8 @@ static notrace void fp_entry_handler(struct fprobe *fp, unsigned long ip, *(u32 *)data = entry_val; } else KUNIT_EXPECT_NULL(current_test, data); + + return 0; } static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, @@ -74,10 +76,11 @@ static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, KUNIT_EXPECT_NULL(current_test, data); } -static notrace void nest_entry_handler(struct fprobe *fp, unsigned long ip, +static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs, void *data) { KUNIT_EXPECT_FALSE(current_test, preemptible()); + return 0; } static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip, diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c index dd794990ad7e..4efc8feb6277 100644 --- a/samples/fprobe/fprobe_example.c +++ b/samples/fprobe/fprobe_example.c @@ -48,8 +48,8 @@ static void show_backtrace(void) stack_trace_print(stacks, len, 24); } -static void sample_entry_handler(struct fprobe *fp, unsigned long ip, - struct pt_regs *regs, void *data) +static int sample_entry_handler(struct fprobe *fp, unsigned long ip, + struct pt_regs *regs, void *data) { if (use_trace) /* @@ -62,6 +62,7 @@ static void sample_entry_handler(struct fprobe *fp, unsigned long ip, nhit++; if (stackdump) show_backtrace(); + return 0; } static void sample_exit_handler(struct fprobe *fp, unsigned long ip, struct pt_regs *regs, -- GitLab From 87de2163a36b3ffb0d2e0df8e903dc7e30566548 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:46 +0900 Subject: [PATCH 1439/5631] lib/test_fprobe: Add a testcase for skipping exit_handler Add a testcase for skipping exit_handler if entry_handler returns !0. Link: https://lkml.kernel.org/r/167526700658.433354.12922388040490848613.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- lib/test_fprobe.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 9fa2ac9eda83..0fe5273e960b 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -21,6 +21,7 @@ static u32 (*target_nest)(u32 value, u32 (*nest)(u32)); static unsigned long target_ip; static unsigned long target2_ip; static unsigned long target_nest_ip; +static int entry_return_value; static noinline u32 fprobe_selftest_target(u32 value) { @@ -52,7 +53,7 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip, } else KUNIT_EXPECT_NULL(current_test, data); - return 0; + return entry_return_value; } static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip, @@ -205,6 +206,28 @@ static void test_fprobe_nest(struct kunit *test) KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); } +static void test_fprobe_skip(struct kunit *test) +{ + struct fprobe fp = { + .entry_handler = fp_entry_handler, + .exit_handler = fp_exit_handler, + }; + + current_test = test; + KUNIT_EXPECT_EQ(test, 0, register_fprobe(&fp, "fprobe_selftest_target", NULL)); + + entry_return_value = 1; + entry_val = 0; + exit_val = 0; + target(rand1); + KUNIT_EXPECT_NE(test, 0, entry_val); + KUNIT_EXPECT_EQ(test, 0, exit_val); + KUNIT_EXPECT_EQ(test, 0, fp.nmissed); + entry_return_value = 0; + + KUNIT_EXPECT_EQ(test, 0, unregister_fprobe(&fp)); +} + static unsigned long get_ftrace_location(void *func) { unsigned long size, addr = (unsigned long)func; @@ -234,6 +257,7 @@ static struct kunit_case fprobe_testcases[] = { KUNIT_CASE(test_fprobe_syms), KUNIT_CASE(test_fprobe_data), KUNIT_CASE(test_fprobe_nest), + KUNIT_CASE(test_fprobe_skip), {} }; -- GitLab From 8be098a9eb2710bc5381ba1ebaac660f8d9b6963 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Thu, 2 Feb 2023 00:56:55 +0900 Subject: [PATCH 1440/5631] docs: tracing: Update fprobe documentation Update fprobe.rst for - the private entry_data argument - the return value of the entry handler - the nr_rethook_node field. Link: https://lkml.kernel.org/r/167526701579.433354.3057889264263546659.stgit@mhiramat.roam.corp.google.com Cc: Florent Revest Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/fprobe.rst | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/Documentation/trace/fprobe.rst b/Documentation/trace/fprobe.rst index b64bec1ce144..40dd2fbce861 100644 --- a/Documentation/trace/fprobe.rst +++ b/Documentation/trace/fprobe.rst @@ -87,14 +87,16 @@ returns as same as unregister_ftrace_function(). The fprobe entry/exit handler ============================= -The prototype of the entry/exit callback function is as follows: +The prototype of the entry/exit callback function are as follows: .. code-block:: c - void callback_func(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + int entry_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); -Note that both entry and exit callbacks have same ptototype. The @entry_ip is -saved at function entry and passed to exit handler. + void exit_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); + +Note that the @entry_ip is saved at function entry and passed to exit handler. +If the entry callback function returns !0, the corresponding exit callback will be cancelled. @fp This is the address of `fprobe` data structure related to this handler. @@ -113,6 +115,12 @@ saved at function entry and passed to exit handler. to use @entry_ip. On the other hand, in the exit_handler, the instruction pointer of @regs is set to the currect return address. +@entry_data + This is a local storage to share the data between entry and exit handlers. + This storage is NULL by default. If the user specify `exit_handler` field + and `entry_data_size` field when registering the fprobe, the storage is + allocated and passed to both `entry_handler` and `exit_handler`. + Share the callbacks with kprobes ================================ -- GitLab From 12318566c5507a5ff4507d5bc5fe45895ffb0e05 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 23 Feb 2023 14:59:47 +0800 Subject: [PATCH 1441/5631] mm: hugetlb_vmemmap: simplify hugetlb_vmemmap_init() a bit The check of IS_ENABLED(CONFIG_PROC_SYSCTL) is unnecessary since register_sysctl_init() will be empty in this case. So, there is no warnings after removing the check. Link: https://lkml.kernel.org/r/20230223065947.64134-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: Mike Kravetz Signed-off-by: Andrew Morton --- mm/hugetlb_vmemmap.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index a559037cce00..a15cc56cf70a 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -590,17 +590,15 @@ static struct ctl_table hugetlb_vmemmap_sysctls[] = { static int __init hugetlb_vmemmap_init(void) { + const struct hstate *h; + /* HUGETLB_VMEMMAP_RESERVE_SIZE should cover all used struct pages */ BUILD_BUG_ON(__NR_USED_SUBPAGE * sizeof(struct page) > HUGETLB_VMEMMAP_RESERVE_SIZE); - if (IS_ENABLED(CONFIG_PROC_SYSCTL)) { - const struct hstate *h; - - for_each_hstate(h) { - if (hugetlb_vmemmap_optimizable(h)) { - register_sysctl_init("vm", hugetlb_vmemmap_sysctls); - break; - } + for_each_hstate(h) { + if (hugetlb_vmemmap_optimizable(h)) { + register_sysctl_init("vm", hugetlb_vmemmap_sysctls); + break; } } return 0; -- GitLab From 94c02ad7ff12b988bd7ccf522f23e0b1f68659e0 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 22 Feb 2023 14:52:47 -0500 Subject: [PATCH 1442/5631] mm/khugepaged: alloc_charge_hpage() take care of mem charge errors If memory charge failed, instead of returning the hpage but with an error, allow the function to cleanup the folio properly, which is normally what a function should do in this case - either return successfully, or return with no side effect of partial runs with an indicated error. This will also avoid the caller calling mem_cgroup_uncharge() unnecessarily with either anon or shmem path (even if it's safe to do so). Link: https://lkml.kernel.org/r/20230222195247.791227-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Stevens Acked-by: Johannes Weiner Reviewed-by: Yang Shi Reviewed-by: Zach O'Keefe Signed-off-by: Andrew Morton --- mm/khugepaged.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 92e6f56a932d..17562c692546 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -972,12 +972,19 @@ static int alloc_charge_hpage(struct page **hpage, struct mm_struct *mm, gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); + struct folio *folio; if (!hpage_collapse_alloc_page(hpage, gfp, node, &cc->alloc_nmask)) return SCAN_ALLOC_HUGE_PAGE_FAIL; - if (unlikely(mem_cgroup_charge(page_folio(*hpage), mm, gfp))) + + folio = page_folio(*hpage); + if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { + folio_put(folio); + *hpage = NULL; return SCAN_CGROUP_CHARGE_FAIL; + } count_memcg_page_event(*hpage, THP_COLLAPSE_ALLOC); + return SCAN_SUCCEED; } -- GitLab From a4a4659d86ec0395164dc346c1a7f4d2d1ff4db2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Mon, 20 Feb 2023 23:23:31 +0000 Subject: [PATCH 1443/5631] mm: cma: make kobj_type structure constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. Link: https://lkml.kernel.org/r/20230220-kobj_type-mm-cma-v1-1-45996cff1a81@weissschuh.net Signed-off-by: Thomas Weißschuh Cc: Wedson Almeida Filho Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton --- mm/cma_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/cma_sysfs.c b/mm/cma_sysfs.c index eb2f39caff59..56347d15b7e8 100644 --- a/mm/cma_sysfs.c +++ b/mm/cma_sysfs.c @@ -64,7 +64,7 @@ static struct attribute *cma_attrs[] = { }; ATTRIBUTE_GROUPS(cma); -static struct kobj_type cma_ktype = { +static const struct kobj_type cma_ktype = { .release = cma_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = cma_groups, -- GitLab From 2ede3c13be889900f8f5c04b5dc6298201d835c4 Mon Sep 17 00:00:00 2001 From: Alexander Halbuer Date: Wed, 1 Feb 2023 17:25:49 +0100 Subject: [PATCH 1444/5631] mm: reduce lock contention of pcp buffer refill rmqueue_bulk() batches the allocation of multiple elements to refill the per-CPU buffers into a single hold of the zone lock. Each element is allocated and checked using check_pcp_refill(). The check touches every related struct page which is especially expensive for higher order allocations (huge pages). This patch reduces the time holding the lock by moving the check out of the critical section similar to rmqueue_buddy() which allocates a single element. Measurements of parallel allocation-heavy workloads show a reduction of the average huge page allocation latency of 50 percent for two cores and nearly 90 percent for 24 cores. Link: https://lkml.kernel.org/r/20230201162549.68384-1-halbuer@sra.uni-hannover.de Signed-off-by: Alexander Halbuer Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/page_alloc.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7136c36c5d01..a853f0aa5d31 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3138,6 +3138,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { unsigned long flags; int i, allocated = 0; + struct list_head *prev_tail = list->prev; + struct page *pos, *n; spin_lock_irqsave(&zone->lock, flags); for (i = 0; i < count; ++i) { @@ -3146,9 +3148,6 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, if (unlikely(page == NULL)) break; - if (unlikely(check_pcp_refill(page, order))) - continue; - /* * Split buddy pages returned by expand() are received here in * physical page order. The page is added to the tail of @@ -3160,7 +3159,6 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, * pages are ordered properly. */ list_add_tail(&page->pcp_list, list); - allocated++; if (is_migrate_cma(get_pcppage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); @@ -3174,6 +3172,22 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock_irqrestore(&zone->lock, flags); + + /* + * Pages are appended to the pcp list without checking to reduce the + * time holding the zone lock. Checking the appended pages happens right + * after the critical section while still holding the pcp lock. + */ + pos = list_first_entry(prev_tail, struct page, pcp_list); + list_for_each_entry_safe_from(pos, n, list, pcp_list) { + if (unlikely(check_pcp_refill(pos, order))) { + list_del(&pos->pcp_list); + continue; + } + + allocated++; + } + return allocated; } -- GitLab From 700d2e9a36b93601270c1e15550acde2521386c5 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 16 Feb 2023 10:51:31 +0100 Subject: [PATCH 1445/5631] mm, page_alloc: reduce page alloc/free sanity checks Historically, we have performed sanity checks on all struct pages being allocated or freed, making sure they have no unexpected page flags or certain field values. This can detect insufficient cleanup and some cases of use-after-free, although on its own it can't always identify the culprit. The result is a warning and the "bad page" being leaked. The checks do need some cpu cycles, so in 4.7 with commits 479f854a207c ("mm, page_alloc: defer debugging checks of pages allocated from the PCP") and 4db7548ccbd9 ("mm, page_alloc: defer debugging checks of freed pages until a PCP drain") they were no longer performed in the hot paths when allocating and freeing from pcplists, but only when pcplists are bypassed, refilled or drained. For debugging purposes, with CONFIG_DEBUG_VM enabled the checks were instead still done in the hot paths and not when refilling or draining pcplists. With 4462b32c9285 ("mm, page_alloc: more extensive free page checking with debug_pagealloc"), enabling debug_pagealloc also moved the sanity checks back to hot pahs. When both debug_pagealloc and CONFIG_DEBUG_VM are enabled, the checks are done both in hotpaths and pcplist refill/drain. Even though the non-debug default today might seem to be a sensible tradeoff between overhead and ability to detect bad pages, on closer look it's arguably not. As most allocations go through the pcplists, catching any bad pages when refilling or draining pcplists has only a small chance, insufficient for debugging or serious hardening purposes. On the other hand the cost of the checks is concentrated in the already expensive drain/refill batching operations, and those are done under the often contended zone lock. That was recently identified as an issue for page allocation and the zone lock contention reduced by moving the checks outside of the locked section with a patch "mm: reduce lock contention of pcp buffer refill", but the cost of the checks is still visible compared to their removal [1]. In the pcplist draining path free_pcppages_bulk() the checks are still done under zone->lock. Thus, remove the checks from pcplist refill and drain paths completely. Introduce a static key check_pages_enabled to control checks during page allocation a freeing (whether pcplist is used or bypassed). The static key is enabled if either is true: - kernel is built with CONFIG_DEBUG_VM=y (debugging) - debug_pagealloc or page poisoning is boot-time enabled (debugging) - init_on_alloc or init_on_free is boot-time enabled (hardening) The resulting user visible changes: - no checks when draining/refilling pcplists - less overhead, with likely no practical reduction of ability to catch bad pages - no checks when bypassing pcplists in default config (no debugging/hardening) - less overhead etc. as above - on typical hardened kernels [2], checks are now performed on each page allocation/free (previously only when bypassing/draining/refilling pcplists) - the init_on_alloc/init_on_free enabled should be sufficient indication for preferring more costly alloc/free operations for hardening purposes and we shouldn't need to introduce another toggle - code (various wrappers) removal and simplification [1] https://lore.kernel.org/all/68ba44d8-6899-c018-dcb3-36f3a96e6bea@sra.uni-hannover.de/ [2] https://lore.kernel.org/all/63ebc499.a70a0220.9ac51.29ea@mx.google.com/ [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: make check_pages_enabled static] Link: https://lkml.kernel.org/r/20230216095131.17336-1-vbabka@suse.cz Reported-by: Alexander Halbuer Reported-by: Andrew Morton Signed-off-by: Vlastimil Babka Cc: Kees Cook Cc: Mel Gorman Signed-off-by: Andrew Morton --- mm/page_alloc.c | 187 ++++++++++++++---------------------------------- 1 file changed, 52 insertions(+), 135 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a853f0aa5d31..a109444e9f44 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -253,6 +253,9 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); +/* perform sanity checks on struct pages being allocated or freed */ +static DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); + static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -893,6 +896,7 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, void __init init_mem_debugging_and_hardening(void) { bool page_poisoning_requested = false; + bool want_check_pages = false; #ifdef CONFIG_PAGE_POISONING /* @@ -904,6 +908,7 @@ void __init init_mem_debugging_and_hardening(void) debug_pagealloc_enabled())) { static_branch_enable(&_page_poisoning_enabled); page_poisoning_requested = true; + want_check_pages = true; } #endif @@ -915,31 +920,41 @@ void __init init_mem_debugging_and_hardening(void) _init_on_free_enabled_early = false; } - if (_init_on_alloc_enabled_early) + if (_init_on_alloc_enabled_early) { + want_check_pages = true; static_branch_enable(&init_on_alloc); - else + } else { static_branch_disable(&init_on_alloc); + } - if (_init_on_free_enabled_early) + if (_init_on_free_enabled_early) { + want_check_pages = true; static_branch_enable(&init_on_free); - else + } else { static_branch_disable(&init_on_free); + } if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); #ifdef CONFIG_DEBUG_PAGEALLOC - if (!debug_pagealloc_enabled()) - return; - - static_branch_enable(&_debug_pagealloc_enabled); - - if (!debug_guardpage_minorder()) - return; + if (debug_pagealloc_enabled()) { + want_check_pages = true; + static_branch_enable(&_debug_pagealloc_enabled); - static_branch_enable(&_debug_guardpage_enabled); + if (debug_guardpage_minorder()) + static_branch_enable(&_debug_guardpage_enabled); + } #endif + + /* + * Any page debugging or hardening option also enables sanity checking + * of struct pages being allocated or freed. With CONFIG_DEBUG_VM it's + * enabled already. + */ + if (!IS_ENABLED(CONFIG_DEBUG_VM) && want_check_pages) + static_branch_enable(&check_pages_enabled); } static inline void set_buddy_order(struct page *page, unsigned int order) @@ -1395,7 +1410,7 @@ static void kernel_init_pages(struct page *page, int numpages) } static __always_inline bool free_pages_prepare(struct page *page, - unsigned int order, bool check_free, fpi_t fpi_flags) + unsigned int order, fpi_t fpi_flags) { int bad = 0; bool skip_kasan_poison = should_skip_kasan_poison(page, fpi_flags); @@ -1433,9 +1448,11 @@ static __always_inline bool free_pages_prepare(struct page *page, for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_pages_check(page, page + i); - if (unlikely(free_page_is_bad(page + i))) { - bad++; - continue; + if (static_branch_unlikely(&check_pages_enabled)) { + if (unlikely(free_page_is_bad(page + i))) { + bad++; + continue; + } } (page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; } @@ -1444,10 +1461,12 @@ static __always_inline bool free_pages_prepare(struct page *page, page->mapping = NULL; if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); - if (check_free && free_page_is_bad(page)) - bad++; - if (bad) - return false; + if (static_branch_unlikely(&check_pages_enabled)) { + if (free_page_is_bad(page)) + bad++; + if (bad) + return false; + } page_cpupid_reset_last(page); page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; @@ -1493,46 +1512,6 @@ static __always_inline bool free_pages_prepare(struct page *page, return true; } -#ifdef CONFIG_DEBUG_VM -/* - * With DEBUG_VM enabled, order-0 pages are checked immediately when being freed - * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when - * moved from pcp lists to free lists. - */ -static bool free_pcp_prepare(struct page *page, unsigned int order) -{ - return free_pages_prepare(page, order, true, FPI_NONE); -} - -/* return true if this page has an inappropriate state */ -static bool bulkfree_pcp_prepare(struct page *page) -{ - if (debug_pagealloc_enabled_static()) - return free_page_is_bad(page); - else - return false; -} -#else -/* - * With DEBUG_VM disabled, order-0 pages being freed are checked only when - * moving from pcp lists to free list in order to reduce overhead. With - * debug_pagealloc enabled, they are checked also immediately when being freed - * to the pcp lists. - */ -static bool free_pcp_prepare(struct page *page, unsigned int order) -{ - if (debug_pagealloc_enabled_static()) - return free_pages_prepare(page, order, true, FPI_NONE); - else - return free_pages_prepare(page, order, false, FPI_NONE); -} - -static bool bulkfree_pcp_prepare(struct page *page) -{ - return free_page_is_bad(page); -} -#endif /* CONFIG_DEBUG_VM */ - /* * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone. @@ -1592,9 +1571,6 @@ static void free_pcppages_bulk(struct zone *zone, int count, count -= nr_pages; pcp->count -= nr_pages; - if (bulkfree_pcp_prepare(page)) - continue; - /* MIGRATE_ISOLATE page should not go to pcplists */ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); /* Pageblock could have been isolated meanwhile */ @@ -1707,7 +1683,7 @@ static void __free_pages_ok(struct page *page, unsigned int order, unsigned long pfn = page_to_pfn(page); struct zone *zone = page_zone(page); - if (!free_pages_prepare(page, order, true, fpi_flags)) + if (!free_pages_prepare(page, order, fpi_flags)) return; /* @@ -2383,7 +2359,7 @@ static void check_new_page_bad(struct page *page) /* * This page is about to be returned from the page allocator */ -static inline int check_new_page(struct page *page) +static int check_new_page(struct page *page) { if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) @@ -2393,56 +2369,20 @@ static inline int check_new_page(struct page *page) return 1; } -static bool check_new_pages(struct page *page, unsigned int order) +static inline bool check_new_pages(struct page *page, unsigned int order) { - int i; - for (i = 0; i < (1 << order); i++) { - struct page *p = page + i; + if (static_branch_unlikely(&check_pages_enabled)) { + for (int i = 0; i < (1 << order); i++) { + struct page *p = page + i; - if (unlikely(check_new_page(p))) - return true; + if (unlikely(check_new_page(p))) + return true; + } } return false; } -#ifdef CONFIG_DEBUG_VM -/* - * With DEBUG_VM enabled, order-0 pages are checked for expected state when - * being allocated from pcp lists. With debug_pagealloc also enabled, they are - * also checked when pcp lists are refilled from the free lists. - */ -static inline bool check_pcp_refill(struct page *page, unsigned int order) -{ - if (debug_pagealloc_enabled_static()) - return check_new_pages(page, order); - else - return false; -} - -static inline bool check_new_pcp(struct page *page, unsigned int order) -{ - return check_new_pages(page, order); -} -#else -/* - * With DEBUG_VM disabled, free order-0 pages are checked for expected state - * when pcp lists are being refilled from the free lists. With debug_pagealloc - * enabled, they are also checked when being allocated from the pcp lists. - */ -static inline bool check_pcp_refill(struct page *page, unsigned int order) -{ - return check_new_pages(page, order); -} -static inline bool check_new_pcp(struct page *page, unsigned int order) -{ - if (debug_pagealloc_enabled_static()) - return check_new_pages(page, order); - else - return false; -} -#endif /* CONFIG_DEBUG_VM */ - static inline bool should_skip_kasan_unpoison(gfp_t flags) { /* Don't skip if a software KASAN mode is enabled. */ @@ -3137,9 +3077,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, int migratetype, unsigned int alloc_flags) { unsigned long flags; - int i, allocated = 0; - struct list_head *prev_tail = list->prev; - struct page *pos, *n; + int i; spin_lock_irqsave(&zone->lock, flags); for (i = 0; i < count; ++i) { @@ -3164,31 +3102,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, -(1 << order)); } - /* - * i pages were removed from the buddy list even if some leak due - * to check_pcp_refill failing so adjust NR_FREE_PAGES based - * on i. Do not confuse with 'allocated' which is the number of - * pages added to the pcp list. - */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock_irqrestore(&zone->lock, flags); - /* - * Pages are appended to the pcp list without checking to reduce the - * time holding the zone lock. Checking the appended pages happens right - * after the critical section while still holding the pcp lock. - */ - pos = list_first_entry(prev_tail, struct page, pcp_list); - list_for_each_entry_safe_from(pos, n, list, pcp_list) { - if (unlikely(check_pcp_refill(pos, order))) { - list_del(&pos->pcp_list); - continue; - } - - allocated++; - } - - return allocated; + return i; } #ifdef CONFIG_NUMA @@ -3399,7 +3316,7 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn, { int migratetype; - if (!free_pcp_prepare(page, order)) + if (!free_pages_prepare(page, order, FPI_NONE)) return false; migratetype = get_pfnblock_migratetype(page, pfn); @@ -3805,7 +3722,7 @@ struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, page = list_first_entry(list, struct page, pcp_list); list_del(&page->pcp_list); pcp->count -= 1 << order; - } while (check_new_pcp(page, order)); + } while (check_new_pages(page, order)); return page; } -- GitLab From a1b92a3f14984c96ace381f204b5d72c0805296e Mon Sep 17 00:00:00 2001 From: Muhammad Usama Anjum Date: Fri, 17 Feb 2023 15:55:58 +0500 Subject: [PATCH 1446/5631] mm/userfaultfd: support WP on multiple VMAs mwriteprotect_range() errors out if [start, end) doesn't fall in one VMA. We are facing a use case where multiple VMAs are present in one range of interest. For example, the following pseudocode reproduces the error which we are trying to fix: - Allocate memory of size 16 pages with PROT_NONE with mmap - Register userfaultfd - Change protection of the first half (1 to 8 pages) of memory to PROT_READ | PROT_WRITE. This breaks the memory area in two VMAs. - Now UFFDIO_WRITEPROTECT_MODE_WP on the whole memory of 16 pages errors out. This is a simple use case where user may or may not know if the memory area has been divided into multiple VMAs. We need an implementation which doesn't disrupt the already present users. So keeping things simple, stop going over all the VMAs if any one of the VMA hasn't been registered in WP mode. While at it, remove the un-needed error check as well. [akpm@linux-foundation.org: s/VM_WARN_ON_ONCE/VM_WARN_ONCE/ to fix build] Link: https://lkml.kernel.org/r/20230217105558.832710-1-usama.anjum@collabora.com Signed-off-by: Muhammad Usama Anjum Acked-by: Peter Xu Acked-by: David Hildenbrand Reported-by: Paul Gofman Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 41 ++++++++++++++++++++++++----------------- 1 file changed, 24 insertions(+), 17 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 53c3d916ff66..23cabd02ac52 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -717,6 +717,8 @@ long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, struct mmu_gather tlb; long ret; + VM_WARN_ONCE(start < dst_vma->vm_start || start + len > dst_vma->vm_end, + "The address range exceeds VMA boundary.\n"); if (enable_wp) mm_cp_flags = MM_CP_UFFD_WP; else @@ -741,9 +743,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing) { + unsigned long end = start + len; + unsigned long _start, _end; struct vm_area_struct *dst_vma; unsigned long page_mask; long err; + VMA_ITERATOR(vmi, dst_mm, start); /* * Sanitize the command parameters: @@ -766,28 +771,30 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, goto out_unlock; err = -ENOENT; - dst_vma = find_dst_vma(dst_mm, start, len); + for_each_vma_range(vmi, dst_vma, end) { - if (!dst_vma) - goto out_unlock; - if (!userfaultfd_wp(dst_vma)) - goto out_unlock; - if (!vma_can_userfault(dst_vma, dst_vma->vm_flags)) - goto out_unlock; + if (!userfaultfd_wp(dst_vma)) { + err = -ENOENT; + break; + } - if (is_vm_hugetlb_page(dst_vma)) { - err = -EINVAL; - page_mask = vma_kernel_pagesize(dst_vma) - 1; - if ((start & page_mask) || (len & page_mask)) - goto out_unlock; - } + if (is_vm_hugetlb_page(dst_vma)) { + err = -EINVAL; + page_mask = vma_kernel_pagesize(dst_vma) - 1; + if ((start & page_mask) || (len & page_mask)) + break; + } - err = uffd_wp_range(dst_mm, dst_vma, start, len, enable_wp); + _start = max(dst_vma->vm_start, start); + _end = min(dst_vma->vm_end, end); - /* Return 0 on success, <0 on failures */ - if (err > 0) - err = 0; + err = uffd_wp_range(dst_mm, dst_vma, _start, _end - _start, enable_wp); + /* Return 0 on success, <0 on failures */ + if (err < 0) + break; + err = 0; + } out_unlock: mmap_read_unlock(dst_mm); return err; -- GitLab From d155df53f31068c3340733d586eb9b3ddfd70fc5 Mon Sep 17 00:00:00 2001 From: Ma Wupeng Date: Fri, 17 Feb 2023 10:56:15 +0800 Subject: [PATCH 1447/5631] x86/mm/pat: clear VM_PAT if copy_p4d_range failed Syzbot reports a warning in untrack_pfn(). Digging into the root we found that this is due to memory allocation failure in pmd_alloc_one. And this failure is produced due to failslab. In copy_page_range(), memory alloaction for pmd failed. During the error handling process in copy_page_range(), mmput() is called to remove all vmas. While untrack_pfn this empty pfn, warning happens. Here's a simplified flow: dup_mm dup_mmap copy_page_range copy_p4d_range copy_pud_range copy_pmd_range pmd_alloc __pmd_alloc pmd_alloc_one page = alloc_pages(gfp, 0); if (!page) return NULL; mmput exit_mmap unmap_vmas unmap_single_vma untrack_pfn follow_phys WARN_ON_ONCE(1); Since this vma is not generate successfully, we can clear flag VM_PAT. In this case, untrack_pfn() will not be called while cleaning this vma. Function untrack_pfn_moved() has also been renamed to fit the new logic. Link: https://lkml.kernel.org/r/20230217025615.1595558-1-mawupeng1@huawei.com Signed-off-by: Ma Wupeng Reported-by: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Peter Zijlstra Cc: Suresh Siddha Cc: Toshi Kani Signed-off-by: Andrew Morton --- arch/x86/mm/pat/memtype.c | 12 ++++++++---- include/linux/pgtable.h | 7 ++++--- mm/memory.c | 1 + mm/mremap.c | 2 +- 4 files changed, 14 insertions(+), 8 deletions(-) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 46a00aa858b6..de10800cd4dd 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -1073,11 +1073,15 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, } /* - * untrack_pfn_moved is called, while mremapping a pfnmap for a new region, - * with the old vma after its pfnmap page table has been removed. The new - * vma has a new pfnmap to the same pfn & cache type with VM_PAT set. + * untrack_pfn_clear is called if the following situation fits: + * + * 1) while mremapping a pfnmap for a new region, with the old vma after + * its pfnmap page table has been removed. The new vma has a new pfnmap + * to the same pfn & cache type with VM_PAT set. + * 2) while duplicating vm area, the new vma fails to copy the pgtable from + * old vma. */ -void untrack_pfn_moved(struct vm_area_struct *vma) +void untrack_pfn_clear(struct vm_area_struct *vma) { vm_flags_clear(vma, VM_PAT); } diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c63cd44777ec..9dc936bc77d1 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1191,9 +1191,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma, } /* - * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + * untrack_pfn_clear is called while mremapping a pfnmap for a new region + * or fails to copy pgtable during duplicate vm area. */ -static inline void untrack_pfn_moved(struct vm_area_struct *vma) +static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else @@ -1205,7 +1206,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); -extern void untrack_pfn_moved(struct vm_area_struct *vma); +extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU diff --git a/mm/memory.c b/mm/memory.c index f456f3b5049c..bfa3100ec5a3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1290,6 +1290,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { + untrack_pfn_clear(dst_vma); ret = -ENOMEM; break; } diff --git a/mm/mremap.c b/mm/mremap.c index 411a85682b58..1ddf7beb62e9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -683,7 +683,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) - untrack_pfn_moved(vma); + untrack_pfn_clear(vma); if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) { /* We always clear VM_LOCKED[ONFAULT] on the old vma */ -- GitLab From 9a52b2f32a0942047348b30f866b846da5fcf4e3 Mon Sep 17 00:00:00 2001 From: "T.J. Alumbaugh" Date: Tue, 14 Feb 2023 03:54:44 +0000 Subject: [PATCH 1448/5631] mm: multi-gen LRU: clean up sysfs code This patch cleans up the sysfs code. Specifically, 1. use sysfs_emit(), 2. use __ATTR_RW(), and 3. constify multi-gen LRU struct attribute_group. Link: https://lkml.kernel.org/r/20230214035445.1250139-1-talumbau@google.com Signed-off-by: T.J. Alumbaugh Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 +- mm/vmscan.c | 22 +++++++++------------- 2 files changed, 10 insertions(+), 14 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9fb1b03b83b2..bf8786d45b31 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1369,7 +1369,7 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ - struct lru_gen_mm_walk mm_walk; + struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 9c1c5e8b24b8..7ac7d1ec13e0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -5663,14 +5663,14 @@ static void lru_gen_change_state(bool enabled) * sysfs interface ******************************************************************************/ -static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); + return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ -static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, - const char *buf, size_t len) +static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t len) { unsigned int msecs; @@ -5682,11 +5682,9 @@ static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, return len; } -static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR( - min_ttl_ms, 0644, show_min_ttl, store_min_ttl -); +static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); -static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; @@ -5703,7 +5701,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ -static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr, +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; @@ -5730,9 +5728,7 @@ static ssize_t store_enabled(struct kobject *kobj, struct kobj_attribute *attr, return len; } -static struct kobj_attribute lru_gen_enabled_attr = __ATTR( - enabled, 0644, show_enabled, store_enabled -); +static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, @@ -5740,7 +5736,7 @@ static struct attribute *lru_gen_attrs[] = { NULL }; -static struct attribute_group lru_gen_attr_group = { +static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; -- GitLab From 32d32ef140de3cc3f6817999415a72f7b0cb52f5 Mon Sep 17 00:00:00 2001 From: "T.J. Alumbaugh" Date: Tue, 14 Feb 2023 03:54:45 +0000 Subject: [PATCH 1449/5631] mm: multi-gen LRU: improve design doc This patch improves the design doc. Specifically, 1. add a section for the per-memcg mm_struct list, and 2. add a section for the PID controller. Link: https://lkml.kernel.org/r/20230214035445.1250139-2-talumbau@google.com Signed-off-by: T.J. Alumbaugh Cc: Yu Zhao Signed-off-by: Andrew Morton --- Documentation/mm/multigen_lru.rst | 44 +++++++++++++++++++++++++++---- mm/vmscan.c | 2 +- 2 files changed, 40 insertions(+), 6 deletions(-) diff --git a/Documentation/mm/multigen_lru.rst b/Documentation/mm/multigen_lru.rst index 5f1f6ecbb79b..52ed5092022f 100644 --- a/Documentation/mm/multigen_lru.rst +++ b/Documentation/mm/multigen_lru.rst @@ -103,7 +103,8 @@ moving across tiers only involves atomic operations on ``folio->flags`` and therefore has a negligible cost. A feedback loop modeled after the PID controller monitors refaults over all the tiers from anon and file types and decides which tiers from which types to -evict or protect. +evict or protect. The desired effect is to balance refault percentages +between anon and file types proportional to the swappiness level. There are two conceptually independent procedures: the aging and the eviction. They form a closed-loop system, i.e., the page reclaim. @@ -156,6 +157,27 @@ This time-based approach has the following advantages: and memory sizes. 2. It is more reliable because it is directly wired to the OOM killer. +``mm_struct`` list +------------------ +An ``mm_struct`` list is maintained for each memcg, and an +``mm_struct`` follows its owner task to the new memcg when this task +is migrated. + +A page table walker iterates ``lruvec_memcg()->mm_list`` and calls +``walk_page_range()`` with each ``mm_struct`` on this list to scan +PTEs. When multiple page table walkers iterate the same list, each of +them gets a unique ``mm_struct``, and therefore they can run in +parallel. + +Page table walkers ignore any misplaced pages, e.g., if an +``mm_struct`` was migrated, pages left in the previous memcg will be +ignored when the current memcg is under reclaim. Similarly, page table +walkers will ignore pages from nodes other than the one under reclaim. + +This infrastructure also tracks the usage of ``mm_struct`` between +context switches so that page table walkers can skip processes that +have been sleeping since the last iteration. + Rmap/PT walk feedback --------------------- Searching the rmap for PTEs mapping each page on an LRU list (to test @@ -170,7 +192,7 @@ promotes hot pages. If the scan was done cacheline efficiently, it adds the PMD entry pointing to the PTE table to the Bloom filter. This forms a feedback loop between the eviction and the aging. -Bloom Filters +Bloom filters ------------- Bloom filters are a space and memory efficient data structure for set membership test, i.e., test if an element is not in the set or may be @@ -186,6 +208,18 @@ is false positive, the cost is an additional scan of a range of PTEs, which may yield hot pages anyway. Parameters of the filter itself can control the false positive rate in the limit. +PID controller +-------------- +A feedback loop modeled after the Proportional-Integral-Derivative +(PID) controller monitors refaults over anon and file types and +decides which type to evict when both types are available from the +same generation. + +The PID controller uses generations rather than the wall clock as the +time domain because a CPU can scan pages at different rates under +varying memory pressure. It calculates a moving average for each new +generation to avoid being permanently locked in a suboptimal state. + Memcg LRU --------- An memcg LRU is a per-node LRU of memcgs. It is also an LRU of LRUs, @@ -223,9 +257,9 @@ parts: * Generations * Rmap walks -* Page table walks -* Bloom filters -* PID controller +* Page table walks via ``mm_struct`` list +* Bloom filters for rmap/PT walk feedback +* PID controller for refault feedback The aging and the eviction form a producer-consumer model; specifically, the latter drives the former by the sliding window over diff --git a/mm/vmscan.c b/mm/vmscan.c index 7ac7d1ec13e0..9414226218f0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3604,7 +3604,7 @@ static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq) } /****************************************************************************** - * refault feedback loop + * PID controller ******************************************************************************/ /* -- GitLab From 62bf1258ec90554c3c0925951149cfe4b67a3e98 Mon Sep 17 00:00:00 2001 From: Taejoon Song Date: Mon, 6 Feb 2023 04:00:36 +0900 Subject: [PATCH 1450/5631] mm/zswap: try to avoid worst-case scenario on same element pages The worst-case scenario on finding same element pages is that almost all elements are same at the first glance but only last few elements are different. Since the same element tends to be grouped from the beginning of the pages, if we check the first element with the last element before looping through all elements, we might have some chances to quickly detect non-same element pages. 1. Test is done under LG webOS TV (64-bit arch) 2. Dump the swap-out pages (~819200 pages) 3. Analyze the pages with simple test script which counts the iteration number and measures the speed at off-line Under 64-bit arch, the worst iteration count is PAGE_SIZE / 8 bytes = 512. The speed is based on the time to consume page_same_filled() function only. The result, on average, is listed as below: Num of Iter Speed(MB/s) Looping-Forward (Orig) 38 99265 Looping-Backward 36 102725 Last-element-check (This Patch) 33 125072 The result shows that the average iteration count decreases by 13% and the speed increases by 25% with this patch. This patch does not increase the overall time complexity, though. I also ran simpler version which uses backward loop. Just looping backward also makes some improvement, but less than this patch. A similar change has already been made to zram in 90f82cbfe502 ("zram: try to avoid worst-case scenario on same element pages"). Link: https://lkml.kernel.org/r/20230205190036.1730134-1-taejoon.song@lge.com Signed-off-by: Taejoon Song Reviewed-by: Sergey Senozhatsky Cc: Dan Streetman Cc: Seth Jennings Cc: Taejoon Song Cc: Vitaly Wool Cc: Minchan Kim Cc: Signed-off-by: Andrew Morton --- mm/zswap.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index f6c89049cf70..2f0ebd8bc620 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1073,15 +1073,23 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) static int zswap_is_page_same_filled(void *ptr, unsigned long *value) { - unsigned int pos; unsigned long *page; + unsigned long val; + unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1; page = (unsigned long *)ptr; - for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) { - if (page[pos] != page[0]) + val = page[0]; + + if (val != page[last_pos]) + return 0; + + for (pos = 1; pos < last_pos; pos++) { + if (val != page[pos]) return 0; } - *value = page[0]; + + *value = val; + return 1; } -- GitLab From 6cad87b0d216c6acdc40c5531c7b62db33fef5b1 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:33 +1000 Subject: [PATCH 1451/5631] kthread: simplify kthread_use_mm refcounting Patch series "shoot lazy tlbs (lazy tlb refcount scalability improvement)", v7. This series improves scalability of context switching between user and kernel threads on large systems with a threaded process spread across a lot of CPUs. Discussion of v6 here: https://lore.kernel.org/linux-mm/20230118080011.2258375-1-npiggin@gmail.com/ This patch (of 5): Remove the special case avoiding refcounting when the mm to be used is the same as the kernel thread's active (lazy tlb) mm. kthread_use_mm() should not be such a performance critical path that this matters much. This simplifies a later change to lazy tlb mm refcounting. Link: https://lkml.kernel.org/r/20230203071837.1136453-1-npiggin@gmail.com Link: https://lkml.kernel.org/r/20230203071837.1136453-2-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Dave Hansen Cc: Linus Torvalds Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Signed-off-by: Andrew Morton --- kernel/kthread.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/kernel/kthread.c b/kernel/kthread.c index 7e6751b29101..1f1b60f1a746 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1415,14 +1415,13 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); + mmgrab(mm); + task_lock(tsk); /* Hold off tlb flush IPIs while switching mm's */ local_irq_disable(); active_mm = tsk->active_mm; - if (active_mm != mm) { - mmgrab(mm); - tsk->active_mm = mm; - } + tsk->active_mm = mm; tsk->mm = mm; membarrier_update_current_mm(mm); switch_mm_irqs_off(active_mm, mm, tsk); @@ -1439,12 +1438,9 @@ void kthread_use_mm(struct mm_struct *mm) * memory barrier after storing to tsk->mm, before accessing * user-space memory. A full memory barrier for membarrier * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by - * mmdrop(), or explicitly with smp_mb(). + * mmdrop(). */ - if (active_mm != mm) - mmdrop(active_mm); - else - smp_mb(); + mmdrop(active_mm); } EXPORT_SYMBOL_GPL(kthread_use_mm); -- GitLab From aa464ba9a1e444d5ef95bb63ee3b2ef26fc96ed7 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:34 +1000 Subject: [PATCH 1452/5631] lazy tlb: introduce lazy tlb mm refcount helper functions Add explicit _lazy_tlb annotated functions for lazy tlb mm refcounting. This makes the lazy tlb mm references more obvious, and allows the refcounting scheme to be modified in later changes. There is no functional change with this patch. Link: https://lkml.kernel.org/r/20230203071837.1136453-3-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm/mach-rpc/ecard.c | 2 +- arch/powerpc/kernel/smp.c | 2 +- arch/powerpc/mm/book3s64/radix_tlb.c | 4 ++-- fs/exec.c | 2 +- include/linux/sched/mm.h | 16 ++++++++++++++++ kernel/cpu.c | 2 +- kernel/exit.c | 2 +- kernel/kthread.c | 12 ++++++++++-- kernel/sched/core.c | 15 ++++++++------- 9 files changed, 41 insertions(+), 16 deletions(-) diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 53813f9464a2..c30df1097c52 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -253,7 +253,7 @@ static int ecard_init_mm(void) current->mm = mm; current->active_mm = mm; activate_mm(active_mm, mm); - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); ecard_init_pgtables(mm); return 0; } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6b90f10a6c81..7db6b3faea65 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1611,7 +1611,7 @@ void start_secondary(void *unused) if (IS_ENABLED(CONFIG_PPC32)) setup_kup(); - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); current->active_mm = &init_mm; smp_store_cpu_info(cpu); diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index e50bc5fc7ddf..ce804b7bf84e 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -797,10 +797,10 @@ void exit_lazy_flush_tlb(struct mm_struct *mm, bool always_flush) if (current->active_mm == mm) { WARN_ON_ONCE(current->mm != NULL); /* Is a kernel thread and is using mm as the lazy tlb */ - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); current->active_mm = &init_mm; switch_mm_irqs_off(mm, &init_mm, current); - mmdrop(mm); + mmdrop_lazy_tlb(mm); } /* diff --git a/fs/exec.c b/fs/exec.c index 7c44d0c65b1b..87cf3a2f0e9a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1034,7 +1034,7 @@ static int exec_mmap(struct mm_struct *mm) mmput(old_mm); return 0; } - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); return 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..5376caf6fcf3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -79,6 +79,22 @@ static inline void mmdrop_sched(struct mm_struct *mm) } #endif +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + mmdrop(mm); +} + +static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) +{ + mmdrop_sched(mm); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/kernel/cpu.c b/kernel/cpu.c index 6c0a92ca6bb5..189895288d9d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -623,7 +623,7 @@ static int finish_cpu(unsigned int cpu) */ if (mm != &init_mm) idle->active_mm = &init_mm; - mmdrop(mm); + mmdrop_lazy_tlb(mm); return 0; } diff --git a/kernel/exit.c b/kernel/exit.c index f2afdb0add7c..86902cb5ab78 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -537,7 +537,7 @@ static void exit_mm(void) return; sync_mm_rss(mm); mmap_read_lock(mm); - mmgrab(mm); + mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); diff --git a/kernel/kthread.c b/kernel/kthread.c index 1f1b60f1a746..470708c205e8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1415,6 +1415,11 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); + /* + * It is possible for mm to be the same as tsk->active_mm, but + * we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm), + * because these references are not equivalent. + */ mmgrab(mm); task_lock(tsk); @@ -1438,9 +1443,9 @@ void kthread_use_mm(struct mm_struct *mm) * memory barrier after storing to tsk->mm, before accessing * user-space memory. A full memory barrier for membarrier * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by - * mmdrop(). + * mmdrop_lazy_tlb(). */ - mmdrop(active_mm); + mmdrop_lazy_tlb(active_mm); } EXPORT_SYMBOL_GPL(kthread_use_mm); @@ -1468,10 +1473,13 @@ void kthread_unuse_mm(struct mm_struct *mm) local_irq_disable(); tsk->mm = NULL; membarrier_update_current_mm(NULL); + mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); local_irq_enable(); task_unlock(tsk); + + mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0d18c3969f90..143e46bd2a68 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5203,13 +5203,14 @@ static struct rq *finish_task_switch(struct task_struct *prev) * rq->curr, before returning to userspace, so provide them here: * * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly - * provided by mmdrop(), + * provided by mmdrop_lazy_tlb(), * - a sync_core for SYNC_CORE. */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop_sched(mm); + mmdrop_lazy_tlb_sched(mm); } + if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); @@ -5266,9 +5267,9 @@ context_switch(struct rq *rq, struct task_struct *prev, /* * kernel -> kernel lazy + transfer active - * user -> kernel lazy + mmgrab() active + * user -> kernel lazy + mmgrab_lazy_tlb() active * - * kernel -> user switch + mmdrop() active + * kernel -> user switch + mmdrop_lazy_tlb() active * user -> user switch */ if (!next->mm) { // to kernel @@ -5276,7 +5277,7 @@ context_switch(struct rq *rq, struct task_struct *prev, next->active_mm = prev->active_mm; if (prev->mm) // from user - mmgrab(prev->active_mm); + mmgrab_lazy_tlb(prev->active_mm); else prev->active_mm = NULL; } else { // to user @@ -5293,7 +5294,7 @@ context_switch(struct rq *rq, struct task_struct *prev, lru_gen_use_mm(next->mm); if (!prev->mm) { // from kernel - /* will mmdrop() in finish_task_switch(). */ + /* will mmdrop_lazy_tlb() in finish_task_switch(). */ rq->prev_mm = prev->active_mm; prev->active_mm = NULL; } @@ -9935,7 +9936,7 @@ void __init sched_init(void) /* * The boot idle thread does lazy MMU switching as well: */ - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); enter_lazy_tlb(&init_mm, current); /* -- GitLab From 88e3009b5283bbd41447f0352d0b9df16cf6f183 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:35 +1000 Subject: [PATCH 1453/5631] lazy tlb: allow lazy tlb mm refcounting to be configurable Add CONFIG_MMU_TLB_REFCOUNT which enables refcounting of the lazy tlb mm when it is context switched. This can be disabled by architectures that don't require this refcounting if they clean up lazy tlb mms when the last refcount is dropped. Currently this is always enabled, so the patch introduces no functional change. Link: https://lkml.kernel.org/r/20230203071837.1136453-4-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- Documentation/mm/active_mm.rst | 6 ++++++ arch/Kconfig | 17 +++++++++++++++++ include/linux/sched/mm.h | 18 +++++++++++++++--- 3 files changed, 38 insertions(+), 3 deletions(-) diff --git a/Documentation/mm/active_mm.rst b/Documentation/mm/active_mm.rst index 45d89f8fb3a8..d096fc091e23 100644 --- a/Documentation/mm/active_mm.rst +++ b/Documentation/mm/active_mm.rst @@ -2,6 +2,12 @@ Active MM ========= +Note, the mm_count refcount may no longer include the "lazy" users +(running tasks with ->active_mm == mm && ->mm == NULL) on kernels +with CONFIG_MMU_LAZY_TLB_REFCOUNT=n. Taking and releasing these lazy +references must be done with mmgrab_lazy_tlb() and mmdrop_lazy_tlb() +helpers, which abstract this config option. + :: List: linux-kernel diff --git a/arch/Kconfig b/arch/Kconfig index e3511afbb7f2..643f8a04141e 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -465,6 +465,23 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM irqs disabled over activate_mm. Architectures that do IPI based TLB shootdowns should enable this. +# Use normal mm refcounting for MMU_LAZY_TLB kernel thread references. +# MMU_LAZY_TLB_REFCOUNT=n can improve the scalability of context switching +# to/from kernel threads when the same mm is running on a lot of CPUs (a large +# multi-threaded application), by reducing contention on the mm refcount. +# +# This can be disabled if the architecture ensures no CPUs are using an mm as a +# "lazy tlb" beyond its final refcount (i.e., by the time __mmdrop frees the mm +# or its kernel page tables). This could be arranged by arch_exit_mmap(), or +# final exit(2) TLB flush, for example. +# +# To implement this, an arch *must*: +# Ensure the _lazy_tlb variants of mmgrab/mmdrop are used when manipulating +# the lazy tlb reference of a kthread's ->active_mm (non-arch code has been +# converted already). +config MMU_LAZY_TLB_REFCOUNT + def_bool y + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 5376caf6fcf3..689dbe812563 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -82,17 +82,29 @@ static inline void mmdrop_sched(struct mm_struct *mm) /* Helpers for lazy TLB mm refcounting */ static inline void mmgrab_lazy_tlb(struct mm_struct *mm) { - mmgrab(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmgrab(mm); } static inline void mmdrop_lazy_tlb(struct mm_struct *mm) { - mmdrop(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { + mmdrop(mm); + } else { + /* + * mmdrop_lazy_tlb must provide a full memory barrier, see the + * membarrier comment finish_task_switch which relies on this. + */ + smp_mb(); + } } static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) { - mmdrop_sched(mm); + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmdrop_sched(mm); + else + smp_mb(); /* see mmdrop_lazy_tlb() above */ } /** -- GitLab From 2655421ae69fa479df1575cb2630af9131d28939 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:36 +1000 Subject: [PATCH 1454/5631] lazy tlb: shoot lazies, non-refcounting lazy tlb mm reference handling scheme On big systems, the mm refcount can become highly contented when doing a lot of context switching with threaded applications. user<->idle switch is one of the important cases. Abandoning lazy tlb entirely slows this switching down quite a bit in the common uncontended case, so that is not viable. Implement a scheme where lazy tlb mm references do not contribute to the refcount, instead they get explicitly removed when the refcount reaches zero. The final mmdrop() sends IPIs to all CPUs in the mm_cpumask and they switch away from this mm to init_mm if it was being used as the lazy tlb mm. Enabling the shoot lazies option therefore requires that the arch ensures that mm_cpumask contains all CPUs that could possibly be using mm. A DEBUG_VM option IPIs every CPU in the system after this to ensure there are no references remaining before the mm is freed. Shootdown IPIs cost could be an issue, but they have not been observed to be a serious problem with this scheme, because short-lived processes tend not to migrate CPUs much, therefore they don't get much chance to leave lazy tlb mm references on remote CPUs. There are a lot of options to reduce them if necessary, described in comments. The near-worst-case can be benchmarked with will-it-scale: context_switch1_threads -t $(($(nproc) / 2)) This will create nproc threads (nproc / 2 switching pairs) all sharing the same mm that spread over all CPUs so each CPU does thread->idle->thread switching. [ Rik came up with basically the same idea a few years ago, so credit to him for that. ] Link: https://lore.kernel.org/linux-mm/20230118080011.2258375-1-npiggin@gmail.com/ Link: https://lore.kernel.org/all/20180728215357.3249-11-riel@surriel.com/ Link: https://lkml.kernel.org/r/20230203071837.1136453-5-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/Kconfig | 15 +++++++++++ kernel/fork.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 10 ++++++++ 3 files changed, 90 insertions(+) diff --git a/arch/Kconfig b/arch/Kconfig index 643f8a04141e..205fd23e0cad 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -481,6 +481,21 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM # converted already). config MMU_LAZY_TLB_REFCOUNT def_bool y + depends on !MMU_LAZY_TLB_SHOOTDOWN + +# This option allows MMU_LAZY_TLB_REFCOUNT=n. It ensures no CPUs are using an +# mm as a lazy tlb beyond its last reference count, by shooting down these +# users before the mm is deallocated. __mmdrop() first IPIs all CPUs that may +# be using the mm as a lazy tlb, so that they may switch themselves to using +# init_mm for their active mm. mm_cpumask(mm) is used to determine which CPUs +# may be using mm as a lazy tlb mm. +# +# To implement this, an arch *must*: +# - At the time of the final mmdrop of the mm, ensure mm_cpumask(mm) contains +# at least all possible CPUs in which the mm is lazy. +# - It must meet the requirements for MMU_LAZY_TLB_REFCOUNT=n (see above). +config MMU_LAZY_TLB_SHOOTDOWN + bool config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..cea99f003f24 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -772,6 +772,67 @@ static void check_mm(struct mm_struct *mm) #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) +static void do_check_lazy_tlb(void *arg) +{ + struct mm_struct *mm = arg; + + WARN_ON_ONCE(current->active_mm == mm); +} + +static void do_shoot_lazy_tlb(void *arg) +{ + struct mm_struct *mm = arg; + + if (current->active_mm == mm) { + WARN_ON_ONCE(current->mm); + current->active_mm = &init_mm; + switch_mm(mm, &init_mm, current); + } +} + +static void cleanup_lazy_tlbs(struct mm_struct *mm) +{ + if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { + /* + * In this case, lazy tlb mms are refounted and would not reach + * __mmdrop until all CPUs have switched away and mmdrop()ed. + */ + return; + } + + /* + * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it + * requires lazy mm users to switch to another mm when the refcount + * drops to zero, before the mm is freed. This requires IPIs here to + * switch kernel threads to init_mm. + * + * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm + * switch with the final userspace teardown TLB flush which leaves the + * mm lazy on this CPU but no others, reducing the need for additional + * IPIs here. There are cases where a final IPI is still required here, + * such as the final mmdrop being performed on a different CPU than the + * one exiting, or kernel threads using the mm when userspace exits. + * + * IPI overheads have not found to be expensive, but they could be + * reduced in a number of possible ways, for example (roughly + * increasing order of complexity): + * - The last lazy reference created by exit_mm() could instead switch + * to init_mm, however it's probable this will run on the same CPU + * immediately afterwards, so this may not reduce IPIs much. + * - A batch of mms requiring IPIs could be gathered and freed at once. + * - CPUs store active_mm where it can be remotely checked without a + * lock, to filter out false-positives in the cpumask. + * - After mm_users or mm_count reaches zero, switching away from the + * mm could clear mm_cpumask to reduce some IPIs, perhaps together + * with some batching or delaying of the final IPIs. + * - A delayed freeing and RCU-like quiescing sequence based on mm + * switching to avoid IPIs completely. + */ + on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); + if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) + on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); +} + /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by @@ -783,6 +844,10 @@ void __mmdrop(struct mm_struct *mm) BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); + + /* Ensure no CPUs are using this as their lazy tlb mm */ + cleanup_lazy_tlbs(mm); + WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 39d1d93164bd..5cd8183bb4c1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -791,6 +791,16 @@ config DEBUG_VM If unsure, say N. +config DEBUG_VM_SHOOT_LAZIES + bool "Debug MMU_LAZY_TLB_SHOOTDOWN implementation" + depends on DEBUG_VM + depends on MMU_LAZY_TLB_SHOOTDOWN + help + Enable additional IPIs that ensure lazy tlb mm references are removed + before the mm is freed. + + If unsure, say N. + config DEBUG_VM_MAPLE_TREE bool "Debug VM maple trees" depends on DEBUG_VM -- GitLab From 77f68ebeee201e8960944863c03bd7ac613ca7ed Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 3 Feb 2023 17:18:37 +1000 Subject: [PATCH 1455/5631] powerpc/64s: enable MMU_LAZY_TLB_SHOOTDOWN On a 16-socket 192-core POWER8 system, the context_switch1_threads benchmark from will-it-scale (see earlier changelog), upstream can achieve a rate of about 1 million context switches per second, due to contention on the mm refcount. 64s meets the prerequisites for CONFIG_MMU_LAZY_TLB_SHOOTDOWN, so enable the option. This increases the above benchmark to 118 million context switches per second. This generates 314 additional IPI interrupts on a 144 CPU system doing a kernel compile, which is in the noise in terms of kernel cycles. Link: https://lkml.kernel.org/r/20230203071837.1136453-6-npiggin@gmail.com Signed-off-by: Nicholas Piggin Acked-by: Linus Torvalds Cc: Andy Lutomirski Cc: Catalin Marinas Cc: Christophe Leroy Cc: Dave Hansen Cc: Michael Ellerman Cc: Nadav Amit Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/powerpc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a6c4407d3ec8..49c6d36b2b3e 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -266,6 +266,7 @@ config PPC select MMU_GATHER_PAGE_SIZE select MMU_GATHER_RCU_TABLE_FREE select MMU_GATHER_MERGE_VMAS + select MMU_LAZY_TLB_SHOOTDOWN if PPC_BOOK3S_64 select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64 -- GitLab From 739100c88f49a67c6487bb2d826b0b5a2ddc80e2 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Fri, 10 Feb 2023 13:46:45 -0800 Subject: [PATCH 1456/5631] mm: add tracepoints to ksm This adds the following tracepoints to ksm: - start / stop scan - ksm enter / exit - merge a page - merge a page with ksm - remove a page - remove a rmap item This patch has been split off from the RFC patch series "mm: process/cgroup ksm support". Link: https://lkml.kernel.org/r/20230210214645.2720847-1-shr@devkernel.io Signed-off-by: Stefan Roesch Reviewed-by: Steven Rostedt (Google) Signed-off-by: Andrew Morton --- MAINTAINERS | 1 + include/trace/events/ksm.h | 251 +++++++++++++++++++++++++++++++++++++ mm/ksm.c | 21 +++- 3 files changed, 271 insertions(+), 2 deletions(-) create mode 100644 include/trace/events/ksm.h diff --git a/MAINTAINERS b/MAINTAINERS index 1dc8bd26b6cf..a62ffb710b47 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13409,6 +13409,7 @@ F: include/linux/memory_hotplug.h F: include/linux/mm.h F: include/linux/mmzone.h F: include/linux/pagewalk.h +F: include/trace/events/ksm.h F: mm/ F: tools/mm/ F: tools/testing/selftests/mm/ diff --git a/include/trace/events/ksm.h b/include/trace/events/ksm.h new file mode 100644 index 000000000000..b5ac35c1d0e8 --- /dev/null +++ b/include/trace/events/ksm.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ksm + +#if !defined(_TRACE_KSM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KSM_H + +#include + +/** + * ksm_scan_template - called for start / stop scan + * + * @seq: sequence number of scan + * @rmap_entries: actual number of rmap entries + * + * Allows to trace the start / stop of a ksm scan. + */ +DECLARE_EVENT_CLASS(ksm_scan_template, + + TP_PROTO(int seq, u32 rmap_entries), + + TP_ARGS(seq, rmap_entries), + + TP_STRUCT__entry( + __field(int, seq) + __field(u32, rmap_entries) + ), + + TP_fast_assign( + __entry->seq = seq; + __entry->rmap_entries = rmap_entries; + ), + + TP_printk("seq %d rmap size %d", + __entry->seq, __entry->rmap_entries) +); + +/** + * ksm_start_scan - called after a new ksm scan is started + * + * @seq: sequence number of scan + * @rmap_entries: actual number of rmap entries + * + * Allows to trace the start of a ksm scan. + */ +DEFINE_EVENT(ksm_scan_template, ksm_start_scan, + + TP_PROTO(int seq, u32 rmap_entries), + + TP_ARGS(seq, rmap_entries) +); + +/** + * ksm_stop_scan - called after a new ksm scan has completed + * + * @seq: sequence number of scan + * @rmap_entries: actual number of rmap entries + * + * Allows to trace the completion of a ksm scan. + */ +DEFINE_EVENT(ksm_scan_template, ksm_stop_scan, + + TP_PROTO(int seq, u32 rmap_entries), + + TP_ARGS(seq, rmap_entries) +); + +/** + * ksm_enter - called after a new process has been added / removed from ksm + * + * @mm: address of the mm object of the process + * + * Allows to trace the when a process has been added or removed from ksm. + */ +DECLARE_EVENT_CLASS(ksm_enter_exit_template, + + TP_PROTO(void *mm), + + TP_ARGS(mm), + + TP_STRUCT__entry( + __field(void *, mm) + ), + + TP_fast_assign( + __entry->mm = mm; + ), + + TP_printk("mm %p", __entry->mm) +); + +/** + * ksm_enter - called after a new process has been added to ksm + * + * @mm: address of the mm object of the process + * + * Allows to trace the when a process has been added to ksm. + */ +DEFINE_EVENT(ksm_enter_exit_template, ksm_enter, + + TP_PROTO(void *mm), + + TP_ARGS(mm) +); + +/** + * ksm_exit - called after a new process has been removed from ksm + * + * @mm: address of the mm object of the process + * + * Allows to trace the when a process has been removed from ksm. + */ +DEFINE_EVENT(ksm_enter_exit_template, ksm_exit, + + TP_PROTO(void *mm), + + TP_ARGS(mm) +); + +/** + * ksm_merge_one_page - called after a page has been merged + * + * @pfn: page frame number of ksm page + * @rmap_item: address of rmap_item object + * @mm: address of the process mm struct + * @err: success + * + * Allows to trace the ksm merging of individual pages. + */ +TRACE_EVENT(ksm_merge_one_page, + + TP_PROTO(unsigned long pfn, void *rmap_item, void *mm, int err), + + TP_ARGS(pfn, rmap_item, mm, err), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + __field(void *, rmap_item) + __field(void *, mm) + __field(int, err) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->rmap_item = rmap_item; + __entry->mm = mm; + __entry->err = err; + ), + + TP_printk("ksm pfn %lu rmap_item %p mm %p error %d", + __entry->pfn, __entry->rmap_item, __entry->mm, __entry->err) +); + +/** + * ksm_merge_with_ksm_page - called after a page has been merged with a ksm page + * + * @ksm_page: address ksm page + * @pfn: page frame number of ksm page + * @rmap_item: address of rmap_item object + * @mm: address of the mm object of the process + * @err: success + * + * Allows to trace the merging of a page with a ksm page. + */ +TRACE_EVENT(ksm_merge_with_ksm_page, + + TP_PROTO(void *ksm_page, unsigned long pfn, void *rmap_item, void *mm, int err), + + TP_ARGS(ksm_page, pfn, rmap_item, mm, err), + + TP_STRUCT__entry( + __field(void *, ksm_page) + __field(unsigned long, pfn) + __field(void *, rmap_item) + __field(void *, mm) + __field(int, err) + ), + + TP_fast_assign( + __entry->ksm_page = ksm_page; + __entry->pfn = pfn; + __entry->rmap_item = rmap_item; + __entry->mm = mm; + __entry->err = err; + ), + + TP_printk("%spfn %lu rmap_item %p mm %p error %d", + (__entry->ksm_page ? "ksm " : ""), + __entry->pfn, __entry->rmap_item, __entry->mm, __entry->err) +); + +/** + * ksm_remove_ksm_page - called after a ksm page has been removed + * + * @pfn: page frame number of ksm page + * + * Allows to trace the removing of stable ksm pages. + */ +TRACE_EVENT(ksm_remove_ksm_page, + + TP_PROTO(unsigned long pfn), + + TP_ARGS(pfn), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + ), + + TP_fast_assign( + __entry->pfn = pfn; + ), + + TP_printk("pfn %lu", __entry->pfn) +); + +/** + * ksm_remove_rmap_item - called after a rmap_item has been removed from the + * stable tree + * + * @pfn: page frame number of ksm page + * @rmap_item: address of rmap_item object + * @mm: address of the process mm struct + * + * Allows to trace the removal of pages from the stable tree list. + */ +TRACE_EVENT(ksm_remove_rmap_item, + + TP_PROTO(unsigned long pfn, void *rmap_item, void *mm), + + TP_ARGS(pfn, rmap_item, mm), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + __field(void *, rmap_item) + __field(void *, mm) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->rmap_item = rmap_item; + __entry->mm = mm; + ), + + TP_printk("pfn %lu rmap_item %p mm %p", + __entry->pfn, __entry->rmap_item, __entry->mm) +); + +#endif /* _TRACE_KSM_H */ + +/* This part must be outside protection */ +#include diff --git a/mm/ksm.c b/mm/ksm.c index 2b8d30068cbb..290a3eb6d8de 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -45,6 +45,9 @@ #include "internal.h" #include "mm_slot.h" +#define CREATE_TRACE_POINTS +#include + #ifdef CONFIG_NUMA #define NUMA(x) (x) #define DO_NUMA(x) do { (x); } while (0) @@ -633,10 +636,12 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) BUG_ON(stable_node->rmap_hlist_len < 0); hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { - if (rmap_item->hlist.next) + if (rmap_item->hlist.next) { ksm_pages_sharing--; - else + trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm); + } else { ksm_pages_shared--; + } rmap_item->mm->ksm_merging_pages--; @@ -657,6 +662,7 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node) BUILD_BUG_ON(STABLE_NODE_DUP_HEAD <= &migrate_nodes); BUILD_BUG_ON(STABLE_NODE_DUP_HEAD >= &migrate_nodes + 1); + trace_ksm_remove_ksm_page(stable_node->kpfn); if (stable_node->head == &migrate_nodes) list_del(&stable_node->list); else @@ -1324,6 +1330,8 @@ static int try_to_merge_with_ksm_page(struct ksm_rmap_item *rmap_item, get_anon_vma(vma->anon_vma); out: mmap_read_unlock(mm); + trace_ksm_merge_with_ksm_page(kpage, page_to_pfn(kpage ? kpage : page), + rmap_item, mm, err); return err; } @@ -2142,6 +2150,9 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite if (vma) { err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); + trace_ksm_merge_one_page( + page_to_pfn(ZERO_PAGE(rmap_item->address)), + rmap_item, mm, err); } else { /* * If the vma is out of date, we do not need to @@ -2264,6 +2275,8 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) mm_slot = ksm_scan.mm_slot; if (mm_slot == &ksm_mm_head) { + trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); + /* * A number of pages can hang around indefinitely on per-cpu * pagevecs, raised page count preventing write_protect_page @@ -2414,6 +2427,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) if (mm_slot != &ksm_mm_head) goto next_mm; + trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; } @@ -2565,6 +2579,7 @@ int __ksm_enter(struct mm_struct *mm) if (needs_wakeup) wake_up_interruptible(&ksm_thread_wait); + trace_ksm_enter(mm); return 0; } @@ -2606,6 +2621,8 @@ void __ksm_exit(struct mm_struct *mm) mmap_write_lock(mm); mmap_write_unlock(mm); } + + trace_ksm_exit(mm); } struct page *ksm_might_need_to_copy(struct page *page, -- GitLab From e26fcc02c7f6c76cba42d043756e35a78ce9ac11 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Mon, 30 Jan 2023 13:25:12 +0900 Subject: [PATCH 1457/5631] mmflags.h: use less error prone method to define pageflag_names Patch series "mm, printk: introduce new format for page_type", v4. This series moves PG_slab page flag to page_type, freeing one bit in page->flags and introduces %pGt format that prints human-readable page_type like %pGp for printing page flags. See changelog of patch 2 for more implementation details. Thanks everyone that gave valuable comments. This patch (of 3): Use helper macro to decrease chances of typo when defining pageflag_names. Link: https://lkml.kernel.org/r/20230130042514.2418-1-42.hyeyoo@gmail.com Link: https://lore.kernel.org/lkml/Y6AycLbpjVzXM5I9@smile.fi.intel.com Link: https://lkml.kernel.org/r/20230130042514.2418-2-42.hyeyoo@gmail.com Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Cc: David Hildenbrand Cc: Joe Perches Cc: Matthew Wilcox Cc: Petr Mladek Cc: Steven Rostedt (Google) Cc: Vlastimil Babka Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: John Ogness Signed-off-by: Andrew Morton --- include/trace/events/mmflags.h | 85 ++++++++++++++++++---------------- 1 file changed, 44 insertions(+), 41 deletions(-) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 9db52bc4ce19..f453babe29b3 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -67,71 +67,74 @@ ) : "none" #ifdef CONFIG_MMU -#define IF_HAVE_PG_MLOCK(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_MLOCK(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_MLOCK(flag,string) +#define IF_HAVE_PG_MLOCK(_name) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED -#define IF_HAVE_PG_UNCACHED(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_UNCACHED(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_UNCACHED(flag,string) +#define IF_HAVE_PG_UNCACHED(_name) #endif #ifdef CONFIG_MEMORY_FAILURE -#define IF_HAVE_PG_HWPOISON(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_HWPOISON(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_HWPOISON(flag,string) +#define IF_HAVE_PG_HWPOISON(_name) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) -#define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_IDLE(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_IDLE(flag,string) +#define IF_HAVE_PG_IDLE(_name) #endif #ifdef CONFIG_ARCH_USES_PG_ARCH_X -#define IF_HAVE_PG_ARCH_X(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_ARCH_X(_name) ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_ARCH_X(flag,string) +#define IF_HAVE_PG_ARCH_X(_name) #endif #ifdef CONFIG_KASAN_HW_TAGS -#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) ,{1UL << flag, string} +#define IF_HAVE_PG_SKIP_KASAN_POISON(_name) \ + ,{1UL << PG_##_name, __stringify(_name)} #else -#define IF_HAVE_PG_SKIP_KASAN_POISON(flag,string) +#define IF_HAVE_PG_SKIP_KASAN_POISON(_name) #endif +#define DEF_PAGEFLAG_NAME(_name) { 1UL << PG_##_name, __stringify(_name) } + #define __def_pageflag_names \ - {1UL << PG_locked, "locked" }, \ - {1UL << PG_waiters, "waiters" }, \ - {1UL << PG_error, "error" }, \ - {1UL << PG_referenced, "referenced" }, \ - {1UL << PG_uptodate, "uptodate" }, \ - {1UL << PG_dirty, "dirty" }, \ - {1UL << PG_lru, "lru" }, \ - {1UL << PG_active, "active" }, \ - {1UL << PG_workingset, "workingset" }, \ - {1UL << PG_slab, "slab" }, \ - {1UL << PG_owner_priv_1, "owner_priv_1" }, \ - {1UL << PG_arch_1, "arch_1" }, \ - {1UL << PG_reserved, "reserved" }, \ - {1UL << PG_private, "private" }, \ - {1UL << PG_private_2, "private_2" }, \ - {1UL << PG_writeback, "writeback" }, \ - {1UL << PG_head, "head" }, \ - {1UL << PG_mappedtodisk, "mappedtodisk" }, \ - {1UL << PG_reclaim, "reclaim" }, \ - {1UL << PG_swapbacked, "swapbacked" }, \ - {1UL << PG_unevictable, "unevictable" } \ -IF_HAVE_PG_MLOCK(PG_mlocked, "mlocked" ) \ -IF_HAVE_PG_UNCACHED(PG_uncached, "uncached" ) \ -IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ -IF_HAVE_PG_IDLE(PG_young, "young" ) \ -IF_HAVE_PG_IDLE(PG_idle, "idle" ) \ -IF_HAVE_PG_ARCH_X(PG_arch_2, "arch_2" ) \ -IF_HAVE_PG_ARCH_X(PG_arch_3, "arch_3" ) \ -IF_HAVE_PG_SKIP_KASAN_POISON(PG_skip_kasan_poison, "skip_kasan_poison") + DEF_PAGEFLAG_NAME(locked), \ + DEF_PAGEFLAG_NAME(waiters), \ + DEF_PAGEFLAG_NAME(error), \ + DEF_PAGEFLAG_NAME(referenced), \ + DEF_PAGEFLAG_NAME(uptodate), \ + DEF_PAGEFLAG_NAME(dirty), \ + DEF_PAGEFLAG_NAME(lru), \ + DEF_PAGEFLAG_NAME(active), \ + DEF_PAGEFLAG_NAME(workingset), \ + DEF_PAGEFLAG_NAME(slab), \ + DEF_PAGEFLAG_NAME(owner_priv_1), \ + DEF_PAGEFLAG_NAME(arch_1), \ + DEF_PAGEFLAG_NAME(reserved), \ + DEF_PAGEFLAG_NAME(private), \ + DEF_PAGEFLAG_NAME(private_2), \ + DEF_PAGEFLAG_NAME(writeback), \ + DEF_PAGEFLAG_NAME(head), \ + DEF_PAGEFLAG_NAME(mappedtodisk), \ + DEF_PAGEFLAG_NAME(reclaim), \ + DEF_PAGEFLAG_NAME(swapbacked), \ + DEF_PAGEFLAG_NAME(unevictable) \ +IF_HAVE_PG_MLOCK(mlocked) \ +IF_HAVE_PG_UNCACHED(uncached) \ +IF_HAVE_PG_HWPOISON(hwpoison) \ +IF_HAVE_PG_IDLE(idle) \ +IF_HAVE_PG_IDLE(young) \ +IF_HAVE_PG_ARCH_X(arch_2) \ +IF_HAVE_PG_ARCH_X(arch_3) \ +IF_HAVE_PG_SKIP_KASAN_POISON(skip_kasan_poison) #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ -- GitLab From 4c85c0be3d7a9a7ffe48bfe0954eacc0ba9d3c75 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Mon, 30 Jan 2023 13:25:13 +0900 Subject: [PATCH 1458/5631] mm, printk: introduce new format %pGt for page_type %pGp format is used to display 'flags' field of a struct page. However, some page flags (i.e. PG_buddy, see page-flags.h for more details) are stored in page_type field. To display human-readable output of page_type, introduce %pGt format. It is important to note the meaning of bits are different in page_type. if page_type is 0xffffffff, no flags are set. Setting PG_buddy (0x00000080) flag results in a page_type of 0xffffff7f. Clearing a bit actually means setting a flag. Bits in page_type are inverted when displaying type names. Only values for which page_type_has_type() returns true are considered as page_type, to avoid confusion with mapcount values. if it returns false, only raw values are displayed and not page type names. Link: https://lkml.kernel.org/r/20230130042514.2418-3-42.hyeyoo@gmail.com Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reviewed-by: Petr Mladek [vsprintf part] Cc: Andy Shevchenko Cc: David Hildenbrand Cc: Joe Perches Cc: John Ogness Cc: Matthew Wilcox Cc: Sergey Senozhatsky Cc: Steven Rostedt (Google) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- Documentation/core-api/printk-formats.rst | 16 +++++++++----- include/linux/page-flags.h | 7 +++++- include/trace/events/mmflags.h | 8 +++++++ lib/test_printf.c | 26 +++++++++++++++++++++++ lib/vsprintf.c | 21 ++++++++++++++++++ mm/debug.c | 5 +++++ mm/internal.h | 1 + 7 files changed, 78 insertions(+), 6 deletions(-) diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index dbe1aacc79d0..dfe7e75a71de 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -575,20 +575,26 @@ The field width is passed by value, the bitmap is passed by reference. Helper macros cpumask_pr_args() and nodemask_pr_args() are available to ease printing cpumask and nodemask. -Flags bitfields such as page flags, gfp_flags ---------------------------------------------- +Flags bitfields such as page flags, page_type, gfp_flags +-------------------------------------------------------- :: %pGp 0x17ffffc0002036(referenced|uptodate|lru|active|private|node=0|zone=2|lastcpupid=0x1fffff) + %pGt 0xffffff7f(buddy) %pGg GFP_USER|GFP_DMA32|GFP_NOWARN %pGv read|exec|mayread|maywrite|mayexec|denywrite For printing flags bitfields as a collection of symbolic constants that would construct the value. The type of flags is given by the third -character. Currently supported are [p]age flags, [v]ma_flags (both -expect ``unsigned long *``) and [g]fp_flags (expects ``gfp_t *``). The flag -names and print order depends on the particular type. +character. Currently supported are: + + - p - [p]age flags, expects value of type (``unsigned long *``) + - t - page [t]ype, expects value of type (``unsigned int *``) + - v - [v]ma_flags, expects value of type (``unsigned long *``) + - g - [g]fp_flags, expects value of type (``gfp_t *``) + +The flag names and print order depends on the particular type. Note that this format should not be used directly in the :c:func:`TP_printk()` part of a tracepoint. Instead, use the show_*_flags() diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a7e3a3405520..57287102c5bd 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -926,9 +926,14 @@ static inline bool is_page_hwpoison(struct page *page) #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +static inline int page_type_has_type(unsigned int page_type) +{ + return (int)page_type < PAGE_MAPCOUNT_RESERVE; +} + static inline int page_has_type(struct page *page) { - return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; + return page_type_has_type(page->page_type); } #define PAGE_TYPE_OPS(uname, lname) \ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index f453babe29b3..b28218b7998e 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -141,6 +141,14 @@ IF_HAVE_PG_SKIP_KASAN_POISON(skip_kasan_poison) __def_pageflag_names \ ) : "none" +#define DEF_PAGETYPE_NAME(_name) { PG_##_name, __stringify(_name) } + +#define __def_pagetype_names \ + DEF_PAGETYPE_NAME(offline), \ + DEF_PAGETYPE_NAME(guard), \ + DEF_PAGETYPE_NAME(table), \ + DEF_PAGETYPE_NAME(buddy) + #if defined(CONFIG_X86) #define __VM_ARCH_SPECIFIC_1 {VM_PAT, "pat" } #elif defined(CONFIG_PPC) diff --git a/lib/test_printf.c b/lib/test_printf.c index 46b4e6c414a3..7677ebccf3c3 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -642,12 +642,26 @@ page_flags_test(int section, int node, int zone, int last_cpupid, test(cmp_buf, "%pGp", &flags); } +static void __init page_type_test(unsigned int page_type, const char *name, + char *cmp_buf) +{ + unsigned long size; + + size = scnprintf(cmp_buf, BUF_SIZE, "%#x(", page_type); + if (page_type_has_type(page_type)) + size += scnprintf(cmp_buf + size, BUF_SIZE - size, "%s", name); + + snprintf(cmp_buf + size, BUF_SIZE - size, ")"); + test(cmp_buf, "%pGt", &page_type); +} + static void __init flags(void) { unsigned long flags; char *cmp_buffer; gfp_t gfp; + unsigned int page_type; cmp_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); if (!cmp_buffer) @@ -687,6 +701,18 @@ flags(void) gfp |= __GFP_HIGH; test(cmp_buffer, "%pGg", &gfp); + page_type = ~0; + page_type_test(page_type, "", cmp_buffer); + + page_type = 10; + page_type_test(page_type, "", cmp_buffer); + + page_type = ~PG_buddy; + page_type_test(page_type, "buddy", cmp_buffer); + + page_type = ~(PG_table | PG_buddy); + page_type_test(page_type, "table|buddy", cmp_buffer); + kfree(cmp_buffer); } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index be71a03c936a..fbe320b5e89f 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2052,6 +2052,25 @@ char *format_page_flags(char *buf, char *end, unsigned long flags) return buf; } +static +char *format_page_type(char *buf, char *end, unsigned int page_type) +{ + buf = number(buf, end, page_type, default_flag_spec); + + if (buf < end) + *buf = '('; + buf++; + + if (page_type_has_type(page_type)) + buf = format_flags(buf, end, ~page_type, pagetype_names); + + if (buf < end) + *buf = ')'; + buf++; + + return buf; +} + static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) @@ -2065,6 +2084,8 @@ char *flags_string(char *buf, char *end, void *flags_ptr, switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); + case 't': + return format_page_type(buf, end, *(unsigned int *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; diff --git a/mm/debug.c b/mm/debug.c index 96d594e16292..01cf0435723b 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -36,6 +36,11 @@ const struct trace_print_flags pageflag_names[] = { {0, NULL} }; +const struct trace_print_flags pagetype_names[] = { + __def_pagetype_names, + {0, NULL} +}; + const struct trace_print_flags gfpflag_names[] = { __def_gfpflag_names, {0, NULL} diff --git a/mm/internal.h b/mm/internal.h index 7920a8b7982e..2a7ffd9962c4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -802,6 +802,7 @@ static inline void flush_tlb_batched_pending(struct mm_struct *mm) #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; +extern const struct trace_print_flags pagetype_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; -- GitLab From f2421a16f42a2f121c587c89b60cc8f3f2df36c2 Mon Sep 17 00:00:00 2001 From: Hyeonggon Yoo <42.hyeyoo@gmail.com> Date: Mon, 30 Jan 2023 13:25:14 +0900 Subject: [PATCH 1459/5631] mm/debug: use %pGt to display page_type in dump_page() Some page flags are stored in page_type rather than ->flags field. Use newly introduced page type %pGt in dump_page(). Below are some examples: page:00000000da7184dd refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x101cb3 flags: 0x2ffff0000000000(node=0|zone=2|lastcpupid=0xffff) page_type: 0xffffffff() raw: 02ffff0000000000 0000000000000000 dead000000000122 0000000000000000 raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 page dumped because: newly allocated page page:00000000da7184dd refcount:0 mapcount:-128 mapping:0000000000000000 index:0x0 pfn:0x101cb3 flags: 0x2ffff0000000000(node=0|zone=2|lastcpupid=0xffff) page_type: 0xffffff7f(buddy) raw: 02ffff0000000000 ffff88813fff8e80 ffff88813fff8e80 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffff7f 0000000000000000 page dumped because: freed page page:0000000042202316 refcount:3 mapcount:2 mapping:0000000000000000 index:0x7f634722a pfn:0x11994e memcg:ffff888100135000 anon flags: 0x2ffff0000080024(uptodate|active|swapbacked|node=0|zone=2|lastcpupid=0xffff) page_type: 0x1() raw: 02ffff0000080024 0000000000000000 dead000000000122 ffff8881193398f1 raw: 00000007f634722a 0000000000000000 0000000300000001 ffff888100135000 page dumped because: user-mapped page Link: https://lkml.kernel.org/r/20230130042514.2418-4-42.hyeyoo@gmail.com Signed-off-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Andy Shevchenko Cc: David Hildenbrand Cc: Joe Perches Cc: John Ogness Cc: Matthew Wilcox Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Steven Rostedt (Google) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/debug.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/debug.c b/mm/debug.c index 01cf0435723b..c7b228097bd9 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -120,6 +120,8 @@ static void __dump_page(struct page *page) pr_warn("%sflags: %pGp%s\n", type, &head->flags, page_cma ? " CMA" : ""); + pr_warn("page_type: %pGt\n", &head->page_type); + print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, sizeof(struct page), false); -- GitLab From bdeb91881088810ab1d8ae620862c3b4d78f4041 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Mon, 27 Feb 2023 22:42:28 +0100 Subject: [PATCH 1460/5631] mm/rmap: use atomic_try_cmpxchg in set_tlb_ubc_flush_pending Use atomic_try_cmpxchg instead of atomic_cmpxchg (*ptr, old, new) == old in set_tlb_ubc_flush_pending. 86 CMPXCHG instruction returns success in ZF flag, so this change saves a compare after cmpxchg (and related move instruction in front of cmpxchg). Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg fails. No functional change intended. Link: https://lkml.kernel.org/r/20230227214228.3533299-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Signed-off-by: Andrew Morton --- mm/rmap.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index 8632e02661ac..1ea2756b2797 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -644,7 +644,7 @@ void try_to_unmap_flush_dirty(void) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; - int batch, nbatch; + int batch; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; @@ -662,11 +662,8 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ - nbatch = atomic_cmpxchg(&mm->tlb_flush_batched, batch, 1); - if (nbatch != batch) { - batch = nbatch; + if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; - } } else { atomic_inc(&mm->tlb_flush_batched); } -- GitLab From af7df1c986adfe0684cb0b91114e0ac442b942e9 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Sun, 26 Feb 2023 16:16:33 +0300 Subject: [PATCH 1461/5631] selftests: cgroup: add 'malloc' failures checks in test_memcontrol There are several 'malloc' calls in test_memcontrol, which can be unsuccessful. This patch will add 'malloc' failures checking to give more details about test's fail reasons and avoid possible undefined behavior during the future null dereference (like the one in alloc_anon_50M_check_swap function). Link: https://lkml.kernel.org/r/20230226131634.34366-1-ivan.orlov0322@gmail.com Signed-off-by: Ivan Orlov Reviewed-by: Muchun Song Acked-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Shuah Khan Cc: Tejun Heo Cc: Zefan Li Signed-off-by: Andrew Morton --- tools/testing/selftests/cgroup/test_memcontrol.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index 1e616a8c6a9c..f4f7c0aef702 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -98,6 +98,11 @@ static int alloc_anon_50M_check(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -211,6 +216,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg) char *buf, *ptr; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; @@ -778,6 +788,11 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg) int ret = -1; buf = malloc(size); + if (buf == NULL) { + fprintf(stderr, "malloc() failed\n"); + return -1; + } + for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE) *ptr = 0; -- GitLab From 16d91faf09be148d9c1cf4999f4d15fb24a7cd72 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 16 Feb 2023 11:59:24 -0800 Subject: [PATCH 1462/5631] kasan: call clear_page with a match-all tag instead of changing page tag Instead of changing the page's tag solely in order to obtain a pointer with a match-all tag and then changing it back again, just convert the pointer that we get from kmap_atomic() into one with a match-all tag before passing it to clear_page(). On a certain microarchitecture, this has been observed to cause a measurable improvement in microbenchmark performance, presumably as a result of being able to avoid the atomic operations on the page tag. Link: https://lkml.kernel.org/r/20230216195924.3287772-1-pcc@google.com Signed-off-by: Peter Collingbourne Link: https://linux-review.googlesource.com/id/I0249822cc29097ca7a04ad48e8eb14871f80e711 Reviewed-by: Andrey Konovalov Reviewed-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Evgenii Stepanov Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/highmem.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8fc10089e19e..9c7cdaa3de8c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -243,12 +243,10 @@ static inline void clear_highpage(struct page *page) static inline void clear_highpage_kasan_tagged(struct page *page) { - u8 tag; + void *kaddr = kmap_local_page(page); - tag = page_kasan_tag(page); - page_kasan_tag_reset(page); - clear_highpage(page); - page_kasan_tag_set(page, tag); + clear_page(kasan_reset_tag(kaddr)); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE -- GitLab From cfe3236d32d07bf261760472fee5d7029eb02779 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:29 +0800 Subject: [PATCH 1463/5631] mm: huge_memory: convert __do_huge_pmd_anonymous_page() to use a folio Patch series "mm: remove cgroup_throttle_swaprate() completely", v2. Convert all the caller functions of cgroup_throttle_swaprate() to use folios, and use folio_throttle_swaprate(), which allows us to remove cgroup_throttle_swaprate() completely. This patch (of 7): Convert from page to folio within __do_huge_pmd_anonymous_page(), as we need the precise page which is to be stored at this PTE in the folio, the function still keep a page as the parameter. Link: https://lkml.kernel.org/r/20230302115835.105364-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20230302115835.105364-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/huge_memory.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 032fb0ef9cd1..0c1df321ad64 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -656,19 +656,20 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, gfp_t gfp) { struct vm_area_struct *vma = vmf->vma; + struct folio *folio = page_folio(page); pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret = 0; - VM_BUG_ON_PAGE(!PageCompound(page), page); + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { - put_page(page); + if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { + folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } - cgroup_throttle_swaprate(page, gfp); + folio_throttle_swaprate(folio, gfp); pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { @@ -678,11 +679,11 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, clear_huge_page(page, vmf->address, HPAGE_PMD_NR); /* - * The memory barrier inside __SetPageUptodate makes sure that + * The memory barrier inside __folio_mark_uptodate makes sure that * clear_huge_page writes become visible before the set_pmd_at() * write. */ - __SetPageUptodate(page); + __folio_mark_uptodate(folio); vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { @@ -697,7 +698,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); - put_page(page); + folio_put(folio); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); @@ -706,8 +707,8 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr); - lru_cache_add_inactive_or_unevictable(page, vma); + folio_add_new_anon_rmap(folio, vma, haddr); + folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); @@ -724,7 +725,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, release: if (pgtable) pte_free(vma->vm_mm, pgtable); - put_page(page); + folio_put(folio); return ret; } -- GitLab From 4231f8425833b144f165f01f33887b67f494acf0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:30 +0800 Subject: [PATCH 1464/5631] mm: memory: use folio_throttle_swaprate() in do_swap_page() Directly use folio_throttle_swaprate() instead of cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index bfa3100ec5a3..fe15cf7c86ae 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3839,7 +3839,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) lru_add_drain(); } - cgroup_throttle_swaprate(page, GFP_KERNEL); + folio_throttle_swaprate(folio, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. -- GitLab From e601ded4247f959702adb5170ca8abac17a0313f Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:31 +0800 Subject: [PATCH 1465/5631] mm: memory: use folio_throttle_swaprate() in page_copy_prealloc() Directly use folio_throttle_swaprate() instead of cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index fe15cf7c86ae..1789c16aae73 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -970,7 +970,7 @@ static inline struct folio *page_copy_prealloc(struct mm_struct *src_mm, folio_put(new_folio); return NULL; } - cgroup_throttle_swaprate(&new_folio->page, GFP_KERNEL); + folio_throttle_swaprate(new_folio, GFP_KERNEL); return new_folio; } -- GitLab From 4d4f75bf3293f35ae1eb1ecf8b70bffdde58ffbe Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:32 +0800 Subject: [PATCH 1466/5631] mm: memory: use folio_throttle_swaprate() in wp_page_copy() Directly use folio_throttle_swaprate() instead of cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 1789c16aae73..5c2465287e6a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3092,7 +3092,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) if (mem_cgroup_charge(new_folio, mm, GFP_KERNEL)) goto oom_free_new; - cgroup_throttle_swaprate(&new_folio->page, GFP_KERNEL); + folio_throttle_swaprate(new_folio, GFP_KERNEL); __folio_mark_uptodate(new_folio); -- GitLab From e2bf3e2caa62f72d6a67048df440d83a12ae1a2a Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:33 +0800 Subject: [PATCH 1467/5631] mm: memory: use folio_throttle_swaprate() in do_anonymous_page() Directly use folio_throttle_swaprate() instead of cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-6-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index 5c2465287e6a..b6474883a6be 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4056,7 +4056,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; - cgroup_throttle_swaprate(&folio->page, GFP_KERNEL); + folio_throttle_swaprate(folio, GFP_KERNEL); /* * The memory barrier inside __folio_mark_uptodate makes sure that -- GitLab From 68fa572b503ce8bfd0d0c2e5bb185134086d7d7d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:34 +0800 Subject: [PATCH 1468/5631] mm: memory: use folio_throttle_swaprate() in do_cow_fault() Directly use folio_throttle_swaprate() instead of cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-7-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory.c b/mm/memory.c index b6474883a6be..fdc903825981 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4518,7 +4518,7 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) put_page(vmf->cow_page); return VM_FAULT_OOM; } - cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); + folio_throttle_swaprate(page_folio(vmf->cow_page), GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) -- GitLab From 3e4fb13ac34bad94cf390415b1e6bc3ca9520d65 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 2 Mar 2023 19:58:35 +0800 Subject: [PATCH 1469/5631] mm: swap: remove unneeded cgroup_throttle_swaprate() All the callers of cgroup_throttle_swaprate() are converted to folio_throttle_swaprate(), so make __cgroup_throttle_swaprate() to take a folio, and rename it to __folio_throttle_swaprate(), also rename gfp_mask to gfp and drop redundant extern keyword. finally, drop unused cgroup_throttle_swaprate(). Link: https://lkml.kernel.org/r/20230302115835.105364-8-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/swap.h | 12 ++++-------- mm/swapfile.c | 6 +++--- 2 files changed, 7 insertions(+), 11 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 209a425739a9..d5d0b54e90e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -641,22 +641,18 @@ extern atomic_t zswap_stored_pages; #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; - __cgroup_throttle_swaprate(page, gfp_mask); + __folio_throttle_swaprate(folio, gfp); } #else -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) -{ -} -#endif static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { - cgroup_throttle_swaprate(&folio->page, gfp); } +#endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); diff --git a/mm/swapfile.c b/mm/swapfile.c index 62ba2bf577d7..c1b97436f811 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3635,12 +3635,12 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; - int nid = page_to_nid(page); + int nid = folio_nid(folio); - if (!(gfp_mask & __GFP_IO)) + if (!(gfp & __GFP_IO)) return; if (!blk_cgroup_congested()) -- GitLab From 1da28f1b5ab1dd15919e75bb9a47e17912fd756c Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 2 Mar 2023 08:23:49 +0530 Subject: [PATCH 1470/5631] mm/migrate: drop pte_mkhuge() in remove_migration_pte() Since the following commit, arch_make_huge_pte() should be used directly in generic memory subsystem as a platform provided page table helper, instead of pte_mkhuge(). This just drops pte_mkhuge() from remove_migration_pte(), which has now become redundant. 'commit 16785bd77431 ("mm: merge pte_mkhuge() call into arch_make_huge_pte()")' Link: https://lkml.kernel.org/r/20230302025349.358341-1-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reported-by: Christophe Leroy Link: https://lore.kernel.org/all/1ea45095-0926-a56a-a273-816709e9075e@csgroup.eu/ Reviewed-by: David Hildenbrand Cc: Mike Kravetz Signed-off-by: Andrew Morton --- mm/migrate.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index db3f154446af..afe21c48dc6e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -249,7 +249,6 @@ static bool remove_migration_pte(struct folio *folio, if (folio_test_hugetlb(folio)) { unsigned int shift = huge_page_shift(hstate_vma(vma)); - pte = pte_mkhuge(pte); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (folio_test_anon(folio)) hugepage_add_anon_rmap(new, vma, pvmw.address, -- GitLab From 9dabf6e1374519f89d9fc326a129b5cc35088479 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 2 Mar 2023 17:18:45 +0530 Subject: [PATCH 1471/5631] mm/debug_vm_pgtable: replace pte_mkhuge() with arch_make_huge_pte() Since the following commit arch_make_huge_pte() should be used directly in generic memory subsystem as a platform provided page table helper, instead of pte_mkhuge(). Change hugetlb_basic_tests() to call arch_make_huge_pte() directly, and update its relevant documentation entry as required. 'commit 16785bd77431 ("mm: merge pte_mkhuge() call into arch_make_huge_pte()")' Link: https://lkml.kernel.org/r/20230302114845.421674-1-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reported-by: Christophe Leroy Link: https://lore.kernel.org/all/1ea45095-0926-a56a-a273-816709e9075e@csgroup.eu/ Cc: Jonathan Corbet Cc: David Hildenbrand Cc: Mike Kravetz Cc: Mike Rapoport Signed-off-by: Andrew Morton --- Documentation/mm/arch_pgtable_helpers.rst | 2 +- mm/debug_vm_pgtable.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst index 30d9a09f01f4..af3891f895b0 100644 --- a/Documentation/mm/arch_pgtable_helpers.rst +++ b/Documentation/mm/arch_pgtable_helpers.rst @@ -214,7 +214,7 @@ HugeTLB Page Table Helpers +---------------------------+--------------------------------------------------+ | pte_huge | Tests a HugeTLB | +---------------------------+--------------------------------------------------+ -| pte_mkhuge | Creates a HugeTLB | +| arch_make_huge_pte | Creates a HugeTLB | +---------------------------+--------------------------------------------------+ | huge_pte_dirty | Tests a dirty HugeTLB | +---------------------------+--------------------------------------------------+ diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index af59cc7bd307..7887cc2b75bf 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -934,7 +934,7 @@ static void __init hugetlb_basic_tests(struct pgtable_debug_args *args) #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte = pfn_pte(args->fixed_pmd_pfn, args->page_prot); - WARN_ON(!pte_huge(pte_mkhuge(pte))); + WARN_ON(!pte_huge(arch_make_huge_pte(pte, PMD_SHIFT, VM_ACCESS_FLAGS))); #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ } #else /* !CONFIG_HUGETLB_PAGE */ -- GitLab From 7cb1d7ef667716a9ff4e692e7ba1c3817d872222 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 3 Mar 2023 10:12:18 -0500 Subject: [PATCH 1472/5631] mm/khugepaged: cleanup memcg uncharge for failure path Explicit memcg uncharging is not needed when the memcg accounting has the same lifespan of the page/folio. That becomes the case for khugepaged after Yang & Zach's recent rework so the hpage will be allocated for each collapse rather than being cached. Cleanup the explicit memcg uncharge in khugepaged failure path and leave that for put_page(). Link: https://lkml.kernel.org/r/20230303151218.311015-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Zach O'Keefe Reviewed-by: Zach O'Keefe Reviewed-by: Yang Shi Cc: David Stevens Cc: Johannes Weiner Signed-off-by: Andrew Morton --- mm/khugepaged.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 17562c692546..074ea534f786 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1135,10 +1135,8 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, out_up_write: mmap_write_unlock(mm); out_nolock: - if (hpage) { - mem_cgroup_uncharge(page_folio(hpage)); + if (hpage) put_page(hpage); - } trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } @@ -2137,10 +2135,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, unlock_page(hpage); out: VM_BUG_ON(!list_empty(&pagelist)); - if (hpage) { - mem_cgroup_uncharge(page_folio(hpage)); + if (hpage) put_page(hpage); - } trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result); return result; -- GitLab From 6dc4bd4e2fe395f8c9d5d0892e45ff7fed5c66f3 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 3 Mar 2023 15:14:30 +0100 Subject: [PATCH 1473/5631] x86: kmsan: don't rename memintrinsics in uninstrumented files clang -fsanitize=kernel-memory already replaces calls to memset/memcpy/memmove and their __builtin_ versions with __msan_memset/__msan_memcpy/__msan_memmove in instrumented files, so there is no need to override them. In non-instrumented versions we are now required to leave memset() and friends intact, so we cannot replace them with __msan_XXX() functions. Link: https://lkml.kernel.org/r/20230303141433.3422671-1-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Marco Elver Reviewed-by: Marco Elver Cc: Kees Cook Cc: Daniel Vetter Cc: Geert Uytterhoeven Cc: Helge Deller Cc: Tetsuo Handa Signed-off-by: Andrew Morton --- arch/x86/include/asm/string_64.h | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index c1e14cee0722..65537d8711ee 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -15,22 +15,11 @@ #endif #define __HAVE_ARCH_MEMCPY 1 -#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) -#undef memcpy -#define memcpy __msan_memcpy -#else extern void *memcpy(void *to, const void *from, size_t len); -#endif extern void *__memcpy(void *to, const void *from, size_t len); #define __HAVE_ARCH_MEMSET -#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) -extern void *__msan_memset(void *s, int c, size_t n); -#undef memset -#define memset __msan_memset -#else void *memset(void *s, int c, size_t n); -#endif void *__memset(void *s, int c, size_t n); #define __HAVE_ARCH_MEMSET16 @@ -70,13 +59,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n) } #define __HAVE_ARCH_MEMMOVE -#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) -#undef memmove -void *__msan_memmove(void *dest, const void *src, size_t len); -#define memmove __msan_memmove -#else void *memmove(void *dest, const void *src, size_t count); -#endif void *__memmove(void *dest, const void *src, size_t count); int memcmp(const void *cs, const void *ct, size_t count); -- GitLab From d340292553ab48d32d3e768bbb1d11fb942fe02e Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 3 Mar 2023 15:14:31 +0100 Subject: [PATCH 1474/5631] kmsan: another take at fixing memcpy tests commit 5478afc55a21 ("kmsan: fix memcpy tests") uses OPTIMIZER_HIDE_VAR() to hide the uninitialized var from the compiler optimizations. However OPTIMIZER_HIDE_VAR(uninit) enforces an immediate check of @uninit, so memcpy tests did not actually check the behavior of memcpy(), because they always contained a KMSAN report. Replace OPTIMIZER_HIDE_VAR() with a file-local macro that just clobbers the memory with a barrier(), and add a test case for memcpy() that does not expect an error report. Also reflow kmsan_test.c with clang-format. Link: https://lkml.kernel.org/r/20230303141433.3422671-2-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Daniel Vetter Cc: Geert Uytterhoeven Cc: Helge Deller Cc: Kees Cook Cc: Tetsuo Handa Signed-off-by: Andrew Morton --- mm/kmsan/kmsan_test.c | 44 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 38 insertions(+), 6 deletions(-) diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 088e21a48dc4..aeddfdd4f679 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -407,6 +407,37 @@ static void test_printk(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } +/* + * Prevent the compiler from optimizing @var away. Without this, Clang may + * notice that @var is uninitialized and drop memcpy() calls that use it. + * + * There is OPTIMIZER_HIDE_VAR() in linux/compier.h that we cannot use here, + * because it is implemented as inline assembly receiving @var as a parameter + * and will enforce a KMSAN check. Same is true for e.g. barrier_data(var). + */ +#define DO_NOT_OPTIMIZE(var) barrier() + +/* + * Test case: ensure that memcpy() correctly copies initialized values. + * Also serves as a regression test to ensure DO_NOT_OPTIMIZE() does not cause + * extra checks. + */ +static void test_init_memcpy(struct kunit *test) +{ + EXPECTATION_NO_REPORT(expect); + volatile int src; + volatile int dst = 0; + + DO_NOT_OPTIMIZE(src); + src = 1; + kunit_info( + test, + "memcpy()ing aligned initialized src to aligned dst (no reports)\n"); + memcpy((void *)&dst, (void *)&src, sizeof(src)); + kmsan_check_memory((void *)&dst, sizeof(dst)); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + /* * Test case: ensure that memcpy() correctly copies uninitialized values between * aligned `src` and `dst`. @@ -420,7 +451,7 @@ static void test_memcpy_aligned_to_aligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to aligned dst (UMR report)\n"); - OPTIMIZER_HIDE_VAR(uninit_src); + DO_NOT_OPTIMIZE(uninit_src); memcpy((void *)&dst, (void *)&uninit_src, sizeof(uninit_src)); kmsan_check_memory((void *)&dst, sizeof(dst)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); @@ -443,7 +474,7 @@ static void test_memcpy_aligned_to_unaligned(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to unaligned dst (UMR report)\n"); - OPTIMIZER_HIDE_VAR(uninit_src); + DO_NOT_OPTIMIZE(uninit_src); memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); kmsan_check_memory((void *)dst, 4); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); @@ -467,13 +498,14 @@ static void test_memcpy_aligned_to_unaligned2(struct kunit *test) kunit_info( test, "memcpy()ing aligned uninit src to unaligned dst - part 2 (UMR report)\n"); - OPTIMIZER_HIDE_VAR(uninit_src); + DO_NOT_OPTIMIZE(uninit_src); memcpy((void *)&dst[1], (void *)&uninit_src, sizeof(uninit_src)); kmsan_check_memory((void *)&dst[4], sizeof(uninit_src)); KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } -static noinline void fibonacci(int *array, int size, int start) { +static noinline void fibonacci(int *array, int size, int start) +{ if (start < 2 || (start == size)) return; array[start] = array[start - 1] + array[start - 2]; @@ -482,8 +514,7 @@ static noinline void fibonacci(int *array, int size, int start) { static void test_long_origin_chain(struct kunit *test) { - EXPECTATION_UNINIT_VALUE_FN(expect, - "test_long_origin_chain"); + EXPECTATION_UNINIT_VALUE_FN(expect, "test_long_origin_chain"); /* (KMSAN_MAX_ORIGIN_DEPTH * 2) recursive calls to fibonacci(). */ volatile int accum[KMSAN_MAX_ORIGIN_DEPTH * 2 + 2]; int last = ARRAY_SIZE(accum) - 1; @@ -515,6 +546,7 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_uaf), KUNIT_CASE(test_percpu_propagate), KUNIT_CASE(test_printk), + KUNIT_CASE(test_init_memcpy), KUNIT_CASE(test_memcpy_aligned_to_aligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned2), -- GitLab From 27f644dc5a77f8d9ab6d08bc7b95f8631c1530c8 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 3 Mar 2023 15:14:32 +0100 Subject: [PATCH 1475/5631] x86: kmsan: use C versions of memset16/memset32/memset64 KMSAN must see as many memory accesses as possible to prevent false positive reports. Fall back to versions of memset16()/memset32()/memset64() implemented in lib/string.c instead of those written in assembly. Link: https://lkml.kernel.org/r/20230303141433.3422671-3-glider@google.com Signed-off-by: Alexander Potapenko Suggested-by: Tetsuo Handa Reviewed-by: Marco Elver Cc: Geert Uytterhoeven Cc: Daniel Vetter Cc: Helge Deller Cc: Kees Cook Signed-off-by: Andrew Morton --- arch/x86/include/asm/string_64.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 65537d8711ee..857d364b9888 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -22,6 +22,11 @@ extern void *__memcpy(void *to, const void *from, size_t len); void *memset(void *s, int c, size_t n); void *__memset(void *s, int c, size_t n); +/* + * KMSAN needs to instrument as much code as possible. Use C versions of + * memsetXX() from lib/string.c under KMSAN. + */ +#if !defined(CONFIG_KMSAN) #define __HAVE_ARCH_MEMSET16 static inline void *memset16(uint16_t *s, uint16_t v, size_t n) { @@ -57,6 +62,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n) : "memory"); return s; } +#endif #define __HAVE_ARCH_MEMMOVE void *memmove(void *dest, const void *src, size_t count); -- GitLab From 78c74aeee5c82f68955bdff6a9511d04cde1a3c3 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 3 Mar 2023 15:14:33 +0100 Subject: [PATCH 1476/5631] kmsan: add memsetXX tests Add tests ensuring that memset16()/memset32()/memset64() are instrumented by KMSAN and correctly initialize the memory. Link: https://lkml.kernel.org/r/20230303141433.3422671-4-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Daniel Vetter Cc: Geert Uytterhoeven Cc: Helge Deller Cc: Kees Cook Cc: Tetsuo Handa Signed-off-by: Andrew Morton --- mm/kmsan/kmsan_test.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index aeddfdd4f679..7095d3fbb23a 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -504,6 +504,25 @@ static void test_memcpy_aligned_to_unaligned2(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } +/* Generate test cases for memset16(), memset32(), memset64(). */ +#define DEFINE_TEST_MEMSETXX(size) \ + static void test_memset##size(struct kunit *test) \ + { \ + EXPECTATION_NO_REPORT(expect); \ + volatile uint##size##_t uninit; \ + \ + kunit_info(test, \ + "memset" #size "() should initialize memory\n"); \ + DO_NOT_OPTIMIZE(uninit); \ + memset##size((uint##size##_t *)&uninit, 0, 1); \ + kmsan_check_memory((void *)&uninit, sizeof(uninit)); \ + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); \ + } + +DEFINE_TEST_MEMSETXX(16) +DEFINE_TEST_MEMSETXX(32) +DEFINE_TEST_MEMSETXX(64) + static noinline void fibonacci(int *array, int size, int start) { if (start < 2 || (start == size)) @@ -550,6 +569,9 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_memcpy_aligned_to_aligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned), KUNIT_CASE(test_memcpy_aligned_to_unaligned2), + KUNIT_CASE(test_memset16), + KUNIT_CASE(test_memset32), + KUNIT_CASE(test_memset64), KUNIT_CASE(test_long_origin_chain), {}, }; -- GitLab From 3ccefdea226ba3f3b69f9e868d2b1c9995b56615 Mon Sep 17 00:00:00 2001 From: Jaewon Kim Date: Fri, 3 Mar 2023 14:03:32 +0900 Subject: [PATCH 1477/5631] dma-buf: system_heap: avoid reclaim for order 4 Using order 4 pages would be helpful for IOMMUs mapping, but trying to get order 4 pages could spend quite much time in the page allocation. From the perspective of responsiveness, the deterministic memory allocation speed, I think, is quite important. The order 4 allocation with __GFP_RECLAIM may spend much time in reclaim and compation logic. __GFP_NORETRY also may affect. These cause unpredictable delay. To get reasonable allocation speed from dma-buf system heap, use HIGH_ORDER_GFP for order 4 to avoid reclaim. And let me remove meaningless __GFP_COMP for order 0. According to my tests, order 4 with MID_ORDER_GFP could get more number of order 4 pages but the elapsed times could be very slow. time order 8 order 4 order 0 584 usec 0 160 0 28,428 usec 0 160 0 100,701 usec 0 160 0 76,645 usec 0 160 0 25,522 usec 0 160 0 38,798 usec 0 160 0 89,012 usec 0 160 0 23,015 usec 0 160 0 73,360 usec 0 160 0 76,953 usec 0 160 0 31,492 usec 0 160 0 75,889 usec 0 160 0 84,551 usec 0 160 0 84,352 usec 0 160 0 57,103 usec 0 160 0 93,452 usec 0 160 0 If HIGH_ORDER_GFP is used for order 4, the number of order 4 could be decreased but the elapsed time results were quite stable and fast enough. time order 8 order 4 order 0 1,356 usec 0 155 80 1,901 usec 0 11 2384 1,912 usec 0 0 2560 1,911 usec 0 0 2560 1,884 usec 0 0 2560 1,577 usec 0 0 2560 1,366 usec 0 0 2560 1,711 usec 0 0 2560 1,635 usec 0 28 2112 544 usec 10 0 0 633 usec 2 128 0 848 usec 0 160 0 729 usec 0 160 0 1,000 usec 0 160 0 1,358 usec 0 160 0 2,638 usec 0 31 2064 Link: https://lkml.kernel.org/r/20230303050332.10138-1-jaewon31.kim@samsung.com Signed-off-by: Jaewon Kim Reviewed-by: John Stultz Cc: Daniel Vetter Cc: Johannes Weiner Cc: Michal Hocko Cc: Sumit Semwal Cc: T.J. Mercier Signed-off-by: Andrew Morton --- drivers/dma-buf/heaps/system_heap.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index e8bd10e60998..920db302a273 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -41,12 +41,11 @@ struct dma_heap_attachment { bool mapped; }; -#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO | __GFP_COMP) -#define MID_ORDER_GFP (LOW_ORDER_GFP | __GFP_NOWARN) +#define LOW_ORDER_GFP (GFP_HIGHUSER | __GFP_ZERO) #define HIGH_ORDER_GFP (((GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN \ | __GFP_NORETRY) & ~__GFP_RECLAIM) \ | __GFP_COMP) -static gfp_t order_flags[] = {HIGH_ORDER_GFP, MID_ORDER_GFP, LOW_ORDER_GFP}; +static gfp_t order_flags[] = {HIGH_ORDER_GFP, HIGH_ORDER_GFP, LOW_ORDER_GFP}; /* * The selection of the orders used for allocation (1MB, 64K, 4K) is designed * to match with the sizes often found in IOMMUs. Using order 4 pages instead -- GitLab From a40a71e8343e281fedce9747ac1972c5556a982b Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 4 Mar 2023 12:48:32 +0900 Subject: [PATCH 1478/5631] zsmalloc: remove insert_zspage() ->inuse optimization Patch series "zsmalloc: fine-grained fullness and new compaction algorithm", v4. Existing zsmalloc page fullness grouping leads to suboptimal page selection for both zs_malloc() and zs_compact(). This patchset reworks zsmalloc fullness grouping/classification. Additinally it also implements new compaction algorithm that is expected to use less CPU-cycles (as it potentially does fewer memcpy-s in zs_object_copy()). Test (synthetic) results can be seen in patch 0003. This patch (of 4): This optimization has no effect. It only ensures that when a zspage was added to its corresponding fullness list, its "inuse" counter was higher or lower than the "inuse" counter of the zspage at the head of the list. The intention was to keep busy zspages at the head, so they could be filled up and moved to the ZS_FULL fullness group more quickly. However, this doesn't work as the "inuse" counter of a zspage can be modified by obj_free() but the zspage may still belong to the same fullness list. So, fix_fullness_group() won't change the zspage's position in relation to the head's "inuse" counter, leading to a largely random order of zspages within the fullness list. For instance, consider a printout of the "inuse" counters of the first 10 zspages in a class that holds 93 objects per zspage: ZS_ALMOST_EMPTY: 36 67 68 64 35 54 63 52 As we can see the zspage with the lowest "inuse" counter is actually the head of the fullness list. Remove this pointless "optimisation". Link: https://lkml.kernel.org/r/20230304034835.2082479-1-senozhatsky@chromium.org Link: https://lkml.kernel.org/r/20230304034835.2082479-2-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 3aed46ab7e6c..abe0c4d7942d 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -762,19 +762,8 @@ static void insert_zspage(struct size_class *class, struct zspage *zspage, enum fullness_group fullness) { - struct zspage *head; - class_stat_inc(class, fullness, 1); - head = list_first_entry_or_null(&class->fullness_list[fullness], - struct zspage, list); - /* - * We want to see more ZS_FULL pages and less almost empty/full. - * Put pages with higher ->inuse first. - */ - if (head && get_zspage_inuse(zspage) < get_zspage_inuse(head)) - list_add(&zspage->list, &head->list); - else - list_add(&zspage->list, &class->fullness_list[fullness]); + list_add(&zspage->list, &class->fullness_list[fullness]); } /* -- GitLab From 4c7ac97285d8dcb970d22b6dda9872f2c9d5f8b4 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 4 Mar 2023 12:48:33 +0900 Subject: [PATCH 1479/5631] zsmalloc: fine-grained inuse ratio based fullness grouping Each zspage maintains ->inuse counter which keeps track of the number of objects stored in the zspage. The ->inuse counter also determines the zspage's "fullness group" which is calculated as the ratio of the "inuse" objects to the total number of objects the zspage can hold (objs_per_zspage). The closer the ->inuse counter is to objs_per_zspage, the better. Each size class maintains several fullness lists, that keep track of zspages of particular "fullness". Pages within each fullness list are stored in random order with regard to the ->inuse counter. This is because sorting the zspages by ->inuse counter each time obj_malloc() or obj_free() is called would be too expensive. However, the ->inuse counter is still a crucial factor in many situations. For the two major zsmalloc operations, zs_malloc() and zs_compact(), we typically select the head zspage from the corresponding fullness list as the best candidate zspage. However, this assumption is not always accurate. For the zs_malloc() operation, the optimal candidate zspage should have the highest ->inuse counter. This is because the goal is to maximize the number of ZS_FULL zspages and make full use of all allocated memory. For the zs_compact() operation, the optimal source zspage should have the lowest ->inuse counter. This is because compaction needs to move objects in use to another page before it can release the zspage and return its physical pages to the buddy allocator. The fewer objects in use, the quicker compaction can release the zspage. Additionally, compaction is measured by the number of pages it releases. This patch reworks the fullness grouping mechanism. Instead of having two groups - ZS_ALMOST_EMPTY (usage ratio below 3/4) and ZS_ALMOST_FULL (usage ration above 3/4) - that result in too many zspages being included in the ALMOST_EMPTY group for specific classes, size classes maintain a larger number of fullness lists that give strict guarantees on the minimum and maximum ->inuse values within each group. Each group represents a 10% change in the ->inuse ratio compared to neighboring groups. In essence, there are groups for zspages with 0%, 10%, 20% usage ratios, and so on, up to 100%. This enhances the selection of candidate zspages for both zs_malloc() and zs_compact(). A printout of the ->inuse counters of the first 7 zspages per (random) class fullness group: class-768 objs_per_zspage 16: fullness 100%: empty fullness 99%: empty fullness 90%: empty fullness 80%: empty fullness 70%: empty fullness 60%: 8 8 9 9 8 8 8 fullness 50%: empty fullness 40%: 5 5 6 5 5 5 5 fullness 30%: 4 4 4 4 4 4 4 fullness 20%: 2 3 2 3 3 2 2 fullness 10%: 1 1 1 1 1 1 1 fullness 0%: empty The zs_malloc() function searches through the groups of pages starting with the one having the highest usage ratio. This means that it always selects a zspage from the group with the least internal fragmentation (highest usage ratio) and makes it even less fragmented by increasing its usage ratio. The zs_compact() function, on the other hand, begins by scanning the group with the highest fragmentation (lowest usage ratio) to locate the source page. The first available zspage is selected, and then the function moves downward to find a destination zspage in the group with the lowest internal fragmentation (highest usage ratio). Link: https://lkml.kernel.org/r/20230304034835.2082479-3-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 248 ++++++++++++++++++++++++++------------------------ 1 file changed, 130 insertions(+), 118 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index abe0c4d7942d..cc59336a966a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -127,7 +127,7 @@ #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) #define HUGE_BITS 1 -#define FULLNESS_BITS 2 +#define FULLNESS_BITS 4 #define CLASS_BITS 8 #define ISOLATED_BITS 5 #define MAGIC_VAL_BITS 8 @@ -159,51 +159,46 @@ #define ZS_SIZE_CLASSES (DIV_ROUND_UP(ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE, \ ZS_SIZE_CLASS_DELTA) + 1) +/* + * Pages are distinguished by the ratio of used memory (that is the ratio + * of ->inuse objects to all objects that page can store). For example, + * INUSE_RATIO_10 means that the ratio of used objects is > 0% and <= 10%. + * + * The number of fullness groups is not random. It allows us to keep + * difference between the least busy page in the group (minimum permitted + * number of ->inuse objects) and the most busy page (maximum permitted + * number of ->inuse objects) at a reasonable value. + */ enum fullness_group { - ZS_EMPTY, - ZS_ALMOST_EMPTY, - ZS_ALMOST_FULL, - ZS_FULL, - NR_ZS_FULLNESS, + ZS_INUSE_RATIO_0, + ZS_INUSE_RATIO_10, + /* NOTE: 5 more fullness groups here */ + ZS_INUSE_RATIO_70 = 7, + /* NOTE: 2 more fullness groups here */ + ZS_INUSE_RATIO_99 = 10, + ZS_INUSE_RATIO_100, + NR_FULLNESS_GROUPS, }; enum class_stat_type { - CLASS_EMPTY, - CLASS_ALMOST_EMPTY, - CLASS_ALMOST_FULL, - CLASS_FULL, - OBJ_ALLOCATED, - OBJ_USED, - NR_ZS_STAT_TYPE, + /* NOTE: stats for 12 fullness groups here: from inuse 0 to 100 */ + ZS_OBJS_ALLOCATED = NR_FULLNESS_GROUPS, + ZS_OBJS_INUSE, + NR_CLASS_STAT_TYPES, }; struct zs_size_stat { - unsigned long objs[NR_ZS_STAT_TYPE]; + unsigned long objs[NR_CLASS_STAT_TYPES]; }; #ifdef CONFIG_ZSMALLOC_STAT static struct dentry *zs_stat_root; #endif -/* - * We assign a page to ZS_ALMOST_EMPTY fullness group when: - * n <= N / f, where - * n = number of allocated objects - * N = total number of objects zspage can store - * f = fullness_threshold_frac - * - * Similarly, we assign zspage to: - * ZS_ALMOST_FULL when n > N / f - * ZS_EMPTY when n == 0 - * ZS_FULL when n == N - * - * (see: fix_fullness_group()) - */ -static const int fullness_threshold_frac = 4; static size_t huge_class_size; struct size_class { - struct list_head fullness_list[NR_ZS_FULLNESS]; + struct list_head fullness_list[NR_FULLNESS_GROUPS]; /* * Size of objects stored in this class. Must be multiple * of ZS_ALIGN. @@ -547,8 +542,8 @@ static inline void set_freeobj(struct zspage *zspage, unsigned int obj) } static void get_zspage_mapping(struct zspage *zspage, - unsigned int *class_idx, - enum fullness_group *fullness) + unsigned int *class_idx, + int *fullness) { BUG_ON(zspage->magic != ZSPAGE_MAGIC); @@ -557,14 +552,14 @@ static void get_zspage_mapping(struct zspage *zspage, } static struct size_class *zspage_class(struct zs_pool *pool, - struct zspage *zspage) + struct zspage *zspage) { return pool->size_class[zspage->class]; } static void set_zspage_mapping(struct zspage *zspage, - unsigned int class_idx, - enum fullness_group fullness) + unsigned int class_idx, + int fullness) { zspage->class = class_idx; zspage->fullness = fullness; @@ -588,23 +583,19 @@ static int get_size_class_index(int size) return min_t(int, ZS_SIZE_CLASSES - 1, idx); } -/* type can be of enum type class_stat_type or fullness_group */ static inline void class_stat_inc(struct size_class *class, int type, unsigned long cnt) { class->stats.objs[type] += cnt; } -/* type can be of enum type class_stat_type or fullness_group */ static inline void class_stat_dec(struct size_class *class, int type, unsigned long cnt) { class->stats.objs[type] -= cnt; } -/* type can be of enum type class_stat_type or fullness_group */ -static inline unsigned long zs_stat_get(struct size_class *class, - int type) +static inline unsigned long zs_stat_get(struct size_class *class, int type) { return class->stats.objs[type]; } @@ -646,16 +637,27 @@ static int zs_stats_size_show(struct seq_file *s, void *v) "pages_per_zspage", "freeable"); for (i = 0; i < ZS_SIZE_CLASSES; i++) { + int fg; + class = pool->size_class[i]; if (class->index != i) continue; spin_lock(&pool->lock); - class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); - class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); - obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); - obj_used = zs_stat_get(class, OBJ_USED); + class_almost_full = 0; + class_almost_empty = 0; + /* + * Replicate old behaviour for almost_full and almost_empty + * stats. + */ + for (fg = ZS_INUSE_RATIO_70; fg <= ZS_INUSE_RATIO_99; fg++) + class_almost_full += zs_stat_get(class, fg); + for (fg = ZS_INUSE_RATIO_10; fg < ZS_INUSE_RATIO_70; fg++) + class_almost_empty += zs_stat_get(class, fg); + + obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED); + obj_used = zs_stat_get(class, ZS_OBJS_INUSE); freeable = zs_can_compact(class); spin_unlock(&pool->lock); @@ -726,30 +728,28 @@ static inline void zs_pool_stat_destroy(struct zs_pool *pool) /* * For each size class, zspages are divided into different groups - * depending on how "full" they are. This was done so that we could - * easily find empty or nearly empty zspages when we try to shrink - * the pool (not yet implemented). This function returns fullness + * depending on their usage ratio. This function returns fullness * status of the given page. */ -static enum fullness_group get_fullness_group(struct size_class *class, - struct zspage *zspage) +static int get_fullness_group(struct size_class *class, struct zspage *zspage) { - int inuse, objs_per_zspage; - enum fullness_group fg; + int inuse, objs_per_zspage, ratio; inuse = get_zspage_inuse(zspage); objs_per_zspage = class->objs_per_zspage; if (inuse == 0) - fg = ZS_EMPTY; - else if (inuse == objs_per_zspage) - fg = ZS_FULL; - else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac) - fg = ZS_ALMOST_EMPTY; - else - fg = ZS_ALMOST_FULL; + return ZS_INUSE_RATIO_0; + if (inuse == objs_per_zspage) + return ZS_INUSE_RATIO_100; - return fg; + ratio = 100 * inuse / objs_per_zspage; + /* + * Take integer division into consideration: a page with one inuse + * object out of 127 possible, will end up having 0 usage ratio, + * which is wrong as it belongs in ZS_INUSE_RATIO_10 fullness group. + */ + return ratio / 10 + 1; } /* @@ -760,7 +760,7 @@ static enum fullness_group get_fullness_group(struct size_class *class, */ static void insert_zspage(struct size_class *class, struct zspage *zspage, - enum fullness_group fullness) + int fullness) { class_stat_inc(class, fullness, 1); list_add(&zspage->list, &class->fullness_list[fullness]); @@ -772,7 +772,7 @@ static void insert_zspage(struct size_class *class, */ static void remove_zspage(struct size_class *class, struct zspage *zspage, - enum fullness_group fullness) + int fullness) { VM_BUG_ON(list_empty(&class->fullness_list[fullness])); @@ -783,17 +783,16 @@ static void remove_zspage(struct size_class *class, /* * Each size class maintains zspages in different fullness groups depending * on the number of live objects they contain. When allocating or freeing - * objects, the fullness status of the page can change, say, from ALMOST_FULL - * to ALMOST_EMPTY when freeing an object. This function checks if such - * a status change has occurred for the given page and accordingly moves the - * page from the freelist of the old fullness group to that of the new - * fullness group. + * objects, the fullness status of the page can change, for instance, from + * INUSE_RATIO_80 to INUSE_RATIO_70 when freeing an object. This function + * checks if such a status change has occurred for the given page and + * accordingly moves the page from the list of the old fullness group to that + * of the new fullness group. */ -static enum fullness_group fix_fullness_group(struct size_class *class, - struct zspage *zspage) +static int fix_fullness_group(struct size_class *class, struct zspage *zspage) { int class_idx; - enum fullness_group currfg, newfg; + int currfg, newfg; get_zspage_mapping(zspage, &class_idx, &currfg); newfg = get_fullness_group(class, zspage); @@ -966,7 +965,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, struct zspage *zspage) { struct page *page, *next; - enum fullness_group fg; + int fg; unsigned int class_idx; get_zspage_mapping(zspage, &class_idx, &fg); @@ -974,7 +973,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, assert_spin_locked(&pool->lock); VM_BUG_ON(get_zspage_inuse(zspage)); - VM_BUG_ON(fg != ZS_EMPTY); + VM_BUG_ON(fg != ZS_INUSE_RATIO_0); /* Free all deferred handles from zs_free */ free_handles(pool, class, zspage); @@ -992,9 +991,8 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, cache_free_zspage(pool, zspage); - class_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage); - atomic_long_sub(class->pages_per_zspage, - &pool->pages_allocated); + class_stat_dec(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); + atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated); } static void free_zspage(struct zs_pool *pool, struct size_class *class, @@ -1013,7 +1011,7 @@ static void free_zspage(struct zs_pool *pool, struct size_class *class, return; } - remove_zspage(class, zspage, ZS_EMPTY); + remove_zspage(class, zspage, ZS_INUSE_RATIO_0); #ifdef CONFIG_ZPOOL list_del(&zspage->lru); #endif @@ -1149,9 +1147,9 @@ static struct zspage *find_get_zspage(struct size_class *class) int i; struct zspage *zspage; - for (i = ZS_ALMOST_FULL; i >= ZS_EMPTY; i--) { + for (i = ZS_INUSE_RATIO_99; i >= ZS_INUSE_RATIO_0; i--) { zspage = list_first_entry_or_null(&class->fullness_list[i], - struct zspage, list); + struct zspage, list); if (zspage) break; } @@ -1510,7 +1508,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) { unsigned long handle, obj; struct size_class *class; - enum fullness_group newfg; + int newfg; struct zspage *zspage; if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE)) @@ -1532,7 +1530,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* Now move the zspage to another fullness group, if required */ fix_fullness_group(class, zspage); record_obj(handle, obj); - class_stat_inc(class, OBJ_USED, 1); + class_stat_inc(class, ZS_OBJS_INUSE, 1); spin_unlock(&pool->lock); return handle; @@ -1552,10 +1550,9 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) insert_zspage(class, zspage, newfg); set_zspage_mapping(zspage, class->index, newfg); record_obj(handle, obj); - atomic_long_add(class->pages_per_zspage, - &pool->pages_allocated); - class_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage); - class_stat_inc(class, OBJ_USED, 1); + atomic_long_add(class->pages_per_zspage, &pool->pages_allocated); + class_stat_inc(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage); + class_stat_inc(class, ZS_OBJS_INUSE, 1); /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); @@ -1611,7 +1608,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle) struct page *f_page; unsigned long obj; struct size_class *class; - enum fullness_group fullness; + int fullness; if (IS_ERR_OR_NULL((void *)handle)) return; @@ -1626,7 +1623,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle) zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - class_stat_dec(class, OBJ_USED, 1); + class_stat_dec(class, ZS_OBJS_INUSE, 1); #ifdef CONFIG_ZPOOL if (zspage->under_reclaim) { @@ -1644,7 +1641,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle) obj_free(class->size, obj, NULL); fullness = fix_fullness_group(class, zspage); - if (fullness == ZS_EMPTY) + if (fullness == ZS_INUSE_RATIO_0) free_zspage(pool, class, zspage); spin_unlock(&pool->lock); @@ -1826,22 +1823,33 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, return ret; } -static struct zspage *isolate_zspage(struct size_class *class, bool source) +static struct zspage *isolate_src_zspage(struct size_class *class) { - int i; struct zspage *zspage; - enum fullness_group fg[2] = {ZS_ALMOST_EMPTY, ZS_ALMOST_FULL}; + int fg; - if (!source) { - fg[0] = ZS_ALMOST_FULL; - fg[1] = ZS_ALMOST_EMPTY; + for (fg = ZS_INUSE_RATIO_10; fg <= ZS_INUSE_RATIO_99; fg++) { + zspage = list_first_entry_or_null(&class->fullness_list[fg], + struct zspage, list); + if (zspage) { + remove_zspage(class, zspage, fg); + return zspage; + } } - for (i = 0; i < 2; i++) { - zspage = list_first_entry_or_null(&class->fullness_list[fg[i]], - struct zspage, list); + return zspage; +} + +static struct zspage *isolate_dst_zspage(struct size_class *class) +{ + struct zspage *zspage; + int fg; + + for (fg = ZS_INUSE_RATIO_99; fg >= ZS_INUSE_RATIO_10; fg--) { + zspage = list_first_entry_or_null(&class->fullness_list[fg], + struct zspage, list); if (zspage) { - remove_zspage(class, zspage, fg[i]); + remove_zspage(class, zspage, fg); return zspage; } } @@ -1854,12 +1862,11 @@ static struct zspage *isolate_zspage(struct size_class *class, bool source) * @class: destination class * @zspage: target page * - * Return @zspage's fullness_group + * Return @zspage's fullness status */ -static enum fullness_group putback_zspage(struct size_class *class, - struct zspage *zspage) +static int putback_zspage(struct size_class *class, struct zspage *zspage) { - enum fullness_group fullness; + int fullness; fullness = get_fullness_group(class, zspage); insert_zspage(class, zspage, fullness); @@ -2123,7 +2130,7 @@ static void async_free_zspage(struct work_struct *work) int i; struct size_class *class; unsigned int class_idx; - enum fullness_group fullness; + int fullness; struct zspage *zspage, *tmp; LIST_HEAD(free_pages); struct zs_pool *pool = container_of(work, struct zs_pool, @@ -2135,7 +2142,8 @@ static void async_free_zspage(struct work_struct *work) continue; spin_lock(&pool->lock); - list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); + list_splice_init(&class->fullness_list[ZS_INUSE_RATIO_0], + &free_pages); spin_unlock(&pool->lock); } @@ -2144,7 +2152,7 @@ static void async_free_zspage(struct work_struct *work) lock_zspage(zspage); get_zspage_mapping(zspage, &class_idx, &fullness); - VM_BUG_ON(fullness != ZS_EMPTY); + VM_BUG_ON(fullness != ZS_INUSE_RATIO_0); class = pool->size_class[class_idx]; spin_lock(&pool->lock); #ifdef CONFIG_ZPOOL @@ -2192,8 +2200,8 @@ static inline void zs_flush_migration(struct zs_pool *pool) { } static unsigned long zs_can_compact(struct size_class *class) { unsigned long obj_wasted; - unsigned long obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); - unsigned long obj_used = zs_stat_get(class, OBJ_USED); + unsigned long obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED); + unsigned long obj_used = zs_stat_get(class, ZS_OBJS_INUSE); if (obj_allocated <= obj_used) return 0; @@ -2217,7 +2225,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, * as well as zpage allocation/free */ spin_lock(&pool->lock); - while ((src_zspage = isolate_zspage(class, true))) { + while ((src_zspage = isolate_src_zspage(class))) { /* protect someone accessing the zspage(i.e., zs_map_object) */ migrate_write_lock(src_zspage); @@ -2227,7 +2235,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, cc.obj_idx = 0; cc.s_page = get_first_page(src_zspage); - while ((dst_zspage = isolate_zspage(class, false))) { + while ((dst_zspage = isolate_dst_zspage(class))) { migrate_write_lock_nested(dst_zspage); cc.d_page = get_first_page(dst_zspage); @@ -2252,7 +2260,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, putback_zspage(class, dst_zspage); migrate_write_unlock(dst_zspage); - if (putback_zspage(class, src_zspage) == ZS_EMPTY) { + if (putback_zspage(class, src_zspage) == ZS_INUSE_RATIO_0) { migrate_write_unlock(src_zspage); free_zspage(pool, class, src_zspage); pages_freed += class->pages_per_zspage; @@ -2410,7 +2418,7 @@ struct zs_pool *zs_create_pool(const char *name) int pages_per_zspage; int objs_per_zspage; struct size_class *class; - int fullness = 0; + int fullness; size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA; if (size > ZS_MAX_ALLOC_SIZE) @@ -2464,9 +2472,12 @@ struct zs_pool *zs_create_pool(const char *name) class->pages_per_zspage = pages_per_zspage; class->objs_per_zspage = objs_per_zspage; pool->size_class[i] = class; - for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; - fullness++) + + fullness = ZS_INUSE_RATIO_0; + while (fullness < NR_FULLNESS_GROUPS) { INIT_LIST_HEAD(&class->fullness_list[fullness]); + fullness++; + } prev_class = class; } @@ -2512,11 +2523,12 @@ void zs_destroy_pool(struct zs_pool *pool) if (class->index != i) continue; - for (fg = ZS_EMPTY; fg < NR_ZS_FULLNESS; fg++) { - if (!list_empty(&class->fullness_list[fg])) { - pr_info("Freeing non-empty class with size %db, fullness group %d\n", - class->size, fg); - } + for (fg = ZS_INUSE_RATIO_0; fg < NR_FULLNESS_GROUPS; fg++) { + if (list_empty(&class->fullness_list[fg])) + continue; + + pr_err("Class-%d fullness group %d is not empty\n", + class->size, fg); } kfree(class); } @@ -2618,7 +2630,7 @@ static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) unsigned long handle; struct zspage *zspage; struct page *page; - enum fullness_group fullness; + int fullness; /* Lock LRU and fullness list */ spin_lock(&pool->lock); @@ -2688,7 +2700,7 @@ static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) * while the page is removed from the pool. Fix it * up for the check in __free_zspage(). */ - zspage->fullness = ZS_EMPTY; + zspage->fullness = ZS_INUSE_RATIO_0; __free_zspage(pool, class, zspage); spin_unlock(&pool->lock); -- GitLab From 5a845e9f2d660907a7e1f9f333f7927b6f81b894 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 4 Mar 2023 12:48:34 +0900 Subject: [PATCH 1480/5631] zsmalloc: rework compaction algorithm The zsmalloc compaction algorithm has the potential to waste some CPU cycles, particularly when compacting pages within the same fullness group. This is due to the way it selects the head page of the fullness list for source and destination pages, and how it reinserts those pages during each iteration. The algorithm may first use a page as a migration destination and then as a migration source, leading to an unnecessary back-and-forth movement of objects. Consider the following fullness list: PageA PageB PageC PageD PageE During the first iteration, the compaction algorithm will select PageA as the source and PageB as the destination. All of PageA's objects will be moved to PageB, and then PageA will be released while PageB is reinserted into the fullness list. PageB PageC PageD PageE During the next iteration, the compaction algorithm will again select the head of the list as the source and destination, meaning that PageB will now serve as the source and PageC as the destination. This will result in the objects being moved away from PageB, the same objects that were just moved to PageB in the previous iteration. To prevent this avalanche effect, the compaction algorithm should not reinsert the destination page between iterations. By doing so, the most optimal page will continue to be used and its usage ratio will increase, reducing internal fragmentation. The destination page should only be reinserted into the fullness list if: - It becomes full - No source page is available. TEST ==== It's very challenging to reliably test this series. I ended up developing my own synthetic test that has 100% reproducibility. The test generates significan fragmentation (for each size class) and then performs compaction for each class individually and tracks the number of memcpy() in zs_object_copy(), so that we can compare the amount work compaction does on per-class basis. Total amount of work (zram mm_stat objs_moved) ---------------------------------------------- Old fullness grouping, old compaction algorithm: 323977 memcpy() in zs_object_copy(). Old fullness grouping, new compaction algorithm: 262944 memcpy() in zs_object_copy(). New fullness grouping, new compaction algorithm: 213978 memcpy() in zs_object_copy(). Per-class compaction memcpy() comparison (T-test) ------------------------------------------------- x Old fullness grouping, old compaction algorithm + Old fullness grouping, new compaction algorithm N Min Max Median Avg Stddev x 140 349 3513 2461 2314.1214 806.03271 + 140 289 2778 2006 1878.1714 641.02073 Difference at 95.0% confidence -435.95 +/- 170.595 -18.8387% +/- 7.37193% (Student's t, pooled s = 728.216) x Old fullness grouping, old compaction algorithm + New fullness grouping, new compaction algorithm N Min Max Median Avg Stddev x 140 349 3513 2461 2314.1214 806.03271 + 140 226 2279 1644 1528.4143 524.85268 Difference at 95.0% confidence -785.707 +/- 159.331 -33.9527% +/- 6.88516% (Student's t, pooled s = 680.132) Link: https://lkml.kernel.org/r/20230304034835.2082479-4-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 78 ++++++++++++++++++++++++--------------------------- 1 file changed, 36 insertions(+), 42 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index cc59336a966a..a61540afbb28 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1782,15 +1782,14 @@ struct zs_compact_control { int obj_idx; }; -static int migrate_zspage(struct zs_pool *pool, struct size_class *class, - struct zs_compact_control *cc) +static void migrate_zspage(struct zs_pool *pool, struct size_class *class, + struct zs_compact_control *cc) { unsigned long used_obj, free_obj; unsigned long handle; struct page *s_page = cc->s_page; struct page *d_page = cc->d_page; int obj_idx = cc->obj_idx; - int ret = 0; while (1) { handle = find_alloced_obj(class, s_page, &obj_idx); @@ -1803,10 +1802,8 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, } /* Stop if there is no more space */ - if (zspage_full(class, get_zspage(d_page))) { - ret = -ENOMEM; + if (zspage_full(class, get_zspage(d_page))) break; - } used_obj = handle_to_obj(handle); free_obj = obj_malloc(pool, get_zspage(d_page), handle); @@ -1819,8 +1816,6 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, /* Remember last position in this iteration */ cc->s_page = s_page; cc->obj_idx = obj_idx; - - return ret; } static struct zspage *isolate_src_zspage(struct size_class *class) @@ -2216,7 +2211,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, struct size_class *class) { struct zs_compact_control cc; - struct zspage *src_zspage; + struct zspage *src_zspage = NULL; struct zspage *dst_zspage = NULL; unsigned long pages_freed = 0; @@ -2225,50 +2220,45 @@ static unsigned long __zs_compact(struct zs_pool *pool, * as well as zpage allocation/free */ spin_lock(&pool->lock); - while ((src_zspage = isolate_src_zspage(class))) { - /* protect someone accessing the zspage(i.e., zs_map_object) */ - migrate_write_lock(src_zspage); + while (zs_can_compact(class)) { + int fg; - if (!zs_can_compact(class)) + if (!dst_zspage) { + dst_zspage = isolate_dst_zspage(class); + if (!dst_zspage) + break; + migrate_write_lock(dst_zspage); + cc.d_page = get_first_page(dst_zspage); + } + + src_zspage = isolate_src_zspage(class); + if (!src_zspage) break; + migrate_write_lock_nested(src_zspage); + cc.obj_idx = 0; cc.s_page = get_first_page(src_zspage); + migrate_zspage(pool, class, &cc); + fg = putback_zspage(class, src_zspage); + migrate_write_unlock(src_zspage); - while ((dst_zspage = isolate_dst_zspage(class))) { - migrate_write_lock_nested(dst_zspage); - - cc.d_page = get_first_page(dst_zspage); - /* - * If there is no more space in dst_page, resched - * and see if anyone had allocated another zspage. - */ - if (!migrate_zspage(pool, class, &cc)) - break; + if (fg == ZS_INUSE_RATIO_0) { + free_zspage(pool, class, src_zspage); + pages_freed += class->pages_per_zspage; + src_zspage = NULL; + } + if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100 + || spin_is_contended(&pool->lock)) { putback_zspage(class, dst_zspage); migrate_write_unlock(dst_zspage); dst_zspage = NULL; - if (spin_is_contended(&pool->lock)) - break; - } - /* Stop if we couldn't find slot */ - if (dst_zspage == NULL) - break; - - putback_zspage(class, dst_zspage); - migrate_write_unlock(dst_zspage); - - if (putback_zspage(class, src_zspage) == ZS_INUSE_RATIO_0) { - migrate_write_unlock(src_zspage); - free_zspage(pool, class, src_zspage); - pages_freed += class->pages_per_zspage; - } else - migrate_write_unlock(src_zspage); - spin_unlock(&pool->lock); - cond_resched(); - spin_lock(&pool->lock); + spin_unlock(&pool->lock); + cond_resched(); + spin_lock(&pool->lock); + } } if (src_zspage) { @@ -2276,6 +2266,10 @@ static unsigned long __zs_compact(struct zs_pool *pool, migrate_write_unlock(src_zspage); } + if (dst_zspage) { + putback_zspage(class, dst_zspage); + migrate_write_unlock(dst_zspage); + } spin_unlock(&pool->lock); return pages_freed; -- GitLab From e1807d5d27ddf1c1388fea0e9af3ed9273844e67 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 4 Mar 2023 12:48:35 +0900 Subject: [PATCH 1481/5631] zsmalloc: show per fullness group class stats We keep the old fullness (3/4 threshold) reporting in zs_stats_size_show(). Switch from allmost full/empty stats to fine-grained per inuse ratio (fullness group) reporting, which gives signicantly more data on classes fragmentation. Link: https://lkml.kernel.org/r/20230304034835.2082479-5-senozhatsky@chromium.org Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 53 ++++++++++++++++++++++----------------------------- 1 file changed, 23 insertions(+), 30 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index a61540afbb28..aea50e2aa350 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -172,9 +172,7 @@ enum fullness_group { ZS_INUSE_RATIO_0, ZS_INUSE_RATIO_10, - /* NOTE: 5 more fullness groups here */ - ZS_INUSE_RATIO_70 = 7, - /* NOTE: 2 more fullness groups here */ + /* NOTE: 8 more fullness groups here */ ZS_INUSE_RATIO_99 = 10, ZS_INUSE_RATIO_100, NR_FULLNESS_GROUPS, @@ -621,23 +619,22 @@ static unsigned long zs_can_compact(struct size_class *class); static int zs_stats_size_show(struct seq_file *s, void *v) { - int i; + int i, fg; struct zs_pool *pool = s->private; struct size_class *class; int objs_per_zspage; - unsigned long class_almost_full, class_almost_empty; unsigned long obj_allocated, obj_used, pages_used, freeable; - unsigned long total_class_almost_full = 0, total_class_almost_empty = 0; unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; unsigned long total_freeable = 0; + unsigned long inuse_totals[NR_FULLNESS_GROUPS] = {0, }; - seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s %8s\n", - "class", "size", "almost_full", "almost_empty", + seq_printf(s, " %5s %5s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %9s %13s %10s %10s %16s %8s\n", + "class", "size", "10%", "20%", "30%", "40%", + "50%", "60%", "70%", "80%", "90%", "99%", "100%", "obj_allocated", "obj_used", "pages_used", "pages_per_zspage", "freeable"); for (i = 0; i < ZS_SIZE_CLASSES; i++) { - int fg; class = pool->size_class[i]; @@ -645,16 +642,12 @@ static int zs_stats_size_show(struct seq_file *s, void *v) continue; spin_lock(&pool->lock); - class_almost_full = 0; - class_almost_empty = 0; - /* - * Replicate old behaviour for almost_full and almost_empty - * stats. - */ - for (fg = ZS_INUSE_RATIO_70; fg <= ZS_INUSE_RATIO_99; fg++) - class_almost_full += zs_stat_get(class, fg); - for (fg = ZS_INUSE_RATIO_10; fg < ZS_INUSE_RATIO_70; fg++) - class_almost_empty += zs_stat_get(class, fg); + + seq_printf(s, " %5u %5u ", i, class->size); + for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++) { + inuse_totals[fg] += zs_stat_get(class, fg); + seq_printf(s, "%9lu ", zs_stat_get(class, fg)); + } obj_allocated = zs_stat_get(class, ZS_OBJS_ALLOCATED); obj_used = zs_stat_get(class, ZS_OBJS_INUSE); @@ -665,14 +658,10 @@ static int zs_stats_size_show(struct seq_file *s, void *v) pages_used = obj_allocated / objs_per_zspage * class->pages_per_zspage; - seq_printf(s, " %5u %5u %11lu %12lu %13lu" - " %10lu %10lu %16d %8lu\n", - i, class->size, class_almost_full, class_almost_empty, - obj_allocated, obj_used, pages_used, - class->pages_per_zspage, freeable); + seq_printf(s, "%13lu %10lu %10lu %16d %8lu\n", + obj_allocated, obj_used, pages_used, + class->pages_per_zspage, freeable); - total_class_almost_full += class_almost_full; - total_class_almost_empty += class_almost_empty; total_objs += obj_allocated; total_used_objs += obj_used; total_pages += pages_used; @@ -680,10 +669,14 @@ static int zs_stats_size_show(struct seq_file *s, void *v) } seq_puts(s, "\n"); - seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu %16s %8lu\n", - "Total", "", total_class_almost_full, - total_class_almost_empty, total_objs, - total_used_objs, total_pages, "", total_freeable); + seq_printf(s, " %5s %5s ", "Total", ""); + + for (fg = ZS_INUSE_RATIO_10; fg < NR_FULLNESS_GROUPS; fg++) + seq_printf(s, "%9lu ", inuse_totals[fg]); + + seq_printf(s, "%13lu %10lu %10lu %16s %8lu\n", + total_objs, total_used_objs, total_pages, "", + total_freeable); return 0; } -- GitLab From 99c29133639a29fa803ea27ec79bf9e732efd062 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Mon, 6 Mar 2023 17:15:48 +0100 Subject: [PATCH 1482/5631] mm: add PTE pointer parameter to flush_tlb_fix_spurious_fault() s390 can do more fine-grained handling of spurious TLB protection faults, when there also is the PTE pointer available. Therefore, pass on the PTE pointer to flush_tlb_fix_spurious_fault() as an additional parameter. This will add no functional change to other architectures, but those with private flush_tlb_fix_spurious_fault() implementations need to be made aware of the new parameter. Link: https://lkml.kernel.org/r/20230306161548.661740-1-gerald.schaefer@linux.ibm.com Signed-off-by: Gerald Schaefer Reviewed-by: Alexander Gordeev Acked-by: Catalin Marinas [arm64] Acked-by: Michael Ellerman [powerpc] Acked-by: David Hildenbrand Cc: Anshuman Khandual Cc: Borislav Petkov (AMD) Cc: Christophe Leroy Cc: Dave Hansen Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Nicholas Piggin Cc: Thomas Bogendoerfer Cc: Thomas Gleixner Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/pgtable.h | 2 +- arch/mips/include/asm/pgtable.h | 3 ++- arch/powerpc/include/asm/book3s/64/tlbflush.h | 3 ++- arch/s390/include/asm/pgtable.h | 12 +++++++----- arch/x86/include/asm/pgtable.h | 2 +- include/linux/pgtable.h | 2 +- mm/memory.c | 3 ++- mm/pgtable-generic.c | 2 +- 8 files changed, 17 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b6ba466e2e8a..0bd18de9fd97 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -57,7 +57,7 @@ static inline bool arch_thp_swp_supported(void) * fault on one CPU which has been handled concurrently by another CPU * does not need to perform additional invalidation. */ -#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) /* * ZERO_PAGE is a global shared page that is always zero: used diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 791389bf3c12..574fa14ac8b2 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -469,7 +469,8 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot) } static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, - unsigned long address) + unsigned long address, + pte_t *ptep) { } diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index 2bbc0fcce04a..ff7f0ee179e5 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -121,7 +121,8 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, - unsigned long address) + unsigned long address, + pte_t *ptep) { /* * Book3S 64 does not require spurious fault flushes because the PTE diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2c70b4d1263d..c1f6b46ec555 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1239,7 +1239,8 @@ static inline int pte_allow_rdp(pte_t old, pte_t new) } static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, - unsigned long address) + unsigned long address, + pte_t *ptep) { /* * RDP might not have propagated the PTE protection reset to all CPUs, @@ -1247,11 +1248,12 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, * NOTE: This will also be called when a racing pagetable update on * another thread already installed the correct PTE. Both cases cannot * really be distinguished. - * Therefore, only do the local TLB flush when RDP can be used, to avoid - * unnecessary overhead. + * Therefore, only do the local TLB flush when RDP can be used, and the + * PTE does not have _PAGE_PROTECT set, to avoid unnecessary overhead. + * A local RDP can be used to do the flush. */ - if (MACHINE_HAS_RDP) - asm volatile("ptlb" : : : "memory"); + if (MACHINE_HAS_RDP && !(pte_val(*ptep) & _PAGE_PROTECT)) + __ptep_rdp(address, ptep, 0, 0, 1); } #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 7425f32e5293..15ae4d6ba476 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1097,7 +1097,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte); } -#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 9dc936bc77d1..c5a51481bbb9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -817,7 +817,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef flush_tlb_fix_spurious_fault -#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* diff --git a/mm/memory.c b/mm/memory.c index fdc903825981..6285cad1f4fb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4944,7 +4944,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) - flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); + flush_tlb_fix_spurious_fault(vmf->vma, vmf->address, + vmf->pte); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 90ab721a12a8..d2fc52bffafc 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -69,7 +69,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed) { set_pte_at(vma->vm_mm, address, ptep, entry); - flush_tlb_fix_spurious_fault(vma, address); + flush_tlb_fix_spurious_fault(vma, address, ptep); } return changed; } -- GitLab From dd63bd7df41a8f9393a2e3ff9157a441c08eb996 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Mon, 6 Mar 2023 11:09:07 -0500 Subject: [PATCH 1483/5631] selftests/mm: fix split huge page tests Fix two inputs to check_anon_huge() and one if condition, so the tests work as expected. Link: https://lkml.kernel.org/r/20230306160907.16804-1-zi.yan@sent.com Fixes: c07c343cda8e ("selftests/vm: dedup THP helpers") Signed-off-by: Zi Yan Reviewed-by: Zach O'Keefe Tested-by: Zach O'Keefe Acked-by: David Hildenbrand Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/split_huge_page_test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 76e1c36dd9e5..b8558c7f1a39 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -106,7 +106,7 @@ void split_pmd_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 1, pmd_pagesize)) { + if (!check_huge_anon(one_page, 4, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } @@ -122,7 +122,7 @@ void split_pmd_thp(void) } - if (check_huge_anon(one_page, 0, pmd_pagesize)) { + if (!check_huge_anon(one_page, 0, pmd_pagesize)) { printf("Still AnonHugePages not split\n"); exit(EXIT_FAILURE); } @@ -169,7 +169,7 @@ void split_pte_mapped_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 1, pmd_pagesize)) { + if (!check_huge_anon(one_page, 4, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } -- GitLab From eaf7b66b76f85ce340c50b76e482c6f91593b8b0 Mon Sep 17 00:00:00 2001 From: Yue Zhao Date: Mon, 6 Mar 2023 23:41:35 +0800 Subject: [PATCH 1484/5631] mm, memcg: Prevent memory.oom.group load/store tearing Patch series "mm, memcg: cgroup v1 and v2 tunable load/store tearing fixes", v2. This patch series helps to prevent load/store tearing in several cgroup knobs. As kindly pointed out by Michal Hocko and Roman Gushchin , the changelog has been rephrased. Besides, more knobs were checked, according to kind suggestions from Shakeel Butt and Muchun Song. This patch (of 4): The knob for cgroup v2 memory controller: memory.oom.group is not protected by any locking so it can be modified while it is used. This is not an actual problem because races are unlikely (the knob is usually configured long before any workloads hits actual memcg oom) but it is better to use READ_ONCE/WRITE_ONCE to prevent compiler from doing anything funky. The access of memcg->oom_group is lockless, so it can be concurrently set at the same time as we are trying to read it. Link: https://lkml.kernel.org/r/20230306154138.3775-1-findns94@gmail.com Link: https://lkml.kernel.org/r/20230306154138.3775-2-findns94@gmail.com Signed-off-by: Yue Zhao Acked-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Tang Yizhou Signed-off-by: Andrew Morton --- mm/memcontrol.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5abffe6f8389..06821e5f7604 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2067,7 +2067,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, * highest-level memory cgroup with oom.group set. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - if (memcg->oom_group) + if (READ_ONCE(memcg->oom_group)) oom_group = memcg; if (memcg == oom_domain) @@ -6623,7 +6623,7 @@ static int memory_oom_group_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); - seq_printf(m, "%d\n", memcg->oom_group); + seq_printf(m, "%d\n", READ_ONCE(memcg->oom_group)); return 0; } @@ -6645,7 +6645,7 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, if (oom_group != 0 && oom_group != 1) return -EINVAL; - memcg->oom_group = oom_group; + WRITE_ONCE(memcg->oom_group, oom_group); return nbytes; } -- GitLab From 82b3aa2681ca92421c4b508e7c390000273c53fe Mon Sep 17 00:00:00 2001 From: Yue Zhao Date: Mon, 6 Mar 2023 23:41:36 +0800 Subject: [PATCH 1485/5631] mm, memcg: Prevent memory.swappiness load/store tearing The knob for cgroup v1 memory controller: memory.swappiness is not protected by any locking so it can be modified while it is used. This is not an actual problem because races are unlikely. But it is better to use [READ|WRITE]_ONCE to prevent compiler from doing anything funky. The access of memcg->swappiness and vm_swappiness is lockless, so both of them can be concurrently set at the same time as we are trying to read them. All occurrences of memcg->swappiness and vm_swappiness are updated with [READ|WRITE]_ONCE. [findns94@gmail.com: v3] Link: https://lkml.kernel.org/r/20230308162555.14195-3-findns94@gmail.com Link: https://lkml.kernel.org/r/20230306154138.3775-3-findns94@gmail.com Signed-off-by: Yue Zhao Acked-by: Michal Hocko Acked-by: Shakeel Butt Acked-by: Roman Gushchin Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Tang Yizhou Signed-off-by: Andrew Morton --- include/linux/swap.h | 8 ++++---- mm/memcontrol.c | 6 +++--- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index d5d0b54e90e8..bfc3b06b5f8f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -620,18 +620,18 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); - return memcg->swappiness; + return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { - return vm_swappiness; + return READ_ONCE(vm_swappiness); } #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 06821e5f7604..1b0112afcad3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4179,9 +4179,9 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css, return -EINVAL; if (!mem_cgroup_is_root(memcg)) - memcg->swappiness = val; + WRITE_ONCE(memcg->swappiness, val); else - vm_swappiness = val; + WRITE_ONCE(vm_swappiness, val); return 0; } @@ -5353,7 +5353,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) #endif page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { - memcg->swappiness = mem_cgroup_swappiness(parent); + WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent)); memcg->oom_kill_disable = parent->oom_kill_disable; page_counter_init(&memcg->memory, &parent->memory); -- GitLab From 17c56de6a8c9970f56375c13f8654bbcbc94c090 Mon Sep 17 00:00:00 2001 From: Yue Zhao Date: Mon, 6 Mar 2023 23:41:37 +0800 Subject: [PATCH 1486/5631] mm, memcg: Prevent memory.oom_control load/store tearing The knob for cgroup v1 memory controller: memory.oom_control is not protected by any locking so it can be modified while it is used. This is not an actual problem because races are unlikely. But it is better to use [READ|WRITE]_ONCE to prevent compiler from doing anything funky. The access of memcg->oom_kill_disable is lockless, so it can be concurrently set at the same time as we are trying to read it. All occurrences of memcg->oom_kill_disable are updated with [READ|WRITE]_ONCE. [findns94@gmail.com: v3] Link: https://lkml.kernel.org/r/20230308162555.14195-4-findns94@gmail.com Link: https://lkml.kernel.org/r/20230306154138.377-4-findns94@gmail.com Signed-off-by: Yue Zhao Acked-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Tang Yizhou Signed-off-by: Andrew Morton --- mm/memcontrol.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1b0112afcad3..5b7062d0f5e0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1929,7 +1929,7 @@ static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) * Please note that mem_cgroup_out_of_memory might fail to find a * victim and then we have to bail out from the charge path. */ - if (memcg->oom_kill_disable) { + if (READ_ONCE(memcg->oom_kill_disable)) { if (current->in_user_fault) { css_get(&memcg->css); current->memcg_in_oom = memcg; @@ -1999,7 +1999,7 @@ bool mem_cgroup_oom_synchronize(bool handle) if (locked) mem_cgroup_oom_notify(memcg); - if (locked && !memcg->oom_kill_disable) { + if (locked && !READ_ONCE(memcg->oom_kill_disable)) { mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask, @@ -4515,7 +4515,7 @@ static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(sf); - seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); + seq_printf(sf, "oom_kill_disable %d\n", READ_ONCE(memcg->oom_kill_disable)); seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); seq_printf(sf, "oom_kill %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_OOM_KILL])); @@ -4531,7 +4531,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, if (mem_cgroup_is_root(memcg) || !((val == 0) || (val == 1))) return -EINVAL; - memcg->oom_kill_disable = val; + WRITE_ONCE(memcg->oom_kill_disable, val); if (!val) memcg_oom_recover(memcg); @@ -5354,7 +5354,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent)); - memcg->oom_kill_disable = parent->oom_kill_disable; + WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); page_counter_init(&memcg->memory, &parent->memory); page_counter_init(&memcg->swap, &parent->swap); -- GitLab From 2178e20c24406548c97b18a2d9781d16c35b8881 Mon Sep 17 00:00:00 2001 From: Yue Zhao Date: Mon, 6 Mar 2023 23:41:38 +0800 Subject: [PATCH 1487/5631] mm, memcg: Prevent memory.soft_limit_in_bytes load/store tearing The knob for cgroup v1 memory controller: memory.soft_limit_in_bytes is not protected by any locking so it can be modified while it is used. This is not an actual problem because races are unlikely. But it is better to use [READ|WRITE]_ONCE to prevent compiler from doing anything funky. The access of memcg->soft_limit is lockless, so it can be concurrently set at the same time as we are trying to read it. All occurrences of memcg->soft_limit are updated with [READ|WRITE]_ONCE. [findns94@gmail.com: v3] Link: https://lkml.kernel.org/r/20230308162555.14195-5-findns94@gmail.com Link: https://lkml.kernel.org/r/20230306154138.3775-5-findns94@gmail.com Signed-off-by: Yue Zhao Acked-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Tang Yizhou Signed-off-by: Andrew Morton --- mm/memcontrol.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5b7062d0f5e0..13ec89c45389 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3728,7 +3728,7 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, case RES_FAILCNT: return counter->failcnt; case RES_SOFT_LIMIT: - return (u64)memcg->soft_limit * PAGE_SIZE; + return (u64)READ_ONCE(memcg->soft_limit) * PAGE_SIZE; default: BUG(); } @@ -3870,7 +3870,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, if (IS_ENABLED(CONFIG_PREEMPT_RT)) { ret = -EOPNOTSUPP; } else { - memcg->soft_limit = nr_pages; + WRITE_ONCE(memcg->soft_limit, nr_pages); ret = 0; } break; @@ -5347,7 +5347,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return ERR_CAST(memcg); page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); - memcg->soft_limit = PAGE_COUNTER_MAX; + WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX); #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) memcg->zswap_max = PAGE_COUNTER_MAX; #endif @@ -5502,7 +5502,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) page_counter_set_min(&memcg->memory, 0); page_counter_set_low(&memcg->memory, 0); page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); - memcg->soft_limit = PAGE_COUNTER_MAX; + WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX); page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); memcg_wb_domain_size_changed(memcg); } -- GitLab From 8e00b2dffd822b34d8d1c627dc19f0743f9f5ac6 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 6 Mar 2023 12:13:21 +0100 Subject: [PATCH 1488/5631] lib/stackdepot: kmsan: mark API outputs as initialized KMSAN does not instrument stackdepot and may treat memory allocated by it as uninitialized. This is not a problem for KMSAN itself, because its functions calling stackdepot API are also not instrumented. But other kernel features (e.g. netdev tracker) may access stack depot from instrumented code, which will lead to false positives, unless we explicitly mark stackdepot outputs as initialized. Link: https://lkml.kernel.org/r/20230306111322.205724-1-glider@google.com Signed-off-by: Alexander Potapenko Reported-by: syzbot Reviewed-by: Dmitry Vyukov Suggested-by: Dmitry Vyukov Reviewed-by: Andrey Konovalov Cc: Marco Elver Signed-off-by: Andrew Morton --- lib/stackdepot.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 036da8e295d1..2f5aa851834e 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -306,6 +307,11 @@ depot_alloc_stack(unsigned long *entries, int size, u32 hash, void **prealloc) stack->handle.extra = 0; memcpy(stack->entries, entries, flex_array_size(stack, entries, size)); pool_offset += required_size; + /* + * Let KMSAN know the stored stack record is initialized. This shall + * prevent false positive reports if instrumented code accesses it. + */ + kmsan_unpoison_memory(stack, required_size); return stack; } @@ -465,6 +471,12 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, struct stack_record *stack; *entries = NULL; + /* + * Let KMSAN know *entries is initialized. This shall prevent false + * positive reports if instrumented code accesses it. + */ + kmsan_unpoison_memory(entries, sizeof(*entries)); + if (!handle) return 0; -- GitLab From 6204c9ab4a5a05a72e04c12276fffdd6c6636489 Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Mon, 6 Mar 2023 12:13:22 +0100 Subject: [PATCH 1489/5631] kmsan: add test_stackdepot_roundtrip Ensure that KMSAN does not report false positives in instrumented callers of stack_depot_save(), stack_depot_print(), and stack_depot_fetch(). Link: https://lkml.kernel.org/r/20230306111322.205724-2-glider@google.com Signed-off-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Marco Elver Cc: syzbot Signed-off-by: Andrew Morton --- mm/kmsan/kmsan_test.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index 7095d3fbb23a..d9eb141c27aa 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -551,6 +551,36 @@ static void test_long_origin_chain(struct kunit *test) KUNIT_EXPECT_TRUE(test, report_matches(&expect)); } +/* + * Test case: ensure that saving/restoring/printing stacks to/from stackdepot + * does not trigger errors. + * + * KMSAN uses stackdepot to store origin stack traces, that's why we do not + * instrument lib/stackdepot.c. Yet it must properly mark its outputs as + * initialized because other kernel features (e.g. netdev tracker) may also + * access stackdepot from instrumented code. + */ +static void test_stackdepot_roundtrip(struct kunit *test) +{ + unsigned long src_entries[16], *dst_entries; + unsigned int src_nentries, dst_nentries; + EXPECTATION_NO_REPORT(expect); + depot_stack_handle_t handle; + + kunit_info(test, "testing stackdepot roundtrip (no reports)\n"); + + src_nentries = + stack_trace_save(src_entries, ARRAY_SIZE(src_entries), 1); + handle = stack_depot_save(src_entries, src_nentries, GFP_KERNEL); + stack_depot_print(handle); + dst_nentries = stack_depot_fetch(handle, &dst_entries); + KUNIT_EXPECT_TRUE(test, src_nentries == dst_nentries); + + kmsan_check_memory((void *)dst_entries, + sizeof(*dst_entries) * dst_nentries); + KUNIT_EXPECT_TRUE(test, report_matches(&expect)); +} + static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_uninit_kmalloc), KUNIT_CASE(test_init_kmalloc), @@ -573,6 +603,7 @@ static struct kunit_case kmsan_test_cases[] = { KUNIT_CASE(test_memset32), KUNIT_CASE(test_memset64), KUNIT_CASE(test_long_origin_chain), + KUNIT_CASE(test_stackdepot_roundtrip), {}, }; -- GitLab From 8b8d9a2d328164083b84e5b2515fa4d040bcdcdd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:31:23 +0100 Subject: [PATCH 1490/5631] ufs: don't flush page immediately for DIRSYNC directories Patch series "remove most callers of write_one_page", v4. This series removes most users of the write_one_page API. These helpers internally call ->writepage which we are gradually removing from the kernel. This patch (of 3): We do not need to writeout modified directory blocks immediately when modifying them while the page is locked. It is enough to do the flush somewhat later which has the added benefit that inode times can be flushed as well. It also allows us to stop depending on write_one_page() function. Ported from an ext2 patch by Jan Kara. Link: https://lkml.kernel.org/r/20230307143125.27778-1-hch@lst.de Link: https://lkml.kernel.org/r/20230307143125.27778-2-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Dave Kleikamp Cc: Evgeniy Dushistov Cc: Jan Kara via Ocfs2-devel Cc: Joel Becker Cc: Matthew Wilcox (Oracle) Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Jan Kara Cc: Joseph Qi Signed-off-by: Andrew Morton --- fs/ufs/dir.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 391efaf1d528..379d75796a5c 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -42,11 +42,10 @@ static inline int ufs_match(struct super_block *sb, int len, return !memcmp(name, de->d_name, len); } -static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) +static void ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) { struct address_space *mapping = page->mapping; struct inode *dir = mapping->host; - int err = 0; inode_inc_iversion(dir); block_write_end(NULL, mapping, pos, len, len, page, NULL); @@ -54,10 +53,16 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) i_size_write(dir, pos+len); mark_inode_dirty(dir); } - if (IS_DIRSYNC(dir)) - err = write_one_page(page); - else - unlock_page(page); + unlock_page(page); +} + +static int ufs_handle_dirsync(struct inode *dir) +{ + int err; + + err = filemap_write_and_wait(dir->i_mapping); + if (!err) + err = sync_inode_metadata(dir, 1); return err; } @@ -99,11 +104,12 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, de->d_ino = cpu_to_fs32(dir->i_sb, inode->i_ino); ufs_set_de_type(dir->i_sb, de, inode->i_mode); - err = ufs_commit_chunk(page, pos, len); + ufs_commit_chunk(page, pos, len); ufs_put_page(page); if (update_times) dir->i_mtime = dir->i_ctime = current_time(dir); mark_inode_dirty(dir); + ufs_handle_dirsync(dir); } @@ -390,10 +396,11 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode) de->d_ino = cpu_to_fs32(sb, inode->i_ino); ufs_set_de_type(sb, de, inode->i_mode); - err = ufs_commit_chunk(page, pos, rec_len); + ufs_commit_chunk(page, pos, rec_len); dir->i_mtime = dir->i_ctime = current_time(dir); mark_inode_dirty(dir); + err = ufs_handle_dirsync(dir); /* OFFSET_CACHE */ out_put: ufs_put_page(page); @@ -531,9 +538,10 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir, if (pde) pde->d_reclen = cpu_to_fs16(sb, to - from); dir->d_ino = 0; - err = ufs_commit_chunk(page, pos, to - from); + ufs_commit_chunk(page, pos, to - from); inode->i_ctime = inode->i_mtime = current_time(inode); mark_inode_dirty(inode); + err = ufs_handle_dirsync(inode); out: ufs_put_page(page); UFSD("EXIT\n"); @@ -579,7 +587,8 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) strcpy (de->d_name, ".."); kunmap(page); - err = ufs_commit_chunk(page, 0, chunk_size); + ufs_commit_chunk(page, 0, chunk_size); + err = ufs_handle_dirsync(inode); fail: put_page(page); return err; -- GitLab From a0d50b11bff644a6e4339874ba48f4bc02b842bc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:31:24 +0100 Subject: [PATCH 1491/5631] ocfs2: don't use write_one_page in ocfs2_duplicate_clusters_by_page Use filemap_write_and_wait_range to write back the range of the dirty page instead of write_one_page in preparation of removing write_one_page and eventually ->writepage. Link: https://lkml.kernel.org/r/20230307143125.27778-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Reviewed-by: Joseph Qi Cc: Changwei Ge Cc: Dave Kleikamp Cc: Evgeniy Dushistov Cc: Gang He Cc: Jan Kara via Ocfs2-devel Cc: Joel Becker Cc: Joseph Qi Cc: Jun Piao Cc: Junxiao Bi Cc: Mark Fasheh Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/ocfs2/refcounttree.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 5a656dc683f1..564ab48d03ef 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2952,10 +2952,11 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle, */ if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { if (PageDirty(page)) { - /* - * write_on_page will unlock the page on return - */ - ret = write_one_page(page); + unlock_page(page); + put_page(page); + + ret = filemap_write_and_wait_range(mapping, + offset, map_end - 1); goto retry; } } -- GitLab From 452a8f40728065800b5a5b81f1152e9a16d39656 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:31:25 +0100 Subject: [PATCH 1492/5631] mm,jfs: move write_one_page/folio_write_one to jfs The last remaining user of folio_write_one through the write_one_page wrapper is jfs, so move the functionality there and hard code the call to metapage_writepage. Note that the use of the pagecache by the JFS 'metapage' buffer cache is a bit odd, and we could probably do without VM-level dirty tracking at all, but that's a change for another time. Link: https://lkml.kernel.org/r/20230307143125.27778-4-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Dave Kleikamp Cc: Changwei Ge Cc: Evgeniy Dushistov Cc: Gang He Cc: Jan Kara Cc: Jan Kara via Ocfs2-devel Cc: Joel Becker Cc: Joseph Qi Cc: Joseph Qi Cc: Jun Piao Cc: Junxiao Bi Cc: Mark Fasheh Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- fs/jfs/jfs_metapage.c | 39 ++++++++++++++++++++++++++++++++++----- include/linux/pagemap.h | 6 ------ mm/page-writeback.c | 40 ---------------------------------------- 3 files changed, 34 insertions(+), 51 deletions(-) diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 2e8461ce74de..961569c11159 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -691,6 +691,35 @@ void grab_metapage(struct metapage * mp) unlock_page(mp->page); } +static int metapage_write_one(struct page *page) +{ + struct folio *folio = page_folio(page); + struct address_space *mapping = folio->mapping; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = folio_nr_pages(folio), + }; + int ret = 0; + + BUG_ON(!folio_test_locked(folio)); + + folio_wait_writeback(folio); + + if (folio_clear_dirty_for_io(folio)) { + folio_get(folio); + ret = metapage_writepage(page, &wbc); + if (ret == 0) + folio_wait_writeback(folio); + folio_put(folio); + } else { + folio_unlock(folio); + } + + if (!ret) + ret = filemap_check_errors(mapping); + return ret; +} + void force_metapage(struct metapage *mp) { struct page *page = mp->page; @@ -700,8 +729,8 @@ void force_metapage(struct metapage *mp) get_page(page); lock_page(page); set_page_dirty(page); - if (write_one_page(page)) - jfs_error(mp->sb, "write_one_page() failed\n"); + if (metapage_write_one(page)) + jfs_error(mp->sb, "metapage_write_one() failed\n"); clear_bit(META_forcewrite, &mp->flag); put_page(page); } @@ -746,9 +775,9 @@ void release_metapage(struct metapage * mp) set_page_dirty(page); if (test_bit(META_sync, &mp->flag)) { clear_bit(META_sync, &mp->flag); - if (write_one_page(page)) - jfs_error(mp->sb, "write_one_page() failed\n"); - lock_page(page); /* write_one_page unlocks the page */ + if (metapage_write_one(page)) + jfs_error(mp->sb, "metapage_write_one() failed\n"); + lock_page(page); } } else if (mp->lsn) /* discard_metapage doesn't remove it */ remove_from_logsync(mp); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0acb8e1fb7af..853184a46411 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1066,12 +1066,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __must_check folio_write_one(struct folio *folio); -static inline int __must_check write_one_page(struct page *page) -{ - return folio_write_one(page_folio(page)); -} - int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 516b1aa247e8..db7943999007 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2583,46 +2583,6 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) return ret; } -/** - * folio_write_one - write out a single folio and wait on I/O. - * @folio: The folio to write. - * - * The folio must be locked by the caller and will be unlocked upon return. - * - * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this - * function returns. - * - * Return: %0 on success, negative error code otherwise - */ -int folio_write_one(struct folio *folio) -{ - struct address_space *mapping = folio->mapping; - int ret = 0; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = folio_nr_pages(folio), - }; - - BUG_ON(!folio_test_locked(folio)); - - folio_wait_writeback(folio); - - if (folio_clear_dirty_for_io(folio)) { - folio_get(folio); - ret = mapping->a_ops->writepage(&folio->page, &wbc); - if (ret == 0) - folio_wait_writeback(folio); - folio_put(folio); - } else { - folio_unlock(folio); - } - - if (!ret) - ret = filemap_check_errors(mapping); - return ret; -} -EXPORT_SYMBOL(folio_write_one); - /* * For address_spaces which do not use buffers nor write back. */ -- GitLab From 5c63a7c32a94a7e2fecdd6754a6ff47cd4226ee1 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Thu, 2 Mar 2023 02:10:35 +0100 Subject: [PATCH 1493/5631] maple_tree: export symbol mas_preallocate() Fix missing EXPORT_SYMBOL_GPL() statement for mas_preallocate(). It isn't actually used by anything yet, but mas_preallocate() is part of the maple tree's 'Advanced API'. All other functions of this API are exported already. Link: https://lkml.kernel.org/r/20230302011035.4928-1-dakr@redhat.com Signed-off-by: Danilo Krummrich Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- lib/maple_tree.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 9e2735cbc2b4..ae37a167e25d 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5726,6 +5726,7 @@ int mas_preallocate(struct ma_state *mas, gfp_t gfp) mas_reset(mas); return ret; } +EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. -- GitLab From 5da1a8687a9685d60a92abf4f6b735579ebe6b40 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Thu, 9 Mar 2023 18:48:13 +0800 Subject: [PATCH 1494/5631] mm/gup.c: fix typo in comments Link: https://lkml.kernel.org/r/20230309104813.170309-1-jingyuwang_vip@163.com Signed-off-by: Jingyu Wang Signed-off-by: Andrew Morton --- mm/gup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/gup.c b/mm/gup.c index eab18ba045db..1f72a717232b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2193,7 +2193,7 @@ static bool is_valid_gup_args(struct page **pages, struct vm_area_struct **vmas, * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated - * and subsequently re faulted). However it does guarantee that the page + * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because -- GitLab From 1f514bee0c086e70fb8137c15dc91c9711a3feeb Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:40 -0800 Subject: [PATCH 1495/5631] shmem: remove check for folio lock on writepage() Patch series "tmpfs: add the option to disable swap", v2. I'm doing this work as part of future experimentation with tmpfs and the page cache, but given a common complaint found about tmpfs is the innability to work without the page cache I figured this might be useful to others. It turns out it is -- at least Christian Brauner indicates systemd uses ramfs for a few use-cases because they don't want to use swap and so having this option would let them move over to using tmpfs for those small use cases, see systemd-creds(1). To see if you hit swap: mkswap /dev/nvme2n1 swapon /dev/nvme2n1 free -h With swap - what we see today ============================= mount -t tmpfs -o size=5G tmpfs /data-tmpfs/ dd if=/dev/urandom of=/data-tmpfs/5g-rand2 bs=1G count=5 free -h total used free shared buff/cache available Mem: 3.7Gi 2.6Gi 1.2Gi 2.2Gi 2.2Gi 1.2Gi Swap: 99Gi 2.8Gi 97Gi Without swap ============= free -h total used free shared buff/cache available Mem: 3.7Gi 387Mi 3.4Gi 2.1Mi 57Mi 3.3Gi Swap: 99Gi 0B 99Gi mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/ dd if=/dev/urandom of=/data-tmpfs/5g-rand2 bs=1G count=5 free -h total used free shared buff/cache available Mem: 3.7Gi 2.6Gi 1.2Gi 2.3Gi 2.3Gi 1.1Gi Swap: 99Gi 21Mi 99Gi The mix and match remount testing ================================= # Cannot disable swap after it was first enabled: mount -t tmpfs -o size=5G tmpfs /data-tmpfs/ mount -t tmpfs -o remount -o size=5G -o noswap tmpfs /data-tmpfs/ mount: /data-tmpfs: mount point not mounted or bad option. dmesg(1) may have more information after failed mount system call. dmesg -c tmpfs: Cannot disable swap on remount # Remount with the same noswap option is OK: mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/ mount -t tmpfs -o remount -o size=5G -o noswap tmpfs /data-tmpfs/ dmesg -c # Trying to enable swap with a remount after it first disabled: mount -t tmpfs -o size=5G -o noswap tmpfs /data-tmpfs/ mount -t tmpfs -o remount -o size=5G tmpfs /data-tmpfs/ mount: /data-tmpfs: mount point not mounted or bad option. dmesg(1) may have more information after failed mount system call. dmesg -c tmpfs: Cannot enable swap on remount if it was disabled on first mount This patch (of 6): Matthew notes we should not need to check the folio lock on the writepage() callback so remove it. This sanity check has been lingering since linux-history days. We remove this as we tidy up the writepage() callback to make things a bit clearer. Link: https://lkml.kernel.org/r/20230309230545.2930737-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20230309230545.2930737-2-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Suggested-by: Matthew Wilcox Acked-by: David Hildenbrand Reviewed-by: Christian Brauner Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/shmem.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/shmem.c b/mm/shmem.c index 448f393d8ab2..6d44b2ed4afb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1351,7 +1351,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) folio_clear_dirty(folio); } - BUG_ON(!folio_test_locked(folio)); mapping = folio->mapping; index = folio->index; inode = mapping->host; -- GitLab From 8ccee8c19c605a7d74f02413c59d4d3a822827d5 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:41 -0800 Subject: [PATCH 1496/5631] shmem: set shmem_writepage() variables early shmem_writepage() sets up variables typically used *after* a possible huge page split. However even if that does happen the address space mapping should not change, and the inode does not change either. So it should be safe to set that from the very beginning. This commit makes no functional changes. Link: https://lkml.kernel.org/r/20230309230545.2930737-3-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Acked-by: David Hildenbrand Reviewed-by: Christian Brauner Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/shmem.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 6d44b2ed4afb..6431c8e85661 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1331,9 +1331,9 @@ int shmem_unuse(unsigned int type) static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct folio *folio = page_folio(page); - struct shmem_inode_info *info; - struct address_space *mapping; - struct inode *inode; + struct address_space *mapping = folio->mapping; + struct inode *inode = mapping->host; + struct shmem_inode_info *info = SHMEM_I(inode); swp_entry_t swap; pgoff_t index; @@ -1351,10 +1351,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) folio_clear_dirty(folio); } - mapping = folio->mapping; index = folio->index; - inode = mapping->host; - info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; if (!total_swap_pages) -- GitLab From cf7992bf6105b93d1b275001e043d8c8643015e3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:42 -0800 Subject: [PATCH 1497/5631] shmem: move reclaim check early on writepages() i915_gem requires huge folios to be split when swapping. However we have check for usage of writepages() to ensure it used only for swap purposes later. Avoid the splits if we're not being called for reclaim, even if they should in theory not happen. This makes the conditions easier to follow on shem_writepage(). Link: https://lkml.kernel.org/r/20230309230545.2930737-4-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Acked-by: David Hildenbrand Reviewed-by: Yosry Ahmed Reviewed-by: Christian Brauner Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Signed-off-by: Andrew Morton --- mm/shmem.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 6431c8e85661..b297eaf43f43 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1337,6 +1337,16 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) swp_entry_t swap; pgoff_t index; + /* + * Our capabilities prevent regular writeback or sync from ever calling + * shmem_writepage; but a stacking filesystem might use ->writepage of + * its underlying filesystem, in which case tmpfs should write out to + * swap only in response to memory pressure, and not for the writeback + * threads or sync. + */ + if (WARN_ON_ONCE(!wbc->for_reclaim)) + goto redirty; + /* * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages, @@ -1357,18 +1367,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (!total_swap_pages) goto redirty; - /* - * Our capabilities prevent regular writeback or sync from ever calling - * shmem_writepage; but a stacking filesystem might use ->writepage of - * its underlying filesystem, in which case tmpfs should write out to - * swap only in response to memory pressure, and not for the writeback - * threads or sync. - */ - if (!wbc->for_reclaim) { - WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ - goto redirty; - } - /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a -- GitLab From 9a976f0c847b67d22ed694556a3626ed92da0422 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:43 -0800 Subject: [PATCH 1498/5631] shmem: skip page split if we're not reclaiming In theory when info->flags & VM_LOCKED we should not be getting shem_writepage() called so we should be verifying this with a WARN_ON_ONCE(). Since we should not be swapping then best to ensure we also don't do the folio split earlier too. So just move the check early to avoid folio splits in case its a dubious call. We also have a similar early bail when !total_swap_pages so just move that earlier to avoid the possible folio split in the same situation. Link: https://lkml.kernel.org/r/20230309230545.2930737-5-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Acked-by: David Hildenbrand Reviewed-by: Christian Brauner Reviewed-by: Yosry Ahmed Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Signed-off-by: Andrew Morton --- mm/shmem.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index b297eaf43f43..7751c136eadb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1347,6 +1347,12 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (WARN_ON_ONCE(!wbc->for_reclaim)) goto redirty; + if (WARN_ON_ONCE(info->flags & VM_LOCKED)) + goto redirty; + + if (!total_swap_pages) + goto redirty; + /* * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages, @@ -1362,10 +1368,6 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } index = folio->index; - if (info->flags & VM_LOCKED) - goto redirty; - if (!total_swap_pages) - goto redirty; /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC -- GitLab From d0f5a85442d1a0552eae681b2e8cdc86ac08aba2 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:44 -0800 Subject: [PATCH 1499/5631] shmem: update documentation Update the docs to reflect a bit better why some folks prefer tmpfs over ramfs and clarify a bit more about the difference between brd ramdisks. While at it, add THP docs for tmpfs, both the mount options and the sysfs file. Link: https://lkml.kernel.org/r/20230309230545.2930737-6-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Reviewed-by: Christian Brauner Reviewed-by: David Hildenbrand Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- Documentation/filesystems/tmpfs.rst | 57 +++++++++++++++++++++++++---- 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/Documentation/filesystems/tmpfs.rst b/Documentation/filesystems/tmpfs.rst index 0408c245785e..1ec9a9f8196b 100644 --- a/Documentation/filesystems/tmpfs.rst +++ b/Documentation/filesystems/tmpfs.rst @@ -13,14 +13,25 @@ everything stored therein is lost. tmpfs puts everything into the kernel internal caches and grows and shrinks to accommodate the files it contains and is able to swap -unneeded pages out to swap space. It has maximum size limits which can -be adjusted on the fly via 'mount -o remount ...' - -If you compare it to ramfs (which was the template to create tmpfs) -you gain swapping and limit checking. Another similar thing is the RAM -disk (/dev/ram*), which simulates a fixed size hard disk in physical -RAM, where you have to create an ordinary filesystem on top. Ramdisks -cannot swap and you do not have the possibility to resize them. +unneeded pages out to swap space, and supports THP. + +tmpfs extends ramfs with a few userspace configurable options listed and +explained further below, some of which can be reconfigured dynamically on the +fly using a remount ('mount -o remount ...') of the filesystem. A tmpfs +filesystem can be resized but it cannot be resized to a size below its current +usage. tmpfs also supports POSIX ACLs, and extended attributes for the +trusted.* and security.* namespaces. ramfs does not use swap and you cannot +modify any parameter for a ramfs filesystem. The size limit of a ramfs +filesystem is how much memory you have available, and so care must be taken if +used so to not run out of memory. + +An alternative to tmpfs and ramfs is to use brd to create RAM disks +(/dev/ram*), which allows you to simulate a block device disk in physical RAM. +To write data you would just then need to create an regular filesystem on top +this ramdisk. As with ramfs, brd ramdisks cannot swap. brd ramdisks are also +configured in size at initialization and you cannot dynamically resize them. +Contrary to brd ramdisks, tmpfs has its own filesystem, it does not rely on the +block layer at all. Since tmpfs lives completely in the page cache and on swap, all tmpfs pages will be shown as "Shmem" in /proc/meminfo and "Shared" in @@ -85,6 +96,36 @@ mount with such options, since it allows any user with write access to use up all the memory on the machine; but enhances the scalability of that instance in a system with many CPUs making intensive use of it. +tmpfs also supports Transparent Huge Pages which requires a kernel +configured with CONFIG_TRANSPARENT_HUGEPAGE and with huge supported for +your system (has_transparent_hugepage(), which is architecture specific). +The mount options for this are: + +====== ============================================================ +huge=0 never: disables huge pages for the mount +huge=1 always: enables huge pages for the mount +huge=2 within_size: only allocate huge pages if the page will be + fully within i_size, also respect fadvise()/madvise() hints. +huge=3 advise: only allocate huge pages if requested with + fadvise()/madvise() +====== ============================================================ + +There is a sysfs file which you can also use to control system wide THP +configuration for all tmpfs mounts, the file is: + +/sys/kernel/mm/transparent_hugepage/shmem_enabled + +This sysfs file is placed on top of THP sysfs directory and so is registered +by THP code. It is however only used to control all tmpfs mounts with one +single knob. Since it controls all tmpfs mounts it should only be used either +for emergency or testing purposes. The values you can set for shmem_enabled are: + +== ============================================================ +-1 deny: disables huge on shm_mnt and all mounts, for + emergency use +-2 force: enables huge on shm_mnt and all mounts, w/o needing + option, for testing +== ============================================================ tmpfs has a mount option to set the NUMA memory allocation policy for all files in that instance (if CONFIG_NUMA is enabled) - which can be -- GitLab From 2c6efe9cf2d7841b75fe38ed1adbd41a90f51ba0 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 9 Mar 2023 15:05:45 -0800 Subject: [PATCH 1500/5631] shmem: add support to ignore swap In doing experimentations with shmem having the option to avoid swap becomes a useful mechanism. One of the *raves* about brd over shmem is you can avoid swap, but that's not really a good reason to use brd if we can instead use shmem. Using brd has its own good reasons to exist, but just because "tmpfs" doesn't let you do that is not a great reason to avoid it if we can easily add support for it. I don't add support for reconfiguring incompatible options, but if we really wanted to we can add support for that. To avoid swap we use mapping_set_unevictable() upon inode creation, and put a WARN_ON_ONCE() stop-gap on writepages() for reclaim. Link: https://lkml.kernel.org/r/20230309230545.2930737-7-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Acked-by: Christian Brauner Tested-by: Xin Hao Reviewed-by: Davidlohr Bueso Cc: Adam Manzanares Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Hugh Dickins Cc: Kees Cook Cc: Matthew Wilcox Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- Documentation/filesystems/tmpfs.rst | 9 ++++++--- Documentation/mm/unevictable-lru.rst | 2 ++ include/linux/shmem_fs.h | 1 + mm/shmem.c | 28 +++++++++++++++++++++++++++- 4 files changed, 36 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/tmpfs.rst b/Documentation/filesystems/tmpfs.rst index 1ec9a9f8196b..f18f46be5c0c 100644 --- a/Documentation/filesystems/tmpfs.rst +++ b/Documentation/filesystems/tmpfs.rst @@ -13,7 +13,8 @@ everything stored therein is lost. tmpfs puts everything into the kernel internal caches and grows and shrinks to accommodate the files it contains and is able to swap -unneeded pages out to swap space, and supports THP. +unneeded pages out to swap space, if swap was enabled for the tmpfs +mount. tmpfs also supports THP. tmpfs extends ramfs with a few userspace configurable options listed and explained further below, some of which can be reconfigured dynamically on the @@ -33,8 +34,8 @@ configured in size at initialization and you cannot dynamically resize them. Contrary to brd ramdisks, tmpfs has its own filesystem, it does not rely on the block layer at all. -Since tmpfs lives completely in the page cache and on swap, all tmpfs -pages will be shown as "Shmem" in /proc/meminfo and "Shared" in +Since tmpfs lives completely in the page cache and optionally on swap, +all tmpfs pages will be shown as "Shmem" in /proc/meminfo and "Shared" in free(1). Notice that these counters also include shared memory (shmem, see ipcs(1)). The most reliable way to get the count is using df(1) and du(1). @@ -83,6 +84,8 @@ nr_inodes The maximum number of inodes for this instance. The default is half of the number of your physical RAM pages, or (on a machine with highmem) the number of lowmem RAM pages, whichever is the lower. +noswap Disables swap. Remounts must respect the original settings. + By default swap is enabled. ========= ============================================================ These parameters accept a suffix k, m or g for kilo, mega and giga and diff --git a/Documentation/mm/unevictable-lru.rst b/Documentation/mm/unevictable-lru.rst index 92ac5dca420c..d5ac8511eb67 100644 --- a/Documentation/mm/unevictable-lru.rst +++ b/Documentation/mm/unevictable-lru.rst @@ -42,6 +42,8 @@ The unevictable list addresses the following classes of unevictable pages: * Those owned by ramfs. + * Those owned by tmpfs with the noswap mount option. + * Those mapped into SHM_LOCK'd shared memory regions. * Those mapped into VM_LOCKED [mlock()ed] VMAs. diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 103d1000a5a2..50bf82b36995 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -45,6 +45,7 @@ struct shmem_sb_info { kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ + bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ diff --git a/mm/shmem.c b/mm/shmem.c index 7751c136eadb..787e83791eb5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -116,10 +116,12 @@ struct shmem_options { bool full_inums; int huge; int seen; + bool noswap; #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 +#define SHMEM_SEEN_NOSWAP 16 }; #ifdef CONFIG_TMPFS @@ -1334,6 +1336,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); swp_entry_t swap; pgoff_t index; @@ -1347,7 +1350,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (WARN_ON_ONCE(!wbc->for_reclaim)) goto redirty; - if (WARN_ON_ONCE(info->flags & VM_LOCKED)) + if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap)) goto redirty; if (!total_swap_pages) @@ -2372,6 +2375,8 @@ static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block shmem_set_inode_flags(inode, info->fsflags); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); + if (sbinfo->noswap) + mapping_set_unevictable(inode->i_mapping); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); mapping_set_large_folios(inode->i_mapping); @@ -3459,6 +3464,7 @@ enum shmem_param { Opt_uid, Opt_inode32, Opt_inode64, + Opt_noswap, }; static const struct constant_table shmem_param_enums_huge[] = { @@ -3480,6 +3486,7 @@ const struct fs_parameter_spec shmem_fs_parameters[] = { fsparam_u32 ("uid", Opt_uid), fsparam_flag ("inode32", Opt_inode32), fsparam_flag ("inode64", Opt_inode64), + fsparam_flag ("noswap", Opt_noswap), {} }; @@ -3563,6 +3570,10 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) ctx->full_inums = true; ctx->seen |= SHMEM_SEEN_INUMS; break; + case Opt_noswap: + ctx->noswap = true; + ctx->seen |= SHMEM_SEEN_NOSWAP; + break; } return 0; @@ -3661,6 +3672,14 @@ static int shmem_reconfigure(struct fs_context *fc) err = "Current inum too high to switch to 32-bit inums"; goto out; } + if ((ctx->seen & SHMEM_SEEN_NOSWAP) && ctx->noswap && !sbinfo->noswap) { + err = "Cannot disable swap on remount"; + goto out; + } + if (!(ctx->seen & SHMEM_SEEN_NOSWAP) && !ctx->noswap && sbinfo->noswap) { + err = "Cannot enable swap on remount if it was disabled on first mount"; + goto out; + } if (ctx->seen & SHMEM_SEEN_HUGE) sbinfo->huge = ctx->huge; @@ -3681,6 +3700,10 @@ static int shmem_reconfigure(struct fs_context *fc) sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } + + if (ctx->noswap) + sbinfo->noswap = true; + raw_spin_unlock(&sbinfo->stat_lock); mpol_put(mpol); return 0; @@ -3735,6 +3758,8 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); #endif shmem_show_mpol(seq, sbinfo->mpol); + if (sbinfo->noswap) + seq_printf(seq, ",noswap"); return 0; } @@ -3778,6 +3803,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) ctx->inodes = shmem_default_max_inodes(); if (!(ctx->seen & SHMEM_SEEN_INUMS)) ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64); + sbinfo->noswap = ctx->noswap; } else { sb->s_flags |= SB_NOUSER; } -- GitLab From 7eb16f23b9a415f062db22739e59bb144e0b24ab Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 10 Mar 2023 17:29:05 +0100 Subject: [PATCH 1501/5631] io-mapping: don't disable preempt on RT in io_mapping_map_atomic_wc(). io_mapping_map_atomic_wc() disables preemption and pagefaults for historical reasons. The conversion to io_mapping_map_local_wc(), which only disables migration, cannot be done wholesale because quite some call sites need to be updated to accommodate with the changed semantics. On PREEMPT_RT enabled kernels the io_mapping_map_atomic_wc() semantics are problematic due to the implicit disabling of preemption which makes it impossible to acquire 'sleeping' spinlocks within the mapped atomic sections. PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for more than a decade. It could be argued that this is a justification to do this unconditionally, but PREEMPT_RT covers only a limited number of architectures and it disables some functionality which limits the coverage further. Limit the replacement to PREEMPT_RT for now. This is also done kmap_atomic(). Link: https://lkml.kernel.org/r/20230310162905.O57Pj7hh@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Reported-by: Richard Weinberger Link: https://lore.kernel.org/CAFLxGvw0WMxaMqYqJ5WgvVSbKHq2D2xcXTOgMCpgq9nDC-MWTQ@mail.gmail.com Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/io-mapping.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 09d4f17c8d3b..7376c1df9c90 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -69,7 +69,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot); } @@ -79,7 +82,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { kunmap_local_indexed((void __force *)vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * @@ -162,7 +168,10 @@ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return io_mapping_map_wc(mapping, offset, PAGE_SIZE); } @@ -172,7 +181,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { io_mapping_unmap(vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * -- GitLab From 0a54864f8dfb64b64c84c9db6ff70e0e93690a33 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 9 Mar 2023 20:29:14 -0800 Subject: [PATCH 1502/5631] kasan: remove PG_skip_kasan_poison flag Code inspection reveals that PG_skip_kasan_poison is redundant with kasantag, because the former is intended to be set iff the latter is the match-all tag. It can also be observed that it's basically pointless to poison pages which have kasantag=0, because any pages with this tag would have been pointed to by pointers with match-all tags, so poisoning the pages would have little to no effect in terms of bug detection. Therefore, change the condition in should_skip_kasan_poison() to check kasantag instead, and remove PG_skip_kasan_poison and associated flags. Link: https://lkml.kernel.org/r/20230310042914.3805818-3-pcc@google.com Link: https://linux-review.googlesource.com/id/I57f825f2eaeaf7e8389d6cf4597c8a5821359838 Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Evgenii Stepanov Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/gfp_types.h | 30 ++++++------- include/linux/page-flags.h | 9 ---- include/trace/events/mmflags.h | 13 +----- mm/kasan/hw_tags.c | 2 +- mm/page_alloc.c | 81 +++++++++++++--------------------- mm/vmalloc.c | 2 +- 6 files changed, 47 insertions(+), 90 deletions(-) diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 5088637fe5c2..6583a58670c5 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -47,16 +47,14 @@ typedef unsigned int __bitwise gfp_t; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u -#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN 0x2000000u #else -#define ___GFP_SKIP_ZERO 0 -#define ___GFP_SKIP_KASAN_UNPOISON 0 -#define ___GFP_SKIP_KASAN_POISON 0 +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x8000000u +#define ___GFP_NOLOCKDEP 0x4000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -234,25 +232,24 @@ typedef unsigned int __bitwise gfp_t; * memory tags at the same time as zeroing memory has minimal additional * performace impact. * - * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. - * Only effective in HW_TAGS mode. - * - * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. - * Typically, used for userspace pages. Only effective in HW_TAGS mode. + * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. + * Used for userspace and vmalloc pages; the latter are unpoisoned by + * kasan_unpoison_vmalloc instead. For userspace pages, results in + * poisoning being skipped as well, see should_skip_kasan_poison for + * details. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) -#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_KASAN ((__force gfp_t)___GFP_SKIP_KASAN) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -335,8 +332,7 @@ typedef unsigned int __bitwise gfp_t; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | __GFP_SKIP_KASAN) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 57287102c5bd..dcda20c47b8f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -135,9 +135,6 @@ enum pageflags { #ifdef CONFIG_ARCH_USES_PG_ARCH_X PG_arch_2, PG_arch_3, -#endif -#ifdef CONFIG_KASAN_HW_TAGS - PG_skip_kasan_poison, #endif __NR_PAGEFLAGS, @@ -594,12 +591,6 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif -#ifdef CONFIG_KASAN_HW_TAGS -PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) -#else -PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) -#endif - /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index b28218b7998e..b63e7c0fbbe5 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -55,8 +55,7 @@ #ifdef CONFIG_KASAN_HW_TAGS #define __def_gfpflag_names_kasan , \ gfpflag_string(__GFP_SKIP_ZERO), \ - gfpflag_string(__GFP_SKIP_KASAN_POISON), \ - gfpflag_string(__GFP_SKIP_KASAN_UNPOISON) + gfpflag_string(__GFP_SKIP_KASAN) #else #define __def_gfpflag_names_kasan #endif @@ -96,13 +95,6 @@ #define IF_HAVE_PG_ARCH_X(_name) #endif -#ifdef CONFIG_KASAN_HW_TAGS -#define IF_HAVE_PG_SKIP_KASAN_POISON(_name) \ - ,{1UL << PG_##_name, __stringify(_name)} -#else -#define IF_HAVE_PG_SKIP_KASAN_POISON(_name) -#endif - #define DEF_PAGEFLAG_NAME(_name) { 1UL << PG_##_name, __stringify(_name) } #define __def_pageflag_names \ @@ -133,8 +125,7 @@ IF_HAVE_PG_HWPOISON(hwpoison) \ IF_HAVE_PG_IDLE(idle) \ IF_HAVE_PG_IDLE(young) \ IF_HAVE_PG_ARCH_X(arch_2) \ -IF_HAVE_PG_ARCH_X(arch_3) \ -IF_HAVE_PG_SKIP_KASAN_POISON(skip_kasan_poison) +IF_HAVE_PG_ARCH_X(arch_3) #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index d1bcb0205327..bb4f56e5bdec 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -318,7 +318,7 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, * Thus, for VM_ALLOC mappings, hardware tag-based KASAN only tags * the first virtual mapping, which is created by vmalloc(). * Tagging the page_alloc memory backing that vmalloc() allocation is - * skipped, see ___GFP_SKIP_KASAN_UNPOISON. + * skipped, see ___GFP_SKIP_KASAN. * * For non-VM_ALLOC allocations, page_alloc memory is tagged as usual. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a109444e9f44..3737f9d58f5f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -112,17 +112,6 @@ typedef int __bitwise fpi_t; */ #define FPI_TO_TAIL ((__force fpi_t)BIT(1)) -/* - * Don't poison memory with KASAN (only for the tag-based modes). - * During boot, all non-reserved memblock memory is exposed to page_alloc. - * Poisoning all that memory lengthens boot time, especially on systems with - * large amount of RAM. This flag is used to skip that poisoning. - * This is only done for the tag-based KASAN modes, as those are able to - * detect memory corruptions with the memory tags assigned by default. - * All memory allocated normally after boot gets poisoned as usual. - */ -#define FPI_SKIP_KASAN_POISON ((__force fpi_t)BIT(2)) - /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); #define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) @@ -1370,13 +1359,19 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) /* * Skip KASAN memory poisoning when either: * - * 1. Deferred memory initialization has not yet completed, - * see the explanation below. - * 2. Skipping poisoning is requested via FPI_SKIP_KASAN_POISON, - * see the comment next to it. - * 3. Skipping poisoning is requested via __GFP_SKIP_KASAN_POISON, - * see the comment next to it. - * 4. The allocation is excluded from being checked due to sampling, + * 1. For generic KASAN: deferred memory initialization has not yet completed. + * Tag-based KASAN modes skip pages freed via deferred memory initialization + * using page tags instead (see below). + * 2. For tag-based KASAN modes: the page has a match-all KASAN tag, indicating + * that error detection is disabled for accesses via the page address. + * + * Pages will have match-all tags in the following circumstances: + * + * 1. Pages are being initialized for the first time, including during deferred + * memory init; see the call to page_kasan_tag_reset in __init_single_page. + * 2. The allocation was not unpoisoned due to __GFP_SKIP_KASAN, with the + * exception of pages unpoisoned by kasan_unpoison_vmalloc. + * 3. The allocation was excluded from being checked due to sampling, * see the call to kasan_unpoison_pages. * * Poisoning pages during deferred memory init will greatly lengthen the @@ -1392,10 +1387,10 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) */ static inline bool should_skip_kasan_poison(struct page *page, fpi_t fpi_flags) { - return deferred_pages_enabled() || - (!IS_ENABLED(CONFIG_KASAN_GENERIC) && - (fpi_flags & FPI_SKIP_KASAN_POISON)) || - PageSkipKASanPoison(page); + if (IS_ENABLED(CONFIG_KASAN_GENERIC)) + return deferred_pages_enabled(); + + return page_kasan_tag(page) == 0xff; } static void kernel_init_pages(struct page *page, int numpages) @@ -1730,7 +1725,7 @@ void __free_pages_core(struct page *page, unsigned int order) * Bypass PCP and place fresh pages right to the tail, primarily * relevant for memory onlining. */ - __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON); + __free_pages_ok(page, order, FPI_TO_TAIL); } #ifdef CONFIG_NUMA @@ -2396,9 +2391,9 @@ static inline bool should_skip_kasan_unpoison(gfp_t flags) /* * With hardware tag-based KASAN enabled, skip if this has been - * requested via __GFP_SKIP_KASAN_UNPOISON. + * requested via __GFP_SKIP_KASAN. */ - return flags & __GFP_SKIP_KASAN_UNPOISON; + return flags & __GFP_SKIP_KASAN; } static inline bool should_skip_init(gfp_t flags) @@ -2417,7 +2412,6 @@ inline void post_alloc_hook(struct page *page, unsigned int order, bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); - bool reset_tags = true; int i; set_page_private(page, 0); @@ -2451,37 +2445,22 @@ inline void post_alloc_hook(struct page *page, unsigned int order, /* Take note that memory was initialized by the loop above. */ init = false; } - if (!should_skip_kasan_unpoison(gfp_flags)) { - /* Try unpoisoning (or setting tags) and initializing memory. */ - if (kasan_unpoison_pages(page, order, init)) { - /* Take note that memory was initialized by KASAN. */ - if (kasan_has_integrated_init()) - init = false; - /* Take note that memory tags were set by KASAN. */ - reset_tags = false; - } else { - /* - * KASAN decided to exclude this allocation from being - * (un)poisoned due to sampling. Make KASAN skip - * poisoning when the allocation is freed. - */ - SetPageSkipKASanPoison(page); - } - } - /* - * If memory tags have not been set by KASAN, reset the page tags to - * ensure page_address() dereferencing does not fault. - */ - if (reset_tags) { + if (!should_skip_kasan_unpoison(gfp_flags) && + kasan_unpoison_pages(page, order, init)) { + /* Take note that memory was initialized by KASAN. */ + if (kasan_has_integrated_init()) + init = false; + } else { + /* + * If memory tags have not been set by KASAN, reset the page + * tags to ensure page_address() dereferencing does not fault. + */ for (i = 0; i != 1 << order; ++i) page_kasan_tag_reset(page + i); } /* If memory is still not initialized, initialize it now. */ if (init) kernel_init_pages(page, 1 << order); - /* Propagate __GFP_SKIP_KASAN_POISON to page flags. */ - if (kasan_hw_tags_enabled() && (gfp_flags & __GFP_SKIP_KASAN_POISON)) - SetPageSkipKASanPoison(page); set_page_owner(page, order, gfp_flags); page_table_check_alloc(page, order); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bef6cf2b4d46..5e60e9792cbf 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3188,7 +3188,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc(). */ - gfp_mask |= __GFP_SKIP_KASAN_UNPOISON | __GFP_SKIP_ZERO; + gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; } /* Take note that the mapping is PAGE_KERNEL. */ -- GitLab From dcc1be119071f034f3123d3c618d2ef70c80125e Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Mon, 13 Mar 2023 12:27:14 +0000 Subject: [PATCH 1503/5631] mm: prefer xxx_page() alloc/free functions for order-0 pages Update instances of alloc_pages(..., 0), __get_free_pages(..., 0) and __free_pages(..., 0) to use alloc_page(), __get_free_page() and __free_page() respectively in core code. Link: https://lkml.kernel.org/r/50c48ca4789f1da2a65795f2346f5ae3eff7d665.1678710232.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Acked-by: Mel Gorman Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Uladzislau Rezki (Sony) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/asm-generic/pgalloc.h | 4 ++-- mm/debug_vm_pgtable.c | 4 ++-- mm/hugetlb_vmemmap.c | 2 +- mm/mmu_gather.c | 2 +- mm/page_alloc.c | 2 +- mm/vmalloc.c | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 977bea16cf1b..a7cf825befae 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -123,11 +123,11 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; - page = alloc_pages(gfp, 0); + page = alloc_page(gfp); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { - __free_pages(page, 0); + __free_page(page); return NULL; } return (pmd_t *)page_address(page); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 7887cc2b75bf..4362021b1ce7 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -1048,7 +1048,7 @@ static void __init destroy_args(struct pgtable_debug_args *args) if (args->pte_pfn != ULONG_MAX) { page = pfn_to_page(args->pte_pfn); - __free_pages(page, 0); + __free_page(page); args->pte_pfn = ULONG_MAX; } @@ -1290,7 +1290,7 @@ static int __init init_args(struct pgtable_debug_args *args) } } - page = alloc_pages(GFP_KERNEL, 0); + page = alloc_page(GFP_KERNEL); if (page) args->pte_pfn = page_to_pfn(page); diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index a15cc56cf70a..1198064f80eb 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -400,7 +400,7 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, return 0; out: list_for_each_entry_safe(page, next, list, lru) - __free_pages(page, 0); + __free_page(page); return -ENOMEM; } diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 2b93cf6ac9ae..ea9683e12936 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -32,7 +32,7 @@ static bool tlb_next_batch(struct mmu_gather *tlb) if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) return false; - batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); + batch = (void *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (!batch) return false; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3737f9d58f5f..0936bde1d486 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5558,7 +5558,7 @@ EXPORT_SYMBOL(__get_free_pages); unsigned long get_zeroed_page(gfp_t gfp_mask) { - return __get_free_pages(gfp_mask | __GFP_ZERO, 0); + return __get_free_page(gfp_mask | __GFP_ZERO); } EXPORT_SYMBOL(get_zeroed_page); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5e60e9792cbf..978194dc2bb8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2739,7 +2739,7 @@ void vfree(const void *addr) * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations */ - __free_pages(page, 0); + __free_page(page); cond_resched(); } atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); -- GitLab From 42c9db39704839eeb77b27db4c1d57bfa2a54a5b Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:12 +0800 Subject: [PATCH 1504/5631] mm: vmscan: add a map_nr_max field to shrinker_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "make slab shrink lockless", v5. This patch series aims to make slab shrink lockless. 1. Background ============= On our servers, we often find the following system cpu hotspots: 52.22% [kernel] [k] down_read_trylock 19.60% [kernel] [k] up_read 8.86% [kernel] [k] shrink_slab 2.44% [kernel] [k] idr_find 1.25% [kernel] [k] count_shadow_nodes 1.18% [kernel] [k] shrink lruvec 0.71% [kernel] [k] mem_cgroup_iter 0.71% [kernel] [k] shrink_node 0.55% [kernel] [k] find_next_bit And we used bpftrace to capture its calltrace as follows: @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 do_try_to_free_pages+232 try_to_free_pages+243 _alloc_pages_slowpath+771 _alloc_pages_nodemask+702 pagecache_get_page+255 filemap_fault+1361 ext4_filemap_fault+44 __do_fault+76 handle_mm_fault+3543 do_user_addr_fault+442 do_page_fault+48 page_fault+62 ]: 1161690 @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 balance_pgdat+690 kswapd+389 kthread+246 ret_from_fork+31 ]: 8424884 @[ down_read_trylock+1 shrink_slab+128 shrink_node+371 do_try_to_free_pages+232 try_to_free_pages+243 __alloc_pages_slowpath+771 __alloc_pages_nodemask+702 __do_page_cache_readahead+244 filemap_fault+1674 ext4_filemap_fault+44 __do_fault+76 handle_mm_fault+3543 do_user_addr_fault+442 do_page_fault+48 page_fault+62 ]: 20917631 We can see that down_read_trylock() of shrinker_rwsem is being called with high frequency at that time. Because of the poor multicore scalability of atomic operations, this can lead to a significant drop in IPC (instructions per cycle). And more, the shrinker_rwsem is a global read-write lock in shrinkers subsystem, which protects most operations such as slab shrink, registration and unregistration of shrinkers, etc. This can easily cause problems in the following cases. 1) When the memory pressure is high and there are many filesystems mounted or unmounted at the same time, slab shrink will be affected (down_read_trylock() failed). Such as the real workload mentioned by Kirill Tkhai: ``` One of the real workloads from my experience is start of an overcommitted node containing many starting containers after node crash (or many resuming containers after reboot for kernel update). In these cases memory pressure is huge, and the node goes round in long reclaim. ``` 2) If a shrinker is blocked (such as the case mentioned in [1]) and a writer comes in (such as mount a fs), then this writer will be blocked and cause all subsequent shrinker-related operations to be blocked. [1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@virtuozzo.com/ All the above cases can be solved by replacing the shrinker_rwsem trylocks with SRCU. 2. Survey ========= Before doing the code implementation, I found that there were many similar submissions in the community: a. Davidlohr Bueso submitted a patch in 2015. Subject: [PATCH -next v2] mm: srcu-ify shrinkers Link: https://lore.kernel.org/all/1437080113.3596.2.camel@stgolabs.net/ Result: It was finally merged into the linux-next branch, but failed on arm allnoconfig (without CONFIG_SRCU) b. Tetsuo Handa submitted a patchset in 2017. Subject: [PATCH 1/2] mm,vmscan: Kill global shrinker lock. Link: https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp/ Result: Finally chose to use the current simple way (break when rwsem_is_contended()). And Christoph Hellwig suggested to using SRCU, but SRCU was not unconditionally enabled at the time. c. Kirill Tkhai submitted a patchset in 2018. Subject: [PATCH RFC 00/10] Introduce lockless shrink_slab() Link: https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/ Result: At that time, SRCU was not unconditionally enabled, and there were some objections to enabling SRCU. Later, because Kirill's focus was moved to other things, this patchset was not continued to be updated. d. Sultan Alsawaf submitted a patch in 2021. Subject: [PATCH] mm: vmscan: Replace shrinker_rwsem trylocks with SRCU protection Link: https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@kerneltoast.com/ Result: Rejected because SRCU was not unconditionally enabled. We can find that almost all these historical commits were abandoned because SRCU was not unconditionally enabled. But now SRCU has been unconditionally enable by Paul E. McKenney in 2023 [2], so it's time to replace shrinker_rwsem trylocks with SRCU. [2] https://lore.kernel.org/lkml/20230105003759.GA1769545@paulmck-ThinkPad-P17-Gen-1/ 3. Reproduction and testing =========================== We can reproduce the down_read_trylock() hotspot through the following script: ``` #!/bin/bash DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test mkdir -p /sys/fs/cgroup/perf_event/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 32.31% [kernel] [k] down_read_trylock 19.40% [kernel] [k] pv_native_safe_halt 16.24% [kernel] [k] up_read 15.70% [kernel] [k] shrink_slab 4.69% [kernel] [k] _find_next_bit 2.62% [kernel] [k] shrink_node 1.78% [kernel] [k] shrink_lruvec 0.76% [kernel] [k] do_shrink_slab 2) After applying this patchset: 27.83% [kernel] [k] _find_next_bit 16.97% [kernel] [k] shrink_slab 15.82% [kernel] [k] pv_native_safe_halt 9.58% [kernel] [k] shrink_node 8.31% [kernel] [k] shrink_lruvec 5.64% [kernel] [k] do_shrink_slab 3.88% [kernel] [k] mem_cgroup_iter At the same time, we use the following perf command to capture IPC information: perf stat -e cycles,instructions -G test -a --repeat 5 -- sleep 10 1) Before applying this patchset: Performance counter stats for 'system wide' (5 runs): 454187219766 cycles test ( +- 1.84% ) 78896433101 instructions test # 0.17 insn per cycle ( +- 0.44% ) 10.0020430 +- 0.0000366 seconds time elapsed ( +- 0.00% ) 2) After applying this patchset: Performance counter stats for 'system wide' (5 runs): 841954709443 cycles test ( +- 15.80% ) (98.69%) 527258677936 instructions test # 0.63 insn per cycle ( +- 15.11% ) (98.68%) 10.01064 +- 0.00831 seconds time elapsed ( +- 0.08% ) We can see that IPC drops very seriously when calling down_read_trylock() at high frequency. After using SRCU, the IPC is at a normal level. This patch (of 8): To prepare for the subsequent lockless memcg slab shrink, add a map_nr_max field to struct shrinker_info to records its own real shrinker_nr_max. Link: https://lkml.kernel.org/r/20230313112819.38938-1-zhengqi.arch@bytedance.com Link: https://lkml.kernel.org/r/20230313112819.38938-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Suggested-by: Kirill Tkhai Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Qi Zheng Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 1 + mm/vmscan.c | 35 ++++++++++++++++++----------------- 2 files changed, 19 insertions(+), 17 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b6eda2ab205d..aa69ea98e2d8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,7 @@ struct shrinker_info { struct rcu_head rcu; atomic_long_t *nr_deferred; unsigned long *map; + int map_nr_max; }; struct lruvec_stats_percpu { diff --git a/mm/vmscan.c b/mm/vmscan.c index 9414226218f0..9a2a6301052c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -226,7 +226,8 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, static int expand_one_shrinker_info(struct mem_cgroup *memcg, int map_size, int defer_size, - int old_map_size, int old_defer_size) + int old_map_size, int old_defer_size, + int new_nr_max) { struct shrinker_info *new, *old; struct mem_cgroup_per_node *pn; @@ -240,12 +241,17 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, if (!old) return 0; + /* Already expanded this shrinker_info */ + if (new_nr_max <= old->map_nr_max) + continue; + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); if (!new) return -ENOMEM; new->nr_deferred = (atomic_long_t *)(new + 1); new->map = (void *)new->nr_deferred + defer_size; + new->map_nr_max = new_nr_max; /* map: set all old bits, clear all new bits */ memset(new->map, (int)0xff, old_map_size); @@ -295,6 +301,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) } info->nr_deferred = (atomic_long_t *)(info + 1); info->map = (void *)info->nr_deferred + defer_size; + info->map_nr_max = shrinker_nr_max; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } up_write(&shrinker_rwsem); @@ -302,23 +309,14 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) return ret; } -static inline bool need_expand(int nr_max) -{ - return round_up(nr_max, BITS_PER_LONG) > - round_up(shrinker_nr_max, BITS_PER_LONG); -} - static int expand_shrinker_info(int new_id) { int ret = 0; - int new_nr_max = new_id + 1; + int new_nr_max = round_up(new_id + 1, BITS_PER_LONG); int map_size, defer_size = 0; int old_map_size, old_defer_size = 0; struct mem_cgroup *memcg; - if (!need_expand(new_nr_max)) - goto out; - if (!root_mem_cgroup) goto out; @@ -332,7 +330,8 @@ static int expand_shrinker_info(int new_id) memcg = mem_cgroup_iter(NULL, NULL, NULL); do { ret = expand_one_shrinker_info(memcg, map_size, defer_size, - old_map_size, old_defer_size); + old_map_size, old_defer_size, + new_nr_max); if (ret) { mem_cgroup_iter_break(NULL, memcg); goto out; @@ -352,9 +351,11 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) rcu_read_lock(); info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, info->map); + if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id, info->map); + } rcu_read_unlock(); } } @@ -432,7 +433,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); - for (i = 0; i < shrinker_nr_max; i++) { + for (i = 0; i < child_info->map_nr_max; i++) { nr = atomic_long_read(&child_info->nr_deferred[i]); atomic_long_add(nr, &parent_info->nr_deferred[i]); } @@ -899,7 +900,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, if (unlikely(!info)) goto unlock; - for_each_set_bit(i, info->map, shrinker_nr_max) { + for_each_set_bit(i, info->map, info->map_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, -- GitLab From f95bdb700bc6bb74e1199b1f5f90c613e152cfa7 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:13 +0800 Subject: [PATCH 1505/5631] mm: vmscan: make global slab shrink lockless MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The shrinker_rwsem is a global read-write lock in shrinkers subsystem, which protects most operations such as slab shrink, registration and unregistration of shrinkers, etc. This can easily cause problems in the following cases. 1) When the memory pressure is high and there are many filesystems mounted or unmounted at the same time, slab shrink will be affected (down_read_trylock() failed). Such as the real workload mentioned by Kirill Tkhai: ``` One of the real workloads from my experience is start of an overcommitted node containing many starting containers after node crash (or many resuming containers after reboot for kernel update). In these cases memory pressure is huge, and the node goes round in long reclaim. ``` 2) If a shrinker is blocked (such as the case mentioned in [1]) and a writer comes in (such as mount a fs), then this writer will be blocked and cause all subsequent shrinker-related operations to be blocked. Even if there is no competitor when shrinking slab, there may still be a problem. If we have a long shrinker list and we do not reclaim enough memory with each shrinker, then the down_read_trylock() may be called with high frequency. Because of the poor multicore scalability of atomic operations, this can lead to a significant drop in IPC (instructions per cycle). So many times in history ([2],[3],[4],[5]), some people wanted to replace shrinker_rwsem trylock with SRCU in the slab shrink, but all these patches were abandoned because SRCU was not unconditionally enabled. But now, since commit 1cd0bd06093c ("rcu: Remove CONFIG_SRCU"), the SRCU is unconditionally enabled. So it's time to use SRCU to protect readers who previously held shrinker_rwsem. This commit uses SRCU to make global slab shrink lockless, the memcg slab shrink is handled in the subsequent patch. [1]. https://lore.kernel.org/lkml/20191129214541.3110-1-ptikhomirov@virtuozzo.com/ [2]. https://lore.kernel.org/all/1437080113.3596.2.camel@stgolabs.net/ [3]. https://lore.kernel.org/lkml/1510609063-3327-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp/ [4]. https://lore.kernel.org/lkml/153365347929.19074.12509495712735843805.stgit@localhost.localdomain/ [5]. https://lore.kernel.org/lkml/20210927074823.5825-1-sultan@kerneltoast.com/ Link: https://lkml.kernel.org/r/20230313112819.38938-3-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/vmscan.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 9a2a6301052c..db2ed6e08f67 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include @@ -202,6 +203,7 @@ static void set_task_reclaim_state(struct task_struct *task, LIST_HEAD(shrinker_list); DECLARE_RWSEM(shrinker_rwsem); +DEFINE_SRCU(shrinker_srcu); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -700,7 +702,7 @@ void free_prealloced_shrinker(struct shrinker *shrinker) void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); - list_add_tail(&shrinker->list, &shrinker_list); + list_add_tail_rcu(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); up_write(&shrinker_rwsem); @@ -754,13 +756,15 @@ void unregister_shrinker(struct shrinker *shrinker) return; down_write(&shrinker_rwsem); - list_del(&shrinker->list); + list_del_rcu(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); debugfs_entry = shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); + synchronize_srcu(&shrinker_srcu); + debugfs_remove_recursive(debugfs_entry); kfree(shrinker->nr_deferred); @@ -780,6 +784,7 @@ void synchronize_shrinkers(void) { down_write(&shrinker_rwsem); up_write(&shrinker_rwsem); + synchronize_srcu(&shrinker_srcu); } EXPORT_SYMBOL(synchronize_shrinkers); @@ -990,6 +995,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, { unsigned long ret, freed = 0; struct shrinker *shrinker; + int srcu_idx; /* * The root memcg might be allocated even though memcg is disabled @@ -1001,10 +1007,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - if (!down_read_trylock(&shrinker_rwsem)) - goto out; + srcu_idx = srcu_read_lock(&shrinker_srcu); - list_for_each_entry(shrinker, &shrinker_list, list) { + list_for_each_entry_srcu(shrinker, &shrinker_list, list, + srcu_read_lock_held(&shrinker_srcu)) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -1015,19 +1021,9 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; freed += ret; - /* - * Bail out if someone want to register a new shrinker to - * prevent the registration from being stalled for long periods - * by parallel ongoing shrinking. - */ - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } } - up_read(&shrinker_rwsem); -out: + srcu_read_unlock(&shrinker_srcu, srcu_idx); cond_resched(); return freed; } -- GitLab From caa05325c9126c77ebf114edce51536a0d0a9a08 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:14 +0800 Subject: [PATCH 1506/5631] mm: vmscan: make memcg slab shrink lockless MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Like global slab shrink, this commit also uses SRCU to make memcg slab shrink lockless. We can reproduce the down_read_trylock() hotspot through the following script: ``` DIR="/root/shrinker/memcg/mnt" do_create() { mkdir -p /sys/fs/cgroup/memory/test mkdir -p /sys/fs/cgroup/perf_event/test echo 4G > /sys/fs/cgroup/memory/test/memory.limit_in_bytes for i in `seq 0 $1`; do mkdir -p /sys/fs/cgroup/memory/test/$i; echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; mkdir -p $DIR/$i; done } do_mount() { for i in `seq $1 $2`; do mount -t tmpfs $i $DIR/$i; done } do_touch() { for i in `seq $1 $2`; do echo $$ > /sys/fs/cgroup/memory/test/$i/cgroup.procs; echo $$ > /sys/fs/cgroup/perf_event/test/cgroup.procs; dd if=/dev/zero of=$DIR/$i/file$i bs=1M count=1 & done } case "$1" in touch) do_touch $2 $3 ;; test) do_create 4000 do_mount 0 4000 do_touch 0 3000 ;; *) exit 1 ;; esac ``` Save the above script, then run test and touch commands. Then we can use the following perf command to view hotspots: perf top -U -F 999 1) Before applying this patchset: 32.31% [kernel] [k] down_read_trylock 19.40% [kernel] [k] pv_native_safe_halt 16.24% [kernel] [k] up_read 15.70% [kernel] [k] shrink_slab 4.69% [kernel] [k] _find_next_bit 2.62% [kernel] [k] shrink_node 1.78% [kernel] [k] shrink_lruvec 0.76% [kernel] [k] do_shrink_slab 2) After applying this patchset: 27.83% [kernel] [k] _find_next_bit 16.97% [kernel] [k] shrink_slab 15.82% [kernel] [k] pv_native_safe_halt 9.58% [kernel] [k] shrink_node 8.31% [kernel] [k] shrink_lruvec 5.64% [kernel] [k] do_shrink_slab 3.88% [kernel] [k] mem_cgroup_iter At the same time, we use the following perf command to capture IPC information: perf stat -e cycles,instructions -G test -a --repeat 5 -- sleep 10 1) Before applying this patchset: Performance counter stats for 'system wide' (5 runs): 454187219766 cycles test ( +- 1.84% ) 78896433101 instructions test # 0.17 insn per cycle ( +- 0.44% ) 10.0020430 +- 0.0000366 seconds time elapsed ( +- 0.00% ) 2) After applying this patchset: Performance counter stats for 'system wide' (5 runs): 841954709443 cycles test ( +- 15.80% ) (98.69%) 527258677936 instructions test # 0.63 insn per cycle ( +- 15.11% ) (98.68%) 10.01064 +- 0.00831 seconds time elapsed ( +- 0.08% ) We can see that IPC drops very seriously when calling down_read_trylock() at high frequency. After using SRCU, the IPC is at a normal level. Link: https://lkml.kernel.org/r/20230313112819.38938-4-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Kirill Tkhai Acked-by: Vlastimil Babka Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/vmscan.c | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index db2ed6e08f67..ce7834030f75 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -222,8 +222,21 @@ static inline int shrinker_defer_size(int nr_items) static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { - return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, - lockdep_is_held(&shrinker_rwsem)); + return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info, + &shrinker_srcu, + lockdep_is_held(&shrinker_rwsem)); +} + +static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg, + int nid) +{ + return srcu_dereference(memcg->nodeinfo[nid]->shrinker_info, + &shrinker_srcu); +} + +static void free_shrinker_info_rcu(struct rcu_head *head) +{ + kvfree(container_of(head, struct shrinker_info, rcu)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, @@ -264,7 +277,7 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, defer_size - old_defer_size); rcu_assign_pointer(pn->shrinker_info, new); - kvfree_rcu(old, rcu); + call_srcu(&shrinker_srcu, &old->rcu, free_shrinker_info_rcu); } return 0; @@ -350,15 +363,16 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { struct shrinker_info *info; + int srcu_idx; - rcu_read_lock(); - info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); + srcu_idx = srcu_read_lock(&shrinker_srcu); + info = shrinker_info_srcu(memcg, nid); if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { /* Pairs with smp mb in shrink_slab() */ smp_mb__before_atomic(); set_bit(shrinker_id, info->map); } - rcu_read_unlock(); + srcu_read_unlock(&shrinker_srcu, srcu_idx); } } @@ -372,7 +386,6 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) return -ENOSYS; down_write(&shrinker_rwsem); - /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -406,7 +419,7 @@ static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_protected(memcg, nid); + info = shrinker_info_srcu(memcg, nid); return atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); } @@ -415,7 +428,7 @@ static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, { struct shrinker_info *info; - info = shrinker_info_protected(memcg, nid); + info = shrinker_info_srcu(memcg, nid); return atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); } @@ -893,15 +906,14 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, { struct shrinker_info *info; unsigned long ret, freed = 0; + int srcu_idx; int i; if (!mem_cgroup_online(memcg)) return 0; - if (!down_read_trylock(&shrinker_rwsem)) - return 0; - - info = shrinker_info_protected(memcg, nid); + srcu_idx = srcu_read_lock(&shrinker_srcu); + info = shrinker_info_srcu(memcg, nid); if (unlikely(!info)) goto unlock; @@ -951,14 +963,9 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, set_shrinker_bit(memcg, nid, i); } freed += ret; - - if (rwsem_is_contended(&shrinker_rwsem)) { - freed = freed ? : 1; - break; - } } unlock: - up_read(&shrinker_rwsem); + srcu_read_unlock(&shrinker_srcu, srcu_idx); return freed; } #else /* CONFIG_MEMCG */ -- GitLab From 475733dda5aedba9e086379aafe6b5ffd53e8f5e Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 13 Mar 2023 19:28:15 +0800 Subject: [PATCH 1507/5631] mm: vmscan: add shrinker_srcu_generation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After we make slab shrink lockless with SRCU, the longest sleep unregister_shrinker() will be a sleep waiting for all do_shrink_slab() calls. To avoid long unbreakable action in the unregister_shrinker(), add shrinker_srcu_generation to restore a check similar to the rwsem_is_contendent() check that we had before. And for memcg slab shrink, we unlock SRCU and continue iterations from the next shrinker id. Link: https://lkml.kernel.org/r/20230313112819.38938-5-zhengqi.arch@bytedance.com Signed-off-by: Kirill Tkhai Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/vmscan.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index ce7834030f75..5c2a22454320 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -204,6 +204,7 @@ static void set_task_reclaim_state(struct task_struct *task, LIST_HEAD(shrinker_list); DECLARE_RWSEM(shrinker_rwsem); DEFINE_SRCU(shrinker_srcu); +static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -776,6 +777,7 @@ void unregister_shrinker(struct shrinker *shrinker) debugfs_entry = shrinker_debugfs_remove(shrinker); up_write(&shrinker_rwsem); + atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); debugfs_remove_recursive(debugfs_entry); @@ -797,6 +799,7 @@ void synchronize_shrinkers(void) { down_write(&shrinker_rwsem); up_write(&shrinker_rwsem); + atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); } EXPORT_SYMBOL(synchronize_shrinkers); @@ -906,18 +909,20 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, { struct shrinker_info *info; unsigned long ret, freed = 0; - int srcu_idx; - int i; + int srcu_idx, generation; + int i = 0; if (!mem_cgroup_online(memcg)) return 0; +again: srcu_idx = srcu_read_lock(&shrinker_srcu); info = shrinker_info_srcu(memcg, nid); if (unlikely(!info)) goto unlock; - for_each_set_bit(i, info->map, info->map_nr_max) { + generation = atomic_read(&shrinker_srcu_generation); + for_each_set_bit_from(i, info->map, info->map_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, @@ -963,6 +968,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, set_shrinker_bit(memcg, nid, i); } freed += ret; + if (atomic_read(&shrinker_srcu_generation) != generation) { + srcu_read_unlock(&shrinker_srcu, srcu_idx); + i++; + goto again; + } } unlock: srcu_read_unlock(&shrinker_srcu, srcu_idx); @@ -1002,7 +1012,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, { unsigned long ret, freed = 0; struct shrinker *shrinker; - int srcu_idx; + int srcu_idx, generation; /* * The root memcg might be allocated even though memcg is disabled @@ -1016,6 +1026,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, srcu_idx = srcu_read_lock(&shrinker_srcu); + generation = atomic_read(&shrinker_srcu_generation); list_for_each_entry_srcu(shrinker, &shrinker_list, list, srcu_read_lock_held(&shrinker_srcu)) { struct shrink_control sc = { @@ -1028,6 +1039,11 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, if (ret == SHRINK_EMPTY) ret = 0; freed += ret; + + if (atomic_read(&shrinker_srcu_generation) != generation) { + freed = freed ? : 1; + break; + } } srcu_read_unlock(&shrinker_srcu, srcu_idx); -- GitLab From 20cd1892fcc3efc10a7ac327cc3790494bec46b5 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:16 +0800 Subject: [PATCH 1508/5631] mm: shrinkers: make count and scan in shrinker debugfs lockless MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Like global and memcg slab shrink, also use SRCU to make count and scan operations in memory shrinker debugfs lockless. Link: https://lkml.kernel.org/r/20230313112819.38938-6-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/shrinker_debug.c | 25 ++++++++----------------- 1 file changed, 8 insertions(+), 17 deletions(-) diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 39c3491e28a3..37d54d037495 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -5,10 +5,12 @@ #include #include #include +#include /* defined in vmscan.c */ extern struct rw_semaphore shrinker_rwsem; extern struct list_head shrinker_list; +extern struct srcu_struct shrinker_srcu; static DEFINE_IDA(shrinker_debugfs_ida); static struct dentry *shrinker_debugfs_root; @@ -49,18 +51,13 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) struct mem_cgroup *memcg; unsigned long total; bool memcg_aware; - int ret, nid; + int ret = 0, nid, srcu_idx; count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL); if (!count_per_node) return -ENOMEM; - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - kfree(count_per_node); - return ret; - } - rcu_read_lock(); + srcu_idx = srcu_read_lock(&shrinker_srcu); memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE; @@ -91,8 +88,7 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v) } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); - rcu_read_unlock(); - up_read(&shrinker_rwsem); + srcu_read_unlock(&shrinker_srcu, srcu_idx); kfree(count_per_node); return ret; @@ -115,9 +111,8 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, .gfp_mask = GFP_KERNEL, }; struct mem_cgroup *memcg = NULL; - int nid; + int nid, srcu_idx; char kbuf[72]; - ssize_t ret; read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1); if (copy_from_user(kbuf, buf, read_len)) @@ -146,11 +141,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, return -EINVAL; } - ret = down_read_killable(&shrinker_rwsem); - if (ret) { - mem_cgroup_put(memcg); - return ret; - } + srcu_idx = srcu_read_lock(&shrinker_srcu); sc.nid = nid; sc.memcg = memcg; @@ -159,7 +150,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file, shrinker->scan_objects(shrinker, &sc); - up_read(&shrinker_rwsem); + srcu_read_unlock(&shrinker_srcu, srcu_idx); mem_cgroup_put(memcg); return size; -- GitLab From b3cabea3c9153fd42fe5cb851ac58b51ea2b32b8 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:17 +0800 Subject: [PATCH 1509/5631] mm: vmscan: hold write lock to reparent shrinker nr_deferred MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For now, reparent_shrinker_deferred() is the only holder of read lock of shrinker_rwsem. And it already holds the global cgroup_mutex, so it will not be called in parallel. Therefore, in order to convert shrinker_rwsem to shrinker_mutex later, here we change to hold the write lock of shrinker_rwsem to reparent. Link: https://lkml.kernel.org/r/20230313112819.38938-7-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/vmscan.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 5c2a22454320..8c1ae7ea8dea 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -445,7 +445,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - down_read(&shrinker_rwsem); + down_write(&shrinker_rwsem); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -454,7 +454,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) atomic_long_add(nr, &parent_info->nr_deferred[i]); } } - up_read(&shrinker_rwsem); + up_write(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) -- GitLab From 1643db98d9b314e0a592d152603094fbf7ab906e Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:18 +0800 Subject: [PATCH 1510/5631] mm: vmscan: remove shrinker_rwsem from synchronize_shrinkers() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, the synchronize_shrinkers() is only used by TTM pool. It only requires that no shrinkers run in parallel, and doesn't care about registering and unregistering of shrinkers. Since slab shrink is protected by SRCU, synchronize_srcu() is sufficient to ensure that no shrinker is running in parallel. So the shrinker_rwsem in synchronize_shrinkers() is no longer needed, just remove it. Link: https://lkml.kernel.org/r/20230313112819.38938-8-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/vmscan.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 8c1ae7ea8dea..2b22a42d83c4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -790,15 +790,11 @@ EXPORT_SYMBOL(unregister_shrinker); /** * synchronize_shrinkers - Wait for all running shrinkers to complete. * - * This is equivalent to calling unregister_shrink() and register_shrinker(), - * but atomically and with less overhead. This is useful to guarantee that all - * shrinker invocations have seen an update, before freeing memory, similar to - * rcu. + * This is useful to guarantee that all shrinker invocations have seen an + * update, before freeing memory. */ void synchronize_shrinkers(void) { - down_write(&shrinker_rwsem); - up_write(&shrinker_rwsem); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); } -- GitLab From cf2e309ebca7bb0916771839f9b580b06c778530 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 13 Mar 2023 19:28:19 +0800 Subject: [PATCH 1511/5631] mm: shrinkers: convert shrinker_rwsem to mutex MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now there are no readers of shrinker_rwsem, so we can simply replace it with mutex lock. Link: https://lkml.kernel.org/r/20230313112819.38938-9-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Vlastimil Babka Acked-by: Kirill Tkhai Acked-by: Roman Gushchin Cc: Christian König Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Cc: Paul E. McKenney Cc: Shakeel Butt Cc: Sultan Alsawaf Cc: Tetsuo Handa Cc: Yang Shi Signed-off-by: Andrew Morton --- drivers/md/dm-cache-metadata.c | 2 +- drivers/md/dm-thin-metadata.c | 2 +- fs/super.c | 2 +- mm/shrinker_debug.c | 14 +++++++------- mm/vmscan.c | 34 +++++++++++++++++----------------- 5 files changed, 27 insertions(+), 27 deletions(-) diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index acffed750e3e..9e0c69958587 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs cmd root_lock). - * - must take shrinker_rwsem without holding cmd->root_lock + * - must take shrinker_mutex without holding cmd->root_lock */ new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index fd464fb024c3..9f5cb52c5763 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -1887,7 +1887,7 @@ int dm_pool_abort_metadata(struct dm_pool_metadata *pmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs pmd root_lock). - * - must take shrinker_rwsem without holding pmd->root_lock + * - must take shrinker_mutex without holding pmd->root_lock */ new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, THIN_MAX_CONCURRENT_LOCKS); diff --git a/fs/super.c b/fs/super.c index 04bc62ab7dfe..34afe411cf2b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = { * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we + * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 37d54d037495..fdd155fd35ed 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -8,7 +8,7 @@ #include /* defined in vmscan.c */ -extern struct rw_semaphore shrinker_rwsem; +extern struct mutex shrinker_mutex; extern struct list_head shrinker_list; extern struct srcu_struct shrinker_srcu; @@ -168,7 +168,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -211,7 +211,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); old = shrinker->name; shrinker->name = new; @@ -229,7 +229,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); kfree_const(old); @@ -241,7 +241,7 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); kfree_const(shrinker->name); shrinker->name = NULL; @@ -266,14 +266,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 2b22a42d83c4..8faac4310cb5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,7 @@ #include #include #include -#include +#include #include #include #include @@ -202,7 +202,7 @@ static void set_task_reclaim_state(struct task_struct *task, } LIST_HEAD(shrinker_list); -DECLARE_RWSEM(shrinker_rwsem); +DEFINE_MUTEX(shrinker_mutex); DEFINE_SRCU(shrinker_srcu); static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0); @@ -225,7 +225,7 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, { return srcu_dereference_check(memcg->nodeinfo[nid]->shrinker_info, &shrinker_srcu, - lockdep_is_held(&shrinker_rwsem)); + lockdep_is_held(&shrinker_mutex)); } static struct shrinker_info *shrinker_info_srcu(struct mem_cgroup *memcg, @@ -304,7 +304,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) int nid, size, ret = 0; int map_size, defer_size = 0; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); map_size = shrinker_map_size(shrinker_nr_max); defer_size = shrinker_defer_size(shrinker_nr_max); size = map_size + defer_size; @@ -320,7 +320,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) info->map_nr_max = shrinker_nr_max; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } @@ -336,7 +336,7 @@ static int expand_shrinker_info(int new_id) if (!root_mem_cgroup) goto out; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); map_size = shrinker_map_size(new_nr_max); defer_size = shrinker_defer_size(new_nr_max); @@ -386,7 +386,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) if (mem_cgroup_disabled()) return -ENOSYS; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -400,7 +400,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker) shrinker->id = id; ret = 0; unlock: - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } @@ -410,7 +410,7 @@ static void unregister_memcg_shrinker(struct shrinker *shrinker) BUG_ON(id < 0); - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); idr_remove(&shrinker_idr, id); } @@ -445,7 +445,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -454,7 +454,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) atomic_long_add(nr, &parent_info->nr_deferred[i]); } } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); } static bool cgroup_reclaim(struct scan_control *sc) @@ -703,9 +703,9 @@ void free_prealloced_shrinker(struct shrinker *shrinker) shrinker->name = NULL; #endif if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); unregister_memcg_shrinker(shrinker); - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return; } @@ -715,11 +715,11 @@ void free_prealloced_shrinker(struct shrinker *shrinker) void register_shrinker_prepared(struct shrinker *shrinker) { - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_add_tail_rcu(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); } static int __register_shrinker(struct shrinker *shrinker) @@ -769,13 +769,13 @@ void unregister_shrinker(struct shrinker *shrinker) if (!(shrinker->flags & SHRINKER_REGISTERED)) return; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_del_rcu(&shrinker->list); shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); debugfs_entry = shrinker_debugfs_remove(shrinker); - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); -- GitLab From 611b9fd80fb53e79079744fb29d8c1363f4b5c02 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 13 Mar 2023 13:39:29 +0800 Subject: [PATCH 1512/5631] mm: memory-failure: directly use IS_ENABLED(CONFIG_HWPOISON_INJECT) It's more clear and simple to just use IS_ENABLED(CONFIG_HWPOISON_INJECT) to check whether or not to enable HWPoison injector module instead of CONFIG_HWPOISON_INJECT/CONFIG_HWPOISON_INJECT_MODULE. Link: https://lkml.kernel.org/r/20230313053929.84607-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: David Hildenbrand Acked-by: Naoya Horiguchi Cc: Miaohe Lin Signed-off-by: Andrew Morton --- mm/memory-failure.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fae9baf3be16..f761704d27d7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -168,7 +168,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo return true; } -#if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE) +#if IS_ENABLED(CONFIG_HWPOISON_INJECT) u32 hwpoison_filter_enable = 0; u32 hwpoison_filter_dev_major = ~0U; -- GitLab From 3c556d2425b04054e22045d4ef7d34f163b7a71a Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 15 Mar 2023 13:16:42 -0400 Subject: [PATCH 1513/5631] mm/thp: rename TRANSPARENT_HUGEPAGE_NEVER_DAX to _UNSUPPORTED TRANSPARENT_HUGEPAGE_NEVER_DAX has nothing to do with DAX. It's set when has_transparent_hugepage() returns false, checked in hugepage_vma_check() and will disable THP completely if false. Rename it to TRANSPARENT_HUGEPAGE_UNSUPPORTED to reflect its real purpose. [peterx@redhat.com: fix comment, per David] Link: https://lkml.kernel.org/r/ZBMzQW674oHQJV7F@x1n Link: https://lkml.kernel.org/r/20230315171642.1244625-1-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: Aneesh Kumar K.V Cc: Yang Shi Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 2 +- mm/huge_memory.c | 8 ++------ 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 70bd867eba94..9a3a3af2dd80 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -79,7 +79,7 @@ static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, } enum transparent_hugepage_flag { - TRANSPARENT_HUGEPAGE_NEVER_DAX, + TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0c1df321ad64..cbf095e7f059 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -88,7 +88,7 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags, /* * If the hardware/firmware marked hugepage support disabled. */ - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) return false; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ @@ -460,11 +460,7 @@ static int __init hugepage_init(void) struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { - /* - * Hardware doesn't support hugepages, hence disable - * DAX PMD support. - */ - transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_NEVER_DAX; + transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED; return -EINVAL; } -- GitLab From c73e435e9b754d43aa8925152caedd54758e55be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:44 +0100 Subject: [PATCH 1514/5631] clk: tegra: Don't warn three times about failure to unregister MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit tegra124_dfll_fcpu_remove() calls tegra_dfll_unregister() and the former emits an error message if the latter fails. In that case tegra_dfll_unregister() already printed an error message. Additionally tegra124_dfll_fcpu_remove() returns an error code which results in yet another warning emitted by platform_remove(). So drop the error message from tegra124_dfll_fcpu_remove() and let it return 0. (Retuning 0 has no side effect but suppressing the error message in platform_remove().) Also add two comments about exiting early being wrong. This is something that needs fixing separately. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-3-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-dfll.c | 5 ++++- drivers/clk/tegra/clk-tegra124-dfll-fcpu.c | 11 ++++++----- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c index 41433927b55c..58fa5a59e0c7 100644 --- a/drivers/clk/tegra/clk-dfll.c +++ b/drivers/clk/tegra/clk-dfll.c @@ -2081,7 +2081,10 @@ struct tegra_dfll_soc_data *tegra_dfll_unregister(struct platform_device *pdev) { struct tegra_dfll *td = platform_get_drvdata(pdev); - /* Try to prevent removal while the DFLL is active */ + /* + * Note that exiting early here doesn't prevent unbinding the driver. + * Exiting early here only leaks some resources. + */ if (td->mode != DFLL_DISABLED) { dev_err(&pdev->dev, "must disable DFLL before removing driver\n"); diff --git a/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c index 5e339ad0a97c..15c5e14dd82f 100644 --- a/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c +++ b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c @@ -616,12 +616,13 @@ static int tegra124_dfll_fcpu_remove(struct platform_device *pdev) { struct tegra_dfll_soc_data *soc; + /* + * Note that exiting early here is dangerous as after this function + * returns *soc is freed. + */ soc = tegra_dfll_unregister(pdev); - if (IS_ERR(soc)) { - dev_err(&pdev->dev, "failed to unregister DFLL: %ld\n", - PTR_ERR(soc)); - return PTR_ERR(soc); - } + if (IS_ERR(soc)) + return 0; tegra_cvb_remove_opp_table(soc->dev, soc->cvb, soc->max_freq); -- GitLab From b46d59cb18321705d7fe8cf84c20e01553116418 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:45 +0100 Subject: [PATCH 1515/5631] clk: xilinx: Drop if block with always false condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit xvcu_remove() is only called for a device after after xvcu_probe() completed successfully. In that case dev_set_drvdata() was called for that device with a non-NULL parameter, so platform_get_drvdata() won't return NULL and the if condition is never true. Drop the if, preparing a conversion to make platform driver's remove callback return void. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-4-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/xilinx/xlnx_vcu.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/xilinx/xlnx_vcu.c b/drivers/clk/xilinx/xlnx_vcu.c index d66b1315114e..54b44debfd3e 100644 --- a/drivers/clk/xilinx/xlnx_vcu.c +++ b/drivers/clk/xilinx/xlnx_vcu.c @@ -707,8 +707,6 @@ static int xvcu_remove(struct platform_device *pdev) struct xvcu_device *xvcu; xvcu = platform_get_drvdata(pdev); - if (!xvcu) - return -ENODEV; xvcu_unregister_clock_provider(xvcu); -- GitLab From b3438f55f06ef9e9449ef366ef531738c1cb74ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:46 +0100 Subject: [PATCH 1516/5631] clk: axs10x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-5-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/axs10x/i2s_pll_clock.c | 5 ++--- drivers/clk/axs10x/pll_clock.c | 5 ++--- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/clk/axs10x/i2s_pll_clock.c b/drivers/clk/axs10x/i2s_pll_clock.c index e1fda6ad5cd5..2334e6c334cf 100644 --- a/drivers/clk/axs10x/i2s_pll_clock.c +++ b/drivers/clk/axs10x/i2s_pll_clock.c @@ -198,10 +198,9 @@ static int i2s_pll_clk_probe(struct platform_device *pdev) return of_clk_add_provider(node, of_clk_src_simple_get, clk); } -static int i2s_pll_clk_remove(struct platform_device *pdev) +static void i2s_pll_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static const struct of_device_id i2s_pll_clk_id[] = { @@ -216,7 +215,7 @@ static struct platform_driver i2s_pll_clk_driver = { .of_match_table = i2s_pll_clk_id, }, .probe = i2s_pll_clk_probe, - .remove = i2s_pll_clk_remove, + .remove_new = i2s_pll_clk_remove, }; module_platform_driver(i2s_pll_clk_driver); diff --git a/drivers/clk/axs10x/pll_clock.c b/drivers/clk/axs10x/pll_clock.c index 90fb0e6ff573..dbbfa12e530d 100644 --- a/drivers/clk/axs10x/pll_clock.c +++ b/drivers/clk/axs10x/pll_clock.c @@ -257,10 +257,9 @@ static int axs10x_pll_clk_probe(struct platform_device *pdev) &pll_clk->hw); } -static int axs10x_pll_clk_remove(struct platform_device *pdev) +static void axs10x_pll_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static void __init of_axs10x_pll_clk_setup(struct device_node *node) @@ -332,7 +331,7 @@ static struct platform_driver axs10x_pll_clk_driver = { .of_match_table = axs10x_pll_clk_id, }, .probe = axs10x_pll_clk_probe, - .remove = axs10x_pll_clk_remove, + .remove_new = axs10x_pll_clk_remove, }; builtin_platform_driver(axs10x_pll_clk_driver); -- GitLab From 04d19184d266d40af5e77c2b90e1d2195c17e849 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:47 +0100 Subject: [PATCH 1517/5631] clk: bcm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-6-u.kleine-koenig@pengutronix.de Reviewed-by: Florian Fainelli Signed-off-by: Stephen Boyd --- drivers/clk/bcm/clk-bcm2711-dvp.c | 6 ++---- drivers/clk/bcm/clk-bcm63xx-gate.c | 6 ++---- drivers/clk/bcm/clk-raspberrypi.c | 6 ++---- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/clk/bcm/clk-bcm2711-dvp.c b/drivers/clk/bcm/clk-bcm2711-dvp.c index e63a42618ac2..e4fbbf3c40fe 100644 --- a/drivers/clk/bcm/clk-bcm2711-dvp.c +++ b/drivers/clk/bcm/clk-bcm2711-dvp.c @@ -92,15 +92,13 @@ static int clk_dvp_probe(struct platform_device *pdev) return ret; }; -static int clk_dvp_remove(struct platform_device *pdev) +static void clk_dvp_remove(struct platform_device *pdev) { struct clk_dvp *dvp = platform_get_drvdata(pdev); struct clk_hw_onecell_data *data = dvp->data; clk_hw_unregister_gate(data->hws[1]); clk_hw_unregister_gate(data->hws[0]); - - return 0; } static const struct of_device_id clk_dvp_dt_ids[] = { @@ -111,7 +109,7 @@ MODULE_DEVICE_TABLE(of, clk_dvp_dt_ids); static struct platform_driver clk_dvp_driver = { .probe = clk_dvp_probe, - .remove = clk_dvp_remove, + .remove_new = clk_dvp_remove, .driver = { .name = "brcm2711-dvp", .of_match_table = clk_dvp_dt_ids, diff --git a/drivers/clk/bcm/clk-bcm63xx-gate.c b/drivers/clk/bcm/clk-bcm63xx-gate.c index 89297c57881e..0769f98767da 100644 --- a/drivers/clk/bcm/clk-bcm63xx-gate.c +++ b/drivers/clk/bcm/clk-bcm63xx-gate.c @@ -541,7 +541,7 @@ static int clk_bcm63xx_probe(struct platform_device *pdev) return ret; } -static int clk_bcm63xx_remove(struct platform_device *pdev) +static void clk_bcm63xx_remove(struct platform_device *pdev) { struct clk_bcm63xx_hw *hw = platform_get_drvdata(pdev); int i; @@ -552,8 +552,6 @@ static int clk_bcm63xx_remove(struct platform_device *pdev) if (!IS_ERR(hw->data.hws[i])) clk_hw_unregister_gate(hw->data.hws[i]); } - - return 0; } static const struct of_device_id clk_bcm63xx_dt_ids[] = { @@ -570,7 +568,7 @@ static const struct of_device_id clk_bcm63xx_dt_ids[] = { static struct platform_driver clk_bcm63xx = { .probe = clk_bcm63xx_probe, - .remove = clk_bcm63xx_remove, + .remove_new = clk_bcm63xx_remove, .driver = { .name = "bcm63xx-clock", .of_match_table = clk_bcm63xx_dt_ids, diff --git a/drivers/clk/bcm/clk-raspberrypi.c b/drivers/clk/bcm/clk-raspberrypi.c index ce2f93479736..eb399a4d141b 100644 --- a/drivers/clk/bcm/clk-raspberrypi.c +++ b/drivers/clk/bcm/clk-raspberrypi.c @@ -439,13 +439,11 @@ static int raspberrypi_clk_probe(struct platform_device *pdev) return 0; } -static int raspberrypi_clk_remove(struct platform_device *pdev) +static void raspberrypi_clk_remove(struct platform_device *pdev) { struct raspberrypi_clk *rpi = platform_get_drvdata(pdev); platform_device_unregister(rpi->cpufreq); - - return 0; } static const struct of_device_id raspberrypi_clk_match[] = { @@ -460,7 +458,7 @@ static struct platform_driver raspberrypi_clk_driver = { .of_match_table = raspberrypi_clk_match, }, .probe = raspberrypi_clk_probe, - .remove = raspberrypi_clk_remove, + .remove_new = raspberrypi_clk_remove, }; module_platform_driver(raspberrypi_clk_driver); -- GitLab From 778dc8bb1dd44dd09c2da67a6cedebb2903e7945 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:48 +0100 Subject: [PATCH 1518/5631] clk: axi-clkgen: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-7-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-axi-clkgen.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c index ac6ff736ac8f..671bee55ceb3 100644 --- a/drivers/clk/clk-axi-clkgen.c +++ b/drivers/clk/clk-axi-clkgen.c @@ -557,11 +557,9 @@ static int axi_clkgen_probe(struct platform_device *pdev) &axi_clkgen->clk_hw); } -static int axi_clkgen_remove(struct platform_device *pdev) +static void axi_clkgen_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static const struct of_device_id axi_clkgen_ids[] = { @@ -583,7 +581,7 @@ static struct platform_driver axi_clkgen_driver = { .of_match_table = axi_clkgen_ids, }, .probe = axi_clkgen_probe, - .remove = axi_clkgen_remove, + .remove_new = axi_clkgen_remove, }; module_platform_driver(axi_clkgen_driver); -- GitLab From 1920aa93a8d09034f16f307c522792c1b5805116 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:49 +0100 Subject: [PATCH 1519/5631] clk: axm5516: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-8-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-axm5516.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk-axm5516.c b/drivers/clk/clk-axm5516.c index 07e80fe8c310..1dff2017ad9d 100644 --- a/drivers/clk/clk-axm5516.c +++ b/drivers/clk/clk-axm5516.c @@ -572,15 +572,14 @@ static int axmclk_probe(struct platform_device *pdev) return of_clk_add_hw_provider(dev->of_node, of_clk_axmclk_get, NULL); } -static int axmclk_remove(struct platform_device *pdev) +static void axmclk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static struct platform_driver axmclk_driver = { .probe = axmclk_probe, - .remove = axmclk_remove, + .remove_new = axmclk_remove, .driver = { .name = "clk-axm5516", .of_match_table = axmclk_match_table, -- GitLab From 27237f4b37b0ff8d8d48912780176c626c734720 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:50 +0100 Subject: [PATCH 1520/5631] clk: fixed-factor: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-9-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-fixed-factor.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index f734e34735a9..b3e66202b942 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -297,14 +297,12 @@ void __init of_fixed_factor_clk_setup(struct device_node *node) CLK_OF_DECLARE(fixed_factor_clk, "fixed-factor-clock", of_fixed_factor_clk_setup); -static int of_fixed_factor_clk_remove(struct platform_device *pdev) +static void of_fixed_factor_clk_remove(struct platform_device *pdev) { struct clk_hw *clk = platform_get_drvdata(pdev); of_clk_del_provider(pdev->dev.of_node); clk_hw_unregister_fixed_factor(clk); - - return 0; } static int of_fixed_factor_clk_probe(struct platform_device *pdev) @@ -336,7 +334,7 @@ static struct platform_driver of_fixed_factor_clk_driver = { .of_match_table = of_fixed_factor_clk_ids, }, .probe = of_fixed_factor_clk_probe, - .remove = of_fixed_factor_clk_remove, + .remove_new = of_fixed_factor_clk_remove, }; builtin_platform_driver(of_fixed_factor_clk_driver); #endif -- GitLab From 6f149b65891d7b6302c19ad6d0c44c89367b7e17 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:51 +0100 Subject: [PATCH 1521/5631] clk: fixed-mmio: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-10-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-fixed-mmio.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-fixed-mmio.c b/drivers/clk/clk-fixed-mmio.c index 5225d17d6b3f..7435055670d2 100644 --- a/drivers/clk/clk-fixed-mmio.c +++ b/drivers/clk/clk-fixed-mmio.c @@ -71,14 +71,12 @@ static int of_fixed_mmio_clk_probe(struct platform_device *pdev) return 0; } -static int of_fixed_mmio_clk_remove(struct platform_device *pdev) +static void of_fixed_mmio_clk_remove(struct platform_device *pdev) { struct clk_hw *clk = platform_get_drvdata(pdev); of_clk_del_provider(pdev->dev.of_node); clk_hw_unregister_fixed_rate(clk); - - return 0; } static const struct of_device_id of_fixed_mmio_clk_ids[] = { @@ -93,7 +91,7 @@ static struct platform_driver of_fixed_mmio_clk_driver = { .of_match_table = of_fixed_mmio_clk_ids, }, .probe = of_fixed_mmio_clk_probe, - .remove = of_fixed_mmio_clk_remove, + .remove_new = of_fixed_mmio_clk_remove, }; module_platform_driver(of_fixed_mmio_clk_driver); -- GitLab From 57e20d68f90fcd6276e7fc0e064ed0e27fc6c9ab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:52 +0100 Subject: [PATCH 1522/5631] clk: fixed-rate: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-11-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-fixed-rate.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c index 7d775954e26d..3481eb8cdeb3 100644 --- a/drivers/clk/clk-fixed-rate.c +++ b/drivers/clk/clk-fixed-rate.c @@ -196,14 +196,12 @@ void __init of_fixed_clk_setup(struct device_node *node) } CLK_OF_DECLARE(fixed_clk, "fixed-clock", of_fixed_clk_setup); -static int of_fixed_clk_remove(struct platform_device *pdev) +static void of_fixed_clk_remove(struct platform_device *pdev) { struct clk_hw *hw = platform_get_drvdata(pdev); of_clk_del_provider(pdev->dev.of_node); clk_hw_unregister_fixed_rate(hw); - - return 0; } static int of_fixed_clk_probe(struct platform_device *pdev) @@ -234,7 +232,7 @@ static struct platform_driver of_fixed_clk_driver = { .of_match_table = of_fixed_clk_ids, }, .probe = of_fixed_clk_probe, - .remove = of_fixed_clk_remove, + .remove_new = of_fixed_clk_remove, }; builtin_platform_driver(of_fixed_clk_driver); #endif -- GitLab From 601b2f146084bc16c5280a5d2945b2d13b4bc1fa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:53 +0100 Subject: [PATCH 1523/5631] clk: hsdk-pll: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-12-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-hsdk-pll.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk-hsdk-pll.c b/drivers/clk/clk-hsdk-pll.c index 60007b508590..766e139972fe 100644 --- a/drivers/clk/clk-hsdk-pll.c +++ b/drivers/clk/clk-hsdk-pll.c @@ -350,10 +350,9 @@ static int hsdk_pll_clk_probe(struct platform_device *pdev) &pll_clk->hw); } -static int hsdk_pll_clk_remove(struct platform_device *pdev) +static void hsdk_pll_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static void __init of_hsdk_pll_clk_setup(struct device_node *node) @@ -432,6 +431,6 @@ static struct platform_driver hsdk_pll_clk_driver = { .of_match_table = hsdk_pll_clk_id, }, .probe = hsdk_pll_clk_probe, - .remove = hsdk_pll_clk_remove, + .remove_new = hsdk_pll_clk_remove, }; builtin_platform_driver(hsdk_pll_clk_driver); -- GitLab From 8ffd6c28c95524e6e701a4210bf706e9f21060cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:54 +0100 Subject: [PATCH 1524/5631] clk: palmas: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-13-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-palmas.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk-palmas.c b/drivers/clk/clk-palmas.c index b8c3d0da1918..74a241b1e1f4 100644 --- a/drivers/clk/clk-palmas.c +++ b/drivers/clk/clk-palmas.c @@ -271,10 +271,9 @@ static int palmas_clks_probe(struct platform_device *pdev) return ret; } -static int palmas_clks_remove(struct platform_device *pdev) +static void palmas_clks_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - return 0; } static struct platform_driver palmas_clks_driver = { @@ -283,7 +282,7 @@ static struct platform_driver palmas_clks_driver = { .of_match_table = palmas_clks_of_match, }, .probe = palmas_clks_probe, - .remove = palmas_clks_remove, + .remove_new = palmas_clks_remove, }; module_platform_driver(palmas_clks_driver); -- GitLab From e72cdad50cdd1401525b37ac30519361d73fd139 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:55 +0100 Subject: [PATCH 1525/5631] clk: pwm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-14-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-pwm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-pwm.c b/drivers/clk/clk-pwm.c index da2c8eddfd9f..3dd2b83d0404 100644 --- a/drivers/clk/clk-pwm.c +++ b/drivers/clk/clk-pwm.c @@ -129,11 +129,9 @@ static int clk_pwm_probe(struct platform_device *pdev) return of_clk_add_hw_provider(node, of_clk_hw_simple_get, &clk_pwm->hw); } -static int clk_pwm_remove(struct platform_device *pdev) +static void clk_pwm_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static const struct of_device_id clk_pwm_dt_ids[] = { @@ -144,7 +142,7 @@ MODULE_DEVICE_TABLE(of, clk_pwm_dt_ids); static struct platform_driver clk_pwm_driver = { .probe = clk_pwm_probe, - .remove = clk_pwm_remove, + .remove_new = clk_pwm_remove, .driver = { .name = "pwm-clock", .of_match_table = clk_pwm_dt_ids, -- GitLab From 34014ff811c6e6423a0215e90fb5a02cf80d4e3c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:56 +0100 Subject: [PATCH 1526/5631] clk: s2mps11: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-15-u.kleine-koenig@pengutronix.de Reviewed-by: Krzysztof Kozlowski Signed-off-by: Stephen Boyd --- drivers/clk/clk-s2mps11.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c index a3e883a9f406..38c456540d1b 100644 --- a/drivers/clk/clk-s2mps11.c +++ b/drivers/clk/clk-s2mps11.c @@ -202,7 +202,7 @@ static int s2mps11_clk_probe(struct platform_device *pdev) return ret; } -static int s2mps11_clk_remove(struct platform_device *pdev) +static void s2mps11_clk_remove(struct platform_device *pdev) { struct s2mps11_clk *s2mps11_clks = platform_get_drvdata(pdev); int i; @@ -217,8 +217,6 @@ static int s2mps11_clk_remove(struct platform_device *pdev) continue; clkdev_drop(s2mps11_clks[i].lookup); } - - return 0; } static const struct platform_device_id s2mps11_clk_id[] = { @@ -265,7 +263,7 @@ static struct platform_driver s2mps11_clk_driver = { .name = "s2mps11-clk", }, .probe = s2mps11_clk_probe, - .remove = s2mps11_clk_remove, + .remove_new = s2mps11_clk_remove, .id_table = s2mps11_clk_id, }; module_platform_driver(s2mps11_clk_driver); -- GitLab From dd904848b484bd48dca843d6633472ea07062ac4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:57 +0100 Subject: [PATCH 1527/5631] clk: scpi: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-16-u.kleine-koenig@pengutronix.de Acked-by: Sudeep Holla Signed-off-by: Stephen Boyd --- drivers/clk/clk-scpi.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c index a39af7616b13..3fb4003453ee 100644 --- a/drivers/clk/clk-scpi.c +++ b/drivers/clk/clk-scpi.c @@ -246,7 +246,7 @@ static int scpi_clk_add(struct device *dev, struct device_node *np, return of_clk_add_hw_provider(np, scpi_of_clk_src_get, clk_data); } -static int scpi_clocks_remove(struct platform_device *pdev) +static void scpi_clocks_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *child, *np = dev->of_node; @@ -258,7 +258,6 @@ static int scpi_clocks_remove(struct platform_device *pdev) for_each_available_child_of_node(np, child) of_clk_del_provider(np); - return 0; } static int scpi_clocks_probe(struct platform_device *pdev) @@ -305,7 +304,7 @@ static struct platform_driver scpi_clocks_driver = { .of_match_table = scpi_clocks_ids, }, .probe = scpi_clocks_probe, - .remove = scpi_clocks_remove, + .remove_new = scpi_clocks_remove, }; module_platform_driver(scpi_clocks_driver); -- GitLab From 8ad00c147dc615db1dc8d85b6d34e09ee696404a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:58 +0100 Subject: [PATCH 1528/5631] clk: stm32mp1: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-17-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-stm32mp1.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/clk-stm32mp1.c b/drivers/clk/clk-stm32mp1.c index 01e5a466897f..939779f66867 100644 --- a/drivers/clk/clk-stm32mp1.c +++ b/drivers/clk/clk-stm32mp1.c @@ -2434,15 +2434,13 @@ static int stm32mp1_rcc_clocks_probe(struct platform_device *pdev) return ret; } -static int stm32mp1_rcc_clocks_remove(struct platform_device *pdev) +static void stm32mp1_rcc_clocks_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *child, *np = dev_of_node(dev); for_each_available_child_of_node(np, child) of_clk_del_provider(child); - - return 0; } static struct platform_driver stm32mp1_rcc_clocks_driver = { @@ -2451,7 +2449,7 @@ static struct platform_driver stm32mp1_rcc_clocks_driver = { .of_match_table = stm32mp1_match_data, }, .probe = stm32mp1_rcc_clocks_probe, - .remove = stm32mp1_rcc_clocks_remove, + .remove_new = stm32mp1_rcc_clocks_remove, }; static int __init stm32mp1_clocks_init(void) -- GitLab From bfa8370b283d5791e3667c0f8041a4b4f8af6c82 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:14:59 +0100 Subject: [PATCH 1529/5631] clk: hisilicon: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-18-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/hisilicon/clk-hi3519.c | 5 ++--- drivers/clk/hisilicon/clk-hi3559a.c | 5 ++--- drivers/clk/hisilicon/crg-hi3516cv300.c | 5 ++--- drivers/clk/hisilicon/crg-hi3798cv200.c | 5 ++--- 4 files changed, 8 insertions(+), 12 deletions(-) diff --git a/drivers/clk/hisilicon/clk-hi3519.c b/drivers/clk/hisilicon/clk-hi3519.c index ad0c7f350cf0..b871872d9960 100644 --- a/drivers/clk/hisilicon/clk-hi3519.c +++ b/drivers/clk/hisilicon/clk-hi3519.c @@ -162,13 +162,12 @@ static int hi3519_clk_probe(struct platform_device *pdev) return 0; } -static int hi3519_clk_remove(struct platform_device *pdev) +static void hi3519_clk_remove(struct platform_device *pdev) { struct hi3519_crg_data *crg = platform_get_drvdata(pdev); hisi_reset_exit(crg->rstc); hi3519_clk_unregister(pdev); - return 0; } @@ -180,7 +179,7 @@ MODULE_DEVICE_TABLE(of, hi3519_clk_match_table); static struct platform_driver hi3519_clk_driver = { .probe = hi3519_clk_probe, - .remove = hi3519_clk_remove, + .remove_new = hi3519_clk_remove, .driver = { .name = "hi3519-clk", .of_match_table = hi3519_clk_match_table, diff --git a/drivers/clk/hisilicon/clk-hi3559a.c b/drivers/clk/hisilicon/clk-hi3559a.c index 9ea1a80acbe8..4f97638809b7 100644 --- a/drivers/clk/hisilicon/clk-hi3559a.c +++ b/drivers/clk/hisilicon/clk-hi3559a.c @@ -810,18 +810,17 @@ static int hi3559av100_crg_probe(struct platform_device *pdev) return 0; } -static int hi3559av100_crg_remove(struct platform_device *pdev) +static void hi3559av100_crg_remove(struct platform_device *pdev) { struct hisi_crg_dev *crg = platform_get_drvdata(pdev); hisi_reset_exit(crg->rstc); crg->funcs->unregister_clks(pdev); - return 0; } static struct platform_driver hi3559av100_crg_driver = { .probe = hi3559av100_crg_probe, - .remove = hi3559av100_crg_remove, + .remove_new = hi3559av100_crg_remove, .driver = { .name = "hi3559av100-clock", .of_match_table = hi3559av100_crg_match_table, diff --git a/drivers/clk/hisilicon/crg-hi3516cv300.c b/drivers/clk/hisilicon/crg-hi3516cv300.c index 5d4e61c7a429..fe1bd3e3f988 100644 --- a/drivers/clk/hisilicon/crg-hi3516cv300.c +++ b/drivers/clk/hisilicon/crg-hi3516cv300.c @@ -284,18 +284,17 @@ static int hi3516cv300_crg_probe(struct platform_device *pdev) return 0; } -static int hi3516cv300_crg_remove(struct platform_device *pdev) +static void hi3516cv300_crg_remove(struct platform_device *pdev) { struct hisi_crg_dev *crg = platform_get_drvdata(pdev); hisi_reset_exit(crg->rstc); crg->funcs->unregister_clks(pdev); - return 0; } static struct platform_driver hi3516cv300_crg_driver = { .probe = hi3516cv300_crg_probe, - .remove = hi3516cv300_crg_remove, + .remove_new = hi3516cv300_crg_remove, .driver = { .name = "hi3516cv300-crg", .of_match_table = hi3516cv300_crg_match_table, diff --git a/drivers/clk/hisilicon/crg-hi3798cv200.c b/drivers/clk/hisilicon/crg-hi3798cv200.c index 08a19ba776e6..a0b16be1e25d 100644 --- a/drivers/clk/hisilicon/crg-hi3798cv200.c +++ b/drivers/clk/hisilicon/crg-hi3798cv200.c @@ -367,18 +367,17 @@ static int hi3798cv200_crg_probe(struct platform_device *pdev) return 0; } -static int hi3798cv200_crg_remove(struct platform_device *pdev) +static void hi3798cv200_crg_remove(struct platform_device *pdev) { struct hisi_crg_dev *crg = platform_get_drvdata(pdev); hisi_reset_exit(crg->rstc); crg->funcs->unregister_clks(pdev); - return 0; } static struct platform_driver hi3798cv200_crg_driver = { .probe = hi3798cv200_crg_probe, - .remove = hi3798cv200_crg_remove, + .remove_new = hi3798cv200_crg_remove, .driver = { .name = "hi3798cv200-crg", .of_match_table = hi3798cv200_crg_match_table, -- GitLab From 678471d83a568f3195b5b4cea7325297c56a0e37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:00 +0100 Subject: [PATCH 1530/5631] clk: keystone: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-19-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/keystone/sci-clk.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/keystone/sci-clk.c b/drivers/clk/keystone/sci-clk.c index d4b4e74e22da..910ecd58c4ca 100644 --- a/drivers/clk/keystone/sci-clk.c +++ b/drivers/clk/keystone/sci-clk.c @@ -689,16 +689,14 @@ static int ti_sci_clk_probe(struct platform_device *pdev) * via common clock framework. Any memory allocated for the device will * be free'd silently via the devm framework. Returns 0 always. */ -static int ti_sci_clk_remove(struct platform_device *pdev) +static void ti_sci_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static struct platform_driver ti_sci_clk_driver = { .probe = ti_sci_clk_probe, - .remove = ti_sci_clk_remove, + .remove_new = ti_sci_clk_remove, .driver = { .name = "ti-sci-clk", .of_match_table = of_match_ptr(ti_sci_clk_of_match), -- GitLab From 65ef13feb7ae5c0fe38c00db8ebffeb4f64a8297 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:02 +0100 Subject: [PATCH 1531/5631] clk: mmp: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-21-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/mmp/clk-audio.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/mmp/clk-audio.c b/drivers/clk/mmp/clk-audio.c index 7aa7f4a9564f..6fb1aa9487b5 100644 --- a/drivers/clk/mmp/clk-audio.c +++ b/drivers/clk/mmp/clk-audio.c @@ -384,12 +384,10 @@ static int mmp2_audio_clk_probe(struct platform_device *pdev) return ret; } -static int mmp2_audio_clk_remove(struct platform_device *pdev) +static void mmp2_audio_clk_remove(struct platform_device *pdev) { pm_clk_destroy(&pdev->dev); pm_runtime_disable(&pdev->dev); - - return 0; } #ifdef CONFIG_PM @@ -436,7 +434,7 @@ static struct platform_driver mmp2_audio_clk_driver = { .pm = &mmp2_audio_clk_pm_ops, }, .probe = mmp2_audio_clk_probe, - .remove = mmp2_audio_clk_remove, + .remove_new = mmp2_audio_clk_remove, }; module_platform_driver(mmp2_audio_clk_driver); -- GitLab From d9f139da6f245fd8a4c106ffa31e8017da797c07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:03 +0100 Subject: [PATCH 1532/5631] clk: mvebu: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-22-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/mvebu/armada-37xx-periph.c | 6 ++---- drivers/clk/mvebu/armada-37xx-tbg.c | 6 ++---- drivers/clk/mvebu/armada-37xx-xtal.c | 6 ++---- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index e3777ca65912..3ae6078f6ff7 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -781,7 +781,7 @@ static int armada_3700_periph_clock_probe(struct platform_device *pdev) return 0; } -static int armada_3700_periph_clock_remove(struct platform_device *pdev) +static void armada_3700_periph_clock_remove(struct platform_device *pdev) { struct clk_periph_driver_data *data = platform_get_drvdata(pdev); struct clk_hw_onecell_data *hw_data = data->hw_data; @@ -791,13 +791,11 @@ static int armada_3700_periph_clock_remove(struct platform_device *pdev) for (i = 0; i < hw_data->num; i++) clk_hw_unregister(hw_data->hws[i]); - - return 0; } static struct platform_driver armada_3700_periph_clock_driver = { .probe = armada_3700_periph_clock_probe, - .remove = armada_3700_periph_clock_remove, + .remove_new = armada_3700_periph_clock_remove, .driver = { .name = "marvell-armada-3700-periph-clock", .of_match_table = armada_3700_periph_clock_of_match, diff --git a/drivers/clk/mvebu/armada-37xx-tbg.c b/drivers/clk/mvebu/armada-37xx-tbg.c index fc403ad735ad..eccc1aeefbaf 100644 --- a/drivers/clk/mvebu/armada-37xx-tbg.c +++ b/drivers/clk/mvebu/armada-37xx-tbg.c @@ -126,7 +126,7 @@ static int armada_3700_tbg_clock_probe(struct platform_device *pdev) return of_clk_add_hw_provider(np, of_clk_hw_onecell_get, hw_tbg_data); } -static int armada_3700_tbg_clock_remove(struct platform_device *pdev) +static void armada_3700_tbg_clock_remove(struct platform_device *pdev) { int i; struct clk_hw_onecell_data *hw_tbg_data = platform_get_drvdata(pdev); @@ -134,8 +134,6 @@ static int armada_3700_tbg_clock_remove(struct platform_device *pdev) of_clk_del_provider(pdev->dev.of_node); for (i = 0; i < hw_tbg_data->num; i++) clk_hw_unregister_fixed_factor(hw_tbg_data->hws[i]); - - return 0; } static const struct of_device_id armada_3700_tbg_clock_of_match[] = { @@ -145,7 +143,7 @@ static const struct of_device_id armada_3700_tbg_clock_of_match[] = { static struct platform_driver armada_3700_tbg_clock_driver = { .probe = armada_3700_tbg_clock_probe, - .remove = armada_3700_tbg_clock_remove, + .remove_new = armada_3700_tbg_clock_remove, .driver = { .name = "marvell-armada-3700-tbg-clock", .of_match_table = armada_3700_tbg_clock_of_match, diff --git a/drivers/clk/mvebu/armada-37xx-xtal.c b/drivers/clk/mvebu/armada-37xx-xtal.c index 41271351cf1f..0e2e7d00ae11 100644 --- a/drivers/clk/mvebu/armada-37xx-xtal.c +++ b/drivers/clk/mvebu/armada-37xx-xtal.c @@ -65,11 +65,9 @@ static int armada_3700_xtal_clock_probe(struct platform_device *pdev) return ret; } -static int armada_3700_xtal_clock_remove(struct platform_device *pdev) +static void armada_3700_xtal_clock_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static const struct of_device_id armada_3700_xtal_clock_of_match[] = { @@ -79,7 +77,7 @@ static const struct of_device_id armada_3700_xtal_clock_of_match[] = { static struct platform_driver armada_3700_xtal_clock_driver = { .probe = armada_3700_xtal_clock_probe, - .remove = armada_3700_xtal_clock_remove, + .remove_new = armada_3700_xtal_clock_remove, .driver = { .name = "marvell-armada-3700-xtal-clock", .of_match_table = armada_3700_xtal_clock_of_match, -- GitLab From 0d65f746957bb7784574cb03a4014ee8305d7e69 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:07 +0100 Subject: [PATCH 1533/5631] clk: stm32: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-26-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/stm32/clk-stm32mp13.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/stm32/clk-stm32mp13.c b/drivers/clk/stm32/clk-stm32mp13.c index 1192eee8abe4..c4a737482fe5 100644 --- a/drivers/clk/stm32/clk-stm32mp13.c +++ b/drivers/clk/stm32/clk-stm32mp13.c @@ -1593,15 +1593,13 @@ static int stm32mp1_rcc_clocks_probe(struct platform_device *pdev) return ret; } -static int stm32mp1_rcc_clocks_remove(struct platform_device *pdev) +static void stm32mp1_rcc_clocks_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *child, *np = dev_of_node(dev); for_each_available_child_of_node(np, child) of_clk_del_provider(child); - - return 0; } static struct platform_driver stm32mp13_rcc_clocks_driver = { @@ -1610,7 +1608,7 @@ static struct platform_driver stm32mp13_rcc_clocks_driver = { .of_match_table = stm32mp13_match_data, }, .probe = stm32mp1_rcc_clocks_probe, - .remove = stm32mp1_rcc_clocks_remove, + .remove_new = stm32mp1_rcc_clocks_remove, }; static int __init stm32mp13_clocks_init(void) -- GitLab From 3fd43a2c3acdd4565f961afb3cf327af2a9c6af0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:08 +0100 Subject: [PATCH 1534/5631] clk: tegra: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-27-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-tegra124-dfll-fcpu.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c index 15c5e14dd82f..2a164e565c86 100644 --- a/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c +++ b/drivers/clk/tegra/clk-tegra124-dfll-fcpu.c @@ -612,7 +612,7 @@ static int tegra124_dfll_fcpu_probe(struct platform_device *pdev) return 0; } -static int tegra124_dfll_fcpu_remove(struct platform_device *pdev) +static void tegra124_dfll_fcpu_remove(struct platform_device *pdev) { struct tegra_dfll_soc_data *soc; @@ -622,11 +622,9 @@ static int tegra124_dfll_fcpu_remove(struct platform_device *pdev) */ soc = tegra_dfll_unregister(pdev); if (IS_ERR(soc)) - return 0; + return; tegra_cvb_remove_opp_table(soc->dev, soc->cvb, soc->max_freq); - - return 0; } static const struct dev_pm_ops tegra124_dfll_pm_ops = { @@ -637,7 +635,7 @@ static const struct dev_pm_ops tegra124_dfll_pm_ops = { static struct platform_driver tegra124_dfll_fcpu_driver = { .probe = tegra124_dfll_fcpu_probe, - .remove = tegra124_dfll_fcpu_remove, + .remove_new = tegra124_dfll_fcpu_remove, .driver = { .name = "tegra124-dfll", .of_match_table = tegra124_dfll_fcpu_of_match, -- GitLab From c8bb21be9fc48df65e25bea69400e84b8c1084f6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:09 +0100 Subject: [PATCH 1535/5631] clk: ti: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-28-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/ti/adpll.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/ti/adpll.c b/drivers/clk/ti/adpll.c index f5e7e2049241..6ecbba4342c5 100644 --- a/drivers/clk/ti/adpll.c +++ b/drivers/clk/ti/adpll.c @@ -931,13 +931,11 @@ static int ti_adpll_probe(struct platform_device *pdev) return err; } -static int ti_adpll_remove(struct platform_device *pdev) +static void ti_adpll_remove(struct platform_device *pdev) { struct ti_adpll_data *d = dev_get_drvdata(&pdev->dev); ti_adpll_free_resources(d); - - return 0; } static struct platform_driver ti_adpll_driver = { @@ -946,7 +944,7 @@ static struct platform_driver ti_adpll_driver = { .of_match_table = ti_adpll_match, }, .probe = ti_adpll_probe, - .remove = ti_adpll_remove, + .remove_new = ti_adpll_remove, }; static int __init ti_adpll_init(void) -- GitLab From 0d086cc521e71e2714f740e2d63060f51e5224e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:10 +0100 Subject: [PATCH 1536/5631] clk: uniphier: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-29-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/uniphier/clk-uniphier-core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c index 46c66fac48e6..92f4ddc593db 100644 --- a/drivers/clk/uniphier/clk-uniphier-core.c +++ b/drivers/clk/uniphier/clk-uniphier-core.c @@ -91,11 +91,9 @@ static int uniphier_clk_probe(struct platform_device *pdev) hw_data); } -static int uniphier_clk_remove(struct platform_device *pdev) +static void uniphier_clk_remove(struct platform_device *pdev) { of_clk_del_provider(pdev->dev.of_node); - - return 0; } static const struct of_device_id uniphier_clk_match[] = { @@ -220,7 +218,7 @@ static const struct of_device_id uniphier_clk_match[] = { static struct platform_driver uniphier_clk_driver = { .probe = uniphier_clk_probe, - .remove = uniphier_clk_remove, + .remove_new = uniphier_clk_remove, .driver = { .name = "uniphier-clk", .of_match_table = uniphier_clk_match, -- GitLab From 4690d24624e27fe5294185b5f7cf02df25c7d113 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:11 +0100 Subject: [PATCH 1537/5631] clk: x86: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-30-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/x86/clk-fch.c | 7 +++---- drivers/clk/x86/clk-pmc-atom.c | 5 ++--- 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/clk/x86/clk-fch.c b/drivers/clk/x86/clk-fch.c index fdc060e75839..aed7d22fae63 100644 --- a/drivers/clk/x86/clk-fch.c +++ b/drivers/clk/x86/clk-fch.c @@ -92,14 +92,14 @@ static int fch_clk_probe(struct platform_device *pdev) return 0; } -static int fch_clk_remove(struct platform_device *pdev) +static void fch_clk_remove(struct platform_device *pdev) { int i, clks; struct pci_dev *rdev; rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0)); if (!rdev) - return -ENODEV; + return; clks = pci_match_id(fch_pci_ids, rdev) ? CLK_MAX_FIXED : ST_MAX_CLKS; @@ -107,7 +107,6 @@ static int fch_clk_remove(struct platform_device *pdev) clk_hw_unregister(hws[i]); pci_dev_put(rdev); - return 0; } static struct platform_driver fch_clk_driver = { @@ -116,6 +115,6 @@ static struct platform_driver fch_clk_driver = { .suppress_bind_attrs = true, }, .probe = fch_clk_probe, - .remove = fch_clk_remove, + .remove_new = fch_clk_remove, }; builtin_platform_driver(fch_clk_driver); diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index e746e3f8d05a..2974dd0ec6f4 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -367,7 +367,7 @@ static int plt_clk_probe(struct platform_device *pdev) return err; } -static int plt_clk_remove(struct platform_device *pdev) +static void plt_clk_remove(struct platform_device *pdev) { struct clk_plt_data *data; @@ -377,7 +377,6 @@ static int plt_clk_remove(struct platform_device *pdev) clkdev_drop(data->mclk_lookup); plt_clk_unregister_loop(data, PMC_CLK_NUM); plt_clk_unregister_parents(data); - return 0; } static struct platform_driver plt_clk_driver = { @@ -385,6 +384,6 @@ static struct platform_driver plt_clk_driver = { .name = "clk-pmc-atom", }, .probe = plt_clk_probe, - .remove = plt_clk_remove, + .remove_new = plt_clk_remove, }; builtin_platform_driver(plt_clk_driver); -- GitLab From ce1c5f840fb7cf080523eb94396f0182ab74ac4f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Sun, 12 Mar 2023 17:15:12 +0100 Subject: [PATCH 1538/5631] clk: xilinx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230312161512.2715500-31-u.kleine-koenig@pengutronix.de Signed-off-by: Stephen Boyd --- drivers/clk/xilinx/clk-xlnx-clock-wizard.c | 6 ++---- drivers/clk/xilinx/xlnx_vcu.c | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c index eb1dfe7ecc1b..fa829c01a444 100644 --- a/drivers/clk/xilinx/clk-xlnx-clock-wizard.c +++ b/drivers/clk/xilinx/clk-xlnx-clock-wizard.c @@ -593,7 +593,7 @@ static int clk_wzrd_probe(struct platform_device *pdev) return ret; } -static int clk_wzrd_remove(struct platform_device *pdev) +static void clk_wzrd_remove(struct platform_device *pdev) { int i; struct clk_wzrd *clk_wzrd = platform_get_drvdata(pdev); @@ -611,8 +611,6 @@ static int clk_wzrd_remove(struct platform_device *pdev) } clk_disable_unprepare(clk_wzrd->axi_clk); - - return 0; } static const struct of_device_id clk_wzrd_ids[] = { @@ -630,7 +628,7 @@ static struct platform_driver clk_wzrd_driver = { .pm = &clk_wzrd_dev_pm_ops, }, .probe = clk_wzrd_probe, - .remove = clk_wzrd_remove, + .remove_new = clk_wzrd_remove, }; module_platform_driver(clk_wzrd_driver); diff --git a/drivers/clk/xilinx/xlnx_vcu.c b/drivers/clk/xilinx/xlnx_vcu.c index 54b44debfd3e..0786f15ebbe8 100644 --- a/drivers/clk/xilinx/xlnx_vcu.c +++ b/drivers/clk/xilinx/xlnx_vcu.c @@ -702,7 +702,7 @@ static int xvcu_probe(struct platform_device *pdev) * Return: Returns 0 on success * Negative error code otherwise */ -static int xvcu_remove(struct platform_device *pdev) +static void xvcu_remove(struct platform_device *pdev) { struct xvcu_device *xvcu; @@ -714,8 +714,6 @@ static int xvcu_remove(struct platform_device *pdev) regmap_write(xvcu->logicore_reg_ba, VCU_GASKET_INIT, 0); clk_disable_unprepare(xvcu->aclk); - - return 0; } static const struct of_device_id xvcu_of_id_table[] = { @@ -731,7 +729,7 @@ static struct platform_driver xvcu_driver = { .of_match_table = xvcu_of_id_table, }, .probe = xvcu_probe, - .remove = xvcu_remove, + .remove_new = xvcu_remove, }; module_platform_driver(xvcu_driver); -- GitLab From 75a2d4226b53710380d1017b3f4c88f937ddba78 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 09:45:37 +0100 Subject: [PATCH 1539/5631] driver core: class: mark the struct class for sysfs callbacks as constant struct class should never be modified in a sysfs callback as there is nothing in the structure to modify, and frankly, the structure is almost never used in a sysfs callback, so mark it as constant to allow struct class to be moved to read-only memory. While we are touching all class sysfs callbacks also mark the attribute as constant as it can not be modified. The bonding code still uses this structure so it can not be removed from the function callbacks. Cc: "David S. Miller" Cc: "Rafael J. Wysocki" Cc: Bartosz Golaszewski Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Jens Axboe Cc: Johannes Berg Cc: Linus Walleij Cc: Minchan Kim Cc: Miquel Raynal Cc: Namjae Jeon Cc: Paolo Abeni Cc: Russ Weight Cc: Sergey Senozhatsky Cc: Steve French Cc: Vignesh Raghavendra Cc: linux-cifs@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: linux-mtd@lists.infradead.org Cc: linux-rdma@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: netdev@vger.kernel.org Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/20230325084537.3622280-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/platforms/pseries/dlpar.c | 4 ++-- arch/powerpc/platforms/pseries/mobility.c | 4 ++-- drivers/base/class.c | 4 ++-- drivers/base/devcoredump.c | 4 ++-- drivers/base/firmware_loader/sysfs.c | 4 ++-- drivers/block/pktcdvd.c | 6 +++--- drivers/block/zram/zram_drv.c | 11 +++++------ drivers/gpio/gpiolib-sysfs.c | 8 ++++---- drivers/infiniband/core/user_mad.c | 4 ++-- drivers/mtd/ubi/build.c | 2 +- drivers/net/bonding/bond_sysfs.c | 18 +++++++++--------- drivers/s390/crypto/zcrypt_api.c | 8 ++++---- fs/ksmbd/server.c | 10 +++++----- include/linux/device/class.h | 9 +++++---- 14 files changed, 48 insertions(+), 48 deletions(-) diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 75ffdbcd2865..719c97a155ed 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -512,7 +512,7 @@ static int dlpar_parse_id_type(char **cmd, struct pseries_hp_errorlog *hp_elog) return 0; } -static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, +static ssize_t dlpar_store(const struct class *class, const struct class_attribute *attr, const char *buf, size_t count) { struct pseries_hp_errorlog hp_elog; @@ -551,7 +551,7 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr, return rc ? rc : count; } -static ssize_t dlpar_show(struct class *class, struct class_attribute *attr, +static ssize_t dlpar_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sprintf(buf, "%s\n", "memory,cpu"); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 643d309d1bd0..6b25642adfa0 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -787,8 +787,8 @@ int rtas_syscall_dispatch_ibm_suspend_me(u64 handle) return pseries_migrate_partition(handle); } -static ssize_t migration_store(struct class *class, - struct class_attribute *attr, const char *buf, +static ssize_t migration_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t count) { u64 streamid; diff --git a/drivers/base/class.c b/drivers/base/class.c index 8ae91e118827..04de20e0dba8 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -482,8 +482,8 @@ void class_interface_unregister(struct class_interface *class_intf) } EXPORT_SYMBOL_GPL(class_interface_unregister); -ssize_t show_class_attr_string(struct class *class, - struct class_attribute *attr, char *buf) +ssize_t show_class_attr_string(const struct class *class, + const struct class_attribute *attr, char *buf) { struct class_attribute_string *cs; diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 59aaf2e1375a..91536ee05f14 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -167,7 +167,7 @@ static int devcd_free(struct device *dev, void *data) return 0; } -static ssize_t disabled_show(struct class *class, struct class_attribute *attr, +static ssize_t disabled_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", devcd_disabled); @@ -197,7 +197,7 @@ static ssize_t disabled_show(struct class *class, struct class_attribute *attr, * so, above situation would not occur. */ -static ssize_t disabled_store(struct class *class, struct class_attribute *attr, +static ssize_t disabled_store(const struct class *class, const struct class_attribute *attr, const char *buf, size_t count) { long tmp = simple_strtol(buf, NULL, 10); diff --git a/drivers/base/firmware_loader/sysfs.c b/drivers/base/firmware_loader/sysfs.c index 56911d75b90a..c9c93b47d9a5 100644 --- a/drivers/base/firmware_loader/sysfs.c +++ b/drivers/base/firmware_loader/sysfs.c @@ -25,7 +25,7 @@ void __fw_load_abort(struct fw_priv *fw_priv) } #ifdef CONFIG_FW_LOADER_USER_HELPER -static ssize_t timeout_show(struct class *class, struct class_attribute *attr, +static ssize_t timeout_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", __firmware_loading_timeout()); @@ -44,7 +44,7 @@ static ssize_t timeout_show(struct class *class, struct class_attribute *attr, * * Note: zero means 'wait forever'. **/ -static ssize_t timeout_store(struct class *class, struct class_attribute *attr, +static ssize_t timeout_store(const struct class *class, const struct class_attribute *attr, const char *buf, size_t count) { int tmp_loading_timeout = simple_strtol(buf, NULL, 10); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 642e3377441a..ba9bbdef9ef5 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -343,7 +343,7 @@ static void class_pktcdvd_release(struct class *cls) kfree(cls); } -static ssize_t device_map_show(struct class *c, struct class_attribute *attr, +static ssize_t device_map_show(const struct class *c, const struct class_attribute *attr, char *data) { int n = 0; @@ -364,7 +364,7 @@ static ssize_t device_map_show(struct class *c, struct class_attribute *attr, } static CLASS_ATTR_RO(device_map); -static ssize_t add_store(struct class *c, struct class_attribute *attr, +static ssize_t add_store(const struct class *c, const struct class_attribute *attr, const char *buf, size_t count) { unsigned int major, minor; @@ -385,7 +385,7 @@ static ssize_t add_store(struct class *c, struct class_attribute *attr, } static CLASS_ATTR_WO(add); -static ssize_t remove_store(struct class *c, struct class_attribute *attr, +static ssize_t remove_store(const struct class *c, const struct class_attribute *attr, const char *buf, size_t count) { unsigned int major, minor; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index b7bb52f8dfbd..3feadfb96114 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2424,8 +2424,8 @@ static int zram_remove(struct zram *zram) * creates a new un-initialized zram device and returns back this device's * device_id (or an error code if it fails to create a new device). */ -static ssize_t hot_add_show(struct class *class, - struct class_attribute *attr, +static ssize_t hot_add_show(const struct class *class, + const struct class_attribute *attr, char *buf) { int ret; @@ -2438,11 +2438,10 @@ static ssize_t hot_add_show(struct class *class, return ret; return scnprintf(buf, PAGE_SIZE, "%d\n", ret); } -static struct class_attribute class_attr_hot_add = - __ATTR(hot_add, 0400, hot_add_show, NULL); +static CLASS_ATTR_RO(hot_add); -static ssize_t hot_remove_store(struct class *class, - struct class_attribute *attr, +static ssize_t hot_remove_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t count) { diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 774755052618..a895915affa5 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -426,8 +426,8 @@ ATTRIBUTE_GROUPS(gpiochip); * /sys/class/gpio/unexport ... write-only * integer N ... number of GPIO to unexport */ -static ssize_t export_store(struct class *class, - struct class_attribute *attr, +static ssize_t export_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t len) { long gpio; @@ -478,8 +478,8 @@ static ssize_t export_store(struct class *class, } static CLASS_ATTR_WO(export); -static ssize_t unexport_store(struct class *class, - struct class_attribute *attr, +static ssize_t unexport_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t len) { long gpio; diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f83954180a33..0e9e04f8c685 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -1229,8 +1229,8 @@ static char *umad_devnode(const struct device *dev, umode_t *mode) return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } -static ssize_t abi_version_show(struct class *class, - struct class_attribute *attr, char *buf) +static ssize_t abi_version_show(const struct class *class, + const struct class_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", IB_USER_MAD_ABI_VERSION); } diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index ae6d35e3da9c..32105bd35831 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -95,7 +95,7 @@ static DEFINE_SPINLOCK(ubi_devices_lock); /* "Show" method for files in '//class/ubi/' */ /* UBI version attribute ('//class/ubi/version') */ -static ssize_t version_show(struct class *class, struct class_attribute *attr, +static ssize_t version_show(const struct class *class, const struct class_attribute *attr, char *buf) { return sprintf(buf, "%d\n", UBI_VERSION); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8996bd0a194a..0bb59da24922 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -31,12 +31,12 @@ /* "show" function for the bond_masters attribute. * The class parameter is ignored. */ -static ssize_t bonding_show_bonds(struct class *cls, - struct class_attribute *attr, +static ssize_t bonding_show_bonds(const struct class *cls, + const struct class_attribute *attr, char *buf) { - struct bond_net *bn = - container_of(attr, struct bond_net, class_attr_bonding_masters); + const struct bond_net *bn = + container_of_const(attr, struct bond_net, class_attr_bonding_masters); int res = 0; struct bonding *bond; @@ -59,7 +59,7 @@ static ssize_t bonding_show_bonds(struct class *cls, return res; } -static struct net_device *bond_get_by_name(struct bond_net *bn, const char *ifname) +static struct net_device *bond_get_by_name(const struct bond_net *bn, const char *ifname) { struct bonding *bond; @@ -75,12 +75,12 @@ static struct net_device *bond_get_by_name(struct bond_net *bn, const char *ifna * * The class parameter is ignored. */ -static ssize_t bonding_store_bonds(struct class *cls, - struct class_attribute *attr, +static ssize_t bonding_store_bonds(const struct class *cls, + const struct class_attribute *attr, const char *buffer, size_t count) { - struct bond_net *bn = - container_of(attr, struct bond_net, class_attr_bonding_masters); + const struct bond_net *bn = + container_of_const(attr, struct bond_net, class_attr_bonding_masters); char command[IFNAMSIZ + 1] = {0, }; char *ifname; int rv, res = count; diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 582ac301d315..cff2eea88f98 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -340,8 +340,8 @@ static const struct attribute_group *zcdn_dev_attr_groups[] = { NULL }; -static ssize_t zcdn_create_store(struct class *class, - struct class_attribute *attr, +static ssize_t zcdn_create_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t count) { int rc; @@ -357,8 +357,8 @@ static ssize_t zcdn_create_store(struct class *class, static const struct class_attribute class_attr_zcdn_create = __ATTR(create, 0600, NULL, zcdn_create_store); -static ssize_t zcdn_destroy_store(struct class *class, - struct class_attribute *attr, +static ssize_t zcdn_destroy_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t count) { int rc; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index b5af3e43e677..c2c958a5423e 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -418,7 +418,7 @@ int server_queue_ctrl_reset_work(void) return __queue_ctrl_work(SERVER_CTRL_TYPE_RESET); } -static ssize_t stats_show(struct class *class, struct class_attribute *attr, +static ssize_t stats_show(const struct class *class, const struct class_attribute *attr, char *buf) { /* @@ -437,8 +437,8 @@ static ssize_t stats_show(struct class *class, struct class_attribute *attr, server_conf.ipc_last_active / HZ); } -static ssize_t kill_server_store(struct class *class, - struct class_attribute *attr, const char *buf, +static ssize_t kill_server_store(const struct class *class, + const struct class_attribute *attr, const char *buf, size_t len) { if (!sysfs_streq(buf, "hard")) @@ -458,7 +458,7 @@ static const char * const debug_type_strings[] = {"smb", "auth", "vfs", "oplock", "ipc", "conn", "rdma"}; -static ssize_t debug_show(struct class *class, struct class_attribute *attr, +static ssize_t debug_show(const struct class *class, const struct class_attribute *attr, char *buf) { ssize_t sz = 0; @@ -476,7 +476,7 @@ static ssize_t debug_show(struct class *class, struct class_attribute *attr, return sz; } -static ssize_t debug_store(struct class *class, struct class_attribute *attr, +static ssize_t debug_store(const struct class *class, const struct class_attribute *attr, const char *buf, size_t len) { int i; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 73436c578d37..b53728ca56fb 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -174,10 +174,10 @@ static inline struct device *class_find_device_by_acpi_dev(const struct class *c struct class_attribute { struct attribute attr; - ssize_t (*show)(struct class *class, struct class_attribute *attr, + ssize_t (*show)(const struct class *class, const struct class_attribute *attr, char *buf); - ssize_t (*store)(struct class *class, struct class_attribute *attr, - const char *buf, size_t count); + ssize_t (*store)(const struct class *class, const struct class_attribute *attr, + const char *buf, size_t count); }; #define CLASS_ATTR_RW(_name) \ @@ -217,7 +217,8 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, char *buf); +ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, + char *buf); struct class_interface { struct list_head node; -- GitLab From 884f8ce42ccec9d0bf11d8bf9f111e5961ca1c82 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 20:42:33 +0100 Subject: [PATCH 1540/5631] driver core: class: implement class_get/put without the private pointer. Much like what was done in commit 273afac615ad ("driver core: bus: implement bus_get/put() without the private pointer"), it is time to move the driver core away from using the internal private pointer in struct class in order to enable it to be always a constant and be placed in read-only memory in the future. First step in doing this is to create a helper function that turns a 'struct class' into 'struct subsys_private' called class_to_subsys(). class_to_subsys() walks the list of registered busses in the system and finds the matching one based on the pointer to the class itself. As this is a short list, and this function is not on any fast path, it should not be noticable. Implement class_get() and class_put() using this new helper function. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230325194234.46588-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 81 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 63 insertions(+), 18 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 04de20e0dba8..c53d6f98cfc6 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -20,8 +20,70 @@ #include #include "base.h" +/* /sys/class */ +static struct kset *class_kset; + #define to_class_attr(_attr) container_of(_attr, struct class_attribute, attr) +/** + * class_to_subsys - Turn a struct class into a struct subsys_private + * + * @class: pointer to the struct bus_type to look up + * + * The driver core internals need to work on the subsys_private structure, not + * the external struct class pointer. This function walks the list of + * registered classes in the system and finds the matching one and returns the + * internal struct subsys_private that relates to that class. + * + * Note, the reference count of the return value is INCREMENTED if it is not + * NULL. A call to subsys_put() must be done when finished with the pointer in + * order for it to be properly freed. + */ +static struct subsys_private *class_to_subsys(const struct class *class) +{ + struct subsys_private *sp = NULL; + struct kobject *kobj; + + if (!class || !class_kset) + return NULL; + + spin_lock(&class_kset->list_lock); + + if (list_empty(&class_kset->list)) + goto done; + + list_for_each_entry(kobj, &class_kset->list, entry) { + struct kset *kset = container_of(kobj, struct kset, kobj); + + sp = container_of_const(kset, struct subsys_private, subsys); + if (sp->class == class) + goto done; + } + sp = NULL; +done: + sp = subsys_get(sp); + spin_unlock(&class_kset->list_lock); + return sp; +} + +static const struct class *class_get(const struct class *class) +{ + struct subsys_private *sp = class_to_subsys(class); + + if (sp) + return class; + return NULL; +} + +static void class_put(const struct class *class) +{ + struct subsys_private *sp = class_to_subsys(class); + + /* two puts are required as the call to bus_to_subsys incremented it again */ + subsys_put(sp); + subsys_put(sp); +} + static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -83,10 +145,6 @@ static const struct kobj_type class_ktype = { .child_ns_type = class_child_ns_type, }; -/* Hotplug events for classes go to the class subsys */ -static struct kset *class_kset; - - int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { @@ -109,19 +167,6 @@ void class_remove_file_ns(const struct class *cls, const struct class_attribute } EXPORT_SYMBOL_GPL(class_remove_file_ns); -static struct class *class_get(struct class *cls) -{ - if (cls) - kset_get(&cls->p->subsys); - return cls; -} - -static void class_put(struct class *cls) -{ - if (cls) - kset_put(&cls->p->subsys); -} - static struct device *klist_class_to_dev(struct klist_node *n) { struct device_private *p = to_device_private_class(n); @@ -434,7 +479,7 @@ EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { - struct class *parent; + const struct class *parent; struct class_dev_iter iter; struct device *dev; -- GitLab From 7b884b7f24b42fa25e92ed724ad82f137610afaf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 25 Mar 2023 20:42:34 +0100 Subject: [PATCH 1541/5631] driver core: class.c: convert to only use class_to_subsys Now that class_to_subsys() can be used to get access to the internal class private pointer, convert the remaining few places in class.c that were accessing the pointer directly to use class_to_subsys() instead. By doing this, the need for class_get() and class_put() goes away as no one actually tries to increment the class structures anymore, only the internal dynamic one. Cc: "Rafael J. Wysocki" Link: https://lore.kernel.org/r/20230325194234.46588-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 113 +++++++++++++++++++++++-------------------- 1 file changed, 61 insertions(+), 52 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index c53d6f98cfc6..1f12bd5d56d9 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -66,24 +66,6 @@ static struct subsys_private *class_to_subsys(const struct class *class) return sp; } -static const struct class *class_get(const struct class *class) -{ - struct subsys_private *sp = class_to_subsys(class); - - if (sp) - return class; - return NULL; -} - -static void class_put(const struct class *class) -{ - struct subsys_private *sp = class_to_subsys(class); - - /* two puts are required as the call to bus_to_subsys incremented it again */ - subsys_put(sp); - subsys_put(sp); -} - static ssize_t class_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -148,13 +130,15 @@ static const struct kobj_type class_ktype = { int class_create_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { + struct subsys_private *sp = class_to_subsys(cls); int error; - if (cls) - error = sysfs_create_file_ns(&cls->p->subsys.kobj, - &attr->attr, ns); - else - error = -EINVAL; + if (!sp) + return -EINVAL; + + error = sysfs_create_file_ns(&sp->subsys.kobj, &attr->attr, ns); + subsys_put(sp); + return error; } EXPORT_SYMBOL_GPL(class_create_file_ns); @@ -162,8 +146,13 @@ EXPORT_SYMBOL_GPL(class_create_file_ns); void class_remove_file_ns(const struct class *cls, const struct class_attribute *attr, const void *ns) { - if (cls) - sysfs_remove_file_ns(&cls->p->subsys.kobj, &attr->attr, ns); + struct subsys_private *sp = class_to_subsys(cls); + + if (!sp) + return; + + sysfs_remove_file_ns(&sp->subsys.kobj, &attr->attr, ns); + subsys_put(sp); } EXPORT_SYMBOL_GPL(class_remove_file_ns); @@ -187,18 +176,6 @@ static void klist_class_dev_put(struct klist_node *n) put_device(dev); } -static int class_add_groups(const struct class *cls, - const struct attribute_group **groups) -{ - return sysfs_create_groups(&cls->p->subsys.kobj, groups); -} - -static void class_remove_groups(const struct class *cls, - const struct attribute_group **groups) -{ - return sysfs_remove_groups(&cls->p->subsys.kobj, groups); -} - int class_register(struct class *cls) { struct subsys_private *cp; @@ -235,8 +212,7 @@ int class_register(struct class *cls) if (error) goto err_out; - error = class_add_groups(class_get(cls), cls->class_groups); - class_put(cls); + error = sysfs_create_groups(&cp->subsys.kobj, cls->class_groups); if (error) { kobject_del(&cp->subsys.kobj); kfree_const(cp->subsys.kobj.name); @@ -253,9 +229,16 @@ EXPORT_SYMBOL_GPL(class_register); void class_unregister(const struct class *cls) { + struct subsys_private *sp = class_to_subsys(cls); + + if (!sp) + return; + pr_debug("device class '%s': unregistering\n", cls->name); - class_remove_groups(cls, cls->class_groups); - kset_unregister(&cls->p->subsys); + + sysfs_remove_groups(&sp->subsys.kobj, cls->class_groups); + kset_unregister(&sp->subsys); + subsys_put(sp); } EXPORT_SYMBOL_GPL(class_unregister); @@ -334,11 +317,15 @@ EXPORT_SYMBOL_GPL(class_destroy); void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, const struct device *start, const struct device_type *type) { + struct subsys_private *sp = class_to_subsys(class); struct klist_node *start_knode = NULL; + if (!sp) + return; + if (start) start_knode = &start->p->knode_class; - klist_iter_init_node(&class->p->klist_devices, &iter->ki, start_knode); + klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -405,13 +392,14 @@ EXPORT_SYMBOL_GPL(class_dev_iter_exit); int class_for_each_device(const struct class *class, const struct device *start, void *data, int (*fn)(struct device *, void *)) { + struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; int error = 0; if (!class) return -EINVAL; - if (!class->p) { + if (!sp) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return -EINVAL; @@ -424,6 +412,7 @@ int class_for_each_device(const struct class *class, const struct device *start, break; } class_dev_iter_exit(&iter); + subsys_put(sp); return error; } @@ -453,12 +442,13 @@ struct device *class_find_device(const struct class *class, const struct device const void *data, int (*match)(struct device *, const void *)) { + struct subsys_private *sp = class_to_subsys(class); struct class_dev_iter iter; struct device *dev; if (!class) return NULL; - if (!class->p) { + if (!sp) { WARN(1, "%s called for class '%s' before it was initialized", __func__, class->name); return NULL; @@ -472,6 +462,7 @@ struct device *class_find_device(const struct class *class, const struct device } } class_dev_iter_exit(&iter); + subsys_put(sp); return dev; } @@ -479,6 +470,7 @@ EXPORT_SYMBOL_GPL(class_find_device); int class_interface_register(struct class_interface *class_intf) { + struct subsys_private *sp; const struct class *parent; struct class_dev_iter iter; struct device *dev; @@ -486,19 +478,25 @@ int class_interface_register(struct class_interface *class_intf) if (!class_intf || !class_intf->class) return -ENODEV; - parent = class_get(class_intf->class); - if (!parent) + parent = class_intf->class; + sp = class_to_subsys(parent); + if (!sp) return -EINVAL; - mutex_lock(&parent->p->mutex); - list_add_tail(&class_intf->node, &parent->p->interfaces); + /* + * Reference in sp is now incremented and will be dropped when + * the interface is removed in the call to class_interface_unregister() + */ + + mutex_lock(&sp->mutex); + list_add_tail(&class_intf->node, &sp->interfaces); if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) class_intf->add_dev(dev, class_intf); class_dev_iter_exit(&iter); } - mutex_unlock(&parent->p->mutex); + mutex_unlock(&sp->mutex); return 0; } @@ -506,6 +504,7 @@ EXPORT_SYMBOL_GPL(class_interface_register); void class_interface_unregister(struct class_interface *class_intf) { + struct subsys_private *sp; struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; @@ -513,7 +512,11 @@ void class_interface_unregister(struct class_interface *class_intf) if (!parent) return; - mutex_lock(&parent->p->mutex); + sp = class_to_subsys(parent); + if (!sp) + return; + + mutex_lock(&sp->mutex); list_del_init(&class_intf->node); if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); @@ -521,9 +524,15 @@ void class_interface_unregister(struct class_interface *class_intf) class_intf->remove_dev(dev, class_intf); class_dev_iter_exit(&iter); } - mutex_unlock(&parent->p->mutex); + mutex_unlock(&sp->mutex); - class_put(parent); + /* + * Decrement the reference count twice, once for the class_to_subsys() + * call in the start of this function, and the second one from the + * reference increment in class_interface_register() + */ + subsys_put(sp); + subsys_put(sp); } EXPORT_SYMBOL_GPL(class_interface_unregister); -- GitLab From 0d6a119cecd7ffa059970dbc5b557bfce737945f Mon Sep 17 00:00:00 2001 From: Aswath Govindraju Date: Fri, 24 Mar 2023 15:18:53 +0200 Subject: [PATCH 1542/5631] usb: typec: tps6598x: Add support for polling interrupts status Some development boards don't have the interrupt line connected. In such cases we can resort to polling the interrupt status. Signed-off-by: Aswath Govindraju Signed-off-by: Roger Quadros Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230324131853.41102-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 41 ++++++++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 5 deletions(-) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index af6ecb54b52c..8b075ca82ef6 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "tps6598x.h" #include "trace.h" @@ -97,6 +98,8 @@ struct tps6598x { int wakeup; u16 pwr_status; + struct delayed_work wq_poll; + irq_handler_t irq_handler; }; static enum power_supply_property tps6598x_psy_props[] = { @@ -558,6 +561,18 @@ static irqreturn_t tps6598x_interrupt(int irq, void *data) return IRQ_NONE; } +/* Time interval for Polling */ +#define POLL_INTERVAL 500 /* msecs */ +static void tps6598x_poll_work(struct work_struct *work) +{ + struct tps6598x *tps = container_of(to_delayed_work(work), + struct tps6598x, wq_poll); + + tps->irq_handler(0, tps); + queue_delayed_work(system_power_efficient_wq, + &tps->wq_poll, msecs_to_jiffies(POLL_INTERVAL)); +} + static int tps6598x_check_mode(struct tps6598x *tps) { char mode[5] = { }; @@ -736,6 +751,7 @@ static int tps6598x_probe(struct i2c_client *client) TPS_REG_INT_PLUG_EVENT; } + tps->irq_handler = irq_handler; /* Make sure the controller has application firmware running */ ret = tps6598x_check_mode(tps); if (ret) @@ -827,10 +843,18 @@ static int tps6598x_probe(struct i2c_client *client) dev_err(&client->dev, "failed to register partner\n"); } - ret = devm_request_threaded_irq(&client->dev, client->irq, NULL, - irq_handler, - IRQF_SHARED | IRQF_ONESHOT, - dev_name(&client->dev), tps); + if (client->irq) { + ret = devm_request_threaded_irq(&client->dev, client->irq, NULL, + irq_handler, + IRQF_SHARED | IRQF_ONESHOT, + dev_name(&client->dev), tps); + } else { + dev_warn(tps->dev, "Unable to find the interrupt, switching to polling\n"); + INIT_DELAYED_WORK(&tps->wq_poll, tps6598x_poll_work); + queue_delayed_work(system_power_efficient_wq, &tps->wq_poll, + msecs_to_jiffies(POLL_INTERVAL)); + } + if (ret) goto err_disconnect; @@ -838,7 +862,7 @@ static int tps6598x_probe(struct i2c_client *client) fwnode_handle_put(fwnode); tps->wakeup = device_property_read_bool(tps->dev, "wakeup-source"); - if (tps->wakeup) { + if (tps->wakeup && client->irq) { device_init_wakeup(&client->dev, true); enable_irq_wake(client->irq); } @@ -877,6 +901,9 @@ static int __maybe_unused tps6598x_suspend(struct device *dev) enable_irq_wake(client->irq); } + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + return 0; } @@ -890,6 +917,10 @@ static int __maybe_unused tps6598x_resume(struct device *dev) enable_irq(client->irq); } + if (client->irq) + queue_delayed_work(system_power_efficient_wq, &tps->wq_poll, + msecs_to_jiffies(POLL_INTERVAL)); + return 0; } -- GitLab From 7bf1c56a90decd3bec4d49815289d2e40bb771ae Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Thu, 9 Mar 2023 10:58:25 +0000 Subject: [PATCH 1543/5631] usb: gadget: uvc: Make bmControls attr read/write For the Processing Unit and Camera Terminal descriptors defined in the UVC Gadget we currently hard-code values into their bmControls fields, which enumerates which controls the gadget is able to support. This isn't appropriate since only the userspace companion program to the kernel driver will know which controls are supported. Make the configfs attributes that point to those fields read/write so userspace can set them to appropriate values. Document the new behaviour at the same time so the functionality is clear. Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20230309105825.216745-1-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- .../ABI/testing/configfs-usb-gadget-uvc | 4 +- Documentation/usb/gadget_uvc.rst | 28 ++++ drivers/usb/gadget/function/uvc_configfs.c | 121 +++++++++++++++++- 3 files changed, 149 insertions(+), 4 deletions(-) diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc index 80b98a4a4d0f..4feb692c4c1d 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-uvc +++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc @@ -76,7 +76,7 @@ Date: Dec 2014 KernelVersion: 4.0 Description: Default camera terminal descriptors - All attributes read only: + All attributes read only except bmControls, which is read/write: ======================== ==================================== bmControls bitmap specifying which controls are @@ -101,7 +101,7 @@ Date: Dec 2014 KernelVersion: 4.0 Description: Default processing unit descriptors - All attributes read only: + All attributes read only except bmControls, which is read/write: =============== ======================================== iProcessing index of string descriptor diff --git a/Documentation/usb/gadget_uvc.rst b/Documentation/usb/gadget_uvc.rst index 6d22faceb1a0..62bd81ba3dd1 100644 --- a/Documentation/usb/gadget_uvc.rst +++ b/Documentation/usb/gadget_uvc.rst @@ -275,6 +275,34 @@ out with 0x00, for example: bNrInPins and baSourceID function in the same way. +Configuring Supported Controls for Camera Terminal and Processing Unit +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The Camera Terminal and Processing Units in the UVC chain also have bmControls +attributes which function similarly to the same field in an Extension Unit. +Unlike XUs however, the meaning of the bitflag for these units is defined in +the UVC specification; you should consult the "Camera Terminal Descriptor" and +"Processing Unit Descriptor" sections for an enumeration of the flags. + +.. code-block:: bash + + # Set the Processing Unit's bmControls, flagging Brightness, Contrast + # and Hue as available controls: + echo 0x05 > $FUNCTION/control/processing/default/bmControls + + # Set the Camera Terminal's bmControls, flagging Focus Absolute and + # Focus Relative as available controls: + echo 0x60 > $FUNCTION/control/terminal/camera/default/bmControls + +If you do not set these fields then by default the Auto-Exposure Mode control +for the Camera Terminal and the Brightness control for the Processing Unit will +be flagged as available; if they are not supported you should set the field to +0x00. + +Note that the size of the bmControls field for a Camera Terminal or Processing +Unit is fixed by the UVC specification, and so the bControlSize attribute is +read-only here. + Custom Strings Support ~~~~~~~~~~~~~~~~~~~~~~ diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 62b759bb7613..9bf0e985acfa 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -334,6 +334,64 @@ UVCG_DEFAULT_PROCESSING_ATTR(i_processing, iProcessing, 8); #undef UVCG_DEFAULT_PROCESSING_ATTR +static ssize_t uvcg_default_processing_bm_controls_store( + struct config_item *item, const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct mutex *su_mutex = &group->cg_subsys->su_mutex; + struct uvc_processing_unit_descriptor *pd; + struct config_item *opts_item; + struct f_uvc_opts *opts; + u8 *bm_controls, *tmp; + unsigned int i; + int ret, n = 0; + + mutex_lock(su_mutex); + + opts_item = group->cg_item.ci_parent->ci_parent->ci_parent; + opts = to_f_uvc_opts(opts_item); + pd = &opts->uvc_processing; + + mutex_lock(&opts->lock); + if (opts->refcnt) { + ret = -EBUSY; + goto unlock; + } + + ret = __uvcg_iter_item_entries(page, len, __uvcg_count_item_entries, &n, + sizeof(u8)); + if (ret) + goto unlock; + + if (n > pd->bControlSize) { + ret = -EINVAL; + goto unlock; + } + + tmp = bm_controls = kcalloc(n, sizeof(u8), GFP_KERNEL); + if (!bm_controls) { + ret = -ENOMEM; + goto unlock; + } + + ret = __uvcg_iter_item_entries(page, len, __uvcg_fill_item_entries, &tmp, + sizeof(u8)); + if (ret) + goto free_mem; + + for (i = 0; i < n; i++) + pd->bmControls[i] = bm_controls[i]; + + ret = len; + +free_mem: + kfree(bm_controls); +unlock: + mutex_unlock(&opts->lock); + mutex_unlock(su_mutex); + return ret; +} + static ssize_t uvcg_default_processing_bm_controls_show( struct config_item *item, char *page) { @@ -363,7 +421,7 @@ static ssize_t uvcg_default_processing_bm_controls_show( return result; } -UVC_ATTR_RO(uvcg_default_processing_, bm_controls, bmControls); +UVC_ATTR(uvcg_default_processing_, bm_controls, bmControls); static struct configfs_attribute *uvcg_default_processing_attrs[] = { &uvcg_default_processing_attr_b_unit_id, @@ -445,6 +503,65 @@ UVCG_DEFAULT_CAMERA_ATTR(w_ocular_focal_length, wOcularFocalLength, #undef UVCG_DEFAULT_CAMERA_ATTR +static ssize_t uvcg_default_camera_bm_controls_store( + struct config_item *item, const char *page, size_t len) +{ + struct config_group *group = to_config_group(item); + struct mutex *su_mutex = &group->cg_subsys->su_mutex; + struct uvc_camera_terminal_descriptor *cd; + struct config_item *opts_item; + struct f_uvc_opts *opts; + u8 *bm_controls, *tmp; + unsigned int i; + int ret, n = 0; + + mutex_lock(su_mutex); + + opts_item = group->cg_item.ci_parent->ci_parent->ci_parent-> + ci_parent; + opts = to_f_uvc_opts(opts_item); + cd = &opts->uvc_camera_terminal; + + mutex_lock(&opts->lock); + if (opts->refcnt) { + ret = -EBUSY; + goto unlock; + } + + ret = __uvcg_iter_item_entries(page, len, __uvcg_count_item_entries, &n, + sizeof(u8)); + if (ret) + goto unlock; + + if (n > cd->bControlSize) { + ret = -EINVAL; + goto unlock; + } + + tmp = bm_controls = kcalloc(n, sizeof(u8), GFP_KERNEL); + if (!bm_controls) { + ret = -ENOMEM; + goto unlock; + } + + ret = __uvcg_iter_item_entries(page, len, __uvcg_fill_item_entries, &tmp, + sizeof(u8)); + if (ret) + goto free_mem; + + for (i = 0; i < n; i++) + cd->bmControls[i] = bm_controls[i]; + + ret = len; + +free_mem: + kfree(bm_controls); +unlock: + mutex_unlock(&opts->lock); + mutex_unlock(su_mutex); + return ret; +} + static ssize_t uvcg_default_camera_bm_controls_show( struct config_item *item, char *page) { @@ -474,7 +591,7 @@ static ssize_t uvcg_default_camera_bm_controls_show( return result; } -UVC_ATTR_RO(uvcg_default_camera_, bm_controls, bmControls); +UVC_ATTR(uvcg_default_camera_, bm_controls, bmControls); static struct configfs_attribute *uvcg_default_camera_attrs[] = { &uvcg_default_camera_attr_b_terminal_id, -- GitLab From f54134b3fc7954dbaa4da42198286e49bcb48ed7 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 27 Mar 2023 18:12:15 +0800 Subject: [PATCH 1544/5631] usb: gadget: ffs: remove ENTER() macro ENTER() used to show function name which called during runtime, ftrace can be used to get same information, let's remove it. Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/1679911940-4727-1-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_fs.c | 94 ------------------------------ drivers/usb/gadget/function/u_fs.h | 2 - drivers/usb/gadget/legacy/g_ffs.c | 9 --- 3 files changed, 105 deletions(-) diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index a277c70aac84..8830847fbf97 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -335,8 +335,6 @@ static ssize_t ffs_ep0_write(struct file *file, const char __user *buf, ssize_t ret; char *data; - ENTER(); - /* Fast check if setup was canceled */ if (ffs_setup_state_clear_cancelled(ffs) == FFS_SETUP_CANCELLED) return -EIDRM; @@ -512,8 +510,6 @@ static ssize_t ffs_ep0_read(struct file *file, char __user *buf, size_t n; int ret; - ENTER(); - /* Fast check if setup was canceled */ if (ffs_setup_state_clear_cancelled(ffs) == FFS_SETUP_CANCELLED) return -EIDRM; @@ -612,8 +608,6 @@ static int ffs_ep0_open(struct inode *inode, struct file *file) { struct ffs_data *ffs = inode->i_private; - ENTER(); - if (ffs->state == FFS_CLOSING) return -EBUSY; @@ -627,8 +621,6 @@ static int ffs_ep0_release(struct inode *inode, struct file *file) { struct ffs_data *ffs = file->private_data; - ENTER(); - ffs_data_closed(ffs); return 0; @@ -640,8 +632,6 @@ static long ffs_ep0_ioctl(struct file *file, unsigned code, unsigned long value) struct usb_gadget *gadget = ffs->gadget; long ret; - ENTER(); - if (code == FUNCTIONFS_INTERFACE_REVMAP) { struct ffs_function *func = ffs->func; ret = func ? ffs_func_revmap_intf(func, value) : -ENODEV; @@ -715,7 +705,6 @@ static void ffs_epfile_io_complete(struct usb_ep *_ep, struct usb_request *req) { struct ffs_io_data *io_data = req->context; - ENTER(); if (req->status) io_data->status = req->status; else @@ -856,8 +845,6 @@ static void ffs_epfile_async_io_complete(struct usb_ep *_ep, struct ffs_io_data *io_data = req->context; struct ffs_data *ffs = io_data->ffs; - ENTER(); - io_data->status = req->status ? req->status : req->actual; usb_ep_free_request(_ep, req); @@ -1161,8 +1148,6 @@ ffs_epfile_open(struct inode *inode, struct file *file) { struct ffs_epfile *epfile = inode->i_private; - ENTER(); - if (WARN_ON(epfile->ffs->state != FFS_ACTIVE)) return -ENODEV; @@ -1179,8 +1164,6 @@ static int ffs_aio_cancel(struct kiocb *kiocb) unsigned long flags; int value; - ENTER(); - spin_lock_irqsave(&epfile->ffs->eps_lock, flags); if (io_data && io_data->ep && io_data->req) @@ -1198,8 +1181,6 @@ static ssize_t ffs_epfile_write_iter(struct kiocb *kiocb, struct iov_iter *from) struct ffs_io_data io_data, *p = &io_data; ssize_t res; - ENTER(); - if (!is_sync_kiocb(kiocb)) { p = kzalloc(sizeof(io_data), GFP_KERNEL); if (!p) @@ -1235,8 +1216,6 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) struct ffs_io_data io_data, *p = &io_data; ssize_t res; - ENTER(); - if (!is_sync_kiocb(kiocb)) { p = kzalloc(sizeof(io_data), GFP_KERNEL); if (!p) @@ -1284,8 +1263,6 @@ ffs_epfile_release(struct inode *inode, struct file *file) { struct ffs_epfile *epfile = inode->i_private; - ENTER(); - __ffs_epfile_read_buffer_free(epfile); ffs_data_closed(epfile->ffs); @@ -1299,8 +1276,6 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, struct ffs_ep *ep; int ret; - ENTER(); - if (WARN_ON(epfile->ffs->state != FFS_ACTIVE)) return -ENODEV; @@ -1399,8 +1374,6 @@ ffs_sb_make_inode(struct super_block *sb, void *data, { struct inode *inode; - ENTER(); - inode = new_inode(sb); if (inode) { @@ -1432,8 +1405,6 @@ static struct dentry *ffs_sb_create_file(struct super_block *sb, struct dentry *dentry; struct inode *inode; - ENTER(); - dentry = d_alloc_name(sb->s_root, name); if (!dentry) return NULL; @@ -1468,8 +1439,6 @@ static int ffs_sb_fill(struct super_block *sb, struct fs_context *fc) struct inode *inode; struct ffs_data *ffs = data->ffs_data; - ENTER(); - ffs->sb = sb; data->ffs_data = NULL; sb->s_fs_info = ffs; @@ -1521,8 +1490,6 @@ static int ffs_fs_parse_param(struct fs_context *fc, struct fs_parameter *param) struct fs_parse_result result; int opt; - ENTER(); - opt = fs_parse(fc, ffs_fs_fs_parameters, param, &result); if (opt < 0) return opt; @@ -1572,8 +1539,6 @@ static int ffs_fs_get_tree(struct fs_context *fc) struct ffs_data *ffs; int ret; - ENTER(); - if (!fc->source) return invalf(fc, "No source specified"); @@ -1640,8 +1605,6 @@ static int ffs_fs_init_fs_context(struct fs_context *fc) static void ffs_fs_kill_sb(struct super_block *sb) { - ENTER(); - kill_litter_super(sb); if (sb->s_fs_info) ffs_data_closed(sb->s_fs_info); @@ -1663,8 +1626,6 @@ static int functionfs_init(void) { int ret; - ENTER(); - ret = register_filesystem(&ffs_fs_type); if (!ret) pr_info("file system registered\n"); @@ -1676,8 +1637,6 @@ static int functionfs_init(void) static void functionfs_cleanup(void) { - ENTER(); - pr_info("unloading\n"); unregister_filesystem(&ffs_fs_type); } @@ -1690,15 +1649,11 @@ static void ffs_data_reset(struct ffs_data *ffs); static void ffs_data_get(struct ffs_data *ffs) { - ENTER(); - refcount_inc(&ffs->ref); } static void ffs_data_opened(struct ffs_data *ffs) { - ENTER(); - refcount_inc(&ffs->ref); if (atomic_add_return(1, &ffs->opened) == 1 && ffs->state == FFS_DEACTIVATED) { @@ -1709,8 +1664,6 @@ static void ffs_data_opened(struct ffs_data *ffs) static void ffs_data_put(struct ffs_data *ffs) { - ENTER(); - if (refcount_dec_and_test(&ffs->ref)) { pr_info("%s(): freeing\n", __func__); ffs_data_clear(ffs); @@ -1729,8 +1682,6 @@ static void ffs_data_closed(struct ffs_data *ffs) struct ffs_epfile *epfiles; unsigned long flags; - ENTER(); - if (atomic_dec_and_test(&ffs->opened)) { if (ffs->no_disconnect) { ffs->state = FFS_DEACTIVATED; @@ -1765,8 +1716,6 @@ static struct ffs_data *ffs_data_new(const char *dev_name) if (!ffs) return NULL; - ENTER(); - ffs->io_completion_wq = alloc_ordered_workqueue("%s", 0, dev_name); if (!ffs->io_completion_wq) { kfree(ffs); @@ -1793,8 +1742,6 @@ static void ffs_data_clear(struct ffs_data *ffs) struct ffs_epfile *epfiles; unsigned long flags; - ENTER(); - ffs_closed(ffs); BUG_ON(ffs->gadget); @@ -1826,8 +1773,6 @@ static void ffs_data_clear(struct ffs_data *ffs) static void ffs_data_reset(struct ffs_data *ffs) { - ENTER(); - ffs_data_clear(ffs); ffs->raw_descs_data = NULL; @@ -1861,8 +1806,6 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) struct usb_gadget_strings **lang; int first_id; - ENTER(); - if (WARN_ON(ffs->state != FFS_ACTIVE || test_and_set_bit(FFS_FL_BOUND, &ffs->flags))) return -EBADFD; @@ -1894,8 +1837,6 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) static void functionfs_unbind(struct ffs_data *ffs) { - ENTER(); - if (!WARN_ON(!ffs->gadget)) { /* dequeue before freeing ep0req */ usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req); @@ -1914,8 +1855,6 @@ static int ffs_epfiles_create(struct ffs_data *ffs) struct ffs_epfile *epfile, *epfiles; unsigned i, count; - ENTER(); - count = ffs->eps_count; epfiles = kcalloc(count, sizeof(*epfiles), GFP_KERNEL); if (!epfiles) @@ -1946,8 +1885,6 @@ static void ffs_epfiles_destroy(struct ffs_epfile *epfiles, unsigned count) { struct ffs_epfile *epfile = epfiles; - ENTER(); - for (; count; --count, ++epfile) { BUG_ON(mutex_is_locked(&epfile->mutex)); if (epfile->dentry) { @@ -2064,8 +2001,6 @@ static int __must_check ffs_do_single_desc(char *data, unsigned len, u8 length; int ret; - ENTER(); - /* At least two bytes are required: length and type */ if (len < 2) { pr_vdebug("descriptor too short\n"); @@ -2204,8 +2139,6 @@ static int __must_check ffs_do_descs(unsigned count, char *data, unsigned len, unsigned long num = 0; int current_class = -1; - ENTER(); - for (;;) { int ret; @@ -2243,8 +2176,6 @@ static int __ffs_data_do_entity(enum ffs_entity_type type, struct ffs_desc_helper *helper = priv; struct usb_endpoint_descriptor *d; - ENTER(); - switch (type) { case FFS_DESCRIPTOR: break; @@ -2329,8 +2260,6 @@ static int __must_check ffs_do_single_os_desc(char *data, unsigned len, int ret; const unsigned _len = len; - ENTER(); - /* loop over all ext compat/ext prop descriptors */ while (feature_count--) { ret = entity(type, h, data, len, priv); @@ -2352,8 +2281,6 @@ static int __must_check ffs_do_os_descs(unsigned count, const unsigned _len = len; unsigned long num = 0; - ENTER(); - for (num = 0; num < count; ++num) { int ret; enum ffs_os_desc_type type; @@ -2416,8 +2343,6 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type, struct ffs_data *ffs = priv; u8 length; - ENTER(); - switch (type) { case FFS_OS_DESC_EXT_COMPAT: { struct usb_ext_compat_desc *d = data; @@ -2493,8 +2418,6 @@ static int __ffs_data_got_descs(struct ffs_data *ffs, int ret = -EINVAL, i; struct ffs_desc_helper helper; - ENTER(); - if (get_unaligned_le32(data + 4) != len) goto error; @@ -2625,8 +2548,6 @@ static int __ffs_data_got_strings(struct ffs_data *ffs, const char *data = _data; struct usb_string *s; - ENTER(); - if (len < 16 || get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC || get_unaligned_le32(data + 4) != len) @@ -3085,8 +3006,6 @@ static inline struct f_fs_opts *ffs_do_functionfs_bind(struct usb_function *f, struct ffs_data *ffs_data; int ret; - ENTER(); - /* * Legacy gadget triggers binding in functionfs_ready_callback, * which already uses locking; taking the same lock here would @@ -3163,8 +3082,6 @@ static int _ffs_func_bind(struct usb_configuration *c, vla_item_with_sz(d, char, raw_descs, ffs->raw_descs_length); char *vlabuf; - ENTER(); - /* Has descriptors only for speeds gadget does not support */ if (!(full | high | super)) return -ENOTSUPP; @@ -3368,8 +3285,6 @@ static int ffs_func_setup(struct usb_function *f, unsigned long flags; int ret; - ENTER(); - pr_vdebug("creq->bRequestType = %02x\n", creq->bRequestType); pr_vdebug("creq->bRequest = %02x\n", creq->bRequest); pr_vdebug("creq->wValue = %04x\n", le16_to_cpu(creq->wValue)); @@ -3444,13 +3359,11 @@ static bool ffs_func_req_match(struct usb_function *f, static void ffs_func_suspend(struct usb_function *f) { - ENTER(); ffs_event_add(ffs_func_from_usb(f)->ffs, FUNCTIONFS_SUSPEND); } static void ffs_func_resume(struct usb_function *f) { - ENTER(); ffs_event_add(ffs_func_from_usb(f)->ffs, FUNCTIONFS_RESUME); } @@ -3614,7 +3527,6 @@ static void ffs_func_unbind(struct usb_configuration *c, unsigned count = ffs->eps_count; unsigned long flags; - ENTER(); if (ffs->func == func) { ffs_func_eps_disable(func); ffs->func = NULL; @@ -3654,8 +3566,6 @@ static struct usb_function *ffs_alloc(struct usb_function_instance *fi) { struct ffs_function *func; - ENTER(); - func = kzalloc(sizeof(*func), GFP_KERNEL); if (!func) return ERR_PTR(-ENOMEM); @@ -3756,7 +3666,6 @@ static int ffs_acquire_dev(const char *dev_name, struct ffs_data *ffs_data) int ret = 0; struct ffs_dev *ffs_dev; - ENTER(); ffs_dev_lock(); ffs_dev = _ffs_find_dev(dev_name); @@ -3779,7 +3688,6 @@ static int ffs_acquire_dev(const char *dev_name, struct ffs_data *ffs_data) static void ffs_release_dev(struct ffs_dev *ffs_dev) { - ENTER(); ffs_dev_lock(); if (ffs_dev && ffs_dev->mounted) { @@ -3801,7 +3709,6 @@ static int ffs_ready(struct ffs_data *ffs) struct ffs_dev *ffs_obj; int ret = 0; - ENTER(); ffs_dev_lock(); ffs_obj = ffs->private_data; @@ -3834,7 +3741,6 @@ static void ffs_closed(struct ffs_data *ffs) struct f_fs_opts *opts; struct config_item *ci; - ENTER(); ffs_dev_lock(); ffs_obj = ffs->private_data; diff --git a/drivers/usb/gadget/function/u_fs.h b/drivers/usb/gadget/function/u_fs.h index f102ec23f3af..4b3365f23fd7 100644 --- a/drivers/usb/gadget/function/u_fs.h +++ b/drivers/usb/gadget/function/u_fs.h @@ -32,8 +32,6 @@ # define ffs_dump_mem(prefix, ptr, len) do { } while (0) #endif /* VERBOSE_DEBUG */ -#define ENTER() pr_vdebug("%s()\n", __func__) - struct f_fs_opts; struct ffs_dev { diff --git a/drivers/usb/gadget/legacy/g_ffs.c b/drivers/usb/gadget/legacy/g_ffs.c index ae6d8f7092b8..097854683e5b 100644 --- a/drivers/usb/gadget/legacy/g_ffs.c +++ b/drivers/usb/gadget/legacy/g_ffs.c @@ -180,8 +180,6 @@ static int __init gfs_init(void) int i; int ret = 0; - ENTER(); - if (func_num < 2) { gfs_single_func = true; func_num = 1; @@ -242,8 +240,6 @@ static void __exit gfs_exit(void) { int i; - ENTER(); - if (gfs_registered) usb_composite_unregister(&gfs_driver); gfs_registered = false; @@ -316,8 +312,6 @@ static int gfs_bind(struct usb_composite_dev *cdev) #endif int ret, i; - ENTER(); - if (missing_funcs) return -ENODEV; #if defined CONFIG_USB_FUNCTIONFS_ETH @@ -445,9 +439,6 @@ static int gfs_unbind(struct usb_composite_dev *cdev) { int i; - ENTER(); - - #ifdef CONFIG_USB_FUNCTIONFS_RNDIS usb_put_function(f_rndis); usb_put_function_instance(fi_rndis); -- GitLab From 130eac4170859fb368681e00d390f20f44bbf27b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 Mar 2023 15:10:43 +0200 Subject: [PATCH 1545/5631] xhci: use pm_ptr() instead of #ifdef for CONFIG_PM conditionals A recent patch caused an unused-function warning in builds with CONFIG_PM disabled, after the function became marked 'static': drivers/usb/host/xhci-pci.c:91:13: error: 'xhci_msix_sync_irqs' defined but not used [-Werror=unused-function] 91 | static void xhci_msix_sync_irqs(struct xhci_hcd *xhci) | ^~~~~~~~~~~~~~~~~~~ This could be solved by adding another #ifdef, but as there is a trend towards removing CONFIG_PM checks in favor of helper macros, do the same conversion here and use pm_ptr() to get either a function pointer or NULL but avoid the warning. As the hidden functions reference some other symbols, make sure those are visible at compile time, at the minimal cost of a few extra bytes for 'struct usb_device'. Fixes: 9abe15d55dcc ("xhci: Move xhci MSI sync function to to xhci-pci") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230328131114.1296430-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 16 +++++----------- include/linux/usb.h | 3 +-- include/linux/usb/hcd.h | 2 -- 3 files changed, 6 insertions(+), 15 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index a53ecc8ff8c5..bbbb01282038 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -728,7 +728,6 @@ static void xhci_pci_remove(struct pci_dev *dev) usb_hcd_pci_remove(dev); } -#ifdef CONFIG_PM /* * In some Intel xHCI controllers, in order to get D3 working, * through a vendor specific SSIC CONFIG register at offset 0x883c, @@ -927,7 +926,6 @@ static void xhci_pci_shutdown(struct usb_hcd *hcd) if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) pci_set_power_state(pdev, PCI_D3hot); } -#endif /* CONFIG_PM */ /*-------------------------------------------------------------------------*/ @@ -970,9 +968,7 @@ static struct pci_driver xhci_pci_driver = { .shutdown = usb_hcd_pci_shutdown, .driver = { -#ifdef CONFIG_PM - .pm = &usb_hcd_pci_pm_ops, -#endif + .pm = pm_ptr(&usb_hcd_pci_pm_ops), .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; @@ -980,12 +976,10 @@ static struct pci_driver xhci_pci_driver = { static int __init xhci_pci_init(void) { xhci_init_driver(&xhci_pci_hc_driver, &xhci_pci_overrides); -#ifdef CONFIG_PM - xhci_pci_hc_driver.pci_suspend = xhci_pci_suspend; - xhci_pci_hc_driver.pci_resume = xhci_pci_resume; - xhci_pci_hc_driver.pci_poweroff_late = xhci_pci_poweroff_late; - xhci_pci_hc_driver.shutdown = xhci_pci_shutdown; -#endif + xhci_pci_hc_driver.pci_suspend = pm_ptr(xhci_pci_suspend); + xhci_pci_hc_driver.pci_resume = pm_ptr(xhci_pci_resume); + xhci_pci_hc_driver.pci_poweroff_late = pm_ptr(xhci_pci_poweroff_late); + xhci_pci_hc_driver.shutdown = pm_ptr(xhci_pci_shutdown); xhci_pci_hc_driver.stop = xhci_pci_stop; return pci_register_driver(&xhci_pci_driver); } diff --git a/include/linux/usb.h b/include/linux/usb.h index 9642ee02d713..d510fabcafa2 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -704,13 +704,12 @@ struct usb_device { unsigned long active_duration; -#ifdef CONFIG_PM unsigned long connect_time; unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; -#endif + struct wusb_dev *wusb_dev; int slot_id; struct usb2_lpm_parameters l1_params; diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index b51c07111729..094c77eaf455 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -488,9 +488,7 @@ extern void usb_hcd_pci_shutdown(struct pci_dev *dev); extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); -#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; -#endif #endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ -- GitLab From df9ba6a245b34332e82df07b078988abf0ac1f09 Mon Sep 17 00:00:00 2001 From: Deming Wang Date: Sat, 25 Mar 2023 02:38:32 -0400 Subject: [PATCH 1546/5631] usb: dwc2: Fix spelling mistake "schduler" -> "scheduler" There is a spelling mistakes in dev_warn messages. Fix them. Signed-off-by: Deming Wang Link: https://lore.kernel.org/r/20230325063832.1642-1-wangdeming@inspur.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/hcd_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c index 0a1145592fc7..0d4495c6b9f7 100644 --- a/drivers/usb/dwc2/hcd_queue.c +++ b/drivers/usb/dwc2/hcd_queue.c @@ -1078,7 +1078,7 @@ static void dwc2_pick_first_frame(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh) earliest_frame = dwc2_frame_num_inc(frame_number, 1); next_active_frame = earliest_frame; - /* Get the "no microframe schduler" out of the way... */ + /* Get the "no microframe scheduler" out of the way... */ if (!hsotg->params.uframe_sched) { if (qh->do_split) /* Splits are active at microframe 0 minus 1 */ -- GitLab From c03ff66dc0e0cbad9ed0c29500843e1da8533118 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 23 Mar 2023 20:40:22 +0100 Subject: [PATCH 1547/5631] usb: pci-quirks: Reduce the length of a spinlock section in usb_amd_find_chipset_info() 'info' is local to the function. There is no need to zeroing it within a spin_lock section. Moreover, there is no need to explicitly initialize the .need_pll_quirk field. Initialize the structure when defined and remove the now useless memset(). Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/08ee42fced6af6bd56892cd14f2464380ab071fa.1679600396.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/pci-quirks.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index ef08d68b9714..2665832f9add 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -207,8 +207,7 @@ EXPORT_SYMBOL_GPL(sb800_prefetch); static void usb_amd_find_chipset_info(void) { unsigned long flags; - struct amd_chipset_info info; - info.need_pll_quirk = false; + struct amd_chipset_info info = { }; spin_lock_irqsave(&amd_lock, flags); @@ -218,7 +217,6 @@ static void usb_amd_find_chipset_info(void) spin_unlock_irqrestore(&amd_lock, flags); return; } - memset(&info, 0, sizeof(info)); spin_unlock_irqrestore(&amd_lock, flags); if (!amd_chipset_sb_type_init(&info)) { -- GitLab From db2c2b161d4a8f4a81e6f643848b1531517a67a5 Mon Sep 17 00:00:00 2001 From: Mingxuan Xiang Date: Fri, 24 Mar 2023 14:09:34 +0800 Subject: [PATCH 1548/5631] usb: dwc3: host: remove dead code in dwc3_host_get_irq() According to the description of platform_get_irq() * Return: non-zero IRQ number on success, negative error number on failure. and the code, platform_get_irq() will return -EINVAL instead of IRQ0. So platform_get_irq() no longer returns 0, there is no need to check whether the return value is 0. Found by Smatch: drivers/usb/dwc3/host.c:60 dwc3_host_get_irq() warn: platform_get_irq() does not return zero Signed-off-by: Mingxuan Xiang Reviewed-by: Dan Carpenter Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230324060934.1686859-1-mx_xiang@hust.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/host.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c index f6f13e7f1ba1..61f57fe5bb78 100644 --- a/drivers/usb/dwc3/host.c +++ b/drivers/usb/dwc3/host.c @@ -52,13 +52,8 @@ static int dwc3_host_get_irq(struct dwc3 *dwc) goto out; irq = platform_get_irq(dwc3_pdev, 0); - if (irq > 0) { + if (irq > 0) dwc3_host_fill_xhci_irq_res(dwc, irq, NULL); - goto out; - } - - if (!irq) - irq = -EINVAL; out: return irq; -- GitLab From 2926c5275028e44f6a2ac31b37d75d6d6e260306 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 24 Mar 2023 13:44:29 +0200 Subject: [PATCH 1549/5631] usb: dwc3-am62: Fix up wake-up configuration and spurious wake up Explicitly set and clear wakeup config so we don't leave anything to chance. Clear wakeup status on suspend so we know what caused wake up. The LINESTATE wake up should not be enabled in device mode if we are not connected to a USB host and in USB suspend (U2/L3) else it will cause spurious wake up. For now, don't enable LINESTATE. This means wake up from USB resume will not work but at least we won't have any spurious wake ups. Signed-off-by: Roger Quadros Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230324114429.21838-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-am62.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 859b48279658..b22fb78bc8e7 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -60,6 +60,13 @@ #define USBSS_WAKEUP_CFG_SESSVALID_EN BIT(1) #define USBSS_WAKEUP_CFG_VBUSVALID_EN BIT(0) +#define USBSS_WAKEUP_CFG_ALL (USBSS_WAKEUP_CFG_VBUSVALID_EN | \ + USBSS_WAKEUP_CFG_SESSVALID_EN | \ + USBSS_WAKEUP_CFG_LINESTATE_EN | \ + USBSS_WAKEUP_CFG_OVERCURRENT_EN) + +#define USBSS_WAKEUP_CFG_NONE 0 + /* WAKEUP STAT register bits */ #define USBSS_WAKEUP_STAT_OVERCURRENT BIT(4) #define USBSS_WAKEUP_STAT_LINESTATE BIT(3) @@ -103,6 +110,7 @@ struct dwc3_data { struct regmap *syscon; unsigned int offset; unsigned int vbus_divider; + u32 wakeup_stat; }; static const int dwc3_ti_rate_table[] = { /* in KHZ */ @@ -302,12 +310,17 @@ static int dwc3_ti_suspend_common(struct device *dev) /* Set wakeup config enable bits */ reg = dwc3_ti_readl(data, USBSS_WAKEUP_CONFIG); if (current_prtcap_dir == DWC3_GCTL_PRTCAP_HOST) { - reg |= USBSS_WAKEUP_CFG_LINESTATE_EN | USBSS_WAKEUP_CFG_OVERCURRENT_EN; + reg = USBSS_WAKEUP_CFG_LINESTATE_EN | USBSS_WAKEUP_CFG_OVERCURRENT_EN; } else { - reg |= USBSS_WAKEUP_CFG_OVERCURRENT_EN | USBSS_WAKEUP_CFG_LINESTATE_EN | - USBSS_WAKEUP_CFG_VBUSVALID_EN; + reg = USBSS_WAKEUP_CFG_VBUSVALID_EN | USBSS_WAKEUP_CFG_SESSVALID_EN; + /* + * Enable LINESTATE wake up only if connected to bus + * and in U2/L3 state else it causes spurious wake-up. + */ } dwc3_ti_writel(data, USBSS_WAKEUP_CONFIG, reg); + /* clear wakeup status so we know what caused the wake up */ + dwc3_ti_writel(data, USBSS_WAKEUP_STAT, USBSS_WAKEUP_STAT_CLR); } clk_disable_unprepare(data->usb2_refclk); @@ -324,16 +337,11 @@ static int dwc3_ti_resume_common(struct device *dev) if (device_may_wakeup(dev)) { /* Clear wakeup config enable bits */ - reg = dwc3_ti_readl(data, USBSS_WAKEUP_CONFIG); - reg &= ~(USBSS_WAKEUP_CFG_OVERCURRENT_EN | USBSS_WAKEUP_CFG_LINESTATE_EN | - USBSS_WAKEUP_CFG_VBUSVALID_EN); - dwc3_ti_writel(data, USBSS_WAKEUP_CONFIG, reg); + dwc3_ti_writel(data, USBSS_WAKEUP_CONFIG, USBSS_WAKEUP_CFG_NONE); } reg = dwc3_ti_readl(data, USBSS_WAKEUP_STAT); - /* Clear the wakeup status with wakeup clear bit */ - reg |= USBSS_WAKEUP_STAT_CLR; - dwc3_ti_writel(data, USBSS_WAKEUP_STAT, reg); + data->wakeup_stat = reg; return 0; } -- GitLab From d54bd5abf4d26e1b6722238f75e36069ea91def9 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Wed, 15 Mar 2023 01:16:55 -0700 Subject: [PATCH 1550/5631] RDMA/bnxt_re: Add resize_cq support Add resize_cq verb support for user space CQs. Resize operation for kernel CQs are not supported now. Driver should free the current CQ only after user library polls for all the completions and switch to new CQ. So after the resize_cq is returned from the driver, user library polls for existing completions and store it as temporary data. Once library reaps all completions in the current CQ, it invokes the ibv_cmd_poll_cq to inform the driver about the resize_cq completion. Adding a check for user CQs in driver's poll_cq and complete the resize operation for user CQs. Updating uverbs_cmd_mask with poll_cq to support this. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1678868215-23626-1-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 109 +++++++++++++++++++++++ drivers/infiniband/hw/bnxt_re/ib_verbs.h | 3 + drivers/infiniband/hw/bnxt_re/main.c | 2 + drivers/infiniband/hw/bnxt_re/qplib_fp.c | 44 +++++++++ drivers/infiniband/hw/bnxt_re/qplib_fp.h | 5 ++ include/uapi/rdma/bnxt_re-abi.h | 4 + 6 files changed, 167 insertions(+) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 989edc789633..e86afecfbe46 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -2912,6 +2912,106 @@ int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, return rc; } +static void bnxt_re_resize_cq_complete(struct bnxt_re_cq *cq) +{ + struct bnxt_re_dev *rdev = cq->rdev; + + bnxt_qplib_resize_cq_complete(&rdev->qplib_res, &cq->qplib_cq); + + cq->qplib_cq.max_wqe = cq->resize_cqe; + if (cq->resize_umem) { + ib_umem_release(cq->umem); + cq->umem = cq->resize_umem; + cq->resize_umem = NULL; + cq->resize_cqe = 0; + } +} + +int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata) +{ + struct bnxt_qplib_sg_info sg_info = {}; + struct bnxt_qplib_dpi *orig_dpi = NULL; + struct bnxt_qplib_dev_attr *dev_attr; + struct bnxt_re_ucontext *uctx = NULL; + struct bnxt_re_resize_cq_req req; + struct bnxt_re_dev *rdev; + struct bnxt_re_cq *cq; + int rc, entries; + + cq = container_of(ibcq, struct bnxt_re_cq, ib_cq); + rdev = cq->rdev; + dev_attr = &rdev->dev_attr; + if (!ibcq->uobject) { + ibdev_err(&rdev->ibdev, "Kernel CQ Resize not supported"); + return -EOPNOTSUPP; + } + + if (cq->resize_umem) { + ibdev_err(&rdev->ibdev, "Resize CQ %#x failed - Busy", + cq->qplib_cq.id); + return -EBUSY; + } + + /* Check the requested cq depth out of supported depth */ + if (cqe < 1 || cqe > dev_attr->max_cq_wqes) { + ibdev_err(&rdev->ibdev, "Resize CQ %#x failed - out of range cqe %d", + cq->qplib_cq.id, cqe); + return -EINVAL; + } + + entries = roundup_pow_of_two(cqe + 1); + if (entries > dev_attr->max_cq_wqes + 1) + entries = dev_attr->max_cq_wqes + 1; + + uctx = rdma_udata_to_drv_context(udata, struct bnxt_re_ucontext, + ib_uctx); + /* uverbs consumer */ + if (ib_copy_from_udata(&req, udata, sizeof(req))) { + rc = -EFAULT; + goto fail; + } + + cq->resize_umem = ib_umem_get(&rdev->ibdev, req.cq_va, + entries * sizeof(struct cq_base), + IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(cq->resize_umem)) { + rc = PTR_ERR(cq->resize_umem); + cq->resize_umem = NULL; + ibdev_err(&rdev->ibdev, "%s: ib_umem_get failed! rc = %d\n", + __func__, rc); + goto fail; + } + cq->resize_cqe = entries; + memcpy(&sg_info, &cq->qplib_cq.sg_info, sizeof(sg_info)); + orig_dpi = cq->qplib_cq.dpi; + + cq->qplib_cq.sg_info.umem = cq->resize_umem; + cq->qplib_cq.sg_info.pgsize = PAGE_SIZE; + cq->qplib_cq.sg_info.pgshft = PAGE_SHIFT; + cq->qplib_cq.dpi = &uctx->dpi; + + rc = bnxt_qplib_resize_cq(&rdev->qplib_res, &cq->qplib_cq, entries); + if (rc) { + ibdev_err(&rdev->ibdev, "Resize HW CQ %#x failed!", + cq->qplib_cq.id); + goto fail; + } + + cq->ib_cq.cqe = cq->resize_cqe; + + return 0; + +fail: + if (cq->resize_umem) { + ib_umem_release(cq->resize_umem); + cq->resize_umem = NULL; + cq->resize_cqe = 0; + memcpy(&cq->qplib_cq.sg_info, &sg_info, sizeof(sg_info)); + cq->qplib_cq.dpi = orig_dpi; + } + return rc; +} + static u8 __req_to_ib_wc_status(u8 qstatus) { switch (qstatus) { @@ -3425,6 +3525,15 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc) struct bnxt_re_sqp_entries *sqp_entry = NULL; unsigned long flags; + /* User CQ; the only processing we do is to + * complete any pending CQ resize operation. + */ + if (cq->umem) { + if (cq->resize_umem) + bnxt_re_resize_cq_complete(cq); + return 0; + } + spin_lock_irqsave(&cq->cq_lock, flags); budget = min_t(u32, num_entries, cq->max_cql); num_entries = budget; diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.h b/drivers/infiniband/hw/bnxt_re/ib_verbs.h index 94326267f9bb..31f7e34040f7 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.h +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.h @@ -104,6 +104,8 @@ struct bnxt_re_cq { #define MAX_CQL_PER_POLL 1024 u32 max_cql; struct ib_umem *umem; + struct ib_umem *resize_umem; + int resize_cqe; }; struct bnxt_re_mr { @@ -191,6 +193,7 @@ int bnxt_re_post_recv(struct ib_qp *qp, const struct ib_recv_wr *recv_wr, const struct ib_recv_wr **bad_recv_wr); int bnxt_re_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, struct ib_udata *udata); +int bnxt_re_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata); int bnxt_re_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int bnxt_re_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int bnxt_re_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags); diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index c5867e78f231..48bbba7df22e 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -553,6 +553,7 @@ static const struct ib_device_ops bnxt_re_dev_ops = { .query_srq = bnxt_re_query_srq, .reg_user_mr = bnxt_re_reg_user_mr, .req_notify_cq = bnxt_re_req_notify_cq, + .resize_cq = bnxt_re_resize_cq, INIT_RDMA_OBJ_SIZE(ib_ah, bnxt_re_ah, ib_ah), INIT_RDMA_OBJ_SIZE(ib_cq, bnxt_re_cq, ib_cq), INIT_RDMA_OBJ_SIZE(ib_pd, bnxt_re_pd, ib_pd), @@ -584,6 +585,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) return ret; dma_set_max_seg_size(&rdev->en_dev->pdev->dev, UINT_MAX); + ibdev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POLL_CQ); return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev); } diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 96e581ced50e..1d769a3106f6 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2100,6 +2100,50 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) return rc; } +void bnxt_qplib_resize_cq_complete(struct bnxt_qplib_res *res, + struct bnxt_qplib_cq *cq) +{ + bnxt_qplib_free_hwq(res, &cq->hwq); + memcpy(&cq->hwq, &cq->resize_hwq, sizeof(cq->hwq)); +} + +int bnxt_qplib_resize_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq, + int new_cqes) +{ + struct bnxt_qplib_hwq_attr hwq_attr = {}; + struct bnxt_qplib_rcfw *rcfw = res->rcfw; + struct creq_resize_cq_resp resp = {}; + struct cmdq_resize_cq req = {}; + struct bnxt_qplib_pbl *pbl; + u32 pg_sz, lvl, new_sz; + u16 cmd_flags = 0; + int rc; + + RCFW_CMD_PREP(req, RESIZE_CQ, cmd_flags); + hwq_attr.sginfo = &cq->sg_info; + hwq_attr.res = res; + hwq_attr.depth = new_cqes; + hwq_attr.stride = sizeof(struct cq_base); + hwq_attr.type = HWQ_TYPE_QUEUE; + rc = bnxt_qplib_alloc_init_hwq(&cq->resize_hwq, &hwq_attr); + if (rc) + return rc; + + req.cq_cid = cpu_to_le32(cq->id); + pbl = &cq->resize_hwq.pbl[PBL_LVL_0]; + pg_sz = bnxt_qplib_base_pg_size(&cq->resize_hwq); + lvl = (cq->resize_hwq.level << CMDQ_RESIZE_CQ_LVL_SFT) & + CMDQ_RESIZE_CQ_LVL_MASK; + new_sz = (new_cqes << CMDQ_RESIZE_CQ_NEW_CQ_SIZE_SFT) & + CMDQ_RESIZE_CQ_NEW_CQ_SIZE_MASK; + req.new_cq_size_pg_size_lvl = cpu_to_le32(new_sz | pg_sz | lvl); + req.new_pbl = cpu_to_le64(pbl->pg_map_arr[0]); + + rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, + (void *)&resp, NULL, 0); + return rc; +} + int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index 037501952543..d74d5ead2e32 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -400,6 +400,7 @@ struct bnxt_qplib_cq { u16 count; u16 period; struct bnxt_qplib_hwq hwq; + struct bnxt_qplib_hwq resize_hwq; u32 cnq_hw_ring_id; struct bnxt_qplib_nq *nq; bool resize_in_progress; @@ -532,6 +533,10 @@ void bnxt_qplib_post_recv_db(struct bnxt_qplib_qp *qp); int bnxt_qplib_post_recv(struct bnxt_qplib_qp *qp, struct bnxt_qplib_swqe *wqe); int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq); +int bnxt_qplib_resize_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq, + int new_cqes); +void bnxt_qplib_resize_cq_complete(struct bnxt_qplib_res *res, + struct bnxt_qplib_cq *cq); int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq); int bnxt_qplib_poll_cq(struct bnxt_qplib_cq *cq, struct bnxt_qplib_cqe *cqe, int num, struct bnxt_qplib_qp **qp); diff --git a/include/uapi/rdma/bnxt_re-abi.h b/include/uapi/rdma/bnxt_re-abi.h index b1de99bf56ce..c4e90775da0c 100644 --- a/include/uapi/rdma/bnxt_re-abi.h +++ b/include/uapi/rdma/bnxt_re-abi.h @@ -96,6 +96,10 @@ struct bnxt_re_cq_resp { __u32 rsvd; }; +struct bnxt_re_resize_cq_req { + __aligned_u64 cq_va; +}; + struct bnxt_re_qp_req { __aligned_u64 qpsva; __aligned_u64 qprva; -- GitLab From 77f7eb9f3416aace703971156133926e44e2195b Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 23 Mar 2023 12:13:51 +0200 Subject: [PATCH 1551/5631] net/mlx5: Introduce other vport query for Q-counters These new fields in QUERY_Q_COUNTER command allow us to access another vport counters during the query command, which is specially useful to query representor vports. In addition also add the required caps to check if this capability is actually supported. Signed-off-by: Patrisious Haddad Reviewed-by: Michael Guralnik Link: https://lore.kernel.org/r/75c73a4a0e60f18c37b35a4a11ca2e2415e4a6f3.1679566038.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 62039b147432..e4306cd87cd7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1729,7 +1729,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_transport_domain[0x5]; u8 reserved_at_328[0x3]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0xb]; + u8 reserved_at_330[0x9]; + u8 q_counter_aggregation[0x1]; + u8 q_counter_other_vport[0x1]; u8 log_max_xrcd[0x5]; u8 nic_receive_steering_discard[0x1]; @@ -5603,10 +5605,15 @@ struct mlx5_ifc_query_q_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x80]; + u8 other_vport[0x1]; + u8 reserved_at_41[0xf]; + u8 vport_number[0x10]; + + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_at_c1[0x1f]; + u8 aggregate[0x1]; + u8 reserved_at_c2[0x1e]; u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; -- GitLab From d22467a71ebe96ff5ab7e000dbef60d4ea76e5b0 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 23 Mar 2023 12:13:52 +0200 Subject: [PATCH 1552/5631] RDMA/mlx5: Expand switchdev Q-counters to expose representor statistics Previously for switchdev only per device counters were supported. Currently we allocate counters for switchdev per port, which also includes the ports that belong to VF representors in order to expose them to users through the rdma tool, allowing the host to track the VFs statistics through their representors counters. Signed-off-by: Patrisious Haddad Link: https://lore.kernel.org/r/ea31e1103c125cd27931ba213f307cde30d2eaed.1679566038.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/counters.c | 171 +++++++++++++++++++++----- 1 file changed, 142 insertions(+), 29 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c index 3e1272695d99..1c06920505d2 100644 --- a/drivers/infiniband/hw/mlx5/counters.c +++ b/drivers/infiniband/hw/mlx5/counters.c @@ -5,6 +5,7 @@ #include "mlx5_ib.h" #include +#include #include "counters.h" #include "ib_rep.h" #include "qp.h" @@ -18,6 +19,10 @@ struct mlx5_ib_counter { #define INIT_Q_COUNTER(_name) \ { .name = #_name, .offset = MLX5_BYTE_OFF(query_q_counter_out, _name)} +#define INIT_VPORT_Q_COUNTER(_name) \ + { .name = "vport_" #_name, .offset = \ + MLX5_BYTE_OFF(query_q_counter_out, _name)} + static const struct mlx5_ib_counter basic_q_cnts[] = { INIT_Q_COUNTER(rx_write_requests), INIT_Q_COUNTER(rx_read_requests), @@ -37,6 +42,25 @@ static const struct mlx5_ib_counter retrans_q_cnts[] = { INIT_Q_COUNTER(local_ack_timeout_err), }; +static const struct mlx5_ib_counter vport_basic_q_cnts[] = { + INIT_VPORT_Q_COUNTER(rx_write_requests), + INIT_VPORT_Q_COUNTER(rx_read_requests), + INIT_VPORT_Q_COUNTER(rx_atomic_requests), + INIT_VPORT_Q_COUNTER(out_of_buffer), +}; + +static const struct mlx5_ib_counter vport_out_of_seq_q_cnts[] = { + INIT_VPORT_Q_COUNTER(out_of_sequence), +}; + +static const struct mlx5_ib_counter vport_retrans_q_cnts[] = { + INIT_VPORT_Q_COUNTER(duplicate_request), + INIT_VPORT_Q_COUNTER(rnr_nak_retry_err), + INIT_VPORT_Q_COUNTER(packet_seq_err), + INIT_VPORT_Q_COUNTER(implied_nak_seq_err), + INIT_VPORT_Q_COUNTER(local_ack_timeout_err), +}; + #define INIT_CONG_COUNTER(_name) \ { .name = #_name, .offset = \ MLX5_BYTE_OFF(query_cong_statistics_out, _name ## _high)} @@ -67,6 +91,25 @@ static const struct mlx5_ib_counter roce_accl_cnts[] = { INIT_Q_COUNTER(roce_slow_restart_trans), }; +static const struct mlx5_ib_counter vport_extended_err_cnts[] = { + INIT_VPORT_Q_COUNTER(resp_local_length_error), + INIT_VPORT_Q_COUNTER(resp_cqe_error), + INIT_VPORT_Q_COUNTER(req_cqe_error), + INIT_VPORT_Q_COUNTER(req_remote_invalid_request), + INIT_VPORT_Q_COUNTER(req_remote_access_errors), + INIT_VPORT_Q_COUNTER(resp_remote_access_errors), + INIT_VPORT_Q_COUNTER(resp_cqe_flush_error), + INIT_VPORT_Q_COUNTER(req_cqe_flush_error), +}; + +static const struct mlx5_ib_counter vport_roce_accl_cnts[] = { + INIT_VPORT_Q_COUNTER(roce_adp_retrans), + INIT_VPORT_Q_COUNTER(roce_adp_retrans_to), + INIT_VPORT_Q_COUNTER(roce_slow_restart), + INIT_VPORT_Q_COUNTER(roce_slow_restart_cnps), + INIT_VPORT_Q_COUNTER(roce_slow_restart_trans), +}; + #define INIT_EXT_PPCNT_COUNTER(_name) \ { .name = #_name, .offset = \ MLX5_BYTE_OFF(ppcnt_reg, \ @@ -153,12 +196,20 @@ static int mlx5_ib_create_counters(struct ib_counters *counters, return 0; } +static bool vport_qcounters_supported(struct mlx5_ib_dev *dev) +{ + return MLX5_CAP_GEN(dev->mdev, q_counter_other_vport) && + MLX5_CAP_GEN(dev->mdev, q_counter_aggregation); +} static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev, u32 port_num) { - return is_mdev_switchdev_mode(dev->mdev) ? &dev->port[0].cnts : - &dev->port[port_num].cnts; + if ((is_mdev_switchdev_mode(dev->mdev) && + !vport_qcounters_supported(dev)) || !port_num) + return &dev->port[0].cnts; + + return &dev->port[port_num - 1].cnts; } /** @@ -172,7 +223,7 @@ static const struct mlx5_ib_counters *get_counters(struct mlx5_ib_dev *dev, */ u16 mlx5_ib_get_counters_id(struct mlx5_ib_dev *dev, u32 port_num) { - const struct mlx5_ib_counters *cnts = get_counters(dev, port_num); + const struct mlx5_ib_counters *cnts = get_counters(dev, port_num + 1); return cnts->set_id; } @@ -270,12 +321,44 @@ static int mlx5_ib_query_ext_ppcnt_counters(struct mlx5_ib_dev *dev, return ret; } +static int mlx5_ib_query_q_counters_vport(struct mlx5_ib_dev *dev, + u32 port_num, + const struct mlx5_ib_counters *cnts, + struct rdma_hw_stats *stats) + +{ + u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; + __be32 val; + int ret, i; + + if (!dev->port[port_num].rep || + dev->port[port_num].rep->vport == MLX5_VPORT_UPLINK) + return 0; + + MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); + MLX5_SET(query_q_counter_in, in, other_vport, 1); + MLX5_SET(query_q_counter_in, in, vport_number, + dev->port[port_num].rep->vport); + MLX5_SET(query_q_counter_in, in, aggregate, 1); + ret = mlx5_cmd_exec_inout(dev->mdev, query_q_counter, in, out); + if (ret) + return ret; + + for (i = 0; i < cnts->num_q_counters; i++) { + val = *(__be32 *)((void *)out + cnts->offsets[i]); + stats->value[i] = (u64)be32_to_cpu(val); + } + + return 0; +} + static int do_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, u32 port_num, int index) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1); + const struct mlx5_ib_counters *cnts = get_counters(dev, port_num); struct mlx5_core_dev *mdev; int ret, num_counters; @@ -286,11 +369,19 @@ static int do_get_hw_stats(struct ib_device *ibdev, cnts->num_cong_counters + cnts->num_ext_ppcnt_counters; - /* q_counters are per IB device, query the master mdev */ - ret = mlx5_ib_query_q_counters(dev->mdev, cnts, stats, cnts->set_id); + if (is_mdev_switchdev_mode(dev->mdev) && dev->is_rep && port_num != 0) + ret = mlx5_ib_query_q_counters_vport(dev, port_num - 1, cnts, + stats); + else + ret = mlx5_ib_query_q_counters(dev->mdev, cnts, stats, + cnts->set_id); if (ret) return ret; + /* We don't expose device counters over Vports */ + if (is_mdev_switchdev_mode(dev->mdev) && port_num != 0) + goto done; + if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) { ret = mlx5_ib_query_ext_ppcnt_counters(dev, cnts, stats); if (ret) @@ -335,7 +426,8 @@ static int do_get_op_stat(struct ib_device *ibdev, u32 type; int ret; - cnts = get_counters(dev, port_num - 1); + cnts = get_counters(dev, port_num); + opfcs = cnts->opfcs; type = *(u32 *)cnts->descs[index].priv; if (type >= MLX5_IB_OPCOUNTER_MAX) @@ -362,7 +454,7 @@ static int do_get_op_stats(struct ib_device *ibdev, const struct mlx5_ib_counters *cnts; int index, ret, num_hw_counters; - cnts = get_counters(dev, port_num - 1); + cnts = get_counters(dev, port_num); num_hw_counters = cnts->num_q_counters + cnts->num_cong_counters + cnts->num_ext_ppcnt_counters; for (index = num_hw_counters; @@ -383,7 +475,7 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev, struct mlx5_ib_dev *dev = to_mdev(ibdev); const struct mlx5_ib_counters *cnts; - cnts = get_counters(dev, port_num - 1); + cnts = get_counters(dev, port_num); num_hw_counters = cnts->num_q_counters + cnts->num_cong_counters + cnts->num_ext_ppcnt_counters; num_counters = num_hw_counters + cnts->num_op_counters; @@ -410,8 +502,7 @@ static struct rdma_hw_stats * mlx5_ib_counter_alloc_stats(struct rdma_counter *counter) { struct mlx5_ib_dev *dev = to_mdev(counter->device); - const struct mlx5_ib_counters *cnts = - get_counters(dev, counter->port - 1); + const struct mlx5_ib_counters *cnts = get_counters(dev, counter->port); return do_alloc_stats(cnts); } @@ -419,8 +510,7 @@ mlx5_ib_counter_alloc_stats(struct rdma_counter *counter) static int mlx5_ib_counter_update_stats(struct rdma_counter *counter) { struct mlx5_ib_dev *dev = to_mdev(counter->device); - const struct mlx5_ib_counters *cnts = - get_counters(dev, counter->port - 1); + const struct mlx5_ib_counters *cnts = get_counters(dev, counter->port); return mlx5_ib_query_q_counters(dev->mdev, cnts, counter->stats, counter->id); @@ -479,44 +569,55 @@ static int mlx5_ib_counter_unbind_qp(struct ib_qp *qp) } static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev, - struct rdma_stat_desc *descs, size_t *offsets) + struct rdma_stat_desc *descs, size_t *offsets, + u32 port_num) { - int i; - int j = 0; + bool is_vport = is_mdev_switchdev_mode(dev->mdev) && + port_num != MLX5_VPORT_PF; + const struct mlx5_ib_counter *names; + int j = 0, i; + names = is_vport ? vport_basic_q_cnts : basic_q_cnts; for (i = 0; i < ARRAY_SIZE(basic_q_cnts); i++, j++) { - descs[j].name = basic_q_cnts[i].name; + descs[j].name = names[i].name; offsets[j] = basic_q_cnts[i].offset; } + names = is_vport ? vport_out_of_seq_q_cnts : out_of_seq_q_cnts; if (MLX5_CAP_GEN(dev->mdev, out_of_seq_cnt)) { for (i = 0; i < ARRAY_SIZE(out_of_seq_q_cnts); i++, j++) { - descs[j].name = out_of_seq_q_cnts[i].name; + descs[j].name = names[i].name; offsets[j] = out_of_seq_q_cnts[i].offset; } } + names = is_vport ? vport_retrans_q_cnts : retrans_q_cnts; if (MLX5_CAP_GEN(dev->mdev, retransmission_q_counters)) { for (i = 0; i < ARRAY_SIZE(retrans_q_cnts); i++, j++) { - descs[j].name = retrans_q_cnts[i].name; + descs[j].name = names[i].name; offsets[j] = retrans_q_cnts[i].offset; } } + names = is_vport ? vport_extended_err_cnts : extended_err_cnts; if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters)) { for (i = 0; i < ARRAY_SIZE(extended_err_cnts); i++, j++) { - descs[j].name = extended_err_cnts[i].name; + descs[j].name = names[i].name; offsets[j] = extended_err_cnts[i].offset; } } + names = is_vport ? vport_roce_accl_cnts : roce_accl_cnts; if (MLX5_CAP_GEN(dev->mdev, roce_accl)) { for (i = 0; i < ARRAY_SIZE(roce_accl_cnts); i++, j++) { - descs[j].name = roce_accl_cnts[i].name; + descs[j].name = names[i].name; offsets[j] = roce_accl_cnts[i].offset; } } + if (is_vport) + return; + if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { for (i = 0; i < ARRAY_SIZE(cong_cnts); i++, j++) { descs[j].name = cong_cnts[i].name; @@ -558,9 +659,9 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev, static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev, - struct mlx5_ib_counters *cnts) + struct mlx5_ib_counters *cnts, u32 port_num) { - u32 num_counters, num_op_counters; + u32 num_counters, num_op_counters = 0; num_counters = ARRAY_SIZE(basic_q_cnts); @@ -578,6 +679,9 @@ static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev, cnts->num_q_counters = num_counters; + if (is_mdev_switchdev_mode(dev->mdev) && port_num != MLX5_VPORT_PF) + goto skip_non_qcounters; + if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { cnts->num_cong_counters = ARRAY_SIZE(cong_cnts); num_counters += ARRAY_SIZE(cong_cnts); @@ -597,6 +701,7 @@ static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev, ft_field_support_2_nic_transmit_rdma.bth_opcode)) num_op_counters += ARRAY_SIZE(rdmatx_cnp_op_cnts); +skip_non_qcounters: cnts->num_op_counters = num_op_counters; num_counters += num_op_counters; cnts->descs = kcalloc(num_counters, @@ -623,7 +728,8 @@ static void mlx5_ib_dealloc_counters(struct mlx5_ib_dev *dev) int num_cnt_ports; int i, j; - num_cnt_ports = is_mdev_switchdev_mode(dev->mdev) ? 1 : dev->num_ports; + num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) || + vport_qcounters_supported(dev)) ? dev->num_ports : 1; MLX5_SET(dealloc_q_counter_in, in, opcode, MLX5_CMD_OP_DEALLOC_Q_COUNTER); @@ -662,15 +768,16 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev) MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER); is_shared = MLX5_CAP_GEN(dev->mdev, log_max_uctx) != 0; - num_cnt_ports = is_mdev_switchdev_mode(dev->mdev) ? 1 : dev->num_ports; + num_cnt_ports = (!is_mdev_switchdev_mode(dev->mdev) || + vport_qcounters_supported(dev)) ? dev->num_ports : 1; for (i = 0; i < num_cnt_ports; i++) { - err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts); + err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts, i); if (err) goto err_alloc; mlx5_ib_fill_counters(dev, dev->port[i].cnts.descs, - dev->port[i].cnts.offsets); + dev->port[i].cnts.offsets, i); MLX5_SET(alloc_q_counter_in, in, uid, is_shared ? MLX5_SHARED_RESOURCE_UID : 0); @@ -889,6 +996,10 @@ static const struct ib_device_ops hw_stats_ops = { mlx5_ib_modify_stat : NULL, }; +static const struct ib_device_ops hw_switchdev_vport_op = { + .alloc_hw_port_stats = mlx5_ib_alloc_hw_port_stats, +}; + static const struct ib_device_ops hw_switchdev_stats_ops = { .alloc_hw_device_stats = mlx5_ib_alloc_hw_device_stats, .get_hw_stats = mlx5_ib_get_hw_stats, @@ -914,9 +1025,11 @@ int mlx5_ib_counters_init(struct mlx5_ib_dev *dev) if (!MLX5_CAP_GEN(dev->mdev, max_qp_cnt)) return 0; - if (is_mdev_switchdev_mode(dev->mdev)) + if (is_mdev_switchdev_mode(dev->mdev)) { ib_set_device_ops(&dev->ib_dev, &hw_switchdev_stats_ops); - else + if (vport_qcounters_supported(dev)) + ib_set_device_ops(&dev->ib_dev, &hw_switchdev_vport_op); + } else ib_set_device_ops(&dev->ib_dev, &hw_stats_ops); return mlx5_ib_alloc_counters(dev); } -- GitLab From 4e99c98e3071bd7fd4d7f20440f1a5c3bf533149 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 20:20:16 +0300 Subject: [PATCH 1553/5631] thunderbolt: Get rid of redundant 'else' In the snippets like the following if (...) return / goto / break / continue ...; else ... the 'else' is redundant. Get rid of it. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg --- drivers/thunderbolt/acpi.c | 2 +- drivers/thunderbolt/ctl.c | 2 +- drivers/thunderbolt/nhi.c | 3 ++- drivers/thunderbolt/switch.c | 4 ++-- drivers/thunderbolt/usb4.c | 6 +++--- drivers/thunderbolt/xdomain.c | 24 ++++++++++-------------- 6 files changed, 19 insertions(+), 22 deletions(-) diff --git a/drivers/thunderbolt/acpi.c b/drivers/thunderbolt/acpi.c index 628225deb8fe..3514bf65b7a4 100644 --- a/drivers/thunderbolt/acpi.c +++ b/drivers/thunderbolt/acpi.c @@ -341,7 +341,7 @@ static struct acpi_device *tb_acpi_find_companion(struct device *dev) */ if (tb_is_switch(dev)) return tb_acpi_switch_find_companion(tb_to_switch(dev)); - else if (tb_is_usb4_port_device(dev)) + if (tb_is_usb4_port_device(dev)) return acpi_find_child_by_adr(ACPI_COMPANION(dev->parent), tb_to_usb4_port_device(dev)->port->port); return NULL; diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index 6e7d28e8d81a..3a213322ec7a 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -1033,7 +1033,7 @@ static int tb_cfg_get_error(struct tb_ctl *ctl, enum tb_cfg_space space, if (res->tb_error == TB_CFG_ERROR_LOCK) return -EACCES; - else if (res->tb_error == TB_CFG_ERROR_PORT_NOT_CONNECTED) + if (res->tb_error == TB_CFG_ERROR_PORT_NOT_CONNECTED) return -ENOTCONN; return -EIO; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 4dce2edd86ea..4400e1383e3e 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -515,7 +515,8 @@ static int nhi_alloc_hop(struct tb_nhi *nhi, struct tb_ring *ring) ring->hop); ret = -EBUSY; goto err_unlock; - } else if (!ring->is_tx && nhi->rx_rings[ring->hop]) { + } + if (!ring->is_tx && nhi->rx_rings[ring->hop]) { dev_warn(&nhi->pdev->dev, "RX hop %d already allocated\n", ring->hop); ret = -EBUSY; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 3370e18ba05f..0a34880a6636 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -271,9 +271,9 @@ static int nvm_authenticate(struct tb_switch *sw, bool auth_only) } sw->nvm->authenticating = true; return usb4_switch_nvm_authenticate(sw); - } else if (auth_only) { - return -EOPNOTSUPP; } + if (auth_only) + return -EOPNOTSUPP; sw->nvm->authenticating = true; if (!tb_route(sw)) { diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 1e5e9c147a31..28e3ec2d7633 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -851,7 +851,7 @@ bool usb4_switch_query_dp_resource(struct tb_switch *sw, struct tb_port *in) */ if (ret == -EOPNOTSUPP) return true; - else if (ret) + if (ret) return false; return !status; @@ -877,7 +877,7 @@ int usb4_switch_alloc_dp_resource(struct tb_switch *sw, struct tb_port *in) &status); if (ret == -EOPNOTSUPP) return 0; - else if (ret) + if (ret) return ret; return status ? -EBUSY : 0; @@ -900,7 +900,7 @@ int usb4_switch_dealloc_dp_resource(struct tb_switch *sw, struct tb_port *in) &status); if (ret == -EOPNOTSUPP) return 0; - else if (ret) + if (ret) return ret; return status ? -EIO : 0; diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index a48335c95d39..e2b54887d331 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1178,9 +1178,8 @@ static int tb_xdomain_get_uuid(struct tb_xdomain *xd) if (xd->state_retries-- > 0) { dev_dbg(&xd->dev, "failed to request UUID, retrying\n"); return -EAGAIN; - } else { - dev_dbg(&xd->dev, "failed to read remote UUID\n"); } + dev_dbg(&xd->dev, "failed to read remote UUID\n"); return ret; } @@ -1367,12 +1366,10 @@ static int tb_xdomain_get_properties(struct tb_xdomain *xd) dev_dbg(&xd->dev, "failed to request remote properties, retrying\n"); return -EAGAIN; - } else { - /* Give up now */ - dev_err(&xd->dev, - "failed read XDomain properties from %pUb\n", - xd->remote_uuid); } + /* Give up now */ + dev_err(&xd->dev, "failed read XDomain properties from %pUb\n", + xd->remote_uuid); return ret; } @@ -2179,13 +2176,12 @@ static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw, if (xd->remote_uuid && uuid_equal(xd->remote_uuid, lookup->uuid)) return xd; - } else if (lookup->link && - lookup->link == xd->link && - lookup->depth == xd->depth) { - return xd; - } else if (lookup->route && - lookup->route == xd->route) { - return xd; + } else { + if (lookup->link && lookup->link == xd->link && + lookup->depth == xd->depth) + return xd; + if (lookup->route && lookup->route == xd->route) + return xd; } } else if (tb_port_has_remote(port)) { xd = switch_find_xdomain(port->remote->sw, lookup); -- GitLab From 5d88366807fce55ab5bd1bf94055e1d1d0032604 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 20:20:17 +0300 Subject: [PATCH 1554/5631] thunderbolt: Make use of SI units from units.h In a couple of places it seems reasonable to use MEGA intead of explicit number. It makes code more readable and robust. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg --- drivers/thunderbolt/usb4.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 28e3ec2d7633..8dcdde61a15f 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -9,6 +9,7 @@ #include #include +#include #include "sb_regs.h" #include "tb.h" @@ -1968,7 +1969,7 @@ static unsigned int usb3_bw_to_mbps(u32 bw, u8 scale) unsigned long uframes; uframes = bw * 512UL << scale; - return DIV_ROUND_CLOSEST(uframes * 8000, 1000 * 1000); + return DIV_ROUND_CLOSEST(uframes * 8000, MEGA); } static u32 mbps_to_usb3_bw(unsigned int mbps, u8 scale) @@ -1976,7 +1977,7 @@ static u32 mbps_to_usb3_bw(unsigned int mbps, u8 scale) unsigned long uframes; /* 1 uframe is 1/8 ms (125 us) -> 1 / 8000 s */ - uframes = ((unsigned long)mbps * 1000 * 1000) / 8000; + uframes = ((unsigned long)mbps * MEGA) / 8000; return DIV_ROUND_UP(uframes, 512UL << scale); } -- GitLab From 580f4ea2cd1666bac76a67167d0901536e93c58c Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:24:55 +0800 Subject: [PATCH 1555/5631] dt-bindings: usb: usbmisc-imx: convert to DT schema Convert usbmisc-imx to DT schema format, add missing compatibles Reviewed-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-2-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/fsl,usbmisc.yaml | 68 +++++++++++++++++++ .../devicetree/bindings/usb/usbmisc-imx.txt | 19 ------ 2 files changed, 68 insertions(+), 19 deletions(-) create mode 100644 Documentation/devicetree/bindings/usb/fsl,usbmisc.yaml delete mode 100644 Documentation/devicetree/bindings/usb/usbmisc-imx.txt diff --git a/Documentation/devicetree/bindings/usb/fsl,usbmisc.yaml b/Documentation/devicetree/bindings/usb/fsl,usbmisc.yaml new file mode 100644 index 000000000000..2d3589d284b2 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/fsl,usbmisc.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/fsl,usbmisc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale i.MX wrapper module for Chipidea USB2 controller + +maintainers: + - Xu Yang + - Peng Fan + +properties: + compatible: + oneOf: + - enum: + - fsl,imx25-usbmisc + - fsl,imx27-usbmisc + - fsl,imx35-usbmisc + - fsl,imx51-usbmisc + - fsl,imx53-usbmisc + - fsl,imx6q-usbmisc + - fsl,vf610-usbmisc + - items: + - enum: + - fsl,imx6ul-usbmisc + - fsl,imx6sl-usbmisc + - fsl,imx6sx-usbmisc + - fsl,imx7d-usbmisc + - const: fsl,imx6q-usbmisc + - items: + - enum: + - fsl,imx7ulp-usbmisc + - fsl,imx8mm-usbmisc + - fsl,imx8mn-usbmisc + - const: fsl,imx7d-usbmisc + - const: fsl,imx6q-usbmisc + - items: + - const: fsl,imx6sll-usbmisc + - const: fsl,imx6ul-usbmisc + - const: fsl,imx6q-usbmisc + + clocks: + maxItems: 1 + + reg: + maxItems: 1 + + '#index-cells': + const: 1 + description: Cells used to describe usb controller index. + deprecated: true + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + usbmisc@2184800 { + compatible = "fsl,imx6q-usbmisc"; + reg = <0x02184800 0x200>; + #index-cells = <1>; + }; + +... diff --git a/Documentation/devicetree/bindings/usb/usbmisc-imx.txt b/Documentation/devicetree/bindings/usb/usbmisc-imx.txt deleted file mode 100644 index 29b8f65ff849..000000000000 --- a/Documentation/devicetree/bindings/usb/usbmisc-imx.txt +++ /dev/null @@ -1,19 +0,0 @@ -* Freescale i.MX non-core registers - -Required properties: -- #index-cells: Cells used to describe usb controller index. Should be <1> -- compatible: Should be one of below: - "fsl,imx6q-usbmisc" for imx6q - "fsl,vf610-usbmisc" for Vybrid vf610 - "fsl,imx6sx-usbmisc" for imx6sx - "fsl,imx7d-usbmisc" for imx7d - "fsl,imx7ulp-usbmisc" for imx7ulp - "fsl,imx8mm-usbmisc" for imx8mm -- reg: Should contain registers location and length - -Examples: -usbmisc@2184800 { - #index-cells = <1>; - compatible = "fsl,imx6q-usbmisc"; - reg = <0x02184800 0x200>; -}; -- GitLab From 4c8375d35f72f2daef1ac0c35831c43a36357d81 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:24:56 +0800 Subject: [PATCH 1556/5631] dt-bindings: usb: ci-hdrc-usb2: convert to DT schema format Convert the binding to DT schema format. To fix the dtbs_check error, some properties were also added, such as nvidia,phy, reset-names ulpi; missing compatibles are added. Signed-off-by: Peng Fan Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230322052504.2629429-3-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/ci-hdrc-usb2.txt | 159 ------- .../devicetree/bindings/usb/ci-hdrc-usb2.yaml | 447 ++++++++++++++++++ 2 files changed, 447 insertions(+), 159 deletions(-) delete mode 100644 Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt create mode 100644 Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt deleted file mode 100644 index 72ceea575d58..000000000000 --- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt +++ /dev/null @@ -1,159 +0,0 @@ -* USB2 ChipIdea USB controller for ci13xxx - -Required properties: -- compatible: should be one of: - "fsl,imx23-usb" - "fsl,imx27-usb" - "fsl,imx28-usb" - "fsl,imx6q-usb" - "fsl,imx6sl-usb" - "fsl,imx6sx-usb" - "fsl,imx6ul-usb" - "fsl,imx7d-usb" - "fsl,imx7ulp-usb" - "fsl,imx8mm-usb" - "lsi,zevio-usb" - "qcom,ci-hdrc" - "chipidea,usb2" - "xlnx,zynq-usb-2.20a" - "nvidia,tegra20-udc" - "nvidia,tegra30-udc" - "nvidia,tegra114-udc" - "nvidia,tegra124-udc" -- reg: base address and length of the registers -- interrupts: interrupt for the USB controller - -Recommended properies: -- phy_type: the type of the phy connected to the core. Should be one - of "utmi", "utmi_wide", "ulpi", "serial" or "hsic". Without this - property the PORTSC register won't be touched. -- dr_mode: One of "host", "peripheral" or "otg". Defaults to "otg" - -Deprecated properties: -- usb-phy: phandle for the PHY device. Use "phys" instead. -- fsl,usbphy: phandle of usb phy that connects to the port. Use "phys" instead. - -Optional properties: -- clocks: reference to the USB clock -- phys: reference to the USB PHY -- phy-names: should be "usb-phy" -- vbus-supply: reference to the VBUS regulator -- maximum-speed: limit the maximum connection speed to "full-speed". -- tpl-support: TPL (Targeted Peripheral List) feature for targeted hosts -- itc-setting: interrupt threshold control register control, the setting - should be aligned with ITC bits at register USBCMD. -- ahb-burst-config: it is vendor dependent, the required value should be - aligned with AHBBRST at SBUSCFG, the range is from 0x0 to 0x7. This - property is used to change AHB burst configuration, check the chipidea - spec for meaning of each value. If this property is not existed, it - will use the reset value. -- tx-burst-size-dword: it is vendor dependent, the tx burst size in dword - (4 bytes), This register represents the maximum length of a the burst - in 32-bit words while moving data from system memory to the USB - bus, the value of this property will only take effect if property - "ahb-burst-config" is set to 0, if this property is missing the reset - default of the hardware implementation will be used. -- rx-burst-size-dword: it is vendor dependent, the rx burst size in dword - (4 bytes), This register represents the maximum length of a the burst - in 32-bit words while moving data from the USB bus to system memory, - the value of this property will only take effect if property - "ahb-burst-config" is set to 0, if this property is missing the reset - default of the hardware implementation will be used. -- extcon: phandles to external connector devices. First phandle should point to - external connector, which provide "USB" cable events, the second should point - to external connector device, which provide "USB-HOST" cable events. If one - of the external connector devices is not required, empty <0> phandle should - be specified. -- phy-clkgate-delay-us: the delay time (us) between putting the PHY into - low power mode and gating the PHY clock. -- non-zero-ttctrl-ttha: after setting this property, the value of register - ttctrl.ttha will be 0x7f; if not, the value will be 0x0, this is the default - value. It needs to be very carefully for setting this property, it is - recommended that consult with your IC engineer before setting this value. - On the most of chipidea platforms, the "usage_tt" flag at RTL is 0, so this - property only affects siTD. - If this property is not set, the max packet size is 1023 bytes, and if - the total of packet size for pervious transactions are more than 256 bytes, - it can't accept any transactions within this frame. The use case is single - transaction, but higher frame rate. - If this property is set, the max packet size is 188 bytes, it can handle - more transactions than above case, it can accept transactions until it - considers the left room size within frame is less than 188 bytes, software - needs to make sure it does not send more than 90% - maximum_periodic_data_per_frame. The use case is multiple transactions, but - less frame rate. -- mux-controls: The mux control for toggling host/device output of this - controller. It's expected that a mux state of 0 indicates device mode and a - mux state of 1 indicates host mode. -- mux-control-names: Shall be "usb_switch" if mux-controls is specified. -- pinctrl-names: Names for optional pin modes in "default", "host", "device". - In case of HSIC-mode, "idle" and "active" pin modes are mandatory. In this - case, the "idle" state needs to pull down the data and strobe pin - and the "active" state needs to pull up the strobe pin. -- pinctrl-n: alternate pin modes - -i.mx specific properties -- fsl,usbmisc: phandler of non-core register device, with one - argument that indicate usb controller index -- disable-over-current: disable over current detect -- over-current-active-low: over current signal polarity is active low. -- over-current-active-high: over current signal polarity is active high. - It's recommended to specify the over current polarity. -- power-active-high: power signal polarity is active high -- external-vbus-divider: enables off-chip resistor divider for Vbus -- samsung,picophy-pre-emp-curr-control: HS Transmitter Pre-Emphasis Current - Control. This signal controls the amount of current sourced to the - USB_OTG*_DP and USB_OTG*_DN pins after a J-to-K or K-to-J transition. - The range is from 0x0 to 0x3, the default value is 0x1. - Details can refer to TXPREEMPAMPTUNE0 bits of USBNC_n_PHY_CFG1. -- samsung,picophy-dc-vol-level-adjust: HS DC Voltage Level Adjustment. - Adjust the high-speed transmitter DC level voltage. - The range is from 0x0 to 0xf, the default value is 0x3. - Details can refer to TXVREFTUNE0 bits of USBNC_n_PHY_CFG1. - -Example: - - usb@f7ed0000 { - compatible = "chipidea,usb2"; - reg = <0xf7ed0000 0x10000>; - interrupts = ; - clocks = <&chip CLKID_USB0>; - phys = <&usb_phy0>; - phy-names = "usb-phy"; - vbus-supply = <®_usb0_vbus>; - itc-setting = <0x4>; /* 4 micro-frames */ - /* Incremental burst of unspecified length */ - ahb-burst-config = <0x0>; - tx-burst-size-dword = <0x10>; /* 64 bytes */ - rx-burst-size-dword = <0x10>; - extcon = <0>, <&usb_id>; - phy-clkgate-delay-us = <400>; - mux-controls = <&usb_switch>; - mux-control-names = "usb_switch"; - }; - -Example for HSIC: - - usb@2184400 { - compatible = "fsl,imx6q-usb", "fsl,imx27-usb"; - reg = <0x02184400 0x200>; - interrupts = <0 41 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clks IMX6QDL_CLK_USBOH3>; - fsl,usbphy = <&usbphynop1>; - fsl,usbmisc = <&usbmisc 2>; - phy_type = "hsic"; - dr_mode = "host"; - ahb-burst-config = <0x0>; - tx-burst-size-dword = <0x10>; - rx-burst-size-dword = <0x10>; - pinctrl-names = "idle", "active"; - pinctrl-0 = <&pinctrl_usbh2_idle>; - pinctrl-1 = <&pinctrl_usbh2_active>; - #address-cells = <1>; - #size-cells = <0>; - - usbnet: ethernet@1 { - compatible = "usb424,9730"; - reg = <1>; - }; - }; diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml new file mode 100644 index 000000000000..e5e4dbc5a7a0 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml @@ -0,0 +1,447 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/ci-hdrc-usb2.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: USB2 ChipIdea USB controller + +maintainers: + - Xu Yang + - Peng Fan + +properties: + compatible: + oneOf: + - enum: + - chipidea,usb2 + - lsi,zevio-usb + - nvidia,tegra20-ehci + - nvidia,tegra20-udc + - nvidia,tegra30-ehci + - nvidia,tegra30-udc + - nvidia,tegra114-udc + - nvidia,tegra124-udc + - qcom,ci-hdrc + - items: + - enum: + - nvidia,tegra114-ehci + - nvidia,tegra124-ehci + - nvidia,tegra210-ehci + - const: nvidia,tegra30-ehci + - items: + - enum: + - fsl,imx23-usb + - fsl,imx25-usb + - fsl,imx28-usb + - fsl,imx50-usb + - fsl,imx51-usb + - fsl,imx53-usb + - fsl,imx6q-usb + - fsl,imx6sl-usb + - fsl,imx6sx-usb + - fsl,imx6ul-usb + - fsl,imx7d-usb + - fsl,vf610-usb + - const: fsl,imx27-usb + - items: + - const: fsl,imx8dxl-usb + - const: fsl,imx7ulp-usb + - const: fsl,imx6ul-usb + - items: + - enum: + - fsl,imx8mm-usb + - fsl,imx8mn-usb + - const: fsl,imx7d-usb + - const: fsl,imx27-usb + - items: + - enum: + - fsl,imx6sll-usb + - fsl,imx7ulp-usb + - const: fsl,imx6ul-usb + - const: fsl,imx27-usb + - items: + - const: xlnx,zynq-usb-2.20a + - const: chipidea,usb2 + + reg: + minItems: 1 + maxItems: 2 + + interrupts: + minItems: 1 + maxItems: 2 + + clocks: + minItems: 1 + maxItems: 2 + + clock-names: + minItems: 1 + maxItems: 2 + + dr_mode: true + + power-domains: + maxItems: 1 + + resets: + maxItems: 1 + + reset-names: + maxItems: 1 + + "#reset-cells": + const: 1 + + phy_type: true + + itc-setting: + description: + interrupt threshold control register control, the setting should be + aligned with ITC bits at register USBCMD. + $ref: /schemas/types.yaml#/definitions/uint32 + + ahb-burst-config: + description: + it is vendor dependent, the required value should be aligned with + AHBBRST at SBUSCFG, the range is from 0x0 to 0x7. This property is + used to change AHB burst configuration, check the chipidea spec for + meaning of each value. If this property is not existed, it will use + the reset value. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0x0 + maximum: 0x7 + + tx-burst-size-dword: + description: + it is vendor dependent, the tx burst size in dword (4 bytes), This + register represents the maximum length of a the burst in 32-bit + words while moving data from system memory to the USB bus, the value + of this property will only take effect if property "ahb-burst-config" + is set to 0, if this property is missing the reset default of the + hardware implementation will be used. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0x0 + maximum: 0x20 + + rx-burst-size-dword: + description: + it is vendor dependent, the rx burst size in dword (4 bytes), This + register represents the maximum length of a the burst in 32-bit words + while moving data from the USB bus to system memory, the value of + this property will only take effect if property "ahb-burst-config" + is set to 0, if this property is missing the reset default of the + hardware implementation will be used. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0x0 + maximum: 0x20 + + extcon: + description: + Phandles to external connector devices. First phandle should point + to external connector, which provide "USB" cable events, the second + should point to external connector device, which provide "USB-HOST" + cable events. If one of the external connector devices is not + required, empty <0> phandle should be specified. + $ref: /schemas/types.yaml#/definitions/phandle-array + minItems: 1 + items: + - description: vbus extcon + - description: id extcon + + phy-clkgate-delay-us: + description: + The delay time (us) between putting the PHY into low power mode and + gating the PHY clock. + + non-zero-ttctrl-ttha: + description: + After setting this property, the value of register ttctrl.ttha + will be 0x7f; if not, the value will be 0x0, this is the default + value. It needs to be very carefully for setting this property, it + is recommended that consult with your IC engineer before setting + this value. On the most of chipidea platforms, the "usage_tt" flag + at RTL is 0, so this property only affects siTD. + + If this property is not set, the max packet size is 1023 bytes, and + if the total of packet size for pervious transactions are more than + 256 bytes, it can't accept any transactions within this frame. The + use case is single transaction, but higher frame rate. + + If this property is set, the max packet size is 188 bytes, it can + handle more transactions than above case, it can accept transactions + until it considers the left room size within frame is less than 188 + bytes, software needs to make sure it does not send more than 90% + maximum_periodic_data_per_frame. The use case is multiple + transactions, but less frame rate. + type: boolean + + mux-controls: + description: + The mux control for toggling host/device output of this controller. + It's expected that a mux state of 0 indicates device mode and a mux + state of 1 indicates host mode. + maxItems: 1 + + mux-control-names: + const: usb_switch + + operating-points-v2: + description: A phandle to the OPP table containing the performance states. + $ref: /schemas/types.yaml#/definitions/phandle + + pinctrl-names: + description: + Names for optional pin modes in "default", "host", "device". + In case of HSIC-mode, "idle" and "active" pin modes are mandatory. + In this case, the "idle" state needs to pull down the data and + strobe pin and the "active" state needs to pull up the strobe pin. + oneOf: + - items: + - const: idle + - const: active + - items: + - const: default + - enum: + - host + - device + - items: + - const: default + + pinctrl-0: + maxItems: 1 + + pinctrl-1: + maxItems: 1 + + phys: + maxItems: 1 + + phy-names: + const: usb-phy + + phy-select: + description: + Phandler of TCSR node with two argument that indicate register + offset, and phy index + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - description: phandle to TCSR node + - description: register offset + - description: phy index + + vbus-supply: + description: reference to the VBUS regulator. + + fsl,usbmisc: + description: + Phandler of non-core register device, with one argument that + indicate usb controller index + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: phandle to usbmisc node + - description: index of usb controller + + fsl,anatop: + description: phandle for the anatop node. + $ref: /schemas/types.yaml#/definitions/phandle + + disable-over-current: + type: boolean + description: disable over current detect + + over-current-active-low: + type: boolean + description: over current signal polarity is active low + + over-current-active-high: + type: boolean + description: + Over current signal polarity is active high. It's recommended to + specify the over current polarity. + + power-active-high: + type: boolean + description: power signal polarity is active high + + external-vbus-divider: + type: boolean + description: enables off-chip resistor divider for Vbus + + samsung,picophy-pre-emp-curr-control: + description: + HS Transmitter Pre-Emphasis Current Control. This signal controls + the amount of current sourced to the USB_OTG*_DP and USB_OTG*_DN + pins after a J-to-K or K-to-J transition. The range is from 0x0 to + 0x3, the default value is 0x1. Details can refer to TXPREEMPAMPTUNE0 + bits of USBNC_n_PHY_CFG1. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0x0 + maximum: 0x3 + + samsung,picophy-dc-vol-level-adjust: + description: + HS DC Voltage Level Adjustment. Adjust the high-speed transmitter DC + level voltage. The range is from 0x0 to 0xf, the default value is + 0x3. Details can refer to TXVREFTUNE0 bits of USBNC_n_PHY_CFG1. + $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 0x0 + maximum: 0xf + + usb-phy: + description: phandle for the PHY device. Use "phys" instead. + $ref: /schemas/types.yaml#/definitions/phandle + deprecated: true + + fsl,usbphy: + description: phandle of usb phy that connects to the port. Use "phys" instead. + $ref: /schemas/types.yaml#/definitions/phandle + deprecated: true + + nvidia,phy: + description: phandle of usb phy that connects to the port. Use "phys" instead. + $ref: /schemas/types.yaml#/definitions/phandle + deprecated: true + + nvidia,needs-double-reset: + description: Indicates double reset or not. + type: boolean + deprecated: true + + port: + description: + Any connector to the data bus of this controller should be modelled + using the OF graph bindings specified, if the "usb-role-switch" + property is used. + $ref: /schemas/graph.yaml#/properties/port + + reset-gpios: + maxItems: 1 + + ulpi: + type: object + properties: + phy: + description: The phy child node for Qcom chips. + type: object + $ref: /schemas/phy/qcom,usb-hs-phy.yaml + +dependencies: + port: [ usb-role-switch ] + mux-controls: [ mux-control-names ] + +required: + - compatible + - reg + - interrupts + +allOf: + - $ref: usb-hcd.yaml# + - $ref: usb-drd.yaml# + - if: + properties: + phy_type: + const: hsic + required: + - phy_type + then: + properties: + pinctrl-names: + items: + - const: idle + - const: active + else: + properties: + pinctrl-names: + minItems: 1 + maxItems: 2 + oneOf: + - items: + - const: default + - enum: + - host + - device + - items: + - const: default + - if: + properties: + compatible: + contains: + enum: + - chipidea,usb2 + - lsi,zevio-usb + - nvidia,tegra20-udc + - nvidia,tegra30-udc + - nvidia,tegra114-udc + - nvidia,tegra124-udc + - qcom,ci-hdrc + - xlnx,zynq-usb-2.20a + then: + properties: + fsl,usbmisc: false + disable-over-current: false + over-current-active-low: false + over-current-active-high: false + power-active-high: false + external-vbus-divider: false + samsung,picophy-pre-emp-curr-control: false + samsung,picophy-dc-vol-level-adjust: false + +unevaluatedProperties: false + +examples: + - | + #include + #include + + usb@f7ed0000 { + compatible = "chipidea,usb2"; + reg = <0xf7ed0000 0x10000>; + interrupts = ; + clocks = <&chip CLKID_USB0>; + phys = <&usb_phy0>; + phy-names = "usb-phy"; + vbus-supply = <®_usb0_vbus>; + itc-setting = <0x4>; /* 4 micro-frames */ + /* Incremental burst of unspecified length */ + ahb-burst-config = <0x0>; + tx-burst-size-dword = <0x10>; /* 64 bytes */ + rx-burst-size-dword = <0x10>; + extcon = <0>, <&usb_id>; + phy-clkgate-delay-us = <400>; + mux-controls = <&usb_switch>; + mux-control-names = "usb_switch"; + }; + + # Example for HSIC: + - | + #include + #include + + usb@2184400 { + compatible = "fsl,imx6q-usb", "fsl,imx27-usb"; + reg = <0x02184400 0x200>; + interrupts = <0 41 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clks IMX6QDL_CLK_USBOH3>; + fsl,usbphy = <&usbphynop1>; + fsl,usbmisc = <&usbmisc 2>; + phy_type = "hsic"; + dr_mode = "host"; + ahb-burst-config = <0x0>; + tx-burst-size-dword = <0x10>; + rx-burst-size-dword = <0x10>; + pinctrl-names = "idle", "active"; + pinctrl-0 = <&pinctrl_usbh2_idle>; + pinctrl-1 = <&pinctrl_usbh2_active>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet@1 { + compatible = "usb424,9730"; + reg = <1>; + }; + }; + +... -- GitLab From 64de129680a45a25b822bd0bf4c4aeb62f1b9c2f Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:24:57 +0800 Subject: [PATCH 1557/5631] dt-bindings: usb: usb-nop-xceiv: add power-domains property Add power-domains optional property Acked-by: Rob Herring Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-4-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/usb-nop-xceiv.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/usb-nop-xceiv.yaml b/Documentation/devicetree/bindings/usb/usb-nop-xceiv.yaml index 921b986adc47..6734f4d3aa78 100644 --- a/Documentation/devicetree/bindings/usb/usb-nop-xceiv.yaml +++ b/Documentation/devicetree/bindings/usb/usb-nop-xceiv.yaml @@ -27,6 +27,9 @@ properties: vcc-supply: description: phandle to the regulator that provides power to the PHY. + power-domains: + maxItems: 1 + reset-gpios: maxItems: 1 -- GitLab From 835765da87d8d07db20218a5676bb5b3d9f2e7c6 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:24:58 +0800 Subject: [PATCH 1558/5631] arm64: dts: imx8mn: update usb compatible Update usb compatible per binding doc Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-5-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8mn.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index 9e0ddd6b7a32..7b58660d9ef4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -1091,7 +1091,7 @@ }; usbotg1: usb@32e40000 { - compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb"; + compatible = "fsl,imx8mn-usb", "fsl,imx7d-usb", "fsl,imx27-usb"; reg = <0x32e40000 0x200>; interrupts = ; clocks = <&clk IMX8MN_CLK_USB1_CTRL_ROOT>; @@ -1105,7 +1105,8 @@ }; usbmisc1: usbmisc@32e40200 { - compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc"; + compatible = "fsl,imx8mn-usbmisc", "fsl,imx7d-usbmisc", + "fsl,imx6q-usbmisc"; #index-cells = <1>; reg = <0x32e40200 0x200>; }; -- GitLab From 69fef68e4c8f5f80539b6a7d4f76af0de0732da3 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:24:59 +0800 Subject: [PATCH 1559/5631] arm64: dts: imx8mm: update usb compatible Update usb compatible per binding doc Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-6-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8mm.dtsi | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index 31f4548f85cf..719e38223bef 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -1198,7 +1198,7 @@ }; usbotg1: usb@32e40000 { - compatible = "fsl,imx8mm-usb", "fsl,imx7d-usb"; + compatible = "fsl,imx8mm-usb", "fsl,imx7d-usb", "fsl,imx27-usb"; reg = <0x32e40000 0x200>; interrupts = ; clocks = <&clk IMX8MM_CLK_USB1_CTRL_ROOT>; @@ -1212,13 +1212,14 @@ }; usbmisc1: usbmisc@32e40200 { - compatible = "fsl,imx8mm-usbmisc", "fsl,imx7d-usbmisc"; + compatible = "fsl,imx8mm-usbmisc", "fsl,imx7d-usbmisc", + "fsl,imx6q-usbmisc"; #index-cells = <1>; reg = <0x32e40200 0x200>; }; usbotg2: usb@32e50000 { - compatible = "fsl,imx8mm-usb", "fsl,imx7d-usb"; + compatible = "fsl,imx8mm-usb", "fsl,imx7d-usb", "fsl,imx27-usb"; reg = <0x32e50000 0x200>; interrupts = ; clocks = <&clk IMX8MM_CLK_USB1_CTRL_ROOT>; @@ -1232,7 +1233,8 @@ }; usbmisc2: usbmisc@32e50200 { - compatible = "fsl,imx8mm-usbmisc", "fsl,imx7d-usbmisc"; + compatible = "fsl,imx8mm-usbmisc", "fsl,imx7d-usbmisc", + "fsl,imx6q-usbmisc"; #index-cells = <1>; reg = <0x32e50200 0x200>; }; -- GitLab From 276dd9a66e7157a0f317a7a59bf9fbe8ec0cd3d0 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:25:00 +0800 Subject: [PATCH 1560/5631] arm64: dts: imx8: update usb compatible Update usb compatible per binding doc Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-7-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 4852760adeee..6ed084862345 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -35,7 +35,7 @@ conn_subsys: bus@5b000000 { }; usbotg1: usb@5b0d0000 { - compatible = "fsl,imx7ulp-usb"; + compatible = "fsl,imx7ulp-usb", "fsl,imx6ul-usb", "fsl,imx27-usb"; reg = <0x5b0d0000 0x200>; interrupt-parent = <&gic>; interrupts = ; @@ -51,7 +51,7 @@ conn_subsys: bus@5b000000 { usbmisc1: usbmisc@5b0d0200 { #index-cells = <1>; - compatible = "fsl,imx7ulp-usbmisc", "fsl,imx6q-usbmisc"; + compatible = "fsl,imx7ulp-usbmisc", "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc"; reg = <0x5b0d0200 0x200>; }; -- GitLab From 2656e9f5119f8dfb9796e4ba11082ffe49d8cecc Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:25:01 +0800 Subject: [PATCH 1561/5631] arm64: dts: imx8dxl: update usb compatible Update usb compatible per binding doc Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-8-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi index ca195e6d8f37..88913869ae9c 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi @@ -34,7 +34,7 @@ }; usbotg2: usb@5b0e0000 { - compatible = "fsl,imx8dxl-usb", "fsl,imx7ulp-usb"; + compatible = "fsl,imx8dxl-usb", "fsl,imx7ulp-usb", "fsl,imx6ul-usb"; reg = <0x5b0e0000 0x200>; interrupt-parent = <&gic>; interrupts = ; @@ -63,7 +63,7 @@ usbmisc2: usbmisc@5b0e0200 { #index-cells = <1>; - compatible = "fsl,imx7ulp-usbmisc"; + compatible = "fsl,imx7ulp-usbmisc", "fsl,imx7d-usbmisc", "fsl,imx6q-usbmisc"; reg = <0x5b0e0200 0x200>; }; -- GitLab From 6304876355fb6ac60fef306fff6da71bb08401b7 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:25:02 +0800 Subject: [PATCH 1562/5631] arm64: dts: imx8dxl: drop #stream-id-cells for usb node There is no SMMU in i.MX8DXL, drop #stream-id-cells which is for SMMU-v2. Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-9-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi index 88913869ae9c..652493ae4bb5 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8dxl-ss-conn.dtsi @@ -49,7 +49,6 @@ ahb-burst-config = <0x0>; tx-burst-size-dword = <0x10>; rx-burst-size-dword = <0x10>; - #stream-id-cells = <1>; power-domains = <&pd IMX_SC_R_USB_1>; status = "disabled"; -- GitLab From 79e94aa19736ec8f38ec02880eeec37cc5900bd8 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Wed, 22 Mar 2023 13:25:04 +0800 Subject: [PATCH 1563/5631] ARM64: dts: imx7ulp: update usb compatible Per binding doc, update the compatible Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230322052504.2629429-11-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/imx7ulp.dtsi | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/imx7ulp.dtsi b/arch/arm/boot/dts/imx7ulp.dtsi index 7f7d2d5122fb..f91bf719d4e2 100644 --- a/arch/arm/boot/dts/imx7ulp.dtsi +++ b/arch/arm/boot/dts/imx7ulp.dtsi @@ -189,7 +189,7 @@ }; usbotg1: usb@40330000 { - compatible = "fsl,imx7ulp-usb", "fsl,imx6ul-usb"; + compatible = "fsl,imx7ulp-usb", "fsl,imx6ul-usb", "fsl,imx27-usb"; reg = <0x40330000 0x200>; interrupts = ; clocks = <&pcc2 IMX7ULP_CLK_USB0>; @@ -202,7 +202,8 @@ }; usbmisc1: usbmisc@40330200 { - compatible = "fsl,imx7ulp-usbmisc", "fsl,imx7d-usbmisc"; + compatible = "fsl,imx7ulp-usbmisc", "fsl,imx7d-usbmisc", + "fsl,imx6q-usbmisc"; #index-cells = <1>; reg = <0x40330200 0x200>; }; -- GitLab From b93c2a68f3d9dc98ec30dcb342ae47c1c8d09d18 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:47:57 -0700 Subject: [PATCH 1564/5631] usb: gadget: Properly configure the device for remote wakeup The wakeup bit in the bmAttributes field indicates whether the device is configured for remote wakeup. But this field should be allowed to set only if the UDC supports such wakeup mechanism. So configure this field based on UDC capability. Also inform the UDC whether the device is configured for remote wakeup by implementing a gadget op. Reviewed-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-2-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 18 ++++++++++++++++++ drivers/usb/gadget/configfs.c | 3 +++ drivers/usb/gadget/udc/core.c | 27 +++++++++++++++++++++++++++ drivers/usb/gadget/udc/trace.h | 5 +++++ include/linux/usb/composite.h | 2 ++ include/linux/usb/gadget.h | 8 ++++++++ 6 files changed, 63 insertions(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index f1ecd12b62c3..00c89571de2a 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -513,6 +513,19 @@ static u8 encode_bMaxPower(enum usb_device_speed speed, return min(val, 900U) / 8; } +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c) +{ + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) { + /* Reset the rw bit if gadget is not capable of it */ + if (!g->wakeup_capable && g->ops->set_remote_wakeup) { + WARN(c->cdev, "Clearing wakeup bit for config c.%d\n", + c->bConfigurationValue); + c->bmAttributes &= ~USB_CONFIG_ATT_WAKEUP; + } + } +} + static int config_buf(struct usb_configuration *config, enum usb_device_speed speed, void *buf, u8 type) { @@ -994,6 +1007,11 @@ static int set_config(struct usb_composite_dev *cdev, power = min(power, 500U); else power = min(power, 900U); + + if (USB_CONFIG_ATT_WAKEUP & c->bmAttributes) + usb_gadget_set_remote_wakeup(gadget, 1); + else + usb_gadget_set_remote_wakeup(gadget, 0); done: if (power <= USB_SELF_POWER_VBUS_MAX_DRAW) usb_gadget_set_selfpowered(gadget); diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index b9f1136aa0a2..4c639e9ddedc 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1761,6 +1761,9 @@ static int configfs_composite_bind(struct usb_gadget *gadget, if (gadget_is_otg(gadget)) c->descriptors = otg_desc; + /* Properly configure the bmAttributes wakeup bit */ + check_remote_wakeup_config(gadget, c); + cfg = container_of(c, struct config_usb_cfg, c); if (!list_empty(&cfg->string_list)) { i = 0; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 23b0629a8774..3dcbba739db6 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -513,6 +513,33 @@ int usb_gadget_wakeup(struct usb_gadget *gadget) } EXPORT_SYMBOL_GPL(usb_gadget_wakeup); +/** + * usb_gadget_set_remote_wakeup - configures the device remote wakeup feature. + * @gadget:the device being configured for remote wakeup + * @set:value to be configured. + * + * set to one to enable remote wakeup feature and zero to disable it. + * + * returns zero on success, else negative errno. + */ +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ + int ret = 0; + + if (!gadget->ops->set_remote_wakeup) { + ret = -EOPNOTSUPP; + goto out; + } + + ret = gadget->ops->set_remote_wakeup(gadget, set); + +out: + trace_usb_gadget_set_remote_wakeup(gadget, ret); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_set_remote_wakeup); + /** * usb_gadget_set_selfpowered - sets the device selfpowered feature. * @gadget:the device being declared as self-powered diff --git a/drivers/usb/gadget/udc/trace.h b/drivers/usb/gadget/udc/trace.h index abdbcb1bacb0..a5ed26fbc2da 100644 --- a/drivers/usb/gadget/udc/trace.h +++ b/drivers/usb/gadget/udc/trace.h @@ -91,6 +91,11 @@ DEFINE_EVENT(udc_log_gadget, usb_gadget_wakeup, TP_ARGS(g, ret) ); +DEFINE_EVENT(udc_log_gadget, usb_gadget_set_remote_wakeup, + TP_PROTO(struct usb_gadget *g, int ret), + TP_ARGS(g, ret) +); + DEFINE_EVENT(udc_log_gadget, usb_gadget_set_selfpowered, TP_PROTO(struct usb_gadget *g, int ret), TP_ARGS(g, ret) diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 608dc962748b..d949e91ceb48 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -413,6 +413,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c); static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 00750f7020f3..1d796128030b 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -384,6 +385,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -445,6 +448,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -601,6 +606,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -616,6 +622,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) -- GitLab From 047161686b813ae9035a3fb342ba8b6932053492 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:47:58 -0700 Subject: [PATCH 1565/5631] usb: dwc3: Add remote wakeup handling An usb device can initate a remote wakeup and bring the link out of suspend as dictated by the DEVICE_REMOTE_WAKEUP feature selector. Add support to handle this packet and set the remote wakeup capability. Some hosts may take longer time to initiate the resume signaling after device triggers a remote wakeup. So add async support to the wakeup API by enabling link status change events. Acked-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-3-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 2 ++ drivers/usb/dwc3/ep0.c | 7 ++++ drivers/usb/dwc3/gadget.c | 76 +++++++++++++++++++++++++++++++++++---- 3 files changed, 79 insertions(+), 6 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 912208585da2..8541708ed2cb 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1113,6 +1113,7 @@ struct dwc3_scratchpad_array { * 3 - Reserved * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. + * @wakeup_configured: set if the device is configured for remote wakeup. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1331,6 +1332,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; + unsigned wakeup_configured:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 61de693461da..8aa14a596406 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -356,6 +356,9 @@ static int dwc3_ep0_handle_status(struct dwc3 *dwc, usb_status |= 1 << USB_DEV_STAT_U1_ENABLED; if (reg & DWC3_DCTL_INITU2ENA) usb_status |= 1 << USB_DEV_STAT_U2_ENABLED; + } else { + usb_status |= dwc->gadget->wakeup_armed << + USB_DEVICE_REMOTE_WAKEUP; } break; @@ -476,6 +479,10 @@ static int dwc3_ep0_handle_device(struct dwc3 *dwc, switch (wValue) { case USB_DEVICE_REMOTE_WAKEUP: + if (dwc->wakeup_configured) + dwc->gadget->wakeup_armed = set; + else + ret = -EINVAL; break; /* * 9.4.1 says only for SS, in AddressState only for diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 29f8f9311d77..7ceff08a1b8c 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -258,7 +258,7 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd, return ret; } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc); +static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async); /** * dwc3_send_gadget_ep_cmd - issue an endpoint command @@ -325,7 +325,7 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd, fallthrough; case DWC3_LINK_STATE_U3: - ret = __dwc3_gadget_wakeup(dwc); + ret = __dwc3_gadget_wakeup(dwc, false); dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n", ret); break; @@ -2273,6 +2273,22 @@ static const struct usb_ep_ops dwc3_gadget_ep_ops = { /* -------------------------------------------------------------------------- */ +static void dwc3_gadget_enable_linksts_evts(struct dwc3 *dwc, bool set) +{ + u32 reg; + + if (DWC3_VER_IS_PRIOR(DWC3, 250A)) + return; + + reg = dwc3_readl(dwc->regs, DWC3_DEVTEN); + if (set) + reg |= DWC3_DEVTEN_ULSTCNGEN; + else + reg &= ~DWC3_DEVTEN_ULSTCNGEN; + + dwc3_writel(dwc->regs, DWC3_DEVTEN, reg); +} + static int dwc3_gadget_get_frame(struct usb_gadget *g) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2280,7 +2296,7 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g) return __dwc3_gadget_get_frame(dwc); } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc) +static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) { int retries; @@ -2311,9 +2327,13 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc) return -EINVAL; } + if (async) + dwc3_gadget_enable_linksts_evts(dwc, true); + ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV); if (ret < 0) { dev_err(dwc->dev, "failed to put link in Recovery\n"); + dwc3_gadget_enable_linksts_evts(dwc, false); return ret; } @@ -2325,6 +2345,13 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCTL, reg); } + /* + * Since link status change events are enabled we will receive + * an U0 event when wakeup is successful. So bail out. + */ + if (async) + return 0; + /* poll until Link State changes to ON */ retries = 20000; @@ -2350,13 +2377,36 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g) unsigned long flags; int ret; + if (!dwc->wakeup_configured) { + dev_err(dwc->dev, "remote wakeup not configured\n"); + return -EINVAL; + } + spin_lock_irqsave(&dwc->lock, flags); - ret = __dwc3_gadget_wakeup(dwc); + if (!dwc->gadget->wakeup_armed) { + dev_err(dwc->dev, "not armed for remote wakeup\n"); + spin_unlock_irqrestore(&dwc->lock, flags); + return -EINVAL; + } + ret = __dwc3_gadget_wakeup(dwc, true); + spin_unlock_irqrestore(&dwc->lock, flags); return ret; } +static int dwc3_gadget_set_remote_wakeup(struct usb_gadget *g, int set) +{ + struct dwc3 *dwc = gadget_to_dwc(g); + unsigned long flags; + + spin_lock_irqsave(&dwc->lock, flags); + dwc->wakeup_configured = !!set; + spin_unlock_irqrestore(&dwc->lock, flags); + + return 0; +} + static int dwc3_gadget_set_selfpowered(struct usb_gadget *g, int is_selfpowered) { @@ -2982,6 +3032,7 @@ static void dwc3_gadget_async_callbacks(struct usb_gadget *g, bool enable) static const struct usb_gadget_ops dwc3_gadget_ops = { .get_frame = dwc3_gadget_get_frame, .wakeup = dwc3_gadget_wakeup, + .set_remote_wakeup = dwc3_gadget_set_remote_wakeup, .set_selfpowered = dwc3_gadget_set_selfpowered, .pullup = dwc3_gadget_pullup, .udc_start = dwc3_gadget_start, @@ -3827,6 +3878,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc->gadget->speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; + dwc->gadget->wakeup_armed = false; + dwc3_gadget_enable_linksts_evts(dwc, false); usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED); if (dwc->ep0state != EP0_SETUP_PHASE) { @@ -3920,6 +3973,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) reg &= ~DWC3_DCTL_TSTCTRL_MASK; dwc3_gadget_dctl_write_safe(dwc, reg); dwc->test_mode = false; + dwc->gadget->wakeup_armed = false; + dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_clear_stall_all_ep(dwc); /* Reset device address to zero */ @@ -4072,7 +4127,7 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) */ } -static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc) +static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { /* * TODO take core out of low power mode when that's @@ -4084,6 +4139,8 @@ static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc) dwc->gadget_driver->resume(dwc->gadget); spin_lock(&dwc->lock); } + + dwc->link_state = evtinfo & DWC3_LINK_STATE_MASK; } static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, @@ -4165,6 +4222,12 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, } switch (next) { + case DWC3_LINK_STATE_U0: + if (dwc->gadget->wakeup_armed) { + dwc3_gadget_enable_linksts_evts(dwc, false); + dwc3_resume_gadget(dwc); + } + break; case DWC3_LINK_STATE_U1: if (dwc->speed == USB_SPEED_SUPER) dwc3_suspend_gadget(dwc); @@ -4233,7 +4296,7 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, dwc3_gadget_conndone_interrupt(dwc); break; case DWC3_DEVICE_EVENT_WAKEUP: - dwc3_gadget_wakeup_interrupt(dwc); + dwc3_gadget_wakeup_interrupt(dwc, event->event_info); break; case DWC3_DEVICE_EVENT_HIBER_REQ: if (dev_WARN_ONCE(dwc->dev, !dwc->has_hibernation, @@ -4481,6 +4544,7 @@ int dwc3_gadget_init(struct dwc3 *dwc) dwc->gadget->sg_supported = true; dwc->gadget->name = "dwc3-gadget"; dwc->gadget->lpm_capable = !dwc->usb2_gadget_lpm_disable; + dwc->gadget->wakeup_capable = true; /* * FIXME We might be setting max_speed to Date: Fri, 24 Mar 2023 14:47:59 -0700 Subject: [PATCH 1566/5631] usb: gadget: Add function wakeup support USB3.2 spec section 9.2.5.4 quotes that a function may signal that it wants to exit from Function Suspend by sending a Function Wake Notification to the host if it is enabled for function remote wakeup. Add an api in composite layer that can be used by the function drivers to support this feature. Also expose a gadget op so that composite layer can trigger a wakeup request to the UDC driver. Reviewed-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-4-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 40 ++++++++++++++++++++++++++++++++++ include/linux/usb/composite.h | 6 +++++ include/linux/usb/gadget.h | 1 + 3 files changed, 47 insertions(+) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 00c89571de2a..d3fd2d1d8096 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -492,6 +492,46 @@ int usb_interface_id(struct usb_configuration *config, } EXPORT_SYMBOL_GPL(usb_interface_id); +/** + * usb_func_wakeup - sends function wake notification to the host. + * @func: function that sends the remote wakeup notification. + * + * Applicable to devices operating at enhanced superspeed when usb + * functions are put in function suspend state and armed for function + * remote wakeup. On completion, function wake notification is sent. If + * the device is in low power state it tries to bring the device to active + * state before sending the wake notification. Since it is a synchronous + * call, caller must take care of not calling it in interrupt context. + * For devices operating at lower speeds returns negative errno. + * + * Returns zero on success, else negative errno. + */ +int usb_func_wakeup(struct usb_function *func) +{ + struct usb_gadget *gadget = func->config->cdev->gadget; + int id; + + if (!gadget->ops->func_wakeup) + return -EOPNOTSUPP; + + if (!func->func_wakeup_armed) { + ERROR(func->config->cdev, "not armed for func remote wakeup\n"); + return -EINVAL; + } + + for (id = 0; id < MAX_CONFIG_INTERFACES; id++) + if (func->config->interface[id] == func) + break; + + if (id == MAX_CONFIG_INTERFACES) { + ERROR(func->config->cdev, "Invalid function\n"); + return -EINVAL; + } + + return gadget->ops->func_wakeup(gadget, id); +} +EXPORT_SYMBOL_GPL(usb_func_wakeup); + static u8 encode_bMaxPower(enum usb_device_speed speed, struct usb_configuration *c) { diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index d949e91ceb48..a2448e98854f 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -150,6 +150,9 @@ struct usb_os_desc_table { * GetStatus() request when the recipient is Interface. * @func_suspend: callback to be called when * SetFeature(FUNCTION_SUSPEND) is reseived + * @func_suspended: Indicates whether the function is in function suspend state. + * @func_wakeup_armed: Indicates whether the function is armed by the host for + * wakeup signaling. * * A single USB function uses one or more interfaces, and should in most * cases support operation at both full and high speeds. Each function is @@ -220,6 +223,8 @@ struct usb_function { int (*get_status)(struct usb_function *); int (*func_suspend)(struct usb_function *, u8 suspend_opt); + bool func_suspended; + bool func_wakeup_armed; /* private: */ /* internals */ struct list_head list; @@ -241,6 +246,7 @@ int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); +int usb_func_wakeup(struct usb_function *func); #define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 1d796128030b..75bda0783395 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,7 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*func_wakeup)(struct usb_gadget *gadget, int intf_id); int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); -- GitLab From 92c08a84b53e5dd1f2150e870db2ae9e5a5459e1 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:48:00 -0700 Subject: [PATCH 1567/5631] usb: dwc3: Add function suspend and function wakeup support USB host sends function suspend and function resume notifications to the interface through SET_FEATURE/CLEAR_FEATURE setup packets. Add support to handle these packets by delegating the requests to composite layer. Also add support to handle function wake notification requests to exit from function suspend state. Acked-by: Thinh Nguyen Signed-off-by: Elson Roy Serrao Link: https://lore.kernel.org/r/1679694482-16430-5-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 3 +++ drivers/usb/dwc3/debug.h | 2 ++ drivers/usb/dwc3/ep0.c | 12 ++++------- drivers/usb/dwc3/gadget.c | 42 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 51 insertions(+), 8 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 8541708ed2cb..26c8efefbff9 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -527,6 +527,7 @@ #define DWC3_DGCMD_SET_ENDPOINT_NRDY 0x0c #define DWC3_DGCMD_SET_ENDPOINT_PRIME 0x0d #define DWC3_DGCMD_RUN_SOC_BUS_LOOPBACK 0x10 +#define DWC3_DGCMD_DEV_NOTIFICATION 0x07 #define DWC3_DGCMD_STATUS(n) (((n) >> 12) & 0x0F) #define DWC3_DGCMD_CMDACT BIT(10) @@ -539,6 +540,8 @@ #define DWC3_DGCMDPAR_TX_FIFO BIT(5) #define DWC3_DGCMDPAR_LOOPBACK_DIS (0 << 0) #define DWC3_DGCMDPAR_LOOPBACK_ENA BIT(0) +#define DWC3_DGCMDPAR_DN_FUNC_WAKE BIT(0) +#define DWC3_DGCMDPAR_INTF_SEL(n) ((n) << 4) /* Device Endpoint Command Register */ #define DWC3_DEPCMD_PARAM_SHIFT 16 diff --git a/drivers/usb/dwc3/debug.h b/drivers/usb/dwc3/debug.h index 8bb2c9e3b9ac..09d703852a92 100644 --- a/drivers/usb/dwc3/debug.h +++ b/drivers/usb/dwc3/debug.h @@ -72,6 +72,8 @@ dwc3_gadget_generic_cmd_string(u8 cmd) return "Set Endpoint Prime"; case DWC3_DGCMD_RUN_SOC_BUS_LOOPBACK: return "Run SoC Bus Loopback Test"; + case DWC3_DGCMD_DEV_NOTIFICATION: + return "Device Notification"; default: return "UNKNOWN"; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 8aa14a596406..953b752a5052 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -30,6 +30,8 @@ static void __dwc3_ep0_do_control_status(struct dwc3 *dwc, struct dwc3_ep *dep); static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_request *req); +static int dwc3_ep0_delegate_req(struct dwc3 *dwc, + struct usb_ctrlrequest *ctrl); static void dwc3_ep0_prepare_one_trb(struct dwc3_ep *dep, dma_addr_t buf_dma, u32 len, u32 type, bool chain) @@ -368,7 +370,7 @@ static int dwc3_ep0_handle_status(struct dwc3 *dwc, * Function Remote Wake Capable D0 * Function Remote Wakeup D1 */ - break; + return dwc3_ep0_delegate_req(dwc, ctrl); case USB_RECIP_ENDPOINT: dep = dwc3_wIndex_to_dep(dwc, ctrl->wIndex); @@ -517,13 +519,7 @@ static int dwc3_ep0_handle_intf(struct dwc3 *dwc, switch (wValue) { case USB_INTRF_FUNC_SUSPEND: - /* - * REVISIT: Ideally we would enable some low power mode here, - * however it's unclear what we should be doing here. - * - * For now, we're not doing anything, just making sure we return - * 0 so USB Command Verifier tests pass without any errors. - */ + ret = dwc3_ep0_delegate_req(dwc, ctrl); break; default: ret = -EINVAL; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 7ceff08a1b8c..287ea6ee2463 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2395,6 +2395,47 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g) return ret; } +static void dwc3_resume_gadget(struct dwc3 *dwc); + +static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) +{ + struct dwc3 *dwc = gadget_to_dwc(g); + unsigned long flags; + int ret; + int link_state; + + if (!dwc->wakeup_configured) { + dev_err(dwc->dev, "remote wakeup not configured\n"); + return -EINVAL; + } + + spin_lock_irqsave(&dwc->lock, flags); + /* + * If the link is in U3, signal for remote wakeup and wait for the + * link to transition to U0 before sending device notification. + */ + link_state = dwc3_gadget_get_link_state(dwc); + if (link_state == DWC3_LINK_STATE_U3) { + ret = __dwc3_gadget_wakeup(dwc, false); + if (ret) { + spin_unlock_irqrestore(&dwc->lock, flags); + return -EINVAL; + } + dwc3_resume_gadget(dwc); + dwc->link_state = DWC3_LINK_STATE_U0; + } + + ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION, + DWC3_DGCMDPAR_DN_FUNC_WAKE | + DWC3_DGCMDPAR_INTF_SEL(intf_id)); + if (ret) + dev_err(dwc->dev, "function remote wakeup failed, ret:%d\n", ret); + + spin_unlock_irqrestore(&dwc->lock, flags); + + return ret; +} + static int dwc3_gadget_set_remote_wakeup(struct usb_gadget *g, int set) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -3032,6 +3073,7 @@ static void dwc3_gadget_async_callbacks(struct usb_gadget *g, bool enable) static const struct usb_gadget_ops dwc3_gadget_ops = { .get_frame = dwc3_gadget_get_frame, .wakeup = dwc3_gadget_wakeup, + .func_wakeup = dwc3_gadget_func_wakeup, .set_remote_wakeup = dwc3_gadget_set_remote_wakeup, .set_selfpowered = dwc3_gadget_set_selfpowered, .pullup = dwc3_gadget_pullup, -- GitLab From 481c225c4802be62e52aabddae5338ed1705b232 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:48:01 -0700 Subject: [PATCH 1568/5631] usb: gadget: Handle function suspend feature selector When host sends function suspend feature selector to the device, inspect the received packet and trigger function suspend or function resume accordingly. Inspect the remote wakeup bit and arm the function for remote wakeup if it is wakeup capable. Also host queries the function wakeup capability through a get status request before sending function resume. Handle such requests in composite layer. Signed-off-by: Elson Roy Serrao Reviewed-by: Thinh Nguyen Link: https://lore.kernel.org/r/1679694482-16430-6-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/composite.c | 65 +++++++++++++++++++++++++++++++--- 1 file changed, 60 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d3fd2d1d8096..1b3489149e5e 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -941,6 +941,9 @@ static void reset_config(struct usb_composite_dev *cdev) if (f->disable) f->disable(f); + /* Section 9.1.1.6, disable remote wakeup when device is reset */ + f->func_wakeup_armed = false; + bitmap_zero(f->endpoints, 32); } cdev->config = NULL; @@ -2006,9 +2009,20 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) f = cdev->config->interface[intf]; if (!f) break; - status = f->get_status ? f->get_status(f) : 0; - if (status < 0) - break; + + if (f->get_status) { + status = f->get_status(f); + if (status < 0) + break; + } else { + /* Set D0 and D1 bits based on func wakeup capability */ + if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) { + status |= USB_INTRF_STAT_FUNC_RW_CAP; + if (f->func_wakeup_armed) + status |= USB_INTRF_STAT_FUNC_RW; + } + } + put_unaligned_le16(status & 0x0000ffff, req->buf); break; /* @@ -2030,8 +2044,44 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) if (!f) break; value = 0; - if (f->func_suspend) + if (f->func_suspend) { value = f->func_suspend(f, w_index >> 8); + /* SetFeature(FUNCTION_SUSPEND) */ + } else if (ctrl->bRequest == USB_REQ_SET_FEATURE) { + if (!(f->config->bmAttributes & + USB_CONFIG_ATT_WAKEUP) && + (w_index & USB_INTRF_FUNC_SUSPEND_RW)) + break; + + f->func_wakeup_armed = !!(w_index & + USB_INTRF_FUNC_SUSPEND_RW); + + if (w_index & USB_INTRF_FUNC_SUSPEND_LP) { + if (f->suspend && !f->func_suspended) { + f->suspend(f); + f->func_suspended = true; + } + /* + * Handle cases where host sends function resume + * through SetFeature(FUNCTION_SUSPEND) but low power + * bit reset + */ + } else { + if (f->resume && f->func_suspended) { + f->resume(f); + f->func_suspended = false; + } + } + /* ClearFeature(FUNCTION_SUSPEND) */ + } else if (ctrl->bRequest == USB_REQ_CLEAR_FEATURE) { + f->func_wakeup_armed = false; + + if (f->resume && f->func_suspended) { + f->resume(f); + f->func_suspended = false; + } + } + if (value < 0) { ERROR(cdev, "func_suspend() returned error %d\n", @@ -2573,7 +2623,12 @@ void composite_resume(struct usb_gadget *gadget) cdev->driver->resume(cdev); if (cdev->config) { list_for_each_entry(f, &cdev->config->functions, list) { - if (f->resume) + /* + * Check for func_suspended flag to see if the function is + * in USB3 FUNCTION_SUSPEND state. In this case resume is + * done via FUNCTION_SUSPEND feature selector. + */ + if (f->resume && !f->func_suspended) f->resume(f); } -- GitLab From 0a1af6dfa0772ffedaef422127f1338fa0ddfed3 Mon Sep 17 00:00:00 2001 From: Elson Roy Serrao Date: Fri, 24 Mar 2023 14:48:02 -0700 Subject: [PATCH 1569/5631] usb: gadget: f_ecm: Add suspend/resume and remote wakeup support When host sends suspend notification to the device, handle the suspend callbacks in the function driver. Depending on the remote wakeup capability the device can either trigger a remote wakeup or wait for the host initiated resume to resume data transfer. Signed-off-by: Elson Roy Serrao Reviewed-by: Thinh Nguyen Link: https://lore.kernel.org/r/1679694482-16430-7-git-send-email-quic_eserrao@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_ecm.c | 22 ++++++++++ drivers/usb/gadget/function/u_ether.c | 63 +++++++++++++++++++++++++++ drivers/usb/gadget/function/u_ether.h | 4 ++ 3 files changed, 89 insertions(+) diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index a7ab30e603e2..c6e63ad77a40 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -885,6 +885,26 @@ static struct usb_function_instance *ecm_alloc_inst(void) return &opts->func_inst; } +static void ecm_suspend(struct usb_function *f) +{ + struct f_ecm *ecm = func_to_ecm(f); + struct usb_composite_dev *cdev = ecm->port.func.config->cdev; + + DBG(cdev, "ECM Suspend\n"); + + gether_suspend(&ecm->port); +} + +static void ecm_resume(struct usb_function *f) +{ + struct f_ecm *ecm = func_to_ecm(f); + struct usb_composite_dev *cdev = ecm->port.func.config->cdev; + + DBG(cdev, "ECM Resume\n"); + + gether_resume(&ecm->port); +} + static void ecm_free(struct usb_function *f) { struct f_ecm *ecm; @@ -952,6 +972,8 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi) ecm->port.func.setup = ecm_setup; ecm->port.func.disable = ecm_disable; ecm->port.func.free_func = ecm_free; + ecm->port.func.suspend = ecm_suspend; + ecm->port.func.resume = ecm_resume; return &ecm->port.func; } diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index f259975dfba4..6956ad8ba8dd 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -437,6 +437,20 @@ static inline int is_promisc(u16 cdc_filter) return cdc_filter & USB_CDC_PACKET_TYPE_PROMISCUOUS; } +static int ether_wakeup_host(struct gether *port) +{ + int ret; + struct usb_function *func = &port->func; + struct usb_gadget *gadget = func->config->cdev->gadget; + + if (func->func_suspended) + ret = usb_func_wakeup(func); + else + ret = usb_gadget_wakeup(gadget); + + return ret; +} + static netdev_tx_t eth_start_xmit(struct sk_buff *skb, struct net_device *net) { @@ -456,6 +470,15 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, in = NULL; cdc_filter = 0; } + + if (dev->port_usb && dev->port_usb->is_suspend) { + DBG(dev, "Port suspended. Triggering wakeup\n"); + netif_stop_queue(net); + spin_unlock_irqrestore(&dev->lock, flags); + ether_wakeup_host(dev->port_usb); + return NETDEV_TX_BUSY; + } + spin_unlock_irqrestore(&dev->lock, flags); if (!in) { @@ -1014,6 +1037,45 @@ int gether_set_ifname(struct net_device *net, const char *name, int len) } EXPORT_SYMBOL_GPL(gether_set_ifname); +void gether_suspend(struct gether *link) +{ + struct eth_dev *dev = link->ioport; + unsigned long flags; + + if (!dev) + return; + + if (atomic_read(&dev->tx_qlen)) { + /* + * There is a transfer in progress. So we trigger a remote + * wakeup to inform the host. + */ + ether_wakeup_host(dev->port_usb); + return; + } + spin_lock_irqsave(&dev->lock, flags); + link->is_suspend = true; + spin_unlock_irqrestore(&dev->lock, flags); +} +EXPORT_SYMBOL_GPL(gether_suspend); + +void gether_resume(struct gether *link) +{ + struct eth_dev *dev = link->ioport; + unsigned long flags; + + if (!dev) + return; + + if (netif_queue_stopped(dev->net)) + netif_start_queue(dev->net); + + spin_lock_irqsave(&dev->lock, flags); + link->is_suspend = false; + spin_unlock_irqrestore(&dev->lock, flags); +} +EXPORT_SYMBOL_GPL(gether_resume); + /* * gether_cleanup - remove Ethernet-over-USB device * Context: may sleep @@ -1176,6 +1238,7 @@ void gether_disconnect(struct gether *link) spin_lock(&dev->lock); dev->port_usb = NULL; + link->is_suspend = false; spin_unlock(&dev->lock); } EXPORT_SYMBOL_GPL(gether_disconnect); diff --git a/drivers/usb/gadget/function/u_ether.h b/drivers/usb/gadget/function/u_ether.h index 40144546d1b0..851ee10d6e63 100644 --- a/drivers/usb/gadget/function/u_ether.h +++ b/drivers/usb/gadget/function/u_ether.h @@ -79,6 +79,7 @@ struct gether { /* called on network open/close */ void (*open)(struct gether *); void (*close)(struct gether *); + bool is_suspend; }; #define DEFAULT_FILTER (USB_CDC_PACKET_TYPE_BROADCAST \ @@ -258,6 +259,9 @@ int gether_set_ifname(struct net_device *net, const char *name, int len); void gether_cleanup(struct eth_dev *dev); +void gether_suspend(struct gether *link); +void gether_resume(struct gether *link); + /* connect/disconnect is handled by individual functions */ struct net_device *gether_connect(struct gether *); void gether_disconnect(struct gether *); -- GitLab From d629c0e221cd99198b843d8351a0a9bfec6c0423 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 29 Mar 2023 09:51:25 +0200 Subject: [PATCH 1570/5631] usb: move config USB_USS720 to usb's misc Kconfig The USS720 parport driver source code is in drivers/usb/misc/, the corresponding config is defined in drivers/usb/Kconfig. Some digging in the kernel's history revealed no good reason why it needs to be defined in USB's top-level Kconfig file, and why the config for the USS720 parport driver should be the first in the list of USB port drivers, while all other configs for drivers in drivers/usb/misc are in the USB Miscellaneous driver configuration file. Most probably, it was simply considered a bit more special when the USB Miscellaneous driver configuration file (drivers/usb/misc/Config.in back then) was initially created, and this config simply survived to remain at the top-level USB Kconfig file with all further code/Kconfig transformations and additions later on. Users rarely notice this config being at this position, as CONFIG_PARPORT (Parallel port support) needs to be enabled and only few users enable that. Nowadays, this USB_USS720 driver is probably not that special that it needs to be listed as first item of the USB port drivers. Move the configuration of the USS720 parport driver to the top of the USB Miscellaneous drivers section, as the configurations does not have a lot of specific ordering USB Miscellaneous drivers. This way, the USS720 parport driver is moved to the comment "USB Miscellaneous drivers", fitting to the driver's source code location, but still is at the top of the list for those few acquainted users of Kconfig UIs that might be looking for the config that was once at the top of the list of the USB port drivers. Put this config definition to a more local place. No semantic change. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230329075125.32352-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/Kconfig | 29 ----------------------------- drivers/usb/misc/Kconfig | 29 +++++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 29 deletions(-) diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig index a871a988829d..7f33bcc315f2 100644 --- a/drivers/usb/Kconfig +++ b/drivers/usb/Kconfig @@ -133,35 +133,6 @@ comment "USB port drivers" if USB -config USB_USS720 - tristate "USS720 parport driver" - depends on PARPORT - select PARPORT_NOT_PC - help - This driver is for USB parallel port adapters that use the Lucent - Technologies USS-720 chip. These cables are plugged into your USB - port and provide USB compatibility to peripherals designed with - parallel port interfaces. - - The chip has two modes: automatic mode and manual mode. In automatic - mode, it looks to the computer like a standard USB printer. Only - printers may be connected to the USS-720 in this mode. The generic - USB printer driver ("USB Printer support", above) may be used in - that mode, and you can say N here if you want to use the chip only - in this mode. - - Manual mode is not limited to printers, any parallel port - device should work. This driver utilizes manual mode. - Note however that some operations are three orders of magnitude - slower than on a PCI/ISA Parallel Port, so timing critical - applications might not work. - - Say Y here if you own an USS-720 USB->Parport cable and intend to - connect anything other than a printer to it. - - To compile this driver as a module, choose M here: the - module will be called uss720. - source "drivers/usb/serial/Kconfig" source "drivers/usb/misc/Kconfig" diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig index 08e3cf9efb38..99b15b77dfd5 100644 --- a/drivers/usb/misc/Kconfig +++ b/drivers/usb/misc/Kconfig @@ -4,6 +4,35 @@ # comment "USB Miscellaneous drivers" +config USB_USS720 + tristate "USS720 parport driver" + depends on PARPORT + select PARPORT_NOT_PC + help + This driver is for USB parallel port adapters that use the Lucent + Technologies USS-720 chip. These cables are plugged into your USB + port and provide USB compatibility to peripherals designed with + parallel port interfaces. + + The chip has two modes: automatic mode and manual mode. In automatic + mode, it looks to the computer like a standard USB printer. Only + printers may be connected to the USS-720 in this mode. The generic + USB printer driver ("USB Printer support", above) may be used in + that mode, and you can say N here if you want to use the chip only + in this mode. + + Manual mode is not limited to printers, any parallel port + device should work. This driver utilizes manual mode. + Note however that some operations are three orders of magnitude + slower than on a PCI/ISA Parallel Port, so timing critical + applications might not work. + + Say Y here if you own an USS-720 USB->Parport cable and intend to + connect anything other than a printer to it. + + To compile this driver as a module, choose M here: the + module will be called uss720. + config USB_EMI62 tristate "EMI 6|2m USB Audio interface support" help -- GitLab From 2b76ffe81e32afd6d318dc4547e2ba8c46207b77 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 28 Mar 2023 19:15:29 -0700 Subject: [PATCH 1571/5631] linux/vt_buffer.h: allow either builtin or modular for macros Fix build errors on ARCH=alpha when CONFIG_MDA_CONSOLE=m. This allows the ARCH macros to be the only ones defined. In file included from ../drivers/video/console/mdacon.c:37: ../arch/alpha/include/asm/vga.h:17:40: error: expected identifier or '(' before 'volatile' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~ ../include/linux/vt_buffer.h:24:34: note: in definition of macro 'scr_writew' 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^~~~ ../include/linux/vt_buffer.h:24:40: error: expected ')' before '=' token 24 | #define scr_writew(val, addr) (*(addr) = (val)) | ^ ../arch/alpha/include/asm/vga.h:17:20: note: in expansion of macro 'scr_writew' 17 | static inline void scr_writew(u16 val, volatile u16 *addr) | ^~~~~~~~~~ ../arch/alpha/include/asm/vga.h:25:29: error: expected identifier or '(' before 'volatile' 25 | static inline u16 scr_readw(volatile const u16 *addr) | ^~~~~~~~ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Randy Dunlap Cc: Greg Kroah-Hartman Cc: Jiri Slaby Cc: dri-devel@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Link: https://lore.kernel.org/r/20230329021529.16188-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/vt_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include #endif -- GitLab From cb95de8d4317b9335f1e8b687bca714cd5713502 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 12:01:36 -0500 Subject: [PATCH 1572/5631] dt-bindings: serial: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230327170137.4104272-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/serial/amlogic,meson-uart.yaml | 4 ++-- .../devicetree/bindings/serial/qcom,serial-geni-qcom.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,em-uart.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,hscif.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,sci.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,scif.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,scifa.yaml | 4 ++-- Documentation/devicetree/bindings/serial/renesas,scifb.yaml | 4 ++-- Documentation/devicetree/bindings/serial/serial.yaml | 4 ++-- Documentation/devicetree/bindings/serial/sprd-uart.yaml | 4 ++-- .../devicetree/bindings/serial/sunplus,sp7021-uart.yaml | 4 ++-- 11 files changed, 22 insertions(+), 22 deletions(-) diff --git a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml index 22656efe8ddc..01ec45b3b406 100644 --- a/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml +++ b/Documentation/devicetree/bindings/serial/amlogic,meson-uart.yaml @@ -2,8 +2,8 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/amlogic,meson-uart.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/amlogic,meson-uart.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic Meson SoC UART Serial Interface diff --git a/Documentation/devicetree/bindings/serial/qcom,serial-geni-qcom.yaml b/Documentation/devicetree/bindings/serial/qcom,serial-geni-qcom.yaml index 05a6999808d1..dd33794b3534 100644 --- a/Documentation/devicetree/bindings/serial/qcom,serial-geni-qcom.yaml +++ b/Documentation/devicetree/bindings/serial/qcom,serial-geni-qcom.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/qcom,serial-geni-qcom.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/qcom,serial-geni-qcom.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Geni based QUP UART interface diff --git a/Documentation/devicetree/bindings/serial/renesas,em-uart.yaml b/Documentation/devicetree/bindings/serial/renesas,em-uart.yaml index 12d0fa34f9f9..3fc2601f1338 100644 --- a/Documentation/devicetree/bindings/serial/renesas,em-uart.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,em-uart.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,em-uart.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,em-uart.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas EMMA Mobile UART Interface diff --git a/Documentation/devicetree/bindings/serial/renesas,hscif.yaml b/Documentation/devicetree/bindings/serial/renesas,hscif.yaml index afedb6edfc34..1c7f1276aed6 100644 --- a/Documentation/devicetree/bindings/serial/renesas,hscif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,hscif.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,hscif.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,hscif.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas High Speed Serial Communication Interface with FIFO (HSCIF) diff --git a/Documentation/devicetree/bindings/serial/renesas,sci.yaml b/Documentation/devicetree/bindings/serial/renesas,sci.yaml index dc445b327e0b..9f7305200c47 100644 --- a/Documentation/devicetree/bindings/serial/renesas,sci.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,sci.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,sci.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,sci.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas Serial Communication Interface diff --git a/Documentation/devicetree/bindings/serial/renesas,scif.yaml b/Documentation/devicetree/bindings/serial/renesas,scif.yaml index 1989bd67d04e..f26bea2d7398 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scif.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scif.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,scif.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,scif.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas Serial Communication Interface with FIFO (SCIF) diff --git a/Documentation/devicetree/bindings/serial/renesas,scifa.yaml b/Documentation/devicetree/bindings/serial/renesas,scifa.yaml index 4c3b5e7270da..499507678cdf 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scifa.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scifa.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,scifa.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,scifa.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas Serial Communications Interface with FIFO A (SCIFA) diff --git a/Documentation/devicetree/bindings/serial/renesas,scifb.yaml b/Documentation/devicetree/bindings/serial/renesas,scifb.yaml index 2f7cbbb48960..810d8a991fdd 100644 --- a/Documentation/devicetree/bindings/serial/renesas,scifb.yaml +++ b/Documentation/devicetree/bindings/serial/renesas,scifb.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/renesas,scifb.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/renesas,scifb.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas Serial Communications Interface with FIFO B (SCIFB) diff --git a/Documentation/devicetree/bindings/serial/serial.yaml b/Documentation/devicetree/bindings/serial/serial.yaml index c9231e501f1f..ea277560a596 100644 --- a/Documentation/devicetree/bindings/serial/serial.yaml +++ b/Documentation/devicetree/bindings/serial/serial.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/serial.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/serial.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Serial Interface Generic diff --git a/Documentation/devicetree/bindings/serial/sprd-uart.yaml b/Documentation/devicetree/bindings/serial/sprd-uart.yaml index da0e2745b5fc..28ff77aa86c8 100644 --- a/Documentation/devicetree/bindings/serial/sprd-uart.yaml +++ b/Documentation/devicetree/bindings/serial/sprd-uart.yaml @@ -2,8 +2,8 @@ # Copyright 2019 Unisoc Inc. %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/sprd-uart.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/sprd-uart.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Spreadtrum serial UART diff --git a/Documentation/devicetree/bindings/serial/sunplus,sp7021-uart.yaml b/Documentation/devicetree/bindings/serial/sunplus,sp7021-uart.yaml index ea1e637661c7..7d0a4bcb88e9 100644 --- a/Documentation/devicetree/bindings/serial/sunplus,sp7021-uart.yaml +++ b/Documentation/devicetree/bindings/serial/sunplus,sp7021-uart.yaml @@ -2,8 +2,8 @@ # Copyright (C) Sunplus Co., Ltd. 2021 %YAML 1.2 --- -$id: "http://devicetree.org/schemas/serial/sunplus,sp7021-uart.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/serial/sunplus,sp7021-uart.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Sunplus SoC SP7021 UART Controller -- GitLab From 4ca589661d964840d0d5de4b3baabbef78f453e3 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Wed, 15 Mar 2023 11:53:52 +0100 Subject: [PATCH 1573/5631] tty: n_gsm: add ioctl for DLC specific parameter configuration Parameter negotiation has been introduced with commit 92f1f0c3290d ("tty: n_gsm: add parameter negotiation support") However, means to set individual parameters per DLCI are not yet implemented. Furthermore, it is currently not possible to keep a DLCI half open until the user application sets the right parameters for it. This is required to allow a user application to set its specific parameters before the underlying link is established. Otherwise, the link is opened and re-established right afterwards if the user application sets incompatible parameters. This may be an unexpected behavior for the peer. Add parameter 'wait_config' to 'gsm_config' to support setups where the DLCI specific user application sets its specific parameters after open() and before the link gets fully established. Setting this to zero disables the user application specific DLCI configuration option. Add the ioctls 'GSMIOC_GETCONF_DLCI' and 'GSMIOC_SETCONF_DLCI' for the ldisc and virtual ttys. This gets/sets the DLCI specific parameters and may trigger a reconnect of the DLCI if incompatible values have been set. Only the parameters for the DLCI associated with the virtual tty can be set or retrieved if called on these. Add remark within the documentation to introduce the new ioctls. Link: https://lore.kernel.org/oe-kbuild-all/202302281856.S9Lz4gHB-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230315105354.6234-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/tty/n_gsm.rst | 4 + drivers/tty/n_gsm.c | 192 ++++++++++++++++++++++++- include/uapi/linux/gsmmux.h | 17 ++- 3 files changed, 207 insertions(+), 6 deletions(-) diff --git a/Documentation/driver-api/tty/n_gsm.rst b/Documentation/driver-api/tty/n_gsm.rst index 9447b8a3b8e2..c2624546fb8f 100644 --- a/Documentation/driver-api/tty/n_gsm.rst +++ b/Documentation/driver-api/tty/n_gsm.rst @@ -29,6 +29,8 @@ Config Initiator #. Configure the mux using ``GSMIOC_GETCONF``/``GSMIOC_SETCONF`` ioctl. +#. Configure DLCs using ``GSMIOC_GETCONF_DLCI``/``GSMIOC_SETCONF_DLCI`` ioctl for non-defaults. + #. Obtain base gsmtty number for the used serial port. Major parts of the initialization program @@ -120,6 +122,8 @@ Config Requester #. Configure the mux using ``GSMIOC_GETCONF``/``GSMIOC_SETCONF`` ioctl. +#. Configure DLCs using ``GSMIOC_GETCONF_DLCI``/``GSMIOC_SETCONF_DLCI`` ioctl for non-defaults. + #. Obtain base gsmtty number for the used serial port:: #include diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 7aa05ebed8e1..9d0e7701ffd4 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -128,6 +128,7 @@ struct gsm_msg { enum gsm_dlci_state { DLCI_CLOSED, + DLCI_WAITING_CONFIG, /* Waiting for DLCI configuration from user */ DLCI_CONFIGURE, /* Sending PN (for adaption > 1) */ DLCI_OPENING, /* Sending SABM not seen UA */ DLCI_OPEN, /* SABM/UA complete */ @@ -330,6 +331,7 @@ struct gsm_mux { unsigned int t3; /* Power wake-up timer in seconds. */ int n2; /* Retry count */ u8 k; /* Window size */ + bool wait_config; /* Wait for configuration by ioctl before DLCI open */ u32 keep_alive; /* Control channel keep-alive in 10ms */ /* Statistics (not currently exposed) */ @@ -451,6 +453,7 @@ static int gsm_modem_update(struct gsm_dlci *dlci, u8 brk); static struct gsm_msg *gsm_data_alloc(struct gsm_mux *gsm, u8 addr, int len, u8 ctrl); static int gsm_send_packet(struct gsm_mux *gsm, struct gsm_msg *msg); +static struct gsm_dlci *gsm_dlci_alloc(struct gsm_mux *gsm, int addr); static void gsmld_write_trigger(struct gsm_mux *gsm); static void gsmld_write_task(struct work_struct *work); @@ -2280,6 +2283,7 @@ static void gsm_dlci_begin_open(struct gsm_dlci *dlci) switch (dlci->state) { case DLCI_CLOSED: + case DLCI_WAITING_CONFIG: case DLCI_CLOSING: dlci->retries = gsm->n2; if (!need_pn) { @@ -2311,6 +2315,7 @@ static void gsm_dlci_set_opening(struct gsm_dlci *dlci) { switch (dlci->state) { case DLCI_CLOSED: + case DLCI_WAITING_CONFIG: case DLCI_CLOSING: dlci->state = DLCI_OPENING; break; @@ -2319,6 +2324,24 @@ static void gsm_dlci_set_opening(struct gsm_dlci *dlci) } } +/** + * gsm_dlci_set_wait_config - wait for channel configuration + * @dlci: DLCI to configure + * + * Wait for a DLCI configuration from the application. + */ +static void gsm_dlci_set_wait_config(struct gsm_dlci *dlci) +{ + switch (dlci->state) { + case DLCI_CLOSED: + case DLCI_CLOSING: + dlci->state = DLCI_WAITING_CONFIG; + break; + default: + break; + } +} + /** * gsm_dlci_begin_close - start channel open procedure * @dlci: DLCI to open @@ -2453,6 +2476,128 @@ static void gsm_kick_timer(struct timer_list *t) pr_info("%s TX queue stalled\n", __func__); } +/** + * gsm_dlci_copy_config_values - copy DLCI configuration + * @dlci: source DLCI + * @dc: configuration structure to fill + */ +static void gsm_dlci_copy_config_values(struct gsm_dlci *dlci, struct gsm_dlci_config *dc) +{ + memset(dc, 0, sizeof(*dc)); + dc->channel = (u32)dlci->addr; + dc->adaption = (u32)dlci->adaption; + dc->mtu = (u32)dlci->mtu; + dc->priority = (u32)dlci->prio; + if (dlci->ftype == UIH) + dc->i = 1; + else + dc->i = 2; + dc->k = (u32)dlci->k; +} + +/** + * gsm_dlci_config - configure DLCI from configuration + * @dlci: DLCI to configure + * @dc: DLCI configuration + * @open: open DLCI after configuration? + */ +static int gsm_dlci_config(struct gsm_dlci *dlci, struct gsm_dlci_config *dc, int open) +{ + struct gsm_mux *gsm; + bool need_restart = false; + bool need_open = false; + unsigned int i; + + /* + * Check that userspace doesn't put stuff in here to prevent breakages + * in the future. + */ + for (i = 0; i < ARRAY_SIZE(dc->reserved); i++) + if (dc->reserved[i]) + return -EINVAL; + + if (!dlci) + return -EINVAL; + gsm = dlci->gsm; + + /* Stuff we don't support yet - I frame transport */ + if (dc->adaption != 1 && dc->adaption != 2) + return -EOPNOTSUPP; + if (dc->mtu > MAX_MTU || dc->mtu < MIN_MTU || dc->mtu > gsm->mru) + return -EINVAL; + if (dc->priority >= 64) + return -EINVAL; + if (dc->i == 0 || dc->i > 2) /* UIH and UI only */ + return -EINVAL; + if (dc->k > 7) + return -EINVAL; + + /* + * See what is needed for reconfiguration + */ + /* Framing fields */ + if (dc->adaption != dlci->adaption) + need_restart = true; + if (dc->mtu != dlci->mtu) + need_restart = true; + if (dc->i != dlci->ftype) + need_restart = true; + /* Requires care */ + if (dc->priority != dlci->prio) + need_restart = true; + + if ((open && gsm->wait_config) || need_restart) + need_open = true; + if (dlci->state == DLCI_WAITING_CONFIG) { + need_restart = false; + need_open = true; + } + + /* + * Close down what is needed, restart and initiate the new + * configuration. + */ + if (need_restart) { + gsm_dlci_begin_close(dlci); + wait_event_interruptible(gsm->event, dlci->state == DLCI_CLOSED); + if (signal_pending(current)) + return -EINTR; + } + /* + * Setup the new configuration values + */ + dlci->adaption = (int)dc->adaption; + + if (dc->mtu) + dlci->mtu = (unsigned int)dc->mtu; + else + dlci->mtu = gsm->mtu; + + if (dc->priority) + dlci->prio = (u8)dc->priority; + else + dlci->prio = roundup(dlci->addr + 1, 8) - 1; + + if (dc->i == 1) + dlci->ftype = UIH; + else if (dc->i == 2) + dlci->ftype = UI; + + if (dc->k) + dlci->k = (u8)dc->k; + else + dlci->k = gsm->k; + + if (need_open) { + if (gsm->initiator) + gsm_dlci_begin_open(dlci); + else + gsm_dlci_set_opening(dlci); + } + + return 0; +} + /* * Allocate/Free DLCI channels */ @@ -3078,6 +3223,7 @@ static struct gsm_mux *gsm_alloc_mux(void) gsm->mru = 64; /* Default to encoding 1 so these should be 64 */ gsm->mtu = 64; gsm->dead = true; /* Avoid early tty opens */ + gsm->wait_config = false; /* Disabled */ gsm->keep_alive = 0; /* Disabled */ /* Store the instance to the mux array or abort if no space is @@ -3218,6 +3364,7 @@ static void gsm_copy_config_ext_values(struct gsm_mux *gsm, struct gsm_config_ext *ce) { memset(ce, 0, sizeof(*ce)); + ce->wait_config = gsm->wait_config ? 1 : 0; ce->keep_alive = gsm->keep_alive; } @@ -3233,7 +3380,12 @@ static int gsm_config_ext(struct gsm_mux *gsm, struct gsm_config_ext *ce) if (ce->reserved[i]) return -EINVAL; + /* + * Setup the new configuration values + */ + gsm->wait_config = ce->wait_config ? true : false; gsm->keep_alive = ce->keep_alive; + return 0; } @@ -3436,6 +3588,14 @@ static int gsmld_open(struct tty_struct *tty) gsm->encoding = GSM_ADV_OPT; gsmld_attach_gsm(tty, gsm); + /* The mux will not be activated yet, we wait for correct + * configuration first. + */ + if (gsm->encoding == GSM_BASIC_OPT) + gsm->receive = gsm0_receive; + else + gsm->receive = gsm1_receive; + return 0; } @@ -4008,7 +4168,6 @@ static int gsmtty_open(struct tty_struct *tty, struct file *filp) { struct gsm_dlci *dlci = tty->driver_data; struct tty_port *port = &dlci->port; - struct gsm_mux *gsm = dlci->gsm; port->count++; tty_port_tty_set(port, tty); @@ -4018,10 +4177,15 @@ static int gsmtty_open(struct tty_struct *tty, struct file *filp) a DM straight back. This is ok as that will have caused a hangup */ tty_port_set_initialized(port, true); /* Start sending off SABM messages */ - if (gsm->initiator) - gsm_dlci_begin_open(dlci); - else - gsm_dlci_set_opening(dlci); + if (!dlci->gsm->wait_config) { + /* Start sending off SABM messages */ + if (dlci->gsm->initiator) + gsm_dlci_begin_open(dlci); + else + gsm_dlci_set_opening(dlci); + } else { + gsm_dlci_set_wait_config(dlci); + } /* And wait for virtual carrier */ return tty_port_block_til_ready(port, tty, filp); } @@ -4142,6 +4306,7 @@ static int gsmtty_ioctl(struct tty_struct *tty, { struct gsm_dlci *dlci = tty->driver_data; struct gsm_netconfig nc; + struct gsm_dlci_config dc; int index; if (dlci->state == DLCI_CLOSED) @@ -4165,6 +4330,23 @@ static int gsmtty_ioctl(struct tty_struct *tty, gsm_destroy_network(dlci); mutex_unlock(&dlci->mutex); return 0; + case GSMIOC_GETCONF_DLCI: + if (copy_from_user(&dc, (void __user *)arg, sizeof(dc))) + return -EFAULT; + if (dc.channel != dlci->addr) + return -EPERM; + gsm_dlci_copy_config_values(dlci, &dc); + if (copy_to_user((void __user *)arg, &dc, sizeof(dc))) + return -EFAULT; + return 0; + case GSMIOC_SETCONF_DLCI: + if (copy_from_user(&dc, (void __user *)arg, sizeof(dc))) + return -EFAULT; + if (dc.channel >= NUM_DLCI) + return -EINVAL; + if (dc.channel != 0 && dc.channel != dlci->addr) + return -EPERM; + return gsm_dlci_config(dlci, &dc, 1); case TIOCMIWAIT: return gsm_wait_modem_change(dlci, (u32)arg); default: diff --git a/include/uapi/linux/gsmmux.h b/include/uapi/linux/gsmmux.h index a703780aa095..eb67884e5f38 100644 --- a/include/uapi/linux/gsmmux.h +++ b/include/uapi/linux/gsmmux.h @@ -43,10 +43,25 @@ struct gsm_config_ext { __u32 keep_alive; /* Control channel keep-alive in 1/100th of a * second (0 to disable) */ - __u32 reserved[7]; /* For future use, must be initialized to zero */ + __u32 wait_config; /* Wait for DLCI config before opening virtual link? */ + __u32 reserved[6]; /* For future use, must be initialized to zero */ }; #define GSMIOC_GETCONF_EXT _IOR('G', 5, struct gsm_config_ext) #define GSMIOC_SETCONF_EXT _IOW('G', 6, struct gsm_config_ext) +/* Set channel accordingly before calling GSMIOC_GETCONF_DLCI. */ +struct gsm_dlci_config { + __u32 channel; /* DLCI (0 for the associated DLCI) */ + __u32 adaption; /* Convergence layer type */ + __u32 mtu; /* Maximum transfer unit */ + __u32 priority; /* Priority (0 for default value) */ + __u32 i; /* Frame type (1 = UIH, 2 = UI) */ + __u32 k; /* Window size (0 for default value) */ + __u32 reserved[8]; /* For future use, must be initialized to zero */ +}; + +#define GSMIOC_GETCONF_DLCI _IOWR('G', 7, struct gsm_dlci_config) +#define GSMIOC_SETCONF_DLCI _IOW('G', 8, struct gsm_dlci_config) + #endif -- GitLab From 8629745ccc21ba1c20bbb2aead2800cf96643536 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Wed, 15 Mar 2023 11:53:53 +0100 Subject: [PATCH 1574/5631] tty: n_gsm: allow window size configuration n_gsm is based on the 3GPP 07.010 and its newer version is the 3GPP 27.010. See https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=1516 The changes from 07.010 to 27.010 are non-functional. Therefore, I refer to the newer 27.010 here. Chapter 6 describes the error recovery mode option which is based on I frames. The k parameter defines the maximum number of I frames that a DLC can have unacknowledged as described in chapter 5.7.4. The current n_gsm implementation does not support the error recovery mode option. However, the k parameter is also part of the parameter negotiation message as described in chapter 5.4.6.3.1. Chapter 5.7.4 also notes that the allowed value range for k is 1-7. That means a 0 is counted as invalid here. This means that the user needs to configure a valid value here even if the function itself is not supported. Otherwise, parameter negotiation may fail. Allow setting of k via ioctl in gsm_config(). Range checks are already included. Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230315105354.6234-2-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 9d0e7701ffd4..5bbedfc36fd1 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3276,8 +3276,8 @@ static int gsm_config(struct gsm_mux *gsm, struct gsm_config *c) int need_close = 0; int need_restart = 0; - /* Stuff we don't support yet - UI or I frame transport, windowing */ - if ((c->adaption != 1 && c->adaption != 2) || c->k) + /* Stuff we don't support yet - UI or I frame transport */ + if (c->adaption != 1 && c->adaption != 2) return -EOPNOTSUPP; /* Check the MRU/MTU range looks sane */ if (c->mru < MIN_MTU || c->mtu < MIN_MTU) -- GitLab From afe3154ba87e798de87ab65c72d6e3f6cd32d9d1 Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Wed, 15 Mar 2023 11:53:54 +0100 Subject: [PATCH 1575/5631] tty: n_gsm: add ioctl for DLC config via ldisc handle The application which initializes the n_gsm ldisc may like to set individual default parameters for each DLCI or take over of the application specific DLCI configuration completely. This is currently not possible. It is either possible to set common default parameters for all DLCIs or let the user application set its DLCI specific configuration parameters. Add support of GSMIOC_GETCONF_DLCI and GSMIOC_SETCONF_DLCI for the n_gsm ldisc handle to support DLCI specific parameter configuration upfront. Add a code example for this use case to the n_gsm documentation. Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230315105354.6234-3-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/tty/n_gsm.rst | 16 ++++++++++++++ drivers/tty/n_gsm.c | 29 ++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/Documentation/driver-api/tty/n_gsm.rst b/Documentation/driver-api/tty/n_gsm.rst index c2624546fb8f..120317ec990f 100644 --- a/Documentation/driver-api/tty/n_gsm.rst +++ b/Documentation/driver-api/tty/n_gsm.rst @@ -47,6 +47,7 @@ Config Initiator int ldisc = N_GSM0710; struct gsm_config c; struct gsm_config_ext ce; + struct gsm_dlci_config dc; struct termios configuration; uint32_t first; @@ -83,6 +84,13 @@ Config Initiator c.mtu = 127; /* set the new configuration */ ioctl(fd, GSMIOC_SETCONF, &c); + /* get DLC 1 configuration */ + dc.channel = 1; + ioctl(fd, GSMIOC_GETCONF_DLCI, &dc); + /* the first user channel gets a higher priority */ + dc.priority = 1; + /* set the new DLC 1 specific configuration */ + ioctl(fd, GSMIOC_SETCONF_DLCI, &dc); /* get first gsmtty device node */ ioctl(fd, GSMIOC_GETFIRST, &first); printf("first muxed line: /dev/gsmtty%i\n", first); @@ -136,6 +144,7 @@ Config Requester int ldisc = N_GSM0710; struct gsm_config c; struct gsm_config_ext ce; + struct gsm_dlci_config dc; struct termios configuration; uint32_t first; @@ -165,6 +174,13 @@ Config Requester c.mtu = 127; /* set the new configuration */ ioctl(fd, GSMIOC_SETCONF, &c); + /* get DLC 1 configuration */ + dc.channel = 1; + ioctl(fd, GSMIOC_GETCONF_DLCI, &dc); + /* the first user channel gets a higher priority */ + dc.priority = 1; + /* set the new DLC 1 specific configuration */ + ioctl(fd, GSMIOC_SETCONF_DLCI, &dc); /* get first gsmtty device node */ ioctl(fd, GSMIOC_GETFIRST, &first); printf("first muxed line: /dev/gsmtty%i\n", first); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 5bbedfc36fd1..b7e1369a035c 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3716,7 +3716,9 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, { struct gsm_config c; struct gsm_config_ext ce; + struct gsm_dlci_config dc; struct gsm_mux *gsm = tty->disc_data; + struct gsm_dlci *dlci; unsigned int base; switch (cmd) { @@ -3741,6 +3743,33 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, if (copy_from_user(&ce, (void __user *)arg, sizeof(ce))) return -EFAULT; return gsm_config_ext(gsm, &ce); + case GSMIOC_GETCONF_DLCI: + if (copy_from_user(&dc, (void __user *)arg, sizeof(dc))) + return -EFAULT; + if (dc.channel == 0 || dc.channel >= NUM_DLCI) + return -EINVAL; + dlci = gsm->dlci[dc.channel]; + if (!dlci) { + dlci = gsm_dlci_alloc(gsm, dc.channel); + if (!dlci) + return -ENOMEM; + } + gsm_dlci_copy_config_values(dlci, &dc); + if (copy_to_user((void __user *)arg, &dc, sizeof(dc))) + return -EFAULT; + return 0; + case GSMIOC_SETCONF_DLCI: + if (copy_from_user(&dc, (void __user *)arg, sizeof(dc))) + return -EFAULT; + if (dc.channel == 0 || dc.channel >= NUM_DLCI) + return -EINVAL; + dlci = gsm->dlci[dc.channel]; + if (!dlci) { + dlci = gsm_dlci_alloc(gsm, dc.channel); + if (!dlci) + return -ENOMEM; + } + return gsm_dlci_config(dlci, &dc, 0); default: return n_tty_ioctl_helper(tty, cmd, arg); } -- GitLab From 5e227ef2aa388f14ceeafa65eb8a38fa37918eb4 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 16 Mar 2023 13:20:56 -0700 Subject: [PATCH 1576/5631] serial: uart_poll_init() should power on the UART On Qualcomm devices which use the "geni" serial driver, kdb/kgdb won't be very happy if you use it but the resources of the port haven't been powered on. Today kdb/kgdb rely on someone else powering the port on. This could be the normal kernel console or an agetty running. Let's fix this to explicitly power things on when setting up a polling driver. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20230316132027.RESEND.1.I106c39498d8094c6f5e7ada42c7db17aa5c64e48@changeid Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index db7f6c0c39bf..afafbb7edb4a 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2590,6 +2590,7 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; + enum uart_pm_state pm_state; struct tty_port *tport; struct uart_port *port; int baud = 9600; @@ -2607,6 +2608,9 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options) goto out; } + pm_state = state->pm_state; + uart_change_pm(state, UART_PM_STATE_ON); + if (port->ops->poll_init) { /* * We don't set initialized as we only initialized the hw, @@ -2623,6 +2627,8 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options) console_list_unlock(); } out: + if (ret) + uart_change_pm(state, pm_state); mutex_unlock(&tport->mutex); return ret; } -- GitLab From d8851a96ba25d5fa2a3d89550f8333db5b694919 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 16 Mar 2023 13:20:57 -0700 Subject: [PATCH 1577/5631] tty: serial: qcom-geni-serial: Add a poll_init() function On sc7180 Chromebooks, I did the following: * Didn't enable earlycon in the kernel command line. * Didn't enable serial console in the kernel command line. * Didn't enable an agetty or any other client of "/dev/ttyMSM0". * Added "kgdboc=ttyMSM0" to the kernel command line. After I did that, I tried to enter kdb with this command over an ssh session: echo g > /proc/sysrq-trigger When I did that the system just hung. Although I thought I'd tested this scenario before, I couldn't go back and find a time when it was working. Previous testing must have relied on either the UART acting as the kernel console or an agetty running. It turns out to be pretty easy to fix: we can just use qcom_geni_serial_port_setup() as the .poll_init() function. This, together with the patch ("serial: uart_poll_init() should power on the UART"), allows the debugger to work even if there are no other users of the serial port. Signed-off-by: Douglas Anderson Link: https://lore.kernel.org/r/20230316132027.RESEND.2.Ie678853bb101091afe78cc8c22344bf3ff3aed74@changeid Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 28fbc927a546..1881dd5b3c4d 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1535,6 +1535,7 @@ static const struct uart_ops qcom_geni_console_pops = { #ifdef CONFIG_CONSOLE_POLL .poll_get_char = qcom_geni_serial_get_char, .poll_put_char = qcom_geni_serial_poll_put_char, + .poll_init = qcom_geni_serial_port_setup, #endif .pm = qcom_geni_serial_pm, }; -- GitLab From 5953ab340df0585d345291ace718548f5e5de942 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 17 Mar 2023 08:15:38 +0100 Subject: [PATCH 1578/5631] tty: serial: remove obsolete config SERIAL_SAMSUNG_UARTS_4 Commit 1ea35b355722 ("ARM: s3c: remove s3c24xx specific hacks"), allows simplifying the whole config logic for SERIAL_SAMSUNG_UARTS, and did this config simplification. However, it misses that SERIAL_SAMSUNG_UARTS_4's effect was just to control SERIAL_SAMSUNG_UARTS, and with the commit's change, the config SERIAL_SAMSUNG_UARTS_4 has no remaining effect and can be deleted. Remove this obsolete config SERIAL_SAMSUNG_UARTS_4. Signed-off-by: Lukas Bulwahn Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230317071538.29366-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 0072892ca7fc..39a0078f54f6 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -248,13 +248,6 @@ config SERIAL_SAMSUNG Choose Y/M here only if you build for such SoC. -config SERIAL_SAMSUNG_UARTS_4 - bool - depends on SERIAL_SAMSUNG - default y - help - Internal node for the common case of 4 Samsung compatible UARTs - config SERIAL_SAMSUNG_UARTS int depends on SERIAL_SAMSUNG -- GitLab From 7553574900f37847a25c4d572b13c512811604ed Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 17 Mar 2023 16:57:10 -0400 Subject: [PATCH 1579/5631] serial: imx: remove unused imx_uart_is_imx* functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit clang with W=1 reports drivers/tty/serial/imx.c:292:19: error: unused function 'imx_uart_is_imx21' [-Werror,-Wunused-function] static inline int imx_uart_is_imx21(struct imx_port *sport) ^ drivers/tty/serial/imx.c:297:19: error: unused function 'imx_uart_is_imx53' [-Werror,-Wunused-function] static inline int imx_uart_is_imx53(struct imx_port *sport) ^ drivers/tty/serial/imx.c:302:19: error: unused function 'imx_uart_is_imx6q' [-Werror,-Wunused-function] static inline int imx_uart_is_imx6q(struct imx_port *sport) ^ These static functions are not used, so remove them. Signed-off-by: Tom Rix Reviewed-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230317205710.1672232-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/imx.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 0fa1bd8cdec7..c5e17569c3ad 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -289,20 +289,6 @@ static inline int imx_uart_is_imx1(struct imx_port *sport) return sport->devdata->devtype == IMX1_UART; } -static inline int imx_uart_is_imx21(struct imx_port *sport) -{ - return sport->devdata->devtype == IMX21_UART; -} - -static inline int imx_uart_is_imx53(struct imx_port *sport) -{ - return sport->devdata->devtype == IMX53_UART; -} - -static inline int imx_uart_is_imx6q(struct imx_port *sport) -{ - return sport->devdata->devtype == IMX6Q_UART; -} /* * Save and restore functions for UCR1, UCR2 and UCR3 registers */ -- GitLab From b7313f1d65d668ad0056ca1d93a9017ebb78aeaf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 20 Mar 2023 15:50:08 +0200 Subject: [PATCH 1580/5631] serial: ucc_uart: Use uart_circ_empty() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use uart_circ_empty() rather than open coding it. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230320135009.47170-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/ucc_uart.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c index 676840847962..404230c1ebb2 100644 --- a/drivers/tty/serial/ucc_uart.c +++ b/drivers/tty/serial/ucc_uart.c @@ -366,15 +366,14 @@ static int qe_uart_tx_pump(struct uart_qe_port *qe_port) /* Pick next descriptor and fill from buffer */ bdp = qe_port->tx_cur; - while (!(ioread16be(&bdp->status) & BD_SC_READY) && - (xmit->tail != xmit->head)) { + while (!(ioread16be(&bdp->status) & BD_SC_READY) && !uart_circ_empty(xmit)) { count = 0; p = qe2cpu_addr(be32_to_cpu(bdp->buf), qe_port); while (count < qe_port->tx_fifosize) { *p++ = xmit->buf[xmit->tail]; uart_xmit_advance(port, 1); count++; - if (xmit->head == xmit->tail) + if (uart_circ_empty(xmit)) break; } -- GitLab From cd74c5e35546362fdb410551fe650e7e3fa2208e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 20 Mar 2023 15:50:09 +0200 Subject: [PATCH 1581/5631] serial: cpm_uart: Use uart_circ_empty() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use uart_circ_empty() instead of open coding it. Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230320135009.47170-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/cpm_uart/cpm_uart_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 5565f302cb21..349e7da643f0 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -678,15 +678,14 @@ static int cpm_uart_tx_pump(struct uart_port *port) /* Pick next descriptor and fill from buffer */ bdp = pinfo->tx_cur; - while (!(in_be16(&bdp->cbd_sc) & BD_SC_READY) && - xmit->tail != xmit->head) { + while (!(in_be16(&bdp->cbd_sc) & BD_SC_READY) && !uart_circ_empty(xmit)) { count = 0; p = cpm2cpu_addr(in_be32(&bdp->cbd_bufaddr), pinfo); while (count < pinfo->tx_fifosize) { *p++ = xmit->buf[xmit->tail]; uart_xmit_advance(port, 1); count++; - if (xmit->head == xmit->tail) + if (uart_circ_empty(xmit)) break; } out_be16(&bdp->cbd_datlen, count); -- GitLab From dedd376e0c7096daf4171d54957a679b4dfeadbf Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 17 Mar 2023 16:57:12 +0100 Subject: [PATCH 1582/5631] dt-bindings: serial: snps-dw-apb-uart: correct number of DMAs The "minItems" alone does not impose any upper limit of DMAs, so switch it to "maxItems" which also implies same value for minItems. Fixes: 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") Signed-off-by: Krzysztof Kozlowski Reviewed-by: Conor Dooley Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230317155712.99654-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml index 2becdfab4f15..8212a9f483b5 100644 --- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml +++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml @@ -68,7 +68,7 @@ properties: - const: apb_pclk dmas: - minItems: 2 + maxItems: 2 dma-names: items: -- GitLab From f1d81e3cf0e91bf3455a643b87184c2288cfba8e Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 22 Mar 2023 07:47:17 +0000 Subject: [PATCH 1583/5631] tty: serial: sh-sci: Remove setting {src,dst}_{addr,addr_width} based on DMA direction The direction field in the DMA config is deprecated. The sh-sci driver sets {src,dst}_{addr,addr_width} based on the DMA direction and it results in dmaengine_slave_config() failure as RZ DMAC driver validates {src,dst}_addr_width values independent of DMA direction. Fix this issue by passing both {src,dst}_{addr,addr_width} values independent of DMA direction. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230322074717.6057-1-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index af4a7a865764..027dfe535fe5 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1530,15 +1530,12 @@ static struct dma_chan *sci_request_dma_chan(struct uart_port *port, memset(&cfg, 0, sizeof(cfg)); cfg.direction = dir; - if (dir == DMA_MEM_TO_DEV) { - cfg.dst_addr = port->mapbase + - (sci_getreg(port, SCxTDR)->offset << port->regshift); - cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - } else { - cfg.src_addr = port->mapbase + - (sci_getreg(port, SCxRDR)->offset << port->regshift); - cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; - } + cfg.dst_addr = port->mapbase + + (sci_getreg(port, SCxTDR)->offset << port->regshift); + cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + cfg.src_addr = port->mapbase + + (sci_getreg(port, SCxRDR)->offset << port->regshift); + cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; ret = dmaengine_slave_config(chan, &cfg); if (ret) { -- GitLab From 945de8be2f7ff7d4dd578d97307ae650b95de294 Mon Sep 17 00:00:00 2001 From: Arend van Spriel Date: Wed, 22 Mar 2023 23:39:56 +0100 Subject: [PATCH 1584/5631] serial: bcm63xx-uart: add polling support The tty framework can support polling console to allow operation in situations where interrupts are turned off. Adding polling mode support allows using KGDB over serial console, Signed-off-by: Arend van Spriel Link: https://lore.kernel.org/r/20230322223956.84647-1-arend.vanspriel@broadcom.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/bcm63xx_uart.c | 38 +++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index 62bc7244dc67..55e82d0bf92d 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -596,6 +596,40 @@ static int bcm_uart_verify_port(struct uart_port *port, return 0; } +#ifdef CONFIG_CONSOLE_POLL +/* + * return true when outstanding tx equals fifo size + */ +static bool bcm_uart_tx_full(struct uart_port *port) +{ + unsigned int val; + + val = bcm_uart_readl(port, UART_MCTL_REG); + val = (val & UART_MCTL_TXFIFOFILL_MASK) >> UART_MCTL_TXFIFOFILL_SHIFT; + return !(port->fifosize - val); +} + +static int bcm_uart_poll_get_char(struct uart_port *port) +{ + unsigned int iestat; + + iestat = bcm_uart_readl(port, UART_IR_REG); + if (!(iestat & UART_IR_STAT(UART_IR_RXNOTEMPTY))) + return NO_POLL_CHAR; + + return bcm_uart_readl(port, UART_FIFO_REG); +} + +static void bcm_uart_poll_put_char(struct uart_port *port, unsigned char c) +{ + while (bcm_uart_tx_full(port)) { + cpu_relax(); + } + + bcm_uart_writel(port, c, UART_FIFO_REG); +} +#endif + /* serial core callbacks */ static const struct uart_ops bcm_uart_ops = { .tx_empty = bcm_uart_tx_empty, @@ -614,6 +648,10 @@ static const struct uart_ops bcm_uart_ops = { .request_port = bcm_uart_request_port, .config_port = bcm_uart_config_port, .verify_port = bcm_uart_verify_port, +#ifdef CONFIG_CONSOLE_POLL + .poll_get_char = bcm_uart_poll_get_char, + .poll_put_char = bcm_uart_poll_put_char, +#endif }; -- GitLab From a4312fd4444b289147e21541fe7d4ef62e9b7353 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 23 Mar 2023 08:10:53 +0100 Subject: [PATCH 1585/5631] serial: sb1250-duart: clean up after SIBYTE_BCM1x55 removal With commit b984d7b56dfc ("MIPS: sibyte: Remove unused config option SIBYTE_BCM1x55"), an #if in the Broadcom SiByte DUART driver can be simplified. Simplify the prepreprocessor condition after config SIBYTE_BCM1x55 removal. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230323071053.417-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sb1250-duart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c index de56f383964e..b6de0dc51f29 100644 --- a/drivers/tty/serial/sb1250-duart.c +++ b/drivers/tty/serial/sb1250-duart.c @@ -41,7 +41,7 @@ #include -#if defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80) +#if defined(CONFIG_SIBYTE_BCM1x80) #include #include -- GitLab From 094fb49a2d0d6827c86d2e0840873e6db0c491d2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 17 Mar 2023 13:33:17 +0200 Subject: [PATCH 1586/5631] tty: Prevent writing chars during tcsetattr TCSADRAIN/FLUSH MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If userspace races tcsetattr() with a write, the drained condition might not be guaranteed by the kernel. There is a race window after checking Tx is empty before tty_set_termios() takes termios_rwsem for write. During that race window, more characters can be queued by a racing writer. Any ongoing transmission might produce garbage during HW's ->set_termios() call. The intent of TCSADRAIN/FLUSH seems to be preventing such a character corruption. If those flags are set, take tty's write lock to stop any writer before performing the lower layer Tx empty check and wait for the pending characters to be sent (if any). The initial wait for all-writers-done must be placed outside of tty's write lock to avoid deadlock which makes it impossible to use tty_wait_until_sent(). The write lock is retried if a racing write is detected. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230317113318.31327-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty.h | 2 ++ drivers/tty/tty_io.c | 4 ++-- drivers/tty/tty_ioctl.c | 45 ++++++++++++++++++++++++++++++----------- 3 files changed, 37 insertions(+), 14 deletions(-) diff --git a/drivers/tty/tty.h b/drivers/tty/tty.h index f45cd683c02e..1e0d80e98d26 100644 --- a/drivers/tty/tty.h +++ b/drivers/tty/tty.h @@ -62,6 +62,8 @@ int __tty_check_change(struct tty_struct *tty, int sig); int tty_check_change(struct tty_struct *tty); void __stop_tty(struct tty_struct *tty); void __start_tty(struct tty_struct *tty); +void tty_write_unlock(struct tty_struct *tty); +int tty_write_lock(struct tty_struct *tty, int ndelay); void tty_vhangup_session(struct tty_struct *tty); void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty); int tty_signal_session_leader(struct tty_struct *tty, int exit_session); diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 766750e355ac..cfb3da0dee47 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -933,13 +933,13 @@ static ssize_t tty_read(struct kiocb *iocb, struct iov_iter *to) return i; } -static void tty_write_unlock(struct tty_struct *tty) +void tty_write_unlock(struct tty_struct *tty) { mutex_unlock(&tty->atomic_write_lock); wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } -static int tty_write_lock(struct tty_struct *tty, int ndelay) +int tty_write_lock(struct tty_struct *tty, int ndelay) { if (!mutex_trylock(&tty->atomic_write_lock)) { if (ndelay) diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 32ff9959b565..2e88b414cf95 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -501,21 +501,42 @@ static int set_termios(struct tty_struct *tty, void __user *arg, int opt) tmp_termios.c_ispeed = tty_termios_input_baud_rate(&tmp_termios); tmp_termios.c_ospeed = tty_termios_baud_rate(&tmp_termios); - ld = tty_ldisc_ref(tty); + if (opt & (TERMIOS_FLUSH|TERMIOS_WAIT)) { +retry_write_wait: + retval = wait_event_interruptible(tty->write_wait, !tty_chars_in_buffer(tty)); + if (retval < 0) + return retval; - if (ld != NULL) { - if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) - ld->ops->flush_buffer(tty); - tty_ldisc_deref(ld); - } + if (tty_write_lock(tty, 0) < 0) + goto retry_write_wait; - if (opt & TERMIOS_WAIT) { - tty_wait_until_sent(tty, 0); - if (signal_pending(current)) - return -ERESTARTSYS; - } + /* Racing writer? */ + if (tty_chars_in_buffer(tty)) { + tty_write_unlock(tty); + goto retry_write_wait; + } - tty_set_termios(tty, &tmp_termios); + ld = tty_ldisc_ref(tty); + if (ld != NULL) { + if ((opt & TERMIOS_FLUSH) && ld->ops->flush_buffer) + ld->ops->flush_buffer(tty); + tty_ldisc_deref(ld); + } + + if ((opt & TERMIOS_WAIT) && tty->ops->wait_until_sent) { + tty->ops->wait_until_sent(tty, 0); + if (signal_pending(current)) { + tty_write_unlock(tty); + return -ERESTARTSYS; + } + } + + tty_set_termios(tty, &tmp_termios); + + tty_write_unlock(tty); + } else { + tty_set_termios(tty, &tmp_termios); + } /* FIXME: Arguably if tmp_termios == tty->termios AND the actual requested termios was not tmp_termios then we may -- GitLab From 146a37e05d620cef4ad430e5d1c9c077fe6fa76f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Fri, 17 Mar 2023 13:33:18 +0200 Subject: [PATCH 1587/5631] serial: 8250: Fix serial8250_tx_empty() race with DMA Tx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There's a potential race before THRE/TEMT deasserts when DMA Tx is starting up (or the next batch of continuous Tx is being submitted). This can lead to misdetecting Tx empty condition. It is entirely normal for THRE/TEMT to be set for some time after the DMA Tx had been setup in serial8250_tx_dma(). As Tx side is definitely not empty at that point, it seems incorrect for serial8250_tx_empty() claim Tx is empty. Fix the race by also checking in serial8250_tx_empty() whether there's DMA Tx active. Note: This fix only addresses in-kernel race mainly to make using TCSADRAIN/FLUSH robust. Userspace can still cause other races but they seem userspace concurrency control problems. Fixes: 9ee4b83e51f74 ("serial: 8250: Add support for dmaengine") Cc: stable@vger.kernel.org Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230317113318.31327-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 12 ++++++++++++ drivers/tty/serial/8250/8250_port.c | 7 ++++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 287153d32536..1e8fe44a7099 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -365,6 +365,13 @@ static inline void serial8250_do_prepare_rx_dma(struct uart_8250_port *p) if (dma->prepare_rx_dma) dma->prepare_rx_dma(p); } + +static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) +{ + struct uart_8250_dma *dma = p->dma; + + return dma && dma->tx_running; +} #else static inline int serial8250_tx_dma(struct uart_8250_port *p) { @@ -380,6 +387,11 @@ static inline int serial8250_request_dma(struct uart_8250_port *p) return -1; } static inline void serial8250_release_dma(struct uart_8250_port *p) { } + +static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) +{ + return false; +} #endif static inline int ns16550a_goto_highspeed(struct uart_8250_port *up) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fa43df05342b..107bcdfb119c 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2005,18 +2005,19 @@ static int serial8250_tx_threshold_handle_irq(struct uart_port *port) static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); + unsigned int result = 0; unsigned long flags; - u16 lsr; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); - lsr = serial_lsr_in(up); + if (!serial8250_tx_dma_running(up) && uart_lsr_tx_empty(serial_lsr_in(up))) + result = TIOCSER_TEMT; spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); - return uart_lsr_tx_empty(lsr) ? TIOCSER_TEMT : 0; + return result; } unsigned int serial8250_do_get_mctrl(struct uart_port *port) -- GitLab From ec956e2c6f4e65c797a7107b32e22484f687f88d Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:15 +0200 Subject: [PATCH 1588/5631] dt-bindings: serial: snps-dw-apb-uart: Switch dma-names order Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a different board expects: rk3326-odroid-go2.dtb: serial@ff030000: dma-names:0: 'rx' was expected A quick and incomplete check shows the inconsistency is present in many other DTS files: $ git grep -A10 snps,dw-apb-uart | grep dma-names | sort -u arch/arm64/boot/dts/rockchip/px30.dtsi- dma-names = "tx", "rx"; arch/arm64/boot/dts/rockchip/rk3328.dtsi- dma-names = "tx", "rx"; arch/arm64/boot/dts/rockchip/rk3588s.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/rk3066a.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/rk3128.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/rk3288.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/rv1126.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/socfpga.dtsi- dma-names = "tx", "rx"; arch/arm/boot/dts/sun6i-a31.dtsi- dma-names = "rx", "tx"; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dma-names = "rx", "tx"; arch/arm/boot/dts/sun8i-v3s.dtsi- dma-names = "rx", "tx"; arch/arm/boot/dts/sunxi-h3-h5.dtsi- dma-names = "rx", "tx"; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dma-names = "rx", "tx"; The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not really affected, since all of them are using a shared DMA channel for rx and tx: $ git grep -A10 snps,dw-apb-uart | grep 'sun.*dmas' | sort -u arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 10>, <&dma 10>; arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 22>, <&dma 22>; arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 6>, <&dma 6>; arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 7>, <&dma 7>; arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 8>, <&dma 8>; arch/arm/boot/dts/sun6i-a31.dtsi- dmas = <&dma 9>, <&dma 9>; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dmas = <&dma 10>, <&dma 10>; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dmas = <&dma 6>, <&dma 6>; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dmas = <&dma 7>, <&dma 7>; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dmas = <&dma 8>, <&dma 8>; arch/arm/boot/dts/sun8i-a23-a33.dtsi- dmas = <&dma 9>, <&dma 9>; arch/arm/boot/dts/sun8i-v3s.dtsi- dmas = <&dma 6>, <&dma 6>; arch/arm/boot/dts/sun8i-v3s.dtsi- dmas = <&dma 7>, <&dma 7>; arch/arm/boot/dts/sun8i-v3s.dtsi- dmas = <&dma 8>, <&dma 8>; arch/arm/boot/dts/sunxi-h3-h5.dtsi- dmas = <&dma 6>, <&dma 6>; arch/arm/boot/dts/sunxi-h3-h5.dtsi- dmas = <&dma 7>, <&dma 7>; arch/arm/boot/dts/sunxi-h3-h5.dtsi- dmas = <&dma 8>, <&dma 8>; arch/arm/boot/dts/sunxi-h3-h5.dtsi- dmas = <&dma 9>, <&dma 9>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 14>, <&dma 14>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 15>, <&dma 15>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 16>, <&dma 16>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 17>, <&dma 17>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 18>, <&dma 18>; arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi- dmas = <&dma 19>, <&dma 19>; Switch dma-names order to tx->rx as the first step in fixing the inconsistency. The remaining DTS fixes will be handled by separate patches. Signed-off-by: Cristian Ciocaltea Reviewed-by: Conor Dooley Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230321215624.78383-2-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml index 8212a9f483b5..3862411c77b5 100644 --- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml +++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.yaml @@ -72,8 +72,8 @@ properties: dma-names: items: - - const: rx - const: tx + - const: rx snps,uart-16550-compatible: description: reflects the value of UART_16550_COMPATIBLE configuration -- GitLab From a4b7c361602fefd1120b58b327aef156768e846a Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:16 +0200 Subject: [PATCH 1589/5631] ARM: dts: sun6i: a31: Switch dma-names order for snps,dw-apb-uart nodes Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a bunch of different boards expect. The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not affected, since they are using a shared DMA channel for rx and tx. Hence, the first step in fixing the inconsistency was to change dma-names order in the binding to tx->rx. Do the same for the snps,dw-apb-uart nodes in the DTS file. Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230321215624.78383-3-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/sun6i-a31.dtsi | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 6cdadba6a3ac..5cce4918f84c 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -822,7 +822,7 @@ clocks = <&ccu CLK_APB2_UART0>; resets = <&ccu RST_APB2_UART0>; dmas = <&dma 6>, <&dma 6>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -835,7 +835,7 @@ clocks = <&ccu CLK_APB2_UART1>; resets = <&ccu RST_APB2_UART1>; dmas = <&dma 7>, <&dma 7>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -848,7 +848,7 @@ clocks = <&ccu CLK_APB2_UART2>; resets = <&ccu RST_APB2_UART2>; dmas = <&dma 8>, <&dma 8>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -861,7 +861,7 @@ clocks = <&ccu CLK_APB2_UART3>; resets = <&ccu RST_APB2_UART3>; dmas = <&dma 9>, <&dma 9>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -874,7 +874,7 @@ clocks = <&ccu CLK_APB2_UART4>; resets = <&ccu RST_APB2_UART4>; dmas = <&dma 10>, <&dma 10>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -887,7 +887,7 @@ clocks = <&ccu CLK_APB2_UART5>; resets = <&ccu RST_APB2_UART5>; dmas = <&dma 22>, <&dma 22>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; -- GitLab From 0b796ffab3b4fe5eea7b2b613a5710c323a24d44 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:17 +0200 Subject: [PATCH 1590/5631] ARM: dts: sun8i: a23/a33: Switch dma-names order for snps,dw-apb-uart nodes Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a bunch of different boards expect. The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not affected, since they are using a shared DMA channel for rx and tx. Hence, the first step in fixing the inconsistency was to change dma-names order in the binding to tx->rx. Do the same for the snps,dw-apb-uart nodes in the DTS file. Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230321215624.78383-4-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/sun8i-a23-a33.dtsi | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi index f630ab55bb6a..4aa9d88c9ea3 100644 --- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi +++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi @@ -490,7 +490,7 @@ clocks = <&ccu CLK_BUS_UART0>; resets = <&ccu RST_BUS_UART0>; dmas = <&dma 6>, <&dma 6>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -503,7 +503,7 @@ clocks = <&ccu CLK_BUS_UART1>; resets = <&ccu RST_BUS_UART1>; dmas = <&dma 7>, <&dma 7>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -516,7 +516,7 @@ clocks = <&ccu CLK_BUS_UART2>; resets = <&ccu RST_BUS_UART2>; dmas = <&dma 8>, <&dma 8>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -529,7 +529,7 @@ clocks = <&ccu CLK_BUS_UART3>; resets = <&ccu RST_BUS_UART3>; dmas = <&dma 9>, <&dma 9>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -542,7 +542,7 @@ clocks = <&ccu CLK_BUS_UART4>; resets = <&ccu RST_BUS_UART4>; dmas = <&dma 10>, <&dma 10>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; -- GitLab From 646a203a661bdb5777dd57fb1abd76fc6ed01bc1 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:18 +0200 Subject: [PATCH 1591/5631] ARM: dts: sun8i: v3s: Switch dma-names order for snps,dw-apb-uart nodes Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a bunch of different boards expect. The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not affected, since they are using a shared DMA channel for rx and tx. Hence, the first step in fixing the inconsistency was to change dma-names order in the binding to tx->rx. Do the same for the snps,dw-apb-uart nodes in the DTS file. Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230321215624.78383-5-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/sun8i-v3s.dtsi | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/sun8i-v3s.dtsi b/arch/arm/boot/dts/sun8i-v3s.dtsi index db194c606fdc..b001251644f7 100644 --- a/arch/arm/boot/dts/sun8i-v3s.dtsi +++ b/arch/arm/boot/dts/sun8i-v3s.dtsi @@ -479,7 +479,7 @@ reg-io-width = <4>; clocks = <&ccu CLK_BUS_UART0>; dmas = <&dma 6>, <&dma 6>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; resets = <&ccu RST_BUS_UART0>; status = "disabled"; }; @@ -492,7 +492,7 @@ reg-io-width = <4>; clocks = <&ccu CLK_BUS_UART1>; dmas = <&dma 7>, <&dma 7>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; resets = <&ccu RST_BUS_UART1>; status = "disabled"; }; @@ -505,7 +505,7 @@ reg-io-width = <4>; clocks = <&ccu CLK_BUS_UART2>; dmas = <&dma 8>, <&dma 8>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; resets = <&ccu RST_BUS_UART2>; pinctrl-0 = <&uart2_pins>; pinctrl-names = "default"; -- GitLab From 28cbc3a4473fa607e4501112d700585b1ee4ce75 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:19 +0200 Subject: [PATCH 1592/5631] ARM: dts: sunxi: h3/h5: Switch dma-names order for snps,dw-apb-uart nodes Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a bunch of different boards expect. The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not affected, since they are using a shared DMA channel for rx and tx. Hence, the first step in fixing the inconsistency was to change dma-names order in the binding to tx->rx. Do the same for the snps,dw-apb-uart nodes in the DTS file. Signed-off-by: Cristian Ciocaltea Link: https://lore.kernel.org/r/20230321215624.78383-6-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/sunxi-h3-h5.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi index 686193bd6bd9..ade1cd50e445 100644 --- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi +++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi @@ -710,7 +710,7 @@ clocks = <&ccu CLK_BUS_UART0>; resets = <&ccu RST_BUS_UART0>; dmas = <&dma 6>, <&dma 6>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -723,7 +723,7 @@ clocks = <&ccu CLK_BUS_UART1>; resets = <&ccu RST_BUS_UART1>; dmas = <&dma 7>, <&dma 7>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -736,7 +736,7 @@ clocks = <&ccu CLK_BUS_UART2>; resets = <&ccu RST_BUS_UART2>; dmas = <&dma 8>, <&dma 8>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -749,7 +749,7 @@ clocks = <&ccu CLK_BUS_UART3>; resets = <&ccu RST_BUS_UART3>; dmas = <&dma 9>, <&dma 9>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; -- GitLab From d30a28a764a8221874ab53b7cbe79f842c30b671 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 21 Mar 2023 23:56:20 +0200 Subject: [PATCH 1593/5631] riscv: dts: allwinner: d1: Switch dma-names order for snps,dw-apb-uart nodes Commit 370f696e4474 ("dt-bindings: serial: snps-dw-apb-uart: add dma & dma-names properties") documented dma-names property to handle Allwinner D1 dtbs_check warnings, but relies on the rx->tx ordering, which is the reverse of what a bunch of different boards expect. The initial proposed solution was to allow a flexible dma-names order in the binding, due to potential ABI breakage concerns after fixing the DTS files. But luckily the Allwinner boards are not affected, since they are using a shared DMA channel for rx and tx. Hence, the first step in fixing the inconsistency was to change dma-names order in the binding to tx->rx. Do the same for the snps,dw-apb-uart nodes in the DTS file. Signed-off-by: Cristian Ciocaltea Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230321215624.78383-7-cristian.ciocaltea@collabora.com Signed-off-by: Greg Kroah-Hartman --- arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi index 6fadcee7800f..3ab69c35d26c 100644 --- a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi +++ b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi @@ -211,7 +211,7 @@ clocks = <&ccu CLK_BUS_UART0>; resets = <&ccu RST_BUS_UART0>; dmas = <&dma 14>, <&dma 14>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -224,7 +224,7 @@ clocks = <&ccu CLK_BUS_UART1>; resets = <&ccu RST_BUS_UART1>; dmas = <&dma 15>, <&dma 15>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -237,7 +237,7 @@ clocks = <&ccu CLK_BUS_UART2>; resets = <&ccu RST_BUS_UART2>; dmas = <&dma 16>, <&dma 16>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -250,7 +250,7 @@ clocks = <&ccu CLK_BUS_UART3>; resets = <&ccu RST_BUS_UART3>; dmas = <&dma 17>, <&dma 17>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -263,7 +263,7 @@ clocks = <&ccu CLK_BUS_UART4>; resets = <&ccu RST_BUS_UART4>; dmas = <&dma 18>, <&dma 18>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; @@ -276,7 +276,7 @@ clocks = <&ccu CLK_BUS_UART5>; resets = <&ccu RST_BUS_UART5>; dmas = <&dma 19>, <&dma 19>; - dma-names = "rx", "tx"; + dma-names = "tx", "rx"; status = "disabled"; }; -- GitLab From a8a9e95243581d4f30295960f968d56a401c0eb1 Mon Sep 17 00:00:00 2001 From: Daniel Watson Date: Tue, 28 Mar 2023 17:29:58 -0700 Subject: [PATCH 1594/5631] staging: rtl8723bs: conform if's braces to kernel style Move the open brace of if-statements to the same line. This matches the brace placement style described in the kernel's style guide. Signed-off-by: Daniel Watson Link: https://lore.kernel.org/r/ZCOGhkLvLtBEo92Y@trent-reznor Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/include/rtw_recv.h | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/staging/rtl8723bs/include/rtw_recv.h b/drivers/staging/rtl8723bs/include/rtw_recv.h index 44f67103503a..fef2fd0e8c84 100644 --- a/drivers/staging/rtl8723bs/include/rtw_recv.h +++ b/drivers/staging/rtl8723bs/include/rtw_recv.h @@ -398,8 +398,7 @@ static inline u8 *recvframe_pull(union recv_frame *precvframe, signed int sz) precvframe->u.hdr.rx_data += sz; - if (precvframe->u.hdr.rx_data > precvframe->u.hdr.rx_tail) - { + if (precvframe->u.hdr.rx_data > precvframe->u.hdr.rx_tail) { precvframe->u.hdr.rx_data -= sz; return NULL; } @@ -425,8 +424,7 @@ static inline u8 *recvframe_put(union recv_frame *precvframe, signed int sz) precvframe->u.hdr.rx_tail += sz; - if (precvframe->u.hdr.rx_tail > precvframe->u.hdr.rx_end) - { + if (precvframe->u.hdr.rx_tail > precvframe->u.hdr.rx_end) { precvframe->u.hdr.rx_tail = prev_rx_tail; return NULL; } @@ -451,8 +449,7 @@ static inline u8 *recvframe_pull_tail(union recv_frame *precvframe, signed int s precvframe->u.hdr.rx_tail -= sz; - if (precvframe->u.hdr.rx_tail < precvframe->u.hdr.rx_data) - { + if (precvframe->u.hdr.rx_tail < precvframe->u.hdr.rx_data) { precvframe->u.hdr.rx_tail += sz; return NULL; } -- GitLab From fc36ce35e9458589ed7443985d11d044d17c6456 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Thu, 23 Mar 2023 19:57:42 +0800 Subject: [PATCH 1595/5631] RDMA/usnic: Remove redundant pci_clear_master Remove pci_clear_master to simplify the code, the bus-mastering is also cleared in do_pci_disable_device, like this: ./drivers/pci/pci.c:2197 static void do_pci_disable_device(struct pci_dev *dev) { u16 pci_command; pci_read_config_word(dev, PCI_COMMAND, &pci_command); if (pci_command & PCI_COMMAND_MASTER) { pci_command &= ~PCI_COMMAND_MASTER; pci_write_config_word(dev, PCI_COMMAND, pci_command); } pcibios_disable_device(dev); }. And dev->is_busmaster is set to 0 in pci_disable_device. Signed-off-by: Cai Huoqing Link: https://lore.kernel.org/r/20230323115742.13836-1-cai.huoqing@linux.dev Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/usnic/usnic_ib_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index 46653ad56f5a..13b654ddd3cc 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -602,7 +602,6 @@ static int usnic_ib_pci_probe(struct pci_dev *pdev, usnic_vnic_free(vf->vnic); out_release_regions: pci_set_drvdata(pdev, NULL); - pci_clear_master(pdev); pci_release_regions(pdev); out_disable_device: pci_disable_device(pdev); @@ -623,7 +622,6 @@ static void usnic_ib_pci_remove(struct pci_dev *pdev) kref_put(&pf->vf_cnt, usnic_ib_undiscover_pf); usnic_vnic_free(vf->vnic); pci_set_drvdata(pdev, NULL); - pci_clear_master(pdev); pci_release_regions(pdev); pci_disable_device(pdev); kfree(vf); -- GitLab From 52a7a5e91f9f63c99632687e85a7531d9ac9a706 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 19 Mar 2023 13:04:47 -0400 Subject: [PATCH 1596/5631] misc: hpilo: remove unused is_device_reset function clang with W=1 reports drivers/misc/hpilo.c:395:19: error: unused function 'is_device_reset' [-Werror,-Wunused-function] static inline int is_device_reset(struct ilo_hwinfo *hw) ^ This function is not used, so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230319170447.1707655-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/hpilo.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 8d00df9243c4..ba4b00b8bea1 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -392,12 +392,6 @@ static inline int is_db_reset(int db_out) return db_out & (1 << DB_RESET); } -static inline int is_device_reset(struct ilo_hwinfo *hw) -{ - /* check for global reset condition */ - return is_db_reset(get_device_outbound(hw)); -} - static inline void clear_pending_db(struct ilo_hwinfo *hw, int clr) { iowrite32(clr, &hw->mmio_vaddr[DB_OUT]); -- GitLab From 71d74aaa15b49d2ea6927706ee2a7debc88fe3c2 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 20 Mar 2023 20:02:03 -0400 Subject: [PATCH 1597/5631] misc: alcor_pci: remove unused alcor functions clang with W=1 reports drivers/misc/cardreader/alcor_pci.c:98:20: error: unused function 'alcor_mask_sd_irqs' [-Werror,-Wunused-function] static inline void alcor_mask_sd_irqs(struct alcor_pci_priv *priv) ^ drivers/misc/cardreader/alcor_pci.c:103:20: error: unused function 'alcor_unmask_sd_irqs' [-Werror,-Wunused-function] static inline void alcor_unmask_sd_irqs(struct alcor_pci_priv *priv) ^ drivers/misc/cardreader/alcor_pci.c:111:20: error: unused function 'alcor_mask_ms_irqs' [-Werror,-Wunused-function] static inline void alcor_mask_ms_irqs(struct alcor_pci_priv *priv) ^ drivers/misc/cardreader/alcor_pci.c:116:20: error: unused function 'alcor_unmask_ms_irqs' [-Werror,-Wunused-function] static inline void alcor_unmask_ms_irqs(struct alcor_pci_priv *priv) ^ These functions are not used, so remove them. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230321000203.1730802-1-trix@redhat.com Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/alcor_pci.c | 23 ----------------------- 1 file changed, 23 deletions(-) diff --git a/drivers/misc/cardreader/alcor_pci.c b/drivers/misc/cardreader/alcor_pci.c index 5b637171c46c..0142c4bf4f42 100644 --- a/drivers/misc/cardreader/alcor_pci.c +++ b/drivers/misc/cardreader/alcor_pci.c @@ -95,29 +95,6 @@ u32 alcor_read32be(struct alcor_pci_priv *priv, unsigned int addr) } EXPORT_SYMBOL_GPL(alcor_read32be); -static inline void alcor_mask_sd_irqs(struct alcor_pci_priv *priv) -{ - alcor_write32(priv, 0, AU6601_REG_INT_ENABLE); -} - -static inline void alcor_unmask_sd_irqs(struct alcor_pci_priv *priv) -{ - alcor_write32(priv, AU6601_INT_CMD_MASK | AU6601_INT_DATA_MASK | - AU6601_INT_CARD_INSERT | AU6601_INT_CARD_REMOVE | - AU6601_INT_OVER_CURRENT_ERR, - AU6601_REG_INT_ENABLE); -} - -static inline void alcor_mask_ms_irqs(struct alcor_pci_priv *priv) -{ - alcor_write32(priv, 0, AU6601_MS_INT_ENABLE); -} - -static inline void alcor_unmask_ms_irqs(struct alcor_pci_priv *priv) -{ - alcor_write32(priv, 0x3d00fa, AU6601_MS_INT_ENABLE); -} - static int alcor_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { -- GitLab From 3f84aa5ec052dba960baca4ab8a352d43d47028e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 17 Mar 2023 13:36:18 +0100 Subject: [PATCH 1598/5631] base: soc: populate machine name in soc_device_register if empty Several SoC drivers use the same of-based mechanism to populate the machine name. Therefore move this to the core and try to populate the machine name in soc_device_register if it's not set yet. Signed-off-by: Heiner Kallweit Acked-by: Martin Blumenstingl Link: https://lore.kernel.org/r/6dbdf458-9f46-613e-de58-b4a56a6cdd9f@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/soc.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/base/soc.c b/drivers/base/soc.c index 0fb1d4ab9d8a..8dec5228fde3 100644 --- a/drivers/base/soc.c +++ b/drivers/base/soc.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -110,6 +111,18 @@ static void soc_release(struct device *dev) kfree(soc_dev); } +static void soc_device_get_machine(struct soc_device_attribute *soc_dev_attr) +{ + struct device_node *np; + + if (soc_dev_attr->machine) + return; + + np = of_find_node_by_path("/"); + of_property_read_string(np, "model", &soc_dev_attr->machine); + of_node_put(np); +} + static struct soc_device_attribute *early_soc_dev_attr; struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr) @@ -118,6 +131,8 @@ struct soc_device *soc_device_register(struct soc_device_attribute *soc_dev_attr const struct attribute_group **soc_attr_groups; int ret; + soc_device_get_machine(soc_dev_attr); + if (!soc_bus_registered) { if (early_soc_dev_attr) return ERR_PTR(-EBUSY); -- GitLab From 67ca1b9346fe255cfe503b967407fd24ec76da37 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 17 Mar 2023 13:37:05 +0100 Subject: [PATCH 1599/5631] soc: amlogic: meson-gx-socinfo: use new soc_device_register functionality to populate machine name A new fallback mechanism has been added to soc_device_register that populates machine with the DT model information if machine isn't set yet. This allows to remove this code here. Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Link: https://lore.kernel.org/r/ac3b4356-d4c3-25e4-9bc2-c5b369c676b2@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/soc/amlogic/meson-gx-socinfo.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/soc/amlogic/meson-gx-socinfo.c b/drivers/soc/amlogic/meson-gx-socinfo.c index 165f7548401b..6abb730344ab 100644 --- a/drivers/soc/amlogic/meson-gx-socinfo.c +++ b/drivers/soc/amlogic/meson-gx-socinfo.c @@ -174,11 +174,6 @@ static int __init meson_gx_socinfo_init(void) return -ENODEV; soc_dev_attr->family = "Amlogic Meson"; - - np = of_find_node_by_path("/"); - of_property_read_string(np, "model", &soc_dev_attr->machine); - of_node_put(np); - soc_dev_attr->revision = kasprintf(GFP_KERNEL, "%x:%x - %x:%x", socinfo_to_major(socinfo), socinfo_to_minor(socinfo), -- GitLab From 02fe26f25325b547b7a31a65deb0326c04bb5174 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Amadeusz=20S=C5=82awi=C5=84ski?= Date: Fri, 17 Mar 2023 23:47:29 +0100 Subject: [PATCH 1600/5631] firmware_loader: Add debug message with checksum for FW file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enable dynamic-debug logging of firmware filenames and SHA256 checksums to clearly identify the firmware files that are loaded by the system. Example output: [ 34.944619] firmware_class:_request_firmware: i915 0000:00:02.0: Loaded FW: i915/kbl_dmc_ver1_04.bin, sha256: 2cde41c3e5ad181423bcc3e98ff9c49f743c88f18646af4d0b3c3a9664b831a1 [ 48.155884] firmware_class:_request_firmware: snd_soc_avs 0000:00:1f.3: Loaded FW: intel/avs/cnl/dsp_basefw.bin, sha256: 43f6ac1b066e9bd0423d914960fbbdccb391af27d2b1da1085eee3ea8df0f357 [ 49.579540] firmware_class:_request_firmware: snd_soc_avs 0000:00:1f.3: Loaded FW: intel/avs/rt274-tplg.bin, sha256: 4b3580da96dc3d2c443ba20c6728d8b665fceb3ed57223c3a57582bbad8e2413 [ 49.798196] firmware_class:_request_firmware: snd_soc_avs 0000:00:1f.3: Loaded FW: intel/avs/hda-8086280c-tplg.bin, sha256: 5653172579b2be1b51fd69f5cf46e2bac8d63f2a1327924311c13b2f1fe6e601 [ 49.859627] firmware_class:_request_firmware: snd_soc_avs 0000:00:1f.3: Loaded FW: intel/avs/dmic-tplg.bin, sha256: 00fb7fbdb74683333400d7e46925dae60db448b88638efcca0b30215db9df63f Reviewed-by: Cezary Rojewski Reviewed-by: Russ Weight Signed-off-by: Amadeusz Sławiński Link: https://lore.kernel.org/r/20230317224729.1025879-1-amadeuszx.slawinski@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/Kconfig | 12 +++++++ drivers/base/firmware_loader/main.c | 48 +++++++++++++++++++++++++++- 2 files changed, 59 insertions(+), 1 deletion(-) diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig index 5166b323a0f8..0cabc783d67a 100644 --- a/drivers/base/firmware_loader/Kconfig +++ b/drivers/base/firmware_loader/Kconfig @@ -24,6 +24,18 @@ config FW_LOADER You also want to be sure to enable this built-in if you are going to enable built-in firmware (CONFIG_EXTRA_FIRMWARE). +config FW_LOADER_DEBUG + bool "Log filenames and checksums for loaded firmware" + depends on DYNAMIC_DEBUG + depends on FW_LOADER + depends on CRYPTO + depends on CRYPTO_SHA256 + default FW_LOADER + help + Select this option to use dynamic debug to log firmware filenames and + SHA256 checksums to the kernel log for each firmware file that is + loaded. + if FW_LOADER config FW_LOADER_PAGED_BUF diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 017c4cdb219e..b2c292ca95e8 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -791,6 +791,50 @@ static void fw_abort_batch_reqs(struct firmware *fw) mutex_unlock(&fw_lock); } +#if defined(CONFIG_FW_LOADER_DEBUG) +#include +#include + +static void fw_log_firmware_info(const struct firmware *fw, const char *name, struct device *device) +{ + struct shash_desc *shash; + struct crypto_shash *alg; + u8 *sha256buf; + char *outbuf; + + alg = crypto_alloc_shash("sha256", 0, 0); + if (!alg) + return; + + sha256buf = kmalloc(SHA256_DIGEST_SIZE, GFP_KERNEL); + outbuf = kmalloc(SHA256_BLOCK_SIZE + 1, GFP_KERNEL); + shash = kmalloc(sizeof(*shash) + crypto_shash_descsize(alg), GFP_KERNEL); + if (!sha256buf || !outbuf || !shash) + goto out_free; + + shash->tfm = alg; + + if (crypto_shash_digest(shash, fw->data, fw->size, sha256buf) < 0) + goto out_shash; + + for (int i = 0; i < SHA256_DIGEST_SIZE; i++) + sprintf(&outbuf[i * 2], "%02x", sha256buf[i]); + outbuf[SHA256_BLOCK_SIZE] = 0; + dev_dbg(device, "Loaded FW: %s, sha256: %s\n", name, outbuf); + +out_shash: + crypto_free_shash(alg); +out_free: + kfree(shash); + kfree(outbuf); + kfree(sha256buf); +} +#else +static void fw_log_firmware_info(const struct firmware *fw, const char *name, + struct device *device) +{} +#endif + /* called from request_firmware() and request_firmware_work_func() */ static int _request_firmware(const struct firmware **firmware_p, const char *name, @@ -861,11 +905,13 @@ _request_firmware(const struct firmware **firmware_p, const char *name, revert_creds(old_cred); put_cred(kern_cred); - out: +out: if (ret < 0) { fw_abort_batch_reqs(fw); release_firmware(fw); fw = NULL; + } else { + fw_log_firmware_info(fw, name, device); } *firmware_p = fw; -- GitLab From 9caf696142252a466fb89e629d0eddcdced027b0 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Thu, 9 Mar 2023 22:09:30 +1100 Subject: [PATCH 1601/5631] kernfs: Introduce separate rwsem to protect inode attributes. Right now a global per-fs rwsem (kernfs_rwsem) synchronizes multiple kernfs operations. On a large system with few hundred CPUs and few hundred applications simultaneoulsy trying to access sysfs, this results in multiple sys_open(s) contending on kernfs_rwsem via kernfs_iop_permission and kernfs_dop_revalidate. For example on a system with 384 cores, if I run 200 instances of an application which is mostly executing the following loop: for (int loop = 0; loop <100 ; loop++) { for (int port_num = 1; port_num < 2; port_num++) { for (int gid_index = 0; gid_index < 254; gid_index++ ) { char ret_buf[64], ret_buf_lo[64]; char gid_file_path[1024]; int ret_len; int ret_fd; ssize_t ret_rd; ub4 i, saved_errno; memset(ret_buf, 0, sizeof(ret_buf)); memset(gid_file_path, 0, sizeof(gid_file_path)); ret_len = snprintf(gid_file_path, sizeof(gid_file_path), "/sys/class/infiniband/%s/ports/%d/gids/%d", dev_name, port_num, gid_index); ret_fd = open(gid_file_path, O_RDONLY | O_CLOEXEC); if (ret_fd < 0) { printf("Failed to open %s\n", gid_file_path); continue; } /* Read the GID */ ret_rd = read(ret_fd, ret_buf, 40); if (ret_rd == -1) { printf("Failed to read from file %s, errno: %u\n", gid_file_path, saved_errno); continue; } close(ret_fd); } } I see contention around kernfs_rwsem as follows: path_openat | |----link_path_walk.part.0.constprop.0 | | | |--49.92%--inode_permission | | | | | --48.69%--kernfs_iop_permission | | | | | |--18.16%--down_read | | | | | |--15.38%--up_read | | | | | --14.58%--_raw_spin_lock | | | | | ----- | | | |--29.08%--walk_component | | | | | --29.02%--lookup_fast | | | | | |--24.26%--kernfs_dop_revalidate | | | | | | | |--14.97%--down_read | | | | | | | --9.01%--up_read | | | | | --4.74%--__d_lookup | | | | | --4.64%--_raw_spin_lock | | | | | ---- Having a separate per-fs rwsem to protect kernfs inode attributes, will avoid the above mentioned contention and result in better performance as can bee seen below: path_openat | |----link_path_walk.part.0.constprop.0 | | | | | |--27.06%--inode_permission | | | | | --25.84%--kernfs_iop_permission | | | | | |--9.29%--up_read | | | | | |--8.19%--down_read | | | | | --7.89%--_raw_spin_lock | | | | | ---- | | | |--22.42%--walk_component | | | | | --22.36%--lookup_fast | | | | | |--16.07%--__d_lookup | | | | | | | --16.01%--_raw_spin_lock | | | | | | | ---- | | | | | --6.28%--kernfs_dop_revalidate | | | | | |--3.76%--down_read | | | | | --2.26%--up_read As can be seen from the above data the overhead due to both kerfs_iop_permission and kernfs_dop_revalidate have gone down and this also reduces overall run time of the earlier mentioned loop. Signed-off-by: Imran Khan Link: https://lore.kernel.org/r/20230309110932.2889010-2-imran.f.khan@oracle.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 7 +++++++ fs/kernfs/inode.c | 16 ++++++++-------- fs/kernfs/kernfs-internal.h | 1 + 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ef00b5fe8cee..953b2717c60e 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -770,12 +770,15 @@ int kernfs_add_one(struct kernfs_node *kn) goto out_unlock; /* Update timestamps on the parent */ + down_write(&root->kernfs_iattr_rwsem); + ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&root->kernfs_iattr_rwsem); up_write(&root->kernfs_rwsem); /* @@ -940,6 +943,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, idr_init(&root->ino_idr); init_rwsem(&root->kernfs_rwsem); + init_rwsem(&root->kernfs_iattr_rwsem); INIT_LIST_HEAD(&root->supers); /* @@ -1462,11 +1466,14 @@ static void __kernfs_remove(struct kernfs_node *kn) pos->parent ? pos->parent->iattr : NULL; /* update timestamps on the parent */ + down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); + if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } + up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_put(pos); } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 30494dcb0df3..b22b74d1a115 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -101,9 +101,9 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) int ret; struct kernfs_root *root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_iattr_rwsem); ret = __kernfs_setattr(kn, iattr); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return ret; } @@ -119,7 +119,7 @@ int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EINVAL; root = kernfs_root(kn); - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_iattr_rwsem); error = setattr_prepare(&nop_mnt_idmap, dentry, iattr); if (error) goto out; @@ -132,7 +132,7 @@ int kernfs_iop_setattr(struct mnt_idmap *idmap, struct dentry *dentry, setattr_copy(&nop_mnt_idmap, inode, iattr); out: - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_iattr_rwsem); return error; } @@ -189,10 +189,10 @@ int kernfs_iop_getattr(struct mnt_idmap *idmap, struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); generic_fillattr(&nop_mnt_idmap, inode, stat); - up_read(&root->kernfs_rwsem); + up_read(&root->kernfs_iattr_rwsem); return 0; } @@ -285,10 +285,10 @@ int kernfs_iop_permission(struct mnt_idmap *idmap, kn = inode->i_private; root = kernfs_root(kn); - down_read(&root->kernfs_rwsem); + down_read(&root->kernfs_iattr_rwsem); kernfs_refresh_inode(kn, inode); ret = generic_permission(&nop_mnt_idmap, inode, mask); - up_read(&root->kernfs_rwsem); + up_read(&root->kernfs_iattr_rwsem); return ret; } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 236c3a6113f1..3297093c920d 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -47,6 +47,7 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; + struct rw_semaphore kernfs_iattr_rwsem; }; /* +1 to avoid triggering overflow warning when negating it */ -- GitLab From c9f2dfb7b59e5a6db054f821a6e1a6db8fa57d64 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Thu, 9 Mar 2023 22:09:31 +1100 Subject: [PATCH 1602/5631] kernfs: Use a per-fs rwsem to protect per-fs list of kernfs_super_info. Right now per-fs kernfs_rwsem protects list of kernfs_super_info instances for a kernfs_root. Since kernfs_rwsem is used to synchronize several other operations across kernfs and since most of these operations don't impact kernfs_super_info, we can use a separate per-fs rwsem to synchronize access to list of kernfs_super_info. This helps in reducing contention around kernfs_rwsem and also allows operations that change/access list of kernfs_super_info to proceed without contending for kernfs_rwsem. Signed-off-by: Imran Khan Link: https://lore.kernel.org/r/20230309110932.2889010-3-imran.f.khan@oracle.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 1 + fs/kernfs/file.c | 4 ++-- fs/kernfs/kernfs-internal.h | 1 + fs/kernfs/mount.c | 8 ++++---- 4 files changed, 8 insertions(+), 6 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 953b2717c60e..2cdb8516e528 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -944,6 +944,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, idr_init(&root->ino_idr); init_rwsem(&root->kernfs_rwsem); init_rwsem(&root->kernfs_iattr_rwsem); + init_rwsem(&root->kernfs_supers_rwsem); INIT_LIST_HEAD(&root->supers); /* diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e4a50e4ff0d2..40c4661f15b7 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -922,8 +922,8 @@ static void kernfs_notify_workfn(struct work_struct *work) root = kernfs_root(kn); /* kick fsnotify */ - down_write(&root->kernfs_rwsem); + down_read(&root->kernfs_supers_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; @@ -960,7 +960,7 @@ static void kernfs_notify_workfn(struct work_struct *work) iput(inode); } - up_write(&root->kernfs_rwsem); + up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3297093c920d..a9b854cdfdb5 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -48,6 +48,7 @@ struct kernfs_root { wait_queue_head_t deactivate_waitq; struct rw_semaphore kernfs_rwsem; struct rw_semaphore kernfs_iattr_rwsem; + struct rw_semaphore kernfs_supers_rwsem; }; /* +1 to avoid triggering overflow warning when negating it */ diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index e08e8d999807..d49606accb07 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -351,9 +351,9 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_supers_rwsem); list_add(&info->node, &info->root->supers); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); } fc->root = dget(sb->s_root); @@ -380,9 +380,9 @@ void kernfs_kill_sb(struct super_block *sb) struct kernfs_super_info *info = kernfs_info(sb); struct kernfs_root *root = info->root; - down_write(&root->kernfs_rwsem); + down_write(&root->kernfs_supers_rwsem); list_del(&info->node); - up_write(&root->kernfs_rwsem); + up_write(&root->kernfs_supers_rwsem); /* * Remove the superblock from fs_supers/s_instances -- GitLab From 06fb4736139fde0e1431fe2a5b4912dcb7588d09 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Thu, 9 Mar 2023 22:09:32 +1100 Subject: [PATCH 1603/5631] kernfs: change kernfs_rename_lock into a read-write lock. kernfs_rename_lock protects a node's ->parent and thus kernfs topology. Thus it can be used in cases that rely on a stable kernfs topology. Change it to a read-write lock for better scalability. Suggested by: Al Viro Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Imran Khan Link: https://lore.kernel.org/r/20230309110932.2889010-4-imran.f.khan@oracle.com Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 2cdb8516e528..06e27b36216f 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,7 @@ #include "kernfs-internal.h" -static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ +static DEFINE_RWLOCK(kernfs_rename_lock); /* kn->parent and ->name */ /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() @@ -196,9 +196,9 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) unsigned long flags; int ret; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_name_locked(kn, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } @@ -224,9 +224,9 @@ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, unsigned long flags; int ret; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); ret = kernfs_path_from_node_locked(to, from, buf, buflen); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return ret; } EXPORT_SYMBOL_GPL(kernfs_path_from_node); @@ -294,10 +294,10 @@ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) struct kernfs_node *parent; unsigned long flags; - spin_lock_irqsave(&kernfs_rename_lock, flags); + read_lock_irqsave(&kernfs_rename_lock, flags); parent = kn->parent; kernfs_get(parent); - spin_unlock_irqrestore(&kernfs_rename_lock, flags); + read_unlock_irqrestore(&kernfs_rename_lock, flags); return parent; } @@ -1731,7 +1731,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, kernfs_get(new_parent); /* rename_lock protects ->parent and ->name accessors */ - spin_lock_irq(&kernfs_rename_lock); + write_lock_irq(&kernfs_rename_lock); old_parent = kn->parent; kn->parent = new_parent; @@ -1742,7 +1742,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, kn->name = new_name; } - spin_unlock_irq(&kernfs_rename_lock); + write_unlock_irq(&kernfs_rename_lock); kn->hash = kernfs_name_hash(kn->name, kn->ns); kernfs_link_sibling(kn); -- GitLab From 2959ab247061e67485d83b6af8feb3761ec08cb9 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:30 +0530 Subject: [PATCH 1604/5631] cdx: add the cdx bus driver Introduce AMD CDX bus, which provides a mechanism for scanning and probing CDX devices. These devices are memory mapped on system bus for Application Processors(APUs). CDX devices can be changed dynamically in the Fabric and CDX bus interacts with CDX controller to rescan the bus and rediscover the devices. Signed-off-by: Nipun Gupta Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-2-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-cdx | 12 + MAINTAINERS | 7 + drivers/Kconfig | 2 + drivers/Makefile | 1 + drivers/cdx/Kconfig | 17 + drivers/cdx/Makefile | 8 + drivers/cdx/cdx.c | 408 ++++++++++++++++++++++++ drivers/cdx/cdx.h | 62 ++++ include/linux/cdx/cdx_bus.h | 147 +++++++++ include/linux/mod_devicetable.h | 15 + scripts/mod/devicetable-offsets.c | 4 + scripts/mod/file2alias.c | 12 + 12 files changed, 695 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-bus-cdx create mode 100644 drivers/cdx/Kconfig create mode 100644 drivers/cdx/Makefile create mode 100644 drivers/cdx/cdx.c create mode 100644 drivers/cdx/cdx.h create mode 100644 include/linux/cdx/cdx_bus.h diff --git a/Documentation/ABI/testing/sysfs-bus-cdx b/Documentation/ABI/testing/sysfs-bus-cdx new file mode 100644 index 000000000000..43b4e161f226 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-bus-cdx @@ -0,0 +1,12 @@ +What: /sys/bus/cdx/rescan +Date: March 2023 +Contact: nipun.gupta@amd.com +Description: + Writing y/1/on to this file will cause rescan of the bus + and devices on the CDX bus. Any new devices are scanned and + added to the list of Linux devices and any devices removed are + also deleted from Linux. + + For example:: + + # echo 1 > /sys/bus/cdx/rescan diff --git a/MAINTAINERS b/MAINTAINERS index 619c30ec36dc..973cfbd3e3e0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -964,6 +964,13 @@ Q: https://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/efa/ F: include/uapi/rdma/efa-abi.h +AMD CDX BUS DRIVER +M: Nipun Gupta +M: Nikhil Agarwal +S: Maintained +F: drivers/cdx/* +F: include/linux/cdx/* + AMD CRYPTOGRAPHIC COPROCESSOR (CCP) DRIVER M: Tom Lendacky M: John Allen diff --git a/drivers/Kconfig b/drivers/Kconfig index 968bd0a6fd78..514ae6b24cb2 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -241,4 +241,6 @@ source "drivers/peci/Kconfig" source "drivers/hte/Kconfig" +source "drivers/cdx/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index 20b118dca999..7241d80a7b29 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -194,3 +194,4 @@ obj-$(CONFIG_MOST) += most/ obj-$(CONFIG_PECI) += peci/ obj-$(CONFIG_HTE) += hte/ obj-$(CONFIG_DRM_ACCEL) += accel/ +obj-$(CONFIG_CDX_BUS) += cdx/ diff --git a/drivers/cdx/Kconfig b/drivers/cdx/Kconfig new file mode 100644 index 000000000000..1aaee0ec5bd9 --- /dev/null +++ b/drivers/cdx/Kconfig @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# CDX bus configuration +# +# Copyright (C) 2022-2023, Advanced Micro Devices, Inc. +# + +config CDX_BUS + bool "CDX Bus driver" + depends on OF && ARM64 + help + Driver to enable Composable DMA Transfer(CDX) Bus. CDX bus + exposes Fabric devices which uses composable DMA IP to the + APU. CDX bus provides a mechanism for scanning and probing + of CDX devices. CDX devices are memory mapped on system bus + for embedded CPUs. CDX bus uses CDX controller and firmware + to scan these CDX devices. diff --git a/drivers/cdx/Makefile b/drivers/cdx/Makefile new file mode 100644 index 000000000000..c5feb11fc718 --- /dev/null +++ b/drivers/cdx/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for CDX +# +# Copyright (C) 2022-2023, Advanced Micro Devices, Inc. +# + +obj-$(CONFIG_CDX_BUS) += cdx.o diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c new file mode 100644 index 000000000000..6b162bbb9b25 --- /dev/null +++ b/drivers/cdx/cdx.c @@ -0,0 +1,408 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CDX bus driver. + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +/* + * Architecture Overview + * ===================== + * CDX is a Hardware Architecture designed for AMD FPGA devices. It + * consists of sophisticated mechanism for interaction between FPGA, + * Firmware and the APUs (Application CPUs). + * + * Firmware resides on RPU (Realtime CPUs) which interacts with + * the FPGA program manager and the APUs. The RPU provides memory-mapped + * interface (RPU if) which is used to communicate with APUs. + * + * The diagram below shows an overview of the CDX architecture: + * + * +--------------------------------------+ + * | Application CPUs (APU) | + * | | + * | CDX device drivers| + * | Linux OS | | + * | CDX bus | + * | | | + * | CDX controller | + * | | | + * +-----------------------------|--------+ + * | (discover, config, + * | reset, rescan) + * | + * +------------------------| RPU if |----+ + * | | | + * | V | + * | Realtime CPUs (RPU) | + * | | + * +--------------------------------------+ + * | + * +---------------------|----------------+ + * | FPGA | | + * | +-----------------------+ | + * | | | | | + * | +-------+ +-------+ +-------+ | + * | | dev 1 | | dev 2 | | dev 3 | | + * | +-------+ +-------+ +-------+ | + * +--------------------------------------+ + * + * The RPU firmware extracts the device information from the loaded FPGA + * image and implements a mechanism that allows the APU drivers to + * enumerate such devices (device personality and resource details) via + * a dedicated communication channel. RPU mediates operations such as + * discover, reset and rescan of the FPGA devices for the APU. This is + * done using memory mapped interface provided by the RPU to APU. + */ + +#include +#include +#include +#include +#include +#include +#include +#include "cdx.h" + +/* Default DMA mask for devices on a CDX bus */ +#define CDX_DEFAULT_DMA_MASK (~0ULL) +#define MAX_CDX_CONTROLLERS 16 + +/* CDX controllers registered with the CDX bus */ +static DEFINE_XARRAY_ALLOC(cdx_controllers); + +/** + * cdx_unregister_device - Unregister a CDX device + * @dev: CDX device + * @data: This is always passed as NULL, and is not used in this API, + * but is required here as the bus_for_each_dev() API expects + * the passed function (cdx_unregister_device) to have this + * as an argument. + * + * Return: 0 on success. + */ +static int cdx_unregister_device(struct device *dev, + void *data) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + + kfree(cdx_dev->driver_override); + cdx_dev->driver_override = NULL; + /* + * Do not free cdx_dev here as it would be freed in + * cdx_device_release() called from within put_device(). + */ + device_del(&cdx_dev->dev); + put_device(&cdx_dev->dev); + + return 0; +} + +static void cdx_unregister_devices(struct bus_type *bus) +{ + /* Reset all the devices attached to cdx bus */ + bus_for_each_dev(bus, NULL, NULL, cdx_unregister_device); +} + +/** + * cdx_match_one_device - Tell if a CDX device structure has a matching + * CDX device id structure + * @id: single CDX device id structure to match + * @dev: the CDX device structure to match against + * + * Return: matching cdx_device_id structure or NULL if there is no match. + */ +static inline const struct cdx_device_id * +cdx_match_one_device(const struct cdx_device_id *id, + const struct cdx_device *dev) +{ + /* Use vendor ID and device ID for matching */ + if ((id->vendor == CDX_ANY_ID || id->vendor == dev->vendor) && + (id->device == CDX_ANY_ID || id->device == dev->device)) + return id; + return NULL; +} + +/** + * cdx_match_id - See if a CDX device matches a given cdx_id table + * @ids: array of CDX device ID structures to search in + * @dev: the CDX device structure to match against. + * + * Used by a driver to check whether a CDX device is in its list of + * supported devices. Returns the matching cdx_device_id structure or + * NULL if there is no match. + * + * Return: matching cdx_device_id structure or NULL if there is no match. + */ +static inline const struct cdx_device_id * +cdx_match_id(const struct cdx_device_id *ids, struct cdx_device *dev) +{ + if (ids) { + while (ids->vendor || ids->device) { + if (cdx_match_one_device(ids, dev)) + return ids; + ids++; + } + } + return NULL; +} + +/** + * cdx_bus_match - device to driver matching callback + * @dev: the cdx device to match against + * @drv: the device driver to search for matching cdx device + * structures + * + * Return: true on success, false otherwise. + */ +static int cdx_bus_match(struct device *dev, struct device_driver *drv) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + struct cdx_driver *cdx_drv = to_cdx_driver(drv); + const struct cdx_device_id *found_id = NULL; + const struct cdx_device_id *ids; + + ids = cdx_drv->match_id_table; + + /* When driver_override is set, only bind to the matching driver */ + if (cdx_dev->driver_override && strcmp(cdx_dev->driver_override, drv->name)) + return false; + + found_id = cdx_match_id(ids, cdx_dev); + if (!found_id) + return false; + + do { + /* + * In case override_only was set, enforce driver_override + * matching. + */ + if (!found_id->override_only) + return true; + if (cdx_dev->driver_override) + return true; + + ids = found_id + 1; + found_id = cdx_match_id(ids, cdx_dev); + } while (found_id); + + return false; +} + +static int cdx_probe(struct device *dev) +{ + struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver); + struct cdx_device *cdx_dev = to_cdx_device(dev); + int error; + + error = cdx_drv->probe(cdx_dev); + if (error) { + dev_err_probe(dev, error, "%s failed\n", __func__); + return error; + } + + return 0; +} + +static void cdx_remove(struct device *dev) +{ + struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver); + struct cdx_device *cdx_dev = to_cdx_device(dev); + + if (cdx_drv && cdx_drv->remove) + cdx_drv->remove(cdx_dev); +} + +static void cdx_shutdown(struct device *dev) +{ + struct cdx_driver *cdx_drv = to_cdx_driver(dev->driver); + struct cdx_device *cdx_dev = to_cdx_device(dev); + + if (cdx_drv && cdx_drv->shutdown) + cdx_drv->shutdown(cdx_dev); +} + +static int cdx_dma_configure(struct device *dev) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + u32 input_id = cdx_dev->req_id; + int ret; + + ret = of_dma_configure_id(dev, dev->parent->of_node, 0, &input_id); + if (ret && ret != -EPROBE_DEFER) { + dev_err(dev, "of_dma_configure_id() failed\n"); + return ret; + } + + return 0; +} + +static ssize_t rescan_store(struct bus_type *bus, + const char *buf, size_t count) +{ + struct cdx_controller *cdx; + unsigned long index; + bool val; + + if (kstrtobool(buf, &val) < 0) + return -EINVAL; + + if (!val) + return -EINVAL; + + /* Unregister all the devices on the bus */ + cdx_unregister_devices(&cdx_bus_type); + + /* Rescan all the devices */ + xa_for_each(&cdx_controllers, index, cdx) { + int ret; + + ret = cdx->ops->scan(cdx); + if (ret) + dev_err(cdx->dev, "cdx bus scanning failed\n"); + } + + return count; +} +static BUS_ATTR_WO(rescan); + +static struct attribute *cdx_bus_attrs[] = { + &bus_attr_rescan.attr, + NULL, +}; +ATTRIBUTE_GROUPS(cdx_bus); + +struct bus_type cdx_bus_type = { + .name = "cdx", + .match = cdx_bus_match, + .probe = cdx_probe, + .remove = cdx_remove, + .shutdown = cdx_shutdown, + .dma_configure = cdx_dma_configure, + .bus_groups = cdx_bus_groups, +}; +EXPORT_SYMBOL_GPL(cdx_bus_type); + +int __cdx_driver_register(struct cdx_driver *cdx_driver, + struct module *owner) +{ + int error; + + cdx_driver->driver.owner = owner; + cdx_driver->driver.bus = &cdx_bus_type; + + error = driver_register(&cdx_driver->driver); + if (error) { + pr_err("driver_register() failed for %s: %d\n", + cdx_driver->driver.name, error); + return error; + } + + return 0; +} +EXPORT_SYMBOL_GPL(__cdx_driver_register); + +void cdx_driver_unregister(struct cdx_driver *cdx_driver) +{ + driver_unregister(&cdx_driver->driver); +} +EXPORT_SYMBOL_GPL(cdx_driver_unregister); + +static void cdx_device_release(struct device *dev) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + + kfree(cdx_dev); +} + +int cdx_device_add(struct cdx_dev_params *dev_params) +{ + struct cdx_controller *cdx = dev_params->cdx; + struct device *parent = cdx->dev; + struct cdx_device *cdx_dev; + int ret; + + cdx_dev = kzalloc(sizeof(*cdx_dev), GFP_KERNEL); + if (!cdx_dev) + return -ENOMEM; + + /* Populate resource */ + memcpy(cdx_dev->res, dev_params->res, sizeof(struct resource) * + dev_params->res_count); + cdx_dev->res_count = dev_params->res_count; + + /* Populate CDX dev params */ + cdx_dev->req_id = dev_params->req_id; + cdx_dev->vendor = dev_params->vendor; + cdx_dev->device = dev_params->device; + cdx_dev->bus_num = dev_params->bus_num; + cdx_dev->dev_num = dev_params->dev_num; + cdx_dev->cdx = dev_params->cdx; + cdx_dev->dma_mask = CDX_DEFAULT_DMA_MASK; + + /* Initialize generic device */ + device_initialize(&cdx_dev->dev); + cdx_dev->dev.parent = parent; + cdx_dev->dev.bus = &cdx_bus_type; + cdx_dev->dev.dma_mask = &cdx_dev->dma_mask; + cdx_dev->dev.release = cdx_device_release; + + /* Set Name */ + dev_set_name(&cdx_dev->dev, "cdx-%02x:%02x", + ((cdx->id << CDX_CONTROLLER_ID_SHIFT) | (cdx_dev->bus_num & CDX_BUS_NUM_MASK)), + cdx_dev->dev_num); + + ret = device_add(&cdx_dev->dev); + if (ret) { + dev_err(&cdx_dev->dev, + "cdx device add failed: %d", ret); + goto fail; + } + + return 0; +fail: + /* + * Do not free cdx_dev here as it would be freed in + * cdx_device_release() called from put_device(). + */ + put_device(&cdx_dev->dev); + + return ret; +} +EXPORT_SYMBOL_GPL(cdx_device_add); + +int cdx_register_controller(struct cdx_controller *cdx) +{ + int ret; + + ret = xa_alloc(&cdx_controllers, &cdx->id, cdx, + XA_LIMIT(0, MAX_CDX_CONTROLLERS - 1), GFP_KERNEL); + if (ret) { + dev_err(cdx->dev, + "No free index available. Maximum controllers already registered\n"); + cdx->id = (u8)MAX_CDX_CONTROLLERS; + return ret; + } + + /* Scan all the devices */ + cdx->ops->scan(cdx); + + return 0; +} +EXPORT_SYMBOL_GPL(cdx_register_controller); + +void cdx_unregister_controller(struct cdx_controller *cdx) +{ + if (cdx->id >= MAX_CDX_CONTROLLERS) + return; + + device_for_each_child(cdx->dev, NULL, cdx_unregister_device); + xa_erase(&cdx_controllers, cdx->id); +} +EXPORT_SYMBOL_GPL(cdx_unregister_controller); + +static int __init cdx_bus_init(void) +{ + return bus_register(&cdx_bus_type); +} +postcore_initcall(cdx_bus_init); diff --git a/drivers/cdx/cdx.h b/drivers/cdx/cdx.h new file mode 100644 index 000000000000..c436ac7ac86f --- /dev/null +++ b/drivers/cdx/cdx.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Header file for the CDX Bus + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef _CDX_H_ +#define _CDX_H_ + +#include + +/** + * struct cdx_dev_params - CDX device parameters + * @cdx: CDX controller associated with the device + * @parent: Associated CDX controller + * @vendor: Vendor ID for CDX device + * @device: Device ID for CDX device + * @bus_num: Bus number for this CDX device + * @dev_num: Device number for this device + * @res: array of MMIO region entries + * @res_count: number of valid MMIO regions + * @req_id: Requestor ID associated with CDX device + */ +struct cdx_dev_params { + struct cdx_controller *cdx; + u16 vendor; + u16 device; + u8 bus_num; + u8 dev_num; + struct resource res[MAX_CDX_DEV_RESOURCES]; + u8 res_count; + u32 req_id; +}; + +/** + * cdx_register_controller - Register a CDX controller and its ports + * on the CDX bus. + * @cdx: The CDX controller to register + * + * Return: -errno on failure, 0 on success. + */ +int cdx_register_controller(struct cdx_controller *cdx); + +/** + * cdx_unregister_controller - Unregister a CDX controller + * @cdx: The CDX controller to unregister + */ +void cdx_unregister_controller(struct cdx_controller *cdx); + +/** + * cdx_device_add - Add a CDX device. This function adds a CDX device + * on the CDX bus as per the device parameters provided + * by caller. It also creates and registers an associated + * Linux generic device. + * @dev_params: device parameters associated with the device to be created. + * + * Return: -errno on failure, 0 on success. + */ +int cdx_device_add(struct cdx_dev_params *dev_params); + +#endif /* _CDX_H_ */ diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h new file mode 100644 index 000000000000..d134e0104724 --- /dev/null +++ b/include/linux/cdx/cdx_bus.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CDX bus public interface + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + * + */ + +#ifndef _CDX_BUS_H_ +#define _CDX_BUS_H_ + +#include +#include +#include + +#define MAX_CDX_DEV_RESOURCES 4 +#define CDX_ANY_ID (0xFFFF) +#define CDX_CONTROLLER_ID_SHIFT 4 +#define CDX_BUS_NUM_MASK 0xF + +/* Forward declaration for CDX controller */ +struct cdx_controller; + +typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); + +/** + * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with + * override_only flags. + * @vend: the 16 bit CDX Vendor ID + * @dev: the 16 bit CDX Device ID + * @driver_override: the 32 bit CDX Device override_only + * + * This macro is used to create a struct cdx_device_id that matches only a + * driver_override device. + */ +#define CDX_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \ + .vendor = (vend), .device = (dev), .override_only = (driver_override) + +/** + * struct cdx_ops - Callbacks supported by CDX controller. + * @scan: scan the devices on the controller + */ +struct cdx_ops { + cdx_scan_cb scan; +}; + +/** + * struct cdx_controller: CDX controller object + * @dev: Linux device associated with the CDX controller. + * @priv: private data + * @id: Controller ID + * @ops: CDX controller ops + */ +struct cdx_controller { + struct device *dev; + void *priv; + u32 id; + struct cdx_ops *ops; +}; + +/** + * struct cdx_device - CDX device object + * @dev: Linux driver model device object + * @cdx: CDX controller associated with the device + * @vendor: Vendor ID for CDX device + * @device: Device ID for CDX device + * @bus_num: Bus number for this CDX device + * @dev_num: Device number for this device + * @res: array of MMIO region entries + * @res_attr: resource binary attribute + * @res_count: number of valid MMIO regions + * @dma_mask: Default DMA mask + * @flags: CDX device flags + * @req_id: Requestor ID associated with CDX device + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. + */ +struct cdx_device { + struct device dev; + struct cdx_controller *cdx; + u16 vendor; + u16 device; + u8 bus_num; + u8 dev_num; + struct resource res[MAX_CDX_DEV_RESOURCES]; + u8 res_count; + u64 dma_mask; + u16 flags; + u32 req_id; + const char *driver_override; +}; + +#define to_cdx_device(_dev) \ + container_of(_dev, struct cdx_device, dev) + +/** + * struct cdx_driver - CDX device driver + * @driver: Generic device driver + * @match_id_table: table of supported device matching Ids + * @probe: Function called when a device is added + * @remove: Function called when a device is removed + * @shutdown: Function called at shutdown time to quiesce the device + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. + */ +struct cdx_driver { + struct device_driver driver; + const struct cdx_device_id *match_id_table; + int (*probe)(struct cdx_device *dev); + int (*remove)(struct cdx_device *dev); + void (*shutdown)(struct cdx_device *dev); + bool driver_managed_dma; +}; + +#define to_cdx_driver(_drv) \ + container_of(_drv, struct cdx_driver, driver) + +/* Macro to avoid include chaining to get THIS_MODULE */ +#define cdx_driver_register(drv) \ + __cdx_driver_register(drv, THIS_MODULE) + +/** + * __cdx_driver_register - registers a CDX device driver + * @cdx_driver: CDX driver to register + * @owner: module owner + * + * Return: -errno on failure, 0 on success. + */ +int __must_check __cdx_driver_register(struct cdx_driver *cdx_driver, + struct module *owner); + +/** + * cdx_driver_unregister - unregisters a device driver from the + * CDX bus. + * @cdx_driver: CDX driver to register + */ +void cdx_driver_unregister(struct cdx_driver *cdx_driver); + +extern struct bus_type cdx_bus_type; + +#endif /* _CDX_BUS_H_ */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 35203ca3fc37..ccaaeda792c0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -912,4 +912,19 @@ struct ishtp_device_id { kernel_ulong_t driver_data; }; +/** + * struct cdx_device_id - CDX device identifier + * @vendor: Vendor ID + * @device: Device ID + * @override_only: Match only when dev->driver_override is this driver. + * + * Type of entries in the "device Id" table for CDX devices supported by + * a CDX device driver. + */ +struct cdx_device_id { + __u16 vendor; + __u16 device; + __u32 override_only; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index c0d3bcb99138..62dc988df84d 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -262,5 +262,9 @@ int main(void) DEVID(ishtp_device_id); DEVID_FIELD(ishtp_device_id, guid); + DEVID(cdx_device_id); + DEVID_FIELD(cdx_device_id, vendor); + DEVID_FIELD(cdx_device_id, device); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 91c2e7ba5e52..28da34ba4359 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -1452,6 +1452,17 @@ static int do_dfl_entry(const char *filename, void *symval, char *alias) return 1; } +/* Looks like: cdx:vNdN */ +static int do_cdx_entry(const char *filename, void *symval, + char *alias) +{ + DEF_FIELD(symval, cdx_device_id, vendor); + DEF_FIELD(symval, cdx_device_id, device); + + sprintf(alias, "cdx:v%08Xd%08Xd", vendor, device); + return 1; +} + /* Does namelen bytes of name exactly match the symbol? */ static bool sym_is(const char *name, unsigned namelen, const char *symbol) { @@ -1531,6 +1542,7 @@ static const struct devtable devtable[] = { {"ssam", SIZE_ssam_device_id, do_ssam_entry}, {"dfl", SIZE_dfl_device_id, do_dfl_entry}, {"ishtp", SIZE_ishtp_device_id, do_ishtp_entry}, + {"cdx", SIZE_cdx_device_id, do_cdx_entry}, }; /* Create MODULE_ALIAS() statements. -- GitLab From 3f47d3e44df0072c340ce417f6509a7cbd51ef7c Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:31 +0530 Subject: [PATCH 1605/5631] iommu: Add iommu probe for CDX bus Add CDX bus to iommu_buses so that IOMMU probe is called for it. Signed-off-by: Nipun Gupta Reviewed-by: Pieter Jansen van Vuuren Reviewed-by: Lu Baolu Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-3-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/iommu/iommu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 10db680acaed..0025a631b8e1 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -129,6 +130,9 @@ static struct bus_type * const iommu_buses[] = { #ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS &host1x_context_device_bus_type, #endif +#ifdef CONFIG_CDX_BUS + &cdx_bus_type, +#endif }; /* -- GitLab From c47a88e1930fa0f2df8aaa643a5cc86bcf5812bf Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:32 +0530 Subject: [PATCH 1606/5631] dt-bindings: bus: add CDX bus controller for versal net Add CDX bus controller device tree bindings for versal-net devices. Signed-off-by: Nipun Gupta Reviewed-by: Rob Herring Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-4-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- .../bindings/bus/xlnx,versal-net-cdx.yaml | 82 +++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 83 insertions(+) create mode 100644 Documentation/devicetree/bindings/bus/xlnx,versal-net-cdx.yaml diff --git a/Documentation/devicetree/bindings/bus/xlnx,versal-net-cdx.yaml b/Documentation/devicetree/bindings/bus/xlnx,versal-net-cdx.yaml new file mode 100644 index 000000000000..7f62ffbdc245 --- /dev/null +++ b/Documentation/devicetree/bindings/bus/xlnx,versal-net-cdx.yaml @@ -0,0 +1,82 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/bus/xlnx,versal-net-cdx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: AMD CDX bus controller + +description: | + CDX bus controller for AMD devices is implemented to dynamically + detect CDX bus and devices using the firmware. + The CDX bus manages multiple FPGA based hardware devices, which + can support network, crypto or any other specialized type of + devices. These FPGA based devices can be added/modified dynamically + on run-time. + + All devices on the CDX bus will have a unique streamid (for IOMMU) + and a unique device ID (for MSI) corresponding to a requestor ID + (one to one associated with the device). The streamid and deviceid + are used to configure SMMU and GIC-ITS respectively. + + iommu-map property is used to define the set of stream ids + corresponding to each device and the associated IOMMU. + + The MSI writes are accompanied by sideband data (Device ID). + The msi-map property is used to associate the devices with the + device ID as well as the associated ITS controller. + + rproc property (xlnx,rproc) is used to identify the remote processor + with which APU (Application Processor Unit) interacts to find out + the bus and device configuration. + +maintainers: + - Nipun Gupta + - Nikhil Agarwal + +properties: + compatible: + const: xlnx,versal-net-cdx + + iommu-map: true + + msi-map: true + + xlnx,rproc: + $ref: /schemas/types.yaml#/definitions/phandle + description: + phandle to the remoteproc_r5 rproc node using which APU interacts + with remote processor. + + ranges: true + + "#address-cells": + enum: [1, 2] + + "#size-cells": + enum: [1, 2] + +required: + - compatible + - iommu-map + - msi-map + - xlnx,rproc + - ranges + - "#address-cells" + - "#size-cells" + +additionalProperties: false + +examples: + - | + cdx { + compatible = "xlnx,versal-net-cdx"; + #address-cells = <1>; + #size-cells = <1>; + /* define map for RIDs 250-259 */ + iommu-map = <250 &smmu 250 10>; + /* define msi map for RIDs 250-259 */ + msi-map = <250 &its 250 10>; + xlnx,rproc = <&remoteproc_r5>; + ranges; + }; diff --git a/MAINTAINERS b/MAINTAINERS index 973cfbd3e3e0..4d4f778ede5d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -968,6 +968,7 @@ AMD CDX BUS DRIVER M: Nipun Gupta M: Nikhil Agarwal S: Maintained +F: Documentation/devicetree/bindings/bus/xlnx,versal-net-cdx.yaml F: drivers/cdx/* F: include/linux/cdx/* -- GitLab From eb96b740192b2a09720aaed8a8c132e6a29d5bdb Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:33 +0530 Subject: [PATCH 1607/5631] cdx: add MCDI protocol interface for firmware interaction The MCDI (Management CPU Driver Interface) is used as a protocol to communicate with the RPU firmware. It has pre-defined set of messages for different message exchanges between APU and RPU. Signed-off-by: Puneet Gupta Signed-off-by: Nipun Gupta Signed-off-by: Tarak Reddy Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-5-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/cdx/Kconfig | 2 + drivers/cdx/Makefile | 2 +- drivers/cdx/controller/Kconfig | 20 + drivers/cdx/controller/Makefile | 9 + drivers/cdx/controller/bitfield.h | 90 +++ drivers/cdx/controller/mc_cdx_pcol.h | 590 +++++++++++++++++ drivers/cdx/controller/mcdi.c | 903 +++++++++++++++++++++++++++ drivers/cdx/controller/mcdi.h | 238 +++++++ 8 files changed, 1853 insertions(+), 1 deletion(-) create mode 100644 drivers/cdx/controller/Kconfig create mode 100644 drivers/cdx/controller/Makefile create mode 100644 drivers/cdx/controller/bitfield.h create mode 100644 drivers/cdx/controller/mc_cdx_pcol.h create mode 100644 drivers/cdx/controller/mcdi.c create mode 100644 drivers/cdx/controller/mcdi.h diff --git a/drivers/cdx/Kconfig b/drivers/cdx/Kconfig index 1aaee0ec5bd9..a08958485e31 100644 --- a/drivers/cdx/Kconfig +++ b/drivers/cdx/Kconfig @@ -15,3 +15,5 @@ config CDX_BUS of CDX devices. CDX devices are memory mapped on system bus for embedded CPUs. CDX bus uses CDX controller and firmware to scan these CDX devices. + +source "drivers/cdx/controller/Kconfig" diff --git a/drivers/cdx/Makefile b/drivers/cdx/Makefile index c5feb11fc718..0324e4914f6e 100644 --- a/drivers/cdx/Makefile +++ b/drivers/cdx/Makefile @@ -5,4 +5,4 @@ # Copyright (C) 2022-2023, Advanced Micro Devices, Inc. # -obj-$(CONFIG_CDX_BUS) += cdx.o +obj-$(CONFIG_CDX_BUS) += cdx.o controller/ diff --git a/drivers/cdx/controller/Kconfig b/drivers/cdx/controller/Kconfig new file mode 100644 index 000000000000..785c71063b2a --- /dev/null +++ b/drivers/cdx/controller/Kconfig @@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# CDX controller configuration +# +# Copyright (C) 2022-2023, Advanced Micro Devices, Inc. +# + +if CDX_BUS + +config MCDI_LOGGING + bool "MCDI Logging for the CDX controller" + depends on CDX_CONTROLLER + help + Enable MCDI Logging for + the CDX Controller for debug + purpose. + + If unsure, say N. + +endif diff --git a/drivers/cdx/controller/Makefile b/drivers/cdx/controller/Makefile new file mode 100644 index 000000000000..0ce200678eda --- /dev/null +++ b/drivers/cdx/controller/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for CDX controller drivers +# +# Copyright (C) 2022-2023, Advanced Micro Devices, Inc. +# + +obj-$(CONFIG_CDX_CONTROLLER) += cdx-controller.o +cdx-controller-objs := mcdi.o diff --git a/drivers/cdx/controller/bitfield.h b/drivers/cdx/controller/bitfield.h new file mode 100644 index 000000000000..567f8ec47582 --- /dev/null +++ b/drivers/cdx/controller/bitfield.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2013 Solarflare Communications Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef CDX_BITFIELD_H +#define CDX_BITFIELD_H + +#include + +/* Lowest bit numbers and widths */ +#define CDX_DWORD_LBN 0 +#define CDX_DWORD_WIDTH 32 + +/* Specified attribute (e.g. LBN) of the specified field */ +#define CDX_VAL(field, attribute) field ## _ ## attribute +/* Low bit number of the specified field */ +#define CDX_LOW_BIT(field) CDX_VAL(field, LBN) +/* Bit width of the specified field */ +#define CDX_WIDTH(field) CDX_VAL(field, WIDTH) +/* High bit number of the specified field */ +#define CDX_HIGH_BIT(field) (CDX_LOW_BIT(field) + CDX_WIDTH(field) - 1) + +/* A doubleword (i.e. 4 byte) datatype - little-endian in HW */ +struct cdx_dword { + __le32 cdx_u32; +}; + +/* Value expanders for printk */ +#define CDX_DWORD_VAL(dword) \ + ((unsigned int)le32_to_cpu((dword).cdx_u32)) + +/* + * Extract bit field portion [low,high) from the 32-bit little-endian + * element which contains bits [min,max) + */ +#define CDX_DWORD_FIELD(dword, field) \ + (FIELD_GET(GENMASK(CDX_HIGH_BIT(field), CDX_LOW_BIT(field)), \ + le32_to_cpu((dword).cdx_u32))) + +/* + * Creates the portion of the named bit field that lies within the + * range [min,max). + */ +#define CDX_INSERT_FIELD(field, value) \ + (FIELD_PREP(GENMASK(CDX_HIGH_BIT(field), \ + CDX_LOW_BIT(field)), value)) + +/* + * Creates the portion of the named bit fields that lie within the + * range [min,max). + */ +#define CDX_INSERT_FIELDS(field1, value1, \ + field2, value2, \ + field3, value3, \ + field4, value4, \ + field5, value5, \ + field6, value6, \ + field7, value7) \ + (CDX_INSERT_FIELD(field1, (value1)) | \ + CDX_INSERT_FIELD(field2, (value2)) | \ + CDX_INSERT_FIELD(field3, (value3)) | \ + CDX_INSERT_FIELD(field4, (value4)) | \ + CDX_INSERT_FIELD(field5, (value5)) | \ + CDX_INSERT_FIELD(field6, (value6)) | \ + CDX_INSERT_FIELD(field7, (value7))) + +#define CDX_POPULATE_DWORD(dword, ...) \ + (dword).cdx_u32 = cpu_to_le32(CDX_INSERT_FIELDS(__VA_ARGS__)) + +/* Populate a dword field with various numbers of arguments */ +#define CDX_POPULATE_DWORD_7 CDX_POPULATE_DWORD +#define CDX_POPULATE_DWORD_6(dword, ...) \ + CDX_POPULATE_DWORD_7(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_5(dword, ...) \ + CDX_POPULATE_DWORD_6(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_4(dword, ...) \ + CDX_POPULATE_DWORD_5(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_3(dword, ...) \ + CDX_POPULATE_DWORD_4(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_2(dword, ...) \ + CDX_POPULATE_DWORD_3(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_POPULATE_DWORD_1(dword, ...) \ + CDX_POPULATE_DWORD_2(dword, CDX_DWORD, 0, __VA_ARGS__) +#define CDX_SET_DWORD(dword) \ + CDX_POPULATE_DWORD_1(dword, CDX_DWORD, 0xffffffff) + +#endif /* CDX_BITFIELD_H */ diff --git a/drivers/cdx/controller/mc_cdx_pcol.h b/drivers/cdx/controller/mc_cdx_pcol.h new file mode 100644 index 000000000000..4ccb7b52951b --- /dev/null +++ b/drivers/cdx/controller/mc_cdx_pcol.h @@ -0,0 +1,590 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Driver for AMD network controllers and boards + * + * Copyright (C) 2021, Xilinx, Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef MC_CDX_PCOL_H +#define MC_CDX_PCOL_H + +/* The current version of the MCDI protocol. */ +#define MCDI_PCOL_VERSION 2 + +/* + * Each MCDI request starts with an MCDI_HEADER, which is a 32bit + * structure, filled in by the client. + * + * 0 7 8 16 20 22 23 24 31 + * | CODE | R | LEN | SEQ | Rsvd | E | R | XFLAGS | + * | | | + * | | \--- Response + * | \------- Error + * \------------------------------ Resync (always set) + * + * The client writes its request into MC shared memory, and rings the + * doorbell. Each request is completed either by the MC writing + * back into shared memory, or by writing out an event. + * + * All MCDI commands support completion by shared memory response. Each + * request may also contain additional data (accounted for by HEADER.LEN), + * and some responses may also contain additional data (again, accounted + * for by HEADER.LEN). + * + * Some MCDI commands support completion by event, in which any associated + * response data is included in the event. + * + * The protocol requires one response to be delivered for every request; a + * request should not be sent unless the response for the previous request + * has been received (either by polling shared memory, or by receiving + * an event). + */ + +/** Request/Response structure */ +#define MCDI_HEADER_OFST 0 +#define MCDI_HEADER_CODE_LBN 0 +#define MCDI_HEADER_CODE_WIDTH 7 +#define MCDI_HEADER_RESYNC_LBN 7 +#define MCDI_HEADER_RESYNC_WIDTH 1 +#define MCDI_HEADER_DATALEN_LBN 8 +#define MCDI_HEADER_DATALEN_WIDTH 8 +#define MCDI_HEADER_SEQ_LBN 16 +#define MCDI_HEADER_SEQ_WIDTH 4 +#define MCDI_HEADER_RSVD_LBN 20 +#define MCDI_HEADER_RSVD_WIDTH 1 +#define MCDI_HEADER_NOT_EPOCH_LBN 21 +#define MCDI_HEADER_NOT_EPOCH_WIDTH 1 +#define MCDI_HEADER_ERROR_LBN 22 +#define MCDI_HEADER_ERROR_WIDTH 1 +#define MCDI_HEADER_RESPONSE_LBN 23 +#define MCDI_HEADER_RESPONSE_WIDTH 1 +#define MCDI_HEADER_XFLAGS_LBN 24 +#define MCDI_HEADER_XFLAGS_WIDTH 8 +/* Request response using event */ +#define MCDI_HEADER_XFLAGS_EVREQ 0x01 +/* Request (and signal) early doorbell return */ +#define MCDI_HEADER_XFLAGS_DBRET 0x02 + +/* Maximum number of payload bytes */ +#define MCDI_CTL_SDU_LEN_MAX_V2 0x400 + +#define MCDI_CTL_SDU_LEN_MAX MCDI_CTL_SDU_LEN_MAX_V2 + +/* + * The MC can generate events for two reasons: + * - To advance a shared memory request if XFLAGS_EVREQ was set + * - As a notification (link state, i2c event), controlled + * via MC_CMD_LOG_CTRL + * + * Both events share a common structure: + * + * 0 32 33 36 44 52 60 + * | Data | Cont | Level | Src | Code | Rsvd | + * | + * \ There is another event pending in this notification + * + * If Code==CMDDONE, then the fields are further interpreted as: + * + * - LEVEL==INFO Command succeeded + * - LEVEL==ERR Command failed + * + * 0 8 16 24 32 + * | Seq | Datalen | Errno | Rsvd | + * + * These fields are taken directly out of the standard MCDI header, i.e., + * LEVEL==ERR, Datalen == 0 => Reboot + * + * Events can be squirted out of the UART (using LOG_CTRL) without a + * MCDI header. An event can be distinguished from a MCDI response by + * examining the first byte which is 0xc0. This corresponds to the + * non-existent MCDI command MC_CMD_DEBUG_LOG. + * + * 0 7 8 + * | command | Resync | = 0xc0 + * + * Since the event is written in big-endian byte order, this works + * providing bits 56-63 of the event are 0xc0. + * + * 56 60 63 + * | Rsvd | Code | = 0xc0 + * + * Which means for convenience the event code is 0xc for all MC + * generated events. + */ + +/* + * the errno value may be followed by the (0-based) number of the + * first argument that could not be processed. + */ +#define MC_CMD_ERR_ARG_OFST 4 + +/* MC_CMD_ERR MCDI error codes. */ +/* Operation not permitted. */ +#define MC_CMD_ERR_EPERM 0x1 +/* Non-existent command target */ +#define MC_CMD_ERR_ENOENT 0x2 +/* assert() has killed the MC */ +#define MC_CMD_ERR_EINTR 0x4 +/* I/O failure */ +#define MC_CMD_ERR_EIO 0x5 +/* Already exists */ +#define MC_CMD_ERR_EEXIST 0x6 +/* Try again */ +#define MC_CMD_ERR_EAGAIN 0xb +/* Out of memory */ +#define MC_CMD_ERR_ENOMEM 0xc +/* Caller does not hold required locks */ +#define MC_CMD_ERR_EACCES 0xd +/* Resource is currently unavailable (e.g. lock contention) */ +#define MC_CMD_ERR_EBUSY 0x10 +/* No such device */ +#define MC_CMD_ERR_ENODEV 0x13 +/* Invalid argument to target */ +#define MC_CMD_ERR_EINVAL 0x16 +/* No space */ +#define MC_CMD_ERR_ENOSPC 0x1c +/* Read-only */ +#define MC_CMD_ERR_EROFS 0x1e +/* Broken pipe */ +#define MC_CMD_ERR_EPIPE 0x20 +/* Out of range */ +#define MC_CMD_ERR_ERANGE 0x22 +/* Non-recursive resource is already acquired */ +#define MC_CMD_ERR_EDEADLK 0x23 +/* Operation not implemented */ +#define MC_CMD_ERR_ENOSYS 0x26 +/* Operation timed out */ +#define MC_CMD_ERR_ETIME 0x3e +/* Link has been severed */ +#define MC_CMD_ERR_ENOLINK 0x43 +/* Protocol error */ +#define MC_CMD_ERR_EPROTO 0x47 +/* Bad message */ +#define MC_CMD_ERR_EBADMSG 0x4a +/* Operation not supported */ +#define MC_CMD_ERR_ENOTSUP 0x5f +/* Address not available */ +#define MC_CMD_ERR_EADDRNOTAVAIL 0x63 +/* Not connected */ +#define MC_CMD_ERR_ENOTCONN 0x6b +/* Operation already in progress */ +#define MC_CMD_ERR_EALREADY 0x72 +/* Stale handle. The handle references resource that no longer exists */ +#define MC_CMD_ERR_ESTALE 0x74 +/* Resource allocation failed. */ +#define MC_CMD_ERR_ALLOC_FAIL 0x1000 +/* V-adaptor not found. */ +#define MC_CMD_ERR_NO_VADAPTOR 0x1001 +/* EVB port not found. */ +#define MC_CMD_ERR_NO_EVB_PORT 0x1002 +/* V-switch not found. */ +#define MC_CMD_ERR_NO_VSWITCH 0x1003 +/* Too many VLAN tags. */ +#define MC_CMD_ERR_VLAN_LIMIT 0x1004 +/* Bad PCI function number. */ +#define MC_CMD_ERR_BAD_PCI_FUNC 0x1005 +/* Invalid VLAN mode. */ +#define MC_CMD_ERR_BAD_VLAN_MODE 0x1006 +/* Invalid v-switch type. */ +#define MC_CMD_ERR_BAD_VSWITCH_TYPE 0x1007 +/* Invalid v-port type. */ +#define MC_CMD_ERR_BAD_VPORT_TYPE 0x1008 +/* MAC address exists. */ +#define MC_CMD_ERR_MAC_EXIST 0x1009 +/* Slave core not present */ +#define MC_CMD_ERR_SLAVE_NOT_PRESENT 0x100a +/* The datapath is disabled. */ +#define MC_CMD_ERR_DATAPATH_DISABLED 0x100b +/* The requesting client is not a function */ +#define MC_CMD_ERR_CLIENT_NOT_FN 0x100c +/* + * The requested operation might require the command to be passed between + * MCs, and the transport doesn't support that. Should only ever been seen over + * the UART. + */ +#define MC_CMD_ERR_NO_PRIVILEGE 0x1013 +/* + * Workaround 26807 could not be turned on/off because some functions + * have already installed filters. See the comment at + * MC_CMD_WORKAROUND_BUG26807. May also returned for other operations such as + * sub-variant switching. + */ +#define MC_CMD_ERR_FILTERS_PRESENT 0x1014 +/* The clock whose frequency you've attempted to set doesn't exist */ +#define MC_CMD_ERR_NO_CLOCK 0x1015 +/* + * Returned by MC_CMD_TESTASSERT if the action that should have caused an + * assertion failed to do so. + */ +#define MC_CMD_ERR_UNREACHABLE 0x1016 +/* + * This command needs to be processed in the background but there were no + * resources to do so. Send it again after a command has completed. + */ +#define MC_CMD_ERR_QUEUE_FULL 0x1017 +/* + * The operation could not be completed because the PCIe link has gone + * away. This error code is never expected to be returned over the TLP + * transport. + */ +#define MC_CMD_ERR_NO_PCIE 0x1018 +/* + * The operation could not be completed because the datapath has gone + * away. This is distinct from MC_CMD_ERR_DATAPATH_DISABLED in that the + * datapath absence may be temporary + */ +#define MC_CMD_ERR_NO_DATAPATH 0x1019 +/* The operation could not complete because some VIs are allocated */ +#define MC_CMD_ERR_VIS_PRESENT 0x101a +/* + * The operation could not complete because some PIO buffers are + * allocated + */ +#define MC_CMD_ERR_PIOBUFS_PRESENT 0x101b + +/***********************************/ +/* + * MC_CMD_CDX_BUS_ENUM_BUSES + * CDX bus hosts devices (functions) that are implemented using the Composable + * DMA subsystem and directly mapped into the memory space of the FGPA PSX + * Application Processors (APUs). As such, they only apply to the PSX APU side, + * not the host (PCIe). Unlike PCIe, these devices have no native configuration + * space or enumeration mechanism, so this message set provides a minimal + * interface for discovery and management (bus reset, FLR, BME) of such + * devices. This command returns the number of CDX buses present in the system. + */ +#define MC_CMD_CDX_BUS_ENUM_BUSES 0x1 +#define MC_CMD_CDX_BUS_ENUM_BUSES_MSGSET 0x1 +#undef MC_CMD_0x1_PRIVILEGE_CTG + +#define MC_CMD_0x1_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_BUS_ENUM_BUSES_IN msgrequest */ +#define MC_CMD_CDX_BUS_ENUM_BUSES_IN_LEN 0 + +/* MC_CMD_CDX_BUS_ENUM_BUSES_OUT msgresponse */ +#define MC_CMD_CDX_BUS_ENUM_BUSES_OUT_LEN 4 +/* + * Number of CDX buses present in the system. Buses are numbered 0 to + * BUS_COUNT-1 + */ +#define MC_CMD_CDX_BUS_ENUM_BUSES_OUT_BUS_COUNT_OFST 0 +#define MC_CMD_CDX_BUS_ENUM_BUSES_OUT_BUS_COUNT_LEN 4 + +/***********************************/ +/* + * MC_CMD_CDX_BUS_ENUM_DEVICES + * Enumerate CDX bus devices on a given bus + */ +#define MC_CMD_CDX_BUS_ENUM_DEVICES 0x2 +#define MC_CMD_CDX_BUS_ENUM_DEVICES_MSGSET 0x2 +#undef MC_CMD_0x2_PRIVILEGE_CTG + +#define MC_CMD_0x2_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_BUS_ENUM_DEVICES_IN msgrequest */ +#define MC_CMD_CDX_BUS_ENUM_DEVICES_IN_LEN 4 +/* + * Bus number to enumerate, in range 0 to BUS_COUNT-1, as returned by + * MC_CMD_CDX_BUS_ENUM_BUSES_OUT + */ +#define MC_CMD_CDX_BUS_ENUM_DEVICES_IN_BUS_OFST 0 +#define MC_CMD_CDX_BUS_ENUM_DEVICES_IN_BUS_LEN 4 + +/* MC_CMD_CDX_BUS_ENUM_DEVICES_OUT msgresponse */ +#define MC_CMD_CDX_BUS_ENUM_DEVICES_OUT_LEN 4 +/* + * Number of devices present on the bus. Devices on the bus are numbered 0 to + * DEVICE_COUNT-1. Returns EAGAIN if number of devices unknown or if the target + * devices are not ready (e.g. undergoing a bus reset) + */ +#define MC_CMD_CDX_BUS_ENUM_DEVICES_OUT_DEVICE_COUNT_OFST 0 +#define MC_CMD_CDX_BUS_ENUM_DEVICES_OUT_DEVICE_COUNT_LEN 4 + +/***********************************/ +/* + * MC_CMD_CDX_BUS_GET_DEVICE_CONFIG + * Returns device identification and MMIO/MSI resource data for a CDX device. + * The expected usage is for the caller to first retrieve the number of devices + * on the bus using MC_CMD_BUS_ENUM_DEVICES, then loop through the range (0, + * DEVICE_COUNT - 1), retrieving device resource data. May return EAGAIN if the + * number of exposed devices or device resources change during enumeration (due + * to e.g. a PL reload / bus reset), in which case the caller is expected to + * restart the enumeration loop. MMIO addresses are specified in terms of bus + * addresses (prior to any potential IOMMU translation). For versal-net, these + * are equivalent to APU physical addresses. Implementation note - for this to + * work, the implementation needs to keep state (generation count) per client. + */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG 0x3 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_MSGSET 0x3 +#undef MC_CMD_0x3_PRIVILEGE_CTG + +#define MC_CMD_0x3_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN msgrequest */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_LEN 8 +/* Device bus number, in range 0 to BUS_COUNT-1 */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_BUS_OFST 0 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_BUS_LEN 4 +/* Device number relative to the bus, in range 0 to DEVICE_COUNT-1 for that bus */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_DEVICE_OFST 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_DEVICE_LEN 4 + +/* MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT msgresponse */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_LEN 88 +/* 16-bit Vendor identifier, compliant with PCI-SIG VendorID assignment. */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_VENDOR_ID_OFST 0 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_VENDOR_ID_LEN 2 +/* 16-bit Device ID assigned by the vendor */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_ID_OFST 2 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_ID_LEN 2 +/* + * 16-bit Subsystem Vendor ID, , compliant with PCI-SIG VendorID assignment. + * For further device differentiation, as required. 0 if unused. + */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_SUBSYS_VENDOR_ID_OFST 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_SUBSYS_VENDOR_ID_LEN 2 +/* + * 16-bit Subsystem Device ID assigned by the vendor. For further device + * differentiation, as required. 0 if unused. + */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_SUBSYS_DEVICE_ID_OFST 6 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_SUBSYS_DEVICE_ID_LEN 2 +/* 24-bit Device Class code, compliant with PCI-SIG Device Class codes */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_CLASS_OFST 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_CLASS_LEN 3 +/* 8-bit vendor-assigned revision */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_REVISION_OFST 11 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_REVISION_LEN 1 +/* Reserved (alignment) */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_RESERVED_OFST 12 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_RESERVED_LEN 4 +/* MMIO region 0 base address (bus address), 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_OFST 16 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_LO_OFST 16 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_LO_LBN 128 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_HI_OFST 20 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_HI_LBN 160 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE_HI_WIDTH 32 +/* MMIO region 0 size, 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_OFST 24 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_LO_OFST 24 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_LO_LBN 192 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_HI_OFST 28 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_HI_LBN 224 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE_HI_WIDTH 32 +/* MMIO region 1 base address (bus address), 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_OFST 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_LO_OFST 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_LO_LBN 256 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_HI_OFST 36 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_HI_LBN 288 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE_HI_WIDTH 32 +/* MMIO region 1 size, 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_OFST 40 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_LO_OFST 40 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_LO_LBN 320 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_HI_OFST 44 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_HI_LBN 352 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE_HI_WIDTH 32 +/* MMIO region 2 base address (bus address), 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_OFST 48 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_LO_OFST 48 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_LO_LBN 384 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_HI_OFST 52 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_HI_LBN 416 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE_HI_WIDTH 32 +/* MMIO region 2 size, 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_OFST 56 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_LO_OFST 56 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_LO_LBN 448 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_HI_OFST 60 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_HI_LBN 480 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE_HI_WIDTH 32 +/* MMIO region 3 base address (bus address), 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_OFST 64 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_LO_OFST 64 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_LO_LBN 512 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_HI_OFST 68 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_HI_LBN 544 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE_HI_WIDTH 32 +/* MMIO region 3 size, 0 if unused */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_OFST 72 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_LEN 8 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_LO_OFST 72 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_LO_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_LO_LBN 576 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_LO_WIDTH 32 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_HI_OFST 76 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_HI_LEN 4 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_HI_LBN 608 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE_HI_WIDTH 32 +/* MSI vector count */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MSI_COUNT_OFST 80 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_MSI_COUNT_LEN 4 +/* Requester ID used by device (SMMU StreamID, GIC ITS DeviceID) */ +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_REQUESTER_ID_OFST 84 +#define MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_REQUESTER_ID_LEN 4 + +/***********************************/ +/* + * MC_CMD_CDX_DEVICE_RESET + * After this call completes, device DMA and interrupts are quiesced, devices + * logic is reset in a hardware-specific way and DMA bus mastering is disabled. + */ +#define MC_CMD_CDX_DEVICE_RESET 0x6 +#define MC_CMD_CDX_DEVICE_RESET_MSGSET 0x6 +#undef MC_CMD_0x6_PRIVILEGE_CTG + +#define MC_CMD_0x6_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_DEVICE_RESET_IN msgrequest */ +#define MC_CMD_CDX_DEVICE_RESET_IN_LEN 8 +/* Device bus number, in range 0 to BUS_COUNT-1 */ +#define MC_CMD_CDX_DEVICE_RESET_IN_BUS_OFST 0 +#define MC_CMD_CDX_DEVICE_RESET_IN_BUS_LEN 4 +/* Device number relative to the bus, in range 0 to DEVICE_COUNT-1 for that bus */ +#define MC_CMD_CDX_DEVICE_RESET_IN_DEVICE_OFST 4 +#define MC_CMD_CDX_DEVICE_RESET_IN_DEVICE_LEN 4 + +/* + * MC_CMD_CDX_DEVICE_RESET_OUT msgresponse: The device is quiesced and all + * pending device initiated DMA has completed. + */ +#define MC_CMD_CDX_DEVICE_RESET_OUT_LEN 0 + +/***********************************/ +/* + * MC_CMD_CDX_DEVICE_CONTROL_SET + * If BUS_MASTER is set to disabled, device DMA and interrupts are quiesced. + * Pending DMA requests and MSI interrupts are flushed and no further DMA or + * interrupts are issued after this command returns. If BUS_MASTER is set to + * enabled, device is allowed to initiate DMA. Whether interrupts are enabled + * also depends on the value of MSI_ENABLE bit. Note that, in this case, the + * device may start DMA before the host receives and processes the MCDI + * response. MSI_ENABLE masks or unmasks device interrupts only. Note that for + * interrupts to be delivered to the host, both BUS_MASTER and MSI_ENABLE needs + * to be set. MMIO_REGIONS_ENABLE enables or disables host accesses to device + * MMIO regions. Note that an implementation is allowed to permanently set this + * bit to 1, in which case MC_CMD_CDX_DEVICE_CONTROL_GET will always return 1 + * for this bit, regardless of the value set here. + */ +#define MC_CMD_CDX_DEVICE_CONTROL_SET 0x7 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_MSGSET 0x7 +#undef MC_CMD_0x7_PRIVILEGE_CTG + +#define MC_CMD_0x7_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_DEVICE_CONTROL_SET_IN msgrequest */ +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_LEN 12 +/* Device bus number, in range 0 to BUS_COUNT-1 */ +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_BUS_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_BUS_LEN 4 +/* Device number relative to the bus, in range 0 to DEVICE_COUNT-1 for that bus */ +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_DEVICE_OFST 4 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_DEVICE_LEN 4 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_FLAGS_OFST 8 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_FLAGS_LEN 4 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_BUS_MASTER_ENABLE_OFST 8 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_BUS_MASTER_ENABLE_LBN 0 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_BUS_MASTER_ENABLE_WIDTH 1 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MSI_ENABLE_OFST 8 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MSI_ENABLE_LBN 1 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MSI_ENABLE_WIDTH 1 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MMIO_REGIONS_ENABLE_OFST 8 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MMIO_REGIONS_ENABLE_LBN 2 +#define MC_CMD_CDX_DEVICE_CONTROL_SET_IN_MMIO_REGIONS_ENABLE_WIDTH 1 + +/* MC_CMD_CDX_DEVICE_CONTROL_SET_OUT msgresponse */ +#define MC_CMD_CDX_DEVICE_CONTROL_SET_OUT_LEN 0 + +/***********************************/ +/* + * MC_CMD_CDX_DEVICE_CONTROL_GET + * Returns device DMA, interrupt and MMIO region access control bits. See + * MC_CMD_CDX_DEVICE_CONTROL_SET for definition of the available control bits. + */ +#define MC_CMD_CDX_DEVICE_CONTROL_GET 0x8 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_MSGSET 0x8 +#undef MC_CMD_0x8_PRIVILEGE_CTG + +#define MC_CMD_0x8_PRIVILEGE_CTG SRIOV_CTG_ADMIN + +/* MC_CMD_CDX_DEVICE_CONTROL_GET_IN msgrequest */ +#define MC_CMD_CDX_DEVICE_CONTROL_GET_IN_LEN 8 +/* Device bus number, in range 0 to BUS_COUNT-1 */ +#define MC_CMD_CDX_DEVICE_CONTROL_GET_IN_BUS_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_IN_BUS_LEN 4 +/* Device number relative to the bus, in range 0 to DEVICE_COUNT-1 for that bus */ +#define MC_CMD_CDX_DEVICE_CONTROL_GET_IN_DEVICE_OFST 4 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_IN_DEVICE_LEN 4 + +/* MC_CMD_CDX_DEVICE_CONTROL_GET_OUT msgresponse */ +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_LEN 4 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_FLAGS_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_FLAGS_LEN 4 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_BUS_MASTER_ENABLE_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_BUS_MASTER_ENABLE_LBN 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_BUS_MASTER_ENABLE_WIDTH 1 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MSI_ENABLE_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MSI_ENABLE_LBN 1 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MSI_ENABLE_WIDTH 1 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MMIO_REGIONS_ENABLE_OFST 0 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MMIO_REGIONS_ENABLE_LBN 2 +#define MC_CMD_CDX_DEVICE_CONTROL_GET_OUT_MMIO_REGIONS_ENABLE_WIDTH 1 + +/***********************************/ +/* MC_CMD_V2_EXTN - Encapsulation for a v2 extended command */ +#define MC_CMD_V2_EXTN 0x7f + +/* MC_CMD_V2_EXTN_IN msgrequest */ +#define MC_CMD_V2_EXTN_IN_LEN 4 +/* the extended command number */ +#define MC_CMD_V2_EXTN_IN_EXTENDED_CMD_LBN 0 +#define MC_CMD_V2_EXTN_IN_EXTENDED_CMD_WIDTH 15 +#define MC_CMD_V2_EXTN_IN_UNUSED_LBN 15 +#define MC_CMD_V2_EXTN_IN_UNUSED_WIDTH 1 +/* the actual length of the encapsulated command */ +#define MC_CMD_V2_EXTN_IN_ACTUAL_LEN_LBN 16 +#define MC_CMD_V2_EXTN_IN_ACTUAL_LEN_WIDTH 10 +#define MC_CMD_V2_EXTN_IN_UNUSED2_LBN 26 +#define MC_CMD_V2_EXTN_IN_UNUSED2_WIDTH 2 +/* Type of command/response */ +#define MC_CMD_V2_EXTN_IN_MESSAGE_TYPE_LBN 28 +#define MC_CMD_V2_EXTN_IN_MESSAGE_TYPE_WIDTH 4 +/* + * enum: MCDI command directed to versal-net. MCDI responses of this type + * are not defined. + */ +#define MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_PLATFORM 0x2 + +#endif /* MC_CDX_PCOL_H */ diff --git a/drivers/cdx/controller/mcdi.c b/drivers/cdx/controller/mcdi.c new file mode 100644 index 000000000000..a211a2ca762e --- /dev/null +++ b/drivers/cdx/controller/mcdi.c @@ -0,0 +1,903 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Management-Controller-to-Driver Interface + * + * Copyright 2008-2013 Solarflare Communications Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bitfield.h" +#include "mcdi.h" + +struct cdx_mcdi_copy_buffer { + struct cdx_dword buffer[DIV_ROUND_UP(MCDI_CTL_SDU_LEN_MAX, 4)]; +}; + +#ifdef CONFIG_MCDI_LOGGING +#define LOG_LINE_MAX (1024 - 32) +#endif + +static void cdx_mcdi_cancel_cmd(struct cdx_mcdi *cdx, struct cdx_mcdi_cmd *cmd); +static void cdx_mcdi_wait_for_cleanup(struct cdx_mcdi *cdx); +static int cdx_mcdi_rpc_async_internal(struct cdx_mcdi *cdx, + struct cdx_mcdi_cmd *cmd, + unsigned int *handle); +static void cdx_mcdi_start_or_queue(struct cdx_mcdi_iface *mcdi, + bool allow_retry); +static void cdx_mcdi_cmd_start_or_queue(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd); +static bool cdx_mcdi_complete_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct cdx_dword *outbuf, + int len, + struct list_head *cleanup_list); +static void cdx_mcdi_timeout_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct list_head *cleanup_list); +static void cdx_mcdi_cmd_work(struct work_struct *context); +static void cdx_mcdi_mode_fail(struct cdx_mcdi *cdx, struct list_head *cleanup_list); +static void _cdx_mcdi_display_error(struct cdx_mcdi *cdx, unsigned int cmd, + size_t inlen, int raw, int arg, int err_no); + +static bool cdx_cmd_cancelled(struct cdx_mcdi_cmd *cmd) +{ + return cmd->state == MCDI_STATE_RUNNING_CANCELLED; +} + +static void cdx_mcdi_cmd_release(struct kref *ref) +{ + kfree(container_of(ref, struct cdx_mcdi_cmd, ref)); +} + +static unsigned int cdx_mcdi_cmd_handle(struct cdx_mcdi_cmd *cmd) +{ + return cmd->handle; +} + +static void _cdx_mcdi_remove_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct list_head *cleanup_list) +{ + /* if cancelled, the completers have already been called */ + if (cdx_cmd_cancelled(cmd)) + return; + + if (cmd->completer) { + list_add_tail(&cmd->cleanup_list, cleanup_list); + ++mcdi->outstanding_cleanups; + kref_get(&cmd->ref); + } +} + +static void cdx_mcdi_remove_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct list_head *cleanup_list) +{ + list_del(&cmd->list); + _cdx_mcdi_remove_cmd(mcdi, cmd, cleanup_list); + cmd->state = MCDI_STATE_FINISHED; + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + if (list_empty(&mcdi->cmd_list)) + wake_up(&mcdi->cmd_complete_wq); +} + +static unsigned long cdx_mcdi_rpc_timeout(struct cdx_mcdi *cdx, unsigned int cmd) +{ + if (!cdx->mcdi_ops->mcdi_rpc_timeout) + return MCDI_RPC_TIMEOUT; + else + return cdx->mcdi_ops->mcdi_rpc_timeout(cdx, cmd); +} + +int cdx_mcdi_init(struct cdx_mcdi *cdx) +{ + struct cdx_mcdi_iface *mcdi; + int rc = -ENOMEM; + + cdx->mcdi = kzalloc(sizeof(*cdx->mcdi), GFP_KERNEL); + if (!cdx->mcdi) + goto fail; + + mcdi = cdx_mcdi_if(cdx); + mcdi->cdx = cdx; + +#ifdef CONFIG_MCDI_LOGGING + mcdi->logging_buffer = kmalloc(LOG_LINE_MAX, GFP_KERNEL); + if (!mcdi->logging_buffer) + goto fail2; +#endif + mcdi->workqueue = alloc_ordered_workqueue("mcdi_wq", 0); + if (!mcdi->workqueue) + goto fail3; + mutex_init(&mcdi->iface_lock); + mcdi->mode = MCDI_MODE_EVENTS; + INIT_LIST_HEAD(&mcdi->cmd_list); + init_waitqueue_head(&mcdi->cmd_complete_wq); + + mcdi->new_epoch = true; + + return 0; +fail3: +#ifdef CONFIG_MCDI_LOGGING + kfree(mcdi->logging_buffer); +fail2: +#endif + kfree(cdx->mcdi); + cdx->mcdi = NULL; +fail: + return rc; +} + +void cdx_mcdi_finish(struct cdx_mcdi *cdx) +{ + struct cdx_mcdi_iface *mcdi; + + mcdi = cdx_mcdi_if(cdx); + if (!mcdi) + return; + + cdx_mcdi_wait_for_cleanup(cdx); + +#ifdef CONFIG_MCDI_LOGGING + kfree(mcdi->logging_buffer); +#endif + + destroy_workqueue(mcdi->workqueue); + kfree(cdx->mcdi); + cdx->mcdi = NULL; +} + +static bool cdx_mcdi_flushed(struct cdx_mcdi_iface *mcdi, bool ignore_cleanups) +{ + bool flushed; + + mutex_lock(&mcdi->iface_lock); + flushed = list_empty(&mcdi->cmd_list) && + (ignore_cleanups || !mcdi->outstanding_cleanups); + mutex_unlock(&mcdi->iface_lock); + return flushed; +} + +/* Wait for outstanding MCDI commands to complete. */ +static void cdx_mcdi_wait_for_cleanup(struct cdx_mcdi *cdx) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + + if (!mcdi) + return; + + wait_event(mcdi->cmd_complete_wq, + cdx_mcdi_flushed(mcdi, false)); +} + +int cdx_mcdi_wait_for_quiescence(struct cdx_mcdi *cdx, + unsigned int timeout_jiffies) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int rc = 0; + + if (!mcdi) + return -EINVAL; + + flush_workqueue(mcdi->workqueue); + + add_wait_queue(&mcdi->cmd_complete_wq, &wait); + + while (!cdx_mcdi_flushed(mcdi, true)) { + rc = wait_woken(&wait, TASK_IDLE, timeout_jiffies); + if (rc) + continue; + break; + } + + remove_wait_queue(&mcdi->cmd_complete_wq, &wait); + + if (rc > 0) + rc = 0; + else if (rc == 0) + rc = -ETIMEDOUT; + + return rc; +} + +static u8 cdx_mcdi_payload_csum(const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len) +{ + u8 *p = (u8 *)hdr; + u8 csum = 0; + int i; + + for (i = 0; i < hdr_len; i++) + csum += p[i]; + + p = (u8 *)sdu; + for (i = 0; i < sdu_len; i++) + csum += p[i]; + + return ~csum & 0xff; +} + +static void cdx_mcdi_send_request(struct cdx_mcdi *cdx, + struct cdx_mcdi_cmd *cmd) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + const struct cdx_dword *inbuf = cmd->inbuf; + size_t inlen = cmd->inlen; + struct cdx_dword hdr[2]; + size_t hdr_len; + bool not_epoch; + u32 xflags; +#ifdef CONFIG_MCDI_LOGGING + char *buf; +#endif + + if (!mcdi) + return; +#ifdef CONFIG_MCDI_LOGGING + buf = mcdi->logging_buffer; /* page-sized */ +#endif + + mcdi->prev_seq = cmd->seq; + mcdi->seq_held_by[cmd->seq] = cmd; + mcdi->db_held_by = cmd; + cmd->started = jiffies; + + not_epoch = !mcdi->new_epoch; + xflags = 0; + + /* MCDI v2 */ + WARN_ON(inlen > MCDI_CTL_SDU_LEN_MAX_V2); + CDX_POPULATE_DWORD_7(hdr[0], + MCDI_HEADER_RESPONSE, 0, + MCDI_HEADER_RESYNC, 1, + MCDI_HEADER_CODE, MC_CMD_V2_EXTN, + MCDI_HEADER_DATALEN, 0, + MCDI_HEADER_SEQ, cmd->seq, + MCDI_HEADER_XFLAGS, xflags, + MCDI_HEADER_NOT_EPOCH, not_epoch); + CDX_POPULATE_DWORD_3(hdr[1], + MC_CMD_V2_EXTN_IN_EXTENDED_CMD, cmd->cmd, + MC_CMD_V2_EXTN_IN_ACTUAL_LEN, inlen, + MC_CMD_V2_EXTN_IN_MESSAGE_TYPE, + MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_PLATFORM); + hdr_len = 8; + +#ifdef CONFIG_MCDI_LOGGING + if (!WARN_ON_ONCE(!buf)) { + const struct cdx_dword *frags[] = { hdr, inbuf }; + const size_t frag_len[] = { hdr_len, round_up(inlen, 4) }; + int bytes = 0; + int i, j; + + for (j = 0; j < ARRAY_SIZE(frags); j++) { + const struct cdx_dword *frag; + + frag = frags[j]; + for (i = 0; + i < frag_len[j] / 4; + i++) { + /* + * Do not exceed the internal printk limit. + * The string before that is just over 70 bytes. + */ + if ((bytes + 75) > LOG_LINE_MAX) { + pr_info("MCDI RPC REQ:%s \\\n", buf); + bytes = 0; + } + bytes += snprintf(buf + bytes, + LOG_LINE_MAX - bytes, " %08x", + le32_to_cpu(frag[i].cdx_u32)); + } + } + + pr_info("MCDI RPC REQ:%s\n", buf); + } +#endif + hdr[0].cdx_u32 |= (__force __le32)(cdx_mcdi_payload_csum(hdr, hdr_len, inbuf, inlen) << + MCDI_HEADER_XFLAGS_LBN); + cdx->mcdi_ops->mcdi_request(cdx, hdr, hdr_len, inbuf, inlen); + + mcdi->new_epoch = false; +} + +static int cdx_mcdi_errno(struct cdx_mcdi *cdx, unsigned int mcdi_err) +{ + switch (mcdi_err) { + case 0: + case MC_CMD_ERR_QUEUE_FULL: + return mcdi_err; + case MC_CMD_ERR_EPERM: + return -EPERM; + case MC_CMD_ERR_ENOENT: + return -ENOENT; + case MC_CMD_ERR_EINTR: + return -EINTR; + case MC_CMD_ERR_EAGAIN: + return -EAGAIN; + case MC_CMD_ERR_EACCES: + return -EACCES; + case MC_CMD_ERR_EBUSY: + return -EBUSY; + case MC_CMD_ERR_EINVAL: + return -EINVAL; + case MC_CMD_ERR_ERANGE: + return -ERANGE; + case MC_CMD_ERR_EDEADLK: + return -EDEADLK; + case MC_CMD_ERR_ENOSYS: + return -EOPNOTSUPP; + case MC_CMD_ERR_ETIME: + return -ETIME; + case MC_CMD_ERR_EALREADY: + return -EALREADY; + case MC_CMD_ERR_ENOSPC: + return -ENOSPC; + case MC_CMD_ERR_ENOMEM: + return -ENOMEM; + case MC_CMD_ERR_ENOTSUP: + return -EOPNOTSUPP; + case MC_CMD_ERR_ALLOC_FAIL: + return -ENOBUFS; + case MC_CMD_ERR_MAC_EXIST: + return -EADDRINUSE; + case MC_CMD_ERR_NO_EVB_PORT: + return -EAGAIN; + default: + return -EPROTO; + } +} + +static void cdx_mcdi_process_cleanup_list(struct cdx_mcdi *cdx, + struct list_head *cleanup_list) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + unsigned int cleanups = 0; + + if (!mcdi) + return; + + while (!list_empty(cleanup_list)) { + struct cdx_mcdi_cmd *cmd = + list_first_entry(cleanup_list, + struct cdx_mcdi_cmd, cleanup_list); + cmd->completer(cdx, cmd->cookie, cmd->rc, + cmd->outbuf, cmd->outlen); + list_del(&cmd->cleanup_list); + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + ++cleanups; + } + + if (cleanups) { + bool all_done; + + mutex_lock(&mcdi->iface_lock); + CDX_WARN_ON_PARANOID(cleanups > mcdi->outstanding_cleanups); + all_done = (mcdi->outstanding_cleanups -= cleanups) == 0; + mutex_unlock(&mcdi->iface_lock); + if (all_done) + wake_up(&mcdi->cmd_complete_wq); + } +} + +static void _cdx_mcdi_cancel_cmd(struct cdx_mcdi_iface *mcdi, + unsigned int handle, + struct list_head *cleanup_list) +{ + struct cdx_mcdi_cmd *cmd; + + list_for_each_entry(cmd, &mcdi->cmd_list, list) + if (cdx_mcdi_cmd_handle(cmd) == handle) { + switch (cmd->state) { + case MCDI_STATE_QUEUED: + case MCDI_STATE_RETRY: + pr_debug("command %#x inlen %zu cancelled in queue\n", + cmd->cmd, cmd->inlen); + /* if not yet running, properly cancel it */ + cmd->rc = -EPIPE; + cdx_mcdi_remove_cmd(mcdi, cmd, cleanup_list); + break; + case MCDI_STATE_RUNNING: + case MCDI_STATE_RUNNING_CANCELLED: + case MCDI_STATE_FINISHED: + default: + /* invalid state? */ + WARN_ON(1); + } + break; + } +} + +static void cdx_mcdi_cancel_cmd(struct cdx_mcdi *cdx, struct cdx_mcdi_cmd *cmd) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + LIST_HEAD(cleanup_list); + + if (!mcdi) + return; + + mutex_lock(&mcdi->iface_lock); + cdx_mcdi_timeout_cmd(mcdi, cmd, &cleanup_list); + mutex_unlock(&mcdi->iface_lock); + cdx_mcdi_process_cleanup_list(cdx, &cleanup_list); +} + +struct cdx_mcdi_blocking_data { + struct kref ref; + bool done; + wait_queue_head_t wq; + int rc; + struct cdx_dword *outbuf; + size_t outlen; + size_t outlen_actual; +}; + +static void cdx_mcdi_blocking_data_release(struct kref *ref) +{ + kfree(container_of(ref, struct cdx_mcdi_blocking_data, ref)); +} + +static void cdx_mcdi_rpc_completer(struct cdx_mcdi *cdx, unsigned long cookie, + int rc, struct cdx_dword *outbuf, + size_t outlen_actual) +{ + struct cdx_mcdi_blocking_data *wait_data = + (struct cdx_mcdi_blocking_data *)cookie; + + wait_data->rc = rc; + memcpy(wait_data->outbuf, outbuf, + min(outlen_actual, wait_data->outlen)); + wait_data->outlen_actual = outlen_actual; + /* memory barrier */ + smp_wmb(); + wait_data->done = true; + wake_up(&wait_data->wq); + kref_put(&wait_data->ref, cdx_mcdi_blocking_data_release); +} + +static int cdx_mcdi_rpc_sync(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + struct cdx_dword *outbuf, size_t outlen, + size_t *outlen_actual, bool quiet) +{ + struct cdx_mcdi_blocking_data *wait_data; + struct cdx_mcdi_cmd *cmd_item; + unsigned int handle; + int rc; + + if (outlen_actual) + *outlen_actual = 0; + + wait_data = kmalloc(sizeof(*wait_data), GFP_KERNEL); + if (!wait_data) + return -ENOMEM; + + cmd_item = kmalloc(sizeof(*cmd_item), GFP_KERNEL); + if (!cmd_item) { + kfree(wait_data); + return -ENOMEM; + } + + kref_init(&wait_data->ref); + wait_data->done = false; + init_waitqueue_head(&wait_data->wq); + wait_data->outbuf = outbuf; + wait_data->outlen = outlen; + + kref_init(&cmd_item->ref); + cmd_item->quiet = quiet; + cmd_item->cookie = (unsigned long)wait_data; + cmd_item->completer = &cdx_mcdi_rpc_completer; + cmd_item->cmd = cmd; + cmd_item->inlen = inlen; + cmd_item->inbuf = inbuf; + + /* Claim an extra reference for the completer to put. */ + kref_get(&wait_data->ref); + rc = cdx_mcdi_rpc_async_internal(cdx, cmd_item, &handle); + if (rc) { + kref_put(&wait_data->ref, cdx_mcdi_blocking_data_release); + goto out; + } + + if (!wait_event_timeout(wait_data->wq, wait_data->done, + cdx_mcdi_rpc_timeout(cdx, cmd)) && + !wait_data->done) { + pr_err("MC command 0x%x inlen %zu timed out (sync)\n", + cmd, inlen); + + cdx_mcdi_cancel_cmd(cdx, cmd_item); + + wait_data->rc = -ETIMEDOUT; + wait_data->outlen_actual = 0; + } + + if (outlen_actual) + *outlen_actual = wait_data->outlen_actual; + rc = wait_data->rc; + +out: + kref_put(&wait_data->ref, cdx_mcdi_blocking_data_release); + + return rc; +} + +static bool cdx_mcdi_get_seq(struct cdx_mcdi_iface *mcdi, unsigned char *seq) +{ + *seq = mcdi->prev_seq; + do { + *seq = (*seq + 1) % ARRAY_SIZE(mcdi->seq_held_by); + } while (mcdi->seq_held_by[*seq] && *seq != mcdi->prev_seq); + return !mcdi->seq_held_by[*seq]; +} + +static int cdx_mcdi_rpc_async_internal(struct cdx_mcdi *cdx, + struct cdx_mcdi_cmd *cmd, + unsigned int *handle) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + LIST_HEAD(cleanup_list); + + if (!mcdi) { + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + return -ENETDOWN; + } + + if (mcdi->mode == MCDI_MODE_FAIL) { + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + return -ENETDOWN; + } + + cmd->mcdi = mcdi; + INIT_WORK(&cmd->work, cdx_mcdi_cmd_work); + INIT_LIST_HEAD(&cmd->list); + INIT_LIST_HEAD(&cmd->cleanup_list); + cmd->rc = 0; + cmd->outbuf = NULL; + cmd->outlen = 0; + + queue_work(mcdi->workqueue, &cmd->work); + return 0; +} + +static void cdx_mcdi_cmd_start_or_queue(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd) +{ + struct cdx_mcdi *cdx = mcdi->cdx; + u8 seq; + + if (!mcdi->db_held_by && + cdx_mcdi_get_seq(mcdi, &seq)) { + cmd->seq = seq; + cmd->reboot_seen = false; + cdx_mcdi_send_request(cdx, cmd); + cmd->state = MCDI_STATE_RUNNING; + } else { + cmd->state = MCDI_STATE_QUEUED; + } +} + +/* try to advance other commands */ +static void cdx_mcdi_start_or_queue(struct cdx_mcdi_iface *mcdi, + bool allow_retry) +{ + struct cdx_mcdi_cmd *cmd, *tmp; + + list_for_each_entry_safe(cmd, tmp, &mcdi->cmd_list, list) + if (cmd->state == MCDI_STATE_QUEUED || + (cmd->state == MCDI_STATE_RETRY && allow_retry)) + cdx_mcdi_cmd_start_or_queue(mcdi, cmd); +} + +void cdx_mcdi_process_cmd(struct cdx_mcdi *cdx, struct cdx_dword *outbuf, int len) +{ + struct cdx_mcdi_iface *mcdi; + struct cdx_mcdi_cmd *cmd; + LIST_HEAD(cleanup_list); + unsigned int respseq; + + if (!len || !outbuf) { + pr_err("Got empty MC response\n"); + return; + } + + mcdi = cdx_mcdi_if(cdx); + if (!mcdi) + return; + + respseq = CDX_DWORD_FIELD(outbuf[0], MCDI_HEADER_SEQ); + + mutex_lock(&mcdi->iface_lock); + cmd = mcdi->seq_held_by[respseq]; + + if (cmd) { + if (cmd->state == MCDI_STATE_FINISHED) { + mutex_unlock(&mcdi->iface_lock); + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + return; + } + + cdx_mcdi_complete_cmd(mcdi, cmd, outbuf, len, &cleanup_list); + } else { + pr_err("MC response unexpected for seq : %0X\n", respseq); + } + + mutex_unlock(&mcdi->iface_lock); + + cdx_mcdi_process_cleanup_list(mcdi->cdx, &cleanup_list); +} + +static void cdx_mcdi_cmd_work(struct work_struct *context) +{ + struct cdx_mcdi_cmd *cmd = + container_of(context, struct cdx_mcdi_cmd, work); + struct cdx_mcdi_iface *mcdi = cmd->mcdi; + + mutex_lock(&mcdi->iface_lock); + + cmd->handle = mcdi->prev_handle++; + list_add_tail(&cmd->list, &mcdi->cmd_list); + cdx_mcdi_cmd_start_or_queue(mcdi, cmd); + + mutex_unlock(&mcdi->iface_lock); +} + +/* + * Returns true if the MCDI module is finished with the command. + * (examples of false would be if the command was proxied, or it was + * rejected by the MC due to lack of resources and requeued). + */ +static bool cdx_mcdi_complete_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct cdx_dword *outbuf, + int len, + struct list_head *cleanup_list) +{ + size_t resp_hdr_len, resp_data_len; + struct cdx_mcdi *cdx = mcdi->cdx; + unsigned int respcmd, error; + bool completed = false; + int rc; + + /* ensure the command can't go away before this function returns */ + kref_get(&cmd->ref); + + respcmd = CDX_DWORD_FIELD(outbuf[0], MCDI_HEADER_CODE); + error = CDX_DWORD_FIELD(outbuf[0], MCDI_HEADER_ERROR); + + if (respcmd != MC_CMD_V2_EXTN) { + resp_hdr_len = 4; + resp_data_len = CDX_DWORD_FIELD(outbuf[0], MCDI_HEADER_DATALEN); + } else { + resp_data_len = 0; + resp_hdr_len = 8; + if (len >= 8) + resp_data_len = + CDX_DWORD_FIELD(outbuf[1], MC_CMD_V2_EXTN_IN_ACTUAL_LEN); + } + + if ((resp_hdr_len + resp_data_len) > len) { + pr_warn("Incomplete MCDI response received %d. Expected %zu\n", + len, (resp_hdr_len + resp_data_len)); + resp_data_len = 0; + } + +#ifdef CONFIG_MCDI_LOGGING + if (!WARN_ON_ONCE(!mcdi->logging_buffer)) { + char *log = mcdi->logging_buffer; + int i, bytes = 0; + size_t rlen; + + WARN_ON_ONCE(resp_hdr_len % 4); + + rlen = resp_hdr_len / 4 + DIV_ROUND_UP(resp_data_len, 4); + + for (i = 0; i < rlen; i++) { + if ((bytes + 75) > LOG_LINE_MAX) { + pr_info("MCDI RPC RESP:%s \\\n", log); + bytes = 0; + } + bytes += snprintf(log + bytes, LOG_LINE_MAX - bytes, + " %08x", le32_to_cpu(outbuf[i].cdx_u32)); + } + + pr_info("MCDI RPC RESP:%s\n", log); + } +#endif + + if (error && resp_data_len == 0) { + /* MC rebooted during command */ + rc = -EIO; + } else { + if (WARN_ON_ONCE(error && resp_data_len < 4)) + resp_data_len = 4; + if (error) { + rc = CDX_DWORD_FIELD(outbuf[resp_hdr_len / 4], CDX_DWORD); + if (!cmd->quiet) { + int err_arg = 0; + + if (resp_data_len >= MC_CMD_ERR_ARG_OFST + 4) { + int offset = (resp_hdr_len + MC_CMD_ERR_ARG_OFST) / 4; + + err_arg = CDX_DWORD_VAL(outbuf[offset]); + } + + _cdx_mcdi_display_error(cdx, cmd->cmd, + cmd->inlen, rc, err_arg, + cdx_mcdi_errno(cdx, rc)); + } + rc = cdx_mcdi_errno(cdx, rc); + } else { + rc = 0; + } + } + + /* free doorbell */ + if (mcdi->db_held_by == cmd) + mcdi->db_held_by = NULL; + + if (cdx_cmd_cancelled(cmd)) { + list_del(&cmd->list); + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + completed = true; + } else if (rc == MC_CMD_ERR_QUEUE_FULL) { + cmd->state = MCDI_STATE_RETRY; + } else { + cmd->rc = rc; + cmd->outbuf = outbuf + DIV_ROUND_UP(resp_hdr_len, 4); + cmd->outlen = resp_data_len; + cdx_mcdi_remove_cmd(mcdi, cmd, cleanup_list); + completed = true; + } + + /* free sequence number and buffer */ + mcdi->seq_held_by[cmd->seq] = NULL; + + cdx_mcdi_start_or_queue(mcdi, rc != MC_CMD_ERR_QUEUE_FULL); + + /* wake up anyone waiting for flush */ + wake_up(&mcdi->cmd_complete_wq); + + kref_put(&cmd->ref, cdx_mcdi_cmd_release); + + return completed; +} + +static void cdx_mcdi_timeout_cmd(struct cdx_mcdi_iface *mcdi, + struct cdx_mcdi_cmd *cmd, + struct list_head *cleanup_list) +{ + struct cdx_mcdi *cdx = mcdi->cdx; + + pr_err("MC command 0x%x inlen %zu state %d timed out after %u ms\n", + cmd->cmd, cmd->inlen, cmd->state, + jiffies_to_msecs(jiffies - cmd->started)); + + cmd->rc = -ETIMEDOUT; + cdx_mcdi_remove_cmd(mcdi, cmd, cleanup_list); + + cdx_mcdi_mode_fail(cdx, cleanup_list); +} + +/** + * cdx_mcdi_rpc - Issue an MCDI command and wait for completion + * @cdx: NIC through which to issue the command + * @cmd: Command type number + * @inbuf: Command parameters + * @inlen: Length of command parameters, in bytes. Must be a multiple + * of 4 and no greater than %MCDI_CTL_SDU_LEN_MAX_V1. + * @outbuf: Response buffer. May be %NULL if @outlen is 0. + * @outlen: Length of response buffer, in bytes. If the actual + * response is longer than @outlen & ~3, it will be truncated + * to that length. + * @outlen_actual: Pointer through which to return the actual response + * length. May be %NULL if this is not needed. + * + * This function may sleep and therefore must be called in process + * context. + * + * Return: A negative error code, or zero if successful. The error + * code may come from the MCDI response or may indicate a failure + * to communicate with the MC. In the former case, the response + * will still be copied to @outbuf and *@outlen_actual will be + * set accordingly. In the latter case, *@outlen_actual will be + * set to zero. + */ +int cdx_mcdi_rpc(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + struct cdx_dword *outbuf, size_t outlen, + size_t *outlen_actual) +{ + return cdx_mcdi_rpc_sync(cdx, cmd, inbuf, inlen, outbuf, outlen, + outlen_actual, false); +} + +/** + * cdx_mcdi_rpc_async - Schedule an MCDI command to run asynchronously + * @cdx: NIC through which to issue the command + * @cmd: Command type number + * @inbuf: Command parameters + * @inlen: Length of command parameters, in bytes + * @complete: Function to be called on completion or cancellation. + * @cookie: Arbitrary value to be passed to @complete. + * + * This function does not sleep and therefore may be called in atomic + * context. It will fail if event queues are disabled or if MCDI + * event completions have been disabled due to an error. + * + * If it succeeds, the @complete function will be called exactly once + * in process context, when one of the following occurs: + * (a) the completion event is received (in process context) + * (b) event queues are disabled (in the process that disables them) + */ +int +cdx_mcdi_rpc_async(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + cdx_mcdi_async_completer *complete, unsigned long cookie) +{ + struct cdx_mcdi_cmd *cmd_item = + kmalloc(sizeof(struct cdx_mcdi_cmd) + inlen, GFP_ATOMIC); + + if (!cmd_item) + return -ENOMEM; + + kref_init(&cmd_item->ref); + cmd_item->quiet = true; + cmd_item->cookie = cookie; + cmd_item->completer = complete; + cmd_item->cmd = cmd; + cmd_item->inlen = inlen; + /* inbuf is probably not valid after return, so take a copy */ + cmd_item->inbuf = (struct cdx_dword *)(cmd_item + 1); + memcpy(cmd_item + 1, inbuf, inlen); + + return cdx_mcdi_rpc_async_internal(cdx, cmd_item, NULL); +} + +static void _cdx_mcdi_display_error(struct cdx_mcdi *cdx, unsigned int cmd, + size_t inlen, int raw, int arg, int err_no) +{ + pr_err("MC command 0x%x inlen %d failed err_no=%d (raw=%d) arg=%d\n", + cmd, (int)inlen, err_no, raw, arg); +} + +/* + * Set MCDI mode to fail to prevent any new commands, then cancel any + * outstanding commands. + * Caller must hold the mcdi iface_lock. + */ +static void cdx_mcdi_mode_fail(struct cdx_mcdi *cdx, struct list_head *cleanup_list) +{ + struct cdx_mcdi_iface *mcdi = cdx_mcdi_if(cdx); + + if (!mcdi) + return; + + mcdi->mode = MCDI_MODE_FAIL; + + while (!list_empty(&mcdi->cmd_list)) { + struct cdx_mcdi_cmd *cmd; + + cmd = list_first_entry(&mcdi->cmd_list, struct cdx_mcdi_cmd, + list); + _cdx_mcdi_cancel_cmd(mcdi, cdx_mcdi_cmd_handle(cmd), cleanup_list); + } +} diff --git a/drivers/cdx/controller/mcdi.h b/drivers/cdx/controller/mcdi.h new file mode 100644 index 000000000000..63933ede33ed --- /dev/null +++ b/drivers/cdx/controller/mcdi.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2008-2013 Solarflare Communications Inc. + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef CDX_MCDI_H +#define CDX_MCDI_H + +#include +#include + +#include "bitfield.h" +#include "mc_cdx_pcol.h" + +#ifdef DEBUG +#define CDX_WARN_ON_ONCE_PARANOID(x) WARN_ON_ONCE(x) +#define CDX_WARN_ON_PARANOID(x) WARN_ON(x) +#else +#define CDX_WARN_ON_ONCE_PARANOID(x) do {} while (0) +#define CDX_WARN_ON_PARANOID(x) do {} while (0) +#endif + +/** + * enum cdx_mcdi_mode - MCDI transaction mode + * @MCDI_MODE_EVENTS: wait for an mcdi response callback. + * @MCDI_MODE_FAIL: we think MCDI is dead, so fail-fast all calls + */ +enum cdx_mcdi_mode { + MCDI_MODE_EVENTS, + MCDI_MODE_FAIL, +}; + +#define MCDI_RPC_TIMEOUT (10 * HZ) +#define MCDI_RPC_LONG_TIMEOU (60 * HZ) +#define MCDI_RPC_POST_RST_TIME (10 * HZ) + +#define MCDI_BUF_LEN (8 + MCDI_CTL_SDU_LEN_MAX) + +/** + * enum cdx_mcdi_cmd_state - State for an individual MCDI command + * @MCDI_STATE_QUEUED: Command not started and is waiting to run. + * @MCDI_STATE_RETRY: Command was submitted and MC rejected with no resources, + * as MC have too many outstanding commands. Command will be retried once + * another command returns. + * @MCDI_STATE_RUNNING: Command was accepted and is running. + * @MCDI_STATE_RUNNING_CANCELLED: Command is running but the issuer cancelled + * the command. + * @MCDI_STATE_FINISHED: Processing of this command has completed. + */ + +enum cdx_mcdi_cmd_state { + MCDI_STATE_QUEUED, + MCDI_STATE_RETRY, + MCDI_STATE_RUNNING, + MCDI_STATE_RUNNING_CANCELLED, + MCDI_STATE_FINISHED, +}; + +/** + * struct cdx_mcdi - CDX MCDI Firmware interface, to interact + * with CDX controller. + * @mcdi: MCDI interface + * @mcdi_ops: MCDI operations + */ +struct cdx_mcdi { + /* MCDI interface */ + struct cdx_mcdi_data *mcdi; + const struct cdx_mcdi_ops *mcdi_ops; +}; + +struct cdx_mcdi_ops { + void (*mcdi_request)(struct cdx_mcdi *cdx, + const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len); + unsigned int (*mcdi_rpc_timeout)(struct cdx_mcdi *cdx, unsigned int cmd); +}; + +typedef void cdx_mcdi_async_completer(struct cdx_mcdi *cdx, + unsigned long cookie, int rc, + struct cdx_dword *outbuf, + size_t outlen_actual); + +/** + * struct cdx_mcdi_cmd - An outstanding MCDI command + * @ref: Reference count. There will be one reference if the command is + * in the mcdi_iface cmd_list, another if it's on a cleanup list, + * and a third if it's queued in the work queue. + * @list: The data for this entry in mcdi->cmd_list + * @cleanup_list: The data for this entry in a cleanup list + * @work: The work item for this command, queued in mcdi->workqueue + * @mcdi: The mcdi_iface for this command + * @state: The state of this command + * @inlen: inbuf length + * @inbuf: Input buffer + * @quiet: Whether to silence errors + * @reboot_seen: Whether a reboot has been seen during this command, + * to prevent duplicates + * @seq: Sequence number + * @started: Jiffies this command was started at + * @cookie: Context for completion function + * @completer: Completion function + * @handle: Command handle + * @cmd: Command number + * @rc: Return code + * @outlen: Length of output buffer + * @outbuf: Output buffer + */ +struct cdx_mcdi_cmd { + struct kref ref; + struct list_head list; + struct list_head cleanup_list; + struct work_struct work; + struct cdx_mcdi_iface *mcdi; + enum cdx_mcdi_cmd_state state; + size_t inlen; + const struct cdx_dword *inbuf; + bool quiet; + bool reboot_seen; + u8 seq; + unsigned long started; + unsigned long cookie; + cdx_mcdi_async_completer *completer; + unsigned int handle; + unsigned int cmd; + int rc; + size_t outlen; + struct cdx_dword *outbuf; + /* followed by inbuf data if necessary */ +}; + +/** + * struct cdx_mcdi_iface - MCDI protocol context + * @cdx: The associated NIC + * @iface_lock: Serialise access to this structure + * @outstanding_cleanups: Count of cleanups + * @cmd_list: List of outstanding and running commands + * @workqueue: Workqueue used for delayed processing + * @cmd_complete_wq: Waitqueue for command completion + * @db_held_by: Command the MC doorbell is in use by + * @seq_held_by: Command each sequence number is in use by + * @prev_handle: The last used command handle + * @mode: Poll for mcdi completion, or wait for an mcdi_event + * @prev_seq: The last used sequence number + * @new_epoch: Indicates start of day or start of MC reboot recovery + * @logging_buffer: Buffer that may be used to build MCDI tracing messages + * @logging_enabled: Whether to trace MCDI + */ +struct cdx_mcdi_iface { + struct cdx_mcdi *cdx; + /* Serialise access */ + struct mutex iface_lock; + unsigned int outstanding_cleanups; + struct list_head cmd_list; + struct workqueue_struct *workqueue; + wait_queue_head_t cmd_complete_wq; + struct cdx_mcdi_cmd *db_held_by; + struct cdx_mcdi_cmd *seq_held_by[16]; + unsigned int prev_handle; + enum cdx_mcdi_mode mode; + u8 prev_seq; + bool new_epoch; +#ifdef CONFIG_MCDI_LOGGING + bool logging_enabled; + char *logging_buffer; +#endif +}; + +/** + * struct cdx_mcdi_data - extra state for NICs that implement MCDI + * @iface: Interface/protocol state + * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH. + */ +struct cdx_mcdi_data { + struct cdx_mcdi_iface iface; + u32 fn_flags; +}; + +static inline struct cdx_mcdi_iface *cdx_mcdi_if(struct cdx_mcdi *cdx) +{ + return cdx->mcdi ? &cdx->mcdi->iface : NULL; +} + +int cdx_mcdi_init(struct cdx_mcdi *cdx); +void cdx_mcdi_finish(struct cdx_mcdi *cdx); + +void cdx_mcdi_process_cmd(struct cdx_mcdi *cdx, struct cdx_dword *outbuf, int len); +int cdx_mcdi_rpc(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + struct cdx_dword *outbuf, size_t outlen, size_t *outlen_actual); +int cdx_mcdi_rpc_async(struct cdx_mcdi *cdx, unsigned int cmd, + const struct cdx_dword *inbuf, size_t inlen, + cdx_mcdi_async_completer *complete, + unsigned long cookie); +int cdx_mcdi_wait_for_quiescence(struct cdx_mcdi *cdx, + unsigned int timeout_jiffies); + +/* + * We expect that 16- and 32-bit fields in MCDI requests and responses + * are appropriately aligned, but 64-bit fields are only + * 32-bit-aligned. + */ +#define MCDI_DECLARE_BUF(_name, _len) struct cdx_dword _name[DIV_ROUND_UP(_len, 4)] = {{0}} +#define _MCDI_PTR(_buf, _offset) \ + ((u8 *)(_buf) + (_offset)) +#define MCDI_PTR(_buf, _field) \ + _MCDI_PTR(_buf, MC_CMD_ ## _field ## _OFST) +#define _MCDI_CHECK_ALIGN(_ofst, _align) \ + ((void)BUILD_BUG_ON_ZERO((_ofst) & ((_align) - 1)), \ + (_ofst)) +#define _MCDI_DWORD(_buf, _field) \ + ((_buf) + (_MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _OFST, 4) >> 2)) + +#define MCDI_BYTE(_buf, _field) \ + ((void)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 1), \ + *MCDI_PTR(_buf, _field)) +#define MCDI_WORD(_buf, _field) \ + ((void)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2), \ + le16_to_cpu(*(__force const __le16 *)MCDI_PTR(_buf, _field))) +#define MCDI_SET_DWORD(_buf, _field, _value) \ + CDX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), CDX_DWORD, _value) +#define MCDI_DWORD(_buf, _field) \ + CDX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), CDX_DWORD) +#define MCDI_POPULATE_DWORD_1(_buf, _field, _name1, _value1) \ + CDX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), \ + MC_CMD_ ## _name1, _value1) +#define MCDI_SET_QWORD(_buf, _field, _value) \ + do { \ + CDX_POPULATE_DWORD_1(_MCDI_DWORD(_buf, _field)[0], \ + CDX_DWORD, (u32)(_value)); \ + CDX_POPULATE_DWORD_1(_MCDI_DWORD(_buf, _field)[1], \ + CDX_DWORD, (u64)(_value) >> 32); \ + } while (0) +#define MCDI_QWORD(_buf, _field) \ + (CDX_DWORD_FIELD(_MCDI_DWORD(_buf, _field)[0], CDX_DWORD) | \ + (u64)CDX_DWORD_FIELD(_MCDI_DWORD(_buf, _field)[1], CDX_DWORD) << 32) + +#endif /* CDX_MCDI_H */ -- GitLab From 8a7923df35d3a0fa44985148cee5b7fde4a370ba Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:34 +0530 Subject: [PATCH 1608/5631] cdx: add cdx controller CDX controller uses MCDI interface as a protocol to communicate with the RPU firmware and registers the detected CDX devices on the CDX bus. It also uses RPMsg as the communication channel with the Firmware. Signed-off-by: Nipun Gupta Signed-off-by: Puneet Gupta Signed-off-by: Abhijit Gangurde Signed-off-by: Nikhil Agarwal Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-6-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/cdx/controller/Kconfig | 9 ++ drivers/cdx/controller/Makefile | 2 +- drivers/cdx/controller/cdx_controller.c | 188 ++++++++++++++++++++++++ drivers/cdx/controller/mcdi_functions.c | 125 ++++++++++++++++ drivers/cdx/controller/mcdi_functions.h | 50 +++++++ 5 files changed, 373 insertions(+), 1 deletion(-) create mode 100644 drivers/cdx/controller/cdx_controller.c create mode 100644 drivers/cdx/controller/mcdi_functions.c create mode 100644 drivers/cdx/controller/mcdi_functions.h diff --git a/drivers/cdx/controller/Kconfig b/drivers/cdx/controller/Kconfig index 785c71063b2a..17f9c6be2fe1 100644 --- a/drivers/cdx/controller/Kconfig +++ b/drivers/cdx/controller/Kconfig @@ -7,6 +7,15 @@ if CDX_BUS +config CDX_CONTROLLER + tristate "CDX bus controller" + help + CDX controller drives the CDX bus. It interacts with + firmware to get the hardware devices and registers with + the CDX bus. Say Y to enable the CDX hardware driver. + + If unsure, say N. + config MCDI_LOGGING bool "MCDI Logging for the CDX controller" depends on CDX_CONTROLLER diff --git a/drivers/cdx/controller/Makefile b/drivers/cdx/controller/Makefile index 0ce200678eda..f7437c882cc9 100644 --- a/drivers/cdx/controller/Makefile +++ b/drivers/cdx/controller/Makefile @@ -6,4 +6,4 @@ # obj-$(CONFIG_CDX_CONTROLLER) += cdx-controller.o -cdx-controller-objs := mcdi.o +cdx-controller-objs := cdx_controller.o mcdi.o mcdi_functions.o diff --git a/drivers/cdx/controller/cdx_controller.c b/drivers/cdx/controller/cdx_controller.c new file mode 100644 index 000000000000..fbebc8cdcbf8 --- /dev/null +++ b/drivers/cdx/controller/cdx_controller.c @@ -0,0 +1,188 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * CDX host controller driver for AMD versal-net platform. + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#include +#include +#include + +#include "../cdx.h" +#include "mcdi_functions.h" +#include "mcdi.h" + +static unsigned int cdx_mcdi_rpc_timeout(struct cdx_mcdi *cdx, unsigned int cmd) +{ + return MCDI_RPC_TIMEOUT; +} + +static void cdx_mcdi_request(struct cdx_mcdi *cdx, + const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len) +{ + /* + * This will get updated by rpmsg APIs, with RPMSG introduction + * in CDX controller as a transport layer. + */ +} + +static const struct cdx_mcdi_ops mcdi_ops = { + .mcdi_rpc_timeout = cdx_mcdi_rpc_timeout, + .mcdi_request = cdx_mcdi_request, +}; + +static int cdx_scan_devices(struct cdx_controller *cdx) +{ + struct cdx_mcdi *cdx_mcdi = cdx->priv; + u8 bus_num, dev_num, num_cdx_bus; + int ret; + + /* MCDI FW Read: Fetch the number of CDX buses on this controller */ + ret = cdx_mcdi_get_num_buses(cdx_mcdi); + if (ret < 0) { + dev_err(cdx->dev, + "Get number of CDX buses failed: %d\n", ret); + return ret; + } + num_cdx_bus = (u8)ret; + + for (bus_num = 0; bus_num < num_cdx_bus; bus_num++) { + u8 num_cdx_dev; + + /* MCDI FW Read: Fetch the number of devices present */ + ret = cdx_mcdi_get_num_devs(cdx_mcdi, bus_num); + if (ret < 0) { + dev_err(cdx->dev, + "Get devices on CDX bus %d failed: %d\n", bus_num, ret); + continue; + } + num_cdx_dev = (u8)ret; + + for (dev_num = 0; dev_num < num_cdx_dev; dev_num++) { + struct cdx_dev_params dev_params; + + /* MCDI FW: Get the device config */ + ret = cdx_mcdi_get_dev_config(cdx_mcdi, bus_num, + dev_num, &dev_params); + if (ret) { + dev_err(cdx->dev, + "CDX device config get failed for %d(bus):%d(dev), %d\n", + bus_num, dev_num, ret); + continue; + } + dev_params.cdx = cdx; + + /* Add the device to the cdx bus */ + ret = cdx_device_add(&dev_params); + if (ret) { + dev_err(cdx->dev, "registering cdx dev: %d failed: %d\n", + dev_num, ret); + continue; + } + + dev_dbg(cdx->dev, "CDX dev: %d on cdx bus: %d created\n", + dev_num, bus_num); + } + } + + return 0; +} + +static struct cdx_ops cdx_ops = { + .scan = cdx_scan_devices, +}; + +static int xlnx_cdx_probe(struct platform_device *pdev) +{ + struct cdx_controller *cdx; + struct cdx_mcdi *cdx_mcdi; + int ret; + + cdx_mcdi = kzalloc(sizeof(*cdx_mcdi), GFP_KERNEL); + if (!cdx_mcdi) + return -ENOMEM; + + /* Store the MCDI ops */ + cdx_mcdi->mcdi_ops = &mcdi_ops; + /* MCDI FW: Initialize the FW path */ + ret = cdx_mcdi_init(cdx_mcdi); + if (ret) { + dev_err_probe(&pdev->dev, ret, "MCDI Initialization failed\n"); + goto mcdi_init_fail; + } + + cdx = kzalloc(sizeof(*cdx), GFP_KERNEL); + if (!cdx) { + ret = -ENOMEM; + goto cdx_alloc_fail; + } + platform_set_drvdata(pdev, cdx); + + cdx->dev = &pdev->dev; + cdx->priv = cdx_mcdi; + cdx->ops = &cdx_ops; + + return 0; + +cdx_alloc_fail: + cdx_mcdi_finish(cdx_mcdi); +mcdi_init_fail: + kfree(cdx_mcdi); + + return ret; +} + +static int xlnx_cdx_remove(struct platform_device *pdev) +{ + struct cdx_controller *cdx = platform_get_drvdata(pdev); + struct cdx_mcdi *cdx_mcdi = cdx->priv; + + kfree(cdx); + + cdx_mcdi_finish(cdx_mcdi); + kfree(cdx_mcdi); + + return 0; +} + +static const struct of_device_id cdx_match_table[] = { + {.compatible = "xlnx,versal-net-cdx",}, + { }, +}; + +MODULE_DEVICE_TABLE(of, cdx_match_table); + +static struct platform_driver cdx_pdriver = { + .driver = { + .name = "cdx-controller", + .pm = NULL, + .of_match_table = cdx_match_table, + }, + .probe = xlnx_cdx_probe, + .remove = xlnx_cdx_remove, +}; + +static int __init cdx_controller_init(void) +{ + int ret; + + ret = platform_driver_register(&cdx_pdriver); + if (ret) + pr_err("platform_driver_register() failed: %d\n", ret); + + return ret; +} + +static void __exit cdx_controller_exit(void) +{ + platform_driver_unregister(&cdx_pdriver); +} + +module_init(cdx_controller_init); +module_exit(cdx_controller_exit); + +MODULE_AUTHOR("AMD Inc."); +MODULE_DESCRIPTION("CDX controller for AMD devices"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cdx/controller/mcdi_functions.c b/drivers/cdx/controller/mcdi_functions.c new file mode 100644 index 000000000000..012b52881dd5 --- /dev/null +++ b/drivers/cdx/controller/mcdi_functions.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#include + +#include "mcdi.h" +#include "mcdi_functions.h" + +int cdx_mcdi_get_num_buses(struct cdx_mcdi *cdx) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_CDX_BUS_ENUM_BUSES_OUT_LEN); + size_t outlen; + int ret; + + ret = cdx_mcdi_rpc(cdx, MC_CMD_CDX_BUS_ENUM_BUSES, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (ret) + return ret; + + if (outlen != MC_CMD_CDX_BUS_ENUM_BUSES_OUT_LEN) + return -EIO; + + return MCDI_DWORD(outbuf, CDX_BUS_ENUM_BUSES_OUT_BUS_COUNT); +} + +int cdx_mcdi_get_num_devs(struct cdx_mcdi *cdx, int bus_num) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_CDX_BUS_ENUM_DEVICES_OUT_LEN); + MCDI_DECLARE_BUF(inbuf, MC_CMD_CDX_BUS_ENUM_DEVICES_IN_LEN); + size_t outlen; + int ret; + + MCDI_SET_DWORD(inbuf, CDX_BUS_ENUM_DEVICES_IN_BUS, bus_num); + + ret = cdx_mcdi_rpc(cdx, MC_CMD_CDX_BUS_ENUM_DEVICES, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (ret) + return ret; + + if (outlen != MC_CMD_CDX_BUS_ENUM_DEVICES_OUT_LEN) + return -EIO; + + return MCDI_DWORD(outbuf, CDX_BUS_ENUM_DEVICES_OUT_DEVICE_COUNT); +} + +int cdx_mcdi_get_dev_config(struct cdx_mcdi *cdx, + u8 bus_num, u8 dev_num, + struct cdx_dev_params *dev_params) +{ + MCDI_DECLARE_BUF(outbuf, MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_LEN); + MCDI_DECLARE_BUF(inbuf, MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_IN_LEN); + struct resource *res = &dev_params->res[0]; + size_t outlen; + u32 req_id; + int ret; + + MCDI_SET_DWORD(inbuf, CDX_BUS_GET_DEVICE_CONFIG_IN_BUS, bus_num); + MCDI_SET_DWORD(inbuf, CDX_BUS_GET_DEVICE_CONFIG_IN_DEVICE, dev_num); + + ret = cdx_mcdi_rpc(cdx, MC_CMD_CDX_BUS_GET_DEVICE_CONFIG, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (ret) + return ret; + + if (outlen != MC_CMD_CDX_BUS_GET_DEVICE_CONFIG_OUT_LEN) + return -EIO; + + dev_params->bus_num = bus_num; + dev_params->dev_num = dev_num; + + req_id = MCDI_DWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_REQUESTER_ID); + dev_params->req_id = req_id; + + dev_params->res_count = 0; + if (MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE) != 0) { + res[dev_params->res_count].start = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE); + res[dev_params->res_count].end = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_BASE) + + MCDI_QWORD(outbuf, + CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION0_SIZE) - 1; + res[dev_params->res_count].flags = IORESOURCE_MEM; + dev_params->res_count++; + } + + if (MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE) != 0) { + res[dev_params->res_count].start = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE); + res[dev_params->res_count].end = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_BASE) + + MCDI_QWORD(outbuf, + CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION1_SIZE) - 1; + res[dev_params->res_count].flags = IORESOURCE_MEM; + dev_params->res_count++; + } + + if (MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE) != 0) { + res[dev_params->res_count].start = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE); + res[dev_params->res_count].end = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_BASE) + + MCDI_QWORD(outbuf, + CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION2_SIZE) - 1; + res[dev_params->res_count].flags = IORESOURCE_MEM; + dev_params->res_count++; + } + + if (MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE) != 0) { + res[dev_params->res_count].start = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE); + res[dev_params->res_count].end = + MCDI_QWORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_BASE) + + MCDI_QWORD(outbuf, + CDX_BUS_GET_DEVICE_CONFIG_OUT_MMIO_REGION3_SIZE) - 1; + res[dev_params->res_count].flags = IORESOURCE_MEM; + dev_params->res_count++; + } + + dev_params->vendor = MCDI_WORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_VENDOR_ID); + dev_params->device = MCDI_WORD(outbuf, CDX_BUS_GET_DEVICE_CONFIG_OUT_DEVICE_ID); + + return 0; +} diff --git a/drivers/cdx/controller/mcdi_functions.h b/drivers/cdx/controller/mcdi_functions.h new file mode 100644 index 000000000000..6bf5a4a0778f --- /dev/null +++ b/drivers/cdx/controller/mcdi_functions.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Header file for MCDI FW interaction for CDX bus. + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef CDX_MCDI_FUNCTIONS_H +#define CDX_MCDI_FUNCTIONS_H + +#include "mcdi.h" +#include "../cdx.h" + +/** + * cdx_mcdi_get_num_buses - Get the total number of buses on + * the controller. + * @cdx: pointer to MCDI interface. + * + * Return: total number of buses available on the controller, + * <0 on failure + */ +int cdx_mcdi_get_num_buses(struct cdx_mcdi *cdx); + +/** + * cdx_mcdi_get_num_devs - Get the total number of devices on + * a particular bus of the controller. + * @cdx: pointer to MCDI interface. + * @bus_num: Bus number. + * + * Return: total number of devices available on the bus, <0 on failure + */ +int cdx_mcdi_get_num_devs(struct cdx_mcdi *cdx, int bus_num); + +/** + * cdx_mcdi_get_dev_config - Get configuration for a particular + * bus_num:dev_num + * @cdx: pointer to MCDI interface. + * @bus_num: Bus number. + * @dev_num: Device number. + * @dev_params: Pointer to cdx_dev_params, this is populated by this + * device with the configuration corresponding to the provided + * bus_num:dev_num. + * + * Return: 0 total number of devices available on the bus, <0 on failure + */ +int cdx_mcdi_get_dev_config(struct cdx_mcdi *cdx, + u8 bus_num, u8 dev_num, + struct cdx_dev_params *dev_params); + +#endif /* CDX_MCDI_FUNCTIONS_H */ -- GitLab From 2a226927d9b836ddec674aebbcea311727d04240 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:35 +0530 Subject: [PATCH 1609/5631] cdx: add rpmsg communication channel for CDX RPMsg is used as a transport communication channel. This change introduces RPMsg driver and integrates it with the CDX controller. Signed-off-by: Abhijit Gangurde Signed-off-by: Nipun Gupta Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-7-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- drivers/cdx/controller/Kconfig | 2 + drivers/cdx/controller/Makefile | 2 +- drivers/cdx/controller/cdx_controller.c | 32 +++- drivers/cdx/controller/cdx_controller.h | 30 ++++ drivers/cdx/controller/cdx_rpmsg.c | 202 ++++++++++++++++++++++++ drivers/cdx/controller/mcdi.h | 10 ++ 6 files changed, 273 insertions(+), 5 deletions(-) create mode 100644 drivers/cdx/controller/cdx_controller.h create mode 100644 drivers/cdx/controller/cdx_rpmsg.c diff --git a/drivers/cdx/controller/Kconfig b/drivers/cdx/controller/Kconfig index 17f9c6be2fe1..c3e3b9ff8dfe 100644 --- a/drivers/cdx/controller/Kconfig +++ b/drivers/cdx/controller/Kconfig @@ -9,6 +9,8 @@ if CDX_BUS config CDX_CONTROLLER tristate "CDX bus controller" + select REMOTEPROC + select RPMSG help CDX controller drives the CDX bus. It interacts with firmware to get the hardware devices and registers with diff --git a/drivers/cdx/controller/Makefile b/drivers/cdx/controller/Makefile index f7437c882cc9..f071be411d96 100644 --- a/drivers/cdx/controller/Makefile +++ b/drivers/cdx/controller/Makefile @@ -6,4 +6,4 @@ # obj-$(CONFIG_CDX_CONTROLLER) += cdx-controller.o -cdx-controller-objs := cdx_controller.o mcdi.o mcdi_functions.o +cdx-controller-objs := cdx_controller.o cdx_rpmsg.o mcdi.o mcdi_functions.o diff --git a/drivers/cdx/controller/cdx_controller.c b/drivers/cdx/controller/cdx_controller.c index fbebc8cdcbf8..0d1826980935 100644 --- a/drivers/cdx/controller/cdx_controller.c +++ b/drivers/cdx/controller/cdx_controller.c @@ -9,6 +9,7 @@ #include #include +#include "cdx_controller.h" #include "../cdx.h" #include "mcdi_functions.h" #include "mcdi.h" @@ -22,10 +23,8 @@ static void cdx_mcdi_request(struct cdx_mcdi *cdx, const struct cdx_dword *hdr, size_t hdr_len, const struct cdx_dword *sdu, size_t sdu_len) { - /* - * This will get updated by rpmsg APIs, with RPMSG introduction - * in CDX controller as a transport layer. - */ + if (cdx_rpmsg_send(cdx, hdr, hdr_len, sdu, sdu_len)) + dev_err(&cdx->rpdev->dev, "Failed to send rpmsg data\n"); } static const struct cdx_mcdi_ops mcdi_ops = { @@ -33,6 +32,19 @@ static const struct cdx_mcdi_ops mcdi_ops = { .mcdi_request = cdx_mcdi_request, }; +void cdx_rpmsg_post_probe(struct cdx_controller *cdx) +{ + /* Register CDX controller with CDX bus driver */ + if (cdx_register_controller(cdx)) + dev_err(cdx->dev, "Failed to register CDX controller\n"); +} + +void cdx_rpmsg_pre_remove(struct cdx_controller *cdx) +{ + cdx_unregister_controller(cdx); + cdx_mcdi_wait_for_quiescence(cdx->priv, MCDI_RPC_TIMEOUT); +} + static int cdx_scan_devices(struct cdx_controller *cdx) { struct cdx_mcdi *cdx_mcdi = cdx->priv; @@ -124,8 +136,18 @@ static int xlnx_cdx_probe(struct platform_device *pdev) cdx->priv = cdx_mcdi; cdx->ops = &cdx_ops; + ret = cdx_setup_rpmsg(pdev); + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "Failed to register CDX RPMsg transport\n"); + goto cdx_rpmsg_fail; + } + + dev_info(&pdev->dev, "Successfully registered CDX controller with RPMsg as transport\n"); return 0; +cdx_rpmsg_fail: + kfree(cdx); cdx_alloc_fail: cdx_mcdi_finish(cdx_mcdi); mcdi_init_fail: @@ -139,6 +161,8 @@ static int xlnx_cdx_remove(struct platform_device *pdev) struct cdx_controller *cdx = platform_get_drvdata(pdev); struct cdx_mcdi *cdx_mcdi = cdx->priv; + cdx_destroy_rpmsg(pdev); + kfree(cdx); cdx_mcdi_finish(cdx_mcdi); diff --git a/drivers/cdx/controller/cdx_controller.h b/drivers/cdx/controller/cdx_controller.h new file mode 100644 index 000000000000..43b7c742df87 --- /dev/null +++ b/drivers/cdx/controller/cdx_controller.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Header file for the CDX Controller + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#ifndef _CDX_CONTROLLER_H_ +#define _CDX_CONTROLLER_H_ + +#include +#include "mcdi_functions.h" + +void cdx_rpmsg_post_probe(struct cdx_controller *cdx); + +void cdx_rpmsg_pre_remove(struct cdx_controller *cdx); + +int cdx_rpmsg_send(struct cdx_mcdi *cdx_mcdi, + const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len); + +void cdx_rpmsg_read_resp(struct cdx_mcdi *cdx_mcdi, + struct cdx_dword *outbuf, size_t offset, + size_t outlen); + +int cdx_setup_rpmsg(struct platform_device *pdev); + +void cdx_destroy_rpmsg(struct platform_device *pdev); + +#endif /* _CDX_CONT_PRIV_H_ */ diff --git a/drivers/cdx/controller/cdx_rpmsg.c b/drivers/cdx/controller/cdx_rpmsg.c new file mode 100644 index 000000000000..f37e639d6ce3 --- /dev/null +++ b/drivers/cdx/controller/cdx_rpmsg.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Platform driver for CDX bus. + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include + +#include "../cdx.h" +#include "cdx_controller.h" +#include "mcdi_functions.h" +#include "mcdi.h" + +static struct rpmsg_device_id cdx_rpmsg_id_table[] = { + { .name = "mcdi_ipc" }, + { }, +}; +MODULE_DEVICE_TABLE(rpmsg, cdx_rpmsg_id_table); + +int cdx_rpmsg_send(struct cdx_mcdi *cdx_mcdi, + const struct cdx_dword *hdr, size_t hdr_len, + const struct cdx_dword *sdu, size_t sdu_len) +{ + unsigned char *send_buf; + int ret; + + send_buf = kzalloc(hdr_len + sdu_len, GFP_KERNEL); + if (!send_buf) + return -ENOMEM; + + memcpy(send_buf, hdr, hdr_len); + memcpy(send_buf + hdr_len, sdu, sdu_len); + + ret = rpmsg_send(cdx_mcdi->ept, send_buf, hdr_len + sdu_len); + kfree(send_buf); + + return ret; +} + +static int cdx_attach_to_rproc(struct platform_device *pdev) +{ + struct device_node *r5_core_node; + struct cdx_controller *cdx_c; + struct cdx_mcdi *cdx_mcdi; + struct device *dev; + struct rproc *rp; + int ret; + + dev = &pdev->dev; + cdx_c = platform_get_drvdata(pdev); + cdx_mcdi = cdx_c->priv; + + r5_core_node = of_parse_phandle(dev->of_node, "xlnx,rproc", 0); + if (!r5_core_node) { + dev_err(&pdev->dev, "xlnx,rproc: invalid phandle\n"); + return -EINVAL; + } + + rp = rproc_get_by_phandle(r5_core_node->phandle); + if (!rp) { + ret = -EPROBE_DEFER; + goto pdev_err; + } + + /* Attach to remote processor */ + ret = rproc_boot(rp); + if (ret) { + dev_err(&pdev->dev, "Failed to attach to remote processor\n"); + rproc_put(rp); + goto pdev_err; + } + + cdx_mcdi->r5_rproc = rp; +pdev_err: + of_node_put(r5_core_node); + return ret; +} + +static void cdx_detach_to_r5(struct platform_device *pdev) +{ + struct cdx_controller *cdx_c; + struct cdx_mcdi *cdx_mcdi; + + cdx_c = platform_get_drvdata(pdev); + cdx_mcdi = cdx_c->priv; + + rproc_detach(cdx_mcdi->r5_rproc); + rproc_put(cdx_mcdi->r5_rproc); +} + +static int cdx_rpmsg_cb(struct rpmsg_device *rpdev, void *data, + int len, void *priv, u32 src) +{ + struct cdx_controller *cdx_c = dev_get_drvdata(&rpdev->dev); + struct cdx_mcdi *cdx_mcdi = cdx_c->priv; + + if (len > MCDI_BUF_LEN) + return -EINVAL; + + cdx_mcdi_process_cmd(cdx_mcdi, (struct cdx_dword *)data, len); + + return 0; +} + +static void cdx_rpmsg_post_probe_work(struct work_struct *work) +{ + struct cdx_controller *cdx_c; + struct cdx_mcdi *cdx_mcdi; + + cdx_mcdi = container_of(work, struct cdx_mcdi, work); + cdx_c = dev_get_drvdata(&cdx_mcdi->rpdev->dev); + cdx_rpmsg_post_probe(cdx_c); +} + +static int cdx_rpmsg_probe(struct rpmsg_device *rpdev) +{ + struct rpmsg_channel_info chinfo = {0}; + struct cdx_controller *cdx_c; + struct cdx_mcdi *cdx_mcdi; + + cdx_c = (struct cdx_controller *)cdx_rpmsg_id_table[0].driver_data; + cdx_mcdi = cdx_c->priv; + + chinfo.src = RPMSG_ADDR_ANY; + chinfo.dst = rpdev->dst; + strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, + strlen(cdx_rpmsg_id_table[0].name)); + + cdx_mcdi->ept = rpmsg_create_ept(rpdev, cdx_rpmsg_cb, NULL, chinfo); + if (!cdx_mcdi->ept) { + dev_err_probe(&rpdev->dev, -ENXIO, + "Failed to create ept for channel %s\n", + chinfo.name); + return -EINVAL; + } + + cdx_mcdi->rpdev = rpdev; + dev_set_drvdata(&rpdev->dev, cdx_c); + + schedule_work(&cdx_mcdi->work); + return 0; +} + +static void cdx_rpmsg_remove(struct rpmsg_device *rpdev) +{ + struct cdx_controller *cdx_c = dev_get_drvdata(&rpdev->dev); + struct cdx_mcdi *cdx_mcdi = cdx_c->priv; + + flush_work(&cdx_mcdi->work); + cdx_rpmsg_pre_remove(cdx_c); + + rpmsg_destroy_ept(cdx_mcdi->ept); + dev_set_drvdata(&rpdev->dev, NULL); +} + +static struct rpmsg_driver cdx_rpmsg_driver = { + .drv.name = KBUILD_MODNAME, + .id_table = cdx_rpmsg_id_table, + .probe = cdx_rpmsg_probe, + .remove = cdx_rpmsg_remove, + .callback = cdx_rpmsg_cb, +}; + +int cdx_setup_rpmsg(struct platform_device *pdev) +{ + struct cdx_controller *cdx_c; + struct cdx_mcdi *cdx_mcdi; + int ret; + + /* Attach to remote processor */ + ret = cdx_attach_to_rproc(pdev); + if (ret) + return ret; + + cdx_c = platform_get_drvdata(pdev); + cdx_mcdi = cdx_c->priv; + + /* Register RPMsg driver */ + cdx_rpmsg_id_table[0].driver_data = (kernel_ulong_t)cdx_c; + + INIT_WORK(&cdx_mcdi->work, cdx_rpmsg_post_probe_work); + ret = register_rpmsg_driver(&cdx_rpmsg_driver); + if (ret) { + dev_err(&pdev->dev, + "Failed to register cdx RPMsg driver: %d\n", ret); + cdx_detach_to_r5(pdev); + } + + return ret; +} + +void cdx_destroy_rpmsg(struct platform_device *pdev) +{ + unregister_rpmsg_driver(&cdx_rpmsg_driver); + + cdx_detach_to_r5(pdev); +} diff --git a/drivers/cdx/controller/mcdi.h b/drivers/cdx/controller/mcdi.h index 63933ede33ed..0bfbeab04e43 100644 --- a/drivers/cdx/controller/mcdi.h +++ b/drivers/cdx/controller/mcdi.h @@ -9,6 +9,7 @@ #include #include +#include #include "bitfield.h" #include "mc_cdx_pcol.h" @@ -62,11 +63,20 @@ enum cdx_mcdi_cmd_state { * with CDX controller. * @mcdi: MCDI interface * @mcdi_ops: MCDI operations + * @r5_rproc : R5 Remoteproc device handle + * @rpdev: RPMsg device + * @ept: RPMsg endpoint + * @work: Post probe work */ struct cdx_mcdi { /* MCDI interface */ struct cdx_mcdi_data *mcdi; const struct cdx_mcdi_ops *mcdi_ops; + + struct rproc *r5_rproc; + struct rpmsg_device *rpdev; + struct rpmsg_endpoint *ept; + struct work_struct work; }; struct cdx_mcdi_ops { -- GitLab From 48a6c7bced2a781c911497f073347bec5ab4d7a5 Mon Sep 17 00:00:00 2001 From: Nipun Gupta Date: Mon, 13 Mar 2023 18:56:36 +0530 Subject: [PATCH 1610/5631] cdx: add device attributes Create sysfs entry for CDX devices. Sysfs entries provided in each of the CDX device detected by the CDX controller - vendor id - device id - remove - reset of the device. - driver override Signed-off-by: Puneet Gupta Signed-off-by: Nipun Gupta Signed-off-by: Tarak Reddy Reviewed-by: Pieter Jansen van Vuuren Tested-by: Nikhil Agarwal Link: https://lore.kernel.org/r/20230313132636.31850-8-nipun.gupta@amd.com Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-cdx | 44 ++++++++ drivers/cdx/cdx.c | 127 ++++++++++++++++++++++++ drivers/cdx/controller/cdx_controller.c | 18 ++++ drivers/cdx/controller/mcdi_functions.c | 14 +++ drivers/cdx/controller/mcdi_functions.h | 11 ++ include/linux/cdx/cdx_bus.h | 27 +++++ 6 files changed, 241 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-cdx b/Documentation/ABI/testing/sysfs-bus-cdx index 43b4e161f226..7af477f49998 100644 --- a/Documentation/ABI/testing/sysfs-bus-cdx +++ b/Documentation/ABI/testing/sysfs-bus-cdx @@ -10,3 +10,47 @@ Description: For example:: # echo 1 > /sys/bus/cdx/rescan + +What: /sys/bus/cdx/devices/.../vendor +Date: March 2023 +Contact: nipun.gupta@amd.com +Description: + Vendor ID for this CDX device, in hexadecimal. Vendor ID is + 16 bit identifier which is specific to the device manufacturer. + Combination of Vendor ID and Device ID identifies a device. + +What: /sys/bus/cdx/devices/.../device +Date: March 2023 +Contact: nipun.gupta@amd.com +Description: + Device ID for this CDX device, in hexadecimal. Device ID is + 16 bit identifier to identify a device type within the range + of a device manufacturer. + Combination of Vendor ID and Device ID identifies a device. + +What: /sys/bus/cdx/devices/.../reset +Date: March 2023 +Contact: nipun.gupta@amd.com +Description: + Writing y/1/on to this file resets the CDX device. + On resetting the device, the corresponding driver is notified + twice, once before the device is being reset, and again after + the reset has been complete. + + For example:: + + # echo 1 > /sys/bus/cdx/.../reset + +What: /sys/bus/cdx/devices/.../remove +Date: March 2023 +Contact: tarak.reddy@amd.com +Description: + Writing y/1/on to this file removes the corresponding + device from the CDX bus. If the device is to be reconfigured + reconfigured in the Hardware, the device can be removed, so + that the device driver does not access the device while it is + being reconfigured. + + For example:: + + # echo 1 > /sys/bus/cdx/devices/.../remove diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c index 6b162bbb9b25..67c32cb2c006 100644 --- a/drivers/cdx/cdx.c +++ b/drivers/cdx/cdx.c @@ -71,6 +71,39 @@ /* CDX controllers registered with the CDX bus */ static DEFINE_XARRAY_ALLOC(cdx_controllers); +/** + * cdx_dev_reset - Reset a CDX device + * @dev: CDX device + * + * Return: -errno on failure, 0 on success. + */ +int cdx_dev_reset(struct device *dev) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + struct cdx_controller *cdx = cdx_dev->cdx; + struct cdx_device_config dev_config = {0}; + struct cdx_driver *cdx_drv; + int ret; + + cdx_drv = to_cdx_driver(dev->driver); + /* Notify driver that device is being reset */ + if (cdx_drv && cdx_drv->reset_prepare) + cdx_drv->reset_prepare(cdx_dev); + + dev_config.type = CDX_DEV_RESET_CONF; + ret = cdx->ops->dev_configure(cdx, cdx_dev->bus_num, + cdx_dev->dev_num, &dev_config); + if (ret) + dev_err(dev, "cdx device reset failed\n"); + + /* Notify driver that device reset is complete */ + if (cdx_drv && cdx_drv->reset_done) + cdx_drv->reset_done(cdx_dev); + + return ret; +} +EXPORT_SYMBOL_GPL(cdx_dev_reset); + /** * cdx_unregister_device - Unregister a CDX device * @dev: CDX device @@ -237,6 +270,99 @@ static int cdx_dma_configure(struct device *dev) return 0; } +/* show configuration fields */ +#define cdx_config_attr(field, format_string) \ +static ssize_t \ +field##_show(struct device *dev, struct device_attribute *attr, char *buf) \ +{ \ + struct cdx_device *cdx_dev = to_cdx_device(dev); \ + return sysfs_emit(buf, format_string, cdx_dev->field); \ +} \ +static DEVICE_ATTR_RO(field) + +cdx_config_attr(vendor, "0x%04x\n"); +cdx_config_attr(device, "0x%04x\n"); + +static ssize_t remove_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + + if (kstrtobool(buf, &val) < 0) + return -EINVAL; + + if (!val) + return -EINVAL; + + if (device_remove_file_self(dev, attr)) { + int ret; + + ret = cdx_unregister_device(dev, NULL); + if (ret) + return ret; + } + + return count; +} +static DEVICE_ATTR_WO(remove); + +static ssize_t reset_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + int ret; + + if (kstrtobool(buf, &val) < 0) + return -EINVAL; + + if (!val) + return -EINVAL; + + ret = cdx_dev_reset(dev); + if (ret) + return ret; + + return count; +} +static DEVICE_ATTR_WO(reset); + +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + int ret; + + if (WARN_ON(dev->bus != &cdx_bus_type)) + return -EINVAL; + + ret = driver_set_override(dev, &cdx_dev->driver_override, buf, count); + if (ret) + return ret; + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cdx_device *cdx_dev = to_cdx_device(dev); + + return sysfs_emit(buf, "%s\n", cdx_dev->driver_override); +} +static DEVICE_ATTR_RW(driver_override); + +static struct attribute *cdx_dev_attrs[] = { + &dev_attr_remove.attr, + &dev_attr_reset.attr, + &dev_attr_vendor.attr, + &dev_attr_device.attr, + &dev_attr_driver_override.attr, + NULL, +}; +ATTRIBUTE_GROUPS(cdx_dev); + static ssize_t rescan_store(struct bus_type *bus, const char *buf, size_t count) { @@ -280,6 +406,7 @@ struct bus_type cdx_bus_type = { .shutdown = cdx_shutdown, .dma_configure = cdx_dma_configure, .bus_groups = cdx_bus_groups, + .dev_groups = cdx_dev_groups, }; EXPORT_SYMBOL_GPL(cdx_bus_type); diff --git a/drivers/cdx/controller/cdx_controller.c b/drivers/cdx/controller/cdx_controller.c index 0d1826980935..dc52f95f8978 100644 --- a/drivers/cdx/controller/cdx_controller.c +++ b/drivers/cdx/controller/cdx_controller.c @@ -45,6 +45,23 @@ void cdx_rpmsg_pre_remove(struct cdx_controller *cdx) cdx_mcdi_wait_for_quiescence(cdx->priv, MCDI_RPC_TIMEOUT); } +static int cdx_configure_device(struct cdx_controller *cdx, + u8 bus_num, u8 dev_num, + struct cdx_device_config *dev_config) +{ + int ret = 0; + + switch (dev_config->type) { + case CDX_DEV_RESET_CONF: + ret = cdx_mcdi_reset_device(cdx->priv, bus_num, dev_num); + break; + default: + ret = -EINVAL; + } + + return ret; +} + static int cdx_scan_devices(struct cdx_controller *cdx) { struct cdx_mcdi *cdx_mcdi = cdx->priv; @@ -104,6 +121,7 @@ static int cdx_scan_devices(struct cdx_controller *cdx) static struct cdx_ops cdx_ops = { .scan = cdx_scan_devices, + .dev_configure = cdx_configure_device, }; static int xlnx_cdx_probe(struct platform_device *pdev) diff --git a/drivers/cdx/controller/mcdi_functions.c b/drivers/cdx/controller/mcdi_functions.c index 012b52881dd5..0158f26533dd 100644 --- a/drivers/cdx/controller/mcdi_functions.c +++ b/drivers/cdx/controller/mcdi_functions.c @@ -123,3 +123,17 @@ int cdx_mcdi_get_dev_config(struct cdx_mcdi *cdx, return 0; } + +int cdx_mcdi_reset_device(struct cdx_mcdi *cdx, u8 bus_num, u8 dev_num) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_CDX_DEVICE_RESET_IN_LEN); + int ret; + + MCDI_SET_DWORD(inbuf, CDX_DEVICE_RESET_IN_BUS, bus_num); + MCDI_SET_DWORD(inbuf, CDX_DEVICE_RESET_IN_DEVICE, dev_num); + + ret = cdx_mcdi_rpc(cdx, MC_CMD_CDX_DEVICE_RESET, inbuf, sizeof(inbuf), + NULL, 0, NULL); + + return ret; +} diff --git a/drivers/cdx/controller/mcdi_functions.h b/drivers/cdx/controller/mcdi_functions.h index 6bf5a4a0778f..7440ace5539a 100644 --- a/drivers/cdx/controller/mcdi_functions.h +++ b/drivers/cdx/controller/mcdi_functions.h @@ -47,4 +47,15 @@ int cdx_mcdi_get_dev_config(struct cdx_mcdi *cdx, u8 bus_num, u8 dev_num, struct cdx_dev_params *dev_params); +/** + * cdx_mcdi_reset_device - Reset cdx device represented by bus_num:dev_num + * @cdx: pointer to MCDI interface. + * @bus_num: Bus number. + * @dev_num: Device number. + * + * Return: 0 on success, <0 on failure + */ +int cdx_mcdi_reset_device(struct cdx_mcdi *cdx, + u8 bus_num, u8 dev_num); + #endif /* CDX_MCDI_FUNCTIONS_H */ diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h index d134e0104724..35ef41d8a61a 100644 --- a/include/linux/cdx/cdx_bus.h +++ b/include/linux/cdx/cdx_bus.h @@ -21,8 +21,20 @@ /* Forward declaration for CDX controller */ struct cdx_controller; +enum { + CDX_DEV_RESET_CONF, +}; + +struct cdx_device_config { + u8 type; +}; + typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); +typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx, + u8 bus_num, u8 dev_num, + struct cdx_device_config *dev_config); + /** * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with * override_only flags. @@ -39,9 +51,12 @@ typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); /** * struct cdx_ops - Callbacks supported by CDX controller. * @scan: scan the devices on the controller + * @dev_configure: configuration like reset, master_enable, + * msi_config etc for a CDX device */ struct cdx_ops { cdx_scan_cb scan; + cdx_dev_configure_cb dev_configure; }; /** @@ -101,6 +116,8 @@ struct cdx_device { * @probe: Function called when a device is added * @remove: Function called when a device is removed * @shutdown: Function called at shutdown time to quiesce the device + * @reset_prepare: Function called before is reset to notify driver + * @reset_done: Function called after reset is complete to notify driver * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. * For most device drivers, no need to care about this flag * as long as all DMAs are handled through the kernel DMA API. @@ -115,6 +132,8 @@ struct cdx_driver { int (*probe)(struct cdx_device *dev); int (*remove)(struct cdx_device *dev); void (*shutdown)(struct cdx_device *dev); + void (*reset_prepare)(struct cdx_device *dev); + void (*reset_done)(struct cdx_device *dev); bool driver_managed_dma; }; @@ -144,4 +163,12 @@ void cdx_driver_unregister(struct cdx_driver *cdx_driver); extern struct bus_type cdx_bus_type; +/** + * cdx_dev_reset - Reset CDX device + * @dev: device pointer + * + * Return: 0 for success, -errno on failure + */ +int cdx_dev_reset(struct device *dev); + #endif /* _CDX_BUS_H_ */ -- GitLab From 4336cc15b9f7b34bc0ddc85c76f71be6a0355028 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Mon, 13 Mar 2023 15:17:43 -0600 Subject: [PATCH 1611/5631] selftests: use canonical ftrace path The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing A few spots in tools/testing/selftests still refer to this older debugfs path, so let's update them to avoid confusion. Link: https://lkml.kernel.org/r/20230313211746.1541525-1-zwisler@kernel.org Cc: "Tobin C. Harding" Cc: Andrew Morton Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Paolo Bonzini Cc: Shuah Khan Cc: Tycho Andersen Reviewed-by: Steven Rostedt (Google) Reviewed-by: Mukesh Ojha Signed-off-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- tools/testing/selftests/mm/protection_keys.c | 4 ++-- tools/testing/selftests/user_events/dyn_test.c | 2 +- tools/testing/selftests/user_events/ftrace_test.c | 10 +++++----- tools/testing/selftests/user_events/perf_test.c | 8 ++++---- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 95f403a0c46d..0381c34fdd56 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -98,7 +98,7 @@ int tracing_root_ok(void) void tracing_on(void) { #if CONTROL_TRACING > 0 -#define TRACEDIR "/sys/kernel/debug/tracing" +#define TRACEDIR "/sys/kernel/tracing" char pidstr[32]; if (!tracing_root_ok()) @@ -124,7 +124,7 @@ void tracing_off(void) #if CONTROL_TRACING > 0 if (!tracing_root_ok()) return; - cat_into_file("0", "/sys/kernel/debug/tracing/tracing_on"); + cat_into_file("0", "/sys/kernel/tracing/tracing_on"); #endif } diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index d6265d14cd51..8879a7b04c6a 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -16,7 +16,7 @@ #include "../kselftest_harness.h" -const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events"; +const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; const char *clear = "!u:__test_event"; static int Append(const char *value) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 404a2713dcae..a0b2c96eb252 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -16,11 +16,11 @@ #include "../kselftest_harness.h" -const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; -const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; -const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable"; -const char *trace_file = "/sys/kernel/debug/tracing/trace"; -const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *status_file = "/sys/kernel/tracing/user_events_status"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/enable"; +const char *trace_file = "/sys/kernel/tracing/trace"; +const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; static inline int status_check(char *status_page, int status_bit) { diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 8b4c7879d5a7..31505642aa9b 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -18,10 +18,10 @@ #include "../kselftest_harness.h" -const char *data_file = "/sys/kernel/debug/tracing/user_events_data"; -const char *status_file = "/sys/kernel/debug/tracing/user_events_status"; -const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id"; -const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format"; +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *status_file = "/sys/kernel/tracing/user_events_status"; +const char *id_file = "/sys/kernel/tracing/events/user_events/__test_event/id"; +const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; struct event { __u32 index; -- GitLab From d1c27c55427e3fe54c1bc22bd4d40fc21ff5406c Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Mon, 13 Mar 2023 15:17:44 -0600 Subject: [PATCH 1612/5631] leaking_addresses: also skip canonical ftrace path The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing scripts/leaking_addresses.pl only skipped this older debugfs path, so let's add the canonical path as well. Link: https://lkml.kernel.org/r/20230313211746.1541525-2-zwisler@kernel.org Cc: "Tobin C. Harding" Cc: Andrew Morton Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Paolo Bonzini Cc: Shuah Khan Acked-by: Tycho Andersen Reviewed-by: Steven Rostedt (Google) Signed-off-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- scripts/leaking_addresses.pl | 1 + 1 file changed, 1 insertion(+) diff --git a/scripts/leaking_addresses.pl b/scripts/leaking_addresses.pl index 8f636a23bc3f..e695634d153d 100755 --- a/scripts/leaking_addresses.pl +++ b/scripts/leaking_addresses.pl @@ -61,6 +61,7 @@ my @skip_abs = ( '/proc/device-tree', '/proc/1/syscall', '/sys/firmware/devicetree', + '/sys/kernel/tracing/trace_pipe', '/sys/kernel/debug/tracing/trace_pipe', '/sys/kernel/security/apparmor/revision'); -- GitLab From c2f92e8b2d24615acda3fc571180d8b44a710df5 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Mon, 13 Mar 2023 15:17:45 -0600 Subject: [PATCH 1613/5631] tools/kvm_stat: use canonical ftrace path The canonical location for the tracefs filesystem is at /sys/kernel/tracing. But, from Documentation/trace/ftrace.rst: Before 4.1, all ftrace tracing control files were within the debugfs file system, which is typically located at /sys/kernel/debug/tracing. For backward compatibility, when mounting the debugfs file system, the tracefs file system will be automatically mounted at: /sys/kernel/debug/tracing A comment in kvm_stat still refers to this older debugfs path, so let's update it to avoid confusion. Link: https://lkml.kernel.org/r/20230313211746.1541525-3-zwisler@kernel.org Cc: "Tobin C. Harding" Cc: Andrew Morton Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Shuah Khan Cc: Tycho Andersen Acked-by: Paolo Bonzini Reviewed-by: Steven Rostedt (Google) Reviewed-by: Mukesh Ojha Signed-off-by: Ross Zwisler Signed-off-by: Steven Rostedt (Google) --- tools/kvm/kvm_stat/kvm_stat | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 6f28180ffeea..15bf00e79e3f 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -627,7 +627,7 @@ class TracepointProvider(Provider): name)'. All available events have directories under - /sys/kernel/debug/tracing/events/ which export information + /sys/kernel/tracing/events/ which export information about the specific event. Therefore, listing the dirs gives us a list of all available events. -- GitLab From 80a76994b2d88161697bd92b8b6367d9040dbe2a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 28 Mar 2023 14:51:56 -0400 Subject: [PATCH 1614/5631] tracing: Add "fields" option to show raw trace event fields The hex, raw and bin formats come from the old PREEMPT_RT patch set latency tracer. That actually gave real alternatives to reading the ascii buffer. But they have started to bit rot and they do not give a good representation of the tracing data. Add "fields" option that will read the trace event fields and parse the data from how the fields are defined: With "fields" = 0 (default) echo 1 > events/sched/sched_switch/enable cat trace -0 [003] d..2. 540.078653: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/3:1 next_pid=83 next_prio=120 kworker/3:1-83 [003] d..2. 540.078860: sched_switch: prev_comm=kworker/3:1 prev_pid=83 prev_prio=120 prev_state=I ==> next_comm=swapper/3 next_pid=0 next_prio=120 -0 [003] d..2. 540.206423: sched_switch: prev_comm=swapper/3 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=sshd next_pid=807 next_prio=120 sshd-807 [003] d..2. 540.206531: sched_switch: prev_comm=sshd prev_pid=807 prev_prio=120 prev_state=S ==> next_comm=swapper/3 next_pid=0 next_prio=120 -0 [001] d..2. 540.206597: sched_switch: prev_comm=swapper/1 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206617: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206678: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 kworker/u16:4-58 [001] d..2. 540.206696: sched_switch: prev_comm=kworker/u16:4 prev_pid=58 prev_prio=120 prev_state=I ==> next_comm=bash next_pid=830 next_prio=120 bash-830 [001] d..2. 540.206713: sched_switch: prev_comm=bash prev_pid=830 prev_prio=120 prev_state=R ==> next_comm=kworker/u16:4 next_pid=58 next_prio=120 echo 1 > options/fields <...>-998 [002] d..2. 538.643732: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/2 prev_state=0x20 (32) prev_prio=0x78 (120) prev_pid=0x3e6 (998) prev_comm=trace-cmd -0 [001] d..2. 538.643806: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/1 bash-830 [001] d..2. 538.644106: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644130: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644180: sched_switch: next_prio=0x78 (120) next_pid=0x3a (58) next_comm=kworker/u16:4 prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash kworker/u16:4-58 [001] d..2. 538.644185: sched_switch: next_prio=0x78 (120) next_pid=0x33e (830) next_comm=bash prev_state=0x80 (128) prev_prio=0x78 (120) prev_pid=0x3a (58) prev_comm=kworker/u16:4 bash-830 [001] d..2. 538.644204: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/1 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x33e (830) prev_comm=bash -0 [003] d..2. 538.644211: sched_switch: next_prio=0x78 (120) next_pid=0x327 (807) next_comm=sshd prev_state=0x0 (0) prev_prio=0x78 (120) prev_pid=0x0 (0) prev_comm=swapper/3 sshd-807 [003] d..2. 538.644340: sched_switch: next_prio=0x78 (120) next_pid=0x0 (0) next_comm=swapper/3 prev_state=0x1 (1) prev_prio=0x78 (120) prev_pid=0x327 (807) prev_comm=sshd It traces the data safely without using the trace print formatting. Link: https://lore.kernel.org/linux-trace-kernel/20230328145156.497651be@gandalf.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/ftrace.rst | 6 ++ kernel/trace/trace.c | 7 +- kernel/trace/trace.h | 2 + kernel/trace/trace_output.c | 168 +++++++++++++++++++++++++++++++++ kernel/trace/trace_output.h | 2 + 5 files changed, 183 insertions(+), 2 deletions(-) diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index b927fb2b94dc..aaebb821912e 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -1027,6 +1027,7 @@ To see what is available, simply cat the file:: nohex nobin noblock + nofields trace_printk annotate nouserstacktrace @@ -1110,6 +1111,11 @@ Here are the available options: block When set, reading trace_pipe will not block when polled. + fields + Print the fields as described by their types. This is a better + option than using hex, bin or raw, as it gives a better parsing + of the content of the event. + trace_printk Can disable trace_printk() from writing into the buffer. diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 937e9676dfd4..076d893d2965 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3726,7 +3726,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, #define STATIC_FMT_BUF_SIZE 128 static char static_fmt_buf[STATIC_FMT_BUF_SIZE]; -static char *trace_iter_expand_format(struct trace_iterator *iter) +char *trace_iter_expand_format(struct trace_iterator *iter) { char *tmp; @@ -4446,8 +4446,11 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; - if (event) + if (event) { + if (tr->trace_flags & TRACE_ITER_FIELDS) + return print_event_fields(iter, event); return event->funcs->trace(iter, sym_flags, event); + } trace_seq_printf(s, "Unknown type %d\n", entry->type); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 616e1aa1c4da..79bdefe9261b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -619,6 +619,7 @@ bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, va_list ap) __printf(2, 0); +char *trace_iter_expand_format(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1199,6 +1200,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, C(HEX, "hex"), \ C(BIN, "bin"), \ C(BLOCK, "block"), \ + C(FIELDS, "fields"), \ C(PRINTK, "trace_printk"), \ C(ANNOTATE, "annotate"), \ C(USERSTACKTRACE, "userstacktrace"), \ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bd475a00f96d..780c6971c944 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -808,6 +808,174 @@ EXPORT_SYMBOL_GPL(unregister_trace_event); * Standard events */ +static void print_array(struct trace_iterator *iter, void *pos, + struct ftrace_event_field *field) +{ + int offset; + int len; + int i; + + offset = *(int *)pos & 0xffff; + len = *(int *)pos >> 16; + + if (field) + offset += field->offset; + + if (offset + len >= iter->ent_size) { + trace_seq_puts(&iter->seq, ""); + return; + } + + for (i = 0; i < len; i++, pos++) { + if (i) + trace_seq_putc(&iter->seq, ','); + trace_seq_printf(&iter->seq, "%02x", *(unsigned char *)pos); + } +} + +static void print_fields(struct trace_iterator *iter, struct trace_event_call *call, + struct list_head *head) +{ + struct ftrace_event_field *field; + int offset; + int len; + int ret; + void *pos; + + list_for_each_entry(field, head, link) { + trace_seq_printf(&iter->seq, " %s=", field->name); + if (field->offset + field->size > iter->ent_size) { + trace_seq_puts(&iter->seq, ""); + continue; + } + pos = (void *)iter->ent + field->offset; + + switch (field->filter_type) { + case FILTER_COMM: + case FILTER_STATIC_STRING: + trace_seq_printf(&iter->seq, "%.*s", field->size, (char *)pos); + break; + case FILTER_RDYN_STRING: + case FILTER_DYN_STRING: + offset = *(int *)pos & 0xffff; + len = *(int *)pos >> 16; + + if (field->filter_type == FILTER_RDYN_STRING) + offset += field->offset; + + if (offset + len >= iter->ent_size) { + trace_seq_puts(&iter->seq, ""); + break; + } + pos = (void *)iter->ent + offset; + trace_seq_printf(&iter->seq, "%.*s", len, (char *)pos); + break; + case FILTER_PTR_STRING: + if (!iter->fmt_size) + trace_iter_expand_format(iter); + pos = *(void **)pos; + ret = strncpy_from_kernel_nofault(iter->fmt, pos, + iter->fmt_size); + if (ret < 0) + trace_seq_printf(&iter->seq, "(0x%px)", pos); + else + trace_seq_printf(&iter->seq, "(0x%px:%s)", + pos, iter->fmt); + break; + case FILTER_TRACE_FN: + pos = *(void **)pos; + trace_seq_printf(&iter->seq, "%pS", pos); + break; + case FILTER_CPU: + case FILTER_OTHER: + switch (field->size) { + case 1: + if (isprint(*(char *)pos)) { + trace_seq_printf(&iter->seq, "'%c'", + *(unsigned char *)pos); + } + trace_seq_printf(&iter->seq, "(%d)", + *(unsigned char *)pos); + break; + case 2: + trace_seq_printf(&iter->seq, "0x%x (%d)", + *(unsigned short *)pos, + *(unsigned short *)pos); + break; + case 4: + /* dynamic array info is 4 bytes */ + if (strstr(field->type, "__data_loc")) { + print_array(iter, pos, NULL); + break; + } + + if (strstr(field->type, "__rel_loc")) { + print_array(iter, pos, field); + break; + } + + trace_seq_printf(&iter->seq, "0x%x (%d)", + *(unsigned int *)pos, + *(unsigned int *)pos); + break; + case 8: + trace_seq_printf(&iter->seq, "0x%llx (%lld)", + *(unsigned long long *)pos, + *(unsigned long long *)pos); + break; + default: + trace_seq_puts(&iter->seq, ""); + break; + } + break; + default: + trace_seq_puts(&iter->seq, ""); + } + } + trace_seq_putc(&iter->seq, '\n'); +} + +enum print_line_t print_event_fields(struct trace_iterator *iter, + struct trace_event *event) +{ + struct trace_event_call *call; + struct list_head *head; + + /* ftrace defined events have separate call structures */ + if (event->type <= __TRACE_LAST_TYPE) { + bool found = false; + + down_read(&trace_event_sem); + list_for_each_entry(call, &ftrace_events, list) { + if (call->event.type == event->type) { + found = true; + break; + } + /* No need to search all events */ + if (call->event.type > __TRACE_LAST_TYPE) + break; + } + up_read(&trace_event_sem); + if (!found) { + trace_seq_printf(&iter->seq, "UNKNOWN TYPE %d\n", event->type); + goto out; + } + } else { + call = container_of(event, struct trace_event_call, event); + } + head = trace_get_fields(call); + + trace_seq_printf(&iter->seq, "%s:", trace_event_name(call)); + + if (head && !list_empty(head)) + print_fields(iter, call, head); + else + trace_seq_puts(&iter->seq, "No fields found\n"); + + out: + return trace_handle_return(&iter->seq); +} + enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags, struct trace_event *event) { diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index 4c954636caf0..dca40f1f1da4 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -19,6 +19,8 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, extern void trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset); extern int trace_print_context(struct trace_iterator *iter); extern int trace_print_lat_context(struct trace_iterator *iter); +extern enum print_line_t print_event_fields(struct trace_iterator *iter, + struct trace_event *event); extern void trace_event_read_lock(void); extern void trace_event_read_unlock(void); -- GitLab From e5a26a4048eeb9558e5c84f340a989c78db4adf4 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:08 -0700 Subject: [PATCH 1615/5631] tracing/user_events: Split header into uapi and kernel The UAPI parts need to be split out from the kernel parts of user_events now that other parts of the kernel will reference it. Do so by moving the existing include/linux/user_events.h into include/uapi/linux/user_events.h. Link: https://lkml.kernel.org/r/20230328235219.203-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 52 ++++---------------------------- include/uapi/linux/user_events.h | 48 +++++++++++++++++++++++++++++ kernel/trace/trace_events_user.c | 5 --- 3 files changed, 54 insertions(+), 51 deletions(-) create mode 100644 include/uapi/linux/user_events.h diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 592a3fbed98e..13689589d36e 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -1,54 +1,14 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2021, Microsoft Corporation. + * Copyright (c) 2022, Microsoft Corporation. * * Authors: * Beau Belgrave */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H -#include -#include +#ifndef _LINUX_USER_EVENTS_H +#define _LINUX_USER_EVENTS_H -#ifdef __KERNEL__ -#include -#else -#include -#endif +#include -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" - -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) - -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { - - /* Input: Size of the user_reg structure being used */ - __u32 size; - - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; - - /* Output: Bitwise index of the event within the status page */ - __u32 status_bit; - - /* Output: Index of the event to use when writing data */ - __u32 write_index; -} __attribute__((__packed__)); - -#define DIAG_IOC_MAGIC '*' - -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) - -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) - -#endif /* _UAPI_LINUX_USER_EVENTS_H */ +#endif /* _LINUX_USER_EVENTS_H */ diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h new file mode 100644 index 000000000000..03f92366068d --- /dev/null +++ b/include/uapi/linux/user_events.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (c) 2021-2022, Microsoft Corporation. + * + * Authors: + * Beau Belgrave + */ +#ifndef _UAPI_LINUX_USER_EVENTS_H +#define _UAPI_LINUX_USER_EVENTS_H + +#include +#include + +#define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_PREFIX "u:" + +/* Create dynamic location entry within a 32-bit value */ +#define DYN_LOC(offset, size) ((size) << 16 | (offset)) + +/* + * Describes an event registration and stores the results of the registration. + * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum + * must set the size and name_args before invocation. + */ +struct user_reg { + + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Bitwise index of the event within the status page */ + __u32 status_bit; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; +} __attribute__((__packed__)); + +#define DIAG_IOC_MAGIC '*' + +/* Request to register a user_event */ +#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg *) + +/* Request to delete a user_event */ +#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char *) + +#endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 908e8a13c675..070551480747 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -19,12 +19,7 @@ #include #include #include -/* Reminder to move to uapi when everything works */ -#ifdef CONFIG_COMPILE_TEST #include -#else -#include -#endif #include "trace.h" #include "trace_dynevent.h" -- GitLab From fd593511cdfc0b0e38af2eb21c99f5154a1d7acf Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:09 -0700 Subject: [PATCH 1616/5631] tracing/user_events: Track fork/exec/exit for mm lifetime During tracefs discussions it was decided instead of requiring a mapping within a user-process to track the lifetime of memory descriptors we should hook the appropriate calls. Do this by adding the minimal stubs required for task fork, exec, and exit. Currently this is just a NOP. Future patches will implement these calls fully. Link: https://lkml.kernel.org/r/20230328235219.203-3-beaub@linux.microsoft.com Suggested-by: Mathieu Desnoyers Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- fs/exec.c | 2 ++ include/linux/sched.h | 5 +++++ include/linux/user_events.h | 18 ++++++++++++++++++ kernel/exit.c | 2 ++ kernel/fork.c | 2 ++ 5 files changed, 29 insertions(+) diff --git a/fs/exec.c b/fs/exec.c index 7c44d0c65b1b..2b0042f8deec 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -1859,6 +1860,7 @@ static int bprm_execve(struct linux_binprm *bprm, current->fs->in_exec = 0; current->in_execve = 0; rseq_execve(current); + user_events_execve(current); acct_update_integrals(current); task_numa_free(current, false); return retval; diff --git a/include/linux/sched.h b/include/linux/sched.h index 63d242164b1a..bf37846e90c2 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -69,6 +69,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct user_event_mm; /* * Task state bitmask. NOTE! These bits are also @@ -1528,6 +1529,10 @@ struct task_struct { union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif +#ifdef CONFIG_USER_EVENTS + struct user_event_mm *user_event_mm; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 13689589d36e..3d747c45d2fa 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -11,4 +11,22 @@ #include +#ifdef CONFIG_USER_EVENTS +struct user_event_mm { +}; +#endif + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ +} + +static inline void user_events_execve(struct task_struct *t) +{ +} + +static inline void user_events_exit(struct task_struct *t) +{ +} + #endif /* _LINUX_USER_EVENTS_H */ diff --git a/kernel/exit.c b/kernel/exit.c index f2afdb0add7c..875d6a134df8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -68,6 +68,7 @@ #include #include #include +#include #include #include @@ -818,6 +819,7 @@ void __noreturn do_exit(long code) coredump_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); + user_events_exit(tsk); validate_creds_for_do_exit(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index d8cda4c6de6c..efb1f2257772 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include @@ -2505,6 +2506,7 @@ static __latent_entropy struct task_struct *copy_process( trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); + user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); -- GitLab From 7235759084a4f8524a46bd2638885ff3b34ce279 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:10 -0700 Subject: [PATCH 1617/5631] tracing/user_events: Use remote writes for event enablement As part of the discussions for user_events aligned with user space tracers, it was determined that user programs should register a aligned value to set or clear a bit when an event becomes enabled. Currently a shared page is being used that requires mmap(). Remove the shared page implementation and move to a user registered address implementation. In this new model during the event registration from user programs 3 new values are specified. The first is the address to update when the event is either enabled or disabled. The second is the bit to set/clear to reflect the event being enabled. The third is the size of the value at the specified address. This allows for a local 32/64-bit value in user programs to support both kernel and user tracers. As an example, setting bit 31 for kernel tracers when the event becomes enabled allows for user tracers to use the other bits for ref counts or other flags. The kernel side updates the bit atomically, user programs need to also update these values atomically. User provided addresses must be aligned on a natural boundary, this allows for single page checking and prevents odd behaviors such as a enable value straddling 2 pages instead of a single page. Currently page faults are only logged, future patches will handle these. Link: https://lkml.kernel.org/r/20230328235219.203-4-beaub@linux.microsoft.com Suggested-by: Mathieu Desnoyers Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 53 ++- include/uapi/linux/user_events.h | 15 +- kernel/trace/Kconfig | 5 +- kernel/trace/trace_events_user.c | 586 ++++++++++++++++++++++++------- 4 files changed, 517 insertions(+), 142 deletions(-) diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 3d747c45d2fa..0120b3dd5b03 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -9,13 +9,63 @@ #ifndef _LINUX_USER_EVENTS_H #define _LINUX_USER_EVENTS_H +#include +#include +#include +#include #include #ifdef CONFIG_USER_EVENTS struct user_event_mm { + struct list_head link; + struct list_head enablers; + struct mm_struct *mm; + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; }; -#endif +extern void user_event_mm_dup(struct task_struct *t, + struct user_event_mm *old_mm); + +extern void user_event_mm_remove(struct task_struct *t); + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ + struct user_event_mm *old_mm; + + if (!t || !current->user_event_mm) + return; + + old_mm = current->user_event_mm; + + if (clone_flags & CLONE_VM) { + t->user_event_mm = old_mm; + refcount_inc(&old_mm->tasks); + return; + } + + user_event_mm_dup(t, old_mm); +} + +static inline void user_events_execve(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} + +static inline void user_events_exit(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} +#else static inline void user_events_fork(struct task_struct *t, unsigned long clone_flags) { @@ -28,5 +78,6 @@ static inline void user_events_execve(struct task_struct *t) static inline void user_events_exit(struct task_struct *t) { } +#endif /* CONFIG_USER_EVENTS */ #endif /* _LINUX_USER_EVENTS_H */ diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index 03f92366068d..22521bc622db 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -27,12 +27,21 @@ struct user_reg { /* Input: Size of the user_reg structure being used */ __u32 size; + /* Input: Bit in enable address to use */ + __u8 enable_bit; + + /* Input: Enable size in bytes at address */ + __u8 enable_size; + + /* Input: Flags for future use, set to 0 */ + __u16 flags; + + /* Input: Address to update when enabled */ + __u64 enable_addr; + /* Input: Pointer to string with event name, description and flags */ __u64 name_args; - /* Output: Bitwise index of the event within the status page */ - __u32 status_bit; - /* Output: Index of the event to use when writing data */ __u32 write_index; } __attribute__((__packed__)); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 5b1e7fa41ca8..c7020e071bf9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -798,9 +798,10 @@ config USER_EVENTS can be used like an existing kernel trace event. User trace events are generated by writing to a tracefs file. User processes can determine if their tracing events should be - generated by memory mapping a tracefs file and checking for - an associated byte being non-zero. + generated by registering a value and bit with the kernel + that reflects when it is enabled or not. + See Documentation/trace/user_events.rst. If in doubt, say N. config HIST_TRIGGERS diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 070551480747..553a82ee7aeb 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "trace.h" #include "trace_dynevent.h" @@ -29,34 +30,11 @@ #define FIELD_DEPTH_NAME 1 #define FIELD_DEPTH_SIZE 2 -/* - * Limits how many trace_event calls user processes can create: - * Must be a power of two of PAGE_SIZE. - */ -#define MAX_PAGE_ORDER 0 -#define MAX_PAGES (1 << MAX_PAGE_ORDER) -#define MAX_BYTES (MAX_PAGES * PAGE_SIZE) -#define MAX_EVENTS (MAX_BYTES * 8) - /* Limit how long of an event name plus args within the subsystem. */ #define MAX_EVENT_DESC 512 #define EVENT_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 -/* - * The MAP_STATUS_* macros are used for taking a index and determining the - * appropriate byte and the bit in the byte to set/reset for an event. - * - * The lower 3 bits of the index decide which bit to set. - * The remaining upper bits of the index decide which byte to use for the bit. - * - * This is used when an event has a probe attached/removed to reflect live - * status of the event wanting tracing or not to user-programs via shared - * memory maps. - */ -#define MAP_STATUS_BYTE(index) ((index) >> 3) -#define MAP_STATUS_MASK(index) BIT((index) & 7) - /* * Internal bits (kernel side only) to keep track of connected probes: * These are used when status is requested in text form about an event. These @@ -70,20 +48,14 @@ #define EVENT_STATUS_OTHER BIT(7) /* - * Stores the pages, tables, and locks for a group of events. - * Each logical grouping of events has its own group, with a - * matching page for status checks within user programs. This - * allows for isolation of events to user programs by various - * means. + * Stores the system name, tables, and locks for a group of events. This + * allows isolation for events by various means. */ struct user_event_group { - struct page *pages; - char *register_page_data; char *system_name; struct hlist_node node; struct mutex reg_mutex; DECLARE_HASHTABLE(register_table, 8); - DECLARE_BITMAP(page_bitmap, MAX_EVENTS); }; /* Group for init_user_ns mapping, top-most group */ @@ -106,12 +78,34 @@ struct user_event { struct list_head fields; struct list_head validators; refcount_t refcnt; - int index; - int flags; int min_size; char status; }; +/* + * Stores per-mm/event properties that enable an address to be + * updated properly for each task. As tasks are forked, we use + * these to track enablement sites that are tied to an event. + */ +struct user_event_enabler { + struct list_head link; + struct user_event *event; + unsigned long addr; + + /* Track enable bit, flags, etc. Aligned for bitops. */ + unsigned int values; +}; + +/* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ +#define ENABLE_VAL_BIT_MASK 0x3F + +/* Only duplicate the bit value */ +#define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK + +/* Global list of memory descriptors using user_events */ +static LIST_HEAD(user_event_mms); +static DEFINE_SPINLOCK(user_event_mms_lock); + /* * Stores per-file events references, as users register events * within a file this structure is modified and freed via RCU. @@ -145,33 +139,17 @@ static int user_event_parse(struct user_event_group *group, char *name, char *args, char *flags, struct user_event **newuser); +static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm); +static struct user_event_mm *user_event_mm_get_all(struct user_event *user); +static void user_event_mm_put(struct user_event_mm *mm); + static u32 user_event_key(char *name) { return jhash(name, strlen(name), 0); } -static void set_page_reservations(char *pages, bool set) -{ - int page; - - for (page = 0; page < MAX_PAGES; ++page) { - void *addr = pages + (PAGE_SIZE * page); - - if (set) - SetPageReserved(virt_to_page(addr)); - else - ClearPageReserved(virt_to_page(addr)); - } -} - static void user_event_group_destroy(struct user_event_group *group) { - if (group->register_page_data) - set_page_reservations(group->register_page_data, false); - - if (group->pages) - __free_pages(group->pages, MAX_PAGE_ORDER); - kfree(group->system_name); kfree(group); } @@ -242,19 +220,6 @@ static struct user_event_group if (!group->system_name) goto error; - group->pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, MAX_PAGE_ORDER); - - if (!group->pages) - goto error; - - group->register_page_data = page_address(group->pages); - - set_page_reservations(group->register_page_data, true); - - /* Zero all bits beside 0 (which is reserved for failures) */ - bitmap_zero(group->page_bitmap, MAX_EVENTS); - set_bit(0, group->page_bitmap); - mutex_init(&group->reg_mutex); hash_init(group->register_table); @@ -266,20 +231,367 @@ static struct user_event_group return NULL; }; -static __always_inline -void user_event_register_set(struct user_event *user) +static void user_event_enabler_destroy(struct user_event_enabler *enabler) +{ + list_del_rcu(&enabler->link); + + /* No longer tracking the event via the enabler */ + refcount_dec(&enabler->event->refcnt); + + kfree(enabler); +} + +static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr) +{ + bool unlocked; + int ret; + + mmap_read_lock(mm->mm); + + /* Ensure MM has tasks, cannot use after exit_mm() */ + if (refcount_read(&mm->tasks) == 0) { + ret = -ENOENT; + goto out; + } + + ret = fixup_user_fault(mm->mm, uaddr, FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + &unlocked); +out: + mmap_read_unlock(mm->mm); + + return ret; +} + +static int user_event_enabler_write(struct user_event_mm *mm, + struct user_event_enabler *enabler) +{ + unsigned long uaddr = enabler->addr; + unsigned long *ptr; + struct page *page; + void *kaddr; + int ret; + + lockdep_assert_held(&event_mutex); + mmap_assert_locked(mm->mm); + + /* Ensure MM has tasks, cannot use after exit_mm() */ + if (refcount_read(&mm->tasks) == 0) + return -ENOENT; + + ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT, + &page, NULL, NULL); + + if (ret <= 0) { + pr_warn("user_events: Enable write failed\n"); + return -EFAULT; + } + + kaddr = kmap_local_page(page); + ptr = kaddr + (uaddr & ~PAGE_MASK); + + /* Update bit atomically, user tracers must be atomic as well */ + if (enabler->event && enabler->event->status) + set_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + else + clear_bit(enabler->values & ENABLE_VAL_BIT_MASK, ptr); + + kunmap_local(kaddr); + unpin_user_pages_dirty_lock(&page, 1, true); + + return 0; +} + +static void user_event_enabler_update(struct user_event *user) +{ + struct user_event_enabler *enabler; + struct user_event_mm *mm = user_event_mm_get_all(user); + struct user_event_mm *next; + + while (mm) { + next = mm->next; + mmap_read_lock(mm->mm); + rcu_read_lock(); + + list_for_each_entry_rcu(enabler, &mm->enablers, link) + if (enabler->event == user) + user_event_enabler_write(mm, enabler); + + rcu_read_unlock(); + mmap_read_unlock(mm->mm); + user_event_mm_put(mm); + mm = next; + } +} + +static bool user_event_enabler_dup(struct user_event_enabler *orig, + struct user_event_mm *mm) +{ + struct user_event_enabler *enabler; + + enabler = kzalloc(sizeof(*enabler), GFP_NOWAIT); + + if (!enabler) + return false; + + enabler->event = orig->event; + enabler->addr = orig->addr; + + /* Only dup part of value (ignore future flags, etc) */ + enabler->values = orig->values & ENABLE_VAL_DUP_MASK; + + refcount_inc(&enabler->event->refcnt); + list_add_rcu(&enabler->link, &mm->enablers); + + return true; +} + +static struct user_event_mm *user_event_mm_get(struct user_event_mm *mm) +{ + refcount_inc(&mm->refcnt); + + return mm; +} + +static struct user_event_mm *user_event_mm_get_all(struct user_event *user) +{ + struct user_event_mm *found = NULL; + struct user_event_enabler *enabler; + struct user_event_mm *mm; + + /* + * We do not want to block fork/exec while enablements are being + * updated, so we use RCU to walk the current tasks that have used + * user_events ABI for 1 or more events. Each enabler found in each + * task that matches the event being updated has a write to reflect + * the kernel state back into the process. Waits/faults must not occur + * during this. So we scan the list under RCU for all the mm that have + * the event within it. This is needed because mm_read_lock() can wait. + * Each user mm returned has a ref inc to handle remove RCU races. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(mm, &user_event_mms, link) + list_for_each_entry_rcu(enabler, &mm->enablers, link) + if (enabler->event == user) { + mm->next = found; + found = user_event_mm_get(mm); + break; + } + + rcu_read_unlock(); + + return found; +} + +static struct user_event_mm *user_event_mm_create(struct task_struct *t) +{ + struct user_event_mm *user_mm; + unsigned long flags; + + user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL); + + if (!user_mm) + return NULL; + + user_mm->mm = t->mm; + INIT_LIST_HEAD(&user_mm->enablers); + refcount_set(&user_mm->refcnt, 1); + refcount_set(&user_mm->tasks, 1); + + spin_lock_irqsave(&user_event_mms_lock, flags); + list_add_rcu(&user_mm->link, &user_event_mms); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + t->user_event_mm = user_mm; + + /* + * The lifetime of the memory descriptor can slightly outlast + * the task lifetime if a ref to the user_event_mm is taken + * between list_del_rcu() and call_rcu(). Therefore we need + * to take a reference to it to ensure it can live this long + * under this corner case. This can also occur in clones that + * outlast the parent. + */ + mmgrab(user_mm->mm); + + return user_mm; +} + +static struct user_event_mm *current_user_event_mm(void) +{ + struct user_event_mm *user_mm = current->user_event_mm; + + if (user_mm) + goto inc; + + user_mm = user_event_mm_create(current); + + if (!user_mm) + goto error; +inc: + refcount_inc(&user_mm->refcnt); +error: + return user_mm; +} + +static void user_event_mm_destroy(struct user_event_mm *mm) +{ + struct user_event_enabler *enabler, *next; + + list_for_each_entry_safe(enabler, next, &mm->enablers, link) + user_event_enabler_destroy(enabler); + + mmdrop(mm->mm); + kfree(mm); +} + +static void user_event_mm_put(struct user_event_mm *mm) +{ + if (mm && refcount_dec_and_test(&mm->refcnt)) + user_event_mm_destroy(mm); +} + +static void delayed_user_event_mm_put(struct work_struct *work) +{ + struct user_event_mm *mm; + + mm = container_of(to_rcu_work(work), struct user_event_mm, put_rwork); + user_event_mm_put(mm); +} + +void user_event_mm_remove(struct task_struct *t) { - int i = user->index; + struct user_event_mm *mm; + unsigned long flags; + + might_sleep(); + + mm = t->user_event_mm; + t->user_event_mm = NULL; + + /* Clone will increment the tasks, only remove if last clone */ + if (!refcount_dec_and_test(&mm->tasks)) + return; + + /* Remove the mm from the list, so it can no longer be enabled */ + spin_lock_irqsave(&user_event_mms_lock, flags); + list_del_rcu(&mm->link); + spin_unlock_irqrestore(&user_event_mms_lock, flags); + + /* + * We need to wait for currently occurring writes to stop within + * the mm. This is required since exit_mm() snaps the current rss + * stats and clears them. On the final mmdrop(), check_mm() will + * report a bug if these increment. + * + * All writes/pins are done under mmap_read lock, take the write + * lock to ensure in-progress faults have completed. Faults that + * are pending but yet to run will check the task count and skip + * the fault since the mm is going away. + */ + mmap_write_lock(mm->mm); + mmap_write_unlock(mm->mm); - user->group->register_page_data[MAP_STATUS_BYTE(i)] |= MAP_STATUS_MASK(i); + /* + * Put for mm must be done after RCU delay to handle new refs in + * between the list_del_rcu() and now. This ensures any get refs + * during rcu_read_lock() are accounted for during list removal. + * + * CPU A | CPU B + * --------------------------------------------------------------- + * user_event_mm_remove() | rcu_read_lock(); + * list_del_rcu() | list_for_each_entry_rcu(); + * call_rcu() | refcount_inc(); + * . | rcu_read_unlock(); + * schedule_work() | . + * user_event_mm_put() | . + * + * mmdrop() cannot be called in the softirq context of call_rcu() + * so we use a work queue after call_rcu() to run within. + */ + INIT_RCU_WORK(&mm->put_rwork, delayed_user_event_mm_put); + queue_rcu_work(system_wq, &mm->put_rwork); } -static __always_inline -void user_event_register_clear(struct user_event *user) +void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) { - int i = user->index; + struct user_event_mm *mm = user_event_mm_create(t); + struct user_event_enabler *enabler; - user->group->register_page_data[MAP_STATUS_BYTE(i)] &= ~MAP_STATUS_MASK(i); + if (!mm) + return; + + rcu_read_lock(); + + list_for_each_entry_rcu(enabler, &old_mm->enablers, link) + if (!user_event_enabler_dup(enabler, mm)) + goto error; + + rcu_read_unlock(); + + return; +error: + rcu_read_unlock(); + user_event_mm_remove(t); +} + +static struct user_event_enabler +*user_event_enabler_create(struct user_reg *reg, struct user_event *user, + int *write_result) +{ + struct user_event_enabler *enabler; + struct user_event_mm *user_mm; + unsigned long uaddr = (unsigned long)reg->enable_addr; + + user_mm = current_user_event_mm(); + + if (!user_mm) + return NULL; + + enabler = kzalloc(sizeof(*enabler), GFP_KERNEL); + + if (!enabler) + goto out; + + enabler->event = user; + enabler->addr = uaddr; + enabler->values = reg->enable_bit; +retry: + /* Prevents state changes from racing with new enablers */ + mutex_lock(&event_mutex); + + /* Attempt to reflect the current state within the process */ + mmap_read_lock(user_mm->mm); + *write_result = user_event_enabler_write(user_mm, enabler); + mmap_read_unlock(user_mm->mm); + + /* + * If the write works, then we will track the enabler. A ref to the + * underlying user_event is held by the enabler to prevent it going + * away while the enabler is still in use by a process. The ref is + * removed when the enabler is destroyed. This means a event cannot + * be forcefully deleted from the system until all tasks using it + * exit or run exec(), which includes forks and clones. + */ + if (!*write_result) { + refcount_inc(&enabler->event->refcnt); + list_add_rcu(&enabler->link, &user_mm->enablers); + } + + mutex_unlock(&event_mutex); + + if (*write_result) { + /* Attempt to fault-in and retry if it worked */ + if (!user_event_mm_fault_in(user_mm, uaddr)) + goto retry; + + kfree(enabler); + enabler = NULL; + } +out: + user_event_mm_put(user_mm); + + return enabler; } static __always_inline __must_check @@ -824,9 +1136,6 @@ static int destroy_user_event(struct user_event *user) return ret; dyn_event_remove(&user->devent); - - user_event_register_clear(user); - clear_bit(user->index, user->group->page_bitmap); hash_del(&user->node); user_event_destroy_validators(user); @@ -972,9 +1281,9 @@ static void user_event_perf(struct user_event *user, struct iov_iter *i, #endif /* - * Update the register page that is shared between user processes. + * Update the enabled bit among all user processes. */ -static void update_reg_page_for(struct user_event *user) +static void update_enable_bit_for(struct user_event *user) { struct tracepoint *tp = &user->tracepoint; char status = 0; @@ -1005,12 +1314,9 @@ static void update_reg_page_for(struct user_event *user) rcu_read_unlock_sched(); } - if (status) - user_event_register_set(user); - else - user_event_register_clear(user); - user->status = status; + + user_event_enabler_update(user); } /* @@ -1067,10 +1373,10 @@ static int user_event_reg(struct trace_event_call *call, return ret; inc: refcount_inc(&user->refcnt); - update_reg_page_for(user); + update_enable_bit_for(user); return 0; dec: - update_reg_page_for(user); + update_enable_bit_for(user); refcount_dec(&user->refcnt); return 0; } @@ -1266,7 +1572,6 @@ static int user_event_parse(struct user_event_group *group, char *name, struct user_event **newuser) { int ret; - int index; u32 key; struct user_event *user; @@ -1285,11 +1590,6 @@ static int user_event_parse(struct user_event_group *group, char *name, return 0; } - index = find_first_zero_bit(group->page_bitmap, MAX_EVENTS); - - if (index == MAX_EVENTS) - return -EMFILE; - user = kzalloc(sizeof(*user), GFP_KERNEL); if (!user) @@ -1335,14 +1635,11 @@ static int user_event_parse(struct user_event_group *group, char *name, if (ret) goto put_user_lock; - user->index = index; - /* Ensure we track self ref and caller ref (2) */ refcount_set(&user->refcnt, 2); dyn_event_init(&user->devent, &user_event_dops); dyn_event_add(&user->devent, &user->call); - set_bit(user->index, group->page_bitmap); hash_add(group->register_table, &user->node, key); mutex_unlock(&event_mutex); @@ -1559,6 +1856,37 @@ static long user_reg_get(struct user_reg __user *ureg, struct user_reg *kreg) if (ret) return ret; + /* Ensure no flags, since we don't support any yet */ + if (kreg->flags != 0) + return -EINVAL; + + /* Ensure supported size */ + switch (kreg->enable_size) { + case 4: + /* 32-bit */ + break; +#if BITS_PER_LONG >= 64 + case 8: + /* 64-bit */ + break; +#endif + default: + return -EINVAL; + } + + /* Ensure natural alignment */ + if (kreg->enable_addr % kreg->enable_size) + return -EINVAL; + + /* Ensure bit range for size */ + if (kreg->enable_bit > (kreg->enable_size * BITS_PER_BYTE) - 1) + return -EINVAL; + + /* Ensure accessible */ + if (!access_ok((const void __user *)(uintptr_t)kreg->enable_addr, + kreg->enable_size)) + return -EFAULT; + kreg->size = size; return 0; @@ -1573,8 +1901,10 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, struct user_reg __user *ureg = (struct user_reg __user *)uarg; struct user_reg reg; struct user_event *user; + struct user_event_enabler *enabler; char *name; long ret; + int write_result; ret = user_reg_get(ureg, ®); @@ -1605,8 +1935,28 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, if (ret < 0) return ret; + /* + * user_events_ref_add succeeded: + * At this point we have a user_event, it's lifetime is bound by the + * reference count, not this file. If anything fails, the user_event + * still has a reference until the file is released. During release + * any remaining references (from user_events_ref_add) are decremented. + * + * Attempt to create an enabler, which too has a lifetime tied in the + * same way for the event. Once the task that caused the enabler to be + * created exits or issues exec() then the enablers it has created + * will be destroyed and the ref to the event will be decremented. + */ + enabler = user_event_enabler_create(®, user, &write_result); + + if (!enabler) + return -ENOMEM; + + /* Write failed/faulted, give error back to caller */ + if (write_result) + return write_result; + put_user((u32)ret, &ureg->write_index); - put_user(user->index, &ureg->status_bit); return 0; } @@ -1720,38 +2070,6 @@ static const struct file_operations user_data_fops = { .release = user_events_release, }; -static struct user_event_group *user_status_group(struct file *file) -{ - struct seq_file *m = file->private_data; - - if (!m) - return NULL; - - return m->private; -} - -/* - * Maps the shared page into the user process for checking if event is enabled. - */ -static int user_status_mmap(struct file *file, struct vm_area_struct *vma) -{ - char *pages; - struct user_event_group *group = user_status_group(file); - unsigned long size = vma->vm_end - vma->vm_start; - - if (size != MAX_BYTES) - return -EINVAL; - - if (!group) - return -EINVAL; - - pages = group->register_page_data; - - return remap_pfn_range(vma, vma->vm_start, - virt_to_phys(pages) >> PAGE_SHIFT, - size, vm_get_page_prot(VM_READ)); -} - static void *user_seq_start(struct seq_file *m, loff_t *pos) { if (*pos) @@ -1775,7 +2093,7 @@ static int user_seq_show(struct seq_file *m, void *p) struct user_event_group *group = m->private; struct user_event *user; char status; - int i, active = 0, busy = 0, flags; + int i, active = 0, busy = 0; if (!group) return -EINVAL; @@ -1784,11 +2102,10 @@ static int user_seq_show(struct seq_file *m, void *p) hash_for_each(group->register_table, i, user, node) { status = user->status; - flags = user->flags; - seq_printf(m, "%d:%s", user->index, EVENT_NAME(user)); + seq_printf(m, "%s", EVENT_NAME(user)); - if (flags != 0 || status != 0) + if (status != 0) seq_puts(m, " #"); if (status != 0) { @@ -1811,7 +2128,6 @@ static int user_seq_show(struct seq_file *m, void *p) seq_puts(m, "\n"); seq_printf(m, "Active: %d\n", active); seq_printf(m, "Busy: %d\n", busy); - seq_printf(m, "Max: %ld\n", MAX_EVENTS); return 0; } @@ -1847,7 +2163,6 @@ static int user_status_open(struct inode *node, struct file *file) static const struct file_operations user_status_fops = { .open = user_status_open, - .mmap = user_status_mmap, .read = seq_read, .llseek = seq_lseek, .release = seq_release, @@ -1868,8 +2183,7 @@ static int create_user_tracefs(void) goto err; } - /* mmap with MAP_SHARED requires writable fd */ - emmap = tracefs_create_file("user_events_status", TRACE_MODE_WRITE, + emmap = tracefs_create_file("user_events_status", TRACE_MODE_READ, NULL, NULL, &user_status_fops); if (!emmap) { -- GitLab From 81f8fb65499817a4d1d5d66d9e74a903061ce637 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:11 -0700 Subject: [PATCH 1618/5631] tracing/user_events: Fixup enable faults asyncly When events are enabled within the various tracing facilities, such as ftrace/perf, the event_mutex is held. As events are enabled pages are accessed. We do not want page faults to occur under this lock. Instead queue the fault to a workqueue to be handled in a process context safe way without the lock. The enable address is marked faulting while the async fault-in occurs. This ensures that we don't attempt to fault-in more than is necessary. Once the page has been faulted in, an address write is re-attempted. If the page couldn't fault-in, then we wait until the next time the event is enabled to prevent any potential infinite loops. Link: https://lkml.kernel.org/r/20230328235219.203-5-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 120 +++++++++++++++++++++++++++++-- 1 file changed, 114 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 553a82ee7aeb..86bda1660536 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -99,9 +99,23 @@ struct user_event_enabler { /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ #define ENABLE_VAL_BIT_MASK 0x3F +/* Bit 6 is for faulting status of enablement */ +#define ENABLE_VAL_FAULTING_BIT 6 + /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK +#define ENABLE_BITOPS(e) ((unsigned long *)&(e)->values) + +/* Used for asynchronous faulting in of pages */ +struct user_event_enabler_fault { + struct work_struct work; + struct user_event_mm *mm; + struct user_event_enabler *enabler; +}; + +static struct kmem_cache *fault_cache; + /* Global list of memory descriptors using user_events */ static LIST_HEAD(user_event_mms); static DEFINE_SPINLOCK(user_event_mms_lock); @@ -263,7 +277,85 @@ static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr) } static int user_event_enabler_write(struct user_event_mm *mm, - struct user_event_enabler *enabler) + struct user_event_enabler *enabler, + bool fixup_fault); + +static void user_event_enabler_fault_fixup(struct work_struct *work) +{ + struct user_event_enabler_fault *fault = container_of( + work, struct user_event_enabler_fault, work); + struct user_event_enabler *enabler = fault->enabler; + struct user_event_mm *mm = fault->mm; + unsigned long uaddr = enabler->addr; + int ret; + + ret = user_event_mm_fault_in(mm, uaddr); + + if (ret && ret != -ENOENT) { + struct user_event *user = enabler->event; + + pr_warn("user_events: Fault for mm: 0x%pK @ 0x%llx event: %s\n", + mm->mm, (unsigned long long)uaddr, EVENT_NAME(user)); + } + + /* Prevent state changes from racing */ + mutex_lock(&event_mutex); + + /* + * If we managed to get the page, re-issue the write. We do not + * want to get into a possible infinite loop, which is why we only + * attempt again directly if the page came in. If we couldn't get + * the page here, then we will try again the next time the event is + * enabled/disabled. + */ + clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)); + + if (!ret) { + mmap_read_lock(mm->mm); + user_event_enabler_write(mm, enabler, true); + mmap_read_unlock(mm->mm); + } + + mutex_unlock(&event_mutex); + + /* In all cases we no longer need the mm or fault */ + user_event_mm_put(mm); + kmem_cache_free(fault_cache, fault); +} + +static bool user_event_enabler_queue_fault(struct user_event_mm *mm, + struct user_event_enabler *enabler) +{ + struct user_event_enabler_fault *fault; + + fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN); + + if (!fault) + return false; + + INIT_WORK(&fault->work, user_event_enabler_fault_fixup); + fault->mm = user_event_mm_get(mm); + fault->enabler = enabler; + + /* Don't try to queue in again while we have a pending fault */ + set_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)); + + if (!schedule_work(&fault->work)) { + /* Allow another attempt later */ + clear_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)); + + user_event_mm_put(mm); + kmem_cache_free(fault_cache, fault); + + return false; + } + + return true; +} + +static int user_event_enabler_write(struct user_event_mm *mm, + struct user_event_enabler *enabler, + bool fixup_fault) { unsigned long uaddr = enabler->addr; unsigned long *ptr; @@ -278,11 +370,19 @@ static int user_event_enabler_write(struct user_event_mm *mm, if (refcount_read(&mm->tasks) == 0) return -ENOENT; + if (unlikely(test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))) + return -EBUSY; + ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT, &page, NULL, NULL); - if (ret <= 0) { - pr_warn("user_events: Enable write failed\n"); + if (unlikely(ret <= 0)) { + if (!fixup_fault) + return -EFAULT; + + if (!user_event_enabler_queue_fault(mm, enabler)) + pr_warn("user_events: Unable to queue fault handler\n"); + return -EFAULT; } @@ -314,7 +414,7 @@ static void user_event_enabler_update(struct user_event *user) list_for_each_entry_rcu(enabler, &mm->enablers, link) if (enabler->event == user) - user_event_enabler_write(mm, enabler); + user_event_enabler_write(mm, enabler, true); rcu_read_unlock(); mmap_read_unlock(mm->mm); @@ -562,7 +662,7 @@ static struct user_event_enabler /* Attempt to reflect the current state within the process */ mmap_read_lock(user_mm->mm); - *write_result = user_event_enabler_write(user_mm, enabler); + *write_result = user_event_enabler_write(user_mm, enabler, false); mmap_read_unlock(user_mm->mm); /* @@ -2201,16 +2301,24 @@ static int __init trace_events_user_init(void) { int ret; + fault_cache = KMEM_CACHE(user_event_enabler_fault, 0); + + if (!fault_cache) + return -ENOMEM; + init_group = user_event_group_create(&init_user_ns); - if (!init_group) + if (!init_group) { + kmem_cache_destroy(fault_cache); return -ENOMEM; + } ret = create_user_tracefs(); if (ret) { pr_warn("user_events could not register with tracefs\n"); user_event_group_destroy(init_group); + kmem_cache_destroy(fault_cache); init_group = NULL; return ret; } -- GitLab From dcb8177c13953872c9e5ce4a99b63a87a3c2f683 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:12 -0700 Subject: [PATCH 1619/5631] tracing/user_events: Add ioctl for disabling addresses Enablements are now tracked by the lifetime of the task/mm. User processes need to be able to disable their addresses if tracing is requested to be turned off. Before unmapping the page would suffice. However, we now need a stronger contract. Add an ioctl to enable this. A new flag bit is added, freeing, to user_event_enabler to ensure that if the event is attempted to be removed while a fault is being handled that the remove is delayed until after the fault is reattempted. Link: https://lkml.kernel.org/r/20230328235219.203-6-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 24 ++++++++ kernel/trace/trace_events_user.c | 97 +++++++++++++++++++++++++++++++- 2 files changed, 119 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index 22521bc622db..3e7275e3234a 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -46,6 +46,27 @@ struct user_reg { __u32 write_index; } __attribute__((__packed__)); +/* + * Describes an event unregister, callers must set the size, address and bit. + * This structure is passed to the DIAG_IOCSUNREG ioctl to disable bit updates. + */ +struct user_unreg { + /* Input: Size of the user_unreg structure being used */ + __u32 size; + + /* Input: Bit to unregister */ + __u8 disable_bit; + + /* Input: Reserved, set to 0 */ + __u8 __reserved; + + /* Input: Reserved, set to 0 */ + __u16 __reserved2; + + /* Input: Address to unregister */ + __u64 disable_addr; +} __attribute__((__packed__)); + #define DIAG_IOC_MAGIC '*' /* Request to register a user_event */ @@ -54,4 +75,7 @@ struct user_reg { /* Request to delete a user_event */ #define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char *) +/* Requests to unregister a user_event */ +#define DIAG_IOCSUNREG _IOW(DIAG_IOC_MAGIC, 2, struct user_unreg*) + #endif /* _UAPI_LINUX_USER_EVENTS_H */ diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 86bda1660536..f88bab3f1fe1 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -102,6 +102,9 @@ struct user_event_enabler { /* Bit 6 is for faulting status of enablement */ #define ENABLE_VAL_FAULTING_BIT 6 +/* Bit 7 is for freeing status of enablement */ +#define ENABLE_VAL_FREEING_BIT 7 + /* Only duplicate the bit value */ #define ENABLE_VAL_DUP_MASK ENABLE_VAL_BIT_MASK @@ -301,6 +304,12 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) /* Prevent state changes from racing */ mutex_lock(&event_mutex); + /* User asked for enabler to be removed during fault */ + if (test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler))) { + user_event_enabler_destroy(enabler); + goto out; + } + /* * If we managed to get the page, re-issue the write. We do not * want to get into a possible infinite loop, which is why we only @@ -315,7 +324,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) user_event_enabler_write(mm, enabler, true); mmap_read_unlock(mm->mm); } - +out: mutex_unlock(&event_mutex); /* In all cases we no longer need the mm or fault */ @@ -370,7 +379,8 @@ static int user_event_enabler_write(struct user_event_mm *mm, if (refcount_read(&mm->tasks) == 0) return -ENOENT; - if (unlikely(test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)))) + if (unlikely(test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)) || + test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)))) return -EBUSY; ret = pin_user_pages_remote(mm->mm, uaddr, 1, FOLL_WRITE | FOLL_NOFAULT, @@ -428,6 +438,10 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, { struct user_event_enabler *enabler; + /* Skip pending frees */ + if (unlikely(test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(orig)))) + return true; + enabler = kzalloc(sizeof(*enabler), GFP_NOWAIT); if (!enabler) @@ -2086,6 +2100,79 @@ static long user_events_ioctl_del(struct user_event_file_info *info, return ret; } +static long user_unreg_get(struct user_unreg __user *ureg, + struct user_unreg *kreg) +{ + u32 size; + long ret; + + ret = get_user(size, &ureg->size); + + if (ret) + return ret; + + if (size > PAGE_SIZE) + return -E2BIG; + + if (size < offsetofend(struct user_unreg, disable_addr)) + return -EINVAL; + + ret = copy_struct_from_user(kreg, sizeof(*kreg), ureg, size); + + /* Ensure no reserved values, since we don't support any yet */ + if (kreg->__reserved || kreg->__reserved2) + return -EINVAL; + + return ret; +} + +/* + * Unregisters an enablement address/bit within a task/user mm. + */ +static long user_events_ioctl_unreg(unsigned long uarg) +{ + struct user_unreg __user *ureg = (struct user_unreg __user *)uarg; + struct user_event_mm *mm = current->user_event_mm; + struct user_event_enabler *enabler, *next; + struct user_unreg reg; + long ret; + + ret = user_unreg_get(ureg, ®); + + if (ret) + return ret; + + if (!mm) + return -ENOENT; + + ret = -ENOENT; + + /* + * Flags freeing and faulting are used to indicate if the enabler is in + * use at all. When faulting is set a page-fault is occurring asyncly. + * During async fault if freeing is set, the enabler will be destroyed. + * If no async fault is happening, we can destroy it now since we hold + * the event_mutex during these checks. + */ + mutex_lock(&event_mutex); + + list_for_each_entry_safe(enabler, next, &mm->enablers, link) + if (enabler->addr == reg.disable_addr && + (enabler->values & ENABLE_VAL_BIT_MASK) == reg.disable_bit) { + set_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(enabler)); + + if (!test_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler))) + user_event_enabler_destroy(enabler); + + /* Removed at least one */ + ret = 0; + } + + mutex_unlock(&event_mutex); + + return ret; +} + /* * Handles the ioctl from user mode to register or alter operations. */ @@ -2108,6 +2195,12 @@ static long user_events_ioctl(struct file *file, unsigned int cmd, ret = user_events_ioctl_del(info, uarg); mutex_unlock(&group->reg_mutex); break; + + case DIAG_IOCSUNREG: + mutex_lock(&group->reg_mutex); + ret = user_events_ioctl_unreg(uarg); + mutex_unlock(&group->reg_mutex); + break; } return ret; -- GitLab From 0d309f04f8089759bed62bf6c8a805b31d725cb8 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:13 -0700 Subject: [PATCH 1620/5631] tracing/user_events: Update self-tests to write ABI ABI has been changed to remote writes, update existing test cases to use this new ABI to ensure existing functionality continues to work. Link: https://lkml.kernel.org/r/20230328235219.203-7-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- .../selftests/user_events/ftrace_test.c | 152 ++++++++++-------- .../testing/selftests/user_events/perf_test.c | 33 ++-- 2 files changed, 96 insertions(+), 89 deletions(-) diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index a0b2c96eb252..aceafacfb126 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include "../kselftest_harness.h" @@ -22,11 +23,6 @@ const char *enable_file = "/sys/kernel/tracing/events/user_events/__test_event/e const char *trace_file = "/sys/kernel/tracing/trace"; const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; -static inline int status_check(char *status_page, int status_bit) -{ - return status_page[status_bit >> 3] & (1 << (status_bit & 7)); -} - static int trace_bytes(void) { int fd = open(trace_file, O_RDONLY); @@ -106,13 +102,23 @@ static int get_print_fmt(char *buffer, int len) return -1; } -static int clear(void) +static int clear(int *check) { + struct user_unreg unreg = {0}; + + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)check; + int fd = open(data_file, O_RDWR); if (fd == -1) return -1; + if (ioctl(fd, DIAG_IOCSUNREG, &unreg) == -1) + if (errno != ENOENT) + return -1; + if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) if (errno != ENOENT) return -1; @@ -122,7 +128,7 @@ static int clear(void) return 0; } -static int check_print_fmt(const char *event, const char *expected) +static int check_print_fmt(const char *event, const char *expected, int *check) { struct user_reg reg = {0}; char print_fmt[256]; @@ -130,7 +136,7 @@ static int check_print_fmt(const char *event, const char *expected) int fd; /* Ensure cleared */ - ret = clear(); + ret = clear(check); if (ret != 0) return ret; @@ -142,14 +148,19 @@ static int check_print_fmt(const char *event, const char *expected) reg.size = sizeof(reg); reg.name_args = (__u64)event; + reg.enable_bit = 31; + reg.enable_addr = (__u64)check; + reg.enable_size = sizeof(*check); /* Register should work */ ret = ioctl(fd, DIAG_IOCSREG, ®); close(fd); - if (ret != 0) + if (ret != 0) { + printf("Reg failed in fmt\n"); return ret; + } /* Ensure correct print_fmt */ ret = get_print_fmt(print_fmt, sizeof(print_fmt)); @@ -164,6 +175,7 @@ FIXTURE(user) { int status_fd; int data_fd; int enable_fd; + int check; }; FIXTURE_SETUP(user) { @@ -185,59 +197,56 @@ FIXTURE_TEARDOWN(user) { close(self->enable_fd); } - ASSERT_EQ(0, clear()); + if (clear(&self->check) != 0) + printf("WARNING: Clear didn't work!\n"); } TEST_F(user, register_events) { struct user_reg reg = {0}; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; + struct user_unreg unreg = {0}; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); + unreg.size = sizeof(unreg); + unreg.disable_bit = 31; + unreg.disable_addr = (__u64)&self->check; /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); /* Multiple registers should result in same index */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); /* Ensure disabled */ self->enable_fd = open(enable_file, O_RDWR); ASSERT_NE(-1, self->enable_fd); ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); - /* Enable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); /* Disable event and ensure bits updated in status */ ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0"))) - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* File still open should return -EBUSY for delete */ ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); ASSERT_EQ(EBUSY, errno); - /* Delete should work only after close */ + /* Unregister */ + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); + + /* Delete should work only after close and unregister */ close(self->data_fd); self->data_fd = open(data_file, O_RDWR); ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event")); - - /* Unmap should work */ - ASSERT_EQ(0, munmap(status_page, page_size)); } TEST_F(user, write_events) { @@ -245,11 +254,12 @@ TEST_F(user, write_events) { struct iovec io[3]; __u32 field1, field2; int before = 0, after = 0; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); field1 = 1; field2 = 2; @@ -261,18 +271,10 @@ TEST_F(user, write_events) { io[2].iov_base = &field2; io[2].iov_len = sizeof(field2); - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); - /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* Write should fail on invalid slot with ENOENT */ io[0].iov_base = &field2; @@ -287,7 +289,7 @@ TEST_F(user, write_events) { ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) /* Event should now be enabled */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_NE(1 << reg.enable_bit, self->check); /* Write should make it out to ftrace buffers */ before = trace_bytes(); @@ -304,6 +306,9 @@ TEST_F(user, write_fault) { reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u64 anon"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); ASSERT_NE(MAP_FAILED, anon); @@ -316,7 +321,6 @@ TEST_F(user, write_fault) { /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); /* Write should work normally */ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2)); @@ -333,24 +337,17 @@ TEST_F(user, write_validator) { int loc, bytes; char data[8]; int before = 0, after = 0; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; - - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event __rel_loc char[] data"; + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - - /* MMAP should work and be zero'd */ - ASSERT_NE(MAP_FAILED, status_page); - ASSERT_NE(NULL, status_page); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); io[0].iov_base = ®.write_index; io[0].iov_len = sizeof(reg.write_index); @@ -369,7 +366,7 @@ TEST_F(user, write_validator) { ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1"))) /* Event should now be enabled */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); /* Full in-bounds write should work */ before = trace_bytes(); @@ -409,71 +406,88 @@ TEST_F(user, print_fmt) { int ret; ret = check_print_fmt("__test_event __rel_loc char[] data", - "print fmt: \"data=%s\", __get_rel_str(data)"); + "print fmt: \"data=%s\", __get_rel_str(data)", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event __data_loc char[] data", - "print fmt: \"data=%s\", __get_str(data)"); + "print fmt: \"data=%s\", __get_str(data)", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s64 data", - "print fmt: \"data=%lld\", REC->data"); + "print fmt: \"data=%lld\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u64 data", - "print fmt: \"data=%llu\", REC->data"); + "print fmt: \"data=%llu\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s32 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u32 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event int data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned int data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s16 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u16 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event short data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned short data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event s8 data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event u8 data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event char data", - "print fmt: \"data=%d\", REC->data"); + "print fmt: \"data=%d\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event unsigned char data", - "print fmt: \"data=%u\", REC->data"); + "print fmt: \"data=%u\", REC->data", + &self->check); ASSERT_EQ(0, ret); ret = check_print_fmt("__test_event char[4] data", - "print fmt: \"data=%s\", REC->data"); + "print fmt: \"data=%s\", REC->data", + &self->check); ASSERT_EQ(0, ret); } diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 31505642aa9b..a070258d4449 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -19,7 +19,6 @@ #include "../kselftest_harness.h" const char *data_file = "/sys/kernel/tracing/user_events_data"; -const char *status_file = "/sys/kernel/tracing/user_events_status"; const char *id_file = "/sys/kernel/tracing/events/user_events/__test_event/id"; const char *fmt_file = "/sys/kernel/tracing/events/user_events/__test_event/format"; @@ -35,11 +34,6 @@ static long perf_event_open(struct perf_event_attr *pe, pid_t pid, return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags); } -static inline int status_check(char *status_page, int status_bit) -{ - return status_page[status_bit >> 3] & (1 << (status_bit & 7)); -} - static int get_id(void) { FILE *fp = fopen(id_file, "r"); @@ -88,45 +82,38 @@ static int get_offset(void) } FIXTURE(user) { - int status_fd; int data_fd; + int check; }; FIXTURE_SETUP(user) { - self->status_fd = open(status_file, O_RDONLY); - ASSERT_NE(-1, self->status_fd); - self->data_fd = open(data_file, O_RDWR); ASSERT_NE(-1, self->data_fd); } FIXTURE_TEARDOWN(user) { - close(self->status_fd); close(self->data_fd); } TEST_F(user, perf_write) { struct perf_event_attr pe = {0}; struct user_reg reg = {0}; - int page_size = sysconf(_SC_PAGESIZE); - char *status_page; struct event event; struct perf_event_mmap_page *perf_page; + int page_size = sysconf(_SC_PAGESIZE); int id, fd, offset; __u32 *val; reg.size = sizeof(reg); reg.name_args = (__u64)"__test_event u32 field1; u32 field2"; - - status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, - self->status_fd, 0); - ASSERT_NE(MAP_FAILED, status_page); + reg.enable_bit = 31; + reg.enable_addr = (__u64)&self->check; + reg.enable_size = sizeof(self->check); /* Register should work */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - ASSERT_NE(0, reg.status_bit); - ASSERT_EQ(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(0, self->check); /* Id should be there */ id = get_id(); @@ -149,7 +136,7 @@ TEST_F(user, perf_write) { ASSERT_NE(MAP_FAILED, perf_page); /* Status should be updated */ - ASSERT_NE(0, status_check(status_page, reg.status_bit)); + ASSERT_EQ(1 << reg.enable_bit, self->check); event.index = reg.write_index; event.field1 = 0xc001; @@ -165,6 +152,12 @@ TEST_F(user, perf_write) { /* Ensure correct */ ASSERT_EQ(event.field1, *val++); ASSERT_EQ(event.field2, *val++); + + munmap(perf_page, page_size * 2); + close(fd); + + /* Status should be updated */ + ASSERT_EQ(0, self->check); } int main(int argc, char **argv) -- GitLab From 60b1af8de8c17f0edc86dc55c0bea9be3bb41626 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:14 -0700 Subject: [PATCH 1621/5631] tracing/user_events: Add ABI self-test Add ABI specific self-test to ensure enablements work in various scenarios such as fork, VM_CLONE, and basic event enable/disable. Ensure ABI contracts/limits are also being upheld, such as bit limits and data size limits. Link: https://lkml.kernel.org/r/20230328235219.203-8-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- tools/testing/selftests/user_events/Makefile | 2 +- .../testing/selftests/user_events/abi_test.c | 226 ++++++++++++++++++ 2 files changed, 227 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/user_events/abi_test.c diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile index 6b512b86aec3..9e95bd41b0b4 100644 --- a/tools/testing/selftests/user_events/Makefile +++ b/tools/testing/selftests/user_events/Makefile @@ -10,7 +10,7 @@ LDLIBS += -lrt -lpthread -lm # This test will not compile until user_events.h is added # back to uapi. -TEST_GEN_PROGS = ftrace_test dyn_test perf_test +TEST_GEN_PROGS = ftrace_test dyn_test perf_test abi_test TEST_FILES := settings diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c new file mode 100644 index 000000000000..e0323d3777a7 --- /dev/null +++ b/tools/testing/selftests/user_events/abi_test.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * User Events ABI Test Program + * + * Copyright (c) 2022 Beau Belgrave + */ + +#define _GNU_SOURCE +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest_harness.h" + +const char *data_file = "/sys/kernel/tracing/user_events_data"; +const char *enable_file = "/sys/kernel/tracing/events/user_events/__abi_event/enable"; + +static int change_event(bool enable) +{ + int fd = open(enable_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + if (enable) + ret = write(fd, "1", 1); + else + ret = write(fd, "0", 1); + + close(fd); + + if (ret == 1) + ret = 0; + else + ret = -1; + + return ret; +} + +static int reg_enable(long *enable, int size, int bit) +{ + struct user_reg reg = {0}; + int fd = open(data_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + reg.size = sizeof(reg); + reg.name_args = (__u64)"__abi_event"; + reg.enable_bit = bit; + reg.enable_addr = (__u64)enable; + reg.enable_size = size; + + ret = ioctl(fd, DIAG_IOCSREG, ®); + + close(fd); + + return ret; +} + +static int reg_disable(long *enable, int bit) +{ + struct user_unreg reg = {0}; + int fd = open(data_file, O_RDWR); + int ret; + + if (fd < 0) + return -1; + + reg.size = sizeof(reg); + reg.disable_bit = bit; + reg.disable_addr = (__u64)enable; + + ret = ioctl(fd, DIAG_IOCSUNREG, ®); + + close(fd); + + return ret; +} + +FIXTURE(user) { + long check; +}; + +FIXTURE_SETUP(user) { + change_event(false); + self->check = 0; +} + +FIXTURE_TEARDOWN(user) { +} + +TEST_F(user, enablement) { + /* Changes should be reflected immediately */ + ASSERT_EQ(0, self->check); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, change_event(false)); + ASSERT_EQ(0, self->check); + + /* Should not change after disable */ + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, reg_disable(&self->check, 0)); + ASSERT_EQ(0, change_event(false)); + ASSERT_EQ(1, self->check); + self->check = 0; +} + +TEST_F(user, bit_sizes) { + /* Allow 0-31 bits for 32-bit */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 31)); + ASSERT_NE(0, reg_enable(&self->check, sizeof(int), 32)); + ASSERT_EQ(0, reg_disable(&self->check, 0)); + ASSERT_EQ(0, reg_disable(&self->check, 31)); + +#if BITS_PER_LONG == 8 + /* Allow 0-64 bits for 64-bit */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(long), 63)); + ASSERT_NE(0, reg_enable(&self->check, sizeof(long), 64)); + ASSERT_EQ(0, reg_disable(&self->check, 63)); +#endif + + /* Disallowed sizes (everything beside 4 and 8) */ + ASSERT_NE(0, reg_enable(&self->check, 1, 0)); + ASSERT_NE(0, reg_enable(&self->check, 2, 0)); + ASSERT_NE(0, reg_enable(&self->check, 3, 0)); + ASSERT_NE(0, reg_enable(&self->check, 5, 0)); + ASSERT_NE(0, reg_enable(&self->check, 6, 0)); + ASSERT_NE(0, reg_enable(&self->check, 7, 0)); + ASSERT_NE(0, reg_enable(&self->check, 9, 0)); + ASSERT_NE(0, reg_enable(&self->check, 128, 0)); +} + +TEST_F(user, forks) { + int i; + + /* Ensure COW pages get updated after fork */ + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, self->check); + + if (fork() == 0) { + /* Force COW */ + self->check = 0; + + /* Up to 1 sec for enablement */ + for (i = 0; i < 10; ++i) { + usleep(100000); + + if (self->check) + exit(0); + } + + exit(1); + } + + /* Allow generous time for COW, then enable */ + usleep(100000); + ASSERT_EQ(0, change_event(true)); + + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + + /* Ensure child doesn't disable parent */ + if (fork() == 0) + exit(reg_disable(&self->check, 0)); + + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + ASSERT_EQ(1, self->check); + ASSERT_EQ(0, change_event(false)); + ASSERT_EQ(0, self->check); +} + +/* Waits up to 1 sec for enablement */ +static int clone_check(void *check) +{ + int i; + + for (i = 0; i < 10; ++i) { + usleep(100000); + + if (*(long *)check) + return 0; + } + + return 1; +} + +TEST_F(user, clones) { + int i, stack_size = 4096; + void *stack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, + -1, 0); + + ASSERT_NE(MAP_FAILED, stack); + ASSERT_EQ(0, reg_enable(&self->check, sizeof(int), 0)); + ASSERT_EQ(0, self->check); + + /* Shared VM should see enablements */ + ASSERT_NE(-1, clone(&clone_check, stack + stack_size, + CLONE_VM | SIGCHLD, &self->check)); + + ASSERT_EQ(0, change_event(true)); + ASSERT_NE(-1, wait(&i)); + ASSERT_EQ(0, WEXITSTATUS(i)); + munmap(stack, stack_size); + ASSERT_EQ(0, change_event(false)); +} + +int main(int argc, char **argv) +{ + return test_harness_run(argc, argv); +} -- GitLab From 9211ddaa78261373b50711c84de978cff8e2bd17 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:15 -0700 Subject: [PATCH 1622/5631] tracing/user_events: Use write ABI in example The ABI has changed to use a remote write approach. Update the example to show the expected use of this new ABI. Also remove debugfs path and use tracefs to ensure example works in more environments. Link: https://lkml.kernel.org/r/20230328235219.203-9-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- samples/user_events/example.c | 45 +++++++---------------------------- 1 file changed, 8 insertions(+), 37 deletions(-) diff --git a/samples/user_events/example.c b/samples/user_events/example.c index 18e34c9d708e..28165a096697 100644 --- a/samples/user_events/example.c +++ b/samples/user_events/example.c @@ -9,51 +9,28 @@ #include #include #include +#include #include #include #include -#include -#include #include -#if __BITS_PER_LONG == 64 -#define endian_swap(x) htole64(x) -#else -#define endian_swap(x) htole32(x) -#endif - -/* Assumes debugfs is mounted */ const char *data_file = "/sys/kernel/tracing/user_events_data"; -const char *status_file = "/sys/kernel/tracing/user_events_status"; +int enabled = 0; -static int event_status(long **status) -{ - int fd = open(status_file, O_RDONLY); - - *status = mmap(NULL, sysconf(_SC_PAGESIZE), PROT_READ, - MAP_SHARED, fd, 0); - - close(fd); - - if (*status == MAP_FAILED) - return -1; - - return 0; -} - -static int event_reg(int fd, const char *command, long *index, long *mask, - int *write) +static int event_reg(int fd, const char *command, int *write, int *enabled) { struct user_reg reg = {0}; reg.size = sizeof(reg); + reg.enable_bit = 31; + reg.enable_size = sizeof(*enabled); + reg.enable_addr = (__u64)enabled; reg.name_args = (__u64)command; if (ioctl(fd, DIAG_IOCSREG, ®) == -1) return -1; - *index = reg.status_bit / __BITS_PER_LONG; - *mask = endian_swap(1L << (reg.status_bit % __BITS_PER_LONG)); *write = reg.write_index; return 0; @@ -62,17 +39,12 @@ static int event_reg(int fd, const char *command, long *index, long *mask, int main(int argc, char **argv) { int data_fd, write; - long index, mask; - long *status_page; struct iovec io[2]; __u32 count = 0; - if (event_status(&status_page) == -1) - return errno; - data_fd = open(data_file, O_RDWR); - if (event_reg(data_fd, "test u32 count", &index, &mask, &write) == -1) + if (event_reg(data_fd, "test u32 count", &write, &enabled) == -1) return errno; /* Setup iovec */ @@ -80,13 +52,12 @@ int main(int argc, char **argv) io[0].iov_len = sizeof(write); io[1].iov_base = &count; io[1].iov_len = sizeof(count); - ask: printf("Press enter to check status...\n"); getchar(); /* Check if anyone is listening */ - if (status_page[index] & mask) { + if (enabled) { /* Yep, trace out our data */ writev(data_fd, (const struct iovec *)io, 2); -- GitLab From 27dc2ae7c8d88a23014a74171b2194f8d47ecca7 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:16 -0700 Subject: [PATCH 1623/5631] tracing/user_events: Update documentation for ABI The ABI for user_events has changed from mmap() based to remote writes. Update the documentation to reflect these changes, add new section for unregistering events since lifetime is now tied to tasks instead of files. Link: https://lkml.kernel.org/r/20230328235219.203-10-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/user_events.rst | 167 ++++++++++++++++------------ 1 file changed, 97 insertions(+), 70 deletions(-) diff --git a/Documentation/trace/user_events.rst b/Documentation/trace/user_events.rst index 422802ef4025..f79987e16cf4 100644 --- a/Documentation/trace/user_events.rst +++ b/Documentation/trace/user_events.rst @@ -20,11 +20,10 @@ dynamic_events is the same as the ioctl with the u: prefix applied. Typically programs will register a set of events that they wish to expose to tools that can read trace_events (such as ftrace and perf). The registration -process gives back two ints to the program for each event. The first int is -the status bit. This describes which bit in little-endian format in the -/sys/kernel/tracing/user_events_status file represents this event. The -second int is the write index which describes the data when a write() or -writev() is called on the /sys/kernel/tracing/user_events_data file. +process tells the kernel which address and bit to reflect if any tool has +enabled the event and data should be written. The registration will give back +a write index which describes the data when a write() or writev() is called +on the /sys/kernel/tracing/user_events_data file. The structures referenced in this document are contained within the /include/uapi/linux/user_events.h file in the source tree. @@ -41,23 +40,64 @@ DIAG_IOCSREG. This command takes a packed struct user_reg as an argument:: struct user_reg { - u32 size; - u64 name_args; - u32 status_bit; - u32 write_index; - }; + /* Input: Size of the user_reg structure being used */ + __u32 size; + + /* Input: Bit in enable address to use */ + __u8 enable_bit; + + /* Input: Enable size in bytes at address */ + __u8 enable_size; + + /* Input: Flags for future use, set to 0 */ + __u16 flags; + + /* Input: Address to update when enabled */ + __u64 enable_addr; + + /* Input: Pointer to string with event name, description and flags */ + __u64 name_args; + + /* Output: Index of the event to use when writing data */ + __u32 write_index; + } __attribute__((__packed__)); + +The struct user_reg requires all the above inputs to be set appropriately. + ++ size: This must be set to sizeof(struct user_reg). -The struct user_reg requires two inputs, the first is the size of the structure -to ensure forward and backward compatibility. The second is the command string -to issue for registering. Upon success two outputs are set, the status bit -and the write index. ++ enable_bit: The bit to reflect the event status at the address specified by + enable_addr. + ++ enable_size: The size of the value specified by enable_addr. + This must be 4 (32-bit) or 8 (64-bit). 64-bit values are only allowed to be + used on 64-bit kernels, however, 32-bit can be used on all kernels. + ++ flags: The flags to use, if any. For the initial version this must be 0. + Callers should first attempt to use flags and retry without flags to ensure + support for lower versions of the kernel. If a flag is not supported -EINVAL + is returned. + ++ enable_addr: The address of the value to use to reflect event status. This + must be naturally aligned and write accessible within the user program. + ++ name_args: The name and arguments to describe the event, see command format + for details. + +Upon successful registration the following is set. + ++ write_index: The index to use for this file descriptor that represents this + event when writing out data. The index is unique to this instance of the file + descriptor that was used for the registration. See writing data for details. User based events show up under tracefs like any other event under the subsystem named "user_events". This means tools that wish to attach to the events need to use /sys/kernel/tracing/events/user_events/[name]/enable or perf record -e user_events:[name] when attaching/recording. -**NOTE:** *The write_index returned is only valid for the FD that was used* +**NOTE:** The event subsystem name by default is "user_events". Callers should +not assume it will always be "user_events". Operators reserve the right in the +future to change the subsystem name per-process to accomodate event isolation. Command Format ^^^^^^^^^^^^^^ @@ -94,7 +134,7 @@ Would be represented by the following field:: struct mytype myname 20 Deleting ------------ +-------- Deleting an event from within a user process is done via ioctl() out to the /sys/kernel/tracing/user_events_data file. The command to issue is DIAG_IOCSDEL. @@ -104,92 +144,79 @@ its name. Delete will only succeed if there are no references left to the event (in both user and kernel space). User programs should use a separate file to request deletes than the one used for registration due to this. -Status ------- -When tools attach/record user based events the status of the event is updated -in realtime. This allows user programs to only incur the cost of the write() or -writev() calls when something is actively attached to the event. - -User programs call mmap() on /sys/kernel/tracing/user_events_status to -check the status for each event that is registered. The bit to check in the -file is given back after the register ioctl() via user_reg.status_bit. The bit -is always in little-endian format. Programs can check if the bit is set either -using a byte-wise index with a mask or a long-wise index with a little-endian -mask. +Unregistering +------------- +If after registering an event it is no longer wanted to be updated then it can +be disabled via ioctl() out to the /sys/kernel/tracing/user_events_data file. +The command to issue is DIAG_IOCSUNREG. This is different than deleting, where +deleting actually removes the event from the system. Unregistering simply tells +the kernel your process is no longer interested in updates to the event. -Currently the size of user_events_status is a single page, however, custom -kernel configurations can change this size to allow more user based events. In -all cases the size of the file is a multiple of a page size. +This command takes a packed struct user_unreg as an argument:: -For example, if the register ioctl() gives back a status_bit of 3 you would -check byte 0 (3 / 8) of the returned mmap data and then AND the result with 8 -(1 << (3 % 8)) to see if anything is attached to that event. + struct user_unreg { + /* Input: Size of the user_unreg structure being used */ + __u32 size; -A byte-wise index check is performed as follows:: + /* Input: Bit to unregister */ + __u8 disable_bit; - int index, mask; - char *status_page; + /* Input: Reserved, set to 0 */ + __u8 __reserved; - index = status_bit / 8; - mask = 1 << (status_bit % 8); - - ... + /* Input: Reserved, set to 0 */ + __u16 __reserved2; - if (status_page[index] & mask) { - /* Enabled */ - } + /* Input: Address to unregister */ + __u64 disable_addr; + } __attribute__((__packed__)); -A long-wise index check is performed as follows:: +The struct user_unreg requires all the above inputs to be set appropriately. - #include - #include ++ size: This must be set to sizeof(struct user_unreg). - #if __BITS_PER_LONG == 64 - #define endian_swap(x) htole64(x) - #else - #define endian_swap(x) htole32(x) - #endif ++ disable_bit: This must be set to the bit to disable (same bit that was + previously registered via enable_bit). - long index, mask, *status_page; ++ disable_addr: This must be set to the address to disable (same address that was + previously registered via enable_addr). - index = status_bit / __BITS_PER_LONG; - mask = 1L << (status_bit % __BITS_PER_LONG); - mask = endian_swap(mask); +**NOTE:** Events are automatically unregistered when execve() is invoked. During +fork() the registered events will be retained and must be unregistered manually +in each process if wanted. - ... +Status +------ +When tools attach/record user based events the status of the event is updated +in realtime. This allows user programs to only incur the cost of the write() or +writev() calls when something is actively attached to the event. - if (status_page[index] & mask) { - /* Enabled */ - } +The kernel will update the specified bit that was registered for the event as +tools attach/detach from the event. User programs simply check if the bit is set +to see if something is attached or not. Administrators can easily check the status of all registered events by reading the user_events_status file directly via a terminal. The output is as follows:: - Byte:Name [# Comments] + Name [# Comments] ... Active: ActiveCount Busy: BusyCount - Max: MaxCount For example, on a system that has a single event the output looks like this:: - 1:test + test Active: 1 Busy: 0 - Max: 32768 If a user enables the user event via ftrace, the output would change to this:: - 1:test # Used by ftrace + test # Used by ftrace Active: 1 Busy: 1 - Max: 32768 - -**NOTE:** *A status bit of 0 will never be returned. This allows user programs -to have a bit that can be used on error cases.* Writing Data ------------ @@ -217,7 +244,7 @@ For example, if I have a struct like this:: int src; int dst; int flags; - }; + } __attribute__((__packed__)); It's advised for user programs to do the following:: -- GitLab From f9cce238ee287a2aa580de1a0187390d6ffdcdeb Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:17 -0700 Subject: [PATCH 1624/5631] tracing/user_events: Charge event allocs to cgroups Operators need a way to limit how much memory cgroups use. User events need to be included into that accounting. Fix this by using GFP_KERNEL_ACCOUNT for allocations generated by user programs for user_event tracing. Link: https://lkml.kernel.org/r/20230328235219.203-11-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index f88bab3f1fe1..3a01c2df4a90 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -442,7 +442,7 @@ static bool user_event_enabler_dup(struct user_event_enabler *orig, if (unlikely(test_bit(ENABLE_VAL_FREEING_BIT, ENABLE_BITOPS(orig)))) return true; - enabler = kzalloc(sizeof(*enabler), GFP_NOWAIT); + enabler = kzalloc(sizeof(*enabler), GFP_NOWAIT | __GFP_ACCOUNT); if (!enabler) return false; @@ -502,7 +502,7 @@ static struct user_event_mm *user_event_mm_create(struct task_struct *t) struct user_event_mm *user_mm; unsigned long flags; - user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL); + user_mm = kzalloc(sizeof(*user_mm), GFP_KERNEL_ACCOUNT); if (!user_mm) return NULL; @@ -662,7 +662,7 @@ static struct user_event_enabler if (!user_mm) return NULL; - enabler = kzalloc(sizeof(*enabler), GFP_KERNEL); + enabler = kzalloc(sizeof(*enabler), GFP_KERNEL_ACCOUNT); if (!enabler) goto out; @@ -870,7 +870,7 @@ static int user_event_add_field(struct user_event *user, const char *type, struct ftrace_event_field *field; int validator_flags = 0; - field = kmalloc(sizeof(*field), GFP_KERNEL); + field = kmalloc(sizeof(*field), GFP_KERNEL_ACCOUNT); if (!field) return -ENOMEM; @@ -889,7 +889,7 @@ static int user_event_add_field(struct user_event *user, const char *type, if (strstr(type, "char") != NULL) validator_flags |= VALIDATOR_ENSURE_NULL; - validator = kmalloc(sizeof(*validator), GFP_KERNEL); + validator = kmalloc(sizeof(*validator), GFP_KERNEL_ACCOUNT); if (!validator) { kfree(field); @@ -1175,7 +1175,7 @@ static int user_event_create_print_fmt(struct user_event *user) len = user_event_set_print_fmt(user, NULL, 0); - print_fmt = kmalloc(len, GFP_KERNEL); + print_fmt = kmalloc(len, GFP_KERNEL_ACCOUNT); if (!print_fmt) return -ENOMEM; @@ -1508,7 +1508,7 @@ static int user_event_create(const char *raw_command) raw_command += USER_EVENTS_PREFIX_LEN; raw_command = skip_spaces(raw_command); - name = kstrdup(raw_command, GFP_KERNEL); + name = kstrdup(raw_command, GFP_KERNEL_ACCOUNT); if (!name) return -ENOMEM; @@ -1704,7 +1704,7 @@ static int user_event_parse(struct user_event_group *group, char *name, return 0; } - user = kzalloc(sizeof(*user), GFP_KERNEL); + user = kzalloc(sizeof(*user), GFP_KERNEL_ACCOUNT); if (!user) return -ENOMEM; @@ -1874,7 +1874,7 @@ static int user_events_open(struct inode *node, struct file *file) if (!group) return -ENOENT; - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL_ACCOUNT); if (!info) return -ENOMEM; @@ -1927,7 +1927,7 @@ static int user_events_ref_add(struct user_event_file_info *info, size = struct_size(refs, events, count + 1); - new_refs = kzalloc(size, GFP_KERNEL); + new_refs = kzalloc(size, GFP_KERNEL_ACCOUNT); if (!new_refs) return -ENOMEM; -- GitLab From ce58e96e9fe24022312ee1eeefb18ed460efdb18 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:18 -0700 Subject: [PATCH 1625/5631] tracing/user_events: Limit global user_event count Operators want to be able to ensure enough tracepoints exist on the system for kernel components as well as for user components. Since there are only up to 64K events, by default allow up to half to be used by user events. Add a kernel sysctl parameter (kernel.user_events_max) to set a global limit that is honored among all groups on the system. This ensures hard limits can be setup to prevent user processes from consuming all event IDs on the system. Link: https://lkml.kernel.org/r/20230328235219.203-12-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 47 ++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 3a01c2df4a90..9b43a02e1597 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include "trace.h" #include "trace_dynevent.h" @@ -61,6 +62,12 @@ struct user_event_group { /* Group for init_user_ns mapping, top-most group */ static struct user_event_group *init_group; +/* Max allowed events for the whole system */ +static unsigned int max_user_events = 32768; + +/* Current number of events on the whole system */ +static unsigned int current_user_events; + /* * Stores per-event properties, as users register events * within a file a user_event might be created if it does not @@ -1241,6 +1248,8 @@ static int destroy_user_event(struct user_event *user) { int ret = 0; + lockdep_assert_held(&event_mutex); + /* Must destroy fields before call removal */ user_event_destroy_fields(user); @@ -1257,6 +1266,11 @@ static int destroy_user_event(struct user_event *user) kfree(EVENT_NAME(user)); kfree(user); + if (current_user_events > 0) + current_user_events--; + else + pr_alert("BUG: Bad current_user_events\n"); + return ret; } @@ -1744,6 +1758,11 @@ static int user_event_parse(struct user_event_group *group, char *name, mutex_lock(&event_mutex); + if (current_user_events >= max_user_events) { + ret = -EMFILE; + goto put_user_lock; + } + ret = user_event_trace_register(user); if (ret) @@ -1755,6 +1774,7 @@ static int user_event_parse(struct user_event_group *group, char *name, dyn_event_init(&user->devent, &user_event_dops); dyn_event_add(&user->devent, &user->call); hash_add(group->register_table, &user->node, key); + current_user_events++; mutex_unlock(&event_mutex); @@ -2390,6 +2410,31 @@ static int create_user_tracefs(void) return -ENODEV; } +static int set_max_user_events_sysctl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + mutex_lock(&event_mutex); + + ret = proc_douintvec(table, write, buffer, lenp, ppos); + + mutex_unlock(&event_mutex); + + return ret; +} + +static struct ctl_table user_event_sysctls[] = { + { + .procname = "user_events_max", + .data = &max_user_events, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = set_max_user_events_sysctl, + }, + {} +}; + static int __init trace_events_user_init(void) { int ret; @@ -2419,6 +2464,8 @@ static int __init trace_events_user_init(void) if (dyn_event_register(&user_event_dops)) pr_warn("user_events could not register with dyn_events\n"); + register_sysctl_init("kernel", user_event_sysctls); + return 0; } -- GitLab From a4c40c1349e32f9510707ed09e0961626980d8cb Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 28 Mar 2023 16:52:19 -0700 Subject: [PATCH 1626/5631] tracing/user_events: Align structs with tabs for readability Add tabs to make struct members easier to read and unify the style of the code. Link: https://lkml.kernel.org/r/20230328235219.203-13-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/linux/user_events.h | 14 +++--- include/uapi/linux/user_events.h | 24 +++++----- kernel/trace/trace_events_user.c | 82 ++++++++++++++++---------------- 3 files changed, 60 insertions(+), 60 deletions(-) diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 0120b3dd5b03..2847f5a18a86 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -17,13 +17,13 @@ #ifdef CONFIG_USER_EVENTS struct user_event_mm { - struct list_head link; - struct list_head enablers; - struct mm_struct *mm; - struct user_event_mm *next; - refcount_t refcnt; - refcount_t tasks; - struct rcu_work put_rwork; + struct list_head link; + struct list_head enablers; + struct mm_struct *mm; + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; }; extern void user_event_mm_dup(struct task_struct *t, diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index 3e7275e3234a..2984aae4a2b4 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -25,25 +25,25 @@ struct user_reg { /* Input: Size of the user_reg structure being used */ - __u32 size; + __u32 size; /* Input: Bit in enable address to use */ - __u8 enable_bit; + __u8 enable_bit; /* Input: Enable size in bytes at address */ - __u8 enable_size; + __u8 enable_size; /* Input: Flags for future use, set to 0 */ - __u16 flags; + __u16 flags; /* Input: Address to update when enabled */ - __u64 enable_addr; + __u64 enable_addr; /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; + __u64 name_args; /* Output: Index of the event to use when writing data */ - __u32 write_index; + __u32 write_index; } __attribute__((__packed__)); /* @@ -52,19 +52,19 @@ struct user_reg { */ struct user_unreg { /* Input: Size of the user_unreg structure being used */ - __u32 size; + __u32 size; /* Input: Bit to unregister */ - __u8 disable_bit; + __u8 disable_bit; /* Input: Reserved, set to 0 */ - __u8 __reserved; + __u8 __reserved; /* Input: Reserved, set to 0 */ - __u16 __reserved2; + __u16 __reserved2; /* Input: Address to unregister */ - __u64 disable_addr; + __u64 disable_addr; } __attribute__((__packed__)); #define DIAG_IOC_MAGIC '*' diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 9b43a02e1597..67cb7b53caf6 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -53,9 +53,9 @@ * allows isolation for events by various means. */ struct user_event_group { - char *system_name; - struct hlist_node node; - struct mutex reg_mutex; + char *system_name; + struct hlist_node node; + struct mutex reg_mutex; DECLARE_HASHTABLE(register_table, 8); }; @@ -76,17 +76,17 @@ static unsigned int current_user_events; * refcnt reaches one. */ struct user_event { - struct user_event_group *group; - struct tracepoint tracepoint; - struct trace_event_call call; - struct trace_event_class class; - struct dyn_event devent; - struct hlist_node node; - struct list_head fields; - struct list_head validators; - refcount_t refcnt; - int min_size; - char status; + struct user_event_group *group; + struct tracepoint tracepoint; + struct trace_event_call call; + struct trace_event_class class; + struct dyn_event devent; + struct hlist_node node; + struct list_head fields; + struct list_head validators; + refcount_t refcnt; + int min_size; + char status; }; /* @@ -95,12 +95,12 @@ struct user_event { * these to track enablement sites that are tied to an event. */ struct user_event_enabler { - struct list_head link; - struct user_event *event; - unsigned long addr; + struct list_head link; + struct user_event *event; + unsigned long addr; /* Track enable bit, flags, etc. Aligned for bitops. */ - unsigned int values; + unsigned int values; }; /* Bits 0-5 are for the bit to update upon enable/disable (0-63 allowed) */ @@ -119,9 +119,9 @@ struct user_event_enabler { /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { - struct work_struct work; - struct user_event_mm *mm; - struct user_event_enabler *enabler; + struct work_struct work; + struct user_event_mm *mm; + struct user_event_enabler *enabler; }; static struct kmem_cache *fault_cache; @@ -137,23 +137,23 @@ static DEFINE_SPINLOCK(user_event_mms_lock); * These are not shared and only accessible by the file that created it. */ struct user_event_refs { - struct rcu_head rcu; - int count; - struct user_event *events[]; + struct rcu_head rcu; + int count; + struct user_event *events[]; }; struct user_event_file_info { - struct user_event_group *group; - struct user_event_refs *refs; + struct user_event_group *group; + struct user_event_refs *refs; }; #define VALIDATOR_ENSURE_NULL (1 << 0) #define VALIDATOR_REL (1 << 1) struct user_event_validator { - struct list_head link; - int offset; - int flags; + struct list_head link; + int offset; + int flags; }; typedef void (*user_event_func_t) (struct user_event *user, struct iov_iter *i, @@ -2276,11 +2276,11 @@ static int user_events_release(struct inode *node, struct file *file) } static const struct file_operations user_data_fops = { - .open = user_events_open, - .write = user_events_write, - .write_iter = user_events_write_iter, + .open = user_events_open, + .write = user_events_write, + .write_iter = user_events_write_iter, .unlocked_ioctl = user_events_ioctl, - .release = user_events_release, + .release = user_events_release, }; static void *user_seq_start(struct seq_file *m, loff_t *pos) @@ -2346,10 +2346,10 @@ static int user_seq_show(struct seq_file *m, void *p) } static const struct seq_operations user_seq_ops = { - .start = user_seq_start, - .next = user_seq_next, - .stop = user_seq_stop, - .show = user_seq_show, + .start = user_seq_start, + .next = user_seq_next, + .stop = user_seq_stop, + .show = user_seq_show, }; static int user_status_open(struct inode *node, struct file *file) @@ -2375,10 +2375,10 @@ static int user_status_open(struct inode *node, struct file *file) } static const struct file_operations user_status_fops = { - .open = user_status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, + .open = user_status_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, }; /* -- GitLab From 4bec284cc0b99d880c3fb00fe0d2af7a0c285db3 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 28 Mar 2023 15:14:13 -0400 Subject: [PATCH 1627/5631] tracing/user_events: Use print_format_fields() for trace output Currently, user events are shown using the "hex" output for "safety" reasons as one cannot trust user events behaving nicely. But the hex output is not the only utility for safe outputting of trace events. The print_event_fields() is just as safe and gives user readable output. Before: example-839 [001] ..... 43.222244: 00000000: b1 06 00 00 47 03 00 00 00 00 00 00 ....G....... example-839 [001] ..... 43.564433: 00000000: b1 06 00 00 47 03 00 00 01 00 00 00 ....G....... example-839 [001] ..... 43.763917: 00000000: b1 06 00 00 47 03 00 00 02 00 00 00 ....G....... example-839 [001] ..... 43.967929: 00000000: b1 06 00 00 47 03 00 00 03 00 00 00 ....G....... After: example-837 [006] ..... 55.739249: test: count=0x0 (0) example-837 [006] ..... 111.104784: test: count=0x1 (1) example-837 [006] ..... 111.268444: test: count=0x2 (2) example-837 [006] ..... 111.416533: test: count=0x3 (3) example-837 [006] ..... 111.542859: test: count=0x4 (4) Link: https://lore.kernel.org/linux-trace-kernel/20230328151413.4770b8d7@gandalf.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 67cb7b53caf6..cc8c6d8b69b5 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -22,8 +22,9 @@ #include #include #include -#include "trace.h" #include "trace_dynevent.h" +#include "trace_output.h" +#include "trace.h" #define USER_EVENTS_PREFIX_LEN (sizeof(USER_EVENTS_PREFIX)-1) @@ -1198,11 +1199,7 @@ static enum print_line_t user_event_print_trace(struct trace_iterator *iter, int flags, struct trace_event *event) { - /* Unsafe to try to decode user provided print_fmt, use hex */ - trace_print_hex_dump_seq(&iter->seq, "", DUMP_PREFIX_OFFSET, 16, - 1, iter->ent, iter->ent_size, true); - - return trace_handle_return(&iter->seq); + return print_event_fields(iter, event); } static struct trace_event_functions user_event_funcs = { -- GitLab From 88fe1ec75fcb296579e05eaf3807da3ee83137e4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 28 Mar 2023 11:10:57 -0400 Subject: [PATCH 1628/5631] tracing: Unbreak user events The user events was added a bit prematurely, and there were a few kernel developers that had issues with it. The API also needed a bit of work to make sure it would be stable. It was decided to make user events "broken" until this was settled. Now it has a new API that appears to be as stable as it will be without the use of a crystal ball. It's being used within Microsoft as is, which means the API has had some testing in real world use cases. It went through many discussions in the bi-weekly tracing meetings, and there's been no more comments about updates. I feel this is good to go. Cc: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- kernel/trace/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index c7020e071bf9..8cf97fa4a4b3 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -792,7 +792,6 @@ config USER_EVENTS bool "User trace events" select TRACING select DYNAMIC_EVENTS - depends on BROKEN || COMPILE_TEST # API needs to be straighten out help User trace events are user-defined trace events that can be used like an existing kernel trace event. User trace -- GitLab From 1b69f1e3d7449d0c66f7bc0f429ed94fc03dfeb3 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sat, 25 Mar 2023 10:05:59 -0400 Subject: [PATCH 1629/5631] RDMA/bnxt_re: remove unused num_srqne_processed and num_cqne_processed variables clang with W=1 reports drivers/infiniband/hw/bnxt_re/qplib_fp.c:303:6: error: variable 'num_srqne_processed' set but not used [-Werror,-Wunused-but-set-variable] int num_srqne_processed = 0; ^ drivers/infiniband/hw/bnxt_re/qplib_fp.c:304:6: error: variable 'num_cqne_processed' set but not used [-Werror,-Wunused-but-set-variable] int num_cqne_processed = 0; ^ These variables are not used so remove them. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230325140559.1336056-1-trix@redhat.com Acked-by: Selvin Xavier Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 1d769a3106f6..e9296bce9533 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -300,8 +300,6 @@ static void bnxt_qplib_service_nq(struct tasklet_struct *t) { struct bnxt_qplib_nq *nq = from_tasklet(nq, t, nq_tasklet); struct bnxt_qplib_hwq *hwq = &nq->hwq; - int num_srqne_processed = 0; - int num_cqne_processed = 0; struct bnxt_qplib_cq *cq; int budget = nq->budget; u32 sw_cons, raw_cons; @@ -340,9 +338,7 @@ static void bnxt_qplib_service_nq(struct tasklet_struct *t) DBC_DBC_TYPE_CQ_ARMENA); spin_lock_bh(&cq->compl_lock); atomic_set(&cq->arm_state, 0); - if (!nq->cqn_handler(nq, (cq))) - num_cqne_processed++; - else + if (nq->cqn_handler(nq, (cq))) dev_warn(&nq->pdev->dev, "cqn - type 0x%x not handled\n", type); cq->cnq_events++; @@ -361,11 +357,9 @@ static void bnxt_qplib_service_nq(struct tasklet_struct *t) srq = (struct bnxt_qplib_srq *)q_handle; bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA); - if (!nq->srqn_handler(nq, - (struct bnxt_qplib_srq *)q_handle, - nqsrqe->event)) - num_srqne_processed++; - else + if (nq->srqn_handler(nq, + (struct bnxt_qplib_srq *)q_handle, + nqsrqe->event)) dev_warn(&nq->pdev->dev, "SRQ event 0x%x not handled\n", nqsrqe->event); -- GitLab From cba968e33e5df086b6e681179d199f959bc71f33 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 26 Mar 2023 08:09:59 -0400 Subject: [PATCH 1630/5631] RDMA/ocrdma: remove unused discard_cnt variable clang with W=1 reports drivers/infiniband/hw/ocrdma/ocrdma_verbs.c:1592:6: error: variable 'discard_cnt' set but not used [-Werror,-Wunused-but-set-variable] int discard_cnt = 0; ^ This variable is not used so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230326120959.1351948-1-trix@redhat.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index dd4021b11963..58f994341e9a 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -1589,7 +1589,6 @@ static void ocrdma_discard_cqes(struct ocrdma_qp *qp, struct ocrdma_cq *cq) { unsigned long cq_flags; unsigned long flags; - int discard_cnt = 0; u32 cur_getp, stop_getp; struct ocrdma_cqe *cqe; u32 qpn = 0, wqe_idx = 0; @@ -1641,7 +1640,6 @@ static void ocrdma_discard_cqes(struct ocrdma_qp *qp, struct ocrdma_cq *cq) /* mark cqe discarded so that it is not picked up later * in the poll_cq(). */ - discard_cnt += 1; cqe->cmn.qpn = 0; skip_cqe: cur_getp = (cur_getp + 1) % cq->max_hw_cqe; -- GitLab From 78b26a335310a097d6b22581b706050db42f196c Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Mon, 27 Mar 2023 16:56:44 -0500 Subject: [PATCH 1631/5631] RDMA/rxe: Remove tasklet call from rxe_cq.c Remove the tasklet call in rxe_cq.c and also the is_dying in the cq struct. There is no reason for the rxe driver to defer the call to the cq completion handler by scheduling a tasklet. rxe_cq_post() is not called in a hard irq context. The rxe driver currently is incorrect because the tasklet call is made without protecting the cq pointer with a reference from having the underlying memory freed before the deferred routine is called. Executing the comp_handler inline fixes this problem. Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Bob Pearson Link: https://lore.kernel.org/r/20230327215643.10410-1-rpearsonhpe@gmail.com Acked-by: Zhu Yanjun Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rxe/rxe_cq.c | 32 +++------------------------ drivers/infiniband/sw/rxe/rxe_verbs.c | 2 -- drivers/infiniband/sw/rxe/rxe_verbs.h | 2 -- 3 files changed, 3 insertions(+), 33 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c index 66a13c935d50..20ff0c0c4605 100644 --- a/drivers/infiniband/sw/rxe/rxe_cq.c +++ b/drivers/infiniband/sw/rxe/rxe_cq.c @@ -39,21 +39,6 @@ int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq, return -EINVAL; } -static void rxe_send_complete(struct tasklet_struct *t) -{ - struct rxe_cq *cq = from_tasklet(cq, t, comp_task); - unsigned long flags; - - spin_lock_irqsave(&cq->cq_lock, flags); - if (cq->is_dying) { - spin_unlock_irqrestore(&cq->cq_lock, flags); - return; - } - spin_unlock_irqrestore(&cq->cq_lock, flags); - - cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); -} - int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, int comp_vector, struct ib_udata *udata, struct rxe_create_cq_resp __user *uresp) @@ -79,10 +64,6 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe, cq->is_user = uresp; - cq->is_dying = false; - - tasklet_setup(&cq->comp_task, rxe_send_complete); - spin_lock_init(&cq->cq_lock); cq->ibcq.cqe = cqe; return 0; @@ -103,6 +84,7 @@ int rxe_cq_resize_queue(struct rxe_cq *cq, int cqe, return err; } +/* caller holds reference to cq */ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) { struct ib_event ev; @@ -136,21 +118,13 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited) if ((cq->notify == IB_CQ_NEXT_COMP) || (cq->notify == IB_CQ_SOLICITED && solicited)) { cq->notify = 0; - tasklet_schedule(&cq->comp_task); + + cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); } return 0; } -void rxe_cq_disable(struct rxe_cq *cq) -{ - unsigned long flags; - - spin_lock_irqsave(&cq->cq_lock, flags); - cq->is_dying = true; - spin_unlock_irqrestore(&cq->cq_lock, flags); -} - void rxe_cq_cleanup(struct rxe_pool_elem *elem) { struct rxe_cq *cq = container_of(elem, typeof(*cq), elem); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 84b53c070fc5..090d5bfb1e18 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1178,8 +1178,6 @@ static int rxe_destroy_cq(struct ib_cq *ibcq, struct ib_udata *udata) goto err_out; } - rxe_cq_disable(cq); - err = rxe_cleanup(cq); if (err) rxe_err_cq(cq, "cleanup failed, err = %d", err); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index c269ae2a3224..d812093a3916 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -63,9 +63,7 @@ struct rxe_cq { struct rxe_queue *queue; spinlock_t cq_lock; u8 notify; - bool is_dying; bool is_user; - struct tasklet_struct comp_task; atomic_t num_wq; }; -- GitLab From 0398abca61482ae47a41ae8f2401338aea366327 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 15 Mar 2023 16:20:55 -0700 Subject: [PATCH 1632/5631] powerpc: Remove memcpy_page_flushcache() Commit 21b56c847753 ("iov_iter: get rid of separate bvec and xarray callbacks") removed the calls to memcpy_page_flushcache(). Remove the unnecessary memcpy_page_flushcache() call. Signed-off-by: Ira Weiny Signed-off-by: Michael Ellerman Link: https://msgid.link/20221230-kmap-x86-v1-2-15f1ecccab50@intel.com --- arch/powerpc/include/asm/uaccess.h | 2 -- arch/powerpc/lib/pmem.c | 7 ------- 2 files changed, 9 deletions(-) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 3ddc65c63a49..52378e641d38 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -361,8 +361,6 @@ copy_mc_to_user(void __user *to, const void *from, unsigned long n) extern long __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size); -extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, - size_t len); static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) { diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c index eb2919ddf9b9..4e724c4c01ad 100644 --- a/arch/powerpc/lib/pmem.c +++ b/arch/powerpc/lib/pmem.c @@ -85,10 +85,3 @@ void memcpy_flushcache(void *dest, const void *src, size_t size) clean_pmem_range(start, start + size); } EXPORT_SYMBOL(memcpy_flushcache); - -void memcpy_page_flushcache(char *to, struct page *page, size_t offset, - size_t len) -{ - memcpy_flushcache(to, page_to_virt(page) + offset, len); -} -EXPORT_SYMBOL(memcpy_page_flushcache); -- GitLab From 0acc7239c20a8401b8968c2adace8f7c9b0295ae Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Mar 2023 16:47:44 +0000 Subject: [PATCH 1633/5631] KVM: arm64: Avoid vcpu->mutex v. kvm->lock inversion in CPU_ON KVM/arm64 had the lock ordering backwards on vcpu->mutex and kvm->lock from the very beginning. One such example is the way vCPU resets are handled: the kvm->lock is acquired while handling a guest CPU_ON PSCI call. Add a dedicated lock to serialize writes to kvm_vcpu_arch::{mp_state, reset_state}. Promote all accessors of mp_state to {READ,WRITE}_ONCE() as readers do not acquire the mp_state_lock. While at it, plug yet another race by taking the mp_state_lock in the KVM_SET_MP_STATE ioctl handler. As changes to MP state are now guarded with a dedicated lock, drop the kvm->lock acquisition from the PSCI CPU_ON path. Similarly, move the reader of reset_state outside of the kvm->lock and instead protect it with the mp_state_lock. Note that writes to reset_state::reset have been demoted to regular stores as both readers and writers acquire the mp_state_lock. While the kvm->lock inversion still exists in kvm_reset_vcpu(), at least now PSCI CPU_ON no longer depends on it for serializing vCPU reset. Cc: stable@vger.kernel.org Tested-by: Jeremy Linton Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230327164747.2466958-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/kvm/arm.c | 31 ++++++++++++++++++++++--------- arch/arm64/kvm/psci.c | 28 ++++++++++++++++------------ arch/arm64/kvm/reset.c | 9 +++++---- 4 files changed, 44 insertions(+), 25 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bcd774d74f34..917586237a4d 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -522,6 +522,7 @@ struct kvm_vcpu_arch { /* vcpu power state */ struct kvm_mp_state mp_state; + spinlock_t mp_state_lock; /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3bd732eaf087..647798da8c41 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -326,6 +326,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int err; + spin_lock_init(&vcpu->arch.mp_state_lock); + /* Force users to call KVM_ARM_VCPU_INIT */ vcpu->arch.target = -1; bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); @@ -443,34 +445,41 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; } -void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) +static void __kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) { - vcpu->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); kvm_make_request(KVM_REQ_SLEEP, vcpu); kvm_vcpu_kick(vcpu); } +void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu) +{ + spin_lock(&vcpu->arch.mp_state_lock); + __kvm_arm_vcpu_power_off(vcpu); + spin_unlock(&vcpu->arch.mp_state_lock); +} + bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu) { - return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_STOPPED; + return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED; } static void kvm_arm_vcpu_suspend(struct kvm_vcpu *vcpu) { - vcpu->arch.mp_state.mp_state = KVM_MP_STATE_SUSPENDED; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_SUSPENDED); kvm_make_request(KVM_REQ_SUSPEND, vcpu); kvm_vcpu_kick(vcpu); } static bool kvm_arm_vcpu_suspended(struct kvm_vcpu *vcpu) { - return vcpu->arch.mp_state.mp_state == KVM_MP_STATE_SUSPENDED; + return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_SUSPENDED; } int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - *mp_state = vcpu->arch.mp_state; + *mp_state = READ_ONCE(vcpu->arch.mp_state); return 0; } @@ -480,12 +489,14 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int ret = 0; + spin_lock(&vcpu->arch.mp_state_lock); + switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: - vcpu->arch.mp_state = *mp_state; + WRITE_ONCE(vcpu->arch.mp_state, *mp_state); break; case KVM_MP_STATE_STOPPED: - kvm_arm_vcpu_power_off(vcpu); + __kvm_arm_vcpu_power_off(vcpu); break; case KVM_MP_STATE_SUSPENDED: kvm_arm_vcpu_suspend(vcpu); @@ -494,6 +505,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, ret = -EINVAL; } + spin_unlock(&vcpu->arch.mp_state_lock); + return ret; } @@ -1213,7 +1226,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) kvm_arm_vcpu_power_off(vcpu); else - vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); return 0; } diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 7fbc4c1b9df0..5767e6baa61a 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -62,6 +62,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) struct vcpu_reset_state *reset_state; struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; + int ret = PSCI_RET_SUCCESS; unsigned long cpu_id; cpu_id = smccc_get_arg1(source_vcpu); @@ -76,11 +77,15 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) */ if (!vcpu) return PSCI_RET_INVALID_PARAMS; + + spin_lock(&vcpu->arch.mp_state_lock); if (!kvm_arm_vcpu_stopped(vcpu)) { if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1) - return PSCI_RET_ALREADY_ON; + ret = PSCI_RET_ALREADY_ON; else - return PSCI_RET_INVALID_PARAMS; + ret = PSCI_RET_INVALID_PARAMS; + + goto out_unlock; } reset_state = &vcpu->arch.reset_state; @@ -96,7 +101,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) */ reset_state->r0 = smccc_get_arg3(source_vcpu); - WRITE_ONCE(reset_state->reset, true); + reset_state->reset = true; kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); /* @@ -108,7 +113,9 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; kvm_vcpu_wake_up(vcpu); - return PSCI_RET_SUCCESS; +out_unlock: + spin_unlock(&vcpu->arch.mp_state_lock); + return ret; } static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) @@ -168,8 +175,11 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags) * after this call is handled and before the VCPUs have been * re-initialized. */ - kvm_for_each_vcpu(i, tmp, vcpu->kvm) - tmp->arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + spin_lock(&tmp->arch.mp_state_lock); + WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); + spin_unlock(&tmp->arch.mp_state_lock); + } kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event)); @@ -229,7 +239,6 @@ static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; u32 psci_fn = smccc_get_function(vcpu); unsigned long val; int ret = 1; @@ -254,9 +263,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) kvm_psci_narrow_to_32bit(vcpu); fallthrough; case PSCI_0_2_FN64_CPU_ON: - mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); - mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: kvm_psci_narrow_to_32bit(vcpu); @@ -395,7 +402,6 @@ static int kvm_psci_1_x_call(struct kvm_vcpu *vcpu, u32 minor) static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; u32 psci_fn = smccc_get_function(vcpu); unsigned long val; @@ -405,9 +411,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case KVM_PSCI_FN_CPU_ON: - mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); - mutex_unlock(&kvm->lock); break; default: val = PSCI_RET_NOT_SUPPORTED; diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 49a3257dec46..9e023546bde0 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -264,15 +264,16 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) mutex_lock(&vcpu->kvm->lock); ret = kvm_set_vm_width(vcpu); - if (!ret) { - reset_state = vcpu->arch.reset_state; - WRITE_ONCE(vcpu->arch.reset_state.reset, false); - } mutex_unlock(&vcpu->kvm->lock); if (ret) return ret; + spin_lock(&vcpu->arch.mp_state_lock); + reset_state = vcpu->arch.reset_state; + vcpu->arch.reset_state.reset = false; + spin_unlock(&vcpu->arch.mp_state_lock); + /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); -- GitLab From c43120afb5c66a3465c7468f5cf9806a26484cde Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Mar 2023 16:47:45 +0000 Subject: [PATCH 1634/5631] KVM: arm64: Avoid lock inversion when setting the VM register width kvm->lock must be taken outside of the vcpu->mutex. Of course, the locking documentation for KVM makes this abundantly clear. Nonetheless, the locking order in KVM/arm64 has been wrong for quite a while; we acquire the kvm->lock while holding the vcpu->mutex all over the shop. All was seemingly fine until commit 42a90008f890 ("KVM: Ensure lockdep knows about kvm->lock vs. vcpu->mutex ordering rule") caught us with our pants down, leading to lockdep barfing: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc7+ #19 Not tainted ------------------------------------------------------ qemu-system-aar/859 is trying to acquire lock: ffff5aa69269eba0 (&host_kvm->lock){+.+.}-{3:3}, at: kvm_reset_vcpu+0x34/0x274 but task is already holding lock: ffff5aa68768c0b8 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8c/0xba0 which lock already depends on the new lock. Add a dedicated lock to serialize writes to VM-scoped configuration from the context of a vCPU. Protect the register width flags with the new lock, thus avoiding the need to grab the kvm->lock while holding vcpu->mutex in kvm_reset_vcpu(). Cc: stable@vger.kernel.org Reported-by: Jeremy Linton Link: https://lore.kernel.org/kvmarm/f6452cdd-65ff-34b8-bab0-5c06416da5f6@arm.com/ Tested-by: Jeremy Linton Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230327164747.2466958-3-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/arm.c | 18 ++++++++++++++++++ arch/arm64/kvm/reset.c | 6 +++--- 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 917586237a4d..cd1ef8716719 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -199,6 +199,9 @@ struct kvm_arch { /* Mandated version of PSCI */ u32 psci_version; + /* Protects VM-scoped configuration data */ + struct mutex config_lock; + /* * If we encounter a data abort without valid instruction syndrome * information, report this to user space. User space can (and diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 647798da8c41..1620ec3d95ef 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -128,6 +128,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; + mutex_init(&kvm->arch.config_lock); + +#ifdef CONFIG_LOCKDEP + /* Clue in lockdep that the config_lock must be taken inside kvm->lock */ + mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); + mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->lock); +#endif + ret = kvm_share_hyp(kvm, kvm + 1); if (ret) return ret; @@ -328,6 +338,14 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) spin_lock_init(&vcpu->arch.mp_state_lock); +#ifdef CONFIG_LOCKDEP + /* Inform lockdep that the config_lock is acquired after vcpu->mutex */ + mutex_lock(&vcpu->mutex); + mutex_lock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->mutex); +#endif + /* Force users to call KVM_ARM_VCPU_INIT */ vcpu->arch.target = -1; bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 9e023546bde0..b5dee8e57e77 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -205,7 +205,7 @@ static int kvm_set_vm_width(struct kvm_vcpu *vcpu) is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); - lockdep_assert_held(&kvm->lock); + lockdep_assert_held(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { /* @@ -262,9 +262,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) bool loaded; u32 pstate; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_set_vm_width(vcpu); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); if (ret) return ret; -- GitLab From 4bba7f7def6f278266dadf845da472cfbfed784e Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Mar 2023 16:47:46 +0000 Subject: [PATCH 1635/5631] KVM: arm64: Use config_lock to protect data ordered against KVM_RUN There are various bits of VM-scoped data that can only be configured before the first call to KVM_RUN, such as the hypercall bitmaps and the PMU. As these fields are protected by the kvm->lock and accessed while holding vcpu->mutex, this is yet another example of lock inversion. Change out the kvm->lock for kvm->arch.config_lock in all of these instances. Opportunistically simplify the locking mechanics of the PMU configuration by holding the config_lock for the entirety of kvm_arm_pmu_v3_set_attr(). Note that this also addresses a couple of bugs. There is an unguarded read of the PMU version in KVM_ARM_VCPU_PMU_V3_FILTER which could race with KVM_ARM_VCPU_PMU_V3_SET_PMU. Additionally, until now writes to the per-vCPU vPMU irq were not serialized VM-wide, meaning concurrent calls to KVM_ARM_VCPU_PMU_V3_IRQ could lead to a false positive in pmu_irq_is_valid(). Cc: stable@vger.kernel.org Tested-by: Jeremy Linton Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230327164747.2466958-4-oliver.upton@linux.dev --- arch/arm64/kvm/arm.c | 4 ++-- arch/arm64/kvm/guest.c | 2 ++ arch/arm64/kvm/hypercalls.c | 4 ++-- arch/arm64/kvm/pmu-emul.c | 23 ++++++----------------- 4 files changed, 12 insertions(+), 21 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1620ec3d95ef..fd8d355aca15 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -624,9 +624,9 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (kvm_vm_is_protected(kvm)) kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu); - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07444fa22888..481c79cf22cd 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -957,7 +957,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: + mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_arm_pmu_v3_set_attr(vcpu, attr); + mutex_unlock(&vcpu->kvm->arch.config_lock); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 5da884e11337..fbdbf4257f76 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -377,7 +377,7 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) if (val & ~fw_reg_features) return -EINVAL; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) && val != *fw_reg_bmap) { @@ -387,7 +387,7 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) WRITE_ONCE(*fw_reg_bmap, val); out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 24908400e190..240168416838 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -874,7 +874,7 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) struct arm_pmu *arm_pmu; int ret = -ENXIO; - mutex_lock(&kvm->lock); + lockdep_assert_held(&kvm->arch.config_lock); mutex_lock(&arm_pmus_lock); list_for_each_entry(entry, &arm_pmus, entry) { @@ -894,7 +894,6 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) } mutex_unlock(&arm_pmus_lock); - mutex_unlock(&kvm->lock); return ret; } @@ -902,22 +901,20 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; + lockdep_assert_held(&kvm->arch.config_lock); + if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) return -EBUSY; - mutex_lock(&kvm->lock); if (!kvm->arch.arm_pmu) { /* No PMU set, get the default one */ kvm->arch.arm_pmu = kvm_pmu_probe_armpmu(); - if (!kvm->arch.arm_pmu) { - mutex_unlock(&kvm->lock); + if (!kvm->arch.arm_pmu) return -ENODEV; - } } - mutex_unlock(&kvm->lock); switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { @@ -961,19 +958,13 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) filter.action != KVM_PMU_EVENT_DENY)) return -EINVAL; - mutex_lock(&kvm->lock); - - if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) { - mutex_unlock(&kvm->lock); + if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) return -EBUSY; - } if (!kvm->arch.pmu_filter) { kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT); - if (!kvm->arch.pmu_filter) { - mutex_unlock(&kvm->lock); + if (!kvm->arch.pmu_filter) return -ENOMEM; - } /* * The default depends on the first applied filter. @@ -992,8 +983,6 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) else bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents); - mutex_unlock(&kvm->lock); - return 0; } case KVM_ARM_VCPU_PMU_V3_SET_PMU: { -- GitLab From f00327731131d1b5aa6a1aa9f50bcf8d620ace4c Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Mon, 27 Mar 2023 16:47:47 +0000 Subject: [PATCH 1636/5631] KVM: arm64: Use config_lock to protect vgic state Almost all of the vgic state is VM-scoped but accessed from the context of a vCPU. These accesses were serialized on the kvm->lock which cannot be nested within a vcpu->mutex critical section. Move over the vgic state to using the config_lock. Tweak the lock ordering where necessary to ensure that the config_lock is acquired after the vcpu->mutex. Acquire the config_lock in kvm_vgic_create() to avoid a race between the converted flows and GIC creation. Where necessary, continue to acquire kvm->lock to avoid a race with vCPU creation (i.e. flows that use lock_all_vcpus()). Finally, promote the locking expectations in comments to lockdep assertions and update the locking documentation for the config_lock as well as vcpu->mutex. Cc: stable@vger.kernel.org Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230327164747.2466958-5-oliver.upton@linux.dev --- arch/arm64/kvm/vgic/vgic-debug.c | 8 ++--- arch/arm64/kvm/vgic/vgic-init.c | 36 ++++++++++++-------- arch/arm64/kvm/vgic/vgic-its.c | 18 ++++++---- arch/arm64/kvm/vgic/vgic-kvm-device.c | 47 ++++++++++++++++----------- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 4 +-- arch/arm64/kvm/vgic/vgic-mmio.c | 12 +++---- arch/arm64/kvm/vgic/vgic-v4.c | 11 ++++--- arch/arm64/kvm/vgic/vgic.c | 12 ++++--- 8 files changed, 88 insertions(+), 60 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 78cde687383c..07aa0437125a 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -85,7 +85,7 @@ static void *vgic_debug_start(struct seq_file *s, loff_t *pos) struct kvm *kvm = s->private; struct vgic_state_iter *iter; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; if (iter) { iter = ERR_PTR(-EBUSY); @@ -104,7 +104,7 @@ static void *vgic_debug_start(struct seq_file *s, loff_t *pos) if (end_of_vgic(iter)) iter = NULL; out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return iter; } @@ -132,12 +132,12 @@ static void vgic_debug_stop(struct seq_file *s, void *v) if (IS_ERR(v)) return; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; kfree(iter->lpi_array); kfree(iter); kvm->arch.vgic.iter = NULL; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } static void print_dist_state(struct seq_file *s, struct vgic_dist *dist) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index cd134db41a57..9d42c7cb2b58 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -74,9 +74,6 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) unsigned long i; int ret; - if (irqchip_in_kernel(kvm)) - return -EEXIST; - /* * This function is also called by the KVM_CREATE_IRQCHIP handler, * which had no chance yet to check the availability of the GICv2 @@ -87,10 +84,20 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; + /* Must be held to avoid race with vCPU creation */ + lockdep_assert_held(&kvm->lock); + ret = -EBUSY; if (!lock_all_vcpus(kvm)) return ret; + mutex_lock(&kvm->arch.config_lock); + + if (irqchip_in_kernel(kvm)) { + ret = -EEXIST; + goto out_unlock; + } + kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_has_run_once(vcpu)) goto out_unlock; @@ -118,6 +125,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: + mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); return ret; } @@ -227,9 +235,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); ret = vgic_register_redist_iodev(vcpu); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } return ret; } @@ -250,7 +258,6 @@ static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu) * The function is generally called when nr_spis has been explicitly set * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. * vgic_initialized() returns true when this function has succeeded. - * Must be called with kvm->lock held! */ int vgic_init(struct kvm *kvm) { @@ -259,6 +266,8 @@ int vgic_init(struct kvm *kvm) int ret = 0, i; unsigned long idx; + lockdep_assert_held(&kvm->arch.config_lock); + if (vgic_initialized(kvm)) return 0; @@ -373,12 +382,13 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; } -/* To be called with kvm->lock held */ static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) @@ -389,9 +399,9 @@ static void __kvm_vgic_destroy(struct kvm *kvm) void kvm_vgic_destroy(struct kvm *kvm) { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); __kvm_vgic_destroy(kvm); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } /** @@ -414,9 +424,9 @@ int vgic_lazy_init(struct kvm *kvm) if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); ret = vgic_init(kvm); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } return ret; @@ -441,7 +451,7 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (likely(vgic_ready(kvm))) return 0; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); if (vgic_ready(kvm)) goto out; @@ -459,7 +469,7 @@ int kvm_vgic_map_resources(struct kvm *kvm) dist->ready = true; out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 2642e9ce2819..7713cd06104e 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2045,6 +2045,13 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; + } + + mutex_lock(&dev->kvm->arch.config_lock); + if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -ENXIO; goto out; @@ -2058,11 +2065,6 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, goto out; } - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - addr = its->vgic_its_base + offset; len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; @@ -2076,8 +2078,9 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, } else { *reg = region->its_read(dev->kvm, its, addr, len); } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return ret; } @@ -2757,6 +2760,8 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) return -EBUSY; } + mutex_lock(&kvm->arch.config_lock); + switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: vgic_its_reset(kvm, its); @@ -2769,6 +2774,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) break; } + mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); mutex_unlock(&its->its_lock); mutex_unlock(&kvm->lock); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index edeac2380591..07e727023deb 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -46,7 +46,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev struct vgic_dist *vgic = &kvm->arch.vgic; int r; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -68,7 +68,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev r = -ENODEV; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return r; } @@ -102,7 +102,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (get_user(addr, uaddr)) return -EFAULT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -191,7 +191,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri } out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); if (!r && !write) r = put_user(addr, uaddr); @@ -227,7 +227,7 @@ static int vgic_set_common_attr(struct kvm_device *dev, (val & 31)) return -EINVAL; - mutex_lock(&dev->kvm->lock); + mutex_lock(&dev->kvm->arch.config_lock); if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; @@ -235,16 +235,16 @@ static int vgic_set_common_attr(struct kvm_device *dev, dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; - mutex_unlock(&dev->kvm->lock); + mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - mutex_lock(&dev->kvm->lock); + mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); - mutex_unlock(&dev->kvm->lock); + mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* @@ -260,7 +260,10 @@ static int vgic_set_common_attr(struct kvm_device *dev, mutex_unlock(&dev->kvm->lock); return -EBUSY; } + + mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); + mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; @@ -411,15 +414,17 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; + } + + mutex_lock(&dev->kvm->arch.config_lock); + ret = vgic_init(dev->kvm); if (ret) goto out; - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); @@ -432,8 +437,9 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev, break; } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) @@ -569,12 +575,14 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); - if (unlikely(!vgic_initialized(dev->kvm))) { - ret = -EBUSY; - goto out; + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; } - if (!lock_all_vcpus(dev->kvm)) { + mutex_lock(&dev->kvm->arch.config_lock); + + if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } @@ -609,8 +617,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, break; } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 91201f743033..472b18ac92a2 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -111,7 +111,7 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, case GICD_CTLR: { bool was_enabled, is_hwsgi; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); was_enabled = dist->enabled; is_hwsgi = dist->nassgireq; @@ -139,7 +139,7 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, else if (!was_enabled && dist->enabled) vgic_kick_vcpus(vcpu->kvm); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); break; } case GICD_TYPER: diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index e67b3b2c8044..1939c94e0b24 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -530,13 +530,13 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 val; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); val = __vgic_mmio_read_active(vcpu, addr, len); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); return val; } @@ -625,13 +625,13 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, @@ -662,13 +662,13 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index a413718be92b..3bb003478060 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -232,9 +232,8 @@ int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) * @kvm: Pointer to the VM being initialized * * We may be called each time a vITS is created, or when the - * vgic is initialized. This relies on kvm->lock to be - * held. In both cases, the number of vcpus should now be - * fixed. + * vgic is initialized. In both cases, the number of vcpus + * should now be fixed. */ int vgic_v4_init(struct kvm *kvm) { @@ -243,6 +242,8 @@ int vgic_v4_init(struct kvm *kvm) int nr_vcpus, ret; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ @@ -309,14 +310,14 @@ int vgic_v4_init(struct kvm *kvm) /** * vgic_v4_teardown - Free the GICv4 data structures * @kvm: Pointer to the VM being destroyed - * - * Relies on kvm->lock to be held. */ void vgic_v4_teardown(struct kvm *kvm) { struct its_vm *its_vm = &kvm->arch.vgic.its_vm; int i; + lockdep_assert_held(&kvm->arch.config_lock); + if (!its_vm->vpes) return; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index d97e6080b421..0a005da83ae6 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -24,11 +24,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { /* * Locking order is always: * kvm->lock (mutex) - * its->cmd_lock (mutex) - * its->its_lock (mutex) - * vgic_cpu->ap_list_lock must be taken with IRQs disabled - * kvm->lpi_list_lock must be taken with IRQs disabled - * vgic_irq->irq_lock must be taken with IRQs disabled + * vcpu->mutex (mutex) + * kvm->arch.config_lock (mutex) + * its->cmd_lock (mutex) + * its->its_lock (mutex) + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, * we have to disable IRQs before taking this lock and everything lower -- GitLab From 61f21988d806a5c93c39179f2d91ea2d3219b025 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 29 Mar 2023 13:34:26 +0100 Subject: [PATCH 1637/5631] docs: driver-api: firmware_loader: fix missing argument in usage example By the time firmware-upload support landed in commit 97730bbb242c ("firmware_loader: Add firmware-upload support"), the arguments for firmware_upload_register() had changed, and while this is automagically represented in the kernel doc bits, the usage example was not kept in sync. Add the missing argument as per the driver. Fixes: 97730bbb242c ("firmware_loader: Add firmware-upload support") Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230329123425.4177084-1-conor.dooley@microchip.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/firmware/fw_upload.rst | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/driver-api/firmware/fw_upload.rst b/Documentation/driver-api/firmware/fw_upload.rst index 76922591e446..edf1d0c5e7c3 100644 --- a/Documentation/driver-api/firmware/fw_upload.rst +++ b/Documentation/driver-api/firmware/fw_upload.rst @@ -57,7 +57,8 @@ function calls firmware_upload_unregister() such as:: len = (truncate) ? truncate - fw_name : strlen(fw_name); sec->fw_name = kmemdup_nul(fw_name, len, GFP_KERNEL); - fwl = firmware_upload_register(sec->dev, sec->fw_name, &m10bmc_ops, sec); + fwl = firmware_upload_register(THIS_MODULE, sec->dev, sec->fw_name, + &m10bmc_ops, sec); if (IS_ERR(fwl)) { dev_err(sec->dev, "Firmware Upload driver failed to start\n"); kfree(sec->fw_name); -- GitLab From d490be6dd8aa3194d8b5d509846275b4b2b2ac38 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 24 Mar 2023 17:49:56 +0100 Subject: [PATCH 1638/5631] pinctrl: mcp23s08: Rename and change function that wraps regmap_update_bits() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The semantic of mcp_set_mask() was surprising to me when I first read that driver. So it was unexpected that in the call mcp_set_mask(mcp, MCP_OLAT, mask, value); value was a bool. Make the function a thinner wrapper around regmap_update_bits() and rename it to also have a similar name. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230324164957.485924-2-u.kleine-koenig@pengutronix.de Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-mcp23s08.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 5f356edfd0fd..79a41d418482 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -144,10 +144,9 @@ static int mcp_write(struct mcp23s08 *mcp, unsigned int reg, unsigned int val) return regmap_write(mcp->regmap, reg << mcp->reg_shift, val); } -static int mcp_set_mask(struct mcp23s08 *mcp, unsigned int reg, - unsigned int mask, bool enabled) +static int mcp_update_bits(struct mcp23s08 *mcp, unsigned int reg, + unsigned int mask, unsigned int val) { - u16 val = enabled ? 0xffff : 0x0000; return regmap_update_bits(mcp->regmap, reg << mcp->reg_shift, mask, val); } @@ -156,7 +155,7 @@ static int mcp_set_bit(struct mcp23s08 *mcp, unsigned int reg, unsigned int pin, bool enabled) { u16 mask = BIT(pin); - return mcp_set_mask(mcp, reg, mask, enabled); + return mcp_update_bits(mcp, reg, mask, enabled ? mask : 0); } static const struct pinctrl_pin_desc mcp23x08_pins[] = { @@ -310,7 +309,7 @@ static int mcp23s08_get(struct gpio_chip *chip, unsigned offset) static int __mcp23s08_set(struct mcp23s08 *mcp, unsigned mask, bool value) { - return mcp_set_mask(mcp, MCP_OLAT, mask, value); + return mcp_update_bits(mcp, MCP_OLAT, mask, value ? mask : 0); } static void mcp23s08_set(struct gpio_chip *chip, unsigned offset, int value) @@ -333,7 +332,7 @@ mcp23s08_direction_output(struct gpio_chip *chip, unsigned offset, int value) mutex_lock(&mcp->lock); status = __mcp23s08_set(mcp, mask, value); if (status == 0) { - status = mcp_set_mask(mcp, MCP_IODIR, mask, false); + status = mcp_update_bits(mcp, MCP_IODIR, mask, 0); } mutex_unlock(&mcp->lock); return status; -- GitLab From c458290702441f2e9eac22001ef52ae82717160a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 24 Mar 2023 17:49:57 +0100 Subject: [PATCH 1639/5631] pinctrl: mcp23s08: Implement gpio bulk functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To speed up some usecases implement reading and writing several IO lines at once. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230324164957.485924-3-u.kleine-koenig@pengutronix.de Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-mcp23s08.c | 34 ++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 79a41d418482..8ec7f2a3d009 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -307,6 +307,28 @@ static int mcp23s08_get(struct gpio_chip *chip, unsigned offset) return status; } +static int mcp23s08_get_multiple(struct gpio_chip *chip, + unsigned long *mask, unsigned long *bits) +{ + struct mcp23s08 *mcp = gpiochip_get_data(chip); + unsigned int status; + int ret; + + mutex_lock(&mcp->lock); + + /* REVISIT reading this clears any IRQ ... */ + ret = mcp_read(mcp, MCP_GPIO, &status); + if (ret < 0) + status = 0; + else { + mcp->cached_gpio = status; + *bits = status; + } + + mutex_unlock(&mcp->lock); + return ret; +} + static int __mcp23s08_set(struct mcp23s08 *mcp, unsigned mask, bool value) { return mcp_update_bits(mcp, MCP_OLAT, mask, value ? mask : 0); @@ -322,6 +344,16 @@ static void mcp23s08_set(struct gpio_chip *chip, unsigned offset, int value) mutex_unlock(&mcp->lock); } +static void mcp23s08_set_multiple(struct gpio_chip *chip, + unsigned long *mask, unsigned long *bits) +{ + struct mcp23s08 *mcp = gpiochip_get_data(chip); + + mutex_lock(&mcp->lock); + mcp_update_bits(mcp, MCP_OLAT, *mask, *bits); + mutex_unlock(&mcp->lock); +} + static int mcp23s08_direction_output(struct gpio_chip *chip, unsigned offset, int value) { @@ -546,8 +578,10 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, mcp->chip.direction_input = mcp23s08_direction_input; mcp->chip.get = mcp23s08_get; + mcp->chip.get_multiple = mcp23s08_get_multiple; mcp->chip.direction_output = mcp23s08_direction_output; mcp->chip.set = mcp23s08_set; + mcp->chip.set_multiple = mcp23s08_set_multiple; mcp->chip.base = base; mcp->chip.can_sleep = true; -- GitLab From a8fd44cbd283cb9825f9d799da14234148e5a4dd Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Sun, 19 Mar 2023 14:49:03 +0700 Subject: [PATCH 1640/5631] Documentation: leds: MT6370: Use bullet lists for timing variables The timing description contains list of timing pattern variables, but it uses code block without indentation instead. Switch to bullet list as it is better fit for this purpose. While at it, substitute "load" for "duty" because the variables control timing for current load into the device. Link: https://lore.kernel.org/oe-kbuild-all/202303182310.tB1mUzU7-lkp@intel.com/ Fixes: 4ba9df04b7ac66 ("docs: leds: Add MT6370 RGB LED pattern document") Reported-by: kernel test robot Signed-off-by: Bagas Sanjaya Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230319074903.13075-4-bagasdotme@gmail.com --- Documentation/leds/leds-mt6370-rgb.rst | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/Documentation/leds/leds-mt6370-rgb.rst b/Documentation/leds/leds-mt6370-rgb.rst index ea782797a06d..152a2e592172 100644 --- a/Documentation/leds/leds-mt6370-rgb.rst +++ b/Documentation/leds/leds-mt6370-rgb.rst @@ -45,17 +45,17 @@ Pattern diagram:: +----------------------------------============------------> Time < Tr1>< Ton >< Toff >< Tr1> -Timing description:: +Timing description: -Tr1: First rising time for duty 0 to 30%. -Tr2: Second rising time for duty 31% to 100%. -Ton: On time for duty 100%. -Tf1: First falling time for duty 100% to 31%. -Tf2: Second falling time for duty 30% to 0%. -Toff: Off time for duty 0%. + * Tr1: First rising time for 0% - 30% load. + * Tr2: Second rising time for 31% - 100% load. + * Ton: On time for 100% load. + * Tf1: First falling time for 100% - 31% load. + * Tf2: Second falling time for 30% to 0% load. + * Toff: Off time for 0% load. -Tr1/Tr2/Tf1/Tf2/Ton: 125ms to 3125ms, 200ms per step. -Toff: 250ms to 6250ms, 400ms per step. + * Tr1/Tr2/Tf1/Tf2/Ton: 125ms to 3125ms, 200ms per step. + * Toff: 250ms to 6250ms, 400ms per step. Pattern example:: -- GitLab From df59b72cd8fb8ca00301f47e65853efed195d23f Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 17 Mar 2023 11:15:06 -0400 Subject: [PATCH 1641/5631] cgroup/cpuset: Skip task update if hotplug doesn't affect current cpuset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a hotplug event doesn't affect the current cpuset, there is no point to call hotplug_update_tasks() or hotplug_update_tasks_legacy(). So just skip it. Signed-off-by: Waiman Long Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8472c711eb1b..a05bc93215ac 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3516,6 +3516,8 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); + if (!cpus_updated && !mems_updated) + goto unlock; /* Hotplug doesn't affect this cpuset */ if (mems_updated) check_insane_mems_config(&new_mems); @@ -3527,6 +3529,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); +unlock: percpu_up_write(&cpuset_rwsem); } -- GitLab From 6667439f51c446fead5d991ff49b842a811a6195 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 17 Mar 2023 11:15:07 -0400 Subject: [PATCH 1642/5631] cgroup/cpuset: Include offline CPUs when tasks' cpumasks in top_cpuset are updated Similar to commit 3fb906e7fabb ("group/cpuset: Don't filter offline CPUs in cpuset_cpus_allowed() for top cpuset tasks"), the whole set of possible CPUs including offline ones should be used for setting cpumasks for tasks in the top cpuset when a cpuset partition is modified as the hotplug code won't update cpumasks for tasks in the top cpuset when CPUs become online or offline. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a05bc93215ac..bc4dcfd7bee5 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1209,7 +1209,9 @@ void rebuild_sched_domains(void) * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_rwsem held, - * cpuset membership stays stable. + * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask() + * is used instead of effective_cpus to make sure all offline CPUs are also + * included as hotplug code won't update cpumasks for tasks in top_cpuset. */ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { @@ -1219,15 +1221,18 @@ static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { - /* - * Percpu kthreads in top_cpuset are ignored - */ - if (top_cs && (task->flags & PF_KTHREAD) && - kthread_is_per_cpu(task)) - continue; + const struct cpumask *possible_mask = task_cpu_possible_mask(task); - cpumask_and(new_cpus, cs->effective_cpus, - task_cpu_possible_mask(task)); + if (top_cs) { + /* + * Percpu kthreads in top_cpuset are ignored + */ + if ((task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) + continue; + cpumask_andnot(new_cpus, possible_mask, cs->subparts_cpus); + } else { + cpumask_and(new_cpus, possible_mask, cs->effective_cpus); + } set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); -- GitLab From 1bf33285d98536da6b015627341e4f789fee067e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 17 Mar 2023 11:15:08 -0400 Subject: [PATCH 1643/5631] cgroup/cpuset: Minor updates to test_cpuset_prs.sh This patch makes the following minor updates to the cpuset partition testing script test_cpuset_prs.sh. - Remove online_cpus function call as it will be called anyway on exit in cleanup. - Make the enabling of sched/verbose debugfs flag conditional on the "-v" verbose option and set DELAY_FACTOR to 2 in this case as cpuset partition operations are likely to be slowed down by enabling that. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- .../selftests/cgroup/test_cpuset_prs.sh | 25 +++++++++++-------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 75c100de90ff..2b5215cc599f 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -15,13 +15,6 @@ skip_test() { [[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!" -# Set sched verbose flag, if available -if [[ -d /sys/kernel/debug/sched ]] -then - # Used to restore the original setting during cleanup - SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose) - echo Y > /sys/kernel/debug/sched/verbose -fi # Get wait_inotify location WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify @@ -37,10 +30,14 @@ CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//") PROG=$1 VERBOSE= DELAY_FACTOR=1 +SCHED_DEBUG= while [[ "$1" = -* ]] do case "$1" in -v) VERBOSE=1 + # Enable sched/verbose can slow thing down + [[ $DELAY_FACTOR -eq 1 ]] && + DELAY_FACTOR=2 break ;; -d) DELAY_FACTOR=$2 @@ -54,6 +51,14 @@ do shift done +# Set sched verbose flag if available when "-v" option is specified +if [[ -n "$VERBOSE" && -d /sys/kernel/debug/sched ]] +then + # Used to restore the original setting during cleanup + SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose) + echo Y > /sys/kernel/debug/sched/verbose +fi + cd $CGROUP2 echo +cpuset > cgroup.subtree_control [[ -d test ]] || mkdir test @@ -65,7 +70,8 @@ cleanup() rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1 cd .. rmdir test > /dev/null 2>&1 - echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose + [[ -n "$SCHED_DEBUG" ]] && + echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose } # Pause in ms @@ -571,7 +577,6 @@ run_state_test() echo "Test $TEST[$I] failed result check!" eval echo \"\${$TEST[$I]}\" dump_states - online_cpus exit 1 } @@ -582,7 +587,6 @@ run_state_test() eval echo \"\${$TEST[$I]}\" echo dump_states - online_cpus exit 1 } } @@ -594,7 +598,6 @@ run_state_test() eval echo \"\${$TEST[$I]}\" echo dump_states - online_cpus exit 1 } } -- GitLab From 12ca59b91d04df32e41be5a52f0cabba912c11de Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 7 Mar 2023 14:29:28 +0100 Subject: [PATCH 1644/5631] clk: Print an info line before disabling unused clocks Currently, the regulator framework informs us before calling into their unused cleanup paths, which eases at least some debugging. The same could be beneficial for clocks, so that random shutdowns shortly after most initcalls are done can be less of a guess. Add a pr_info before disabling unused clocks to do so. Reviewed-by: Marijn Suijten Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230307132928.3887737-1-konrad.dybcio@linaro.org Signed-off-by: Stephen Boyd --- drivers/clk/clk.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9410a4e1b04b..663933c52efa 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1406,6 +1406,8 @@ static int __init clk_disable_unused(void) return 0; } + pr_info("clk: Disabling unused clocks\n"); + clk_prepare_lock(); hlist_for_each_entry(core, &clk_root_list, child_node) -- GitLab From d34a6b715a23ccd9c9d0bc7a475bea59dc3e28b2 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 24 Mar 2023 12:12:41 +0000 Subject: [PATCH 1645/5631] RISC-V: convert new selectors of RISCV_ALTERNATIVE to dependencies for-next contains two additional extensions that select RISCV_ALTERNATIVE. RISCV_ALTERNATIVE no longer needs to be selected by individual config options as it is now selected for !XIP_KERNEL builds by the top level RISCV option. These extensions rely on the alternative framework, so convert the "select"s to "depends on"s instead. Signed-off-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230324121240.3594777-1-conor.dooley@microchip.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b47c08364dc3..cc02eb9eee1f 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -402,8 +402,8 @@ config RISCV_ISA_C config RISCV_ISA_SVNAPOT bool "SVNAPOT extension support" depends on 64BIT && MMU + depends on RISCV_ALTERNATIVE default y - select RISCV_ALTERNATIVE help Allow kernel to detect the SVNAPOT ISA-extension dynamically at boot time and enable its usage. @@ -478,8 +478,8 @@ config RISCV_ISA_ZICBOM config RISCV_ISA_ZICBOZ bool "Zicboz extension support for faster zeroing of memory" - depends on !XIP_KERNEL && MMU - select RISCV_ALTERNATIVE + depends on MMU + depends on RISCV_ALTERNATIVE default y help Enable the use of the ZICBOZ extension (cbo.zero instruction) -- GitLab From 27a2195efa8d26447c40dd4a6299ea0247786d75 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:55 +0100 Subject: [PATCH 1646/5631] power: supply: core: auto-exposure of simple-battery data Automatically expose data from the simple-battery firmware node for all battery drivers. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_core.c | 179 +++++++++++++++++++--- drivers/power/supply/power_supply_sysfs.c | 23 ++- include/linux/power_supply.h | 8 + 3 files changed, 191 insertions(+), 19 deletions(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index f3d7c1da299f..b2504d205035 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -388,7 +388,7 @@ static int __power_supply_get_supplier_property(struct device *dev, void *_data) struct psy_get_supplier_prop_data *data = _data; if (__power_supply_is_supplied_by(epsy, data->psy)) - if (!epsy->desc->get_property(epsy, data->psp, data->val)) + if (!power_supply_get_property(epsy, data->psp, data->val)) return 1; /* Success */ return 0; /* Continue iterating */ @@ -832,6 +832,133 @@ void power_supply_put_battery_info(struct power_supply *psy, } EXPORT_SYMBOL_GPL(power_supply_put_battery_info); +const enum power_supply_property power_supply_battery_info_properties[] = { + POWER_SUPPLY_PROP_TECHNOLOGY, + POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN, + POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, + POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, + POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN, + POWER_SUPPLY_PROP_PRECHARGE_CURRENT, + POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, + POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX, + POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX, + POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN, + POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX, + POWER_SUPPLY_PROP_TEMP_ALERT_MIN, + POWER_SUPPLY_PROP_TEMP_ALERT_MAX, + POWER_SUPPLY_PROP_TEMP_MIN, + POWER_SUPPLY_PROP_TEMP_MAX, +}; +EXPORT_SYMBOL_GPL(power_supply_battery_info_properties); + +const size_t power_supply_battery_info_properties_size = ARRAY_SIZE(power_supply_battery_info_properties); +EXPORT_SYMBOL_GPL(power_supply_battery_info_properties_size); + +bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, + enum power_supply_property psp) +{ + if (!info) + return false; + + switch (psp) { + case POWER_SUPPLY_PROP_TECHNOLOGY: + return info->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN; + case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: + return info->energy_full_design_uwh >= 0; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + return info->charge_full_design_uah >= 0; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + return info->voltage_min_design_uv >= 0; + case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: + return info->voltage_max_design_uv >= 0; + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + return info->precharge_current_ua >= 0; + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: + return info->charge_term_current_ua >= 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + return info->constant_charge_current_max_ua >= 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: + return info->constant_charge_voltage_max_uv >= 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: + return info->temp_ambient_alert_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: + return info->temp_ambient_alert_max < INT_MAX; + case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: + return info->temp_alert_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: + return info->temp_alert_max < INT_MAX; + case POWER_SUPPLY_PROP_TEMP_MIN: + return info->temp_min > INT_MIN; + case POWER_SUPPLY_PROP_TEMP_MAX: + return info->temp_max < INT_MAX; + default: + return false; + } +} +EXPORT_SYMBOL_GPL(power_supply_battery_info_has_prop); + +int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, + enum power_supply_property psp, + union power_supply_propval *val) +{ + if (!info) + return -EINVAL; + + if (!power_supply_battery_info_has_prop(info, psp)) + return -EINVAL; + + switch (psp) { + case POWER_SUPPLY_PROP_TECHNOLOGY: + val->intval = info->technology; + return 0; + case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN: + val->intval = info->energy_full_design_uwh; + return 0; + case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: + val->intval = info->charge_full_design_uah; + return 0; + case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: + val->intval = info->voltage_min_design_uv; + return 0; + case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: + val->intval = info->voltage_max_design_uv; + return 0; + case POWER_SUPPLY_PROP_PRECHARGE_CURRENT: + val->intval = info->precharge_current_ua; + return 0; + case POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT: + val->intval = info->charge_term_current_ua; + return 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX: + val->intval = info->constant_charge_current_max_ua; + return 0; + case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE_MAX: + val->intval = info->constant_charge_voltage_max_uv; + return 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MIN: + val->intval = info->temp_ambient_alert_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_AMBIENT_ALERT_MAX: + val->intval = info->temp_ambient_alert_max; + return 0; + case POWER_SUPPLY_PROP_TEMP_ALERT_MIN: + val->intval = info->temp_alert_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_ALERT_MAX: + val->intval = info->temp_alert_max; + return 0; + case POWER_SUPPLY_PROP_TEMP_MIN: + val->intval = info->temp_min; + return 0; + case POWER_SUPPLY_PROP_TEMP_MAX: + val->intval = info->temp_max; + return 0; + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(power_supply_battery_info_get_prop); + /** * power_supply_temp2resist_simple() - find the battery internal resistance * percent from temperature @@ -1046,6 +1173,22 @@ bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, } EXPORT_SYMBOL_GPL(power_supply_battery_bti_in_range); +static bool psy_has_property(const struct power_supply_desc *psy_desc, + enum power_supply_property psp) +{ + bool found = false; + int i; + + for (i = 0; i < psy_desc->num_properties; i++) { + if (psy_desc->properties[i] == psp) { + found = true; + break; + } + } + + return found; +} + int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) @@ -1056,7 +1199,12 @@ int power_supply_get_property(struct power_supply *psy, return -ENODEV; } - return psy->desc->get_property(psy, psp, val); + if (psy_has_property(psy->desc, psp)) + return psy->desc->get_property(psy, psp, val); + else if (power_supply_battery_info_has_prop(psy->battery_info, psp)) + return power_supply_battery_info_get_prop(psy->battery_info, psp, val); + else + return -EINVAL; } EXPORT_SYMBOL_GPL(power_supply_get_property); @@ -1117,22 +1265,6 @@ void power_supply_unreg_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(power_supply_unreg_notifier); -static bool psy_has_property(const struct power_supply_desc *psy_desc, - enum power_supply_property psp) -{ - bool found = false; - int i; - - for (i = 0; i < psy_desc->num_properties; i++) { - if (psy_desc->properties[i] == psp) { - found = true; - break; - } - } - - return found; -} - #ifdef CONFIG_THERMAL static int power_supply_read_temp(struct thermal_zone_device *tzd, int *temp) @@ -1255,6 +1387,17 @@ __power_supply_register(struct device *parent, goto check_supplies_failed; } + /* + * Expose constant battery info, if it is available. While there are + * some chargers accessing constant battery data, we only want to + * expose battery data to userspace for battery devices. + */ + if (desc->type == POWER_SUPPLY_TYPE_BATTERY) { + rc = power_supply_get_battery_info(psy, &psy->battery_info); + if (rc && rc != -ENODEV && rc != -ENOENT) + goto check_supplies_failed; + } + spin_lock_init(&psy->changed_lock); rc = device_add(dev); if (rc) diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index c228205e0953..ba3b125cd66e 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -221,9 +221,10 @@ static struct power_supply_attr power_supply_attrs[] = { POWER_SUPPLY_ATTR(MANUFACTURER), POWER_SUPPLY_ATTR(SERIAL_NUMBER), }; +#define POWER_SUPPLY_ATTR_CNT ARRAY_SIZE(power_supply_attrs) static struct attribute * -__power_supply_attrs[ARRAY_SIZE(power_supply_attrs) + 1]; +__power_supply_attrs[POWER_SUPPLY_ATTR_CNT + 1]; static struct power_supply_attr *to_ps_attr(struct device_attribute *attr) { @@ -380,6 +381,9 @@ static umode_t power_supply_attr_is_visible(struct kobject *kobj, } } + if (power_supply_battery_info_has_prop(psy->battery_info, attrno)) + return mode; + return 0; } @@ -461,6 +465,10 @@ static int add_prop_uevent(const struct device *dev, struct kobj_uevent_env *env int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct power_supply *psy = dev_get_drvdata(dev); + const enum power_supply_property *battery_props = + power_supply_battery_info_properties; + unsigned long psy_drv_properties[POWER_SUPPLY_ATTR_CNT / + sizeof(unsigned long) + 1] = {0}; int ret = 0, j; char *prop_buf; @@ -482,12 +490,25 @@ int power_supply_uevent(const struct device *dev, struct kobj_uevent_env *env) goto out; for (j = 0; j < psy->desc->num_properties; j++) { + set_bit(psy->desc->properties[j], psy_drv_properties); ret = add_prop_uevent(dev, env, psy->desc->properties[j], prop_buf); if (ret) goto out; } + for (j = 0; j < power_supply_battery_info_properties_size; j++) { + if (test_bit(battery_props[j], psy_drv_properties)) + continue; + if (!power_supply_battery_info_has_prop(psy->battery_info, + battery_props[j])) + continue; + ret = add_prop_uevent(dev, env, battery_props[j], + prop_buf); + if (ret) + goto out; + } + out: free_page((unsigned long)prop_buf); diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index aa2c4a7c4826..a427f13c757f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -301,6 +301,7 @@ struct power_supply { bool initialized; bool removing; atomic_t use_cnt; + struct power_supply_battery_info *battery_info; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; @@ -791,10 +792,17 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ +extern const enum power_supply_property power_supply_battery_info_properties[]; +extern const size_t power_supply_battery_info_properties_size; extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); +extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, + enum power_supply_property psp); +extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, int table_len, int ocv); extern struct power_supply_battery_ocv_table * -- GitLab From 93297ef6920f071ed109cbdcf640edfc693d0456 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:56 +0100 Subject: [PATCH 1647/5631] power: supply: generic-adc-battery: convert to managed resources Convert driver to use managed resources to simplify driver code. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 81 ++++++---------------- 1 file changed, 23 insertions(+), 58 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 66039c665dd1..917bd2a6cc52 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -23,6 +23,7 @@ #include #include #include +#include #define JITTER_DEFAULT 10 /* hope 10ms is enough */ @@ -266,14 +267,13 @@ static int gab_probe(struct platform_device *pdev) * copying the static properties and allocating extra memory for holding * the extra configurable properties received from platform data. */ - properties = kcalloc(ARRAY_SIZE(gab_props) + - ARRAY_SIZE(gab_chan_name), - sizeof(*properties), - GFP_KERNEL); - if (!properties) { - ret = -ENOMEM; - goto first_mem_fail; - } + properties = devm_kcalloc(&pdev->dev, + ARRAY_SIZE(gab_props) + + ARRAY_SIZE(gab_chan_name), + sizeof(*properties), + GFP_KERNEL); + if (!properties) + return -ENOMEM; memcpy(properties, gab_props, sizeof(gab_props)); @@ -282,12 +282,13 @@ static int gab_probe(struct platform_device *pdev) * based on the channel supported by consumer device. */ for (chan = 0; chan < ARRAY_SIZE(gab_chan_name); chan++) { - adc_bat->channel[chan] = iio_channel_get(&pdev->dev, - gab_chan_name[chan]); + adc_bat->channel[chan] = devm_iio_channel_get(&pdev->dev, gab_chan_name[chan]); if (IS_ERR(adc_bat->channel[chan])) { ret = PTR_ERR(adc_bat->channel[chan]); + if (ret != -ENODEV) + return dev_err_probe(&pdev->dev, ret, "Failed to get ADC channel %s\n", gab_chan_name[chan]); adc_bat->channel[chan] = NULL; - } else { + } else if (adc_bat->channel[chan]) { /* copying properties for supported channels only */ int index2; @@ -302,10 +303,8 @@ static int gab_probe(struct platform_device *pdev) } /* none of the channels are supported so let's bail out */ - if (!any) { - ret = -ENODEV; - goto second_mem_fail; - } + if (!any) + return dev_err_probe(&pdev->dev, -ENODEV, "Failed to get any ADC channel\n"); /* * Total number of properties is equal to static properties @@ -316,25 +315,24 @@ static int gab_probe(struct platform_device *pdev) psy_desc->properties = properties; psy_desc->num_properties = index; - adc_bat->psy = power_supply_register(&pdev->dev, psy_desc, &psy_cfg); - if (IS_ERR(adc_bat->psy)) { - ret = PTR_ERR(adc_bat->psy); - goto err_reg_fail; - } + adc_bat->psy = devm_power_supply_register(&pdev->dev, psy_desc, &psy_cfg); + if (IS_ERR(adc_bat->psy)) + return dev_err_probe(&pdev->dev, PTR_ERR(adc_bat->psy), "Failed to register power-supply device\n"); - INIT_DELAYED_WORK(&adc_bat->bat_work, gab_work); + ret = devm_delayed_work_autocancel(&pdev->dev, &adc_bat->bat_work, gab_work); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to register delayed work\n"); - adc_bat->charge_finished = devm_gpiod_get_optional(&pdev->dev, - "charged", GPIOD_IN); + adc_bat->charge_finished = devm_gpiod_get_optional(&pdev->dev, "charged", GPIOD_IN); if (adc_bat->charge_finished) { int irq; irq = gpiod_to_irq(adc_bat->charge_finished); - ret = request_any_context_irq(irq, gab_charged, + ret = devm_request_any_context_irq(&pdev->dev, irq, gab_charged, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING, "battery charged", adc_bat); if (ret < 0) - goto gpio_req_fail; + return dev_err_probe(&pdev->dev, ret, "Failed to register irq\n"); } platform_set_drvdata(pdev, adc_bat); @@ -343,38 +341,6 @@ static int gab_probe(struct platform_device *pdev) schedule_delayed_work(&adc_bat->bat_work, msecs_to_jiffies(0)); return 0; - -gpio_req_fail: - power_supply_unregister(adc_bat->psy); -err_reg_fail: - for (chan = 0; chan < ARRAY_SIZE(gab_chan_name); chan++) { - if (adc_bat->channel[chan]) - iio_channel_release(adc_bat->channel[chan]); - } -second_mem_fail: - kfree(properties); -first_mem_fail: - return ret; -} - -static int gab_remove(struct platform_device *pdev) -{ - int chan; - struct gab *adc_bat = platform_get_drvdata(pdev); - - power_supply_unregister(adc_bat->psy); - - if (adc_bat->charge_finished) - free_irq(gpiod_to_irq(adc_bat->charge_finished), adc_bat); - - for (chan = 0; chan < ARRAY_SIZE(gab_chan_name); chan++) { - if (adc_bat->channel[chan]) - iio_channel_release(adc_bat->channel[chan]); - } - - kfree(adc_bat->psy_desc.properties); - cancel_delayed_work_sync(&adc_bat->bat_work); - return 0; } static int __maybe_unused gab_suspend(struct device *dev) @@ -408,7 +374,6 @@ static struct platform_driver gab_driver = { .pm = &gab_pm_ops, }, .probe = gab_probe, - .remove = gab_remove, }; module_platform_driver(gab_driver); -- GitLab From 44263f50065969f2344808388bd589740f026167 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:57 +0100 Subject: [PATCH 1648/5631] power: supply: generic-adc-battery: fix unit scaling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit power-supply properties are reported in µV, µA and µW. The IIO API provides mV, mA, mW, so the values need to be multiplied by 1000. Fixes: e60fea794e6e ("power: battery: Generic battery driver using IIO") Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 917bd2a6cc52..535972a332b3 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -136,6 +136,9 @@ static int read_channel(struct gab *adc_bat, enum power_supply_property psp, result); if (ret < 0) pr_err("read channel error\n"); + else + *result *= 1000; + return ret; } -- GitLab From c8f573f312f36861db8e40d9953b6d4b84f1321b Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:58 +0100 Subject: [PATCH 1649/5631] power: supply: generic-adc-battery: drop jitter delay support Drop support for configuring IRQ jitter delay by using big enough fixed value. Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 13 ++++--------- include/linux/power/generic-adc-battery.h | 3 --- 2 files changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 535972a332b3..e20894460d7f 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -227,12 +227,10 @@ static void gab_work(struct work_struct *work) static irqreturn_t gab_charged(int irq, void *dev_id) { struct gab *adc_bat = dev_id; - struct gab_platform_data *pdata = adc_bat->pdata; - int delay; - delay = pdata->jitter_delay ? pdata->jitter_delay : JITTER_DEFAULT; schedule_delayed_work(&adc_bat->bat_work, - msecs_to_jiffies(delay)); + msecs_to_jiffies(JITTER_DEFAULT)); + return IRQ_HANDLED; } @@ -358,14 +356,11 @@ static int __maybe_unused gab_suspend(struct device *dev) static int __maybe_unused gab_resume(struct device *dev) { struct gab *adc_bat = dev_get_drvdata(dev); - struct gab_platform_data *pdata = adc_bat->pdata; - int delay; - - delay = pdata->jitter_delay ? pdata->jitter_delay : JITTER_DEFAULT; /* Schedule timer to check current status */ schedule_delayed_work(&adc_bat->bat_work, - msecs_to_jiffies(delay)); + msecs_to_jiffies(JITTER_DEFAULT)); + return 0; } diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h index c68cbf34cd34..50eb4bf28286 100644 --- a/include/linux/power/generic-adc-battery.h +++ b/include/linux/power/generic-adc-battery.h @@ -11,13 +11,10 @@ * @battery_info: recommended structure to specify static power supply * parameters * @cal_charge: calculate charge level. - * @jitter_delay: delay required after the interrupt to check battery - * status.Default set is 10ms. */ struct gab_platform_data { struct power_supply_info battery_info; int (*cal_charge)(long value); - int jitter_delay; }; #endif /* GENERIC_ADC_BATTERY_H */ -- GitLab From 3b6fd262bfcd696aa98af99d71dcf952f289cbee Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:56:59 +0100 Subject: [PATCH 1650/5631] power: supply: generic-adc-battery: drop charge now support Drop CHARGE_NOW support, which requires a platform specific calculation method. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 4 ---- include/linux/power/generic-adc-battery.h | 2 -- 2 files changed, 6 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index e20894460d7f..d07eeb7d46d3 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -72,7 +72,6 @@ static const enum power_supply_property gab_props[] = { POWER_SUPPLY_PROP_STATUS, POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, POWER_SUPPLY_PROP_CHARGE_EMPTY_DESIGN, - POWER_SUPPLY_PROP_CHARGE_NOW, POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_CURRENT_NOW, POWER_SUPPLY_PROP_TECHNOLOGY, @@ -166,9 +165,6 @@ static int gab_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_CHARGE_EMPTY_DESIGN: val->intval = 0; break; - case POWER_SUPPLY_PROP_CHARGE_NOW: - val->intval = pdata->cal_charge(result); - break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: case POWER_SUPPLY_PROP_CURRENT_NOW: case POWER_SUPPLY_PROP_POWER_NOW: diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h index 50eb4bf28286..54434e4304d3 100644 --- a/include/linux/power/generic-adc-battery.h +++ b/include/linux/power/generic-adc-battery.h @@ -10,11 +10,9 @@ * struct gab_platform_data - platform_data for generic adc iio battery driver. * @battery_info: recommended structure to specify static power supply * parameters - * @cal_charge: calculate charge level. */ struct gab_platform_data { struct power_supply_info battery_info; - int (*cal_charge)(long value); }; #endif /* GENERIC_ADC_BATTERY_H */ -- GitLab From 2f25b9750fa0d79090cadf6e7d0e3edba4fa58e3 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:00 +0100 Subject: [PATCH 1651/5631] power: supply: generic-adc-battery: drop memory alloc error message Error printing happens automatically for memory allocation problems. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index d07eeb7d46d3..771e5cfc49c3 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -243,10 +243,8 @@ static int gab_probe(struct platform_device *pdev) bool any = false; adc_bat = devm_kzalloc(&pdev->dev, sizeof(*adc_bat), GFP_KERNEL); - if (!adc_bat) { - dev_err(&pdev->dev, "failed to allocate memory\n"); + if (!adc_bat) return -ENOMEM; - } psy_cfg.drv_data = adc_bat; psy_desc = &adc_bat->psy_desc; -- GitLab From 1b27bf793fd46219c882b8e545ec736cfadc0841 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:01 +0100 Subject: [PATCH 1652/5631] power: supply: generic-adc-battery: use simple-battery API Constant battery data is available through power-supply's simple-battery API. This works automatically, so the manual handling can be removed without loosing any feature :) Note, that the POWER_SUPPLY_STATUS_FULL check for the level variable can be dropped, since the variable is never written. It can be re-introduced properly once the driver gets functionality to calculate the current charge level. Apart from that the check must be done fuzzy anyways, since charge estimation usually is not precise enough to always return exactly the full charge capacity for a full battery. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 60 ++-------------------- include/linux/power/generic-adc-battery.h | 18 ------- 2 files changed, 4 insertions(+), 74 deletions(-) delete mode 100644 include/linux/power/generic-adc-battery.h diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 771e5cfc49c3..42765cbf7518 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #define JITTER_DEFAULT 10 /* hope 10ms is enough */ @@ -48,9 +47,7 @@ struct gab { struct power_supply *psy; struct power_supply_desc psy_desc; struct iio_channel *channel[GAB_MAX_CHAN_TYPE]; - struct gab_platform_data *pdata; struct delayed_work bat_work; - int level; int status; bool cable_plugged; struct gpio_desc *charge_finished; @@ -70,14 +67,6 @@ static void gab_ext_power_changed(struct power_supply *psy) static const enum power_supply_property gab_props[] = { POWER_SUPPLY_PROP_STATUS, - POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN, - POWER_SUPPLY_PROP_CHARGE_EMPTY_DESIGN, - POWER_SUPPLY_PROP_VOLTAGE_NOW, - POWER_SUPPLY_PROP_CURRENT_NOW, - POWER_SUPPLY_PROP_TECHNOLOGY, - POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN, - POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN, - POWER_SUPPLY_PROP_MODEL_NAME, }; /* @@ -97,17 +86,6 @@ static bool gab_charge_finished(struct gab *adc_bat) return gpiod_get_value(adc_bat->charge_finished); } -static int gab_get_status(struct gab *adc_bat) -{ - struct gab_platform_data *pdata = adc_bat->pdata; - struct power_supply_info *bat_info; - - bat_info = &pdata->battery_info; - if (adc_bat->level == bat_info->charge_full_design) - return POWER_SUPPLY_STATUS_FULL; - return adc_bat->status; -} - static enum gab_chan_type gab_prop_to_chan(enum power_supply_property psp) { switch (psp) { @@ -144,27 +122,14 @@ static int read_channel(struct gab *adc_bat, enum power_supply_property psp, static int gab_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { - struct gab *adc_bat; - struct gab_platform_data *pdata; - struct power_supply_info *bat_info; + struct gab *adc_bat = to_generic_bat(psy); int result = 0; int ret = 0; - adc_bat = to_generic_bat(psy); - if (!adc_bat) { - dev_err(&psy->dev, "no battery infos ?!\n"); - return -EINVAL; - } - pdata = adc_bat->pdata; - bat_info = &pdata->battery_info; - switch (psp) { case POWER_SUPPLY_PROP_STATUS: - val->intval = gab_get_status(adc_bat); - break; - case POWER_SUPPLY_PROP_CHARGE_EMPTY_DESIGN: - val->intval = 0; - break; + val->intval = adc_bat->status; + return 0; case POWER_SUPPLY_PROP_VOLTAGE_NOW: case POWER_SUPPLY_PROP_CURRENT_NOW: case POWER_SUPPLY_PROP_POWER_NOW: @@ -173,21 +138,6 @@ static int gab_get_property(struct power_supply *psy, goto err; val->intval = result; break; - case POWER_SUPPLY_PROP_TECHNOLOGY: - val->intval = bat_info->technology; - break; - case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN: - val->intval = bat_info->voltage_min_design; - break; - case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN: - val->intval = bat_info->voltage_max_design; - break; - case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: - val->intval = bat_info->charge_full_design; - break; - case POWER_SUPPLY_PROP_MODEL_NAME: - val->strval = bat_info->name; - break; default: return -EINVAL; } @@ -235,7 +185,6 @@ static int gab_probe(struct platform_device *pdev) struct gab *adc_bat; struct power_supply_desc *psy_desc; struct power_supply_config psy_cfg = {}; - struct gab_platform_data *pdata = pdev->dev.platform_data; enum power_supply_property *properties; int ret = 0; int chan; @@ -248,7 +197,7 @@ static int gab_probe(struct platform_device *pdev) psy_cfg.drv_data = adc_bat; psy_desc = &adc_bat->psy_desc; - psy_desc->name = pdata->battery_info.name; + psy_desc->name = dev_name(&pdev->dev); /* bootup default values for the battery */ adc_bat->cable_plugged = false; @@ -256,7 +205,6 @@ static int gab_probe(struct platform_device *pdev) psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; psy_desc->get_property = gab_get_property; psy_desc->external_power_changed = gab_ext_power_changed; - adc_bat->pdata = pdata; /* * copying the static properties and allocating extra memory for holding diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h deleted file mode 100644 index 54434e4304d3..000000000000 --- a/include/linux/power/generic-adc-battery.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012, Anish Kumar - */ - -#ifndef GENERIC_ADC_BATTERY_H -#define GENERIC_ADC_BATTERY_H - -/** - * struct gab_platform_data - platform_data for generic adc iio battery driver. - * @battery_info: recommended structure to specify static power supply - * parameters - */ -struct gab_platform_data { - struct power_supply_info battery_info; -}; - -#endif /* GENERIC_ADC_BATTERY_H */ -- GitLab From 9489d1bdb763a3dd954e61522043190a9fd1cb4c Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:02 +0100 Subject: [PATCH 1653/5631] power: supply: generic-adc-battery: simplify read_channel logic Drop mostly useless gab_prop_to_chan() function by directly supplying the correct enum value to read_channel(). Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 35 ++++------------------ 1 file changed, 5 insertions(+), 30 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 42765cbf7518..4811e72df8cd 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -86,31 +86,12 @@ static bool gab_charge_finished(struct gab *adc_bat) return gpiod_get_value(adc_bat->charge_finished); } -static enum gab_chan_type gab_prop_to_chan(enum power_supply_property psp) -{ - switch (psp) { - case POWER_SUPPLY_PROP_POWER_NOW: - return GAB_POWER; - case POWER_SUPPLY_PROP_VOLTAGE_NOW: - return GAB_VOLTAGE; - case POWER_SUPPLY_PROP_CURRENT_NOW: - return GAB_CURRENT; - default: - WARN_ON(1); - break; - } - return GAB_POWER; -} - -static int read_channel(struct gab *adc_bat, enum power_supply_property psp, +static int read_channel(struct gab *adc_bat, enum gab_chan_type channel, int *result) { int ret; - int chan_index; - chan_index = gab_prop_to_chan(psp); - ret = iio_read_channel_processed(adc_bat->channel[chan_index], - result); + ret = iio_read_channel_processed(adc_bat->channel[channel], result); if (ret < 0) pr_err("read channel error\n"); else @@ -123,26 +104,20 @@ static int gab_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { struct gab *adc_bat = to_generic_bat(psy); - int result = 0; - int ret = 0; switch (psp) { case POWER_SUPPLY_PROP_STATUS: val->intval = adc_bat->status; return 0; case POWER_SUPPLY_PROP_VOLTAGE_NOW: + return read_channel(adc_bat, GAB_VOLTAGE, &val->intval); case POWER_SUPPLY_PROP_CURRENT_NOW: + return read_channel(adc_bat, GAB_CURRENT, &val->intval); case POWER_SUPPLY_PROP_POWER_NOW: - ret = read_channel(adc_bat, psp, &result); - if (ret < 0) - goto err; - val->intval = result; - break; + return read_channel(adc_bat, GAB_POWER, &val->intval); default: return -EINVAL; } -err: - return ret; } static void gab_work(struct work_struct *work) -- GitLab From 33088c0513818d1d4cf2c510fd67456fd577d887 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:03 +0100 Subject: [PATCH 1654/5631] power: supply: generic-adc-battery: add temperature support Another typical thing to monitor via an ADC line is the battery temperature. Reviewed-by: Matti Vaittinen Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 4811e72df8cd..0124d8d51af7 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -30,6 +30,7 @@ enum gab_chan_type { GAB_VOLTAGE = 0, GAB_CURRENT, GAB_POWER, + GAB_TEMP, GAB_MAX_CHAN_TYPE }; @@ -40,7 +41,8 @@ enum gab_chan_type { static const char *const gab_chan_name[] = { [GAB_VOLTAGE] = "voltage", [GAB_CURRENT] = "current", - [GAB_POWER] = "power", + [GAB_POWER] = "power", + [GAB_TEMP] = "temperature", }; struct gab { @@ -77,6 +79,7 @@ static const enum power_supply_property gab_dyn_props[] = { POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_CURRENT_NOW, POWER_SUPPLY_PROP_POWER_NOW, + POWER_SUPPLY_PROP_TEMP, }; static bool gab_charge_finished(struct gab *adc_bat) @@ -115,6 +118,8 @@ static int gab_get_property(struct power_supply *psy, return read_channel(adc_bat, GAB_CURRENT, &val->intval); case POWER_SUPPLY_PROP_POWER_NOW: return read_channel(adc_bat, GAB_POWER, &val->intval); + case POWER_SUPPLY_PROP_TEMP: + return read_channel(adc_bat, GAB_TEMP, &val->intval); default: return -EINVAL; } -- GitLab From 165663addf0ea9cf6e18c8d1ab9b9a8ef6f5a5b7 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:04 +0100 Subject: [PATCH 1655/5631] power: supply: generic-adc-battery: add DT support This adds full DT support to the driver. Because of the previous changes just adding a compatible value is enough. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 0124d8d51af7..e11ad43ab968 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #define JITTER_DEFAULT 10 /* hope 10ms is enough */ @@ -175,6 +176,7 @@ static int gab_probe(struct platform_device *pdev) if (!adc_bat) return -ENOMEM; + psy_cfg.of_node = pdev->dev.of_node; psy_cfg.drv_data = adc_bat; psy_desc = &adc_bat->psy_desc; psy_desc->name = dev_name(&pdev->dev); @@ -288,10 +290,17 @@ static int __maybe_unused gab_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(gab_pm_ops, gab_suspend, gab_resume); +static const struct of_device_id gab_match[] = { + { .compatible = "adc-battery" }, + { } +}; +MODULE_DEVICE_TABLE(of, gab_match); + static struct platform_driver gab_driver = { .driver = { .name = "generic-adc-battery", .pm = &gab_pm_ops, + .of_match_table = gab_match, }, .probe = gab_probe, }; -- GitLab From ca0f6e0d1499e8e23e340d8b7187eeec5c4f6593 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:05 +0100 Subject: [PATCH 1656/5631] power: supply: generic-adc-battery: update copyright info jz4740-battery.c and s3c_adc_battery.c have been removed from the tree and after all of my restructuring the driver is basically no longer based on them. Thus update the copyright information and switch to SPDX license identifier while being at it. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index e11ad43ab968..df1c0a1c6b52 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * Generic battery driver code using IIO + * Generic battery driver using IIO * Copyright (C) 2012, Anish Kumar - * based on jz4740-battery.c - * based on s3c_adc_battery.c - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file COPYING in the main directory of this archive for - * more details. - * + * Copyright (c) 2023, Sebastian Reichel */ #include #include -- GitLab From 4fc1befb3a30d76a3f4b19833d45fb81ab1652b1 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:06 +0100 Subject: [PATCH 1657/5631] power: supply: generic-adc-battery: improve error message Add device context and error code to the error messages to make it useful. Reviewed-by: Linus Walleij Reviewed-by: Matti Vaittinen Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index df1c0a1c6b52..2fa946c93fb4 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -92,7 +92,7 @@ static int read_channel(struct gab *adc_bat, enum gab_chan_type channel, ret = iio_read_channel_processed(adc_bat->channel[channel], result); if (ret < 0) - pr_err("read channel error\n"); + dev_err(&adc_bat->psy->dev, "read channel error: %d\n", ret); else *result *= 1000; -- GitLab From 7cc7478e093782d2ac176c11a966de00bd0792dc Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Fri, 17 Mar 2023 23:57:07 +0100 Subject: [PATCH 1658/5631] power: supply: generic-adc-battery: style fixes This does the following code-style changes: * fix inconsistent indentation in 'struct gab' * remove unused cable_plugged from 'struct gab' * remove pointless temporary is_plugged variable * add gab_ prefix to read_channel No functionality changes are intended. Signed-off-by: Sebastian Reichel --- drivers/power/supply/generic-adc-battery.c | 26 +++++++++------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/drivers/power/supply/generic-adc-battery.c b/drivers/power/supply/generic-adc-battery.c index 2fa946c93fb4..7bdc6b263609 100644 --- a/drivers/power/supply/generic-adc-battery.c +++ b/drivers/power/supply/generic-adc-battery.c @@ -42,12 +42,11 @@ static const char *const gab_chan_name[] = { }; struct gab { - struct power_supply *psy; - struct power_supply_desc psy_desc; - struct iio_channel *channel[GAB_MAX_CHAN_TYPE]; + struct power_supply *psy; + struct power_supply_desc psy_desc; + struct iio_channel *channel[GAB_MAX_CHAN_TYPE]; struct delayed_work bat_work; - int status; - bool cable_plugged; + int status; struct gpio_desc *charge_finished; }; @@ -85,7 +84,7 @@ static bool gab_charge_finished(struct gab *adc_bat) return gpiod_get_value(adc_bat->charge_finished); } -static int read_channel(struct gab *adc_bat, enum gab_chan_type channel, +static int gab_read_channel(struct gab *adc_bat, enum gab_chan_type channel, int *result) { int ret; @@ -109,13 +108,13 @@ static int gab_get_property(struct power_supply *psy, val->intval = adc_bat->status; return 0; case POWER_SUPPLY_PROP_VOLTAGE_NOW: - return read_channel(adc_bat, GAB_VOLTAGE, &val->intval); + return gab_read_channel(adc_bat, GAB_VOLTAGE, &val->intval); case POWER_SUPPLY_PROP_CURRENT_NOW: - return read_channel(adc_bat, GAB_CURRENT, &val->intval); + return gab_read_channel(adc_bat, GAB_CURRENT, &val->intval); case POWER_SUPPLY_PROP_POWER_NOW: - return read_channel(adc_bat, GAB_POWER, &val->intval); + return gab_read_channel(adc_bat, GAB_POWER, &val->intval); case POWER_SUPPLY_PROP_TEMP: - return read_channel(adc_bat, GAB_TEMP, &val->intval); + return gab_read_channel(adc_bat, GAB_TEMP, &val->intval); default: return -EINVAL; } @@ -125,17 +124,13 @@ static void gab_work(struct work_struct *work) { struct gab *adc_bat; struct delayed_work *delayed_work; - bool is_plugged; int status; delayed_work = to_delayed_work(work); adc_bat = container_of(delayed_work, struct gab, bat_work); status = adc_bat->status; - is_plugged = power_supply_am_i_supplied(adc_bat->psy); - adc_bat->cable_plugged = is_plugged; - - if (!is_plugged) + if (!power_supply_am_i_supplied(adc_bat->psy)) adc_bat->status = POWER_SUPPLY_STATUS_DISCHARGING; else if (gab_charge_finished(adc_bat)) adc_bat->status = POWER_SUPPLY_STATUS_NOT_CHARGING; @@ -177,7 +172,6 @@ static int gab_probe(struct platform_device *pdev) psy_desc->name = dev_name(&pdev->dev); /* bootup default values for the battery */ - adc_bat->cable_plugged = false; adc_bat->status = POWER_SUPPLY_STATUS_DISCHARGING; psy_desc->type = POWER_SUPPLY_TYPE_BATTERY; psy_desc->get_property = gab_get_property; -- GitLab From 27a6e1b09a782517fddac91259970ac466a3f7b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Tue, 31 Jan 2023 09:32:27 +0100 Subject: [PATCH 1659/5631] clk: add missing of_node_put() in "assigned-clocks" property parsing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When returning from of_parse_phandle_with_args(), the np member of the of_phandle_args structure should be put after usage. Add missing of_node_put() calls in both __set_clk_parents() and __set_clk_rates(). Fixes: 86be408bfbd8 ("clk: Support for clock parents and rates assigned from device tree") Signed-off-by: Clément Léger Link: https://lore.kernel.org/r/20230131083227.10990-1-clement.leger@bootlin.com Signed-off-by: Stephen Boyd --- drivers/clk/clk-conf.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c index 2ef819606c41..1a4e6340f95c 100644 --- a/drivers/clk/clk-conf.c +++ b/drivers/clk/clk-conf.c @@ -33,9 +33,12 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier) else return rc; } - if (clkspec.np == node && !clk_supplier) + if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); return 0; + } pclk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(pclk)) { if (PTR_ERR(pclk) != -EPROBE_DEFER) pr_warn("clk: couldn't get parent clock %d for %pOF\n", @@ -48,10 +51,12 @@ static int __set_clk_parents(struct device_node *node, bool clk_supplier) if (rc < 0) goto err; if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); rc = 0; goto err; } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { if (PTR_ERR(clk) != -EPROBE_DEFER) pr_warn("clk: couldn't get assigned clock %d for %pOF\n", @@ -93,10 +98,13 @@ static int __set_clk_rates(struct device_node *node, bool clk_supplier) else return rc; } - if (clkspec.np == node && !clk_supplier) + if (clkspec.np == node && !clk_supplier) { + of_node_put(clkspec.np); return 0; + } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { if (PTR_ERR(clk) != -EPROBE_DEFER) pr_warn("clk: couldn't get clock %d for %pOF\n", -- GitLab From 6cba789f8982b38be37daa1b67b8488710b47b29 Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Fri, 11 Nov 2022 14:39:35 +0800 Subject: [PATCH 1660/5631] clock: milbeaut: use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Minghao Chi Link: https://lore.kernel.org/r/202211111439357842458@zte.com.cn Signed-off-by: Stephen Boyd --- drivers/clk/clk-milbeaut.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/clk/clk-milbeaut.c b/drivers/clk/clk-milbeaut.c index 80b9d78493bc..050fd4fb588f 100644 --- a/drivers/clk/clk-milbeaut.c +++ b/drivers/clk/clk-milbeaut.c @@ -560,14 +560,12 @@ static void m10v_reg_mux_pre(const struct m10v_clk_mux_factors *factors, static int m10v_clk_probe(struct platform_device *pdev) { int id; - struct resource *res; struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; void __iomem *base; const char *parent_name; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(dev, res); + base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(base)) return PTR_ERR(base); -- GitLab From b4a2adbf3586efa12fe78b9dec047423e01f3010 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Feb 2023 09:59:10 +0100 Subject: [PATCH 1661/5631] clk: tegra20: fix gcc-7 constant overflow warning Older gcc versions get confused by comparing a u32 value to a negative constant in a switch()/case block: drivers/clk/tegra/clk-tegra20.c: In function 'tegra20_clk_measure_input_freq': drivers/clk/tegra/clk-tegra20.c:581:2: error: case label does not reduce to an integer constant case OSC_CTRL_OSC_FREQ_12MHZ: ^~~~ drivers/clk/tegra/clk-tegra20.c:593:2: error: case label does not reduce to an integer constant case OSC_CTRL_OSC_FREQ_26MHZ: Make the constants unsigned instead. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230227085914.2560984-1-arnd@kernel.org Signed-off-by: Stephen Boyd --- drivers/clk/tegra/clk-tegra20.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index 422d78247553..dcacc5064d33 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -21,24 +21,24 @@ #define MISC_CLK_ENB 0x48 #define OSC_CTRL 0x50 -#define OSC_CTRL_OSC_FREQ_MASK (3<<30) -#define OSC_CTRL_OSC_FREQ_13MHZ (0<<30) -#define OSC_CTRL_OSC_FREQ_19_2MHZ (1<<30) -#define OSC_CTRL_OSC_FREQ_12MHZ (2<<30) -#define OSC_CTRL_OSC_FREQ_26MHZ (3<<30) -#define OSC_CTRL_MASK (0x3f2 | OSC_CTRL_OSC_FREQ_MASK) - -#define OSC_CTRL_PLL_REF_DIV_MASK (3<<28) -#define OSC_CTRL_PLL_REF_DIV_1 (0<<28) -#define OSC_CTRL_PLL_REF_DIV_2 (1<<28) -#define OSC_CTRL_PLL_REF_DIV_4 (2<<28) +#define OSC_CTRL_OSC_FREQ_MASK (3u<<30) +#define OSC_CTRL_OSC_FREQ_13MHZ (0u<<30) +#define OSC_CTRL_OSC_FREQ_19_2MHZ (1u<<30) +#define OSC_CTRL_OSC_FREQ_12MHZ (2u<<30) +#define OSC_CTRL_OSC_FREQ_26MHZ (3u<<30) +#define OSC_CTRL_MASK (0x3f2u | OSC_CTRL_OSC_FREQ_MASK) + +#define OSC_CTRL_PLL_REF_DIV_MASK (3u<<28) +#define OSC_CTRL_PLL_REF_DIV_1 (0u<<28) +#define OSC_CTRL_PLL_REF_DIV_2 (1u<<28) +#define OSC_CTRL_PLL_REF_DIV_4 (2u<<28) #define OSC_FREQ_DET 0x58 -#define OSC_FREQ_DET_TRIG (1<<31) +#define OSC_FREQ_DET_TRIG (1u<<31) #define OSC_FREQ_DET_STATUS 0x5c -#define OSC_FREQ_DET_BUSY (1<<31) -#define OSC_FREQ_DET_CNT_MASK 0xFFFF +#define OSC_FREQ_DET_BUSYu (1<<31) +#define OSC_FREQ_DET_CNT_MASK 0xFFFFu #define TEGRA20_CLK_PERIPH_BANKS 3 -- GitLab From b31507dcaf3566d8ec3bdbf9922d8d5748b08a0f Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 29 Mar 2023 09:14:05 +0200 Subject: [PATCH 1662/5631] dma-debug: Use %pa to format phys_addr_t MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On 32-bit without LPAE: kernel/dma/debug.c: In function ‘debug_dma_dump_mappings’: kernel/dma/debug.c:537:7: warning: format ‘%llx’ expects argument of type ‘long long unsigned int’, but argument 9 has type ‘phys_addr_t’ {aka ‘unsigned int’} [-Wformat=] kernel/dma/debug.c: In function ‘dump_show’: kernel/dma/debug.c:568:59: warning: format ‘%llx’ expects argument of type ‘long long unsigned int’, but argument 11 has type ‘phys_addr_t’ {aka ‘unsigned int’} [-Wformat=] Fixes: bd89d69a529fbef3 ("dma-debug: add cacheline to user/kernel space dump messages") Reported-by: kernel test robot Link: https://lore.kernel.org/r/202303160548.ReyuTsGD-lkp@intel.com Reported-by: noreply@ellerman.id.au Signed-off-by: Geert Uytterhoeven Signed-off-by: Christoph Hellwig --- kernel/dma/debug.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index 676142072d99..f190651bcadd 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -534,11 +534,11 @@ void debug_dma_dump_mappings(struct device *dev) if (!dev || dev == entry->dev) { cln = to_cacheline_number(entry); dev_info(entry->dev, - "%s idx %d P=%llx N=%lx D=%llx L=%llx cln=%llx %s %s\n", + "%s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n", type2name[entry->type], idx, phys_addr(entry), entry->pfn, entry->dev_addr, entry->size, - cln, dir2name[entry->direction], + &cln, dir2name[entry->direction], maperr2str[entry->map_err_type]); } } @@ -565,13 +565,13 @@ static int dump_show(struct seq_file *seq, void *v) list_for_each_entry(entry, &bucket->list, list) { cln = to_cacheline_number(entry); seq_printf(seq, - "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx cln=%llx %s %s\n", + "%s %s %s idx %d P=%llx N=%lx D=%llx L=%llx cln=%pa %s %s\n", dev_driver_string(entry->dev), dev_name(entry->dev), type2name[entry->type], idx, phys_addr(entry), entry->pfn, entry->dev_addr, entry->size, - cln, dir2name[entry->direction], + &cln, dir2name[entry->direction], maperr2str[entry->map_err_type]); } spin_unlock_irqrestore(&bucket->lock, flags); -- GitLab From b6ba68555d75fd99f7daa9c5a5e476f8635cb155 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 29 Mar 2023 21:14:01 +0300 Subject: [PATCH 1663/5631] RDMA/rxe: Clean kzalloc failure paths There is no need to print any debug messages after failure to allocate memory, because kernel will print OOM dumps anyway. Together with removal of these messages, remove useless goto jumps. Fixes: 5bf944f24129 ("RDMA/rxe: Add error messages") Reported-by: Dan Carpenter Link: https://lore.kernel.org/all/ea43486f-43dd-4054-b1d5-3a0d202be621@kili.mountain Link: https://lore.kernel.org/r/d3cedf723b84e73e8062a67b7489d33802bafba2.1680113597.git.leon@kernel.org Reviewed-by: Bob Pearson Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rxe/rxe_queue.c | 5 ++--- drivers/infiniband/sw/rxe/rxe_verbs.c | 27 +++++++-------------------- 2 files changed, 9 insertions(+), 23 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c index d6dbf5a0058d..9611ee191a46 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.c +++ b/drivers/infiniband/sw/rxe/rxe_queue.c @@ -61,11 +61,11 @@ struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, /* num_elem == 0 is allowed, but uninteresting */ if (*num_elem < 0) - goto err1; + return NULL; q = kzalloc(sizeof(*q), GFP_KERNEL); if (!q) - goto err1; + return NULL; q->rxe = rxe; q->type = type; @@ -100,7 +100,6 @@ struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe, int *num_elem, err2: kfree(q); -err1: return NULL; } diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 090d5bfb1e18..4e2db7c2e4ed 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1198,11 +1198,8 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) int err; mr = kzalloc(sizeof(*mr), GFP_KERNEL); - if (!mr) { - err = -ENOMEM; - rxe_dbg_dev(rxe, "no memory for mr"); - goto err_out; - } + if (!mr) + return ERR_PTR(-ENOMEM); err = rxe_add_to_pool(&rxe->mr_pool, mr); if (err) { @@ -1220,7 +1217,6 @@ static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access) err_free: kfree(mr); -err_out: rxe_err_pd(pd, "returned err = %d", err); return ERR_PTR(err); } @@ -1235,11 +1231,8 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start, int err, cleanup_err; mr = kzalloc(sizeof(*mr), GFP_KERNEL); - if (!mr) { - err = -ENOMEM; - rxe_dbg_pd(pd, "no memory for mr"); - goto err_out; - } + if (!mr) + return ERR_PTR(-ENOMEM); err = rxe_add_to_pool(&rxe->mr_pool, mr); if (err) { @@ -1266,7 +1259,6 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start, rxe_err_mr(mr, "cleanup failed, err = %d", cleanup_err); err_free: kfree(mr); -err_out: rxe_err_pd(pd, "returned err = %d", err); return ERR_PTR(err); } @@ -1287,17 +1279,12 @@ static struct ib_mr *rxe_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type, } mr = kzalloc(sizeof(*mr), GFP_KERNEL); - if (!mr) { - err = -ENOMEM; - rxe_dbg_mr(mr, "no memory for mr"); - goto err_out; - } + if (!mr) + return ERR_PTR(-ENOMEM); err = rxe_add_to_pool(&rxe->mr_pool, mr); - if (err) { - rxe_dbg_mr(mr, "unable to create mr, err = %d", err); + if (err) goto err_free; - } rxe_get(pd); mr->ibmr.pd = ibpd; -- GitLab From 9467af61bf6a92bb0e2f783fcfc379f943fa4e0d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 29 Mar 2023 08:01:27 +0200 Subject: [PATCH 1664/5631] mISDN: remove unneeded mISDN_class_release() The mISDN_class_release() is not needed at all, as the class structure is static, and it does not actually do anything either, so it is safe to remove as struct class does not require a release callback. Cc: Karsten Keil Cc: netdev@vger.kernel.org Reviewed-by: Simon Horman Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20230329060127.2688492-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/isdn/mISDN/core.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index f5989c9907ee..ab8513a7acd5 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -152,17 +152,11 @@ static int mISDN_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -static void mISDN_class_release(struct class *cls) -{ - /* do nothing, it's static */ -} - static struct class mISDN_class = { .name = "mISDN", .dev_uevent = mISDN_uevent, .dev_groups = mISDN_groups, .dev_release = mISDN_dev_release, - .class_release = mISDN_class_release, }; static int -- GitLab From 91b8961eaf051bd437a357a604bb420ce5274003 Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Sun, 19 Mar 2023 15:46:04 +0700 Subject: [PATCH 1665/5631] MAINTAINERS: Add entry for LED devices documentation When given patches that only touch documentation directory for LED devices (Documentation/leds/), get_maintainer doesn't list mailing list for LED subsystem. However, the patch should be seen on that list in order to be applied. Add the entry for Documentation/leds/. Signed-off-by: Bagas Sanjaya Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230319084604.19749-1-bagasdotme@gmail.com --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..8cc35a2e24e5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11648,6 +11648,7 @@ L: linux-leds@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git F: Documentation/devicetree/bindings/leds/ +F: Documentation/leds/ F: drivers/leds/ F: include/dt-bindings/leds/ F: include/linux/leds.h -- GitLab From 631cf002826007ab7415258ee647dcaf8845ad5a Mon Sep 17 00:00:00 2001 From: Liang He Date: Thu, 30 Mar 2023 11:35:58 +0800 Subject: [PATCH 1666/5631] macintosh/windfarm_smu_sat: Add missing of_node_put() We call of_node_get() in wf_sat_probe() after sat is created, so we need the of_node_put() before *kfree(sat)*. Fixes: ac171c46667c ("[PATCH] powerpc: Thermal control for dual core G5s") Signed-off-by: Liang He Signed-off-by: Michael Ellerman Link: https://msgid.link/20230330033558.2562778-1-windhl@126.com --- drivers/macintosh/windfarm_smu_sat.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index ebc4256a9e4a..089f2743a070 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -171,6 +171,7 @@ static void wf_sat_release(struct kref *ref) if (sat->nr >= 0) sats[sat->nr] = NULL; + of_node_put(sat->node); kfree(sat); } -- GitLab From 2747fd26f801c98d0a8177278b4f5c91b8de9c94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20Van=C4=9Bk?= Date: Fri, 24 Mar 2023 23:00:41 +0100 Subject: [PATCH 1667/5631] powerpc/pseries: Add spaces around / operator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is follow up change after 14b5d59a261b ("powerpc/pseries: Fix formatting to make code look more beautiful") to conform to kernel coding style. Signed-off-by: Petr Vaněk Signed-off-by: Michael Ellerman Link: https://msgid.link/20230324220041.11378-1-arkamar@atlas.cz --- arch/powerpc/platforms/pseries/iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index de77c8c43211..256493111d1d 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -479,7 +479,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, * Set up the page with TCE data, looping through and setting * the values. */ - limit = min_t(long, num_tce, 4096/TCE_ENTRY_SIZE); + limit = min_t(long, num_tce, 4096 / TCE_ENTRY_SIZE); dma_offset = next + be64_to_cpu(maprange->dma_base); for (l = 0; l < limit; l++) { -- GitLab From 69608683a65be5322ef44091eaeb9890472b2eea Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 28 Feb 2023 11:07:07 +1100 Subject: [PATCH 1668/5631] selftests/powerpc: Use CLEAN macro to fix make warning The CLEAN macro was added in 337f1e36 to prevent the Makefile:50: warning: overriding recipe for target 'clean' ../../lib.mk:124: warning: ignoring old recipe for target 'clean' style warnings. Expand it's use to fix another case of redefining a target directly. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228000709.124727-2-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/pmu/Makefile | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index 30803353bd7c..d2c1accc2e69 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -46,11 +46,14 @@ override define INSTALL_RULE TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef -clean: +DEFAULT_CLEAN := $(CLEAN) +override define CLEAN + $(DEFAULT_CLEAN) $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean +endef ebb: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all @@ -61,4 +64,4 @@ sampling_tests: event_code_tests: TARGET=$@; BUILD_TARGET=$$OUTPUT/$$TARGET; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $$TARGET all -.PHONY: all run_tests clean ebb sampling_tests event_code_tests +.PHONY: all run_tests ebb sampling_tests event_code_tests -- GitLab From 4ecd0868c5138238dec8a1549bb6ff8e5b48208b Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 28 Feb 2023 11:07:08 +1100 Subject: [PATCH 1669/5631] selftests/powerpc: Pass make context to children Make supports passing the 'jobserver' (parallel make support) to child invocations of make when either 1. The target command uses $(MAKE) directly 2. The command starts with '+' This context is not passed through expansions that result in $(MAKE), so the macros used in several places fail to pass on the jobserver context. Warnings are also raised by the child mentioning this. Prepend macros lines that invoke $(MAKE) with '+' to allow passing the jobserver context to these children. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228000709.124727-3-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/Makefile | 8 +++---- tools/testing/selftests/powerpc/pmu/Makefile | 24 ++++++++++---------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 6ba95cd19e42..ae2bfc0d822f 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -45,28 +45,28 @@ $(SUB_DIRS): include ../lib.mk override define RUN_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\ done; endef override define INSTALL_RULE - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\ done; endef override define EMIT_TESTS - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\ done; endef override define CLEAN - @for TARGET in $(SUB_DIRS); do \ + +@for TARGET in $(SUB_DIRS); do \ BUILD_TARGET=$(OUTPUT)/$$TARGET; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \ done; diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index d2c1accc2e69..2b95e44d20ff 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -25,34 +25,34 @@ $(OUTPUT)/per_event_excludes: ../utils.c DEFAULT_RUN_TESTS := $(RUN_TESTS) override define RUN_TESTS $(DEFAULT_RUN_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests endef DEFAULT_EMIT_TESTS := $(EMIT_TESTS) override define EMIT_TESTS $(DEFAULT_EMIT_TESTS) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests endef DEFAULT_INSTALL_RULE := $(INSTALL_RULE) override define INSTALL_RULE $(DEFAULT_INSTALL_RULE) - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install endef DEFAULT_CLEAN := $(CLEAN) override define CLEAN $(DEFAULT_CLEAN) $(RM) $(TEST_GEN_PROGS) $(OUTPUT)/loop.o - TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean - TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=ebb; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=sampling_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean + +TARGET=event_code_tests; BUILD_TARGET=$$OUTPUT/$$TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean endef ebb: -- GitLab From d3cf1662b665f20444a08bff52b6daae912e0d1d Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Tue, 28 Feb 2023 11:07:09 +1100 Subject: [PATCH 1670/5631] selftests/powerpc: Make dd output quiet dd logs info to stderr by default. This info is pointless in the selftests and makes legitimate issues harder to spot. Pass the option to silence the info logs. Actual errors would still be printed. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228000709.124727-4-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/mm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 19dd0b2ea397..4a6608beef0e 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -32,7 +32,7 @@ $(OUTPUT)/stack_expansion_ldst: CFLAGS += -fno-stack-protector $(OUTPUT)/stack_expansion_ldst: ../utils.c $(OUTPUT)/tempfile: - dd if=/dev/zero of=$@ bs=64k count=1 + dd if=/dev/zero of=$@ bs=64k count=1 status=none $(OUTPUT)/tlbie_test: LDLIBS += -lpthread $(OUTPUT)/pkey_siginfo: LDLIBS += -lpthread -- GitLab From e7299f961fe5e4496db0bfaa9e819f5e97f3846b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 27 Feb 2023 16:54:45 +0100 Subject: [PATCH 1671/5631] powerpc/perf: Properly detect mpc7450 family Unlike PVR_POWER8, etc ...., PVR_7450 represents a full PVR value and not a family value. To avoid confusion, do like E500 family and define the relevant PVR_VER_xxxx values for the 7450 family: 0x8000 ==> 7450 0x8001 ==> 7455 0x8002 ==> 7447 0x8003 ==> 7447A 0x8004 ==> 7448 And use them to detect 7450 family for perf events. Reported-by: kernel test robot Reported-by: Dan Carpenter Link: https://lore.kernel.org/r/202302260657.7dM9Uwev-lkp@intel.com/ Fixes: ec3eb9d941a9 ("powerpc/perf: Use PVR rather than oprofile field to determine CPU version") Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/99ca1da2e5a6cf82a8abf4bc034918e500e31781.1677513277.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/reg.h | 5 +++++ arch/powerpc/perf/mpc7450-pmu.c | 6 +++--- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 1e8b2e04e626..8fda87af2fa5 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1310,6 +1310,11 @@ #define PVR_VER_E500MC 0x8023 #define PVR_VER_E5500 0x8024 #define PVR_VER_E6500 0x8040 +#define PVR_VER_7450 0x8000 +#define PVR_VER_7455 0x8001 +#define PVR_VER_7447 0x8002 +#define PVR_VER_7447A 0x8003 +#define PVR_VER_7448 0x8004 /* * For the 8xx processors, all of them report the same PVR family for diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c index 552d51a925d3..db451b9aac35 100644 --- a/arch/powerpc/perf/mpc7450-pmu.c +++ b/arch/powerpc/perf/mpc7450-pmu.c @@ -417,9 +417,9 @@ struct power_pmu mpc7450_pmu = { static int __init init_mpc7450_pmu(void) { - unsigned int pvr = mfspr(SPRN_PVR); - - if (PVR_VER(pvr) != PVR_7450) + if (!pvr_version_is(PVR_VER_7450) && !pvr_version_is(PVR_VER_7455) && + !pvr_version_is(PVR_VER_7447) && !pvr_version_is(PVR_VER_7447A) && + !pvr_version_is(PVR_VER_7448)) return -ENODEV; return register_power_pmu(&mpc7450_pmu); -- GitLab From 7538c97e2b80ff6b7a8ea2ecf16a04355461b439 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:13 -0800 Subject: [PATCH 1672/5631] powerpc/mpc512x: fix resource printk format warning Use "%pa" format specifier for resource_size_t to avoid a compiler printk format warning. ../arch/powerpc/platforms/512x/clock-commonclk.c: In function 'mpc5121_clk_provide_backwards_compat': ../arch/powerpc/platforms/512x/clock-commonclk.c:989:44: error: format '%x' expects argument of type 'unsigned int', but argument 4 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] 989 | snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ | ^~~~~~~~~ ~~~~~~~~~ | | | resource_size_t {aka long long unsigned int} Prevents 24 such warnings. Fixes: 01f25c371658 ("clk: mpc512x: add backwards compat to the CCF code") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-2-rdunlap@infradead.org --- arch/powerpc/platforms/512x/clock-commonclk.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index 42abeba4f698..079cb3627eac 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -986,7 +986,7 @@ static void __init mpc5121_clk_provide_migration_support(void) #define NODE_PREP do { \ of_address_to_resource(np, 0, &res); \ - snprintf(devname, sizeof(devname), "%08x.%s", res.start, np->name); \ + snprintf(devname, sizeof(devname), "%pa.%s", &res.start, np->name); \ } while (0) #define NODE_CHK(clkname, clkitem, regnode, regflag) do { \ -- GitLab From 7b69600d4da0049244e9be2f5ef5a2f8e04fcd9a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:14 -0800 Subject: [PATCH 1673/5631] powerpc/wii: fix resource printk format warnings Use "%pa" format specifier for resource_size_t to avoid compiler printk format warnings. ../arch/powerpc/platforms/embedded6xx/flipper-pic.c: In function 'flipper_pic_init': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/flipper-pic.c:148:9: note: in expansion of macro 'pr_info' 148 | pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); | ^~~~~~~ ../arch/powerpc/platforms/embedded6xx/hlwd-pic.c: In function 'hlwd_pic_init': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/hlwd-pic.c:174:9: note: in expansion of macro 'pr_info' 174 | pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); | ^~~~~~~ ../arch/powerpc/platforms/embedded6xx/wii.c: In function 'wii_ioremap_hw_regs': ../include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 3 has type 'resource_size_t' {aka 'long long unsigned int'} [-Werror=format=] ../arch/powerpc/platforms/embedded6xx/wii.c:77:17: note: in expansion of macro 'pr_info' 77 | pr_info("%s at 0x%08x mapped to 0x%p\n", name, | ^~~~~~~ Fixes: 028ee972f032 ("powerpc: gamecube/wii: flipper interrupt controller support") Fixes: 9c21025c7845 ("powerpc: wii: hollywood interrupt controller support") Fixes: 5a7ee3198dfa ("powerpc: wii: platform support") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-3-rdunlap@infradead.org --- arch/powerpc/platforms/embedded6xx/flipper-pic.c | 2 +- arch/powerpc/platforms/embedded6xx/hlwd-pic.c | 2 +- arch/powerpc/platforms/embedded6xx/wii.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index 609bda2ad5dd..4d9200bdba78 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -145,7 +145,7 @@ static struct irq_domain * __init flipper_pic_init(struct device_node *np) } io_base = ioremap(res.start, resource_size(&res)); - pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); + pr_info("controller at 0x%pa mapped to 0x%p\n", &res.start, io_base); __flipper_quiesce(io_base); diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c index 380b4285cce4..4d2d92de30af 100644 --- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c +++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c @@ -171,7 +171,7 @@ static struct irq_domain *__init hlwd_pic_init(struct device_node *np) return NULL; } - pr_info("controller at 0x%08x mapped to 0x%p\n", res.start, io_base); + pr_info("controller at 0x%pa mapped to 0x%p\n", &res.start, io_base); __hlwd_quiesce(io_base); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index b54382a8ccc6..cb3be6d6e339 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -74,8 +74,8 @@ static void __iomem *__init wii_ioremap_hw_regs(char *name, char *compatible) hw_regs = ioremap(res.start, resource_size(&res)); if (hw_regs) { - pr_info("%s at 0x%08x mapped to 0x%p\n", name, - res.start, hw_regs); + pr_info("%s at 0x%pa mapped to 0x%p\n", name, + &res.start, hw_regs); } out_put: -- GitLab From 55d8bd02cc1b9f1063993b5c42c9cabf4af67dea Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 23:01:16 -0800 Subject: [PATCH 1674/5631] powerpc/sysdev/tsi108: fix resource printk format warnings Use "%pa" format specifier for resource_size_t to avoid a compiler printk format warning. arch/powerpc/sysdev/tsi108_pci.c: In function 'tsi108_setup_pci': include/linux/kern_levels.h:5:25: error: format '%x' expects argument of type 'unsigned int', but argument 2 has type 'resource_size_t' Fixes: c4342ff92bed ("[POWERPC] Update mpc7448hpc2 board irq support using device tree") Fixes: 2b9d7467a6db ("[POWERPC] Add tsi108 pci and platform device data register function") Signed-off-by: Randy Dunlap [mpe: Use pr_info() and unsplit string] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223070116.660-5-rdunlap@infradead.org --- arch/powerpc/sysdev/tsi108_pci.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 5af4c35ff584..0e42f7bad7db 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -217,9 +217,8 @@ int __init tsi108_setup_pci(struct device_node *dev, u32 cfg_phys, int primary) (hose)->ops = &tsi108_direct_pci_ops; - printk(KERN_INFO "Found tsi108 PCI host bridge at 0x%08x. " - "Firmware bus number: %d->%d\n", - rsrc.start, hose->first_busno, hose->last_busno); + pr_info("Found tsi108 PCI host bridge at 0x%pa. Firmware bus number: %d->%d\n", + &rsrc.start, hose->first_busno, hose->last_busno); /* Interpret the "ranges" property */ /* This also maps the I/O region and sets isa_io/mem_base */ -- GitLab From 05dce4ba125336875cd3eed3c1503fa81cd2f691 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 17:42:41 -0800 Subject: [PATCH 1675/5631] macintosh: via-pmu-led: requires ATA to be set LEDS_TRIGGER_DISK depends on ATA, so selecting LEDS_TRIGGER_DISK when ATA is not set/enabled causes a Kconfig warning: WARNING: unmet direct dependencies detected for LEDS_TRIGGER_DISK Depends on [n]: NEW_LEDS [=y] && LEDS_TRIGGERS [=y] && ATA [=n] Selected by [y]: - ADB_PMU_LED_DISK [=y] && MACINTOSH_DRIVERS [=y] && ADB_PMU_LED [=y] && LEDS_CLASS [=y] Fix this by making ADB_PMU_LED_DISK depend on ATA. Seen on both PPC32 and PPC64. Fixes: 0e865a80c135 ("macintosh: Remove dependency on IDE_GD_ATA if ADB_PMU_LED_DISK is selected") Signed-off-by: Randy Dunlap Signed-off-by: Michael Ellerman Link: https://msgid.link/20230223014241.20878-1-rdunlap@infradead.org --- drivers/macintosh/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig index 539a2ed4e13d..a0e717a986dc 100644 --- a/drivers/macintosh/Kconfig +++ b/drivers/macintosh/Kconfig @@ -86,6 +86,7 @@ config ADB_PMU_LED config ADB_PMU_LED_DISK bool "Use front LED as DISK LED by default" + depends on ATA depends on ADB_PMU_LED depends on LEDS_CLASS select LEDS_TRIGGERS -- GitLab From f40b0f6c5c27de167fdd10e541e0a4b5f2bc772b Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:40 -0600 Subject: [PATCH 1676/5631] powerpc/rtas: ensure 8-byte alignment for struct rtas_args CHRP and PAPR agree: "In order to make an RTAS call, the operating system must construct an argument call buffer aligned on an eight byte boundary in physically contiguous real memory [...]." (7.2.7 Calling Mechanism and Conventions). struct rtas_args is the type used for this argument call buffer. The unarchitected 'rets' member happens to produce 8-byte alignment for the struct on 64-bit targets in practice. But without an alignment directive the structure will have only 4-byte alignment on 32-bit targets: $ nm b/{before,after}/chrp32/vmlinux | grep rtas_args c096881c b rtas_args c0968820 b rtas_args Add an alignment directive to the struct rtas_args declaration so all instances have the alignment required by the specs. rtas-types.h no longer refers to any spinlock types, so drop the spinlock_types.h inclusion while we're here. Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-1-010e4416f13f@linux.ibm.com --- arch/powerpc/include/asm/rtas-types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/rtas-types.h b/arch/powerpc/include/asm/rtas-types.h index f2ad4a96cbc5..9d5b16803cbb 100644 --- a/arch/powerpc/include/asm/rtas-types.h +++ b/arch/powerpc/include/asm/rtas-types.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_RTAS_TYPES_H #define _ASM_POWERPC_RTAS_TYPES_H -#include +#include typedef __be32 rtas_arg_t; @@ -12,7 +12,7 @@ struct rtas_args { __be32 nret; rtas_arg_t args[16]; rtas_arg_t *rets; /* Pointer to return values in args[]. */ -}; +} __aligned(8); struct rtas_t { unsigned long entry; /* physical address pointer */ -- GitLab From 271208ee5e335cb1ad280d22784940daf7ddf820 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:41 -0600 Subject: [PATCH 1677/5631] powerpc/rtas: use memmove for potentially overlapping buffer copy Using memcpy() isn't safe when buf is identical to rtas_err_buf, which can happen during boot before slab is up. Full context which may not be obvious from the diff: if (altbuf) { buf = altbuf; } else { buf = rtas_err_buf; if (slab_is_available()) buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); } if (buf) memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); This was found by inspection and I'm not aware of it causing problems in practice. It appears to have been introduced by commit 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel"); the old ppc64 version of this code did not have this problem. Use memmove() instead. Fixes: 033ef338b6e0 ("powerpc: Merge rtas.c into arch/powerpc/kernel") Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-2-010e4416f13f@linux.ibm.com --- arch/powerpc/kernel/rtas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 31175b34856a..9256cfaa8b6f 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -981,7 +981,7 @@ static char *__fetch_rtas_last_error(char *altbuf) buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC); } if (buf) - memcpy(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); + memmove(buf, rtas_err_buf, RTAS_ERROR_LOG_MAX); } return buf; -- GitLab From 1792e46ed0cfc1fa27c8c805f8098f806bcc5fc3 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:42 -0600 Subject: [PATCH 1678/5631] powerpc/rtas: rtas_call_unlocked() kerneldoc Add documentation for rtas_call_unlocked(), including details on how it differs from rtas_call(). Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-3-010e4416f13f@linux.ibm.com --- arch/powerpc/kernel/rtas.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 9256cfaa8b6f..c73b01d722f6 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1016,6 +1016,23 @@ va_rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, do_enter_rtas(args); } +/** + * rtas_call_unlocked() - Invoke an RTAS firmware function without synchronization. + * @args: RTAS parameter block to be used for the call, must obey RTAS addressing + * constraints. + * @token: Identifies the function being invoked. + * @nargs: Number of input parameters. Does not include token. + * @nret: Number of output parameters, including the call status. + * @....: List of @nargs input parameters. + * + * Invokes the RTAS function indicated by @token, which the caller + * should obtain via rtas_function_token(). + * + * This function is similar to rtas_call(), but must be used with a + * limited set of RTAS calls specifically exempted from the general + * requirement that only one RTAS call may be in progress at any + * time. Examples include stop-self and ibm,nmi-interlock. + */ void rtas_call_unlocked(struct rtas_args *args, int token, int nargs, int nret, ...) { va_list list; -- GitLab From 32740fce09f98d30f3c71a09ee4e9d90b3965427 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:43 -0600 Subject: [PATCH 1679/5631] powerpc/rtas: fix miswording in rtas_function kerneldoc The 'filter' member is a pointer, not a bool; fix the wording accordingly. Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-4-010e4416f13f@linux.ibm.com --- arch/powerpc/kernel/rtas.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c73b01d722f6..c29c38b1a55a 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -68,7 +68,7 @@ struct rtas_filter { * functions are believed to have no users on * ppc64le, and we want to keep it that way. It does * not make sense for this to be set when @filter - * is false. + * is NULL. */ struct rtas_function { s32 token; -- GitLab From af8bc68263b2184e63ee67ca70cecff4636f7901 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Mon, 6 Mar 2023 15:33:45 -0600 Subject: [PATCH 1680/5631] powerpc/rtas: lockdep annotations Add lockdep annotations for the following properties that must hold: * Any error log retrieval must be atomically coupled with the prior RTAS call, without a window for another RTAS call to occur before the error log can be retrieved. * All users of the core rtas_args parameter block must hold rtas_lock. Move the definitions of rtas_lock and rtas_args up in the file so that __do_enter_rtas_trace() can refer to them. Signed-off-by: Nathan Lynch Reviewed-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220-rtas-queue-for-6-4-v1-6-010e4416f13f@linux.ibm.com --- arch/powerpc/kernel/rtas.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c29c38b1a55a..c087eeee320f 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -453,6 +454,16 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { }, }; +/* + * Nearly all RTAS calls need to be serialized. All uses of the + * default rtas_args block must hold rtas_lock. + * + * Exceptions to the RTAS serialization requirement (e.g. stop-self) + * must use a separate rtas_args structure. + */ +static DEFINE_RAW_SPINLOCK(rtas_lock); +static struct rtas_args rtas_args; + /** * rtas_function_token() - RTAS function token lookup. * @handle: Function handle, e.g. RTAS_FN_EVENT_SCAN. @@ -560,6 +571,9 @@ static void __do_enter_rtas(struct rtas_args *args) static void __do_enter_rtas_trace(struct rtas_args *args) { const char *name = NULL; + + if (args == &rtas_args) + lockdep_assert_held(&rtas_lock); /* * If the tracepoints that consume the function name aren't * active, avoid the lookup. @@ -619,16 +633,6 @@ static void do_enter_rtas(struct rtas_args *args) struct rtas_t rtas; -/* - * Nearly all RTAS calls need to be serialized. All uses of the - * default rtas_args block must hold rtas_lock. - * - * Exceptions to the RTAS serialization requirement (e.g. stop-self) - * must use a separate rtas_args structure. - */ -static DEFINE_RAW_SPINLOCK(rtas_lock); -static struct rtas_args rtas_args; - DEFINE_SPINLOCK(rtas_data_buf_lock); EXPORT_SYMBOL_GPL(rtas_data_buf_lock); @@ -951,6 +955,8 @@ static char *__fetch_rtas_last_error(char *altbuf) u32 bufsz; char *buf = NULL; + lockdep_assert_held(&rtas_lock); + if (token == -1) return NULL; @@ -1108,6 +1114,7 @@ static bool token_is_restricted_errinjct(s32 token) */ int rtas_call(int token, int nargs, int nret, int *outputs, ...) { + struct pin_cookie cookie; va_list list; int i; unsigned long flags; @@ -1134,6 +1141,8 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) } raw_spin_lock_irqsave(&rtas_lock, flags); + cookie = lockdep_pin_lock(&rtas_lock); + /* We use the global rtas args buffer */ args = &rtas_args; @@ -1151,6 +1160,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...) outputs[i] = be32_to_cpu(args->rets[i + 1]); ret = (nret > 0) ? be32_to_cpu(args->rets[0]) : 0; + lockdep_unpin_lock(&rtas_lock, cookie); raw_spin_unlock_irqrestore(&rtas_lock, flags); if (buff_copy) { @@ -1782,6 +1792,7 @@ static bool block_rtas_call(int token, int nargs, /* We assume to be passed big endian arguments */ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { + struct pin_cookie cookie; struct rtas_args args; unsigned long flags; char *buff_copy, *errbuf = NULL; @@ -1850,6 +1861,7 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) buff_copy = get_errorlog_buffer(); raw_spin_lock_irqsave(&rtas_lock, flags); + cookie = lockdep_pin_lock(&rtas_lock); rtas_args = args; do_enter_rtas(&rtas_args); @@ -1860,6 +1872,7 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) if (be32_to_cpu(args.rets[0]) == -1) errbuf = __fetch_rtas_last_error(buff_copy); + lockdep_unpin_lock(&rtas_lock, cookie); raw_spin_unlock_irqrestore(&rtas_lock, flags); if (buff_copy) { -- GitLab From 857d423c74228cfa064f79ff3a16b163fdb8d542 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:46:56 -0600 Subject: [PATCH 1681/5631] powerpc: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring [mpe: Drop change in ppc4xx_probe_pci_bridge(), formatting] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230310144657.1541039-1-robh@kernel.org --- arch/powerpc/kernel/legacy_serial.c | 8 ++++---- arch/powerpc/platforms/44x/iss4xx.c | 2 +- arch/powerpc/platforms/44x/ppc476.c | 2 +- arch/powerpc/platforms/cell/spu_manage.c | 2 +- arch/powerpc/platforms/powermac/pic.c | 3 +-- arch/powerpc/platforms/powernv/opal-lpc.c | 2 +- arch/powerpc/platforms/pseries/hotplug-cpu.c | 2 +- arch/powerpc/platforms/pseries/vio.c | 2 +- arch/powerpc/sysdev/mpic_msgr.c | 2 +- 9 files changed, 12 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index f048c424c525..1a3b7f3513b4 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -171,11 +171,11 @@ static int __init add_legacy_soc_port(struct device_node *np, /* We only support ports that have a clock frequency properly * encoded in the device-tree. */ - if (of_get_property(np, "clock-frequency", NULL) == NULL) + if (!of_property_present(np, "clock-frequency")) return -1; /* if reg-offset don't try to use it */ - if ((of_get_property(np, "reg-offset", NULL) != NULL)) + if (of_property_present(np, "reg-offset")) return -1; /* if rtas uses this device, don't try to use it as well */ @@ -237,7 +237,7 @@ static int __init add_legacy_isa_port(struct device_node *np, * Note: Don't even try on P8 lpc, we know it's not directly mapped */ if (!of_device_is_compatible(isa_brg, "ibm,power8-lpc") || - of_get_property(isa_brg, "ranges", NULL)) { + of_property_present(isa_brg, "ranges")) { taddr = of_translate_address(np, reg); if (taddr == OF_BAD_ADDR) taddr = 0; @@ -268,7 +268,7 @@ static int __init add_legacy_pci_port(struct device_node *np, * compatible UARTs on PCI need all sort of quirks (port offsets * etc...) that this code doesn't know about */ - if (of_get_property(np, "clock-frequency", NULL) == NULL) + if (!of_property_present(np, "clock-frequency")) return -1; /* Get the PCI address. Assume BAR 0 */ diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c index 981972e8347f..ef883d97fe15 100644 --- a/arch/powerpc/platforms/44x/iss4xx.c +++ b/arch/powerpc/platforms/44x/iss4xx.c @@ -52,7 +52,7 @@ static void __init iss4xx_init_irq(void) /* Find top level interrupt controller */ for_each_node_with_property(np, "interrupt-controller") { - if (of_get_property(np, "interrupts", NULL) == NULL) + if (!of_property_present(np, "interrupts")) break; } if (np == NULL) diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 3135e654a743..fbc6edad481f 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -123,7 +123,7 @@ static void __init ppc47x_init_irq(void) /* Find top level interrupt controller */ for_each_node_with_property(np, "interrupt-controller") { - if (of_get_property(np, "interrupts", NULL) == NULL) + if (!of_property_present(np, "interrupts")) break; } if (np == NULL) diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index f1ac4c742069..74567b32c48c 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -402,7 +402,7 @@ static int __init of_has_vicinity(void) struct device_node *dn; for_each_node_by_type(dn, "spe") { - if (of_find_property(dn, "vicinity", NULL)) { + if (of_property_present(dn, "vicinity")) { of_node_put(dn); return 1; } diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 8c8d8e0a7d13..7425f94e271e 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -475,8 +475,7 @@ static int __init pmac_pic_probe_mpic(void) /* We can have up to 2 MPICs cascaded */ for_each_node_by_type(np, "open-pic") { - if (master == NULL && - of_get_property(np, "interrupts", NULL) == NULL) + if (master == NULL && !of_property_present(np, "interrupts")) master = of_node_get(np); else if (slave == NULL) slave = of_node_get(np); diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index d129d6d45a50..a16f07cdab26 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -403,7 +403,7 @@ void __init opal_lpc_init(void) return; /* Does it support direct mapping ? */ - if (of_get_property(np, "ranges", NULL)) { + if (of_property_present(np, "ranges")) { pr_info("OPAL: Found memory mapped LPC bus on chip %d\n", opal_lpc_chip_id); isa_bridge_init_non_pci(np); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 982e5e4b5e06..1a3cb313976a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -493,7 +493,7 @@ static bool valid_cpu_drc_index(struct device_node *parent, u32 drc_index) bool found = false; int rc, index; - if (of_find_property(parent, "ibm,drc-info", NULL)) + if (of_property_present(parent, "ibm,drc-info")) return drc_info_valid_index(parent, drc_index); /* Note that the format of the ibm,drc-indexes array is diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 770df9351aaa..d54306a936d5 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1440,7 +1440,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) viodev->dev.bus = &vio_bus_type; viodev->dev.release = vio_dev_release; - if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) { + if (of_property_present(viodev->dev.of_node, "ibm,my-dma-window")) { if (firmware_has_feature(FW_FEATURE_CMO)) vio_cmo_set_dma_ops(viodev); else diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index d75064fb7d12..1a3ac0b5dd89 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -116,7 +116,7 @@ static unsigned int mpic_msgr_number_of_blocks(void) for (;;) { snprintf(buf, sizeof(buf), "mpic-msgr-block%d", count); - if (!of_find_property(aliases, buf, NULL)) + if (!of_property_present(aliases, buf)) break; count += 1; -- GitLab From 4d57e3515e3838b12eccbeb5e0e52f053e3f638a Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:46:57 -0600 Subject: [PATCH 1682/5631] powerpc: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230310144659.1541127-1-robh@kernel.org --- arch/powerpc/kernel/btext.c | 2 +- arch/powerpc/kernel/legacy_serial.c | 2 +- arch/powerpc/platforms/4xx/pci.c | 18 +++++++----------- arch/powerpc/platforms/52xx/mpc52xx_common.c | 4 ++-- arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 4 ++-- arch/powerpc/platforms/maple/setup.c | 2 +- arch/powerpc/platforms/pasemi/iommu.c | 2 +- arch/powerpc/platforms/powermac/feature.c | 2 +- arch/powerpc/platforms/powermac/pic.c | 4 ++-- arch/powerpc/platforms/powermac/setup.c | 2 +- arch/powerpc/platforms/powermac/smp.c | 2 +- arch/powerpc/platforms/pseries/vio.c | 2 +- arch/powerpc/sysdev/dcr.c | 2 +- arch/powerpc/sysdev/ehv_pic.c | 6 +----- arch/powerpc/sysdev/fsl_soc.c | 2 +- arch/powerpc/sysdev/mpic.c | 6 +++--- arch/powerpc/sysdev/tsi108_dev.c | 2 +- arch/powerpc/sysdev/xive/native.c | 6 ++---- 18 files changed, 30 insertions(+), 40 deletions(-) diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 2769889219bf..19e46fd623b0 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -235,7 +235,7 @@ int __init btext_find_display(int allow_nonstdout) return rc; for_each_node_by_type(np, "display") { - if (of_get_property(np, "linux,opened", NULL)) { + if (of_property_read_bool(np, "linux,opened")) { printk("trying %pOF ...\n", np); rc = btext_initialize(np); printk("result: %d\n", rc); diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 1a3b7f3513b4..c9ad12461d44 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -179,7 +179,7 @@ static int __init add_legacy_soc_port(struct device_node *np, return -1; /* if rtas uses this device, don't try to use it as well */ - if (of_get_property(np, "used-by-rtas", NULL) != NULL) + if (of_property_read_bool(np, "used-by-rtas")) return -1; /* Get the address */ diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index ca5dd7a5842a..3638505a138c 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -348,7 +348,7 @@ static void __init ppc4xx_probe_pci_bridge(struct device_node *np) } /* Check if primary bridge */ - if (of_get_property(np, "primary", NULL)) + if (of_property_read_bool(np, "primary")) primary = 1; /* Get bus range if any */ @@ -530,7 +530,7 @@ static void __init ppc4xx_probe_pcix_bridge(struct device_node *np) struct pci_controller *hose = NULL; void __iomem *reg = NULL; const int *bus_range; - int big_pim = 0, msi = 0, primary = 0; + int big_pim, msi, primary; /* Fetch config space registers address */ if (of_address_to_resource(np, 0, &rsrc_cfg)) { @@ -546,16 +546,13 @@ static void __init ppc4xx_probe_pcix_bridge(struct device_node *np) } /* Check if it supports large PIMs (440GX) */ - if (of_get_property(np, "large-inbound-windows", NULL)) - big_pim = 1; + big_pim = of_property_read_bool(np, "large-inbound-windows"); /* Check if we should enable MSIs inbound hole */ - if (of_get_property(np, "enable-msi-hole", NULL)) - msi = 1; + msi = of_property_read_bool(np, "enable-msi-hole"); /* Check if primary bridge */ - if (of_get_property(np, "primary", NULL)) - primary = 1; + primary = of_property_read_bool(np, "primary"); /* Get bus range if any */ bus_range = of_get_property(np, "bus-range", NULL); @@ -1915,14 +1912,13 @@ static void __init ppc4xx_pciex_port_setup_hose(struct ppc4xx_pciex_port *port) struct resource dma_window; struct pci_controller *hose = NULL; const int *bus_range; - int primary = 0, busses; + int primary, busses; void __iomem *mbase = NULL, *cfg_data = NULL; const u32 *pval; u32 val; /* Check if primary bridge */ - if (of_get_property(port->node, "primary", NULL)) - primary = 1; + primary = of_property_read_bool(port->node, "primary"); /* Get bus range if any */ bus_range = of_get_property(port->node, "bus-range", NULL); diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c index 409c0ec06265..b4938e344f71 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_common.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c @@ -141,8 +141,8 @@ mpc52xx_map_common_devices(void) * on a gpt0, so check has-wdt property before mapping. */ for_each_matching_node(np, mpc52xx_gpt_ids) { - if (of_get_property(np, "fsl,has-wdt", NULL) || - of_get_property(np, "has-wdt", NULL)) { + if (of_property_read_bool(np, "fsl,has-wdt") || + of_property_read_bool(np, "has-wdt")) { mpc52xx_wdt = of_iomap(np, 0); of_node_put(np); break; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index e43e08d991ea..3fce4e1c3af6 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -735,8 +735,8 @@ static int mpc52xx_gpt_probe(struct platform_device *ofdev) mutex_unlock(&mpc52xx_gpt_list_mutex); /* check if this device could be a watchdog */ - if (of_get_property(ofdev->dev.of_node, "fsl,has-wdt", NULL) || - of_get_property(ofdev->dev.of_node, "has-wdt", NULL)) { + if (of_property_read_bool(ofdev->dev.of_node, "fsl,has-wdt") || + of_property_read_bool(ofdev->dev.of_node, "has-wdt")) { const u32 *on_boot_wdt; gpt->wdt_mode = MPC52xx_GPT_CAN_WDT; diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index 40618513e3f5..a4a79d77eca2 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -235,7 +235,7 @@ static void __init maple_init_IRQ(void) BUG_ON(openpic_addr == 0); /* Check for a big endian MPIC */ - if (of_get_property(np, "big-endian", NULL) != NULL) + if (of_property_read_bool(np, "big-endian")) flags |= MPIC_BIG_ENDIAN; /* XXX Maple specific bits */ diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 0a38663d44ed..375487cba874 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -254,7 +254,7 @@ void __init iommu_init_early_pasemi(void) iommu_off = 1; #else iommu_off = of_chosen && - of_get_property(of_chosen, "linux,iommu-off", NULL); + of_property_read_bool(of_chosen, "linux,iommu-off"); #endif if (iommu_off) return; diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 0382d20b5619..6b1f974b074f 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2506,7 +2506,7 @@ static int __init probe_motherboard(void) int cpu_count = 1; /* Nap mode not supported on SMP */ - if (of_get_property(np, "flush-on-lock", NULL) || + if (of_property_read_bool(np, "flush-on-lock") || (cpu_count > 1)) { powersave_nap = 0; of_node_put(np); diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 7425f94e271e..7135ea1d7db6 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -450,7 +450,7 @@ static struct mpic * __init pmac_setup_one_mpic(struct device_node *np, pmac_call_feature(PMAC_FTR_ENABLE_MPIC, np, 0, 0); - if (of_get_property(np, "big-endian", NULL)) + if (of_property_read_bool(np, "big-endian")) flags |= MPIC_BIG_ENDIAN; /* Primary Big Endian means HT interrupts. This is quite dodgy @@ -527,7 +527,7 @@ void __init pmac_pic_init(void) #ifdef CONFIG_PPC32 if (!pmac_newworld) of_irq_workarounds |= OF_IMAP_OLDWORLD_MAC; - if (of_get_property(of_chosen, "linux,bootx", NULL) != NULL) + if (of_property_read_bool(of_chosen, "linux,bootx")) of_irq_workarounds |= OF_IMAP_NO_PHANDLE; /* If we don't have phandles on a newworld, then try to locate a diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 4f7ee885a78f..193cc9c39422 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -137,7 +137,7 @@ static void pmac_show_cpuinfo(struct seq_file *m) of_get_property(np, "d-cache-size", NULL); seq_printf(m, "L2 cache\t:"); has_l2cache = 1; - if (of_get_property(np, "cache-unified", NULL) && dc) { + if (of_property_read_bool(np, "cache-unified") && dc) { seq_printf(m, " %dK unified", *dc / 1024); } else { if (ic) diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index 5b26a9012d2e..8be71920e63c 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -706,7 +706,7 @@ static void __init smp_core99_setup(int ncpus) struct device_node *cpus = of_find_node_by_path("/cpus"); if (cpus && - of_get_property(cpus, "platform-cpu-timebase", NULL)) { + of_property_read_bool(cpus, "platform-cpu-timebase")) { pmac_tb_freeze = smp_core99_pfunc_tb_freeze; printk(KERN_INFO "Processor timebase sync using" " platform function\n"); diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index d54306a936d5..a533ab3c7236 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1381,7 +1381,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) } if (family == PFO) { - if (of_get_property(of_node, "interrupt-controller", NULL)) { + if (of_property_read_bool(of_node, "interrupt-controller")) { pr_debug("%s: Skipping the interrupt controller %pOFn.\n", __func__, of_node); return NULL; diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c index 3093f14111e6..70ce66eadff1 100644 --- a/arch/powerpc/sysdev/dcr.c +++ b/arch/powerpc/sysdev/dcr.c @@ -18,7 +18,7 @@ static struct device_node *find_dcr_parent(struct device_node *node) const u32 *p; for (par = of_node_get(node); par;) { - if (of_get_property(par, "dcr-controller", NULL)) + if (of_property_read_bool(par, "dcr-controller")) break; p = of_get_property(par, "dcr-parent", NULL); tmp = par; diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index 00705258ecf9..c7327b836d2b 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -256,7 +256,6 @@ void __init ehv_pic_init(void) { struct device_node *np, *np2; struct ehv_pic *ehv_pic; - int coreint_flag = 1; np = of_find_compatible_node(NULL, NULL, "epapr,hv-pic"); if (!np) { @@ -264,9 +263,6 @@ void __init ehv_pic_init(void) return; } - if (!of_find_property(np, "has-external-proxy", NULL)) - coreint_flag = 0; - ehv_pic = kzalloc(sizeof(struct ehv_pic), GFP_KERNEL); if (!ehv_pic) { of_node_put(np); @@ -292,7 +288,7 @@ void __init ehv_pic_init(void) ehv_pic->hc_irq = ehv_pic_irq_chip; ehv_pic->hc_irq.irq_set_affinity = ehv_pic_set_affinity; - ehv_pic->coreint_flag = coreint_flag; + ehv_pic->coreint_flag = of_property_read_bool(np, "has-external-proxy"); global_ehv_pic = ehv_pic; irq_set_default_host(global_ehv_pic->irqhost); diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 78118c188993..6ebbbca41065 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -174,7 +174,7 @@ static int __init setup_rstcr(void) }; for_each_node_by_name(np, "global-utilities") { - if ((of_get_property(np, "fsl,has-rstcr", NULL))) { + if (of_property_read_bool(np, "fsl,has-rstcr")) { rstcr = of_iomap(np, 0) + 0xb0; if (!rstcr) { printk (KERN_ERR "Error: reset control " diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 9a9381f102d6..ba287abcb008 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1260,11 +1260,11 @@ struct mpic * __init mpic_alloc(struct device_node *node, } /* Read extra device-tree properties into the flags variable */ - if (of_get_property(node, "big-endian", NULL)) + if (of_property_read_bool(node, "big-endian")) flags |= MPIC_BIG_ENDIAN; - if (of_get_property(node, "pic-no-reset", NULL)) + if (of_property_read_bool(node, "pic-no-reset")) flags |= MPIC_NO_RESET; - if (of_get_property(node, "single-cpu-affinity", NULL)) + if (of_property_read_bool(node, "single-cpu-affinity")) flags |= MPIC_SINGLE_DEST_CPU; if (of_device_is_compatible(node, "fsl,mpic")) { flags |= MPIC_FSL | MPIC_LARGE_VECTORS; diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c index 30051397292f..bbccbe9f2b84 100644 --- a/arch/powerpc/sysdev/tsi108_dev.c +++ b/arch/powerpc/sysdev/tsi108_dev.c @@ -132,7 +132,7 @@ static int __init tsi108_eth_of_init(void) * driver itself to phylib and use a non-misleading * name for the workaround flag - it's not actually to * do with the model of PHY in use */ - if (of_get_property(phy, "txc-rxc-delay-disable", NULL)) + if (of_property_read_bool(phy, "txc-rxc-delay-disable")) tsi_eth_data.phy_type = TSI108_PHY_BCM54XX; of_node_put(phy); diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 19d880ebc5e6..9f0af4d795d8 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -599,11 +599,9 @@ bool __init xive_native_init(void) } /* Do we support single escalation */ - if (of_get_property(np, "single-escalation-support", NULL) != NULL) - xive_has_single_esc = true; + xive_has_single_esc = of_property_read_bool(np, "single-escalation-support"); - if (of_get_property(np, "vp-save-restore", NULL)) - xive_has_save_restore = true; + xive_has_save_restore = of_property_read_bool(np, "vp-save-restore"); /* Configure Thread Management areas for KVM */ for_each_possible_cpu(cpu) -- GitLab From 87b626a66dd4ab7d5caf5199d98ec0b5953d73f8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:35 -0600 Subject: [PATCH 1683/5631] macintosh: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230310144735.1546817-1-robh@kernel.org --- drivers/macintosh/rack-meter.c | 2 +- drivers/macintosh/therm_adt746x.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c index c28893e41a8b..40240bce77b0 100644 --- a/drivers/macintosh/rack-meter.c +++ b/drivers/macintosh/rack-meter.c @@ -387,7 +387,7 @@ static int rackmeter_probe(struct macio_dev* mdev, if (of_node_name_eq(np, "lightshow")) break; if (of_node_name_eq(np, "sound") && - of_get_property(np, "virtual", NULL) != NULL) + of_property_present(np, "virtual")) break; } if (np == NULL) { diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c index 8f5db9093c9a..384b87d661e1 100644 --- a/drivers/macintosh/therm_adt746x.c +++ b/drivers/macintosh/therm_adt746x.c @@ -483,7 +483,7 @@ static int probe_thermostat(struct i2c_client *client) if (vers != 1) return -ENXIO; - if (of_get_property(np, "hwsensor-location", NULL)) { + if (of_property_present(np, "hwsensor-location")) { for (i = 0; i < 3; i++) { sensor_location[i] = of_get_property(np, "hwsensor-location", NULL) + offset; -- GitLab From 560f2eb7d6a775e488832b724b25bde33ce71b9f Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 23 Mar 2023 11:54:10 +0100 Subject: [PATCH 1684/5631] leds: rgb: mt6370: Correct config name to select in LEDS_MT6370_RGB Commit 55a8a5c16eb3 ("leds: rgb: mt6370: Add MediaTek MT6370 current sink type LED Indicator support") introduces the config LEDS_MT6370_RGB, which selects the non-existing config LINEAR_RANGE. As the driver includes linux/linear_range.h, it is a safe guess that the config actually intends to select LINEAR_RANGES, which provides the library implementation for the function prototypes defined in the linear_range header file. Correct this naming confusion in the LEDS_MT6370_RGB config definition. Fixes: 55a8a5c16eb3 ("leds: rgb: mt6370: Add MediaTek MT6370 current sink type LED Indicator support") Signed-off-by: Lukas Bulwahn Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230323105410.10396-1-lukas.bulwahn@gmail.com --- drivers/leds/rgb/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/leds/rgb/Kconfig b/drivers/leds/rgb/Kconfig index 7d86bb26c54b..360c8679c6e2 100644 --- a/drivers/leds/rgb/Kconfig +++ b/drivers/leds/rgb/Kconfig @@ -29,7 +29,7 @@ config LEDS_QCOM_LPG config LEDS_MT6370_RGB tristate "LED Support for MediaTek MT6370 PMIC" depends on MFD_MT6370 - select LINEAR_RANGE + select LINEAR_RANGES help Say Y here to enable support for MT6370_RGB LED device. In MT6370, there are four channel current-sink LED drivers that -- GitLab From 22dc3789b737fe29d8f54f0d084047aede5550ad Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 17 Mar 2023 15:13:41 -0400 Subject: [PATCH 1685/5631] leds: flash: Set variables mvflash_{3,4}ch_regs storage-class-specifier to static Smatch reports: drivers/leds/flash/leds-qcom-flash.c:103:18: warning: symbol 'mvflash_3ch_regs' was not declared. Should it be static? drivers/leds/flash/leds-qcom-flash.c:115:18: warning: symbol 'mvflash_4ch_regs' was not declared. Should it be static? These variables are only used locally, so it should be static. Signed-off-by: Tom Rix Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230317191341.1670660-1-trix@redhat.com --- drivers/leds/flash/leds-qcom-flash.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/leds/flash/leds-qcom-flash.c b/drivers/leds/flash/leds-qcom-flash.c index 406ed8761c78..90a24fa25a49 100644 --- a/drivers/leds/flash/leds-qcom-flash.c +++ b/drivers/leds/flash/leds-qcom-flash.c @@ -100,7 +100,7 @@ enum { REG_MAX_COUNT, }; -struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = { +static struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = { REG_FIELD(0x08, 0, 7), /* status1 */ REG_FIELD(0x09, 0, 7), /* status2 */ REG_FIELD(0x0a, 0, 7), /* status3 */ @@ -112,7 +112,7 @@ struct reg_field mvflash_3ch_regs[REG_MAX_COUNT] = { REG_FIELD(0x4c, 0, 2), /* chan_en */ }; -struct reg_field mvflash_4ch_regs[REG_MAX_COUNT] = { +static struct reg_field mvflash_4ch_regs[REG_MAX_COUNT] = { REG_FIELD(0x06, 0, 7), /* status1 */ REG_FIELD(0x07, 0, 6), /* status2 */ REG_FIELD(0x09, 0, 7), /* status3 */ -- GitLab From 31f0a454d3dff997eb6570297e0c555d511dbdd6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:37 +0100 Subject: [PATCH 1686/5631] pinctrl: renesas: r8a77995: Retain POCCTRL0 register across suspend/resume The POC Control Register 0 (POCCTRL0) on R-Car D3 is not registered in the pinmux_ioctrl_regs[] array. Hence it is not saved/restored during suspend/resume, and its contents may be lost after s2ram. This went unnoticed when improving suspend/resume support in commit d92ee9cf8ec8d7fe ("pinctrl: sh-pfc: rcar-gen3: Retain TDSELCTRL register across suspend/resume"). Fix this by moving the pinmux_ioctrl_regs[] array up, and adding the POCCTRL0 register. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/d17402b83b1f3fa0f572527c0382027bccb86205.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77995.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77995.c b/drivers/pinctrl/renesas/pfc-r8a77995.c index d949ae59c757..8e4ba9c61234 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77995.c +++ b/drivers/pinctrl/renesas/pfc-r8a77995.c @@ -2855,11 +2855,23 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { { }, }; +enum ioctrl_regs { + POCCTRL0, + TDSELCTRL, +}; + +static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { + [POCCTRL0] = { 0xe6060380, }, + [TDSELCTRL] = { 0xe60603c0, }, + { /* sentinel */ }, +}; + + static int r8a77995_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { int bit = -EINVAL; - *pocctrl = 0xe6060380; + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 9)) bit = 29 - (pin - RCAR_GP_PIN(3, 0)); @@ -3075,15 +3087,6 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { { /* sentinel */ } }; -enum ioctrl_regs { - TDSELCTRL, -}; - -static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { - [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, -}; - static const struct pinmux_bias_reg * r8a77995_pin_to_bias_reg(const struct sh_pfc *pfc, unsigned int pin, unsigned int *puen_bit, unsigned int *pud_bit) -- GitLab From a3ca1e18931e60c9f1765f630b677cad8372d1b7 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:38 +0100 Subject: [PATCH 1687/5631] pinctrl: renesas: rcar: Phase out old SH_PFC_PIN_CFG_IO_VOLTAGE flag Commit 537db25ca330dce0 ("pinctrl: renesas: Add I/O voltage level flag") introduced new flags to support pins that can switch their voltage levels between either 1.8V and 3.3V, or between 2.5V and 3.3V. The old SH_PFC_PIN_CFG_IO_VOLTAGE flag was retained to avoid having to change existing drivers. Replace SH_PFC_PIN_CFG_IO_VOLTAGE by SH_PFC_PIN_CFG_IO_VOLTAGE_18_33, to make the voltage configuration explicit, and to prepare for the advent of support for more voltage levels. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/ae5f879c093f3e3cd50ba1495975bccfad81237b.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77470.c | 44 +++++++++++------------ drivers/pinctrl/renesas/pfc-r8a7790.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7791.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7794.c | 48 +++++++++++++------------- drivers/pinctrl/renesas/pfc-r8a77951.c | 4 +-- drivers/pinctrl/renesas/pfc-r8a7796.c | 4 +-- drivers/pinctrl/renesas/pfc-r8a77965.c | 4 +-- drivers/pinctrl/renesas/pfc-r8a77970.c | 6 ++-- drivers/pinctrl/renesas/pfc-r8a77980.c | 6 ++-- drivers/pinctrl/renesas/pfc-r8a77990.c | 4 +-- drivers/pinctrl/renesas/pfc-r8a77995.c | 2 +- 11 files changed, 63 insertions(+), 63 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77470.c b/drivers/pinctrl/renesas/pfc-r8a77470.c index b5725c3ed2b6..4ba710610255 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77470.c +++ b/drivers/pinctrl/renesas/pfc-r8a77470.c @@ -13,24 +13,24 @@ #define CPU_ALL_GP(fn, sfx) \ PORT_GP_CFG_4(0, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(0, 4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 5, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 7, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 8, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 9, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 10, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 5, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 7, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 8, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 9, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 10, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(0, 11, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(0, 12, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 13, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 20, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 21, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(0, 22, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 13, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 20, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 21, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(0, 22, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_23(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_32(2, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ @@ -38,12 +38,12 @@ PORT_GP_CFG_1(3, 28, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(3, 29, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_14(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(4, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(4, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(4, 20, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(4, 21, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(4, 22, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ diff --git a/drivers/pinctrl/renesas/pfc-r8a7790.c b/drivers/pinctrl/renesas/pfc-r8a7790.c index ee21d650991b..149700ee1d10 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7790.c +++ b/drivers/pinctrl/renesas/pfc-r8a7790.c @@ -24,7 +24,7 @@ PORT_GP_CFG_32(0, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_30(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_30(2, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_32(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_32(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_32(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_32(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP) diff --git a/drivers/pinctrl/renesas/pfc-r8a7791.c b/drivers/pinctrl/renesas/pfc-r8a7791.c index d57458504117..c83e21c4c395 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7791.c +++ b/drivers/pinctrl/renesas/pfc-r8a7791.c @@ -22,7 +22,7 @@ PORT_GP_CFG_32(3, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_32(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_32(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_24(6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_24(6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(6, 24, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(6, 25, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(6, 26, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ diff --git a/drivers/pinctrl/renesas/pfc-r8a7794.c b/drivers/pinctrl/renesas/pfc-r8a7794.c index 668643553a70..6e801ae90d25 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7794.c +++ b/drivers/pinctrl/renesas/pfc-r8a7794.c @@ -42,30 +42,30 @@ PORT_GP_1(5, 25, fn, sfx), \ PORT_GP_1(5, 26, fn, sfx), \ PORT_GP_1(5, 27, fn, sfx), \ - PORT_GP_CFG_1(6, 0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_1(6, 1, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 4, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 5, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 7, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 8, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_1(6, 9, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 10, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 11, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 12, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 13, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE), \ - PORT_GP_CFG_1(6, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 20, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 21, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 22, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ - PORT_GP_CFG_1(6, 23, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ + PORT_GP_CFG_1(6, 1, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 4, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 5, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 6, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 7, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 8, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ + PORT_GP_CFG_1(6, 9, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 10, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 11, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 12, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 13, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 14, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 15, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 16, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ + PORT_GP_CFG_1(6, 17, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 18, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 19, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 20, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 21, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 22, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(6, 23, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(6, 24, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ PORT_GP_CFG_1(6, 25, fn, sfx, SH_PFC_PIN_CFG_PULL_UP) diff --git a/drivers/pinctrl/renesas/pfc-r8a77951.c b/drivers/pinctrl/renesas/pfc-r8a77951.c index d4d271dff055..321014c8bc16 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77951.c +++ b/drivers/pinctrl/renesas/pfc-r8a77951.c @@ -17,12 +17,12 @@ PORT_GP_CFG_16(0, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_29(1, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_15(2, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_26(5, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_32(6, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_4(7, fn, sfx, CFG_FLAGS) diff --git a/drivers/pinctrl/renesas/pfc-r8a7796.c b/drivers/pinctrl/renesas/pfc-r8a7796.c index a0096ef5e68d..5db8429c54fe 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7796.c +++ b/drivers/pinctrl/renesas/pfc-r8a7796.c @@ -22,12 +22,12 @@ PORT_GP_CFG_16(0, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_29(1, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_15(2, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_26(5, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_32(6, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_4(7, fn, sfx, CFG_FLAGS) diff --git a/drivers/pinctrl/renesas/pfc-r8a77965.c b/drivers/pinctrl/renesas/pfc-r8a77965.c index acd0bdf13018..2b8b49b18b10 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77965.c +++ b/drivers/pinctrl/renesas/pfc-r8a77965.c @@ -23,12 +23,12 @@ PORT_GP_CFG_16(0, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_29(1, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_15(2, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \ + PORT_GP_CFG_18(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33), \ PORT_GP_CFG_26(5, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_32(6, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_4(7, fn, sfx, CFG_FLAGS) diff --git a/drivers/pinctrl/renesas/pfc-r8a77970.c b/drivers/pinctrl/renesas/pfc-r8a77970.c index 4a7803eaafaa..578c1d6fc2e0 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77970.c +++ b/drivers/pinctrl/renesas/pfc-r8a77970.c @@ -19,10 +19,10 @@ #include "sh_pfc.h" #define CPU_ALL_GP(fn, sfx) \ - PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_28(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_6(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_15(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN) diff --git a/drivers/pinctrl/renesas/pfc-r8a77980.c b/drivers/pinctrl/renesas/pfc-r8a77980.c index ac03309c5c0c..b632ea1b29c7 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77980.c +++ b/drivers/pinctrl/renesas/pfc-r8a77980.c @@ -19,10 +19,10 @@ #include "sh_pfc.h" #define CPU_ALL_GP(fn, sfx) \ - PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_28(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PORT_GP_CFG_30(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_30(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_25(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_15(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN) diff --git a/drivers/pinctrl/renesas/pfc-r8a77990.c b/drivers/pinctrl/renesas/pfc-r8a77990.c index b0936962fad7..57de0580a440 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77990.c +++ b/drivers/pinctrl/renesas/pfc-r8a77990.c @@ -22,12 +22,12 @@ PORT_GP_CFG_18(0, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_23(1, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_26(2, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ + PORT_GP_CFG_12(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ PORT_GP_CFG_1(3, 12, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 13, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 14, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(3, 15, fn, sfx, CFG_FLAGS), \ - PORT_GP_CFG_11(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ + PORT_GP_CFG_11(4, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_DRIVE_STRENGTH), \ PORT_GP_CFG_20(5, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_9(6, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_1(6, 9, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ diff --git a/drivers/pinctrl/renesas/pfc-r8a77995.c b/drivers/pinctrl/renesas/pfc-r8a77995.c index 8e4ba9c61234..5a42213c680c 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77995.c +++ b/drivers/pinctrl/renesas/pfc-r8a77995.c @@ -21,7 +21,7 @@ PORT_GP_CFG_9(0, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_32(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_32(2, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PORT_GP_CFG_10(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PORT_GP_CFG_10(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 | SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_32(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_21(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PORT_GP_CFG_14(6, fn, sfx, SH_PFC_PIN_CFG_PULL_UP_DOWN) -- GitLab From b88e733ac5170efe5f26c62606ff97901dad9248 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:39 +0100 Subject: [PATCH 1688/5631] pinctrl: renesas: Add support for 1.8V/2.5V I/O voltage levels Currently, the Renesas pin control driver supports pins that can switch their I/O voltage levels between either 1.8V and 3.3V, or between 2.5V and 3.3V. However, some SoCs have pins that can switch between 1.8V and 2.5V. Add support for this by replacing the separate SH_PFC_PIN_CFG_IO_VOLTAGE capability and voltage level flags by a 2-bit field, to cover three possible I/O voltage switching options. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/0c04925457bf3f7e78e7e3851528d9a4c29246da.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/core.c | 4 ++-- drivers/pinctrl/renesas/pinctrl.c | 22 ++++++++++++---------- drivers/pinctrl/renesas/sh_pfc.h | 13 +++++-------- 3 files changed, 19 insertions(+), 20 deletions(-) diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index ed092ca314dd..336cfae756b0 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -1114,9 +1114,9 @@ static void __init sh_pfc_check_info(const struct sh_pfc_soc_info *info) } } - if (pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE) { + if (pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE_MASK) { if (!info->ops || !info->ops->pin_to_pocctrl) - sh_pfc_err_once(power, "SH_PFC_PIN_CFG_IO_VOLTAGE flag set but .pin_to_pocctrl() not implemented\n"); + sh_pfc_err_once(power, "SH_PFC_PIN_CFG_IO_VOLTAGE set but .pin_to_pocctrl() not implemented\n"); else if (info->ops->pin_to_pocctrl(pin->pin, &x) < 0) sh_pfc_err("pin %s: SH_PFC_PIN_CFG_IO_VOLTAGE set but invalid pin_to_pocctrl()\n", pin->name); diff --git a/drivers/pinctrl/renesas/pinctrl.c b/drivers/pinctrl/renesas/pinctrl.c index adaca1f7ccf8..4d9d58fc1356 100644 --- a/drivers/pinctrl/renesas/pinctrl.c +++ b/drivers/pinctrl/renesas/pinctrl.c @@ -559,7 +559,7 @@ static bool sh_pfc_pinconf_validate(struct sh_pfc *pfc, unsigned int _pin, return pin->configs & SH_PFC_PIN_CFG_DRIVE_STRENGTH; case PIN_CONFIG_POWER_SOURCE: - return pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE; + return pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE_MASK; default: return false; @@ -612,7 +612,7 @@ static int sh_pfc_pinconf_get(struct pinctrl_dev *pctldev, unsigned _pin, case PIN_CONFIG_POWER_SOURCE: { int idx = sh_pfc_get_pin_index(pfc, _pin); const struct sh_pfc_pin *pin = &pfc->info->pins[idx]; - unsigned int lower_voltage; + unsigned int mode, lo, hi; u32 pocctrl, val; int bit; @@ -625,10 +625,11 @@ static int sh_pfc_pinconf_get(struct pinctrl_dev *pctldev, unsigned _pin, val = sh_pfc_read(pfc, pocctrl); - lower_voltage = (pin->configs & SH_PFC_PIN_VOLTAGE_25_33) ? - 2500 : 1800; + mode = pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE_MASK; + lo = mode <= SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 ? 1800 : 2500; + hi = mode >= SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 ? 3300 : 2500; - arg = (val & BIT(bit)) ? 3300 : lower_voltage; + arg = (val & BIT(bit)) ? hi : lo; break; } @@ -684,7 +685,7 @@ static int sh_pfc_pinconf_set(struct pinctrl_dev *pctldev, unsigned _pin, unsigned int mV = pinconf_to_config_argument(configs[i]); int idx = sh_pfc_get_pin_index(pfc, _pin); const struct sh_pfc_pin *pin = &pfc->info->pins[idx]; - unsigned int lower_voltage; + unsigned int mode, lo, hi; u32 pocctrl, val; int bit; @@ -695,15 +696,16 @@ static int sh_pfc_pinconf_set(struct pinctrl_dev *pctldev, unsigned _pin, if (WARN(bit < 0, "invalid pin %#x", _pin)) return bit; - lower_voltage = (pin->configs & SH_PFC_PIN_VOLTAGE_25_33) ? - 2500 : 1800; + mode = pin->configs & SH_PFC_PIN_CFG_IO_VOLTAGE_MASK; + lo = mode <= SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 ? 1800 : 2500; + hi = mode >= SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 ? 3300 : 2500; - if (mV != lower_voltage && mV != 3300) + if (mV != lo && mV != hi) return -EINVAL; spin_lock_irqsave(&pfc->lock, flags); val = sh_pfc_read(pfc, pocctrl); - if (mV == 3300) + if (mV == hi) val |= BIT(bit); else val &= ~BIT(bit); diff --git a/drivers/pinctrl/renesas/sh_pfc.h b/drivers/pinctrl/renesas/sh_pfc.h index 83312fac14e5..8dc7a66009ad 100644 --- a/drivers/pinctrl/renesas/sh_pfc.h +++ b/drivers/pinctrl/renesas/sh_pfc.h @@ -29,16 +29,13 @@ enum { #define SH_PFC_PIN_CFG_PULL_DOWN (1 << 3) #define SH_PFC_PIN_CFG_PULL_UP_DOWN (SH_PFC_PIN_CFG_PULL_UP | \ SH_PFC_PIN_CFG_PULL_DOWN) -#define SH_PFC_PIN_CFG_IO_VOLTAGE (1 << 4) -#define SH_PFC_PIN_CFG_DRIVE_STRENGTH (1 << 5) -#define SH_PFC_PIN_VOLTAGE_18_33 (0 << 6) -#define SH_PFC_PIN_VOLTAGE_25_33 (1 << 6) +#define SH_PFC_PIN_CFG_IO_VOLTAGE_MASK GENMASK(5, 4) +#define SH_PFC_PIN_CFG_IO_VOLTAGE_18_25 (1 << 4) +#define SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 (2 << 4) +#define SH_PFC_PIN_CFG_IO_VOLTAGE_25_33 (3 << 4) -#define SH_PFC_PIN_CFG_IO_VOLTAGE_18_33 (SH_PFC_PIN_CFG_IO_VOLTAGE | \ - SH_PFC_PIN_VOLTAGE_18_33) -#define SH_PFC_PIN_CFG_IO_VOLTAGE_25_33 (SH_PFC_PIN_CFG_IO_VOLTAGE | \ - SH_PFC_PIN_VOLTAGE_25_33) +#define SH_PFC_PIN_CFG_DRIVE_STRENGTH (1 << 6) #define SH_PFC_PIN_CFG_NO_GPIO (1 << 31) -- GitLab From a7bebdc5905ed23a3d33ec194a800b04b4161d3c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:40 +0100 Subject: [PATCH 1689/5631] pinctrl: renesas: r8a77970: Add support for AVB power-source Add support for configuring the I/O voltage level of the Ethernet AVB pins on the R-Car V3M SoC. "PIN_VDDQ_AVB0" can be configured for 2.5V or 3.3V operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/eb4db82bdeb67507a1a77f63b9d90280d6f38ba4.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77970.c | 28 ++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77970.c b/drivers/pinctrl/renesas/pfc-r8a77970.c index 578c1d6fc2e0..54da0c025458 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77970.c +++ b/drivers/pinctrl/renesas/pfc-r8a77970.c @@ -34,7 +34,8 @@ PIN_NOGP_CFG(TCK, "TCK", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TDI, "TDI", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TMS, "TMS", fn, SH_PFC_PIN_CFG_PULL_UP), \ - PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP) + PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(VDDQ_AVB0, "VDDQ_AVB0", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_25_33) /* * F_() : just information @@ -2364,19 +2365,30 @@ static int r8a77970_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { int bit = pin & 0x1f; - *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; - if (pin >= RCAR_GP_PIN(0, 0) && pin <= RCAR_GP_PIN(0, 21)) + switch (pin) { + case RCAR_GP_PIN(0, 0) ... RCAR_GP_PIN(0, 21): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; return bit; - if (pin >= RCAR_GP_PIN(2, 0) && pin <= RCAR_GP_PIN(2, 9)) + + case RCAR_GP_PIN(2, 0) ... RCAR_GP_PIN(2, 9): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; return bit + 22; - *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; - if (pin >= RCAR_GP_PIN(2, 10) && pin <= RCAR_GP_PIN(2, 16)) + case RCAR_GP_PIN(2, 10) ... RCAR_GP_PIN(2, 16): + *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; return bit - 10; - if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 16)) + + case RCAR_GP_PIN(3, 0) ... RCAR_GP_PIN(3, 16): + *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; return bit + 7; - return -EINVAL; + case PIN_VDDQ_AVB0: + *pocctrl = pinmux_ioctrl_regs[POCCTRL2].reg; + return 0; + + default: + return -EINVAL; + } } static const struct pinmux_bias_reg pinmux_bias_regs[] = { -- GitLab From 6cd853a45324e26d71d7848b7f0fe28b5c023375 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:41 +0100 Subject: [PATCH 1690/5631] pinctrl: renesas: r8a77980: Add support for AVB/GE power-sources Add support for configuring the I/O voltage levels of the Ethernet AVB and Gigabit Ethernet pins on the R-Car V3H SoC. "PIN_VDDQ_AVB" and "PIN_VDDQ_GE" can be configured for 2.5V or 3.3V operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/3c26c4f3735a6d071685c507c065172e63af5d70.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77980.c | 39 ++++++++++++++++++-------- 1 file changed, 28 insertions(+), 11 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77980.c b/drivers/pinctrl/renesas/pfc-r8a77980.c index b632ea1b29c7..8effbcec0b22 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77980.c +++ b/drivers/pinctrl/renesas/pfc-r8a77980.c @@ -35,7 +35,9 @@ PIN_NOGP_CFG(EXTALR, "EXTALR", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PIN_NOGP_CFG(FSCLKST, "FSCLKST", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ PIN_NOGP_CFG(FSCLKST_N, "FSCLKST#", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ - PIN_NOGP_CFG(PRESETOUT_N, "PRESETOUT#", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN) + PIN_NOGP_CFG(PRESETOUT_N, "PRESETOUT#", fn, SH_PFC_PIN_CFG_PULL_UP_DOWN), \ + PIN_NOGP_CFG(VDDQ_AVB, "VDDQ_AVB", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_25_33), \ + PIN_NOGP_CFG(VDDQ_GE, "VDDQ_GE", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_25_33) /* * F_() : just information @@ -2837,24 +2839,39 @@ static int r8a77980_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { int bit = pin & 0x1f; - *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; - if (pin >= RCAR_GP_PIN(0, 0) && pin <= RCAR_GP_PIN(0, 21)) + switch (pin) { + case RCAR_GP_PIN(0, 0) ... RCAR_GP_PIN(0, 21): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; return bit; - else if (pin >= RCAR_GP_PIN(2, 0) && pin <= RCAR_GP_PIN(2, 9)) + + case RCAR_GP_PIN(2, 0) ... RCAR_GP_PIN(2, 9): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; return bit + 22; - *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; - if (pin >= RCAR_GP_PIN(2, 10) && pin <= RCAR_GP_PIN(2, 16)) + case RCAR_GP_PIN(2, 10) ... RCAR_GP_PIN(2, 16): + *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; return bit - 10; - if ((pin >= RCAR_GP_PIN(2, 17) && pin <= RCAR_GP_PIN(2, 24)) || - (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 16))) + + case RCAR_GP_PIN(2, 17) ... RCAR_GP_PIN(2, 24): + case RCAR_GP_PIN(3, 0) ... RCAR_GP_PIN(3, 16): + *pocctrl = pinmux_ioctrl_regs[POCCTRL1].reg; return bit + 7; - *pocctrl = pinmux_ioctrl_regs[POCCTRL2].reg; - if (pin >= RCAR_GP_PIN(2, 25) && pin <= RCAR_GP_PIN(2, 29)) + case RCAR_GP_PIN(2, 25) ... RCAR_GP_PIN(2, 29): + *pocctrl = pinmux_ioctrl_regs[POCCTRL2].reg; return pin - 25; - return -EINVAL; + case PIN_VDDQ_AVB: + *pocctrl = pinmux_ioctrl_regs[POCCTRL3].reg; + return 0; + + case PIN_VDDQ_GE: + *pocctrl = pinmux_ioctrl_regs[POCCTRL3].reg; + return 1; + + default: + return -EINVAL; + } } static const struct pinmux_bias_reg pinmux_bias_regs[] = { -- GitLab From 7f25d5b04af2ec0b85a18071ab59f9a6e456dfe0 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:42 +0100 Subject: [PATCH 1691/5631] pinctrl: renesas: r8a77990: Add support for AVB power-source Add support for configuring the I/O voltage level of the Ethernet AVB pins on the R-Car E3 SoC. "PIN_VDDQ_AVB0" can be configured for 2.5V or 3.3V operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/57883cd2d94c7919dc0f0db07cf6169ca89538e6.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77990.c | 29 +++++++++++++++++--------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77990.c b/drivers/pinctrl/renesas/pfc-r8a77990.c index 57de0580a440..229ad12bc9b7 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77990.c +++ b/drivers/pinctrl/renesas/pfc-r8a77990.c @@ -56,7 +56,8 @@ PIN_NOGP_CFG(TCK, "TCK", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TDI, "TDI", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TMS, "TMS", fn, SH_PFC_PIN_CFG_PULL_UP), \ - PIN_NOGP_CFG(TRST_N, "TRST_N", fn, SH_PFC_PIN_CFG_PULL_UP) + PIN_NOGP_CFG(TRST_N, "TRST_N", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(VDDQ_AVB0, "VDDQ_AVB0", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_25_33) /* * F_() : just information @@ -507,7 +508,8 @@ MOD_SEL0_1_0 FM(AVB_TD3) \ FM(PRESETOUT_N) FM(FSCLKST_N) FM(TRST_N) FM(TCK) FM(TMS) FM(TDI) \ FM(ASEBRK) \ - FM(MLB_REF) + FM(MLB_REF) \ + FM(VDDQ_AVB0) enum { PINMUX_RESERVED = 0, @@ -5040,28 +5042,35 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { enum ioctrl_regs { POCCTRL0, + POCCTRL2, TDSELCTRL, }; static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL0] = { 0xe6060380, }, + [POCCTRL2] = { 0xe6060388, }, [TDSELCTRL] = { 0xe60603c0, }, { /* sentinel */ }, }; static int r8a77990_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { - int bit = -EINVAL; + switch (pin) { + case RCAR_GP_PIN(3, 0) ... RCAR_GP_PIN(3, 11): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; + return pin & 0x1f; - *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; + case RCAR_GP_PIN(4, 0) ... RCAR_GP_PIN(4, 10): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; + return (pin & 0x1f) + 19; - if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 11)) - bit = pin & 0x1f; + case PIN_VDDQ_AVB0: + *pocctrl = pinmux_ioctrl_regs[POCCTRL2].reg; + return 0; - if (pin >= RCAR_GP_PIN(4, 0) && pin <= RCAR_GP_PIN(4, 10)) - bit = (pin & 0x1f) + 19; - - return bit; + default: + return -EINVAL; + } } static const struct pinmux_bias_reg pinmux_bias_regs[] = { -- GitLab From d04b961dd44d02c47ca7b716b493478d4a3f3967 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:43 +0100 Subject: [PATCH 1692/5631] pinctrl: renesas: r8a77995: Add support for AVB power-source Add support for configuring the I/O voltage level of the Ethernet AVB pins on the R-Car D3 SoC. "PIN_VDDQ_AVB0" can be configured for 2.5V or 3.3V operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/8f9164487715d8a4898ca651038c0b4d5013764c.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a77995.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a77995.c b/drivers/pinctrl/renesas/pfc-r8a77995.c index 5a42213c680c..29664d97e5ec 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77995.c +++ b/drivers/pinctrl/renesas/pfc-r8a77995.c @@ -34,7 +34,8 @@ PIN_NOGP_CFG(TCK, "TCK", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TDI, "TDI", fn, SH_PFC_PIN_CFG_PULL_UP), \ PIN_NOGP_CFG(TMS, "TMS", fn, SH_PFC_PIN_CFG_PULL_UP), \ - PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP) + PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(VDDQ_AVB0, "VDDQ_AVB0", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_25_33) /* * F_() : just information @@ -2857,11 +2858,13 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { enum ioctrl_regs { POCCTRL0, + POCCTRL2, TDSELCTRL, }; static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL0] = { 0xe6060380, }, + [POCCTRL2] = { 0xe6060388, }, [TDSELCTRL] = { 0xe60603c0, }, { /* sentinel */ }, }; @@ -2869,14 +2872,18 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { static int r8a77995_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { - int bit = -EINVAL; - - *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; + switch (pin) { + case RCAR_GP_PIN(3, 0) ... RCAR_GP_PIN(3, 9): + *pocctrl = pinmux_ioctrl_regs[POCCTRL0].reg; + return 29 - (pin - RCAR_GP_PIN(3, 0)); - if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 9)) - bit = 29 - (pin - RCAR_GP_PIN(3, 0)); + case PIN_VDDQ_AVB0: + *pocctrl = pinmux_ioctrl_regs[POCCTRL2].reg; + return 0; - return bit; + default: + return -EINVAL; + } } static const struct pinmux_bias_reg pinmux_bias_regs[] = { -- GitLab From 3c2465067f32beacc61ff898af7d8add1390aa95 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:42:44 +0100 Subject: [PATCH 1693/5631] pinctrl: renesas: r8a779g0: Add support for AVB/TSN power-sources Add support for configuring the I/O voltage levels of the Ethernet AVB and Ethernet TSN pins on the R-Car V4H SoC. "PIN_VDDQ_AVB[012]" and "PIN_VDDQ_TSN0" can be configured for 1.8V or 2.5V operation. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/c046e0be7d26302061d7aa629180a451734ddf8f.1678271030.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a779g0.c | 45 ++++++++++++++++++++------ 1 file changed, 36 insertions(+), 9 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 7c5379e2ede8..585ea6ada99a 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -49,6 +49,12 @@ PORT_GP_CFG_21(7, fn, sfx, CFG_FLAGS), \ PORT_GP_CFG_14(8, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE_18_33) +#define CPU_ALL_NOGP(fn) \ + PIN_NOGP_CFG(VDDQ_AVB0, "VDDQ_AVB0", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_18_25), \ + PIN_NOGP_CFG(VDDQ_AVB1, "VDDQ_AVB1", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_18_25), \ + PIN_NOGP_CFG(VDDQ_AVB2, "VDDQ_AVB2", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_18_25), \ + PIN_NOGP_CFG(VDDQ_TSN0, "VDDQ_TSN0", fn, SH_PFC_PIN_CFG_IO_VOLTAGE_18_25) + /* GPSR0 */ #define GPSR0_18 F_(MSIOF2_RXD, IP2SR0_11_8) #define GPSR0_17 F_(MSIOF2_SCK, IP2SR0_7_4) @@ -1221,10 +1227,12 @@ static const u16 pinmux_data[] = { */ enum { GP_ASSIGN_LAST(), + NOGP_ALL(), }; static const struct sh_pfc_pin pinmux_pins[] = { PINMUX_GPIO_GP_ALL(), + PINMUX_NOGP_ALL(), }; /* - AUDIO CLOCK ----------------------------------------- */ @@ -3973,23 +3981,42 @@ static int r8a779g0_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) { int bit = pin & 0x1f; - *pocctrl = pinmux_ioctrl_regs[POC0].reg; - if (pin >= RCAR_GP_PIN(0, 0) && pin <= RCAR_GP_PIN(0, 18)) + switch (pin) { + case RCAR_GP_PIN(0, 0) ... RCAR_GP_PIN(0, 18): + *pocctrl = pinmux_ioctrl_regs[POC0].reg; return bit; - *pocctrl = pinmux_ioctrl_regs[POC1].reg; - if (pin >= RCAR_GP_PIN(1, 0) && pin <= RCAR_GP_PIN(1, 22)) + case RCAR_GP_PIN(1, 0) ... RCAR_GP_PIN(1, 22): + *pocctrl = pinmux_ioctrl_regs[POC1].reg; return bit; - *pocctrl = pinmux_ioctrl_regs[POC3].reg; - if (pin >= RCAR_GP_PIN(3, 0) && pin <= RCAR_GP_PIN(3, 12)) + case RCAR_GP_PIN(3, 0) ... RCAR_GP_PIN(3, 12): + *pocctrl = pinmux_ioctrl_regs[POC3].reg; return bit; - *pocctrl = pinmux_ioctrl_regs[POC8].reg; - if (pin >= RCAR_GP_PIN(8, 0) && pin <= RCAR_GP_PIN(8, 13)) + case PIN_VDDQ_TSN0: + *pocctrl = pinmux_ioctrl_regs[POC4].reg; + return 0; + + case PIN_VDDQ_AVB2: + *pocctrl = pinmux_ioctrl_regs[POC5].reg; + return 0; + + case PIN_VDDQ_AVB1: + *pocctrl = pinmux_ioctrl_regs[POC6].reg; + return 0; + + case PIN_VDDQ_AVB0: + *pocctrl = pinmux_ioctrl_regs[POC7].reg; + return 0; + + case RCAR_GP_PIN(8, 0) ... RCAR_GP_PIN(8, 13): + *pocctrl = pinmux_ioctrl_regs[POC8].reg; return bit; - return -EINVAL; + default: + return -EINVAL; + } } static const struct pinmux_bias_reg pinmux_bias_regs[] = { -- GitLab From 0256b6aeee11d705ae248c5a47aa0867976b00a5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 8 Mar 2023 11:44:27 +0100 Subject: [PATCH 1694/5631] pinctrl: renesas: Annotate sentinels in tables It does not make sense to have a comma after a sentinel, as any new elements must be added before the sentinel. Hence drop all such commas. Add comments to clarify the purpose of the empty elements. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/845f1d8285dd44522af1b0f429d4c6bd4759eb9e.1678272180.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/core.c | 4 ++-- drivers/pinctrl/renesas/pfc-emev2.c | 2 +- drivers/pinctrl/renesas/pfc-r8a73a4.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a7740.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a77470.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7778.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a7779.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7790.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7791.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a7792.c | 2 +- drivers/pinctrl/renesas/pfc-r8a7794.c | 2 +- drivers/pinctrl/renesas/pfc-r8a77951.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a7796.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a77965.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a77970.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a77980.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a77990.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a77995.c | 4 ++-- drivers/pinctrl/renesas/pfc-r8a779a0.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a779f0.c | 8 ++++---- drivers/pinctrl/renesas/pfc-r8a779g0.c | 8 ++++---- drivers/pinctrl/renesas/pfc-sh7203.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7264.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7269.c | 6 ++---- drivers/pinctrl/renesas/pfc-sh73a0.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7720.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7722.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7723.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7724.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7734.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7757.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7785.c | 4 ++-- drivers/pinctrl/renesas/pfc-sh7786.c | 4 ++-- drivers/pinctrl/renesas/pfc-shx3.c | 4 ++-- drivers/pinctrl/renesas/pinctrl-rza1.c | 2 +- drivers/pinctrl/renesas/pinctrl-rzn1.c | 2 +- 36 files changed, 78 insertions(+), 80 deletions(-) diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index 336cfae756b0..17f70be2b2b9 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -645,7 +645,7 @@ static const struct of_device_id sh_pfc_of_table[] = { .data = &sh73a0_pinmux_info, }, #endif - { }, + { /* sentinel */ } }; #endif @@ -1411,7 +1411,7 @@ static const struct platform_device_id sh_pfc_id_table[] = { #ifdef CONFIG_PINCTRL_PFC_SHX3 { "pfc-shx3", (kernel_ulong_t)&shx3_pinmux_info }, #endif - { }, + { /* sentinel */ } }; static struct platform_driver sh_pfc_driver = { diff --git a/drivers/pinctrl/renesas/pfc-emev2.c b/drivers/pinctrl/renesas/pfc-emev2.c index 1d8b540110f2..86d18b03668e 100644 --- a/drivers/pinctrl/renesas/pfc-emev2.c +++ b/drivers/pinctrl/renesas/pfc-emev2.c @@ -1644,7 +1644,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { FN_SEL_HSI_1_0_00, FN_SEL_HSI_1_0_01, 0, 0, )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info emev2_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-r8a73a4.c b/drivers/pinctrl/renesas/pfc-r8a73a4.c index dbfc46fe2f27..be0a4914eab3 100644 --- a/drivers/pinctrl/renesas/pfc-r8a73a4.c +++ b/drivers/pinctrl/renesas/pfc-r8a73a4.c @@ -2384,7 +2384,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MSEL8CR_00_0, MSEL8CR_00_1, )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2510,7 +2510,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PORT323_DATA, PORT322_DATA, PORT321_DATA, PORT320_DATA, )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_irq pinmux_irqs[] = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7740.c b/drivers/pinctrl/renesas/pfc-r8a7740.c index 6dcd39918daf..9ee3b700a3d3 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7740.c +++ b/drivers/pinctrl/renesas/pfc-r8a7740.c @@ -3348,7 +3348,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MSEL5CR_0_0, MSEL5CR_0_1, )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -3452,7 +3452,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { 0, 0, 0, 0, 0, 0, 0, 0 )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_irq pinmux_irqs[] = { diff --git a/drivers/pinctrl/renesas/pfc-r8a77470.c b/drivers/pinctrl/renesas/pfc-r8a77470.c index 4ba710610255..ed48b043763f 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77470.c +++ b/drivers/pinctrl/renesas/pfc-r8a77470.c @@ -3252,7 +3252,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* SEL_SSI0 [2] */ FN_SEL_SSI0_0, FN_SEL_SSI0_1, 0, 0, )) }, - { }, + { /* sentinel */ } }; static int r8a77470_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) diff --git a/drivers/pinctrl/renesas/pfc-r8a7778.c b/drivers/pinctrl/renesas/pfc-r8a7778.c index 35bdb9af8160..c52761d80f7b 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7778.c +++ b/drivers/pinctrl/renesas/pfc-r8a7778.c @@ -2832,7 +2832,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { FN_SEL_I2C1_A, FN_SEL_I2C1_B, )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_bias_reg pinmux_bias_regs[] = { @@ -3040,7 +3040,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a7778_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7779.c b/drivers/pinctrl/renesas/pfc-r8a7779.c index fcc8ea48881f..0a94ef64f954 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7779.c +++ b/drivers/pinctrl/renesas/pfc-r8a7779.c @@ -3919,7 +3919,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* SEL_I2C1 [2] */ FN_SEL_I2C1_0, FN_SEL_I2C1_1, FN_SEL_I2C1_2, FN_SEL_I2C1_3 )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info r8a7779_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7790.c b/drivers/pinctrl/renesas/pfc-r8a7790.c index 149700ee1d10..791e089d47db 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7790.c +++ b/drivers/pinctrl/renesas/pfc-r8a7790.c @@ -5824,7 +5824,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* SEL_I2C1 [2] */ FN_SEL_I2C1_0, FN_SEL_I2C1_1, FN_SEL_I2C1_2, 0, )) }, - { }, + { /* sentinel */ } }; static int r8a7790_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) diff --git a/drivers/pinctrl/renesas/pfc-r8a7791.c b/drivers/pinctrl/renesas/pfc-r8a7791.c index c83e21c4c395..d9e5ce0dfb5b 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7791.c +++ b/drivers/pinctrl/renesas/pfc-r8a7791.c @@ -6552,7 +6552,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { FN_SEL_SSP_0, FN_SEL_SSP_1, FN_SEL_SSP_2, 0, /* RESERVED [6] */ )) }, - { }, + { /* sentinel */ } }; static int r8a7791_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -6874,7 +6874,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a7791_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7792.c b/drivers/pinctrl/renesas/pfc-r8a7792.c index 808a85d62415..2c51c32b8e09 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7792.c +++ b/drivers/pinctrl/renesas/pfc-r8a7792.c @@ -2625,7 +2625,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* IP7_1_0 [2] */ FN_PWM0, FN_TCLK1, FN_FSO_CFE_0, 0 )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_bias_reg pinmux_bias_regs[] = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7794.c b/drivers/pinctrl/renesas/pfc-r8a7794.c index 6e801ae90d25..e800fef91ddb 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7794.c +++ b/drivers/pinctrl/renesas/pfc-r8a7794.c @@ -5512,7 +5512,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { FN_SEL_SSI9_0, FN_SEL_SSI9_1, /* RESERVED [12] */ )) }, - { }, + { /* sentinel */ } }; static int r8a7794_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) diff --git a/drivers/pinctrl/renesas/pfc-r8a77951.c b/drivers/pinctrl/renesas/pfc-r8a77951.c index 321014c8bc16..a1d74f61fd8c 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77951.c +++ b/drivers/pinctrl/renesas/pfc-r8a77951.c @@ -5610,7 +5610,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* RESERVED 16-1 */ MOD_SEL2_0 )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -5861,7 +5861,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(6, 30), 8, 3 }, /* GP6_30/USB2_CH3_PWEN */ { RCAR_GP_PIN(6, 31), 4, 3 }, /* GP6_31/USB2_CH3_OVC */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -5872,7 +5872,7 @@ enum ioctrl_regs { static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL] = { 0xe6060380, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a77951_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -6129,7 +6129,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a77951_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a7796.c b/drivers/pinctrl/renesas/pfc-r8a7796.c index 5db8429c54fe..807834f319f0 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7796.c +++ b/drivers/pinctrl/renesas/pfc-r8a7796.c @@ -5565,7 +5565,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* RESERVED 16-1 */ MOD_SEL2_0 )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -5813,7 +5813,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(6, 30), 8, 3 }, /* GP6_30 */ { RCAR_GP_PIN(6, 31), 4, 3 }, /* GP6_31 */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -5824,7 +5824,7 @@ enum ioctrl_regs { static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL] = { 0xe6060380, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a7796_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -6081,7 +6081,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a7796_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a77965.c b/drivers/pinctrl/renesas/pfc-r8a77965.c index 2b8b49b18b10..e7c88a5d983f 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77965.c +++ b/drivers/pinctrl/renesas/pfc-r8a77965.c @@ -5806,7 +5806,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* RESERVED 16-1 */ MOD_SEL2_0 )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -6054,7 +6054,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(6, 30), 8, 3 }, /* GP6_30 */ { RCAR_GP_PIN(6, 31), 4, 3 }, /* GP6_31 */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -6065,7 +6065,7 @@ enum ioctrl_regs { static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL] = { 0xe6060380, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a77965_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -6322,7 +6322,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a77965_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a77970.c b/drivers/pinctrl/renesas/pfc-r8a77970.c index 54da0c025458..5b66d7b1af95 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77970.c +++ b/drivers/pinctrl/renesas/pfc-r8a77970.c @@ -2343,7 +2343,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL0_1 MOD_SEL0_0 )) }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -2358,7 +2358,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL1] = { 0xe6060384 }, [POCCTRL2] = { 0xe6060388 }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a77970_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) diff --git a/drivers/pinctrl/renesas/pfc-r8a77980.c b/drivers/pinctrl/renesas/pfc-r8a77980.c index 8effbcec0b22..384faa0d6937 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77980.c +++ b/drivers/pinctrl/renesas/pfc-r8a77980.c @@ -2815,7 +2815,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL0_1 MOD_SEL0_0 )) }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -2832,7 +2832,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL2] = { 0xe6060388, }, [POCCTRL3] = { 0xe606038c, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a77980_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) diff --git a/drivers/pinctrl/renesas/pfc-r8a77990.c b/drivers/pinctrl/renesas/pfc-r8a77990.c index 229ad12bc9b7..262390dd7d67 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77990.c +++ b/drivers/pinctrl/renesas/pfc-r8a77990.c @@ -5004,7 +5004,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL1_4 /* RESERVED 3, 2, 1, 0 */ )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -5037,7 +5037,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(4, 9), 17, 2 }, /* SD3_DAT7 */ { RCAR_GP_PIN(4, 10), 14, 2 }, /* SD3_DS */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -5050,7 +5050,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL0] = { 0xe6060380, }, [POCCTRL2] = { 0xe6060388, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a77990_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -5278,7 +5278,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = RCAR_GP_PIN(6, 9), /* USB30_OVC */ [31] = RCAR_GP_PIN(6, 17), /* USB30_PWEN */ } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a77990_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a77995.c b/drivers/pinctrl/renesas/pfc-r8a77995.c index 29664d97e5ec..298e7a07e493 100644 --- a/drivers/pinctrl/renesas/pfc-r8a77995.c +++ b/drivers/pinctrl/renesas/pfc-r8a77995.c @@ -2853,7 +2853,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL1_26 /* RESERVED 25-0 */ )) }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -2866,7 +2866,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POCCTRL0] = { 0xe6060380, }, [POCCTRL2] = { 0xe6060388, }, [TDSELCTRL] = { 0xe60603c0, }, - { /* sentinel */ }, + { /* sentinel */ } }; diff --git a/drivers/pinctrl/renesas/pfc-r8a779a0.c b/drivers/pinctrl/renesas/pfc-r8a779a0.c index 6069869353bb..a01bc197d706 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779a0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779a0.c @@ -3630,7 +3630,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL2_3_2 /* RESERVED 1-0 */ )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -3935,7 +3935,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(9, 17), 4, 3 }, /* AVB5_LINK */ { RCAR_GP_PIN(9, 16), 0, 3 }, /* AVB5_PHY_INT */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -3962,7 +3962,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POC8] = { 0xe60690a0, }, [POC9] = { 0xe60698a0, }, [TD1SEL0] = { 0xe6058124, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a779a0_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -4349,7 +4349,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a779a0_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a779f0.c b/drivers/pinctrl/renesas/pfc-r8a779f0.c index 65c141ce909a..16e722a4d18f 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779f0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779f0.c @@ -1784,7 +1784,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL1_3_2 MOD_SEL1_1_0)) }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -1896,7 +1896,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(3, 17), 4, 3 }, /* TSN0_AVTP_MATCH_B */ { RCAR_GP_PIN(3, 16), 0, 3 }, /* TSN0_AVTP_PPS */ } }, - { /* sentinel */ }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -1911,7 +1911,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POC1] = { 0xe60508a0, }, [POC3] = { 0xe60518a0, }, [TD0SEL1] = { 0xe6050920, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a779f0_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -2070,7 +2070,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a779f0_pfc_ops = { diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c index 585ea6ada99a..acdea6ac1525 100644 --- a/drivers/pinctrl/renesas/pfc-r8a779g0.c +++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c @@ -3689,7 +3689,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MOD_SEL8_1 MOD_SEL8_0)) }, - { }, + { /* sentinel */ } }; static const struct pinmux_drive_reg pinmux_drive_regs[] = { @@ -3951,7 +3951,7 @@ static const struct pinmux_drive_reg pinmux_drive_regs[] = { { RCAR_GP_PIN(8, 9), 4, 3 }, /* SDA4 */ { RCAR_GP_PIN(8, 8), 0, 3 }, /* SCL4 */ } }, - { }, + { /* sentinel */ } }; enum ioctrl_regs { @@ -3974,7 +3974,7 @@ static const struct pinmux_ioctrl_reg pinmux_ioctrl_regs[] = { [POC6] = { 0xE60610A0, }, [POC7] = { 0xE60618A0, }, [POC8] = { 0xE60680A0, }, - { /* sentinel */ }, + { /* sentinel */ } }; static int r8a779g0_pin_to_pocctrl(unsigned int pin, u32 *pocctrl) @@ -4326,7 +4326,7 @@ static const struct pinmux_bias_reg pinmux_bias_regs[] = { [30] = SH_PFC_PIN_NONE, [31] = SH_PFC_PIN_NONE, } }, - { /* sentinel */ }, + { /* sentinel */ } }; static const struct sh_pfc_soc_operations r8a779g0_pin_ops = { diff --git a/drivers/pinctrl/renesas/pfc-sh7203.c b/drivers/pinctrl/renesas/pfc-sh7203.c index 19735746b1bb..640564db2c0b 100644 --- a/drivers/pinctrl/renesas/pfc-sh7203.c +++ b/drivers/pinctrl/renesas/pfc-sh7203.c @@ -1509,7 +1509,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PF0MD_00, PF0MD_01, PF0MD_10, PF0MD_11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -1555,7 +1555,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PF7_DATA, PF6_DATA, PF5_DATA, PF4_DATA, PF3_DATA, PF2_DATA, PF1_DATA, PF0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7203_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7264.c b/drivers/pinctrl/renesas/pfc-sh7264.c index 30096925a70c..8417c4243dda 100644 --- a/drivers/pinctrl/renesas/pfc-sh7264.c +++ b/drivers/pinctrl/renesas/pfc-sh7264.c @@ -2031,7 +2031,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PK1_IN, PK1_OUT, PK0_IN, PK0_OUT )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2109,7 +2109,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PK7_DATA, PK6_DATA, PK5_DATA, PK4_DATA, PK3_DATA, PK2_DATA, PK1_DATA, PK0_DATA )) }, - { } + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7264_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7269.c b/drivers/pinctrl/renesas/pfc-sh7269.c index f59f558d75ae..3569093f17ae 100644 --- a/drivers/pinctrl/renesas/pfc-sh7269.c +++ b/drivers/pinctrl/renesas/pfc-sh7269.c @@ -2749,8 +2749,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PJ1_IN, PJ1_OUT, PJ0_IN, PJ0_OUT )) }, - - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2828,8 +2827,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PJ7_DATA, PJ6_DATA, PJ5_DATA, PJ4_DATA, PJ3_DATA, PJ2_DATA, PJ1_DATA, PJ0_DATA )) }, - - { } + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7269_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh73a0.c b/drivers/pinctrl/renesas/pfc-sh73a0.c index 4f54dfd5a967..ca5adf2095be 100644 --- a/drivers/pinctrl/renesas/pfc-sh73a0.c +++ b/drivers/pinctrl/renesas/pfc-sh73a0.c @@ -3876,7 +3876,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { /* RESERVED [1] */ )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -3980,7 +3980,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PORT295_DATA, PORT294_DATA, PORT293_DATA, PORT292_DATA, PORT291_DATA, PORT290_DATA, PORT289_DATA, PORT288_DATA )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_irq pinmux_irqs[] = { diff --git a/drivers/pinctrl/renesas/pfc-sh7720.c b/drivers/pinctrl/renesas/pfc-sh7720.c index 6eedcc5bbb4d..91434743fb1c 100644 --- a/drivers/pinctrl/renesas/pfc-sh7720.c +++ b/drivers/pinctrl/renesas/pfc-sh7720.c @@ -1103,7 +1103,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PTV1_FN, PTV1_OUT, 0, PTV1_IN, PTV0_FN, PTV0_OUT, 0, PTV0_IN )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -1179,7 +1179,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { 0, 0, 0, PTV4_DATA, PTV3_DATA, PTV2_DATA, PTV1_DATA, PTV0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7720_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7722.c b/drivers/pinctrl/renesas/pfc-sh7722.c index 4b82ac2c5e91..54b4625b52cf 100644 --- a/drivers/pinctrl/renesas/pfc-sh7722.c +++ b/drivers/pinctrl/renesas/pfc-sh7722.c @@ -1585,7 +1585,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { MSELB8_RGB, MSELB8_SYS, /* RESERVED [8] */ )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -1681,7 +1681,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { 0, 0, PTZ5_DATA, PTZ4_DATA, PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7722_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7723.c b/drivers/pinctrl/renesas/pfc-sh7723.c index 95344281966e..c1abdec9bf1d 100644 --- a/drivers/pinctrl/renesas/pfc-sh7723.c +++ b/drivers/pinctrl/renesas/pfc-sh7723.c @@ -1784,7 +1784,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PSD3_PSD2_FN1, PSD3_PSD2_FN2, 0, 0, PSD1_PSD0_FN1, PSD1_PSD0_FN2, 0, 0 )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -1880,7 +1880,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PTZ7_DATA, PTZ6_DATA, PTZ5_DATA, PTZ4_DATA, PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7723_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7724.c b/drivers/pinctrl/renesas/pfc-sh7724.c index 26517ad26a0f..5148a3460cc6 100644 --- a/drivers/pinctrl/renesas/pfc-sh7724.c +++ b/drivers/pinctrl/renesas/pfc-sh7724.c @@ -2059,7 +2059,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PSE1_0, PSE1_1, PSE0_0, PSE0_1)) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2155,7 +2155,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PTZ7_DATA, PTZ6_DATA, PTZ5_DATA, PTZ4_DATA, PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7724_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7734.c b/drivers/pinctrl/renesas/pfc-sh7734.c index 106a500ad13d..a0a5d8b94086 100644 --- a/drivers/pinctrl/renesas/pfc-sh7734.c +++ b/drivers/pinctrl/renesas/pfc-sh7734.c @@ -2366,7 +2366,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { GP_5_1_IN, GP_5_1_OUT, GP_5_0_IN, GP_5_0_OUT )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2383,7 +2383,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { GP_5_7_DATA, GP_5_6_DATA, GP_5_5_DATA, GP_5_4_DATA, GP_5_3_DATA, GP_5_2_DATA, GP_5_1_DATA, GP_5_0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7734_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7757.c b/drivers/pinctrl/renesas/pfc-sh7757.c index 0d7857d7efef..817b22c3e639 100644 --- a/drivers/pinctrl/renesas/pfc-sh7757.c +++ b/drivers/pinctrl/renesas/pfc-sh7757.c @@ -2089,7 +2089,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PS8_8_FN1, PS8_8_FN2, /* RESERVED [8] */ )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -2197,7 +2197,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PTZ7_DATA, PTZ6_DATA, PTZ5_DATA, PTZ4_DATA, PTZ3_DATA, PTZ2_DATA, PTZ1_DATA, PTZ0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7757_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7785.c b/drivers/pinctrl/renesas/pfc-sh7785.c index 126b663bb6eb..0b6fbbac7c6d 100644 --- a/drivers/pinctrl/renesas/pfc-sh7785.c +++ b/drivers/pinctrl/renesas/pfc-sh7785.c @@ -1168,7 +1168,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { P2MSEL1_0, P2MSEL1_1, P2MSEL0_0, P2MSEL0_1 )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -1236,7 +1236,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { 0, 0, 0, 0, PR3_DATA, PR2_DATA, PR1_DATA, PR0_DATA )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7785_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-sh7786.c b/drivers/pinctrl/renesas/pfc-sh7786.c index f09f4a769010..a1ff39c5424d 100644 --- a/drivers/pinctrl/renesas/pfc-sh7786.c +++ b/drivers/pinctrl/renesas/pfc-sh7786.c @@ -747,7 +747,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { P2MSEL1_0, P2MSEL1_1, P2MSEL0_0, P2MSEL0_1 )) }, - {} + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -787,7 +787,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { PJ7_DATA, PJ6_DATA, PJ5_DATA, PJ4_DATA, PJ3_DATA, PJ2_DATA, PJ1_DATA, 0 )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info sh7786_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pfc-shx3.c b/drivers/pinctrl/renesas/pfc-shx3.c index 96a65d83774f..e2ba5e3b9ec3 100644 --- a/drivers/pinctrl/renesas/pfc-shx3.c +++ b/drivers/pinctrl/renesas/pfc-shx3.c @@ -502,7 +502,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { PH1_FN, PH1_OUT, PH1_IN, 0, PH0_FN, PH0_OUT, PH0_IN, 0, )) }, - { }, + { /* sentinel */ } }; static const struct pinmux_data_reg pinmux_data_regs[] = { @@ -538,7 +538,7 @@ static const struct pinmux_data_reg pinmux_data_regs[] = { 0, 0, PH5_DATA, PH4_DATA, PH3_DATA, PH2_DATA, PH1_DATA, PH0_DATA, )) }, - { }, + { /* sentinel */ } }; const struct sh_pfc_soc_info shx3_pinmux_info = { diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c index 529c0fc4ec06..f0897b23a2ed 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza1.c +++ b/drivers/pinctrl/renesas/pinctrl-rza1.c @@ -1388,7 +1388,7 @@ static const struct of_device_id rza1_pinctrl_of_match[] = { .compatible = "renesas,r7s72102-ports", .data = &rza1l_pmx_conf, }, - { } + { /* sentinel */ } }; static struct platform_driver rza1_pinctrl_driver = { diff --git a/drivers/pinctrl/renesas/pinctrl-rzn1.c b/drivers/pinctrl/renesas/pinctrl-rzn1.c index 9158c1757492..8c4425fd7b06 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzn1.c +++ b/drivers/pinctrl/renesas/pinctrl-rzn1.c @@ -931,7 +931,7 @@ static int rzn1_pinctrl_remove(struct platform_device *pdev) static const struct of_device_id rzn1_pinctrl_match[] = { { .compatible = "renesas,rzn1-pinctrl", }, - {} + { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, rzn1_pinctrl_match); -- GitLab From 63a66eb8ff1d620333ce388d121eb101a353b014 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 20 Mar 2023 17:17:47 +0100 Subject: [PATCH 1695/5631] pinctrl: renesas: r8a7779: Add bias pinconf support Implement support for pull-up handling for the R-Car H1 SoC, using the common R-Car bias handling. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/dd966cfc916ef881051ec53bc3393dce7eea8e03.1679328215.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a7779.c | 335 +++++++++++++++++++++++++- 1 file changed, 328 insertions(+), 7 deletions(-) diff --git a/drivers/pinctrl/renesas/pfc-r8a7779.c b/drivers/pinctrl/renesas/pfc-r8a7779.c index 0a94ef64f954..26136d90d6ed 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7779.c +++ b/drivers/pinctrl/renesas/pfc-r8a7779.c @@ -12,13 +12,76 @@ #include "sh_pfc.h" #define CPU_ALL_GP(fn, sfx) \ - PORT_GP_32(0, fn, sfx), \ - PORT_GP_32(1, fn, sfx), \ - PORT_GP_32(2, fn, sfx), \ - PORT_GP_32(3, fn, sfx), \ - PORT_GP_32(4, fn, sfx), \ - PORT_GP_32(5, fn, sfx), \ - PORT_GP_9(6, fn, sfx) + PORT_GP_CFG_32(0, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_32(1, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(2, 0, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_1(2, 1, fn, sfx), \ + PORT_GP_1(2, 2, fn, sfx), \ + PORT_GP_1(2, 3, fn, sfx), \ + PORT_GP_1(2, 4, fn, sfx), \ + PORT_GP_1(2, 5, fn, sfx), \ + PORT_GP_1(2, 6, fn, sfx), \ + PORT_GP_1(2, 7, fn, sfx), \ + PORT_GP_1(2, 8, fn, sfx), \ + PORT_GP_1(2, 9, fn, sfx), \ + PORT_GP_1(2, 10, fn, sfx), \ + PORT_GP_1(2, 11, fn, sfx), \ + PORT_GP_1(2, 12, fn, sfx), \ + PORT_GP_1(2, 13, fn, sfx), \ + PORT_GP_1(2, 14, fn, sfx), \ + PORT_GP_1(2, 15, fn, sfx), \ + PORT_GP_1(2, 16, fn, sfx), \ + PORT_GP_1(2, 17, fn, sfx), \ + PORT_GP_1(2, 18, fn, sfx), \ + PORT_GP_1(2, 19, fn, sfx), \ + PORT_GP_1(2, 20, fn, sfx), \ + PORT_GP_1(2, 21, fn, sfx), \ + PORT_GP_1(2, 22, fn, sfx), \ + PORT_GP_1(2, 23, fn, sfx), \ + PORT_GP_1(2, 24, fn, sfx), \ + PORT_GP_1(2, 25, fn, sfx), \ + PORT_GP_1(2, 26, fn, sfx), \ + PORT_GP_1(2, 27, fn, sfx), \ + PORT_GP_1(2, 28, fn, sfx), \ + PORT_GP_1(2, 29, fn, sfx), \ + PORT_GP_CFG_1(2, 30, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(2, 31, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_25(3, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_1(3, 25, fn, sfx), \ + PORT_GP_1(3, 26, fn, sfx), \ + PORT_GP_1(3, 27, fn, sfx), \ + PORT_GP_CFG_1(3, 28, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(3, 29, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(3, 30, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_1(3, 31, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_32(4, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_32(5, fn, sfx, SH_PFC_PIN_CFG_PULL_UP), \ + PORT_GP_CFG_9(6, fn, sfx, SH_PFC_PIN_CFG_PULL_UP) + +#define CPU_ALL_NOGP(fn) \ + PIN_NOGP_CFG(ASEBRK_N_ACK, "ASEBRK#/ACK", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D0, "D0", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D1, "D1", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D2, "D2", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D3, "D3", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D4, "D4", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D5, "D5", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D6, "D6", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D7, "D7", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D8, "D8", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D9, "D9", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D10, "D10", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D11, "D11", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D12, "D12", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D13, "D13", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D14, "D14", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(D15, "D15", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(PRESETOUT_N, "PRESETOUT#", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(TCK, "TCK", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(TDI, "TDI", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(TDO, "TDO", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(TMS, "TMS", fn, SH_PFC_PIN_CFG_PULL_UP), \ + PIN_NOGP_CFG(TRST_N, "TRST#", fn, SH_PFC_PIN_CFG_PULL_UP) enum { PINMUX_RESERVED = 0, @@ -1390,8 +1453,17 @@ static const u16 pinmux_data[] = { PINMUX_IPSR_MSEL(IP12_17_15, SCK4_B, SEL_SCIF4_1), }; +/* + * Pins not associated with a GPIO port. + */ +enum { + GP_ASSIGN_LAST(), + NOGP_ALL(), +}; + static const struct sh_pfc_pin pinmux_pins[] = { PINMUX_GPIO_GP_ALL(), + PINMUX_NOGP_ALL(), }; /* - DU0 -------------------------------------------------------------------- */ @@ -3922,8 +3994,256 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = { { /* sentinel */ } }; +static const struct pinmux_bias_reg pinmux_bias_regs[] = { + { PINMUX_BIAS_REG("PUPR0", 0xfffc0100, "N/A", 0) { + [ 0] = RCAR_GP_PIN(0, 2), /* A0 */ + [ 1] = RCAR_GP_PIN(5, 0), /* A1 */ + [ 2] = RCAR_GP_PIN(5, 1), /* A2 */ + [ 3] = RCAR_GP_PIN(5, 2), /* A3 */ + [ 4] = RCAR_GP_PIN(5, 3), /* A4 */ + [ 5] = RCAR_GP_PIN(5, 4), /* A5 */ + [ 6] = RCAR_GP_PIN(5, 5), /* A6 */ + [ 7] = RCAR_GP_PIN(5, 6), /* A7 */ + [ 8] = RCAR_GP_PIN(5, 7), /* A8 */ + [ 9] = RCAR_GP_PIN(5, 8), /* A9 */ + [10] = RCAR_GP_PIN(5, 9), /* A10 */ + [11] = RCAR_GP_PIN(5, 10), /* A11 */ + [12] = RCAR_GP_PIN(5, 11), /* A12 */ + [13] = RCAR_GP_PIN(5, 12), /* A13 */ + [14] = RCAR_GP_PIN(5, 13), /* A14 */ + [15] = RCAR_GP_PIN(5, 14), /* A15 */ + [16] = RCAR_GP_PIN(5, 15), /* A16 */ + [17] = RCAR_GP_PIN(0, 3), /* A17 */ + [18] = RCAR_GP_PIN(0, 4), /* A18 */ + [19] = RCAR_GP_PIN(0, 5), /* A19 */ + [20] = RCAR_GP_PIN(0, 6), /* A20 */ + [21] = RCAR_GP_PIN(0, 7), /* A21 */ + [22] = RCAR_GP_PIN(0, 8), /* A22 */ + [23] = RCAR_GP_PIN(0, 9), /* A23 */ + [24] = RCAR_GP_PIN(0, 10), /* A24 */ + [25] = RCAR_GP_PIN(0, 11), /* A25 */ + [26] = RCAR_GP_PIN(0, 15), /* EX_CS0# */ + [27] = RCAR_GP_PIN(0, 16), /* EX_CS1# */ + [28] = RCAR_GP_PIN(0, 17), /* EX_CS2# */ + [29] = RCAR_GP_PIN(0, 18), /* EX_CS3# */ + [30] = RCAR_GP_PIN(0, 19), /* EX_CS4# */ + [31] = RCAR_GP_PIN(0, 20), /* EX_CS5# */ + } }, + { PINMUX_BIAS_REG("PUPR1", 0xfffc0104, "N/A", 0) { + [ 0] = PIN_PRESETOUT_N, /* PRESETOUT# */ + [ 1] = RCAR_GP_PIN(0, 21), /* BS# */ + [ 2] = RCAR_GP_PIN(0, 22), /* RD/WR# */ + [ 3] = RCAR_GP_PIN(5, 17), /* WE0# */ + [ 4] = RCAR_GP_PIN(5, 18), /* WE1# */ + [ 5] = RCAR_GP_PIN(5, 19), /* EX_WAIT0 */ + [ 6] = RCAR_GP_PIN(0, 0), /* AVS1 */ + [ 7] = RCAR_GP_PIN(0, 1), /* AVS2 */ + [ 8] = SH_PFC_PIN_NONE, + [ 9] = SH_PFC_PIN_NONE, + [10] = PIN_TRST_N, /* TRST# */ + [11] = PIN_TCK, /* TCK */ + [12] = PIN_TMS, /* TMS */ + [13] = PIN_TDI, /* TDI */ + [14] = PIN_TDO, /* TDO */ + [15] = PIN_ASEBRK_N_ACK, /* ASEBRK#/ACK */ + [16] = PIN_D0, /* D0 */ + [17] = PIN_D1, /* D1 */ + [18] = PIN_D2, /* D2 */ + [19] = PIN_D3, /* D3 */ + [20] = PIN_D4, /* D4 */ + [21] = PIN_D5, /* D5 */ + [22] = PIN_D6, /* D6 */ + [23] = PIN_D7, /* D7 */ + [24] = PIN_D8, /* D8 */ + [25] = PIN_D9, /* D9 */ + [26] = PIN_D10, /* D10 */ + [27] = PIN_D11, /* D11 */ + [28] = PIN_D12, /* D12 */ + [29] = PIN_D13, /* D13 */ + [30] = PIN_D14, /* D14 */ + [31] = PIN_D15, /* D15 */ + } }, + { PINMUX_BIAS_REG("PUPR2", 0xfffc0108, "N/A", 0) { + [ 0] = RCAR_GP_PIN(0, 23), /* DU0_DR0 */ + [ 1] = RCAR_GP_PIN(0, 24), /* DU0_DR1 */ + [ 2] = RCAR_GP_PIN(5, 23), /* DU0_DR2 */ + [ 3] = RCAR_GP_PIN(5, 24), /* DU0_DR3 */ + [ 4] = RCAR_GP_PIN(5, 25), /* DU0_DR4 */ + [ 5] = RCAR_GP_PIN(5, 26), /* DU0_DR5 */ + [ 6] = RCAR_GP_PIN(5, 27), /* DU0_DR6 */ + [ 7] = RCAR_GP_PIN(5, 28), /* DU0_DR7 */ + [ 8] = RCAR_GP_PIN(0, 25), /* DU0_DG0 */ + [ 9] = RCAR_GP_PIN(0, 26), /* DU0_DG1 */ + [10] = RCAR_GP_PIN(5, 29), /* DU0_DG2 */ + [11] = RCAR_GP_PIN(5, 30), /* DU0_DG3 */ + [12] = RCAR_GP_PIN(5, 31), /* DU0_DG4 */ + [13] = RCAR_GP_PIN(6, 0), /* DU0_DG5 */ + [14] = RCAR_GP_PIN(6, 1), /* DU0_DG6 */ + [15] = RCAR_GP_PIN(6, 2), /* DU0_DG7 */ + [16] = RCAR_GP_PIN(0, 27), /* DU0_DB0 */ + [17] = RCAR_GP_PIN(0, 28), /* DU0_DB1 */ + [18] = RCAR_GP_PIN(6, 3), /* DU0_DB2 */ + [19] = RCAR_GP_PIN(6, 4), /* DU0_DB3 */ + [20] = RCAR_GP_PIN(6, 5), /* DU0_DB4 */ + [21] = RCAR_GP_PIN(6, 6), /* DU0_DB5 */ + [22] = RCAR_GP_PIN(6, 7), /* DU0_DB6 */ + [23] = RCAR_GP_PIN(6, 8), /* DU0_DB7 */ + [24] = RCAR_GP_PIN(0, 29), /* DU0_DOTCLKIN */ + [25] = RCAR_GP_PIN(5, 20), /* DU0_DOTCLKOUT0 */ + [26] = RCAR_GP_PIN(5, 21), /* DU0_HSYNC */ + [27] = RCAR_GP_PIN(5, 22), /* DU0_VSYNC */ + [28] = RCAR_GP_PIN(0, 31), /* DU0_EXODDF */ + [29] = RCAR_GP_PIN(1, 0), /* DU0_DISP */ + [30] = RCAR_GP_PIN(1, 1), /* DU0_CDE */ + [31] = RCAR_GP_PIN(0, 30), /* DU0_DOTCLKOUT1 */ + } }, + { PINMUX_BIAS_REG("PUPR3", 0xfffc010c, "N/A", 0) { + [ 0] = RCAR_GP_PIN(1, 2), /* DU1_DR0 */ + [ 1] = RCAR_GP_PIN(1, 3), /* DU1_DR1 */ + [ 2] = RCAR_GP_PIN(1, 4), /* DU1_DR2 */ + [ 3] = RCAR_GP_PIN(1, 5), /* DU1_DR3 */ + [ 4] = RCAR_GP_PIN(1, 6), /* DU1_DR4 */ + [ 5] = RCAR_GP_PIN(1, 7), /* DU1_DR5 */ + [ 6] = RCAR_GP_PIN(1, 8), /* DU1_DR6 */ + [ 7] = RCAR_GP_PIN(1, 9), /* DU1_DR7 */ + [ 8] = RCAR_GP_PIN(1, 10), /* DU1_DG0 */ + [ 9] = RCAR_GP_PIN(1, 11), /* DU1_DG1 */ + [10] = RCAR_GP_PIN(1, 12), /* DU1_DG2 */ + [11] = RCAR_GP_PIN(1, 13), /* DU1_DG3 */ + [12] = RCAR_GP_PIN(1, 14), /* DU1_DG4 */ + [13] = RCAR_GP_PIN(1, 15), /* DU1_DG5 */ + [14] = RCAR_GP_PIN(1, 16), /* DU1_DG6 */ + [15] = RCAR_GP_PIN(1, 17), /* DU1_DG7 */ + [16] = RCAR_GP_PIN(1, 18), /* DU1_DB0 */ + [17] = RCAR_GP_PIN(1, 19), /* DU1_DB1 */ + [18] = RCAR_GP_PIN(1, 20), /* DU1_DB2 */ + [19] = RCAR_GP_PIN(1, 21), /* DU1_DB3 */ + [20] = RCAR_GP_PIN(1, 22), /* DU1_DB4 */ + [21] = RCAR_GP_PIN(1, 23), /* DU1_DB5 */ + [22] = RCAR_GP_PIN(1, 24), /* DU1_DB6 */ + [23] = RCAR_GP_PIN(1, 25), /* DU1_DB7 */ + [24] = RCAR_GP_PIN(1, 26), /* DU1_DOTCLKIN */ + [25] = RCAR_GP_PIN(1, 27), /* DU1_DOTCLKOUT */ + [26] = RCAR_GP_PIN(1, 28), /* DU1_HSYNC */ + [27] = RCAR_GP_PIN(1, 29), /* DU1_VSYNC */ + [28] = RCAR_GP_PIN(1, 30), /* DU1_EXODDF */ + [29] = RCAR_GP_PIN(1, 31), /* DU1_DISP */ + [30] = RCAR_GP_PIN(2, 0), /* DU1_CDE */ + [31] = SH_PFC_PIN_NONE, + } }, + { PINMUX_BIAS_REG("PUPR4", 0xfffc0110, "N/A", 0) { + [ 0] = RCAR_GP_PIN(2, 30), /* VI1_CLK */ + [ 1] = SH_PFC_PIN_NONE, + [ 2] = SH_PFC_PIN_NONE, + [ 3] = RCAR_GP_PIN(2, 31), /* VI1_HSYNC# */ + [ 4] = RCAR_GP_PIN(3, 0), /* VI1_VSYNC# */ + [ 5] = RCAR_GP_PIN(3, 1), /* VI1_DATA0 */ + [ 6] = RCAR_GP_PIN(3, 2), /* VI1_DATA1 */ + [ 7] = RCAR_GP_PIN(3, 3), /* VI1_DATA2 */ + [ 8] = RCAR_GP_PIN(3, 4), /* VI1_DATA3 */ + [ 9] = RCAR_GP_PIN(3, 5), /* VI1_DATA4 */ + [10] = RCAR_GP_PIN(3, 6), /* VI1_DATA5 */ + [11] = RCAR_GP_PIN(3, 7), /* VI1_DATA6 */ + [12] = RCAR_GP_PIN(3, 8), /* VI1_DATA7 */ + [13] = RCAR_GP_PIN(3, 9), /* VI1_G0 */ + [14] = RCAR_GP_PIN(3, 10), /* VI1_G1 */ + [15] = RCAR_GP_PIN(3, 11), /* VI1_G2 */ + [16] = RCAR_GP_PIN(3, 12), /* VI1_G3 */ + [17] = RCAR_GP_PIN(3, 13), /* VI1_G4 */ + [18] = RCAR_GP_PIN(3, 14), /* VI1_G5 */ + [19] = RCAR_GP_PIN(3, 15), /* VI1_G6 */ + [20] = RCAR_GP_PIN(3, 16), /* VI1_G7 */ + [21] = SH_PFC_PIN_NONE, + [22] = SH_PFC_PIN_NONE, + [23] = SH_PFC_PIN_NONE, + [24] = SH_PFC_PIN_NONE, + [25] = SH_PFC_PIN_NONE, + [26] = SH_PFC_PIN_NONE, + [27] = SH_PFC_PIN_NONE, + [28] = SH_PFC_PIN_NONE, + [29] = SH_PFC_PIN_NONE, + [30] = SH_PFC_PIN_NONE, + [31] = SH_PFC_PIN_NONE, + } }, + { PINMUX_BIAS_REG("PUPR5", 0xfffc0114, "N/A", 0) { + [ 0] = RCAR_GP_PIN(3, 30), /* SSI_SCK0129 */ + [ 1] = RCAR_GP_PIN(3, 31), /* SSI_WS0129 */ + [ 2] = RCAR_GP_PIN(4, 0), /* SSI_SDATA0 */ + [ 3] = RCAR_GP_PIN(4, 1), /* SSI_SDATA1 */ + [ 4] = RCAR_GP_PIN(4, 2), /* SSI_SDATA2 */ + [ 5] = RCAR_GP_PIN(4, 3), /* SSI_SCK34 */ + [ 6] = RCAR_GP_PIN(4, 4), /* SSI_WS34 */ + [ 7] = RCAR_GP_PIN(4, 5), /* SSI_SDATA3 */ + [ 8] = RCAR_GP_PIN(4, 6), /* SSI_SDATA4 */ + [ 9] = RCAR_GP_PIN(4, 7), /* SSI_SCK5 */ + [10] = RCAR_GP_PIN(4, 8), /* SSI_WS5 */ + [11] = RCAR_GP_PIN(4, 9), /* SSI_SDATA5 */ + [12] = RCAR_GP_PIN(4, 10), /* SSI_SCK6 */ + [13] = RCAR_GP_PIN(4, 11), /* SSI_WS6 */ + [14] = RCAR_GP_PIN(4, 12), /* SSI_SDATA6 */ + [15] = RCAR_GP_PIN(4, 13), /* SSI_SCK78 */ + [16] = RCAR_GP_PIN(4, 14), /* SSI_WS78 */ + [17] = RCAR_GP_PIN(4, 15), /* SSI_SDATA7 */ + [18] = RCAR_GP_PIN(4, 16), /* SSI_SDATA8 */ + [19] = SH_PFC_PIN_NONE, + [20] = RCAR_GP_PIN(3, 17), /* SD0_CLK */ + [21] = RCAR_GP_PIN(3, 18), /* SD0_CMD */ + [22] = RCAR_GP_PIN(3, 21), /* SD0_DAT0 */ + [23] = RCAR_GP_PIN(3, 22), /* SD0_DAT1 */ + [24] = RCAR_GP_PIN(3, 23), /* SD0_DAT2 */ + [25] = RCAR_GP_PIN(3, 24), /* SD0_DAT3 */ + [26] = RCAR_GP_PIN(3, 19), /* SD0_CD */ + [27] = RCAR_GP_PIN(3, 20), /* SD0_WP */ + [28] = RCAR_GP_PIN(3, 28), /* AUDIO_CLKA */ + [29] = RCAR_GP_PIN(3, 29), /* AUDIO_CLKB */ + [30] = SH_PFC_PIN_NONE, + [31] = SH_PFC_PIN_NONE, + } }, + { PINMUX_BIAS_REG("PUPR6", 0xfffc0118, "N/A", 0) { + [ 0] = RCAR_GP_PIN(4, 26), /* PENC0 */ + [ 1] = RCAR_GP_PIN(4, 27), /* PENC1 */ + [ 2] = RCAR_GP_PIN(4, 28), /* PENC2 */ + [ 3] = SH_PFC_PIN_NONE, + [ 4] = SH_PFC_PIN_NONE, + [ 5] = RCAR_GP_PIN(4, 20), /* HTX0 */ + [ 6] = RCAR_GP_PIN(4, 21), /* HRX0 */ + [ 7] = RCAR_GP_PIN(4, 17), /* HSCK0 */ + [ 8] = RCAR_GP_PIN(4, 18), /* HCTS0# */ + [ 9] = RCAR_GP_PIN(4, 19), /* HRTS0# */ + [10] = RCAR_GP_PIN(4, 22), /* HSPI_CLK0 */ + [11] = RCAR_GP_PIN(4, 23), /* HSPI_CS0# */ + [12] = RCAR_GP_PIN(4, 24), /* HSPI_TX0 */ + [13] = RCAR_GP_PIN(4, 25), /* HSPI_RX0 */ + [14] = RCAR_GP_PIN(4, 29), /* FMCLK */ + [15] = RCAR_GP_PIN(4, 30), /* BPFCLK */ + [16] = RCAR_GP_PIN(4, 31), /* FMIN */ + [17] = RCAR_GP_PIN(0, 12), /* CLKOUT */ + [18] = RCAR_GP_PIN(0, 13), /* CS0# */ + [19] = RCAR_GP_PIN(0, 14), /* CS1#/A26 */ + [20] = RCAR_GP_PIN(5, 16), /* RD# */ + [21] = SH_PFC_PIN_NONE, + [22] = SH_PFC_PIN_NONE, + [23] = SH_PFC_PIN_NONE, + [24] = SH_PFC_PIN_NONE, + [25] = SH_PFC_PIN_NONE, + [26] = SH_PFC_PIN_NONE, + [27] = SH_PFC_PIN_NONE, + [28] = SH_PFC_PIN_NONE, + [29] = SH_PFC_PIN_NONE, + [30] = SH_PFC_PIN_NONE, + [31] = SH_PFC_PIN_NONE, + } }, + { /* sentinel */ } +}; + +static const struct sh_pfc_soc_operations r8a7779_pfc_ops = { + .get_bias = rcar_pinmux_get_bias, + .set_bias = rcar_pinmux_set_bias, +}; + const struct sh_pfc_soc_info r8a7779_pinmux_info = { .name = "r8a7779_pfc", + .ops = &r8a7779_pfc_ops, .unlock_reg = 0xfffc0000, /* PMMR */ @@ -3937,6 +4257,7 @@ const struct sh_pfc_soc_info r8a7779_pinmux_info = { .nr_functions = ARRAY_SIZE(pinmux_functions), .cfg_regs = pinmux_config_regs, + .bias_regs = pinmux_bias_regs, .pinmux_data = pinmux_data, .pinmux_data_size = ARRAY_SIZE(pinmux_data), -- GitLab From 890c3a6ff25fbbcedcd9c77fc97ac4d54d7a5a61 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 20 Mar 2023 17:18:58 +0100 Subject: [PATCH 1696/5631] pinctrl: renesas: r8a7779: Add PWM pins, groups, and functions Add pins, groups, and functions for the PWM Timers on the Renesas R-Car H1 (R8A7779) SoC. Signed-off-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/cea9723e9c3df4b1408750caa38886aac1fab5f7.1679329090.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/pfc-r8a7779.c | 109 ++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/drivers/pinctrl/renesas/pfc-r8a7779.c b/drivers/pinctrl/renesas/pfc-r8a7779.c index 26136d90d6ed..1172a359384d 100644 --- a/drivers/pinctrl/renesas/pfc-r8a7779.c +++ b/drivers/pinctrl/renesas/pfc-r8a7779.c @@ -2034,6 +2034,67 @@ static const unsigned int mmc1_ctrl_pins[] = { static const unsigned int mmc1_ctrl_mux[] = { MMC1_CMD_MARK, MMC1_CLK_MARK, }; +/* - PWM -------------------------------------------------------------------- */ +static const unsigned int pwm0_pins[] = { + RCAR_GP_PIN(1, 3), +}; +static const unsigned int pwm0_mux[] = { + PWM0_MARK, +}; +static const unsigned int pwm0_b_pins[] = { + RCAR_GP_PIN(0, 12), +}; +static const unsigned int pwm0_b_mux[] = { + PWM0_B_MARK, +}; +static const unsigned int pwm0_c_pins[] = { + RCAR_GP_PIN(4, 5), +}; +static const unsigned int pwm0_c_mux[] = { + PWM0_C_MARK, +}; +static const unsigned int pwm0_d_pins[] = { + RCAR_GP_PIN(4, 18), +}; +static const unsigned int pwm0_d_mux[] = { + PWM0_D_MARK, +}; +static const unsigned int pwm1_pins[] = { + RCAR_GP_PIN(4, 28), +}; +static const unsigned int pwm1_mux[] = { + PWM1_MARK, +}; +static const unsigned int pwm2_pins[] = { + RCAR_GP_PIN(3, 25), +}; +static const unsigned int pwm2_mux[] = { + PWM2_MARK, +}; +static const unsigned int pwm3_pins[] = { + RCAR_GP_PIN(3, 26), +}; +static const unsigned int pwm3_mux[] = { + PWM3_MARK, +}; +static const unsigned int pwm4_pins[] = { + RCAR_GP_PIN(3, 27), +}; +static const unsigned int pwm4_mux[] = { + PWM4_MARK, +}; +static const unsigned int pwm5_pins[] = { + RCAR_GP_PIN(4, 17), +}; +static const unsigned int pwm5_mux[] = { + PWM5_MARK, +}; +static const unsigned int pwm6_pins[] = { + RCAR_GP_PIN(1, 2), +}; +static const unsigned int pwm6_mux[] = { + PWM6_MARK, +}; /* - SCIF0 ------------------------------------------------------------------ */ static const unsigned int scif0_data_pins[] = { /* RXD, TXD */ @@ -2771,6 +2832,16 @@ static const struct sh_pfc_pin_group pinmux_groups[] = { BUS_DATA_PIN_GROUP(mmc1_data, 4), BUS_DATA_PIN_GROUP(mmc1_data, 8), SH_PFC_PIN_GROUP(mmc1_ctrl), + SH_PFC_PIN_GROUP(pwm0), + SH_PFC_PIN_GROUP(pwm0_b), + SH_PFC_PIN_GROUP(pwm0_c), + SH_PFC_PIN_GROUP(pwm0_d), + SH_PFC_PIN_GROUP(pwm1), + SH_PFC_PIN_GROUP(pwm2), + SH_PFC_PIN_GROUP(pwm3), + SH_PFC_PIN_GROUP(pwm4), + SH_PFC_PIN_GROUP(pwm5), + SH_PFC_PIN_GROUP(pwm6), SH_PFC_PIN_GROUP(scif0_data), SH_PFC_PIN_GROUP(scif0_clk), SH_PFC_PIN_GROUP(scif0_ctrl), @@ -2984,6 +3055,37 @@ static const char * const mmc1_groups[] = { "mmc1_ctrl", }; +static const char * const pwm0_groups[] = { + "pwm0", + "pwm0_b", + "pwm0_c", + "pwm0_d", +}; + +static const char * const pwm1_groups[] = { + "pwm1", +}; + +static const char * const pwm2_groups[] = { + "pwm2", +}; + +static const char * const pwm3_groups[] = { + "pwm3", +}; + +static const char * const pwm4_groups[] = { + "pwm4", +}; + +static const char * const pwm5_groups[] = { + "pwm5", +}; + +static const char * const pwm6_groups[] = { + "pwm6", +}; + static const char * const scif0_groups[] = { "scif0_data", "scif0_clk", @@ -3147,6 +3249,13 @@ static const struct sh_pfc_function pinmux_functions[] = { SH_PFC_FUNCTION(lbsc), SH_PFC_FUNCTION(mmc0), SH_PFC_FUNCTION(mmc1), + SH_PFC_FUNCTION(pwm0), + SH_PFC_FUNCTION(pwm1), + SH_PFC_FUNCTION(pwm2), + SH_PFC_FUNCTION(pwm3), + SH_PFC_FUNCTION(pwm4), + SH_PFC_FUNCTION(pwm5), + SH_PFC_FUNCTION(pwm6), SH_PFC_FUNCTION(scif0), SH_PFC_FUNCTION(scif1), SH_PFC_FUNCTION(scif2), -- GitLab From 45e6cc8ef1cd8576707506a4eeffef858e4a1a83 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 21 Mar 2023 17:28:00 +0100 Subject: [PATCH 1697/5631] pinctrl: renesas: core: Drop unneeded #ifdef CONFIG_OF As the of_node member of struct device always exists, and there is a dummy of of_device_get_match_data() for the !CONFIG_OF case, there is no longer a need to protect code using these interfaces with an #ifdef. Signed-off-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/55d72ce46b43ec2f41681cb5ba7ca7fcebdb98d1.1679416005.git.geert+renesas@glider.be --- drivers/pinctrl/renesas/core.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/pinctrl/renesas/core.c b/drivers/pinctrl/renesas/core.c index 17f70be2b2b9..0c8d081da6a8 100644 --- a/drivers/pinctrl/renesas/core.c +++ b/drivers/pinctrl/renesas/core.c @@ -1304,11 +1304,9 @@ static int sh_pfc_probe(struct platform_device *pdev) struct sh_pfc *pfc; int ret; -#ifdef CONFIG_OF if (pdev->dev.of_node) info = of_device_get_match_data(&pdev->dev); else -#endif info = (const void *)platform_get_device_id(pdev)->driver_data; pfc = devm_kzalloc(&pdev->dev, sizeof(*pfc), GFP_KERNEL); -- GitLab From 5fce94170ad8a67b839f3dd8e8e8a87039ba0251 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:16 +0100 Subject: [PATCH 1698/5631] pwm: atmel-hlcdc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Signed-off-by: Thierry Reding --- drivers/pwm/pwm-atmel-hlcdc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c index a43b2babc809..96a709a9d49a 100644 --- a/drivers/pwm/pwm-atmel-hlcdc.c +++ b/drivers/pwm/pwm-atmel-hlcdc.c @@ -278,15 +278,13 @@ static int atmel_hlcdc_pwm_probe(struct platform_device *pdev) return 0; } -static int atmel_hlcdc_pwm_remove(struct platform_device *pdev) +static void atmel_hlcdc_pwm_remove(struct platform_device *pdev) { struct atmel_hlcdc_pwm *chip = platform_get_drvdata(pdev); pwmchip_remove(&chip->chip); clk_disable_unprepare(chip->hlcdc->periph_clk); - - return 0; } static const struct of_device_id atmel_hlcdc_pwm_dt_ids[] = { @@ -301,7 +299,7 @@ static struct platform_driver atmel_hlcdc_pwm_driver = { .pm = &atmel_hlcdc_pwm_pm_ops, }, .probe = atmel_hlcdc_pwm_probe, - .remove = atmel_hlcdc_pwm_remove, + .remove_new = atmel_hlcdc_pwm_remove, }; module_platform_driver(atmel_hlcdc_pwm_driver); -- GitLab From 9609284a76978daf53a54e05cff36873a75e4d13 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:17 +0100 Subject: [PATCH 1699/5631] pwm: atmel-tcb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Signed-off-by: Thierry Reding --- drivers/pwm/pwm-atmel-tcb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c index 2837b4ce8053..4a116dc44f6e 100644 --- a/drivers/pwm/pwm-atmel-tcb.c +++ b/drivers/pwm/pwm-atmel-tcb.c @@ -500,7 +500,7 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev) return err; } -static int atmel_tcb_pwm_remove(struct platform_device *pdev) +static void atmel_tcb_pwm_remove(struct platform_device *pdev) { struct atmel_tcb_pwm_chip *tcbpwm = platform_get_drvdata(pdev); @@ -509,8 +509,6 @@ static int atmel_tcb_pwm_remove(struct platform_device *pdev) clk_disable_unprepare(tcbpwm->slow_clk); clk_put(tcbpwm->slow_clk); clk_put(tcbpwm->clk); - - return 0; } static const struct of_device_id atmel_tcb_pwm_dt_ids[] = { @@ -564,7 +562,7 @@ static struct platform_driver atmel_tcb_pwm_driver = { .pm = &atmel_tcb_pwm_pm_ops, }, .probe = atmel_tcb_pwm_probe, - .remove = atmel_tcb_pwm_remove, + .remove_new = atmel_tcb_pwm_remove, }; module_platform_driver(atmel_tcb_pwm_driver); -- GitLab From a3c28bca114b9f62d58b8a053aa0240b277e5959 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:18 +0100 Subject: [PATCH 1700/5631] pwm: atmel: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Claudiu Beznea Signed-off-by: Thierry Reding --- drivers/pwm/pwm-atmel.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c index cdbc23649032..0c567d9623cd 100644 --- a/drivers/pwm/pwm-atmel.c +++ b/drivers/pwm/pwm-atmel.c @@ -511,15 +511,13 @@ static int atmel_pwm_probe(struct platform_device *pdev) return ret; } -static int atmel_pwm_remove(struct platform_device *pdev) +static void atmel_pwm_remove(struct platform_device *pdev) { struct atmel_pwm_chip *atmel_pwm = platform_get_drvdata(pdev); pwmchip_remove(&atmel_pwm->chip); clk_unprepare(atmel_pwm->clk); - - return 0; } static struct platform_driver atmel_pwm_driver = { @@ -528,7 +526,7 @@ static struct platform_driver atmel_pwm_driver = { .of_match_table = of_match_ptr(atmel_pwm_dt_ids), }, .probe = atmel_pwm_probe, - .remove = atmel_pwm_remove, + .remove_new = atmel_pwm_remove, }; module_platform_driver(atmel_pwm_driver); -- GitLab From bbacca0ee408d94fa08d932cb0f1a6200b4f409a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:19 +0100 Subject: [PATCH 1701/5631] pwm: bcm-iproc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-bcm-iproc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c index 97ec131eb7c1..7d70b6f186a6 100644 --- a/drivers/pwm/pwm-bcm-iproc.c +++ b/drivers/pwm/pwm-bcm-iproc.c @@ -239,15 +239,13 @@ static int iproc_pwmc_probe(struct platform_device *pdev) return ret; } -static int iproc_pwmc_remove(struct platform_device *pdev) +static void iproc_pwmc_remove(struct platform_device *pdev) { struct iproc_pwmc *ip = platform_get_drvdata(pdev); pwmchip_remove(&ip->chip); clk_disable_unprepare(ip->clk); - - return 0; } static const struct of_device_id bcm_iproc_pwmc_dt[] = { @@ -262,7 +260,7 @@ static struct platform_driver iproc_pwmc_driver = { .of_match_table = bcm_iproc_pwmc_dt, }, .probe = iproc_pwmc_probe, - .remove = iproc_pwmc_remove, + .remove_new = iproc_pwmc_remove, }; module_platform_driver(iproc_pwmc_driver); -- GitLab From c49670108b76af7d5aca63f2d7a4bc2a9f15f49e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:20 +0100 Subject: [PATCH 1702/5631] pwm: bcm2835: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-bcm2835.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-bcm2835.c b/drivers/pwm/pwm-bcm2835.c index 50b8594be31d..bdfc2a5ec0d6 100644 --- a/drivers/pwm/pwm-bcm2835.c +++ b/drivers/pwm/pwm-bcm2835.c @@ -173,15 +173,13 @@ static int bcm2835_pwm_probe(struct platform_device *pdev) return ret; } -static int bcm2835_pwm_remove(struct platform_device *pdev) +static void bcm2835_pwm_remove(struct platform_device *pdev) { struct bcm2835_pwm *pc = platform_get_drvdata(pdev); pwmchip_remove(&pc->chip); clk_disable_unprepare(pc->clk); - - return 0; } static const struct of_device_id bcm2835_pwm_of_match[] = { @@ -196,7 +194,7 @@ static struct platform_driver bcm2835_pwm_driver = { .of_match_table = bcm2835_pwm_of_match, }, .probe = bcm2835_pwm_probe, - .remove = bcm2835_pwm_remove, + .remove_new = bcm2835_pwm_remove, }; module_platform_driver(bcm2835_pwm_driver); -- GitLab From 9baa8a00de7db7655e333c1749b3acb87401f62f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:21 +0100 Subject: [PATCH 1703/5631] pwm: berlin: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-berlin.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-berlin.c b/drivers/pwm/pwm-berlin.c index e157273fd2f7..0c5992a046b2 100644 --- a/drivers/pwm/pwm-berlin.c +++ b/drivers/pwm/pwm-berlin.c @@ -250,15 +250,13 @@ static int berlin_pwm_probe(struct platform_device *pdev) return 0; } -static int berlin_pwm_remove(struct platform_device *pdev) +static void berlin_pwm_remove(struct platform_device *pdev) { struct berlin_pwm_chip *bpc = platform_get_drvdata(pdev); pwmchip_remove(&bpc->chip); clk_disable_unprepare(bpc->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -317,7 +315,7 @@ static SIMPLE_DEV_PM_OPS(berlin_pwm_pm_ops, berlin_pwm_suspend, static struct platform_driver berlin_pwm_driver = { .probe = berlin_pwm_probe, - .remove = berlin_pwm_remove, + .remove_new = berlin_pwm_remove, .driver = { .name = "berlin-pwm", .of_match_table = berlin_pwm_match, -- GitLab From e577bffd7afc48f9388fd2652b8a015523448a32 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:22 +0100 Subject: [PATCH 1704/5631] pwm: brcmstb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-brcmstb.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-brcmstb.c b/drivers/pwm/pwm-brcmstb.c index 3db3f96edf78..a3faa9a3de7c 100644 --- a/drivers/pwm/pwm-brcmstb.c +++ b/drivers/pwm/pwm-brcmstb.c @@ -275,14 +275,12 @@ static int brcmstb_pwm_probe(struct platform_device *pdev) return ret; } -static int brcmstb_pwm_remove(struct platform_device *pdev) +static void brcmstb_pwm_remove(struct platform_device *pdev) { struct brcmstb_pwm *p = platform_get_drvdata(pdev); pwmchip_remove(&p->chip); clk_disable_unprepare(p->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -310,7 +308,7 @@ static SIMPLE_DEV_PM_OPS(brcmstb_pwm_pm_ops, brcmstb_pwm_suspend, static struct platform_driver brcmstb_pwm_driver = { .probe = brcmstb_pwm_probe, - .remove = brcmstb_pwm_remove, + .remove_new = brcmstb_pwm_remove, .driver = { .name = "pwm-brcmstb", .of_match_table = brcmstb_pwm_of_match, -- GitLab From d5806ac636a9e7c2751435ee5c06731261155fd2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:23 +0100 Subject: [PATCH 1705/5631] pwm: clk: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-clk.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-clk.c b/drivers/pwm/pwm-clk.c index c2a503d684a7..f1da99881adf 100644 --- a/drivers/pwm/pwm-clk.c +++ b/drivers/pwm/pwm-clk.c @@ -112,7 +112,7 @@ static int pwm_clk_probe(struct platform_device *pdev) return 0; } -static int pwm_clk_remove(struct platform_device *pdev) +static void pwm_clk_remove(struct platform_device *pdev) { struct pwm_clk_chip *pcchip = platform_get_drvdata(pdev); @@ -122,8 +122,6 @@ static int pwm_clk_remove(struct platform_device *pdev) clk_disable(pcchip->clk); clk_unprepare(pcchip->clk); - - return 0; } static const struct of_device_id pwm_clk_dt_ids[] = { @@ -138,7 +136,7 @@ static struct platform_driver pwm_clk_driver = { .of_match_table = pwm_clk_dt_ids, }, .probe = pwm_clk_probe, - .remove = pwm_clk_remove, + .remove_new = pwm_clk_remove, }; module_platform_driver(pwm_clk_driver); -- GitLab From 159a61a7b5b01dc158cbe718a181f1943ab6dcac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:24 +0100 Subject: [PATCH 1706/5631] pwm: cros-ec: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Signed-off-by: Thierry Reding --- drivers/pwm/pwm-cros-ec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c index ad18b0ebe3f1..74e863aa1d8d 100644 --- a/drivers/pwm/pwm-cros-ec.c +++ b/drivers/pwm/pwm-cros-ec.c @@ -329,14 +329,12 @@ static int cros_ec_pwm_probe(struct platform_device *pdev) return ret; } -static int cros_ec_pwm_remove(struct platform_device *dev) +static void cros_ec_pwm_remove(struct platform_device *dev) { struct cros_ec_pwm_device *ec_pwm = platform_get_drvdata(dev); struct pwm_chip *chip = &ec_pwm->chip; pwmchip_remove(chip); - - return 0; } #ifdef CONFIG_OF @@ -350,7 +348,7 @@ MODULE_DEVICE_TABLE(of, cros_ec_pwm_of_match); static struct platform_driver cros_ec_pwm_driver = { .probe = cros_ec_pwm_probe, - .remove = cros_ec_pwm_remove, + .remove_new = cros_ec_pwm_remove, .driver = { .name = "cros-ec-pwm", .of_match_table = of_match_ptr(cros_ec_pwm_of_match), -- GitLab From 1b6d6ce5a5f3800b98a7db76036c822c52d1ba63 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:25 +0100 Subject: [PATCH 1707/5631] pwm: hibvt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-hibvt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c index 1b9274c5ad87..b95df1a96127 100644 --- a/drivers/pwm/pwm-hibvt.c +++ b/drivers/pwm/pwm-hibvt.c @@ -245,7 +245,7 @@ static int hibvt_pwm_probe(struct platform_device *pdev) return 0; } -static int hibvt_pwm_remove(struct platform_device *pdev) +static void hibvt_pwm_remove(struct platform_device *pdev) { struct hibvt_pwm_chip *pwm_chip; @@ -258,8 +258,6 @@ static int hibvt_pwm_remove(struct platform_device *pdev) reset_control_deassert(pwm_chip->rstc); clk_disable_unprepare(pwm_chip->clk); - - return 0; } static const struct of_device_id hibvt_pwm_of_match[] = { @@ -281,7 +279,7 @@ static struct platform_driver hibvt_pwm_driver = { .of_match_table = hibvt_pwm_of_match, }, .probe = hibvt_pwm_probe, - .remove = hibvt_pwm_remove, + .remove_new = hibvt_pwm_remove, }; module_platform_driver(hibvt_pwm_driver); -- GitLab From f365a94660f76599541f7deb83a5d6b388da7dec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:26 +0100 Subject: [PATCH 1708/5631] pwm: img: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-img.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c index 89362afe3c91..326af85888e7 100644 --- a/drivers/pwm/pwm-img.c +++ b/drivers/pwm/pwm-img.c @@ -343,7 +343,7 @@ static int img_pwm_probe(struct platform_device *pdev) return ret; } -static int img_pwm_remove(struct platform_device *pdev) +static void img_pwm_remove(struct platform_device *pdev) { struct img_pwm_chip *imgchip = platform_get_drvdata(pdev); @@ -352,8 +352,6 @@ static int img_pwm_remove(struct platform_device *pdev) img_pwm_runtime_suspend(&pdev->dev); pwmchip_remove(&imgchip->chip); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -423,7 +421,7 @@ static struct platform_driver img_pwm_driver = { .of_match_table = img_pwm_of_match, }, .probe = img_pwm_probe, - .remove = img_pwm_remove, + .remove_new = img_pwm_remove, }; module_platform_driver(img_pwm_driver); -- GitLab From ed60a877affc9ae1a14f59d253d6346273a5ebda Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:27 +0100 Subject: [PATCH 1709/5631] pwm: imx-tpm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-imx-tpm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c index ed1aad96fff0..5e2b452ee5f2 100644 --- a/drivers/pwm/pwm-imx-tpm.c +++ b/drivers/pwm/pwm-imx-tpm.c @@ -381,15 +381,13 @@ static int pwm_imx_tpm_probe(struct platform_device *pdev) return ret; } -static int pwm_imx_tpm_remove(struct platform_device *pdev) +static void pwm_imx_tpm_remove(struct platform_device *pdev) { struct imx_tpm_pwm_chip *tpm = platform_get_drvdata(pdev); pwmchip_remove(&tpm->chip); clk_disable_unprepare(tpm->clk); - - return 0; } static int __maybe_unused pwm_imx_tpm_suspend(struct device *dev) @@ -432,7 +430,7 @@ static struct platform_driver imx_tpm_pwm_driver = { .pm = &imx_tpm_pwm_pm, }, .probe = pwm_imx_tpm_probe, - .remove = pwm_imx_tpm_remove, + .remove_new = pwm_imx_tpm_remove, }; module_platform_driver(imx_tpm_pwm_driver); -- GitLab From fbd2d733e3b7313d396bca6398cd7605fdb63394 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:28 +0100 Subject: [PATCH 1710/5631] pwm: lpc18xx-sct: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-lpc18xx-sct.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-lpc18xx-sct.c b/drivers/pwm/pwm-lpc18xx-sct.c index 378e1df944dc..b9bf5b366f4b 100644 --- a/drivers/pwm/pwm-lpc18xx-sct.c +++ b/drivers/pwm/pwm-lpc18xx-sct.c @@ -449,7 +449,7 @@ static int lpc18xx_pwm_probe(struct platform_device *pdev) return ret; } -static int lpc18xx_pwm_remove(struct platform_device *pdev) +static void lpc18xx_pwm_remove(struct platform_device *pdev) { struct lpc18xx_pwm_chip *lpc18xx_pwm = platform_get_drvdata(pdev); u32 val; @@ -461,8 +461,6 @@ static int lpc18xx_pwm_remove(struct platform_device *pdev) val | LPC18XX_PWM_CTRL_HALT); clk_disable_unprepare(lpc18xx_pwm->pwm_clk); - - return 0; } static struct platform_driver lpc18xx_pwm_driver = { @@ -471,7 +469,7 @@ static struct platform_driver lpc18xx_pwm_driver = { .of_match_table = lpc18xx_pwm_of_match, }, .probe = lpc18xx_pwm_probe, - .remove = lpc18xx_pwm_remove, + .remove_new = lpc18xx_pwm_remove, }; module_platform_driver(lpc18xx_pwm_driver); -- GitLab From 9a9174eadd8ca8fc2c6b43710b8a5e7e95f64268 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:29 +0100 Subject: [PATCH 1711/5631] pwm: lpss-platform: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-lpss-platform.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-lpss-platform.c b/drivers/pwm/pwm-lpss-platform.c index f350607e28bd..319809aac2c4 100644 --- a/drivers/pwm/pwm-lpss-platform.c +++ b/drivers/pwm/pwm-lpss-platform.c @@ -62,10 +62,9 @@ static int pwm_lpss_probe_platform(struct platform_device *pdev) return 0; } -static int pwm_lpss_remove_platform(struct platform_device *pdev) +static void pwm_lpss_remove_platform(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - return 0; } static const struct acpi_device_id pwm_lpss_acpi_match[] = { @@ -83,7 +82,7 @@ static struct platform_driver pwm_lpss_driver_platform = { .acpi_match_table = pwm_lpss_acpi_match, }, .probe = pwm_lpss_probe_platform, - .remove = pwm_lpss_remove_platform, + .remove_new = pwm_lpss_remove_platform, }; module_platform_driver(pwm_lpss_driver_platform); -- GitLab From a19cf5a571c49d289cccee7c17d185fc2eb4af88 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:30 +0100 Subject: [PATCH 1712/5631] pwm: mtk-disp: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-mtk-disp.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index 692a06121b28..4cfe88d54652 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -260,13 +260,11 @@ static int mtk_disp_pwm_probe(struct platform_device *pdev) return 0; } -static int mtk_disp_pwm_remove(struct platform_device *pdev) +static void mtk_disp_pwm_remove(struct platform_device *pdev) { struct mtk_disp_pwm *mdp = platform_get_drvdata(pdev); pwmchip_remove(&mdp->chip); - - return 0; } static const struct mtk_pwm_data mt2701_pwm_data = { @@ -314,7 +312,7 @@ static struct platform_driver mtk_disp_pwm_driver = { .of_match_table = mtk_disp_pwm_of_match, }, .probe = mtk_disp_pwm_probe, - .remove = mtk_disp_pwm_remove, + .remove_new = mtk_disp_pwm_remove, }; module_platform_driver(mtk_disp_pwm_driver); -- GitLab From fed5d59d82dd11e1a651384225a8f054bee4a1b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:31 +0100 Subject: [PATCH 1713/5631] pwm: omap-dmtimer: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-omap-dmtimer.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c index fa800fcf31d4..4889fbd8a431 100644 --- a/drivers/pwm/pwm-omap-dmtimer.c +++ b/drivers/pwm/pwm-omap-dmtimer.c @@ -441,7 +441,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev) return ret; } -static int pwm_omap_dmtimer_remove(struct platform_device *pdev) +static void pwm_omap_dmtimer_remove(struct platform_device *pdev) { struct pwm_omap_dmtimer_chip *omap = platform_get_drvdata(pdev); @@ -455,8 +455,6 @@ static int pwm_omap_dmtimer_remove(struct platform_device *pdev) put_device(&omap->dm_timer_pdev->dev); mutex_destroy(&omap->mutex); - - return 0; } static const struct of_device_id pwm_omap_dmtimer_of_match[] = { @@ -471,7 +469,7 @@ static struct platform_driver pwm_omap_dmtimer_driver = { .of_match_table = of_match_ptr(pwm_omap_dmtimer_of_match), }, .probe = pwm_omap_dmtimer_probe, - .remove = pwm_omap_dmtimer_remove, + .remove_new = pwm_omap_dmtimer_remove, }; module_platform_driver(pwm_omap_dmtimer_driver); -- GitLab From e7fa6e8447a74582382dbbe72d5c7af72f9f3157 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:32 +0100 Subject: [PATCH 1714/5631] pwm: rcar: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-rcar.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c index 55f46d09602b..e9d8646dc331 100644 --- a/drivers/pwm/pwm-rcar.c +++ b/drivers/pwm/pwm-rcar.c @@ -238,15 +238,13 @@ static int rcar_pwm_probe(struct platform_device *pdev) return 0; } -static int rcar_pwm_remove(struct platform_device *pdev) +static void rcar_pwm_remove(struct platform_device *pdev) { struct rcar_pwm_chip *rcar_pwm = platform_get_drvdata(pdev); pwmchip_remove(&rcar_pwm->chip); pm_runtime_disable(&pdev->dev); - - return 0; } static const struct of_device_id rcar_pwm_of_table[] = { @@ -257,7 +255,7 @@ MODULE_DEVICE_TABLE(of, rcar_pwm_of_table); static struct platform_driver rcar_pwm_driver = { .probe = rcar_pwm_probe, - .remove = rcar_pwm_remove, + .remove_new = rcar_pwm_remove, .driver = { .name = "pwm-rcar", .of_match_table = of_match_ptr(rcar_pwm_of_table), -- GitLab From 18a95d363098bc2a77d4921f0e2483e21589d980 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:33 +0100 Subject: [PATCH 1715/5631] pwm: rockchip: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-rockchip.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c index 7f084eb34092..c1a1f2d864b5 100644 --- a/drivers/pwm/pwm-rockchip.c +++ b/drivers/pwm/pwm-rockchip.c @@ -376,7 +376,7 @@ static int rockchip_pwm_probe(struct platform_device *pdev) return ret; } -static int rockchip_pwm_remove(struct platform_device *pdev) +static void rockchip_pwm_remove(struct platform_device *pdev) { struct rockchip_pwm_chip *pc = platform_get_drvdata(pdev); @@ -384,8 +384,6 @@ static int rockchip_pwm_remove(struct platform_device *pdev) clk_unprepare(pc->pclk); clk_unprepare(pc->clk); - - return 0; } static struct platform_driver rockchip_pwm_driver = { @@ -394,7 +392,7 @@ static struct platform_driver rockchip_pwm_driver = { .of_match_table = rockchip_pwm_dt_ids, }, .probe = rockchip_pwm_probe, - .remove = rockchip_pwm_remove, + .remove_new = rockchip_pwm_remove, }; module_platform_driver(rockchip_pwm_driver); -- GitLab From 1d4f9972dca4905650b858ec493e7b36db7ecc71 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:34 +0100 Subject: [PATCH 1716/5631] pwm: samsung: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-samsung.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c index 9c5b4f515641..e8828f57ab15 100644 --- a/drivers/pwm/pwm-samsung.c +++ b/drivers/pwm/pwm-samsung.c @@ -621,15 +621,13 @@ static int pwm_samsung_probe(struct platform_device *pdev) return 0; } -static int pwm_samsung_remove(struct platform_device *pdev) +static void pwm_samsung_remove(struct platform_device *pdev) { struct samsung_pwm_chip *chip = platform_get_drvdata(pdev); pwmchip_remove(&chip->chip); clk_disable_unprepare(chip->base_clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -676,7 +674,7 @@ static struct platform_driver pwm_samsung_driver = { .of_match_table = of_match_ptr(samsung_pwm_matches), }, .probe = pwm_samsung_probe, - .remove = pwm_samsung_remove, + .remove_new = pwm_samsung_remove, }; module_platform_driver(pwm_samsung_driver); -- GitLab From 533d29471b3c9405cf6e5f211ae5079f64dac257 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:35 +0100 Subject: [PATCH 1717/5631] pwm: sifive: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sifive.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c index 393a4b97fc19..5b0574f635f6 100644 --- a/drivers/pwm/pwm-sifive.c +++ b/drivers/pwm/pwm-sifive.c @@ -313,7 +313,7 @@ static int pwm_sifive_probe(struct platform_device *pdev) return ret; } -static int pwm_sifive_remove(struct platform_device *dev) +static void pwm_sifive_remove(struct platform_device *dev) { struct pwm_sifive_ddata *ddata = platform_get_drvdata(dev); struct pwm_device *pwm; @@ -329,8 +329,6 @@ static int pwm_sifive_remove(struct platform_device *dev) } clk_unprepare(ddata->clk); - - return 0; } static const struct of_device_id pwm_sifive_of_match[] = { @@ -341,7 +339,7 @@ MODULE_DEVICE_TABLE(of, pwm_sifive_of_match); static struct platform_driver pwm_sifive_driver = { .probe = pwm_sifive_probe, - .remove = pwm_sifive_remove, + .remove_new = pwm_sifive_remove, .driver = { .name = "pwm-sifive", .of_match_table = pwm_sifive_of_match, -- GitLab From f113c11bf28cb0ce0ba28576feafd651638c1132 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:36 +0100 Subject: [PATCH 1718/5631] pwm: spear: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-spear.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-spear.c b/drivers/pwm/pwm-spear.c index 54c7990967dd..4e1cfd8d7c03 100644 --- a/drivers/pwm/pwm-spear.c +++ b/drivers/pwm/pwm-spear.c @@ -247,7 +247,7 @@ static int spear_pwm_probe(struct platform_device *pdev) return ret; } -static int spear_pwm_remove(struct platform_device *pdev) +static void spear_pwm_remove(struct platform_device *pdev) { struct spear_pwm_chip *pc = platform_get_drvdata(pdev); @@ -255,8 +255,6 @@ static int spear_pwm_remove(struct platform_device *pdev) /* clk was prepared in probe, hence unprepare it here */ clk_unprepare(pc->clk); - - return 0; } static const struct of_device_id spear_pwm_of_match[] = { @@ -273,7 +271,7 @@ static struct platform_driver spear_pwm_driver = { .of_match_table = spear_pwm_of_match, }, .probe = spear_pwm_probe, - .remove = spear_pwm_remove, + .remove_new = spear_pwm_remove, }; module_platform_driver(spear_pwm_driver); -- GitLab From c51638065bb436901e639782e9c27f7a4ba10c8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:37 +0100 Subject: [PATCH 1719/5631] pwm: sprd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sprd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-sprd.c b/drivers/pwm/pwm-sprd.c index bde579a338c2..d43a6fa3f4e0 100644 --- a/drivers/pwm/pwm-sprd.c +++ b/drivers/pwm/pwm-sprd.c @@ -280,13 +280,11 @@ static int sprd_pwm_probe(struct platform_device *pdev) return ret; } -static int sprd_pwm_remove(struct platform_device *pdev) +static void sprd_pwm_remove(struct platform_device *pdev) { struct sprd_pwm_chip *spc = platform_get_drvdata(pdev); pwmchip_remove(&spc->chip); - - return 0; } static const struct of_device_id sprd_pwm_of_match[] = { @@ -301,7 +299,7 @@ static struct platform_driver sprd_pwm_driver = { .of_match_table = sprd_pwm_of_match, }, .probe = sprd_pwm_probe, - .remove = sprd_pwm_remove, + .remove_new = sprd_pwm_remove, }; module_platform_driver(sprd_pwm_driver); -- GitLab From e13cec3617c6ace4fc389b60d2a7d5b305b62683 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:38 +0100 Subject: [PATCH 1720/5631] pwm: sti: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sti.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-sti.c b/drivers/pwm/pwm-sti.c index 44b1f93256b3..b1d1373648a3 100644 --- a/drivers/pwm/pwm-sti.c +++ b/drivers/pwm/pwm-sti.c @@ -669,7 +669,7 @@ static int sti_pwm_probe(struct platform_device *pdev) return 0; } -static int sti_pwm_remove(struct platform_device *pdev) +static void sti_pwm_remove(struct platform_device *pdev) { struct sti_pwm_chip *pc = platform_get_drvdata(pdev); @@ -677,8 +677,6 @@ static int sti_pwm_remove(struct platform_device *pdev) clk_unprepare(pc->pwm_clk); clk_unprepare(pc->cpt_clk); - - return 0; } static const struct of_device_id sti_pwm_of_match[] = { @@ -693,7 +691,7 @@ static struct platform_driver sti_pwm_driver = { .of_match_table = sti_pwm_of_match, }, .probe = sti_pwm_probe, - .remove = sti_pwm_remove, + .remove_new = sti_pwm_remove, }; module_platform_driver(sti_pwm_driver); -- GitLab From 000b97ab8737ed0e7f4a20b493749e2a21dfef1a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:39 +0100 Subject: [PATCH 1721/5631] pwm: stm32: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-stm32.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index 21e4a34dfff3..a482f7e0e4ab 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -642,7 +642,7 @@ static int stm32_pwm_probe(struct platform_device *pdev) return 0; } -static int stm32_pwm_remove(struct platform_device *pdev) +static void stm32_pwm_remove(struct platform_device *pdev) { struct stm32_pwm *priv = platform_get_drvdata(pdev); unsigned int i; @@ -651,8 +651,6 @@ static int stm32_pwm_remove(struct platform_device *pdev) pwm_disable(&priv->chip.pwms[i]); pwmchip_remove(&priv->chip); - - return 0; } static int __maybe_unused stm32_pwm_suspend(struct device *dev) @@ -699,7 +697,7 @@ MODULE_DEVICE_TABLE(of, stm32_pwm_of_match); static struct platform_driver stm32_pwm_driver = { .probe = stm32_pwm_probe, - .remove = stm32_pwm_remove, + .remove_new = stm32_pwm_remove, .driver = { .name = "stm32-pwm", .of_match_table = stm32_pwm_of_match, -- GitLab From 0bda6b0187fd57761bbe4cc6101f2297b01b90fb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:40 +0100 Subject: [PATCH 1722/5631] pwm: sun4i: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Jernej Skrabec Signed-off-by: Thierry Reding --- drivers/pwm/pwm-sun4i.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c index b973da73e9ab..a8790a8fc53e 100644 --- a/drivers/pwm/pwm-sun4i.c +++ b/drivers/pwm/pwm-sun4i.c @@ -477,7 +477,7 @@ static int sun4i_pwm_probe(struct platform_device *pdev) return ret; } -static int sun4i_pwm_remove(struct platform_device *pdev) +static void sun4i_pwm_remove(struct platform_device *pdev) { struct sun4i_pwm_chip *sun4ichip = platform_get_drvdata(pdev); @@ -485,8 +485,6 @@ static int sun4i_pwm_remove(struct platform_device *pdev) clk_disable_unprepare(sun4ichip->bus_clk); reset_control_assert(sun4ichip->rst); - - return 0; } static struct platform_driver sun4i_pwm_driver = { @@ -495,7 +493,7 @@ static struct platform_driver sun4i_pwm_driver = { .of_match_table = sun4i_pwm_dt_ids, }, .probe = sun4i_pwm_probe, - .remove = sun4i_pwm_remove, + .remove_new = sun4i_pwm_remove, }; module_platform_driver(sun4i_pwm_driver); -- GitLab From e39cb6f9be7ead36ec64aab9f3e51352aab9695d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:41 +0100 Subject: [PATCH 1723/5631] pwm: tegra: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tegra.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index 249dc0193297..5810abf66e2a 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -350,7 +350,7 @@ static int tegra_pwm_probe(struct platform_device *pdev) return ret; } -static int tegra_pwm_remove(struct platform_device *pdev) +static void tegra_pwm_remove(struct platform_device *pdev) { struct tegra_pwm_chip *pc = platform_get_drvdata(pdev); @@ -359,8 +359,6 @@ static int tegra_pwm_remove(struct platform_device *pdev) reset_control_assert(pc->rst); pm_runtime_force_suspend(&pdev->dev); - - return 0; } static int __maybe_unused tegra_pwm_runtime_suspend(struct device *dev) @@ -434,7 +432,7 @@ static struct platform_driver tegra_pwm_driver = { .pm = &tegra_pwm_pm_ops, }, .probe = tegra_pwm_probe, - .remove = tegra_pwm_remove, + .remove_new = tegra_pwm_remove, }; module_platform_driver(tegra_pwm_driver); -- GitLab From dc75f6bc5b6c6993d63267fcd1e315d8c04a7162 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:42 +0100 Subject: [PATCH 1724/5631] pwm: tiecap: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tiecap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c index 4701f0c9b921..109449956307 100644 --- a/drivers/pwm/pwm-tiecap.c +++ b/drivers/pwm/pwm-tiecap.c @@ -265,11 +265,9 @@ static int ecap_pwm_probe(struct platform_device *pdev) return 0; } -static int ecap_pwm_remove(struct platform_device *pdev) +static void ecap_pwm_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -326,7 +324,7 @@ static struct platform_driver ecap_pwm_driver = { .pm = &ecap_pwm_pm_ops, }, .probe = ecap_pwm_probe, - .remove = ecap_pwm_remove, + .remove_new = ecap_pwm_remove, }; module_platform_driver(ecap_pwm_driver); -- GitLab From 91e92e82b1da6d5da355594179bca5131fa67746 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:43 +0100 Subject: [PATCH 1725/5631] pwm: tiehrpwm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-tiehrpwm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c index 48ca0ff690ae..bb3959ace6b4 100644 --- a/drivers/pwm/pwm-tiehrpwm.c +++ b/drivers/pwm/pwm-tiehrpwm.c @@ -511,7 +511,7 @@ static int ehrpwm_pwm_probe(struct platform_device *pdev) return ret; } -static int ehrpwm_pwm_remove(struct platform_device *pdev) +static void ehrpwm_pwm_remove(struct platform_device *pdev) { struct ehrpwm_pwm_chip *pc = platform_get_drvdata(pdev); @@ -520,8 +520,6 @@ static int ehrpwm_pwm_remove(struct platform_device *pdev) clk_unprepare(pc->tbclk); pm_runtime_disable(&pdev->dev); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -604,7 +602,7 @@ static struct platform_driver ehrpwm_pwm_driver = { .pm = &ehrpwm_pwm_pm_ops, }, .probe = ehrpwm_pwm_probe, - .remove = ehrpwm_pwm_remove, + .remove_new = ehrpwm_pwm_remove, }; module_platform_driver(ehrpwm_pwm_driver); -- GitLab From 22e1d1f44d3fabbfb88690d06cf7249addbc3691 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:44 +0100 Subject: [PATCH 1726/5631] pwm: vt8500: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-vt8500.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c index f1ff9940b37c..d2c48fd98706 100644 --- a/drivers/pwm/pwm-vt8500.c +++ b/drivers/pwm/pwm-vt8500.c @@ -279,20 +279,18 @@ static int vt8500_pwm_probe(struct platform_device *pdev) return ret; } -static int vt8500_pwm_remove(struct platform_device *pdev) +static void vt8500_pwm_remove(struct platform_device *pdev) { struct vt8500_chip *vt8500 = platform_get_drvdata(pdev); pwmchip_remove(&vt8500->chip); clk_unprepare(vt8500->clk); - - return 0; } static struct platform_driver vt8500_pwm_driver = { .probe = vt8500_pwm_probe, - .remove = vt8500_pwm_remove, + .remove_new = vt8500_pwm_remove, .driver = { .name = "vt8500-pwm", .of_match_table = vt8500_pwm_dt_ids, -- GitLab From 9a2273a16157b9429f07571b3a9d40407b68dbe1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 19:54:45 +0100 Subject: [PATCH 1727/5631] pwm: xilinx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Sean Anderson Signed-off-by: Thierry Reding --- drivers/pwm/pwm-xilinx.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-xilinx.c b/drivers/pwm/pwm-xilinx.c index f7a50fdcd9a5..85153ee90809 100644 --- a/drivers/pwm/pwm-xilinx.c +++ b/drivers/pwm/pwm-xilinx.c @@ -292,14 +292,13 @@ static int xilinx_pwm_probe(struct platform_device *pdev) return 0; } -static int xilinx_pwm_remove(struct platform_device *pdev) +static void xilinx_pwm_remove(struct platform_device *pdev) { struct xilinx_pwm_device *xilinx_pwm = platform_get_drvdata(pdev); pwmchip_remove(&xilinx_pwm->chip); clk_rate_exclusive_put(xilinx_pwm->priv.clk); clk_disable_unprepare(xilinx_pwm->priv.clk); - return 0; } static const struct of_device_id xilinx_pwm_of_match[] = { @@ -310,7 +309,7 @@ MODULE_DEVICE_TABLE(of, xilinx_pwm_of_match); static struct platform_driver xilinx_pwm_driver = { .probe = xilinx_pwm_probe, - .remove = xilinx_pwm_remove, + .remove_new = xilinx_pwm_remove, .driver = { .name = "xilinx-pwm", .of_match_table = of_match_ptr(xilinx_pwm_of_match), -- GitLab From 5e96c2e0e88d3617477313b071cf199bfc29d794 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Tue, 28 Mar 2023 09:39:02 +0600 Subject: [PATCH 1728/5631] clk: renesas: r8a77980: Add I2C5 clock The MSSR clock definition for I2C5 was missing. Add it. Signed-off-by: Nikita Yushchenko Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20230328033902.830269-1-nikita.yoush@cogentembedded.com Signed-off-by: Geert Uytterhoeven --- drivers/clk/renesas/r8a77980-cpg-mssr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/renesas/r8a77980-cpg-mssr.c b/drivers/clk/renesas/r8a77980-cpg-mssr.c index bac92c606d0b..aaa685ec35df 100644 --- a/drivers/clk/renesas/r8a77980-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77980-cpg-mssr.c @@ -190,6 +190,7 @@ static const struct mssr_mod_clk r8a77980_mod_clks[] __initconst = { DEF_MOD("gpio0", 912, R8A77980_CLK_CP), DEF_MOD("can-fd", 914, R8A77980_CLK_S3D2), DEF_MOD("rpc-if", 917, R8A77980_CLK_RPCD2), + DEF_MOD("i2c5", 919, R8A77980_CLK_S0D6), DEF_MOD("i2c4", 927, R8A77980_CLK_S0D6), DEF_MOD("i2c3", 928, R8A77980_CLK_S0D6), DEF_MOD("i2c2", 929, R8A77980_CLK_S3D2), -- GitLab From 67ea0b7ce41844eae7c10bb04dfe66a23318c224 Mon Sep 17 00:00:00 2001 From: Tomas Krcka Date: Wed, 29 Mar 2023 12:34:19 +0000 Subject: [PATCH 1729/5631] iommu/arm-smmu-v3: Acknowledge pri/event queue overflow if any When an overflow occurs in the PRI queue, the SMMU toggles the overflow flag in the PROD register. To exit the overflow condition, the PRI thread is supposed to acknowledge it by toggling this flag in the CONS register. Unacknowledged overflow causes the queue to stop adding anything new. Currently, the priq thread always writes the CONS register back to the SMMU after clearing the queue. The writeback is not necessary if the OVFLG in the PROD register has not been changed, no overflow has occured. This commit checks the difference of the overflow flag between CONS and PROD register. If it's different, toggles the OVACKFLG flag in the CONS register and write it to the SMMU. The situation is similar for the event queue. The acknowledge register is also toggled after clearing the event queue but never propagated to the hardware. This would only be done the next time when executing evtq thread. Unacknowledged event queue overflow doesn't affect the event queue, because the SMMU still adds elements to that queue when the overflow condition is active. But it feel nicer to keep SMMU in sync when possible, so use the same way here as well. Signed-off-by: Tomas Krcka Link: https://lore.kernel.org/r/20230329123420.34641-1-tomas.krcka@gmail.com Signed-off-by: Will Deacon --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a8410c132f1e..e00e92c71239 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -152,6 +152,18 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q) q->cons = Q_OVF(q->cons) | Q_WRP(q, cons) | Q_IDX(q, cons); } +static void queue_sync_cons_ovf(struct arm_smmu_queue *q) +{ + struct arm_smmu_ll_queue *llq = &q->llq; + + if (likely(Q_OVF(llq->prod) == Q_OVF(llq->cons))) + return; + + llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | + Q_IDX(llq, llq->cons); + queue_sync_cons_out(q); +} + static int queue_sync_prod_in(struct arm_smmu_queue *q) { u32 prod; @@ -1577,8 +1589,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } @@ -1636,9 +1647,7 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev) } while (!queue_empty(llq)); /* Sync our overflow flag, as we believe we're up to speed */ - llq->cons = Q_OVF(llq->prod) | Q_WRP(llq, llq->cons) | - Q_IDX(llq, llq->cons); - queue_sync_cons_out(q); + queue_sync_cons_ovf(q); return IRQ_HANDLED; } -- GitLab From 0d0ae656b71155ccc0be9388beef77a1f7e7558e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:41 +0100 Subject: [PATCH 1730/5631] KVM: arm64: timers: Use a per-vcpu, per-timer accumulator for fractional ns Instead of accumulating the fractional ns value generated every time we compute a ns delta in a global variable, use a per-vcpu, per-timer variable. This keeps the fractional ns local to the timer instead of contributing to any odd, unrelated timer. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-2-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 2 +- include/kvm/arm_arch_timer.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index e1af4301b913..9515c645f03d 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -212,7 +212,7 @@ static u64 kvm_counter_compute_delta(struct arch_timer_context *timer_ctx, ns = cyclecounter_cyc2ns(timecounter->cc, val - now, timecounter->mask, - &timecounter->frac); + &timer_ctx->ns_frac); return ns; } diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index c52a6e6839da..70d47c4adc6a 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -44,6 +44,7 @@ struct arch_timer_context { /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; + u64 ns_frac; /* Offset for this counter/timer */ struct arch_timer_offset offset; -- GitLab From eaacaa4f26ade43dfdfdd3707c95d734b5ffc530 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:42 +0100 Subject: [PATCH 1731/5631] arm64: Add CNTPOFF_EL2 register definition Add the definition for CNTPOFF_EL2 in the description file. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-3-maz@kernel.org --- arch/arm64/tools/sysreg | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index dd5a9c7e310f..7063f1aacc54 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1952,6 +1952,10 @@ Sysreg CONTEXTIDR_EL2 3 4 13 0 1 Fields CONTEXTIDR_ELx EndSysreg +Sysreg CNTPOFF_EL2 3 4 14 0 6 +Field 63:0 PhysicalOffset +EndSysreg + Sysreg CPACR_EL12 3 5 1 0 2 Fields CPACR_ELx EndSysreg -- GitLab From 326349943ed181890b8b2af2755bd0eac93bd66d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:43 +0100 Subject: [PATCH 1732/5631] arm64: Add HAS_ECV_CNTPOFF capability Add the probing code for the FEAT_ECV variant that implements CNTPOFF_EL2. Why it is optional is a mystery, but let's try and detect it. Reviewed-by: Reiji Watanabe Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-4-maz@kernel.org --- arch/arm64/kernel/cpufeature.c | 11 +++++++++++ arch/arm64/tools/cpucaps | 1 + 2 files changed, 12 insertions(+) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 2e3e55139777..c331c49a7d19 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2223,6 +2223,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sign = FTR_UNSIGNED, .min_field_value = 1, }, + { + .desc = "Enhanced Counter Virtualization (CNTPOFF)", + .capability = ARM64_HAS_ECV_CNTPOFF, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64MMFR0_EL1, + .field_pos = ID_AA64MMFR0_EL1_ECV_SHIFT, + .field_width = 4, + .sign = FTR_UNSIGNED, + .min_field_value = ID_AA64MMFR0_EL1_ECV_CNTPOFF, + }, #ifdef CONFIG_ARM64_PAN { .desc = "Privileged Access Never", diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 37b1340e9646..40ba95472594 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -23,6 +23,7 @@ HAS_DCPOP HAS_DIT HAS_E0PD HAS_ECV +HAS_ECV_CNTPOFF HAS_EPAN HAS_GENERIC_AUTH HAS_GENERIC_AUTH_ARCH_QARMA3 -- GitLab From 2b4825a8694018901e641ccc2eafd0fff58d1415 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:44 +0100 Subject: [PATCH 1733/5631] KVM: arm64: timers: Use CNTPOFF_EL2 to offset the physical timer With ECV and CNTPOFF_EL2, it is very easy to offer an offset for the physical timer. So let's do just that. Nothing can set the offset yet, so this should have no effect whatsoever (famous last words...). Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-5-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 18 +++++++++++++++++- arch/arm64/kvm/hypercalls.c | 2 +- include/clocksource/arm_arch_timer.h | 1 + include/kvm/arm_arch_timer.h | 2 ++ 4 files changed, 21 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 9515c645f03d..3118ea0a1b41 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -52,6 +52,11 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg); +static bool has_cntpoff(void) +{ + return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); +} + u32 timer_get_ctl(struct arch_timer_context *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; @@ -84,7 +89,7 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) static u64 timer_get_offset(struct arch_timer_context *ctxt) { - if (ctxt->offset.vm_offset) + if (ctxt && ctxt->offset.vm_offset) return *ctxt->offset.vm_offset; return 0; @@ -432,6 +437,12 @@ static void set_cntvoff(u64 cntvoff) kvm_call_hyp(__kvm_timer_set_cntvoff, cntvoff); } +static void set_cntpoff(u64 cntpoff) +{ + if (has_cntpoff()) + write_sysreg_s(cntpoff, SYS_CNTPOFF_EL2); +} + static void timer_save_state(struct arch_timer_context *ctx) { struct arch_timer_cpu *timer = vcpu_timer(ctx->vcpu); @@ -480,6 +491,7 @@ static void timer_save_state(struct arch_timer_context *ctx) write_sysreg_el0(0, SYS_CNTP_CTL); isb(); + set_cntpoff(0); break; case NR_KVM_TIMERS: BUG(); @@ -550,6 +562,7 @@ static void timer_restore_state(struct arch_timer_context *ctx) write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; case TIMER_PTIMER: + set_cntpoff(timer_get_offset(ctx)); write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); @@ -767,6 +780,7 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) vtimer->vcpu = vcpu; vtimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.voffset; ptimer->vcpu = vcpu; + ptimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.poffset; /* Synchronize cntvoff across all vtimers of a VM. */ timer_set_offset(vtimer, kvm_phys_timer_read()); @@ -1297,6 +1311,8 @@ void kvm_timer_init_vhe(void) val = read_sysreg(cnthctl_el2); val |= (CNTHCTL_EL1PCEN << cnthctl_shift); val |= (CNTHCTL_EL1PCTEN << cnthctl_shift); + if (cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)) + val |= CNTHCTL_ECV; write_sysreg(val, cnthctl_el2); } diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 5da884e11337..39a4707e081d 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -47,7 +47,7 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: - cycles = systime_snapshot.cycles; + cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.poffset; break; default: return; diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h index 057c8964aefb..cbbc9a6dc571 100644 --- a/include/clocksource/arm_arch_timer.h +++ b/include/clocksource/arm_arch_timer.h @@ -21,6 +21,7 @@ #define CNTHCTL_EVNTEN (1 << 2) #define CNTHCTL_EVNTDIR (1 << 3) #define CNTHCTL_EVNTI (0xF << 4) +#define CNTHCTL_ECV (1 << 12) enum arch_timer_reg { ARCH_TIMER_REG_CTRL, diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 70d47c4adc6a..2dd0fd2406fb 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -34,6 +34,8 @@ struct arch_timer_offset { struct arch_timer_vm_data { /* Offset applied to the virtual timer/counter */ u64 voffset; + /* Offset applied to the physical timer/counter */ + u64 poffset; }; struct arch_timer_context { -- GitLab From c605ee245097d02ed5933e63ac601a8571712457 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:45 +0100 Subject: [PATCH 1734/5631] KVM: arm64: timers: Allow physical offset without CNTPOFF_EL2 CNTPOFF_EL2 is awesome, but it is mostly vapourware, and no publicly available implementation has it. So for the common mortals, let's implement the emulated version of this thing. It means trapping accesses to the physical counter and timer, and emulate some of it as necessary. As for CNTPOFF_EL2, nobody sets the offset yet. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-6-maz@kernel.org --- arch/arm64/include/asm/sysreg.h | 2 + arch/arm64/kvm/arch_timer.c | 98 +++++++++++++++++++++++------- arch/arm64/kvm/hyp/nvhe/timer-sr.c | 18 ++++-- arch/arm64/kvm/sys_regs.c | 9 +++ 4 files changed, 98 insertions(+), 29 deletions(-) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 9e3ecba3c4e6..f8da9e1b0c11 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -388,6 +388,7 @@ #define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0) +#define SYS_CNTPCT_EL0 sys_reg(3, 3, 14, 0, 1) #define SYS_CNTPCTSS_EL0 sys_reg(3, 3, 14, 0, 5) #define SYS_CNTVCTSS_EL0 sys_reg(3, 3, 14, 0, 6) @@ -400,6 +401,7 @@ #define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0) #define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) +#define SYS_AARCH32_CNTPCT sys_reg(0, 0, 0, 14, 0) #define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) #define __PMEV_op2(n) ((n) & 0x7) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3118ea0a1b41..bb64a71ae193 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -458,6 +458,8 @@ static void timer_save_state(struct arch_timer_context *ctx) goto out; switch (index) { + u64 cval; + case TIMER_VTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL)); timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL)); @@ -485,7 +487,12 @@ static void timer_save_state(struct arch_timer_context *ctx) break; case TIMER_PTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); - timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL)); + cval = read_sysreg_el0(SYS_CNTP_CVAL); + + if (!has_cntpoff()) + cval -= timer_get_offset(ctx); + + timer_set_cval(ctx, cval); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTP_CTL); @@ -555,6 +562,8 @@ static void timer_restore_state(struct arch_timer_context *ctx) goto out; switch (index) { + u64 cval, offset; + case TIMER_VTIMER: set_cntvoff(timer_get_offset(ctx)); write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); @@ -562,8 +571,12 @@ static void timer_restore_state(struct arch_timer_context *ctx) write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; case TIMER_PTIMER: - set_cntpoff(timer_get_offset(ctx)); - write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL); + cval = timer_get_cval(ctx); + offset = timer_get_offset(ctx); + set_cntpoff(offset); + if (!has_cntpoff()) + cval += offset; + write_sysreg_el0(cval, SYS_CNTP_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); break; @@ -634,6 +647,61 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } +/* If _pred is true, set bit in _set, otherwise set it in _clr */ +#define assign_clear_set_bit(_pred, _bit, _clr, _set) \ + do { \ + if (_pred) \ + (_set) |= (_bit); \ + else \ + (_clr) |= (_bit); \ + } while (0) + +static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) +{ + bool tpt, tpc; + u64 clr, set; + + /* + * No trapping gets configured here with nVHE. See + * __timer_enable_traps(), which is where the stuff happens. + */ + if (!has_vhe()) + return; + + /* + * Our default policy is not to trap anything. As we progress + * within this function, reality kicks in and we start adding + * traps based on emulation requirements. + */ + tpt = tpc = false; + + /* + * We have two possibility to deal with a physical offset: + * + * - Either we have CNTPOFF (yay!) or the offset is 0: + * we let the guest freely access the HW + * + * - or neither of these condition apply: + * we trap accesses to the HW, but still use it + * after correcting the physical offset + */ + if (!has_cntpoff() && timer_get_offset(map->direct_ptimer)) + tpt = tpc = true; + + /* + * Now that we have collected our requirements, compute the + * trap and enable bits. + */ + set = 0; + clr = 0; + + assign_clear_set_bit(tpt, CNTHCTL_EL1PCEN << 10, set, clr); + assign_clear_set_bit(tpc, CNTHCTL_EL1PCTEN << 10, set, clr); + + /* This only happens on VHE, so use the CNTKCTL_EL1 accessor */ + sysreg_clear_set(cntkctl_el1, clr, set); +} + void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); @@ -657,9 +725,10 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) timer_restore_state(map.direct_vtimer); if (map.direct_ptimer) timer_restore_state(map.direct_ptimer); - if (map.emul_ptimer) timer_emulate(map.emul_ptimer); + + timer_set_traps(vcpu, &map); } bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu) @@ -1292,28 +1361,11 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) return 0; } -/* - * On VHE system, we only need to configure the EL2 timer trap register once, - * not for every world switch. - * The host kernel runs at EL2 with HCR_EL2.TGE == 1, - * and this makes those bits have no effect for the host kernel execution. - */ +/* If we have CNTPOFF, permanently set ECV to enable it */ void kvm_timer_init_vhe(void) { - /* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */ - u32 cnthctl_shift = 10; - u64 val; - - /* - * VHE systems allow the guest direct access to the EL1 physical - * timer/counter. - */ - val = read_sysreg(cnthctl_el2); - val |= (CNTHCTL_EL1PCEN << cnthctl_shift); - val |= (CNTHCTL_EL1PCTEN << cnthctl_shift); if (cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)) - val |= CNTHCTL_ECV; - write_sysreg(val, cnthctl_el2); + sysreg_clear_set(cntkctl_el1, 0, CNTHCTL_ECV); } static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c index 9072e71693ba..b185ac0dbd47 100644 --- a/arch/arm64/kvm/hyp/nvhe/timer-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c @@ -9,6 +9,7 @@ #include #include +#include void __kvm_timer_set_cntvoff(u64 cntvoff) { @@ -35,14 +36,19 @@ void __timer_disable_traps(struct kvm_vcpu *vcpu) */ void __timer_enable_traps(struct kvm_vcpu *vcpu) { - u64 val; + u64 clr = 0, set = 0; /* * Disallow physical timer access for the guest - * Physical counter access is allowed + * Physical counter access is allowed if no offset is enforced + * or running protected (we don't offset anything in this case). */ - val = read_sysreg(cnthctl_el2); - val &= ~CNTHCTL_EL1PCEN; - val |= CNTHCTL_EL1PCTEN; - write_sysreg(val, cnthctl_el2); + clr = CNTHCTL_EL1PCEN; + if (is_protected_kvm_enabled() || + !kern_hyp_va(vcpu->kvm)->arch.timer_data.poffset) + set |= CNTHCTL_EL1PCTEN; + else + clr |= CNTHCTL_EL1PCTEN; + + sysreg_clear_set(cnthctl_el2, clr, set); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 53749d3a0996..be7c2598e563 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1139,6 +1139,12 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, tmr = TIMER_PTIMER; treg = TIMER_REG_CVAL; break; + case SYS_CNTPCT_EL0: + case SYS_CNTPCTSS_EL0: + case SYS_AARCH32_CNTPCT: + tmr = TIMER_PTIMER; + treg = TIMER_REG_CNT; + break; default: print_sys_reg_msg(p, "%s", "Unhandled trapped timer register"); kvm_inject_undefined(vcpu); @@ -2075,6 +2081,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { AMU_AMEVTYPER1_EL0(14), AMU_AMEVTYPER1_EL0(15), + { SYS_DESC(SYS_CNTPCT_EL0), access_arch_timer }, + { SYS_DESC(SYS_CNTPCTSS_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer }, { SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer }, @@ -2525,6 +2533,7 @@ static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 0), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR0_EL1 }, { CP15_PMU_SYS_REG(DIRECT, 0, 0, 9, 0), .access = access_pmu_evcntr }, { Op1( 0), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI1R */ + { SYS_DESC(SYS_AARCH32_CNTPCT), access_arch_timer }, { Op1( 1), CRn( 0), CRm( 2), Op2( 0), access_vm_reg, NULL, TTBR1_EL1 }, { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ -- GitLab From 96906a9150a86a86b0464939625279b8e19f6e88 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:46 +0100 Subject: [PATCH 1735/5631] KVM: arm64: Expose {un,}lock_all_vcpus() to the rest of KVM Being able to lock/unlock all vcpus in one go is a feature that only the vgic has enjoyed so far. Let's be brave and expose it to the world. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-7-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 3 ++ arch/arm64/kvm/arm.c | 43 +++++++++++++++++++++++++++ arch/arm64/kvm/vgic/vgic-kvm-device.c | 38 ----------------------- arch/arm64/kvm/vgic/vgic.h | 3 -- 4 files changed, 46 insertions(+), 41 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bcd774d74f34..002a10cbade2 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -922,6 +922,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); int __init kvm_sys_reg_table_init(void); +bool lock_all_vcpus(struct kvm *kvm); +void unlock_all_vcpus(struct kvm *kvm); + /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3bd732eaf087..ae5110cc3bad 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1484,6 +1484,49 @@ long kvm_arch_vm_ioctl(struct file *filp, } } +/* unlocks vcpus from @vcpu_lock_idx and smaller */ +static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) +{ + struct kvm_vcpu *tmp_vcpu; + + for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { + tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); + mutex_unlock(&tmp_vcpu->mutex); + } +} + +void unlock_all_vcpus(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->lock); + + unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); +} + +/* Returns true if all vcpus were locked, false otherwise */ +bool lock_all_vcpus(struct kvm *kvm) +{ + struct kvm_vcpu *tmp_vcpu; + unsigned long c; + + lockdep_assert_held(&kvm->lock); + + /* + * Any time a vcpu is in an ioctl (including running), the + * core KVM code tries to grab the vcpu->mutex. + * + * By grabbing the vcpu->mutex of all VCPUs we ensure that no + * other VCPUs can fiddle with the state while we access it. + */ + kvm_for_each_vcpu(c, tmp_vcpu, kvm) { + if (!mutex_trylock(&tmp_vcpu->mutex)) { + unlock_vcpus(kvm, c - 1); + return false; + } + } + + return true; +} + static unsigned long nvhe_percpu_size(void) { return (unsigned long)CHOOSE_NVHE_SYM(__per_cpu_end) - diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index edeac2380591..04dd68835b3f 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -342,44 +342,6 @@ int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, return 0; } -/* unlocks vcpus from @vcpu_lock_idx and smaller */ -static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx) -{ - struct kvm_vcpu *tmp_vcpu; - - for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { - tmp_vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); - mutex_unlock(&tmp_vcpu->mutex); - } -} - -void unlock_all_vcpus(struct kvm *kvm) -{ - unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1); -} - -/* Returns true if all vcpus were locked, false otherwise */ -bool lock_all_vcpus(struct kvm *kvm) -{ - struct kvm_vcpu *tmp_vcpu; - unsigned long c; - - /* - * Any time a vcpu is run, vcpu_load is called which tries to grab the - * vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure - * that no other VCPUs are run and fiddle with the vgic state while we - * access it. - */ - kvm_for_each_vcpu(c, tmp_vcpu, kvm) { - if (!mutex_trylock(&tmp_vcpu->mutex)) { - unlock_vcpus(kvm, c - 1); - return false; - } - } - - return true; -} - /** * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state * diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 7f7f3c5ed85a..f9923beedd27 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -273,9 +273,6 @@ int vgic_init(struct kvm *kvm); void vgic_debug_init(struct kvm *kvm); void vgic_debug_destroy(struct kvm *kvm); -bool lock_all_vcpus(struct kvm *kvm); -void unlock_all_vcpus(struct kvm *kvm); - static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) { struct vgic_cpu *cpu_if = &vcpu->arch.vgic_cpu; -- GitLab From 30ec7997d175cd689fc61bfc4059f4d35b11858c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:47 +0100 Subject: [PATCH 1736/5631] KVM: arm64: timers: Allow userspace to set the global counter offset And this is the moment you have all been waiting for: setting the counter offset from userspace. We expose a brand new capability that reports the ability to set the offset for both the virtual and physical sides. In keeping with the architecture, the offset is expressed as a delta that is substracted from the physical counter value. Once this new API is used, there is no going back, and the counters cannot be written to to set the offsets implicitly (the writes are instead ignored). Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-8-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 4 +++ arch/arm64/include/uapi/asm/kvm.h | 9 ++++++ arch/arm64/kvm/arch_timer.c | 54 ++++++++++++++++++++++++++++--- arch/arm64/kvm/arm.c | 8 +++++ include/uapi/linux/kvm.h | 3 ++ 5 files changed, 73 insertions(+), 5 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 002a10cbade2..116233a390e9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -221,6 +221,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_EL1_32BIT 4 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 + /* VM counter offset */ +#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 6 unsigned long flags; @@ -1010,6 +1012,8 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); +int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, + struct kvm_arm_counter_offset *offset); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..12fb0d8a760a 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index bb64a71ae193..771504c79711 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -851,9 +851,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) ptimer->vcpu = vcpu; ptimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.poffset; - /* Synchronize cntvoff across all vtimers of a VM. */ - timer_set_offset(vtimer, kvm_phys_timer_read()); - timer_set_offset(ptimer, 0); + /* Synchronize offsets across timers of a VM if not already provided */ + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { + timer_set_offset(vtimer, kvm_phys_timer_read()); + timer_set_offset(ptimer, 0); + } hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; @@ -897,8 +899,11 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; case KVM_REG_ARM_TIMER_CNT: - timer = vcpu_vtimer(vcpu); - timer_set_offset(timer, kvm_phys_timer_read() - value); + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, + &vcpu->kvm->arch.flags)) { + timer = vcpu_vtimer(vcpu); + timer_set_offset(timer, kvm_phys_timer_read() - value); + } break; case KVM_REG_ARM_TIMER_CVAL: timer = vcpu_vtimer(vcpu); @@ -908,6 +913,13 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CTL, value); break; + case KVM_REG_ARM_PTIMER_CNT: + if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, + &vcpu->kvm->arch.flags)) { + timer = vcpu_ptimer(vcpu); + timer_set_offset(timer, kvm_phys_timer_read() - value); + } + break; case KVM_REG_ARM_PTIMER_CVAL: timer = vcpu_ptimer(vcpu); kvm_arm_timer_write(vcpu, timer, TIMER_REG_CVAL, value); @@ -1443,3 +1455,35 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } + +int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, + struct kvm_arm_counter_offset *offset) +{ + int ret = 0; + + if (offset->reserved) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (lock_all_vcpus(kvm)) { + set_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &kvm->arch.flags); + + /* + * If userspace decides to set the offset using this + * API rather than merely restoring the counter + * values, the offset applies to both the virtual and + * physical views. + */ + kvm->arch.timer_data.voffset = offset->counter_offset; + kvm->arch.timer_data.poffset = offset->counter_offset; + + unlock_all_vcpus(kvm); + } else { + ret = -EBUSY; + } + + mutex_unlock(&kvm->lock); + + return ret; +} diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ae5110cc3bad..1c8a4bbae684 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -220,6 +220,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_PTP_KVM: case KVM_CAP_ARM_SYSTEM_SUSPEND: + case KVM_CAP_COUNTER_OFFSET: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -1479,6 +1480,13 @@ long kvm_arch_vm_ioctl(struct file *filp, return -EFAULT; return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); } + case KVM_ARM_SET_COUNTER_OFFSET: { + struct kvm_arm_counter_offset offset; + + if (copy_from_user(&offset, argp, sizeof(offset))) + return -EFAULT; + return kvm_vm_ioctl_set_counter_offset(kvm, &offset); + } default: return -EINVAL; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..6a7e1a0ecf04 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1184,6 +1184,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1544,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- GitLab From 680232a94c1289aad25ffae02f2785823763b456 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:48 +0100 Subject: [PATCH 1737/5631] KVM: arm64: timers: Allow save/restoring of the physical timer Nothing like being 10 year late to a party! Now that userspace can set counter offsets, we can save/restore the physical timer as well! Nobody really cared so far, but you're welcome anyway. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-9-maz@kernel.org --- arch/arm64/kvm/guest.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07444fa22888..46e910819de6 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -590,11 +590,16 @@ static unsigned long num_core_regs(const struct kvm_vcpu *vcpu) return copy_core_reg_indices(vcpu, NULL); } -/** - * ARM64 versions of the TIMER registers, always available on arm64 - */ +static const u64 timer_reg_list[] = { + KVM_REG_ARM_TIMER_CTL, + KVM_REG_ARM_TIMER_CNT, + KVM_REG_ARM_TIMER_CVAL, + KVM_REG_ARM_PTIMER_CTL, + KVM_REG_ARM_PTIMER_CNT, + KVM_REG_ARM_PTIMER_CVAL, +}; -#define NUM_TIMER_REGS 3 +#define NUM_TIMER_REGS ARRAY_SIZE(timer_reg_list) static bool is_timer_reg(u64 index) { @@ -602,6 +607,9 @@ static bool is_timer_reg(u64 index) case KVM_REG_ARM_TIMER_CTL: case KVM_REG_ARM_TIMER_CNT: case KVM_REG_ARM_TIMER_CVAL: + case KVM_REG_ARM_PTIMER_CTL: + case KVM_REG_ARM_PTIMER_CNT: + case KVM_REG_ARM_PTIMER_CVAL: return true; } return false; @@ -609,14 +617,11 @@ static bool is_timer_reg(u64 index) static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { - if (put_user(KVM_REG_ARM_TIMER_CTL, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CNT, uindices)) - return -EFAULT; - uindices++; - if (put_user(KVM_REG_ARM_TIMER_CVAL, uindices)) - return -EFAULT; + for (int i = 0; i < NUM_TIMER_REGS; i++) { + if (put_user(timer_reg_list[i], uindices)) + return -EFAULT; + uindices++; + } return 0; } -- GitLab From 5591805d2c21b70838b723b71b8ff613de51cfff Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:49 +0100 Subject: [PATCH 1738/5631] KVM: arm64: timers: Rationalise per-vcpu timer init The way we initialise our timer contexts may be satisfactory for two timers, but will be getting pretty annoying with four. Cleanup the whole thing by removing the code duplication and getting rid of unused IRQ configuration elements. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-10-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 73 +++++++++++++++++++----------------- include/kvm/arm_arch_timer.h | 1 - 2 files changed, 39 insertions(+), 35 deletions(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 771504c79711..e46f04ed8f86 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -30,14 +30,9 @@ static u32 host_ptimer_irq_flags; static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); -static const struct kvm_irq_level default_ptimer_irq = { - .irq = 30, - .level = 1, -}; - -static const struct kvm_irq_level default_vtimer_irq = { - .irq = 27, - .level = 1, +static const u8 default_ppi[] = { + [TIMER_PTIMER] = 30, + [TIMER_VTIMER] = 27, }; static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); @@ -820,12 +815,14 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) * resets the timer to be disabled and unmasked and is compliant with * the ARMv7 architecture. */ - timer_set_ctl(vcpu_vtimer(vcpu), 0); - timer_set_ctl(vcpu_ptimer(vcpu), 0); + for (int i = 0; i < NR_KVM_TIMERS; i++) + timer_set_ctl(vcpu_get_timer(vcpu, i), 0); + if (timer->enabled) { - kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu)); - kvm_timer_update_irq(vcpu, false, vcpu_ptimer(vcpu)); + for (int i = 0; i < NR_KVM_TIMERS; i++) + kvm_timer_update_irq(vcpu, false, + vcpu_get_timer(vcpu, i)); if (irqchip_in_kernel(vcpu->kvm)) { kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq); @@ -840,39 +837,47 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) return 0; } +static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) +{ + struct arch_timer_context *ctxt = vcpu_get_timer(vcpu, timerid); + struct kvm *kvm = vcpu->kvm; + + ctxt->vcpu = vcpu; + + if (timerid == TIMER_VTIMER) + ctxt->offset.vm_offset = &kvm->arch.timer_data.voffset; + else + ctxt->offset.vm_offset = &kvm->arch.timer_data.poffset; + + hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + ctxt->hrtimer.function = kvm_hrtimer_expire; + ctxt->irq.irq = default_ppi[timerid]; + + switch (timerid) { + case TIMER_PTIMER: + ctxt->host_timer_irq = host_ptimer_irq; + break; + case TIMER_VTIMER: + ctxt->host_timer_irq = host_vtimer_irq; + break; + } +} + void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - vtimer->vcpu = vcpu; - vtimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.voffset; - ptimer->vcpu = vcpu; - ptimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.poffset; + for (int i = 0; i < NR_KVM_TIMERS; i++) + timer_context_init(vcpu, i); /* Synchronize offsets across timers of a VM if not already provided */ if (!test_bit(KVM_ARCH_FLAG_VM_COUNTER_OFFSET, &vcpu->kvm->arch.flags)) { - timer_set_offset(vtimer, kvm_phys_timer_read()); - timer_set_offset(ptimer, 0); + timer_set_offset(vcpu_vtimer(vcpu), kvm_phys_timer_read()); + timer_set_offset(vcpu_ptimer(vcpu), 0); } hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; - - hrtimer_init(&vtimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - hrtimer_init(&ptimer->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - vtimer->hrtimer.function = kvm_hrtimer_expire; - ptimer->hrtimer.function = kvm_hrtimer_expire; - - vtimer->irq.irq = default_vtimer_irq.irq; - ptimer->irq.irq = default_ptimer_irq.irq; - - vtimer->host_timer_irq = host_vtimer_irq; - ptimer->host_timer_irq = host_ptimer_irq; - - vtimer->host_timer_irq_flags = host_vtimer_irq_flags; - ptimer->host_timer_irq_flags = host_ptimer_irq_flags; } void kvm_timer_cpu_up(void) diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 2dd0fd2406fb..c746ef64220b 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -59,7 +59,6 @@ struct arch_timer_context { /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; - u32 host_timer_irq_flags; }; struct timer_map { -- GitLab From 33c549460ef9119eb115484e81f54521122341db Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:50 +0100 Subject: [PATCH 1739/5631] KVM: arm64: timers: Abstract per-timer IRQ access As we are about to move the location of the per-timer IRQ into the VM structure, abstract the location of the IRQ behind an accessor. This will make the repainting sligntly less painful. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-11-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 38 ++++++++++++++++++------------------ include/kvm/arm_arch_timer.h | 2 ++ 2 files changed, 21 insertions(+), 19 deletions(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index e46f04ed8f86..d08d8c2fc30d 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -392,12 +392,12 @@ static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, int ret; timer_ctx->irq.level = new_level; - trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq, + trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); if (!userspace_irqchip(vcpu->kvm)) { ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id, - timer_ctx->irq.irq, + timer_irq(timer_ctx), timer_ctx->irq.level, timer_ctx); WARN_ON(ret); @@ -607,7 +607,7 @@ static void kvm_timer_vcpu_load_gic(struct arch_timer_context *ctx) kvm_timer_update_irq(ctx->vcpu, kvm_timer_should_fire(ctx), ctx); if (irqchip_in_kernel(vcpu->kvm)) - phys_active = kvm_vgic_map_is_active(vcpu, ctx->irq.irq); + phys_active = kvm_vgic_map_is_active(vcpu, timer_irq(ctx)); phys_active |= ctx->irq.level; @@ -825,9 +825,9 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) vcpu_get_timer(vcpu, i)); if (irqchip_in_kernel(vcpu->kvm)) { - kvm_vgic_reset_mapped_irq(vcpu, map.direct_vtimer->irq.irq); + kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_vtimer)); if (map.direct_ptimer) - kvm_vgic_reset_mapped_irq(vcpu, map.direct_ptimer->irq.irq); + kvm_vgic_reset_mapped_irq(vcpu, timer_irq(map.direct_ptimer)); } } @@ -851,7 +851,7 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ctxt->hrtimer.function = kvm_hrtimer_expire; - ctxt->irq.irq = default_ppi[timerid]; + timer_irq(ctxt) = default_ppi[timerid]; switch (timerid) { case TIMER_PTIMER: @@ -1295,19 +1295,19 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) int vtimer_irq, ptimer_irq, ret; unsigned long i; - vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; + vtimer_irq = timer_irq(vcpu_vtimer(vcpu)); ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); if (ret) return false; - ptimer_irq = vcpu_ptimer(vcpu)->irq.irq; + ptimer_irq = timer_irq(vcpu_ptimer(vcpu)); ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu)); if (ret) return false; kvm_for_each_vcpu(i, vcpu, vcpu->kvm) { - if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq || - vcpu_ptimer(vcpu)->irq.irq != ptimer_irq) + if (timer_irq(vcpu_vtimer(vcpu)) != vtimer_irq || + timer_irq(vcpu_ptimer(vcpu)) != ptimer_irq) return false; } @@ -1322,9 +1322,9 @@ bool kvm_arch_timer_get_input_level(int vintid) if (WARN(!vcpu, "No vcpu context!\n")) return false; - if (vintid == vcpu_vtimer(vcpu)->irq.irq) + if (vintid == timer_irq(vcpu_vtimer(vcpu))) timer = vcpu_vtimer(vcpu); - else if (vintid == vcpu_ptimer(vcpu)->irq.irq) + else if (vintid == timer_irq(vcpu_ptimer(vcpu))) timer = vcpu_ptimer(vcpu); else BUG(); @@ -1358,7 +1358,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) ret = kvm_vgic_map_phys_irq(vcpu, map.direct_vtimer->host_timer_irq, - map.direct_vtimer->irq.irq, + timer_irq(map.direct_vtimer), &arch_timer_irq_ops); if (ret) return ret; @@ -1366,7 +1366,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) if (map.direct_ptimer) { ret = kvm_vgic_map_phys_irq(vcpu, map.direct_ptimer->host_timer_irq, - map.direct_ptimer->irq.irq, + timer_irq(map.direct_ptimer), &arch_timer_irq_ops); } @@ -1391,8 +1391,8 @@ static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { - vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; - vcpu_ptimer(vcpu)->irq.irq = ptimer_irq; + timer_irq(vcpu_vtimer(vcpu)) = vtimer_irq; + timer_irq(vcpu_ptimer(vcpu)) = ptimer_irq; } } @@ -1417,10 +1417,10 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: - set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq); + set_timer_irqs(vcpu->kvm, irq, timer_irq(ptimer)); break; case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: - set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq); + set_timer_irqs(vcpu->kvm, timer_irq(vtimer), irq); break; default: return -ENXIO; @@ -1446,7 +1446,7 @@ int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) return -ENXIO; } - irq = timer->irq.irq; + irq = timer_irq(timer); return put_user(irq, uaddr); } diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index c746ef64220b..27cada09f588 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -109,6 +109,8 @@ bool kvm_arch_timer_get_input_level(int vintid); #define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) +#define timer_irq(ctx) ((ctx)->irq.irq) + u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg); -- GitLab From 8a5eb2d210807e7dbe9ece7075533014cf4b9c27 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:51 +0100 Subject: [PATCH 1740/5631] KVM: arm64: timers: Move the timer IRQs into arch_timer_vm_data Having the timer IRQs duplicated into each vcpu isn't great, and becomes absolutely awful with NV. So let's move these into the per-VM arch_timer_vm_data structure. This simplifies a lot of code, but requires us to introduce a mutex so that we can reason about userspace trying to change an interrupt number while another vcpu is running, something that wasn't really well handled so far. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-12-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 2 + arch/arm64/kvm/arch_timer.c | 108 ++++++++++++++++++------------ arch/arm64/kvm/arm.c | 2 + include/kvm/arm_arch_timer.h | 18 +++-- 4 files changed, 82 insertions(+), 48 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 116233a390e9..1280154c9ef3 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -223,6 +223,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 /* VM counter offset */ #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 6 + /* Timer PPIs made immutable */ +#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 7 unsigned long flags; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index d08d8c2fc30d..1d811735e05f 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -851,7 +851,6 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) hrtimer_init(&ctxt->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); ctxt->hrtimer.function = kvm_hrtimer_expire; - timer_irq(ctxt) = default_ppi[timerid]; switch (timerid) { case TIMER_PTIMER: @@ -880,6 +879,13 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) timer->bg_timer.function = kvm_bg_timer_expire; } +void kvm_timer_init_vm(struct kvm *kvm) +{ + mutex_init(&kvm->arch.timer_data.lock); + for (int i = 0; i < NR_KVM_TIMERS; i++) + kvm->arch.timer_data.ppi[i] = default_ppi[i]; +} + void kvm_timer_cpu_up(void) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); @@ -1292,44 +1298,56 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { - int vtimer_irq, ptimer_irq, ret; - unsigned long i; + u32 ppis = 0; + bool valid; - vtimer_irq = timer_irq(vcpu_vtimer(vcpu)); - ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); - if (ret) - return false; + mutex_lock(&vcpu->kvm->arch.timer_data.lock); - ptimer_irq = timer_irq(vcpu_ptimer(vcpu)); - ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu)); - if (ret) - return false; + for (int i = 0; i < NR_KVM_TIMERS; i++) { + struct arch_timer_context *ctx; + int irq; - kvm_for_each_vcpu(i, vcpu, vcpu->kvm) { - if (timer_irq(vcpu_vtimer(vcpu)) != vtimer_irq || - timer_irq(vcpu_ptimer(vcpu)) != ptimer_irq) - return false; + ctx = vcpu_get_timer(vcpu, i); + irq = timer_irq(ctx); + if (kvm_vgic_set_owner(vcpu, irq, ctx)) + break; + + /* + * We know by construction that we only have PPIs, so + * all values are less than 32. + */ + ppis |= BIT(irq); } - return true; + valid = hweight32(ppis) == NR_KVM_TIMERS; + + if (valid) + set_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags); + + mutex_unlock(&vcpu->kvm->arch.timer_data.lock); + + return valid; } bool kvm_arch_timer_get_input_level(int vintid) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - struct arch_timer_context *timer; if (WARN(!vcpu, "No vcpu context!\n")) return false; - if (vintid == timer_irq(vcpu_vtimer(vcpu))) - timer = vcpu_vtimer(vcpu); - else if (vintid == timer_irq(vcpu_ptimer(vcpu))) - timer = vcpu_ptimer(vcpu); - else - BUG(); + for (int i = 0; i < NR_KVM_TIMERS; i++) { + struct arch_timer_context *ctx; + + ctx = vcpu_get_timer(vcpu, i); + if (timer_irq(ctx) == vintid) + return kvm_timer_should_fire(ctx); + } - return kvm_timer_should_fire(timer); + /* A timer IRQ has fired, but no matching timer was found? */ + WARN_RATELIMIT(1, "timer INTID%d unknown\n", vintid); + + return false; } int kvm_timer_enable(struct kvm_vcpu *vcpu) @@ -1385,23 +1403,10 @@ void kvm_timer_init_vhe(void) sysreg_clear_set(cntkctl_el1, 0, CNTHCTL_ECV); } -static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) -{ - struct kvm_vcpu *vcpu; - unsigned long i; - - kvm_for_each_vcpu(i, vcpu, kvm) { - timer_irq(vcpu_vtimer(vcpu)) = vtimer_irq; - timer_irq(vcpu_ptimer(vcpu)) = ptimer_irq; - } -} - int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { int __user *uaddr = (int __user *)(long)attr->addr; - struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); - struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); - int irq; + int irq, idx, ret = 0; if (!irqchip_in_kernel(vcpu->kvm)) return -EINVAL; @@ -1412,21 +1417,36 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) if (!(irq_is_ppi(irq))) return -EINVAL; - if (vcpu->arch.timer_cpu.enabled) - return -EBUSY; + mutex_lock(&vcpu->kvm->arch.timer_data.lock); + + if (test_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, + &vcpu->kvm->arch.flags)) { + ret = -EBUSY; + goto out; + } switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: - set_timer_irqs(vcpu->kvm, irq, timer_irq(ptimer)); + idx = TIMER_VTIMER; break; case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: - set_timer_irqs(vcpu->kvm, timer_irq(vtimer), irq); + idx = TIMER_PTIMER; break; default: - return -ENXIO; + ret = -ENXIO; + goto out; } - return 0; + /* + * We cannot validate the IRQ unicity before we run, so take it at + * face value. The verdict will be given on first vcpu run, for each + * vcpu. Yes this is late. Blame it on the stupid API. + */ + vcpu->kvm->arch.timer_data.ppi[idx] = irq; + +out: + mutex_unlock(&vcpu->kvm->arch.timer_data.lock); + return ret; } int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1c8a4bbae684..4c5e9dfbf83a 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -148,6 +148,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_vgic_early_init(kvm); + kvm_timer_init_vm(kvm); + /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->max_vcpus = kvm_arm_default_max_vcpus(); diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 27cada09f588..f093ea9f540d 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -36,14 +36,16 @@ struct arch_timer_vm_data { u64 voffset; /* Offset applied to the physical timer/counter */ u64 poffset; + + struct mutex lock; + + /* The PPI for each timer, global to the VM */ + u8 ppi[NR_KVM_TIMERS]; }; struct arch_timer_context { struct kvm_vcpu *vcpu; - /* Timer IRQ */ - struct kvm_irq_level irq; - /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; u64 ns_frac; @@ -57,6 +59,11 @@ struct arch_timer_context { */ bool loaded; + /* Output level of the timer IRQ */ + struct { + bool level; + } irq; + /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; }; @@ -86,6 +93,8 @@ bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); void kvm_timer_update_run(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); +void kvm_timer_init_vm(struct kvm *kvm); + u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); @@ -109,7 +118,8 @@ bool kvm_arch_timer_get_input_level(int vintid); #define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) -#define timer_irq(ctx) ((ctx)->irq.irq) +#define timer_vm_data(ctx) (&(ctx)->vcpu->kvm->arch.timer_data) +#define timer_irq(ctx) (timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)]) u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, -- GitLab From 1a6511eb8430533920559c5f01f487f4901081cd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:52 +0100 Subject: [PATCH 1741/5631] KVM: arm64: Elide kern_hyp_va() in VHE-specific parts of the hypervisor For VHE-specific hypervisor code, kern_hyp_va() is a NOP. Actually, it is a whole range of NOPs. It'd be much better if this code simply didn't exist. Let's just do that. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-13-maz@kernel.org --- arch/arm64/include/asm/kvm_mmu.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 083cc47dca08..27e63c111f78 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -63,6 +63,7 @@ * specific registers encoded in the instructions). */ .macro kern_hyp_va reg +#ifndef __KVM_VHE_HYPERVISOR__ alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask and \reg, \reg, #1 /* mask with va_mask */ ror \reg, \reg, #1 /* rotate to the first tag bit */ @@ -70,6 +71,7 @@ alternative_cb ARM64_ALWAYS_SYSTEM, kvm_update_va_mask add \reg, \reg, #0, lsl 12 /* insert the top 12 bits of the tag */ ror \reg, \reg, #63 /* rotate back */ alternative_cb_end +#endif .endm /* @@ -127,6 +129,7 @@ void kvm_apply_hyp_relocations(void); static __always_inline unsigned long __kern_hyp_va(unsigned long v) { +#ifndef __KVM_VHE_HYPERVISOR__ asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" "ror %0, %0, #1\n" "add %0, %0, #0\n" @@ -135,6 +138,7 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v) ARM64_ALWAYS_SYSTEM, kvm_update_va_mask) : "+r" (v)); +#endif return v; } -- GitLab From e9adde432bf7371f1c83f67d9f8d75b95810f124 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:53 +0100 Subject: [PATCH 1742/5631] KVM: arm64: timers: Fast-track CNTPCT_EL0 trap handling Now that it is likely that CNTPCT_EL0 accesses will trap, fast-track the emulation of the counter read which doesn't need more that a simple offsetting. One day, we'll have CNTPOFF everywhere. One day. Suggested-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-14-maz@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 36 +++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 07d37ff88a3f..9954368f639d 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -326,6 +327,38 @@ static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } +static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *ctxt; + u32 sysreg; + u64 val; + + /* + * We only get here for 64bit guests, 32bit guests will hit + * the long and winding road all the way to the standard + * handling. Yes, it sucks to be irrelevant. + */ + sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + + switch (sysreg) { + case SYS_CNTPCT_EL0: + case SYS_CNTPCTSS_EL0: + ctxt = vcpu_ptimer(vcpu); + break; + default: + return false; + } + + val = arch_timer_read_cntpct_el0(); + + if (ctxt->offset.vm_offset) + val -= *kern_hyp_va(ctxt->offset.vm_offset); + + vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); + __kvm_skip_instr(vcpu); + return true; +} + static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && @@ -339,6 +372,9 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu))) return kvm_hyp_handle_ptrauth(vcpu, exit_code); + if (kvm_hyp_handle_cntpct(vcpu)) + return true; + return false; } -- GitLab From 476fcd4b7bb54ac959b683f30d0cf305c3e11f3c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:54 +0100 Subject: [PATCH 1743/5631] KVM: arm64: timers: Abstract the number of valid timers per vcpu We so far have a pretty fixed number of timers to take care of. This is about to change as NV brings another two into the picture, and we must be careful not to try and emulate non-valid timers in a given VM. For this, abstract the number of timers for a given vcpu behind an accessor, which helpfully returns a constant for now. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-15-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 1d811735e05f..d3a7902269c1 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -52,6 +52,11 @@ static bool has_cntpoff(void) return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); } +static int nr_timers(struct kvm_vcpu *vcpu) +{ + return NR_KVM_TIMERS; +} + u32 timer_get_ctl(struct arch_timer_context *ctxt) { struct kvm_vcpu *vcpu = ctxt->vcpu; @@ -255,7 +260,7 @@ static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu) u64 min_delta = ULLONG_MAX; int i; - for (i = 0; i < NR_KVM_TIMERS; i++) { + for (i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx = &vcpu->arch.timer_cpu.timers[i]; WARN(ctx->loaded, "timer %d loaded\n", i); @@ -815,12 +820,12 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) * resets the timer to be disabled and unmasked and is compliant with * the ARMv7 architecture. */ - for (int i = 0; i < NR_KVM_TIMERS; i++) + for (int i = 0; i < nr_timers(vcpu); i++) timer_set_ctl(vcpu_get_timer(vcpu, i), 0); if (timer->enabled) { - for (int i = 0; i < NR_KVM_TIMERS; i++) + for (int i = 0; i < nr_timers(vcpu); i++) kvm_timer_update_irq(vcpu, false, vcpu_get_timer(vcpu, i)); @@ -1303,7 +1308,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) mutex_lock(&vcpu->kvm->arch.timer_data.lock); - for (int i = 0; i < NR_KVM_TIMERS; i++) { + for (int i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx; int irq; @@ -1319,7 +1324,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) ppis |= BIT(irq); } - valid = hweight32(ppis) == NR_KVM_TIMERS; + valid = hweight32(ppis) == nr_timers(vcpu); if (valid) set_bit(KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE, &vcpu->kvm->arch.flags); @@ -1336,7 +1341,7 @@ bool kvm_arch_timer_get_input_level(int vintid) if (WARN(!vcpu, "No vcpu context!\n")) return false; - for (int i = 0; i < NR_KVM_TIMERS; i++) { + for (int i = 0; i < nr_timers(vcpu); i++) { struct arch_timer_context *ctx; ctx = vcpu_get_timer(vcpu, i); -- GitLab From 1935d34afaebe01ddb75bfaa62fb7fe957ddc210 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:55 +0100 Subject: [PATCH 1744/5631] KVM: arm64: Document KVM_ARM_SET_CNT_OFFSETS and co Add some basic documentation on the effects of KVM_ARM_SET_CNT_OFFSETS. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-16-maz@kernel.org --- Documentation/virt/kvm/api.rst | 38 ++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 62de0768d6aa..192adcb61add 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6029,6 +6029,44 @@ delivery must be provided via the "reg_aen" struct. The "pad" and "reserved" fields may be used for future extensions and should be set to 0s by userspace. +4.138 KVM_ARM_SET_COUNTER_OFFSET +-------------------------------- + +:Capability: KVM_CAP_COUNTER_OFFSET +:Architectures: arm64 +:Type: vm ioctl +:Parameters: struct kvm_arm_counter_offset (in) +:Returns: 0 on success, < 0 on error + +This capability indicates that userspace is able to apply a single VM-wide +offset to both the virtual and physical counters as viewed by the guest +using the KVM_ARM_SET_CNT_OFFSET ioctl and the following data structure: + +:: + + struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; + }; + +The offset describes a number of counter cycles that are subtracted from +both virtual and physical counter views (similar to the effects of the +CNTVOFF_EL2 and CNTPOFF_EL2 system registers, but only global). The offset +always applies to all vcpus (already created or created after this ioctl) +for this VM. + +It is userspace's responsibility to compute the offset based, for example, +on previous values of the guest counters. + +Any value other than 0 for the "reserved" field may result in an error +(-EINVAL) being returned. This ioctl can also return -EBUSY if any vcpu +ioctl is issued concurrently. + +Note that using this ioctl results in KVM ignoring subsequent userspace +writes to the CNTVCT_EL0 and CNTPCT_EL0 registers using the SET_ONE_REG +interface. No error will be returned, but the resulting offset will not be +applied. + 5. The kvm_run structure ======================== -- GitLab From 1e0eec09d43a55125ff80e40b2d6e2f369a338b9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:56 +0100 Subject: [PATCH 1745/5631] KVM: arm64: nv: timers: Add a per-timer, per-vcpu offset Being able to set a global offset isn't enough. With NV, we also need to a per-vcpu, per-timer offset (for example, CNTVCT_EL0 being offset by CNTVOFF_EL2). Use a similar method as the VM-wide offset to have a timer point to the shadow register that contains the offset value. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-17-maz@kernel.org --- arch/arm64/kvm/arch_timer.c | 13 ++++++++++--- arch/arm64/kvm/hyp/include/hyp/switch.h | 2 ++ include/kvm/arm_arch_timer.h | 5 +++++ 3 files changed, 17 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index d3a7902269c1..b87bf182af33 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -89,10 +89,17 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) static u64 timer_get_offset(struct arch_timer_context *ctxt) { - if (ctxt && ctxt->offset.vm_offset) - return *ctxt->offset.vm_offset; + u64 offset = 0; - return 0; + if (!ctxt) + return 0; + + if (ctxt->offset.vm_offset) + offset += *ctxt->offset.vm_offset; + if (ctxt->offset.vcpu_offset) + offset += *ctxt->offset.vcpu_offset; + + return offset; } static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 9954368f639d..d07cbc313889 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -353,6 +353,8 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) if (ctxt->offset.vm_offset) val -= *kern_hyp_va(ctxt->offset.vm_offset); + if (ctxt->offset.vcpu_offset) + val -= *kern_hyp_va(ctxt->offset.vcpu_offset); vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); __kvm_skip_instr(vcpu); diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index f093ea9f540d..209da0c2ac9f 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -29,6 +29,11 @@ struct arch_timer_offset { * structure. If NULL, assume a zero offset. */ u64 *vm_offset; + /* + * If set, pointer to one of the offsets in the vcpu's sysreg + * array. If NULL, assume a zero offset. + */ + u64 *vcpu_offset; }; struct arch_timer_vm_data { -- GitLab From 81dc9504a7006b484cfcf074796094ee526b0c45 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:57 +0100 Subject: [PATCH 1746/5631] KVM: arm64: nv: timers: Support hyp timer emulation Emulating EL2 also means emulating the EL2 timers. To do so, we expand our timer framework to deal with at most 4 timers. At any given time, two timers are using the HW timers, and the two others are purely emulated. The role of deciding which is which at any given time is left to a mapping function which is called every time we need to make such a decision. Reviewed-by: Colton Lewis Co-developed-by: Christoffer Dall Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-18-maz@kernel.org --- arch/arm64/include/asm/kvm_host.h | 4 + arch/arm64/include/uapi/asm/kvm.h | 2 + arch/arm64/kvm/arch_timer.c | 180 ++++++++++++++++++++++-- arch/arm64/kvm/hyp/include/hyp/switch.h | 15 ++ arch/arm64/kvm/trace_arm.h | 6 +- arch/arm64/kvm/vgic/vgic.c | 15 ++ include/kvm/arm_arch_timer.h | 9 +- include/kvm/arm_vgic.h | 1 + 8 files changed, 220 insertions(+), 12 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 1280154c9ef3..633a7c0750bb 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -369,6 +369,10 @@ enum vcpu_sysreg { TPIDR_EL2, /* EL2 Software Thread ID Register */ CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ SP_EL2, /* EL2 Stack Pointer */ + CNTHP_CTL_EL2, + CNTHP_CVAL_EL2, + CNTHV_CTL_EL2, + CNTHV_CVAL_EL2, NR_SYS_REGS /* Nothing after this line! */ }; diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 12fb0d8a760a..0921f366c49f 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -420,6 +420,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index b87bf182af33..c5c8cc3c25ae 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -33,6 +34,8 @@ static DEFINE_STATIC_KEY_FALSE(has_gic_active_state); static const u8 default_ppi[] = { [TIMER_PTIMER] = 30, [TIMER_VTIMER] = 27, + [TIMER_HPTIMER] = 26, + [TIMER_HVTIMER] = 28, }; static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx); @@ -46,6 +49,11 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg); +static bool kvm_arch_timer_get_input_level(int vintid); + +static struct irq_ops arch_timer_irq_ops = { + .get_input_level = kvm_arch_timer_get_input_level, +}; static bool has_cntpoff(void) { @@ -54,6 +62,9 @@ static bool has_cntpoff(void) static int nr_timers(struct kvm_vcpu *vcpu) { + if (!vcpu_has_nv(vcpu)) + return NR_KVM_EL0_TIMERS; + return NR_KVM_TIMERS; } @@ -66,6 +77,10 @@ u32 timer_get_ctl(struct arch_timer_context *ctxt) return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); case TIMER_PTIMER: return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); + case TIMER_HVTIMER: + return __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2); + case TIMER_HPTIMER: + return __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2); default: WARN_ON(1); return 0; @@ -81,6 +96,10 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); case TIMER_PTIMER: return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + case TIMER_HVTIMER: + return __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2); + case TIMER_HPTIMER: + return __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); default: WARN_ON(1); return 0; @@ -113,6 +132,12 @@ static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) case TIMER_PTIMER: __vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl; break; + case TIMER_HVTIMER: + __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl; + break; + case TIMER_HPTIMER: + __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl; + break; default: WARN_ON(1); } @@ -129,6 +154,12 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval) case TIMER_PTIMER: __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval; break; + case TIMER_HVTIMER: + __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval; + break; + case TIMER_HPTIMER: + __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval; + break; default: WARN_ON(1); } @@ -151,13 +182,27 @@ u64 kvm_phys_timer_read(void) static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) { - if (has_vhe()) { + if (vcpu_has_nv(vcpu)) { + if (is_hyp_ctxt(vcpu)) { + map->direct_vtimer = vcpu_hvtimer(vcpu); + map->direct_ptimer = vcpu_hptimer(vcpu); + map->emul_vtimer = vcpu_vtimer(vcpu); + map->emul_ptimer = vcpu_ptimer(vcpu); + } else { + map->direct_vtimer = vcpu_vtimer(vcpu); + map->direct_ptimer = vcpu_ptimer(vcpu); + map->emul_vtimer = vcpu_hvtimer(vcpu); + map->emul_ptimer = vcpu_hptimer(vcpu); + } + } else if (has_vhe()) { map->direct_vtimer = vcpu_vtimer(vcpu); map->direct_ptimer = vcpu_ptimer(vcpu); + map->emul_vtimer = NULL; map->emul_ptimer = NULL; } else { map->direct_vtimer = vcpu_vtimer(vcpu); map->direct_ptimer = NULL; + map->emul_vtimer = NULL; map->emul_ptimer = vcpu_ptimer(vcpu); } @@ -252,8 +297,11 @@ static bool vcpu_has_wfit_active(struct kvm_vcpu *vcpu) static u64 wfit_delay_ns(struct kvm_vcpu *vcpu) { - struct arch_timer_context *ctx = vcpu_vtimer(vcpu); u64 val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + struct arch_timer_context *ctx; + + ctx = (vcpu_has_nv(vcpu) && is_hyp_ctxt(vcpu)) ? vcpu_hvtimer(vcpu) + : vcpu_vtimer(vcpu); return kvm_counter_compute_delta(ctx, val); } @@ -350,9 +398,11 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) switch (index) { case TIMER_VTIMER: + case TIMER_HVTIMER: cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); break; case TIMER_PTIMER: + case TIMER_HPTIMER: cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); break; case NR_KVM_TIMERS: @@ -468,6 +518,7 @@ static void timer_save_state(struct arch_timer_context *ctx) u64 cval; case TIMER_VTIMER: + case TIMER_HVTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL)); timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL)); @@ -493,6 +544,7 @@ static void timer_save_state(struct arch_timer_context *ctx) set_cntvoff(0); break; case TIMER_PTIMER: + case TIMER_HPTIMER: timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); cval = read_sysreg_el0(SYS_CNTP_CVAL); @@ -536,6 +588,7 @@ static void kvm_timer_blocking(struct kvm_vcpu *vcpu) */ if (!kvm_timer_irq_can_fire(map.direct_vtimer) && !kvm_timer_irq_can_fire(map.direct_ptimer) && + !kvm_timer_irq_can_fire(map.emul_vtimer) && !kvm_timer_irq_can_fire(map.emul_ptimer) && !vcpu_has_wfit_active(vcpu)) return; @@ -572,12 +625,14 @@ static void timer_restore_state(struct arch_timer_context *ctx) u64 cval, offset; case TIMER_VTIMER: + case TIMER_HVTIMER: set_cntvoff(timer_get_offset(ctx)); write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; case TIMER_PTIMER: + case TIMER_HPTIMER: cval = timer_get_cval(ctx); offset = timer_get_offset(ctx); set_cntpoff(offset); @@ -663,6 +718,57 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu) (_clr) |= (_bit); \ } while (0) +static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, + struct timer_map *map) +{ + int hw, ret; + + if (!irqchip_in_kernel(vcpu->kvm)) + return; + + /* + * We only ever unmap the vtimer irq on a VHE system that runs nested + * virtualization, in which case we have both a valid emul_vtimer, + * emul_ptimer, direct_vtimer, and direct_ptimer. + * + * Since this is called from kvm_timer_vcpu_load(), a change between + * vEL2 and vEL1/0 will have just happened, and the timer_map will + * represent this, and therefore we switch the emul/direct mappings + * below. + */ + hw = kvm_vgic_get_map(vcpu, timer_irq(map->direct_vtimer)); + if (hw < 0) { + kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_vtimer)); + kvm_vgic_unmap_phys_irq(vcpu, timer_irq(map->emul_ptimer)); + + ret = kvm_vgic_map_phys_irq(vcpu, + map->direct_vtimer->host_timer_irq, + timer_irq(map->direct_vtimer), + &arch_timer_irq_ops); + WARN_ON_ONCE(ret); + ret = kvm_vgic_map_phys_irq(vcpu, + map->direct_ptimer->host_timer_irq, + timer_irq(map->direct_ptimer), + &arch_timer_irq_ops); + WARN_ON_ONCE(ret); + + /* + * The virtual offset behaviour is "interresting", as it + * always applies when HCR_EL2.E2H==0, but only when + * accessed from EL1 when HCR_EL2.E2H==1. So make sure we + * track E2H when putting the HV timer in "direct" mode. + */ + if (map->direct_vtimer == vcpu_hvtimer(vcpu)) { + struct arch_timer_offset *offs = &map->direct_vtimer->offset; + + if (vcpu_el2_e2h_is_set(vcpu)) + offs->vcpu_offset = NULL; + else + offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2); + } + } +} + static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) { bool tpt, tpc; @@ -695,6 +801,22 @@ static void timer_set_traps(struct kvm_vcpu *vcpu, struct timer_map *map) if (!has_cntpoff() && timer_get_offset(map->direct_ptimer)) tpt = tpc = true; + /* + * Apply the enable bits that the guest hypervisor has requested for + * its own guest. We can only add traps that wouldn't have been set + * above. + */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { + u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); + + /* Use the VHE format for mental sanity */ + if (!vcpu_el2_e2h_is_set(vcpu)) + val = (val & (CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN)) << 10; + + tpt |= !(val & (CNTHCTL_EL1PCEN << 10)); + tpc |= !(val & (CNTHCTL_EL1PCTEN << 10)); + } + /* * Now that we have collected our requirements, compute the * trap and enable bits. @@ -720,6 +842,9 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) get_timer_map(vcpu, &map); if (static_branch_likely(&has_gic_active_state)) { + if (vcpu_has_nv(vcpu)) + kvm_timer_vcpu_load_nested_switch(vcpu, &map); + kvm_timer_vcpu_load_gic(map.direct_vtimer); if (map.direct_ptimer) kvm_timer_vcpu_load_gic(map.direct_ptimer); @@ -732,6 +857,8 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) timer_restore_state(map.direct_vtimer); if (map.direct_ptimer) timer_restore_state(map.direct_ptimer); + if (map.emul_vtimer) + timer_emulate(map.emul_vtimer); if (map.emul_ptimer) timer_emulate(map.emul_ptimer); @@ -778,6 +905,8 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) * In any case, we re-schedule the hrtimer for the physical timer when * coming back to the VCPU thread in kvm_timer_vcpu_load(). */ + if (map.emul_vtimer) + soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); @@ -830,6 +959,17 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) for (int i = 0; i < nr_timers(vcpu); i++) timer_set_ctl(vcpu_get_timer(vcpu, i), 0); + /* + * A vcpu running at EL2 is in charge of the offset applied to + * the virtual timer, so use the physical VM offset, and point + * the vcpu offset to CNTVOFF_EL2. + */ + if (vcpu_has_nv(vcpu)) { + struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset; + + offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2); + offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset; + } if (timer->enabled) { for (int i = 0; i < nr_timers(vcpu); i++) @@ -843,6 +983,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) } } + if (map.emul_vtimer) + soft_timer_cancel(&map.emul_vtimer->hrtimer); if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); @@ -866,9 +1008,11 @@ static void timer_context_init(struct kvm_vcpu *vcpu, int timerid) switch (timerid) { case TIMER_PTIMER: + case TIMER_HPTIMER: ctxt->host_timer_irq = host_ptimer_irq; break; case TIMER_VTIMER: + case TIMER_HVTIMER: ctxt->host_timer_irq = host_vtimer_irq; break; } @@ -1020,6 +1164,10 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, val = kvm_phys_timer_read() - timer_get_offset(timer); break; + case TIMER_REG_VOFF: + val = *timer->offset.vcpu_offset; + break; + default: BUG(); } @@ -1038,7 +1186,7 @@ u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, get_timer_map(vcpu, &map); timer = vcpu_get_timer(vcpu, tmr); - if (timer == map.emul_ptimer) + if (timer == map.emul_vtimer || timer == map.emul_ptimer) return kvm_arm_timer_read(vcpu, timer, treg); preempt_disable(); @@ -1070,6 +1218,10 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, timer_set_cval(timer, val); break; + case TIMER_REG_VOFF: + *timer->offset.vcpu_offset = val; + break; + default: BUG(); } @@ -1085,7 +1237,7 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, get_timer_map(vcpu, &map); timer = vcpu_get_timer(vcpu, tmr); - if (timer == map.emul_ptimer) { + if (timer == map.emul_vtimer || timer == map.emul_ptimer) { soft_timer_cancel(&timer->hrtimer); kvm_arm_timer_write(vcpu, timer, treg, val); timer_emulate(timer); @@ -1165,10 +1317,6 @@ static const struct irq_domain_ops timer_domain_ops = { .free = timer_irq_domain_free, }; -static struct irq_ops arch_timer_irq_ops = { - .get_input_level = kvm_arch_timer_get_input_level, -}; - static void kvm_irq_fixup_flags(unsigned int virq, u32 *flags) { *flags = irq_get_trigger_type(virq); @@ -1341,7 +1489,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) return valid; } -bool kvm_arch_timer_get_input_level(int vintid) +static bool kvm_arch_timer_get_input_level(int vintid) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); @@ -1444,6 +1592,12 @@ int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: idx = TIMER_PTIMER; break; + case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: + idx = TIMER_HVTIMER; + break; + case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: + idx = TIMER_HPTIMER; + break; default: ret = -ENXIO; goto out; @@ -1474,6 +1628,12 @@ int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: timer = vcpu_ptimer(vcpu); break; + case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: + timer = vcpu_hvtimer(vcpu); + break; + case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: + timer = vcpu_hptimer(vcpu); + break; default: return -ENXIO; } @@ -1487,6 +1647,8 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) switch (attr->attr) { case KVM_ARM_VCPU_TIMER_IRQ_VTIMER: case KVM_ARM_VCPU_TIMER_IRQ_PTIMER: + case KVM_ARM_VCPU_TIMER_IRQ_HVTIMER: + case KVM_ARM_VCPU_TIMER_IRQ_HPTIMER: return 0; } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index d07cbc313889..c41166f1a1dd 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -343,6 +343,21 @@ static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) switch (sysreg) { case SYS_CNTPCT_EL0: case SYS_CNTPCTSS_EL0: + if (vcpu_has_nv(vcpu)) { + if (is_hyp_ctxt(vcpu)) { + ctxt = vcpu_hptimer(vcpu); + break; + } + + /* Check for guest hypervisor trapping */ + val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); + if (!vcpu_el2_e2h_is_set(vcpu)) + val = (val & CNTHCTL_EL1PCTEN) << 10; + + if (!(val & (CNTHCTL_EL1PCTEN << 10))) + return false; + } + ctxt = vcpu_ptimer(vcpu); break; default: diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index f3e46a976125..6ce5c025218d 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -206,6 +206,7 @@ TRACE_EVENT(kvm_get_timer_map, __field( unsigned long, vcpu_id ) __field( int, direct_vtimer ) __field( int, direct_ptimer ) + __field( int, emul_vtimer ) __field( int, emul_ptimer ) ), @@ -214,14 +215,17 @@ TRACE_EVENT(kvm_get_timer_map, __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); __entry->direct_ptimer = (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; + __entry->emul_vtimer = + (map->emul_vtimer) ? arch_timer_ctx_index(map->emul_vtimer) : -1; __entry->emul_ptimer = (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; ), - TP_printk("VCPU: %ld, dv: %d, dp: %d, ep: %d", + TP_printk("VCPU: %ld, dv: %d, dp: %d, ev: %d, ep: %d", __entry->vcpu_id, __entry->direct_vtimer, __entry->direct_ptimer, + __entry->emul_vtimer, __entry->emul_ptimer) ); diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index d97e6080b421..ae491ef97188 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -573,6 +573,21 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) return 0; } +int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid) +{ + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); + unsigned long flags; + int ret = -1; + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + if (irq->hw) + ret = irq->hwintid; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + return ret; +} + /** * kvm_vgic_set_owner - Set the owner of an interrupt for a VM * diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 209da0c2ac9f..52008f5cff06 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -13,6 +13,9 @@ enum kvm_arch_timers { TIMER_PTIMER, TIMER_VTIMER, + NR_KVM_EL0_TIMERS, + TIMER_HVTIMER = NR_KVM_EL0_TIMERS, + TIMER_HPTIMER, NR_KVM_TIMERS }; @@ -21,6 +24,7 @@ enum kvm_arch_timer_regs { TIMER_REG_CVAL, TIMER_REG_TVAL, TIMER_REG_CTL, + TIMER_REG_VOFF, }; struct arch_timer_offset { @@ -76,6 +80,7 @@ struct arch_timer_context { struct timer_map { struct arch_timer_context *direct_vtimer; struct arch_timer_context *direct_ptimer; + struct arch_timer_context *emul_vtimer; struct arch_timer_context *emul_ptimer; }; @@ -114,12 +119,12 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); void kvm_timer_init_vhe(void); -bool kvm_arch_timer_get_input_level(int vintid); - #define vcpu_timer(v) (&(v)->arch.timer_cpu) #define vcpu_get_timer(v,t) (&vcpu_timer(v)->timers[(t)]) #define vcpu_vtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_VTIMER]) #define vcpu_ptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_PTIMER]) +#define vcpu_hvtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HVTIMER]) +#define vcpu_hptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HPTIMER]) #define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index d3ad51fde9db..402b545959af 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -380,6 +380,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, u32 vintid, struct irq_ops *ops); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid); +int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid); bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); -- GitLab From 0630fb8e0a4873e436f0c1c1b27fa60a37eb960c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:58 +0100 Subject: [PATCH 1747/5631] KVM: arm64: selftests: Add physical timer registers to the sysreg list Now that KVM exposes CNTPCT_EL0, CNTP_CTL_EL0 and CNT_CVAL_EL0 to userspace, add them to the get-reg-list selftest. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-19-maz@kernel.org --- tools/testing/selftests/kvm/aarch64/get-reg-list.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d287dd2cac0a..1b976b333d2c 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -651,7 +651,7 @@ int main(int ac, char **av) * The current blessed list was primed with the output of kernel version * v4.15 with --core-reg-fixup and then later updated with new registers. * - * The blessed list is up to date with kernel version v5.13-rc3 + * The blessed list is up to date with kernel version v6.4 (or so we hope) */ static __u64 base_regs[] = { KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), @@ -858,6 +858,9 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 1), /* CNTPCT_EL0 */ + ARM64_SYS_REG(3, 3, 14, 2, 1), /* CNTP_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 2, 2), /* CNTP_CVAL_EL0 */ ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ -- GitLab From 056c15669a01677ba3e44456580bf4a351f71ff7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:47:59 +0100 Subject: [PATCH 1748/5631] KVM: arm64: selftests: Deal with spurious timer interrupts Make sure the timer test can properly handle a spurious timer interrupt, something that is far from being unlikely. This involves checking for the GIC IAR return value (don't bother handling the interrupt if it was spurious) as well as the timer control register (don't do anything if the interrupt is masked or the timer disabled). Take this opportunity to rewrite the timer handler in a more readable way. This solves a bunch of failures that creep up on systems that are slow to retire the interrupt, something that the GIC architecture makes no guarantee about. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-20-maz@kernel.org --- .../selftests/kvm/aarch64/arch_timer.c | 40 ++++++++++++------- 1 file changed, 25 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 26556a266021..176ab41dd01b 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -121,25 +121,35 @@ static void guest_validate_irq(unsigned int intid, uint64_t xcnt = 0, xcnt_diff_us, cval = 0; unsigned long xctl = 0; unsigned int timer_irq = 0; + unsigned int accessor; - if (stage == GUEST_STAGE_VTIMER_CVAL || - stage == GUEST_STAGE_VTIMER_TVAL) { - xctl = timer_get_ctl(VIRTUAL); - timer_set_ctl(VIRTUAL, CTL_IMASK); - xcnt = timer_get_cntct(VIRTUAL); - cval = timer_get_cval(VIRTUAL); + if (intid == IAR_SPURIOUS) + return; + + switch (stage) { + case GUEST_STAGE_VTIMER_CVAL: + case GUEST_STAGE_VTIMER_TVAL: + accessor = VIRTUAL; timer_irq = vtimer_irq; - } else if (stage == GUEST_STAGE_PTIMER_CVAL || - stage == GUEST_STAGE_PTIMER_TVAL) { - xctl = timer_get_ctl(PHYSICAL); - timer_set_ctl(PHYSICAL, CTL_IMASK); - xcnt = timer_get_cntct(PHYSICAL); - cval = timer_get_cval(PHYSICAL); + break; + case GUEST_STAGE_PTIMER_CVAL: + case GUEST_STAGE_PTIMER_TVAL: + accessor = PHYSICAL; timer_irq = ptimer_irq; - } else { + break; + default: GUEST_ASSERT(0); + return; } + xctl = timer_get_ctl(accessor); + if ((xctl & CTL_IMASK) || !(xctl & CTL_ENABLE)) + return; + + timer_set_ctl(accessor, CTL_IMASK); + xcnt = timer_get_cntct(accessor); + cval = timer_get_cval(accessor); + xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt); /* Make sure we are dealing with the correct timer IRQ */ @@ -148,6 +158,8 @@ static void guest_validate_irq(unsigned int intid, /* Basic 'timer condition met' check */ GUEST_ASSERT_3(xcnt >= cval, xcnt, cval, xcnt_diff_us); GUEST_ASSERT_1(xctl & CTL_ISTATUS, xctl); + + WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); } static void guest_irq_handler(struct ex_regs *regs) @@ -158,8 +170,6 @@ static void guest_irq_handler(struct ex_regs *regs) guest_validate_irq(intid, shared_data); - WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1); - gic_set_eoi(intid); } -- GitLab From 2fe9e0fc21602339b82cdba58ef81a5a97d90ca2 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 30 Mar 2023 18:48:00 +0100 Subject: [PATCH 1749/5631] KVM: arm64: selftests: Augment existing timer test to handle variable offset Allow a user to specify the global offset on the command-line. Reviewed-by: Colton Lewis Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230330174800.2677007-21-maz@kernel.org --- tools/testing/selftests/kvm/aarch64/arch_timer.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 176ab41dd01b..8ef370924a02 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -47,6 +47,7 @@ struct test_args { int nr_iter; int timer_period_ms; int migration_freq_ms; + struct kvm_arm_counter_offset offset; }; static struct test_args test_args = { @@ -54,6 +55,7 @@ static struct test_args test_args = { .nr_iter = NR_TEST_ITERS_DEF, .timer_period_ms = TIMER_TEST_PERIOD_MS_DEF, .migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS, + .offset = { .reserved = 1 }, }; #define msecs_to_usecs(msec) ((msec) * 1000LL) @@ -382,6 +384,13 @@ static struct kvm_vm *test_vm_create(void) vm_init_descriptor_tables(vm); vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler); + if (!test_args.offset.reserved) { + if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET)) + vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset); + else + TEST_FAIL("no support for global offset\n"); + } + for (i = 0; i < nr_vcpus; i++) vcpu_init_descriptor_tables(vcpus[i]); @@ -413,6 +422,7 @@ static void test_print_help(char *name) TIMER_TEST_PERIOD_MS_DEF); pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n", TIMER_TEST_MIGRATION_FREQ_MS); + pr_info("\t-o: Counter offset (in counter cycles, default: 0)\n"); pr_info("\t-h: print this help screen\n"); } @@ -420,7 +430,7 @@ static bool parse_args(int argc, char *argv[]) { int opt; - while ((opt = getopt(argc, argv, "hn:i:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hn:i:p:m:o:")) != -1) { switch (opt) { case 'n': test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg); @@ -439,6 +449,10 @@ static bool parse_args(int argc, char *argv[]) case 'm': test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg); break; + case 'o': + test_args.offset.counter_offset = strtol(optarg, NULL, 0); + test_args.offset.reserved = 0; + break; case 'h': default: goto err; -- GitLab From a2bed39057b434c4fd816005d1b950fefc61569d Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Wed, 8 Mar 2023 11:09:46 +0000 Subject: [PATCH 1750/5631] KVM: selftests: Fixup config fragment for access_tracking_perf_test access_tracking_perf_test requires CONFIG_IDLE_PAGE_TRACKING. However this is missing from the config fragment, so add it in so that this test is no longer skipped. Signed-off-by: Ryan Roberts Reviewed-by: Sean Christopherson Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230308110948.1820163-2-ryan.roberts@arm.com --- tools/testing/selftests/kvm/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index d011b38e259e..8835fed09e9f 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -2,3 +2,4 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y CONFIG_USERFAULTFD=y +CONFIG_IDLE_PAGE_TRACKING=y -- GitLab From e659babfc5a693553cf9473470840464f0ed5d77 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Wed, 8 Mar 2023 11:09:47 +0000 Subject: [PATCH 1751/5631] KVM: selftests: arm64: Fix pte encode/decode for PA bits > 48 The high bits [51:48] of a physical address should appear at [15:12] in a 64K pte, not at [51:48] as was previously being programmed. Fix this with new helper functions that do the conversion correctly. This also sets us up nicely for adding LPA2 encodings in future. Fixes: 7a6629ef746d ("kvm: selftests: add virt mem support for aarch64") Signed-off-by: Ryan Roberts Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230308110948.1820163-3-ryan.roberts@arm.com --- .../selftests/kvm/lib/aarch64/processor.c | 32 ++++++++++++++----- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 5972a23b2765..c413085d58b7 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -58,10 +58,27 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva) return (gva >> vm->page_shift) & mask; } -static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry) +static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs) { - uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift; - return entry & mask; + uint64_t pte; + + pte = pa & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pte |= FIELD_GET(GENMASK(51, 48), pa) << 12; + pte |= attrs; + + return pte; +} + +static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) +{ + uint64_t pa; + + pa = pte & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pa |= FIELD_GET(GENMASK(15, 12), pte) << 48; + + return pa; } static uint64_t ptrs_per_pgd(struct kvm_vm *vm) @@ -110,18 +127,18 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); switch (vm->pgtable_levels) { case 4: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); /* fall through */ case 3: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8; if (!*ptep) - *ptep = vm_alloc_page_table(vm) | 3; + *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3); /* fall through */ case 2: ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8; @@ -130,8 +147,7 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, TEST_FAIL("Page table levels must be 2, 3, or 4"); } - *ptep = paddr | 3; - *ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */; + *ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3); /* AF */ } void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) -- GitLab From e17071754cf50e5f6ff8ebee077e0e4114d3bea5 Mon Sep 17 00:00:00 2001 From: Ryan Roberts Date: Wed, 8 Mar 2023 11:09:48 +0000 Subject: [PATCH 1752/5631] KVM: selftests: arm64: Fix ttbr0_el1 encoding for PA bits > 48 Bits [51:48] of the pgd address are stored at bits [5:2] of ttbr0_el1. page_table_test stores its page tables at the far end of IPA space so was tripping over this when run on a system that supports FEAT_LPA (or FEAT_LPA2). Signed-off-by: Ryan Roberts Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230308110948.1820163-4-ryan.roberts@arm.com --- tools/testing/selftests/kvm/lib/aarch64/processor.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index c413085d58b7..233357d2f1cc 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -242,7 +242,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) { struct kvm_vcpu_init default_init = { .target = -1, }; struct kvm_vm *vm = vcpu->vm; - uint64_t sctlr_el1, tcr_el1; + uint64_t sctlr_el1, tcr_el1, ttbr0_el1; if (!init) init = &default_init; @@ -293,10 +293,13 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); } + ttbr0_el1 = vm->pgd & GENMASK(47, vm->page_shift); + /* Configure output size */ switch (vm->mode) { case VM_MODE_P52V48_64K: tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ + ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2; break; case VM_MODE_P48V48_4K: case VM_MODE_P48V48_16K: @@ -326,7 +329,7 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1); - vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd); + vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), ttbr0_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id); } -- GitLab From 767cc0501bbb51f2daad35d1bc4f6eaa857ed057 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 6 Mar 2023 16:15:07 +0000 Subject: [PATCH 1753/5631] KVM: selftests: Comment newly defined aarch64 ID registers All otherwise unspecified aarch64 ID registers should be read as zero so we cover the whole ID register space in the get-reg-list test but we've added comments for those that have been named. Add comments for ID_AA64PFR2_EL1, ID_AA64SMFR0_EL1, ID_AA64ISAR2_EL1, ID_AA64MMFR3_EL1 and ID_AA64MMFR4_EL1 which have been defined since the comments were added so someone looking for them will see that they are covered. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230210-kvm-arm64-getreg-comments-v1-1-a16c73be5ab4@kernel.org --- tools/testing/selftests/kvm/aarch64/get-reg-list.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index d287dd2cac0a..df8a8afca4fc 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -807,10 +807,10 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 3, 7), ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ - ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 2), /* ID_AA64PFR2_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 3), ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ - ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 5), /* ID_AA64SMFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 4, 6), ARM64_SYS_REG(3, 0, 0, 4, 7), ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ @@ -823,7 +823,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 5, 7), ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ - ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 2), /* ID_AA64ISAR2_EL1 */ ARM64_SYS_REG(3, 0, 0, 6, 3), ARM64_SYS_REG(3, 0, 0, 6, 4), ARM64_SYS_REG(3, 0, 0, 6, 5), @@ -832,8 +832,8 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), - ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 4), /* ID_AA64MMFR4_EL1 */ ARM64_SYS_REG(3, 0, 0, 7, 5), ARM64_SYS_REG(3, 0, 0, 7, 6), ARM64_SYS_REG(3, 0, 0, 7, 7), -- GitLab From a2972cb89935160bfe515b15d28a77694723ac06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:16 +0100 Subject: [PATCH 1754/5631] iommu/arm-smmu: Drop if with an always false condition MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The remove and shutdown callback are only called after probe completed successfully. In this case platform_set_drvdata() was called with a non-NULL argument and so smmu is never NULL. Other functions in this driver also don't check for smmu being non-NULL before using it. Also note that returning an error code from a remove callback doesn't result in the device staying bound. It's still removed and devm allocated resources are freed (among others *smmu and the register mapping). So after an early exit to iommu device stayed around and using it probably oopses. Signed-off-by: Uwe Kleine-König Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/20230321084125.337021-2-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 2ff7a72cf377..f4a36533ae47 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -2195,9 +2195,6 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); - if (!smmu) - return; - if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS)) dev_notice(&pdev->dev, "disabling translation\n"); @@ -2218,9 +2215,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); - if (!smmu) - return -ENODEV; - iommu_device_unregister(&smmu->iommu); iommu_device_sysfs_remove(&smmu->iommu); -- GitLab From f80473183b40bb98a7499c61091c3c55b646f387 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:17 +0100 Subject: [PATCH 1755/5631] iommu/apple-dart: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-3-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/apple-dart.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c index 06169d36eab8..8af64b57f048 100644 --- a/drivers/iommu/apple-dart.c +++ b/drivers/iommu/apple-dart.c @@ -1150,7 +1150,7 @@ static int apple_dart_probe(struct platform_device *pdev) return ret; } -static int apple_dart_remove(struct platform_device *pdev) +static void apple_dart_remove(struct platform_device *pdev) { struct apple_dart *dart = platform_get_drvdata(pdev); @@ -1161,8 +1161,6 @@ static int apple_dart_remove(struct platform_device *pdev) iommu_device_sysfs_remove(&dart->iommu); clk_bulk_disable_unprepare(dart->num_clks, dart->clks); - - return 0; } static const struct apple_dart_hw apple_dart_hw_t8103 = { @@ -1296,7 +1294,7 @@ static struct platform_driver apple_dart_driver = { .pm = pm_sleep_ptr(&apple_dart_pm_ops), }, .probe = apple_dart_probe, - .remove = apple_dart_remove, + .remove_new = apple_dart_remove, }; module_platform_driver(apple_dart_driver); -- GitLab From 66c7076f7636f197d8a67416961037d6d2d7b4df Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:18 +0100 Subject: [PATCH 1756/5631] iommu/arm-smmu-v3: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-4-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index f2425b0f0cd6..d99e1a8dbe44 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3844,7 +3844,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) return 0; } -static int arm_smmu_device_remove(struct platform_device *pdev) +static void arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); @@ -3852,8 +3852,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev) iommu_device_sysfs_remove(&smmu->iommu); arm_smmu_device_disable(smmu); iopf_queue_free(smmu->evtq.iopf); - - return 0; } static void arm_smmu_device_shutdown(struct platform_device *pdev) @@ -3882,7 +3880,7 @@ static struct platform_driver arm_smmu_driver = { .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, - .remove = arm_smmu_device_remove, + .remove_new = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; module_driver(arm_smmu_driver, platform_driver_register, -- GitLab From 62565a77c2323d32f2be737455729ac7d3efe6ad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:19 +0100 Subject: [PATCH 1757/5631] iommu/arm-smmu: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-5-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/arm/arm-smmu/arm-smmu.c | 6 ++---- drivers/iommu/arm/arm-smmu/qcom_iommu.c | 12 ++++-------- 2 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index f4a36533ae47..b30a4bd7c79d 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -2211,7 +2211,7 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev) clk_bulk_unprepare(smmu->num_clks, smmu->clks); } -static int arm_smmu_device_remove(struct platform_device *pdev) +static void arm_smmu_device_remove(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); @@ -2219,8 +2219,6 @@ static int arm_smmu_device_remove(struct platform_device *pdev) iommu_device_sysfs_remove(&smmu->iommu); arm_smmu_device_shutdown(pdev); - - return 0; } static int __maybe_unused arm_smmu_runtime_resume(struct device *dev) @@ -2296,7 +2294,7 @@ static struct platform_driver arm_smmu_driver = { .suppress_bind_attrs = true, }, .probe = arm_smmu_device_probe, - .remove = arm_smmu_device_remove, + .remove_new = arm_smmu_device_remove, .shutdown = arm_smmu_device_shutdown, }; module_platform_driver(arm_smmu_driver); diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c index c8b70f476cd8..a503ed758ec3 100644 --- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c +++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c @@ -682,7 +682,7 @@ static int qcom_iommu_ctx_probe(struct platform_device *pdev) return 0; } -static int qcom_iommu_ctx_remove(struct platform_device *pdev) +static void qcom_iommu_ctx_remove(struct platform_device *pdev) { struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(pdev->dev.parent); struct qcom_iommu_ctx *ctx = platform_get_drvdata(pdev); @@ -690,8 +690,6 @@ static int qcom_iommu_ctx_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); qcom_iommu->ctxs[ctx->asid - 1] = NULL; - - return 0; } static const struct of_device_id ctx_of_match[] = { @@ -706,7 +704,7 @@ static struct platform_driver qcom_iommu_ctx_driver = { .of_match_table = ctx_of_match, }, .probe = qcom_iommu_ctx_probe, - .remove = qcom_iommu_ctx_remove, + .remove_new = qcom_iommu_ctx_remove, }; static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu) @@ -824,7 +822,7 @@ static int qcom_iommu_device_probe(struct platform_device *pdev) return ret; } -static int qcom_iommu_device_remove(struct platform_device *pdev) +static void qcom_iommu_device_remove(struct platform_device *pdev) { struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev); @@ -832,8 +830,6 @@ static int qcom_iommu_device_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); iommu_device_sysfs_remove(&qcom_iommu->iommu); iommu_device_unregister(&qcom_iommu->iommu); - - return 0; } static int __maybe_unused qcom_iommu_resume(struct device *dev) @@ -870,7 +866,7 @@ static struct platform_driver qcom_iommu_driver = { .pm = &qcom_iommu_pm_ops, }, .probe = qcom_iommu_device_probe, - .remove = qcom_iommu_device_remove, + .remove_new = qcom_iommu_device_remove, }; static int __init qcom_iommu_init(void) -- GitLab From 7471ea50eae448953126c285e8ee0351db5e2b44 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:20 +0100 Subject: [PATCH 1758/5631] iommu/ipmmu-vmsa: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-6-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/ipmmu-vmsa.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index bdf1a4e5eae0..813dbd1f7ba0 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1073,7 +1073,7 @@ static int ipmmu_probe(struct platform_device *pdev) return 0; } -static int ipmmu_remove(struct platform_device *pdev) +static void ipmmu_remove(struct platform_device *pdev) { struct ipmmu_vmsa_device *mmu = platform_get_drvdata(pdev); @@ -1083,8 +1083,6 @@ static int ipmmu_remove(struct platform_device *pdev) arm_iommu_release_mapping(mmu->mapping); ipmmu_device_reset(mmu); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -1131,6 +1129,6 @@ static struct platform_driver ipmmu_driver = { .pm = DEV_PM_OPS, }, .probe = ipmmu_probe, - .remove = ipmmu_remove, + .remove_new = ipmmu_remove, }; builtin_platform_driver(ipmmu_driver); -- GitLab From 816a4afce133e75f5977bbf0f4c24c02280b1a99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:21 +0100 Subject: [PATCH 1759/5631] iommu/msm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-7-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/msm_iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 454f6331c889..79d89bad5132 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -811,13 +811,12 @@ static const struct of_device_id msm_iommu_dt_match[] = { {} }; -static int msm_iommu_remove(struct platform_device *pdev) +static void msm_iommu_remove(struct platform_device *pdev) { struct msm_iommu_dev *iommu = platform_get_drvdata(pdev); clk_unprepare(iommu->clk); clk_unprepare(iommu->pclk); - return 0; } static struct platform_driver msm_iommu_driver = { @@ -826,6 +825,6 @@ static struct platform_driver msm_iommu_driver = { .of_match_table = msm_iommu_dt_match, }, .probe = msm_iommu_probe, - .remove = msm_iommu_remove, + .remove_new = msm_iommu_remove, }; builtin_platform_driver(msm_iommu_driver); -- GitLab From d8149d39299ec89125a1cb35cdd77defd7a79deb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:22 +0100 Subject: [PATCH 1760/5631] iommu/mtk: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230321084125.337021-8-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index d5a4955910ff..bcc7ccdb2d6e 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1316,7 +1316,7 @@ static int mtk_iommu_probe(struct platform_device *pdev) return ret; } -static int mtk_iommu_remove(struct platform_device *pdev) +static void mtk_iommu_remove(struct platform_device *pdev) { struct mtk_iommu_data *data = platform_get_drvdata(pdev); struct mtk_iommu_bank_data *bank; @@ -1338,7 +1338,6 @@ static int mtk_iommu_remove(struct platform_device *pdev) continue; devm_free_irq(&pdev->dev, bank->irq, bank); } - return 0; } static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev) @@ -1595,7 +1594,7 @@ static const struct of_device_id mtk_iommu_of_ids[] = { static struct platform_driver mtk_iommu_driver = { .probe = mtk_iommu_probe, - .remove = mtk_iommu_remove, + .remove_new = mtk_iommu_remove, .driver = { .name = "mtk-iommu", .of_match_table = mtk_iommu_of_ids, -- GitLab From 85e1049e50da9409678fc247ebad4c019d68041f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:23 +0100 Subject: [PATCH 1761/5631] iommu/mtk_iommu_v1: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230321084125.337021-9-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu_v1.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 43e4c8f89e23..8a0a5e5d049f 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -703,7 +703,7 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) return ret; } -static int mtk_iommu_v1_remove(struct platform_device *pdev) +static void mtk_iommu_v1_remove(struct platform_device *pdev) { struct mtk_iommu_v1_data *data = platform_get_drvdata(pdev); @@ -713,7 +713,6 @@ static int mtk_iommu_v1_remove(struct platform_device *pdev) clk_disable_unprepare(data->bclk); devm_free_irq(&pdev->dev, data->irq, data); component_master_del(&pdev->dev, &mtk_iommu_v1_com_ops); - return 0; } static int __maybe_unused mtk_iommu_v1_suspend(struct device *dev) @@ -752,7 +751,7 @@ static const struct dev_pm_ops mtk_iommu_v1_pm_ops = { static struct platform_driver mtk_iommu_v1_driver = { .probe = mtk_iommu_v1_probe, - .remove = mtk_iommu_v1_remove, + .remove_new = mtk_iommu_v1_remove, .driver = { .name = "mtk-iommu-v1", .of_match_table = mtk_iommu_v1_of_ids, -- GitLab From 5930df68aec6cc63ea8525c75561dfb203a9441f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:24 +0100 Subject: [PATCH 1762/5631] iommu/omap: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-10-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/omap-iommu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 3ab078112a7c..dec7cdcfbe9c 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1257,7 +1257,7 @@ static int omap_iommu_probe(struct platform_device *pdev) return err; } -static int omap_iommu_remove(struct platform_device *pdev) +static void omap_iommu_remove(struct platform_device *pdev) { struct omap_iommu *obj = platform_get_drvdata(pdev); @@ -1274,7 +1274,6 @@ static int omap_iommu_remove(struct platform_device *pdev) pm_runtime_disable(obj->dev); dev_info(&pdev->dev, "%s removed\n", obj->name); - return 0; } static const struct dev_pm_ops omap_iommu_pm_ops = { @@ -1295,7 +1294,7 @@ static const struct of_device_id omap_iommu_of_match[] = { static struct platform_driver omap_iommu_driver = { .probe = omap_iommu_probe, - .remove = omap_iommu_remove, + .remove_new = omap_iommu_remove, .driver = { .name = "omap-iommu", .pm = &omap_iommu_pm_ops, -- GitLab From 421b6093f5ac3edf9cb79f36e79b7e2d51d6182b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 21 Mar 2023 09:41:25 +0100 Subject: [PATCH 1763/5631] iommu/sprd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230321084125.337021-11-u.kleine-koenig@pengutronix.de Signed-off-by: Joerg Roedel --- drivers/iommu/sprd-iommu.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index ae94d74b73f4..907569e76d59 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -507,7 +507,7 @@ static int sprd_iommu_probe(struct platform_device *pdev) return ret; } -static int sprd_iommu_remove(struct platform_device *pdev) +static void sprd_iommu_remove(struct platform_device *pdev) { struct sprd_iommu_device *sdev = platform_get_drvdata(pdev); @@ -519,8 +519,6 @@ static int sprd_iommu_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); iommu_device_sysfs_remove(&sdev->iommu); iommu_device_unregister(&sdev->iommu); - - return 0; } static struct platform_driver sprd_iommu_driver = { @@ -530,7 +528,7 @@ static struct platform_driver sprd_iommu_driver = { .suppress_bind_attrs = true, }, .probe = sprd_iommu_probe, - .remove = sprd_iommu_remove, + .remove_new = sprd_iommu_remove, }; module_platform_driver(sprd_iommu_driver); -- GitLab From 760f41d182ec94a651977e70045fd61b57973408 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:07:57 -0700 Subject: [PATCH 1764/5631] iommu/vt-d: Remove virtual command interface Virtual command interface was introduced to allow using host PASIDs inside VMs. It is unused and abandoned due to architectural change. With this patch, we can safely remove this feature and the related helpers. Link: https://lore.kernel.org/r/20230210230206.3160144-2-jacob.jun.pan@linux.intel.com Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/20230322200803.869130-2-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/cap_audit.c | 2 - drivers/iommu/intel/dmar.c | 2 - drivers/iommu/intel/iommu.c | 85 --------------------------------- drivers/iommu/intel/iommu.h | 2 - 4 files changed, 91 deletions(-) diff --git a/drivers/iommu/intel/cap_audit.c b/drivers/iommu/intel/cap_audit.c index 806986696841..9862dc20b35e 100644 --- a/drivers/iommu/intel/cap_audit.c +++ b/drivers/iommu/intel/cap_audit.c @@ -54,7 +54,6 @@ static inline void check_dmar_capabilities(struct intel_iommu *a, CHECK_FEATURE_MISMATCH(a, b, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH(a, b, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH(a, b, ecap, dit, ECAP_DIT_MASK); @@ -101,7 +100,6 @@ static int cap_audit_hotplug(struct intel_iommu *iommu, enum cap_audit_type type CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slts, ECAP_SLTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, nwfs, ECAP_NWFS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, slads, ECAP_SLADS_MASK); - CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, vcs, ECAP_VCS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, smts, ECAP_SMTS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, pds, ECAP_PDS_MASK); CHECK_FEATURE_MISMATCH_HOTPLUG(iommu, ecap, dit, ECAP_DIT_MASK); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 6acfe879589c..0f348439ef0e 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -993,8 +993,6 @@ static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd) warn_invalid_dmar(phys_addr, " returns all ones"); goto unmap; } - if (ecap_vcs(iommu->ecap)) - iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG); /* the registers might be more than one page */ map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap), diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a366790fb781..6c2d1ffb5b0a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1722,9 +1722,6 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); } - if (vccap_pasid(iommu->vccap)) - ioasid_unregister_allocator(&iommu->pasid_allocator); - #endif } @@ -2797,85 +2794,6 @@ static int copy_translation_tables(struct intel_iommu *iommu) return ret; } -#ifdef CONFIG_INTEL_IOMMU_SVM -static ioasid_t intel_vcmd_ioasid_alloc(ioasid_t min, ioasid_t max, void *data) -{ - struct intel_iommu *iommu = data; - ioasid_t ioasid; - - if (!iommu) - return INVALID_IOASID; - /* - * VT-d virtual command interface always uses the full 20 bit - * PASID range. Host can partition guest PASID range based on - * policies but it is out of guest's control. - */ - if (min < PASID_MIN || max > intel_pasid_max_id) - return INVALID_IOASID; - - if (vcmd_alloc_pasid(iommu, &ioasid)) - return INVALID_IOASID; - - return ioasid; -} - -static void intel_vcmd_ioasid_free(ioasid_t ioasid, void *data) -{ - struct intel_iommu *iommu = data; - - if (!iommu) - return; - /* - * Sanity check the ioasid owner is done at upper layer, e.g. VFIO - * We can only free the PASID when all the devices are unbound. - */ - if (ioasid_find(NULL, ioasid, NULL)) { - pr_alert("Cannot free active IOASID %d\n", ioasid); - return; - } - vcmd_free_pasid(iommu, ioasid); -} - -static void register_pasid_allocator(struct intel_iommu *iommu) -{ - /* - * If we are running in the host, no need for custom allocator - * in that PASIDs are allocated from the host system-wide. - */ - if (!cap_caching_mode(iommu->cap)) - return; - - if (!sm_supported(iommu)) { - pr_warn("VT-d Scalable Mode not enabled, no PASID allocation\n"); - return; - } - - /* - * Register a custom PASID allocator if we are running in a guest, - * guest PASID must be obtained via virtual command interface. - * There can be multiple vIOMMUs in each guest but only one allocator - * is active. All vIOMMU allocators will eventually be calling the same - * host allocator. - */ - if (!vccap_pasid(iommu->vccap)) - return; - - pr_info("Register custom PASID allocator\n"); - iommu->pasid_allocator.alloc = intel_vcmd_ioasid_alloc; - iommu->pasid_allocator.free = intel_vcmd_ioasid_free; - iommu->pasid_allocator.pdata = (void *)iommu; - if (ioasid_register_allocator(&iommu->pasid_allocator)) { - pr_warn("Custom PASID allocator failed, scalable mode disabled\n"); - /* - * Disable scalable mode on this IOMMU if there - * is no custom allocator. Mixing SM capable vIOMMU - * and non-SM vIOMMU are not supported. - */ - intel_iommu_sm = 0; - } -} -#endif - static int __init init_dmars(void) { struct dmar_drhd_unit *drhd; @@ -2964,9 +2882,6 @@ static int __init init_dmars(void) */ for_each_active_iommu(iommu, drhd) { iommu_flush_write_buffer(iommu); -#ifdef CONFIG_INTEL_IOMMU_SVM - register_pasid_allocator(iommu); -#endif iommu_set_root_entry(iommu); } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..a2010fb120e2 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -198,7 +198,6 @@ #define ecap_flts(e) (((e) >> 47) & 0x1) #define ecap_slts(e) (((e) >> 46) & 0x1) #define ecap_slads(e) (((e) >> 45) & 0x1) -#define ecap_vcs(e) (((e) >> 44) & 0x1) #define ecap_smts(e) (((e) >> 43) & 0x1) #define ecap_dit(e) (((e) >> 41) & 0x1) #define ecap_pds(e) (((e) >> 42) & 0x1) @@ -676,7 +675,6 @@ struct intel_iommu { unsigned char prq_name[16]; /* Name for PRQ interrupt */ unsigned long prq_seq_number; struct completion prq_complete; - struct ioasid_allocator_ops pasid_allocator; /* Custom allocator for PASIDs */ #endif struct iopf_queue *iopf_queue; unsigned char iopfq_name[16]; -- GitLab From cd3891158a77685aee6129f7374a018d13540b2c Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:07:58 -0700 Subject: [PATCH 1765/5631] iommu/sva: Move PASID helpers to sva code Preparing to remove IOASID infrastructure, PASID management will be under SVA code. Decouple mm code from IOASID. Reviewed-by: Jason Gunthorpe Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230322200803.869130-3-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-sva.c | 10 +++++++++- include/linux/ioasid.h | 11 +---------- include/linux/iommu.h | 14 +++++++++++++- include/linux/sched/mm.h | 26 -------------------------- kernel/fork.c | 1 + 5 files changed, 24 insertions(+), 38 deletions(-) diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 24bf9b2b58aa..fcfdc80a3939 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -44,7 +44,7 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) if (!pasid_valid(pasid)) ret = -ENOMEM; else - mm_pasid_set(mm, pasid); + mm->pasid = pasid; out: mutex_unlock(&iommu_sva_lock); return ret; @@ -238,3 +238,11 @@ iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) return status; } + +void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index af1c9d62e642..734bf0e036ee 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -4,8 +4,8 @@ #include #include +#include -#define INVALID_IOASID ((ioasid_t)-1) typedef unsigned int ioasid_t; typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); @@ -40,10 +40,6 @@ void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -74,10 +70,5 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..d3f81dc6e4dd 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,7 +13,6 @@ #include #include #include -#include #include #define IOMMU_READ (1 << 0) @@ -192,6 +191,8 @@ enum iommu_dev_features { }; #define IOMMU_PASID_INVALID (-1U) +typedef unsigned int ioasid_t; +#define INVALID_IOASID ((ioasid_t)-1) #ifdef CONFIG_IOMMU_API @@ -1172,7 +1173,16 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream return false; } +static inline bool pasid_valid(ioasid_t ioasid) +{ + return ioasid != INVALID_IOASID; +} #ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} +void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); @@ -1192,6 +1202,8 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; } +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..da9712a3ba73 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,7 +8,6 @@ #include #include #include -#include /* * Routines for handling mm_structs @@ -451,29 +450,4 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif -#ifdef CONFIG_IOMMU_SVA -static inline void mm_pasid_init(struct mm_struct *mm) -{ - mm->pasid = INVALID_IOASID; -} - -/* Associate a PASID with an mm_struct: */ -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) -{ - mm->pasid = pasid; -} - -static inline void mm_pasid_drop(struct mm_struct *mm) -{ - if (pasid_valid(mm->pasid)) { - ioasid_free(mm->pasid); - mm->pasid = INVALID_IOASID; - } -} -#else -static inline void mm_pasid_init(struct mm_struct *mm) {} -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} -static inline void mm_pasid_drop(struct mm_struct *mm) {} -#endif - #endif /* _LINUX_SCHED_MM_H */ diff --git a/kernel/fork.c b/kernel/fork.c index d8cda4c6de6c..9f14e4084fc0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include -- GitLab From 2bef9ba8aefc211674427a0db046a773001b3329 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:07:59 -0700 Subject: [PATCH 1766/5631] iommu/sva: Remove PASID to mm lookup function There is no user of iommu_sva_find() function, remove it so that PASID allocator can be a simple IDA. Device drivers are expected to store and keep track of their own PASID metadata. Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230322200803.869130-4-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-sva.c | 20 -------------------- drivers/iommu/iommu-sva.h | 1 - 2 files changed, 21 deletions(-) diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index fcfdc80a3939..4f357ef14f04 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -51,26 +51,6 @@ int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) } EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); -/* ioasid_find getter() requires a void * argument */ -static bool __mmget_not_zero(void *mm) -{ - return mmget_not_zero(mm); -} - -/** - * iommu_sva_find() - Find mm associated to the given PASID - * @pasid: Process Address Space ID assigned to the mm - * - * On success a reference to the mm is taken, and must be released with mmput(). - * - * Returns the mm corresponding to this PASID, or an error if not found. - */ -struct mm_struct *iommu_sva_find(ioasid_t pasid) -{ - return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero); -} -EXPORT_SYMBOL_GPL(iommu_sva_find); - /** * iommu_sva_bind_device() - Bind a process address space to a device * @dev: the device diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h index 7215a761b962..102eae1817a2 100644 --- a/drivers/iommu/iommu-sva.h +++ b/drivers/iommu/iommu-sva.h @@ -9,7 +9,6 @@ #include int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); -struct mm_struct *iommu_sva_find(ioasid_t pasid); /* I/O Page fault */ struct device; -- GitLab From 4e14176ab13fb6986dd079c711d46b70712da2f1 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 Mar 2023 13:08:00 -0700 Subject: [PATCH 1767/5631] iommu/sva: Stop using ioasid_set for SVA Instead SVA drivers can use a simple global IDA to allocate PASIDs for each mm_struct. Future work would be to allow drivers using the SVA APIs to reserve global PASIDs from this IDA for their internal use, eg with the DMA API PASID support. Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe Signed-off-by: Jacob Pan Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20230322200803.869130-5-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-sva.c | 41 +++++++++++++-------------------------- drivers/iommu/iommu-sva.h | 2 -- 2 files changed, 14 insertions(+), 29 deletions(-) diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 4f357ef14f04..48e8a15ddc9b 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -9,47 +9,34 @@ #include "iommu-sva.h" static DEFINE_MUTEX(iommu_sva_lock); -static DECLARE_IOASID_SET(iommu_sva_pasid); +static DEFINE_IDA(iommu_global_pasid_ida); -/** - * iommu_sva_alloc_pasid - Allocate a PASID for the mm - * @mm: the mm - * @min: minimum PASID value (inclusive) - * @max: maximum PASID value (inclusive) - * - * Try to allocate a PASID for this mm, or take a reference to the existing one - * provided it fits within the [@min, @max] range. On success the PASID is - * available in mm->pasid and will be available for the lifetime of the mm. - * - * Returns 0 on success and < 0 on error. - */ -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) +/* Allocate a PASID for the mm within range (inclusive) */ +static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) { int ret = 0; - ioasid_t pasid; - if (min == INVALID_IOASID || max == INVALID_IOASID || + if (!pasid_valid(min) || !pasid_valid(max) || min == 0 || max < min) return -EINVAL; mutex_lock(&iommu_sva_lock); /* Is a PASID already associated with this mm? */ if (pasid_valid(mm->pasid)) { - if (mm->pasid < min || mm->pasid >= max) + if (mm->pasid < min || mm->pasid > max) ret = -EOVERFLOW; goto out; } - pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); - if (!pasid_valid(pasid)) - ret = -ENOMEM; - else - mm->pasid = pasid; + ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_ATOMIC); + if (ret < 0) + goto out; + mm->pasid = ret; + ret = 0; out: mutex_unlock(&iommu_sva_lock); return ret; } -EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); /** * iommu_sva_bind_device() - Bind a process address space to a device @@ -221,8 +208,8 @@ iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) void mm_pasid_drop(struct mm_struct *mm) { - if (pasid_valid(mm->pasid)) { - ioasid_free(mm->pasid); - mm->pasid = INVALID_IOASID; - } + if (likely(!pasid_valid(mm->pasid))) + return; + + ida_free(&iommu_global_pasid_ida, mm->pasid); } diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h index 102eae1817a2..c22d0174ad61 100644 --- a/drivers/iommu/iommu-sva.h +++ b/drivers/iommu/iommu-sva.h @@ -8,8 +8,6 @@ #include #include -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); - /* I/O Page fault */ struct device; struct iommu_fault; -- GitLab From 1a14bf0fc7ed9476284cd6ab358c783fd9a0cb5b Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:08:01 -0700 Subject: [PATCH 1768/5631] iommu/sva: Use GFP_KERNEL for pasid allocation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We’re not using spinlock-protected IOASID allocation anymore, there’s no need for GFP_ATOMIC. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Reviewed-by: Jason Gunthorpe Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-6-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-sva.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 48e8a15ddc9b..c434b95dc8eb 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -28,8 +28,8 @@ static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t ma goto out; } - ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_ATOMIC); - if (ret < 0) + ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL); + if (ret < min) goto out; mm->pasid = ret; ret = 0; -- GitLab From fffaed1e24b8d114e958d180cb4a8aed3febbb5a Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Wed, 22 Mar 2023 13:08:02 -0700 Subject: [PATCH 1769/5631] iommu/ioasid: Rename INVALID_IOASID INVALID_IOASID and IOMMU_PASID_INVALID are duplicated. Rename INVALID_IOASID and consolidate since we are moving away from IOASID infrastructure. Reviewed-by: Dave Jiang Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-7-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- Documentation/x86/sva.rst | 2 +- arch/x86/kernel/traps.c | 2 +- drivers/dma/idxd/device.c | 8 ++++---- drivers/dma/idxd/idxd.h | 1 + drivers/dma/idxd/init.c | 2 +- drivers/dma/idxd/irq.c | 2 +- drivers/iommu/intel/dmar.c | 4 ++-- drivers/iommu/intel/iommu.c | 2 +- drivers/iommu/intel/svm.c | 2 +- include/linux/ioasid.h | 1 + include/linux/iommu.h | 6 +++--- mm/init-mm.c | 4 ++-- 12 files changed, 19 insertions(+), 17 deletions(-) diff --git a/Documentation/x86/sva.rst b/Documentation/x86/sva.rst index 2e9b8b0f9a0f..33cb05005982 100644 --- a/Documentation/x86/sva.rst +++ b/Documentation/x86/sva.rst @@ -107,7 +107,7 @@ process share the same page tables, thus the same MSR value. PASID Life Cycle Management =========================== -PASID is initialized as INVALID_IOASID (-1) when a process is created. +PASID is initialized as IOMMU_PASID_INVALID (-1) when a process is created. Only processes that access SVA-capable devices need to have a PASID allocated. This allocation happens when a process opens/binds an SVA-capable diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d317dc3d06a3..492a60febb11 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 5f321f3b4242..6fca8fa8d3a8 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -1194,7 +1194,7 @@ static void idxd_device_set_perm_entry(struct idxd_device *idxd, { union msix_perm mperm; - if (ie->pasid == INVALID_IOASID) + if (ie->pasid == IOMMU_PASID_INVALID) return; mperm.bits = 0; @@ -1224,7 +1224,7 @@ void idxd_wq_free_irq(struct idxd_wq *wq) idxd_device_clear_perm_entry(idxd, ie); ie->vector = -1; ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; } int idxd_wq_request_irq(struct idxd_wq *wq) @@ -1240,7 +1240,7 @@ int idxd_wq_request_irq(struct idxd_wq *wq) ie = &wq->ie; ie->vector = pci_irq_vector(pdev, ie->id); - ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID; + ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : IOMMU_PASID_INVALID; idxd_device_set_perm_entry(idxd, ie); rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie); @@ -1265,7 +1265,7 @@ int idxd_wq_request_irq(struct idxd_wq *wq) free_irq(ie->vector, ie); err_irq: idxd_device_clear_perm_entry(idxd, ie); - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; return rc; } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 7ced8d283d98..417e602a46b6 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include "registers.h" diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 640d3048368e..e6ee267da0ff 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -105,7 +105,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) ie = idxd_get_ie(idxd, msix_idx); ie->id = msix_idx; ie->int_handle = INVALID_INT_HANDLE; - ie->pasid = INVALID_IOASID; + ie->pasid = IOMMU_PASID_INVALID; spin_lock_init(&ie->list_lock); init_llist_head(&ie->pending_llist); diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index aa314ebec587..242f1f0b9f09 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -80,7 +80,7 @@ static void idxd_int_handle_revoke_drain(struct idxd_irq_entry *ie) desc.opcode = DSA_OPCODE_DRAIN; desc.priv = 1; - if (ie->pasid != INVALID_IOASID) + if (ie->pasid != IOMMU_PASID_INVALID) desc.pasid = ie->pasid; desc.int_handle = ie->int_handle; portal = idxd_wq_portal_addr(wq); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 0f348439ef0e..10bb20ff50fd 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1958,7 +1958,7 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, return 0; } - if (pasid == INVALID_IOASID) + if (pasid == IOMMU_PASID_INVALID) pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), @@ -2039,7 +2039,7 @@ irqreturn_t dmar_fault(int irq, void *dev_id) if (!ratelimited) /* Using pasid -1 if pasid is not present */ dmar_fault_do_one(iommu, type, fault_reason, - pasid_present ? pasid : INVALID_IOASID, + pasid_present ? pasid : IOMMU_PASID_INVALID, source_id, guest_addr); fault_index++; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6c2d1ffb5b0a..350c33605fd3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -876,7 +876,7 @@ void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, return; } /* For request-without-pasid, get the pasid from context entry */ - if (intel_iommu_sm && pasid == INVALID_IOASID) + if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID) pasid = PASID_RID2PASID; dir_index = pasid >> PASID_PDE_SHIFT; diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7367f56c3bad..3848a1b0800c 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -273,7 +273,7 @@ static int pasid_to_svm_sdev(struct device *dev, unsigned int pasid, if (WARN_ON(!mutex_is_locked(&pasid_mutex))) return -EINVAL; - if (pasid == INVALID_IOASID || pasid >= PASID_MAX) + if (pasid == IOMMU_PASID_INVALID || pasid >= PASID_MAX) return -EINVAL; svm = pasid_private_find(pasid); diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index 734bf0e036ee..bbc9c6fd3310 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -7,6 +7,7 @@ #include typedef unsigned int ioasid_t; +#define INVALID_IOASID ((ioasid_t)-1) typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d3f81dc6e4dd..54f535ff9868 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -192,7 +192,6 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) #ifdef CONFIG_IOMMU_API @@ -1175,12 +1174,13 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream static inline bool pasid_valid(ioasid_t ioasid) { - return ioasid != INVALID_IOASID; + return ioasid != IOMMU_PASID_INVALID; } + #ifdef CONFIG_IOMMU_SVA static inline void mm_pasid_init(struct mm_struct *mm) { - mm->pasid = INVALID_IOASID; + mm->pasid = IOMMU_PASID_INVALID; } void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, diff --git a/mm/init-mm.c b/mm/init-mm.c index c9327abb771c..a084039f55d8 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -10,7 +10,7 @@ #include #include -#include +#include #include #ifndef INIT_MM_CONTEXT @@ -40,7 +40,7 @@ struct mm_struct init_mm = { .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, #ifdef CONFIG_IOMMU_SVA - .pasid = INVALID_IOASID, + .pasid = IOMMU_PASID_INVALID, #endif INIT_MM_CONTEXT(init_mm) }; -- GitLab From 99b5726b44230329f35b4c4d7fe1577d4f4edb31 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 22 Mar 2023 13:08:03 -0700 Subject: [PATCH 1770/5631] iommu: Remove ioasid infrastructure This has no use anymore, delete it all. Reviewed-by: Kevin Tian Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230322200803.869130-8-jacob.jun.pan@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/dma/idxd/idxd.h | 1 - drivers/iommu/Kconfig | 5 - drivers/iommu/Makefile | 1 - drivers/iommu/intel/iommu.h | 1 - drivers/iommu/intel/svm.c | 1 - drivers/iommu/ioasid.c | 422 ------------------------------------ drivers/iommu/iommu-sva.h | 1 - include/linux/ioasid.h | 75 ------- 8 files changed, 507 deletions(-) delete mode 100644 drivers/iommu/ioasid.c delete mode 100644 include/linux/ioasid.h diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 417e602a46b6..dd2a6ed8949b 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index c4928514e5e2..db98c3f86e8c 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -3,10 +3,6 @@ config IOMMU_IOVA tristate -# The IOASID library may also be used by non-IOMMU_API users -config IOASID - tristate - # IOMMU_API always gets selected by whoever wants it. config IOMMU_API bool @@ -160,7 +156,6 @@ config IOMMU_DMA # Shared Virtual Addressing config IOMMU_SVA bool - select IOASID config FSL_PAMU bool "Freescale IOMMU support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index f461d0651385..769e43d780ce 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o obj-$(CONFIG_IOMMU_IO_PGTABLE_DART) += io-pgtable-dart.o -obj-$(CONFIG_IOASID) += ioasid.o obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index a2010fb120e2..65b15be72878 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 3848a1b0800c..e95b339e9cdc 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c deleted file mode 100644 index a786c034907c..000000000000 --- a/drivers/iommu/ioasid.c +++ /dev/null @@ -1,422 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * I/O Address Space ID allocator. There is one global IOASID space, split into - * subsets. Users create a subset with DECLARE_IOASID_SET, then allocate and - * free IOASIDs with ioasid_alloc() and ioasid_free(). - */ -#include -#include -#include -#include -#include - -struct ioasid_data { - ioasid_t id; - struct ioasid_set *set; - void *private; - struct rcu_head rcu; -}; - -/* - * struct ioasid_allocator_data - Internal data structure to hold information - * about an allocator. There are two types of allocators: - * - * - Default allocator always has its own XArray to track the IOASIDs allocated. - * - Custom allocators may share allocation helpers with different private data. - * Custom allocators that share the same helper functions also share the same - * XArray. - * Rules: - * 1. Default allocator is always available, not dynamically registered. This is - * to prevent race conditions with early boot code that want to register - * custom allocators or allocate IOASIDs. - * 2. Custom allocators take precedence over the default allocator. - * 3. When all custom allocators sharing the same helper functions are - * unregistered (e.g. due to hotplug), all outstanding IOASIDs must be - * freed. Otherwise, outstanding IOASIDs will be lost and orphaned. - * 4. When switching between custom allocators sharing the same helper - * functions, outstanding IOASIDs are preserved. - * 5. When switching between custom allocator and default allocator, all IOASIDs - * must be freed to ensure unadulterated space for the new allocator. - * - * @ops: allocator helper functions and its data - * @list: registered custom allocators - * @slist: allocators share the same ops but different data - * @flags: attributes of the allocator - * @xa: xarray holds the IOASID space - * @rcu: used for kfree_rcu when unregistering allocator - */ -struct ioasid_allocator_data { - struct ioasid_allocator_ops *ops; - struct list_head list; - struct list_head slist; -#define IOASID_ALLOCATOR_CUSTOM BIT(0) /* Needs framework to track results */ - unsigned long flags; - struct xarray xa; - struct rcu_head rcu; -}; - -static DEFINE_SPINLOCK(ioasid_allocator_lock); -static LIST_HEAD(allocators_list); - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque); -static void default_free(ioasid_t ioasid, void *opaque); - -static struct ioasid_allocator_ops default_ops = { - .alloc = default_alloc, - .free = default_free, -}; - -static struct ioasid_allocator_data default_allocator = { - .ops = &default_ops, - .flags = 0, - .xa = XARRAY_INIT(ioasid_xa, XA_FLAGS_ALLOC), -}; - -static struct ioasid_allocator_data *active_allocator = &default_allocator; - -static ioasid_t default_alloc(ioasid_t min, ioasid_t max, void *opaque) -{ - ioasid_t id; - - if (xa_alloc(&default_allocator.xa, &id, opaque, XA_LIMIT(min, max), GFP_ATOMIC)) { - pr_err("Failed to alloc ioasid from %d to %d\n", min, max); - return INVALID_IOASID; - } - - return id; -} - -static void default_free(ioasid_t ioasid, void *opaque) -{ - struct ioasid_data *ioasid_data; - - ioasid_data = xa_erase(&default_allocator.xa, ioasid); - kfree_rcu(ioasid_data, rcu); -} - -/* Allocate and initialize a new custom allocator with its helper functions */ -static struct ioasid_allocator_data *ioasid_alloc_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - - ia_data = kzalloc(sizeof(*ia_data), GFP_ATOMIC); - if (!ia_data) - return NULL; - - xa_init_flags(&ia_data->xa, XA_FLAGS_ALLOC); - INIT_LIST_HEAD(&ia_data->slist); - ia_data->flags |= IOASID_ALLOCATOR_CUSTOM; - ia_data->ops = ops; - - /* For tracking custom allocators that share the same ops */ - list_add_tail(&ops->list, &ia_data->slist); - - return ia_data; -} - -static bool use_same_ops(struct ioasid_allocator_ops *a, struct ioasid_allocator_ops *b) -{ - return (a->free == b->free) && (a->alloc == b->alloc); -} - -/** - * ioasid_register_allocator - register a custom allocator - * @ops: the custom allocator ops to be registered - * - * Custom allocators take precedence over the default xarray based allocator. - * Private data associated with the IOASID allocated by the custom allocators - * are managed by IOASID framework similar to data stored in xa by default - * allocator. - * - * There can be multiple allocators registered but only one is active. In case - * of runtime removal of a custom allocator, the next one is activated based - * on the registration ordering. - * - * Multiple allocators can share the same alloc() function, in this case the - * IOASID space is shared. - */ -int ioasid_register_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *ia_data; - struct ioasid_allocator_data *pallocator; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - - ia_data = ioasid_alloc_allocator(ops); - if (!ia_data) { - ret = -ENOMEM; - goto out_unlock; - } - - /* - * No particular preference, we activate the first one and keep - * the later registered allocators in a list in case the first one gets - * removed due to hotplug. - */ - if (list_empty(&allocators_list)) { - WARN_ON(active_allocator != &default_allocator); - /* Use this new allocator if default is not active */ - if (xa_empty(&active_allocator->xa)) { - rcu_assign_pointer(active_allocator, ia_data); - list_add_tail(&ia_data->list, &allocators_list); - goto out_unlock; - } - pr_warn("Default allocator active with outstanding IOASID\n"); - ret = -EAGAIN; - goto out_free; - } - - /* Check if the allocator is already registered */ - list_for_each_entry(pallocator, &allocators_list, list) { - if (pallocator->ops == ops) { - pr_err("IOASID allocator already registered\n"); - ret = -EEXIST; - goto out_free; - } else if (use_same_ops(pallocator->ops, ops)) { - /* - * If the new allocator shares the same ops, - * then they will share the same IOASID space. - * We should put them under the same xarray. - */ - list_add_tail(&ops->list, &pallocator->slist); - goto out_free; - } - } - list_add_tail(&ia_data->list, &allocators_list); - - spin_unlock(&ioasid_allocator_lock); - return 0; -out_free: - kfree(ia_data); -out_unlock: - spin_unlock(&ioasid_allocator_lock); - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_register_allocator); - -/** - * ioasid_unregister_allocator - Remove a custom IOASID allocator ops - * @ops: the custom allocator to be removed - * - * Remove an allocator from the list, activate the next allocator in - * the order it was registered. Or revert to default allocator if all - * custom allocators are unregistered without outstanding IOASIDs. - */ -void ioasid_unregister_allocator(struct ioasid_allocator_ops *ops) -{ - struct ioasid_allocator_data *pallocator; - struct ioasid_allocator_ops *sops; - - spin_lock(&ioasid_allocator_lock); - if (list_empty(&allocators_list)) { - pr_warn("No custom IOASID allocators active!\n"); - goto exit_unlock; - } - - list_for_each_entry(pallocator, &allocators_list, list) { - if (!use_same_ops(pallocator->ops, ops)) - continue; - - if (list_is_singular(&pallocator->slist)) { - /* No shared helper functions */ - list_del(&pallocator->list); - /* - * All IOASIDs should have been freed before - * the last allocator that shares the same ops - * is unregistered. - */ - WARN_ON(!xa_empty(&pallocator->xa)); - if (list_empty(&allocators_list)) { - pr_info("No custom IOASID allocators, switch to default.\n"); - rcu_assign_pointer(active_allocator, &default_allocator); - } else if (pallocator == active_allocator) { - rcu_assign_pointer(active_allocator, - list_first_entry(&allocators_list, - struct ioasid_allocator_data, list)); - pr_info("IOASID allocator changed"); - } - kfree_rcu(pallocator, rcu); - break; - } - /* - * Find the matching shared ops to delete, - * but keep outstanding IOASIDs - */ - list_for_each_entry(sops, &pallocator->slist, list) { - if (sops == ops) { - list_del(&ops->list); - break; - } - } - break; - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_unregister_allocator); - -/** - * ioasid_set_data - Set private data for an allocated ioasid - * @ioasid: the ID to set data - * @data: the private data - * - * For IOASID that is already allocated, private data can be set - * via this API. Future lookup can be done via ioasid_find. - */ -int ioasid_set_data(ioasid_t ioasid, void *data) -{ - struct ioasid_data *ioasid_data; - int ret = 0; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (ioasid_data) - rcu_assign_pointer(ioasid_data->private, data); - else - ret = -ENOENT; - spin_unlock(&ioasid_allocator_lock); - - /* - * Wait for readers to stop accessing the old private data, so the - * caller can free it. - */ - if (!ret) - synchronize_rcu(); - - return ret; -} -EXPORT_SYMBOL_GPL(ioasid_set_data); - -/** - * ioasid_alloc - Allocate an IOASID - * @set: the IOASID set - * @min: the minimum ID (inclusive) - * @max: the maximum ID (inclusive) - * @private: data private to the caller - * - * Allocate an ID between @min and @max. The @private pointer is stored - * internally and can be retrieved with ioasid_find(). - * - * Return: the allocated ID on success, or %INVALID_IOASID on failure. - */ -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private) -{ - struct ioasid_data *data; - void *adata; - ioasid_t id; - - data = kzalloc(sizeof(*data), GFP_ATOMIC); - if (!data) - return INVALID_IOASID; - - data->set = set; - data->private = private; - - /* - * Custom allocator needs allocator data to perform platform specific - * operations. - */ - spin_lock(&ioasid_allocator_lock); - adata = active_allocator->flags & IOASID_ALLOCATOR_CUSTOM ? active_allocator->ops->pdata : data; - id = active_allocator->ops->alloc(min, max, adata); - if (id == INVALID_IOASID) { - pr_err("Failed ASID allocation %lu\n", active_allocator->flags); - goto exit_free; - } - - if ((active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) && - xa_alloc(&active_allocator->xa, &id, data, XA_LIMIT(id, id), GFP_ATOMIC)) { - /* Custom allocator needs framework to store and track allocation results */ - pr_err("Failed to alloc ioasid from %d\n", id); - active_allocator->ops->free(id, active_allocator->ops->pdata); - goto exit_free; - } - data->id = id; - - spin_unlock(&ioasid_allocator_lock); - return id; -exit_free: - spin_unlock(&ioasid_allocator_lock); - kfree(data); - return INVALID_IOASID; -} -EXPORT_SYMBOL_GPL(ioasid_alloc); - -/** - * ioasid_free - Free an ioasid - * @ioasid: the ID to remove - */ -void ioasid_free(ioasid_t ioasid) -{ - struct ioasid_data *ioasid_data; - - spin_lock(&ioasid_allocator_lock); - ioasid_data = xa_load(&active_allocator->xa, ioasid); - if (!ioasid_data) { - pr_err("Trying to free unknown IOASID %u\n", ioasid); - goto exit_unlock; - } - - active_allocator->ops->free(ioasid, active_allocator->ops->pdata); - /* Custom allocator needs additional steps to free the xa element */ - if (active_allocator->flags & IOASID_ALLOCATOR_CUSTOM) { - ioasid_data = xa_erase(&active_allocator->xa, ioasid); - kfree_rcu(ioasid_data, rcu); - } - -exit_unlock: - spin_unlock(&ioasid_allocator_lock); -} -EXPORT_SYMBOL_GPL(ioasid_free); - -/** - * ioasid_find - Find IOASID data - * @set: the IOASID set - * @ioasid: the IOASID to find - * @getter: function to call on the found object - * - * The optional getter function allows to take a reference to the found object - * under the rcu lock. The function can also check if the object is still valid: - * if @getter returns false, then the object is invalid and NULL is returned. - * - * If the IOASID exists, return the private pointer passed to ioasid_alloc. - * Private data can be NULL if not set. Return an error if the IOASID is not - * found, or if @set is not NULL and the IOASID does not belong to the set. - */ -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - void *priv; - struct ioasid_data *ioasid_data; - struct ioasid_allocator_data *idata; - - rcu_read_lock(); - idata = rcu_dereference(active_allocator); - ioasid_data = xa_load(&idata->xa, ioasid); - if (!ioasid_data) { - priv = ERR_PTR(-ENOENT); - goto unlock; - } - if (set && ioasid_data->set != set) { - /* data found but does not belong to the set */ - priv = ERR_PTR(-EACCES); - goto unlock; - } - /* Now IOASID and its set is verified, we can return the private data */ - priv = rcu_dereference(ioasid_data->private); - if (getter && !getter(priv)) - priv = NULL; -unlock: - rcu_read_unlock(); - - return priv; -} -EXPORT_SYMBOL_GPL(ioasid_find); - -MODULE_AUTHOR("Jean-Philippe Brucker "); -MODULE_AUTHOR("Jacob Pan "); -MODULE_DESCRIPTION("IO Address Space ID (IOASID) allocator"); -MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h index c22d0174ad61..54946b5a7caf 100644 --- a/drivers/iommu/iommu-sva.h +++ b/drivers/iommu/iommu-sva.h @@ -5,7 +5,6 @@ #ifndef _IOMMU_SVA_H #define _IOMMU_SVA_H -#include #include /* I/O Page fault */ diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h deleted file mode 100644 index bbc9c6fd3310..000000000000 --- a/include/linux/ioasid.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_IOASID_H -#define __LINUX_IOASID_H - -#include -#include -#include - -typedef unsigned int ioasid_t; -#define INVALID_IOASID ((ioasid_t)-1) -typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); -typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); - -struct ioasid_set { - int dummy; -}; - -/** - * struct ioasid_allocator_ops - IOASID allocator helper functions and data - * - * @alloc: helper function to allocate IOASID - * @free: helper function to free IOASID - * @list: for tracking ops that share helper functions but not data - * @pdata: data belong to the allocator, provided when calling alloc() - */ -struct ioasid_allocator_ops { - ioasid_alloc_fn_t alloc; - ioasid_free_fn_t free; - struct list_head list; - void *pdata; -}; - -#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } - -#if IS_ENABLED(CONFIG_IOASID) -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private); -void ioasid_free(ioasid_t ioasid); -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)); -int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); -void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); -int ioasid_set_data(ioasid_t ioasid, void *data); - -#else /* !CONFIG_IOASID */ -static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, - ioasid_t max, void *private) -{ - return INVALID_IOASID; -} - -static inline void ioasid_free(ioasid_t ioasid) { } - -static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - return NULL; -} - -static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) -{ - return -ENOTSUPP; -} - -static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) -{ -} - -static inline int ioasid_set_data(ioasid_t ioasid, void *data) -{ - return -ENOTSUPP; -} - -#endif /* CONFIG_IOASID */ -#endif /* __LINUX_IOASID_H */ -- GitLab From 7511f28792c6c724cc584a42f3eeb2fa5af689c4 Mon Sep 17 00:00:00 2001 From: Mark Salter Date: Wed, 29 Mar 2023 13:21:29 -0400 Subject: [PATCH 1771/5631] dmaengine: tegra: explicitly select DMA_VIRTUAL_CHANNELS Enabling TEGRA186_GPC_DMA will cause this build failure unless some other DMA driver which uses DMA_VIRTUAL_CHANNELS is enabled: ERROR: modpost: "vchan_dma_desc_free_list" [drivers/dma/tegra186-gpc-dma.ko] undefined! ERROR: modpost: "vchan_init" [drivers/dma/tegra186-gpc-dma.ko] undefined! ERROR: modpost: "vchan_tx_submit" [drivers/dma/tegra186-gpc-dma.ko] undefined! ERROR: modpost: "vchan_tx_desc_free" [drivers/dma/tegra186-gpc-dma.ko] undefined! ERROR: modpost: "vchan_find_desc" [drivers/dma/tegra186-gpc-dma.ko] undefined! make[1]: *** [scripts/Makefile.modpost:136: Module.symvers] Error 1 Add an explicit select of DMA_VIRTUAL_CHANNELS to avoid this. Signed-off-by: Mark Salter Link: https://lore.kernel.org/r/20230329172129.88403-1-msalter@redhat.com Signed-off-by: Vinod Koul --- drivers/dma/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index fb7073fc034f..f5f422f9b850 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -623,6 +623,7 @@ config TEGRA186_GPC_DMA depends on (ARCH_TEGRA || COMPILE_TEST) && ARCH_DMA_ADDR_T_64BIT depends on IOMMU_API select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS help Support for the NVIDIA Tegra General Purpose Central DMA controller. The DMA controller has multiple DMA channels which can be configured -- GitLab From fbe05149e40bc6891b1ed6097ac26dbaa32d2bf8 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Wed, 29 Mar 2023 21:23:49 +0530 Subject: [PATCH 1772/5631] dmaengine: ti: k3-udma: Add system suspend/resume support The K3 platforms configure the DMA resources with the help of the TI's System Firmware's Device Manager(DM) over TISCI. The group of DMA related Resource Manager[1] TISCI messages includes: INTA, RINGACC, UDMAP, and PSI-L. This configuration however, does not persist in the DM after leaving from Suspend-to-RAM state. We have to restore the DMA channel configuration over TISCI for all configured channels when returning from suspend. The TISCI resource management calls for each DMA type (UDMA, PKTDMA, BCDMA) happen in device_free_chan_resources() and device_alloc_chan_resources(). In pm_suspend() we store the current udma_chan_config for channels that still have attached clients and call device_free_chan_resources(). In pm_resume() restore the udma_channel_config from backup and call device_alloc_chan_resources() for those channels. Drivers like CPSW that use k3-udma-glue already do their own DMA resource management so use the late system suspend/resume hooks. [1] https://software-dl.ti.com/tisci/esd/latest/2_tisci_msgs/index.html#resource-management-rm Signed-off-by: Vignesh Raghavendra [g-vlaev@ti.com: Add patch description and config backup] [g-vlaev@ti.com: Supend only channels with clients] Signed-off-by: Georgi Vlaev Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20230329155349.2566010-1-vigneshr@ti.com Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma.c | 54 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 7e23a6fdef95..f652a217be76 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -305,6 +305,8 @@ struct udma_chan { /* Channel configuration parameters */ struct udma_chan_config config; + /* Channel configuration parameters (backup) */ + struct udma_chan_config backup_config; /* dmapool for packet mode descriptors */ bool use_dma_pool; @@ -5522,11 +5524,63 @@ static int udma_probe(struct platform_device *pdev) return ret; } +static int udma_pm_suspend(struct device *dev) +{ + struct udma_dev *ud = dev_get_drvdata(dev); + struct dma_device *dma_dev = &ud->ddev; + struct dma_chan *chan; + struct udma_chan *uc; + + list_for_each_entry(chan, &dma_dev->channels, device_node) { + if (chan->client_count) { + uc = to_udma_chan(chan); + /* backup the channel configuration */ + memcpy(&uc->backup_config, &uc->config, + sizeof(struct udma_chan_config)); + dev_dbg(dev, "Suspending channel %s\n", + dma_chan_name(chan)); + ud->ddev.device_free_chan_resources(chan); + } + } + + return 0; +} + +static int udma_pm_resume(struct device *dev) +{ + struct udma_dev *ud = dev_get_drvdata(dev); + struct dma_device *dma_dev = &ud->ddev; + struct dma_chan *chan; + struct udma_chan *uc; + int ret; + + list_for_each_entry(chan, &dma_dev->channels, device_node) { + if (chan->client_count) { + uc = to_udma_chan(chan); + /* restore the channel configuration */ + memcpy(&uc->config, &uc->backup_config, + sizeof(struct udma_chan_config)); + dev_dbg(dev, "Resuming channel %s\n", + dma_chan_name(chan)); + ret = ud->ddev.device_alloc_chan_resources(chan); + if (ret) + return ret; + } + } + + return 0; +} + +static const struct dev_pm_ops udma_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(udma_pm_suspend, udma_pm_resume) +}; + static struct platform_driver udma_driver = { .driver = { .name = "ti-udma", .of_match_table = udma_of_match, .suppress_bind_attrs = true, + .pm = &udma_pm_ops, }, .probe = udma_probe, }; -- GitLab From 9afea57384d4ae7b2034593eac7fa76c7122762a Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Fri, 31 Mar 2023 11:31:23 +0800 Subject: [PATCH 1773/5631] iommu/sprd: Release dma buffer to avoid memory leak When attaching to a domain, the driver would alloc a DMA buffer which is used to store address mapping table, and it need to be released when the IOMMU domain is freed. Signed-off-by: Chunyan Zhang Link: https://lore.kernel.org/r/20230331033124.864691-2-zhang.lyra@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/sprd-iommu.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index ae94d74b73f4..7df1f730c778 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -151,13 +151,6 @@ static struct iommu_domain *sprd_iommu_domain_alloc(unsigned int domain_type) return &dom->domain; } -static void sprd_iommu_domain_free(struct iommu_domain *domain) -{ - struct sprd_iommu_domain *dom = to_sprd_domain(domain); - - kfree(dom); -} - static void sprd_iommu_first_vpn(struct sprd_iommu_domain *dom) { struct sprd_iommu_device *sdev = dom->sdev; @@ -230,6 +223,28 @@ static void sprd_iommu_hw_en(struct sprd_iommu_device *sdev, bool en) sprd_iommu_update_bits(sdev, reg_cfg, mask, 0, val); } +static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom) +{ + size_t pgt_size; + + /* Nothing need to do if the domain hasn't been attached */ + if (!dom->sdev) + return; + + pgt_size = sprd_iommu_pgt_size(&dom->domain); + dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa); + dom->sdev = NULL; + sprd_iommu_hw_en(dom->sdev, false); +} + +static void sprd_iommu_domain_free(struct iommu_domain *domain) +{ + struct sprd_iommu_domain *dom = to_sprd_domain(domain); + + sprd_iommu_cleanup(dom); + kfree(dom); +} + static int sprd_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { -- GitLab From 816c698c052471f525bea92ff0aeeda8a5844a85 Mon Sep 17 00:00:00 2001 From: Chunyan Zhang Date: Fri, 31 Mar 2023 11:31:24 +0800 Subject: [PATCH 1774/5631] iommu/sprd: Add support for reattaching an existing domain This IOMMU driver should allow a domain to be attached more than once. If IOMMU is reattaching to the same domain which is attached, there's nothing to be done. If reattching to a previously-used domain, do not alloc DMA buffer again which stores address mapping table to avoid memory leak. Signed-off-by: Chunyan Zhang Link: https://lore.kernel.org/r/20230331033124.864691-3-zhang.lyra@gmail.com Signed-off-by: Joerg Roedel --- drivers/iommu/sprd-iommu.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c index 7df1f730c778..3513b2b108bf 100644 --- a/drivers/iommu/sprd-iommu.c +++ b/drivers/iommu/sprd-iommu.c @@ -62,6 +62,7 @@ enum sprd_iommu_version { * @eb: gate clock which controls IOMMU access */ struct sprd_iommu_device { + struct sprd_iommu_domain *dom; enum sprd_iommu_version ver; u32 *prot_page_va; dma_addr_t prot_page_pa; @@ -252,15 +253,27 @@ static int sprd_iommu_attach_device(struct iommu_domain *domain, struct sprd_iommu_domain *dom = to_sprd_domain(domain); size_t pgt_size = sprd_iommu_pgt_size(domain); - if (dom->sdev) - return -EINVAL; + /* The device is attached to this domain */ + if (sdev->dom == dom) + return 0; - dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); - if (!dom->pgt_va) - return -ENOMEM; + /* The first time that domain is attaching to a device */ + if (!dom->pgt_va) { + dom->pgt_va = dma_alloc_coherent(sdev->dev, pgt_size, &dom->pgt_pa, GFP_KERNEL); + if (!dom->pgt_va) + return -ENOMEM; + + dom->sdev = sdev; + } - dom->sdev = sdev; + sdev->dom = dom; + /* + * One sprd IOMMU serves one client device only, disabled it before + * configure mapping table to avoid access conflict in case other + * mapping table is stored in. + */ + sprd_iommu_hw_en(sdev, false); sprd_iommu_first_ppn(dom); sprd_iommu_first_vpn(dom); sprd_iommu_vpn_range(dom); -- GitLab From 6332a6ced62ac0c9ad7617be34aa2ee4543a52ab Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 29 Mar 2023 08:01:32 +0200 Subject: [PATCH 1775/5631] media: pvrusb2: clean up unneeded complexity in pvrusb2 class logic The pvrusb2 driver struct class logic was dynamically creating a class that should have just been static as it did not do anything special and was only a wrapper around a stock "struct class" implementation. Clean this all up by making a static struct class and modifying the code to correctly reference it. By doing so, lots of unneeded lines of code were removed, and #ifdef logic was cleaned up so that the .c files are not cluttered up with extra complexity following the proper kernel coding style. Cc: Mike Isely Cc: Mauro Carvalho Chehab Cc: linux-media@vger.kernel.org Reviewed-by: Hans Verkuil Link: https://lore.kernel.org/r/20230329060132.2688621-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/media/usb/pvrusb2/pvrusb2-main.c | 18 ++----- drivers/media/usb/pvrusb2/pvrusb2-sysfs.c | 59 +++++++---------------- drivers/media/usb/pvrusb2/pvrusb2-sysfs.h | 16 +++--- 3 files changed, 29 insertions(+), 64 deletions(-) diff --git a/drivers/media/usb/pvrusb2/pvrusb2-main.c b/drivers/media/usb/pvrusb2/pvrusb2-main.c index ce4d566e4e5a..721dafd2c14b 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-main.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-main.c @@ -16,9 +16,7 @@ #include "pvrusb2-context.h" #include "pvrusb2-debug.h" #include "pvrusb2-v4l2.h" -#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS #include "pvrusb2-sysfs.h" -#endif /* CONFIG_VIDEO_PVRUSB2_SYSFS */ #define DRIVER_AUTHOR "Mike Isely " #define DRIVER_DESC "Hauppauge WinTV-PVR-USB2 MPEG2 Encoder/Tuner" @@ -36,10 +34,6 @@ int pvrusb2_debug = DEFAULT_DEBUG_MASK; module_param_named(debug,pvrusb2_debug,int,S_IRUGO|S_IWUSR); MODULE_PARM_DESC(debug, "Debug trace mask"); -#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS -static struct pvr2_sysfs_class *class_ptr = NULL; -#endif /* CONFIG_VIDEO_PVRUSB2_SYSFS */ - static void pvr_setup_attach(struct pvr2_context *pvr) { /* Create association with v4l layer */ @@ -48,9 +42,7 @@ static void pvr_setup_attach(struct pvr2_context *pvr) /* Create association with dvb layer */ pvr2_dvb_create(pvr); #endif -#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS - pvr2_sysfs_create(pvr,class_ptr); -#endif /* CONFIG_VIDEO_PVRUSB2_SYSFS */ + pvr2_sysfs_create(pvr); } static int pvr_probe(struct usb_interface *intf, @@ -115,9 +107,7 @@ static int __init pvr_init(void) return ret; } -#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS - class_ptr = pvr2_sysfs_class_create(); -#endif /* CONFIG_VIDEO_PVRUSB2_SYSFS */ + pvr2_sysfs_class_create(); ret = usb_register(&pvr_driver); @@ -141,9 +131,7 @@ static void __exit pvr_exit(void) pvr2_context_global_done(); -#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS - pvr2_sysfs_class_destroy(class_ptr); -#endif /* CONFIG_VIDEO_PVRUSB2_SYSFS */ + pvr2_sysfs_class_destroy(); pvr2_trace(PVR2_TRACE_INIT,"pvr_exit complete"); } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c index 3e42e209be37..a8c0b513e58e 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c +++ b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c @@ -66,10 +66,6 @@ struct pvr2_sysfs_ctl_item { char name[80]; }; -struct pvr2_sysfs_class { - struct class class; -}; - static ssize_t show_name(struct device *class_dev, struct device_attribute *attr, char *buf) @@ -487,15 +483,6 @@ static void pvr2_sysfs_tear_down_controls(struct pvr2_sysfs *sfp) } -static void pvr2_sysfs_class_release(struct class *class) -{ - struct pvr2_sysfs_class *clp; - clp = container_of(class,struct pvr2_sysfs_class,class); - pvr2_sysfs_trace("Destroying pvr2_sysfs_class id=%p",clp); - kfree(clp); -} - - static void pvr2_sysfs_release(struct device *class_dev) { pvr2_sysfs_trace("Releasing class_dev id=%p",class_dev); @@ -503,6 +490,12 @@ static void pvr2_sysfs_release(struct device *class_dev) } +static struct class pvr2_class = { + .name = "pvrusb2", + .dev_release = pvr2_sysfs_release, +}; + + static void class_dev_destroy(struct pvr2_sysfs *sfp) { struct device *dev; @@ -614,8 +607,7 @@ static ssize_t unit_number_show(struct device *class_dev, } -static void class_dev_create(struct pvr2_sysfs *sfp, - struct pvr2_sysfs_class *class_ptr) +static void class_dev_create(struct pvr2_sysfs *sfp) { struct usb_device *usb_dev; struct device *class_dev; @@ -628,7 +620,7 @@ static void class_dev_create(struct pvr2_sysfs *sfp, pvr2_sysfs_trace("Creating class_dev id=%p",class_dev); - class_dev->class = &class_ptr->class; + class_dev->class = &pvr2_class; dev_set_name(class_dev, "%s", pvr2_hdw_get_device_identifier(sfp->channel.hdw)); @@ -753,47 +745,30 @@ static void pvr2_sysfs_internal_check(struct pvr2_channel *chp) } -struct pvr2_sysfs *pvr2_sysfs_create(struct pvr2_context *mp, - struct pvr2_sysfs_class *class_ptr) +void pvr2_sysfs_create(struct pvr2_context *mp) { struct pvr2_sysfs *sfp; sfp = kzalloc(sizeof(*sfp),GFP_KERNEL); - if (!sfp) return sfp; + if (!sfp) + return; pvr2_trace(PVR2_TRACE_STRUCT,"Creating pvr2_sysfs id=%p",sfp); pvr2_channel_init(&sfp->channel,mp); sfp->channel.check_func = pvr2_sysfs_internal_check; - class_dev_create(sfp,class_ptr); - return sfp; + class_dev_create(sfp); } - -struct pvr2_sysfs_class *pvr2_sysfs_class_create(void) +void pvr2_sysfs_class_create(void) { - struct pvr2_sysfs_class *clp; - clp = kzalloc(sizeof(*clp),GFP_KERNEL); - if (!clp) return clp; - pvr2_sysfs_trace("Creating and registering pvr2_sysfs_class id=%p", - clp); - clp->class.name = "pvrusb2"; - clp->class.class_release = pvr2_sysfs_class_release; - clp->class.dev_release = pvr2_sysfs_release; - if (class_register(&clp->class)) { - pvr2_sysfs_trace( - "Registration failed for pvr2_sysfs_class id=%p",clp); - kfree(clp); - clp = NULL; - } - return clp; + if (class_register(&pvr2_class)) + pvr2_sysfs_trace("Registration failed for pvr2_sysfs_class"); } -void pvr2_sysfs_class_destroy(struct pvr2_sysfs_class *clp) +void pvr2_sysfs_class_destroy(void) { - pvr2_sysfs_trace("Unregistering pvr2_sysfs_class id=%p", clp); - if (clp) - class_unregister(&clp->class); + class_unregister(&pvr2_class); } diff --git a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h index ac580ff39b5f..375a5372e95c 100644 --- a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h +++ b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h @@ -10,13 +10,15 @@ #include #include "pvrusb2-context.h" -struct pvr2_sysfs; -struct pvr2_sysfs_class; +#ifdef CONFIG_VIDEO_PVRUSB2_SYSFS +void pvr2_sysfs_class_create(void); +void pvr2_sysfs_class_destroy(void); +void pvr2_sysfs_create(struct pvr2_context *mp); +#else +static inline void pvr2_sysfs_class_create(void) { } +static inline void pvr2_sysfs_class_destroy(void) { } +static inline void pvr2_sysfs_create(struct pvr2_context *mp) { } +#endif -struct pvr2_sysfs_class *pvr2_sysfs_class_create(void); -void pvr2_sysfs_class_destroy(struct pvr2_sysfs_class *); - -struct pvr2_sysfs *pvr2_sysfs_create(struct pvr2_context *, - struct pvr2_sysfs_class *); #endif /* __PVRUSB2_SYSFS_H */ -- GitLab From 827026ae2e56ec05ef1155661079badbbfc0b038 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Mar 2023 09:06:37 +0200 Subject: [PATCH 1776/5631] dmaengine: mv_xor_v2: Fix an error code. If the probe is deferred, -EPROBE_DEFER should be returned, not +EPROBE_DEFER. Fixes: 3cd2c313f1d6 ("dmaengine: mv_xor_v2: Fix clock resource by adding a register clock") Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/201170dff832a3c496d125772e10070cd834ebf2.1679814350.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- drivers/dma/mv_xor_v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 89790beba305..0991b8265829 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -752,7 +752,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev) xor_dev->clk = devm_clk_get(&pdev->dev, NULL); if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { - ret = EPROBE_DEFER; + ret = -EPROBE_DEFER; goto disable_reg_clk; } if (!IS_ERR(xor_dev->clk)) { -- GitLab From 376c2c9b04e97ddb1fbb9d9156456e2331891506 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Mar 2023 09:06:38 +0200 Subject: [PATCH 1777/5631] dmaengine: mv_xor_v2: Use some clk_ helper functions to simplify code Use devm_clk_get_[optional_]enabled() instead of hand writing it. It saves some LoC. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/cc14e490f4e6002a17c9c7d283fe6a93179766c2.1679814350.git.christophe.jaillet@wanadoo.fr Signed-off-by: Vinod Koul --- drivers/dma/mv_xor_v2.c | 35 +++++++---------------------------- 1 file changed, 7 insertions(+), 28 deletions(-) diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 0991b8265829..cea8aa946f9c 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -739,32 +739,18 @@ static int mv_xor_v2_probe(struct platform_device *pdev) if (ret) return ret; - xor_dev->reg_clk = devm_clk_get(&pdev->dev, "reg"); - if (PTR_ERR(xor_dev->reg_clk) != -ENOENT) { - if (!IS_ERR(xor_dev->reg_clk)) { - ret = clk_prepare_enable(xor_dev->reg_clk); - if (ret) - return ret; - } else { - return PTR_ERR(xor_dev->reg_clk); - } - } + xor_dev->reg_clk = devm_clk_get_optional_enabled(&pdev->dev, "reg"); + if (IS_ERR(xor_dev->reg_clk)) + return PTR_ERR(xor_dev->reg_clk); - xor_dev->clk = devm_clk_get(&pdev->dev, NULL); - if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; - goto disable_reg_clk; - } - if (!IS_ERR(xor_dev->clk)) { - ret = clk_prepare_enable(xor_dev->clk); - if (ret) - goto disable_reg_clk; - } + xor_dev->clk = devm_clk_get_enabled(&pdev->dev, NULL); + if (IS_ERR(xor_dev->clk)) + return PTR_ERR(xor_dev->clk); ret = platform_msi_domain_alloc_irqs(&pdev->dev, 1, mv_xor_v2_set_msi_msg); if (ret) - goto disable_clk; + return ret; xor_dev->irq = msi_get_virq(&pdev->dev, 0); @@ -866,10 +852,6 @@ static int mv_xor_v2_probe(struct platform_device *pdev) xor_dev->hw_desq_virt, xor_dev->hw_desq); free_msi_irqs: platform_msi_domain_free_irqs(&pdev->dev); -disable_clk: - clk_disable_unprepare(xor_dev->clk); -disable_reg_clk: - clk_disable_unprepare(xor_dev->reg_clk); return ret; } @@ -889,9 +871,6 @@ static int mv_xor_v2_remove(struct platform_device *pdev) tasklet_kill(&xor_dev->irq_tasklet); - clk_disable_unprepare(xor_dev->clk); - clk_disable_unprepare(xor_dev->reg_clk); - return 0; } -- GitLab From 9e410fe3dc9a938bc47f71dff254be7419bd40d2 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 3 Mar 2023 13:34:11 -0800 Subject: [PATCH 1778/5631] dmaengine: idxd: Add descriptor definitions for 16 bytes of pattern in memory fill operation The memory fill operation (0x04) can fill in memory with either 8 bytes or 16 bytes of pattern. To fill in memory with 16 bytes of pattern, the first 8 bytes are provided in pattern lower in bytes 16-23 and the next 8 bytes are in pattern upper in bytes 40-47 in the descriptor. Currently only 8 bytes of pattern is enabled. Add descriptor definitions for pattern lower and pattern upper so that user can use 16 bytes of pattern to fill memory. Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230303213413.3357431-2-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 1d553bedbdb5..c43d7df5fc15 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -180,6 +180,7 @@ struct dsa_hw_desc { uint64_t rdback_addr; uint64_t pattern; uint64_t desc_list_addr; + uint64_t pattern_lower; }; union { uint64_t dst_addr; @@ -244,6 +245,9 @@ struct dsa_hw_desc { uint16_t dest_app_tag_seed; }; + /* Fill */ + uint64_t pattern_upper; + uint8_t op_specific[24]; }; } __attribute__((packed)); -- GitLab From 12bbc2c2605516e781cd86e3cde9fe1f889b72cc Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 3 Mar 2023 13:34:12 -0800 Subject: [PATCH 1779/5631] dmaengine: idxd: Add descriptor definitions for DIX generate operation The Data Integrity Extension (DIX) generate operation (0x17) computes the Data Integrity Field (DIF) on the source data and writes only the computed DIF for each source block to the PI destination address. Add descriptor definitions for this operation so that user can use DSA to accelerate DIX generate operation. Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230303213413.3357431-3-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index c43d7df5fc15..4c12e93a6aa6 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -78,6 +78,7 @@ enum dsa_opcode { DSA_OPCODE_DIF_INS, DSA_OPCODE_DIF_STRP, DSA_OPCODE_DIF_UPDT, + DSA_OPCODE_DIX_GEN = 0x17, DSA_OPCODE_CFLUSH = 0x20, }; @@ -248,6 +249,17 @@ struct dsa_hw_desc { /* Fill */ uint64_t pattern_upper; + /* DIX generate */ + struct { + uint8_t dix_gen_res; + uint8_t dest_dif_flags; + uint8_t dif_flags; + uint8_t dix_gen_res2[13]; + uint32_t ref_tag_seed; + uint16_t app_tag_mask; + uint16_t app_tag_seed; + }; + uint8_t op_specific[24]; }; } __attribute__((packed)); @@ -326,6 +338,14 @@ struct dsa_completion_record { uint16_t dif_upd_dest_app_tag; }; + /* DIX generate */ + struct { + uint64_t dix_gen_res; + uint32_t dix_ref_tag; + uint16_t dix_app_tag_mask; + uint16_t dix_app_tag; + }; + uint8_t op_specific[16]; }; } __attribute__((packed)); -- GitLab From 6fec8938b7b4fe2b2c503fe87b2783a50bff0415 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 3 Mar 2023 13:34:13 -0800 Subject: [PATCH 1780/5631] dmaengine: idxd: Add descriptor definitions for translation fetch operation The translation fetch operation (0x0A) fetches address translations for the address range specified in the descriptor by issuing address translation (ATS) requests to the IOMMU. Add descriptor definitions for the operation so that user can use DSA to accelerate translation fetch. Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230303213413.3357431-4-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 4c12e93a6aa6..fc47635b57dc 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -72,6 +72,7 @@ enum dsa_opcode { DSA_OPCODE_CR_DELTA, DSA_OPCODE_AP_DELTA, DSA_OPCODE_DUALCAST, + DSA_OPCODE_TRANSL_FETCH, DSA_OPCODE_CRCGEN = 0x10, DSA_OPCODE_COPY_CRC, DSA_OPCODE_DIF_CHECK, @@ -182,6 +183,7 @@ struct dsa_hw_desc { uint64_t pattern; uint64_t desc_list_addr; uint64_t pattern_lower; + uint64_t transl_fetch_addr; }; union { uint64_t dst_addr; @@ -192,6 +194,7 @@ struct dsa_hw_desc { union { uint32_t xfer_size; uint32_t desc_count; + uint32_t region_size; }; uint16_t int_handle; uint16_t rsvd1; @@ -249,6 +252,12 @@ struct dsa_hw_desc { /* Fill */ uint64_t pattern_upper; + /* Translation fetch */ + struct { + uint64_t transl_fetch_res; + uint32_t region_stride; + }; + /* DIX generate */ struct { uint8_t dix_gen_res; -- GitLab From 34ca00662eb7f184f249dd2168ebea78d945e3e4 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 3 Mar 2023 13:37:31 -0800 Subject: [PATCH 1781/5631] dmaengine: idxd: reformat swerror output to standard Linux bitmap output SWERROR register is 4 64bit wide registers. Currently the sysfs attribute just outputs 4 64bit hex integers. Convert to output with %*pb format specifier. Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230303213732.3357494-2-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/idxd.h | 1 + drivers/dma/idxd/init.c | 2 +- drivers/dma/idxd/sysfs.c | 10 ++++------ 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 7ced8d283d98..ad7a1e8a0e1c 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -598,6 +598,7 @@ int idxd_register_driver(void); void idxd_unregister_driver(void); void idxd_wqs_quiesce(struct idxd_device *idxd); bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc); +void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count); /* device interrupt control */ irqreturn_t idxd_misc_thread(int vec, void *data); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index a85efcda7095..bddff1d4359d 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -388,7 +388,7 @@ static void idxd_read_table_offsets(struct idxd_device *idxd) dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset); } -static void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count) +void multi_u64_to_bmap(unsigned long *bmap, u64 *val, int count) { int i, j, nr; diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 18cd8151dee0..927c9d645121 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1452,15 +1452,13 @@ static ssize_t errors_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idxd_device *idxd = confdev_to_idxd(dev); - int i, out = 0; + DECLARE_BITMAP(swerr_bmap, 256); + bitmap_zero(swerr_bmap, 256); spin_lock(&idxd->dev_lock); - for (i = 0; i < 4; i++) - out += sysfs_emit_at(buf, out, "%#018llx ", idxd->sw_err.bits[i]); + multi_u64_to_bmap(swerr_bmap, &idxd->sw_err.bits[0], 4); spin_unlock(&idxd->dev_lock); - out--; - out += sysfs_emit_at(buf, out, "\n"); - return out; + return sysfs_emit(buf, "%*pb\n", 256, swerr_bmap); } static DEVICE_ATTR_RO(errors); -- GitLab From 9f0d99b327edd217462852635498694aaf471b33 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 3 Mar 2023 13:37:32 -0800 Subject: [PATCH 1782/5631] dmaengine: idxd: expose IAA CAP register via sysfs knob Add IAA (IAX) capability mask sysfs attribute to expose to applications. The mask provides application knowledge of what capabilities this IAA device supports. This mask is available for IAA 2.0 device or later. Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230303213732.3357494-3-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- .../ABI/stable/sysfs-driver-dma-idxd | 8 +++++++ drivers/dma/idxd/idxd.h | 1 + drivers/dma/idxd/init.c | 4 ++++ drivers/dma/idxd/registers.h | 21 ++++++++++++++++ drivers/dma/idxd/sysfs.c | 24 +++++++++++++++++++ 5 files changed, 58 insertions(+) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index 3becc9a82bdf..d5e3dd3d8434 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -136,6 +136,14 @@ Description: The last executed device administrative command's status/error. Also last configuration error overloaded. Writing to it will clear the status. +What: /sys/bus/dsa/devices/dsa/iaa_cap +Date: Sept 14, 2022 +KernelVersion: 6.0.0 +Contact: dmaengine@vger.kernel.org +Description: IAA (IAX) capability mask. Exported to user space for application + consumption. This attribute should only be visible on IAA devices + that are version 2 or later. + What: /sys/bus/dsa/devices/wq./block_on_fault Date: Oct 27, 2020 KernelVersion: 5.11.0 diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index ad7a1e8a0e1c..eca2c9d76db6 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -232,6 +232,7 @@ struct idxd_hw { union engine_cap_reg engine_cap; struct opcap opcap; u32 cmd_cap; + union iaa_cap_reg iaa_cap; }; enum idxd_device_state { diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index bddff1d4359d..a78cfd361c04 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -460,6 +460,10 @@ static void idxd_read_caps(struct idxd_device *idxd) dev_dbg(dev, "opcap[%d]: %#llx\n", i, idxd->hw.opcap.bits[i]); } multi_u64_to_bmap(idxd->opcap_bmap, &idxd->hw.opcap.bits[0], 4); + + /* read iaa cap */ + if (idxd->data->type == IDXD_TYPE_IAX && idxd->hw.version >= DEVICE_VERSION_2) + idxd->hw.iaa_cap.bits = ioread64(idxd->reg_base + IDXD_IAACAP_OFFSET); } static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_data *data) diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index fe3b8d04f9db..338289a66f00 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -276,6 +276,27 @@ union sw_err_reg { u64 bits[4]; } __packed; +union iaa_cap_reg { + struct { + u64 dec_aecs_format_ver:1; + u64 drop_init_bits:1; + u64 chaining:1; + u64 force_array_output_mod:1; + u64 load_part_aecs:1; + u64 comp_early_abort:1; + u64 nested_comp:1; + u64 diction_comp:1; + u64 header_gen:1; + u64 crypto_gcm:1; + u64 crypto_cfb:1; + u64 crypto_xts:1; + u64 rsvd:52; + }; + u64 bits; +} __packed; + +#define IDXD_IAACAP_OFFSET 0x180 + union msix_perm { struct { u32 rsvd:2; diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 927c9d645121..2eba8cab25a1 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1561,6 +1561,18 @@ static ssize_t cmd_status_store(struct device *dev, struct device_attribute *att } static DEVICE_ATTR_RW(cmd_status); +static ssize_t iaa_cap_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = confdev_to_idxd(dev); + + if (idxd->hw.version < DEVICE_VERSION_2) + return -EOPNOTSUPP; + + return sysfs_emit(buf, "%#llx\n", idxd->hw.iaa_cap.bits); +} +static DEVICE_ATTR_RO(iaa_cap); + static bool idxd_device_attr_max_batch_size_invisible(struct attribute *attr, struct idxd_device *idxd) { @@ -1583,6 +1595,14 @@ static bool idxd_device_attr_read_buffers_invisible(struct attribute *attr, idxd->data->type == IDXD_TYPE_IAX; } +static bool idxd_device_attr_iaa_cap_invisible(struct attribute *attr, + struct idxd_device *idxd) +{ + return attr == &dev_attr_iaa_cap.attr && + (idxd->data->type != IDXD_TYPE_IAX || + idxd->hw.version < DEVICE_VERSION_2); +} + static umode_t idxd_device_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { @@ -1595,6 +1615,9 @@ static umode_t idxd_device_attr_visible(struct kobject *kobj, if (idxd_device_attr_read_buffers_invisible(attr, idxd)) return 0; + if (idxd_device_attr_iaa_cap_invisible(attr, idxd)) + return 0; + return attr->mode; } @@ -1620,6 +1643,7 @@ static struct attribute *idxd_device_attributes[] = { &dev_attr_read_buffer_limit.attr, &dev_attr_cdev_major.attr, &dev_attr_cmd_status.attr, + &dev_attr_iaa_cap.attr, NULL, }; -- GitLab From 86de3bbfe45e5a7e64d4f24a1c034725072420d8 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 27 Mar 2023 11:48:33 +0200 Subject: [PATCH 1783/5631] dmaengine: sh: rz-dmac: Remove unused rz_dmac_chan.*_word_size The src_word_size and dst_word_size members of the rz_dmac_chan structure were never used, so they can be removed. Signed-off-by: Geert Uytterhoeven Reviewed-by: Biju Das Link: https://lore.kernel.org/r/021bdf56f1716276a55bcfb1ea81bba5f1d42b3d.1679910274.git.geert+renesas@glider.be Signed-off-by: Vinod Koul --- drivers/dma/sh/rz-dmac.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c index 6b62e01ba658..9479f29692d3 100644 --- a/drivers/dma/sh/rz-dmac.c +++ b/drivers/dma/sh/rz-dmac.c @@ -67,8 +67,6 @@ struct rz_dmac_chan { struct rz_dmac_desc *desc; int descs_allocated; - enum dma_slave_buswidth src_word_size; - enum dma_slave_buswidth dst_word_size; dma_addr_t src_per_address; dma_addr_t dst_per_address; @@ -603,9 +601,7 @@ static int rz_dmac_config(struct dma_chan *chan, u32 val; channel->src_per_address = config->src_addr; - channel->src_word_size = config->src_addr_width; channel->dst_per_address = config->dst_addr; - channel->dst_word_size = config->dst_addr_width; val = rz_dmac_ds_to_val_mapping(config->dst_addr_width); if (val == CHCFG_DS_INVALID) -- GitLab From 27fc5ec673b527dbc2f44787246a39c5ecc01de5 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 1 Mar 2023 17:32:53 +0100 Subject: [PATCH 1784/5631] clk: Introduce devm_clk_hw_register_gate_parent_data() Add an API for clock gate that uses parent_data for the parent instead of a string parent_name. Reviewed-by: Peng Fan Reviewed-by: Fabio Estevam Tested-by: Adam Ford #imx8mp-beacon-kit Tested-by: Alexander Stein Signed-off-by: Marek Vasut Tested-by: Richard Leitner Reviewed-by: Stephen Boyd Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230301163257.49005-1-marex@denx.de --- include/linux/clk-provider.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..92b7c794c627 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) + +/** + * devm_clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- GitLab From 6cd95f7b151cdd7852ed9f212faeea8f98ecba10 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 1 Mar 2023 17:32:54 +0100 Subject: [PATCH 1785/5631] clk: imx: imx8mp: Add audiomix block control Unlike the other block control IPs in i.MX8M, the audiomix is mostly a series of clock gates and muxes. Model it as a large static table of gates and muxes with one exception, which is the PLL14xx . The PLL14xx SAI PLL has to be registered separately. Reviewed-by: Marco Felsch Reviewed-by: Peng Fan Reviewed-by: Fabio Estevam Tested-by: Adam Ford #imx8mp-beacon-kit Tested-by: Alexander Stein Tested-by: Luca Ceresoli Signed-off-by: Marek Vasut Tested-by: Richard Leitner Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230301163257.49005-2-marex@denx.de --- drivers/clk/imx/Makefile | 2 +- drivers/clk/imx/clk-imx8mp-audiomix.c | 277 ++++++++++++++++++++++++++ 2 files changed, 278 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/imx/clk-imx8mp-audiomix.c diff --git a/drivers/clk/imx/Makefile b/drivers/clk/imx/Makefile index a75d59f7cb8a..ae9d84ef046b 100644 --- a/drivers/clk/imx/Makefile +++ b/drivers/clk/imx/Makefile @@ -27,7 +27,7 @@ obj-$(CONFIG_MXC_CLK) += mxc-clk.o obj-$(CONFIG_CLK_IMX8MM) += clk-imx8mm.o obj-$(CONFIG_CLK_IMX8MN) += clk-imx8mn.o -obj-$(CONFIG_CLK_IMX8MP) += clk-imx8mp.o +obj-$(CONFIG_CLK_IMX8MP) += clk-imx8mp.o clk-imx8mp-audiomix.o obj-$(CONFIG_CLK_IMX8MQ) += clk-imx8mq.o obj-$(CONFIG_CLK_IMX93) += clk-imx93.o diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c new file mode 100644 index 000000000000..e4300df88f1a --- /dev/null +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -0,0 +1,277 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for i.MX8M Plus Audio BLK_CTRL + * + * Copyright (C) 2022 Marek Vasut + */ + +#include +#include +#include +#include +#include +#include + +#include + +#include "clk.h" + +#define CLKEN0 0x000 +#define CLKEN1 0x004 +#define SAI_MCLK_SEL(n) (0x300 + 4 * (n)) /* n in 0..5 */ +#define PDM_SEL 0x318 +#define SAI_PLL_GNRL_CTL 0x400 + +#define SAIn_MCLK1_PARENT(n) \ +static const struct clk_parent_data \ +clk_imx8mp_audiomix_sai##n##_mclk1_parents[] = { \ + { \ + .fw_name = "sai"__stringify(n), \ + .name = "sai"__stringify(n) \ + }, { \ + .fw_name = "sai"__stringify(n)"_mclk", \ + .name = "sai"__stringify(n)"_mclk" \ + }, \ +} + +SAIn_MCLK1_PARENT(1); +SAIn_MCLK1_PARENT(2); +SAIn_MCLK1_PARENT(3); +SAIn_MCLK1_PARENT(5); +SAIn_MCLK1_PARENT(6); +SAIn_MCLK1_PARENT(7); + +static const struct clk_parent_data clk_imx8mp_audiomix_sai_mclk2_parents[] = { + { .fw_name = "sai1", .name = "sai1" }, + { .fw_name = "sai2", .name = "sai2" }, + { .fw_name = "sai3", .name = "sai3" }, + { .name = "dummy" }, + { .fw_name = "sai5", .name = "sai5" }, + { .fw_name = "sai6", .name = "sai6" }, + { .fw_name = "sai7", .name = "sai7" }, + { .fw_name = "sai1_mclk", .name = "sai1_mclk" }, + { .fw_name = "sai2_mclk", .name = "sai2_mclk" }, + { .fw_name = "sai3_mclk", .name = "sai3_mclk" }, + { .name = "dummy" }, + { .fw_name = "sai5_mclk", .name = "sai5_mclk" }, + { .fw_name = "sai6_mclk", .name = "sai6_mclk" }, + { .fw_name = "sai7_mclk", .name = "sai7_mclk" }, + { .fw_name = "spdif_extclk", .name = "spdif_extclk" }, + { .name = "dummy" }, +}; + +static const struct clk_parent_data clk_imx8mp_audiomix_pdm_parents[] = { + { .fw_name = "pdm", .name = "pdm" }, + { .name = "sai_pll_out_div2" }, + { .fw_name = "sai1_mclk", .name = "sai1_mclk" }, + { .name = "dummy" }, +}; + + +static const struct clk_parent_data clk_imx8mp_audiomix_pll_parents[] = { + { .fw_name = "osc_24m", .name = "osc_24m" }, + { .name = "dummy" }, + { .name = "dummy" }, + { .name = "dummy" }, +}; + +static const struct clk_parent_data clk_imx8mp_audiomix_pll_bypass_sels[] = { + { .fw_name = "sai_pll", .name = "sai_pll" }, + { .fw_name = "sai_pll_ref_sel", .name = "sai_pll_ref_sel" }, +}; + +#define CLK_GATE(gname, cname) \ + { \ + gname"_cg", \ + IMX8MP_CLK_AUDIOMIX_##cname, \ + { .fw_name = "ahb", .name = "ahb" }, NULL, 1, \ + CLKEN0 + 4 * !!(IMX8MP_CLK_AUDIOMIX_##cname / 32), \ + 1, IMX8MP_CLK_AUDIOMIX_##cname % 32 \ + } + +#define CLK_SAIn(n) \ + { \ + "sai"__stringify(n)"_mclk1_sel", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK1_SEL, {}, \ + clk_imx8mp_audiomix_sai##n##_mclk1_parents, \ + ARRAY_SIZE(clk_imx8mp_audiomix_sai##n##_mclk1_parents), \ + SAI_MCLK_SEL(n), 1, 0 \ + }, { \ + "sai"__stringify(n)"_mclk2_sel", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK2_SEL, {}, \ + clk_imx8mp_audiomix_sai_mclk2_parents, \ + ARRAY_SIZE(clk_imx8mp_audiomix_sai_mclk2_parents), \ + SAI_MCLK_SEL(n), 4, 1 \ + }, { \ + "sai"__stringify(n)"_ipg_cg", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_IPG, \ + { .fw_name = "ahb", .name = "ahb" }, NULL, 1, \ + CLKEN0, 1, IMX8MP_CLK_AUDIOMIX_SAI##n##_IPG \ + }, { \ + "sai"__stringify(n)"_mclk1_cg", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK1, \ + { \ + .fw_name = "sai"__stringify(n)"_mclk1_sel", \ + .name = "sai"__stringify(n)"_mclk1_sel" \ + }, NULL, 1, \ + CLKEN0, 1, IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK1 \ + }, { \ + "sai"__stringify(n)"_mclk2_cg", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK2, \ + { \ + .fw_name = "sai"__stringify(n)"_mclk2_sel", \ + .name = "sai"__stringify(n)"_mclk2_sel" \ + }, NULL, 1, \ + CLKEN0, 1, IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK2 \ + }, { \ + "sai"__stringify(n)"_mclk3_cg", \ + IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK3, \ + { \ + .fw_name = "sai_pll_out_div2", \ + .name = "sai_pll_out_div2" \ + }, NULL, 1, \ + CLKEN0, 1, IMX8MP_CLK_AUDIOMIX_SAI##n##_MCLK3 \ + } + +#define CLK_PDM \ + { \ + "pdm_sel", IMX8MP_CLK_AUDIOMIX_PDM_SEL, {}, \ + clk_imx8mp_audiomix_pdm_parents, \ + ARRAY_SIZE(clk_imx8mp_audiomix_pdm_parents), \ + PDM_SEL, 2, 0 \ + } + +struct clk_imx8mp_audiomix_sel { + const char *name; + int clkid; + const struct clk_parent_data parent; /* For gate */ + const struct clk_parent_data *parents; /* For mux */ + int num_parents; + u16 reg; + u8 width; + u8 shift; +}; + +static struct clk_imx8mp_audiomix_sel sels[] = { + CLK_GATE("asrc", ASRC_IPG), + CLK_GATE("pdm", PDM_IPG), + CLK_GATE("earc", EARC_IPG), + CLK_GATE("ocrama", OCRAMA_IPG), + CLK_GATE("aud2htx", AUD2HTX_IPG), + CLK_GATE("earc_phy", EARC_PHY), + CLK_GATE("sdma2", SDMA2_ROOT), + CLK_GATE("sdma3", SDMA3_ROOT), + CLK_GATE("spba2", SPBA2_ROOT), + CLK_GATE("dsp", DSP_ROOT), + CLK_GATE("dspdbg", DSPDBG_ROOT), + CLK_GATE("edma", EDMA_ROOT), + CLK_GATE("audpll", AUDPLL_ROOT), + CLK_GATE("mu2", MU2_ROOT), + CLK_GATE("mu3", MU3_ROOT), + CLK_PDM, + CLK_SAIn(1), + CLK_SAIn(2), + CLK_SAIn(3), + CLK_SAIn(5), + CLK_SAIn(6), + CLK_SAIn(7) +}; + +static int clk_imx8mp_audiomix_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *priv; + struct device *dev = &pdev->dev; + void __iomem *base; + struct clk_hw *hw; + int i; + + priv = devm_kzalloc(dev, + struct_size(priv, hws, IMX8MP_CLK_AUDIOMIX_END), + GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->num = IMX8MP_CLK_AUDIOMIX_END; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) + return PTR_ERR(base); + + for (i = 0; i < ARRAY_SIZE(sels); i++) { + if (sels[i].num_parents == 1) { + hw = devm_clk_hw_register_gate_parent_data(dev, + sels[i].name, &sels[i].parent, 0, + base + sels[i].reg, sels[i].shift, 0, NULL); + } else { + hw = devm_clk_hw_register_mux_parent_data_table(dev, + sels[i].name, sels[i].parents, + sels[i].num_parents, 0, + base + sels[i].reg, + sels[i].shift, sels[i].width, + 0, NULL, NULL); + } + + if (IS_ERR(hw)) + return PTR_ERR(hw); + + priv->hws[sels[i].clkid] = hw; + } + + /* SAI PLL */ + hw = devm_clk_hw_register_mux_parent_data_table(dev, + "sai_pll_ref_sel", clk_imx8mp_audiomix_pll_parents, + ARRAY_SIZE(clk_imx8mp_audiomix_pll_parents), + CLK_SET_RATE_NO_REPARENT, base + SAI_PLL_GNRL_CTL, + 0, 2, 0, NULL, NULL); + priv->hws[IMX8MP_CLK_AUDIOMIX_SAI_PLL_REF_SEL] = hw; + + hw = imx_dev_clk_hw_pll14xx(dev, "sai_pll", "sai_pll_ref_sel", + base + 0x400, &imx_1443x_pll); + if (IS_ERR(hw)) + return PTR_ERR(hw); + priv->hws[IMX8MP_CLK_AUDIOMIX_SAI_PLL] = hw; + + hw = devm_clk_hw_register_mux_parent_data_table(dev, + "sai_pll_bypass", clk_imx8mp_audiomix_pll_bypass_sels, + ARRAY_SIZE(clk_imx8mp_audiomix_pll_bypass_sels), + CLK_SET_RATE_NO_REPARENT | CLK_SET_RATE_PARENT, + base + SAI_PLL_GNRL_CTL, 16, 1, 0, NULL, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + priv->hws[IMX8MP_CLK_AUDIOMIX_SAI_PLL_BYPASS] = hw; + + hw = devm_clk_hw_register_gate(dev, "sai_pll_out", "sai_pll_bypass", + 0, base + SAI_PLL_GNRL_CTL, 13, + 0, NULL); + if (IS_ERR(hw)) + return PTR_ERR(hw); + priv->hws[IMX8MP_CLK_AUDIOMIX_SAI_PLL_OUT] = hw; + + hw = devm_clk_hw_register_fixed_factor(dev, "sai_pll_out_div2", + "sai_pll_out", 0, 1, 2); + if (IS_ERR(hw)) + return PTR_ERR(hw); + + return devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_onecell_get, + priv); +} + +static const struct of_device_id clk_imx8mp_audiomix_of_match[] = { + { .compatible = "fsl,imx8mp-audio-blk-ctrl" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, clk_imx8mp_audiomix_of_match); + +static struct platform_driver clk_imx8mp_audiomix_driver = { + .probe = clk_imx8mp_audiomix_probe, + .driver = { + .name = "imx8mp-audio-blk-ctrl", + .of_match_table = clk_imx8mp_audiomix_of_match, + }, +}; + +module_platform_driver(clk_imx8mp_audiomix_driver); + +MODULE_AUTHOR("Marek Vasut "); +MODULE_DESCRIPTION("Freescale i.MX8MP Audio Block Controller driver"); +MODULE_LICENSE("GPL"); -- GitLab From 95a0aa7bb10e79cfbe8a1dc4b993d21dd58c253f Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 1 Mar 2023 17:32:55 +0100 Subject: [PATCH 1786/5631] dt-bindings: clock: imx8mp: Add audiomix block control Unlike the other block control IPs in i.MX8M, the audiomix is mostly a series of clock gates and muxes. Add DT bindings for this IP. Reviewed-by: Fabio Estevam Reviewed-by: Marco Felsch Reviewed-by: Peng Fan Reviewed-by: Rob Herring Tested-by: Adam Ford #imx8mp-beacon-kit Tested-by: Alexander Stein Signed-off-by: Marek Vasut Tested-by: Richard Leitner Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230301163257.49005-3-marex@denx.de --- .../bindings/clock/imx8mp-audiomix.yaml | 79 +++++++++++++++++++ 1 file changed, 79 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/imx8mp-audiomix.yaml diff --git a/Documentation/devicetree/bindings/clock/imx8mp-audiomix.yaml b/Documentation/devicetree/bindings/clock/imx8mp-audiomix.yaml new file mode 100644 index 000000000000..ff9600474df2 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/imx8mp-audiomix.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/imx8mp-audiomix.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP i.MX8MP AudioMIX Block Control Binding + +maintainers: + - Marek Vasut + +description: | + NXP i.MX8M Plus AudioMIX is dedicated clock muxing and gating IP + used to control Audio related clock on the SoC. + +properties: + compatible: + const: fsl,imx8mp-audio-blk-ctrl + + reg: + maxItems: 1 + + power-domains: + maxItems: 1 + + clocks: + minItems: 7 + maxItems: 7 + + clock-names: + items: + - const: ahb + - const: sai1 + - const: sai2 + - const: sai3 + - const: sai5 + - const: sai6 + - const: sai7 + + '#clock-cells': + const: 1 + description: + The clock consumer should specify the desired clock by having the clock + ID in its "clocks" phandle cell. See include/dt-bindings/clock/imx8mp-clock.h + for the full list of i.MX8MP IMX8MP_CLK_AUDIOMIX_ clock IDs. + +required: + - compatible + - reg + - clocks + - clock-names + - power-domains + - '#clock-cells' + +additionalProperties: false + +examples: + # Clock Control Module node: + - | + #include + + clock-controller@30e20000 { + compatible = "fsl,imx8mp-audio-blk-ctrl"; + reg = <0x30e20000 0x10000>; + #clock-cells = <1>; + clocks = <&clk IMX8MP_CLK_AUDIO_ROOT>, + <&clk IMX8MP_CLK_SAI1>, + <&clk IMX8MP_CLK_SAI2>, + <&clk IMX8MP_CLK_SAI3>, + <&clk IMX8MP_CLK_SAI5>, + <&clk IMX8MP_CLK_SAI6>, + <&clk IMX8MP_CLK_SAI7>; + clock-names = "ahb", + "sai1", "sai2", "sai3", + "sai5", "sai6", "sai7"; + power-domains = <&pgc_audio>; + }; + +... -- GitLab From f806bea3093cb3568e01b4375d5e1d7c8c47c1d4 Mon Sep 17 00:00:00 2001 From: Vignesh Raghavendra Date: Thu, 23 Mar 2023 17:31:07 +0530 Subject: [PATCH 1787/5631] dmaengine: ti: k3-udma: Workaround errata i2234 Per [1], UDMA TR15 transactions may hang if ICNT0 is less than 64B Work around is to set EOL flag is to 1 for ICNT0. Since, there is no performance penalty / side effects of setting EOL flag event ICNTO > 64B, just set the flag for all UDMAP TR15 descriptors. [1] https://www.ti.com/lit/er/sprz455a/sprz455a.pdf Errata doc for J721E DRA829/TDA4VM Processors Silicon Revision 1.1/1.0 (Rev. A) Signed-off-by: Vignesh Raghavendra [j-choudhary@ti.com: minor cleanups] Signed-off-by: Jayesh Choudhary Link: https://lore.kernel.org/r/20230323120107.27638-1-j-choudhary@ti.com Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma.c | 20 +++++++++++--------- include/linux/dma/ti-cppi5.h | 1 + 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index f652a217be76..c07feaff69c0 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -2966,6 +2966,7 @@ udma_prep_slave_sg_triggered_tr(struct udma_chan *uc, struct scatterlist *sgl, struct scatterlist *sgent; struct cppi5_tr_type15_t *tr_req = NULL; enum dma_slave_buswidth dev_width; + u32 csf = CPPI5_TR_CSF_SUPR_EVT; u16 tr_cnt0, tr_cnt1; dma_addr_t dev_addr; struct udma_desc *d; @@ -3036,6 +3037,7 @@ udma_prep_slave_sg_triggered_tr(struct udma_chan *uc, struct scatterlist *sgl, if (uc->ud->match_data->type == DMA_TYPE_UDMA) { asel = 0; + csf |= CPPI5_TR_CSF_EOL_ICNT0; } else { asel = (u64)uc->config.asel << K3_ADDRESS_ASEL_SHIFT; dev_addr |= asel; @@ -3059,7 +3061,7 @@ udma_prep_slave_sg_triggered_tr(struct udma_chan *uc, struct scatterlist *sgl, cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE15, false, true, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); - cppi5_tr_csf_set(&tr_req[tr_idx].flags, CPPI5_TR_CSF_SUPR_EVT); + cppi5_tr_csf_set(&tr_req[tr_idx].flags, csf); cppi5_tr_set_trigger(&tr_req[tr_idx].flags, uc->config.tr_trigger_type, CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC, 0, 0); @@ -3105,8 +3107,7 @@ udma_prep_slave_sg_triggered_tr(struct udma_chan *uc, struct scatterlist *sgl, cppi5_tr_init(&tr_req[tr_idx].flags, CPPI5_TR_TYPE15, false, true, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); - cppi5_tr_csf_set(&tr_req[tr_idx].flags, - CPPI5_TR_CSF_SUPR_EVT); + cppi5_tr_csf_set(&tr_req[tr_idx].flags, csf); cppi5_tr_set_trigger(&tr_req[tr_idx].flags, uc->config.tr_trigger_type, CPPI5_TR_TRIGGER_TYPE_ICNT2_DEC, @@ -3150,8 +3151,7 @@ udma_prep_slave_sg_triggered_tr(struct udma_chan *uc, struct scatterlist *sgl, d->residue += sg_len; } - cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, - CPPI5_TR_CSF_SUPR_EVT | CPPI5_TR_CSF_EOP); + cppi5_tr_csf_set(&tr_req[tr_idx - 1].flags, csf | CPPI5_TR_CSF_EOP); return d; } @@ -3680,6 +3680,7 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, int num_tr; size_t tr_size = sizeof(struct cppi5_tr_type15_t); u16 tr0_cnt0, tr0_cnt1, tr1_cnt0; + u32 csf = CPPI5_TR_CSF_SUPR_EVT; if (uc->config.dir != DMA_MEM_TO_MEM) { dev_err(chan->device->dev, @@ -3710,13 +3711,15 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, if (uc->ud->match_data->type != DMA_TYPE_UDMA) { src |= (u64)uc->ud->asel << K3_ADDRESS_ASEL_SHIFT; dest |= (u64)uc->ud->asel << K3_ADDRESS_ASEL_SHIFT; + } else { + csf |= CPPI5_TR_CSF_EOL_ICNT0; } tr_req = d->hwdesc[0].tr_req_base; cppi5_tr_init(&tr_req[0].flags, CPPI5_TR_TYPE15, false, true, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); - cppi5_tr_csf_set(&tr_req[0].flags, CPPI5_TR_CSF_SUPR_EVT); + cppi5_tr_csf_set(&tr_req[0].flags, csf); tr_req[0].addr = src; tr_req[0].icnt0 = tr0_cnt0; @@ -3735,7 +3738,7 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, if (num_tr == 2) { cppi5_tr_init(&tr_req[1].flags, CPPI5_TR_TYPE15, false, true, CPPI5_TR_EVENT_SIZE_COMPLETION, 0); - cppi5_tr_csf_set(&tr_req[1].flags, CPPI5_TR_CSF_SUPR_EVT); + cppi5_tr_csf_set(&tr_req[1].flags, csf); tr_req[1].addr = src + tr0_cnt1 * tr0_cnt0; tr_req[1].icnt0 = tr1_cnt0; @@ -3750,8 +3753,7 @@ udma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, tr_req[1].dicnt3 = 1; } - cppi5_tr_csf_set(&tr_req[num_tr - 1].flags, - CPPI5_TR_CSF_SUPR_EVT | CPPI5_TR_CSF_EOP); + cppi5_tr_csf_set(&tr_req[num_tr - 1].flags, csf | CPPI5_TR_CSF_EOP); if (uc->config.metadata_size) d->vd.tx.metadata_ops = &metadata_ops; diff --git a/include/linux/dma/ti-cppi5.h b/include/linux/dma/ti-cppi5.h index efa2f0309f00..c53c0f6e3b1a 100644 --- a/include/linux/dma/ti-cppi5.h +++ b/include/linux/dma/ti-cppi5.h @@ -616,6 +616,7 @@ static inline void *cppi5_hdesc_get_swdata(struct cppi5_host_desc_t *desc) #define CPPI5_TR_CSF_SUPR_EVT BIT(2) #define CPPI5_TR_CSF_EOL_ADV_SHIFT (4U) #define CPPI5_TR_CSF_EOL_ADV_MASK GENMASK(6, 4) +#define CPPI5_TR_CSF_EOL_ICNT0 BIT(4) #define CPPI5_TR_CSF_EOP BIT(7) /** -- GitLab From a747051efa16d4304aacaf44fa0771667e28ca54 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 22 Mar 2023 08:10:01 -0400 Subject: [PATCH 1788/5631] dmaengine: tegra-apb: remove unused tdma_read function clang with W=1 reports drivers/dma/tegra20-apb-dma.c:236:19: error: unused function 'tdma_read' [-Werror,-Wunused-function] static inline u32 tdma_read(struct tegra_dma *tdma, u32 reg) ^ This function is not used so remove it. Signed-off-by: Tom Rix Reviewed-by: Jon Hunter Link: https://lore.kernel.org/r/20230322121001.2569909-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/dma/tegra20-apb-dma.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index eaafcbe4ca94..cc6b91f48979 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -233,11 +233,6 @@ static inline void tdma_write(struct tegra_dma *tdma, u32 reg, u32 val) writel(val, tdma->base_addr + reg); } -static inline u32 tdma_read(struct tegra_dma *tdma, u32 reg) -{ - return readl(tdma->base_addr + reg); -} - static inline void tdc_write(struct tegra_dma_channel *tdc, u32 reg, u32 val) { -- GitLab From 75358cf3319d5fed595946019deda5c2c26a203d Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 28 Mar 2023 12:42:30 -0500 Subject: [PATCH 1789/5631] pinctrl: amd: Adjust debugfs output More fields are to be added, so to keep the display from being too busy, adjust it. 1) Add a header to all columns 2) Except for interrupt, when fields have no data show empty 3) Remove otherwise blank whitespace Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230328174231.8924-2-mario.limonciello@amd.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 76 ++++++++++++++--------------------- 1 file changed, 30 insertions(+), 46 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 9236a132c7ba..822f29440f15 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -206,15 +206,12 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) char *level_trig; char *active_level; - char *interrupt_enable; char *interrupt_mask; char *wake_cntrl0; char *wake_cntrl1; char *wake_cntrl2; char *pin_sts; char *pull_up_sel; - char *pull_up_enable; - char *pull_down_enable; char *orientation; char debounce_value[40]; char *debounce_enable; @@ -246,6 +243,7 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) continue; } seq_printf(s, "GPIO bank%d\n", bank); + seq_puts(s, "gpio\tint|active|trigger|S0i3| S3|S4/S5| Z|wake|pull| orient| debounce|reg\n"); for (; i < pin_num; i++) { seq_printf(s, "#%d\t", i); raw_spin_lock_irqsave(&gpio_dev->lock, flags); @@ -255,7 +253,6 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) if (pin_reg & BIT(INTERRUPT_ENABLE_OFF)) { u8 level = (pin_reg >> ACTIVE_LEVEL_OFF) & ACTIVE_LEVEL_MASK; - interrupt_enable = "+"; if (level == ACTIVE_LEVEL_HIGH) active_level = "↑"; @@ -272,65 +269,54 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) else level_trig = " edge"; - } else { - interrupt_enable = "∅"; - active_level = "∅"; - level_trig = " ∅"; - } + if (pin_reg & BIT(INTERRUPT_MASK_OFF)) + interrupt_mask = "😛"; + else + interrupt_mask = "😷"; - if (pin_reg & BIT(INTERRUPT_MASK_OFF)) - interrupt_mask = "😛"; - else - interrupt_mask = "😷"; - seq_printf(s, "int %s (%s)| active-%s| %s-⚡| ", - interrupt_enable, + seq_printf(s, "%s| %s| %s|", interrupt_mask, active_level, level_trig); + } else + seq_puts(s, " ∅| | |"); if (pin_reg & BIT(WAKE_CNTRL_OFF_S0I3)) wake_cntrl0 = "⏰"; else - wake_cntrl0 = " ∅"; - seq_printf(s, "S0i3 %s| ", wake_cntrl0); + wake_cntrl0 = " "; + seq_printf(s, " %s| ", wake_cntrl0); if (pin_reg & BIT(WAKE_CNTRL_OFF_S3)) wake_cntrl1 = "⏰"; else - wake_cntrl1 = " ∅"; - seq_printf(s, "S3 %s| ", wake_cntrl1); + wake_cntrl1 = " "; + seq_printf(s, "%s|", wake_cntrl1); if (pin_reg & BIT(WAKE_CNTRL_OFF_S4)) wake_cntrl2 = "⏰"; else - wake_cntrl2 = " ∅"; - seq_printf(s, "S4/S5 %s| ", wake_cntrl2); + wake_cntrl2 = " "; + seq_printf(s, " %s|", wake_cntrl2); if (pin_reg & BIT(WAKECNTRL_Z_OFF)) wake_cntrlz = "⏰"; else - wake_cntrlz = " ∅"; - seq_printf(s, "Z %s| ", wake_cntrlz); + wake_cntrlz = " "; + seq_printf(s, "%s|", wake_cntrlz); if (pin_reg & BIT(PULL_UP_ENABLE_OFF)) { - pull_up_enable = "+"; if (pin_reg & BIT(PULL_UP_SEL_OFF)) pull_up_sel = "8k"; else pull_up_sel = "4k"; - } else { - pull_up_enable = "∅"; - pull_up_sel = " "; + seq_printf(s, "%s ↑|", + pull_up_sel); + } else if (pin_reg & BIT(PULL_DOWN_ENABLE_OFF)) { + seq_puts(s, " ↓|"); + } else { + seq_puts(s, " |"); } - seq_printf(s, "pull-↑ %s (%s)| ", - pull_up_enable, - pull_up_sel); - - if (pin_reg & BIT(PULL_DOWN_ENABLE_OFF)) - pull_down_enable = "+"; - else - pull_down_enable = "∅"; - seq_printf(s, "pull-↓ %s| ", pull_down_enable); if (pin_reg & BIT(OUTPUT_ENABLE_OFF)) { pin_sts = "output"; @@ -345,7 +331,7 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) else orientation = "↓"; } - seq_printf(s, "%s %s| ", pin_sts, orientation); + seq_printf(s, "%s %s|", pin_sts, orientation); db_cntrl = (DB_CNTRl_MASK << DB_CNTRL_OFF) & pin_reg; if (db_cntrl) { @@ -364,19 +350,17 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) unit = 61; } if ((DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF) == db_cntrl) - debounce_enable = "b +"; + debounce_enable = "b"; else if ((DB_TYPE_PRESERVE_LOW_GLITCH << DB_CNTRL_OFF) == db_cntrl) - debounce_enable = "↓ +"; + debounce_enable = "↓"; else - debounce_enable = "↑ +"; - + debounce_enable = "↑"; + snprintf(debounce_value, sizeof(debounce_value), "%06u", time * unit); + seq_printf(s, "%s (🕑 %sus)|", debounce_enable, debounce_value); } else { - debounce_enable = " ∅"; - time = 0; + seq_puts(s, " |"); } - snprintf(debounce_value, sizeof(debounce_value), "%u", time * unit); - seq_printf(s, "debounce %s (🕑 %sus)| ", debounce_enable, debounce_value); - seq_printf(s, " 0x%x\n", pin_reg); + seq_printf(s, "0x%x\n", pin_reg); } } } -- GitLab From 010f493d90ee1dbc32fa1ce51398f20d494c20c2 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 28 Mar 2023 12:42:31 -0500 Subject: [PATCH 1790/5631] pinctrl: amd: Add fields for interrupt status and wake status If the firmware has misconfigured a GPIO it may cause interrupt status or wake status bits to be set and not asserted. Add these to debug output to catch this case. Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230328174231.8924-3-mario.limonciello@amd.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-amd.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 822f29440f15..c250110f6775 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -211,6 +211,8 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) char *wake_cntrl1; char *wake_cntrl2; char *pin_sts; + char *interrupt_sts; + char *wake_sts; char *pull_up_sel; char *orientation; char debounce_value[40]; @@ -243,7 +245,7 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) continue; } seq_printf(s, "GPIO bank%d\n", bank); - seq_puts(s, "gpio\tint|active|trigger|S0i3| S3|S4/S5| Z|wake|pull| orient| debounce|reg\n"); + seq_puts(s, "gpio\t int|active|trigger|S0i3| S3|S4/S5| Z|wake|pull| orient| debounce|reg\n"); for (; i < pin_num; i++) { seq_printf(s, "#%d\t", i); raw_spin_lock_irqsave(&gpio_dev->lock, flags); @@ -274,12 +276,18 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) else interrupt_mask = "😷"; - seq_printf(s, "%s| %s| %s|", + if (pin_reg & BIT(INTERRUPT_STS_OFF)) + interrupt_sts = "🔥"; + else + interrupt_sts = " "; + + seq_printf(s, "%s %s| %s| %s|", + interrupt_sts, interrupt_mask, active_level, level_trig); } else - seq_puts(s, " ∅| | |"); + seq_puts(s, " ∅| | |"); if (pin_reg & BIT(WAKE_CNTRL_OFF_S0I3)) wake_cntrl0 = "⏰"; @@ -305,6 +313,12 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) wake_cntrlz = " "; seq_printf(s, "%s|", wake_cntrlz); + if (pin_reg & BIT(WAKE_STS_OFF)) + wake_sts = "🔥"; + else + wake_sts = " "; + seq_printf(s, " %s|", wake_sts); + if (pin_reg & BIT(PULL_UP_ENABLE_OFF)) { if (pin_reg & BIT(PULL_UP_SEL_OFF)) pull_up_sel = "8k"; -- GitLab From e9f92b9999055110249dacdc5f1a6dfda2a155f6 Mon Sep 17 00:00:00 2001 From: Harini Katakam Date: Thu, 16 Mar 2023 15:03:18 +0530 Subject: [PATCH 1791/5631] dmaengine: zynqmp_dma: Sync DMA and coherent masks Align ZDMA DMA as well as coherent memory masks to 44 bit. This is required when using >32 bit memory regions. Signed-off-by: Harini Katakam Acked-by: Michal Simek Link: https://lore.kernel.org/r/20230316093318.6722-1-harini.katakam@amd.com Signed-off-by: Vinod Koul --- drivers/dma/xilinx/zynqmp_dma.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c index ce359058c638..9360f43b8e0f 100644 --- a/drivers/dma/xilinx/zynqmp_dma.c +++ b/drivers/dma/xilinx/zynqmp_dma.c @@ -1060,7 +1060,11 @@ static int zynqmp_dma_probe(struct platform_device *pdev) zdev->dev = &pdev->dev; INIT_LIST_HEAD(&zdev->common.channels); - dma_set_mask(&pdev->dev, DMA_BIT_MASK(44)); + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44)); + if (ret) { + dev_err(&pdev->dev, "DMA not available for address range\n"); + return ret; + } dma_cap_set(DMA_MEMCPY, zdev->common.cap_mask); p = &zdev->common; -- GitLab From 156e96ff2172518b6f83e97d8f11f677bc668e22 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 23 Mar 2023 18:01:24 -0500 Subject: [PATCH 1792/5631] clk: imx: composite-8m: Add support to determine_rate Similar to imx/clk-composite-93 and imx/clk-divider-gate, the imx8m_clk_composite_divider_ops can support determine_rate. Without this the parent clocks are set to a fixed value, and if a consumer needs a slower reate, the clock is divided, but the division is only as good as the parent clock rate. With this added, the system can attempt to adjust the parent rate if the proper flags are set which can lead to a more precise clock value. Signed-off-by: Adam Ford Reviewed-by: Peng Fan Reviewed-by: Fabio Estevam Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230323230127.120883-2-aford173@gmail.com --- drivers/clk/imx/clk-composite-8m.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index cbf0d7955a00..6883a8199b6c 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -119,10 +119,17 @@ static int imx8m_clk_composite_divider_set_rate(struct clk_hw *hw, return ret; } +static int imx8m_clk_divider_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + return clk_divider_ops.determine_rate(hw, req); +} + static const struct clk_ops imx8m_clk_composite_divider_ops = { .recalc_rate = imx8m_clk_composite_divider_recalc_rate, .round_rate = imx8m_clk_composite_divider_round_rate, .set_rate = imx8m_clk_composite_divider_set_rate, + .determine_rate = imx8m_clk_divider_determine_rate, }; static u8 imx8m_clk_composite_mux_get_parent(struct clk_hw *hw) -- GitLab From 784a9b3916e949c00666588fd167c4ab245ec9d6 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 23 Mar 2023 18:01:25 -0500 Subject: [PATCH 1793/5631] clk: imx: Add imx8m_clk_hw_composite_flags macro In order to set custom flags to imx8m_clk_hw_composite, split it off into a separate macro which can accept additional flags. Signed-off-by: Adam Ford Reviewed-by: Fabio Estevam Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230323230127.120883-3-aford173@gmail.com --- drivers/clk/imx/clk.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 3d94722bbf99..621b0e84ef27 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -417,6 +417,10 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, _imx8m_clk_hw_composite(name, parent_names, reg, \ 0, IMX_COMPOSITE_CLK_FLAGS_DEFAULT) +#define imx8m_clk_hw_composite_flags(name, parent_names, reg, flags) \ + _imx8m_clk_hw_composite(name, parent_names, reg, \ + 0, IMX_COMPOSITE_CLK_FLAGS_DEFAULT | flags) + #define imx8m_clk_hw_composite_critical(name, parent_names, reg) \ _imx8m_clk_hw_composite(name, parent_names, reg, \ 0, IMX_COMPOSITE_CLK_FLAGS_CRITICAL) -- GitLab From 5fe6ec93f10b0765d59e0efb6ecba419a6a49d48 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 23 Mar 2023 18:01:26 -0500 Subject: [PATCH 1794/5631] clk: imx8mm: Let IMX8MM_CLK_LCDIF_PIXEL set parent rate By default the display pixel clock needs to be evenly divide down from 594MHz which rules out a significant number of resolution and refresh rates. The current clock tree looks something like: video_pll1 594000000 video_pll1_bypass 594000000 video_pll1_out 594000000 lcdif_pixel 148500000 Now that composite-8m supports determine_rate, we can allow lcdif_pixel to set the parent rate which then switches every clock in the chain to a new frequency when lcdif_pixel cannot evenly divide from video_pll1_out. Signed-off-by: Adam Ford Reviewed-by: Fabio Estevam Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230323230127.120883-4-aford173@gmail.com --- drivers/clk/imx/clk-imx8mm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index b618892170f2..075f643e3f35 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -468,7 +468,7 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_PCIE1_PHY] = imx8m_clk_hw_composite("pcie1_phy", imx8mm_pcie1_phy_sels, base + 0xa380); hws[IMX8MM_CLK_PCIE1_AUX] = imx8m_clk_hw_composite("pcie1_aux", imx8mm_pcie1_aux_sels, base + 0xa400); hws[IMX8MM_CLK_DC_PIXEL] = imx8m_clk_hw_composite("dc_pixel", imx8mm_dc_pixel_sels, base + 0xa480); - hws[IMX8MM_CLK_LCDIF_PIXEL] = imx8m_clk_hw_composite("lcdif_pixel", imx8mm_lcdif_pixel_sels, base + 0xa500); + hws[IMX8MM_CLK_LCDIF_PIXEL] = imx8m_clk_hw_composite_flags("lcdif_pixel", imx8mm_lcdif_pixel_sels, base + 0xa500, CLK_SET_RATE_PARENT); hws[IMX8MM_CLK_SAI1] = imx8m_clk_hw_composite("sai1", imx8mm_sai1_sels, base + 0xa580); hws[IMX8MM_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mm_sai2_sels, base + 0xa600); hws[IMX8MM_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mm_sai3_sels, base + 0xa680); -- GitLab From 46a974433ea7fa468b45db70536f7cea81feb87c Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 23 Mar 2023 18:01:27 -0500 Subject: [PATCH 1795/5631] clk: imx: Let IMX8MN_CLK_DISP_PIXEL set parent rate By default the display pixel clock needs to be evenly divide down from the video_pll_out clock which rules out a significant number of resolution and refresh rates. The current clock tree looks something like: video_pll 594000000 video_pll_bypass 594000000 video_pll_out 594000000 disp_pixel 148500000 disp_pixel_clk 148500000 Now that composite-8m supports determine_rate, we can allow disp_pixel to set the parent rate which then switches every clock in the chain to a new frequency when disp_pixel cannot evenly divide from video_pll_out. Signed-off-by: Adam Ford Reviewed-by: Fabio Estevam Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230323230127.120883-5-aford173@gmail.com --- drivers/clk/imx/clk-imx8mn.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index a042ed3a9d6c..4b23a4648600 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -470,7 +470,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_DRAM_ALT] = imx8m_clk_hw_fw_managed_composite("dram_alt", imx8mn_dram_alt_sels, base + 0xa000); hws[IMX8MN_CLK_DRAM_APB] = imx8m_clk_hw_fw_managed_composite_critical("dram_apb", imx8mn_dram_apb_sels, base + 0xa080); - hws[IMX8MN_CLK_DISP_PIXEL] = imx8m_clk_hw_composite("disp_pixel", imx8mn_disp_pixel_sels, base + 0xa500); + hws[IMX8MN_CLK_DISP_PIXEL] = imx8m_clk_hw_composite_flags("disp_pixel", imx8mn_disp_pixel_sels, base + 0xa500, CLK_SET_RATE_PARENT); hws[IMX8MN_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mn_sai2_sels, base + 0xa600); hws[IMX8MN_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mn_sai3_sels, base + 0xa680); hws[IMX8MN_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mn_sai5_sels, base + 0xa780); -- GitLab From 3366c6fe2769fe653107626b3273e03156d9cac8 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 20 Mar 2023 19:12:09 -0400 Subject: [PATCH 1796/5631] dmaengine: ti: edma: remove unused edma_and function clang with W=1 reports drivers/dma/ti/edma.c:321:20: error: unused function 'edma_and' [-Werror,-Wunused-function] static inline void edma_and(struct edma_cc *ecc, int offset, unsigned and) ^ This function is not used, so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230320231209.1728940-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/dma/ti/edma.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index fa06d7e6d8e3..9ea91c640c32 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -318,14 +318,6 @@ static inline void edma_modify(struct edma_cc *ecc, int offset, unsigned and, edma_write(ecc, offset, val); } -static inline void edma_and(struct edma_cc *ecc, int offset, unsigned and) -{ - unsigned val = edma_read(ecc, offset); - - val &= and; - edma_write(ecc, offset, val); -} - static inline void edma_or(struct edma_cc *ecc, int offset, unsigned or) { unsigned val = edma_read(ecc, offset); -- GitLab From d77c4502d6238bbfed7cb9422748477839d506f2 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 20 Mar 2023 19:49:06 -0400 Subject: [PATCH 1797/5631] dmaengine: dw-edma: remove unused readq_ch and writeq_ch functions clang with W=1 reports drivers/dma/dw-edma/dw-edma-v0-core.c:162:20: error: unused function 'writeq_ch' [-Werror,-Wunused-function] static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, ^ drivers/dma/dw-edma/dw-edma-v0-core.c:185:19: error: unused function 'readq_ch' [-Werror,-Wunused-function] static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, ^ These functions and their wrapping macros are not used, so remove them. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230320234906.1730308-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-v0-core.c | 56 --------------------------- 1 file changed, 56 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index 72e79a0c0a4e..32f834a3848a 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -159,62 +159,6 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, #define GET_CH_32(dw, dir, ch, name) \ readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name)) -static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, - u64 value, void __iomem *addr) -{ - if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) { - u32 viewport_sel; - unsigned long flags; - - raw_spin_lock_irqsave(&dw->lock, flags); - - viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch); - if (dir == EDMA_DIR_READ) - viewport_sel |= BIT(31); - - writel(viewport_sel, - &(__dw_regs(dw)->type.legacy.viewport_sel)); - writeq(value, addr); - - raw_spin_unlock_irqrestore(&dw->lock, flags); - } else { - writeq(value, addr); - } -} - -static inline u64 readq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch, - const void __iomem *addr) -{ - u64 value; - - if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) { - u32 viewport_sel; - unsigned long flags; - - raw_spin_lock_irqsave(&dw->lock, flags); - - viewport_sel = FIELD_PREP(EDMA_V0_VIEWPORT_MASK, ch); - if (dir == EDMA_DIR_READ) - viewport_sel |= BIT(31); - - writel(viewport_sel, - &(__dw_regs(dw)->type.legacy.viewport_sel)); - value = readq(addr); - - raw_spin_unlock_irqrestore(&dw->lock, flags); - } else { - value = readq(addr); - } - - return value; -} - -#define SET_CH_64(dw, dir, ch, name, value) \ - writeq_ch(dw, dir, ch, value, &(__dw_ch_regs(dw, dir, ch)->name)) - -#define GET_CH_64(dw, dir, ch, name) \ - readq_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name)) - /* eDMA management callbacks */ void dw_edma_v0_core_off(struct dw_edma *dw) { -- GitLab From 49cd1dd15f74d73d4752b2c4f23f99b0753d2b3d Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 30 Mar 2023 15:03:58 -0500 Subject: [PATCH 1798/5631] dt-bindings: pinctrl: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Reviewed-by: Linus Walleij Acked-by: Hector Martin Acked-by: Geert Uytterhoeven Acked-by: Jernej Skrabec Reviewed-by: Heiko Stuebner #rockchip Reviewed-by: Damien Le Moal Reviewed-by: Krzysztof Kozlowski Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230330200402.2731992-1-robh@kernel.org Signed-off-by: Linus Walleij --- .../bindings/pinctrl/actions,s500-pinctrl.yaml | 2 +- .../bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/apple,pinctrl.yaml | 2 +- .../bindings/pinctrl/aspeed,ast2400-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/aspeed,ast2500-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/aspeed,ast2600-pinctrl.yaml | 6 +++--- .../bindings/pinctrl/brcm,bcm6318-pinctrl.yaml | 2 +- .../bindings/pinctrl/brcm,bcm63268-pinctrl.yaml | 2 +- .../bindings/pinctrl/brcm,bcm6328-pinctrl.yaml | 2 +- .../bindings/pinctrl/brcm,bcm6358-pinctrl.yaml | 2 +- .../bindings/pinctrl/brcm,bcm6362-pinctrl.yaml | 2 +- .../bindings/pinctrl/brcm,bcm6368-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml | 2 +- .../devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml | 2 +- .../devicetree/bindings/pinctrl/cirrus,lochnagar.yaml | 2 +- .../devicetree/bindings/pinctrl/cirrus,madera.yaml | 4 ++-- .../devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml | 2 +- .../devicetree/bindings/pinctrl/fsl,imx7d-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/fsl,imx8m-pinctrl.yaml | 2 +- .../bindings/pinctrl/fsl,imx8ulp-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/fsl,imx93-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/ingenic,pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/intel,lgm-io.yaml | 2 +- .../bindings/pinctrl/marvell,ac5-pinctrl.yaml | 4 ++-- .../bindings/pinctrl/mscc,ocelot-pinctrl.yaml | 6 +++--- .../devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml | 4 ++-- .../devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml | 4 ++-- .../pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml | 2 +- .../pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/qcom,tlmm-common.yaml | 2 +- .../devicetree/bindings/pinctrl/renesas,pfc.yaml | 2 +- .../bindings/pinctrl/renesas,rza1-ports.yaml | 2 +- .../bindings/pinctrl/renesas,rza2-pinctrl.yaml | 2 +- .../bindings/pinctrl/renesas,rzg2l-pinctrl.yaml | 2 +- .../bindings/pinctrl/renesas,rzn1-pinctrl.yaml | 2 +- .../bindings/pinctrl/renesas,rzv2m-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/rockchip,pinctrl.yaml | 10 +++++----- .../devicetree/bindings/pinctrl/samsung,pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/semtech,sx1501q.yaml | 6 +++--- .../bindings/pinctrl/socionext,uniphier-pinctrl.yaml | 2 +- .../devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml | 10 +++++----- .../bindings/pinctrl/starfive,jh7100-pinctrl.yaml | 6 +++--- .../bindings/pinctrl/sunplus,sp7021-pinctrl.yaml | 6 +++--- .../bindings/pinctrl/toshiba,visconti-pinctrl.yaml | 8 ++++---- .../devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml | 2 +- 45 files changed, 72 insertions(+), 72 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml index fb0f69ce9c16..7cb8a747feee 100644 --- a/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/actions,s500-pinctrl.yaml @@ -185,7 +185,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml index 1e3c8de6cae1..467016cbb037 100644 --- a/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sun4i-a10-pinctrl.yaml @@ -142,7 +142,7 @@ allOf: # boards are defining it at the moment so it would generate a lot of # warnings. - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: not: properties: diff --git a/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml index d3b11351ca45..9b4e0ae61ffe 100644 --- a/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml @@ -73,7 +73,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml index f4f1ee6b116e..bef85c25cdef 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml @@ -32,7 +32,7 @@ patternProperties: then: patternProperties: "^function|groups$": - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ ACPI, ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, DDCCLK, DDCDAT, EXTRST, FLACK, FLBUSY, FLWP, GPID, GPID0, GPID2, GPID4, GPID6, GPIE0, @@ -51,7 +51,7 @@ patternProperties: VGAHS, VGAVS, VPI18, VPI24, VPI30, VPO12, VPO24, WDTRST1, WDTRST2] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml index 8168f0088471..14c391f16899 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml @@ -44,7 +44,7 @@ patternProperties: then: patternProperties: "^function|groups$": - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ ACPI, ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, DDCCLK, DDCDAT, ESPI, FWSPICS1, FWSPICS2, GPID0, GPID2, GPID4, GPID6, GPIE0, GPIE2, @@ -65,7 +65,7 @@ patternProperties: VGAVS, VPI24, VPO, WDTRST1, WDTRST2] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml index 62424c42c981..859a1889dc1e 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml @@ -30,7 +30,7 @@ patternProperties: then: properties: function: - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC, ESPI, ESPIALT, FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, @@ -55,7 +55,7 @@ patternProperties: USB2BD, USB2BH, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, WDTRST4 ] groups: - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15, ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1, EMMCG4, EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWQSPI, FWSPIABR, FWSPID, FWSPIWP, @@ -84,7 +84,7 @@ patternProperties: WDTRST3, WDTRST4] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6318-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6318-pinctrl.yaml index ab019a1998e8..4478a76171f7 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6318-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6318-pinctrl.yaml @@ -38,7 +38,7 @@ patternProperties: gpio8, gpio9, gpio10, gpio11, gpio12, gpio13, gpio40 ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm63268-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm63268-pinctrl.yaml index 8c9d4668c8c4..73e1caa7c011 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm63268-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm63268-pinctrl.yaml @@ -42,7 +42,7 @@ patternProperties: vdsl_phy_override_3_grp, dsl_gpio8, dsl_gpio9 ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6328-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6328-pinctrl.yaml index a8e22ec02215..2750ba42aeb8 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6328-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6328-pinctrl.yaml @@ -37,7 +37,7 @@ patternProperties: usb_port1 ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6358-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6358-pinctrl.yaml index 35867355a47a..2f6c540498bc 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6358-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6358-pinctrl.yaml @@ -35,7 +35,7 @@ patternProperties: led_grp, spi_cs_grp, utopia_grp, pwm_syn_clk, sys_irq_grp ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6362-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6362-pinctrl.yaml index b584d4b27223..b3044f805753 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6362-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6362-pinctrl.yaml @@ -42,7 +42,7 @@ patternProperties: gpio22, gpio23, gpio24, gpio25, gpio26, gpio27, nand_grp ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6368-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6368-pinctrl.yaml index 229323d9237d..3236871827df 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,bcm6368-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,bcm6368-pinctrl.yaml @@ -43,7 +43,7 @@ patternProperties: gpio31, uart1_grp ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml index 8d1e5b1cdd5f..0a39dd26ee1a 100644 --- a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml +++ b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml @@ -53,7 +53,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml index a78cb2796001..7f4f36a58e56 100644 --- a/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml +++ b/Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml @@ -144,7 +144,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml index 5cd512b7d5ba..5e000b3fadde 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.yaml @@ -173,7 +173,7 @@ properties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml index 6bd42e43cdab..bb61a30321a1 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml @@ -40,8 +40,8 @@ properties: '-pins$': type: object allOf: - - $ref: "pincfg-node.yaml#" - - $ref: "pinmux-node.yaml#" + - $ref: pincfg-node.yaml# + - $ref: pinmux-node.yaml# properties: groups: description: diff --git a/Documentation/devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml b/Documentation/devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml index 915cbbcc3555..222d57541b65 100644 --- a/Documentation/devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cypress,cy8c95x0.yaml @@ -109,7 +109,7 @@ required: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# examples: - | diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx7d-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/fsl,imx7d-pinctrl.yaml index 621038662188..7bd723ab1281 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx7d-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx7d-pinctrl.yaml @@ -68,7 +68,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx8m-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/fsl,imx8m-pinctrl.yaml index 7ae084397258..6068be11dfe2 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx8m-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx8m-pinctrl.yaml @@ -65,7 +65,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx8ulp-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/fsl,imx8ulp-pinctrl.yaml index 693398d88223..7dcf681271d3 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx8ulp-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx8ulp-pinctrl.yaml @@ -57,7 +57,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx93-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/fsl,imx93-pinctrl.yaml index 66baa6082a4f..2f2405102996 100644 --- a/Documentation/devicetree/bindings/pinctrl/fsl,imx93-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx93-pinctrl.yaml @@ -14,7 +14,7 @@ description: for common binding part and usage. allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/ingenic,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/ingenic,pinctrl.yaml index a4397930e0e8..35723966b70a 100644 --- a/Documentation/devicetree/bindings/pinctrl/ingenic,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/ingenic,pinctrl.yaml @@ -119,7 +119,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/intel,lgm-io.yaml b/Documentation/devicetree/bindings/pinctrl/intel,lgm-io.yaml index ca0fef6e535e..1144ca2896e3 100644 --- a/Documentation/devicetree/bindings/pinctrl/intel,lgm-io.yaml +++ b/Documentation/devicetree/bindings/pinctrl/intel,lgm-io.yaml @@ -48,7 +48,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/marvell,ac5-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/marvell,ac5-pinctrl.yaml index 491f67e7cc4f..afea9424c7e1 100644 --- a/Documentation/devicetree/bindings/pinctrl/marvell,ac5-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/marvell,ac5-pinctrl.yaml @@ -28,7 +28,7 @@ patternProperties: properties: marvell,function: - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string description: Indicates the function to select. enum: [ dev_init_done, ge, gpio, i2c0, i2c1, int_out, led, nand, pcie, ptp, sdio, @@ -47,7 +47,7 @@ patternProperties: mpp40, mpp41, mpp42, mpp43, mpp44, mpp45 ] allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml index 98d547c34ef3..dbb3e1bd58c1 100644 --- a/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mscc,ocelot-pinctrl.yaml @@ -54,8 +54,8 @@ patternProperties: '-pins$': type: object allOf: - - $ref: "pinmux-node.yaml" - - $ref: "pincfg-node.yaml" + - $ref: pinmux-node.yaml + - $ref: pincfg-node.yaml properties: function: true @@ -78,7 +78,7 @@ required: - gpio-ranges allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml index db505fdeac86..1096655961f7 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml @@ -395,8 +395,8 @@ $defs: qcom-pmic-gpio-state: type: object allOf: - - $ref: "pinmux-node.yaml" - - $ref: "pincfg-node.yaml" + - $ref: pinmux-node.yaml + - $ref: pincfg-node.yaml properties: pins: description: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml index 9412b9362328..c91d3e3a094b 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-mpp.yaml @@ -82,8 +82,8 @@ $defs: qcom-pmic-mpp-state: type: object allOf: - - $ref: "pinmux-node.yaml" - - $ref: "pincfg-node.yaml" + - $ref: pinmux-node.yaml + - $ref: pincfg-node.yaml properties: pins: description: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml index e51feb4c0700..fa51fa9536f7 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-lpass-lpi-pinctrl.yaml @@ -50,7 +50,7 @@ $defs: description: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pins: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml index de9d8854c690..4b4be7efc150 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-lpass-lpi-pinctrl.yaml @@ -55,7 +55,7 @@ $defs: description: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pins: diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,tlmm-common.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,tlmm-common.yaml index 90b7d75840c1..aae3dcf6cac8 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,tlmm-common.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,tlmm-common.yaml @@ -52,7 +52,7 @@ properties: information. allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - interrupts diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,pfc.yaml index 4fc758fea7e6..0fc3c0f52c19 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc.yaml @@ -73,7 +73,7 @@ properties: maxItems: 1 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rza1-ports.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rza1-ports.yaml index 9083040c996a..83800fcf0ce4 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rza1-ports.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rza1-ports.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml index d761fddc2206..37173a64fed2 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rza2-pinctrl.yaml @@ -73,7 +73,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml index f081acb7ba04..9ce1a07fc015 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml @@ -113,7 +113,7 @@ additionalProperties: $ref: "#/additionalProperties/anyOf/0" allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml index 70b1788ab594..f3b85b7eae31 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml @@ -32,7 +32,7 @@ properties: The bus clock, sometimes described as pclk, for register accesses. allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml index eac6245db7dc..03f084292d68 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml @@ -94,7 +94,7 @@ additionalProperties: $ref: "#/additionalProperties/anyOf/0" allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml index 45b767986a87..10c335efe619 100644 --- a/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/rockchip,pinctrl.yaml @@ -50,12 +50,12 @@ properties: - rockchip,rv1126-pinctrl rockchip,grf: - $ref: "/schemas/types.yaml#/definitions/phandle" + $ref: /schemas/types.yaml#/definitions/phandle description: The phandle of the syscon node for the GRF registers. rockchip,pmu: - $ref: "/schemas/types.yaml#/definitions/phandle" + $ref: /schemas/types.yaml#/definitions/phandle description: The phandle of the syscon node for the PMU registers, as some SoCs carry parts of the iomux controller registers there. @@ -71,7 +71,7 @@ properties: ranges: true allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible @@ -81,7 +81,7 @@ patternProperties: "gpio@[0-9a-f]+$": type: object - $ref: "/schemas/gpio/rockchip,gpio-bank.yaml#" + $ref: /schemas/gpio/rockchip,gpio-bank.yaml# deprecated: true unevaluatedProperties: false @@ -117,7 +117,7 @@ additionalProperties: type: object properties: rockchip,pins: - $ref: "/schemas/types.yaml#/definitions/uint32-matrix" + $ref: /schemas/types.yaml#/definitions/uint32-matrix minItems: 1 items: items: diff --git a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml index eb2b2692607d..26614621774a 100644 --- a/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/samsung,pinctrl.yaml @@ -117,7 +117,7 @@ required: - reg allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml b/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml index 0719c03d6f4b..4214d7311f6b 100644 --- a/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml +++ b/Documentation/devicetree/bindings/pinctrl/semtech,sx1501q.yaml @@ -62,8 +62,8 @@ patternProperties: - pins allOf: - - $ref: "pincfg-node.yaml#" - - $ref: "pinmux-node.yaml#" + - $ref: pincfg-node.yaml# + - $ref: pinmux-node.yaml# - if: properties: pins: @@ -86,7 +86,7 @@ required: - gpio-controller allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# - if: not: properties: diff --git a/Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml index bc34e2c872bc..a6f34df82e90 100644 --- a/Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/socionext,uniphier-pinctrl.yaml @@ -61,7 +61,7 @@ additionalProperties: unevaluatedProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml index eeb29b4ad4d1..1ab0f8dde477 100644 --- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml @@ -44,7 +44,7 @@ properties: st,syscfg: description: Phandle+args to the syscon node which includes IRQ mux selection. - $ref: "/schemas/types.yaml#/definitions/phandle-array" + $ref: /schemas/types.yaml#/definitions/phandle-array items: - items: - description: syscon node which includes IRQ mux selection @@ -89,7 +89,7 @@ patternProperties: st,bank-name: description: Should be a name string for this bank as specified in the datasheet. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: - GPIOA - GPIOB @@ -108,7 +108,7 @@ patternProperties: description: Should correspond to the EXTI IOport selection (EXTI line used to select GPIOs as interrupts). - $ref: "/schemas/types.yaml#/definitions/uint32" + $ref: /schemas/types.yaml#/definitions/uint32 minimum: 0 maximum: 11 @@ -140,7 +140,7 @@ patternProperties: configuration, pullups, drive, output high/low and output speed. properties: pinmux: - $ref: "/schemas/types.yaml#/definitions/uint32-array" + $ref: /schemas/types.yaml#/definitions/uint32-array description: | Integer array, represents gpio pin number and mux setting. Supported pin number and mux varies for different SoCs, and are @@ -201,7 +201,7 @@ patternProperties: - pinmux allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/pinctrl/starfive,jh7100-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/starfive,jh7100-pinctrl.yaml index 69c0dd9998ea..27eff891685b 100644 --- a/Documentation/devicetree/bindings/pinctrl/starfive,jh7100-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/starfive,jh7100-pinctrl.yaml @@ -111,7 +111,7 @@ patternProperties: pins it needs, and how they should be configured, with regard to muxer configuration, bias, input enable/disable, input schmitt trigger enable/disable, slew-rate and drive strength. - $ref: "/schemas/pinctrl/pincfg-node.yaml" + $ref: /schemas/pinctrl/pincfg-node.yaml properties: pins: @@ -120,14 +120,14 @@ patternProperties: This should be set using either the PAD_GPIO or PAD_FUNC_SHARE macros. Either this or "pinmux" has to be specified, but not both. - $ref: "/schemas/pinctrl/pinmux-node.yaml#/properties/pins" + $ref: /schemas/pinctrl/pinmux-node.yaml#/properties/pins pinmux: description: | The list of GPIOs and their mux settings that properties in the node apply to. This should be set using the GPIOMUX macro. Either this or "pins" has to be specified, but not both. - $ref: "/schemas/pinctrl/pinmux-node.yaml#/properties/pinmux" + $ref: /schemas/pinctrl/pinmux-node.yaml#/properties/pinmux bias-disable: true diff --git a/Documentation/devicetree/bindings/pinctrl/sunplus,sp7021-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/sunplus,sp7021-pinctrl.yaml index 347061eece9e..94b868c7ceb1 100644 --- a/Documentation/devicetree/bindings/pinctrl/sunplus,sp7021-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/sunplus,sp7021-pinctrl.yaml @@ -138,7 +138,7 @@ patternProperties: description: | Define pin-function which is used by pinctrl node's client device. The name should be one of string in the following enumeration. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ SPI_FLASH, SPI_FLASH_4BIT, SPI_NAND, CARD0_EMMC, SD_CARD, UA0, FPGA_IFX, HDMI_TX, LCDIF, USB0_OTG, USB1_OTG ] @@ -146,7 +146,7 @@ patternProperties: description: | Define pin-group in a specified pin-function. The name should be one of string in the following enumeration. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [ SPI_FLASH1, SPI_FLASH2, SPI_FLASH_4BIT1, SPI_FLASH_4BIT2, SPI_NAND, CARD0_EMMC, SD_CARD, UA0, FPGA_IFX, HDMI_TX1, HDMI_TX2, HDMI_TX3, LCDIF, USB0_OTG, USB1_OTG ] @@ -289,7 +289,7 @@ required: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# examples: - | diff --git a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml index 98b4663f9766..19d47fd414bc 100644 --- a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml @@ -21,7 +21,7 @@ properties: maxItems: 1 allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible @@ -35,14 +35,14 @@ patternProperties: pinctrl groups available on the machine. Each subnode will list the pins it needs, and how they should be configured, with regard to muxer configuration, pullups, drive strength. - $ref: "pinmux-node.yaml" + $ref: pinmux-node.yaml additionalProperties: false properties: function: description: Function to mux. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [i2c0, i2c1, i2c2, i2c3, i2c4, i2c5, i2c6, i2c7, i2c8, spi0, spi1, spi2, spi3, spi4, spi5, spi6, uart0, uart1, uart2, uart3, pwm, pcmif_out, pcmif_in] @@ -50,7 +50,7 @@ patternProperties: groups: description: Name of the pin group to use for the functions. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string enum: [i2c0_grp, i2c1_grp, i2c2_grp, i2c3_grp, i2c4_grp, i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp, spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp, diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml index cfd0cc549a7b..598a042850b8 100644 --- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynq-pinctrl.yaml @@ -168,7 +168,7 @@ patternProperties: additionalProperties: false allOf: - - $ref: "pinctrl.yaml#" + - $ref: pinctrl.yaml# required: - compatible -- GitLab From 33a36b8188b530f6ed8a0fba6626bd0702d6f11d Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Thu, 30 Mar 2023 23:22:24 +0200 Subject: [PATCH 1799/5631] pinctrl: xway: drop the deprecated compatible strings This code are marked as deprecated since kernel 4.5[1]. Downstream OpenWRT and upstream switched to the new string compatible 7 years ago. The old compatible strings can safely be dropped. [1] commit be14811c03cf ("pinctrl/lantiq: introduce new dedicated devicetree bindings") Signed-off-by: Aleksander Jan Bajkowski Link: https://lore.kernel.org/r/20230330212225.10214-1-olek2@wp.pl Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-xway.c | 252 --------------------------------- 1 file changed, 252 deletions(-) diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c index 3a03beb8a755..858abb23b337 100644 --- a/drivers/pinctrl/pinctrl-xway.c +++ b/drivers/pinctrl/pinctrl-xway.c @@ -107,243 +107,6 @@ enum xway_mux { XWAY_MUX_NONE = 0xffff, }; -/* --------- DEPRECATED: xr9 related code --------- */ -/* ---------- use xrx100/xrx200 instead ---------- */ -#define XR9_MAX_PIN 56 - -static const struct ltq_mfp_pin xway_mfp[] = { - /* pin f0 f1 f2 f3 */ - MFP_XWAY(GPIO0, GPIO, EXIN, NONE, TDM), - MFP_XWAY(GPIO1, GPIO, EXIN, NONE, NONE), - MFP_XWAY(GPIO2, GPIO, CGU, EXIN, GPHY), - MFP_XWAY(GPIO3, GPIO, CGU, NONE, PCI), - MFP_XWAY(GPIO4, GPIO, STP, NONE, ASC), - MFP_XWAY(GPIO5, GPIO, STP, GPHY, NONE), - MFP_XWAY(GPIO6, GPIO, STP, GPT, ASC), - MFP_XWAY(GPIO7, GPIO, CGU, PCI, GPHY), - MFP_XWAY(GPIO8, GPIO, CGU, NMI, NONE), - MFP_XWAY(GPIO9, GPIO, ASC, SPI, EXIN), - MFP_XWAY(GPIO10, GPIO, ASC, SPI, NONE), - MFP_XWAY(GPIO11, GPIO, ASC, PCI, SPI), - MFP_XWAY(GPIO12, GPIO, ASC, NONE, NONE), - MFP_XWAY(GPIO13, GPIO, EBU, SPI, NONE), - MFP_XWAY(GPIO14, GPIO, CGU, PCI, NONE), - MFP_XWAY(GPIO15, GPIO, SPI, JTAG, NONE), - MFP_XWAY(GPIO16, GPIO, SPI, NONE, JTAG), - MFP_XWAY(GPIO17, GPIO, SPI, NONE, JTAG), - MFP_XWAY(GPIO18, GPIO, SPI, NONE, JTAG), - MFP_XWAY(GPIO19, GPIO, PCI, NONE, NONE), - MFP_XWAY(GPIO20, GPIO, JTAG, NONE, NONE), - MFP_XWAY(GPIO21, GPIO, PCI, EBU, GPT), - MFP_XWAY(GPIO22, GPIO, SPI, NONE, NONE), - MFP_XWAY(GPIO23, GPIO, EBU, PCI, STP), - MFP_XWAY(GPIO24, GPIO, EBU, TDM, PCI), - MFP_XWAY(GPIO25, GPIO, TDM, NONE, ASC), - MFP_XWAY(GPIO26, GPIO, EBU, NONE, TDM), - MFP_XWAY(GPIO27, GPIO, TDM, NONE, ASC), - MFP_XWAY(GPIO28, GPIO, GPT, NONE, NONE), - MFP_XWAY(GPIO29, GPIO, PCI, NONE, NONE), - MFP_XWAY(GPIO30, GPIO, PCI, NONE, NONE), - MFP_XWAY(GPIO31, GPIO, EBU, PCI, NONE), - MFP_XWAY(GPIO32, GPIO, NONE, NONE, EBU), - MFP_XWAY(GPIO33, GPIO, NONE, NONE, EBU), - MFP_XWAY(GPIO34, GPIO, NONE, NONE, EBU), - MFP_XWAY(GPIO35, GPIO, NONE, NONE, EBU), - MFP_XWAY(GPIO36, GPIO, SIN, NONE, EBU), - MFP_XWAY(GPIO37, GPIO, PCI, NONE, NONE), - MFP_XWAY(GPIO38, GPIO, PCI, NONE, NONE), - MFP_XWAY(GPIO39, GPIO, EXIN, NONE, NONE), - MFP_XWAY(GPIO40, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO41, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO42, GPIO, MDIO, NONE, NONE), - MFP_XWAY(GPIO43, GPIO, MDIO, NONE, NONE), - MFP_XWAY(GPIO44, GPIO, MII, SIN, GPHY), - MFP_XWAY(GPIO45, GPIO, NONE, GPHY, SIN), - MFP_XWAY(GPIO46, GPIO, NONE, NONE, EXIN), - MFP_XWAY(GPIO47, GPIO, MII, GPHY, SIN), - MFP_XWAY(GPIO48, GPIO, EBU, NONE, NONE), - MFP_XWAY(GPIO49, GPIO, EBU, NONE, NONE), - MFP_XWAY(GPIO50, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO51, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO52, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO53, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO54, GPIO, NONE, NONE, NONE), - MFP_XWAY(GPIO55, GPIO, NONE, NONE, NONE), -}; - -static const unsigned pins_jtag[] = {GPIO15, GPIO16, GPIO17, GPIO19, GPIO35}; -static const unsigned pins_asc0[] = {GPIO11, GPIO12}; -static const unsigned pins_asc0_cts_rts[] = {GPIO9, GPIO10}; -static const unsigned pins_stp[] = {GPIO4, GPIO5, GPIO6}; -static const unsigned pins_nmi[] = {GPIO8}; -static const unsigned pins_mdio[] = {GPIO42, GPIO43}; - -static const unsigned pins_gphy0_led0[] = {GPIO5}; -static const unsigned pins_gphy0_led1[] = {GPIO7}; -static const unsigned pins_gphy0_led2[] = {GPIO2}; -static const unsigned pins_gphy1_led0[] = {GPIO44}; -static const unsigned pins_gphy1_led1[] = {GPIO45}; -static const unsigned pins_gphy1_led2[] = {GPIO47}; - -static const unsigned pins_ebu_a24[] = {GPIO13}; -static const unsigned pins_ebu_clk[] = {GPIO21}; -static const unsigned pins_ebu_cs1[] = {GPIO23}; -static const unsigned pins_ebu_a23[] = {GPIO24}; -static const unsigned pins_ebu_wait[] = {GPIO26}; -static const unsigned pins_ebu_a25[] = {GPIO31}; -static const unsigned pins_ebu_rdy[] = {GPIO48}; -static const unsigned pins_ebu_rd[] = {GPIO49}; - -static const unsigned pins_nand_ale[] = {GPIO13}; -static const unsigned pins_nand_cs1[] = {GPIO23}; -static const unsigned pins_nand_cle[] = {GPIO24}; -static const unsigned pins_nand_rdy[] = {GPIO48}; -static const unsigned pins_nand_rd[] = {GPIO49}; - -static const unsigned xway_exin_pin_map[] = {GPIO0, GPIO1, GPIO2, GPIO39, GPIO46, GPIO9}; - -static const unsigned pins_exin0[] = {GPIO0}; -static const unsigned pins_exin1[] = {GPIO1}; -static const unsigned pins_exin2[] = {GPIO2}; -static const unsigned pins_exin3[] = {GPIO39}; -static const unsigned pins_exin4[] = {GPIO46}; -static const unsigned pins_exin5[] = {GPIO9}; - -static const unsigned pins_spi[] = {GPIO16, GPIO17, GPIO18}; -static const unsigned pins_spi_cs1[] = {GPIO15}; -static const unsigned pins_spi_cs2[] = {GPIO22}; -static const unsigned pins_spi_cs3[] = {GPIO13}; -static const unsigned pins_spi_cs4[] = {GPIO10}; -static const unsigned pins_spi_cs5[] = {GPIO9}; -static const unsigned pins_spi_cs6[] = {GPIO11}; - -static const unsigned pins_gpt1[] = {GPIO28}; -static const unsigned pins_gpt2[] = {GPIO21}; -static const unsigned pins_gpt3[] = {GPIO6}; - -static const unsigned pins_clkout0[] = {GPIO8}; -static const unsigned pins_clkout1[] = {GPIO7}; -static const unsigned pins_clkout2[] = {GPIO3}; -static const unsigned pins_clkout3[] = {GPIO2}; - -static const unsigned pins_pci_gnt1[] = {GPIO30}; -static const unsigned pins_pci_gnt2[] = {GPIO23}; -static const unsigned pins_pci_gnt3[] = {GPIO19}; -static const unsigned pins_pci_gnt4[] = {GPIO38}; -static const unsigned pins_pci_req1[] = {GPIO29}; -static const unsigned pins_pci_req2[] = {GPIO31}; -static const unsigned pins_pci_req3[] = {GPIO3}; -static const unsigned pins_pci_req4[] = {GPIO37}; - -static const struct ltq_pin_group xway_grps[] = { - GRP_MUX("exin0", EXIN, pins_exin0), - GRP_MUX("exin1", EXIN, pins_exin1), - GRP_MUX("exin2", EXIN, pins_exin2), - GRP_MUX("jtag", JTAG, pins_jtag), - GRP_MUX("ebu a23", EBU, pins_ebu_a23), - GRP_MUX("ebu a24", EBU, pins_ebu_a24), - GRP_MUX("ebu a25", EBU, pins_ebu_a25), - GRP_MUX("ebu clk", EBU, pins_ebu_clk), - GRP_MUX("ebu cs1", EBU, pins_ebu_cs1), - GRP_MUX("ebu wait", EBU, pins_ebu_wait), - GRP_MUX("nand ale", EBU, pins_nand_ale), - GRP_MUX("nand cs1", EBU, pins_nand_cs1), - GRP_MUX("nand cle", EBU, pins_nand_cle), - GRP_MUX("spi", SPI, pins_spi), - GRP_MUX("spi_cs1", SPI, pins_spi_cs1), - GRP_MUX("spi_cs2", SPI, pins_spi_cs2), - GRP_MUX("spi_cs3", SPI, pins_spi_cs3), - GRP_MUX("spi_cs4", SPI, pins_spi_cs4), - GRP_MUX("spi_cs5", SPI, pins_spi_cs5), - GRP_MUX("spi_cs6", SPI, pins_spi_cs6), - GRP_MUX("asc0", ASC, pins_asc0), - GRP_MUX("asc0 cts rts", ASC, pins_asc0_cts_rts), - GRP_MUX("stp", STP, pins_stp), - GRP_MUX("nmi", NMI, pins_nmi), - GRP_MUX("gpt1", GPT, pins_gpt1), - GRP_MUX("gpt2", GPT, pins_gpt2), - GRP_MUX("gpt3", GPT, pins_gpt3), - GRP_MUX("clkout0", CGU, pins_clkout0), - GRP_MUX("clkout1", CGU, pins_clkout1), - GRP_MUX("clkout2", CGU, pins_clkout2), - GRP_MUX("clkout3", CGU, pins_clkout3), - GRP_MUX("gnt1", PCI, pins_pci_gnt1), - GRP_MUX("gnt2", PCI, pins_pci_gnt2), - GRP_MUX("gnt3", PCI, pins_pci_gnt3), - GRP_MUX("req1", PCI, pins_pci_req1), - GRP_MUX("req2", PCI, pins_pci_req2), - GRP_MUX("req3", PCI, pins_pci_req3), -/* xrx only */ - GRP_MUX("nand rdy", EBU, pins_nand_rdy), - GRP_MUX("nand rd", EBU, pins_nand_rd), - GRP_MUX("exin3", EXIN, pins_exin3), - GRP_MUX("exin4", EXIN, pins_exin4), - GRP_MUX("exin5", EXIN, pins_exin5), - GRP_MUX("gnt4", PCI, pins_pci_gnt4), - GRP_MUX("req4", PCI, pins_pci_gnt4), - GRP_MUX("mdio", MDIO, pins_mdio), - GRP_MUX("gphy0 led0", GPHY, pins_gphy0_led0), - GRP_MUX("gphy0 led1", GPHY, pins_gphy0_led1), - GRP_MUX("gphy0 led2", GPHY, pins_gphy0_led2), - GRP_MUX("gphy1 led0", GPHY, pins_gphy1_led0), - GRP_MUX("gphy1 led1", GPHY, pins_gphy1_led1), - GRP_MUX("gphy1 led2", GPHY, pins_gphy1_led2), -}; - -static const char * const xway_pci_grps[] = {"gnt1", "gnt2", - "gnt3", "req1", - "req2", "req3"}; -static const char * const xway_spi_grps[] = {"spi", "spi_cs1", - "spi_cs2", "spi_cs3", - "spi_cs4", "spi_cs5", - "spi_cs6"}; -static const char * const xway_cgu_grps[] = {"clkout0", "clkout1", - "clkout2", "clkout3"}; -static const char * const xway_ebu_grps[] = {"ebu a23", "ebu a24", - "ebu a25", "ebu cs1", - "ebu wait", "ebu clk", - "nand ale", "nand cs1", - "nand cle"}; -static const char * const xway_exin_grps[] = {"exin0", "exin1", "exin2"}; -static const char * const xway_gpt_grps[] = {"gpt1", "gpt2", "gpt3"}; -static const char * const xway_asc_grps[] = {"asc0", "asc0 cts rts"}; -static const char * const xway_jtag_grps[] = {"jtag"}; -static const char * const xway_stp_grps[] = {"stp"}; -static const char * const xway_nmi_grps[] = {"nmi"}; - -/* ar9/vr9/gr9 */ -static const char * const xrx_mdio_grps[] = {"mdio"}; -static const char * const xrx_gphy_grps[] = {"gphy0 led0", "gphy0 led1", - "gphy0 led2", "gphy1 led0", - "gphy1 led1", "gphy1 led2"}; -static const char * const xrx_ebu_grps[] = {"ebu a23", "ebu a24", - "ebu a25", "ebu cs1", - "ebu wait", "ebu clk", - "nand ale", "nand cs1", - "nand cle", "nand rdy", - "nand rd"}; -static const char * const xrx_exin_grps[] = {"exin0", "exin1", "exin2", - "exin3", "exin4", "exin5"}; -static const char * const xrx_pci_grps[] = {"gnt1", "gnt2", - "gnt3", "gnt4", - "req1", "req2", - "req3", "req4"}; - -static const struct ltq_pmx_func xrx_funcs[] = { - {"spi", ARRAY_AND_SIZE(xway_spi_grps)}, - {"asc", ARRAY_AND_SIZE(xway_asc_grps)}, - {"cgu", ARRAY_AND_SIZE(xway_cgu_grps)}, - {"jtag", ARRAY_AND_SIZE(xway_jtag_grps)}, - {"exin", ARRAY_AND_SIZE(xrx_exin_grps)}, - {"stp", ARRAY_AND_SIZE(xway_stp_grps)}, - {"gpt", ARRAY_AND_SIZE(xway_gpt_grps)}, - {"nmi", ARRAY_AND_SIZE(xway_nmi_grps)}, - {"pci", ARRAY_AND_SIZE(xrx_pci_grps)}, - {"ebu", ARRAY_AND_SIZE(xrx_ebu_grps)}, - {"mdio", ARRAY_AND_SIZE(xrx_mdio_grps)}, - {"gphy", ARRAY_AND_SIZE(xrx_gphy_grps)}, -}; - /* --------- ase related code --------- */ #define ASE_MAX_PIN 32 @@ -1611,18 +1374,6 @@ struct pinctrl_xway_soc { unsigned int num_exin; }; -/* xway xr9 series (DEPRECATED: Use XWAY xRX100/xRX200 Family) */ -static struct pinctrl_xway_soc xr9_pinctrl = { - .pin_count = XR9_MAX_PIN, - .mfp = xway_mfp, - .grps = xway_grps, - .num_grps = ARRAY_SIZE(xway_grps), - .funcs = xrx_funcs, - .num_funcs = ARRAY_SIZE(xrx_funcs), - .exin = xway_exin_pin_map, - .num_exin = 6 -}; - /* XWAY AMAZON Family */ static struct pinctrl_xway_soc ase_pinctrl = { .pin_count = ASE_MAX_PIN, @@ -1689,9 +1440,6 @@ static struct pinctrl_gpio_range xway_gpio_range = { }; static const struct of_device_id xway_match[] = { - { .compatible = "lantiq,pinctrl-xway", .data = &danube_pinctrl}, /*DEPRECATED*/ - { .compatible = "lantiq,pinctrl-xr9", .data = &xr9_pinctrl}, /*DEPRECATED*/ - { .compatible = "lantiq,pinctrl-ase", .data = &ase_pinctrl}, /*DEPRECATED*/ { .compatible = "lantiq,ase-pinctrl", .data = &ase_pinctrl}, { .compatible = "lantiq,danube-pinctrl", .data = &danube_pinctrl}, { .compatible = "lantiq,xrx100-pinctrl", .data = &xrx100_pinctrl}, -- GitLab From c436561687421493fe745c2cc26a8ad0f8dc208b Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Thu, 30 Mar 2023 23:22:25 +0200 Subject: [PATCH 1800/5631] dt-bindings: pinctrl: xway: drop the deprecated compatible strings This code are marked as deprecated since kernel 4.5[1]. Downstream OpenWRT and upstream switched to the new string compatible 7 years ago. The old compatible strings can safely be dropped. [1] commit be14811c03cf ("pinctrl/lantiq: introduce new dedicated devicetree bindings") Signed-off-by: Aleksander Jan Bajkowski Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230330212225.10214-2-olek2@wp.pl Signed-off-by: Linus Walleij --- .../bindings/pinctrl/lantiq,pinctrl-xway.txt | 35 +------------------ 1 file changed, 1 insertion(+), 34 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt index 4658f105fa09..6bd9bc61becb 100644 --- a/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt +++ b/Documentation/devicetree/bindings/pinctrl/lantiq,pinctrl-xway.txt @@ -1,11 +1,7 @@ Lantiq XWAY pinmux controller Required properties: -- compatible: "lantiq,pinctrl-xway", (DEPRECATED: Use "lantiq,pinctrl-danube") - "lantiq,pinctrl-xr9", (DEPRECATED: Use "lantiq,xrx100-pinctrl" or - "lantiq,xrx200-pinctrl") - "lantiq,pinctrl-ase", (DEPRECATED: Use "lantiq,ase-pinctrl") - "lantiq,-pinctrl", where is: +- compatible: "lantiq,-pinctrl", where is: "ase" (XWAY AMAZON Family) "danube" (XWAY DANUBE Family) "xrx100" (XWAY xRX100 Family) @@ -45,29 +41,6 @@ Required subnode-properties: Valid values for group and function names: -XWAY: (DEPRECATED: Use DANUBE) - mux groups: - exin0, exin1, exin2, jtag, ebu a23, ebu a24, ebu a25, ebu clk, ebu cs1, - ebu wait, nand ale, nand cs1, nand cle, spi, spi_cs1, spi_cs2, spi_cs3, - spi_cs4, spi_cs5, spi_cs6, asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, - gpt3, clkout0, clkout1, clkout2, clkout3, gnt1, gnt2, gnt3, req1, req2, - req3 - - functions: - spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu - -XR9: ( DEPRECATED: Use xRX100/xRX200) - mux groups: - exin0, exin1, exin2, exin3, exin4, jtag, ebu a23, ebu a24, ebu a25, - ebu clk, ebu cs1, ebu wait, nand ale, nand cs1, nand cle, nand rdy, - nand rd, spi, spi_cs1, spi_cs2, spi_cs3, spi_cs4, spi_cs5, spi_cs6, - asc0, asc0 cts rts, stp, nmi, gpt1, gpt2, gpt3, clkout0, clkout1, - clkout2, clkout3, gnt1, gnt2, gnt3, gnt4, req1, req2, req3, req4, mdio, - gphy0 led0, gphy0 led1, gphy0 led2, gphy1 led0, gphy1 led1, gphy1 led2 - - functions: - spi, asc, cgu, jtag, exin, stp, gpt, nmi, pci, ebu, mdio, gphy - AMAZON: mux groups: exin0, exin1, exin2, jtag, spi_di, spi_do, spi_clk, spi_cs1, spi_cs2, @@ -139,12 +112,6 @@ Optional subnode-properties: 0: none, 1: down, 2: up. - lantiq,open-drain: Boolean, enables open-drain on the defined pin. -Valid values for XWAY pin names: (DEPRECATED: Use DANUBE) - Pinconf pins can be referenced via the names io0-io31. - -Valid values for XR9 pin names: (DEPRECATED: Use xrX100/xRX200) - Pinconf pins can be referenced via the names io0-io55. - Valid values for AMAZON pin names: Pinconf pins can be referenced via the names io0-io31. -- GitLab From f47a669ffa11c6c14b463d762562fe9681345c6e Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Wed, 8 Mar 2023 19:46:03 +0100 Subject: [PATCH 1801/5631] clk: imx: clk-gpr-mux: Provide clock name in error message In error case the error message doesn't provide much context: imx:clk-gpr-mux: failed to get parent (-EINVAL) So additionally provide the clock name in the message, in order to simplify the further analyze. Signed-off-by: Stefan Wahren Reviewed-by: Peng Fan Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230308184603.10049-1-stefan.wahren@i2se.com --- drivers/clk/imx/clk-gpr-mux.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-gpr-mux.c b/drivers/clk/imx/clk-gpr-mux.c index c8d6090f15d6..0b5a97698b47 100644 --- a/drivers/clk/imx/clk-gpr-mux.c +++ b/drivers/clk/imx/clk-gpr-mux.c @@ -48,7 +48,8 @@ static u8 imx_clk_gpr_mux_get_parent(struct clk_hw *hw) return ret; get_parent_err: - pr_err("failed to get parent (%pe)\n", ERR_PTR(ret)); + pr_err("%s: failed to get parent (%pe)\n", + clk_hw_get_name(hw), ERR_PTR(ret)); /* return some realistic non negative value. Potentially we could * give index to some dummy error parent. -- GitLab From f60a150822a7946c97059dad3416ea3de501eaed Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 19 Mar 2023 11:32:22 -0500 Subject: [PATCH 1802/5631] dmaengine: bestcomm: Use of_address_to_resource() Replace of_get_address() and of_translate_address() calls with single call to of_address_to_resource(). Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230319163222.226377-1-robh@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/bestcomm/sram.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-) diff --git a/drivers/dma/bestcomm/sram.c b/drivers/dma/bestcomm/sram.c index c465758e7193..0553956f7456 100644 --- a/drivers/dma/bestcomm/sram.c +++ b/drivers/dma/bestcomm/sram.c @@ -38,7 +38,7 @@ int bcom_sram_init(struct device_node *sram_node, char *owner) { int rv; const u32 *regaddr_p; - u64 regaddr64, size64; + struct resource res; unsigned int psize; /* Create our state struct */ @@ -56,21 +56,18 @@ int bcom_sram_init(struct device_node *sram_node, char *owner) } /* Get address and size of the sram */ - regaddr_p = of_get_address(sram_node, 0, &size64, NULL); - if (!regaddr_p) { + rv = of_address_to_resource(sram_node, 0, &res); + if (rv) { printk(KERN_ERR "%s: bcom_sram_init: " "Invalid device node !\n", owner); - rv = -EINVAL; goto error_free; } - regaddr64 = of_translate_address(sram_node, regaddr_p); - - bcom_sram->base_phys = (phys_addr_t) regaddr64; - bcom_sram->size = (unsigned int) size64; + bcom_sram->base_phys = res.start; + bcom_sram->size = resource_size(&res); /* Request region */ - if (!request_mem_region(bcom_sram->base_phys, bcom_sram->size, owner)) { + if (!request_mem_region(res.start, resource_size(&res), owner)) { printk(KERN_ERR "%s: bcom_sram_init: " "Couldn't request region !\n", owner); rv = -EBUSY; @@ -79,7 +76,7 @@ int bcom_sram_init(struct device_node *sram_node, char *owner) /* Map SRAM */ /* sram is not really __iomem */ - bcom_sram->base_virt = (void*) ioremap(bcom_sram->base_phys, bcom_sram->size); + bcom_sram->base_virt = (void *)ioremap(res.start, resource_size(&res)); if (!bcom_sram->base_virt) { printk(KERN_ERR "%s: bcom_sram_init: " @@ -120,7 +117,7 @@ int bcom_sram_init(struct device_node *sram_node, char *owner) return 0; error_release: - release_mem_region(bcom_sram->base_phys, bcom_sram->size); + release_mem_region(res.start, resource_size(&res)); error_free: kfree(bcom_sram); bcom_sram = NULL; -- GitLab From 82e6051a48957a89066d15b17bb85d2f662f2bad Mon Sep 17 00:00:00 2001 From: Apurva Nandan Date: Thu, 9 Mar 2023 01:45:13 +0530 Subject: [PATCH 1803/5631] dmaengine: ti: k3-psil: Add PSI-L thread support for J784s4 Add psil thread IDs for J784s4 and include J784s4 in the set of "k3_soc_devices" in k3-psil.c. Signed-off-by: Apurva Nandan Signed-off-by: Hari Nagalla Signed-off-by: Siddharth Vadapalli Signed-off-by: Vignesh Raghavendra [vaishnav.a@ti.com: add MCSPI-TX and 3rd CSI2RX instance entries] Signed-off-by: Vaishnav Achath [j-choudhary@ti.com: add sa2ul entries, minor cleanups] Signed-off-by: Jayesh Choudhary Acked-by: Peter Ujfalusi Link: https://lore.kernel.org/r/20230308201513.116638-1-j-choudhary@ti.com Signed-off-by: Vinod Koul --- drivers/dma/ti/Makefile | 3 +- drivers/dma/ti/k3-psil-j784s4.c | 354 ++++++++++++++++++++++++++++++++ drivers/dma/ti/k3-psil-priv.h | 1 + drivers/dma/ti/k3-psil.c | 1 + drivers/dma/ti/k3-udma.c | 1 + 5 files changed, 359 insertions(+), 1 deletion(-) create mode 100644 drivers/dma/ti/k3-psil-j784s4.c diff --git a/drivers/dma/ti/Makefile b/drivers/dma/ti/Makefile index bd1e07fda559..acc950bf609c 100644 --- a/drivers/dma/ti/Makefile +++ b/drivers/dma/ti/Makefile @@ -11,6 +11,7 @@ k3-psil-lib-objs := k3-psil.o \ k3-psil-am64.o \ k3-psil-j721s2.o \ k3-psil-am62.o \ - k3-psil-am62a.o + k3-psil-am62a.o \ + k3-psil-j784s4.o obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o diff --git a/drivers/dma/ti/k3-psil-j784s4.c b/drivers/dma/ti/k3-psil-j784s4.c new file mode 100644 index 000000000000..12bfa2478f92 --- /dev/null +++ b/drivers/dma/ti/k3-psil-j784s4.c @@ -0,0 +1,354 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Texas Instruments Incorporated - https://www.ti.com + */ + +#include + +#include "k3-psil-priv.h" + +#define PSIL_PDMA_XY_TR(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + }, \ + } + +#define PSIL_PDMA_XY_PKT(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pkt_mode = 1, \ + }, \ + } + +#define PSIL_PDMA_MCASP(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_PDMA_XY, \ + .pdma_acc32 = 1, \ + .pdma_burst = 1, \ + }, \ + } + +#define PSIL_ETHERNET(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 16, \ + }, \ + } + +#define PSIL_SA2UL(x, tx) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + .pkt_mode = 1, \ + .needs_epib = 1, \ + .psd_size = 64, \ + .notdpkt = tx, \ + }, \ + } + +#define PSIL_CSI2RX(x) \ + { \ + .thread_id = x, \ + .ep_config = { \ + .ep_type = PSIL_EP_NATIVE, \ + }, \ + } + +/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */ +static struct psil_ep j784s4_src_ep_map[] = { + /* PDMA_MCASP - McASP0-4 */ + PSIL_PDMA_MCASP(0x4400), + PSIL_PDMA_MCASP(0x4401), + PSIL_PDMA_MCASP(0x4402), + PSIL_PDMA_MCASP(0x4403), + PSIL_PDMA_MCASP(0x4404), + /* PDMA_SPI_G0 - SPI0-3 */ + PSIL_PDMA_XY_PKT(0x4600), + PSIL_PDMA_XY_PKT(0x4601), + PSIL_PDMA_XY_PKT(0x4602), + PSIL_PDMA_XY_PKT(0x4603), + PSIL_PDMA_XY_PKT(0x4604), + PSIL_PDMA_XY_PKT(0x4605), + PSIL_PDMA_XY_PKT(0x4606), + PSIL_PDMA_XY_PKT(0x4607), + PSIL_PDMA_XY_PKT(0x4608), + PSIL_PDMA_XY_PKT(0x4609), + PSIL_PDMA_XY_PKT(0x460a), + PSIL_PDMA_XY_PKT(0x460b), + PSIL_PDMA_XY_PKT(0x460c), + PSIL_PDMA_XY_PKT(0x460d), + PSIL_PDMA_XY_PKT(0x460e), + PSIL_PDMA_XY_PKT(0x460f), + /* PDMA_SPI_G1 - SPI4-7 */ + PSIL_PDMA_XY_PKT(0x4620), + PSIL_PDMA_XY_PKT(0x4621), + PSIL_PDMA_XY_PKT(0x4622), + PSIL_PDMA_XY_PKT(0x4623), + PSIL_PDMA_XY_PKT(0x4624), + PSIL_PDMA_XY_PKT(0x4625), + PSIL_PDMA_XY_PKT(0x4626), + PSIL_PDMA_XY_PKT(0x4627), + PSIL_PDMA_XY_PKT(0x4628), + PSIL_PDMA_XY_PKT(0x4629), + PSIL_PDMA_XY_PKT(0x462a), + PSIL_PDMA_XY_PKT(0x462b), + PSIL_PDMA_XY_PKT(0x462c), + PSIL_PDMA_XY_PKT(0x462d), + PSIL_PDMA_XY_PKT(0x462e), + PSIL_PDMA_XY_PKT(0x462f), + /* MAIN_CPSW2G */ + PSIL_ETHERNET(0x4640), + /* PDMA_USART_G0 - UART0-1 */ + PSIL_PDMA_XY_PKT(0x4700), + PSIL_PDMA_XY_PKT(0x4701), + /* PDMA_USART_G1 - UART2-3 */ + PSIL_PDMA_XY_PKT(0x4702), + PSIL_PDMA_XY_PKT(0x4703), + /* PDMA_USART_G2 - UART4-9 */ + PSIL_PDMA_XY_PKT(0x4704), + PSIL_PDMA_XY_PKT(0x4705), + PSIL_PDMA_XY_PKT(0x4706), + PSIL_PDMA_XY_PKT(0x4707), + PSIL_PDMA_XY_PKT(0x4708), + PSIL_PDMA_XY_PKT(0x4709), + /* CSI2RX */ + PSIL_CSI2RX(0x4900), + PSIL_CSI2RX(0x4901), + PSIL_CSI2RX(0x4902), + PSIL_CSI2RX(0x4903), + PSIL_CSI2RX(0x4940), + PSIL_CSI2RX(0x4941), + PSIL_CSI2RX(0x4942), + PSIL_CSI2RX(0x4943), + PSIL_CSI2RX(0x4944), + PSIL_CSI2RX(0x4945), + PSIL_CSI2RX(0x4946), + PSIL_CSI2RX(0x4947), + PSIL_CSI2RX(0x4948), + PSIL_CSI2RX(0x4949), + PSIL_CSI2RX(0x494a), + PSIL_CSI2RX(0x494b), + PSIL_CSI2RX(0x494c), + PSIL_CSI2RX(0x494d), + PSIL_CSI2RX(0x494e), + PSIL_CSI2RX(0x494f), + PSIL_CSI2RX(0x4950), + PSIL_CSI2RX(0x4951), + PSIL_CSI2RX(0x4952), + PSIL_CSI2RX(0x4953), + PSIL_CSI2RX(0x4954), + PSIL_CSI2RX(0x4955), + PSIL_CSI2RX(0x4956), + PSIL_CSI2RX(0x4957), + PSIL_CSI2RX(0x4958), + PSIL_CSI2RX(0x4959), + PSIL_CSI2RX(0x495a), + PSIL_CSI2RX(0x495b), + PSIL_CSI2RX(0x495c), + PSIL_CSI2RX(0x495d), + PSIL_CSI2RX(0x495e), + PSIL_CSI2RX(0x495f), + PSIL_CSI2RX(0x4960), + PSIL_CSI2RX(0x4961), + PSIL_CSI2RX(0x4962), + PSIL_CSI2RX(0x4963), + PSIL_CSI2RX(0x4964), + PSIL_CSI2RX(0x4965), + PSIL_CSI2RX(0x4966), + PSIL_CSI2RX(0x4967), + PSIL_CSI2RX(0x4968), + PSIL_CSI2RX(0x4969), + PSIL_CSI2RX(0x496a), + PSIL_CSI2RX(0x496b), + PSIL_CSI2RX(0x496c), + PSIL_CSI2RX(0x496d), + PSIL_CSI2RX(0x496e), + PSIL_CSI2RX(0x496f), + PSIL_CSI2RX(0x4970), + PSIL_CSI2RX(0x4971), + PSIL_CSI2RX(0x4972), + PSIL_CSI2RX(0x4973), + PSIL_CSI2RX(0x4974), + PSIL_CSI2RX(0x4975), + PSIL_CSI2RX(0x4976), + PSIL_CSI2RX(0x4977), + PSIL_CSI2RX(0x4978), + PSIL_CSI2RX(0x4979), + PSIL_CSI2RX(0x497a), + PSIL_CSI2RX(0x497b), + PSIL_CSI2RX(0x497c), + PSIL_CSI2RX(0x497d), + PSIL_CSI2RX(0x497e), + PSIL_CSI2RX(0x497f), + PSIL_CSI2RX(0x4980), + PSIL_CSI2RX(0x4981), + PSIL_CSI2RX(0x4982), + PSIL_CSI2RX(0x4983), + PSIL_CSI2RX(0x4984), + PSIL_CSI2RX(0x4985), + PSIL_CSI2RX(0x4986), + PSIL_CSI2RX(0x4987), + PSIL_CSI2RX(0x4988), + PSIL_CSI2RX(0x4989), + PSIL_CSI2RX(0x498a), + PSIL_CSI2RX(0x498b), + PSIL_CSI2RX(0x498c), + PSIL_CSI2RX(0x498d), + PSIL_CSI2RX(0x498e), + PSIL_CSI2RX(0x498f), + PSIL_CSI2RX(0x4990), + PSIL_CSI2RX(0x4991), + PSIL_CSI2RX(0x4992), + PSIL_CSI2RX(0x4993), + PSIL_CSI2RX(0x4994), + PSIL_CSI2RX(0x4995), + PSIL_CSI2RX(0x4996), + PSIL_CSI2RX(0x4997), + PSIL_CSI2RX(0x4998), + PSIL_CSI2RX(0x4999), + PSIL_CSI2RX(0x499a), + PSIL_CSI2RX(0x499b), + PSIL_CSI2RX(0x499c), + PSIL_CSI2RX(0x499d), + PSIL_CSI2RX(0x499e), + PSIL_CSI2RX(0x499f), + /* MAIN_CPSW9G */ + PSIL_ETHERNET(0x4a00), + /* MAIN-SA2UL */ + PSIL_SA2UL(0x4a40, 0), + PSIL_SA2UL(0x4a41, 0), + PSIL_SA2UL(0x4a42, 0), + PSIL_SA2UL(0x4a43, 0), + /* MCU_CPSW0 */ + PSIL_ETHERNET(0x7000), + /* MCU_PDMA0 (MCU_PDMA_MISC_G0) - SPI0 */ + PSIL_PDMA_XY_PKT(0x7100), + PSIL_PDMA_XY_PKT(0x7101), + PSIL_PDMA_XY_PKT(0x7102), + PSIL_PDMA_XY_PKT(0x7103), + /* MCU_PDMA1 (MCU_PDMA_MISC_G1) - SPI1-2 */ + PSIL_PDMA_XY_PKT(0x7200), + PSIL_PDMA_XY_PKT(0x7201), + PSIL_PDMA_XY_PKT(0x7202), + PSIL_PDMA_XY_PKT(0x7203), + PSIL_PDMA_XY_PKT(0x7204), + PSIL_PDMA_XY_PKT(0x7205), + PSIL_PDMA_XY_PKT(0x7206), + PSIL_PDMA_XY_PKT(0x7207), + /* MCU_PDMA2 (MCU_PDMA_MISC_G2) - UART0 */ + PSIL_PDMA_XY_PKT(0x7300), + /* MCU_PDMA_ADC - ADC0-1 */ + PSIL_PDMA_XY_TR(0x7400), + PSIL_PDMA_XY_TR(0x7401), + PSIL_PDMA_XY_TR(0x7402), + PSIL_PDMA_XY_TR(0x7403), + /* MCU_SA2UL */ + PSIL_SA2UL(0x7500, 0), + PSIL_SA2UL(0x7501, 0), + PSIL_SA2UL(0x7502, 0), + PSIL_SA2UL(0x7503, 0), +}; + +/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */ +static struct psil_ep j784s4_dst_ep_map[] = { + /* MAIN_CPSW2G */ + PSIL_ETHERNET(0xc640), + PSIL_ETHERNET(0xc641), + PSIL_ETHERNET(0xc642), + PSIL_ETHERNET(0xc643), + PSIL_ETHERNET(0xc644), + PSIL_ETHERNET(0xc645), + PSIL_ETHERNET(0xc646), + PSIL_ETHERNET(0xc647), + /* MAIN_CPSW9G */ + PSIL_ETHERNET(0xca00), + PSIL_ETHERNET(0xca01), + PSIL_ETHERNET(0xca02), + PSIL_ETHERNET(0xca03), + PSIL_ETHERNET(0xca04), + PSIL_ETHERNET(0xca05), + PSIL_ETHERNET(0xca06), + PSIL_ETHERNET(0xca07), + /* MAIN-SA2UL */ + PSIL_SA2UL(0xca40, 1), + PSIL_SA2UL(0xca41, 1), + /* PDMA_SPI_G0 - SPI0-3 */ + PSIL_PDMA_XY_PKT(0xc600), + PSIL_PDMA_XY_PKT(0xc601), + PSIL_PDMA_XY_PKT(0xc602), + PSIL_PDMA_XY_PKT(0xc603), + PSIL_PDMA_XY_PKT(0xc604), + PSIL_PDMA_XY_PKT(0xc605), + PSIL_PDMA_XY_PKT(0xc606), + PSIL_PDMA_XY_PKT(0xc607), + PSIL_PDMA_XY_PKT(0xc608), + PSIL_PDMA_XY_PKT(0xc609), + PSIL_PDMA_XY_PKT(0xc60a), + PSIL_PDMA_XY_PKT(0xc60b), + PSIL_PDMA_XY_PKT(0xc60c), + PSIL_PDMA_XY_PKT(0xc60d), + PSIL_PDMA_XY_PKT(0xc60e), + PSIL_PDMA_XY_PKT(0xc60f), + /* PDMA_SPI_G1 - SPI4-7 */ + PSIL_PDMA_XY_PKT(0xc620), + PSIL_PDMA_XY_PKT(0xc621), + PSIL_PDMA_XY_PKT(0xc622), + PSIL_PDMA_XY_PKT(0xc623), + PSIL_PDMA_XY_PKT(0xc624), + PSIL_PDMA_XY_PKT(0xc625), + PSIL_PDMA_XY_PKT(0xc626), + PSIL_PDMA_XY_PKT(0xc627), + PSIL_PDMA_XY_PKT(0xc628), + PSIL_PDMA_XY_PKT(0xc629), + PSIL_PDMA_XY_PKT(0xc62a), + PSIL_PDMA_XY_PKT(0xc62b), + PSIL_PDMA_XY_PKT(0xc62c), + PSIL_PDMA_XY_PKT(0xc62d), + PSIL_PDMA_XY_PKT(0xc62e), + PSIL_PDMA_XY_PKT(0xc62f), + /* MCU_CPSW0 */ + PSIL_ETHERNET(0xf000), + PSIL_ETHERNET(0xf001), + PSIL_ETHERNET(0xf002), + PSIL_ETHERNET(0xf003), + PSIL_ETHERNET(0xf004), + PSIL_ETHERNET(0xf005), + PSIL_ETHERNET(0xf006), + PSIL_ETHERNET(0xf007), + /* MCU_PDMA_MISC_G0 - SPI0 */ + PSIL_PDMA_XY_PKT(0xf100), + PSIL_PDMA_XY_PKT(0xf101), + PSIL_PDMA_XY_PKT(0xf102), + PSIL_PDMA_XY_PKT(0xf103), + /* MCU_PDMA_MISC_G1 - SPI1-2 */ + PSIL_PDMA_XY_PKT(0xf200), + PSIL_PDMA_XY_PKT(0xf201), + PSIL_PDMA_XY_PKT(0xf202), + PSIL_PDMA_XY_PKT(0xf203), + PSIL_PDMA_XY_PKT(0xf204), + PSIL_PDMA_XY_PKT(0xf205), + PSIL_PDMA_XY_PKT(0xf206), + PSIL_PDMA_XY_PKT(0xf207), + /* MCU_SA2UL */ + PSIL_SA2UL(0xf500, 1), + PSIL_SA2UL(0xf501, 1), +}; + +struct psil_ep_map j784s4_ep_map = { + .name = "j784s4", + .src = j784s4_src_ep_map, + .src_count = ARRAY_SIZE(j784s4_src_ep_map), + .dst = j784s4_dst_ep_map, + .dst_count = ARRAY_SIZE(j784s4_dst_ep_map), +}; diff --git a/drivers/dma/ti/k3-psil-priv.h b/drivers/dma/ti/k3-psil-priv.h index abd650bb7600..c383723d1c8f 100644 --- a/drivers/dma/ti/k3-psil-priv.h +++ b/drivers/dma/ti/k3-psil-priv.h @@ -44,5 +44,6 @@ extern struct psil_ep_map am64_ep_map; extern struct psil_ep_map j721s2_ep_map; extern struct psil_ep_map am62_ep_map; extern struct psil_ep_map am62a_ep_map; +extern struct psil_ep_map j784s4_ep_map; #endif /* K3_PSIL_PRIV_H_ */ diff --git a/drivers/dma/ti/k3-psil.c b/drivers/dma/ti/k3-psil.c index 2da6988a0e7b..c11389d67a3f 100644 --- a/drivers/dma/ti/k3-psil.c +++ b/drivers/dma/ti/k3-psil.c @@ -25,6 +25,7 @@ static const struct soc_device_attribute k3_soc_devices[] = { { .family = "J721S2", .data = &j721s2_ep_map }, { .family = "AM62X", .data = &am62_ep_map }, { .family = "AM62AX", .data = &am62a_ep_map }, + { .family = "J784S4", .data = &j784s4_ep_map }, { /* sentinel */ } }; diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index c07feaff69c0..fc3a2a05ab7b 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4416,6 +4416,7 @@ static const struct soc_device_attribute k3_soc_devices[] = { { .family = "J721S2", .data = &j721e_soc_data}, { .family = "AM62X", .data = &am64_soc_data }, { .family = "AM62AX", .data = &am64_soc_data }, + { .family = "J784S4", .data = &j721e_soc_data }, { /* sentinel */ } }; -- GitLab From 7d90e81a2d5edbd04037100bdd54d955bdd9b0d0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:12 +0200 Subject: [PATCH 1804/5631] driver core: core: move to use class_to_subsys() There are a number of places in core.c that need access to the private subsystem structure of struct class, so move them to use class_to_subsys() instead of accessing it directly. This requires exporting class_to_subsys() out of class.c, but keeping it local to the driver core. Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 + drivers/base/class.c | 2 +- drivers/base/core.c | 121 ++++++++++++++++++++++++++++--------------- 3 files changed, 81 insertions(+), 44 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index 2867ca4ee4ce..6296164bb7f3 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -73,6 +73,8 @@ static inline void subsys_put(struct subsys_private *sp) kset_put(&sp->subsys); } +struct subsys_private *class_to_subsys(const struct class *class); + struct driver_private { struct kobject kobj; struct klist klist_devices; diff --git a/drivers/base/class.c b/drivers/base/class.c index 1f12bd5d56d9..68a6f9b56d19 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -39,7 +39,7 @@ static struct kset *class_kset; * NULL. A call to subsys_put() must be done when finished with the pointer in * order for it to be properly freed. */ -static struct subsys_private *class_to_subsys(const struct class *class) +struct subsys_private *class_to_subsys(const struct class *class) { struct subsys_private *sp = NULL; struct kobject *kobj; diff --git a/drivers/base/core.c b/drivers/base/core.c index 89249be22161..e3bc34fcf779 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3149,8 +3149,8 @@ static const struct kobj_type class_dir_ktype = { .child_ns_type = class_dir_child_ns_type }; -static struct kobject * -class_dir_create_and_add(const struct class *class, struct kobject *parent_kobj) +static struct kobject *class_dir_create_and_add(struct subsys_private *sp, + struct kobject *parent_kobj) { struct class_dir *dir; int retval; @@ -3159,12 +3159,12 @@ class_dir_create_and_add(const struct class *class, struct kobject *parent_kobj) if (!dir) return ERR_PTR(-ENOMEM); - dir->class = class; + dir->class = sp->class; kobject_init(&dir->kobj, &class_dir_ktype); - dir->kobj.kset = &class->p->glue_dirs; + dir->kobj.kset = &sp->glue_dirs; - retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name); + retval = kobject_add(&dir->kobj, parent_kobj, "%s", sp->class->name); if (retval < 0) { kobject_put(&dir->kobj); return ERR_PTR(retval); @@ -3177,9 +3177,10 @@ static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { + struct subsys_private *sp = class_to_subsys(dev->class); struct kobject *kobj = NULL; - if (dev->class) { + if (sp) { struct kobject *parent_kobj; struct kobject *k; @@ -3190,30 +3191,34 @@ static struct kobject *get_device_parent(struct device *dev, */ if (parent == NULL) parent_kobj = virtual_device_parent(dev); - else if (parent->class && !dev->class->ns_type) + else if (parent->class && !dev->class->ns_type) { + subsys_put(sp); return &parent->kobj; - else + } else { parent_kobj = &parent->kobj; + } mutex_lock(&gdp_mutex); /* find our class-directory at the parent and reference it */ - spin_lock(&dev->class->p->glue_dirs.list_lock); - list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) + spin_lock(&sp->glue_dirs.list_lock); + list_for_each_entry(k, &sp->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } - spin_unlock(&dev->class->p->glue_dirs.list_lock); + spin_unlock(&sp->glue_dirs.list_lock); if (kobj) { mutex_unlock(&gdp_mutex); + subsys_put(sp); return kobj; } /* or create a new class-directory at the parent device */ - k = class_dir_create_and_add(dev->class, parent_kobj); + k = class_dir_create_and_add(sp, parent_kobj); /* do not emit an uevent for this simple "glue" directory */ mutex_unlock(&gdp_mutex); + subsys_put(sp); return k; } @@ -3236,10 +3241,23 @@ static struct kobject *get_device_parent(struct device *dev, static inline bool live_in_glue_dir(struct kobject *kobj, struct device *dev) { - if (!kobj || !dev->class || - kobj->kset != &dev->class->p->glue_dirs) + struct subsys_private *sp; + bool retval; + + if (!kobj || !dev->class) return false; - return true; + + sp = class_to_subsys(dev->class); + if (!sp) + return false; + + if (kobj->kset == &sp->glue_dirs) + retval = true; + else + retval = false; + + subsys_put(sp); + return retval; } static inline struct kobject *get_glue_dir(struct device *dev) @@ -3336,6 +3354,7 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) static int device_add_class_symlinks(struct device *dev) { struct device_node *of_node = dev_of_node(dev); + struct subsys_private *sp; int error; if (of_node) { @@ -3345,12 +3364,11 @@ static int device_add_class_symlinks(struct device *dev) /* An error here doesn't warrant bringing down the device */ } - if (!dev->class) + sp = class_to_subsys(dev->class); + if (!sp) return 0; - error = sysfs_create_link(&dev->kobj, - &dev->class->p->subsys.kobj, - "subsystem"); + error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem"); if (error) goto out_devnode; @@ -3362,35 +3380,37 @@ static int device_add_class_symlinks(struct device *dev) } /* link in the class directory pointing to the device */ - error = sysfs_create_link(&dev->class->p->subsys.kobj, - &dev->kobj, dev_name(dev)); + error = sysfs_create_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev)); if (error) goto out_device; - - return 0; + goto exit; out_device: sysfs_remove_link(&dev->kobj, "device"); - out_subsys: sysfs_remove_link(&dev->kobj, "subsystem"); out_devnode: sysfs_remove_link(&dev->kobj, "of_node"); +exit: + subsys_put(sp); return error; } static void device_remove_class_symlinks(struct device *dev) { + struct subsys_private *sp = class_to_subsys(dev->class); + if (dev_of_node(dev)) sysfs_remove_link(&dev->kobj, "of_node"); - if (!dev->class) + if (!sp) return; if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->kobj, "subsystem"); - sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); + sysfs_delete_link(&sp->subsys.kobj, &dev->kobj, dev_name(dev)); + subsys_put(sp); } /** @@ -3499,6 +3519,7 @@ static int device_private_init(struct device *dev) */ int device_add(struct device *dev) { + struct subsys_private *sp; struct device *parent; struct kobject *kobj; struct class_interface *class_intf; @@ -3627,18 +3648,18 @@ int device_add(struct device *dev) klist_add_tail(&dev->p->knode_parent, &parent->p->klist_children); - if (dev->class) { - mutex_lock(&dev->class->p->mutex); + sp = class_to_subsys(dev->class); + if (sp) { + mutex_lock(&sp->mutex); /* tie the class to the device */ - klist_add_tail(&dev->p->knode_class, - &dev->class->p->klist_devices); + klist_add_tail(&dev->p->knode_class, &sp->klist_devices); /* notify any interfaces that the device is here */ - list_for_each_entry(class_intf, - &dev->class->p->interfaces, node) + list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->add_dev) class_intf->add_dev(dev, class_intf); - mutex_unlock(&dev->class->p->mutex); + mutex_unlock(&sp->mutex); + subsys_put(sp); } done: put_device(dev); @@ -3758,6 +3779,7 @@ EXPORT_SYMBOL_GPL(kill_device); */ void device_del(struct device *dev) { + struct subsys_private *sp; struct device *parent = dev->parent; struct kobject *glue_dir = NULL; struct class_interface *class_intf; @@ -3784,18 +3806,20 @@ void device_del(struct device *dev) device_remove_sys_dev_entry(dev); device_remove_file(dev, &dev_attr_dev); } - if (dev->class) { + + sp = class_to_subsys(dev->class); + if (sp) { device_remove_class_symlinks(dev); - mutex_lock(&dev->class->p->mutex); + mutex_lock(&sp->mutex); /* notify any interfaces that the device is now gone */ - list_for_each_entry(class_intf, - &dev->class->p->interfaces, node) + list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->remove_dev) class_intf->remove_dev(dev, class_intf); /* remove the device from the class list */ klist_del(&dev->p->knode_class); - mutex_unlock(&dev->class->p->mutex); + mutex_unlock(&sp->mutex); + subsys_put(sp); } device_remove_file(dev, &dev_attr_uevent); device_remove_attrs(dev); @@ -4458,9 +4482,16 @@ int device_rename(struct device *dev, const char *new_name) } if (dev->class) { - error = sysfs_rename_link_ns(&dev->class->p->subsys.kobj, - kobj, old_device_name, + struct subsys_private *sp = class_to_subsys(dev->class); + + if (!sp) { + error = -EINVAL; + goto out; + } + + error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); + subsys_put(sp); if (error) goto out; } @@ -4643,6 +4674,7 @@ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int error; struct kobject *kobj = &dev->kobj; + struct subsys_private *sp; dev = get_device(dev); if (!dev) @@ -4685,10 +4717,13 @@ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) * directory entry for @dev to @kuid/@kgid. This ensures that the * symlink shows the same permissions as its target. */ - error = sysfs_link_change_owner(&dev->class->p->subsys.kobj, &dev->kobj, - dev_name(dev), kuid, kgid); - if (error) + sp = class_to_subsys(dev->class); + if (!sp) { + error = -EINVAL; goto out; + } + error = sysfs_link_change_owner(&sp->subsys.kobj, &dev->kobj, dev_name(dev), kuid, kgid); + subsys_put(sp); out: put_device(dev); -- GitLab From c8879d3f87ffbaf6954dabec2199905616b0139e Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Mon, 27 Feb 2023 16:13:19 +0100 Subject: [PATCH 1805/5631] phy: stm32-usphyc: add 200 to 300 us delay to fix timeout on some machines An minimum udelay of 200 us seems to be necessary on some machines. After the setup of the pll, which needs about 100 us to be locked there seem to be additional 100 us to get the phy really functional. Without this delay the usb runs not functional. With this additional short udelay this issue was not reported again. Signed-off-by: Michael Grzeschik Reviewed-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230227151318.1894938-1-m.grzeschik@pengutronix.de Signed-off-by: Vinod Koul --- drivers/phy/st/phy-stm32-usbphyc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 1add3b75f92f..0a8552628cbd 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -317,6 +317,9 @@ static int stm32_usbphyc_pll_enable(struct stm32_usbphyc *usbphyc) stm32_usbphyc_set_bits(pll_reg, PLLEN); + /* Wait for maximum lock time */ + usleep_range(200, 300); + return 0; reg_disable: -- GitLab From c8481d996f2f68244a5b3cf59915b43128f40db8 Mon Sep 17 00:00:00 2001 From: Radhey Shyam Pandey Date: Mon, 27 Mar 2023 23:36:47 +0530 Subject: [PATCH 1806/5631] phy: xilinx: phy-zynqmp: mention SGMII as supported protocol SGMII is validated on kria KR260 robotics starter kit. So modify the comment description to include it in supported controllers list. Signed-off-by: Radhey Shyam Pandey Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/1679940407-13131-1-git-send-email-radhey.shyam.pandey@amd.com Signed-off-by: Vinod Koul --- drivers/phy/xilinx/phy-zynqmp.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c index 9be9535ad7ab..8833680923a1 100644 --- a/drivers/phy/xilinx/phy-zynqmp.c +++ b/drivers/phy/xilinx/phy-zynqmp.c @@ -8,9 +8,8 @@ * Author: Subbaraya Sundeep * Author: Laurent Pinchart * - * This driver is tested for USB, SATA and Display Port currently. - * Other controllers PCIe and SGMII should also work but that is - * experimental as of now. + * This driver is tested for USB, SGMII, SATA and Display Port currently. + * PCIe should also work but that is experimental as of now. */ #include -- GitLab From 6ef7aa323bd8c1f02bbf83afd1987f5dd7eaaef4 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 25 Mar 2023 18:14:15 -0700 Subject: [PATCH 1807/5631] phy: cadence: Sierra: Replace `clk_register(`) with `clk_hw_register()` The `devm_clk_register()` API is deprecated. Switch to `devm_clk_hw_register()`. Since the driver enables its own internal PLLs using the clock API we still need to get a reference to the PLL clocks using the `devm_clk_hw_get_clk()` API. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230326011416.363318-1-lars@metafoo.de Signed-off-by: Vinod Koul --- drivers/phy/cadence/phy-cadence-sierra.c | 46 +++++++++++++----------- 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index 294d59b9eaed..05abce477ce5 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -371,8 +371,8 @@ struct cdns_sierra_phy { u32 num_lanes; bool autoconf; int already_configured; - struct clk_onecell_data clk_data; - struct clk *output_clks[CDNS_SIERRA_OUTPUT_CLOCKS]; + struct clk *pll_clks[SIERRA_NUM_CMN_PLLC]; + struct clk_hw_onecell_data clk_data; }; static int cdns_regmap_write(void *context, unsigned int reg, unsigned int val) @@ -726,6 +726,7 @@ static int cdns_sierra_pll_mux_register(struct cdns_sierra_phy *sp, unsigned int num_parents; char clk_name[100]; struct clk *clk; + int ret; int i; mux = devm_kzalloc(dev, sizeof(*mux), GFP_KERNEL); @@ -761,11 +762,14 @@ static int cdns_sierra_pll_mux_register(struct cdns_sierra_phy *sp, mux->termen_field = termen_field; mux->hw.init = init; - clk = devm_clk_register(dev, &mux->hw); - if (IS_ERR(clk)) - return PTR_ERR(clk); + ret = devm_clk_hw_register(dev, &mux->hw); + if (ret) + return ret; + + sp->clk_data.hws[clk_index] = &mux->hw; - sp->output_clks[clk_index] = clk; + sp->pll_clks[clk_index] = devm_clk_hw_get_clk(dev, &mux->hw, + clk_names[clk_index]); return 0; } @@ -838,7 +842,7 @@ static int cdns_sierra_derived_refclk_register(struct cdns_sierra_phy *sp) struct clk_init_data *init; struct regmap *regmap; char clk_name[100]; - struct clk *clk; + int ret; derived_refclk = devm_kzalloc(dev, sizeof(*derived_refclk), GFP_KERNEL); if (!derived_refclk) @@ -871,11 +875,11 @@ static int cdns_sierra_derived_refclk_register(struct cdns_sierra_phy *sp) derived_refclk->hw.init = init; - clk = devm_clk_register(dev, &derived_refclk->hw); - if (IS_ERR(clk)) - return PTR_ERR(clk); + ret = devm_clk_hw_register(dev, &derived_refclk->hw); + if (ret) + return ret; - sp->output_clks[CDNS_SIERRA_DERIVED_REFCLK] = clk; + sp->clk_data.hws[CDNS_SIERRA_DERIVED_REFCLK] = &derived_refclk->hw; return 0; } @@ -906,9 +910,9 @@ static int cdns_sierra_clk_register(struct cdns_sierra_phy *sp) return ret; } - sp->clk_data.clks = sp->output_clks; - sp->clk_data.clk_num = CDNS_SIERRA_OUTPUT_CLOCKS; - ret = of_clk_add_provider(node, of_clk_src_onecell_get, &sp->clk_data); + sp->clk_data.num = CDNS_SIERRA_OUTPUT_CLOCKS; + ret = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, + &sp->clk_data); if (ret) dev_err(dev, "Failed to add clock provider: %s\n", node->name); @@ -1190,26 +1194,26 @@ static int cdns_sierra_phy_enable_clocks(struct cdns_sierra_phy *sp) { int ret; - ret = clk_prepare_enable(sp->output_clks[CDNS_SIERRA_PLL_CMNLC]); + ret = clk_prepare_enable(sp->pll_clks[CDNS_SIERRA_PLL_CMNLC]); if (ret) return ret; - ret = clk_prepare_enable(sp->output_clks[CDNS_SIERRA_PLL_CMNLC1]); + ret = clk_prepare_enable(sp->pll_clks[CDNS_SIERRA_PLL_CMNLC1]); if (ret) goto err_pll_cmnlc1; return 0; err_pll_cmnlc1: - clk_disable_unprepare(sp->output_clks[CDNS_SIERRA_PLL_CMNLC]); + clk_disable_unprepare(sp->pll_clks[CDNS_SIERRA_PLL_CMNLC]); return ret; } static void cdns_sierra_phy_disable_clocks(struct cdns_sierra_phy *sp) { - clk_disable_unprepare(sp->output_clks[CDNS_SIERRA_PLL_CMNLC1]); - clk_disable_unprepare(sp->output_clks[CDNS_SIERRA_PLL_CMNLC]); + clk_disable_unprepare(sp->pll_clks[CDNS_SIERRA_PLL_CMNLC1]); + clk_disable_unprepare(sp->pll_clks[CDNS_SIERRA_PLL_CMNLC]); if (!sp->already_configured) clk_disable_unprepare(sp->input_clks[PHY_CLK]); } @@ -1370,7 +1374,9 @@ static int cdns_sierra_phy_probe(struct platform_device *pdev) if (!data) return -EINVAL; - sp = devm_kzalloc(dev, sizeof(*sp), GFP_KERNEL); + sp = devm_kzalloc(dev, struct_size(sp, clk_data.hws, + CDNS_SIERRA_OUTPUT_CLOCKS), + GFP_KERNEL); if (!sp) return -ENOMEM; dev_set_drvdata(dev, sp); -- GitLab From a59f6006cc07a676aff7c0e2ae70a8094b670034 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sat, 25 Mar 2023 18:14:16 -0700 Subject: [PATCH 1808/5631] phy: cadence: Sierra: Use clk_parent_data to provide parent information Rather than requesting the parent reference clocks for the sierra PHY PLLs and then assigning the parents as a struct clk. Use the clk_parent_data feature for the clock framework and only specify the firmware names of the parent clocks. The clock framework internally will then translate this to the actual clocks. This allows to remove a bit of boilerplate code. It also allows to only specify a single reference clock for both PLLs, which is a valid use case. The clock framework can handle the case where not all inputs for a clock mux are connected, while the custom implementation in the driver could not. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230326011416.363318-2-lars@metafoo.de Signed-off-by: Vinod Koul --- drivers/phy/cadence/phy-cadence-sierra.c | 57 +++++++----------------- 1 file changed, 15 insertions(+), 42 deletions(-) diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index 05abce477ce5..ab0a37618ef3 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -206,13 +206,11 @@ #define PLL_LOCK_TIME 100000 #define CDNS_SIERRA_OUTPUT_CLOCKS 3 -#define CDNS_SIERRA_INPUT_CLOCKS 5 +#define CDNS_SIERRA_INPUT_CLOCKS 3 enum cdns_sierra_clock_input { PHY_CLK, CMN_REFCLK_DIG_DIV, CMN_REFCLK1_DIG_DIV, - PLL0_REFCLK, - PLL1_REFCLK, }; #define SIERRA_NUM_CMN_PLLC 2 @@ -274,9 +272,18 @@ struct cdns_sierra_pll_mux { #define to_cdns_sierra_pll_mux(_hw) \ container_of(_hw, struct cdns_sierra_pll_mux, hw) -static const int pll_mux_parent_index[][SIERRA_NUM_CMN_PLLC_PARENTS] = { - [CMN_PLLLC] = { PLL0_REFCLK, PLL1_REFCLK }, - [CMN_PLLLC1] = { PLL1_REFCLK, PLL0_REFCLK }, +#define PLL0_REFCLK_NAME "pll0_refclk" +#define PLL1_REFCLK_NAME "pll1_refclk" + +static const struct clk_parent_data pll_mux_parent_data[][SIERRA_NUM_CMN_PLLC_PARENTS] = { + [CMN_PLLLC] = { + { .fw_name = PLL0_REFCLK_NAME }, + { .fw_name = PLL1_REFCLK_NAME } + }, + [CMN_PLLLC1] = { + { .fw_name = PLL1_REFCLK_NAME }, + { .fw_name = PLL0_REFCLK_NAME } + }, }; static u32 cdns_sierra_pll_mux_table[][SIERRA_NUM_CMN_PLLC_PARENTS] = { @@ -722,39 +729,21 @@ static int cdns_sierra_pll_mux_register(struct cdns_sierra_phy *sp, struct cdns_sierra_pll_mux *mux; struct device *dev = sp->dev; struct clk_init_data *init; - const char **parent_names; - unsigned int num_parents; char clk_name[100]; - struct clk *clk; int ret; - int i; mux = devm_kzalloc(dev, sizeof(*mux), GFP_KERNEL); if (!mux) return -ENOMEM; - num_parents = SIERRA_NUM_CMN_PLLC_PARENTS; - parent_names = devm_kzalloc(dev, (sizeof(char *) * num_parents), GFP_KERNEL); - if (!parent_names) - return -ENOMEM; - - for (i = 0; i < num_parents; i++) { - clk = sp->input_clks[pll_mux_parent_index[clk_index][i]]; - if (IS_ERR_OR_NULL(clk)) { - dev_err(dev, "No parent clock for PLL mux clocks\n"); - return IS_ERR(clk) ? PTR_ERR(clk) : -ENOENT; - } - parent_names[i] = __clk_get_name(clk); - } - snprintf(clk_name, sizeof(clk_name), "%s_%s", dev_name(dev), clk_names[clk_index]); init = &mux->clk_data; init->ops = &cdns_sierra_pll_mux_ops; init->flags = CLK_SET_RATE_NO_REPARENT; - init->parent_names = parent_names; - init->num_parents = num_parents; + init->parent_data = pll_mux_parent_data[clk_index]; + init->num_parents = SIERRA_NUM_CMN_PLLC_PARENTS; init->name = clk_name; mux->pfdclk_sel_preg = pfdclk1_sel_field; @@ -1151,22 +1140,6 @@ static int cdns_sierra_phy_get_clocks(struct cdns_sierra_phy *sp, } sp->input_clks[CMN_REFCLK1_DIG_DIV] = clk; - clk = devm_clk_get_optional(dev, "pll0_refclk"); - if (IS_ERR(clk)) { - dev_err(dev, "pll0_refclk clock not found\n"); - ret = PTR_ERR(clk); - return ret; - } - sp->input_clks[PLL0_REFCLK] = clk; - - clk = devm_clk_get_optional(dev, "pll1_refclk"); - if (IS_ERR(clk)) { - dev_err(dev, "pll1_refclk clock not found\n"); - ret = PTR_ERR(clk); - return ret; - } - sp->input_clks[PLL1_REFCLK] = clk; - return 0; } -- GitLab From e43462c15b33a15816d8d6373ff721c17f5436e1 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 20 Mar 2023 18:39:52 -0500 Subject: [PATCH 1809/5631] dt-bindings: phy: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Acked-by: Jernej Skrabec Acked-by: Marc Kleine-Budde # for ti,tcan104x-can.yaml Reviewed-by: Krzysztof Kozlowski Acked-by: Sergio Paracuellos Link: https://lore.kernel.org/r/20230320233955.2921179-1-robh@kernel.org Signed-off-by: Vinod Koul --- .../bindings/phy/allwinner,sun50i-h6-usb3-phy.yaml | 4 ++-- .../bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml | 2 +- .../devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml | 4 ++-- .../bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml | 4 ++-- .../devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml | 4 ++-- .../devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml | 4 ++-- .../bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml | 4 ++-- .../devicetree/bindings/phy/amlogic,meson-axg-pcie.yaml | 4 ++-- .../devicetree/bindings/phy/amlogic,meson8-hdmi-tx-phy.yaml | 4 ++-- .../devicetree/bindings/phy/amlogic,meson8b-usb2-phy.yaml | 4 ++-- .../devicetree/bindings/phy/brcm,bcm63xx-usbh-phy.yaml | 4 ++-- Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml | 4 ++-- Documentation/devicetree/bindings/phy/cdns,salvo-phy.yaml | 4 ++-- .../devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml | 4 ++-- .../devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml | 6 +++--- .../bindings/phy/marvell,armada-3700-utmi-phy.yaml | 4 ++-- .../bindings/phy/marvell,armada-cp110-utmi-phy.yaml | 4 ++-- .../devicetree/bindings/phy/marvell,mmp3-hsic-phy.yaml | 4 ++-- .../devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml | 4 ++-- .../devicetree/bindings/phy/phy-cadence-sierra.yaml | 4 ++-- .../devicetree/bindings/phy/phy-cadence-torrent.yaml | 4 ++-- Documentation/devicetree/bindings/phy/phy-tegra194-p2u.yaml | 4 ++-- Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml | 4 ++-- Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml | 4 ++-- Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml | 4 ++-- .../devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml | 4 ++-- Documentation/devicetree/bindings/phy/qcom,usb-ss.yaml | 4 ++-- .../devicetree/bindings/phy/qcom-usb-ipq4019-phy.yaml | 4 ++-- .../devicetree/bindings/phy/samsung,exynos-pcie-phy.yaml | 4 ++-- Documentation/devicetree/bindings/phy/samsung,ufs-phy.yaml | 2 +- .../devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml | 4 ++-- .../devicetree/bindings/phy/ti,phy-am654-serdes.yaml | 4 ++-- Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml | 4 ++-- Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml | 4 ++-- Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml | 4 ++-- 35 files changed, 69 insertions(+), 69 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb3-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb3-phy.yaml index c03b83103e87..cf4eed230565 100644 --- a/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb3-phy.yaml +++ b/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb3-phy.yaml @@ -2,8 +2,8 @@ # Copyright 2019 Ondrej Jirman %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/allwinner,sun50i-h6-usb3-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/allwinner,sun50i-h6-usb3-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Allwinner H6 USB3 PHY diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml index fe9702e7bdd8..6a4fd4929959 100644 --- a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml +++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml @@ -45,7 +45,7 @@ properties: maxItems: 1 allwinner,direction: - $ref: '/schemas/types.yaml#/definitions/string' + $ref: /schemas/types.yaml#/definitions/string description: | Direction of the D-PHY: - "rx" for receiving (e.g. when used with MIPI CSI-2); diff --git a/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml index 5eddaed3d853..64795f170f32 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,axg-mipi-dphy.yaml @@ -2,8 +2,8 @@ # Copyright 2020 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,axg-mipi-dphy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,axg-mipi-dphy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic AXG MIPI D-PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml index 7aa0c05d6ce4..c8c83acfb871 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-mipi-dphy-analog.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,g12a-mipi-dphy-analog.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,g12a-mipi-dphy-analog.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic G12A MIPI analog PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml index bb01c6b34dab..0031fb6a4e76 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml @@ -2,8 +2,8 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic G12A USB2 PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml index 3314711292d6..1a5a12adb72b 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml @@ -2,8 +2,8 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic G12A USB3 + PCIE Combo PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml index a90fa1baadab..009a39808318 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-mipi-pcie-analog.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-axg-mipi-pcie-analog.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,meson-axg-mipi-pcie-analog.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic AXG shared MIPI/PCIE analog PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-pcie.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-pcie.yaml index 45f3d72b1cca..40fbf8ac3271 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-axg-pcie.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,meson-axg-pcie.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-axg-pcie.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,meson-axg-pcie.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic AXG PCIE PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson8-hdmi-tx-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson8-hdmi-tx-phy.yaml index 1f085cdd1c85..6f9fd1c953f0 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson8-hdmi-tx-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,meson8-hdmi-tx-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson8-hdmi-tx-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,meson8-hdmi-tx-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic Meson8, Meson8b and Meson8m2 HDMI TX PHY diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson8b-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,meson8b-usb2-phy.yaml index 03c4809dbe8d..df68bfe5f407 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson8b-usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,meson8b-usb2-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson8b-usb2-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/amlogic,meson8b-usb2-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Amlogic Meson8, Meson8b, Meson8m2 and GXBB USB2 PHY diff --git a/Documentation/devicetree/bindings/phy/brcm,bcm63xx-usbh-phy.yaml b/Documentation/devicetree/bindings/phy/brcm,bcm63xx-usbh-phy.yaml index 0f0bcde9eb88..bd527f566c3b 100644 --- a/Documentation/devicetree/bindings/phy/brcm,bcm63xx-usbh-phy.yaml +++ b/Documentation/devicetree/bindings/phy/brcm,bcm63xx-usbh-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/brcm,bcm63xx-usbh-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/brcm,bcm63xx-usbh-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: BCM63xx USBH PHY diff --git a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml index 435b971dfd9b..8467c8e6368c 100644 --- a/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml +++ b/Documentation/devicetree/bindings/phy/brcm,sata-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/brcm,sata-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/brcm,sata-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Broadcom SATA3 PHY diff --git a/Documentation/devicetree/bindings/phy/cdns,salvo-phy.yaml b/Documentation/devicetree/bindings/phy/cdns,salvo-phy.yaml index 3a07285b5470..c9e65a2facd5 100644 --- a/Documentation/devicetree/bindings/phy/cdns,salvo-phy.yaml +++ b/Documentation/devicetree/bindings/phy/cdns,salvo-phy.yaml @@ -2,8 +2,8 @@ # Copyright (c) 2020 NXP %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/cdns,salvo-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/cdns,salvo-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Cadence SALVO PHY diff --git a/Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml b/Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml index b11d9873854a..405c6b0b88c0 100644 --- a/Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml +++ b/Documentation/devicetree/bindings/phy/hisilicon,hi3660-usb3.yaml @@ -19,11 +19,11 @@ properties: const: 0 hisilicon,pericrg-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle of syscon used to control iso refclk. hisilicon,pctrl-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle of syscon used to control usb tcxo. hisilicon,eye-diagram-param: diff --git a/Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml b/Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml index 3c69aca6c7eb..a1a8a84dfc54 100644 --- a/Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml +++ b/Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml @@ -20,15 +20,15 @@ properties: const: 0 hisilicon,pericrg-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle of syscon used to control iso refclk. hisilicon,pctrl-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle of syscon used to control usb tcxo. hisilicon,sctrl-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle of syscon used to control phy deep sleep. hisilicon,eye-diagram-param: diff --git a/Documentation/devicetree/bindings/phy/marvell,armada-3700-utmi-phy.yaml b/Documentation/devicetree/bindings/phy/marvell,armada-3700-utmi-phy.yaml index 632d61c07f40..3aa1a46796dd 100644 --- a/Documentation/devicetree/bindings/phy/marvell,armada-3700-utmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/marvell,armada-3700-utmi-phy.yaml @@ -2,8 +2,8 @@ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/marvell,armada-3700-utmi-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/marvell,armada-3700-utmi-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell Armada UTMI/UTMI+ PHY diff --git a/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml b/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml index 30f3b5f32a95..34a56e3cfff5 100644 --- a/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/marvell,armada-cp110-utmi-phy.yaml @@ -2,8 +2,8 @@ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/marvell,armada-cp110-utmi-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/marvell,armada-cp110-utmi-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell Armada CP110/CP115 UTMI PHY diff --git a/Documentation/devicetree/bindings/phy/marvell,mmp3-hsic-phy.yaml b/Documentation/devicetree/bindings/phy/marvell,mmp3-hsic-phy.yaml index ff255aa4cc10..bd3bd2f8b1cd 100644 --- a/Documentation/devicetree/bindings/phy/marvell,mmp3-hsic-phy.yaml +++ b/Documentation/devicetree/bindings/phy/marvell,mmp3-hsic-phy.yaml @@ -2,8 +2,8 @@ # Copyright 2019 Lubomir Rintel %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/marvell,mmp3-hsic-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/marvell,mmp3-hsic-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Marvell MMP3 HSIC PHY diff --git a/Documentation/devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml index c2f4cb0b254a..b35c4d256e40 100644 --- a/Documentation/devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml +++ b/Documentation/devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only or BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/mediatek,mt7621-pci-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/mediatek,mt7621-pci-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek Mt7621 PCIe PHY diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml index 6a09472740ed..c3d1fa102798 100644 --- a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml +++ b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/phy-cadence-sierra.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/phy-cadence-sierra.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Cadence Sierra PHY diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml index 2ad1faadda2a..dc92be05fe5f 100644 --- a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml +++ b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/phy-cadence-torrent.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/phy-cadence-torrent.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Cadence Torrent SD0801 PHY diff --git a/Documentation/devicetree/bindings/phy/phy-tegra194-p2u.yaml b/Documentation/devicetree/bindings/phy/phy-tegra194-p2u.yaml index 445b2467f4f6..4790c6238a40 100644 --- a/Documentation/devicetree/bindings/phy/phy-tegra194-p2u.yaml +++ b/Documentation/devicetree/bindings/phy/phy-tegra194-p2u.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/phy-tegra194-p2u.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/phy-tegra194-p2u.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: NVIDIA Tegra194 & Tegra234 P2U diff --git a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml index 1e104ae76ee6..c4f8e6ffa5c3 100644 --- a/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,edp-phy.yaml @@ -2,8 +2,8 @@ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom,edp-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom,edp-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm eDP PHY diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml index 7f403e77f320..543c1a2811a5 100644 --- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml @@ -2,8 +2,8 @@ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom,qusb2-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom,qusb2-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm QUSB2 phy controller diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml index ca6a0836b53c..6c99e02b2b4f 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom,usb-hs-28nm.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom,usb-hs-28nm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Synopsys DesignWare Core 28nm High-Speed PHY diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml index 85d405e028b9..a26524b7e7b7 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-snps-femto-v2.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom,usb-snps-femto-v2.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom,usb-snps-femto-v2.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Synopsys Femto High-Speed USB PHY V2 diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-ss.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-ss.yaml index bd1388d62ce0..6e4254ff1cd7 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-ss.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-ss.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom,usb-ss.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom,usb-ss.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Synopsys 1.0.0 SuperSpeed USB PHY diff --git a/Documentation/devicetree/bindings/phy/qcom-usb-ipq4019-phy.yaml b/Documentation/devicetree/bindings/phy/qcom-usb-ipq4019-phy.yaml index 3e7191b168fb..09c614952fea 100644 --- a/Documentation/devicetree/bindings/phy/qcom-usb-ipq4019-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom-usb-ipq4019-phy.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/qcom-usb-ipq4019-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/qcom-usb-ipq4019-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcom IPQ40xx Dakota HS/SS USB PHY diff --git a/Documentation/devicetree/bindings/phy/samsung,exynos-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,exynos-pcie-phy.yaml index 28e299a9609d..41df8bb08ff7 100644 --- a/Documentation/devicetree/bindings/phy/samsung,exynos-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,exynos-pcie-phy.yaml @@ -21,12 +21,12 @@ properties: maxItems: 1 samsung,pmu-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle for PMU system controller interface, used to control PMU registers bits for PCIe PHY samsung,fsys-sysreg: - $ref: '/schemas/types.yaml#/definitions/phandle' + $ref: /schemas/types.yaml#/definitions/phandle description: phandle for FSYS sysreg interface, used to control sysreg registers bits for PCIe PHY diff --git a/Documentation/devicetree/bindings/phy/samsung,ufs-phy.yaml b/Documentation/devicetree/bindings/phy/samsung,ufs-phy.yaml index c5dbb91ac402..782f975b43ae 100644 --- a/Documentation/devicetree/bindings/phy/samsung,ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/samsung,ufs-phy.yaml @@ -35,7 +35,7 @@ properties: maxItems: 4 samsung,pmu-syscon: - $ref: '/schemas/types.yaml#/definitions/phandle-array' + $ref: /schemas/types.yaml#/definitions/phandle-array maxItems: 1 items: minItems: 1 diff --git a/Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml index 069d422775bb..57914f214e06 100644 --- a/Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml @@ -2,8 +2,8 @@ # Copyright (C) Sunplus Co., Ltd. 2021 %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/sunplus,sp7021-usb2-phy.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/sunplus,sp7021-usb2-phy.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Sunplus SP7021 USB 2.0 PHY Controller diff --git a/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml b/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml index 738c92bb7518..2a886b91bf2d 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml @@ -35,9 +35,9 @@ properties: clock. assigned-clocks: - $ref: "/schemas/types.yaml#/definitions/phandle-array" + $ref: /schemas/types.yaml#/definitions/phandle-array assigned-clock-parents: - $ref: "/schemas/types.yaml#/definitions/phandle-array" + $ref: /schemas/types.yaml#/definitions/phandle-array '#phy-cells': const: 2 diff --git a/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml b/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml index 6d46f57fa1b4..3699a06bdf6e 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml @@ -2,8 +2,8 @@ # Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/ti,phy-gmii-sel.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/ti,phy-gmii-sel.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: CPSW Port's Interface Mode Selection PHY diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index c54b36c104ab..a55fc0f24533 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -2,8 +2,8 @@ # Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/ti,phy-j721e-wiz.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/ti,phy-j721e-wiz.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: TI J721E WIZ (SERDES Wrapper) diff --git a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml index 237295b2b5a8..79dad3e89aa6 100644 --- a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml +++ b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/ti,tcan104x-can.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/phy/ti,tcan104x-can.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: TCAN104x CAN TRANSCEIVER PHY -- GitLab From 4546334fc14fc1176384c7c7a426be9fef738c3e Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 23 Mar 2023 17:47:25 +0300 Subject: [PATCH 1810/5631] phy: qcom-qmp-combo: fix v3 offsets table SM8350 and SM8450 use qmp_combo_offsets_v3 table, which doesn't have PCS_USB offset. Add the usb3_pcs_usb entry to program correct registers while setting up sm8350 and sm8450 USB+DP combo PHYs. Fixes: 05bd18348b88 ("phy: qcom-qmp-combo: Add config for SM6350") Cc: Neil Armstrong Signed-off-by: Dmitry Baryshkov Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230323144726.1614344-1-dmitry.baryshkov@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index c1483e157af4..3b488d12c933 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -1396,6 +1396,7 @@ static const struct qmp_combo_offsets qmp_combo_offsets_v3 = { .usb3_serdes = 0x1000, .usb3_pcs_misc = 0x1a00, .usb3_pcs = 0x1c00, + .usb3_pcs_usb = 0x1f00, .dp_serdes = 0x2000, .dp_txa = 0x2200, .dp_txb = 0x2600, -- GitLab From eb016875080cf035f588fa31c7d1e43dfe462451 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Thu, 23 Mar 2023 17:47:26 +0300 Subject: [PATCH 1811/5631] phy: qcom-qmp-combo: use qmp_combo_offsets_v3 instead of _v6 The qmp_combo_offsets_v3 table is already used for v3 and v4 PHYs. Reuse it for v6 too, dropping the separate qmp_combo_offsets_v6. Signed-off-by: Dmitry Baryshkov Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230323144726.1614344-2-dmitry.baryshkov@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 3b488d12c933..6850e04c329b 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -1417,22 +1417,6 @@ static const struct qmp_combo_offsets qmp_combo_offsets_v5 = { .dp_dp_phy = 0x2200, }; -static const struct qmp_combo_offsets qmp_combo_offsets_v6 = { - .com = 0x0000, - .txa = 0x1200, - .rxa = 0x1400, - .txb = 0x1600, - .rxb = 0x1800, - .usb3_serdes = 0x1000, - .usb3_pcs_misc = 0x1a00, - .usb3_pcs = 0x1c00, - .usb3_pcs_usb = 0x1f00, - .dp_serdes = 0x2000, - .dp_txa = 0x2200, - .dp_txb = 0x2600, - .dp_dp_phy = 0x2a00, -}; - static const struct qmp_phy_cfg sc7180_usb3dpphy_cfg = { .serdes_tbl = qmp_v3_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(qmp_v3_usb3_serdes_tbl), @@ -1759,7 +1743,7 @@ static const struct qmp_phy_cfg sm8350_usb3dpphy_cfg = { }; static const struct qmp_phy_cfg sm8550_usb3dpphy_cfg = { - .offsets = &qmp_combo_offsets_v6, + .offsets = &qmp_combo_offsets_v3, .serdes_tbl = sm8550_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(sm8550_usb3_serdes_tbl), -- GitLab From d414c14c2d162f379f62bc48ef8eb7dfd1c08be5 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Thu, 23 Mar 2023 15:35:34 +0800 Subject: [PATCH 1812/5631] phy: dphy: Use devm_platform_ioremap_resource() According to commit 7945f929f1a7 ("drivers: provide devm_platform_ioremap_resource()"), convert platform_get_resource(), devm_ioremap_resource() to a single call to use devm_platform_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Yang Li Reviewed-by: Neil Armstrong Link: https://lore.kernel.org/r/20230323073534.75037-1-yang.lee@linux.alibaba.com Signed-off-by: Vinod Koul --- drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c b/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c index 32d1ff09befb..6e9af79e152c 100644 --- a/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c +++ b/drivers/phy/amlogic/phy-meson-axg-mipi-dphy.c @@ -335,7 +335,6 @@ static int phy_meson_axg_mipi_dphy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct phy_provider *phy_provider; - struct resource *res; struct phy_meson_axg_mipi_dphy_priv *priv; struct phy *phy; void __iomem *base; @@ -348,8 +347,7 @@ static int phy_meson_axg_mipi_dphy_probe(struct platform_device *pdev) priv->dev = dev; platform_set_drvdata(pdev, priv); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); -- GitLab From 623cb3e22c9d7ecb655df8e32701c8a92313746b Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Thu, 23 Mar 2023 15:45:52 +0800 Subject: [PATCH 1813/5631] phy: omap-usb2-phy: Use dev_err_probe() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace the open-code with dev_err_probe() to simplify the code. Signed-off-by: Ye Xingchen Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/202303231545522162256@zte.com.cn Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-omap-usb2.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index bbe5d25b0351..762d3de8b3c5 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -445,11 +445,9 @@ static int omap_usb2_probe(struct platform_device *pdev) PTR_ERR(phy->wkupclk)); phy->wkupclk = devm_clk_get(phy->dev, "usb_phy_cm_clk32k"); - if (IS_ERR(phy->wkupclk)) { - if (PTR_ERR(phy->wkupclk) != -EPROBE_DEFER) - dev_err(&pdev->dev, "unable to get usb_phy_cm_clk32k\n"); - return PTR_ERR(phy->wkupclk); - } + if (IS_ERR(phy->wkupclk)) + return dev_err_probe(&pdev->dev, PTR_ERR(phy->wkupclk), + "unable to get usb_phy_cm_clk32k\n"); dev_warn(&pdev->dev, "found usb_phy_cm_clk32k, please fix DTS\n"); -- GitLab From 64cdc036081153981d01406d0a847c535d8e6a75 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 21 Mar 2023 08:25:03 -0400 Subject: [PATCH 1814/5631] phy: rockchip-pcie: remove unused phy_rd_cfg function clang with W=1 reports drivers/phy/rockchip/phy-rockchip-pcie.c:122:19: error: unused function 'phy_rd_cfg' [-Werror,-Wunused-function] static inline u32 phy_rd_cfg(struct rockchip_pcie_phy *rk_phy, ^ This function is not used, so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230321122503.1783311-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-pcie.c | 15 --------------- 1 file changed, 15 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c index 75216091d901..8234b83fdd88 100644 --- a/drivers/phy/rockchip/phy-rockchip-pcie.c +++ b/drivers/phy/rockchip/phy-rockchip-pcie.c @@ -119,21 +119,6 @@ static inline void phy_wr_cfg(struct rockchip_pcie_phy *rk_phy, PHY_CFG_WR_SHIFT)); } -static inline u32 phy_rd_cfg(struct rockchip_pcie_phy *rk_phy, - u32 addr) -{ - u32 val; - - regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf, - HIWORD_UPDATE(addr, - PHY_CFG_RD_MASK, - PHY_CFG_ADDR_SHIFT)); - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &val); - return val; -} - static int rockchip_pcie_phy_power_off(struct phy *phy) { struct phy_pcie_instance *inst = phy_get_drvdata(phy); -- GitLab From 0d678713118352614b14aba0c1fb066b1ba39f53 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Fri, 17 Mar 2023 12:08:33 +0530 Subject: [PATCH 1815/5631] dt-bindings: phy: qcom,qmp: Add SDX65 QMP PHY Add devicetree YAML binding for Qualcomm QMP Super Speed (SS) PHY found in SDX65. Signed-off-by: Rohit Agarwal Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/1679035114-19879-2-git-send-email-quic_rohiagar@quicinc.com Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index ef49efbd0a20..a0407fc79563 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -19,6 +19,7 @@ properties: - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy + - qcom,sdx65-qmp-gen4x2-pcie-phy - qcom,sm8350-qmp-gen3x1-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen4x2-pcie-phy -- GitLab From 92bd868f529a7771f15a141e8db6b6b62b32310a Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Fri, 17 Mar 2023 12:08:34 +0530 Subject: [PATCH 1816/5631] phy: qcom-qmp: Add support for SDX65 QMP PCIe PHY The PCIe PHY version used in SDX65 is v5.20 which has different register offsets compared to the v5.0x and v4.0x PHYs. So separate register defines are used for init sequence and PHY status. Signed-off-by: Rohit Agarwal Link: https://lore.kernel.org/r/1679035114-19879-3-git-send-email-quic_rohiagar@quicinc.com Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 165 ++++++++++++++++++ .../qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h | 3 + drivers/phy/qualcomm/phy-qcom-qmp-pcs-v5_20.h | 1 + .../phy-qcom-qmp-qserdes-txrx-v5_20.h | 24 +++ 4 files changed, 193 insertions(+) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index d671748bc097..b1e81530d551 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -1270,6 +1270,139 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V5_COM_BG_TIMER, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_BIAS_EN_CLKBUFLR_EN, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_SYS_CLK_CTRL, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_IVCO, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CP_CTRL_MODE0, 0x27), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CP_CTRL_MODE1, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_RCTRL_MODE0, 0x17), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_RCTRL_MODE1, 0x19), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_CCTRL_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_PLL_CCTRL_MODE1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_SYSCLK_EN_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP_EN, 0x46), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP_CFG, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP1_MODE0, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP2_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP1_MODE1, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_LOCK_CMP2_MODE1, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_DEC_START_MODE0, 0x19), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_DEC_START_MODE1, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_INTEGLOOP_GAIN0_MODE0, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_INTEGLOOP_GAIN1_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_INTEGLOOP_GAIN0_MODE1, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_INTEGLOOP_GAIN1_MODE1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_VCO_TUNE_MAP, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_HSCLK_SEL, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_HSCLK_HS_SWITCH_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CORECLK_DIV_MODE0, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CORE_CLK_EN, 0x60), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CMN_MISC1, 0x88), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CMN_CONFIG, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CMN_MODE, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_CMN_MODE_CONTD, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_COM_VCO_DC_LEVEL_CTRL, 0x0f), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_LANE_MODE_1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_LANE_MODE_2, 0xf6), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_LANE_MODE_3, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_VMODE_CTRL1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_PI_QEC_CTRL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_RES_CODE_LANE_OFFSET_TX, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_RES_CODE_LANE_OFFSET_RX, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V5_20_TX_RCV_DETECT_LVL_2, 0x12), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_AUX_DATA_THRESH_BIN_RATE_0_1, 0x3f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_1, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_2, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_PRE_THRESH1, 0x3e), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_PRE_THRESH2, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_POST_THRESH1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_POST_THRESH2, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_MAIN_THRESH1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_TX_ADAPT_MAIN_THRESH2, 0x1d), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_VGA_CAL_CNTRL1, 0x44), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_VGA_CAL_CNTRL2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4a), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x74), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_OFFSET_ADAPTOR_CNTRL2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_SIGDET_ENABLES, 0x1c), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_SIGDET_CNTRL, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_SIGDET_DEGLITCH_CNTRL, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B1, 0xcc), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B2, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B3, 0xcc), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B4, 0x64), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B5, 0x4a), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B6, 0x29), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_PHPRE_CTRL, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DCC_CTRL1, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH1_RATE210, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH1_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH2_RATE210, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH2_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH3_RATE210, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH3_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH4_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH5_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH6_RATE3, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_UCDR_FO_GAIN_RATE2, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_UCDR_FO_GAIN_RATE3, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_UCDR_PI_CONTROLS, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_AUX_DATA_THRESH_BIN_RATE_2_3, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_IDAC_SAOFFSET, 0x10), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_3, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_DAC_ENABLE1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_DAC_ENABLE2, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_VGA_CAL_MAN_VAL, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_GM_CAL, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B0, 0xc5), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B1, 0xac), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B2, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B3, 0xc0), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B4, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B5, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE2_B6, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B0, 0xc5), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B1, 0xee), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B2, 0xbf), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B3, 0xa0), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B4, 0x81), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B5, 0xde), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_RX_MODE_RATE3_B6, 0x7f), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_EN_TIMER, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V5_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_G3S2_PRE_GAIN, 0x2e), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_RX_SIGDET_LVL, 0xaa), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG2, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG4, 0x16), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG5, 0x22), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_misc_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_EQ_CONFIG1, 0x16), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_RX_MARGINING_CONFIG3, 0x28), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_OSC_DTCT_MODE2_CONFIG5, 0x08), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG2, 0x0d), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN, 0x2e), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), + QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), +}; + static const struct qmp_phy_init_tbl sm8450_qmp_gen3_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_COM_SYSCLK_EN_SEL, 0x08), QMP_PHY_INIT_CFG(QSERDES_V5_COM_CLK_SELECT, 0x34), @@ -2448,6 +2581,35 @@ static const struct qmp_phy_cfg sm8350_qmp_gen3x2_pciephy_cfg = { .phy_status = PHYSTATUS, }; +static const struct qmp_phy_cfg sdx65_qmp_pciephy_cfg = { + .lanes = 2, + + .offsets = &qmp_pcie_offsets_v6_20, + + .tbls = { + .serdes = sdx65_qmp_pcie_serdes_tbl, + .serdes_num = ARRAY_SIZE(sdx65_qmp_pcie_serdes_tbl), + .tx = sdx65_qmp_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(sdx65_qmp_pcie_tx_tbl), + .rx = sdx65_qmp_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(sdx65_qmp_pcie_rx_tbl), + .pcs = sdx65_qmp_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_tbl), + .pcs_misc = sdx65_qmp_pcie_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_misc_tbl), + }, + .clk_list = sdm845_pciephy_clk_l, + .num_clks = ARRAY_SIZE(sdm845_pciephy_clk_l), + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = pciephy_v5_regs_layout, + + .pwrdn_ctrl = SW_PWRDN, + .phy_status = PHYSTATUS_4_20, +}; + static const struct qmp_phy_cfg sm8450_qmp_gen3x1_pciephy_cfg = { .lanes = 1, @@ -3241,6 +3403,9 @@ static const struct of_device_id qmp_pcie_of_match_table[] = { }, { .compatible = "qcom,sdx55-qmp-pcie-phy", .data = &sdx55_qmp_pciephy_cfg, + }, { + .compatible = "qcom,sdx65-qmp-gen4x2-pcie-phy", + .data = &sdx65_qmp_pciephy_cfg, }, { .compatible = "qcom,sm8250-qmp-gen3x1-pcie-phy", .data = &sm8250_qmp_gen3x1_pciephy_cfg, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h index 3d9713d348fe..a3a056741fc7 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h @@ -12,8 +12,11 @@ #define QPHY_V5_20_PCS_PCIE_OSC_DTCT_ACTIONS 0x090 #define QPHY_V5_20_PCS_PCIE_EQ_CONFIG1 0x0a0 #define QPHY_V5_20_PCS_PCIE_PRESET_P10_POST 0x0e0 +#define QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG2 0x0fc #define QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5 0x108 #define QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN 0x15c #define QPHY_V5_20_PCS_PCIE_RX_MARGINING_CONFIG3 0x184 +#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2 0xa24 +#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2 0xa28 #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v5_20.h index 9a5a20daf62c..f0754b6f9e3a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v5_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v5_20.h @@ -8,6 +8,7 @@ #define QPHY_V5_20_PCS_G3S2_PRE_GAIN 0x170 #define QPHY_V5_20_PCS_RX_SIGDET_LVL 0x188 +#define QPHY_V5_20_PCS_EQ_CONFIG2 0x1d8 #define QPHY_V5_20_PCS_EQ_CONFIG4 0x1e0 #define QPHY_V5_20_PCS_EQ_CONFIG5 0x1e4 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v5_20.h index 86c01104799e..c7b12c1fb7f5 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v5_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v5_20.h @@ -11,6 +11,10 @@ #define QSERDES_V5_20_TX_RES_CODE_LANE_OFFSET_RX 0x34 #define QSERDES_V5_20_TX_LANE_MODE_1 0x78 #define QSERDES_V5_20_TX_LANE_MODE_2 0x7c +#define QSERDES_V5_20_TX_LANE_MODE_3 0x80 +#define QSERDES_V5_20_TX_RCV_DETECT_LVL_2 0x90 +#define QSERDES_V5_20_TX_VMODE_CTRL1 0xb0 +#define QSERDES_V5_20_TX_PI_QEC_CTRL 0xcc /* Only for QMP V5_20 PHY - RX registers */ #define QSERDES_V5_20_RX_UCDR_FO_GAIN_RATE2 0x008 @@ -19,16 +23,33 @@ #define QSERDES_V5_20_RX_AUX_DATA_THRESH_BIN_RATE_0_1 0x02c #define QSERDES_V5_20_RX_AUX_DATA_THRESH_BIN_RATE_2_3 0x030 #define QSERDES_V5_20_RX_RX_IDAC_SAOFFSET 0x07c +#define QSERDES_V5_20_RX_DFE_1 0x088 +#define QSERDES_V5_20_RX_DFE_2 0x08c #define QSERDES_V5_20_RX_DFE_3 0x090 #define QSERDES_V5_20_RX_DFE_DAC_ENABLE1 0x0b4 +#define QSERDES_V5_20_RX_TX_ADAPT_PRE_THRESH1 0x0bc +#define QSERDES_V5_20_RX_TX_ADAPT_PRE_THRESH2 0x0c0 #define QSERDES_V5_20_RX_TX_ADAPT_POST_THRESH1 0x0c4 #define QSERDES_V5_20_RX_TX_ADAPT_POST_THRESH2 0x0c8 +#define QSERDES_V5_20_RX_TX_ADAPT_MAIN_THRESH1 0x0cc +#define QSERDES_V5_20_RX_TX_ADAPT_MAIN_THRESH2 0x0d0 +#define QSERDES_V5_20_RX_VGA_CAL_CNTRL1 0x0d4 +#define QSERDES_V5_20_RX_VGA_CAL_CNTRL2 0x0d8 #define QSERDES_V5_20_RX_VGA_CAL_MAN_VAL 0x0dc #define QSERDES_V5_20_RX_GM_CAL 0x0ec +#define QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL2 0x100 +#define QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL3 0x104 #define QSERDES_V5_20_RX_RX_EQU_ADAPTOR_CNTRL4 0x108 +#define QSERDES_V5_20_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1 0x118 +#define QSERDES_V5_20_RX_RX_OFFSET_ADAPTOR_CNTRL2 0x11c +#define QSERDES_V5_20_RX_SIGDET_ENABLES 0x120 +#define QSERDES_V5_20_RX_SIGDET_CNTRL 0x124 +#define QSERDES_V5_20_RX_SIGDET_DEGLITCH_CNTRL 0x12c +#define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B0 0x160 #define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B1 0x164 #define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B2 0x168 #define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B3 0x16c +#define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B4 0x170 #define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B5 0x174 #define QSERDES_V5_20_RX_RX_MODE_RATE_0_1_B6 0x178 #define QSERDES_V5_20_RX_RX_MODE_RATE2_B0 0x17c @@ -46,7 +67,10 @@ #define QSERDES_V5_20_RX_RX_MODE_RATE3_B5 0x1ac #define QSERDES_V5_20_RX_RX_MODE_RATE3_B6 0x1b0 #define QSERDES_V5_20_RX_PHPRE_CTRL 0x1b4 +#define QSERDES_V5_20_RX_DFE_DAC_ENABLE2 0x1b8 +#define QSERDES_V5_20_RX_DFE_EN_TIMER 0x1bc #define QSERDES_V5_20_RX_DFE_CTLE_POST_CAL_OFFSET 0x1c0 +#define QSERDES_V5_20_RX_DCC_CTRL1 0x1c4 #define QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH1_RATE210 0x1f4 #define QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH1_RATE3 0x1f8 #define QSERDES_V5_20_RX_RX_MARG_COARSE_THRESH2_RATE210 0x1fc -- GitLab From 13803c86e24f5a409406cd428ed0aa69cfcf61f0 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Tue, 14 Mar 2023 13:55:53 +0000 Subject: [PATCH 1817/5631] dt-bindings: PCI: dwc: Add rk3588 compatible PCIe for RK3588 is the same as RK3568. Signed-off-by: Lucas Tanure Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230314135555.44162-2-lucas.tanure@collabora.com Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml index 2be72ae1169f..24c88942e59e 100644 --- a/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/rockchip-dw-pcie.yaml @@ -21,8 +21,12 @@ allOf: properties: compatible: - items: + oneOf: - const: rockchip,rk3568-pcie + - items: + - enum: + - rockchip,rk3588-pcie + - const: rockchip,rk3568-pcie reg: items: -- GitLab From c3becf9cd857606582eea7a5393dc29fb695f59c Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Tue, 14 Mar 2023 13:55:54 +0000 Subject: [PATCH 1818/5631] dt-bindings: phy: rockchip: Add rk3588 compatible RK3568 Naneng Combo Phy driver can support RK3588 with the additional clocks and initial configuration, so add the compatible line. Signed-off-by: Lucas Tanure Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230314135555.44162-3-lucas.tanure@collabora.com Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml index 8d8698412de0..9ae514fa7533 100644 --- a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml +++ b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml @@ -13,6 +13,7 @@ properties: compatible: enum: - rockchip,rk3568-naneng-combphy + - rockchip,rk3588-naneng-combphy reg: maxItems: 1 -- GitLab From a03c4427725301328ccbe414d0a19ad39e90d008 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Tue, 14 Mar 2023 13:55:55 +0000 Subject: [PATCH 1819/5631] phy: rockchip: Add naneng combo phy support for RK3588 Add support for RK3588 combo phy This is based on prior work from XiaoDong Huang and Peter Geis fixing this issue specifically for Rockchip 356x. Co-developed-by: Andrew Powers-Holmes Signed-off-by: Andrew Powers-Holmes Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20230314135555.44162-4-lucas.tanure@collabora.com Signed-off-by: Vinod Koul --- .../rockchip/phy-rockchip-naneng-combphy.c | 184 ++++++++++++++++++ 1 file changed, 184 insertions(+) diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 7b213825fb5d..7b8b001e4f9e 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -63,6 +63,9 @@ #define PHYREG18 0x44 #define PHYREG18_PLL_LOOP 0x32 +#define PHYREG27 0x6C +#define PHYREG27_RX_TRIM_RK3588 0x4C + #define PHYREG32 0x7C #define PHYREG32_SSC_MASK GENMASK(7, 4) #define PHYREG32_SSC_DIR_SHIFT 4 @@ -114,7 +117,10 @@ struct rockchip_combphy_grfcfg { struct combphy_reg con2_for_sata; struct combphy_reg con3_for_sata; struct combphy_reg pipe_con0_for_sata; + struct combphy_reg pipe_con1_for_sata; struct combphy_reg pipe_xpcs_phy_ready; + struct combphy_reg pipe_pcie1l0_sel; + struct combphy_reg pipe_pcie1l1_sel; }; struct rockchip_combphy_cfg { @@ -559,11 +565,189 @@ static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = { .combphy_cfg = rk3568_combphy_cfg, }; +static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) +{ + const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg; + unsigned long rate; + u32 val; + + switch (priv->type) { + case PHY_TYPE_PCIE: + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l0_sel, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_pcie1l1_sel, true); + break; + case PHY_TYPE_USB3: + /* Set SSC downward spread spectrum */ + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, + PHYREG32_SSC_DOWNWARD << PHYREG32_SSC_DIR_SHIFT, + PHYREG32); + + /* Enable adaptive CTLE for USB3.0 Rx. */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + + /* Set PLL KVCO fine tuning signals. */ + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + PHYREG33_PLL_KVCO_VALUE << PHYREG33_PLL_KVCO_SHIFT, + PHYREG33); + + /* Enable controlling random jitter. */ + writel(PHYREG12_PLL_LPF_ADJ_VALUE, priv->mmio + PHYREG12); + + /* Set PLL input clock divider 1/2. */ + rockchip_combphy_updatel(priv, PHYREG6_PLL_DIV_MASK, + PHYREG6_PLL_DIV_2 << PHYREG6_PLL_DIV_SHIFT, + PHYREG6); + + writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18); + writel(PHYREG11_SU_TRIM_0_7, priv->mmio + PHYREG11); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txcomp_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txelec_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->usb_mode_set, true); + break; + case PHY_TYPE_SATA: + /* Enable adaptive CTLE for SATA Rx. */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + /* + * Set tx_rterm=50ohm and rx_rterm=44ohm for SATA. + * 0: 60ohm, 8: 50ohm 15: 44ohm (by step abort 1ohm) + */ + val = PHYREG7_TX_RTERM_50OHM << PHYREG7_TX_RTERM_SHIFT; + val |= PHYREG7_RX_RTERM_44OHM << PHYREG7_RX_RTERM_SHIFT; + writel(val, priv->mmio + PHYREG7); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con0_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con1_for_sata, true); + break; + case PHY_TYPE_SGMII: + case PHY_TYPE_QSGMII: + default: + dev_err(priv->dev, "incompatible PHY type\n"); + return -EINVAL; + } + + rate = clk_get_rate(priv->refclk); + + switch (rate) { + case REF_CLOCK_24MHz: + if (priv->type == PHY_TYPE_USB3 || priv->type == PHY_TYPE_SATA) { + /* Set ssc_cnt[9:0]=0101111101 & 31.5KHz. */ + val = PHYREG15_SSC_CNT_VALUE << PHYREG15_SSC_CNT_SHIFT; + rockchip_combphy_updatel(priv, PHYREG15_SSC_CNT_MASK, + val, PHYREG15); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + } + break; + + case REF_CLOCK_25MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_25m, true); + break; + case REF_CLOCK_100MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true); + if (priv->type == PHY_TYPE_PCIE) { + /* PLL KVCO fine tuning. */ + val = 4 << PHYREG33_PLL_KVCO_SHIFT; + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Enable controlling random jitter. */ + writel(PHYREG12_PLL_LPF_ADJ_VALUE, priv->mmio + PHYREG12); + + /* Set up rx_trim: PLL LPF C1 85pf R1 1.25kohm */ + writel(PHYREG27_RX_TRIM_RK3588, priv->mmio + PHYREG27); + + /* Set up su_trim: */ + writel(PHYREG11_SU_TRIM_0_7, priv->mmio + PHYREG11); + } else if (priv->type == PHY_TYPE_SATA) { + /* downward spread spectrum +500ppm */ + val = PHYREG32_SSC_DOWNWARD << PHYREG32_SSC_DIR_SHIFT; + val |= PHYREG32_SSC_OFFSET_500PPM << PHYREG32_SSC_OFFSET_SHIFT; + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + } + break; + default: + dev_err(priv->dev, "Unsupported rate: %lu\n", rate); + return -EINVAL; + } + + if (priv->ext_refclk) { + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_ext, true); + if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_100MHz) { + val = PHYREG13_RESISTER_HIGH_Z << PHYREG13_RESISTER_SHIFT; + val |= PHYREG13_CKRCV_AMP0; + rockchip_combphy_updatel(priv, PHYREG13_RESISTER_MASK, val, PHYREG13); + + val = readl(priv->mmio + PHYREG14); + val |= PHYREG14_CKRCV_AMP1; + writel(val, priv->mmio + PHYREG14); + } + } + + if (priv->enable_ssc) { + val = readl(priv->mmio + PHYREG8); + val |= PHYREG8_SSC_EN; + writel(val, priv->mmio + PHYREG8); + } + + return 0; +} + +static const struct rockchip_combphy_grfcfg rk3588_combphy_grfcfgs = { + /* pipe-phy-grf */ + .pcie_mode_set = { 0x0000, 5, 0, 0x00, 0x11 }, + .usb_mode_set = { 0x0000, 5, 0, 0x00, 0x04 }, + .pipe_rxterm_set = { 0x0000, 12, 12, 0x00, 0x01 }, + .pipe_txelec_set = { 0x0004, 1, 1, 0x00, 0x01 }, + .pipe_txcomp_set = { 0x0004, 4, 4, 0x00, 0x01 }, + .pipe_clk_25m = { 0x0004, 14, 13, 0x00, 0x01 }, + .pipe_clk_100m = { 0x0004, 14, 13, 0x00, 0x02 }, + .pipe_rxterm_sel = { 0x0008, 8, 8, 0x00, 0x01 }, + .pipe_txelec_sel = { 0x0008, 12, 12, 0x00, 0x01 }, + .pipe_txcomp_sel = { 0x0008, 15, 15, 0x00, 0x01 }, + .pipe_clk_ext = { 0x000c, 9, 8, 0x02, 0x01 }, + .pipe_phy_status = { 0x0034, 6, 6, 0x01, 0x00 }, + .con0_for_pcie = { 0x0000, 15, 0, 0x00, 0x1000 }, + .con1_for_pcie = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_pcie = { 0x0008, 15, 0, 0x00, 0x0101 }, + .con3_for_pcie = { 0x000c, 15, 0, 0x00, 0x0200 }, + .con0_for_sata = { 0x0000, 15, 0, 0x00, 0x0129 }, + .con1_for_sata = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_sata = { 0x0008, 15, 0, 0x00, 0x80c1 }, + .con3_for_sata = { 0x000c, 15, 0, 0x00, 0x0407 }, + /* pipe-grf */ + .pipe_con0_for_sata = { 0x0000, 11, 5, 0x00, 0x22 }, + .pipe_con1_for_sata = { 0x0000, 2, 0, 0x00, 0x2 }, + .pipe_pcie1l0_sel = { 0x0100, 0, 0, 0x01, 0x0 }, + .pipe_pcie1l1_sel = { 0x0100, 1, 1, 0x01, 0x0 }, +}; + +static const struct rockchip_combphy_cfg rk3588_combphy_cfgs = { + .grfcfg = &rk3588_combphy_grfcfgs, + .combphy_cfg = rk3588_combphy_cfg, +}; + static const struct of_device_id rockchip_combphy_of_match[] = { { .compatible = "rockchip,rk3568-naneng-combphy", .data = &rk3568_combphy_cfgs, }, + { + .compatible = "rockchip,rk3588-naneng-combphy", + .data = &rk3588_combphy_cfgs, + }, { }, }; MODULE_DEVICE_TABLE(of, rockchip_combphy_of_match); -- GitLab From 001c00efdb0441a6133674ea103ae7505400813d Mon Sep 17 00:00:00 2001 From: David Wronek Date: Sun, 12 Mar 2023 02:17:32 +0300 Subject: [PATCH 1820/5631] dt-bindings: phy: Add QMP UFS PHY comptible for SM7150 Document the QMP UFS PHY compatible for SM7150. Signed-off-by: David Wronek Signed-off-by: Danila Tikhonov Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230311231733.141806-2-danila@jiaxyga.com Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index 64ed331880f6..cd0fbbd3593d 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -18,6 +18,7 @@ properties: enum: - qcom,sc8280xp-qmp-ufs-phy - qcom,sm6125-qmp-ufs-phy + - qcom,sm7150-qmp-ufs-phy - qcom,sm8550-qmp-ufs-phy reg: -- GitLab From 868c2a6ceead022aa61b94b7173c177cf0169be2 Mon Sep 17 00:00:00 2001 From: David Wronek Date: Sun, 12 Mar 2023 02:17:33 +0300 Subject: [PATCH 1821/5631] phy: qcom-qmp-ufs: Add SM7150 support Add the tables and constants for init sequences for UFS QMP phy found in SM7150 SoC. Signed-off-by: David Wronek Signed-off-by: Danila Tikhonov Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230311231733.141806-3-danila@jiaxyga.com Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-ufs.c | 61 +++++++++++++++++++++++++ 1 file changed, 61 insertions(+) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index 994ddd5d4a81..d58822049211 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -349,6 +349,36 @@ static const struct qmp_phy_init_tbl sdm845_ufsphy_pcs[] = { QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_MULTI_LANE_CTRL1, 0x02), }; +static const struct qmp_phy_init_tbl sm7150_ufsphy_rx[] = { + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_LVL, 0x24), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_CNTRL, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_SIGDET_DEGLITCH_CNTRL, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_INTERFACE_MODE, 0x40), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_TERM_BW, 0x5b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL3, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL4, 0x1b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SVS_SO_GAIN_HALF, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SVS_SO_GAIN_QUARTER, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SVS_SO_GAIN, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x5b), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_PI_CONTROLS, 0x81), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_COUNT_LOW, 0x80), + QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_MODE_00, 0x59), +}; + +static const struct qmp_phy_init_tbl sm7150_ufsphy_pcs[] = { + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_RX_SIGDET_CTRL2, 0x6f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_TX_LARGE_AMP_DRV_LVL, 0x0f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_TX_SMALL_AMP_DRV_LVL, 0x02), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_RX_SYM_RESYNC_CTRL, 0x03), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_TX_MID_TERM_CTRL1, 0x43), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_RX_SIGDET_CTRL1, 0x0f), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_RX_MIN_HIBERN8_TIME, 0xff), + QMP_PHY_INIT_CFG(QPHY_V3_PCS_UFS_MULTI_LANE_CTRL1, 0x02), +}; + static const struct qmp_phy_init_tbl sm8150_ufsphy_serdes[] = { QMP_PHY_INIT_CFG(QSERDES_V4_COM_SYSCLK_EN_SEL, 0xd9), QMP_PHY_INIT_CFG(QSERDES_V4_COM_HSCLK_SEL, 0x11), @@ -911,6 +941,34 @@ static const struct qmp_phy_cfg sm6115_ufsphy_cfg = { .no_pcs_sw_reset = true, }; +static const struct qmp_phy_cfg sm7150_ufsphy_cfg = { + .lanes = 1, + + .offsets = &qmp_ufs_offsets, + + .tbls = { + .serdes = sdm845_ufsphy_serdes, + .serdes_num = ARRAY_SIZE(sdm845_ufsphy_serdes), + .tx = sdm845_ufsphy_tx, + .tx_num = ARRAY_SIZE(sdm845_ufsphy_tx), + .rx = sm7150_ufsphy_rx, + .rx_num = ARRAY_SIZE(sm7150_ufsphy_rx), + .pcs = sm7150_ufsphy_pcs, + .pcs_num = ARRAY_SIZE(sm7150_ufsphy_pcs), + }, + .tbls_hs_b = { + .serdes = sdm845_ufsphy_hs_b_serdes, + .serdes_num = ARRAY_SIZE(sdm845_ufsphy_hs_b_serdes), + }, + .clk_list = sdm845_ufs_phy_clk_l, + .num_clks = ARRAY_SIZE(sdm845_ufs_phy_clk_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = ufsphy_v3_regs_layout, + + .no_pcs_sw_reset = true, +}; + static const struct qmp_phy_cfg sm8150_ufsphy_cfg = { .lanes = 2, @@ -1560,6 +1618,9 @@ static const struct of_device_id qmp_ufs_of_match_table[] = { }, { .compatible = "qcom,sm6350-qmp-ufs-phy", .data = &sdm845_ufsphy_cfg, + }, { + .compatible = "qcom,sm7150-qmp-ufs-phy", + .data = &sm7150_ufsphy_cfg, }, { .compatible = "qcom,sm8150-qmp-ufs-phy", .data = &sm8150_ufsphy_cfg, -- GitLab From 6f14c02220c791d5c46b0f965b9340c58f3d503d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:13 +0200 Subject: [PATCH 1822/5631] driver core: create class_is_registered() Some classes (i.e. gpio), want to know if they have been registered or not, and poke around in the class's internal structures to try to figure this out. Because this is not really a good idea, provide a function for classes to call to try to figure this out. Note, this is racy as the state of the class could change at any moment in time after the call is made, but as usually a class only wants to know if it has been registered yet or not, it should be fairly safe to use, and is just as safe as the previous "poke at the class internals" check was. Move the gpiolib code to use this function as proof that it works properly. Cc: Bartosz Golaszewski Cc: Sebastian Reichel Cc: Benjamin Tissoires Cc: linux-gpio@vger.kernel.org Reviewed-by: Linus Walleij Reviewed-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 25 +++++++++++++++++++++++++ drivers/gpio/gpiolib-sysfs.c | 4 ++-- include/linux/device/class.h | 1 + 3 files changed, 28 insertions(+), 2 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 68a6f9b56d19..a8a1bf976290 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -634,6 +634,31 @@ void class_compat_remove_link(struct class_compat *cls, struct device *dev, } EXPORT_SYMBOL_GPL(class_compat_remove_link); +/** + * class_is_registered - determine if at this moment in time, a class is + * registered in the driver core or not. + * @class: the class to check + * + * Returns a boolean to state if the class is registered in the driver core + * or not. Note that the value could switch right after this call is made, + * so only use this in places where you "know" it is safe to do so (usually + * to determine if the specific class has been registered yet or not). + * + * Be careful in using this. + */ +bool class_is_registered(const struct class *class) +{ + struct subsys_private *sp = class_to_subsys(class); + bool is_initialized = false; + + if (sp) { + is_initialized = true; + subsys_put(sp); + } + return is_initialized; +} +EXPORT_SYMBOL_GPL(class_is_registered); + int __init classes_init(void) { class_kset = kset_create_and_add("class", NULL, NULL); diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index a895915affa5..1a9b21731cc9 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -554,7 +554,7 @@ int gpiod_export(struct gpio_desc *desc, bool direction_may_change) int offset; /* can't export until sysfs is available ... */ - if (!gpio_class.p) { + if (!class_is_registered(&gpio_class)) { pr_debug("%s: called too early!\n", __func__); return -ENOENT; } @@ -728,7 +728,7 @@ int gpiochip_sysfs_register(struct gpio_device *gdev) * register later, in gpiolib_sysfs_init() ... here we just * verify that _some_ field of gpio_class got initialized. */ - if (!gpio_class.p) + if (!class_is_registered(&gpio_class)) return 0; /* diff --git a/include/linux/device/class.h b/include/linux/device/class.h index b53728ca56fb..9cb5db0588c8 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -84,6 +84,7 @@ extern struct kobject *sysfs_dev_block_kobj; int __must_check class_register(struct class *class); void class_unregister(const struct class *class); +bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); -- GitLab From 2df418cf4b720fe3a0db4b4aab67be43d26af9dd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:14 +0200 Subject: [PATCH 1823/5631] driver core: class: remove subsystem private pointer from struct class Now that the last users of the subsystem private pointer in struct class are gone, the pointer can be removed, as no one is using it. One step closer to allowing struct class to be const and moved into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-3-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 4 ---- include/linux/device/class.h | 2 -- 2 files changed, 6 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index a8a1bf976290..fcfb295363cc 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -97,8 +97,6 @@ static void class_release(struct kobject *kobj) pr_debug("class '%s': release.\n", class->name); - class->p = NULL; - if (class->class_release) class->class_release(class); else @@ -206,7 +204,6 @@ int class_register(struct class *cls) cp->subsys.kobj.kset = class_kset; cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; - cls->p = cp; error = kset_register(&cp->subsys); if (error) @@ -222,7 +219,6 @@ int class_register(struct class *cls) err_out: kfree(cp); - cls->p = NULL; return error; } EXPORT_SYMBOL_GPL(class_register); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9cb5db0588c8..f7aad64e256a 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -71,8 +71,6 @@ struct class { void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid); const struct dev_pm_ops *pm; - - struct subsys_private *p; }; struct class_dev_iter { -- GitLab From d6bdbbdfb0d45a92407b90209e377bf8c0ed49e9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:15 +0200 Subject: [PATCH 1824/5631] driver core: clean up the logic to determine which /sys/dev/ directory to use When a dev_t is set in a struct device, an symlink in /sys/dev/ is created for it either under /sys/dev/block/ or /sys/dev/char/ depending on the device type. The logic to determine this would trigger off of the class of the object, and the kobj_type set in that location. But it turns out that this deep nesting isn't needed at all, as it's either a choice of block or "everything else" which is a char device. So make the logic a lot more simple and obvious, and remove the incorrect comments in the code that tried to document something that was not happening at all (it is impossible to set class->dev_kobj to NULL as the class core prevented that from happening. This removes the only place that class->dev_kobj was being used, so after this, it can be removed entirely. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-4-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 10 ++++++++++ drivers/base/core.c | 22 ++++------------------ drivers/base/devtmpfs.c | 9 --------- 3 files changed, 14 insertions(+), 27 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index 6296164bb7f3..4660e1159ee0 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -209,6 +209,16 @@ int devtmpfs_init(void); static inline int devtmpfs_init(void) { return 0; } #endif +#ifdef CONFIG_BLOCK +extern struct class block_class; +static inline bool is_blockdev(struct device *dev) +{ + return dev->class == &block_class; +} +#else +static inline bool is_blockdev(struct device *dev) { return false; } +#endif + /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); diff --git a/drivers/base/core.c b/drivers/base/core.c index e3bc34fcf779..dbc2ba6dfffc 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3430,27 +3430,13 @@ int dev_set_name(struct device *dev, const char *fmt, ...) } EXPORT_SYMBOL_GPL(dev_set_name); -/** - * device_to_dev_kobj - select a /sys/dev/ directory for the device - * @dev: device - * - * By default we select char/ for new entries. Setting class->dev_obj - * to NULL prevents an entry from being created. class->dev_kobj must - * be set (or cleared) before any devices are registered to the class - * otherwise device_create_sys_dev_entry() and - * device_remove_sys_dev_entry() will disagree about the presence of - * the link. - */ +/* select a /sys/dev/ directory for the device */ static struct kobject *device_to_dev_kobj(struct device *dev) { - struct kobject *kobj; - - if (dev->class) - kobj = dev->class->dev_kobj; + if (is_blockdev(dev)) + return sysfs_dev_block_kobj; else - kobj = sysfs_dev_char_kobj; - - return kobj; + return sysfs_dev_char_kobj; } static int device_create_sys_dev_entry(struct device *dev) diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index ae72d4ba8547..b848764ef018 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -94,15 +94,6 @@ static struct file_system_type dev_fs_type = { .mount = public_dev_mount, }; -#ifdef CONFIG_BLOCK -static inline int is_blockdev(struct device *dev) -{ - return dev->class == &block_class; -} -#else -static inline int is_blockdev(struct device *dev) { return 0; } -#endif - static int devtmpfs_submit_req(struct req *req, const char *tmp) { init_completion(&req->done); -- GitLab From e78195d52981fc634a4e1e66610a316088bd7458 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:16 +0200 Subject: [PATCH 1825/5631] driver core: class: remove dev_kobj from struct class The dev_kobj field in struct class is now only written to, but never read from, so it can be removed as it is useless. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-5-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- block/genhd.c | 1 - drivers/base/class.c | 4 ---- include/linux/device/class.h | 2 -- 3 files changed, 7 deletions(-) diff --git a/block/genhd.c b/block/genhd.c index e1e1230b1b9f..af7208a37c53 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -899,7 +899,6 @@ static int __init genhd_device_init(void) { int error; - block_class.dev_kobj = sysfs_dev_block_kobj; error = class_register(&block_class); if (unlikely(error)) return error; diff --git a/drivers/base/class.c b/drivers/base/class.c index fcfb295363cc..06b96d6faa19 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -197,10 +197,6 @@ int class_register(struct class *cls) return error; } - /* set the default /sys/dev directory for devices of this class */ - if (!cls->dev_kobj) - cls->dev_kobj = sysfs_dev_char_kobj; - cp->subsys.kobj.kset = class_kset; cp->subsys.kobj.ktype = &class_ktype; cp->class = cls; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index f7aad64e256a..e946642c314e 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -27,7 +27,6 @@ struct fwnode_handle; * @name: Name of the class. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. - * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a * few other things that generate uevents to add the environment * variables. @@ -55,7 +54,6 @@ struct class { const struct attribute_group **class_groups; const struct attribute_group **dev_groups; - struct kobject *dev_kobj; int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); -- GitLab From 575ab414c90a317158db48475a88de42f37e0afa Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:17 +0200 Subject: [PATCH 1826/5631] driver core: make sysfs_dev_block_kobj static Nothing outside of drivers/base/core.c uses sysfs_dev_block_kobj, so make it static and document what it is used for so we remember it the next time we touch it 15 years from now. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-6-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 4 +++- include/linux/device/class.h | 2 -- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index dbc2ba6dfffc..cf6f41c2060c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2256,7 +2256,9 @@ int (*platform_notify)(struct device *dev) = NULL; int (*platform_notify_remove)(struct device *dev) = NULL; static struct kobject *dev_kobj; struct kobject *sysfs_dev_char_kobj; -struct kobject *sysfs_dev_block_kobj; + +/* /sys/dev/block */ +static struct kobject *sysfs_dev_block_kobj; static DEFINE_MUTEX(device_hotplug_lock); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index e946642c314e..7e4a1a6329f4 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -76,8 +76,6 @@ struct class_dev_iter { const struct device_type *type; }; -extern struct kobject *sysfs_dev_block_kobj; - int __must_check class_register(struct class *class); void class_unregister(const struct class *class); bool class_is_registered(const struct class *class); -- GitLab From 980c05616e5d554c46176fe08b5601801f2f8192 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 11:33:18 +0200 Subject: [PATCH 1827/5631] driver core: make sysfs_dev_char_kobj static Nothing outside of drivers/base/core.c uses sysfs_dev_char_kobj, so make it static and document what it is used for so we remember it the next time we touch it 15 years from now. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20230331093318.82288-7-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 3 --- drivers/base/core.c | 4 +++- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index 4660e1159ee0..e96f3343fd7c 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -191,9 +191,6 @@ const char *device_get_devnode(const struct device *dev, umode_t *mode, extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); -/* /sys/dev/char directory */ -extern struct kobject *sysfs_dev_char_kobj; - #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) void module_add_driver(struct module *mod, struct device_driver *drv); void module_remove_driver(struct device_driver *drv); diff --git a/drivers/base/core.c b/drivers/base/core.c index cf6f41c2060c..47e16c088e77 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2255,7 +2255,9 @@ static void fw_devlink_link_device(struct device *dev) int (*platform_notify)(struct device *dev) = NULL; int (*platform_notify_remove)(struct device *dev) = NULL; static struct kobject *dev_kobj; -struct kobject *sysfs_dev_char_kobj; + +/* /sys/dev/char */ +static struct kobject *sysfs_dev_char_kobj; /* /sys/dev/block */ static struct kobject *sysfs_dev_block_kobj; -- GitLab From 1086a5310f9c9421398cd12c00f605866aad24a5 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:03 +0800 Subject: [PATCH 1828/5631] dt-bindings: clock: mediatek: Add new MT8188 clock Add the new binding documentation for system clock and functional clock on MediaTek MT8188. Signed-off-by: Garmin.Chang Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230331123621.16167-2-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- .../bindings/clock/mediatek,mt8188-clock.yaml | 71 ++ .../clock/mediatek,mt8188-sys-clock.yaml | 55 ++ .../dt-bindings/clock/mediatek,mt8188-clk.h | 726 ++++++++++++++++++ 3 files changed, 852 insertions(+) create mode 100644 Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml create mode 100644 Documentation/devicetree/bindings/clock/mediatek,mt8188-sys-clock.yaml create mode 100644 include/dt-bindings/clock/mediatek,mt8188-clk.h diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml new file mode 100644 index 000000000000..d7214d97b2ba --- /dev/null +++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/mediatek,mt8188-clock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek Functional Clock Controller for MT8188 + +maintainers: + - Garmin Chang + +description: | + The clock architecture in MediaTek like below + PLLs --> + dividers --> + muxes + --> + clock gate + + The devices provide clock gate control in different IP blocks. + +properties: + compatible: + enum: + - mediatek,mt8188-adsp-audio26m + - mediatek,mt8188-camsys + - mediatek,mt8188-camsys-rawa + - mediatek,mt8188-camsys-rawb + - mediatek,mt8188-camsys-yuva + - mediatek,mt8188-camsys-yuvb + - mediatek,mt8188-ccusys + - mediatek,mt8188-imgsys + - mediatek,mt8188-imgsys-wpe1 + - mediatek,mt8188-imgsys-wpe2 + - mediatek,mt8188-imgsys-wpe3 + - mediatek,mt8188-imgsys1-dip-nr + - mediatek,mt8188-imgsys1-dip-top + - mediatek,mt8188-imp-iic-wrap-c + - mediatek,mt8188-imp-iic-wrap-en + - mediatek,mt8188-imp-iic-wrap-w + - mediatek,mt8188-ipesys + - mediatek,mt8188-mfgcfg + - mediatek,mt8188-vdecsys + - mediatek,mt8188-vdecsys-soc + - mediatek,mt8188-vencsys + - mediatek,mt8188-vppsys0 + - mediatek,mt8188-vppsys1 + - mediatek,mt8188-wpesys + - mediatek,mt8188-wpesys-vpp0 + + reg: + maxItems: 1 + + '#clock-cells': + const: 1 + +required: + - compatible + - reg + - '#clock-cells' + +additionalProperties: false + +examples: + - | + clock-controller@11283000 { + compatible = "mediatek,mt8188-imp-iic-wrap-c"; + reg = <0x11283000 0x1000>; + #clock-cells = <1>; + }; + diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-sys-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-sys-clock.yaml new file mode 100644 index 000000000000..4cf8d3af9803 --- /dev/null +++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-sys-clock.yaml @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/clock/mediatek,mt8188-sys-clock.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek System Clock Controller for MT8188 + +maintainers: + - Garmin Chang + +description: | + The clock architecture in MediaTek like below + PLLs --> + dividers --> + muxes + --> + clock gate + + The apmixedsys provides most of PLLs which generated from SoC 26m. + The topckgen provides dividers and muxes which provide the clock source to other IP blocks. + The infracfg_ao provides clock gate in peripheral and infrastructure IP blocks. + The mcusys provides mux control to select the clock source in AP MCU. + The device nodes also provide the system control capacity for configuration. + +properties: + compatible: + items: + - enum: + - mediatek,mt8188-apmixedsys + - mediatek,mt8188-infracfg-ao + - mediatek,mt8188-pericfg-ao + - mediatek,mt8188-topckgen + - const: syscon + + reg: + maxItems: 1 + + '#clock-cells': + const: 1 + +required: + - compatible + - reg + - '#clock-cells' + +additionalProperties: false + +examples: + - | + clock-controller@10000000 { + compatible = "mediatek,mt8188-topckgen", "syscon"; + reg = <0x10000000 0x1000>; + #clock-cells = <1>; + }; diff --git a/include/dt-bindings/clock/mediatek,mt8188-clk.h b/include/dt-bindings/clock/mediatek,mt8188-clk.h new file mode 100644 index 000000000000..bd5cd100b796 --- /dev/null +++ b/include/dt-bindings/clock/mediatek,mt8188-clk.h @@ -0,0 +1,726 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#ifndef _DT_BINDINGS_CLK_MT8188_H +#define _DT_BINDINGS_CLK_MT8188_H + +/* TOPCKGEN */ +#define CLK_TOP_AXI 0 +#define CLK_TOP_SPM 1 +#define CLK_TOP_SCP 2 +#define CLK_TOP_BUS_AXIMEM 3 +#define CLK_TOP_VPP 4 +#define CLK_TOP_ETHDR 5 +#define CLK_TOP_IPE 6 +#define CLK_TOP_CAM 7 +#define CLK_TOP_CCU 8 +#define CLK_TOP_CCU_AHB 9 +#define CLK_TOP_IMG 10 +#define CLK_TOP_CAMTM 11 +#define CLK_TOP_DSP 12 +#define CLK_TOP_DSP1 13 +#define CLK_TOP_DSP2 14 +#define CLK_TOP_DSP3 15 +#define CLK_TOP_DSP4 16 +#define CLK_TOP_DSP5 17 +#define CLK_TOP_DSP6 18 +#define CLK_TOP_DSP7 19 +#define CLK_TOP_MFG_CORE_TMP 20 +#define CLK_TOP_CAMTG 21 +#define CLK_TOP_CAMTG2 22 +#define CLK_TOP_CAMTG3 23 +#define CLK_TOP_UART 24 +#define CLK_TOP_SPI 25 +#define CLK_TOP_MSDC50_0_HCLK 26 +#define CLK_TOP_MSDC50_0 27 +#define CLK_TOP_MSDC30_1 28 +#define CLK_TOP_MSDC30_2 29 +#define CLK_TOP_INTDIR 30 +#define CLK_TOP_AUD_INTBUS 31 +#define CLK_TOP_AUDIO_H 32 +#define CLK_TOP_PWRAP_ULPOSC 33 +#define CLK_TOP_ATB 34 +#define CLK_TOP_SSPM 35 +#define CLK_TOP_DP 36 +#define CLK_TOP_EDP 37 +#define CLK_TOP_DPI 38 +#define CLK_TOP_DISP_PWM0 39 +#define CLK_TOP_DISP_PWM1 40 +#define CLK_TOP_USB_TOP 41 +#define CLK_TOP_SSUSB_XHCI 42 +#define CLK_TOP_USB_TOP_2P 43 +#define CLK_TOP_SSUSB_XHCI_2P 44 +#define CLK_TOP_USB_TOP_3P 45 +#define CLK_TOP_SSUSB_XHCI_3P 46 +#define CLK_TOP_I2C 47 +#define CLK_TOP_SENINF 48 +#define CLK_TOP_SENINF1 49 +#define CLK_TOP_GCPU 50 +#define CLK_TOP_VENC 51 +#define CLK_TOP_VDEC 52 +#define CLK_TOP_PWM 53 +#define CLK_TOP_MCUPM 54 +#define CLK_TOP_SPMI_P_MST 55 +#define CLK_TOP_SPMI_M_MST 56 +#define CLK_TOP_DVFSRC 57 +#define CLK_TOP_TL 58 +#define CLK_TOP_AES_MSDCFDE 59 +#define CLK_TOP_DSI_OCC 60 +#define CLK_TOP_WPE_VPP 61 +#define CLK_TOP_HDCP 62 +#define CLK_TOP_HDCP_24M 63 +#define CLK_TOP_HDMI_APB 64 +#define CLK_TOP_SNPS_ETH_250M 65 +#define CLK_TOP_SNPS_ETH_62P4M_PTP 66 +#define CLK_TOP_SNPS_ETH_50M_RMII 67 +#define CLK_TOP_ADSP 68 +#define CLK_TOP_AUDIO_LOCAL_BUS 69 +#define CLK_TOP_ASM_H 70 +#define CLK_TOP_ASM_L 71 +#define CLK_TOP_APLL1 72 +#define CLK_TOP_APLL2 73 +#define CLK_TOP_APLL3 74 +#define CLK_TOP_APLL4 75 +#define CLK_TOP_APLL5 76 +#define CLK_TOP_I2SO1 77 +#define CLK_TOP_I2SO2 78 +#define CLK_TOP_I2SI1 79 +#define CLK_TOP_I2SI2 80 +#define CLK_TOP_DPTX 81 +#define CLK_TOP_AUD_IEC 82 +#define CLK_TOP_A1SYS_HP 83 +#define CLK_TOP_A2SYS 84 +#define CLK_TOP_A3SYS 85 +#define CLK_TOP_A4SYS 86 +#define CLK_TOP_ECC 87 +#define CLK_TOP_SPINOR 88 +#define CLK_TOP_ULPOSC 89 +#define CLK_TOP_SRCK 90 +#define CLK_TOP_MFG_CK_FAST_REF 91 +#define CLK_TOP_MAINPLL_D3 92 +#define CLK_TOP_MAINPLL_D4 93 +#define CLK_TOP_MAINPLL_D4_D2 94 +#define CLK_TOP_MAINPLL_D4_D4 95 +#define CLK_TOP_MAINPLL_D4_D8 96 +#define CLK_TOP_MAINPLL_D5 97 +#define CLK_TOP_MAINPLL_D5_D2 98 +#define CLK_TOP_MAINPLL_D5_D4 99 +#define CLK_TOP_MAINPLL_D5_D8 100 +#define CLK_TOP_MAINPLL_D6 101 +#define CLK_TOP_MAINPLL_D6_D2 102 +#define CLK_TOP_MAINPLL_D6_D4 103 +#define CLK_TOP_MAINPLL_D6_D8 104 +#define CLK_TOP_MAINPLL_D7 105 +#define CLK_TOP_MAINPLL_D7_D2 106 +#define CLK_TOP_MAINPLL_D7_D4 107 +#define CLK_TOP_MAINPLL_D7_D8 108 +#define CLK_TOP_MAINPLL_D9 109 +#define CLK_TOP_UNIVPLL_D2 110 +#define CLK_TOP_UNIVPLL_D3 111 +#define CLK_TOP_UNIVPLL_D4 112 +#define CLK_TOP_UNIVPLL_D4_D2 113 +#define CLK_TOP_UNIVPLL_D4_D4 114 +#define CLK_TOP_UNIVPLL_D4_D8 115 +#define CLK_TOP_UNIVPLL_D5 116 +#define CLK_TOP_UNIVPLL_D5_D2 117 +#define CLK_TOP_UNIVPLL_D5_D4 118 +#define CLK_TOP_UNIVPLL_D5_D8 119 +#define CLK_TOP_UNIVPLL_D6 120 +#define CLK_TOP_UNIVPLL_D6_D2 121 +#define CLK_TOP_UNIVPLL_D6_D4 122 +#define CLK_TOP_UNIVPLL_D6_D8 123 +#define CLK_TOP_UNIVPLL_D7 124 +#define CLK_TOP_UNIVPLL_192M 125 +#define CLK_TOP_UNIVPLL_192M_D4 126 +#define CLK_TOP_UNIVPLL_192M_D8 127 +#define CLK_TOP_UNIVPLL_192M_D10 128 +#define CLK_TOP_UNIVPLL_192M_D16 129 +#define CLK_TOP_UNIVPLL_192M_D32 130 +#define CLK_TOP_APLL1_D3 131 +#define CLK_TOP_APLL1_D4 132 +#define CLK_TOP_APLL2_D3 133 +#define CLK_TOP_APLL2_D4 134 +#define CLK_TOP_APLL3_D4 135 +#define CLK_TOP_APLL4_D4 136 +#define CLK_TOP_APLL5_D4 137 +#define CLK_TOP_MMPLL_D4 138 +#define CLK_TOP_MMPLL_D4_D2 139 +#define CLK_TOP_MMPLL_D5 140 +#define CLK_TOP_MMPLL_D5_D2 141 +#define CLK_TOP_MMPLL_D5_D4 142 +#define CLK_TOP_MMPLL_D6 143 +#define CLK_TOP_MMPLL_D6_D2 144 +#define CLK_TOP_MMPLL_D7 145 +#define CLK_TOP_MMPLL_D9 146 +#define CLK_TOP_TVDPLL1 147 +#define CLK_TOP_TVDPLL1_D2 148 +#define CLK_TOP_TVDPLL1_D4 149 +#define CLK_TOP_TVDPLL1_D8 150 +#define CLK_TOP_TVDPLL1_D16 151 +#define CLK_TOP_TVDPLL2 152 +#define CLK_TOP_TVDPLL2_D2 153 +#define CLK_TOP_TVDPLL2_D4 154 +#define CLK_TOP_TVDPLL2_D8 155 +#define CLK_TOP_TVDPLL2_D16 156 +#define CLK_TOP_MSDCPLL_D2 157 +#define CLK_TOP_MSDCPLL_D16 158 +#define CLK_TOP_ETHPLL 159 +#define CLK_TOP_ETHPLL_D2 160 +#define CLK_TOP_ETHPLL_D4 161 +#define CLK_TOP_ETHPLL_D8 162 +#define CLK_TOP_ETHPLL_D10 163 +#define CLK_TOP_ADSPPLL_D2 164 +#define CLK_TOP_ADSPPLL_D4 165 +#define CLK_TOP_ADSPPLL_D8 166 +#define CLK_TOP_ULPOSC1 167 +#define CLK_TOP_ULPOSC1_D2 168 +#define CLK_TOP_ULPOSC1_D4 169 +#define CLK_TOP_ULPOSC1_D8 170 +#define CLK_TOP_ULPOSC1_D7 171 +#define CLK_TOP_ULPOSC1_D10 172 +#define CLK_TOP_ULPOSC1_D16 173 +#define CLK_TOP_MPHONE_SLAVE_BCK 174 +#define CLK_TOP_PAD_FPC 175 +#define CLK_TOP_466M_FMEM 176 +#define CLK_TOP_PEXTP_PIPE 177 +#define CLK_TOP_DSI_PHY 178 +#define CLK_TOP_APLL12_CK_DIV0 179 +#define CLK_TOP_APLL12_CK_DIV1 180 +#define CLK_TOP_APLL12_CK_DIV2 181 +#define CLK_TOP_APLL12_CK_DIV3 182 +#define CLK_TOP_APLL12_CK_DIV4 183 +#define CLK_TOP_APLL12_CK_DIV9 184 +#define CLK_TOP_CFGREG_CLOCK_EN_VPP0 185 +#define CLK_TOP_CFGREG_CLOCK_EN_VPP1 186 +#define CLK_TOP_CFGREG_CLOCK_EN_VDO0 187 +#define CLK_TOP_CFGREG_CLOCK_EN_VDO1 188 +#define CLK_TOP_CFGREG_CLOCK_ISP_AXI_GALS 189 +#define CLK_TOP_CFGREG_F26M_VPP0 190 +#define CLK_TOP_CFGREG_F26M_VPP1 191 +#define CLK_TOP_CFGREG_F26M_VDO0 192 +#define CLK_TOP_CFGREG_F26M_VDO1 193 +#define CLK_TOP_CFGREG_AUD_F26M_AUD 194 +#define CLK_TOP_CFGREG_UNIPLL_SES 195 +#define CLK_TOP_CFGREG_F_PCIE_PHY_REF 196 +#define CLK_TOP_SSUSB_TOP_REF 197 +#define CLK_TOP_SSUSB_PHY_REF 198 +#define CLK_TOP_SSUSB_TOP_P1_REF 199 +#define CLK_TOP_SSUSB_PHY_P1_REF 200 +#define CLK_TOP_SSUSB_TOP_P2_REF 201 +#define CLK_TOP_SSUSB_PHY_P2_REF 202 +#define CLK_TOP_SSUSB_TOP_P3_REF 203 +#define CLK_TOP_SSUSB_PHY_P3_REF 204 +#define CLK_TOP_NR_CLK 205 + +/* INFRACFG_AO */ +#define CLK_INFRA_AO_PMIC_TMR 0 +#define CLK_INFRA_AO_PMIC_AP 1 +#define CLK_INFRA_AO_PMIC_MD 2 +#define CLK_INFRA_AO_PMIC_CONN 3 +#define CLK_INFRA_AO_SEJ 4 +#define CLK_INFRA_AO_APXGPT 5 +#define CLK_INFRA_AO_GCE 6 +#define CLK_INFRA_AO_GCE2 7 +#define CLK_INFRA_AO_THERM 8 +#define CLK_INFRA_AO_PWM_HCLK 9 +#define CLK_INFRA_AO_PWM1 10 +#define CLK_INFRA_AO_PWM2 11 +#define CLK_INFRA_AO_PWM3 12 +#define CLK_INFRA_AO_PWM4 13 +#define CLK_INFRA_AO_PWM 14 +#define CLK_INFRA_AO_UART0 15 +#define CLK_INFRA_AO_UART1 16 +#define CLK_INFRA_AO_UART2 17 +#define CLK_INFRA_AO_UART3 18 +#define CLK_INFRA_AO_UART4 19 +#define CLK_INFRA_AO_GCE_26M 20 +#define CLK_INFRA_AO_CQ_DMA_FPC 21 +#define CLK_INFRA_AO_UART5 22 +#define CLK_INFRA_AO_HDMI_26M 23 +#define CLK_INFRA_AO_SPI0 24 +#define CLK_INFRA_AO_MSDC0 25 +#define CLK_INFRA_AO_MSDC1 26 +#define CLK_INFRA_AO_MSDC2 27 +#define CLK_INFRA_AO_MSDC0_SRC 28 +#define CLK_INFRA_AO_DVFSRC 29 +#define CLK_INFRA_AO_TRNG 30 +#define CLK_INFRA_AO_AUXADC 31 +#define CLK_INFRA_AO_CPUM 32 +#define CLK_INFRA_AO_HDMI_32K 33 +#define CLK_INFRA_AO_CEC_66M_HCLK 34 +#define CLK_INFRA_AO_PCIE_TL_26M 35 +#define CLK_INFRA_AO_MSDC1_SRC 36 +#define CLK_INFRA_AO_CEC_66M_BCLK 37 +#define CLK_INFRA_AO_PCIE_TL_96M 38 +#define CLK_INFRA_AO_DEVICE_APC 39 +#define CLK_INFRA_AO_ECC_66M_HCLK 40 +#define CLK_INFRA_AO_DEBUGSYS 41 +#define CLK_INFRA_AO_AUDIO 42 +#define CLK_INFRA_AO_PCIE_TL_32K 43 +#define CLK_INFRA_AO_DBG_TRACE 44 +#define CLK_INFRA_AO_DRAMC_F26M 45 +#define CLK_INFRA_AO_IRTX 46 +#define CLK_INFRA_AO_DISP_PWM 47 +#define CLK_INFRA_AO_CLDMA_BCLK 48 +#define CLK_INFRA_AO_AUDIO_26M_BCLK 49 +#define CLK_INFRA_AO_SPI1 50 +#define CLK_INFRA_AO_SPI2 51 +#define CLK_INFRA_AO_SPI3 52 +#define CLK_INFRA_AO_FSSPM 53 +#define CLK_INFRA_AO_SSPM_BUS_HCLK 54 +#define CLK_INFRA_AO_APDMA_BCLK 55 +#define CLK_INFRA_AO_SPI4 56 +#define CLK_INFRA_AO_SPI5 57 +#define CLK_INFRA_AO_CQ_DMA 58 +#define CLK_INFRA_AO_MSDC0_SELF 59 +#define CLK_INFRA_AO_MSDC1_SELF 60 +#define CLK_INFRA_AO_MSDC2_SELF 61 +#define CLK_INFRA_AO_I2S_DMA 62 +#define CLK_INFRA_AO_AP_MSDC0 63 +#define CLK_INFRA_AO_MD_MSDC0 64 +#define CLK_INFRA_AO_MSDC30_2 65 +#define CLK_INFRA_AO_GCPU 66 +#define CLK_INFRA_AO_PCIE_PERI_26M 67 +#define CLK_INFRA_AO_GCPU_66M_BCLK 68 +#define CLK_INFRA_AO_GCPU_133M_BCLK 69 +#define CLK_INFRA_AO_DISP_PWM1 70 +#define CLK_INFRA_AO_FBIST2FPC 71 +#define CLK_INFRA_AO_DEVICE_APC_SYNC 72 +#define CLK_INFRA_AO_PCIE_P1_PERI_26M 73 +#define CLK_INFRA_AO_133M_MCLK_CK 74 +#define CLK_INFRA_AO_66M_MCLK_CK 75 +#define CLK_INFRA_AO_PCIE_PL_P_250M_P0 76 +#define CLK_INFRA_AO_RG_AES_MSDCFDE_CK_0P 77 +#define CLK_INFRA_AO_NR_CLK 78 + +/* APMIXEDSYS */ +#define CLK_APMIXED_ETHPLL 0 +#define CLK_APMIXED_MSDCPLL 1 +#define CLK_APMIXED_TVDPLL1 2 +#define CLK_APMIXED_TVDPLL2 3 +#define CLK_APMIXED_MMPLL 4 +#define CLK_APMIXED_MAINPLL 5 +#define CLK_APMIXED_IMGPLL 6 +#define CLK_APMIXED_UNIVPLL 7 +#define CLK_APMIXED_ADSPPLL 8 +#define CLK_APMIXED_APLL1 9 +#define CLK_APMIXED_APLL2 10 +#define CLK_APMIXED_APLL3 11 +#define CLK_APMIXED_APLL4 12 +#define CLK_APMIXED_APLL5 13 +#define CLK_APMIXED_MFGPLL 14 +#define CLK_APMIXED_PLL_SSUSB26M_EN 15 +#define CLK_APMIXED_NR_CLK 16 + +/* AUDIODSP */ +#define CLK_AUDIODSP_AUDIO26M 0 +#define CLK_AUDIODSP_NR_CLK 1 + +/* PERICFG_AO */ +#define CLK_PERI_AO_ETHERNET 0 +#define CLK_PERI_AO_ETHERNET_BUS 1 +#define CLK_PERI_AO_FLASHIF_BUS 2 +#define CLK_PERI_AO_FLASHIF_26M 3 +#define CLK_PERI_AO_FLASHIFLASHCK 4 +#define CLK_PERI_AO_SSUSB_2P_BUS 5 +#define CLK_PERI_AO_SSUSB_2P_XHCI 6 +#define CLK_PERI_AO_SSUSB_3P_BUS 7 +#define CLK_PERI_AO_SSUSB_3P_XHCI 8 +#define CLK_PERI_AO_SSUSB_BUS 9 +#define CLK_PERI_AO_SSUSB_XHCI 10 +#define CLK_PERI_AO_ETHERNET_MAC 11 +#define CLK_PERI_AO_PCIE_P0_FMEM 12 +#define CLK_PERI_AO_NR_CLK 13 + +/* IMP_IIC_WRAP_C */ +#define CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C0 0 +#define CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C2 1 +#define CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C3 2 +#define CLK_IMP_IIC_WRAP_C_NR_CLK 3 + +/* IMP_IIC_WRAP_W */ +#define CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C1 0 +#define CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C4 1 +#define CLK_IMP_IIC_WRAP_W_NR_CLK 2 + +/* IMP_IIC_WRAP_EN */ +#define CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C5 0 +#define CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C6 1 +#define CLK_IMP_IIC_WRAP_EN_NR_CLK 2 + +/* MFGCFG */ +#define CLK_MFGCFG_BG3D 0 +#define CLK_MFGCFG_NR_CLK 1 + +/* VPPSYS0 */ +#define CLK_VPP0_MDP_FG 0 +#define CLK_VPP0_STITCH 1 +#define CLK_VPP0_PADDING 2 +#define CLK_VPP0_MDP_TCC 3 +#define CLK_VPP0_WARP0_ASYNC_TX 4 +#define CLK_VPP0_WARP1_ASYNC_TX 5 +#define CLK_VPP0_MUTEX 6 +#define CLK_VPP02VPP1_RELAY 7 +#define CLK_VPP0_VPP12VPP0_ASYNC 8 +#define CLK_VPP0_MMSYSRAM_TOP 9 +#define CLK_VPP0_MDP_AAL 10 +#define CLK_VPP0_MDP_RSZ 11 +#define CLK_VPP0_SMI_COMMON_MMSRAM 12 +#define CLK_VPP0_GALS_VDO0_LARB0_MMSRAM 13 +#define CLK_VPP0_GALS_VDO0_LARB1_MMSRAM 14 +#define CLK_VPP0_GALS_VENCSYS_MMSRAM 15 +#define CLK_VPP0_GALS_VENCSYS_CORE1_MMSRAM 16 +#define CLK_VPP0_GALS_INFRA_MMSRAM 17 +#define CLK_VPP0_GALS_CAMSYS_MMSRAM 18 +#define CLK_VPP0_GALS_VPP1_LARB5_MMSRAM 19 +#define CLK_VPP0_GALS_VPP1_LARB6_MMSRAM 20 +#define CLK_VPP0_SMI_REORDER_MMSRAM 21 +#define CLK_VPP0_SMI_IOMMU 22 +#define CLK_VPP0_GALS_IMGSYS_CAMSYS 23 +#define CLK_VPP0_MDP_RDMA 24 +#define CLK_VPP0_MDP_WROT 25 +#define CLK_VPP0_GALS_EMI0_EMI1 26 +#define CLK_VPP0_SMI_SUB_COMMON_REORDER 27 +#define CLK_VPP0_SMI_RSI 28 +#define CLK_VPP0_SMI_COMMON_LARB4 29 +#define CLK_VPP0_GALS_VDEC_VDEC_CORE1 30 +#define CLK_VPP0_GALS_VPP1_WPESYS 31 +#define CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1 32 +#define CLK_VPP0_FAKE_ENG 33 +#define CLK_VPP0_MDP_HDR 34 +#define CLK_VPP0_MDP_TDSHP 35 +#define CLK_VPP0_MDP_COLOR 36 +#define CLK_VPP0_MDP_OVL 37 +#define CLK_VPP0_DSIP_RDMA 38 +#define CLK_VPP0_DISP_WDMA 39 +#define CLK_VPP0_MDP_HMS 40 +#define CLK_VPP0_WARP0_RELAY 41 +#define CLK_VPP0_WARP0_ASYNC 42 +#define CLK_VPP0_WARP1_RELAY 43 +#define CLK_VPP0_WARP1_ASYNC 44 +#define CLK_VPP0_NR_CLK 45 + +/* WPESYS */ +#define CLK_WPE_TOP_WPE_VPP0 0 +#define CLK_WPE_TOP_SMI_LARB7 1 +#define CLK_WPE_TOP_WPESYS_EVENT_TX 2 +#define CLK_WPE_TOP_SMI_LARB7_PCLK_EN 3 +#define CLK_WPE_TOP_NR_CLK 4 + +/* WPESYS_VPP0 */ +#define CLK_WPE_VPP0_VECI 0 +#define CLK_WPE_VPP0_VEC2I 1 +#define CLK_WPE_VPP0_VEC3I 2 +#define CLK_WPE_VPP0_WPEO 3 +#define CLK_WPE_VPP0_MSKO 4 +#define CLK_WPE_VPP0_VGEN 5 +#define CLK_WPE_VPP0_EXT 6 +#define CLK_WPE_VPP0_VFC 7 +#define CLK_WPE_VPP0_CACH0_TOP 8 +#define CLK_WPE_VPP0_CACH0_DMA 9 +#define CLK_WPE_VPP0_CACH1_TOP 10 +#define CLK_WPE_VPP0_CACH1_DMA 11 +#define CLK_WPE_VPP0_CACH2_TOP 12 +#define CLK_WPE_VPP0_CACH2_DMA 13 +#define CLK_WPE_VPP0_CACH3_TOP 14 +#define CLK_WPE_VPP0_CACH3_DMA 15 +#define CLK_WPE_VPP0_PSP 16 +#define CLK_WPE_VPP0_PSP2 17 +#define CLK_WPE_VPP0_SYNC 18 +#define CLK_WPE_VPP0_C24 19 +#define CLK_WPE_VPP0_MDP_CROP 20 +#define CLK_WPE_VPP0_ISP_CROP 21 +#define CLK_WPE_VPP0_TOP 22 +#define CLK_WPE_VPP0_NR_CLK 23 + +/* VPPSYS1 */ +#define CLK_VPP1_SVPP1_MDP_OVL 0 +#define CLK_VPP1_SVPP1_MDP_TCC 1 +#define CLK_VPP1_SVPP1_MDP_WROT 2 +#define CLK_VPP1_SVPP1_VPP_PAD 3 +#define CLK_VPP1_SVPP2_MDP_WROT 4 +#define CLK_VPP1_SVPP2_VPP_PAD 5 +#define CLK_VPP1_SVPP3_MDP_WROT 6 +#define CLK_VPP1_SVPP3_VPP_PAD 7 +#define CLK_VPP1_SVPP1_MDP_RDMA 8 +#define CLK_VPP1_SVPP1_MDP_FG 9 +#define CLK_VPP1_SVPP2_MDP_RDMA 10 +#define CLK_VPP1_SVPP2_MDP_FG 11 +#define CLK_VPP1_SVPP3_MDP_RDMA 12 +#define CLK_VPP1_SVPP3_MDP_FG 13 +#define CLK_VPP1_VPP_SPLIT 14 +#define CLK_VPP1_SVPP2_VDO0_DL_RELAY 15 +#define CLK_VPP1_SVPP1_MDP_RSZ 16 +#define CLK_VPP1_SVPP1_MDP_TDSHP 17 +#define CLK_VPP1_SVPP1_MDP_COLOR 18 +#define CLK_VPP1_SVPP3_VDO1_DL_RELAY 19 +#define CLK_VPP1_SVPP2_MDP_RSZ 20 +#define CLK_VPP1_SVPP2_VPP_MERGE 21 +#define CLK_VPP1_SVPP2_MDP_TDSHP 22 +#define CLK_VPP1_SVPP2_MDP_COLOR 23 +#define CLK_VPP1_SVPP3_MDP_RSZ 24 +#define CLK_VPP1_SVPP3_VPP_MERGE 25 +#define CLK_VPP1_SVPP3_MDP_TDSHP 26 +#define CLK_VPP1_SVPP3_MDP_COLOR 27 +#define CLK_VPP1_GALS5 28 +#define CLK_VPP1_GALS6 29 +#define CLK_VPP1_LARB5 30 +#define CLK_VPP1_LARB6 31 +#define CLK_VPP1_SVPP1_MDP_HDR 32 +#define CLK_VPP1_SVPP1_MDP_AAL 33 +#define CLK_VPP1_SVPP2_MDP_HDR 34 +#define CLK_VPP1_SVPP2_MDP_AAL 35 +#define CLK_VPP1_SVPP3_MDP_HDR 36 +#define CLK_VPP1_SVPP3_MDP_AAL 37 +#define CLK_VPP1_DISP_MUTEX 38 +#define CLK_VPP1_SVPP2_VDO1_DL_RELAY 39 +#define CLK_VPP1_SVPP3_VDO0_DL_RELAY 40 +#define CLK_VPP1_VPP0_DL_ASYNC 41 +#define CLK_VPP1_VPP0_DL1_RELAY 42 +#define CLK_VPP1_LARB5_FAKE_ENG 43 +#define CLK_VPP1_LARB6_FAKE_ENG 44 +#define CLK_VPP1_HDMI_META 45 +#define CLK_VPP1_VPP_SPLIT_HDMI 46 +#define CLK_VPP1_DGI_IN 47 +#define CLK_VPP1_DGI_OUT 48 +#define CLK_VPP1_VPP_SPLIT_DGI 49 +#define CLK_VPP1_DL_CON_OCC 50 +#define CLK_VPP1_VPP_SPLIT_26M 51 +#define CLK_VPP1_NR_CLK 52 + +/* IMGSYS */ +#define CLK_IMGSYS_MAIN_LARB9 0 +#define CLK_IMGSYS_MAIN_TRAW0 1 +#define CLK_IMGSYS_MAIN_TRAW1 2 +#define CLK_IMGSYS_MAIN_VCORE_GALS 3 +#define CLK_IMGSYS_MAIN_DIP0 4 +#define CLK_IMGSYS_MAIN_WPE0 5 +#define CLK_IMGSYS_MAIN_IPE 6 +#define CLK_IMGSYS_MAIN_WPE1 7 +#define CLK_IMGSYS_MAIN_WPE2 8 +#define CLK_IMGSYS_MAIN_GALS 9 +#define CLK_IMGSYS_MAIN_NR_CLK 10 + +/* IMGSYS1_DIP_TOP */ +#define CLK_IMGSYS1_DIP_TOP_LARB10 0 +#define CLK_IMGSYS1_DIP_TOP_DIP_TOP 1 +#define CLK_IMGSYS1_DIP_TOP_NR_CLK 2 + +/* IMGSYS1_DIP_NR */ +#define CLK_IMGSYS1_DIP_NR_LARB15 0 +#define CLK_IMGSYS1_DIP_NR_DIP_NR 1 +#define CLK_IMGSYS1_DIP_NR_NR_CLK 2 + +/* IMGSYS_WPE1 */ +#define CLK_IMGSYS_WPE1_LARB11 0 +#define CLK_IMGSYS_WPE1 1 +#define CLK_IMGSYS_WPE1_NR_CLK 2 + +/* IPESYS */ +#define CLK_IPE_DPE 0 +#define CLK_IPE_FDVT 1 +#define CLK_IPE_ME 2 +#define CLK_IPESYS_TOP 3 +#define CLK_IPE_SMI_LARB12 4 +#define CLK_IPE_NR_CLK 5 + +/* IMGSYS_WPE2 */ +#define CLK_IMGSYS_WPE2_LARB11 0 +#define CLK_IMGSYS_WPE2 1 +#define CLK_IMGSYS_WPE2_NR_CLK 2 + +/* IMGSYS_WPE3 */ +#define CLK_IMGSYS_WPE3_LARB11 0 +#define CLK_IMGSYS_WPE3 1 +#define CLK_IMGSYS_WPE3_NR_CLK 2 + +/* CAMSYS */ +#define CLK_CAM_MAIN_LARB13 0 +#define CLK_CAM_MAIN_LARB14 1 +#define CLK_CAM_MAIN_CAM 2 +#define CLK_CAM_MAIN_CAM_SUBA 3 +#define CLK_CAM_MAIN_CAM_SUBB 4 +#define CLK_CAM_MAIN_CAMTG 5 +#define CLK_CAM_MAIN_SENINF 6 +#define CLK_CAM_MAIN_GCAMSVA 7 +#define CLK_CAM_MAIN_GCAMSVB 8 +#define CLK_CAM_MAIN_GCAMSVC 9 +#define CLK_CAM_MAIN_GCAMSVD 10 +#define CLK_CAM_MAIN_GCAMSVE 11 +#define CLK_CAM_MAIN_GCAMSVF 12 +#define CLK_CAM_MAIN_GCAMSVG 13 +#define CLK_CAM_MAIN_GCAMSVH 14 +#define CLK_CAM_MAIN_GCAMSVI 15 +#define CLK_CAM_MAIN_GCAMSVJ 16 +#define CLK_CAM_MAIN_CAMSV_TOP 17 +#define CLK_CAM_MAIN_CAMSV_CQ_A 18 +#define CLK_CAM_MAIN_CAMSV_CQ_B 19 +#define CLK_CAM_MAIN_CAMSV_CQ_C 20 +#define CLK_CAM_MAIN_FAKE_ENG 21 +#define CLK_CAM_MAIN_CAM2MM0_GALS 22 +#define CLK_CAM_MAIN_CAM2MM1_GALS 23 +#define CLK_CAM_MAIN_CAM2SYS_GALS 24 +#define CLK_CAM_MAIN_NR_CLK 25 + +/* CAMSYS_RAWA */ +#define CLK_CAM_RAWA_LARBX 0 +#define CLK_CAM_RAWA_CAM 1 +#define CLK_CAM_RAWA_CAMTG 2 +#define CLK_CAM_RAWA_NR_CLK 3 + +/* CAMSYS_YUVA */ +#define CLK_CAM_YUVA_LARBX 0 +#define CLK_CAM_YUVA_CAM 1 +#define CLK_CAM_YUVA_CAMTG 2 +#define CLK_CAM_YUVA_NR_CLK 3 + +/* CAMSYS_RAWB */ +#define CLK_CAM_RAWB_LARBX 0 +#define CLK_CAM_RAWB_CAM 1 +#define CLK_CAM_RAWB_CAMTG 2 +#define CLK_CAM_RAWB_NR_CLK 3 + +/* CAMSYS_YUVB */ +#define CLK_CAM_YUVB_LARBX 0 +#define CLK_CAM_YUVB_CAM 1 +#define CLK_CAM_YUVB_CAMTG 2 +#define CLK_CAM_YUVB_NR_CLK 3 + +/* CCUSYS */ +#define CLK_CCU_LARB27 0 +#define CLK_CCU_AHB 1 +#define CLK_CCU_CCU0 2 +#define CLK_CCU_NR_CLK 3 + +/* VDECSYS_SOC */ +#define CLK_VDEC1_SOC_LARB1 0 +#define CLK_VDEC1_SOC_LAT 1 +#define CLK_VDEC1_SOC_LAT_ACTIVE 2 +#define CLK_VDEC1_SOC_LAT_ENG 3 +#define CLK_VDEC1_SOC_VDEC 4 +#define CLK_VDEC1_SOC_VDEC_ACTIVE 5 +#define CLK_VDEC1_SOC_VDEC_ENG 6 +#define CLK_VDEC1_NR_CLK 7 + +/* VDECSYS */ +#define CLK_VDEC2_LARB1 0 +#define CLK_VDEC2_LAT 1 +#define CLK_VDEC2_VDEC 2 +#define CLK_VDEC2_VDEC_ACTIVE 3 +#define CLK_VDEC2_VDEC_ENG 4 +#define CLK_VDEC2_NR_CLK 5 + +/* VENCSYS */ +#define CLK_VENC1_LARB 0 +#define CLK_VENC1_VENC 1 +#define CLK_VENC1_JPGENC 2 +#define CLK_VENC1_JPGDEC 3 +#define CLK_VENC1_JPGDEC_C1 4 +#define CLK_VENC1_GALS 5 +#define CLK_VENC1_GALS_SRAM 6 +#define CLK_VENC1_NR_CLK 7 + +/* VDOSYS0 */ +#define CLK_VDO0_DISP_OVL0 0 +#define CLK_VDO0_FAKE_ENG0 1 +#define CLK_VDO0_DISP_CCORR0 2 +#define CLK_VDO0_DISP_MUTEX0 3 +#define CLK_VDO0_DISP_GAMMA0 4 +#define CLK_VDO0_DISP_DITHER0 5 +#define CLK_VDO0_DISP_WDMA0 6 +#define CLK_VDO0_DISP_RDMA0 7 +#define CLK_VDO0_DSI0 8 +#define CLK_VDO0_DSI1 9 +#define CLK_VDO0_DSC_WRAP0 10 +#define CLK_VDO0_VPP_MERGE0 11 +#define CLK_VDO0_DP_INTF0 12 +#define CLK_VDO0_DISP_AAL0 13 +#define CLK_VDO0_INLINEROT0 14 +#define CLK_VDO0_APB_BUS 15 +#define CLK_VDO0_DISP_COLOR0 16 +#define CLK_VDO0_MDP_WROT0 17 +#define CLK_VDO0_DISP_RSZ0 18 +#define CLK_VDO0_DISP_POSTMASK0 19 +#define CLK_VDO0_FAKE_ENG1 20 +#define CLK_VDO0_DL_ASYNC2 21 +#define CLK_VDO0_DL_RELAY3 22 +#define CLK_VDO0_DL_RELAY4 23 +#define CLK_VDO0_SMI_GALS 24 +#define CLK_VDO0_SMI_COMMON 25 +#define CLK_VDO0_SMI_EMI 26 +#define CLK_VDO0_SMI_IOMMU 27 +#define CLK_VDO0_SMI_LARB 28 +#define CLK_VDO0_SMI_RSI 29 +#define CLK_VDO0_DSI0_DSI 30 +#define CLK_VDO0_DSI1_DSI 31 +#define CLK_VDO0_DP_INTF0_DP_INTF 32 +#define CLK_VDO0_NR_CLK 33 + +/* VDOSYS1 */ +#define CLK_VDO1_SMI_LARB2 0 +#define CLK_VDO1_SMI_LARB3 1 +#define CLK_VDO1_GALS 2 +#define CLK_VDO1_FAKE_ENG0 3 +#define CLK_VDO1_FAKE_ENG1 4 +#define CLK_VDO1_MDP_RDMA0 5 +#define CLK_VDO1_MDP_RDMA1 6 +#define CLK_VDO1_MDP_RDMA2 7 +#define CLK_VDO1_MDP_RDMA3 8 +#define CLK_VDO1_VPP_MERGE0 9 +#define CLK_VDO1_VPP_MERGE1 10 +#define CLK_VDO1_VPP_MERGE2 11 +#define CLK_VDO1_VPP_MERGE3 12 +#define CLK_VDO1_VPP_MERGE4 13 +#define CLK_VDO1_VPP2_TO_VDO1_DL_ASYNC 14 +#define CLK_VDO1_VPP3_TO_VDO1_DL_ASYNC 15 +#define CLK_VDO1_DISP_MUTEX 16 +#define CLK_VDO1_MDP_RDMA4 17 +#define CLK_VDO1_MDP_RDMA5 18 +#define CLK_VDO1_MDP_RDMA6 19 +#define CLK_VDO1_MDP_RDMA7 20 +#define CLK_VDO1_DP_INTF0_MMCK 21 +#define CLK_VDO1_DPI0_MM 22 +#define CLK_VDO1_DPI1_MM 23 +#define CLK_VDO1_MERGE0_DL_ASYNC 24 +#define CLK_VDO1_MERGE1_DL_ASYNC 25 +#define CLK_VDO1_MERGE2_DL_ASYNC 26 +#define CLK_VDO1_MERGE3_DL_ASYNC 27 +#define CLK_VDO1_MERGE4_DL_ASYNC 28 +#define CLK_VDO1_DSC_VDO1_DL_ASYNC 29 +#define CLK_VDO1_MERGE_VDO1_DL_ASYNC 30 +#define CLK_VDO1_PADDING0 31 +#define CLK_VDO1_PADDING1 32 +#define CLK_VDO1_PADDING2 33 +#define CLK_VDO1_PADDING3 34 +#define CLK_VDO1_PADDING4 35 +#define CLK_VDO1_PADDING5 36 +#define CLK_VDO1_PADDING6 37 +#define CLK_VDO1_PADDING7 38 +#define CLK_VDO1_DISP_RSZ0 39 +#define CLK_VDO1_DISP_RSZ1 40 +#define CLK_VDO1_DISP_RSZ2 41 +#define CLK_VDO1_DISP_RSZ3 42 +#define CLK_VDO1_HDR_VDO_FE0 43 +#define CLK_VDO1_HDR_GFX_FE0 44 +#define CLK_VDO1_HDR_VDO_BE 45 +#define CLK_VDO1_HDR_VDO_FE1 46 +#define CLK_VDO1_HDR_GFX_FE1 47 +#define CLK_VDO1_DISP_MIXER 48 +#define CLK_VDO1_HDR_VDO_FE0_DL_ASYNC 49 +#define CLK_VDO1_HDR_VDO_FE1_DL_ASYNC 50 +#define CLK_VDO1_HDR_GFX_FE0_DL_ASYNC 51 +#define CLK_VDO1_HDR_GFX_FE1_DL_ASYNC 52 +#define CLK_VDO1_HDR_VDO_BE_DL_ASYNC 53 +#define CLK_VDO1_DPI0 54 +#define CLK_VDO1_DISP_MONITOR_DPI0 55 +#define CLK_VDO1_DPI1 56 +#define CLK_VDO1_DISP_MONITOR_DPI1 57 +#define CLK_VDO1_DPINTF 58 +#define CLK_VDO1_DISP_MONITOR_DPINTF 59 +#define CLK_VDO1_26M_SLOW 60 +#define CLK_VDO1_NR_CLK 61 + +#endif /* _DT_BINDINGS_CLK_MT8188_H */ -- GitLab From 28b2bc99fa76f9a8eaf22ee40fdc2a1e65fff81c Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:04 +0800 Subject: [PATCH 1829/5631] clk: mediatek: Add MT8188 apmixedsys clock support Add MT8188 apmixedsys clock controller which provides Plls generated from SoC 26m and ssusb clock gate control. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-3-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 9 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-apmixedsys.c | 157 +++++++++++++++++++ 3 files changed, 167 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-apmixedsys.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 61e3266d2346..681d392620c5 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -683,6 +683,15 @@ config COMMON_CLK_MT8186_VENCSYS help This driver supports MediaTek MT8186 vencsys clocks. +config COMMON_CLK_MT8188 + tristate "Clock driver for MediaTek MT8188" + depends on ARM64 || COMPILE_TEST + select COMMON_CLK_MEDIATEK + select COMMON_CLK_MEDIATEK_FHCTL + default ARCH_MEDIATEK + help + This driver supports MediaTek MT8188 clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index bcd3b8c465aa..41b1f5f2d5c3 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_MMSYS) += clk-mt8186-mm.o obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o +obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-apmixedsys.c b/drivers/clk/mediatek/clk-mt8188-apmixedsys.c new file mode 100644 index 000000000000..9d21da2d9aa7 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-apmixedsys.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" +#include "clk-pll.h" + +static const struct mtk_gate_regs apmixed_cg_regs = { + .set_ofs = 0x8, + .clr_ofs = 0x8, + .sta_ofs = 0x8, +}; + +#define GATE_APMIXED(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &apmixed_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +static const struct mtk_gate apmixed_clks[] = { + GATE_APMIXED(CLK_APMIXED_PLL_SSUSB26M_EN, "pll_ssusb26m_en", "clk26m", 1), +}; + +#define MT8188_PLL_FMAX (3800UL * MHZ) +#define MT8188_PLL_FMIN (1500UL * MHZ) +#define MT8188_INTEGER_BITS 8 + +#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, \ + _rst_bar_mask, _pcwbits, _pd_reg, _pd_shift, \ + _tuner_reg, _tuner_en_reg, _tuner_en_bit, \ + _pcw_reg, _pcw_shift, _pcw_chg_reg, \ + _en_reg, _pll_en_bit) { \ + .id = _id, \ + .name = _name, \ + .reg = _reg, \ + .pwr_reg = _pwr_reg, \ + .en_mask = _en_mask, \ + .flags = _flags, \ + .rst_bar_mask = _rst_bar_mask, \ + .fmax = MT8188_PLL_FMAX, \ + .fmin = MT8188_PLL_FMIN, \ + .pcwbits = _pcwbits, \ + .pcwibits = MT8188_INTEGER_BITS, \ + .pd_reg = _pd_reg, \ + .pd_shift = _pd_shift, \ + .tuner_reg = _tuner_reg, \ + .tuner_en_reg = _tuner_en_reg, \ + .tuner_en_bit = _tuner_en_bit, \ + .pcw_reg = _pcw_reg, \ + .pcw_shift = _pcw_shift, \ + .pcw_chg_reg = _pcw_chg_reg, \ + .en_reg = _en_reg, \ + .pll_en_bit = _pll_en_bit, \ + } + +static const struct mtk_pll_data plls[] = { + PLL(CLK_APMIXED_ETHPLL, "ethpll", 0x044C, 0x0458, 0, + 0, 0, 22, 0x0450, 24, 0, 0, 0, 0x0450, 0, 0, 0, 9), + PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0514, 0x0520, 0, + 0, 0, 22, 0x0518, 24, 0, 0, 0, 0x0518, 0, 0, 0, 9), + PLL(CLK_APMIXED_TVDPLL1, "tvdpll1", 0x0524, 0x0530, 0, + 0, 0, 22, 0x0528, 24, 0, 0, 0, 0x0528, 0, 0, 0, 9), + PLL(CLK_APMIXED_TVDPLL2, "tvdpll2", 0x0534, 0x0540, 0, + 0, 0, 22, 0x0538, 24, 0, 0, 0, 0x0538, 0, 0, 0, 9), + PLL(CLK_APMIXED_MMPLL, "mmpll", 0x0544, 0x0550, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0548, 24, 0, 0, 0, 0x0548, 0, 0, 0, 9), + PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x045C, 0x0468, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0460, 24, 0, 0, 0, 0x0460, 0, 0, 0, 9), + PLL(CLK_APMIXED_IMGPLL, "imgpll", 0x0554, 0x0560, 0, + 0, 0, 22, 0x0558, 24, 0, 0, 0, 0x0558, 0, 0, 0, 9), + PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0504, 0x0510, 0xff000000, + HAVE_RST_BAR, BIT(23), 22, 0x0508, 24, 0, 0, 0, 0x0508, 0, 0, 0, 9), + PLL(CLK_APMIXED_ADSPPLL, "adsppll", 0x042C, 0x0438, 0, + 0, 0, 22, 0x0430, 24, 0, 0, 0, 0x0430, 0, 0, 0, 9), + PLL(CLK_APMIXED_APLL1, "apll1", 0x0304, 0x0314, 0, + 0, 0, 32, 0x0308, 24, 0x0034, 0x0000, 12, 0x030C, 0, 0, 0, 9), + PLL(CLK_APMIXED_APLL2, "apll2", 0x0318, 0x0328, 0, + 0, 0, 32, 0x031C, 24, 0x0038, 0x0000, 13, 0x0320, 0, 0, 0, 9), + PLL(CLK_APMIXED_APLL3, "apll3", 0x032C, 0x033C, 0, + 0, 0, 32, 0x0330, 24, 0x003C, 0x0000, 14, 0x0334, 0, 0, 0, 9), + PLL(CLK_APMIXED_APLL4, "apll4", 0x0404, 0x0414, 0, + 0, 0, 32, 0x0408, 24, 0x0040, 0x0000, 15, 0x040C, 0, 0, 0, 9), + PLL(CLK_APMIXED_APLL5, "apll5", 0x0418, 0x0428, 0, + 0, 0, 32, 0x041C, 24, 0x0044, 0x0000, 16, 0x0420, 0, 0, 0, 9), + PLL(CLK_APMIXED_MFGPLL, "mfgpll", 0x0340, 0x034C, 0, + 0, 0, 22, 0x0344, 24, 0, 0, 0, 0x0344, 0, 0, 0, 9), +}; + +static const struct of_device_id of_match_clk_mt8188_apmixed[] = { + { .compatible = "mediatek,mt8188-apmixedsys" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_apmixed); + +static int clk_mt8188_apmixed_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *clk_data; + struct device_node *node = pdev->dev.of_node; + int r; + + clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK); + if (!clk_data) + return -ENOMEM; + + r = mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data); + if (r) + goto free_apmixed_data; + + r = mtk_clk_register_gates(&pdev->dev, node, apmixed_clks, + ARRAY_SIZE(apmixed_clks), clk_data); + if (r) + goto unregister_plls; + + r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data); + if (r) + goto unregister_gates; + + platform_set_drvdata(pdev, clk_data); + + return 0; + +unregister_gates: + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); +unregister_plls: + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); +free_apmixed_data: + mtk_free_clk_data(clk_data); + return r; +} + +static int clk_mt8188_apmixed_remove(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct clk_hw_onecell_data *clk_data = platform_get_drvdata(pdev); + + of_clk_del_provider(node); + mtk_clk_unregister_gates(apmixed_clks, ARRAY_SIZE(apmixed_clks), clk_data); + mtk_clk_unregister_plls(plls, ARRAY_SIZE(plls), clk_data); + mtk_free_clk_data(clk_data); + + return 0; +} + +static struct platform_driver clk_mt8188_apmixed_drv = { + .probe = clk_mt8188_apmixed_probe, + .remove = clk_mt8188_apmixed_remove, + .driver = { + .name = "clk-mt8188-apmixed", + .of_match_table = of_match_clk_mt8188_apmixed, + }, +}; +module_platform_driver(clk_mt8188_apmixed_drv); +MODULE_LICENSE("GPL"); -- GitLab From 6c0d1dc233ee7278f02eba0c49ed66209d885925 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:05 +0800 Subject: [PATCH 1830/5631] clk: mediatek: Add MT8188 topckgen clock support Add MT8188 topckgen clock controller which provides muxes, dividers to handle variety clock selection in other IP blocks. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-4-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8188-topckgen.c | 1350 ++++++++++++++++++++ 2 files changed, 1351 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-topckgen.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 41b1f5f2d5c3..8afd30f6b3cc 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -100,7 +100,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_MMSYS) += clk-mt8186-mm.o obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o -obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o +obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-topckgen.c b/drivers/clk/mediatek/clk-mt8188-topckgen.c new file mode 100644 index 000000000000..c56ec42cb15f --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-topckgen.c @@ -0,0 +1,1350 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" +#include "clk-mux.h" + +static DEFINE_SPINLOCK(mt8188_clk_lock); + +static const struct mtk_fixed_clk top_fixed_clks[] = { + FIXED_CLK(CLK_TOP_ULPOSC1, "ulposc_ck1", NULL, 260000000), + FIXED_CLK(CLK_TOP_MPHONE_SLAVE_BCK, "mphone_slave_bck", NULL, 49152000), + FIXED_CLK(CLK_TOP_PAD_FPC, "pad_fpc_ck", NULL, 50000000), + FIXED_CLK(CLK_TOP_466M_FMEM, "hd_466m_fmem_ck", NULL, 533000000), + FIXED_CLK(CLK_TOP_PEXTP_PIPE, "pextp_pipe", NULL, 250000000), + FIXED_CLK(CLK_TOP_DSI_PHY, "dsi_phy", NULL, 500000000), +}; + +static const struct mtk_fixed_factor top_divs[] = { + FACTOR(CLK_TOP_MAINPLL_D3, "mainpll_d3", "mainpll", 1, 3), + FACTOR(CLK_TOP_MAINPLL_D4, "mainpll_d4", "mainpll", 1, 4), + FACTOR(CLK_TOP_MAINPLL_D4_D2, "mainpll_d4_d2", "mainpll_d4", 1, 2), + FACTOR(CLK_TOP_MAINPLL_D4_D4, "mainpll_d4_d4", "mainpll_d4", 1, 4), + FACTOR(CLK_TOP_MAINPLL_D4_D8, "mainpll_d4_d8", "mainpll_d4", 1, 8), + FACTOR(CLK_TOP_MAINPLL_D5, "mainpll_d5", "mainpll", 1, 5), + FACTOR(CLK_TOP_MAINPLL_D5_D2, "mainpll_d5_d2", "mainpll_d5", 1, 2), + FACTOR(CLK_TOP_MAINPLL_D5_D4, "mainpll_d5_d4", "mainpll_d5", 1, 4), + FACTOR(CLK_TOP_MAINPLL_D5_D8, "mainpll_d5_d8", "mainpll_d5", 1, 8), + FACTOR(CLK_TOP_MAINPLL_D6, "mainpll_d6", "mainpll", 1, 6), + FACTOR(CLK_TOP_MAINPLL_D6_D2, "mainpll_d6_d2", "mainpll_d6", 1, 2), + FACTOR(CLK_TOP_MAINPLL_D6_D4, "mainpll_d6_d4", "mainpll_d6", 1, 4), + FACTOR(CLK_TOP_MAINPLL_D6_D8, "mainpll_d6_d8", "mainpll_d6", 1, 8), + FACTOR(CLK_TOP_MAINPLL_D7, "mainpll_d7", "mainpll", 1, 7), + FACTOR(CLK_TOP_MAINPLL_D7_D2, "mainpll_d7_d2", "mainpll_d7", 1, 2), + FACTOR(CLK_TOP_MAINPLL_D7_D4, "mainpll_d7_d4", "mainpll_d7", 1, 4), + FACTOR(CLK_TOP_MAINPLL_D7_D8, "mainpll_d7_d8", "mainpll_d7", 1, 8), + FACTOR(CLK_TOP_MAINPLL_D9, "mainpll_d9", "mainpll", 1, 9), + FACTOR(CLK_TOP_UNIVPLL_D2, "univpll_d2", "univpll", 1, 2), + FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univpll", 1, 3), + FACTOR(CLK_TOP_UNIVPLL_D4, "univpll_d4", "univpll", 1, 4), + FACTOR(CLK_TOP_UNIVPLL_D4_D2, "univpll_d4_d2", "univpll_d4", 1, 2), + FACTOR(CLK_TOP_UNIVPLL_D4_D4, "univpll_d4_d4", "univpll_d4", 1, 4), + FACTOR(CLK_TOP_UNIVPLL_D4_D8, "univpll_d4_d8", "univpll_d4", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univpll", 1, 5), + FACTOR(CLK_TOP_UNIVPLL_D5_D2, "univpll_d5_d2", "univpll_d5", 1, 2), + FACTOR(CLK_TOP_UNIVPLL_D5_D4, "univpll_d5_d4", "univpll_d5", 1, 4), + FACTOR(CLK_TOP_UNIVPLL_D5_D8, "univpll_d5_d8", "univpll_d5", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_D6, "univpll_d6", "univpll", 1, 6), + FACTOR(CLK_TOP_UNIVPLL_D6_D2, "univpll_d6_d2", "univpll_d6", 1, 2), + FACTOR(CLK_TOP_UNIVPLL_D6_D4, "univpll_d6_d4", "univpll_d6", 1, 4), + FACTOR(CLK_TOP_UNIVPLL_D6_D8, "univpll_d6_d8", "univpll_d6", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univpll", 1, 7), + FACTOR(CLK_TOP_UNIVPLL_192M, "univpll_192m", "univpll", 1, 13), + FACTOR(CLK_TOP_UNIVPLL_192M_D4, "univpll_192m_d4", "univpll_192m", 1, 4), + FACTOR(CLK_TOP_UNIVPLL_192M_D8, "univpll_192m_d8", "univpll_192m", 1, 8), + FACTOR(CLK_TOP_UNIVPLL_192M_D10, "univpll_192m_d10", "univpll_192m", 1, 10), + FACTOR(CLK_TOP_UNIVPLL_192M_D16, "univpll_192m_d16", "univpll_192m", 1, 16), + FACTOR(CLK_TOP_UNIVPLL_192M_D32, "univpll_192m_d32", "univpll_192m", 1, 32), + FACTOR(CLK_TOP_APLL1_D3, "apll1_d3", "apll1", 1, 3), + FACTOR(CLK_TOP_APLL1_D4, "apll1_d4", "apll1", 1, 4), + FACTOR(CLK_TOP_APLL2_D3, "apll2_d3", "apll2", 1, 3), + FACTOR(CLK_TOP_APLL2_D4, "apll2_d4", "apll2", 1, 4), + FACTOR(CLK_TOP_APLL3_D4, "apll3_d4", "apll3", 1, 4), + FACTOR(CLK_TOP_APLL4_D4, "apll4_d4", "apll4", 1, 4), + FACTOR(CLK_TOP_APLL5_D4, "apll5_d4", "apll5", 1, 4), + FACTOR(CLK_TOP_MMPLL_D4, "mmpll_d4", "mmpll", 1, 4), + FACTOR(CLK_TOP_MMPLL_D4_D2, "mmpll_d4_d2", "mmpll_d4", 1, 2), + FACTOR(CLK_TOP_MMPLL_D5, "mmpll_d5", "mmpll", 1, 5), + FACTOR(CLK_TOP_MMPLL_D5_D2, "mmpll_d5_d2", "mmpll_d5", 1, 2), + FACTOR(CLK_TOP_MMPLL_D5_D4, "mmpll_d5_d4", "mmpll_d5", 1, 4), + FACTOR(CLK_TOP_MMPLL_D6, "mmpll_d6", "mmpll", 1, 6), + FACTOR(CLK_TOP_MMPLL_D6_D2, "mmpll_d6_d2", "mmpll_d6", 1, 2), + FACTOR(CLK_TOP_MMPLL_D7, "mmpll_d7", "mmpll", 1, 7), + FACTOR(CLK_TOP_MMPLL_D9, "mmpll_d9", "mmpll", 1, 9), + FACTOR(CLK_TOP_TVDPLL1_D2, "tvdpll1_d2", "tvdpll1", 1, 2), + FACTOR(CLK_TOP_TVDPLL1_D4, "tvdpll1_d4", "tvdpll1", 1, 4), + FACTOR(CLK_TOP_TVDPLL1_D8, "tvdpll1_d8", "tvdpll1", 1, 8), + FACTOR(CLK_TOP_TVDPLL1_D16, "tvdpll1_d16", "tvdpll1", 1, 16), + FACTOR(CLK_TOP_TVDPLL2_D2, "tvdpll2_d2", "tvdpll2", 1, 2), + FACTOR(CLK_TOP_TVDPLL2_D4, "tvdpll2_d4", "tvdpll2", 1, 4), + FACTOR(CLK_TOP_TVDPLL2_D8, "tvdpll2_d8", "tvdpll2", 1, 8), + FACTOR(CLK_TOP_TVDPLL2_D16, "tvdpll2_d16", "tvdpll2", 1, 16), + FACTOR(CLK_TOP_MSDCPLL_D2, "msdcpll_d2", "msdcpll", 1, 2), + FACTOR(CLK_TOP_MSDCPLL_D16, "msdcpll_d16", "msdcpll", 1, 16), + FACTOR(CLK_TOP_ETHPLL_D2, "ethpll_d2", "ethpll", 1, 2), + FACTOR(CLK_TOP_ETHPLL_D4, "ethpll_d4", "ethpll", 1, 4), + FACTOR(CLK_TOP_ETHPLL_D8, "ethpll_d8", "ethpll", 1, 8), + FACTOR(CLK_TOP_ETHPLL_D10, "ethpll_d10", "ethpll", 1, 10), + FACTOR(CLK_TOP_ADSPPLL_D2, "adsppll_d2", "adsppll", 1, 2), + FACTOR(CLK_TOP_ADSPPLL_D4, "adsppll_d4", "adsppll", 1, 4), + FACTOR(CLK_TOP_ADSPPLL_D8, "adsppll_d8", "adsppll", 1, 8), + FACTOR(CLK_TOP_ULPOSC1_D2, "ulposc1_d2", "ulposc_ck1", 1, 2), + FACTOR(CLK_TOP_ULPOSC1_D4, "ulposc1_d4", "ulposc_ck1", 1, 4), + FACTOR(CLK_TOP_ULPOSC1_D8, "ulposc1_d8", "ulposc_ck1", 1, 8), + FACTOR(CLK_TOP_ULPOSC1_D7, "ulposc1_d7", "ulposc_ck1", 1, 7), + FACTOR(CLK_TOP_ULPOSC1_D10, "ulposc1_d10", "ulposc_ck1", 1, 10), + FACTOR(CLK_TOP_ULPOSC1_D16, "ulposc1_d16", "ulposc_ck1", 1, 16), +}; + +static const char * const axi_parents[] = { + "clk26m", + "mainpll_d4_d4", + "mainpll_d7_d2", + "mainpll_d4_d2", + "mainpll_d5_d2", + "mainpll_d6_d2", + "ulposc1_d4" +}; + +static const char * const spm_parents[] = { + "clk26m", + "ulposc1_d10", + "mainpll_d7_d4", + "clk32k" +}; + +static const char * const scp_parents[] = { + "clk26m", + "univpll_d4", + "mainpll_d6", + "univpll_d6", + "univpll_d4_d2", + "mainpll_d4_d2", + "univpll_d3", + "mainpll_d3" +}; + +static const char * const bus_aximem_parents[] = { + "clk26m", + "mainpll_d7_d2", + "mainpll_d4_d2", + "mainpll_d5_d2", + "mainpll_d6" +}; + +static const char * const vpp_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d5_d2", + "mmpll_d6_d2", + "univpll_d5_d2", + "univpll_d4_d2", + "mmpll_d4_d2", + "mmpll_d7", + "univpll_d6", + "mainpll_d4", + "mmpll_d5", + "tvdpll1", + "tvdpll2", + "univpll_d4", + "mmpll_d4" +}; + +static const char * const ethdr_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d5_d2", + "mmpll_d6_d2", + "univpll_d5_d2", + "univpll_d4_d2", + "mmpll_d4_d2", + "mmpll_d7", + "univpll_d6", + "mainpll_d4", + "mmpll_d5_d4", + "tvdpll1", + "tvdpll2", + "univpll_d4", + "mmpll_d4" +}; + +static const char * const ipe_parents[] = { + "clk26m", + "imgpll", + "mainpll_d4", + "mmpll_d6", + "univpll_d6", + "mainpll_d6", + "mmpll_d4_d2", + "univpll_d4_d2", + "mainpll_d4_d2", + "mmpll_d6_d2", + "univpll_d5_d2", + "mainpll_d7" +}; + +static const char * const cam_parents[] = { + "clk26m", + "tvdpll1", + "mainpll_d4", + "mmpll_d4", + "univpll_d4", + "univpll_d5", + "univpll_d6", + "mmpll_d7", + "univpll_d4_d2", + "mainpll_d4_d2", + "imgpll" +}; + +static const char * const ccu_parents[] = { + "clk26m", + "univpll_d6", + "mainpll_d4_d2", + "mainpll_d4", + "univpll_d5", + "mainpll_d6", + "mmpll_d6", + "mmpll_d7", + "univpll_d4_d2", + "univpll_d7" +}; + +static const char * const ccu_ahb_parents[] = { + "clk26m", + "univpll_d6", + "mainpll_d4_d2", + "mainpll_d4", + "univpll_d5", + "mainpll_d6", + "mmpll_d6", + "mmpll_d7", + "univpll_d4_d2", + "univpll_d7" +}; + +static const char * const img_parents[] = { + "clk26m", + "imgpll", + "univpll_d4", + "mainpll_d4", + "univpll_d5", + "mmpll_d6", + "mmpll_d7", + "univpll_d6", + "mainpll_d6", + "mmpll_d4_d2", + "univpll_d4_d2", + "mainpll_d4_d2", + "univpll_d5_d2" +}; + +static const char * const camtm_parents[] = { + "clk26m", + "univpll_d4_d4", + "univpll_d6_d2", + "univpll_d6_d4" +}; + +static const char * const dsp_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d4_d2", + "univpll_d5", + "univpll_d4", + "mmpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp1_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d4_d2", + "univpll_d5", + "mmpll_d5", + "univpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp2_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d4_d2", + "univpll_d5", + "mmpll_d5", + "univpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp3_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d4_d2", + "univpll_d5", + "mmpll_d5", + "univpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp4_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d4_d2", + "mainpll_d4", + "univpll_d4", + "mmpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp5_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d4_d2", + "mainpll_d4", + "univpll_d4", + "mmpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp6_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d4_d2", + "mainpll_d4", + "univpll_d4", + "mmpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const dsp7_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d4_d2", + "univpll_d5", + "univpll_d4", + "mmpll_d4", + "mainpll_d3", + "univpll_d3" +}; + +static const char * const mfg_core_tmp_parents[] = { + "clk26m", + "mainpll_d5_d2", + "univpll_d6", + "univpll_d7" +}; + +static const char * const camtg_parents[] = { + "clk26m", + "univpll_192m_d8", + "univpll_d6_d8", + "univpll_192m_d4", + "univpll_192m_d10", + "clk13m", + "univpll_192m_d16", + "univpll_192m_d32" +}; + +static const char * const camtg2_parents[] = { + "clk26m", + "univpll_192m_d8", + "univpll_d6_d8", + "univpll_192m_d4", + "univpll_192m_d10", + "clk13m", + "univpll_192m_d16", + "univpll_192m_d32" +}; + +static const char * const camtg3_parents[] = { + "clk26m", + "univpll_192m_d8", + "univpll_d6_d8", + "univpll_192m_d4", + "univpll_192m_d10", + "clk13m", + "univpll_192m_d16", + "univpll_192m_d32" +}; + +static const char * const uart_parents[] = { + "clk26m", + "univpll_d6_d8" +}; + +static const char * const spi_parents[] = { + "clk26m", + "mainpll_d5_d4", + "mainpll_d6_d4", + "univpll_d6_d4", + "univpll_d6_d2", + "mainpll_d6_d2", + "mainpll_d4_d4", + "univpll_d5_d4" +}; + +static const char * const msdc5hclk_parents[] = { + "clk26m", + "mainpll_d4_d2", + "mainpll_d6_d2" +}; + +static const char * const msdc50_0_parents[] = { + "clk26m", + "msdcpll", + "msdcpll_d2", + "univpll_d4_d4", + "mainpll_d6_d2", + "univpll_d4_d2" +}; + +static const char * const msdc30_1_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d6_d2", + "mainpll_d7_d2", + "msdcpll_d2" +}; + +static const char * const msdc30_2_parents[] = { + "clk26m", + "univpll_d6_d2", + "mainpll_d6_d2", + "mainpll_d7_d2", + "msdcpll_d2" +}; + +static const char * const intdir_parents[] = { + "clk26m", + "univpll_d6", + "mainpll_d4", + "univpll_d4" +}; + +static const char * const aud_intbus_parents[] = { + "clk26m", + "mainpll_d4_d4", + "mainpll_d7_d4" +}; + +static const char * const audio_h_parents[] = { + "clk26m", + "univpll_d7", + "apll1", + "apll2" +}; + +static const char * const pwrap_ulposc_parents[] = { + "clk26m", + "ulposc1_d10", + "ulposc1_d7", + "ulposc1_d8", + "ulposc1_d16", + "mainpll_d4_d8", + "univpll_d5_d8", + "tvdpll1_d16" +}; + +static const char * const atb_parents[] = { + "clk26m", + "mainpll_d4_d2", + "mainpll_d5_d2" +}; + +static const char * const sspm_parents[] = { + "clk26m", + "mainpll_d7_d2", + "mainpll_d6_d2", + "mainpll_d5_d2", + "mainpll_d9", + "mainpll_d4_d2" +}; + +static const char * const dp_parents[] = { + "clk26m", + "tvdpll1_d2", + "tvdpll2_d2", + "tvdpll1_d4", + "tvdpll2_d4", + "tvdpll1_d8", + "tvdpll2_d8", + "tvdpll1_d16", + "tvdpll2_d16" +}; + +static const char * const edp_parents[] = { + "clk26m", + "tvdpll1_d2", + "tvdpll2_d2", + "tvdpll1_d4", + "tvdpll2_d4", + "tvdpll1_d8", + "tvdpll2_d8", + "tvdpll1_d16", + "tvdpll2_d16" +}; + +static const char * const dpi_parents[] = { + "clk26m", + "tvdpll1_d2", + "tvdpll2_d2", + "tvdpll1_d4", + "tvdpll2_d4", + "tvdpll1_d8", + "tvdpll2_d8", + "tvdpll1_d16", + "tvdpll2_d16" +}; + +static const char * const disp_pwm0_parents[] = { + "clk26m", + "univpll_d6_d4", + "ulposc1_d2", + "ulposc1_d4", + "ulposc1_d16", + "ethpll_d4" +}; + +static const char * const disp_pwm1_parents[] = { + "clk26m", + "univpll_d6_d4", + "ulposc1_d2", + "ulposc1_d4", + "ulposc1_d16" +}; + +static const char * const usb_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const ssusb_xhci_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const usb_2p_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const ssusb_xhci_2p_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const usb_3p_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const ssusb_xhci_3p_parents[] = { + "clk26m", + "univpll_d5_d4", + "univpll_d6_d4", + "univpll_d5_d2" +}; + +static const char * const i2c_parents[] = { + "clk26m", + "mainpll_d4_d8", + "univpll_d5_d4" +}; + +static const char * const seninf_parents[] = { + "clk26m", + "univpll_d4_d4", + "univpll_d6_d2", + "mainpll_d4_d2", + "univpll_d7", + "univpll_d6", + "mmpll_d6", + "univpll_d5" +}; + +static const char * const seninf1_parents[] = { + "clk26m", + "univpll_d4_d4", + "univpll_d6_d2", + "mainpll_d4_d2", + "univpll_d7", + "univpll_d6", + "mmpll_d6", + "univpll_d5" +}; + +static const char * const gcpu_parents[] = { + "clk26m", + "mainpll_d6", + "univpll_d4_d2", + "mmpll_d5_d2", + "univpll_d5_d2" +}; + +static const char * const venc_parents[] = { + "clk26m", + "mmpll_d4_d2", + "mainpll_d6", + "univpll_d4_d2", + "mainpll_d4_d2", + "univpll_d6", + "mmpll_d6", + "mainpll_d5_d2", + "mainpll_d6_d2", + "mmpll_d9", + "univpll_d4_d4", + "mainpll_d4", + "univpll_d4", + "univpll_d5", + "univpll_d5_d2", + "mainpll_d5" +}; + +static const char * const vdec_parents[] = { + "clk26m", + "mainpll_d5_d2", + "mmpll_d6_d2", + "univpll_d5_d2", + "univpll_d4_d2", + "mmpll_d4_d2", + "univpll_d6", + "mainpll_d5", + "univpll_d5", + "mmpll_d6", + "mainpll_d4", + "tvdpll2", + "univpll_d4", + "imgpll", + "univpll_d6_d2", + "mmpll_d9" +}; + +static const char * const pwm_parents[] = { + "clk32k", + "clk26m", + "univpll_d4_d8", + "univpll_d6_d4" +}; + +static const char * const mcupm_parents[] = { + "clk26m", + "mainpll_d6_d2", + "mainpll_d7_d4" +}; + +static const char * const spmi_p_mst_parents[] = { + "clk26m", + "clk13m", + "ulposc1_d8", + "ulposc1_d10", + "ulposc1_d16", + "ulposc1_d7", + "clk32k", + "mainpll_d7_d8", + "mainpll_d6_d8", + "mainpll_d5_d8" +}; + +static const char * const spmi_m_mst_parents[] = { + "clk26m", + "clk13m", + "ulposc1_d8", + "ulposc1_d10", + "ulposc1_d16", + "ulposc1_d7", + "clk32k", + "mainpll_d7_d8", + "mainpll_d6_d8", + "mainpll_d5_d8" +}; + +static const char * const dvfsrc_parents[] = { + "clk26m", + "ulposc1_d10", + "univpll_d6_d8", + "msdcpll_d16" +}; + +static const char * const tl_parents[] = { + "clk26m", + "univpll_d5_d4", + "mainpll_d4_d4" +}; + +static const char * const aes_msdcfde_parents[] = { + "clk26m", + "mainpll_d4_d2", + "mainpll_d6", + "mainpll_d4_d4", + "univpll_d4_d2", + "univpll_d6" +}; + +static const char * const dsi_occ_parents[] = { + "clk26m", + "univpll_d6_d2", + "univpll_d5_d2", + "univpll_d4_d2" +}; + +static const char * const wpe_vpp_parents[] = { + "clk26m", + "mainpll_d5_d2", + "mmpll_d6_d2", + "univpll_d5_d2", + "mainpll_d4_d2", + "univpll_d4_d2", + "mmpll_d4_d2", + "mainpll_d6", + "mmpll_d7", + "univpll_d6", + "mainpll_d5", + "univpll_d5", + "mainpll_d4", + "tvdpll1", + "univpll_d4" +}; + +static const char * const hdcp_parents[] = { + "clk26m", + "univpll_d4_d8", + "mainpll_d5_d8", + "univpll_d6_d4" +}; + +static const char * const hdcp_24m_parents[] = { + "clk26m", + "univpll_192m_d4", + "univpll_192m_d8", + "univpll_d6_d8" +}; + +static const char * const hdmi_apb_parents[] = { + "clk26m", + "univpll_d6_d4", + "msdcpll_d2" +}; + +static const char * const snps_eth_250m_parents[] = { + "clk26m", + "ethpll_d2" +}; + +static const char * const snps_eth_62p4m_ptp_parents[] = { + "apll2_d3", + "apll1_d3", + "clk26m", + "ethpll_d8" +}; + +static const char * const snps_eth_50m_rmii_parents[] = { + "clk26m", + "ethpll_d10" +}; + +static const char * const adsp_parents[] = { + "clk26m", + "clk13m", + "mainpll_d6", + "mainpll_d5_d2", + "univpll_d4_d4", + "univpll_d4", + "ulposc1_d2", + "ulposc1_ck1", + "adsppll", + "adsppll_d2", + "adsppll_d4", + "adsppll_d8" +}; + +static const char * const audio_local_bus_parents[] = { + "clk26m", + "clk13m", + "mainpll_d4_d4", + "mainpll_d7_d2", + "mainpll_d5_d2", + "mainpll_d4_d2", + "mainpll_d7", + "mainpll_d4", + "univpll_d6", + "ulposc1_ck1", + "ulposc1_d4", + "ulposc1_d2" +}; + +static const char * const asm_h_parents[] = { + "clk26m", + "univpll_d6_d4", + "univpll_d6_d2", + "mainpll_d5_d2" +}; + +static const char * const asm_l_parents[] = { + "clk26m", + "univpll_d6_d4", + "univpll_d6_d2", + "mainpll_d5_d2" +}; + +static const char * const apll1_parents[] = { + "clk26m", + "apll1_d4" +}; + +static const char * const apll2_parents[] = { + "clk26m", + "apll2_d4" +}; + +static const char * const apll3_parents[] = { + "clk26m", + "apll3_d4" +}; + +static const char * const apll4_parents[] = { + "clk26m", + "apll4_d4" +}; + +static const char * const apll5_parents[] = { + "clk26m", + "apll5_d4" +}; + +static const char * const i2so1_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const i2so2_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const i2si1_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const i2si2_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const dptx_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const aud_iec_parents[] = { + "clk26m", + "apll1", + "apll2", + "apll3", + "apll4", + "apll5" +}; + +static const char * const a1sys_hp_parents[] = { + "clk26m", + "apll1_d4" +}; + +static const char * const a2sys_parents[] = { + "clk26m", + "apll2_d4" +}; + +static const char * const a3sys_parents[] = { + "clk26m", + "apll3_d4", + "apll4_d4", + "apll5_d4" +}; + +static const char * const a4sys_parents[] = { + "clk26m", + "apll3_d4", + "apll4_d4", + "apll5_d4" +}; + +static const char * const ecc_parents[] = { + "clk26m", + "mainpll_d4_d4", + "mainpll_d5_d2", + "mainpll_d4_d2", + "mainpll_d6", + "univpll_d6" +}; + +static const char * const spinor_parents[] = { + "clk26m", + "clk13m", + "mainpll_d7_d8", + "univpll_d6_d8" +}; + +static const char * const ulposc_parents[] = { + "ulposc_ck1", + "ethpll_d2", + "mainpll_d4_d2", + "ethpll_d10" +}; + +static const char * const srck_parents[] = { + "ulposc1_d10", + "clk26m" +}; + +static const char * const mfg_fast_ref_parents[] = { + "top_mfg_core_tmp", + "mfgpll" +}; + +static const struct mtk_mux top_mtk_muxes[] = { + /* + * CLK_CFG_0 + * axi_sel and bus_aximem_sel are bus clocks, should not be closed by Linux. + * spm_sel and scp_sel are main clocks in always-on co-processor. + */ + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_AXI, "top_axi", axi_parents, + 0x020, 0x024, 0x028, 0, 4, 7, 0x04, 0, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_SPM, "top_spm", spm_parents, + 0x020, 0x024, 0x028, 8, 4, 15, 0x04, 1, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_SCP, "top_scp", scp_parents, + 0x020, 0x024, 0x028, 16, 4, 23, 0x04, 2, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_BUS_AXIMEM, "top_bus_aximem", bus_aximem_parents, + 0x020, 0x024, 0x028, 24, 4, 31, 0x04, 3, CLK_IS_CRITICAL), + /* CLK_CFG_1 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_VPP, "top_vpp", + vpp_parents, 0x02C, 0x030, 0x034, 0, 4, 7, 0x04, 4), + MUX_GATE_CLR_SET_UPD(CLK_TOP_ETHDR, "top_ethdr", + ethdr_parents, 0x02C, 0x030, 0x034, 8, 4, 15, 0x04, 5), + MUX_GATE_CLR_SET_UPD(CLK_TOP_IPE, "top_ipe", + ipe_parents, 0x02C, 0x030, 0x034, 16, 4, 23, 0x04, 6), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CAM, "top_cam", + cam_parents, 0x02C, 0x030, 0x034, 24, 4, 31, 0x04, 7), + /* CLK_CFG_2 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_CCU, "top_ccu", + ccu_parents, 0x038, 0x03C, 0x040, 0, 4, 7, 0x04, 8), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CCU_AHB, "top_ccu_ahb", + ccu_ahb_parents, 0x038, 0x03C, 0x040, 8, 4, 15, 0x04, 9), + MUX_GATE_CLR_SET_UPD(CLK_TOP_IMG, "top_img", + img_parents, 0x038, 0x03C, 0x040, 16, 4, 23, 0x04, 10), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CAMTM, "top_camtm", + camtm_parents, 0x038, 0x03C, 0x040, 24, 4, 31, 0x04, 11), + /* CLK_CFG_3 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP, "top_dsp", + dsp_parents, 0x044, 0x048, 0x04C, 0, 4, 7, 0x04, 12), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP1, "top_dsp1", + dsp1_parents, 0x044, 0x048, 0x04C, 8, 4, 15, 0x04, 13), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP2, "top_dsp2", + dsp2_parents, 0x044, 0x048, 0x04C, 16, 4, 23, 0x04, 14), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP3, "top_dsp3", + dsp3_parents, 0x044, 0x048, 0x04C, 24, 4, 31, 0x04, 15), + /* CLK_CFG_4 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP4, "top_dsp4", + dsp4_parents, 0x050, 0x054, 0x058, 0, 4, 7, 0x04, 16), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP5, "top_dsp5", + dsp5_parents, 0x050, 0x054, 0x058, 8, 4, 15, 0x04, 17), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP6, "top_dsp6", + dsp6_parents, 0x050, 0x054, 0x058, 16, 4, 23, 0x04, 18), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSP7, "top_dsp7", + dsp7_parents, 0x050, 0x054, 0x058, 24, 4, 31, 0x04, 19), + /* CLK_CFG_5 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_MFG_CORE_TMP, "top_mfg_core_tmp", + mfg_core_tmp_parents, 0x05C, 0x060, 0x064, 0, 4, 7, 0x04, 20), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CAMTG, "top_camtg", + camtg_parents, 0x05C, 0x060, 0x064, 8, 4, 15, 0x04, 21), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CAMTG2, "top_camtg2", + camtg2_parents, 0x05C, 0x060, 0x064, 16, 4, 23, 0x04, 22), + MUX_GATE_CLR_SET_UPD(CLK_TOP_CAMTG3, "top_camtg3", + camtg3_parents, 0x05C, 0x060, 0x064, 24, 4, 31, 0x04, 23), + /* CLK_CFG_6 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_UART, "top_uart", + uart_parents, 0x068, 0x06C, 0x070, 0, 4, 7, 0x04, 24), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SPI, "top_spi", + spi_parents, 0x068, 0x06C, 0x070, 8, 4, 15, 0x04, 25), + MUX_GATE_CLR_SET_UPD(CLK_TOP_MSDC50_0_HCLK, "top_msdc5hclk", + msdc5hclk_parents, 0x068, 0x06C, 0x070, 16, 4, 23, 0x04, 26), + MUX_GATE_CLR_SET_UPD(CLK_TOP_MSDC50_0, "top_msdc50_0", + msdc50_0_parents, 0x068, 0x06C, 0x070, 24, 4, 31, 0x04, 27), + /* CLK_CFG_7 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_MSDC30_1, "top_msdc30_1", + msdc30_1_parents, 0x074, 0x078, 0x07C, 0, 4, 7, 0x04, 28), + MUX_GATE_CLR_SET_UPD(CLK_TOP_MSDC30_2, "top_msdc30_2", + msdc30_2_parents, 0x074, 0x078, 0x07C, 8, 4, 15, 0x04, 29), + MUX_GATE_CLR_SET_UPD(CLK_TOP_INTDIR, "top_intdir", + intdir_parents, 0x074, 0x078, 0x07C, 16, 4, 23, 0x04, 30), + MUX_GATE_CLR_SET_UPD(CLK_TOP_AUD_INTBUS, "top_aud_intbus", + aud_intbus_parents, 0x074, 0x078, 0x07C, 24, 4, 31, 0x04, 31), + /* CLK_CFG_8 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_AUDIO_H, "top_audio_h", + audio_h_parents, 0x080, 0x084, 0x088, 0, 4, 7, 0x08, 0), + MUX_GATE_CLR_SET_UPD(CLK_TOP_PWRAP_ULPOSC, "top_pwrap_ulposc", + pwrap_ulposc_parents, 0x080, 0x084, 0x088, 8, 4, 15, 0x08, 1), + MUX_GATE_CLR_SET_UPD(CLK_TOP_ATB, "top_atb", + atb_parents, 0x080, 0x084, 0x088, 16, 4, 23, 0x08, 2), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SSPM, "top_sspm", + sspm_parents, 0x080, 0x084, 0x088, 24, 4, 31, 0x08, 3), + /* CLK_CFG_9 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_DP, "top_dp", + dp_parents, 0x08C, 0x090, 0x094, 0, 4, 7, 0x08, 4), + MUX_GATE_CLR_SET_UPD(CLK_TOP_EDP, "top_edp", + edp_parents, 0x08C, 0x090, 0x094, 8, 4, 15, 0x08, 5), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DPI, "top_dpi", + dpi_parents, 0x08C, 0x090, 0x094, 16, 4, 23, 0x08, 6), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DISP_PWM0, "top_disp_pwm0", + disp_pwm0_parents, 0x08C, 0x090, 0x094, 24, 4, 31, 0x08, 7), + /* CLK_CFG_10 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_DISP_PWM1, "top_disp_pwm1", + disp_pwm1_parents, 0x098, 0x09C, 0x0A0, 0, 4, 7, 0x08, 8), + MUX_GATE_CLR_SET_UPD(CLK_TOP_USB_TOP, "top_usb_top", + usb_parents, 0x098, 0x09C, 0x0A0, 8, 4, 15, 0x08, 9), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SSUSB_XHCI, "top_ssusb_xhci", + ssusb_xhci_parents, 0x098, 0x09C, 0x0A0, 16, 4, 23, 0x08, 10), + MUX_GATE_CLR_SET_UPD(CLK_TOP_USB_TOP_2P, "top_usb_top_2p", + usb_2p_parents, 0x098, 0x09C, 0x0A0, 24, 4, 31, 0x08, 11), + /* CLK_CFG_11 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_SSUSB_XHCI_2P, "top_ssusb_xhci_2p", + ssusb_xhci_2p_parents, 0x0A4, 0x0A8, 0x0AC, 0, 4, 7, 0x08, 12), + MUX_GATE_CLR_SET_UPD(CLK_TOP_USB_TOP_3P, "top_usb_top_3p", + usb_3p_parents, 0x0A4, 0x0A8, 0x0AC, 8, 4, 15, 0x08, 13), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SSUSB_XHCI_3P, "top_ssusb_xhci_3p", + ssusb_xhci_3p_parents, 0x0A4, 0x0A8, 0x0AC, 16, 4, 23, 0x08, 14), + MUX_GATE_CLR_SET_UPD(CLK_TOP_I2C, "top_i2c", + i2c_parents, 0x0A4, 0x0A8, 0x0AC, 24, 4, 31, 0x08, 15), + /* CLK_CFG_12 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_SENINF, "top_seninf", + seninf_parents, 0x0B0, 0x0B4, 0x0B8, 0, 4, 7, 0x08, 16), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SENINF1, "top_seninf1", + seninf1_parents, 0x0B0, 0x0B4, 0x0B8, 8, 4, 15, 0x08, 17), + MUX_GATE_CLR_SET_UPD(CLK_TOP_GCPU, "top_gcpu", + gcpu_parents, 0x0B0, 0x0B4, 0x0B8, 16, 4, 23, 0x08, 18), + MUX_GATE_CLR_SET_UPD(CLK_TOP_VENC, "top_venc", + venc_parents, 0x0B0, 0x0B4, 0x0B8, 24, 4, 31, 0x08, 19), + /* + * CLK_CFG_13 + * top_mcupm is main clock in co-processor, should not be handled by Linux. + */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_VDEC, "top_vdec", + vdec_parents, 0x0BC, 0x0C0, 0x0C4, 0, 4, 7, 0x08, 20), + MUX_GATE_CLR_SET_UPD(CLK_TOP_PWM, "top_pwm", + pwm_parents, 0x0BC, 0x0C0, 0x0C4, 8, 4, 15, 0x08, 21), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_MCUPM, "top_mcupm", mcupm_parents, + 0x0BC, 0x0C0, 0x0C4, 16, 4, 23, 0x08, 22, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SPMI_P_MST, "top_spmi_p_mst", + spmi_p_mst_parents, 0x0BC, 0x0C0, 0x0C4, 24, 4, 31, 0x08, 23), + /* + * CLK_CFG_14 + * dvfsrc_sel is for internal DVFS usage, should not be handled by Linux. + */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_SPMI_M_MST, "top_spmi_m_mst", + spmi_m_mst_parents, 0x0C8, 0x0CC, 0x0D0, 0, 4, 7, 0x08, 24), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_DVFSRC, "top_dvfsrc", dvfsrc_parents, + 0x0C8, 0x0CC, 0x0D0, 8, 4, 15, 0x08, 25, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD(CLK_TOP_TL, "top_tl", + tl_parents, 0x0C8, 0x0CC, 0x0D0, 16, 4, 23, 0x08, 26), + MUX_GATE_CLR_SET_UPD(CLK_TOP_AES_MSDCFDE, "top_aes_msdcfde", + aes_msdcfde_parents, 0x0C8, 0x0CC, 0x0D0, 24, 4, 31, 0x08, 27), + /* CLK_CFG_15 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_DSI_OCC, "top_dsi_occ", + dsi_occ_parents, 0x0D4, 0x0D8, 0x0DC, 0, 4, 7, 0x08, 28), + MUX_GATE_CLR_SET_UPD(CLK_TOP_WPE_VPP, "top_wpe_vpp", + wpe_vpp_parents, 0x0D4, 0x0D8, 0x0DC, 8, 4, 15, 0x08, 29), + MUX_GATE_CLR_SET_UPD(CLK_TOP_HDCP, "top_hdcp", + hdcp_parents, 0x0D4, 0x0D8, 0x0DC, 16, 4, 23, 0x08, 30), + MUX_GATE_CLR_SET_UPD(CLK_TOP_HDCP_24M, "top_hdcp_24m", + hdcp_24m_parents, 0x0D4, 0x0D8, 0x0DC, 24, 4, 31, 0x08, 31), + /* CLK_CFG_16 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_HDMI_APB, "top_hdmi_apb", + hdmi_apb_parents, 0x0E0, 0x0E4, 0x0E8, 0, 4, 7, 0x0C, 0), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SNPS_ETH_250M, "top_snps_eth_250m", + snps_eth_250m_parents, 0x0E0, 0x0E4, 0x0E8, 8, 4, 15, 0x0C, 1), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SNPS_ETH_62P4M_PTP, "top_snps_eth_62p4m_ptp", + snps_eth_62p4m_ptp_parents, 0x0E0, 0x0E4, 0x0E8, 16, 4, 23, 0x0C, 2), + MUX_GATE_CLR_SET_UPD(CLK_TOP_SNPS_ETH_50M_RMII, "snps_eth_50m_rmii", + snps_eth_50m_rmii_parents, 0x0E0, 0x0E4, 0x0E8, 24, 4, 31, 0x0C, 3), + /* CLK_CFG_17 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_ADSP, "top_adsp", + adsp_parents, 0x0EC, 0x0F0, 0x0F4, 0, 4, 7, 0x0C, 4), + MUX_GATE_CLR_SET_UPD(CLK_TOP_AUDIO_LOCAL_BUS, "top_audio_local_bus", + audio_local_bus_parents, 0x0EC, 0x0F0, 0x0F4, 8, 4, 15, 0x0C, 5), + MUX_GATE_CLR_SET_UPD(CLK_TOP_ASM_H, "top_asm_h", + asm_h_parents, 0x0EC, 0x0F0, 0x0F4, 16, 4, 23, 0x0C, 6), + MUX_GATE_CLR_SET_UPD(CLK_TOP_ASM_L, "top_asm_l", + asm_l_parents, 0x0EC, 0x0F0, 0x0F4, 24, 4, 31, 0x0C, 7), + /* CLK_CFG_18 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_APLL1, "top_apll1", + apll1_parents, 0x0F8, 0x0FC, 0x100, 0, 4, 7, 0x0C, 8), + MUX_GATE_CLR_SET_UPD(CLK_TOP_APLL2, "top_apll2", + apll2_parents, 0x0F8, 0x0FC, 0x100, 8, 4, 15, 0x0C, 9), + MUX_GATE_CLR_SET_UPD(CLK_TOP_APLL3, "top_apll3", + apll3_parents, 0x0F8, 0x0FC, 0x100, 16, 4, 23, 0x0C, 10), + MUX_GATE_CLR_SET_UPD(CLK_TOP_APLL4, "top_apll4", + apll4_parents, 0x0F8, 0x0FC, 0x100, 24, 4, 31, 0x0C, 11), + /* CLK_CFG_19 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_APLL5, "top_apll5", + apll5_parents, 0x0104, 0x0108, 0x010C, 0, 4, 7, 0x0C, 12), + MUX_GATE_CLR_SET_UPD(CLK_TOP_I2SO1, "top_i2so1", + i2so1_parents, 0x0104, 0x0108, 0x010C, 8, 4, 15, 0x0C, 13), + MUX_GATE_CLR_SET_UPD(CLK_TOP_I2SO2, "top_i2so2", + i2so2_parents, 0x0104, 0x0108, 0x010C, 16, 4, 23, 0x0C, 14), + MUX_GATE_CLR_SET_UPD(CLK_TOP_I2SI1, "top_i2si1", + i2si1_parents, 0x0104, 0x0108, 0x010C, 24, 4, 31, 0x0C, 15), + /* CLK_CFG_20 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_I2SI2, "top_i2si2", + i2si2_parents, 0x0110, 0x0114, 0x0118, 0, 4, 7, 0x0C, 16), + MUX_GATE_CLR_SET_UPD(CLK_TOP_DPTX, "top_dptx", + dptx_parents, 0x0110, 0x0114, 0x0118, 8, 4, 15, 0x0C, 17), + MUX_GATE_CLR_SET_UPD(CLK_TOP_AUD_IEC, "top_aud_iec", + aud_iec_parents, 0x0110, 0x0114, 0x0118, 16, 4, 23, 0x0C, 18), + MUX_GATE_CLR_SET_UPD(CLK_TOP_A1SYS_HP, "top_a1sys_hp", + a1sys_hp_parents, 0x0110, 0x0114, 0x0118, 24, 4, 31, 0x0C, 19), + /* CLK_CFG_21 */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_A2SYS, "top_a2sys", + a2sys_parents, 0x011C, 0x0120, 0x0124, 0, 4, 7, 0x0C, 20), + MUX_GATE_CLR_SET_UPD(CLK_TOP_A3SYS, "top_a3sys", + a3sys_parents, 0x011C, 0x0120, 0x0124, 8, 4, 15, 0x0C, 21), + MUX_GATE_CLR_SET_UPD(CLK_TOP_A4SYS, "top_a4sys", + a4sys_parents, 0x011C, 0x0120, 0x0124, 16, 4, 23, 0x0C, 22), + MUX_GATE_CLR_SET_UPD(CLK_TOP_ECC, "top_ecc", + ecc_parents, 0x011C, 0x0120, 0x0124, 24, 4, 31, 0x0C, 23), + /* + * CLK_CFG_22 + * top_ulposc/top_srck are clock source of always on co-processor, + * should not be closed by Linux. + */ + MUX_GATE_CLR_SET_UPD(CLK_TOP_SPINOR, "top_spinor", + spinor_parents, 0x0128, 0x012C, 0x0130, 0, 4, 7, 0x0C, 24), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_ULPOSC, "top_ulposc", ulposc_parents, + 0x0128, 0x012C, 0x0130, 8, 4, 15, 0x0C, 25, CLK_IS_CRITICAL), + MUX_GATE_CLR_SET_UPD_FLAGS(CLK_TOP_SRCK, "top_srck", srck_parents, + 0x0128, 0x012C, 0x0130, 16, 4, 23, 0x0C, 26, CLK_IS_CRITICAL), +}; + +static const struct mtk_composite top_adj_divs[] = { + DIV_GATE(CLK_TOP_APLL12_CK_DIV0, "apll12_div0", "top_i2si1", 0x0320, 0, 0x0328, 8, 0), + DIV_GATE(CLK_TOP_APLL12_CK_DIV1, "apll12_div1", "top_i2si2", 0x0320, 1, 0x0328, 8, 8), + DIV_GATE(CLK_TOP_APLL12_CK_DIV2, "apll12_div2", "top_i2so1", 0x0320, 2, 0x0328, 8, 16), + DIV_GATE(CLK_TOP_APLL12_CK_DIV3, "apll12_div3", "top_i2so2", 0x0320, 3, 0x0328, 8, 24), + DIV_GATE(CLK_TOP_APLL12_CK_DIV4, "apll12_div4", "top_aud_iec", 0x0320, 4, 0x0334, 8, 0), + DIV_GATE(CLK_TOP_APLL12_CK_DIV9, "apll12_div9", "top_dptx", 0x0320, 9, 0x0338, 8, 8), +}; +static const struct mtk_gate_regs top0_cg_regs = { + .set_ofs = 0x238, + .clr_ofs = 0x238, + .sta_ofs = 0x238, +}; + +static const struct mtk_gate_regs top1_cg_regs = { + .set_ofs = 0x250, + .clr_ofs = 0x250, + .sta_ofs = 0x250, +}; + +#define GATE_TOP0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_TOP1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &top1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +static const struct mtk_gate top_clks[] = { + /* TOP0 */ + GATE_TOP0(CLK_TOP_CFGREG_CLOCK_EN_VPP0, "cfgreg_clock_vpp0", "top_vpp", 0), + GATE_TOP0(CLK_TOP_CFGREG_CLOCK_EN_VPP1, "cfgreg_clock_vpp1", "top_vpp", 1), + GATE_TOP0(CLK_TOP_CFGREG_CLOCK_EN_VDO0, "cfgreg_clock_vdo0", "top_vpp", 2), + GATE_TOP0(CLK_TOP_CFGREG_CLOCK_EN_VDO1, "cfgreg_clock_vdo1", "top_vpp", 3), + GATE_TOP0(CLK_TOP_CFGREG_CLOCK_ISP_AXI_GALS, "cfgreg_clock_isp_axi_gals", "top_vpp", 4), + GATE_TOP0(CLK_TOP_CFGREG_F26M_VPP0, "cfgreg_f26m_vpp0", "clk26m", 5), + GATE_TOP0(CLK_TOP_CFGREG_F26M_VPP1, "cfgreg_f26m_vpp1", "clk26m", 6), + GATE_TOP0(CLK_TOP_CFGREG_F26M_VDO0, "cfgreg_f26m_vdo0", "clk26m", 7), + GATE_TOP0(CLK_TOP_CFGREG_F26M_VDO1, "cfgreg_f26m_vdo1", "clk26m", 8), + GATE_TOP0(CLK_TOP_CFGREG_AUD_F26M_AUD, "cfgreg_aud_f26m_aud", "clk26m", 9), + GATE_TOP0(CLK_TOP_CFGREG_UNIPLL_SES, "cfgreg_unipll_ses", "univpll_d2", 15), + GATE_TOP0(CLK_TOP_CFGREG_F_PCIE_PHY_REF, "cfgreg_f_pcie_phy_ref", "clk26m", 18), + /* TOP1 */ + GATE_TOP1(CLK_TOP_SSUSB_TOP_REF, "ssusb_ref", "clk26m", 0), + GATE_TOP1(CLK_TOP_SSUSB_PHY_REF, "ssusb_phy_ref", "clk26m", 1), + GATE_TOP1(CLK_TOP_SSUSB_TOP_P1_REF, "ssusb_p1_ref", "clk26m", 2), + GATE_TOP1(CLK_TOP_SSUSB_PHY_P1_REF, "ssusb_phy_p1_ref", "clk26m", 3), + GATE_TOP1(CLK_TOP_SSUSB_TOP_P2_REF, "ssusb_p2_ref", "clk26m", 4), + GATE_TOP1(CLK_TOP_SSUSB_PHY_P2_REF, "ssusb_phy_p2_ref", "clk26m", 5), + GATE_TOP1(CLK_TOP_SSUSB_TOP_P3_REF, "ssusb_p3_ref", "clk26m", 6), + GATE_TOP1(CLK_TOP_SSUSB_PHY_P3_REF, "ssusb_phy_p3_ref", "clk26m", 7), +}; + +static const struct of_device_id of_match_clk_mt8188_topck[] = { + { .compatible = "mediatek,mt8188-topckgen" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_topck); + +/* Register mux notifier for MFG mux */ +static int clk_mt8188_reg_mfg_mux_notifier(struct device *dev, struct clk *clk) +{ + struct mtk_mux_nb *mfg_mux_nb; + + mfg_mux_nb = devm_kzalloc(dev, sizeof(*mfg_mux_nb), GFP_KERNEL); + if (!mfg_mux_nb) + return -ENOMEM; + + mfg_mux_nb->ops = &clk_mux_ops; + mfg_mux_nb->bypass_index = 0; /* Bypass to TOP_MFG_CORE_TMP */ + + return devm_mtk_clk_mux_notifier_register(dev, clk, mfg_mux_nb); +} + +static int clk_mt8188_topck_probe(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *top_clk_data; + struct device_node *node = pdev->dev.of_node; + struct clk_hw *hw; + int r; + void __iomem *base; + + top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK); + if (!top_clk_data) + return -ENOMEM; + + base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(base)) { + r = PTR_ERR(base); + goto free_top_data; + } + + r = mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), + top_clk_data); + if (r) + goto free_top_data; + + r = mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); + if (r) + goto unregister_fixed_clks; + + r = mtk_clk_register_muxes(&pdev->dev, top_mtk_muxes, + ARRAY_SIZE(top_mtk_muxes), node, + &mt8188_clk_lock, top_clk_data); + if (r) + goto unregister_factors; + + hw = devm_clk_hw_register_mux(&pdev->dev, "mfg_ck_fast_ref", mfg_fast_ref_parents, + ARRAY_SIZE(mfg_fast_ref_parents), CLK_SET_RATE_PARENT, + (base + 0x250), 8, 1, 0, &mt8188_clk_lock); + if (IS_ERR(hw)) { + r = PTR_ERR(hw); + goto unregister_muxes; + } + top_clk_data->hws[CLK_TOP_MFG_CK_FAST_REF] = hw; + + r = clk_mt8188_reg_mfg_mux_notifier(&pdev->dev, + top_clk_data->hws[CLK_TOP_MFG_CK_FAST_REF]->clk); + if (r) + goto unregister_muxes; + + r = mtk_clk_register_composites(&pdev->dev, top_adj_divs, + ARRAY_SIZE(top_adj_divs), base, + &mt8188_clk_lock, top_clk_data); + if (r) + goto unregister_muxes; + + r = mtk_clk_register_gates(&pdev->dev, node, top_clks, + ARRAY_SIZE(top_clks), top_clk_data); + if (r) + goto unregister_composite_divs; + + r = of_clk_add_hw_provider(node, of_clk_hw_onecell_get, top_clk_data); + if (r) + goto unregister_gates; + + platform_set_drvdata(pdev, top_clk_data); + + return r; + +unregister_gates: + mtk_clk_unregister_gates(top_clks, ARRAY_SIZE(top_clks), top_clk_data); +unregister_composite_divs: + mtk_clk_unregister_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), top_clk_data); +unregister_muxes: + mtk_clk_unregister_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), top_clk_data); +unregister_factors: + mtk_clk_unregister_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); +unregister_fixed_clks: + mtk_clk_unregister_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), top_clk_data); +free_top_data: + mtk_free_clk_data(top_clk_data); + return r; +} + +static int clk_mt8188_topck_remove(struct platform_device *pdev) +{ + struct clk_hw_onecell_data *top_clk_data = platform_get_drvdata(pdev); + struct device_node *node = pdev->dev.of_node; + + of_clk_del_provider(node); + mtk_clk_unregister_gates(top_clks, ARRAY_SIZE(top_clks), top_clk_data); + mtk_clk_unregister_composites(top_adj_divs, ARRAY_SIZE(top_adj_divs), top_clk_data); + mtk_clk_unregister_muxes(top_mtk_muxes, ARRAY_SIZE(top_mtk_muxes), top_clk_data); + mtk_clk_unregister_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data); + mtk_clk_unregister_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks), top_clk_data); + mtk_free_clk_data(top_clk_data); + + return 0; +} + +static struct platform_driver clk_mt8188_topck_drv = { + .probe = clk_mt8188_topck_probe, + .remove = clk_mt8188_topck_remove, + .driver = { + .name = "clk-mt8188-topck", + .of_match_table = of_match_clk_mt8188_topck, + }, +}; +module_platform_driver(clk_mt8188_topck_drv); +MODULE_LICENSE("GPL"); -- GitLab From 643c06dc535be1501ce7e3092a1d3ad0da7296bb Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:06 +0800 Subject: [PATCH 1831/5631] clk: mediatek: Add MT8188 peripheral clock support Add MT8188 peripheral clock controller which provides clock gate control for ethernet/flashif/pcie/ssusb. Signed-off-by: Garmin.Chang Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-5-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 3 +- drivers/clk/mediatek/clk-mt8188-peri_ao.c | 59 +++++++++++++++++++++++ 2 files changed, 61 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-peri_ao.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 8afd30f6b3cc..5f347b4f9b2d 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -100,7 +100,8 @@ obj-$(CONFIG_COMMON_CLK_MT8186_MMSYS) += clk-mt8186-mm.o obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o -obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o +obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ + clk-mt8188-peri_ao.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-peri_ao.c b/drivers/clk/mediatek/clk-mt8188-peri_ao.c new file mode 100644 index 000000000000..b00e1ae8bd26 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-peri_ao.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs peri_ao_cg_regs = { + .set_ofs = 0x10, + .clr_ofs = 0x14, + .sta_ofs = 0x18, +}; + +#define GATE_PERI_AO(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &peri_ao_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate peri_ao_clks[] = { + GATE_PERI_AO(CLK_PERI_AO_ETHERNET, "peri_ao_ethernet", "top_axi", 0), + GATE_PERI_AO(CLK_PERI_AO_ETHERNET_BUS, "peri_ao_ethernet_bus", "top_axi", 1), + GATE_PERI_AO(CLK_PERI_AO_FLASHIF_BUS, "peri_ao_flashif_bus", "top_axi", 3), + GATE_PERI_AO(CLK_PERI_AO_FLASHIF_26M, "peri_ao_flashif_26m", "clk26m", 4), + GATE_PERI_AO(CLK_PERI_AO_FLASHIFLASHCK, "peri_ao_flashiflashck", "top_spinor", 5), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_2P_BUS, "peri_ao_ssusb_2p_bus", "top_usb_top_2p", 9), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_2P_XHCI, "peri_ao_ssusb_2p_xhci", "top_ssusb_xhci_2p", 10), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_3P_BUS, "peri_ao_ssusb_3p_bus", "top_usb_top_3p", 11), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_3P_XHCI, "peri_ao_ssusb_3p_xhci", "top_ssusb_xhci_3p", 12), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_BUS, "peri_ao_ssusb_bus", "top_usb_top", 13), + GATE_PERI_AO(CLK_PERI_AO_SSUSB_XHCI, "peri_ao_ssusb_xhci", "top_ssusb_xhci", 14), + GATE_PERI_AO(CLK_PERI_AO_ETHERNET_MAC, "peri_ao_ethernet_mac_clk", "top_snps_eth_250m", 16), + GATE_PERI_AO(CLK_PERI_AO_PCIE_P0_FMEM, "peri_ao_pcie_p0_fmem", "hd_466m_fmem_ck", 24), +}; + +static const struct mtk_clk_desc peri_ao_desc = { + .clks = peri_ao_clks, + .num_clks = ARRAY_SIZE(peri_ao_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_peri_ao[] = { + { .compatible = "mediatek,mt8188-pericfg-ao", .data = &peri_ao_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_peri_ao); + +static struct platform_driver clk_mt8188_peri_ao_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-peri_ao", + .of_match_table = of_match_clk_mt8188_peri_ao, + }, +}; +module_platform_driver(clk_mt8188_peri_ao_drv); +MODULE_LICENSE("GPL"); -- GitLab From fce4c7a22861eb374eac86b7f3d0642878182df0 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:07 +0800 Subject: [PATCH 1832/5631] clk: mediatek: Add MT8188 infrastructure clock support Add MT8188 infrastructure clock controller which provides clock gate control for basic IP like pwm, uart, spi and so on. Signed-off-by: Garmin.Chang Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-6-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8188-infra_ao.c | 199 +++++++++++++++++++++ 2 files changed, 200 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-infra_ao.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 5f347b4f9b2d..1a642510ce38 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -101,7 +101,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_VDECSYS) += clk-mt8186-vdec.o obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ - clk-mt8188-peri_ao.o + clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-infra_ao.c b/drivers/clk/mediatek/clk-mt8188-infra_ao.c new file mode 100644 index 000000000000..91c35db40b4e --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-infra_ao.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs infra_ao0_cg_regs = { + .set_ofs = 0x80, + .clr_ofs = 0x84, + .sta_ofs = 0x90, +}; + +static const struct mtk_gate_regs infra_ao1_cg_regs = { + .set_ofs = 0x88, + .clr_ofs = 0x8c, + .sta_ofs = 0x94, +}; + +static const struct mtk_gate_regs infra_ao2_cg_regs = { + .set_ofs = 0xa4, + .clr_ofs = 0xa8, + .sta_ofs = 0xac, +}; + +static const struct mtk_gate_regs infra_ao3_cg_regs = { + .set_ofs = 0xc0, + .clr_ofs = 0xc4, + .sta_ofs = 0xc8, +}; + +static const struct mtk_gate_regs infra_ao4_cg_regs = { + .set_ofs = 0xe0, + .clr_ofs = 0xe4, + .sta_ofs = 0xe8, +}; + +#define GATE_INFRA_AO0_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_ao0_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flag) + +#define GATE_INFRA_AO0(_id, _name, _parent, _shift) \ + GATE_INFRA_AO0_FLAGS(_id, _name, _parent, _shift, 0) + +#define GATE_INFRA_AO1_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_ao1_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flag) + +#define GATE_INFRA_AO1(_id, _name, _parent, _shift) \ + GATE_INFRA_AO1_FLAGS(_id, _name, _parent, _shift, 0) + +#define GATE_INFRA_AO2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &infra_ao2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_INFRA_AO2_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_ao2_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flag) + +#define GATE_INFRA_AO3_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_ao3_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flag) + +#define GATE_INFRA_AO3(_id, _name, _parent, _shift) \ + GATE_INFRA_AO3_FLAGS(_id, _name, _parent, _shift, 0) + +#define GATE_INFRA_AO4_FLAGS(_id, _name, _parent, _shift, _flag) \ + GATE_MTK_FLAGS(_id, _name, _parent, &infra_ao4_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flag) + +#define GATE_INFRA_AO4(_id, _name, _parent, _shift) \ + GATE_INFRA_AO4_FLAGS(_id, _name, _parent, _shift, 0) + +static const struct mtk_gate infra_ao_clks[] = { + /* INFRA_AO0 */ + GATE_INFRA_AO0(CLK_INFRA_AO_PMIC_TMR, "infra_ao_pmic_tmr", "top_pwrap_ulposc", 0), + GATE_INFRA_AO0(CLK_INFRA_AO_PMIC_AP, "infra_ao_pmic_ap", "top_pwrap_ulposc", 1), + GATE_INFRA_AO0(CLK_INFRA_AO_PMIC_MD, "infra_ao_pmic_md", "top_pwrap_ulposc", 2), + GATE_INFRA_AO0(CLK_INFRA_AO_PMIC_CONN, "infra_ao_pmic_conn", "top_pwrap_ulposc", 3), + /* infra_ao_sej is main clock is for secure engine with JTAG support */ + GATE_INFRA_AO0_FLAGS(CLK_INFRA_AO_SEJ, "infra_ao_sej", "top_axi", 5, CLK_IS_CRITICAL), + GATE_INFRA_AO0(CLK_INFRA_AO_APXGPT, "infra_ao_apxgpt", "top_axi", 6), + GATE_INFRA_AO0(CLK_INFRA_AO_GCE, "infra_ao_gce", "top_axi", 8), + GATE_INFRA_AO0(CLK_INFRA_AO_GCE2, "infra_ao_gce2", "top_axi", 9), + GATE_INFRA_AO0(CLK_INFRA_AO_THERM, "infra_ao_therm", "top_axi", 10), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM_HCLK, "infra_ao_pwm_h", "top_axi", 15), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM1, "infra_ao_pwm1", "top_pwm", 16), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM2, "infra_ao_pwm2", "top_pwm", 17), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM3, "infra_ao_pwm3", "top_pwm", 18), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM4, "infra_ao_pwm4", "top_pwm", 19), + GATE_INFRA_AO0(CLK_INFRA_AO_PWM, "infra_ao_pwm", "top_pwm", 21), + GATE_INFRA_AO0(CLK_INFRA_AO_UART0, "infra_ao_uart0", "top_uart", 22), + GATE_INFRA_AO0(CLK_INFRA_AO_UART1, "infra_ao_uart1", "top_uart", 23), + GATE_INFRA_AO0(CLK_INFRA_AO_UART2, "infra_ao_uart2", "top_uart", 24), + GATE_INFRA_AO0(CLK_INFRA_AO_UART3, "infra_ao_uart3", "top_uart", 25), + GATE_INFRA_AO0(CLK_INFRA_AO_UART4, "infra_ao_uart4", "top_uart", 26), + GATE_INFRA_AO0(CLK_INFRA_AO_GCE_26M, "infra_ao_gce_26m", "clk26m", 27), + GATE_INFRA_AO0(CLK_INFRA_AO_CQ_DMA_FPC, "infra_ao_dma", "pad_fpc_ck", 28), + GATE_INFRA_AO0(CLK_INFRA_AO_UART5, "infra_ao_uart5", "top_uart", 29), + /* INFRA_AO1 */ + GATE_INFRA_AO1(CLK_INFRA_AO_HDMI_26M, "infra_ao_hdmi_26m", "clk26m", 0), + GATE_INFRA_AO1(CLK_INFRA_AO_SPI0, "infra_ao_spi0", "top_spi", 1), + GATE_INFRA_AO1(CLK_INFRA_AO_MSDC0, "infra_ao_msdc0", "top_msdc5hclk", 2), + GATE_INFRA_AO1(CLK_INFRA_AO_MSDC1, "infra_ao_msdc1", "top_axi", 4), + GATE_INFRA_AO1(CLK_INFRA_AO_MSDC2, "infra_ao_msdc2", "top_axi", 5), + GATE_INFRA_AO1(CLK_INFRA_AO_MSDC0_SRC, "infra_ao_msdc0_clk", "top_msdc50_0", 6), + /* infra_ao_dvfsrc is for internal DVFS usage, should not be handled by Linux. */ + GATE_INFRA_AO1_FLAGS(CLK_INFRA_AO_DVFSRC, "infra_ao_dvfsrc", + "clk26m", 7, CLK_IS_CRITICAL), + GATE_INFRA_AO1(CLK_INFRA_AO_TRNG, "infra_ao_trng", "top_axi", 9), + GATE_INFRA_AO1(CLK_INFRA_AO_AUXADC, "infra_ao_auxadc", "clk26m", 10), + GATE_INFRA_AO1(CLK_INFRA_AO_CPUM, "infra_ao_cpum", "top_axi", 11), + GATE_INFRA_AO1(CLK_INFRA_AO_HDMI_32K, "infra_ao_hdmi_32k", "clk32k", 12), + GATE_INFRA_AO1(CLK_INFRA_AO_CEC_66M_HCLK, "infra_ao_cec_66m_hclk", "top_axi", 13), + GATE_INFRA_AO1(CLK_INFRA_AO_PCIE_TL_26M, "infra_ao_pcie_tl_26m", "clk26m", 15), + GATE_INFRA_AO1(CLK_INFRA_AO_MSDC1_SRC, "infra_ao_msdc1_clk", "top_msdc30_1", 16), + GATE_INFRA_AO1(CLK_INFRA_AO_CEC_66M_BCLK, "infra_ao_cec_66m_bclk", "top_axi", 17), + GATE_INFRA_AO1(CLK_INFRA_AO_PCIE_TL_96M, "infra_ao_pcie_tl_96m", "top_tl", 18), + /* infra_ao_dapc is for device access permission control module */ + GATE_INFRA_AO1_FLAGS(CLK_INFRA_AO_DEVICE_APC, "infra_ao_dapc", + "top_axi", 20, CLK_IS_CRITICAL), + GATE_INFRA_AO1(CLK_INFRA_AO_ECC_66M_HCLK, "infra_ao_ecc_66m_hclk", "top_axi", 23), + GATE_INFRA_AO1(CLK_INFRA_AO_DEBUGSYS, "infra_ao_debugsys", "top_axi", 24), + GATE_INFRA_AO1(CLK_INFRA_AO_AUDIO, "infra_ao_audio", "top_axi", 25), + GATE_INFRA_AO1(CLK_INFRA_AO_PCIE_TL_32K, "infra_ao_pcie_tl_32k", "clk32k", 26), + GATE_INFRA_AO1(CLK_INFRA_AO_DBG_TRACE, "infra_ao_dbg_trace", "top_axi", 29), + GATE_INFRA_AO1(CLK_INFRA_AO_DRAMC_F26M, "infra_ao_dramc26", "clk26m", 31), + /* INFRA_AO2 */ + GATE_INFRA_AO2(CLK_INFRA_AO_IRTX, "infra_ao_irtx", "top_axi", 0), + GATE_INFRA_AO2(CLK_INFRA_AO_DISP_PWM, "infra_ao_disp_pwm", "top_disp_pwm0", 2), + GATE_INFRA_AO2(CLK_INFRA_AO_CLDMA_BCLK, "infra_ao_cldmabclk", "top_axi", 3), + GATE_INFRA_AO2(CLK_INFRA_AO_AUDIO_26M_BCLK, "infra_ao_audio26m", "clk26m", 4), + GATE_INFRA_AO2(CLK_INFRA_AO_SPI1, "infra_ao_spi1", "top_spi", 6), + GATE_INFRA_AO2(CLK_INFRA_AO_SPI2, "infra_ao_spi2", "top_spi", 9), + GATE_INFRA_AO2(CLK_INFRA_AO_SPI3, "infra_ao_spi3", "top_spi", 10), + GATE_INFRA_AO2_FLAGS(CLK_INFRA_AO_FSSPM, "infra_ao_fsspm", + "top_sspm", 15, CLK_IS_CRITICAL), + GATE_INFRA_AO2_FLAGS(CLK_INFRA_AO_SSPM_BUS_HCLK, "infra_ao_sspm_hclk", + "top_axi", 17, CLK_IS_CRITICAL), + GATE_INFRA_AO2(CLK_INFRA_AO_APDMA_BCLK, "infra_ao_apdma_bclk", "top_axi", 18), + GATE_INFRA_AO2(CLK_INFRA_AO_SPI4, "infra_ao_spi4", "top_spi", 25), + GATE_INFRA_AO2(CLK_INFRA_AO_SPI5, "infra_ao_spi5", "top_spi", 26), + GATE_INFRA_AO2(CLK_INFRA_AO_CQ_DMA, "infra_ao_cq_dma", "top_axi", 27), + /* INFRA_AO3 */ + GATE_INFRA_AO3(CLK_INFRA_AO_MSDC0_SELF, "infra_ao_msdc0sf", "top_msdc50_0", 0), + GATE_INFRA_AO3(CLK_INFRA_AO_MSDC1_SELF, "infra_ao_msdc1sf", "top_msdc50_0", 1), + GATE_INFRA_AO3(CLK_INFRA_AO_MSDC2_SELF, "infra_ao_msdc2sf", "top_msdc50_0", 2), + GATE_INFRA_AO3(CLK_INFRA_AO_I2S_DMA, "infra_ao_i2s_dma", "top_axi", 5), + GATE_INFRA_AO3(CLK_INFRA_AO_AP_MSDC0, "infra_ao_ap_msdc0", "top_msdc50_0", 7), + GATE_INFRA_AO3(CLK_INFRA_AO_MD_MSDC0, "infra_ao_md_msdc0", "top_msdc50_0", 8), + GATE_INFRA_AO3(CLK_INFRA_AO_MSDC30_2, "infra_ao_msdc30_2", "top_msdc30_2", 9), + GATE_INFRA_AO3(CLK_INFRA_AO_GCPU, "infra_ao_gcpu", "top_gcpu", 10), + GATE_INFRA_AO3(CLK_INFRA_AO_PCIE_PERI_26M, "infra_ao_pcie_peri_26m", "clk26m", 15), + GATE_INFRA_AO3(CLK_INFRA_AO_GCPU_66M_BCLK, "infra_ao_gcpu_66m_bclk", "top_axi", 16), + GATE_INFRA_AO3(CLK_INFRA_AO_GCPU_133M_BCLK, "infra_ao_gcpu_133m_bclk", "top_axi", 17), + GATE_INFRA_AO3(CLK_INFRA_AO_DISP_PWM1, "infra_ao_disp_pwm1", "top_disp_pwm1", 20), + GATE_INFRA_AO3(CLK_INFRA_AO_FBIST2FPC, "infra_ao_fbist2fpc", "top_msdc50_0", 24), + /* infra_ao_dapc_sync is for device access permission control module */ + GATE_INFRA_AO3_FLAGS(CLK_INFRA_AO_DEVICE_APC_SYNC, "infra_ao_dapc_sync", + "top_axi", 25, CLK_IS_CRITICAL), + GATE_INFRA_AO3(CLK_INFRA_AO_PCIE_P1_PERI_26M, "infra_ao_pcie_p1_peri_26m", "clk26m", 26), + /* INFRA_AO4 */ + /* infra_ao_133m_mclk_set/infra_ao_66m_mclk_set are main clocks of peripheral */ + GATE_INFRA_AO4_FLAGS(CLK_INFRA_AO_133M_MCLK_CK, "infra_ao_133m_mclk_set", + "top_axi", 0, CLK_IS_CRITICAL), + GATE_INFRA_AO4_FLAGS(CLK_INFRA_AO_66M_MCLK_CK, "infra_ao_66m_mclk_set", + "top_axi", 1, CLK_IS_CRITICAL), + GATE_INFRA_AO4(CLK_INFRA_AO_PCIE_PL_P_250M_P0, "infra_ao_pcie_pl_p_250m_p0", + "pextp_pipe", 7), + GATE_INFRA_AO4(CLK_INFRA_AO_RG_AES_MSDCFDE_CK_0P, + "infra_ao_aes_msdcfde_0p", "top_aes_msdcfde", 18), +}; + +static const struct mtk_clk_desc infra_ao_desc = { + .clks = infra_ao_clks, + .num_clks = ARRAY_SIZE(infra_ao_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_infra_ao[] = { + { .compatible = "mediatek,mt8188-infracfg-ao", .data = &infra_ao_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_infra_ao); + +static struct platform_driver clk_mt8188_infra_ao_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-infra_ao", + .of_match_table = of_match_clk_mt8188_infra_ao, + }, +}; +module_platform_driver(clk_mt8188_infra_ao_drv); +MODULE_LICENSE("GPL"); -- GitLab From 9b42835684a5e8fd1f5bcf66050c3be194790aee Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:08 +0800 Subject: [PATCH 1833/5631] clk: mediatek: Add MT8188 camsys clock support Add MT8188 camsys clock controllers which provide clock gate control for camera IP blocks. Signed-off-by: Garmin.Chang Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-7-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-cam.c | 120 ++++++++++++++++++++++++++ 3 files changed, 128 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-cam.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 681d392620c5..9170f76a8ee7 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -692,6 +692,13 @@ config COMMON_CLK_MT8188 help This driver supports MediaTek MT8188 clocks. +config COMMON_CLK_MT8188_CAMSYS + tristate "Clock driver for MediaTek MT8188 camsys" + depends on COMMON_CLK_MT8188_VPPSYS + default COMMON_CLK_MT8188_VPPSYS + help + This driver supports MediaTek MT8188 camsys and camsys_raw clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 1a642510ce38..3a2a35c54101 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -102,6 +102,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o +obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-cam.c b/drivers/clk/mediatek/clk-mt8188-cam.c new file mode 100644 index 000000000000..c5a3856bd223 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-cam.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs cam_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_CAM(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &cam_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate cam_main_clks[] = { + GATE_CAM(CLK_CAM_MAIN_LARB13, "cam_main_larb13", "top_cam", 0), + GATE_CAM(CLK_CAM_MAIN_LARB14, "cam_main_larb14", "top_cam", 1), + GATE_CAM(CLK_CAM_MAIN_CAM, "cam_main_cam", "top_cam", 2), + GATE_CAM(CLK_CAM_MAIN_CAM_SUBA, "cam_main_cam_suba", "top_cam", 3), + GATE_CAM(CLK_CAM_MAIN_CAM_SUBB, "cam_main_cam_subb", "top_cam", 4), + GATE_CAM(CLK_CAM_MAIN_CAMTG, "cam_main_camtg", "top_cam", 7), + GATE_CAM(CLK_CAM_MAIN_SENINF, "cam_main_seninf", "top_cam", 8), + GATE_CAM(CLK_CAM_MAIN_GCAMSVA, "cam_main_gcamsva", "top_cam", 9), + GATE_CAM(CLK_CAM_MAIN_GCAMSVB, "cam_main_gcamsvb", "top_cam", 10), + GATE_CAM(CLK_CAM_MAIN_GCAMSVC, "cam_main_gcamsvc", "top_cam", 11), + GATE_CAM(CLK_CAM_MAIN_GCAMSVD, "cam_main_gcamsvd", "top_cam", 12), + GATE_CAM(CLK_CAM_MAIN_GCAMSVE, "cam_main_gcamsve", "top_cam", 13), + GATE_CAM(CLK_CAM_MAIN_GCAMSVF, "cam_main_gcamsvf", "top_cam", 14), + GATE_CAM(CLK_CAM_MAIN_GCAMSVG, "cam_main_gcamsvg", "top_cam", 15), + GATE_CAM(CLK_CAM_MAIN_GCAMSVH, "cam_main_gcamsvh", "top_cam", 16), + GATE_CAM(CLK_CAM_MAIN_GCAMSVI, "cam_main_gcamsvi", "top_cam", 17), + GATE_CAM(CLK_CAM_MAIN_GCAMSVJ, "cam_main_gcamsvj", "top_cam", 18), + GATE_CAM(CLK_CAM_MAIN_CAMSV_TOP, "cam_main_camsv", "top_cam", 19), + GATE_CAM(CLK_CAM_MAIN_CAMSV_CQ_A, "cam_main_camsv_cq_a", "top_cam", 20), + GATE_CAM(CLK_CAM_MAIN_CAMSV_CQ_B, "cam_main_camsv_cq_b", "top_cam", 21), + GATE_CAM(CLK_CAM_MAIN_CAMSV_CQ_C, "cam_main_camsv_cq_c", "top_cam", 22), + GATE_CAM(CLK_CAM_MAIN_FAKE_ENG, "cam_main_fake_eng", "top_cam", 28), + GATE_CAM(CLK_CAM_MAIN_CAM2MM0_GALS, "cam_main_cam2mm0_gals", "top_cam", 29), + GATE_CAM(CLK_CAM_MAIN_CAM2MM1_GALS, "cam_main_cam2mm1_gals", "top_cam", 30), + GATE_CAM(CLK_CAM_MAIN_CAM2SYS_GALS, "cam_main_cam2sys_gals", "top_cam", 31), +}; + +static const struct mtk_gate cam_rawa_clks[] = { + GATE_CAM(CLK_CAM_RAWA_LARBX, "cam_rawa_larbx", "top_cam", 0), + GATE_CAM(CLK_CAM_RAWA_CAM, "cam_rawa_cam", "top_cam", 1), + GATE_CAM(CLK_CAM_RAWA_CAMTG, "cam_rawa_camtg", "top_cam", 2), +}; + +static const struct mtk_gate cam_rawb_clks[] = { + GATE_CAM(CLK_CAM_RAWB_LARBX, "cam_rawb_larbx", "top_cam", 0), + GATE_CAM(CLK_CAM_RAWB_CAM, "cam_rawb_cam", "top_cam", 1), + GATE_CAM(CLK_CAM_RAWB_CAMTG, "cam_rawb_camtg", "top_cam", 2), +}; + +static const struct mtk_gate cam_yuva_clks[] = { + GATE_CAM(CLK_CAM_YUVA_LARBX, "cam_yuva_larbx", "top_cam", 0), + GATE_CAM(CLK_CAM_YUVA_CAM, "cam_yuva_cam", "top_cam", 1), + GATE_CAM(CLK_CAM_YUVA_CAMTG, "cam_yuva_camtg", "top_cam", 2), +}; + +static const struct mtk_gate cam_yuvb_clks[] = { + GATE_CAM(CLK_CAM_YUVB_LARBX, "cam_yuvb_larbx", "top_cam", 0), + GATE_CAM(CLK_CAM_YUVB_CAM, "cam_yuvb_cam", "top_cam", 1), + GATE_CAM(CLK_CAM_YUVB_CAMTG, "cam_yuvb_camtg", "top_cam", 2), +}; + +static const struct mtk_clk_desc cam_main_desc = { + .clks = cam_main_clks, + .num_clks = ARRAY_SIZE(cam_main_clks), +}; + +static const struct mtk_clk_desc cam_rawa_desc = { + .clks = cam_rawa_clks, + .num_clks = ARRAY_SIZE(cam_rawa_clks), +}; + +static const struct mtk_clk_desc cam_rawb_desc = { + .clks = cam_rawb_clks, + .num_clks = ARRAY_SIZE(cam_rawb_clks), +}; + +static const struct mtk_clk_desc cam_yuva_desc = { + .clks = cam_yuva_clks, + .num_clks = ARRAY_SIZE(cam_yuva_clks), +}; + +static const struct mtk_clk_desc cam_yuvb_desc = { + .clks = cam_yuvb_clks, + .num_clks = ARRAY_SIZE(cam_yuvb_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_cam[] = { + { .compatible = "mediatek,mt8188-camsys", .data = &cam_main_desc }, + { .compatible = "mediatek,mt8188-camsys-rawa", .data = &cam_rawa_desc }, + { .compatible = "mediatek,mt8188-camsys-rawb", .data = &cam_rawb_desc }, + { .compatible = "mediatek,mt8188-camsys-yuva", .data = &cam_yuva_desc }, + { .compatible = "mediatek,mt8188-camsys-yuvb", .data = &cam_yuvb_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_cam); + +static struct platform_driver clk_mt8188_cam_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-cam", + .of_match_table = of_match_clk_mt8188_cam, + }, +}; + +module_platform_driver(clk_mt8188_cam_drv); +MODULE_LICENSE("GPL"); -- GitLab From 87d06fa9d21e6e38c41132c5f546531f6b755f8d Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:09 +0800 Subject: [PATCH 1834/5631] clk: mediatek: Add MT8188 ccusys clock support Add MT8188 ccusys clock controller which provides clock gate control in Camera Computing Unit. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-8-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8188-ccu.c | 50 +++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-ccu.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 3a2a35c54101..fc4faee04636 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -102,7 +102,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o -obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o +obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-ccu.c b/drivers/clk/mediatek/clk-mt8188-ccu.c new file mode 100644 index 000000000000..ebc0d3aeee11 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-ccu.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs ccu_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_CCU(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ccu_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate ccu_clks[] = { + GATE_CCU(CLK_CCU_LARB27, "ccu_larb27", "top_ccu", 0), + GATE_CCU(CLK_CCU_AHB, "ccu_ahb", "top_ccu", 1), + GATE_CCU(CLK_CCU_CCU0, "ccu_ccu0", "top_ccu", 2), +}; + +static const struct mtk_clk_desc ccu_desc = { + .clks = ccu_clks, + .num_clks = ARRAY_SIZE(ccu_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_ccu[] = { + { .compatible = "mediatek,mt8188-ccusys", .data = &ccu_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_ccu); + +static struct platform_driver clk_mt8188_ccu_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-ccu", + .of_match_table = of_match_clk_mt8188_ccu, + }, +}; + +module_platform_driver(clk_mt8188_ccu_drv); +MODULE_LICENSE("GPL"); -- GitLab From b281039a7b4939c62196fd2c690a9a13a093ed2e Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:10 +0800 Subject: [PATCH 1835/5631] clk: mediatek: Add MT8188 imgsys clock support Add MT8188 imgsys clock controllers which provide clock gate control for image IP blocks. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-9-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-img.c | 112 ++++++++++++++++++++++++++ 3 files changed, 120 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-img.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 9170f76a8ee7..74f7d4540718 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -699,6 +699,13 @@ config COMMON_CLK_MT8188_CAMSYS help This driver supports MediaTek MT8188 camsys and camsys_raw clocks. +config COMMON_CLK_MT8188_IMGSYS + tristate "Clock driver for MediaTek MT8188 imgsys" + depends on COMMON_CLK_MT8188_VPPSYS + default COMMON_CLK_MT8188_VPPSYS + help + This driver supports MediaTek MT8188 imgsys and imgsys2 clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index fc4faee04636..6e72ff79b800 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o +obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-img.c b/drivers/clk/mediatek/clk-mt8188-img.c new file mode 100644 index 000000000000..b4622875e14c --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-img.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs imgsys_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_IMGSYS(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &imgsys_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate imgsys_main_clks[] = { + GATE_IMGSYS(CLK_IMGSYS_MAIN_LARB9, "imgsys_main_larb9", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS_MAIN_TRAW0, "imgsys_main_traw0", "top_img", 1), + GATE_IMGSYS(CLK_IMGSYS_MAIN_TRAW1, "imgsys_main_traw1", "top_img", 2), + GATE_IMGSYS(CLK_IMGSYS_MAIN_VCORE_GALS, "imgsys_main_vcore_gals", "top_img", 3), + GATE_IMGSYS(CLK_IMGSYS_MAIN_DIP0, "imgsys_main_dip0", "top_img", 8), + GATE_IMGSYS(CLK_IMGSYS_MAIN_WPE0, "imgsys_main_wpe0", "top_img", 9), + GATE_IMGSYS(CLK_IMGSYS_MAIN_IPE, "imgsys_main_ipe", "top_img", 10), + GATE_IMGSYS(CLK_IMGSYS_MAIN_WPE1, "imgsys_main_wpe1", "top_img", 12), + GATE_IMGSYS(CLK_IMGSYS_MAIN_WPE2, "imgsys_main_wpe2", "top_img", 13), + GATE_IMGSYS(CLK_IMGSYS_MAIN_GALS, "imgsys_main_gals", "top_img", 31), +}; + +static const struct mtk_gate imgsys_wpe1_clks[] = { + GATE_IMGSYS(CLK_IMGSYS_WPE1_LARB11, "imgsys_wpe1_larb11", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS_WPE1, "imgsys_wpe1", "top_img", 1), +}; + +static const struct mtk_gate imgsys_wpe2_clks[] = { + GATE_IMGSYS(CLK_IMGSYS_WPE2_LARB11, "imgsys_wpe2_larb11", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS_WPE2, "imgsys_wpe2", "top_img", 1), +}; + +static const struct mtk_gate imgsys_wpe3_clks[] = { + GATE_IMGSYS(CLK_IMGSYS_WPE3_LARB11, "imgsys_wpe3_larb11", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS_WPE3, "imgsys_wpe3", "top_img", 1), +}; + +static const struct mtk_gate imgsys1_dip_top_clks[] = { + GATE_IMGSYS(CLK_IMGSYS1_DIP_TOP_LARB10, "imgsys1_dip_larb10", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS1_DIP_TOP_DIP_TOP, "imgsys1_dip_dip_top", "top_img", 1), +}; + +static const struct mtk_gate imgsys1_dip_nr_clks[] = { + GATE_IMGSYS(CLK_IMGSYS1_DIP_NR_LARB15, "imgsys1_dip_nr_larb15", "top_img", 0), + GATE_IMGSYS(CLK_IMGSYS1_DIP_NR_DIP_NR, "imgsys1_dip_nr_dip_nr", "top_img", 1), +}; + +static const struct mtk_clk_desc imgsys_main_desc = { + .clks = imgsys_main_clks, + .num_clks = ARRAY_SIZE(imgsys_main_clks), +}; + +static const struct mtk_clk_desc imgsys_wpe1_desc = { + .clks = imgsys_wpe1_clks, + .num_clks = ARRAY_SIZE(imgsys_wpe1_clks), +}; + +static const struct mtk_clk_desc imgsys_wpe2_desc = { + .clks = imgsys_wpe2_clks, + .num_clks = ARRAY_SIZE(imgsys_wpe2_clks), +}; + +static const struct mtk_clk_desc imgsys_wpe3_desc = { + .clks = imgsys_wpe3_clks, + .num_clks = ARRAY_SIZE(imgsys_wpe3_clks), +}; + +static const struct mtk_clk_desc imgsys1_dip_top_desc = { + .clks = imgsys1_dip_top_clks, + .num_clks = ARRAY_SIZE(imgsys1_dip_top_clks), +}; + +static const struct mtk_clk_desc imgsys1_dip_nr_desc = { + .clks = imgsys1_dip_nr_clks, + .num_clks = ARRAY_SIZE(imgsys1_dip_nr_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_imgsys_main[] = { + { .compatible = "mediatek,mt8188-imgsys", .data = &imgsys_main_desc }, + { .compatible = "mediatek,mt8188-imgsys-wpe1", .data = &imgsys_wpe1_desc }, + { .compatible = "mediatek,mt8188-imgsys-wpe2", .data = &imgsys_wpe2_desc }, + { .compatible = "mediatek,mt8188-imgsys-wpe3", .data = &imgsys_wpe3_desc }, + { .compatible = "mediatek,mt8188-imgsys1-dip-top", .data = &imgsys1_dip_top_desc }, + { .compatible = "mediatek,mt8188-imgsys1-dip-nr", .data = &imgsys1_dip_nr_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_imgsys_main); + +static struct platform_driver clk_mt8188_imgsys_main_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-imgsys_main", + .of_match_table = of_match_clk_mt8188_imgsys_main, + }, +}; + +module_platform_driver(clk_mt8188_imgsys_main_drv); +MODULE_LICENSE("GPL"); -- GitLab From 49c9abe1c89203d69875a5c90bc52bf308fab5b4 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:11 +0800 Subject: [PATCH 1836/5631] clk: mediatek: Add MT8188 ipesys clock support Add MT8188 ipesys clock controller which provides clock gate control for Image Process Engine. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-10-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-ipe.c | 52 +++++++++++++++++++++++++++ 3 files changed, 60 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-ipe.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 74f7d4540718..4f75904852be 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -706,6 +706,13 @@ config COMMON_CLK_MT8188_IMGSYS help This driver supports MediaTek MT8188 imgsys and imgsys2 clocks. +config COMMON_CLK_MT8188_IPESYS + tristate "Clock driver for MediaTek MT8188 ipesys" + depends on COMMON_CLK_MT8188_IMGSYS + default COMMON_CLK_MT8188_IMGSYS + help + This driver supports MediaTek MT8188 ipesys clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 6e72ff79b800..c36e3d36ed67 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o +obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-ipe.c b/drivers/clk/mediatek/clk-mt8188-ipe.c new file mode 100644 index 000000000000..c07afbd1429e --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-ipe.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs ipe_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_IPE(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &ipe_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate ipe_clks[] = { + GATE_IPE(CLK_IPE_DPE, "ipe_dpe", "top_ipe", 0), + GATE_IPE(CLK_IPE_FDVT, "ipe_fdvt", "top_ipe", 1), + GATE_IPE(CLK_IPE_ME, "ipe_me", "top_ipe", 2), + GATE_IPE(CLK_IPESYS_TOP, "ipesys_top", "top_ipe", 3), + GATE_IPE(CLK_IPE_SMI_LARB12, "ipe_smi_larb12", "top_ipe", 4), +}; + +static const struct mtk_clk_desc ipe_desc = { + .clks = ipe_clks, + .num_clks = ARRAY_SIZE(ipe_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_ipe[] = { + { .compatible = "mediatek,mt8188-ipesys", .data = &ipe_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_ipe); + +static struct platform_driver clk_mt8188_ipe_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-ipe", + .of_match_table = of_match_clk_mt8188_ipe, + }, +}; + +module_platform_driver(clk_mt8188_ipe_drv); +MODULE_LICENSE("GPL"); -- GitLab From 3e26f30fe42d76d0163416e4ea198901fa02fc19 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:12 +0800 Subject: [PATCH 1837/5631] clk: mediatek: Add MT8188 mfgcfg clock support Add MT8188 mfg clock controller which provides clock gate control for GPU. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-11-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-mfg.c | 49 +++++++++++++++++++++++++++ 3 files changed, 57 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-mfg.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 4f75904852be..d1239c7ac9f4 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -713,6 +713,13 @@ config COMMON_CLK_MT8188_IPESYS help This driver supports MediaTek MT8188 ipesys clocks. +config COMMON_CLK_MT8188_MFGCFG + tristate "Clock driver for MediaTek MT8188 mfgcfg" + depends on COMMON_CLK_MT8188 + default COMMON_CLK_MT8188 + help + This driver supports MediaTek MT8188 mfgcfg clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index c36e3d36ed67..16ba3c97c4e8 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -105,6 +105,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o +obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-mfg.c b/drivers/clk/mediatek/clk-mt8188-mfg.c new file mode 100644 index 000000000000..e5a6eaf84672 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-mfg.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs mfgcfg_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_MFG(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &mfgcfg_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, CLK_SET_RATE_PARENT) + +static const struct mtk_gate mfgcfg_clks[] = { + GATE_MFG(CLK_MFGCFG_BG3D, "mfgcfg_bg3d", "mfg_ck_fast_ref", 0), +}; + +static const struct mtk_clk_desc mfgcfg_desc = { + .clks = mfgcfg_clks, + .num_clks = ARRAY_SIZE(mfgcfg_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_mfgcfg[] = { + { .compatible = "mediatek,mt8188-mfgcfg", .data = &mfgcfg_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_mfgcfg); + +static struct platform_driver clk_mt8188_mfgcfg_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-mfgcfg", + .of_match_table = of_match_clk_mt8188_mfgcfg, + }, +}; + +module_platform_driver(clk_mt8188_mfgcfg_drv); +MODULE_LICENSE("GPL"); -- GitLab From 72753163899d78b4f693c5f6eb35c0706c3f0968 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:13 +0800 Subject: [PATCH 1838/5631] clk: mediatek: Add MT8188 vdecsys clock support Add MT8188 vdec clock controllers which provide clock gate control for video decoder. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-12-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-vdec.c | 92 ++++++++++++++++++++++++++ 3 files changed, 100 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-vdec.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index d1239c7ac9f4..8470684daa46 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -720,6 +720,13 @@ config COMMON_CLK_MT8188_MFGCFG help This driver supports MediaTek MT8188 mfgcfg clocks. +config COMMON_CLK_MT8188_VDECSYS + tristate "Clock driver for MediaTek MT8188 vdecsys" + depends on COMMON_CLK_MT8188_VPPSYS + default COMMON_CLK_MT8188_VPPSYS + help + This driver supports MediaTek MT8188 vdecsys and vdecsys_soc clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 16ba3c97c4e8..b63d38804809 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -106,6 +106,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o +obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-vdec.c b/drivers/clk/mediatek/clk-mt8188-vdec.c new file mode 100644 index 000000000000..8c3d76531753 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-vdec.c @@ -0,0 +1,92 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs vdec0_cg_regs = { + .set_ofs = 0x0, + .clr_ofs = 0x4, + .sta_ofs = 0x0, +}; + +static const struct mtk_gate_regs vdec1_cg_regs = { + .set_ofs = 0x200, + .clr_ofs = 0x204, + .sta_ofs = 0x200, +}; + +static const struct mtk_gate_regs vdec2_cg_regs = { + .set_ofs = 0x8, + .clr_ofs = 0xc, + .sta_ofs = 0x8, +}; + +#define GATE_VDEC0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec0_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) + +#define GATE_VDEC1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) + +#define GATE_VDEC2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdec2_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) + +static const struct mtk_gate vdec1_clks[] = { + /* VDEC1_0 */ + GATE_VDEC0(CLK_VDEC1_SOC_VDEC, "vdec1_soc_vdec", "top_vdec", 0), + GATE_VDEC0(CLK_VDEC1_SOC_VDEC_ACTIVE, "vdec1_soc_vdec_active", "top_vdec", 4), + GATE_VDEC0(CLK_VDEC1_SOC_VDEC_ENG, "vdec1_soc_vdec_eng", "top_vdec", 8), + /* VDEC1_1 */ + GATE_VDEC1(CLK_VDEC1_SOC_LAT, "vdec1_soc_lat", "top_vdec", 0), + GATE_VDEC1(CLK_VDEC1_SOC_LAT_ACTIVE, "vdec1_soc_lat_active", "top_vdec", 4), + GATE_VDEC1(CLK_VDEC1_SOC_LAT_ENG, "vdec1_soc_lat_eng", "top_vdec", 8), + /* VDEC1_2 */ + GATE_VDEC2(CLK_VDEC1_SOC_LARB1, "vdec1_soc_larb1", "top_vdec", 0), +}; + +static const struct mtk_gate vdec2_clks[] = { + /* VDEC2_0 */ + GATE_VDEC0(CLK_VDEC2_VDEC, "vdec2_vdec", "top_vdec", 0), + GATE_VDEC0(CLK_VDEC2_VDEC_ACTIVE, "vdec2_vdec_active", "top_vdec", 4), + GATE_VDEC0(CLK_VDEC2_VDEC_ENG, "vdec2_vdec_eng", "top_vdec", 8), + /* VDEC2_1 */ + GATE_VDEC1(CLK_VDEC2_LAT, "vdec2_lat", "top_vdec", 0), + /* VDEC2_2 */ + GATE_VDEC2(CLK_VDEC2_LARB1, "vdec2_larb1", "top_vdec", 0), +}; + +static const struct mtk_clk_desc vdec1_desc = { + .clks = vdec1_clks, + .num_clks = ARRAY_SIZE(vdec1_clks), +}; + +static const struct mtk_clk_desc vdec2_desc = { + .clks = vdec2_clks, + .num_clks = ARRAY_SIZE(vdec2_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_vdec[] = { + { .compatible = "mediatek,mt8188-vdecsys-soc", .data = &vdec1_desc }, + { .compatible = "mediatek,mt8188-vdecsys", .data = &vdec2_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_vdec); + +static struct platform_driver clk_mt8188_vdec_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-vdec", + .of_match_table = of_match_clk_mt8188_vdec, + }, +}; + +module_platform_driver(clk_mt8188_vdec_drv); +MODULE_LICENSE("GPL"); -- GitLab From e4aaa60eae166f5085a4b9e3c4ad3b698120a486 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:14 +0800 Subject: [PATCH 1839/5631] clk: mediatek: Add MT8188 vdosys0 clock support Add MT8188 vdosys0 clock controller which provides clock gate control in video system. This is integrated with mtk-mmsys driver which will populate device by platform_device_register_data to start vdosys clock driver. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-13-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-vdo0.c | 105 +++++++++++++++++++++++++ 3 files changed, 113 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-vdo0.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 8470684daa46..d39fa2b1c572 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -727,6 +727,13 @@ config COMMON_CLK_MT8188_VDECSYS help This driver supports MediaTek MT8188 vdecsys and vdecsys_soc clocks. +config COMMON_CLK_MT8188_VDOSYS + tristate "Clock driver for MediaTek MT8188 vdosys" + depends on COMMON_CLK_MT8188 + default COMMON_CLK_MT8188 + help + This driver supports MediaTek MT8188 vdosys0/1 (multimedia) clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index b63d38804809..4ca2bdf07b63 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -107,6 +107,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o +obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-vdo0.c b/drivers/clk/mediatek/clk-mt8188-vdo0.c new file mode 100644 index 000000000000..0c61c2dc4337 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-vdo0.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs vdo0_0_cg_regs = { + .set_ofs = 0x104, + .clr_ofs = 0x108, + .sta_ofs = 0x100, +}; + +static const struct mtk_gate_regs vdo0_1_cg_regs = { + .set_ofs = 0x114, + .clr_ofs = 0x118, + .sta_ofs = 0x110, +}; + +static const struct mtk_gate_regs vdo0_2_cg_regs = { + .set_ofs = 0x124, + .clr_ofs = 0x128, + .sta_ofs = 0x120, +}; + +#define GATE_VDO0_0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo0_0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO0_1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo0_1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO0_2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo0_2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO0_2_FLAGS(_id, _name, _parent, _shift, _flags) \ + GATE_MTK_FLAGS(_id, _name, _parent, &vdo0_2_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flags) + +static const struct mtk_gate vdo0_clks[] = { + /* VDO0_0 */ + GATE_VDO0_0(CLK_VDO0_DISP_OVL0, "vdo0_disp_ovl0", "top_vpp", 0), + GATE_VDO0_0(CLK_VDO0_FAKE_ENG0, "vdo0_fake_eng0", "top_vpp", 2), + GATE_VDO0_0(CLK_VDO0_DISP_CCORR0, "vdo0_disp_ccorr0", "top_vpp", 4), + GATE_VDO0_0(CLK_VDO0_DISP_MUTEX0, "vdo0_disp_mutex0", "top_vpp", 6), + GATE_VDO0_0(CLK_VDO0_DISP_GAMMA0, "vdo0_disp_gamma0", "top_vpp", 8), + GATE_VDO0_0(CLK_VDO0_DISP_DITHER0, "vdo0_disp_dither0", "top_vpp", 10), + GATE_VDO0_0(CLK_VDO0_DISP_WDMA0, "vdo0_disp_wdma0", "top_vpp", 17), + GATE_VDO0_0(CLK_VDO0_DISP_RDMA0, "vdo0_disp_rdma0", "top_vpp", 19), + GATE_VDO0_0(CLK_VDO0_DSI0, "vdo0_dsi0", "top_vpp", 21), + GATE_VDO0_0(CLK_VDO0_DSI1, "vdo0_dsi1", "top_vpp", 22), + GATE_VDO0_0(CLK_VDO0_DSC_WRAP0, "vdo0_dsc_wrap0", "top_vpp", 23), + GATE_VDO0_0(CLK_VDO0_VPP_MERGE0, "vdo0_vpp_merge0", "top_vpp", 24), + GATE_VDO0_0(CLK_VDO0_DP_INTF0, "vdo0_dp_intf0", "top_vpp", 25), + GATE_VDO0_0(CLK_VDO0_DISP_AAL0, "vdo0_disp_aal0", "top_vpp", 26), + GATE_VDO0_0(CLK_VDO0_INLINEROT0, "vdo0_inlinerot0", "top_vpp", 27), + GATE_VDO0_0(CLK_VDO0_APB_BUS, "vdo0_apb_bus", "top_vpp", 28), + GATE_VDO0_0(CLK_VDO0_DISP_COLOR0, "vdo0_disp_color0", "top_vpp", 29), + GATE_VDO0_0(CLK_VDO0_MDP_WROT0, "vdo0_mdp_wrot0", "top_vpp", 30), + GATE_VDO0_0(CLK_VDO0_DISP_RSZ0, "vdo0_disp_rsz0", "top_vpp", 31), + /* VDO0_1 */ + GATE_VDO0_1(CLK_VDO0_DISP_POSTMASK0, "vdo0_disp_postmask0", "top_vpp", 0), + GATE_VDO0_1(CLK_VDO0_FAKE_ENG1, "vdo0_fake_eng1", "top_vpp", 1), + GATE_VDO0_1(CLK_VDO0_DL_ASYNC2, "vdo0_dl_async2", "top_vpp", 5), + GATE_VDO0_1(CLK_VDO0_DL_RELAY3, "vdo0_dl_relay3", "top_vpp", 6), + GATE_VDO0_1(CLK_VDO0_DL_RELAY4, "vdo0_dl_relay4", "top_vpp", 7), + GATE_VDO0_1(CLK_VDO0_SMI_GALS, "vdo0_smi_gals", "top_vpp", 10), + GATE_VDO0_1(CLK_VDO0_SMI_COMMON, "vdo0_smi_common", "top_vpp", 11), + GATE_VDO0_1(CLK_VDO0_SMI_EMI, "vdo0_smi_emi", "top_vpp", 12), + GATE_VDO0_1(CLK_VDO0_SMI_IOMMU, "vdo0_smi_iommu", "top_vpp", 13), + GATE_VDO0_1(CLK_VDO0_SMI_LARB, "vdo0_smi_larb", "top_vpp", 14), + GATE_VDO0_1(CLK_VDO0_SMI_RSI, "vdo0_smi_rsi", "top_vpp", 15), + /* VDO0_2 */ + GATE_VDO0_2(CLK_VDO0_DSI0_DSI, "vdo0_dsi0_dsi", "top_dsi_occ", 0), + GATE_VDO0_2(CLK_VDO0_DSI1_DSI, "vdo0_dsi1_dsi", "top_dsi_occ", 8), + GATE_VDO0_2_FLAGS(CLK_VDO0_DP_INTF0_DP_INTF, "vdo0_dp_intf0_dp_intf", + "top_edp", 16, CLK_SET_RATE_PARENT), +}; + +static const struct mtk_clk_desc vdo0_desc = { + .clks = vdo0_clks, + .num_clks = ARRAY_SIZE(vdo0_clks), +}; + +static const struct platform_device_id clk_mt8188_vdo0_id_table[] = { + { .name = "clk-mt8188-vdo0", .driver_data = (kernel_ulong_t)&vdo0_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, clk_mt8188_vdo0_id_table); + +static struct platform_driver clk_mt8188_vdo0_drv = { + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, + .driver = { + .name = "clk-mt8188-vdo0", + }, + .id_table = clk_mt8188_vdo0_id_table, +}; +module_platform_driver(clk_mt8188_vdo0_drv); +MODULE_LICENSE("GPL"); -- GitLab From cfa4609f9bbedcbd80e387bc880c2e1cf6b45fe0 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:15 +0800 Subject: [PATCH 1840/5631] clk: mediatek: Add MT8188 vdosys1 clock support Add MT8188 vdosys1 clock controller which provides clock gate control in video system. This is integrated with mtk-mmsys driver which will populate device by platform_device_register_data to start vdosys clock driver. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-14-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8188-vdo1.c | 152 +++++++++++++++++++++++++ 2 files changed, 153 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-vdo1.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 4ca2bdf07b63..a6b80bb0b1bf 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -107,7 +107,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o -obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o +obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o clk-mt8188-vdo1.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-vdo1.c b/drivers/clk/mediatek/clk-mt8188-vdo1.c new file mode 100644 index 000000000000..99fcf6d7b1ab --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-vdo1.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs vdo1_0_cg_regs = { + .set_ofs = 0x104, + .clr_ofs = 0x108, + .sta_ofs = 0x100, +}; + +static const struct mtk_gate_regs vdo1_1_cg_regs = { + .set_ofs = 0x114, + .clr_ofs = 0x118, + .sta_ofs = 0x110, +}; + +static const struct mtk_gate_regs vdo1_2_cg_regs = { + .set_ofs = 0x124, + .clr_ofs = 0x128, + .sta_ofs = 0x120, +}; + +static const struct mtk_gate_regs vdo1_3_cg_regs = { + .set_ofs = 0x134, + .clr_ofs = 0x138, + .sta_ofs = 0x130, +}; + +static const struct mtk_gate_regs vdo1_4_cg_regs = { + .set_ofs = 0x144, + .clr_ofs = 0x148, + .sta_ofs = 0x140, +}; + +#define GATE_VDO1_0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo1_0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO1_1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo1_1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO1_2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo1_2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO1_3(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo1_3_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VDO1_3_FLAGS(_id, _name, _parent, _shift, _flags) \ + GATE_MTK_FLAGS(_id, _name, _parent, &vdo1_3_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, _flags) + +#define GATE_VDO1_4(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vdo1_4_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate vdo1_clks[] = { + /* VDO1_0 */ + GATE_VDO1_0(CLK_VDO1_SMI_LARB2, "vdo1_smi_larb2", "top_vpp", 0), + GATE_VDO1_0(CLK_VDO1_SMI_LARB3, "vdo1_smi_larb3", "top_vpp", 1), + GATE_VDO1_0(CLK_VDO1_GALS, "vdo1_gals", "top_vpp", 2), + GATE_VDO1_0(CLK_VDO1_FAKE_ENG0, "vdo1_fake_eng0", "top_vpp", 3), + GATE_VDO1_0(CLK_VDO1_FAKE_ENG1, "vdo1_fake_eng1", "top_vpp", 4), + GATE_VDO1_0(CLK_VDO1_MDP_RDMA0, "vdo1_mdp_rdma0", "top_vpp", 5), + GATE_VDO1_0(CLK_VDO1_MDP_RDMA1, "vdo1_mdp_rdma1", "top_vpp", 6), + GATE_VDO1_0(CLK_VDO1_MDP_RDMA2, "vdo1_mdp_rdma2", "top_vpp", 7), + GATE_VDO1_0(CLK_VDO1_MDP_RDMA3, "vdo1_mdp_rdma3", "top_vpp", 8), + GATE_VDO1_0(CLK_VDO1_VPP_MERGE0, "vdo1_vpp_merge0", "top_vpp", 9), + GATE_VDO1_0(CLK_VDO1_VPP_MERGE1, "vdo1_vpp_merge1", "top_vpp", 10), + GATE_VDO1_0(CLK_VDO1_VPP_MERGE2, "vdo1_vpp_merge2", "top_vpp", 11), + /* VDO1_1 */ + GATE_VDO1_1(CLK_VDO1_VPP_MERGE3, "vdo1_vpp_merge3", "top_vpp", 0), + GATE_VDO1_1(CLK_VDO1_VPP_MERGE4, "vdo1_vpp_merge4", "top_vpp", 1), + GATE_VDO1_1(CLK_VDO1_VPP2_TO_VDO1_DL_ASYNC, "vdo1_vpp2_to_vdo1_dl_async", "top_vpp", 2), + GATE_VDO1_1(CLK_VDO1_VPP3_TO_VDO1_DL_ASYNC, "vdo1_vpp3_to_vdo1_dl_async", "top_vpp", 3), + GATE_VDO1_1(CLK_VDO1_DISP_MUTEX, "vdo1_disp_mutex", "top_vpp", 4), + GATE_VDO1_1(CLK_VDO1_MDP_RDMA4, "vdo1_mdp_rdma4", "top_vpp", 5), + GATE_VDO1_1(CLK_VDO1_MDP_RDMA5, "vdo1_mdp_rdma5", "top_vpp", 6), + GATE_VDO1_1(CLK_VDO1_MDP_RDMA6, "vdo1_mdp_rdma6", "top_vpp", 7), + GATE_VDO1_1(CLK_VDO1_MDP_RDMA7, "vdo1_mdp_rdma7", "top_vpp", 8), + GATE_VDO1_1(CLK_VDO1_DP_INTF0_MMCK, "vdo1_dp_intf0_mmck", "top_vpp", 9), + GATE_VDO1_1(CLK_VDO1_DPI0_MM, "vdo1_dpi0_mm_ck", "top_vpp", 10), + GATE_VDO1_1(CLK_VDO1_DPI1_MM, "vdo1_dpi1_mm_ck", "top_vpp", 11), + GATE_VDO1_1(CLK_VDO1_MERGE0_DL_ASYNC, "vdo1_merge0_dl_async", "top_vpp", 13), + GATE_VDO1_1(CLK_VDO1_MERGE1_DL_ASYNC, "vdo1_merge1_dl_async", "top_vpp", 14), + GATE_VDO1_1(CLK_VDO1_MERGE2_DL_ASYNC, "vdo1_merge2_dl_async", "top_vpp", 15), + GATE_VDO1_1(CLK_VDO1_MERGE3_DL_ASYNC, "vdo1_merge3_dl_async", "top_vpp", 16), + GATE_VDO1_1(CLK_VDO1_MERGE4_DL_ASYNC, "vdo1_merge4_dl_async", "top_vpp", 17), + GATE_VDO1_1(CLK_VDO1_DSC_VDO1_DL_ASYNC, "vdo1_dsc_vdo1_dl_async", "top_vpp", 18), + GATE_VDO1_1(CLK_VDO1_MERGE_VDO1_DL_ASYNC, "vdo1_merge_vdo1_dl_async", "top_vpp", 19), + GATE_VDO1_1(CLK_VDO1_PADDING0, "vdo1_padding0", "top_vpp", 20), + GATE_VDO1_1(CLK_VDO1_PADDING1, "vdo1_padding1", "top_vpp", 21), + GATE_VDO1_1(CLK_VDO1_PADDING2, "vdo1_padding2", "top_vpp", 22), + GATE_VDO1_1(CLK_VDO1_PADDING3, "vdo1_padding3", "top_vpp", 23), + GATE_VDO1_1(CLK_VDO1_PADDING4, "vdo1_padding4", "top_vpp", 24), + GATE_VDO1_1(CLK_VDO1_PADDING5, "vdo1_padding5", "top_vpp", 25), + GATE_VDO1_1(CLK_VDO1_PADDING6, "vdo1_padding6", "top_vpp", 26), + GATE_VDO1_1(CLK_VDO1_PADDING7, "vdo1_padding7", "top_vpp", 27), + GATE_VDO1_1(CLK_VDO1_DISP_RSZ0, "vdo1_disp_rsz0", "top_vpp", 28), + GATE_VDO1_1(CLK_VDO1_DISP_RSZ1, "vdo1_disp_rsz1", "top_vpp", 29), + GATE_VDO1_1(CLK_VDO1_DISP_RSZ2, "vdo1_disp_rsz2", "top_vpp", 30), + GATE_VDO1_1(CLK_VDO1_DISP_RSZ3, "vdo1_disp_rsz3", "top_vpp", 31), + /* VDO1_2 */ + GATE_VDO1_2(CLK_VDO1_HDR_VDO_FE0, "vdo1_hdr_vdo_fe0", "top_vpp", 0), + GATE_VDO1_2(CLK_VDO1_HDR_GFX_FE0, "vdo1_hdr_gfx_fe0", "top_vpp", 1), + GATE_VDO1_2(CLK_VDO1_HDR_VDO_BE, "vdo1_hdr_vdo_be", "top_vpp", 2), + GATE_VDO1_2(CLK_VDO1_HDR_VDO_FE1, "vdo1_hdr_vdo_fe1", "top_vpp", 16), + GATE_VDO1_2(CLK_VDO1_HDR_GFX_FE1, "vdo1_hdr_gfx_fe1", "top_vpp", 17), + GATE_VDO1_2(CLK_VDO1_DISP_MIXER, "vdo1_disp_mixer", "top_vpp", 18), + GATE_VDO1_2(CLK_VDO1_HDR_VDO_FE0_DL_ASYNC, "vdo1_hdr_vdo_fe0_dl_async", "top_vpp", 19), + GATE_VDO1_2(CLK_VDO1_HDR_VDO_FE1_DL_ASYNC, "vdo1_hdr_vdo_fe1_dl_async", "top_vpp", 20), + GATE_VDO1_2(CLK_VDO1_HDR_GFX_FE0_DL_ASYNC, "vdo1_hdr_gfx_fe0_dl_async", "top_vpp", 21), + GATE_VDO1_2(CLK_VDO1_HDR_GFX_FE1_DL_ASYNC, "vdo1_hdr_gfx_fe1_dl_async", "top_vpp", 22), + GATE_VDO1_2(CLK_VDO1_HDR_VDO_BE_DL_ASYNC, "vdo1_hdr_vdo_be_dl_async", "top_vpp", 23), + /* VDO1_3 */ + GATE_VDO1_3(CLK_VDO1_DPI0, "vdo1_dpi0_ck", "top_vpp", 0), + GATE_VDO1_3(CLK_VDO1_DISP_MONITOR_DPI0, "vdo1_disp_monitor_dpi0_ck", "top_vpp", 1), + GATE_VDO1_3(CLK_VDO1_DPI1, "vdo1_dpi1_ck", "top_vpp", 8), + GATE_VDO1_3(CLK_VDO1_DISP_MONITOR_DPI1, "vdo1_disp_monitor_dpi1_ck", "top_vpp", 9), + GATE_VDO1_3_FLAGS(CLK_VDO1_DPINTF, "vdo1_dpintf", "top_dp", 16, CLK_SET_RATE_PARENT), + GATE_VDO1_3(CLK_VDO1_DISP_MONITOR_DPINTF, "vdo1_disp_monitor_dpintf_ck", "top_vpp", 17), + /* VDO1_4 */ + GATE_VDO1_4(CLK_VDO1_26M_SLOW, "vdo1_26m_slow_ck", "clk26m", 8), +}; + +static const struct mtk_clk_desc vdo1_desc = { + .clks = vdo1_clks, + .num_clks = ARRAY_SIZE(vdo1_clks), +}; + +static const struct platform_device_id clk_mt8188_vdo1_id_table[] = { + { .name = "clk-mt8188-vdo1", .driver_data = (kernel_ulong_t)&vdo1_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, clk_mt8188_vdo1_id_table); + +static struct platform_driver clk_mt8188_vdo1_drv = { + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, + .driver = { + .name = "clk-mt8188-vdo1", + }, + .id_table = clk_mt8188_vdo1_id_table, +}; +module_platform_driver(clk_mt8188_vdo1_drv); +MODULE_LICENSE("GPL"); -- GitLab From bb87c1109ce2f4c947b5b92a1f82ec75f8f969f8 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:16 +0800 Subject: [PATCH 1841/5631] clk: mediatek: Add MT8188 vencsys clock support Add MT8188 vencsys clock controllers which provide clock gate control for video encoder. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-15-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-venc.c | 54 ++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-venc.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index d39fa2b1c572..87ac1df8e901 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -734,6 +734,13 @@ config COMMON_CLK_MT8188_VDOSYS help This driver supports MediaTek MT8188 vdosys0/1 (multimedia) clocks. +config COMMON_CLK_MT8188_VENCSYS + tristate "Clock driver for MediaTek MT8188 vencsys" + depends on COMMON_CLK_MT8188_VPPSYS + default COMMON_CLK_MT8188_VPPSYS + help + This driver supports MediaTek MT8188 vencsys clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index a6b80bb0b1bf..d56be5cb0534 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -108,6 +108,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o clk-mt8188-vdo1.o +obj-$(CONFIG_COMMON_CLK_MT8188_VENCSYS) += clk-mt8188-venc.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-venc.c b/drivers/clk/mediatek/clk-mt8188-venc.c new file mode 100644 index 000000000000..6f6589ccd5a0 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-venc.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs venc1_cg_regs = { + .set_ofs = 0x4, + .clr_ofs = 0x8, + .sta_ofs = 0x0, +}; + +#define GATE_VENC1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &venc1_cg_regs, _shift, &mtk_clk_gate_ops_setclr_inv) + +static const struct mtk_gate venc1_clks[] = { + GATE_VENC1(CLK_VENC1_LARB, "venc1_larb", "top_venc", 0), + GATE_VENC1(CLK_VENC1_VENC, "venc1_venc", "top_venc", 4), + GATE_VENC1(CLK_VENC1_JPGENC, "venc1_jpgenc", "top_venc", 8), + GATE_VENC1(CLK_VENC1_JPGDEC, "venc1_jpgdec", "top_venc", 12), + GATE_VENC1(CLK_VENC1_JPGDEC_C1, "venc1_jpgdec_c1", "top_venc", 16), + GATE_VENC1(CLK_VENC1_GALS, "venc1_gals", "top_venc", 28), + GATE_VENC1(CLK_VENC1_GALS_SRAM, "venc1_gals_sram", "top_venc", 31), +}; + +static const struct mtk_clk_desc venc1_desc = { + .clks = venc1_clks, + .num_clks = ARRAY_SIZE(venc1_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_venc1[] = { + { .compatible = "mediatek,mt8188-vencsys", .data = &venc1_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_venc1); + +static struct platform_driver clk_mt8188_venc1_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-venc1", + .of_match_table = of_match_clk_mt8188_venc1, + }, +}; + +module_platform_driver(clk_mt8188_venc1_drv); +MODULE_LICENSE("GPL"); -- GitLab From eb48cccda09597a309d66331744e1b8edf196a67 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:17 +0800 Subject: [PATCH 1842/5631] clk: mediatek: Add MT8188 vppsys0 clock support Add MT8188 vppsys0 clock controller which provides clock gate controller for Video Processor Pipe. Signed-off-by: Garmin.Chang Reviewed-by: Matthias Brugger Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-16-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-vpp0.c | 114 +++++++++++++++++++++++++ 3 files changed, 122 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-vpp0.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 87ac1df8e901..70c139256236 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -741,6 +741,13 @@ config COMMON_CLK_MT8188_VENCSYS help This driver supports MediaTek MT8188 vencsys clocks. +config COMMON_CLK_MT8188_VPPSYS + tristate "Clock driver for MediaTek MT8188 vppsys" + depends on COMMON_CLK_MT8188 + default COMMON_CLK_MT8188 + help + This driver supports MediaTek MT8188 vppsys0/1 clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index d56be5cb0534..4189f2ee20f1 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -109,6 +109,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o clk-mt8188-vdo1.o obj-$(CONFIG_COMMON_CLK_MT8188_VENCSYS) += clk-mt8188-venc.o +obj-$(CONFIG_COMMON_CLK_MT8188_VPPSYS) += clk-mt8188-vpp0.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-vpp0.c b/drivers/clk/mediatek/clk-mt8188-vpp0.c new file mode 100644 index 000000000000..07bdedf6a21a --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-vpp0.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs vpp0_0_cg_regs = { + .set_ofs = 0x24, + .clr_ofs = 0x28, + .sta_ofs = 0x20, +}; + +static const struct mtk_gate_regs vpp0_1_cg_regs = { + .set_ofs = 0x30, + .clr_ofs = 0x34, + .sta_ofs = 0x2c, +}; + +static const struct mtk_gate_regs vpp0_2_cg_regs = { + .set_ofs = 0x3c, + .clr_ofs = 0x40, + .sta_ofs = 0x38, +}; + +#define GATE_VPP0_0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vpp0_0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VPP0_1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vpp0_1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VPP0_2(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vpp0_2_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate vpp0_clks[] = { + /* VPP0_0 */ + GATE_VPP0_0(CLK_VPP0_MDP_FG, "vpp0_mdp_fg", "top_vpp", 1), + GATE_VPP0_0(CLK_VPP0_STITCH, "vpp0_stitch", "top_vpp", 2), + GATE_VPP0_0(CLK_VPP0_PADDING, "vpp0_padding", "top_vpp", 7), + GATE_VPP0_0(CLK_VPP0_MDP_TCC, "vpp0_mdp_tcc", "top_vpp", 8), + GATE_VPP0_0(CLK_VPP0_WARP0_ASYNC_TX, "vpp0_warp0_async_tx", "top_vpp", 10), + GATE_VPP0_0(CLK_VPP0_WARP1_ASYNC_TX, "vpp0_warp1_async_tx", "top_vpp", 11), + GATE_VPP0_0(CLK_VPP0_MUTEX, "vpp0_mutex", "top_vpp", 13), + GATE_VPP0_0(CLK_VPP02VPP1_RELAY, "vpp02vpp1_relay", "top_vpp", 14), + GATE_VPP0_0(CLK_VPP0_VPP12VPP0_ASYNC, "vpp0_vpp12vpp0_async", "top_vpp", 15), + GATE_VPP0_0(CLK_VPP0_MMSYSRAM_TOP, "vpp0_mmsysram_top", "top_vpp", 16), + GATE_VPP0_0(CLK_VPP0_MDP_AAL, "vpp0_mdp_aal", "top_vpp", 17), + GATE_VPP0_0(CLK_VPP0_MDP_RSZ, "vpp0_mdp_rsz", "top_vpp", 18), + /* VPP0_1 */ + GATE_VPP0_1(CLK_VPP0_SMI_COMMON_MMSRAM, "vpp0_smi_common_mmsram", "top_vpp", 0), + GATE_VPP0_1(CLK_VPP0_GALS_VDO0_LARB0_MMSRAM, "vpp0_gals_vdo0_larb0_mmsram", "top_vpp", 1), + GATE_VPP0_1(CLK_VPP0_GALS_VDO0_LARB1_MMSRAM, "vpp0_gals_vdo0_larb1_mmsram", "top_vpp", 2), + GATE_VPP0_1(CLK_VPP0_GALS_VENCSYS_MMSRAM, "vpp0_gals_vencsys_mmsram", "top_vpp", 3), + GATE_VPP0_1(CLK_VPP0_GALS_VENCSYS_CORE1_MMSRAM, + "vpp0_gals_vencsys_core1_mmsram", "top_vpp", 4), + GATE_VPP0_1(CLK_VPP0_GALS_INFRA_MMSRAM, "vpp0_gals_infra_mmsram", "top_vpp", 5), + GATE_VPP0_1(CLK_VPP0_GALS_CAMSYS_MMSRAM, "vpp0_gals_camsys_mmsram", "top_vpp", 6), + GATE_VPP0_1(CLK_VPP0_GALS_VPP1_LARB5_MMSRAM, "vpp0_gals_vpp1_larb5_mmsram", "top_vpp", 7), + GATE_VPP0_1(CLK_VPP0_GALS_VPP1_LARB6_MMSRAM, "vpp0_gals_vpp1_larb6_mmsram", "top_vpp", 8), + GATE_VPP0_1(CLK_VPP0_SMI_REORDER_MMSRAM, "vpp0_smi_reorder_mmsram", "top_vpp", 9), + GATE_VPP0_1(CLK_VPP0_SMI_IOMMU, "vpp0_smi_iommu", "top_vpp", 10), + GATE_VPP0_1(CLK_VPP0_GALS_IMGSYS_CAMSYS, "vpp0_gals_imgsys_camsys", "top_vpp", 11), + GATE_VPP0_1(CLK_VPP0_MDP_RDMA, "vpp0_mdp_rdma", "top_vpp", 12), + GATE_VPP0_1(CLK_VPP0_MDP_WROT, "vpp0_mdp_wrot", "top_vpp", 13), + GATE_VPP0_1(CLK_VPP0_GALS_EMI0_EMI1, "vpp0_gals_emi0_emi1", "top_vpp", 16), + GATE_VPP0_1(CLK_VPP0_SMI_SUB_COMMON_REORDER, "vpp0_smi_sub_common_reorder", "top_vpp", 17), + GATE_VPP0_1(CLK_VPP0_SMI_RSI, "vpp0_smi_rsi", "top_vpp", 18), + GATE_VPP0_1(CLK_VPP0_SMI_COMMON_LARB4, "vpp0_smi_common_larb4", "top_vpp", 19), + GATE_VPP0_1(CLK_VPP0_GALS_VDEC_VDEC_CORE1, "vpp0_gals_vdec_vdec_core1", "top_vpp", 20), + GATE_VPP0_1(CLK_VPP0_GALS_VPP1_WPESYS, "vpp0_gals_vpp1_wpesys", "top_vpp", 21), + GATE_VPP0_1(CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1, + "vpp0_gals_vdo0_vdo1_vencsys_core1", "top_vpp", 22), + GATE_VPP0_1(CLK_VPP0_FAKE_ENG, "vpp0_fake_eng", "top_vpp", 23), + GATE_VPP0_1(CLK_VPP0_MDP_HDR, "vpp0_mdp_hdr", "top_vpp", 24), + GATE_VPP0_1(CLK_VPP0_MDP_TDSHP, "vpp0_mdp_tdshp", "top_vpp", 25), + GATE_VPP0_1(CLK_VPP0_MDP_COLOR, "vpp0_mdp_color", "top_vpp", 26), + GATE_VPP0_1(CLK_VPP0_MDP_OVL, "vpp0_mdp_ovl", "top_vpp", 27), + GATE_VPP0_1(CLK_VPP0_DSIP_RDMA, "vpp0_dsip_rdma", "top_vpp", 28), + GATE_VPP0_1(CLK_VPP0_DISP_WDMA, "vpp0_disp_wdma", "top_vpp", 29), + GATE_VPP0_1(CLK_VPP0_MDP_HMS, "vpp0_mdp_hms", "top_vpp", 30), + /* VPP0_2 */ + GATE_VPP0_2(CLK_VPP0_WARP0_RELAY, "vpp0_warp0_relay", "top_wpe_vpp", 0), + GATE_VPP0_2(CLK_VPP0_WARP0_ASYNC, "vpp0_warp0_async", "top_wpe_vpp", 1), + GATE_VPP0_2(CLK_VPP0_WARP1_RELAY, "vpp0_warp1_relay", "top_wpe_vpp", 2), + GATE_VPP0_2(CLK_VPP0_WARP1_ASYNC, "vpp0_warp1_async", "top_wpe_vpp", 3), +}; + +static const struct mtk_clk_desc vpp0_desc = { + .clks = vpp0_clks, + .num_clks = ARRAY_SIZE(vpp0_clks), +}; + +static const struct platform_device_id clk_mt8188_vpp0_id_table[] = { + { .name = "clk-mt8188-vpp0", .driver_data = (kernel_ulong_t)&vpp0_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, clk_mt8188_vpp0_id_table); + +static struct platform_driver clk_mt8188_vpp0_drv = { + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, + .driver = { + .name = "clk-mt8188-vpp0", + }, + .id_table = clk_mt8188_vpp0_id_table, +}; +module_platform_driver(clk_mt8188_vpp0_drv); +MODULE_LICENSE("GPL"); -- GitLab From 4898e77f47e5b028a72c711c97841d74608e61ed Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:18 +0800 Subject: [PATCH 1843/5631] clk: mediatek: Add MT8188 vppsys1 clock support Add MT8188 vppsys1 clock controller which provides clock gate controller for Video Processor Pipe. Signed-off-by: Garmin.Chang Reviewed-by: Matthias Brugger Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-17-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Makefile | 2 +- drivers/clk/mediatek/clk-mt8188-vpp1.c | 109 +++++++++++++++++++++++++ 2 files changed, 110 insertions(+), 1 deletion(-) create mode 100644 drivers/clk/mediatek/clk-mt8188-vpp1.c diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 4189f2ee20f1..dec47ef9830c 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -109,7 +109,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o clk-mt8188-vdo1.o obj-$(CONFIG_COMMON_CLK_MT8188_VENCSYS) += clk-mt8188-venc.o -obj-$(CONFIG_COMMON_CLK_MT8188_VPPSYS) += clk-mt8188-vpp0.o +obj-$(CONFIG_COMMON_CLK_MT8188_VPPSYS) += clk-mt8188-vpp0.o clk-mt8188-vpp1.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-vpp1.c b/drivers/clk/mediatek/clk-mt8188-vpp1.c new file mode 100644 index 000000000000..d4e66b240573 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-vpp1.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs vpp1_0_cg_regs = { + .set_ofs = 0x104, + .clr_ofs = 0x108, + .sta_ofs = 0x100, +}; + +static const struct mtk_gate_regs vpp1_1_cg_regs = { + .set_ofs = 0x114, + .clr_ofs = 0x118, + .sta_ofs = 0x110, +}; + +#define GATE_VPP1_0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vpp1_0_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +#define GATE_VPP1_1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &vpp1_1_cg_regs, _shift, &mtk_clk_gate_ops_setclr) + +static const struct mtk_gate vpp1_clks[] = { + /* VPP1_0 */ + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_OVL, "vpp1_svpp1_mdp_ovl", "top_vpp", 0), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_TCC, "vpp1_svpp1_mdp_tcc", "top_vpp", 1), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_WROT, "vpp1_svpp1_mdp_wrot", "top_vpp", 2), + GATE_VPP1_0(CLK_VPP1_SVPP1_VPP_PAD, "vpp1_svpp1_vpp_pad", "top_vpp", 3), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_WROT, "vpp1_svpp2_mdp_wrot", "top_vpp", 4), + GATE_VPP1_0(CLK_VPP1_SVPP2_VPP_PAD, "vpp1_svpp2_vpp_pad", "top_vpp", 5), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_WROT, "vpp1_svpp3_mdp_wrot", "top_vpp", 6), + GATE_VPP1_0(CLK_VPP1_SVPP3_VPP_PAD, "vpp1_svpp3_vpp_pad", "top_vpp", 7), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_RDMA, "vpp1_svpp1_mdp_rdma", "top_vpp", 8), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_FG, "vpp1_svpp1_mdp_fg", "top_vpp", 9), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_RDMA, "vpp1_svpp2_mdp_rdma", "top_vpp", 10), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_FG, "vpp1_svpp2_mdp_fg", "top_vpp", 11), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_RDMA, "vpp1_svpp3_mdp_rdma", "top_vpp", 12), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_FG, "vpp1_svpp3_mdp_fg", "top_vpp", 13), + GATE_VPP1_0(CLK_VPP1_VPP_SPLIT, "vpp1_vpp_split", "top_vpp", 14), + GATE_VPP1_0(CLK_VPP1_SVPP2_VDO0_DL_RELAY, "vpp1_svpp2_vdo0_dl_relay", "top_vpp", 15), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_RSZ, "vpp1_svpp1_mdp_rsz", "top_vpp", 16), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_TDSHP, "vpp1_svpp1_mdp_tdshp", "top_vpp", 17), + GATE_VPP1_0(CLK_VPP1_SVPP1_MDP_COLOR, "vpp1_svpp1_mdp_color", "top_vpp", 18), + GATE_VPP1_0(CLK_VPP1_SVPP3_VDO1_DL_RELAY, "vpp1_svpp3_vdo1_dl_relay", "top_vpp", 19), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_RSZ, "vpp1_svpp2_mdp_rsz", "top_vpp", 20), + GATE_VPP1_0(CLK_VPP1_SVPP2_VPP_MERGE, "vpp1_svpp2_vpp_merge", "top_vpp", 21), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_TDSHP, "vpp1_svpp2_mdp_tdshp", "top_vpp", 22), + GATE_VPP1_0(CLK_VPP1_SVPP2_MDP_COLOR, "vpp1_svpp2_mdp_color", "top_vpp", 23), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_RSZ, "vpp1_svpp3_mdp_rsz", "top_vpp", 24), + GATE_VPP1_0(CLK_VPP1_SVPP3_VPP_MERGE, "vpp1_svpp3_vpp_merge", "top_vpp", 25), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_TDSHP, "vpp1_svpp3_mdp_tdshp", "top_vpp", 26), + GATE_VPP1_0(CLK_VPP1_SVPP3_MDP_COLOR, "vpp1_svpp3_mdp_color", "top_vpp", 27), + GATE_VPP1_0(CLK_VPP1_GALS5, "vpp1_gals5", "top_vpp", 28), + GATE_VPP1_0(CLK_VPP1_GALS6, "vpp1_gals6", "top_vpp", 29), + GATE_VPP1_0(CLK_VPP1_LARB5, "vpp1_larb5", "top_vpp", 30), + GATE_VPP1_0(CLK_VPP1_LARB6, "vpp1_larb6", "top_vpp", 31), + /* VPP1_1 */ + GATE_VPP1_1(CLK_VPP1_SVPP1_MDP_HDR, "vpp1_svpp1_mdp_hdr", "top_vpp", 0), + GATE_VPP1_1(CLK_VPP1_SVPP1_MDP_AAL, "vpp1_svpp1_mdp_aal", "top_vpp", 1), + GATE_VPP1_1(CLK_VPP1_SVPP2_MDP_HDR, "vpp1_svpp2_mdp_hdr", "top_vpp", 2), + GATE_VPP1_1(CLK_VPP1_SVPP2_MDP_AAL, "vpp1_svpp2_mdp_aal", "top_vpp", 3), + GATE_VPP1_1(CLK_VPP1_SVPP3_MDP_HDR, "vpp1_svpp3_mdp_hdr", "top_vpp", 4), + GATE_VPP1_1(CLK_VPP1_SVPP3_MDP_AAL, "vpp1_svpp3_mdp_aal", "top_vpp", 5), + GATE_VPP1_1(CLK_VPP1_DISP_MUTEX, "vpp1_disp_mutex", "top_vpp", 7), + GATE_VPP1_1(CLK_VPP1_SVPP2_VDO1_DL_RELAY, "vpp1_svpp2_vdo1_dl_relay", "top_vpp", 8), + GATE_VPP1_1(CLK_VPP1_SVPP3_VDO0_DL_RELAY, "vpp1_svpp3_vdo0_dl_relay", "top_vpp", 9), + GATE_VPP1_1(CLK_VPP1_VPP0_DL_ASYNC, "vpp1_vpp0_dl_async", "top_vpp", 10), + GATE_VPP1_1(CLK_VPP1_VPP0_DL1_RELAY, "vpp1_vpp0_dl1_relay", "top_vpp", 11), + GATE_VPP1_1(CLK_VPP1_LARB5_FAKE_ENG, "vpp1_larb5_fake_eng", "top_vpp", 12), + GATE_VPP1_1(CLK_VPP1_LARB6_FAKE_ENG, "vpp1_larb6_fake_eng", "top_vpp", 13), + GATE_VPP1_1(CLK_VPP1_HDMI_META, "vpp1_hdmi_meta", "top_vpp", 16), + GATE_VPP1_1(CLK_VPP1_VPP_SPLIT_HDMI, "vpp1_vpp_split_hdmi", "top_vpp", 17), + GATE_VPP1_1(CLK_VPP1_DGI_IN, "vpp1_dgi_in", "top_vpp", 18), + GATE_VPP1_1(CLK_VPP1_DGI_OUT, "vpp1_dgi_out", "top_vpp", 19), + GATE_VPP1_1(CLK_VPP1_VPP_SPLIT_DGI, "vpp1_vpp_split_dgi", "top_vpp", 20), + GATE_VPP1_1(CLK_VPP1_DL_CON_OCC, "vpp1_dl_con_occ", "top_vpp", 21), + GATE_VPP1_1(CLK_VPP1_VPP_SPLIT_26M, "vpp1_vpp_split_26m", "top_vpp", 26), +}; + +static const struct mtk_clk_desc vpp1_desc = { + .clks = vpp1_clks, + .num_clks = ARRAY_SIZE(vpp1_clks), +}; + +static const struct platform_device_id clk_mt8188_vpp1_id_table[] = { + { .name = "clk-mt8188-vpp1", .driver_data = (kernel_ulong_t)&vpp1_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, clk_mt8188_vpp1_id_table); + +static struct platform_driver clk_mt8188_vpp1_drv = { + .probe = mtk_clk_pdev_probe, + .remove = mtk_clk_pdev_remove, + .driver = { + .name = "clk-mt8188-vpp1", + }, + .id_table = clk_mt8188_vpp1_id_table, +}; +module_platform_driver(clk_mt8188_vpp1_drv); +MODULE_LICENSE("GPL"); -- GitLab From f42b9e9a43e300ef94c3dc0381cc60f50e46e1fe Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:19 +0800 Subject: [PATCH 1844/5631] clk: mediatek: Add MT8188 wpesys clock support Add MT8188 wpesys clock controllers which provide clock gate control in Wrapping Engine. Signed-off-by: Garmin.Chang Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-18-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + drivers/clk/mediatek/clk-mt8188-wpe.c | 103 ++++++++++++++++++++++++++ 3 files changed, 111 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-wpe.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 70c139256236..998cf4f559ea 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -748,6 +748,13 @@ config COMMON_CLK_MT8188_VPPSYS help This driver supports MediaTek MT8188 vppsys0/1 clocks. +config COMMON_CLK_MT8188_WPESYS + tristate "Clock driver for MediaTek MT8188 wpesys" + depends on COMMON_CLK_MT8188_IMGSYS + default COMMON_CLK_MT8188_IMGSYS + help + This driver supports MediaTek MT8188 Warp Engine clocks. + config COMMON_CLK_MT8192 tristate "Clock driver for MediaTek MT8192" depends on ARM64 || COMPILE_TEST diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index dec47ef9830c..df4e2da1ca49 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -110,6 +110,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o obj-$(CONFIG_COMMON_CLK_MT8188_VDOSYS) += clk-mt8188-vdo0.o clk-mt8188-vdo1.o obj-$(CONFIG_COMMON_CLK_MT8188_VENCSYS) += clk-mt8188-venc.o obj-$(CONFIG_COMMON_CLK_MT8188_VPPSYS) += clk-mt8188-vpp0.o clk-mt8188-vpp1.o +obj-$(CONFIG_COMMON_CLK_MT8188_WPESYS) += clk-mt8188-wpe.o obj-$(CONFIG_COMMON_CLK_MT8192) += clk-mt8192-apmixedsys.o clk-mt8192.o obj-$(CONFIG_COMMON_CLK_MT8192_AUDSYS) += clk-mt8192-aud.o obj-$(CONFIG_COMMON_CLK_MT8192_CAMSYS) += clk-mt8192-cam.o diff --git a/drivers/clk/mediatek/clk-mt8188-wpe.c b/drivers/clk/mediatek/clk-mt8188-wpe.c new file mode 100644 index 000000000000..5abded13cece --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-wpe.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs wpe_top_cg_regs = { + .set_ofs = 0x0, + .clr_ofs = 0x0, + .sta_ofs = 0x0, +}; + +static const struct mtk_gate_regs wpe_vpp0_0_cg_regs = { + .set_ofs = 0x58, + .clr_ofs = 0x58, + .sta_ofs = 0x58, +}; + +static const struct mtk_gate_regs wpe_vpp0_1_cg_regs = { + .set_ofs = 0x5c, + .clr_ofs = 0x5c, + .sta_ofs = 0x5c, +}; + +#define GATE_WPE_TOP(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &wpe_top_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_WPE_VPP0_0(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &wpe_vpp0_0_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +#define GATE_WPE_VPP0_1(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &wpe_vpp0_1_cg_regs, _shift, &mtk_clk_gate_ops_no_setclr_inv) + +static const struct mtk_gate wpe_top_clks[] = { + GATE_WPE_TOP(CLK_WPE_TOP_WPE_VPP0, "wpe_wpe_vpp0", "top_wpe_vpp", 16), + GATE_WPE_TOP(CLK_WPE_TOP_SMI_LARB7, "wpe_smi_larb7", "top_wpe_vpp", 18), + GATE_WPE_TOP(CLK_WPE_TOP_WPESYS_EVENT_TX, "wpe_wpesys_event_tx", "top_wpe_vpp", 20), + GATE_WPE_TOP(CLK_WPE_TOP_SMI_LARB7_PCLK_EN, "wpe_smi_larb7_p_en", "top_wpe_vpp", 24), +}; + +static const struct mtk_gate wpe_vpp0_clks[] = { + /* WPE_VPP00 */ + GATE_WPE_VPP0_0(CLK_WPE_VPP0_VGEN, "wpe_vpp0_vgen", "top_img", 0), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_EXT, "wpe_vpp0_ext", "top_img", 1), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_VFC, "wpe_vpp0_vfc", "top_img", 2), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH0_TOP, "wpe_vpp0_cach0_top", "top_img", 3), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH0_DMA, "wpe_vpp0_cach0_dma", "top_img", 4), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH1_TOP, "wpe_vpp0_cach1_top", "top_img", 5), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH1_DMA, "wpe_vpp0_cach1_dma", "top_img", 6), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH2_TOP, "wpe_vpp0_cach2_top", "top_img", 7), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH2_DMA, "wpe_vpp0_cach2_dma", "top_img", 8), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH3_TOP, "wpe_vpp0_cach3_top", "top_img", 9), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_CACH3_DMA, "wpe_vpp0_cach3_dma", "top_img", 10), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_PSP, "wpe_vpp0_psp", "top_img", 11), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_PSP2, "wpe_vpp0_psp2", "top_img", 12), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_SYNC, "wpe_vpp0_sync", "top_img", 13), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_C24, "wpe_vpp0_c24", "top_img", 14), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_MDP_CROP, "wpe_vpp0_mdp_crop", "top_img", 15), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_ISP_CROP, "wpe_vpp0_isp_crop", "top_img", 16), + GATE_WPE_VPP0_0(CLK_WPE_VPP0_TOP, "wpe_vpp0_top", "top_img", 17), + /* WPE_VPP0_1 */ + GATE_WPE_VPP0_1(CLK_WPE_VPP0_VECI, "wpe_vpp0_veci", "top_img", 0), + GATE_WPE_VPP0_1(CLK_WPE_VPP0_VEC2I, "wpe_vpp0_vec2i", "top_img", 1), + GATE_WPE_VPP0_1(CLK_WPE_VPP0_VEC3I, "wpe_vpp0_vec3i", "top_img", 2), + GATE_WPE_VPP0_1(CLK_WPE_VPP0_WPEO, "wpe_vpp0_wpeo", "top_img", 3), + GATE_WPE_VPP0_1(CLK_WPE_VPP0_MSKO, "wpe_vpp0_msko", "top_img", 4), +}; + +static const struct mtk_clk_desc wpe_top_desc = { + .clks = wpe_top_clks, + .num_clks = ARRAY_SIZE(wpe_top_clks), +}; + +static const struct mtk_clk_desc wpe_vpp0_desc = { + .clks = wpe_vpp0_clks, + .num_clks = ARRAY_SIZE(wpe_vpp0_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_wpe[] = { + { .compatible = "mediatek,mt8188-wpesys", .data = &wpe_top_desc }, + { .compatible = "mediatek,mt8188-wpesys-vpp0", .data = &wpe_vpp0_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, clk_mt8188_vpp1_id_table); + +static struct platform_driver clk_mt8188_wpe_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-wpe", + .of_match_table = of_match_clk_mt8188_wpe, + }, +}; + +module_platform_driver(clk_mt8188_wpe_drv); +MODULE_LICENSE("GPL"); -- GitLab From 1b5e5299dd35da0dff2d454826a60870237837da Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:20 +0800 Subject: [PATCH 1845/5631] clk: mediatek: Add MT8188 imp i2c wrapper clock support Add MT8188 imp i2c wrapper clock controllers which provide clock gate control in I2C IP blocks. Signed-off-by: Garmin.Chang Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-19-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 ++ drivers/clk/mediatek/Makefile | 1 + .../clk/mediatek/clk-mt8188-imp_iic_wrap.c | 80 +++++++++++++++++++ 3 files changed, 88 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 998cf4f559ea..afabdffded50 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -706,6 +706,13 @@ config COMMON_CLK_MT8188_IMGSYS help This driver supports MediaTek MT8188 imgsys and imgsys2 clocks. +config COMMON_CLK_MT8188_IMP_IIC_WRAP + tristate "Clock driver for MediaTek MT8188 imp_iic_wrap" + depends on COMMON_CLK_MT8188 + default COMMON_CLK_MT8188 + help + This driver supports MediaTek MT8188 I2C/I3C clocks. + config COMMON_CLK_MT8188_IPESYS tristate "Clock driver for MediaTek MT8188 ipesys" depends on COMMON_CLK_MT8188_IMGSYS diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index df4e2da1ca49..7ef67ac366d8 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -104,6 +104,7 @@ obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o +obj-$(CONFIG_COMMON_CLK_MT8188_IMP_IIC_WRAP) += clk-mt8188-imp_iic_wrap.o obj-$(CONFIG_COMMON_CLK_MT8188_IPESYS) += clk-mt8188-ipe.o obj-$(CONFIG_COMMON_CLK_MT8188_MFGCFG) += clk-mt8188-mfg.o obj-$(CONFIG_COMMON_CLK_MT8188_VDECSYS) += clk-mt8188-vdec.o diff --git a/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c new file mode 100644 index 000000000000..2238d2984320 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs imp_iic_wrap_cg_regs = { + .set_ofs = 0xe08, + .clr_ofs = 0xe04, + .sta_ofs = 0xe00, +}; + +#define GATE_IMP_IIC_WRAP(_id, _name, _parent, _shift) \ + GATE_MTK_FLAGS(_id, _name, _parent, &imp_iic_wrap_cg_regs, _shift, \ + &mtk_clk_gate_ops_setclr, CLK_OPS_PARENT_ENABLE) + +static const struct mtk_gate imp_iic_wrap_c_clks[] = { + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C0, + "imp_iic_wrap_c_ap_clock_i2c0", "top_i2c", 0), + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C2, + "imp_iic_wrap_c_ap_clock_i2c2", "top_i2c", 1), + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_C_AP_CLOCK_I2C3, + "imp_iic_wrap_c_ap_clock_i2c3", "top_i2c", 2), +}; + +static const struct mtk_gate imp_iic_wrap_w_clks[] = { + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C1, + "imp_iic_wrap_w_ap_clock_i2c1", "top_i2c", 0), + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_W_AP_CLOCK_I2C4, + "imp_iic_wrap_w_ap_clock_i2c4", "top_i2c", 1), +}; + +static const struct mtk_gate imp_iic_wrap_en_clks[] = { + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C5, + "imp_iic_wrap_en_ap_clock_i2c5", "top_i2c", 0), + GATE_IMP_IIC_WRAP(CLK_IMP_IIC_WRAP_EN_AP_CLOCK_I2C6, + "imp_iic_wrap_en_ap_clock_i2c6", "top_i2c", 1), +}; + +static const struct mtk_clk_desc imp_iic_wrap_c_desc = { + .clks = imp_iic_wrap_c_clks, + .num_clks = ARRAY_SIZE(imp_iic_wrap_c_clks), +}; + +static const struct mtk_clk_desc imp_iic_wrap_w_desc = { + .clks = imp_iic_wrap_w_clks, + .num_clks = ARRAY_SIZE(imp_iic_wrap_w_clks), +}; + +static const struct mtk_clk_desc imp_iic_wrap_en_desc = { + .clks = imp_iic_wrap_en_clks, + .num_clks = ARRAY_SIZE(imp_iic_wrap_en_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_imp_iic_wrap[] = { + { .compatible = "mediatek,mt8188-imp-iic-wrap-c", .data = &imp_iic_wrap_c_desc }, + { .compatible = "mediatek,mt8188-imp-iic-wrap-w", .data = &imp_iic_wrap_w_desc }, + { .compatible = "mediatek,mt8188-imp-iic-wrap-en", .data = &imp_iic_wrap_en_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_imp_iic_wrap); + +static struct platform_driver clk_mt8188_imp_iic_wrap_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-imp_iic_wrap", + .of_match_table = of_match_clk_mt8188_imp_iic_wrap, + }, +}; + +module_platform_driver(clk_mt8188_imp_iic_wrap_drv); +MODULE_LICENSE("GPL"); -- GitLab From 0d2f2cefba64729a0730ce183ad58cf3e7929b94 Mon Sep 17 00:00:00 2001 From: "Garmin.Chang" Date: Fri, 31 Mar 2023 20:36:21 +0800 Subject: [PATCH 1846/5631] clk: mediatek: Add MT8188 adsp clock support Add MT8188 adsp clock controller which provides clock gate control for Audio DSP. Signed-off-by: Garmin.Chang Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230331123621.16167-20-Garmin.Chang@mediatek.com Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/Kconfig | 7 +++ drivers/clk/mediatek/Makefile | 1 + .../clk/mediatek/clk-mt8188-adsp_audio26m.c | 48 +++++++++++++++++++ 3 files changed, 56 insertions(+) create mode 100644 drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index afabdffded50..99e67c07e638 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -692,6 +692,13 @@ config COMMON_CLK_MT8188 help This driver supports MediaTek MT8188 clocks. +config COMMON_CLK_MT8188_ADSP_AUDIO26M + tristate "Clock driver for MediaTek MT8188 adsp audio26m" + depends on COMMON_CLK_MT8188 + default COMMON_CLK_MT8188 + help + This driver supports MediaTek MT8188 adsp audio26m clocks. + config COMMON_CLK_MT8188_CAMSYS tristate "Clock driver for MediaTek MT8188 camsys" depends on COMMON_CLK_MT8188_VPPSYS diff --git a/drivers/clk/mediatek/Makefile b/drivers/clk/mediatek/Makefile index 7ef67ac366d8..dbeaa5b41177 100644 --- a/drivers/clk/mediatek/Makefile +++ b/drivers/clk/mediatek/Makefile @@ -102,6 +102,7 @@ obj-$(CONFIG_COMMON_CLK_MT8186_VENCSYS) += clk-mt8186-venc.o obj-$(CONFIG_COMMON_CLK_MT8186_WPESYS) += clk-mt8186-wpe.o obj-$(CONFIG_COMMON_CLK_MT8188) += clk-mt8188-apmixedsys.o clk-mt8188-topckgen.o \ clk-mt8188-peri_ao.o clk-mt8188-infra_ao.o +obj-$(CONFIG_COMMON_CLK_MT8188_ADSP_AUDIO26M) += clk-mt8188-adsp_audio26m.o obj-$(CONFIG_COMMON_CLK_MT8188_CAMSYS) += clk-mt8188-cam.o clk-mt8188-ccu.o obj-$(CONFIG_COMMON_CLK_MT8188_IMGSYS) += clk-mt8188-img.o obj-$(CONFIG_COMMON_CLK_MT8188_IMP_IIC_WRAP) += clk-mt8188-imp_iic_wrap.o diff --git a/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c b/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c new file mode 100644 index 000000000000..b3c31ffff931 --- /dev/null +++ b/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 MediaTek Inc. + * Author: Garmin Chang + */ + +#include +#include +#include + +#include "clk-gate.h" +#include "clk-mtk.h" + +static const struct mtk_gate_regs adsp_audio26m_cg_regs = { + .set_ofs = 0x80, + .clr_ofs = 0x80, + .sta_ofs = 0x80, +}; + +#define GATE_ADSP_FLAGS(_id, _name, _parent, _shift) \ + GATE_MTK(_id, _name, _parent, &adsp_audio26m_cg_regs, _shift, \ + &mtk_clk_gate_ops_no_setclr) + +static const struct mtk_gate adsp_audio26m_clks[] = { + GATE_ADSP_FLAGS(CLK_AUDIODSP_AUDIO26M, "audiodsp_audio26m", "clk26m", 3), +}; + +static const struct mtk_clk_desc adsp_audio26m_desc = { + .clks = adsp_audio26m_clks, + .num_clks = ARRAY_SIZE(adsp_audio26m_clks), +}; + +static const struct of_device_id of_match_clk_mt8188_adsp_audio26m[] = { + { .compatible = "mediatek,mt8188-adsp-audio26m", .data = &adsp_audio26m_desc }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_adsp_audio26m); + +static struct platform_driver clk_mt8188_adsp_audio26m_drv = { + .probe = mtk_clk_simple_probe, + .remove = mtk_clk_simple_remove, + .driver = { + .name = "clk-mt8188-adsp_audio26m", + .of_match_table = of_match_clk_mt8188_adsp_audio26m, + }, +}; +module_platform_driver(clk_mt8188_adsp_audio26m_drv); +MODULE_LICENSE("GPL"); -- GitLab From 1aff44abf68a8000fcb3502fc2b704f20de4535f Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 13:28:16 -0500 Subject: [PATCH 1847/5631] openrisc: Use common of_get_cpu_node() instead of open-coding The common of_get_cpu_node() is equivalent to setup_find_cpu_node(), so use it instead. Signed-off-by: Rob Herring Signed-off-by: Stafford Horne --- arch/openrisc/kernel/setup.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 0cd04d936a7a..9cf7fb60441f 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -152,21 +152,6 @@ static void print_cpuinfo(void) printk(KERN_INFO "-- custom unit(s)\n"); } -static struct device_node *setup_find_cpu_node(int cpu) -{ - u32 hwid; - struct device_node *cpun; - - for_each_of_cpu_node(cpun) { - if (of_property_read_u32(cpun, "reg", &hwid)) - continue; - if (hwid == cpu) - return cpun; - } - - return NULL; -} - void __init setup_cpuinfo(void) { struct device_node *cpu; @@ -175,7 +160,7 @@ void __init setup_cpuinfo(void) int cpu_id = smp_processor_id(); struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id]; - cpu = setup_find_cpu_node(cpu_id); + cpu = of_get_cpu_node(cpu_id, NULL); if (!cpu) panic("Couldn't find CPU%d in device tree...\n", cpu_id); @@ -255,7 +240,7 @@ static inline unsigned long extract_value(unsigned long reg, unsigned long mask) void calibrate_delay(void) { const int *val; - struct device_node *cpu = setup_find_cpu_node(smp_processor_id()); + struct device_node *cpu = of_get_cpu_node(smp_processor_id(), NULL); val = of_get_property(cpu, "clock-frequency", NULL); if (!val) -- GitLab From f326ea63ecc683b3dc88d8ee4f598598d4ed3b39 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 1 Apr 2023 12:09:26 +0200 Subject: [PATCH 1848/5631] driver core: class: fix slab-use-after-free Read in class_register() Syzbot found that we had forgotten to unregister the lock_class_key when using it in commit dcfbb67e48a2 ("driver core: class: use lock_class_key already present in struct subsys_private") so fix that up and correctly release it when done. Cc: "Rafael J. Wysocki" Reported-and-tested-by: Fixes: dcfbb67e48a2 ("driver core: class: use lock_class_key already present in struct subsys_private") Link: https://lore.kernel.org/r/2023040126-blandness-duckling-bd55@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/base/class.c b/drivers/base/class.c index 06b96d6faa19..65502bd7d5c5 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -103,6 +103,7 @@ static void class_release(struct kobject *kobj) pr_debug("class '%s' does not have a release() function, " "be careful\n", class->name); + lockdep_unregister_key(&cp->lock_key); kfree(cp); } -- GitLab From ce38f3fc0f87a358a9560a3815265a94f1b38c37 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 1 Apr 2023 17:06:51 +0200 Subject: [PATCH 1849/5631] power: supply: axp288_charger: Use alt usb-id extcon on some x86 android tablets x86 ACPI boards which ship with only Android as their factory image may have pretty broken ACPI tables. This includes broken _AEI ACPI GPIO event handlers, which are normally used to listen to the micro-USB ID pin and: 1. Switch the USB-mux to the host / device USB controllers 2. Disable Vbus path before enabling the 5V boost (AXP reg 0x30 bit 7) 3. Turn 5V Vboost on / off On non broken systems where this is not done through an ACPI GPIO event handler, there is an ACPI INT3496 device describing the involved GPIOs which are handled by the extcon-intel-int3496 driver; and axp288-charger.ko listens to this extcon-device and disables the Vbus path when necessary. On x86 Android boards, with broken ACPI GPIO event handlers, these are disabled by acpi_quirk_skip_gpio_event_handlers() and an intel-int3496 extcon device is manually instantiated by x86-android-tablets.ko . Add support to the axp288-charger code for this setup, so that it properly disables the Vbus path when necessary. Note this uses acpi_quirk_skip_gpio_event_handlers() to identify these systems, to avoid the need to add a separate DMI match table for this. Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/axp288_charger.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c index 15219ed43ce9..b5903193e2f9 100644 --- a/drivers/power/supply/axp288_charger.c +++ b/drivers/power/supply/axp288_charger.c @@ -836,6 +836,7 @@ static int axp288_charger_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent); struct power_supply_config charger_cfg = {}; + const char *extcon_name = NULL; unsigned int val; /* @@ -872,8 +873,18 @@ static int axp288_charger_probe(struct platform_device *pdev) return PTR_ERR(info->cable.edev); } - if (acpi_dev_present(USB_HOST_EXTCON_HID, NULL, -1)) { - info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_NAME); + /* + * On devices with broken ACPI GPIO event handlers there also is no ACPI + * "INT3496" (USB_HOST_EXTCON_HID) device. x86-android-tablets.ko + * instantiates an "intel-int3496" extcon on these devs as a workaround. + */ + if (acpi_quirk_skip_gpio_event_handlers()) + extcon_name = "intel-int3496"; + else if (acpi_dev_present(USB_HOST_EXTCON_HID, NULL, -1)) + extcon_name = USB_HOST_EXTCON_NAME; + + if (extcon_name) { + info->otg.cable = extcon_get_extcon_dev(extcon_name); if (IS_ERR(info->otg.cable)) { dev_err_probe(dev, PTR_ERR(info->otg.cable), "extcon_get_extcon_dev(%s) failed\n", -- GitLab From 8fb1bcd0baffd42fc44e6fb6f0633914cd48ec8d Mon Sep 17 00:00:00 2001 From: "Pierre-Loup A. Griffais" Date: Fri, 24 Mar 2023 10:40:39 -0700 Subject: [PATCH 1850/5631] Input: xpad - treat Qanba controllers as Xbox360 controllers They act that way in PC mode. Reviewed-by: Lyude Paul Signed-off-by: Pierre-Loup A. Griffais Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230324040446.3487725-2-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 49ae963e5f9d..c2c688156b2e 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -493,6 +493,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOXONE_VENDOR(0x24c6), /* PowerA Controllers */ XPAD_XBOX360_VENDOR(0x2563), /* OneXPlayer Gamepad */ XPAD_XBOX360_VENDOR(0x260d), /* Dareu H101 */ + XPAD_XBOX360_VENDOR(0x2c22), /* Qanba Controllers */ XPAD_XBOX360_VENDOR(0x2dc8), /* 8BitDo Pro 2 Wired Controller */ XPAD_XBOXONE_VENDOR(0x2dc8), /* 8BitDo Pro 2 Wired Controller for Xbox */ XPAD_XBOXONE_VENDOR(0x2e24), /* Hyperkin Duke X-Box One pad */ -- GitLab From db7220c48d8d71476f881a7ae1285e1df4105409 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Fri, 24 Mar 2023 10:42:27 -0700 Subject: [PATCH 1851/5631] Input: xpad - fix support for some third-party controllers Some third-party controllers, such as the HORPIAD FPS for Nintendo Switch and Gamesir-G3w, require a specific packet that the first-party XInput driver sends before it will start sending reports. It's not currently known what this packet does, but since the first-party driver always sends it's unlikely that this could cause issues with existing controllers. Co-authored-by: Andrey Smirnov Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230324040446.3487725-3-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index c2c688156b2e..260f91fef427 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -264,6 +264,7 @@ static const struct xpad_device { { 0x0f0d, 0x0067, "HORIPAD ONE", 0, XTYPE_XBOXONE }, { 0x0f0d, 0x0078, "Hori Real Arcade Pro V Kai Xbox One", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x0f0d, 0x00c5, "Hori Fighting Commander ONE", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, + { 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX }, { 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX }, { 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX }, @@ -2013,6 +2014,28 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id goto err_free_in_urb; } + if (xpad->xtype == XTYPE_XBOX360) { + /* + * Some third-party controllers Xbox 360-style controllers + * require this message to finish initialization. + */ + u8 dummy[20]; + + error = usb_control_msg_recv(udev, 0, + /* bRequest */ 0x01, + /* bmRequestType */ + USB_TYPE_VENDOR | USB_DIR_IN | + USB_RECIP_INTERFACE, + /* wValue */ 0x100, + /* wIndex */ 0x00, + dummy, sizeof(dummy), + 25, GFP_KERNEL); + if (error) + dev_warn(&xpad->dev->dev, + "unable to receive magic message: %d\n", + error); + } + ep_irq_in = ep_irq_out = NULL; for (i = 0; i < 2; i++) { -- GitLab From 57d94d150d17754ae1b4e87e9a883155cbb3ab05 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 1 Apr 2023 14:21:43 -0700 Subject: [PATCH 1852/5631] Input: add a new Novatek NVT-ts driver Add a new driver for the Novatek i2c touchscreen controller as found on the Acer Iconia One 7 B1-750 tablet. Unfortunately the touchscreen controller model-number is unknown. Even with the tablet opened up it is impossible to read the model-number. Android calls this a "NVT-ts" touchscreen, but that may apply to other Novatek controller models too. This appears to be the same controller as the one supported by https://github.com/advx9600/android/blob/master/touchscreen/NVTtouch_Android4.0/NVTtouch.c but unfortunately that does not give us a model-number either. Signed-off-by: Hans de Goede Reviewed-by: Jeff LaBundy Link: https://lore.kernel.org/r/20230326212308.55730-1-hdegoede@redhat.com Signed-off-by: Dmitry Torokhov --- MAINTAINERS | 6 + drivers/input/touchscreen/Kconfig | 10 + drivers/input/touchscreen/Makefile | 1 + drivers/input/touchscreen/novatek-nvt-ts.c | 301 +++++++++++++++++++++ 4 files changed, 318 insertions(+) create mode 100644 drivers/input/touchscreen/novatek-nvt-ts.c diff --git a/MAINTAINERS b/MAINTAINERS index ec57c42ed544..2b073facf399 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14781,6 +14781,12 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/nolibc.git F: tools/include/nolibc/ F: tools/testing/selftests/nolibc/ +NOVATEK NVT-TS I2C TOUCHSCREEN DRIVER +M: Hans de Goede +L: linux-input@vger.kernel.org +S: Maintained +F: drivers/input/touchscreen/novatek-nvt-ts.c + NSDEPS M: Matthias Maennich S: Maintained diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 1a2049b336a6..1feecd7ed3cb 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -654,6 +654,16 @@ config TOUCHSCREEN_MTOUCH To compile this driver as a module, choose M here: the module will be called mtouch. +config TOUCHSCREEN_NOVATEK_NVT_TS + tristate "Novatek NVT-ts touchscreen support" + depends on I2C + help + Say Y here if you have a Novatek NVT-ts touchscreen. + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called novatek-nvt-ts. + config TOUCHSCREEN_IMAGIS tristate "Imagis touchscreen support" depends on I2C diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index f2fd28cc34a6..159cd5136fdb 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_TOUCHSCREEN_MMS114) += mms114.o obj-$(CONFIG_TOUCHSCREEN_MSG2638) += msg2638.o obj-$(CONFIG_TOUCHSCREEN_MTOUCH) += mtouch.o obj-$(CONFIG_TOUCHSCREEN_MK712) += mk712.o +obj-$(CONFIG_TOUCHSCREEN_NOVATEK_NVT_TS) += novatek-nvt-ts.o obj-$(CONFIG_TOUCHSCREEN_HP600) += hp680_ts_input.o obj-$(CONFIG_TOUCHSCREEN_HP7XX) += jornada720_ts.o obj-$(CONFIG_TOUCHSCREEN_IPAQ_MICRO) += ipaq-micro-ts.o diff --git a/drivers/input/touchscreen/novatek-nvt-ts.c b/drivers/input/touchscreen/novatek-nvt-ts.c new file mode 100644 index 000000000000..3e551f9d31d7 --- /dev/null +++ b/drivers/input/touchscreen/novatek-nvt-ts.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Novatek i2c touchscreen controller as found on + * the Acer Iconia One 7 B1-750 tablet. The Touchscreen controller + * model-number is unknown. Android calls this a "NVT-ts" touchscreen, + * but that may apply to other Novatek controller models too. + * + * Copyright (c) 2023 Hans de Goede + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define NVT_TS_TOUCH_START 0x00 +#define NVT_TS_TOUCH_SIZE 6 + +#define NVT_TS_PARAMETERS_START 0x78 +/* These are offsets from NVT_TS_PARAMETERS_START */ +#define NVT_TS_PARAMS_WIDTH 0x04 +#define NVT_TS_PARAMS_HEIGHT 0x06 +#define NVT_TS_PARAMS_MAX_TOUCH 0x09 +#define NVT_TS_PARAMS_MAX_BUTTONS 0x0a +#define NVT_TS_PARAMS_IRQ_TYPE 0x0b +#define NVT_TS_PARAMS_WAKE_TYPE 0x0c +#define NVT_TS_PARAMS_CHIP_ID 0x0e +#define NVT_TS_PARAMS_SIZE 0x0f + +#define NVT_TS_SUPPORTED_WAKE_TYPE 0x05 +#define NVT_TS_SUPPORTED_CHIP_ID 0x05 + +#define NVT_TS_MAX_TOUCHES 10 +#define NVT_TS_MAX_SIZE 4096 + +#define NVT_TS_TOUCH_INVALID 0xff +#define NVT_TS_TOUCH_SLOT_SHIFT 3 +#define NVT_TS_TOUCH_TYPE_MASK GENMASK(2, 0) +#define NVT_TS_TOUCH_NEW 1 +#define NVT_TS_TOUCH_UPDATE 2 +#define NVT_TS_TOUCH_RELEASE 3 + +static const int nvt_ts_irq_type[4] = { + IRQF_TRIGGER_RISING, + IRQF_TRIGGER_FALLING, + IRQF_TRIGGER_LOW, + IRQF_TRIGGER_HIGH +}; + +struct nvt_ts_data { + struct i2c_client *client; + struct input_dev *input; + struct gpio_desc *reset_gpio; + struct touchscreen_properties prop; + int max_touches; + u8 buf[NVT_TS_TOUCH_SIZE * NVT_TS_MAX_TOUCHES]; +}; + +static int nvt_ts_read_data(struct i2c_client *client, u8 reg, u8 *data, int count) +{ + struct i2c_msg msg[2] = { + { + .addr = client->addr, + .len = 1, + .buf = ®, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .len = count, + .buf = data, + } + }; + int ret; + + ret = i2c_transfer(client->adapter, msg, ARRAY_SIZE(msg)); + if (ret != ARRAY_SIZE(msg)) { + dev_err(&client->dev, "Error reading from 0x%02x: %d\n", reg, ret); + return (ret < 0) ? ret : -EIO; + } + + return 0; +} + +static irqreturn_t nvt_ts_irq(int irq, void *dev_id) +{ + struct nvt_ts_data *data = dev_id; + struct device *dev = &data->client->dev; + int i, error, slot, x, y; + bool active; + u8 *touch; + + error = nvt_ts_read_data(data->client, NVT_TS_TOUCH_START, data->buf, + data->max_touches * NVT_TS_TOUCH_SIZE); + if (error) + return IRQ_HANDLED; + + for (i = 0; i < data->max_touches; i++) { + touch = &data->buf[i * NVT_TS_TOUCH_SIZE]; + + if (touch[0] == NVT_TS_TOUCH_INVALID) + continue; + + slot = touch[0] >> NVT_TS_TOUCH_SLOT_SHIFT; + if (slot < 1 || slot > data->max_touches) { + dev_warn(dev, "slot %d out of range, ignoring\n", slot); + continue; + } + + switch (touch[0] & NVT_TS_TOUCH_TYPE_MASK) { + case NVT_TS_TOUCH_NEW: + case NVT_TS_TOUCH_UPDATE: + active = true; + break; + case NVT_TS_TOUCH_RELEASE: + active = false; + break; + default: + dev_warn(dev, "slot %d unknown state %d\n", slot, touch[0] & 7); + continue; + } + + slot--; + x = (touch[1] << 4) | (touch[3] >> 4); + y = (touch[2] << 4) | (touch[3] & 0x0f); + + input_mt_slot(data->input, slot); + input_mt_report_slot_state(data->input, MT_TOOL_FINGER, active); + touchscreen_report_pos(data->input, &data->prop, x, y, true); + } + + input_mt_sync_frame(data->input); + input_sync(data->input); + + return IRQ_HANDLED; +} + +static int nvt_ts_start(struct input_dev *dev) +{ + struct nvt_ts_data *data = input_get_drvdata(dev); + + enable_irq(data->client->irq); + gpiod_set_value_cansleep(data->reset_gpio, 0); + + return 0; +} + +static void nvt_ts_stop(struct input_dev *dev) +{ + struct nvt_ts_data *data = input_get_drvdata(dev); + + disable_irq(data->client->irq); + gpiod_set_value_cansleep(data->reset_gpio, 1); +} + +static int nvt_ts_suspend(struct device *dev) +{ + struct nvt_ts_data *data = i2c_get_clientdata(to_i2c_client(dev)); + + mutex_lock(&data->input->mutex); + if (input_device_enabled(data->input)) + nvt_ts_stop(data->input); + mutex_unlock(&data->input->mutex); + + return 0; +} + +static int nvt_ts_resume(struct device *dev) +{ + struct nvt_ts_data *data = i2c_get_clientdata(to_i2c_client(dev)); + + mutex_lock(&data->input->mutex); + if (input_device_enabled(data->input)) + nvt_ts_start(data->input); + mutex_unlock(&data->input->mutex); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(nvt_ts_pm_ops, nvt_ts_suspend, nvt_ts_resume); + +static int nvt_ts_probe(struct i2c_client *client) +{ + struct device *dev = &client->dev; + int error, width, height, irq_type; + struct nvt_ts_data *data; + struct input_dev *input; + + if (!client->irq) { + dev_err(dev, "Error no irq specified\n"); + return -EINVAL; + } + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->client = client; + i2c_set_clientdata(client, data); + + data->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + error = PTR_ERR_OR_ZERO(data->reset_gpio); + if (error) { + dev_err(dev, "failed to request reset GPIO: %d\n", error); + return error; + } + + /* Wait for controller to come out of reset before params read */ + msleep(100); + error = nvt_ts_read_data(data->client, NVT_TS_PARAMETERS_START, + data->buf, NVT_TS_PARAMS_SIZE); + gpiod_set_value_cansleep(data->reset_gpio, 1); /* Put back in reset */ + if (error) + return error; + + width = get_unaligned_be16(&data->buf[NVT_TS_PARAMS_WIDTH]); + height = get_unaligned_be16(&data->buf[NVT_TS_PARAMS_HEIGHT]); + data->max_touches = data->buf[NVT_TS_PARAMS_MAX_TOUCH]; + irq_type = data->buf[NVT_TS_PARAMS_IRQ_TYPE]; + + if (width > NVT_TS_MAX_SIZE || height >= NVT_TS_MAX_SIZE || + data->max_touches > NVT_TS_MAX_TOUCHES || + irq_type >= ARRAY_SIZE(nvt_ts_irq_type) || + data->buf[NVT_TS_PARAMS_WAKE_TYPE] != NVT_TS_SUPPORTED_WAKE_TYPE || + data->buf[NVT_TS_PARAMS_CHIP_ID] != NVT_TS_SUPPORTED_CHIP_ID) { + dev_err(dev, "Unsupported touchscreen parameters: %*ph\n", + NVT_TS_PARAMS_SIZE, data->buf); + return -EIO; + } + + dev_dbg(dev, "Detected %dx%d touchscreen with %d max touches\n", + width, height, data->max_touches); + + if (data->buf[NVT_TS_PARAMS_MAX_BUTTONS]) + dev_warn(dev, "Touchscreen buttons are not supported\n"); + + input = devm_input_allocate_device(dev); + if (!input) + return -ENOMEM; + + input->name = client->name; + input->id.bustype = BUS_I2C; + input->open = nvt_ts_start; + input->close = nvt_ts_stop; + + input_set_abs_params(input, ABS_MT_POSITION_X, 0, width - 1, 0, 0); + input_set_abs_params(input, ABS_MT_POSITION_Y, 0, height - 1, 0, 0); + touchscreen_parse_properties(input, true, &data->prop); + + error = input_mt_init_slots(input, data->max_touches, + INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); + if (error) + return error; + + data->input = input; + input_set_drvdata(input, data); + + error = devm_request_threaded_irq(dev, client->irq, NULL, nvt_ts_irq, + IRQF_ONESHOT | IRQF_NO_AUTOEN | + nvt_ts_irq_type[irq_type], + client->name, data); + if (error) { + dev_err(dev, "failed to request irq: %d\n", error); + return error; + } + + error = input_register_device(input); + if (error) { + dev_err(dev, "failed to request irq: %d\n", error); + return error; + } + + return 0; +} + +static const struct i2c_device_id nvt_ts_i2c_id[] = { + { "NVT-ts" }, + { } +}; +MODULE_DEVICE_TABLE(i2c, nvt_ts_i2c_id); + +static struct i2c_driver nvt_ts_driver = { + .driver = { + .name = "novatek-nvt-ts", + .pm = pm_sleep_ptr(&nvt_ts_pm_ops), + }, + .probe_new = nvt_ts_probe, + .id_table = nvt_ts_i2c_id, +}; + +module_i2c_driver(nvt_ts_driver); + +MODULE_DESCRIPTION("Novatek NVT-ts touchscreen driver"); +MODULE_AUTHOR("Hans de Goede "); +MODULE_LICENSE("GPL"); -- GitLab From fdefcbdd6f3618410a0afb2ac0071c04036f9602 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Sat, 1 Apr 2023 22:45:09 -0700 Subject: [PATCH 1853/5631] Input: Add KUnit tests for some of the input core helper functions The input subsystem doesn't currently have any unit tests, let's add a CONFIG_INPUT_KUNIT_TEST option that builds a test suite to be executed with the KUnit test infrastructure. For now, only three tests were added for some of the input core helper functions that are trivial to test: * input_test_polling: set/get poll interval and set-up a poll handler. * input_test_timestamp: set/get input event timestamps. * input_test_match_device_id: match a device by bus, vendor, product, version and events capable of handling. But having the minimal KUnit support allows to add more tests and suites as follow-up changes. The tests can be run with the following command: $ ./tools/testing/kunit/kunit.py run --kunitconfig=drivers/input/tests/ Signed-off-by: Javier Martinez Canillas Tested-by: Enric Balletbo i Serra config: powerpc-allnoconfig (https://download.01.org/0day-ci/archive/20230330/202303301815.kRKFM3NH-lkp@intel.com/config) Link: https://lore.kernel.org/r/20230330081831.2291351-1-javierm@redhat.com Signed-off-by: Dmitry Torokhov --- drivers/input/Kconfig | 10 +++ drivers/input/Makefile | 1 + drivers/input/tests/.kunitconfig | 3 + drivers/input/tests/Makefile | 3 + drivers/input/tests/input_test.c | 150 +++++++++++++++++++++++++++++++ 5 files changed, 167 insertions(+) create mode 100644 drivers/input/tests/.kunitconfig create mode 100644 drivers/input/tests/Makefile create mode 100644 drivers/input/tests/input_test.c diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index e2752f7364bc..735f90b74ee5 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -166,6 +166,16 @@ config INPUT_EVBUG To compile this driver as a module, choose M here: the module will be called evbug. +config INPUT_KUNIT_TEST + tristate "KUnit tests for Input" if !KUNIT_ALL_TESTS + depends on INPUT && KUNIT=y + default KUNIT_ALL_TESTS + help + Say Y here if you want to build the KUnit tests for the input + subsystem. + + If in doubt, say "N". + config INPUT_APMPOWER tristate "Input Power Event -> APM Bridge" if EXPERT depends on INPUT && APM_EMULATION diff --git a/drivers/input/Makefile b/drivers/input/Makefile index 2266c7d010ef..c78753274921 100644 --- a/drivers/input/Makefile +++ b/drivers/input/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_INPUT_JOYSTICK) += joystick/ obj-$(CONFIG_INPUT_TABLET) += tablet/ obj-$(CONFIG_INPUT_TOUCHSCREEN) += touchscreen/ obj-$(CONFIG_INPUT_MISC) += misc/ +obj-$(CONFIG_INPUT_KUNIT_TEST) += tests/ obj-$(CONFIG_INPUT_APMPOWER) += apm-power.o diff --git a/drivers/input/tests/.kunitconfig b/drivers/input/tests/.kunitconfig new file mode 100644 index 000000000000..2f5bedf8028e --- /dev/null +++ b/drivers/input/tests/.kunitconfig @@ -0,0 +1,3 @@ +CONFIG_KUNIT=y +CONFIG_INPUT=y +CONFIG_INPUT_KUNIT_TEST=y diff --git a/drivers/input/tests/Makefile b/drivers/input/tests/Makefile new file mode 100644 index 000000000000..90cf954181bc --- /dev/null +++ b/drivers/input/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_INPUT_KUNIT_TEST) += input_test.o diff --git a/drivers/input/tests/input_test.c b/drivers/input/tests/input_test.c new file mode 100644 index 000000000000..e5a6c1ad2167 --- /dev/null +++ b/drivers/input/tests/input_test.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit test for the input core. + * + * Copyright (c) 2023 Red Hat Inc + */ + +#include +#include + +#include + +#define POLL_INTERVAL 100 + +static int input_test_init(struct kunit *test) +{ + struct input_dev *input_dev; + int ret; + + input_dev = input_allocate_device(); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, input_dev); + + input_dev->name = "Test input device"; + input_dev->id.bustype = BUS_VIRTUAL; + input_dev->id.vendor = 1; + input_dev->id.product = 1; + input_dev->id.version = 1; + input_set_capability(input_dev, EV_KEY, BTN_LEFT); + input_set_capability(input_dev, EV_KEY, BTN_RIGHT); + + ret = input_register_device(input_dev); + if (ret) { + input_free_device(input_dev); + KUNIT_ASSERT_FAILURE(test, "Register device failed: %d", ret); + } + + test->priv = input_dev; + + return 0; +} + +static void input_test_exit(struct kunit *test) +{ + struct input_dev *input_dev = test->priv; + + input_unregister_device(input_dev); + input_free_device(input_dev); +} + +static void input_test_poll(struct input_dev *input) { } + +static void input_test_polling(struct kunit *test) +{ + struct input_dev *input_dev = test->priv; + + /* Must fail because a poll handler has not been set-up yet */ + KUNIT_ASSERT_EQ(test, input_get_poll_interval(input_dev), -EINVAL); + + KUNIT_ASSERT_EQ(test, input_setup_polling(input_dev, input_test_poll), 0); + + input_set_poll_interval(input_dev, POLL_INTERVAL); + + /* Must succeed because poll handler was set-up and poll interval set */ + KUNIT_ASSERT_EQ(test, input_get_poll_interval(input_dev), POLL_INTERVAL); +} + +static void input_test_timestamp(struct kunit *test) +{ + const ktime_t invalid_timestamp = ktime_set(0, 0); + struct input_dev *input_dev = test->priv; + ktime_t *timestamp, time; + + timestamp = input_get_timestamp(input_dev); + time = timestamp[INPUT_CLK_MONO]; + + /* The returned timestamp must always be valid */ + KUNIT_ASSERT_EQ(test, ktime_compare(time, invalid_timestamp), 1); + + time = ktime_get(); + input_set_timestamp(input_dev, time); + + timestamp = input_get_timestamp(input_dev); + /* The timestamp must be the same than set before */ + KUNIT_ASSERT_EQ(test, ktime_compare(timestamp[INPUT_CLK_MONO], time), 0); +} + +static void input_test_match_device_id(struct kunit *test) +{ + struct input_dev *input_dev = test->priv; + struct input_device_id id; + + /* + * Must match when the input device bus, vendor, product, version + * and events capable of handling are the same and fail to match + * otherwise. + */ + id.flags = INPUT_DEVICE_ID_MATCH_BUS; + id.bustype = BUS_VIRTUAL; + KUNIT_ASSERT_TRUE(test, input_match_device_id(input_dev, &id)); + + id.bustype = BUS_I2C; + KUNIT_ASSERT_FALSE(test, input_match_device_id(input_dev, &id)); + + id.flags = INPUT_DEVICE_ID_MATCH_VENDOR; + id.vendor = 1; + KUNIT_ASSERT_TRUE(test, input_match_device_id(input_dev, &id)); + + id.vendor = 2; + KUNIT_ASSERT_FALSE(test, input_match_device_id(input_dev, &id)); + + id.flags = INPUT_DEVICE_ID_MATCH_PRODUCT; + id.product = 1; + KUNIT_ASSERT_TRUE(test, input_match_device_id(input_dev, &id)); + + id.product = 2; + KUNIT_ASSERT_FALSE(test, input_match_device_id(input_dev, &id)); + + id.flags = INPUT_DEVICE_ID_MATCH_VERSION; + id.version = 1; + KUNIT_ASSERT_TRUE(test, input_match_device_id(input_dev, &id)); + + id.version = 2; + KUNIT_ASSERT_FALSE(test, input_match_device_id(input_dev, &id)); + + id.flags = INPUT_DEVICE_ID_MATCH_EVBIT; + __set_bit(EV_KEY, id.evbit); + KUNIT_ASSERT_TRUE(test, input_match_device_id(input_dev, &id)); + + __set_bit(EV_ABS, id.evbit); + KUNIT_ASSERT_FALSE(test, input_match_device_id(input_dev, &id)); +} + +static struct kunit_case input_tests[] = { + KUNIT_CASE(input_test_polling), + KUNIT_CASE(input_test_timestamp), + KUNIT_CASE(input_test_match_device_id), + { /* sentinel */ } +}; + +static struct kunit_suite input_test_suite = { + .name = "input_core", + .init = input_test_init, + .exit = input_test_exit, + .test_cases = input_tests, +}; + +kunit_test_suite(input_test_suite); + +MODULE_AUTHOR("Javier Martinez Canillas "); +MODULE_LICENSE("GPL"); -- GitLab From 43ba3d4af7a73ae958207caada6af0612d67f08e Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2023 18:47:24 +0200 Subject: [PATCH 1854/5631] pktcdvd: simplify the class_pktcdvd logic There is no need to dynamically create and destroy the class_pktcdvd structure, just make it static and remove the memory allocation logic which simplifies and cleans up the logic a lot. Cc: linux-block@vger.kernel.org Cc: Jens Axboe Link: https://lore.kernel.org/r/20230331164724.319703-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- drivers/block/pktcdvd.c | 40 ++++++++++++---------------------------- 1 file changed, 12 insertions(+), 28 deletions(-) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index ba9bbdef9ef5..79af8a59142e 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -100,7 +100,8 @@ static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */ static mempool_t psd_pool; static struct bio_set pkt_bio_set; -static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */ +/* /sys/class/pktcdvd */ +static struct class class_pktcdvd; static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ /* forward declaration */ @@ -315,8 +316,8 @@ static const struct attribute_group *pkt_groups[] = { static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) { - if (class_pktcdvd) { - pd->dev = device_create_with_groups(class_pktcdvd, NULL, + if (class_is_registered(&class_pktcdvd)) { + pd->dev = device_create_with_groups(&class_pktcdvd, NULL, MKDEV(0, 0), pd, pkt_groups, "%s", pd->name); if (IS_ERR(pd->dev)) @@ -326,7 +327,7 @@ static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd) { - if (class_pktcdvd) + if (class_is_registered(&class_pktcdvd)) device_unregister(pd->dev); } @@ -338,11 +339,6 @@ static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd) device_map show mappings *******************************************************************/ -static void class_pktcdvd_release(struct class *cls) -{ - kfree(cls); -} - static ssize_t device_map_show(const struct class *c, const struct class_attribute *attr, char *data) { @@ -405,35 +401,23 @@ static struct attribute *class_pktcdvd_attrs[] = { }; ATTRIBUTE_GROUPS(class_pktcdvd); +static struct class class_pktcdvd = { + .name = DRIVER_NAME, + .class_groups = class_pktcdvd_groups, +}; + static int pkt_sysfs_init(void) { - int ret = 0; - /* * create control files in sysfs * /sys/class/pktcdvd/... */ - class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL); - if (!class_pktcdvd) - return -ENOMEM; - class_pktcdvd->name = DRIVER_NAME; - class_pktcdvd->class_release = class_pktcdvd_release; - class_pktcdvd->class_groups = class_pktcdvd_groups; - ret = class_register(class_pktcdvd); - if (ret) { - kfree(class_pktcdvd); - class_pktcdvd = NULL; - pr_err("failed to create class pktcdvd\n"); - return ret; - } - return 0; + return class_register(&class_pktcdvd); } static void pkt_sysfs_cleanup(void) { - if (class_pktcdvd) - class_destroy(class_pktcdvd); - class_pktcdvd = NULL; + class_unregister(&class_pktcdvd); } /******************************************************************** -- GitLab From 1661f60adc3b7e6864b4cb6790d579b468bd243f Mon Sep 17 00:00:00 2001 From: Benjamin Bara Date: Sun, 2 Apr 2023 16:55:27 -0700 Subject: [PATCH 1855/5631] Input: tsc2007 - enable cansleep pendown GPIO When a hard IRQ is triggered, the soft IRQ, which decides if an actual pen down happened, should always be triggered. This enables the usage of "can_sleep" GPIO chips as "pen down" GPIO, as the value is not read during the hard IRQ anymore. This might be the case if the GPIO chip is an expander behind i2c. Signed-off-by: Benjamin Bara Signed-off-by: Richard Leitner Link: https://lore.kernel.org/r/20230328-tsc2007-sleep-v5-1-fc55e76d0ced@skidata.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/tsc2007_core.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) diff --git a/drivers/input/touchscreen/tsc2007_core.c b/drivers/input/touchscreen/tsc2007_core.c index 3c793fb70a0e..21916a30fb76 100644 --- a/drivers/input/touchscreen/tsc2007_core.c +++ b/drivers/input/touchscreen/tsc2007_core.c @@ -172,19 +172,6 @@ static irqreturn_t tsc2007_soft_irq(int irq, void *handle) return IRQ_HANDLED; } -static irqreturn_t tsc2007_hard_irq(int irq, void *handle) -{ - struct tsc2007 *ts = handle; - - if (tsc2007_is_pen_down(ts)) - return IRQ_WAKE_THREAD; - - if (ts->clear_penirq) - ts->clear_penirq(); - - return IRQ_HANDLED; -} - static void tsc2007_stop(struct tsc2007 *ts) { ts->stopped = true; @@ -226,7 +213,7 @@ static int tsc2007_get_pendown_state_gpio(struct device *dev) struct i2c_client *client = to_i2c_client(dev); struct tsc2007 *ts = i2c_get_clientdata(client); - return gpiod_get_value(ts->gpiod); + return gpiod_get_value_cansleep(ts->gpiod); } static int tsc2007_probe_properties(struct device *dev, struct tsc2007 *ts) @@ -376,7 +363,7 @@ static int tsc2007_probe(struct i2c_client *client) } err = devm_request_threaded_irq(&client->dev, ts->irq, - tsc2007_hard_irq, tsc2007_soft_irq, + NULL, tsc2007_soft_irq, IRQF_ONESHOT, client->dev.driver->name, ts); if (err) { -- GitLab From d19ec82c74a50aec614530b0e7d795913be77221 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 16:57:04 -0700 Subject: [PATCH 1856/5631] Input: edt-ft5x06 - fix indentation Matches the alignment to the open parenthesis as suggested by checkpatch. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-2-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 36 ++++++++++++++------------ 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 2746649561c7..daba6472fc65 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -241,11 +241,11 @@ static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) /* M09/M12 does not send header or CRC */ if (tsdata->version == EDT_M06) { if (rdbuf[0] != 0xaa || rdbuf[1] != 0xaa || - rdbuf[2] != datalen) { + rdbuf[2] != datalen) { tsdata->header_errors++; dev_err_ratelimited(dev, - "Unexpected header: %02x%02x%02x!\n", - rdbuf[0], rdbuf[1], rdbuf[2]); + "Unexpected header: %02x%02x%02x!\n", + rdbuf[0], rdbuf[1], rdbuf[2]); goto out; } @@ -618,7 +618,7 @@ static void edt_ft5x06_restore_reg_parameters(struct edt_ft5x06_ts_data *tsdata) tsdata->offset_y); if (reg_addr->reg_report_rate != NO_REGISTER) edt_ft5x06_register_write(tsdata, reg_addr->reg_report_rate, - tsdata->report_rate); + tsdata->report_rate); } @@ -757,7 +757,8 @@ DEFINE_SIMPLE_ATTRIBUTE(debugfs_mode_fops, edt_ft5x06_debugfs_mode_get, edt_ft5x06_debugfs_mode_set, "%llu\n"); static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, - char __user *buf, size_t count, loff_t *off) + char __user *buf, size_t count, + loff_t *off) { struct edt_ft5x06_ts_data *tsdata = file->private_data; struct i2c_client *client = tsdata->client; @@ -965,12 +966,12 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client, case 0x70: /* EDT EP0700M09 */ tsdata->version = EDT_M09; snprintf(model_name, EDT_NAME_LEN, "EP0%i%i0M09", - rdbuf[0] >> 4, rdbuf[0] & 0x0F); + rdbuf[0] >> 4, rdbuf[0] & 0x0F); break; case 0xa1: /* EDT EP1010ML00 */ tsdata->version = EDT_M09; snprintf(model_name, EDT_NAME_LEN, "EP%i%i0ML00", - rdbuf[0] >> 4, rdbuf[0] & 0x0F); + rdbuf[0] >> 4, rdbuf[0] & 0x0F); break; case 0x5a: /* Solomon Goldentek Display */ snprintf(model_name, EDT_NAME_LEN, "GKTW50SCED1R0"); @@ -1051,14 +1052,17 @@ static void edt_ft5x06_ts_get_parameters(struct edt_ft5x06_ts_data *tsdata) tsdata->offset = edt_ft5x06_register_read(tsdata, reg_addr->reg_offset); if (reg_addr->reg_offset_x != NO_REGISTER) - tsdata->offset_x = edt_ft5x06_register_read(tsdata, - reg_addr->reg_offset_x); + tsdata->offset_x = + edt_ft5x06_register_read(tsdata, + reg_addr->reg_offset_x); if (reg_addr->reg_offset_y != NO_REGISTER) - tsdata->offset_y = edt_ft5x06_register_read(tsdata, - reg_addr->reg_offset_y); + tsdata->offset_y = + edt_ft5x06_register_read(tsdata, + reg_addr->reg_offset_y); if (reg_addr->reg_report_rate != NO_REGISTER) - tsdata->report_rate = edt_ft5x06_register_read(tsdata, - reg_addr->reg_report_rate); + tsdata->report_rate = + edt_ft5x06_register_read(tsdata, + reg_addr->reg_report_rate); tsdata->num_x = EDT_DEFAULT_NUM_X; if (reg_addr->reg_num_x != NO_REGISTER) tsdata->num_x = edt_ft5x06_register_read(tsdata, @@ -1306,7 +1310,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) touchscreen_parse_properties(input, true, &tsdata->prop); error = input_mt_init_slots(input, tsdata->max_support_points, - INPUT_MT_DIRECT); + INPUT_MT_DIRECT); if (error) { dev_err(&client->dev, "Unable to init MT slots.\n"); return error; @@ -1320,8 +1324,8 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) irq_flags |= IRQF_ONESHOT; error = devm_request_threaded_irq(&client->dev, client->irq, - NULL, edt_ft5x06_ts_isr, irq_flags, - client->name, tsdata); + NULL, edt_ft5x06_ts_isr, irq_flags, + client->name, tsdata); if (error) { dev_err(&client->dev, "Unable to request touchscreen IRQ.\n"); return error; -- GitLab From 6114f4749b4662d4f444e2a184e236d9d9df9115 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 16:58:14 -0700 Subject: [PATCH 1857/5631] Input: edt-ft5x06 - remove unnecessary blank lines It removes unnecessary blank lines so that checkpatch doesn't complain anymore. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-3-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index daba6472fc65..c0ad3e4b6662 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -619,7 +619,6 @@ static void edt_ft5x06_restore_reg_parameters(struct edt_ft5x06_ts_data *tsdata) if (reg_addr->reg_report_rate != NO_REGISTER) edt_ft5x06_register_write(tsdata, reg_addr->reg_report_rate, tsdata->report_rate); - } #ifdef CONFIG_DEBUG_FS @@ -1459,7 +1458,6 @@ static int edt_ft5x06_ts_resume(struct device *dev) gpiod_set_value_cansleep(wake_gpio, 1); } - return ret; } -- GitLab From f8a2257056d9e60e4339072e8e89a5a708a99d40 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 16:58:29 -0700 Subject: [PATCH 1858/5631] Input: edt-ft5x06 - add spaces to ensure format specification It adds spaces around '-' as recommended by the Linux coding style. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-4-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index c0ad3e4b6662..c96fe6520578 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -183,11 +183,11 @@ static bool edt_ft5x06_ts_check_crc(struct edt_ft5x06_ts_data *tsdata, for (i = 0; i < buflen - 1; i++) crc ^= buf[i]; - if (crc != buf[buflen-1]) { + if (crc != buf[buflen - 1]) { tsdata->crc_errors++; dev_err_ratelimited(&tsdata->client->dev, "crc error: 0x%02x expected, got 0x%02x\n", - crc, buf[buflen-1]); + crc, buf[buflen - 1]); return false; } -- GitLab From 38e8cf7b97612a7e615e498987bd0758a65633c6 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:27:34 -0700 Subject: [PATCH 1859/5631] Input: edt-ft5x06 - don't recalculate the CRC There is no need to recalculate the CRC when the data has not changed. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-5-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index c96fe6520578..d4f39724b259 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -319,7 +319,7 @@ static int edt_ft5x06_register_write(struct edt_ft5x06_ts_data *tsdata, static int edt_ft5x06_register_read(struct edt_ft5x06_ts_data *tsdata, u8 addr) { - u8 wrbuf[2], rdbuf[2]; + u8 wrbuf[2], rdbuf[2], crc; int error; switch (tsdata->version) { @@ -333,11 +333,11 @@ static int edt_ft5x06_register_read(struct edt_ft5x06_ts_data *tsdata, if (error) return error; - if ((wrbuf[0] ^ wrbuf[1] ^ rdbuf[0]) != rdbuf[1]) { + crc = wrbuf[0] ^ wrbuf[1] ^ rdbuf[0]; + if (crc != rdbuf[1]) { dev_err(&tsdata->client->dev, "crc error: 0x%02x expected, got 0x%02x\n", - wrbuf[0] ^ wrbuf[1] ^ rdbuf[0], - rdbuf[1]); + crc, rdbuf[1]); return -EIO; } break; -- GitLab From 65c67985a0305f444f3f88f3506c6e7ee237423b Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:27:48 -0700 Subject: [PATCH 1860/5631] Input: edt-ft5x06 - remove code duplication The use of the macros M06_REG_ADDR and M06_REG_CMD avoids code duplication without impacting the application load, and reduces the chances of errors or mistakes. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-6-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index d4f39724b259..7d82f412ab15 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -75,6 +75,9 @@ #define EDT_DEFAULT_NUM_X 1024 #define EDT_DEFAULT_NUM_Y 1024 +#define M06_REG_CMD(factory) ((factory) ? 0xf3 : 0xfc) +#define M06_REG_ADDR(factory, addr) ((factory) ? (addr) & 0x7f : (addr) & 0x3f) + enum edt_pmode { EDT_PMODE_NOT_SUPPORTED, EDT_PMODE_HIBERNATE, @@ -294,8 +297,8 @@ static int edt_ft5x06_register_write(struct edt_ft5x06_ts_data *tsdata, switch (tsdata->version) { case EDT_M06: - wrbuf[0] = tsdata->factory_mode ? 0xf3 : 0xfc; - wrbuf[1] = tsdata->factory_mode ? addr & 0x7f : addr & 0x3f; + wrbuf[0] = M06_REG_CMD(tsdata->factory_mode); + wrbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); wrbuf[2] = value; wrbuf[3] = wrbuf[0] ^ wrbuf[1] ^ wrbuf[2]; return edt_ft5x06_ts_readwrite(tsdata->client, 4, @@ -324,8 +327,8 @@ static int edt_ft5x06_register_read(struct edt_ft5x06_ts_data *tsdata, switch (tsdata->version) { case EDT_M06: - wrbuf[0] = tsdata->factory_mode ? 0xf3 : 0xfc; - wrbuf[1] = tsdata->factory_mode ? addr & 0x7f : addr & 0x3f; + wrbuf[0] = M06_REG_CMD(tsdata->factory_mode); + wrbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); wrbuf[1] |= tsdata->factory_mode ? 0x80 : 0x40; error = edt_ft5x06_ts_readwrite(tsdata->client, 2, wrbuf, 2, -- GitLab From 24642661e956b268459bea31e11cbc3bc8dda136 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:36:12 -0700 Subject: [PATCH 1861/5631] Input: edt-ft5x06 - don't print error messages with dev_dbg() In some parts of the code, error messages were improperly printed with dev_dbg() calls. In those cases, dev_dbg() has been replaced with dev_err(). Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-7-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 7d82f412ab15..89958881fca1 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -783,7 +783,7 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, error = edt_ft5x06_register_write(tsdata, 0x08, 0x01); if (error) { - dev_dbg(&client->dev, + dev_err(&client->dev, "failed to write 0x08 register, error %d\n", error); goto out; } @@ -797,13 +797,13 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, if (val < 0) { error = val; - dev_dbg(&client->dev, + dev_err(&client->dev, "failed to read 0x08 register, error %d\n", error); goto out; } if (retries == 0) { - dev_dbg(&client->dev, + dev_err(&client->dev, "timed out waiting for register to settle\n"); error = -ETIMEDOUT; goto out; -- GitLab From 9dfd9708ffba1e7969af5e4ecda660151146de98 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:36:23 -0700 Subject: [PATCH 1862/5631] Input: edt-ft5x06 - convert to use regmap API It replaces custom read/write functions with regmap API, making the driver code more generic. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-8-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 424 +++++++++++++------------ 1 file changed, 214 insertions(+), 210 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 89958881fca1..8aae4c1e6b73 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -3,6 +3,7 @@ * Copyright (C) 2012 Simon Budig, * Daniel Wagener (M09 firmware support) * Lothar Waßmann (DT support) + * Dario Binacchi (regmap support) */ /* @@ -26,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -115,6 +117,8 @@ struct edt_ft5x06_ts_data { struct gpio_desc *reset_gpio; struct gpio_desc *wake_gpio; + struct regmap *regmap; + #if defined(CONFIG_DEBUG_FS) struct dentry *debug_dir; u8 *raw_buffer; @@ -145,37 +149,10 @@ struct edt_i2c_chip_data { int max_support_points; }; -static int edt_ft5x06_ts_readwrite(struct i2c_client *client, - u16 wr_len, u8 *wr_buf, - u16 rd_len, u8 *rd_buf) -{ - struct i2c_msg wrmsg[2]; - int i = 0; - int ret; - - if (wr_len) { - wrmsg[i].addr = client->addr; - wrmsg[i].flags = 0; - wrmsg[i].len = wr_len; - wrmsg[i].buf = wr_buf; - i++; - } - if (rd_len) { - wrmsg[i].addr = client->addr; - wrmsg[i].flags = I2C_M_RD; - wrmsg[i].len = rd_len; - wrmsg[i].buf = rd_buf; - i++; - } - - ret = i2c_transfer(client->adapter, wrmsg, i); - if (ret < 0) - return ret; - if (ret != i) - return -EIO; - - return 0; -} +static const struct regmap_config edt_ft5x06_i2c_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; static bool edt_ft5x06_ts_check_crc(struct edt_ft5x06_ts_data *tsdata, u8 *buf, int buflen) @@ -197,6 +174,127 @@ static bool edt_ft5x06_ts_check_crc(struct edt_ft5x06_ts_data *tsdata, return true; } +static int edt_M06_i2c_read(void *context, const void *reg_buf, size_t reg_size, + void *val_buf, size_t val_size) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + struct edt_ft5x06_ts_data *tsdata = i2c_get_clientdata(i2c); + struct i2c_msg xfer[2]; + bool reg_read = false; + u8 addr; + u8 wlen; + u8 wbuf[4], rbuf[3]; + int ret; + + addr = *((u8 *)reg_buf); + wbuf[0] = addr; + switch (addr) { + case 0xf5: + wlen = 3; + wbuf[0] = 0xf5; + wbuf[1] = 0xe; + wbuf[2] = *((u8 *)val_buf); + break; + case 0xf9: + wlen = 1; + break; + default: + wlen = 2; + reg_read = true; + wbuf[0] = M06_REG_CMD(tsdata->factory_mode); + wbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); + wbuf[1] |= tsdata->factory_mode ? 0x80 : 0x40; + } + + xfer[0].addr = i2c->addr; + xfer[0].flags = 0; + xfer[0].len = wlen; + xfer[0].buf = wbuf; + + xfer[1].addr = i2c->addr; + xfer[1].flags = I2C_M_RD; + xfer[1].len = reg_read ? 2 : val_size; + xfer[1].buf = reg_read ? rbuf : val_buf; + + ret = i2c_transfer(i2c->adapter, xfer, 2); + if (ret != 2) { + if (ret < 0) + return ret; + + return -EIO; + } + + if (addr == 0xf9) { + u8 *buf = (u8 *)val_buf; + + if (buf[0] != 0xaa || buf[1] != 0xaa || + buf[2] != val_size) { + tsdata->header_errors++; + dev_err_ratelimited(dev, + "Unexpected header: %02x%02x%02x\n", + buf[0], buf[1], buf[2]); + return -EIO; + } + + if (!edt_ft5x06_ts_check_crc(tsdata, val_buf, val_size)) + return -EIO; + } else if (reg_read) { + u8 crc = wbuf[0] ^ wbuf[1] ^ rbuf[0]; + + if (crc != rbuf[1]) { + dev_err(dev, "crc error: 0x%02x expected, got 0x%02x\n", + crc, rbuf[1]); + return -EIO; + } + + *((u8 *)val_buf) = rbuf[0]; + } + + return 0; +} + +static int edt_M06_i2c_write(void *context, const void *data, size_t count) +{ + struct device *dev = context; + struct i2c_client *i2c = to_i2c_client(dev); + struct edt_ft5x06_ts_data *tsdata = i2c_get_clientdata(i2c); + u8 addr, val; + u8 wbuf[4]; + struct i2c_msg xfer; + int ret; + + addr = *((u8 *)data); + val = *((u8 *)data + 1); + + wbuf[0] = M06_REG_CMD(tsdata->factory_mode); + wbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); + wbuf[2] = val; + wbuf[3] = wbuf[0] ^ wbuf[1] ^ wbuf[2]; + + xfer.addr = i2c->addr; + xfer.flags = 0; + xfer.len = 4; + xfer.buf = wbuf; + + ret = i2c_transfer(i2c->adapter, &xfer, 1); + if (ret != 1) { + if (ret < 0) + return ret; + + return -EIO; + } + + return 0; +} + +static const struct regmap_config edt_M06_i2c_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .read = edt_M06_i2c_read, + .write = edt_M06_i2c_write, +}; + static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) { struct edt_ft5x06_ts_data *tsdata = dev_id; @@ -232,30 +330,13 @@ static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) memset(rdbuf, 0, sizeof(rdbuf)); datalen = tplen * tsdata->max_support_points + offset + crclen; - error = edt_ft5x06_ts_readwrite(tsdata->client, - sizeof(cmd), &cmd, - datalen, rdbuf); + error = regmap_bulk_read(tsdata->regmap, cmd, rdbuf, datalen); if (error) { dev_err_ratelimited(dev, "Unable to fetch data, error: %d\n", error); goto out; } - /* M09/M12 does not send header or CRC */ - if (tsdata->version == EDT_M06) { - if (rdbuf[0] != 0xaa || rdbuf[1] != 0xaa || - rdbuf[2] != datalen) { - tsdata->header_errors++; - dev_err_ratelimited(dev, - "Unexpected header: %02x%02x%02x!\n", - rdbuf[0], rdbuf[1], rdbuf[2]); - goto out; - } - - if (!edt_ft5x06_ts_check_crc(tsdata, rdbuf, datalen)) - goto out; - } - for (i = 0; i < tsdata->max_support_points; i++) { u8 *buf = &rdbuf[i * tplen + offset]; @@ -290,79 +371,6 @@ static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) return IRQ_HANDLED; } -static int edt_ft5x06_register_write(struct edt_ft5x06_ts_data *tsdata, - u8 addr, u8 value) -{ - u8 wrbuf[4]; - - switch (tsdata->version) { - case EDT_M06: - wrbuf[0] = M06_REG_CMD(tsdata->factory_mode); - wrbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); - wrbuf[2] = value; - wrbuf[3] = wrbuf[0] ^ wrbuf[1] ^ wrbuf[2]; - return edt_ft5x06_ts_readwrite(tsdata->client, 4, - wrbuf, 0, NULL); - - case EDT_M09: - case EDT_M12: - case EV_FT: - case GENERIC_FT: - wrbuf[0] = addr; - wrbuf[1] = value; - - return edt_ft5x06_ts_readwrite(tsdata->client, 2, - wrbuf, 0, NULL); - - default: - return -EINVAL; - } -} - -static int edt_ft5x06_register_read(struct edt_ft5x06_ts_data *tsdata, - u8 addr) -{ - u8 wrbuf[2], rdbuf[2], crc; - int error; - - switch (tsdata->version) { - case EDT_M06: - wrbuf[0] = M06_REG_CMD(tsdata->factory_mode); - wrbuf[1] = M06_REG_ADDR(tsdata->factory_mode, addr); - wrbuf[1] |= tsdata->factory_mode ? 0x80 : 0x40; - - error = edt_ft5x06_ts_readwrite(tsdata->client, 2, wrbuf, 2, - rdbuf); - if (error) - return error; - - crc = wrbuf[0] ^ wrbuf[1] ^ rdbuf[0]; - if (crc != rdbuf[1]) { - dev_err(&tsdata->client->dev, - "crc error: 0x%02x expected, got 0x%02x\n", - crc, rdbuf[1]); - return -EIO; - } - break; - - case EDT_M09: - case EDT_M12: - case EV_FT: - case GENERIC_FT: - wrbuf[0] = addr; - error = edt_ft5x06_ts_readwrite(tsdata->client, 1, - wrbuf, 1, rdbuf); - if (error) - return error; - break; - - default: - return -EINVAL; - } - - return rdbuf[0]; -} - struct edt_ft5x06_attribute { struct device_attribute dattr; size_t field_offset; @@ -396,7 +404,7 @@ static ssize_t edt_ft5x06_setting_show(struct device *dev, struct edt_ft5x06_attribute *attr = container_of(dattr, struct edt_ft5x06_attribute, dattr); u8 *field = (u8 *)tsdata + attr->field_offset; - int val; + unsigned int val; size_t count = 0; int error = 0; u8 addr; @@ -429,9 +437,8 @@ static ssize_t edt_ft5x06_setting_show(struct device *dev, } if (addr != NO_REGISTER) { - val = edt_ft5x06_register_read(tsdata, addr); - if (val < 0) { - error = val; + error = regmap_read(tsdata->regmap, addr, &val); + if (error) { dev_err(&tsdata->client->dev, "Failed to fetch attribute %s, error %d\n", dattr->attr.name, error); @@ -504,7 +511,7 @@ static ssize_t edt_ft5x06_setting_store(struct device *dev, } if (addr != NO_REGISTER) { - error = edt_ft5x06_register_write(tsdata, addr, val); + error = regmap_write(tsdata->regmap, addr, val); if (error) { dev_err(&tsdata->client->dev, "Failed to update attribute %s, error: %d\n", @@ -605,23 +612,19 @@ static const struct attribute_group edt_ft5x06_attr_group = { static void edt_ft5x06_restore_reg_parameters(struct edt_ft5x06_ts_data *tsdata) { struct edt_reg_addr *reg_addr = &tsdata->reg_addr; + struct regmap *regmap = tsdata->regmap; - edt_ft5x06_register_write(tsdata, reg_addr->reg_threshold, - tsdata->threshold); - edt_ft5x06_register_write(tsdata, reg_addr->reg_gain, - tsdata->gain); + regmap_write(regmap, reg_addr->reg_threshold, tsdata->threshold); + regmap_write(regmap, reg_addr->reg_gain, tsdata->gain); if (reg_addr->reg_offset != NO_REGISTER) - edt_ft5x06_register_write(tsdata, reg_addr->reg_offset, - tsdata->offset); + regmap_write(regmap, reg_addr->reg_offset, tsdata->offset); if (reg_addr->reg_offset_x != NO_REGISTER) - edt_ft5x06_register_write(tsdata, reg_addr->reg_offset_x, - tsdata->offset_x); + regmap_write(regmap, reg_addr->reg_offset_x, tsdata->offset_x); if (reg_addr->reg_offset_y != NO_REGISTER) - edt_ft5x06_register_write(tsdata, reg_addr->reg_offset_y, - tsdata->offset_y); + regmap_write(regmap, reg_addr->reg_offset_y, tsdata->offset_y); if (reg_addr->reg_report_rate != NO_REGISTER) - edt_ft5x06_register_write(tsdata, reg_addr->reg_report_rate, - tsdata->report_rate); + regmap_write(regmap, reg_addr->reg_report_rate, + tsdata->report_rate); } #ifdef CONFIG_DEBUG_FS @@ -629,7 +632,7 @@ static int edt_ft5x06_factory_mode(struct edt_ft5x06_ts_data *tsdata) { struct i2c_client *client = tsdata->client; int retries = EDT_SWITCH_MODE_RETRIES; - int ret; + unsigned int val; int error; if (tsdata->version != EDT_M06) { @@ -651,7 +654,7 @@ static int edt_ft5x06_factory_mode(struct edt_ft5x06_ts_data *tsdata) } /* mode register is 0x3c when in the work mode */ - error = edt_ft5x06_register_write(tsdata, WORK_REGISTER_OPMODE, 0x03); + error = regmap_write(tsdata->regmap, WORK_REGISTER_OPMODE, 0x03); if (error) { dev_err(&client->dev, "failed to switch to factory mode, error %d\n", error); @@ -662,8 +665,9 @@ static int edt_ft5x06_factory_mode(struct edt_ft5x06_ts_data *tsdata) do { mdelay(EDT_SWITCH_MODE_DELAY); /* mode register is 0x01 when in factory mode */ - ret = edt_ft5x06_register_read(tsdata, FACTORY_REGISTER_OPMODE); - if (ret == 0x03) + error = regmap_read(tsdata->regmap, FACTORY_REGISTER_OPMODE, + &val); + if (!error && val == 0x03) break; } while (--retries > 0); @@ -689,11 +693,11 @@ static int edt_ft5x06_work_mode(struct edt_ft5x06_ts_data *tsdata) { struct i2c_client *client = tsdata->client; int retries = EDT_SWITCH_MODE_RETRIES; - int ret; + unsigned int val; int error; /* mode register is 0x01 when in the factory mode */ - error = edt_ft5x06_register_write(tsdata, FACTORY_REGISTER_OPMODE, 0x1); + error = regmap_write(tsdata->regmap, FACTORY_REGISTER_OPMODE, 0x1); if (error) { dev_err(&client->dev, "failed to switch to work mode, error: %d\n", error); @@ -705,8 +709,8 @@ static int edt_ft5x06_work_mode(struct edt_ft5x06_ts_data *tsdata) do { mdelay(EDT_SWITCH_MODE_DELAY); /* mode register is 0x01 when in factory mode */ - ret = edt_ft5x06_register_read(tsdata, WORK_REGISTER_OPMODE); - if (ret == 0x01) + error = regmap_read(tsdata->regmap, WORK_REGISTER_OPMODE, &val); + if (!error && val == 0x01) break; } while (--retries > 0); @@ -765,10 +769,10 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, struct edt_ft5x06_ts_data *tsdata = file->private_data; struct i2c_client *client = tsdata->client; int retries = EDT_RAW_DATA_RETRIES; - int val, i, error; + unsigned int val; + int i, error; size_t read = 0; int colbytes; - char wrbuf[3]; u8 *rdbuf; if (*off < 0 || *off >= tsdata->raw_bufsize) @@ -781,7 +785,7 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, goto out; } - error = edt_ft5x06_register_write(tsdata, 0x08, 0x01); + error = regmap_write(tsdata->regmap, 0x08, 0x01); if (error) { dev_err(&client->dev, "failed to write 0x08 register, error %d\n", error); @@ -790,18 +794,18 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, do { usleep_range(EDT_RAW_DATA_DELAY, EDT_RAW_DATA_DELAY + 100); - val = edt_ft5x06_register_read(tsdata, 0x08); - if (val < 1) + error = regmap_read(tsdata->regmap, 0x08, &val); + if (error) { + dev_err(&client->dev, + "failed to read 0x08 register, error %d\n", + error); + goto out; + } + + if (val == 1) break; } while (--retries > 0); - if (val < 0) { - error = val; - dev_err(&client->dev, - "failed to read 0x08 register, error %d\n", error); - goto out; - } - if (retries == 0) { dev_err(&client->dev, "timed out waiting for register to settle\n"); @@ -812,13 +816,9 @@ static ssize_t edt_ft5x06_debugfs_raw_data_read(struct file *file, rdbuf = tsdata->raw_buffer; colbytes = tsdata->num_y * sizeof(u16); - wrbuf[0] = 0xf5; - wrbuf[1] = 0x0e; for (i = 0; i < tsdata->num_x; i++) { - wrbuf[2] = i; /* column index */ - error = edt_ft5x06_ts_readwrite(tsdata->client, - sizeof(wrbuf), wrbuf, - colbytes, rdbuf); + rdbuf[0] = i; /* column index */ + error = regmap_bulk_read(tsdata->regmap, 0xf5, rdbuf, colbytes); if (error) goto out; @@ -894,8 +894,7 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client, * to have garbage in there */ memset(rdbuf, 0, sizeof(rdbuf)); - error = edt_ft5x06_ts_readwrite(client, 1, "\xBB", - EDT_NAME_LEN - 1, rdbuf); + error = regmap_bulk_read(tsdata->regmap, 0xBB, rdbuf, EDT_NAME_LEN - 1); if (error) return error; @@ -917,6 +916,14 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client, *p++ = '\0'; strscpy(model_name, rdbuf + 1, EDT_NAME_LEN); strscpy(fw_version, p ? p : "", EDT_NAME_LEN); + + regmap_exit(tsdata->regmap); + tsdata->regmap = regmap_init_i2c(client, + &edt_M06_i2c_regmap_config); + if (IS_ERR(tsdata->regmap)) { + dev_err(&client->dev, "regmap allocation failed\n"); + return PTR_ERR(tsdata->regmap); + } } else if (!strncasecmp(rdbuf, "EP0", 3)) { tsdata->version = EDT_M12; @@ -943,15 +950,13 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client, */ tsdata->version = GENERIC_FT; - error = edt_ft5x06_ts_readwrite(client, 1, "\xA6", - 2, rdbuf); + error = regmap_bulk_read(tsdata->regmap, 0xA6, rdbuf, 2); if (error) return error; strscpy(fw_version, rdbuf, 2); - error = edt_ft5x06_ts_readwrite(client, 1, "\xA8", - 1, rdbuf); + error = regmap_bulk_read(tsdata->regmap, 0xA8, rdbuf, 1); if (error) return error; @@ -980,8 +985,7 @@ static int edt_ft5x06_ts_identify(struct i2c_client *client, break; case 0x59: /* Evervision Display with FT5xx6 TS */ tsdata->version = EV_FT; - error = edt_ft5x06_ts_readwrite(client, 1, "\x53", - 1, rdbuf); + error = regmap_bulk_read(tsdata->regmap, 0x53, rdbuf, 1); if (error) return error; strscpy(fw_version, rdbuf, 1); @@ -1003,42 +1007,40 @@ static void edt_ft5x06_ts_get_defaults(struct device *dev, struct edt_ft5x06_ts_data *tsdata) { struct edt_reg_addr *reg_addr = &tsdata->reg_addr; + struct regmap *regmap = tsdata->regmap; u32 val; int error; error = device_property_read_u32(dev, "threshold", &val); if (!error) { - edt_ft5x06_register_write(tsdata, reg_addr->reg_threshold, val); + regmap_write(regmap, reg_addr->reg_threshold, val); tsdata->threshold = val; } error = device_property_read_u32(dev, "gain", &val); if (!error) { - edt_ft5x06_register_write(tsdata, reg_addr->reg_gain, val); + regmap_write(regmap, reg_addr->reg_gain, val); tsdata->gain = val; } error = device_property_read_u32(dev, "offset", &val); if (!error) { if (reg_addr->reg_offset != NO_REGISTER) - edt_ft5x06_register_write(tsdata, - reg_addr->reg_offset, val); + regmap_write(regmap, reg_addr->reg_offset, val); tsdata->offset = val; } error = device_property_read_u32(dev, "offset-x", &val); if (!error) { if (reg_addr->reg_offset_x != NO_REGISTER) - edt_ft5x06_register_write(tsdata, - reg_addr->reg_offset_x, val); + regmap_write(regmap, reg_addr->reg_offset_x, val); tsdata->offset_x = val; } error = device_property_read_u32(dev, "offset-y", &val); if (!error) { if (reg_addr->reg_offset_y != NO_REGISTER) - edt_ft5x06_register_write(tsdata, - reg_addr->reg_offset_y, val); + regmap_write(regmap, reg_addr->reg_offset_y, val); tsdata->offset_y = val; } } @@ -1046,33 +1048,30 @@ static void edt_ft5x06_ts_get_defaults(struct device *dev, static void edt_ft5x06_ts_get_parameters(struct edt_ft5x06_ts_data *tsdata) { struct edt_reg_addr *reg_addr = &tsdata->reg_addr; + struct regmap *regmap = tsdata->regmap; + unsigned int val; - tsdata->threshold = edt_ft5x06_register_read(tsdata, - reg_addr->reg_threshold); - tsdata->gain = edt_ft5x06_register_read(tsdata, reg_addr->reg_gain); + regmap_read(regmap, reg_addr->reg_threshold, &tsdata->threshold); + regmap_read(regmap, reg_addr->reg_gain, &tsdata->gain); if (reg_addr->reg_offset != NO_REGISTER) - tsdata->offset = - edt_ft5x06_register_read(tsdata, reg_addr->reg_offset); + regmap_read(regmap, reg_addr->reg_offset, &tsdata->offset); if (reg_addr->reg_offset_x != NO_REGISTER) - tsdata->offset_x = - edt_ft5x06_register_read(tsdata, - reg_addr->reg_offset_x); + regmap_read(regmap, reg_addr->reg_offset_x, &tsdata->offset_x); if (reg_addr->reg_offset_y != NO_REGISTER) - tsdata->offset_y = - edt_ft5x06_register_read(tsdata, - reg_addr->reg_offset_y); + regmap_read(regmap, reg_addr->reg_offset_y, &tsdata->offset_y); if (reg_addr->reg_report_rate != NO_REGISTER) - tsdata->report_rate = - edt_ft5x06_register_read(tsdata, - reg_addr->reg_report_rate); + regmap_read(regmap, reg_addr->reg_report_rate, + &tsdata->report_rate); tsdata->num_x = EDT_DEFAULT_NUM_X; - if (reg_addr->reg_num_x != NO_REGISTER) - tsdata->num_x = edt_ft5x06_register_read(tsdata, - reg_addr->reg_num_x); + if (reg_addr->reg_num_x != NO_REGISTER) { + if (!regmap_read(regmap, reg_addr->reg_num_x, &val)) + tsdata->num_x = val; + } tsdata->num_y = EDT_DEFAULT_NUM_Y; - if (reg_addr->reg_num_y != NO_REGISTER) - tsdata->num_y = edt_ft5x06_register_read(tsdata, - reg_addr->reg_num_y); + if (reg_addr->reg_num_y != NO_REGISTER) { + if (!regmap_read(regmap, reg_addr->reg_num_y, &val)) + tsdata->num_y = val; + } } static void edt_ft5x06_ts_set_regs(struct edt_ft5x06_ts_data *tsdata) @@ -1142,7 +1141,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) const struct i2c_device_id *id = i2c_client_get_device_id(client); const struct edt_i2c_chip_data *chip_data; struct edt_ft5x06_ts_data *tsdata; - u8 buf[2] = { 0xfc, 0x00 }; + unsigned int val; struct input_dev *input; unsigned long irq_flags; int error; @@ -1156,6 +1155,12 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) return -ENOMEM; } + tsdata->regmap = regmap_init_i2c(client, &edt_ft5x06_i2c_regmap_config); + if (IS_ERR(tsdata->regmap)) { + dev_err(&client->dev, "regmap allocation failed\n"); + return PTR_ERR(tsdata->regmap); + } + chip_data = device_get_match_data(&client->dev); if (!chip_data) chip_data = (const struct edt_i2c_chip_data *)id->driver_data; @@ -1258,6 +1263,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) tsdata->client = client; tsdata->input = input; tsdata->factory_mode = false; + i2c_set_clientdata(client, tsdata); error = edt_ft5x06_ts_identify(client, tsdata); if (error) { @@ -1269,7 +1275,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) * Dummy read access. EP0700MLP1 returns bogus data on the first * register read access and ignores writes. */ - edt_ft5x06_ts_readwrite(tsdata->client, 2, buf, 2, buf); + regmap_read(tsdata->regmap, 0x00, &val); edt_ft5x06_ts_set_regs(tsdata); edt_ft5x06_ts_get_defaults(&client->dev, tsdata); @@ -1291,9 +1297,8 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) if (tsdata->version == EDT_M06) tsdata->report_rate /= 10; - edt_ft5x06_register_write(tsdata, - tsdata->reg_addr.reg_report_rate, - tsdata->report_rate); + regmap_write(tsdata->regmap, tsdata->reg_addr.reg_report_rate, + tsdata->report_rate); } dev_dbg(&client->dev, @@ -1318,8 +1323,6 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) return error; } - i2c_set_clientdata(client, tsdata); - irq_flags = irq_get_trigger_type(client->irq); if (irq_flags == IRQF_TRIGGER_NONE) irq_flags = IRQF_TRIGGER_FALLING; @@ -1357,6 +1360,7 @@ static void edt_ft5x06_ts_remove(struct i2c_client *client) struct edt_ft5x06_ts_data *tsdata = i2c_get_clientdata(client); edt_ft5x06_ts_teardown_debugfs(tsdata); + regmap_exit(tsdata->regmap); } static int edt_ft5x06_ts_suspend(struct device *dev) @@ -1373,8 +1377,8 @@ static int edt_ft5x06_ts_suspend(struct device *dev) return 0; /* Enter hibernate mode. */ - ret = edt_ft5x06_register_write(tsdata, PMOD_REGISTER_OPMODE, - PMOD_REGISTER_HIBERNATE); + ret = regmap_write(tsdata->regmap, PMOD_REGISTER_OPMODE, + PMOD_REGISTER_HIBERNATE); if (ret) dev_warn(dev, "Failed to set hibernate mode\n"); -- GitLab From 079e60a53c25aeb1920e783fa7f7390eabb6afc0 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:36:33 -0700 Subject: [PATCH 1863/5631] Input: edt-ft5x06 - unify the crc check With this patch, the CRC is always verified by the same function, even in the case of accessing registers where the number of bytes is minimal. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-9-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index 8aae4c1e6b73..fdb32e3591be 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -240,13 +240,10 @@ static int edt_M06_i2c_read(void *context, const void *reg_buf, size_t reg_size, if (!edt_ft5x06_ts_check_crc(tsdata, val_buf, val_size)) return -EIO; } else if (reg_read) { - u8 crc = wbuf[0] ^ wbuf[1] ^ rbuf[0]; - - if (crc != rbuf[1]) { - dev_err(dev, "crc error: 0x%02x expected, got 0x%02x\n", - crc, rbuf[1]); + wbuf[2] = rbuf[0]; + wbuf[3] = rbuf[1]; + if (!edt_ft5x06_ts_check_crc(tsdata, wbuf, 4)) return -EIO; - } *((u8 *)val_buf) = rbuf[0]; } -- GitLab From 0df28e7166e803028c380c59dda530ffada0503c Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Sun, 2 Apr 2023 21:36:46 -0700 Subject: [PATCH 1864/5631] Input: edt-ft5x06 - calculate points data length only once It is pointless and expensive to calculate data in the interrupt that depends on the type of touchscreen, which is detected on the driver probe and cannot then be changed. So calculate the size of the data buffer on the driver probe, as well as the data retrieval command, and then use them in the ISR. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/r/20230402200951.1032513-10-dario.binacchi@amarulasolutions.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/edt-ft5x06.c | 56 +++++++++++++------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c index fdb32e3591be..24ab9e9f5b21 100644 --- a/drivers/input/touchscreen/edt-ft5x06.c +++ b/drivers/input/touchscreen/edt-ft5x06.c @@ -135,6 +135,10 @@ struct edt_ft5x06_ts_data { int offset_y; int report_rate; int max_support_points; + int point_len; + u8 tdata_cmd; + int tdata_len; + int tdata_offset; char name[EDT_NAME_LEN]; char fw_version[EDT_NAME_LEN]; @@ -296,38 +300,13 @@ static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) { struct edt_ft5x06_ts_data *tsdata = dev_id; struct device *dev = &tsdata->client->dev; - u8 cmd; u8 rdbuf[63]; int i, type, x, y, id; - int offset, tplen, datalen, crclen; int error; - switch (tsdata->version) { - case EDT_M06: - cmd = 0xf9; /* tell the controller to send touch data */ - offset = 5; /* where the actual touch data starts */ - tplen = 4; /* data comes in so called frames */ - crclen = 1; /* length of the crc data */ - break; - - case EDT_M09: - case EDT_M12: - case EV_FT: - case GENERIC_FT: - cmd = 0x0; - offset = 3; - tplen = 6; - crclen = 0; - break; - - default: - goto out; - } - memset(rdbuf, 0, sizeof(rdbuf)); - datalen = tplen * tsdata->max_support_points + offset + crclen; - - error = regmap_bulk_read(tsdata->regmap, cmd, rdbuf, datalen); + error = regmap_bulk_read(tsdata->regmap, tsdata->tdata_cmd, rdbuf, + tsdata->tdata_len); if (error) { dev_err_ratelimited(dev, "Unable to fetch data, error: %d\n", error); @@ -335,7 +314,7 @@ static irqreturn_t edt_ft5x06_ts_isr(int irq, void *dev_id) } for (i = 0; i < tsdata->max_support_points; i++) { - u8 *buf = &rdbuf[i * tplen + offset]; + u8 *buf = &rdbuf[i * tsdata->point_len + tsdata->tdata_offset]; type = buf[0] >> 6; /* ignore Reserved events */ @@ -1071,6 +1050,26 @@ static void edt_ft5x06_ts_get_parameters(struct edt_ft5x06_ts_data *tsdata) } } +static void edt_ft5x06_ts_set_tdata_parameters(struct edt_ft5x06_ts_data *tsdata) +{ + int crclen; + + if (tsdata->version == EDT_M06) { + tsdata->tdata_cmd = 0xf9; + tsdata->tdata_offset = 5; + tsdata->point_len = 4; + crclen = 1; + } else { + tsdata->tdata_cmd = 0x0; + tsdata->tdata_offset = 3; + tsdata->point_len = 6; + crclen = 0; + } + + tsdata->tdata_len = tsdata->point_len * tsdata->max_support_points + + tsdata->tdata_offset + crclen; +} + static void edt_ft5x06_ts_set_regs(struct edt_ft5x06_ts_data *tsdata) { struct edt_reg_addr *reg_addr = &tsdata->reg_addr; @@ -1274,6 +1273,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client) */ regmap_read(tsdata->regmap, 0x00, &val); + edt_ft5x06_ts_set_tdata_parameters(tsdata); edt_ft5x06_ts_set_regs(tsdata); edt_ft5x06_ts_get_defaults(&client->dev, tsdata); edt_ft5x06_ts_get_parameters(tsdata); -- GitLab From 43d05c6123ca1ace5982ca326c156502e735b7d5 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 3 Apr 2023 14:46:36 +1000 Subject: [PATCH 1865/5631] KVM: PPC: BookE: Fix W=1 warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix various W=1 warnings in booke.c: arch/powerpc/kvm/booke.c:1008:5: error: no previous prototype for ‘kvmppc_handle_exit’ [-Werror=missing-prototypes] 1008 | int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) | ^~~~~~~~~~~~~~~~~~ arch/powerpc/kvm/booke.c:1009: warning: Function parameter or member 'vcpu' not described in 'kvmppc_handle_exit' arch/powerpc/kvm/booke.c:1009: warning: Function parameter or member 'exit_nr' not described in 'kvmppc_handle_exit' Reported-by: kernel test robot Link: https://lore.kernel.org/r/202304020827.3LEZ86WB-lkp@intel.com/ Signed-off-by: Michael Ellerman Link: https://msgid.link/20230403045314.3095410-1-mpe@ellerman.id.au --- arch/powerpc/kvm/booke.c | 2 +- arch/powerpc/kvm/booke.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index ce37d282be6d..a9c04073d27e 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1000,7 +1000,7 @@ static int kvmppc_resume_inst_load(struct kvm_vcpu *vcpu, } } -/** +/* * kvmppc_handle_exit * * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV) diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h index be9da96d9f06..9c5b8e76014f 100644 --- a/arch/powerpc/kvm/booke.h +++ b/arch/powerpc/kvm/booke.h @@ -109,4 +109,7 @@ static inline void kvmppc_clear_dbsr(void) { mtspr(SPRN_DBSR, mfspr(SPRN_DBSR)); } + +int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr); + #endif /* __KVM_BOOKE_H__ */ -- GitLab From 460ba21d83fef766a5d34260e464c9ab8f10aa05 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 30 Mar 2023 20:32:23 +1000 Subject: [PATCH 1866/5631] KVM: PPC: Permit SRR1 flags in more injected interrupt types The prefix architecture in ISA v3.1 introduces a prefixed bit in SRR1 for many types of synchronous interrupts which is set when the interrupt is caused by a prefixed instruction. This requires KVM to be able to set this bit when injecting interrupts into a guest. Plumb through the SRR1 "flags" argument to the core_queue APIs where it's missing for this. For now they are set to 0, which is no change. Signed-off-by: Nicholas Piggin [mpe: Fixup kvmppc_core_queue_alignment() in booke.c] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230330103224.3589928-2-npiggin@gmail.com --- arch/powerpc/include/asm/kvm_ppc.h | 27 ++++++++++++++-------- arch/powerpc/kvm/book3s.c | 32 +++++++++++++------------- arch/powerpc/kvm/book3s_64_mmu_radix.c | 8 +++---- arch/powerpc/kvm/book3s_hv.c | 4 ++-- arch/powerpc/kvm/book3s_hv_nested.c | 4 ++-- arch/powerpc/kvm/book3s_pr.c | 4 ++-- arch/powerpc/kvm/booke.c | 11 +++++---- arch/powerpc/kvm/emulate_loadstore.c | 6 ++--- arch/powerpc/kvm/powerpc.c | 3 ++- 9 files changed, 56 insertions(+), 43 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 6bef23d6d0e3..23ea02b06ffa 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -126,25 +126,34 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu); extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu); extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags); + +extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, + ulong srr1_flags); extern void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags); -extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu); +extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); +extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu, + ulong srr1_flags); extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq); extern void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu); -extern void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, ulong dear_flags, +extern void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, + ulong dear_flags, ulong esr_flags); extern void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, - ulong dear_flags, - ulong esr_flags); + ulong srr1_flags, + ulong dar, + ulong dsisr); extern void kvmppc_core_queue_itlb_miss(struct kvm_vcpu *vcpu); extern void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, - ulong esr_flags); + ulong srr1_flags); + extern void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu); extern int kvmppc_core_check_requests(struct kvm_vcpu *vcpu); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 57f4e7896d67..fa6ac24f3280 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -188,10 +188,10 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec) } EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio); -void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags) +void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong srr1_flags) { /* might as well deliver this straight away */ - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, flags); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, srr1_flags); } EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check); @@ -201,29 +201,29 @@ void kvmppc_core_queue_syscall(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL(kvmppc_core_queue_syscall); -void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags) +void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong srr1_flags) { /* might as well deliver this straight away */ - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, srr1_flags); } EXPORT_SYMBOL_GPL(kvmppc_core_queue_program); -void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu, ulong srr1_flags) { /* might as well deliver this straight away */ - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, 0); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, srr1_flags); } -void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu, ulong srr1_flags) { /* might as well deliver this straight away */ - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, 0); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, srr1_flags); } -void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu, ulong srr1_flags) { /* might as well deliver this straight away */ - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, 0); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, srr1_flags); } void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) @@ -278,18 +278,18 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu) kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL); } -void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar, - ulong flags) +void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong srr1_flags, + ulong dar, ulong dsisr) { kvmppc_set_dar(vcpu, dar); - kvmppc_set_dsisr(vcpu, flags); - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0); + kvmppc_set_dsisr(vcpu, dsisr); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, srr1_flags); } EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage); -void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags) +void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong srr1_flags) { - kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, flags); + kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE, srr1_flags); } EXPORT_SYMBOL_GPL(kvmppc_core_queue_inst_storage); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 9d3743ca16d5..215a6b5ba104 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -954,7 +954,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, if (dsisr & DSISR_BADACCESS) { /* Reflect to the guest as DSI */ pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr); - kvmppc_core_queue_data_storage(vcpu, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); return RESUME_GUEST; } @@ -979,7 +979,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, * Bad address in guest page table tree, or other * unusual error - reflect it to the guest as DSI. */ - kvmppc_core_queue_data_storage(vcpu, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); return RESUME_GUEST; } return kvmppc_hv_emulate_mmio(vcpu, gpa, ea, writing); @@ -988,8 +988,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, if (memslot->flags & KVM_MEM_READONLY) { if (writing) { /* give the guest a DSI */ - kvmppc_core_queue_data_storage(vcpu, ea, DSISR_ISSTORE | - DSISR_PROTFAULT); + kvmppc_core_queue_data_storage(vcpu, 0, ea, + DSISR_ISSTORE | DSISR_PROTFAULT); return RESUME_GUEST; } kvm_ro = true; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6ba68dd6190b..38c6b33d759e 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1739,7 +1739,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } if (!(vcpu->arch.fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT))) { - kvmppc_core_queue_data_storage(vcpu, + kvmppc_core_queue_data_storage(vcpu, 0, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); r = RESUME_GUEST; break; @@ -1757,7 +1757,7 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } else if (err == -1 || err == -2) { r = RESUME_PAGE_FAULT; } else { - kvmppc_core_queue_data_storage(vcpu, + kvmppc_core_queue_data_storage(vcpu, 0, vcpu->arch.fault_dar, err); r = RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 5a64a1341e6f..2c9db6119d89 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -1560,7 +1560,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu, if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) { if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) { /* unusual error -> reflect to the guest as a DSI */ - kvmppc_core_queue_data_storage(vcpu, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); return RESUME_GUEST; } @@ -1570,7 +1570,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu, if (memslot->flags & KVM_MEM_READONLY) { if (writing) { /* Give the guest a DSI */ - kvmppc_core_queue_data_storage(vcpu, ea, + kvmppc_core_queue_data_storage(vcpu, 0, ea, DSISR_ISSTORE | DSISR_PROTFAULT); return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 9fc4dd8f66eb..fdbc88a4c056 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -759,7 +759,7 @@ static int kvmppc_handle_pagefault(struct kvm_vcpu *vcpu, flags = DSISR_NOHPTE; if (data) { flags |= vcpu->arch.fault_dsisr & DSISR_ISSTORE; - kvmppc_core_queue_data_storage(vcpu, eaddr, flags); + kvmppc_core_queue_data_storage(vcpu, 0, eaddr, flags); } else { kvmppc_core_queue_inst_storage(vcpu, flags); } @@ -1236,7 +1236,7 @@ int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) r = kvmppc_handle_pagefault(vcpu, dar, exit_nr); srcu_read_unlock(&vcpu->kvm->srcu, idx); } else { - kvmppc_core_queue_data_storage(vcpu, dar, fault_dsisr); + kvmppc_core_queue_data_storage(vcpu, 0, dar, fault_dsisr); r = RESUME_GUEST; } break; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index a9c04073d27e..8a9a0e112fc5 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -283,9 +283,10 @@ void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu, kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS); } -void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, +void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong srr1_flags, ulong dear_flags, ulong esr_flags) { + WARN_ON_ONCE(srr1_flags); vcpu->arch.queued_dear = dear_flags; vcpu->arch.queued_esr = esr_flags; kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE); @@ -316,14 +317,16 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags) kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM); } -void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu, ulong srr1_flags) { + WARN_ON_ONCE(srr1_flags); kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL); } #ifdef CONFIG_ALTIVEC -void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu) +void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu, ulong srr1_flags) { + WARN_ON_ONCE(srr1_flags); kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL); } #endif @@ -1225,7 +1228,7 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) #endif case BOOKE_INTERRUPT_DATA_STORAGE: - kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear, + kvmppc_core_queue_data_storage(vcpu, 0, vcpu->arch.fault_dear, vcpu->arch.fault_esr); kvmppc_account_exit(vcpu, DSI_EXITS); r = RESUME_GUEST; diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index cfc9114b87d0..e324a174b585 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -28,7 +28,7 @@ static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_FP)) { - kvmppc_core_queue_fpunavail(vcpu); + kvmppc_core_queue_fpunavail(vcpu, 0); return true; } @@ -40,7 +40,7 @@ static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu) static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_VSX)) { - kvmppc_core_queue_vsx_unavail(vcpu); + kvmppc_core_queue_vsx_unavail(vcpu, 0); return true; } @@ -52,7 +52,7 @@ static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_VEC)) { - kvmppc_core_queue_vec_unavail(vcpu); + kvmppc_core_queue_vec_unavail(vcpu, 0); return true; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 4c5405fc5538..f9d9e0d1ab23 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -321,7 +321,8 @@ int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu) if (vcpu->mmio_is_write) dsisr |= DSISR_ISSTORE; - kvmppc_core_queue_data_storage(vcpu, vcpu->arch.vaddr_accessed, dsisr); + kvmppc_core_queue_data_storage(vcpu, 0, + vcpu->arch.vaddr_accessed, dsisr); } else { /* * BookE does not send a SIGBUS on a bad -- GitLab From 6cd5c1db9983600f1848822e86e4906377b4a899 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 30 Mar 2023 20:32:24 +1000 Subject: [PATCH 1867/5631] KVM: PPC: Book3S HV: Set SRR1[PREFIX] bit on injected interrupts Pass the hypervisor (H)SRR1[PREFIX] indication through to synchronous interrupts injected into the guest. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230330103224.3589928-3-npiggin@gmail.com --- arch/powerpc/kvm/book3s_64_mmu_radix.c | 13 +++++++++---- arch/powerpc/kvm/book3s_hv.c | 27 +++++++++++++++++--------- arch/powerpc/kvm/book3s_hv_nested.c | 9 ++++++--- arch/powerpc/kvm/emulate_loadstore.c | 6 +++--- arch/powerpc/kvm/powerpc.c | 3 ++- 5 files changed, 38 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 215a6b5ba104..461307b89c3a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -954,7 +954,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, if (dsisr & DSISR_BADACCESS) { /* Reflect to the guest as DSI */ pr_err("KVM: Got radix HV page fault with DSISR=%lx\n", dsisr); - kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + ea, dsisr); return RESUME_GUEST; } @@ -979,7 +981,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, * Bad address in guest page table tree, or other * unusual error - reflect it to the guest as DSI. */ - kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + ea, dsisr); return RESUME_GUEST; } return kvmppc_hv_emulate_mmio(vcpu, gpa, ea, writing); @@ -988,8 +992,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu, if (memslot->flags & KVM_MEM_READONLY) { if (writing) { /* give the guest a DSI */ - kvmppc_core_queue_data_storage(vcpu, 0, ea, - DSISR_ISSTORE | DSISR_PROTFAULT); + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + ea, DSISR_ISSTORE | DSISR_PROTFAULT); return RESUME_GUEST; } kvm_ro = true; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 38c6b33d759e..b2be366b5309 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1428,7 +1428,8 @@ static int kvmppc_emulate_debug_inst(struct kvm_vcpu *vcpu) vcpu->run->debug.arch.address = kvmppc_get_pc(vcpu); return RESUME_HOST; } else { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); return RESUME_GUEST; } } @@ -1630,7 +1631,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * so that it knows that the machine check occurred. */ if (!vcpu->kvm->arch.fwnmi_enabled) { - ulong flags = vcpu->arch.shregs.msr & 0x083c0000; + ulong flags = (vcpu->arch.shregs.msr & 0x083c0000) | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_machine_check(vcpu, flags); r = RESUME_GUEST; break; @@ -1659,7 +1661,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, * as a result of a hypervisor emulation interrupt * (e40) getting turned into a 700 by BML RTAS. */ - flags = vcpu->arch.shregs.msr & 0x1f0000ull; + flags = (vcpu->arch.shregs.msr & 0x1f0000ull) | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; @@ -1739,7 +1742,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } if (!(vcpu->arch.fault_dsisr & (DSISR_NOHPTE | DSISR_PROTFAULT))) { - kvmppc_core_queue_data_storage(vcpu, 0, + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, vcpu->arch.fault_dar, vcpu->arch.fault_dsisr); r = RESUME_GUEST; break; @@ -1757,7 +1761,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } else if (err == -1 || err == -2) { r = RESUME_PAGE_FAULT; } else { - kvmppc_core_queue_data_storage(vcpu, 0, + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, vcpu->arch.fault_dar, err); r = RESUME_GUEST; } @@ -1785,7 +1790,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, if (!(vcpu->arch.fault_dsisr & SRR1_ISI_NOPT)) { kvmppc_core_queue_inst_storage(vcpu, - vcpu->arch.fault_dsisr); + vcpu->arch.fault_dsisr | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; break; } @@ -1802,7 +1808,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, } else if (err == -1) { r = RESUME_PAGE_FAULT; } else { - kvmppc_core_queue_inst_storage(vcpu, err); + kvmppc_core_queue_inst_storage(vcpu, + err | (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; } break; @@ -1823,7 +1830,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) { r = kvmppc_emulate_debug_inst(vcpu); } else { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; } break; @@ -1864,7 +1872,8 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, r = kvmppc_tm_unavailable(vcpu); } if (r == EMULATE_FAIL) { - kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL | + (kvmppc_get_msr(vcpu) & SRR1_PREFIXED)); r = RESUME_GUEST; } break; diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 2c9db6119d89..377d0b4a05ee 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -1560,7 +1560,9 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu, if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) { if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS)) { /* unusual error -> reflect to the guest as a DSI */ - kvmppc_core_queue_data_storage(vcpu, 0, ea, dsisr); + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + ea, dsisr); return RESUME_GUEST; } @@ -1570,8 +1572,9 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu, if (memslot->flags & KVM_MEM_READONLY) { if (writing) { /* Give the guest a DSI */ - kvmppc_core_queue_data_storage(vcpu, 0, ea, - DSISR_ISSTORE | DSISR_PROTFAULT); + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, + ea, DSISR_ISSTORE | DSISR_PROTFAULT); return RESUME_GUEST; } kvm_ro = true; diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index e324a174b585..1abe25ac3855 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -28,7 +28,7 @@ static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_FP)) { - kvmppc_core_queue_fpunavail(vcpu, 0); + kvmppc_core_queue_fpunavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED); return true; } @@ -40,7 +40,7 @@ static bool kvmppc_check_fp_disabled(struct kvm_vcpu *vcpu) static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_VSX)) { - kvmppc_core_queue_vsx_unavail(vcpu, 0); + kvmppc_core_queue_vsx_unavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED); return true; } @@ -52,7 +52,7 @@ static bool kvmppc_check_vsx_disabled(struct kvm_vcpu *vcpu) static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu) { if (!(kvmppc_get_msr(vcpu) & MSR_VEC)) { - kvmppc_core_queue_vec_unavail(vcpu, 0); + kvmppc_core_queue_vec_unavail(vcpu, kvmppc_get_msr(vcpu) & SRR1_PREFIXED); return true; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f9d9e0d1ab23..ec531ddc3ee5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -321,7 +321,8 @@ int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu) if (vcpu->mmio_is_write) dsisr |= DSISR_ISSTORE; - kvmppc_core_queue_data_storage(vcpu, 0, + kvmppc_core_queue_data_storage(vcpu, + kvmppc_get_msr(vcpu) & SRR1_PREFIXED, vcpu->arch.vaddr_accessed, dsisr); } else { /* -- GitLab From 6a0c637bfee69a74c104468544d9f2a6579626d0 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Fri, 24 Mar 2023 10:13:04 -0600 Subject: [PATCH 1868/5631] bus: mhi: host: Range check CHDBOFF and ERDBOFF If the value read from the CHDBOFF and ERDBOFF registers is outside the range of the MHI register space then an invalid address might be computed which later causes a kernel panic. Range check the read value to prevent a crash due to bad data from the device. Fixes: 6cd330ae76ff ("bus: mhi: core: Add support for ringing channel/event ring doorbells") Cc: stable@vger.kernel.org Signed-off-by: Jeffrey Hugo Reviewed-by: Pranjal Ramajor Asha Kanojiya Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1679674384-27209-1-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/init.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index 3d779ee6396d..b46a0821adf9 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -516,6 +516,12 @@ int mhi_init_mmio(struct mhi_controller *mhi_cntrl) return -EIO; } + if (val >= mhi_cntrl->reg_len - (8 * MHI_DEV_WAKE_DB)) { + dev_err(dev, "CHDB offset: 0x%x is out of range: 0x%zx\n", + val, mhi_cntrl->reg_len - (8 * MHI_DEV_WAKE_DB)); + return -ERANGE; + } + /* Setup wake db */ mhi_cntrl->wake_db = base + val + (8 * MHI_DEV_WAKE_DB); mhi_cntrl->wake_set = false; @@ -532,6 +538,12 @@ int mhi_init_mmio(struct mhi_controller *mhi_cntrl) return -EIO; } + if (val >= mhi_cntrl->reg_len - (8 * mhi_cntrl->total_ev_rings)) { + dev_err(dev, "ERDB offset: 0x%x is out of range: 0x%zx\n", + val, mhi_cntrl->reg_len - (8 * mhi_cntrl->total_ev_rings)); + return -ERANGE; + } + /* Setup event db address for each ev_ring */ mhi_event = mhi_cntrl->mhi_event; for (i = 0; i < mhi_cntrl->total_ev_rings; i++, val += 8, mhi_event++) { -- GitLab From 446271e5d7bcb5f1c70bc35b11abbd92e6bb4378 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Fri, 24 Mar 2023 10:21:00 -0600 Subject: [PATCH 1869/5631] bus: mhi: host: Use ERANGE for BHIOFF/BHIEOFF range check If the BHIOFF or BHIEOFF range checks fail, they return EINVAL. ERANGE is a better error code since it implies an out of range condition. Suggested-by: Manivannan Sadhasivam Signed-off-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1679674860-28229-1-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c index b46a0821adf9..f72fcb66f408 100644 --- a/drivers/bus/mhi/host/init.c +++ b/drivers/bus/mhi/host/init.c @@ -1112,7 +1112,7 @@ int mhi_prepare_for_power_up(struct mhi_controller *mhi_cntrl) if (bhi_off >= mhi_cntrl->reg_len) { dev_err(dev, "BHI offset: 0x%x is out of range: 0x%zx\n", bhi_off, mhi_cntrl->reg_len); - ret = -EINVAL; + ret = -ERANGE; goto error_reg_offset; } mhi_cntrl->bhi = mhi_cntrl->regs + bhi_off; @@ -1129,7 +1129,7 @@ int mhi_prepare_for_power_up(struct mhi_controller *mhi_cntrl) dev_err(dev, "BHIe offset: 0x%x is out of range: 0x%zx\n", bhie_off, mhi_cntrl->reg_len); - ret = -EINVAL; + ret = -ERANGE; goto error_reg_offset; } mhi_cntrl->bhie = mhi_cntrl->regs + bhie_off; -- GitLab From c2dbd34f6a9558b7e99849d4f73eb9b95a45a83c Mon Sep 17 00:00:00 2001 From: Slark Xiao Date: Wed, 29 Mar 2023 15:22:39 +0800 Subject: [PATCH 1870/5631] bus: mhi: pci_generic: Add Foxconn T99W510 The Foxconn T99W510 device is designed based on Qualcomm SDX24. Add 3 variants for different potential customer. Signed-off-by: Slark Xiao Link: https://lore.kernel.org/r/20230329072239.93632-1-slark_xiao@163.com Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/pci_generic.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 91d02f84ba21..db0a0b062d8e 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -363,6 +363,15 @@ static const struct mhi_controller_config modem_foxconn_sdx55_config = { .event_cfg = mhi_foxconn_sdx55_events, }; +static const struct mhi_pci_dev_info mhi_foxconn_sdx24_info = { + .name = "foxconn-sdx24", + .config = &modem_foxconn_sdx55_config, + .bar_num = MHI_PCI_DEFAULT_BAR_NUM, + .dma_data_width = 32, + .mru_default = 32768, + .sideband_wake = false, +}; + static const struct mhi_pci_dev_info mhi_foxconn_sdx55_info = { .name = "foxconn-sdx55", .fw = "qcom/sdx55m/sbl1.mbn", @@ -587,6 +596,15 @@ static const struct pci_device_id mhi_pci_id_table[] = { /* T99W373 (sdx62) */ { PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe0d9), .driver_data = (kernel_ulong_t) &mhi_foxconn_sdx65_info }, + /* T99W510 (sdx24), variant 1 */ + { PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe0f0), + .driver_data = (kernel_ulong_t) &mhi_foxconn_sdx24_info }, + /* T99W510 (sdx24), variant 2 */ + { PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe0f1), + .driver_data = (kernel_ulong_t) &mhi_foxconn_sdx24_info }, + /* T99W510 (sdx24), variant 3 */ + { PCI_DEVICE(PCI_VENDOR_ID_FOXCONN, 0xe0f2), + .driver_data = (kernel_ulong_t) &mhi_foxconn_sdx24_info }, /* MV31-W (Cinterion) */ { PCI_DEVICE(PCI_VENDOR_ID_THALES, 0x00b3), .driver_data = (kernel_ulong_t) &mhi_mv31_info }, -- GitLab From 1f15af76784cc902a1fe85e864c7ddf3d74b4130 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Mar 2023 13:23:42 +0300 Subject: [PATCH 1871/5631] thunderbolt: Introduce usb4_port_sb_opcode_err_to_errno() helper The usb4_port_sb_opcode_err_to_errno() converts from USB4 error codes to the Linux errno space. In particular, this makes the intention of the repeating usb4_port_retimer_read() call in the usb4_port_retimer_nvm_authenticate_status() clearer. Signed-off-by: Andy Shevchenko Signed-off-by: Mika Westerberg --- drivers/thunderbolt/usb4.c | 41 +++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 21 deletions(-) diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 8dcdde61a15f..bcc3ec2eb221 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1303,6 +1303,20 @@ static int usb4_port_sb_write(struct tb_port *port, enum usb4_sb_target target, return 0; } +static int usb4_port_sb_opcode_err_to_errno(u32 val) +{ + switch (val) { + case 0: + return 0; + case USB4_SB_OPCODE_ERR: + return -EAGAIN; + case USB4_SB_OPCODE_ONS: + return -EOPNOTSUPP; + default: + return -EIO; + } +} + static int usb4_port_sb_op(struct tb_port *port, enum usb4_sb_target target, u8 index, enum usb4_sb_opcode opcode, int timeout_msec) { @@ -1325,21 +1339,8 @@ static int usb4_port_sb_op(struct tb_port *port, enum usb4_sb_target target, if (ret) return ret; - switch (val) { - case 0: - return 0; - - case USB4_SB_OPCODE_ERR: - return -EAGAIN; - - case USB4_SB_OPCODE_ONS: - return -EOPNOTSUPP; - - default: - if (val != opcode) - return -EIO; - break; - } + if (val != opcode) + return usb4_port_sb_opcode_err_to_errno(val); } while (ktime_before(ktime_get(), timeout)); return -ETIMEDOUT; @@ -1800,12 +1801,13 @@ int usb4_port_retimer_nvm_authenticate_status(struct tb_port *port, u8 index, if (ret) return ret; - switch (val) { + ret = usb4_port_sb_opcode_err_to_errno(val); + switch (ret) { case 0: *status = 0; return 0; - case USB4_SB_OPCODE_ERR: + case -EAGAIN: ret = usb4_port_retimer_read(port, index, USB4_SB_METADATA, &metadata, sizeof(metadata)); if (ret) @@ -1814,11 +1816,8 @@ int usb4_port_retimer_nvm_authenticate_status(struct tb_port *port, u8 index, *status = metadata & USB4_SB_METADATA_NVM_AUTH_WRITE_MASK; return 0; - case USB4_SB_OPCODE_ONS: - return -EOPNOTSUPP; - default: - return -EIO; + return ret; } } -- GitLab From acf17878da680a0c11c0bcb8a54b4f676ff39c80 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 8 Mar 2023 17:34:48 +1100 Subject: [PATCH 1872/5631] KVM: PPC: Make kvmppc_get_last_inst() produce a ppc_inst_t This changes kvmppc_get_last_inst() so that the instruction it fetches is returned in a ppc_inst_t variable rather than a u32. This will allow us to return a 64-bit prefixed instruction on those 64-bit machines that implement Power ISA v3.1 or later, such as POWER10. On 32-bit platforms, ppc_inst_t is 32 bits wide, and is turned back into a u32 by ppc_inst_val, which is an identity operation on those platforms. Reviewed-by: Nicholas Piggin Tested-by: Nicholas Piggin Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://msgid.link/ZAgsiPlL9O7KnlZZ@cleo --- arch/powerpc/include/asm/kvm_ppc.h | 5 +++-- arch/powerpc/kvm/book3s_64_mmu_hv.c | 12 ++++++++---- arch/powerpc/kvm/book3s_hv.c | 13 ++++++++----- arch/powerpc/kvm/book3s_paired_singles.c | 4 +++- arch/powerpc/kvm/book3s_pr.c | 20 ++++++++++---------- arch/powerpc/kvm/booke.c | 10 +++++++--- arch/powerpc/kvm/emulate.c | 4 +++- arch/powerpc/kvm/emulate_loadstore.c | 6 +++--- arch/powerpc/kvm/powerpc.c | 4 ++-- 9 files changed, 47 insertions(+), 31 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 23ea02b06ffa..d703d1b3ba7e 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -28,6 +28,7 @@ #include #include #endif +#include /* * KVMPPC_INST_SW_BREAKPOINT is debug Instruction @@ -324,7 +325,7 @@ extern struct kvmppc_ops *kvmppc_hv_ops; extern struct kvmppc_ops *kvmppc_pr_ops; static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *inst) + enum instruction_fetch_type type, ppc_inst_t *inst) { int ret = EMULATE_DONE; u32 fetched_inst; @@ -342,7 +343,7 @@ static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu, else fetched_inst = vcpu->arch.last_inst; - *inst = fetched_inst; + *inst = ppc_inst(fetched_inst); return ret; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7006bcbc2e37..0be313e71615 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -415,20 +415,24 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, * embodied here.) If the instruction isn't a load or store, then * this doesn't return anything useful. */ -static int instruction_is_store(unsigned int instr) +static int instruction_is_store(ppc_inst_t instr) { unsigned int mask; + unsigned int suffix; mask = 0x10000000; - if ((instr & 0xfc000000) == 0x7c000000) + suffix = ppc_inst_val(instr); + if (ppc_inst_prefixed(instr)) + suffix = ppc_inst_suffix(instr); + else if ((suffix & 0xfc000000) == 0x7c000000) mask = 0x100; /* major opcode 31 */ - return (instr & mask) != 0; + return (suffix & mask) != 0; } int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu, unsigned long gpa, gva_t ea, int is_store) { - u32 last_inst; + ppc_inst_t last_inst; /* * Fast path - check if the guest physical address corresponds to a diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b2be366b5309..6a573bcad8b8 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1412,7 +1412,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd) static int kvmppc_emulate_debug_inst(struct kvm_vcpu *vcpu) { - u32 last_inst; + ppc_inst_t last_inst; if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) != EMULATE_DONE) { @@ -1423,7 +1423,7 @@ static int kvmppc_emulate_debug_inst(struct kvm_vcpu *vcpu) return RESUME_GUEST; } - if (last_inst == KVMPPC_INST_SW_BREAKPOINT) { + if (ppc_inst_val(last_inst) == KVMPPC_INST_SW_BREAKPOINT) { vcpu->run->exit_reason = KVM_EXIT_DEBUG; vcpu->run->debug.arch.address = kvmppc_get_pc(vcpu); return RESUME_HOST; @@ -1477,9 +1477,11 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu) unsigned long arg; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tvcpu; + ppc_inst_t pinst; - if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE) + if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst) != EMULATE_DONE) return RESUME_GUEST; + inst = ppc_inst_val(pinst); if (get_op(inst) != 31) return EMULATE_FAIL; rb = get_rb(inst); @@ -2003,14 +2005,15 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) */ if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) || (vcpu->arch.nested_hfscr & (1UL << cause))) { + ppc_inst_t pinst; vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST; /* * If the fetch failed, return to guest and * try executing it again. */ - r = kvmppc_get_last_inst(vcpu, INST_GENERIC, - &vcpu->arch.emul_inst); + r = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + vcpu->arch.emul_inst = ppc_inst_val(pinst); if (r != EMULATE_DONE) r = RESUME_GUEST; else diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c index a11436720a8c..bc39c76c9d9f 100644 --- a/arch/powerpc/kvm/book3s_paired_singles.c +++ b/arch/powerpc/kvm/book3s_paired_singles.c @@ -621,6 +621,7 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc, int kvmppc_emulate_paired_single(struct kvm_vcpu *vcpu) { u32 inst; + ppc_inst_t pinst; enum emulation_result emulated = EMULATE_DONE; int ax_rd, ax_ra, ax_rb, ax_rc; short full_d; @@ -632,7 +633,8 @@ int kvmppc_emulate_paired_single(struct kvm_vcpu *vcpu) int i; #endif - emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst); + emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + inst = ppc_inst_val(pinst); if (emulated != EMULATE_DONE) return emulated; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index fdbc88a4c056..556d90e018b3 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1079,7 +1079,7 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr) { enum emulation_result er; ulong flags; - u32 last_inst; + ppc_inst_t last_inst; int emul, r; /* @@ -1100,9 +1100,9 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr) if (kvmppc_get_msr(vcpu) & MSR_PR) { #ifdef EXIT_DEBUG pr_info("Userspace triggered 0x700 exception at\n 0x%lx (0x%x)\n", - kvmppc_get_pc(vcpu), last_inst); + kvmppc_get_pc(vcpu), ppc_inst_val(last_inst)); #endif - if ((last_inst & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { + if ((ppc_inst_val(last_inst) & 0xff0007ff) != (INS_DCBZ & 0xfffffff7)) { kvmppc_core_queue_program(vcpu, flags); return RESUME_GUEST; } @@ -1119,7 +1119,7 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr) break; case EMULATE_FAIL: pr_crit("%s: emulation at %lx failed (%08x)\n", - __func__, kvmppc_get_pc(vcpu), last_inst); + __func__, kvmppc_get_pc(vcpu), ppc_inst_val(last_inst)); kvmppc_core_queue_program(vcpu, flags); r = RESUME_GUEST; break; @@ -1281,7 +1281,7 @@ int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) break; case BOOK3S_INTERRUPT_SYSCALL: { - u32 last_sc; + ppc_inst_t last_sc; int emul; /* Get last sc for papr */ @@ -1296,7 +1296,7 @@ int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) } if (vcpu->arch.papr_enabled && - (last_sc == 0x44000022) && + (ppc_inst_val(last_sc) == 0x44000022) && !(kvmppc_get_msr(vcpu) & MSR_PR)) { /* SC 1 papr hypercalls */ ulong cmd = kvmppc_get_gpr(vcpu, 3); @@ -1348,7 +1348,7 @@ int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) { int ext_msr = 0; int emul; - u32 last_inst; + ppc_inst_t last_inst; if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE) { /* Do paired single instruction emulation */ @@ -1382,15 +1382,15 @@ int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) } case BOOK3S_INTERRUPT_ALIGNMENT: { - u32 last_inst; + ppc_inst_t last_inst; int emul = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); if (emul == EMULATE_DONE) { u32 dsisr; u64 dar; - dsisr = kvmppc_alignment_dsisr(vcpu, last_inst); - dar = kvmppc_alignment_dar(vcpu, last_inst); + dsisr = kvmppc_alignment_dsisr(vcpu, ppc_inst_val(last_inst)); + dar = kvmppc_alignment_dar(vcpu, ppc_inst_val(last_inst)); kvmppc_set_dsisr(vcpu, dsisr); kvmppc_set_dar(vcpu, dar); diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8a9a0e112fc5..7e1d9d7d659d 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1015,6 +1015,7 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) int s; int idx; u32 last_inst = KVM_INST_FETCH_FAILED; + ppc_inst_t pinst; enum emulation_result emulated = EMULATE_DONE; /* Fix irq state (pairs with kvmppc_fix_ee_before_entry()) */ @@ -1034,12 +1035,15 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) case BOOKE_INTERRUPT_DATA_STORAGE: case BOOKE_INTERRUPT_DTLB_MISS: case BOOKE_INTERRUPT_HV_PRIV: - emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); + emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + last_inst = ppc_inst_val(pinst); break; case BOOKE_INTERRUPT_PROGRAM: /* SW breakpoints arrive as illegal instructions on HV */ - if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) { + emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + last_inst = ppc_inst_val(pinst); + } break; default: break; diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index ee1147c98cd8..2a51d5baabf4 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -194,6 +194,7 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt) int kvmppc_emulate_instruction(struct kvm_vcpu *vcpu) { u32 inst; + ppc_inst_t pinst; int rs, rt, sprn; enum emulation_result emulated; int advance = 1; @@ -201,7 +202,8 @@ int kvmppc_emulate_instruction(struct kvm_vcpu *vcpu) /* this default type might be overwritten by subcategories */ kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS); - emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst); + emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &pinst); + inst = ppc_inst_val(pinst); if (emulated != EMULATE_DONE) return emulated; diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 1abe25ac3855..64b93eb1e457 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -71,7 +71,7 @@ static bool kvmppc_check_altivec_disabled(struct kvm_vcpu *vcpu) */ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) { - u32 inst; + ppc_inst_t inst; enum emulation_result emulated = EMULATE_FAIL; struct instruction_op op; @@ -93,7 +93,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) emulated = EMULATE_FAIL; vcpu->arch.regs.msr = vcpu->arch.shared->msr; - if (analyse_instr(&op, &vcpu->arch.regs, ppc_inst(inst)) == 0) { + if (analyse_instr(&op, &vcpu->arch.regs, inst) == 0) { int type = op.type & INSTR_TYPE_MASK; int size = GETSIZE(op.type); @@ -356,7 +356,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) } } - trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated); + trace_kvm_ppc_instr(ppc_inst_val(inst), kvmppc_get_pc(vcpu), emulated); /* Advance past emulated instruction. */ if (emulated != EMULATE_FAIL) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index ec531ddc3ee5..339267c33636 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -304,11 +304,11 @@ int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu) break; case EMULATE_FAIL: { - u32 last_inst; + ppc_inst_t last_inst; kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); kvm_debug_ratelimited("Guest access to device memory using unsupported instruction (opcode: %#08x)\n", - last_inst); + ppc_inst_val(last_inst)); /* * Injecting a Data Storage here is a bit more -- GitLab From 953e37397fb61be61f095d36972188bac5235021 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 8 Mar 2023 17:35:23 +1100 Subject: [PATCH 1873/5631] KVM: PPC: Fetch prefixed instructions from the guest In order to handle emulation of prefixed instructions in the guest, this first makes vcpu->arch.last_inst be an unsigned long, i.e. 64 bits on 64-bit platforms. For prefixed instructions, the upper 32 bits are used for the prefix and the lower 32 bits for the suffix, and both halves are byte-swapped if the guest endianness differs from the host. Next, vcpu->arch.emul_inst is now 64 bits wide, to match the HEIR register on POWER10. Like HEIR, for a prefixed instruction it is defined to have the prefix is in the top 32 bits and the suffix in the bottom 32 bits, with both halves in the correct byte order. kvmppc_get_last_inst is extended on 64-bit machines to put the prefix and suffix in the right places in the ppc_inst_t being returned. kvmppc_load_last_inst now returns the instruction in an unsigned long in the same format as vcpu->arch.last_inst. It makes the decision about whether to fetch a suffix based on the SRR1_PREFIXED bit in the MSR image stored in the vcpu struct, which generally comes from SRR1 or HSRR1 on an interrupt. This bit is defined in Power ISA v3.1B to be set if the interrupt occurred due to a prefixed instruction and cleared otherwise for all interrupts except for instruction storage interrupt, which does not come to the hypervisor. It is set to zero for asynchronous interrupts such as external interrupts. In previous ISA versions it was always set to 0 for all interrupts except instruction storage interrupt. The code in book3s_hv_rmhandlers.S that loads the faulting instruction on a HDSI is only used on POWER8 and therefore doesn't ever need to load a suffix. [npiggin@gmail.com - check that the is-prefixed bit in SRR1 matches the type of instruction that was fetched.] Reviewed-by: Nicholas Piggin Tested-by: Nicholas Piggin Signed-off-by: Paul Mackerras Signed-off-by: Michael Ellerman Link: https://msgid.link/ZAgsq9h1CCzouQuV@cleo --- arch/powerpc/include/asm/kvm_host.h | 4 ++-- arch/powerpc/include/asm/kvm_ppc.h | 32 ++++++++++++++++++------- arch/powerpc/kvm/book3s.c | 32 +++++++++++++++++++++---- arch/powerpc/kvm/book3s_64_mmu_hv.c | 14 +++++++++-- arch/powerpc/kvm/book3s_hv.c | 2 +- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 6 ++--- arch/powerpc/kvm/booke.c | 2 +- arch/powerpc/kvm/bookehv_interrupts.S | 2 +- arch/powerpc/kvm/e500_mmu_host.c | 4 ++-- arch/powerpc/kvm/emulate.c | 4 ++++ arch/powerpc/kvm/emulate_loadstore.c | 2 +- 11 files changed, 78 insertions(+), 26 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 959f566a455c..14ee0dece853 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -758,7 +758,7 @@ struct kvm_vcpu_arch { u8 prodded; u8 doorbell_request; u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ - u32 last_inst; + unsigned long last_inst; struct rcuwait wait; struct rcuwait *waitp; @@ -818,7 +818,7 @@ struct kvm_vcpu_arch { u64 busy_stolen; u64 busy_preempt; - u32 emul_inst; + u64 emul_inst; u32 online; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index d703d1b3ba7e..bc57d058ad5b 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -85,7 +85,8 @@ extern int kvmppc_handle_vsx_store(struct kvm_vcpu *vcpu, int is_default_endian); extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *inst); + enum instruction_fetch_type type, + unsigned long *inst); extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data); @@ -336,15 +337,30 @@ static inline int kvmppc_get_last_inst(struct kvm_vcpu *vcpu, ret = kvmppc_load_last_inst(vcpu, type, &vcpu->arch.last_inst); /* Write fetch_failed unswapped if the fetch failed */ - if (ret == EMULATE_DONE) - fetched_inst = kvmppc_need_byteswap(vcpu) ? - swab32(vcpu->arch.last_inst) : - vcpu->arch.last_inst; - else - fetched_inst = vcpu->arch.last_inst; + if (ret != EMULATE_DONE) { + *inst = ppc_inst(KVM_INST_FETCH_FAILED); + return ret; + } + +#ifdef CONFIG_PPC64 + /* Is this a prefixed instruction? */ + if ((vcpu->arch.last_inst >> 32) != 0) { + u32 prefix = vcpu->arch.last_inst >> 32; + u32 suffix = vcpu->arch.last_inst; + if (kvmppc_need_byteswap(vcpu)) { + prefix = swab32(prefix); + suffix = swab32(suffix); + } + *inst = ppc_inst_prefix(prefix, suffix); + return EMULATE_DONE; + } +#endif + fetched_inst = kvmppc_need_byteswap(vcpu) ? + swab32(vcpu->arch.last_inst) : + vcpu->arch.last_inst; *inst = ppc_inst(fetched_inst); - return ret; + return EMULATE_DONE; } static inline bool is_kvmppc_hv_enabled(struct kvm *kvm) diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index fa6ac24f3280..686d8d9eda3e 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -481,20 +481,42 @@ int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, enum xlate_instdata xlid, return r; } +/* + * Returns prefixed instructions with the prefix in the high 32 bits + * of *inst and suffix in the low 32 bits. This is the same convention + * as used in HEIR, vcpu->arch.last_inst and vcpu->arch.emul_inst. + * Like vcpu->arch.last_inst but unlike vcpu->arch.emul_inst, each + * half of the value needs byte-swapping if the guest endianness is + * different from the host endianness. + */ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *inst) + enum instruction_fetch_type type, unsigned long *inst) { ulong pc = kvmppc_get_pc(vcpu); int r; + u32 iw; if (type == INST_SC) pc -= 4; - r = kvmppc_ld(vcpu, &pc, sizeof(u32), inst, false); - if (r == EMULATE_DONE) - return r; - else + r = kvmppc_ld(vcpu, &pc, sizeof(u32), &iw, false); + if (r != EMULATE_DONE) return EMULATE_AGAIN; + /* + * If [H]SRR1 indicates that the instruction that caused the + * current interrupt is a prefixed instruction, get the suffix. + */ + if (kvmppc_get_msr(vcpu) & SRR1_PREFIXED) { + u32 suffix; + pc += 4; + r = kvmppc_ld(vcpu, &pc, sizeof(u32), &suffix, false); + if (r != EMULATE_DONE) + return EMULATE_AGAIN; + *inst = ((u64)iw << 32) | suffix; + } else { + *inst = iw; + } + return r; } EXPORT_SYMBOL_GPL(kvmppc_load_last_inst); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 0be313e71615..af1f060533f2 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -433,6 +433,7 @@ int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu, unsigned long gpa, gva_t ea, int is_store) { ppc_inst_t last_inst; + bool is_prefixed = !!(kvmppc_get_msr(vcpu) & SRR1_PREFIXED); /* * Fast path - check if the guest physical address corresponds to a @@ -447,7 +448,7 @@ int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); if (!ret) { - kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + (is_prefixed ? 8 : 4)); return RESUME_GUEST; } } @@ -462,7 +463,16 @@ int kvmppc_hv_emulate_mmio(struct kvm_vcpu *vcpu, /* * WARNING: We do not know for sure whether the instruction we just * read from memory is the same that caused the fault in the first - * place. If the instruction we read is neither an load or a store, + * place. + * + * If the fault is prefixed but the instruction is not or vice + * versa, try again so that we don't advance pc the wrong amount. + */ + if (ppc_inst_prefixed(last_inst) != is_prefixed) + return RESUME_GUEST; + + /* + * If the instruction we read is neither an load or a store, * then it can't access memory, so we don't need to worry about * enforcing access permissions. So, assuming it is a load or * store, we just check that its direction (load or store) is diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 6a573bcad8b8..283b9bcb014c 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -474,7 +474,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu) for (r = 0; r < vcpu->arch.slb_max; ++r) pr_err(" ESID = %.16llx VSID = %.16llx\n", vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv); - pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n", + pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.16lx\n", vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1, vcpu->arch.last_inst); } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 0a9781192b86..800892dab48e 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1071,11 +1071,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Save HEIR (HV emulation assist reg) in emul_inst if this is an HEI (HV emulation interrupt, e40) */ li r3,KVM_INST_FETCH_FAILED - stw r3,VCPU_LAST_INST(r9) + std r3,VCPU_LAST_INST(r9) cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST bne 11f mfspr r3,SPRN_HEIR -11: stw r3,VCPU_HEIR(r9) +11: std r3,VCPU_HEIR(r9) /* these are volatile across C function calls */ mfctr r3 @@ -1676,7 +1676,7 @@ fast_interrupt_c_return: mtmsrd r3 /* Store the result */ - stw r8, VCPU_LAST_INST(r9) + std r8, VCPU_LAST_INST(r9) /* Unset guest mode. */ li r0, KVM_GUEST_MODE_HOST_HV diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 7e1d9d7d659d..6a5be025a8af 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -844,7 +844,7 @@ static int emulation_exit(struct kvm_vcpu *vcpu) return RESUME_GUEST; case EMULATE_FAIL: - printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n", + printk(KERN_CRIT "%s: emulation at %lx failed (%08lx)\n", __func__, vcpu->arch.regs.nip, vcpu->arch.last_inst); /* For debugging, encode the failing instruction and * report it to userspace. */ diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index b5fe6fb53c66..8b4a402217ba 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -139,7 +139,7 @@ END_BTB_FLUSH_SECTION * kvmppc_get_last_inst(). */ li r9, KVM_INST_FETCH_FAILED - stw r9, VCPU_LAST_INST(r4) + PPC_STL r9, VCPU_LAST_INST(r4) .endif .if \flags & NEED_ESR diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 05668e964140..ccb8f16ffe41 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -623,7 +623,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr, #ifdef CONFIG_KVM_BOOKE_HV int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *instr) + enum instruction_fetch_type type, unsigned long *instr) { gva_t geaddr; hpa_t addr; @@ -713,7 +713,7 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, } #else int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, - enum instruction_fetch_type type, u32 *instr) + enum instruction_fetch_type type, unsigned long *instr) { return EMULATE_AGAIN; } diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index 2a51d5baabf4..355d5206e8aa 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -301,6 +301,10 @@ int kvmppc_emulate_instruction(struct kvm_vcpu *vcpu) trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated); /* Advance past emulated instruction. */ + /* + * If this ever handles prefixed instructions, the 4 + * will need to become ppc_inst_len(pinst) instead. + */ if (advance) kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 64b93eb1e457..059c08ae0340 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -360,7 +360,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) /* Advance past emulated instruction. */ if (emulated != EMULATE_FAIL) - kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); + kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + ppc_inst_len(inst)); return emulated; } -- GitLab From a3800ef9c48c4497dafe5ede1b65d91d9ef9cf1e Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 8 Mar 2023 17:36:11 +1100 Subject: [PATCH 1874/5631] KVM: PPC: Enable prefixed instructions for HV KVM and disable for PR KVM Now that we can read prefixed instructions from a HV KVM guest and emulate prefixed load/store instructions to emulated MMIO locations, we can add HFSCR_PREFIXED into the set of bits that are set in the HFSCR for a HV KVM guest on POWER10, allowing the guest to use prefixed instructions. PR KVM has not yet been extended to handle prefixed instructions in all situations where we might need to emulate them, so prevent the guest from enabling prefixed instructions in the FSCR for now. Reviewed-by: Nicholas Piggin Tested-by: Nicholas Piggin Signed-off-by: Paul Mackerras Tested-by: Sachin Sant Signed-off-by: Michael Ellerman Link: https://msgid.link/ZAgs25dCmLrVkBdU@cleo --- arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/kvm/book3s_hv.c | 9 +++++++-- arch/powerpc/kvm/book3s_pr.c | 2 ++ arch/powerpc/kvm/book3s_rmhandlers.S | 1 + 4 files changed, 11 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 1e8b2e04e626..7434a3300d84 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -417,6 +417,7 @@ #define FSCR_DSCR __MASK(FSCR_DSCR_LG) #define FSCR_INTR_CAUSE (ASM_CONST(0xFF) << 56) /* interrupt cause */ #define SPRN_HFSCR 0xbe /* HV=1 Facility Status & Control Register */ +#define HFSCR_PREFIX __MASK(FSCR_PREFIX_LG) #define HFSCR_MSGP __MASK(FSCR_MSGP_LG) #define HFSCR_TAR __MASK(FSCR_TAR_LG) #define HFSCR_EBB __MASK(FSCR_EBB_LG) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 283b9bcb014c..c973bf556fb3 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2930,13 +2930,18 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) /* * Set the default HFSCR for the guest from the host value. - * This value is only used on POWER9. - * On POWER9, we want to virtualize the doorbell facility, so we + * This value is only used on POWER9 and later. + * On >= POWER9, we want to virtualize the doorbell facility, so we * don't set the HFSCR_MSGP bit, and that causes those instructions * to trap and then we emulate them. */ vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + + /* On POWER10 and later, allow prefixed instructions */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + vcpu->arch.hfscr |= HFSCR_PREFIX; + if (cpu_has_feature(CPU_FTR_HVMODE)) { vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 556d90e018b3..da0e888e2521 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1044,6 +1044,8 @@ void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { if (fscr & FSCR_SCV) fscr &= ~FSCR_SCV; /* SCV must not be enabled */ + /* Prohibit prefixed instructions for now */ + fscr &= ~FSCR_PREFIX; if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 03886ca24498..0a557ffca9fe 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -123,6 +123,7 @@ INTERRUPT_TRAMPOLINE BOOK3S_INTERRUPT_ALTIVEC kvmppc_handler_skip_ins: /* Patch the IP to the next instruction */ + /* Note that prefixed instructions are disabled in PR KVM for now */ mfsrr0 r12 addi r12, r12, 4 mtsrr0 r12 -- GitLab From b7727e231dad51150ef14e1dbcbf0d185077e54b Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 30 Mar 2023 16:13:31 +0300 Subject: [PATCH 1875/5631] IB/iser: remove unused macros The removed macros are old leftovers. Reviewed-by: Sergey Gorenko Signed-off-by: Max Gurtovoy Link: https://lore.kernel.org/r/20230330131333.37900-1-mgurtovoy@nvidia.com Reviewed-by: Sagi Grimberg Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/iser/iser_verbs.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 1b8eda0dae4e..95b8eebf7e04 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -37,12 +37,6 @@ #include "iscsi_iser.h" -#define ISCSI_ISER_MAX_CONN 8 -#define ISER_MAX_RX_LEN (ISER_QP_MAX_RECV_DTOS * ISCSI_ISER_MAX_CONN) -#define ISER_MAX_TX_LEN (ISER_QP_MAX_REQ_DTOS * ISCSI_ISER_MAX_CONN) -#define ISER_MAX_CQ_LEN (ISER_MAX_RX_LEN + ISER_MAX_TX_LEN + \ - ISCSI_ISER_MAX_CONN) - static void iser_qp_event_callback(struct ib_event *cause, void *context) { iser_err("qp event %s (%d)\n", -- GitLab From 92363895b6c31bb5ba846b1f04cf624b8ed893a6 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 30 Mar 2023 16:13:32 +0300 Subject: [PATCH 1876/5631] IB/iser: centralize setting desc type and done callback Move this common logic into iser_create_send_desc instead of duplicating the code. Reviewed-by: Sergey Gorenko Signed-off-by: Max Gurtovoy Link: https://lore.kernel.org/r/20230330131333.37900-2-mgurtovoy@nvidia.com Reviewed-by: Sagi Grimberg Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/iser/iser_initiator.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 7b83f48f60c5..354928408399 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -141,10 +141,14 @@ static int iser_prepare_write_cmd(struct iscsi_task *task, unsigned int imm_sz, /* creates a new tx descriptor and adds header regd buffer */ static void iser_create_send_desc(struct iser_conn *iser_conn, - struct iser_tx_desc *tx_desc) + struct iser_tx_desc *tx_desc, enum iser_desc_type type, + void (*done)(struct ib_cq *cq, struct ib_wc *wc)) { struct iser_device *device = iser_conn->ib_conn.device; + tx_desc->type = type; + tx_desc->cqe.done = done; + ib_dma_sync_single_for_cpu(device->ib_device, tx_desc->dma_addr, ISER_HEADERS_LEN, DMA_TO_DEVICE); @@ -349,9 +353,8 @@ int iser_send_command(struct iscsi_conn *conn, struct iscsi_task *task) edtl = ntohl(hdr->data_length); /* build the tx desc regd header and add it to the tx desc dto */ - tx_desc->type = ISCSI_TX_SCSI_COMMAND; - tx_desc->cqe.done = iser_cmd_comp; - iser_create_send_desc(iser_conn, tx_desc); + iser_create_send_desc(iser_conn, tx_desc, ISCSI_TX_SCSI_COMMAND, + iser_cmd_comp); if (hdr->flags & ISCSI_FLAG_CMD_READ) { data_buf = &iser_task->data[ISER_DIR_IN]; @@ -478,9 +481,8 @@ int iser_send_control(struct iscsi_conn *conn, struct iscsi_task *task) struct iser_device *device; /* build the tx desc regd header and add it to the tx desc dto */ - mdesc->type = ISCSI_TX_CONTROL; - mdesc->cqe.done = iser_ctrl_comp; - iser_create_send_desc(iser_conn, mdesc); + iser_create_send_desc(iser_conn, mdesc, ISCSI_TX_CONTROL, + iser_ctrl_comp); device = iser_conn->ib_conn.device; -- GitLab From 070fc1c0e272a03c194bb1a54565d8eda23960a5 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 30 Mar 2023 16:13:33 +0300 Subject: [PATCH 1877/5631] IB/iser: remove redundant new line This commit doesn't change any logic. Reviewed-by: Sergey Gorenko Signed-off-by: Max Gurtovoy Link: https://lore.kernel.org/r/20230330131333.37900-3-mgurtovoy@nvidia.com Reviewed-by: Sagi Grimberg Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/iser/iser_initiator.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 354928408399..39ea73f69016 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -460,7 +460,6 @@ int iser_send_data_out(struct iscsi_conn *conn, struct iscsi_task *task, iser_dbg("data-out itt: %d, offset: %ld, sz: %ld\n", itt, buf_offset, data_seg_len); - err = iser_post_send(&iser_conn->ib_conn, tx_desc); if (!err) return 0; -- GitLab From 081c27b3bcdbfad6fa3c16975e02e33073f1267d Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Thu, 30 Mar 2023 11:36:07 -0400 Subject: [PATCH 1878/5631] RDMA/mlx5: Remove unused num_alloc_xa_entries variable clang with W=1 reports drivers/infiniband/hw/mlx5/devx.c:1996:6: error: variable 'num_alloc_xa_entries' set but not used [-Werror,-Wunused-but-set-variable] int num_alloc_xa_entries = 0; ^ This variable is not used so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230330153607.1838750-1-trix@redhat.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 2211a0be16f3..07037b829c7e 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1993,7 +1993,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)( int redirect_fd; bool use_eventfd = false; int num_events; - int num_alloc_xa_entries = 0; u16 obj_type = 0; u64 cookie = 0; u32 obj_id = 0; @@ -2075,7 +2074,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)( if (err) goto err; - num_alloc_xa_entries++; event_sub = kzalloc(sizeof(*event_sub), GFP_KERNEL); if (!event_sub) { err = -ENOMEM; -- GitLab From e7706c4bbfe88fe5bc9b8a6b1b5a84a5d58e2f7e Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Thu, 30 Mar 2023 19:58:00 -0400 Subject: [PATCH 1879/5631] IB/qib: Remove unused cnt variable clang with W=1 reports drivers/infiniband/hw/qib/qib_file_ops.c:487:20: error: variable 'cnt' set but not used [-Werror,-Wunused-but-set-variable] u32 tid, ctxttid, cnt, limit, tidcnt; ^ drivers/infiniband/hw/qib/qib_file_ops.c:1771:9: error: variable 'cnt' set but not used [-Werror,-Wunused-but-set-variable] int i, cnt = 0, maxtid = ctxt_tidbase + dd->rcvtidcnt; ^ This variable is not used so remove it. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230330235800.1845815-1-trix@redhat.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/qib/qib_file_ops.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 80fe92a21f96..076098803f52 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -484,7 +484,7 @@ static int qib_tid_free(struct qib_ctxtdata *rcd, unsigned subctxt, const struct qib_tid_info *ti) { int ret = 0; - u32 tid, ctxttid, cnt, limit, tidcnt; + u32 tid, ctxttid, limit, tidcnt; struct qib_devdata *dd = rcd->dd; u64 __iomem *tidbase; unsigned long tidmap[8]; @@ -520,7 +520,7 @@ static int qib_tid_free(struct qib_ctxtdata *rcd, unsigned subctxt, /* just in case size changes in future */ limit = tidcnt; tid = find_first_bit(tidmap, limit); - for (cnt = 0; tid < limit; tid++) { + for (; tid < limit; tid++) { /* * small optimization; if we detect a run of 3 or so without * any set, use find_first_bit again. That's mainly to @@ -530,7 +530,7 @@ static int qib_tid_free(struct qib_ctxtdata *rcd, unsigned subctxt, */ if (!test_bit(tid, tidmap)) continue; - cnt++; + if (dd->pageshadow[ctxttid + tid]) { struct page *p; dma_addr_t phys; @@ -1768,7 +1768,7 @@ static void unlock_expected_tids(struct qib_ctxtdata *rcd) { struct qib_devdata *dd = rcd->dd; int ctxt_tidbase = rcd->ctxt * dd->rcvtidcnt; - int i, cnt = 0, maxtid = ctxt_tidbase + dd->rcvtidcnt; + int i, maxtid = ctxt_tidbase + dd->rcvtidcnt; for (i = ctxt_tidbase; i < maxtid; i++) { struct page *p = dd->pageshadow[i]; @@ -1783,7 +1783,6 @@ static void unlock_expected_tids(struct qib_ctxtdata *rcd) dma_unmap_page(&dd->pcidev->dev, phys, PAGE_SIZE, DMA_FROM_DEVICE); qib_release_user_pages(&p, 1); - cnt++; } } -- GitLab From 08ebf57f6e1d73cc1890e1ff1b1c74887c53770b Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 31 Mar 2023 09:06:33 +0800 Subject: [PATCH 1880/5631] RDMA/cma: Remove NULL check before dev_{put, hold} The call netdev_{put, hold} of dev_{put, hold} will check NULL, so there is no need to check before using dev_{put, hold}, remove it to silence the warnings: ./drivers/infiniband/core/cma.c:713:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed. ./drivers/infiniband/core/cma.c:2433:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed. Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4668 Signed-off-by: Yang Li Link: https://lore.kernel.org/r/20230331010633.63261-1-yang.lee@linux.alibaba.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/cma.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 308155937713..9c7d26a7d243 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -710,8 +710,7 @@ cma_validate_port(struct ib_device *device, u32 port, } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); - if (ndev) - dev_put(ndev); + dev_put(ndev); return sgid_attr; } @@ -2430,8 +2429,7 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id, mutex_unlock(&listen_id->handler_mutex); net_dev_put: - if (net_dev) - dev_put(net_dev); + dev_put(net_dev); return ret; } -- GitLab From 5b524e4d16685a548ba143551709ded609d8ee05 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 11:05:45 +0200 Subject: [PATCH 1881/5631] MIPS: vpe-cmp: remove module owner pointer from struct class usage. In commit 6e30a66433af ("driver core: class: remove struct module owner out of struct class"), the module owner pointer was removed from struct class, but this was missed for the mips vpe-cmp code due to lack of build testing (and it being burried under a very unused config settings.) Fix this up by removing the module pointer to resolve the build error. Note, there are other problems with the driver model usage in this file (static struct device usage, empty device release function, etc.), so it probably could use some good cleaning up, but odds are this driver really isn't used so hopefully it will just be removed entirely someday soon as part of the general "remove unused arches" cleanup that is slowly happening. Cc: Dengcheng Zhu Cc: John Crispin Cc: Qais Yousef Cc: Steven J. Hill Cc: Yang Yingliang Cc: linux-mips@vger.kernel.org Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304020802.xbRTJKjW-lkp@intel.com/ Fixes: 6e30a66433af ("driver core: class: remove struct module owner out of struct class") Acked-by: Thomas Bogendoerfer Link: https://lore.kernel.org/r/2023040242-pursuable-frown-48d8@gregkh Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/vpe-cmp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/kernel/vpe-cmp.c b/arch/mips/kernel/vpe-cmp.c index 92140edb3ce3..4ef7f49a4c6d 100644 --- a/arch/mips/kernel/vpe-cmp.c +++ b/arch/mips/kernel/vpe-cmp.c @@ -79,7 +79,6 @@ static void vpe_device_release(struct device *cd) static struct class vpe_class = { .name = "vpe", - .owner = THIS_MODULE, .dev_release = vpe_device_release, .dev_groups = vpe_groups, }; -- GitLab From a131e33715fca8a047bdfc3d67b10eb743eea4b0 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 11:11:18 +0200 Subject: [PATCH 1882/5631] driver core: remove incorrect comment for device_create* The device_create() and device_create_with_groups() function comments incorrectly state that they only work with a struct class that was created using class_create(), but that is not true now and I am not sure if it ever was. So just remove the comment as it's not needed now. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040218-scouts-unplowed-24d2@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 47e16c088e77..64d188be4df9 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4332,9 +4332,6 @@ device_create_groups_vargs(const struct class *class, struct device *parent, * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. - * - * Note: the struct class passed to this function must have previously - * been created with a call to class_create(). */ struct device *device_create(const struct class *class, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...) @@ -4373,9 +4370,6 @@ EXPORT_SYMBOL_GPL(device_create); * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. - * - * Note: the struct class passed to this function must have previously - * been created with a call to class_create(). */ struct device *device_create_with_groups(const struct class *class, struct device *parent, dev_t devt, -- GitLab From 266e9b3475ba82212062771fdbc40be0e3c06ec8 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sun, 2 Apr 2023 14:10:13 +0900 Subject: [PATCH 1883/5631] RDMA/siw: Remove namespace check from siw_netdev_event() syzbot is reporting that siw_netdev_event(NETDEV_UNREGISTER) cannot destroy siw_device created after unshare(CLONE_NEWNET) due to net namespace check. It seems that this check was by error there and should be removed. Reported-by: syzbot Link: https://syzkaller.appspot.com/bug?extid=5e70d01ee8985ae62a3b Suggested-by: Jason Gunthorpe Suggested-by: Leon Romanovsky Fixes: bdcf26bf9b3a ("rdma/siw: network and RDMA core interface") Signed-off-by: Tetsuo Handa Link: https://lore.kernel.org/r/a44e9ac5-44e2-d575-9e30-02483cc7ffd1@I-love.SAKURA.ne.jp Reviewed-by: Bernard Metzler Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/siw/siw_main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index dacc174604bf..65b5cda5457b 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -437,9 +437,6 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, dev_dbg(&netdev->dev, "siw: event %lu\n", event); - if (dev_net(netdev) != &init_net) - return NOTIFY_OK; - base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; -- GitLab From 979207cac517833c828133ffb2633bcdf6edce00 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:46 +0200 Subject: [PATCH 1884/5631] driver core: class: mark class_release() as taking a const * The struct class callback, class_release(), is only called in 2 places, the pcmcia cardservices code, and in the class driver core code. Both places it is safe to mark the structure as a const *, to allow us to in the future mark all struct class usages as constant and move into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040248-outrage-obsolete-5a9a@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 +- drivers/pcmcia/cs.c | 2 +- include/linux/device/class.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 65502bd7d5c5..53fc7052340c 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -235,7 +235,7 @@ void class_unregister(const struct class *cls) } EXPORT_SYMBOL_GPL(class_unregister); -static void class_create_release(struct class *cls) +static void class_create_release(const struct class *cls) { pr_debug("%s called for %s\n", __func__, cls->name); kfree(cls); diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index e3224e49c43f..5658745c398f 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -824,7 +824,7 @@ static int pcmcia_socket_uevent(const struct device *dev, static struct completion pcmcia_unload; -static void pcmcia_release_socket_class(struct class *data) +static void pcmcia_release_socket_class(const struct class *data) { complete(&pcmcia_unload); } diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 7e4a1a6329f4..f3c418fa129a 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -58,7 +58,7 @@ struct class { int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); - void (*class_release)(struct class *class); + void (*class_release)(const struct class *class); void (*dev_release)(struct device *dev); int (*shutdown_pre)(struct device *dev); -- GitLab From 43a7206b0963c2153c95d6985624d1dc1b3abd4d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:47 +0200 Subject: [PATCH 1885/5631] driver core: class: make class_register() take a const * Now that the class code is cleaned up to not modify the class pointer registered with it, change class_register() to take a const * to allow the structure to be placed into read-only memory. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040248-customary-release-4aec@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/base.h | 2 +- drivers/base/class.c | 6 +++--- include/linux/device/class.h | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index e96f3343fd7c..eb4c0ace9242 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -54,7 +54,7 @@ struct subsys_private { struct device *dev_root; struct kset glue_dirs; - struct class *class; + const struct class *class; struct lock_class_key lock_key; }; diff --git a/drivers/base/class.c b/drivers/base/class.c index 53fc7052340c..05bce79d3d19 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -93,7 +93,7 @@ static ssize_t class_attr_store(struct kobject *kobj, struct attribute *attr, static void class_release(struct kobject *kobj) { struct subsys_private *cp = to_subsys_private(kobj); - struct class *class = cp->class; + const struct class *class = cp->class; pr_debug("class '%s': release.\n", class->name); @@ -110,7 +110,7 @@ static void class_release(struct kobject *kobj) static const struct kobj_ns_type_operations *class_child_ns_type(const struct kobject *kobj) { const struct subsys_private *cp = to_subsys_private(kobj); - struct class *class = cp->class; + const struct class *class = cp->class; return class->ns_type; } @@ -175,7 +175,7 @@ static void klist_class_dev_put(struct klist_node *n) put_device(dev); } -int class_register(struct class *cls) +int class_register(const struct class *cls) { struct subsys_private *cp; struct lock_class_key *key; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index f3c418fa129a..4bf46f9bbb56 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -76,7 +76,7 @@ struct class_dev_iter { const struct device_type *type; }; -int __must_check class_register(struct class *class); +int __must_check class_register(const struct class *class); void class_unregister(const struct class *class); bool class_is_registered(const struct class *class); -- GitLab From 6b0d49be81cf4f1cf30ebd079cbf4643cab0a01d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:48 +0200 Subject: [PATCH 1886/5631] driver core: class: mark the struct class in struct class_interface constant The struct class pointer in struct class_interface is never modified, so mark it as const so that no one accidentally tries to modify it in the future. Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/2023040249-handball-gruffly-5da7@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 +- include/linux/device/class.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index 05bce79d3d19..ad8b9f163fd2 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -498,7 +498,7 @@ EXPORT_SYMBOL_GPL(class_interface_register); void class_interface_unregister(struct class_interface *class_intf) { struct subsys_private *sp; - struct class *parent = class_intf->class; + const struct class *parent = class_intf->class; struct class_dev_iter iter; struct device *dev; diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 4bf46f9bbb56..53287aa105b8 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -217,7 +217,7 @@ ssize_t show_class_attr_string(const struct class *class, const struct class_att struct class_interface { struct list_head node; - struct class *class; + const struct class *class; int (*add_dev) (struct device *, struct class_interface *); void (*remove_dev) (struct device *, struct class_interface *); -- GitLab From 2243acd50ac4026e93ac4f024109be6dbd7f9098 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:49 +0200 Subject: [PATCH 1887/5631] driver core: class: remove struct class_interface * from callbacks The add_dev and remove_dev callbacks in struct class_interface currently pass in a pointer back to the class_interface structure that is calling them, but none of the callback implementations actually use this pointer as it is pointless (the structure is known, the driver passed it in in the first place if it is really needed again.) So clean this up and just remove the pointer from the callbacks and fix up all callback functions. Cc: Jean Delvare Cc: Guenter Roeck Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Kurt Schwemmer Cc: Jon Mason Cc: Dave Jiang Cc: Allen Hubbe Cc: Dominik Brodowski Cc: Matt Porter Cc: Alexandre Bounine Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Doug Gilbert Cc: John Stultz Cc: Thomas Gleixner Cc: Stephen Boyd Cc: Hans de Goede Cc: Andrew Morton Cc: Wang Weiyang Cc: Yang Yingliang Cc: Jakob Koschel Cc: Cai Xinchen Acked-by: Rafael J. Wysocki Acked-by: Logan Gunthorpe Link: https://lore.kernel.org/r/2023040250-pushover-platter-509c@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 4 ++-- drivers/base/core.c | 10 ++++------ drivers/hwmon/drivetemp.c | 4 ++-- drivers/net/rionet.c | 3 +-- drivers/ntb/hw/mscc/ntb_hw_switchtec.c | 6 ++---- drivers/pcmcia/ds.c | 6 ++---- drivers/pcmcia/rsrc_nonstatic.c | 6 ++---- drivers/rapidio/devices/rio_mport_cdev.c | 7 ++----- drivers/rapidio/rio_cm.c | 8 ++------ drivers/scsi/ses.c | 6 ++---- drivers/scsi/sg.c | 8 ++++---- include/linux/device/class.h | 4 ++-- kernel/time/alarmtimer.c | 3 +-- 13 files changed, 28 insertions(+), 47 deletions(-) diff --git a/drivers/base/class.c b/drivers/base/class.c index ad8b9f163fd2..ac1808d1a2e8 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -486,7 +486,7 @@ int class_interface_register(struct class_interface *class_intf) if (class_intf->add_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) - class_intf->add_dev(dev, class_intf); + class_intf->add_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); @@ -514,7 +514,7 @@ void class_interface_unregister(struct class_interface *class_intf) if (class_intf->remove_dev) { class_dev_iter_init(&iter, parent, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) - class_intf->remove_dev(dev, class_intf); + class_intf->remove_dev(dev); class_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); diff --git a/drivers/base/core.c b/drivers/base/core.c index 64d188be4df9..7a42d1b6b721 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -541,8 +541,7 @@ static struct class devlink_class = { .dev_release = devlink_dev_release, }; -static int devlink_add_symlinks(struct device *dev, - struct class_interface *class_intf) +static int devlink_add_symlinks(struct device *dev) { int ret; size_t len; @@ -591,8 +590,7 @@ static int devlink_add_symlinks(struct device *dev, return ret; } -static void devlink_remove_symlinks(struct device *dev, - struct class_interface *class_intf) +static void devlink_remove_symlinks(struct device *dev) { struct device_link *link = to_devlink(dev); size_t len; @@ -3647,7 +3645,7 @@ int device_add(struct device *dev) /* notify any interfaces that the device is here */ list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->add_dev) - class_intf->add_dev(dev, class_intf); + class_intf->add_dev(dev); mutex_unlock(&sp->mutex); subsys_put(sp); } @@ -3805,7 +3803,7 @@ void device_del(struct device *dev) /* notify any interfaces that the device is now gone */ list_for_each_entry(class_intf, &sp->interfaces, node) if (class_intf->remove_dev) - class_intf->remove_dev(dev, class_intf); + class_intf->remove_dev(dev); /* remove the device from the class list */ klist_del(&dev->p->knode_class); mutex_unlock(&sp->mutex); diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 8e5759b42390..86171031ddc5 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -550,7 +550,7 @@ static const struct hwmon_chip_info drivetemp_chip_info = { * The device argument points to sdev->sdev_dev. Its parent is * sdev->sdev_gendev, which we can use to get the scsi_device pointer. */ -static int drivetemp_add(struct device *dev, struct class_interface *intf) +static int drivetemp_add(struct device *dev) { struct scsi_device *sdev = to_scsi_device(dev->parent); struct drivetemp_data *st; @@ -585,7 +585,7 @@ static int drivetemp_add(struct device *dev, struct class_interface *intf) return err; } -static void drivetemp_remove(struct device *dev, struct class_interface *intf) +static void drivetemp_remove(struct device *dev) { struct drivetemp_data *st, *tmp; diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index fbcb9d05da64..4eececc94513 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -662,8 +662,7 @@ static int rionet_shutdown(struct notifier_block *nb, unsigned long code, return NOTIFY_DONE; } -static void rionet_remove_mport(struct device *dev, - struct class_interface *class_intf) +static void rionet_remove_mport(struct device *dev) { struct rio_mport *mport = to_rio_mport(dev); struct net_device *ndev; diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index 88ae18b0efa8..d6bbcc7b5b90 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -1470,8 +1470,7 @@ static int switchtec_ntb_reinit_peer(struct switchtec_ntb *sndev) return rc; } -static int switchtec_ntb_add(struct device *dev, - struct class_interface *class_intf) +static int switchtec_ntb_add(struct device *dev) { struct switchtec_dev *stdev = to_stdev(dev); struct switchtec_ntb *sndev; @@ -1541,8 +1540,7 @@ static int switchtec_ntb_add(struct device *dev, return rc; } -static void switchtec_ntb_remove(struct device *dev, - struct class_interface *class_intf) +static void switchtec_ntb_remove(struct device *dev) { struct switchtec_dev *stdev = to_stdev(dev); struct switchtec_ntb *sndev = stdev->sndev; diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index c8087efa5e4a..d500e5dbbc3f 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -1335,8 +1335,7 @@ static struct pcmcia_callback pcmcia_bus_callback = { .resume = pcmcia_bus_resume, }; -static int pcmcia_bus_add_socket(struct device *dev, - struct class_interface *class_intf) +static int pcmcia_bus_add_socket(struct device *dev) { struct pcmcia_socket *socket = dev_get_drvdata(dev); int ret; @@ -1369,8 +1368,7 @@ static int pcmcia_bus_add_socket(struct device *dev, return 0; } -static void pcmcia_bus_remove_socket(struct device *dev, - struct class_interface *class_intf) +static void pcmcia_bus_remove_socket(struct device *dev) { struct pcmcia_socket *socket = dev_get_drvdata(dev); diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index ad1141fddb4c..471e0c5815f3 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -1200,8 +1200,7 @@ static const struct attribute_group rsrc_attributes = { .attrs = pccard_rsrc_attributes, }; -static int pccard_sysfs_add_rsrc(struct device *dev, - struct class_interface *class_intf) +static int pccard_sysfs_add_rsrc(struct device *dev) { struct pcmcia_socket *s = dev_get_drvdata(dev); @@ -1210,8 +1209,7 @@ static int pccard_sysfs_add_rsrc(struct device *dev, return sysfs_create_group(&dev->kobj, &rsrc_attributes); } -static void pccard_sysfs_remove_rsrc(struct device *dev, - struct class_interface *class_intf) +static void pccard_sysfs_remove_rsrc(struct device *dev) { struct pcmcia_socket *s = dev_get_drvdata(dev); diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index deb96c3160a7..a115730ebf14 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -2536,10 +2536,8 @@ static void mport_cdev_remove(struct mport_dev *md) /* * mport_add_mport() - Add rio_mport from LDM device struct * @dev: Linux device model struct - * @class_intf: Linux class_interface */ -static int mport_add_mport(struct device *dev, - struct class_interface *class_intf) +static int mport_add_mport(struct device *dev) { struct rio_mport *mport = NULL; struct mport_dev *chdev = NULL; @@ -2559,8 +2557,7 @@ static int mport_add_mport(struct device *dev, * mport_remove_mport() - Remove rio_mport from global list * TODO remove device from global mport_dev list */ -static void mport_remove_mport(struct device *dev, - struct class_interface *class_intf) +static void mport_remove_mport(struct device *dev) { struct rio_mport *mport = NULL; struct mport_dev *chdev; diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index acaf9cda014c..49f8d111e546 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -2087,13 +2087,11 @@ static int riocm_cdev_add(dev_t devno) /* * riocm_add_mport - add new local mport device into channel management core * @dev: device object associated with mport - * @class_intf: class interface * * When a new mport device is added, CM immediately reserves inbound and * outbound RapidIO mailboxes that will be used. */ -static int riocm_add_mport(struct device *dev, - struct class_interface *class_intf) +static int riocm_add_mport(struct device *dev) { int rc; int i; @@ -2166,14 +2164,12 @@ static int riocm_add_mport(struct device *dev, /* * riocm_remove_mport - remove local mport device from channel management core * @dev: device object associated with mport - * @class_intf: class interface * * Removes a local mport device from the list of registered devices that provide * channel management services. Returns an error if the specified mport is not * registered with the CM core. */ -static void riocm_remove_mport(struct device *dev, - struct class_interface *class_intf) +static void riocm_remove_mport(struct device *dev) { struct rio_mport *mport = to_rio_mport(dev); struct cm_dev *cm; diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index b11a9162e73a..57feb0cae896 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -663,8 +663,7 @@ static void ses_match_to_enclosure(struct enclosure_device *edev, } } -static int ses_intf_add(struct device *cdev, - struct class_interface *intf) +static int ses_intf_add(struct device *cdev) { struct scsi_device *sdev = to_scsi_device(cdev->parent); struct scsi_device *tmp_sdev; @@ -869,8 +868,7 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) enclosure_unregister(edev); } -static void ses_intf_remove(struct device *cdev, - struct class_interface *intf) +static void ses_intf_remove(struct device *cdev) { struct scsi_device *sdev = to_scsi_device(cdev->parent); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4997f880d4a4..037f8c98a6d3 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -96,8 +96,8 @@ static int scatter_elem_sz_prev = SG_SCATTER_SZ; #define SG_SECTOR_SZ 512 -static int sg_add_device(struct device *, struct class_interface *); -static void sg_remove_device(struct device *, struct class_interface *); +static int sg_add_device(struct device *); +static void sg_remove_device(struct device *); static DEFINE_IDR(sg_index_idr); static DEFINE_RWLOCK(sg_index_lock); /* Also used to lock @@ -1488,7 +1488,7 @@ sg_alloc(struct scsi_device *scsidp) } static int -sg_add_device(struct device *cl_dev, struct class_interface *cl_intf) +sg_add_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = NULL; @@ -1578,7 +1578,7 @@ sg_device_destroy(struct kref *kref) } static void -sg_remove_device(struct device *cl_dev, struct class_interface *cl_intf) +sg_remove_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = dev_get_drvdata(cl_dev); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 53287aa105b8..9deeaeb457bb 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -219,8 +219,8 @@ struct class_interface { struct list_head node; const struct class *class; - int (*add_dev) (struct device *, struct class_interface *); - void (*remove_dev) (struct device *, struct class_interface *); + int (*add_dev) (struct device *dev); + void (*remove_dev) (struct device *dev); }; int __must_check class_interface_register(struct class_interface *); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 7e5dff602585..82b28ab0f328 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -81,8 +81,7 @@ struct rtc_device *alarmtimer_get_rtcdev(void) } EXPORT_SYMBOL_GPL(alarmtimer_get_rtcdev); -static int alarmtimer_rtc_add_device(struct device *dev, - struct class_interface *class_intf) +static int alarmtimer_rtc_add_device(struct device *dev) { unsigned long flags; struct rtc_device *rtc = to_rtc_device(dev); -- GitLab From 862d8312eed994a8a9af7aa8e9e15456183b10a7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sun, 2 Apr 2023 19:58:50 +0200 Subject: [PATCH 1888/5631] tty: make tty_class a static const structure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that the driver core allows for struct class to be in read-only memory, move the tty_class structure to be declared at build time placing it into read-only memory, instead of having to be dynamically allocated at boot time. Cc: "Ilpo Järvinen" Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/2023040250-landowner-unfitted-11f4@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/tty/pty.c | 2 +- drivers/tty/tty_io.c | 24 +++++++++++------------- drivers/tty/vt/vt.c | 2 +- include/linux/tty.h | 2 +- 4 files changed, 14 insertions(+), 16 deletions(-) diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 07394fdaf522..2b1c8ab99dba 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -931,7 +931,7 @@ static void __init unix98_pty_init(void) if (cdev_add(&ptmx_cdev, MKDEV(TTYAUX_MAJOR, 2), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0) panic("Couldn't register /dev/ptmx driver"); - device_create(tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx"); + device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx"); } #else diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 1382d9050ce8..44e0d53aa0b8 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -3070,7 +3070,7 @@ static struct device *tty_get_device(struct tty_struct *tty) { dev_t devt = tty_devnum(tty); - return class_find_device_by_devt(tty_class, devt); + return class_find_device_by_devt(&tty_class, devt); } @@ -3143,8 +3143,6 @@ int tty_put_char(struct tty_struct *tty, unsigned char ch) } EXPORT_SYMBOL_GPL(tty_put_char); -struct class *tty_class; - static int tty_cdev_add(struct tty_driver *driver, dev_t dev, unsigned int index, unsigned int count) { @@ -3239,7 +3237,7 @@ struct device *tty_register_device_attr(struct tty_driver *driver, return ERR_PTR(-ENOMEM); dev->devt = devt; - dev->class = tty_class; + dev->class = &tty_class; dev->parent = device; dev->release = tty_device_create_release; dev_set_name(dev, "%s", name); @@ -3294,8 +3292,7 @@ EXPORT_SYMBOL_GPL(tty_register_device_attr); */ void tty_unregister_device(struct tty_driver *driver, unsigned index) { - device_destroy(tty_class, - MKDEV(driver->major, driver->minor_start) + index); + device_destroy(&tty_class, MKDEV(driver->major, driver->minor_start) + index); if (!(driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)) { cdev_del(driver->cdevs[index]); driver->cdevs[index] = NULL; @@ -3510,13 +3507,14 @@ static char *tty_devnode(const struct device *dev, umode_t *mode) return NULL; } +const struct class tty_class = { + .name = "tty", + .devnode = tty_devnode, +}; + static int __init tty_class_init(void) { - tty_class = class_create("tty"); - if (IS_ERR(tty_class)) - return PTR_ERR(tty_class); - tty_class->devnode = tty_devnode; - return 0; + return class_register(&tty_class); } postcore_initcall(tty_class_init); @@ -3643,13 +3641,13 @@ int __init tty_init(void) if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0) panic("Couldn't register /dev/tty driver\n"); - device_create(tty_class, NULL, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty"); + device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty"); cdev_init(&console_cdev, &console_fops); if (cdev_add(&console_cdev, MKDEV(TTYAUX_MAJOR, 1), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 1), 1, "/dev/console") < 0) panic("Couldn't register /dev/console driver\n"); - consdev = device_create_with_groups(tty_class, NULL, + consdev = device_create_with_groups(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 1), NULL, cons_dev_groups, "console"); if (IS_ERR(consdev)) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 81c148064aa6..40e4928eddaf 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3539,7 +3539,7 @@ int __init vty_init(const struct file_operations *console_fops) if (cdev_add(&vc0_cdev, MKDEV(TTY_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTY_MAJOR, 0), 1, "/dev/vc/0") < 0) panic("Couldn't register /dev/tty0 driver\n"); - tty0dev = device_create_with_groups(tty_class, NULL, + tty0dev = device_create_with_groups(&tty_class, NULL, MKDEV(TTY_MAJOR, 0), NULL, vt_dev_groups, "tty0"); if (IS_ERR(tty0dev)) diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..121eb4b0d325 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -387,7 +387,7 @@ extern struct ktermios tty_std_termios; int vcs_init(void); -extern struct class *tty_class; +extern const struct class tty_class; /** * tty_kref_get - get a tty reference -- GitLab From 63b2af49654b11b57ca1746e48c1ac63e0bd6de1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:39:51 +0200 Subject: [PATCH 1889/5631] staging: axis-fifo: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/axis-fifo/axis-fifo.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 0a85ea667a1b..7a21f2423204 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -916,15 +916,13 @@ static int axis_fifo_probe(struct platform_device *pdev) return rc; } -static int axis_fifo_remove(struct platform_device *pdev) +static void axis_fifo_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct axis_fifo *fifo = dev_get_drvdata(dev); misc_deregister(&fifo->miscdev); dev_set_drvdata(dev, NULL); - - return 0; } static const struct of_device_id axis_fifo_of_match[] = { @@ -939,7 +937,7 @@ static struct platform_driver axis_fifo_driver = { .of_match_table = axis_fifo_of_match, }, .probe = axis_fifo_probe, - .remove = axis_fifo_remove, + .remove_new = axis_fifo_remove, }; static int __init axis_fifo_init(void) -- GitLab From 68c8e9ff5d32d0ce34f972746b96d1e4a2f5b042 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:39:52 +0200 Subject: [PATCH 1890/5631] staging: emxx_udc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/emxx_udc/emxx_udc.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/emxx_udc/emxx_udc.c b/drivers/staging/emxx_udc/emxx_udc.c index f9765841c4aa..eb63daaca702 100644 --- a/drivers/staging/emxx_udc/emxx_udc.c +++ b/drivers/staging/emxx_udc/emxx_udc.c @@ -3137,7 +3137,7 @@ static void nbu2ss_drv_shutdown(struct platform_device *pdev) } /*-------------------------------------------------------------------------*/ -static int nbu2ss_drv_remove(struct platform_device *pdev) +static void nbu2ss_drv_remove(struct platform_device *pdev) { struct nbu2ss_udc *udc; struct nbu2ss_ep *ep; @@ -3154,8 +3154,6 @@ static int nbu2ss_drv_remove(struct platform_device *pdev) /* Interrupt Handler - Release */ free_irq(vbus_irq, udc); - - return 0; } /*-------------------------------------------------------------------------*/ @@ -3210,7 +3208,7 @@ static int nbu2ss_drv_resume(struct platform_device *pdev) static struct platform_driver udc_driver = { .probe = nbu2ss_drv_probe, .shutdown = nbu2ss_drv_shutdown, - .remove = nbu2ss_drv_remove, + .remove_new = nbu2ss_drv_remove, .suspend = nbu2ss_drv_suspend, .resume = nbu2ss_drv_resume, .driver = { -- GitLab From ba110722924c1b2c111170736278d87ee381484b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:39:53 +0200 Subject: [PATCH 1891/5631] staging: fieldbus: arcx-anybus: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-4-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/fieldbus/anybuss/arcx-anybus.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/fieldbus/anybuss/arcx-anybus.c b/drivers/staging/fieldbus/anybuss/arcx-anybus.c index 9af2e63050d1..afef35bbea74 100644 --- a/drivers/staging/fieldbus/anybuss/arcx-anybus.c +++ b/drivers/staging/fieldbus/anybuss/arcx-anybus.c @@ -321,7 +321,7 @@ static int controller_probe(struct platform_device *pdev) return err; } -static int controller_remove(struct platform_device *pdev) +static void controller_remove(struct platform_device *pdev) { struct controller_priv *cd = platform_get_drvdata(pdev); int id = cd->class_dev->id; @@ -329,7 +329,6 @@ static int controller_remove(struct platform_device *pdev) device_unregister(cd->class_dev); ida_simple_remove(&controller_index_ida, id); gpiod_set_value_cansleep(cd->reset_gpiod, 1); - return 0; } static const struct of_device_id controller_of_match[] = { @@ -341,7 +340,7 @@ MODULE_DEVICE_TABLE(of, controller_of_match); static struct platform_driver controller_driver = { .probe = controller_probe, - .remove = controller_remove, + .remove_new = controller_remove, .driver = { .name = "arcx-anybus-controller", .of_match_table = of_match_ptr(controller_of_match), -- GitLab From 9b19a31c20f1040004e4cbda4945023e2ce86ad3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:39:54 +0200 Subject: [PATCH 1892/5631] staging: greybus: arche-apb-ctrl: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/arche-apb-ctrl.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/greybus/arche-apb-ctrl.c b/drivers/staging/greybus/arche-apb-ctrl.c index 45afa208d004..8541995008da 100644 --- a/drivers/staging/greybus/arche-apb-ctrl.c +++ b/drivers/staging/greybus/arche-apb-ctrl.c @@ -419,13 +419,11 @@ static int arche_apb_ctrl_probe(struct platform_device *pdev) return 0; } -static int arche_apb_ctrl_remove(struct platform_device *pdev) +static void arche_apb_ctrl_remove(struct platform_device *pdev) { device_remove_file(&pdev->dev, &dev_attr_state); poweroff_seq(pdev); platform_set_drvdata(pdev, NULL); - - return 0; } static int __maybe_unused arche_apb_ctrl_suspend(struct device *dev) @@ -471,7 +469,7 @@ static const struct of_device_id arche_apb_ctrl_of_match[] = { static struct platform_driver arche_apb_ctrl_device_driver = { .probe = arche_apb_ctrl_probe, - .remove = arche_apb_ctrl_remove, + .remove_new = arche_apb_ctrl_remove, .shutdown = arche_apb_ctrl_shutdown, .driver = { .name = "arche-apb-ctrl", -- GitLab From 7846a2ae5ccd1d08bcfff4a6cfedbc33680cf6cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:39:55 +0200 Subject: [PATCH 1893/5631] staging: greybus: arche: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/arche-platform.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/greybus/arche-platform.c b/drivers/staging/greybus/arche-platform.c index fcbd5f71eff2..ebe835f25d13 100644 --- a/drivers/staging/greybus/arche-platform.c +++ b/drivers/staging/greybus/arche-platform.c @@ -559,7 +559,7 @@ static int arche_remove_child(struct device *dev, void *unused) return 0; } -static int arche_platform_remove(struct platform_device *pdev) +static void arche_platform_remove(struct platform_device *pdev) { struct arche_platform_drvdata *arche_pdata = platform_get_drvdata(pdev); @@ -570,8 +570,6 @@ static int arche_platform_remove(struct platform_device *pdev) if (usb3613_hub_mode_ctrl(false)) dev_warn(arche_pdata->dev, "failed to control hub device\n"); - /* TODO: Should we do anything more here ?? */ - return 0; } static __maybe_unused int arche_platform_suspend(struct device *dev) @@ -631,7 +629,7 @@ MODULE_DEVICE_TABLE(of, arche_combined_id); static struct platform_driver arche_platform_device_driver = { .probe = arche_platform_probe, - .remove = arche_platform_remove, + .remove_new = arche_platform_remove, .shutdown = arche_platform_shutdown, .driver = { .name = "arche-platform-ctrl", -- GitLab From 51559b8e9bf9e3324413ab1c171df05d408dd81b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:07 +0200 Subject: [PATCH 1894/5631] staging: most: dim2: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-18-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/most/dim2/dim2.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/most/dim2/dim2.c b/drivers/staging/most/dim2/dim2.c index 9fa665c4038f..44d3252d4612 100644 --- a/drivers/staging/most/dim2/dim2.c +++ b/drivers/staging/most/dim2/dim2.c @@ -908,13 +908,11 @@ static int dim2_probe(struct platform_device *pdev) * * Unregister the interface from mostcore */ -static int dim2_remove(struct platform_device *pdev) +static void dim2_remove(struct platform_device *pdev) { struct dim2_hdm *dev = platform_get_drvdata(pdev); most_deregister_interface(&dev->most_iface); - - return 0; } /* platform specific functions [[ */ @@ -1092,7 +1090,7 @@ MODULE_DEVICE_TABLE(of, dim2_of_match); static struct platform_driver dim2_driver = { .probe = dim2_probe, - .remove = dim2_remove, + .remove_new = dim2_remove, .driver = { .name = "hdm_dim2", .of_match_table = dim2_of_match, -- GitLab From 398296fd509df4d36b8b09bb0c839e80ebb9a05b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:08 +0200 Subject: [PATCH 1895/5631] staging: nvec: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-19-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/nvec.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/nvec/nvec.c b/drivers/staging/nvec/nvec.c index b3f114cb00dc..2823cacde130 100644 --- a/drivers/staging/nvec/nvec.c +++ b/drivers/staging/nvec/nvec.c @@ -882,7 +882,7 @@ static int tegra_nvec_probe(struct platform_device *pdev) return 0; } -static int tegra_nvec_remove(struct platform_device *pdev) +static void tegra_nvec_remove(struct platform_device *pdev) { struct nvec_chip *nvec = platform_get_drvdata(pdev); @@ -893,8 +893,6 @@ static int tegra_nvec_remove(struct platform_device *pdev) cancel_work_sync(&nvec->tx_work); /* FIXME: needs check whether nvec is responsible for power off */ pm_power_off = NULL; - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -942,7 +940,7 @@ MODULE_DEVICE_TABLE(of, nvidia_nvec_of_match); static struct platform_driver nvec_device_driver = { .probe = tegra_nvec_probe, - .remove = tegra_nvec_remove, + .remove_new = tegra_nvec_remove, .driver = { .name = "nvec", .pm = &nvec_pm_ops, -- GitLab From 46ea3230264b591dcabbceb06e87fc33236900a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:09 +0200 Subject: [PATCH 1896/5631] staging: nvec: nvec_kbd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-20-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/nvec_kbd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/nvec/nvec_kbd.c b/drivers/staging/nvec/nvec_kbd.c index 386d619e3ee9..f9a1da952c0a 100644 --- a/drivers/staging/nvec/nvec_kbd.c +++ b/drivers/staging/nvec/nvec_kbd.c @@ -161,7 +161,7 @@ static int nvec_kbd_probe(struct platform_device *pdev) return 0; } -static int nvec_kbd_remove(struct platform_device *pdev) +static void nvec_kbd_remove(struct platform_device *pdev) { struct nvec_chip *nvec = dev_get_drvdata(pdev->dev.parent); char disable_kbd[] = { NVEC_KBD, DISABLE_KBD }, @@ -170,13 +170,11 @@ static int nvec_kbd_remove(struct platform_device *pdev) nvec_write_async(nvec, uncnfg_wake_key_reporting, 3); nvec_write_async(nvec, disable_kbd, 2); nvec_unregister_notifier(nvec, &keys_dev.notifier); - - return 0; } static struct platform_driver nvec_kbd_driver = { .probe = nvec_kbd_probe, - .remove = nvec_kbd_remove, + .remove_new = nvec_kbd_remove, .driver = { .name = "nvec-kbd", }, -- GitLab From f1e870c45be5b6262dc452b7131ab81290ad7180 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:10 +0200 Subject: [PATCH 1897/5631] staging: nvec_power: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-21-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/nvec_power.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/nvec/nvec_power.c b/drivers/staging/nvec/nvec_power.c index b1ef196e1cfe..9943b1fff190 100644 --- a/drivers/staging/nvec/nvec_power.c +++ b/drivers/staging/nvec/nvec_power.c @@ -416,7 +416,7 @@ static int nvec_power_probe(struct platform_device *pdev) return PTR_ERR_OR_ZERO(*psy); } -static int nvec_power_remove(struct platform_device *pdev) +static void nvec_power_remove(struct platform_device *pdev) { struct nvec_power *power = platform_get_drvdata(pdev); @@ -429,13 +429,11 @@ static int nvec_power_remove(struct platform_device *pdev) case BAT: power_supply_unregister(nvec_bat_psy); } - - return 0; } static struct platform_driver nvec_power_driver = { .probe = nvec_power_probe, - .remove = nvec_power_remove, + .remove_new = nvec_power_remove, .driver = { .name = "nvec-power", } -- GitLab From cedff4e3e23c5b26c64e901b139fe88b89678540 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:11 +0200 Subject: [PATCH 1898/5631] staging: nvec_ps2: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-22-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/nvec/nvec_ps2.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/nvec/nvec_ps2.c b/drivers/staging/nvec/nvec_ps2.c index 06041c7f7d4f..cb6d71b8dc83 100644 --- a/drivers/staging/nvec/nvec_ps2.c +++ b/drivers/staging/nvec/nvec_ps2.c @@ -125,7 +125,7 @@ static int nvec_mouse_probe(struct platform_device *pdev) return 0; } -static int nvec_mouse_remove(struct platform_device *pdev) +static void nvec_mouse_remove(struct platform_device *pdev) { struct nvec_chip *nvec = dev_get_drvdata(pdev->dev.parent); @@ -133,8 +133,6 @@ static int nvec_mouse_remove(struct platform_device *pdev) ps2_stopstreaming(ps2_dev.ser_dev); nvec_unregister_notifier(nvec, &ps2_dev.notifier); serio_unregister_port(ps2_dev.ser_dev); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -166,7 +164,7 @@ static SIMPLE_DEV_PM_OPS(nvec_mouse_pm_ops, nvec_mouse_suspend, static struct platform_driver nvec_mouse_driver = { .probe = nvec_mouse_probe, - .remove = nvec_mouse_remove, + .remove_new = nvec_mouse_remove, .driver = { .name = "nvec-mouse", .pm = &nvec_mouse_pm_ops, -- GitLab From c46d4073ec6871c3531fa96c49bf45c8598bf791 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:12 +0200 Subject: [PATCH 1899/5631] staging: octeon: ethernet: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-23-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/staging/octeon/ethernet.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c index f662739137b5..9eee28f2940c 100644 --- a/drivers/staging/octeon/ethernet.c +++ b/drivers/staging/octeon/ethernet.c @@ -924,7 +924,7 @@ static int cvm_oct_probe(struct platform_device *pdev) return 0; } -static int cvm_oct_remove(struct platform_device *pdev) +static void cvm_oct_remove(struct platform_device *pdev) { int port; @@ -965,7 +965,6 @@ static int cvm_oct_remove(struct platform_device *pdev) if (CVMX_FPA_OUTPUT_BUFFER_POOL != CVMX_FPA_PACKET_POOL) cvm_oct_mem_empty_fpa(CVMX_FPA_OUTPUT_BUFFER_POOL, CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE, 128); - return 0; } static const struct of_device_id cvm_oct_match[] = { @@ -978,7 +977,7 @@ MODULE_DEVICE_TABLE(of, cvm_oct_match); static struct platform_driver cvm_oct_driver = { .probe = cvm_oct_probe, - .remove = cvm_oct_remove, + .remove_new = cvm_oct_remove, .driver = { .name = KBUILD_MODNAME, .of_match_table = cvm_oct_match, -- GitLab From 360365104dca5d3f6e5f1c00dd16e7a9996406f8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:13 +0200 Subject: [PATCH 1900/5631] staging: vc04_services: bcm2835-camera: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-24-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- .../staging/vc04_services/bcm2835-camera/bcm2835-camera.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c index 4f81765912ea..346d00df815a 100644 --- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c +++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c @@ -1976,7 +1976,7 @@ static int bcm2835_mmal_probe(struct platform_device *pdev) return ret; } -static int bcm2835_mmal_remove(struct platform_device *pdev) +static void bcm2835_mmal_remove(struct platform_device *pdev) { int camera; struct vchiq_mmal_instance *instance = gdev[0]->instance; @@ -1986,13 +1986,11 @@ static int bcm2835_mmal_remove(struct platform_device *pdev) gdev[camera] = NULL; } vchiq_mmal_finalise(instance); - - return 0; } static struct platform_driver bcm2835_camera_driver = { .probe = bcm2835_mmal_probe, - .remove = bcm2835_mmal_remove, + .remove_new = bcm2835_mmal_remove, .driver = { .name = "bcm2835-camera", }, -- GitLab From e3e1e149176c7c9371b04d3b96c873cca31f520e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 3 Apr 2023 17:40:14 +0200 Subject: [PATCH 1901/5631] staging: vc04_services: vchiq_arm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230403154014.2564054-25-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- .../staging/vc04_services/interface/vchiq_arm/vchiq_arm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index cddcd3c596c9..40dd62cf7399 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -1849,14 +1849,12 @@ static int vchiq_probe(struct platform_device *pdev) return err; } -static int vchiq_remove(struct platform_device *pdev) +static void vchiq_remove(struct platform_device *pdev) { platform_device_unregister(bcm2835_audio); platform_device_unregister(bcm2835_camera); vchiq_debugfs_deinit(); vchiq_deregister_chrdev(); - - return 0; } static struct platform_driver vchiq_driver = { @@ -1865,7 +1863,7 @@ static struct platform_driver vchiq_driver = { .of_match_table = vchiq_of_match, }, .probe = vchiq_probe, - .remove = vchiq_remove, + .remove_new = vchiq_remove, }; static int __init vchiq_driver_init(void) -- GitLab From 79ef82c55a37b9c3605602c4909db84481c9fb2f Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 16:27:28 +0800 Subject: [PATCH 1902/5631] clk: imx: drop duplicated macro Drop duplicated macro definition Signed-off-by: Peng Fan Reviewed-by: Ahmad Fatoum Signed-off-by: Abel Vesa Link: https://lore.kernel.org/r/20230403082728.3199849-1-peng.fan@oss.nxp.com --- drivers/clk/imx/clk.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 621b0e84ef27..ecce45b0dd70 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -153,9 +153,6 @@ extern struct imx_fracn_gppll_clk imx_fracn_gppll; #define imx_clk_pllv2(name, parent, base) \ to_clk(imx_clk_hw_pllv2(name, parent, base)) -#define imx_clk_mux_flags(name, reg, shift, width, parents, num_parents, flags) \ - to_clk(imx_clk_hw_mux_flags(name, reg, shift, width, parents, num_parents, flags)) - #define imx_clk_hw_gate(name, parent, reg, shift) \ imx_clk_hw_gate_flags(name, parent, reg, shift, 0) -- GitLab From 643980fb08d00d7e750af03fe0101c9910ab4c1f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 1 Apr 2023 17:52:12 +0200 Subject: [PATCH 1903/5631] clk: stm32h7: Remove an unused field in struct stm32_fractional_divider 'mmask' has never been used in this driver. Remove it. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/e08a470fbd6151ebd83a548714c08807a80a8ad0.1680364296.git.christophe.jaillet@wanadoo.fr Signed-off-by: Stephen Boyd --- drivers/clk/clk-stm32h7.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/clk-stm32h7.c b/drivers/clk/clk-stm32h7.c index 1a701eada0c1..04c18a1d45d3 100644 --- a/drivers/clk/clk-stm32h7.c +++ b/drivers/clk/clk-stm32h7.c @@ -667,7 +667,6 @@ struct stm32_fractional_divider { void __iomem *mreg; u8 mshift; u8 mwidth; - u32 mmask; void __iomem *nreg; u8 nshift; -- GitLab From a9a457f338e7711af391f618b60d8a4b15ba8050 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:34 -0700 Subject: [PATCH 1904/5631] RDMA/bnxt_re: Update HW interface headers Updating the HW structures to the latest version. This is copied from the code maintained internally. No functionality changes in this patch. Code is re-organized to match the file maintained in the internal tree. Also, New HW interface structures are added, which will be used by the drivers in future. CC: Michael Chan Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-2-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 2 +- drivers/infiniband/hw/bnxt_re/roce_hsi.h | 7423 ++++++++++------- drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 81 + 3 files changed, 4429 insertions(+), 3077 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e9296bce9533..d4e616cacc4d 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -1280,7 +1280,7 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) memcpy(req.dest_mac, qp->ah.dmac, 6); if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU) - req.path_mtu = qp->path_mtu; + req.path_mtu_pingpong_push_enable |= qp->path_mtu; if (bmask & CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT) req.timeout = qp->timeout; diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h index ecb719098b75..4a10303e0392 100644 --- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h +++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h @@ -42,3169 +42,4440 @@ /* include bnxt_hsi.h from bnxt_en driver */ #include "bnxt_hsi.h" -/* CMP Door Bell Format (4 bytes) */ -struct cmpl_doorbell { - __le32 key_mask_valid_idx; - #define CMPL_DOORBELL_IDX_MASK 0xffffffUL - #define CMPL_DOORBELL_IDX_SFT 0 - #define CMPL_DOORBELL_RESERVED_MASK 0x3000000UL - #define CMPL_DOORBELL_RESERVED_SFT 24 - #define CMPL_DOORBELL_IDX_VALID 0x4000000UL - #define CMPL_DOORBELL_MASK 0x8000000UL - #define CMPL_DOORBELL_KEY_MASK 0xf0000000UL - #define CMPL_DOORBELL_KEY_SFT 28 - #define CMPL_DOORBELL_KEY_CMPL (0x2UL << 28) -}; - -/* Status Door Bell Format (4 bytes) */ -struct status_doorbell { - __le32 key_idx; - #define STATUS_DOORBELL_IDX_MASK 0xffffffUL - #define STATUS_DOORBELL_IDX_SFT 0 - #define STATUS_DOORBELL_RESERVED_MASK 0xf000000UL - #define STATUS_DOORBELL_RESERVED_SFT 24 - #define STATUS_DOORBELL_KEY_MASK 0xf0000000UL - #define STATUS_DOORBELL_KEY_SFT 28 - #define STATUS_DOORBELL_KEY_STAT (0x3UL << 28) -}; - -/* RoCE Host Structures */ - -/* Doorbell Structures */ -/* dbc_dbc (size:64b/8B) */ -struct dbc_dbc { - __le32 index; - #define DBC_DBC_INDEX_MASK 0xffffffUL - #define DBC_DBC_INDEX_SFT 0 - __le32 type_path_xid; - #define DBC_DBC_XID_MASK 0xfffffUL - #define DBC_DBC_XID_SFT 0 - #define DBC_DBC_PATH_MASK 0x3000000UL - #define DBC_DBC_PATH_SFT 24 - #define DBC_DBC_PATH_ROCE (0x0UL << 24) - #define DBC_DBC_PATH_L2 (0x1UL << 24) - #define DBC_DBC_PATH_ENGINE (0x2UL << 24) - #define DBC_DBC_PATH_LAST DBC_DBC_PATH_ENGINE - #define DBC_DBC_DEBUG_TRACE 0x8000000UL - #define DBC_DBC_TYPE_MASK 0xf0000000UL - #define DBC_DBC_TYPE_SFT 28 - #define DBC_DBC_TYPE_SQ (0x0UL << 28) - #define DBC_DBC_TYPE_RQ (0x1UL << 28) - #define DBC_DBC_TYPE_SRQ (0x2UL << 28) - #define DBC_DBC_TYPE_SRQ_ARM (0x3UL << 28) - #define DBC_DBC_TYPE_CQ (0x4UL << 28) - #define DBC_DBC_TYPE_CQ_ARMSE (0x5UL << 28) - #define DBC_DBC_TYPE_CQ_ARMALL (0x6UL << 28) - #define DBC_DBC_TYPE_CQ_ARMENA (0x7UL << 28) - #define DBC_DBC_TYPE_SRQ_ARMENA (0x8UL << 28) - #define DBC_DBC_TYPE_CQ_CUTOFF_ACK (0x9UL << 28) - #define DBC_DBC_TYPE_NQ (0xaUL << 28) - #define DBC_DBC_TYPE_NQ_ARM (0xbUL << 28) - #define DBC_DBC_TYPE_NULL (0xfUL << 28) - #define DBC_DBC_TYPE_LAST DBC_DBC_TYPE_NULL -}; - -/* dbc_dbc32 (size:32b/4B) */ -struct dbc_dbc32 { - __le32 type_abs_incr_xid; - #define DBC_DBC32_XID_MASK 0xfffffUL - #define DBC_DBC32_XID_SFT 0 - #define DBC_DBC32_PATH_MASK 0xc00000UL - #define DBC_DBC32_PATH_SFT 22 - #define DBC_DBC32_PATH_ROCE (0x0UL << 22) - #define DBC_DBC32_PATH_L2 (0x1UL << 22) - #define DBC_DBC32_PATH_LAST DBC_DBC32_PATH_L2 - #define DBC_DBC32_INCR_MASK 0xf000000UL - #define DBC_DBC32_INCR_SFT 24 - #define DBC_DBC32_ABS 0x10000000UL - #define DBC_DBC32_TYPE_MASK 0xe0000000UL - #define DBC_DBC32_TYPE_SFT 29 - #define DBC_DBC32_TYPE_SQ (0x0UL << 29) - #define DBC_DBC32_TYPE_LAST DBC_DBC32_TYPE_SQ -}; - -/* SQ WQE Structures */ -/* Base SQ WQE (8 bytes) */ -struct sq_base { - u8 wqe_type; - #define SQ_BASE_WQE_TYPE_SEND 0x0UL - #define SQ_BASE_WQE_TYPE_SEND_W_IMMEAD 0x1UL - #define SQ_BASE_WQE_TYPE_SEND_W_INVALID 0x2UL - #define SQ_BASE_WQE_TYPE_WRITE_WQE 0x4UL - #define SQ_BASE_WQE_TYPE_WRITE_W_IMMEAD 0x5UL - #define SQ_BASE_WQE_TYPE_READ_WQE 0x6UL - #define SQ_BASE_WQE_TYPE_ATOMIC_CS 0x8UL - #define SQ_BASE_WQE_TYPE_ATOMIC_FA 0xbUL - #define SQ_BASE_WQE_TYPE_LOCAL_INVALID 0xcUL - #define SQ_BASE_WQE_TYPE_FR_PMR 0xdUL - #define SQ_BASE_WQE_TYPE_BIND 0xeUL - u8 unused_0[7]; -}; - -/* WQE SGE (16 bytes) */ -struct sq_sge { - __le64 va_or_pa; - __le32 l_key; - __le32 size; +/* tx_doorbell (size:32b/4B) */ +struct tx_doorbell { + __le32 key_idx; + #define TX_DOORBELL_IDX_MASK 0xffffffUL + #define TX_DOORBELL_IDX_SFT 0 + #define TX_DOORBELL_KEY_MASK 0xf0000000UL + #define TX_DOORBELL_KEY_SFT 28 + #define TX_DOORBELL_KEY_TX (0x0UL << 28) + #define TX_DOORBELL_KEY_LAST TX_DOORBELL_KEY_TX }; -/* PSN Search Structure (8 bytes) */ -struct sq_psn_search { - __le32 opcode_start_psn; - #define SQ_PSN_SEARCH_START_PSN_MASK 0xffffffUL - #define SQ_PSN_SEARCH_START_PSN_SFT 0 - #define SQ_PSN_SEARCH_OPCODE_MASK 0xff000000UL - #define SQ_PSN_SEARCH_OPCODE_SFT 24 - __le32 flags_next_psn; - #define SQ_PSN_SEARCH_NEXT_PSN_MASK 0xffffffUL - #define SQ_PSN_SEARCH_NEXT_PSN_SFT 0 - #define SQ_PSN_SEARCH_FLAGS_MASK 0xff000000UL - #define SQ_PSN_SEARCH_FLAGS_SFT 24 +/* rx_doorbell (size:32b/4B) */ +struct rx_doorbell { + __le32 key_idx; + #define RX_DOORBELL_IDX_MASK 0xffffffUL + #define RX_DOORBELL_IDX_SFT 0 + #define RX_DOORBELL_KEY_MASK 0xf0000000UL + #define RX_DOORBELL_KEY_SFT 28 + #define RX_DOORBELL_KEY_RX (0x1UL << 28) + #define RX_DOORBELL_KEY_LAST RX_DOORBELL_KEY_RX }; -/* sq_psn_search_ext (size:128b/16B) */ -struct sq_psn_search_ext { - __le32 opcode_start_psn; - #define SQ_PSN_SEARCH_EXT_START_PSN_MASK 0xffffffUL - #define SQ_PSN_SEARCH_EXT_START_PSN_SFT 0 - #define SQ_PSN_SEARCH_EXT_OPCODE_MASK 0xff000000UL - #define SQ_PSN_SEARCH_EXT_OPCODE_SFT 24 - __le32 flags_next_psn; - #define SQ_PSN_SEARCH_EXT_NEXT_PSN_MASK 0xffffffUL - #define SQ_PSN_SEARCH_EXT_NEXT_PSN_SFT 0 - #define SQ_PSN_SEARCH_EXT_FLAGS_MASK 0xff000000UL - #define SQ_PSN_SEARCH_EXT_FLAGS_SFT 24 - __le16 start_slot_idx; - __le16 reserved16; - __le32 reserved32; -}; - -/* Send SQ WQE (40 bytes) */ -struct sq_send { - u8 wqe_type; - #define SQ_SEND_WQE_TYPE_SEND 0x0UL - #define SQ_SEND_WQE_TYPE_SEND_W_IMMEAD 0x1UL - #define SQ_SEND_WQE_TYPE_SEND_W_INVALID 0x2UL - u8 flags; - #define SQ_SEND_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_SEND_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_SEND_FLAGS_UC_FENCE 0x4UL - #define SQ_SEND_FLAGS_SE 0x8UL - #define SQ_SEND_FLAGS_INLINE 0x10UL - u8 wqe_size; - u8 reserved8_1; - __le32 inv_key_or_imm_data; - __le32 length; - __le32 q_key; - __le32 dst_qp; - #define SQ_SEND_DST_QP_MASK 0xffffffUL - #define SQ_SEND_DST_QP_SFT 0 - #define SQ_SEND_RESERVED8_2_MASK 0xff000000UL - #define SQ_SEND_RESERVED8_2_SFT 24 - __le32 avid; - #define SQ_SEND_AVID_MASK 0xfffffUL - #define SQ_SEND_AVID_SFT 0 - #define SQ_SEND_RESERVED_AVID_MASK 0xfff00000UL - #define SQ_SEND_RESERVED_AVID_SFT 20 - __le64 reserved64; - __le32 data[24]; +/* cmpl_doorbell (size:32b/4B) */ +struct cmpl_doorbell { + __le32 key_mask_valid_idx; + #define CMPL_DOORBELL_IDX_MASK 0xffffffUL + #define CMPL_DOORBELL_IDX_SFT 0 + #define CMPL_DOORBELL_IDX_VALID 0x4000000UL + #define CMPL_DOORBELL_MASK 0x8000000UL + #define CMPL_DOORBELL_KEY_MASK 0xf0000000UL + #define CMPL_DOORBELL_KEY_SFT 28 + #define CMPL_DOORBELL_KEY_CMPL (0x2UL << 28) + #define CMPL_DOORBELL_KEY_LAST CMPL_DOORBELL_KEY_CMPL }; -/* sq_send_hdr (size:256b/32B) */ -struct sq_send_hdr { - u8 wqe_type; - u8 flags; - u8 wqe_size; - u8 reserved8_1; - __le32 inv_key_or_imm_data; - __le32 length; - __le32 q_key; - __le32 dst_qp; - __le32 avid; - __le64 reserved64; +/* status_doorbell (size:32b/4B) */ +struct status_doorbell { + __le32 key_idx; + #define STATUS_DOORBELL_IDX_MASK 0xffffffUL + #define STATUS_DOORBELL_IDX_SFT 0 + #define STATUS_DOORBELL_KEY_MASK 0xf0000000UL + #define STATUS_DOORBELL_KEY_SFT 28 + #define STATUS_DOORBELL_KEY_STAT (0x3UL << 28) + #define STATUS_DOORBELL_KEY_LAST STATUS_DOORBELL_KEY_STAT }; -/* Send Raw Ethernet and QP1 SQ WQE (40 bytes) */ -struct sq_send_raweth_qp1 { - u8 wqe_type; - #define SQ_SEND_RAWETH_QP1_WQE_TYPE_SEND 0x0UL - u8 flags; - #define SQ_SEND_RAWETH_QP1_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_SEND_RAWETH_QP1_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_SEND_RAWETH_QP1_FLAGS_UC_FENCE 0x4UL - #define SQ_SEND_RAWETH_QP1_FLAGS_SE 0x8UL - #define SQ_SEND_RAWETH_QP1_FLAGS_INLINE 0x10UL - u8 wqe_size; - u8 reserved8; - __le16 lflags; - #define SQ_SEND_RAWETH_QP1_LFLAGS_TCP_UDP_CHKSUM 0x1UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM 0x2UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_NOCRC 0x4UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_STAMP 0x8UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_T_IP_CHKSUM 0x10UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_1 0x20UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_2 0x40UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_RESERVED1_3 0x80UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC 0x100UL - #define SQ_SEND_RAWETH_QP1_LFLAGS_FCOE_CRC 0x200UL - __le16 cfa_action; - __le32 length; - __le32 reserved32_1; - __le32 cfa_meta; - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_MASK 0xfffUL - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_SFT 0 - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_DE 0x1000UL - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_MASK 0xe000UL - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_SFT 13 - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_MASK 0x70000UL - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_SFT 16 - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID88A8 (0x0UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID8100 (0x1UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9100 (0x2UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9200 (0x3UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9300 (0x4UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG (0x5UL << 16) - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_LAST \ - SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_MASK 0xff80000UL - #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_SFT 19 - #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_MASK 0xf0000000UL - #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_SFT 28 - #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_NONE (0x0UL << 28) - #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG (0x1UL << 28) - #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_LAST \ - SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG - __le32 reserved32_2; - __le64 reserved64; - __le32 data[24]; +/* cmdq_init (size:128b/16B) */ +struct cmdq_init { + __le64 cmdq_pbl; + __le16 cmdq_size_cmdq_lvl; + #define CMDQ_INIT_CMDQ_LVL_MASK 0x3UL + #define CMDQ_INIT_CMDQ_LVL_SFT 0 + #define CMDQ_INIT_CMDQ_SIZE_MASK 0xfffcUL + #define CMDQ_INIT_CMDQ_SIZE_SFT 2 + __le16 creq_ring_id; + __le32 prod_idx; }; -/* sq_send_raweth_qp1_hdr (size:256b/32B) */ -struct sq_send_raweth_qp1_hdr { - u8 wqe_type; - u8 flags; - u8 wqe_size; +/* cmdq_base (size:128b/16B) */ +struct cmdq_base { + u8 opcode; + #define CMDQ_BASE_OPCODE_CREATE_QP 0x1UL + #define CMDQ_BASE_OPCODE_DESTROY_QP 0x2UL + #define CMDQ_BASE_OPCODE_MODIFY_QP 0x3UL + #define CMDQ_BASE_OPCODE_QUERY_QP 0x4UL + #define CMDQ_BASE_OPCODE_CREATE_SRQ 0x5UL + #define CMDQ_BASE_OPCODE_DESTROY_SRQ 0x6UL + #define CMDQ_BASE_OPCODE_QUERY_SRQ 0x8UL + #define CMDQ_BASE_OPCODE_CREATE_CQ 0x9UL + #define CMDQ_BASE_OPCODE_DESTROY_CQ 0xaUL + #define CMDQ_BASE_OPCODE_RESIZE_CQ 0xcUL + #define CMDQ_BASE_OPCODE_ALLOCATE_MRW 0xdUL + #define CMDQ_BASE_OPCODE_DEALLOCATE_KEY 0xeUL + #define CMDQ_BASE_OPCODE_REGISTER_MR 0xfUL + #define CMDQ_BASE_OPCODE_DEREGISTER_MR 0x10UL + #define CMDQ_BASE_OPCODE_ADD_GID 0x11UL + #define CMDQ_BASE_OPCODE_DELETE_GID 0x12UL + #define CMDQ_BASE_OPCODE_MODIFY_GID 0x17UL + #define CMDQ_BASE_OPCODE_QUERY_GID 0x18UL + #define CMDQ_BASE_OPCODE_CREATE_QP1 0x13UL + #define CMDQ_BASE_OPCODE_DESTROY_QP1 0x14UL + #define CMDQ_BASE_OPCODE_CREATE_AH 0x15UL + #define CMDQ_BASE_OPCODE_DESTROY_AH 0x16UL + #define CMDQ_BASE_OPCODE_INITIALIZE_FW 0x80UL + #define CMDQ_BASE_OPCODE_DEINITIALIZE_FW 0x81UL + #define CMDQ_BASE_OPCODE_STOP_FUNC 0x82UL + #define CMDQ_BASE_OPCODE_QUERY_FUNC 0x83UL + #define CMDQ_BASE_OPCODE_SET_FUNC_RESOURCES 0x84UL + #define CMDQ_BASE_OPCODE_READ_CONTEXT 0x85UL + #define CMDQ_BASE_OPCODE_VF_BACKCHANNEL_REQUEST 0x86UL + #define CMDQ_BASE_OPCODE_READ_VF_MEMORY 0x87UL + #define CMDQ_BASE_OPCODE_COMPLETE_VF_REQUEST 0x88UL + #define CMDQ_BASE_OPCODE_EXTEND_CONTEXT_ARRRAY 0x89UL + #define CMDQ_BASE_OPCODE_MAP_TC_TO_COS 0x8aUL + #define CMDQ_BASE_OPCODE_QUERY_VERSION 0x8bUL + #define CMDQ_BASE_OPCODE_MODIFY_ROCE_CC 0x8cUL + #define CMDQ_BASE_OPCODE_QUERY_ROCE_CC 0x8dUL + #define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS 0x8eUL + #define CMDQ_BASE_OPCODE_SET_LINK_AGGR_MODE 0x8fUL + #define CMDQ_BASE_OPCODE_MODIFY_CQ 0x90UL + #define CMDQ_BASE_OPCODE_QUERY_QP_EXTEND 0x91UL + #define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS_EXT 0x92UL + #define CMDQ_BASE_OPCODE_LAST CMDQ_BASE_OPCODE_QUERY_ROCE_STATS_EXT + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; u8 reserved8; - __le16 lflags; - __le16 cfa_action; - __le32 length; - __le32 reserved32_1; - __le32 cfa_meta; - __le32 reserved32_2; - __le64 reserved64; + __le64 resp_addr; }; -/* RDMA SQ WQE (40 bytes) */ -struct sq_rdma { - u8 wqe_type; - #define SQ_RDMA_WQE_TYPE_WRITE_WQE 0x4UL - #define SQ_RDMA_WQE_TYPE_WRITE_W_IMMEAD 0x5UL - #define SQ_RDMA_WQE_TYPE_READ_WQE 0x6UL - u8 flags; - #define SQ_RDMA_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_RDMA_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_RDMA_FLAGS_UC_FENCE 0x4UL - #define SQ_RDMA_FLAGS_SE 0x8UL - #define SQ_RDMA_FLAGS_INLINE 0x10UL - u8 wqe_size; - u8 reserved8; - __le32 imm_data; - __le32 length; - __le32 reserved32_1; - __le64 remote_va; - __le32 remote_key; - __le32 reserved32_2; - __le32 data[24]; +/* creq_base (size:128b/16B) */ +struct creq_base { + u8 type; + #define CREQ_BASE_TYPE_MASK 0x3fUL + #define CREQ_BASE_TYPE_SFT 0 + #define CREQ_BASE_TYPE_QP_EVENT 0x38UL + #define CREQ_BASE_TYPE_FUNC_EVENT 0x3aUL + #define CREQ_BASE_TYPE_LAST CREQ_BASE_TYPE_FUNC_EVENT + u8 reserved56[7]; + u8 v; + #define CREQ_BASE_V 0x1UL + u8 event; + u8 reserved48[6]; }; -/* sq_rdma_hdr (size:256b/32B) */ -struct sq_rdma_hdr { - u8 wqe_type; - u8 flags; - u8 wqe_size; +/* cmdq_query_version (size:128b/16B) */ +struct cmdq_query_version { + u8 opcode; + #define CMDQ_QUERY_VERSION_OPCODE_QUERY_VERSION 0x8bUL + #define CMDQ_QUERY_VERSION_OPCODE_LAST CMDQ_QUERY_VERSION_OPCODE_QUERY_VERSION + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; u8 reserved8; - __le32 imm_data; - __le32 length; - __le32 reserved32_1; - __le64 remote_va; - __le32 remote_key; - __le32 reserved32_2; -}; - -/* Atomic SQ WQE (40 bytes) */ -struct sq_atomic { - u8 wqe_type; - #define SQ_ATOMIC_WQE_TYPE_ATOMIC_CS 0x8UL - #define SQ_ATOMIC_WQE_TYPE_ATOMIC_FA 0xbUL - u8 flags; - #define SQ_ATOMIC_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_ATOMIC_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_ATOMIC_FLAGS_UC_FENCE 0x4UL - #define SQ_ATOMIC_FLAGS_SE 0x8UL - #define SQ_ATOMIC_FLAGS_INLINE 0x10UL - __le16 reserved16; - __le32 remote_key; - __le64 remote_va; - __le64 swap_data; - __le64 cmp_data; - __le32 data[24]; + __le64 resp_addr; }; -/* sq_atomic_hdr (size:256b/32B) */ -struct sq_atomic_hdr { - u8 wqe_type; - u8 flags; +/* creq_query_version_resp (size:128b/16B) */ +struct creq_query_version_resp { + u8 type; + #define CREQ_QUERY_VERSION_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_VERSION_RESP_TYPE_SFT 0 + #define CREQ_QUERY_VERSION_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_VERSION_RESP_TYPE_LAST CREQ_QUERY_VERSION_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + u8 fw_maj; + u8 fw_minor; + u8 fw_bld; + u8 fw_rsvd; + u8 v; + #define CREQ_QUERY_VERSION_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_VERSION_RESP_EVENT_QUERY_VERSION 0x8bUL + #define CREQ_QUERY_VERSION_RESP_EVENT_LAST \ + CREQ_QUERY_VERSION_RESP_EVENT_QUERY_VERSION __le16 reserved16; - __le32 remote_key; - __le64 remote_va; - __le64 swap_data; - __le64 cmp_data; + u8 intf_maj; + u8 intf_minor; + u8 intf_bld; + u8 intf_rsvd; }; -/* Local Invalidate SQ WQE (40 bytes) */ -struct sq_localinvalidate { - u8 wqe_type; - #define SQ_LOCALINVALIDATE_WQE_TYPE_LOCAL_INVALID 0xcUL - u8 flags; - #define SQ_LOCALINVALIDATE_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_LOCALINVALIDATE_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_LOCALINVALIDATE_FLAGS_UC_FENCE 0x4UL - #define SQ_LOCALINVALIDATE_FLAGS_SE 0x8UL - #define SQ_LOCALINVALIDATE_FLAGS_INLINE 0x10UL - __le16 reserved16; - __le32 inv_l_key; - __le64 reserved64; - __le32 reserved128[4]; - __le32 data[24]; -}; - -/* sq_localinvalidate_hdr (size:256b/32B) */ -struct sq_localinvalidate_hdr { - u8 wqe_type; - u8 flags; - __le16 reserved16; - __le32 inv_l_key; - __le64 reserved64; - u8 reserved128[16]; +/* cmdq_initialize_fw (size:896b/112B) */ +struct cmdq_initialize_fw { + u8 opcode; + #define CMDQ_INITIALIZE_FW_OPCODE_INITIALIZE_FW 0x80UL + #define CMDQ_INITIALIZE_FW_OPCODE_LAST CMDQ_INITIALIZE_FW_OPCODE_INITIALIZE_FW + u8 cmd_size; + __le16 flags; + #define CMDQ_INITIALIZE_FW_FLAGS_MRAV_RESERVATION_SPLIT 0x1UL + #define CMDQ_INITIALIZE_FW_FLAGS_HW_REQUESTER_RETX_SUPPORTED 0x2UL + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + u8 qpc_pg_size_qpc_lvl; + #define CMDQ_INITIALIZE_FW_QPC_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_QPC_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_QPC_LVL_LAST CMDQ_INITIALIZE_FW_QPC_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_LAST CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_1G + u8 mrw_pg_size_mrw_lvl; + #define CMDQ_INITIALIZE_FW_MRW_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_MRW_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_MRW_LVL_LAST CMDQ_INITIALIZE_FW_MRW_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_LAST CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_1G + u8 srq_pg_size_srq_lvl; + #define CMDQ_INITIALIZE_FW_SRQ_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_SRQ_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_SRQ_LVL_LAST CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_LAST CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_1G + u8 cq_pg_size_cq_lvl; + #define CMDQ_INITIALIZE_FW_CQ_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_CQ_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_CQ_LVL_LAST CMDQ_INITIALIZE_FW_CQ_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_LAST CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_1G + u8 tqm_pg_size_tqm_lvl; + #define CMDQ_INITIALIZE_FW_TQM_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_TQM_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_TQM_LVL_LAST CMDQ_INITIALIZE_FW_TQM_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_LAST CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_1G + u8 tim_pg_size_tim_lvl; + #define CMDQ_INITIALIZE_FW_TIM_LVL_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_TIM_LVL_SFT 0 + #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_0 0x0UL + #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_1 0x1UL + #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_2 0x2UL + #define CMDQ_INITIALIZE_FW_TIM_LVL_LAST CMDQ_INITIALIZE_FW_TIM_LVL_LVL_2 + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_MASK 0xf0UL + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_SFT 4 + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_LAST CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G + __le16 log2_dbr_pg_size; + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT 0 + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K 0x0UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K 0x1UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K 0x2UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K 0x3UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K 0x4UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K 0x5UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K 0x6UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K 0x7UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M 0x8UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M 0x9UL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M 0xaUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M 0xbUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M 0xcUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M 0xdUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M 0xeUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M 0xfUL + #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST \ + CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M + #define CMDQ_INITIALIZE_FW_RSVD_MASK 0xfff0UL + #define CMDQ_INITIALIZE_FW_RSVD_SFT 4 + __le64 qpc_page_dir; + __le64 mrw_page_dir; + __le64 srq_page_dir; + __le64 cq_page_dir; + __le64 tqm_page_dir; + __le64 tim_page_dir; + __le32 number_of_qp; + __le32 number_of_mrw; + __le32 number_of_srq; + __le32 number_of_cq; + __le32 max_qp_per_vf; + __le32 max_mrw_per_vf; + __le32 max_srq_per_vf; + __le32 max_cq_per_vf; + __le32 max_gid_per_vf; + __le32 stat_ctx_id; }; -/* FR-PMR SQ WQE (40 bytes) */ -struct sq_fr_pmr { - u8 wqe_type; - #define SQ_FR_PMR_WQE_TYPE_FR_PMR 0xdUL - u8 flags; - #define SQ_FR_PMR_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_FR_PMR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_FR_PMR_FLAGS_UC_FENCE 0x4UL - #define SQ_FR_PMR_FLAGS_SE 0x8UL - #define SQ_FR_PMR_FLAGS_INLINE 0x10UL - u8 access_cntl; - #define SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE 0x1UL - #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_READ 0x2UL - #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_WRITE 0x4UL - #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL - #define SQ_FR_PMR_ACCESS_CNTL_WINDOW_BIND 0x10UL - u8 zero_based_page_size_log; - #define SQ_FR_PMR_PAGE_SIZE_LOG_MASK 0x1fUL - #define SQ_FR_PMR_PAGE_SIZE_LOG_SFT 0 - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4K 0x0UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8K 0x1UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_64K 0x4UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_256K 0x6UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1M 0x8UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_2M 0x9UL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4M 0xaUL - #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1G 0x12UL - #define SQ_FR_PMR_ZERO_BASED 0x20UL - #define SQ_FR_PMR_RESERVED2_MASK 0xc0UL - #define SQ_FR_PMR_RESERVED2_SFT 6 - __le32 l_key; - u8 length[5]; - u8 reserved8_1; - u8 reserved8_2; - u8 numlevels_pbl_page_size_log; - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_MASK 0x1fUL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_SFT 0 - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4K 0x0UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8K 0x1UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_64K 0x4UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_256K 0x6UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1M 0x8UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_2M 0x9UL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4M 0xaUL - #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1G 0x12UL - #define SQ_FR_PMR_RESERVED1 0x20UL - #define SQ_FR_PMR_NUMLEVELS_MASK 0xc0UL - #define SQ_FR_PMR_NUMLEVELS_SFT 6 - #define SQ_FR_PMR_NUMLEVELS_PHYSICAL (0x0UL << 6) - #define SQ_FR_PMR_NUMLEVELS_LAYER1 (0x1UL << 6) - #define SQ_FR_PMR_NUMLEVELS_LAYER2 (0x2UL << 6) - __le64 pblptr; - __le64 va; - __le32 data[24]; +/* creq_initialize_fw_resp (size:128b/16B) */ +struct creq_initialize_fw_resp { + u8 type; + #define CREQ_INITIALIZE_FW_RESP_TYPE_MASK 0x3fUL + #define CREQ_INITIALIZE_FW_RESP_TYPE_SFT 0 + #define CREQ_INITIALIZE_FW_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_INITIALIZE_FW_RESP_TYPE_LAST CREQ_INITIALIZE_FW_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_INITIALIZE_FW_RESP_V 0x1UL + u8 event; + #define CREQ_INITIALIZE_FW_RESP_EVENT_INITIALIZE_FW 0x80UL + #define CREQ_INITIALIZE_FW_RESP_EVENT_LAST \ + CREQ_INITIALIZE_FW_RESP_EVENT_INITIALIZE_FW + u8 reserved48[6]; }; -/* sq_fr_pmr_hdr (size:256b/32B) */ -struct sq_fr_pmr_hdr { - u8 wqe_type; - u8 flags; - u8 access_cntl; - u8 zero_based_page_size_log; - __le32 l_key; - u8 length[5]; - u8 reserved8_1; - u8 reserved8_2; - u8 numlevels_pbl_page_size_log; - __le64 pblptr; - __le64 va; +/* cmdq_deinitialize_fw (size:128b/16B) */ +struct cmdq_deinitialize_fw { + u8 opcode; + #define CMDQ_DEINITIALIZE_FW_OPCODE_DEINITIALIZE_FW 0x81UL + #define CMDQ_DEINITIALIZE_FW_OPCODE_LAST \ + CMDQ_DEINITIALIZE_FW_OPCODE_DEINITIALIZE_FW + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; }; -/* Bind SQ WQE (40 bytes) */ -struct sq_bind { - u8 wqe_type; - #define SQ_BIND_WQE_TYPE_BIND 0xeUL - u8 flags; - #define SQ_BIND_FLAGS_SIGNAL_COMP 0x1UL - #define SQ_BIND_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL - #define SQ_BIND_FLAGS_UC_FENCE 0x4UL - #define SQ_BIND_FLAGS_SE 0x8UL - #define SQ_BIND_FLAGS_INLINE 0x10UL - u8 access_cntl; - #define SQ_BIND_ACCESS_CNTL_LOCAL_WRITE 0x1UL - #define SQ_BIND_ACCESS_CNTL_REMOTE_READ 0x2UL - #define SQ_BIND_ACCESS_CNTL_REMOTE_WRITE 0x4UL - #define SQ_BIND_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL - #define SQ_BIND_ACCESS_CNTL_WINDOW_BIND 0x10UL - u8 reserved8_1; - u8 mw_type_zero_based; - #define SQ_BIND_ZERO_BASED 0x1UL - #define SQ_BIND_MW_TYPE 0x2UL - #define SQ_BIND_MW_TYPE_TYPE1 (0x0UL << 1) - #define SQ_BIND_MW_TYPE_TYPE2 (0x1UL << 1) - #define SQ_BIND_RESERVED6_MASK 0xfcUL - #define SQ_BIND_RESERVED6_SFT 2 - u8 reserved8_2; - __le16 reserved16; - __le32 parent_l_key; - __le32 l_key; - __le64 va; - u8 length[5]; - u8 data_reserved24[99]; - #define SQ_BIND_RESERVED24_MASK 0xffffff00UL - #define SQ_BIND_RESERVED24_SFT 8 - #define SQ_BIND_DATA_MASK 0xffffffffUL - #define SQ_BIND_DATA_SFT 0 +/* creq_deinitialize_fw_resp (size:128b/16B) */ +struct creq_deinitialize_fw_resp { + u8 type; + #define CREQ_DEINITIALIZE_FW_RESP_TYPE_MASK 0x3fUL + #define CREQ_DEINITIALIZE_FW_RESP_TYPE_SFT 0 + #define CREQ_DEINITIALIZE_FW_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DEINITIALIZE_FW_RESP_TYPE_LAST CREQ_DEINITIALIZE_FW_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_DEINITIALIZE_FW_RESP_V 0x1UL + u8 event; + #define CREQ_DEINITIALIZE_FW_RESP_EVENT_DEINITIALIZE_FW 0x81UL + #define CREQ_DEINITIALIZE_FW_RESP_EVENT_LAST \ + CREQ_DEINITIALIZE_FW_RESP_EVENT_DEINITIALIZE_FW + u8 reserved48[6]; }; -/* sq_bind_hdr (size:256b/32B) */ -struct sq_bind_hdr { - u8 wqe_type; - u8 flags; - u8 access_cntl; - u8 reserved8_1; - u8 mw_type_zero_based; - u8 reserved8_2; - __le16 reserved16; - __le32 parent_l_key; - __le32 l_key; - __le64 va; - u8 length[5]; - u8 reserved24[3]; +/* cmdq_create_qp (size:768b/96B) */ +struct cmdq_create_qp { + u8 opcode; + #define CMDQ_CREATE_QP_OPCODE_CREATE_QP 0x1UL + #define CMDQ_CREATE_QP_OPCODE_LAST CMDQ_CREATE_QP_OPCODE_CREATE_QP + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le64 qp_handle; + __le32 qp_flags; + #define CMDQ_CREATE_QP_QP_FLAGS_SRQ_USED 0x1UL + #define CMDQ_CREATE_QP_QP_FLAGS_FORCE_COMPLETION 0x2UL + #define CMDQ_CREATE_QP_QP_FLAGS_RESERVED_LKEY_ENABLE 0x4UL + #define CMDQ_CREATE_QP_QP_FLAGS_FR_PMR_ENABLED 0x8UL + #define CMDQ_CREATE_QP_QP_FLAGS_VARIABLE_SIZED_WQE_ENABLED 0x10UL + #define CMDQ_CREATE_QP_QP_FLAGS_OPTIMIZED_TRANSMIT_ENABLED 0x20UL + #define CMDQ_CREATE_QP_QP_FLAGS_RESPONDER_UD_CQE_WITH_CFA 0x40UL + #define CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED 0x80UL + #define CMDQ_CREATE_QP_QP_FLAGS_LAST \ + CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED + u8 type; + #define CMDQ_CREATE_QP_TYPE_RC 0x2UL + #define CMDQ_CREATE_QP_TYPE_UD 0x4UL + #define CMDQ_CREATE_QP_TYPE_RAW_ETHERTYPE 0x6UL + #define CMDQ_CREATE_QP_TYPE_GSI 0x7UL + #define CMDQ_CREATE_QP_TYPE_LAST CMDQ_CREATE_QP_TYPE_GSI + u8 sq_pg_size_sq_lvl; + #define CMDQ_CREATE_QP_SQ_LVL_MASK 0xfUL + #define CMDQ_CREATE_QP_SQ_LVL_SFT 0 + #define CMDQ_CREATE_QP_SQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_QP_SQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_QP_SQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_QP_SQ_LVL_LAST CMDQ_CREATE_QP_SQ_LVL_LVL_2 + #define CMDQ_CREATE_QP_SQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_CREATE_QP_SQ_PG_SIZE_SFT 4 + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_CREATE_QP_SQ_PG_SIZE_LAST CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G + u8 rq_pg_size_rq_lvl; + #define CMDQ_CREATE_QP_RQ_LVL_MASK 0xfUL + #define CMDQ_CREATE_QP_RQ_LVL_SFT 0 + #define CMDQ_CREATE_QP_RQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_QP_RQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_QP_RQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_QP_RQ_LVL_LAST CMDQ_CREATE_QP_RQ_LVL_LVL_2 + #define CMDQ_CREATE_QP_RQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_CREATE_QP_RQ_PG_SIZE_SFT 4 + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_CREATE_QP_RQ_PG_SIZE_LAST CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G + u8 unused_0; + __le32 dpi; + __le32 sq_size; + __le32 rq_size; + __le16 sq_fwo_sq_sge; + #define CMDQ_CREATE_QP_SQ_SGE_MASK 0xfUL + #define CMDQ_CREATE_QP_SQ_SGE_SFT 0 + #define CMDQ_CREATE_QP_SQ_FWO_MASK 0xfff0UL + #define CMDQ_CREATE_QP_SQ_FWO_SFT 4 + __le16 rq_fwo_rq_sge; + #define CMDQ_CREATE_QP_RQ_SGE_MASK 0xfUL + #define CMDQ_CREATE_QP_RQ_SGE_SFT 0 + #define CMDQ_CREATE_QP_RQ_FWO_MASK 0xfff0UL + #define CMDQ_CREATE_QP_RQ_FWO_SFT 4 + __le32 scq_cid; + __le32 rcq_cid; + __le32 srq_cid; + __le32 pd_id; + __le64 sq_pbl; + __le64 rq_pbl; + __le64 irrq_addr; + __le64 orrq_addr; }; -/* RQ/SRQ WQE Structures */ -/* RQ/SRQ WQE (40 bytes) */ -struct rq_wqe { - u8 wqe_type; - #define RQ_WQE_WQE_TYPE_RCV 0x80UL - u8 flags; - u8 wqe_size; - u8 reserved8; - __le32 reserved32; - __le32 wr_id[2]; - #define RQ_WQE_WR_ID_MASK 0xfffffUL - #define RQ_WQE_WR_ID_SFT 0 - #define RQ_WQE_RESERVED44_MASK 0xfff00000UL - #define RQ_WQE_RESERVED44_SFT 20 - __le32 reserved128[4]; - __le32 data[24]; +/* creq_create_qp_resp (size:128b/16B) */ +struct creq_create_qp_resp { + u8 type; + #define CREQ_CREATE_QP_RESP_TYPE_MASK 0x3fUL + #define CREQ_CREATE_QP_RESP_TYPE_SFT 0 + #define CREQ_CREATE_QP_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_CREATE_QP_RESP_TYPE_LAST CREQ_CREATE_QP_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_CREATE_QP_RESP_V 0x1UL + u8 event; + #define CREQ_CREATE_QP_RESP_EVENT_CREATE_QP 0x1UL + #define CREQ_CREATE_QP_RESP_EVENT_LAST CREQ_CREATE_QP_RESP_EVENT_CREATE_QP + u8 optimized_transmit_enabled; + u8 reserved48[5]; }; -/* rq_wqe_hdr (size:256b/32B) */ -struct rq_wqe_hdr { - u8 wqe_type; - u8 flags; - u8 wqe_size; +/* cmdq_destroy_qp (size:192b/24B) */ +struct cmdq_destroy_qp { + u8 opcode; + #define CMDQ_DESTROY_QP_OPCODE_DESTROY_QP 0x2UL + #define CMDQ_DESTROY_QP_OPCODE_LAST CMDQ_DESTROY_QP_OPCODE_DESTROY_QP + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; u8 reserved8; - __le32 reserved32; - __le32 wr_id[2]; - u8 reserved128[16]; + __le64 resp_addr; + __le32 qp_cid; + __le32 unused_0; }; -/* CQ CQE Structures */ -/* Base CQE (32 bytes) */ -struct cq_base { - __le64 reserved64_1; - __le64 reserved64_2; - __le64 reserved64_3; - u8 cqe_type_toggle; - #define CQ_BASE_TOGGLE 0x1UL - #define CQ_BASE_CQE_TYPE_MASK 0x1eUL - #define CQ_BASE_CQE_TYPE_SFT 1 - #define CQ_BASE_CQE_TYPE_REQ (0x0UL << 1) - #define CQ_BASE_CQE_TYPE_RES_RC (0x1UL << 1) - #define CQ_BASE_CQE_TYPE_RES_UD (0x2UL << 1) - #define CQ_BASE_CQE_TYPE_RES_RAWETH_QP1 (0x3UL << 1) - #define CQ_BASE_CQE_TYPE_TERMINAL (0xeUL << 1) - #define CQ_BASE_CQE_TYPE_CUT_OFF (0xfUL << 1) - #define CQ_BASE_RESERVED3_MASK 0xe0UL - #define CQ_BASE_RESERVED3_SFT 5 - u8 status; - __le16 reserved16; - __le32 reserved32; -}; - -/* Requester CQ CQE (32 bytes) */ -struct cq_req { - __le64 qp_handle; - __le16 sq_cons_idx; - __le16 reserved16_1; - __le32 reserved32_2; - __le64 reserved64; - u8 cqe_type_toggle; - #define CQ_REQ_TOGGLE 0x1UL - #define CQ_REQ_CQE_TYPE_MASK 0x1eUL - #define CQ_REQ_CQE_TYPE_SFT 1 - #define CQ_REQ_CQE_TYPE_REQ (0x0UL << 1) - #define CQ_REQ_RESERVED3_MASK 0xe0UL - #define CQ_REQ_RESERVED3_SFT 5 - u8 status; - #define CQ_REQ_STATUS_OK 0x0UL - #define CQ_REQ_STATUS_BAD_RESPONSE_ERR 0x1UL - #define CQ_REQ_STATUS_LOCAL_LENGTH_ERR 0x2UL - #define CQ_REQ_STATUS_LOCAL_QP_OPERATION_ERR 0x3UL - #define CQ_REQ_STATUS_LOCAL_PROTECTION_ERR 0x4UL - #define CQ_REQ_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL - #define CQ_REQ_STATUS_REMOTE_INVALID_REQUEST_ERR 0x6UL - #define CQ_REQ_STATUS_REMOTE_ACCESS_ERR 0x7UL - #define CQ_REQ_STATUS_REMOTE_OPERATION_ERR 0x8UL - #define CQ_REQ_STATUS_RNR_NAK_RETRY_CNT_ERR 0x9UL - #define CQ_REQ_STATUS_TRANSPORT_RETRY_CNT_ERR 0xaUL - #define CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR 0xbUL - __le16 reserved16_2; - __le32 reserved32_1; -}; - -/* Responder RC CQE (32 bytes) */ -struct cq_res_rc { - __le32 length; - __le32 imm_data_or_inv_r_key; - __le64 qp_handle; - __le64 mr_handle; - u8 cqe_type_toggle; - #define CQ_RES_RC_TOGGLE 0x1UL - #define CQ_RES_RC_CQE_TYPE_MASK 0x1eUL - #define CQ_RES_RC_CQE_TYPE_SFT 1 - #define CQ_RES_RC_CQE_TYPE_RES_RC (0x1UL << 1) - #define CQ_RES_RC_RESERVED3_MASK 0xe0UL - #define CQ_RES_RC_RESERVED3_SFT 5 - u8 status; - #define CQ_RES_RC_STATUS_OK 0x0UL - #define CQ_RES_RC_STATUS_LOCAL_ACCESS_ERROR 0x1UL - #define CQ_RES_RC_STATUS_LOCAL_LENGTH_ERR 0x2UL - #define CQ_RES_RC_STATUS_LOCAL_PROTECTION_ERR 0x3UL - #define CQ_RES_RC_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL - #define CQ_RES_RC_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL - #define CQ_RES_RC_STATUS_REMOTE_INVALID_REQUEST_ERR 0x6UL - #define CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL - #define CQ_RES_RC_STATUS_HW_FLUSH_ERR 0x8UL - __le16 flags; - #define CQ_RES_RC_FLAGS_SRQ 0x1UL - #define CQ_RES_RC_FLAGS_SRQ_RQ (0x0UL << 0) - #define CQ_RES_RC_FLAGS_SRQ_SRQ (0x1UL << 0) - #define CQ_RES_RC_FLAGS_SRQ_LAST CQ_RES_RC_FLAGS_SRQ_SRQ - #define CQ_RES_RC_FLAGS_IMM 0x2UL - #define CQ_RES_RC_FLAGS_INV 0x4UL - #define CQ_RES_RC_FLAGS_RDMA 0x8UL - #define CQ_RES_RC_FLAGS_RDMA_SEND (0x0UL << 3) - #define CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE (0x1UL << 3) - #define CQ_RES_RC_FLAGS_RDMA_LAST CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE - __le32 srq_or_rq_wr_id; - #define CQ_RES_RC_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL - #define CQ_RES_RC_SRQ_OR_RQ_WR_ID_SFT 0 - #define CQ_RES_RC_RESERVED12_MASK 0xfff00000UL - #define CQ_RES_RC_RESERVED12_SFT 20 -}; - -/* Responder UD CQE (32 bytes) */ -struct cq_res_ud { - __le16 length; - #define CQ_RES_UD_LENGTH_MASK 0x3fffUL - #define CQ_RES_UD_LENGTH_SFT 0 - __le16 cfa_metadata; - #define CQ_RES_UD_CFA_METADATA_VID_MASK 0xfffUL - #define CQ_RES_UD_CFA_METADATA_VID_SFT 0 - #define CQ_RES_UD_CFA_METADATA_DE 0x1000UL - #define CQ_RES_UD_CFA_METADATA_PRI_MASK 0xe000UL - #define CQ_RES_UD_CFA_METADATA_PRI_SFT 13 - __le32 imm_data; - __le64 qp_handle; - __le16 src_mac[3]; - __le16 src_qp_low; - u8 cqe_type_toggle; - #define CQ_RES_UD_TOGGLE 0x1UL - #define CQ_RES_UD_CQE_TYPE_MASK 0x1eUL - #define CQ_RES_UD_CQE_TYPE_SFT 1 - #define CQ_RES_UD_CQE_TYPE_RES_UD (0x2UL << 1) - u8 status; - #define CQ_RES_UD_STATUS_OK 0x0UL - #define CQ_RES_UD_STATUS_LOCAL_ACCESS_ERROR 0x1UL - #define CQ_RES_UD_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL - #define CQ_RES_UD_STATUS_LOCAL_PROTECTION_ERR 0x3UL - #define CQ_RES_UD_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL - #define CQ_RES_UD_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL - #define CQ_RES_UD_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL - #define CQ_RES_UD_STATUS_HW_FLUSH_ERR 0x8UL - __le16 flags; - #define CQ_RES_UD_FLAGS_SRQ 0x1UL - #define CQ_RES_UD_FLAGS_SRQ_RQ (0x0UL << 0) - #define CQ_RES_UD_FLAGS_SRQ_SRQ (0x1UL << 0) - #define CQ_RES_UD_FLAGS_SRQ_LAST CQ_RES_UD_FLAGS_SRQ_SRQ - #define CQ_RES_UD_FLAGS_IMM 0x2UL - #define CQ_RES_UD_FLAGS_UNUSED_MASK 0xcUL - #define CQ_RES_UD_FLAGS_UNUSED_SFT 2 - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_MASK 0x30UL - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_SFT 4 - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V1 (0x0UL << 4) - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV4 (0x2UL << 4) - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6 (0x3UL << 4) - #define CQ_RES_UD_FLAGS_ROCE_IP_VER_LAST \ - CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6 - #define CQ_RES_UD_FLAGS_META_FORMAT_MASK 0x3c0UL - #define CQ_RES_UD_FLAGS_META_FORMAT_SFT 6 - #define CQ_RES_UD_FLAGS_META_FORMAT_NONE (0x0UL << 6) - #define CQ_RES_UD_FLAGS_META_FORMAT_VLAN (0x1UL << 6) - #define CQ_RES_UD_FLAGS_META_FORMAT_TUNNEL_ID (0x2UL << 6) - #define CQ_RES_UD_FLAGS_META_FORMAT_CHDR_DATA (0x3UL << 6) - #define CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET (0x4UL << 6) - #define CQ_RES_UD_FLAGS_META_FORMAT_LAST \ - CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET - #define CQ_RES_UD_FLAGS_EXT_META_FORMAT_MASK 0xc00UL - #define CQ_RES_UD_FLAGS_EXT_META_FORMAT_SFT 10 - - __le32 src_qp_high_srq_or_rq_wr_id; - #define CQ_RES_UD_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL - #define CQ_RES_UD_SRQ_OR_RQ_WR_ID_SFT 0 - #define CQ_RES_UD_SRC_QP_HIGH_MASK 0xff000000UL - #define CQ_RES_UD_SRC_QP_HIGH_SFT 24 -}; - -/* Responder RawEth and QP1 CQE (32 bytes) */ -struct cq_res_raweth_qp1 { - __le16 length; - #define CQ_RES_RAWETH_QP1_LENGTH_MASK 0x3fffUL - #define CQ_RES_RAWETH_QP1_LENGTH_SFT 0 - #define CQ_RES_RAWETH_QP1_RESERVED2_MASK 0xc000UL - #define CQ_RES_RAWETH_QP1_RESERVED2_SFT 14 - __le16 raweth_qp1_flags; - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ERROR 0x1UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_RESERVED5_1_MASK 0x3eUL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_RESERVED5_1_SFT 1 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_MASK 0x3c0UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_SFT 6 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_NOT_KNOWN (0x0UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_IP (0x1UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_TCP (0x2UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_UDP (0x3UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_FCOE (0x4UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE (0x5UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ICMP (0x7UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_WO_TIMESTAMP \ - (0x8UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP \ - (0x9UL << 6) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_LAST \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_MASK 0x3ffUL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_SFT 0 - #define CQ_RES_RAWETH_QP1_RESERVED6_MASK 0xfc00UL - #define CQ_RES_RAWETH_QP1_RESERVED6_SFT 10 - __le16 raweth_qp1_errors; - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_RESERVED4_MASK 0xfUL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_RESERVED4_SFT 0 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_IP_CS_ERROR 0x10UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_L4_CS_ERROR 0x20UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_IP_CS_ERROR 0x40UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_L4_CS_ERROR 0x80UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_CRC_ERROR 0x100UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_MASK 0xe00UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_SFT 9 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_NO_ERROR \ - (0x0UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_VERSION \ - (0x1UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_HDR_LEN \ - (0x2UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_TUNNEL_TOTAL_ERROR \ - (0x3UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_IP_TOTAL_ERROR \ - (0x4UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_UDP_TOTAL_ERROR \ - (0x5UL << 9) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL \ - (0x6UL << 9) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_LAST \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_MASK 0xf000UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_SFT 12 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_NO_ERROR \ - (0x0UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_VERSION \ - (0x1UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_HDR_LEN \ - (0x2UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_TTL \ - (0x3UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_IP_TOTAL_ERROR \ - (0x4UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_UDP_TOTAL_ERROR \ - (0x5UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN \ - (0x6UL << 12) - #define \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN_TOO_SMALL\ - (0x7UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN \ - (0x8UL << 12) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_LAST \ - CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN - __le16 raweth_qp1_cfa_code; - __le64 qp_handle; - __le32 raweth_qp1_flags2; - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_CS_CALC 0x1UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_L4_CS_CALC 0x2UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_IP_CS_CALC 0x4UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_L4_CS_CALC 0x8UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_MASK 0xf0UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_SFT 4 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_NONE \ - (0x0UL << 4) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN \ - (0x1UL << 4) - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_LAST\ - CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_TYPE 0x100UL - __le32 raweth_qp1_metadata; - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_MASK 0xfffUL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_SFT 0 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_DE 0x1000UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_MASK 0xe000UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_SFT 13 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_MASK 0xffff0000UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_SFT 16 - u8 cqe_type_toggle; - #define CQ_RES_RAWETH_QP1_TOGGLE 0x1UL - #define CQ_RES_RAWETH_QP1_CQE_TYPE_MASK 0x1eUL - #define CQ_RES_RAWETH_QP1_CQE_TYPE_SFT 1 - #define CQ_RES_RAWETH_QP1_CQE_TYPE_RES_RAWETH_QP1 (0x3UL << 1) - #define CQ_RES_RAWETH_QP1_RESERVED3_MASK 0xe0UL - #define CQ_RES_RAWETH_QP1_RESERVED3_SFT 5 - u8 status; - #define CQ_RES_RAWETH_QP1_STATUS_OK 0x0UL - #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_ACCESS_ERROR 0x1UL - #define CQ_RES_RAWETH_QP1_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL - #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_PROTECTION_ERR 0x3UL - #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL - #define CQ_RES_RAWETH_QP1_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL - #define CQ_RES_RAWETH_QP1_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL - #define CQ_RES_RAWETH_QP1_STATUS_HW_FLUSH_ERR 0x8UL - __le16 flags; - #define CQ_RES_RAWETH_QP1_FLAGS_SRQ 0x1UL - #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_RQ 0x0UL - #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ 0x1UL - #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_LAST \ - CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ - __le32 raweth_qp1_payload_offset_srq_or_rq_wr_id; - #define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL - #define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_SFT 0 - #define CQ_RES_RAWETH_QP1_RESERVED4_MASK 0xf00000UL - #define CQ_RES_RAWETH_QP1_RESERVED4_SFT 20 - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_MASK 0xff000000UL - #define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_SFT 24 -}; - -/* Terminal CQE (32 bytes) */ -struct cq_terminal { - __le64 qp_handle; - __le16 sq_cons_idx; - __le16 rq_cons_idx; - __le32 reserved32_1; - __le64 reserved64_3; - u8 cqe_type_toggle; - #define CQ_TERMINAL_TOGGLE 0x1UL - #define CQ_TERMINAL_CQE_TYPE_MASK 0x1eUL - #define CQ_TERMINAL_CQE_TYPE_SFT 1 - #define CQ_TERMINAL_CQE_TYPE_TERMINAL (0xeUL << 1) - #define CQ_TERMINAL_RESERVED3_MASK 0xe0UL - #define CQ_TERMINAL_RESERVED3_SFT 5 - u8 status; - #define CQ_TERMINAL_STATUS_OK 0x0UL - __le16 reserved16; - __le32 reserved32_2; -}; - -/* Cutoff CQE (32 bytes) */ -struct cq_cutoff { - __le64 reserved64_1; - __le64 reserved64_2; - __le64 reserved64_3; - u8 cqe_type_toggle; - #define CQ_CUTOFF_TOGGLE 0x1UL - #define CQ_CUTOFF_CQE_TYPE_MASK 0x1eUL - #define CQ_CUTOFF_CQE_TYPE_SFT 1 - #define CQ_CUTOFF_CQE_TYPE_CUT_OFF (0xfUL << 1) - #define CQ_CUTOFF_RESERVED3_MASK 0xe0UL - #define CQ_CUTOFF_RESERVED3_SFT 5 - u8 status; - #define CQ_CUTOFF_STATUS_OK 0x0UL - __le16 reserved16; - __le32 reserved32; -}; - -/* Notification Queue (NQ) Structures */ -/* Base NQ Record (16 bytes) */ -struct nq_base { - __le16 info10_type; - #define NQ_BASE_TYPE_MASK 0x3fUL - #define NQ_BASE_TYPE_SFT 0 - #define NQ_BASE_TYPE_CQ_NOTIFICATION 0x30UL - #define NQ_BASE_TYPE_SRQ_EVENT 0x32UL - #define NQ_BASE_TYPE_DBQ_EVENT 0x34UL - #define NQ_BASE_TYPE_QP_EVENT 0x38UL - #define NQ_BASE_TYPE_FUNC_EVENT 0x3aUL - #define NQ_BASE_INFO10_MASK 0xffc0UL - #define NQ_BASE_INFO10_SFT 6 - __le16 info16; - __le32 info32; - __le32 info63_v[2]; - #define NQ_BASE_V 0x1UL - #define NQ_BASE_INFO63_MASK 0xfffffffeUL - #define NQ_BASE_INFO63_SFT 1 -}; - -/* Completion Queue Notification (16 bytes) */ -struct nq_cn { - __le16 type; - #define NQ_CN_TYPE_MASK 0x3fUL - #define NQ_CN_TYPE_SFT 0 - #define NQ_CN_TYPE_CQ_NOTIFICATION 0x30UL - #define NQ_CN_RESERVED9_MASK 0xffc0UL - #define NQ_CN_RESERVED9_SFT 6 - __le16 reserved16; - __le32 cq_handle_low; - __le32 v; - #define NQ_CN_V 0x1UL - #define NQ_CN_RESERVED31_MASK 0xfffffffeUL - #define NQ_CN_RESERVED31_SFT 1 - __le32 cq_handle_high; -}; - -/* SRQ Event Notification (16 bytes) */ -struct nq_srq_event { - u8 type; - #define NQ_SRQ_EVENT_TYPE_MASK 0x3fUL - #define NQ_SRQ_EVENT_TYPE_SFT 0 - #define NQ_SRQ_EVENT_TYPE_SRQ_EVENT 0x32UL - #define NQ_SRQ_EVENT_RESERVED1_MASK 0xc0UL - #define NQ_SRQ_EVENT_RESERVED1_SFT 6 - u8 event; - #define NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT 0x1UL - __le16 reserved16; - __le32 srq_handle_low; - __le32 v; - #define NQ_SRQ_EVENT_V 0x1UL - #define NQ_SRQ_EVENT_RESERVED31_MASK 0xfffffffeUL - #define NQ_SRQ_EVENT_RESERVED31_SFT 1 - __le32 srq_handle_high; -}; - -/* DBQ Async Event Notification (16 bytes) */ -struct nq_dbq_event { - u8 type; - #define NQ_DBQ_EVENT_TYPE_MASK 0x3fUL - #define NQ_DBQ_EVENT_TYPE_SFT 0 - #define NQ_DBQ_EVENT_TYPE_DBQ_EVENT 0x34UL - #define NQ_DBQ_EVENT_RESERVED1_MASK 0xc0UL - #define NQ_DBQ_EVENT_RESERVED1_SFT 6 - u8 event; - #define NQ_DBQ_EVENT_EVENT_DBQ_THRESHOLD_EVENT 0x1UL - __le16 db_pfid; - #define NQ_DBQ_EVENT_DB_PFID_MASK 0xfUL - #define NQ_DBQ_EVENT_DB_PFID_SFT 0 - #define NQ_DBQ_EVENT_RESERVED12_MASK 0xfff0UL - #define NQ_DBQ_EVENT_RESERVED12_SFT 4 - __le32 db_dpi; - #define NQ_DBQ_EVENT_DB_DPI_MASK 0xfffffUL - #define NQ_DBQ_EVENT_DB_DPI_SFT 0 - #define NQ_DBQ_EVENT_RESERVED12_2_MASK 0xfff00000UL - #define NQ_DBQ_EVENT_RESERVED12_2_SFT 20 - __le32 v; - #define NQ_DBQ_EVENT_V 0x1UL - #define NQ_DBQ_EVENT_RESERVED32_MASK 0xfffffffeUL - #define NQ_DBQ_EVENT_RESERVED32_SFT 1 - __le32 db_type_db_xid; - #define NQ_DBQ_EVENT_DB_XID_MASK 0xfffffUL - #define NQ_DBQ_EVENT_DB_XID_SFT 0 - #define NQ_DBQ_EVENT_RESERVED8_MASK 0xff00000UL - #define NQ_DBQ_EVENT_RESERVED8_SFT 20 - #define NQ_DBQ_EVENT_DB_TYPE_MASK 0xf0000000UL - #define NQ_DBQ_EVENT_DB_TYPE_SFT 28 -}; - -/* Read Request/Response Queue Structures */ -/* Input Read Request Queue (IRRQ) Message (32 bytes) */ -struct xrrq_irrq { - __le16 credits_type; - #define XRRQ_IRRQ_TYPE 0x1UL - #define XRRQ_IRRQ_TYPE_READ_REQ 0x0UL - #define XRRQ_IRRQ_TYPE_ATOMIC_REQ 0x1UL - #define XRRQ_IRRQ_RESERVED10_MASK 0x7feUL - #define XRRQ_IRRQ_RESERVED10_SFT 1 - #define XRRQ_IRRQ_CREDITS_MASK 0xf800UL - #define XRRQ_IRRQ_CREDITS_SFT 11 - __le16 reserved16; - __le32 reserved32; - __le32 psn; - #define XRRQ_IRRQ_PSN_MASK 0xffffffUL - #define XRRQ_IRRQ_PSN_SFT 0 - #define XRRQ_IRRQ_RESERVED8_1_MASK 0xff000000UL - #define XRRQ_IRRQ_RESERVED8_1_SFT 24 - __le32 msn; - #define XRRQ_IRRQ_MSN_MASK 0xffffffUL - #define XRRQ_IRRQ_MSN_SFT 0 - #define XRRQ_IRRQ_RESERVED8_2_MASK 0xff000000UL - #define XRRQ_IRRQ_RESERVED8_2_SFT 24 - __le64 va_or_atomic_result; - __le32 rdma_r_key; - __le32 length; -}; - -/* Output Read Request Queue (ORRQ) Message (32 bytes) */ -struct xrrq_orrq { - __le16 num_sges_type; - #define XRRQ_ORRQ_TYPE 0x1UL - #define XRRQ_ORRQ_TYPE_READ_REQ 0x0UL - #define XRRQ_ORRQ_TYPE_ATOMIC_REQ 0x1UL - #define XRRQ_ORRQ_RESERVED10_MASK 0x7feUL - #define XRRQ_ORRQ_RESERVED10_SFT 1 - #define XRRQ_ORRQ_NUM_SGES_MASK 0xf800UL - #define XRRQ_ORRQ_NUM_SGES_SFT 11 - __le16 reserved16; - __le32 length; - __le32 psn; - #define XRRQ_ORRQ_PSN_MASK 0xffffffUL - #define XRRQ_ORRQ_PSN_SFT 0 - #define XRRQ_ORRQ_RESERVED8_1_MASK 0xff000000UL - #define XRRQ_ORRQ_RESERVED8_1_SFT 24 - __le32 end_psn; - #define XRRQ_ORRQ_END_PSN_MASK 0xffffffUL - #define XRRQ_ORRQ_END_PSN_SFT 0 - #define XRRQ_ORRQ_RESERVED8_2_MASK 0xff000000UL - #define XRRQ_ORRQ_RESERVED8_2_SFT 24 - __le64 first_sge_phy_or_sing_sge_va; - __le32 single_sge_l_key; - __le32 single_sge_size; -}; - -/* Page Buffer List Memory Structures (PBL) */ -/* Page Table Entry (PTE) (8 bytes) */ -struct ptu_pte { - __le32 page_next_to_last_last_valid[2]; - #define PTU_PTE_VALID 0x1UL - #define PTU_PTE_LAST 0x2UL - #define PTU_PTE_NEXT_TO_LAST 0x4UL - #define PTU_PTE_PAGE_MASK 0xfffff000UL - #define PTU_PTE_PAGE_SFT 12 +/* creq_destroy_qp_resp (size:128b/16B) */ +struct creq_destroy_qp_resp { + u8 type; + #define CREQ_DESTROY_QP_RESP_TYPE_MASK 0x3fUL + #define CREQ_DESTROY_QP_RESP_TYPE_SFT 0 + #define CREQ_DESTROY_QP_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DESTROY_QP_RESP_TYPE_LAST CREQ_DESTROY_QP_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DESTROY_QP_RESP_V 0x1UL + u8 event; + #define CREQ_DESTROY_QP_RESP_EVENT_DESTROY_QP 0x2UL + #define CREQ_DESTROY_QP_RESP_EVENT_LAST CREQ_DESTROY_QP_RESP_EVENT_DESTROY_QP + u8 reserved48[6]; }; -/* Page Directory Entry (PDE) (8 bytes) */ -struct ptu_pde { - __le32 page_valid[2]; - #define PTU_PDE_VALID 0x1UL - #define PTU_PDE_PAGE_MASK 0xfffff000UL - #define PTU_PDE_PAGE_SFT 12 +/* cmdq_modify_qp (size:1024b/128B) */ +struct cmdq_modify_qp { + u8 opcode; + #define CMDQ_MODIFY_QP_OPCODE_MODIFY_QP 0x3UL + #define CMDQ_MODIFY_QP_OPCODE_LAST CMDQ_MODIFY_QP_OPCODE_MODIFY_QP + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 modify_mask; + #define CMDQ_MODIFY_QP_MODIFY_MASK_STATE 0x1UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_EN_SQD_ASYNC_NOTIFY 0x2UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS 0x4UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_PKEY 0x8UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_QKEY 0x10UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_DGID 0x20UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL 0x40UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX 0x80UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT 0x100UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS 0x200UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC 0x400UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_PINGPONG_PUSH_MODE 0x800UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU 0x1000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT 0x2000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT 0x4000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY 0x8000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN 0x10000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC 0x20000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER 0x40000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN 0x80000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC 0x100000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE 0x200000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE 0x400000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SGE 0x800000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SGE 0x1000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_INLINE_DATA 0x2000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID 0x4000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_SRC_MAC 0x8000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID 0x10000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_ENABLE_CC 0x20000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_ECN 0x40000000UL + #define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_DSCP 0x80000000UL + __le32 qp_cid; + u8 network_type_en_sqd_async_notify_new_state; + #define CMDQ_MODIFY_QP_NEW_STATE_MASK 0xfUL + #define CMDQ_MODIFY_QP_NEW_STATE_SFT 0 + #define CMDQ_MODIFY_QP_NEW_STATE_RESET 0x0UL + #define CMDQ_MODIFY_QP_NEW_STATE_INIT 0x1UL + #define CMDQ_MODIFY_QP_NEW_STATE_RTR 0x2UL + #define CMDQ_MODIFY_QP_NEW_STATE_RTS 0x3UL + #define CMDQ_MODIFY_QP_NEW_STATE_SQD 0x4UL + #define CMDQ_MODIFY_QP_NEW_STATE_SQE 0x5UL + #define CMDQ_MODIFY_QP_NEW_STATE_ERR 0x6UL + #define CMDQ_MODIFY_QP_NEW_STATE_LAST CMDQ_MODIFY_QP_NEW_STATE_ERR + #define CMDQ_MODIFY_QP_EN_SQD_ASYNC_NOTIFY 0x10UL + #define CMDQ_MODIFY_QP_UNUSED1 0x20UL + #define CMDQ_MODIFY_QP_NETWORK_TYPE_MASK 0xc0UL + #define CMDQ_MODIFY_QP_NETWORK_TYPE_SFT 6 + #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV1 (0x0UL << 6) + #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV4 (0x2UL << 6) + #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV6 (0x3UL << 6) + #define CMDQ_MODIFY_QP_NETWORK_TYPE_LAST CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV6 + u8 access; + #define CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC_REMOTE_READ_REMOTE_WRITE_LOCAL_WRITE_MASK \ + 0xffUL + #define CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC_REMOTE_READ_REMOTE_WRITE_LOCAL_WRITE_SFT \ + 0 + #define CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE 0x1UL + #define CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE 0x2UL + #define CMDQ_MODIFY_QP_ACCESS_REMOTE_READ 0x4UL + #define CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC 0x8UL + __le16 pkey; + __le32 qkey; + __le32 dgid[4]; + __le32 flow_label; + __le16 sgid_index; + u8 hop_limit; + u8 traffic_class; + __le16 dest_mac[3]; + u8 tos_dscp_tos_ecn; + #define CMDQ_MODIFY_QP_TOS_ECN_MASK 0x3UL + #define CMDQ_MODIFY_QP_TOS_ECN_SFT 0 + #define CMDQ_MODIFY_QP_TOS_DSCP_MASK 0xfcUL + #define CMDQ_MODIFY_QP_TOS_DSCP_SFT 2 + u8 path_mtu_pingpong_push_enable; + #define CMDQ_MODIFY_QP_PINGPONG_PUSH_ENABLE 0x1UL + #define CMDQ_MODIFY_QP_UNUSED3_MASK 0xeUL + #define CMDQ_MODIFY_QP_UNUSED3_SFT 1 + #define CMDQ_MODIFY_QP_PATH_MTU_MASK 0xf0UL + #define CMDQ_MODIFY_QP_PATH_MTU_SFT 4 + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_256 (0x0UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_512 (0x1UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_1024 (0x2UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_2048 (0x3UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_4096 (0x4UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_MTU_8192 (0x5UL << 4) + #define CMDQ_MODIFY_QP_PATH_MTU_LAST CMDQ_MODIFY_QP_PATH_MTU_MTU_8192 + u8 timeout; + u8 retry_cnt; + u8 rnr_retry; + u8 min_rnr_timer; + __le32 rq_psn; + __le32 sq_psn; + u8 max_rd_atomic; + u8 max_dest_rd_atomic; + __le16 enable_cc; + #define CMDQ_MODIFY_QP_ENABLE_CC 0x1UL + #define CMDQ_MODIFY_QP_UNUSED15_MASK 0xfffeUL + #define CMDQ_MODIFY_QP_UNUSED15_SFT 1 + __le32 sq_size; + __le32 rq_size; + __le16 sq_sge; + __le16 rq_sge; + __le32 max_inline_data; + __le32 dest_qp_id; + __le32 pingpong_push_dpi; + __le16 src_mac[3]; + __le16 vlan_pcp_vlan_dei_vlan_id; + #define CMDQ_MODIFY_QP_VLAN_ID_MASK 0xfffUL + #define CMDQ_MODIFY_QP_VLAN_ID_SFT 0 + #define CMDQ_MODIFY_QP_VLAN_DEI 0x1000UL + #define CMDQ_MODIFY_QP_VLAN_PCP_MASK 0xe000UL + #define CMDQ_MODIFY_QP_VLAN_PCP_SFT 13 + __le64 irrq_addr; + __le64 orrq_addr; }; -/* RoCE Fastpath Host Structures */ -/* Command Queue (CMDQ) Interface */ -/* Init CMDQ (16 bytes) */ -struct cmdq_init { - __le64 cmdq_pbl; - __le16 cmdq_size_cmdq_lvl; - #define CMDQ_INIT_CMDQ_LVL_MASK 0x3UL - #define CMDQ_INIT_CMDQ_LVL_SFT 0 - #define CMDQ_INIT_CMDQ_SIZE_MASK 0xfffcUL - #define CMDQ_INIT_CMDQ_SIZE_SFT 2 - __le16 creq_ring_id; - __le32 prod_idx; +/* creq_modify_qp_resp (size:128b/16B) */ +struct creq_modify_qp_resp { + u8 type; + #define CREQ_MODIFY_QP_RESP_TYPE_MASK 0x3fUL + #define CREQ_MODIFY_QP_RESP_TYPE_SFT 0 + #define CREQ_MODIFY_QP_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_MODIFY_QP_RESP_TYPE_LAST CREQ_MODIFY_QP_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_MODIFY_QP_RESP_V 0x1UL + u8 event; + #define CREQ_MODIFY_QP_RESP_EVENT_MODIFY_QP 0x3UL + #define CREQ_MODIFY_QP_RESP_EVENT_LAST CREQ_MODIFY_QP_RESP_EVENT_MODIFY_QP + u8 pingpong_push_state_index_enabled; + #define CREQ_MODIFY_QP_RESP_PINGPONG_PUSH_ENABLED 0x1UL + #define CREQ_MODIFY_QP_RESP_PINGPONG_PUSH_INDEX_MASK 0xeUL + #define CREQ_MODIFY_QP_RESP_PINGPONG_PUSH_INDEX_SFT 1 + #define CREQ_MODIFY_QP_RESP_PINGPONG_PUSH_STATE 0x10UL + u8 reserved8; + __le32 lag_src_mac; }; -/* Update CMDQ producer index (16 bytes) */ -struct cmdq_update { - __le64 reserved64; - __le32 reserved32; - __le32 prod_idx; +/* cmdq_query_qp (size:192b/24B) */ +struct cmdq_query_qp { + u8 opcode; + #define CMDQ_QUERY_QP_OPCODE_QUERY_QP 0x4UL + #define CMDQ_QUERY_QP_OPCODE_LAST CMDQ_QUERY_QP_OPCODE_QUERY_QP + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 qp_cid; + __le32 unused_0; }; -/* CMDQ common header structure (16 bytes) */ -struct cmdq_base { - u8 opcode; - #define CMDQ_BASE_OPCODE_CREATE_QP 0x1UL - #define CMDQ_BASE_OPCODE_DESTROY_QP 0x2UL - #define CMDQ_BASE_OPCODE_MODIFY_QP 0x3UL - #define CMDQ_BASE_OPCODE_QUERY_QP 0x4UL - #define CMDQ_BASE_OPCODE_CREATE_SRQ 0x5UL - #define CMDQ_BASE_OPCODE_DESTROY_SRQ 0x6UL - #define CMDQ_BASE_OPCODE_QUERY_SRQ 0x8UL - #define CMDQ_BASE_OPCODE_CREATE_CQ 0x9UL - #define CMDQ_BASE_OPCODE_DESTROY_CQ 0xaUL - #define CMDQ_BASE_OPCODE_RESIZE_CQ 0xcUL - #define CMDQ_BASE_OPCODE_ALLOCATE_MRW 0xdUL - #define CMDQ_BASE_OPCODE_DEALLOCATE_KEY 0xeUL - #define CMDQ_BASE_OPCODE_REGISTER_MR 0xfUL - #define CMDQ_BASE_OPCODE_DEREGISTER_MR 0x10UL - #define CMDQ_BASE_OPCODE_ADD_GID 0x11UL - #define CMDQ_BASE_OPCODE_DELETE_GID 0x12UL - #define CMDQ_BASE_OPCODE_MODIFY_GID 0x17UL - #define CMDQ_BASE_OPCODE_QUERY_GID 0x18UL - #define CMDQ_BASE_OPCODE_CREATE_QP1 0x13UL - #define CMDQ_BASE_OPCODE_DESTROY_QP1 0x14UL - #define CMDQ_BASE_OPCODE_CREATE_AH 0x15UL - #define CMDQ_BASE_OPCODE_DESTROY_AH 0x16UL - #define CMDQ_BASE_OPCODE_INITIALIZE_FW 0x80UL - #define CMDQ_BASE_OPCODE_DEINITIALIZE_FW 0x81UL - #define CMDQ_BASE_OPCODE_STOP_FUNC 0x82UL - #define CMDQ_BASE_OPCODE_QUERY_FUNC 0x83UL - #define CMDQ_BASE_OPCODE_SET_FUNC_RESOURCES 0x84UL - #define CMDQ_BASE_OPCODE_READ_CONTEXT 0x85UL - #define CMDQ_BASE_OPCODE_VF_BACKCHANNEL_REQUEST 0x86UL - #define CMDQ_BASE_OPCODE_READ_VF_MEMORY 0x87UL - #define CMDQ_BASE_OPCODE_COMPLETE_VF_REQUEST 0x88UL - #define CMDQ_BASE_OPCODE_EXTEND_CONTEXT_ARRRAY 0x89UL - #define CMDQ_BASE_OPCODE_MAP_TC_TO_COS 0x8aUL - #define CMDQ_BASE_OPCODE_QUERY_VERSION 0x8bUL - #define CMDQ_BASE_OPCODE_MODIFY_CC 0x8cUL - #define CMDQ_BASE_OPCODE_QUERY_CC 0x8dUL - #define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS 0x8eUL - #define CMDQ_BASE_OPCODE_QUERY_ROCE_STATS_EXT 0x92UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; -}; - -/* Create QP command (96 bytes) */ -struct cmdq_create_qp { - u8 opcode; - #define CMDQ_CREATE_QP_OPCODE_CREATE_QP 0x1UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 qp_handle; - __le32 qp_flags; - #define CMDQ_CREATE_QP_QP_FLAGS_SRQ_USED 0x1UL - #define CMDQ_CREATE_QP_QP_FLAGS_FORCE_COMPLETION 0x2UL - #define CMDQ_CREATE_QP_QP_FLAGS_RESERVED_LKEY_ENABLE 0x4UL - #define CMDQ_CREATE_QP_QP_FLAGS_FR_PMR_ENABLED 0x8UL - #define CMDQ_CREATE_QP_QP_FLAGS_VARIABLE_SIZED_WQE_ENABLED 0x10UL - #define CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED 0x80UL - #define CMDQ_CREATE_QP_QP_FLAGS_LAST \ - CMDQ_CREATE_QP_QP_FLAGS_EXT_STATS_ENABLED +/* creq_query_qp_resp (size:128b/16B) */ +struct creq_query_qp_resp { + u8 type; + #define CREQ_QUERY_QP_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_QP_RESP_TYPE_SFT 0 + #define CREQ_QUERY_QP_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_QP_RESP_TYPE_LAST CREQ_QUERY_QP_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_QP_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_QP_RESP_EVENT_QUERY_QP 0x4UL + #define CREQ_QUERY_QP_RESP_EVENT_LAST CREQ_QUERY_QP_RESP_EVENT_QUERY_QP + u8 reserved48[6]; +}; - u8 type; - #define CMDQ_CREATE_QP_TYPE_RC 0x2UL - #define CMDQ_CREATE_QP_TYPE_UD 0x4UL - #define CMDQ_CREATE_QP_TYPE_RAW_ETHERTYPE 0x6UL - #define CMDQ_CREATE_QP_TYPE_GSI 0x7UL - u8 sq_pg_size_sq_lvl; - #define CMDQ_CREATE_QP_SQ_LVL_MASK 0xfUL - #define CMDQ_CREATE_QP_SQ_LVL_SFT 0 - #define CMDQ_CREATE_QP_SQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_QP_SQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_QP_SQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_QP_SQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_CREATE_QP_SQ_PG_SIZE_SFT 4 - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_CREATE_QP_SQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 rq_pg_size_rq_lvl; - #define CMDQ_CREATE_QP_RQ_LVL_MASK 0xfUL - #define CMDQ_CREATE_QP_RQ_LVL_SFT 0 - #define CMDQ_CREATE_QP_RQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_QP_RQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_QP_RQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_QP_RQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_CREATE_QP_RQ_PG_SIZE_SFT 4 - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_CREATE_QP_RQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 unused_0; - __le32 dpi; - __le32 sq_size; - __le32 rq_size; - __le16 sq_fwo_sq_sge; - #define CMDQ_CREATE_QP_SQ_SGE_MASK 0xfUL - #define CMDQ_CREATE_QP_SQ_SGE_SFT 0 - #define CMDQ_CREATE_QP_SQ_FWO_MASK 0xfff0UL - #define CMDQ_CREATE_QP_SQ_FWO_SFT 4 - __le16 rq_fwo_rq_sge; - #define CMDQ_CREATE_QP_RQ_SGE_MASK 0xfUL - #define CMDQ_CREATE_QP_RQ_SGE_SFT 0 - #define CMDQ_CREATE_QP_RQ_FWO_MASK 0xfff0UL - #define CMDQ_CREATE_QP_RQ_FWO_SFT 4 - __le32 scq_cid; - __le32 rcq_cid; - __le32 srq_cid; - __le32 pd_id; - __le64 sq_pbl; - __le64 rq_pbl; - __le64 irrq_addr; - __le64 orrq_addr; -}; - -/* Destroy QP command (24 bytes) */ -struct cmdq_destroy_qp { - u8 opcode; - #define CMDQ_DESTROY_QP_OPCODE_DESTROY_QP 0x2UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 qp_cid; - __le32 unused_0; -}; - -/* Modify QP command (112 bytes) */ -struct cmdq_modify_qp { - u8 opcode; - #define CMDQ_MODIFY_QP_OPCODE_MODIFY_QP 0x3UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 modify_mask; - #define CMDQ_MODIFY_QP_MODIFY_MASK_STATE 0x1UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_EN_SQD_ASYNC_NOTIFY 0x2UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_ACCESS 0x4UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_PKEY 0x8UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_QKEY 0x10UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_DGID 0x20UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_FLOW_LABEL 0x40UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_SGID_INDEX 0x80UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_HOP_LIMIT 0x100UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_TRAFFIC_CLASS 0x200UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_MAC 0x400UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU 0x1000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_TIMEOUT 0x2000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_RETRY_CNT 0x4000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_RNR_RETRY 0x8000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_PSN 0x10000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_RD_ATOMIC 0x20000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_MIN_RNR_TIMER 0x40000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_PSN 0x80000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_DEST_RD_ATOMIC 0x100000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SIZE 0x200000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SIZE 0x400000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_SQ_SGE 0x800000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_RQ_SGE 0x1000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_MAX_INLINE_DATA 0x2000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_DEST_QP_ID 0x4000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_SRC_MAC 0x8000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID 0x10000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_ENABLE_CC 0x20000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_ECN 0x40000000UL - #define CMDQ_MODIFY_QP_MODIFY_MASK_TOS_DSCP 0x80000000UL - __le32 qp_cid; - u8 network_type_en_sqd_async_notify_new_state; - #define CMDQ_MODIFY_QP_NEW_STATE_MASK 0xfUL - #define CMDQ_MODIFY_QP_NEW_STATE_SFT 0 - #define CMDQ_MODIFY_QP_NEW_STATE_RESET 0x0UL - #define CMDQ_MODIFY_QP_NEW_STATE_INIT 0x1UL - #define CMDQ_MODIFY_QP_NEW_STATE_RTR 0x2UL - #define CMDQ_MODIFY_QP_NEW_STATE_RTS 0x3UL - #define CMDQ_MODIFY_QP_NEW_STATE_SQD 0x4UL - #define CMDQ_MODIFY_QP_NEW_STATE_SQE 0x5UL - #define CMDQ_MODIFY_QP_NEW_STATE_ERR 0x6UL - #define CMDQ_MODIFY_QP_EN_SQD_ASYNC_NOTIFY 0x10UL - #define CMDQ_MODIFY_QP_NETWORK_TYPE_MASK 0xc0UL - #define CMDQ_MODIFY_QP_NETWORK_TYPE_SFT 6 - #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV1 (0x0UL << 6) - #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV4 (0x2UL << 6) - #define CMDQ_MODIFY_QP_NETWORK_TYPE_ROCEV2_IPV6 (0x3UL << 6) - u8 access; - #define CMDQ_MODIFY_QP_ACCESS_LOCAL_WRITE 0x1UL - #define CMDQ_MODIFY_QP_ACCESS_REMOTE_WRITE 0x2UL - #define CMDQ_MODIFY_QP_ACCESS_REMOTE_READ 0x4UL - #define CMDQ_MODIFY_QP_ACCESS_REMOTE_ATOMIC 0x8UL - __le16 pkey; - __le32 qkey; - __le32 dgid[4]; - __le32 flow_label; - __le16 sgid_index; - u8 hop_limit; - u8 traffic_class; - __le16 dest_mac[3]; - u8 tos_dscp_tos_ecn; - #define CMDQ_MODIFY_QP_TOS_ECN_MASK 0x3UL - #define CMDQ_MODIFY_QP_TOS_ECN_SFT 0 - #define CMDQ_MODIFY_QP_TOS_DSCP_MASK 0xfcUL - #define CMDQ_MODIFY_QP_TOS_DSCP_SFT 2 - u8 path_mtu; - #define CMDQ_MODIFY_QP_PATH_MTU_MASK 0xf0UL - #define CMDQ_MODIFY_QP_PATH_MTU_SFT 4 - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_256 (0x0UL << 4) - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_512 (0x1UL << 4) - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_1024 (0x2UL << 4) - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_2048 (0x3UL << 4) - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_4096 (0x4UL << 4) - #define CMDQ_MODIFY_QP_PATH_MTU_MTU_8192 (0x5UL << 4) - u8 timeout; - u8 retry_cnt; - u8 rnr_retry; - u8 min_rnr_timer; - __le32 rq_psn; - __le32 sq_psn; - u8 max_rd_atomic; - u8 max_dest_rd_atomic; - __le16 enable_cc; - #define CMDQ_MODIFY_QP_ENABLE_CC 0x1UL - __le32 sq_size; - __le32 rq_size; - __le16 sq_sge; - __le16 rq_sge; - __le32 max_inline_data; - __le32 dest_qp_id; - __le32 unused_3; - __le16 src_mac[3]; - __le16 vlan_pcp_vlan_dei_vlan_id; - #define CMDQ_MODIFY_QP_VLAN_ID_MASK 0xfffUL - #define CMDQ_MODIFY_QP_VLAN_ID_SFT 0 - #define CMDQ_MODIFY_QP_VLAN_DEI 0x1000UL - #define CMDQ_MODIFY_QP_VLAN_PCP_MASK 0xe000UL - #define CMDQ_MODIFY_QP_VLAN_PCP_SFT 13 -}; - -/* Query QP command (24 bytes) */ -struct cmdq_query_qp { - u8 opcode; - #define CMDQ_QUERY_QP_OPCODE_QUERY_QP 0x4UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 qp_cid; - __le32 unused_0; -}; - -/* Create SRQ command (48 bytes) */ -struct cmdq_create_srq { - u8 opcode; - #define CMDQ_CREATE_SRQ_OPCODE_CREATE_SRQ 0x5UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 srq_handle; - __le16 pg_size_lvl; - #define CMDQ_CREATE_SRQ_LVL_MASK 0x3UL - #define CMDQ_CREATE_SRQ_LVL_SFT 0 - #define CMDQ_CREATE_SRQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_SRQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_SRQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_SRQ_PG_SIZE_MASK 0x1cUL - #define CMDQ_CREATE_SRQ_PG_SIZE_SFT 2 - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_4K (0x0UL << 2) - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_8K (0x1UL << 2) - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_64K (0x2UL << 2) - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_2M (0x3UL << 2) - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_8M (0x4UL << 2) - #define CMDQ_CREATE_SRQ_PG_SIZE_PG_1G (0x5UL << 2) - __le16 eventq_id; - #define CMDQ_CREATE_SRQ_EVENTQ_ID_MASK 0xfffUL - #define CMDQ_CREATE_SRQ_EVENTQ_ID_SFT 0 - __le16 srq_size; - __le16 srq_fwo; - __le32 dpi; - __le32 pd_id; - __le64 pbl; -}; - -/* Destroy SRQ command (24 bytes) */ -struct cmdq_destroy_srq { - u8 opcode; - #define CMDQ_DESTROY_SRQ_OPCODE_DESTROY_SRQ 0x6UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 srq_cid; - __le32 unused_0; -}; - -/* Query SRQ command (24 bytes) */ -struct cmdq_query_srq { - u8 opcode; - #define CMDQ_QUERY_SRQ_OPCODE_QUERY_SRQ 0x8UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 srq_cid; - __le32 unused_0; -}; - -/* Create CQ command (48 bytes) */ -struct cmdq_create_cq { - u8 opcode; - #define CMDQ_CREATE_CQ_OPCODE_CREATE_CQ 0x9UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 cq_handle; - __le32 pg_size_lvl; - #define CMDQ_CREATE_CQ_LVL_MASK 0x3UL - #define CMDQ_CREATE_CQ_LVL_SFT 0 - #define CMDQ_CREATE_CQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_CQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_CQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_CQ_PG_SIZE_MASK 0x1cUL - #define CMDQ_CREATE_CQ_PG_SIZE_SFT 2 - #define CMDQ_CREATE_CQ_PG_SIZE_PG_4K (0x0UL << 2) - #define CMDQ_CREATE_CQ_PG_SIZE_PG_8K (0x1UL << 2) - #define CMDQ_CREATE_CQ_PG_SIZE_PG_64K (0x2UL << 2) - #define CMDQ_CREATE_CQ_PG_SIZE_PG_2M (0x3UL << 2) - #define CMDQ_CREATE_CQ_PG_SIZE_PG_8M (0x4UL << 2) - #define CMDQ_CREATE_CQ_PG_SIZE_PG_1G (0x5UL << 2) - __le32 cq_fco_cnq_id; - #define CMDQ_CREATE_CQ_CNQ_ID_MASK 0xfffUL - #define CMDQ_CREATE_CQ_CNQ_ID_SFT 0 - #define CMDQ_CREATE_CQ_CQ_FCO_MASK 0xfffff000UL - #define CMDQ_CREATE_CQ_CQ_FCO_SFT 12 - __le32 dpi; - __le32 cq_size; - __le64 pbl; -}; - -/* Destroy CQ command (24 bytes) */ -struct cmdq_destroy_cq { - u8 opcode; - #define CMDQ_DESTROY_CQ_OPCODE_DESTROY_CQ 0xaUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 cq_cid; - __le32 unused_0; -}; - -/* Resize CQ command (40 bytes) */ -struct cmdq_resize_cq { - u8 opcode; - #define CMDQ_RESIZE_CQ_OPCODE_RESIZE_CQ 0xcUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 cq_cid; - __le32 new_cq_size_pg_size_lvl; - #define CMDQ_RESIZE_CQ_LVL_MASK 0x3UL - #define CMDQ_RESIZE_CQ_LVL_SFT 0 - #define CMDQ_RESIZE_CQ_LVL_LVL_0 0x0UL - #define CMDQ_RESIZE_CQ_LVL_LVL_1 0x1UL - #define CMDQ_RESIZE_CQ_LVL_LVL_2 0x2UL - #define CMDQ_RESIZE_CQ_PG_SIZE_MASK 0x1cUL - #define CMDQ_RESIZE_CQ_PG_SIZE_SFT 2 - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_4K (0x0UL << 2) - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_8K (0x1UL << 2) - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_64K (0x2UL << 2) - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_2M (0x3UL << 2) - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_8M (0x4UL << 2) - #define CMDQ_RESIZE_CQ_PG_SIZE_PG_1G (0x5UL << 2) - #define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_MASK 0x1fffe0UL - #define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_SFT 5 - __le64 new_pbl; - __le32 new_cq_fco; - __le32 unused_2; -}; - -/* Allocate MRW command (32 bytes) */ -struct cmdq_allocate_mrw { - u8 opcode; - #define CMDQ_ALLOCATE_MRW_OPCODE_ALLOCATE_MRW 0xdUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 mrw_handle; - u8 mrw_flags; - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MASK 0xfUL - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_SFT 0 - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR 0x0UL - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR 0x1UL - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1 0x2UL - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A 0x3UL - #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B 0x4UL - u8 access; - #define CMDQ_ALLOCATE_MRW_ACCESS_RESERVED_MASK 0x1fUL - #define CMDQ_ALLOCATE_MRW_ACCESS_RESERVED_SFT 0 - #define CMDQ_ALLOCATE_MRW_ACCESS_CONSUMER_OWNED_KEY 0x20UL - __le16 unused_1; - __le32 pd_id; -}; - -/* De-allocate key command (24 bytes) */ -struct cmdq_deallocate_key { - u8 opcode; - #define CMDQ_DEALLOCATE_KEY_OPCODE_DEALLOCATE_KEY 0xeUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - u8 mrw_flags; - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MASK 0xfUL - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_SFT 0 - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MR 0x0UL - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_PMR 0x1UL - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE1 0x2UL - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2A 0x3UL - #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2B 0x4UL - u8 unused_1[3]; - __le32 key; -}; - -/* Register MR command (48 bytes) */ -struct cmdq_register_mr { - u8 opcode; - #define CMDQ_REGISTER_MR_OPCODE_REGISTER_MR 0xfUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - u8 log2_pg_size_lvl; - #define CMDQ_REGISTER_MR_LVL_MASK 0x3UL - #define CMDQ_REGISTER_MR_LVL_SFT 0 - #define CMDQ_REGISTER_MR_LVL_LVL_0 0x0UL - #define CMDQ_REGISTER_MR_LVL_LVL_1 0x1UL - #define CMDQ_REGISTER_MR_LVL_LVL_2 0x2UL - #define CMDQ_REGISTER_MR_LVL_LAST CMDQ_REGISTER_MR_LVL_LVL_2 - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_MASK 0x7cUL - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_SFT 2 - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4K (0xcUL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_8K (0xdUL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_64K (0x10UL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_256K (0x12UL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1M (0x14UL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_2M (0x15UL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4M (0x16UL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G (0x1eUL << 2) - #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_LAST \ - CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G - #define CMDQ_REGISTER_MR_UNUSED1 0x80UL - u8 access; - #define CMDQ_REGISTER_MR_ACCESS_LOCAL_WRITE 0x1UL - #define CMDQ_REGISTER_MR_ACCESS_REMOTE_READ 0x2UL - #define CMDQ_REGISTER_MR_ACCESS_REMOTE_WRITE 0x4UL - #define CMDQ_REGISTER_MR_ACCESS_REMOTE_ATOMIC 0x8UL - #define CMDQ_REGISTER_MR_ACCESS_MW_BIND 0x10UL - #define CMDQ_REGISTER_MR_ACCESS_ZERO_BASED 0x20UL - __le16 log2_pbl_pg_size; - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_MASK 0x1fUL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_SFT 0 - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4K 0xcUL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_8K 0xdUL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_64K 0x10UL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_256K 0x12UL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1M 0x14UL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_2M 0x15UL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4M 0x16UL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G 0x1eUL - #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_LAST \ - CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G - #define CMDQ_REGISTER_MR_UNUSED11_MASK 0xffe0UL - #define CMDQ_REGISTER_MR_UNUSED11_SFT 5 - __le32 key; - __le64 pbl; - __le64 va; - __le64 mr_size; +/* creq_query_qp_resp_sb (size:832b/104B) */ +struct creq_query_qp_resp_sb { + u8 opcode; + #define CREQ_QUERY_QP_RESP_SB_OPCODE_QUERY_QP 0x4UL + #define CREQ_QUERY_QP_RESP_SB_OPCODE_LAST CREQ_QUERY_QP_RESP_SB_OPCODE_QUERY_QP + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + __le32 xid; + u8 en_sqd_async_notify_state; + #define CREQ_QUERY_QP_RESP_SB_STATE_MASK 0xfUL + #define CREQ_QUERY_QP_RESP_SB_STATE_SFT 0 + #define CREQ_QUERY_QP_RESP_SB_STATE_RESET 0x0UL + #define CREQ_QUERY_QP_RESP_SB_STATE_INIT 0x1UL + #define CREQ_QUERY_QP_RESP_SB_STATE_RTR 0x2UL + #define CREQ_QUERY_QP_RESP_SB_STATE_RTS 0x3UL + #define CREQ_QUERY_QP_RESP_SB_STATE_SQD 0x4UL + #define CREQ_QUERY_QP_RESP_SB_STATE_SQE 0x5UL + #define CREQ_QUERY_QP_RESP_SB_STATE_ERR 0x6UL + #define CREQ_QUERY_QP_RESP_SB_STATE_LAST CREQ_QUERY_QP_RESP_SB_STATE_ERR + #define CREQ_QUERY_QP_RESP_SB_EN_SQD_ASYNC_NOTIFY 0x10UL + #define CREQ_QUERY_QP_RESP_SB_UNUSED3_MASK 0xe0UL + #define CREQ_QUERY_QP_RESP_SB_UNUSED3_SFT 5 + u8 access; + #define \ + CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_ATOMIC_REMOTE_READ_REMOTE_WRITE_LOCAL_WRITE_MASK\ + 0xffUL + #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_ATOMIC_REMOTE_READ_REMOTE_WRITE_LOCAL_WRITE_SFT\ + 0 + #define CREQ_QUERY_QP_RESP_SB_ACCESS_LOCAL_WRITE 0x1UL + #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_WRITE 0x2UL + #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_READ 0x4UL + #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_ATOMIC 0x8UL + __le16 pkey; + __le32 qkey; + __le32 reserved32; + __le32 dgid[4]; + __le32 flow_label; + __le16 sgid_index; + u8 hop_limit; + u8 traffic_class; + __le16 dest_mac[3]; + __le16 path_mtu_dest_vlan_id; + #define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_MASK 0xfffUL + #define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_SFT 0 + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK 0xf000UL + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_SFT 12 + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_256 (0x0UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_512 (0x1UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_1024 (0x2UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_2048 (0x3UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_4096 (0x4UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_8192 (0x5UL << 12) + #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_LAST CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_8192 + u8 timeout; + u8 retry_cnt; + u8 rnr_retry; + u8 min_rnr_timer; + __le32 rq_psn; + __le32 sq_psn; + u8 max_rd_atomic; + u8 max_dest_rd_atomic; + u8 tos_dscp_tos_ecn; + #define CREQ_QUERY_QP_RESP_SB_TOS_ECN_MASK 0x3UL + #define CREQ_QUERY_QP_RESP_SB_TOS_ECN_SFT 0 + #define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_MASK 0xfcUL + #define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_SFT 2 + u8 enable_cc; + #define CREQ_QUERY_QP_RESP_SB_ENABLE_CC 0x1UL + __le32 sq_size; + __le32 rq_size; + __le16 sq_sge; + __le16 rq_sge; + __le32 max_inline_data; + __le32 dest_qp_id; + __le16 port_id; + u8 unused_0; + u8 stat_collection_id; + __le16 src_mac[3]; + __le16 vlan_pcp_vlan_dei_vlan_id; + #define CREQ_QUERY_QP_RESP_SB_VLAN_ID_MASK 0xfffUL + #define CREQ_QUERY_QP_RESP_SB_VLAN_ID_SFT 0 + #define CREQ_QUERY_QP_RESP_SB_VLAN_DEI 0x1000UL + #define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_MASK 0xe000UL + #define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_SFT 13 }; -/* Deregister MR command (24 bytes) */ -struct cmdq_deregister_mr { - u8 opcode; - #define CMDQ_DEREGISTER_MR_OPCODE_DEREGISTER_MR 0x10UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 lkey; - __le32 unused_0; -}; - -/* Add GID command (48 bytes) */ -struct cmdq_add_gid { - u8 opcode; - #define CMDQ_ADD_GID_OPCODE_ADD_GID 0x11UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __be32 gid[4]; - __be16 src_mac[3]; - __le16 vlan; - #define CMDQ_ADD_GID_VLAN_VLAN_ID_MASK 0xfffUL - #define CMDQ_ADD_GID_VLAN_VLAN_ID_SFT 0 - #define CMDQ_ADD_GID_VLAN_TPID_MASK 0x7000UL - #define CMDQ_ADD_GID_VLAN_TPID_SFT 12 - #define CMDQ_ADD_GID_VLAN_TPID_TPID_88A8 (0x0UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_8100 (0x1UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_9100 (0x2UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_9200 (0x3UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_9300 (0x4UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG1 (0x5UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG2 (0x6UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3 (0x7UL << 12) - #define CMDQ_ADD_GID_VLAN_TPID_LAST CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3 - #define CMDQ_ADD_GID_VLAN_VLAN_EN 0x8000UL - __le16 ipid; - __le16 stats_ctx; - #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_MASK 0x7fffUL - #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_SFT 0 - #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_VALID 0x8000UL - __le32 unused_0; -}; - -/* Delete GID command (24 bytes) */ -struct cmdq_delete_gid { - u8 opcode; - #define CMDQ_DELETE_GID_OPCODE_DELETE_GID 0x12UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le16 gid_index; - __le16 unused_0; - __le32 unused_1; -}; - -/* Modify GID command (48 bytes) */ -struct cmdq_modify_gid { - u8 opcode; - #define CMDQ_MODIFY_GID_OPCODE_MODIFY_GID 0x17UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __be32 gid[4]; - __be16 src_mac[3]; - __le16 vlan; - #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_MASK 0xfffUL - #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_SFT 0 - #define CMDQ_MODIFY_GID_VLAN_TPID_MASK 0x7000UL - #define CMDQ_MODIFY_GID_VLAN_TPID_SFT 12 - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_88A8 (0x0UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_8100 (0x1UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9100 (0x2UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9200 (0x3UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9300 (0x4UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG1 (0x5UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG2 (0x6UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3 (0x7UL << 12) - #define CMDQ_MODIFY_GID_VLAN_TPID_LAST \ - CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3 - #define CMDQ_MODIFY_GID_VLAN_VLAN_EN 0x8000UL - __le16 ipid; - __le16 gid_index; - __le16 stats_ctx; - #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_MASK 0x7fffUL - #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_SFT 0 - #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_VALID 0x8000UL - __le16 unused_0; -}; - -/* Query GID command (24 bytes) */ -struct cmdq_query_gid { - u8 opcode; - #define CMDQ_QUERY_GID_OPCODE_QUERY_GID 0x18UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le16 gid_index; - __le16 unused_0; - __le32 unused_1; -}; - -/* Create QP1 command (80 bytes) */ -struct cmdq_create_qp1 { - u8 opcode; - #define CMDQ_CREATE_QP1_OPCODE_CREATE_QP1 0x13UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 qp_handle; - __le32 qp_flags; - #define CMDQ_CREATE_QP1_QP_FLAGS_SRQ_USED 0x1UL - #define CMDQ_CREATE_QP1_QP_FLAGS_FORCE_COMPLETION 0x2UL - #define CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE 0x4UL - u8 type; - #define CMDQ_CREATE_QP1_TYPE_GSI 0x1UL - u8 sq_pg_size_sq_lvl; - #define CMDQ_CREATE_QP1_SQ_LVL_MASK 0xfUL - #define CMDQ_CREATE_QP1_SQ_LVL_SFT 0 - #define CMDQ_CREATE_QP1_SQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_QP1_SQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_QP1_SQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_SFT 4 - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 rq_pg_size_rq_lvl; - #define CMDQ_CREATE_QP1_RQ_LVL_MASK 0xfUL - #define CMDQ_CREATE_QP1_RQ_LVL_SFT 0 - #define CMDQ_CREATE_QP1_RQ_LVL_LVL_0 0x0UL - #define CMDQ_CREATE_QP1_RQ_LVL_LVL_1 0x1UL - #define CMDQ_CREATE_QP1_RQ_LVL_LVL_2 0x2UL - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_SFT 4 - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 unused_0; - __le32 dpi; - __le32 sq_size; - __le32 rq_size; - __le16 sq_fwo_sq_sge; - #define CMDQ_CREATE_QP1_SQ_SGE_MASK 0xfUL - #define CMDQ_CREATE_QP1_SQ_SGE_SFT 0 - #define CMDQ_CREATE_QP1_SQ_FWO_MASK 0xfff0UL - #define CMDQ_CREATE_QP1_SQ_FWO_SFT 4 - __le16 rq_fwo_rq_sge; - #define CMDQ_CREATE_QP1_RQ_SGE_MASK 0xfUL - #define CMDQ_CREATE_QP1_RQ_SGE_SFT 0 - #define CMDQ_CREATE_QP1_RQ_FWO_MASK 0xfff0UL - #define CMDQ_CREATE_QP1_RQ_FWO_SFT 4 - __le32 scq_cid; - __le32 rcq_cid; - __le32 srq_cid; - __le32 pd_id; - __le64 sq_pbl; - __le64 rq_pbl; -}; - -/* Destroy QP1 command (24 bytes) */ -struct cmdq_destroy_qp1 { - u8 opcode; - #define CMDQ_DESTROY_QP1_OPCODE_DESTROY_QP1 0x14UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 qp1_cid; - __le32 unused_0; -}; - -/* Create AH command (64 bytes) */ -struct cmdq_create_ah { - u8 opcode; - #define CMDQ_CREATE_AH_OPCODE_CREATE_AH 0x15UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le64 ah_handle; - __le32 dgid[4]; - u8 type; - #define CMDQ_CREATE_AH_TYPE_V1 0x0UL - #define CMDQ_CREATE_AH_TYPE_V2IPV4 0x2UL - #define CMDQ_CREATE_AH_TYPE_V2IPV6 0x3UL - u8 hop_limit; - __le16 sgid_index; - __le32 dest_vlan_id_flow_label; - #define CMDQ_CREATE_AH_FLOW_LABEL_MASK 0xfffffUL - #define CMDQ_CREATE_AH_FLOW_LABEL_SFT 0 - #define CMDQ_CREATE_AH_DEST_VLAN_ID_MASK 0xfff00000UL - #define CMDQ_CREATE_AH_DEST_VLAN_ID_SFT 20 - __le32 pd_id; - __le32 unused_0; - __le16 dest_mac[3]; - u8 traffic_class; - u8 unused_1; -}; - -/* Destroy AH command (24 bytes) */ -struct cmdq_destroy_ah { - u8 opcode; - #define CMDQ_DESTROY_AH_OPCODE_DESTROY_AH 0x16UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 ah_cid; - __le32 unused_0; -}; - -/* Initialize Firmware command (112 bytes) */ -struct cmdq_initialize_fw { - u8 opcode; - #define CMDQ_INITIALIZE_FW_OPCODE_INITIALIZE_FW 0x80UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - u8 qpc_pg_size_qpc_lvl; - #define CMDQ_INITIALIZE_FW_QPC_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_QPC_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_QPC_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_QPC_PG_SIZE_PG_1G (0x5UL << 4) - u8 mrw_pg_size_mrw_lvl; - #define CMDQ_INITIALIZE_FW_MRW_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_MRW_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_MRW_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_MRW_PG_SIZE_PG_1G (0x5UL << 4) - u8 srq_pg_size_srq_lvl; - #define CMDQ_INITIALIZE_FW_SRQ_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_SRQ_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_SRQ_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_SRQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 cq_pg_size_cq_lvl; - #define CMDQ_INITIALIZE_FW_CQ_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_CQ_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_CQ_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_CQ_PG_SIZE_PG_1G (0x5UL << 4) - u8 tqm_pg_size_tqm_lvl; - #define CMDQ_INITIALIZE_FW_TQM_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_TQM_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_TQM_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_TQM_PG_SIZE_PG_1G (0x5UL << 4) - u8 tim_pg_size_tim_lvl; - #define CMDQ_INITIALIZE_FW_TIM_LVL_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_TIM_LVL_SFT 0 - #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_0 0x0UL - #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_1 0x1UL - #define CMDQ_INITIALIZE_FW_TIM_LVL_LVL_2 0x2UL - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_MASK 0xf0UL - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_SFT 4 - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_4K (0x0UL << 4) - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8K (0x1UL << 4) - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_64K (0x2UL << 4) - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_2M (0x3UL << 4) - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_8M (0x4UL << 4) - #define CMDQ_INITIALIZE_FW_TIM_PG_SIZE_PG_1G (0x5UL << 4) - /* This value is (log-base-2-of-DBR-page-size - 12). - * 0 for 4KB. HW supported values are enumerated below. - */ - __le16 log2_dbr_pg_size; - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_MASK 0xfUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_SFT 0 - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4K 0x0UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8K 0x1UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16K 0x2UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32K 0x3UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64K 0x4UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128K 0x5UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_256K 0x6UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_512K 0x7UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_1M 0x8UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_2M 0x9UL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_4M 0xaUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_8M 0xbUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_16M 0xcUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_32M 0xdUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_64M 0xeUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M 0xfUL - #define CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_LAST \ - CMDQ_INITIALIZE_FW_LOG2_DBR_PG_SIZE_PG_128M - __le64 qpc_page_dir; - __le64 mrw_page_dir; - __le64 srq_page_dir; - __le64 cq_page_dir; - __le64 tqm_page_dir; - __le64 tim_page_dir; - __le32 number_of_qp; - __le32 number_of_mrw; - __le32 number_of_srq; - __le32 number_of_cq; - __le32 max_qp_per_vf; - __le32 max_mrw_per_vf; - __le32 max_srq_per_vf; - __le32 max_cq_per_vf; - __le32 max_gid_per_vf; - __le32 stat_ctx_id; -}; - -/* De-initialize Firmware command (16 bytes) */ -struct cmdq_deinitialize_fw { - u8 opcode; - #define CMDQ_DEINITIALIZE_FW_OPCODE_DEINITIALIZE_FW 0x81UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; -}; - -/* Stop function command (16 bytes) */ -struct cmdq_stop_func { - u8 opcode; - #define CMDQ_STOP_FUNC_OPCODE_STOP_FUNC 0x82UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; -}; - -/* Query function command (16 bytes) */ -struct cmdq_query_func { - u8 opcode; - #define CMDQ_QUERY_FUNC_OPCODE_QUERY_FUNC 0x83UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; +/* cmdq_query_qp_extend (size:192b/24B) */ +struct cmdq_query_qp_extend { + u8 opcode; + #define CMDQ_QUERY_QP_EXTEND_OPCODE_QUERY_QP_EXTEND 0x91UL + #define CMDQ_QUERY_QP_EXTEND_OPCODE_LAST CMDQ_QUERY_QP_EXTEND_OPCODE_QUERY_QP_EXTEND + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 num_qps; + __le64 resp_addr; + __le32 function_id; + #define CMDQ_QUERY_QP_EXTEND_PF_NUM_MASK 0xffUL + #define CMDQ_QUERY_QP_EXTEND_PF_NUM_SFT 0 + #define CMDQ_QUERY_QP_EXTEND_VF_NUM_MASK 0xffff00UL + #define CMDQ_QUERY_QP_EXTEND_VF_NUM_SFT 8 + #define CMDQ_QUERY_QP_EXTEND_VF_VALID 0x1000000UL + __le32 current_index; }; -/* Set function resources command (16 bytes) */ -struct cmdq_set_func_resources { - u8 opcode; - #define CMDQ_SET_FUNC_RESOURCES_OPCODE_SET_FUNC_RESOURCES 0x84UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 number_of_qp; - __le32 number_of_mrw; - __le32 number_of_srq; - __le32 number_of_cq; - __le32 max_qp_per_vf; - __le32 max_mrw_per_vf; - __le32 max_srq_per_vf; - __le32 max_cq_per_vf; - __le32 max_gid_per_vf; - __le32 stat_ctx_id; -}; - -/* Read hardware resource context command (24 bytes) */ -struct cmdq_read_context { - u8 opcode; - #define CMDQ_READ_CONTEXT_OPCODE_READ_CONTEXT 0x85UL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le32 type_xid; - #define CMDQ_READ_CONTEXT_XID_MASK 0xffffffUL - #define CMDQ_READ_CONTEXT_XID_SFT 0 - #define CMDQ_READ_CONTEXT_TYPE_MASK 0xff000000UL - #define CMDQ_READ_CONTEXT_TYPE_SFT 24 - #define CMDQ_READ_CONTEXT_TYPE_QPC (0x0UL << 24) - #define CMDQ_READ_CONTEXT_TYPE_CQ (0x1UL << 24) - #define CMDQ_READ_CONTEXT_TYPE_MRW (0x2UL << 24) - #define CMDQ_READ_CONTEXT_TYPE_SRQ (0x3UL << 24) - __le32 unused_0; -}; - -/* Map TC to COS. Can only be issued from a PF (24 bytes) */ -struct cmdq_map_tc_to_cos { - u8 opcode; - #define CMDQ_MAP_TC_TO_COS_OPCODE_MAP_TC_TO_COS 0x8aUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; - __le16 cos0; - #define CMDQ_MAP_TC_TO_COS_COS0_NO_CHANGE 0xffffUL - __le16 cos1; - #define CMDQ_MAP_TC_TO_COS_COS1_DISABLE 0x8000UL - #define CMDQ_MAP_TC_TO_COS_COS1_NO_CHANGE 0xffffUL - __le32 unused_0; -}; - -/* Query version command (16 bytes) */ -struct cmdq_query_version { - u8 opcode; - #define CMDQ_QUERY_VERSION_OPCODE_QUERY_VERSION 0x8bUL - u8 cmd_size; - __le16 flags; - __le16 cookie; - u8 resp_size; - u8 reserved8; - __le64 resp_addr; -}; - -/* Command-Response Event Queue (CREQ) Structures */ -/* Base CREQ Record (16 bytes) */ -struct creq_base { - u8 type; - #define CREQ_BASE_TYPE_MASK 0x3fUL - #define CREQ_BASE_TYPE_SFT 0 - #define CREQ_BASE_TYPE_QP_EVENT 0x38UL - #define CREQ_BASE_TYPE_FUNC_EVENT 0x3aUL - #define CREQ_BASE_RESERVED2_MASK 0xc0UL - #define CREQ_BASE_RESERVED2_SFT 6 - u8 reserved56[7]; - u8 v; - #define CREQ_BASE_V 0x1UL - #define CREQ_BASE_RESERVED7_MASK 0xfeUL - #define CREQ_BASE_RESERVED7_SFT 1 - u8 event; - __le16 reserved48[3]; -}; - -/* RoCE Function Async Event Notification (16 bytes) */ -struct creq_func_event { - u8 type; - #define CREQ_FUNC_EVENT_TYPE_MASK 0x3fUL - #define CREQ_FUNC_EVENT_TYPE_SFT 0 - #define CREQ_FUNC_EVENT_TYPE_FUNC_EVENT 0x3aUL - #define CREQ_FUNC_EVENT_RESERVED2_MASK 0xc0UL - #define CREQ_FUNC_EVENT_RESERVED2_SFT 6 - u8 reserved56[7]; - u8 v; - #define CREQ_FUNC_EVENT_V 0x1UL - #define CREQ_FUNC_EVENT_RESERVED7_MASK 0xfeUL - #define CREQ_FUNC_EVENT_RESERVED7_SFT 1 - u8 event; - #define CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR 0x1UL - #define CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR 0x2UL - #define CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR 0x3UL - #define CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR 0x4UL - #define CREQ_FUNC_EVENT_EVENT_CQ_ERROR 0x5UL - #define CREQ_FUNC_EVENT_EVENT_TQM_ERROR 0x6UL - #define CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR 0x7UL - #define CREQ_FUNC_EVENT_EVENT_CFCS_ERROR 0x8UL - #define CREQ_FUNC_EVENT_EVENT_CFCC_ERROR 0x9UL - #define CREQ_FUNC_EVENT_EVENT_CFCM_ERROR 0xaUL - #define CREQ_FUNC_EVENT_EVENT_TIM_ERROR 0xbUL - #define CREQ_FUNC_EVENT_EVENT_VF_COMM_REQUEST 0x80UL - #define CREQ_FUNC_EVENT_EVENT_RESOURCE_EXHAUSTED 0x81UL - __le16 reserved48[3]; -}; - -/* RoCE Slowpath Command Completion (16 bytes) */ -struct creq_qp_event { - u8 type; - #define CREQ_QP_EVENT_TYPE_MASK 0x3fUL - #define CREQ_QP_EVENT_TYPE_SFT 0 - #define CREQ_QP_EVENT_TYPE_QP_EVENT 0x38UL - #define CREQ_QP_EVENT_RESERVED2_MASK 0xc0UL - #define CREQ_QP_EVENT_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_QP_EVENT_V 0x1UL - #define CREQ_QP_EVENT_RESERVED7_MASK 0xfeUL - #define CREQ_QP_EVENT_RESERVED7_SFT 1 - u8 event; - #define CREQ_QP_EVENT_EVENT_CREATE_QP 0x1UL - #define CREQ_QP_EVENT_EVENT_DESTROY_QP 0x2UL - #define CREQ_QP_EVENT_EVENT_MODIFY_QP 0x3UL - #define CREQ_QP_EVENT_EVENT_QUERY_QP 0x4UL - #define CREQ_QP_EVENT_EVENT_CREATE_SRQ 0x5UL - #define CREQ_QP_EVENT_EVENT_DESTROY_SRQ 0x6UL - #define CREQ_QP_EVENT_EVENT_QUERY_SRQ 0x8UL - #define CREQ_QP_EVENT_EVENT_CREATE_CQ 0x9UL - #define CREQ_QP_EVENT_EVENT_DESTROY_CQ 0xaUL - #define CREQ_QP_EVENT_EVENT_RESIZE_CQ 0xcUL - #define CREQ_QP_EVENT_EVENT_ALLOCATE_MRW 0xdUL - #define CREQ_QP_EVENT_EVENT_DEALLOCATE_KEY 0xeUL - #define CREQ_QP_EVENT_EVENT_REGISTER_MR 0xfUL - #define CREQ_QP_EVENT_EVENT_DEREGISTER_MR 0x10UL - #define CREQ_QP_EVENT_EVENT_ADD_GID 0x11UL - #define CREQ_QP_EVENT_EVENT_DELETE_GID 0x12UL - #define CREQ_QP_EVENT_EVENT_MODIFY_GID 0x17UL - #define CREQ_QP_EVENT_EVENT_QUERY_GID 0x18UL - #define CREQ_QP_EVENT_EVENT_CREATE_QP1 0x13UL - #define CREQ_QP_EVENT_EVENT_DESTROY_QP1 0x14UL - #define CREQ_QP_EVENT_EVENT_CREATE_AH 0x15UL - #define CREQ_QP_EVENT_EVENT_DESTROY_AH 0x16UL - #define CREQ_QP_EVENT_EVENT_INITIALIZE_FW 0x80UL - #define CREQ_QP_EVENT_EVENT_DEINITIALIZE_FW 0x81UL - #define CREQ_QP_EVENT_EVENT_STOP_FUNC 0x82UL - #define CREQ_QP_EVENT_EVENT_QUERY_FUNC 0x83UL - #define CREQ_QP_EVENT_EVENT_SET_FUNC_RESOURCES 0x84UL - #define CREQ_QP_EVENT_EVENT_MAP_TC_TO_COS 0x8aUL - #define CREQ_QP_EVENT_EVENT_QUERY_VERSION 0x8bUL - #define CREQ_QP_EVENT_EVENT_MODIFY_CC 0x8cUL - #define CREQ_QP_EVENT_EVENT_QUERY_CC 0x8dUL - #define CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION 0xc0UL - __le16 reserved48[3]; -}; - -/* Create QP command response (16 bytes) */ -struct creq_create_qp_resp { - u8 type; - #define CREQ_CREATE_QP_RESP_TYPE_MASK 0x3fUL - #define CREQ_CREATE_QP_RESP_TYPE_SFT 0 - #define CREQ_CREATE_QP_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_CREATE_QP_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_CREATE_QP_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_CREATE_QP_RESP_V 0x1UL - #define CREQ_CREATE_QP_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_CREATE_QP_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_CREATE_QP_RESP_EVENT_CREATE_QP 0x1UL - __le16 reserved48[3]; -}; - -/* Destroy QP command response (16 bytes) */ -struct creq_destroy_qp_resp { - u8 type; - #define CREQ_DESTROY_QP_RESP_TYPE_MASK 0x3fUL - #define CREQ_DESTROY_QP_RESP_TYPE_SFT 0 - #define CREQ_DESTROY_QP_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DESTROY_QP_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DESTROY_QP_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DESTROY_QP_RESP_V 0x1UL - #define CREQ_DESTROY_QP_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DESTROY_QP_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DESTROY_QP_RESP_EVENT_DESTROY_QP 0x2UL - __le16 reserved48[3]; -}; - -/* Modify QP command response (16 bytes) */ -struct creq_modify_qp_resp { - u8 type; - #define CREQ_MODIFY_QP_RESP_TYPE_MASK 0x3fUL - #define CREQ_MODIFY_QP_RESP_TYPE_SFT 0 - #define CREQ_MODIFY_QP_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_MODIFY_QP_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_MODIFY_QP_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_MODIFY_QP_RESP_V 0x1UL - #define CREQ_MODIFY_QP_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_MODIFY_QP_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_MODIFY_QP_RESP_EVENT_MODIFY_QP 0x3UL - __le16 reserved48[3]; -}; - -/* cmdq_query_roce_stats (size:128b/16B) */ -struct cmdq_query_roce_stats { +/* creq_query_qp_extend_resp (size:128b/16B) */ +struct creq_query_qp_extend_resp { + u8 type; + #define CREQ_QUERY_QP_EXTEND_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_QP_EXTEND_RESP_TYPE_SFT 0 + #define CREQ_QUERY_QP_EXTEND_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_QP_EXTEND_RESP_TYPE_LAST CREQ_QUERY_QP_EXTEND_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_QP_EXTEND_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_QP_EXTEND_RESP_EVENT_QUERY_QP_EXTEND 0x91UL + #define CREQ_QUERY_QP_EXTEND_RESP_EVENT_LAST CREQ_QUERY_QP_EXTEND_RESP_EVENT_QUERY_QP_EXTEND + __le16 reserved16; + __le32 current_index; +}; + +/* creq_query_qp_extend_resp_sb (size:384b/48B) */ +struct creq_query_qp_extend_resp_sb { u8 opcode; - #define CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS 0x8eUL - #define CMDQ_QUERY_ROCE_STATS_OPCODE_LAST \ - CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS + #define CREQ_QUERY_QP_EXTEND_RESP_SB_OPCODE_QUERY_QP_EXTEND 0x91UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_OPCODE_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_OPCODE_QUERY_QP_EXTEND + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + __le32 xid; + u8 state; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_MASK 0xfUL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_SFT 0 + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_RESET 0x0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_INIT 0x1UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_RTR 0x2UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_RTS 0x3UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_SQD 0x4UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_SQE 0x5UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_ERR 0x6UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_LAST CREQ_QUERY_QP_EXTEND_RESP_SB_STATE_ERR + #define CREQ_QUERY_QP_EXTEND_RESP_SB_UNUSED4_MASK 0xf0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_UNUSED4_SFT 4 + u8 reserved_8; + __le16 port_id; + __le32 qkey; + __le16 sgid_index; + u8 network_type; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_NETWORK_TYPE_ROCEV1 0x0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_NETWORK_TYPE_ROCEV2_IPV4 0x2UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_NETWORK_TYPE_ROCEV2_IPV6 0x3UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_NETWORK_TYPE_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_NETWORK_TYPE_ROCEV2_IPV6 + u8 unused_0; + __le32 dgid[4]; + __le32 dest_qp_id; + u8 stat_collection_id; + u8 reservred_8; + __le16 reserved_16; +}; + +/* creq_query_qp_extend_resp_sb_tlv (size:512b/64B) */ +struct creq_query_qp_extend_resp_sb_tlv { + __le16 cmd_discr; + u8 reserved_8b; + u8 tlv_flags; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_MORE 0x1UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_MORE_LAST 0x0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_MORE_NOT_LAST 0x1UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_REQUIRED 0x2UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_REQUIRED_NO (0x0UL << 1) + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES (0x1UL << 1) + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_REQUIRED_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES + __le16 tlv_type; + __le16 length; + u8 total_size; + u8 reserved56[7]; + u8 opcode; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_OPCODE_QUERY_QP_EXTEND 0x91UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_OPCODE_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_OPCODE_QUERY_QP_EXTEND + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + __le32 xid; + u8 state; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_MASK 0xfUL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_SFT 0 + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_RESET 0x0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_INIT 0x1UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_RTR 0x2UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_RTS 0x3UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_SQD 0x4UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_SQE 0x5UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_ERR 0x6UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_STATE_ERR + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_UNUSED4_MASK 0xf0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_UNUSED4_SFT 4 + u8 reserved_8; + __le16 port_id; + __le32 qkey; + __le16 sgid_index; + u8 network_type; + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_NETWORK_TYPE_ROCEV1 0x0UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_NETWORK_TYPE_ROCEV2_IPV4 0x2UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_NETWORK_TYPE_ROCEV2_IPV6 0x3UL + #define CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_NETWORK_TYPE_LAST \ + CREQ_QUERY_QP_EXTEND_RESP_SB_TLV_NETWORK_TYPE_ROCEV2_IPV6 + u8 unused_0; + __le32 dgid[4]; + __le32 dest_qp_id; + u8 stat_collection_id; + u8 reservred_8; + __le16 reserved_16; +}; + +/* cmdq_create_srq (size:384b/48B) */ +struct cmdq_create_srq { + u8 opcode; + #define CMDQ_CREATE_SRQ_OPCODE_CREATE_SRQ 0x5UL + #define CMDQ_CREATE_SRQ_OPCODE_LAST CMDQ_CREATE_SRQ_OPCODE_CREATE_SRQ u8 cmd_size; __le16 flags; __le16 cookie; u8 resp_size; u8 reserved8; __le64 resp_addr; + __le64 srq_handle; + __le16 pg_size_lvl; + #define CMDQ_CREATE_SRQ_LVL_MASK 0x3UL + #define CMDQ_CREATE_SRQ_LVL_SFT 0 + #define CMDQ_CREATE_SRQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_SRQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_SRQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_SRQ_LVL_LAST CMDQ_CREATE_SRQ_LVL_LVL_2 + #define CMDQ_CREATE_SRQ_PG_SIZE_MASK 0x1cUL + #define CMDQ_CREATE_SRQ_PG_SIZE_SFT 2 + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_4K (0x0UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_8K (0x1UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_64K (0x2UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_2M (0x3UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_8M (0x4UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_PG_1G (0x5UL << 2) + #define CMDQ_CREATE_SRQ_PG_SIZE_LAST CMDQ_CREATE_SRQ_PG_SIZE_PG_1G + #define CMDQ_CREATE_SRQ_UNUSED11_MASK 0xffe0UL + #define CMDQ_CREATE_SRQ_UNUSED11_SFT 5 + __le16 eventq_id; + #define CMDQ_CREATE_SRQ_EVENTQ_ID_MASK 0xfffUL + #define CMDQ_CREATE_SRQ_EVENTQ_ID_SFT 0 + #define CMDQ_CREATE_SRQ_UNUSED4_MASK 0xf000UL + #define CMDQ_CREATE_SRQ_UNUSED4_SFT 12 + __le16 srq_size; + __le16 srq_fwo; + __le32 dpi; + __le32 pd_id; + __le64 pbl; }; -/* Query QP command response (16 bytes) */ -struct creq_query_qp_resp { - u8 type; - #define CREQ_QUERY_QP_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_QP_RESP_TYPE_SFT 0 - #define CREQ_QUERY_QP_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_QP_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_QP_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_QP_RESP_V 0x1UL - #define CREQ_QUERY_QP_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_QP_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_QP_RESP_EVENT_QUERY_QP 0x4UL - __le16 reserved48[3]; -}; - -/* Query QP command response side buffer structure (104 bytes) */ -struct creq_query_qp_resp_sb { - u8 opcode; - #define CREQ_QUERY_QP_RESP_SB_OPCODE_QUERY_QP 0x4UL - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 reserved8; - __le32 xid; - u8 en_sqd_async_notify_state; - #define CREQ_QUERY_QP_RESP_SB_STATE_MASK 0xfUL - #define CREQ_QUERY_QP_RESP_SB_STATE_SFT 0 - #define CREQ_QUERY_QP_RESP_SB_STATE_RESET 0x0UL - #define CREQ_QUERY_QP_RESP_SB_STATE_INIT 0x1UL - #define CREQ_QUERY_QP_RESP_SB_STATE_RTR 0x2UL - #define CREQ_QUERY_QP_RESP_SB_STATE_RTS 0x3UL - #define CREQ_QUERY_QP_RESP_SB_STATE_SQD 0x4UL - #define CREQ_QUERY_QP_RESP_SB_STATE_SQE 0x5UL - #define CREQ_QUERY_QP_RESP_SB_STATE_ERR 0x6UL - #define CREQ_QUERY_QP_RESP_SB_EN_SQD_ASYNC_NOTIFY 0x10UL - u8 access; - #define CREQ_QUERY_QP_RESP_SB_ACCESS_LOCAL_WRITE 0x1UL - #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_WRITE 0x2UL - #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_READ 0x4UL - #define CREQ_QUERY_QP_RESP_SB_ACCESS_REMOTE_ATOMIC 0x8UL - __le16 pkey; - __le32 qkey; - __le32 reserved32; - __le32 dgid[4]; - __le32 flow_label; - __le16 sgid_index; - u8 hop_limit; - u8 traffic_class; - __le16 dest_mac[3]; - __le16 path_mtu_dest_vlan_id; - #define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_MASK 0xfffUL - #define CREQ_QUERY_QP_RESP_SB_DEST_VLAN_ID_SFT 0 - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MASK 0xf000UL - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_SFT 12 - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_256 (0x0UL << 12) - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_512 (0x1UL << 12) - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_1024 (0x2UL << 12) - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_2048 (0x3UL << 12) - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_4096 (0x4UL << 12) - #define CREQ_QUERY_QP_RESP_SB_PATH_MTU_MTU_8192 (0x5UL << 12) - u8 timeout; - u8 retry_cnt; - u8 rnr_retry; - u8 min_rnr_timer; - __le32 rq_psn; - __le32 sq_psn; - u8 max_rd_atomic; - u8 max_dest_rd_atomic; - u8 tos_dscp_tos_ecn; - #define CREQ_QUERY_QP_RESP_SB_TOS_ECN_MASK 0x3UL - #define CREQ_QUERY_QP_RESP_SB_TOS_ECN_SFT 0 - #define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_MASK 0xfcUL - #define CREQ_QUERY_QP_RESP_SB_TOS_DSCP_SFT 2 - u8 enable_cc; - #define CREQ_QUERY_QP_RESP_SB_ENABLE_CC 0x1UL - #define CREQ_QUERY_QP_RESP_SB_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_QP_RESP_SB_RESERVED7_SFT 1 - __le32 sq_size; - __le32 rq_size; - __le16 sq_sge; - __le16 rq_sge; - __le32 max_inline_data; - __le32 dest_qp_id; - __le32 unused_1; - __le16 src_mac[3]; - __le16 vlan_pcp_vlan_dei_vlan_id; - #define CREQ_QUERY_QP_RESP_SB_VLAN_ID_MASK 0xfffUL - #define CREQ_QUERY_QP_RESP_SB_VLAN_ID_SFT 0 - #define CREQ_QUERY_QP_RESP_SB_VLAN_DEI 0x1000UL - #define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_MASK 0xe000UL - #define CREQ_QUERY_QP_RESP_SB_VLAN_PCP_SFT 13 -}; - -/* Create SRQ command response (16 bytes) */ +/* creq_create_srq_resp (size:128b/16B) */ struct creq_create_srq_resp { - u8 type; - #define CREQ_CREATE_SRQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_CREATE_SRQ_RESP_TYPE_SFT 0 - #define CREQ_CREATE_SRQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_CREATE_SRQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_CREATE_SRQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_CREATE_SRQ_RESP_V 0x1UL - #define CREQ_CREATE_SRQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_CREATE_SRQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_CREATE_SRQ_RESP_EVENT_CREATE_SRQ 0x5UL - __le16 reserved48[3]; -}; - -/* Destroy SRQ command response (16 bytes) */ + u8 type; + #define CREQ_CREATE_SRQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_CREATE_SRQ_RESP_TYPE_SFT 0 + #define CREQ_CREATE_SRQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_CREATE_SRQ_RESP_TYPE_LAST CREQ_CREATE_SRQ_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_CREATE_SRQ_RESP_V 0x1UL + u8 event; + #define CREQ_CREATE_SRQ_RESP_EVENT_CREATE_SRQ 0x5UL + #define CREQ_CREATE_SRQ_RESP_EVENT_LAST CREQ_CREATE_SRQ_RESP_EVENT_CREATE_SRQ + u8 reserved48[6]; +}; + +/* cmdq_destroy_srq (size:192b/24B) */ +struct cmdq_destroy_srq { + u8 opcode; + #define CMDQ_DESTROY_SRQ_OPCODE_DESTROY_SRQ 0x6UL + #define CMDQ_DESTROY_SRQ_OPCODE_LAST CMDQ_DESTROY_SRQ_OPCODE_DESTROY_SRQ + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 srq_cid; + __le32 unused_0; +}; + +/* creq_destroy_srq_resp (size:128b/16B) */ struct creq_destroy_srq_resp { - u8 type; - #define CREQ_DESTROY_SRQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_DESTROY_SRQ_RESP_TYPE_SFT 0 - #define CREQ_DESTROY_SRQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DESTROY_SRQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DESTROY_SRQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DESTROY_SRQ_RESP_V 0x1UL - #define CREQ_DESTROY_SRQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DESTROY_SRQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DESTROY_SRQ_RESP_EVENT_DESTROY_SRQ 0x6UL - __le16 enable_for_arm[3]; - #define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_MASK 0x30000UL - #define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_SFT 16 - #define CREQ_DESTROY_SRQ_RESP_RESERVED46_MASK 0xfffc0000UL - #define CREQ_DESTROY_SRQ_RESP_RESERVED46_SFT 18 -}; - -/* Query SRQ command response (16 bytes) */ -struct creq_query_srq_resp { - u8 type; - #define CREQ_QUERY_SRQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_SRQ_RESP_TYPE_SFT 0 - #define CREQ_QUERY_SRQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_SRQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_SRQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_SRQ_RESP_V 0x1UL - #define CREQ_QUERY_SRQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_SRQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_SRQ_RESP_EVENT_QUERY_SRQ 0x8UL - __le16 reserved48[3]; -}; - -/* Query SRQ command response side buffer structure (24 bytes) */ -struct creq_query_srq_resp_sb { - u8 opcode; - #define CREQ_QUERY_SRQ_RESP_SB_OPCODE_QUERY_SRQ 0x8UL - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 reserved8; - __le32 xid; - __le16 srq_limit; - __le16 reserved16; - __le32 data[4]; -}; - -/* Create CQ command Response (16 bytes) */ -struct creq_create_cq_resp { - u8 type; - #define CREQ_CREATE_CQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_CREATE_CQ_RESP_TYPE_SFT 0 - #define CREQ_CREATE_CQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_CREATE_CQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_CREATE_CQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_CREATE_CQ_RESP_V 0x1UL - #define CREQ_CREATE_CQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_CREATE_CQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_CREATE_CQ_RESP_EVENT_CREATE_CQ 0x9UL - __le16 reserved48[3]; -}; - -/* Destroy CQ command response (16 bytes) */ -struct creq_destroy_cq_resp { - u8 type; - #define CREQ_DESTROY_CQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_DESTROY_CQ_RESP_TYPE_SFT 0 - #define CREQ_DESTROY_CQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DESTROY_CQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DESTROY_CQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DESTROY_CQ_RESP_V 0x1UL - #define CREQ_DESTROY_CQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DESTROY_CQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DESTROY_CQ_RESP_EVENT_DESTROY_CQ 0xaUL - __le16 cq_arm_lvl; - #define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_MASK 0x3UL - #define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_SFT 0 - #define CREQ_DESTROY_CQ_RESP_RESERVED14_MASK 0xfffcUL - #define CREQ_DESTROY_CQ_RESP_RESERVED14_SFT 2 - __le16 total_cnq_events; - __le16 reserved16; -}; - -/* Resize CQ command response (16 bytes) */ -struct creq_resize_cq_resp { - u8 type; - #define CREQ_RESIZE_CQ_RESP_TYPE_MASK 0x3fUL - #define CREQ_RESIZE_CQ_RESP_TYPE_SFT 0 - #define CREQ_RESIZE_CQ_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_RESIZE_CQ_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_RESIZE_CQ_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_RESIZE_CQ_RESP_V 0x1UL - #define CREQ_RESIZE_CQ_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_RESIZE_CQ_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_RESIZE_CQ_RESP_EVENT_RESIZE_CQ 0xcUL - __le16 reserved48[3]; -}; - -/* Allocate MRW command response (16 bytes) */ -struct creq_allocate_mrw_resp { - u8 type; - #define CREQ_ALLOCATE_MRW_RESP_TYPE_MASK 0x3fUL - #define CREQ_ALLOCATE_MRW_RESP_TYPE_SFT 0 - #define CREQ_ALLOCATE_MRW_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_ALLOCATE_MRW_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_ALLOCATE_MRW_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_ALLOCATE_MRW_RESP_V 0x1UL - #define CREQ_ALLOCATE_MRW_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_ALLOCATE_MRW_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_ALLOCATE_MRW_RESP_EVENT_ALLOCATE_MRW 0xdUL - __le16 reserved48[3]; -}; - -/* De-allocate key command response (16 bytes) */ -struct creq_deallocate_key_resp { - u8 type; - #define CREQ_DEALLOCATE_KEY_RESP_TYPE_MASK 0x3fUL - #define CREQ_DEALLOCATE_KEY_RESP_TYPE_SFT 0 - #define CREQ_DEALLOCATE_KEY_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DEALLOCATE_KEY_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DEALLOCATE_KEY_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DEALLOCATE_KEY_RESP_V 0x1UL - #define CREQ_DEALLOCATE_KEY_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DEALLOCATE_KEY_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DEALLOCATE_KEY_RESP_EVENT_DEALLOCATE_KEY 0xeUL - __le16 reserved16; - __le32 bound_window_info; -}; - -/* Register MR command response (16 bytes) */ -struct creq_register_mr_resp { - u8 type; - #define CREQ_REGISTER_MR_RESP_TYPE_MASK 0x3fUL - #define CREQ_REGISTER_MR_RESP_TYPE_SFT 0 - #define CREQ_REGISTER_MR_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_REGISTER_MR_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_REGISTER_MR_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_REGISTER_MR_RESP_V 0x1UL - #define CREQ_REGISTER_MR_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_REGISTER_MR_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_REGISTER_MR_RESP_EVENT_REGISTER_MR 0xfUL - __le16 reserved48[3]; -}; - -/* Deregister MR command response (16 bytes) */ -struct creq_deregister_mr_resp { - u8 type; - #define CREQ_DEREGISTER_MR_RESP_TYPE_MASK 0x3fUL - #define CREQ_DEREGISTER_MR_RESP_TYPE_SFT 0 - #define CREQ_DEREGISTER_MR_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DEREGISTER_MR_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DEREGISTER_MR_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DEREGISTER_MR_RESP_V 0x1UL - #define CREQ_DEREGISTER_MR_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DEREGISTER_MR_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DEREGISTER_MR_RESP_EVENT_DEREGISTER_MR 0x10UL - __le16 reserved16; - __le32 bound_windows; -}; - -/* Add GID command response (16 bytes) */ -struct creq_add_gid_resp { - u8 type; - #define CREQ_ADD_GID_RESP_TYPE_MASK 0x3fUL - #define CREQ_ADD_GID_RESP_TYPE_SFT 0 - #define CREQ_ADD_GID_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_ADD_GID_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_ADD_GID_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_ADD_GID_RESP_V 0x1UL - #define CREQ_ADD_GID_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_ADD_GID_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_ADD_GID_RESP_EVENT_ADD_GID 0x11UL - __le16 reserved48[3]; -}; - -/* Delete GID command response (16 bytes) */ -struct creq_delete_gid_resp { - u8 type; - #define CREQ_DELETE_GID_RESP_TYPE_MASK 0x3fUL - #define CREQ_DELETE_GID_RESP_TYPE_SFT 0 - #define CREQ_DELETE_GID_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DELETE_GID_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DELETE_GID_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DELETE_GID_RESP_V 0x1UL - #define CREQ_DELETE_GID_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DELETE_GID_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DELETE_GID_RESP_EVENT_DELETE_GID 0x12UL - __le16 reserved48[3]; -}; - -/* Modify GID command response (16 bytes) */ -struct creq_modify_gid_resp { - u8 type; - #define CREQ_MODIFY_GID_RESP_TYPE_MASK 0x3fUL - #define CREQ_MODIFY_GID_RESP_TYPE_SFT 0 - #define CREQ_MODIFY_GID_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_MODIFY_GID_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_MODIFY_GID_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_MODIFY_GID_RESP_V 0x1UL - #define CREQ_MODIFY_GID_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_MODIFY_GID_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_MODIFY_GID_RESP_EVENT_ADD_GID 0x11UL - __le16 reserved48[3]; -}; - -/* Query GID command response (16 bytes) */ -struct creq_query_gid_resp { - u8 type; - #define CREQ_QUERY_GID_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_GID_RESP_TYPE_SFT 0 - #define CREQ_QUERY_GID_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_GID_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_GID_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_GID_RESP_V 0x1UL - #define CREQ_QUERY_GID_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_GID_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_GID_RESP_EVENT_QUERY_GID 0x18UL - __le16 reserved48[3]; -}; - -/* Query GID command response side buffer structure (40 bytes) */ -struct creq_query_gid_resp_sb { - u8 opcode; - #define CREQ_QUERY_GID_RESP_SB_OPCODE_QUERY_GID 0x18UL - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 reserved8; - __le32 gid[4]; - __le16 src_mac[3]; - __le16 vlan; - #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_MASK 0xfffUL - #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_SFT 0 - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_MASK 0x7000UL - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_SFT 12 - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_88A8 (0x0UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_8100 (0x1UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9100 (0x2UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9200 (0x3UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9300 (0x4UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG1 (0x5UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG2 (0x6UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3 (0x7UL << 12) - #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_LAST \ - CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3 - #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_EN 0x8000UL - __le16 ipid; - __le16 gid_index; - __le32 unused_0; -}; - -/* Create QP1 command response (16 bytes) */ -struct creq_create_qp1_resp { - u8 type; - #define CREQ_CREATE_QP1_RESP_TYPE_MASK 0x3fUL - #define CREQ_CREATE_QP1_RESP_TYPE_SFT 0 - #define CREQ_CREATE_QP1_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_CREATE_QP1_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_CREATE_QP1_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_CREATE_QP1_RESP_V 0x1UL - #define CREQ_CREATE_QP1_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_CREATE_QP1_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_CREATE_QP1_RESP_EVENT_CREATE_QP1 0x13UL - __le16 reserved48[3]; -}; - -/* Destroy QP1 command response (16 bytes) */ -struct creq_destroy_qp1_resp { - u8 type; - #define CREQ_DESTROY_QP1_RESP_TYPE_MASK 0x3fUL - #define CREQ_DESTROY_QP1_RESP_TYPE_SFT 0 - #define CREQ_DESTROY_QP1_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DESTROY_QP1_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DESTROY_QP1_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DESTROY_QP1_RESP_V 0x1UL - #define CREQ_DESTROY_QP1_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DESTROY_QP1_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DESTROY_QP1_RESP_EVENT_DESTROY_QP1 0x14UL - __le16 reserved48[3]; -}; - -/* Create AH command response (16 bytes) */ -struct creq_create_ah_resp { - u8 type; - #define CREQ_CREATE_AH_RESP_TYPE_MASK 0x3fUL - #define CREQ_CREATE_AH_RESP_TYPE_SFT 0 - #define CREQ_CREATE_AH_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_CREATE_AH_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_CREATE_AH_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_CREATE_AH_RESP_V 0x1UL - #define CREQ_CREATE_AH_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_CREATE_AH_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_CREATE_AH_RESP_EVENT_CREATE_AH 0x15UL - __le16 reserved48[3]; -}; - -/* Destroy AH command response (16 bytes) */ -struct creq_destroy_ah_resp { - u8 type; - #define CREQ_DESTROY_AH_RESP_TYPE_MASK 0x3fUL - #define CREQ_DESTROY_AH_RESP_TYPE_SFT 0 - #define CREQ_DESTROY_AH_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DESTROY_AH_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DESTROY_AH_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 xid; - u8 v; - #define CREQ_DESTROY_AH_RESP_V 0x1UL - #define CREQ_DESTROY_AH_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DESTROY_AH_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DESTROY_AH_RESP_EVENT_DESTROY_AH 0x16UL - __le16 reserved48[3]; -}; - -/* Initialize Firmware command response (16 bytes) */ -struct creq_initialize_fw_resp { - u8 type; - #define CREQ_INITIALIZE_FW_RESP_TYPE_MASK 0x3fUL - #define CREQ_INITIALIZE_FW_RESP_TYPE_SFT 0 - #define CREQ_INITIALIZE_FW_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_INITIALIZE_FW_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_INITIALIZE_FW_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_INITIALIZE_FW_RESP_V 0x1UL - #define CREQ_INITIALIZE_FW_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_INITIALIZE_FW_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_INITIALIZE_FW_RESP_EVENT_INITIALIZE_FW 0x80UL - __le16 reserved48[3]; -}; - -/* De-initialize Firmware command response (16 bytes) */ -struct creq_deinitialize_fw_resp { - u8 type; - #define CREQ_DEINITIALIZE_FW_RESP_TYPE_MASK 0x3fUL - #define CREQ_DEINITIALIZE_FW_RESP_TYPE_SFT 0 - #define CREQ_DEINITIALIZE_FW_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_DEINITIALIZE_FW_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_DEINITIALIZE_FW_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_DEINITIALIZE_FW_RESP_V 0x1UL - #define CREQ_DEINITIALIZE_FW_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_DEINITIALIZE_FW_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_DEINITIALIZE_FW_RESP_EVENT_DEINITIALIZE_FW 0x81UL - __le16 reserved48[3]; -}; - -/* Stop function command response (16 bytes) */ -struct creq_stop_func_resp { - u8 type; - #define CREQ_STOP_FUNC_RESP_TYPE_MASK 0x3fUL - #define CREQ_STOP_FUNC_RESP_TYPE_SFT 0 - #define CREQ_STOP_FUNC_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_STOP_FUNC_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_STOP_FUNC_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_STOP_FUNC_RESP_V 0x1UL - #define CREQ_STOP_FUNC_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_STOP_FUNC_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_STOP_FUNC_RESP_EVENT_STOP_FUNC 0x82UL - __le16 reserved48[3]; -}; - -/* Query function command response (16 bytes) */ -struct creq_query_func_resp { - u8 type; - #define CREQ_QUERY_FUNC_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_FUNC_RESP_TYPE_SFT 0 - #define CREQ_QUERY_FUNC_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_FUNC_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_FUNC_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_FUNC_RESP_V 0x1UL - #define CREQ_QUERY_FUNC_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_FUNC_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_FUNC_RESP_EVENT_QUERY_FUNC 0x83UL - __le16 reserved48[3]; -}; - -/* Query function command response side buffer structure (88 bytes) */ -struct creq_query_func_resp_sb { - u8 opcode; - #define CREQ_QUERY_FUNC_RESP_SB_OPCODE_QUERY_FUNC 0x83UL - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 reserved8; - __le64 max_mr_size; - __le32 max_qp; - __le16 max_qp_wr; - __le16 dev_cap_flags; - #define CREQ_QUERY_FUNC_RESP_SB_DEV_CAP_FLAGS_RESIZE_QP 0x1UL - #define CREQ_QUERY_FUNC_RESP_SB_EXT_STATS 0x10UL - __le32 max_cq; - __le32 max_cqe; - __le32 max_pd; - u8 max_sge; - u8 max_srq_sge; - u8 max_qp_rd_atom; - u8 max_qp_init_rd_atom; - __le32 max_mr; - __le32 max_mw; - __le32 max_raw_eth_qp; - __le32 max_ah; - __le32 max_fmr; - __le32 max_srq_wr; - __le32 max_pkeys; - __le32 max_inline_data; - u8 max_map_per_fmr; - u8 l2_db_space_size; - __le16 max_srq; - __le32 max_gid; - __le32 tqm_alloc_reqs[12]; - __le32 max_dpi; - __le32 reserved_32; -}; - -/* Set resources command response (16 bytes) */ -struct creq_set_func_resources_resp { - u8 type; - #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_MASK 0x3fUL - #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_SFT 0 - #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_SET_FUNC_RESOURCES_RESP_V 0x1UL - #define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_SET_FUNC_RESOURCES_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_SET_FUNC_RESOURCES_RESP_EVENT_SET_FUNC_RESOURCES 0x84UL - __le16 reserved48[3]; + u8 type; + #define CREQ_DESTROY_SRQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_DESTROY_SRQ_RESP_TYPE_SFT 0 + #define CREQ_DESTROY_SRQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DESTROY_SRQ_RESP_TYPE_LAST CREQ_DESTROY_SRQ_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DESTROY_SRQ_RESP_V 0x1UL + u8 event; + #define CREQ_DESTROY_SRQ_RESP_EVENT_DESTROY_SRQ 0x6UL + #define CREQ_DESTROY_SRQ_RESP_EVENT_LAST CREQ_DESTROY_SRQ_RESP_EVENT_DESTROY_SRQ + __le16 enable_for_arm[3]; + #define CREQ_DESTROY_SRQ_RESP_UNUSED0_MASK 0xffffUL + #define CREQ_DESTROY_SRQ_RESP_UNUSED0_SFT 0 + #define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_MASK 0x30000UL + #define CREQ_DESTROY_SRQ_RESP_ENABLE_FOR_ARM_SFT 16 }; -/* Map TC to COS response (16 bytes) */ -struct creq_map_tc_to_cos_resp { - u8 type; - #define CREQ_MAP_TC_TO_COS_RESP_TYPE_MASK 0x3fUL - #define CREQ_MAP_TC_TO_COS_RESP_TYPE_SFT 0 - #define CREQ_MAP_TC_TO_COS_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_MAP_TC_TO_COS_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_MAP_TC_TO_COS_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_MAP_TC_TO_COS_RESP_V 0x1UL - #define CREQ_MAP_TC_TO_COS_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_MAP_TC_TO_COS_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_MAP_TC_TO_COS_RESP_EVENT_MAP_TC_TO_COS 0x8aUL - __le16 reserved48[3]; -}; - -/* Query version response (16 bytes) */ -struct creq_query_version_resp { - u8 type; - #define CREQ_QUERY_VERSION_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_VERSION_RESP_TYPE_SFT 0 - #define CREQ_QUERY_VERSION_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_VERSION_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_VERSION_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - u8 fw_maj; - u8 fw_minor; - u8 fw_bld; - u8 fw_rsvd; - u8 v; - #define CREQ_QUERY_VERSION_RESP_V 0x1UL - #define CREQ_QUERY_VERSION_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_VERSION_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_VERSION_RESP_EVENT_QUERY_VERSION 0x8bUL - __le16 reserved16; - u8 intf_maj; - u8 intf_minor; - u8 intf_bld; - u8 intf_rsvd; -}; - -/* Modify congestion control command response (16 bytes) */ -struct creq_modify_cc_resp { - u8 type; - #define CREQ_MODIFY_CC_RESP_TYPE_MASK 0x3fUL - #define CREQ_MODIFY_CC_RESP_TYPE_SFT 0 - #define CREQ_MODIFY_CC_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_MODIFY_CC_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_MODIFY_CC_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 reserved32; - u8 v; - #define CREQ_MODIFY_CC_RESP_V 0x1UL - #define CREQ_MODIFY_CC_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_MODIFY_CC_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_MODIFY_CC_RESP_EVENT_MODIFY_CC 0x8cUL - __le16 reserved48[3]; -}; - -/* Query congestion control command response (16 bytes) */ -struct creq_query_cc_resp { - u8 type; - #define CREQ_QUERY_CC_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_CC_RESP_TYPE_SFT 0 - #define CREQ_QUERY_CC_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_CC_RESP_RESERVED2_MASK 0xc0UL - #define CREQ_QUERY_CC_RESP_RESERVED2_SFT 6 - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_CC_RESP_V 0x1UL - #define CREQ_QUERY_CC_RESP_RESERVED7_MASK 0xfeUL - #define CREQ_QUERY_CC_RESP_RESERVED7_SFT 1 - u8 event; - #define CREQ_QUERY_CC_RESP_EVENT_QUERY_CC 0x8dUL - __le16 reserved48[3]; -}; - -/* Query congestion control command response side buffer structure (32 bytes) */ -struct creq_query_cc_resp_sb { - u8 opcode; - #define CREQ_QUERY_CC_RESP_SB_OPCODE_QUERY_CC 0x8dUL - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 reserved8; - u8 enable_cc; - #define CREQ_QUERY_CC_RESP_SB_ENABLE_CC 0x1UL - u8 g; - #define CREQ_QUERY_CC_RESP_SB_G_MASK 0x7UL - #define CREQ_QUERY_CC_RESP_SB_G_SFT 0 - u8 num_phases_per_state; - __le16 init_cr; - u8 unused_2; - __le16 unused_3; - u8 unused_4; - __le16 init_tr; - u8 tos_dscp_tos_ecn; - #define CREQ_QUERY_CC_RESP_SB_TOS_ECN_MASK 0x3UL - #define CREQ_QUERY_CC_RESP_SB_TOS_ECN_SFT 0 - #define CREQ_QUERY_CC_RESP_SB_TOS_DSCP_MASK 0xfcUL - #define CREQ_QUERY_CC_RESP_SB_TOS_DSCP_SFT 2 - __le64 reserved64; - __le64 reserved64_1; +/* cmdq_query_srq (size:192b/24B) */ +struct cmdq_query_srq { + u8 opcode; + #define CMDQ_QUERY_SRQ_OPCODE_QUERY_SRQ 0x8UL + #define CMDQ_QUERY_SRQ_OPCODE_LAST CMDQ_QUERY_SRQ_OPCODE_QUERY_SRQ + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 srq_cid; + __le32 unused_0; }; -/* creq_query_roce_stats_resp (size:128b/16B) */ -struct creq_query_roce_stats_resp { +/* creq_query_srq_resp (size:128b/16B) */ +struct creq_query_srq_resp { u8 type; - #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_SFT 0 - #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_LAST \ - CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT + #define CREQ_QUERY_SRQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_SRQ_RESP_TYPE_SFT 0 + #define CREQ_QUERY_SRQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_SRQ_RESP_TYPE_LAST CREQ_QUERY_SRQ_RESP_TYPE_QP_EVENT u8 status; __le16 cookie; __le32 size; u8 v; - #define CREQ_QUERY_ROCE_STATS_RESP_V 0x1UL + #define CREQ_QUERY_SRQ_RESP_V 0x1UL u8 event; - #define CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS 0x8eUL - #define CREQ_QUERY_ROCE_STATS_RESP_EVENT_LAST \ - CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS + #define CREQ_QUERY_SRQ_RESP_EVENT_QUERY_SRQ 0x8UL + #define CREQ_QUERY_SRQ_RESP_EVENT_LAST CREQ_QUERY_SRQ_RESP_EVENT_QUERY_SRQ u8 reserved48[6]; }; -/* creq_query_roce_stats_resp_sb (size:2624b/328B) */ -struct creq_query_roce_stats_resp_sb { +/* creq_query_srq_resp_sb (size:256b/32B) */ +struct creq_query_srq_resp_sb { u8 opcode; - #define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS 0x8eUL - #define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_LAST \ - CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS + #define CREQ_QUERY_SRQ_RESP_SB_OPCODE_QUERY_SRQ 0x8UL + #define CREQ_QUERY_SRQ_RESP_SB_OPCODE_LAST CREQ_QUERY_SRQ_RESP_SB_OPCODE_QUERY_SRQ u8 status; __le16 cookie; __le16 flags; u8 resp_size; - u8 rsvd; - __le32 num_counters; - __le32 rsvd1; - __le64 to_retransmits; - __le64 seq_err_naks_rcvd; - __le64 max_retry_exceeded; - __le64 rnr_naks_rcvd; - __le64 missing_resp; - __le64 unrecoverable_err; - __le64 bad_resp_err; - __le64 local_qp_op_err; - __le64 local_protection_err; - __le64 mem_mgmt_op_err; - __le64 remote_invalid_req_err; - __le64 remote_access_err; - __le64 remote_op_err; - __le64 dup_req; - __le64 res_exceed_max; - __le64 res_length_mismatch; - __le64 res_exceeds_wqe; - __le64 res_opcode_err; - __le64 res_rx_invalid_rkey; - __le64 res_rx_domain_err; - __le64 res_rx_no_perm; - __le64 res_rx_range_err; - __le64 res_tx_invalid_rkey; - __le64 res_tx_domain_err; - __le64 res_tx_no_perm; - __le64 res_tx_range_err; - __le64 res_irrq_oflow; - __le64 res_unsup_opcode; - __le64 res_unaligned_atomic; - __le64 res_rem_inv_err; - __le64 res_mem_error; - __le64 res_srq_err; - __le64 res_cmp_err; - __le64 res_invalid_dup_rkey; - __le64 res_wqe_format_err; - __le64 res_cq_load_err; - __le64 res_srq_load_err; - __le64 res_tx_pci_err; - __le64 res_rx_pci_err; - __le64 res_oos_drop_count; - __le64 active_qp_count_p0; - __le64 active_qp_count_p1; - __le64 active_qp_count_p2; - __le64 active_qp_count_p3; + u8 reserved8; + __le32 xid; + __le16 srq_limit; + __le16 reserved16; + __le32 data[4]; }; -/* cmdq_query_roce_stats_ext (size:192b/24B) */ -struct cmdq_query_roce_stats_ext { - u8 opcode; - #define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS 0x92UL - #define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_LAST \ - CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS - u8 cmd_size; - __le16 flags; - #define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_COLLECTION_ID 0x1UL - #define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_FUNCTION_ID 0x2UL - __le16 cookie; - u8 resp_size; - u8 collection_id; - __le64 resp_addr; - __le32 function_id; - #define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_MASK 0xffUL - #define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_SFT 0 - #define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_MASK 0xffff00UL - #define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_SFT 8 - #define CMDQ_QUERY_ROCE_STATS_EXT_VF_VALID 0x1000000UL - __le32 reserved32; +/* cmdq_create_cq (size:384b/48B) */ +struct cmdq_create_cq { + u8 opcode; + #define CMDQ_CREATE_CQ_OPCODE_CREATE_CQ 0x9UL + #define CMDQ_CREATE_CQ_OPCODE_LAST CMDQ_CREATE_CQ_OPCODE_CREATE_CQ + u8 cmd_size; + __le16 flags; + #define CMDQ_CREATE_CQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION 0x1UL + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le64 cq_handle; + __le32 pg_size_lvl; + #define CMDQ_CREATE_CQ_LVL_MASK 0x3UL + #define CMDQ_CREATE_CQ_LVL_SFT 0 + #define CMDQ_CREATE_CQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_CQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_CQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_CQ_LVL_LAST CMDQ_CREATE_CQ_LVL_LVL_2 + #define CMDQ_CREATE_CQ_PG_SIZE_MASK 0x1cUL + #define CMDQ_CREATE_CQ_PG_SIZE_SFT 2 + #define CMDQ_CREATE_CQ_PG_SIZE_PG_4K (0x0UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_PG_8K (0x1UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_PG_64K (0x2UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_PG_2M (0x3UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_PG_8M (0x4UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_PG_1G (0x5UL << 2) + #define CMDQ_CREATE_CQ_PG_SIZE_LAST CMDQ_CREATE_CQ_PG_SIZE_PG_1G + #define CMDQ_CREATE_CQ_UNUSED27_MASK 0xffffffe0UL + #define CMDQ_CREATE_CQ_UNUSED27_SFT 5 + __le32 cq_fco_cnq_id; + #define CMDQ_CREATE_CQ_CNQ_ID_MASK 0xfffUL + #define CMDQ_CREATE_CQ_CNQ_ID_SFT 0 + #define CMDQ_CREATE_CQ_CQ_FCO_MASK 0xfffff000UL + #define CMDQ_CREATE_CQ_CQ_FCO_SFT 12 + __le32 dpi; + __le32 cq_size; + __le64 pbl; }; -/* creq_query_roce_stats_ext_resp (size:128b/16B) */ -struct creq_query_roce_stats_ext_resp { - u8 type; - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_MASK 0x3fUL - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_SFT 0 - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT 0x38UL - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_LAST \ - CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT - u8 status; - __le16 cookie; - __le32 size; - u8 v; - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_V 0x1UL - u8 event; +/* creq_create_cq_resp (size:128b/16B) */ +struct creq_create_cq_resp { + u8 type; + #define CREQ_CREATE_CQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_CREATE_CQ_RESP_TYPE_SFT 0 + #define CREQ_CREATE_CQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_CREATE_CQ_RESP_TYPE_LAST CREQ_CREATE_CQ_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_CREATE_CQ_RESP_V 0x1UL + u8 event; + #define CREQ_CREATE_CQ_RESP_EVENT_CREATE_CQ 0x9UL + #define CREQ_CREATE_CQ_RESP_EVENT_LAST CREQ_CREATE_CQ_RESP_EVENT_CREATE_CQ + u8 reserved48[6]; +}; + +/* cmdq_destroy_cq (size:192b/24B) */ +struct cmdq_destroy_cq { + u8 opcode; + #define CMDQ_DESTROY_CQ_OPCODE_DESTROY_CQ 0xaUL + #define CMDQ_DESTROY_CQ_OPCODE_LAST CMDQ_DESTROY_CQ_OPCODE_DESTROY_CQ + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 cq_cid; + __le32 unused_0; +}; + +/* creq_destroy_cq_resp (size:128b/16B) */ +struct creq_destroy_cq_resp { + u8 type; + #define CREQ_DESTROY_CQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_DESTROY_CQ_RESP_TYPE_SFT 0 + #define CREQ_DESTROY_CQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DESTROY_CQ_RESP_TYPE_LAST CREQ_DESTROY_CQ_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DESTROY_CQ_RESP_V 0x1UL + u8 event; + #define CREQ_DESTROY_CQ_RESP_EVENT_DESTROY_CQ 0xaUL + #define CREQ_DESTROY_CQ_RESP_EVENT_LAST CREQ_DESTROY_CQ_RESP_EVENT_DESTROY_CQ + __le16 cq_arm_lvl; + #define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_MASK 0x3UL + #define CREQ_DESTROY_CQ_RESP_CQ_ARM_LVL_SFT 0 + __le16 total_cnq_events; + __le16 reserved16; +}; + +/* cmdq_resize_cq (size:320b/40B) */ +struct cmdq_resize_cq { + u8 opcode; + #define CMDQ_RESIZE_CQ_OPCODE_RESIZE_CQ 0xcUL + #define CMDQ_RESIZE_CQ_OPCODE_LAST CMDQ_RESIZE_CQ_OPCODE_RESIZE_CQ + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 cq_cid; + __le32 new_cq_size_pg_size_lvl; + #define CMDQ_RESIZE_CQ_LVL_MASK 0x3UL + #define CMDQ_RESIZE_CQ_LVL_SFT 0 + #define CMDQ_RESIZE_CQ_LVL_LVL_0 0x0UL + #define CMDQ_RESIZE_CQ_LVL_LVL_1 0x1UL + #define CMDQ_RESIZE_CQ_LVL_LVL_2 0x2UL + #define CMDQ_RESIZE_CQ_LVL_LAST CMDQ_RESIZE_CQ_LVL_LVL_2 + #define CMDQ_RESIZE_CQ_PG_SIZE_MASK 0x1cUL + #define CMDQ_RESIZE_CQ_PG_SIZE_SFT 2 + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_4K (0x0UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_8K (0x1UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_64K (0x2UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_2M (0x3UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_8M (0x4UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_PG_1G (0x5UL << 2) + #define CMDQ_RESIZE_CQ_PG_SIZE_LAST CMDQ_RESIZE_CQ_PG_SIZE_PG_1G + #define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_MASK 0x1fffffe0UL + #define CMDQ_RESIZE_CQ_NEW_CQ_SIZE_SFT 5 + __le64 new_pbl; + __le32 new_cq_fco; + __le32 unused_0; +}; + +/* creq_resize_cq_resp (size:128b/16B) */ +struct creq_resize_cq_resp { + u8 type; + #define CREQ_RESIZE_CQ_RESP_TYPE_MASK 0x3fUL + #define CREQ_RESIZE_CQ_RESP_TYPE_SFT 0 + #define CREQ_RESIZE_CQ_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_RESIZE_CQ_RESP_TYPE_LAST CREQ_RESIZE_CQ_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_RESIZE_CQ_RESP_V 0x1UL + u8 event; + #define CREQ_RESIZE_CQ_RESP_EVENT_RESIZE_CQ 0xcUL + #define CREQ_RESIZE_CQ_RESP_EVENT_LAST CREQ_RESIZE_CQ_RESP_EVENT_RESIZE_CQ + u8 reserved48[6]; +}; + +/* cmdq_allocate_mrw (size:256b/32B) */ +struct cmdq_allocate_mrw { + u8 opcode; + #define CMDQ_ALLOCATE_MRW_OPCODE_ALLOCATE_MRW 0xdUL + #define CMDQ_ALLOCATE_MRW_OPCODE_LAST CMDQ_ALLOCATE_MRW_OPCODE_ALLOCATE_MRW + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le64 mrw_handle; + u8 mrw_flags; + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MASK 0xfUL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_SFT 0 + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MR 0x0UL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_PMR 0x1UL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE1 0x2UL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2A 0x3UL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B 0x4UL + #define CMDQ_ALLOCATE_MRW_MRW_FLAGS_LAST CMDQ_ALLOCATE_MRW_MRW_FLAGS_MW_TYPE2B + #define CMDQ_ALLOCATE_MRW_UNUSED4_MASK 0xf0UL + #define CMDQ_ALLOCATE_MRW_UNUSED4_SFT 4 + u8 access; + #define CMDQ_ALLOCATE_MRW_ACCESS_CONSUMER_OWNED_KEY 0x20UL + __le16 unused16; + __le32 pd_id; +}; + +/* creq_allocate_mrw_resp (size:128b/16B) */ +struct creq_allocate_mrw_resp { + u8 type; + #define CREQ_ALLOCATE_MRW_RESP_TYPE_MASK 0x3fUL + #define CREQ_ALLOCATE_MRW_RESP_TYPE_SFT 0 + #define CREQ_ALLOCATE_MRW_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_ALLOCATE_MRW_RESP_TYPE_LAST CREQ_ALLOCATE_MRW_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_ALLOCATE_MRW_RESP_V 0x1UL + u8 event; + #define CREQ_ALLOCATE_MRW_RESP_EVENT_ALLOCATE_MRW 0xdUL + #define CREQ_ALLOCATE_MRW_RESP_EVENT_LAST CREQ_ALLOCATE_MRW_RESP_EVENT_ALLOCATE_MRW + u8 reserved48[6]; +}; + +/* cmdq_deallocate_key (size:192b/24B) */ +struct cmdq_deallocate_key { + u8 opcode; + #define CMDQ_DEALLOCATE_KEY_OPCODE_DEALLOCATE_KEY 0xeUL + #define CMDQ_DEALLOCATE_KEY_OPCODE_LAST CMDQ_DEALLOCATE_KEY_OPCODE_DEALLOCATE_KEY + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + u8 mrw_flags; + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MASK 0xfUL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_SFT 0 + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MR 0x0UL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_PMR 0x1UL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE1 0x2UL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2A 0x3UL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2B 0x4UL + #define CMDQ_DEALLOCATE_KEY_MRW_FLAGS_LAST CMDQ_DEALLOCATE_KEY_MRW_FLAGS_MW_TYPE2B + #define CMDQ_DEALLOCATE_KEY_UNUSED4_MASK 0xf0UL + #define CMDQ_DEALLOCATE_KEY_UNUSED4_SFT 4 + u8 unused24[3]; + __le32 key; +}; + +/* creq_deallocate_key_resp (size:128b/16B) */ +struct creq_deallocate_key_resp { + u8 type; + #define CREQ_DEALLOCATE_KEY_RESP_TYPE_MASK 0x3fUL + #define CREQ_DEALLOCATE_KEY_RESP_TYPE_SFT 0 + #define CREQ_DEALLOCATE_KEY_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DEALLOCATE_KEY_RESP_TYPE_LAST CREQ_DEALLOCATE_KEY_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DEALLOCATE_KEY_RESP_V 0x1UL + u8 event; + #define CREQ_DEALLOCATE_KEY_RESP_EVENT_DEALLOCATE_KEY 0xeUL + #define CREQ_DEALLOCATE_KEY_RESP_EVENT_LAST CREQ_DEALLOCATE_KEY_RESP_EVENT_DEALLOCATE_KEY + __le16 reserved16; + __le32 bound_window_info; +}; + +/* cmdq_register_mr (size:384b/48B) */ +struct cmdq_register_mr { + u8 opcode; + #define CMDQ_REGISTER_MR_OPCODE_REGISTER_MR 0xfUL + #define CMDQ_REGISTER_MR_OPCODE_LAST CMDQ_REGISTER_MR_OPCODE_REGISTER_MR + u8 cmd_size; + __le16 flags; + #define CMDQ_REGISTER_MR_FLAGS_ALLOC_MR 0x1UL + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + u8 log2_pg_size_lvl; + #define CMDQ_REGISTER_MR_LVL_MASK 0x3UL + #define CMDQ_REGISTER_MR_LVL_SFT 0 + #define CMDQ_REGISTER_MR_LVL_LVL_0 0x0UL + #define CMDQ_REGISTER_MR_LVL_LVL_1 0x1UL + #define CMDQ_REGISTER_MR_LVL_LVL_2 0x2UL + #define CMDQ_REGISTER_MR_LVL_LAST CMDQ_REGISTER_MR_LVL_LVL_2 + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_MASK 0x7cUL + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_SFT 2 + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4K (0xcUL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_8K (0xdUL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_64K (0x10UL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_256K (0x12UL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1M (0x14UL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_2M (0x15UL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_4M (0x16UL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G (0x1eUL << 2) + #define CMDQ_REGISTER_MR_LOG2_PG_SIZE_LAST CMDQ_REGISTER_MR_LOG2_PG_SIZE_PG_1G + #define CMDQ_REGISTER_MR_UNUSED1 0x80UL + u8 access; + #define CMDQ_REGISTER_MR_ACCESS_LOCAL_WRITE 0x1UL + #define CMDQ_REGISTER_MR_ACCESS_REMOTE_READ 0x2UL + #define CMDQ_REGISTER_MR_ACCESS_REMOTE_WRITE 0x4UL + #define CMDQ_REGISTER_MR_ACCESS_REMOTE_ATOMIC 0x8UL + #define CMDQ_REGISTER_MR_ACCESS_MW_BIND 0x10UL + #define CMDQ_REGISTER_MR_ACCESS_ZERO_BASED 0x20UL + __le16 log2_pbl_pg_size; + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_MASK 0x1fUL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_SFT 0 + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4K 0xcUL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_8K 0xdUL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_64K 0x10UL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_256K 0x12UL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1M 0x14UL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_2M 0x15UL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_4M 0x16UL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G 0x1eUL + #define CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_LAST CMDQ_REGISTER_MR_LOG2_PBL_PG_SIZE_PG_1G + #define CMDQ_REGISTER_MR_UNUSED11_MASK 0xffe0UL + #define CMDQ_REGISTER_MR_UNUSED11_SFT 5 + __le32 key; + __le64 pbl; + __le64 va; + __le64 mr_size; +}; + +/* creq_register_mr_resp (size:128b/16B) */ +struct creq_register_mr_resp { + u8 type; + #define CREQ_REGISTER_MR_RESP_TYPE_MASK 0x3fUL + #define CREQ_REGISTER_MR_RESP_TYPE_SFT 0 + #define CREQ_REGISTER_MR_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_REGISTER_MR_RESP_TYPE_LAST CREQ_REGISTER_MR_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_REGISTER_MR_RESP_V 0x1UL + u8 event; + #define CREQ_REGISTER_MR_RESP_EVENT_REGISTER_MR 0xfUL + #define CREQ_REGISTER_MR_RESP_EVENT_LAST CREQ_REGISTER_MR_RESP_EVENT_REGISTER_MR + u8 reserved48[6]; +}; + +/* cmdq_deregister_mr (size:192b/24B) */ +struct cmdq_deregister_mr { + u8 opcode; + #define CMDQ_DEREGISTER_MR_OPCODE_DEREGISTER_MR 0x10UL + #define CMDQ_DEREGISTER_MR_OPCODE_LAST CMDQ_DEREGISTER_MR_OPCODE_DEREGISTER_MR + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 lkey; + __le32 unused_0; +}; + +/* creq_deregister_mr_resp (size:128b/16B) */ +struct creq_deregister_mr_resp { + u8 type; + #define CREQ_DEREGISTER_MR_RESP_TYPE_MASK 0x3fUL + #define CREQ_DEREGISTER_MR_RESP_TYPE_SFT 0 + #define CREQ_DEREGISTER_MR_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DEREGISTER_MR_RESP_TYPE_LAST CREQ_DEREGISTER_MR_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DEREGISTER_MR_RESP_V 0x1UL + u8 event; + #define CREQ_DEREGISTER_MR_RESP_EVENT_DEREGISTER_MR 0x10UL + #define CREQ_DEREGISTER_MR_RESP_EVENT_LAST CREQ_DEREGISTER_MR_RESP_EVENT_DEREGISTER_MR + __le16 reserved16; + __le32 bound_windows; +}; + +/* cmdq_add_gid (size:384b/48B) */ +struct cmdq_add_gid { + u8 opcode; + #define CMDQ_ADD_GID_OPCODE_ADD_GID 0x11UL + #define CMDQ_ADD_GID_OPCODE_LAST CMDQ_ADD_GID_OPCODE_ADD_GID + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __be32 gid[4]; + __be16 src_mac[3]; + __le16 vlan; + #define CMDQ_ADD_GID_VLAN_VLAN_EN_TPID_VLAN_ID_MASK 0xffffUL + #define CMDQ_ADD_GID_VLAN_VLAN_EN_TPID_VLAN_ID_SFT 0 + #define CMDQ_ADD_GID_VLAN_VLAN_ID_MASK 0xfffUL + #define CMDQ_ADD_GID_VLAN_VLAN_ID_SFT 0 + #define CMDQ_ADD_GID_VLAN_TPID_MASK 0x7000UL + #define CMDQ_ADD_GID_VLAN_TPID_SFT 12 + #define CMDQ_ADD_GID_VLAN_TPID_TPID_88A8 (0x0UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_8100 (0x1UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_9100 (0x2UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_9200 (0x3UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_9300 (0x4UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG1 (0x5UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG2 (0x6UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3 (0x7UL << 12) + #define CMDQ_ADD_GID_VLAN_TPID_LAST CMDQ_ADD_GID_VLAN_TPID_TPID_CFG3 + #define CMDQ_ADD_GID_VLAN_VLAN_EN 0x8000UL + __le16 ipid; + __le16 stats_ctx; + #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_VALID_STATS_CTX_ID_MASK 0xffffUL + #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_VALID_STATS_CTX_ID_SFT 0 + #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_MASK 0x7fffUL + #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_ID_SFT 0 + #define CMDQ_ADD_GID_STATS_CTX_STATS_CTX_VALID 0x8000UL + __le32 unused_0; +}; + +/* creq_add_gid_resp (size:128b/16B) */ +struct creq_add_gid_resp { + u8 type; + #define CREQ_ADD_GID_RESP_TYPE_MASK 0x3fUL + #define CREQ_ADD_GID_RESP_TYPE_SFT 0 + #define CREQ_ADD_GID_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_ADD_GID_RESP_TYPE_LAST CREQ_ADD_GID_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_ADD_GID_RESP_V 0x1UL + u8 event; + #define CREQ_ADD_GID_RESP_EVENT_ADD_GID 0x11UL + #define CREQ_ADD_GID_RESP_EVENT_LAST CREQ_ADD_GID_RESP_EVENT_ADD_GID + u8 reserved48[6]; +}; + +/* cmdq_delete_gid (size:192b/24B) */ +struct cmdq_delete_gid { + u8 opcode; + #define CMDQ_DELETE_GID_OPCODE_DELETE_GID 0x12UL + #define CMDQ_DELETE_GID_OPCODE_LAST CMDQ_DELETE_GID_OPCODE_DELETE_GID + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le16 gid_index; + u8 unused_0[6]; +}; + +/* creq_delete_gid_resp (size:128b/16B) */ +struct creq_delete_gid_resp { + u8 type; + #define CREQ_DELETE_GID_RESP_TYPE_MASK 0x3fUL + #define CREQ_DELETE_GID_RESP_TYPE_SFT 0 + #define CREQ_DELETE_GID_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DELETE_GID_RESP_TYPE_LAST CREQ_DELETE_GID_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DELETE_GID_RESP_V 0x1UL + u8 event; + #define CREQ_DELETE_GID_RESP_EVENT_DELETE_GID 0x12UL + #define CREQ_DELETE_GID_RESP_EVENT_LAST CREQ_DELETE_GID_RESP_EVENT_DELETE_GID + u8 reserved48[6]; +}; + +/* cmdq_modify_gid (size:384b/48B) */ +struct cmdq_modify_gid { + u8 opcode; + #define CMDQ_MODIFY_GID_OPCODE_MODIFY_GID 0x17UL + #define CMDQ_MODIFY_GID_OPCODE_LAST CMDQ_MODIFY_GID_OPCODE_MODIFY_GID + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __be32 gid[4]; + __be16 src_mac[3]; + __le16 vlan; + #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_MASK 0xfffUL + #define CMDQ_MODIFY_GID_VLAN_VLAN_ID_SFT 0 + #define CMDQ_MODIFY_GID_VLAN_TPID_MASK 0x7000UL + #define CMDQ_MODIFY_GID_VLAN_TPID_SFT 12 + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_88A8 (0x0UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_8100 (0x1UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9100 (0x2UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9200 (0x3UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_9300 (0x4UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG1 (0x5UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG2 (0x6UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3 (0x7UL << 12) + #define CMDQ_MODIFY_GID_VLAN_TPID_LAST CMDQ_MODIFY_GID_VLAN_TPID_TPID_CFG3 + #define CMDQ_MODIFY_GID_VLAN_VLAN_EN 0x8000UL + __le16 ipid; + __le16 gid_index; + __le16 stats_ctx; + #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_MASK 0x7fffUL + #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_ID_SFT 0 + #define CMDQ_MODIFY_GID_STATS_CTX_STATS_CTX_VALID 0x8000UL + __le16 unused_0; +}; + +/* creq_modify_gid_resp (size:128b/16B) */ +struct creq_modify_gid_resp { + u8 type; + #define CREQ_MODIFY_GID_RESP_TYPE_MASK 0x3fUL + #define CREQ_MODIFY_GID_RESP_TYPE_SFT 0 + #define CREQ_MODIFY_GID_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_MODIFY_GID_RESP_TYPE_LAST CREQ_MODIFY_GID_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_MODIFY_GID_RESP_V 0x1UL + u8 event; + #define CREQ_MODIFY_GID_RESP_EVENT_ADD_GID 0x11UL + #define CREQ_MODIFY_GID_RESP_EVENT_LAST CREQ_MODIFY_GID_RESP_EVENT_ADD_GID + u8 reserved48[6]; +}; + +/* cmdq_query_gid (size:192b/24B) */ +struct cmdq_query_gid { + u8 opcode; + #define CMDQ_QUERY_GID_OPCODE_QUERY_GID 0x18UL + #define CMDQ_QUERY_GID_OPCODE_LAST CMDQ_QUERY_GID_OPCODE_QUERY_GID + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le16 gid_index; + u8 unused16[6]; +}; + +/* creq_query_gid_resp (size:128b/16B) */ +struct creq_query_gid_resp { + u8 type; + #define CREQ_QUERY_GID_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_GID_RESP_TYPE_SFT 0 + #define CREQ_QUERY_GID_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_GID_RESP_TYPE_LAST CREQ_QUERY_GID_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_GID_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_GID_RESP_EVENT_QUERY_GID 0x18UL + #define CREQ_QUERY_GID_RESP_EVENT_LAST CREQ_QUERY_GID_RESP_EVENT_QUERY_GID + u8 reserved48[6]; +}; + +/* creq_query_gid_resp_sb (size:320b/40B) */ +struct creq_query_gid_resp_sb { + u8 opcode; + #define CREQ_QUERY_GID_RESP_SB_OPCODE_QUERY_GID 0x18UL + #define CREQ_QUERY_GID_RESP_SB_OPCODE_LAST CREQ_QUERY_GID_RESP_SB_OPCODE_QUERY_GID + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + __le32 gid[4]; + __le16 src_mac[3]; + __le16 vlan; + #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_EN_TPID_VLAN_ID_MASK 0xffffUL + #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_EN_TPID_VLAN_ID_SFT 0 + #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_MASK 0xfffUL + #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_ID_SFT 0 + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_MASK 0x7000UL + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_SFT 12 + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_88A8 (0x0UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_8100 (0x1UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9100 (0x2UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9200 (0x3UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_9300 (0x4UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG1 (0x5UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG2 (0x6UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3 (0x7UL << 12) + #define CREQ_QUERY_GID_RESP_SB_VLAN_TPID_LAST CREQ_QUERY_GID_RESP_SB_VLAN_TPID_TPID_CFG3 + #define CREQ_QUERY_GID_RESP_SB_VLAN_VLAN_EN 0x8000UL + __le16 ipid; + __le16 gid_index; + __le32 unused_0; +}; + +/* cmdq_create_qp1 (size:640b/80B) */ +struct cmdq_create_qp1 { + u8 opcode; + #define CMDQ_CREATE_QP1_OPCODE_CREATE_QP1 0x13UL + #define CMDQ_CREATE_QP1_OPCODE_LAST CMDQ_CREATE_QP1_OPCODE_CREATE_QP1 + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le64 qp_handle; + __le32 qp_flags; + #define CMDQ_CREATE_QP1_QP_FLAGS_SRQ_USED 0x1UL + #define CMDQ_CREATE_QP1_QP_FLAGS_FORCE_COMPLETION 0x2UL + #define CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE 0x4UL + #define CMDQ_CREATE_QP1_QP_FLAGS_LAST CMDQ_CREATE_QP1_QP_FLAGS_RESERVED_LKEY_ENABLE + u8 type; + #define CMDQ_CREATE_QP1_TYPE_GSI 0x1UL + #define CMDQ_CREATE_QP1_TYPE_LAST CMDQ_CREATE_QP1_TYPE_GSI + u8 sq_pg_size_sq_lvl; + #define CMDQ_CREATE_QP1_SQ_LVL_MASK 0xfUL + #define CMDQ_CREATE_QP1_SQ_LVL_SFT 0 + #define CMDQ_CREATE_QP1_SQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_QP1_SQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_QP1_SQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_QP1_SQ_LVL_LAST CMDQ_CREATE_QP1_SQ_LVL_LVL_2 + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_SFT 4 + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_CREATE_QP1_SQ_PG_SIZE_LAST CMDQ_CREATE_QP1_SQ_PG_SIZE_PG_1G + u8 rq_pg_size_rq_lvl; + #define CMDQ_CREATE_QP1_RQ_LVL_MASK 0xfUL + #define CMDQ_CREATE_QP1_RQ_LVL_SFT 0 + #define CMDQ_CREATE_QP1_RQ_LVL_LVL_0 0x0UL + #define CMDQ_CREATE_QP1_RQ_LVL_LVL_1 0x1UL + #define CMDQ_CREATE_QP1_RQ_LVL_LVL_2 0x2UL + #define CMDQ_CREATE_QP1_RQ_LVL_LAST CMDQ_CREATE_QP1_RQ_LVL_LVL_2 + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_MASK 0xf0UL + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_SFT 4 + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_4K (0x0UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8K (0x1UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_64K (0x2UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_2M (0x3UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_8M (0x4UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G (0x5UL << 4) + #define CMDQ_CREATE_QP1_RQ_PG_SIZE_LAST CMDQ_CREATE_QP1_RQ_PG_SIZE_PG_1G + u8 unused_0; + __le32 dpi; + __le32 sq_size; + __le32 rq_size; + __le16 sq_fwo_sq_sge; + #define CMDQ_CREATE_QP1_SQ_SGE_MASK 0xfUL + #define CMDQ_CREATE_QP1_SQ_SGE_SFT 0 + #define CMDQ_CREATE_QP1_SQ_FWO_MASK 0xfff0UL + #define CMDQ_CREATE_QP1_SQ_FWO_SFT 4 + __le16 rq_fwo_rq_sge; + #define CMDQ_CREATE_QP1_RQ_SGE_MASK 0xfUL + #define CMDQ_CREATE_QP1_RQ_SGE_SFT 0 + #define CMDQ_CREATE_QP1_RQ_FWO_MASK 0xfff0UL + #define CMDQ_CREATE_QP1_RQ_FWO_SFT 4 + __le32 scq_cid; + __le32 rcq_cid; + __le32 srq_cid; + __le32 pd_id; + __le64 sq_pbl; + __le64 rq_pbl; +}; + +/* creq_create_qp1_resp (size:128b/16B) */ +struct creq_create_qp1_resp { + u8 type; + #define CREQ_CREATE_QP1_RESP_TYPE_MASK 0x3fUL + #define CREQ_CREATE_QP1_RESP_TYPE_SFT 0 + #define CREQ_CREATE_QP1_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_CREATE_QP1_RESP_TYPE_LAST CREQ_CREATE_QP1_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_CREATE_QP1_RESP_V 0x1UL + u8 event; + #define CREQ_CREATE_QP1_RESP_EVENT_CREATE_QP1 0x13UL + #define CREQ_CREATE_QP1_RESP_EVENT_LAST CREQ_CREATE_QP1_RESP_EVENT_CREATE_QP1 + u8 reserved48[6]; +}; + +/* cmdq_destroy_qp1 (size:192b/24B) */ +struct cmdq_destroy_qp1 { + u8 opcode; + #define CMDQ_DESTROY_QP1_OPCODE_DESTROY_QP1 0x14UL + #define CMDQ_DESTROY_QP1_OPCODE_LAST CMDQ_DESTROY_QP1_OPCODE_DESTROY_QP1 + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 qp1_cid; + __le32 unused_0; +}; + +/* creq_destroy_qp1_resp (size:128b/16B) */ +struct creq_destroy_qp1_resp { + u8 type; + #define CREQ_DESTROY_QP1_RESP_TYPE_MASK 0x3fUL + #define CREQ_DESTROY_QP1_RESP_TYPE_SFT 0 + #define CREQ_DESTROY_QP1_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DESTROY_QP1_RESP_TYPE_LAST CREQ_DESTROY_QP1_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DESTROY_QP1_RESP_V 0x1UL + u8 event; + #define CREQ_DESTROY_QP1_RESP_EVENT_DESTROY_QP1 0x14UL + #define CREQ_DESTROY_QP1_RESP_EVENT_LAST CREQ_DESTROY_QP1_RESP_EVENT_DESTROY_QP1 + u8 reserved48[6]; +}; + +/* cmdq_create_ah (size:512b/64B) */ +struct cmdq_create_ah { + u8 opcode; + #define CMDQ_CREATE_AH_OPCODE_CREATE_AH 0x15UL + #define CMDQ_CREATE_AH_OPCODE_LAST CMDQ_CREATE_AH_OPCODE_CREATE_AH + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le64 ah_handle; + __le32 dgid[4]; + u8 type; + #define CMDQ_CREATE_AH_TYPE_V1 0x0UL + #define CMDQ_CREATE_AH_TYPE_V2IPV4 0x2UL + #define CMDQ_CREATE_AH_TYPE_V2IPV6 0x3UL + #define CMDQ_CREATE_AH_TYPE_LAST CMDQ_CREATE_AH_TYPE_V2IPV6 + u8 hop_limit; + __le16 sgid_index; + __le32 dest_vlan_id_flow_label; + #define CMDQ_CREATE_AH_FLOW_LABEL_MASK 0xfffffUL + #define CMDQ_CREATE_AH_FLOW_LABEL_SFT 0 + #define CMDQ_CREATE_AH_DEST_VLAN_ID_MASK 0xfff00000UL + #define CMDQ_CREATE_AH_DEST_VLAN_ID_SFT 20 + __le32 pd_id; + __le32 unused_0; + __le16 dest_mac[3]; + u8 traffic_class; + u8 enable_cc; + #define CMDQ_CREATE_AH_ENABLE_CC 0x1UL +}; + +/* creq_create_ah_resp (size:128b/16B) */ +struct creq_create_ah_resp { + u8 type; + #define CREQ_CREATE_AH_RESP_TYPE_MASK 0x3fUL + #define CREQ_CREATE_AH_RESP_TYPE_SFT 0 + #define CREQ_CREATE_AH_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_CREATE_AH_RESP_TYPE_LAST CREQ_CREATE_AH_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_CREATE_AH_RESP_V 0x1UL + u8 event; + #define CREQ_CREATE_AH_RESP_EVENT_CREATE_AH 0x15UL + #define CREQ_CREATE_AH_RESP_EVENT_LAST CREQ_CREATE_AH_RESP_EVENT_CREATE_AH + u8 reserved48[6]; +}; + +/* cmdq_destroy_ah (size:192b/24B) */ +struct cmdq_destroy_ah { + u8 opcode; + #define CMDQ_DESTROY_AH_OPCODE_DESTROY_AH 0x16UL + #define CMDQ_DESTROY_AH_OPCODE_LAST CMDQ_DESTROY_AH_OPCODE_DESTROY_AH + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 ah_cid; + __le32 unused_0; +}; + +/* creq_destroy_ah_resp (size:128b/16B) */ +struct creq_destroy_ah_resp { + u8 type; + #define CREQ_DESTROY_AH_RESP_TYPE_MASK 0x3fUL + #define CREQ_DESTROY_AH_RESP_TYPE_SFT 0 + #define CREQ_DESTROY_AH_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_DESTROY_AH_RESP_TYPE_LAST CREQ_DESTROY_AH_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 xid; + u8 v; + #define CREQ_DESTROY_AH_RESP_V 0x1UL + u8 event; + #define CREQ_DESTROY_AH_RESP_EVENT_DESTROY_AH 0x16UL + #define CREQ_DESTROY_AH_RESP_EVENT_LAST CREQ_DESTROY_AH_RESP_EVENT_DESTROY_AH + u8 reserved48[6]; +}; + +/* cmdq_query_roce_stats (size:192b/24B) */ +struct cmdq_query_roce_stats { + u8 opcode; + #define CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS 0x8eUL + #define CMDQ_QUERY_ROCE_STATS_OPCODE_LAST CMDQ_QUERY_ROCE_STATS_OPCODE_QUERY_ROCE_STATS + u8 cmd_size; + __le16 flags; + #define CMDQ_QUERY_ROCE_STATS_FLAGS_COLLECTION_ID 0x1UL + #define CMDQ_QUERY_ROCE_STATS_FLAGS_FUNCTION_ID 0x2UL + __le16 cookie; + u8 resp_size; + u8 collection_id; + __le64 resp_addr; + __le32 function_id; + #define CMDQ_QUERY_ROCE_STATS_PF_NUM_MASK 0xffUL + #define CMDQ_QUERY_ROCE_STATS_PF_NUM_SFT 0 + #define CMDQ_QUERY_ROCE_STATS_VF_NUM_MASK 0xffff00UL + #define CMDQ_QUERY_ROCE_STATS_VF_NUM_SFT 8 + #define CMDQ_QUERY_ROCE_STATS_VF_VALID 0x1000000UL + __le32 reserved32; +}; + +/* creq_query_roce_stats_resp (size:128b/16B) */ +struct creq_query_roce_stats_resp { + u8 type; + #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_SFT 0 + #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_ROCE_STATS_RESP_TYPE_LAST CREQ_QUERY_ROCE_STATS_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_ROCE_STATS_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS 0x8eUL + #define CREQ_QUERY_ROCE_STATS_RESP_EVENT_LAST \ + CREQ_QUERY_ROCE_STATS_RESP_EVENT_QUERY_ROCE_STATS + u8 reserved48[6]; +}; + +/* creq_query_roce_stats_resp_sb (size:2944b/368B) */ +struct creq_query_roce_stats_resp_sb { + u8 opcode; + #define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS 0x8eUL + #define CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_LAST \ + CREQ_QUERY_ROCE_STATS_RESP_SB_OPCODE_QUERY_ROCE_STATS + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 rsvd; + __le32 num_counters; + __le32 rsvd1; + __le64 to_retransmits; + __le64 seq_err_naks_rcvd; + __le64 max_retry_exceeded; + __le64 rnr_naks_rcvd; + __le64 missing_resp; + __le64 unrecoverable_err; + __le64 bad_resp_err; + __le64 local_qp_op_err; + __le64 local_protection_err; + __le64 mem_mgmt_op_err; + __le64 remote_invalid_req_err; + __le64 remote_access_err; + __le64 remote_op_err; + __le64 dup_req; + __le64 res_exceed_max; + __le64 res_length_mismatch; + __le64 res_exceeds_wqe; + __le64 res_opcode_err; + __le64 res_rx_invalid_rkey; + __le64 res_rx_domain_err; + __le64 res_rx_no_perm; + __le64 res_rx_range_err; + __le64 res_tx_invalid_rkey; + __le64 res_tx_domain_err; + __le64 res_tx_no_perm; + __le64 res_tx_range_err; + __le64 res_irrq_oflow; + __le64 res_unsup_opcode; + __le64 res_unaligned_atomic; + __le64 res_rem_inv_err; + __le64 res_mem_error; + __le64 res_srq_err; + __le64 res_cmp_err; + __le64 res_invalid_dup_rkey; + __le64 res_wqe_format_err; + __le64 res_cq_load_err; + __le64 res_srq_load_err; + __le64 res_tx_pci_err; + __le64 res_rx_pci_err; + __le64 res_oos_drop_count; + __le64 active_qp_count_p0; + __le64 active_qp_count_p1; + __le64 active_qp_count_p2; + __le64 active_qp_count_p3; +}; + +/* cmdq_query_roce_stats_ext (size:192b/24B) */ +struct cmdq_query_roce_stats_ext { + u8 opcode; + #define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS 0x92UL + #define CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_LAST \ + CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS + u8 cmd_size; + __le16 flags; + #define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_COLLECTION_ID 0x1UL + #define CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_FUNCTION_ID 0x2UL + __le16 cookie; + u8 resp_size; + u8 collection_id; + __le64 resp_addr; + __le32 function_id; + #define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_MASK 0xffUL + #define CMDQ_QUERY_ROCE_STATS_EXT_PF_NUM_SFT 0 + #define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_MASK 0xffff00UL + #define CMDQ_QUERY_ROCE_STATS_EXT_VF_NUM_SFT 8 + #define CMDQ_QUERY_ROCE_STATS_EXT_VF_VALID 0x1000000UL + __le32 reserved32; +}; + +/* creq_query_roce_stats_ext_resp (size:128b/16B) */ +struct creq_query_roce_stats_ext_resp { + u8 type; + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_SFT 0 + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_LAST \ + CREQ_QUERY_ROCE_STATS_EXT_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_V 0x1UL + u8 event; #define CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_QUERY_ROCE_STATS_EXT 0x92UL #define CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_LAST \ CREQ_QUERY_ROCE_STATS_EXT_RESP_EVENT_QUERY_ROCE_STATS_EXT - u8 reserved48[6]; + u8 reserved48[6]; +}; + +/* creq_query_roce_stats_ext_resp_sb (size:1856b/232B) */ +struct creq_query_roce_stats_ext_resp_sb { + u8 opcode; + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT 0x92UL + #define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_LAST \ + CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 rsvd; + __le64 tx_atomic_req_pkts; + __le64 tx_read_req_pkts; + __le64 tx_read_res_pkts; + __le64 tx_write_req_pkts; + __le64 tx_send_req_pkts; + __le64 tx_roce_pkts; + __le64 tx_roce_bytes; + __le64 rx_atomic_req_pkts; + __le64 rx_read_req_pkts; + __le64 rx_read_res_pkts; + __le64 rx_write_req_pkts; + __le64 rx_send_req_pkts; + __le64 rx_roce_pkts; + __le64 rx_roce_bytes; + __le64 rx_roce_good_pkts; + __le64 rx_roce_good_bytes; + __le64 rx_out_of_buffer_pkts; + __le64 rx_out_of_sequence_pkts; + __le64 tx_cnp_pkts; + __le64 rx_cnp_pkts; + __le64 rx_ecn_marked_pkts; + __le64 tx_cnp_bytes; + __le64 rx_cnp_bytes; + __le64 seq_err_naks_rcvd; + __le64 rnr_naks_rcvd; + __le64 missing_resp; + __le64 to_retransmit; + __le64 dup_req; +}; + +/* cmdq_query_func (size:128b/16B) */ +struct cmdq_query_func { + u8 opcode; + #define CMDQ_QUERY_FUNC_OPCODE_QUERY_FUNC 0x83UL + #define CMDQ_QUERY_FUNC_OPCODE_LAST CMDQ_QUERY_FUNC_OPCODE_QUERY_FUNC + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; +}; + +/* creq_query_func_resp (size:128b/16B) */ +struct creq_query_func_resp { + u8 type; + #define CREQ_QUERY_FUNC_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_FUNC_RESP_TYPE_SFT 0 + #define CREQ_QUERY_FUNC_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_FUNC_RESP_TYPE_LAST CREQ_QUERY_FUNC_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_FUNC_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_FUNC_RESP_EVENT_QUERY_FUNC 0x83UL + #define CREQ_QUERY_FUNC_RESP_EVENT_LAST CREQ_QUERY_FUNC_RESP_EVENT_QUERY_FUNC + u8 reserved48[6]; +}; + +/* creq_query_func_resp_sb (size:1088b/136B) */ +struct creq_query_func_resp_sb { + u8 opcode; + #define CREQ_QUERY_FUNC_RESP_SB_OPCODE_QUERY_FUNC 0x83UL + #define CREQ_QUERY_FUNC_RESP_SB_OPCODE_LAST CREQ_QUERY_FUNC_RESP_SB_OPCODE_QUERY_FUNC + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + __le64 max_mr_size; + __le32 max_qp; + __le16 max_qp_wr; + __le16 dev_cap_flags; + #define CREQ_QUERY_FUNC_RESP_SB_RESIZE_QP 0x1UL + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_MASK 0xeUL + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_SFT 1 + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_CC_GEN0 (0x0UL << 1) + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_CC_GEN1 (0x1UL << 1) + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_CC_GEN1_EXT (0x2UL << 1) + #define CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_LAST \ + CREQ_QUERY_FUNC_RESP_SB_CC_GENERATION_CC_GEN1_EXT + #define CREQ_QUERY_FUNC_RESP_SB_EXT_STATS 0x10UL + #define CREQ_QUERY_FUNC_RESP_SB_MR_REGISTER_ALLOC 0x20UL + #define CREQ_QUERY_FUNC_RESP_SB_OPTIMIZED_TRANSMIT_ENABLED 0x40UL + #define CREQ_QUERY_FUNC_RESP_SB_CQE_V2 0x80UL + #define CREQ_QUERY_FUNC_RESP_SB_PINGPONG_PUSH_MODE 0x100UL + #define CREQ_QUERY_FUNC_RESP_SB_HW_REQUESTER_RETX_ENABLED 0x200UL + #define CREQ_QUERY_FUNC_RESP_SB_HW_RESPONDER_RETX_ENABLED 0x400UL + __le32 max_cq; + __le32 max_cqe; + __le32 max_pd; + u8 max_sge; + u8 max_srq_sge; + u8 max_qp_rd_atom; + u8 max_qp_init_rd_atom; + __le32 max_mr; + __le32 max_mw; + __le32 max_raw_eth_qp; + __le32 max_ah; + __le32 max_fmr; + __le32 max_srq_wr; + __le32 max_pkeys; + __le32 max_inline_data; + u8 max_map_per_fmr; + u8 l2_db_space_size; + __le16 max_srq; + __le32 max_gid; + __le32 tqm_alloc_reqs[12]; + __le32 max_dpi; + u8 max_sge_var_wqe; + u8 reserved_8; + __le16 max_inline_data_var_wqe; +}; + +/* cmdq_set_func_resources (size:448b/56B) */ +struct cmdq_set_func_resources { + u8 opcode; + #define CMDQ_SET_FUNC_RESOURCES_OPCODE_SET_FUNC_RESOURCES 0x84UL + #define CMDQ_SET_FUNC_RESOURCES_OPCODE_LAST\ + CMDQ_SET_FUNC_RESOURCES_OPCODE_SET_FUNC_RESOURCES + u8 cmd_size; + __le16 flags; + #define CMDQ_SET_FUNC_RESOURCES_FLAGS_MRAV_RESERVATION_SPLIT 0x1UL + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 number_of_qp; + __le32 number_of_mrw; + __le32 number_of_srq; + __le32 number_of_cq; + __le32 max_qp_per_vf; + __le32 max_mrw_per_vf; + __le32 max_srq_per_vf; + __le32 max_cq_per_vf; + __le32 max_gid_per_vf; + __le32 stat_ctx_id; +}; + +/* creq_set_func_resources_resp (size:128b/16B) */ +struct creq_set_func_resources_resp { + u8 type; + #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_MASK 0x3fUL + #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_SFT 0 + #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_SET_FUNC_RESOURCES_RESP_TYPE_LAST CREQ_SET_FUNC_RESOURCES_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_SET_FUNC_RESOURCES_RESP_V 0x1UL + u8 event; + #define CREQ_SET_FUNC_RESOURCES_RESP_EVENT_SET_FUNC_RESOURCES 0x84UL + #define CREQ_SET_FUNC_RESOURCES_RESP_EVENT_LAST \ + CREQ_SET_FUNC_RESOURCES_RESP_EVENT_SET_FUNC_RESOURCES + u8 reserved48[6]; +}; + +/* cmdq_map_tc_to_cos (size:192b/24B) */ +struct cmdq_map_tc_to_cos { + u8 opcode; + #define CMDQ_MAP_TC_TO_COS_OPCODE_MAP_TC_TO_COS 0x8aUL + #define CMDQ_MAP_TC_TO_COS_OPCODE_LAST CMDQ_MAP_TC_TO_COS_OPCODE_MAP_TC_TO_COS + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le16 cos0; + #define CMDQ_MAP_TC_TO_COS_COS0_NO_CHANGE 0xffffUL + #define CMDQ_MAP_TC_TO_COS_COS0_LAST CMDQ_MAP_TC_TO_COS_COS0_NO_CHANGE + __le16 cos1; + #define CMDQ_MAP_TC_TO_COS_COS1_DISABLE 0x8000UL + #define CMDQ_MAP_TC_TO_COS_COS1_NO_CHANGE 0xffffUL + #define CMDQ_MAP_TC_TO_COS_COS1_LAST CMDQ_MAP_TC_TO_COS_COS1_NO_CHANGE + __le32 unused_0; +}; + +/* creq_map_tc_to_cos_resp (size:128b/16B) */ +struct creq_map_tc_to_cos_resp { + u8 type; + #define CREQ_MAP_TC_TO_COS_RESP_TYPE_MASK 0x3fUL + #define CREQ_MAP_TC_TO_COS_RESP_TYPE_SFT 0 + #define CREQ_MAP_TC_TO_COS_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_MAP_TC_TO_COS_RESP_TYPE_LAST CREQ_MAP_TC_TO_COS_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_MAP_TC_TO_COS_RESP_V 0x1UL + u8 event; + #define CREQ_MAP_TC_TO_COS_RESP_EVENT_MAP_TC_TO_COS 0x8aUL + #define CREQ_MAP_TC_TO_COS_RESP_EVENT_LAST CREQ_MAP_TC_TO_COS_RESP_EVENT_MAP_TC_TO_COS + u8 reserved48[6]; +}; + +/* cmdq_query_roce_cc (size:128b/16B) */ +struct cmdq_query_roce_cc { + u8 opcode; + #define CMDQ_QUERY_ROCE_CC_OPCODE_QUERY_ROCE_CC 0x8dUL + #define CMDQ_QUERY_ROCE_CC_OPCODE_LAST CMDQ_QUERY_ROCE_CC_OPCODE_QUERY_ROCE_CC + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; +}; + +/* creq_query_roce_cc_resp (size:128b/16B) */ +struct creq_query_roce_cc_resp { + u8 type; + #define CREQ_QUERY_ROCE_CC_RESP_TYPE_MASK 0x3fUL + #define CREQ_QUERY_ROCE_CC_RESP_TYPE_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_QUERY_ROCE_CC_RESP_TYPE_LAST CREQ_QUERY_ROCE_CC_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 size; + u8 v; + #define CREQ_QUERY_ROCE_CC_RESP_V 0x1UL + u8 event; + #define CREQ_QUERY_ROCE_CC_RESP_EVENT_QUERY_ROCE_CC 0x8dUL + #define CREQ_QUERY_ROCE_CC_RESP_EVENT_LAST CREQ_QUERY_ROCE_CC_RESP_EVENT_QUERY_ROCE_CC + u8 reserved48[6]; +}; + +/* creq_query_roce_cc_resp_sb (size:256b/32B) */ +struct creq_query_roce_cc_resp_sb { + u8 opcode; + #define CREQ_QUERY_ROCE_CC_RESP_SB_OPCODE_QUERY_ROCE_CC 0x8dUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_OPCODE_LAST \ + CREQ_QUERY_ROCE_CC_RESP_SB_OPCODE_QUERY_ROCE_CC + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + u8 enable_cc; + #define CREQ_QUERY_ROCE_CC_RESP_SB_ENABLE_CC 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_UNUSED7_MASK 0xfeUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_UNUSED7_SFT 1 + u8 tos_dscp_tos_ecn; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TOS_ECN_MASK 0x3UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TOS_ECN_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TOS_DSCP_MASK 0xfcUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TOS_DSCP_SFT 2 + u8 g; + u8 num_phases_per_state; + __le16 init_cr; + __le16 init_tr; + u8 alt_vlan_pcp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_ALT_VLAN_PCP_MASK 0x7UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_ALT_VLAN_PCP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD1_MASK 0xf8UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD1_SFT 3 + u8 alt_tos_dscp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_ALT_TOS_DSCP_MASK 0x3fUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_ALT_TOS_DSCP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD4_MASK 0xc0UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD4_SFT 6 + u8 cc_mode; + #define CREQ_QUERY_ROCE_CC_RESP_SB_CC_MODE_DCTCP 0x0UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_CC_MODE_PROBABILISTIC 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_CC_MODE_LAST \ + CREQ_QUERY_ROCE_CC_RESP_SB_CC_MODE_PROBABILISTIC + u8 tx_queue; + __le16 rtt; + #define CREQ_QUERY_ROCE_CC_RESP_SB_RTT_MASK 0x3fffUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_RTT_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD5_MASK 0xc000UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD5_SFT 14 + __le16 tcp_cp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TCP_CP_MASK 0x3ffUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TCP_CP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD6_MASK 0xfc00UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_RSVD6_SFT 10 + __le16 inactivity_th; + u8 pkts_per_phase; + u8 time_per_phase; + __le32 reserved32; +}; + +/* creq_query_roce_cc_resp_sb_tlv (size:384b/48B) */ +struct creq_query_roce_cc_resp_sb_tlv { + __le16 cmd_discr; + u8 reserved_8b; + u8 tlv_flags; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_MORE 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_MORE_LAST 0x0UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_MORE_NOT_LAST 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_REQUIRED 0x2UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_REQUIRED_NO (0x0UL << 1) + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES (0x1UL << 1) + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_REQUIRED_LAST \ + CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES + __le16 tlv_type; + __le16 length; + u8 total_size; + u8 reserved56[7]; + u8 opcode; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_OPCODE_QUERY_ROCE_CC 0x8dUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_OPCODE_LAST \ + CREQ_QUERY_ROCE_CC_RESP_SB_TLV_OPCODE_QUERY_ROCE_CC + u8 status; + __le16 cookie; + __le16 flags; + u8 resp_size; + u8 reserved8; + u8 enable_cc; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_ENABLE_CC 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_UNUSED7_MASK 0xfeUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_UNUSED7_SFT 1 + u8 tos_dscp_tos_ecn; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TOS_ECN_MASK 0x3UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TOS_ECN_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TOS_DSCP_MASK 0xfcUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TOS_DSCP_SFT 2 + u8 g; + u8 num_phases_per_state; + __le16 init_cr; + __le16 init_tr; + u8 alt_vlan_pcp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_ALT_VLAN_PCP_MASK 0x7UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_ALT_VLAN_PCP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD1_MASK 0xf8UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD1_SFT 3 + u8 alt_tos_dscp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_ALT_TOS_DSCP_MASK 0x3fUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_ALT_TOS_DSCP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD4_MASK 0xc0UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD4_SFT 6 + u8 cc_mode; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_CC_MODE_DCTCP 0x0UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_CC_MODE_PROBABILISTIC 0x1UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_CC_MODE_LAST\ + CREQ_QUERY_ROCE_CC_RESP_SB_TLV_CC_MODE_PROBABILISTIC + u8 tx_queue; + __le16 rtt; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RTT_MASK 0x3fffUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RTT_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD5_MASK 0xc000UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD5_SFT 14 + __le16 tcp_cp; + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TCP_CP_MASK 0x3ffUL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_TCP_CP_SFT 0 + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD6_MASK 0xfc00UL + #define CREQ_QUERY_ROCE_CC_RESP_SB_TLV_RSVD6_SFT 10 + __le16 inactivity_th; + u8 pkts_per_phase; + u8 time_per_phase; + __le32 reserved32; +}; + +/* creq_query_roce_cc_gen1_resp_sb_tlv (size:704b/88B) */ +struct creq_query_roce_cc_gen1_resp_sb_tlv { + __le16 cmd_discr; + u8 reserved_8b; + u8 tlv_flags; + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_MORE 0x1UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_MORE_LAST 0x0UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_MORE_NOT_LAST 0x1UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_REQUIRED 0x2UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_REQUIRED_NO (0x0UL << 1) + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES (0x1UL << 1) + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_REQUIRED_LAST \ + CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_TLV_FLAGS_REQUIRED_YES + __le16 tlv_type; + __le16 length; + __le64 reserved64; + __le16 inactivity_th_hi; + __le16 min_time_between_cnps; + __le16 init_cp; + u8 tr_update_mode; + u8 tr_update_cycles; + u8 fr_num_rtts; + u8 ai_rate_increase; + __le16 reduction_relax_rtts_th; + __le16 additional_relax_cr_th; + __le16 cr_min_th; + u8 bw_avg_weight; + u8 actual_cr_factor; + __le16 max_cp_cr_th; + u8 cp_bias_en; + u8 cp_bias; + u8 cnp_ecn; + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_CNP_ECN_NOT_ECT 0x0UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_CNP_ECN_ECT_1 0x1UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_CNP_ECN_ECT_0 0x2UL + #define CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_CNP_ECN_LAST \ + CREQ_QUERY_ROCE_CC_GEN1_RESP_SB_TLV_CNP_ECN_ECT_0 + u8 rtt_jitter_en; + __le16 link_bytes_per_usec; + __le16 reset_cc_cr_th; + u8 cr_width; + u8 quota_period_min; + u8 quota_period_max; + u8 quota_period_abs_max; + __le16 tr_lower_bound; + u8 cr_prob_factor; + u8 tr_prob_factor; + __le16 fairness_cr_th; + u8 red_div; + u8 cnp_ratio_th; + __le16 exp_ai_rtts; + u8 exp_ai_cr_cp_ratio; + u8 use_rate_table; + __le16 cp_exp_update_th; + __le16 high_exp_ai_rtts_th1; + __le16 high_exp_ai_rtts_th2; + __le16 actual_cr_cong_free_rtts_th; + __le16 severe_cong_cr_th1; + __le16 severe_cong_cr_th2; + __le32 link64B_per_rtt; + u8 cc_ack_bytes; + u8 reduce_init_en; + __le16 reduce_init_cong_free_rtts_th; + u8 random_no_red_en; + u8 actual_cr_shift_correction_en; + u8 quota_period_adjust_en; + u8 reserved[5]; +}; + +/* cmdq_modify_roce_cc (size:448b/56B) */ +struct cmdq_modify_roce_cc { + u8 opcode; + #define CMDQ_MODIFY_ROCE_CC_OPCODE_MODIFY_ROCE_CC 0x8cUL + #define CMDQ_MODIFY_ROCE_CC_OPCODE_LAST CMDQ_MODIFY_ROCE_CC_OPCODE_MODIFY_ROCE_CC + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 modify_mask; + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ENABLE_CC 0x1UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_G 0x2UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_NUMPHASEPERSTATE 0x4UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_INIT_CR 0x8UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_INIT_TR 0x10UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TOS_ECN 0x20UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TOS_DSCP 0x40UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ALT_VLAN_PCP 0x80UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ALT_TOS_DSCP 0x100UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_RTT 0x200UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_CC_MODE 0x400UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TCP_CP 0x800UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TX_QUEUE 0x1000UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_INACTIVITY_CP 0x2000UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TIME_PER_PHASE 0x4000UL + #define CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_PKTS_PER_PHASE 0x8000UL + u8 enable_cc; + #define CMDQ_MODIFY_ROCE_CC_ENABLE_CC 0x1UL + #define CMDQ_MODIFY_ROCE_CC_RSVD1_MASK 0xfeUL + #define CMDQ_MODIFY_ROCE_CC_RSVD1_SFT 1 + u8 g; + u8 num_phases_per_state; + u8 pkts_per_phase; + __le16 init_cr; + __le16 init_tr; + u8 tos_dscp_tos_ecn; + #define CMDQ_MODIFY_ROCE_CC_TOS_ECN_MASK 0x3UL + #define CMDQ_MODIFY_ROCE_CC_TOS_ECN_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TOS_DSCP_MASK 0xfcUL + #define CMDQ_MODIFY_ROCE_CC_TOS_DSCP_SFT 2 + u8 alt_vlan_pcp; + #define CMDQ_MODIFY_ROCE_CC_ALT_VLAN_PCP_MASK 0x7UL + #define CMDQ_MODIFY_ROCE_CC_ALT_VLAN_PCP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_RSVD3_MASK 0xf8UL + #define CMDQ_MODIFY_ROCE_CC_RSVD3_SFT 3 + __le16 alt_tos_dscp; + #define CMDQ_MODIFY_ROCE_CC_ALT_TOS_DSCP_MASK 0x3fUL + #define CMDQ_MODIFY_ROCE_CC_ALT_TOS_DSCP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_RSVD4_MASK 0xffc0UL + #define CMDQ_MODIFY_ROCE_CC_RSVD4_SFT 6 + __le16 rtt; + #define CMDQ_MODIFY_ROCE_CC_RTT_MASK 0x3fffUL + #define CMDQ_MODIFY_ROCE_CC_RTT_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_RSVD5_MASK 0xc000UL + #define CMDQ_MODIFY_ROCE_CC_RSVD5_SFT 14 + __le16 tcp_cp; + #define CMDQ_MODIFY_ROCE_CC_TCP_CP_MASK 0x3ffUL + #define CMDQ_MODIFY_ROCE_CC_TCP_CP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_RSVD6_MASK 0xfc00UL + #define CMDQ_MODIFY_ROCE_CC_RSVD6_SFT 10 + u8 cc_mode; + #define CMDQ_MODIFY_ROCE_CC_CC_MODE_DCTCP_CC_MODE 0x0UL + #define CMDQ_MODIFY_ROCE_CC_CC_MODE_PROBABILISTIC_CC_MODE 0x1UL + #define CMDQ_MODIFY_ROCE_CC_CC_MODE_LAST CMDQ_MODIFY_ROCE_CC_CC_MODE_PROBABILISTIC_CC_MODE + u8 tx_queue; + __le16 inactivity_th; + u8 time_per_phase; + u8 reserved8_1; + __le16 reserved16; + __le32 reserved32; + __le64 reserved64; +}; + +/* cmdq_modify_roce_cc_tlv (size:640b/80B) */ +struct cmdq_modify_roce_cc_tlv { + __le16 cmd_discr; + u8 reserved_8b; + u8 tlv_flags; + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_MORE 0x1UL + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_MORE_LAST 0x0UL + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_MORE_NOT_LAST 0x1UL + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_REQUIRED 0x2UL + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_REQUIRED_NO (0x0UL << 1) + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_REQUIRED_YES (0x1UL << 1) + #define CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_REQUIRED_LAST \ + CMDQ_MODIFY_ROCE_CC_TLV_TLV_FLAGS_REQUIRED_YES + __le16 tlv_type; + __le16 length; + u8 total_size; + u8 reserved56[7]; + u8 opcode; + #define CMDQ_MODIFY_ROCE_CC_TLV_OPCODE_MODIFY_ROCE_CC 0x8cUL + #define CMDQ_MODIFY_ROCE_CC_TLV_OPCODE_LAST CMDQ_MODIFY_ROCE_CC_TLV_OPCODE_MODIFY_ROCE_CC + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 modify_mask; + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_ENABLE_CC 0x1UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_G 0x2UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_NUMPHASEPERSTATE 0x4UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_INIT_CR 0x8UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_INIT_TR 0x10UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_TOS_ECN 0x20UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_TOS_DSCP 0x40UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_ALT_VLAN_PCP 0x80UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_ALT_TOS_DSCP 0x100UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_RTT 0x200UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_CC_MODE 0x400UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_TCP_CP 0x800UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_TX_QUEUE 0x1000UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_INACTIVITY_CP 0x2000UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_TIME_PER_PHASE 0x4000UL + #define CMDQ_MODIFY_ROCE_CC_TLV_MODIFY_MASK_PKTS_PER_PHASE 0x8000UL + u8 enable_cc; + #define CMDQ_MODIFY_ROCE_CC_TLV_ENABLE_CC 0x1UL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD1_MASK 0xfeUL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD1_SFT 1 + u8 g; + u8 num_phases_per_state; + u8 pkts_per_phase; + __le16 init_cr; + __le16 init_tr; + u8 tos_dscp_tos_ecn; + #define CMDQ_MODIFY_ROCE_CC_TLV_TOS_ECN_MASK 0x3UL + #define CMDQ_MODIFY_ROCE_CC_TLV_TOS_ECN_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TLV_TOS_DSCP_MASK 0xfcUL + #define CMDQ_MODIFY_ROCE_CC_TLV_TOS_DSCP_SFT 2 + u8 alt_vlan_pcp; + #define CMDQ_MODIFY_ROCE_CC_TLV_ALT_VLAN_PCP_MASK 0x7UL + #define CMDQ_MODIFY_ROCE_CC_TLV_ALT_VLAN_PCP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD3_MASK 0xf8UL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD3_SFT 3 + __le16 alt_tos_dscp; + #define CMDQ_MODIFY_ROCE_CC_TLV_ALT_TOS_DSCP_MASK 0x3fUL + #define CMDQ_MODIFY_ROCE_CC_TLV_ALT_TOS_DSCP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD4_MASK 0xffc0UL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD4_SFT 6 + __le16 rtt; + #define CMDQ_MODIFY_ROCE_CC_TLV_RTT_MASK 0x3fffUL + #define CMDQ_MODIFY_ROCE_CC_TLV_RTT_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD5_MASK 0xc000UL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD5_SFT 14 + __le16 tcp_cp; + #define CMDQ_MODIFY_ROCE_CC_TLV_TCP_CP_MASK 0x3ffUL + #define CMDQ_MODIFY_ROCE_CC_TLV_TCP_CP_SFT 0 + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD6_MASK 0xfc00UL + #define CMDQ_MODIFY_ROCE_CC_TLV_RSVD6_SFT 10 + u8 cc_mode; + #define CMDQ_MODIFY_ROCE_CC_TLV_CC_MODE_DCTCP_CC_MODE 0x0UL + #define CMDQ_MODIFY_ROCE_CC_TLV_CC_MODE_PROBABILISTIC_CC_MODE 0x1UL + #define CMDQ_MODIFY_ROCE_CC_TLV_CC_MODE_LAST\ + CMDQ_MODIFY_ROCE_CC_TLV_CC_MODE_PROBABILISTIC_CC_MODE + u8 tx_queue; + __le16 inactivity_th; + u8 time_per_phase; + u8 reserved8_1; + __le16 reserved16; + __le32 reserved32; + __le64 reserved64; + __le64 reservedtlvpad; +}; + +/* cmdq_modify_roce_cc_gen1_tlv (size:768b/96B) */ +struct cmdq_modify_roce_cc_gen1_tlv { + __le16 cmd_discr; + u8 reserved_8b; + u8 tlv_flags; + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_MORE 0x1UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_MORE_LAST 0x0UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_MORE_NOT_LAST 0x1UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_REQUIRED 0x2UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_REQUIRED_NO (0x0UL << 1) + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_REQUIRED_YES (0x1UL << 1) + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_REQUIRED_LAST\ + CMDQ_MODIFY_ROCE_CC_GEN1_TLV_TLV_FLAGS_REQUIRED_YES + __le16 tlv_type; + __le16 length; + __le64 reserved64; + __le64 modify_mask; + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_MIN_TIME_BETWEEN_CNPS 0x1UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_INIT_CP 0x2UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_TR_UPDATE_MODE 0x4UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_TR_UPDATE_CYCLES 0x8UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_FR_NUM_RTTS 0x10UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_AI_RATE_INCREASE 0x20UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_REDUCTION_RELAX_RTTS_TH 0x40UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_ADDITIONAL_RELAX_CR_TH 0x80UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CR_MIN_TH 0x100UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_BW_AVG_WEIGHT 0x200UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_ACTUAL_CR_FACTOR 0x400UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_MAX_CP_CR_TH 0x800UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CP_BIAS_EN 0x1000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CP_BIAS 0x2000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CNP_ECN 0x4000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_RTT_JITTER_EN 0x8000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_LINK_BYTES_PER_USEC 0x10000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_RESET_CC_CR_TH 0x20000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CR_WIDTH 0x40000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_QUOTA_PERIOD_MIN 0x80000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_QUOTA_PERIOD_MAX 0x100000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_QUOTA_PERIOD_ABS_MAX 0x200000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_TR_LOWER_BOUND 0x400000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CR_PROB_FACTOR 0x800000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_TR_PROB_FACTOR 0x1000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_FAIRNESS_CR_TH 0x2000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_RED_DIV 0x4000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CNP_RATIO_TH 0x8000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_EXP_AI_RTTS 0x10000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_EXP_AI_CR_CP_RATIO 0x20000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CP_EXP_UPDATE_TH 0x40000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_HIGH_EXP_AI_RTTS_TH1 0x80000000UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_HIGH_EXP_AI_RTTS_TH2 0x100000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_USE_RATE_TABLE 0x200000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_LINK64B_PER_RTT 0x400000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_ACTUAL_CR_CONG_FREE_RTTS_TH 0x800000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_SEVERE_CONG_CR_TH1 0x1000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_SEVERE_CONG_CR_TH2 0x2000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_CC_ACK_BYTES 0x4000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_REDUCE_INIT_EN 0x8000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_REDUCE_INIT_CONG_FREE_RTTS_TH \ + 0x10000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_RANDOM_NO_RED_EN 0x20000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_ACTUAL_CR_SHIFT_CORRECTION_EN \ + 0x40000000000ULL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_MODIFY_MASK_QUOTA_PERIOD_ADJUST_EN 0x80000000000ULL + __le16 inactivity_th_hi; + __le16 min_time_between_cnps; + __le16 init_cp; + u8 tr_update_mode; + u8 tr_update_cycles; + u8 fr_num_rtts; + u8 ai_rate_increase; + __le16 reduction_relax_rtts_th; + __le16 additional_relax_cr_th; + __le16 cr_min_th; + u8 bw_avg_weight; + u8 actual_cr_factor; + __le16 max_cp_cr_th; + u8 cp_bias_en; + u8 cp_bias; + u8 cnp_ecn; + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_CNP_ECN_NOT_ECT 0x0UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_CNP_ECN_ECT_1 0x1UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_CNP_ECN_ECT_0 0x2UL + #define CMDQ_MODIFY_ROCE_CC_GEN1_TLV_CNP_ECN_LAST CMDQ_MODIFY_ROCE_CC_GEN1_TLV_CNP_ECN_ECT_0 + u8 rtt_jitter_en; + __le16 link_bytes_per_usec; + __le16 reset_cc_cr_th; + u8 cr_width; + u8 quota_period_min; + u8 quota_period_max; + u8 quota_period_abs_max; + __le16 tr_lower_bound; + u8 cr_prob_factor; + u8 tr_prob_factor; + __le16 fairness_cr_th; + u8 red_div; + u8 cnp_ratio_th; + __le16 exp_ai_rtts; + u8 exp_ai_cr_cp_ratio; + u8 use_rate_table; + __le16 cp_exp_update_th; + __le16 high_exp_ai_rtts_th1; + __le16 high_exp_ai_rtts_th2; + __le16 actual_cr_cong_free_rtts_th; + __le16 severe_cong_cr_th1; + __le16 severe_cong_cr_th2; + __le32 link64B_per_rtt; + u8 cc_ack_bytes; + u8 reduce_init_en; + __le16 reduce_init_cong_free_rtts_th; + u8 random_no_red_en; + u8 actual_cr_shift_correction_en; + u8 quota_period_adjust_en; + u8 reserved[5]; +}; + +/* creq_modify_roce_cc_resp (size:128b/16B) */ +struct creq_modify_roce_cc_resp { + u8 type; + #define CREQ_MODIFY_ROCE_CC_RESP_TYPE_MASK 0x3fUL + #define CREQ_MODIFY_ROCE_CC_RESP_TYPE_SFT 0 + #define CREQ_MODIFY_ROCE_CC_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_MODIFY_ROCE_CC_RESP_TYPE_LAST CREQ_MODIFY_ROCE_CC_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_MODIFY_ROCE_CC_RESP_V 0x1UL + u8 event; + #define CREQ_MODIFY_ROCE_CC_RESP_EVENT_MODIFY_ROCE_CC 0x8cUL + #define CREQ_MODIFY_ROCE_CC_RESP_EVENT_LAST CREQ_MODIFY_ROCE_CC_RESP_EVENT_MODIFY_ROCE_CC + u8 reserved48[6]; +}; + +/* cmdq_set_link_aggr_mode_cc (size:320b/40B) */ +struct cmdq_set_link_aggr_mode_cc { + u8 opcode; + #define CMDQ_SET_LINK_AGGR_MODE_OPCODE_SET_LINK_AGGR_MODE 0x8fUL + #define CMDQ_SET_LINK_AGGR_MODE_OPCODE_LAST \ + CMDQ_SET_LINK_AGGR_MODE_OPCODE_SET_LINK_AGGR_MODE + u8 cmd_size; + __le16 flags; + __le16 cookie; + u8 resp_size; + u8 reserved8; + __le64 resp_addr; + __le32 modify_mask; + #define CMDQ_SET_LINK_AGGR_MODE_MODIFY_MASK_AGGR_EN 0x1UL + #define CMDQ_SET_LINK_AGGR_MODE_MODIFY_MASK_ACTIVE_PORT_MAP 0x2UL + #define CMDQ_SET_LINK_AGGR_MODE_MODIFY_MASK_MEMBER_PORT_MAP 0x4UL + #define CMDQ_SET_LINK_AGGR_MODE_MODIFY_MASK_AGGR_MODE 0x8UL + #define CMDQ_SET_LINK_AGGR_MODE_MODIFY_MASK_STAT_CTX_ID 0x10UL + u8 aggr_enable; + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_ENABLE 0x1UL + #define CMDQ_SET_LINK_AGGR_MODE_RSVD1_MASK 0xfeUL + #define CMDQ_SET_LINK_AGGR_MODE_RSVD1_SFT 1 + u8 active_port_map; + #define CMDQ_SET_LINK_AGGR_MODE_ACTIVE_PORT_MAP_MASK 0xfUL + #define CMDQ_SET_LINK_AGGR_MODE_ACTIVE_PORT_MAP_SFT 0 + #define CMDQ_SET_LINK_AGGR_MODE_RSVD2_MASK 0xf0UL + #define CMDQ_SET_LINK_AGGR_MODE_RSVD2_SFT 4 + u8 member_port_map; + u8 link_aggr_mode; + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_ACTIVE_ACTIVE 0x1UL + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_ACTIVE_BACKUP 0x2UL + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_BALANCE_XOR 0x3UL + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_802_3_AD 0x4UL + #define CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_LAST CMDQ_SET_LINK_AGGR_MODE_AGGR_MODE_802_3_AD + __le16 stat_ctx_id[4]; + __le64 rsvd1; +}; + +/* creq_set_link_aggr_mode_resources_resp (size:128b/16B) */ +struct creq_set_link_aggr_mode_resources_resp { + u8 type; + #define CREQ_SET_LINK_AGGR_MODE_RESP_TYPE_MASK 0x3fUL + #define CREQ_SET_LINK_AGGR_MODE_RESP_TYPE_SFT 0 + #define CREQ_SET_LINK_AGGR_MODE_RESP_TYPE_QP_EVENT 0x38UL + #define CREQ_SET_LINK_AGGR_MODE_RESP_TYPE_LAST CREQ_SET_LINK_AGGR_MODE_RESP_TYPE_QP_EVENT + u8 status; + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_SET_LINK_AGGR_MODE_RESP_V 0x1UL + u8 event; + #define CREQ_SET_LINK_AGGR_MODE_RESP_EVENT_SET_LINK_AGGR_MODE 0x8fUL + #define CREQ_SET_LINK_AGGR_MODE_RESP_EVENT_LAST\ + CREQ_SET_LINK_AGGR_MODE_RESP_EVENT_SET_LINK_AGGR_MODE + u8 reserved48[6]; +}; + +/* creq_func_event (size:128b/16B) */ +struct creq_func_event { + u8 type; + #define CREQ_FUNC_EVENT_TYPE_MASK 0x3fUL + #define CREQ_FUNC_EVENT_TYPE_SFT 0 + #define CREQ_FUNC_EVENT_TYPE_FUNC_EVENT 0x3aUL + #define CREQ_FUNC_EVENT_TYPE_LAST CREQ_FUNC_EVENT_TYPE_FUNC_EVENT + u8 reserved56[7]; + u8 v; + #define CREQ_FUNC_EVENT_V 0x1UL + u8 event; + #define CREQ_FUNC_EVENT_EVENT_TX_WQE_ERROR 0x1UL + #define CREQ_FUNC_EVENT_EVENT_TX_DATA_ERROR 0x2UL + #define CREQ_FUNC_EVENT_EVENT_RX_WQE_ERROR 0x3UL + #define CREQ_FUNC_EVENT_EVENT_RX_DATA_ERROR 0x4UL + #define CREQ_FUNC_EVENT_EVENT_CQ_ERROR 0x5UL + #define CREQ_FUNC_EVENT_EVENT_TQM_ERROR 0x6UL + #define CREQ_FUNC_EVENT_EVENT_CFCQ_ERROR 0x7UL + #define CREQ_FUNC_EVENT_EVENT_CFCS_ERROR 0x8UL + #define CREQ_FUNC_EVENT_EVENT_CFCC_ERROR 0x9UL + #define CREQ_FUNC_EVENT_EVENT_CFCM_ERROR 0xaUL + #define CREQ_FUNC_EVENT_EVENT_TIM_ERROR 0xbUL + #define CREQ_FUNC_EVENT_EVENT_VF_COMM_REQUEST 0x80UL + #define CREQ_FUNC_EVENT_EVENT_RESOURCE_EXHAUSTED 0x81UL + #define CREQ_FUNC_EVENT_EVENT_LAST CREQ_FUNC_EVENT_EVENT_RESOURCE_EXHAUSTED + u8 reserved48[6]; +}; + +/* creq_qp_event (size:128b/16B) */ +struct creq_qp_event { + u8 type; + #define CREQ_QP_EVENT_TYPE_MASK 0x3fUL + #define CREQ_QP_EVENT_TYPE_SFT 0 + #define CREQ_QP_EVENT_TYPE_QP_EVENT 0x38UL + #define CREQ_QP_EVENT_TYPE_LAST CREQ_QP_EVENT_TYPE_QP_EVENT + u8 status; + #define CREQ_QP_EVENT_STATUS_SUCCESS 0x0UL + #define CREQ_QP_EVENT_STATUS_FAIL 0x1UL + #define CREQ_QP_EVENT_STATUS_RESOURCES 0x2UL + #define CREQ_QP_EVENT_STATUS_INVALID_CMD 0x3UL + #define CREQ_QP_EVENT_STATUS_NOT_IMPLEMENTED 0x4UL + #define CREQ_QP_EVENT_STATUS_INVALID_PARAMETER 0x5UL + #define CREQ_QP_EVENT_STATUS_HARDWARE_ERROR 0x6UL + #define CREQ_QP_EVENT_STATUS_INTERNAL_ERROR 0x7UL + #define CREQ_QP_EVENT_STATUS_LAST CREQ_QP_EVENT_STATUS_INTERNAL_ERROR + __le16 cookie; + __le32 reserved32; + u8 v; + #define CREQ_QP_EVENT_V 0x1UL + u8 event; + #define CREQ_QP_EVENT_EVENT_CREATE_QP 0x1UL + #define CREQ_QP_EVENT_EVENT_DESTROY_QP 0x2UL + #define CREQ_QP_EVENT_EVENT_MODIFY_QP 0x3UL + #define CREQ_QP_EVENT_EVENT_QUERY_QP 0x4UL + #define CREQ_QP_EVENT_EVENT_CREATE_SRQ 0x5UL + #define CREQ_QP_EVENT_EVENT_DESTROY_SRQ 0x6UL + #define CREQ_QP_EVENT_EVENT_QUERY_SRQ 0x8UL + #define CREQ_QP_EVENT_EVENT_CREATE_CQ 0x9UL + #define CREQ_QP_EVENT_EVENT_DESTROY_CQ 0xaUL + #define CREQ_QP_EVENT_EVENT_RESIZE_CQ 0xcUL + #define CREQ_QP_EVENT_EVENT_ALLOCATE_MRW 0xdUL + #define CREQ_QP_EVENT_EVENT_DEALLOCATE_KEY 0xeUL + #define CREQ_QP_EVENT_EVENT_REGISTER_MR 0xfUL + #define CREQ_QP_EVENT_EVENT_DEREGISTER_MR 0x10UL + #define CREQ_QP_EVENT_EVENT_ADD_GID 0x11UL + #define CREQ_QP_EVENT_EVENT_DELETE_GID 0x12UL + #define CREQ_QP_EVENT_EVENT_MODIFY_GID 0x17UL + #define CREQ_QP_EVENT_EVENT_QUERY_GID 0x18UL + #define CREQ_QP_EVENT_EVENT_CREATE_QP1 0x13UL + #define CREQ_QP_EVENT_EVENT_DESTROY_QP1 0x14UL + #define CREQ_QP_EVENT_EVENT_CREATE_AH 0x15UL + #define CREQ_QP_EVENT_EVENT_DESTROY_AH 0x16UL + #define CREQ_QP_EVENT_EVENT_INITIALIZE_FW 0x80UL + #define CREQ_QP_EVENT_EVENT_DEINITIALIZE_FW 0x81UL + #define CREQ_QP_EVENT_EVENT_STOP_FUNC 0x82UL + #define CREQ_QP_EVENT_EVENT_QUERY_FUNC 0x83UL + #define CREQ_QP_EVENT_EVENT_SET_FUNC_RESOURCES 0x84UL + #define CREQ_QP_EVENT_EVENT_READ_CONTEXT 0x85UL + #define CREQ_QP_EVENT_EVENT_MAP_TC_TO_COS 0x8aUL + #define CREQ_QP_EVENT_EVENT_QUERY_VERSION 0x8bUL + #define CREQ_QP_EVENT_EVENT_MODIFY_CC 0x8cUL + #define CREQ_QP_EVENT_EVENT_QUERY_CC 0x8dUL + #define CREQ_QP_EVENT_EVENT_QUERY_ROCE_STATS 0x8eUL + #define CREQ_QP_EVENT_EVENT_SET_LINK_AGGR_MODE 0x8fUL + #define CREQ_QP_EVENT_EVENT_QUERY_QP_EXTEND 0x91UL + #define CREQ_QP_EVENT_EVENT_QP_ERROR_NOTIFICATION 0xc0UL + #define CREQ_QP_EVENT_EVENT_CQ_ERROR_NOTIFICATION 0xc1UL + #define CREQ_QP_EVENT_EVENT_LAST CREQ_QP_EVENT_EVENT_CQ_ERROR_NOTIFICATION + u8 reserved48[6]; +}; + +/* creq_qp_error_notification (size:128b/16B) */ +struct creq_qp_error_notification { + u8 type; + #define CREQ_QP_ERROR_NOTIFICATION_TYPE_MASK 0x3fUL + #define CREQ_QP_ERROR_NOTIFICATION_TYPE_SFT 0 + #define CREQ_QP_ERROR_NOTIFICATION_TYPE_QP_EVENT 0x38UL + #define CREQ_QP_ERROR_NOTIFICATION_TYPE_LAST CREQ_QP_ERROR_NOTIFICATION_TYPE_QP_EVENT + u8 status; + u8 req_slow_path_state; + u8 req_err_state_reason; + __le32 xid; + u8 v; + #define CREQ_QP_ERROR_NOTIFICATION_V 0x1UL + u8 event; + #define CREQ_QP_ERROR_NOTIFICATION_EVENT_QP_ERROR_NOTIFICATION 0xc0UL + #define CREQ_QP_ERROR_NOTIFICATION_EVENT_LAST \ + CREQ_QP_ERROR_NOTIFICATION_EVENT_QP_ERROR_NOTIFICATION + u8 res_slow_path_state; + u8 res_err_state_reason; + __le16 sq_cons_idx; + __le16 rq_cons_idx; +}; + +/* creq_cq_error_notification (size:128b/16B) */ +struct creq_cq_error_notification { + u8 type; + #define CREQ_CQ_ERROR_NOTIFICATION_TYPE_MASK 0x3fUL + #define CREQ_CQ_ERROR_NOTIFICATION_TYPE_SFT 0 + #define CREQ_CQ_ERROR_NOTIFICATION_TYPE_CQ_EVENT 0x38UL + #define CREQ_CQ_ERROR_NOTIFICATION_TYPE_LAST CREQ_CQ_ERROR_NOTIFICATION_TYPE_CQ_EVENT + u8 status; + u8 cq_err_reason; + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_REQ_CQ_INVALID_ERROR 0x1UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_REQ_CQ_OVERFLOW_ERROR 0x2UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_REQ_CQ_LOAD_ERROR 0x3UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_RES_CQ_INVALID_ERROR 0x4UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_RES_CQ_OVERFLOW_ERROR 0x5UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_RES_CQ_LOAD_ERROR 0x6UL + #define CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_LAST \ + CREQ_CQ_ERROR_NOTIFICATION_CQ_ERR_REASON_RES_CQ_LOAD_ERROR + u8 reserved8; + __le32 xid; + u8 v; + #define CREQ_CQ_ERROR_NOTIFICATION_V 0x1UL + u8 event; + #define CREQ_CQ_ERROR_NOTIFICATION_EVENT_CQ_ERROR_NOTIFICATION 0xc1UL + #define CREQ_CQ_ERROR_NOTIFICATION_EVENT_LAST \ + CREQ_CQ_ERROR_NOTIFICATION_EVENT_CQ_ERROR_NOTIFICATION + u8 reserved48[6]; +}; + +/* sq_base (size:64b/8B) */ +struct sq_base { + u8 wqe_type; + #define SQ_BASE_WQE_TYPE_SEND 0x0UL + #define SQ_BASE_WQE_TYPE_SEND_W_IMMEAD 0x1UL + #define SQ_BASE_WQE_TYPE_SEND_W_INVALID 0x2UL + #define SQ_BASE_WQE_TYPE_WRITE_WQE 0x4UL + #define SQ_BASE_WQE_TYPE_WRITE_W_IMMEAD 0x5UL + #define SQ_BASE_WQE_TYPE_READ_WQE 0x6UL + #define SQ_BASE_WQE_TYPE_ATOMIC_CS 0x8UL + #define SQ_BASE_WQE_TYPE_ATOMIC_FA 0xbUL + #define SQ_BASE_WQE_TYPE_LOCAL_INVALID 0xcUL + #define SQ_BASE_WQE_TYPE_FR_PMR 0xdUL + #define SQ_BASE_WQE_TYPE_BIND 0xeUL + #define SQ_BASE_WQE_TYPE_FR_PPMR 0xfUL + #define SQ_BASE_WQE_TYPE_LAST SQ_BASE_WQE_TYPE_FR_PPMR + u8 unused_0[7]; +}; + +/* sq_sge (size:128b/16B) */ +struct sq_sge { + __le64 va_or_pa; + __le32 l_key; + __le32 size; +}; + +/* sq_psn_search (size:64b/8B) */ +struct sq_psn_search { + __le32 opcode_start_psn; + #define SQ_PSN_SEARCH_START_PSN_MASK 0xffffffUL + #define SQ_PSN_SEARCH_START_PSN_SFT 0 + #define SQ_PSN_SEARCH_OPCODE_MASK 0xff000000UL + #define SQ_PSN_SEARCH_OPCODE_SFT 24 + __le32 flags_next_psn; + #define SQ_PSN_SEARCH_NEXT_PSN_MASK 0xffffffUL + #define SQ_PSN_SEARCH_NEXT_PSN_SFT 0 + #define SQ_PSN_SEARCH_FLAGS_MASK 0xff000000UL + #define SQ_PSN_SEARCH_FLAGS_SFT 24 +}; + +/* sq_psn_search_ext (size:128b/16B) */ +struct sq_psn_search_ext { + __le32 opcode_start_psn; + #define SQ_PSN_SEARCH_EXT_START_PSN_MASK 0xffffffUL + #define SQ_PSN_SEARCH_EXT_START_PSN_SFT 0 + #define SQ_PSN_SEARCH_EXT_OPCODE_MASK 0xff000000UL + #define SQ_PSN_SEARCH_EXT_OPCODE_SFT 24 + __le32 flags_next_psn; + #define SQ_PSN_SEARCH_EXT_NEXT_PSN_MASK 0xffffffUL + #define SQ_PSN_SEARCH_EXT_NEXT_PSN_SFT 0 + #define SQ_PSN_SEARCH_EXT_FLAGS_MASK 0xff000000UL + #define SQ_PSN_SEARCH_EXT_FLAGS_SFT 24 + __le16 start_slot_idx; + __le16 reserved16; + __le32 reserved32; +}; + +/* sq_send (size:1024b/128B) */ +struct sq_send { + u8 wqe_type; + #define SQ_SEND_WQE_TYPE_SEND 0x0UL + #define SQ_SEND_WQE_TYPE_SEND_W_IMMEAD 0x1UL + #define SQ_SEND_WQE_TYPE_SEND_W_INVALID 0x2UL + #define SQ_SEND_WQE_TYPE_LAST SQ_SEND_WQE_TYPE_SEND_W_INVALID + u8 flags; + #define SQ_SEND_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_SEND_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_SEND_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_SEND_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_SEND_FLAGS_UC_FENCE 0x4UL + #define SQ_SEND_FLAGS_SE 0x8UL + #define SQ_SEND_FLAGS_INLINE 0x10UL + #define SQ_SEND_FLAGS_WQE_TS_EN 0x20UL + #define SQ_SEND_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8_1; + __le32 inv_key_or_imm_data; + __le32 length; + __le32 q_key; + __le32 dst_qp; + #define SQ_SEND_DST_QP_MASK 0xffffffUL + #define SQ_SEND_DST_QP_SFT 0 + __le32 avid; + #define SQ_SEND_AVID_MASK 0xfffffUL + #define SQ_SEND_AVID_SFT 0 + __le32 reserved32; + __le32 timestamp; + #define SQ_SEND_TIMESTAMP_MASK 0xffffffUL + #define SQ_SEND_TIMESTAMP_SFT 0 + __le32 data[24]; +}; + +/* sq_send_hdr (size:256b/32B) */ +struct sq_send_hdr { + u8 wqe_type; + #define SQ_SEND_HDR_WQE_TYPE_SEND 0x0UL + #define SQ_SEND_HDR_WQE_TYPE_SEND_W_IMMEAD 0x1UL + #define SQ_SEND_HDR_WQE_TYPE_SEND_W_INVALID 0x2UL + #define SQ_SEND_HDR_WQE_TYPE_LAST SQ_SEND_HDR_WQE_TYPE_SEND_W_INVALID + u8 flags; + #define SQ_SEND_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_SEND_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_SEND_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_SEND_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_SEND_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_SEND_HDR_FLAGS_SE 0x8UL + #define SQ_SEND_HDR_FLAGS_INLINE 0x10UL + #define SQ_SEND_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_SEND_HDR_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8_1; + __le32 inv_key_or_imm_data; + __le32 length; + __le32 q_key; + __le32 dst_qp; + #define SQ_SEND_HDR_DST_QP_MASK 0xffffffUL + #define SQ_SEND_HDR_DST_QP_SFT 0 + __le32 avid; + #define SQ_SEND_HDR_AVID_MASK 0xfffffUL + #define SQ_SEND_HDR_AVID_SFT 0 + __le32 reserved32; + __le32 timestamp; + #define SQ_SEND_HDR_TIMESTAMP_MASK 0xffffffUL + #define SQ_SEND_HDR_TIMESTAMP_SFT 0 +}; + +/* sq_send_raweth_qp1 (size:1024b/128B) */ +struct sq_send_raweth_qp1 { + u8 wqe_type; + #define SQ_SEND_RAWETH_QP1_WQE_TYPE_SEND 0x0UL + #define SQ_SEND_RAWETH_QP1_WQE_TYPE_LAST SQ_SEND_RAWETH_QP1_WQE_TYPE_SEND + u8 flags; + #define SQ_SEND_RAWETH_QP1_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK \ + 0xffUL + #define SQ_SEND_RAWETH_QP1_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT \ + 0 + #define SQ_SEND_RAWETH_QP1_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_SEND_RAWETH_QP1_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_SEND_RAWETH_QP1_FLAGS_UC_FENCE 0x4UL + #define SQ_SEND_RAWETH_QP1_FLAGS_SE 0x8UL + #define SQ_SEND_RAWETH_QP1_FLAGS_INLINE 0x10UL + #define SQ_SEND_RAWETH_QP1_FLAGS_WQE_TS_EN 0x20UL + #define SQ_SEND_RAWETH_QP1_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8; + __le16 lflags; + #define SQ_SEND_RAWETH_QP1_LFLAGS_TCP_UDP_CHKSUM 0x1UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_IP_CHKSUM 0x2UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_NOCRC 0x4UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_STAMP 0x8UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_T_IP_CHKSUM 0x10UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_ROCE_CRC 0x100UL + #define SQ_SEND_RAWETH_QP1_LFLAGS_FCOE_CRC 0x200UL + __le16 cfa_action; + __le32 length; + __le32 reserved32_1; + __le32 cfa_meta; + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_MASK 0xfffUL + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_VID_SFT 0 + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_DE 0x1000UL + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_MASK 0xe000UL + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_PRI_SFT 13 + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_MASK 0x70000UL + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_SFT 16 + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID88A8 (0x0UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID8100 (0x1UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9100 (0x2UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9200 (0x3UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPID9300 (0x4UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG (0x5UL << 16) + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_LAST\ + SQ_SEND_RAWETH_QP1_CFA_META_VLAN_TPID_TPIDCFG + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_MASK 0xff80000UL + #define SQ_SEND_RAWETH_QP1_CFA_META_VLAN_RESERVED_SFT 19 + #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_MASK 0xf0000000UL + #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_SFT 28 + #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_NONE (0x0UL << 28) + #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG (0x1UL << 28) + #define SQ_SEND_RAWETH_QP1_CFA_META_KEY_LAST SQ_SEND_RAWETH_QP1_CFA_META_KEY_VLAN_TAG + __le32 reserved32_2; + __le32 reserved32_3; + __le32 timestamp; + #define SQ_SEND_RAWETH_QP1_TIMESTAMP_MASK 0xffffffUL + #define SQ_SEND_RAWETH_QP1_TIMESTAMP_SFT 0 + __le32 data[24]; +}; + +/* sq_send_raweth_qp1_hdr (size:256b/32B) */ +struct sq_send_raweth_qp1_hdr { + u8 wqe_type; + #define SQ_SEND_RAWETH_QP1_HDR_WQE_TYPE_SEND 0x0UL + #define SQ_SEND_RAWETH_QP1_HDR_WQE_TYPE_LAST SQ_SEND_RAWETH_QP1_HDR_WQE_TYPE_SEND + u8 flags; + #define \ + SQ_SEND_RAWETH_QP1_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT\ + 0 + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_SE 0x8UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_INLINE 0x10UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_SEND_RAWETH_QP1_HDR_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8; + __le16 lflags; + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_TCP_UDP_CHKSUM 0x1UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_IP_CHKSUM 0x2UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_NOCRC 0x4UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_STAMP 0x8UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_T_IP_CHKSUM 0x10UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_ROCE_CRC 0x100UL + #define SQ_SEND_RAWETH_QP1_HDR_LFLAGS_FCOE_CRC 0x200UL + __le16 cfa_action; + __le32 length; + __le32 reserved32_1; + __le32 cfa_meta; + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_VID_MASK 0xfffUL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_VID_SFT 0 + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_DE 0x1000UL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_PRI_MASK 0xe000UL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_PRI_SFT 13 + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_MASK 0x70000UL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_SFT 16 + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPID88A8 (0x0UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPID8100 (0x1UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPID9100 (0x2UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPID9200 (0x3UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPID9300 (0x4UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPIDCFG (0x5UL << 16) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_LAST\ + SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_TPID_TPIDCFG + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_RESERVED_MASK 0xff80000UL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_VLAN_RESERVED_SFT 19 + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_MASK 0xf0000000UL + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_SFT 28 + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_NONE (0x0UL << 28) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_VLAN_TAG (0x1UL << 28) + #define SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_LAST\ + SQ_SEND_RAWETH_QP1_HDR_CFA_META_KEY_VLAN_TAG + __le32 reserved32_2; + __le32 reserved32_3; + __le32 timestamp; + #define SQ_SEND_RAWETH_QP1_HDR_TIMESTAMP_MASK 0xffffffUL + #define SQ_SEND_RAWETH_QP1_HDR_TIMESTAMP_SFT 0 +}; + +/* sq_rdma (size:1024b/128B) */ +struct sq_rdma { + u8 wqe_type; + #define SQ_RDMA_WQE_TYPE_WRITE_WQE 0x4UL + #define SQ_RDMA_WQE_TYPE_WRITE_W_IMMEAD 0x5UL + #define SQ_RDMA_WQE_TYPE_READ_WQE 0x6UL + #define SQ_RDMA_WQE_TYPE_LAST SQ_RDMA_WQE_TYPE_READ_WQE + u8 flags; + #define SQ_RDMA_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_RDMA_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_RDMA_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_RDMA_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_RDMA_FLAGS_UC_FENCE 0x4UL + #define SQ_RDMA_FLAGS_SE 0x8UL + #define SQ_RDMA_FLAGS_INLINE 0x10UL + #define SQ_RDMA_FLAGS_WQE_TS_EN 0x20UL + #define SQ_RDMA_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8; + __le32 imm_data; + __le32 length; + __le32 reserved32_1; + __le64 remote_va; + __le32 remote_key; + __le32 timestamp; + #define SQ_RDMA_TIMESTAMP_MASK 0xffffffUL + #define SQ_RDMA_TIMESTAMP_SFT 0 + __le32 data[24]; }; -/* creq_query_roce_stats_ext_resp_sb (size:1536b/192B) */ -struct creq_query_roce_stats_ext_resp_sb { - u8 opcode; - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT 0x92UL - #define CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_LAST \ - CREQ_QUERY_ROCE_STATS_EXT_RESP_SB_OPCODE_QUERY_ROCE_STATS_EXT - u8 status; - __le16 cookie; - __le16 flags; - u8 resp_size; - u8 rsvd; - __le64 tx_atomic_req_pkts; - __le64 tx_read_req_pkts; - __le64 tx_read_res_pkts; - __le64 tx_write_req_pkts; - __le64 tx_send_req_pkts; - __le64 tx_roce_pkts; - __le64 tx_roce_bytes; - __le64 rx_atomic_req_pkts; - __le64 rx_read_req_pkts; - __le64 rx_read_res_pkts; - __le64 rx_write_req_pkts; - __le64 rx_send_req_pkts; - __le64 rx_roce_pkts; - __le64 rx_roce_bytes; - __le64 rx_roce_good_pkts; - __le64 rx_roce_good_bytes; - __le64 rx_out_of_buffer_pkts; - __le64 rx_out_of_sequence_pkts; - __le64 tx_cnp_pkts; - __le64 rx_cnp_pkts; - __le64 rx_ecn_marked_pkts; - __le64 tx_cnp_bytes; - __le64 rx_cnp_bytes; -}; - -/* QP error notification event (16 bytes) */ -struct creq_qp_error_notification { - u8 type; - #define CREQ_QP_ERROR_NOTIFICATION_TYPE_MASK 0x3fUL - #define CREQ_QP_ERROR_NOTIFICATION_TYPE_SFT 0 - #define CREQ_QP_ERROR_NOTIFICATION_TYPE_QP_EVENT 0x38UL - #define CREQ_QP_ERROR_NOTIFICATION_RESERVED2_MASK 0xc0UL - #define CREQ_QP_ERROR_NOTIFICATION_RESERVED2_SFT 6 - u8 status; - u8 req_slow_path_state; - u8 req_err_state_reason; - __le32 xid; - u8 v; - #define CREQ_QP_ERROR_NOTIFICATION_V 0x1UL - #define CREQ_QP_ERROR_NOTIFICATION_RESERVED7_MASK 0xfeUL - #define CREQ_QP_ERROR_NOTIFICATION_RESERVED7_SFT 1 - u8 event; - #define CREQ_QP_ERROR_NOTIFICATION_EVENT_QP_ERROR_NOTIFICATION 0xc0UL - u8 res_slow_path_state; - u8 res_err_state_reason; - __le16 sq_cons_idx; - __le16 rq_cons_idx; +/* sq_rdma_hdr (size:256b/32B) */ +struct sq_rdma_hdr { + u8 wqe_type; + #define SQ_RDMA_HDR_WQE_TYPE_WRITE_WQE 0x4UL + #define SQ_RDMA_HDR_WQE_TYPE_WRITE_W_IMMEAD 0x5UL + #define SQ_RDMA_HDR_WQE_TYPE_READ_WQE 0x6UL + #define SQ_RDMA_HDR_WQE_TYPE_LAST SQ_RDMA_HDR_WQE_TYPE_READ_WQE + u8 flags; + #define SQ_RDMA_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_RDMA_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_RDMA_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_RDMA_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_RDMA_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_RDMA_HDR_FLAGS_SE 0x8UL + #define SQ_RDMA_HDR_FLAGS_INLINE 0x10UL + #define SQ_RDMA_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_RDMA_HDR_FLAGS_DEBUG_TRACE 0x40UL + u8 wqe_size; + u8 reserved8; + __le32 imm_data; + __le32 length; + __le32 reserved32_1; + __le64 remote_va; + __le32 remote_key; + __le32 timestamp; + #define SQ_RDMA_HDR_TIMESTAMP_MASK 0xffffffUL + #define SQ_RDMA_HDR_TIMESTAMP_SFT 0 }; -/* RoCE Slowpath HSI Specification 1.6.0 */ -#define ROCE_SP_HSI_VERSION_MAJOR 1 -#define ROCE_SP_HSI_VERSION_MINOR 6 -#define ROCE_SP_HSI_VERSION_UPDATE 0 +/* sq_atomic (size:1024b/128B) */ +struct sq_atomic { + u8 wqe_type; + #define SQ_ATOMIC_WQE_TYPE_ATOMIC_CS 0x8UL + #define SQ_ATOMIC_WQE_TYPE_ATOMIC_FA 0xbUL + #define SQ_ATOMIC_WQE_TYPE_LAST SQ_ATOMIC_WQE_TYPE_ATOMIC_FA + u8 flags; + #define SQ_ATOMIC_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_ATOMIC_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_ATOMIC_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_ATOMIC_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_ATOMIC_FLAGS_UC_FENCE 0x4UL + #define SQ_ATOMIC_FLAGS_SE 0x8UL + #define SQ_ATOMIC_FLAGS_INLINE 0x10UL + #define SQ_ATOMIC_FLAGS_WQE_TS_EN 0x20UL + #define SQ_ATOMIC_FLAGS_DEBUG_TRACE 0x40UL + __le16 reserved16; + __le32 remote_key; + __le64 remote_va; + __le64 swap_data; + __le64 cmp_data; + __le32 data[24]; +}; -#define ROCE_SP_HSI_VERSION_STR "1.6.0" -/* - * Following is the signature for ROCE_SP_HSI message field that indicates not - * applicable (All F's). Need to cast it the size of the field if needed. - */ -#define ROCE_SP_HSI_NA_SIGNATURE ((__le32)(-1)) -#endif /* __BNXT_RE_HSI_H__ */ +/* sq_atomic_hdr (size:256b/32B) */ +struct sq_atomic_hdr { + u8 wqe_type; + #define SQ_ATOMIC_HDR_WQE_TYPE_ATOMIC_CS 0x8UL + #define SQ_ATOMIC_HDR_WQE_TYPE_ATOMIC_FA 0xbUL + #define SQ_ATOMIC_HDR_WQE_TYPE_LAST SQ_ATOMIC_HDR_WQE_TYPE_ATOMIC_FA + u8 flags; + #define SQ_ATOMIC_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_ATOMIC_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_ATOMIC_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_ATOMIC_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_ATOMIC_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_ATOMIC_HDR_FLAGS_SE 0x8UL + #define SQ_ATOMIC_HDR_FLAGS_INLINE 0x10UL + #define SQ_ATOMIC_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_ATOMIC_HDR_FLAGS_DEBUG_TRACE 0x40UL + __le16 reserved16; + __le32 remote_key; + __le64 remote_va; + __le64 swap_data; + __le64 cmp_data; +}; + +/* sq_localinvalidate (size:1024b/128B) */ +struct sq_localinvalidate { + u8 wqe_type; + #define SQ_LOCALINVALIDATE_WQE_TYPE_LOCAL_INVALID 0xcUL + #define SQ_LOCALINVALIDATE_WQE_TYPE_LAST SQ_LOCALINVALIDATE_WQE_TYPE_LOCAL_INVALID + u8 flags; + #define SQ_LOCALINVALIDATE_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK\ + 0xffUL + #define SQ_LOCALINVALIDATE_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT\ + 0 + #define SQ_LOCALINVALIDATE_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_LOCALINVALIDATE_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_LOCALINVALIDATE_FLAGS_UC_FENCE 0x4UL + #define SQ_LOCALINVALIDATE_FLAGS_SE 0x8UL + #define SQ_LOCALINVALIDATE_FLAGS_INLINE 0x10UL + #define SQ_LOCALINVALIDATE_FLAGS_WQE_TS_EN 0x20UL + #define SQ_LOCALINVALIDATE_FLAGS_DEBUG_TRACE 0x40UL + __le16 reserved16; + __le32 inv_l_key; + __le64 reserved64; + u8 reserved128[16]; + __le32 data[24]; +}; + +/* sq_localinvalidate_hdr (size:256b/32B) */ +struct sq_localinvalidate_hdr { + u8 wqe_type; + #define SQ_LOCALINVALIDATE_HDR_WQE_TYPE_LOCAL_INVALID 0xcUL + #define SQ_LOCALINVALIDATE_HDR_WQE_TYPE_LAST SQ_LOCALINVALIDATE_HDR_WQE_TYPE_LOCAL_INVALID + u8 flags; + #define \ + SQ_LOCALINVALIDATE_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT\ + 0 + #define SQ_LOCALINVALIDATE_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_SE 0x8UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_INLINE 0x10UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_LOCALINVALIDATE_HDR_FLAGS_DEBUG_TRACE 0x40UL + __le16 reserved16; + __le32 inv_l_key; + __le64 reserved64; + u8 reserved128[16]; +}; + +/* sq_fr_pmr (size:1024b/128B) */ +struct sq_fr_pmr { + u8 wqe_type; + #define SQ_FR_PMR_WQE_TYPE_FR_PMR 0xdUL + #define SQ_FR_PMR_WQE_TYPE_LAST SQ_FR_PMR_WQE_TYPE_FR_PMR + u8 flags; + #define SQ_FR_PMR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_FR_PMR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_FR_PMR_FLAGS_UC_FENCE 0x4UL + #define SQ_FR_PMR_FLAGS_SE 0x8UL + #define SQ_FR_PMR_FLAGS_INLINE 0x10UL + #define SQ_FR_PMR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_FR_PMR_FLAGS_DEBUG_TRACE 0x40UL + u8 access_cntl; + #define SQ_FR_PMR_ACCESS_CNTL_LOCAL_WRITE 0x1UL + #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_READ 0x2UL + #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_WRITE 0x4UL + #define SQ_FR_PMR_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL + #define SQ_FR_PMR_ACCESS_CNTL_WINDOW_BIND 0x10UL + u8 zero_based_page_size_log; + #define SQ_FR_PMR_PAGE_SIZE_LOG_MASK 0x1fUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_SFT 0 + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4K 0x0UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8K 0x1UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_16K 0x2UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_32K 0x3UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_64K 0x4UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_128K 0x5UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_256K 0x6UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_512K 0x7UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1M 0x8UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_2M 0x9UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4M 0xaUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8M 0xbUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_16M 0xcUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_32M 0xdUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_64M 0xeUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_128M 0xfUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_256M 0x10UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_512M 0x11UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1G 0x12UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_2G 0x13UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4G 0x14UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8G 0x15UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_16G 0x16UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_32G 0x17UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_64G 0x18UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_128G 0x19UL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_256G 0x1aUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_512G 0x1bUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_1T 0x1cUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_2T 0x1dUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_4T 0x1eUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8T 0x1fUL + #define SQ_FR_PMR_PAGE_SIZE_LOG_LAST SQ_FR_PMR_PAGE_SIZE_LOG_PGSZ_8T + #define SQ_FR_PMR_ZERO_BASED 0x20UL + __le32 l_key; + u8 length[5]; + u8 reserved8_1; + u8 reserved8_2; + u8 numlevels_pbl_page_size_log; + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_MASK 0x1fUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_SFT 0 + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4K 0x0UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8K 0x1UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_16K 0x2UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_32K 0x3UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_64K 0x4UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_128K 0x5UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_256K 0x6UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_512K 0x7UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1M 0x8UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_2M 0x9UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4M 0xaUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8M 0xbUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_16M 0xcUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_32M 0xdUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_64M 0xeUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_128M 0xfUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_256M 0x10UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_512M 0x11UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1G 0x12UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_2G 0x13UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4G 0x14UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8G 0x15UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_16G 0x16UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_32G 0x17UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_64G 0x18UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_128G 0x19UL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_256G 0x1aUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_512G 0x1bUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_1T 0x1cUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_2T 0x1dUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_4T 0x1eUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8T 0x1fUL + #define SQ_FR_PMR_PBL_PAGE_SIZE_LOG_LAST SQ_FR_PMR_PBL_PAGE_SIZE_LOG_PGSZ_8T + #define SQ_FR_PMR_NUMLEVELS_MASK 0xc0UL + #define SQ_FR_PMR_NUMLEVELS_SFT 6 + #define SQ_FR_PMR_NUMLEVELS_PHYSICAL (0x0UL << 6) + #define SQ_FR_PMR_NUMLEVELS_LAYER1 (0x1UL << 6) + #define SQ_FR_PMR_NUMLEVELS_LAYER2 (0x2UL << 6) + #define SQ_FR_PMR_NUMLEVELS_LAST SQ_FR_PMR_NUMLEVELS_LAYER2 + __le64 pblptr; + __le64 va; + __le32 data[24]; +}; + +/* sq_fr_pmr_hdr (size:256b/32B) */ +struct sq_fr_pmr_hdr { + u8 wqe_type; + #define SQ_FR_PMR_HDR_WQE_TYPE_FR_PMR 0xdUL + #define SQ_FR_PMR_HDR_WQE_TYPE_LAST SQ_FR_PMR_HDR_WQE_TYPE_FR_PMR + u8 flags; + #define SQ_FR_PMR_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_FR_PMR_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_FR_PMR_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_FR_PMR_HDR_FLAGS_SE 0x8UL + #define SQ_FR_PMR_HDR_FLAGS_INLINE 0x10UL + #define SQ_FR_PMR_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_FR_PMR_HDR_FLAGS_DEBUG_TRACE 0x40UL + u8 access_cntl; + #define SQ_FR_PMR_HDR_ACCESS_CNTL_LOCAL_WRITE 0x1UL + #define SQ_FR_PMR_HDR_ACCESS_CNTL_REMOTE_READ 0x2UL + #define SQ_FR_PMR_HDR_ACCESS_CNTL_REMOTE_WRITE 0x4UL + #define SQ_FR_PMR_HDR_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL + #define SQ_FR_PMR_HDR_ACCESS_CNTL_WINDOW_BIND 0x10UL + u8 zero_based_page_size_log; + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_MASK 0x1fUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_SFT 0 + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_4K 0x0UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_8K 0x1UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_16K 0x2UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_32K 0x3UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_64K 0x4UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_128K 0x5UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_256K 0x6UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_512K 0x7UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_1M 0x8UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_2M 0x9UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_4M 0xaUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_8M 0xbUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_16M 0xcUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_32M 0xdUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_64M 0xeUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_128M 0xfUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_256M 0x10UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_512M 0x11UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_1G 0x12UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_2G 0x13UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_4G 0x14UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_8G 0x15UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_16G 0x16UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_32G 0x17UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_64G 0x18UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_128G 0x19UL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_256G 0x1aUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_512G 0x1bUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_1T 0x1cUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_2T 0x1dUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_4T 0x1eUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_8T 0x1fUL + #define SQ_FR_PMR_HDR_PAGE_SIZE_LOG_LAST SQ_FR_PMR_HDR_PAGE_SIZE_LOG_PGSZ_8T + #define SQ_FR_PMR_HDR_ZERO_BASED 0x20UL + __le32 l_key; + u8 length[5]; + u8 reserved8_1; + u8 reserved8_2; + u8 numlevels_pbl_page_size_log; + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_MASK 0x1fUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_SFT 0 + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_4K 0x0UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_8K 0x1UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_16K 0x2UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_32K 0x3UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_64K 0x4UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_128K 0x5UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_256K 0x6UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_512K 0x7UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_1M 0x8UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_2M 0x9UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_4M 0xaUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_8M 0xbUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_16M 0xcUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_32M 0xdUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_64M 0xeUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_128M 0xfUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_256M 0x10UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_512M 0x11UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_1G 0x12UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_2G 0x13UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_4G 0x14UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_8G 0x15UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_16G 0x16UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_32G 0x17UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_64G 0x18UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_128G 0x19UL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_256G 0x1aUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_512G 0x1bUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_1T 0x1cUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_2T 0x1dUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_4T 0x1eUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_8T 0x1fUL + #define SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_LAST SQ_FR_PMR_HDR_PBL_PAGE_SIZE_LOG_PGSZ_8T + #define SQ_FR_PMR_HDR_NUMLEVELS_MASK 0xc0UL + #define SQ_FR_PMR_HDR_NUMLEVELS_SFT 6 + #define SQ_FR_PMR_HDR_NUMLEVELS_PHYSICAL (0x0UL << 6) + #define SQ_FR_PMR_HDR_NUMLEVELS_LAYER1 (0x1UL << 6) + #define SQ_FR_PMR_HDR_NUMLEVELS_LAYER2 (0x2UL << 6) + #define SQ_FR_PMR_HDR_NUMLEVELS_LAST SQ_FR_PMR_HDR_NUMLEVELS_LAYER2 + __le64 pblptr; + __le64 va; +}; + +/* sq_bind (size:1024b/128B) */ +struct sq_bind { + u8 wqe_type; + #define SQ_BIND_WQE_TYPE_BIND 0xeUL + #define SQ_BIND_WQE_TYPE_LAST SQ_BIND_WQE_TYPE_BIND + u8 flags; + #define SQ_BIND_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_BIND_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_BIND_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_BIND_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_BIND_FLAGS_UC_FENCE 0x4UL + #define SQ_BIND_FLAGS_SE 0x8UL + #define SQ_BIND_FLAGS_INLINE 0x10UL + #define SQ_BIND_FLAGS_WQE_TS_EN 0x20UL + #define SQ_BIND_FLAGS_DEBUG_TRACE 0x40UL + u8 access_cntl; + #define \ + SQ_BIND_ACCESS_CNTL_WINDOW_BIND_REMOTE_ATOMIC_REMOTE_WRITE_REMOTE_READ_LOCAL_WRITE_MASK\ + 0xffUL + #define \ + SQ_BIND_ACCESS_CNTL_WINDOW_BIND_REMOTE_ATOMIC_REMOTE_WRITE_REMOTE_READ_LOCAL_WRITE_SFT 0 + #define SQ_BIND_ACCESS_CNTL_LOCAL_WRITE 0x1UL + #define SQ_BIND_ACCESS_CNTL_REMOTE_READ 0x2UL + #define SQ_BIND_ACCESS_CNTL_REMOTE_WRITE 0x4UL + #define SQ_BIND_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL + #define SQ_BIND_ACCESS_CNTL_WINDOW_BIND 0x10UL + u8 reserved8_1; + u8 mw_type_zero_based; + #define SQ_BIND_ZERO_BASED 0x1UL + #define SQ_BIND_MW_TYPE 0x2UL + #define SQ_BIND_MW_TYPE_TYPE1 (0x0UL << 1) + #define SQ_BIND_MW_TYPE_TYPE2 (0x1UL << 1) + #define SQ_BIND_MW_TYPE_LAST SQ_BIND_MW_TYPE_TYPE2 + u8 reserved8_2; + __le16 reserved16; + __le32 parent_l_key; + __le32 l_key; + __le64 va; + u8 length[5]; + u8 reserved24[3]; + __le32 data[24]; +}; + +/* sq_bind_hdr (size:256b/32B) */ +struct sq_bind_hdr { + u8 wqe_type; + #define SQ_BIND_HDR_WQE_TYPE_BIND 0xeUL + #define SQ_BIND_HDR_WQE_TYPE_LAST SQ_BIND_HDR_WQE_TYPE_BIND + u8 flags; + #define SQ_BIND_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_MASK 0xffUL + #define SQ_BIND_HDR_FLAGS_INLINE_SE_UC_FENCE_RD_OR_ATOMIC_FENCE_SIGNAL_COMP_SFT 0 + #define SQ_BIND_HDR_FLAGS_SIGNAL_COMP 0x1UL + #define SQ_BIND_HDR_FLAGS_RD_OR_ATOMIC_FENCE 0x2UL + #define SQ_BIND_HDR_FLAGS_UC_FENCE 0x4UL + #define SQ_BIND_HDR_FLAGS_SE 0x8UL + #define SQ_BIND_HDR_FLAGS_INLINE 0x10UL + #define SQ_BIND_HDR_FLAGS_WQE_TS_EN 0x20UL + #define SQ_BIND_HDR_FLAGS_DEBUG_TRACE 0x40UL + u8 access_cntl; + #define \ + SQ_BIND_HDR_ACCESS_CNTL_WINDOW_BIND_REMOTE_ATOMIC_REMOTE_WRITE_REMOTE_READ_LOCAL_WRITE_MASK\ + 0xffUL + #define \ + SQ_BIND_HDR_ACCESS_CNTL_WINDOW_BIND_REMOTE_ATOMIC_REMOTE_WRITE_REMOTE_READ_LOCAL_WRITE_SFT \ + 0 + #define SQ_BIND_HDR_ACCESS_CNTL_LOCAL_WRITE 0x1UL + #define SQ_BIND_HDR_ACCESS_CNTL_REMOTE_READ 0x2UL + #define SQ_BIND_HDR_ACCESS_CNTL_REMOTE_WRITE 0x4UL + #define SQ_BIND_HDR_ACCESS_CNTL_REMOTE_ATOMIC 0x8UL + #define SQ_BIND_HDR_ACCESS_CNTL_WINDOW_BIND 0x10UL + u8 reserved8_1; + u8 mw_type_zero_based; + #define SQ_BIND_HDR_ZERO_BASED 0x1UL + #define SQ_BIND_HDR_MW_TYPE 0x2UL + #define SQ_BIND_HDR_MW_TYPE_TYPE1 (0x0UL << 1) + #define SQ_BIND_HDR_MW_TYPE_TYPE2 (0x1UL << 1) + #define SQ_BIND_HDR_MW_TYPE_LAST SQ_BIND_HDR_MW_TYPE_TYPE2 + u8 reserved8_2; + __le16 reserved16; + __le32 parent_l_key; + __le32 l_key; + __le64 va; + u8 length[5]; + u8 reserved24[3]; +}; + +/* rq_wqe (size:1024b/128B) */ +struct rq_wqe { + u8 wqe_type; + #define RQ_WQE_WQE_TYPE_RCV 0x80UL + #define RQ_WQE_WQE_TYPE_LAST RQ_WQE_WQE_TYPE_RCV + u8 flags; + u8 wqe_size; + u8 reserved8; + __le32 reserved32; + __le32 wr_id[2]; + #define RQ_WQE_WR_ID_MASK 0xfffffUL + #define RQ_WQE_WR_ID_SFT 0 + u8 reserved128[16]; + __le32 data[24]; +}; + +/* rq_wqe_hdr (size:256b/32B) */ +struct rq_wqe_hdr { + u8 wqe_type; + #define RQ_WQE_HDR_WQE_TYPE_RCV 0x80UL + #define RQ_WQE_HDR_WQE_TYPE_LAST RQ_WQE_HDR_WQE_TYPE_RCV + u8 flags; + u8 wqe_size; + u8 reserved8; + __le32 reserved32; + __le32 wr_id[2]; + #define RQ_WQE_HDR_WR_ID_MASK 0xfffffUL + #define RQ_WQE_HDR_WR_ID_SFT 0 + u8 reserved128[16]; +}; + +/* cq_base (size:256b/32B) */ +struct cq_base { + __le64 reserved64_1; + __le64 reserved64_2; + __le64 reserved64_3; + u8 cqe_type_toggle; + #define CQ_BASE_TOGGLE 0x1UL + #define CQ_BASE_CQE_TYPE_MASK 0x1eUL + #define CQ_BASE_CQE_TYPE_SFT 1 + #define CQ_BASE_CQE_TYPE_REQ (0x0UL << 1) + #define CQ_BASE_CQE_TYPE_RES_RC (0x1UL << 1) + #define CQ_BASE_CQE_TYPE_RES_UD (0x2UL << 1) + #define CQ_BASE_CQE_TYPE_RES_RAWETH_QP1 (0x3UL << 1) + #define CQ_BASE_CQE_TYPE_RES_UD_CFA (0x4UL << 1) + #define CQ_BASE_CQE_TYPE_NO_OP (0xdUL << 1) + #define CQ_BASE_CQE_TYPE_TERMINAL (0xeUL << 1) + #define CQ_BASE_CQE_TYPE_CUT_OFF (0xfUL << 1) + #define CQ_BASE_CQE_TYPE_LAST CQ_BASE_CQE_TYPE_CUT_OFF + u8 status; + __le16 reserved16; + __le32 reserved32; +}; + +/* cq_req (size:256b/32B) */ +struct cq_req { + __le64 qp_handle; + __le16 sq_cons_idx; + __le16 reserved16_1; + __le32 reserved32_2; + __le64 reserved64; + u8 cqe_type_toggle; + #define CQ_REQ_TOGGLE 0x1UL + #define CQ_REQ_CQE_TYPE_MASK 0x1eUL + #define CQ_REQ_CQE_TYPE_SFT 1 + #define CQ_REQ_CQE_TYPE_REQ (0x0UL << 1) + #define CQ_REQ_CQE_TYPE_LAST CQ_REQ_CQE_TYPE_REQ + #define CQ_REQ_PUSH 0x20UL + u8 status; + #define CQ_REQ_STATUS_OK 0x0UL + #define CQ_REQ_STATUS_BAD_RESPONSE_ERR 0x1UL + #define CQ_REQ_STATUS_LOCAL_LENGTH_ERR 0x2UL + #define CQ_REQ_STATUS_LOCAL_QP_OPERATION_ERR 0x3UL + #define CQ_REQ_STATUS_LOCAL_PROTECTION_ERR 0x4UL + #define CQ_REQ_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_REQ_STATUS_REMOTE_INVALID_REQUEST_ERR 0x6UL + #define CQ_REQ_STATUS_REMOTE_ACCESS_ERR 0x7UL + #define CQ_REQ_STATUS_REMOTE_OPERATION_ERR 0x8UL + #define CQ_REQ_STATUS_RNR_NAK_RETRY_CNT_ERR 0x9UL + #define CQ_REQ_STATUS_TRANSPORT_RETRY_CNT_ERR 0xaUL + #define CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR 0xbUL + #define CQ_REQ_STATUS_LAST CQ_REQ_STATUS_WORK_REQUEST_FLUSHED_ERR + __le16 reserved16_2; + __le32 reserved32_1; +}; + +/* cq_res_rc (size:256b/32B) */ +struct cq_res_rc { + __le32 length; + __le32 imm_data_or_inv_r_key; + __le64 qp_handle; + __le64 mr_handle; + u8 cqe_type_toggle; + #define CQ_RES_RC_TOGGLE 0x1UL + #define CQ_RES_RC_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_RC_CQE_TYPE_SFT 1 + #define CQ_RES_RC_CQE_TYPE_RES_RC (0x1UL << 1) + #define CQ_RES_RC_CQE_TYPE_LAST CQ_RES_RC_CQE_TYPE_RES_RC + u8 status; + #define CQ_RES_RC_STATUS_OK 0x0UL + #define CQ_RES_RC_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_RC_STATUS_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_RC_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_RC_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_RC_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_RC_STATUS_REMOTE_INVALID_REQUEST_ERR 0x6UL + #define CQ_RES_RC_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_RC_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_RC_STATUS_LAST CQ_RES_RC_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_RC_FLAGS_SRQ 0x1UL + #define CQ_RES_RC_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_RC_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_RC_FLAGS_SRQ_LAST CQ_RES_RC_FLAGS_SRQ_SRQ + #define CQ_RES_RC_FLAGS_IMM 0x2UL + #define CQ_RES_RC_FLAGS_INV 0x4UL + #define CQ_RES_RC_FLAGS_RDMA 0x8UL + #define CQ_RES_RC_FLAGS_RDMA_SEND (0x0UL << 3) + #define CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE (0x1UL << 3) + #define CQ_RES_RC_FLAGS_RDMA_LAST CQ_RES_RC_FLAGS_RDMA_RDMA_WRITE + __le32 srq_or_rq_wr_id; + #define CQ_RES_RC_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_RC_SRQ_OR_RQ_WR_ID_SFT 0 +}; + +/* cq_res_ud (size:256b/32B) */ +struct cq_res_ud { + __le16 length; + #define CQ_RES_UD_LENGTH_MASK 0x3fffUL + #define CQ_RES_UD_LENGTH_SFT 0 + __le16 cfa_metadata; + #define CQ_RES_UD_CFA_METADATA_VID_MASK 0xfffUL + #define CQ_RES_UD_CFA_METADATA_VID_SFT 0 + #define CQ_RES_UD_CFA_METADATA_DE 0x1000UL + #define CQ_RES_UD_CFA_METADATA_PRI_MASK 0xe000UL + #define CQ_RES_UD_CFA_METADATA_PRI_SFT 13 + __le32 imm_data; + __le64 qp_handle; + __le16 src_mac[3]; + __le16 src_qp_low; + u8 cqe_type_toggle; + #define CQ_RES_UD_TOGGLE 0x1UL + #define CQ_RES_UD_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_UD_CQE_TYPE_SFT 1 + #define CQ_RES_UD_CQE_TYPE_RES_UD (0x2UL << 1) + #define CQ_RES_UD_CQE_TYPE_LAST CQ_RES_UD_CQE_TYPE_RES_UD + u8 status; + #define CQ_RES_UD_STATUS_OK 0x0UL + #define CQ_RES_UD_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_UD_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_UD_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_UD_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_UD_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_UD_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_UD_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_UD_STATUS_LAST CQ_RES_UD_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_UD_FLAGS_SRQ 0x1UL + #define CQ_RES_UD_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_UD_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_UD_FLAGS_SRQ_LAST CQ_RES_UD_FLAGS_SRQ_SRQ + #define CQ_RES_UD_FLAGS_IMM 0x2UL + #define CQ_RES_UD_FLAGS_UNUSED_MASK 0xcUL + #define CQ_RES_UD_FLAGS_UNUSED_SFT 2 + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_MASK 0x30UL + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_SFT 4 + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V1 (0x0UL << 4) + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV4 (0x2UL << 4) + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6 (0x3UL << 4) + #define CQ_RES_UD_FLAGS_ROCE_IP_VER_LAST CQ_RES_UD_FLAGS_ROCE_IP_VER_V2IPV6 + #define CQ_RES_UD_FLAGS_META_FORMAT_MASK 0x3c0UL + #define CQ_RES_UD_FLAGS_META_FORMAT_SFT 6 + #define CQ_RES_UD_FLAGS_META_FORMAT_NONE (0x0UL << 6) + #define CQ_RES_UD_FLAGS_META_FORMAT_VLAN (0x1UL << 6) + #define CQ_RES_UD_FLAGS_META_FORMAT_TUNNEL_ID (0x2UL << 6) + #define CQ_RES_UD_FLAGS_META_FORMAT_CHDR_DATA (0x3UL << 6) + #define CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET (0x4UL << 6) + #define CQ_RES_UD_FLAGS_META_FORMAT_LAST CQ_RES_UD_FLAGS_META_FORMAT_HDR_OFFSET + #define CQ_RES_UD_FLAGS_EXT_META_FORMAT_MASK 0xc00UL + #define CQ_RES_UD_FLAGS_EXT_META_FORMAT_SFT 10 + __le32 src_qp_high_srq_or_rq_wr_id; + #define CQ_RES_UD_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_UD_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_UD_SRC_QP_HIGH_MASK 0xff000000UL + #define CQ_RES_UD_SRC_QP_HIGH_SFT 24 +}; + +/* cq_res_ud_v2 (size:256b/32B) */ +struct cq_res_ud_v2 { + __le16 length; + #define CQ_RES_UD_V2_LENGTH_MASK 0x3fffUL + #define CQ_RES_UD_V2_LENGTH_SFT 0 + __le16 cfa_metadata0; + #define CQ_RES_UD_V2_CFA_METADATA0_VID_MASK 0xfffUL + #define CQ_RES_UD_V2_CFA_METADATA0_VID_SFT 0 + #define CQ_RES_UD_V2_CFA_METADATA0_DE 0x1000UL + #define CQ_RES_UD_V2_CFA_METADATA0_PRI_MASK 0xe000UL + #define CQ_RES_UD_V2_CFA_METADATA0_PRI_SFT 13 + __le32 imm_data; + __le64 qp_handle; + __le16 src_mac[3]; + __le16 src_qp_low; + u8 cqe_type_toggle; + #define CQ_RES_UD_V2_TOGGLE 0x1UL + #define CQ_RES_UD_V2_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_UD_V2_CQE_TYPE_SFT 1 + #define CQ_RES_UD_V2_CQE_TYPE_RES_UD (0x2UL << 1) + #define CQ_RES_UD_V2_CQE_TYPE_LAST CQ_RES_UD_V2_CQE_TYPE_RES_UD + u8 status; + #define CQ_RES_UD_V2_STATUS_OK 0x0UL + #define CQ_RES_UD_V2_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_UD_V2_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_UD_V2_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_UD_V2_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_UD_V2_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_UD_V2_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_UD_V2_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_UD_V2_STATUS_LAST CQ_RES_UD_V2_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_UD_V2_FLAGS_SRQ 0x1UL + #define CQ_RES_UD_V2_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_UD_V2_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_UD_V2_FLAGS_SRQ_LAST CQ_RES_UD_V2_FLAGS_SRQ_SRQ + #define CQ_RES_UD_V2_FLAGS_IMM 0x2UL + #define CQ_RES_UD_V2_FLAGS_UNUSED_MASK 0xcUL + #define CQ_RES_UD_V2_FLAGS_UNUSED_SFT 2 + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_MASK 0x30UL + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_SFT 4 + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_V1 (0x0UL << 4) + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_V2IPV4 (0x2UL << 4) + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_V2IPV6 (0x3UL << 4) + #define CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_LAST CQ_RES_UD_V2_FLAGS_ROCE_IP_VER_V2IPV6 + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_MASK 0x3c0UL + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_SFT 6 + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_NONE (0x0UL << 6) + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_ACT_REC_PTR (0x1UL << 6) + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_TUNNEL_ID (0x2UL << 6) + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_CHDR_DATA (0x3UL << 6) + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_HDR_OFFSET (0x4UL << 6) + #define CQ_RES_UD_V2_FLAGS_META_FORMAT_LAST CQ_RES_UD_V2_FLAGS_META_FORMAT_HDR_OFFSET + __le32 src_qp_high_srq_or_rq_wr_id; + #define CQ_RES_UD_V2_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_UD_V2_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_UD_V2_CFA_METADATA1_MASK 0xf00000UL + #define CQ_RES_UD_V2_CFA_METADATA1_SFT 20 + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_MASK 0x700000UL + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_SFT 20 + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPID88A8 (0x0UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPID8100 (0x1UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPID9100 (0x2UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPID9200 (0x3UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPID9300 (0x4UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPIDCFG (0x5UL << 20) + #define CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_LAST CQ_RES_UD_V2_CFA_METADATA1_TPID_SEL_TPIDCFG + #define CQ_RES_UD_V2_CFA_METADATA1_VALID 0x800000UL + #define CQ_RES_UD_V2_SRC_QP_HIGH_MASK 0xff000000UL + #define CQ_RES_UD_V2_SRC_QP_HIGH_SFT 24 +}; + +/* cq_res_ud_cfa (size:256b/32B) */ +struct cq_res_ud_cfa { + __le16 length; + #define CQ_RES_UD_CFA_LENGTH_MASK 0x3fffUL + #define CQ_RES_UD_CFA_LENGTH_SFT 0 + __le16 cfa_code; + __le32 imm_data; + __le32 qid; + #define CQ_RES_UD_CFA_QID_MASK 0xfffffUL + #define CQ_RES_UD_CFA_QID_SFT 0 + __le32 cfa_metadata; + #define CQ_RES_UD_CFA_CFA_METADATA_VID_MASK 0xfffUL + #define CQ_RES_UD_CFA_CFA_METADATA_VID_SFT 0 + #define CQ_RES_UD_CFA_CFA_METADATA_DE 0x1000UL + #define CQ_RES_UD_CFA_CFA_METADATA_PRI_MASK 0xe000UL + #define CQ_RES_UD_CFA_CFA_METADATA_PRI_SFT 13 + #define CQ_RES_UD_CFA_CFA_METADATA_TPID_MASK 0xffff0000UL + #define CQ_RES_UD_CFA_CFA_METADATA_TPID_SFT 16 + __le16 src_mac[3]; + __le16 src_qp_low; + u8 cqe_type_toggle; + #define CQ_RES_UD_CFA_TOGGLE 0x1UL + #define CQ_RES_UD_CFA_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_UD_CFA_CQE_TYPE_SFT 1 + #define CQ_RES_UD_CFA_CQE_TYPE_RES_UD_CFA (0x4UL << 1) + #define CQ_RES_UD_CFA_CQE_TYPE_LAST CQ_RES_UD_CFA_CQE_TYPE_RES_UD_CFA + u8 status; + #define CQ_RES_UD_CFA_STATUS_OK 0x0UL + #define CQ_RES_UD_CFA_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_UD_CFA_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_UD_CFA_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_UD_CFA_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_UD_CFA_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_UD_CFA_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_UD_CFA_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_UD_CFA_STATUS_LAST CQ_RES_UD_CFA_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_UD_CFA_FLAGS_SRQ 0x1UL + #define CQ_RES_UD_CFA_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_UD_CFA_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_UD_CFA_FLAGS_SRQ_LAST CQ_RES_UD_CFA_FLAGS_SRQ_SRQ + #define CQ_RES_UD_CFA_FLAGS_IMM 0x2UL + #define CQ_RES_UD_CFA_FLAGS_UNUSED_MASK 0xcUL + #define CQ_RES_UD_CFA_FLAGS_UNUSED_SFT 2 + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_MASK 0x30UL + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_SFT 4 + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_V1 (0x0UL << 4) + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_V2IPV4 (0x2UL << 4) + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_V2IPV6 (0x3UL << 4) + #define CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_LAST CQ_RES_UD_CFA_FLAGS_ROCE_IP_VER_V2IPV6 + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_MASK 0x3c0UL + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_SFT 6 + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_NONE (0x0UL << 6) + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_VLAN (0x1UL << 6) + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_TUNNEL_ID (0x2UL << 6) + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_CHDR_DATA (0x3UL << 6) + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_HDR_OFFSET (0x4UL << 6) + #define CQ_RES_UD_CFA_FLAGS_META_FORMAT_LAST CQ_RES_UD_CFA_FLAGS_META_FORMAT_HDR_OFFSET + #define CQ_RES_UD_CFA_FLAGS_EXT_META_FORMAT_MASK 0xc00UL + #define CQ_RES_UD_CFA_FLAGS_EXT_META_FORMAT_SFT 10 + __le32 src_qp_high_srq_or_rq_wr_id; + #define CQ_RES_UD_CFA_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_UD_CFA_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_UD_CFA_SRC_QP_HIGH_MASK 0xff000000UL + #define CQ_RES_UD_CFA_SRC_QP_HIGH_SFT 24 +}; + +/* cq_res_ud_cfa_v2 (size:256b/32B) */ +struct cq_res_ud_cfa_v2 { + __le16 length; + #define CQ_RES_UD_CFA_V2_LENGTH_MASK 0x3fffUL + #define CQ_RES_UD_CFA_V2_LENGTH_SFT 0 + __le16 cfa_metadata0; + #define CQ_RES_UD_CFA_V2_CFA_METADATA0_VID_MASK 0xfffUL + #define CQ_RES_UD_CFA_V2_CFA_METADATA0_VID_SFT 0 + #define CQ_RES_UD_CFA_V2_CFA_METADATA0_DE 0x1000UL + #define CQ_RES_UD_CFA_V2_CFA_METADATA0_PRI_MASK 0xe000UL + #define CQ_RES_UD_CFA_V2_CFA_METADATA0_PRI_SFT 13 + __le32 imm_data; + __le32 qid; + #define CQ_RES_UD_CFA_V2_QID_MASK 0xfffffUL + #define CQ_RES_UD_CFA_V2_QID_SFT 0 + __le32 cfa_metadata2; + __le16 src_mac[3]; + __le16 src_qp_low; + u8 cqe_type_toggle; + #define CQ_RES_UD_CFA_V2_TOGGLE 0x1UL + #define CQ_RES_UD_CFA_V2_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_UD_CFA_V2_CQE_TYPE_SFT 1 + #define CQ_RES_UD_CFA_V2_CQE_TYPE_RES_UD_CFA (0x4UL << 1) + #define CQ_RES_UD_CFA_V2_CQE_TYPE_LAST CQ_RES_UD_CFA_V2_CQE_TYPE_RES_UD_CFA + u8 status; + #define CQ_RES_UD_CFA_V2_STATUS_OK 0x0UL + #define CQ_RES_UD_CFA_V2_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_UD_CFA_V2_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_UD_CFA_V2_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_UD_CFA_V2_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_UD_CFA_V2_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_UD_CFA_V2_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_UD_CFA_V2_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_UD_CFA_V2_STATUS_LAST CQ_RES_UD_CFA_V2_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_UD_CFA_V2_FLAGS_SRQ 0x1UL + #define CQ_RES_UD_CFA_V2_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_UD_CFA_V2_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_UD_CFA_V2_FLAGS_SRQ_LAST CQ_RES_UD_CFA_V2_FLAGS_SRQ_SRQ + #define CQ_RES_UD_CFA_V2_FLAGS_IMM 0x2UL + #define CQ_RES_UD_CFA_V2_FLAGS_UNUSED_MASK 0xcUL + #define CQ_RES_UD_CFA_V2_FLAGS_UNUSED_SFT 2 + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_MASK 0x30UL + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_SFT 4 + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_V1 (0x0UL << 4) + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_V2IPV4 (0x2UL << 4) + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_V2IPV6 (0x3UL << 4) + #define CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_LAST CQ_RES_UD_CFA_V2_FLAGS_ROCE_IP_VER_V2IPV6 + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_MASK 0x3c0UL + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_SFT 6 + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_NONE (0x0UL << 6) + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_ACT_REC_PTR (0x1UL << 6) + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_TUNNEL_ID (0x2UL << 6) + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_CHDR_DATA (0x3UL << 6) + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_HDR_OFFSET (0x4UL << 6) + #define CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_LAST \ + CQ_RES_UD_CFA_V2_FLAGS_META_FORMAT_HDR_OFFSET + __le32 src_qp_high_srq_or_rq_wr_id; + #define CQ_RES_UD_CFA_V2_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_UD_CFA_V2_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_MASK 0xf00000UL + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_SFT 20 + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_MASK 0x700000UL + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_SFT 20 + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPID88A8 (0x0UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPID8100 (0x1UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPID9100 (0x2UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPID9200 (0x3UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPID9300 (0x4UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPIDCFG (0x5UL << 20) + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_LAST \ + CQ_RES_UD_CFA_V2_CFA_METADATA1_TPID_SEL_TPIDCFG + #define CQ_RES_UD_CFA_V2_CFA_METADATA1_VALID 0x800000UL + #define CQ_RES_UD_CFA_V2_SRC_QP_HIGH_MASK 0xff000000UL + #define CQ_RES_UD_CFA_V2_SRC_QP_HIGH_SFT 24 +}; + +/* cq_res_raweth_qp1 (size:256b/32B) */ +struct cq_res_raweth_qp1 { + __le16 length; + #define CQ_RES_RAWETH_QP1_LENGTH_MASK 0x3fffUL + #define CQ_RES_RAWETH_QP1_LENGTH_SFT 0 + __le16 raweth_qp1_flags; + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_MASK 0x3ffUL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_SFT 0 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ERROR 0x1UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_MASK 0x3c0UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_SFT 6 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_NOT_KNOWN (0x0UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_IP (0x1UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_TCP (0x2UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_UDP (0x3UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_FCOE (0x4UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ROCE (0x5UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_ICMP (0x7UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_WO_TIMESTAMP (0x8UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP (0x9UL << 6) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_LAST \ + CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP + __le16 raweth_qp1_errors; + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_IP_CS_ERROR 0x10UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_L4_CS_ERROR 0x20UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_IP_CS_ERROR 0x40UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_L4_CS_ERROR 0x80UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_CRC_ERROR 0x100UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_MASK 0xe00UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_SFT 9 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_NO_ERROR (0x0UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_VERSION (0x1UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_HDR_LEN (0x2UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_TUNNEL_TOTAL_ERROR (0x3UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_IP_TOTAL_ERROR (0x4UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_UDP_TOTAL_ERROR (0x5UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL (0x6UL << 9) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_LAST \ + CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_MASK 0xf000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_SFT 12 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_NO_ERROR (0x0UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_VERSION (0x1UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_HDR_LEN (0x2UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_TTL (0x3UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_IP_TOTAL_ERROR (0x4UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_UDP_TOTAL_ERROR (0x5UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN (0x6UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN_TOO_SMALL (0x7UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN (0x8UL << 12) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_LAST \ + CQ_RES_RAWETH_QP1_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN + __le16 raweth_qp1_cfa_code; + __le64 qp_handle; + __le32 raweth_qp1_flags2; + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_CS_CALC 0x1UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_L4_CS_CALC 0x2UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_IP_CS_CALC 0x4UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_T_L4_CS_CALC 0x8UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_MASK 0xf0UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_SFT 4 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_NONE (0x0UL << 4) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_VLAN (0x1UL << 4) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_TUNNEL_ID (0x2UL << 4) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_CHDR_DATA (0x3UL << 4) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_HDR_OFFSET (0x4UL << 4) + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_LAST \ + CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_META_FORMAT_HDR_OFFSET + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_IP_TYPE 0x100UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_CALC 0x200UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_EXT_META_FORMAT_MASK 0xc00UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_EXT_META_FORMAT_SFT 10 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_MASK 0xffff0000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_SFT 16 + __le32 raweth_qp1_metadata; + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_DE_VID_MASK 0xffffUL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_DE_VID_SFT 0 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_MASK 0xfffUL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_VID_SFT 0 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_DE 0x1000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_MASK 0xe000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_PRI_SFT 13 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_MASK 0xffff0000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_METADATA_TPID_SFT 16 + u8 cqe_type_toggle; + #define CQ_RES_RAWETH_QP1_TOGGLE 0x1UL + #define CQ_RES_RAWETH_QP1_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_RAWETH_QP1_CQE_TYPE_SFT 1 + #define CQ_RES_RAWETH_QP1_CQE_TYPE_RES_RAWETH_QP1 (0x3UL << 1) + #define CQ_RES_RAWETH_QP1_CQE_TYPE_LAST CQ_RES_RAWETH_QP1_CQE_TYPE_RES_RAWETH_QP1 + u8 status; + #define CQ_RES_RAWETH_QP1_STATUS_OK 0x0UL + #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_RAWETH_QP1_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_RAWETH_QP1_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_RAWETH_QP1_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_RAWETH_QP1_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_RAWETH_QP1_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_RAWETH_QP1_STATUS_LAST CQ_RES_RAWETH_QP1_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_RAWETH_QP1_FLAGS_SRQ 0x1UL + #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_RAWETH_QP1_FLAGS_SRQ_LAST CQ_RES_RAWETH_QP1_FLAGS_SRQ_SRQ + __le32 raweth_qp1_payload_offset_srq_or_rq_wr_id; + #define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_RAWETH_QP1_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_MASK 0xff000000UL + #define CQ_RES_RAWETH_QP1_RAWETH_QP1_PAYLOAD_OFFSET_SFT 24 +}; + +/* cq_res_raweth_qp1_v2 (size:256b/32B) */ +struct cq_res_raweth_qp1_v2 { + __le16 length; + #define CQ_RES_RAWETH_QP1_V2_LENGTH_MASK 0x3fffUL + #define CQ_RES_RAWETH_QP1_V2_LENGTH_SFT 0 + __le16 raweth_qp1_flags; + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_MASK 0x3ffUL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_SFT 0 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ERROR 0x1UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_MASK 0x3c0UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_SFT 6 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_NOT_KNOWN (0x0UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_IP (0x1UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_TCP (0x2UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_UDP (0x3UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_FCOE (0x4UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_ROCE (0x5UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_ICMP (0x7UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_PTP_WO_TIMESTAMP (0x8UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP (0x9UL << 6) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_LAST \ + CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS_ITYPE_PTP_W_TIMESTAMP + __le16 raweth_qp1_errors; + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_IP_CS_ERROR 0x10UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_L4_CS_ERROR 0x20UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_IP_CS_ERROR 0x40UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_L4_CS_ERROR 0x80UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_CRC_ERROR 0x100UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_MASK 0xe00UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_SFT 9 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_NO_ERROR (0x0UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_VERSION (0x1UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_HDR_LEN (0x2UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_TUNNEL_TOTAL_ERROR (0x3UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_IP_TOTAL_ERROR (0x4UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_UDP_TOTAL_ERROR (0x5UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL (0x6UL << 9) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_LAST \ + CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_MASK 0xf000UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_SFT 12 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_NO_ERROR (0x0UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_VERSION (0x1UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_HDR_LEN (0x2UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L3_BAD_TTL (0x3UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_IP_TOTAL_ERROR (0x4UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_UDP_TOTAL_ERROR (0x5UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN (0x6UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN_TOO_SMALL \ + (0x7UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN \ + (0x8UL << 12) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_LAST \ + CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN + __le16 cfa_metadata0; + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA0_VID_MASK 0xfffUL + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA0_VID_SFT 0 + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA0_DE 0x1000UL + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA0_PRI_MASK 0xe000UL + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA0_PRI_SFT 13 + __le64 qp_handle; + __le32 raweth_qp1_flags2; + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_CS_ALL_OK_MODE 0x8UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_MASK 0xf0UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_SFT 4 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_NONE (0x0UL << 4) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_ACT_REC_PTR (0x1UL << 4) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_TUNNEL_ID (0x2UL << 4) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_CHDR_DATA (0x3UL << 4) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_HDR_OFFSET (0x4UL << 4) + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_LAST \ + CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_META_FORMAT_HDR_OFFSET + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_IP_TYPE 0x100UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_CALC 0x200UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_CS_OK_MASK 0xfc00UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_CS_OK_SFT 10 + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_MASK 0xffff0000UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_FLAGS2_COMPLETE_CHECKSUM_SFT 16 + __le32 cfa_metadata2; + u8 cqe_type_toggle; + #define CQ_RES_RAWETH_QP1_V2_TOGGLE 0x1UL + #define CQ_RES_RAWETH_QP1_V2_CQE_TYPE_MASK 0x1eUL + #define CQ_RES_RAWETH_QP1_V2_CQE_TYPE_SFT 1 + #define CQ_RES_RAWETH_QP1_V2_CQE_TYPE_RES_RAWETH_QP1 (0x3UL << 1) + #define CQ_RES_RAWETH_QP1_V2_CQE_TYPE_LAST CQ_RES_RAWETH_QP1_V2_CQE_TYPE_RES_RAWETH_QP1 + u8 status; + #define CQ_RES_RAWETH_QP1_V2_STATUS_OK 0x0UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_LOCAL_ACCESS_ERROR 0x1UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_HW_LOCAL_LENGTH_ERR 0x2UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_LOCAL_PROTECTION_ERR 0x3UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_LOCAL_QP_OPERATION_ERR 0x4UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_MEMORY_MGT_OPERATION_ERR 0x5UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_WORK_REQUEST_FLUSHED_ERR 0x7UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_HW_FLUSH_ERR 0x8UL + #define CQ_RES_RAWETH_QP1_V2_STATUS_LAST CQ_RES_RAWETH_QP1_V2_STATUS_HW_FLUSH_ERR + __le16 flags; + #define CQ_RES_RAWETH_QP1_V2_FLAGS_SRQ 0x1UL + #define CQ_RES_RAWETH_QP1_V2_FLAGS_SRQ_RQ 0x0UL + #define CQ_RES_RAWETH_QP1_V2_FLAGS_SRQ_SRQ 0x1UL + #define CQ_RES_RAWETH_QP1_V2_FLAGS_SRQ_LAST CQ_RES_RAWETH_QP1_V2_FLAGS_SRQ_SRQ + __le32 raweth_qp1_payload_offset_srq_or_rq_wr_id; + #define CQ_RES_RAWETH_QP1_V2_SRQ_OR_RQ_WR_ID_MASK 0xfffffUL + #define CQ_RES_RAWETH_QP1_V2_SRQ_OR_RQ_WR_ID_SFT 0 + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_MASK 0xf00000UL + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_SFT 20 + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_MASK 0x700000UL + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_SFT 20 + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPID88A8 (0x0UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPID8100 (0x1UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPID9100 (0x2UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPID9200 (0x3UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPID9300 (0x4UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPIDCFG (0x5UL << 20) + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_LAST \ + CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_TPID_SEL_TPIDCFG + #define CQ_RES_RAWETH_QP1_V2_CFA_METADATA1_VALID 0x800000UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_PAYLOAD_OFFSET_MASK 0xff000000UL + #define CQ_RES_RAWETH_QP1_V2_RAWETH_QP1_PAYLOAD_OFFSET_SFT 24 +}; + +/* cq_terminal (size:256b/32B) */ +struct cq_terminal { + __le64 qp_handle; + __le16 sq_cons_idx; + __le16 rq_cons_idx; + __le32 reserved32_1; + __le64 reserved64_3; + u8 cqe_type_toggle; + #define CQ_TERMINAL_TOGGLE 0x1UL + #define CQ_TERMINAL_CQE_TYPE_MASK 0x1eUL + #define CQ_TERMINAL_CQE_TYPE_SFT 1 + #define CQ_TERMINAL_CQE_TYPE_TERMINAL (0xeUL << 1) + #define CQ_TERMINAL_CQE_TYPE_LAST CQ_TERMINAL_CQE_TYPE_TERMINAL + u8 status; + #define CQ_TERMINAL_STATUS_OK 0x0UL + #define CQ_TERMINAL_STATUS_LAST CQ_TERMINAL_STATUS_OK + __le16 reserved16; + __le32 reserved32_2; +}; + +/* cq_cutoff (size:256b/32B) */ +struct cq_cutoff { + __le64 reserved64_1; + __le64 reserved64_2; + __le64 reserved64_3; + u8 cqe_type_toggle; + #define CQ_CUTOFF_TOGGLE 0x1UL + #define CQ_CUTOFF_CQE_TYPE_MASK 0x1eUL + #define CQ_CUTOFF_CQE_TYPE_SFT 1 + #define CQ_CUTOFF_CQE_TYPE_CUT_OFF (0xfUL << 1) + #define CQ_CUTOFF_CQE_TYPE_LAST CQ_CUTOFF_CQE_TYPE_CUT_OFF + u8 status; + #define CQ_CUTOFF_STATUS_OK 0x0UL + #define CQ_CUTOFF_STATUS_LAST CQ_CUTOFF_STATUS_OK + __le16 reserved16; + __le32 reserved32; +}; + +/* nq_base (size:128b/16B) */ +struct nq_base { + __le16 info10_type; + #define NQ_BASE_TYPE_MASK 0x3fUL + #define NQ_BASE_TYPE_SFT 0 + #define NQ_BASE_TYPE_CQ_NOTIFICATION 0x30UL + #define NQ_BASE_TYPE_SRQ_EVENT 0x32UL + #define NQ_BASE_TYPE_DBQ_EVENT 0x34UL + #define NQ_BASE_TYPE_QP_EVENT 0x38UL + #define NQ_BASE_TYPE_FUNC_EVENT 0x3aUL + #define NQ_BASE_TYPE_LAST NQ_BASE_TYPE_FUNC_EVENT + #define NQ_BASE_INFO10_MASK 0xffc0UL + #define NQ_BASE_INFO10_SFT 6 + __le16 info16; + __le32 info32; + __le32 info63_v[2]; + #define NQ_BASE_V 0x1UL + #define NQ_BASE_INFO63_MASK 0xfffffffeUL + #define NQ_BASE_INFO63_SFT 1 +}; + +/* nq_cn (size:128b/16B) */ +struct nq_cn { + __le16 type; + #define NQ_CN_TYPE_MASK 0x3fUL + #define NQ_CN_TYPE_SFT 0 + #define NQ_CN_TYPE_CQ_NOTIFICATION 0x30UL + #define NQ_CN_TYPE_LAST NQ_CN_TYPE_CQ_NOTIFICATION + #define NQ_CN_TOGGLE_MASK 0xc0UL + #define NQ_CN_TOGGLE_SFT 6 + __le16 reserved16; + __le32 cq_handle_low; + __le32 v; + #define NQ_CN_V 0x1UL + __le32 cq_handle_high; +}; + +/* nq_srq_event (size:128b/16B) */ +struct nq_srq_event { + u8 type; + #define NQ_SRQ_EVENT_TYPE_MASK 0x3fUL + #define NQ_SRQ_EVENT_TYPE_SFT 0 + #define NQ_SRQ_EVENT_TYPE_SRQ_EVENT 0x32UL + #define NQ_SRQ_EVENT_TYPE_LAST NQ_SRQ_EVENT_TYPE_SRQ_EVENT + u8 event; + #define NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT 0x1UL + #define NQ_SRQ_EVENT_EVENT_LAST NQ_SRQ_EVENT_EVENT_SRQ_THRESHOLD_EVENT + __le16 reserved16; + __le32 srq_handle_low; + __le32 v; + #define NQ_SRQ_EVENT_V 0x1UL + __le32 srq_handle_high; +}; + +/* nq_dbq_event (size:128b/16B) */ +struct nq_dbq_event { + u8 type; + #define NQ_DBQ_EVENT_TYPE_MASK 0x3fUL + #define NQ_DBQ_EVENT_TYPE_SFT 0 + #define NQ_DBQ_EVENT_TYPE_DBQ_EVENT 0x34UL + #define NQ_DBQ_EVENT_TYPE_LAST NQ_DBQ_EVENT_TYPE_DBQ_EVENT + u8 event; + #define NQ_DBQ_EVENT_EVENT_DBQ_THRESHOLD_EVENT 0x1UL + #define NQ_DBQ_EVENT_EVENT_LAST NQ_DBQ_EVENT_EVENT_DBQ_THRESHOLD_EVENT + __le16 db_pfid; + #define NQ_DBQ_EVENT_DB_PFID_MASK 0xfUL + #define NQ_DBQ_EVENT_DB_PFID_SFT 0 + __le32 db_dpi; + #define NQ_DBQ_EVENT_DB_DPI_MASK 0xfffffUL + #define NQ_DBQ_EVENT_DB_DPI_SFT 0 + __le32 v; + #define NQ_DBQ_EVENT_V 0x1UL + __le32 db_type_db_xid; + #define NQ_DBQ_EVENT_DB_XID_MASK 0xfffffUL + #define NQ_DBQ_EVENT_DB_XID_SFT 0 + #define NQ_DBQ_EVENT_DB_TYPE_MASK 0xf0000000UL + #define NQ_DBQ_EVENT_DB_TYPE_SFT 28 +}; + +/* xrrq_irrq (size:256b/32B) */ +struct xrrq_irrq { + __le16 credits_type; + #define XRRQ_IRRQ_TYPE 0x1UL + #define XRRQ_IRRQ_TYPE_READ_REQ 0x0UL + #define XRRQ_IRRQ_TYPE_ATOMIC_REQ 0x1UL + #define XRRQ_IRRQ_TYPE_LAST XRRQ_IRRQ_TYPE_ATOMIC_REQ + #define XRRQ_IRRQ_CREDITS_MASK 0xf800UL + #define XRRQ_IRRQ_CREDITS_SFT 11 + __le16 reserved16; + __le32 reserved32; + __le32 psn; + #define XRRQ_IRRQ_PSN_MASK 0xffffffUL + #define XRRQ_IRRQ_PSN_SFT 0 + __le32 msn; + #define XRRQ_IRRQ_MSN_MASK 0xffffffUL + #define XRRQ_IRRQ_MSN_SFT 0 + __le64 va_or_atomic_result; + __le32 rdma_r_key; + __le32 length; +}; + +/* xrrq_orrq (size:256b/32B) */ +struct xrrq_orrq { + __le16 num_sges_type; + #define XRRQ_ORRQ_TYPE 0x1UL + #define XRRQ_ORRQ_TYPE_READ_REQ 0x0UL + #define XRRQ_ORRQ_TYPE_ATOMIC_REQ 0x1UL + #define XRRQ_ORRQ_TYPE_LAST XRRQ_ORRQ_TYPE_ATOMIC_REQ + #define XRRQ_ORRQ_NUM_SGES_MASK 0xf800UL + #define XRRQ_ORRQ_NUM_SGES_SFT 11 + __le16 reserved16; + __le32 length; + __le32 psn; + #define XRRQ_ORRQ_PSN_MASK 0xffffffUL + #define XRRQ_ORRQ_PSN_SFT 0 + __le32 end_psn; + #define XRRQ_ORRQ_END_PSN_MASK 0xffffffUL + #define XRRQ_ORRQ_END_PSN_SFT 0 + __le64 first_sge_phy_or_sing_sge_va; + __le32 single_sge_l_key; + __le32 single_sge_size; +}; + +/* ptu_pte (size:64b/8B) */ +struct ptu_pte { + __le32 page_next_to_last_last_valid[2]; + #define PTU_PTE_VALID 0x1UL + #define PTU_PTE_LAST 0x2UL + #define PTU_PTE_NEXT_TO_LAST 0x4UL + #define PTU_PTE_UNUSED_MASK 0xff8UL + #define PTU_PTE_UNUSED_SFT 3 + #define PTU_PTE_PAGE_MASK 0xfffff000UL + #define PTU_PTE_PAGE_SFT 12 +}; + +/* ptu_pde (size:64b/8B) */ +struct ptu_pde { + __le32 page_valid[2]; + #define PTU_PDE_VALID 0x1UL + #define PTU_PDE_UNUSED_MASK 0xffeUL + #define PTU_PDE_UNUSED_SFT 1 + #define PTU_PDE_PAGE_MASK 0xfffff000UL + #define PTU_PDE_PAGE_SFT 12 +}; + +#endif /* ___BNXT_RE_HSI_H__ */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index a5408879e077..b31de4cf6534 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -10321,6 +10321,87 @@ struct hwrm_selftest_irq_output { u8 valid; }; +/* dbc_dbc (size:64b/8B) */ +struct dbc_dbc { + u32 index; + #define DBC_DBC_INDEX_MASK 0xffffffUL + #define DBC_DBC_INDEX_SFT 0 + #define DBC_DBC_EPOCH 0x1000000UL + #define DBC_DBC_TOGGLE_MASK 0x6000000UL + #define DBC_DBC_TOGGLE_SFT 25 + u32 type_path_xid; + #define DBC_DBC_XID_MASK 0xfffffUL + #define DBC_DBC_XID_SFT 0 + #define DBC_DBC_PATH_MASK 0x3000000UL + #define DBC_DBC_PATH_SFT 24 + #define DBC_DBC_PATH_ROCE (0x0UL << 24) + #define DBC_DBC_PATH_L2 (0x1UL << 24) + #define DBC_DBC_PATH_ENGINE (0x2UL << 24) + #define DBC_DBC_PATH_LAST DBC_DBC_PATH_ENGINE + #define DBC_DBC_VALID 0x4000000UL + #define DBC_DBC_DEBUG_TRACE 0x8000000UL + #define DBC_DBC_TYPE_MASK 0xf0000000UL + #define DBC_DBC_TYPE_SFT 28 + #define DBC_DBC_TYPE_SQ (0x0UL << 28) + #define DBC_DBC_TYPE_RQ (0x1UL << 28) + #define DBC_DBC_TYPE_SRQ (0x2UL << 28) + #define DBC_DBC_TYPE_SRQ_ARM (0x3UL << 28) + #define DBC_DBC_TYPE_CQ (0x4UL << 28) + #define DBC_DBC_TYPE_CQ_ARMSE (0x5UL << 28) + #define DBC_DBC_TYPE_CQ_ARMALL (0x6UL << 28) + #define DBC_DBC_TYPE_CQ_ARMENA (0x7UL << 28) + #define DBC_DBC_TYPE_SRQ_ARMENA (0x8UL << 28) + #define DBC_DBC_TYPE_CQ_CUTOFF_ACK (0x9UL << 28) + #define DBC_DBC_TYPE_NQ (0xaUL << 28) + #define DBC_DBC_TYPE_NQ_ARM (0xbUL << 28) + #define DBC_DBC_TYPE_NQ_MASK (0xeUL << 28) + #define DBC_DBC_TYPE_NULL (0xfUL << 28) + #define DBC_DBC_TYPE_LAST DBC_DBC_TYPE_NULL +}; + +/* db_push_start (size:64b/8B) */ +struct db_push_start { + u64 db; + #define DB_PUSH_START_DB_INDEX_MASK 0xffffffUL + #define DB_PUSH_START_DB_INDEX_SFT 0 + #define DB_PUSH_START_DB_PI_LO_MASK 0xff000000UL + #define DB_PUSH_START_DB_PI_LO_SFT 24 + #define DB_PUSH_START_DB_XID_MASK 0xfffff00000000ULL + #define DB_PUSH_START_DB_XID_SFT 32 + #define DB_PUSH_START_DB_PI_HI_MASK 0xf0000000000000ULL + #define DB_PUSH_START_DB_PI_HI_SFT 52 + #define DB_PUSH_START_DB_TYPE_MASK 0xf000000000000000ULL + #define DB_PUSH_START_DB_TYPE_SFT 60 + #define DB_PUSH_START_DB_TYPE_PUSH_START (0xcULL << 60) + #define DB_PUSH_START_DB_TYPE_PUSH_END (0xdULL << 60) + #define DB_PUSH_START_DB_TYPE_LAST DB_PUSH_START_DB_TYPE_PUSH_END +}; + +/* db_push_end (size:64b/8B) */ +struct db_push_end { + u64 db; + #define DB_PUSH_END_DB_INDEX_MASK 0xffffffUL + #define DB_PUSH_END_DB_INDEX_SFT 0 + #define DB_PUSH_END_DB_PI_LO_MASK 0xff000000UL + #define DB_PUSH_END_DB_PI_LO_SFT 24 + #define DB_PUSH_END_DB_XID_MASK 0xfffff00000000ULL + #define DB_PUSH_END_DB_XID_SFT 32 + #define DB_PUSH_END_DB_PI_HI_MASK 0xf0000000000000ULL + #define DB_PUSH_END_DB_PI_HI_SFT 52 + #define DB_PUSH_END_DB_PATH_MASK 0x300000000000000ULL + #define DB_PUSH_END_DB_PATH_SFT 56 + #define DB_PUSH_END_DB_PATH_ROCE (0x0ULL << 56) + #define DB_PUSH_END_DB_PATH_L2 (0x1ULL << 56) + #define DB_PUSH_END_DB_PATH_ENGINE (0x2ULL << 56) + #define DB_PUSH_END_DB_PATH_LAST DB_PUSH_END_DB_PATH_ENGINE + #define DB_PUSH_END_DB_DEBUG_TRACE 0x800000000000000ULL + #define DB_PUSH_END_DB_TYPE_MASK 0xf000000000000000ULL + #define DB_PUSH_END_DB_TYPE_SFT 60 + #define DB_PUSH_END_DB_TYPE_PUSH_START (0xcULL << 60) + #define DB_PUSH_END_DB_TYPE_PUSH_END (0xdULL << 60) + #define DB_PUSH_END_DB_TYPE_LAST DB_PUSH_END_DB_TYPE_PUSH_END +}; + /* db_push_info (size:64b/8B) */ struct db_push_info { u32 push_size_push_index; -- GitLab From b400acee0622d550d325078558d3bd3f0c60967d Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:35 -0700 Subject: [PATCH 1905/5631] RDMA/bnxt_re: Remove HW queue mapping from RoCE Driver bnxt_en driver does the queue mapping for RoCE traffic. Removing the queue mapping from RoCE driver. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-3-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/main.c | 77 ------------------------ drivers/infiniband/hw/bnxt_re/qplib_sp.c | 15 ----- drivers/infiniband/hw/bnxt_re/qplib_sp.h | 1 - 3 files changed, 93 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 48bbba7df22e..4aa344288b0f 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -921,49 +921,6 @@ static void bnxt_re_dispatch_event(struct ib_device *ibdev, struct ib_qp *qp, } } -#define HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN 0x02 -static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir, - u64 *cid_map) -{ - struct hwrm_queue_pri2cos_qcfg_input req = {0}; - struct hwrm_queue_pri2cos_qcfg_output resp; - struct bnxt_en_dev *en_dev = rdev->en_dev; - struct bnxt_fw_msg fw_msg; - u32 flags = 0; - u8 *qcfgmap, *tmp_map; - int rc = 0, i; - - if (!cid_map) - return -EINVAL; - - memset(&fw_msg, 0, sizeof(fw_msg)); - bnxt_re_init_hwrm_hdr(rdev, (void *)&req, - HWRM_QUEUE_PRI2COS_QCFG, -1, -1); - flags |= (dir & 0x01); - flags |= HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN; - req.flags = cpu_to_le32(flags); - req.port_id = en_dev->pf_port_id; - - bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, - sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = bnxt_send_msg(en_dev, &fw_msg); - if (rc) - return rc; - - if (resp.queue_cfg_info) { - ibdev_warn(&rdev->ibdev, - "Asymmetric cos queue configuration detected"); - ibdev_warn(&rdev->ibdev, - " on device, QoS may not be fully functional\n"); - } - qcfgmap = &resp.pri0_cos_queue_id; - tmp_map = (u8 *)cid_map; - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - tmp_map[i] = qcfgmap[i]; - - return rc; -} - static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev, struct bnxt_re_qp *qp) { @@ -1056,26 +1013,9 @@ static u32 bnxt_re_get_priority_mask(struct bnxt_re_dev *rdev) return prio_map; } -static void bnxt_re_parse_cid_map(u8 prio_map, u8 *cid_map, u16 *cosq) -{ - u16 prio; - u8 id; - - for (prio = 0, id = 0; prio < 8; prio++) { - if (prio_map & (1 << prio)) { - cosq[id] = cid_map[prio]; - id++; - if (id == 2) /* Max 2 tcs supported */ - break; - } - } -} - static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) { u8 prio_map = 0; - u64 cid_map; - int rc; /* Get priority for roce */ prio_map = bnxt_re_get_priority_mask(rdev); @@ -1083,23 +1023,6 @@ static int bnxt_re_setup_qos(struct bnxt_re_dev *rdev) if (prio_map == rdev->cur_prio_map) return 0; rdev->cur_prio_map = prio_map; - /* Get cosq id for this priority */ - rc = bnxt_re_query_hwrm_pri2cos(rdev, 0, &cid_map); - if (rc) { - ibdev_warn(&rdev->ibdev, "no cos for p_mask %x\n", prio_map); - return rc; - } - /* Parse CoS IDs for app priority */ - bnxt_re_parse_cid_map(prio_map, (u8 *)&cid_map, rdev->cosq); - - /* Config BONO. */ - rc = bnxt_qplib_map_tc2cos(&rdev->qplib_res, rdev->cosq); - if (rc) { - ibdev_warn(&rdev->ibdev, "no tc for cos{%x, %x}\n", - rdev->cosq[0], rdev->cosq[1]); - return rc; - } - /* Actual priorities are not programmed as they are already * done by L2 driver; just enable or disable priority vlan tagging */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index b802981b7171..3f4998aa2ef0 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -679,21 +679,6 @@ int bnxt_qplib_free_fast_reg_page_list(struct bnxt_qplib_res *res, return 0; } -int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids) -{ - struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_map_tc_to_cos req; - struct creq_map_tc_to_cos_resp resp; - u16 cmd_flags = 0; - - RCFW_CMD_PREP(req, MAP_TC_TO_COS, cmd_flags); - req.cos0 = cpu_to_le16(cids[0]); - req.cos1 = cpu_to_le16(cids[1]); - - return bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - NULL, 0); -} - int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_roce_stats *stats) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 5939e8fc8353..96e61db6ac6b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -277,7 +277,6 @@ int bnxt_qplib_alloc_fast_reg_page_list(struct bnxt_qplib_res *res, struct bnxt_qplib_frpl *frpl, int max); int bnxt_qplib_free_fast_reg_page_list(struct bnxt_qplib_res *res, struct bnxt_qplib_frpl *frpl); -int bnxt_qplib_map_tc2cos(struct bnxt_qplib_res *res, u16 *cids); int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_roce_stats *stats); int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, -- GitLab From e576adf583b52542f16940d33af5c968be4f1253 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:36 -0700 Subject: [PATCH 1906/5631] RDMA/bnxt_re: Convert RCFW_CMD_PREP macro to static inline function Convert RCFW_CMD_PREP macro to static inline function. Also, remove the cmd_flags passed as none of the functions are using it. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-4-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 55 +++++++++------ drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 10 +-- drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 23 ++++--- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 79 +++++++++++++--------- 4 files changed, 98 insertions(+), 69 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index d4e616cacc4d..3951c0336760 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -577,10 +577,11 @@ void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_destroy_srq req; struct creq_destroy_srq_resp resp; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, DESTROY_SRQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DESTROY_SRQ, + sizeof(req)); /* Configure the request */ req.srq_cid = cpu_to_le32(srq->id); @@ -601,7 +602,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, struct creq_create_srq_resp resp; struct cmdq_create_srq req; struct bnxt_qplib_pbl *pbl; - u16 cmd_flags = 0; u16 pg_sz_lvl; int rc, idx; @@ -621,7 +621,9 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, goto fail; } - RCFW_CMD_PREP(req, CREATE_SRQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_CREATE_SRQ, + sizeof(req)); /* Configure the request */ req.dpi = cpu_to_le32(srq->dpi->dpi); @@ -698,10 +700,11 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, struct creq_query_srq_resp resp; struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_srq_resp_sb *sb; - u16 cmd_flags = 0; int rc = 0; - RCFW_CMD_PREP(req, QUERY_SRQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_QUERY_SRQ, + sizeof(req)); /* Configure the request */ sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb)); @@ -810,13 +813,14 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) struct creq_create_qp1_resp resp; struct cmdq_create_qp1 req; struct bnxt_qplib_pbl *pbl; - u16 cmd_flags = 0; u32 qp_flags = 0; u8 pg_sz_lvl; u32 tbl_indx; int rc; - RCFW_CMD_PREP(req, CREATE_QP1, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_CREATE_QP1, + sizeof(req)); /* General */ req.type = qp->type; @@ -953,13 +957,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) struct bnxt_qplib_hwq *xrrq; struct bnxt_qplib_pbl *pbl; struct cmdq_create_qp req; - u16 cmd_flags = 0; u32 qp_flags = 0; u8 pg_sz_lvl; u32 tbl_indx; u16 nsge; - RCFW_CMD_PREP(req, CREATE_QP, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_CREATE_QP, + sizeof(req)); /* General */ req.type = qp->type; @@ -1227,12 +1232,13 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_modify_qp req; struct creq_modify_qp_resp resp; - u16 cmd_flags = 0; u32 temp32[4]; u32 bmask; int rc; - RCFW_CMD_PREP(req, MODIFY_QP, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_MODIFY_QP, + sizeof(req)); /* Filter out the qp_attr_mask based on the state->new transition */ __filter_modify_flags(qp); @@ -1333,11 +1339,12 @@ int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) struct creq_query_qp_resp resp; struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_qp_resp_sb *sb; - u16 cmd_flags = 0; u32 temp32[4]; int i, rc = 0; - RCFW_CMD_PREP(req, QUERY_QP, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_QUERY_QP, + sizeof(req)); sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb)); if (!sbuf) @@ -1456,7 +1463,6 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_destroy_qp req; struct creq_destroy_qp_resp resp; - u16 cmd_flags = 0; u32 tbl_indx; int rc; @@ -1464,7 +1470,9 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, rcfw->qp_tbl[tbl_indx].qp_id = BNXT_QPLIB_QP_ID_INVALID; rcfw->qp_tbl[tbl_indx].qp_handle = NULL; - RCFW_CMD_PREP(req, DESTROY_QP, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DESTROY_QP, + sizeof(req)); req.qp_cid = cpu_to_le32(qp->id); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, @@ -2033,7 +2041,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) struct creq_create_cq_resp resp; struct bnxt_qplib_pbl *pbl; struct cmdq_create_cq req; - u16 cmd_flags = 0; u32 pg_sz_lvl; int rc; @@ -2046,7 +2053,9 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) if (rc) goto exit; - RCFW_CMD_PREP(req, CREATE_CQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_CREATE_CQ, + sizeof(req)); if (!cq->dpi) { dev_err(&rcfw->pdev->dev, @@ -2110,10 +2119,11 @@ int bnxt_qplib_resize_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq, struct cmdq_resize_cq req = {}; struct bnxt_qplib_pbl *pbl; u32 pg_sz, lvl, new_sz; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, RESIZE_CQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_RESIZE_CQ, + sizeof(req)); hwq_attr.sginfo = &cq->sg_info; hwq_attr.res = res; hwq_attr.depth = new_cqes; @@ -2144,10 +2154,11 @@ int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) struct cmdq_destroy_cq req; struct creq_destroy_cq_resp resp; u16 total_cnq_events; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, DESTROY_CQ, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DESTROY_CQ, + sizeof(req)); req.cq_cid = cpu_to_le32(cq->id); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 061b2895dd9b..1eab4517d3b1 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -454,10 +454,11 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw) { struct cmdq_deinitialize_fw req; struct creq_deinitialize_fw_resp resp; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, DEINITIALIZE_FW, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DEINITIALIZE_FW, + sizeof(req)); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, 0); if (rc) @@ -472,11 +473,12 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, { struct creq_initialize_fw_resp resp; struct cmdq_initialize_fw req; - u16 cmd_flags = 0; u8 pgsz, lvl; int rc; - RCFW_CMD_PREP(req, INITIALIZE_FW, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_INITIALIZE_FW, + sizeof(req)); /* Supply (log-base-2-of-host-page-size - base-page-shift) * to bono to adjust the doorbell page sizes. */ diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 0a3d8e7da3d4..b7f4d0a66b18 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -51,25 +51,26 @@ #define RCFW_DBR_PCI_BAR_REGION 2 #define RCFW_DBR_BASE_PAGE_SHIFT 12 -#define RCFW_CMD_PREP(req, CMD, cmd_flags) \ - do { \ - memset(&(req), 0, sizeof((req))); \ - (req).opcode = CMDQ_BASE_OPCODE_##CMD; \ - (req).cmd_size = sizeof((req)); \ - (req).flags = cpu_to_le16(cmd_flags); \ - } while (0) - -#define RCFW_CMD_WAIT_TIME_MS 20000 /* 20 Seconds timeout */ - /* Cmdq contains a fix number of a 16-Byte slots */ struct bnxt_qplib_cmdqe { u8 data[16]; }; +#define BNXT_QPLIB_CMDQE_UNITS sizeof(struct bnxt_qplib_cmdqe) + +static inline void bnxt_qplib_rcfw_cmd_prep(struct cmdq_base *req, + u8 opcode, u8 cmd_size) +{ + memset(req, 0, cmd_size); + req->opcode = opcode; + req->cmd_size = cmd_size; +} + +#define RCFW_CMD_WAIT_TIME_MS 20000 /* 20 Seconds timeout */ + /* CMDQ elements */ #define BNXT_QPLIB_CMDQE_MAX_CNT_256 256 #define BNXT_QPLIB_CMDQE_MAX_CNT_8192 8192 -#define BNXT_QPLIB_CMDQE_UNITS sizeof(struct bnxt_qplib_cmdqe) #define BNXT_QPLIB_CMDQE_BYTES(depth) ((depth) * BNXT_QPLIB_CMDQE_UNITS) static inline u32 bnxt_qplib_cmdqe_npages(u32 depth) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 3f4998aa2ef0..4e2727485f9e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -70,10 +70,11 @@ static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, { struct cmdq_query_version req; struct creq_query_version_resp resp; - u16 cmd_flags = 0; int rc = 0; - RCFW_CMD_PREP(req, QUERY_VERSION, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_QUERY_VERSION, + sizeof(req)); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, 0); @@ -88,16 +89,17 @@ static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_dev_attr *attr, bool vf) { - struct cmdq_query_func req; - struct creq_query_func_resp resp; - struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_func_resp_sb *sb; - u16 cmd_flags = 0; - u32 temp; + struct bnxt_qplib_rcfw_sbuf *sbuf; + struct creq_query_func_resp resp; + struct cmdq_query_func req; u8 *tqm_alloc; int i, rc = 0; + u32 temp; - RCFW_CMD_PREP(req, QUERY_FUNC, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_QUERY_FUNC, + sizeof(req)); sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb)); if (!sbuf) { @@ -176,10 +178,11 @@ int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res, { struct cmdq_set_func_resources req; struct creq_set_func_resources_resp resp; - u16 cmd_flags = 0; int rc = 0; - RCFW_CMD_PREP(req, SET_FUNC_RESOURCES, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_SET_FUNC_RESOURCES, + sizeof(req)); req.number_of_qp = cpu_to_le32(ctx->qpc_count); req.number_of_mrw = cpu_to_le32(ctx->mrw_count); @@ -247,10 +250,11 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, if (update) { struct cmdq_delete_gid req; struct creq_delete_gid_resp resp; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, DELETE_GID, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DELETE_GID, + sizeof(req)); if (sgid_tbl->hw_id[index] == 0xFFFF) { dev_err(&res->pdev->dev, "GID entry contains an invalid HW id\n"); @@ -317,10 +321,11 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, if (update) { struct cmdq_add_gid req; struct creq_add_gid_resp resp; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, ADD_GID, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_ADD_GID, + sizeof(req)); req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]); req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]); @@ -378,9 +383,10 @@ int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct creq_modify_gid_resp resp; struct cmdq_modify_gid req; int rc; - u16 cmd_flags = 0; - RCFW_CMD_PREP(req, MODIFY_GID, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_MODIFY_GID, + sizeof(req)); req.gid[0] = cpu_to_be32(((u32 *)gid->data)[3]); req.gid[1] = cpu_to_be32(((u32 *)gid->data)[2]); @@ -411,12 +417,13 @@ int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_create_ah req; struct creq_create_ah_resp resp; - u16 cmd_flags = 0; u32 temp32[4]; u16 temp16[3]; int rc; - RCFW_CMD_PREP(req, CREATE_AH, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_CREATE_AH, + sizeof(req)); memcpy(temp32, ah->dgid.data, sizeof(struct bnxt_qplib_gid)); req.dgid[0] = cpu_to_le32(temp32[0]); @@ -454,10 +461,11 @@ void bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_destroy_ah req; struct creq_destroy_ah_resp resp; - u16 cmd_flags = 0; /* Clean up the AH table in the device */ - RCFW_CMD_PREP(req, DESTROY_AH, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DESTROY_AH, + sizeof(req)); req.ah_cid = cpu_to_le32(ah->id); @@ -471,7 +479,6 @@ int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_deallocate_key req; struct creq_deallocate_key_resp resp; - u16 cmd_flags = 0; int rc; if (mrw->lkey == 0xFFFFFFFF) { @@ -479,7 +486,9 @@ int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) return 0; } - RCFW_CMD_PREP(req, DEALLOCATE_KEY, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DEALLOCATE_KEY, + sizeof(req)); req.mrw_flags = mrw->type; @@ -507,11 +516,12 @@ int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_allocate_mrw req; struct creq_allocate_mrw_resp resp; - u16 cmd_flags = 0; unsigned long tmp; int rc; - RCFW_CMD_PREP(req, ALLOCATE_MRW, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_ALLOCATE_MRW, + sizeof(req)); req.pd_id = cpu_to_le32(mrw->pd->id); req.mrw_flags = mrw->type; @@ -543,10 +553,11 @@ int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct cmdq_deregister_mr req; struct creq_deregister_mr_resp resp; - u16 cmd_flags = 0; int rc; - RCFW_CMD_PREP(req, DEREGISTER_MR, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_DEREGISTER_MR, + sizeof(req)); req.lkey = cpu_to_le32(mrw->lkey); rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, @@ -572,9 +583,9 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, struct bnxt_qplib_sg_info sginfo = {}; struct creq_register_mr_resp resp; struct cmdq_register_mr req; - u16 cmd_flags = 0, level; int pages, rc; u32 pg_size; + u16 level; if (num_pbls) { pages = roundup_pow_of_two(num_pbls); @@ -602,7 +613,9 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, } } - RCFW_CMD_PREP(req, REGISTER_MR, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_REGISTER_MR, + sizeof(req)); /* Configure the request */ if (mr->hwq.level == PBL_LVL_MAX) { @@ -686,10 +699,11 @@ int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, struct creq_query_roce_stats_resp resp; struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_roce_stats_resp_sb *sb; - u16 cmd_flags = 0; int rc = 0; - RCFW_CMD_PREP(req, QUERY_ROCE_STATS, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_BASE_OPCODE_QUERY_ROCE_STATS, + sizeof(req)); sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb)); if (!sbuf) { @@ -766,7 +780,6 @@ int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, struct creq_query_roce_stats_ext_resp_sb *sb; struct cmdq_query_roce_stats_ext req = {}; struct bnxt_qplib_rcfw_sbuf *sbuf; - u16 cmd_flags = 0; int rc; sbuf = bnxt_qplib_rcfw_alloc_sbuf(rcfw, sizeof(*sb)); @@ -776,7 +789,9 @@ int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, return -ENOMEM; } - RCFW_CMD_PREP(req, QUERY_ROCE_STATS_EXT, cmd_flags); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, + CMDQ_QUERY_ROCE_STATS_EXT_OPCODE_QUERY_ROCE_STATS, + sizeof(req)); req.resp_size = ALIGN(sizeof(*sb), BNXT_QPLIB_CMDQE_UNITS); req.resp_addr = cpu_to_le64(sbuf->dma_addr); -- GitLab From ff015bcd213b5d8e234482394e1a7c5c92e5da39 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:37 -0700 Subject: [PATCH 1907/5631] RDMA/bnxt_re: Reduce number of argumets to control path command APIs Reducing the number of arguments to bnxt_qplib_rcfw_send_message by enclosing all its arguments into a command message structure. Use the same struct while passing the command information to send_message. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-5-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 104 +++++++++------- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 70 +++++------ drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 25 +++- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 138 ++++++++++++--------- 4 files changed, 199 insertions(+), 138 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 3951c0336760..f139d4cd1712 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -575,8 +575,9 @@ void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_srq *srq) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_destroy_srq req; - struct creq_destroy_srq_resp resp; + struct creq_destroy_srq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_destroy_srq req = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -586,8 +587,8 @@ void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res, /* Configure the request */ req.srq_cid = cpu_to_le32(srq->id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (struct cmdq_base *)&req, - (struct creq_base *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); kfree(srq->swq); if (rc) return; @@ -599,8 +600,9 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, { struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; - struct creq_create_srq_resp resp; - struct cmdq_create_srq req; + struct creq_create_srq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_create_srq req = {}; struct bnxt_qplib_pbl *pbl; u16 pg_sz_lvl; int rc, idx; @@ -640,8 +642,8 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, req.pd_id = cpu_to_le32(srq->pd->id); req.eventq_id = cpu_to_le16(srq->eventq_hw_ring_id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto fail; @@ -696,10 +698,11 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, struct bnxt_qplib_srq *srq) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_query_srq req; - struct creq_query_srq_resp resp; + struct creq_query_srq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_srq_resp_sb *sb; + struct cmdq_query_srq req = {}; int rc = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -713,8 +716,9 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS; req.srq_cid = cpu_to_le32(srq->id); sb = sbuf->sb; - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - (void *)sbuf, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); srq->threshold = le16_to_cpu(sb->srq_limit); bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf); @@ -808,10 +812,11 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_hwq_attr hwq_attr = {}; struct bnxt_qplib_rcfw *rcfw = res->rcfw; + struct creq_create_qp1_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct bnxt_qplib_q *sq = &qp->sq; struct bnxt_qplib_q *rq = &qp->rq; - struct creq_create_qp1_resp resp; - struct cmdq_create_qp1 req; + struct cmdq_create_qp1 req = {}; struct bnxt_qplib_pbl *pbl; u32 qp_flags = 0; u8 pg_sz_lvl; @@ -821,7 +826,6 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_QP1, sizeof(req)); - /* General */ req.type = qp->type; req.dpi = cpu_to_le32(qp->dpi->dpi); @@ -889,8 +893,8 @@ int bnxt_qplib_create_qp1(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) req.qp_flags = cpu_to_le32(qp_flags); req.pd_id = cpu_to_le32(qp->pd->id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto fail; @@ -950,13 +954,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; struct bnxt_qplib_sg_info sginfo = {}; + struct creq_create_qp_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct bnxt_qplib_q *sq = &qp->sq; struct bnxt_qplib_q *rq = &qp->rq; - struct creq_create_qp_resp resp; + struct cmdq_create_qp req = {}; int rc, req_size, psn_sz = 0; struct bnxt_qplib_hwq *xrrq; struct bnxt_qplib_pbl *pbl; - struct cmdq_create_qp req; u32 qp_flags = 0; u8 pg_sz_lvl; u32 tbl_indx; @@ -1097,8 +1102,9 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) } req.pd_id = cpu_to_le32(qp->pd->id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto fail; @@ -1230,8 +1236,9 @@ static void __filter_modify_flags(struct bnxt_qplib_qp *qp) int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_modify_qp req; - struct creq_modify_qp_resp resp; + struct creq_modify_qp_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_modify_qp req = {}; u32 temp32[4]; u32 bmask; int rc; @@ -1324,8 +1331,8 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) req.vlan_pcp_vlan_dei_vlan_id = cpu_to_le16(qp->vlan_id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; qp->cur_qp_state = qp->state; @@ -1335,10 +1342,11 @@ int bnxt_qplib_modify_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_query_qp req; - struct creq_query_qp_resp resp; + struct creq_query_qp_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct bnxt_qplib_rcfw_sbuf *sbuf; struct creq_query_qp_resp_sb *sb; + struct cmdq_query_qp req = {}; u32 temp32[4]; int i, rc = 0; @@ -1353,8 +1361,9 @@ int bnxt_qplib_query_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) req.qp_cid = cpu_to_le32(qp->id); req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS; - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - (void *)sbuf, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto bail; /* Extract the context from the side buffer */ @@ -1461,8 +1470,9 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_destroy_qp req; - struct creq_destroy_qp_resp resp; + struct creq_destroy_qp_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_destroy_qp req = {}; u32 tbl_indx; int rc; @@ -1475,8 +1485,9 @@ int bnxt_qplib_destroy_qp(struct bnxt_qplib_res *res, sizeof(req)); req.qp_cid = cpu_to_le32(qp->id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) { rcfw->qp_tbl[tbl_indx].qp_id = qp->id; rcfw->qp_tbl[tbl_indx].qp_handle = qp; @@ -2038,9 +2049,10 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; - struct creq_create_cq_resp resp; + struct creq_create_cq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_create_cq req = {}; struct bnxt_qplib_pbl *pbl; - struct cmdq_create_cq req; u32 pg_sz_lvl; int rc; @@ -2074,9 +2086,9 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) req.cq_fco_cnq_id = cpu_to_le32( (cq->cnq_hw_ring_id & CMDQ_CREATE_CQ_CNQ_ID_MASK) << CMDQ_CREATE_CQ_CNQ_ID_SFT); - - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto fail; @@ -2116,6 +2128,7 @@ int bnxt_qplib_resize_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq, struct bnxt_qplib_hwq_attr hwq_attr = {}; struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct creq_resize_cq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct cmdq_resize_cq req = {}; struct bnxt_qplib_pbl *pbl; u32 pg_sz, lvl, new_sz; @@ -2143,16 +2156,18 @@ int bnxt_qplib_resize_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq, req.new_cq_size_pg_size_lvl = cpu_to_le32(new_sz | pg_sz | lvl); req.new_pbl = cpu_to_le64(pbl->pg_map_arr[0]); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); return rc; } int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_destroy_cq req; - struct creq_destroy_cq_resp resp; + struct creq_destroy_cq_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_destroy_cq req = {}; u16 total_cnq_events; int rc; @@ -2161,8 +2176,9 @@ int bnxt_qplib_destroy_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) sizeof(req)); req.cq_cid = cpu_to_le32(cq->id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; total_cnq_events = le16_to_cpu(resp.total_cnq_events); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 1eab4517d3b1..7403a4ed0f9e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -85,8 +85,8 @@ static int __block_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie) return count ? 0 : -ETIMEDOUT; }; -static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, - struct creq_base *resp, void *sb, u8 is_block) +static int __send_message(struct bnxt_qplib_rcfw *rcfw, + struct bnxt_qplib_cmdqmsg *msg) { struct bnxt_qplib_cmdq_ctx *cmdq = &rcfw->cmdq; struct bnxt_qplib_hwq *hwq = &cmdq->hwq; @@ -101,7 +101,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, pdev = rcfw->pdev; - opcode = req->opcode; + opcode = msg->req->opcode; if (!test_bit(FIRMWARE_INITIALIZED_FLAG, &cmdq->flags) && (opcode != CMDQ_BASE_OPCODE_QUERY_FUNC && opcode != CMDQ_BASE_OPCODE_INITIALIZE_FW && @@ -124,7 +124,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, * cmdqe */ spin_lock_irqsave(&hwq->lock, flags); - if (req->cmd_size >= HWQ_FREE_SLOTS(hwq)) { + if (msg->req->cmd_size >= HWQ_FREE_SLOTS(hwq)) { dev_err(&pdev->dev, "RCFW: CMDQ is full!\n"); spin_unlock_irqrestore(&hwq->lock, flags); return -EAGAIN; @@ -133,36 +133,36 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, cookie = cmdq->seq_num & RCFW_MAX_COOKIE_VALUE; cbit = cookie % rcfw->cmdq_depth; - if (is_block) + if (msg->block) cookie |= RCFW_CMD_IS_BLOCKING; set_bit(cbit, cmdq->cmdq_bitmap); - req->cookie = cpu_to_le16(cookie); + msg->req->cookie = cpu_to_le16(cookie); crsqe = &rcfw->crsqe_tbl[cbit]; if (crsqe->resp) { spin_unlock_irqrestore(&hwq->lock, flags); return -EBUSY; } - size = req->cmd_size; + size = msg->req->cmd_size; /* change the cmd_size to the number of 16byte cmdq unit. * req->cmd_size is modified here */ - bnxt_qplib_set_cmd_slots(req); + bnxt_qplib_set_cmd_slots(msg->req); - memset(resp, 0, sizeof(*resp)); - crsqe->resp = (struct creq_qp_event *)resp; - crsqe->resp->cookie = req->cookie; - crsqe->req_size = req->cmd_size; - if (req->resp_size && sb) { - struct bnxt_qplib_rcfw_sbuf *sbuf = sb; + memset(msg->resp, 0, sizeof(*msg->resp)); + crsqe->resp = (struct creq_qp_event *)msg->resp; + crsqe->resp->cookie = msg->req->cookie; + crsqe->req_size = msg->req->cmd_size; + if (msg->req->resp_size && msg->sb) { + struct bnxt_qplib_rcfw_sbuf *sbuf = msg->sb; - req->resp_addr = cpu_to_le64(sbuf->dma_addr); - req->resp_size = (sbuf->size + BNXT_QPLIB_CMDQE_UNITS - 1) / + msg->req->resp_addr = cpu_to_le64(sbuf->dma_addr); + msg->req->resp_size = (sbuf->size + BNXT_QPLIB_CMDQE_UNITS - 1) / BNXT_QPLIB_CMDQE_UNITS; } - preq = (u8 *)req; + preq = (u8 *)msg->req; do { /* Locate the next cmdq slot */ sw_prod = HWQ_CMP(hwq->prod, hwq); @@ -191,7 +191,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, cmdq_prod |= BIT(FIRMWARE_FIRST_FLAG); clear_bit(FIRMWARE_FIRST_FLAG, &cmdq->flags); } - /* ring CMDQ DB */ wmb(); writel(cmdq_prod, cmdq->cmdq_mbox.prod); @@ -203,11 +202,9 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req, } int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, - struct cmdq_base *req, - struct creq_base *resp, - void *sb, u8 is_block) + struct bnxt_qplib_cmdqmsg *msg) { - struct creq_qp_event *evnt = (struct creq_qp_event *)resp; + struct creq_qp_event *evnt = (struct creq_qp_event *)msg->resp; u16 cookie; u8 opcode, retry_cnt = 0xFF; int rc = 0; @@ -217,9 +214,9 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, return 0; do { - opcode = req->opcode; - rc = __send_message(rcfw, req, resp, sb, is_block); - cookie = le16_to_cpu(req->cookie) & RCFW_MAX_COOKIE_VALUE; + opcode = msg->req->opcode; + rc = __send_message(rcfw, msg); + cookie = le16_to_cpu(msg->req->cookie) & RCFW_MAX_COOKIE_VALUE; if (!rc) break; @@ -229,11 +226,11 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, cookie, opcode); return rc; } - is_block ? mdelay(1) : usleep_range(500, 1000); + msg->block ? mdelay(1) : usleep_range(500, 1000); } while (retry_cnt--); - if (is_block) + if (msg->block) rc = __block_for_resp(rcfw, cookie); else rc = __wait_for_resp(rcfw, cookie); @@ -452,15 +449,17 @@ static irqreturn_t bnxt_qplib_creq_irq(int irq, void *dev_instance) /* RCFW */ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw) { - struct cmdq_deinitialize_fw req; - struct creq_deinitialize_fw_resp resp; + struct creq_deinitialize_fw_resp resp = {}; + struct cmdq_deinitialize_fw req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_DEINITIALIZE_FW, sizeof(req)); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, + sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; @@ -471,8 +470,9 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw) int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_ctx *ctx, int is_virtfn) { - struct creq_initialize_fw_resp resp; - struct cmdq_initialize_fw req; + struct creq_initialize_fw_resp resp = {}; + struct cmdq_initialize_fw req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; u8 pgsz, lvl; int rc; @@ -547,8 +547,8 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, skip_ctx_setup: req.stat_ctx_id = cpu_to_le32(ctx->stats.fw_id); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; set_bit(FIRMWARE_INITIALIZED_FLAG, &rcfw->cmdq.flags); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index b7f4d0a66b18..5d619ce56726 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -61,7 +61,6 @@ struct bnxt_qplib_cmdqe { static inline void bnxt_qplib_rcfw_cmd_prep(struct cmdq_base *req, u8 opcode, u8 cmd_size) { - memset(req, 0, cmd_size); req->opcode = opcode; req->cmd_size = cmd_size; } @@ -191,6 +190,27 @@ struct bnxt_qplib_rcfw { u32 cmdq_depth; }; +struct bnxt_qplib_cmdqmsg { + struct cmdq_base *req; + struct creq_base *resp; + void *sb; + u32 req_sz; + u32 res_sz; + u8 block; +}; + +static inline void bnxt_qplib_fill_cmdqmsg(struct bnxt_qplib_cmdqmsg *msg, + void *req, void *resp, void *sb, + u32 req_sz, u32 res_sz, u8 block) +{ + msg->req = req; + msg->resp = resp; + msg->sb = sb; + msg->req_sz = req_sz; + msg->res_sz = res_sz; + msg->block = block; +} + void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw, @@ -211,8 +231,7 @@ struct bnxt_qplib_rcfw_sbuf *bnxt_qplib_rcfw_alloc_sbuf( void bnxt_qplib_rcfw_free_sbuf(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_rcfw_sbuf *sbuf); int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, - struct cmdq_base *req, struct creq_base *resp, - void *sbuf, u8 is_block); + struct bnxt_qplib_cmdqmsg *msg); int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw); int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw, diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 4e2727485f9e..54c26c59bbfd 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -68,16 +68,17 @@ static bool bnxt_qplib_is_atomic_cap(struct bnxt_qplib_rcfw *rcfw) static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, char *fw_ver) { - struct cmdq_query_version req; - struct creq_query_version_resp resp; + struct creq_query_version_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_query_version req = {}; int rc = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_QUERY_VERSION, sizeof(req)); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return; fw_ver[0] = resp.fw_maj; @@ -89,10 +90,11 @@ static void bnxt_qplib_query_version(struct bnxt_qplib_rcfw *rcfw, int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_dev_attr *attr, bool vf) { + struct creq_query_func_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct creq_query_func_resp_sb *sb; struct bnxt_qplib_rcfw_sbuf *sbuf; - struct creq_query_func_resp resp; - struct cmdq_query_func req; + struct cmdq_query_func req = {}; u8 *tqm_alloc; int i, rc = 0; u32 temp; @@ -110,8 +112,9 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, sb = sbuf->sb; req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS; - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - (void *)sbuf, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto bail; @@ -176,8 +179,9 @@ int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res, struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_ctx *ctx) { - struct cmdq_set_func_resources req; - struct creq_set_func_resources_resp resp; + struct creq_set_func_resources_resp resp = {}; + struct cmdq_set_func_resources req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; int rc = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -195,9 +199,9 @@ int bnxt_qplib_set_func_resources(struct bnxt_qplib_res *res, req.max_cq_per_vf = cpu_to_le32(ctx->vf_res.max_cq_per_vf); req.max_gid_per_vf = cpu_to_le32(ctx->vf_res.max_gid_per_vf); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, - NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) { dev_err(&res->pdev->dev, "Failed to set function resources\n"); } @@ -248,8 +252,9 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, } /* Remove GID from the SGID table */ if (update) { - struct cmdq_delete_gid req; - struct creq_delete_gid_resp resp; + struct creq_delete_gid_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_delete_gid req = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -261,8 +266,9 @@ int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, return -EINVAL; } req.gid_index = cpu_to_le16(sgid_tbl->hw_id[index]); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; } @@ -319,8 +325,9 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, return -ENOMEM; } if (update) { - struct cmdq_add_gid req; - struct creq_add_gid_resp resp; + struct creq_add_gid_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_add_gid req = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -350,8 +357,9 @@ int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, req.src_mac[1] = cpu_to_be16(((u16 *)smac)[1]); req.src_mac[2] = cpu_to_be16(((u16 *)smac)[2]); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; sgid_tbl->hw_id[free_idx] = le32_to_cpu(resp.xid); @@ -380,8 +388,9 @@ int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, struct bnxt_qplib_res, sgid_tbl); struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct creq_modify_gid_resp resp; - struct cmdq_modify_gid req; + struct creq_modify_gid_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_modify_gid req = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -405,8 +414,9 @@ int bnxt_qplib_update_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl, req.gid_index = cpu_to_le16(gid_idx); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); return rc; } @@ -415,8 +425,9 @@ int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, bool block) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_create_ah req; - struct creq_create_ah_resp resp; + struct creq_create_ah_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_create_ah req = {}; u32 temp32[4]; u16 temp16[3]; int rc; @@ -446,8 +457,9 @@ int bnxt_qplib_create_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, req.dest_mac[1] = cpu_to_le16(temp16[1]); req.dest_mac[2] = cpu_to_le16(temp16[2]); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - NULL, block); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), block); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; @@ -459,8 +471,9 @@ void bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, bool block) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_destroy_ah req; - struct creq_destroy_ah_resp resp; + struct creq_destroy_ah_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_destroy_ah req = {}; /* Clean up the AH table in the device */ bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -469,16 +482,18 @@ void bnxt_qplib_destroy_ah(struct bnxt_qplib_res *res, struct bnxt_qplib_ah *ah, req.ah_cid = cpu_to_le32(ah->id); - bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, NULL, - block); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), block); + bnxt_qplib_rcfw_send_message(rcfw, &msg); } /* MRW */ int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) { + struct creq_deallocate_key_resp resp = {}; struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_deallocate_key req; - struct creq_deallocate_key_resp resp; + struct cmdq_deallocate_key req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; int rc; if (mrw->lkey == 0xFFFFFFFF) { @@ -499,8 +514,9 @@ int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) else req.key = cpu_to_le32(mrw->lkey); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; @@ -514,8 +530,9 @@ int bnxt_qplib_free_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_allocate_mrw req; - struct creq_allocate_mrw_resp resp; + struct creq_allocate_mrw_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_allocate_mrw req = {}; unsigned long tmp; int rc; @@ -533,8 +550,9 @@ int bnxt_qplib_alloc_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw) tmp = (unsigned long)mrw; req.mrw_handle = cpu_to_le64(tmp); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; @@ -551,8 +569,9 @@ int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, bool block) { struct bnxt_qplib_rcfw *rcfw = res->rcfw; - struct cmdq_deregister_mr req; - struct creq_deregister_mr_resp resp; + struct creq_deregister_mr_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_deregister_mr req = {}; int rc; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -560,8 +579,9 @@ int bnxt_qplib_dereg_mrw(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mrw, sizeof(req)); req.lkey = cpu_to_le32(mrw->lkey); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, block); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), block); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) return rc; @@ -581,8 +601,9 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, struct bnxt_qplib_rcfw *rcfw = res->rcfw; struct bnxt_qplib_hwq_attr hwq_attr = {}; struct bnxt_qplib_sg_info sginfo = {}; - struct creq_register_mr_resp resp; - struct cmdq_register_mr req; + struct creq_register_mr_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_register_mr req = {}; int pages, rc; u32 pg_size; u16 level; @@ -640,8 +661,9 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, req.key = cpu_to_le32(mr->lkey); req.mr_size = cpu_to_le64(mr->total_size); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, NULL, false); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, NULL, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto fail; @@ -695,10 +717,11 @@ int bnxt_qplib_free_fast_reg_page_list(struct bnxt_qplib_res *res, int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_roce_stats *stats) { - struct cmdq_query_roce_stats req; - struct creq_query_roce_stats_resp resp; - struct bnxt_qplib_rcfw_sbuf *sbuf; + struct creq_query_roce_stats_resp resp = {}; struct creq_query_roce_stats_resp_sb *sb; + struct cmdq_query_roce_stats req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct bnxt_qplib_rcfw_sbuf *sbuf; int rc = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, @@ -714,8 +737,9 @@ int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, sb = sbuf->sb; req.resp_size = sizeof(*sb) / BNXT_QPLIB_CMDQE_UNITS; - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, (void *)&resp, - (void *)sbuf, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto bail; /* Extract the context from the side buffer */ @@ -779,6 +803,7 @@ int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, struct creq_query_roce_stats_ext_resp resp = {}; struct creq_query_roce_stats_ext_resp_sb *sb; struct cmdq_query_roce_stats_ext req = {}; + struct bnxt_qplib_cmdqmsg msg = {}; struct bnxt_qplib_rcfw_sbuf *sbuf; int rc; @@ -798,8 +823,9 @@ int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, req.function_id = cpu_to_le32(fid); req.flags = cpu_to_le16(CMDQ_QUERY_ROCE_STATS_EXT_FLAGS_FUNCTION_ID); - rc = bnxt_qplib_rcfw_send_message(rcfw, (void *)&req, - (void *)&resp, (void *)sbuf, 0); + bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, sbuf, sizeof(req), + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); if (rc) goto bail; -- GitLab From 0722f1f7bf85c83a8ed62c626e49f97d6ebd09c3 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:38 -0700 Subject: [PATCH 1908/5631] RDMA/bnxt_re: RoCE slow path TLV support Header file to support TLV encapsulated commands. These functions will be used by the driver in the follow up patches. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-6-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_tlv.h | 162 ++++++++++++++++++++++ 1 file changed, 162 insertions(+) create mode 100644 drivers/infiniband/hw/bnxt_re/qplib_tlv.h diff --git a/drivers/infiniband/hw/bnxt_re/qplib_tlv.h b/drivers/infiniband/hw/bnxt_re/qplib_tlv.h new file mode 100644 index 000000000000..402c220734f6 --- /dev/null +++ b/drivers/infiniband/hw/bnxt_re/qplib_tlv.h @@ -0,0 +1,162 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */ + +#ifndef __QPLIB_TLV_H__ +#define __QPLIB_TLV_H__ + +struct roce_tlv { + struct tlv tlv; + u8 total_size; // in units of 16 byte chunks + u8 unused[7]; // for 16 byte alignment +}; + +#define CHUNK_SIZE 16 +#define CHUNKS(x) (((x) + CHUNK_SIZE - 1) / CHUNK_SIZE) + +static inline void __roce_1st_tlv_prep(struct roce_tlv *rtlv, u8 tot_chunks, + u16 content_bytes, u8 flags) +{ + rtlv->tlv.cmd_discr = cpu_to_le16(CMD_DISCR_TLV_ENCAP); + rtlv->tlv.tlv_type = cpu_to_le16(TLV_TYPE_ROCE_SP_COMMAND); + rtlv->tlv.length = cpu_to_le16(content_bytes); + rtlv->tlv.flags = TLV_FLAGS_REQUIRED; + rtlv->tlv.flags |= flags ? TLV_FLAGS_MORE : 0; + rtlv->total_size = (tot_chunks); +} + +static inline void __roce_ext_tlv_prep(struct roce_tlv *rtlv, u16 tlv_type, + u16 content_bytes, u8 more, u8 flags) +{ + rtlv->tlv.cmd_discr = cpu_to_le16(CMD_DISCR_TLV_ENCAP); + rtlv->tlv.tlv_type = cpu_to_le16(tlv_type); + rtlv->tlv.length = cpu_to_le16(content_bytes); + rtlv->tlv.flags |= more ? TLV_FLAGS_MORE : 0; + rtlv->tlv.flags |= flags ? TLV_FLAGS_REQUIRED : 0; +} + +/* + * TLV size in units of 16 byte chunks + */ +#define TLV_SIZE ((sizeof(struct roce_tlv) + 15) / 16) +/* + * TLV length in bytes + */ +#define TLV_BYTES (TLV_SIZE * 16) + +#define HAS_TLV_HEADER(msg) (le16_to_cpu(((struct tlv *)(msg))->cmd_discr) == CMD_DISCR_TLV_ENCAP) +#define GET_TLV_DATA(tlv) ((void *)&((uint8_t *)(tlv))[TLV_BYTES]) + +static inline u8 __get_cmdq_base_opcode(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct cmdq_base *)GET_TLV_DATA(req))->opcode; + else + return req->opcode; +} + +static inline void __set_cmdq_base_opcode(struct cmdq_base *req, + u32 size, u8 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->opcode = val; + else + req->opcode = val; +} + +static inline __le16 __get_cmdq_base_cookie(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct cmdq_base *)GET_TLV_DATA(req))->cookie; + else + return req->cookie; +} + +static inline void __set_cmdq_base_cookie(struct cmdq_base *req, + u32 size, __le16 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->cookie = val; + else + req->cookie = val; +} + +static inline __le64 __get_cmdq_base_resp_addr(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct cmdq_base *)GET_TLV_DATA(req))->resp_addr; + else + return req->resp_addr; +} + +static inline void __set_cmdq_base_resp_addr(struct cmdq_base *req, + u32 size, __le64 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->resp_addr = val; + else + req->resp_addr = val; +} + +static inline u8 __get_cmdq_base_resp_size(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct cmdq_base *)GET_TLV_DATA(req))->resp_size; + else + return req->resp_size; +} + +static inline void __set_cmdq_base_resp_size(struct cmdq_base *req, + u32 size, u8 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->resp_size = val; + else + req->resp_size = val; +} + +static inline u8 __get_cmdq_base_cmd_size(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct roce_tlv *)(req))->total_size; + else + return req->cmd_size; +} + +static inline void __set_cmdq_base_cmd_size(struct cmdq_base *req, + u32 size, u8 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->cmd_size = val; + else + req->cmd_size = val; +} + +static inline __le16 __get_cmdq_base_flags(struct cmdq_base *req, u32 size) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + return ((struct cmdq_base *)GET_TLV_DATA(req))->flags; + else + return req->flags; +} + +static inline void __set_cmdq_base_flags(struct cmdq_base *req, + u32 size, __le16 val) +{ + if (HAS_TLV_HEADER(req) && size > TLV_BYTES) + ((struct cmdq_base *)GET_TLV_DATA(req))->flags = val; + else + req->flags = val; +} + +struct bnxt_qplib_tlv_modify_cc_req { + struct roce_tlv tlv_hdr; + struct cmdq_modify_roce_cc base_req; + __le64 tlvpad; + struct cmdq_modify_roce_cc_gen1_tlv ext_req; +}; + +struct bnxt_qplib_tlv_query_rcc_sb { + struct roce_tlv tlv_hdr; + struct creq_query_roce_cc_resp_sb base_sb; + struct creq_query_roce_cc_gen1_resp_sb_tlv gen1_sb; +}; +#endif /* __QPLIB_TLV_H__ */ -- GitLab From c682c6eda08140c4706bc9e3e763867fd705dd1c Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:39 -0700 Subject: [PATCH 1909/5631] RDAM/bnxt_re: Use tlv apis while processing the slow path commands Use the new TLV APIs for existing slow path commands. The TLV APIs will be used to populate extended headers for some of the Firmware commands, which will be introduced in the patches that follow. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-7-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 7403a4ed0f9e..06979f7e1385 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -49,6 +49,7 @@ #include "qplib_rcfw.h" #include "qplib_sp.h" #include "qplib_fp.h" +#include "qplib_tlv.h" static void bnxt_qplib_service_creq(struct tasklet_struct *t); @@ -101,7 +102,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, pdev = rcfw->pdev; - opcode = msg->req->opcode; + opcode = __get_cmdq_base_opcode(msg->req, msg->req_sz); if (!test_bit(FIRMWARE_INITIALIZED_FLAG, &cmdq->flags) && (opcode != CMDQ_BASE_OPCODE_QUERY_FUNC && opcode != CMDQ_BASE_OPCODE_INITIALIZE_FW && @@ -137,7 +138,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, cookie |= RCFW_CMD_IS_BLOCKING; set_bit(cbit, cmdq->cmdq_bitmap); - msg->req->cookie = cpu_to_le16(cookie); + __set_cmdq_base_cookie(msg->req, msg->req_sz, cpu_to_le16(cookie)); crsqe = &rcfw->crsqe_tbl[cbit]; if (crsqe->resp) { spin_unlock_irqrestore(&hwq->lock, flags); @@ -153,13 +154,12 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, memset(msg->resp, 0, sizeof(*msg->resp)); crsqe->resp = (struct creq_qp_event *)msg->resp; crsqe->resp->cookie = msg->req->cookie; - crsqe->req_size = msg->req->cmd_size; - if (msg->req->resp_size && msg->sb) { + crsqe->req_size = __get_cmdq_base_cmd_size(msg->req, msg->req_sz); + if (__get_cmdq_base_resp_size(msg->req, msg->req_sz) && msg->sb) { struct bnxt_qplib_rcfw_sbuf *sbuf = msg->sb; - - msg->req->resp_addr = cpu_to_le64(sbuf->dma_addr); - msg->req->resp_size = (sbuf->size + BNXT_QPLIB_CMDQE_UNITS - 1) / - BNXT_QPLIB_CMDQE_UNITS; + __set_cmdq_base_resp_addr(msg->req, msg->req_sz, cpu_to_le64(sbuf->dma_addr)); + __set_cmdq_base_resp_size(msg->req, msg->req_sz, + ALIGN(sbuf->size, BNXT_QPLIB_CMDQE_UNITS)); } preq = (u8 *)msg->req; @@ -214,12 +214,12 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, return 0; do { - opcode = msg->req->opcode; + opcode = __get_cmdq_base_opcode(msg->req, msg->req_sz); rc = __send_message(rcfw, msg); - cookie = le16_to_cpu(msg->req->cookie) & RCFW_MAX_COOKIE_VALUE; + cookie = le16_to_cpu(__get_cmdq_base_cookie(msg->req, msg->req_sz)) & + RCFW_MAX_COOKIE_VALUE; if (!rc) break; - if (!retry_cnt || (rc != -EAGAIN && rc != -EBUSY)) { /* send failed */ dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x send failed\n", -- GitLab From f13bcef04ba0467b7901998c22408d5847d314a1 Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Thu, 30 Mar 2023 02:45:40 -0700 Subject: [PATCH 1910/5631] RDMA/bnxt_re: Enable congestion control by default Enable Congesion control by default. Issue FW command enable the CC during driver load and disable it during unload. Signed-off-by: Selvin Xavier Link: https://lore.kernel.org/r/1680169540-10029-8-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/bnxt_re/main.c | 24 ++++- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 15 ++- drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 20 +++- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 109 +++++++++++++++++++++ drivers/infiniband/hw/bnxt_re/qplib_sp.h | 67 +++++++++++++ 5 files changed, 222 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 4aa344288b0f..b9e2f89337e8 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1332,6 +1332,27 @@ static int bnxt_re_add_device(struct auxiliary_device *adev, u8 wqe_mode) return rc; } +static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) +{ + struct bnxt_qplib_cc_param cc_param = {}; + + /* Currently enabling only for GenP5 adapters */ + if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) + return; + + if (enable) { + cc_param.enable = 1; + cc_param.cc_mode = CMDQ_MODIFY_ROCE_CC_CC_MODE_PROBABILISTIC_CC_MODE; + } + + cc_param.mask = (CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_CC_MODE | + CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_ENABLE_CC | + CMDQ_MODIFY_ROCE_CC_MODIFY_MASK_TOS_ECN); + + if (bnxt_qplib_modify_cc(&rdev->qplib_res, &cc_param)) + ibdev_err(&rdev->ibdev, "Failed to setup CC enable = %d\n", enable); +} + /* * "Notifier chain callback can be invoked for the same chain from * different CPUs at the same time". @@ -1400,7 +1421,7 @@ static void bnxt_re_remove(struct auxiliary_device *adev) */ goto skip_remove; } - + bnxt_re_setup_cc(rdev, false); ib_unregister_device(&rdev->ibdev); ib_dealloc_device(&rdev->ibdev); bnxt_re_dev_uninit(rdev); @@ -1432,6 +1453,7 @@ static int bnxt_re_probe(struct auxiliary_device *adev, goto err; } + bnxt_re_setup_cc(rdev, true); mutex_unlock(&bnxt_re_mutex); return 0; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index 06979f7e1385..de9069103177 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -96,7 +96,7 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, u32 sw_prod, cmdq_prod; struct pci_dev *pdev; unsigned long flags; - u32 size, opcode; + u32 bsize, opcode; u16 cookie, cbit; u8 *preq; @@ -145,15 +145,14 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, return -EBUSY; } - size = msg->req->cmd_size; /* change the cmd_size to the number of 16byte cmdq unit. * req->cmd_size is modified here */ - bnxt_qplib_set_cmd_slots(msg->req); + bsize = bnxt_qplib_set_cmd_slots(msg->req); memset(msg->resp, 0, sizeof(*msg->resp)); crsqe->resp = (struct creq_qp_event *)msg->resp; - crsqe->resp->cookie = msg->req->cookie; + crsqe->resp->cookie = cpu_to_le16(cookie); crsqe->req_size = __get_cmdq_base_cmd_size(msg->req, msg->req_sz); if (__get_cmdq_base_resp_size(msg->req, msg->req_sz) && msg->sb) { struct bnxt_qplib_rcfw_sbuf *sbuf = msg->sb; @@ -174,11 +173,11 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, } /* Copy a segment of the req cmd to the cmdq */ memset(cmdqe, 0, sizeof(*cmdqe)); - memcpy(cmdqe, preq, min_t(u32, size, sizeof(*cmdqe))); - preq += min_t(u32, size, sizeof(*cmdqe)); - size -= min_t(u32, size, sizeof(*cmdqe)); + memcpy(cmdqe, preq, min_t(u32, bsize, sizeof(*cmdqe))); + preq += min_t(u32, bsize, sizeof(*cmdqe)); + bsize -= min_t(u32, bsize, sizeof(*cmdqe)); hwq->prod++; - } while (size > 0); + } while (bsize > 0); cmdq->seq_num++; cmdq_prod = hwq->prod; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h index 5d619ce56726..dd5651478bbb 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h @@ -39,6 +39,8 @@ #ifndef __BNXT_QPLIB_RCFW_H__ #define __BNXT_QPLIB_RCFW_H__ +#include "qplib_tlv.h" + #define RCFW_CMDQ_TRIG_VAL 1 #define RCFW_COMM_PCI_BAR_REGION 0 #define RCFW_COMM_CONS_PCI_BAR_REGION 2 @@ -87,11 +89,21 @@ static inline u32 bnxt_qplib_cmdqe_page_size(u32 depth) return (bnxt_qplib_cmdqe_npages(depth) * PAGE_SIZE); } -/* Set the cmd_size to a factor of CMDQE unit */ -static inline void bnxt_qplib_set_cmd_slots(struct cmdq_base *req) +static inline u32 bnxt_qplib_set_cmd_slots(struct cmdq_base *req) { - req->cmd_size = (req->cmd_size + BNXT_QPLIB_CMDQE_UNITS - 1) / - BNXT_QPLIB_CMDQE_UNITS; + u32 cmd_byte = 0; + + if (HAS_TLV_HEADER(req)) { + struct roce_tlv *tlv_req = (struct roce_tlv *)req; + + cmd_byte = tlv_req->total_size * BNXT_QPLIB_CMDQE_UNITS; + } else { + cmd_byte = req->cmd_size; + req->cmd_size = (req->cmd_size + BNXT_QPLIB_CMDQE_UNITS - 1) / + BNXT_QPLIB_CMDQE_UNITS; + } + + return cmd_byte; } #define RCFW_MAX_COOKIE_VALUE 0x7FFF diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 54c26c59bbfd..1714a1e23113 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -48,6 +48,7 @@ #include "qplib_res.h" #include "qplib_rcfw.h" #include "qplib_sp.h" +#include "qplib_tlv.h" const struct bnxt_qplib_gid bnxt_qplib_gid_zero = {{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 } }; @@ -849,3 +850,111 @@ int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, bnxt_qplib_rcfw_free_sbuf(rcfw, sbuf); return rc; } + +static void bnxt_qplib_fill_cc_gen1(struct cmdq_modify_roce_cc_gen1_tlv *ext_req, + struct bnxt_qplib_cc_param_ext *cc_ext) +{ + ext_req->modify_mask = cpu_to_le64(cc_ext->ext_mask); + cc_ext->ext_mask = 0; + ext_req->inactivity_th_hi = cpu_to_le16(cc_ext->inact_th_hi); + ext_req->min_time_between_cnps = cpu_to_le16(cc_ext->min_delta_cnp); + ext_req->init_cp = cpu_to_le16(cc_ext->init_cp); + ext_req->tr_update_mode = cc_ext->tr_update_mode; + ext_req->tr_update_cycles = cc_ext->tr_update_cyls; + ext_req->fr_num_rtts = cc_ext->fr_rtt; + ext_req->ai_rate_increase = cc_ext->ai_rate_incr; + ext_req->reduction_relax_rtts_th = cpu_to_le16(cc_ext->rr_rtt_th); + ext_req->additional_relax_cr_th = cpu_to_le16(cc_ext->ar_cr_th); + ext_req->cr_min_th = cpu_to_le16(cc_ext->cr_min_th); + ext_req->bw_avg_weight = cc_ext->bw_avg_weight; + ext_req->actual_cr_factor = cc_ext->cr_factor; + ext_req->max_cp_cr_th = cpu_to_le16(cc_ext->cr_th_max_cp); + ext_req->cp_bias_en = cc_ext->cp_bias_en; + ext_req->cp_bias = cc_ext->cp_bias; + ext_req->cnp_ecn = cc_ext->cnp_ecn; + ext_req->rtt_jitter_en = cc_ext->rtt_jitter_en; + ext_req->link_bytes_per_usec = cpu_to_le16(cc_ext->bytes_per_usec); + ext_req->reset_cc_cr_th = cpu_to_le16(cc_ext->cc_cr_reset_th); + ext_req->cr_width = cc_ext->cr_width; + ext_req->quota_period_min = cc_ext->min_quota; + ext_req->quota_period_max = cc_ext->max_quota; + ext_req->quota_period_abs_max = cc_ext->abs_max_quota; + ext_req->tr_lower_bound = cpu_to_le16(cc_ext->tr_lb); + ext_req->cr_prob_factor = cc_ext->cr_prob_fac; + ext_req->tr_prob_factor = cc_ext->tr_prob_fac; + ext_req->fairness_cr_th = cpu_to_le16(cc_ext->fair_cr_th); + ext_req->red_div = cc_ext->red_div; + ext_req->cnp_ratio_th = cc_ext->cnp_ratio_th; + ext_req->exp_ai_rtts = cpu_to_le16(cc_ext->ai_ext_rtt); + ext_req->exp_ai_cr_cp_ratio = cc_ext->exp_crcp_ratio; + ext_req->use_rate_table = cc_ext->low_rate_en; + ext_req->cp_exp_update_th = cpu_to_le16(cc_ext->cpcr_update_th); + ext_req->high_exp_ai_rtts_th1 = cpu_to_le16(cc_ext->ai_rtt_th1); + ext_req->high_exp_ai_rtts_th2 = cpu_to_le16(cc_ext->ai_rtt_th2); + ext_req->actual_cr_cong_free_rtts_th = cpu_to_le16(cc_ext->cf_rtt_th); + ext_req->severe_cong_cr_th1 = cpu_to_le16(cc_ext->sc_cr_th1); + ext_req->severe_cong_cr_th2 = cpu_to_le16(cc_ext->sc_cr_th2); + ext_req->link64B_per_rtt = cpu_to_le32(cc_ext->l64B_per_rtt); + ext_req->cc_ack_bytes = cc_ext->cc_ack_bytes; +} + +int bnxt_qplib_modify_cc(struct bnxt_qplib_res *res, + struct bnxt_qplib_cc_param *cc_param) +{ + struct bnxt_qplib_tlv_modify_cc_req tlv_req = {}; + struct creq_modify_roce_cc_resp resp = {}; + struct bnxt_qplib_cmdqmsg msg = {}; + struct cmdq_modify_roce_cc *req; + int req_size; + void *cmd; + int rc; + + /* Prepare the older base command */ + req = &tlv_req.base_req; + cmd = req; + req_size = sizeof(*req); + bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)req, CMDQ_BASE_OPCODE_MODIFY_ROCE_CC, + sizeof(*req)); + req->modify_mask = cpu_to_le32(cc_param->mask); + req->enable_cc = cc_param->enable; + req->g = cc_param->g; + req->num_phases_per_state = cc_param->nph_per_state; + req->time_per_phase = cc_param->time_pph; + req->pkts_per_phase = cc_param->pkts_pph; + req->init_cr = cpu_to_le16(cc_param->init_cr); + req->init_tr = cpu_to_le16(cc_param->init_tr); + req->tos_dscp_tos_ecn = (cc_param->tos_dscp << CMDQ_MODIFY_ROCE_CC_TOS_DSCP_SFT) | + (cc_param->tos_ecn & CMDQ_MODIFY_ROCE_CC_TOS_ECN_MASK); + req->alt_vlan_pcp = cc_param->alt_vlan_pcp; + req->alt_tos_dscp = cpu_to_le16(cc_param->alt_tos_dscp); + req->rtt = cpu_to_le16(cc_param->rtt); + req->tcp_cp = cpu_to_le16(cc_param->tcp_cp); + req->cc_mode = cc_param->cc_mode; + req->inactivity_th = cpu_to_le16(cc_param->inact_th); + + /* For chip gen P5 onwards fill extended cmd and header */ + if (bnxt_qplib_is_chip_gen_p5(res->cctx)) { + struct roce_tlv *hdr; + u32 payload; + u32 chunks; + + cmd = &tlv_req; + req_size = sizeof(tlv_req); + /* Prepare primary tlv header */ + hdr = &tlv_req.tlv_hdr; + chunks = CHUNKS(sizeof(struct bnxt_qplib_tlv_modify_cc_req)); + payload = sizeof(struct cmdq_modify_roce_cc); + __roce_1st_tlv_prep(hdr, chunks, payload, true); + /* Prepare secondary tlv header */ + hdr = (struct roce_tlv *)&tlv_req.ext_req; + payload = sizeof(struct cmdq_modify_roce_cc_gen1_tlv) - + sizeof(struct roce_tlv); + __roce_ext_tlv_prep(hdr, TLV_TYPE_MODIFY_ROCE_CC_GEN1, payload, false, true); + bnxt_qplib_fill_cc_gen1(&tlv_req.ext_req, &cc_param->cc_ext); + } + + bnxt_qplib_fill_cmdqmsg(&msg, cmd, &resp, NULL, req_size, + sizeof(resp), 0); + rc = bnxt_qplib_rcfw_send_message(res->rcfw, &msg); + return rc; +} diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.h b/drivers/infiniband/hw/bnxt_re/qplib_sp.h index 96e61db6ac6b..5de874659cdf 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.h @@ -244,6 +244,71 @@ struct bnxt_qplib_ext_stat { u64 rx_ecn_marked; }; +struct bnxt_qplib_cc_param_ext { + u64 ext_mask; + u16 inact_th_hi; + u16 min_delta_cnp; + u16 init_cp; + u8 tr_update_mode; + u8 tr_update_cyls; + u8 fr_rtt; + u8 ai_rate_incr; + u16 rr_rtt_th; + u16 ar_cr_th; + u16 cr_min_th; + u8 bw_avg_weight; + u8 cr_factor; + u16 cr_th_max_cp; + u8 cp_bias_en; + u8 cp_bias; + u8 cnp_ecn; + u8 rtt_jitter_en; + u16 bytes_per_usec; + u16 cc_cr_reset_th; + u8 cr_width; + u8 min_quota; + u8 max_quota; + u8 abs_max_quota; + u16 tr_lb; + u8 cr_prob_fac; + u8 tr_prob_fac; + u16 fair_cr_th; + u8 red_div; + u8 cnp_ratio_th; + u16 ai_ext_rtt; + u8 exp_crcp_ratio; + u8 low_rate_en; + u16 cpcr_update_th; + u16 ai_rtt_th1; + u16 ai_rtt_th2; + u16 cf_rtt_th; + u16 sc_cr_th1; /* severe congestion cr threshold 1 */ + u16 sc_cr_th2; /* severe congestion cr threshold 2 */ + u32 l64B_per_rtt; + u8 cc_ack_bytes; + u16 reduce_cf_rtt_th; +}; + +struct bnxt_qplib_cc_param { + u8 alt_vlan_pcp; + u16 alt_tos_dscp; + u8 cc_mode; + u8 enable; + u16 inact_th; + u16 init_cr; + u16 init_tr; + u16 rtt; + u8 g; + u8 nph_per_state; + u8 time_pph; + u8 pkts_pph; + u8 tos_ecn; + u8 tos_dscp; + u16 tcp_cp; + struct bnxt_qplib_cc_param_ext cc_ext; + u32 mask; +}; + int bnxt_qplib_get_sgid(struct bnxt_qplib_res *res, struct bnxt_qplib_sgid_tbl *sgid_tbl, int index, struct bnxt_qplib_gid *gid); @@ -281,5 +346,7 @@ int bnxt_qplib_get_roce_stats(struct bnxt_qplib_rcfw *rcfw, struct bnxt_qplib_roce_stats *stats); int bnxt_qplib_qext_stat(struct bnxt_qplib_rcfw *rcfw, u32 fid, struct bnxt_qplib_ext_stat *estat); +int bnxt_qplib_modify_cc(struct bnxt_qplib_res *res, + struct bnxt_qplib_cc_param *cc_param); #endif /* __BNXT_QPLIB_SP_H__*/ -- GitLab From e4ab08be5b4902e5b350b0e1e1a3c25eb21d76d4 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 17:30:45 -0500 Subject: [PATCH 1911/5631] powerpc/isa-bridge: Remove open coded "ranges" parsing "ranges" is a standard property with common parsing functions. Users shouldn't be implementing their own parsing of it. Reimplement the ISA brige "ranges" parsing using the common ranges iterator functions. The common routines are flexible enough to work on PCI and non-PCI to ISA bridges, so refactor pci_process_ISA_OF_ranges() and isa_bridge_init_non_pci() into a single implementation. Signed-off-by: Rob Herring [mpe: Unsplit some strings and use pr_xxx()] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230327223045.819852-1-robh@kernel.org --- arch/powerpc/kernel/isa-bridge.c | 166 +++++++------------------------ 1 file changed, 37 insertions(+), 129 deletions(-) diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index dc746611ebc0..85bdd7d3652f 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -55,80 +55,49 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size) } } -static void pci_process_ISA_OF_ranges(struct device_node *isa_node, - unsigned long phb_io_base_phys) +static int process_ISA_OF_ranges(struct device_node *isa_node, + unsigned long phb_io_base_phys) { - /* We should get some saner parsing here and remove these structs */ - struct pci_address { - u32 a_hi; - u32 a_mid; - u32 a_lo; - }; - - struct isa_address { - u32 a_hi; - u32 a_lo; - }; - - struct isa_range { - struct isa_address isa_addr; - struct pci_address pci_addr; - unsigned int size; - }; - - const struct isa_range *range; - unsigned long pci_addr; - unsigned int isa_addr; unsigned int size; - int rlen = 0; + struct of_range_parser parser; + struct of_range range; - range = of_get_property(isa_node, "ranges", &rlen); - if (range == NULL || (rlen < sizeof(struct isa_range))) + if (of_range_parser_init(&parser, isa_node)) goto inval_range; - /* From "ISA Binding to 1275" - * The ranges property is laid out as an array of elements, - * each of which comprises: - * cells 0 - 1: an ISA address - * cells 2 - 4: a PCI address - * (size depending on dev->n_addr_cells) - * cell 5: the size of the range - */ - if ((range->isa_addr.a_hi & ISA_SPACE_MASK) != ISA_SPACE_IO) { - range++; - rlen -= sizeof(struct isa_range); - if (rlen < sizeof(struct isa_range)) - goto inval_range; - } - if ((range->isa_addr.a_hi & ISA_SPACE_MASK) != ISA_SPACE_IO) - goto inval_range; + for_each_of_range(&parser, &range) { + if ((range.flags & ISA_SPACE_MASK) != ISA_SPACE_IO) + continue; - isa_addr = range->isa_addr.a_lo; - pci_addr = (unsigned long) range->pci_addr.a_mid << 32 | - range->pci_addr.a_lo; + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("ISA: Bad CPU mapping: %s\n", __func__); + return -EINVAL; + } - /* Assume these are both zero. Note: We could fix that and - * do a proper parsing instead ... oh well, that will do for - * now as nobody uses fancy mappings for ISA bridges - */ - if ((pci_addr != 0) || (isa_addr != 0)) { - printk(KERN_ERR "unexpected isa to pci mapping: %s\n", - __func__); - return; - } + /* We need page alignment */ + if ((range.bus_addr & ~PAGE_MASK) || (range.cpu_addr & ~PAGE_MASK)) { + pr_warn("ISA: bridge %pOF has non aligned IO range\n", isa_node); + return -EINVAL; + } - /* Align size and make sure it's cropped to 64K */ - size = PAGE_ALIGN(range->size); - if (size > 0x10000) - size = 0x10000; + /* Align size and make sure it's cropped to 64K */ + size = PAGE_ALIGN(range.size); + if (size > 0x10000) + size = 0x10000; - remap_isa_base(phb_io_base_phys, size); - return; + if (!phb_io_base_phys) + phb_io_base_phys = range.cpu_addr; + + remap_isa_base(phb_io_base_phys, size); + return 0; + } inval_range: - printk(KERN_ERR "no ISA IO ranges or unexpected isa range, " - "mapping 64k\n"); - remap_isa_base(phb_io_base_phys, 0x10000); + if (!phb_io_base_phys) { + pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); + remap_isa_base(phb_io_base_phys, 0x10000); + } + return 0; } @@ -170,7 +139,7 @@ void __init isa_bridge_find_early(struct pci_controller *hose) isa_bridge_devnode = np; /* Now parse the "ranges" property and setup the ISA mapping */ - pci_process_ISA_OF_ranges(np, hose->io_base_phys); + process_ISA_OF_ranges(np, hose->io_base_phys); /* Set the global ISA io base to indicate we have an ISA bridge */ isa_io_base = ISA_IO_BASE; @@ -186,75 +155,15 @@ void __init isa_bridge_find_early(struct pci_controller *hose) */ void __init isa_bridge_init_non_pci(struct device_node *np) { - const __be32 *ranges, *pbasep = NULL; - int rlen, i, rs; - u32 na, ns, pna; - u64 cbase, pbase, size = 0; + int ret; /* If we already have an ISA bridge, bail off */ if (isa_bridge_devnode != NULL) return; - pna = of_n_addr_cells(np); - if (of_property_read_u32(np, "#address-cells", &na) || - of_property_read_u32(np, "#size-cells", &ns)) { - pr_warn("ISA: Non-PCI bridge %pOF is missing address format\n", - np); - return; - } - - /* Check it's a supported address format */ - if (na != 2 || ns != 1) { - pr_warn("ISA: Non-PCI bridge %pOF has unsupported address format\n", - np); - return; - } - rs = na + ns + pna; - - /* Grab the ranges property */ - ranges = of_get_property(np, "ranges", &rlen); - if (ranges == NULL || rlen < rs) { - pr_warn("ISA: Non-PCI bridge %pOF has absent or invalid ranges\n", - np); - return; - } - - /* Parse it. We are only looking for IO space */ - for (i = 0; (i + rs - 1) < rlen; i += rs) { - if (be32_to_cpup(ranges + i) != 1) - continue; - cbase = be32_to_cpup(ranges + i + 1); - size = of_read_number(ranges + i + na + pna, ns); - pbasep = ranges + i + na; - break; - } - - /* Got something ? */ - if (!size || !pbasep) { - pr_warn("ISA: Non-PCI bridge %pOF has no usable IO range\n", - np); + ret = process_ISA_OF_ranges(np, 0); + if (ret) return; - } - - /* Align size and make sure it's cropped to 64K */ - size = PAGE_ALIGN(size); - if (size > 0x10000) - size = 0x10000; - - /* Map pbase */ - pbase = of_translate_address(np, pbasep); - if (pbase == OF_BAD_ADDR) { - pr_warn("ISA: Non-PCI bridge %pOF failed to translate IO base\n", - np); - return; - } - - /* We need page alignment */ - if ((cbase & ~PAGE_MASK) || (pbase & ~PAGE_MASK)) { - pr_warn("ISA: Non-PCI bridge %pOF has non aligned IO range\n", - np); - return; - } /* Got it */ isa_bridge_devnode = np; @@ -263,7 +172,6 @@ void __init isa_bridge_init_non_pci(struct device_node *np) * and map it */ isa_io_base = ISA_IO_BASE; - remap_isa_base(pbase, size); pr_debug("ISA: Non-PCI bridge is %pOF\n", np); } @@ -282,7 +190,7 @@ static void isa_bridge_find_late(struct pci_dev *pdev, isa_bridge_pcidev = pdev; /* Now parse the "ranges" property and setup the ISA mapping */ - pci_process_ISA_OF_ranges(devnode, hose->io_base_phys); + process_ISA_OF_ranges(devnode, hose->io_base_phys); /* Set the global ISA io base to indicate we have an ISA bridge */ isa_io_base = ISA_IO_BASE; -- GitLab From 037c47a436eab2d336d5e131ab1c1394f223a57b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 17:30:56 -0500 Subject: [PATCH 1912/5631] powerpc/xics: Use of_address_count() icp_native_init_one_node() only needs the number of entries in "reg". Replace the open coded "reg" parsing with of_address_count() to get the number of "reg" entries. Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230327223056.820086-1-robh@kernel.org --- arch/powerpc/sysdev/xics/icp-native.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index edc17b6b1cc2..f6ec6dba92dc 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -259,7 +259,7 @@ static int __init icp_native_init_one_node(struct device_node *np, unsigned int ilen; const __be32 *ireg; int i; - int reg_tuple_size; + int num_reg; int num_servers = 0; /* This code does the theorically broken assumption that the interrupt @@ -280,21 +280,14 @@ static int __init icp_native_init_one_node(struct device_node *np, num_servers = of_read_number(ireg + 1, 1); } - ireg = of_get_property(np, "reg", &ilen); - if (!ireg) { - pr_err("icp_native: Can't find interrupt reg property"); - return -1; - } - - reg_tuple_size = (of_n_addr_cells(np) + of_n_size_cells(np)) * 4; - if (((ilen % reg_tuple_size) != 0) - || (num_servers && (num_servers != (ilen / reg_tuple_size)))) { + num_reg = of_address_count(np); + if (num_servers && (num_servers != num_reg)) { pr_err("icp_native: ICP reg len (%d) != num servers (%d)", - ilen / reg_tuple_size, num_servers); + num_reg, num_servers); return -1; } - for (i = 0; i < (ilen / reg_tuple_size); i++) { + for (i = 0; i < num_reg; i++) { struct resource r; int err; -- GitLab From de8d11bc6ec412a498acf795911c8597ae37d4e7 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 17:31:02 -0500 Subject: [PATCH 1913/5631] powerpc/fsl_rio: Use of_iomap() Replace of_address_to_resource()+ioremap() with a call to of_iomap() which does both of those steps. Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230327223103.820229-1-robh@kernel.org --- arch/powerpc/sysdev/fsl_rio.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index c8f044d62fe2..f8e492ee54cc 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -450,7 +450,6 @@ int fsl_rio_setup(struct platform_device *dev) int rc = 0; const u32 *dt_range, *cell, *port_index; u32 active_ports = 0; - struct resource regs, rmu_regs; struct device_node *np, *rmu_node; int rlen; u32 ccsr; @@ -465,17 +464,7 @@ int fsl_rio_setup(struct platform_device *dev) return -ENODEV; } - rc = of_address_to_resource(dev->dev.of_node, 0, ®s); - if (rc) { - dev_err(&dev->dev, "Can't get %pOF property 'reg'\n", - dev->dev.of_node); - return -EFAULT; - } - dev_info(&dev->dev, "Of-device full name %pOF\n", - dev->dev.of_node); - dev_info(&dev->dev, "Regs: %pR\n", ®s); - - rio_regs_win = ioremap(regs.start, resource_size(®s)); + rio_regs_win = of_iomap(dev->dev.of_node, 0); if (!rio_regs_win) { dev_err(&dev->dev, "Unable to map rio register window\n"); rc = -ENOMEM; @@ -509,15 +498,9 @@ int fsl_rio_setup(struct platform_device *dev) rc = -ENOENT; goto err_rmu; } - rc = of_address_to_resource(rmu_node, 0, &rmu_regs); - if (rc) { - dev_err(&dev->dev, "Can't get %pOF property 'reg'\n", - rmu_node); - of_node_put(rmu_node); - goto err_rmu; - } + rmu_regs_win = of_iomap(rmu_node, 0); + of_node_put(rmu_node); - rmu_regs_win = ioremap(rmu_regs.start, resource_size(&rmu_regs)); if (!rmu_regs_win) { dev_err(&dev->dev, "Unable to map rmu register window\n"); rc = -ENOMEM; -- GitLab From 83a8fe569ef84d6eefcb99420a731cb87508f004 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 17:31:09 -0500 Subject: [PATCH 1914/5631] powerpc/usbgecko: Use of_iomap() Replace of_get_property()+of_translate_address()+ioremap() with a call to of_iomap() which does all those steps. Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230327223109.820381-1-robh@kernel.org --- .../platforms/embedded6xx/usbgecko_udbg.c | 20 +------------------ 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c index e02bdabf358c..221577f32b01 100644 --- a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c +++ b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c @@ -192,24 +192,6 @@ static int ug_udbg_getc_poll(void) return ug_getc(); } -/* - * Retrieves and prepares the virtual address needed to access the hardware. - */ -static void __iomem *__init ug_udbg_setup_exi_io_base(struct device_node *np) -{ - void __iomem *exi_io_base = NULL; - phys_addr_t paddr; - const unsigned int *reg; - - reg = of_get_property(np, "reg", NULL); - if (reg) { - paddr = of_translate_address(np, reg); - if (paddr) - exi_io_base = ioremap(paddr, reg[1]); - } - return exi_io_base; -} - /* * Checks if a USB Gecko adapter is inserted in any memory card slot. */ @@ -246,7 +228,7 @@ void __init ug_udbg_init(void) goto out; } - exi_io_base = ug_udbg_setup_exi_io_base(np); + exi_io_base = of_iomap(np, 0); if (!exi_io_base) { udbg_printf("%s: failed to setup EXI io base\n", __func__); goto done; -- GitLab From 2500763dd3db37fad94d9b506907c59c2f5e97c6 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 29 Mar 2023 17:03:36 -0500 Subject: [PATCH 1915/5631] powerpc: Use of_address_to_resource() Replace open coded reading of "reg" or of_get_address()/ of_translate_address() calls with a single call to of_address_to_resource(). Signed-off-by: Rob Herring Signed-off-by: Michael Ellerman Link: https://msgid.link/20230329220337.141295-1-robh@kernel.org --- arch/powerpc/mm/numa.c | 21 +++------ arch/powerpc/platforms/52xx/lite5200_pm.c | 9 ++-- arch/powerpc/platforms/cell/axon_msi.c | 9 ++-- arch/powerpc/platforms/embedded6xx/holly.c | 7 ++- arch/powerpc/platforms/embedded6xx/ls_uart.c | 17 ++++--- arch/powerpc/platforms/powermac/feature.c | 16 +++---- .../platforms/pseries/hotplug-memory.c | 45 +++++-------------- arch/powerpc/platforms/pseries/iommu.c | 20 +++------ arch/powerpc/sysdev/tsi108_dev.c | 6 +-- 9 files changed, 51 insertions(+), 99 deletions(-) diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b44ce71917d7..3a5c0d56b1ad 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -1288,23 +1289,15 @@ static int hot_add_node_scn_to_nid(unsigned long scn_addr) int nid = NUMA_NO_NODE; for_each_node_by_type(memory, "memory") { - unsigned long start, size; - int ranges; - const __be32 *memcell_buf; - unsigned int len; - - memcell_buf = of_get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) - continue; + int i = 0; - /* ranges in cell */ - ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells); + while (1) { + struct resource res; - while (ranges--) { - start = read_n_cells(n_mem_addr_cells, &memcell_buf); - size = read_n_cells(n_mem_size_cells, &memcell_buf); + if (of_address_to_resource(memory, i++, &res)) + break; - if ((scn_addr < start) || (scn_addr >= (start + size))) + if ((scn_addr < res.start) || (scn_addr > res.end)) continue; nid = of_node_to_nid_single(memory); diff --git a/arch/powerpc/platforms/52xx/lite5200_pm.c b/arch/powerpc/platforms/52xx/lite5200_pm.c index 129313b1d021..ee29b63fca16 100644 --- a/arch/powerpc/platforms/52xx/lite5200_pm.c +++ b/arch/powerpc/platforms/52xx/lite5200_pm.c @@ -54,8 +54,7 @@ static int lite5200_pm_prepare(void) { .type = "builtin", .compatible = "mpc5200", }, /* efika */ {} }; - u64 regaddr64 = 0; - const u32 *regaddr_p; + struct resource res; /* deep sleep? let mpc52xx code handle that */ if (lite5200_pm_target_state == PM_SUSPEND_STANDBY) @@ -66,12 +65,10 @@ static int lite5200_pm_prepare(void) /* map registers */ np = of_find_matching_node(NULL, immr_ids); - regaddr_p = of_get_address(np, 0, NULL, NULL); - if (regaddr_p) - regaddr64 = of_translate_address(np, regaddr_p); + of_address_to_resource(np, 0, &res); of_node_put(np); - mbar = ioremap((u32) regaddr64, 0xC000); + mbar = ioremap(res.start, 0xC000); if (!mbar) { printk(KERN_ERR "%s:%i Error mapping registers\n", __func__, __LINE__); return -ENOSYS; diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 0c11aad896c7..106000449d3b 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -460,15 +460,14 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_msic, msic_get, msic_set, "%llu\n"); void axon_msi_debug_setup(struct device_node *dn, struct axon_msic *msic) { char name[8]; - u64 addr; + struct resource res; - addr = of_translate_address(dn, of_get_property(dn, "reg", NULL)); - if (addr == OF_BAD_ADDR) { - pr_devel("axon_msi: couldn't translate reg property\n"); + if (of_address_to_resource(dn, 0, &res)) { + pr_devel("axon_msi: couldn't get reg property\n"); return; } - msic->trigger = ioremap(addr, 0x4); + msic->trigger = ioremap(res.start, 0x4); if (!msic->trigger) { pr_devel("axon_msi: ioremap failed\n"); return; diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c index a167ee88fbf9..02ff260ae1ee 100644 --- a/arch/powerpc/platforms/embedded6xx/holly.c +++ b/arch/powerpc/platforms/embedded6xx/holly.c @@ -205,16 +205,15 @@ static void __noreturn holly_restart(char *cmd) __be32 __iomem *ocn_bar1 = NULL; unsigned long bar; struct device_node *bridge = NULL; - const void *prop; - int size; + struct resource res; phys_addr_t addr = 0xc0000000; local_irq_disable(); bridge = of_find_node_by_type(NULL, "tsi-bridge"); if (bridge) { - prop = of_get_property(bridge, "reg", &size); - addr = of_translate_address(bridge, prop); + of_address_to_resource(bridge, 0, &res); + addr = res.start; of_node_put(bridge); } addr += (TSI108_PB_OFFSET + 0x414); diff --git a/arch/powerpc/platforms/embedded6xx/ls_uart.c b/arch/powerpc/platforms/embedded6xx/ls_uart.c index 4ecbc55b37c0..6c1dbf8ae718 100644 --- a/arch/powerpc/platforms/embedded6xx/ls_uart.c +++ b/arch/powerpc/platforms/embedded6xx/ls_uart.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -114,22 +115,24 @@ static void __init ls_uart_init(void) static int __init ls_uarts_init(void) { struct device_node *avr; - phys_addr_t phys_addr; - int len; + struct resource res; + int len, ret; avr = of_find_node_by_path("/soc10x/serial@80004500"); if (!avr) return -EINVAL; avr_clock = *(u32*)of_get_property(avr, "clock-frequency", &len); - phys_addr = ((u32*)of_get_property(avr, "reg", &len))[0]; + if (!avr_clock) + return -EINVAL; - of_node_put(avr); + ret = of_address_to_resource(avr, 0, &res); + if (ret) + return ret; - if (!avr_clock || !phys_addr) - return -EINVAL; + of_node_put(avr); - avr_addr = ioremap(phys_addr, 32); + avr_addr = ioremap(res.start, 32); if (!avr_addr) return -EFAULT; diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 6b1f974b074f..a195d5faa4e5 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2545,8 +2545,7 @@ static int __init probe_motherboard(void) */ static void __init probe_uninorth(void) { - const u32 *addrp; - phys_addr_t address; + struct resource res; unsigned long actrl; /* Locate core99 Uni-N */ @@ -2568,18 +2567,15 @@ static void __init probe_uninorth(void) return; } - addrp = of_get_property(uninorth_node, "reg", NULL); - if (addrp == NULL) + if (of_address_to_resource(uninorth_node, 0, &res)) return; - address = of_translate_address(uninorth_node, addrp); - if (address == 0) - return; - uninorth_base = ioremap(address, 0x40000); + + uninorth_base = ioremap(res.start, 0x40000); if (uninorth_base == NULL) return; uninorth_rev = in_be32(UN_REG(UNI_N_VERSION)); if (uninorth_maj == 3 || uninorth_maj == 4) { - u3_ht_base = ioremap(address + U3_HT_CONFIG_BASE, 0x1000); + u3_ht_base = ioremap(res.start + U3_HT_CONFIG_BASE, 0x1000); if (u3_ht_base == NULL) { iounmap(uninorth_base); return; @@ -2589,7 +2585,7 @@ static void __init probe_uninorth(void) printk(KERN_INFO "Found %s memory controller & host bridge" " @ 0x%08x revision: 0x%02x\n", uninorth_maj == 3 ? "U3" : uninorth_maj == 4 ? "U4" : "UniNorth", - (unsigned int)address, uninorth_rev); + (unsigned int)res.start, uninorth_rev); printk(KERN_INFO "Mapped at 0x%08lx\n", (unsigned long)uninorth_base); /* Set the arbitrer QAck delay according to what Apple does diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2e3a317722a8..9c62c2c3b3d0 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -311,11 +311,8 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si static int pseries_remove_mem_node(struct device_node *np) { - const __be32 *prop; - unsigned long base; - unsigned long lmb_size; - int ret = -EINVAL; - int addr_cells, size_cells; + int ret; + struct resource res; /* * Check to see if we are actually removing memory @@ -326,21 +323,11 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Find the base address and size of the memblock */ - prop = of_get_property(np, "reg", NULL); - if (!prop) + ret = of_address_to_resource(np, 0, &res); + if (ret) return ret; - addr_cells = of_n_addr_cells(np); - size_cells = of_n_size_cells(np); - - /* - * "reg" property represents (addr,size) tuple. - */ - base = of_read_number(prop, addr_cells); - prop += addr_cells; - lmb_size = of_read_number(prop, size_cells); - - pseries_remove_memblock(base, lmb_size); + pseries_remove_memblock(res.start, resource_size(&res)); return 0; } @@ -929,11 +916,8 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const __be32 *prop; - unsigned long base; - unsigned long lmb_size; - int ret = -EINVAL; - int addr_cells, size_cells; + int ret; + struct resource res; /* * Check to see if we are actually adding memory @@ -944,23 +928,14 @@ static int pseries_add_mem_node(struct device_node *np) /* * Find the base and size of the memblock */ - prop = of_get_property(np, "reg", NULL); - if (!prop) + ret = of_address_to_resource(np, 0, &res); + if (ret) return ret; - addr_cells = of_n_addr_cells(np); - size_cells = of_n_size_cells(np); - /* - * "reg" property represents (addr,size) tuple. - */ - base = of_read_number(prop, addr_cells); - prop += addr_cells; - lmb_size = of_read_number(prop, size_cells); - /* * Update memory region to represent the memory add */ - ret = memblock_add(base, lmb_size); + ret = memblock_add(res.start, resource_size(&res)); return (ret < 0) ? -EINVAL : 0; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 256493111d1d..7464fa6e4145 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -1116,27 +1117,16 @@ static LIST_HEAD(failed_ddw_pdn_list); static phys_addr_t ddw_memory_hotplug_max(void) { - phys_addr_t max_addr = memory_hotplug_max(); + resource_size_t max_addr = memory_hotplug_max(); struct device_node *memory; for_each_node_by_type(memory, "memory") { - unsigned long start, size; - int n_mem_addr_cells, n_mem_size_cells, len; - const __be32 *memcell_buf; + struct resource res; - memcell_buf = of_get_property(memory, "reg", &len); - if (!memcell_buf || len <= 0) + if (of_address_to_resource(memory, 0, &res)) continue; - n_mem_addr_cells = of_n_addr_cells(memory); - n_mem_size_cells = of_n_size_cells(memory); - - start = of_read_number(memcell_buf, n_mem_addr_cells); - memcell_buf += n_mem_addr_cells; - size = of_read_number(memcell_buf, n_mem_size_cells); - memcell_buf += n_mem_size_cells; - - max_addr = max_t(phys_addr_t, max_addr, start + size); + max_addr = max_t(resource_size_t, max_addr, res.end + 1); } return max_addr; diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c index bbccbe9f2b84..db520c40cb6f 100644 --- a/arch/powerpc/sysdev/tsi108_dev.c +++ b/arch/powerpc/sysdev/tsi108_dev.c @@ -45,9 +45,9 @@ phys_addr_t get_csrbase(void) tsi = of_find_node_by_type(NULL, "tsi-bridge"); if (tsi) { - unsigned int size; - const void *prop = of_get_property(tsi, "reg", &size); - tsi108_csr_base = of_translate_address(tsi, prop); + struct resource res; + of_address_to_resource(tsi, 0, &res); + tsi108_csr_base = res.start; of_node_put(tsi); } return tsi108_csr_base; -- GitLab From ac9c8901cb10aab043bf3599d19eebacfcda2858 Mon Sep 17 00:00:00 2001 From: Nicholas Miehlbradt Date: Tue, 28 Feb 2023 05:43:55 +0000 Subject: [PATCH 1916/5631] powerpc: Implement arch_within_stack_frames Walks the stack when copy_{to,from}_user address is in the stack to ensure that the object being copied is entirely a single stack frame and does not contain stack metadata. Substantially similar to the x86 implementation. The back chain is used to traverse the stack and identify stack frame boundaries. Signed-off-by: Nicholas Miehlbradt Signed-off-by: Michael Ellerman Link: https://msgid.link/20230228054355.300628-1-nicholas@linux.ibm.com --- arch/powerpc/Kconfig | 1 + arch/powerpc/include/asm/ppc_asm.h | 8 ++++++ arch/powerpc/include/asm/thread_info.h | 38 ++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 47017975fc2b..fc4e81dafca7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -200,6 +200,7 @@ config PPC select HAVE_ARCH_KCSAN if PPC_BOOK3S_64 select HAVE_ARCH_KFENCE if ARCH_SUPPORTS_DEBUG_PAGEALLOC select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET + select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index d2f44612f4b0..1f1a64b780e3 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -837,4 +837,12 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define BTB_FLUSH(reg) #endif /* CONFIG_PPC_E500 */ +#if defined(CONFIG_PPC64_ELF_ABI_V1) +#define STACK_FRAME_PARAMS 48 +#elif defined(CONFIG_PPC64_ELF_ABI_V2) +#define STACK_FRAME_PARAMS 32 +#elif defined(CONFIG_PPC32) +#define STACK_FRAME_PARAMS 8 +#endif + #endif /* _ASM_POWERPC_PPC_ASM_H */ diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index af58f1ed3952..cf13d84c4eb9 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -45,6 +45,7 @@ #include #include #include +#include #define SLB_PRELOAD_NR 16U /* @@ -186,6 +187,43 @@ static inline bool test_thread_local_flags(unsigned int flags) #define is_elf2_task() (0) #endif +/* + * Walks up the stack frames to make sure that the specified object is + * entirely contained by a single stack frame. + * + * Returns: + * GOOD_FRAME if within a frame + * BAD_STACK if placed across a frame boundary (or outside stack) + */ +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + const void *params; + const void *frame; + + params = *(const void * const *)current_stack_pointer + STACK_FRAME_PARAMS; + frame = **(const void * const * const *)current_stack_pointer; + + /* + * low -----------------------------------------------------------> high + * [backchain][metadata][params][local vars][saved registers][backchain] + * ^------------------------------------^ + * | allows copies only in this region | + * | | + * params frame + * The metadata region contains the saved LR, CR etc. + */ + while (stack <= frame && frame < stackend) { + if (obj + len <= frame) + return obj >= params ? GOOD_FRAME : BAD_STACK; + params = frame + STACK_FRAME_PARAMS; + frame = *(const void * const *)frame; + } + + return BAD_STACK; +} + #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ -- GitLab From b0bbe5a2915201e3231e788d716d39dc54493b03 Mon Sep 17 00:00:00 2001 From: "Nysal Jan K.A" Date: Fri, 24 Feb 2023 16:09:40 +0530 Subject: [PATCH 1917/5631] powerpc/atomics: Remove unused function Remove arch_atomic_try_cmpxchg_lock function as it is no longer used since commit 9f61521c7a28 ("powerpc/qspinlock: powerpc qspinlock implementation") Signed-off-by: Nysal Jan K.A Reviewed-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230224103940.1328725-1-nysal@linux.ibm.com --- arch/powerpc/include/asm/atomic.h | 29 ----------------------------- 1 file changed, 29 deletions(-) diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 486ab7889121..b3a53830446b 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -130,35 +130,6 @@ ATOMIC_OPS(xor, xor, "", K) #define arch_atomic_xchg_relaxed(v, new) \ arch_xchg_relaxed(&((v)->counter), (new)) -/* - * Don't want to override the generic atomic_try_cmpxchg_acquire, because - * we add a lock hint to the lwarx, which may not be wanted for the - * _acquire case (and is not used by the other _acquire variants so it - * would be a surprise). - */ -static __always_inline bool -arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new) -{ - int r, o = *old; - unsigned int eh = IS_ENABLED(CONFIG_PPC64); - - __asm__ __volatile__ ( -"1: lwarx %0,0,%2,%[eh] # atomic_try_cmpxchg_acquire \n" -" cmpw 0,%0,%3 \n" -" bne- 2f \n" -" stwcx. %4,0,%2 \n" -" bne- 1b \n" -"\t" PPC_ACQUIRE_BARRIER " \n" -"2: \n" - : "=&r" (r), "+m" (v->counter) - : "r" (&v->counter), "r" (o), "r" (new), [eh] "n" (eh) - : "cr0", "memory"); - - if (unlikely(r != o)) - *old = r; - return likely(r == o); -} - /** * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t -- GitLab From 46d21ec067490ab9cdcc89b9de5aae28786a8b8e Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Thu, 16 Mar 2023 14:35:57 +0100 Subject: [PATCH 1918/5631] perf report: Append inlines to non-DWARF callchains Append information about inlined functions to FP and LBR callchains from DWARF debuginfo when available. Do so by calling append_inlines() from add_callchain_ip(). Testing it: Frame-pointer mode recorded with 'perf record --call-graph=fp --freq=max -- ./a.out' #include #include static __attribute__((noinline)) uint32_t func5(uint32_t i) { return i + 10; } static uint32_t func4(uint32_t i) { return func5(i + 5); } static inline uint32_t func3(uint32_t i) { return func4(i + 4); } static __attribute__((noinline)) uint32_t func2(uint32_t i) { return func3(i + 3); } static uint32_t func1(uint32_t i) { return func2(i + 2); } __attribute__((noinline)) uint64_t entry(void) { uint64_t ret = 0; uint32_t i = 0; for (i = 0; i < 1000000; i++) { ret += func1(i); ret -= func2(i); ret += func3(i); ret += func4(i); ret -= func5(i); } return ret; } int main(int argc, char **argv) { printf("%s\n", __func__); return entry(); } ====== Here is the output I get with '--call-graph callee --no-children' ====== # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 250 of event 'cycles:u' # Event count (approx.): 26819859 # # Overhead Command Shared Object Symbol # ........ ....... .................... ..................................... # 43.58% a.out a.out [.] func5 | |--28.93%--entry | main | __libc_start_call_main | --14.65%--func4 (inlined) | |--10.45%--entry | main | __libc_start_call_main | --4.20%--func3 (inlined) entry main __libc_start_call_main 38.80% a.out a.out [.] entry | |--23.27%--func4 (inlined) | | | |--20.28%--func3 (inlined) | | func2 | | main | | __libc_start_call_main | | | --2.99%--entry | main | __libc_start_call_main | |--8.17%--func5 | main | __libc_start_call_main | |--3.89%--func1 (inlined) | entry | main | __libc_start_call_main | --3.48%--entry main __libc_start_call_main 13.07% a.out a.out [.] func2 | ---func5 main __libc_start_call_main 1.54% a.out [unknown] [k] 0xffffffff81e011b7 1.16% a.out [unknown] [k] 0xffffffff81e00193 | --0.57%--__mmap64 (inlined) __mmap64 (inlined) 0.34% a.out ld-linux-x86-64.so.2 [.] __tunable_get_val 0.34% a.out ld-linux-x86-64.so.2 [.] strcmp 0.32% a.out libc.so.6 [.] strchr 0.31% a.out ld-linux-x86-64.so.2 [.] _dl_relocate_object 0.22% a.out ld-linux-x86-64.so.2 [.] _dl_init_paths 0.18% a.out ld-linux-x86-64.so.2 [.] get_common_cache_info.constprop.0 0.14% a.out ld-linux-x86-64.so.2 [.] __GI___tunables_init # # (Tip: Show individual samples with: perf script) # ====== It does not seem to be out of order, or at least it is consistent with what I get with dwarf unwinders. Committer notes: Adrian Hunter pointed out that this breaks --branch-history, so don't do it for branches, see the second Link below. Suggested-by: Andrii Nakryiko Signed-off-by: Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Milian Wolff Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230316133557.868731-2-asavkov@redhat.com Link: https://lore.kernel.org/r/54129783-2960-84e1-05e9-97ac70ffb432@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 803c9d1803dd..3182815c73c6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -44,6 +44,7 @@ #include static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock); +static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip); static struct dso *machine__kernel_dso(struct machine *machine) { @@ -2322,6 +2323,10 @@ static int add_callchain_ip(struct thread *thread, ms.maps = al.maps; ms.map = al.map; ms.sym = al.sym; + + if (!branch && append_inlines(cursor, &ms, ip) == 0) + return 0; + srcline = callchain_srcline(&ms, al.addr); return callchain_cursor_append(cursor, ip, &ms, branch, flags, nr_loop_iter, -- GitLab From 1d7966547e11b1355f88086c26eb2086f6ea4770 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 22 Mar 2023 11:31:08 -0700 Subject: [PATCH 1919/5631] perf build: Add warning for when vmlinux.h generation fails The warning advises on the NO_BPF_SKEL=1 option. Suggested-by: Stephen Rothwell Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230322183108.1380882-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index ed6b6a070f79..48aba186ceb5 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1072,7 +1072,11 @@ VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) ifeq ($(VMLINUX_H),) - $(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@ + $(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@ || \ + (echo "Failure to generate vmlinux.h needed for the recommended BPF skeleton support." && \ + echo "To disable this use the build option NO_BPF_SKEL=1." && \ + echo "Alternatively point at a pre-generated vmlinux.h with VMLINUX_H=." && \ + false) else $(Q)cp "$(VMLINUX_H)" $@ endif -- GitLab From 30df88a80f32ccca5c5cdcf2710d1fb2de5e314d Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 22 Mar 2023 10:47:31 +0100 Subject: [PATCH 1920/5631] perf test: Fix wrong size expectation for 'Setup struct perf_event_attr' The test case "perf test 'Setup struct perf_event_attr'" is failing. On s390 this output is observed: # ./perf test -Fvvvv 17 17: Setup struct perf_event_attr : --- start --- running './tests/attr/test-stat-C0' Using CPUID IBM,8561,703,T01,3.6,002f ..... Event event:base-stat fd = 1 group_fd = -1 flags = 0|8 cpu = * type = 0 size = 128 <<<--- wrong, specified in file base-stat config = 0 sample_period = 0 sample_type = 65536 ... 'PERF_TEST_ATTR=/tmp/tmpgw574wvg ./perf stat -o \ /tmp/tmpgw574wvg/perf.data -e cycles -C 0 kill >/dev/null \ 2>&1 ret '1', expected '1' loading result events Event event-0-0-4 fd = 4 group_fd = -1 cpu = 0 pid = -1 flags = 8 type = 0 size = 136 <<<--- actual size used in system call ..... compare matching [event-0-0-4] to [event:base-stat] [cpu] 0 * [flags] 8 0|8 [type] 0 0 [size] 136 128 ->FAIL match: [event-0-0-4] matches [] expected size=136, got 128 FAILED './tests/attr/test-stat-C0' - match failure This mismatch is caused by commit 09519ec3b19e ("perf: Add perf_event_attr::config3") which enlarges the structure perf_event_attr by 8 bytes. Fix this by adjusting the expected value of size. Output after: # ./perf test -Fvvvv 17 17: Setup struct perf_event_attr : --- start --- running './tests/attr/test-stat-C0' Using CPUID IBM,8561,703,T01,3.6,002f ... matched compare matching [event-0-0-4] to [event:base-stat] [cpu] 0 * [flags] 8 0|8 [type] 0 0 [size] 136 136 .... ->OK match: [event-0-0-4] matches ['event:base-stat'] matched Fixes: 09519ec3b19e4144 ("perf: Add perf_event_attr::config3") Signed-off-by: Thomas Richter Acked-by: Namhyung Kim Cc: Heiko Carstens Cc: Rob Herring Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Cc: Will Deacon Link: https://lore.kernel.org/r/20230322094731.1768281-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/base-record | 2 +- tools/perf/tests/attr/base-stat | 2 +- tools/perf/tests/attr/system-wide-dummy | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 3ef07a12aa14..27c21271a16c 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=128 +size=136 config=0 sample_period=* sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index 408164456530..a21fb65bc012 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=128 +size=136 config=0 sample_period=0 sample_type=65536 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index 8fec06eda5f9..2f3e3eb728eb 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -7,7 +7,7 @@ cpu=* pid=-1 flags=8 type=1 -size=128 +size=136 config=9 sample_period=4000 sample_type=455 -- GitLab From 6094c7744bb0563e833e81d8df8513f9a4e7a257 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 22 Mar 2023 19:50:05 -0700 Subject: [PATCH 1921/5631] perf hist: Improve srcfile sort key performance (really) The earlier commit f0cdde28fecc0d7f ("perf hist: Improve srcfile sort key performance") updated the srcfile logic but missed to change the ->cmp() callback which is called for every sample. It should use the same logic like in the srcline to speed up the processing because it'd return the same information repeatedly for the same address. The real processing will be done in sort__srcfile_collapse(). Fixes: f0cdde28fecc0d7f ("perf hist: Improve srcfile sort key performance") Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230323025005.191239-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index e11e68ecf0a2..2b5cc8e4aa6e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -657,12 +657,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e) static int64_t sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right) { - if (!left->srcfile) - left->srcfile = hist_entry__get_srcfile(left); - if (!right->srcfile) - right->srcfile = hist_entry__get_srcfile(right); - - return strcmp(right->srcfile, left->srcfile); + return sort__srcline_cmp(left, right); } static int64_t -- GitLab From eb2feb68cb7d404288493c41480843bc9f404789 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 23 Mar 2023 13:25:32 +0100 Subject: [PATCH 1922/5631] perf vendor events s390: Remove UTF-8 characters from JSON file Commit 7f76b31130680fb3 ("perf list: Add IBM z16 event description for s390") contains the verbal description for z16 extended counter set. However some entries of the public description contain UTF-8 characters which breaks the build on some distros. Fix this and remove the UTF-8 characters. Fixes: 7f76b31130680fb3 ("perf list: Add IBM z16 event description for s390") Reported-by: Arnaldo Carvalho de Melo Suggested-by: Heiko Carstens Signed-off-by: Thomas Richter Tested-by: Arnaldo Carvalho de Melo Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Thomas Richter Cc: Vasily Gorbik Link: https://lore.kernel.org/r/ZBwkl77/I31AQk12@osiris Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/s390/cf_z16/extended.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/extended.json b/tools/perf/pmu-events/arch/s390/cf_z16/extended.json index c306190fc06f..c2b10ec1c6e0 100644 --- a/tools/perf/pmu-events/arch/s390/cf_z16/extended.json +++ b/tools/perf/pmu-events/arch/s390/cf_z16/extended.json @@ -95,28 +95,28 @@ "EventCode": "145", "EventName": "DCW_REQ", "BriefDescription": "Directory Write Level 1 Data Cache from Cache", - "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestor’s Level-2 cache." + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestors Level-2 cache." }, { "Unit": "CPU-M-CF", "EventCode": "146", "EventName": "DCW_REQ_IV", "BriefDescription": "Directory Write Level 1 Data Cache from Cache with Intervention", - "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestor’s Level-2 cache with intervention." + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestors Level-2 cache with intervention." }, { "Unit": "CPU-M-CF", "EventCode": "147", "EventName": "DCW_REQ_CHIP_HIT", "BriefDescription": "Directory Write Level 1 Data Cache from Cache with Chip HP Hit", - "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestor’s Level-2 cache after using chip level horizontal persistence, Chip-HP hit." + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestors Level-2 cache after using chip level horizontal persistence, Chip-HP hit." }, { "Unit": "CPU-M-CF", "EventCode": "148", "EventName": "DCW_REQ_DRAWER_HIT", "BriefDescription": "Directory Write Level 1 Data Cache from Cache with Drawer HP Hit", - "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestor’s Level-2 cache after using drawer level horizontal persistence, Drawer-HP hit." + "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the requestors Level-2 cache after using drawer level horizontal persistence, Drawer-HP hit." }, { "Unit": "CPU-M-CF", @@ -284,7 +284,7 @@ "EventCode": "172", "EventName": "ICW_REQ_DRAWER_HIT", "BriefDescription": "Directory Write Level 1 Instruction Cache from Cache with Drawer HP Hit", - "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the requestor’s Level-2 cache using drawer level horizontal persistence, Drawer-HP hit." + "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the requestors Level-2 cache using drawer level horizontal persistence, Drawer-HP hit." }, { "Unit": "CPU-M-CF", -- GitLab From 5d8c0f0e11852d22fc3464c82453ddd1286f5d72 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 23 Mar 2023 17:19:22 -0700 Subject: [PATCH 1923/5631] perf lock contention: Fix msan issue in lock_contention_read() I got a report of a msan failure like below: $ sudo perf lock con -ab -- sleep 1 ... ==224416==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x5651160d6c96 in lock_contention_read util/bpf_lock_contention.c:290:8 #1 0x565115f90870 in __cmd_contention builtin-lock.c:1919:3 #2 0x565115f90870 in cmd_lock builtin-lock.c:2385:8 #3 0x565115f03a83 in run_builtin perf.c:330:11 #4 0x565115f03756 in handle_internal_command perf.c:384:8 #5 0x565115f02d53 in run_argv perf.c:428:2 #6 0x565115f02d53 in main perf.c:562:3 #7 0x7f43553bc632 in __libc_start_main #8 0x565115e865a9 in _start It was because the 'key' variable is not initialized. Actually it'd be set by bpf_map_get_next_key() but msan didn't seem to understand it. Let's make msan happy by initializing the variable. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230324001922.937634-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_lock_contention.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 235fc7150545..5927bf0bd92b 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -249,7 +249,7 @@ static const char *lock_contention_get_name(struct lock_contention *con, int lock_contention_read(struct lock_contention *con) { int fd, stack, err = 0; - struct contention_key *prev_key, key; + struct contention_key *prev_key, key = {}; struct contention_data data = {}; struct lock_stat *st = NULL; struct machine *machine = con->machine; -- GitLab From 7803654576db93c49be73ff02d53030558c971b7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:10 -0700 Subject: [PATCH 1924/5631] perf vendor events intel: Broadwell v27 events Description updates and formatting changes. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/broadwell/cache.json | 296 +++++++++--------- .../arch/x86/broadwell/floating-point.json | 7 + .../arch/x86/broadwell/frontend.json | 18 +- .../pmu-events/arch/x86/broadwell/memory.json | 248 +++++++-------- .../arch/x86/broadwell/pipeline.json | 22 +- .../arch/x86/broadwell/uncore-other.json | 2 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 7 files changed, 305 insertions(+), 290 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json index 26199d3ebb25..f8ee5aefccea 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -16,7 +16,7 @@ "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles", + "BriefDescription": "L1D miss outstandings duration in cycles", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", @@ -424,22 +424,22 @@ "UMask": "0x20" }, { - "BriefDescription": "All retired load uops.", + "BriefDescription": "Retired load uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", + "PublicDescription": "Counts all retired load uops. This event accounts for SW prefetch uops of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "All retired store uops.", + "BriefDescription": "Retired store uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1", - "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", + "PublicDescription": "Counts all retired store uops.", "SampleAfterValue": "2000003", "UMask": "0x82" }, @@ -511,10 +511,10 @@ "UMask": "0x80" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "This event counts both cacheable and noncachaeble code read requests.", + "PublicDescription": "This event counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, @@ -629,7 +629,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010091", + "MSRValue": "0x10091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -656,7 +656,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0091", + "MSRValue": "0x4003C0091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -665,7 +665,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0091", + "MSRValue": "0x2003C0091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -674,7 +674,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0091", + "MSRValue": "0x803C0091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -683,7 +683,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0091", + "MSRValue": "0x1003C0091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -710,7 +710,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020091", + "MSRValue": "0x400020091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -719,7 +719,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020091", + "MSRValue": "0x200020091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -728,7 +728,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020091", + "MSRValue": "0x80020091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -737,7 +737,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020091", + "MSRValue": "0x100020091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -746,7 +746,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010240", + "MSRValue": "0x10240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -773,7 +773,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0240", + "MSRValue": "0x4003C0240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -782,7 +782,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0240", + "MSRValue": "0x2003C0240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -791,7 +791,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0240", + "MSRValue": "0x803C0240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -800,7 +800,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0240", + "MSRValue": "0x1003C0240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -827,7 +827,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020240", + "MSRValue": "0x400020240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -836,7 +836,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020240", + "MSRValue": "0x200020240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -845,7 +845,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020240", + "MSRValue": "0x80020240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -854,7 +854,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020240", + "MSRValue": "0x100020240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -863,7 +863,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010090", + "MSRValue": "0x10090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -890,7 +890,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0090", + "MSRValue": "0x4003C0090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -899,7 +899,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0090", + "MSRValue": "0x2003C0090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -908,7 +908,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0090", + "MSRValue": "0x803C0090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -917,7 +917,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0090", + "MSRValue": "0x1003C0090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -944,7 +944,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020090", + "MSRValue": "0x400020090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -953,7 +953,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020090", + "MSRValue": "0x200020090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -962,7 +962,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020090", + "MSRValue": "0x80020090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -971,7 +971,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020090", + "MSRValue": "0x100020090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -980,7 +980,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010120", + "MSRValue": "0x10120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1007,7 +1007,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0120", + "MSRValue": "0x4003C0120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1016,7 +1016,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0120", + "MSRValue": "0x2003C0120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1025,7 +1025,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0120", + "MSRValue": "0x803C0120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1034,7 +1034,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0120", + "MSRValue": "0x1003C0120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1061,7 +1061,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020120", + "MSRValue": "0x400020120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1070,7 +1070,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020120", + "MSRValue": "0x200020120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1079,7 +1079,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020120", + "MSRValue": "0x80020120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1088,7 +1088,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020120", + "MSRValue": "0x100020120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1097,7 +1097,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010122", + "MSRValue": "0x10122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1124,7 +1124,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0122", + "MSRValue": "0x4003C0122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1133,7 +1133,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0122", + "MSRValue": "0x2003C0122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1142,7 +1142,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0122", + "MSRValue": "0x803C0122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1151,7 +1151,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0122", + "MSRValue": "0x1003C0122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1178,7 +1178,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020122", + "MSRValue": "0x400020122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1187,7 +1187,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020122", + "MSRValue": "0x200020122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1196,7 +1196,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020122", + "MSRValue": "0x80020122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1205,7 +1205,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020122", + "MSRValue": "0x100020122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1214,7 +1214,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010008", + "MSRValue": "0x10008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1241,7 +1241,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0008", + "MSRValue": "0x4003C0008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1250,7 +1250,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0008", + "MSRValue": "0x2003C0008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1259,7 +1259,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0008", + "MSRValue": "0x803C0008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1268,7 +1268,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0008", + "MSRValue": "0x1003C0008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1295,7 +1295,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020008", + "MSRValue": "0x400020008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1304,7 +1304,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020008", + "MSRValue": "0x200020008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1313,7 +1313,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020008", + "MSRValue": "0x80020008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1322,7 +1322,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020008", + "MSRValue": "0x100020008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1331,7 +1331,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010004", + "MSRValue": "0x10004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1358,7 +1358,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0004", + "MSRValue": "0x4003C0004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1367,7 +1367,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0004", + "MSRValue": "0x2003C0004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1376,7 +1376,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0004", + "MSRValue": "0x803C0004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1385,7 +1385,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0004", + "MSRValue": "0x1003C0004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1412,7 +1412,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020004", + "MSRValue": "0x400020004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1421,7 +1421,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020004", + "MSRValue": "0x200020004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1430,7 +1430,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020004", + "MSRValue": "0x80020004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1439,7 +1439,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020004", + "MSRValue": "0x100020004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1448,7 +1448,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010001", + "MSRValue": "0x10001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1475,7 +1475,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0001", + "MSRValue": "0x4003C0001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1484,7 +1484,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0001", + "MSRValue": "0x2003C0001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1493,7 +1493,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0001", + "MSRValue": "0x803C0001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1502,7 +1502,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0001", + "MSRValue": "0x1003C0001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1529,7 +1529,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020001", + "MSRValue": "0x400020001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1538,7 +1538,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020001", + "MSRValue": "0x200020001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1547,7 +1547,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020001", + "MSRValue": "0x80020001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1556,7 +1556,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020001", + "MSRValue": "0x100020001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1565,7 +1565,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010002", + "MSRValue": "0x10002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1592,7 +1592,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0002", + "MSRValue": "0x4003C0002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1601,7 +1601,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0002", + "MSRValue": "0x2003C0002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1610,7 +1610,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0002", + "MSRValue": "0x803C0002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1619,7 +1619,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0002", + "MSRValue": "0x1003C0002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1628,7 +1628,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000018000", + "MSRValue": "0x18000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1655,7 +1655,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C8000", + "MSRValue": "0x4003C8000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1664,7 +1664,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C8000", + "MSRValue": "0x2003C8000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1673,7 +1673,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C8000", + "MSRValue": "0x803C8000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1682,7 +1682,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C8000", + "MSRValue": "0x1003C8000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1709,7 +1709,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400028000", + "MSRValue": "0x400028000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1718,7 +1718,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200028000", + "MSRValue": "0x200028000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1727,7 +1727,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080028000", + "MSRValue": "0x80028000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1736,7 +1736,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100028000", + "MSRValue": "0x100028000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1745,7 +1745,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010040", + "MSRValue": "0x10040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1772,7 +1772,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0040", + "MSRValue": "0x4003C0040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1781,7 +1781,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0040", + "MSRValue": "0x2003C0040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1790,7 +1790,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0040", + "MSRValue": "0x803C0040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1799,7 +1799,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0040", + "MSRValue": "0x1003C0040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1826,7 +1826,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020040", + "MSRValue": "0x400020040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1835,7 +1835,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020040", + "MSRValue": "0x200020040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1844,7 +1844,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020040", + "MSRValue": "0x80020040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1853,7 +1853,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020040", + "MSRValue": "0x100020040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1862,7 +1862,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010010", + "MSRValue": "0x10010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1889,7 +1889,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0010", + "MSRValue": "0x4003C0010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1898,7 +1898,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0010", + "MSRValue": "0x2003C0010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1907,7 +1907,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0010", + "MSRValue": "0x803C0010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1916,7 +1916,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0010", + "MSRValue": "0x1003C0010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1943,7 +1943,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020010", + "MSRValue": "0x400020010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1952,7 +1952,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020010", + "MSRValue": "0x200020010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1961,7 +1961,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020010", + "MSRValue": "0x80020010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1970,7 +1970,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020010", + "MSRValue": "0x100020010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1979,7 +1979,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010020", + "MSRValue": "0x10020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2006,7 +2006,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0020", + "MSRValue": "0x4003C0020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2015,7 +2015,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0020", + "MSRValue": "0x2003C0020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2024,7 +2024,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0020", + "MSRValue": "0x803C0020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2033,7 +2033,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0020", + "MSRValue": "0x1003C0020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2060,7 +2060,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020020", + "MSRValue": "0x400020020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2069,7 +2069,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020020", + "MSRValue": "0x200020020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2078,7 +2078,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020020", + "MSRValue": "0x80020020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2087,7 +2087,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020020", + "MSRValue": "0x100020020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2096,7 +2096,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010200", + "MSRValue": "0x10200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2123,7 +2123,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0200", + "MSRValue": "0x4003C0200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2132,7 +2132,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0200", + "MSRValue": "0x2003C0200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2141,7 +2141,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0200", + "MSRValue": "0x803C0200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2150,7 +2150,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0200", + "MSRValue": "0x1003C0200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2177,7 +2177,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020200", + "MSRValue": "0x400020200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2186,7 +2186,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020200", + "MSRValue": "0x200020200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2195,7 +2195,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020200", + "MSRValue": "0x80020200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2204,7 +2204,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020200", + "MSRValue": "0x100020200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2213,7 +2213,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010080", + "MSRValue": "0x10080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2240,7 +2240,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0080", + "MSRValue": "0x4003C0080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2249,7 +2249,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0080", + "MSRValue": "0x2003C0080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2258,7 +2258,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0080", + "MSRValue": "0x803C0080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2267,7 +2267,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0080", + "MSRValue": "0x1003C0080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2294,7 +2294,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020080", + "MSRValue": "0x400020080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2303,7 +2303,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020080", + "MSRValue": "0x200020080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2312,7 +2312,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020080", + "MSRValue": "0x80020080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2321,7 +2321,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020080", + "MSRValue": "0x100020080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2330,7 +2330,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010100", + "MSRValue": "0x10100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2357,7 +2357,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0100", + "MSRValue": "0x4003C0100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2366,7 +2366,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x02003C0100", + "MSRValue": "0x2003C0100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2375,7 +2375,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00803C0100", + "MSRValue": "0x803C0100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2384,7 +2384,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0100", + "MSRValue": "0x1003C0100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2411,7 +2411,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0400020100", + "MSRValue": "0x400020100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2420,7 +2420,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0200020100", + "MSRValue": "0x200020100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2429,7 +2429,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0080020100", + "MSRValue": "0x80020100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -2438,7 +2438,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0100020100", + "MSRValue": "0x100020100", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json index 0de16d9a80da..e4826dc7f797 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json @@ -3,6 +3,7 @@ "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -10,6 +11,7 @@ "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x8" }, @@ -17,6 +19,7 @@ "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x10" }, @@ -24,6 +27,7 @@ "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -45,6 +49,7 @@ "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation operation. Applies to SSE* and AVX* scalar double and single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x3" }, @@ -52,6 +57,7 @@ "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -59,6 +65,7 @@ "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json index d0f6678609ae..bd5da39564e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json @@ -125,16 +125,16 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -143,7 +143,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -153,7 +153,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", @@ -161,10 +161,10 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.", + "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -178,10 +178,10 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json index 394ed602fcb1..ac7cdb831960 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json @@ -206,7 +206,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000091", + "MSRValue": "0x43C000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -215,7 +215,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000091", + "MSRValue": "0x23C000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -224,7 +224,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000091", + "MSRValue": "0xBC000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -233,7 +233,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000091", + "MSRValue": "0x13C000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -260,7 +260,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000091", + "MSRValue": "0x404000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -269,7 +269,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000091", + "MSRValue": "0x204000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -278,7 +278,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000091", + "MSRValue": "0x84000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -296,7 +296,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000091", + "MSRValue": "0x104000091", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -323,7 +323,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000240", + "MSRValue": "0x43C000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -332,7 +332,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000240", + "MSRValue": "0x23C000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -341,7 +341,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000240", + "MSRValue": "0xBC000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -350,7 +350,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000240", + "MSRValue": "0x13C000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -377,7 +377,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000240", + "MSRValue": "0x404000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -386,7 +386,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000240", + "MSRValue": "0x204000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -395,7 +395,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000240", + "MSRValue": "0x84000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -413,7 +413,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000240", + "MSRValue": "0x104000240", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -440,7 +440,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000090", + "MSRValue": "0x43C000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -449,7 +449,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000090", + "MSRValue": "0x23C000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -458,7 +458,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000090", + "MSRValue": "0xBC000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -467,7 +467,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000090", + "MSRValue": "0x13C000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -494,7 +494,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000090", + "MSRValue": "0x404000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -503,7 +503,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000090", + "MSRValue": "0x204000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -512,7 +512,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000090", + "MSRValue": "0x84000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -530,7 +530,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000090", + "MSRValue": "0x104000090", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -557,7 +557,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000120", + "MSRValue": "0x43C000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -566,7 +566,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000120", + "MSRValue": "0x23C000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -575,7 +575,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000120", + "MSRValue": "0xBC000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -584,7 +584,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000120", + "MSRValue": "0x13C000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -611,7 +611,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000120", + "MSRValue": "0x404000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -620,7 +620,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000120", + "MSRValue": "0x204000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -629,7 +629,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000120", + "MSRValue": "0x84000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -647,7 +647,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000120", + "MSRValue": "0x104000120", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -674,7 +674,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000122", + "MSRValue": "0x43C000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -683,7 +683,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000122", + "MSRValue": "0x23C000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -692,7 +692,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000122", + "MSRValue": "0xBC000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -701,7 +701,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000122", + "MSRValue": "0x13C000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -728,7 +728,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000122", + "MSRValue": "0x404000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -737,7 +737,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000122", + "MSRValue": "0x204000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -746,7 +746,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000122", + "MSRValue": "0x84000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -764,7 +764,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000122", + "MSRValue": "0x104000122", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -791,7 +791,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000008", + "MSRValue": "0x43C000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -800,7 +800,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000008", + "MSRValue": "0x23C000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -809,7 +809,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000008", + "MSRValue": "0xBC000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -818,7 +818,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000008", + "MSRValue": "0x13C000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -845,7 +845,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000008", + "MSRValue": "0x404000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -854,7 +854,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000008", + "MSRValue": "0x204000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -863,7 +863,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000008", + "MSRValue": "0x84000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -881,7 +881,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000008", + "MSRValue": "0x104000008", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -908,7 +908,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000004", + "MSRValue": "0x43C000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -917,7 +917,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000004", + "MSRValue": "0x23C000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -926,7 +926,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000004", + "MSRValue": "0xBC000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -935,7 +935,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000004", + "MSRValue": "0x13C000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -962,7 +962,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000004", + "MSRValue": "0x404000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -971,7 +971,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000004", + "MSRValue": "0x204000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -980,7 +980,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000004", + "MSRValue": "0x84000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -998,7 +998,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000004", + "MSRValue": "0x104000004", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1025,7 +1025,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000001", + "MSRValue": "0x43C000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1034,7 +1034,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000001", + "MSRValue": "0x23C000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1043,7 +1043,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000001", + "MSRValue": "0xBC000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1052,7 +1052,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000001", + "MSRValue": "0x13C000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1079,7 +1079,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000001", + "MSRValue": "0x404000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1088,7 +1088,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000001", + "MSRValue": "0x204000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1097,7 +1097,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000001", + "MSRValue": "0x84000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1115,7 +1115,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000001", + "MSRValue": "0x104000001", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1142,7 +1142,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000002", + "MSRValue": "0x43C000002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1151,7 +1151,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000002", + "MSRValue": "0x23C000002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1160,7 +1160,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000002", + "MSRValue": "0xBC000002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1169,7 +1169,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000002", + "MSRValue": "0x13C000002", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1196,7 +1196,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C008000", + "MSRValue": "0x43C008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1205,7 +1205,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C008000", + "MSRValue": "0x23C008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1214,7 +1214,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC008000", + "MSRValue": "0xBC008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1223,7 +1223,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C008000", + "MSRValue": "0x13C008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1250,7 +1250,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404008000", + "MSRValue": "0x404008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1259,7 +1259,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204008000", + "MSRValue": "0x204008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1268,7 +1268,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084008000", + "MSRValue": "0x84008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1286,7 +1286,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104008000", + "MSRValue": "0x104008000", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1313,7 +1313,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000040", + "MSRValue": "0x43C000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1322,7 +1322,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000040", + "MSRValue": "0x23C000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1331,7 +1331,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000040", + "MSRValue": "0xBC000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1340,7 +1340,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000040", + "MSRValue": "0x13C000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1367,7 +1367,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000040", + "MSRValue": "0x404000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1376,7 +1376,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000040", + "MSRValue": "0x204000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1385,7 +1385,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000040", + "MSRValue": "0x84000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1403,7 +1403,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000040", + "MSRValue": "0x104000040", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1430,7 +1430,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000010", + "MSRValue": "0x43C000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1439,7 +1439,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000010", + "MSRValue": "0x23C000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1448,7 +1448,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000010", + "MSRValue": "0xBC000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1457,7 +1457,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000010", + "MSRValue": "0x13C000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1484,7 +1484,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000010", + "MSRValue": "0x404000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1493,7 +1493,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000010", + "MSRValue": "0x204000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1502,7 +1502,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000010", + "MSRValue": "0x84000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1520,7 +1520,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000010", + "MSRValue": "0x104000010", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1547,7 +1547,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000020", + "MSRValue": "0x43C000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1556,7 +1556,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000020", + "MSRValue": "0x23C000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1565,7 +1565,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000020", + "MSRValue": "0xBC000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1574,7 +1574,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000020", + "MSRValue": "0x13C000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1601,7 +1601,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000020", + "MSRValue": "0x404000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1610,7 +1610,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000020", + "MSRValue": "0x204000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1619,7 +1619,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000020", + "MSRValue": "0x84000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1637,7 +1637,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000020", + "MSRValue": "0x104000020", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1664,7 +1664,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000200", + "MSRValue": "0x43C000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1673,7 +1673,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000200", + "MSRValue": "0x23C000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1682,7 +1682,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000200", + "MSRValue": "0xBC000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1691,7 +1691,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000200", + "MSRValue": "0x13C000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1718,7 +1718,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000200", + "MSRValue": "0x404000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1727,7 +1727,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000200", + "MSRValue": "0x204000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1736,7 +1736,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000200", + "MSRValue": "0x84000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1754,7 +1754,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000200", + "MSRValue": "0x104000200", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1781,7 +1781,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000080", + "MSRValue": "0x43C000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1790,7 +1790,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000080", + "MSRValue": "0x23C000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1799,7 +1799,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000080", + "MSRValue": "0xBC000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1808,7 +1808,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000080", + "MSRValue": "0x13C000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1835,7 +1835,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000080", + "MSRValue": "0x404000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1844,7 +1844,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000080", + "MSRValue": "0x204000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1853,7 +1853,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000080", + "MSRValue": "0x84000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1871,7 +1871,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000080", + "MSRValue": "0x104000080", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1898,7 +1898,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x043C000100", + "MSRValue": "0x43C000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1907,7 +1907,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x023C000100", + "MSRValue": "0x23C000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1916,7 +1916,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x00BC000100", + "MSRValue": "0xBC000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1925,7 +1925,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x013C000100", + "MSRValue": "0x13C000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1952,7 +1952,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0404000100", + "MSRValue": "0x404000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1961,7 +1961,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0204000100", + "MSRValue": "0x204000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1970,7 +1970,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0084000100", + "MSRValue": "0x84000100", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -1988,7 +1988,7 @@ "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0104000100", + "MSRValue": "0x104000100", "SampleAfterValue": "100003", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json index 2f0fe6b35334..9a902d2160e6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json @@ -214,6 +214,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", "EventCode": "0x89", @@ -500,7 +508,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "EventCode": "0x87", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -909,7 +917,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", + "BriefDescription": "Cycles per core when uops are executed in port 0.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", @@ -925,7 +933,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", + "BriefDescription": "Cycles per core when uops are executed in port 1.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", @@ -973,7 +981,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", + "BriefDescription": "Cycles per core when uops are executed in port 4.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", @@ -989,7 +997,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", + "BriefDescription": "Cycles per core when uops are executed in port 5.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", "SampleAfterValue": "2000003", @@ -1005,7 +1013,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", + "BriefDescription": "Cycles per core when uops are executed in port 6.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", "SampleAfterValue": "2000003", @@ -1097,7 +1105,7 @@ }, { "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", + "CounterMask": "16", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "Invert": "1", diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json index ddcf7faa9d10..368a958a18a0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json @@ -8,7 +8,7 @@ "Unit": "ARB" }, { - "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", "EventCode": "0x80", "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 9abebe50ae0d..70be860bcb53 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -2,7 +2,7 @@ Family-model,Version,Filename,EventType GenuineIntel-6-(97|9A|B7|BA|BF),v1.19,alderlake,core GenuineIntel-6-BE,v1.19,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core -GenuineIntel-6-(3D|47),v26,broadwell,core +GenuineIntel-6-(3D|47),v27,broadwell,core GenuineIntel-6-56,v7,broadwellde,core GenuineIntel-6-4F,v19,broadwellx,core GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core -- GitLab From 8aae803f66aa070fc5062fdaabaeaddb4cf18bf8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:11 -0700 Subject: [PATCH 1925/5631] perf vendor events intel: Broadwellde v9 events Updates descriptions and encodings. Adds BR_MISP_EXEC.INDIRECT events. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwellde/cache.json | 105 +++---- .../arch/x86/broadwellde/floating-point.json | 45 +-- .../arch/x86/broadwellde/frontend.json | 18 +- .../arch/x86/broadwellde/memory.json | 64 +++-- .../arch/x86/broadwellde/pipeline.json | 79 +++--- .../arch/x86/broadwellde/uncore-cache.json | 72 ++--- .../arch/x86/broadwellde/uncore-memory.json | 256 +++++++++++++++++- .../arch/x86/broadwellde/uncore-other.json | 27 +- .../arch/x86/broadwellde/uncore-power.json | 10 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 10 files changed, 495 insertions(+), 183 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json index fcc99fd22b0a..6784331ac1cb 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -16,7 +16,7 @@ "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles", + "BriefDescription": "L1D miss outstandings duration in cycles", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", @@ -139,7 +139,7 @@ "EventCode": "0x24", "EventName": "L2_RQSTS.CODE_RD_HIT", "SampleAfterValue": "200003", - "UMask": "0x44" + "UMask": "0xc4" }, { "BriefDescription": "L2 cache misses when fetching instructions.", @@ -152,9 +152,9 @@ "BriefDescription": "Demand Data Read requests that hit L2 cache", "EventCode": "0x24", "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", - "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.", + "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.", "SampleAfterValue": "200003", - "UMask": "0x41" + "UMask": "0xc1" }, { "BriefDescription": "Demand Data Read miss L2, no rejects", @@ -170,7 +170,7 @@ "EventName": "L2_RQSTS.L2_PF_HIT", "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.", "SampleAfterValue": "200003", - "UMask": "0x50" + "UMask": "0xd0" }, { "BriefDescription": "L2 prefetch requests that miss L2 cache", @@ -199,7 +199,7 @@ "EventCode": "0x24", "EventName": "L2_RQSTS.RFO_HIT", "SampleAfterValue": "200003", - "UMask": "0x42" + "UMask": "0xc2" }, { "BriefDescription": "RFO requests that miss L2 cache.", @@ -297,61 +297,62 @@ "UMask": "0x4f" }, { - "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.", "Data_LA": "1", "Errata": "BDM100", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x2" }, { - "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.", "Data_LA": "1", "Errata": "BDM100", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", + "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).", "SampleAfterValue": "20011", "UMask": "0x4" }, { - "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Data_LA": "1", "Errata": "BDM100", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", + "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.", "SampleAfterValue": "20011", "UMask": "0x1" }, { - "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.", "Data_LA": "1", "Errata": "BDM100", "EventCode": "0xD2", "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "100003", "UMask": "0x8" }, { + "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "Errata": "BDE70, BDM100", "EventCode": "0xD3", "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM", "PEBS": "1", - "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.", + "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).", "SampleAfterValue": "100007", "UMask": "0x1" }, { - "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)", "Data_LA": "1", "Errata": "BDE70", "EventCode": "0xD3", @@ -361,7 +362,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache", "Data_LA": "1", "Errata": "BDE70", "EventCode": "0xD3", @@ -371,7 +372,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)", + "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM", "Data_LA": "1", "Errata": "BDE70", "EventCode": "0xD3", @@ -381,69 +382,69 @@ "UMask": "0x10" }, { - "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.", "Data_LA": "1", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", + "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.", "SampleAfterValue": "100003", "UMask": "0x40" }, { - "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L1 cache hits as data sources.", "Data_LA": "1", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.", + "BriefDescription": "Retired load uops misses in L1 cache as data sources.", "Data_LA": "1", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "100003", "UMask": "0x8" }, { - "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with L2 cache hits as data sources.", "Data_LA": "1", "Errata": "BDM35", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.", + "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.", "SampleAfterValue": "100003", "UMask": "0x2" }, { - "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.", + "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.", "Data_LA": "1", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", + "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.", "SampleAfterValue": "50021", "UMask": "0x10" }, { - "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.", "Data_LA": "1", "Errata": "BDM100", "EventCode": "0xD1", "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", + "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.", "SampleAfterValue": "50021", "UMask": "0x4" }, { - "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).", + "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.", "Data_LA": "1", "Errata": "BDM100, BDE70", "EventCode": "0xD1", @@ -453,73 +454,73 @@ "UMask": "0x20" }, { - "BriefDescription": "All retired load uops. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", + "PublicDescription": "Counts all retired load uops. This event accounts for SW prefetch uops of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", + "PublicDescription": "Counts all retired store uops.", "SampleAfterValue": "2000003", "UMask": "0x82" }, { - "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops with locked access.", "Data_LA": "1", "Errata": "BDM35", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.", + "PublicDescription": "This event counts load uops with locked access retired to the architected path.", "SampleAfterValue": "100007", "UMask": "0x21" }, { - "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)", + "BriefDescription": "Retired load uops that split across a cacheline boundary.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "UMask": "0x41" }, { - "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that split across a cacheline boundary.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", + "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).", "SampleAfterValue": "100003", "UMask": "0x42" }, { - "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired load uops that miss the STLB.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x11" }, { - "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)", + "BriefDescription": "Retired store uops that miss the STLB.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", + "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.", "SampleAfterValue": "100003", "UMask": "0x12" }, @@ -532,10 +533,18 @@ "UMask": "0x8" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Any memory transaction that reached the SQ.", + "EventCode": "0xb0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "This event counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, and so on.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "This event counts both cacheable and noncachaeble code read requests.", + "PublicDescription": "This event counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json index 0b3f026158e2..e4826dc7f797 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json @@ -1,70 +1,77 @@ [ { - "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired. Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x4" }, { - "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x8" }, { - "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired. Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 4 calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired. Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x20" }, { - "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.DOUBLE", "SampleAfterValue": "2000006", "UMask": "0x15" }, { - "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* packed double and single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.PACKED", "SampleAfterValue": "2000004", "UMask": "0x3c" }, { - "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation operation. Applies to SSE* and AVX* scalar double and single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x3" }, { - "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired. Each count represents 1 computation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", "SampleAfterValue": "2000003", "UMask": "0x2" }, { - "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.", - "EventCode": "0xC7", + "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", "EventName": "FP_ARITH_INST_RETIRED.SINGLE", "SampleAfterValue": "2000005", "UMask": "0x2a" diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json index d0f6678609ae..bd5da39564e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/frontend.json @@ -125,16 +125,16 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -143,7 +143,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -153,7 +153,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", @@ -161,10 +161,10 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.", + "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -178,10 +178,10 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json index 12cc384d7f18..041b6ff4062e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/memory.json @@ -1,10 +1,10 @@ [ { - "BriefDescription": "Number of times HLE abort was triggered (PEBS)", + "BriefDescription": "Number of times HLE abort was triggered", "EventCode": "0xc8", "EventName": "HLE_RETIRED.ABORTED", "PEBS": "1", - "PublicDescription": "Number of times HLE abort was triggered (PEBS).", + "PublicDescription": "Number of times HLE abort was triggered.", "SampleAfterValue": "2000003", "UMask": "0x4" }, @@ -73,98 +73,106 @@ "UMask": "0x2" }, { - "BriefDescription": "Loads with latency value being above 128", + "BriefDescription": "Randomly selected loads with latency value being above 128", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", "MSRIndex": "0x3F6", "MSRValue": "0x80", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 128.", + "PublicDescription": "Counts randomly selected loads with latency value being above 128.", "SampleAfterValue": "1009", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 16", + "BriefDescription": "Randomly selected loads with latency value being above 16", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", "MSRIndex": "0x3F6", "MSRValue": "0x10", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 16.", + "PublicDescription": "Counts randomly selected loads with latency value being above 16.", "SampleAfterValue": "20011", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 256", + "BriefDescription": "Randomly selected loads with latency value being above 256", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", "MSRIndex": "0x3F6", "MSRValue": "0x100", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 256.", + "PublicDescription": "Counts randomly selected loads with latency value being above 256.", "SampleAfterValue": "503", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 32", + "BriefDescription": "Randomly selected loads with latency value being above 32", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", "MSRIndex": "0x3F6", "MSRValue": "0x20", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 32.", + "PublicDescription": "Counts randomly selected loads with latency value being above 32.", "SampleAfterValue": "100007", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 4", + "BriefDescription": "Randomly selected loads with latency value being above 4", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", "MSRIndex": "0x3F6", "MSRValue": "0x4", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above four.", + "PublicDescription": "Counts randomly selected loads with latency value being above four.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 512", + "BriefDescription": "Randomly selected loads with latency value being above 512", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", "MSRIndex": "0x3F6", "MSRValue": "0x200", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 512.", + "PublicDescription": "Counts randomly selected loads with latency value being above 512.", "SampleAfterValue": "101", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 64", + "BriefDescription": "Randomly selected loads with latency value being above 64", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", "MSRIndex": "0x3F6", "MSRValue": "0x40", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above 64.", + "PublicDescription": "Counts randomly selected loads with latency value being above 64.", "SampleAfterValue": "2003", "UMask": "0x1" }, { - "BriefDescription": "Loads with latency value being above 8", + "BriefDescription": "Randomly selected loads with latency value being above 8", + "Data_LA": "1", "Errata": "BDM100, BDM35", - "EventCode": "0xCD", + "EventCode": "0xcd", "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", "MSRIndex": "0x3F6", "MSRValue": "0x8", "PEBS": "2", - "PublicDescription": "This event counts loads with latency value being above eight.", + "PublicDescription": "Counts randomly selected loads with latency value being above eight.", "SampleAfterValue": "50021", "UMask": "0x1" }, @@ -185,11 +193,11 @@ "UMask": "0x2" }, { - "BriefDescription": "Number of times RTM abort was triggered (PEBS)", + "BriefDescription": "Number of times RTM abort was triggered", "EventCode": "0xc9", "EventName": "RTM_RETIRED.ABORTED", "PEBS": "1", - "PublicDescription": "Number of times RTM abort was triggered (PEBS).", + "PublicDescription": "Number of times RTM abort was triggered .", "SampleAfterValue": "2000003", "UMask": "0x4" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json index 9e7d66b07f01..9a902d2160e6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json @@ -129,11 +129,11 @@ "UMask": "0x4" }, { - "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Conditional branch instructions retired.", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.CONDITIONAL", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.", + "PublicDescription": "This event counts conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" }, @@ -147,38 +147,38 @@ "UMask": "0x40" }, { - "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect near call instructions retired.", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_CALL", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", "SampleAfterValue": "100007", "UMask": "0x2" }, { - "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)", + "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_CALL_R3", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).", + "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).", "SampleAfterValue": "100007", "UMask": "0x2" }, { - "BriefDescription": "Return instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Return instructions retired.", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_RETURN", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.", + "PublicDescription": "This event counts return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" }, { - "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Taken branch instructions retired.", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.", + "PublicDescription": "This event counts taken branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x20" }, @@ -214,6 +214,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", "EventCode": "0x89", @@ -270,29 +278,29 @@ "UMask": "0x4" }, { - "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)", + "BriefDescription": "Mispredicted conditional branch instructions retired.", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.CONDITIONAL", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", "SampleAfterValue": "400009", "UMask": "0x1" }, { - "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", "PEBS": "1", - "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).", + "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.", "SampleAfterValue": "400009", "UMask": "0x20" }, { - "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)", + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.RET", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.", + "PublicDescription": "This event counts mispredicted return instructions retired.", "SampleAfterValue": "100007", "UMask": "0x8" }, @@ -300,7 +308,7 @@ "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", "EventCode": "0x3c", "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x2" }, { @@ -308,7 +316,7 @@ "EventCode": "0x3C", "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", "PublicDescription": "This is a fixed-frequency event programmed to general counters. It counts when the core is unhalted at 100 Mhz.", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x1" }, { @@ -316,14 +324,14 @@ "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "EventCode": "0x3C", "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x1" }, { "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.", "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x2" }, { @@ -338,7 +346,7 @@ "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.REF_XCLK", "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x1" }, { @@ -346,7 +354,7 @@ "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).", "EventCode": "0x3C", "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "2000003", + "SampleAfterValue": "100003", "UMask": "0x1" }, { @@ -500,7 +508,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "EventCode": "0x87", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -681,9 +689,9 @@ }, { "BriefDescription": "Resource-related stall cycles", - "EventCode": "0xA2", + "EventCode": "0xa2", "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.", + "PublicDescription": "This event counts resource-related stall cycles.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -909,7 +917,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", + "BriefDescription": "Cycles per core when uops are executed in port 0.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", @@ -925,7 +933,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", + "BriefDescription": "Cycles per core when uops are executed in port 1.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", @@ -973,7 +981,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", + "BriefDescription": "Cycles per core when uops are executed in port 4.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", @@ -989,7 +997,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", + "BriefDescription": "Cycles per core when uops are executed in port 5.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", "SampleAfterValue": "2000003", @@ -1005,7 +1013,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", + "BriefDescription": "Cycles per core when uops are executed in port 6.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", "SampleAfterValue": "2000003", @@ -1068,21 +1076,20 @@ "UMask": "0x1" }, { - "BriefDescription": "Actually retired uops. (Precise Event - PEBS)", - "Data_LA": "1", + "BriefDescription": "Actually retired uops.", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.ALL", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", + "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Retirement slots used. (Precise Event - PEBS)", + "BriefDescription": "Retirement slots used.", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.RETIRE_SLOTS", "PEBS": "1", - "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.", + "PublicDescription": "This event counts the number of retirement slots used.", "SampleAfterValue": "2000003", "UMask": "0x2" }, @@ -1098,7 +1105,7 @@ }, { "BriefDescription": "Cycles with less than 10 actually retired uops.", - "CounterMask": "10", + "CounterMask": "16", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.TOTAL_CYCLES", "Invert": "1", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json index b8c9845308b2..2bf23ef7bfac 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -78,7 +78,7 @@ "EventCode": "0x34", "EventName": "UNC_C_LLC_LOOKUP.WRITE", "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cachable and UC.", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", "Unit": "CBO" }, @@ -968,7 +968,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", "Unit": "CBO" }, @@ -977,7 +977,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", "Unit": "CBO" }, @@ -986,7 +986,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", "Unit": "CBO" }, @@ -995,7 +995,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", "Unit": "CBO" }, @@ -1004,7 +1004,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", "Unit": "CBO" }, @@ -1013,7 +1013,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", "Unit": "CBO" }, @@ -1022,7 +1022,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", "Unit": "CBO" }, @@ -1031,7 +1031,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", "Unit": "CBO" }, @@ -1040,7 +1040,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", "Unit": "CBO" }, @@ -1049,7 +1049,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", "Unit": "CBO" }, @@ -1058,7 +1058,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", "Unit": "CBO" }, @@ -1067,7 +1067,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", "Unit": "CBO" }, @@ -1076,7 +1076,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", "Unit": "CBO" }, @@ -1085,7 +1085,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", "Unit": "CBO" }, @@ -1094,7 +1094,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", "Unit": "CBO" }, @@ -1103,7 +1103,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", "Unit": "CBO" }, @@ -1112,7 +1112,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", "Unit": "CBO" }, @@ -1121,7 +1121,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", "Unit": "CBO" }, @@ -1130,7 +1130,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", "Unit": "CBO" }, @@ -1166,7 +1166,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisifed by an opcode, in the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", "Unit": "CBO" }, @@ -1193,7 +1193,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisifed by an opcode, in the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", "Unit": "CBO" }, @@ -1220,7 +1220,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisifed by an opcode, in the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", "Unit": "CBO" }, @@ -1301,7 +1301,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisifed by an opcode, in the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", "Unit": "CBO" }, @@ -1388,7 +1388,7 @@ "EventCode": "0x2", "EventName": "UNC_C_TxR_INSERTS.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transfering writeback data to the cache.", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", "Unit": "CBO" }, @@ -1535,7 +1535,7 @@ "EventCode": "0x41", "EventName": "UNC_H_DIRECTORY_LAT_OPT", "PerPkg": "1", - "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory retuned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", + "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory returned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", "Unit": "HA" }, { @@ -2647,7 +2647,7 @@ "EventCode": "0x21", "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", "PerPkg": "1", - "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currentl copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", "UMask": "0x8", "Unit": "HA" }, @@ -2719,7 +2719,7 @@ "EventCode": "0x60", "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPSFWD", "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currentl copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", "UMask": "0x8", "Unit": "HA" }, @@ -2931,7 +2931,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_LOCAL", "PerPkg": "1", @@ -2940,7 +2940,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_REMOTE", "PerPkg": "1", @@ -2949,7 +2949,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_LOCAL", "PerPkg": "1", @@ -2958,7 +2958,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_REMOTE", "PerPkg": "1", @@ -2967,7 +2967,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_LOCAL", "PerPkg": "1", @@ -2976,7 +2976,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_REMOTE", "PerPkg": "1", @@ -2985,7 +2985,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Local Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Local Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.LOCAL", "PerPkg": "1", @@ -2994,7 +2994,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Remote Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Remote Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.REMOTE", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json index c3f2f6c2ac74..a764234a3584 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json @@ -166,7 +166,7 @@ "EventCode": "0x9", "EventName": "UNC_M_ECC_CORRECTABLE_ERRORS", "PerPkg": "1", - "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit erros in lockstep mode.", + "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit errors in lockstep mode.", "Unit": "iMC" }, { @@ -302,6 +302,7 @@ "Unit": "iMC" }, { + "BriefDescription": "UNC_M_POWER_PCU_THROTTLING", "EventCode": "0x42", "EventName": "UNC_M_POWER_PCU_THROTTLING", "PerPkg": "1", @@ -487,6 +488,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -495,6 +497,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -502,6 +505,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -510,6 +514,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -518,6 +523,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -526,6 +532,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -534,6 +541,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -542,6 +550,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -550,6 +559,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -558,6 +568,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -566,6 +577,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -574,6 +586,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -582,6 +595,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -590,6 +604,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -598,6 +613,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -606,6 +622,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -614,6 +631,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -622,6 +640,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -630,6 +649,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -638,6 +658,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -646,6 +667,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -654,6 +676,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -662,6 +685,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -669,6 +693,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -677,6 +702,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -685,6 +711,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -693,6 +720,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -701,6 +729,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -709,6 +738,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -717,6 +747,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -725,6 +756,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -733,6 +765,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -741,6 +774,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -749,6 +783,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -757,6 +792,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -765,6 +801,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -773,6 +810,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -781,6 +819,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -789,6 +828,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -797,6 +837,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -805,6 +846,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -813,6 +855,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -821,6 +864,7 @@ "EventCode": "0xB2", "EventName": "UNC_M_RD_CAS_RANK2.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -828,6 +872,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -836,6 +881,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -843,6 +889,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -851,6 +898,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -859,6 +907,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -867,6 +916,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -875,6 +925,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -883,6 +934,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -891,6 +943,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -899,6 +952,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -907,6 +961,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -915,6 +970,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -923,6 +979,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -931,6 +988,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -939,6 +997,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -947,6 +1006,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -955,6 +1015,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -963,6 +1024,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -971,6 +1033,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -979,6 +1042,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -987,6 +1051,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -995,6 +1060,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1003,6 +1069,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1010,6 +1077,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1018,6 +1086,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1026,6 +1095,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1034,6 +1104,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1042,6 +1113,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1050,6 +1122,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1058,6 +1131,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1066,6 +1140,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1074,6 +1149,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1082,6 +1158,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1090,6 +1167,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1098,6 +1176,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1106,6 +1185,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1114,6 +1194,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1122,6 +1203,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1130,6 +1212,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1138,6 +1221,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1146,6 +1230,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1154,6 +1239,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1162,6 +1248,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1170,6 +1257,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1177,6 +1265,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1185,6 +1274,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1193,6 +1283,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1201,6 +1292,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1209,6 +1301,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1217,6 +1310,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1225,6 +1319,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1233,6 +1328,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1241,6 +1337,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1249,6 +1346,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1257,6 +1355,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1265,6 +1364,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1273,6 +1373,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1281,6 +1382,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1289,6 +1391,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1297,6 +1400,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1305,6 +1409,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1313,6 +1418,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1321,6 +1427,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1329,6 +1436,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.ALLBANKS", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1337,6 +1445,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1344,6 +1453,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1352,6 +1462,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK10", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1360,6 +1471,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK11", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1368,6 +1480,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK12", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1376,6 +1489,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK13", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1384,6 +1498,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK14", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1392,6 +1507,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK15", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1400,6 +1516,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1408,6 +1525,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1416,6 +1534,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK4", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1424,6 +1543,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK5", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1432,6 +1552,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK6", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1440,6 +1561,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK7", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1448,6 +1570,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK8", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1456,6 +1579,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK9", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1464,6 +1588,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG0", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1472,6 +1597,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG1", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1480,6 +1606,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG2", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1488,6 +1615,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG3", "PerPkg": "1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1598,6 +1726,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1606,6 +1735,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1613,6 +1743,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1621,6 +1752,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1629,6 +1761,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1637,6 +1770,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1645,6 +1779,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1653,6 +1788,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1661,6 +1797,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1669,6 +1806,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1677,6 +1815,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1685,6 +1824,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1693,6 +1833,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1701,6 +1842,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1709,6 +1851,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1717,6 +1860,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1725,6 +1869,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1733,6 +1878,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1741,6 +1887,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1749,6 +1896,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1757,6 +1905,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1765,6 +1914,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1773,6 +1923,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1780,6 +1931,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1788,6 +1940,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1796,6 +1949,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1804,6 +1958,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1812,6 +1967,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1820,6 +1976,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1828,6 +1985,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1836,6 +1994,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1844,6 +2003,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1852,6 +2012,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1860,6 +2021,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1868,6 +2030,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1876,6 +2039,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1884,6 +2048,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1892,6 +2057,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1900,6 +2066,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1908,6 +2075,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1916,6 +2084,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1924,6 +2093,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1932,6 +2102,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1940,6 +2111,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1947,6 +2119,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1955,6 +2128,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1963,6 +2137,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1971,6 +2146,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1979,6 +2155,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1987,6 +2164,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1995,6 +2173,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2003,6 +2182,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2011,6 +2191,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2019,6 +2200,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2027,6 +2209,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2035,6 +2218,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2043,6 +2227,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2051,6 +2236,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2059,6 +2245,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2067,6 +2254,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2075,6 +2263,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2083,6 +2272,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2091,6 +2281,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2099,6 +2290,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2107,6 +2299,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2114,6 +2307,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2122,6 +2316,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2130,6 +2325,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2138,6 +2334,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2146,6 +2343,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2154,6 +2352,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2162,6 +2361,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2170,6 +2370,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2178,6 +2379,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2186,6 +2388,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2194,6 +2397,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2202,6 +2406,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2210,6 +2415,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2218,6 +2424,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2226,6 +2433,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2234,6 +2442,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2242,6 +2451,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2250,6 +2460,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2258,6 +2469,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2266,6 +2478,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2274,6 +2487,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2281,6 +2495,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2289,6 +2504,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2297,6 +2513,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2305,6 +2522,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2313,6 +2531,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2321,6 +2540,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2329,6 +2549,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2337,6 +2558,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2345,6 +2567,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2353,6 +2576,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2361,6 +2585,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2369,6 +2594,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2377,6 +2603,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2385,6 +2612,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2393,6 +2621,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2401,6 +2630,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2409,6 +2639,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2417,6 +2648,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2425,6 +2657,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2433,6 +2666,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.ALLBANKS", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2441,6 +2675,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2448,6 +2683,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2456,6 +2692,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK10", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2464,6 +2701,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK11", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2472,6 +2710,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK12", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2480,6 +2719,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK13", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2488,6 +2728,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK14", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2496,6 +2737,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK15", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2504,6 +2746,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2512,6 +2755,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2520,6 +2764,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK4", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2528,6 +2773,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK5", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2536,6 +2782,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK6", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2544,6 +2791,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK7", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2552,6 +2800,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK8", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2560,6 +2809,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK9", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2568,6 +2818,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG0", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2576,6 +2827,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG1", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2584,6 +2836,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG2", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2592,6 +2845,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG3", "PerPkg": "1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json index 753b381b77fe..fea3dea67f38 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json @@ -101,6 +101,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", "UMask": "0x10", "Unit": "IRP" }, @@ -109,6 +110,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_RD_INSERT", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", "UMask": "0x4", "Unit": "IRP" }, @@ -117,6 +119,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_WR_INSERT", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", "UMask": "0x8", "Unit": "IRP" }, @@ -125,6 +128,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_REJ", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", "UMask": "0x2", "Unit": "IRP" }, @@ -133,6 +137,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_REQ", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", "UMask": "0x1", "Unit": "IRP" }, @@ -141,6 +146,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_XFER", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", "UMask": "0x20", "Unit": "IRP" }, @@ -149,6 +155,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.PF_ACK_HINT", "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", "UMask": "0x40", "Unit": "IRP" }, @@ -175,6 +182,7 @@ "EventCode": "0x15", "EventName": "UNC_I_MISC1.LOST_FWD", "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", "UMask": "0x10", "Unit": "IRP" }, @@ -241,6 +249,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", @@ -256,6 +265,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", @@ -263,6 +273,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", @@ -278,6 +289,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", @@ -285,6 +297,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", @@ -300,6 +313,7 @@ "Unit": "IRP" }, { + "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", @@ -311,6 +325,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_ES", "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit E or S", "UMask": "0x4", "Unit": "IRP" }, @@ -319,6 +334,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_I", "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit I", "UMask": "0x2", "Unit": "IRP" }, @@ -327,6 +343,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_M", "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit M", "UMask": "0x8", "Unit": "IRP" }, @@ -335,6 +352,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.MISS", "PerPkg": "1", + "PublicDescription": "Snoop Responses : Miss", "UMask": "0x1", "Unit": "IRP" }, @@ -343,6 +361,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPCODE", "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpCode", "UMask": "0x10", "Unit": "IRP" }, @@ -351,6 +370,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPDATA", "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpData", "UMask": "0x20", "Unit": "IRP" }, @@ -359,6 +379,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPINV", "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpInv", "UMask": "0x40", "Unit": "IRP" }, @@ -453,7 +474,7 @@ "EventCode": "0xD", "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -465,6 +486,7 @@ "Unit": "R2PCIe" }, { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", "EventCode": "0x2D", "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", "PerPkg": "1", @@ -472,6 +494,7 @@ "Unit": "R2PCIe" }, { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", "EventCode": "0x2D", "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", "PerPkg": "1", @@ -479,6 +502,7 @@ "Unit": "R2PCIe" }, { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI0", "EventCode": "0x2D", "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI0", "PerPkg": "1", @@ -486,6 +510,7 @@ "Unit": "R2PCIe" }, { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI1", "EventCode": "0x2D", "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI1", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json index 124b3fe2e0e1..83d20130c217 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json @@ -395,7 +395,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -403,7 +403,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -411,7 +411,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -427,7 +427,7 @@ "EventCode": "0x9", "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that we are in Interal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", "Unit": "PCU" }, { @@ -439,6 +439,7 @@ "Unit": "PCU" }, { + "BriefDescription": "UNC_P_UFS_TRANSITIONS_RING_GV", "EventCode": "0x79", "EventName": "UNC_P_UFS_TRANSITIONS_RING_GV", "PerPkg": "1", @@ -450,6 +451,7 @@ "EventCode": "0x42", "EventName": "UNC_P_VR_HOT_CYCLES", "PerPkg": "1", + "PublicDescription": "VR Hot : Number of cycles that a CPU SVID VR is hot. Does not cover DRAM VRs", "Unit": "PCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 70be860bcb53..4fa827c7f719 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -3,7 +3,7 @@ GenuineIntel-6-(97|9A|B7|BA|BF),v1.19,alderlake,core GenuineIntel-6-BE,v1.19,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v27,broadwell,core -GenuineIntel-6-56,v7,broadwellde,core +GenuineIntel-6-56,v9,broadwellde,core GenuineIntel-6-4F,v19,broadwellx,core GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core -- GitLab From 74a87b6aa275ced4908cd04ba443e49cda2294e1 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:12 -0700 Subject: [PATCH 1926/5631] perf vendor events intel: Broadwellx v20 events Updates descriptions and encodings. Adds BR_MISP_EXEC.INDIRECT events. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/broadwellx/cache.json | 16 +- .../arch/x86/broadwellx/frontend.json | 18 +- .../arch/x86/broadwellx/pipeline.json | 20 +- .../arch/x86/broadwellx/uncore-cache.json | 156 ++---- .../x86/broadwellx/uncore-interconnect.json | 84 +-- .../arch/x86/broadwellx/uncore-memory.json | 522 +++++++++--------- .../arch/x86/broadwellx/uncore-other.json | 44 +- .../arch/x86/broadwellx/uncore-power.json | 10 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 9 files changed, 403 insertions(+), 469 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json index 6a134928b3f0..781e7c64e71f 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -16,7 +16,7 @@ "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles", + "BriefDescription": "L1D miss outstandings duration in cycles", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "This event counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand; from the demand Hit FB, if it is allocated by hardware or software prefetch.\nNote: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", @@ -454,22 +454,22 @@ "UMask": "0x20" }, { - "BriefDescription": "All retired load uops.", + "BriefDescription": "Retired load uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.", + "PublicDescription": "Counts all retired load uops. This event accounts for SW prefetch uops of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", "SampleAfterValue": "2000003", "UMask": "0x81" }, { - "BriefDescription": "All retired store uops.", + "BriefDescription": "Retired store uops.", "Data_LA": "1", "EventCode": "0xD0", "EventName": "MEM_UOPS_RETIRED.ALL_STORES", "PEBS": "1", - "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.", + "PublicDescription": "Counts all retired store uops.", "SampleAfterValue": "2000003", "UMask": "0x82" }, @@ -541,10 +541,10 @@ "UMask": "0x80" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and non-cacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "This event counts both cacheable and noncachaeble code read requests.", + "PublicDescription": "This event counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json index d0f6678609ae..bd5da39564e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/frontend.json @@ -125,16 +125,16 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", - "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", @@ -143,7 +143,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", @@ -153,7 +153,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "This event counts the number of uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", @@ -161,10 +161,10 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ.", + "PublicDescription": "This event counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ.", "SampleAfterValue": "2000003", "UMask": "0x20" }, @@ -178,10 +178,10 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", - "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequenser (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "PublicDescription": "This event counts the total number of uops delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may bypass the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", "UMask": "0x30" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json index 75233316640b..9a902d2160e6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json @@ -214,6 +214,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", "EventCode": "0x89", @@ -500,7 +508,7 @@ "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "EventCode": "0x87", "EventName": "ILD_STALL.LCP", - "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", + "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.", "SampleAfterValue": "2000003", "UMask": "0x1" }, @@ -909,7 +917,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 0.", + "BriefDescription": "Cycles per core when uops are executed in port 0.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_0_CORE", "SampleAfterValue": "2000003", @@ -925,7 +933,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 1.", + "BriefDescription": "Cycles per core when uops are executed in port 1.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_1_CORE", "SampleAfterValue": "2000003", @@ -973,7 +981,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 4.", + "BriefDescription": "Cycles per core when uops are executed in port 4.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_4_CORE", "SampleAfterValue": "2000003", @@ -989,7 +997,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 5.", + "BriefDescription": "Cycles per core when uops are executed in port 5.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_5_CORE", "SampleAfterValue": "2000003", @@ -1005,7 +1013,7 @@ }, { "AnyThread": "1", - "BriefDescription": "Cycles per core when uops are exectuted in port 6.", + "BriefDescription": "Cycles per core when uops are executed in port 6.", "EventCode": "0xA1", "EventName": "UOPS_EXECUTED_PORT.PORT_6_CORE", "SampleAfterValue": "2000003", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json index 746954775437..f794d2992323 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -5,7 +5,7 @@ "EventName": "LLC_MISSES.CODE_LLC_PREFETCH", "Filter": "filter_opc=0x191", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -16,7 +16,7 @@ "EventName": "LLC_MISSES.DATA_LLC_PREFETCH", "Filter": "filter_opc=0x192", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -27,7 +27,7 @@ "EventName": "LLC_MISSES.DATA_READ", "Filter": "filter_opc=0x182", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -38,7 +38,7 @@ "EventName": "LLC_MISSES.MMIO_READ", "Filter": "filter_opc=0x187,filter_nc=1", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -49,7 +49,7 @@ "EventName": "LLC_MISSES.MMIO_WRITE", "Filter": "filter_opc=0x18f,filter_nc=1", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -60,7 +60,7 @@ "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE", "Filter": "filter_opc=0x1c8,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -71,7 +71,7 @@ "EventName": "LLC_MISSES.PCIE_READ", "Filter": "filter_opc=0x19e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -82,7 +82,7 @@ "EventName": "LLC_MISSES.PCIE_WRITE", "Filter": "filter_opc=0x1c8", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -93,7 +93,7 @@ "EventName": "LLC_MISSES.RFO_LLC_PREFETCH", "Filter": "filter_opc=0x190", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -104,7 +104,7 @@ "EventName": "LLC_MISSES.UNCACHEABLE", "Filter": "filter_opc=0x187", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", "Unit": "CBO" @@ -115,7 +115,7 @@ "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH", "Filter": "filter_opc=0x181", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -126,7 +126,7 @@ "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE", "Filter": "filter_opc=0x180,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", "Unit": "CBO" }, @@ -136,7 +136,7 @@ "EventName": "LLC_REFERENCES.PCIE_READ", "Filter": "filter_opc=0x19e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -147,7 +147,7 @@ "EventName": "LLC_REFERENCES.PCIE_WRITE", "Filter": "filter_opc=0x1c8,filter_tid=0x3e", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -158,7 +158,7 @@ "EventName": "LLC_REFERENCES.STREAMING_FULL", "Filter": "filter_opc=0x18c", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -169,7 +169,7 @@ "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", "Filter": "filter_opc=0x18d", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", "Unit": "CBO" @@ -179,14 +179,12 @@ "EventCode": "0xA", "EventName": "UNC_C_BOUNCE_CONTROL", "PerPkg": "1", - "PublicDescription": "UNC_C_BOUNCE_CONTROL", "Unit": "CBO" }, { "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "UNC_C_CLOCKTICKS", "Unit": "CBO" }, { @@ -257,7 +255,7 @@ "EventCode": "0x34", "EventName": "UNC_C_LLC_LOOKUP.WRITE", "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cachable and UC.", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", "Unit": "CBO" }, @@ -618,7 +616,6 @@ "EventCode": "0x5", "EventName": "UNC_C_RING_BOUNCES.AD", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_BOUNCES.AD", "UMask": "0x1", "Unit": "CBO" }, @@ -627,7 +624,6 @@ "EventCode": "0x5", "EventName": "UNC_C_RING_BOUNCES.AK", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_BOUNCES.AK", "UMask": "0x2", "Unit": "CBO" }, @@ -636,7 +632,6 @@ "EventCode": "0x5", "EventName": "UNC_C_RING_BOUNCES.BL", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_BOUNCES.BL", "UMask": "0x4", "Unit": "CBO" }, @@ -645,7 +640,6 @@ "EventCode": "0x5", "EventName": "UNC_C_RING_BOUNCES.IV", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_BOUNCES.IV", "UMask": "0x10", "Unit": "CBO" }, @@ -690,7 +684,6 @@ "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AD", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_SINK_STARVED.AD", "UMask": "0x1", "Unit": "CBO" }, @@ -699,7 +692,6 @@ "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AK", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_SINK_STARVED.AK", "UMask": "0x2", "Unit": "CBO" }, @@ -708,7 +700,6 @@ "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.BL", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_SINK_STARVED.BL", "UMask": "0x4", "Unit": "CBO" }, @@ -717,7 +708,6 @@ "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.IV", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_SINK_STARVED.IV", "UMask": "0x8", "Unit": "CBO" }, @@ -726,7 +716,6 @@ "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "PublicDescription": "UNC_C_RING_SRC_THRTL", "Unit": "CBO" }, { @@ -1157,7 +1146,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", "Unit": "CBO" }, @@ -1166,7 +1155,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", "Unit": "CBO" }, @@ -1175,7 +1164,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", "Unit": "CBO" }, @@ -1184,7 +1173,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", "Unit": "CBO" }, @@ -1193,7 +1182,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", "Unit": "CBO" }, @@ -1202,7 +1191,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", "Unit": "CBO" }, @@ -1211,7 +1200,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", "Unit": "CBO" }, @@ -1220,7 +1209,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", "Unit": "CBO" }, @@ -1229,7 +1218,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", "Unit": "CBO" }, @@ -1238,7 +1227,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", "Unit": "CBO" }, @@ -1247,7 +1236,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_EVICTION", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", "Unit": "CBO" }, @@ -1256,7 +1245,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_ALL", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", "Unit": "CBO" }, @@ -1265,7 +1254,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_MISS_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", "Unit": "CBO" }, @@ -1274,7 +1263,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", "Unit": "CBO" }, @@ -1283,7 +1272,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.NID_WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", "Unit": "CBO" }, @@ -1292,7 +1281,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", "Unit": "CBO" }, @@ -1301,7 +1290,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", "Unit": "CBO" }, @@ -1310,7 +1299,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisifed by an opcode, inserted into the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", "Unit": "CBO" }, @@ -1319,7 +1308,7 @@ "EventCode": "0x35", "EventName": "UNC_C_TOR_INSERTS.WB", "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfuly inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", "Unit": "CBO" }, @@ -1365,7 +1354,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisifed by an opcode, in the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", "Unit": "CBO" }, @@ -1392,7 +1381,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisifed by an opcode, in the TOR that are satisifed by locally HOMed memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", "Unit": "CBO" }, @@ -1419,7 +1408,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisifed by an opcode, in the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", "Unit": "CBO" }, @@ -1500,7 +1489,7 @@ "EventCode": "0x36", "EventName": "UNC_C_TOR_OCCUPANCY.REMOTE_OPCODE", "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisifed by an opcode, in the TOR that are satisifed by remote caches or remote memory.", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", "Unit": "CBO" }, @@ -1518,7 +1507,6 @@ "EventCode": "0x4", "EventName": "UNC_C_TxR_ADS_USED.AD", "PerPkg": "1", - "PublicDescription": "UNC_C_TxR_ADS_USED.AD", "UMask": "0x1", "Unit": "CBO" }, @@ -1527,7 +1515,6 @@ "EventCode": "0x4", "EventName": "UNC_C_TxR_ADS_USED.AK", "PerPkg": "1", - "PublicDescription": "UNC_C_TxR_ADS_USED.AK", "UMask": "0x2", "Unit": "CBO" }, @@ -1536,7 +1523,6 @@ "EventCode": "0x4", "EventName": "UNC_C_TxR_ADS_USED.BL", "PerPkg": "1", - "PublicDescription": "UNC_C_TxR_ADS_USED.BL", "UMask": "0x4", "Unit": "CBO" }, @@ -1590,7 +1576,7 @@ "EventCode": "0x2", "EventName": "UNC_C_TxR_INSERTS.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transfering writeback data to the cache.", + "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", "Unit": "CBO" }, @@ -1737,7 +1723,7 @@ "EventCode": "0x41", "EventName": "UNC_H_DIRECTORY_LAT_OPT", "PerPkg": "1", - "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory retuned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", + "PublicDescription": "Directory Latency Optimization Data Return Path Taken. When directory mode is enabled and the directory returned for a read is Dir=I, then data can be returned using a faster path if certain conditions are met (credits, free pipeline, etc).", "Unit": "HA" }, { @@ -1790,7 +1776,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.ACKCNFLTWBI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.ACKCNFLTWBI", "UMask": "0x4", "Unit": "HA" }, @@ -1799,7 +1784,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.ALL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.ALL", "UMask": "0xff", "Unit": "HA" }, @@ -1808,7 +1792,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.ALLOCS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.ALLOCS", "UMask": "0x70", "Unit": "HA" }, @@ -1817,7 +1800,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.EVICTS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.EVICTS", "UMask": "0x42", "Unit": "HA" }, @@ -1826,7 +1808,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.HOM", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.HOM", "UMask": "0xf", "Unit": "HA" }, @@ -1835,7 +1816,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.INVALS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.INVALS", "UMask": "0x26", "Unit": "HA" }, @@ -1844,7 +1824,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.READ_OR_INVITOE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.READ_OR_INVITOE", "UMask": "0x1", "Unit": "HA" }, @@ -1853,7 +1832,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.RSP", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.RSP", "UMask": "0x80", "Unit": "HA" }, @@ -1862,7 +1840,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.RSPFWDI_LOCAL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.RSPFWDI_LOCAL", "UMask": "0x20", "Unit": "HA" }, @@ -1871,7 +1848,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.RSPFWDI_REMOTE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.RSPFWDI_REMOTE", "UMask": "0x10", "Unit": "HA" }, @@ -1880,7 +1856,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.RSPFWDS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.RSPFWDS", "UMask": "0x40", "Unit": "HA" }, @@ -1889,7 +1864,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.WBMTOE_OR_S", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.WBMTOE_OR_S", "UMask": "0x8", "Unit": "HA" }, @@ -1898,7 +1872,6 @@ "EventCode": "0x71", "EventName": "UNC_H_HITME_HIT.WBMTOI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT.WBMTOI", "UMask": "0x2", "Unit": "HA" }, @@ -1907,7 +1880,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.ACKCNFLTWBI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.ACKCNFLTWBI", "UMask": "0x4", "Unit": "HA" }, @@ -1916,7 +1888,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.ALL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.ALL", "UMask": "0xff", "Unit": "HA" }, @@ -1925,7 +1896,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.HOM", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.HOM", "UMask": "0xf", "Unit": "HA" }, @@ -1934,7 +1904,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.READ_OR_INVITOE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.READ_OR_INVITOE", "UMask": "0x1", "Unit": "HA" }, @@ -1943,7 +1912,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.RSP", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.RSP", "UMask": "0x80", "Unit": "HA" }, @@ -1952,7 +1920,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDI_LOCAL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDI_LOCAL", "UMask": "0x20", "Unit": "HA" }, @@ -1961,7 +1928,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDI_REMOTE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDI_REMOTE", "UMask": "0x10", "Unit": "HA" }, @@ -1970,7 +1936,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.RSPFWDS", "UMask": "0x40", "Unit": "HA" }, @@ -1979,7 +1944,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.WBMTOE_OR_S", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.WBMTOE_OR_S", "UMask": "0x8", "Unit": "HA" }, @@ -1988,7 +1952,6 @@ "EventCode": "0x72", "EventName": "UNC_H_HITME_HIT_PV_BITS_SET.WBMTOI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_HIT_PV_BITS_SET.WBMTOI", "UMask": "0x2", "Unit": "HA" }, @@ -1997,7 +1960,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.ACKCNFLTWBI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.ACKCNFLTWBI", "UMask": "0x4", "Unit": "HA" }, @@ -2006,7 +1968,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.ALL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.ALL", "UMask": "0xff", "Unit": "HA" }, @@ -2015,7 +1976,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.ALLOCS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.ALLOCS", "UMask": "0x70", "Unit": "HA" }, @@ -2024,7 +1984,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.HOM", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.HOM", "UMask": "0xf", "Unit": "HA" }, @@ -2033,7 +1992,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.INVALS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.INVALS", "UMask": "0x26", "Unit": "HA" }, @@ -2042,7 +2000,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.READ_OR_INVITOE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.READ_OR_INVITOE", "UMask": "0x1", "Unit": "HA" }, @@ -2051,7 +2008,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.RSP", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.RSP", "UMask": "0x80", "Unit": "HA" }, @@ -2060,7 +2016,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.RSPFWDI_LOCAL", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.RSPFWDI_LOCAL", "UMask": "0x20", "Unit": "HA" }, @@ -2069,7 +2024,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.RSPFWDI_REMOTE", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.RSPFWDI_REMOTE", "UMask": "0x10", "Unit": "HA" }, @@ -2078,7 +2032,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.RSPFWDS", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.RSPFWDS", "UMask": "0x40", "Unit": "HA" }, @@ -2087,7 +2040,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.WBMTOE_OR_S", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.WBMTOE_OR_S", "UMask": "0x8", "Unit": "HA" }, @@ -2096,7 +2048,6 @@ "EventCode": "0x70", "EventName": "UNC_H_HITME_LOOKUP.WBMTOI", "PerPkg": "1", - "PublicDescription": "UNC_H_HITME_LOOKUP.WBMTOI", "UMask": "0x2", "Unit": "HA" }, @@ -2168,7 +2119,6 @@ "EventCode": "0x1E", "EventName": "UNC_H_IMC_RETRY", "PerPkg": "1", - "PublicDescription": "UNC_H_IMC_RETRY", "Unit": "HA" }, { @@ -2221,7 +2171,6 @@ "EventCode": "0x61", "EventName": "UNC_H_IOT_BACKPRESSURE.HUB", "PerPkg": "1", - "PublicDescription": "UNC_H_IOT_BACKPRESSURE.HUB", "UMask": "0x2", "Unit": "HA" }, @@ -2230,7 +2179,6 @@ "EventCode": "0x61", "EventName": "UNC_H_IOT_BACKPRESSURE.SAT", "PerPkg": "1", - "PublicDescription": "UNC_H_IOT_BACKPRESSURE.SAT", "UMask": "0x1", "Unit": "HA" }, @@ -2889,7 +2837,7 @@ "EventCode": "0x21", "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", "PerPkg": "1", - "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currentl copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", "ScaleUnit": "64Bytes", "UMask": "0x8", "Unit": "HA" @@ -2963,7 +2911,7 @@ "EventCode": "0x60", "EventName": "UNC_H_SNP_RESP_RECV_LOCAL.RSPSFWD", "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its currentl copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", "UMask": "0x8", "Unit": "HA" }, @@ -3175,7 +3123,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_LOCAL", "PerPkg": "1", @@ -3184,7 +3132,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_REMOTE", "PerPkg": "1", @@ -3193,7 +3141,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_LOCAL", "PerPkg": "1", @@ -3202,7 +3150,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_REMOTE", "PerPkg": "1", @@ -3211,7 +3159,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_LOCAL", "PerPkg": "1", @@ -3220,7 +3168,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_REMOTE", "PerPkg": "1", @@ -3229,7 +3177,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Local Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Local Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.LOCAL", "PerPkg": "1", @@ -3238,7 +3186,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Remote Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Remote Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.REMOTE", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json index 489a3673323d..2819c6621089 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -3,7 +3,7 @@ "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data", "EventName": "QPI_CTL_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "ScaleUnit": "8Bytes", "UMask": "0x4", "Unit": "QPI LL" @@ -12,7 +12,7 @@ "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", "EventName": "QPI_DATA_BANDWIDTH_TX", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "ScaleUnit": "8Bytes", "UMask": "0x2", "Unit": "QPI LL" @@ -38,7 +38,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -47,7 +47,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", "UMask": "0x20", "Unit": "QPI LL" }, @@ -56,7 +56,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -65,7 +65,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", "UMask": "0x80", "Unit": "QPI LL" }, @@ -74,7 +74,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -83,7 +83,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core tranaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -92,7 +92,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", "UMask": "0x40", "Unit": "QPI LL" }, @@ -101,7 +101,7 @@ "EventCode": "0x13", "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exlusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -134,7 +134,7 @@ "EventCode": "0x9", "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", "Unit": "QPI LL" }, { @@ -391,7 +391,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generall not considered part of the QPI bandwidth.", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -400,7 +400,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -409,7 +409,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", "Unit": "QPI LL" }, @@ -418,7 +418,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -427,7 +427,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -436,7 +436,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -445,7 +445,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -454,7 +454,7 @@ "EventCode": "0x2", "EventName": "UNC_Q_RxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -463,7 +463,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -472,7 +472,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -481,7 +481,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -490,7 +490,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -499,7 +499,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -508,7 +508,7 @@ "EventCode": "0x3", "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -924,7 +924,7 @@ "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -932,7 +932,7 @@ "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -940,7 +940,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", "EventName": "UNC_Q_TxL_FLITS_G1.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", "UMask": "0x18", "Unit": "QPI LL" }, @@ -948,7 +948,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", "Unit": "QPI LL" }, @@ -956,7 +956,7 @@ "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -964,7 +964,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", "UMask": "0x6", "Unit": "QPI LL" }, @@ -972,7 +972,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -980,7 +980,7 @@ "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -988,7 +988,7 @@ "BriefDescription": "Flits Transferred - Group 1; SNP Flits", "EventName": "UNC_Q_TxL_FLITS_G1.SNP", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -997,7 +997,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", "Unit": "QPI LL" }, @@ -1006,7 +1006,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not te NCB headers.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", "Unit": "QPI LL" }, @@ -1015,7 +1015,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", "Unit": "QPI LL" }, @@ -1024,7 +1024,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NCS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", "UMask": "0x10", "Unit": "QPI LL" }, @@ -1033,7 +1033,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -1042,7 +1042,7 @@ "EventCode": "0x1", "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits trasmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transfering a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", "Unit": "QPI LL" }, @@ -1157,7 +1157,7 @@ "EventCode": "0x23", "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO fro Snoop messages on AD.", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x1", "Unit": "QPI LL" }, @@ -1166,7 +1166,7 @@ "EventCode": "0x23", "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO fro Snoop messages on AD.", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x2", "Unit": "QPI LL" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json index 34dfc3cf22ef..b5a33e7a68c6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json @@ -51,7 +51,6 @@ "EventCode": "0xA1", "EventName": "UNC_M_BYP_CMDS.ACT", "PerPkg": "1", - "PublicDescription": "UNC_M_BYP_CMDS.ACT", "UMask": "0x1", "Unit": "iMC" }, @@ -60,7 +59,6 @@ "EventCode": "0xA1", "EventName": "UNC_M_BYP_CMDS.CAS", "PerPkg": "1", - "PublicDescription": "UNC_M_BYP_CMDS.CAS", "UMask": "0x2", "Unit": "iMC" }, @@ -69,7 +67,6 @@ "EventCode": "0xA1", "EventName": "UNC_M_BYP_CMDS.PRE", "PerPkg": "1", - "PublicDescription": "UNC_M_BYP_CMDS.PRE", "UMask": "0x4", "Unit": "iMC" }, @@ -202,7 +199,7 @@ "EventCode": "0x9", "EventName": "UNC_M_ECC_CORRECTABLE_ERRORS", "PerPkg": "1", - "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit erros in lockstep mode.", + "PublicDescription": "Counts the number of ECC errors detected and corrected by the iMC on this channel. This counter is only useful with ECC DRAM devices. This count will increment one time for each correction regardless of the number of bits corrected. The iMC can correct up to 4 bit errors in independent channel mode and 8 bit errors in lockstep mode.", "Unit": "iMC" }, { @@ -492,7 +489,6 @@ "EventCode": "0xA0", "EventName": "UNC_M_RD_CAS_PRIO.HIGH", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_PRIO.HIGH", "UMask": "0x4", "Unit": "iMC" }, @@ -501,7 +497,6 @@ "EventCode": "0xA0", "EventName": "UNC_M_RD_CAS_PRIO.LOW", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_PRIO.LOW", "UMask": "0x1", "Unit": "iMC" }, @@ -510,7 +505,6 @@ "EventCode": "0xA0", "EventName": "UNC_M_RD_CAS_PRIO.MED", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_PRIO.MED", "UMask": "0x2", "Unit": "iMC" }, @@ -519,7 +513,6 @@ "EventCode": "0xA0", "EventName": "UNC_M_RD_CAS_PRIO.PANIC", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_PRIO.PANIC", "UMask": "0x8", "Unit": "iMC" }, @@ -528,7 +521,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -537,7 +530,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -545,7 +538,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -554,7 +547,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -563,7 +556,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -572,7 +565,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -581,7 +574,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -590,7 +583,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -599,7 +592,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -608,7 +601,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -617,7 +610,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -626,7 +619,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -635,7 +628,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -644,7 +637,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -653,7 +646,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -662,7 +655,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -671,7 +664,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -680,7 +673,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -689,7 +682,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -698,7 +691,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -707,7 +700,7 @@ "EventCode": "0xB0", "EventName": "UNC_M_RD_CAS_RANK0.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK0.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -716,7 +709,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -725,7 +718,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -733,7 +726,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -742,7 +735,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -751,7 +744,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -760,7 +753,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -769,7 +762,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -778,7 +771,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -787,7 +780,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -796,7 +789,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -805,7 +798,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -814,7 +807,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -823,7 +816,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -832,7 +825,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -841,7 +834,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -850,7 +843,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -859,7 +852,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -868,7 +861,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -877,7 +870,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -886,7 +879,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -895,7 +888,7 @@ "EventCode": "0xB1", "EventName": "UNC_M_RD_CAS_RANK1.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK1.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -904,7 +897,7 @@ "EventCode": "0xB2", "EventName": "UNC_M_RD_CAS_RANK2.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK2.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -912,7 +905,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -921,7 +914,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -929,7 +922,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -938,7 +931,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -947,7 +940,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -956,7 +949,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -965,7 +958,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -974,7 +967,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -983,7 +976,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -992,7 +985,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1001,7 +994,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1010,7 +1003,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1019,7 +1012,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1028,7 +1021,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1037,7 +1030,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1046,7 +1039,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1055,7 +1048,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1064,7 +1057,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1073,7 +1066,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1082,7 +1075,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1091,7 +1084,7 @@ "EventCode": "0xB4", "EventName": "UNC_M_RD_CAS_RANK4.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK4.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1100,7 +1093,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1109,7 +1102,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1117,7 +1110,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1126,7 +1119,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1135,7 +1128,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1144,7 +1137,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1153,7 +1146,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1162,7 +1155,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1171,7 +1164,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1180,7 +1173,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1189,7 +1182,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1198,7 +1191,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1207,7 +1200,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1216,7 +1209,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1225,7 +1218,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1234,7 +1227,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1243,7 +1236,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1252,7 +1245,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1261,7 +1254,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1270,7 +1263,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1279,7 +1272,7 @@ "EventCode": "0xB5", "EventName": "UNC_M_RD_CAS_RANK5.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK5.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1288,7 +1281,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1297,7 +1290,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1305,7 +1298,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1314,7 +1307,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1323,7 +1316,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1332,7 +1325,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1341,7 +1334,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1350,7 +1343,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1359,7 +1352,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1368,7 +1361,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1377,7 +1370,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1386,7 +1379,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1395,7 +1388,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1404,7 +1397,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1413,7 +1406,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1422,7 +1415,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1431,7 +1424,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1440,7 +1433,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1449,7 +1442,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1458,7 +1451,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1467,7 +1460,7 @@ "EventCode": "0xB6", "EventName": "UNC_M_RD_CAS_RANK6.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK6.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1476,7 +1469,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.ALLBANKS", + "PublicDescription": "RD_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1485,7 +1478,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1493,7 +1486,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1502,7 +1495,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK10", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1511,7 +1504,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK11", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1520,7 +1513,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK12", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1529,7 +1522,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK13", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1538,7 +1531,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK14", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1547,7 +1540,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK15", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1556,7 +1549,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1565,7 +1558,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1574,7 +1567,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK4", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1583,7 +1576,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK5", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1592,7 +1585,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK6", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1601,7 +1594,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK7", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1610,7 +1603,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK8", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1619,7 +1612,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANK9", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1628,7 +1621,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANKG0", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1637,7 +1630,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANKG1", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1646,7 +1639,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANKG2", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1655,7 +1648,7 @@ "EventCode": "0xB7", "EventName": "UNC_M_RD_CAS_RANK7.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_RD_CAS_RANK7.BANKG3", + "PublicDescription": "RD_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1680,7 +1673,6 @@ "EventCode": "0x91", "EventName": "UNC_M_VMSE_MXB_WR_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "UNC_M_VMSE_MXB_WR_OCCUPANCY", "Unit": "iMC" }, { @@ -1688,7 +1680,6 @@ "EventCode": "0x90", "EventName": "UNC_M_VMSE_WR_PUSH.RMM", "PerPkg": "1", - "PublicDescription": "UNC_M_VMSE_WR_PUSH.RMM", "UMask": "0x2", "Unit": "iMC" }, @@ -1697,7 +1688,6 @@ "EventCode": "0x90", "EventName": "UNC_M_VMSE_WR_PUSH.WMM", "PerPkg": "1", - "PublicDescription": "UNC_M_VMSE_WR_PUSH.WMM", "UMask": "0x1", "Unit": "iMC" }, @@ -1706,7 +1696,6 @@ "EventCode": "0xC0", "EventName": "UNC_M_WMM_TO_RMM.LOW_THRESH", "PerPkg": "1", - "PublicDescription": "UNC_M_WMM_TO_RMM.LOW_THRESH", "UMask": "0x1", "Unit": "iMC" }, @@ -1715,7 +1704,6 @@ "EventCode": "0xC0", "EventName": "UNC_M_WMM_TO_RMM.STARVE", "PerPkg": "1", - "PublicDescription": "UNC_M_WMM_TO_RMM.STARVE", "UMask": "0x2", "Unit": "iMC" }, @@ -1724,7 +1712,6 @@ "EventCode": "0xC0", "EventName": "UNC_M_WMM_TO_RMM.VMSE_RETRY", "PerPkg": "1", - "PublicDescription": "UNC_M_WMM_TO_RMM.VMSE_RETRY", "UMask": "0x4", "Unit": "iMC" }, @@ -1765,7 +1752,6 @@ "EventCode": "0xC1", "EventName": "UNC_M_WRONG_MM", "PerPkg": "1", - "PublicDescription": "UNC_M_WRONG_MM", "Unit": "iMC" }, { @@ -1773,7 +1759,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1782,7 +1768,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1790,7 +1776,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1799,7 +1785,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1808,7 +1794,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -1817,7 +1803,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -1826,7 +1812,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -1835,7 +1821,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -1844,7 +1830,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -1853,7 +1839,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -1862,7 +1848,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -1871,7 +1857,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -1880,7 +1866,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -1889,7 +1875,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -1898,7 +1884,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -1907,7 +1893,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -1916,7 +1902,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -1925,7 +1911,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -1934,7 +1920,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -1943,7 +1929,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -1952,7 +1938,7 @@ "EventCode": "0xB8", "EventName": "UNC_M_WR_CAS_RANK0.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK0.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -1961,7 +1947,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -1970,7 +1956,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -1978,7 +1964,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -1987,7 +1973,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -1996,7 +1982,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2005,7 +1991,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2014,7 +2000,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2023,7 +2009,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2032,7 +2018,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2041,7 +2027,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2050,7 +2036,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2059,7 +2045,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2068,7 +2054,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2077,7 +2063,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2086,7 +2072,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2095,7 +2081,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2104,7 +2090,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2113,7 +2099,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2122,7 +2108,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2131,7 +2117,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2140,7 +2126,7 @@ "EventCode": "0xB9", "EventName": "UNC_M_WR_CAS_RANK1.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK1.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2149,7 +2135,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2158,7 +2144,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2166,7 +2152,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2175,7 +2161,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2184,7 +2170,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2193,7 +2179,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2202,7 +2188,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2211,7 +2197,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2220,7 +2206,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2229,7 +2215,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2238,7 +2224,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2247,7 +2233,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2256,7 +2242,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2265,7 +2251,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2274,7 +2260,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2283,7 +2269,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2292,7 +2278,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2301,7 +2287,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2310,7 +2296,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2319,7 +2305,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2328,7 +2314,7 @@ "EventCode": "0xBC", "EventName": "UNC_M_WR_CAS_RANK4.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK4.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2337,7 +2323,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2346,7 +2332,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2354,7 +2340,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2363,7 +2349,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2372,7 +2358,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2381,7 +2367,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2390,7 +2376,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2399,7 +2385,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2408,7 +2394,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2417,7 +2403,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2426,7 +2412,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2435,7 +2421,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2444,7 +2430,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2453,7 +2439,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2462,7 +2448,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2471,7 +2457,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2480,7 +2466,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2489,7 +2475,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2498,7 +2484,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2507,7 +2493,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2516,7 +2502,7 @@ "EventCode": "0xBD", "EventName": "UNC_M_WR_CAS_RANK5.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK5.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2525,7 +2511,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2534,7 +2520,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2542,7 +2528,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2551,7 +2537,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2560,7 +2546,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2569,7 +2555,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2578,7 +2564,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2587,7 +2573,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2596,7 +2582,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2605,7 +2591,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2614,7 +2600,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2623,7 +2609,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2632,7 +2618,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2641,7 +2627,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2650,7 +2636,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2659,7 +2645,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2668,7 +2654,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2677,7 +2663,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2686,7 +2672,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2695,7 +2681,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2704,7 +2690,7 @@ "EventCode": "0xBE", "EventName": "UNC_M_WR_CAS_RANK6.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK6.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" }, @@ -2713,7 +2699,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.ALLBANKS", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.ALLBANKS", + "PublicDescription": "WR_CAS Access to Rank 0 : All Banks", "UMask": "0x10", "Unit": "iMC" }, @@ -2722,7 +2708,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 0", "Unit": "iMC" }, { @@ -2730,7 +2716,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 1", "UMask": "0x1", "Unit": "iMC" }, @@ -2739,7 +2725,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK10", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK10", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 10", "UMask": "0xa", "Unit": "iMC" }, @@ -2748,7 +2734,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK11", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK11", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 11", "UMask": "0xb", "Unit": "iMC" }, @@ -2757,7 +2743,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK12", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK12", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 12", "UMask": "0xc", "Unit": "iMC" }, @@ -2766,7 +2752,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK13", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK13", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 13", "UMask": "0xd", "Unit": "iMC" }, @@ -2775,7 +2761,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK14", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK14", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 14", "UMask": "0xe", "Unit": "iMC" }, @@ -2784,7 +2770,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK15", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK15", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 15", "UMask": "0xf", "Unit": "iMC" }, @@ -2793,7 +2779,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 2", "UMask": "0x2", "Unit": "iMC" }, @@ -2802,7 +2788,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 3", "UMask": "0x3", "Unit": "iMC" }, @@ -2811,7 +2797,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK4", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK4", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 4", "UMask": "0x4", "Unit": "iMC" }, @@ -2820,7 +2806,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK5", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK5", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 5", "UMask": "0x5", "Unit": "iMC" }, @@ -2829,7 +2815,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK6", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK6", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 6", "UMask": "0x6", "Unit": "iMC" }, @@ -2838,7 +2824,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK7", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK7", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 7", "UMask": "0x7", "Unit": "iMC" }, @@ -2847,7 +2833,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK8", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK8", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 8", "UMask": "0x8", "Unit": "iMC" }, @@ -2856,7 +2842,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANK9", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANK9", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank 9", "UMask": "0x9", "Unit": "iMC" }, @@ -2865,7 +2851,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG0", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANKG0", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 0 (Banks 0-3)", "UMask": "0x11", "Unit": "iMC" }, @@ -2874,7 +2860,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG1", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANKG1", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 1 (Banks 4-7)", "UMask": "0x12", "Unit": "iMC" }, @@ -2883,7 +2869,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG2", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANKG2", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 2 (Banks 8-11)", "UMask": "0x13", "Unit": "iMC" }, @@ -2892,7 +2878,7 @@ "EventCode": "0xBF", "EventName": "UNC_M_WR_CAS_RANK7.BANKG3", "PerPkg": "1", - "PublicDescription": "UNC_M_WR_CAS_RANK7.BANKG3", + "PublicDescription": "WR_CAS Access to Rank 0 : Bank Group 3 (Banks 12-15)", "UMask": "0x14", "Unit": "iMC" } diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json index a80d931dc3d5..43def2582617 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json @@ -101,7 +101,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", "UMask": "0x10", "Unit": "IRP" }, @@ -110,7 +110,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_RD_INSERT", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.2ND_RD_INSERT", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", "UMask": "0x4", "Unit": "IRP" }, @@ -119,7 +119,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.2ND_WR_INSERT", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.2ND_WR_INSERT", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", "UMask": "0x8", "Unit": "IRP" }, @@ -128,7 +128,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_REJ", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.FAST_REJ", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", "UMask": "0x2", "Unit": "IRP" }, @@ -137,7 +137,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_REQ", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.FAST_REQ", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", "UMask": "0x1", "Unit": "IRP" }, @@ -146,7 +146,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.FAST_XFER", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.FAST_XFER", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", "UMask": "0x20", "Unit": "IRP" }, @@ -155,7 +155,7 @@ "EventCode": "0x14", "EventName": "UNC_I_MISC0.PF_ACK_HINT", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC0.PF_ACK_HINT", + "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", "UMask": "0x40", "Unit": "IRP" }, @@ -182,7 +182,7 @@ "EventCode": "0x15", "EventName": "UNC_I_MISC1.LOST_FWD", "PerPkg": "1", - "PublicDescription": "UNC_I_MISC1.LOST_FWD", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", "UMask": "0x10", "Unit": "IRP" }, @@ -325,7 +325,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_ES", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.HIT_ES", + "PublicDescription": "Snoop Responses : Hit E or S", "UMask": "0x4", "Unit": "IRP" }, @@ -334,7 +334,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_I", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.HIT_I", + "PublicDescription": "Snoop Responses : Hit I", "UMask": "0x2", "Unit": "IRP" }, @@ -343,7 +343,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.HIT_M", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.HIT_M", + "PublicDescription": "Snoop Responses : Hit M", "UMask": "0x8", "Unit": "IRP" }, @@ -352,7 +352,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.MISS", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.MISS", + "PublicDescription": "Snoop Responses : Miss", "UMask": "0x1", "Unit": "IRP" }, @@ -361,7 +361,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPCODE", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.SNPCODE", + "PublicDescription": "Snoop Responses : SnpCode", "UMask": "0x10", "Unit": "IRP" }, @@ -370,7 +370,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPDATA", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.SNPDATA", + "PublicDescription": "Snoop Responses : SnpData", "UMask": "0x20", "Unit": "IRP" }, @@ -379,7 +379,7 @@ "EventCode": "0x17", "EventName": "UNC_I_SNOOP_RESP.SNPINV", "PerPkg": "1", - "PublicDescription": "UNC_I_SNOOP_RESP.SNPINV", + "PublicDescription": "Snoop Responses : SnpInv", "UMask": "0x40", "Unit": "IRP" }, @@ -474,7 +474,7 @@ "EventCode": "0xD", "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -1223,7 +1223,6 @@ "EventCode": "0xB", "EventName": "UNC_R3_IOT_BACKPRESSURE.HUB", "PerPkg": "1", - "PublicDescription": "UNC_R3_IOT_BACKPRESSURE.HUB", "UMask": "0x2", "Unit": "R3QPI" }, @@ -1232,7 +1231,6 @@ "EventCode": "0xB", "EventName": "UNC_R3_IOT_BACKPRESSURE.SAT", "PerPkg": "1", - "PublicDescription": "UNC_R3_IOT_BACKPRESSURE.SAT", "UMask": "0x1", "Unit": "R3QPI" }, @@ -2312,7 +2310,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transfered). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transfered in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", "Unit": "R3QPI" }, @@ -2321,7 +2319,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transfered). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transfered in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x4", "Unit": "R3QPI" }, @@ -2384,14 +2382,12 @@ "EventCode": "0xA", "EventName": "UNC_S_BOUNCE_CONTROL", "PerPkg": "1", - "PublicDescription": "UNC_S_BOUNCE_CONTROL", "Unit": "SBO" }, { "BriefDescription": "Uncore Clocks", "EventName": "UNC_S_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "UNC_S_CLOCKTICKS", "Unit": "SBO" }, { @@ -2596,7 +2592,6 @@ "EventCode": "0x5", "EventName": "UNC_S_RING_BOUNCES.AD_CACHE", "PerPkg": "1", - "PublicDescription": "UNC_S_RING_BOUNCES.AD_CACHE", "UMask": "0x1", "Unit": "SBO" }, @@ -2605,7 +2600,6 @@ "EventCode": "0x5", "EventName": "UNC_S_RING_BOUNCES.AK_CORE", "PerPkg": "1", - "PublicDescription": "UNC_S_RING_BOUNCES.AK_CORE", "UMask": "0x2", "Unit": "SBO" }, @@ -2614,7 +2608,6 @@ "EventCode": "0x5", "EventName": "UNC_S_RING_BOUNCES.BL_CORE", "PerPkg": "1", - "PublicDescription": "UNC_S_RING_BOUNCES.BL_CORE", "UMask": "0x4", "Unit": "SBO" }, @@ -2623,7 +2616,6 @@ "EventCode": "0x5", "EventName": "UNC_S_RING_BOUNCES.IV_CORE", "PerPkg": "1", - "PublicDescription": "UNC_S_RING_BOUNCES.IV_CORE", "UMask": "0x8", "Unit": "SBO" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json index e682eedf644a..83d20130c217 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json @@ -395,7 +395,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -403,7 +403,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -411,7 +411,7 @@ "EventCode": "0x80", "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6", "PerPkg": "1", - "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", "Unit": "PCU" }, { @@ -427,7 +427,7 @@ "EventCode": "0x9", "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that we are in Interal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "PublicDescription": "Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", "Unit": "PCU" }, { @@ -451,7 +451,7 @@ "EventCode": "0x42", "EventName": "UNC_P_VR_HOT_CYCLES", "PerPkg": "1", - "PublicDescription": "UNC_P_VR_HOT_CYCLES", + "PublicDescription": "VR Hot : Number of cycles that a CPU SVID VR is hot. Does not cover DRAM VRs", "Unit": "PCU" } ] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 4fa827c7f719..dfed265c95ab 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -4,7 +4,7 @@ GenuineIntel-6-BE,v1.19,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v27,broadwell,core GenuineIntel-6-56,v9,broadwellde,core -GenuineIntel-6-4F,v19,broadwellx,core +GenuineIntel-6-4F,v20,broadwellx,core GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core -- GitLab From 67245a7eea604b61ce7973329c1bb99d5e35dcf7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:13 -0700 Subject: [PATCH 1927/5631] perf vendor events intel: Haswell v33 events Updates descriptions and encodings. Adds BR_MISP_EXEC.INDIRECT events. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/haswell/cache.json | 38 +++++++++---------- .../pmu-events/arch/x86/haswell/memory.json | 38 +++++++++---------- .../pmu-events/arch/x86/haswell/pipeline.json | 8 ++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 4 files changed, 47 insertions(+), 39 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json index 5a1489e79859..0831f14b3cc6 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", @@ -643,7 +643,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch code readshit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -652,7 +652,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data readshit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", @@ -661,7 +661,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data readshit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -688,7 +688,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all requestshit in the L3", + "BriefDescription": "Counts all requests hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -697,7 +697,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOshit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", @@ -706,7 +706,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOshit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -715,7 +715,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code readshit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", @@ -724,7 +724,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code readshit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -733,7 +733,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data readshit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", @@ -742,7 +742,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data readshit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -751,7 +751,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs)hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", @@ -760,7 +760,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs)hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", + "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", @@ -769,7 +769,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code readshit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -778,7 +778,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data readshit in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -787,7 +787,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOshit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -796,7 +796,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to LLC only) code readshit in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -805,7 +805,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data readshit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -814,7 +814,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOshit in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json index 9fb63e1dab08..2fc25e22a42a 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/memory.json +++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json @@ -179,7 +179,7 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts all demand & prefetch code readsmiss in the L3", + "BriefDescription": "Counts all demand & prefetch code reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -188,7 +188,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch code readsmiss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -197,7 +197,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data readsmiss in the L3", + "BriefDescription": "Counts all demand & prefetch data reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -206,7 +206,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data readsmiss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -233,7 +233,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all requestsmiss in the L3", + "BriefDescription": "Counts all requests miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -242,7 +242,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOsmiss in the L3", + "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -251,7 +251,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOsmiss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -260,7 +260,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code readsmiss in the L3", + "BriefDescription": "Counts all demand code reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -269,7 +269,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code readsmiss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -278,7 +278,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data readsmiss in the L3", + "BriefDescription": "Counts demand data reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -287,7 +287,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data readsmiss the L3 and the data is returned from local dram", + "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -296,7 +296,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs)miss in the L3", + "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -305,7 +305,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs)miss the L3 and the data is returned from local dram", + "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM", "MSRIndex": "0x1a6,0x1a7", @@ -314,7 +314,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) code readsmiss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -323,7 +323,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data readsmiss in the L3", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -332,7 +332,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOsmiss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -341,7 +341,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to LLC only) code readsmiss in the L3", + "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -350,7 +350,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data readsmiss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", @@ -359,7 +359,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOsmiss in the L3", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3", "EventCode": "0xB7, 0xBB", "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json index 9ac36c1c24b6..540f4372623c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json @@ -194,6 +194,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index dfed265c95ab..927e60f3417d 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -10,7 +10,7 @@ GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-A[DE],v1.01,graniterapids,core -GenuineIntel-6-(3C|45|46),v32,haswell,core +GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v26,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.19,icelakex,core -- GitLab From 6e884dad09722abd6ea23a27acc041ba767bdb88 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:14 -0700 Subject: [PATCH 1928/5631] perf vendor events intel: Haswellx v27 events Updates descriptions and encodings. Adds BR_MISP_EXEC.INDIRECT events. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/pmu-events/arch/x86/haswellx/cache.json | 2 +- .../pmu-events/arch/x86/haswellx/pipeline.json | 8 ++++++++ .../arch/x86/haswellx/uncore-cache.json | 16 ++++++++-------- .../arch/x86/haswellx/uncore-other.json | 6 +++--- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 5 files changed, 21 insertions(+), 13 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json index 1836ed62694e..a6c81010b394 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json index 9ac36c1c24b6..540f4372623c 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json @@ -194,6 +194,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json index 183bcac99642..e969dc71bea1 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -3114,7 +3114,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_LOCAL", "PerPkg": "1", @@ -3123,7 +3123,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote InvItoE Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote InvItoE Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.INVITOE_REMOTE", "PerPkg": "1", @@ -3132,7 +3132,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_LOCAL", "PerPkg": "1", @@ -3141,7 +3141,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Read Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Read Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.READS_REMOTE", "PerPkg": "1", @@ -3150,7 +3150,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Local Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Local Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_LOCAL", "PerPkg": "1", @@ -3159,7 +3159,7 @@ "Unit": "HA" }, { - "BriefDescription": "Tracker Occupancy Accumultor; Remote Write Requests", + "BriefDescription": "Tracker Occupancy Accumulator; Remote Write Requests", "EventCode": "0x4", "EventName": "UNC_H_TRACKER_OCCUPANCY.WRITES_REMOTE", "PerPkg": "1", @@ -3168,7 +3168,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Local Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Local Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.LOCAL", "PerPkg": "1", @@ -3177,7 +3177,7 @@ "Unit": "HA" }, { - "BriefDescription": "Data Pending Occupancy Accumultor; Remote Requests", + "BriefDescription": "Data Pending Occupancy Accumulator; Remote Requests", "EventCode": "0x5", "EventName": "UNC_H_TRACKER_PENDING_OCCUPANCY.REMOTE", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json index 4c3e2a794117..d30e3b16c1af 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json @@ -474,7 +474,7 @@ "EventCode": "0xD", "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { @@ -2256,7 +2256,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", "Unit": "R3QPI" }, @@ -2265,7 +2265,7 @@ "EventCode": "0x33", "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credts from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x4", "Unit": "R3QPI" }, diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 927e60f3417d..e1a609401fff 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -11,7 +11,7 @@ GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core -GenuineIntel-6-3F,v26,haswellx,core +GenuineIntel-6-3F,v27,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.19,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core -- GitLab From 101a25b5d96d5ca06e11d07bb83fd72886407fe4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:15 -0700 Subject: [PATCH 1929/5631] perf vendor events intel: Jaketown v23 events Adds BR_MISP_EXEC.INDIRECT event. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/jaketown/pipeline.json | 8 ++++++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json index 85c04fe7632a..d0edfdec9f01 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json @@ -202,6 +202,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index e1a609401fff..e41c289fa427 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -16,7 +16,7 @@ GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.19,icelakex,core GenuineIntel-6-3A,v23,ivybridge,core GenuineIntel-6-3E,v22,ivytown,core -GenuineIntel-6-2D,v22,jaketown,core +GenuineIntel-6-2D,v23,jaketown,core GenuineIntel-6-(57|85),v10,knightslanding,core GenuineIntel-6-A[AC],v1.01,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core -- GitLab From e559b6f53b1b36fd69291962104fa86edf3dadf4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:16 -0700 Subject: [PATCH 1930/5631] perf vendor events intel: Sandybridge v19 events Adds BR_MISP_EXEC.INDIRECT event. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index e41c289fa427..41d755d570e6 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -21,7 +21,7 @@ GenuineIntel-6-(57|85),v10,knightslanding,core GenuineIntel-6-A[AC],v1.01,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core -GenuineIntel-6-2A,v18,sandybridge,core +GenuineIntel-6-2A,v19,sandybridge,core GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v55,skylake,core diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json index 54454e5e262c..ecaf94ccc9c7 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json @@ -210,6 +210,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.", "EventCode": "0x89", -- GitLab From c3bf86f11dc9a11afb83b33f9640bf86adfb1b28 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:17 -0700 Subject: [PATCH 1931/5631] perf metrics: Add has_pmem literal Add literal so that if nvdimms aren't installed we can record fewer events. The file detection mechanism was suggested by Dan Williams in: https://lore.kernel.org/linux-perf-users/641bbe1eced26_1b98bb29440@dwillia2-xfh.jf.intel.com.notmuch/ Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index d46a1878bc9e..bb6ddad7e021 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -14,6 +14,7 @@ #include "util/hashmap.h" #include "smt.h" #include "tsc.h" +#include #include #include #include @@ -400,6 +401,20 @@ double arch_get_tsc_freq(void) } #endif +static double has_pmem(void) +{ + static bool has_pmem, cached; + const char *sysfs = sysfs__mountpoint(); + char path[PATH_MAX]; + + if (!cached) { + snprintf(path, sizeof(path), "%s/firmware/acpi/tables/NFIT", sysfs); + has_pmem = access(path, F_OK) == 0; + cached = true; + } + return has_pmem ? 1.0 : 0.0; +} + double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx) { const struct cpu_topology *topology; @@ -449,6 +464,10 @@ double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx result = perf_pmu__cpu_slots_per_cycle(); goto out; } + if (!strcmp("#has_pmem", literal)) { + result = has_pmem(); + goto out; + } pr_err("Unrecognized literal '%s'", literal); out: -- GitLab From 31c5ba6c2556f80842d464ed743aff50890c8208 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 24 Mar 2023 00:22:18 -0700 Subject: [PATCH 1932/5631] perf vendor events intel: Update metrics to detect pmem at runtime By detecting whether nvdimms are installed at runtime the number of events can be reduced if it isn't. These changes come from this PR: https://github.com/intel/perfmon/pull/63 Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Dan Williams Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Samantha Alt Cc: Weilin Wang Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230324072218.181880-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/cascadelakex/clx-metrics.json | 10 +++++----- .../perf/pmu-events/arch/x86/icelakex/icx-metrics.json | 10 +++++----- .../arch/x86/sapphirerapids/spr-metrics.json | 10 +++++----- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 4e993a3220e3..8f7dc72accd0 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -201,7 +201,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -933,7 +933,7 @@ }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@", + "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@event\\=0x0@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", "MetricName": "tma_info_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" @@ -998,13 +998,13 @@ }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_write_bw" }, @@ -1310,7 +1310,7 @@ { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 8109088a4df7..0f9b174dfc22 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -186,7 +186,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound", + "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_pmem > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -918,7 +918,7 @@ }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@", + "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@event\\=0x0@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", "MetricName": "tma_info_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" @@ -984,13 +984,13 @@ }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_write_bw" }, @@ -1298,7 +1298,7 @@ }, { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 149cc4c07fb5..126300b7ae77 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -185,7 +185,7 @@ { "BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads", "MetricConstraint": "NO_GROUP_EVENTS", - "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound", + "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound if #has_pmem > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks)", "MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", @@ -968,7 +968,7 @@ }, { "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]", - "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@", + "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@event\\=0x1@ if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryLat;Server;SoC", "MetricName": "tma_info_mem_pmm_read_latency", "PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches" @@ -1034,13 +1034,13 @@ }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_read_bw" }, { "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]", - "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time", + "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_pmem > 0 else 0)", "MetricGroup": "Mem;MemoryBW;Server;SoC", "MetricName": "tma_info_pmm_write_bw" }, @@ -1406,7 +1406,7 @@ }, { "BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a", - "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)", + "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_pmem > 0 else 0))) if #has_pmem > 0 else 0)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_pmem > 0 else 0)", "MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_pmm_bound", "MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)", -- GitLab From 9835b742ac3ee16dee361e7ccda8022f99d1cd94 Mon Sep 17 00:00:00 2001 From: Patrice Duroux Date: Fri, 3 Mar 2023 20:30:58 +0100 Subject: [PATCH 1933/5631] perf tests record_offcpu.sh: Fix redirection of stderr to stdin It's not 2&>1, the correct is 2>&1 Fixes: ade1d0307b2fb3d9 ("perf offcpu: Update offcpu test for child process") Signed-off-by: Patrice Duroux Acked-by: Ian Rogers Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230303193058.21274-1-patrice.duroux@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/record_offcpu.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index 24f81ff85793..155d4856551a 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -65,7 +65,7 @@ test_offcpu_child() { # perf bench sched messaging creates 400 processes if ! perf record --off-cpu -e dummy -o ${perfdata} -- \ - perf bench sched messaging -g 10 > /dev/null 2&>1 + perf bench sched messaging -g 10 > /dev/null 2>&1 then echo "Child task off-cpu test [Failed record]" err=1 -- GitLab From 7f8d3fbe094be59a286f3b43431668221123ff30 Mon Sep 17 00:00:00 2001 From: Patrice Duroux Date: Fri, 3 Mar 2023 20:20:56 +0100 Subject: [PATCH 1934/5631] perf tests test_bridge_fdb_stress.sh: Fix redirection of stderr to stdin It's not 2&>1, the correct is 2>&1. Signed-off-by: Patrice Duroux Cc: linux-kselftest@vger.kernel.org Link: https://lore.kernel.org/r/20230303193058.21274-1-patrice.duroux@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- .../testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh index a1f269ee84da..92acab83fbe2 100755 --- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh +++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh @@ -31,7 +31,7 @@ trap 'cleanup' EXIT eth=${NETIFS[p1]} -ip link del br0 2&>1 >/dev/null || : +ip link del br0 2>&1 >/dev/null || : ip link add br0 type bridge && ip link set $eth master br0 (while :; do -- GitLab From 51ea4cb96f35ae2f31d45d9a0dbf30da13bbe441 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 16 Mar 2023 08:49:46 +0100 Subject: [PATCH 1935/5631] perf stat: Suppress warning when using cpum_cf events on s390 Running command perf stat -vv -e cpu_cycles -C0 -- true displays this warning: Attempting to add event pmu 'cpum_cf' with 'cpu_cycles,' that may result in non-fatal errors Make the PMU cpum_cf selectable and avoid this warning. While at it also fix this warning for PMUs pai_crypto and pai_ext. Output before: # ./perf stat -vv -e cpu_cycles -C0 -- true Using CPUID IBM,3931,704,A01,3.7,002f Attempting to add event pmu 'cpum_cf' with 'cpu_cycles,' that may result in non-fatal errors After aliases, add event pmu 'cpum_cf' with 'event,' that may result in non-fatal errors cpu_cycles -> cpum_cf/event=0/ Control descriptor is not initialized ------------------------------------------------------------ perf_event_attr: type 10 size 128 config 0x1001 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 inherit 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 3 cpu_cycles: 0: 290434 2479172 2479172: cpu_cycles: 290434 2479172 2479172 Performance counter stats for 'CPU(s) 0': 290,434 cpu_cycles 0.002465617 seconds time elapsed # Now the warning "Attempting to add event pmu 'cpum_cf' ..." does not show up anymore. Output after: # ./perf stat -vv -e cpu_cycles -C0 -- true Using CPUID IBM,3931,704,A01,3.7,002f After aliases, add event pmu 'cpum_cf' with 'event,' that may result in non-fatal errors cpu_cycles -> cpum_cf/event=0/ Control descriptor is not initialized .... Performance counter stats for 'CPU(s) 0': 357,023 cpu_cycles 0.002454995 seconds time elapsed # Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230316074946.41110-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/util/Build | 1 + tools/perf/arch/s390/util/pmu.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) create mode 100644 tools/perf/arch/s390/util/pmu.c diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build index db6884086997..fa66f15a14ec 100644 --- a/tools/perf/arch/s390/util/Build +++ b/tools/perf/arch/s390/util/Build @@ -6,5 +6,6 @@ perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-y += machine.o +perf-y += pmu.o perf-$(CONFIG_AUXTRACE) += auxtrace.o diff --git a/tools/perf/arch/s390/util/pmu.c b/tools/perf/arch/s390/util/pmu.c new file mode 100644 index 000000000000..11f03f32e3fd --- /dev/null +++ b/tools/perf/arch/s390/util/pmu.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright IBM Corp. 2023 + * Author(s): Thomas Richter + */ + +#include + +#include "../../../util/pmu.h" + +#define S390_PMUPAI_CRYPTO "pai_crypto" +#define S390_PMUPAI_EXT "pai_ext" +#define S390_PMUCPUM_CF "cpum_cf" + +struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu) +{ + if (!strcmp(pmu->name, S390_PMUPAI_CRYPTO) || + !strcmp(pmu->name, S390_PMUPAI_EXT) || + !strcmp(pmu->name, S390_PMUCPUM_CF)) + pmu->selectable = true; + return NULL; +} -- GitLab From ece7f7c0507cc147f72e117e22732091db758885 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 21 Mar 2023 14:57:01 +0800 Subject: [PATCH 1936/5631] perf bench syscall: Add fork syscall benchmark This is a follow up patch for the execve bench which is actually fork + execve, it makes sense to add the fork syscall benchmark to compare the execve part precisely. Some archs have no __NR_fork definition which is used only as a check condition to call test_fork(), let us just define it as -1 to avoid build error. Suggested-by: Namhyung Kim Signed-off-by: Tiezhu Yang Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/1679381821-22736-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/unistd_32.h | 4 +-- tools/arch/x86/include/uapi/asm/unistd_64.h | 3 ++ tools/perf/bench/bench.h | 1 + tools/perf/bench/syscall.c | 35 +++++++++++++++++++++ tools/perf/builtin-bench.c | 1 + 5 files changed, 42 insertions(+), 2 deletions(-) diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 2712d5e03e2e..b8ddfc4c4ab0 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __NR_execve -#define __NR_execve 11 +#ifndef __NR_fork +#define __NR_fork 2 #endif #ifndef __NR_getppid #define __NR_getppid 64 diff --git a/tools/arch/x86/include/uapi/asm/unistd_64.h b/tools/arch/x86/include/uapi/asm/unistd_64.h index a6f7fe84d4df..f70d2cada256 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_64.h +++ b/tools/arch/x86/include/uapi/asm/unistd_64.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NR_fork +#define __NR_fork 57 +#endif #ifndef __NR_execve #define __NR_execve 59 #endif diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index e43893151a3e..edfc25793cca 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -23,6 +23,7 @@ int bench_sched_messaging(int argc, const char **argv); int bench_sched_pipe(int argc, const char **argv); int bench_syscall_basic(int argc, const char **argv); int bench_syscall_getpgid(int argc, const char **argv); +int bench_syscall_fork(int argc, const char **argv); int bench_syscall_execve(int argc, const char **argv); int bench_mem_memcpy(int argc, const char **argv); int bench_mem_memset(int argc, const char **argv); diff --git a/tools/perf/bench/syscall.c b/tools/perf/bench/syscall.c index fe79f7f3091e..ea4dfc07cbd6 100644 --- a/tools/perf/bench/syscall.c +++ b/tools/perf/bench/syscall.c @@ -18,6 +18,10 @@ #include #include +#ifndef __NR_fork +#define __NR_fork -1 +#endif + #define LOOPS_DEFAULT 10000000 static int loops = LOOPS_DEFAULT; @@ -31,6 +35,23 @@ static const char * const bench_syscall_usage[] = { NULL }; +static void test_fork(void) +{ + pid_t pid = fork(); + + if (pid < 0) { + fprintf(stderr, "fork failed\n"); + exit(1); + } else if (pid == 0) { + exit(0); + } else { + if (waitpid(pid, NULL, 0) < 0) { + fprintf(stderr, "waitpid failed\n"); + exit(1); + } + } +} + static void test_execve(void) { const char *pathname = "/bin/true"; @@ -71,6 +92,12 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) case __NR_getpgid: getpgid(0); break; + case __NR_fork: + test_fork(); + /* Only loop 10000 times to save time */ + if (i == 10000) + loops = 10000; + break; case __NR_execve: test_execve(); /* Only loop 10000 times to save time */ @@ -92,6 +119,9 @@ static int bench_syscall_common(int argc, const char **argv, int syscall) case __NR_getpgid: name = "getpgid()"; break; + case __NR_fork: + name = "fork()"; + break; case __NR_execve: name = "execve()"; break; @@ -143,6 +173,11 @@ int bench_syscall_getpgid(int argc, const char **argv) return bench_syscall_common(argc, argv, __NR_getpgid); } +int bench_syscall_fork(int argc, const char **argv) +{ + return bench_syscall_common(argc, argv, __NR_fork); +} + int bench_syscall_execve(int argc, const char **argv) { return bench_syscall_common(argc, argv, __NR_execve); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index 814e9afc86f6..d0fcc3cdc185 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -53,6 +53,7 @@ static struct bench sched_benchmarks[] = { static struct bench syscall_benchmarks[] = { { "basic", "Benchmark for basic getppid(2) calls", bench_syscall_basic }, { "getpgid", "Benchmark for getpgid(2) calls", bench_syscall_getpgid }, + { "fork", "Benchmark for fork(2) calls", bench_syscall_fork }, { "execve", "Benchmark for execve(2) calls", bench_syscall_execve }, { "all", "Run all syscall benchmarks", NULL }, { NULL, NULL, NULL }, -- GitLab From ecd4960d908e27e40b63a7046df2f942c148c6f6 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Fri, 24 Mar 2023 03:27:02 +0000 Subject: [PATCH 1937/5631] perf ftrace: Make system wide the default target for latency subcommand If no target is specified for 'latency' subcommand, the execution fails because - 1 (invalid value) is written to set_ftrace_pid tracefs file. Make system wide the default target, which is the same as the default behavior of 'trace' subcommand. Before the fix: # perf ftrace latency -T schedule failed to set ftrace pid After the fix: # perf ftrace latency -T schedule ^C# DURATION | COUNT | GRAPH | 0 - 1 us | 0 | | 1 - 2 us | 0 | | 2 - 4 us | 0 | | 4 - 8 us | 2828 | #### | 8 - 16 us | 23953 | ######################################## | 16 - 32 us | 408 | | 32 - 64 us | 318 | | 64 - 128 us | 4 | | 128 - 256 us | 3 | | 256 - 512 us | 0 | | 512 - 1024 us | 1 | | 1 - 2 ms | 4 | | 2 - 4 ms | 0 | | 4 - 8 ms | 0 | | 8 - 16 ms | 0 | | 16 - 32 ms | 0 | | 32 - 64 ms | 0 | | 64 - 128 ms | 0 | | 128 - 256 ms | 4 | | 256 - 512 ms | 2 | | 512 - 1024 ms | 0 | | 1 - ... s | 0 | | Fixes: 53be50282269b46c ("perf ftrace: Add 'latency' subcommand") Signed-off-by: Yang Jihong Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230324032702.109964-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-ftrace.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 73d51ce84c3a..810e3376c7d6 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1228,10 +1228,12 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } + /* Make system wide (-a) the default target. */ + if (!argc && target__none(&ftrace.target)) + ftrace.target.system_wide = true; + switch (subcmd) { case PERF_FTRACE_TRACE: - if (!argc && target__none(&ftrace.target)) - ftrace.target.system_wide = true; cmd_func = __cmd_ftrace; break; case PERF_FTRACE_LATENCY: -- GitLab From 5d9df8731c0941f3add30f96745a62586a0c9d52 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Tue, 28 Mar 2023 16:59:08 +0530 Subject: [PATCH 1938/5631] perf vendor events power9: Remove UTF-8 characters from JSON files Commit 3c22ba5243040c13 ("perf vendor events powerpc: Update POWER9 events") added and updated power9 PMU JSON events. However some of the JSON events which are part of other.json and pipeline.json files, contains UTF-8 characters in their brief description. Having UTF-8 character could breaks the perf build on some distros. Fix this issue by removing the UTF-8 characters from other.json and pipeline.json files. Result without the fix: [command]# file -i pmu-events/arch/powerpc/power9/* pmu-events/arch/powerpc/power9/cache.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/floating-point.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/frontend.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/marked.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/memory.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/nest_metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/other.json: application/json; charset=utf-8 pmu-events/arch/powerpc/power9/pipeline.json: application/json; charset=utf-8 pmu-events/arch/powerpc/power9/pmc.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/translation.json: application/json; charset=us-ascii [command]# Result with the fix: [command]# file -i pmu-events/arch/powerpc/power9/* pmu-events/arch/powerpc/power9/cache.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/floating-point.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/frontend.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/marked.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/memory.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/nest_metrics.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/other.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/pipeline.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/pmc.json: application/json; charset=us-ascii pmu-events/arch/powerpc/power9/translation.json: application/json; charset=us-ascii [command]# Fixes: 3c22ba5243040c13 ("perf vendor events powerpc: Update POWER9 events") Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Kajol Jain Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Athira Rajeev Cc: Disha Goel Cc: Jiri Olsa Cc: Madhavan Srinivasan Cc: Sukadev Bhattiprolu Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/lkml/ZBxP77deq7ikTxwG@kernel.org/ Link: https://lore.kernel.org/r/20230328112908.113158-1-kjain@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/powerpc/power9/other.json | 4 ++-- tools/perf/pmu-events/arch/powerpc/power9/pipeline.json | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json index 3f69422c21f9..f10bd554521a 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/other.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json @@ -1417,7 +1417,7 @@ { "EventCode": "0x45054", "EventName": "PM_FMA_CMPL", - "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. " + "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only." }, { "EventCode": "0x201E8", @@ -2017,7 +2017,7 @@ { "EventCode": "0xC0BC", "EventName": "PM_LSU_FLUSH_OTHER", - "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the “bad dval” back and flush all younger ops)" + "BriefDescription": "Other LSU flushes including: Sync (sync ack from L2 caused search of LRQ for oldest snooped load, This will either signal a Precise Flush of the oldest snooped loa or a Flush Next PPC); Data Valid Flush Next (several cases of this, one example is store and reload are lined up such that a store-hit-reload scenario exists and the CDF has already launched and has gotten bad/stale data); Bad Data Valid Flush Next (might be a few cases of this, one example is a larxa (D$ hit) return data and dval but can't allocate to LMQ (LMQ full or other reason). Already gave dval but can't watch it for snoop_hit_larx. Need to take the 'bad dval' back and flush all younger ops)" }, { "EventCode": "0x5094", diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json index d0265f255de2..723bffa41c44 100644 --- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json +++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json @@ -442,7 +442,7 @@ { "EventCode": "0x4D052", "EventName": "PM_2FLOP_CMPL", - "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg " + "BriefDescription": "DP vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres ,fsqrte, fneg" }, { "EventCode": "0x1F142", -- GitLab From c8bb2d76a40ac0ccf6303d369e536fddcde847fb Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 16 Mar 2023 21:41:54 +0200 Subject: [PATCH 1939/5631] perf symbols: Fix use-after-free in get_plt_got_name() Fix use-after-free in get_plt_got_name(). Discovered using EXTRA_CFLAGS="-fsanitize=undefined -fsanitize=address". Fixes: ce4c8e7966f317ef ("perf symbols: Get symbols for .plt.got for x86-64") Reported-by: kernel test robot Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/oe-lkp/202303061424.6ad43294-yujie.liu@intel.com Link: https://lore.kernel.org/r/20230316194156.8320-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index c0a2de42c51b..7ef5f6d7d415 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -557,6 +557,7 @@ static bool get_plt_got_name(GElf_Shdr *shdr, size_t i, const char *sym_name; char *demangled; GElf_Sym sym; + bool result; u32 disp; if (!di->sorted) @@ -583,9 +584,11 @@ static bool get_plt_got_name(GElf_Shdr *shdr, size_t i, snprintf(buf, buf_sz, "%s@plt", sym_name); + result = *sym_name; + free(demangled); - return *sym_name; + return result; } static int dso__synthesize_plt_got_symbols(struct dso *dso, Elf *elf, -- GitLab From a2410b579c72242ac0f77b3768093d8c1b48012e Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 16 Mar 2023 21:41:55 +0200 Subject: [PATCH 1940/5631] perf symbols: Fix unaligned access in get_x86_64_plt_disp() Use memcpy() to avoid unaligned access. Discovered using EXTRA_CFLAGS="-fsanitize=undefined -fsanitize=address". Fixes: ce4c8e7966f317ef ("perf symbols: Get symbols for .plt.got for x86-64") Reported-by: kernel test robot Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/oe-lkp/202303061424.6ad43294-yujie.liu@intel.com Link: https://lore.kernel.org/r/20230316194156.8320-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 7ef5f6d7d415..ae810d4cf3cd 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -542,9 +542,12 @@ static u32 get_x86_64_plt_disp(const u8 *p) n += 1; /* jmp with 4-byte displacement */ if (p[n] == 0xff && p[n + 1] == 0x25) { + u32 disp; + n += 2; /* Also add offset from start of entry to end of instruction */ - return n + 4 + le32toh(*(const u32 *)(p + n)); + memcpy(&disp, p + n, sizeof(disp)); + return n + 4 + le32toh(disp); } return 0; } -- GitLab From f5ceb159d30b87975a49b8a230ffa76bae6684b2 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 16 Mar 2023 21:41:56 +0200 Subject: [PATCH 1941/5631] perf tools: Avoid warning in do_realloc_array_as_needed() do_realloc_array_as_needed() used memcpy() of zero size with a NULL pointer. Check the size first to avoid sanitize warning. Discovered using EXTRA_CFLAGS="-fsanitize=undefined -fsanitize=address". Reported-by: kernel test robot Signed-off-by: Adrian Hunter Acked-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/oe-lkp/202303061424.6ad43294-yujie.liu@intel.com Link: https://lore.kernel.org/r/20230316194156.8320-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/util.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index b356c9f7f0c3..089208b51e68 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -524,7 +524,8 @@ int do_realloc_array_as_needed(void **arr, size_t *arr_sz, size_t x, size_t msz, new_arr = calloc(new_sz, msz); if (!new_arr) return -ENOMEM; - memcpy(new_arr, *arr, *arr_sz * msz); + if (*arr_sz) + memcpy(new_arr, *arr, *arr_sz * msz); if (init_val) { for (i = *arr_sz; i < new_sz; i++) memcpy(new_arr + (i * msz), init_val, msz); -- GitLab From 333b1b11179b7908e3f3a06a2208dcecb0c971ef Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:38 -0700 Subject: [PATCH 1942/5631] perf annotate: Delete session for debug builds Use the debug build indicator as the guide to free the session. This implements a behavior described in a comment, which is consequentially removed. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 4750fac7bf93..98d1b6379230 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -692,16 +692,12 @@ int cmd_annotate(int argc, const char **argv) out_delete: /* - * Speed up the exit process, for large files this can - * take quite a while. - * - * XXX Enable this when using valgrind or if we ever - * librarize this command. - * - * Also experiment with obstacks to see how much speed - * up we'll get here. - * - * perf_session__delete(session); + * Speed up the exit process by only deleting for debug builds. For + * large files this can save time. */ +#ifndef NDEBUG + perf_session__delete(annotate.session); +#endif + return ret; } -- GitLab From 8f08c363fd6c682d10f2b055d4287ad1e54e76ea Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:39 -0700 Subject: [PATCH 1943/5631] perf report: Additional config warnings If the default_sort_order isn't correctly strdup-ed warn and return an error. Debug warn if no option is matched. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-report.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 6400615b5e98..500f9d8902e7 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -143,6 +143,10 @@ static int report__config(const char *var, const char *value, void *cb) if (!strcmp(var, "report.sort_order")) { default_sort_order = strdup(value); + if (!default_sort_order) { + pr_err("Not enough memory for report.sort_order\n"); + return -1; + } return 0; } @@ -151,6 +155,7 @@ static int report__config(const char *var, const char *value, void *cb) return 0; } + pr_debug("%s variable unknown, ignoring...", var); return 0; } -- GitLab From 217b7d41ea2038e52991b7a600a0b958330d8ae6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:40 -0700 Subject: [PATCH 1944/5631] perf annotate: Add init/exit to annotation_options remove default The annotation__default_options global variable was used to initialize annotation_options. Switch to the init/exit pattern as later changes will give ownership over strings and this will be necessary to avoid memory leaks. Committer note: Fix the GTK2=1 build, hist_entry__gtk_annotate() needs to receive a 'struct annotation_options' pointer. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 6 ++++-- tools/perf/builtin-report.c | 7 ++++--- tools/perf/builtin-top.c | 4 +++- tools/perf/ui/gtk/annotate.c | 6 ++++-- tools/perf/ui/gtk/gtk.h | 2 ++ tools/perf/util/annotate.c | 25 +++++++++++++++++-------- tools/perf/util/annotate.h | 5 +++-- 7 files changed, 37 insertions(+), 18 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 98d1b6379230..997a1e65d090 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -352,6 +352,7 @@ static void hists__find_annotations(struct hists *hists, int ret; int (*annotate)(struct hist_entry *he, struct evsel *evsel, + struct annotation_options *options, struct hist_browser_timer *hbt); annotate = dlsym(perf_gtk_handle, @@ -361,7 +362,7 @@ static void hists__find_annotations(struct hists *hists, return; } - ret = annotate(he, evsel, NULL); + ret = annotate(he, evsel, &ann->opts, NULL); if (!ret || !ann->skip_missing) return; @@ -509,7 +510,6 @@ int cmd_annotate(int argc, const char **argv) .ordered_events = true, .ordering_requires_timestamps = true, }, - .opts = annotation__default_options, }; struct perf_data data = { .mode = PERF_DATA_MODE_READ, @@ -598,6 +598,7 @@ int cmd_annotate(int argc, const char **argv) set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE); set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE); + annotation_options__init(&annotate.opts); ret = hists__init(); if (ret < 0) @@ -698,6 +699,7 @@ int cmd_annotate(int argc, const char **argv) #ifndef NDEBUG perf_session__delete(annotate.session); #endif + annotation_options__exit(&annotate.opts); return ret; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 500f9d8902e7..b41e1219d153 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -728,8 +728,7 @@ static int hists__resort_cb(struct hist_entry *he, void *arg) if (rep->symbol_ipc && sym && !sym->annotate2) { struct evsel *evsel = hists_to_evsel(he->hists); - symbol__annotate2(&he->ms, evsel, - &annotation__default_options, NULL); + symbol__annotate2(&he->ms, evsel, &rep->annotation_opts, NULL); } return 0; @@ -1223,7 +1222,6 @@ int cmd_report(int argc, const char **argv) .max_stack = PERF_MAX_STACK_DEPTH, .pretty_printing_style = "normal", .socket_filter = -1, - .annotation_opts = annotation__default_options, .skip_empty = true, }; char *sort_order_help = sort_help("sort by key(s):"); @@ -1403,6 +1401,8 @@ int cmd_report(int argc, const char **argv) if (ret < 0) goto exit; + annotation_options__init(&report.annotation_opts); + ret = perf_config(report__config, &report); if (ret) goto exit; @@ -1706,6 +1706,7 @@ int cmd_report(int argc, const char **argv) zstd_fini(&(session->zstd_data)); perf_session__delete(session); exit: + annotation_options__exit(&report.annotation_opts); free(sort_order_help); free(field_order_help); return ret; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index d4b5b02bab73..592eb827fba9 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1435,7 +1435,6 @@ int cmd_top(int argc, const char **argv) .sample_time_set = true, }, .max_stack = sysctl__max_stack(), - .annotation_opts = annotation__default_options, .nr_threads_synthesize = UINT_MAX, }; struct record_opts *opts = &top.record_opts; @@ -1587,6 +1586,8 @@ int cmd_top(int argc, const char **argv) if (status < 0) return status; + annotation_options__init(&top.annotation_opts); + top.annotation_opts.min_pcnt = 5; top.annotation_opts.context = 4; @@ -1783,6 +1784,7 @@ int cmd_top(int argc, const char **argv) out_delete_evlist: evlist__delete(top.evlist); perf_session__delete(top.session); + annotation_options__exit(&top.annotation_opts); return status; } diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index 0a50e962f9a3..a1c021a6d3c1 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -162,6 +162,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct map_symbol *ms, } static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, + struct annotation_options *options, struct hist_browser_timer *hbt) { struct symbol *sym = ms->sym; @@ -174,7 +175,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, if (ms->map->dso->annotate_warned) return -1; - err = symbol__annotate(ms, evsel, &annotation__default_options, NULL); + err = symbol__annotate(ms, evsel, options, NULL); if (err) { char msg[BUFSIZ]; ms->map->dso->annotate_warned = true; @@ -242,9 +243,10 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, + struct annotation_options *options, struct hist_browser_timer *hbt) { - return symbol__gtk_annotate(&he->ms, evsel, hbt); + return symbol__gtk_annotate(&he->ms, evsel, options, hbt); } void perf_gtk__show_annotations(void) diff --git a/tools/perf/ui/gtk/gtk.h b/tools/perf/ui/gtk/gtk.h index a2b497f03fd6..1e84dceb5267 100644 --- a/tools/perf/ui/gtk/gtk.h +++ b/tools/perf/ui/gtk/gtk.h @@ -56,11 +56,13 @@ struct evsel; struct evlist; struct hist_entry; struct hist_browser_timer; +struct annotation_options; int evlist__gtk_browse_hists(struct evlist *evlist, const char *help, struct hist_browser_timer *hbt, float min_pcnt); int hist_entry__gtk_annotate(struct hist_entry *he, struct evsel *evsel, + struct annotation_options *options, struct hist_browser_timer *hbt); void perf_gtk__show_annotations(void); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index db475e44f42f..a984bdae7811 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -55,14 +55,6 @@ #include -struct annotation_options annotation__default_options = { - .use_offset = true, - .jump_arrows = true, - .annotate_src = true, - .offset_level = ANNOTATION__OFFSET_JUMP_TARGETS, - .percent_type = PERCENT_PERIOD_LOCAL, -}; - static regex_t file_lineno; static struct ins_ops *ins__find(struct arch *arch, const char *name); @@ -3226,6 +3218,23 @@ static int annotation__config(const char *var, const char *value, void *data) return 0; } +void annotation_options__init(struct annotation_options *opt) +{ + memset(opt, 0, sizeof(*opt)); + + /* Default values. */ + opt->use_offset = true; + opt->jump_arrows = true; + opt->annotate_src = true; + opt->offset_level = ANNOTATION__OFFSET_JUMP_TARGETS; + opt->percent_type = PERCENT_PERIOD_LOCAL; +} + + +void annotation_options__exit(struct annotation_options *opt __maybe_unused) +{ +} + void annotation_config__init(struct annotation_options *opt) { perf_config(annotation__config, opt); diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 8934072c39e6..e7238c694465 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -109,8 +109,6 @@ enum { #define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS -extern struct annotation_options annotation__default_options; - struct annotation; struct sym_hist_entry { @@ -418,6 +416,9 @@ static inline int symbol__tui_annotate(struct map_symbol *ms __maybe_unused, } #endif +void annotation_options__init(struct annotation_options *opt); +void annotation_options__exit(struct annotation_options *opt); + void annotation_config__init(struct annotation_options *opt); int annotate_parse_percent_type(const struct option *opt, const char *_str, -- GitLab From 56d9117c5004e7192d8062da67fef220e4fdcd19 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:41 -0700 Subject: [PATCH 1945/5631] perf annotate: Own objdump_path and disassembler_style strings Make struct annotation_options own the strings objdump_path and disassembler_style, freeing them on exit. Add missing strdup for disassembler_style when read from a config file. Committer notes: Converted free(obj->member) to zfree(&obj->member) in annotation_options__exit() Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/common.c | 4 ++-- tools/perf/arch/common.h | 2 +- tools/perf/builtin-annotate.c | 16 ++++++++++++++-- tools/perf/builtin-report.c | 16 ++++++++++++++-- tools/perf/builtin-top.c | 17 +++++++++++++++-- tools/perf/util/annotate.c | 10 ++++++++-- tools/perf/util/annotate.h | 4 ++-- 7 files changed, 56 insertions(+), 13 deletions(-) diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c index 59dd875fd5e4..28ac09997928 100644 --- a/tools/perf/arch/common.c +++ b/tools/perf/arch/common.c @@ -130,7 +130,7 @@ static int lookup_triplets(const char *const *triplets, const char *name) } static int perf_env__lookup_binutils_path(struct perf_env *env, - const char *name, const char **path) + const char *name, char **path) { int idx; const char *arch = perf_env__arch(env), *cross_env; @@ -202,7 +202,7 @@ static int perf_env__lookup_binutils_path(struct perf_env *env, return -1; } -int perf_env__lookup_objdump(struct perf_env *env, const char **path) +int perf_env__lookup_objdump(struct perf_env *env, char **path) { /* * For live mode, env->arch will be NULL and we can use diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h index e965ed8bb328..4224c299cc70 100644 --- a/tools/perf/arch/common.h +++ b/tools/perf/arch/common.h @@ -6,7 +6,7 @@ struct perf_env; -int perf_env__lookup_objdump(struct perf_env *env, const char **path); +int perf_env__lookup_objdump(struct perf_env *env, char **path); bool perf_env__single_address_space(struct perf_env *env); #endif /* ARCH_PERF_COMMON_H */ diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 997a1e65d090..5b31c4ee8d06 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -517,6 +517,7 @@ int cmd_annotate(int argc, const char **argv) struct itrace_synth_opts itrace_synth_opts = { .set = 0, }; + const char *disassembler_style = NULL, *objdump_path = NULL; struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -561,13 +562,13 @@ int cmd_annotate(int argc, const char **argv) "Interleave source code with assembly code (default)"), OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "prefix", &annotate.opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), OPT_STRING(0, "prefix-strip", &annotate.opts.prefix_strip, "N", "Strip first N entries of source file path name in programs (with --prefix)"), - OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path", + OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Enable symbol demangling"), @@ -618,6 +619,17 @@ int cmd_annotate(int argc, const char **argv) annotate.sym_hist_filter = argv[0]; } + if (disassembler_style) { + annotate.opts.disassembler_style = strdup(disassembler_style); + if (!annotate.opts.disassembler_style) + return -ENOMEM; + } + if (objdump_path) { + annotate.opts.objdump_path = strdup(objdump_path); + if (!annotate.opts.objdump_path) + return -ENOMEM; + } + if (annotate_check_args(&annotate.opts) < 0) return -EINVAL; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b41e1219d153..15b0cf649e1a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1226,6 +1226,7 @@ int cmd_report(int argc, const char **argv) }; char *sort_order_help = sort_help("sort by key(s):"); char *field_order_help = sort_help("output field(s): overhead period sample "); + const char *disassembler_style = NULL, *objdump_path = NULL; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1322,7 +1323,7 @@ int cmd_report(int argc, const char **argv) "Interleave source code with assembly code (default)"), OPT_BOOLEAN(0, "asm-raw", &report.annotation_opts.show_asm_raw, "Display raw encoding of assembly instructions (default)"), - OPT_STRING('M', "disassembler-style", &report.annotation_opts.disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "prefix", &report.annotation_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), @@ -1341,7 +1342,7 @@ int cmd_report(int argc, const char **argv) parse_branch_mode), OPT_BOOLEAN(0, "branch-history", &branch_call_mode, "add last branch records to call history"), - OPT_STRING(0, "objdump", &report.annotation_opts.objdump_path, "path", + OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Disable symbol demangling"), @@ -1419,6 +1420,17 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } + if (disassembler_style) { + report.annotation_opts.disassembler_style = strdup(disassembler_style); + if (!report.annotation_opts.disassembler_style) + return -ENOMEM; + } + if (objdump_path) { + report.annotation_opts.objdump_path = strdup(objdump_path); + if (!report.annotation_opts.objdump_path) + return -ENOMEM; + } + if (annotate_check_args(&report.annotation_opts) < 0) { ret = -EINVAL; goto exit; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 592eb827fba9..57a273cd03de 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1439,6 +1439,7 @@ int cmd_top(int argc, const char **argv) }; struct record_opts *opts = &top.record_opts; struct target *target = &opts->target; + const char *disassembler_style = NULL, *objdump_path = NULL; const struct option options[] = { OPT_CALLBACK('e', "event", &top.evlist, "event", "event selector. use 'perf list' to list available events", @@ -1524,9 +1525,9 @@ int cmd_top(int argc, const char **argv) OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, "Enable kernel symbol demangling"), OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"), - OPT_STRING(0, "objdump", &top.annotation_opts.objdump_path, "path", + OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), - OPT_STRING('M', "disassembler-style", &top.annotation_opts.disassembler_style, "disassembler style", + OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix", "Add prefix to source file path names in programs (with --prefix-strip)"), @@ -1618,6 +1619,18 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); + if (disassembler_style) { + top.annotation_opts.disassembler_style = strdup(disassembler_style); + if (!top.annotation_opts.disassembler_style) + return -ENOMEM; + } + if (objdump_path) { + top.annotation_opts.objdump_path = strdup(objdump_path); + if (!top.annotation_opts.objdump_path) + return -ENOMEM; + } + + status = symbol__validate_sym_arguments(); if (status) goto out_delete_evlist; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index a984bdae7811..08e041a9b9cc 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -3206,7 +3206,11 @@ static int annotation__config(const char *var, const char *value, void *data) } else if (!strcmp(var, "annotate.use_offset")) { opt->use_offset = perf_config_bool("use_offset", value); } else if (!strcmp(var, "annotate.disassembler_style")) { - opt->disassembler_style = value; + opt->disassembler_style = strdup(value); + if (!opt->disassembler_style) { + pr_err("Not enough memory for annotate.disassembler_style\n"); + return -1; + } } else if (!strcmp(var, "annotate.demangle")) { symbol_conf.demangle = perf_config_bool("demangle", value); } else if (!strcmp(var, "annotate.demangle_kernel")) { @@ -3231,8 +3235,10 @@ void annotation_options__init(struct annotation_options *opt) } -void annotation_options__exit(struct annotation_options *opt __maybe_unused) +void annotation_options__exit(struct annotation_options *opt) { + zfree(&opt->disassembler_style); + zfree(&opt->objdump_path); } void annotation_config__init(struct annotation_options *opt) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index e7238c694465..1c6335b8333a 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -94,8 +94,8 @@ struct annotation_options { int min_pcnt; int max_lines; int context; - const char *objdump_path; - const char *disassembler_style; + char *objdump_path; + char *disassembler_style; const char *prefix; const char *prefix_strip; unsigned int percent_type; -- GitLab From 0b02b47e71fa0e006407efd4f647b0e1336a2e8c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:42 -0700 Subject: [PATCH 1946/5631] perf annotate: Allow objdump to be set in perfconfig Allow the setting of the objdump command in the perfconfig. Update man page for this new option. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-config.txt | 5 ++++- tools/perf/util/annotate.c | 6 ++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 39c890ead2dc..697f7f924545 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -250,7 +250,10 @@ annotate.*:: These are in control of addresses, jump function, source code in lines of assembly code from a specific program. - annotate.disassembler_style: + annotate.objdump:: + objdump binary to use for disassembly and annotations. + + annotate.disassembler_style:: Use this to change the default disassembler style to some other value supported by binutils, such as "intel", see the '-M' option help in the 'objdump' man page. diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 08e041a9b9cc..317c987d3001 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -3211,6 +3211,12 @@ static int annotation__config(const char *var, const char *value, void *data) pr_err("Not enough memory for annotate.disassembler_style\n"); return -1; } + } else if (!strcmp(var, "annotate.objdump")) { + opt->objdump_path = strdup(value); + if (!opt->objdump_path) { + pr_err("Not enough memory for annotate.objdump\n"); + return -1; + } } else if (!strcmp(var, "annotate.demangle")) { symbol_conf.demangle = perf_config_bool("demangle", value); } else if (!strcmp(var, "annotate.demangle_kernel")) { -- GitLab From 57594454ceb92defaa0707cf29289f0c3c266ede Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:55:43 -0700 Subject: [PATCH 1947/5631] perf symbol: Add command line support for addr2line path Allow addr2line to be set either on the command line or via the perfconfig file. This doesn't currently work with llvm-addr2line as the addr2line code emits two things: 1) the address to decode, 2) a bogus ',' value. The expectation is the bogus value will generate: ?? ??:0 that terminates the addr2line reading. However, the output from llvm-addr2line is a single line with just the input ',' locking up the addr2line reading that is expecting a second line. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Andres Freund Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Sandipan Das Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230328235543.1082207-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-annotate.txt | 3 +++ tools/perf/Documentation/perf-config.txt | 3 +++ tools/perf/Documentation/perf-report.txt | 3 +++ tools/perf/Documentation/perf-top.txt | 6 +++++ tools/perf/builtin-annotate.c | 9 +++++++- tools/perf/builtin-report.c | 9 +++++++- tools/perf/builtin-top.c | 10 +++++++-- tools/perf/util/annotate.c | 6 +++++ tools/perf/util/srcline.c | 26 +++++++++++++--------- tools/perf/util/symbol_conf.h | 1 + 10 files changed, 62 insertions(+), 14 deletions(-) diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt index 980fe2c29275..fe168e8165c8 100644 --- a/tools/perf/Documentation/perf-annotate.txt +++ b/tools/perf/Documentation/perf-annotate.txt @@ -116,6 +116,9 @@ include::itrace.txt[] -M:: --disassembler-style=:: Set disassembler style for objdump. +--addr2line=:: + Path to addr2line binary. + --objdump=:: Path to objdump binary. diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt index 697f7f924545..e56ae54805a8 100644 --- a/tools/perf/Documentation/perf-config.txt +++ b/tools/perf/Documentation/perf-config.txt @@ -250,6 +250,9 @@ annotate.*:: These are in control of addresses, jump function, source code in lines of assembly code from a specific program. + annotate.addr2line:: + addr2line binary to use for file names and line numbers. + annotate.objdump:: objdump binary to use for disassembly and annotations. diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index cfd502f7e6da..af068b4f1e5a 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -381,6 +381,9 @@ OPTIONS This allows to examine the path the program took to each sample. The data collection must have used -b (or -j) and -g. +--addr2line=:: + Path to addr2line binary. + --objdump=:: Path to objdump binary. diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index c60e615b7183..619cc8143ad5 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -161,6 +161,12 @@ Default is to monitor all CPUS. -M:: --disassembler-style=:: Set disassembler style for objdump. +--addr2line=:: + Path to addr2line binary. + +--objdump=:: + Path to objdump binary. + --prefix=PREFIX:: --prefix-strip=N:: Remove first N entries from source file path names in executables diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 5b31c4ee8d06..655987afef58 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -517,7 +517,7 @@ int cmd_annotate(int argc, const char **argv) struct itrace_synth_opts itrace_synth_opts = { .set = 0, }; - const char *disassembler_style = NULL, *objdump_path = NULL; + const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -570,6 +570,8 @@ int cmd_annotate(int argc, const char **argv) "Strip first N entries of source file path name in programs (with --prefix)"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_STRING(0, "addr2line", &addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Enable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, @@ -629,6 +631,11 @@ int cmd_annotate(int argc, const char **argv) if (!annotate.opts.objdump_path) return -ENOMEM; } + if (addr2line_path) { + symbol_conf.addr2line_path = strdup(addr2line_path); + if (!symbol_conf.addr2line_path) + return -ENOMEM; + } if (annotate_check_args(&annotate.opts) < 0) return -EINVAL; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 15b0cf649e1a..4011abc03d0d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1226,7 +1226,7 @@ int cmd_report(int argc, const char **argv) }; char *sort_order_help = sort_help("sort by key(s):"); char *field_order_help = sort_help("output field(s): overhead period sample "); - const char *disassembler_style = NULL, *objdump_path = NULL; + const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; const struct option options[] = { OPT_STRING('i', "input", &input_name, "file", "input file name"), @@ -1344,6 +1344,8 @@ int cmd_report(int argc, const char **argv) "add last branch records to call history"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_STRING(0, "addr2line", &addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle, "Disable symbol demangling"), OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel, @@ -1430,6 +1432,11 @@ int cmd_report(int argc, const char **argv) if (!report.annotation_opts.objdump_path) return -ENOMEM; } + if (addr2line_path) { + symbol_conf.addr2line_path = strdup(addr2line_path); + if (!symbol_conf.addr2line_path) + return -ENOMEM; + } if (annotate_check_args(&report.annotation_opts) < 0) { ret = -EINVAL; diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 57a273cd03de..82c6c065830d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1439,7 +1439,7 @@ int cmd_top(int argc, const char **argv) }; struct record_opts *opts = &top.record_opts; struct target *target = &opts->target; - const char *disassembler_style = NULL, *objdump_path = NULL; + const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; const struct option options[] = { OPT_CALLBACK('e', "event", &top.evlist, "event", "event selector. use 'perf list' to list available events", @@ -1527,6 +1527,8 @@ int cmd_top(int argc, const char **argv) OPT_BOOLEAN(0, "no-bpf-event", &top.record_opts.no_bpf_event, "do not record bpf events"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_STRING(0, "addr2line", &addr2line_path, "path", + "addr2line binary to use for line numbers"), OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style", "Specify disassembler style (e.g. -M intel for intel syntax)"), OPT_STRING(0, "prefix", &top.annotation_opts.prefix, "prefix", @@ -1629,7 +1631,11 @@ int cmd_top(int argc, const char **argv) if (!top.annotation_opts.objdump_path) return -ENOMEM; } - + if (addr2line_path) { + symbol_conf.addr2line_path = strdup(addr2line_path); + if (!symbol_conf.addr2line_path) + return -ENOMEM; + } status = symbol__validate_sym_arguments(); if (status) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 317c987d3001..f47b5dde66bc 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -3217,6 +3217,12 @@ static int annotation__config(const char *var, const char *value, void *data) pr_err("Not enough memory for annotate.objdump\n"); return -1; } + } else if (!strcmp(var, "annotate.addr2line")) { + symbol_conf.addr2line_path = strdup(value); + if (!symbol_conf.addr2line_path) { + pr_err("Not enough memory for annotate.addr2line\n"); + return -1; + } } else if (!strcmp(var, "annotate.demangle")) { symbol_conf.demangle = perf_config_bool("demangle", value); } else if (!strcmp(var, "annotate.demangle_kernel")) { diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 33321867416b..f0a96a834e4b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -414,9 +414,14 @@ static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l) free(a2l); } -static struct a2l_subprocess *addr2line_subprocess_init(const char *path) -{ - const char *argv[] = { "addr2line", "-e", path, "-i", "-f", NULL }; +static struct a2l_subprocess *addr2line_subprocess_init(const char *addr2line_path, + const char *binary_path) +{ + const char *argv[] = { + addr2line_path ?: "addr2line", + "-e", binary_path, + "-i", "-f", NULL + }; struct a2l_subprocess *a2l = zalloc(sizeof(*a2l)); int start_command_status = 0; @@ -436,21 +441,22 @@ static struct a2l_subprocess *addr2line_subprocess_init(const char *path) a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */ if (start_command_status != 0) { - pr_warning("could not start addr2line for %s: start_command return code %d\n", - path, - start_command_status); + pr_warning("could not start addr2line (%s) for %s: start_command return code %d\n", + addr2line_path, binary_path, start_command_status); goto out; } a2l->to_child = fdopen(a2l->addr2line.in, "w"); if (a2l->to_child == NULL) { - pr_warning("could not open write-stream to addr2line of %s\n", path); + pr_warning("could not open write-stream to addr2line (%s) of %s\n", + addr2line_path, binary_path); goto out; } a2l->from_child = fdopen(a2l->addr2line.out, "r"); if (a2l->from_child == NULL) { - pr_warning("could not open read-stream from addr2line of %s\n", path); + pr_warning("could not open read-stream from addr2line (%s) of %s\n", + addr2line_path, binary_path); goto out; } @@ -490,7 +496,6 @@ static int read_addr2line_record(struct a2l_subprocess *a2l, if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) goto error; - if (function != NULL) *function = strdup(strim(line)); @@ -553,7 +558,8 @@ static int addr2line(const char *dso_name, u64 addr, if (!filename__has_section(dso_name, ".debug_line")) goto out; - dso->a2l = addr2line_subprocess_init(dso_name); + dso->a2l = addr2line_subprocess_init(symbol_conf.addr2line_path, + dso_name); a2l = dso->a2l; } diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index bc3d046fbb63..5accd8e69ad2 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -61,6 +61,7 @@ struct symbol_conf { *sym_list_str, *col_width_list_str, *bt_stop_list_str; + char *addr2line_path; unsigned long time_quantum; struct strlist *dso_list, *comm_list, -- GitLab From 0372358a094011663e86f695e81be3b96a93b468 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 29 Mar 2023 09:23:18 -0700 Subject: [PATCH 1948/5631] perf vendor events: Update Alderlake for E-Core TMA v2.3 https://github.com/intel/perfmon/pull/65 Generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py The PR notes state: - E-Core TMA version 2.3. - FP_UOPS changed to FPDIV_Uops - Added BR_MISP breakdown stats - Frontend_Bandwidth/Latency changed to Fetch_Bandwidth/Latency - Load_Store_Bound changed to Memory_Bound - Icache changed to ICache_Misses - ITLB changed to ITLB_Misses - Store_Fwd changed to Store_Fwd_Blk Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230329162318.1227114-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlake/adl-metrics.json | 132 +++++++++++------- .../arch/x86/alderlaken/adln-metrics.json | 120 +++++++++------- 2 files changed, 148 insertions(+), 104 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 7bb8410a2bf9..75d80e70e5cd 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -169,7 +169,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_detect", "MetricThreshold": "tma_branch_detect > 0.05", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", @@ -188,7 +188,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteer", "MetricThreshold": "tma_branch_resteer > 0.05", "ScaleUnit": "100%", @@ -197,7 +197,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_cisc", "MetricThreshold": "tma_cisc > 0.05", "ScaleUnit": "100%", @@ -205,7 +205,7 @@ }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls.", - "MetricExpr": "max(0, tma_backend_bound - tma_load_store_bound)", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", @@ -215,7 +215,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_decode", "MetricThreshold": "tma_decode > 0.05", "ScaleUnit": "100%", @@ -234,7 +234,7 @@ "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1", "ScaleUnit": "100%", @@ -249,6 +249,24 @@ "ScaleUnit": "100%", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.15", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.", "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", @@ -259,20 +277,11 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", + "BriefDescription": "Counts the number of floating point divide operations per uop.", "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", - "MetricName": "tma_fp_uops", - "MetricThreshold": "tma_fp_uops > 0.2", - "ScaleUnit": "100%", - "Unit": "cpu_atom" - }, - { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_frontend_bandwidth", - "MetricThreshold": "tma_frontend_bandwidth > 0.1", + "MetricName": "tma_fpdiv_uops", + "MetricThreshold": "tma_fpdiv_uops > 0.2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -285,21 +294,12 @@ "ScaleUnit": "100%", "Unit": "cpu_atom" }, - { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_frontend_latency", - "MetricThreshold": "tma_frontend_latency > 0.15", - "ScaleUnit": "100%", - "Unit": "cpu_atom" - }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", - "MetricName": "tma_icache", - "MetricThreshold": "tma_icache > 0.05", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -443,7 +443,31 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", + "MetricExpr": "INST_RETIRED.ANY / (BR_MISP_RETIRED.COND - BR_MISP_RETIRED.COND_TAKEN)", + "MetricName": "tma_info_ipmisp_cond_ntaken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricName": "tma_info_ipmisp_cond_taken", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricName": "tma_info_ipmisp_indirect", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired return Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN", + "MetricName": "tma_info_ipmisp_ret", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Instructions per retired Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": " ", "MetricName": "tma_info_ipmispredict", @@ -520,16 +544,16 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", - "MetricName": "tma_itlb", - "MetricThreshold": "tma_itlb > 0.05", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05", "ScaleUnit": "100%", "Unit": "cpu_atom" }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1", "ScaleUnit": "100%", @@ -539,7 +563,7 @@ "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.1", "ScaleUnit": "100%", @@ -548,7 +572,7 @@ { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.1", "ScaleUnit": "100%", @@ -563,15 +587,6 @@ "ScaleUnit": "100%", "Unit": "cpu_atom" }, - { - "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_load_store_bound", - "MetricThreshold": "tma_load_store_bound > 0.2", - "ScaleUnit": "100%", - "Unit": "cpu_atom" - }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", @@ -590,6 +605,15 @@ "ScaleUnit": "100%", "Unit": "cpu_atom" }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2", + "ScaleUnit": "100%", + "Unit": "cpu_atom" + }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.", "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", @@ -630,7 +654,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_other_fb", "MetricThreshold": "tma_other_fb > 0.05", "ScaleUnit": "100%", @@ -647,8 +671,8 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", - "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricExpr": "max(0, tma_memory_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_other_load_store", "MetricThreshold": "tma_other_load_store > 0.1", "ScaleUnit": "100%", @@ -675,7 +699,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_predecode", "MetricThreshold": "tma_predecode > 0.05", "ScaleUnit": "100%", @@ -775,7 +799,7 @@ { "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.1", "ScaleUnit": "100%", @@ -785,8 +809,8 @@ "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd", - "MetricThreshold": "tma_store_fwd > 0.05", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.05", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -2084,7 +2108,7 @@ }, { "BriefDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck", - "MetricExpr": "topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 0 * tma_info_slots", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 5078c468480f..1a85d935c733 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -130,7 +130,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_DETECT / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_detect", "MetricThreshold": "tma_branch_detect > 0.05", "PublicDescription": "Counts the number of issue slots that were not delivered by the frontend due to BACLEARS, which occurs when the Branch Target Buffer (BTB) prediction or lack thereof, was corrected by a later branch predictor in the frontend. Includes BACLEARS due to all branch types including conditional and unconditional jumps, returns, and indirect branches.", @@ -147,7 +147,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to BTCLEARS, which occurs when the Branch Target Buffer (BTB) predicts a taken branch.", "MetricExpr": "TOPDOWN_FE_BOUND.BRANCH_RESTEER / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", "MetricName": "tma_branch_resteer", "MetricThreshold": "tma_branch_resteer > 0.05", "ScaleUnit": "100%" @@ -155,14 +155,14 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to the microcode sequencer (MS).", "MetricExpr": "TOPDOWN_FE_BOUND.CISC / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_cisc", "MetricThreshold": "tma_cisc > 0.05", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles due to backend bound stalls that are core execution bound and not attributed to outstanding demand load or store stalls.", - "MetricExpr": "max(0, tma_backend_bound - tma_load_store_bound)", + "MetricExpr": "max(0, tma_backend_bound - tma_memory_bound)", "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", @@ -171,7 +171,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to decode stalls.", "MetricExpr": "TOPDOWN_FE_BOUND.DECODE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_decode", "MetricThreshold": "tma_decode > 0.05", "ScaleUnit": "100%" @@ -188,7 +188,7 @@ "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hit in DRAM or MMIO (Non-DRAM).", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_DRAM_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_DRAM_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_dram_bound", "MetricThreshold": "tma_dram_bound > 0.1", "ScaleUnit": "100%" @@ -201,6 +201,22 @@ "MetricThreshold": "tma_fast_nuke > 0.05", "ScaleUnit": "100%" }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_bandwidth", + "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "ScaleUnit": "100%" + }, + { + "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", + "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", + "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", + "MetricName": "tma_fetch_latency", + "MetricThreshold": "tma_fetch_latency > 0.15", + "ScaleUnit": "100%" + }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to FP assists.", "MetricExpr": "tma_nuke * (MACHINE_CLEARS.FP_ASSIST / MACHINE_CLEARS.SLOW)", @@ -210,19 +226,11 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the number of floating point operations per uop with all default weighting.", + "BriefDescription": "Counts the number of floating point divide operations per uop.", "MetricExpr": "UOPS_RETIRED.FPDIV / tma_info_slots", "MetricGroup": "TopdownL3;tma_L3_group;tma_base_group", - "MetricName": "tma_fp_uops", - "MetricThreshold": "tma_fp_uops > 0.2", - "ScaleUnit": "100%" - }, - { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_BANDWIDTH / tma_info_slots", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_frontend_bandwidth", - "MetricThreshold": "tma_frontend_bandwidth > 0.1", + "MetricName": "tma_fpdiv_uops", + "MetricThreshold": "tma_fpdiv_uops > 0.2", "ScaleUnit": "100%" }, { @@ -233,20 +241,12 @@ "MetricThreshold": "tma_frontend_bound > 0.2", "ScaleUnit": "100%" }, - { - "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to frontend bandwidth restrictions due to decode, predecode, cisc, and other limitations.", - "MetricExpr": "TOPDOWN_FE_BOUND.FRONTEND_LATENCY / tma_info_slots", - "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", - "MetricName": "tma_frontend_latency", - "MetricThreshold": "tma_frontend_latency > 0.15", - "ScaleUnit": "100%" - }, { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to instruction cache misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ICACHE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", - "MetricName": "tma_icache", - "MetricThreshold": "tma_icache > 0.05", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_icache_misses", + "MetricThreshold": "tma_icache_misses > 0.05", "ScaleUnit": "100%" }, { @@ -369,7 +369,27 @@ "MetricName": "tma_info_ipload" }, { - "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction", + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was not taken", + "MetricExpr": "INST_RETIRED.ANY / (BR_MISP_RETIRED.COND - BR_MISP_RETIRED.COND_TAKEN)", + "MetricName": "tma_info_ipmisp_cond_ntaken" + }, + { + "BriefDescription": "Instructions per retired conditional Branch Misprediction where the branch was taken", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.COND_TAKEN", + "MetricName": "tma_info_ipmisp_cond_taken" + }, + { + "BriefDescription": "Instructions per retired indirect call or jump Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.INDIRECT", + "MetricName": "tma_info_ipmisp_indirect" + }, + { + "BriefDescription": "Instructions per retired return Branch Misprediction", + "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.RETURN", + "MetricName": "tma_info_ipmisp_ret" + }, + { + "BriefDescription": "Instructions per retired Branch Misprediction", "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES", "MetricGroup": " ", "MetricName": "tma_info_ipmispredict" @@ -435,15 +455,15 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to Instruction Table Lookaside Buffer (ITLB) misses.", "MetricExpr": "TOPDOWN_FE_BOUND.ITLB / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_latency_group", - "MetricName": "tma_itlb", - "MetricThreshold": "tma_itlb > 0.05", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_latency_group", + "MetricName": "tma_itlb_misses", + "MetricThreshold": "tma_itlb_misses > 0.05", "ScaleUnit": "100%" }, { "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a load block.", "MetricExpr": "LD_HEAD.L1_BOUND_AT_RET / tma_info_clks", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l1_bound", "MetricThreshold": "tma_l1_bound > 0.1", "ScaleUnit": "100%" @@ -452,7 +472,7 @@ "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the L2 Cache.", "MetricConstraint": "NO_GROUP_EVENTS", "MetricExpr": "MEM_BOUND_STALLS.LOAD_L2_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_L2_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l2_bound", "MetricThreshold": "tma_l2_bound > 0.1", "ScaleUnit": "100%" @@ -460,7 +480,7 @@ { "BriefDescription": "Counts the number of cycles a core is stalled due to a demand load which hit in the Last Level Cache (LLC) or other core with HITE/F/M.", "MetricExpr": "MEM_BOUND_STALLS.LOAD_LLC_HIT / tma_info_clks - MEM_BOUND_STALLS_AT_RET_CORRECTION * MEM_BOUND_STALLS.LOAD_LLC_HIT / MEM_BOUND_STALLS.LOAD", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_l3_bound", "MetricThreshold": "tma_l3_bound > 0.1", "ScaleUnit": "100%" @@ -473,14 +493,6 @@ "MetricThreshold": "tma_ld_buffer > 0.05", "ScaleUnit": "100%" }, - { - "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", - "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", - "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", - "MetricName": "tma_load_store_bound", - "MetricThreshold": "tma_load_store_bound > 0.2", - "ScaleUnit": "100%" - }, { "BriefDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a machine clear (nuke) of any kind including memory ordering and memory disambiguation.", "MetricExpr": "TOPDOWN_BAD_SPECULATION.MACHINE_CLEARS / tma_info_slots", @@ -497,6 +509,14 @@ "MetricThreshold": "tma_mem_scheduler > 0.1", "ScaleUnit": "100%" }, + { + "BriefDescription": "Counts the number of cycles the core is stalled due to stores or loads.", + "MetricExpr": "min(tma_backend_bound, LD_HEAD.ANY_AT_RET / tma_info_clks + tma_store_bound)", + "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", + "MetricName": "tma_memory_bound", + "MetricThreshold": "tma_memory_bound > 0.2", + "ScaleUnit": "100%" + }, { "BriefDescription": "Counts the number of machine clears relative to the number of nuke slots due to memory ordering.", "MetricExpr": "tma_nuke * (MACHINE_CLEARS.MEMORY_ORDERING / MACHINE_CLEARS.SLOW)", @@ -533,7 +553,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to other common frontend stalls not categorized.", "MetricExpr": "TOPDOWN_FE_BOUND.OTHER / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_other_fb", "MetricThreshold": "tma_other_fb > 0.05", "ScaleUnit": "100%" @@ -548,8 +568,8 @@ }, { "BriefDescription": "Counts the number of cycles the core is stalled due to a demand load miss which hits in the L2, LLC, DRAM or MMIO (Non-DRAM) but could not be correctly attributed or cycles in which the load miss is waiting on a request buffer.", - "MetricExpr": "max(0, tma_load_store_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricExpr": "max(0, tma_memory_bound - (tma_store_bound + tma_l1_bound + tma_l2_bound + tma_l3_bound + tma_dram_bound))", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_other_load_store", "MetricThreshold": "tma_other_load_store > 0.1", "ScaleUnit": "100%" @@ -573,7 +593,7 @@ { "BriefDescription": "Counts the number of issue slots that were not delivered by the frontend due to wrong predecodes.", "MetricExpr": "TOPDOWN_FE_BOUND.PREDECODE / tma_info_slots", - "MetricGroup": "TopdownL3;tma_L3_group;tma_frontend_bandwidth_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_fetch_bandwidth_group", "MetricName": "tma_predecode", "MetricThreshold": "tma_predecode > 0.05", "ScaleUnit": "100%" @@ -662,7 +682,7 @@ { "BriefDescription": "Counts the number of cycles the core is stalled due to store buffer full.", "MetricExpr": "tma_mem_scheduler * (MEM_SCHEDULER_BLOCK.ST_BUF / MEM_SCHEDULER_BLOCK.ALL)", - "MetricGroup": "TopdownL3;tma_L3_group;tma_load_store_bound_group", + "MetricGroup": "TopdownL3;tma_L3_group;tma_memory_bound_group", "MetricName": "tma_store_bound", "MetricThreshold": "tma_store_bound > 0.1", "ScaleUnit": "100%" @@ -671,8 +691,8 @@ "BriefDescription": "Counts the number of cycles that the oldest load of the load buffer is stalled at retirement due to a store forward block.", "MetricExpr": "LD_HEAD.ST_ADDR_AT_RET / tma_info_clks", "MetricGroup": "TopdownL4;tma_L4_group;tma_l1_bound_group", - "MetricName": "tma_store_fwd", - "MetricThreshold": "tma_store_fwd > 0.05", + "MetricName": "tma_store_fwd_blk", + "MetricThreshold": "tma_store_fwd_blk > 0.05", "ScaleUnit": "100%" } ] -- GitLab From d1babea9c38282b58a6f822ab95027cba3165a42 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 30 Mar 2023 11:38:25 -0700 Subject: [PATCH 1949/5631] perf bench: Avoid NDEBUG warning With NDEBUG set the asserts are compiled out. This yields "unused-but-set-variable" variables. Move these variables behind NDEBUG to avoid the warning. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Sean Christopherson Link: https://lore.kernel.org/r/20230330183827.1412303-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/find-bit-bench.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/perf/bench/find-bit-bench.c b/tools/perf/bench/find-bit-bench.c index d103c3136983..7e25b0e413f6 100644 --- a/tools/perf/bench/find-bit-bench.c +++ b/tools/perf/bench/find-bit-bench.c @@ -61,7 +61,6 @@ static int do_for_each_set_bit(unsigned int num_bits) double time_average, time_stddev; unsigned int bit, i, j; unsigned int set_bits, skip; - unsigned int old; init_stats(&fb_time_stats); init_stats(&tb_time_stats); @@ -73,7 +72,10 @@ static int do_for_each_set_bit(unsigned int num_bits) __set_bit(i, to_test); for (i = 0; i < outer_iterations; i++) { - old = accumulator; +#ifndef NDEBUG + unsigned int old = accumulator; +#endif + gettimeofday(&start, NULL); for (j = 0; j < inner_iterations; j++) { for_each_set_bit(bit, to_test, num_bits) @@ -85,7 +87,9 @@ static int do_for_each_set_bit(unsigned int num_bits) runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; update_stats(&fb_time_stats, runtime_us); +#ifndef NDEBUG old = accumulator; +#endif gettimeofday(&start, NULL); for (j = 0; j < inner_iterations; j++) { for (bit = 0; bit < num_bits; bit++) { -- GitLab From 984a785f25e5b5db5fa673130b60dca6ca794406 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 30 Mar 2023 11:38:26 -0700 Subject: [PATCH 1950/5631] perf block-range: Move debug code behind ifndef NDEBUG Make good on a comment and avoid a unused-but-set-variable warning. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Sean Christopherson Link: https://lore.kernel.org/r/20230330183827.1412303-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/block-range.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/tools/perf/util/block-range.c b/tools/perf/util/block-range.c index 1be432657501..680e92774d0c 100644 --- a/tools/perf/util/block-range.c +++ b/tools/perf/util/block-range.c @@ -11,11 +11,7 @@ struct { static void block_range__debug(void) { - /* - * XXX still paranoid for now; see if we can make this depend on - * DEBUG=1 builds. - */ -#if 1 +#ifndef NDEBUG struct rb_node *rb; u64 old = 0; /* NULL isn't executable */ -- GitLab From 616b14b47a86d880ba21a363440f20f82152d8f2 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 30 Mar 2023 11:38:27 -0700 Subject: [PATCH 1951/5631] perf build: Conditionally define NDEBUG When a build is done without DEBUG=1 then define NDEBUG. This will compile out asserts and other debug code. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Sean Christopherson Link: https://lore.kernel.org/r/20230330183827.1412303-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3066d0c318c3..236d763181c5 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -228,6 +228,7 @@ ifndef DEBUG endif ifeq ($(DEBUG),0) +CORE_CFLAGS += -DNDEBUG=1 ifeq ($(CC_NO_CLANG), 0) CORE_CFLAGS += -O3 else -- GitLab From 5ef506130c739a0601d234b36f5dfd2129f966c0 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 30 Mar 2023 16:18:32 +0300 Subject: [PATCH 1952/5631] perf top: Add --branch-history option Add --branch-history option, to act the same as that option does for perf report. Example: $ cat tcallf.c volatile a = 10000, b = 100000, c; __attribute__((noinline)) f2() { c = a / b; } __attribute__((noinline)) f1() { f2(); f2(); } main() { while (1) f1(); } $ gcc -w -g -o tcallf tcallf.c $ ./tcallf & [1] 29409 $ perf top -e cycles:u -t $(pidof tcallf) --stdio --no-children --branch-history PerfTop: 3819 irqs/sec kernel: 0.0% exact: 0.0% lost: 0/0 drop: 0/0 [4000Hz cycles:u], (target_tid: 29409) -------------------------------------------------------------------------------------------------------------------- 49.01% tcallf.c:5 [.] f2 tcallf | |--24.91%--f2 tcallf.c:4 | | | |--17.14%--f1 tcallf.c:11 (cycles:1) | | f1 tcallf.c:11 | | f2 tcallf.c:6 (cycles:3) | | f2 tcallf.c:4 | | f1 tcallf.c:10 (cycles:2) | | f1 tcallf.c:9 | | main tcallf.c:16 (cycles:1) | | main tcallf.c:16 | | main tcallf.c:16 (cycles:1) | | main tcallf.c:16 | | f1 tcallf.c:12 (cycles:1) | | f1 tcallf.c:12 | | f2 tcallf.c:6 (cycles:3) | | f2 tcallf.c:4 | | f1 tcallf.c:11 (cycles:1 iter:1 avg_cycles:12) | | f1 tcallf.c:11 | | f2 tcallf.c:6 (cycles:3 iter:1 avg_cycles:12) | | f2 tcallf.c:4 | | f1 tcallf.c:10 (cycles:2 iter:1 avg_cycles:12) | | | --7.78%--f1 tcallf.c:10 (cycles:2) | f1 tcallf.c:9 | main tcallf.c:16 (cycles:1) | main tcallf.c:16 | main tcallf.c:16 (cycles:1) | main tcallf.c:16 | f1 tcallf.c:12 (cycles:1) | f1 tcallf.c:12 | f2 tcallf.c:6 (cycles:3) | f2 tcallf.c:4 | f1 tcallf.c:11 (cycles:1) | f1 tcallf.c:11 | f2 tcallf.c:6 (cycles:3) | f2 tcallf.c:4 | f1 tcallf.c:10 (cycles:2 iter:1 avg_cycles:12) | f1 tcallf.c:9 | main tcallf.c:16 (cycles:1 iter:1 avg_cycles:12) | main tcallf.c:16 | main tcallf.c:16 (cycles:1 iter:1 avg_cycles:12) ... $ pkill tcallf [1]+ Terminated ./tcallf Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230330131833.12864-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-top.txt | 4 ++++ tools/perf/builtin-top.c | 17 +++++++++++++++++ 2 files changed, 21 insertions(+) diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 619cc8143ad5..3c202ec080ba 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -254,6 +254,10 @@ Default is to monitor all CPUS. The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. +--branch-history:: + Add the addresses of sampled taken branches to the callstack. + This allows to examine the path the program took to each sample. + --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 82c6c065830d..2c985cfea517 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1437,6 +1437,7 @@ int cmd_top(int argc, const char **argv) .max_stack = sysctl__max_stack(), .nr_threads_synthesize = UINT_MAX, }; + bool branch_call_mode = false; struct record_opts *opts = &top.record_opts; struct target *target = &opts->target; const char *disassembler_style = NULL, *objdump_path = NULL, *addr2line_path = NULL; @@ -1551,6 +1552,8 @@ int cmd_top(int argc, const char **argv) OPT_CALLBACK('j', "branch-filter", &opts->branch_stack, "branch filter mask", "branch stack filter modes", parse_branch_stack), + OPT_BOOLEAN(0, "branch-history", &branch_call_mode, + "add last branch records to call history"), OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, "Show raw trace event output (do not use print fmt or plugins)"), OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy, @@ -1677,6 +1680,20 @@ int cmd_top(int argc, const char **argv) goto out_delete_evlist; } + if (branch_call_mode) { + if (!opts->branch_stack) + opts->branch_stack = PERF_SAMPLE_BRANCH_ANY; + symbol_conf.use_callchain = true; + callchain_param.key = CCKEY_ADDRESS; + callchain_param.branch_callstack = true; + callchain_param.enabled = true; + if (callchain_param.record_mode == CALLCHAIN_NONE) + callchain_param.record_mode = CALLCHAIN_FP; + callchain_register_param(&callchain_param); + if (!sort_order) + sort_order = "srcline,symbol,dso"; + } + if (opts->branch_stack && callchain_param.enabled) symbol_conf.show_branchflag_count = true; -- GitLab From 5a892c3da39fae73d008cc43706ff29456fa8cf1 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 30 Mar 2023 16:18:33 +0300 Subject: [PATCH 1953/5631] perf symbol: Remove unused branch_callstack branch_callstack was added by commit 8b7bad58efb7 ("perf callchain: Support handling complete branch stacks as histograms") but never used. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230330131833.12864-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol_conf.h | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h index 5accd8e69ad2..f26f81eb8252 100644 --- a/tools/perf/util/symbol_conf.h +++ b/tools/perf/util/symbol_conf.h @@ -33,7 +33,6 @@ struct symbol_conf { demangle_kernel, filter_relative, show_hist_headers, - branch_callstack, has_filter, show_ref_callgraph, hide_unresolved, -- GitLab From 337fa2db04785c60fc3aa736af98ce8358f87d34 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Thu, 30 Mar 2023 09:42:02 +0200 Subject: [PATCH 1954/5631] perf bench numa: Fix type of loop iterator in do_work, it should be 'long' 'j' is of type int and start/end are of type 'long'. Thus 'j' might become negative and cause segfault in access_data(). Fix it by using 'long' for 'j' as well. Reviewed-by: James Clark Signed-off-by: Andreas Herrmann Link: https://lore.kernel.org/r/20230330074202.14052-1-aherrmann@suse.de Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 9717c6c17433..1fbd7c947abc 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -847,7 +847,7 @@ static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val if (g->p.data_rand_walk) { u32 lfsr = nr + loop + val; - int j; + long j; for (i = 0; i < words/1024; i++) { long start, end; -- GitLab From 319593215260da74a78c7de1dccd877ea13916fb Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 28 Mar 2023 16:41:42 -0700 Subject: [PATCH 1955/5631] perf vendor events intel: Update ivybridge and ivytown Update to versions 24 and 23 respectively. Adds the event BR_MISP_EXEC.INDIRECT. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230328234142.1080045-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json | 8 ++++++++ tools/perf/pmu-events/arch/x86/ivytown/pipeline.json | 8 ++++++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 4 ++-- 3 files changed, 18 insertions(+), 2 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json index d1e64e0d683e..30a3da9cd22b 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json @@ -215,6 +215,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json index d1e64e0d683e..30a3da9cd22b 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json @@ -215,6 +215,14 @@ "SampleAfterValue": "200003", "UMask": "0xc4" }, + { + "BriefDescription": "Speculative mispredicted indirect branches", + "EventCode": "0x89", + "EventName": "BR_MISP_EXEC.INDIRECT", + "PublicDescription": "Counts speculatively miss-predicted indirect branches at execution time. Counts for indirect near CALL or JMP instructions (RET excluded).", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, { "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches", "EventCode": "0x89", diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 41d755d570e6..97b3ffc284a6 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -14,8 +14,8 @@ GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v27,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core GenuineIntel-6-6[AC],v1.19,icelakex,core -GenuineIntel-6-3A,v23,ivybridge,core -GenuineIntel-6-3E,v22,ivytown,core +GenuineIntel-6-3A,v24,ivybridge,core +GenuineIntel-6-3E,v23,ivytown,core GenuineIntel-6-2D,v23,jaketown,core GenuineIntel-6-(57|85),v10,knightslanding,core GenuineIntel-6-A[AC],v1.01,meteorlake,core -- GitLab From 35bf007e2ee0447166081646c0797bfa831b062f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 27 Mar 2023 15:57:10 -0700 Subject: [PATCH 1956/5631] perf lock contention: Fix debug stat if no contention It should not divide if the total number is 0. Otherwise it'd show NaN in the bad rate output. Also add a whitespace in the "output for debug" message. $ sudo perf lock contention -abv true Looking at the vmlinux_path (8 entries long) symsrc__init: cannot get elf header. Using /proc/kcore for kernel data Using /proc/kallsyms for symbols contended total wait max wait avg wait type caller === output for debug=== bad: 0, total: 0 bad rate: -nan % <------------------------- (here) histogram of events caused bad sequence acquire: 0 acquired: 0 contended: 0 release: 0 Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230327225711.245738-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 3c8a19ebc496..82dd2dfe5692 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1323,10 +1323,10 @@ static void print_bad_events(int bad, int total) for (i = 0; i < BROKEN_MAX; i++) broken += bad_hist[i]; - if (quiet || (broken == 0 && verbose <= 0)) + if (quiet || total == 0 || (broken == 0 && verbose <= 0)) return; - pr_info("\n=== output for debug===\n\n"); + pr_info("\n=== output for debug ===\n\n"); pr_info("bad: %d, total: %d\n", bad, total); pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100); pr_info("histogram of events caused bad sequence\n"); -- GitLab From 84c3a2bb4c513ca9fd1326cf24d3729b769d9cf1 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 27 Mar 2023 15:57:11 -0700 Subject: [PATCH 1957/5631] perf lock contention: Show detail failure reason for BPF It can fail to collect lock stat from BPF for various reasons. For example, I've got a report that sometimes time calculation seems wrong in case of contended spinlocks. I suspect the time delta went negative for some reason. Count them separately and show in the output like below: $ sudo perf lock contention -abE5 sleep 10 contended total wait max wait avg wait type caller 13 785.61 us 79.36 us 60.43 us spinlock remove_wait_queue+0x14 10 469.02 us 87.51 us 46.90 us spinlock prepare_to_wait+0x27 9 289.09 us 69.08 us 32.12 us spinlock finish_wait+0x36 114 251.05 us 8.56 us 2.20 us spinlock try_to_wake_up+0x1f5 132 188.63 us 5.01 us 1.43 us spinlock __wake_up_common_lock+0x62 === output for debug === bad: 1, total: 279 bad rate: 0.36 % histogram of failure reasons task: 1 stack: 0 time: 0 Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230327225711.245738-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 28 +++++++++++++++---- tools/perf/util/bpf_lock_contention.c | 4 ++- .../perf/util/bpf_skel/lock_contention.bpf.c | 13 +++++++-- tools/perf/util/lock-contention.h | 8 +++++- 4 files changed, 42 insertions(+), 11 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 82dd2dfe5692..32ec58fb80e4 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1619,6 +1619,24 @@ static void sort_contention_result(void) sort_result(); } +static void print_bpf_events(int total, struct lock_contention_fails *fails) +{ + /* Output for debug, this have to be removed */ + int broken = fails->task + fails->stack + fails->time; + + if (quiet || total == 0 || (broken == 0 && verbose <= 0)) + return; + + total += broken; + pr_info("\n=== output for debug ===\n\n"); + pr_info("bad: %d, total: %d\n", broken, total); + pr_info("bad rate: %.2f %%\n", (double)broken / (double)total * 100); + + pr_info("histogram of failure reasons\n"); + pr_info(" %10s: %d\n", "task", fails->task); + pr_info(" %10s: %d\n", "stack", fails->stack); + pr_info(" %10s: %d\n", "time", fails->time); +} static void print_contention_result(struct lock_contention *con) { struct lock_stat *st; @@ -1646,8 +1664,6 @@ static void print_contention_result(struct lock_contention *con) } bad = total = printed = 0; - if (use_bpf) - bad = bad_hist[BROKEN_CONTENDED]; while ((st = pop_from_result())) { struct thread *t; @@ -1704,7 +1720,10 @@ static void print_contention_result(struct lock_contention *con) break; } - print_bad_events(bad, total); + if (use_bpf) + print_bpf_events(total, &con->fails); + else + print_bad_events(bad, total); } static bool force; @@ -1931,9 +1950,6 @@ static int __cmd_contention(int argc, const char **argv) lock_contention_stop(); lock_contention_read(&con); - - /* abuse bad hist stats for lost entries */ - bad_hist[BROKEN_CONTENDED] = con.lost; } else { err = perf_session__process_events(session); if (err) diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 5927bf0bd92b..b3e8aa9cd011 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -259,7 +259,9 @@ int lock_contention_read(struct lock_contention *con) fd = bpf_map__fd(skel->maps.lock_stat); stack = bpf_map__fd(skel->maps.stacks); - con->lost = skel->bss->lost; + con->fails.task = skel->bss->task_fail; + con->fails.stack = skel->bss->stack_fail; + con->fails.time = skel->bss->time_fail; stack_trace = zalloc(stack_size); if (stack_trace == NULL) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index ed9160999c32..3f4ee3992e81 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -124,7 +124,9 @@ int lock_owner; int aggr_mode; /* error stat */ -int lost; +int task_fail; +int stack_fail; +int time_fail; static inline int can_record(u64 *ctx) { @@ -283,7 +285,7 @@ int contention_begin(u64 *ctx) bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY); pelem = bpf_map_lookup_elem(&tstamp, &pid); if (pelem == NULL) { - lost++; + __sync_fetch_and_add(&task_fail, 1); return 0; } } @@ -296,7 +298,7 @@ int contention_begin(u64 *ctx) pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip); if (pelem->stack_id < 0) - lost++; + __sync_fetch_and_add(&stack_fail, 1); } else if (aggr_mode == LOCK_AGGR_TASK) { struct task_struct *task; @@ -340,6 +342,11 @@ int contention_end(u64 *ctx) return 0; duration = bpf_ktime_get_ns() - pelem->timestamp; + if ((__s64)duration < 0) { + bpf_map_delete_elem(&tstamp, &pid); + __sync_fetch_and_add(&time_fail, 1); + return 0; + } switch (aggr_mode) { case LOCK_AGGR_CALLER: diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index 040b618b2215..10c28302420c 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -122,14 +122,20 @@ struct evlist; struct machine; struct target; +struct lock_contention_fails { + int task; + int stack; + int time; +}; + struct lock_contention { struct evlist *evlist; struct target *target; struct machine *machine; struct hlist_head *result; struct lock_filter *filters; + struct lock_contention_fails fails; unsigned long map_nr_entries; - int lost; int max_stack; int stack_skip; int aggr_mode; -- GitLab From 092772955568fa848b1e782e6cb3fa395eccea81 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Fri, 31 Mar 2023 06:56:43 +0100 Subject: [PATCH 1958/5631] perf cs-etm: Move mapping of Trace ID and cpu into helper function The information to associate Trace ID and CPU will be changing. Drivers will start outputting this as a hardware ID packet in the data file which if present will be used in preference to the AUXINFO values. To prepare for this we provide a helper functions to do the individual ID mapping, and one to extract the IDs from the completed metadata blocks. Reviewed-by: James Clark Signed-off-by: Mike Leach Acked-by: Suzuki Poulouse Cc: Alexander Shishkin Cc: Darren Hart Cc: Ganapatrao Kulkarni Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230331055645.26918-2-mike.leach@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 5 ++ tools/perf/util/cs-etm-base.c | 3 +- tools/perf/util/cs-etm.c | 92 +++++++++++++++++++---------- tools/perf/util/cs-etm.h | 14 ++++- 4 files changed, 79 insertions(+), 35 deletions(-) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 6c2fd6cc5a98..db9c7c0abb6a 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -7,9 +7,14 @@ #ifndef _LINUX_CORESIGHT_PMU_H #define _LINUX_CORESIGHT_PMU_H +#include + #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10 +/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/perf/util/cs-etm-base.c b/tools/perf/util/cs-etm-base.c index 5f48b756c4cf..4abe416e3feb 100644 --- a/tools/perf/util/cs-etm-base.c +++ b/tools/perf/util/cs-etm-base.c @@ -148,7 +148,8 @@ static void cs_etm__print_auxtrace_info(u64 *val, int num) for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { if (version == 0) err = cs_etm__print_cpu_metadata_v0(val, &i); - else if (version == 1) + /* printing same for both, but value bit flags added on v2 */ + else if ((version == 1) || (version == 2)) err = cs_etm__print_cpu_metadata_v1(val, &i); if (err) return; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index f65bac5ddbdb..5fc9c288080b 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -196,6 +196,30 @@ int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt) return 0; } +static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata) +{ + struct int_node *inode; + + /* Get an RB node for this CPU */ + inode = intlist__findnew(traceid_list, trace_chan_id); + + /* Something went wrong, no need to continue */ + if (!inode) + return -ENOMEM; + + /* + * The node for that CPU should not be taken. + * Back out if that's the case. + */ + if (inode->priv) + return -EINVAL; + + /* All good, associate the traceID with the metadata pointer */ + inode->priv = cpu_metadata; + + return 0; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { @@ -2804,17 +2828,46 @@ static bool cs_etm__has_virtual_ts(u64 **metadata, int num_cpu) return true; } +/* map trace ids to correct metadata block, from information in metadata */ +static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) +{ + u64 cs_etm_magic; + u8 trace_chan_id; + int i, err; + + for (i = 0; i < num_cpu; i++) { + cs_etm_magic = metadata[i][CS_ETM_MAGIC]; + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + default: + /* unknown magic number */ + return -EINVAL; + } + err = cs_etm__map_trace_id(trace_chan_id, metadata[i]); + if (err) + return err; + } + return 0; +} + int cs_etm__process_auxtrace_info_full(union perf_event *event, struct perf_session *session) { struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; - struct int_node *inode; struct perf_record_time_conv *tc = &session->time_conv; int event_header_size = sizeof(struct perf_event_header); int total_size = auxtrace_info->header.size; int priv_size = 0; - int num_cpu, trcidr_idx; + int num_cpu; int err = 0; int i, j; u64 *ptr = NULL; @@ -2853,23 +2906,13 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, cs_etm__create_meta_blk(ptr, &i, CS_ETM_PRIV_MAX, CS_ETM_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETM_ETMTRACEIDR; - } else if (ptr[i] == __perf_cs_etmv4_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETMV4_PRIV_MAX, CS_ETMV4_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else if (ptr[i] == __perf_cs_ete_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETE_PRIV_MAX, -1); - - /* ETE shares first part of metadata with ETMv4 */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else { ui__error("CS ETM Trace: Unrecognised magic number %#"PRIx64". File could be from a newer version of perf.\n", ptr[i]); @@ -2881,26 +2924,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, err = -ENOMEM; goto err_free_metadata; } - - /* Get an RB node for this CPU */ - inode = intlist__findnew(traceid_list, metadata[j][trcidr_idx]); - - /* Something went wrong, no need to continue */ - if (!inode) { - err = -ENOMEM; - goto err_free_metadata; - } - - /* - * The node for that CPU should not be taken. - * Back out if that's the case. - */ - if (inode->priv) { - err = -EINVAL; - goto err_free_metadata; - } - /* All good, associate the traceID with the metadata pointer */ - inode->priv = metadata[j]; } /* @@ -2994,6 +3017,11 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, if (err) goto err_delete_thread; + /* before aux records are queued, need to map metadata to trace IDs */ + err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + if (err) + goto err_delete_thread; + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 98a4f7113d2f..661f029322e4 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -29,13 +29,17 @@ enum { /* * Update the version for new format. * - * New version 1 format adds a param count to the per cpu metadata. + * Version 1: format adds a param count to the per cpu metadata. * This allows easy adding of new metadata parameters. * Requires that new params always added after current ones. * Also allows client reader to handle file versions that are different by * checking the number of params in the file vs the number expected. + * + * Version 2: Drivers will use PERF_RECORD_AUX_OUTPUT_HW_ID to output + * CoreSight Trace ID. ...TRACEIDR metadata will be set to legacy values + * but with addition flags. */ -#define CS_HEADER_CURRENT_VERSION 1 +#define CS_HEADER_CURRENT_VERSION 2 /* Beginning of header common to both ETMv3 and V4 */ enum { @@ -97,6 +101,12 @@ enum { CS_ETE_PRIV_MAX }; +/* + * Check for valid CoreSight trace ID. If an invalid value is present in the metadata, + * then IDs are present in the hardware ID packet in the data file. + */ +#define CS_IS_VALID_TRACE_ID(id) ((id > 0) && (id < 0x70)) + /* * ETMv3 exception encoding number: * See Embedded Trace Macrocell specification (ARM IHI 0014Q) -- GitLab From e5fa5b4110fe7d0ab08252943fc47072a7ff6c9d Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Fri, 31 Mar 2023 06:56:44 +0100 Subject: [PATCH 1959/5631] perf cs-etm: Update record event to use new Trace ID protocol Trace IDs are now dynamically allocated. Previously used the static association algorithm that is no longer used. The 'cpu * 2 + seed' was outdated and broken for systems with high core counts (>46). as it did not scale and was broken for larger core counts. Trace ID will now be sent in PERF_RECORD_AUX_OUTPUT_HW_ID record. Legacy ID algorithm renamed and retained for limited backward compatibility use. Reviewed-by: James Clark Signed-off-by: Mike Leach Acked-by: Suzuki Poulouse Cc: Alexander Shishkin Cc: Darren Hart Cc: Ganapatrao Kulkarni Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230331055645.26918-2-mike.leach@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 29 +++++++++++++++++------------ tools/perf/arch/arm/util/cs-etm.c | 27 +++++++++++++++++---------- 2 files changed, 34 insertions(+), 22 deletions(-) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index db9c7c0abb6a..1760f9a574b0 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -10,11 +10,27 @@ #include #define CORESIGHT_ETM_PMU_NAME "cs_etm" -#define CORESIGHT_ETM_PMU_SEED 0x10 + +/* + * The legacy Trace ID system based on fixed calculation from the cpu + * number. This has been replaced by drivers using a dynamic allocation + * system - but need to retain the legacy algorithm for backward comparibility + * in certain situations:- + * a) new perf running on older systems that generate the legacy mapping + * b) older tools that may not update at the same time as the kernel. + */ +#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) /* CoreSight trace ID is currently the bottom 7 bits of the value */ #define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) +/* + * perf record will set the legacy meta data values as unused initially. + * This allows perf report to manage the decoders created when dynamic + * allocation in operation. + */ +#define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. @@ -39,15 +55,4 @@ #define ETM4_CFG_BIT_RETSTK 12 #define ETM4_CFG_BIT_VMID_OPT 15 -static inline int coresight_get_trace_id(int cpu) -{ - /* - * A trace ID of value 0 is invalid, so let's start at some - * random value that fits in 7 bits and go from there. Since - * the common convention is to have data trace IDs be I(N) + 1, - * set instruction trace IDs as a function of the CPU number. - */ - return (CORESIGHT_ETM_PMU_SEED + (cpu * 2)); -} - #endif diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 86b61ad74f90..e02a9bfc3d42 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -437,13 +437,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, evlist__to_front(evlist, cs_etm_evsel); /* - * In the case of per-cpu mmaps, we need the CPU on the - * AUX event. We also need the contextID in order to be notified + * get the CPU on the sample - need it to associate trace ID in the + * AUX_OUTPUT_HW_ID event, and the AUX event for per-cpu mmaps. + */ + evsel__set_sample_bit(cs_etm_evsel, CPU); + + /* + * Also the case of per-cpu mmaps, need the contextID in order to be notified * when a context switch happened. */ if (!perf_cpu_map__empty(cpus)) { - evsel__set_sample_bit(cs_etm_evsel, CPU); - err = cs_etm_set_option(itr, cs_etm_evsel, BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS)); if (err) @@ -679,8 +682,10 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr, /* Get trace configuration register */ data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr); - /* Get traceID from the framework */ - data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu); + /* traceID set to legacy version, in case new perf running on older system */ + data[CS_ETMV4_TRCTRACEIDR] = + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG; + /* Get read-only information from sysFS */ data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_etmv4_ro[CS_ETMV4_TRCIDR0]); @@ -711,8 +716,10 @@ static void cs_etm_save_ete_header(__u64 data[], struct auxtrace_record *itr, in /* Get trace configuration register */ data[CS_ETE_TRCCONFIGR] = cs_etmv4_get_config(itr); - /* Get traceID from the framework */ - data[CS_ETE_TRCTRACEIDR] = coresight_get_trace_id(cpu); + /* traceID set to legacy version, in case new perf running on older system */ + data[CS_ETE_TRCTRACEIDR] = + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG; + /* Get read-only information from sysFS */ data[CS_ETE_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu, metadata_ete_ro[CS_ETE_TRCIDR0]); @@ -768,9 +775,9 @@ static void cs_etm_get_metadata(int cpu, u32 *offset, magic = __perf_cs_etmv3_magic; /* Get configuration register */ info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr); - /* Get traceID from the framework */ + /* traceID set to legacy value in case new perf running on old system */ info->priv[*offset + CS_ETM_ETMTRACEIDR] = - coresight_get_trace_id(cpu); + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG; /* Get read-only information from sysFS */ info->priv[*offset + CS_ETM_ETMCCER] = cs_etm_get_ro(cs_etm_pmu, cpu, -- GitLab From b6521ea2a033b0c49669bd60d69ca16d0746dcea Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Fri, 31 Mar 2023 06:56:45 +0100 Subject: [PATCH 1960/5631] perf cs-etm: Handle PERF_RECORD_AUX_OUTPUT_HW_ID packet When using dynamically assigned CoreSight trace IDs the drivers can output the ID / CPU association as a PERF_RECORD_AUX_OUTPUT_HW_ID packet. Update cs-etm decoder to handle this packet by setting the CPU/Trace ID mapping. Reviewed-by: James Clark Signed-off-by: Mike Leach Acked-by: Suzuki Poulouse Cc: Alexander Shishkin Cc: Darren Hart Cc: Ganapatrao Kulkarni Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230331055645.26918-2-mike.leach@linaro.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/coresight-pmu.h | 15 ++ .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 7 + tools/perf/util/cs-etm.c | 246 ++++++++++++++++-- 3 files changed, 250 insertions(+), 18 deletions(-) diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 1760f9a574b0..cef3b1c25335 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -31,6 +31,9 @@ */ #define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31) +/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. @@ -55,4 +58,16 @@ #define ETM4_CFG_BIT_RETSTK 12 #define ETM4_CFG_BIT_VMID_OPT 15 +/* + * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. + * Used to associate a CPU with the CoreSight Trace ID. + * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. + * [59:08] - Unused (SBZ) + * [63:60] - Version + */ +#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0) +#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_CURR_VERSION 0 + #endif diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index d0e521dfcf35..82a27ab90c8b 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -668,6 +668,7 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, switch (t_params->protocol) { case CS_ETM_PROTO_ETMV3: case CS_ETM_PROTO_PTM: + csid = (t_params->etmv3.reg_idr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3); decoder->decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ? OCSD_BUILTIN_DCD_ETMV3 : @@ -675,11 +676,13 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, trace_config = &config_etmv3; break; case CS_ETM_PROTO_ETMV4i: + csid = (t_params->etmv4.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4); decoder->decoder_name = OCSD_BUILTIN_DCD_ETMV4I; trace_config = &trace_config_etmv4; break; case CS_ETM_PROTO_ETE: + csid = (t_params->ete.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_ete_config(t_params, &trace_config_ete); decoder->decoder_name = OCSD_BUILTIN_DCD_ETE; trace_config = &trace_config_ete; @@ -688,6 +691,10 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, return -1; } + /* if the CPU has no trace ID associated, no decoder needed */ + if (csid == CORESIGHT_TRACE_ID_UNUSED_VAL) + return 0; + if (d_params->operation == CS_ETM_OPERATION_DECODE) { if (ocsd_dt_create_decoder(decoder->dcd_tree, decoder->decoder_name, diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 5fc9c288080b..94e2d02009eb 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -220,6 +220,143 @@ static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata) return 0; } +static int cs_etm__metadata_get_trace_id(u8 *trace_chan_id, u64 *cpu_metadata) +{ + u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC]; + + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + *trace_chan_id = (u8)(cpu_metadata[CS_ETM_ETMTRACEIDR] & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + *trace_chan_id = (u8)(cpu_metadata[CS_ETMV4_TRCTRACEIDR] & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + default: + return -EINVAL; + } + return 0; +} + +/* + * update metadata trace ID from the value found in the AUX_HW_INFO packet. + * This will also clear the CORESIGHT_TRACE_ID_UNUSED_FLAG flag if present. + */ +static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata) +{ + u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC]; + + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + cpu_metadata[CS_ETM_ETMTRACEIDR] = trace_chan_id; + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + cpu_metadata[CS_ETMV4_TRCTRACEIDR] = trace_chan_id; + break; + + default: + return -EINVAL; + } + return 0; +} + +/* + * FIELD_GET (linux/bitfield.h) not available outside kernel code, + * and the header contains too many dependencies to just copy over, + * so roll our own based on the original + */ +#define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define FIELD_GET(_mask, _reg) \ + ({ \ + (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ + }) + +/* + * Handle the PERF_RECORD_AUX_OUTPUT_HW_ID event. + * + * The payload associates the Trace ID and the CPU. + * The routine is tolerant of seeing multiple packets with the same association, + * but a CPU / Trace ID association changing during a session is an error. + */ +static int cs_etm__process_aux_output_hw_id(struct perf_session *session, + union perf_event *event) +{ + struct cs_etm_auxtrace *etm; + struct perf_sample sample; + struct int_node *inode; + struct evsel *evsel; + u64 *cpu_data; + u64 hw_id; + int cpu, version, err; + u8 trace_chan_id, curr_chan_id; + + /* extract and parse the HW ID */ + hw_id = event->aux_output_hw_id.hw_id; + version = FIELD_GET(CS_AUX_HW_ID_VERSION_MASK, hw_id); + trace_chan_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id); + + /* check that we can handle this version */ + if (version > CS_AUX_HW_ID_CURR_VERSION) + return -EINVAL; + + /* get access to the etm metadata */ + etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace); + if (!etm || !etm->metadata) + return -EINVAL; + + /* parse the sample to get the CPU */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + err = evsel__parse_sample(evsel, event, &sample); + if (err) + return err; + cpu = sample.cpu; + if (cpu == -1) { + /* no CPU in the sample - possibly recorded with an old version of perf */ + pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record."); + return -EINVAL; + } + + /* See if the ID is mapped to a CPU, and it matches the current CPU */ + inode = intlist__find(traceid_list, trace_chan_id); + if (inode) { + cpu_data = inode->priv; + if ((int)cpu_data[CS_ETM_CPU] != cpu) { + pr_err("CS_ETM: map mismatch between HW_ID packet CPU and Trace ID\n"); + return -EINVAL; + } + + /* check that the mapped ID matches */ + err = cs_etm__metadata_get_trace_id(&curr_chan_id, cpu_data); + if (err) + return err; + if (curr_chan_id != trace_chan_id) { + pr_err("CS_ETM: mismatch between CPU trace ID and HW_ID packet ID\n"); + return -EINVAL; + } + + /* mapped and matched - return OK */ + return 0; + } + + /* not one we've seen before - lets map it */ + cpu_data = etm->metadata[cpu]; + err = cs_etm__map_trace_id(trace_chan_id, cpu_data); + if (err) + return err; + + /* + * if we are picking up the association from the packet, need to plug + * the correct trace ID into the metadata for setting up decoders later. + */ + err = cs_etm__metadata_set_trace_id(trace_chan_id, cpu_data); + return err; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { @@ -2668,11 +2805,16 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o } /* - * In per-thread mode, CPU is set to -1, but TID will be set instead. See - * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + * In per-thread mode, auxtrace CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). However, the sample AUX event will contain a + * CPU as we set this always for the AUX_OUTPUT_HW_ID event. + * So now compare only TIDs if auxtrace CPU is -1, and CPUs if auxtrace CPU is not -1. + * Return 'not found' if mismatch. */ - if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || - auxtrace_event->cpu != sample->cpu) + if (auxtrace_event->cpu == (__u32) -1) { + if (auxtrace_event->tid != sample->tid) + return 1; + } else if (auxtrace_event->cpu != sample->cpu) return 1; if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { @@ -2721,6 +2863,17 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o return 1; } +static int cs_etm__process_aux_hw_id_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + /* look to handle PERF_RECORD_AUX_OUTPUT_HW_ID early to ensure decoders can be set up */ + if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) { + (*(int *)data)++; /* increment found count */ + return cs_etm__process_aux_output_hw_id(session, event); + } + return 0; +} + static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, u64 offset __maybe_unused, void *data __maybe_unused) { @@ -2839,13 +2992,13 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) cs_etm_magic = metadata[i][CS_ETM_MAGIC]; switch (cs_etm_magic) { case __perf_cs_etmv3_magic: - trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) & - CORESIGHT_TRACE_ID_VAL_MASK); + metadata[i][CS_ETM_ETMTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK; + trace_chan_id = (u8)(metadata[i][CS_ETM_ETMTRACEIDR]); break; case __perf_cs_etmv4_magic: case __perf_cs_ete_magic: - trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) & - CORESIGHT_TRACE_ID_VAL_MASK); + metadata[i][CS_ETMV4_TRCTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK; + trace_chan_id = (u8)(metadata[i][CS_ETMV4_TRCTRACEIDR]); break; default: /* unknown magic number */ @@ -2858,6 +3011,35 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) return 0; } +/* + * If we found AUX_HW_ID packets, then set any metadata marked as unused to the + * unused value to reduce the number of unneeded decoders created. + */ +static int cs_etm__clear_unused_trace_ids_metadata(int num_cpu, u64 **metadata) +{ + u64 cs_etm_magic; + int i; + + for (i = 0; i < num_cpu; i++) { + cs_etm_magic = metadata[i][CS_ETM_MAGIC]; + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + if (metadata[i][CS_ETM_ETMTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG) + metadata[i][CS_ETM_ETMTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL; + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + if (metadata[i][CS_ETMV4_TRCTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG) + metadata[i][CS_ETMV4_TRCTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL; + break; + default: + /* unknown magic number */ + return -EINVAL; + } + } + return 0; +} + int cs_etm__process_auxtrace_info_full(union perf_event *event, struct perf_session *session) { @@ -2869,6 +3051,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, int priv_size = 0; int num_cpu; int err = 0; + int aux_hw_id_found; int i, j; u64 *ptr = NULL; u64 **metadata = NULL; @@ -3017,8 +3200,43 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, if (err) goto err_delete_thread; - /* before aux records are queued, need to map metadata to trace IDs */ - err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + /* + * Map Trace ID values to CPU metadata. + * + * Trace metadata will always contain Trace ID values from the legacy algorithm. If the + * files has been recorded by a "new" perf updated to handle AUX_HW_ID then the metadata + * ID value will also have the CORESIGHT_TRACE_ID_UNUSED_FLAG set. + * + * The updated kernel drivers that use AUX_HW_ID to sent Trace IDs will attempt to use + * the same IDs as the old algorithm as far as is possible, unless there are clashes + * in which case a different value will be used. This means an older perf may still + * be able to record and read files generate on a newer system. + * + * For a perf able to interpret AUX_HW_ID packets we first check for the presence of + * those packets. If they are there then the values will be mapped and plugged into + * the metadata. We then set any remaining metadata values with the used flag to a + * value CORESIGHT_TRACE_ID_UNUSED_VAL - which indicates no decoder is required. + * + * If no AUX_HW_ID packets are present - which means a file recorded on an old kernel + * then we map Trace ID values to CPU directly from the metadata - clearing any unused + * flags if present. + */ + + /* first scan for AUX_OUTPUT_HW_ID records to map trace ID values to CPU metadata */ + aux_hw_id_found = 0; + err = perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__process_aux_hw_id_cb, &aux_hw_id_found); + if (err) + goto err_delete_thread; + + /* if HW ID found then clear any unused metadata ID values */ + if (aux_hw_id_found) + err = cs_etm__clear_unused_trace_ids_metadata(num_cpu, metadata); + /* otherwise, this is a file with metadata values only, map from metadata */ + else + err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + if (err) goto err_delete_thread; @@ -3027,14 +3245,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, goto err_delete_thread; etm->data_queued = etm->queues.populated; - /* - * Print warning in pipe mode, see cs_etm__process_auxtrace_event() and - * cs_etm__queue_aux_fragment() for details relating to limitations. - */ - if (!etm->data_queued) - pr_warning("CS ETM warning: Coresight decode and TRBE support requires random file access.\n" - "Continuing with best effort decoding in piped mode.\n\n"); - return 0; err_delete_thread: -- GitLab From 34fb60400e3257f3a046ee8e6b49242cf65cc1a3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 27 Mar 2023 11:20:57 -0500 Subject: [PATCH 1961/5631] perf arm-spe: Add raw decoding for SPEv1.3 MTE and MOPS load/store Arm SPEv1.3 adds new load/store operation subclasses for Memory Tagging Extension (MTE) and memory operations (MOPS). The memory operations are memcpy and memset. Add support for decoding these new subclasses in the raw decoding. Reviewed-by: Leo Yan Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230327162057.4057188-1-robh@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c | 9 +++++++++ tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h | 3 +++ 2 files changed, 12 insertions(+) diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index fed4741f372e..a454c6737563 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -381,6 +381,15 @@ static int arm_spe_pkt_desc_op_type(const struct arm_spe_pkt *packet, case SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG: arm_spe_pkt_out_string(&err, &buf, &buf_len, " NV-SYSREG"); break; + case SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " MTE-TAG"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_MEMCPY: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMCPY"); + break; + case SPE_OP_PKT_LDST_SUBCLASS_MEMSET: + arm_spe_pkt_out_string(&err, &buf, &buf_len, " MEMSET"); + break; default: break; } diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h index f75ed3a8a050..464a912b221c 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.h @@ -123,6 +123,9 @@ enum arm_spe_events { #define SPE_OP_PKT_LDST_SUBCLASS_SIMD_FP 0x4 #define SPE_OP_PKT_LDST_SUBCLASS_UNSPEC_REG 0x10 #define SPE_OP_PKT_LDST_SUBCLASS_NV_SYSREG 0x30 +#define SPE_OP_PKT_LDST_SUBCLASS_MTE_TAG 0x14 +#define SPE_OP_PKT_LDST_SUBCLASS_MEMCPY 0x20 +#define SPE_OP_PKT_LDST_SUBCLASS_MEMSET 0x25 #define SPE_OP_PKT_IS_LDST_ATOMIC(v) (((v) & (GENMASK_ULL(7, 5) | BIT(1))) == 0x2) -- GitLab From 1f9f33ccf0320be21703d9195dd2b36a1c9a07cb Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 3 Apr 2023 18:48:30 +0300 Subject: [PATCH 1962/5631] perf auxtrace: Fix address filter entire kernel size kallsyms is not completely in address order. In find_entire_kern_cb(), calculate the kernel end from the maximum address not the last symbol. Example: Before: $ sudo cat /proc/kallsyms | grep ' [twTw] ' | tail -1 ffffffffc00b8bd0 t bpf_prog_6deef7357e7b4530 [bpf] $ sudo cat /proc/kallsyms | grep ' [twTw] ' | sort | tail -1 ffffffffc15e0cc0 t iwl_mvm_exit [iwlmvm] $ perf.d093603a05aa record -v --kcore -e intel_pt// --filter 'filter *' -- uname |& grep filter Address filter: filter 0xffffffff93200000/0x2ceba000 After: $ perf.8fb0f7a01f8e record -v --kcore -e intel_pt// --filter 'filter *' -- uname |& grep filter Address filter: filter 0xffffffff93200000/0x2e3e2000 Fixes: 1b36c03e356936d6 ("perf record: Add support for using symbols in address filters") Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230403154831.8651-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/auxtrace.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 498ff7f24463..b2a5e5397bad 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2449,6 +2449,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, char type, u64 start) { struct sym_args *args = arg; + u64 size; if (!kallsyms__is_function(type)) return 0; @@ -2458,7 +2459,9 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused, args->start = start; } /* Don't know exactly where the kernel ends, so we add a page */ - args->size = round_up(start, page_size) + page_size - args->start; + size = round_up(start, page_size) + page_size - args->start; + if (size > args->size) + args->size = size; return 0; } -- GitLab From 430635a0ef1ce958b7b4311f172694ece2c692b8 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 3 Apr 2023 18:48:31 +0300 Subject: [PATCH 1963/5631] perf intel-pt: Fix CYC timestamps after standalone CBR After a standalone CBR (not associated with TSC), update the cycles reference timestamp and reset the cycle count, so that CYC timestamps are calculated relative to that point with the new frequency. Fixes: cc33618619cefc6d ("perf tools: Add Intel PT support for decoding CYC packets") Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230403154831.8651-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 0ac860c8dd2b..7145c5890de0 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1998,6 +1998,8 @@ static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) decoder->cbr = cbr; decoder->cbr_cyc_to_tsc = decoder->max_non_turbo_ratio_fp / cbr; + decoder->cyc_ref_timestamp = decoder->timestamp; + decoder->cycle_cnt = 0; intel_pt_mtc_cyc_cnt_cbr(decoder); } -- GitLab From 7edfe0eeeffa03c61bceee27f3c2699a2af851c3 Mon Sep 17 00:00:00 2001 From: Lakshmi Sowjanya D Date: Mon, 3 Apr 2023 17:32:34 +0530 Subject: [PATCH 1964/5631] pinctrl: Remove Intel Thunder Bay pinctrl driver Remove Thunder Bay specific code as the product got cancelled and there are no end customers or users. Signed-off-by: Lakshmi Sowjanya D Link: https://lore.kernel.org/r/20230403120235.939-1-lakshmi.sowjanya.d@intel.com Signed-off-by: Linus Walleij --- drivers/pinctrl/Kconfig | 19 - drivers/pinctrl/Makefile | 1 - drivers/pinctrl/pinctrl-thunderbay.c | 1294 -------------------------- 3 files changed, 1314 deletions(-) delete mode 100644 drivers/pinctrl/pinctrl-thunderbay.c diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig index fc6e2858c90c..5787c579dcf6 100644 --- a/drivers/pinctrl/Kconfig +++ b/drivers/pinctrl/Kconfig @@ -480,25 +480,6 @@ config PINCTRL_TB10X depends on OF && ARC_PLAT_TB10X select GPIOLIB -config PINCTRL_THUNDERBAY - tristate "Generic pinctrl and GPIO driver for Intel Thunder Bay SoC" - depends on ARCH_THUNDERBAY || (ARM64 && COMPILE_TEST) - depends on HAS_IOMEM - select PINMUX - select PINCONF - select GENERIC_PINCONF - select GENERIC_PINCTRL_GROUPS - select GENERIC_PINMUX_FUNCTIONS - select GPIOLIB - select GPIOLIB_IRQCHIP - select GPIO_GENERIC - help - This selects pin control driver for the Intel Thunder Bay SoC. - It provides pin config functions such as pull-up, pull-down, - interrupt, drive strength, sec lock, Schmitt trigger, slew - rate control and direction control. This module will be - called as pinctrl-thunderbay. - config PINCTRL_ZYNQ bool "Pinctrl driver for Xilinx Zynq" depends on ARCH_ZYNQ diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index 930307e248c5..e196c6e324ad 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -49,7 +49,6 @@ obj-$(CONFIG_PINCTRL_ST) += pinctrl-st.o obj-$(CONFIG_PINCTRL_STMFX) += pinctrl-stmfx.o obj-$(CONFIG_PINCTRL_SX150X) += pinctrl-sx150x.o obj-$(CONFIG_PINCTRL_TB10X) += pinctrl-tb10x.o -obj-$(CONFIG_PINCTRL_THUNDERBAY) += pinctrl-thunderbay.o obj-$(CONFIG_PINCTRL_ZYNQMP) += pinctrl-zynqmp.o obj-$(CONFIG_PINCTRL_ZYNQ) += pinctrl-zynq.o diff --git a/drivers/pinctrl/pinctrl-thunderbay.c b/drivers/pinctrl/pinctrl-thunderbay.c deleted file mode 100644 index 7a5ff955877c..000000000000 --- a/drivers/pinctrl/pinctrl-thunderbay.c +++ /dev/null @@ -1,1294 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel Thunder Bay SOC pinctrl/GPIO driver - * - * Copyright (C) 2021 Intel Corporation - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include -#include -#include - -#include "core.h" -#include "pinconf.h" -#include "pinctrl-utils.h" -#include "pinmux.h" - -/* Bit 0:2 and 4:6 should be used for mode selection */ -#define THB_GPIO_PINMUX_MODE_0 0x00 -#define THB_GPIO_PINMUX_MODE_1 0x11 -#define THB_GPIO_PINMUX_MODE_2 0x22 -#define THB_GPIO_PINMUX_MODE_3 0x33 -#define THB_GPIO_PINMUX_MODE_4 0x44 - -#define THB_GPIO_PORT_SELECT_MASK BIT(8) -#define THB_GPIO_PAD_DIRECTION_MASK BIT(10) -#define THB_GPIO_SPU_MASK BIT(11) -#define THB_GPIO_PULL_ENABLE_MASK BIT(12) -#define THB_GPIO_PULL_UP_MASK BIT(13) -#define THB_GPIO_PULL_DOWN_MASK BIT(14) -#define THB_GPIO_ENAQ_MASK BIT(15) -/* bit 16-19: Drive Strength for the Pad */ -#define THB_GPIO_DRIVE_STRENGTH_MASK (0xF0000) -#define THB_GPIO_SLEW_RATE_MASK BIT(20) -#define THB_GPIO_SCHMITT_TRIGGER_MASK BIT(21) - -#define THB_GPIO_REG_OFFSET(pin_num) ((pin_num) * (0x4)) -#define THB_MAX_MODE_SUPPORTED (5u) -#define THB_MAX_NPINS_SUPPORTED (67u) - -/* store Pin status */ -static u32 thb_pinx_status[THB_MAX_NPINS_SUPPORTED]; - -struct thunderbay_mux_desc { - u8 mode; - const char *name; -}; - -#define THUNDERBAY_PIN_DESC(pin_number, pin_name, ...) { \ - .number = pin_number, \ - .name = pin_name, \ - .drv_data = &(struct thunderbay_mux_desc[]) { \ - __VA_ARGS__, { } }, \ -} - -#define THUNDERBAY_MUX(pin_mode, pin_function) { \ - .mode = pin_mode, \ - .name = pin_function, \ -} - -struct thunderbay_pin_soc { - const struct pinctrl_pin_desc *pins; - unsigned int npins; -}; - -/** - * struct thunderbay_pinctrl - Intel Thunderbay pinctrl structure - * @pctrl: Pointer to the pin controller device - * @base0: First register base address - * @dev: Pointer to the device structure - * @chip: GPIO chip used by this pin controller - * @soc: Pin control configuration data based on SoC - * @ngroups: Number of pin groups available - * @nfuncs: Number of pin functions available - */ -struct thunderbay_pinctrl { - struct pinctrl_dev *pctrl; - void __iomem *base0; - struct device *dev; - struct gpio_chip chip; - const struct thunderbay_pin_soc *soc; - unsigned int ngroups; - unsigned int nfuncs; -}; - -static const struct pinctrl_pin_desc thunderbay_pins[] = { - THUNDERBAY_PIN_DESC(0, "GPIO0", - THUNDERBAY_MUX(0X0, "I2C0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(1, "GPIO1", - THUNDERBAY_MUX(0X0, "I2C0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(2, "GPIO2", - THUNDERBAY_MUX(0X0, "I2C1_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(3, "GPIO3", - THUNDERBAY_MUX(0X0, "I2C1_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(4, "GPIO4", - THUNDERBAY_MUX(0X0, "I2C2_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(5, "GPIO5", - THUNDERBAY_MUX(0X0, "I2C2_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(6, "GPIO6", - THUNDERBAY_MUX(0X0, "I2C3_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(7, "GPIO7", - THUNDERBAY_MUX(0X0, "I2C3_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(8, "GPIO8", - THUNDERBAY_MUX(0X0, "I2C4_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(9, "GPIO9", - THUNDERBAY_MUX(0X0, "I2C4_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(10, "GPIO10", - THUNDERBAY_MUX(0X0, "UART0_M0"), - THUNDERBAY_MUX(0X1, "RT0_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(11, "GPIO11", - THUNDERBAY_MUX(0X0, "UART0_M0"), - THUNDERBAY_MUX(0X1, "RT0_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(12, "GPIO12", - THUNDERBAY_MUX(0X0, "UART0_M0"), - THUNDERBAY_MUX(0X1, "RT1_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(13, "GPIO13", - THUNDERBAY_MUX(0X0, "UART0_M0"), - THUNDERBAY_MUX(0X1, "RT1_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(14, "GPIO14", - THUNDERBAY_MUX(0X0, "UART1_M0"), - THUNDERBAY_MUX(0X1, "RT2_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "TRIGGER_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(15, "GPIO15", - THUNDERBAY_MUX(0X0, "UART1_M0"), - THUNDERBAY_MUX(0X1, "RT2_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "TRIGGER_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(16, "GPIO16", - THUNDERBAY_MUX(0X0, "UART1_M0"), - THUNDERBAY_MUX(0X1, "RT3_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(17, "GPIO17", - THUNDERBAY_MUX(0X0, "UART1_M0"), - THUNDERBAY_MUX(0X1, "RT3_DSU_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(18, "GPIO18", - THUNDERBAY_MUX(0X0, "SPI0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(19, "GPIO19", - THUNDERBAY_MUX(0X0, "SPI0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(20, "GPIO20", - THUNDERBAY_MUX(0X0, "SPI0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "TPIU_TRACE_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(21, "GPIO21", - THUNDERBAY_MUX(0X0, "SPI0_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "TPIU_TRACE_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(22, "GPIO22", - THUNDERBAY_MUX(0X0, "SPI1_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M0"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(23, "GPIO23", - THUNDERBAY_MUX(0X0, "SPI1_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(24, "GPIO24", - THUNDERBAY_MUX(0X0, "SPI1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_TRACE_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(25, "GPIO25", - THUNDERBAY_MUX(0X0, "SPI1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_TRACE_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(26, "GPIO26", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(27, "GPIO27", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(28, "GPIO28", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(29, "GPIO29", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(30, "GPIO30", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(31, "GPIO31", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(32, "GPIO32", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(33, "GPIO33", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(34, "GPIO34", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DIG_VIEW_0"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(35, "GPIO35", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DIG_VIEW_1"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(36, "GPIO36", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_0"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(37, "GPIO37", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_1"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(38, "GPIO38", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_2"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(39, "GPIO39", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(40, "GPIO40", - THUNDERBAY_MUX(0X0, "ETHER0_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(41, "GPIO41", - THUNDERBAY_MUX(0X0, "POWER_INTERRUPT_MAX_PLATFORM_POWER_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(42, "GPIO42", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(43, "GPIO43", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(44, "GPIO44", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(45, "GPIO45", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(46, "GPIO46", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(47, "GPIO47", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(48, "GPIO48", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(49, "GPIO49", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DEBUG_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(50, "GPIO50", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DIG_VIEW_0"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(51, "GPIO51", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "DIG_VIEW_1"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(52, "GPIO52", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_0"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(53, "GPIO53", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_1"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(54, "GPIO54", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_2"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(55, "GPIO55", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "CPR_IO_OUT_CLK_3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(56, "GPIO56", - THUNDERBAY_MUX(0X0, "ETHER1_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "POWER_INTERRUPT_ICCMAX_VDDD_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(57, "GPIO57", - THUNDERBAY_MUX(0X0, "POWER_INTERRUPT_ICCMAX_VPU_M0"), - THUNDERBAY_MUX(0X1, "TPIU_DATA_M1"), - THUNDERBAY_MUX(0X2, "TPIU_DATA_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(58, "GPIO58", - THUNDERBAY_MUX(0X0, "THERMTRIP_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(59, "GPIO59", - THUNDERBAY_MUX(0X0, "THERMTRIP_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(60, "GPIO60", - THUNDERBAY_MUX(0X0, "SMBUS_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(61, "GPIO61", - THUNDERBAY_MUX(0X0, "SMBUS_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "POWER_INTERRUPT_ICCMAX_VDDD_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(62, "GPIO62", - THUNDERBAY_MUX(0X0, "PLATFORM_RESET_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(63, "GPIO63", - THUNDERBAY_MUX(0X0, "PLATFORM_RESET_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(64, "GPIO64", - THUNDERBAY_MUX(0X0, "PLATFORM_SHUTDOWN_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(65, "GPIO65", - THUNDERBAY_MUX(0X0, "PLATFORM_SHUTDOWN_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), - THUNDERBAY_PIN_DESC(66, "GPIO66", - THUNDERBAY_MUX(0X0, "POWER_INTERRUPT_ICCMAX_MEDIA_M0"), - THUNDERBAY_MUX(0X1, "EMPTY_M1"), - THUNDERBAY_MUX(0X2, "EMPTY_M2"), - THUNDERBAY_MUX(0X3, "EMPTY_M3"), - THUNDERBAY_MUX(0X4, "GPIO_M4")), -}; - -static const struct thunderbay_pin_soc thunderbay_data = { - .pins = thunderbay_pins, - .npins = ARRAY_SIZE(thunderbay_pins), -}; - -static u32 thb_gpio_read_reg(struct gpio_chip *chip, unsigned int pinnr) -{ - struct thunderbay_pinctrl *tpc = gpiochip_get_data(chip); - - return readl(tpc->base0 + THB_GPIO_REG_OFFSET(pinnr)); -} - -static u32 thb_gpio_write_reg(struct gpio_chip *chip, unsigned int pinnr, u32 value) -{ - struct thunderbay_pinctrl *tpc = gpiochip_get_data(chip); - - writel(value, (tpc->base0 + THB_GPIO_REG_OFFSET(pinnr))); - return 0; -} - -static int thb_read_gpio_data(struct gpio_chip *chip, unsigned int offset, unsigned int pad_dir) -{ - int data_offset; - u32 data_reg; - - /* as per GPIO Spec = pad_dir 0:input, 1:output */ - data_offset = 0x2000u + (offset / 32); - if (!pad_dir) - data_offset += 4; - data_reg = thb_gpio_read_reg(chip, data_offset); - - return data_reg & BIT(offset % 32); -} - -static int thb_write_gpio_data(struct gpio_chip *chip, unsigned int offset, unsigned int value) -{ - int data_offset; - u32 data_reg; - - data_offset = 0x2000u + (offset / 32); - - data_reg = thb_gpio_read_reg(chip, data_offset); - - if (value > 0) - data_reg |= BIT(offset % 32); - else - data_reg &= ~BIT(offset % 32); - - return thb_gpio_write_reg(chip, data_offset, data_reg); -} - -static int thunderbay_gpio_get_direction(struct gpio_chip *chip, unsigned int offset) -{ - u32 reg = thb_gpio_read_reg(chip, offset); - - /* Return direction only if configured as GPIO else negative error */ - if (reg & THB_GPIO_PORT_SELECT_MASK) - return !(reg & THB_GPIO_PAD_DIRECTION_MASK); - return -EINVAL; -} - -static int thunderbay_gpio_set_direction_input(struct gpio_chip *chip, unsigned int offset) -{ - u32 reg = thb_gpio_read_reg(chip, offset); - - /* set pin as input only if it is GPIO else error */ - if (reg & THB_GPIO_PORT_SELECT_MASK) { - reg &= (~THB_GPIO_PAD_DIRECTION_MASK); - thb_gpio_write_reg(chip, offset, reg); - return 0; - } - return -EINVAL; -} - -static void thunderbay_gpio_set_value(struct gpio_chip *chip, unsigned int offset, int value) -{ - u32 reg = thb_gpio_read_reg(chip, offset); - - /* update pin value only if it is GPIO-output else error */ - if ((reg & THB_GPIO_PORT_SELECT_MASK) && (reg & THB_GPIO_PAD_DIRECTION_MASK)) - thb_write_gpio_data(chip, offset, value); -} - -static int thunderbay_gpio_set_direction_output(struct gpio_chip *chip, - unsigned int offset, int value) -{ - u32 reg = thb_gpio_read_reg(chip, offset); - - /* set pin as output only if it is GPIO else error */ - if (reg & THB_GPIO_PORT_SELECT_MASK) { - reg |= THB_GPIO_PAD_DIRECTION_MASK; - thb_gpio_write_reg(chip, offset, reg); - thunderbay_gpio_set_value(chip, offset, value); - return 0; - } - return -EINVAL; -} - -static int thunderbay_gpio_get_value(struct gpio_chip *chip, unsigned int offset) -{ - u32 reg = thb_gpio_read_reg(chip, offset); - int gpio_dir = 0; - - /* Read pin value only if it is GPIO else error */ - if (reg & THB_GPIO_PORT_SELECT_MASK) { - /* 0=in, 1=out */ - gpio_dir = (reg & THB_GPIO_PAD_DIRECTION_MASK) > 0; - - /* Returns negative value when pin is configured as PORT */ - return thb_read_gpio_data(chip, offset, gpio_dir); - } - return -EINVAL; -} - -static int thunderbay_gpiochip_probe(struct thunderbay_pinctrl *tpc) -{ - struct gpio_chip *chip = &tpc->chip; - int ret; - - chip->label = dev_name(tpc->dev); - chip->parent = tpc->dev; - chip->request = gpiochip_generic_request; - chip->free = gpiochip_generic_free; - chip->get_direction = thunderbay_gpio_get_direction; - chip->direction_input = thunderbay_gpio_set_direction_input; - chip->direction_output = thunderbay_gpio_set_direction_output; - chip->get = thunderbay_gpio_get_value; - chip->set = thunderbay_gpio_set_value; - chip->set_config = gpiochip_generic_config; - /* identifies the first GPIO number handled by this chip; or, - * if negative during registration, requests dynamic ID allocation. - * Please pass -1 as base to let gpiolib select the chip base in all possible cases. - * We want to get rid of the static GPIO number space in the long run. - */ - chip->base = -1; - /* Number of GPIOs handled by this controller; the last GPIO handled is (base + ngpio - 1)*/ - chip->ngpio = THB_MAX_NPINS_SUPPORTED; - - /* Register/add Thunder Bay GPIO chip with Linux framework */ - ret = gpiochip_add_data(chip, tpc); - if (ret) - dev_err(tpc->dev, "Failed to add gpiochip\n"); - return ret; -} - -static int thunderbay_request_gpio(struct pinctrl_dev *pctldev, - struct pinctrl_gpio_range *range, - unsigned int pin) -{ - struct thunderbay_pinctrl *tpc = pinctrl_dev_get_drvdata(pctldev); - struct gpio_chip *chip = &tpc->chip; - u32 reg = 0; - - if (thb_pinx_status[pin] == 0u) { - reg = thb_gpio_read_reg(chip, pin); - /* Updates PIN configuration as GPIO and sets GPIO to MODE-4*/ - reg |= (THB_GPIO_PORT_SELECT_MASK | THB_GPIO_PINMUX_MODE_4); - thb_gpio_write_reg(chip, pin, reg); - - /* update pin status as busy */ - thb_pinx_status[pin] = 1u; - - return 0; - } - return -EINVAL; -} - -static void thunderbay_free_gpio(struct pinctrl_dev *pctldev, - struct pinctrl_gpio_range *range, - unsigned int pin) -{ - struct thunderbay_pinctrl *tpc = pinctrl_dev_get_drvdata(pctldev); - struct gpio_chip *chip = &tpc->chip; - u32 reg = 0; - - if (thb_pinx_status[pin] == 1u) { - reg = thb_gpio_read_reg(chip, pin); - - /* Updates PIN configuration from GPIO to PORT */ - reg &= (~THB_GPIO_PORT_SELECT_MASK); - - /* Change Port/gpio mode to default mode-0 */ - reg &= (~THB_GPIO_PINMUX_MODE_4); - - thb_gpio_write_reg(chip, pin, reg); - - /* update pin status as free */ - thb_pinx_status[pin] = 0u; - } -} - -static int thb_pinctrl_set_mux(struct pinctrl_dev *pctldev, - unsigned int func_select, unsigned int group_select) -{ - struct thunderbay_pinctrl *tpc = pinctrl_dev_get_drvdata(pctldev); - struct gpio_chip *chip = &tpc->chip; - struct function_desc *function; - unsigned int i, pin_mode; - struct group_desc *group; - int ret = -EINVAL; - u32 reg = 0u; - - group = pinctrl_generic_get_group(pctldev, group_select); - if (!group) - return -EINVAL; - - function = pinmux_generic_get_function(pctldev, func_select); - if (!function) - return -EINVAL; - - pin_mode = *(unsigned int *)(function->data); - - /* Change modes for pins in the selected group */ - for (i = 0; i < group->num_pins; i++) { - reg = thb_gpio_read_reg(chip, group->pins[i]); - - switch (pin_mode) { - case 0u: - reg |= THB_GPIO_PINMUX_MODE_0; - break; - case 1u: - reg |= THB_GPIO_PINMUX_MODE_1; - break; - case 2u: - reg |= THB_GPIO_PINMUX_MODE_2; - break; - case 3u: - reg |= THB_GPIO_PINMUX_MODE_3; - break; - case 4u: - reg |= THB_GPIO_PINMUX_MODE_4; - break; - default: - return -EINVAL; - } - - ret = thb_gpio_write_reg(chip, group->pins[i], reg); - if (~ret) { - /* update pin status as busy */ - thb_pinx_status[group->pins[i]] = 1u; - } - } - return ret; -} - -static int thunderbay_build_groups(struct thunderbay_pinctrl *tpc) -{ - struct group_desc *thunderbay_groups; - int i; - - tpc->ngroups = tpc->soc->npins; - thunderbay_groups = devm_kcalloc(tpc->dev, tpc->ngroups, - sizeof(*thunderbay_groups), GFP_KERNEL); - if (!thunderbay_groups) - return -ENOMEM; - - for (i = 0; i < tpc->ngroups; i++) { - struct group_desc *group = thunderbay_groups + i; - const struct pinctrl_pin_desc *pin_info = thunderbay_pins + i; - - group->name = pin_info->name; - group->pins = (int *)&pin_info->number; - pinctrl_generic_add_group(tpc->pctrl, group->name, - group->pins, 1, NULL); - } - return 0; -} - -static int thunderbay_add_functions(struct thunderbay_pinctrl *tpc, struct function_desc *funcs) -{ - int i; - - /* Assign the groups for each function */ - for (i = 0; i < tpc->nfuncs; i++) { - struct function_desc *func = &funcs[i]; - const char **group_names; - unsigned int grp_idx = 0; - int j; - - group_names = devm_kcalloc(tpc->dev, func->num_group_names, - sizeof(*group_names), GFP_KERNEL); - if (!group_names) - return -ENOMEM; - - for (j = 0; j < tpc->soc->npins; j++) { - const struct pinctrl_pin_desc *pin_info = &thunderbay_pins[j]; - struct thunderbay_mux_desc *pin_mux; - - for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { - if (!strcmp(pin_mux->name, func->name)) - group_names[grp_idx++] = pin_info->name; - } - } - - func->group_names = group_names; - } - - /* Add all functions */ - for (i = 0; i < tpc->nfuncs; i++) { - pinmux_generic_add_function(tpc->pctrl, - funcs[i].name, - funcs[i].group_names, - funcs[i].num_group_names, - funcs[i].data); - } - - return 0; -} - -static int thunderbay_build_functions(struct thunderbay_pinctrl *tpc) -{ - struct function_desc *thunderbay_funcs; - void *ptr; - int pin; - int ret; - - /* - * Allocate maximum possible number of functions. Assume every pin - * being part of 8 (hw maximum) globally unique muxes. - */ - tpc->nfuncs = 0; - thunderbay_funcs = kcalloc(tpc->soc->npins * 8, - sizeof(*thunderbay_funcs), GFP_KERNEL); - if (!thunderbay_funcs) - return -ENOMEM; - - /* Setup 1 function for each unique mux */ - for (pin = 0; pin < tpc->soc->npins; pin++) { - const struct pinctrl_pin_desc *pin_info = thunderbay_pins + pin; - struct thunderbay_mux_desc *pin_mux; - - for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { - struct function_desc *func; - - /* Check if we already have function for this mux */ - for (func = thunderbay_funcs; func->name; func++) { - if (!strcmp(pin_mux->name, func->name)) { - func->num_group_names++; - break; - } - } - - if (!func->name) { - func->name = pin_mux->name; - func->num_group_names = 1; - func->data = (int *)&pin_mux->mode; - tpc->nfuncs++; - } - } - } - - /* Reallocate memory based on actual number of functions */ - ptr = krealloc(thunderbay_funcs, - tpc->nfuncs * sizeof(*thunderbay_funcs), GFP_KERNEL); - if (!ptr) - return -ENOMEM; - - thunderbay_funcs = ptr; - ret = thunderbay_add_functions(tpc, thunderbay_funcs); - - kfree(thunderbay_funcs); - return ret; -} - -static int thunderbay_pinconf_set_tristate(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg |= THB_GPIO_ENAQ_MASK; - else - reg &= ~THB_GPIO_ENAQ_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_tristate(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = (reg & THB_GPIO_ENAQ_MASK) > 0; - - return 0; -} - -static int thunderbay_pinconf_set_pulldown(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg |= THB_GPIO_PULL_DOWN_MASK; - else - reg &= ~THB_GPIO_PULL_DOWN_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_pulldown(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg = 0; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_PULL_DOWN_MASK) > 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_set_pullup(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg &= ~THB_GPIO_PULL_UP_MASK; - else - reg |= THB_GPIO_PULL_UP_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_pullup(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_PULL_UP_MASK) == 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_set_opendrain(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg &= ~THB_GPIO_PULL_ENABLE_MASK; - else - reg |= THB_GPIO_PULL_ENABLE_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_opendrain(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_PULL_ENABLE_MASK) == 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_set_pushpull(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg |= THB_GPIO_PULL_ENABLE_MASK; - else - reg &= ~THB_GPIO_PULL_ENABLE_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_pushpull(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_PULL_ENABLE_MASK) > 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_set_drivestrength(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - - /* Drive Strength: 0x0 to 0xF */ - if (config <= 0xF) { - reg = (reg | config); - return thb_gpio_write_reg(chip, pin, reg); - } - - return -EINVAL; -} - -static int thunderbay_pinconf_get_drivestrength(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - reg = (reg & THB_GPIO_DRIVE_STRENGTH_MASK) >> 16; - *config = (reg > 0) ? reg : 0; - - return 0; -} - -static int thunderbay_pinconf_set_schmitt(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg |= THB_GPIO_SCHMITT_TRIGGER_MASK; - else - reg &= ~THB_GPIO_SCHMITT_TRIGGER_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_schmitt(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_SCHMITT_TRIGGER_MASK) > 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_set_slew_rate(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg = 0; - - reg = thb_gpio_read_reg(chip, pin); - if (config > 0) - reg |= THB_GPIO_SLEW_RATE_MASK; - else - reg &= ~THB_GPIO_SLEW_RATE_MASK; - - return thb_gpio_write_reg(chip, pin, reg); -} - -static int thunderbay_pinconf_get_slew_rate(struct thunderbay_pinctrl *tpc, - unsigned int pin, u32 *config) -{ - struct gpio_chip *chip = &tpc->chip; - u32 reg; - - reg = thb_gpio_read_reg(chip, pin); - *config = ((reg & THB_GPIO_SLEW_RATE_MASK) > 0) ? 1 : 0; - - return 0; -} - -static int thunderbay_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, - unsigned long *config) -{ - struct thunderbay_pinctrl *tpc = pinctrl_dev_get_drvdata(pctldev); - enum pin_config_param param = pinconf_to_config_param(*config); - u32 arg; - int ret; - - switch (param) { - case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: - ret = thunderbay_pinconf_get_tristate(tpc, pin, &arg); - break; - - case PIN_CONFIG_BIAS_PULL_DOWN: - ret = thunderbay_pinconf_get_pulldown(tpc, pin, &arg); - break; - - case PIN_CONFIG_BIAS_PULL_UP: - ret = thunderbay_pinconf_get_pullup(tpc, pin, &arg); - break; - - case PIN_CONFIG_DRIVE_OPEN_DRAIN: - ret = thunderbay_pinconf_get_opendrain(tpc, pin, &arg); - break; - - case PIN_CONFIG_DRIVE_PUSH_PULL: - ret = thunderbay_pinconf_get_pushpull(tpc, pin, &arg); - break; - - case PIN_CONFIG_DRIVE_STRENGTH: - ret = thunderbay_pinconf_get_drivestrength(tpc, pin, &arg); - break; - - case PIN_CONFIG_INPUT_SCHMITT_ENABLE: - ret = thunderbay_pinconf_get_schmitt(tpc, pin, &arg); - break; - - case PIN_CONFIG_SLEW_RATE: - ret = thunderbay_pinconf_get_slew_rate(tpc, pin, &arg); - break; - - default: - return -ENOTSUPP; - } - - *config = pinconf_to_config_packed(param, arg); - - return ret; -} - -static int thunderbay_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, - unsigned long *configs, unsigned int num_configs) -{ - struct thunderbay_pinctrl *tpc = pinctrl_dev_get_drvdata(pctldev); - enum pin_config_param param; - unsigned int pinconf; - int ret = 0; - u32 arg; - - for (pinconf = 0; pinconf < num_configs; pinconf++) { - param = pinconf_to_config_param(configs[pinconf]); - arg = pinconf_to_config_argument(configs[pinconf]); - - switch (param) { - case PIN_CONFIG_BIAS_HIGH_IMPEDANCE: - ret = thunderbay_pinconf_set_tristate(tpc, pin, arg); - break; - - case PIN_CONFIG_BIAS_PULL_DOWN: - ret = thunderbay_pinconf_set_pulldown(tpc, pin, arg); - break; - - case PIN_CONFIG_BIAS_PULL_UP: - ret = thunderbay_pinconf_set_pullup(tpc, pin, arg); - break; - - case PIN_CONFIG_DRIVE_OPEN_DRAIN: - ret = thunderbay_pinconf_set_opendrain(tpc, pin, arg); - break; - - case PIN_CONFIG_DRIVE_PUSH_PULL: - ret = thunderbay_pinconf_set_pushpull(tpc, pin, arg); - break; - - case PIN_CONFIG_DRIVE_STRENGTH: - ret = thunderbay_pinconf_set_drivestrength(tpc, pin, arg); - break; - - case PIN_CONFIG_INPUT_SCHMITT_ENABLE: - ret = thunderbay_pinconf_set_schmitt(tpc, pin, arg); - break; - - case PIN_CONFIG_SLEW_RATE: - ret = thunderbay_pinconf_set_slew_rate(tpc, pin, arg); - break; - - default: - return -ENOTSUPP; - } - } - return ret; -} - -static const struct pinctrl_ops thunderbay_pctlops = { - .get_groups_count = pinctrl_generic_get_group_count, - .get_group_name = pinctrl_generic_get_group_name, - .get_group_pins = pinctrl_generic_get_group_pins, - .dt_node_to_map = pinconf_generic_dt_node_to_map_all, - .dt_free_map = pinconf_generic_dt_free_map, -}; - -static const struct pinmux_ops thunderbay_pmxops = { - .get_functions_count = pinmux_generic_get_function_count, - .get_function_name = pinmux_generic_get_function_name, - .get_function_groups = pinmux_generic_get_function_groups, - .set_mux = thb_pinctrl_set_mux, - .gpio_request_enable = thunderbay_request_gpio, - .gpio_disable_free = thunderbay_free_gpio, -}; - -static const struct pinconf_ops thunderbay_confops = { - .is_generic = true, - .pin_config_get = thunderbay_pinconf_get, - .pin_config_set = thunderbay_pinconf_set, -}; - -static struct pinctrl_desc thunderbay_pinctrl_desc = { - .name = "thunderbay-pinmux", - .pctlops = &thunderbay_pctlops, - .pmxops = &thunderbay_pmxops, - .confops = &thunderbay_confops, - .owner = THIS_MODULE, -}; - -static const struct of_device_id thunderbay_pinctrl_match[] = { - { - .compatible = "intel,thunderbay-pinctrl", - .data = &thunderbay_data - }, - {} -}; - -static int thunderbay_pinctrl_probe(struct platform_device *pdev) -{ - const struct of_device_id *of_id; - struct device *dev = &pdev->dev; - struct thunderbay_pinctrl *tpc; - int ret; - - of_id = of_match_node(thunderbay_pinctrl_match, pdev->dev.of_node); - if (!of_id) - return -ENODEV; - - tpc = devm_kzalloc(dev, sizeof(*tpc), GFP_KERNEL); - if (!tpc) - return -ENOMEM; - - tpc->dev = dev; - tpc->soc = of_id->data; - - tpc->base0 = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(tpc->base0)) - return PTR_ERR(tpc->base0); - - thunderbay_pinctrl_desc.pins = tpc->soc->pins; - thunderbay_pinctrl_desc.npins = tpc->soc->npins; - - /* Register pinctrl */ - tpc->pctrl = devm_pinctrl_register(dev, &thunderbay_pinctrl_desc, tpc); - if (IS_ERR(tpc->pctrl)) - return PTR_ERR(tpc->pctrl); - - /* Setup pinmux groups */ - ret = thunderbay_build_groups(tpc); - if (ret) - return ret; - - /* Setup pinmux functions */ - ret = thunderbay_build_functions(tpc); - if (ret) - return ret; - - /* Setup GPIO */ - ret = thunderbay_gpiochip_probe(tpc); - if (ret < 0) - return ret; - - platform_set_drvdata(pdev, tpc); - - return 0; -} - -static struct platform_driver thunderbay_pinctrl_driver = { - .driver = { - .name = "thunderbay-pinctrl", - .of_match_table = thunderbay_pinctrl_match, - }, - .probe = thunderbay_pinctrl_probe, -}; - -builtin_platform_driver(thunderbay_pinctrl_driver); - -MODULE_AUTHOR("Lakshmi Sowjanya D "); -MODULE_AUTHOR("Kiran Kumar S "); -MODULE_DESCRIPTION("Intel Thunder Bay Pinctrl/GPIO Driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 9a8d94711dfc0c1e9bfbb064cce8ff9d656ea9df Mon Sep 17 00:00:00 2001 From: Lakshmi Sowjanya D Date: Mon, 3 Apr 2023 17:32:35 +0530 Subject: [PATCH 1965/5631] dt-bindings: pinctrl: Remove bindings for Intel Thunderbay pinctrl driver Remove Thunder Bay specific code as the product got cancelled and there are no end customers or users. Signed-off-by: Lakshmi Sowjanya D Link: https://lore.kernel.org/r/20230403120235.939-2-lakshmi.sowjanya.d@intel.com Signed-off-by: Linus Walleij --- .../pinctrl/intel,pinctrl-thunderbay.yaml | 120 ------------------ MAINTAINERS | 5 - 2 files changed, 125 deletions(-) delete mode 100644 Documentation/devicetree/bindings/pinctrl/intel,pinctrl-thunderbay.yaml diff --git a/Documentation/devicetree/bindings/pinctrl/intel,pinctrl-thunderbay.yaml b/Documentation/devicetree/bindings/pinctrl/intel,pinctrl-thunderbay.yaml deleted file mode 100644 index f001add16814..000000000000 --- a/Documentation/devicetree/bindings/pinctrl/intel,pinctrl-thunderbay.yaml +++ /dev/null @@ -1,120 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/pinctrl/intel,pinctrl-thunderbay.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: Intel Thunder Bay pin controller - -maintainers: - - Lakshmi Sowjanya D - -description: | - Intel Thunder Bay SoC integrates a pin controller which enables control - of pin directions, input/output values and configuration - for a total of 67 pins. - -properties: - compatible: - const: intel,thunderbay-pinctrl - - reg: - maxItems: 1 - - gpio-controller: true - - '#gpio-cells': - const: 2 - - gpio-ranges: - maxItems: 1 - - interrupts: - description: - Specifies the interrupt lines to be used by the controller. - maxItems: 2 - - interrupt-controller: true - - '#interrupt-cells': - const: 2 - -patternProperties: - '^gpio@[0-9a-f]*$': - type: object - additionalProperties: false - - description: - Child nodes can be specified to contain pin configuration information, - which can then be utilized by pinctrl client devices. - The following properties are supported. - - properties: - pins: - description: | - The name(s) of the pins to be configured in the child node. - Supported pin names are "GPIO0" up to "GPIO66". - - bias-disable: true - - bias-pull-down: true - - bias-pull-up: true - - drive-strength: - description: Drive strength for the pad. - enum: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15] - - bias-bus-hold: - type: boolean - - input-schmitt-enable: - type: boolean - - slew-rate: - description: GPIO slew rate control. - 0 - Slow - 1 - Fast - enum: [0, 1] - -additionalProperties: false - -required: - - compatible - - reg - - gpio-controller - - '#gpio-cells' - - gpio-ranges - - interrupts - - interrupt-controller - - '#interrupt-cells' - -examples: - - | - #include - #include - // Example 1 - pinctrl0: gpio@0 { - compatible = "intel,thunderbay-pinctrl"; - reg = <0x600b0000 0x88>; - gpio-controller; - #gpio-cells = <0x2>; - gpio-ranges = <&pinctrl0 0 0 67>; - interrupts = , - ; - interrupt-controller; - #interrupt-cells = <2>; - }; - - // Example 2 - pinctrl1: gpio@1 { - compatible = "intel,thunderbay-pinctrl"; - reg = <0x600c0000 0x88>; - gpio-controller; - #gpio-cells = <0x2>; - gpio-ranges = <&pinctrl1 0 0 53>; - interrupts = , - ; - interrupt-controller; - #interrupt-cells = <2>; - }; diff --git a/MAINTAINERS b/MAINTAINERS index f4ee11dab1ab..476af72e98ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16598,11 +16598,6 @@ L: linux-omap@vger.kernel.org S: Maintained F: drivers/pinctrl/pinctrl-single.c -PIN CONTROLLER - THUNDERBAY -M: Lakshmi Sowjanya D -S: Supported -F: drivers/pinctrl/pinctrl-thunderbay.c - PIN CONTROLLER - SUNPLUS / TIBBO M: Dvorkin Dmitry M: Wells Lu -- GitLab From 743d3336029ffe2bb38e982a3b572ced243c6d43 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 3 Apr 2023 20:45:01 -0400 Subject: [PATCH 1966/5631] pinctrl: mlxbf3: set varaiable mlxbf3_pmx_funcs storage-class-specifier to static smatch reports drivers/pinctrl/pinctrl-mlxbf3.c:162:20: warning: symbol 'mlxbf3_pmx_funcs' was not declared. Should it be static? This variable is only used in one file so it should be static. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230404004501.1913144-1-trix@redhat.com Signed-off-by: Linus Walleij --- drivers/pinctrl/pinctrl-mlxbf3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-mlxbf3.c b/drivers/pinctrl/pinctrl-mlxbf3.c index 3698f7bbd88d..d9944e6a0af9 100644 --- a/drivers/pinctrl/pinctrl-mlxbf3.c +++ b/drivers/pinctrl/pinctrl-mlxbf3.c @@ -159,7 +159,7 @@ static const struct pinctrl_ops mlxbf3_pinctrl_group_ops = { static const char * const mlxbf3_gpiofunc_group_names[] = { "swctrl" }; static const char * const mlxbf3_hwfunc_group_names[] = { "hwctrl" }; -struct pinfunction mlxbf3_pmx_funcs[] = { +static struct pinfunction mlxbf3_pmx_funcs[] = { PINCTRL_PINFUNCTION("hwfunc", mlxbf3_hwfunc_group_names, 1), PINCTRL_PINFUNCTION("gpiofunc", mlxbf3_gpiofunc_group_names, 1), }; -- GitLab From 9e03608e93858620317d54bc88a9a0069bce003d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 4 Apr 2023 11:05:57 -0300 Subject: [PATCH 1967/5631] tools build: Add a feature test for scandirat(), that is not implemented so far in musl and uclibc We use it just when listing tracepoint events, and for root, so just emit a warning about it to get users to ask the library maintainers to implement it, as suggested in this systemd ticket: https://github.com/systemd/casync/issues/129 Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZCwv4z5Dh%2FdHUMG6@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 1 + tools/build/feature/Makefile | 4 ++++ tools/build/feature/test-all.c | 5 +++++ tools/build/feature/test-scandirat.c | 13 +++++++++++++ tools/perf/Makefile.config | 4 ++++ 5 files changed, 27 insertions(+) create mode 100644 tools/build/feature/test-scandirat.c diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 214622d7537c..934e2777a2db 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -64,6 +64,7 @@ FEATURE_TESTS_BASIC := \ lzma \ get_cpuid \ bpf \ + scandirat \ sched_getcpu \ sdt \ setns \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0a3b9281f8b0..0f0aa9b7d7b5 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -65,6 +65,7 @@ FILES= \ test-gettid.bin \ test-jvmti.bin \ test-jvmti-cmlr.bin \ + test-scandirat.bin \ test-sched_getcpu.bin \ test-setns.bin \ test-libopencsd.bin \ @@ -129,6 +130,9 @@ $(OUTPUT)test-get_current_dir_name.bin: $(OUTPUT)test-glibc.bin: $(BUILD) +$(OUTPUT)test-scandirat.bin: + $(BUILD) + $(OUTPUT)test-sched_getcpu.bin: $(BUILD) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 957c02c7b163..6f4bf386a3b5 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -114,6 +114,10 @@ # include "test-pthread-barrier.c" #undef main +#define main main_test_scandirat +# include "test-scandirat.c" +#undef main + #define main main_test_sched_getcpu # include "test-sched_getcpu.c" #undef main @@ -206,6 +210,7 @@ int main(int argc, char *argv[]) main_test_get_cpuid(); main_test_bpf(); main_test_libcrypto(); + main_test_scandirat(); main_test_sched_getcpu(); main_test_sdt(); main_test_setns(); diff --git a/tools/build/feature/test-scandirat.c b/tools/build/feature/test-scandirat.c new file mode 100644 index 000000000000..d7e19e1858a5 --- /dev/null +++ b/tools/build/feature/test-scandirat.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include + +int main(void) +{ + // expects non-NULL, arg3 is 'restrict' so "pointers" have to be different + return scandirat(/*dirfd=*/ 0, /*dirp=*/ (void *)1, /*namelist=*/ (void *)2, /*filter=*/ (void *)3, /*compar=*/ (void *)4); +} + +#undef _GNU_SOURCE diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 236d763181c5..fd1be9596d12 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -479,6 +479,10 @@ ifdef NO_DWARF NO_LIBDW_DWARF_UNWIND := 1 endif +ifeq ($(feature-scandirat), 1) + CFLAGS += -DHAVE_SCANDIRAT_SUPPORT +endif + ifeq ($(feature-sched_getcpu), 1) CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT endif -- GitLab From 00462d8eaca4eb48e4c07a9a9b49cea2a871fd35 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:41 -0700 Subject: [PATCH 1968/5631] perf list: Use relative path for tracepoint scan Committer notes: Added missing #include for the close() prototype to fix this on Alma Linux 8: 1 21.54 almalinux:8 : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-16) (GCC) util/print-events.c: In function 'print_tracepoint_events': util/print-events.c:103:4: error: implicit declaration of function 'close'; did you mean 'clone'? [-Werror=implicit-function-declaration] close(evt_fd); ^~~~~ clone Also use the newly added scandirat feature test to check if that function is available, providing a HAVE_SCANDIRAT_SUPPORT conditional warning to the user if it isn't available. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/print-events.c | 38 +++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 62e9ea7dcf40..386b1ab0b60e 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -4,7 +4,9 @@ #include #include #include +#include #include +#include #include #include @@ -56,7 +58,18 @@ static const struct event_symbol event_symbols_tool[PERF_TOOL_MAX] = { /* * Print the events from /tracing/events */ -void print_tracepoint_events(const struct print_callbacks *print_cb, void *print_state) +void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unused, void *print_state __maybe_unused) +{ + char *events_path = get_tracing_file("events"); + int events_fd = open(events_path, O_PATH); + + put_tracing_file(events_path); + if (events_fd < 0) { + printf("Error: failed to open tracing events directory\n"); + return; + } + +#ifdef HAVE_SCANDIRAT_SUPPORT { struct dirent **sys_namelist = NULL; int sys_items = tracing_events__scandir_alphasort(&sys_namelist); @@ -64,7 +77,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb, void *print for (int i = 0; i < sys_items; i++) { struct dirent *sys_dirent = sys_namelist[i]; struct dirent **evt_namelist = NULL; - char *dir_path; + int dir_fd; int evt_items; if (sys_dirent->d_type != DT_DIR || @@ -72,22 +85,26 @@ void print_tracepoint_events(const struct print_callbacks *print_cb, void *print !strcmp(sys_dirent->d_name, "..")) continue; - dir_path = get_events_file(sys_dirent->d_name); - if (!dir_path) + dir_fd = openat(events_fd, sys_dirent->d_name, O_PATH); + if (dir_fd < 0) continue; - evt_items = scandir(dir_path, &evt_namelist, NULL, alphasort); + evt_items = scandirat(events_fd, sys_dirent->d_name, &evt_namelist, NULL, alphasort); for (int j = 0; j < evt_items; j++) { struct dirent *evt_dirent = evt_namelist[j]; char evt_path[MAXPATHLEN]; + int evt_fd; if (evt_dirent->d_type != DT_DIR || !strcmp(evt_dirent->d_name, ".") || !strcmp(evt_dirent->d_name, "..")) continue; - if (tp_event_has_id(dir_path, evt_dirent) != 0) + snprintf(evt_path, sizeof(evt_path), "%s/id", evt_dirent->d_name); + evt_fd = openat(dir_fd, evt_path, O_RDONLY); + if (evt_fd < 0) continue; + close(evt_fd); snprintf(evt_path, MAXPATHLEN, "%s:%s", sys_dirent->d_name, evt_dirent->d_name); @@ -103,11 +120,18 @@ void print_tracepoint_events(const struct print_callbacks *print_cb, void *print /*long_desc=*/NULL, /*encoding_desc=*/NULL); } - free(dir_path); + close(dir_fd); free(evt_namelist); } + free(sys_namelist); } +#else + printf("\nWARNING: Your libc doesn't have the scandir function, please ask its maintainers to implement it.\n" + " As a rough fallback, please do 'ls %s' to see the available tracepoint events.\n", events_path); +#endif + close(events_fd); +} void print_sdt_events(const struct print_callbacks *print_cb, void *print_state) { -- GitLab From 66c9598bd8916c6c1319d0100ac916cac89d4b0e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:42 -0700 Subject: [PATCH 1969/5631] perf tools: Fix a asan issue in parse_events_multi_pmu_add() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the parse_events_multi_pmu_add() it passes the 'config' variable twice to parse_events_term__num() - one for config and another for loc_term. I'm not sure about the second one as it's converted to YYLTYPE variable. Asan reports it like below: In function ‘parse_events_term__num’, inlined from ‘parse_events_multi_pmu_add’ at util/parse-events.c:1602:6: util/parse-events.c:2653:64: error: array subscript ‘YYLTYPE[0]’ is partly outside array bounds of ‘char[8]’ [-Werror=array-bounds] 2653 | .err_term = loc_term ? loc_term->first_column : 0, | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~ util/parse-events.c: In function ‘parse_events_multi_pmu_add’: util/parse-events.c:1587:15: note: object ‘config’ of size 8 1587 | char *config; | ^~~~~~ cc1: all warnings being treated as errors Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index cc8e8766ca30..0010e5e0ee68 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1601,7 +1601,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, - config, 1, false, &config, + config, 1, false, NULL, NULL) < 0) { free(config); goto out_err; -- GitLab From eec1131091c88e5e72cb012a2e3b3789fbb53c15 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:43 -0700 Subject: [PATCH 1970/5631] perf pmu: Add perf_pmu__destroy() function It seems there's no function to delete the perf pmu struct. Add the perf_pmu__destroy() to do the job. While at it, add some more helper functions to delete pmu aliases and caps. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 50 +++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/pmu.h | 2 ++ 2 files changed, 52 insertions(+) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e3aae731bd6f..b112606f36ec 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -300,6 +300,16 @@ void perf_pmu_free_alias(struct perf_pmu_alias *newalias) free(newalias); } +static void perf_pmu__del_aliases(struct perf_pmu *pmu) +{ + struct perf_pmu_alias *alias, *tmp; + + list_for_each_entry_safe(alias, tmp, &pmu->aliases, list) { + list_del(&alias->list); + perf_pmu_free_alias(alias); + } +} + /* Merge an alias, search in alias list. If this name is already * present merge both of them to combine all information. */ @@ -921,6 +931,8 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name) if (is_hybrid) list_add_tail(&pmu->hybrid_list, &perf_pmu__hybrid_pmus); + else + INIT_LIST_HEAD(&pmu->hybrid_list); pmu->default_config = perf_pmu__get_default_config(pmu); @@ -1750,6 +1762,18 @@ static int perf_pmu__new_caps(struct list_head *list, char *name, char *value) return -ENOMEM; } +static void perf_pmu__del_caps(struct perf_pmu *pmu) +{ + struct perf_pmu_caps *caps, *tmp; + + list_for_each_entry_safe(caps, tmp, &pmu->caps, list) { + list_del(&caps->list); + free(caps->name); + free(caps->value); + free(caps); + } +} + /* * Reading/parsing the given pmu capabilities, which should be located at: * /sys/bus/event_source/devices//caps as sysfs group attributes. @@ -1932,3 +1956,29 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, return 0; return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename); } + +static void perf_pmu__delete(struct perf_pmu *pmu) +{ + perf_pmu__del_formats(&pmu->format); + perf_pmu__del_aliases(pmu); + perf_pmu__del_caps(pmu); + + perf_cpu_map__put(pmu->cpus); + + free(pmu->default_config); + free(pmu->name); + free(pmu->alias_name); + free(pmu); +} + +void perf_pmu__destroy(void) +{ + struct perf_pmu *pmu, *tmp; + + list_for_each_entry_safe(pmu, tmp, &pmus, list) { + list_del(&pmu->list); + list_del(&pmu->hybrid_list); + + perf_pmu__delete(pmu); + } +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 24cf69ab32cd..72fd5de334c0 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -259,4 +259,6 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, const char *pmu_name, const char *filename); FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); +void perf_pmu__destroy(void); + #endif /* __PMU_H */ -- GitLab From f6a7bbbfe61cc34c4e443141d3eb110a80473d8c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:44 -0700 Subject: [PATCH 1971/5631] perf bench: Add pmu-scan benchmark The pmu-scan benchmark will repeatedly scan the sysfs to get the available PMU information. $ ./perf bench internals pmu-scan # Running 'internals/pmu-scan' benchmark: Computing performance of sysfs PMU event scan for 100 times Average PMU scanning took: 6850.990 usec (+- 48.445 usec) Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/Build | 1 + tools/perf/bench/bench.h | 1 + tools/perf/bench/pmu-scan.c | 184 ++++++++++++++++++++++++++++++++++++ tools/perf/builtin-bench.c | 1 + 4 files changed, 187 insertions(+) create mode 100644 tools/perf/bench/pmu-scan.c diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 6b6155a8ad09..0f158dc8139b 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -15,6 +15,7 @@ perf-y += find-bit-bench.o perf-y += inject-buildid.o perf-y += evlist-open-close.o perf-y += breakpoint.o +perf-y += pmu-scan.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h index edfc25793cca..0d2b65976212 100644 --- a/tools/perf/bench/bench.h +++ b/tools/perf/bench/bench.h @@ -42,6 +42,7 @@ int bench_inject_build_id(int argc, const char **argv); int bench_evlist_open_close(int argc, const char **argv); int bench_breakpoint_thread(int argc, const char **argv); int bench_breakpoint_enable(int argc, const char **argv); +int bench_pmu_scan(int argc, const char **argv); #define BENCH_FORMAT_DEFAULT_STR "default" #define BENCH_FORMAT_DEFAULT 0 diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c new file mode 100644 index 000000000000..f0f007843bb8 --- /dev/null +++ b/tools/perf/bench/pmu-scan.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Benchmark scanning sysfs files for PMU information. + * + * Copyright 2023 Google LLC. + */ +#include +#include "bench.h" +#include "util/debug.h" +#include "util/pmu.h" +#include "util/pmus.h" +#include "util/stat.h" +#include +#include +#include +#include + +static unsigned int iterations = 100; + +struct pmu_scan_result { + char *name; + int nr_aliases; + int nr_formats; + int nr_caps; +}; + +static const struct option options[] = { + OPT_UINTEGER('i', "iterations", &iterations, + "Number of iterations used to compute average"), + OPT_END() +}; + +static const char *const bench_usage[] = { + "perf bench internals pmu-scan ", + NULL +}; + +static int nr_pmus; +static struct pmu_scan_result *results; + +static int save_result(void) +{ + struct perf_pmu *pmu; + struct list_head *list; + struct pmu_scan_result *r; + + perf_pmu__scan(NULL); + + perf_pmus__for_each_pmu(pmu) { + r = realloc(results, (nr_pmus + 1) * sizeof(*r)); + if (r == NULL) + return -ENOMEM; + + results = r; + r = results + nr_pmus; + + r->name = strdup(pmu->name); + r->nr_caps = pmu->nr_caps; + + r->nr_aliases = 0; + list_for_each(list, &pmu->aliases) + r->nr_aliases++; + + r->nr_formats = 0; + list_for_each(list, &pmu->format) + r->nr_formats++; + + pr_debug("pmu[%d] name=%s, nr_caps=%d, nr_aliases=%d, nr_formats=%d\n", + nr_pmus, r->name, r->nr_caps, r->nr_aliases, r->nr_formats); + nr_pmus++; + } + + perf_pmu__destroy(); + return 0; +} + +static int check_result(void) +{ + struct pmu_scan_result *r; + struct perf_pmu *pmu; + struct list_head *list; + int nr; + + for (int i = 0; i < nr_pmus; i++) { + r = &results[i]; + pmu = perf_pmu__find(r->name); + if (pmu == NULL) { + pr_err("Cannot find PMU %s\n", r->name); + return -1; + } + + if (pmu->nr_caps != (u32)r->nr_caps) { + pr_err("Unmatched number of event caps in %s: expect %d vs got %d\n", + pmu->name, r->nr_caps, pmu->nr_caps); + return -1; + } + + nr = 0; + list_for_each(list, &pmu->aliases) + nr++; + if (nr != r->nr_aliases) { + pr_err("Unmatched number of event aliases in %s: expect %d vs got %d\n", + pmu->name, r->nr_aliases, nr); + return -1; + } + + nr = 0; + list_for_each(list, &pmu->format) + nr++; + if (nr != r->nr_formats) { + pr_err("Unmatched number of event formats in %s: expect %d vs got %d\n", + pmu->name, r->nr_formats, nr); + return -1; + } + } + return 0; +} + +static void delete_result(void) +{ + for (int i = 0; i < nr_pmus; i++) + free(results[i].name); + free(results); + + results = NULL; + nr_pmus = 0; +} + +static int run_pmu_scan(void) +{ + struct stats stats; + struct timeval start, end, diff; + double time_average, time_stddev; + u64 runtime_us; + unsigned int i; + int ret; + + init_stats(&stats); + pr_info("Computing performance of sysfs PMU event scan for %u times\n", + iterations); + + if (save_result() < 0) { + pr_err("Failed to initialize PMU scan result\n"); + return -1; + } + + for (i = 0; i < iterations; i++) { + gettimeofday(&start, NULL); + perf_pmu__scan(NULL); + gettimeofday(&end, NULL); + + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&stats, runtime_us); + + ret = check_result(); + perf_pmu__destroy(); + if (ret < 0) + break; + } + + time_average = avg_stats(&stats); + time_stddev = stddev_stats(&stats); + pr_info(" Average PMU scanning took: %.3f usec (+- %.3f usec)\n", + time_average, time_stddev); + + delete_result(); + return 0; +} + +int bench_pmu_scan(int argc, const char **argv) +{ + int err = 0; + + argc = parse_options(argc, argv, options, bench_usage, 0); + if (argc) { + usage_with_options(bench_usage, options); + exit(EXIT_FAILURE); + } + + err = run_pmu_scan(); + + return err; +} diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index d0fcc3cdc185..58f1cfe1eb34 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -92,6 +92,7 @@ static struct bench internals_benchmarks[] = { { "kallsyms-parse", "Benchmark kallsyms parsing", bench_kallsyms_parse }, { "inject-build-id", "Benchmark build-id injection", bench_inject_build_id }, { "evlist-open-close", "Benchmark evlist open and close", bench_evlist_open_close }, + { "pmu-scan", "Benchmark sysfs PMU info scanning", bench_pmu_scan }, { NULL, NULL, NULL } }; -- GitLab From e293a5e816c03b57f07078db60497933f3400b2a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:45 -0700 Subject: [PATCH 1972/5631] perf pmu: Use relative path for sysfs scan The PMU information is in the kernel sysfs so it needs to scan the directory to get the whole information like event aliases, formats and so on. During the traversal, it opens a lot of files and directories like below: dir = opendir("/sys/bus/event_source/devices"); while (dentry = readdir(dir)) { char buf[PATH_MAX]; snprintf(buf, sizeof(buf), "%s/%s", "/sys/bus/event_source/devices", dentry->d_name); fd = open(buf, O_RDONLY); ... } But this is not good since it needs to copy the string to build the absolute pathname, and it makes redundant pathname walk (from the /sys) unnecessarily. We can use openat(2) to open the file in the given directory. While it's not a problem ususally, it can be a problem when the kernel has contentions on the sysfs. Add a couple of new helper to return the file descriptor of PMU directory so that it can use it with relative paths. * perf_pmu__event_source_devices_fd() - returns a fd for the PMU root ("/sys/bus/event_source/devices") * perf_pmu__pathname_fd() - returns a fd for "/" under the PMU root Now the above code can be converted something like below: dirfd = perf_pmu__event_source_devices_fd(); dir = fdopendir(dirfd); while (dentry = readdir(dir)) { fd = openat(dirfd, dentry->d_name, O_RDONLY); ... } Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/pmu.c | 9 ++- tools/perf/util/pmu.c | 161 +++++++++++++++++++++++++---------------- tools/perf/util/pmu.h | 4 +- 3 files changed, 111 insertions(+), 63 deletions(-) diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index 8507bd615e97..3cf25f883df7 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -3,6 +3,7 @@ #include "pmu.h" #include "tests.h" #include +#include #include #include #include @@ -149,10 +150,16 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe do { struct perf_event_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); - ret = perf_pmu__format_parse(format, &formats); + fd = open(format, O_DIRECTORY); + if (fd < 0) { + ret = fd; + break; + } + ret = perf_pmu__format_parse(fd, &formats); if (ret) break; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index b112606f36ec..9fc6b8b5732b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -62,38 +62,38 @@ extern FILE *perf_pmu_in; static bool hybrid_scanned; +static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name); + /* * Parse & process all the sysfs attributes located under * the directory specified in 'dir' parameter. */ -int perf_pmu__format_parse(char *dir, struct list_head *head) +int perf_pmu__format_parse(int dirfd, struct list_head *head) { struct dirent *evt_ent; DIR *format_dir; int ret = 0; - format_dir = opendir(dir); + format_dir = fdopendir(dirfd); if (!format_dir) return -EINVAL; while (!ret && (evt_ent = readdir(format_dir))) { - char path[PATH_MAX]; char *name = evt_ent->d_name; - FILE *file; + int fd; if (!strcmp(name, ".") || !strcmp(name, "..")) continue; - snprintf(path, PATH_MAX, "%s/%s", dir, name); ret = -EINVAL; - file = fopen(path, "r"); - if (!file) + fd = openat(dirfd, name, O_RDONLY); + if (fd < 0) break; - perf_pmu_in = file; + perf_pmu_in = fdopen(fd, "r"); ret = perf_pmu_parse(head, name); - fclose(file); + fclose(perf_pmu_in); } closedir(format_dir); @@ -105,17 +105,16 @@ int perf_pmu__format_parse(char *dir, struct list_head *head) * located at: * /sys/bus/event_source/devices//format as sysfs group attributes. */ -static int pmu_format(const char *name, struct list_head *format) +static int pmu_format(int dirfd, const char *name, struct list_head *format) { - char path[PATH_MAX]; - - if (!perf_pmu__pathname_scnprintf(path, sizeof(path), name, "format")) - return -1; + int fd; - if (!file_available(path)) + fd = perf_pmu__pathname_fd(dirfd, name, "format", O_DIRECTORY); + if (fd < 0) return 0; - if (perf_pmu__format_parse(path, format)) + /* it'll close the fd */ + if (perf_pmu__format_parse(fd, format)) return -1; return 0; @@ -158,7 +157,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval) return ret; } -static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name) +static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, int dirfd, char *name) { struct stat st; ssize_t sret; @@ -166,9 +165,9 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * int fd, ret = -1; char path[PATH_MAX]; - scnprintf(path, PATH_MAX, "%s/%s.scale", dir, name); + scnprintf(path, PATH_MAX, "%s.scale", name); - fd = open(path, O_RDONLY); + fd = openat(dirfd, path, O_RDONLY); if (fd == -1) return -1; @@ -190,15 +189,15 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char * return ret; } -static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name) +static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, int dirfd, char *name) { char path[PATH_MAX]; ssize_t sret; int fd; - scnprintf(path, PATH_MAX, "%s/%s.unit", dir, name); + scnprintf(path, PATH_MAX, "%s.unit", name); - fd = open(path, O_RDONLY); + fd = openat(dirfd, path, O_RDONLY); if (fd == -1) return -1; @@ -221,14 +220,14 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n } static int -perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name) +perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, int dirfd, char *name) { char path[PATH_MAX]; int fd; - scnprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name); + scnprintf(path, PATH_MAX, "%s.per-pkg", name); - fd = open(path, O_RDONLY); + fd = openat(dirfd, path, O_RDONLY); if (fd == -1) return -1; @@ -239,14 +238,14 @@ perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name) } static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias, - char *dir, char *name) + int dirfd, char *name) { char path[PATH_MAX]; int fd; - scnprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name); + scnprintf(path, PATH_MAX, "%s.snapshot", name); - fd = open(path, O_RDONLY); + fd = openat(dirfd, path, O_RDONLY); if (fd == -1) return -1; @@ -332,7 +331,7 @@ static bool perf_pmu_merge_alias(struct perf_pmu_alias *newalias, return false; } -static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, +static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, char *desc, char *val, const struct pmu_event *pe) { struct parse_events_term *term; @@ -391,14 +390,14 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, } alias->name = strdup(name); - if (dir) { + if (dirfd >= 0) { /* * load unit name and scale if available */ - perf_pmu__parse_unit(alias, dir, name); - perf_pmu__parse_scale(alias, dir, name); - perf_pmu__parse_per_pkg(alias, dir, name); - perf_pmu__parse_snapshot(alias, dir, name); + perf_pmu__parse_unit(alias, dirfd, name); + perf_pmu__parse_scale(alias, dirfd, name); + perf_pmu__parse_per_pkg(alias, dirfd, name); + perf_pmu__parse_snapshot(alias, dirfd, name); } alias->desc = desc ? strdup(desc) : NULL; @@ -419,7 +418,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, return 0; } -static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file) +static int perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, FILE *file) { char buf[256]; int ret; @@ -433,7 +432,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI /* Remove trailing newline from sysfs file */ strim(buf); - return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL); + return __perf_pmu__new_alias(list, dirfd, name, NULL, buf, NULL); } static inline bool pmu_alias_info_file(char *name) @@ -457,17 +456,17 @@ static inline bool pmu_alias_info_file(char *name) * Process all the sysfs attributes located under the directory * specified in 'dir' parameter. */ -static int pmu_aliases_parse(char *dir, struct list_head *head) +static int pmu_aliases_parse(int dirfd, struct list_head *head) { struct dirent *evt_ent; DIR *event_dir; + int fd; - event_dir = opendir(dir); + event_dir = fdopendir(dirfd); if (!event_dir) return -EINVAL; while ((evt_ent = readdir(event_dir))) { - char path[PATH_MAX]; char *name = evt_ent->d_name; FILE *file; @@ -480,15 +479,14 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) if (pmu_alias_info_file(name)) continue; - scnprintf(path, PATH_MAX, "%s/%s", dir, name); - - file = fopen(path, "r"); + fd = openat(dirfd, name, O_RDONLY); + file = fdopen(fd, "r"); if (!file) { - pr_debug("Cannot open %s\n", path); + pr_debug("Cannot open %s\n", name); continue; } - if (perf_pmu__new_alias(head, dir, name, file) < 0) + if (perf_pmu__new_alias(head, dirfd, name, file) < 0) pr_debug("Cannot set up %s\n", name); fclose(file); } @@ -501,17 +499,16 @@ static int pmu_aliases_parse(char *dir, struct list_head *head) * Reading the pmu event aliases definition, which should be located at: * /sys/bus/event_source/devices//events as sysfs group attributes. */ -static int pmu_aliases(const char *name, struct list_head *head) +static int pmu_aliases(int dirfd, const char *name, struct list_head *head) { - char path[PATH_MAX]; - - if (!perf_pmu__pathname_scnprintf(path, sizeof(path), name, "events")) - return -1; + int fd; - if (!file_available(path)) + fd = perf_pmu__pathname_fd(dirfd, name, "events", O_DIRECTORY); + if (fd < 0) return 0; - if (pmu_aliases_parse(path, head)) + /* it'll close the fd */ + if (pmu_aliases_parse(fd, head)) return -1; return 0; @@ -544,14 +541,15 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, /* Add all pmus in sysfs to pmu list: */ static void pmu_read_sysfs(void) { - char path[PATH_MAX]; + int fd; DIR *dir; struct dirent *dent; - if (!perf_pmu__event_source_devices_scnprintf(path, sizeof(path))) + fd = perf_pmu__event_source_devices_fd(); + if (fd < 0) return; - dir = opendir(path); + dir = fdopendir(fd); if (!dir) return; @@ -559,7 +557,7 @@ static void pmu_read_sysfs(void) if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, "..")) continue; /* add to static LIST_HEAD(pmus): */ - perf_pmu__find(dent->d_name); + perf_pmu__find2(fd, dent->d_name); } closedir(dir); @@ -763,7 +761,7 @@ static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, new_alias: /* need type casts to override 'const' */ - __perf_pmu__new_alias(data->head, NULL, (char *)pe->name, (char *)pe->desc, + __perf_pmu__new_alias(data->head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, pe); return 0; } @@ -814,7 +812,7 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, if (!strcmp(pmu->id, pe->compat) && pmu_uncore_alias_match(pe->pmu, pmu->name)) { - __perf_pmu__new_alias(idata->head, NULL, + __perf_pmu__new_alias(idata->head, -1, (char *)pe->name, (char *)pe->desc, (char *)pe->event, @@ -863,7 +861,7 @@ static int pmu_max_precise(struct perf_pmu *pmu) return max_precise; } -static struct perf_pmu *pmu_lookup(const char *lookup_name) +static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) { struct perf_pmu *pmu; LIST_HEAD(format); @@ -884,13 +882,13 @@ static struct perf_pmu *pmu_lookup(const char *lookup_name) * type value and format definitions. Load both right * now. */ - if (pmu_format(name, &format)) + if (pmu_format(dirfd, name, &format)) return NULL; /* * Check the aliases first to avoid unnecessary work. */ - if (pmu_aliases(name, &aliases)) + if (pmu_aliases(dirfd, name, &aliases)) return NULL; pmu = zalloc(sizeof(*pmu)); @@ -1024,6 +1022,27 @@ bool evsel__is_aux_event(const struct evsel *evsel) } struct perf_pmu *perf_pmu__find(const char *name) +{ + struct perf_pmu *pmu; + int dirfd; + + /* + * Once PMU is loaded it stays in the list, + * so we keep us from multiple reading/parsing + * the pmu format definitions. + */ + pmu = pmu_find(name); + if (pmu) + return pmu; + + dirfd = perf_pmu__event_source_devices_fd(); + pmu = pmu_lookup(dirfd, name); + close(dirfd); + + return pmu; +} + +static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name) { struct perf_pmu *pmu; @@ -1036,7 +1055,7 @@ struct perf_pmu *perf_pmu__find(const char *name) if (pmu) return pmu; - return pmu_lookup(name); + return pmu_lookup(dirfd, name); } static struct perf_pmu_format * @@ -1938,6 +1957,18 @@ int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size) return scnprintf(pathname, size, "%s/bus/event_source/devices/", sysfs); } +int perf_pmu__event_source_devices_fd(void) +{ + char path[PATH_MAX]; + const char *sysfs = sysfs__mountpoint(); + + if (!sysfs) + return -1; + + scnprintf(path, sizeof(path), "%s/bus/event_source/devices/", sysfs); + return open(path, O_DIRECTORY); +} + /* * Fill 'buf' with the path to a file or folder in 'pmu_name' in * sysfs. For example if pmu_name = "cs_etm" and 'filename' = "format" @@ -1957,6 +1988,14 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, return scnprintf(buf, size, "%s%s/%s", base_path, pmu_name, filename); } +int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags) +{ + char path[PATH_MAX]; + + scnprintf(path, sizeof(path), "%s/%s", pmu_name, filename); + return openat(dirfd, path, flags); +} + static void perf_pmu__delete(struct perf_pmu *pmu) { perf_pmu__del_formats(&pmu->format); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 72fd5de334c0..751c7016e7b6 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -211,7 +211,7 @@ void perf_pmu_error(struct list_head *list, char *name, char const *msg); int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits); void perf_pmu__set_format(unsigned long *bits, long from, long to); -int perf_pmu__format_parse(char *dir, struct list_head *head); +int perf_pmu__format_parse(int dirfd, struct list_head *head); void perf_pmu__del_formats(struct list_head *formats); struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu); @@ -257,6 +257,8 @@ double perf_pmu__cpu_slots_per_cycle(void); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, const char *pmu_name, const char *filename); +int perf_pmu__event_source_devices_fd(void); +int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags); FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); void perf_pmu__destroy(void); -- GitLab From b39094d37d0c1f6399a1a1a24453ff48b4a0c7a6 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:46 -0700 Subject: [PATCH 1973/5631] perf pmu: Use relative path in perf_pmu__caps_parse() Likewise, it needs to traverse the pmu/caps directory, let's use openat() with the dirfd instead of open() using the absolute path. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Ingo Molnar Cc: Leo Yan Cc: Kan Liang Cc: LKML Cc: linux-perf-users@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 9fc6b8b5732b..0c1d87f10b23 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1804,6 +1804,7 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) char caps_path[PATH_MAX]; DIR *caps_dir; struct dirent *evt_ent; + int caps_fd; if (pmu->caps_initialized) return pmu->nr_caps; @@ -1822,18 +1823,19 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) if (!caps_dir) return -EINVAL; + caps_fd = dirfd(caps_dir); + while ((evt_ent = readdir(caps_dir)) != NULL) { - char path[PATH_MAX + NAME_MAX + 1]; char *name = evt_ent->d_name; char value[128]; FILE *file; + int fd; if (!strcmp(name, ".") || !strcmp(name, "..")) continue; - snprintf(path, sizeof(path), "%s/%s", caps_path, name); - - file = fopen(path, "r"); + fd = openat(caps_fd, name, O_RDONLY); + file = fdopen(fd, "r"); if (!file) continue; -- GitLab From 463786658d234df43ad1d9dfcf8aba25176d071c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:47 -0700 Subject: [PATCH 1974/5631] perf pmu: Use relative path in setup_pmu_alias_list() Likewise, x86 needs to traverse the PMU list to build alias. Let's use the new helpers to use relative paths. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/pmu.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index f73b80dcd8bd..3c0de3370d7e 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -71,7 +71,7 @@ static struct pmu_alias *pmu_alias__new(char *name, char *alias) static int setup_pmu_alias_list(void) { - char path[PATH_MAX]; + int fd, dirfd; DIR *dir; struct dirent *dent; struct pmu_alias *pmu_alias; @@ -79,10 +79,11 @@ static int setup_pmu_alias_list(void) FILE *file; int ret = -ENOMEM; - if (!perf_pmu__event_source_devices_scnprintf(path, sizeof(path))) + dirfd = perf_pmu__event_source_devices_fd(); + if (dirfd < 0) return -1; - dir = opendir(path); + dir = fdopendir(dirfd); if (!dir) return -errno; @@ -91,11 +92,11 @@ static int setup_pmu_alias_list(void) !strcmp(dent->d_name, "..")) continue; - perf_pmu__pathname_scnprintf(path, sizeof(path), dent->d_name, "alias"); - if (!file_available(path)) + fd = perf_pmu__pathname_fd(dirfd, dent->d_name, "alias", O_RDONLY); + if (fd < 0) continue; - file = fopen(path, "r"); + file = fdopen(fd, "r"); if (!file) continue; -- GitLab From 3a69672e881afc1dcc8ed60272197af8958b5404 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:48 -0700 Subject: [PATCH 1975/5631] perf pmu: Add perf_pmu__{open,scan}_file_at() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These two helpers will also use openat() to reduce the overhead with relative pathnames. Convert other functions in pmu_lookup() to use the new helpers. Committer testing: Before: ⬢[acme@toolbox perf-tools-next]$ perf bench internals pmu-scan # Running 'internals/pmu-scan' benchmark: Computing performance of sysfs PMU event scan for 100 times Average PMU scanning took: 2729.040 usec (+- 7.117 usec) ⬢[acme@toolbox perf-tools-next]$ After: ⬢[acme@toolbox perf-tools-next]$ perf bench internals pmu-scan # Running 'internals/pmu-scan' benchmark: Computing performance of sysfs PMU event scan for 100 times Average PMU scanning took: 2419.870 usec (+- 9.057 usec) ⬢[acme@toolbox perf-tools-next]$ Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 57 ++++++++++++++++++++++++++++++++++--------- tools/perf/util/pmu.h | 6 ++++- 2 files changed, 50 insertions(+), 13 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 0c1d87f10b23..78a407b42ad1 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -567,7 +567,7 @@ static void pmu_read_sysfs(void) * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64) * may have a "cpus" file. */ -static struct perf_cpu_map *pmu_cpumask(const char *name) +static struct perf_cpu_map *pmu_cpumask(int dirfd, const char *name) { struct perf_cpu_map *cpus; const char *templates[] = { @@ -582,10 +582,11 @@ static struct perf_cpu_map *pmu_cpumask(const char *name) strlcpy(pmu_name, name, sizeof(pmu_name)); for (template = templates; *template; template++) { - file = perf_pmu__open_file(&pmu, *template); + file = perf_pmu__open_file_at(&pmu, dirfd, *template); if (!file) continue; cpus = perf_cpu_map__read(file); + fclose(file); if (cpus) return cpus; } @@ -593,15 +594,19 @@ static struct perf_cpu_map *pmu_cpumask(const char *name) return NULL; } -static bool pmu_is_uncore(const char *name) +static bool pmu_is_uncore(int dirfd, const char *name) { - char path[PATH_MAX]; + int fd; if (perf_pmu__hybrid_mounted(name)) return false; - perf_pmu__pathname_scnprintf(path, sizeof(path), name, "cpumask"); - return file_available(path); + fd = perf_pmu__pathname_fd(dirfd, name, "cpumask", O_PATH); + if (fd < 0) + return false; + + close(fd); + return true; } static char *pmu_id(const char *name) @@ -853,11 +858,11 @@ pmu_find_alias_name(const char *name __maybe_unused) return NULL; } -static int pmu_max_precise(struct perf_pmu *pmu) +static int pmu_max_precise(int dirfd, struct perf_pmu *pmu) { int max_precise = -1; - perf_pmu__scan_file(pmu, "caps/max_precise", "%d", &max_precise); + perf_pmu__scan_file_at(pmu, dirfd, "caps/max_precise", "%d", &max_precise); return max_precise; } @@ -895,14 +900,14 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) if (!pmu) return NULL; - pmu->cpus = pmu_cpumask(name); + pmu->cpus = pmu_cpumask(dirfd, name); pmu->name = strdup(name); if (!pmu->name) goto err; /* Read type, and ensure that type value is successfully assigned (return 1) */ - if (perf_pmu__scan_file(pmu, "type", "%u", &type) != 1) + if (perf_pmu__scan_file_at(pmu, dirfd, "type", "%u", &type) != 1) goto err; alias_name = pmu_find_alias_name(name); @@ -913,10 +918,10 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) } pmu->type = type; - pmu->is_uncore = pmu_is_uncore(name); + pmu->is_uncore = pmu_is_uncore(dirfd, name); if (pmu->is_uncore) pmu->id = pmu_id(name); - pmu->max_precise = pmu_max_precise(pmu); + pmu->max_precise = pmu_max_precise(dirfd, pmu); pmu_add_cpu_aliases(&aliases, pmu); pmu_add_sys_aliases(&aliases, pmu); @@ -1730,6 +1735,17 @@ FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) return fopen(path, "r"); } +FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name) +{ + int fd; + + fd = perf_pmu__pathname_fd(dirfd, pmu->name, name, O_RDONLY); + if (fd < 0) + return NULL; + + return fdopen(fd, "r"); +} + int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) { @@ -1747,6 +1763,23 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return ret; } +int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name, + const char *fmt, ...) +{ + va_list args; + FILE *file; + int ret = EOF; + + va_start(args, fmt); + file = perf_pmu__open_file_at(pmu, dirfd, name); + if (file) { + ret = vfscanf(file, fmt, args); + fclose(file); + } + va_end(args); + return ret; +} + bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name) { char path[PATH_MAX]; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 751c7016e7b6..32c3a75bca0e 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -220,7 +220,12 @@ bool is_pmu_core(const char *name); void print_pmu_events(const struct print_callbacks *print_cb, void *print_state); bool pmu_have_event(const char *pname, const char *name); +FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); +FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name); + int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); +int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name, + const char *fmt, ...) __scanf(4, 5); bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name); @@ -259,7 +264,6 @@ int perf_pmu__pathname_scnprintf(char *buf, size_t size, const char *pmu_name, const char *filename); int perf_pmu__event_source_devices_fd(void); int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags); -FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); void perf_pmu__destroy(void); -- GitLab From 98b7ce0ed8f7a93ac0f6e0a0576c70093b669a71 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 31 Mar 2023 13:29:49 -0700 Subject: [PATCH 1976/5631] perf intel-pt: Use perf_pmu__scan_file_at() if possible Intel-PT calls perf_pmu__scan_file() a lot, let's use relative address when it accesses multiple files at one place. Signed-off-by: Namhyung Kim Acked-by: Adrian Hunter Acked-by: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230331202949.810326-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/intel-pt.c | 52 ++++++++++++++++++----------- 1 file changed, 32 insertions(+), 20 deletions(-) diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 1e39a034cee9..2cff11de9d8a 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -194,16 +194,19 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) int pos = 0; u64 config; char c; + int dirfd; + + dirfd = perf_pmu__event_source_devices_fd(); pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc"); - if (perf_pmu__scan_file(intel_pt_pmu, "caps/mtc", "%d", - &mtc) != 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "caps/mtc", "%d", + &mtc) != 1) mtc = 1; if (mtc) { - if (perf_pmu__scan_file(intel_pt_pmu, "caps/mtc_periods", "%x", - &mtc_periods) != 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "caps/mtc_periods", "%x", + &mtc_periods) != 1) mtc_periods = 0; if (mtc_periods) { mtc_period = intel_pt_pick_bit(mtc_periods, 3); @@ -212,13 +215,13 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) } } - if (perf_pmu__scan_file(intel_pt_pmu, "caps/psb_cyc", "%d", - &psb_cyc) != 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "caps/psb_cyc", "%d", + &psb_cyc) != 1) psb_cyc = 1; if (psb_cyc && mtc_periods) { - if (perf_pmu__scan_file(intel_pt_pmu, "caps/psb_periods", "%x", - &psb_periods) != 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "caps/psb_periods", "%x", + &psb_periods) != 1) psb_periods = 0; if (psb_periods) { psb_period = intel_pt_pick_bit(psb_periods, 3); @@ -227,8 +230,8 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) } } - if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && - perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "format/pt", "%c", &c) == 1 && + perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "format/branch", "%c", &c) == 1) pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch"); pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf); @@ -236,6 +239,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format, buf, &config); + close(dirfd); return config; } @@ -488,7 +492,7 @@ static void intel_pt_valid_str(char *str, size_t len, u64 valid) } } -static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, +static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, int dirfd, const char *caps, const char *name, const char *supported, u64 config) { @@ -498,11 +502,11 @@ static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, u64 bits; int ok; - if (perf_pmu__scan_file(intel_pt_pmu, caps, "%llx", &valid) != 1) + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, caps, "%llx", &valid) != 1) valid = 0; if (supported && - perf_pmu__scan_file(intel_pt_pmu, supported, "%d", &ok) == 1 && !ok) + perf_pmu__scan_file_at(intel_pt_pmu, dirfd, supported, "%d", &ok) == 1 && !ok) valid = 0; valid |= 1; @@ -531,37 +535,45 @@ static int intel_pt_val_config_term(struct perf_pmu *intel_pt_pmu, static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, struct evsel *evsel) { - int err; + int err, dirfd; char c; if (!evsel) return 0; + dirfd = perf_pmu__event_source_devices_fd(); + if (dirfd < 0) + return dirfd; + /* * If supported, force pass-through config term (pt=1) even if user * sets pt=0, which avoids senseless kernel errors. */ - if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && + if (perf_pmu__scan_file_at(intel_pt_pmu, dirfd, "format/pt", "%c", &c) == 1 && !(evsel->core.attr.config & 1)) { pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); evsel->core.attr.config |= 1; } - err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", + err = intel_pt_val_config_term(intel_pt_pmu, dirfd, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", evsel->core.attr.config); if (err) - return err; + goto out; - err = intel_pt_val_config_term(intel_pt_pmu, "caps/mtc_periods", + err = intel_pt_val_config_term(intel_pt_pmu, dirfd, "caps/mtc_periods", "mtc_period", "caps/mtc", evsel->core.attr.config); if (err) - return err; + goto out; - return intel_pt_val_config_term(intel_pt_pmu, "caps/psb_periods", + err = intel_pt_val_config_term(intel_pt_pmu, dirfd, "caps/psb_periods", "psb_period", "caps/psb_cyc", evsel->core.attr.config); + +out: + close(dirfd); + return err; } static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu, -- GitLab From c9dc580c43b8d83de0c14158e826f79e41098822 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 11:40:30 -0700 Subject: [PATCH 1977/5631] tools api: Add io__getline Reads a line to allocated memory up to a newline following the getline API. Committer notes: It also adds this new function to the 'api io' 'perf test' entry: $ perf test "api io" 64: Test api io : Ok $ Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230403184033.1836023-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/api/io.h | 45 +++++++++++++++++++++++++++++++++++++++ tools/perf/tests/api-io.c | 36 +++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+) diff --git a/tools/lib/api/io.h b/tools/lib/api/io.h index 777c20f6b604..d5e8cf0dada0 100644 --- a/tools/lib/api/io.h +++ b/tools/lib/api/io.h @@ -7,7 +7,9 @@ #ifndef __API_IO__ #define __API_IO__ +#include #include +#include #include struct io { @@ -112,4 +114,47 @@ static inline int io__get_dec(struct io *io, __u64 *dec) } } +/* Read up to and including the first newline following the pattern of getline. */ +static inline ssize_t io__getline(struct io *io, char **line_out, size_t *line_len_out) +{ + char buf[128]; + int buf_pos = 0; + char *line = NULL, *temp; + size_t line_len = 0; + int ch = 0; + + /* TODO: reuse previously allocated memory. */ + free(*line_out); + while (ch != '\n') { + ch = io__get_char(io); + + if (ch < 0) + break; + + if (buf_pos == sizeof(buf)) { + temp = realloc(line, line_len + sizeof(buf)); + if (!temp) + goto err_out; + line = temp; + memcpy(&line[line_len], buf, sizeof(buf)); + line_len += sizeof(buf); + buf_pos = 0; + } + buf[buf_pos++] = (char)ch; + } + temp = realloc(line, line_len + buf_pos + 1); + if (!temp) + goto err_out; + line = temp; + memcpy(&line[line_len], buf, buf_pos); + line[line_len + buf_pos] = '\0'; + line_len += buf_pos; + *line_out = line; + *line_len_out = line_len; + return line_len; +err_out: + free(line); + return -ENOMEM; +} + #endif /* __API_IO__ */ diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c index e91cf2c127f1..6aea84ca6673 100644 --- a/tools/perf/tests/api-io.c +++ b/tools/perf/tests/api-io.c @@ -289,6 +289,40 @@ static int test_get_dec(void) return ret; } +static int test_get_line(void) +{ + char path[PATH_MAX]; + struct io io; + char test_string[1024]; + char *line = NULL; + size_t i, line_len = 0; + size_t buf_size = 128; + int ret = 0; + + for (i = 0; i < 512; i++) + test_string[i] = 'a'; + test_string[512] = '\n'; + for (i = 513; i < 1023; i++) + test_string[i] = 'b'; + test_string[1023] = '\0'; + + if (setup_test(path, test_string, buf_size, &io)) + return -1; + + EXPECT_EQUAL((int)io__getline(&io, &line, &line_len), 513); + EXPECT_EQUAL((int)strlen(line), 513); + for (i = 0; i < 512; i++) + EXPECT_EQUAL(line[i], 'a'); + EXPECT_EQUAL(line[512], '\n'); + EXPECT_EQUAL((int)io__getline(&io, &line, &line_len), 510); + for (i = 0; i < 510; i++) + EXPECT_EQUAL(line[i], 'b'); + + free(line); + cleanup_test(path, &io); + return ret; +} + static int test__api_io(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { @@ -300,6 +334,8 @@ static int test__api_io(struct test_suite *test __maybe_unused, ret = TEST_FAIL; if (test_get_dec()) ret = TEST_FAIL; + if (test_get_line()) + ret = TEST_FAIL; return ret; } -- GitLab From b3801e7912316c7a100a05de152a80df4121871e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 11:40:31 -0700 Subject: [PATCH 1978/5631] perf srcline: Simplify addr2line subprocess Don't wrap stdin and stdout of subprocess with streams, use the api/io library for buffering. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230403184033.1836023-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 103 ++++++++++++++------------------------ 1 file changed, 38 insertions(+), 65 deletions(-) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f0a96a834e4b..5339ab4c5e12 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -10,6 +10,8 @@ #include #include +#include + #include "util/dso.h" #include "util/debug.h" #include "util/callchain.h" @@ -366,12 +368,6 @@ void dso__free_a2l(struct dso *dso) #else /* HAVE_LIBBFD_SUPPORT */ -struct a2l_subprocess { - struct child_process addr2line; - FILE *to_child; - FILE *from_child; -}; - static int filename_split(char *filename, unsigned int *line_nr) { char *sep; @@ -393,28 +389,18 @@ static int filename_split(char *filename, unsigned int *line_nr) return 0; } -static void addr2line_subprocess_cleanup(struct a2l_subprocess *a2l) +static void addr2line_subprocess_cleanup(struct child_process *a2l) { - if (a2l->addr2line.pid != -1) { - kill(a2l->addr2line.pid, SIGKILL); - finish_command(&a2l->addr2line); /* ignore result, we don't care */ - a2l->addr2line.pid = -1; - } - - if (a2l->to_child != NULL) { - fclose(a2l->to_child); - a2l->to_child = NULL; - } - - if (a2l->from_child != NULL) { - fclose(a2l->from_child); - a2l->from_child = NULL; + if (a2l->pid != -1) { + kill(a2l->pid, SIGKILL); + finish_command(a2l); /* ignore result, we don't care */ + a2l->pid = -1; } free(a2l); } -static struct a2l_subprocess *addr2line_subprocess_init(const char *addr2line_path, +static struct child_process *addr2line_subprocess_init(const char *addr2line_path, const char *binary_path) { const char *argv[] = { @@ -422,54 +408,34 @@ static struct a2l_subprocess *addr2line_subprocess_init(const char *addr2line_pa "-e", binary_path, "-i", "-f", NULL }; - struct a2l_subprocess *a2l = zalloc(sizeof(*a2l)); + struct child_process *a2l = zalloc(sizeof(*a2l)); int start_command_status = 0; - if (a2l == NULL) - goto out; - - a2l->to_child = NULL; - a2l->from_child = NULL; + if (a2l == NULL) { + pr_err("Failed to allocate memory for addr2line"); + return NULL; + } - a2l->addr2line.pid = -1; - a2l->addr2line.in = -1; - a2l->addr2line.out = -1; - a2l->addr2line.no_stderr = 1; + a2l->pid = -1; + a2l->in = -1; + a2l->out = -1; + a2l->no_stderr = 1; - a2l->addr2line.argv = argv; - start_command_status = start_command(&a2l->addr2line); - a2l->addr2line.argv = NULL; /* it's not used after start_command; avoid dangling pointers */ + a2l->argv = argv; + start_command_status = start_command(a2l); + a2l->argv = NULL; /* it's not used after start_command; avoid dangling pointers */ if (start_command_status != 0) { pr_warning("could not start addr2line (%s) for %s: start_command return code %d\n", addr2line_path, binary_path, start_command_status); - goto out; - } - - a2l->to_child = fdopen(a2l->addr2line.in, "w"); - if (a2l->to_child == NULL) { - pr_warning("could not open write-stream to addr2line (%s) of %s\n", - addr2line_path, binary_path); - goto out; - } - - a2l->from_child = fdopen(a2l->addr2line.out, "r"); - if (a2l->from_child == NULL) { - pr_warning("could not open read-stream from addr2line (%s) of %s\n", - addr2line_path, binary_path); - goto out; + addr2line_subprocess_cleanup(a2l); + return NULL; } return a2l; - -out: - if (a2l) - addr2line_subprocess_cleanup(a2l); - - return NULL; } -static int read_addr2line_record(struct a2l_subprocess *a2l, +static int read_addr2line_record(struct io *io, char **function, char **filename, unsigned int *line_nr) @@ -494,7 +460,7 @@ static int read_addr2line_record(struct a2l_subprocess *a2l, if (line_nr != NULL) *line_nr = 0; - if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + if (io__getline(io, &line, &line_len) < 0 || !line_len) goto error; if (function != NULL) *function = strdup(strim(line)); @@ -502,7 +468,7 @@ static int read_addr2line_record(struct a2l_subprocess *a2l, zfree(&line); line_len = 0; - if (getline(&line, &line_len, a2l->from_child) < 0 || !line_len) + if (io__getline(io, &line, &line_len) < 0 || !line_len) goto error; if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0) { @@ -546,13 +512,17 @@ static int addr2line(const char *dso_name, u64 addr, struct inline_node *node, struct symbol *sym __maybe_unused) { - struct a2l_subprocess *a2l = dso->a2l; + struct child_process *a2l = dso->a2l; char *record_function = NULL; char *record_filename = NULL; unsigned int record_line_nr = 0; int record_status = -1; int ret = 0; size_t inline_count = 0; + int len; + char buf[128]; + ssize_t written; + struct io io; if (!a2l) { if (!filename__has_section(dso_name, ".debug_line")) @@ -578,13 +548,16 @@ static int addr2line(const char *dso_name, u64 addr, * though, because it may be genuinely unknown, in which case we'll get two sets of * "??"/"??:0" lines. */ - if (fprintf(a2l->to_child, "%016"PRIx64"\n,\n", addr) < 0 || fflush(a2l->to_child) != 0) { + len = snprintf(buf, sizeof(buf), "%016"PRIx64"\n,\n", addr); + written = len > 0 ? write(a2l->in, buf, len) : -1; + if (written != len) { if (!symbol_conf.disable_add2line_warn) pr_warning("%s %s: could not send request\n", __func__, dso_name); goto out; } + io__init(&io, a2l->out, buf, sizeof(buf)); - switch (read_addr2line_record(a2l, &record_function, &record_filename, &record_line_nr)) { + switch (read_addr2line_record(&io, &record_function, &record_filename, &record_line_nr)) { case -1: if (!symbol_conf.disable_add2line_warn) pr_warning("%s %s: could not read first record\n", __func__, dso_name); @@ -594,7 +567,7 @@ static int addr2line(const char *dso_name, u64 addr, * The first record was invalid, so return failure, but first read another * record, since we asked a junk question and have to clear the answer out. */ - switch (read_addr2line_record(a2l, NULL, NULL, NULL)) { + switch (read_addr2line_record(&io, NULL, NULL, NULL)) { case -1: if (!symbol_conf.disable_add2line_warn) pr_warning("%s %s: could not read delimiter record\n", @@ -632,7 +605,7 @@ static int addr2line(const char *dso_name, u64 addr, } /* We have to read the records even if we don't care about the inline info. */ - while ((record_status = read_addr2line_record(a2l, + while ((record_status = read_addr2line_record(&io, &record_function, &record_filename, &record_line_nr)) == 1) { @@ -656,7 +629,7 @@ static int addr2line(const char *dso_name, u64 addr, void dso__free_a2l(struct dso *dso) { - struct a2l_subprocess *a2l = dso->a2l; + struct child_process *a2l = dso->a2l; if (!a2l) return; -- GitLab From 2c4b928074839425b64155cb3f6d4e0e5e67e835 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 11:40:32 -0700 Subject: [PATCH 1979/5631] perf srcline: Support for llvm-addr2line The sentinel value differs for llvm-addr2line. Configure this once and then detect when reading records. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230403184033.1836023-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 74 +++++++++++++++++++++++++++++++++++---- 1 file changed, 67 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index 5339ab4c5e12..f4fcdada821b 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -435,7 +435,50 @@ static struct child_process *addr2line_subprocess_init(const char *addr2line_pat return a2l; } +enum a2l_style { + BROKEN, + GNU_BINUTILS, + LLVM, +}; + +static enum a2l_style addr2line_configure(struct child_process *a2l) +{ + static bool cached; + static enum a2l_style style; + + if (!cached) { + char buf[128]; + struct io io; + int ch; + + if (write(a2l->in, ",\n", 2) != 2) + return BROKEN; + + io__init(&io, a2l->out, buf, sizeof(buf)); + ch = io__get_char(&io); + if (ch == ',') { + style = LLVM; + cached = true; + } else if (ch == '?') { + style = GNU_BINUTILS; + cached = true; + } else { + style = BROKEN; + } + do { + ch = io__get_char(&io); + } while (ch > 0 && ch != '\n'); + if (style == GNU_BINUTILS) { + do { + ch = io__get_char(&io); + } while (ch > 0 && ch != '\n'); + } + } + return style; +} + static int read_addr2line_record(struct io *io, + enum a2l_style style, char **function, char **filename, unsigned int *line_nr) @@ -462,6 +505,12 @@ static int read_addr2line_record(struct io *io, if (io__getline(io, &line, &line_len) < 0 || !line_len) goto error; + + if (style == LLVM && line_len == 2 && line[0] == ',') { + zfree(&line); + return 0; + } + if (function != NULL) *function = strdup(strim(line)); @@ -471,7 +520,8 @@ static int read_addr2line_record(struct io *io, if (io__getline(io, &line, &line_len) < 0 || !line_len) goto error; - if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0) { + if (filename_split(line, line_nr == NULL ? &dummy_line_nr : line_nr) == 0 && + style == GNU_BINUTILS) { ret = 0; goto error; } @@ -523,6 +573,7 @@ static int addr2line(const char *dso_name, u64 addr, char buf[128]; ssize_t written; struct io io; + enum a2l_style a2l_style; if (!a2l) { if (!filename__has_section(dso_name, ".debug_line")) @@ -538,15 +589,22 @@ static int addr2line(const char *dso_name, u64 addr, pr_warning("%s %s: addr2line_subprocess_init failed\n", __func__, dso_name); goto out; } + a2l_style = addr2line_configure(a2l); + if (a2l_style == BROKEN) { + if (!symbol_conf.disable_add2line_warn) + pr_warning("%s: addr2line configuration failed\n", __func__); + goto out; + } /* * Send our request and then *deliberately* send something that can't be interpreted as * a valid address to ask addr2line about (namely, ","). This causes addr2line to first * write out the answer to our request, in an unbounded/unknown number of records, and - * then to write out the lines "??" and "??:0", so that we can detect when it has - * finished giving us anything useful. We have to be careful about the first record, - * though, because it may be genuinely unknown, in which case we'll get two sets of - * "??"/"??:0" lines. + * then to write out the lines "??" and "??:0", for GNU binutils, or "," for + * llvm-addr2line, so that we can detect when it has finished giving us anything + * useful. With GNU binutils, we have to be careful about the first record, though, + * because it may be genuinely unknown, in which case we'll get two sets of "??"/"??:0" + * lines. */ len = snprintf(buf, sizeof(buf), "%016"PRIx64"\n,\n", addr); written = len > 0 ? write(a2l->in, buf, len) : -1; @@ -557,7 +615,8 @@ static int addr2line(const char *dso_name, u64 addr, } io__init(&io, a2l->out, buf, sizeof(buf)); - switch (read_addr2line_record(&io, &record_function, &record_filename, &record_line_nr)) { + switch (read_addr2line_record(&io, a2l_style, + &record_function, &record_filename, &record_line_nr)) { case -1: if (!symbol_conf.disable_add2line_warn) pr_warning("%s %s: could not read first record\n", __func__, dso_name); @@ -567,7 +626,7 @@ static int addr2line(const char *dso_name, u64 addr, * The first record was invalid, so return failure, but first read another * record, since we asked a junk question and have to clear the answer out. */ - switch (read_addr2line_record(&io, NULL, NULL, NULL)) { + switch (read_addr2line_record(&io, a2l_style, NULL, NULL, NULL)) { case -1: if (!symbol_conf.disable_add2line_warn) pr_warning("%s %s: could not read delimiter record\n", @@ -606,6 +665,7 @@ static int addr2line(const char *dso_name, u64 addr, /* We have to read the records even if we don't care about the inline info. */ while ((record_status = read_addr2line_record(&io, + a2l_style, &record_function, &record_filename, &record_line_nr)) == 1) { -- GitLab From 75a616c6d332342291c45b0381abe00bd597036c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 11:40:33 -0700 Subject: [PATCH 1980/5631] perf srcline: Avoid addr2line SIGPIPEs Ignore SIGPIPEs when addr2line is configured. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20230403184033.1836023-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/srcline.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index f4fcdada821b..cfca03abd6f8 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -473,6 +473,8 @@ static enum a2l_style addr2line_configure(struct child_process *a2l) ch = io__get_char(&io); } while (ch > 0 && ch != '\n'); } + /* Ignore SIGPIPE in the event addr2line exits. */ + signal(SIGPIPE, SIG_IGN); } return style; } -- GitLab From 3ad45105dc44ca8419441032760c04d81504c0e6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 14:10:20 -0700 Subject: [PATCH 1981/5631] perf build: Allow C++ demangle without libelf The cxa demangle support isn't dependent on libelf and so we no longer need to disable demangling if libelf isn't present. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230403211021.1892231-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index fd1be9596d12..16bea51f0bcd 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -412,7 +412,6 @@ endif ifdef NO_LIBELF NO_DWARF := 1 - NO_DEMANGLE := 1 NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 -- GitLab From dc67c7837a832952459c4f7829e89b9d8d15f420 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 3 Apr 2023 13:35:45 -0700 Subject: [PATCH 1982/5631] perf jit: Fix a few memory leaks As reported by leak sanitizer. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Brian Robbins Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Yuan Can Link: https://lore.kernel.org/r/20230403203545.1872196-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/genelf_debug.c | 45 +++++++++++++++++++++------------- tools/perf/util/jitdump.c | 7 +++++- 2 files changed, 34 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index dd40683bd4c0..8786c366566e 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -87,6 +87,12 @@ buffer_ext_init(struct buffer_ext *be) be->max_sz = 0; } +static void +buffer_ext_exit(struct buffer_ext *be) +{ + free(be->data); +} + static inline size_t buffer_ext_size(struct buffer_ext *be) { @@ -487,28 +493,28 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries Elf_Scn *scn; Elf_Shdr *shdr; struct buffer_ext dl, di, da; - int ret; + int ret = -1; buffer_ext_init(&dl); buffer_ext_init(&di); buffer_ext_init(&da); - ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di); - if (ret) - return -1; + if (jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di)) + goto out; + /* * setup .debug_line section */ scn = elf_newscn(e); if (!scn) { warnx("cannot create section"); - return -1; + goto out; } d = elf_newdata(scn); if (!d) { warnx("cannot get new data"); - return -1; + goto out; } d->d_align = 1; @@ -521,7 +527,7 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries shdr = elf_getshdr(scn); if (!shdr) { warnx("cannot get section header"); - return -1; + goto out; } shdr->sh_name = 52; /* .debug_line */ @@ -536,13 +542,13 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries scn = elf_newscn(e); if (!scn) { warnx("cannot create section"); - return -1; + goto out; } d = elf_newdata(scn); if (!d) { warnx("cannot get new data"); - return -1; + goto out; } d->d_align = 1; @@ -555,7 +561,7 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries shdr = elf_getshdr(scn); if (!shdr) { warnx("cannot get section header"); - return -1; + goto out; } shdr->sh_name = 64; /* .debug_info */ @@ -570,13 +576,13 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries scn = elf_newscn(e); if (!scn) { warnx("cannot create section"); - return -1; + goto out; } d = elf_newdata(scn); if (!d) { warnx("cannot get new data"); - return -1; + goto out; } d->d_align = 1; @@ -589,7 +595,7 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries shdr = elf_getshdr(scn); if (!shdr) { warnx("cannot get section header"); - return -1; + goto out; } shdr->sh_name = 76; /* .debug_info */ @@ -601,9 +607,14 @@ jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries /* * now we update the ELF image with all the sections */ - if (elf_update(e, ELF_C_WRITE) < 0) { + if (elf_update(e, ELF_C_WRITE) < 0) warnx("elf_update debug failed"); - return -1; - } - return 0; + else + ret = 0; + +out: + buffer_ext_exit(&dl); + buffer_ext_exit(&di); + buffer_ext_exit(&da); + return ret; } diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 0e033278fa12..28e49502db5e 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -235,9 +235,11 @@ jit_open(struct jit_buf_desc *jd, const char *name) */ strcpy(jd->dir, name); dirname(jd->dir); + free(buf); return 0; error: + free(buf); funlockfile(jd->in); fclose(jd->in); return retval; @@ -523,7 +525,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) ret = perf_event__process_mmap2(tool, event, &sample, jd->machine); if (ret) - return ret; + goto out; ret = jit_inject_event(jd, event); /* @@ -532,6 +534,8 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr) if (!ret) build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine); +out: + free(event); return ret; } @@ -874,6 +878,7 @@ jit_process(struct perf_session *session, } nsinfo__put(jd.nsi); + free(jd.buf); return ret; } -- GitLab From 10679e4d9848a04694eb99ec7390a6585d1b7ca9 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:18 +0100 Subject: [PATCH 1983/5631] s390/uaccess: use symbolic names for inline assembly operands Improve readability of the uaccess inline assemblies by using symbolic names for all input and output operands. Except for debug sections the output of "objdump -Dr" of the uaccess object file is identical before/after this change. Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 105 +++++++++++++++++++++------------------- 1 file changed, 54 insertions(+), 51 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index d44214072779..0ebd522ccd6f 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -44,25 +44,26 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, tmp1 = -4096UL; asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%2),0(%1),%0\n" - "6: jz 4f\n" - "1: algr %0,%3\n" - " slgr %1,%3\n" - " slgr %2,%3\n" - " j 0b\n" - "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */ - " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */ - " slgr %4,%1\n" - " clgr %0,%4\n" /* copy crosses next page boundary? */ - " jnh 5f\n" - "3: mvcos 0(%2),0(%1),%4\n" - "7: slgr %0,%4\n" - " j 5f\n" - "4: slgr %0,%0\n" + " lr 0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "6: jz 4f\n" + "1: algr %[size],%[tmp1]\n" + " slgr %[from],%[tmp1]\n" + " slgr %[to],%[tmp1]\n" + " j 0b\n" + "2: la %[tmp2],4095(%[from])\n"/* tmp2 = from + 4095 */ + " nr %[tmp2],%[tmp1]\n" /* tmp2 = (from + 4095) & -4096 */ + " slgr %[tmp2],%[from]\n" + " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + " jnh 5f\n" + "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" + "7: slgr %[size],%[tmp2]\n" + " j 5f\n" + "4: slgr %[size],%[size]\n" "5:\n" EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) - : "+a" (size), "+a" (from), "+a" (to), "+a" (tmp1), "=a" (tmp2) + : [size] "+a" (size), [from] "+a" (from), [to] "+a" (to), + [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) : [spec] "d" (spec.val) : "cc", "memory", "0"); return size; @@ -104,25 +105,26 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, tmp1 = -4096UL; asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%1),0(%2),%0\n" - "6: jz 4f\n" - "1: algr %0,%3\n" - " slgr %1,%3\n" - " slgr %2,%3\n" - " j 0b\n" - "2: la %4,4095(%1)\n"/* %4 = ptr + 4095 */ - " nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */ - " slgr %4,%1\n" - " clgr %0,%4\n" /* copy crosses next page boundary? */ - " jnh 5f\n" - "3: mvcos 0(%1),0(%2),%4\n" - "7: slgr %0,%4\n" - " j 5f\n" - "4: slgr %0,%0\n" + " lr 0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "6: jz 4f\n" + "1: algr %[size],%[tmp1]\n" + " slgr %[to],%[tmp1]\n" + " slgr %[from],%[tmp1]\n" + " j 0b\n" + "2: la %[tmp2],4095(%[to])\n" /* tmp2 = to + 4095 */ + " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ + " slgr %[tmp2],%[to]\n" + " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + " jnh 5f\n" + "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" + "7: slgr %[size],%[tmp2]\n" + " j 5f\n" + "4: slgr %[size],%[size]\n" "5:\n" EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) - : "+a" (size), "+a" (to), "+a" (from), "+a" (tmp1), "=a" (tmp2) + : [size] "+a" (size), [to] "+a" (to), [from] "+a" (from), + [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) : [spec] "d" (spec.val) : "cc", "memory", "0"); return size; @@ -155,25 +157,26 @@ unsigned long __clear_user(void __user *to, unsigned long size) tmp1 = -4096UL; asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%1),0(%4),%0\n" - "6: jz 4f\n" - "1: algr %0,%2\n" - " slgr %1,%2\n" - " j 0b\n" - "2: la %3,4095(%1)\n"/* %4 = to + 4095 */ - " nr %3,%2\n" /* %4 = (to + 4095) & -4096 */ - " slgr %3,%1\n" - " clgr %0,%3\n" /* copy crosses next page boundary? */ - " jnh 5f\n" - "3: mvcos 0(%1),0(%4),%3\n" - "7: slgr %0,%3\n" - " j 5f\n" - "4: slgr %0,%0\n" + " lr 0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[zeropg]),%[size]\n" + "6: jz 4f\n" + "1: algr %[size],%[tmp1]\n" + " slgr %[to],%[tmp1]\n" + " j 0b\n" + "2: la %[tmp2],4095(%[to])\n" /* tmp2 = to + 4095 */ + " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ + " slgr %[tmp2],%[to]\n" + " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + " jnh 5f\n" + "3: mvcos 0(%[to]),0(%[zeropg]),%[tmp2]\n" + "7: slgr %[size],%[tmp2]\n" + " j 5f\n" + "4: slgr %[size],%[size]\n" "5:\n" EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b) - : "+&a" (size), "+&a" (to), "+a" (tmp1), "=&a" (tmp2) - : "a" (empty_zero_page), [spec] "d" (spec.val) + : [size] "+&a" (size), [to] "+&a" (to), + [tmp1] "+a" (tmp1), [tmp2] "=&a" (tmp2) + : [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val) : "cc", "memory", "0"); return size; } -- GitLab From b96adf0d03e01fa10483f38e302a5f93bb733ed0 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:19 +0100 Subject: [PATCH 1984/5631] s390/uaccess: remove unused label in inline assemblies Remove an unused label in all three uaccess inline assemblies. Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 0ebd522ccd6f..d0bbdcbd7baf 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -47,7 +47,7 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" "6: jz 4f\n" - "1: algr %[size],%[tmp1]\n" + " algr %[size],%[tmp1]\n" " slgr %[from],%[tmp1]\n" " slgr %[to],%[tmp1]\n" " j 0b\n" @@ -108,7 +108,7 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" "6: jz 4f\n" - "1: algr %[size],%[tmp1]\n" + " algr %[size],%[tmp1]\n" " slgr %[to],%[tmp1]\n" " slgr %[from],%[tmp1]\n" " j 0b\n" @@ -160,7 +160,7 @@ unsigned long __clear_user(void __user *to, unsigned long size) " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[zeropg]),%[size]\n" "6: jz 4f\n" - "1: algr %[size],%[tmp1]\n" + " algr %[size],%[tmp1]\n" " slgr %[to],%[tmp1]\n" " j 0b\n" "2: la %[tmp2],4095(%[to])\n" /* tmp2 = to + 4095 */ -- GitLab From 4e0b0ad45c6616d85564cb27dbae04a962d068bd Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:20 +0100 Subject: [PATCH 1985/5631] s390/uaccess: rename/sort labels in inline assemblies Rename and sort labels in uaccess inline assemblies to increase readability. In addition have only one EX_TABLE entry per line - also to increase readability. Except for debug sections the output of "objdump -Dr" of the uaccess object file is identical before/after this change. Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 51 ++++++++++++++++++++++++----------------- 1 file changed, 30 insertions(+), 21 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index d0bbdcbd7baf..4dec9fc12f73 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -46,7 +46,7 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "6: jz 4f\n" + "1: jz 5f\n" " algr %[size],%[tmp1]\n" " slgr %[from],%[tmp1]\n" " slgr %[to],%[tmp1]\n" @@ -55,13 +55,16 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, " nr %[tmp2],%[tmp1]\n" /* tmp2 = (from + 4095) & -4096 */ " slgr %[tmp2],%[from]\n" " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ - " jnh 5f\n" + " jnh 6f\n" "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" - "7: slgr %[size],%[tmp2]\n" - " j 5f\n" - "4: slgr %[size],%[size]\n" - "5:\n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) + "4: slgr %[size],%[tmp2]\n" + " j 6f\n" + "5: slgr %[size],%[size]\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(1b, 2b) + EX_TABLE(4b, 6b) : [size] "+a" (size), [from] "+a" (from), [to] "+a" (to), [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) : [spec] "d" (spec.val) @@ -107,7 +110,7 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "6: jz 4f\n" + "1: jz 5f\n" " algr %[size],%[tmp1]\n" " slgr %[to],%[tmp1]\n" " slgr %[from],%[tmp1]\n" @@ -116,13 +119,16 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ " slgr %[tmp2],%[to]\n" " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ - " jnh 5f\n" + " jnh 6f\n" "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" - "7: slgr %[size],%[tmp2]\n" - " j 5f\n" - "4: slgr %[size],%[size]\n" - "5:\n" - EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b) + "4: slgr %[size],%[tmp2]\n" + " j 6f\n" + "5: slgr %[size],%[size]\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(1b, 2b) + EX_TABLE(4b, 6b) : [size] "+a" (size), [to] "+a" (to), [from] "+a" (from), [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) : [spec] "d" (spec.val) @@ -159,7 +165,7 @@ unsigned long __clear_user(void __user *to, unsigned long size) asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[zeropg]),%[size]\n" - "6: jz 4f\n" + "1: jz 5f\n" " algr %[size],%[tmp1]\n" " slgr %[to],%[tmp1]\n" " j 0b\n" @@ -167,13 +173,16 @@ unsigned long __clear_user(void __user *to, unsigned long size) " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ " slgr %[tmp2],%[to]\n" " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ - " jnh 5f\n" + " jnh 6f\n" "3: mvcos 0(%[to]),0(%[zeropg]),%[tmp2]\n" - "7: slgr %[size],%[tmp2]\n" - " j 5f\n" - "4: slgr %[size],%[size]\n" - "5:\n" - EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b) + "4: slgr %[size],%[tmp2]\n" + " j 6f\n" + "5: slgr %[size],%[size]\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(4b, 6b) : [size] "+&a" (size), [to] "+&a" (to), [tmp1] "+a" (tmp1), [tmp2] "=&a" (tmp2) : [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val) -- GitLab From afdcc2ce3970ccad0ec4fb2d2c614e444c59f770 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:21 +0100 Subject: [PATCH 1986/5631] s390/uaccess: sort EX_TABLE list for inline assemblies Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 4dec9fc12f73..7f33eb4dffba 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -62,8 +62,8 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, "5: slgr %[size],%[size]\n" "6:\n" EX_TABLE(0b, 2b) - EX_TABLE(3b, 6b) EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) : [size] "+a" (size), [from] "+a" (from), [to] "+a" (to), [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) @@ -126,8 +126,8 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, "5: slgr %[size],%[size]\n" "6:\n" EX_TABLE(0b, 2b) - EX_TABLE(3b, 6b) EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) : [size] "+a" (size), [to] "+a" (to), [from] "+a" (from), [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) -- GitLab From 7f65d18329a2546ce6f64ac6bf141c38b15c2ab3 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:22 +0100 Subject: [PATCH 1987/5631] s390/uaccess: rename tmp1 and tmp2 variables Rename tmp1 and tmp2 variables to more meaningful val (for value) and rem (for remainder). Except for debug sections the output of "objdump -Dr" of the uaccess object file is identical before/after this change. Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 70 ++++++++++++++++++++--------------------- 1 file changed, 35 insertions(+), 35 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 7f33eb4dffba..a89f6639818a 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -34,7 +34,7 @@ void debug_user_asce(int exit) static unsigned long raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key) { - unsigned long tmp1, tmp2; + unsigned long val, rem; union oac spec = { .oac2.key = key, .oac2.as = PSW_BITS_AS_SECONDARY, @@ -42,22 +42,22 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, .oac2.a = 1, }; - tmp1 = -4096UL; + val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" "1: jz 5f\n" - " algr %[size],%[tmp1]\n" - " slgr %[from],%[tmp1]\n" - " slgr %[to],%[tmp1]\n" + " algr %[size],%[val]\n" + " slgr %[from],%[val]\n" + " slgr %[to],%[val]\n" " j 0b\n" - "2: la %[tmp2],4095(%[from])\n"/* tmp2 = from + 4095 */ - " nr %[tmp2],%[tmp1]\n" /* tmp2 = (from + 4095) & -4096 */ - " slgr %[tmp2],%[from]\n" - " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + "2: la %[rem],4095(%[from])\n" /* rem = from + 4095 */ + " nr %[rem],%[val]\n" /* rem = (from + 4095) & -4096 */ + " slgr %[rem],%[from]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" - "4: slgr %[size],%[tmp2]\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" " j 6f\n" "5: slgr %[size],%[size]\n" "6:\n" @@ -66,7 +66,7 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) : [size] "+a" (size), [from] "+a" (from), [to] "+a" (to), - [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) + [val] "+a" (val), [rem] "=a" (rem) : [spec] "d" (spec.val) : "cc", "memory", "0"); return size; @@ -98,7 +98,7 @@ EXPORT_SYMBOL(_copy_from_user_key); static unsigned long raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key) { - unsigned long tmp1, tmp2; + unsigned long val, rem; union oac spec = { .oac1.key = key, .oac1.as = PSW_BITS_AS_SECONDARY, @@ -106,22 +106,22 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, .oac1.a = 1, }; - tmp1 = -4096UL; + val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" "1: jz 5f\n" - " algr %[size],%[tmp1]\n" - " slgr %[to],%[tmp1]\n" - " slgr %[from],%[tmp1]\n" + " algr %[size],%[val]\n" + " slgr %[to],%[val]\n" + " slgr %[from],%[val]\n" " j 0b\n" - "2: la %[tmp2],4095(%[to])\n" /* tmp2 = to + 4095 */ - " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ - " slgr %[tmp2],%[to]\n" - " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ + " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ + " slgr %[rem],%[to]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[tmp2]\n" - "4: slgr %[size],%[tmp2]\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" " j 6f\n" "5: slgr %[size],%[size]\n" "6:\n" @@ -130,7 +130,7 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) : [size] "+a" (size), [to] "+a" (to), [from] "+a" (from), - [tmp1] "+a" (tmp1), [tmp2] "=a" (tmp2) + [val] "+a" (val), [rem] "=a" (rem) : [spec] "d" (spec.val) : "cc", "memory", "0"); return size; @@ -155,27 +155,27 @@ EXPORT_SYMBOL(_copy_to_user_key); unsigned long __clear_user(void __user *to, unsigned long size) { - unsigned long tmp1, tmp2; + unsigned long val, rem; union oac spec = { .oac1.as = PSW_BITS_AS_SECONDARY, .oac1.a = 1, }; - tmp1 = -4096UL; + val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[zeropg]),%[size]\n" "1: jz 5f\n" - " algr %[size],%[tmp1]\n" - " slgr %[to],%[tmp1]\n" + " algr %[size],%[val]\n" + " slgr %[to],%[val]\n" " j 0b\n" - "2: la %[tmp2],4095(%[to])\n" /* tmp2 = to + 4095 */ - " nr %[tmp2],%[tmp1]\n" /* tmp2 = (to + 4095) & -4096 */ - " slgr %[tmp2],%[to]\n" - " clgr %[size],%[tmp2]\n" /* copy crosses next page boundary? */ + "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ + " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ + " slgr %[rem],%[to]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[zeropg]),%[tmp2]\n" - "4: slgr %[size],%[tmp2]\n" + "3: mvcos 0(%[to]),0(%[zeropg]),%[rem]\n" + "4: slgr %[size],%[rem]\n" " j 6f\n" "5: slgr %[size],%[size]\n" "6:\n" @@ -184,7 +184,7 @@ unsigned long __clear_user(void __user *to, unsigned long size) EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) : [size] "+&a" (size), [to] "+&a" (to), - [tmp1] "+a" (tmp1), [tmp2] "=&a" (tmp2) + [val] "+a" (val), [rem] "=&a" (rem) : [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val) : "cc", "memory", "0"); return size; -- GitLab From c3bd834328a6b642cfebc8a1a6cd5e5447cbbd12 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:23 +0100 Subject: [PATCH 1988/5631] s390/uaccess: get rid of not needed local variable Get rid of the not needed val local variable and pass the constant value directly as operand value. In addition this turns the val operand into an input operand, since it is not changed within the inline assemblies. This in turn requires also to add the earlyclobber contraint modifier to all output operands, since the (former) val operand is used after all output variants have been modified. The usercopy kunit tests still pass after this change. Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index a89f6639818a..1cd5a3768fcd 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -34,7 +34,7 @@ void debug_user_asce(int exit) static unsigned long raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key) { - unsigned long val, rem; + unsigned long rem; union oac spec = { .oac2.key = key, .oac2.as = PSW_BITS_AS_SECONDARY, @@ -42,7 +42,6 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, .oac2.a = 1, }; - val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" @@ -65,9 +64,8 @@ static unsigned long raw_copy_from_user_key(void *to, const void __user *from, EX_TABLE(1b, 2b) EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) - : [size] "+a" (size), [from] "+a" (from), [to] "+a" (to), - [val] "+a" (val), [rem] "=a" (rem) - : [spec] "d" (spec.val) + : [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) : "cc", "memory", "0"); return size; } @@ -98,7 +96,7 @@ EXPORT_SYMBOL(_copy_from_user_key); static unsigned long raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key) { - unsigned long val, rem; + unsigned long rem; union oac spec = { .oac1.key = key, .oac1.as = PSW_BITS_AS_SECONDARY, @@ -106,7 +104,6 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, .oac1.a = 1, }; - val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[from]),%[size]\n" @@ -129,9 +126,8 @@ static unsigned long raw_copy_to_user_key(void __user *to, const void *from, EX_TABLE(1b, 2b) EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) - : [size] "+a" (size), [to] "+a" (to), [from] "+a" (from), - [val] "+a" (val), [rem] "=a" (rem) - : [spec] "d" (spec.val) + : [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) : "cc", "memory", "0"); return size; } @@ -155,13 +151,12 @@ EXPORT_SYMBOL(_copy_to_user_key); unsigned long __clear_user(void __user *to, unsigned long size) { - unsigned long val, rem; + unsigned long rem; union oac spec = { .oac1.as = PSW_BITS_AS_SECONDARY, .oac1.a = 1, }; - val = -4096UL; asm volatile( " lr 0,%[spec]\n" "0: mvcos 0(%[to]),0(%[zeropg]),%[size]\n" @@ -183,9 +178,8 @@ unsigned long __clear_user(void __user *to, unsigned long size) EX_TABLE(1b, 2b) EX_TABLE(3b, 6b) EX_TABLE(4b, 6b) - : [size] "+&a" (size), [to] "+&a" (to), - [val] "+a" (val), [rem] "=&a" (rem) - : [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val) + : [size] "+&a" (size), [to] "+&a" (to), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [zeropg] "a" (empty_zero_page), [spec] "d" (spec.val) : "cc", "memory", "0"); return size; } -- GitLab From 49d6e68f66132ee521d587ce97645ed2d3183d90 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 24 Mar 2023 15:00:24 +0100 Subject: [PATCH 1989/5631] s390/uaccess: remove extra blank line In order to get uaccess.c (nearly) checkpatch warning free remove an extra blank line: CHECK: Blank lines aren't necessary before a close brace '}' + +} Reviewed-by: Gerald Schaefer Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/uaccess.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index 1cd5a3768fcd..e4a13d7cab6e 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -27,7 +27,6 @@ void debug_user_asce(int exit) "kernel: %016llx user: %016llx\n", exit ? "exit" : "entry", cr1, cr7, S390_lowcore.kernel_asce, S390_lowcore.user_asce); - } #endif /*CONFIG_DEBUG_ENTRY */ -- GitLab From 385bf43c48ffe44af881039779a6be09ac8a77c8 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Tue, 28 Mar 2023 11:09:09 +0200 Subject: [PATCH 1990/5631] s390/entry: rely on long-displacement facility Since commit 4efd417f298b ("s390: raise minimum supported machine generation to z10"), the long-displacement facility is assumed and required for the kernel. Clean up a couple of places in the entry code, where long-displacement could be used directly instead of using a base register. However, there are still a few other places where a base register has to be used to extend short-displacement for the second lowcore page access. Notably, boot/head.S still has to be built for z900, and in mcck_int_handler, spt and lbear, which don't have long-displacements, but need to access save areas at the second lowcore page. Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/entry.S | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 58b85aedca22..c41ec5a03d07 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -489,14 +489,13 @@ ENTRY(mcck_int_handler) la %r1,4095 # validate r1 spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer LBEAR __LC_LAST_BREAK_SAVE_AREA-4095(%r1) # validate bear - lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs + lmg %r0,%r15,__LC_GPREGS_SAVE_AREA # validate gprs lmg %r8,%r9,__LC_MCK_OLD_PSW TSTMSK __LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE jo .Lmcck_panic # yes -> rest of mcck code invalid TSTMSK __LC_MCCK_CODE,MCCK_CODE_CR_VALID jno .Lmcck_panic # control registers invalid -> panic - la %r14,4095 - lctlg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r14) # validate ctl regs + lctlg %c0,%c15,__LC_CREGS_SAVE_AREA # validate ctl regs ptlb lghi %r14,__LC_CPU_TIMER_SAVE_AREA mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) @@ -594,8 +593,7 @@ ENTRY(restart_int_handler) stg %r15,__LC_SAVE_AREA_RESTART TSTMSK __LC_RESTART_FLAGS,RESTART_FLAG_CTLREGS,4 jz 0f - la %r15,4095 - lctlg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r15) + lctlg %c0,%c15,__LC_CREGS_SAVE_AREA 0: larl %r15,.Lstosm_tmp stosm 0(%r15),0x04 # turn dat on, keep irqs off lg %r15,__LC_RESTART_STACK -- GitLab From b46650d56bd31dca8b09b5670ee9441a8f7b8869 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Tue, 28 Mar 2023 10:00:33 +0200 Subject: [PATCH 1991/5631] s390: make extables read-only Currently, exception tables are marked as ro_after_init. However, since they are sorted during compile time using scripts/sorttable, they can be moved to RO_DATA using the RO_EXCEPTION_TABLE_ALIGN macro, which is specifically designed for this purpose. Suggested-by: Heiko Carstens Reviewed-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/vmlinux.lds.S | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 8d2288a5ba25..2ae201ebf90b 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -14,6 +14,8 @@ #define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir) \ *(.bss..invalid_pg_dir) +#define RO_EXCEPTION_TABLE_ALIGN 16 + /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA @@ -66,7 +68,6 @@ SECTIONS *(.data..ro_after_init) JUMP_TABLE_DATA } :data - EXCEPTION_TABLE(16) . = ALIGN(PAGE_SIZE); __end_ro_after_init = .; -- GitLab From bd922f33d4a3255cc33eb7082c47d973ed1da75d Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 22 Mar 2023 15:15:08 +0100 Subject: [PATCH 1992/5631] s390/zcrypt: remove unused ancient padding code There was some ancient code which padded the results of a clear key ME or CRT operation with some PKCS 1.2 header. According to the comment this was only needed by crypto cards older than the CEX2. These cards are not supported any more and so this patch removes this obscure result padding code. Signed-off-by: Harald Freudenberger Reviewed-by: Juergen Christ Reviewed-by: Holger Dengler Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_msgtype6.c | 72 +++------------------------ 1 file changed, 8 insertions(+), 64 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 914151c03753..7c7ff6560858 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -566,8 +566,8 @@ struct type86x_reply { struct type86_fmt2_ext fmt2; struct CPRBX cprbx; unsigned char pad[4]; /* 4 byte function code/rules block ? */ - unsigned short length; - char text[]; + unsigned short length; /* length of data including length field size */ + char data[]; } __packed; struct type86_ep11_reply { @@ -581,45 +581,9 @@ static int convert_type86_ica(struct zcrypt_queue *zq, char __user *outputdata, unsigned int outputdatalength) { - static unsigned char static_pad[] = { - 0x00, 0x02, - 0x1B, 0x7B, 0x5D, 0xB5, 0x75, 0x01, 0x3D, 0xFD, - 0x8D, 0xD1, 0xC7, 0x03, 0x2D, 0x09, 0x23, 0x57, - 0x89, 0x49, 0xB9, 0x3F, 0xBB, 0x99, 0x41, 0x5B, - 0x75, 0x21, 0x7B, 0x9D, 0x3B, 0x6B, 0x51, 0x39, - 0xBB, 0x0D, 0x35, 0xB9, 0x89, 0x0F, 0x93, 0xA5, - 0x0B, 0x47, 0xF1, 0xD3, 0xBB, 0xCB, 0xF1, 0x9D, - 0x23, 0x73, 0x71, 0xFF, 0xF3, 0xF5, 0x45, 0xFB, - 0x61, 0x29, 0x23, 0xFD, 0xF1, 0x29, 0x3F, 0x7F, - 0x17, 0xB7, 0x1B, 0xA9, 0x19, 0xBD, 0x57, 0xA9, - 0xD7, 0x95, 0xA3, 0xCB, 0xED, 0x1D, 0xDB, 0x45, - 0x7D, 0x11, 0xD1, 0x51, 0x1B, 0xED, 0x71, 0xE9, - 0xB1, 0xD1, 0xAB, 0xAB, 0x21, 0x2B, 0x1B, 0x9F, - 0x3B, 0x9F, 0xF7, 0xF7, 0xBD, 0x63, 0xEB, 0xAD, - 0xDF, 0xB3, 0x6F, 0x5B, 0xDB, 0x8D, 0xA9, 0x5D, - 0xE3, 0x7D, 0x77, 0x49, 0x47, 0xF5, 0xA7, 0xFD, - 0xAB, 0x2F, 0x27, 0x35, 0x77, 0xD3, 0x49, 0xC9, - 0x09, 0xEB, 0xB1, 0xF9, 0xBF, 0x4B, 0xCB, 0x2B, - 0xEB, 0xEB, 0x05, 0xFF, 0x7D, 0xC7, 0x91, 0x8B, - 0x09, 0x83, 0xB9, 0xB9, 0x69, 0x33, 0x39, 0x6B, - 0x79, 0x75, 0x19, 0xBF, 0xBB, 0x07, 0x1D, 0xBD, - 0x29, 0xBF, 0x39, 0x95, 0x93, 0x1D, 0x35, 0xC7, - 0xC9, 0x4D, 0xE5, 0x97, 0x0B, 0x43, 0x9B, 0xF1, - 0x16, 0x93, 0x03, 0x1F, 0xA5, 0xFB, 0xDB, 0xF3, - 0x27, 0x4F, 0x27, 0x61, 0x05, 0x1F, 0xB9, 0x23, - 0x2F, 0xC3, 0x81, 0xA9, 0x23, 0x71, 0x55, 0x55, - 0xEB, 0xED, 0x41, 0xE5, 0xF3, 0x11, 0xF1, 0x43, - 0x69, 0x03, 0xBD, 0x0B, 0x37, 0x0F, 0x51, 0x8F, - 0x0B, 0xB5, 0x89, 0x5B, 0x67, 0xA9, 0xD9, 0x4F, - 0x01, 0xF9, 0x21, 0x77, 0x37, 0x73, 0x79, 0xC5, - 0x7F, 0x51, 0xC1, 0xCF, 0x97, 0xA1, 0x75, 0xAD, - 0x35, 0x9D, 0xD3, 0xD3, 0xA7, 0x9D, 0x5D, 0x41, - 0x6F, 0x65, 0x1B, 0xCF, 0xA9, 0x87, 0x91, 0x09 - }; struct type86x_reply *msg = reply->msg; unsigned short service_rc, service_rs; - unsigned int reply_len, pad_len; - char *data; + unsigned int data_len; service_rc = msg->cprbx.ccp_rtcode; if (unlikely(service_rc != 0)) { @@ -647,32 +611,12 @@ static int convert_type86_ica(struct zcrypt_queue *zq, ap_send_online_uevent(&zq->queue->ap_dev, zq->online); return -EAGAIN; } - data = msg->text; - reply_len = msg->length - 2; - if (reply_len > outputdatalength) - return -EINVAL; - /* - * For all encipher requests, the length of the ciphertext (reply_len) - * will always equal the modulus length. For MEX decipher requests - * the output needs to get padded. Minimum pad size is 10. - * - * Currently, the cases where padding will be added is for: - * - PCIXCC_MCL2 using a CRT form token (since PKD didn't support - * ZERO-PAD and CRT is only supported for PKD requests) - * - PCICC, always - */ - pad_len = outputdatalength - reply_len; - if (pad_len > 0) { - if (pad_len < 10) - return -EINVAL; - /* 'restore' padding left in the CEXXC card. */ - if (copy_to_user(outputdata, static_pad, pad_len - 1)) - return -EFAULT; - if (put_user(0, outputdata + pad_len - 1)) - return -EFAULT; - } + data_len = msg->length - sizeof(msg->length); + if (data_len > outputdatalength) + return -EMSGSIZE; + /* Copy the crypto response to user space. */ - if (copy_to_user(outputdata + pad_len, data, reply_len)) + if (copy_to_user(outputdata, msg->data, data_len)) return -EFAULT; return 0; } -- GitLab From 0f2d4fee91e9bdba9ee4f2cfdc9d7cddb033d4a5 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Wed, 22 Mar 2023 15:22:11 +0100 Subject: [PATCH 1993/5631] s390/zcrypt: simplify prep of CCA key token The preparation of the key data struct for a CCA RSA ME operation had some improvement to skip leading zeros in the key's exponent. However, all supported CCA cards nowadays support leading zeros in key tokens. So for simplifying the CCA key preparing code, this patch simply removes this optimization code. Signed-off-by: Harald Freudenberger Reviewed-by: Juergen Christ Reviewed-by: Holger Dengler Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_cca_key.h | 35 ++++++++++------------------ 1 file changed, 12 insertions(+), 23 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index 6229ba9c56d9..5d68b61c9fe1 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -89,10 +89,7 @@ struct cca_pvt_ext_crt_sec { #define CCA_PVT_EXT_CRT_SEC_FMT_CL 0x40 /** - * Set up private key fields of a type6 MEX message. The _pad variant - * strips leading zeroes from the b_key. - * Note that all numerics in the key token are big-endian, - * while the entries in the key block header are little-endian. + * Set up private key fields of a type6 MEX message. * * @mex: pointer to user input data * @p: pointer to memory area for the key @@ -111,10 +108,9 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) struct t6_keyblock_hdr t6_hdr; struct cca_token_hdr pubhdr; struct cca_public_sec pubsec; - char exponent[0]; + char exponent[]; } __packed *key = p; - unsigned char *temp; - int i; + unsigned char *ptr; /* * The inputdatalength was a selection criteria in the dispatching @@ -131,37 +127,29 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p) key->pubsec = static_pub_sec; /* key parameter block */ - temp = key->exponent; - if (copy_from_user(temp, mex->b_key, mex->inputdatalength)) + ptr = key->exponent; + if (copy_from_user(ptr, mex->b_key, mex->inputdatalength)) return -EFAULT; - /* Strip leading zeroes from b_key. */ - for (i = 0; i < mex->inputdatalength; i++) - if (temp[i]) - break; - if (i >= mex->inputdatalength) - return -EINVAL; - memmove(temp, temp + i, mex->inputdatalength - i); - temp += mex->inputdatalength - i; + ptr += mex->inputdatalength; /* modulus */ - if (copy_from_user(temp, mex->n_modulus, mex->inputdatalength)) + if (copy_from_user(ptr, mex->n_modulus, mex->inputdatalength)) return -EFAULT; key->pubsec.modulus_bit_len = 8 * mex->inputdatalength; key->pubsec.modulus_byte_len = mex->inputdatalength; - key->pubsec.exponent_len = mex->inputdatalength - i; + key->pubsec.exponent_len = mex->inputdatalength; key->pubsec.section_length = sizeof(key->pubsec) + - 2 * mex->inputdatalength - i; + 2 * mex->inputdatalength; key->pubhdr.token_length = key->pubsec.section_length + sizeof(key->pubhdr); key->t6_hdr.ulen = key->pubhdr.token_length + 4; key->t6_hdr.blen = key->pubhdr.token_length + 6; - return sizeof(*key) + 2 * mex->inputdatalength - i; + + return sizeof(*key) + 2 * mex->inputdatalength; } /** * Set up private key fields of a type6 CRT message. - * Note that all numerics in the key token are big-endian, - * while the entries in the key block header are little-endian. * * @mex: pointer to user input data * @p: pointer to memory area for the key @@ -242,6 +230,7 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) * used. */ memcpy((char *)(pub + 1), pk_exponent, 3); + return size; } -- GitLab From e6badee94027a4e9586e6b5d087bc96e9e4d554c Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:21 +0200 Subject: [PATCH 1994/5631] s390/dumpstack: simplify in stack logic code The pattern for all in__stack() functions is the same; especially also the size of all stacks is the same. Simplify the code by passing only the stack address to the generic in_stack() helper, which then can assume a THREAD_SIZE sized stack. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/dumpstack.c | 38 +++++++++++++----------------------- 1 file changed, 14 insertions(+), 24 deletions(-) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index f257058d0828..d2012635b093 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -41,60 +41,50 @@ const char *stack_type_name(enum stack_type type) EXPORT_SYMBOL_GPL(stack_type_name); static inline bool in_stack(unsigned long sp, struct stack_info *info, - enum stack_type type, unsigned long low, - unsigned long high) + enum stack_type type, unsigned long stack) { - if (sp < low || sp >= high) + if (sp < stack || sp >= stack + THREAD_SIZE) return false; info->type = type; - info->begin = low; - info->end = high; + info->begin = stack; + info->end = stack + THREAD_SIZE; return true; } static bool in_task_stack(unsigned long sp, struct task_struct *task, struct stack_info *info) { - unsigned long stack; + unsigned long stack = (unsigned long)task_stack_page(task); - stack = (unsigned long) task_stack_page(task); - return in_stack(sp, info, STACK_TYPE_TASK, stack, stack + THREAD_SIZE); + return in_stack(sp, info, STACK_TYPE_TASK, stack); } static bool in_irq_stack(unsigned long sp, struct stack_info *info) { - unsigned long frame_size, top; + unsigned long stack = S390_lowcore.async_stack - STACK_INIT_OFFSET; - frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); - top = S390_lowcore.async_stack + frame_size; - return in_stack(sp, info, STACK_TYPE_IRQ, top - THREAD_SIZE, top); + return in_stack(sp, info, STACK_TYPE_IRQ, stack); } static bool in_nodat_stack(unsigned long sp, struct stack_info *info) { - unsigned long frame_size, top; + unsigned long stack = S390_lowcore.nodat_stack - STACK_INIT_OFFSET; - frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); - top = S390_lowcore.nodat_stack + frame_size; - return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top); + return in_stack(sp, info, STACK_TYPE_NODAT, stack); } static bool in_mcck_stack(unsigned long sp, struct stack_info *info) { - unsigned long frame_size, top; + unsigned long stack = S390_lowcore.mcck_stack - STACK_INIT_OFFSET; - frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); - top = S390_lowcore.mcck_stack + frame_size; - return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top); + return in_stack(sp, info, STACK_TYPE_MCCK, stack); } static bool in_restart_stack(unsigned long sp, struct stack_info *info) { - unsigned long frame_size, top; + unsigned long stack = S390_lowcore.restart_stack - STACK_INIT_OFFSET; - frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); - top = S390_lowcore.restart_stack + frame_size; - return in_stack(sp, info, STACK_TYPE_RESTART, top - THREAD_SIZE, top); + return in_stack(sp, info, STACK_TYPE_RESTART, stack); } int get_stack_info(unsigned long sp, struct task_struct *task, -- GitLab From c2c3258fb55a0f51ea4a3c2cd4c29b23a64b151e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:22 +0200 Subject: [PATCH 1995/5631] s390/stack: use STACK_INIT_OFFSET where possible Make STACK_INIT_OFFSET also available for assembler code, and use it everywhere instead of open-coding it at several places. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/thread_info.h | 8 +++++--- arch/s390/kernel/entry.S | 12 ++++-------- arch/s390/kernel/head64.S | 2 +- arch/s390/kernel/setup.c | 3 +-- arch/s390/kernel/smp.c | 5 ++--- 5 files changed, 13 insertions(+), 17 deletions(-) diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index f19e6f5ec367..c7c97921ed8d 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -9,6 +9,9 @@ #define _ASM_THREAD_INFO_H #include +#ifndef ASM_OFFSETS_C +#include +#endif /* * General size of kernel stacks @@ -21,13 +24,12 @@ #define BOOT_STACK_SIZE (PAGE_SIZE << 2) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) +#define STACK_INIT_OFFSET (THREAD_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE) + #ifndef __ASSEMBLY__ #include #include -#define STACK_INIT_OFFSET \ - (THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs)) - /* * low level task data that entry.S needs immediate access to * - this struct should fit entirely inside of one cache line diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index c41ec5a03d07..fc3d1df09736 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -29,10 +29,6 @@ #include #include -STACK_SHIFT = PAGE_SHIFT + THREAD_SIZE_ORDER -STACK_SIZE = 1 << STACK_SHIFT -STACK_INIT = STACK_SIZE - STACK_FRAME_OVERHEAD - __PT_SIZE - _LPP_OFFSET = __LC_LPP .macro STBEAR address @@ -53,7 +49,7 @@ _LPP_OFFSET = __LC_LPP .macro CHECK_STACK savearea #ifdef CONFIG_CHECK_STACK - tml %r15,STACK_SIZE - CONFIG_STACK_GUARD + tml %r15,THREAD_SIZE - CONFIG_STACK_GUARD lghi %r14,\savearea jz stack_overflow #endif @@ -62,8 +58,8 @@ _LPP_OFFSET = __LC_LPP .macro CHECK_VMAP_STACK savearea,oklabel #ifdef CONFIG_VMAP_STACK lgr %r14,%r15 - nill %r14,0x10000 - STACK_SIZE - oill %r14,STACK_INIT + nill %r14,0x10000 - THREAD_SIZE + oill %r14,STACK_INIT_OFFSET clg %r14,__LC_KERNEL_STACK je \oklabel clg %r14,__LC_ASYNC_STACK @@ -179,7 +175,7 @@ ENTRY(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread - llill %r5,STACK_INIT + llill %r5,STACK_INIT_OFFSET stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev lg %r15,0(%r4,%r3) # start of kernel stack of next agr %r15,%r5 # end of kernel stack of next diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index f68be3951103..82399b4b5f8a 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -24,7 +24,7 @@ ENTRY(startup_continue) # larl %r14,init_task stg %r14,__LC_CURRENT - larl %r15,init_thread_union+THREAD_SIZE-STACK_FRAME_OVERHEAD-__PT_SIZE + larl %r15,init_thread_union+STACK_INIT_OFFSET brasl %r14,sclp_early_adjust_va # allow sclp_early_printk brasl %r14,startup_init # s390 specific early init brasl %r14,start_kernel # common init code diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d25425b8d0c0..061cc771d764 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -436,8 +436,7 @@ static void __init setup_lowcore(void) lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = clock_comparator_max; - lc->nodat_stack = ((unsigned long) &init_thread_union) - + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); + lc->nodat_stack = ((unsigned long)&init_thread_union) + STACK_INIT_OFFSET; lc->current_task = (unsigned long)&init_task; lc->lpp = LPP_MAGIC; lc->machine_flags = S390_lowcore.machine_flags; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 0126c5f6b904..680b4fbdabb1 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -280,9 +280,8 @@ static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) cpu = pcpu - pcpu_devices; lc = lowcore_ptr[cpu]; - lc->kernel_stack = (unsigned long) task_stack_page(tsk) - + THREAD_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); - lc->current_task = (unsigned long) tsk; + lc->kernel_stack = (unsigned long)task_stack_page(tsk) + STACK_INIT_OFFSET; + lc->current_task = (unsigned long)tsk; lc->lpp = LPP_MAGIC; lc->current_pid = tsk->pid; lc->user_timer = tsk->thread.user_timer; -- GitLab From cfea9bc78bc3f99abcef3efbe7631d3ed3b70406 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:23 +0200 Subject: [PATCH 1996/5631] s390/stack: set lowcore kernel stack pointer early Make sure the lowcore kernel stack pointer reflects the kernel stack of the current task as early as possible, instead of having a NULL pointer there. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/head64.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 82399b4b5f8a..f67982f562db 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -25,6 +25,7 @@ ENTRY(startup_continue) larl %r14,init_task stg %r14,__LC_CURRENT larl %r15,init_thread_union+STACK_INIT_OFFSET + stg %r15,__LC_KERNEL_STACK brasl %r14,sclp_early_adjust_va # allow sclp_early_printk brasl %r14,startup_init # s390 specific early init brasl %r14,start_kernel # common init code -- GitLab From 944c78376a39b86a57c0b36c73d1316bd97846bc Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:24 +0200 Subject: [PATCH 1997/5631] s390: use init_thread_union aka initial stack for the first process s390 is the only architecture which switches from the initial stack to a later on allocated different stack for the first process. This is (at least) problematic for the stackleak feature, which instruments functions to save the current stackpointer within the task structure of the running process. The stackleak code compares stack pointers of the current process - and doesn't expect that the kernel stack of a task can change. Even though the stackleak feature itself will not cause any harm, the assumption about kernel stacks being consistent is there, and only s390 doesn't follow that. Therefore switch back to use init_thread_union, just like all other architectures. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 48 +++++++++++++++------------------------- arch/s390/kernel/smp.c | 2 +- 2 files changed, 19 insertions(+), 31 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 061cc771d764..76cfc7c23e70 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -380,6 +380,12 @@ void stack_free(unsigned long stack) #endif } +void __init arch_call_rest_init(void) +{ + smp_reinit_ipl_cpu(); + rest_init(); +} + int __init arch_early_irq_init(void) { unsigned long stack; @@ -391,28 +397,21 @@ int __init arch_early_irq_init(void) return 0; } -void __init arch_call_rest_init(void) +static unsigned long __init stack_alloc_early(void) { unsigned long stack; - smp_reinit_ipl_cpu(); - stack = stack_alloc(); - if (!stack) - panic("Couldn't allocate kernel stack"); - current->stack = (void *) stack; -#ifdef CONFIG_VMAP_STACK - current->stack_vm_area = (void *) stack; -#endif - set_task_stack_end_magic(current); - stack += STACK_INIT_OFFSET; - S390_lowcore.kernel_stack = stack; - call_on_stack_noreturn(rest_init, stack); + stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE); + if (!stack) { + panic("%s: Failed to allocate %lu bytes align=0x%lx\n", + __func__, THREAD_SIZE, THREAD_SIZE); + } + return stack; } static void __init setup_lowcore(void) { struct lowcore *lc, *abs_lc; - unsigned long mcck_stack; /* * Setup lowcore for boot cpu @@ -436,7 +435,6 @@ static void __init setup_lowcore(void) lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; lc->io_new_psw.addr = (unsigned long) io_int_handler; lc->clock_comparator = clock_comparator_max; - lc->nodat_stack = ((unsigned long)&init_thread_union) + STACK_INIT_OFFSET; lc->current_task = (unsigned long)&init_task; lc->lpp = LPP_MAGIC; lc->machine_flags = S390_lowcore.machine_flags; @@ -449,17 +447,14 @@ static void __init setup_lowcore(void) lc->steal_timer = S390_lowcore.steal_timer; lc->last_update_timer = S390_lowcore.last_update_timer; lc->last_update_clock = S390_lowcore.last_update_clock; - /* * Allocate the global restart stack which is the same for - * all CPUs in cast *one* of them does a PSW restart. + * all CPUs in case *one* of them does a PSW restart. */ - restart_stack = memblock_alloc(THREAD_SIZE, THREAD_SIZE); - if (!restart_stack) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, THREAD_SIZE, THREAD_SIZE); - restart_stack += STACK_INIT_OFFSET; - + restart_stack = (void *)(stack_alloc_early() + STACK_INIT_OFFSET); + lc->mcck_stack = stack_alloc_early() + STACK_INIT_OFFSET; + lc->nodat_stack = stack_alloc_early() + STACK_INIT_OFFSET; + lc->kernel_stack = S390_lowcore.kernel_stack; /* * Set up PSW restart to call ipl.c:do_restart(). Copy the relevant * restart data to the absolute zero lowcore. This is necessary if @@ -470,13 +465,6 @@ static void __init setup_lowcore(void) lc->restart_data = 0; lc->restart_source = -1U; __ctl_store(lc->cregs_save_area, 0, 15); - - mcck_stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE); - if (!mcck_stack) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, THREAD_SIZE, THREAD_SIZE); - lc->mcck_stack = mcck_stack + STACK_INIT_OFFSET; - lc->spinlock_lockval = arch_spin_lockval(0); lc->spinlock_index = 0; arch_spin_lock_setup(0); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 680b4fbdabb1..cc98ac26e77c 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1295,7 +1295,7 @@ int __init smp_reinit_ipl_cpu(void) free_pages(lc_ipl->async_stack - STACK_INIT_OFFSET, THREAD_SIZE_ORDER); memblock_free_late(__pa(lc_ipl->mcck_stack - STACK_INIT_OFFSET), THREAD_SIZE); + memblock_free_late(__pa(lc_ipl->nodat_stack - STACK_INIT_OFFSET), THREAD_SIZE); memblock_free_late(__pa(lc_ipl), sizeof(*lc_ipl)); - return 0; } -- GitLab From 23be82f0deb8ce02fbb94d9baac7c2434d5e217e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:25 +0200 Subject: [PATCH 1998/5631] s390/stacktrace: remove call_on_stack_noreturn() There is no user left of call_on_stack_noreturn() - remove it. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/stacktrace.h | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 1802be5abb5d..25e833cd883c 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -189,17 +189,4 @@ static __always_inline unsigned long get_stack_pointer(struct task_struct *task, (rettype)r2; \ }) -#define call_on_stack_noreturn(fn, stack) \ -({ \ - void (*__fn)(void) = fn; \ - \ - asm volatile( \ - " la 15,0(%[_stack])\n" \ - " xc %[_bc](8,15),%[_bc](15)\n" \ - " brasl 14,%[_fn]\n" \ - ::[_bc] "i" (offsetof(struct stack_frame, back_chain)), \ - [_stack] "a" (stack), [_fn] "X" (__fn)); \ - BUG(); \ -}) - #endif /* _ASM_S390_STACKTRACE_H */ -- GitLab From 60afa6d1662c08dd266463231acc129488fffe6e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:26 +0200 Subject: [PATCH 1999/5631] s390: remove arch_early_irq_init() Allocate early async stack like other early stacks and get rid of arch_early_irq_init(). This way the async stack is allocated earlier, and handled like all other stacks. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/setup.c | 12 +----------- arch/s390/kernel/smp.c | 2 +- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 76cfc7c23e70..f2d0d52b3070 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -386,17 +386,6 @@ void __init arch_call_rest_init(void) rest_init(); } -int __init arch_early_irq_init(void) -{ - unsigned long stack; - - stack = __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER); - if (!stack) - panic("Couldn't allocate async stack"); - S390_lowcore.async_stack = stack + STACK_INIT_OFFSET; - return 0; -} - static unsigned long __init stack_alloc_early(void) { unsigned long stack; @@ -453,6 +442,7 @@ static void __init setup_lowcore(void) */ restart_stack = (void *)(stack_alloc_early() + STACK_INIT_OFFSET); lc->mcck_stack = stack_alloc_early() + STACK_INIT_OFFSET; + lc->async_stack = stack_alloc_early() + STACK_INIT_OFFSET; lc->nodat_stack = stack_alloc_early() + STACK_INIT_OFFSET; lc->kernel_stack = S390_lowcore.kernel_stack; /* diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index cc98ac26e77c..27c710178033 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1293,8 +1293,8 @@ int __init smp_reinit_ipl_cpu(void) local_mcck_enable(); local_irq_restore(flags); - free_pages(lc_ipl->async_stack - STACK_INIT_OFFSET, THREAD_SIZE_ORDER); memblock_free_late(__pa(lc_ipl->mcck_stack - STACK_INIT_OFFSET), THREAD_SIZE); + memblock_free_late(__pa(lc_ipl->async_stack - STACK_INIT_OFFSET), THREAD_SIZE); memblock_free_late(__pa(lc_ipl->nodat_stack - STACK_INIT_OFFSET), THREAD_SIZE); memblock_free_late(__pa(lc_ipl), sizeof(*lc_ipl)); return 0; -- GitLab From 22ca1e7738025ae38d07c05bae2af934b1b2c11f Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:27 +0200 Subject: [PATCH 2000/5631] s390: move on_thread_stack() to processor.h As preparation for the stackleak feature move on_thread_stack() to processor.h like x86. Also make it __always_inline, and slightly optimize it by reading current task's kernel stack pointer from lowcore. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/entry-common.h | 5 ----- arch/s390/include/asm/processor.h | 7 +++++++ 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index 000de2b1e67a..fdd319a622b0 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -60,9 +60,4 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare -static inline bool on_thread_stack(void) -{ - return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); -} - #endif diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 80ac0c1034dc..efffc28cbad8 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -226,6 +226,13 @@ static __always_inline unsigned long __current_stack_pointer(void) return sp; } +static __always_inline bool on_thread_stack(void) +{ + unsigned long ksp = S390_lowcore.kernel_stack; + + return !((ksp ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); +} + static __always_inline unsigned short stap(void) { unsigned short cpu_address; -- GitLab From b94c0ebb1ec752016a3e41bfb66bb51ea905e533 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Mar 2023 11:37:28 +0200 Subject: [PATCH 2001/5631] s390: enable HAVE_ARCH_STACKLEAK Add support for the stackleak feature. Whenever the kernel returns to user space the kernel stack is filled with a poison value. Enabling this feature is quite expensive: e.g. after instrumenting the getpid() system call function to have a 4kb stack the result is an increased runtime of the system call by a factor of 3. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/kernel/entry.S | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index d610f911677e..d4db47b0610c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -155,6 +155,7 @@ config S390 select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY + select HAVE_ARCH_STACKLEAK select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_VMAP_STACK diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index fc3d1df09736..d5f8cd4319a4 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -150,6 +150,12 @@ _LPP_OFFSET = __LC_LPP .endm #endif + .macro STACKLEAK_ERASE +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + brasl %r14,stackleak_erase_on_task_stack +#endif + .endm + GEN_BR_THUNK %r14 .section .kprobes.text, "ax" @@ -300,6 +306,7 @@ ENTRY(system_call) MBEAR %r2 lgr %r3,%r14 brasl %r14,__do_syscall + STACKLEAK_ERASE lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) BPON @@ -315,6 +322,7 @@ ENDPROC(system_call) ENTRY(ret_from_fork) lgr %r3,%r11 brasl %r14,__ret_from_fork + STACKLEAK_ERASE lctlg %c1,%c1,__LC_USER_ASCE mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) BPON @@ -375,6 +383,7 @@ ENTRY(pgm_check_handler) brasl %r14,__do_pgm_check tmhh %r8,0x0001 # returning to user space? jno .Lpgm_exit_kernel + STACKLEAK_ERASE lctlg %c1,%c1,__LC_USER_ASCE BPON stpt __LC_EXIT_TIMER @@ -440,6 +449,7 @@ ENTRY(\name) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tmhh %r8,0x0001 # returning to user ? jno 2f + STACKLEAK_ERASE lctlg %c1,%c1,__LC_USER_ASCE BPON stpt __LC_EXIT_TIMER -- GitLab From 83720209961f5cfed17214bc78978a02e3414a41 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 20 Mar 2023 14:22:32 -0700 Subject: [PATCH 2002/5631] perf map: Move map list node into symbol Using a perf map as a list node is only done in symbol. Move the list_node struct into symbol as a single pointer to the map. This makes reference count behavior more obvious and easy to check. Committer notes: Some changes to reduce the number of lines touched by keeping, for instance, the 'new_map' variable and setting it to new_node->map, so that we keep more of the project history in place and keep as much as possible the value of the 'git blame' tool. Also use map__zput() when putting a struct members, so that when we free the container struct we can get use-after-free errors as NULL pointer derefs sometimes. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.h | 5 +-- tools/perf/util/symbol.c | 73 +++++++++++++++++++++++++++++----------- 2 files changed, 54 insertions(+), 24 deletions(-) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 3dcfe06db6b3..2879cae05ee0 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -16,10 +16,7 @@ struct maps; struct machine; struct map { - union { - struct rb_node rb_node; - struct list_head node; - }; + struct rb_node rb_node; u64 start; u64 end; bool erange_warned:1; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a458aa8b87bb..8719074b7f21 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -48,6 +48,11 @@ static bool symbol__is_idle(const char *name); int vmlinux_path__nr_entries; char **vmlinux_path; +struct map_list_node { + struct list_head node; + struct map *map; +}; + struct symbol_conf symbol_conf = { .nanosecs = false, .use_modules = true, @@ -85,6 +90,11 @@ static enum dso_binary_type binary_type_symtab[] = { #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab) +static struct map_list_node *map_list_node__new(void) +{ + return malloc(sizeof(struct map_list_node)); +} + static bool symbol_type__filter(char symbol_type) { symbol_type = toupper(symbol_type); @@ -1219,16 +1229,21 @@ struct kcore_mapfn_data { static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) { struct kcore_mapfn_data *md = data; - struct map *map; + struct map_list_node *list_node = map_list_node__new(); - map = map__new2(start, md->dso); - if (map == NULL) + if (!list_node) return -ENOMEM; - map->end = map->start + len; - map->pgoff = pgoff; + list_node->map = map__new2(start, md->dso); + if (!list_node->map) { + free(list_node); + return -ENOMEM; + } - list_add(&map->node, &md->maps); + list_node->map->end = list_node->map->start + len; + list_node->map->pgoff = pgoff; + + list_add(&list_node->node, &md->maps); return 0; } @@ -1264,12 +1279,18 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) * |new.............| -> |new..| |new..| * |old....| -> |old....| */ - struct map *m = map__clone(new_map); + struct map_list_node *m = map_list_node__new(); if (!m) return -ENOMEM; - m->end = old_map->start; + m->map = map__clone(new_map); + if (!m->map) { + free(m); + return -ENOMEM; + } + + m->map->end = old_map->start; list_add_tail(&m->node, &merged); new_map->pgoff += old_map->end - new_map->start; new_map->start = old_map->end; @@ -1299,10 +1320,13 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) } while (!list_empty(&merged)) { - old_map = list_entry(merged.next, struct map, node); - list_del_init(&old_map->node); - maps__insert(kmaps, old_map); - map__put(old_map); + struct map_list_node *old_node; + + old_node = list_entry(merged.next, struct map_list_node, node); + list_del_init(&old_node->node); + maps__insert(kmaps, old_node->map); + map__put(old_node->map); + free(old_node); } if (new_map) { @@ -1317,7 +1341,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, { struct maps *kmaps = map__kmaps(map); struct kcore_mapfn_data md; - struct map *old_map, *new_map, *replacement_map = NULL, *next; + struct map *old_map, *replacement_map = NULL, *next; struct machine *machine; bool is_64_bit; int err, fd; @@ -1378,8 +1402,10 @@ static int dso__load_kcore(struct dso *dso, struct map *map, /* Find the kernel map using the '_stext' symbol */ if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) { u64 replacement_size = 0; + struct map_list_node *new_node; - list_for_each_entry(new_map, &md.maps, node) { + list_for_each_entry(new_node, &md.maps, node) { + struct map *new_map = new_node->map; u64 new_size = new_map->end - new_map->start; if (!(stext >= new_map->start && stext < new_map->end)) @@ -1399,12 +1425,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } if (!replacement_map) - replacement_map = list_entry(md.maps.next, struct map, node); + replacement_map = list_entry(md.maps.next, struct map_list_node, node)->map; /* Add new maps */ while (!list_empty(&md.maps)) { - new_map = list_entry(md.maps.next, struct map, node); - list_del_init(&new_map->node); + struct map_list_node *new_node = list_entry(md.maps.next, struct map_list_node, node); + struct map *new_map = new_node->map; + + list_del_init(&new_node->node); + if (new_map == replacement_map) { map->start = new_map->start; map->end = new_map->end; @@ -1426,6 +1455,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, if (maps__merge_in(kmaps, new_map)) goto out_err; } + free(new_node); } if (machine__is(machine, "x86_64")) { @@ -1462,9 +1492,12 @@ static int dso__load_kcore(struct dso *dso, struct map *map, out_err: while (!list_empty(&md.maps)) { - map = list_entry(md.maps.next, struct map, node); - list_del_init(&map->node); - map__put(map); + struct map_list_node *list_node; + + list_node = list_entry(md.maps.next, struct map_list_node, node); + list_del_init(&list_node->node); + map__zput(list_node->map); + free(list_node); } close(fd); return -EINVAL; -- GitLab From ff583dc43dc8b62c9ec639604adae641ba38a91d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 20 Mar 2023 14:22:33 -0700 Subject: [PATCH 2003/5631] perf maps: Remove rb_node from struct map struct map is reference counted, having it also be a node in an red-black tree complicates the reference counting. Switch to having a map_rb_node which is a red-block tree node but points at the reference counted struct map. This reference is responsible for a single reference count. Committer notes: Fixed up tools/perf/util/unwind-libunwind-local.c to use map_rb_node as well. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/event.c | 13 +- tools/perf/builtin-report.c | 6 +- tools/perf/tests/maps.c | 8 +- tools/perf/tests/vmlinux-kallsyms.c | 17 ++- tools/perf/util/bpf_lock_contention.c | 2 +- tools/perf/util/machine.c | 68 ++++++--- tools/perf/util/map.c | 16 -- tools/perf/util/map.h | 1 - tools/perf/util/maps.c | 180 +++++++++++++++-------- tools/perf/util/maps.h | 17 ++- tools/perf/util/probe-event.c | 18 ++- tools/perf/util/symbol-elf.c | 9 +- tools/perf/util/symbol.c | 77 ++++++---- tools/perf/util/synthetic-events.c | 26 ++-- tools/perf/util/thread.c | 10 +- tools/perf/util/unwind-libunwind-local.c | 6 +- tools/perf/util/vdso.c | 7 +- 17 files changed, 295 insertions(+), 186 deletions(-) diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index e4288d09f3a0..17bf60babfbd 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -19,7 +19,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, struct machine *machine) { int rc = 0; - struct map *pos; + struct map_rb_node *pos; struct maps *kmaps = machine__kernel_maps(machine); union perf_event *event = zalloc(sizeof(event->mmap) + machine->id_hdr_size); @@ -33,11 +33,12 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, maps__for_each_entry(kmaps, pos) { struct kmap *kmap; size_t size; + struct map *map = pos->map; - if (!__map__is_extra_kernel_map(pos)) + if (!__map__is_extra_kernel_map(map)) continue; - kmap = map__kmap(pos); + kmap = map__kmap(map); size = sizeof(event->mmap) - sizeof(event->mmap.filename) + PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) + @@ -58,9 +59,9 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, event->mmap.header.size = size; - event->mmap.start = pos->start; - event->mmap.len = pos->end - pos->start; - event->mmap.pgoff = pos->pgoff; + event->mmap.start = map->start; + event->mmap.len = map->end - map->start; + event->mmap.pgoff = map->pgoff; event->mmap.pid = machine->pid; strlcpy(event->mmap.filename, kmap->name, PATH_MAX); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 4011abc03d0d..c7e3863e8f44 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -844,9 +844,11 @@ static struct task *tasks_list(struct task *task, struct machine *machine) static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) { size_t printed = 0; - struct map *map; + struct map_rb_node *rb_node; + + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; - maps__for_each_entry(maps, map) { printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", indent, "", map->start, map->end, map->prot & PROT_READ ? 'r' : '-', diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index a69988a89d26..8246d37e4b7a 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -15,10 +15,12 @@ struct map_def { static int check_maps(struct map_def *merged, unsigned int size, struct maps *maps) { - struct map *map; + struct map_rb_node *rb_node; unsigned int i = 0; - maps__for_each_entry(maps, map) { + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; + if (i > 0) TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size)); @@ -74,7 +76,7 @@ static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest map->start = bpf_progs[i].start; map->end = bpf_progs[i].end; - maps__insert(maps, map); + TEST_ASSERT_VAL("failed to insert map", maps__insert(maps, map) == 0); map__put(map); } diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 8ab035b55875..c8abb3ca8347 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -118,7 +118,8 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused int err = TEST_FAIL; struct rb_node *nd; struct symbol *sym; - struct map *kallsyms_map, *vmlinux_map, *map; + struct map *kallsyms_map, *vmlinux_map; + struct map_rb_node *rb_node; struct machine kallsyms, vmlinux; struct maps *maps; u64 mem_start, mem_end; @@ -290,15 +291,15 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused header_printed = false; - maps__for_each_entry(maps, map) { - struct map * + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; /* * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while * the kernel will have the path for the vmlinux file being used, * so use the short name, less descriptive but the same ("[kernel]" in * both cases. */ - pair = maps__find_by_name(kallsyms.kmaps, (map->dso->kernel ? + struct map *pair = maps__find_by_name(kallsyms.kmaps, (map->dso->kernel ? map->dso->short_name : map->dso->name)); if (pair) { @@ -314,8 +315,8 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused header_printed = false; - maps__for_each_entry(maps, map) { - struct map *pair; + maps__for_each_entry(maps, rb_node) { + struct map *pair, *map = rb_node->map; mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start); mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end); @@ -344,7 +345,9 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused maps = machine__kernel_maps(&kallsyms); - maps__for_each_entry(maps, map) { + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; + if (!map->priv) { if (!header_printed) { pr_info("WARN: Maps only in kallsyms:\n"); diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index b3e8aa9cd011..8a5d0eb44189 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -284,7 +284,7 @@ int lock_contention_read(struct lock_contention *con) } /* make sure it loads the kernel map */ - map__load(maps__first(machine->kmaps)); + map__load(maps__first(machine->kmaps)->map); prev_key = NULL; while (!bpf_map_get_next_key(fd, prev_key, &key)) { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 3182815c73c6..2058623726d2 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -883,6 +883,7 @@ static int machine__process_ksymbol_register(struct machine *machine, if (!map) { struct dso *dso = dso__new(event->ksymbol.name); + int err; if (dso) { dso->kernel = DSO_SPACE__KERNEL; @@ -902,8 +903,11 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map->start + event->ksymbol.len; - maps__insert(machine__kernel_maps(machine), map); + err = maps__insert(machine__kernel_maps(machine), map); map__put(map); + if (err) + return err; + dso__set_loaded(dso); if (is_bpf_image(event->ksymbol.name)) { @@ -1003,6 +1007,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start struct map *map = NULL; struct kmod_path m; struct dso *dso; + int err; if (kmod_path__parse_name(&m, filename)) return NULL; @@ -1015,10 +1020,14 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start if (map == NULL) goto out; - maps__insert(machine__kernel_maps(machine), map); + err = maps__insert(machine__kernel_maps(machine), map); /* Put the map here because maps__insert already got it */ map__put(map); + + /* If maps__insert failed, return NULL. */ + if (err) + map = NULL; out: /* put the dso here, corresponding to machine__findnew_module_dso */ dso__put(dso); @@ -1185,10 +1194,11 @@ int machine__create_extra_kernel_map(struct machine *machine, { struct kmap *kmap; struct map *map; + int err; map = map__new2(xm->start, kernel); if (!map) - return -1; + return -ENOMEM; map->end = xm->end; map->pgoff = xm->pgoff; @@ -1197,14 +1207,16 @@ int machine__create_extra_kernel_map(struct machine *machine, strlcpy(kmap->name, xm->name, KMAP_NAME_LEN); - maps__insert(machine__kernel_maps(machine), map); + err = maps__insert(machine__kernel_maps(machine), map); - pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", - kmap->name, map->start, map->end); + if (!err) { + pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", + kmap->name, map->start, map->end); + } map__put(map); - return 0; + return err; } static u64 find_entry_trampoline(struct dso *dso) @@ -1245,16 +1257,16 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, struct maps *kmaps = machine__kernel_maps(machine); int nr_cpus_avail, cpu; bool found = false; - struct map *map; + struct map_rb_node *rb_node; u64 pgoff; /* * In the vmlinux case, pgoff is a virtual address which must now be * mapped to a vmlinux offset. */ - maps__for_each_entry(kmaps, map) { + maps__for_each_entry(kmaps, rb_node) { + struct map *dest_map, *map = rb_node->map; struct kmap *kmap = __map__kmap(map); - struct map *dest_map; if (!kmap || !is_entry_trampoline(kmap->name)) continue; @@ -1309,11 +1321,10 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) machine->vmlinux_map = map__new2(0, kernel); if (machine->vmlinux_map == NULL) - return -1; + return -ENOMEM; machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; - maps__insert(machine__kernel_maps(machine), machine->vmlinux_map); - return 0; + return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map); } void machine__destroy_kernel_maps(struct machine *machine) @@ -1635,25 +1646,26 @@ static void machine__set_kernel_mmap(struct machine *machine, machine->vmlinux_map->end = ~0ULL; } -static void machine__update_kernel_mmap(struct machine *machine, +static int machine__update_kernel_mmap(struct machine *machine, u64 start, u64 end) { struct map *map = machine__kernel_map(machine); + int err; map__get(map); maps__remove(machine__kernel_maps(machine), map); machine__set_kernel_mmap(machine, start, end); - maps__insert(machine__kernel_maps(machine), map); + err = maps__insert(machine__kernel_maps(machine), map); map__put(map); + return err; } int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; - struct map *map; u64 start = 0, end = ~0ULL; int ret; @@ -1685,7 +1697,9 @@ int machine__create_kernel_maps(struct machine *machine) * we have a real start address now, so re-order the kmaps * assume it's the last in the kmaps */ - machine__update_kernel_mmap(machine, start, end); + ret = machine__update_kernel_mmap(machine, start, end); + if (ret < 0) + goto out_put; } if (machine__create_extra_kernel_maps(machine, kernel)) @@ -1693,9 +1707,12 @@ int machine__create_kernel_maps(struct machine *machine) if (end == ~0ULL) { /* update end address of the kernel map using adjacent module address */ - map = map__next(machine__kernel_map(machine)); - if (map) - machine__set_kernel_mmap(machine, start, map->start); + struct map_rb_node *rb_node = maps__find_node(machine__kernel_maps(machine), + machine__kernel_map(machine)); + struct map_rb_node *next = map_rb_node__next(rb_node); + + if (next) + machine__set_kernel_mmap(machine, start, next->map->start); } out_put: @@ -1828,7 +1845,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (strstr(kernel->long_name, "vmlinux")) dso__set_short_name(kernel, "[kernel.vmlinux]", false); - machine__update_kernel_mmap(machine, xm->start, xm->end); + if (machine__update_kernel_mmap(machine, xm->start, xm->end) < 0) { + dso__put(kernel); + goto out_problem; + } if (build_id__is_defined(bid)) dso__set_build_id(kernel, bid); @@ -3330,11 +3350,11 @@ int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv) { struct maps *maps = machine__kernel_maps(machine); - struct map *map; + struct map_rb_node *pos; int err = 0; - for (map = maps__first(maps); map != NULL; map = map__next(map)) { - err = fn(map, priv); + maps__for_each_entry(maps, pos) { + err = fn(pos->map, priv); if (err != 0) { break; } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index f3a3d9b3a40d..7620cfa114d4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -111,7 +111,6 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map->dso = dso__get(dso); map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; - RB_CLEAR_NODE(&map->rb_node); map->erange_warned = false; refcount_set(&map->refcnt, 1); } @@ -397,7 +396,6 @@ struct map *map__clone(struct map *from) map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); - RB_CLEAR_NODE(&map->rb_node); dso__get(map->dso); } @@ -537,20 +535,6 @@ bool map__contains_symbol(const struct map *map, const struct symbol *sym) return ip >= map->start && ip < map->end; } -static struct map *__map__next(struct map *map) -{ - struct rb_node *next = rb_next(&map->rb_node); - - if (next) - return rb_entry(next, struct map, rb_node); - return NULL; -} - -struct map *map__next(struct map *map) -{ - return map ? __map__next(map) : NULL; -} - struct kmap *__map__kmap(struct map *map) { if (!map->dso || !map->dso->kernel) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 2879cae05ee0..d1a6f85fd31d 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -16,7 +16,6 @@ struct maps; struct machine; struct map { - struct rb_node rb_node; u64 start; u64 end; bool erange_warned:1; diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 37bd5b40000d..83ec126bcbe5 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -10,8 +10,6 @@ #include "ui/ui.h" #include "unwind.h" -static void __maps__insert(struct maps *maps, struct map *map); - static void maps__init(struct maps *maps, struct machine *machine) { maps->entries = RB_ROOT; @@ -32,10 +30,44 @@ static void __maps__free_maps_by_name(struct maps *maps) maps->nr_maps_allocated = 0; } -void maps__insert(struct maps *maps, struct map *map) +static int __maps__insert(struct maps *maps, struct map *map) { + struct rb_node **p = &maps->entries.rb_node; + struct rb_node *parent = NULL; + const u64 ip = map->start; + struct map_rb_node *m, *new_rb_node; + + new_rb_node = malloc(sizeof(*new_rb_node)); + if (!new_rb_node) + return -ENOMEM; + + RB_CLEAR_NODE(&new_rb_node->rb_node); + new_rb_node->map = map; + + while (*p != NULL) { + parent = *p; + m = rb_entry(parent, struct map_rb_node, rb_node); + if (ip < m->map->start) + p = &(*p)->rb_left; + else + p = &(*p)->rb_right; + } + + rb_link_node(&new_rb_node->rb_node, parent, p); + rb_insert_color(&new_rb_node->rb_node, &maps->entries); + map__get(map); + return 0; +} + +int maps__insert(struct maps *maps, struct map *map) +{ + int err; + down_write(&maps->lock); - __maps__insert(maps, map); + err = __maps__insert(maps, map); + if (err) + goto out; + ++maps->nr_maps; if (map->dso && map->dso->kernel) { @@ -59,32 +91,39 @@ void maps__insert(struct maps *maps, struct map *map) if (maps_by_name == NULL) { __maps__free_maps_by_name(maps); - up_write(&maps->lock); - return; + err = -ENOMEM; + goto out; } maps->maps_by_name = maps_by_name; maps->nr_maps_allocated = nr_allocate; - } +} maps->maps_by_name[maps->nr_maps - 1] = map; __maps__sort_by_name(maps); } + out: up_write(&maps->lock); + return err; } -static void __maps__remove(struct maps *maps, struct map *map) +static void __maps__remove(struct maps *maps, struct map_rb_node *rb_node) { - rb_erase_init(&map->rb_node, &maps->entries); - map__put(map); + rb_erase_init(&rb_node->rb_node, &maps->entries); + map__put(rb_node->map); + free(rb_node); } void maps__remove(struct maps *maps, struct map *map) { + struct map_rb_node *rb_node; + down_write(&maps->lock); if (maps->last_search_by_name == map) maps->last_search_by_name = NULL; - __maps__remove(maps, map); + rb_node = maps__find_node(maps, map); + assert(rb_node->map == map); + __maps__remove(maps, rb_node); --maps->nr_maps; if (maps->maps_by_name) __maps__free_maps_by_name(maps); @@ -93,11 +132,12 @@ void maps__remove(struct maps *maps, struct map *map) static void __maps__purge(struct maps *maps) { - struct map *pos, *next; + struct map_rb_node *pos, *next; maps__for_each_entry_safe(maps, pos, next) { rb_erase_init(&pos->rb_node, &maps->entries); - map__put(pos); + map__put(pos->map); + free(pos); } } @@ -153,21 +193,21 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { struct symbol *sym; - struct map *pos; + struct map_rb_node *pos; down_read(&maps->lock); maps__for_each_entry(maps, pos) { - sym = map__find_symbol_by_name(pos, name); + sym = map__find_symbol_by_name(pos->map, name); if (sym == NULL) continue; - if (!map__contains_symbol(pos, sym)) { + if (!map__contains_symbol(pos->map, sym)) { sym = NULL; continue; } if (mapp != NULL) - *mapp = pos; + *mapp = pos->map; goto out; } @@ -196,15 +236,15 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) size_t maps__fprintf(struct maps *maps, FILE *fp) { size_t printed = 0; - struct map *pos; + struct map_rb_node *pos; down_read(&maps->lock); maps__for_each_entry(maps, pos) { printed += fprintf(fp, "Map:"); - printed += map__fprintf(pos, fp); + printed += map__fprintf(pos->map, fp); if (verbose > 2) { - printed += dso__fprintf(pos->dso, fp); + printed += dso__fprintf(pos->map->dso, fp); printed += fprintf(fp, "--\n"); } } @@ -231,11 +271,11 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) next = root->rb_node; first = NULL; while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); + struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node); - if (pos->end > map->start) { + if (pos->map->end > map->start) { first = next; - if (pos->start <= map->start) + if (pos->map->start <= map->start) break; next = next->rb_left; } else @@ -244,14 +284,14 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) next = first; while (next) { - struct map *pos = rb_entry(next, struct map, rb_node); + struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node); next = rb_next(&pos->rb_node); /* * Stop if current map starts after map->end. * Maps are ordered by start: next will not overlap for sure. */ - if (pos->start >= map->end) + if (pos->map->start >= map->end) break; if (verbose >= 2) { @@ -262,7 +302,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) } else { fputs("overlapping maps:\n", fp); map__fprintf(map, fp); - map__fprintf(pos, fp); + map__fprintf(pos->map, fp); } } @@ -271,8 +311,8 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) * Now check if we need to create new maps for areas not * overlapped by the new map: */ - if (map->start > pos->start) { - struct map *before = map__clone(pos); + if (map->start > pos->map->start) { + struct map *before = map__clone(pos->map); if (before == NULL) { err = -ENOMEM; @@ -280,14 +320,17 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) } before->end = map->start; - __maps__insert(maps, before); + err = __maps__insert(maps, before); + if (err) + goto put_map; + if (verbose >= 2 && !use_browser) map__fprintf(before, fp); map__put(before); } - if (map->end < pos->end) { - struct map *after = map__clone(pos); + if (map->end < pos->map->end) { + struct map *after = map__clone(pos->map); if (after == NULL) { err = -ENOMEM; @@ -295,15 +338,19 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) } after->start = map->end; - after->pgoff += map->end - pos->start; - assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end)); - __maps__insert(maps, after); + after->pgoff += map->end - pos->map->start; + assert(pos->map->map_ip(pos->map, map->end) == + after->map_ip(after, map->end)); + err = __maps__insert(maps, after); + if (err) + goto put_map; + if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); } put_map: - map__put(pos); + map__put(pos->map); if (err) goto out; @@ -322,12 +369,12 @@ int maps__clone(struct thread *thread, struct maps *parent) { struct maps *maps = thread->maps; int err; - struct map *map; + struct map_rb_node *rb_node; down_read(&parent->lock); - maps__for_each_entry(parent, map) { - struct map *new = map__clone(map); + maps__for_each_entry(parent, rb_node) { + struct map *new = map__clone(rb_node->map); if (new == NULL) { err = -ENOMEM; @@ -338,7 +385,10 @@ int maps__clone(struct thread *thread, struct maps *parent) if (err) goto out_unlock; - maps__insert(maps, new); + err = maps__insert(maps, new); + if (err) + goto out_unlock; + map__put(new); } @@ -348,40 +398,31 @@ int maps__clone(struct thread *thread, struct maps *parent) return err; } -static void __maps__insert(struct maps *maps, struct map *map) +struct map_rb_node *maps__find_node(struct maps *maps, struct map *map) { - struct rb_node **p = &maps->entries.rb_node; - struct rb_node *parent = NULL; - const u64 ip = map->start; - struct map *m; + struct map_rb_node *rb_node; - while (*p != NULL) { - parent = *p; - m = rb_entry(parent, struct map, rb_node); - if (ip < m->start) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; + maps__for_each_entry(maps, rb_node) { + if (rb_node->map == map) + return rb_node; } - - rb_link_node(&map->rb_node, parent, p); - rb_insert_color(&map->rb_node, &maps->entries); - map__get(map); + return NULL; } struct map *maps__find(struct maps *maps, u64 ip) { struct rb_node *p; - struct map *m; + struct map_rb_node *m; + down_read(&maps->lock); p = maps->entries.rb_node; while (p != NULL) { - m = rb_entry(p, struct map, rb_node); - if (ip < m->start) + m = rb_entry(p, struct map_rb_node, rb_node); + if (ip < m->map->start) p = p->rb_left; - else if (ip >= m->end) + else if (ip >= m->map->end) p = p->rb_right; else goto out; @@ -390,14 +431,29 @@ struct map *maps__find(struct maps *maps, u64 ip) m = NULL; out: up_read(&maps->lock); - return m; + return m ? m->map : NULL; } -struct map *maps__first(struct maps *maps) +struct map_rb_node *maps__first(struct maps *maps) { struct rb_node *first = rb_first(&maps->entries); if (first) - return rb_entry(first, struct map, rb_node); + return rb_entry(first, struct map_rb_node, rb_node); return NULL; } + +struct map_rb_node *map_rb_node__next(struct map_rb_node *node) +{ + struct rb_node *next; + + if (!node) + return NULL; + + next = rb_next(&node->rb_node); + + if (!next) + return NULL; + + return rb_entry(next, struct map_rb_node, rb_node); +} diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index 7e729ff42749..512746ec0f9a 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -15,15 +15,22 @@ struct map; struct maps; struct thread; +struct map_rb_node { + struct rb_node rb_node; + struct map *map; +}; + +struct map_rb_node *maps__first(struct maps *maps); +struct map_rb_node *map_rb_node__next(struct map_rb_node *node); +struct map_rb_node *maps__find_node(struct maps *maps, struct map *map); struct map *maps__find(struct maps *maps, u64 addr); -struct map *maps__first(struct maps *maps); -struct map *map__next(struct map *map); #define maps__for_each_entry(maps, map) \ - for (map = maps__first(maps); map; map = map__next(map)) + for (map = maps__first(maps); map; map = map_rb_node__next(map)) #define maps__for_each_entry_safe(maps, map, next) \ - for (map = maps__first(maps), next = map__next(map); map; map = next, next = map__next(map)) + for (map = maps__first(maps), next = map_rb_node__next(map); map; \ + map = next, next = map_rb_node__next(map)) struct maps { struct rb_root entries; @@ -63,7 +70,7 @@ void maps__put(struct maps *maps); int maps__clone(struct thread *thread, struct maps *parent); size_t maps__fprintf(struct maps *maps, FILE *fp); -void maps__insert(struct maps *maps, struct map *map); +int maps__insert(struct maps *maps, struct map *map); void maps__remove(struct maps *maps, struct map *map); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 881d94f65a6b..cdf5d655d84c 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -151,23 +151,27 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, static struct map *kernel_get_module_map(const char *module) { struct maps *maps = machine__kernel_maps(host_machine); - struct map *pos; + struct map_rb_node *pos; /* A file path -- this is an offline module */ if (module && strchr(module, '/')) return dso__new_map(module); if (!module) { - pos = machine__kernel_map(host_machine); - return map__get(pos); + struct map *map = machine__kernel_map(host_machine); + + return map__get(map); } maps__for_each_entry(maps, pos) { /* short_name is "[module]" */ - if (strncmp(pos->dso->short_name + 1, module, - pos->dso->short_name_len - 2) == 0 && - module[pos->dso->short_name_len - 2] == '\0') { - return map__get(pos); + const char *short_name = pos->map->dso->short_name; + u16 short_name_len = pos->map->dso->short_name_len; + + if (strncmp(short_name + 1, module, + short_name_len - 2) == 0 && + module[short_name_len - 2] == '\0') { + return map__get(pos->map); } } return NULL; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index ae810d4cf3cd..33e1f587baa9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1361,10 +1361,14 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map->unmap_ip = map__unmap_ip; /* Ensure maps are correctly ordered */ if (kmaps) { + int err; + map__get(map); maps__remove(kmaps, map); - maps__insert(kmaps, map); + err = maps__insert(kmaps, map); map__put(map); + if (err) + return err; } } @@ -1417,7 +1421,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; } curr_dso->symtab_type = dso->symtab_type; - maps__insert(kmaps, curr_map); + if (maps__insert(kmaps, curr_map)) + return -1; /* * Add it before we drop the reference to curr_map, i.e. while * we still are sure to have a reference to this DSO via diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 8719074b7f21..e7a8ae290c57 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -273,13 +273,13 @@ void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) void maps__fixup_end(struct maps *maps) { - struct map *prev = NULL, *curr; + struct map_rb_node *prev = NULL, *curr; down_write(&maps->lock); maps__for_each_entry(maps, curr) { - if (prev != NULL && !prev->end) - prev->end = curr->start; + if (prev != NULL && !prev->map->end) + prev->map->end = curr->map->start; prev = curr; } @@ -288,8 +288,8 @@ void maps__fixup_end(struct maps *maps) * We still haven't the actual symbols, so guess the * last map final address. */ - if (curr && !curr->end) - curr->end = ~0ULL; + if (curr && !curr->map->end) + curr->map->end = ~0ULL; up_write(&maps->lock); } @@ -942,7 +942,10 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, } curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; - maps__insert(kmaps, curr_map); + if (maps__insert(kmaps, curr_map)) { + dso__put(ndso); + return -1; + } ++kernel_range; } else if (delta) { /* Kernel was relocated at boot time */ @@ -1130,14 +1133,15 @@ int compare_proc_modules(const char *from, const char *to) static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) { struct rb_root modules = RB_ROOT; - struct map *old_map; + struct map_rb_node *old_node; int err; err = read_proc_modules(filename, &modules); if (err) return err; - maps__for_each_entry(kmaps, old_map) { + maps__for_each_entry(kmaps, old_node) { + struct map *old_map = old_node->map; struct module_info *mi; if (!__map__is_kmodule(old_map)) { @@ -1254,10 +1258,13 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) */ int maps__merge_in(struct maps *kmaps, struct map *new_map) { - struct map *old_map; + struct map_rb_node *rb_node; LIST_HEAD(merged); + int err = 0; + + maps__for_each_entry(kmaps, rb_node) { + struct map *old_map = rb_node->map; - maps__for_each_entry(kmaps, old_map) { /* no overload with this one */ if (new_map->end < old_map->start || new_map->start >= old_map->end) @@ -1281,13 +1288,16 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) */ struct map_list_node *m = map_list_node__new(); - if (!m) - return -ENOMEM; + if (!m) { + err = -ENOMEM; + goto out; + } m->map = map__clone(new_map); if (!m->map) { free(m); - return -ENOMEM; + err = -ENOMEM; + goto out; } m->map->end = old_map->start; @@ -1319,21 +1329,24 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) } } +out: while (!list_empty(&merged)) { struct map_list_node *old_node; old_node = list_entry(merged.next, struct map_list_node, node); list_del_init(&old_node->node); - maps__insert(kmaps, old_node->map); + if (!err) + err = maps__insert(kmaps, old_node->map); map__put(old_node->map); free(old_node); } if (new_map) { - maps__insert(kmaps, new_map); + if (!err) + err = maps__insert(kmaps, new_map); map__put(new_map); } - return 0; + return err; } static int dso__load_kcore(struct dso *dso, struct map *map, @@ -1341,7 +1354,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, { struct maps *kmaps = map__kmaps(map); struct kcore_mapfn_data md; - struct map *old_map, *replacement_map = NULL, *next; + struct map *replacement_map = NULL; + struct map_rb_node *old_node, *next; struct machine *machine; bool is_64_bit; int err, fd; @@ -1388,7 +1402,9 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Remove old maps */ - maps__for_each_entry_safe(kmaps, old_map, next) { + maps__for_each_entry_safe(kmaps, old_node, next) { + struct map *old_map = old_node->map; + /* * We need to preserve eBPF maps even if they are * covered by kcore, because we need to access @@ -1443,17 +1459,21 @@ static int dso__load_kcore(struct dso *dso, struct map *map, /* Ensure maps are correctly ordered */ map__get(map); maps__remove(kmaps, map); - maps__insert(kmaps, map); + err = maps__insert(kmaps, map); map__put(map); map__put(new_map); + if (err) + goto out_err; } else { /* * Merge kcore map into existing maps, * and ensure that current maps (eBPF) * stay intact. */ - if (maps__merge_in(kmaps, new_map)) + if (maps__merge_in(kmaps, new_map)) { + err = -EINVAL; goto out_err; + } } free(new_node); } @@ -1500,7 +1520,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, free(list_node); } close(fd); - return -EINVAL; + return err; } /* @@ -2044,8 +2064,9 @@ void __maps__sort_by_name(struct maps *maps) static int map__groups__sort_by_name_from_rbtree(struct maps *maps) { - struct map *map; - struct map **maps_by_name = realloc(maps->maps_by_name, maps->nr_maps * sizeof(map)); + struct map_rb_node *rb_node; + struct map **maps_by_name = realloc(maps->maps_by_name, + maps->nr_maps * sizeof(struct map *)); int i = 0; if (maps_by_name == NULL) @@ -2057,8 +2078,8 @@ static int map__groups__sort_by_name_from_rbtree(struct maps *maps) maps->maps_by_name = maps_by_name; maps->nr_maps_allocated = maps->nr_maps; - maps__for_each_entry(maps, map) - maps_by_name[i++] = map; + maps__for_each_entry(maps, rb_node) + maps_by_name[i++] = rb_node->map; __maps__sort_by_name(maps); @@ -2084,6 +2105,7 @@ static struct map *__maps__find_by_name(struct maps *maps, const char *name) struct map *maps__find_by_name(struct maps *maps, const char *name) { + struct map_rb_node *rb_node; struct map *map; down_read(&maps->lock); @@ -2102,12 +2124,13 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) goto out_unlock; /* Fallback to traversing the rbtree... */ - maps__for_each_entry(maps, map) + maps__for_each_entry(maps, rb_node) { + map = rb_node->map; if (strcmp(map->dso->short_name, name) == 0) { maps->last_search_by_name = map; goto out_unlock; } - + } map = NULL; out_unlock: diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 6def01036eb5..57b95c1d7e39 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -669,7 +669,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t struct machine *machine) { int rc = 0; - struct map *pos; + struct map_rb_node *pos; struct maps *maps = machine__kernel_maps(machine); union perf_event *event; size_t size = symbol_conf.buildid_mmap2 ? @@ -692,37 +692,39 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL; maps__for_each_entry(maps, pos) { - if (!__map__is_kmodule(pos)) + struct map *map = pos->map; + + if (!__map__is_kmodule(map)) continue; if (symbol_conf.buildid_mmap2) { - size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + size = PERF_ALIGN(map->dso->long_name_len + 1, sizeof(u64)); event->mmap2.header.type = PERF_RECORD_MMAP2; event->mmap2.header.size = (sizeof(event->mmap2) - (sizeof(event->mmap2.filename) - size)); memset(event->mmap2.filename + size, 0, machine->id_hdr_size); event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.start = pos->start; - event->mmap2.len = pos->end - pos->start; + event->mmap2.start = map->start; + event->mmap2.len = map->end - map->start; event->mmap2.pid = machine->pid; - memcpy(event->mmap2.filename, pos->dso->long_name, - pos->dso->long_name_len + 1); + memcpy(event->mmap2.filename, map->dso->long_name, + map->dso->long_name_len + 1); perf_record_mmap2__read_build_id(&event->mmap2, machine, false); } else { - size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64)); + size = PERF_ALIGN(map->dso->long_name_len + 1, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); memset(event->mmap.filename + size, 0, machine->id_hdr_size); event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = pos->start; - event->mmap.len = pos->end - pos->start; + event->mmap.start = map->start; + event->mmap.len = map->end - map->start; event->mmap.pid = machine->pid; - memcpy(event->mmap.filename, pos->dso->long_name, - pos->dso->long_name_len + 1); + memcpy(event->mmap.filename, map->dso->long_name, + map->dso->long_name_len + 1); } if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index a2490a20eb56..24e53bd55f7d 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -352,9 +352,7 @@ int thread__insert_map(struct thread *thread, struct map *map) return ret; maps__fixup_overlappings(thread->maps, map, stderr); - maps__insert(thread->maps, map); - - return 0; + return maps__insert(thread->maps, map); } static int __thread__prepare_access(struct thread *thread) @@ -362,12 +360,12 @@ static int __thread__prepare_access(struct thread *thread) bool initialized = false; int err = 0; struct maps *maps = thread->maps; - struct map *map; + struct map_rb_node *rb_node; down_read(&maps->lock); - maps__for_each_entry(maps, map) { - err = unwind__prepare_access(thread->maps, map, &initialized); + maps__for_each_entry(maps, rb_node) { + err = unwind__prepare_access(thread->maps, rb_node->map, &initialized); if (err || initialized) break; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 81b6bd6e1536..dea70a477b91 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -306,7 +306,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, u64 *table_data, u64 *segbase, u64 *fde_count) { - struct map *map; + struct map_rb_node *map_node; u64 base_addr = UINT64_MAX; int ret, fd; @@ -325,7 +325,9 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, return -EINVAL; } - maps__for_each_entry(ui->thread->maps, map) { + maps__for_each_entry(ui->thread->maps, map_node) { + struct map *map = map_node->map; + if (map->dso == dso && map->start < base_addr) base_addr = map->start; } diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 43beb169631d..835c39efb80d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -144,10 +144,11 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct thread *thread) { enum dso_type dso_type = DSO__TYPE_UNKNOWN; - struct map *map; + struct map_rb_node *rb_node; + + maps__for_each_entry(thread->maps, rb_node) { + struct dso *dso = rb_node->map->dso; - maps__for_each_entry(thread->maps, map) { - struct dso *dso = map->dso; if (!dso || dso->long_name[0] != '/') continue; dso_type = dso__type(dso, machine); -- GitLab From c0d0ce9b5a851895f34fd401c9dddc70616711a4 Mon Sep 17 00:00:00 2001 From: Xinghui Li Date: Mon, 3 Apr 2023 17:52:00 +0800 Subject: [PATCH 2004/5631] KVM: SVM: Remove a duplicate definition of VMCB_AVIC_APIC_BAR_MASK VMCB_AVIC_APIC_BAR_MASK is defined twice with the same value in svm.h, which is meaningless. Delete the duplicate one. Fixes: 391503528257 ("KVM: x86: SVM: move avic definitions from AMD's spec to svm.h") Signed-off-by: Xinghui Li Reviewed-by: Like Xu Link: https://lore.kernel.org/r/20230403095200.1391782-1-korantwork@gmail.com [sean: tweak shortlog] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/svm.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 25306a420b84..e7c7379d6ac7 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -287,7 +287,6 @@ static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID); #define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL struct vmcb_seg { -- GitLab From 5ab6d715c32f6249415bcd1972bae7e6c03636f0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 20 Mar 2023 14:22:34 -0700 Subject: [PATCH 2005/5631] perf maps: Add functions to access maps Introduce functions to access struct maps. These functions reduce the number of places reference counting is necessary. While tidying APIs do some small const-ification, in particlar to unwind_libunwind_ops. Committer notes: Fixed up tools/perf/util/unwind-libunwind.c: - return ops->get_entries(cb, arg, thread, data, max_stack); + return ops->get_entries(cb, arg, thread, data, max_stack, best_effort); Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../scripts/python/Perf-Trace-Util/Context.c | 7 +- tools/perf/tests/code-reading.c | 2 +- tools/perf/ui/browsers/hists.c | 3 +- tools/perf/util/callchain.c | 9 +-- tools/perf/util/db-export.c | 12 ++-- tools/perf/util/dlfilter.c | 8 ++- tools/perf/util/event.c | 4 +- tools/perf/util/hist.c | 2 +- tools/perf/util/machine.c | 2 +- tools/perf/util/map.c | 14 ++-- tools/perf/util/maps.c | 71 +++++++++++-------- tools/perf/util/maps.h | 47 +++++++++--- .../scripting-engines/trace-event-python.c | 2 +- tools/perf/util/sort.c | 2 +- tools/perf/util/symbol-elf.c | 2 +- tools/perf/util/symbol.c | 44 ++++++------ tools/perf/util/thread-stack.c | 4 +- tools/perf/util/thread.c | 4 +- tools/perf/util/unwind-libunwind-local.c | 16 +++-- tools/perf/util/unwind-libunwind.c | 31 ++++---- 20 files changed, 175 insertions(+), 111 deletions(-) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index b0d449f41650..feedd02b3b3d 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -100,10 +100,11 @@ static PyObject *perf_sample_insn(PyObject *obj, PyObject *args) if (!c) return NULL; - if (c->sample->ip && !c->sample->insn_len && - c->al->thread->maps && c->al->thread->maps->machine) - script_fetch_insn(c->sample, c->al->thread, c->al->thread->maps->machine); + if (c->sample->ip && !c->sample->insn_len && c->al->thread->maps) { + struct machine *machine = maps__machine(c->al->thread->maps); + script_fetch_insn(c->sample, c->al->thread, machine); + } if (!c->sample->insn_len) Py_RETURN_NONE; /* N.B. This is a return statement */ diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index fb67fd5ebd9f..8d2036f2f944 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -269,7 +269,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len = al.map->end - addr; /* Read the object code using perf */ - ret_len = dso__data_read_offset(al.map->dso, thread->maps->machine, + ret_len = dso__data_read_offset(al.map->dso, maps__machine(thread->maps), al.addr, buf1, len); if (ret_len != len) { pr_debug("dso__data_read_offset failed\n"); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index b72ee6822222..572ff38ceb0f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -3139,7 +3139,8 @@ static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *h continue; case 'k': if (browser->selection != NULL) - hists_browser__zoom_map(browser, browser->selection->maps->machine->vmlinux_map); + hists_browser__zoom_map(browser, + maps__machine(browser->selection->maps)->vmlinux_map); continue; case 'V': verbose = (verbose + 1) % 4; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index a093a15f048f..0aa979f64565 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1112,6 +1112,8 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { + struct machine *machine = maps__machine(node->ms.maps); + al->maps = node->ms.maps; al->map = node->ms.map; al->sym = node->ms.sym; @@ -1124,9 +1126,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * if (al->map == NULL) goto out; } - - if (al->maps == machine__kernel_maps(al->maps->machine)) { - if (machine__is_host(al->maps->machine)) { + if (al->maps == machine__kernel_maps(machine)) { + if (machine__is_host(machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; } else { @@ -1134,7 +1135,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * al->level = 'g'; } } else { - if (machine__is_host(al->maps->machine)) { + if (machine__is_host(machine)) { al->cpumode = PERF_RECORD_MISC_USER; al->level = '.'; } else if (perf_guest) { diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index e0d4f08839fb..1cfcfdd3cf52 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -181,7 +181,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, if (al->map) { struct dso *dso = al->map->dso; - err = db_export__dso(dbe, dso, al->maps->machine); + err = db_export__dso(dbe, dso, maps__machine(al->maps)); if (err) return err; *dso_db_id = dso->db_id; @@ -354,19 +354,21 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, }; struct thread *main_thread; struct comm *comm = NULL; + struct machine *machine; int err; err = db_export__evsel(dbe, evsel); if (err) return err; - err = db_export__machine(dbe, al->maps->machine); + machine = maps__machine(al->maps); + err = db_export__machine(dbe, machine); if (err) return err; - main_thread = thread__main_thread(al->maps->machine, thread); + main_thread = thread__main_thread(machine, thread); - err = db_export__threads(dbe, thread, main_thread, al->maps->machine, &comm); + err = db_export__threads(dbe, thread, main_thread, machine, &comm); if (err) goto out_put; @@ -380,7 +382,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event, goto out_put; if (dbe->cpr) { - struct call_path *cp = call_path_from_sample(dbe, al->maps->machine, + struct call_path *cp = call_path_from_sample(dbe, machine, thread, sample, evsel); if (cp) { diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 37beb7530288..fe2a0752a0f6 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -197,8 +197,12 @@ static const __u8 *dlfilter__insn(void *ctx, __u32 *len) if (!al->thread && machine__resolve(d->machine, al, d->sample) < 0) return NULL; - if (al->thread->maps && al->thread->maps->machine) - script_fetch_insn(d->sample, al->thread, al->thread->maps->machine); + if (al->thread->maps) { + struct machine *machine = maps__machine(al->thread->maps); + + if (machine) + script_fetch_insn(d->sample, al->thread, machine); + } } if (!d->sample->insn_len) diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 1fa14598b916..f40cdd6ac126 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -572,7 +572,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { struct maps *maps = thread->maps; - struct machine *machine = maps->machine; + struct machine *machine = maps__machine(maps); bool load_map = false; al->maps = maps; @@ -637,7 +637,7 @@ struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { struct map *map = thread__find_map(thread, cpumode, addr, al); - struct machine *machine = thread->maps->machine; + struct machine *machine = maps__machine(thread->maps); u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr); if (map || addr_cpumode == cpumode) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index b339ff863fe2..5f9f38ed5da1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -241,7 +241,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->cgroup) { const char *cgrp_name = "unknown"; - struct cgroup *cgrp = cgroup__find(h->ms.maps->machine->env, + struct cgroup *cgrp = cgroup__find(maps__machine(h->ms.maps)->env, h->cgroup); if (cgrp != NULL) cgrp_name = cgrp->name; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2058623726d2..d6da4b5e1333 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2847,7 +2847,7 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread, static u64 get_leaf_frame_caller(struct perf_sample *sample, struct thread *thread, int usr_idx) { - if (machine__normalized_is(thread->maps->machine, "arm64")) + if (machine__normalized_is(maps__machine(thread->maps), "arm64")) return get_leaf_frame_caller_aarch64(sample, thread, usr_idx); else return 0; diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 7620cfa114d4..a99dbde656a2 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -234,7 +234,7 @@ bool __map__is_kernel(const struct map *map) { if (!map->dso->kernel) return false; - return machine__kernel_map(map__kmaps((struct map *)map)->machine) == map; + return machine__kernel_map(maps__machine(map__kmaps((struct map *)map))) == map; } bool __map__is_extra_kernel_map(const struct map *map) @@ -475,11 +475,15 @@ u64 map__rip_2objdump(struct map *map, u64 rip) * kcore may not either. However the trampoline object code is on the * main kernel map, so just use that instead. */ - if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps && kmap->kmaps->machine) { - struct map *kernel_map = machine__kernel_map(kmap->kmaps->machine); + if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps) { + struct machine *machine = maps__machine(kmap->kmaps); - if (kernel_map) - map = kernel_map; + if (machine) { + struct map *kernel_map = machine__kernel_map(machine); + + if (kernel_map) + map = kernel_map; + } } if (!map->dso->adjust_symbols) diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 83ec126bcbe5..91bb015caede 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -13,7 +13,7 @@ static void maps__init(struct maps *maps, struct machine *machine) { maps->entries = RB_ROOT; - init_rwsem(&maps->lock); + init_rwsem(maps__lock(maps)); maps->machine = machine; maps->last_search_by_name = NULL; maps->nr_maps = 0; @@ -32,7 +32,7 @@ static void __maps__free_maps_by_name(struct maps *maps) static int __maps__insert(struct maps *maps, struct map *map) { - struct rb_node **p = &maps->entries.rb_node; + struct rb_node **p = &maps__entries(maps)->rb_node; struct rb_node *parent = NULL; const u64 ip = map->start; struct map_rb_node *m, *new_rb_node; @@ -54,7 +54,7 @@ static int __maps__insert(struct maps *maps, struct map *map) } rb_link_node(&new_rb_node->rb_node, parent, p); - rb_insert_color(&new_rb_node->rb_node, &maps->entries); + rb_insert_color(&new_rb_node->rb_node, maps__entries(maps)); map__get(map); return 0; } @@ -63,7 +63,7 @@ int maps__insert(struct maps *maps, struct map *map) { int err; - down_write(&maps->lock); + down_write(maps__lock(maps)); err = __maps__insert(maps, map); if (err) goto out; @@ -84,10 +84,11 @@ int maps__insert(struct maps *maps, struct map *map) * If we already performed some search by name, then we need to add the just * inserted map and resort. */ - if (maps->maps_by_name) { - if (maps->nr_maps > maps->nr_maps_allocated) { - int nr_allocate = maps->nr_maps * 2; - struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map)); + if (maps__maps_by_name(maps)) { + if (maps__nr_maps(maps) > maps->nr_maps_allocated) { + int nr_allocate = maps__nr_maps(maps) * 2; + struct map **maps_by_name = realloc(maps__maps_by_name(maps), + nr_allocate * sizeof(map)); if (maps_by_name == NULL) { __maps__free_maps_by_name(maps); @@ -97,18 +98,18 @@ int maps__insert(struct maps *maps, struct map *map) maps->maps_by_name = maps_by_name; maps->nr_maps_allocated = nr_allocate; -} - maps->maps_by_name[maps->nr_maps - 1] = map; + } + maps__maps_by_name(maps)[maps__nr_maps(maps) - 1] = map; __maps__sort_by_name(maps); } out: - up_write(&maps->lock); + up_write(maps__lock(maps)); return err; } static void __maps__remove(struct maps *maps, struct map_rb_node *rb_node) { - rb_erase_init(&rb_node->rb_node, &maps->entries); + rb_erase_init(&rb_node->rb_node, maps__entries(maps)); map__put(rb_node->map); free(rb_node); } @@ -117,7 +118,7 @@ void maps__remove(struct maps *maps, struct map *map) { struct map_rb_node *rb_node; - down_write(&maps->lock); + down_write(maps__lock(maps)); if (maps->last_search_by_name == map) maps->last_search_by_name = NULL; @@ -125,9 +126,9 @@ void maps__remove(struct maps *maps, struct map *map) assert(rb_node->map == map); __maps__remove(maps, rb_node); --maps->nr_maps; - if (maps->maps_by_name) + if (maps__maps_by_name(maps)) __maps__free_maps_by_name(maps); - up_write(&maps->lock); + up_write(maps__lock(maps)); } static void __maps__purge(struct maps *maps) @@ -135,7 +136,7 @@ static void __maps__purge(struct maps *maps) struct map_rb_node *pos, *next; maps__for_each_entry_safe(maps, pos, next) { - rb_erase_init(&pos->rb_node, &maps->entries); + rb_erase_init(&pos->rb_node, maps__entries(maps)); map__put(pos->map); free(pos); } @@ -143,9 +144,9 @@ static void __maps__purge(struct maps *maps) static void maps__exit(struct maps *maps) { - down_write(&maps->lock); + down_write(maps__lock(maps)); __maps__purge(maps); - up_write(&maps->lock); + up_write(maps__lock(maps)); } bool maps__empty(struct maps *maps) @@ -170,6 +171,14 @@ void maps__delete(struct maps *maps) free(maps); } +struct maps *maps__get(struct maps *maps) +{ + if (maps) + refcount_inc(&maps->refcnt); + + return maps; +} + void maps__put(struct maps *maps) { if (maps && refcount_dec_and_test(&maps->refcnt)) @@ -195,7 +204,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, st struct symbol *sym; struct map_rb_node *pos; - down_read(&maps->lock); + down_read(maps__lock(maps)); maps__for_each_entry(maps, pos) { sym = map__find_symbol_by_name(pos->map, name); @@ -213,7 +222,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, st sym = NULL; out: - up_read(&maps->lock); + up_read(maps__lock(maps)); return sym; } @@ -238,7 +247,7 @@ size_t maps__fprintf(struct maps *maps, FILE *fp) size_t printed = 0; struct map_rb_node *pos; - down_read(&maps->lock); + down_read(maps__lock(maps)); maps__for_each_entry(maps, pos) { printed += fprintf(fp, "Map:"); @@ -249,7 +258,7 @@ size_t maps__fprintf(struct maps *maps, FILE *fp) } } - up_read(&maps->lock); + up_read(maps__lock(maps)); return printed; } @@ -260,9 +269,9 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) struct rb_node *next, *first; int err = 0; - down_write(&maps->lock); + down_write(maps__lock(maps)); - root = &maps->entries; + root = maps__entries(maps); /* * Find first map where end > map->start. @@ -358,7 +367,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) err = 0; out: - up_write(&maps->lock); + up_write(maps__lock(maps)); return err; } @@ -371,7 +380,7 @@ int maps__clone(struct thread *thread, struct maps *parent) int err; struct map_rb_node *rb_node; - down_read(&parent->lock); + down_read(maps__lock(parent)); maps__for_each_entry(parent, rb_node) { struct map *new = map__clone(rb_node->map); @@ -394,7 +403,7 @@ int maps__clone(struct thread *thread, struct maps *parent) err = 0; out_unlock: - up_read(&parent->lock); + up_read(maps__lock(parent)); return err; } @@ -415,9 +424,9 @@ struct map *maps__find(struct maps *maps, u64 ip) struct map_rb_node *m; - down_read(&maps->lock); + down_read(maps__lock(maps)); - p = maps->entries.rb_node; + p = maps__entries(maps)->rb_node; while (p != NULL) { m = rb_entry(p, struct map_rb_node, rb_node); if (ip < m->map->start) @@ -430,13 +439,13 @@ struct map *maps__find(struct maps *maps, u64 ip) m = NULL; out: - up_read(&maps->lock); + up_read(maps__lock(maps)); return m ? m->map : NULL; } struct map_rb_node *maps__first(struct maps *maps) { - struct rb_node *first = rb_first(&maps->entries); + struct rb_node *first = rb_first(maps__entries(maps)); if (first) return rb_entry(first, struct map_rb_node, rb_node); diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index 512746ec0f9a..bde3390c7096 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -43,7 +43,7 @@ struct maps { unsigned int nr_maps_allocated; #ifdef HAVE_LIBUNWIND_SUPPORT void *addr_space; - struct unwind_libunwind_ops *unwind_libunwind_ops; + const struct unwind_libunwind_ops *unwind_libunwind_ops; #endif }; @@ -58,20 +58,51 @@ struct kmap { struct maps *maps__new(struct machine *machine); void maps__delete(struct maps *maps); bool maps__empty(struct maps *maps); +int maps__clone(struct thread *thread, struct maps *parent); + +struct maps *maps__get(struct maps *maps); +void maps__put(struct maps *maps); -static inline struct maps *maps__get(struct maps *maps) +static inline struct rb_root *maps__entries(struct maps *maps) { - if (maps) - refcount_inc(&maps->refcnt); - return maps; + return &maps->entries; } -void maps__put(struct maps *maps); -int maps__clone(struct thread *thread, struct maps *parent); +static inline struct machine *maps__machine(struct maps *maps) +{ + return maps->machine; +} + +static inline struct rw_semaphore *maps__lock(struct maps *maps) +{ + return &maps->lock; +} + +static inline struct map **maps__maps_by_name(struct maps *maps) +{ + return maps->maps_by_name; +} + +static inline unsigned int maps__nr_maps(const struct maps *maps) +{ + return maps->nr_maps; +} + +#ifdef HAVE_LIBUNWIND_SUPPORT +static inline void *maps__addr_space(struct maps *maps) +{ + return maps->addr_space; +} + +static inline const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps) +{ + return maps->unwind_libunwind_ops; +} +#endif + size_t maps__fprintf(struct maps *maps, FILE *fp); int maps__insert(struct maps *maps, struct map *map); - void maps__remove(struct maps *maps, struct map *map); struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index 0f4ef61f2ffa..e5cc18f6fcda 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -1288,7 +1288,7 @@ static void python_export_sample_table(struct db_export *dbe, tuple_set_d64(t, 0, es->db_id); tuple_set_d64(t, 1, es->evsel->db_id); - tuple_set_d64(t, 2, es->al->maps->machine->db_id); + tuple_set_d64(t, 2, maps__machine(es->al->maps)->db_id); tuple_set_d64(t, 3, es->al->thread->db_id); tuple_set_d64(t, 4, es->comm_db_id); tuple_set_d64(t, 5, es->dso_db_id); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2b5cc8e4aa6e..430f67e7cc82 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -803,7 +803,7 @@ static int hist_entry__cgroup_snprintf(struct hist_entry *he, const char *cgrp_name = "N/A"; if (he->cgroup) { - struct cgroup *cgrp = cgroup__find(he->ms.maps->machine->env, + struct cgroup *cgrp = cgroup__find(maps__machine(he->ms.maps)->env, he->cgroup); if (cgrp != NULL) cgrp_name = cgrp->name; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 33e1f587baa9..3084e556d3eb 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1428,7 +1428,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, * we still are sure to have a reference to this DSO via * *curr_map->dso. */ - dsos__add(&kmaps->machine->dsos, curr_dso); + dsos__add(&maps__machine(kmaps)->dsos, curr_dso); /* kmaps already got it */ map__put(curr_map); dso__set_loaded(curr_dso); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7a8ae290c57..316b63fb5691 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -275,7 +275,7 @@ void maps__fixup_end(struct maps *maps) { struct map_rb_node *prev = NULL, *curr; - down_write(&maps->lock); + down_write(maps__lock(maps)); maps__for_each_entry(maps, curr) { if (prev != NULL && !prev->map->end) @@ -291,7 +291,7 @@ void maps__fixup_end(struct maps *maps) if (curr && !curr->map->end) curr->map->end = ~0ULL; - up_write(&maps->lock); + up_write(maps__lock(maps)); } struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name) @@ -844,7 +844,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (!kmaps) return -1; - machine = kmaps->machine; + machine = maps__machine(kmaps); x86_64 = machine__is(machine, "x86_64"); @@ -968,7 +968,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (curr_map != initial_map && dso->kernel == DSO_SPACE__KERNEL_GUEST && - machine__is_default_guest(kmaps->machine)) { + machine__is_default_guest(maps__machine(kmaps))) { dso__set_loaded(curr_map->dso); } @@ -1365,7 +1365,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, if (!kmaps) return -EINVAL; - machine = kmaps->machine; + machine = maps__machine(kmaps); /* This function requires that the map is the kernel map */ if (!__map__is_kernel(map)) @@ -1894,7 +1894,7 @@ int dso__load(struct dso *dso, struct map *map) else if (dso->kernel == DSO_SPACE__KERNEL_GUEST) ret = dso__load_guest_kernel_sym(dso, map); - machine = map__kmaps(map)->machine; + machine = maps__machine(map__kmaps(map)); if (machine__is(machine, "x86_64")) machine__map_x86_64_entry_trampolines(machine, dso); goto out; @@ -2059,32 +2059,32 @@ static int map__strcmp_name(const void *name, const void *b) void __maps__sort_by_name(struct maps *maps) { - qsort(maps->maps_by_name, maps->nr_maps, sizeof(struct map *), map__strcmp); + qsort(maps__maps_by_name(maps), maps__nr_maps(maps), sizeof(struct map *), map__strcmp); } static int map__groups__sort_by_name_from_rbtree(struct maps *maps) { struct map_rb_node *rb_node; - struct map **maps_by_name = realloc(maps->maps_by_name, - maps->nr_maps * sizeof(struct map *)); + struct map **maps_by_name = realloc(maps__maps_by_name(maps), + maps__nr_maps(maps) * sizeof(struct map *)); int i = 0; if (maps_by_name == NULL) return -1; - up_read(&maps->lock); - down_write(&maps->lock); + up_read(maps__lock(maps)); + down_write(maps__lock(maps)); maps->maps_by_name = maps_by_name; - maps->nr_maps_allocated = maps->nr_maps; + maps->nr_maps_allocated = maps__nr_maps(maps); maps__for_each_entry(maps, rb_node) maps_by_name[i++] = rb_node->map; __maps__sort_by_name(maps); - up_write(&maps->lock); - down_read(&maps->lock); + up_write(maps__lock(maps)); + down_read(maps__lock(maps)); return 0; } @@ -2093,11 +2093,12 @@ static struct map *__maps__find_by_name(struct maps *maps, const char *name) { struct map **mapp; - if (maps->maps_by_name == NULL && + if (maps__maps_by_name(maps) == NULL && map__groups__sort_by_name_from_rbtree(maps)) return NULL; - mapp = bsearch(name, maps->maps_by_name, maps->nr_maps, sizeof(*mapp), map__strcmp_name); + mapp = bsearch(name, maps__maps_by_name(maps), maps__nr_maps(maps), + sizeof(*mapp), map__strcmp_name); if (mapp) return *mapp; return NULL; @@ -2108,9 +2109,10 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) struct map_rb_node *rb_node; struct map *map; - down_read(&maps->lock); + down_read(maps__lock(maps)); - if (maps->last_search_by_name && strcmp(maps->last_search_by_name->dso->short_name, name) == 0) { + if (maps->last_search_by_name && + strcmp(maps->last_search_by_name->dso->short_name, name) == 0) { map = maps->last_search_by_name; goto out_unlock; } @@ -2120,7 +2122,7 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) * made. */ map = __maps__find_by_name(maps, name); - if (map || maps->maps_by_name != NULL) + if (map || maps__maps_by_name(maps) != NULL) goto out_unlock; /* Fallback to traversing the rbtree... */ @@ -2134,7 +2136,7 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) map = NULL; out_unlock: - up_read(&maps->lock); + up_read(maps__lock(maps)); return map; } @@ -2386,7 +2388,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map) { int err; const char *kallsyms_filename; - struct machine *machine = map__kmaps(map)->machine; + struct machine *machine = maps__machine(map__kmaps(map)); char path[PATH_MAX]; if (machine->kallsyms_filename) { diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c index 1b992bbba4e8..4b85c1728012 100644 --- a/tools/perf/util/thread-stack.c +++ b/tools/perf/util/thread-stack.c @@ -155,8 +155,8 @@ static int thread_stack__init(struct thread_stack *ts, struct thread *thread, ts->br_stack_sz = br_stack_sz; } - if (thread->maps && thread->maps->machine) { - struct machine *machine = thread->maps->machine; + if (thread->maps && maps__machine(thread->maps)) { + struct machine *machine = maps__machine(thread->maps); const char *arch = perf_env__arch(machine->env); ts->kernel_start = machine__kernel_start(machine); diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 24e53bd55f7d..292585a52281 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -362,7 +362,7 @@ static int __thread__prepare_access(struct thread *thread) struct maps *maps = thread->maps; struct map_rb_node *rb_node; - down_read(&maps->lock); + down_read(maps__lock(maps)); maps__for_each_entry(maps, rb_node) { err = unwind__prepare_access(thread->maps, rb_node->map, &initialized); @@ -370,7 +370,7 @@ static int __thread__prepare_access(struct thread *thread) break; } - up_read(&maps->lock); + up_read(maps__lock(maps)); return err; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index dea70a477b91..c487a249b33c 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -667,24 +667,26 @@ static unw_accessors_t accessors = { static int _unwind__prepare_access(struct maps *maps) { - maps->addr_space = unw_create_addr_space(&accessors, 0); - if (!maps->addr_space) { + void *addr_space = unw_create_addr_space(&accessors, 0); + + maps->addr_space = addr_space; + if (!addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; } - unw_set_caching_policy(maps->addr_space, UNW_CACHE_GLOBAL); + unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL); return 0; } static void _unwind__flush_access(struct maps *maps) { - unw_flush_cache(maps->addr_space, 0, 0); + unw_flush_cache(maps__addr_space(maps), 0, 0); } static void _unwind__finish_access(struct maps *maps) { - unw_destroy_addr_space(maps->addr_space); + unw_destroy_addr_space(maps__addr_space(maps)); } static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, @@ -709,7 +711,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, */ if (max_stack - 1 > 0) { WARN_ONCE(!ui->thread, "WARNING: ui->thread is NULL"); - addr_space = ui->thread->maps->addr_space; + addr_space = maps__addr_space(ui->thread->maps); if (addr_space == NULL) return -1; @@ -759,7 +761,7 @@ static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info ui = { .sample = data, .thread = thread, - .machine = thread->maps->machine, + .machine = maps__machine(thread->maps), .best_effort = best_effort }; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 509c287ee762..42528ade513e 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -22,12 +22,13 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized const char *arch; enum dso_type dso_type; struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; + struct machine *machine; int err; if (!dwarf_callchain_users) return 0; - if (maps->addr_space) { + if (maps__addr_space(maps)) { pr_debug("unwind: thread map already set, dso=%s\n", map->dso->name); if (initialized) @@ -35,15 +36,16 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized return 0; } + machine = maps__machine(maps); /* env->arch is NULL for live-mode (i.e. perf top) */ - if (!maps->machine->env || !maps->machine->env->arch) + if (!machine->env || !machine->env->arch) goto out_register; - dso_type = dso__type(map->dso, maps->machine); + dso_type = dso__type(map->dso, machine); if (dso_type == DSO__TYPE_UNKNOWN) return 0; - arch = perf_env__arch(maps->machine->env); + arch = perf_env__arch(machine->env); if (!strcmp(arch, "x86")) { if (dso_type != DSO__TYPE_64BIT) @@ -60,7 +62,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized out_register: unwind__register_ops(maps, ops); - err = maps->unwind_libunwind_ops->prepare_access(maps); + err = maps__unwind_libunwind_ops(maps)->prepare_access(maps); if (initialized) *initialized = err ? false : true; return err; @@ -68,14 +70,18 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized void unwind__flush_access(struct maps *maps) { - if (maps->unwind_libunwind_ops) - maps->unwind_libunwind_ops->flush_access(maps); + const struct unwind_libunwind_ops *ops = maps__unwind_libunwind_ops(maps); + + if (ops) + ops->flush_access(maps); } void unwind__finish_access(struct maps *maps) { - if (maps->unwind_libunwind_ops) - maps->unwind_libunwind_ops->finish_access(maps); + const struct unwind_libunwind_ops *ops = maps__unwind_libunwind_ops(maps); + + if (ops) + ops->finish_access(maps); } int unwind__get_entries(unwind_entry_cb_t cb, void *arg, @@ -83,8 +89,9 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct perf_sample *data, int max_stack, bool best_effort) { - if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, - max_stack, best_effort); + const struct unwind_libunwind_ops *ops = maps__unwind_libunwind_ops(thread->maps); + + if (ops) + return ops->get_entries(cb, arg, thread, data, max_stack, best_effort); return 0; } -- GitLab From 41e07665f1a683064f4c69b0d652dff1baf5d689 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:09 -0700 Subject: [PATCH 2006/5631] KVM: x86/mmu: Add a helper function to check if an SPTE needs atomic write Move conditions in kvm_tdp_mmu_write_spte() to check if an SPTE should be written atomically or not to a separate function. This new function, kvm_tdp_mmu_spte_need_atomic_write(), will be used in future commits to optimize clearing bits in SPTEs. Signed-off-by: Vipin Sharma Reviewed-by: David Matlack Reviewed-by: Ben Gardon Link: https://lore.kernel.org/r/20230321220021.2119033-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_iter.h | 34 ++++++++++++++++++++-------------- 1 file changed, 20 insertions(+), 14 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index f0af385c56e0..c11c5d00b2c1 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -29,23 +29,29 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) WRITE_ONCE(*rcu_dereference(sptep), new_spte); } +/* + * SPTEs must be modified atomically if they are shadow-present, leaf + * SPTEs, and have volatile bits, i.e. has bits that can be set outside + * of mmu_lock. The Writable bit can be set by KVM's fast page fault + * handler, and Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ +static inline bool kvm_tdp_mmu_spte_need_atomic_write(u64 old_spte, int level) +{ + return is_shadow_present_pte(old_spte) && + is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte); +} + static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, u64 new_spte, int level) { - /* - * Atomically write the SPTE if it is a shadow-present, leaf SPTE with - * volatile bits, i.e. has bits that can be set outside of mmu_lock. - * The Writable bit can be set by KVM's fast page fault handler, and - * Accessed and Dirty bits can be set by the CPU. - * - * Note, non-leaf SPTEs do have Accessed bits and those bits are - * technically volatile, but KVM doesn't consume the Accessed bit of - * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This - * logic needs to be reassessed if KVM were to use non-leaf Accessed - * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. - */ - if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && - spte_has_volatile_bits(old_spte)) + if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); __kvm_tdp_mmu_write_spte(sptep, new_spte); -- GitLab From 5982a5392663b30f57ee90b0372c19a7e9cb655a Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:10 -0700 Subject: [PATCH 2007/5631] KVM: x86/mmu: Use kvm_ad_enabled() to determine if TDP MMU SPTEs need wrprot Use the constant-after-module-load kvm_ad_enabled() to check if SPTEs in the TDP MMU need to be write-protected when clearing accessed/dirty status instead of manually checking every SPTE. The per-SPTE A/D enabling is specific to nested EPT MMUs, i.e. when KVM is using EPT A/D bits but L1 is not, and so cannot happen in the TDP MMU (which is non-nested only). Keep the original code as sanity checks buried under MMU_WARN_ON(). MMU_WARN_ON() is more or less useless at the moment, but there are plans to change that. Link: https://lore.kernel.org/all/Yz4Qi7cn7TWTWQjj@google.com Signed-off-by: Vipin Sharma [sean: split to separate patch, apply to dirty path, write changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-3-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7c25dbf32ecc..5a5642650c3e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1621,7 +1621,10 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, if (!is_shadow_present_pte(iter.old_spte)) continue; - if (spte_ad_need_write_protect(iter.old_spte)) { + MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); + + if (!kvm_ad_enabled()) { if (is_writable_pte(iter.old_spte)) new_spte = iter.old_spte & ~PT_WRITABLE_MASK; else @@ -1685,13 +1688,16 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; + MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); + if (iter.level > PG_LEVEL_4K || !(mask & (1UL << (iter.gfn - gfn)))) continue; mask &= ~(1UL << (iter.gfn - gfn)); - if (wrprot || spte_ad_need_write_protect(iter.old_spte)) { + if (wrprot || !kvm_ad_enabled()) { if (is_writable_pte(iter.old_spte)) new_spte = iter.old_spte & ~PT_WRITABLE_MASK; else -- GitLab From 697c89bed94effde145d84e618142dd89b2b54af Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:11 -0700 Subject: [PATCH 2008/5631] KVM: x86/mmu: Consolidate Dirty vs. Writable clearing logic in TDP MMU Deduplicate the guts of the TDP MMU's clearing of dirty status by snapshotting whether to check+clear the Dirty bit vs. the Writable bit, which is the only difference between the two flavors of dirty tracking. Note, kvm_ad_enabled() is just a wrapper for shadow_accessed_mask, i.e. is constant after kvm-{intel,amd}.ko is loaded. Link: https://lore.kernel.org/all/Yz4Qi7cn7TWTWQjj@google.com Signed-off-by: Vipin Sharma [sean: split to separate patch, apply to dirty log, write changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-4-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 35 +++++++++-------------------------- 1 file changed, 9 insertions(+), 26 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 5a5642650c3e..b32c9ba05c89 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1607,8 +1607,8 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { + u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; struct tdp_iter iter; - u64 new_spte; bool spte_set = false; rcu_read_lock(); @@ -1624,19 +1624,10 @@ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, MMU_WARN_ON(kvm_ad_enabled() && spte_ad_need_write_protect(iter.old_spte)); - if (!kvm_ad_enabled()) { - if (is_writable_pte(iter.old_spte)) - new_spte = iter.old_spte & ~PT_WRITABLE_MASK; - else - continue; - } else { - if (iter.old_spte & shadow_dirty_mask) - new_spte = iter.old_spte & ~shadow_dirty_mask; - else - continue; - } + if (!(iter.old_spte & dbit)) + continue; - if (tdp_mmu_set_spte_atomic(kvm, &iter, new_spte)) + if (tdp_mmu_set_spte_atomic(kvm, &iter, iter.old_spte & ~dbit)) goto retry; spte_set = true; @@ -1678,8 +1669,9 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { + u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; - u64 new_spte; rcu_read_lock(); @@ -1697,19 +1689,10 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, mask &= ~(1UL << (iter.gfn - gfn)); - if (wrprot || !kvm_ad_enabled()) { - if (is_writable_pte(iter.old_spte)) - new_spte = iter.old_spte & ~PT_WRITABLE_MASK; - else - continue; - } else { - if (iter.old_spte & shadow_dirty_mask) - new_spte = iter.old_spte & ~shadow_dirty_mask; - else - continue; - } + if (!(iter.old_spte & dbit)) + continue; - tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); + tdp_mmu_set_spte_no_dirty_log(kvm, &iter, iter.old_spte & ~dbit); } rcu_read_unlock(); -- GitLab From 89c313f20c1ed30e04cedae735994c902ee93ddb Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:12 -0700 Subject: [PATCH 2009/5631] KVM: x86/mmu: Atomically clear SPTE dirty state in the clear-dirty-log flow Optimize the clearing of dirty state in TDP MMU SPTEs by doing an atomic-AND (on SPTEs that have volatile bits) instead of the full XCHG that currently ends up being invoked (see kvm_tdp_mmu_write_spte()). Clearing _only_ the bit in question will allow KVM to skip the many irrelevant checks in __handle_changed_spte() by avoiding any collateral damage due to the XCHG writing all SPTE bits, e.g. the XCHG could race with fast_page_fault() setting the W-bit and the CPU setting the D-bit, and thus incorrectly drop the CPU's D-bit update. Link: https://lore.kernel.org/all/Y9hXmz%2FnDOr1hQal@google.com Signed-off-by: Vipin Sharma Reviewed-by: David Matlack [sean: split the switch to atomic-AND to a separate patch] Link: https://lore.kernel.org/r/20230321220021.2119033-5-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_iter.h | 14 ++++++++++++++ arch/x86/kvm/mmu/tdp_mmu.c | 16 ++++++++-------- 2 files changed, 22 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index c11c5d00b2c1..fae559559a80 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -58,6 +58,20 @@ static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, return old_spte; } +static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte, + u64 mask, int level) +{ + atomic64_t *sptep_atomic; + + if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) { + sptep_atomic = (atomic64_t *)rcu_dereference(sptep); + return (u64)atomic64_fetch_and(~mask, sptep_atomic); + } + + __kvm_tdp_mmu_write_spte(sptep, old_spte & ~mask); + return old_spte; +} + /* * A TDP iterator performs a pre-order walk over a TDP paging structure. */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index b32c9ba05c89..a70cc1dae18a 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -770,13 +770,6 @@ static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm, _tdp_mmu_set_spte(kvm, iter, new_spte, false, true); } -static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, true, false); -} - #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ for_each_tdp_pte(_iter, _root, _start, _end) @@ -1692,7 +1685,14 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!(iter.old_spte & dbit)) continue; - tdp_mmu_set_spte_no_dirty_log(kvm, &iter, iter.old_spte & ~dbit); + iter.old_spte = tdp_mmu_clear_spte_bits(iter.sptep, + iter.old_spte, dbit, + iter.level); + + __handle_changed_spte(kvm, iter.as_id, iter.gfn, iter.old_spte, + iter.old_spte & ~dbit, iter.level, false); + handle_changed_spte_acc_track(iter.old_spte, iter.old_spte & ~dbit, + iter.level); } rcu_read_unlock(); -- GitLab From cf05e8c7325e341d7e1b1920fa580a130ec2c350 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:13 -0700 Subject: [PATCH 2010/5631] KVM: x86/mmu: Drop access tracking checks when clearing TDP MMU dirty bits Drop the unnecessary call to handle access-tracking changes when clearing the dirty status of TDP MMU SPTEs. Neither the Dirty bit nor the Writable bit has any impact on the accessed state of a page, i.e. clearing only the aforementioned bits doesn't make an accessed SPTE suddently not accessed. Signed-off-by: Vipin Sharma [sean: split to separate patch, write changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-6-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index a70cc1dae18a..950c5d23ecee 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1691,8 +1691,6 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, __handle_changed_spte(kvm, iter.as_id, iter.gfn, iter.old_spte, iter.old_spte & ~dbit, iter.level, false); - handle_changed_spte_acc_track(iter.old_spte, iter.old_spte & ~dbit, - iter.level); } rcu_read_unlock(); -- GitLab From 1e0f42985ffad5c60e7a0a627405e1ff00208289 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:14 -0700 Subject: [PATCH 2011/5631] KVM: x86/mmu: Bypass __handle_changed_spte() when clearing TDP MMU dirty bits Drop everything except marking the PFN dirty and the relevant tracepoint parts of __handle_changed_spte() when clearing the dirty status of gfns in the TDP MMU. Clearing only the Dirty (or Writable) bit doesn't affect the SPTEs shadow-present status, whether or not the SPTE is a leaf, or change the SPTE's PFN. I.e. other than marking the PFN dirty, none of the functional updates handled by __handle_changed_spte() are relevant. Losing __handle_changed_spte()'s sanity checks does mean that a bug could theoretical go unnoticed, but that scenario is extremely unlikely, e.g. would effectively require a misconfigured or a locking bug elsewhere. Opportunistically remove a comment blurb from __handle_changed_spte() about all modifications to TDP MMU SPTEs needing to invoke said function, that "rule" hasn't been true since fast page fault support was added for the TDP MMU (and perhaps even before). Tested on a VM (160 vCPUs, 160 GB memory) and found that performance of clear dirty log stage improved by ~40% in dirty_log_perf_test (with the full optimization applied). Before optimization: -------------------- Iteration 1 clear dirty log time: 3.638543593s Iteration 2 clear dirty log time: 3.145032742s Iteration 3 clear dirty log time: 3.142340358s Clear dirty log over 3 iterations took 9.925916693s. (Avg 3.308638897s/iteration) After optimization: ------------------- Iteration 1 clear dirty log time: 2.318988110s Iteration 2 clear dirty log time: 1.794470164s Iteration 3 clear dirty log time: 1.791668628s Clear dirty log over 3 iterations took 5.905126902s. (Avg 1.968375634s/iteration) Link: https://lore.kernel.org/all/Y9hXmz%2FnDOr1hQal@google.com Signed-off-by: Vipin Sharma Reviewed-by: David Matlack [sean: split the switch to atomic-AND to a separate patch] Link: https://lore.kernel.org/r/20230321220021.2119033-7-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 950c5d23ecee..467931c43968 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -517,7 +517,6 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * threads that might be modifying SPTEs. * * Handle bookkeeping that might result from the modification of a SPTE. - * This function must be called for all TDP SPTE modifications. */ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, u64 old_spte, u64 new_spte, int level, @@ -1689,8 +1688,10 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, iter.old_spte, dbit, iter.level); - __handle_changed_spte(kvm, iter.as_id, iter.gfn, iter.old_spte, - iter.old_spte & ~dbit, iter.level, false); + trace_kvm_tdp_mmu_spte_changed(iter.as_id, iter.gfn, iter.level, + iter.old_spte, + iter.old_spte & ~dbit); + kvm_set_pfn_dirty(spte_to_pfn(iter.old_spte)); } rcu_read_unlock(); -- GitLab From e73008705d0c88ac69e3fe262bb03d86af23c521 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:15 -0700 Subject: [PATCH 2012/5631] KVM: x86/mmu: Remove "record_dirty_log" in __tdp_mmu_set_spte() Remove bool parameter "record_dirty_log" from __tdp_mmu_set_spte() and refactor the code as this variable is always set to true by its caller. Signed-off-by: Vipin Sharma Reviewed-by: David Matlack Link: https://lore.kernel.org/r/20230321220021.2119033-8-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 467931c43968..3cc81fa22b7f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -708,18 +708,13 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * notifier for access tracking. Leaving record_acc_track * unset in that case prevents page accesses from being * double counted. - * @record_dirty_log: Record the page as dirty in the dirty bitmap if - * appropriate for the change being made. Should be set - * unless performing certain dirty logging operations. - * Leaving record_dirty_log unset in that case prevents page - * writes from being double counted. * * Returns the old SPTE value, which _may_ be different than @old_spte if the * SPTE had voldatile bits. */ static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) + bool record_acc_track) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -738,35 +733,34 @@ static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, if (record_acc_track) handle_changed_spte_acc_track(old_spte, new_spte, level); - if (record_dirty_log) - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, - new_spte, level); + + handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, + level); return old_spte; } static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte, bool record_acc_track, - bool record_dirty_log) + u64 new_spte, bool record_acc_track) { WARN_ON_ONCE(iter->yielded); iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, iter->old_spte, new_spte, iter->gfn, iter->level, - record_acc_track, record_dirty_log); + record_acc_track); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - _tdp_mmu_set_spte(kvm, iter, new_spte, true, true); + _tdp_mmu_set_spte(kvm, iter, new_spte, true); } static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - _tdp_mmu_set_spte(kvm, iter, new_spte, false, true); + _tdp_mmu_set_spte(kvm, iter, new_spte, false); } #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ @@ -916,7 +910,7 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) return false; __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, - sp->gfn, sp->role.level + 1, true, true); + sp->gfn, sp->role.level + 1, true); return true; } -- GitLab From 7ee131e3a3c38dc7939ce35861a71f4ee55d9b02 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:16 -0700 Subject: [PATCH 2013/5631] KVM: x86/mmu: Clear only A-bit (if enabled) when aging TDP MMU SPTEs Use tdp_mmu_clear_spte_bits() when clearing the Accessed bit in TDP MMU SPTEs so as to use an atomic-AND instead of XCHG to clear the A-bit. Similar to the D-bit story, this will allow KVM to bypass __handle_changed_spte() by ensuring only the A-bit is modified. Link: https://lore.kernel.org/all/Y9HcHRBShQgjxsQb@google.com Signed-off-by: Vipin Sharma Reviewed-by: David Matlack [sean: massage changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-9-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 3cc81fa22b7f..adbdfed287cc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -756,13 +756,6 @@ static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, _tdp_mmu_set_spte(kvm, iter, new_spte, true); } -static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, false); -} - #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ for_each_tdp_pte(_iter, _root, _start, _end) @@ -1248,33 +1241,44 @@ static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm, /* * Mark the SPTEs range of GFNs [start, end) unaccessed and return non-zero * if any of the GFNs in the range have been accessed. + * + * No need to mark the corresponding PFN as accessed as this call is coming + * from the clear_young() or clear_flush_young() notifier, which uses the + * return value to determine if the page has been accessed. */ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter, struct kvm_gfn_range *range) { - u64 new_spte = 0; + u64 new_spte; /* If we have a non-accessed entry we don't need to change the pte. */ if (!is_accessed_spte(iter->old_spte)) return false; - new_spte = iter->old_spte; - - if (spte_ad_enabled(new_spte)) { - new_spte &= ~shadow_accessed_mask; + if (spte_ad_enabled(iter->old_spte)) { + iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep, + iter->old_spte, + shadow_accessed_mask, + iter->level); + new_spte = iter->old_spte & ~shadow_accessed_mask; } else { /* * Capture the dirty status of the page, so that it doesn't get * lost when the SPTE is marked for access tracking. */ - if (is_writable_pte(new_spte)) - kvm_set_pfn_dirty(spte_to_pfn(new_spte)); + if (is_writable_pte(iter->old_spte)) + kvm_set_pfn_dirty(spte_to_pfn(iter->old_spte)); - new_spte = mark_spte_for_access_track(new_spte); + new_spte = mark_spte_for_access_track(iter->old_spte); + iter->old_spte = kvm_tdp_mmu_write_spte(iter->sptep, + iter->old_spte, new_spte, + iter->level); } - tdp_mmu_set_spte_no_acc_track(kvm, iter, new_spte); - + __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, false); + handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn, + iter->old_spte, new_spte, iter->level); return true; } -- GitLab From 6141df067d04599706994b616e1a4b4c19ae5d07 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:17 -0700 Subject: [PATCH 2014/5631] KVM: x86/mmu: Drop unnecessary dirty log checks when aging TDP MMU SPTEs Drop the unnecessary call to handle dirty log updates when aging TDP MMU SPTEs, as neither clearing the Accessed bit nor marking a SPTE for access tracking can _set_ the Writable bit, i.e. can't trigger marking a gfn dirty in its memslot. The access tracking path can _clear_ the Writable bit, e.g. if the XCHG races with fast_page_fault() and writes the stale value without the Writable bit set, but clearing the Writable bit outside of mmu_lock is not allowed, i.e. access tracking can't spuriously set the Writable bit. Signed-off-by: Vipin Sharma [sean: split to separate patch, apply to dirty path, write changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-10-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index adbdfed287cc..29bb97ff266e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1277,8 +1277,6 @@ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter, __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level, false); - handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn, - iter->old_spte, new_spte, iter->level); return true; } -- GitLab From 891f115960682b84440bdfb1ea72ab2824206db7 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:18 -0700 Subject: [PATCH 2015/5631] KVM: x86/mmu: Bypass __handle_changed_spte() when aging TDP MMU SPTEs Drop everything except the "tdp_mmu_spte_changed" tracepoint part of __handle_changed_spte() when aging SPTEs in the TDP MMU, as clearing the accessed status doesn't affect the SPTE's shadow-present status, whether or not the SPTE is a leaf, or change the PFN. I.e. none of the functional updates handled by __handle_changed_spte() are relevant. Losing __handle_changed_spte()'s sanity checks does mean that a bug could theoretical go unnoticed, but that scenario is extremely unlikely, e.g. would effectively require a misconfigured MMU or a locking bug elsewhere. Link: https://lore.kernel.org/all/Y9HcHRBShQgjxsQb@google.com Signed-off-by: Vipin Sharma Reviewed-by: David Matlack [sean: massage changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-11-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 29bb97ff266e..cdfb67ef5800 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1275,8 +1275,8 @@ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter, iter->level); } - __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, - new_spte, iter->level, false); + trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level, + iter->old_spte, new_spte); return true; } -- GitLab From 0b7cc2547d5329b996b6687e04a82ed4eef1adda Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:19 -0700 Subject: [PATCH 2016/5631] KVM: x86/mmu: Remove "record_acc_track" in __tdp_mmu_set_spte() Remove bool parameter "record_acc_track" from __tdp_mmu_set_spte() and refactor the code. This variable is always set to true by its caller. Remove single and double underscore prefix from tdp_mmu_set_spte() related APIs: 1. Change __tdp_mmu_set_spte() to tdp_mmu_set_spte() 2. Change _tdp_mmu_set_spte() to tdp_mmu_iter_set_spte() Signed-off-by: Vipin Sharma Reviewed-by: David Matlack Link: https://lore.kernel.org/r/20230321220021.2119033-12-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 51 +++++++++++++------------------------- 1 file changed, 17 insertions(+), 34 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index cdfb67ef5800..9649e0fe4302 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -695,7 +695,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* - * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping + * tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping * @kvm: KVM instance * @as_id: Address space ID, i.e. regular vs. SMM * @sptep: Pointer to the SPTE @@ -703,18 +703,12 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * @new_spte: The new value that will be set for the SPTE * @gfn: The base GFN that was (or will be) mapped by the SPTE * @level: The level _containing_ the SPTE (its parent PT's level) - * @record_acc_track: Notify the MM subsystem of changes to the accessed state - * of the page. Should be set unless handling an MMU - * notifier for access tracking. Leaving record_acc_track - * unset in that case prevents page accesses from being - * double counted. * * Returns the old SPTE value, which _may_ be different than @old_spte if the * SPTE had voldatile bits. */ -static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track) +static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -730,30 +724,19 @@ static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); - - if (record_acc_track) - handle_changed_spte_acc_track(old_spte, new_spte, level); - + handle_changed_spte_acc_track(old_spte, new_spte, level); handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, level); return old_spte; } -static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte, bool record_acc_track) +static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, + u64 new_spte) { WARN_ON_ONCE(iter->yielded); - - iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, - iter->old_spte, new_spte, - iter->gfn, iter->level, - record_acc_track); -} - -static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, true); + iter->old_spte = tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level); } #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ @@ -845,7 +828,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, continue; if (!shared) - tdp_mmu_set_spte(kvm, &iter, 0); + tdp_mmu_iter_set_spte(kvm, &iter, 0); else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0)) goto retry; } @@ -902,8 +885,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte))) return false; - __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, - sp->gfn, sp->role.level + 1, true); + tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, + sp->gfn, sp->role.level + 1); return true; } @@ -937,7 +920,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, !is_last_spte(iter.old_spte, iter.level)) continue; - tdp_mmu_set_spte(kvm, &iter, 0); + tdp_mmu_iter_set_spte(kvm, &iter, 0); flush = true; } @@ -1107,7 +1090,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, if (ret) return ret; } else { - tdp_mmu_set_spte(kvm, iter, spte); + tdp_mmu_iter_set_spte(kvm, iter, spte); } tdp_account_mmu_page(kvm, sp); @@ -1314,13 +1297,13 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, * invariant that the PFN of a present * leaf SPTE can never change. * See __handle_changed_spte(). */ - tdp_mmu_set_spte(kvm, iter, 0); + tdp_mmu_iter_set_spte(kvm, iter, 0); if (!pte_write(range->pte)) { new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte, pte_pfn(range->pte)); - tdp_mmu_set_spte(kvm, iter, new_spte); + tdp_mmu_iter_set_spte(kvm, iter, new_spte); } return true; @@ -1805,7 +1788,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, if (new_spte == iter.old_spte) break; - tdp_mmu_set_spte(kvm, &iter, new_spte); + tdp_mmu_iter_set_spte(kvm, &iter, new_spte); spte_set = true; } -- GitLab From 1f9973456e802199e863030ed09493419a02f6c7 Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:20 -0700 Subject: [PATCH 2017/5631] KVM: x86/mmu: Remove handle_changed_spte_dirty_log() Remove handle_changed_spte_dirty_log() as there is no code flow which sets 4KiB SPTE writable and hit this path. This function marks the page dirty in a memslot only if new SPTE is 4KiB in size and writable. Current users of handle_changed_spte_dirty_log() are: 1. set_spte_gfn() - Create only non writable SPTEs. 2. write_protect_gfn() - Change an SPTE to non writable. 3. zap leaf and roots APIs - Everything is 0. 4. handle_removed_pt() - Sets SPTEs to REMOVED_SPTE 5. tdp_mmu_link_sp() - Makes non leaf SPTEs. There is also no path which creates a writable 4KiB without going through make_spte() and this functions takes care of marking SPTE dirty in the memslot if it is PT_WRITABLE. Signed-off-by: Vipin Sharma Reviewed-by: David Matlack [sean: add blurb to __handle_changed_spte()'s comment] Link: https://lore.kernel.org/r/20230321220021.2119033-13-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 9649e0fe4302..e8ee49b6da5b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -345,24 +345,6 @@ static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } -static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level) -{ - bool pfn_changed; - struct kvm_memory_slot *slot; - - if (level > PG_LEVEL_4K) - return; - - pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); - - if ((!is_writable_pte(old_spte) || pfn_changed) && - is_writable_pte(new_spte)) { - slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn); - mark_page_dirty_in_slot(kvm, slot, gfn); - } -} - static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); @@ -516,7 +498,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * the MMU lock and the operation must synchronize with other * threads that might be modifying SPTEs. * - * Handle bookkeeping that might result from the modification of a SPTE. + * Handle bookkeeping that might result from the modification of a SPTE. Note, + * dirty logging updates are handled in common code, not here (see make_spte() + * and fast_pf_fix_direct_spte()). */ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, u64 old_spte, u64 new_spte, int level, @@ -613,8 +597,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, shared); handle_changed_spte_acc_track(old_spte, new_spte, level); - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, - new_spte, level); } /* @@ -725,8 +707,6 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); handle_changed_spte_acc_track(old_spte, new_spte, level); - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, new_spte, - level); return old_spte; } -- GitLab From 40fa907e5a69edbae503a4937f8f487ed1ca92ea Mon Sep 17 00:00:00 2001 From: Vipin Sharma Date: Tue, 21 Mar 2023 15:00:21 -0700 Subject: [PATCH 2018/5631] KVM: x86/mmu: Merge all handle_changed_pte*() functions Merge __handle_changed_pte() and handle_changed_spte_acc_track() into a single function, handle_changed_pte(), as the two are always used together. Remove the existing handle_changed_pte(), as it's just a wrapper that calls __handle_changed_pte() and handle_changed_spte_acc_track(). Signed-off-by: Vipin Sharma Reviewed-by: Ben Gardon Reviewed-by: David Matlack [sean: massage changelog] Link: https://lore.kernel.org/r/20230321220021.2119033-14-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 42 +++++++++++--------------------------- 1 file changed, 12 insertions(+), 30 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index e8ee49b6da5b..b2fca11b91ff 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -334,17 +334,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, u64 old_spte, u64 new_spte, int level, bool shared); -static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) -{ - if (!is_shadow_present_pte(old_spte) || !is_last_spte(old_spte, level)) - return; - - if (is_accessed_spte(old_spte) && - (!is_shadow_present_pte(new_spte) || !is_accessed_spte(new_spte) || - spte_to_pfn(old_spte) != spte_to_pfn(new_spte))) - kvm_set_pfn_accessed(spte_to_pfn(old_spte)); -} - static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); @@ -487,7 +476,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } /** - * __handle_changed_spte - handle bookkeeping associated with an SPTE change + * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of * @gfn: the base GFN that was mapped by the SPTE @@ -502,9 +491,9 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * dirty logging updates are handled in common code, not here (see make_spte() * and fast_pf_fix_direct_spte()). */ -static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level, - bool shared) +static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, + u64 old_spte, u64 new_spte, int level, + bool shared) { bool was_present = is_shadow_present_pte(old_spte); bool is_present = is_shadow_present_pte(new_spte); @@ -588,15 +577,10 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, if (was_present && !was_leaf && (is_leaf || !is_present || WARN_ON_ONCE(pfn_changed))) handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared); -} -static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level, - bool shared) -{ - __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, - shared); - handle_changed_spte_acc_track(old_spte, new_spte, level); + if (was_leaf && is_accessed_spte(old_spte) && + (!is_present || !is_accessed_spte(new_spte) || pfn_changed)) + kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } /* @@ -639,9 +623,8 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) return -EBUSY; - __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, - new_spte, iter->level, true); - handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level); + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, true); return 0; } @@ -705,8 +688,7 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); - __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); - handle_changed_spte_acc_track(old_spte, new_spte, level); + handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); return old_spte; } @@ -1275,7 +1257,7 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, * Note, when changing a read-only SPTE, it's not strictly necessary to * zero the SPTE before setting the new PFN, but doing so preserves the * invariant that the PFN of a present * leaf SPTE can never change. - * See __handle_changed_spte(). + * See handle_changed_spte(). */ tdp_mmu_iter_set_spte(kvm, iter, 0); @@ -1300,7 +1282,7 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) /* * No need to handle the remote TLB flush under RCU protection, the * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a - * shadow page. See the WARN on pfn_changed in __handle_changed_spte(). + * shadow page. See the WARN on pfn_changed in handle_changed_spte(). */ return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn); } -- GitLab From 63df0e4bc368adbd12ed70ed4789d8d52d65661d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 20 Mar 2023 14:22:35 -0700 Subject: [PATCH 2019/5631] perf map: Add accessor for dso Later changes will add reference count checking for struct map, with dso being the most frequently accessed variable. Add an accessor so that the reference count check is only necessary in one place. Additional changes: - add a dso variable to avoid repeated map__dso calls. - in builtin-mem.c dump_raw_samples, code only partially tested for dso == NULL. Make the possibility of NULL consistent. - in thread.c thread__memcpy fix use of spaces and use tabs. Committer notes: Did missing conversions on these files: tools/perf/arch/powerpc/util/skip-callchain-idx.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/ui/browsers/hists.c tools/perf/ui/gtk/annotate.c tools/perf/util/cs-etm.c tools/perf/util/thread.c tools/perf/util/unwind-libunwind-local.c tools/perf/util/unwind-libunwind.c Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/powerpc/util/skip-callchain-idx.c | 2 +- tools/perf/arch/powerpc/util/sym-handling.c | 2 +- tools/perf/builtin-annotate.c | 11 ++- tools/perf/builtin-buildid-list.c | 2 +- tools/perf/builtin-inject.c | 8 +- tools/perf/builtin-kallsyms.c | 4 +- tools/perf/builtin-mem.c | 10 +- tools/perf/builtin-report.c | 7 +- tools/perf/builtin-script.c | 19 ++-- tools/perf/builtin-top.c | 11 ++- tools/perf/builtin-trace.c | 2 +- .../scripts/python/Perf-Trace-Util/Context.c | 6 +- tools/perf/tests/code-reading.c | 28 +++--- tools/perf/tests/hists_common.c | 8 +- tools/perf/tests/hists_cumulate.c | 4 +- tools/perf/tests/hists_filter.c | 4 +- tools/perf/tests/hists_output.c | 2 +- tools/perf/tests/maps.c | 2 +- tools/perf/tests/symbols.c | 6 +- tools/perf/tests/vmlinux-kallsyms.c | 13 ++- tools/perf/ui/browsers/annotate.c | 9 +- tools/perf/ui/browsers/hists.c | 17 ++-- tools/perf/ui/browsers/map.c | 4 +- tools/perf/ui/gtk/annotate.c | 5 +- tools/perf/util/annotate.c | 16 ++-- tools/perf/util/auxtrace.c | 2 +- tools/perf/util/block-info.c | 4 +- tools/perf/util/bpf-event.c | 10 +- tools/perf/util/build-id.c | 2 +- tools/perf/util/callchain.c | 6 +- tools/perf/util/cs-etm.c | 17 ++-- tools/perf/util/data-convert-json.c | 10 +- tools/perf/util/db-export.c | 4 +- tools/perf/util/dlfilter.c | 10 +- tools/perf/util/event.c | 9 +- tools/perf/util/evsel_fprintf.c | 2 +- tools/perf/util/hist.c | 10 +- tools/perf/util/intel-pt.c | 45 +++++---- tools/perf/util/machine.c | 70 ++++++++------ tools/perf/util/map.c | 96 ++++++++++++------- tools/perf/util/map.h | 7 +- tools/perf/util/maps.c | 7 +- tools/perf/util/probe-event.c | 30 +++--- .../util/scripting-engines/trace-event-perl.c | 10 +- .../scripting-engines/trace-event-python.c | 16 ++-- tools/perf/util/sort.c | 49 +++++----- tools/perf/util/symbol-elf.c | 2 +- tools/perf/util/symbol.c | 55 +++++++---- tools/perf/util/synthetic-events.c | 12 +-- tools/perf/util/thread.c | 30 +++--- tools/perf/util/unwind-libdw.c | 10 +- tools/perf/util/unwind-libunwind-local.c | 31 +++--- tools/perf/util/unwind-libunwind.c | 6 +- tools/perf/util/vdso.c | 2 +- 54 files changed, 447 insertions(+), 319 deletions(-) diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index 20cd6244863b..fe0e4530673c 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -255,7 +255,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al); if (al.map) - dso = al.map->dso; + dso = map__dso(al.map); if (!dso) { pr_debug("%" PRIx64 " dso is NULL\n", ip); diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 0856b32f9e08..9f99fc88dbff 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -104,7 +104,7 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym); - if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) + if (map__dso(map)->symtab_type == DSO_BINARY_TYPE__KALLSYMS) tev->point.offset += PPC64LE_LEP_OFFSET; else if (lep_offset) { if (pev->uprobes) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 655987afef58..63fd2080b803 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -205,7 +205,7 @@ static int process_branch_callback(struct evsel *evsel, return 0; if (a.map != NULL) - a.map->dso->hit = 1; + map__dso(a.map)->hit = 1; hist__account_cycles(sample->branch_stack, al, sample, false, NULL); @@ -235,10 +235,11 @@ static int evsel__add_sample(struct evsel *evsel, struct perf_sample *sample, * the DSO? */ if (al->sym != NULL) { - rb_erase_cached(&al->sym->rb_node, - &al->map->dso->symbols); + struct dso *dso = map__dso(al->map); + + rb_erase_cached(&al->sym->rb_node, &dso->symbols); symbol__delete(al->sym); - dso__reset_find_symbol_cache(al->map->dso); + dso__reset_find_symbol_cache(dso); } return 0; } @@ -320,7 +321,7 @@ static void hists__find_annotations(struct hists *hists, struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node); struct annotation *notes; - if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned) + if (he->ms.sym == NULL || map__dso(he->ms.map)->annotate_warned) goto find_next; if (ann->sym_hist_filter && diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 00bfe89f0b5d..cad9ed44ce7c 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -24,7 +24,7 @@ static int buildid__map_cb(struct map *map, void *arg __maybe_unused) { - const struct dso *dso = map->dso; + const struct dso *dso = map__dso(map); char bid_buf[SBUILD_ID_SIZE]; memset(bid_buf, 0, sizeof(bid_buf)); diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 10bb1d494258..8f6909dd8a54 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -753,9 +753,11 @@ int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, } if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) { - if (!al.map->dso->hit) { - al.map->dso->hit = 1; - dso__inject_build_id(al.map->dso, tool, machine, + struct dso *dso = map__dso(al.map); + + if (!dso->hit) { + dso->hit = 1; + dso__inject_build_id(dso, tool, machine, sample->cpumode, al.map->flags); } } diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c index c08ee81529e8..5638ca4dbd8e 100644 --- a/tools/perf/builtin-kallsyms.c +++ b/tools/perf/builtin-kallsyms.c @@ -28,6 +28,7 @@ static int __cmd_kallsyms(int argc, const char **argv) for (i = 0; i < argc; ++i) { struct map *map; + const struct dso *dso; struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map); if (symbol == NULL) { @@ -35,8 +36,9 @@ static int __cmd_kallsyms(int argc, const char **argv) continue; } + dso = map__dso(map); printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n", - symbol->name, map->dso->short_name, map->dso->long_name, + symbol->name, dso->short_name, dso->long_name, map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end), symbol->start, symbol->end); } diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index dedd612eae5e..1e27188b0de1 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -200,6 +200,7 @@ dump_raw_samples(struct perf_tool *tool, struct addr_location al; const char *fmt, *field_sep; char str[PAGE_SIZE_NAME_LEN]; + struct dso *dso = NULL; if (machine__resolve(machine, &al, sample) < 0) { fprintf(stderr, "problem processing %d event, skipping it.\n", @@ -210,8 +211,11 @@ dump_raw_samples(struct perf_tool *tool, if (al.filtered || (mem->hide_unresolved && al.sym == NULL)) goto out_put; - if (al.map != NULL) - al.map->dso->hit = 1; + if (al.map != NULL) { + dso = map__dso(al.map); + if (dso) + dso->hit = 1; + } field_sep = symbol_conf.field_sep; if (field_sep) { @@ -252,7 +256,7 @@ dump_raw_samples(struct perf_tool *tool, symbol_conf.field_sep, sample->data_src, symbol_conf.field_sep, - al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???", + dso ? dso->long_name : "???", al.sym ? al.sym->name : "???"); out_put: addr_location__put(&al); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c7e3863e8f44..ff239b89e4d0 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -319,7 +319,7 @@ static int process_sample_event(struct perf_tool *tool, } if (al.map != NULL) - al.map->dso->hit = 1; + map__dso(al.map)->hit = 1; if (ui__has_annotation() || rep->symbol_ipc || rep->total_cycles_mode) { hist__account_cycles(sample->branch_stack, &al, sample, @@ -608,7 +608,7 @@ static void report__warn_kptr_restrict(const struct report *rep) return; if (kernel_map == NULL || - (kernel_map->dso->hit && + (map__dso(kernel_map)->hit && (kernel_kmap->ref_reloc_sym == NULL || kernel_kmap->ref_reloc_sym->addr == 0))) { const char *desc = @@ -848,6 +848,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) maps__for_each_entry(maps, rb_node) { struct map *map = rb_node->map; + const struct dso *dso = map__dso(map); printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", indent, "", map->start, map->end, @@ -856,7 +857,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) map->prot & PROT_EXEC ? 'x' : '-', map->flags & MAP_SHARED ? 's' : 'p', map->pgoff, - map->dso->id.ino, map->dso->name); + dso->id.ino, dso->name); } return printed; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index c9296d8b33c0..27fd9c203600 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1011,11 +1011,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, to = entries[i].to; if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && - !alf.map->dso->adjust_symbols) + !map__dso(alf.map)->adjust_symbols) from = map__map_ip(alf.map, from); if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && - !alt.map->dso->adjust_symbols) + !map__dso(alt.map)->adjust_symbols) to = map__map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); @@ -1044,6 +1044,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, long offset, len; struct addr_location al; bool kernel; + struct dso *dso; if (!start || !end) return 0; @@ -1074,11 +1075,12 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) { + dso = map__dso(al.map); + if (!thread__find_map(thread, *cpumode, start, &al) || !dso) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } - if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) { + if (dso->data.status == DSO_DATA_STATUS_ERROR) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } @@ -1087,10 +1089,10 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, map__load(al.map); offset = al.map->map_ip(al.map, start); - len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer, + len = dso__data_read_offset(dso, machine, offset, (u8 *)buffer, end - start + MAXINSN); - *is64bit = al.map->dso->is_64_bit; + *is64bit = dso->is_64_bit; if (len <= 0) pr_debug("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n", start, end); @@ -1104,10 +1106,11 @@ static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srcc unsigned line; int len; char *srccode; + struct dso *dso = map__dso(map); - if (!map || !map->dso) + if (!map || !dso) return 0; - srcfile = get_srcline_split(map->dso, + srcfile = get_srcline_split(dso, map__rip_2objdump(map, addr), &line); if (!srcfile) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 2c985cfea517..babfc163efe2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -114,6 +114,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) struct symbol *sym; struct annotation *notes; struct map *map; + struct dso *dso; int err = -1; if (!he || !he->ms.sym) @@ -123,12 +124,12 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he) sym = he->ms.sym; map = he->ms.map; + dso = map__dso(map); /* * We can't annotate with just /proc/kallsyms */ - if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && - !dso__is_kcore(map->dso)) { + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) { pr_err("Can't annotate %s: No vmlinux file was found in the " "path\n", sym->name); sleep(1); @@ -169,6 +170,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) { struct utsname uts; int err = uname(&uts); + struct dso *dso = map__dso(map); ui__warning("Out of bounds address found:\n\n" "Addr: %" PRIx64 "\n" @@ -180,7 +182,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) "Tools: %s\n\n" "Not all samples will be on the annotation output.\n\n" "Please report to linux-kernel@vger.kernel.org\n", - ip, map->dso->long_name, dso__symtab_origin(map->dso), + ip, dso->long_name, dso__symtab_origin(dso), map->start, map->end, sym->start, sym->end, sym->binding == STB_GLOBAL ? 'g' : sym->binding == STB_LOCAL ? 'l' : 'w', sym->name, @@ -810,7 +812,8 @@ static void perf_event__process_sample(struct perf_tool *tool, __map__is_kernel(al.map) && map__has_symbols(al.map)) { if (symbol_conf.vmlinux_name) { char serr[256]; - dso__strerror_load(al.map->dso, serr, sizeof(serr)); + + dso__strerror_load(map__dso(al.map), serr, sizeof(serr)); ui__warning("The %s file can't be used: %s\n%s", symbol_conf.vmlinux_name, serr, msg); } else { diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index b363c609818b..72ef0bebb06b 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2863,7 +2863,7 @@ static void print_location(FILE *f, struct perf_sample *sample, { if ((verbose > 0 || print_dso) && al->map) - fprintf(f, "%s@", al->map->dso->long_name); + fprintf(f, "%s@", map__dso(al->map)->long_name); if ((verbose > 0 || print_sym) && al->sym) fprintf(f, "%s+0x%" PRIx64, al->sym->name, diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c index feedd02b3b3d..53b1587db403 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -145,6 +145,7 @@ static PyObject *perf_sample_src(PyObject *obj, PyObject *args, bool get_srccode char *srccode = NULL; PyObject *result; struct map *map; + struct dso *dso; int len = 0; u64 addr; @@ -153,9 +154,10 @@ static PyObject *perf_sample_src(PyObject *obj, PyObject *args, bool get_srccode map = c->al->map; addr = c->al->addr; + dso = map ? map__dso(map) : NULL; - if (map && map->dso) - srcfile = get_srcline_split(map->dso, map__rip_2objdump(map, addr), &line); + if (dso) + srcfile = get_srcline_split(dso, map__rip_2objdump(map, addr), &line); if (get_srccode) { if (srcfile) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 8d2036f2f944..936c61546e64 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -237,10 +237,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, char decomp_name[KMOD_DECOMP_LEN]; bool decomp = false; int ret, err = 0; + struct dso *dso; pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr); - if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) { + if (!thread__find_map(thread, cpumode, addr, &al) || !map__dso(al.map)) { if (cpumode == PERF_RECORD_MISC_HYPERVISOR) { pr_debug("Hypervisor address can not be resolved - skipping\n"); goto out; @@ -250,11 +251,10 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, err = -1; goto out; } + dso = map__dso(al.map); + pr_debug("File is: %s\n", dso->long_name); - pr_debug("File is: %s\n", al.map->dso->long_name); - - if (al.map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && - !dso__is_kcore(al.map->dso)) { + if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS && !dso__is_kcore(dso)) { pr_debug("Unexpected kernel address - skipping\n"); goto out; } @@ -269,7 +269,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len = al.map->end - addr; /* Read the object code using perf */ - ret_len = dso__data_read_offset(al.map->dso, maps__machine(thread->maps), + ret_len = dso__data_read_offset(dso, maps__machine(thread->maps), al.addr, buf1, len); if (ret_len != len) { pr_debug("dso__data_read_offset failed\n"); @@ -287,7 +287,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, } /* objdump struggles with kcore - try each map only once */ - if (dso__is_kcore(al.map->dso)) { + if (dso__is_kcore(dso)) { size_t d; for (d = 0; d < state->done_cnt; d++) { @@ -304,9 +304,9 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, state->done[state->done_cnt++] = al.map->start; } - objdump_name = al.map->dso->long_name; - if (dso__needs_decompress(al.map->dso)) { - if (dso__decompress_kmodule_path(al.map->dso, objdump_name, + objdump_name = dso->long_name; + if (dso__needs_decompress(dso)) { + if (dso__decompress_kmodule_path(dso, objdump_name, decomp_name, sizeof(decomp_name)) < 0) { pr_debug("decompression failed\n"); @@ -335,7 +335,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len -= ret; if (len) { pr_debug("Reducing len to %zu\n", len); - } else if (dso__is_kcore(al.map->dso)) { + } else if (dso__is_kcore(dso)) { /* * objdump cannot handle very large segments * that may be found in kcore. @@ -572,6 +572,7 @@ static int do_test_code_reading(bool try_kcore) pid_t pid; struct map *map; bool have_vmlinux, have_kcore, excl_kernel = false; + struct dso *dso; pid = getpid(); @@ -595,8 +596,9 @@ static int do_test_code_reading(bool try_kcore) pr_debug("map__load failed\n"); goto out_err; } - have_vmlinux = dso__is_vmlinux(map->dso); - have_kcore = dso__is_kcore(map->dso); + dso = map__dso(map); + have_vmlinux = dso__is_vmlinux(dso); + have_kcore = dso__is_kcore(dso); /* 2nd time through we just try kcore */ if (try_kcore && !have_kcore) diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index 6f34d08b84e5..745ab18d17db 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -179,9 +179,11 @@ void print_hists_in(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node_in); if (!he->filtered) { + struct dso *dso = map__dso(he->ms.map); + pr_info("%2d: entry: %-8s [%-8s] %20s: period = %"PRIu64"\n", i, thread__comm_str(he->thread), - he->ms.map->dso->short_name, + dso->short_name, he->ms.sym->name, he->stat.period); } @@ -206,9 +208,11 @@ void print_hists_out(struct hists *hists) he = rb_entry(node, struct hist_entry, rb_node); if (!he->filtered) { + struct dso *dso = map__dso(he->ms.map); + pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"/%"PRIu64"\n", i, thread__comm_str(he->thread), he->thread->tid, - he->ms.map->dso->short_name, + dso->short_name, he->ms.sym->name, he->stat.period, he->stat_acc ? he->stat_acc->period : 0); } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index b42d37ff2399..f00ec9abdbcd 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -150,12 +150,12 @@ static void del_hist_entries(struct hists *hists) typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) -#define DSO(he) (he->ms.map->dso->short_name) +#define DSO(he) (map__dso(he->ms.map)->short_name) #define SYM(he) (he->ms.sym->name) #define CPU(he) (he->cpu) #define PID(he) (he->thread->tid) #define DEPTH(he) (he->callchain->max_depth) -#define CDSO(cl) (cl->ms.map->dso->short_name) +#define CDSO(cl) (map__dso(cl->ms.map)->short_name) #define CSYM(cl) (cl->ms.sym->name) struct result { diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 8e1ceeb9b7b6..7c552549f4a4 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -194,7 +194,7 @@ static int test__hists_filter(struct test_suite *test __maybe_unused, int subtes hists__filter_by_thread(hists); /* now applying dso filter for 'kernel' */ - hists->dso_filter = fake_samples[0].map->dso; + hists->dso_filter = map__dso(fake_samples[0].map); hists__filter_by_dso(hists); if (verbose > 2) { @@ -288,7 +288,7 @@ static int test__hists_filter(struct test_suite *test __maybe_unused, int subtes /* now applying all filters at once. */ hists->thread_filter = fake_samples[1].thread; - hists->dso_filter = fake_samples[1].map->dso; + hists->dso_filter = map__dso(fake_samples[1].map); hists__filter_by_thread(hists); hists__filter_by_dso(hists); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 62b0093253e3..428d11a938f2 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -116,7 +116,7 @@ static void del_hist_entries(struct hists *hists) typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) -#define DSO(he) (he->ms.map->dso->short_name) +#define DSO(he) (map__dso(he->ms.map)->short_name) #define SYM(he) (he->ms.sym->name) #define CPU(he) (he->cpu) #define PID(he) (he->thread->tid) diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 8246d37e4b7a..ae7028fbf79e 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -26,7 +26,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma TEST_ASSERT_VAL("wrong map start", map->start == merged[i].start); TEST_ASSERT_VAL("wrong map end", map->end == merged[i].end); - TEST_ASSERT_VAL("wrong map name", !strcmp(map->dso->name, merged[i].name)); + TEST_ASSERT_VAL("wrong map name", !strcmp(map__dso(map)->name, merged[i].name)); TEST_ASSERT_VAL("wrong map refcnt", refcount_read(&map->refcnt) == 1); i++; diff --git a/tools/perf/tests/symbols.c b/tools/perf/tests/symbols.c index 0793f8f419e2..2d1aa42d36a9 100644 --- a/tools/perf/tests/symbols.c +++ b/tools/perf/tests/symbols.c @@ -102,6 +102,7 @@ static int test_file(struct test_info *ti, char *filename) { struct map *map = NULL; int ret, nr; + struct dso *dso; pr_debug("Testing %s\n", filename); @@ -109,7 +110,8 @@ static int test_file(struct test_info *ti, char *filename) if (ret != TEST_OK) return ret; - nr = dso__load(map->dso, map); + dso = map__dso(map); + nr = dso__load(dso, map); if (nr < 0) { pr_debug("dso__load() failed!\n"); ret = TEST_FAIL; @@ -122,7 +124,7 @@ static int test_file(struct test_info *ti, char *filename) goto out_put; } - ret = test_dso(map->dso); + ret = test_dso(dso); out_put: map__put(map); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index c8abb3ca8347..c614c2db7e89 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -293,15 +293,16 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused maps__for_each_entry(maps, rb_node) { struct map *map = rb_node->map; + struct dso *dso = map__dso(map); /* * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while * the kernel will have the path for the vmlinux file being used, * so use the short name, less descriptive but the same ("[kernel]" in * both cases. */ - struct map *pair = maps__find_by_name(kallsyms.kmaps, (map->dso->kernel ? - map->dso->short_name : - map->dso->name)); + struct map *pair = maps__find_by_name(kallsyms.kmaps, (dso->kernel ? + dso->short_name : + dso->name)); if (pair) { pair->priv = 1; } else { @@ -326,17 +327,19 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused continue; if (pair->start == mem_start) { + struct dso *dso = map__dso(map); + if (!header_printed) { pr_info("WARN: Maps in vmlinux with a different name in kallsyms:\n"); header_printed = true; } pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", - map->start, map->end, map->pgoff, map->dso->name); + map->start, map->end, map->pgoff, dso->name); if (mem_end != pair->end) pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, pair->start, pair->end, pair->pgoff); - pr_info(" %s\n", pair->dso->name); + pr_info(" %s\n", dso->name); pair->priv = 1; } } diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index c03fa76c02ff..12c3ce530e42 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -441,7 +441,8 @@ static void ui_browser__init_asm_mode(struct ui_browser *browser) static int sym_title(struct symbol *sym, struct map *map, char *title, size_t sz, int percent_type) { - return snprintf(title, sz, "%s %s [Percent: %s]", sym->name, map->dso->long_name, + return snprintf(title, sz, "%s %s [Percent: %s]", sym->name, + map__dso(map)->long_name, percent_type_str(percent_type)); } @@ -964,20 +965,22 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel, }, .opts = opts, }; + struct dso *dso; int ret = -1, err; int not_annotated = list_empty(¬es->src->source); if (sym == NULL) return -1; - if (ms->map->dso->annotate_warned) + dso = map__dso(ms->map); + if (dso->annotate_warned) return -1; if (not_annotated) { err = symbol__annotate2(ms, evsel, opts, &browser.arch); if (err) { char msg[BUFSIZ]; - ms->map->dso->annotate_warned = true; + dso->annotate_warned = true; symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); ui__error("Couldn't annotate %s:\n%s", sym->name, msg); goto out_free_offsets; diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 572ff38ceb0f..9f9f622325ae 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2487,7 +2487,7 @@ static struct symbol *symbol__new_unresolved(u64 addr, struct map *map) return NULL; } - dso__insert_symbol(map->dso, sym); + dso__insert_symbol(map__dso(map), sym); } return sym; @@ -2499,7 +2499,9 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused, struct map_symbol *ms, u64 addr) { - if (!ms->map || !ms->map->dso || ms->map->dso->annotate_warned) + struct dso *dso = map__dso(ms->map); + + if (!ms->map || !dso || dso->annotate_warned) return 0; if (!ms->sym) @@ -2589,9 +2591,10 @@ static int hists_browser__zoom_map(struct hist_browser *browser, struct map *map browser->hists->dso_filter = NULL; ui_helpline__pop(); } else { + struct dso *dso = map__dso(map); ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s DSO\"", - __map__is_kernel(map) ? "the Kernel" : map->dso->short_name); - browser->hists->dso_filter = map->dso; + __map__is_kernel(map) ? "the Kernel" : dso->short_name); + browser->hists->dso_filter = dso; perf_hpp__set_elide(HISTC_DSO, true); pstack__push(browser->pstack, &browser->hists->dso_filter); } @@ -2616,7 +2619,7 @@ add_dso_opt(struct hist_browser *browser, struct popup_action *act, if (asprintf(optstr, "Zoom %s %s DSO (use the 'k' hotkey to zoom directly into the kernel)", browser->hists->dso_filter ? "out of" : "into", - __map__is_kernel(map) ? "the Kernel" : map->dso->short_name) < 0) + __map__is_kernel(map) ? "the Kernel" : map__dso(map)->short_name) < 0) return 0; act->ms.map = map; @@ -3091,8 +3094,8 @@ static int evsel__hists_browse(struct evsel *evsel, int nr_events, const char *h if (!browser->selection || !browser->selection->map || - !browser->selection->map->dso || - browser->selection->map->dso->annotate_warned) { + !map__dso(browser->selection->map) || + map__dso(browser->selection->map)->annotate_warned) { continue; } diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c index 3d49b916c9e4..3d1b958d8832 100644 --- a/tools/perf/ui/browsers/map.c +++ b/tools/perf/ui/browsers/map.c @@ -76,7 +76,7 @@ static int map_browser__run(struct map_browser *browser) { int key; - if (ui_browser__show(&browser->b, browser->map->dso->long_name, + if (ui_browser__show(&browser->b, map__dso(browser->map)->long_name, "Press ESC to exit, %s / to search", verbose > 0 ? "" : "restart with -v to use") < 0) return -1; @@ -106,7 +106,7 @@ int map__browse(struct map *map) { struct map_browser mb = { .b = { - .entries = &map->dso->symbols, + .entries = &map__dso(map)->symbols, .refresh = ui_browser__rb_tree_refresh, .seek = ui_browser__rb_tree_seek, .write = map_browser__write, diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c index a1c021a6d3c1..2effac77ca8c 100644 --- a/tools/perf/ui/gtk/annotate.c +++ b/tools/perf/ui/gtk/annotate.c @@ -165,6 +165,7 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *options, struct hist_browser_timer *hbt) { + struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; GtkWidget *window; GtkWidget *notebook; @@ -172,13 +173,13 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel, GtkWidget *tab_label; int err; - if (ms->map->dso->annotate_warned) + if (dso->annotate_warned) return -1; err = symbol__annotate(ms, evsel, options, NULL); if (err) { char msg[BUFSIZ]; - ms->map->dso->annotate_warned = true; + dso->annotate_warned = true; symbol__strerror_disassemble(ms, err, msg, sizeof(msg)); ui__error("Couldn't annotate %s: %s\n", sym->name, msg); return -1; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index f47b5dde66bc..84100ca5f306 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1585,7 +1585,7 @@ static void delete_last_nop(struct symbol *sym) int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen) { - struct dso *dso = ms->map->dso; + struct dso *dso = map__dso(ms->map); BUG_ON(buflen == 0); @@ -1727,7 +1727,7 @@ static int symbol__disassemble_bpf(struct symbol *sym, struct map *map = args->ms.map; struct perf_bpil *info_linear; struct disassemble_info info; - struct dso *dso = map->dso; + struct dso *dso = map__dso(map); int pc = 0, count, sub_id; struct btf *btf = NULL; char tpath[PATH_MAX]; @@ -1950,7 +1950,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *opts = args->options; struct map *map = args->ms.map; - struct dso *dso = map->dso; + struct dso *dso = map__dso(map); char *command; FILE *file; char symfs_filename[PATH_MAX]; @@ -2395,7 +2395,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel, { struct map *map = ms->map; struct symbol *sym = ms->sym; - struct dso *dso = map->dso; + struct dso *dso = map__dso(map); char *filename; const char *d_filename; const char *evsel_name = evsel__name(evsel); @@ -2578,7 +2578,7 @@ int map_symbol__annotation_dump(struct map_symbol *ms, struct evsel *evsel, } fprintf(fp, "%s() %s\nEvent: %s\n\n", - ms->sym->name, ms->map->dso->long_name, ev_name); + ms->sym->name, map__dso(ms->map)->long_name, ev_name); symbol__annotate_fprintf2(ms->sym, fp, opts); fclose(fp); @@ -2804,7 +2804,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map, if (percent_max <= 0.5) continue; - al->path = get_srcline(map->dso, notes->start + al->offset, NULL, + al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL, false, true, notes->start + al->offset); insert_source_line(&tmp_root, al, opts); } @@ -2823,7 +2823,7 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root, int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = ms->map->dso; + struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; struct hists *hists = evsel__hists(evsel); @@ -2859,7 +2859,7 @@ int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel, int symbol__tty_annotate(struct map_symbol *ms, struct evsel *evsel, struct annotation_options *opts) { - struct dso *dso = ms->map->dso; + struct dso *dso = map__dso(ms->map); struct symbol *sym = ms->sym; struct rb_root source_line = RB_ROOT; int err; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index b2a5e5397bad..a0368202a746 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2560,7 +2560,7 @@ static struct dso *load_dso(const char *name) if (map__load(map) < 0) pr_err("File '%s' not found or has no symbols.\n", name); - dso = dso__get(map->dso); + dso = dso__get(map__dso(map)); map__put(map); diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index 5ecd4f401f32..16a7b4adcf18 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -317,9 +317,9 @@ static int block_dso_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt); struct map *map = he->ms.map; - if (map && map->dso) { + if (map && map__dso(map)) { return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, - map->dso->short_name); + map__dso(map)->short_name); } return scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 025f331b3867..38fcf3ba5749 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -57,10 +57,12 @@ static int machine__process_bpf_event_load(struct machine *machine, struct map *map = maps__find(machine__kernel_maps(machine), addr); if (map) { - map->dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO; - map->dso->bpf_prog.id = id; - map->dso->bpf_prog.sub_id = i; - map->dso->bpf_prog.env = env; + struct dso *dso = map__dso(map); + + dso->binary_type = DSO_BINARY_TYPE__BPF_PROG_INFO; + dso->bpf_prog.id = id; + dso->bpf_prog.sub_id = i; + dso->bpf_prog.env = env; } } return 0; diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index ea9c083ab1e3..06a8cd88cbef 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -59,7 +59,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused, } if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) - al.map->dso->hit = 1; + map__dso(al.map)->hit = 1; thread__put(thread); return 0; diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 0aa979f64565..9e9c39dd9d2b 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -701,8 +701,8 @@ static enum match_result match_chain_strings(const char *left, static enum match_result match_chain_dso_addresses(struct map *left_map, u64 left_ip, struct map *right_map, u64 right_ip) { - struct dso *left_dso = left_map ? left_map->dso : NULL; - struct dso *right_dso = right_map ? right_map->dso : NULL; + struct dso *left_dso = left_map ? map__dso(left_map) : NULL; + struct dso *right_dso = right_map ? map__dso(right_map) : NULL; if (left_dso != right_dso) return left_dso < right_dso ? MATCH_LT : MATCH_GT; @@ -1174,7 +1174,7 @@ char *callchain_list__sym_name(struct callchain_list *cl, if (show_dso) scnprintf(bf + printed, bfsize - printed, " %s", cl->ms.map ? - cl->ms.map->dso->short_name : + map__dso(cl->ms.map)->short_name : "unknown"); return bf; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 94e2d02009eb..528a7fb066cf 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -865,6 +865,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, struct thread *thread; struct machine *machine; struct addr_location al; + struct dso *dso; struct cs_etm_traceid_queue *tidq; if (!etmq) @@ -883,27 +884,29 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, thread = etmq->etm->unknown_thread; } - if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso) + dso = map__dso(al.map); + + if (!thread__find_map(thread, cpumode, address, &al) || !dso) return 0; - if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && - dso__data_status_seen(al.map->dso, DSO_DATA_STATUS_SEEN_ITRACE)) + if (dso->data.status == DSO_DATA_STATUS_ERROR && + dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) return 0; offset = al.map->map_ip(al.map, address); map__load(al.map); - len = dso__data_read_offset(al.map->dso, machine, offset, buffer, size); + len = dso__data_read_offset(dso, machine, offset, buffer, size); if (len <= 0) { ui__warning_once("CS ETM Trace: Missing DSO. Use 'perf archive' or debuginfod to export data from the traced system.\n" " Enable CONFIG_PROC_KCORE or use option '-k /path/to/vmlinux' for kernel symbols.\n"); - if (!al.map->dso->auxtrace_warned) { + if (!dso->auxtrace_warned) { pr_err("CS ETM Trace: Debug data not found for address %#"PRIx64" in %s\n", address, - al.map->dso->long_name ? al.map->dso->long_name : "Unknown"); - al.map->dso->auxtrace_warned = true; + dso->long_name ? dso->long_name : "Unknown"); + dso->auxtrace_warned = true; } return 0; } diff --git a/tools/perf/util/data-convert-json.c b/tools/perf/util/data-convert-json.c index ba9d93ce9463..653709ab867a 100644 --- a/tools/perf/util/data-convert-json.c +++ b/tools/perf/util/data-convert-json.c @@ -128,15 +128,17 @@ static void output_sample_callchain_entry(struct perf_tool *tool, output_json_key_format(out, false, 5, "ip", "\"0x%" PRIx64 "\"", ip); if (al && al->sym && al->sym->namelen) { + struct dso *dso = al->map ? map__dso(al->map) : NULL; + fputc(',', out); output_json_key_string(out, false, 5, "symbol", al->sym->name); - if (al->map && al->map->dso) { - const char *dso = al->map->dso->short_name; + if (dso) { + const char *dso_name = dso->short_name; - if (dso && strlen(dso) > 0) { + if (dso_name && strlen(dso_name) > 0) { fputc(',', out); - output_json_key_string(out, false, 5, "dso", dso); + output_json_key_string(out, false, 5, "dso", dso_name); } } } diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c index 1cfcfdd3cf52..84c970c11794 100644 --- a/tools/perf/util/db-export.c +++ b/tools/perf/util/db-export.c @@ -179,7 +179,7 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al, int err; if (al->map) { - struct dso *dso = al->map->dso; + struct dso *dso = map__dso(al->map); err = db_export__dso(dbe, dso, maps__machine(al->maps)); if (err) @@ -255,7 +255,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe, al.addr = node->ip; if (al.map && !al.sym) - al.sym = dso__find_symbol(al.map->dso, al.addr); + al.sym = dso__find_symbol(map__dso(al.map), al.addr); db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset); diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index fe2a0752a0f6..8a7ffe0d805a 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -29,7 +29,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al) d_al->size = sizeof(*d_al); if (al->map) { - struct dso *dso = al->map->dso; + struct dso *dso = map__dso(al->map); if (symbol_conf.show_kernel_path && dso->long_name) d_al->dso = dso->long_name; @@ -220,6 +220,7 @@ static const char *dlfilter__srcline(void *ctx, __u32 *line_no) unsigned int line = 0; char *srcfile = NULL; struct map *map; + struct dso *dso; u64 addr; if (!d->ctx_valid || !line_no) @@ -231,9 +232,10 @@ static const char *dlfilter__srcline(void *ctx, __u32 *line_no) map = al->map; addr = al->addr; + dso = map ? map__dso(map) : NULL; - if (map && map->dso) - srcfile = get_srcline_split(map->dso, map__rip_2objdump(map, addr), &line); + if (dso) + srcfile = get_srcline_split(dso, map__rip_2objdump(map, addr), &line); *line_no = line; return srcfile; @@ -279,7 +281,7 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) offset = map->map_ip(map, ip); if (ip + len >= map->end) len = map->end - ip; - return dso__data_read_offset(map->dso, d->machine, offset, buf, len); + return dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); } static const struct perf_dlfilter_fns perf_dlfilter_fns = { diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index f40cdd6ac126..2ddc75dee019 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -685,6 +685,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, struct perf_sample *sample) { struct thread *thread; + struct dso *dso; if (symbol_conf.guest_code && !machine__is_host(machine)) thread = machine__findnew_guest_code(machine, sample->pid); @@ -695,9 +696,11 @@ int machine__resolve(struct machine *machine, struct addr_location *al, dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid); thread__find_map(thread, sample->cpumode, sample->ip, al); + dso = al->map ? map__dso(al->map) : NULL; dump_printf(" ...... dso: %s\n", - al->map ? al->map->dso->long_name : - al->level == 'H' ? "[hypervisor]" : ""); + dso + ? dso->long_name + : (al->level == 'H' ? "[hypervisor]" : "")); if (thread__is_filtered(thread)) al->filtered |= (1 << HIST_FILTER__THREAD); @@ -715,8 +718,6 @@ int machine__resolve(struct machine *machine, struct addr_location *al, } if (al->map) { - struct dso *dso = al->map->dso; - if (symbol_conf.dso_list && (!dso || !(strlist__has_entry(symbol_conf.dso_list, dso->short_name) || diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index bd22c4932d10..dff5d8c4b06d 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -155,7 +155,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (print_ip) { /* Show binary offset for userspace addr */ - if (map && !map->dso->kernel) + if (map && !map__dso(map)->kernel) printed += fprintf(fp, "%c%16" PRIx64, s, addr); else printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 5f9f38ed5da1..e494425cad06 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -106,7 +106,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__set_col_len(hists, HISTC_THREAD, len + 8); if (h->ms.map) { - len = dso__name_len(h->ms.map->dso); + len = dso__name_len(map__dso(h->ms.map)); hists__new_col_len(hists, HISTC_DSO, len); } @@ -120,7 +120,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_FROM, symlen); - symlen = dso__name_len(h->branch_info->from.ms.map->dso); + symlen = dso__name_len(map__dso(h->branch_info->from.ms.map)); hists__new_col_len(hists, HISTC_DSO_FROM, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -135,7 +135,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) symlen += BITS_PER_LONG / 4 + 2 + 3; hists__new_col_len(hists, HISTC_SYMBOL_TO, symlen); - symlen = dso__name_len(h->branch_info->to.ms.map->dso); + symlen = dso__name_len(map__dso(h->branch_info->to.ms.map)); hists__new_col_len(hists, HISTC_DSO_TO, symlen); } else { symlen = unresolved_col_width + 4 + 2; @@ -180,7 +180,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) } if (h->mem_info->daddr.ms.map) { - symlen = dso__name_len(h->mem_info->daddr.ms.map->dso); + symlen = dso__name_len(map__dso(h->mem_info->daddr.ms.map)); hists__new_col_len(hists, HISTC_MEM_DADDR_DSO, symlen); } else { @@ -2110,7 +2110,7 @@ static bool hists__filter_entry_by_dso(struct hists *hists, struct hist_entry *he) { if (hists->dso_filter != NULL && - (he->ms.map == NULL || he->ms.map->dso != hists->dso_filter)) { + (he->ms.map == NULL || map__dso(he->ms.map) != hists->dso_filter)) { he->filtered |= (1 << HIST_FILTER__DSO); return true; } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 955c1b9dc6a4..8cec88e09792 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -801,17 +801,19 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, } while (1) { - if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso) { + struct dso *dso; + + if (!thread__find_map(thread, cpumode, *ip, &al) || !map__dso(al.map)) { if (al.map) intel_pt_log("ERROR: thread has no dso for %#" PRIx64 "\n", *ip); else intel_pt_log("ERROR: thread has no map for %#" PRIx64 "\n", *ip); return -EINVAL; } + dso = map__dso(al.map); - if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR && - dso__data_status_seen(al.map->dso, - DSO_DATA_STATUS_SEEN_ITRACE)) + if (dso->data.status == DSO_DATA_STATUS_ERROR && + dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) return -ENOENT; offset = al.map->map_ip(al.map, *ip); @@ -819,7 +821,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, if (!to_ip && one_map) { struct intel_pt_cache_entry *e; - e = intel_pt_cache_lookup(al.map->dso, machine, offset); + e = intel_pt_cache_lookup(dso, machine, offset); if (e && (!max_insn_cnt || e->insn_cnt <= max_insn_cnt)) { *insn_cnt_ptr = e->insn_cnt; @@ -829,8 +831,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, intel_pt_insn->emulated_ptwrite = e->emulated_ptwrite; intel_pt_insn->length = e->length; intel_pt_insn->rel = e->rel; - memcpy(intel_pt_insn->buf, e->insn, - INTEL_PT_INSN_BUF_SZ); + memcpy(intel_pt_insn->buf, e->insn, INTEL_PT_INSN_BUF_SZ); intel_pt_log_insn_no_data(intel_pt_insn, *ip); return 0; } @@ -842,17 +843,17 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, /* Load maps to ensure dso->is_64_bit has been updated */ map__load(al.map); - x86_64 = al.map->dso->is_64_bit; + x86_64 = dso->is_64_bit; while (1) { - len = dso__data_read_offset(al.map->dso, machine, + len = dso__data_read_offset(dso, machine, offset, buf, INTEL_PT_INSN_BUF_SZ); if (len <= 0) { intel_pt_log("ERROR: failed to read at offset %#" PRIx64 " ", offset); if (intel_pt_enable_logging) - dso__fprintf(al.map->dso, intel_pt_log_fp()); + dso__fprintf(dso, intel_pt_log_fp()); return -EINVAL; } @@ -871,7 +872,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, goto out; /* Check for emulated ptwrite */ offs = offset + intel_pt_insn->length; - eptw = intel_pt_emulated_ptwrite(al.map->dso, machine, offs); + eptw = intel_pt_emulated_ptwrite(dso, machine, offs); intel_pt_insn->emulated_ptwrite = eptw; goto out; } @@ -906,13 +907,13 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, if (to_ip) { struct intel_pt_cache_entry *e; - e = intel_pt_cache_lookup(al.map->dso, machine, start_offset); + e = intel_pt_cache_lookup(map__dso(al.map), machine, start_offset); if (e) return 0; } /* Ignore cache errors */ - intel_pt_cache_add(al.map->dso, machine, start_offset, insn_cnt, + intel_pt_cache_add(map__dso(al.map), machine, start_offset, insn_cnt, *ip - start_ip, intel_pt_insn); return 0; @@ -983,13 +984,12 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread) return -EINVAL; - if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso) + if (!thread__find_map(thread, cpumode, ip, &al) || !map__dso(al.map)) return -EINVAL; offset = al.map->map_ip(al.map, ip); - return intel_pt_match_pgd_ip(ptq->pt, ip, offset, - al.map->dso->long_name); + return intel_pt_match_pgd_ip(ptq->pt, ip, offset, map__dso(al.map)->long_name); } static bool intel_pt_pgd_ip(uint64_t ip, void *data) @@ -2744,7 +2744,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) if (map__load(map)) return 0; - start = dso__first_symbol(map->dso); + start = dso__first_symbol(map__dso(map)); for (sym = start; sym; sym = dso__next_symbol(sym)) { if (sym->binding == STB_GLOBAL && @@ -3381,18 +3381,21 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) return 0; for (; cnt; cnt--, addr--) { + struct dso *dso; + if (intel_pt_find_map(thread, cpumode, addr, &al)) { if (addr < event->text_poke.addr) return 0; continue; } - if (!al.map->dso || !al.map->dso->auxtrace_cache) + dso = map__dso(al.map); + if (!dso || !dso->auxtrace_cache) continue; offset = al.map->map_ip(al.map, addr); - e = intel_pt_cache_lookup(al.map->dso, machine, offset); + e = intel_pt_cache_lookup(dso, machine, offset); if (!e) continue; @@ -3405,9 +3408,9 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) if (e->branch != INTEL_PT_BR_NO_BRANCH) return 0; } else { - intel_pt_cache_invalidate(al.map->dso, machine, offset); + intel_pt_cache_invalidate(dso, machine, offset); intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n", - al.map->dso->long_name, addr); + dso->long_name, addr); } } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index d6da4b5e1333..8bae38c96788 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -48,7 +48,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms static struct dso *machine__kernel_dso(struct machine *machine) { - return machine->vmlinux_map->dso; + return map__dso(machine->vmlinux_map); } static void dsos__init(struct dsos *dsos) @@ -879,12 +879,13 @@ static int machine__process_ksymbol_register(struct machine *machine, struct perf_sample *sample __maybe_unused) { struct symbol *sym; + struct dso *dso; struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr); if (!map) { - struct dso *dso = dso__new(event->ksymbol.name); int err; + dso = dso__new(event->ksymbol.name); if (dso) { dso->kernel = DSO_SPACE__KERNEL; map = map__new2(0, dso); @@ -896,9 +897,9 @@ static int machine__process_ksymbol_register(struct machine *machine, } if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) { - map->dso->binary_type = DSO_BINARY_TYPE__OOL; - map->dso->data.file_size = event->ksymbol.len; - dso__set_loaded(map->dso); + dso->binary_type = DSO_BINARY_TYPE__OOL; + dso->data.file_size = event->ksymbol.len; + dso__set_loaded(dso); } map->start = event->ksymbol.addr; @@ -914,6 +915,8 @@ static int machine__process_ksymbol_register(struct machine *machine, dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE; dso__set_long_name(dso, "", false); } + } else { + dso = map__dso(map); } sym = symbol__new(map->map_ip(map, map->start), @@ -921,7 +924,7 @@ static int machine__process_ksymbol_register(struct machine *machine, 0, 0, event->ksymbol.name); if (!sym) return -ENOMEM; - dso__insert_symbol(map->dso, sym); + dso__insert_symbol(dso, sym); return 0; } @@ -939,9 +942,11 @@ static int machine__process_ksymbol_unregister(struct machine *machine, if (map != machine->vmlinux_map) maps__remove(machine__kernel_maps(machine), map); else { - sym = dso__find_symbol(map->dso, map->map_ip(map, map->start)); + struct dso *dso = map__dso(map); + + sym = dso__find_symbol(dso, map->map_ip(map, map->start)); if (sym) - dso__delete_symbol(map->dso, sym); + dso__delete_symbol(dso, sym); } return 0; @@ -965,6 +970,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event, { struct map *map = maps__find(machine__kernel_maps(machine), event->text_poke.addr); u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + struct dso *dso = map ? map__dso(map) : NULL; if (dump_trace) perf_event__fprintf_text_poke(event, machine, stdout); @@ -977,7 +983,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event, return 0; } - if (map && map->dso) { + if (dso) { u8 *new_bytes = event->text_poke.bytes + event->text_poke.old_len; int ret; @@ -986,7 +992,7 @@ int machine__process_text_poke(struct machine *machine, union perf_event *event, * must be done prior to using kernel maps. */ map__load(map); - ret = dso__data_write_cache_addr(map->dso, map, machine, + ret = dso__data_write_cache_addr(dso, map, machine, event->text_poke.addr, new_bytes, event->text_poke.new_len); @@ -1422,10 +1428,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid) int machine__load_kallsyms(struct machine *machine, const char *filename) { struct map *map = machine__kernel_map(machine); - int ret = __dso__load_kallsyms(map->dso, filename, map, true); + struct dso *dso = map__dso(map); + int ret = __dso__load_kallsyms(dso, filename, map, true); if (ret > 0) { - dso__set_loaded(map->dso); + dso__set_loaded(dso); /* * Since /proc/kallsyms will have multiple sessions for the * kernel, with modules between them, fixup the end of all @@ -1440,10 +1447,11 @@ int machine__load_kallsyms(struct machine *machine, const char *filename) int machine__load_vmlinux_path(struct machine *machine) { struct map *map = machine__kernel_map(machine); - int ret = dso__load_vmlinux_path(map->dso, map); + struct dso *dso = map__dso(map); + int ret = dso__load_vmlinux_path(dso, map); if (ret > 0) - dso__set_loaded(map->dso); + dso__set_loaded(dso); return ret; } @@ -1485,6 +1493,7 @@ static bool is_kmod_dso(struct dso *dso) static int maps__set_module_path(struct maps *maps, const char *path, struct kmod_path *m) { char *long_name; + struct dso *dso; struct map *map = maps__find_by_name(maps, m->name); if (map == NULL) @@ -1494,16 +1503,17 @@ static int maps__set_module_path(struct maps *maps, const char *path, struct kmo if (long_name == NULL) return -ENOMEM; - dso__set_long_name(map->dso, long_name, true); - dso__kernel_module_get_build_id(map->dso, ""); + dso = map__dso(map); + dso__set_long_name(dso, long_name, true); + dso__kernel_module_get_build_id(dso, ""); /* * Full name could reveal us kmod compression, so * we need to update the symtab_type if needed. */ - if (m->comp && is_kmod_dso(map->dso)) { - map->dso->symtab_type++; - map->dso->comp = m->comp; + if (m->comp && is_kmod_dso(dso)) { + dso->symtab_type++; + dso->comp = m->comp; } return 0; @@ -1602,7 +1612,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, return -1; map->end = start + size; - dso__kernel_module_get_build_id(map->dso, machine->root_dir); + dso__kernel_module_get_build_id(map__dso(map), machine->root_dir); return 0; } @@ -1788,7 +1798,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, map->end = map->start + xm->end - xm->start; if (build_id__is_defined(bid)) - dso__set_build_id(map->dso, bid); + dso__set_build_id(map__dso(map), bid); } else if (is_kernel_mmap) { const char *symbol_name = xm->name + strlen(mmap_name); @@ -2248,18 +2258,20 @@ static char *callchain_srcline(struct map_symbol *ms, u64 ip) { struct map *map = ms->map; char *srcline = NULL; + struct dso *dso; if (!map || callchain_param.key == CCKEY_FUNCTION) return srcline; - srcline = srcline__tree_find(&map->dso->srclines, ip); + dso = map__dso(map); + srcline = srcline__tree_find(&dso->srclines, ip); if (!srcline) { bool show_sym = false; bool show_addr = callchain_param.key == CCKEY_ADDRESS; - srcline = get_srcline(map->dso, map__rip_2objdump(map, ip), + srcline = get_srcline(dso, map__rip_2objdump(map, ip), ms->sym, show_sym, show_addr, ip); - srcline__tree_insert(&map->dso->srclines, ip, srcline); + srcline__tree_insert(&dso->srclines, ip, srcline); } return srcline; @@ -3039,6 +3051,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms struct map *map = ms->map; struct inline_node *inline_node; struct inline_list *ilist; + struct dso *dso; u64 addr; int ret = 1; @@ -3047,13 +3060,14 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms addr = map__map_ip(map, ip); addr = map__rip_2objdump(map, addr); + dso = map__dso(map); - inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr); + inline_node = inlines__tree_find(&dso->inlined_nodes, addr); if (!inline_node) { - inline_node = dso__parse_addr_inlines(map->dso, addr, sym); + inline_node = dso__parse_addr_inlines(dso, addr, sym); if (!inline_node) return ret; - inlines__tree_insert(&map->dso->inlined_nodes, inline_node); + inlines__tree_insert(&dso->inlined_nodes, inline_node); } list_for_each_entry(ilist, &inline_node->val, list) { @@ -3330,7 +3344,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch if (sym == NULL) return NULL; - *modp = __map__is_kmodule(map) ? (char *)map->dso->short_name : NULL; + *modp = __map__is_kmodule(map) ? (char *)map__dso(map)->short_name : NULL; *addrp = map->unmap_ip(map, sym->start); return sym->name; } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index a99dbde656a2..90062af6675a 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -232,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso) bool __map__is_kernel(const struct map *map) { - if (!map->dso->kernel) + if (!map__dso(map)->kernel) return false; return machine__kernel_map(maps__machine(map__kmaps((struct map *)map))) == map; } @@ -247,8 +247,9 @@ bool __map__is_extra_kernel_map(const struct map *map) bool __map__is_bpf_prog(const struct map *map) { const char *name; + struct dso *dso = map__dso(map); - if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) + if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) return true; /* @@ -256,15 +257,16 @@ bool __map__is_bpf_prog(const struct map *map) * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can * guess the type based on name. */ - name = map->dso->short_name; + name = dso->short_name; return name && (strstr(name, "bpf_prog_") == name); } bool __map__is_bpf_image(const struct map *map) { const char *name; + struct dso *dso = map__dso(map); - if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) + if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) return true; /* @@ -272,18 +274,20 @@ bool __map__is_bpf_image(const struct map *map) * type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can * guess the type based on name. */ - name = map->dso->short_name; + name = dso->short_name; return name && is_bpf_image(name); } bool __map__is_ool(const struct map *map) { - return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL; + const struct dso *dso = map__dso(map); + + return dso && dso->binary_type == DSO_BINARY_TYPE__OOL; } bool map__has_symbols(const struct map *map) { - return dso__has_symbols(map->dso); + return dso__has_symbols(map__dso(map)); } static void map__exit(struct map *map) @@ -306,18 +310,23 @@ void map__put(struct map *map) void map__fixup_start(struct map *map) { - struct rb_root_cached *symbols = &map->dso->symbols; + struct dso *dso = map__dso(map); + struct rb_root_cached *symbols = &dso->symbols; struct rb_node *nd = rb_first_cached(symbols); + if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); + map->start = sym->start; } } void map__fixup_end(struct map *map) { - struct rb_root_cached *symbols = &map->dso->symbols; + struct dso *dso = map__dso(map); + struct rb_root_cached *symbols = &dso->symbols; struct rb_node *nd = rb_last(&symbols->rb_root); + if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); map->end = sym->end; @@ -328,18 +337,19 @@ void map__fixup_end(struct map *map) int map__load(struct map *map) { - const char *name = map->dso->long_name; + struct dso *dso = map__dso(map); + const char *name = dso->long_name; int nr; - if (dso__loaded(map->dso)) + if (dso__loaded(dso)) return 0; - nr = dso__load(map->dso, map); + nr = dso__load(dso, map); if (nr < 0) { - if (map->dso->has_build_id) { + if (dso->has_build_id) { char sbuild_id[SBUILD_ID_SIZE]; - build_id__sprintf(&map->dso->bid, sbuild_id); + build_id__sprintf(&dso->bid, sbuild_id); pr_debug("%s with build id %s not found", name, sbuild_id); } else pr_debug("Failed to open %s", name); @@ -371,32 +381,36 @@ struct symbol *map__find_symbol(struct map *map, u64 addr) if (map__load(map) < 0) return NULL; - return dso__find_symbol(map->dso, addr); + return dso__find_symbol(map__dso(map), addr); } struct symbol *map__find_symbol_by_name(struct map *map, const char *name) { + struct dso *dso; + if (map__load(map) < 0) return NULL; - if (!dso__sorted_by_name(map->dso)) - dso__sort_by_name(map->dso); + dso = map__dso(map); + if (!dso__sorted_by_name(dso)) + dso__sort_by_name(dso); - return dso__find_symbol_by_name(map->dso, name); + return dso__find_symbol_by_name(dso, name); } struct map *map__clone(struct map *from) { size_t size = sizeof(struct map); struct map *map; + struct dso *dso = map__dso(from); - if (from->dso && from->dso->kernel) + if (dso && dso->kernel) size += sizeof(struct kmap); map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); - dso__get(map->dso); + dso__get(dso); } return map; @@ -404,20 +418,23 @@ struct map *map__clone(struct map *from) size_t map__fprintf(struct map *map, FILE *fp) { + const struct dso *dso = map__dso(map); + return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", - map->start, map->end, map->pgoff, map->dso->name); + map->start, map->end, map->pgoff, dso->name); } size_t map__fprintf_dsoname(struct map *map, FILE *fp) { char buf[symbol_conf.pad_output_len_dso + 1]; const char *dsoname = "[unknown]"; + const struct dso *dso = map ? map__dso(map) : NULL; - if (map && map->dso) { - if (symbol_conf.show_kernel_path && map->dso->long_name) - dsoname = map->dso->long_name; + if (dso) { + if (symbol_conf.show_kernel_path && dso->long_name) + dsoname = dso->long_name; else - dsoname = map->dso->name; + dsoname = dso->name; } if (symbol_conf.pad_output_len_dso) { @@ -432,15 +449,17 @@ char *map__srcline(struct map *map, u64 addr, struct symbol *sym) { if (map == NULL) return SRCLINE_UNKNOWN; - return get_srcline(map->dso, map__rip_2objdump(map, addr), sym, true, true, addr); + + return get_srcline(map__dso(map), map__rip_2objdump(map, addr), sym, true, true, addr); } int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix, FILE *fp) { + const struct dso *dso = map ? map__dso(map) : NULL; int ret = 0; - if (map && map->dso) { + if (dso) { char *srcline = map__srcline(map, addr, NULL); if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0) ret = fprintf(fp, "%s%s", prefix, srcline); @@ -469,6 +488,7 @@ void srccode_state_free(struct srccode_state *state) u64 map__rip_2objdump(struct map *map, u64 rip) { struct kmap *kmap = __map__kmap(map); + const struct dso *dso = map__dso(map); /* * vmlinux does not have program headers for PTI entry trampolines and @@ -486,18 +506,18 @@ u64 map__rip_2objdump(struct map *map, u64 rip) } } - if (!map->dso->adjust_symbols) + if (!dso->adjust_symbols) return rip; - if (map->dso->rel) + if (dso->rel) return rip - map->pgoff; /* * kernel modules also have DSO_TYPE_USER in dso->kernel, * but all kernel modules are ET_REL, so won't get here. */ - if (map->dso->kernel == DSO_SPACE__USER) - return rip + map->dso->text_offset; + if (dso->kernel == DSO_SPACE__USER) + return rip + dso->text_offset; return map->unmap_ip(map, rip) - map->reloc; } @@ -516,18 +536,20 @@ u64 map__rip_2objdump(struct map *map, u64 rip) */ u64 map__objdump_2mem(struct map *map, u64 ip) { - if (!map->dso->adjust_symbols) + const struct dso *dso = map__dso(map); + + if (!dso->adjust_symbols) return map->unmap_ip(map, ip); - if (map->dso->rel) + if (dso->rel) return map->unmap_ip(map, ip + map->pgoff); /* * kernel modules also have DSO_TYPE_USER in dso->kernel, * but all kernel modules are ET_REL, so won't get here. */ - if (map->dso->kernel == DSO_SPACE__USER) - return map->unmap_ip(map, ip - map->dso->text_offset); + if (dso->kernel == DSO_SPACE__USER) + return map->unmap_ip(map, ip - dso->text_offset); return ip + map->reloc; } @@ -541,7 +563,9 @@ bool map__contains_symbol(const struct map *map, const struct symbol *sym) struct kmap *__map__kmap(struct map *map) { - if (!map->dso || !map->dso->kernel) + const struct dso *dso = map__dso(map); + + if (!dso || !dso->kernel) return NULL; return (struct kmap *)(map + 1); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index d1a6f85fd31d..36c5add0144d 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -47,6 +47,11 @@ u64 map__unmap_ip(const struct map *map, u64 ip); /* Returns ip */ u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip); +static inline struct dso *map__dso(const struct map *map) +{ + return map->dso; +} + static inline size_t map__size(const struct map *map) { return map->end - map->start; @@ -69,7 +74,7 @@ struct thread; * Note: caller must ensure map->dso is not NULL (map is loaded). */ #define map__for_each_symbol(map, pos, n) \ - dso__for_each_symbol(map->dso, pos, n) + dso__for_each_symbol(map__dso(map), pos, n) /* map__for_each_symbol_with_name - iterate over the symbols in the given map * that have the given name diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 91bb015caede..09ec6bbafcbc 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -62,6 +62,7 @@ static int __maps__insert(struct maps *maps, struct map *map) int maps__insert(struct maps *maps, struct map *map) { int err; + const struct dso *dso = map__dso(map); down_write(maps__lock(maps)); err = __maps__insert(maps, map); @@ -70,7 +71,7 @@ int maps__insert(struct maps *maps, struct map *map) ++maps->nr_maps; - if (map->dso && map->dso->kernel) { + if (dso && dso->kernel) { struct kmap *kmap = map__kmap(map); if (kmap) @@ -253,7 +254,7 @@ size_t maps__fprintf(struct maps *maps, FILE *fp) printed += fprintf(fp, "Map:"); printed += map__fprintf(pos->map, fp); if (verbose > 2) { - printed += dso__fprintf(pos->map->dso, fp); + printed += dso__fprintf(map__dso(pos->map), fp); printed += fprintf(fp, "--\n"); } } @@ -307,7 +308,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) if (use_browser) { pr_debug("overlapping maps in %s (disable tui for more info)\n", - map->dso->name); + map__dso(map)->name); } else { fputs("overlapping maps:\n", fp); map__fprintf(map, fp); diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index cdf5d655d84c..b26670a26005 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -165,8 +165,9 @@ static struct map *kernel_get_module_map(const char *module) maps__for_each_entry(maps, pos) { /* short_name is "[module]" */ - const char *short_name = pos->map->dso->short_name; - u16 short_name_len = pos->map->dso->short_name_len; + struct dso *dso = map__dso(pos->map); + const char *short_name = dso->short_name; + u16 short_name_len = dso->short_name_len; if (strncmp(short_name + 1, module, short_name_len - 2) == 0 && @@ -182,13 +183,15 @@ struct map *get_target_map(const char *target, struct nsinfo *nsi, bool user) /* Init maps of given executable or kernel */ if (user) { struct map *map; + struct dso *dso; map = dso__new_map(target); - if (map && map->dso) { - mutex_lock(&map->dso->lock); - nsinfo__put(map->dso->nsinfo); - map->dso->nsinfo = nsinfo__get(nsi); - mutex_unlock(&map->dso->lock); + dso = map ? map__dso(map) : NULL; + if (dso) { + mutex_lock(&dso->lock); + nsinfo__put(dso->nsinfo); + dso->nsinfo = nsinfo__get(nsi); + mutex_unlock(&dso->lock); } return map; } else { @@ -341,7 +344,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) snprintf(module_name, sizeof(module_name), "[%s]", module); map = maps__find_by_name(machine__kernel_maps(host_machine), module_name); if (map) { - dso = map->dso; + dso = map__dso(map); goto found; } pr_debug("Failed to find module %s.\n", module); @@ -349,7 +352,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso) } map = machine__kernel_map(host_machine); - dso = map->dso; + dso = map__dso(map); if (!dso->has_build_id) dso__read_running_kernel_build_id(dso, host_machine); @@ -3737,6 +3740,7 @@ int show_available_funcs(const char *target, struct nsinfo *nsi, { struct rb_node *nd; struct map *map; + struct dso *dso; int ret; ret = init_probe_symbol_maps(user); @@ -3762,14 +3766,14 @@ int show_available_funcs(const char *target, struct nsinfo *nsi, (target) ? : "kernel"); goto end; } - if (!dso__sorted_by_name(map->dso)) - dso__sort_by_name(map->dso); + dso = map__dso(map); + if (!dso__sorted_by_name(dso)) + dso__sort_by_name(dso); /* Show all (filtered) symbols */ setup_pager(); - for (nd = rb_first_cached(&map->dso->symbol_names); nd; - nd = rb_next(nd)) { + for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) { struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node); if (strfilter__compare(_filter, pos->sym.name)) diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c index 83fd2fd0ba16..039d0365ad41 100644 --- a/tools/perf/util/scripting-engines/trace-event-perl.c +++ b/tools/perf/util/scripting-engines/trace-event-perl.c @@ -315,12 +315,14 @@ static SV *perl_process_callchain(struct perf_sample *sample, if (node->ms.map) { struct map *map = node->ms.map; + struct dso *dso = map ? map__dso(map) : NULL; const char *dsoname = "[unknown]"; - if (map && map->dso) { - if (symbol_conf.show_kernel_path && map->dso->long_name) - dsoname = map->dso->long_name; + + if (dso) { + if (symbol_conf.show_kernel_path && dso->long_name) + dsoname = dso->long_name; else - dsoname = map->dso->name; + dsoname = dso->name; } if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) { hv_undef(elem); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index e5cc18f6fcda..b8e5c6f61d80 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -390,12 +390,13 @@ static PyObject *get_field_numeric_entry(struct tep_event *event, static const char *get_dsoname(struct map *map) { const char *dsoname = "[unknown]"; + struct dso *dso = map ? map__dso(map) : NULL; - if (map && map->dso) { - if (symbol_conf.show_kernel_path && map->dso->long_name) - dsoname = map->dso->long_name; + if (dso) { + if (symbol_conf.show_kernel_path && dso->long_name) + dsoname = dso->long_name; else - dsoname = map->dso->name; + dsoname = dso->name; } return dsoname; @@ -780,9 +781,10 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al, char sbuild_id[SBUILD_ID_SIZE]; if (al->map) { - pydict_set_item_string_decref(dict, dso_field, - _PyUnicode_FromString(al->map->dso->name)); - build_id__sprintf(&al->map->dso->bid, sbuild_id); + struct dso *dso = map__dso(al->map); + + pydict_set_item_string_decref(dict, dso_field, _PyUnicode_FromString(dso->name)); + build_id__sprintf(&dso->bid, sbuild_id); pydict_set_item_string_decref(dict, dso_bid_field, _PyUnicode_FromString(sbuild_id)); pydict_set_item_string_decref(dict, dso_map_start, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 430f67e7cc82..f161589aefda 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -230,8 +230,8 @@ struct sort_entry sort_comm = { static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r) { - struct dso *dso_l = map_l ? map_l->dso : NULL; - struct dso *dso_r = map_r ? map_r->dso : NULL; + struct dso *dso_l = map_l ? map__dso(map_l) : NULL; + struct dso *dso_r = map_r ? map__dso(map_r) : NULL; const char *dso_name_l, *dso_name_r; if (!dso_l || !dso_r) @@ -257,13 +257,13 @@ sort__dso_cmp(struct hist_entry *left, struct hist_entry *right) static int _hist_entry__dso_snprintf(struct map *map, char *bf, size_t size, unsigned int width) { - if (map && map->dso) { - const char *dso_name = verbose > 0 ? map->dso->long_name : - map->dso->short_name; - return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); - } + const struct dso *dso = map ? map__dso(map) : NULL; + const char *dso_name = "[unknown]"; + + if (dso) + dso_name = verbose > 0 ? dso->long_name : dso->short_name; - return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]"); + return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name); } static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf, @@ -279,7 +279,7 @@ static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *a if (type != HIST_FILTER__DSO) return -1; - return dso && (!he->ms.map || he->ms.map->dso != dso); + return dso && (!he->ms.map || map__dso(he->ms.map) != dso); } struct sort_entry sort_dso = { @@ -359,11 +359,11 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms, size_t ret = 0; if (verbose > 0) { - char o = map ? dso__symtab_origin(map->dso) : '!'; + struct dso *dso = map ? map__dso(map) : NULL; + char o = dso ? dso__symtab_origin(dso) : '!'; u64 rip = ip; - if (map && map->dso && map->dso->kernel - && map->dso->adjust_symbols) + if (dso && dso->kernel && dso->adjust_symbols) rip = map->unmap_ip(map, ip); ret += repsep_snprintf(bf, size, "%-#*llx %c ", @@ -641,7 +641,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e) if (!map) return no_srcfile; - sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip), + sf = __get_srcline(map__dso(map), map__rip_2objdump(map, e->ip), e->ms.sym, false, true, true, e->ip); if (!strcmp(sf, SRCLINE_UNKNOWN)) return no_srcfile; @@ -982,7 +982,7 @@ static int hist_entry__dso_from_filter(struct hist_entry *he, int type, return -1; return dso && (!he->branch_info || !he->branch_info->from.ms.map || - he->branch_info->from.ms.map->dso != dso); + map__dso(he->branch_info->from.ms.map) != dso); } static int64_t @@ -1014,7 +1014,7 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, return -1; return dso && (!he->branch_info || !he->branch_info->to.ms.map || - he->branch_info->to.ms.map->dso != dso); + map__dso(he->branch_info->to.ms.map) != dso); } static int64_t @@ -1506,6 +1506,7 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) { u64 l, r; struct map *l_map, *r_map; + struct dso *l_dso, *r_dso; int rc; if (!left->mem_info) return -1; @@ -1525,7 +1526,9 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) if (!l_map) return -1; if (!r_map) return 1; - rc = dso__cmp_id(l_map->dso, r_map->dso); + l_dso = map__dso(l_map); + r_dso = map__dso(r_map); + rc = dso__cmp_id(l_dso, r_dso); if (rc) return rc; /* @@ -1537,9 +1540,8 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) */ if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && - (!(l_map->flags & MAP_SHARED)) && - !l_map->dso->id.maj && !l_map->dso->id.min && - !l_map->dso->id.ino && !l_map->dso->id.ino_generation) { + (!(l_map->flags & MAP_SHARED)) && !l_dso->id.maj && !l_dso->id.min && + !l_dso->id.ino && !l_dso->id.ino_generation) { /* userspace anonymous */ if (left->thread->pid_ > right->thread->pid_) return -1; @@ -1567,6 +1569,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if (he->mem_info) { struct map *map = he->mem_info->daddr.ms.map; + struct dso *dso = map__dso(map); addr = cl_address(he->mem_info->daddr.al_addr, chk_double_cl); ms = &he->mem_info->daddr.ms; @@ -1575,8 +1578,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && map && !(map->prot & PROT_EXEC) && (map->flags & MAP_SHARED) && - (map->dso->id.maj || map->dso->id.min || - map->dso->id.ino || map->dso->id.ino_generation)) + (dso->id.maj || dso->id.min || dso->id.ino || dso->id.ino_generation)) level = 's'; else if (!map) level = 'X'; @@ -2072,9 +2074,8 @@ sort__dso_size_cmp(struct hist_entry *left, struct hist_entry *right) static int _hist_entry__dso_size_snprintf(struct map *map, char *bf, size_t bf_size, unsigned int width) { - if (map && map->dso) - return repsep_snprintf(bf, bf_size, "%*d", width, - map__size(map)); + if (map && map__dso(map)) + return repsep_snprintf(bf, bf_size, "%*d", width, map__size(map)); return repsep_snprintf(bf, bf_size, "%*s", width, "unknown"); } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 3084e556d3eb..561372869792 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1435,7 +1435,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, *curr_mapp = curr_map; *curr_dsop = curr_dso; } else - *curr_dsop = curr_map->dso; + *curr_dsop = map__dso(curr_map); return 0; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 316b63fb5691..a1c85c22676f 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -791,6 +791,7 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) *root = RB_ROOT_CACHED; while (next) { + struct dso *curr_map_dso; char *module; pos = rb_entry(next, struct symbol, rb_node); @@ -808,13 +809,13 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) symbol__delete(pos); continue; } - + curr_map_dso = map__dso(curr_map); pos->start -= curr_map->start - curr_map->pgoff; if (pos->end > curr_map->end) pos->end = curr_map->end; if (pos->end) pos->end -= curr_map->start - curr_map->pgoff; - symbols__insert(&curr_map->dso->symbols, pos); + symbols__insert(&curr_map_dso->symbols, pos); ++count; } @@ -856,12 +857,14 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, module = strchr(pos->name, '\t'); if (module) { + struct dso *curr_map_dso; + if (!symbol_conf.use_modules) goto discard_symbol; *module++ = '\0'; - - if (strcmp(curr_map->dso->short_name, module)) { + curr_map_dso = map__dso(curr_map); + if (strcmp(curr_map_dso->short_name, module)) { if (curr_map != initial_map && dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(machine)) { @@ -872,7 +875,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, * symbols are in its kmap. Mark it as * loaded. */ - dso__set_loaded(curr_map->dso); + dso__set_loaded(curr_map_dso); } curr_map = maps__find_by_name(kmaps, module); @@ -884,8 +887,8 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, curr_map = initial_map; goto discard_symbol; } - - if (curr_map->dso->loaded && + curr_map_dso = map__dso(curr_map); + if (curr_map_dso->loaded && !machine__is_default_guest(machine)) goto discard_symbol; } @@ -954,8 +957,10 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, } add_symbol: if (curr_map != initial_map) { + struct dso *curr_map_dso = map__dso(curr_map); + rb_erase_cached(&pos->rb_node, root); - symbols__insert(&curr_map->dso->symbols, pos); + symbols__insert(&curr_map_dso->symbols, pos); ++moved; } else ++count; @@ -969,7 +974,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, if (curr_map != initial_map && dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(maps__machine(kmaps))) { - dso__set_loaded(curr_map->dso); + dso__set_loaded(map__dso(curr_map)); } return count + moved; @@ -1143,13 +1148,14 @@ static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) maps__for_each_entry(kmaps, old_node) { struct map *old_map = old_node->map; struct module_info *mi; + struct dso *dso; if (!__map__is_kmodule(old_map)) { continue; } - + dso = map__dso(old_map); /* Module must be in memory at the same address */ - mi = find_module(old_map->dso->short_name, &modules); + mi = find_module(dso->short_name, &modules); if (!mi || mi->start != old_map->start) { err = -EINVAL; goto out; @@ -2047,14 +2053,17 @@ int dso__load(struct dso *dso, struct map *map) static int map__strcmp(const void *a, const void *b) { - const struct map *ma = *(const struct map **)a, *mb = *(const struct map **)b; - return strcmp(ma->dso->short_name, mb->dso->short_name); + const struct dso *dso_a = map__dso(*(const struct map **)a); + const struct dso *dso_b = map__dso(*(const struct map **)b); + + return strcmp(dso_a->short_name, dso_b->short_name); } static int map__strcmp_name(const void *name, const void *b) { - const struct map *map = *(const struct map **)b; - return strcmp(name, map->dso->short_name); + const struct dso *dso = map__dso(*(const struct map **)b); + + return strcmp(name, dso->short_name); } void __maps__sort_by_name(struct maps *maps) @@ -2111,10 +2120,13 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) down_read(maps__lock(maps)); - if (maps->last_search_by_name && - strcmp(maps->last_search_by_name->dso->short_name, name) == 0) { - map = maps->last_search_by_name; - goto out_unlock; + if (maps->last_search_by_name) { + const struct dso *dso = map__dso(maps->last_search_by_name); + + if (strcmp(dso->short_name, name) == 0) { + map = maps->last_search_by_name; + goto out_unlock; + } } /* * If we have maps->maps_by_name, then the name isn't in the rbtree, @@ -2127,8 +2139,11 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) /* Fallback to traversing the rbtree... */ maps__for_each_entry(maps, rb_node) { + struct dso *dso; + map = rb_node->map; - if (strcmp(map->dso->short_name, name) == 0) { + dso = map__dso(map); + if (strcmp(dso->short_name, name) == 0) { maps->last_search_by_name = map; goto out_unlock; } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 57b95c1d7e39..fbd1a882b013 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -693,12 +693,14 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t maps__for_each_entry(maps, pos) { struct map *map = pos->map; + struct dso *dso; if (!__map__is_kmodule(map)) continue; + dso = map__dso(map); if (symbol_conf.buildid_mmap2) { - size = PERF_ALIGN(map->dso->long_name_len + 1, sizeof(u64)); + size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); event->mmap2.header.type = PERF_RECORD_MMAP2; event->mmap2.header.size = (sizeof(event->mmap2) - (sizeof(event->mmap2.filename) - size)); @@ -708,12 +710,11 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t event->mmap2.len = map->end - map->start; event->mmap2.pid = machine->pid; - memcpy(event->mmap2.filename, map->dso->long_name, - map->dso->long_name_len + 1); + memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1); perf_record_mmap2__read_build_id(&event->mmap2, machine, false); } else { - size = PERF_ALIGN(map->dso->long_name_len + 1, sizeof(u64)); + size = PERF_ALIGN(dso->long_name_len + 1, sizeof(u64)); event->mmap.header.type = PERF_RECORD_MMAP; event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size)); @@ -723,8 +724,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t event->mmap.len = map->end - map->start; event->mmap.pid = machine->pid; - memcpy(event->mmap.filename, map->dso->long_name, - map->dso->long_name_len + 1); + memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1); } if (perf_tool__process_synth_event(tool, event, machine, process) != 0) { diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 292585a52281..bb7a2ce82d46 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -448,23 +448,27 @@ struct thread *thread__main_thread(struct machine *machine, struct thread *threa int thread__memcpy(struct thread *thread, struct machine *machine, void *buf, u64 ip, int len, bool *is64bit) { - u8 cpumode = PERF_RECORD_MISC_USER; - struct addr_location al; - long offset; + u8 cpumode = PERF_RECORD_MISC_USER; + struct addr_location al; + struct dso *dso; + long offset; - if (machine__kernel_ip(machine, ip)) - cpumode = PERF_RECORD_MISC_KERNEL; + if (machine__kernel_ip(machine, ip)) + cpumode = PERF_RECORD_MISC_KERNEL; - if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso || - al.map->dso->data.status == DSO_DATA_STATUS_ERROR || - map__load(al.map) < 0) - return -1; + if (!thread__find_map(thread, cpumode, ip, &al)) + return -1; - offset = al.map->map_ip(al.map, ip); - if (is64bit) - *is64bit = al.map->dso->is_64_bit; + dso = map__dso(al.map); - return dso__data_read_offset(al.map->dso, machine, offset, buf, len); + if( !dso || dso->data.status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) + return -1; + + offset = al.map->map_ip(al.map, ip); + if (is64bit) + *is64bit = dso->is_64_bit; + + return dso__data_read_offset(dso, machine, offset, buf, len); } void thread__free_stitch_list(struct thread *thread) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 94aa40f6e348..c8cba9d4bfd9 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -52,7 +52,7 @@ static int __report_module(struct addr_location *al, u64 ip, thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al); if (al->map) - dso = al->map->dso; + dso = map__dso(al->map); if (!dso) return 0; @@ -134,17 +134,17 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, { struct addr_location al; ssize_t size; + struct dso *dso; if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } - - if (!al.map->dso) + dso = map__dso(al.map); + if (!dso) return -1; - size = dso__data_read_addr(al.map->dso, al.map, ui->machine, - addr, (u8 *) data, sizeof(*data)); + size = dso__data_read_addr(dso, al.map, ui->machine, addr, (u8 *) data, sizeof(*data)); return !(size == sizeof(*data)); } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index c487a249b33c..108f7b1697a7 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -328,7 +328,7 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, maps__for_each_entry(ui->thread->maps, map_node) { struct map *map = map_node->map; - if (map->dso == dso && map->start < base_addr) + if (map__dso(map) == dso && map->start < base_addr) base_addr = map->start; } base_addr -= dso->data.elf_base_addr; @@ -424,19 +424,23 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, { struct unwind_info *ui = arg; struct map *map; + struct dso *dso; unw_dyn_info_t di; u64 table_data, segbase, fde_count; int ret = -EINVAL; map = find_map(ip, ui); - if (!map || !map->dso) + if (!map) return -EINVAL; - pr_debug("unwind: find_proc_info dso %s\n", map->dso->name); + dso = map__dso(map); + if (!dso) + return -EINVAL; + + pr_debug("unwind: find_proc_info dso %s\n", dso->name); /* Check the .eh_frame section for unwinding info */ - if (!read_unwind_spec_eh_frame(map->dso, ui, - &table_data, &segbase, &fde_count)) { + if (!read_unwind_spec_eh_frame(dso, ui, &table_data, &segbase, &fde_count)) { memset(&di, 0, sizeof(di)); di.format = UNW_INFO_FORMAT_REMOTE_TABLE; di.start_ip = map->start; @@ -452,16 +456,16 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, #ifndef NO_LIBUNWIND_DEBUG_FRAME /* Check the .debug_frame section for unwinding info */ if (ret < 0 && - !read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) { - int fd = dso__data_get_fd(map->dso, ui->machine); - int is_exec = elf_is_exec(fd, map->dso->name); + !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) { + int fd = dso__data_get_fd(dso, ui->machine); + int is_exec = elf_is_exec(fd, dso->name); unw_word_t base = is_exec ? 0 : map->start; const char *symfile; if (fd >= 0) - dso__data_put_fd(map->dso); + dso__data_put_fd(dso); - symfile = map->dso->symsrc_filename ?: map->dso->name; + symfile = dso->symsrc_filename ?: dso->name; memset(&di, 0, sizeof(di)); if (dwarf_find_debug_frame(0, &di, ip, base, symfile, @@ -513,6 +517,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, unw_word_t *data) { struct map *map; + struct dso *dso; ssize_t size; map = find_map(addr, ui); @@ -521,10 +526,12 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, return -1; } - if (!map->dso) + dso = map__dso(map); + + if (!dso) return -1; - size = dso__data_read_addr(map->dso, map, ui->machine, + size = dso__data_read_addr(dso, map, ui->machine, addr, (u8 *) data, sizeof(*data)); return !(size == sizeof(*data)); diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 42528ade513e..4378daaafcd3 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -22,6 +22,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized const char *arch; enum dso_type dso_type; struct unwind_libunwind_ops *ops = local_unwind_libunwind_ops; + struct dso *dso = map__dso(map); struct machine *machine; int err; @@ -29,8 +30,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized return 0; if (maps__addr_space(maps)) { - pr_debug("unwind: thread map already set, dso=%s\n", - map->dso->name); + pr_debug("unwind: thread map already set, dso=%s\n", dso->name); if (initialized) *initialized = true; return 0; @@ -41,7 +41,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized if (!machine->env || !machine->env->arch) goto out_register; - dso_type = dso__type(map->dso, machine); + dso_type = dso__type(dso, machine); if (dso_type == DSO__TYPE_UNKNOWN) return 0; diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 835c39efb80d..ec777ee11493 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -147,7 +147,7 @@ static enum dso_type machine__thread_dso_type(struct machine *machine, struct map_rb_node *rb_node; maps__for_each_entry(thread->maps, rb_node) { - struct dso *dso = rb_node->map->dso; + struct dso *dso = map__dso(rb_node->map); if (!dso || dso->long_name[0] != '/') continue; -- GitLab From e5116f46d44b72ede59a6923829f68a8b8f84e76 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 20 Mar 2023 14:22:36 -0700 Subject: [PATCH 2020/5631] perf map: Add accessor for start and end Later changes will add reference count checking for struct map, start and end are frequently accessed variables. Add an accessor so that the reference count check is only necessary in one place. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230320212248.1175731-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/tests/dwarf-unwind.c | 2 +- tools/perf/arch/arm64/tests/dwarf-unwind.c | 2 +- tools/perf/arch/powerpc/tests/dwarf-unwind.c | 2 +- .../arch/powerpc/util/skip-callchain-idx.c | 2 +- tools/perf/arch/x86/tests/dwarf-unwind.c | 2 +- tools/perf/arch/x86/util/event.c | 4 +- tools/perf/builtin-buildid-list.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-script.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/tests/code-reading.c | 8 ++-- tools/perf/tests/maps.c | 4 +- tools/perf/tests/mmap-thread-lookup.c | 2 +- tools/perf/tests/vmlinux-kallsyms.c | 14 +++--- tools/perf/util/annotate.c | 4 +- tools/perf/util/dlfilter.c | 8 ++-- tools/perf/util/intel-pt.c | 8 ++-- tools/perf/util/machine.c | 14 +++--- tools/perf/util/map.c | 8 ++-- tools/perf/util/map.h | 12 ++++- tools/perf/util/maps.c | 30 ++++++------ tools/perf/util/probe-event.c | 4 +- .../scripting-engines/trace-event-python.c | 6 +-- tools/perf/util/symbol-elf.c | 8 ++-- tools/perf/util/symbol.c | 48 +++++++++---------- tools/perf/util/symbol_fprintf.c | 2 +- tools/perf/util/synthetic-events.c | 16 +++---- tools/perf/util/unwind-libdw.c | 6 +-- tools/perf/util/unwind-libunwind-local.c | 15 +++--- 29 files changed, 125 insertions(+), 114 deletions(-) diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c index ccfa87055c4a..566fb6c0eae7 100644 --- a/tools/perf/arch/arm/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm/tests/dwarf-unwind.c @@ -33,7 +33,7 @@ static int sample_ustack(struct perf_sample *sample, return -1; } - stack_size = map->end - sp; + stack_size = map__end(map) - sp; stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c index 46147a483049..90a7ef293ce7 100644 --- a/tools/perf/arch/arm64/tests/dwarf-unwind.c +++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c @@ -33,7 +33,7 @@ static int sample_ustack(struct perf_sample *sample, return -1; } - stack_size = map->end - sp; + stack_size = map__end(map) - sp; stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c index c9cb4b059392..32fffb593fbf 100644 --- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c +++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c @@ -33,7 +33,7 @@ static int sample_ustack(struct perf_sample *sample, return -1; } - stack_size = map->end - sp; + stack_size = map__end(map) - sp; stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c index fe0e4530673c..b7223feec770 100644 --- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c +++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c @@ -262,7 +262,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain) return skip_slot; } - rc = check_return_addr(dso, al.map->start, ip); + rc = check_return_addr(dso, map__start(al.map), ip); pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n", dso->long_name, al.sym->name, ip, rc); diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index a54dea7c112f..497593be80f2 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -33,7 +33,7 @@ static int sample_ustack(struct perf_sample *sample, return -1; } - stack_size = map->end - sp; + stack_size = map__end(map) - sp; stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size; memcpy(buf, (void *) sp, stack_size); diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 17bf60babfbd..3b2475707756 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -59,8 +59,8 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, event->mmap.header.size = size; - event->mmap.start = map->start; - event->mmap.len = map->end - map->start; + event->mmap.start = map__start(map); + event->mmap.len = map__size(map); event->mmap.pgoff = map->pgoff; event->mmap.pid = machine->pid; diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index cad9ed44ce7c..eea28cbcc0b7 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -30,7 +30,7 @@ static int buildid__map_cb(struct map *map, void *arg __maybe_unused) memset(bid_buf, 0, sizeof(bid_buf)); if (dso->has_build_id) build_id__sprintf(&dso->bid, bid_buf); - printf("%s %16" PRIx64 " %16" PRIx64, bid_buf, map->start, map->end); + printf("%s %16" PRIx64 " %16" PRIx64, bid_buf, map__start(map), map__end(map)); if (dso->long_name != NULL) { printf(" %s", dso->long_name); } else if (dso->short_name != NULL) { diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ff239b89e4d0..2a6e2cee5e0d 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -851,7 +851,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) const struct dso *dso = map__dso(map); printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", - indent, "", map->start, map->end, + indent, "", map__start(map), map__end(map), map->prot & PROT_READ ? 'r' : '-', map->prot & PROT_WRITE ? 'w' : '-', map->prot & PROT_EXEC ? 'x' : '-', diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 27fd9c203600..1d078106abc4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1209,7 +1209,7 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread, if (al.addr < al.sym->end) off = al.addr - al.sym->start; else - off = al.addr - al.map->start - al.sym->start; + off = al.addr - map__start(al.map) - al.sym->start; printed += fprintf(fp, "\t%s", al.sym->name); if (off) printed += fprintf(fp, "%+d", off); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index babfc163efe2..b803af4329d1 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -183,7 +183,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) "Not all samples will be on the annotation output.\n\n" "Please report to linux-kernel@vger.kernel.org\n", ip, dso->long_name, dso__symtab_origin(dso), - map->start, map->end, sym->start, sym->end, + map__start(map), map__end(map), sym->start, sym->end, sym->binding == STB_GLOBAL ? 'g' : sym->binding == STB_LOCAL ? 'l' : 'w', sym->name, err ? "[unknown]" : uts.machine, diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 936c61546e64..1545fcaa95c6 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -265,8 +265,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, len = BUFSZ; /* Do not go off the map */ - if (addr + len > al.map->end) - len = al.map->end - addr; + if (addr + len > map__end(al.map)) + len = map__end(al.map) - addr; /* Read the object code using perf */ ret_len = dso__data_read_offset(dso, maps__machine(thread->maps), @@ -291,7 +291,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, size_t d; for (d = 0; d < state->done_cnt; d++) { - if (state->done[d] == al.map->start) { + if (state->done[d] == map__start(al.map)) { pr_debug("kcore map tested already"); pr_debug(" - skipping\n"); goto out; @@ -301,7 +301,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, pr_debug("Too many kcore maps - skipping\n"); goto out; } - state->done[state->done_cnt++] = al.map->start; + state->done[state->done_cnt++] = map__start(al.map); } objdump_name = dso->long_name; diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index ae7028fbf79e..fd0c464fcf95 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -24,8 +24,8 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma if (i > 0) TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size)); - TEST_ASSERT_VAL("wrong map start", map->start == merged[i].start); - TEST_ASSERT_VAL("wrong map end", map->end == merged[i].end); + TEST_ASSERT_VAL("wrong map start", map__start(map) == merged[i].start); + TEST_ASSERT_VAL("wrong map end", map__end(map) == merged[i].end); TEST_ASSERT_VAL("wrong map name", !strcmp(map__dso(map)->name, merged[i].name)); TEST_ASSERT_VAL("wrong map refcnt", refcount_read(&map->refcnt) == 1); diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index a4301fc7b770..5cc4644e353d 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -202,7 +202,7 @@ static int mmap_events(synth_cb synth) break; } - pr_debug("map %p, addr %" PRIx64 "\n", al.map, al.map->start); + pr_debug("map %p, addr %" PRIx64 "\n", al.map, map__start(al.map)); } machine__delete_threads(machine); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index c614c2db7e89..0a75623172c2 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -267,7 +267,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused continue; } - } else if (mem_start == kallsyms.vmlinux_map->end) { + } else if (mem_start == map__end(kallsyms.vmlinux_map)) { /* * Ignore aliases to _etext, i.e. to the end of the kernel text area, * such as __indirect_thunk_end. @@ -319,14 +319,14 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused maps__for_each_entry(maps, rb_node) { struct map *pair, *map = rb_node->map; - mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start); - mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end); + mem_start = vmlinux_map->unmap_ip(vmlinux_map, map__start(map)); + mem_end = vmlinux_map->unmap_ip(vmlinux_map, map__end(map)); pair = maps__find(kallsyms.kmaps, mem_start); if (pair == NULL || pair->priv) continue; - if (pair->start == mem_start) { + if (map__start(pair) == mem_start) { struct dso *dso = map__dso(map); if (!header_printed) { @@ -335,10 +335,10 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused } pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", - map->start, map->end, map->pgoff, dso->name); - if (mem_end != pair->end) + map__start(map), map__end(map), map->pgoff, dso->name); + if (mem_end != map__end(pair)) pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, - pair->start, pair->end, pair->pgoff); + map__start(pair), map__end(pair), pair->pgoff); pr_info(" %s\n", dso->name); pair->priv = 1; } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 84100ca5f306..b9cff782d7df 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1008,13 +1008,13 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams, if (start && (start->ms.sym == ams->ms.sym || (ams->ms.sym && - start->addr == ams->ms.sym->start + ams->ms.map->start))) + start->addr == ams->ms.sym->start + map__start(ams->ms.map)))) saddr = start->al_addr; if (saddr == 0) pr_debug2("BB with bad start: addr %"PRIx64" start %"PRIx64" sym %"PRIx64" saddr %"PRIx64"\n", ams->addr, start ? start->addr : 0, - ams->ms.sym ? ams->ms.sym->start + ams->ms.map->start : 0, + ams->ms.sym ? ams->ms.sym->start + map__start(ams->ms.map) : 0, saddr); err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles); if (err) diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 8a7ffe0d805a..fe401fa4be02 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -51,7 +51,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al) if (al->addr < sym->end) d_al->symoff = al->addr - sym->start; else - d_al->symoff = al->addr - al->map->start - sym->start; + d_al->symoff = al->addr - map__start(al->map) - sym->start; d_al->sym_binding = sym->binding; } else { d_al->sym = NULL; @@ -268,7 +268,7 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) map = al->map; - if (map && ip >= map->start && ip < map->end && + if (map && ip >= map__start(map) && ip < map__end(map) && machine__kernel_ip(d->machine, ip) == machine__kernel_ip(d->machine, d->sample->ip)) goto have_map; @@ -279,8 +279,8 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) map = a.map; have_map: offset = map->map_ip(map, ip); - if (ip + len >= map->end) - len = map->end - ip; + if (ip + len >= map__end(map)) + len = map__end(map) - ip; return dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); } diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 8cec88e09792..a2e62daa708e 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -887,7 +887,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, goto out_no_cache; } - if (*ip >= al.map->end) + if (*ip >= map__end(al.map)) break; offset += intel_pt_insn->length; @@ -2750,7 +2750,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) if (sym->binding == STB_GLOBAL && !strcmp(sym->name, "__switch_to")) { ip = map->unmap_ip(map, sym->start); - if (ip >= map->start && ip < map->end) { + if (ip >= map__start(map) && ip < map__end(map)) { switch_ip = ip; break; } @@ -2768,7 +2768,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) for (sym = start; sym; sym = dso__next_symbol(sym)) { if (!strcmp(sym->name, ptss)) { ip = map->unmap_ip(map, sym->start); - if (ip >= map->start && ip < map->end) { + if (ip >= map__start(map) && ip < map__end(map)) { *ptss_ip = ip; break; } @@ -3356,7 +3356,7 @@ static int intel_pt_process_aux_output_hw_id(struct intel_pt *pt, static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr, struct addr_location *al) { - if (!al->map || addr < al->map->start || addr >= al->map->end) { + if (!al->map || addr < map__start(al->map) || addr >= map__end(al->map)) { if (!thread__find_map(thread, cpumode, addr, al)) return -1; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8bae38c96788..7852b97da10a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -903,7 +903,7 @@ static int machine__process_ksymbol_register(struct machine *machine, } map->start = event->ksymbol.addr; - map->end = map->start + event->ksymbol.len; + map->end = map__start(map) + event->ksymbol.len; err = maps__insert(machine__kernel_maps(machine), map); map__put(map); if (err) @@ -919,7 +919,7 @@ static int machine__process_ksymbol_register(struct machine *machine, dso = map__dso(map); } - sym = symbol__new(map->map_ip(map, map->start), + sym = symbol__new(map->map_ip(map, map__start(map)), event->ksymbol.len, 0, 0, event->ksymbol.name); if (!sym) @@ -944,7 +944,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine, else { struct dso *dso = map__dso(map); - sym = dso__find_symbol(dso, map->map_ip(map, map->start)); + sym = dso__find_symbol(dso, map->map_ip(map, map__start(map))); if (sym) dso__delete_symbol(dso, sym); } @@ -1217,7 +1217,7 @@ int machine__create_extra_kernel_map(struct machine *machine, if (!err) { pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n", - kmap->name, map->start, map->end); + kmap->name, map__start(map), map__end(map)); } map__put(map); @@ -1722,7 +1722,7 @@ int machine__create_kernel_maps(struct machine *machine) struct map_rb_node *next = map_rb_node__next(rb_node); if (next) - machine__set_kernel_mmap(machine, start, next->map->start); + machine__set_kernel_mmap(machine, start, map__start(next->map)); } out_put: @@ -1795,7 +1795,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (map == NULL) goto out_problem; - map->end = map->start + xm->end - xm->start; + map->end = map__start(map) + xm->end - xm->start; if (build_id__is_defined(bid)) dso__set_build_id(map__dso(map), bid); @@ -3293,7 +3293,7 @@ int machine__get_kernel_start(struct machine *machine) * kernel_start = 1ULL << 63 for x86_64. */ if (!err && !machine__is(machine, "x86_64")) - machine->kernel_start = map->start; + machine->kernel_start = map__start(map); } return err; } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 90062af6675a..416fc449bde8 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -421,7 +421,7 @@ size_t map__fprintf(struct map *map, FILE *fp) const struct dso *dso = map__dso(map); return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", - map->start, map->end, map->pgoff, dso->name); + map__start(map), map__end(map), map->pgoff, dso->name); } size_t map__fprintf_dsoname(struct map *map, FILE *fp) @@ -558,7 +558,7 @@ bool map__contains_symbol(const struct map *map, const struct symbol *sym) { u64 ip = map->unmap_ip(map, sym->start); - return ip >= map->start && ip < map->end; + return ip >= map__start(map) && ip < map__end(map); } struct kmap *__map__kmap(struct map *map) @@ -592,12 +592,12 @@ struct maps *map__kmaps(struct map *map) u64 map__map_ip(const struct map *map, u64 ip) { - return ip - map->start + map->pgoff; + return ip - map__start(map) + map->pgoff; } u64 map__unmap_ip(const struct map *map, u64 ip) { - return ip + map->start - map->pgoff; + return ip + map__start(map) - map->pgoff; } u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 36c5add0144d..16646b94fa3a 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -52,9 +52,19 @@ static inline struct dso *map__dso(const struct map *map) return map->dso; } +static inline u64 map__start(const struct map *map) +{ + return map->start; +} + +static inline u64 map__end(const struct map *map) +{ + return map->end; +} + static inline size_t map__size(const struct map *map) { - return map->end - map->start; + return map__end(map) - map__start(map); } /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */ diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 09ec6bbafcbc..21010a2b8e16 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -34,7 +34,7 @@ static int __maps__insert(struct maps *maps, struct map *map) { struct rb_node **p = &maps__entries(maps)->rb_node; struct rb_node *parent = NULL; - const u64 ip = map->start; + const u64 ip = map__start(map); struct map_rb_node *m, *new_rb_node; new_rb_node = malloc(sizeof(*new_rb_node)); @@ -47,7 +47,7 @@ static int __maps__insert(struct maps *maps, struct map *map) while (*p != NULL) { parent = *p; m = rb_entry(parent, struct map_rb_node, rb_node); - if (ip < m->map->start) + if (ip < map__start(m->map)) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -229,7 +229,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, st int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) { - if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) { + if (ams->addr < map__start(ams->ms.map) || ams->addr >= map__end(ams->ms.map)) { if (maps == NULL) return -1; ams->ms.map = maps__find(maps, ams->addr); @@ -283,9 +283,9 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) while (next) { struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node); - if (pos->map->end > map->start) { + if (map__end(pos->map) > map__start(map)) { first = next; - if (pos->map->start <= map->start) + if (map__start(pos->map) <= map__start(map)) break; next = next->rb_left; } else @@ -301,7 +301,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) * Stop if current map starts after map->end. * Maps are ordered by start: next will not overlap for sure. */ - if (pos->map->start >= map->end) + if (map__start(pos->map) >= map__end(map)) break; if (verbose >= 2) { @@ -321,7 +321,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) * Now check if we need to create new maps for areas not * overlapped by the new map: */ - if (map->start > pos->map->start) { + if (map__start(map) > map__start(pos->map)) { struct map *before = map__clone(pos->map); if (before == NULL) { @@ -329,7 +329,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) goto put_map; } - before->end = map->start; + before->end = map__start(map); err = __maps__insert(maps, before); if (err) goto put_map; @@ -339,7 +339,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) map__put(before); } - if (map->end < pos->map->end) { + if (map__end(map) < map__end(pos->map)) { struct map *after = map__clone(pos->map); if (after == NULL) { @@ -347,10 +347,10 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) goto put_map; } - after->start = map->end; - after->pgoff += map->end - pos->map->start; - assert(pos->map->map_ip(pos->map, map->end) == - after->map_ip(after, map->end)); + after->start = map__end(map); + after->pgoff += map__end(map) - map__start(pos->map); + assert(pos->map->map_ip(pos->map, map__end(map)) == + after->map_ip(after, map__end(map))); err = __maps__insert(maps, after); if (err) goto put_map; @@ -430,9 +430,9 @@ struct map *maps__find(struct maps *maps, u64 ip) p = maps__entries(maps)->rb_node; while (p != NULL) { m = rb_entry(p, struct map_rb_node, rb_node); - if (ip < m->map->start) + if (ip < map__start(m->map)) p = p->rb_left; - else if (ip >= m->map->end) + else if (ip >= map__end(m->map)) p = p->rb_right; else goto out; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index b26670a26005..4d9dbeeb6014 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -143,7 +143,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, return -ENOENT; *addr = map->unmap_ip(map, sym->start) - ((reloc) ? 0 : map->reloc) - - ((reladdr) ? map->start : 0); + ((reladdr) ? map__start(map) : 0); } return 0; } @@ -257,7 +257,7 @@ static bool kprobe_warn_out_range(const char *symbol, u64 address) map = kernel_get_module_map(NULL); if (map) { - ret = address <= map->start || map->end < address; + ret = address <= map__start(map) || map__end(map) < address; if (ret) pr_warning("%s is out of .text, skip it.\n", symbol); map__put(map); diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index b8e5c6f61d80..cbf09eaf3734 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -409,7 +409,7 @@ static unsigned long get_offset(struct symbol *sym, struct addr_location *al) if (al->addr < sym->end) offset = al->addr - sym->start; else - offset = al->addr - al->map->start - sym->start; + offset = al->addr - map__start(al->map) - sym->start; return offset; } @@ -788,9 +788,9 @@ static void set_sym_in_dict(PyObject *dict, struct addr_location *al, pydict_set_item_string_decref(dict, dso_bid_field, _PyUnicode_FromString(sbuild_id)); pydict_set_item_string_decref(dict, dso_map_start, - PyLong_FromUnsignedLong(al->map->start)); + PyLong_FromUnsignedLong(map__start(al->map))); pydict_set_item_string_decref(dict, dso_map_end, - PyLong_FromUnsignedLong(al->map->end)); + PyLong_FromUnsignedLong(map__end(al->map))); } if (al->sym) { pydict_set_item_string_decref(dict, sym_field, diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 561372869792..e715869eab8a 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1355,7 +1355,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, if (*remap_kernel && dso->kernel && !kmodule) { *remap_kernel = false; map->start = shdr->sh_addr + ref_reloc(kmap); - map->end = map->start + shdr->sh_size; + map->end = map__start(map) + shdr->sh_size; map->pgoff = shdr->sh_offset; map->map_ip = map__map_ip; map->unmap_ip = map__unmap_ip; @@ -1397,7 +1397,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, u64 start = sym->st_value; if (kmodule) - start += map->start + shdr->sh_offset; + start += map__start(map) + shdr->sh_offset; curr_dso = dso__new(dso_name); if (curr_dso == NULL) @@ -1415,7 +1415,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, if (adjust_kernel_syms) { curr_map->start = shdr->sh_addr + ref_reloc(kmap); - curr_map->end = curr_map->start + shdr->sh_size; + curr_map->end = map__start(curr_map) + shdr->sh_size; curr_map->pgoff = shdr->sh_offset; } else { curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; @@ -1536,7 +1536,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * attempted to prelink vdso to its virtual address. */ if (dso__is_vdso(dso)) - map->reloc = map->start - dso->text_offset; + map->reloc = map__start(map) - dso->text_offset; dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap); /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a1c85c22676f..b91deb177091 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -278,8 +278,8 @@ void maps__fixup_end(struct maps *maps) down_write(maps__lock(maps)); maps__for_each_entry(maps, curr) { - if (prev != NULL && !prev->map->end) - prev->map->end = curr->map->start; + if (prev != NULL && !map__end(prev->map)) + prev->map->end = map__start(curr->map); prev = curr; } @@ -288,7 +288,7 @@ void maps__fixup_end(struct maps *maps) * We still haven't the actual symbols, so guess the * last map final address. */ - if (curr && !curr->map->end) + if (curr && !map__end(curr->map)) curr->map->end = ~0ULL; up_write(maps__lock(maps)); @@ -810,11 +810,11 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) continue; } curr_map_dso = map__dso(curr_map); - pos->start -= curr_map->start - curr_map->pgoff; - if (pos->end > curr_map->end) - pos->end = curr_map->end; + pos->start -= map__start(curr_map) - curr_map->pgoff; + if (pos->end > map__end(curr_map)) + pos->end = map__end(curr_map); if (pos->end) - pos->end -= curr_map->start - curr_map->pgoff; + pos->end -= map__start(curr_map) - curr_map->pgoff; symbols__insert(&curr_map_dso->symbols, pos); ++count; } @@ -1156,7 +1156,7 @@ static int do_validate_kcore_modules(const char *filename, struct maps *kmaps) dso = map__dso(old_map); /* Module must be in memory at the same address */ mi = find_module(dso->short_name, &modules); - if (!mi || mi->start != old_map->start) { + if (!mi || mi->start != map__start(old_map)) { err = -EINVAL; goto out; } @@ -1250,7 +1250,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) return -ENOMEM; } - list_node->map->end = list_node->map->start + len; + list_node->map->end = map__start(list_node->map) + len; list_node->map->pgoff = pgoff; list_add(&list_node->node, &md->maps); @@ -1272,21 +1272,21 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) struct map *old_map = rb_node->map; /* no overload with this one */ - if (new_map->end < old_map->start || - new_map->start >= old_map->end) + if (map__end(new_map) < map__start(old_map) || + map__start(new_map) >= map__end(old_map)) continue; - if (new_map->start < old_map->start) { + if (map__start(new_map) < map__start(old_map)) { /* * |new...... * |old.... */ - if (new_map->end < old_map->end) { + if (map__end(new_map) < map__end(old_map)) { /* * |new......| -> |new..| * |old....| -> |old....| */ - new_map->end = old_map->start; + new_map->end = map__start(old_map); } else { /* * |new.............| -> |new..| |new..| @@ -1306,17 +1306,17 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) goto out; } - m->map->end = old_map->start; + m->map->end = map__start(old_map); list_add_tail(&m->node, &merged); - new_map->pgoff += old_map->end - new_map->start; - new_map->start = old_map->end; + new_map->pgoff += map__end(old_map) - map__start(new_map); + new_map->start = map__end(old_map); } } else { /* * |new...... * |old.... */ - if (new_map->end < old_map->end) { + if (map__end(new_map) < map__end(old_map)) { /* * |new..| -> x * |old.........| -> |old.........| @@ -1329,8 +1329,8 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) * |new......| -> |new...| * |old....| -> |old....| */ - new_map->pgoff += old_map->end - new_map->start; - new_map->start = old_map->end; + new_map->pgoff += map__end(old_map) - map__start(new_map); + new_map->start = map__end(old_map); } } } @@ -1428,9 +1428,9 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_for_each_entry(new_node, &md.maps, node) { struct map *new_map = new_node->map; - u64 new_size = new_map->end - new_map->start; + u64 new_size = map__size(new_map); - if (!(stext >= new_map->start && stext < new_map->end)) + if (!(stext >= map__start(new_map) && stext < map__end(new_map))) continue; /* @@ -1457,8 +1457,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_del_init(&new_node->node); if (new_map == replacement_map) { - map->start = new_map->start; - map->end = new_map->end; + map->start = map__start(new_map); + map->end = map__end(new_map); map->pgoff = new_map->pgoff; map->map_ip = new_map->map_ip; map->unmap_ip = new_map->unmap_ip; diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c index 2664fb65e47a..d9e5ad040b6a 100644 --- a/tools/perf/util/symbol_fprintf.c +++ b/tools/perf/util/symbol_fprintf.c @@ -30,7 +30,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym, if (al->addr < sym->end) offset = al->addr - sym->start; else - offset = al->addr - al->map->start - sym->start; + offset = al->addr - map__start(al->map) - sym->start; length += fprintf(fp, "+0x%lx", offset); } return length; diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index fbd1a882b013..b2e4afa5efa1 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -706,8 +706,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t (sizeof(event->mmap2.filename) - size)); memset(event->mmap2.filename + size, 0, machine->id_hdr_size); event->mmap2.header.size += machine->id_hdr_size; - event->mmap2.start = map->start; - event->mmap2.len = map->end - map->start; + event->mmap2.start = map__start(map); + event->mmap2.len = map__size(map); event->mmap2.pid = machine->pid; memcpy(event->mmap2.filename, dso->long_name, dso->long_name_len + 1); @@ -720,8 +720,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t (sizeof(event->mmap.filename) - size)); memset(event->mmap.filename + size, 0, machine->id_hdr_size); event->mmap.header.size += machine->id_hdr_size; - event->mmap.start = map->start; - event->mmap.len = map->end - map->start; + event->mmap.start = map__start(map); + event->mmap.len = map__size(map); event->mmap.pid = machine->pid; memcpy(event->mmap.filename, dso->long_name, dso->long_name_len + 1); @@ -1143,8 +1143,8 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, event->mmap2.header.size = (sizeof(event->mmap2) - (sizeof(event->mmap2.filename) - size) + machine->id_hdr_size); event->mmap2.pgoff = kmap->ref_reloc_sym->addr; - event->mmap2.start = map->start; - event->mmap2.len = map->end - event->mmap.start; + event->mmap2.start = map__start(map); + event->mmap2.len = map__end(map) - event->mmap.start; event->mmap2.pid = machine->pid; perf_record_mmap2__read_build_id(&event->mmap2, machine, true); @@ -1156,8 +1156,8 @@ static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool, event->mmap.header.size = (sizeof(event->mmap) - (sizeof(event->mmap.filename) - size) + machine->id_hdr_size); event->mmap.pgoff = kmap->ref_reloc_sym->addr; - event->mmap.start = map->start; - event->mmap.len = map->end - event->mmap.start; + event->mmap.start = map__start(map); + event->mmap.len = map__end(map) - event->mmap.start; event->mmap.pid = machine->pid; } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index c8cba9d4bfd9..b79f57e5648f 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -62,19 +62,19 @@ static int __report_module(struct addr_location *al, u64 ip, Dwarf_Addr s; dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); - if (s != al->map->start - al->map->pgoff) + if (s != map__start(al->map) - al->map->pgoff) mod = 0; } if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, - al->map->start - al->map->pgoff, false); + map__start(al->map) - al->map->pgoff, false); if (!mod) { char filename[PATH_MAX]; if (dso__build_id_filename(dso, filename, sizeof(filename), false)) mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, - al->map->start - al->map->pgoff, false); + map__start(al->map) - al->map->pgoff, false); } if (mod) { diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 108f7b1697a7..1c13f43e7d22 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -327,9 +327,10 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct unwind_info *ui, maps__for_each_entry(ui->thread->maps, map_node) { struct map *map = map_node->map; + u64 start = map__start(map); - if (map__dso(map) == dso && map->start < base_addr) - base_addr = map->start; + if (map__dso(map) == dso && start < base_addr) + base_addr = start; } base_addr -= dso->data.elf_base_addr; /* Address of .eh_frame_hdr */ @@ -443,8 +444,8 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, if (!read_unwind_spec_eh_frame(dso, ui, &table_data, &segbase, &fde_count)) { memset(&di, 0, sizeof(di)); di.format = UNW_INFO_FORMAT_REMOTE_TABLE; - di.start_ip = map->start; - di.end_ip = map->end; + di.start_ip = map__start(map); + di.end_ip = map__end(map); di.u.rti.segbase = segbase; di.u.rti.table_data = table_data; di.u.rti.table_len = fde_count * sizeof(struct table_entry) @@ -459,7 +460,8 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) { int fd = dso__data_get_fd(dso, ui->machine); int is_exec = elf_is_exec(fd, dso->name); - unw_word_t base = is_exec ? 0 : map->start; + u64 start = map__start(map); + unw_word_t base = is_exec ? 0 : start; const char *symfile; if (fd >= 0) @@ -468,8 +470,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi, symfile = dso->symsrc_filename ?: dso->name; memset(&di, 0, sizeof(di)); - if (dwarf_find_debug_frame(0, &di, ip, base, symfile, - map->start, map->end)) + if (dwarf_find_debug_frame(0, &di, ip, base, symfile, start, map__end(map))) return dwarf_search_unwind_table(as, ip, &di, pi, need_unwind_info, arg); } -- GitLab From 5462ade6871e96646502cc95e7e05f0ab4fc84de Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 30 Mar 2023 14:49:43 +0300 Subject: [PATCH 2021/5631] x86/boot: Centralize __pa()/__va() definitions Replace multiple __pa()/__va() definitions with a single one in misc.h. Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport Reviewed-by: Dave Hansen Link: https://lore.kernel.org/all/20230330114956.20342-2-kirill.shutemov%40linux.intel.com --- arch/x86/boot/compressed/ident_map_64.c | 8 -------- arch/x86/boot/compressed/misc.h | 9 +++++++++ arch/x86/boot/compressed/sev.c | 2 -- 3 files changed, 9 insertions(+), 10 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 321a5011042d..bcc956c17872 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -8,14 +8,6 @@ * Copyright (C) 2016 Kees Cook */ -/* - * Since we're dealing with identity mappings, physical and virtual - * addresses are the same, so override these defines which are ultimately - * used by the headers in misc.h. - */ -#define __pa(x) ((unsigned long)(x)) -#define __va(x) ((void *)((unsigned long)(x))) - /* No PAGE_TABLE_ISOLATION support needed either: */ #undef CONFIG_PAGE_TABLE_ISOLATION diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 20118fb7c53b..2f155a0e3041 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -19,6 +19,15 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 +/* + * Boot stub deals with identity mappings, physical and virtual addresses are + * the same, so override these defines. + * + * will not define them if they are already defined. + */ +#define __pa(x) ((unsigned long)(x)) +#define __va(x) ((void *)((unsigned long)(x))) + #include #include #include diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index d63ad8f99f83..014b89c89088 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -104,9 +104,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, } #undef __init -#undef __pa #define __init -#define __pa(x) ((unsigned long)(x)) #define __BOOT_COMPRESSED -- GitLab From e0e3aca997f7f2b9b5b5e27f878e9bf5b573720a Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 4 Apr 2023 13:45:53 -0700 Subject: [PATCH 2022/5631] clk: mediatek: Use right match table, include mod_devicetable This is copy/pasta that breaks modular builds. Fix the match table to use the right pointer, or the right device table type. And while we're including the header, fix the order to be linux, dt-bindings, and finally local. Cc: Garmin.Chang Cc: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Fixes: f42b9e9a43e3 ("clk: mediatek: Add MT8188 wpesys clock support") Fixes: 0d2f2cefba64 ("clk: mediatek: Add MT8188 adsp clock support") Fixes: e4aaa60eae16 ("clk: mediatek: Add MT8188 vdosys0 clock support") Fixes: cfa4609f9bbe ("clk: mediatek: Add MT8188 vdosys1 clock support") Fixes: bb87c1109ce2 ("clk: mediatek: Add MT8188 vencsys clock support") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304011039.UBDX1UOT-lkp@intel.com/ Link: https://lore.kernel.org/oe-kbuild-all/202304020649.QO2HlpD5-lkp@intel.com/ Link: https://lore.kernel.org/oe-kbuild-all/202304021055.WDhQPcoS-lkp@intel.com/ Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230404204553.1256263-1-sboyd@kernel.org --- drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c | 6 ++++-- drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c | 6 ++++-- drivers/clk/mediatek/clk-mt8188-vdo0.c | 4 +++- drivers/clk/mediatek/clk-mt8188-vdo1.c | 4 +++- drivers/clk/mediatek/clk-mt8188-venc.c | 6 ++++-- drivers/clk/mediatek/clk-mt8188-wpe.c | 6 ++++-- 6 files changed, 22 insertions(+), 10 deletions(-) diff --git a/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c b/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c index b3c31ffff931..808f2ad3b7ee 100644 --- a/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c +++ b/drivers/clk/mediatek/clk-mt8188-adsp_audio26m.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" @@ -34,7 +36,7 @@ static const struct of_device_id of_match_clk_mt8188_adsp_audio26m[] = { { .compatible = "mediatek,mt8188-adsp-audio26m", .data = &adsp_audio26m_desc }, { /* sentinel */ } }; -MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_adsp_audio26m); +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_adsp_audio26m); static struct platform_driver clk_mt8188_adsp_audio26m_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c b/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c index 2238d2984320..da41a3c59919 100644 --- a/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c +++ b/drivers/clk/mediatek/clk-mt8188-imp_iic_wrap.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" @@ -65,7 +67,7 @@ static const struct of_device_id of_match_clk_mt8188_imp_iic_wrap[] = { { .compatible = "mediatek,mt8188-imp-iic-wrap-en", .data = &imp_iic_wrap_en_desc }, { /* sentinel */ } }; -MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_imp_iic_wrap); +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_imp_iic_wrap); static struct platform_driver clk_mt8188_imp_iic_wrap_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8188-vdo0.c b/drivers/clk/mediatek/clk-mt8188-vdo0.c index 0c61c2dc4337..d2be44c2f3f5 100644 --- a/drivers/clk/mediatek/clk-mt8188-vdo0.c +++ b/drivers/clk/mediatek/clk-mt8188-vdo0.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" diff --git a/drivers/clk/mediatek/clk-mt8188-vdo1.c b/drivers/clk/mediatek/clk-mt8188-vdo1.c index 99fcf6d7b1ab..2ef8cae2e16e 100644 --- a/drivers/clk/mediatek/clk-mt8188-vdo1.c +++ b/drivers/clk/mediatek/clk-mt8188-vdo1.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" diff --git a/drivers/clk/mediatek/clk-mt8188-venc.c b/drivers/clk/mediatek/clk-mt8188-venc.c index 6f6589ccd5a0..245367f33fa5 100644 --- a/drivers/clk/mediatek/clk-mt8188-venc.c +++ b/drivers/clk/mediatek/clk-mt8188-venc.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" @@ -39,7 +41,7 @@ static const struct of_device_id of_match_clk_mt8188_venc1[] = { { .compatible = "mediatek,mt8188-vencsys", .data = &venc1_desc }, { /* sentinel */ } }; -MODULE_DEVICE_TABLE(platform, of_match_clk_mt8188_venc1); +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_venc1); static struct platform_driver clk_mt8188_venc1_drv = { .probe = mtk_clk_simple_probe, diff --git a/drivers/clk/mediatek/clk-mt8188-wpe.c b/drivers/clk/mediatek/clk-mt8188-wpe.c index 5abded13cece..393ac38a2172 100644 --- a/drivers/clk/mediatek/clk-mt8188-wpe.c +++ b/drivers/clk/mediatek/clk-mt8188-wpe.c @@ -4,10 +4,12 @@ * Author: Garmin Chang */ -#include #include +#include #include +#include + #include "clk-gate.h" #include "clk-mtk.h" @@ -88,7 +90,7 @@ static const struct of_device_id of_match_clk_mt8188_wpe[] = { { .compatible = "mediatek,mt8188-wpesys-vpp0", .data = &wpe_vpp0_desc }, { /* sentinel */ } }; -MODULE_DEVICE_TABLE(platform, clk_mt8188_vpp1_id_table); +MODULE_DEVICE_TABLE(of, of_match_clk_mt8188_wpe); static struct platform_driver clk_mt8188_wpe_drv = { .probe = mtk_clk_simple_probe, -- GitLab From 123ee7550e52700475eff4d673723e03339e629f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 16 Mar 2023 12:48:04 +0100 Subject: [PATCH 2023/5631] dt-bindings: clock: dispcc-qcm2290: Add MDSS_CORE reset Add the MDSS_CORE reset which can be asserted to reset the state of the entire MDSS. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230316-topic-qcm_dispcc_reset-v1-1-dd3708853014@linaro.org --- include/dt-bindings/clock/qcom,dispcc-qcm2290.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/dt-bindings/clock/qcom,dispcc-qcm2290.h b/include/dt-bindings/clock/qcom,dispcc-qcm2290.h index 1db513d6b3ee..cb687949be41 100644 --- a/include/dt-bindings/clock/qcom,dispcc-qcm2290.h +++ b/include/dt-bindings/clock/qcom,dispcc-qcm2290.h @@ -29,6 +29,10 @@ #define DISP_CC_XO_CLK 19 #define DISP_CC_XO_CLK_SRC 20 +/* GDSCs */ #define MDSS_GDSC 0 +/* Resets */ +#define DISP_CC_MDSS_CORE_BCR 0 + #endif -- GitLab From 002c3fb6f4f38b50ef0514247c2d55fc6ed8c6d4 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 16 Mar 2023 12:48:05 +0100 Subject: [PATCH 2024/5631] clk: qcom: dispcc-qcm2290: Add MDSS_CORE reset Add the MDSS_CORE reset which can be asserted to reset the state of the entire MDSS. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230316-topic-qcm_dispcc_reset-v1-2-dd3708853014@linaro.org --- drivers/clk/qcom/dispcc-qcm2290.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/clk/qcom/dispcc-qcm2290.c b/drivers/clk/qcom/dispcc-qcm2290.c index 2ebd9a02b895..cbb5f1ec6a54 100644 --- a/drivers/clk/qcom/dispcc-qcm2290.c +++ b/drivers/clk/qcom/dispcc-qcm2290.c @@ -20,6 +20,7 @@ #include "clk-regmap-divider.h" #include "common.h" #include "gdsc.h" +#include "reset.h" enum { P_BI_TCXO, @@ -445,6 +446,10 @@ static struct clk_branch disp_cc_sleep_clk = { }, }; +static const struct qcom_reset_map disp_cc_qcm2290_resets[] = { + [DISP_CC_MDSS_CORE_BCR] = { 0x2000 }, +}; + static struct gdsc mdss_gdsc = { .gdscr = 0x3000, .pd = { @@ -494,6 +499,8 @@ static const struct qcom_cc_desc disp_cc_qcm2290_desc = { .num_clks = ARRAY_SIZE(disp_cc_qcm2290_clocks), .gdscs = disp_cc_qcm2290_gdscs, .num_gdscs = ARRAY_SIZE(disp_cc_qcm2290_gdscs), + .resets = disp_cc_qcm2290_resets, + .num_resets = ARRAY_SIZE(disp_cc_qcm2290_resets), }; static const struct of_device_id disp_cc_qcm2290_match_table[] = { -- GitLab From 393a759647061bc29c1d62f83c7d36cacc912a89 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:40 +0100 Subject: [PATCH 2025/5631] MIPS: Move declaration of bcache ops to cache.c bcache is not tied to CPU's cache interface. Just move those declaration to cache.c so it can be avaialble to CPU with all cache types. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/cache.h | 2 ++ arch/mips/mm/c-r4k.c | 14 -------------- arch/mips/mm/cache.c | 19 +++++++++++++++++++ 3 files changed, 21 insertions(+), 14 deletions(-) diff --git a/arch/mips/include/asm/cache.h b/arch/mips/include/asm/cache.h index 29187e12b861..3424a7908c0f 100644 --- a/arch/mips/include/asm/cache.h +++ b/arch/mips/include/asm/cache.h @@ -16,4 +16,6 @@ #define __read_mostly __section(".data..read_mostly") +extern void cache_noop(void); + #endif /* _ASM_CACHE_H */ diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7d447050a20b..5599b9c9a737 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -110,20 +110,6 @@ static unsigned long dcache_size __read_mostly; static unsigned long vcache_size __read_mostly; static unsigned long scache_size __read_mostly; -/* - * Dummy cache handling routines for machines without boardcaches - */ -static void cache_noop(void) {} - -static struct bcache_ops no_sc_ops = { - .bc_enable = (void *)cache_noop, - .bc_disable = (void *)cache_noop, - .bc_wback_inv = (void *)cache_noop, - .bc_inv = (void *)cache_noop -}; - -struct bcache_ops *bcops = &no_sc_ops; - #define cpu_is_r4600_v1_x() ((read_c0_prid() & 0xfffffff0) == 0x00002010) #define cpu_is_r4600_v2_x() ((read_c0_prid() & 0xfffffff0) == 0x00002020) diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 11b3e7ddafd5..7dba4b5c02c3 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -56,6 +57,24 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page); EXPORT_SYMBOL(flush_data_cache_page); EXPORT_SYMBOL(flush_icache_all); +/* + * Dummy cache handling routine + */ + +void cache_noop(void) {} + +#ifdef CONFIG_BOARD_SCACHE + +static struct bcache_ops no_sc_ops = { + .bc_enable = (void *)cache_noop, + .bc_disable = (void *)cache_noop, + .bc_wback_inv = (void *)cache_noop, + .bc_inv = (void *)cache_noop +}; + +struct bcache_ops *bcops = &no_sc_ops; +#endif + #ifdef CONFIG_DMA_NONCOHERENT /* DMA cache operations. */ -- GitLab From aa45787c0db0a5f7b21bd16b917ff44761a2c6ac Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:41 +0100 Subject: [PATCH 2026/5631] MIPS: smp-cps: Disable coherence setup for unsupported ISA We don't know how to do coherence setup on ISA before MIPS Release 1. As CPS support only servers simulation purpose on those cores, and simulators are always coherent, just disable initialization code and provide user a warning in case coherence is not setup properly. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/cps-vec.S | 5 +++++ arch/mips/kernel/smp-cps.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 8ef492da827f..64ecfdac6580 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -116,6 +116,8 @@ not_nmi: li t0, ST0_CU1 | ST0_CU0 | ST0_BEV | STATUS_BITDEPS mtc0 t0, CP0_STATUS + /* We don't know how to do coherence setup on earlier ISA */ +#if MIPS_ISA_REV > 0 /* Skip cache & coherence setup if we're already coherent */ lw s7, GCR_CL_COHERENCE_OFS(s1) bnez s7, 1f @@ -129,6 +131,7 @@ not_nmi: li t0, 0xff sw t0, GCR_CL_COHERENCE_OFS(s1) ehb +#endif /* MIPS_ISA_REV > 0 */ /* Set Kseg0 CCA to that in s0 */ 1: mfc0 t0, CP0_CONFIG @@ -515,6 +518,7 @@ LEAF(mips_cps_boot_vpes) nop END(mips_cps_boot_vpes) +#if MIPS_ISA_REV > 0 LEAF(mips_cps_cache_init) /* * Clear the bits used to index the caches. Note that the architecture @@ -588,6 +592,7 @@ dcache_done: jr ra nop END(mips_cps_cache_init) +#endif /* MIPS_ISA_REV > 0 */ #if defined(CONFIG_MIPS_CPS_PM) && defined(CONFIG_CPU_PM) diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 4fc288bb85b9..f968a319d87f 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -361,6 +361,8 @@ static int cps_boot_secondary(int cpu, struct task_struct *idle) static void cps_init_secondary(void) { + int core = cpu_core(¤t_cpu_data); + /* Disable MT - we only want to run 1 TC per VPE */ if (cpu_has_mipsmt) dmt(); @@ -376,6 +378,9 @@ static void cps_init_secondary(void) BUG_ON(ident != mips_cm_vp_id(smp_processor_id())); } + if (core > 0 && !read_gcr_cl_coherence()) + pr_warn("Core %u is not in coherent domain\n", core); + if (cpu_has_veic) clear_c0_status(ST0_IM); else -- GitLab From e1aa1dfef69320141f5d00eddbf279b41e70d4e7 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:42 +0100 Subject: [PATCH 2027/5631] MIPS: mips-cm: Check availability of config registers Prevent reading unsupported config register during probing process. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/mips-cm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index b4f7d950c846..3f00788b0871 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -181,11 +181,16 @@ static DEFINE_PER_CPU_ALIGNED(unsigned long, cm_core_lock_flags); phys_addr_t __mips_cm_phys_base(void) { - u32 config3 = read_c0_config3(); unsigned long cmgcr; /* Check the CMGCRBase register is implemented */ - if (!(config3 & MIPS_CONF3_CMGCR)) + if (!(read_c0_config() & MIPS_CONF_M)) + return 0; + + if (!(read_c0_config2() & MIPS_CONF_M)) + return 0; + + if (!(read_c0_config3() & MIPS_CONF3_CMGCR)) return 0; /* Read the address from CMGCRBase */ -- GitLab From 918d779569dafd81fce4257c552aa4205c918c4a Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:43 +0100 Subject: [PATCH 2028/5631] MIPS: Octeon: Opt-out 4k_cache feature Octeon has a different cache interface with traditional R4K one, just opt-out this flag for octeon to avoid run R4K cache initialization code accidentally. Also remove ISA level assumption for 4k cache. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/cpu-features.h | 2 +- arch/mips/kernel/cpu-probe.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c0983130a44c..c613426b0bfc 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -118,7 +118,7 @@ #define cpu_has_3k_cache __isa_lt_and_opt(1, MIPS_CPU_3K_CACHE) #endif #ifndef cpu_has_4k_cache -#define cpu_has_4k_cache __isa_ge_or_opt(1, MIPS_CPU_4K_CACHE) +#define cpu_has_4k_cache __opt(MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache #define cpu_has_octeon_cache 0 diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 7ddf07f255f3..6d15a398d389 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1602,6 +1602,8 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu) static inline void cpu_probe_cavium(struct cpuinfo_mips *c, unsigned int cpu) { decode_configs(c); + /* Octeon has different cache interface */ + c->options &= ~MIPS_CPU_4K_CACHE; switch (c->processor_id & PRID_IMP_MASK) { case PRID_IMP_CAVIUM_CN38XX: case PRID_IMP_CAVIUM_CN31XX: -- GitLab From f641519409a73403ee6612b8648b95a688ab85c2 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:44 +0100 Subject: [PATCH 2029/5631] MIPS: cpu-features: Enable octeon_cache by cpu_type cpu_has_octeon_cache was tied to 0 for generic cpu-features, whith this generic kernel built for octeon CPU won't boot. Just enable this flag by cpu_type. It won't hurt orther platforms because compiler will eliminate the code path on other processors. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/cpu-features.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h index c613426b0bfc..51a1737b03d0 100644 --- a/arch/mips/include/asm/cpu-features.h +++ b/arch/mips/include/asm/cpu-features.h @@ -121,7 +121,24 @@ #define cpu_has_4k_cache __opt(MIPS_CPU_4K_CACHE) #endif #ifndef cpu_has_octeon_cache -#define cpu_has_octeon_cache 0 +#define cpu_has_octeon_cache \ +({ \ + int __res; \ + \ + switch (current_cpu_type()) { \ + case CPU_CAVIUM_OCTEON: \ + case CPU_CAVIUM_OCTEON_PLUS: \ + case CPU_CAVIUM_OCTEON2: \ + case CPU_CAVIUM_OCTEON3: \ + __res = 1; \ + break; \ + \ + default: \ + __res = 0; \ + } \ + \ + __res; \ +}) #endif /* Don't override `cpu_has_fpu' to 1 or the "nofpu" option won't work. */ #ifndef cpu_has_fpu -- GitLab From 6e90049162b92e683641966e4cdc67febe3c8fc5 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:45 +0100 Subject: [PATCH 2030/5631] MIPS: c-octeon: Provide alternative SMP cache flush function Currently c-octeon relies on octeon's own smp function to flush I-Cache. However this function is not available on generic platform. Just use smp_call_function_many on generic platform. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/mm/c-octeon.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index c7ed589de882..b7393b61cfa7 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -83,8 +83,13 @@ static void octeon_flush_icache_all_cores(struct vm_area_struct *vma) else mask = *cpu_online_mask; cpumask_clear_cpu(cpu, &mask); +#ifdef CONFIG_CAVIUM_OCTEON_SOC for_each_cpu(cpu, &mask) octeon_send_ipi_single(cpu, SMP_ICACHE_FLUSH); +#else + smp_call_function_many(&mask, (smp_call_func_t)octeon_local_flush_icache, + NULL, 1); +#endif preempt_enable(); #endif -- GitLab From b6007ff809682350515936539eb91a2e8a5f799c Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:46 +0100 Subject: [PATCH 2031/5631] MIPS: Octeon: Allow CVMSEG to be disabled Don't include cvmseg states into thread_status when CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE is not defined or 0. Fix compile for kernel without this feature. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/processor.h | 7 ++++++- arch/mips/kernel/asm-offsets.c | 3 +++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 3fde1ff72bd1..ae2cd37a38f0 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -202,11 +202,13 @@ struct octeon_cop2_state { #define COP2_INIT \ .cp2 = {0,}, +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 struct octeon_cvmseg_state { unsigned long cvmseg[CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE] [cpu_dcache_line_size() / sizeof(unsigned long)]; }; - +#endif #else #define COP2_INIT #endif @@ -263,7 +265,10 @@ struct thread_struct { unsigned long trap_nr; #ifdef CONFIG_CPU_CAVIUM_OCTEON struct octeon_cop2_state cp2 __attribute__ ((__aligned__(128))); +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 struct octeon_cvmseg_state cvmseg __attribute__ ((__aligned__(128))); +#endif #endif struct mips_abi *abi; }; diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index c4501897b870..40fd4051bb3d 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -306,7 +306,10 @@ void output_octeon_cop2_state_defines(void) OFFSET(OCTEON_CP2_HSH_IVW, octeon_cop2_state, cop2_hsh_ivw); OFFSET(OCTEON_CP2_SHA3, octeon_cop2_state, cop2_sha3); OFFSET(THREAD_CP2, task_struct, thread.cp2); +#if defined(CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE) && \ + CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0 OFFSET(THREAD_CVMSEG, task_struct, thread.cvmseg.cvmseg); +#endif BLANK(); } #endif -- GitLab From 194a835210521282ad31e8f7047556318611f596 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:47 +0100 Subject: [PATCH 2032/5631] MIPS: Loongson: Move arch cflags to MIPS top level Makefile Arch cflags should be independent to Platform. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Makefile | 38 ++++++++++++++++++++++++++++++++++ arch/mips/loongson2ef/Platform | 35 ------------------------------- arch/mips/loongson64/Platform | 16 -------------- 3 files changed, 38 insertions(+), 51 deletions(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 04e46ec24319..a7a4ee66a9d3 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -181,9 +181,47 @@ endif cflags-$(CONFIG_CAVIUM_CN63XXP1) += -Wa,-mfix-cn63xxp1 cflags-$(CONFIG_CPU_BMIPS) += -march=mips32 -Wa,-mips32 -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -Wa,--trap +cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -Wa,--trap +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-mno-loongson-mmi) +ifdef CONFIG_CPU_LOONGSON64 +cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap +cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a +cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2 +endif +cflags-$(CONFIG_CPU_LOONGSON64) += $(call cc-option,-mno-loongson-mmi) + cflags-$(CONFIG_CPU_R4000_WORKAROUNDS) += $(call cc-option,-mfix-r4000,) cflags-$(CONFIG_CPU_R4400_WORKAROUNDS) += $(call cc-option,-mfix-r4400,) cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS) += $(call cc-option,-mno-daddi,) +ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS +cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa,-mfix-loongson2f-nop +cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa,-mfix-loongson2f-jump +endif + +# +# Some versions of binutils, not currently mainline as of 2019/02/04, support +# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction +# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a +# description). +# +# We disable this in order to prevent the assembler meddling with the +# instruction that labels refer to, ie. if we label an ll instruction: +# +# 1: ll v0, 0(a0) +# +# ...then with the assembler fix applied the label may actually point at a sync +# instruction inserted by the assembler, and if we were using the label in an +# exception table the table would no longer contain the address of the ll +# instruction. +# +# Avoid this by explicitly disabling that assembler behaviour. If upstream +# binutils does not merge support for the flag then we can revisit & remove +# this later - for now it ensures vendor toolchains don't cause problems. +# +cflags-$(CONFIG_CPU_LOONGSON64) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) # For smartmips configurations, there are hundreds of warnings due to ISA overrides # in assembly and header files. smartmips is only supported for MIPS32r1 onwards diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform index c6f7a4b95997..d446b705fba4 100644 --- a/arch/mips/loongson2ef/Platform +++ b/arch/mips/loongson2ef/Platform @@ -2,41 +2,6 @@ # Loongson Processors' Support # -cflags-$(CONFIG_CPU_LOONGSON2EF) += -Wa,--trap -cflags-$(CONFIG_CPU_LOONGSON2E) += -march=loongson2e -cflags-$(CONFIG_CPU_LOONGSON2F) += -march=loongson2f -# -# Some versions of binutils, not currently mainline as of 2019/02/04, support -# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction -# to work around a CPU bug (see __SYNC_loongson3_war in asm/sync.h for a -# description). -# -# We disable this in order to prevent the assembler meddling with the -# instruction that labels refer to, ie. if we label an ll instruction: -# -# 1: ll v0, 0(a0) -# -# ...then with the assembler fix applied the label may actually point at a sync -# instruction inserted by the assembler, and if we were using the label in an -# exception table the table would no longer contain the address of the ll -# instruction. -# -# Avoid this by explicitly disabling that assembler behaviour. If upstream -# binutils does not merge support for the flag then we can revisit & remove -# this later - for now it ensures vendor toolchains don't cause problems. -# -cflags-$(CONFIG_CPU_LOONGSON2EF) += $(call cc-option,-Wa$(comma)-mno-fix-loongson3-llsc,) - -# Enable the workarounds for Loongson2f -ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS -cflags-$(CONFIG_CPU_NOP_WORKAROUNDS) += -Wa,-mfix-loongson2f-nop -cflags-$(CONFIG_CPU_JUMP_WORKAROUNDS) += -Wa,-mfix-loongson2f-jump -endif - -# Some -march= flags enable MMI instructions, and GCC complains about that -# support being enabled alongside -msoft-float. Thus explicitly disable MMI. -cflags-y += $(call cc-option,-mno-loongson-mmi) - # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 473404cae1c4..49c9889e3d56 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -1,19 +1,3 @@ -# -# Loongson Processors' Support -# - - -cflags-$(CONFIG_CPU_LOONGSON64) += -Wa,--trap - -ifdef CONFIG_CPU_LOONGSON64 -cflags-$(CONFIG_CC_IS_GCC) += -march=loongson3a -cflags-$(CONFIG_CC_IS_CLANG) += -march=mips64r2 -endif - -# Some -march= flags enable MMI instructions, and GCC complains about that -# support being enabled alongside -msoft-float. Thus explicitly disable MMI. -cflags-y += $(call cc-option,-mno-loongson-mmi) - # # Loongson Machines' Support # -- GitLab From 0c6ff92773a9c004c44af47b0609f67dcc97ba82 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:48 +0100 Subject: [PATCH 2033/5631] MIPS: Loongson: Don't select platform features with CPU ARCH_HAS_PHYS_TO_DMA and GPIOLIB are all platform level features they shouldn't be selected with CPU. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 2 -- arch/mips/loongson2ef/Kconfig | 3 +++ 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 2082efdb411b..54a6ba91226e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1341,7 +1341,6 @@ config CPU_LOONGSON2F bool "Loongson 2F" depends on SYS_HAS_CPU_LOONGSON2F select CPU_LOONGSON2EF - select GPIOLIB help The Loongson 2F processor implements the MIPS III instruction set with many extensions. @@ -1763,7 +1762,6 @@ config CPU_LOONGSON2EF select CPU_SUPPORTS_64BIT_KERNEL select CPU_SUPPORTS_HIGHMEM select CPU_SUPPORTS_HUGEPAGES - select ARCH_HAS_PHYS_TO_DMA config CPU_LOONGSON32 bool diff --git a/arch/mips/loongson2ef/Kconfig b/arch/mips/loongson2ef/Kconfig index 96dc6eba4310..f93eb6f42238 100644 --- a/arch/mips/loongson2ef/Kconfig +++ b/arch/mips/loongson2ef/Kconfig @@ -7,6 +7,7 @@ choice config LEMOTE_FULOONG2E bool "Lemote Fuloong(2e) mini-PC" select ARCH_SPARSEMEM_ENABLE + select ARCH_HAS_PHYS_TO_DMA select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select CEVT_R4K @@ -36,6 +37,7 @@ config LEMOTE_FULOONG2E config LEMOTE_MACH2F bool "Lemote Loongson 2F family machines" select ARCH_SPARSEMEM_ENABLE + select ARCH_HAS_PHYS_TO_DMA select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select BOARD_SCACHE @@ -46,6 +48,7 @@ config LEMOTE_MACH2F select CSRC_R4K if ! MIPS_EXTERNAL_TIMER select DMA_NONCOHERENT select GENERIC_ISA_DMA_SUPPORT_BROKEN + select GPIOLIB select FORCE_PCI select I8259 select IRQ_MIPS_CPU -- GitLab From 78073b8f1ffe4085309808815746403209bfd6bc Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:49 +0100 Subject: [PATCH 2034/5631] MIPS: Octeon: Disable CVMSEG by default on other platforms QEMU can't emulate CVMSEG on generic platform for now. Just disable it by default. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/cavium-octeon/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index c1899f109e19..450e979ef5d9 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -14,7 +14,8 @@ config CAVIUM_CN63XXP1 config CAVIUM_OCTEON_CVMSEG_SIZE int "Number of L1 cache lines reserved for CVMSEG memory" range 0 54 - default 1 + default 0 if !CAVIUM_OCTEON_SOC + default 1 if CAVIUM_OCTEON_SOC help CVMSEG LM is a segment that accesses portions of the dcache as a local memory; the larger CVMSEG is, the smaller the cache is. -- GitLab From 03be534e1bac6d92cbcebdddfc4242e1e3588350 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:50 +0100 Subject: [PATCH 2035/5631] MIPS: Add board config for virt board Aligned with QEMU MIPS virt board. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/configs/generic/board-virt.config | 38 +++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 arch/mips/configs/generic/board-virt.config diff --git a/arch/mips/configs/generic/board-virt.config b/arch/mips/configs/generic/board-virt.config new file mode 100644 index 000000000000..5594f9e5c3a8 --- /dev/null +++ b/arch/mips/configs/generic/board-virt.config @@ -0,0 +1,38 @@ +CONFIG_COMMON_CLK=y + +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIC=y + +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_PCI_HOST_GENERIC=y + +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_POWER_RESET_SYSCON_POWEROFF=y +CONFIG_SYSCON_REBOOT_MODE=y + +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GOLDFISH=y + +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y + +CONFIG_MTD=y +CONFIG_MTD_CFI=y + +CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_XHCI_HCD=y + +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_NET=y +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y -- GitLab From de34007751aaba992373f2d659001a846aeb8811 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 4 Apr 2023 10:33:51 +0100 Subject: [PATCH 2036/5631] MIPS: generic: Enable all CPUs supported by virt board in Kconfig Enable extra CPUs that may be supported by virt board, including R4x00 (R4000 in QEMU), Cavium Octeon (Octeon68XX in QEMU), loongson2e, loongson2f. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 54a6ba91226e..a975f140ae82 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -153,12 +153,16 @@ config MIPS_GENERIC_KERNEL select PCI_DRIVERS_GENERIC select SMP_UP if SMP select SWAP_IO_SPACE + select SYS_HAS_CPU_CAVIUM_OCTEON + select SYS_HAS_CPU_LOONGSON2E + select SYS_HAS_CPU_LOONGSON2F select SYS_HAS_CPU_MIPS32_R1 select SYS_HAS_CPU_MIPS32_R2 select SYS_HAS_CPU_MIPS32_R6 select SYS_HAS_CPU_MIPS64_R1 select SYS_HAS_CPU_MIPS64_R2 select SYS_HAS_CPU_MIPS64_R6 + select SYS_HAS_CPU_R4X00 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN -- GitLab From 39afe5d6fc59237ff7738bf3ede5a8856822d59d Mon Sep 17 00:00:00 2001 From: Libo Chen Date: Wed, 10 Aug 2022 15:33:13 -0700 Subject: [PATCH 2037/5631] sched/fair: Fix inaccurate tally of ttwu_move_affine There are scenarios where non-affine wakeups are incorrectly counted as affine wakeups by schedstats. When wake_affine_idle() returns prev_cpu which doesn't equal to nr_cpumask_bits, it will slip through the check: target == nr_cpumask_bits in wake_affine() and be counted as if target == this_cpu in schedstats. Replace target == nr_cpumask_bits with target != this_cpu to make sure affine wakeups are accurately tallied. Fixes: 806486c377e33 (sched/fair: Do not migrate if the prev_cpu is idle) Suggested-by: Daniel Jordan Signed-off-by: Libo Chen Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Gautham R. Shenoy Link: https://lore.kernel.org/r/20220810223313.386614-1-libo.chen@oracle.com --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bc358dc4faeb..f5da01a6b35a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6582,7 +6582,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->stats.nr_wakeups_affine_attempts); - if (target == nr_cpumask_bits) + if (target != this_cpu) return prev_cpu; schedstat_inc(sd->ttwu_move_affine); -- GitLab From 7fab21fa0d000a0ea32d73ce8eec68557c6c268b Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:15 +0200 Subject: [PATCH 2038/5631] sched/psi: Rearrange polling code in preparation Move a few functions up in the file to avoid forward declaration needed in the patch implementing unprivileged PSI triggers. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-2-cerasuolodomenico@gmail.com --- kernel/sched/psi.c | 196 ++++++++++++++++++++++----------------------- 1 file changed, 98 insertions(+), 98 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 02e011cabe91..fe9269f1d2a4 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -384,92 +384,6 @@ static void collect_percpu_times(struct psi_group *group, *pchanged_states = changed_states; } -static u64 update_averages(struct psi_group *group, u64 now) -{ - unsigned long missed_periods = 0; - u64 expires, period; - u64 avg_next_update; - int s; - - /* avgX= */ - expires = group->avg_next_update; - if (now - expires >= psi_period) - missed_periods = div_u64(now - expires, psi_period); - - /* - * The periodic clock tick can get delayed for various - * reasons, especially on loaded systems. To avoid clock - * drift, we schedule the clock in fixed psi_period intervals. - * But the deltas we sample out of the per-cpu buckets above - * are based on the actual time elapsing between clock ticks. - */ - avg_next_update = expires + ((1 + missed_periods) * psi_period); - period = now - (group->avg_last_update + (missed_periods * psi_period)); - group->avg_last_update = now; - - for (s = 0; s < NR_PSI_STATES - 1; s++) { - u32 sample; - - sample = group->total[PSI_AVGS][s] - group->avg_total[s]; - /* - * Due to the lockless sampling of the time buckets, - * recorded time deltas can slip into the next period, - * which under full pressure can result in samples in - * excess of the period length. - * - * We don't want to report non-sensical pressures in - * excess of 100%, nor do we want to drop such events - * on the floor. Instead we punt any overage into the - * future until pressure subsides. By doing this we - * don't underreport the occurring pressure curve, we - * just report it delayed by one period length. - * - * The error isn't cumulative. As soon as another - * delta slips from a period P to P+1, by definition - * it frees up its time T in P. - */ - if (sample > period) - sample = period; - group->avg_total[s] += sample; - calc_avgs(group->avg[s], missed_periods, sample, period); - } - - return avg_next_update; -} - -static void psi_avgs_work(struct work_struct *work) -{ - struct delayed_work *dwork; - struct psi_group *group; - u32 changed_states; - u64 now; - - dwork = to_delayed_work(work); - group = container_of(dwork, struct psi_group, avgs_work); - - mutex_lock(&group->avgs_lock); - - now = sched_clock(); - - collect_percpu_times(group, PSI_AVGS, &changed_states); - /* - * If there is task activity, periodically fold the per-cpu - * times and feed samples into the running averages. If things - * are idle and there is no data to process, stop the clock. - * Once restarted, we'll catch up the running averages in one - * go - see calc_avgs() and missed_periods. - */ - if (now >= group->avg_next_update) - group->avg_next_update = update_averages(group, now); - - if (changed_states & PSI_STATE_RESCHEDULE) { - schedule_delayed_work(dwork, nsecs_to_jiffies( - group->avg_next_update - now) + 1); - } - - mutex_unlock(&group->avgs_lock); -} - /* Trigger tracking window manipulations */ static void window_reset(struct psi_window *win, u64 now, u64 value, u64 prev_growth) @@ -516,18 +430,6 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) return growth; } -static void init_triggers(struct psi_group *group, u64 now) -{ - struct psi_trigger *t; - - list_for_each_entry(t, &group->triggers, node) - window_reset(&t->win, now, - group->total[PSI_POLL][t->state], 0); - memcpy(group->polling_total, group->total[PSI_POLL], - sizeof(group->polling_total)); - group->polling_next_update = now + group->poll_min_period; -} - static u64 update_triggers(struct psi_group *group, u64 now) { struct psi_trigger *t; @@ -590,6 +492,104 @@ static u64 update_triggers(struct psi_group *group, u64 now) return now + group->poll_min_period; } +static u64 update_averages(struct psi_group *group, u64 now) +{ + unsigned long missed_periods = 0; + u64 expires, period; + u64 avg_next_update; + int s; + + /* avgX= */ + expires = group->avg_next_update; + if (now - expires >= psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + avg_next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->avg_last_update + (missed_periods * psi_period)); + group->avg_last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[PSI_AVGS][s] - group->avg_total[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->avg_total[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } + + return avg_next_update; +} + +static void psi_avgs_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + u32 changed_states; + u64 now; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, avgs_work); + + mutex_lock(&group->avgs_lock); + + now = sched_clock(); + + collect_percpu_times(group, PSI_AVGS, &changed_states); + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); + + if (changed_states & PSI_STATE_RESCHEDULE) { + schedule_delayed_work(dwork, nsecs_to_jiffies( + group->avg_next_update - now) + 1); + } + + mutex_unlock(&group->avgs_lock); +} + +static void init_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + + list_for_each_entry(t, &group->triggers, node) + window_reset(&t->win, now, + group->total[PSI_POLL][t->state], 0); + memcpy(group->polling_total, group->total[PSI_POLL], + sizeof(group->polling_total)); + group->polling_next_update = now + group->poll_min_period; +} + /* Schedule polling if it's not already scheduled or forced. */ static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay, bool force) -- GitLab From 65457b74aa9437418e552e8d52d7112d4f9901a6 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:16 +0200 Subject: [PATCH 2039/5631] sched/psi: Rename existing poll members in preparation Renaming in PSI implementation to make a clear distinction between privileged and unprivileged triggers code to be implemented in the next patch. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-3-cerasuolodomenico@gmail.com --- include/linux/psi_types.h | 36 ++++----- kernel/sched/psi.c | 163 +++++++++++++++++++------------------- 2 files changed, 100 insertions(+), 99 deletions(-) diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1e0a0d7ace3a..1819afa8b198 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -175,26 +175,26 @@ struct psi_group { u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; - /* Monitor work control */ - struct task_struct __rcu *poll_task; - struct timer_list poll_timer; - wait_queue_head_t poll_wait; - atomic_t poll_wakeup; - atomic_t poll_scheduled; + /* Monitor RT polling work control */ + struct task_struct __rcu *rtpoll_task; + struct timer_list rtpoll_timer; + wait_queue_head_t rtpoll_wait; + atomic_t rtpoll_wakeup; + atomic_t rtpoll_scheduled; /* Protects data used by the monitor */ - struct mutex trigger_lock; - - /* Configured polling triggers */ - struct list_head triggers; - u32 nr_triggers[NR_PSI_STATES - 1]; - u32 poll_states; - u64 poll_min_period; - - /* Total stall times at the start of monitor activation */ - u64 polling_total[NR_PSI_STATES - 1]; - u64 polling_next_update; - u64 polling_until; + struct mutex rtpoll_trigger_lock; + + /* Configured RT polling triggers */ + struct list_head rtpoll_triggers; + u32 rtpoll_nr_triggers[NR_PSI_STATES - 1]; + u32 rtpoll_states; + u64 rtpoll_min_period; + + /* Total stall times at the start of RT polling monitor activation */ + u64 rtpoll_total[NR_PSI_STATES - 1]; + u64 rtpoll_next_update; + u64 rtpoll_until; }; #else /* CONFIG_PSI */ diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe9269f1d2a4..a3d0b5cf797a 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -189,14 +189,14 @@ static void group_init(struct psi_group *group) INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); /* Init trigger-related members */ - atomic_set(&group->poll_scheduled, 0); - mutex_init(&group->trigger_lock); - INIT_LIST_HEAD(&group->triggers); - group->poll_min_period = U32_MAX; - group->polling_next_update = ULLONG_MAX; - init_waitqueue_head(&group->poll_wait); - timer_setup(&group->poll_timer, poll_timer_fn, 0); - rcu_assign_pointer(group->poll_task, NULL); + atomic_set(&group->rtpoll_scheduled, 0); + mutex_init(&group->rtpoll_trigger_lock); + INIT_LIST_HEAD(&group->rtpoll_triggers); + group->rtpoll_min_period = U32_MAX; + group->rtpoll_next_update = ULLONG_MAX; + init_waitqueue_head(&group->rtpoll_wait); + timer_setup(&group->rtpoll_timer, poll_timer_fn, 0); + rcu_assign_pointer(group->rtpoll_task, NULL); } void __init psi_init(void) @@ -440,11 +440,11 @@ static u64 update_triggers(struct psi_group *group, u64 now) * On subsequent updates, calculate growth deltas and let * watchers know when their specified thresholds are exceeded. */ - list_for_each_entry(t, &group->triggers, node) { + list_for_each_entry(t, &group->rtpoll_triggers, node) { u64 growth; bool new_stall; - new_stall = group->polling_total[t->state] != total[t->state]; + new_stall = group->rtpoll_total[t->state] != total[t->state]; /* Check for stall activity or a previous threshold breach */ if (!new_stall && !t->pending_event) @@ -486,10 +486,10 @@ static u64 update_triggers(struct psi_group *group, u64 now) } if (update_total) - memcpy(group->polling_total, total, - sizeof(group->polling_total)); + memcpy(group->rtpoll_total, total, + sizeof(group->rtpoll_total)); - return now + group->poll_min_period; + return now + group->rtpoll_min_period; } static u64 update_averages(struct psi_group *group, u64 now) @@ -582,53 +582,53 @@ static void init_triggers(struct psi_group *group, u64 now) { struct psi_trigger *t; - list_for_each_entry(t, &group->triggers, node) + list_for_each_entry(t, &group->rtpoll_triggers, node) window_reset(&t->win, now, group->total[PSI_POLL][t->state], 0); - memcpy(group->polling_total, group->total[PSI_POLL], - sizeof(group->polling_total)); - group->polling_next_update = now + group->poll_min_period; + memcpy(group->rtpoll_total, group->total[PSI_POLL], + sizeof(group->rtpoll_total)); + group->rtpoll_next_update = now + group->rtpoll_min_period; } /* Schedule polling if it's not already scheduled or forced. */ -static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay, +static void psi_schedule_rtpoll_work(struct psi_group *group, unsigned long delay, bool force) { struct task_struct *task; /* * atomic_xchg should be called even when !force to provide a - * full memory barrier (see the comment inside psi_poll_work). + * full memory barrier (see the comment inside psi_rtpoll_work). */ - if (atomic_xchg(&group->poll_scheduled, 1) && !force) + if (atomic_xchg(&group->rtpoll_scheduled, 1) && !force) return; rcu_read_lock(); - task = rcu_dereference(group->poll_task); + task = rcu_dereference(group->rtpoll_task); /* * kworker might be NULL in case psi_trigger_destroy races with * psi_task_change (hotpath) which can't use locks */ if (likely(task)) - mod_timer(&group->poll_timer, jiffies + delay); + mod_timer(&group->rtpoll_timer, jiffies + delay); else - atomic_set(&group->poll_scheduled, 0); + atomic_set(&group->rtpoll_scheduled, 0); rcu_read_unlock(); } -static void psi_poll_work(struct psi_group *group) +static void psi_rtpoll_work(struct psi_group *group) { bool force_reschedule = false; u32 changed_states; u64 now; - mutex_lock(&group->trigger_lock); + mutex_lock(&group->rtpoll_trigger_lock); now = sched_clock(); - if (now > group->polling_until) { + if (now > group->rtpoll_until) { /* * We are either about to start or might stop polling if no * state change was recorded. Resetting poll_scheduled leaves @@ -638,7 +638,7 @@ static void psi_poll_work(struct psi_group *group) * should be negligible and polling_next_update still keeps * updates correctly on schedule. */ - atomic_set(&group->poll_scheduled, 0); + atomic_set(&group->rtpoll_scheduled, 0); /* * A task change can race with the poll worker that is supposed to * report on it. To avoid missing events, ensure ordering between @@ -667,9 +667,9 @@ static void psi_poll_work(struct psi_group *group) collect_percpu_times(group, PSI_POLL, &changed_states); - if (changed_states & group->poll_states) { + if (changed_states & group->rtpoll_states) { /* Initialize trigger windows when entering polling mode */ - if (now > group->polling_until) + if (now > group->rtpoll_until) init_triggers(group, now); /* @@ -677,50 +677,50 @@ static void psi_poll_work(struct psi_group *group) * minimum tracking window as long as monitor states are * changing. */ - group->polling_until = now + - group->poll_min_period * UPDATES_PER_WINDOW; + group->rtpoll_until = now + + group->rtpoll_min_period * UPDATES_PER_WINDOW; } - if (now > group->polling_until) { - group->polling_next_update = ULLONG_MAX; + if (now > group->rtpoll_until) { + group->rtpoll_next_update = ULLONG_MAX; goto out; } - if (now >= group->polling_next_update) - group->polling_next_update = update_triggers(group, now); + if (now >= group->rtpoll_next_update) + group->rtpoll_next_update = update_triggers(group, now); - psi_schedule_poll_work(group, - nsecs_to_jiffies(group->polling_next_update - now) + 1, + psi_schedule_rtpoll_work(group, + nsecs_to_jiffies(group->rtpoll_next_update - now) + 1, force_reschedule); out: - mutex_unlock(&group->trigger_lock); + mutex_unlock(&group->rtpoll_trigger_lock); } -static int psi_poll_worker(void *data) +static int psi_rtpoll_worker(void *data) { struct psi_group *group = (struct psi_group *)data; sched_set_fifo_low(current); while (true) { - wait_event_interruptible(group->poll_wait, - atomic_cmpxchg(&group->poll_wakeup, 1, 0) || + wait_event_interruptible(group->rtpoll_wait, + atomic_cmpxchg(&group->rtpoll_wakeup, 1, 0) || kthread_should_stop()); if (kthread_should_stop()) break; - psi_poll_work(group); + psi_rtpoll_work(group); } return 0; } static void poll_timer_fn(struct timer_list *t) { - struct psi_group *group = from_timer(group, t, poll_timer); + struct psi_group *group = from_timer(group, t, rtpoll_timer); - atomic_set(&group->poll_wakeup, 1); - wake_up_interruptible(&group->poll_wait); + atomic_set(&group->rtpoll_wakeup, 1); + wake_up_interruptible(&group->rtpoll_wait); } static void record_times(struct psi_group_cpu *groupc, u64 now) @@ -851,8 +851,8 @@ static void psi_group_change(struct psi_group *group, int cpu, write_seqcount_end(&groupc->seq); - if (state_mask & group->poll_states) - psi_schedule_poll_work(group, 1, false); + if (state_mask & group->rtpoll_states) + psi_schedule_rtpoll_work(group, 1, false); if (wake_clock && !delayed_work_pending(&group->avgs_work)) schedule_delayed_work(&group->avgs_work, PSI_FREQ); @@ -1005,8 +1005,8 @@ void psi_account_irqtime(struct task_struct *task, u32 delta) write_seqcount_end(&groupc->seq); - if (group->poll_states & (1 << PSI_IRQ_FULL)) - psi_schedule_poll_work(group, 1, false); + if (group->rtpoll_states & (1 << PSI_IRQ_FULL)) + psi_schedule_rtpoll_work(group, 1, false); } while ((group = group->parent)); } #endif @@ -1101,7 +1101,7 @@ void psi_cgroup_free(struct cgroup *cgroup) cancel_delayed_work_sync(&cgroup->psi->avgs_work); free_percpu(cgroup->psi->pcpu); /* All triggers must be removed by now */ - WARN_ONCE(cgroup->psi->poll_states, "psi: trigger leak\n"); + WARN_ONCE(cgroup->psi->rtpoll_states, "psi: trigger leak\n"); kfree(cgroup->psi); } @@ -1302,29 +1302,29 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, init_waitqueue_head(&t->event_wait); t->pending_event = false; - mutex_lock(&group->trigger_lock); + mutex_lock(&group->rtpoll_trigger_lock); - if (!rcu_access_pointer(group->poll_task)) { + if (!rcu_access_pointer(group->rtpoll_task)) { struct task_struct *task; - task = kthread_create(psi_poll_worker, group, "psimon"); + task = kthread_create(psi_rtpoll_worker, group, "psimon"); if (IS_ERR(task)) { kfree(t); - mutex_unlock(&group->trigger_lock); + mutex_unlock(&group->rtpoll_trigger_lock); return ERR_CAST(task); } - atomic_set(&group->poll_wakeup, 0); + atomic_set(&group->rtpoll_wakeup, 0); wake_up_process(task); - rcu_assign_pointer(group->poll_task, task); + rcu_assign_pointer(group->rtpoll_task, task); } - list_add(&t->node, &group->triggers); - group->poll_min_period = min(group->poll_min_period, + list_add(&t->node, &group->rtpoll_triggers); + group->rtpoll_min_period = min(group->rtpoll_min_period, div_u64(t->win.size, UPDATES_PER_WINDOW)); - group->nr_triggers[t->state]++; - group->poll_states |= (1 << t->state); + group->rtpoll_nr_triggers[t->state]++; + group->rtpoll_states |= (1 << t->state); - mutex_unlock(&group->trigger_lock); + mutex_unlock(&group->rtpoll_trigger_lock); return t; } @@ -1349,51 +1349,52 @@ void psi_trigger_destroy(struct psi_trigger *t) */ wake_up_pollfree(&t->event_wait); - mutex_lock(&group->trigger_lock); + mutex_lock(&group->rtpoll_trigger_lock); if (!list_empty(&t->node)) { struct psi_trigger *tmp; u64 period = ULLONG_MAX; list_del(&t->node); - group->nr_triggers[t->state]--; - if (!group->nr_triggers[t->state]) - group->poll_states &= ~(1 << t->state); + group->rtpoll_nr_triggers[t->state]--; + if (!group->rtpoll_nr_triggers[t->state]) + group->rtpoll_states &= ~(1 << t->state); /* reset min update period for the remaining triggers */ - list_for_each_entry(tmp, &group->triggers, node) + list_for_each_entry(tmp, &group->rtpoll_triggers, node) period = min(period, div_u64(tmp->win.size, UPDATES_PER_WINDOW)); - group->poll_min_period = period; - /* Destroy poll_task when the last trigger is destroyed */ - if (group->poll_states == 0) { - group->polling_until = 0; + group->rtpoll_min_period = period; + /* Destroy rtpoll_task when the last trigger is destroyed */ + if (group->rtpoll_states == 0) { + group->rtpoll_until = 0; task_to_destroy = rcu_dereference_protected( - group->poll_task, - lockdep_is_held(&group->trigger_lock)); - rcu_assign_pointer(group->poll_task, NULL); - del_timer(&group->poll_timer); + group->rtpoll_task, + lockdep_is_held(&group->rtpoll_trigger_lock)); + rcu_assign_pointer(group->rtpoll_task, NULL); + del_timer(&group->rtpoll_timer); } } - mutex_unlock(&group->trigger_lock); + mutex_unlock(&group->rtpoll_trigger_lock); /* - * Wait for psi_schedule_poll_work RCU to complete its read-side + * Wait for psi_schedule_rtpoll_work RCU to complete its read-side * critical section before destroying the trigger and optionally the - * poll_task. + * rtpoll_task. */ synchronize_rcu(); /* - * Stop kthread 'psimon' after releasing trigger_lock to prevent a - * deadlock while waiting for psi_poll_work to acquire trigger_lock + * Stop kthread 'psimon' after releasing rtpoll_trigger_lock to prevent + * a deadlock while waiting for psi_rtpoll_work to acquire + * rtpoll_trigger_lock */ if (task_to_destroy) { /* * After the RCU grace period has expired, the worker - * can no longer be found through group->poll_task. + * can no longer be found through group->rtpoll_task. */ kthread_stop(task_to_destroy); - atomic_set(&group->poll_scheduled, 0); + atomic_set(&group->rtpoll_scheduled, 0); } kfree(t); } -- GitLab From 4468fcae49f08e88fbbffe05b29496192df89991 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:17 +0200 Subject: [PATCH 2040/5631] sched/psi: Extract update_triggers side effect This change moves update_total flag out of update_triggers function, currently called only in psi_poll_work. In the next patch, update_triggers will be called also in psi_avgs_work, but the total update information is specific to psi_poll_work. Returning update_total value to the caller let us avoid differentiating the implementation of update_triggers for different aggregators. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-4-cerasuolodomenico@gmail.com --- kernel/sched/psi.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a3d0b5cf797a..f3df6a8ff493 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -430,11 +430,11 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) return growth; } -static u64 update_triggers(struct psi_group *group, u64 now) +static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total) { struct psi_trigger *t; - bool update_total = false; u64 *total = group->total[PSI_POLL]; + *update_total = false; /* * On subsequent updates, calculate growth deltas and let @@ -462,7 +462,7 @@ static u64 update_triggers(struct psi_group *group, u64 now) * been through all of them. Also remember to extend the * polling time if we see new stall activity. */ - update_total = true; + *update_total = true; /* Calculate growth since last update */ growth = window_update(&t->win, now, total[t->state]); @@ -485,10 +485,6 @@ static u64 update_triggers(struct psi_group *group, u64 now) t->pending_event = false; } - if (update_total) - memcpy(group->rtpoll_total, total, - sizeof(group->rtpoll_total)); - return now + group->rtpoll_min_period; } @@ -622,6 +618,7 @@ static void psi_rtpoll_work(struct psi_group *group) { bool force_reschedule = false; u32 changed_states; + bool update_total; u64 now; mutex_lock(&group->rtpoll_trigger_lock); @@ -686,8 +683,12 @@ static void psi_rtpoll_work(struct psi_group *group) goto out; } - if (now >= group->rtpoll_next_update) - group->rtpoll_next_update = update_triggers(group, now); + if (now >= group->rtpoll_next_update) { + group->rtpoll_next_update = update_triggers(group, now, &update_total); + if (update_total) + memcpy(group->rtpoll_total, group->total[PSI_POLL], + sizeof(group->rtpoll_total)); + } psi_schedule_rtpoll_work(group, nsecs_to_jiffies(group->rtpoll_next_update - now) + 1, -- GitLab From d82caa273565b45fcf103148950549af76c314b0 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Thu, 30 Mar 2023 12:54:18 +0200 Subject: [PATCH 2041/5631] sched/psi: Allow unprivileged polling of N*2s period PSI offers 2 mechanisms to get information about a specific resource pressure. One is reading from /proc/pressure/, which gives average pressures aggregated every 2s. The other is creating a pollable fd for a specific resource and cgroup. The trigger creation requires CAP_SYS_RESOURCE, and gives the possibility to pick specific time window and threshold, spawing an RT thread to aggregate the data. Systemd would like to provide containers the option to monitor pressure on their own cgroup and sub-cgroups. For example, if systemd launches a container that itself then launches services, the container should have the ability to poll() for pressure in individual services. But neither the container nor the services are privileged. This patch implements a mechanism to allow unprivileged users to create pressure triggers. The difference with privileged triggers creation is that unprivileged ones must have a time window that's a multiple of 2s. This is so that we can avoid unrestricted spawning of rt threads, and use instead the same aggregation mechanism done for the averages, which runs independently of any triggers. Suggested-by: Johannes Weiner Signed-off-by: Domenico Cerasuolo Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20230330105418.77061-5-cerasuolodomenico@gmail.com --- Documentation/accounting/psi.rst | 4 + include/linux/psi.h | 2 +- include/linux/psi_types.h | 7 ++ kernel/cgroup/cgroup.c | 2 +- kernel/sched/psi.c | 175 +++++++++++++++++++------------ 5 files changed, 121 insertions(+), 69 deletions(-) diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst index 5e40b3f437f9..df6062eb3abb 100644 --- a/Documentation/accounting/psi.rst +++ b/Documentation/accounting/psi.rst @@ -105,6 +105,10 @@ prevent overly frequent polling. Max limit is chosen as a high enough number after which monitors are most likely not needed and psi averages can be used instead. +Unprivileged users can also create monitors, with the only limitation that the +window size must be a multiple of 2s, in order to prevent excessive resource +usage. + When activated, psi monitor stays active for at least the duration of one tracking window to avoid repeated activations/deactivations when system is bouncing in and out of the stall state. diff --git a/include/linux/psi.h b/include/linux/psi.h index b029a847def1..ab26200c2803 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res); + char *buf, enum psi_res res, struct file *file); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1819afa8b198..040c089581c6 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,9 @@ struct psi_trigger { /* Deferred event(s) from previous ratelimit window */ bool pending_event; + + /* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */ + enum psi_aggregators aggregator; }; struct psi_group { @@ -171,6 +174,10 @@ struct psi_group { /* Aggregator work control */ struct delayed_work avgs_work; + /* Unprivileged triggers against N*PSI_FREQ windows */ + struct list_head avg_triggers; + u32 avg_nr_triggers[NR_PSI_STATES - 1]; + /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 935e8121b21e..dead36969bba 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3761,7 +3761,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_psi(cgrp); - new = psi_trigger_create(psi, buf, res); + new = psi_trigger_create(psi, buf, res, of->file); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index f3df6a8ff493..e072f6b31bf3 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -186,9 +186,14 @@ static void group_init(struct psi_group *group) seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); group->avg_last_update = sched_clock(); group->avg_next_update = group->avg_last_update + psi_period; - INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); mutex_init(&group->avgs_lock); - /* Init trigger-related members */ + + /* Init avg trigger-related members */ + INIT_LIST_HEAD(&group->avg_triggers); + memset(group->avg_nr_triggers, 0, sizeof(group->avg_nr_triggers)); + INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); + + /* Init rtpoll trigger-related members */ atomic_set(&group->rtpoll_scheduled, 0); mutex_init(&group->rtpoll_trigger_lock); INIT_LIST_HEAD(&group->rtpoll_triggers); @@ -430,21 +435,32 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value) return growth; } -static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total) +static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total, + enum psi_aggregators aggregator) { struct psi_trigger *t; - u64 *total = group->total[PSI_POLL]; + u64 *total = group->total[aggregator]; + struct list_head *triggers; + u64 *aggregator_total; *update_total = false; + if (aggregator == PSI_AVGS) { + triggers = &group->avg_triggers; + aggregator_total = group->avg_total; + } else { + triggers = &group->rtpoll_triggers; + aggregator_total = group->rtpoll_total; + } + /* * On subsequent updates, calculate growth deltas and let * watchers know when their specified thresholds are exceeded. */ - list_for_each_entry(t, &group->rtpoll_triggers, node) { + list_for_each_entry(t, triggers, node) { u64 growth; bool new_stall; - new_stall = group->rtpoll_total[t->state] != total[t->state]; + new_stall = aggregator_total[t->state] != total[t->state]; /* Check for stall activity or a previous threshold breach */ if (!new_stall && !t->pending_event) @@ -546,6 +562,7 @@ static void psi_avgs_work(struct work_struct *work) struct delayed_work *dwork; struct psi_group *group; u32 changed_states; + bool update_total; u64 now; dwork = to_delayed_work(work); @@ -563,8 +580,10 @@ static void psi_avgs_work(struct work_struct *work) * Once restarted, we'll catch up the running averages in one * go - see calc_avgs() and missed_periods. */ - if (now >= group->avg_next_update) + if (now >= group->avg_next_update) { + update_triggers(group, now, &update_total, PSI_AVGS); group->avg_next_update = update_averages(group, now); + } if (changed_states & PSI_STATE_RESCHEDULE) { schedule_delayed_work(dwork, nsecs_to_jiffies( @@ -574,7 +593,7 @@ static void psi_avgs_work(struct work_struct *work) mutex_unlock(&group->avgs_lock); } -static void init_triggers(struct psi_group *group, u64 now) +static void init_rtpoll_triggers(struct psi_group *group, u64 now) { struct psi_trigger *t; @@ -667,7 +686,7 @@ static void psi_rtpoll_work(struct psi_group *group) if (changed_states & group->rtpoll_states) { /* Initialize trigger windows when entering polling mode */ if (now > group->rtpoll_until) - init_triggers(group, now); + init_rtpoll_triggers(group, now); /* * Keep the monitor active for at least the duration of the @@ -684,7 +703,7 @@ static void psi_rtpoll_work(struct psi_group *group) } if (now >= group->rtpoll_next_update) { - group->rtpoll_next_update = update_triggers(group, now, &update_total); + group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL); if (update_total) memcpy(group->rtpoll_total, group->total[PSI_POLL], sizeof(group->rtpoll_total)); @@ -1254,16 +1273,23 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res) + char *buf, enum psi_res res, struct file *file) { struct psi_trigger *t; enum psi_states state; u32 threshold_us; + bool privileged; u32 window_us; if (static_branch_likely(&psi_disabled)) return ERR_PTR(-EOPNOTSUPP); + /* + * Checking the privilege here on file->f_cred implies that a privileged user + * could open the file and delegate the write to an unprivileged one. + */ + privileged = cap_raised(file->f_cred->cap_effective, CAP_SYS_RESOURCE); + if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2) state = PSI_IO_SOME + res * 2; else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2) @@ -1283,6 +1309,13 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, window_us > WINDOW_MAX_US) return ERR_PTR(-EINVAL); + /* + * Unprivileged users can only use 2s windows so that averages aggregation + * work is used, and no RT threads need to be spawned. + */ + if (!privileged && window_us % 2000000) + return ERR_PTR(-EINVAL); + /* Check threshold */ if (threshold_us == 0 || threshold_us > window_us) return ERR_PTR(-EINVAL); @@ -1302,31 +1335,40 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->last_event_time = 0; init_waitqueue_head(&t->event_wait); t->pending_event = false; + t->aggregator = privileged ? PSI_POLL : PSI_AVGS; - mutex_lock(&group->rtpoll_trigger_lock); + if (privileged) { + mutex_lock(&group->rtpoll_trigger_lock); - if (!rcu_access_pointer(group->rtpoll_task)) { - struct task_struct *task; + if (!rcu_access_pointer(group->rtpoll_task)) { + struct task_struct *task; - task = kthread_create(psi_rtpoll_worker, group, "psimon"); - if (IS_ERR(task)) { - kfree(t); - mutex_unlock(&group->rtpoll_trigger_lock); - return ERR_CAST(task); + task = kthread_create(psi_rtpoll_worker, group, "psimon"); + if (IS_ERR(task)) { + kfree(t); + mutex_unlock(&group->rtpoll_trigger_lock); + return ERR_CAST(task); + } + atomic_set(&group->rtpoll_wakeup, 0); + wake_up_process(task); + rcu_assign_pointer(group->rtpoll_task, task); } - atomic_set(&group->rtpoll_wakeup, 0); - wake_up_process(task); - rcu_assign_pointer(group->rtpoll_task, task); - } - list_add(&t->node, &group->rtpoll_triggers); - group->rtpoll_min_period = min(group->rtpoll_min_period, - div_u64(t->win.size, UPDATES_PER_WINDOW)); - group->rtpoll_nr_triggers[t->state]++; - group->rtpoll_states |= (1 << t->state); + list_add(&t->node, &group->rtpoll_triggers); + group->rtpoll_min_period = min(group->rtpoll_min_period, + div_u64(t->win.size, UPDATES_PER_WINDOW)); + group->rtpoll_nr_triggers[t->state]++; + group->rtpoll_states |= (1 << t->state); - mutex_unlock(&group->rtpoll_trigger_lock); + mutex_unlock(&group->rtpoll_trigger_lock); + } else { + mutex_lock(&group->avgs_lock); + + list_add(&t->node, &group->avg_triggers); + group->avg_nr_triggers[t->state]++; + mutex_unlock(&group->avgs_lock); + } return t; } @@ -1350,34 +1392,41 @@ void psi_trigger_destroy(struct psi_trigger *t) */ wake_up_pollfree(&t->event_wait); - mutex_lock(&group->rtpoll_trigger_lock); - - if (!list_empty(&t->node)) { - struct psi_trigger *tmp; - u64 period = ULLONG_MAX; - - list_del(&t->node); - group->rtpoll_nr_triggers[t->state]--; - if (!group->rtpoll_nr_triggers[t->state]) - group->rtpoll_states &= ~(1 << t->state); - /* reset min update period for the remaining triggers */ - list_for_each_entry(tmp, &group->rtpoll_triggers, node) - period = min(period, div_u64(tmp->win.size, - UPDATES_PER_WINDOW)); - group->rtpoll_min_period = period; - /* Destroy rtpoll_task when the last trigger is destroyed */ - if (group->rtpoll_states == 0) { - group->rtpoll_until = 0; - task_to_destroy = rcu_dereference_protected( - group->rtpoll_task, - lockdep_is_held(&group->rtpoll_trigger_lock)); - rcu_assign_pointer(group->rtpoll_task, NULL); - del_timer(&group->rtpoll_timer); + if (t->aggregator == PSI_AVGS) { + mutex_lock(&group->avgs_lock); + if (!list_empty(&t->node)) { + list_del(&t->node); + group->avg_nr_triggers[t->state]--; } + mutex_unlock(&group->avgs_lock); + } else { + mutex_lock(&group->rtpoll_trigger_lock); + if (!list_empty(&t->node)) { + struct psi_trigger *tmp; + u64 period = ULLONG_MAX; + + list_del(&t->node); + group->rtpoll_nr_triggers[t->state]--; + if (!group->rtpoll_nr_triggers[t->state]) + group->rtpoll_states &= ~(1 << t->state); + /* reset min update period for the remaining triggers */ + list_for_each_entry(tmp, &group->rtpoll_triggers, node) + period = min(period, div_u64(tmp->win.size, + UPDATES_PER_WINDOW)); + group->rtpoll_min_period = period; + /* Destroy rtpoll_task when the last trigger is destroyed */ + if (group->rtpoll_states == 0) { + group->rtpoll_until = 0; + task_to_destroy = rcu_dereference_protected( + group->rtpoll_task, + lockdep_is_held(&group->rtpoll_trigger_lock)); + rcu_assign_pointer(group->rtpoll_task, NULL); + del_timer(&group->rtpoll_timer); + } + } + mutex_unlock(&group->rtpoll_trigger_lock); } - mutex_unlock(&group->rtpoll_trigger_lock); - /* * Wait for psi_schedule_rtpoll_work RCU to complete its read-side * critical section before destroying the trigger and optionally the @@ -1437,27 +1486,19 @@ static int psi_cpu_show(struct seq_file *m, void *v) return psi_show(m, &psi_system, PSI_CPU); } -static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) -{ - if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return single_open(file, psi_show, NULL); -} - static int psi_io_open(struct inode *inode, struct file *file) { - return psi_open(file, psi_io_show); + return single_open(file, psi_io_show, NULL); } static int psi_memory_open(struct inode *inode, struct file *file) { - return psi_open(file, psi_memory_show); + return single_open(file, psi_memory_show, NULL); } static int psi_cpu_open(struct inode *inode, struct file *file) { - return psi_open(file, psi_cpu_show); + return single_open(file, psi_cpu_show, NULL); } static ssize_t psi_write(struct file *file, const char __user *user_buf, @@ -1491,7 +1532,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, res); + new = psi_trigger_create(&psi_system, buf, res, file); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); @@ -1571,7 +1612,7 @@ static int psi_irq_show(struct seq_file *m, void *v) static int psi_irq_open(struct inode *inode, struct file *file) { - return psi_open(file, psi_irq_show); + return single_open(file, psi_irq_show, NULL); } static ssize_t psi_irq_write(struct file *file, const char __user *user_buf, -- GitLab From db9947cea855eb0b0cbf9724a3aa69f7b39b3d73 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 3 Apr 2023 11:41:10 +0200 Subject: [PATCH 2042/5631] MIPS: mm: Remove unused *cache_page_indexed flush functions The *cache_page_indexed flush functions are no (longer) used. Signed-off-by: Thomas Bogendoerfer --- arch/mips/mm/c-r4k.c | 100 ------------------------------------------- 1 file changed, 100 deletions(-) diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5599b9c9a737..dd31b1007919 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -187,24 +187,6 @@ static void r4k_blast_dcache_user_page_setup(void) #endif -static void (* r4k_blast_dcache_page_indexed)(unsigned long addr); - -static void r4k_blast_dcache_page_indexed_setup(void) -{ - unsigned long dc_lsize = cpu_dcache_line_size(); - - if (dc_lsize == 0) - r4k_blast_dcache_page_indexed = (void *)cache_noop; - else if (dc_lsize == 16) - r4k_blast_dcache_page_indexed = blast_dcache16_page_indexed; - else if (dc_lsize == 32) - r4k_blast_dcache_page_indexed = blast_dcache32_page_indexed; - else if (dc_lsize == 64) - r4k_blast_dcache_page_indexed = blast_dcache64_page_indexed; - else if (dc_lsize == 128) - r4k_blast_dcache_page_indexed = blast_dcache128_page_indexed; -} - void (* r4k_blast_dcache)(void); EXPORT_SYMBOL(r4k_blast_dcache); @@ -266,39 +248,6 @@ static inline void tx49_blast_icache32(void) addr | ws, 32); } -static inline void blast_icache32_r4600_v1_page_indexed(unsigned long page) -{ - unsigned long flags; - - local_irq_save(flags); - blast_icache32_page_indexed(page); - local_irq_restore(flags); -} - -static inline void tx49_blast_icache32_page_indexed(unsigned long page) -{ - unsigned long indexmask = current_cpu_data.icache.waysize - 1; - unsigned long start = INDEX_BASE + (page & indexmask); - unsigned long end = start + PAGE_SIZE; - unsigned long ws_inc = 1UL << current_cpu_data.icache.waybit; - unsigned long ws_end = current_cpu_data.icache.ways << - current_cpu_data.icache.waybit; - unsigned long ws, addr; - - CACHE32_UNROLL32_ALIGN2; - /* I'm in even chunk. blast odd chunks */ - for (ws = 0; ws < ws_end; ws += ws_inc) - for (addr = start + 0x400; addr < end; addr += 0x400 * 2) - cache_unroll(32, kernel_cache, Index_Invalidate_I, - addr | ws, 32); - CACHE32_UNROLL32_ALIGN; - /* I'm in odd chunk. blast even chunks */ - for (ws = 0; ws < ws_end; ws += ws_inc) - for (addr = start; addr < end; addr += 0x400 * 2) - cache_unroll(32, kernel_cache, Index_Invalidate_I, - addr | ws, 32); -} - static void (* r4k_blast_icache_page)(unsigned long addr); static void r4k_blast_icache_page_setup(void) @@ -341,34 +290,6 @@ static void r4k_blast_icache_user_page_setup(void) #endif -static void (* r4k_blast_icache_page_indexed)(unsigned long addr); - -static void r4k_blast_icache_page_indexed_setup(void) -{ - unsigned long ic_lsize = cpu_icache_line_size(); - - if (ic_lsize == 0) - r4k_blast_icache_page_indexed = (void *)cache_noop; - else if (ic_lsize == 16) - r4k_blast_icache_page_indexed = blast_icache16_page_indexed; - else if (ic_lsize == 32) { - if (IS_ENABLED(CONFIG_WAR_R4600_V1_INDEX_ICACHEOP) && - cpu_is_r4600_v1_x()) - r4k_blast_icache_page_indexed = - blast_icache32_r4600_v1_page_indexed; - else if (IS_ENABLED(CONFIG_WAR_TX49XX_ICACHE_INDEX_INV)) - r4k_blast_icache_page_indexed = - tx49_blast_icache32_page_indexed; - else if (current_cpu_type() == CPU_LOONGSON2EF) - r4k_blast_icache_page_indexed = - loongson2_blast_icache32_page_indexed; - else - r4k_blast_icache_page_indexed = - blast_icache32_page_indexed; - } else if (ic_lsize == 64) - r4k_blast_icache_page_indexed = blast_icache64_page_indexed; -} - void (* r4k_blast_icache)(void); EXPORT_SYMBOL(r4k_blast_icache); @@ -414,24 +335,6 @@ static void r4k_blast_scache_page_setup(void) r4k_blast_scache_page = blast_scache128_page; } -static void (* r4k_blast_scache_page_indexed)(unsigned long addr); - -static void r4k_blast_scache_page_indexed_setup(void) -{ - unsigned long sc_lsize = cpu_scache_line_size(); - - if (scache_size == 0) - r4k_blast_scache_page_indexed = (void *)cache_noop; - else if (sc_lsize == 16) - r4k_blast_scache_page_indexed = blast_scache16_page_indexed; - else if (sc_lsize == 32) - r4k_blast_scache_page_indexed = blast_scache32_page_indexed; - else if (sc_lsize == 64) - r4k_blast_scache_page_indexed = blast_scache64_page_indexed; - else if (sc_lsize == 128) - r4k_blast_scache_page_indexed = blast_scache128_page_indexed; -} - static void (* r4k_blast_scache)(void); static void r4k_blast_scache_setup(void) @@ -1807,13 +1710,10 @@ void r4k_cache_init(void) setup_scache(); r4k_blast_dcache_page_setup(); - r4k_blast_dcache_page_indexed_setup(); r4k_blast_dcache_setup(); r4k_blast_icache_page_setup(); - r4k_blast_icache_page_indexed_setup(); r4k_blast_icache_setup(); r4k_blast_scache_page_setup(); - r4k_blast_scache_page_indexed_setup(); r4k_blast_scache_setup(); r4k_blast_scache_node_setup(); #ifdef CONFIG_EVA -- GitLab From 461ba3e7e663a5c87e7b388b073904149b199593 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 3 Apr 2023 11:41:11 +0200 Subject: [PATCH 2043/5631] MIPS: Remove no longer used ide.h There are only three drivers left using ide.h, which are all m68k only. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/ide.h | 13 --- arch/mips/include/asm/mach-generic/ide.h | 138 ----------------------- 2 files changed, 151 deletions(-) delete mode 100644 arch/mips/include/asm/ide.h delete mode 100644 arch/mips/include/asm/mach-generic/ide.h diff --git a/arch/mips/include/asm/ide.h b/arch/mips/include/asm/ide.h deleted file mode 100644 index bb674c3b0303..000000000000 --- a/arch/mips/include/asm/ide.h +++ /dev/null @@ -1,13 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * This file contains the MIPS architecture specific IDE code. - */ -#ifndef __ASM_IDE_H -#define __ASM_IDE_H - -#include - -#endif /* __ASM_IDE_H */ diff --git a/arch/mips/include/asm/mach-generic/ide.h b/arch/mips/include/asm/mach-generic/ide.h deleted file mode 100644 index 4ae5fbcb15a5..000000000000 --- a/arch/mips/include/asm/mach-generic/ide.h +++ /dev/null @@ -1,138 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1994-1996 Linus Torvalds & authors - * - * Copied from i386; many of the especially older MIPS or ISA-based platforms - * are basically identical. Using this file probably implies i8259 PIC - * support in a system but the very least interrupt numbers 0 - 15 need to - * be put aside for legacy devices. - */ -#ifndef __ASM_MACH_GENERIC_IDE_H -#define __ASM_MACH_GENERIC_IDE_H - -#ifdef __KERNEL__ - -#include -#include -#include - -/* MIPS port and memory-mapped I/O string operations. */ -static inline void __ide_flush_prologue(void) -{ -#ifdef CONFIG_SMP - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) - preempt_disable(); -#endif -} - -static inline void __ide_flush_epilogue(void) -{ -#ifdef CONFIG_SMP - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) - preempt_enable(); -#endif -} - -static inline void __ide_flush_dcache_range(unsigned long addr, unsigned long size) -{ - if (cpu_has_dc_aliases || !cpu_has_ic_fills_f_dc) { - unsigned long end = addr + size; - - while (addr < end) { - local_flush_data_cache_page((void *)addr); - addr += PAGE_SIZE; - } - } -} - -/* - * insw() and gang might be called with interrupts disabled, so we can't - * send IPIs for flushing due to the potencial of deadlocks, see the comment - * above smp_call_function() in arch/mips/kernel/smp.c. We work around the - * problem by disabling preemption so we know we actually perform the flush - * on the processor that actually has the lines to be flushed which hopefully - * is even better for performance anyway. - */ -static inline void __ide_insw(unsigned long port, void *addr, - unsigned int count) -{ - __ide_flush_prologue(); - insw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_insl(unsigned long port, void *addr, unsigned int count) -{ - __ide_flush_prologue(); - insl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_outsw(unsigned long port, const void *addr, - unsigned long count) -{ - __ide_flush_prologue(); - outsw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_outsl(unsigned long port, const void *addr, - unsigned long count) -{ - __ide_flush_prologue(); - outsl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_insw(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - readsw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_insl(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - readsl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_outsw(void __iomem *port, void *addr, u32 count) -{ - __ide_flush_prologue(); - writesw(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 2); - __ide_flush_epilogue(); -} - -static inline void __ide_mm_outsl(void __iomem * port, void *addr, u32 count) -{ - __ide_flush_prologue(); - writesl(port, addr, count); - __ide_flush_dcache_range((unsigned long)addr, count * 4); - __ide_flush_epilogue(); -} - -/* ide_insw calls insw, not __ide_insw. Why? */ -#undef insw -#undef insl -#undef outsw -#undef outsl -#define insw(port, addr, count) __ide_insw(port, addr, count) -#define insl(port, addr, count) __ide_insl(port, addr, count) -#define outsw(port, addr, count) __ide_outsw(port, addr, count) -#define outsl(port, addr, count) __ide_outsl(port, addr, count) - -#endif /* __KERNEL__ */ - -#endif /* __ASM_MACH_GENERIC_IDE_H */ -- GitLab From c86df6c0d4fee0028bb208705bcceae548164fde Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Mon, 3 Apr 2023 11:41:12 +0200 Subject: [PATCH 2044/5631] MIPS: mm: Remove local_cache_flush_page After ide.h is gone, there are no users of local_cache_flush_page() left. Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/cacheflush.h | 1 - arch/mips/mm/c-r3k.c | 5 ----- arch/mips/mm/c-r4k.c | 3 --- arch/mips/mm/cache.c | 2 -- 4 files changed, 11 deletions(-) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index b3dc9c589442..d8d3f80f9fc0 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -110,7 +110,6 @@ extern void copy_from_user_page(struct vm_area_struct *vma, unsigned long len); extern void (*flush_icache_all)(void); -extern void (*local_flush_data_cache_page)(void * addr); extern void (*flush_data_cache_page)(unsigned long addr); /* Run kernel code uncached, useful for cache probing functions. */ diff --git a/arch/mips/mm/c-r3k.c b/arch/mips/mm/c-r3k.c index df6755ca1892..5869df848fab 100644 --- a/arch/mips/mm/c-r3k.c +++ b/arch/mips/mm/c-r3k.c @@ -261,10 +261,6 @@ static void r3k_flush_cache_page(struct vm_area_struct *vma, r3k_flush_icache_range(kaddr, kaddr + PAGE_SIZE); } -static void local_r3k_flush_data_cache_page(void *addr) -{ -} - static void r3k_flush_data_cache_page(unsigned long addr) { } @@ -302,7 +298,6 @@ void r3k_cache_init(void) __flush_kernel_vmap_range = r3k_flush_kernel_vmap_range; - local_flush_data_cache_page = local_r3k_flush_data_cache_page; flush_data_cache_page = r3k_flush_data_cache_page; _dma_cache_wback_inv = r3k_dma_cache_wback_inv; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index dd31b1007919..4b6554b48923 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -1745,7 +1745,6 @@ void r4k_cache_init(void) __flush_kernel_vmap_range = r4k_flush_kernel_vmap_range; flush_icache_all = r4k_flush_icache_all; - local_flush_data_cache_page = local_r4k_flush_data_cache_page; flush_data_cache_page = r4k_flush_data_cache_page; flush_icache_range = r4k_flush_icache_range; local_flush_icache_range = local_r4k_flush_icache_range; @@ -1788,7 +1787,6 @@ void r4k_cache_init(void) /* I$ fills from D$ just by emptying the write buffers */ flush_cache_page = (void *)b5k_instruction_hazard; flush_cache_range = (void *)b5k_instruction_hazard; - local_flush_data_cache_page = (void *)b5k_instruction_hazard; flush_data_cache_page = (void *)b5k_instruction_hazard; flush_icache_range = (void *)b5k_instruction_hazard; local_flush_icache_range = (void *)b5k_instruction_hazard; @@ -1808,7 +1806,6 @@ void r4k_cache_init(void) flush_cache_range = (void *)cache_noop; flush_icache_all = (void *)cache_noop; flush_data_cache_page = (void *)cache_noop; - local_flush_data_cache_page = (void *)cache_noop; break; } } diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 7dba4b5c02c3..d21cf8c6cf6c 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -49,11 +49,9 @@ void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size); EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range); /* MIPS specific cache operations */ -void (*local_flush_data_cache_page)(void * addr); void (*flush_data_cache_page)(unsigned long addr); void (*flush_icache_all)(void); -EXPORT_SYMBOL_GPL(local_flush_data_cache_page); EXPORT_SYMBOL(flush_data_cache_page); EXPORT_SYMBOL(flush_icache_all); -- GitLab From 275aca650e76e203e3efc71835d7195e18d2e718 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 4 Apr 2023 14:18:41 -0700 Subject: [PATCH 2045/5631] MIPS: Drop unused positional parameter in local_irq_{dis,en}able When building with clang's integrated assembler, it points out that the CONFIG_CPU_HAS_DIEI versions of local_irq_enable and local_irq_disable have a named parameter that is not used in the body of the macro and it thinks that $8 is a positional parameter, rather than a register: arch/mips/include/asm/asmmacro.h:48:2: warning: macro defined with named parameters which are not used in macro body, possible positional parameter found in body which will have no effect .macro local_irq_enable reg=$8 ^ The comment above the function that performs this check in LLVM notes that the warning may trigger in this case, even though it is not problematic. It is easy enough to clean this up by just omitting the named parameter for this version of the macro, as it is entirely unused. Reported-by: Nick Desaulniers Link: https://github.com/ClangBuiltLinux/linux/issues/1415 Link: https://github.com/llvm/llvm-project/commit/81c944cadb7f9e55b3517b7423a820e2577b9279 Signed-off-by: Nathan Chancellor Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/asmmacro.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 1c4438f3f2ab..067a635d3bc8 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -45,12 +45,12 @@ #endif #ifdef CONFIG_CPU_HAS_DIEI - .macro local_irq_enable reg=t0 + .macro local_irq_enable ei irq_enable_hazard .endm - .macro local_irq_disable reg=t0 + .macro local_irq_disable di irq_disable_hazard .endm -- GitLab From 045c340c86f8a9d7cb675e179dc6297caa6ebc01 Mon Sep 17 00:00:00 2001 From: Aleksander Jan Bajkowski Date: Wed, 29 Mar 2023 23:03:28 +0200 Subject: [PATCH 2046/5631] MIPS: lantiq: remove unused function declaration The removed function declaration is a leftover of the old gphy firmware loader, that has been removed in d5103604f78e1afc29e586785af540c82b573f3a. Signed-off-by: Aleksander Jan Bajkowski Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h index 4790cfa190d6..c2e0acb755cd 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h +++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_soc.h @@ -94,9 +94,6 @@ extern __iomem void *ltq_cgu_membase; #define LTQ_MPS_BASE_ADDR (KSEG1 + 0x1F107000) #define LTQ_MPS_CHIPID ((u32 *)(LTQ_MPS_BASE_ADDR + 0x0344)) -/* allow booting xrx200 phys */ -int xrx200_gphy_boot(struct device *dev, unsigned int id, dma_addr_t dev_addr); - /* request a non-gpio and set the PIO config */ #define PMU_PPE BIT(13) extern void ltq_pmu_enable(unsigned int module); -- GitLab From b2d110cd5d28ded813f060b735cd68bfe2e5010f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:51 +0100 Subject: [PATCH 2047/5631] interconnect: drop unused icc_link_destroy() interface Now that the link array is deallocated when destroying nodes and the explicit link removal has been dropped from the exynos driver there are no further users of and no need for the icc_link_destroy() interface. Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230306075651.2449-24-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 46 --------------------------- include/linux/interconnect-provider.h | 6 ---- 2 files changed, 52 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index da456329c524..0edf85ba055e 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -910,52 +910,6 @@ int icc_link_create(struct icc_node *node, const int dst_id) } EXPORT_SYMBOL_GPL(icc_link_create); -/** - * icc_link_destroy() - destroy a link between two nodes - * @src: pointer to source node - * @dst: pointer to destination node - * - * Return: 0 on success, or an error code otherwise - */ -int icc_link_destroy(struct icc_node *src, struct icc_node *dst) -{ - struct icc_node **new; - size_t slot; - int ret = 0; - - if (IS_ERR_OR_NULL(src)) - return -EINVAL; - - if (IS_ERR_OR_NULL(dst)) - return -EINVAL; - - mutex_lock(&icc_lock); - - for (slot = 0; slot < src->num_links; slot++) - if (src->links[slot] == dst) - break; - - if (WARN_ON(slot == src->num_links)) { - ret = -ENXIO; - goto out; - } - - src->links[slot] = src->links[--src->num_links]; - - new = krealloc(src->links, src->num_links * sizeof(*src->links), - GFP_KERNEL); - if (new) - src->links = new; - else - ret = -ENOMEM; - -out: - mutex_unlock(&icc_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(icc_link_destroy); - /** * icc_node_add() - add interconnect node to interconnect provider * @node: pointer to the interconnect node diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index b9af9016a95e..e6d8aca6886d 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -118,7 +118,6 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); int icc_link_create(struct icc_node *node, const int dst_id); -int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); @@ -150,11 +149,6 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id) return -ENOTSUPP; } -static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst) -{ - return -ENOTSUPP; -} - static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider) { } -- GitLab From 72b2720c18ecde92e6a36c4ac897dd5848e3f379 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 13 Mar 2023 09:49:53 +0100 Subject: [PATCH 2048/5631] interconnect: qcom: rpm: drop bogus pm domain attach Any power domain would already have been attached by the platform bus code so drop the bogus power domain attach which always succeeds from probe. This effectively reverts commit 7de109c0abe9 ("interconnect: icc-rpm: Add support for bus power domain"). Fixes: 7de109c0abe9 ("interconnect: icc-rpm: Add support for bus power domain") Cc: Yassine Oudjana Signed-off-by: Johan Hovold Tested-by: Konrad Dybcio # MSM8996 Sony Kagura Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230313084953.24088-3-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpm.c | 7 ------- drivers/interconnect/qcom/icc-rpm.h | 1 - drivers/interconnect/qcom/msm8996.c | 1 - 3 files changed, 9 deletions(-) diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index 4180a06681b2..c80819557923 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -496,12 +495,6 @@ int qnoc_probe(struct platform_device *pdev) if (ret) return ret; - if (desc->has_bus_pd) { - ret = dev_pm_domain_attach(dev, true); - if (ret) - return ret; - } - provider = &qp->provider; provider->dev = dev; provider->set = qcom_icc_set; diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h index a49af844ab13..02257b0d3d5c 100644 --- a/drivers/interconnect/qcom/icc-rpm.h +++ b/drivers/interconnect/qcom/icc-rpm.h @@ -91,7 +91,6 @@ struct qcom_icc_desc { size_t num_nodes; const char * const *clocks; size_t num_clocks; - bool has_bus_pd; enum qcom_icc_type type; const struct regmap_config *regmap_cfg; unsigned int qos_offset; diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c index 25a1a32bc611..14efd2761b7a 100644 --- a/drivers/interconnect/qcom/msm8996.c +++ b/drivers/interconnect/qcom/msm8996.c @@ -1823,7 +1823,6 @@ static const struct qcom_icc_desc msm8996_a0noc = { .num_nodes = ARRAY_SIZE(a0noc_nodes), .clocks = bus_a0noc_clocks, .num_clocks = ARRAY_SIZE(bus_a0noc_clocks), - .has_bus_pd = true, .regmap_cfg = &msm8996_a0noc_regmap_config }; -- GitLab From 1d779317eb6529d89bfe6d7900a2cf9e03149aeb Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Mar 2023 22:40:07 +0100 Subject: [PATCH 2049/5631] interconnect: qcom: rpm: make QoS INVALID default Currently NOC_QOS_MODE_FIXED is defined as 0x0 which makes it the default option (partial struct initialization). The default option however should be NOC_QOS_MODE_INVALID. That results in bogus QoS configurations being sent for port 0 (which is used for the DRAM endpoint on BIMC, for example) coming from all nodes with .qos.ap_owned = true and uninitialized .qos.qos_mode. It's also an issue for newer SoCs where all nodes are treated as if they were ap_owned, but not all of them have QoS configuration. The NOC_QOS_MODEs are defined as preprocessor constants and are not used anywhere outside qcom_icc_set_noc_qos(), which is easily worked around. Separate the desc->type values from the values sent to msmbus in the aforementioned function. Make the former an enum for better mainainability. Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230228-topic-qos-v7-1-815606092fff@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpm.c | 24 +++++++++++++----------- drivers/interconnect/qcom/icc-rpm.h | 10 ++++++---- 2 files changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index c80819557923..56f29e0f0174 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -47,6 +47,9 @@ #define NOC_QOS_MODEn_ADDR(n) (0xc + (n * 0x1000)) #define NOC_QOS_MODEn_MASK 0x3 +#define NOC_QOS_MODE_FIXED_VAL 0x0 +#define NOC_QOS_MODE_BYPASS_VAL 0x2 + static int qcom_icc_set_qnoc_qos(struct icc_node *src, u64 max_bw) { struct icc_provider *provider = src->provider; @@ -152,7 +155,7 @@ static int qcom_icc_set_noc_qos(struct icc_node *src, u64 max_bw) struct qcom_icc_provider *qp; struct qcom_icc_node *qn; struct icc_provider *provider; - u32 mode = NOC_QOS_MODE_BYPASS; + u32 mode = NOC_QOS_MODE_BYPASS_VAL; int rc = 0; qn = src->data; @@ -166,18 +169,17 @@ static int qcom_icc_set_noc_qos(struct icc_node *src, u64 max_bw) return 0; } - if (qn->qos.qos_mode != NOC_QOS_MODE_INVALID) - mode = qn->qos.qos_mode; - - if (mode == NOC_QOS_MODE_FIXED) { - dev_dbg(src->provider->dev, "NoC QoS: %s: Set Fixed mode\n", - qn->name); + if (qn->qos.qos_mode == NOC_QOS_MODE_FIXED) { + dev_dbg(src->provider->dev, "NoC QoS: %s: Set Fixed mode\n", qn->name); + mode = NOC_QOS_MODE_FIXED_VAL; rc = qcom_icc_noc_set_qos_priority(qp, &qn->qos); if (rc) return rc; - } else if (mode == NOC_QOS_MODE_BYPASS) { - dev_dbg(src->provider->dev, "NoC QoS: %s: Set Bypass mode\n", - qn->name); + } else if (qn->qos.qos_mode == NOC_QOS_MODE_BYPASS) { + dev_dbg(src->provider->dev, "NoC QoS: %s: Set Bypass mode\n", qn->name); + mode = NOC_QOS_MODE_BYPASS_VAL; + } else { + /* How did we get here? */ } return regmap_update_bits(qp->regmap, @@ -243,7 +245,7 @@ static int __qcom_icc_set(struct icc_node *n, struct qcom_icc_node *qn, ret = qcom_icc_rpm_set(qn->mas_rpm_id, qn->slv_rpm_id, sum_bw); if (ret) return ret; - } else if (qn->qos.qos_mode != -1) { + } else if (qn->qos.qos_mode != NOC_QOS_MODE_INVALID) { /* set bandwidth directly from the AP */ ret = qcom_icc_qos_set(n, sum_bw); if (ret) diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h index 02257b0d3d5c..d54f76d8b3fd 100644 --- a/drivers/interconnect/qcom/icc-rpm.h +++ b/drivers/interconnect/qcom/icc-rpm.h @@ -96,10 +96,12 @@ struct qcom_icc_desc { unsigned int qos_offset; }; -/* Valid for both NoC and BIMC */ -#define NOC_QOS_MODE_INVALID -1 -#define NOC_QOS_MODE_FIXED 0x0 -#define NOC_QOS_MODE_BYPASS 0x2 +/* Valid for all bus types */ +enum qos_mode { + NOC_QOS_MODE_INVALID = 0, + NOC_QOS_MODE_FIXED, + NOC_QOS_MODE_BYPASS, +}; int qnoc_probe(struct platform_device *pdev); int qnoc_remove(struct platform_device *pdev); -- GitLab From 02819953b33a4410e6aa4595a043c052408c90d3 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Mar 2023 22:40:08 +0100 Subject: [PATCH 2050/5631] interconnect: qcom: rpm: Add support for specifying channel num Some nodes, like EBI0 (DDR) or L3/LLCC, may be connected over more than one channel. This should be taken into account in bandwidth calcualtion, as we're supposed to feed msmbus with the per-channel bandwidth. Add support for specifying that and use it during bandwidth aggregation. Reviewed-by: Bryan O'Donoghue Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230228-topic-qos-v7-2-815606092fff@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpm.c | 7 ++++++- drivers/interconnect/qcom/icc-rpm.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index 56f29e0f0174..5341fa169dbf 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -316,6 +316,7 @@ static void qcom_icc_bus_aggregate(struct icc_provider *provider, { struct icc_node *node; struct qcom_icc_node *qn; + u64 sum_avg[QCOM_ICC_NUM_BUCKETS]; int i; /* Initialise aggregate values */ @@ -333,7 +334,11 @@ static void qcom_icc_bus_aggregate(struct icc_provider *provider, list_for_each_entry(node, &provider->nodes, node_list) { qn = node->data; for (i = 0; i < QCOM_ICC_NUM_BUCKETS; i++) { - agg_avg[i] += qn->sum_avg[i]; + if (qn->channels) + sum_avg[i] = div_u64(qn->sum_avg[i], qn->channels); + else + sum_avg[i] = qn->sum_avg[i]; + agg_avg[i] += sum_avg[i]; agg_peak[i] = max_t(u64, agg_peak[i], qn->max_peak[i]); } } diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h index d54f76d8b3fd..12566014c179 100644 --- a/drivers/interconnect/qcom/icc-rpm.h +++ b/drivers/interconnect/qcom/icc-rpm.h @@ -66,6 +66,7 @@ struct qcom_icc_qos { * @id: a unique node identifier * @links: an array of nodes where we can go next while traversing * @num_links: the total number of @links + * @channels: number of channels at this node (e.g. DDR channels) * @buswidth: width of the interconnect between a node and the bus (bytes) * @sum_avg: current sum aggregate value of all avg bw requests * @max_peak: current max aggregate value of all peak bw requests @@ -78,6 +79,7 @@ struct qcom_icc_node { u16 id; const u16 *links; u16 num_links; + u16 channels; u16 buswidth; u64 sum_avg[QCOM_ICC_NUM_BUCKETS]; u64 max_peak[QCOM_ICC_NUM_BUCKETS]; -- GitLab From 82a4b285abcaa3631446e7e4103ef61d0787362d Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 8 Mar 2023 22:40:09 +0100 Subject: [PATCH 2051/5631] interconnect: qcom: Sort kerneldoc entries Sort the kerneldoc entries the same way the struct members are sorted. Signed-off-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230228-topic-qos-v7-3-815606092fff@linaro.org Signed-off-by: Georgi Djakov --- drivers/interconnect/qcom/icc-rpm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/interconnect/qcom/icc-rpm.h b/drivers/interconnect/qcom/icc-rpm.h index 12566014c179..22bdb1e4bb12 100644 --- a/drivers/interconnect/qcom/icc-rpm.h +++ b/drivers/interconnect/qcom/icc-rpm.h @@ -23,12 +23,12 @@ enum qcom_icc_type { /** * struct qcom_icc_provider - Qualcomm specific interconnect provider * @provider: generic interconnect provider - * @bus_clks: the clk_bulk_data table of bus clocks * @num_clks: the total number of clk_bulk_data entries * @type: the ICC provider type - * @qos_offset: offset to QoS registers * @regmap: regmap for QoS registers read/write access + * @qos_offset: offset to QoS registers * @bus_clk_rate: bus clock rate in Hz + * @bus_clks: the clk_bulk_data table of bus clocks */ struct qcom_icc_provider { struct icc_provider provider; -- GitLab From e0c35141f9ca5869a51d7c135688350c06ebdded Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Thu, 16 Mar 2023 15:12:51 +0100 Subject: [PATCH 2052/5631] dt-bindings: interconnect: OSM L3: Add SM6375 CPUCP compatible SM6375 includes a CPUCP block responsible for managing different APSS- related tasks, such as scaling the voltage and frequency of the components within the ARM DSU cluster. Add a compatible for the L3 cache DVFS scaler within. Acked-by: Krzysztof Kozlowski Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230303-topic-sm6375_features0_dts-v2-2-708b8191f7eb@linaro.org Signed-off-by: Georgi Djakov --- Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml index 576992a6dc5a..9d0a98d77ae9 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,osm-l3.yaml @@ -29,6 +29,7 @@ properties: - enum: - qcom,sc7280-epss-l3 - qcom,sc8280xp-epss-l3 + - qcom,sm6375-cpucp-l3 - qcom,sm8250-epss-l3 - qcom,sm8350-epss-l3 - const: qcom,epss-l3 -- GitLab From b7590f3841f47d5c6732db9a6d6474162109f487 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 15 Mar 2023 15:11:19 +0100 Subject: [PATCH 2053/5631] dt-bindings: interconnect: qcom,msm8998-bwmon: Resolve MSM8998 support BWMONv4 has two sets of registers: one for handling the monitor itself and one called "global" which hosts some sort of a headswitch and an interrupt control register. We did not handle that one before, as on SoCs starting with SDM845 they have been merged into a single contiguous range. To make the qcom,msm8998-bwmon less confusing and in preparation for actual MSM8998 support, describe the global register space and introduce new "qcom,sdm845-cpu-bwmon" compatible while keeping the "qcom,sdm845-bwmon" as a fallback for SoCs with this merged register space scheme. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230304-topic-ddr_bwmon-v3-1-77a050c2fbda@linaro.org Signed-off-by: Georgi Djakov --- .../interconnect/qcom,msm8998-bwmon.yaml | 41 +++++++++++++++---- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml index 12a0d3ecbabb..5d17bdcfdf70 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml @@ -22,14 +22,14 @@ description: | properties: compatible: oneOf: + - const: qcom,msm8998-bwmon # BWMON v4 - items: - enum: - qcom,sc7280-cpu-bwmon - qcom,sc8280xp-cpu-bwmon - - qcom,sdm845-bwmon + - qcom,sdm845-cpu-bwmon - qcom,sm8550-cpu-bwmon - - const: qcom,msm8998-bwmon - - const: qcom,msm8998-bwmon # BWMON v4 + - const: qcom,sdm845-bwmon # BWMON v4, unified register space - items: - enum: - qcom,sc8280xp-llcc-bwmon @@ -49,9 +49,13 @@ properties: type: object reg: - # BWMON v4 (currently described) and BWMON v5 use one register address - # space. BWMON v2 uses two register spaces - not yet described. - maxItems: 1 + # BWMON v5 uses one register address space, v1-v4 use one or two. + minItems: 1 + maxItems: 2 + + reg-names: + minItems: 1 + maxItems: 2 required: - compatible @@ -63,13 +67,36 @@ required: additionalProperties: false +allOf: + - if: + properties: + compatible: + const: qcom,msm8998-bwmon + then: + properties: + reg: + minItems: 2 + + reg-names: + items: + - const: monitor + - const: global + + else: + properties: + reg: + maxItems: 1 + + reg-names: + maxItems: 1 + examples: - | #include #include pmu@1436400 { - compatible = "qcom,sdm845-bwmon", "qcom,msm8998-bwmon"; + compatible = "qcom,sdm845-cpu-bwmon", "qcom,sdm845-bwmon"; reg = <0x01436400 0x600>; interrupts = ; interconnects = <&gladiator_noc MASTER_APPSS_PROC 3 &mem_noc SLAVE_LLCC 3>; -- GitLab From 8364f6d000ede4185a82b1f2514543ed172d4b51 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Wed, 1 Mar 2023 16:55:45 +0800 Subject: [PATCH 2054/5631] efi/loongarch: Reintroduce efi_relocate_kernel() to relocate kernel Since Linux-6.3, LoongArch supports PIE kernel now, so let's reintroduce efi_relocate_kernel() to relocate the core kernel. Signed-off-by: Huacai Chen Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/loongarch-stub.c | 24 ++++++------------- 1 file changed, 7 insertions(+), 17 deletions(-) diff --git a/drivers/firmware/efi/libstub/loongarch-stub.c b/drivers/firmware/efi/libstub/loongarch-stub.c index eee7ed43cdfb..72c71ae201f0 100644 --- a/drivers/firmware/efi/libstub/loongarch-stub.c +++ b/drivers/firmware/efi/libstub/loongarch-stub.c @@ -21,26 +21,16 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, efi_loaded_image_t *image, efi_handle_t image_handle) { - int nr_pages = round_up(kernel_asize, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; - efi_physical_addr_t kernel_addr = EFI_KIMG_PREFERRED_ADDRESS; efi_status_t status; + unsigned long kernel_addr = 0; - /* - * Allocate space for the kernel image at the preferred offset. This is - * the only location in memory from where we can execute the image, so - * no point in falling back to another allocation. - */ - status = efi_bs_call(allocate_pages, EFI_ALLOCATE_ADDRESS, - EFI_LOADER_DATA, nr_pages, &kernel_addr); - if (status != EFI_SUCCESS) - return status; - - *image_addr = EFI_KIMG_PREFERRED_ADDRESS; - *image_size = kernel_asize; + kernel_addr = (unsigned long)&kernel_offset - kernel_offset; + + status = efi_relocate_kernel(&kernel_addr, kernel_fsize, kernel_asize, + EFI_KIMG_PREFERRED_ADDRESS, efi_get_kimg_min_align(), 0x0); - memcpy((void *)EFI_KIMG_PREFERRED_ADDRESS, - (void *)&kernel_offset - kernel_offset, - kernel_fsize); + *image_addr = kernel_addr; + *image_size = kernel_asize; return status; } -- GitLab From e65733b5c59a1ea20324a03494364958bef3fc68 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:38 +0000 Subject: [PATCH 2055/5631] KVM: x86: Redefine 'longmode' as a flag for KVM_EXIT_HYPERCALL The 'longmode' field is a bit annoying as it blows an entire __u32 to represent a boolean value. Since other architectures are looking to add support for KVM_EXIT_HYPERCALL, now is probably a good time to clean it up. Redefine the field (and the remaining padding) as a set of flags. Preserve the existing ABI by using bit 0 to indicate if the guest was in long mode and requiring that the remaining 31 bits must be zero. Cc: Paolo Bonzini Acked-by: Sean Christopherson Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-2-oliver.upton@linux.dev --- Documentation/virt/kvm/api.rst | 3 +-- arch/x86/include/asm/kvm_host.h | 7 +++++++ arch/x86/include/uapi/asm/kvm.h | 3 +++ arch/x86/kvm/x86.c | 6 +++++- include/uapi/linux/kvm.h | 9 +++++++-- 5 files changed, 23 insertions(+), 5 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 62de0768d6aa..9b01e3d0e757 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6218,8 +6218,7 @@ to the byte array. __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + __u64 flags; } hypercall; Unused. This was once used for 'hypercall to userspace'. To implement diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 808c292ad3f4..15bda40517ff 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2204,4 +2204,11 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) +/* + * KVM previously used a u32 field in kvm_run to indicate the hypercall was + * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the + * remaining 31 lower bits must be 0 to preserve ABI. + */ +#define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7713420abab0..27a1d5c1a018 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9803,7 +9803,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; - vcpu->run->hypercall.longmode = op_64_bit; + vcpu->run->hypercall.flags = 0; + if (op_64_bit) + vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; + + WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); vcpu->arch.complete_userspace_io = complete_hypercall_exit; return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d77aef872a0a..dd42d7dfb86c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { -- GitLab From de40bb8abb764f6866d82c4e2a43acdb22892cf4 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:39 +0000 Subject: [PATCH 2056/5631] KVM: arm64: Add a helper to check if a VM has ran once The test_bit(...) pattern is quite a lot of keystrokes. Replace existing callsites with a helper. No functional change intended. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-3-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/hypercalls.c | 3 +-- arch/arm64/kvm/pmu-emul.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bcd774d74f34..d091d1c9890b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1061,6 +1061,9 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); (system_supports_32bit_el0() && \ !static_branch_unlikely(&arm64_mismatched_32bit_el0)) +#define kvm_vm_has_ran_once(kvm) \ + (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags)) + int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 5da884e11337..a09a526a7d7c 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -379,8 +379,7 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) mutex_lock(&kvm->lock); - if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) && - val != *fw_reg_bmap) { + if (kvm_vm_has_ran_once(kvm) && val != *fw_reg_bmap) { ret = -EBUSY; goto out; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 24908400e190..a0fc569fdbca 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -880,7 +880,7 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) list_for_each_entry(entry, &arm_pmus, entry) { arm_pmu = entry->arm_pmu; if (arm_pmu->pmu.type == pmu_id) { - if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) || + if (kvm_vm_has_ran_once(kvm) || (kvm->arch.pmu_filter && kvm->arch.arm_pmu != arm_pmu)) { ret = -EBUSY; break; @@ -963,7 +963,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) mutex_lock(&kvm->lock); - if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) { + if (kvm_vm_has_ran_once(kvm)) { mutex_unlock(&kvm->lock); return -EBUSY; } -- GitLab From e0fc6b21616dd917899ee4a2d4126b4a963c0871 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:40 +0000 Subject: [PATCH 2057/5631] KVM: arm64: Add vm fd device attribute accessors A subsequent change will allow userspace to convey a filter for hypercalls through a vm device attribute. Add the requisite boilerplate for vm attribute accessors. Reviewed-by: Suzuki K Poulose Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-4-oliver.upton@linux.dev --- arch/arm64/kvm/arm.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3bd732eaf087..b6e26c0e65e5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1439,11 +1439,28 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, } } +static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + switch (attr->group) { + default: + return -ENXIO; + } +} + +static int kvm_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + switch (attr->group) { + default: + return -ENXIO; + } +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; + struct kvm_device_attr attr; switch (ioctl) { case KVM_CREATE_IRQCHIP: { @@ -1479,6 +1496,18 @@ long kvm_arch_vm_ioctl(struct file *filp, return -EFAULT; return kvm_vm_ioctl_mte_copy_tags(kvm, ©_tags); } + case KVM_HAS_DEVICE_ATTR: { + if (copy_from_user(&attr, argp, sizeof(attr))) + return -EFAULT; + + return kvm_vm_has_attr(kvm, &attr); + } + case KVM_SET_DEVICE_ATTR: { + if (copy_from_user(&attr, argp, sizeof(attr))) + return -EFAULT; + + return kvm_vm_set_attr(kvm, &attr); + } default: return -EINVAL; } -- GitLab From aac94968126beb9846c12a940f1302ece7849b4f Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:41 +0000 Subject: [PATCH 2058/5631] KVM: arm64: Rename SMC/HVC call handler to reflect reality KVM handles SMCCC calls from virtual EL2 that use the SMC instruction since commit bd36b1a9eb5a ("KVM: arm64: nv: Handle SMCs taken from virtual EL2"). Thus, the function name of the handler no longer reflects reality. Normalize the name on SMCCC, since that's the only hypercall interface KVM supports in the first place. No fuctional change intended. Reviewed-by: Suzuki K Poulose Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-5-oliver.upton@linux.dev --- arch/arm64/kvm/handle_exit.c | 4 ++-- arch/arm64/kvm/hypercalls.c | 2 +- include/kvm/arm_hypercalls.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index a798c0b4d717..5e4f9737cbd5 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -52,7 +52,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu) return 1; } - ret = kvm_hvc_call_handler(vcpu); + ret = kvm_smccc_call_handler(vcpu); if (ret < 0) { vcpu_set_reg(vcpu, 0, ~0UL); return 1; @@ -89,7 +89,7 @@ static int handle_smc(struct kvm_vcpu *vcpu) * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than * being treated as UNDEFINED. */ - ret = kvm_hvc_call_handler(vcpu); + ret = kvm_smccc_call_handler(vcpu); if (ret < 0) vcpu_set_reg(vcpu, 0, ~0UL); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index a09a526a7d7c..5ead6c6afff0 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -121,7 +121,7 @@ static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id) } } -int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) +int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 1188f116cf4e..8f4e33bc43e8 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -6,7 +6,7 @@ #include -int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); +int kvm_smccc_call_handler(struct kvm_vcpu *vcpu); static inline u32 smccc_get_function(struct kvm_vcpu *vcpu) { -- GitLab From c2d2e9b3d8ce9db825a5630d9d52d542f5138ae0 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:42 +0000 Subject: [PATCH 2059/5631] KVM: arm64: Start handling SMCs from EL1 Whelp, the architecture gods have spoken and confirmed that the function ID space is common between SMCs and HVCs. Not only that, the expectation is that hypervisors handle calls to both SMC and HVC conduits. KVM recently picked up support for SMCCCs in commit bd36b1a9eb5a ("KVM: arm64: nv: Handle SMCs taken from virtual EL2") but scoped it only to a nested hypervisor. Let's just open the floodgates and let EL1 access our SMCCC implementation with the SMC instruction as well. Reviewed-by: Suzuki K Poulose Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-6-oliver.upton@linux.dev --- arch/arm64/kvm/handle_exit.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 5e4f9737cbd5..68f95dcd41a1 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -72,13 +72,15 @@ static int handle_smc(struct kvm_vcpu *vcpu) * * We need to advance the PC after the trap, as it would * otherwise return to the same address... - * - * Only handle SMCs from the virtual EL2 with an immediate of zero and - * skip it otherwise. */ - if (!vcpu_is_el2(vcpu) || kvm_vcpu_hvc_get_imm(vcpu)) { + kvm_incr_pc(vcpu); + + /* + * SMCs with a nonzero immediate are reserved according to DEN0028E 2.9 + * "SMC and HVC immediate value". + */ + if (kvm_vcpu_hvc_get_imm(vcpu)) { vcpu_set_reg(vcpu, 0, ~0UL); - kvm_incr_pc(vcpu); return 1; } @@ -93,8 +95,6 @@ static int handle_smc(struct kvm_vcpu *vcpu) if (ret < 0) vcpu_set_reg(vcpu, 0, ~0UL); - kvm_incr_pc(vcpu); - return ret; } -- GitLab From a8308b3fc9494953c453480fb277e24f82f7d2b9 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:43 +0000 Subject: [PATCH 2060/5631] KVM: arm64: Refactor hvc filtering to support different actions KVM presently allows userspace to filter guest hypercalls with bitmaps expressed via pseudo-firmware registers. These bitmaps have a narrow scope and, of course, can only allow/deny a particular call. A subsequent change to KVM will introduce a generalized UAPI for filtering hypercalls, allowing functions to be forwarded to userspace. Refactor the existing hypercall filtering logic to make room for more than two actions. While at it, generalize the function names around SMCCC as it is the basis for the upcoming UAPI. No functional change intended. Reviewed-by: Suzuki K Poulose Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-7-oliver.upton@linux.dev --- arch/arm64/include/uapi/asm/kvm.h | 9 +++++++++ arch/arm64/kvm/hypercalls.c | 26 ++++++++++++++++++++++---- 2 files changed, 31 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f9672ef1159a 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -469,6 +469,15 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + #endif #endif /* __ARM_KVM_H__ */ diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 5ead6c6afff0..0be974e2f1fc 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -65,7 +65,7 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) val[3] = lower_32_bits(cycles); } -static bool kvm_hvc_call_default_allowed(u32 func_id) +static bool kvm_smccc_default_allowed(u32 func_id) { switch (func_id) { /* @@ -93,7 +93,7 @@ static bool kvm_hvc_call_default_allowed(u32 func_id) } } -static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id) +static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; @@ -117,20 +117,38 @@ static bool kvm_hvc_call_allowed(struct kvm_vcpu *vcpu, u32 func_id) return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, &smccc_feat->vendor_hyp_bmap); default: - return kvm_hvc_call_default_allowed(func_id); + return false; } } +static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) +{ + if (kvm_smccc_test_fw_bmap(vcpu, func_id) || + kvm_smccc_default_allowed(func_id)) + return KVM_SMCCC_FILTER_HANDLE; + + return KVM_SMCCC_FILTER_DENY; +} + int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; + u8 action; gpa_t gpa; - if (!kvm_hvc_call_allowed(vcpu, func_id)) + action = kvm_smccc_get_action(vcpu, func_id); + switch (action) { + case KVM_SMCCC_FILTER_HANDLE: + break; + case KVM_SMCCC_FILTER_DENY: + goto out; + default: + WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action); goto out; + } switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: -- GitLab From fb88707dd39bd1d5ec4a058776de9ee99bcc7b72 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:44 +0000 Subject: [PATCH 2061/5631] KVM: arm64: Use a maple tree to represent the SMCCC filter Maple tree is an efficient B-tree implementation that is intended for storing non-overlapping intervals. Such a data structure is a good fit for the SMCCC filter as it is desirable to sparsely allocate the 32 bit function ID space. To that end, add a maple tree to kvm_arch and correctly init/teardown along with the VM. Wire in a test against the hypercall filter for HVCs which does nothing until the controls are exposed to userspace. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-8-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_host.h | 5 ++- arch/arm64/kvm/arm.c | 2 ++ arch/arm64/kvm/hypercalls.c | 57 +++++++++++++++++++++++++++++++ include/kvm/arm_hypercalls.h | 1 + 4 files changed, 64 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d091d1c9890b..2682b3fd0881 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -221,7 +222,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_EL1_32BIT 4 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 5 - + /* SMCCC filter initialized for the VM */ +#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED 6 unsigned long flags; /* @@ -242,6 +244,7 @@ struct kvm_arch { /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; + struct maple_tree smccc_filter; /* * For an untrusted host VM, 'pkvm.handle' is used to lookup diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index b6e26c0e65e5..1202ac03bee0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -192,6 +192,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_destroy_vcpus(kvm); kvm_unshare_hyp(kvm, kvm + 1); + + kvm_arm_teardown_hypercalls(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 0be974e2f1fc..ba7cd84c6668 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -121,8 +121,58 @@ static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) } } +#define SMCCC_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID +#define SMCCC_ARCH_RANGE_END \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, ARM_SMCCC_FUNC_MASK) + +static void init_smccc_filter(struct kvm *kvm) +{ + int r; + + mt_init(&kvm->arch.smccc_filter); + + /* + * Prevent userspace from handling any SMCCC calls in the architecture + * range, avoiding the risk of misrepresenting Spectre mitigation status + * to the guest. + */ + r = mtree_insert_range(&kvm->arch.smccc_filter, + SMCCC_ARCH_RANGE_BEGIN, SMCCC_ARCH_RANGE_END, + xa_mk_value(KVM_SMCCC_FILTER_HANDLE), + GFP_KERNEL_ACCOUNT); + WARN_ON_ONCE(r); +} + +static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) +{ + unsigned long idx = func_id; + void *val; + + if (!test_bit(KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED, &kvm->arch.flags)) + return KVM_SMCCC_FILTER_HANDLE; + + /* + * But where's the error handling, you say? + * + * mt_find() returns NULL if no entry was found, which just so happens + * to match KVM_SMCCC_FILTER_HANDLE. + */ + val = mt_find(&kvm->arch.smccc_filter, &idx, idx); + return xa_to_value(val); +} + static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) { + /* + * Intervening actions in the SMCCC filter take precedence over the + * pseudo-firmware register bitmaps. + */ + u8 action = kvm_smccc_filter_get_action(vcpu->kvm, func_id); + if (action != KVM_SMCCC_FILTER_HANDLE) + return action; + if (kvm_smccc_test_fw_bmap(vcpu, func_id) || kvm_smccc_default_allowed(func_id)) return KVM_SMCCC_FILTER_HANDLE; @@ -263,6 +313,13 @@ void kvm_arm_init_hypercalls(struct kvm *kvm) smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; + + init_smccc_filter(kvm); +} + +void kvm_arm_teardown_hypercalls(struct kvm *kvm) +{ + mtree_destroy(&kvm->arch.smccc_filter); } int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index 8f4e33bc43e8..fe6c31575b05 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -43,6 +43,7 @@ static inline void smccc_set_retval(struct kvm_vcpu *vcpu, struct kvm_one_reg; void kvm_arm_init_hypercalls(struct kvm *kvm); +void kvm_arm_teardown_hypercalls(struct kvm *kvm); int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); -- GitLab From d824dff1919bbd523d4d5c860437d043c0ad121d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:45 +0000 Subject: [PATCH 2062/5631] KVM: arm64: Add support for KVM_EXIT_HYPERCALL In anticipation of user hypercall filters, add the necessary plumbing to get SMCCC calls out to userspace. Even though the exit structure has space for KVM to pass register arguments, let's just avoid it altogether and let userspace poke at the registers via KVM_GET_ONE_REG. This deliberately stretches the definition of a 'hypercall' to cover SMCs from EL1 in addition to the HVCs we know and love. KVM doesn't support EL1 calls into secure services, but now we can paint that as a userspace problem and be done with it. Finally, we need a flag to let userspace know what conduit instruction was used (i.e. SMC vs. HVC). Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-9-oliver.upton@linux.dev --- Documentation/virt/kvm/api.rst | 18 ++++++++++++++++-- arch/arm64/include/uapi/asm/kvm.h | 4 ++++ arch/arm64/kvm/handle_exit.c | 4 +++- arch/arm64/kvm/hypercalls.c | 16 ++++++++++++++++ 4 files changed, 39 insertions(+), 3 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9b01e3d0e757..9497792c4ee5 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6221,11 +6221,25 @@ to the byte array. __u64 flags; } hypercall; -Unused. This was once used for 'hypercall to userspace'. To implement -such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390). + +It is strongly recommended that userspace use ``KVM_EXIT_IO`` (x86) or +``KVM_EXIT_MMIO`` (all except s390) to implement functionality that +requires a guest to interact with host userpace. .. note:: KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO. +For arm64: +---------- + +``nr`` contains the function ID of the guest's SMCCC call. Userspace is +expected to use the ``KVM_GET_ONE_REG`` ioctl to retrieve the call +parameters from the vCPU's GPRs. + +Definition of ``flags``: + - ``KVM_HYPERCALL_EXIT_SMC``: Indicates that the guest used the SMC + conduit to initiate the SMCCC call. If this bit is 0 then the guest + used the HVC conduit for the SMCCC call. + :: /* KVM_EXIT_TPR_ACCESS */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f9672ef1159a..f86446c5a7e3 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -472,12 +472,16 @@ enum { enum kvm_smccc_filter_action { KVM_SMCCC_FILTER_HANDLE = 0, KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, #ifdef __KERNEL__ NR_SMCCC_FILTER_ACTIONS #endif }; +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 68f95dcd41a1..3f43e20c48b6 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -71,7 +71,9 @@ static int handle_smc(struct kvm_vcpu *vcpu) * Trap exception, not a Secure Monitor Call exception [...]" * * We need to advance the PC after the trap, as it would - * otherwise return to the same address... + * otherwise return to the same address. Furthermore, pre-incrementing + * the PC before potentially exiting to userspace maintains the same + * abstraction for both SMCs and HVCs. */ kvm_incr_pc(vcpu); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index ba7cd84c6668..2db53709bec1 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -180,6 +180,19 @@ static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) return KVM_SMCCC_FILTER_DENY; } +static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id) +{ + u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); + struct kvm_run *run = vcpu->run; + + run->exit_reason = KVM_EXIT_HYPERCALL; + run->hypercall.nr = func_id; + run->hypercall.flags = 0; + + if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64) + run->hypercall.flags |= KVM_HYPERCALL_EXIT_SMC; +} + int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; @@ -195,6 +208,9 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) break; case KVM_SMCCC_FILTER_DENY: goto out; + case KVM_SMCCC_FILTER_FWD_TO_USER: + kvm_prepare_hypercall_exit(vcpu, func_id); + return 0; default: WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action); goto out; -- GitLab From 821d935c87bc95253f82deec3cbb457ccf3de003 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:46 +0000 Subject: [PATCH 2063/5631] KVM: arm64: Introduce support for userspace SMCCC filtering As the SMCCC (and related specifications) march towards an 'everything and the kitchen sink' interface for interacting with a system it becomes less likely that KVM will support every related feature. We could do better by letting userspace have a crack at it instead. Allow userspace to define an 'SMCCC filter' that applies to both HVCs and SMCs initiated by the guest. Supporting both conduits with this interface is important for a couple of reasons. Guest SMC usage is table stakes for a nested guest, as HVCs are always taken to the virtual EL2. Additionally, guests may want to interact with a service on the secure side which can now be proxied by userspace. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-10-oliver.upton@linux.dev --- Documentation/virt/kvm/api.rst | 4 ++ Documentation/virt/kvm/devices/vm.rst | 79 +++++++++++++++++++++++++++ arch/arm64/include/uapi/asm/kvm.h | 11 ++++ arch/arm64/kvm/arm.c | 4 ++ arch/arm64/kvm/hypercalls.c | 60 ++++++++++++++++++++ include/kvm/arm_hypercalls.h | 3 + 6 files changed, 161 insertions(+) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9497792c4ee5..c8ab2f730945 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6231,6 +6231,10 @@ requires a guest to interact with host userpace. For arm64: ---------- +SMCCC exits can be enabled depending on the configuration of the SMCCC +filter. See the Documentation/virt/kvm/devices/vm.rst +``KVM_ARM_SMCCC_FILTER`` for more details. + ``nr`` contains the function ID of the guest's SMCCC call. Userspace is expected to use the ``KVM_GET_ONE_REG`` ioctl to retrieve the call parameters from the vCPU's GPRs. diff --git a/Documentation/virt/kvm/devices/vm.rst b/Documentation/virt/kvm/devices/vm.rst index 147efec626e5..9d726e60ec47 100644 --- a/Documentation/virt/kvm/devices/vm.rst +++ b/Documentation/virt/kvm/devices/vm.rst @@ -321,3 +321,82 @@ Allows userspace to query the status of migration mode. if it is enabled :Returns: -EFAULT if the given address is not accessible from kernel space; 0 in case of success. + +6. GROUP: KVM_ARM_VM_SMCCC_CTRL +=============================== + +:Architectures: arm64 + +6.1. ATTRIBUTE: KVM_ARM_VM_SMCCC_FILTER (w/o) +--------------------------------------------- + +:Parameters: Pointer to a ``struct kvm_smccc_filter`` + +:Returns: + + ====== =========================================== + EEXIST Range intersects with a previously inserted + or reserved range + EBUSY A vCPU in the VM has already run + EINVAL Invalid filter configuration + ENOMEM Failed to allocate memory for the in-kernel + representation of the SMCCC filter + ====== =========================================== + +Requests the installation of an SMCCC call filter described as follows:: + + enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + }; + + struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; + }; + +The filter is defined as a set of non-overlapping ranges. Each +range defines an action to be applied to SMCCC calls within the range. +Userspace can insert multiple ranges into the filter by using +successive calls to this attribute. + +The default configuration of KVM is such that all implemented SMCCC +calls are allowed. Thus, the SMCCC filter can be defined sparsely +by userspace, only describing ranges that modify the default behavior. + +The range expressed by ``struct kvm_smccc_filter`` is +[``base``, ``base + nr_functions``). The range is not allowed to wrap, +i.e. userspace cannot rely on ``base + nr_functions`` overflowing. + +The SMCCC filter applies to both SMC and HVC calls initiated by the +guest. The SMCCC filter gates the in-kernel emulation of SMCCC calls +and as such takes effect before other interfaces that interact with +SMCCC calls (e.g. hypercall bitmap registers). + +Actions: + + - ``KVM_SMCCC_FILTER_HANDLE``: Allows the guest SMCCC call to be + handled in-kernel. It is strongly recommended that userspace *not* + explicitly describe the allowed SMCCC call ranges. + + - ``KVM_SMCCC_FILTER_DENY``: Rejects the guest SMCCC call in-kernel + and returns to the guest. + + - ``KVM_SMCCC_FILTER_FWD_TO_USER``: The guest SMCCC call is forwarded + to userspace with an exit reason of ``KVM_EXIT_HYPERCALL``. + +The ``pad`` field is reserved for future use and must be zero. KVM may +return ``-EINVAL`` if the field is nonzero. + +KVM reserves the 'Arm Architecture Calls' range of function IDs and +will reject attempts to define a filter for any portion of these ranges: + + =========== =============== + Start End (inclusive) + =========== =============== + 0x8000_0000 0x8000_FFFF + 0xC000_0000 0xC000_FFFF + =========== =============== diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index f86446c5a7e3..3dcfa4bfdf83 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -372,6 +372,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -479,6 +483,13 @@ enum kvm_smccc_filter_action { #endif }; +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + /* arm64-specific KVM_EXIT_HYPERCALL flags */ #define KVM_HYPERCALL_EXIT_SMC (1U << 0) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1202ac03bee0..efee032c9560 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1444,6 +1444,8 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { + case KVM_ARM_VM_SMCCC_CTRL: + return kvm_vm_smccc_has_attr(kvm, attr); default: return -ENXIO; } @@ -1452,6 +1454,8 @@ static int kvm_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) static int kvm_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->group) { + case KVM_ARM_VM_SMCCC_CTRL: + return kvm_vm_smccc_set_attr(kvm, attr); default: return -ENXIO; } diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 2db53709bec1..9a35d6d18193 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -145,6 +145,44 @@ static void init_smccc_filter(struct kvm *kvm) WARN_ON_ONCE(r); } +static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) +{ + const void *zero_page = page_to_virt(ZERO_PAGE(0)); + struct kvm_smccc_filter filter; + u32 start, end; + int r; + + if (copy_from_user(&filter, uaddr, sizeof(filter))) + return -EFAULT; + + if (memcmp(filter.pad, zero_page, sizeof(filter.pad))) + return -EINVAL; + + start = filter.base; + end = start + filter.nr_functions - 1; + + if (end < start || filter.action >= NR_SMCCC_FILTER_ACTIONS) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (kvm_vm_has_ran_once(kvm)) { + r = -EBUSY; + goto out_unlock; + } + + r = mtree_insert_range(&kvm->arch.smccc_filter, start, end, + xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT); + if (r) + goto out_unlock; + + set_bit(KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED, &kvm->arch.flags); + +out_unlock: + mutex_unlock(&kvm->lock); + return r; +} + static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) { unsigned long idx = func_id; @@ -569,3 +607,25 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) return -EINVAL; } + +int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + switch (attr->attr) { + case KVM_ARM_VM_SMCCC_FILTER: + return 0; + default: + return -ENXIO; + } +} + +int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) +{ + void __user *uaddr = (void __user *)attr->addr; + + switch (attr->attr) { + case KVM_ARM_VM_SMCCC_FILTER: + return kvm_smccc_set_filter(kvm, uaddr); + default: + return -ENXIO; + } +} diff --git a/include/kvm/arm_hypercalls.h b/include/kvm/arm_hypercalls.h index fe6c31575b05..2df152207ccd 100644 --- a/include/kvm/arm_hypercalls.h +++ b/include/kvm/arm_hypercalls.h @@ -49,4 +49,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr); +int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr); + #endif -- GitLab From 7e484d2785e2a2e526a6b2679d3e4c1402ffe0ec Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:47 +0000 Subject: [PATCH 2064/5631] KVM: arm64: Return NOT_SUPPORTED to guest for unknown PSCI version A subsequent change to KVM will allow negative returns from SMCCC handlers to exit to userspace. Make way for this change by explicitly returning SMCCC_RET_NOT_SUPPORTED to the guest if the VM is configured to use an unknown PSCI version. Add a WARN since this is undoubtedly a KVM bug. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-11-oliver.upton@linux.dev --- arch/arm64/kvm/psci.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 7fbc4c1b9df0..aff54b106c30 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -435,6 +435,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) int kvm_psci_call(struct kvm_vcpu *vcpu) { u32 psci_fn = smccc_get_function(vcpu); + int version = kvm_psci_version(vcpu); unsigned long val; val = kvm_psci_check_allowed_function(vcpu, psci_fn); @@ -443,7 +444,7 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) return 1; } - switch (kvm_psci_version(vcpu)) { + switch (version) { case KVM_ARM_PSCI_1_1: return kvm_psci_1_x_call(vcpu, 1); case KVM_ARM_PSCI_1_0: @@ -453,6 +454,8 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) case KVM_ARM_PSCI_0_1: return kvm_psci_0_1_call(vcpu); default: - return -EINVAL; + WARN_ONCE(1, "Unknown PSCI version %d", version); + smccc_set_retval(vcpu, SMCCC_RET_NOT_SUPPORTED, 0, 0, 0); + return 1; } } -- GitLab From 37c8e494794786aa8e4acba1f0f5b45f37b11699 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:48 +0000 Subject: [PATCH 2065/5631] KVM: arm64: Let errors from SMCCC emulation to reach userspace Typically a negative return from an exit handler is used to request a return to userspace with the specified error. KVM's handling of SMCCC emulation (i.e. both HVCs and SMCs) deviates from the trend and resumes the guest instead. Stop handling negative returns this way and instead let the error percolate to userspace. Suggested-by: Suzuki K Poulose Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-12-oliver.upton@linux.dev --- arch/arm64/kvm/handle_exit.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 3f43e20c48b6..6dcd6604b6bc 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -36,8 +36,6 @@ static void kvm_handle_guest_serror(struct kvm_vcpu *vcpu, u64 esr) static int handle_hvc(struct kvm_vcpu *vcpu) { - int ret; - trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; @@ -52,19 +50,11 @@ static int handle_hvc(struct kvm_vcpu *vcpu) return 1; } - ret = kvm_smccc_call_handler(vcpu); - if (ret < 0) { - vcpu_set_reg(vcpu, 0, ~0UL); - return 1; - } - - return ret; + return kvm_smccc_call_handler(vcpu); } static int handle_smc(struct kvm_vcpu *vcpu) { - int ret; - /* * "If an SMC instruction executed at Non-secure EL1 is * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a @@ -93,11 +83,7 @@ static int handle_smc(struct kvm_vcpu *vcpu) * at Non-secure EL1 is trapped to EL2 if HCR_EL2.TSC==1, rather than * being treated as UNDEFINED. */ - ret = kvm_smccc_call_handler(vcpu); - if (ret < 0) - vcpu_set_reg(vcpu, 0, ~0UL); - - return ret; + return kvm_smccc_call_handler(vcpu); } /* -- GitLab From fab19915f498b0e76fabd4d78841c99b7b6d7851 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:49 +0000 Subject: [PATCH 2066/5631] KVM: selftests: Add a helper for SMCCC calls with SMC instruction Build a helper for doing SMCs in selftests by macro-izing the current HVC implementation and taking the conduit instruction as an argument. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-13-oliver.upton@linux.dev --- .../selftests/kvm/include/aarch64/processor.h | 13 +++++ .../selftests/kvm/lib/aarch64/processor.c | 52 ++++++++++++------- 2 files changed, 46 insertions(+), 19 deletions(-) diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 5f977528e09c..cb537253a6b9 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -214,6 +214,19 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res); +/** + * smccc_smc - Invoke a SMCCC function using the smc conduit + * @function_id: the SMCCC function to be called + * @arg0-arg6: SMCCC function arguments, corresponding to registers x1-x7 + * @res: pointer to write the return values from registers x0-x3 + * + */ +void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res); + + + uint32_t guest_get_vcpuid(void); #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 5972a23b2765..24e8122307f4 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -508,29 +508,43 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, close(kvm_fd); } +#define __smccc_call(insn, function_id, arg0, arg1, arg2, arg3, arg4, arg5, \ + arg6, res) \ + asm volatile("mov w0, %w[function_id]\n" \ + "mov x1, %[arg0]\n" \ + "mov x2, %[arg1]\n" \ + "mov x3, %[arg2]\n" \ + "mov x4, %[arg3]\n" \ + "mov x5, %[arg4]\n" \ + "mov x6, %[arg5]\n" \ + "mov x7, %[arg6]\n" \ + #insn "#0\n" \ + "mov %[res0], x0\n" \ + "mov %[res1], x1\n" \ + "mov %[res2], x2\n" \ + "mov %[res3], x3\n" \ + : [res0] "=r"(res->a0), [res1] "=r"(res->a1), \ + [res2] "=r"(res->a2), [res3] "=r"(res->a3) \ + : [function_id] "r"(function_id), [arg0] "r"(arg0), \ + [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), \ + [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) \ + : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7") + + void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1, uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, uint64_t arg6, struct arm_smccc_res *res) { - asm volatile("mov w0, %w[function_id]\n" - "mov x1, %[arg0]\n" - "mov x2, %[arg1]\n" - "mov x3, %[arg2]\n" - "mov x4, %[arg3]\n" - "mov x5, %[arg4]\n" - "mov x6, %[arg5]\n" - "mov x7, %[arg6]\n" - "hvc #0\n" - "mov %[res0], x0\n" - "mov %[res1], x1\n" - "mov %[res2], x2\n" - "mov %[res3], x3\n" - : [res0] "=r"(res->a0), [res1] "=r"(res->a1), - [res2] "=r"(res->a2), [res3] "=r"(res->a3) - : [function_id] "r"(function_id), [arg0] "r"(arg0), - [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3), - [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6) - : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7"); + __smccc_call(hvc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, + arg6, res); +} + +void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1, + uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5, + uint64_t arg6, struct arm_smccc_res *res) +{ + __smccc_call(smc, function_id, arg0, arg1, arg2, arg3, arg4, arg5, + arg6, res); } void kvm_selftest_arch_init(void) -- GitLab From 60e7dade498eb881bcdf0d9a420c97625f73acc1 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Tue, 4 Apr 2023 15:40:50 +0000 Subject: [PATCH 2067/5631] KVM: selftests: Add test for SMCCC filter Add a selftest for the SMCCC filter, ensuring basic UAPI constraints (e.g. reserved ranges, non-overlapping ranges) are upheld. Additionally, test that the DENIED and FWD_TO_USER work as intended. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230404154050.2270077-14-oliver.upton@linux.dev --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/aarch64/smccc_filter.c | 260 ++++++++++++++++++ 2 files changed, 261 insertions(+) create mode 100644 tools/testing/selftests/kvm/aarch64/smccc_filter.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 84a627c43795..d66a0642cffd 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -141,6 +141,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list TEST_GEN_PROGS_aarch64 += aarch64/hypercalls TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test TEST_GEN_PROGS_aarch64 += aarch64/psci_test +TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config TEST_GEN_PROGS_aarch64 += aarch64/vgic_init TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c new file mode 100644 index 000000000000..0f9db0641847 --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * smccc_filter - Tests for the SMCCC filter UAPI. + * + * Copyright (c) 2023 Google LLC + * + * This test includes: + * - Tests that the UAPI constraints are upheld by KVM. For example, userspace + * is prevented from filtering the architecture range of SMCCC calls. + * - Test that the filter actions (DENIED, FWD_TO_USER) work as intended. + */ + +#include +#include +#include + +#include "processor.h" +#include "test_util.h" + +enum smccc_conduit { + HVC_INSN, + SMC_INSN, +}; + +#define for_each_conduit(conduit) \ + for (conduit = HVC_INSN; conduit <= SMC_INSN; conduit++) + +static void guest_main(uint32_t func_id, enum smccc_conduit conduit) +{ + struct arm_smccc_res res; + + if (conduit == SMC_INSN) + smccc_smc(func_id, 0, 0, 0, 0, 0, 0, 0, &res); + else + smccc_hvc(func_id, 0, 0, 0, 0, 0, 0, 0, &res); + + GUEST_SYNC(res.a0); +} + +static int __set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, + enum kvm_smccc_filter_action action) +{ + struct kvm_smccc_filter filter = { + .base = start, + .nr_functions = nr_functions, + .action = action, + }; + + return __kvm_device_attr_set(vm->fd, KVM_ARM_VM_SMCCC_CTRL, + KVM_ARM_VM_SMCCC_FILTER, &filter); +} + +static void set_smccc_filter(struct kvm_vm *vm, uint32_t start, uint32_t nr_functions, + enum kvm_smccc_filter_action action) +{ + int ret = __set_smccc_filter(vm, start, nr_functions, action); + + TEST_ASSERT(!ret, "failed to configure SMCCC filter: %d", ret); +} + +static struct kvm_vm *setup_vm(struct kvm_vcpu **vcpu) +{ + struct kvm_vcpu_init init; + struct kvm_vm *vm; + + vm = vm_create(1); + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + + /* + * Enable in-kernel emulation of PSCI to ensure that calls are denied + * due to the SMCCC filter, not because of KVM. + */ + init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2); + + *vcpu = aarch64_vcpu_add(vm, 0, &init, guest_main); + return vm; +} + +static void test_pad_must_be_zero(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + struct kvm_smccc_filter filter = { + .base = PSCI_0_2_FN_PSCI_VERSION, + .nr_functions = 1, + .action = KVM_SMCCC_FILTER_DENY, + .pad = { -1 }, + }; + int r; + + r = __kvm_device_attr_set(vm->fd, KVM_ARM_VM_SMCCC_CTRL, + KVM_ARM_VM_SMCCC_FILTER, &filter); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Setting filter with nonzero padding should return EINVAL"); +} + +/* Ensure that userspace cannot filter the Arm Architecture SMCCC range */ +static void test_filter_reserved_range(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, ARM_SMCCC_ARCH_WORKAROUND_1, + 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter reserved range should return EEXIST"); + + kvm_vm_free(vm); +} + +static void test_invalid_nr_functions(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 0, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to filter 0 functions should return EINVAL"); + + kvm_vm_free(vm); +} + +static void test_overflow_nr_functions(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, ~0, ~0, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to overflow filter range should return EINVAL"); + + kvm_vm_free(vm); +} + +static void test_reserved_action(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, -1); + TEST_ASSERT(r < 0 && errno == EINVAL, + "Attempt to use reserved filter action should return EINVAL"); + + kvm_vm_free(vm); +} + + +/* Test that overlapping configurations of the SMCCC filter are rejected */ +static void test_filter_overlap(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = setup_vm(&vcpu); + int r; + + set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, KVM_SMCCC_FILTER_DENY); + + r = __set_smccc_filter(vm, PSCI_0_2_FN64_CPU_ON, 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter already configured range should return EEXIST"); + + kvm_vm_free(vm); +} + +static void expect_call_denied(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + if (get_ucall(vcpu, &uc) != UCALL_SYNC) + TEST_FAIL("Unexpected ucall: %lu\n", uc.cmd); + + TEST_ASSERT(uc.args[1] == SMCCC_RET_NOT_SUPPORTED, + "Unexpected SMCCC return code: %lu", uc.args[1]); +} + +/* Denied SMCCC calls have a return code of SMCCC_RET_NOT_SUPPORTED */ +static void test_filter_denied(void) +{ + enum smccc_conduit conduit; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + for_each_conduit(conduit) { + vm = setup_vm(&vcpu); + + set_smccc_filter(vm, PSCI_0_2_FN_PSCI_VERSION, 1, KVM_SMCCC_FILTER_DENY); + vcpu_args_set(vcpu, 2, PSCI_0_2_FN_PSCI_VERSION, conduit); + + vcpu_run(vcpu); + expect_call_denied(vcpu); + + kvm_vm_free(vm); + } +} + +static void expect_call_fwd_to_user(struct kvm_vcpu *vcpu, uint32_t func_id, + enum smccc_conduit conduit) +{ + struct kvm_run *run = vcpu->run; + + TEST_ASSERT(run->exit_reason == KVM_EXIT_HYPERCALL, + "Unexpected exit reason: %u", run->exit_reason); + TEST_ASSERT(run->hypercall.nr == func_id, + "Unexpected SMCCC function: %llu", run->hypercall.nr); + + if (conduit == SMC_INSN) + TEST_ASSERT(run->hypercall.flags & KVM_HYPERCALL_EXIT_SMC, + "KVM_HYPERCALL_EXIT_SMC is not set"); + else + TEST_ASSERT(!(run->hypercall.flags & KVM_HYPERCALL_EXIT_SMC), + "KVM_HYPERCAL_EXIT_SMC is set"); +} + +/* SMCCC calls forwarded to userspace cause KVM_EXIT_HYPERCALL exits */ +static void test_filter_fwd_to_user(void) +{ + enum smccc_conduit conduit; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + for_each_conduit(conduit) { + vm = setup_vm(&vcpu); + + set_smccc_filter(vm, PSCI_0_2_FN_PSCI_VERSION, 1, KVM_SMCCC_FILTER_FWD_TO_USER); + vcpu_args_set(vcpu, 2, PSCI_0_2_FN_PSCI_VERSION, conduit); + + vcpu_run(vcpu); + expect_call_fwd_to_user(vcpu, PSCI_0_2_FN_PSCI_VERSION, conduit); + + kvm_vm_free(vm); + } +} + +static bool kvm_supports_smccc_filter(void) +{ + struct kvm_vm *vm = vm_create_barebones(); + int r; + + r = __kvm_has_device_attr(vm->fd, KVM_ARM_VM_SMCCC_CTRL, KVM_ARM_VM_SMCCC_FILTER); + + kvm_vm_free(vm); + return !r; +} + +int main(void) +{ + TEST_REQUIRE(kvm_supports_smccc_filter()); + + test_pad_must_be_zero(); + test_invalid_nr_functions(); + test_overflow_nr_functions(); + test_reserved_action(); + test_filter_reserved_range(); + test_filter_overlap(); + test_filter_denied(); + test_filter_fwd_to_user(); +} -- GitLab From ad813605f77553f5e73cd23913fa7591b0d794f6 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 21 Mar 2023 14:12:55 -0400 Subject: [PATCH 2068/5631] USB: serial: quatech2: remove unused qt2_setdevice function clang with W=1 reports drivers/usb/serial/quatech2.c:179:19: error: unused function 'qt2_setdevice' [-Werror,-Wunused-function] static inline int qt2_setdevice(struct usb_device *dev, u8 *data) ^ This function is not used, so remove it. Signed-off-by: Tom Rix Signed-off-by: Johan Hovold --- drivers/usb/serial/quatech2.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c index 6fca40ace83a..fee581409bf6 100644 --- a/drivers/usb/serial/quatech2.c +++ b/drivers/usb/serial/quatech2.c @@ -176,14 +176,6 @@ static inline int qt2_control_msg(struct usb_device *dev, NULL, 0, QT2_USB_TIMEOUT); } -static inline int qt2_setdevice(struct usb_device *dev, u8 *data) -{ - u16 x = ((u16) (data[1] << 8) | (u16) (data[0])); - - return qt2_control_msg(dev, QT_SET_GET_DEVICE, x, 0); -} - - static inline int qt2_getregister(struct usb_device *dev, u8 uart, u8 reg, -- GitLab From 80472350d9d1b8c4094b48a2dc8fdea172dab85b Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 29 Mar 2023 09:43:42 +0200 Subject: [PATCH 2069/5631] staging: vme: clean up duplicate definitions of dependencies The file staging/vme_user/Kconfig is only included by the top-level staging/Kconfig if STAGING is enabled. So, there is no need to mention the dependency on STAGING within the vme_user Kconfig file. Further, the config VME_USER is already within the "if VME_BUS" block, so there is no need to mention the dependency on VME_BUS. Clean up these duplications of dependencies. No semantic change. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230329074342.27595-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/vme_user/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/staging/vme_user/Kconfig b/drivers/staging/vme_user/Kconfig index c8eabf8f40f1..d65cc5510649 100644 --- a/drivers/staging/vme_user/Kconfig +++ b/drivers/staging/vme_user/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig VME_BUS bool "VME bridge support" - depends on STAGING && PCI + depends on PCI help If you say Y here you get support for the VME bridge Framework. @@ -28,7 +28,6 @@ comment "VME Device Drivers" config VME_USER tristate "VME user space access driver" - depends on STAGING && VME_BUS help If you say Y here you want to be able to access a limited number of VME windows in a manner at least semi-compatible with the interface -- GitLab From 7c2455436242b1187e86e954aae4b04cfc81b14c Mon Sep 17 00:00:00 2001 From: Daniel Watson Date: Fri, 31 Mar 2023 16:00:24 -0700 Subject: [PATCH 2070/5631] staging: rtl8723bs: indent with tab, align with space Use tabs to indent code and spaces to align in order to make the code consistent and easier to read. Signed-off-by: Daniel Watson Link: https://lore.kernel.org/r/ZCdmCBIdabBGqm11@trent-reznor Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8723bs/include/ieee80211.h | 49 ++++++++++--------- 1 file changed, 26 insertions(+), 23 deletions(-) diff --git a/drivers/staging/rtl8723bs/include/ieee80211.h b/drivers/staging/rtl8723bs/include/ieee80211.h index 9041d8dc5fb1..1098b0209200 100644 --- a/drivers/staging/rtl8723bs/include/ieee80211.h +++ b/drivers/staging/rtl8723bs/include/ieee80211.h @@ -174,7 +174,7 @@ struct ieee_param { u8 reserved[32]; u8 data[]; } wpa_ie; - struct{ + struct{ int command; int reason_code; } mlme; @@ -271,10 +271,10 @@ struct eapol { #define P80211_OUI_LEN 3 struct ieee80211_snap_hdr { - u8 dsap; /* always 0xAA */ - u8 ssap; /* always 0xAA */ - u8 ctrl; /* always 0x03 */ - u8 oui[P80211_OUI_LEN]; /* organizational universal id */ + u8 dsap; /* always 0xAA */ + u8 ssap; /* always 0xAA */ + u8 ctrl; /* always 0x03 */ + u8 oui[P80211_OUI_LEN]; /* organizational universal id */ } __attribute__ ((packed)); #define SNAP_SIZE sizeof(struct ieee80211_snap_hdr) @@ -342,12 +342,13 @@ struct ieee80211_snap_hdr { #define IEEE80211_OFDM_RATE_48MB_MASK (1<<10) #define IEEE80211_OFDM_RATE_54MB_MASK (1<<11) -#define IEEE80211_CCK_RATES_MASK 0x0000000F +#define IEEE80211_CCK_RATES_MASK 0x0000000F #define IEEE80211_CCK_BASIC_RATES_MASK (IEEE80211_CCK_RATE_1MB_MASK | \ IEEE80211_CCK_RATE_2MB_MASK) -#define IEEE80211_CCK_DEFAULT_RATES_MASK (IEEE80211_CCK_BASIC_RATES_MASK | \ - IEEE80211_CCK_RATE_5MB_MASK | \ - IEEE80211_CCK_RATE_11MB_MASK) +#define IEEE80211_CCK_DEFAULT_RATES_MASK \ + (IEEE80211_CCK_BASIC_RATES_MASK | \ + IEEE80211_CCK_RATE_5MB_MASK | \ + IEEE80211_CCK_RATE_11MB_MASK) #define IEEE80211_OFDM_RATES_MASK 0x00000FF0 #define IEEE80211_OFDM_BASIC_RATES_MASK (IEEE80211_OFDM_RATE_6MB_MASK | \ @@ -359,8 +360,9 @@ struct ieee80211_snap_hdr { IEEE80211_OFDM_RATE_36MB_MASK | \ IEEE80211_OFDM_RATE_48MB_MASK | \ IEEE80211_OFDM_RATE_54MB_MASK) -#define IEEE80211_DEFAULT_RATES_MASK (IEEE80211_OFDM_DEFAULT_RATES_MASK | \ - IEEE80211_CCK_DEFAULT_RATES_MASK) +#define IEEE80211_DEFAULT_RATES_MASK \ + (IEEE80211_OFDM_DEFAULT_RATES_MASK | \ + IEEE80211_CCK_DEFAULT_RATES_MASK) #define IEEE80211_NUM_OFDM_RATES 8 #define IEEE80211_NUM_CCK_RATES 4 @@ -509,7 +511,7 @@ Total: 28-2340 bytes static inline int is_multicast_mac_addr(const u8 *addr) { - return ((addr[0] != 0xff) && (0x01 & addr[0])); + return ((addr[0] != 0xff) && (0x01 & addr[0])); } static inline int is_broadcast_mac_addr(const u8 *addr) @@ -612,17 +614,18 @@ enum { * @RTW_IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel * is not permitted. */ - enum rtw_ieee80211_channel_flags { - RTW_IEEE80211_CHAN_DISABLED = 1<<0, - RTW_IEEE80211_CHAN_PASSIVE_SCAN = 1<<1, - RTW_IEEE80211_CHAN_NO_IBSS = 1<<2, - RTW_IEEE80211_CHAN_RADAR = 1<<3, - RTW_IEEE80211_CHAN_NO_HT40PLUS = 1<<4, - RTW_IEEE80211_CHAN_NO_HT40MINUS = 1<<5, - }; - - #define RTW_IEEE80211_CHAN_NO_HT40 \ - (RTW_IEEE80211_CHAN_NO_HT40PLUS | RTW_IEEE80211_CHAN_NO_HT40MINUS) +enum rtw_ieee80211_channel_flags { + RTW_IEEE80211_CHAN_DISABLED = 1<<0, + RTW_IEEE80211_CHAN_PASSIVE_SCAN = 1<<1, + RTW_IEEE80211_CHAN_NO_IBSS = 1<<2, + RTW_IEEE80211_CHAN_RADAR = 1<<3, + RTW_IEEE80211_CHAN_NO_HT40PLUS = 1<<4, + RTW_IEEE80211_CHAN_NO_HT40MINUS = 1<<5, +}; + +#define RTW_IEEE80211_CHAN_NO_HT40 \ + (RTW_IEEE80211_CHAN_NO_HT40PLUS | \ + RTW_IEEE80211_CHAN_NO_HT40MINUS) /* Represent channel details, subset of ieee80211_channel */ struct rtw_ieee80211_channel { -- GitLab From d8571801a61c01841ac1813e0fb97048c2505a6a Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:51:42 +0200 Subject: [PATCH 2071/5631] staging: rtl8192e: Remove RF_Type from .._dm_tx_update_tssi_weak_signal Remove RF_Type from _rtl92e_dm_tx_update_tssi_weak_signal and _rtl92e_dm_tx_update_tssi_strong_signal as it is unused. Reported-by: kernel test robot Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/95744a9d271723b44b92465809d092f90edf9bc9.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index b5f4d0230da7..258ea66ab2fd 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -475,8 +475,7 @@ static u8 CCKSwingTable_Ch14[CCK_TABLE_LEN][8] = { #define Tssi_Report_Value2 0x13e #define FW_Busy_Flag 0x13f -static void _rtl92e_dm_tx_update_tssi_weak_signal(struct net_device *dev, - u8 RF_Type) +static void _rtl92e_dm_tx_update_tssi_weak_signal(struct net_device *dev) { struct r8192_priv *p = rtllib_priv(dev); @@ -495,8 +494,7 @@ static void _rtl92e_dm_tx_update_tssi_weak_signal(struct net_device *dev, } } -static void _rtl92e_dm_tx_update_tssi_strong_signal(struct net_device *dev, - u8 RF_Type) +static void _rtl92e_dm_tx_update_tssi_strong_signal(struct net_device *dev) { struct r8192_priv *p = rtllib_priv(dev); @@ -610,10 +608,9 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) return; } if (Avg_TSSI_Meas_from_driver < tssi_13dBm - E_FOR_TX_POWER_TRACK) - _rtl92e_dm_tx_update_tssi_weak_signal(dev, - RF_Type); + _rtl92e_dm_tx_update_tssi_weak_signal(dev); else - _rtl92e_dm_tx_update_tssi_strong_signal(dev, RF_Type); + _rtl92e_dm_tx_update_tssi_strong_signal(dev); priv->cck_present_attn_diff = priv->rfa_txpowertrackingindex_real - priv->rfa_txpowertracking_default; -- GitLab From b7119698bcca83d6d755b866bcf7328314d9cde0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:51:47 +0200 Subject: [PATCH 2072/5631] staging: rtl8192e: Remove enum RF_1T2R and RF_Type enum RF_1T2R is used to initialize a local variable RF_Type that is then shifted. The result of the shift is zero. Remove code that has always the same result to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/6c29e709f5c328703870ca8e7d61ee6338886fa7.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 5 ++--- drivers/staging/rtl8192e/rtllib.h | 4 ---- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 258ea66ab2fd..a21b3798db48 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -518,7 +518,7 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) struct dcmd_txcmd tx_cmd; u8 powerlevelOFDM24G; int i = 0, j = 0, k = 0; - u8 RF_Type, tmp_report[5] = {0, 0, 0, 0, 0}; + u8 tmp_report[5] = {0, 0, 0, 0, 0}; u32 Value; u8 Pwr_Flag; u16 Avg_TSSI_Meas, tssi_13dBm, Avg_TSSI_Meas_from_driver = 0; @@ -529,8 +529,7 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) priv->rtllib->bdynamic_txpower_enable = false; powerlevelOFDM24G = priv->pwr_track >> 24; - RF_Type = RF_1T2R; - Value = (RF_Type<<8) | powerlevelOFDM24G; + Value = powerlevelOFDM24G; for (j = 0; j <= 30; j++) { diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 197c0a44ebd6..7d83a4c322cf 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -433,10 +433,6 @@ enum led_ctl_mode { LED_CTL_START_TO_LINK = 8, }; -enum rt_rf_type_def { - RF_1T2R = 0, -}; - enum wireless_mode { WIRELESS_MODE_UNKNOWN = 0x00, WIRELESS_MODE_A = 0x01, -- GitLab From 0be699ab84b1e796173bbc8a055f8a1b30da85a9 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:51:54 +0200 Subject: [PATCH 2073/5631] staging: rtl8192e: Remove local variable Value and powerlevelOFDM24G powerlevelOFDM24G is set to priv->pwr_track. Then Value is set to powerlevelOFDM24G and then only once used. Remove both variables to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/2076dc2f8f5afc11cbab23bc3f5d4ace9bf33bfd.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index a21b3798db48..cde41111012a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -516,10 +516,8 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) struct r8192_priv *priv = rtllib_priv(dev); bool viviflag = false; struct dcmd_txcmd tx_cmd; - u8 powerlevelOFDM24G; int i = 0, j = 0, k = 0; u8 tmp_report[5] = {0, 0, 0, 0, 0}; - u32 Value; u8 Pwr_Flag; u16 Avg_TSSI_Meas, tssi_13dBm, Avg_TSSI_Meas_from_driver = 0; u32 delta = 0; @@ -528,14 +526,11 @@ static void _rtl92e_dm_tx_power_tracking_callback_tssi(struct net_device *dev) rtl92e_writeb(dev, FW_Busy_Flag, 0); priv->rtllib->bdynamic_txpower_enable = false; - powerlevelOFDM24G = priv->pwr_track >> 24; - Value = powerlevelOFDM24G; - for (j = 0; j <= 30; j++) { tx_cmd.op = TXCMD_SET_TX_PWR_TRACKING; tx_cmd.length = 4; - tx_cmd.value = Value; + tx_cmd.value = priv->pwr_track >> 24; rtl92e_send_cmd_pkt(dev, DESC_PACKET_TYPE_NORMAL, (u8 *)&tx_cmd, sizeof(struct dcmd_txcmd)); mdelay(1); -- GitLab From 8e45222d792cf50ff17632892d4ab932a61e62f0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:51:59 +0200 Subject: [PATCH 2074/5631] staging: rtl8192e: Remove case customer_id = RT_CID_DLINK customer_id is initialize to zero. Changing customer_id to RT_CID_DLINK would not change the program execution as there is no equation for RT_CID_DLINK. Remove useless code lines to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/e4ecef11015c32c9909cd07e0939c4de53fd501a.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 6 ------ drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 3 files changed, 8 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index 1da14e737aa4..cbe66b4a6ad9 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -431,9 +431,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) else priv->chnl_plan = priv->reg_chnl_plan; - if (priv->eeprom_vid == 0x1186 && priv->eeprom_did == 0x3304) - priv->customer_id = RT_CID_DLINK; - switch (priv->eeprom_customer_id) { case EEPROM_CID_DEFAULT: priv->customer_id = RT_CID_DEFAULT; @@ -460,9 +457,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) case EEPROM_CID_Pronet: priv->customer_id = RT_CID_PRONET; break; - case EEPROM_CID_DLINK: - priv->customer_id = RT_CID_DLINK; - break; case EEPROM_CID_WHQL: break; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h index 99640c4779f7..706d024bcfd1 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h @@ -37,7 +37,6 @@ enum baseband_config { #define EEPROM_CID_NetCore 0x5 #define EEPROM_CID_Nettronix 0x6 #define EEPROM_CID_Pronet 0x7 -#define EEPROM_CID_DLINK 0x8 #define EEPROM_CID_WHQL 0xFE enum _RTL8192PCI_HW { MAC0 = 0x000, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 1e99eb833405..91d634f5d3e7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -134,7 +134,6 @@ enum rt_customer_id { RT_CID_TOSHIBA = 9, RT_CID_819X_NETCORE = 10, RT_CID_Nettronix = 11, - RT_CID_DLINK = 12, RT_CID_PRONET = 13, }; -- GitLab From 795916c1c8be85fc49bf50823343b075517fe573 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:52:05 +0200 Subject: [PATCH 2075/5631] staging: rtl8192e: Remove case customer_id = RT_CID_819x_CAMEO, .. customer_id is initialize to zero. Changing customer_id to RT_CID_819x_CAMEO, RT_CID_819x_RUNTOP, RT_CID_Nettronix or RT_CID_PRONET would not change the program execution as there is no equation for RT_CID_819x_CAMEO, RT_CID_819x_RUNTOP, RT_CID_Nettronix or RT_CID_PRONET. Remove useless code lines to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/b546933897acc20a6ac5be2bd5ef5ad979599c66.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 12 ------------ drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h | 4 ---- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 4 ---- 3 files changed, 20 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index cbe66b4a6ad9..df8de35cbe0e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -435,12 +435,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) case EEPROM_CID_DEFAULT: priv->customer_id = RT_CID_DEFAULT; break; - case EEPROM_CID_CAMEO: - priv->customer_id = RT_CID_819x_CAMEO; - break; - case EEPROM_CID_RUNTOP: - priv->customer_id = RT_CID_819x_RUNTOP; - break; case EEPROM_CID_NetCore: priv->customer_id = RT_CID_819X_NETCORE; break; @@ -451,12 +445,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) else priv->chnl_plan = 0x0; break; - case EEPROM_CID_Nettronix: - priv->customer_id = RT_CID_Nettronix; - break; - case EEPROM_CID_Pronet: - priv->customer_id = RT_CID_PRONET; - break; case EEPROM_CID_WHQL: break; diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h index 706d024bcfd1..4ee78b7a558e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h @@ -31,12 +31,8 @@ enum baseband_config { #define EEPROM_TxPwIndex_OFDM_24G 0x3A #define EEPROM_CID_DEFAULT 0x0 -#define EEPROM_CID_CAMEO 0x1 -#define EEPROM_CID_RUNTOP 0x2 #define EEPROM_CID_TOSHIBA 0x4 #define EEPROM_CID_NetCore 0x5 -#define EEPROM_CID_Nettronix 0x6 -#define EEPROM_CID_Pronet 0x7 #define EEPROM_CID_WHQL 0xFE enum _RTL8192PCI_HW { MAC0 = 0x000, diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 91d634f5d3e7..2b2d8af4cf6e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -129,12 +129,8 @@ enum dcmg_txcmd_op { enum rt_customer_id { RT_CID_DEFAULT = 0, - RT_CID_819x_CAMEO = 6, - RT_CID_819x_RUNTOP = 7, RT_CID_TOSHIBA = 9, RT_CID_819X_NETCORE = 10, - RT_CID_Nettronix = 11, - RT_CID_PRONET = 13, }; enum reset_type { -- GitLab From 3642e50acc63b92123b95bf8a63da204e44c4efb Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 2 Apr 2023 11:52:13 +0200 Subject: [PATCH 2076/5631] staging: rtl8192e: Remove case customer_id = RT_CID_DEFAULT, .. customer_id is initialize to zero. Changing customer_id to RT_CID_DEFAULT will not change customer_id as it is already zero. default and EEPROM_CID_WHQL contain only a break. Remove useless code lines to increase readability. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/58df9db5da84991206266e739b2a12c893d1be8e.1680427945.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c | 8 -------- drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h | 2 -- 2 files changed, 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c index df8de35cbe0e..aed53fedeb61 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_dev.c @@ -432,9 +432,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) priv->chnl_plan = priv->reg_chnl_plan; switch (priv->eeprom_customer_id) { - case EEPROM_CID_DEFAULT: - priv->customer_id = RT_CID_DEFAULT; - break; case EEPROM_CID_NetCore: priv->customer_id = RT_CID_819X_NETCORE; break; @@ -445,11 +442,6 @@ static void _rtl92e_read_eeprom_info(struct net_device *dev) else priv->chnl_plan = 0x0; break; - - case EEPROM_CID_WHQL: - break; - default: - break; } if (priv->chnl_plan > CHANNEL_PLAN_LEN - 1) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h index 4ee78b7a558e..f4d4b01630a2 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_hw.h @@ -30,10 +30,8 @@ enum baseband_config { #define EEPROM_TxPwIndex_CCK 0x2C #define EEPROM_TxPwIndex_OFDM_24G 0x3A -#define EEPROM_CID_DEFAULT 0x0 #define EEPROM_CID_TOSHIBA 0x4 #define EEPROM_CID_NetCore 0x5 -#define EEPROM_CID_WHQL 0xFE enum _RTL8192PCI_HW { MAC0 = 0x000, MAC4 = 0x004, -- GitLab From f395d3f9d2d08a8b312eab72b9094f4f9cb72636 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sun, 2 Apr 2023 19:32:42 +0500 Subject: [PATCH 2077/5631] staging: rtl8192e: remove extra blank lines in rtllib_crypt_ccmp.c Remove extra blank lines as suggested by the Linux kernel coding-style. These issues were reported by checkpatch. "CHECK: Please don't use multiple blank lines" Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/283265f6a5ff938f8425e14af86cee9e2da36318.1680445545.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c index a8d22da8bc9a..eb7b6deb2ca7 100644 --- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c +++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c @@ -74,7 +74,6 @@ static void *rtllib_ccmp_init(int key_idx) return NULL; } - static void rtllib_ccmp_deinit(void *priv) { struct rtllib_ccmp_data *_priv = priv; @@ -84,7 +83,6 @@ static void rtllib_ccmp_deinit(void *priv) kfree(priv); } - static int ccmp_init_iv_and_aad(struct rtllib_hdr_4addr *hdr, u8 *pn, u8 *iv, u8 *aad) { @@ -150,8 +148,6 @@ static int ccmp_init_iv_and_aad(struct rtllib_hdr_4addr *hdr, return aad_len; } - - static int rtllib_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) { struct rtllib_ccmp_data *key = priv; @@ -220,7 +216,6 @@ static int rtllib_ccmp_encrypt(struct sk_buff *skb, int hdr_len, void *priv) return 0; } - static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) { struct rtllib_ccmp_data *key = priv; @@ -315,7 +310,6 @@ static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) return keyidx; } - static int rtllib_ccmp_set_key(void *key, int len, u8 *seq, void *priv) { struct rtllib_ccmp_data *data = priv; @@ -349,7 +343,6 @@ static int rtllib_ccmp_set_key(void *key, int len, u8 *seq, void *priv) return 0; } - static int rtllib_ccmp_get_key(void *key, int len, u8 *seq, void *priv) { struct rtllib_ccmp_data *data = priv; @@ -373,7 +366,6 @@ static int rtllib_ccmp_get_key(void *key, int len, u8 *seq, void *priv) return CCMP_TK_LEN; } - static void rtllib_ccmp_print_stats(struct seq_file *m, void *priv) { struct rtllib_ccmp_data *ccmp = priv; @@ -403,13 +395,11 @@ static struct lib80211_crypto_ops rtllib_crypt_ccmp = { .owner = THIS_MODULE, }; - static int __init rtllib_crypto_ccmp_init(void) { return lib80211_register_crypto_ops(&rtllib_crypt_ccmp); } - static void __exit rtllib_crypto_ccmp_exit(void) { lib80211_unregister_crypto_ops(&rtllib_crypt_ccmp); -- GitLab From 7cf3f17b58e20c8a3b9266b8aa205cafb2e10d3c Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sun, 2 Apr 2023 19:32:43 +0500 Subject: [PATCH 2078/5631] staging: rtl8192e: fix alignment to match open parenthesis Fix alignemnt to match opening parenthesis as suggested by Linux kernel coding-style. This issue is reported by checkpatch. Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/76814f7a2a026ef195334b0c42ecd2aeb8e8ea40.1680445545.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c index eb7b6deb2ca7..8d3067a6ccca 100644 --- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c +++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c @@ -332,7 +332,7 @@ static int rtllib_ccmp_set_key(void *key, int len, u8 *seq, void *priv) data->rx_pn[5] = seq[0]; } if (crypto_aead_setauthsize(data->tfm, CCMP_MIC_LEN) || - crypto_aead_setkey(data->tfm, data->key, CCMP_TK_LEN)) + crypto_aead_setkey(data->tfm, data->key, CCMP_TK_LEN)) return -1; } else if (len == 0) { data->key_set = 0; -- GitLab From 73749c7fb4ab99eb9930ed400ce56eb18a077983 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sun, 2 Apr 2023 19:32:44 +0500 Subject: [PATCH 2079/5631] staging: rtl8192e: avoid CamelCase Linux kernel coding-style suggests to not use mixed-case names. Fix checkpatch issue by changing the variable name from camel case to snake case. Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/ebfd9c40400eac872b9af2a5120b0829ff71e077.1680445545.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c index 8d3067a6ccca..d37ca72678c8 100644 --- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c +++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c @@ -34,7 +34,7 @@ struct rtllib_ccmp_data { u8 tx_pn[CCMP_PN_LEN]; u8 rx_pn[CCMP_PN_LEN]; - u32 dot11RSNAStatsCCMPFormatErrors; + u32 dot11rsna_stats_ccmp_format_errors; u32 dot11RSNAStatsCCMPReplays; u32 dot11RSNAStatsCCMPDecryptErrors; @@ -226,7 +226,7 @@ static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) u8 pn[6]; if (skb->len < hdr_len + CCMP_HDR_LEN + CCMP_MIC_LEN) { - key->dot11RSNAStatsCCMPFormatErrors++; + key->dot11rsna_stats_ccmp_format_errors++; return -1; } @@ -238,7 +238,7 @@ static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) pr_debug("CCMP: received packet without ExtIV flag from %pM\n", hdr->addr2); } - key->dot11RSNAStatsCCMPFormatErrors++; + key->dot11rsna_stats_ccmp_format_errors++; return -2; } keyidx >>= 6; @@ -374,7 +374,7 @@ static void rtllib_ccmp_print_stats(struct seq_file *m, void *priv) "key[%d] alg=CCMP key_set=%d tx_pn=%pM rx_pn=%pM format_errors=%d replays=%d decrypt_errors=%d\n", ccmp->key_idx, ccmp->key_set, ccmp->tx_pn, ccmp->rx_pn, - ccmp->dot11RSNAStatsCCMPFormatErrors, + ccmp->dot11rsna_stats_ccmp_format_errors, ccmp->dot11RSNAStatsCCMPReplays, ccmp->dot11RSNAStatsCCMPDecryptErrors); } -- GitLab From f60fc1311bcc7601750ec38bb215d6202c1c9461 Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sun, 2 Apr 2023 19:32:45 +0500 Subject: [PATCH 2080/5631] staging: rtl8192e: avoid CamelCase Linux kernel coding-style suggests to not use mixed-case names. Fix checkpatch issue by changing the variable name from camel case to snake case. Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/7166160c0face9e32dbb28c44727eb8856173f0a.1680445545.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c index d37ca72678c8..448c0a931c78 100644 --- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c +++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c @@ -35,7 +35,7 @@ struct rtllib_ccmp_data { u8 rx_pn[CCMP_PN_LEN]; u32 dot11rsna_stats_ccmp_format_errors; - u32 dot11RSNAStatsCCMPReplays; + u32 dot11rsna_stats_ccmp_replays; u32 dot11RSNAStatsCCMPDecryptErrors; int key_idx; @@ -263,7 +263,7 @@ static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) pn[5] = pos[0]; pos += 8; if (memcmp(pn, key->rx_pn, CCMP_PN_LEN) <= 0) { - key->dot11RSNAStatsCCMPReplays++; + key->dot11rsna_stats_ccmp_replays++; return -4; } if (!tcb_desc->bHwSec) { @@ -375,7 +375,7 @@ static void rtllib_ccmp_print_stats(struct seq_file *m, void *priv) ccmp->key_idx, ccmp->key_set, ccmp->tx_pn, ccmp->rx_pn, ccmp->dot11rsna_stats_ccmp_format_errors, - ccmp->dot11RSNAStatsCCMPReplays, + ccmp->dot11rsna_stats_ccmp_replays, ccmp->dot11RSNAStatsCCMPDecryptErrors); } -- GitLab From 85f76d9301ff439ef2c11ce0f854468285133f0e Mon Sep 17 00:00:00 2001 From: Khadija Kamran Date: Sun, 2 Apr 2023 19:32:46 +0500 Subject: [PATCH 2081/5631] staging: rtl8192e: avoid CamelCase Linux kernel coding-style suggests to not use mixed-case names. Fix checkpatch issue by changing the variable name from camel case to snake case. Signed-off-by: Khadija Kamran Tested-by: Philipp Hortmann Link: https://lore.kernel.org/r/d29ff5db6f19d79ee762a835db88155bee2aefba.1680445545.git.kamrankhadijadj@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c index 448c0a931c78..f88096bcb181 100644 --- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c +++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c @@ -36,7 +36,7 @@ struct rtllib_ccmp_data { u32 dot11rsna_stats_ccmp_format_errors; u32 dot11rsna_stats_ccmp_replays; - u32 dot11RSNAStatsCCMPDecryptErrors; + u32 dot11rsna_stats_ccmp_decrypt_errors; int key_idx; @@ -296,7 +296,7 @@ static int rtllib_ccmp_decrypt(struct sk_buff *skb, int hdr_len, void *priv) pr_debug("CCMP: decrypt failed: STA= %pM\n", hdr->addr2); } - key->dot11RSNAStatsCCMPDecryptErrors++; + key->dot11rsna_stats_ccmp_decrypt_errors++; return -5; } @@ -376,7 +376,7 @@ static void rtllib_ccmp_print_stats(struct seq_file *m, void *priv) ccmp->tx_pn, ccmp->rx_pn, ccmp->dot11rsna_stats_ccmp_format_errors, ccmp->dot11rsna_stats_ccmp_replays, - ccmp->dot11RSNAStatsCCMPDecryptErrors); + ccmp->dot11rsna_stats_ccmp_decrypt_errors); } static struct lib80211_crypto_ops rtllib_crypt_ccmp = { -- GitLab From 41500f45356277f20dbca6e40b33f799f3d1e72a Mon Sep 17 00:00:00 2001 From: Sumitra Sharma Date: Tue, 4 Apr 2023 23:30:03 -0700 Subject: [PATCH 2082/5631] staging: rtl8192e: Add blank lines after declarations Add blank lines after declarations to adhere to the Linux kernel coding-style. Check reported by checkpatch.pl "CHECK: Please use a blank line after function/struct/union/enum declarations" Signed-off-by: Sumitra Sharma Link: https://lore.kernel.org/r/20230405063003.GA218972@sumitra.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 7d83a4c322cf..1a0177cd64af 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -967,6 +967,7 @@ static inline const char *eap_get_type(int type) return ((u32)type >= ARRAY_SIZE(eap_types)) ? "Unknown" : eap_types[type]; } + static inline u8 Frame_QoSTID(u8 *buf) { struct rtllib_hdr_3addr *hdr; @@ -1199,6 +1200,7 @@ struct rx_reorder_entry { u16 SeqNum; struct rtllib_rxb *prxb; }; + enum fsync_state { Default_Fsync, HW_Fsync, @@ -1325,6 +1327,7 @@ struct sw_cam_table { u8 key_index; }; + #define TOTAL_CAM_ENTRY 32 struct rate_adaptive { u8 rate_adaptive_disabled; -- GitLab From c61f19ec3be35271fc005dac34390d9c5e1a2737 Mon Sep 17 00:00:00 2001 From: Hal Feng Date: Sat, 1 Apr 2023 19:19:15 +0800 Subject: [PATCH 2083/5631] clk: starfive: Replace SOC_STARFIVE with ARCH_STARFIVE Using ARCH_FOO symbol is preferred than SOC_FOO. Set obj-y for starfive/ in Makefile, so the StarFive drivers can be compiled with COMPILE_TEST=y but ARCH_STARFIVE=n. Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Reviewed-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/clk/Makefile | 2 +- drivers/clk/starfive/Kconfig | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e3ca0d058a25..3bed88d67a3a 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -117,7 +117,7 @@ obj-$(CONFIG_PLAT_SPEAR) += spear/ obj-y += sprd/ obj-$(CONFIG_ARCH_STI) += st/ obj-$(CONFIG_ARCH_STM32) += stm32/ -obj-$(CONFIG_SOC_STARFIVE) += starfive/ +obj-y += starfive/ obj-$(CONFIG_ARCH_SUNXI) += sunxi/ obj-y += sunxi-ng/ obj-$(CONFIG_ARCH_TEGRA) += tegra/ diff --git a/drivers/clk/starfive/Kconfig b/drivers/clk/starfive/Kconfig index 003bd2d56ce7..ef3517f4a276 100644 --- a/drivers/clk/starfive/Kconfig +++ b/drivers/clk/starfive/Kconfig @@ -2,8 +2,8 @@ config CLK_STARFIVE_JH7100 bool "StarFive JH7100 clock support" - depends on SOC_STARFIVE || COMPILE_TEST - default SOC_STARFIVE + depends on ARCH_STARFIVE || COMPILE_TEST + default ARCH_STARFIVE help Say yes here to support the clock controller on the StarFive JH7100 SoC. @@ -11,7 +11,7 @@ config CLK_STARFIVE_JH7100 config CLK_STARFIVE_JH7100_AUDIO tristate "StarFive JH7100 audio clock support" depends on CLK_STARFIVE_JH7100 - default m if SOC_STARFIVE + default m if ARCH_STARFIVE help Say Y or M here to support the audio clocks on the StarFive JH7100 SoC. -- GitLab From 00f1cb17aeb71daf3d9ead5d11412c650329d6cf Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:16 +0800 Subject: [PATCH 2084/5631] clk: starfive: Factor out common JH7100 and JH7110 code The clock control registers on the StarFive JH7100 and JH7110 work identically, so factor out the code then drivers for the two SoCs can share it without depending on each other. No functional change. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/clk/starfive/Kconfig | 5 + drivers/clk/starfive/Makefile | 3 +- drivers/clk/starfive/clk-starfive-jh7100.c | 325 -------------------- drivers/clk/starfive/clk-starfive-jh7100.h | 2 + drivers/clk/starfive/clk-starfive-jh71x0.c | 333 +++++++++++++++++++++ 5 files changed, 342 insertions(+), 326 deletions(-) create mode 100644 drivers/clk/starfive/clk-starfive-jh71x0.c diff --git a/drivers/clk/starfive/Kconfig b/drivers/clk/starfive/Kconfig index ef3517f4a276..3ceeb19b5eda 100644 --- a/drivers/clk/starfive/Kconfig +++ b/drivers/clk/starfive/Kconfig @@ -1,8 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 +config CLK_STARFIVE_JH71X0 + bool + config CLK_STARFIVE_JH7100 bool "StarFive JH7100 clock support" depends on ARCH_STARFIVE || COMPILE_TEST + select CLK_STARFIVE_JH71X0 default ARCH_STARFIVE help Say yes here to support the clock controller on the StarFive JH7100 @@ -11,6 +15,7 @@ config CLK_STARFIVE_JH7100 config CLK_STARFIVE_JH7100_AUDIO tristate "StarFive JH7100 audio clock support" depends on CLK_STARFIVE_JH7100 + select CLK_STARFIVE_JH71X0 default m if ARCH_STARFIVE help Say Y or M here to support the audio clocks on the StarFive JH7100 diff --git a/drivers/clk/starfive/Makefile b/drivers/clk/starfive/Makefile index 0fa8ecb9ec1c..82edfa9f9cb8 100644 --- a/drivers/clk/starfive/Makefile +++ b/drivers/clk/starfive/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# StarFive Clock +obj-$(CONFIG_CLK_STARFIVE_JH71X0) += clk-starfive-jh71x0.o + obj-$(CONFIG_CLK_STARFIVE_JH7100) += clk-starfive-jh7100.o obj-$(CONFIG_CLK_STARFIVE_JH7100_AUDIO) += clk-starfive-jh7100-audio.o diff --git a/drivers/clk/starfive/clk-starfive-jh7100.c b/drivers/clk/starfive/clk-starfive-jh7100.c index 691aeebc7092..eea52f16af0d 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100.c +++ b/drivers/clk/starfive/clk-starfive-jh7100.c @@ -7,15 +7,10 @@ * Copyright (C) 2021 Emil Renner Berthing */ -#include #include -#include #include #include -#include -#include #include -#include #include #include @@ -269,326 +264,6 @@ static const struct jh7100_clk_data jh7100_clk_data[] __initconst = { JH7100_GATE(JH7100_CLK_SYSERR_APB, "syserr_apb", 0, JH7100_CLK_APB2_BUS), }; -static struct jh7100_clk *jh7100_clk_from(struct clk_hw *hw) -{ - return container_of(hw, struct jh7100_clk, hw); -} - -static struct jh7100_clk_priv *jh7100_priv_from(struct jh7100_clk *clk) -{ - return container_of(clk, struct jh7100_clk_priv, reg[clk->idx]); -} - -static u32 jh7100_clk_reg_get(struct jh7100_clk *clk) -{ - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); - void __iomem *reg = priv->base + 4 * clk->idx; - - return readl_relaxed(reg); -} - -static void jh7100_clk_reg_rmw(struct jh7100_clk *clk, u32 mask, u32 value) -{ - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); - void __iomem *reg = priv->base + 4 * clk->idx; - unsigned long flags; - - spin_lock_irqsave(&priv->rmw_lock, flags); - value |= readl_relaxed(reg) & ~mask; - writel_relaxed(value, reg); - spin_unlock_irqrestore(&priv->rmw_lock, flags); -} - -static int jh7100_clk_enable(struct clk_hw *hw) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - - jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, JH7100_CLK_ENABLE); - return 0; -} - -static void jh7100_clk_disable(struct clk_hw *hw) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - - jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, 0); -} - -static int jh7100_clk_is_enabled(struct clk_hw *hw) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - - return !!(jh7100_clk_reg_get(clk) & JH7100_CLK_ENABLE); -} - -static unsigned long jh7100_clk_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 div = jh7100_clk_reg_get(clk) & JH7100_CLK_DIV_MASK; - - return div ? parent_rate / div : 0; -} - -static int jh7100_clk_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - unsigned long parent = req->best_parent_rate; - unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); - unsigned long div = min_t(unsigned long, DIV_ROUND_UP(parent, rate), clk->max_div); - unsigned long result = parent / div; - - /* - * we want the result clamped by min_rate and max_rate if possible: - * case 1: div hits the max divider value, which means it's less than - * parent / rate, so the result is greater than rate and min_rate in - * particular. we can't do anything about result > max_rate because the - * divider doesn't go any further. - * case 2: div = DIV_ROUND_UP(parent, rate) which means the result is - * always lower or equal to rate and max_rate. however the result may - * turn out lower than min_rate, but then the next higher rate is fine: - * div - 1 = ceil(parent / rate) - 1 < parent / rate - * and thus - * min_rate <= rate < parent / (div - 1) - */ - if (result < req->min_rate && div > 1) - result = parent / (div - 1); - - req->rate = result; - return 0; -} - -static int jh7100_clk_set_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long parent_rate) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - unsigned long div = clamp(DIV_ROUND_CLOSEST(parent_rate, rate), - 1UL, (unsigned long)clk->max_div); - - jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, div); - return 0; -} - -static unsigned long jh7100_clk_frac_recalc_rate(struct clk_hw *hw, - unsigned long parent_rate) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 reg = jh7100_clk_reg_get(clk); - unsigned long div100 = 100 * (reg & JH7100_CLK_INT_MASK) + - ((reg & JH7100_CLK_FRAC_MASK) >> JH7100_CLK_FRAC_SHIFT); - - return (div100 >= JH7100_CLK_FRAC_MIN) ? 100 * parent_rate / div100 : 0; -} - -static int jh7100_clk_frac_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - unsigned long parent100 = 100 * req->best_parent_rate; - unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); - unsigned long div100 = clamp(DIV_ROUND_CLOSEST(parent100, rate), - JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); - unsigned long result = parent100 / div100; - - /* clamp the result as in jh7100_clk_determine_rate() above */ - if (result > req->max_rate && div100 < JH7100_CLK_FRAC_MAX) - result = parent100 / (div100 + 1); - if (result < req->min_rate && div100 > JH7100_CLK_FRAC_MIN) - result = parent100 / (div100 - 1); - - req->rate = result; - return 0; -} - -static int jh7100_clk_frac_set_rate(struct clk_hw *hw, - unsigned long rate, - unsigned long parent_rate) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - unsigned long div100 = clamp(DIV_ROUND_CLOSEST(100 * parent_rate, rate), - JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); - u32 value = ((div100 % 100) << JH7100_CLK_FRAC_SHIFT) | (div100 / 100); - - jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, value); - return 0; -} - -static u8 jh7100_clk_get_parent(struct clk_hw *hw) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = jh7100_clk_reg_get(clk); - - return (value & JH7100_CLK_MUX_MASK) >> JH7100_CLK_MUX_SHIFT; -} - -static int jh7100_clk_set_parent(struct clk_hw *hw, u8 index) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = (u32)index << JH7100_CLK_MUX_SHIFT; - - jh7100_clk_reg_rmw(clk, JH7100_CLK_MUX_MASK, value); - return 0; -} - -static int jh7100_clk_mux_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - return clk_mux_determine_rate_flags(hw, req, 0); -} - -static int jh7100_clk_get_phase(struct clk_hw *hw) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = jh7100_clk_reg_get(clk); - - return (value & JH7100_CLK_INVERT) ? 180 : 0; -} - -static int jh7100_clk_set_phase(struct clk_hw *hw, int degrees) -{ - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value; - - if (degrees == 0) - value = 0; - else if (degrees == 180) - value = JH7100_CLK_INVERT; - else - return -EINVAL; - - jh7100_clk_reg_rmw(clk, JH7100_CLK_INVERT, value); - return 0; -} - -#ifdef CONFIG_DEBUG_FS -static void jh7100_clk_debug_init(struct clk_hw *hw, struct dentry *dentry) -{ - static const struct debugfs_reg32 jh7100_clk_reg = { - .name = "CTRL", - .offset = 0, - }; - struct jh7100_clk *clk = jh7100_clk_from(hw); - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); - struct debugfs_regset32 *regset; - - regset = devm_kzalloc(priv->dev, sizeof(*regset), GFP_KERNEL); - if (!regset) - return; - - regset->regs = &jh7100_clk_reg; - regset->nregs = 1; - regset->base = priv->base + 4 * clk->idx; - - debugfs_create_regset32("registers", 0400, dentry, regset); -} -#else -#define jh7100_clk_debug_init NULL -#endif - -static const struct clk_ops jh7100_clk_gate_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_div_ops = { - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_fdiv_ops = { - .recalc_rate = jh7100_clk_frac_recalc_rate, - .determine_rate = jh7100_clk_frac_determine_rate, - .set_rate = jh7100_clk_frac_set_rate, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_gdiv_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_mux_ops = { - .determine_rate = jh7100_clk_mux_determine_rate, - .set_parent = jh7100_clk_set_parent, - .get_parent = jh7100_clk_get_parent, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_gmux_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .determine_rate = jh7100_clk_mux_determine_rate, - .set_parent = jh7100_clk_set_parent, - .get_parent = jh7100_clk_get_parent, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_mdiv_ops = { - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .get_parent = jh7100_clk_get_parent, - .set_parent = jh7100_clk_set_parent, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_gmd_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .get_parent = jh7100_clk_get_parent, - .set_parent = jh7100_clk_set_parent, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, -}; - -static const struct clk_ops jh7100_clk_inv_ops = { - .get_phase = jh7100_clk_get_phase, - .set_phase = jh7100_clk_set_phase, - .debug_init = jh7100_clk_debug_init, -}; - -const struct clk_ops *starfive_jh7100_clk_ops(u32 max) -{ - if (max & JH7100_CLK_DIV_MASK) { - if (max & JH7100_CLK_MUX_MASK) { - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gmd_ops; - return &jh7100_clk_mdiv_ops; - } - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gdiv_ops; - if (max == JH7100_CLK_FRAC_MAX) - return &jh7100_clk_fdiv_ops; - return &jh7100_clk_div_ops; - } - - if (max & JH7100_CLK_MUX_MASK) { - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gmux_ops; - return &jh7100_clk_mux_ops; - } - - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gate_ops; - - return &jh7100_clk_inv_ops; -} -EXPORT_SYMBOL_GPL(starfive_jh7100_clk_ops); - static struct clk_hw *jh7100_clk_get(struct of_phandle_args *clkspec, void *data) { struct jh7100_clk_priv *priv = data; diff --git a/drivers/clk/starfive/clk-starfive-jh7100.h b/drivers/clk/starfive/clk-starfive-jh7100.h index f116be5740a5..a8ba6e25b5ce 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100.h +++ b/drivers/clk/starfive/clk-starfive-jh7100.h @@ -4,6 +4,8 @@ #include #include +#include +#include /* register fields */ #define JH7100_CLK_ENABLE BIT(31) diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.c b/drivers/clk/starfive/clk-starfive-jh71x0.c new file mode 100644 index 000000000000..6c07b61b4a32 --- /dev/null +++ b/drivers/clk/starfive/clk-starfive-jh71x0.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * StarFive JH7100 Clock Generator Driver + * + * Copyright (C) 2021-2022 Emil Renner Berthing + */ + +#include +#include +#include +#include + +#include "clk-starfive-jh7100.h" + +static struct jh7100_clk *jh7100_clk_from(struct clk_hw *hw) +{ + return container_of(hw, struct jh7100_clk, hw); +} + +static struct jh7100_clk_priv *jh7100_priv_from(struct jh7100_clk *clk) +{ + return container_of(clk, struct jh7100_clk_priv, reg[clk->idx]); +} + +static u32 jh7100_clk_reg_get(struct jh7100_clk *clk) +{ + struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + void __iomem *reg = priv->base + 4 * clk->idx; + + return readl_relaxed(reg); +} + +static void jh7100_clk_reg_rmw(struct jh7100_clk *clk, u32 mask, u32 value) +{ + struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + void __iomem *reg = priv->base + 4 * clk->idx; + unsigned long flags; + + spin_lock_irqsave(&priv->rmw_lock, flags); + value |= readl_relaxed(reg) & ~mask; + writel_relaxed(value, reg); + spin_unlock_irqrestore(&priv->rmw_lock, flags); +} + +static int jh7100_clk_enable(struct clk_hw *hw) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + + jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, JH7100_CLK_ENABLE); + return 0; +} + +static void jh7100_clk_disable(struct clk_hw *hw) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + + jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, 0); +} + +static int jh7100_clk_is_enabled(struct clk_hw *hw) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + + return !!(jh7100_clk_reg_get(clk) & JH7100_CLK_ENABLE); +} + +static unsigned long jh7100_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 div = jh7100_clk_reg_get(clk) & JH7100_CLK_DIV_MASK; + + return div ? parent_rate / div : 0; +} + +static int jh7100_clk_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + unsigned long parent = req->best_parent_rate; + unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); + unsigned long div = min_t(unsigned long, DIV_ROUND_UP(parent, rate), clk->max_div); + unsigned long result = parent / div; + + /* + * we want the result clamped by min_rate and max_rate if possible: + * case 1: div hits the max divider value, which means it's less than + * parent / rate, so the result is greater than rate and min_rate in + * particular. we can't do anything about result > max_rate because the + * divider doesn't go any further. + * case 2: div = DIV_ROUND_UP(parent, rate) which means the result is + * always lower or equal to rate and max_rate. however the result may + * turn out lower than min_rate, but then the next higher rate is fine: + * div - 1 = ceil(parent / rate) - 1 < parent / rate + * and thus + * min_rate <= rate < parent / (div - 1) + */ + if (result < req->min_rate && div > 1) + result = parent / (div - 1); + + req->rate = result; + return 0; +} + +static int jh7100_clk_set_rate(struct clk_hw *hw, + unsigned long rate, + unsigned long parent_rate) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + unsigned long div = clamp(DIV_ROUND_CLOSEST(parent_rate, rate), + 1UL, (unsigned long)clk->max_div); + + jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, div); + return 0; +} + +static unsigned long jh7100_clk_frac_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 reg = jh7100_clk_reg_get(clk); + unsigned long div100 = 100 * (reg & JH7100_CLK_INT_MASK) + + ((reg & JH7100_CLK_FRAC_MASK) >> JH7100_CLK_FRAC_SHIFT); + + return (div100 >= JH7100_CLK_FRAC_MIN) ? 100 * parent_rate / div100 : 0; +} + +static int jh7100_clk_frac_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + unsigned long parent100 = 100 * req->best_parent_rate; + unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); + unsigned long div100 = clamp(DIV_ROUND_CLOSEST(parent100, rate), + JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); + unsigned long result = parent100 / div100; + + /* clamp the result as in jh7100_clk_determine_rate() above */ + if (result > req->max_rate && div100 < JH7100_CLK_FRAC_MAX) + result = parent100 / (div100 + 1); + if (result < req->min_rate && div100 > JH7100_CLK_FRAC_MIN) + result = parent100 / (div100 - 1); + + req->rate = result; + return 0; +} + +static int jh7100_clk_frac_set_rate(struct clk_hw *hw, + unsigned long rate, + unsigned long parent_rate) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + unsigned long div100 = clamp(DIV_ROUND_CLOSEST(100 * parent_rate, rate), + JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); + u32 value = ((div100 % 100) << JH7100_CLK_FRAC_SHIFT) | (div100 / 100); + + jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, value); + return 0; +} + +static u8 jh7100_clk_get_parent(struct clk_hw *hw) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 value = jh7100_clk_reg_get(clk); + + return (value & JH7100_CLK_MUX_MASK) >> JH7100_CLK_MUX_SHIFT; +} + +static int jh7100_clk_set_parent(struct clk_hw *hw, u8 index) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 value = (u32)index << JH7100_CLK_MUX_SHIFT; + + jh7100_clk_reg_rmw(clk, JH7100_CLK_MUX_MASK, value); + return 0; +} + +static int jh7100_clk_mux_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + return clk_mux_determine_rate_flags(hw, req, 0); +} + +static int jh7100_clk_get_phase(struct clk_hw *hw) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 value = jh7100_clk_reg_get(clk); + + return (value & JH7100_CLK_INVERT) ? 180 : 0; +} + +static int jh7100_clk_set_phase(struct clk_hw *hw, int degrees) +{ + struct jh7100_clk *clk = jh7100_clk_from(hw); + u32 value; + + if (degrees == 0) + value = 0; + else if (degrees == 180) + value = JH7100_CLK_INVERT; + else + return -EINVAL; + + jh7100_clk_reg_rmw(clk, JH7100_CLK_INVERT, value); + return 0; +} + +#ifdef CONFIG_DEBUG_FS +static void jh7100_clk_debug_init(struct clk_hw *hw, struct dentry *dentry) +{ + static const struct debugfs_reg32 jh7100_clk_reg = { + .name = "CTRL", + .offset = 0, + }; + struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + struct debugfs_regset32 *regset; + + regset = devm_kzalloc(priv->dev, sizeof(*regset), GFP_KERNEL); + if (!regset) + return; + + regset->regs = &jh7100_clk_reg; + regset->nregs = 1; + regset->base = priv->base + 4 * clk->idx; + + debugfs_create_regset32("registers", 0400, dentry, regset); +} +#else +#define jh7100_clk_debug_init NULL +#endif + +static const struct clk_ops jh7100_clk_gate_ops = { + .enable = jh7100_clk_enable, + .disable = jh7100_clk_disable, + .is_enabled = jh7100_clk_is_enabled, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_div_ops = { + .recalc_rate = jh7100_clk_recalc_rate, + .determine_rate = jh7100_clk_determine_rate, + .set_rate = jh7100_clk_set_rate, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_fdiv_ops = { + .recalc_rate = jh7100_clk_frac_recalc_rate, + .determine_rate = jh7100_clk_frac_determine_rate, + .set_rate = jh7100_clk_frac_set_rate, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_gdiv_ops = { + .enable = jh7100_clk_enable, + .disable = jh7100_clk_disable, + .is_enabled = jh7100_clk_is_enabled, + .recalc_rate = jh7100_clk_recalc_rate, + .determine_rate = jh7100_clk_determine_rate, + .set_rate = jh7100_clk_set_rate, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_mux_ops = { + .determine_rate = jh7100_clk_mux_determine_rate, + .set_parent = jh7100_clk_set_parent, + .get_parent = jh7100_clk_get_parent, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_gmux_ops = { + .enable = jh7100_clk_enable, + .disable = jh7100_clk_disable, + .is_enabled = jh7100_clk_is_enabled, + .determine_rate = jh7100_clk_mux_determine_rate, + .set_parent = jh7100_clk_set_parent, + .get_parent = jh7100_clk_get_parent, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_mdiv_ops = { + .recalc_rate = jh7100_clk_recalc_rate, + .determine_rate = jh7100_clk_determine_rate, + .get_parent = jh7100_clk_get_parent, + .set_parent = jh7100_clk_set_parent, + .set_rate = jh7100_clk_set_rate, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_gmd_ops = { + .enable = jh7100_clk_enable, + .disable = jh7100_clk_disable, + .is_enabled = jh7100_clk_is_enabled, + .recalc_rate = jh7100_clk_recalc_rate, + .determine_rate = jh7100_clk_determine_rate, + .get_parent = jh7100_clk_get_parent, + .set_parent = jh7100_clk_set_parent, + .set_rate = jh7100_clk_set_rate, + .debug_init = jh7100_clk_debug_init, +}; + +static const struct clk_ops jh7100_clk_inv_ops = { + .get_phase = jh7100_clk_get_phase, + .set_phase = jh7100_clk_set_phase, + .debug_init = jh7100_clk_debug_init, +}; + +const struct clk_ops *starfive_jh7100_clk_ops(u32 max) +{ + if (max & JH7100_CLK_DIV_MASK) { + if (max & JH7100_CLK_MUX_MASK) { + if (max & JH7100_CLK_ENABLE) + return &jh7100_clk_gmd_ops; + return &jh7100_clk_mdiv_ops; + } + if (max & JH7100_CLK_ENABLE) + return &jh7100_clk_gdiv_ops; + if (max == JH7100_CLK_FRAC_MAX) + return &jh7100_clk_fdiv_ops; + return &jh7100_clk_div_ops; + } + + if (max & JH7100_CLK_MUX_MASK) { + if (max & JH7100_CLK_ENABLE) + return &jh7100_clk_gmux_ops; + return &jh7100_clk_mux_ops; + } + + if (max & JH7100_CLK_ENABLE) + return &jh7100_clk_gate_ops; + + return &jh7100_clk_inv_ops; +} +EXPORT_SYMBOL_GPL(starfive_jh7100_clk_ops); -- GitLab From e19aa7861fccced5f72745fcd14b87d281c9bb99 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:17 +0800 Subject: [PATCH 2085/5631] clk: starfive: Rename clk-starfive-jh7100.h to clk-starfive-jh71x0.h Rename clk-starfive-jh7100.h to clk-starfive-jh71x0.h for making the code to be common. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/clk/starfive/clk-starfive-jh7100-audio.c | 2 +- drivers/clk/starfive/clk-starfive-jh7100.c | 2 +- drivers/clk/starfive/clk-starfive-jh71x0.c | 2 +- .../starfive/{clk-starfive-jh7100.h => clk-starfive-jh71x0.h} | 0 4 files changed, 3 insertions(+), 3 deletions(-) rename drivers/clk/starfive/{clk-starfive-jh7100.h => clk-starfive-jh71x0.h} (100%) diff --git a/drivers/clk/starfive/clk-starfive-jh7100-audio.c b/drivers/clk/starfive/clk-starfive-jh7100-audio.c index 8473a65e219b..db0d9533bd9c 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100-audio.c +++ b/drivers/clk/starfive/clk-starfive-jh7100-audio.c @@ -16,7 +16,7 @@ #include -#include "clk-starfive-jh7100.h" +#include "clk-starfive-jh71x0.h" /* external clocks */ #define JH7100_AUDCLK_AUDIO_SRC (JH7100_AUDCLK_END + 0) diff --git a/drivers/clk/starfive/clk-starfive-jh7100.c b/drivers/clk/starfive/clk-starfive-jh7100.c index eea52f16af0d..662eb8f74c12 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100.c +++ b/drivers/clk/starfive/clk-starfive-jh7100.c @@ -15,7 +15,7 @@ #include -#include "clk-starfive-jh7100.h" +#include "clk-starfive-jh71x0.h" /* external clocks */ #define JH7100_CLK_OSC_SYS (JH7100_CLK_END + 0) diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.c b/drivers/clk/starfive/clk-starfive-jh71x0.c index 6c07b61b4a32..0140bdf27a01 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.c +++ b/drivers/clk/starfive/clk-starfive-jh71x0.c @@ -10,7 +10,7 @@ #include #include -#include "clk-starfive-jh7100.h" +#include "clk-starfive-jh71x0.h" static struct jh7100_clk *jh7100_clk_from(struct clk_hw *hw) { diff --git a/drivers/clk/starfive/clk-starfive-jh7100.h b/drivers/clk/starfive/clk-starfive-jh71x0.h similarity index 100% rename from drivers/clk/starfive/clk-starfive-jh7100.h rename to drivers/clk/starfive/clk-starfive-jh71x0.h -- GitLab From 147455edfe8a2a3748d411d588ad952124773efe Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:18 +0800 Subject: [PATCH 2086/5631] clk: starfive: Rename "jh7100" to "jh71x0" for the common code Rename some variables from "jh7100" or "JH7100" to "jh71x0" or "JH71X0". Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- .../clk/starfive/clk-starfive-jh7100-audio.c | 72 ++-- drivers/clk/starfive/clk-starfive-jh7100.c | 389 +++++++++--------- drivers/clk/starfive/clk-starfive-jh71x0.c | 282 ++++++------- drivers/clk/starfive/clk-starfive-jh71x0.h | 81 ++-- 4 files changed, 418 insertions(+), 406 deletions(-) diff --git a/drivers/clk/starfive/clk-starfive-jh7100-audio.c b/drivers/clk/starfive/clk-starfive-jh7100-audio.c index db0d9533bd9c..02aefb7264f8 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100-audio.c +++ b/drivers/clk/starfive/clk-starfive-jh7100-audio.c @@ -28,66 +28,66 @@ #define JH7100_AUDCLK_I2SDAC_LRCLK_IOPAD (JH7100_AUDCLK_END + 6) #define JH7100_AUDCLK_VAD_INTMEM (JH7100_AUDCLK_END + 7) -static const struct jh7100_clk_data jh7100_audclk_data[] = { - JH7100__GMD(JH7100_AUDCLK_ADC_MCLK, "adc_mclk", 0, 15, 2, +static const struct jh71x0_clk_data jh7100_audclk_data[] = { + JH71X0__GMD(JH7100_AUDCLK_ADC_MCLK, "adc_mclk", 0, 15, 2, JH7100_AUDCLK_AUDIO_SRC, JH7100_AUDCLK_AUDIO_12288), - JH7100__GMD(JH7100_AUDCLK_I2S1_MCLK, "i2s1_mclk", 0, 15, 2, + JH71X0__GMD(JH7100_AUDCLK_I2S1_MCLK, "i2s1_mclk", 0, 15, 2, JH7100_AUDCLK_AUDIO_SRC, JH7100_AUDCLK_AUDIO_12288), - JH7100_GATE(JH7100_AUDCLK_I2SADC_APB, "i2sadc_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100_MDIV(JH7100_AUDCLK_I2SADC_BCLK, "i2sadc_bclk", 31, 2, + JH71X0_GATE(JH7100_AUDCLK_I2SADC_APB, "i2sadc_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0_MDIV(JH7100_AUDCLK_I2SADC_BCLK, "i2sadc_bclk", 31, 2, JH7100_AUDCLK_ADC_MCLK, JH7100_AUDCLK_I2SADC_BCLK_IOPAD), - JH7100__INV(JH7100_AUDCLK_I2SADC_BCLK_N, "i2sadc_bclk_n", JH7100_AUDCLK_I2SADC_BCLK), - JH7100_MDIV(JH7100_AUDCLK_I2SADC_LRCLK, "i2sadc_lrclk", 63, 3, + JH71X0__INV(JH7100_AUDCLK_I2SADC_BCLK_N, "i2sadc_bclk_n", JH7100_AUDCLK_I2SADC_BCLK), + JH71X0_MDIV(JH7100_AUDCLK_I2SADC_LRCLK, "i2sadc_lrclk", 63, 3, JH7100_AUDCLK_I2SADC_BCLK_N, JH7100_AUDCLK_I2SADC_LRCLK_IOPAD, JH7100_AUDCLK_I2SADC_BCLK), - JH7100_GATE(JH7100_AUDCLK_PDM_APB, "pdm_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100__GMD(JH7100_AUDCLK_PDM_MCLK, "pdm_mclk", 0, 15, 2, + JH71X0_GATE(JH7100_AUDCLK_PDM_APB, "pdm_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0__GMD(JH7100_AUDCLK_PDM_MCLK, "pdm_mclk", 0, 15, 2, JH7100_AUDCLK_AUDIO_SRC, JH7100_AUDCLK_AUDIO_12288), - JH7100_GATE(JH7100_AUDCLK_I2SVAD_APB, "i2svad_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100__GMD(JH7100_AUDCLK_SPDIF, "spdif", 0, 15, 2, + JH71X0_GATE(JH7100_AUDCLK_I2SVAD_APB, "i2svad_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0__GMD(JH7100_AUDCLK_SPDIF, "spdif", 0, 15, 2, JH7100_AUDCLK_AUDIO_SRC, JH7100_AUDCLK_AUDIO_12288), - JH7100_GATE(JH7100_AUDCLK_SPDIF_APB, "spdif_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100_GATE(JH7100_AUDCLK_PWMDAC_APB, "pwmdac_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100__GMD(JH7100_AUDCLK_DAC_MCLK, "dac_mclk", 0, 15, 2, + JH71X0_GATE(JH7100_AUDCLK_SPDIF_APB, "spdif_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0_GATE(JH7100_AUDCLK_PWMDAC_APB, "pwmdac_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0__GMD(JH7100_AUDCLK_DAC_MCLK, "dac_mclk", 0, 15, 2, JH7100_AUDCLK_AUDIO_SRC, JH7100_AUDCLK_AUDIO_12288), - JH7100_GATE(JH7100_AUDCLK_I2SDAC_APB, "i2sdac_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100_MDIV(JH7100_AUDCLK_I2SDAC_BCLK, "i2sdac_bclk", 31, 2, + JH71X0_GATE(JH7100_AUDCLK_I2SDAC_APB, "i2sdac_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0_MDIV(JH7100_AUDCLK_I2SDAC_BCLK, "i2sdac_bclk", 31, 2, JH7100_AUDCLK_DAC_MCLK, JH7100_AUDCLK_I2SDAC_BCLK_IOPAD), - JH7100__INV(JH7100_AUDCLK_I2SDAC_BCLK_N, "i2sdac_bclk_n", JH7100_AUDCLK_I2SDAC_BCLK), - JH7100_MDIV(JH7100_AUDCLK_I2SDAC_LRCLK, "i2sdac_lrclk", 31, 2, + JH71X0__INV(JH7100_AUDCLK_I2SDAC_BCLK_N, "i2sdac_bclk_n", JH7100_AUDCLK_I2SDAC_BCLK), + JH71X0_MDIV(JH7100_AUDCLK_I2SDAC_LRCLK, "i2sdac_lrclk", 31, 2, JH7100_AUDCLK_I2S1_MCLK, JH7100_AUDCLK_I2SDAC_BCLK_IOPAD), - JH7100_GATE(JH7100_AUDCLK_I2S1_APB, "i2s1_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100_MDIV(JH7100_AUDCLK_I2S1_BCLK, "i2s1_bclk", 31, 2, + JH71X0_GATE(JH7100_AUDCLK_I2S1_APB, "i2s1_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0_MDIV(JH7100_AUDCLK_I2S1_BCLK, "i2s1_bclk", 31, 2, JH7100_AUDCLK_I2S1_MCLK, JH7100_AUDCLK_I2SDAC_BCLK_IOPAD), - JH7100__INV(JH7100_AUDCLK_I2S1_BCLK_N, "i2s1_bclk_n", JH7100_AUDCLK_I2S1_BCLK), - JH7100_MDIV(JH7100_AUDCLK_I2S1_LRCLK, "i2s1_lrclk", 63, 3, + JH71X0__INV(JH7100_AUDCLK_I2S1_BCLK_N, "i2s1_bclk_n", JH7100_AUDCLK_I2S1_BCLK), + JH71X0_MDIV(JH7100_AUDCLK_I2S1_LRCLK, "i2s1_lrclk", 63, 3, JH7100_AUDCLK_I2S1_BCLK_N, JH7100_AUDCLK_I2SDAC_LRCLK_IOPAD), - JH7100_GATE(JH7100_AUDCLK_I2SDAC16K_APB, "i2s1dac16k_apb", 0, JH7100_AUDCLK_APB0_BUS), - JH7100__DIV(JH7100_AUDCLK_APB0_BUS, "apb0_bus", 8, JH7100_AUDCLK_DOM7AHB_BUS), - JH7100_GATE(JH7100_AUDCLK_DMA1P_AHB, "dma1p_ahb", 0, JH7100_AUDCLK_DOM7AHB_BUS), - JH7100_GATE(JH7100_AUDCLK_USB_APB, "usb_apb", CLK_IGNORE_UNUSED, JH7100_AUDCLK_APB_EN), - JH7100_GDIV(JH7100_AUDCLK_USB_LPM, "usb_lpm", CLK_IGNORE_UNUSED, 4, JH7100_AUDCLK_USB_APB), - JH7100_GDIV(JH7100_AUDCLK_USB_STB, "usb_stb", CLK_IGNORE_UNUSED, 3, JH7100_AUDCLK_USB_APB), - JH7100__DIV(JH7100_AUDCLK_APB_EN, "apb_en", 8, JH7100_AUDCLK_DOM7AHB_BUS), - JH7100__MUX(JH7100_AUDCLK_VAD_MEM, "vad_mem", 2, + JH71X0_GATE(JH7100_AUDCLK_I2SDAC16K_APB, "i2s1dac16k_apb", 0, JH7100_AUDCLK_APB0_BUS), + JH71X0__DIV(JH7100_AUDCLK_APB0_BUS, "apb0_bus", 8, JH7100_AUDCLK_DOM7AHB_BUS), + JH71X0_GATE(JH7100_AUDCLK_DMA1P_AHB, "dma1p_ahb", 0, JH7100_AUDCLK_DOM7AHB_BUS), + JH71X0_GATE(JH7100_AUDCLK_USB_APB, "usb_apb", CLK_IGNORE_UNUSED, JH7100_AUDCLK_APB_EN), + JH71X0_GDIV(JH7100_AUDCLK_USB_LPM, "usb_lpm", CLK_IGNORE_UNUSED, 4, JH7100_AUDCLK_USB_APB), + JH71X0_GDIV(JH7100_AUDCLK_USB_STB, "usb_stb", CLK_IGNORE_UNUSED, 3, JH7100_AUDCLK_USB_APB), + JH71X0__DIV(JH7100_AUDCLK_APB_EN, "apb_en", 8, JH7100_AUDCLK_DOM7AHB_BUS), + JH71X0__MUX(JH7100_AUDCLK_VAD_MEM, "vad_mem", 2, JH7100_AUDCLK_VAD_INTMEM, JH7100_AUDCLK_AUDIO_12288), }; static struct clk_hw *jh7100_audclk_get(struct of_phandle_args *clkspec, void *data) { - struct jh7100_clk_priv *priv = data; + struct jh71x0_clk_priv *priv = data; unsigned int idx = clkspec->args[0]; if (idx < JH7100_AUDCLK_END) @@ -98,7 +98,7 @@ static struct clk_hw *jh7100_audclk_get(struct of_phandle_args *clkspec, void *d static int jh7100_audclk_probe(struct platform_device *pdev) { - struct jh7100_clk_priv *priv; + struct jh71x0_clk_priv *priv; unsigned int idx; int ret; @@ -117,12 +117,12 @@ static int jh7100_audclk_probe(struct platform_device *pdev) struct clk_parent_data parents[4] = {}; struct clk_init_data init = { .name = jh7100_audclk_data[idx].name, - .ops = starfive_jh7100_clk_ops(max), + .ops = starfive_jh71x0_clk_ops(max), .parent_data = parents, - .num_parents = ((max & JH7100_CLK_MUX_MASK) >> JH7100_CLK_MUX_SHIFT) + 1, + .num_parents = ((max & JH71X0_CLK_MUX_MASK) >> JH71X0_CLK_MUX_SHIFT) + 1, .flags = jh7100_audclk_data[idx].flags, }; - struct jh7100_clk *clk = &priv->reg[idx]; + struct jh71x0_clk *clk = &priv->reg[idx]; unsigned int i; for (i = 0; i < init.num_parents; i++) { @@ -140,7 +140,7 @@ static int jh7100_audclk_probe(struct platform_device *pdev) clk->hw.init = &init; clk->idx = idx; - clk->max_div = max & JH7100_CLK_DIV_MASK; + clk->max_div = max & JH71X0_CLK_DIV_MASK; ret = devm_clk_hw_register(priv->dev, &clk->hw); if (ret) diff --git a/drivers/clk/starfive/clk-starfive-jh7100.c b/drivers/clk/starfive/clk-starfive-jh7100.c index 662eb8f74c12..69cc11ea7e33 100644 --- a/drivers/clk/starfive/clk-starfive-jh7100.c +++ b/drivers/clk/starfive/clk-starfive-jh7100.c @@ -23,250 +23,253 @@ #define JH7100_CLK_GMAC_RMII_REF (JH7100_CLK_END + 2) #define JH7100_CLK_GMAC_GR_MII_RX (JH7100_CLK_END + 3) -static const struct jh7100_clk_data jh7100_clk_data[] __initconst = { - JH7100__MUX(JH7100_CLK_CPUNDBUS_ROOT, "cpundbus_root", 4, +static const struct jh71x0_clk_data jh7100_clk_data[] __initconst = { + JH71X0__MUX(JH7100_CLK_CPUNDBUS_ROOT, "cpundbus_root", 4, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL1_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_DLA_ROOT, "dla_root", 3, + JH71X0__MUX(JH7100_CLK_DLA_ROOT, "dla_root", 3, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL1_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_DSP_ROOT, "dsp_root", 4, + JH71X0__MUX(JH7100_CLK_DSP_ROOT, "dsp_root", 4, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL1_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_GMACUSB_ROOT, "gmacusb_root", 3, + JH71X0__MUX(JH7100_CLK_GMACUSB_ROOT, "gmacusb_root", 3, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_PERH0_ROOT, "perh0_root", 2, + JH71X0__MUX(JH7100_CLK_PERH0_ROOT, "perh0_root", 2, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL0_OUT), - JH7100__MUX(JH7100_CLK_PERH1_ROOT, "perh1_root", 2, + JH71X0__MUX(JH7100_CLK_PERH1_ROOT, "perh1_root", 2, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_VIN_ROOT, "vin_root", 3, + JH71X0__MUX(JH7100_CLK_VIN_ROOT, "vin_root", 3, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL1_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_VOUT_ROOT, "vout_root", 3, + JH71X0__MUX(JH7100_CLK_VOUT_ROOT, "vout_root", 3, JH7100_CLK_OSC_AUD, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL2_OUT), - JH7100_GDIV(JH7100_CLK_AUDIO_ROOT, "audio_root", 0, 8, JH7100_CLK_PLL0_OUT), - JH7100__MUX(JH7100_CLK_CDECHIFI4_ROOT, "cdechifi4_root", 3, + JH71X0_GDIV(JH7100_CLK_AUDIO_ROOT, "audio_root", 0, 8, JH7100_CLK_PLL0_OUT), + JH71X0__MUX(JH7100_CLK_CDECHIFI4_ROOT, "cdechifi4_root", 3, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL1_OUT, JH7100_CLK_PLL2_OUT), - JH7100__MUX(JH7100_CLK_CDEC_ROOT, "cdec_root", 3, + JH71X0__MUX(JH7100_CLK_CDEC_ROOT, "cdec_root", 3, JH7100_CLK_OSC_SYS, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL1_OUT), - JH7100__MUX(JH7100_CLK_VOUTBUS_ROOT, "voutbus_root", 3, + JH71X0__MUX(JH7100_CLK_VOUTBUS_ROOT, "voutbus_root", 3, JH7100_CLK_OSC_AUD, JH7100_CLK_PLL0_OUT, JH7100_CLK_PLL2_OUT), - JH7100__DIV(JH7100_CLK_CPUNBUS_ROOT_DIV, "cpunbus_root_div", 2, JH7100_CLK_CPUNDBUS_ROOT), - JH7100__DIV(JH7100_CLK_DSP_ROOT_DIV, "dsp_root_div", 4, JH7100_CLK_DSP_ROOT), - JH7100__DIV(JH7100_CLK_PERH0_SRC, "perh0_src", 4, JH7100_CLK_PERH0_ROOT), - JH7100__DIV(JH7100_CLK_PERH1_SRC, "perh1_src", 4, JH7100_CLK_PERH1_ROOT), - JH7100_GDIV(JH7100_CLK_PLL0_TESTOUT, "pll0_testout", 0, 31, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_PLL1_TESTOUT, "pll1_testout", 0, 31, JH7100_CLK_DLA_ROOT), - JH7100_GDIV(JH7100_CLK_PLL2_TESTOUT, "pll2_testout", 0, 31, JH7100_CLK_PERH1_SRC), - JH7100__MUX(JH7100_CLK_PLL2_REF, "pll2_refclk", 2, + JH71X0__DIV(JH7100_CLK_CPUNBUS_ROOT_DIV, "cpunbus_root_div", 2, JH7100_CLK_CPUNDBUS_ROOT), + JH71X0__DIV(JH7100_CLK_DSP_ROOT_DIV, "dsp_root_div", 4, JH7100_CLK_DSP_ROOT), + JH71X0__DIV(JH7100_CLK_PERH0_SRC, "perh0_src", 4, JH7100_CLK_PERH0_ROOT), + JH71X0__DIV(JH7100_CLK_PERH1_SRC, "perh1_src", 4, JH7100_CLK_PERH1_ROOT), + JH71X0_GDIV(JH7100_CLK_PLL0_TESTOUT, "pll0_testout", 0, 31, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_PLL1_TESTOUT, "pll1_testout", 0, 31, JH7100_CLK_DLA_ROOT), + JH71X0_GDIV(JH7100_CLK_PLL2_TESTOUT, "pll2_testout", 0, 31, JH7100_CLK_PERH1_SRC), + JH71X0__MUX(JH7100_CLK_PLL2_REF, "pll2_refclk", 2, JH7100_CLK_OSC_SYS, JH7100_CLK_OSC_AUD), - JH7100__DIV(JH7100_CLK_CPU_CORE, "cpu_core", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100__DIV(JH7100_CLK_CPU_AXI, "cpu_axi", 8, JH7100_CLK_CPU_CORE), - JH7100__DIV(JH7100_CLK_AHB_BUS, "ahb_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100__DIV(JH7100_CLK_APB1_BUS, "apb1_bus", 8, JH7100_CLK_AHB_BUS), - JH7100__DIV(JH7100_CLK_APB2_BUS, "apb2_bus", 8, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_DOM3AHB_BUS, "dom3ahb_bus", CLK_IS_CRITICAL, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_DOM7AHB_BUS, "dom7ahb_bus", CLK_IS_CRITICAL, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_U74_CORE0, "u74_core0", CLK_IS_CRITICAL, JH7100_CLK_CPU_CORE), - JH7100_GDIV(JH7100_CLK_U74_CORE1, "u74_core1", CLK_IS_CRITICAL, 8, JH7100_CLK_CPU_CORE), - JH7100_GATE(JH7100_CLK_U74_AXI, "u74_axi", CLK_IS_CRITICAL, JH7100_CLK_CPU_AXI), - JH7100_GATE(JH7100_CLK_U74RTC_TOGGLE, "u74rtc_toggle", CLK_IS_CRITICAL, JH7100_CLK_OSC_SYS), - JH7100_GATE(JH7100_CLK_SGDMA2P_AXI, "sgdma2p_axi", 0, JH7100_CLK_CPU_AXI), - JH7100_GATE(JH7100_CLK_DMA2PNOC_AXI, "dma2pnoc_axi", 0, JH7100_CLK_CPU_AXI), - JH7100_GATE(JH7100_CLK_SGDMA2P_AHB, "sgdma2p_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100__DIV(JH7100_CLK_DLA_BUS, "dla_bus", 4, JH7100_CLK_DLA_ROOT), - JH7100_GATE(JH7100_CLK_DLA_AXI, "dla_axi", 0, JH7100_CLK_DLA_BUS), - JH7100_GATE(JH7100_CLK_DLANOC_AXI, "dlanoc_axi", 0, JH7100_CLK_DLA_BUS), - JH7100_GATE(JH7100_CLK_DLA_APB, "dla_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_VP6_CORE, "vp6_core", 0, 4, JH7100_CLK_DSP_ROOT_DIV), - JH7100__DIV(JH7100_CLK_VP6BUS_SRC, "vp6bus_src", 4, JH7100_CLK_DSP_ROOT), - JH7100_GDIV(JH7100_CLK_VP6_AXI, "vp6_axi", 0, 4, JH7100_CLK_VP6BUS_SRC), - JH7100__DIV(JH7100_CLK_VCDECBUS_SRC, "vcdecbus_src", 4, JH7100_CLK_CDECHIFI4_ROOT), - JH7100__DIV(JH7100_CLK_VDEC_BUS, "vdec_bus", 8, JH7100_CLK_VCDECBUS_SRC), - JH7100_GATE(JH7100_CLK_VDEC_AXI, "vdec_axi", 0, JH7100_CLK_VDEC_BUS), - JH7100_GATE(JH7100_CLK_VDECBRG_MAIN, "vdecbrg_mainclk", 0, JH7100_CLK_VDEC_BUS), - JH7100_GDIV(JH7100_CLK_VDEC_BCLK, "vdec_bclk", 0, 8, JH7100_CLK_VCDECBUS_SRC), - JH7100_GDIV(JH7100_CLK_VDEC_CCLK, "vdec_cclk", 0, 8, JH7100_CLK_CDEC_ROOT), - JH7100_GATE(JH7100_CLK_VDEC_APB, "vdec_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_JPEG_AXI, "jpeg_axi", 0, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100_GDIV(JH7100_CLK_JPEG_CCLK, "jpeg_cclk", 0, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100_GATE(JH7100_CLK_JPEG_APB, "jpeg_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_GC300_2X, "gc300_2x", 0, 8, JH7100_CLK_CDECHIFI4_ROOT), - JH7100_GATE(JH7100_CLK_GC300_AHB, "gc300_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100__DIV(JH7100_CLK_JPCGC300_AXIBUS, "jpcgc300_axibus", 8, JH7100_CLK_VCDECBUS_SRC), - JH7100_GATE(JH7100_CLK_GC300_AXI, "gc300_axi", 0, JH7100_CLK_JPCGC300_AXIBUS), - JH7100_GATE(JH7100_CLK_JPCGC300_MAIN, "jpcgc300_mainclk", 0, JH7100_CLK_JPCGC300_AXIBUS), - JH7100__DIV(JH7100_CLK_VENC_BUS, "venc_bus", 8, JH7100_CLK_VCDECBUS_SRC), - JH7100_GATE(JH7100_CLK_VENC_AXI, "venc_axi", 0, JH7100_CLK_VENC_BUS), - JH7100_GATE(JH7100_CLK_VENCBRG_MAIN, "vencbrg_mainclk", 0, JH7100_CLK_VENC_BUS), - JH7100_GDIV(JH7100_CLK_VENC_BCLK, "venc_bclk", 0, 8, JH7100_CLK_VCDECBUS_SRC), - JH7100_GDIV(JH7100_CLK_VENC_CCLK, "venc_cclk", 0, 8, JH7100_CLK_CDEC_ROOT), - JH7100_GATE(JH7100_CLK_VENC_APB, "venc_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_DDRPLL_DIV2, "ddrpll_div2", CLK_IS_CRITICAL, 2, JH7100_CLK_PLL1_OUT), - JH7100_GDIV(JH7100_CLK_DDRPLL_DIV4, "ddrpll_div4", CLK_IS_CRITICAL, 2, JH7100_CLK_DDRPLL_DIV2), - JH7100_GDIV(JH7100_CLK_DDRPLL_DIV8, "ddrpll_div8", CLK_IS_CRITICAL, 2, JH7100_CLK_DDRPLL_DIV4), - JH7100_GDIV(JH7100_CLK_DDROSC_DIV2, "ddrosc_div2", CLK_IS_CRITICAL, 2, JH7100_CLK_OSC_SYS), - JH7100_GMUX(JH7100_CLK_DDRC0, "ddrc0", CLK_IS_CRITICAL, 4, + JH71X0__DIV(JH7100_CLK_CPU_CORE, "cpu_core", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0__DIV(JH7100_CLK_CPU_AXI, "cpu_axi", 8, JH7100_CLK_CPU_CORE), + JH71X0__DIV(JH7100_CLK_AHB_BUS, "ahb_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0__DIV(JH7100_CLK_APB1_BUS, "apb1_bus", 8, JH7100_CLK_AHB_BUS), + JH71X0__DIV(JH7100_CLK_APB2_BUS, "apb2_bus", 8, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_DOM3AHB_BUS, "dom3ahb_bus", CLK_IS_CRITICAL, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_DOM7AHB_BUS, "dom7ahb_bus", CLK_IS_CRITICAL, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_U74_CORE0, "u74_core0", CLK_IS_CRITICAL, JH7100_CLK_CPU_CORE), + JH71X0_GDIV(JH7100_CLK_U74_CORE1, "u74_core1", CLK_IS_CRITICAL, 8, JH7100_CLK_CPU_CORE), + JH71X0_GATE(JH7100_CLK_U74_AXI, "u74_axi", CLK_IS_CRITICAL, JH7100_CLK_CPU_AXI), + JH71X0_GATE(JH7100_CLK_U74RTC_TOGGLE, "u74rtc_toggle", CLK_IS_CRITICAL, JH7100_CLK_OSC_SYS), + JH71X0_GATE(JH7100_CLK_SGDMA2P_AXI, "sgdma2p_axi", 0, JH7100_CLK_CPU_AXI), + JH71X0_GATE(JH7100_CLK_DMA2PNOC_AXI, "dma2pnoc_axi", 0, JH7100_CLK_CPU_AXI), + JH71X0_GATE(JH7100_CLK_SGDMA2P_AHB, "sgdma2p_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0__DIV(JH7100_CLK_DLA_BUS, "dla_bus", 4, JH7100_CLK_DLA_ROOT), + JH71X0_GATE(JH7100_CLK_DLA_AXI, "dla_axi", 0, JH7100_CLK_DLA_BUS), + JH71X0_GATE(JH7100_CLK_DLANOC_AXI, "dlanoc_axi", 0, JH7100_CLK_DLA_BUS), + JH71X0_GATE(JH7100_CLK_DLA_APB, "dla_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_VP6_CORE, "vp6_core", 0, 4, JH7100_CLK_DSP_ROOT_DIV), + JH71X0__DIV(JH7100_CLK_VP6BUS_SRC, "vp6bus_src", 4, JH7100_CLK_DSP_ROOT), + JH71X0_GDIV(JH7100_CLK_VP6_AXI, "vp6_axi", 0, 4, JH7100_CLK_VP6BUS_SRC), + JH71X0__DIV(JH7100_CLK_VCDECBUS_SRC, "vcdecbus_src", 4, JH7100_CLK_CDECHIFI4_ROOT), + JH71X0__DIV(JH7100_CLK_VDEC_BUS, "vdec_bus", 8, JH7100_CLK_VCDECBUS_SRC), + JH71X0_GATE(JH7100_CLK_VDEC_AXI, "vdec_axi", 0, JH7100_CLK_VDEC_BUS), + JH71X0_GATE(JH7100_CLK_VDECBRG_MAIN, "vdecbrg_mainclk", 0, JH7100_CLK_VDEC_BUS), + JH71X0_GDIV(JH7100_CLK_VDEC_BCLK, "vdec_bclk", 0, 8, JH7100_CLK_VCDECBUS_SRC), + JH71X0_GDIV(JH7100_CLK_VDEC_CCLK, "vdec_cclk", 0, 8, JH7100_CLK_CDEC_ROOT), + JH71X0_GATE(JH7100_CLK_VDEC_APB, "vdec_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_JPEG_AXI, "jpeg_axi", 0, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0_GDIV(JH7100_CLK_JPEG_CCLK, "jpeg_cclk", 0, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0_GATE(JH7100_CLK_JPEG_APB, "jpeg_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_GC300_2X, "gc300_2x", 0, 8, JH7100_CLK_CDECHIFI4_ROOT), + JH71X0_GATE(JH7100_CLK_GC300_AHB, "gc300_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0__DIV(JH7100_CLK_JPCGC300_AXIBUS, "jpcgc300_axibus", 8, JH7100_CLK_VCDECBUS_SRC), + JH71X0_GATE(JH7100_CLK_GC300_AXI, "gc300_axi", 0, JH7100_CLK_JPCGC300_AXIBUS), + JH71X0_GATE(JH7100_CLK_JPCGC300_MAIN, "jpcgc300_mainclk", 0, JH7100_CLK_JPCGC300_AXIBUS), + JH71X0__DIV(JH7100_CLK_VENC_BUS, "venc_bus", 8, JH7100_CLK_VCDECBUS_SRC), + JH71X0_GATE(JH7100_CLK_VENC_AXI, "venc_axi", 0, JH7100_CLK_VENC_BUS), + JH71X0_GATE(JH7100_CLK_VENCBRG_MAIN, "vencbrg_mainclk", 0, JH7100_CLK_VENC_BUS), + JH71X0_GDIV(JH7100_CLK_VENC_BCLK, "venc_bclk", 0, 8, JH7100_CLK_VCDECBUS_SRC), + JH71X0_GDIV(JH7100_CLK_VENC_CCLK, "venc_cclk", 0, 8, JH7100_CLK_CDEC_ROOT), + JH71X0_GATE(JH7100_CLK_VENC_APB, "venc_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_DDRPLL_DIV2, "ddrpll_div2", CLK_IS_CRITICAL, 2, JH7100_CLK_PLL1_OUT), + JH71X0_GDIV(JH7100_CLK_DDRPLL_DIV4, "ddrpll_div4", CLK_IS_CRITICAL, 2, + JH7100_CLK_DDRPLL_DIV2), + JH71X0_GDIV(JH7100_CLK_DDRPLL_DIV8, "ddrpll_div8", CLK_IS_CRITICAL, 2, + JH7100_CLK_DDRPLL_DIV4), + JH71X0_GDIV(JH7100_CLK_DDROSC_DIV2, "ddrosc_div2", CLK_IS_CRITICAL, 2, JH7100_CLK_OSC_SYS), + JH71X0_GMUX(JH7100_CLK_DDRC0, "ddrc0", CLK_IS_CRITICAL, 4, JH7100_CLK_DDROSC_DIV2, JH7100_CLK_DDRPLL_DIV2, JH7100_CLK_DDRPLL_DIV4, JH7100_CLK_DDRPLL_DIV8), - JH7100_GMUX(JH7100_CLK_DDRC1, "ddrc1", CLK_IS_CRITICAL, 4, + JH71X0_GMUX(JH7100_CLK_DDRC1, "ddrc1", CLK_IS_CRITICAL, 4, JH7100_CLK_DDROSC_DIV2, JH7100_CLK_DDRPLL_DIV2, JH7100_CLK_DDRPLL_DIV4, JH7100_CLK_DDRPLL_DIV8), - JH7100_GATE(JH7100_CLK_DDRPHY_APB, "ddrphy_apb", 0, JH7100_CLK_APB1_BUS), - JH7100__DIV(JH7100_CLK_NOC_ROB, "noc_rob", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100__DIV(JH7100_CLK_NOC_COG, "noc_cog", 8, JH7100_CLK_DLA_ROOT), - JH7100_GATE(JH7100_CLK_NNE_AHB, "nne_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100__DIV(JH7100_CLK_NNEBUS_SRC1, "nnebus_src1", 4, JH7100_CLK_DSP_ROOT), - JH7100__MUX(JH7100_CLK_NNE_BUS, "nne_bus", 2, + JH71X0_GATE(JH7100_CLK_DDRPHY_APB, "ddrphy_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0__DIV(JH7100_CLK_NOC_ROB, "noc_rob", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0__DIV(JH7100_CLK_NOC_COG, "noc_cog", 8, JH7100_CLK_DLA_ROOT), + JH71X0_GATE(JH7100_CLK_NNE_AHB, "nne_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0__DIV(JH7100_CLK_NNEBUS_SRC1, "nnebus_src1", 4, JH7100_CLK_DSP_ROOT), + JH71X0__MUX(JH7100_CLK_NNE_BUS, "nne_bus", 2, JH7100_CLK_CPU_AXI, JH7100_CLK_NNEBUS_SRC1), - JH7100_GATE(JH7100_CLK_NNE_AXI, "nne_axi", 0, JH7100_CLK_NNE_BUS), - JH7100_GATE(JH7100_CLK_NNENOC_AXI, "nnenoc_axi", 0, JH7100_CLK_NNE_BUS), - JH7100_GATE(JH7100_CLK_DLASLV_AXI, "dlaslv_axi", 0, JH7100_CLK_NNE_BUS), - JH7100_GATE(JH7100_CLK_DSPX2C_AXI, "dspx2c_axi", CLK_IS_CRITICAL, JH7100_CLK_NNE_BUS), - JH7100__DIV(JH7100_CLK_HIFI4_SRC, "hifi4_src", 4, JH7100_CLK_CDECHIFI4_ROOT), - JH7100__DIV(JH7100_CLK_HIFI4_COREFREE, "hifi4_corefree", 8, JH7100_CLK_HIFI4_SRC), - JH7100_GATE(JH7100_CLK_HIFI4_CORE, "hifi4_core", 0, JH7100_CLK_HIFI4_COREFREE), - JH7100__DIV(JH7100_CLK_HIFI4_BUS, "hifi4_bus", 8, JH7100_CLK_HIFI4_COREFREE), - JH7100_GATE(JH7100_CLK_HIFI4_AXI, "hifi4_axi", 0, JH7100_CLK_HIFI4_BUS), - JH7100_GATE(JH7100_CLK_HIFI4NOC_AXI, "hifi4noc_axi", 0, JH7100_CLK_HIFI4_BUS), - JH7100__DIV(JH7100_CLK_SGDMA1P_BUS, "sgdma1p_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100_GATE(JH7100_CLK_SGDMA1P_AXI, "sgdma1p_axi", 0, JH7100_CLK_SGDMA1P_BUS), - JH7100_GATE(JH7100_CLK_DMA1P_AXI, "dma1p_axi", 0, JH7100_CLK_SGDMA1P_BUS), - JH7100_GDIV(JH7100_CLK_X2C_AXI, "x2c_axi", CLK_IS_CRITICAL, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100__DIV(JH7100_CLK_USB_BUS, "usb_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), - JH7100_GATE(JH7100_CLK_USB_AXI, "usb_axi", 0, JH7100_CLK_USB_BUS), - JH7100_GATE(JH7100_CLK_USBNOC_AXI, "usbnoc_axi", 0, JH7100_CLK_USB_BUS), - JH7100__DIV(JH7100_CLK_USBPHY_ROOTDIV, "usbphy_rootdiv", 4, JH7100_CLK_GMACUSB_ROOT), - JH7100_GDIV(JH7100_CLK_USBPHY_125M, "usbphy_125m", 0, 8, JH7100_CLK_USBPHY_ROOTDIV), - JH7100_GDIV(JH7100_CLK_USBPHY_PLLDIV25M, "usbphy_plldiv25m", 0, 32, JH7100_CLK_USBPHY_ROOTDIV), - JH7100__MUX(JH7100_CLK_USBPHY_25M, "usbphy_25m", 2, + JH71X0_GATE(JH7100_CLK_NNE_AXI, "nne_axi", 0, JH7100_CLK_NNE_BUS), + JH71X0_GATE(JH7100_CLK_NNENOC_AXI, "nnenoc_axi", 0, JH7100_CLK_NNE_BUS), + JH71X0_GATE(JH7100_CLK_DLASLV_AXI, "dlaslv_axi", 0, JH7100_CLK_NNE_BUS), + JH71X0_GATE(JH7100_CLK_DSPX2C_AXI, "dspx2c_axi", CLK_IS_CRITICAL, JH7100_CLK_NNE_BUS), + JH71X0__DIV(JH7100_CLK_HIFI4_SRC, "hifi4_src", 4, JH7100_CLK_CDECHIFI4_ROOT), + JH71X0__DIV(JH7100_CLK_HIFI4_COREFREE, "hifi4_corefree", 8, JH7100_CLK_HIFI4_SRC), + JH71X0_GATE(JH7100_CLK_HIFI4_CORE, "hifi4_core", 0, JH7100_CLK_HIFI4_COREFREE), + JH71X0__DIV(JH7100_CLK_HIFI4_BUS, "hifi4_bus", 8, JH7100_CLK_HIFI4_COREFREE), + JH71X0_GATE(JH7100_CLK_HIFI4_AXI, "hifi4_axi", 0, JH7100_CLK_HIFI4_BUS), + JH71X0_GATE(JH7100_CLK_HIFI4NOC_AXI, "hifi4noc_axi", 0, JH7100_CLK_HIFI4_BUS), + JH71X0__DIV(JH7100_CLK_SGDMA1P_BUS, "sgdma1p_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0_GATE(JH7100_CLK_SGDMA1P_AXI, "sgdma1p_axi", 0, JH7100_CLK_SGDMA1P_BUS), + JH71X0_GATE(JH7100_CLK_DMA1P_AXI, "dma1p_axi", 0, JH7100_CLK_SGDMA1P_BUS), + JH71X0_GDIV(JH7100_CLK_X2C_AXI, "x2c_axi", CLK_IS_CRITICAL, 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0__DIV(JH7100_CLK_USB_BUS, "usb_bus", 8, JH7100_CLK_CPUNBUS_ROOT_DIV), + JH71X0_GATE(JH7100_CLK_USB_AXI, "usb_axi", 0, JH7100_CLK_USB_BUS), + JH71X0_GATE(JH7100_CLK_USBNOC_AXI, "usbnoc_axi", 0, JH7100_CLK_USB_BUS), + JH71X0__DIV(JH7100_CLK_USBPHY_ROOTDIV, "usbphy_rootdiv", 4, JH7100_CLK_GMACUSB_ROOT), + JH71X0_GDIV(JH7100_CLK_USBPHY_125M, "usbphy_125m", 0, 8, JH7100_CLK_USBPHY_ROOTDIV), + JH71X0_GDIV(JH7100_CLK_USBPHY_PLLDIV25M, "usbphy_plldiv25m", 0, 32, + JH7100_CLK_USBPHY_ROOTDIV), + JH71X0__MUX(JH7100_CLK_USBPHY_25M, "usbphy_25m", 2, JH7100_CLK_OSC_SYS, JH7100_CLK_USBPHY_PLLDIV25M), - JH7100_FDIV(JH7100_CLK_AUDIO_DIV, "audio_div", JH7100_CLK_AUDIO_ROOT), - JH7100_GATE(JH7100_CLK_AUDIO_SRC, "audio_src", 0, JH7100_CLK_AUDIO_DIV), - JH7100_GATE(JH7100_CLK_AUDIO_12288, "audio_12288", 0, JH7100_CLK_OSC_AUD), - JH7100_GDIV(JH7100_CLK_VIN_SRC, "vin_src", 0, 4, JH7100_CLK_VIN_ROOT), - JH7100__DIV(JH7100_CLK_ISP0_BUS, "isp0_bus", 8, JH7100_CLK_VIN_SRC), - JH7100_GATE(JH7100_CLK_ISP0_AXI, "isp0_axi", 0, JH7100_CLK_ISP0_BUS), - JH7100_GATE(JH7100_CLK_ISP0NOC_AXI, "isp0noc_axi", 0, JH7100_CLK_ISP0_BUS), - JH7100_GATE(JH7100_CLK_ISPSLV_AXI, "ispslv_axi", 0, JH7100_CLK_ISP0_BUS), - JH7100__DIV(JH7100_CLK_ISP1_BUS, "isp1_bus", 8, JH7100_CLK_VIN_SRC), - JH7100_GATE(JH7100_CLK_ISP1_AXI, "isp1_axi", 0, JH7100_CLK_ISP1_BUS), - JH7100_GATE(JH7100_CLK_ISP1NOC_AXI, "isp1noc_axi", 0, JH7100_CLK_ISP1_BUS), - JH7100__DIV(JH7100_CLK_VIN_BUS, "vin_bus", 8, JH7100_CLK_VIN_SRC), - JH7100_GATE(JH7100_CLK_VIN_AXI, "vin_axi", 0, JH7100_CLK_VIN_BUS), - JH7100_GATE(JH7100_CLK_VINNOC_AXI, "vinnoc_axi", 0, JH7100_CLK_VIN_BUS), - JH7100_GDIV(JH7100_CLK_VOUT_SRC, "vout_src", 0, 4, JH7100_CLK_VOUT_ROOT), - JH7100__DIV(JH7100_CLK_DISPBUS_SRC, "dispbus_src", 4, JH7100_CLK_VOUTBUS_ROOT), - JH7100__DIV(JH7100_CLK_DISP_BUS, "disp_bus", 4, JH7100_CLK_DISPBUS_SRC), - JH7100_GATE(JH7100_CLK_DISP_AXI, "disp_axi", 0, JH7100_CLK_DISP_BUS), - JH7100_GATE(JH7100_CLK_DISPNOC_AXI, "dispnoc_axi", 0, JH7100_CLK_DISP_BUS), - JH7100_GATE(JH7100_CLK_SDIO0_AHB, "sdio0_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GDIV(JH7100_CLK_SDIO0_CCLKINT, "sdio0_cclkint", 0, 24, JH7100_CLK_PERH0_SRC), - JH7100__INV(JH7100_CLK_SDIO0_CCLKINT_INV, "sdio0_cclkint_inv", JH7100_CLK_SDIO0_CCLKINT), - JH7100_GATE(JH7100_CLK_SDIO1_AHB, "sdio1_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GDIV(JH7100_CLK_SDIO1_CCLKINT, "sdio1_cclkint", 0, 24, JH7100_CLK_PERH1_SRC), - JH7100__INV(JH7100_CLK_SDIO1_CCLKINT_INV, "sdio1_cclkint_inv", JH7100_CLK_SDIO1_CCLKINT), - JH7100_GATE(JH7100_CLK_GMAC_AHB, "gmac_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100__DIV(JH7100_CLK_GMAC_ROOT_DIV, "gmac_root_div", 8, JH7100_CLK_GMACUSB_ROOT), - JH7100_GDIV(JH7100_CLK_GMAC_PTP_REF, "gmac_ptp_refclk", 0, 31, JH7100_CLK_GMAC_ROOT_DIV), - JH7100_GDIV(JH7100_CLK_GMAC_GTX, "gmac_gtxclk", 0, 255, JH7100_CLK_GMAC_ROOT_DIV), - JH7100_GDIV(JH7100_CLK_GMAC_RMII_TX, "gmac_rmii_txclk", 0, 8, JH7100_CLK_GMAC_RMII_REF), - JH7100_GDIV(JH7100_CLK_GMAC_RMII_RX, "gmac_rmii_rxclk", 0, 8, JH7100_CLK_GMAC_RMII_REF), - JH7100__MUX(JH7100_CLK_GMAC_TX, "gmac_tx", 3, + JH71X0_FDIV(JH7100_CLK_AUDIO_DIV, "audio_div", JH7100_CLK_AUDIO_ROOT), + JH71X0_GATE(JH7100_CLK_AUDIO_SRC, "audio_src", 0, JH7100_CLK_AUDIO_DIV), + JH71X0_GATE(JH7100_CLK_AUDIO_12288, "audio_12288", 0, JH7100_CLK_OSC_AUD), + JH71X0_GDIV(JH7100_CLK_VIN_SRC, "vin_src", 0, 4, JH7100_CLK_VIN_ROOT), + JH71X0__DIV(JH7100_CLK_ISP0_BUS, "isp0_bus", 8, JH7100_CLK_VIN_SRC), + JH71X0_GATE(JH7100_CLK_ISP0_AXI, "isp0_axi", 0, JH7100_CLK_ISP0_BUS), + JH71X0_GATE(JH7100_CLK_ISP0NOC_AXI, "isp0noc_axi", 0, JH7100_CLK_ISP0_BUS), + JH71X0_GATE(JH7100_CLK_ISPSLV_AXI, "ispslv_axi", 0, JH7100_CLK_ISP0_BUS), + JH71X0__DIV(JH7100_CLK_ISP1_BUS, "isp1_bus", 8, JH7100_CLK_VIN_SRC), + JH71X0_GATE(JH7100_CLK_ISP1_AXI, "isp1_axi", 0, JH7100_CLK_ISP1_BUS), + JH71X0_GATE(JH7100_CLK_ISP1NOC_AXI, "isp1noc_axi", 0, JH7100_CLK_ISP1_BUS), + JH71X0__DIV(JH7100_CLK_VIN_BUS, "vin_bus", 8, JH7100_CLK_VIN_SRC), + JH71X0_GATE(JH7100_CLK_VIN_AXI, "vin_axi", 0, JH7100_CLK_VIN_BUS), + JH71X0_GATE(JH7100_CLK_VINNOC_AXI, "vinnoc_axi", 0, JH7100_CLK_VIN_BUS), + JH71X0_GDIV(JH7100_CLK_VOUT_SRC, "vout_src", 0, 4, JH7100_CLK_VOUT_ROOT), + JH71X0__DIV(JH7100_CLK_DISPBUS_SRC, "dispbus_src", 4, JH7100_CLK_VOUTBUS_ROOT), + JH71X0__DIV(JH7100_CLK_DISP_BUS, "disp_bus", 4, JH7100_CLK_DISPBUS_SRC), + JH71X0_GATE(JH7100_CLK_DISP_AXI, "disp_axi", 0, JH7100_CLK_DISP_BUS), + JH71X0_GATE(JH7100_CLK_DISPNOC_AXI, "dispnoc_axi", 0, JH7100_CLK_DISP_BUS), + JH71X0_GATE(JH7100_CLK_SDIO0_AHB, "sdio0_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GDIV(JH7100_CLK_SDIO0_CCLKINT, "sdio0_cclkint", 0, 24, JH7100_CLK_PERH0_SRC), + JH71X0__INV(JH7100_CLK_SDIO0_CCLKINT_INV, "sdio0_cclkint_inv", JH7100_CLK_SDIO0_CCLKINT), + JH71X0_GATE(JH7100_CLK_SDIO1_AHB, "sdio1_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GDIV(JH7100_CLK_SDIO1_CCLKINT, "sdio1_cclkint", 0, 24, JH7100_CLK_PERH1_SRC), + JH71X0__INV(JH7100_CLK_SDIO1_CCLKINT_INV, "sdio1_cclkint_inv", JH7100_CLK_SDIO1_CCLKINT), + JH71X0_GATE(JH7100_CLK_GMAC_AHB, "gmac_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0__DIV(JH7100_CLK_GMAC_ROOT_DIV, "gmac_root_div", 8, JH7100_CLK_GMACUSB_ROOT), + JH71X0_GDIV(JH7100_CLK_GMAC_PTP_REF, "gmac_ptp_refclk", 0, 31, JH7100_CLK_GMAC_ROOT_DIV), + JH71X0_GDIV(JH7100_CLK_GMAC_GTX, "gmac_gtxclk", 0, 255, JH7100_CLK_GMAC_ROOT_DIV), + JH71X0_GDIV(JH7100_CLK_GMAC_RMII_TX, "gmac_rmii_txclk", 0, 8, JH7100_CLK_GMAC_RMII_REF), + JH71X0_GDIV(JH7100_CLK_GMAC_RMII_RX, "gmac_rmii_rxclk", 0, 8, JH7100_CLK_GMAC_RMII_REF), + JH71X0__MUX(JH7100_CLK_GMAC_TX, "gmac_tx", 3, JH7100_CLK_GMAC_GTX, JH7100_CLK_GMAC_TX_INV, JH7100_CLK_GMAC_RMII_TX), - JH7100__INV(JH7100_CLK_GMAC_TX_INV, "gmac_tx_inv", JH7100_CLK_GMAC_TX), - JH7100__MUX(JH7100_CLK_GMAC_RX_PRE, "gmac_rx_pre", 2, + JH71X0__INV(JH7100_CLK_GMAC_TX_INV, "gmac_tx_inv", JH7100_CLK_GMAC_TX), + JH71X0__MUX(JH7100_CLK_GMAC_RX_PRE, "gmac_rx_pre", 2, JH7100_CLK_GMAC_GR_MII_RX, JH7100_CLK_GMAC_RMII_RX), - JH7100__INV(JH7100_CLK_GMAC_RX_INV, "gmac_rx_inv", JH7100_CLK_GMAC_RX_PRE), - JH7100_GATE(JH7100_CLK_GMAC_RMII, "gmac_rmii", 0, JH7100_CLK_GMAC_RMII_REF), - JH7100_GDIV(JH7100_CLK_GMAC_TOPHYREF, "gmac_tophyref", 0, 127, JH7100_CLK_GMAC_ROOT_DIV), - JH7100_GATE(JH7100_CLK_SPI2AHB_AHB, "spi2ahb_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GDIV(JH7100_CLK_SPI2AHB_CORE, "spi2ahb_core", 0, 31, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_EZMASTER_AHB, "ezmaster_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_E24_AHB, "e24_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_E24RTC_TOGGLE, "e24rtc_toggle", 0, JH7100_CLK_OSC_SYS), - JH7100_GATE(JH7100_CLK_QSPI_AHB, "qspi_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_QSPI_APB, "qspi_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_QSPI_REF, "qspi_refclk", 0, 31, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_SEC_AHB, "sec_ahb", 0, JH7100_CLK_AHB_BUS), - JH7100_GATE(JH7100_CLK_AES, "aes_clk", 0, JH7100_CLK_SEC_AHB), - JH7100_GATE(JH7100_CLK_SHA, "sha_clk", 0, JH7100_CLK_SEC_AHB), - JH7100_GATE(JH7100_CLK_PKA, "pka_clk", 0, JH7100_CLK_SEC_AHB), - JH7100_GATE(JH7100_CLK_TRNG_APB, "trng_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GATE(JH7100_CLK_OTP_APB, "otp_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GATE(JH7100_CLK_UART0_APB, "uart0_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_UART0_CORE, "uart0_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_UART1_APB, "uart1_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_UART1_CORE, "uart1_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_SPI0_APB, "spi0_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_SPI0_CORE, "spi0_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_SPI1_APB, "spi1_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_SPI1_CORE, "spi1_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_I2C0_APB, "i2c0_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_I2C0_CORE, "i2c0_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_I2C1_APB, "i2c1_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GDIV(JH7100_CLK_I2C1_CORE, "i2c1_core", 0, 63, JH7100_CLK_PERH1_SRC), - JH7100_GATE(JH7100_CLK_GPIO_APB, "gpio_apb", 0, JH7100_CLK_APB1_BUS), - JH7100_GATE(JH7100_CLK_UART2_APB, "uart2_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_UART2_CORE, "uart2_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_UART3_APB, "uart3_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_UART3_CORE, "uart3_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_SPI2_APB, "spi2_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_SPI2_CORE, "spi2_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_SPI3_APB, "spi3_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_SPI3_CORE, "spi3_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_I2C2_APB, "i2c2_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_I2C2_CORE, "i2c2_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_I2C3_APB, "i2c3_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_I2C3_CORE, "i2c3_core", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_WDTIMER_APB, "wdtimer_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_WDT_CORE, "wdt_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER0_CORE, "timer0_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER1_CORE, "timer1_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER2_CORE, "timer2_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER3_CORE, "timer3_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER4_CORE, "timer4_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER5_CORE, "timer5_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GDIV(JH7100_CLK_TIMER6_CORE, "timer6_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), - JH7100_GATE(JH7100_CLK_VP6INTC_APB, "vp6intc_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GATE(JH7100_CLK_PWM_APB, "pwm_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GATE(JH7100_CLK_MSI_APB, "msi_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GATE(JH7100_CLK_TEMP_APB, "temp_apb", 0, JH7100_CLK_APB2_BUS), - JH7100_GDIV(JH7100_CLK_TEMP_SENSE, "temp_sense", 0, 31, JH7100_CLK_OSC_SYS), - JH7100_GATE(JH7100_CLK_SYSERR_APB, "syserr_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0__INV(JH7100_CLK_GMAC_RX_INV, "gmac_rx_inv", JH7100_CLK_GMAC_RX_PRE), + JH71X0_GATE(JH7100_CLK_GMAC_RMII, "gmac_rmii", 0, JH7100_CLK_GMAC_RMII_REF), + JH71X0_GDIV(JH7100_CLK_GMAC_TOPHYREF, "gmac_tophyref", 0, 127, JH7100_CLK_GMAC_ROOT_DIV), + JH71X0_GATE(JH7100_CLK_SPI2AHB_AHB, "spi2ahb_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GDIV(JH7100_CLK_SPI2AHB_CORE, "spi2ahb_core", 0, 31, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_EZMASTER_AHB, "ezmaster_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_E24_AHB, "e24_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_E24RTC_TOGGLE, "e24rtc_toggle", 0, JH7100_CLK_OSC_SYS), + JH71X0_GATE(JH7100_CLK_QSPI_AHB, "qspi_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_QSPI_APB, "qspi_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_QSPI_REF, "qspi_refclk", 0, 31, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_SEC_AHB, "sec_ahb", 0, JH7100_CLK_AHB_BUS), + JH71X0_GATE(JH7100_CLK_AES, "aes_clk", 0, JH7100_CLK_SEC_AHB), + JH71X0_GATE(JH7100_CLK_SHA, "sha_clk", 0, JH7100_CLK_SEC_AHB), + JH71X0_GATE(JH7100_CLK_PKA, "pka_clk", 0, JH7100_CLK_SEC_AHB), + JH71X0_GATE(JH7100_CLK_TRNG_APB, "trng_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GATE(JH7100_CLK_OTP_APB, "otp_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GATE(JH7100_CLK_UART0_APB, "uart0_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_UART0_CORE, "uart0_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_UART1_APB, "uart1_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_UART1_CORE, "uart1_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_SPI0_APB, "spi0_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_SPI0_CORE, "spi0_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_SPI1_APB, "spi1_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_SPI1_CORE, "spi1_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_I2C0_APB, "i2c0_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_I2C0_CORE, "i2c0_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_I2C1_APB, "i2c1_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GDIV(JH7100_CLK_I2C1_CORE, "i2c1_core", 0, 63, JH7100_CLK_PERH1_SRC), + JH71X0_GATE(JH7100_CLK_GPIO_APB, "gpio_apb", 0, JH7100_CLK_APB1_BUS), + JH71X0_GATE(JH7100_CLK_UART2_APB, "uart2_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_UART2_CORE, "uart2_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_UART3_APB, "uart3_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_UART3_CORE, "uart3_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_SPI2_APB, "spi2_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_SPI2_CORE, "spi2_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_SPI3_APB, "spi3_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_SPI3_CORE, "spi3_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_I2C2_APB, "i2c2_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_I2C2_CORE, "i2c2_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_I2C3_APB, "i2c3_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_I2C3_CORE, "i2c3_core", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_WDTIMER_APB, "wdtimer_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_WDT_CORE, "wdt_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER0_CORE, "timer0_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER1_CORE, "timer1_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER2_CORE, "timer2_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER3_CORE, "timer3_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER4_CORE, "timer4_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER5_CORE, "timer5_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GDIV(JH7100_CLK_TIMER6_CORE, "timer6_coreclk", 0, 63, JH7100_CLK_PERH0_SRC), + JH71X0_GATE(JH7100_CLK_VP6INTC_APB, "vp6intc_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GATE(JH7100_CLK_PWM_APB, "pwm_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GATE(JH7100_CLK_MSI_APB, "msi_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GATE(JH7100_CLK_TEMP_APB, "temp_apb", 0, JH7100_CLK_APB2_BUS), + JH71X0_GDIV(JH7100_CLK_TEMP_SENSE, "temp_sense", 0, 31, JH7100_CLK_OSC_SYS), + JH71X0_GATE(JH7100_CLK_SYSERR_APB, "syserr_apb", 0, JH7100_CLK_APB2_BUS), }; static struct clk_hw *jh7100_clk_get(struct of_phandle_args *clkspec, void *data) { - struct jh7100_clk_priv *priv = data; + struct jh71x0_clk_priv *priv = data; unsigned int idx = clkspec->args[0]; if (idx < JH7100_CLK_PLL0_OUT) @@ -280,7 +283,7 @@ static struct clk_hw *jh7100_clk_get(struct of_phandle_args *clkspec, void *data static int __init clk_starfive_jh7100_probe(struct platform_device *pdev) { - struct jh7100_clk_priv *priv; + struct jh71x0_clk_priv *priv; unsigned int idx; int ret; @@ -314,12 +317,12 @@ static int __init clk_starfive_jh7100_probe(struct platform_device *pdev) struct clk_parent_data parents[4] = {}; struct clk_init_data init = { .name = jh7100_clk_data[idx].name, - .ops = starfive_jh7100_clk_ops(max), + .ops = starfive_jh71x0_clk_ops(max), .parent_data = parents, - .num_parents = ((max & JH7100_CLK_MUX_MASK) >> JH7100_CLK_MUX_SHIFT) + 1, + .num_parents = ((max & JH71X0_CLK_MUX_MASK) >> JH71X0_CLK_MUX_SHIFT) + 1, .flags = jh7100_clk_data[idx].flags, }; - struct jh7100_clk *clk = &priv->reg[idx]; + struct jh71x0_clk *clk = &priv->reg[idx]; unsigned int i; for (i = 0; i < init.num_parents; i++) { @@ -341,7 +344,7 @@ static int __init clk_starfive_jh7100_probe(struct platform_device *pdev) clk->hw.init = &init; clk->idx = idx; - clk->max_div = max & JH7100_CLK_DIV_MASK; + clk->max_div = max & JH71X0_CLK_DIV_MASK; ret = devm_clk_hw_register(priv->dev, &clk->hw); if (ret) diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.c b/drivers/clk/starfive/clk-starfive-jh71x0.c index 0140bdf27a01..b372083d11c3 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.c +++ b/drivers/clk/starfive/clk-starfive-jh71x0.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * StarFive JH7100 Clock Generator Driver + * StarFive JH71X0 Clock Generator Driver * * Copyright (C) 2021-2022 Emil Renner Berthing */ @@ -12,27 +12,27 @@ #include "clk-starfive-jh71x0.h" -static struct jh7100_clk *jh7100_clk_from(struct clk_hw *hw) +static struct jh71x0_clk *jh71x0_clk_from(struct clk_hw *hw) { - return container_of(hw, struct jh7100_clk, hw); + return container_of(hw, struct jh71x0_clk, hw); } -static struct jh7100_clk_priv *jh7100_priv_from(struct jh7100_clk *clk) +static struct jh71x0_clk_priv *jh71x0_priv_from(struct jh71x0_clk *clk) { - return container_of(clk, struct jh7100_clk_priv, reg[clk->idx]); + return container_of(clk, struct jh71x0_clk_priv, reg[clk->idx]); } -static u32 jh7100_clk_reg_get(struct jh7100_clk *clk) +static u32 jh71x0_clk_reg_get(struct jh71x0_clk *clk) { - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + struct jh71x0_clk_priv *priv = jh71x0_priv_from(clk); void __iomem *reg = priv->base + 4 * clk->idx; return readl_relaxed(reg); } -static void jh7100_clk_reg_rmw(struct jh7100_clk *clk, u32 mask, u32 value) +static void jh71x0_clk_reg_rmw(struct jh71x0_clk *clk, u32 mask, u32 value) { - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + struct jh71x0_clk_priv *priv = jh71x0_priv_from(clk); void __iomem *reg = priv->base + 4 * clk->idx; unsigned long flags; @@ -42,41 +42,41 @@ static void jh7100_clk_reg_rmw(struct jh7100_clk *clk, u32 mask, u32 value) spin_unlock_irqrestore(&priv->rmw_lock, flags); } -static int jh7100_clk_enable(struct clk_hw *hw) +static int jh71x0_clk_enable(struct clk_hw *hw) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); - jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, JH7100_CLK_ENABLE); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_ENABLE, JH71X0_CLK_ENABLE); return 0; } -static void jh7100_clk_disable(struct clk_hw *hw) +static void jh71x0_clk_disable(struct clk_hw *hw) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); - jh7100_clk_reg_rmw(clk, JH7100_CLK_ENABLE, 0); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_ENABLE, 0); } -static int jh7100_clk_is_enabled(struct clk_hw *hw) +static int jh71x0_clk_is_enabled(struct clk_hw *hw) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); - return !!(jh7100_clk_reg_get(clk) & JH7100_CLK_ENABLE); + return !!(jh71x0_clk_reg_get(clk) & JH71X0_CLK_ENABLE); } -static unsigned long jh7100_clk_recalc_rate(struct clk_hw *hw, +static unsigned long jh71x0_clk_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 div = jh7100_clk_reg_get(clk) & JH7100_CLK_DIV_MASK; + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + u32 div = jh71x0_clk_reg_get(clk) & JH71X0_CLK_DIV_MASK; return div ? parent_rate / div : 0; } -static int jh7100_clk_determine_rate(struct clk_hw *hw, +static int jh71x0_clk_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); unsigned long parent = req->best_parent_rate; unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); unsigned long div = min_t(unsigned long, DIV_ROUND_UP(parent, rate), clk->max_div); @@ -102,232 +102,232 @@ static int jh7100_clk_determine_rate(struct clk_hw *hw, return 0; } -static int jh7100_clk_set_rate(struct clk_hw *hw, +static int jh71x0_clk_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); unsigned long div = clamp(DIV_ROUND_CLOSEST(parent_rate, rate), 1UL, (unsigned long)clk->max_div); - jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, div); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_DIV_MASK, div); return 0; } -static unsigned long jh7100_clk_frac_recalc_rate(struct clk_hw *hw, +static unsigned long jh71x0_clk_frac_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) { - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 reg = jh7100_clk_reg_get(clk); - unsigned long div100 = 100 * (reg & JH7100_CLK_INT_MASK) + - ((reg & JH7100_CLK_FRAC_MASK) >> JH7100_CLK_FRAC_SHIFT); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + u32 reg = jh71x0_clk_reg_get(clk); + unsigned long div100 = 100 * (reg & JH71X0_CLK_INT_MASK) + + ((reg & JH71X0_CLK_FRAC_MASK) >> JH71X0_CLK_FRAC_SHIFT); - return (div100 >= JH7100_CLK_FRAC_MIN) ? 100 * parent_rate / div100 : 0; + return (div100 >= JH71X0_CLK_FRAC_MIN) ? 100 * parent_rate / div100 : 0; } -static int jh7100_clk_frac_determine_rate(struct clk_hw *hw, +static int jh71x0_clk_frac_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { unsigned long parent100 = 100 * req->best_parent_rate; unsigned long rate = clamp(req->rate, req->min_rate, req->max_rate); unsigned long div100 = clamp(DIV_ROUND_CLOSEST(parent100, rate), - JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); + JH71X0_CLK_FRAC_MIN, JH71X0_CLK_FRAC_MAX); unsigned long result = parent100 / div100; - /* clamp the result as in jh7100_clk_determine_rate() above */ - if (result > req->max_rate && div100 < JH7100_CLK_FRAC_MAX) + /* clamp the result as in jh71x0_clk_determine_rate() above */ + if (result > req->max_rate && div100 < JH71X0_CLK_FRAC_MAX) result = parent100 / (div100 + 1); - if (result < req->min_rate && div100 > JH7100_CLK_FRAC_MIN) + if (result < req->min_rate && div100 > JH71X0_CLK_FRAC_MIN) result = parent100 / (div100 - 1); req->rate = result; return 0; } -static int jh7100_clk_frac_set_rate(struct clk_hw *hw, +static int jh71x0_clk_frac_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); unsigned long div100 = clamp(DIV_ROUND_CLOSEST(100 * parent_rate, rate), - JH7100_CLK_FRAC_MIN, JH7100_CLK_FRAC_MAX); - u32 value = ((div100 % 100) << JH7100_CLK_FRAC_SHIFT) | (div100 / 100); + JH71X0_CLK_FRAC_MIN, JH71X0_CLK_FRAC_MAX); + u32 value = ((div100 % 100) << JH71X0_CLK_FRAC_SHIFT) | (div100 / 100); - jh7100_clk_reg_rmw(clk, JH7100_CLK_DIV_MASK, value); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_DIV_MASK, value); return 0; } -static u8 jh7100_clk_get_parent(struct clk_hw *hw) +static u8 jh71x0_clk_get_parent(struct clk_hw *hw) { - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = jh7100_clk_reg_get(clk); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + u32 value = jh71x0_clk_reg_get(clk); - return (value & JH7100_CLK_MUX_MASK) >> JH7100_CLK_MUX_SHIFT; + return (value & JH71X0_CLK_MUX_MASK) >> JH71X0_CLK_MUX_SHIFT; } -static int jh7100_clk_set_parent(struct clk_hw *hw, u8 index) +static int jh71x0_clk_set_parent(struct clk_hw *hw, u8 index) { - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = (u32)index << JH7100_CLK_MUX_SHIFT; + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + u32 value = (u32)index << JH71X0_CLK_MUX_SHIFT; - jh7100_clk_reg_rmw(clk, JH7100_CLK_MUX_MASK, value); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_MUX_MASK, value); return 0; } -static int jh7100_clk_mux_determine_rate(struct clk_hw *hw, +static int jh71x0_clk_mux_determine_rate(struct clk_hw *hw, struct clk_rate_request *req) { return clk_mux_determine_rate_flags(hw, req, 0); } -static int jh7100_clk_get_phase(struct clk_hw *hw) +static int jh71x0_clk_get_phase(struct clk_hw *hw) { - struct jh7100_clk *clk = jh7100_clk_from(hw); - u32 value = jh7100_clk_reg_get(clk); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + u32 value = jh71x0_clk_reg_get(clk); - return (value & JH7100_CLK_INVERT) ? 180 : 0; + return (value & JH71X0_CLK_INVERT) ? 180 : 0; } -static int jh7100_clk_set_phase(struct clk_hw *hw, int degrees) +static int jh71x0_clk_set_phase(struct clk_hw *hw, int degrees) { - struct jh7100_clk *clk = jh7100_clk_from(hw); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); u32 value; if (degrees == 0) value = 0; else if (degrees == 180) - value = JH7100_CLK_INVERT; + value = JH71X0_CLK_INVERT; else return -EINVAL; - jh7100_clk_reg_rmw(clk, JH7100_CLK_INVERT, value); + jh71x0_clk_reg_rmw(clk, JH71X0_CLK_INVERT, value); return 0; } #ifdef CONFIG_DEBUG_FS -static void jh7100_clk_debug_init(struct clk_hw *hw, struct dentry *dentry) +static void jh71x0_clk_debug_init(struct clk_hw *hw, struct dentry *dentry) { - static const struct debugfs_reg32 jh7100_clk_reg = { + static const struct debugfs_reg32 jh71x0_clk_reg = { .name = "CTRL", .offset = 0, }; - struct jh7100_clk *clk = jh7100_clk_from(hw); - struct jh7100_clk_priv *priv = jh7100_priv_from(clk); + struct jh71x0_clk *clk = jh71x0_clk_from(hw); + struct jh71x0_clk_priv *priv = jh71x0_priv_from(clk); struct debugfs_regset32 *regset; regset = devm_kzalloc(priv->dev, sizeof(*regset), GFP_KERNEL); if (!regset) return; - regset->regs = &jh7100_clk_reg; + regset->regs = &jh71x0_clk_reg; regset->nregs = 1; regset->base = priv->base + 4 * clk->idx; debugfs_create_regset32("registers", 0400, dentry, regset); } #else -#define jh7100_clk_debug_init NULL +#define jh71x0_clk_debug_init NULL #endif -static const struct clk_ops jh7100_clk_gate_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_gate_ops = { + .enable = jh71x0_clk_enable, + .disable = jh71x0_clk_disable, + .is_enabled = jh71x0_clk_is_enabled, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_div_ops = { - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_div_ops = { + .recalc_rate = jh71x0_clk_recalc_rate, + .determine_rate = jh71x0_clk_determine_rate, + .set_rate = jh71x0_clk_set_rate, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_fdiv_ops = { - .recalc_rate = jh7100_clk_frac_recalc_rate, - .determine_rate = jh7100_clk_frac_determine_rate, - .set_rate = jh7100_clk_frac_set_rate, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_fdiv_ops = { + .recalc_rate = jh71x0_clk_frac_recalc_rate, + .determine_rate = jh71x0_clk_frac_determine_rate, + .set_rate = jh71x0_clk_frac_set_rate, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_gdiv_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_gdiv_ops = { + .enable = jh71x0_clk_enable, + .disable = jh71x0_clk_disable, + .is_enabled = jh71x0_clk_is_enabled, + .recalc_rate = jh71x0_clk_recalc_rate, + .determine_rate = jh71x0_clk_determine_rate, + .set_rate = jh71x0_clk_set_rate, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_mux_ops = { - .determine_rate = jh7100_clk_mux_determine_rate, - .set_parent = jh7100_clk_set_parent, - .get_parent = jh7100_clk_get_parent, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_mux_ops = { + .determine_rate = jh71x0_clk_mux_determine_rate, + .set_parent = jh71x0_clk_set_parent, + .get_parent = jh71x0_clk_get_parent, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_gmux_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .determine_rate = jh7100_clk_mux_determine_rate, - .set_parent = jh7100_clk_set_parent, - .get_parent = jh7100_clk_get_parent, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_gmux_ops = { + .enable = jh71x0_clk_enable, + .disable = jh71x0_clk_disable, + .is_enabled = jh71x0_clk_is_enabled, + .determine_rate = jh71x0_clk_mux_determine_rate, + .set_parent = jh71x0_clk_set_parent, + .get_parent = jh71x0_clk_get_parent, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_mdiv_ops = { - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .get_parent = jh7100_clk_get_parent, - .set_parent = jh7100_clk_set_parent, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_mdiv_ops = { + .recalc_rate = jh71x0_clk_recalc_rate, + .determine_rate = jh71x0_clk_determine_rate, + .get_parent = jh71x0_clk_get_parent, + .set_parent = jh71x0_clk_set_parent, + .set_rate = jh71x0_clk_set_rate, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_gmd_ops = { - .enable = jh7100_clk_enable, - .disable = jh7100_clk_disable, - .is_enabled = jh7100_clk_is_enabled, - .recalc_rate = jh7100_clk_recalc_rate, - .determine_rate = jh7100_clk_determine_rate, - .get_parent = jh7100_clk_get_parent, - .set_parent = jh7100_clk_set_parent, - .set_rate = jh7100_clk_set_rate, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_gmd_ops = { + .enable = jh71x0_clk_enable, + .disable = jh71x0_clk_disable, + .is_enabled = jh71x0_clk_is_enabled, + .recalc_rate = jh71x0_clk_recalc_rate, + .determine_rate = jh71x0_clk_determine_rate, + .get_parent = jh71x0_clk_get_parent, + .set_parent = jh71x0_clk_set_parent, + .set_rate = jh71x0_clk_set_rate, + .debug_init = jh71x0_clk_debug_init, }; -static const struct clk_ops jh7100_clk_inv_ops = { - .get_phase = jh7100_clk_get_phase, - .set_phase = jh7100_clk_set_phase, - .debug_init = jh7100_clk_debug_init, +static const struct clk_ops jh71x0_clk_inv_ops = { + .get_phase = jh71x0_clk_get_phase, + .set_phase = jh71x0_clk_set_phase, + .debug_init = jh71x0_clk_debug_init, }; -const struct clk_ops *starfive_jh7100_clk_ops(u32 max) +const struct clk_ops *starfive_jh71x0_clk_ops(u32 max) { - if (max & JH7100_CLK_DIV_MASK) { - if (max & JH7100_CLK_MUX_MASK) { - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gmd_ops; - return &jh7100_clk_mdiv_ops; + if (max & JH71X0_CLK_DIV_MASK) { + if (max & JH71X0_CLK_MUX_MASK) { + if (max & JH71X0_CLK_ENABLE) + return &jh71x0_clk_gmd_ops; + return &jh71x0_clk_mdiv_ops; } - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gdiv_ops; - if (max == JH7100_CLK_FRAC_MAX) - return &jh7100_clk_fdiv_ops; - return &jh7100_clk_div_ops; + if (max & JH71X0_CLK_ENABLE) + return &jh71x0_clk_gdiv_ops; + if (max == JH71X0_CLK_FRAC_MAX) + return &jh71x0_clk_fdiv_ops; + return &jh71x0_clk_div_ops; } - if (max & JH7100_CLK_MUX_MASK) { - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gmux_ops; - return &jh7100_clk_mux_ops; + if (max & JH71X0_CLK_MUX_MASK) { + if (max & JH71X0_CLK_ENABLE) + return &jh71x0_clk_gmux_ops; + return &jh71x0_clk_mux_ops; } - if (max & JH7100_CLK_ENABLE) - return &jh7100_clk_gate_ops; + if (max & JH71X0_CLK_ENABLE) + return &jh71x0_clk_gate_ops; - return &jh7100_clk_inv_ops; + return &jh71x0_clk_inv_ops; } -EXPORT_SYMBOL_GPL(starfive_jh7100_clk_ops); +EXPORT_SYMBOL_GPL(starfive_jh71x0_clk_ops); diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.h b/drivers/clk/starfive/clk-starfive-jh71x0.h index a8ba6e25b5ce..34bb11c72eb7 100644 --- a/drivers/clk/starfive/clk-starfive-jh71x0.h +++ b/drivers/clk/starfive/clk-starfive-jh71x0.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __CLK_STARFIVE_JH7100_H -#define __CLK_STARFIVE_JH7100_H +#ifndef __CLK_STARFIVE_JH71X0_H +#define __CLK_STARFIVE_JH71X0_H #include #include @@ -8,107 +8,116 @@ #include /* register fields */ -#define JH7100_CLK_ENABLE BIT(31) -#define JH7100_CLK_INVERT BIT(30) -#define JH7100_CLK_MUX_MASK GENMASK(27, 24) -#define JH7100_CLK_MUX_SHIFT 24 -#define JH7100_CLK_DIV_MASK GENMASK(23, 0) -#define JH7100_CLK_FRAC_MASK GENMASK(15, 8) -#define JH7100_CLK_FRAC_SHIFT 8 -#define JH7100_CLK_INT_MASK GENMASK(7, 0) +#define JH71X0_CLK_ENABLE BIT(31) +#define JH71X0_CLK_INVERT BIT(30) +#define JH71X0_CLK_MUX_MASK GENMASK(27, 24) +#define JH71X0_CLK_MUX_SHIFT 24 +#define JH71X0_CLK_DIV_MASK GENMASK(23, 0) +#define JH71X0_CLK_FRAC_MASK GENMASK(15, 8) +#define JH71X0_CLK_FRAC_SHIFT 8 +#define JH71X0_CLK_INT_MASK GENMASK(7, 0) /* fractional divider min/max */ -#define JH7100_CLK_FRAC_MIN 100UL -#define JH7100_CLK_FRAC_MAX 25599UL +#define JH71X0_CLK_FRAC_MIN 100UL +#define JH71X0_CLK_FRAC_MAX 25599UL /* clock data */ -struct jh7100_clk_data { +struct jh71x0_clk_data { const char *name; unsigned long flags; u32 max; u8 parents[4]; }; -#define JH7100_GATE(_idx, _name, _flags, _parent) [_idx] = { \ +#define JH71X0_GATE(_idx, _name, _flags, _parent) \ +[_idx] = { \ .name = _name, \ .flags = CLK_SET_RATE_PARENT | (_flags), \ - .max = JH7100_CLK_ENABLE, \ + .max = JH71X0_CLK_ENABLE, \ .parents = { [0] = _parent }, \ } -#define JH7100__DIV(_idx, _name, _max, _parent) [_idx] = { \ +#define JH71X0__DIV(_idx, _name, _max, _parent) \ +[_idx] = { \ .name = _name, \ .flags = 0, \ .max = _max, \ .parents = { [0] = _parent }, \ } -#define JH7100_GDIV(_idx, _name, _flags, _max, _parent) [_idx] = { \ +#define JH71X0_GDIV(_idx, _name, _flags, _max, _parent) \ +[_idx] = { \ .name = _name, \ .flags = _flags, \ - .max = JH7100_CLK_ENABLE | (_max), \ + .max = JH71X0_CLK_ENABLE | (_max), \ .parents = { [0] = _parent }, \ } -#define JH7100_FDIV(_idx, _name, _parent) [_idx] = { \ +#define JH71X0_FDIV(_idx, _name, _parent) \ +[_idx] = { \ .name = _name, \ .flags = 0, \ - .max = JH7100_CLK_FRAC_MAX, \ + .max = JH71X0_CLK_FRAC_MAX, \ .parents = { [0] = _parent }, \ } -#define JH7100__MUX(_idx, _name, _nparents, ...) [_idx] = { \ +#define JH71X0__MUX(_idx, _name, _nparents, ...) \ +[_idx] = { \ .name = _name, \ .flags = 0, \ - .max = ((_nparents) - 1) << JH7100_CLK_MUX_SHIFT, \ + .max = ((_nparents) - 1) << JH71X0_CLK_MUX_SHIFT, \ .parents = { __VA_ARGS__ }, \ } -#define JH7100_GMUX(_idx, _name, _flags, _nparents, ...) [_idx] = { \ +#define JH71X0_GMUX(_idx, _name, _flags, _nparents, ...) \ +[_idx] = { \ .name = _name, \ .flags = _flags, \ - .max = JH7100_CLK_ENABLE | \ - (((_nparents) - 1) << JH7100_CLK_MUX_SHIFT), \ + .max = JH71X0_CLK_ENABLE | \ + (((_nparents) - 1) << JH71X0_CLK_MUX_SHIFT), \ .parents = { __VA_ARGS__ }, \ } -#define JH7100_MDIV(_idx, _name, _max, _nparents, ...) [_idx] = { \ +#define JH71X0_MDIV(_idx, _name, _max, _nparents, ...) \ +[_idx] = { \ .name = _name, \ .flags = 0, \ - .max = (((_nparents) - 1) << JH7100_CLK_MUX_SHIFT) | (_max), \ + .max = (((_nparents) - 1) << JH71X0_CLK_MUX_SHIFT) | (_max), \ .parents = { __VA_ARGS__ }, \ } -#define JH7100__GMD(_idx, _name, _flags, _max, _nparents, ...) [_idx] = { \ +#define JH71X0__GMD(_idx, _name, _flags, _max, _nparents, ...) \ +[_idx] = { \ .name = _name, \ .flags = _flags, \ - .max = JH7100_CLK_ENABLE | \ - (((_nparents) - 1) << JH7100_CLK_MUX_SHIFT) | (_max), \ + .max = JH71X0_CLK_ENABLE | \ + (((_nparents) - 1) << JH71X0_CLK_MUX_SHIFT) | (_max), \ .parents = { __VA_ARGS__ }, \ } -#define JH7100__INV(_idx, _name, _parent) [_idx] = { \ +#define JH71X0__INV(_idx, _name, _parent) \ +[_idx] = { \ .name = _name, \ .flags = CLK_SET_RATE_PARENT, \ - .max = JH7100_CLK_INVERT, \ + .max = JH71X0_CLK_INVERT, \ .parents = { [0] = _parent }, \ } -struct jh7100_clk { +struct jh71x0_clk { struct clk_hw hw; unsigned int idx; unsigned int max_div; }; -struct jh7100_clk_priv { +struct jh71x0_clk_priv { /* protect clk enable and set rate/parent from happening at the same time */ spinlock_t rmw_lock; struct device *dev; void __iomem *base; struct clk_hw *pll[3]; - struct jh7100_clk reg[]; + struct jh71x0_clk reg[]; }; -const struct clk_ops *starfive_jh7100_clk_ops(u32 max); +const struct clk_ops *starfive_jh71x0_clk_ops(u32 max); #endif -- GitLab From c49a757a5a9e2eab2202ecd28aedc22a0aedfbe8 Mon Sep 17 00:00:00 2001 From: Hal Feng Date: Sat, 1 Apr 2023 19:19:19 +0800 Subject: [PATCH 2087/5631] reset: starfive: Replace SOC_STARFIVE with ARCH_STARFIVE Using ARCH_FOO symbol is preferred than SOC_FOO. Reviewed-by: Philipp Zabel Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/reset/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index 2a52c990d4fe..6ae5aa46a6b2 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -234,8 +234,8 @@ config RESET_SOCFPGA config RESET_STARFIVE_JH7100 bool "StarFive JH7100 Reset Driver" - depends on SOC_STARFIVE || COMPILE_TEST - default SOC_STARFIVE + depends on ARCH_STARFIVE || COMPILE_TEST + default ARCH_STARFIVE help This enables the reset controller driver for the StarFive JH7100 SoC. -- GitLab From 69bfec7548f4c1595bac0e3ddfc0458a5af31f4c Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:20 +0800 Subject: [PATCH 2088/5631] reset: Create subdirectory for StarFive drivers This moves the StarFive JH7100 reset driver to a new subdirectory in preparation for adding more StarFive reset drivers. Reviewed-by: Philipp Zabel Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/reset/Kconfig | 8 +------- drivers/reset/Makefile | 2 +- drivers/reset/starfive/Kconfig | 8 ++++++++ drivers/reset/starfive/Makefile | 2 ++ drivers/reset/{ => starfive}/reset-starfive-jh7100.c | 0 5 files changed, 12 insertions(+), 8 deletions(-) create mode 100644 drivers/reset/starfive/Kconfig create mode 100644 drivers/reset/starfive/Makefile rename drivers/reset/{ => starfive}/reset-starfive-jh7100.c (100%) diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index 6ae5aa46a6b2..6aa8f243b30c 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -232,13 +232,6 @@ config RESET_SOCFPGA This enables the reset driver for the SoCFPGA ARMv7 platforms. This driver gets initialized early during platform init calls. -config RESET_STARFIVE_JH7100 - bool "StarFive JH7100 Reset Driver" - depends on ARCH_STARFIVE || COMPILE_TEST - default ARCH_STARFIVE - help - This enables the reset controller driver for the StarFive JH7100 SoC. - config RESET_SUNPLUS bool "Sunplus SoCs Reset Driver" if COMPILE_TEST default ARCH_SUNPLUS @@ -320,6 +313,7 @@ config RESET_ZYNQ help This enables the reset controller driver for Xilinx Zynq SoCs. +source "drivers/reset/starfive/Kconfig" source "drivers/reset/sti/Kconfig" source "drivers/reset/hisilicon/Kconfig" source "drivers/reset/tegra/Kconfig" diff --git a/drivers/reset/Makefile b/drivers/reset/Makefile index 3e7e5fd633a8..7fec5af6c964 100644 --- a/drivers/reset/Makefile +++ b/drivers/reset/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += core.o obj-y += hisilicon/ +obj-y += starfive/ obj-$(CONFIG_ARCH_STI) += sti/ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-$(CONFIG_RESET_A10SR) += reset-a10sr.o @@ -30,7 +31,6 @@ obj-$(CONFIG_RESET_RZG2L_USBPHY_CTRL) += reset-rzg2l-usbphy-ctrl.o obj-$(CONFIG_RESET_SCMI) += reset-scmi.o obj-$(CONFIG_RESET_SIMPLE) += reset-simple.o obj-$(CONFIG_RESET_SOCFPGA) += reset-socfpga.o -obj-$(CONFIG_RESET_STARFIVE_JH7100) += reset-starfive-jh7100.o obj-$(CONFIG_RESET_SUNPLUS) += reset-sunplus.o obj-$(CONFIG_RESET_SUNXI) += reset-sunxi.o obj-$(CONFIG_RESET_TI_SCI) += reset-ti-sci.o diff --git a/drivers/reset/starfive/Kconfig b/drivers/reset/starfive/Kconfig new file mode 100644 index 000000000000..abbf0c52d03e --- /dev/null +++ b/drivers/reset/starfive/Kconfig @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config RESET_STARFIVE_JH7100 + bool "StarFive JH7100 Reset Driver" + depends on ARCH_STARFIVE || COMPILE_TEST + default ARCH_STARFIVE + help + This enables the reset controller driver for the StarFive JH7100 SoC. diff --git a/drivers/reset/starfive/Makefile b/drivers/reset/starfive/Makefile new file mode 100644 index 000000000000..670d049423f5 --- /dev/null +++ b/drivers/reset/starfive/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_RESET_STARFIVE_JH7100) += reset-starfive-jh7100.o diff --git a/drivers/reset/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c similarity index 100% rename from drivers/reset/reset-starfive-jh7100.c rename to drivers/reset/starfive/reset-starfive-jh7100.c -- GitLab From 1ec3d20e4e2fef33c618b2ef550cbf3b4728e4cd Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:21 +0800 Subject: [PATCH 2089/5631] reset: starfive: Factor out common JH71X0 reset code The StarFive JH7100 SoC has additional reset controllers for audio and video, but the registers follow the same structure. On the JH7110 the reset registers don't get their own memory range, but instead follow the clock control registers. The registers still follow the same structure though, so let's factor out the common code to handle all these cases. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/reset/starfive/Kconfig | 4 + drivers/reset/starfive/Makefile | 2 + .../reset/starfive/reset-starfive-jh7100.c | 150 +--------------- .../reset/starfive/reset-starfive-jh71x0.c | 162 ++++++++++++++++++ .../reset/starfive/reset-starfive-jh71x0.h | 11 ++ 5 files changed, 180 insertions(+), 149 deletions(-) create mode 100644 drivers/reset/starfive/reset-starfive-jh71x0.c create mode 100644 drivers/reset/starfive/reset-starfive-jh71x0.h diff --git a/drivers/reset/starfive/Kconfig b/drivers/reset/starfive/Kconfig index abbf0c52d03e..1927a5a3b53a 100644 --- a/drivers/reset/starfive/Kconfig +++ b/drivers/reset/starfive/Kconfig @@ -1,8 +1,12 @@ # SPDX-License-Identifier: GPL-2.0-only +config RESET_STARFIVE_JH71X0 + bool + config RESET_STARFIVE_JH7100 bool "StarFive JH7100 Reset Driver" depends on ARCH_STARFIVE || COMPILE_TEST + select RESET_STARFIVE_JH71X0 default ARCH_STARFIVE help This enables the reset controller driver for the StarFive JH7100 SoC. diff --git a/drivers/reset/starfive/Makefile b/drivers/reset/starfive/Makefile index 670d049423f5..f6aa12466fad 100644 --- a/drivers/reset/starfive/Makefile +++ b/drivers/reset/starfive/Makefile @@ -1,2 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_RESET_STARFIVE_JH71X0) += reset-starfive-jh71x0.o + obj-$(CONFIG_RESET_STARFIVE_JH7100) += reset-starfive-jh7100.o diff --git a/drivers/reset/starfive/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c index fc44b2fb3e03..5a68327c1f6a 100644 --- a/drivers/reset/starfive/reset-starfive-jh7100.c +++ b/drivers/reset/starfive/reset-starfive-jh7100.c @@ -5,158 +5,10 @@ * Copyright (C) 2021 Emil Renner Berthing */ -#include -#include -#include -#include #include #include -#include -#include -#include - -/* register offsets */ -#define JH7100_RESET_ASSERT0 0x00 -#define JH7100_RESET_ASSERT1 0x04 -#define JH7100_RESET_ASSERT2 0x08 -#define JH7100_RESET_ASSERT3 0x0c -#define JH7100_RESET_STATUS0 0x10 -#define JH7100_RESET_STATUS1 0x14 -#define JH7100_RESET_STATUS2 0x18 -#define JH7100_RESET_STATUS3 0x1c - -/* - * Writing a 1 to the n'th bit of the m'th ASSERT register asserts - * line 32m + n, and writing a 0 deasserts the same line. - * Most reset lines have their status inverted so a 0 bit in the STATUS - * register means the line is asserted and a 1 means it's deasserted. A few - * lines don't though, so store the expected value of the status registers when - * all lines are asserted. - */ -static const u64 jh7100_reset_asserted[2] = { - /* STATUS0 */ - BIT_ULL_MASK(JH7100_RST_U74) | - BIT_ULL_MASK(JH7100_RST_VP6_DRESET) | - BIT_ULL_MASK(JH7100_RST_VP6_BRESET) | - /* STATUS1 */ - BIT_ULL_MASK(JH7100_RST_HIFI4_DRESET) | - BIT_ULL_MASK(JH7100_RST_HIFI4_BRESET), - /* STATUS2 */ - BIT_ULL_MASK(JH7100_RST_E24) | - /* STATUS3 */ - 0, -}; - -struct jh7100_reset { - struct reset_controller_dev rcdev; - /* protect registers against concurrent read-modify-write */ - spinlock_t lock; - void __iomem *base; -}; - -static inline struct jh7100_reset * -jh7100_reset_from(struct reset_controller_dev *rcdev) -{ - return container_of(rcdev, struct jh7100_reset, rcdev); -} - -static int jh7100_reset_update(struct reset_controller_dev *rcdev, - unsigned long id, bool assert) -{ - struct jh7100_reset *data = jh7100_reset_from(rcdev); - unsigned long offset = BIT_ULL_WORD(id); - u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_assert = data->base + JH7100_RESET_ASSERT0 + offset * sizeof(u64); - void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); - u64 done = jh7100_reset_asserted[offset] & mask; - u64 value; - unsigned long flags; - int ret; - - if (!assert) - done ^= mask; - - spin_lock_irqsave(&data->lock, flags); - - value = readq(reg_assert); - if (assert) - value |= mask; - else - value &= ~mask; - writeq(value, reg_assert); - - /* if the associated clock is gated, deasserting might otherwise hang forever */ - ret = readq_poll_timeout_atomic(reg_status, value, (value & mask) == done, 0, 1000); - - spin_unlock_irqrestore(&data->lock, flags); - return ret; -} - -static int jh7100_reset_assert(struct reset_controller_dev *rcdev, - unsigned long id) -{ - return jh7100_reset_update(rcdev, id, true); -} - -static int jh7100_reset_deassert(struct reset_controller_dev *rcdev, - unsigned long id) -{ - return jh7100_reset_update(rcdev, id, false); -} - -static int jh7100_reset_reset(struct reset_controller_dev *rcdev, - unsigned long id) -{ - int ret; - - ret = jh7100_reset_assert(rcdev, id); - if (ret) - return ret; - - return jh7100_reset_deassert(rcdev, id); -} - -static int jh7100_reset_status(struct reset_controller_dev *rcdev, - unsigned long id) -{ - struct jh7100_reset *data = jh7100_reset_from(rcdev); - unsigned long offset = BIT_ULL_WORD(id); - u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); - u64 value = readq(reg_status); - - return !((value ^ jh7100_reset_asserted[offset]) & mask); -} - -static const struct reset_control_ops jh7100_reset_ops = { - .assert = jh7100_reset_assert, - .deassert = jh7100_reset_deassert, - .reset = jh7100_reset_reset, - .status = jh7100_reset_status, -}; - -static int __init jh7100_reset_probe(struct platform_device *pdev) -{ - struct jh7100_reset *data; - - data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(data->base)) - return PTR_ERR(data->base); - - data->rcdev.ops = &jh7100_reset_ops; - data->rcdev.owner = THIS_MODULE; - data->rcdev.nr_resets = JH7100_RSTN_END; - data->rcdev.dev = &pdev->dev; - data->rcdev.of_node = pdev->dev.of_node; - spin_lock_init(&data->lock); - - return devm_reset_controller_register(&pdev->dev, &data->rcdev); -} +#include "reset-starfive-jh71x0.h" static const struct of_device_id jh7100_reset_dt_ids[] = { { .compatible = "starfive,jh7100-reset" }, diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.c b/drivers/reset/starfive/reset-starfive-jh71x0.c new file mode 100644 index 000000000000..114a13c4b8a6 --- /dev/null +++ b/drivers/reset/starfive/reset-starfive-jh71x0.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Reset driver for the StarFive JH7100 SoC + * + * Copyright (C) 2021 Emil Renner Berthing + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "reset-starfive-jh71x0.h" + +#include + +/* register offsets */ +#define JH7100_RESET_ASSERT0 0x00 +#define JH7100_RESET_ASSERT1 0x04 +#define JH7100_RESET_ASSERT2 0x08 +#define JH7100_RESET_ASSERT3 0x0c +#define JH7100_RESET_STATUS0 0x10 +#define JH7100_RESET_STATUS1 0x14 +#define JH7100_RESET_STATUS2 0x18 +#define JH7100_RESET_STATUS3 0x1c + +/* + * Writing a 1 to the n'th bit of the m'th ASSERT register asserts + * line 32m + n, and writing a 0 deasserts the same line. + * Most reset lines have their status inverted so a 0 bit in the STATUS + * register means the line is asserted and a 1 means it's deasserted. A few + * lines don't though, so store the expected value of the status registers when + * all lines are asserted. + */ +static const u64 jh7100_reset_asserted[2] = { + /* STATUS0 */ + BIT_ULL_MASK(JH7100_RST_U74) | + BIT_ULL_MASK(JH7100_RST_VP6_DRESET) | + BIT_ULL_MASK(JH7100_RST_VP6_BRESET) | + /* STATUS1 */ + BIT_ULL_MASK(JH7100_RST_HIFI4_DRESET) | + BIT_ULL_MASK(JH7100_RST_HIFI4_BRESET), + /* STATUS2 */ + BIT_ULL_MASK(JH7100_RST_E24) | + /* STATUS3 */ + 0, +}; + +struct jh7100_reset { + struct reset_controller_dev rcdev; + /* protect registers against concurrent read-modify-write */ + spinlock_t lock; + void __iomem *base; +}; + +static inline struct jh7100_reset * +jh7100_reset_from(struct reset_controller_dev *rcdev) +{ + return container_of(rcdev, struct jh7100_reset, rcdev); +} + +static int jh7100_reset_update(struct reset_controller_dev *rcdev, + unsigned long id, bool assert) +{ + struct jh7100_reset *data = jh7100_reset_from(rcdev); + unsigned long offset = BIT_ULL_WORD(id); + u64 mask = BIT_ULL_MASK(id); + void __iomem *reg_assert = data->base + JH7100_RESET_ASSERT0 + offset * sizeof(u64); + void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); + u64 done = jh7100_reset_asserted[offset] & mask; + u64 value; + unsigned long flags; + int ret; + + if (!assert) + done ^= mask; + + spin_lock_irqsave(&data->lock, flags); + + value = readq(reg_assert); + if (assert) + value |= mask; + else + value &= ~mask; + writeq(value, reg_assert); + + /* if the associated clock is gated, deasserting might otherwise hang forever */ + ret = readq_poll_timeout_atomic(reg_status, value, (value & mask) == done, 0, 1000); + + spin_unlock_irqrestore(&data->lock, flags); + return ret; +} + +static int jh7100_reset_assert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + return jh7100_reset_update(rcdev, id, true); +} + +static int jh7100_reset_deassert(struct reset_controller_dev *rcdev, + unsigned long id) +{ + return jh7100_reset_update(rcdev, id, false); +} + +static int jh7100_reset_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + int ret; + + ret = jh7100_reset_assert(rcdev, id); + if (ret) + return ret; + + return jh7100_reset_deassert(rcdev, id); +} + +static int jh7100_reset_status(struct reset_controller_dev *rcdev, + unsigned long id) +{ + struct jh7100_reset *data = jh7100_reset_from(rcdev); + unsigned long offset = BIT_ULL_WORD(id); + u64 mask = BIT_ULL_MASK(id); + void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); + u64 value = readq(reg_status); + + return !((value ^ jh7100_reset_asserted[offset]) & mask); +} + +static const struct reset_control_ops jh7100_reset_ops = { + .assert = jh7100_reset_assert, + .deassert = jh7100_reset_deassert, + .reset = jh7100_reset_reset, + .status = jh7100_reset_status, +}; + +int jh7100_reset_probe(struct platform_device *pdev) +{ + struct jh7100_reset *data; + + data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(data->base)) + return PTR_ERR(data->base); + + data->rcdev.ops = &jh7100_reset_ops; + data->rcdev.owner = THIS_MODULE; + data->rcdev.nr_resets = JH7100_RSTN_END; + data->rcdev.dev = &pdev->dev; + data->rcdev.of_node = pdev->dev.of_node; + spin_lock_init(&data->lock); + + return devm_reset_controller_register(&pdev->dev, &data->rcdev); +} +EXPORT_SYMBOL_GPL(jh7100_reset_probe); diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.h b/drivers/reset/starfive/reset-starfive-jh71x0.h new file mode 100644 index 000000000000..318d7a0e096a --- /dev/null +++ b/drivers/reset/starfive/reset-starfive-jh71x0.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 Emil Renner Berthing + */ + +#ifndef __RESET_STARFIVE_JH71X0_H +#define __RESET_STARFIVE_JH71X0_H + +int jh7100_reset_probe(struct platform_device *pdev); + +#endif /* __RESET_STARFIVE_JH71X0_H */ -- GitLab From ed36fcd160f3a703e0264539abdf0da2f3e0fc35 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:22 +0800 Subject: [PATCH 2090/5631] reset: starfive: Extract the common JH71X0 reset code Extract the common JH71X0 reset code for reusing them to support JH7110 SoC. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- .../reset/starfive/reset-starfive-jh7100.c | 49 ++++++++++++ .../reset/starfive/reset-starfive-jh71x0.c | 76 ++++++------------- .../reset/starfive/reset-starfive-jh71x0.h | 5 +- 3 files changed, 76 insertions(+), 54 deletions(-) diff --git a/drivers/reset/starfive/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c index 5a68327c1f6a..9d7cb4ed8869 100644 --- a/drivers/reset/starfive/reset-starfive-jh7100.c +++ b/drivers/reset/starfive/reset-starfive-jh7100.c @@ -10,6 +10,55 @@ #include "reset-starfive-jh71x0.h" +#include + +/* register offsets */ +#define JH7100_RESET_ASSERT0 0x00 +#define JH7100_RESET_ASSERT1 0x04 +#define JH7100_RESET_ASSERT2 0x08 +#define JH7100_RESET_ASSERT3 0x0c +#define JH7100_RESET_STATUS0 0x10 +#define JH7100_RESET_STATUS1 0x14 +#define JH7100_RESET_STATUS2 0x18 +#define JH7100_RESET_STATUS3 0x1c + +/* + * Writing a 1 to the n'th bit of the m'th ASSERT register asserts + * line 32m + n, and writing a 0 deasserts the same line. + * Most reset lines have their status inverted so a 0 bit in the STATUS + * register means the line is asserted and a 1 means it's deasserted. A few + * lines don't though, so store the expected value of the status registers when + * all lines are asserted. + */ +static const u64 jh7100_reset_asserted[2] = { + /* STATUS0 */ + BIT_ULL_MASK(JH7100_RST_U74) | + BIT_ULL_MASK(JH7100_RST_VP6_DRESET) | + BIT_ULL_MASK(JH7100_RST_VP6_BRESET) | + /* STATUS1 */ + BIT_ULL_MASK(JH7100_RST_HIFI4_DRESET) | + BIT_ULL_MASK(JH7100_RST_HIFI4_BRESET), + /* STATUS2 */ + BIT_ULL_MASK(JH7100_RST_E24) | + /* STATUS3 */ + 0, +}; + +static int __init jh7100_reset_probe(struct platform_device *pdev) +{ + void __iomem *base = devm_platform_ioremap_resource(pdev, 0); + + if (IS_ERR(base)) + return PTR_ERR(base); + + return reset_starfive_jh7100_register(&pdev->dev, pdev->dev.of_node, + base + JH7100_RESET_ASSERT0, + base + JH7100_RESET_STATUS0, + jh7100_reset_asserted, + JH7100_RSTN_END, + THIS_MODULE); +} + static const struct of_device_id jh7100_reset_dt_ids[] = { { .compatible = "starfive,jh7100-reset" }, { /* sentinel */ } diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.c b/drivers/reset/starfive/reset-starfive-jh71x0.c index 114a13c4b8a6..3577444a89c6 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.c +++ b/drivers/reset/starfive/reset-starfive-jh71x0.c @@ -10,51 +10,18 @@ #include #include #include -#include #include #include #include "reset-starfive-jh71x0.h" -#include - -/* register offsets */ -#define JH7100_RESET_ASSERT0 0x00 -#define JH7100_RESET_ASSERT1 0x04 -#define JH7100_RESET_ASSERT2 0x08 -#define JH7100_RESET_ASSERT3 0x0c -#define JH7100_RESET_STATUS0 0x10 -#define JH7100_RESET_STATUS1 0x14 -#define JH7100_RESET_STATUS2 0x18 -#define JH7100_RESET_STATUS3 0x1c - -/* - * Writing a 1 to the n'th bit of the m'th ASSERT register asserts - * line 32m + n, and writing a 0 deasserts the same line. - * Most reset lines have their status inverted so a 0 bit in the STATUS - * register means the line is asserted and a 1 means it's deasserted. A few - * lines don't though, so store the expected value of the status registers when - * all lines are asserted. - */ -static const u64 jh7100_reset_asserted[2] = { - /* STATUS0 */ - BIT_ULL_MASK(JH7100_RST_U74) | - BIT_ULL_MASK(JH7100_RST_VP6_DRESET) | - BIT_ULL_MASK(JH7100_RST_VP6_BRESET) | - /* STATUS1 */ - BIT_ULL_MASK(JH7100_RST_HIFI4_DRESET) | - BIT_ULL_MASK(JH7100_RST_HIFI4_BRESET), - /* STATUS2 */ - BIT_ULL_MASK(JH7100_RST_E24) | - /* STATUS3 */ - 0, -}; - struct jh7100_reset { struct reset_controller_dev rcdev; /* protect registers against concurrent read-modify-write */ spinlock_t lock; - void __iomem *base; + void __iomem *assert; + void __iomem *status; + const u64 *asserted; }; static inline struct jh7100_reset * @@ -69,9 +36,9 @@ static int jh7100_reset_update(struct reset_controller_dev *rcdev, struct jh7100_reset *data = jh7100_reset_from(rcdev); unsigned long offset = BIT_ULL_WORD(id); u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_assert = data->base + JH7100_RESET_ASSERT0 + offset * sizeof(u64); - void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); - u64 done = jh7100_reset_asserted[offset] & mask; + void __iomem *reg_assert = data->assert + offset * sizeof(u64); + void __iomem *reg_status = data->status + offset * sizeof(u64); + u64 done = data->asserted ? data->asserted[offset] & mask : 0; u64 value; unsigned long flags; int ret; @@ -125,10 +92,10 @@ static int jh7100_reset_status(struct reset_controller_dev *rcdev, struct jh7100_reset *data = jh7100_reset_from(rcdev); unsigned long offset = BIT_ULL_WORD(id); u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_status = data->base + JH7100_RESET_STATUS0 + offset * sizeof(u64); + void __iomem *reg_status = data->status + offset * sizeof(u64); u64 value = readq(reg_status); - return !((value ^ jh7100_reset_asserted[offset]) & mask); + return !((value ^ data->asserted[offset]) & mask); } static const struct reset_control_ops jh7100_reset_ops = { @@ -138,25 +105,28 @@ static const struct reset_control_ops jh7100_reset_ops = { .status = jh7100_reset_status, }; -int jh7100_reset_probe(struct platform_device *pdev) +int reset_starfive_jh7100_register(struct device *dev, struct device_node *of_node, + void __iomem *assert, void __iomem *status, + const u64 *asserted, unsigned int nr_resets, + struct module *owner) { struct jh7100_reset *data; - data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL); + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(data->base)) - return PTR_ERR(data->base); - data->rcdev.ops = &jh7100_reset_ops; - data->rcdev.owner = THIS_MODULE; - data->rcdev.nr_resets = JH7100_RSTN_END; - data->rcdev.dev = &pdev->dev; - data->rcdev.of_node = pdev->dev.of_node; + data->rcdev.owner = owner; + data->rcdev.nr_resets = nr_resets; + data->rcdev.dev = dev; + data->rcdev.of_node = of_node; + spin_lock_init(&data->lock); + data->assert = assert; + data->status = status; + data->asserted = asserted; - return devm_reset_controller_register(&pdev->dev, &data->rcdev); + return devm_reset_controller_register(dev, &data->rcdev); } -EXPORT_SYMBOL_GPL(jh7100_reset_probe); +EXPORT_SYMBOL_GPL(reset_starfive_jh7100_register); diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.h b/drivers/reset/starfive/reset-starfive-jh71x0.h index 318d7a0e096a..1fc5a648c8d8 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.h +++ b/drivers/reset/starfive/reset-starfive-jh71x0.h @@ -6,6 +6,9 @@ #ifndef __RESET_STARFIVE_JH71X0_H #define __RESET_STARFIVE_JH71X0_H -int jh7100_reset_probe(struct platform_device *pdev); +int reset_starfive_jh7100_register(struct device *dev, struct device_node *of_node, + void __iomem *assert, void __iomem *status, + const u64 *asserted, unsigned int nr_resets, + struct module *owner); #endif /* __RESET_STARFIVE_JH71X0_H */ -- GitLab From 0333103ee96069a7a53d8f599e70d86d4c18a53c Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:23 +0800 Subject: [PATCH 2091/5631] reset: starfive: Rename "jh7100" to "jh71x0" for the common code For the common code will be shared with the StarFive JH7110 SoC. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- .../reset/starfive/reset-starfive-jh7100.c | 2 +- .../reset/starfive/reset-starfive-jh71x0.c | 50 +++++++++---------- .../reset/starfive/reset-starfive-jh71x0.h | 2 +- 3 files changed, 27 insertions(+), 27 deletions(-) diff --git a/drivers/reset/starfive/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c index 9d7cb4ed8869..5f06e5ae3346 100644 --- a/drivers/reset/starfive/reset-starfive-jh7100.c +++ b/drivers/reset/starfive/reset-starfive-jh7100.c @@ -51,7 +51,7 @@ static int __init jh7100_reset_probe(struct platform_device *pdev) if (IS_ERR(base)) return PTR_ERR(base); - return reset_starfive_jh7100_register(&pdev->dev, pdev->dev.of_node, + return reset_starfive_jh71x0_register(&pdev->dev, pdev->dev.of_node, base + JH7100_RESET_ASSERT0, base + JH7100_RESET_STATUS0, jh7100_reset_asserted, diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.c b/drivers/reset/starfive/reset-starfive-jh71x0.c index 3577444a89c6..a689f4730ed7 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.c +++ b/drivers/reset/starfive/reset-starfive-jh71x0.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Reset driver for the StarFive JH7100 SoC + * Reset driver for the StarFive JH71X0 SoCs * * Copyright (C) 2021 Emil Renner Berthing */ @@ -15,7 +15,7 @@ #include "reset-starfive-jh71x0.h" -struct jh7100_reset { +struct jh71x0_reset { struct reset_controller_dev rcdev; /* protect registers against concurrent read-modify-write */ spinlock_t lock; @@ -24,16 +24,16 @@ struct jh7100_reset { const u64 *asserted; }; -static inline struct jh7100_reset * -jh7100_reset_from(struct reset_controller_dev *rcdev) +static inline struct jh71x0_reset * +jh71x0_reset_from(struct reset_controller_dev *rcdev) { - return container_of(rcdev, struct jh7100_reset, rcdev); + return container_of(rcdev, struct jh71x0_reset, rcdev); } -static int jh7100_reset_update(struct reset_controller_dev *rcdev, +static int jh71x0_reset_update(struct reset_controller_dev *rcdev, unsigned long id, bool assert) { - struct jh7100_reset *data = jh7100_reset_from(rcdev); + struct jh71x0_reset *data = jh71x0_reset_from(rcdev); unsigned long offset = BIT_ULL_WORD(id); u64 mask = BIT_ULL_MASK(id); void __iomem *reg_assert = data->assert + offset * sizeof(u64); @@ -62,34 +62,34 @@ static int jh7100_reset_update(struct reset_controller_dev *rcdev, return ret; } -static int jh7100_reset_assert(struct reset_controller_dev *rcdev, +static int jh71x0_reset_assert(struct reset_controller_dev *rcdev, unsigned long id) { - return jh7100_reset_update(rcdev, id, true); + return jh71x0_reset_update(rcdev, id, true); } -static int jh7100_reset_deassert(struct reset_controller_dev *rcdev, +static int jh71x0_reset_deassert(struct reset_controller_dev *rcdev, unsigned long id) { - return jh7100_reset_update(rcdev, id, false); + return jh71x0_reset_update(rcdev, id, false); } -static int jh7100_reset_reset(struct reset_controller_dev *rcdev, +static int jh71x0_reset_reset(struct reset_controller_dev *rcdev, unsigned long id) { int ret; - ret = jh7100_reset_assert(rcdev, id); + ret = jh71x0_reset_assert(rcdev, id); if (ret) return ret; - return jh7100_reset_deassert(rcdev, id); + return jh71x0_reset_deassert(rcdev, id); } -static int jh7100_reset_status(struct reset_controller_dev *rcdev, +static int jh71x0_reset_status(struct reset_controller_dev *rcdev, unsigned long id) { - struct jh7100_reset *data = jh7100_reset_from(rcdev); + struct jh71x0_reset *data = jh71x0_reset_from(rcdev); unsigned long offset = BIT_ULL_WORD(id); u64 mask = BIT_ULL_MASK(id); void __iomem *reg_status = data->status + offset * sizeof(u64); @@ -98,25 +98,25 @@ static int jh7100_reset_status(struct reset_controller_dev *rcdev, return !((value ^ data->asserted[offset]) & mask); } -static const struct reset_control_ops jh7100_reset_ops = { - .assert = jh7100_reset_assert, - .deassert = jh7100_reset_deassert, - .reset = jh7100_reset_reset, - .status = jh7100_reset_status, +static const struct reset_control_ops jh71x0_reset_ops = { + .assert = jh71x0_reset_assert, + .deassert = jh71x0_reset_deassert, + .reset = jh71x0_reset_reset, + .status = jh71x0_reset_status, }; -int reset_starfive_jh7100_register(struct device *dev, struct device_node *of_node, +int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node, void __iomem *assert, void __iomem *status, const u64 *asserted, unsigned int nr_resets, struct module *owner) { - struct jh7100_reset *data; + struct jh71x0_reset *data; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; - data->rcdev.ops = &jh7100_reset_ops; + data->rcdev.ops = &jh71x0_reset_ops; data->rcdev.owner = owner; data->rcdev.nr_resets = nr_resets; data->rcdev.dev = dev; @@ -129,4 +129,4 @@ int reset_starfive_jh7100_register(struct device *dev, struct device_node *of_no return devm_reset_controller_register(dev, &data->rcdev); } -EXPORT_SYMBOL_GPL(reset_starfive_jh7100_register); +EXPORT_SYMBOL_GPL(reset_starfive_jh71x0_register); diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.h b/drivers/reset/starfive/reset-starfive-jh71x0.h index 1fc5a648c8d8..ac9e80dd3f59 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.h +++ b/drivers/reset/starfive/reset-starfive-jh71x0.h @@ -6,7 +6,7 @@ #ifndef __RESET_STARFIVE_JH71X0_H #define __RESET_STARFIVE_JH71X0_H -int reset_starfive_jh7100_register(struct device *dev, struct device_node *of_node, +int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node, void __iomem *assert, void __iomem *status, const u64 *asserted, unsigned int nr_resets, struct module *owner); -- GitLab From b6d7406cd7a199fabf93008e9fc0aa0358695a79 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:24 +0800 Subject: [PATCH 2092/5631] reset: starfive: jh71x0: Use 32bit I/O on 32bit registers We currently use 64bit I/O on the 32bit registers. This works because there are an even number of assert and status registers, so they're only ever accessed in pairs on 64bit boundaries. There are however other reset controllers for audio and video on the JH7100 SoC with only one status register that isn't 64bit aligned so 64bit I/O results in an unaligned access exception. Switch to 32bit I/O in preparation for supporting these resets too. Tested-by: Tommaso Merciai Reviewed-by: Conor Dooley Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- .../reset/starfive/reset-starfive-jh7100.c | 14 ++++----- .../reset/starfive/reset-starfive-jh71x0.c | 31 +++++++++---------- .../reset/starfive/reset-starfive-jh71x0.h | 2 +- 3 files changed, 23 insertions(+), 24 deletions(-) diff --git a/drivers/reset/starfive/reset-starfive-jh7100.c b/drivers/reset/starfive/reset-starfive-jh7100.c index 5f06e5ae3346..2a56f7fd4ba7 100644 --- a/drivers/reset/starfive/reset-starfive-jh7100.c +++ b/drivers/reset/starfive/reset-starfive-jh7100.c @@ -30,16 +30,16 @@ * lines don't though, so store the expected value of the status registers when * all lines are asserted. */ -static const u64 jh7100_reset_asserted[2] = { +static const u32 jh7100_reset_asserted[4] = { /* STATUS0 */ - BIT_ULL_MASK(JH7100_RST_U74) | - BIT_ULL_MASK(JH7100_RST_VP6_DRESET) | - BIT_ULL_MASK(JH7100_RST_VP6_BRESET) | + BIT(JH7100_RST_U74 % 32) | + BIT(JH7100_RST_VP6_DRESET % 32) | + BIT(JH7100_RST_VP6_BRESET % 32), /* STATUS1 */ - BIT_ULL_MASK(JH7100_RST_HIFI4_DRESET) | - BIT_ULL_MASK(JH7100_RST_HIFI4_BRESET), + BIT(JH7100_RST_HIFI4_DRESET % 32) | + BIT(JH7100_RST_HIFI4_BRESET % 32), /* STATUS2 */ - BIT_ULL_MASK(JH7100_RST_E24) | + BIT(JH7100_RST_E24 % 32), /* STATUS3 */ 0, }; diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.c b/drivers/reset/starfive/reset-starfive-jh71x0.c index a689f4730ed7..55bbbd2de52c 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.c +++ b/drivers/reset/starfive/reset-starfive-jh71x0.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include @@ -21,7 +20,7 @@ struct jh71x0_reset { spinlock_t lock; void __iomem *assert; void __iomem *status; - const u64 *asserted; + const u32 *asserted; }; static inline struct jh71x0_reset * @@ -34,12 +33,12 @@ static int jh71x0_reset_update(struct reset_controller_dev *rcdev, unsigned long id, bool assert) { struct jh71x0_reset *data = jh71x0_reset_from(rcdev); - unsigned long offset = BIT_ULL_WORD(id); - u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_assert = data->assert + offset * sizeof(u64); - void __iomem *reg_status = data->status + offset * sizeof(u64); - u64 done = data->asserted ? data->asserted[offset] & mask : 0; - u64 value; + unsigned long offset = id / 32; + u32 mask = BIT(id % 32); + void __iomem *reg_assert = data->assert + offset * sizeof(u32); + void __iomem *reg_status = data->status + offset * sizeof(u32); + u32 done = data->asserted ? data->asserted[offset] & mask : 0; + u32 value; unsigned long flags; int ret; @@ -48,15 +47,15 @@ static int jh71x0_reset_update(struct reset_controller_dev *rcdev, spin_lock_irqsave(&data->lock, flags); - value = readq(reg_assert); + value = readl(reg_assert); if (assert) value |= mask; else value &= ~mask; - writeq(value, reg_assert); + writel(value, reg_assert); /* if the associated clock is gated, deasserting might otherwise hang forever */ - ret = readq_poll_timeout_atomic(reg_status, value, (value & mask) == done, 0, 1000); + ret = readl_poll_timeout_atomic(reg_status, value, (value & mask) == done, 0, 1000); spin_unlock_irqrestore(&data->lock, flags); return ret; @@ -90,10 +89,10 @@ static int jh71x0_reset_status(struct reset_controller_dev *rcdev, unsigned long id) { struct jh71x0_reset *data = jh71x0_reset_from(rcdev); - unsigned long offset = BIT_ULL_WORD(id); - u64 mask = BIT_ULL_MASK(id); - void __iomem *reg_status = data->status + offset * sizeof(u64); - u64 value = readq(reg_status); + unsigned long offset = id / 32; + u32 mask = BIT(id % 32); + void __iomem *reg_status = data->status + offset * sizeof(u32); + u32 value = readl(reg_status); return !((value ^ data->asserted[offset]) & mask); } @@ -107,7 +106,7 @@ static const struct reset_control_ops jh71x0_reset_ops = { int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node, void __iomem *assert, void __iomem *status, - const u64 *asserted, unsigned int nr_resets, + const u32 *asserted, unsigned int nr_resets, struct module *owner) { struct jh71x0_reset *data; diff --git a/drivers/reset/starfive/reset-starfive-jh71x0.h b/drivers/reset/starfive/reset-starfive-jh71x0.h index ac9e80dd3f59..db7d39a87f87 100644 --- a/drivers/reset/starfive/reset-starfive-jh71x0.h +++ b/drivers/reset/starfive/reset-starfive-jh71x0.h @@ -8,7 +8,7 @@ int reset_starfive_jh71x0_register(struct device *dev, struct device_node *of_node, void __iomem *assert, void __iomem *status, - const u64 *asserted, unsigned int nr_resets, + const u32 *asserted, unsigned int nr_resets, struct module *owner); #endif /* __RESET_STARFIVE_JH71X0_H */ -- GitLab From edab7204afe55bdf2d17d3490eb88497ba60f628 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:25 +0800 Subject: [PATCH 2093/5631] clk: starfive: Add StarFive JH7110 system clock driver Add driver for the StarFive JH7110 system clock controller and register an auxiliary device for system reset controller which is named as "rst-sys". Tested-by: Tommaso Merciai Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Co-developed-by: Hal Feng Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/clk/starfive/Kconfig | 11 + drivers/clk/starfive/Makefile | 2 + .../clk/starfive/clk-starfive-jh7110-sys.c | 490 ++++++++++++++++++ drivers/clk/starfive/clk-starfive-jh7110.h | 11 + 4 files changed, 514 insertions(+) create mode 100644 drivers/clk/starfive/clk-starfive-jh7110-sys.c create mode 100644 drivers/clk/starfive/clk-starfive-jh7110.h diff --git a/drivers/clk/starfive/Kconfig b/drivers/clk/starfive/Kconfig index 3ceeb19b5eda..670c5084aeb8 100644 --- a/drivers/clk/starfive/Kconfig +++ b/drivers/clk/starfive/Kconfig @@ -20,3 +20,14 @@ config CLK_STARFIVE_JH7100_AUDIO help Say Y or M here to support the audio clocks on the StarFive JH7100 SoC. + +config CLK_STARFIVE_JH7110_SYS + bool "StarFive JH7110 system clock support" + depends on ARCH_STARFIVE || COMPILE_TEST + select AUXILIARY_BUS + select CLK_STARFIVE_JH71X0 + select RESET_STARFIVE_JH7110 + default ARCH_STARFIVE + help + Say yes here to support the system clock controller on the + StarFive JH7110 SoC. diff --git a/drivers/clk/starfive/Makefile b/drivers/clk/starfive/Makefile index 82edfa9f9cb8..5ca4e887fb9c 100644 --- a/drivers/clk/starfive/Makefile +++ b/drivers/clk/starfive/Makefile @@ -3,3 +3,5 @@ obj-$(CONFIG_CLK_STARFIVE_JH71X0) += clk-starfive-jh71x0.o obj-$(CONFIG_CLK_STARFIVE_JH7100) += clk-starfive-jh7100.o obj-$(CONFIG_CLK_STARFIVE_JH7100_AUDIO) += clk-starfive-jh7100-audio.o + +obj-$(CONFIG_CLK_STARFIVE_JH7110_SYS) += clk-starfive-jh7110-sys.o diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c new file mode 100644 index 000000000000..5ec210644e1d --- /dev/null +++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c @@ -0,0 +1,490 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * StarFive JH7110 System Clock Driver + * + * Copyright (C) 2022 Emil Renner Berthing + * Copyright (C) 2022 StarFive Technology Co., Ltd. + */ + +#include +#include +#include +#include +#include + +#include + +#include "clk-starfive-jh7110.h" + +/* external clocks */ +#define JH7110_SYSCLK_OSC (JH7110_SYSCLK_END + 0) +#define JH7110_SYSCLK_GMAC1_RMII_REFIN (JH7110_SYSCLK_END + 1) +#define JH7110_SYSCLK_GMAC1_RGMII_RXIN (JH7110_SYSCLK_END + 2) +#define JH7110_SYSCLK_I2STX_BCLK_EXT (JH7110_SYSCLK_END + 3) +#define JH7110_SYSCLK_I2STX_LRCK_EXT (JH7110_SYSCLK_END + 4) +#define JH7110_SYSCLK_I2SRX_BCLK_EXT (JH7110_SYSCLK_END + 5) +#define JH7110_SYSCLK_I2SRX_LRCK_EXT (JH7110_SYSCLK_END + 6) +#define JH7110_SYSCLK_TDM_EXT (JH7110_SYSCLK_END + 7) +#define JH7110_SYSCLK_MCLK_EXT (JH7110_SYSCLK_END + 8) +#define JH7110_SYSCLK_PLL0_OUT (JH7110_SYSCLK_END + 9) +#define JH7110_SYSCLK_PLL1_OUT (JH7110_SYSCLK_END + 10) +#define JH7110_SYSCLK_PLL2_OUT (JH7110_SYSCLK_END + 11) + +static const struct jh71x0_clk_data jh7110_sysclk_data[] __initconst = { + /* root */ + JH71X0__MUX(JH7110_SYSCLK_CPU_ROOT, "cpu_root", 2, + JH7110_SYSCLK_OSC, + JH7110_SYSCLK_PLL0_OUT), + JH71X0__DIV(JH7110_SYSCLK_CPU_CORE, "cpu_core", 7, JH7110_SYSCLK_CPU_ROOT), + JH71X0__DIV(JH7110_SYSCLK_CPU_BUS, "cpu_bus", 2, JH7110_SYSCLK_CPU_CORE), + JH71X0__MUX(JH7110_SYSCLK_GPU_ROOT, "gpu_root", 2, + JH7110_SYSCLK_PLL2_OUT, + JH7110_SYSCLK_PLL1_OUT), + JH71X0_MDIV(JH7110_SYSCLK_PERH_ROOT, "perh_root", 2, 2, + JH7110_SYSCLK_PLL0_OUT, + JH7110_SYSCLK_PLL2_OUT), + JH71X0__MUX(JH7110_SYSCLK_BUS_ROOT, "bus_root", 2, + JH7110_SYSCLK_OSC, + JH7110_SYSCLK_PLL2_OUT), + JH71X0__DIV(JH7110_SYSCLK_NOCSTG_BUS, "nocstg_bus", 3, JH7110_SYSCLK_BUS_ROOT), + JH71X0__DIV(JH7110_SYSCLK_AXI_CFG0, "axi_cfg0", 3, JH7110_SYSCLK_BUS_ROOT), + JH71X0__DIV(JH7110_SYSCLK_STG_AXIAHB, "stg_axiahb", 2, JH7110_SYSCLK_AXI_CFG0), + JH71X0_GATE(JH7110_SYSCLK_AHB0, "ahb0", CLK_IS_CRITICAL, JH7110_SYSCLK_STG_AXIAHB), + JH71X0_GATE(JH7110_SYSCLK_AHB1, "ahb1", CLK_IS_CRITICAL, JH7110_SYSCLK_STG_AXIAHB), + JH71X0__DIV(JH7110_SYSCLK_APB_BUS, "apb_bus", 8, JH7110_SYSCLK_STG_AXIAHB), + JH71X0_GATE(JH7110_SYSCLK_APB0, "apb0", CLK_IS_CRITICAL, JH7110_SYSCLK_APB_BUS), + JH71X0__DIV(JH7110_SYSCLK_PLL0_DIV2, "pll0_div2", 2, JH7110_SYSCLK_PLL0_OUT), + JH71X0__DIV(JH7110_SYSCLK_PLL1_DIV2, "pll1_div2", 2, JH7110_SYSCLK_PLL1_OUT), + JH71X0__DIV(JH7110_SYSCLK_PLL2_DIV2, "pll2_div2", 2, JH7110_SYSCLK_PLL2_OUT), + JH71X0__DIV(JH7110_SYSCLK_AUDIO_ROOT, "audio_root", 8, JH7110_SYSCLK_PLL2_OUT), + JH71X0__DIV(JH7110_SYSCLK_MCLK_INNER, "mclk_inner", 64, JH7110_SYSCLK_AUDIO_ROOT), + JH71X0__MUX(JH7110_SYSCLK_MCLK, "mclk", 2, + JH7110_SYSCLK_MCLK_INNER, + JH7110_SYSCLK_MCLK_EXT), + JH71X0_GATE(JH7110_SYSCLK_MCLK_OUT, "mclk_out", 0, JH7110_SYSCLK_MCLK_INNER), + JH71X0_MDIV(JH7110_SYSCLK_ISP_2X, "isp_2x", 8, 2, + JH7110_SYSCLK_PLL2_OUT, + JH7110_SYSCLK_PLL1_OUT), + JH71X0__DIV(JH7110_SYSCLK_ISP_AXI, "isp_axi", 4, JH7110_SYSCLK_ISP_2X), + JH71X0_GDIV(JH7110_SYSCLK_GCLK0, "gclk0", 0, 62, JH7110_SYSCLK_PLL0_DIV2), + JH71X0_GDIV(JH7110_SYSCLK_GCLK1, "gclk1", 0, 62, JH7110_SYSCLK_PLL1_DIV2), + JH71X0_GDIV(JH7110_SYSCLK_GCLK2, "gclk2", 0, 62, JH7110_SYSCLK_PLL2_DIV2), + /* cores */ + JH71X0_GATE(JH7110_SYSCLK_CORE, "core", CLK_IS_CRITICAL, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_CORE1, "core1", CLK_IS_CRITICAL, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_CORE2, "core2", CLK_IS_CRITICAL, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_CORE3, "core3", CLK_IS_CRITICAL, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_CORE4, "core4", CLK_IS_CRITICAL, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_DEBUG, "debug", 0, JH7110_SYSCLK_CPU_BUS), + JH71X0__DIV(JH7110_SYSCLK_RTC_TOGGLE, "rtc_toggle", 6, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_TRACE0, "trace0", 0, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_TRACE1, "trace1", 0, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_TRACE2, "trace2", 0, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_TRACE3, "trace3", 0, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_TRACE4, "trace4", 0, JH7110_SYSCLK_CPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_TRACE_COM, "trace_com", 0, JH7110_SYSCLK_CPU_BUS), + /* noc */ + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_CPU_AXI, "noc_bus_cpu_axi", CLK_IS_CRITICAL, + JH7110_SYSCLK_CPU_BUS), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_AXICFG0_AXI, "noc_bus_axicfg0_axi", CLK_IS_CRITICAL, + JH7110_SYSCLK_AXI_CFG0), + /* ddr */ + JH71X0__DIV(JH7110_SYSCLK_OSC_DIV2, "osc_div2", 2, JH7110_SYSCLK_OSC), + JH71X0__DIV(JH7110_SYSCLK_PLL1_DIV4, "pll1_div4", 2, JH7110_SYSCLK_PLL1_DIV2), + JH71X0__DIV(JH7110_SYSCLK_PLL1_DIV8, "pll1_div8", 2, JH7110_SYSCLK_PLL1_DIV4), + JH71X0__MUX(JH7110_SYSCLK_DDR_BUS, "ddr_bus", 4, + JH7110_SYSCLK_OSC_DIV2, + JH7110_SYSCLK_PLL1_DIV2, + JH7110_SYSCLK_PLL1_DIV4, + JH7110_SYSCLK_PLL1_DIV8), + JH71X0_GATE(JH7110_SYSCLK_DDR_AXI, "ddr_axi", CLK_IS_CRITICAL, JH7110_SYSCLK_DDR_BUS), + /* gpu */ + JH71X0__DIV(JH7110_SYSCLK_GPU_CORE, "gpu_core", 7, JH7110_SYSCLK_GPU_ROOT), + JH71X0_GATE(JH7110_SYSCLK_GPU_CORE_CLK, "gpu_core_clk", 0, JH7110_SYSCLK_GPU_CORE), + JH71X0_GATE(JH7110_SYSCLK_GPU_SYS_CLK, "gpu_sys_clk", 0, JH7110_SYSCLK_ISP_AXI), + JH71X0_GATE(JH7110_SYSCLK_GPU_APB, "gpu_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GDIV(JH7110_SYSCLK_GPU_RTC_TOGGLE, "gpu_rtc_toggle", 0, 12, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_GPU_AXI, "noc_bus_gpu_axi", 0, JH7110_SYSCLK_GPU_CORE), + /* isp */ + JH71X0_GATE(JH7110_SYSCLK_ISP_TOP_CORE, "isp_top_core", 0, JH7110_SYSCLK_ISP_2X), + JH71X0_GATE(JH7110_SYSCLK_ISP_TOP_AXI, "isp_top_axi", 0, JH7110_SYSCLK_ISP_AXI), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_ISP_AXI, "noc_bus_isp_axi", CLK_IS_CRITICAL, + JH7110_SYSCLK_ISP_AXI), + /* hifi4 */ + JH71X0__DIV(JH7110_SYSCLK_HIFI4_CORE, "hifi4_core", 15, JH7110_SYSCLK_BUS_ROOT), + JH71X0__DIV(JH7110_SYSCLK_HIFI4_AXI, "hifi4_axi", 2, JH7110_SYSCLK_HIFI4_CORE), + /* axi_cfg1 */ + JH71X0_GATE(JH7110_SYSCLK_AXI_CFG1_MAIN, "axi_cfg1_main", CLK_IS_CRITICAL, + JH7110_SYSCLK_ISP_AXI), + JH71X0_GATE(JH7110_SYSCLK_AXI_CFG1_AHB, "axi_cfg1_ahb", CLK_IS_CRITICAL, + JH7110_SYSCLK_AHB0), + /* vout */ + JH71X0_GATE(JH7110_SYSCLK_VOUT_SRC, "vout_src", 0, JH7110_SYSCLK_PLL2_OUT), + JH71X0__DIV(JH7110_SYSCLK_VOUT_AXI, "vout_axi", 7, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_DISP_AXI, "noc_bus_disp_axi", 0, JH7110_SYSCLK_VOUT_AXI), + JH71X0_GATE(JH7110_SYSCLK_VOUT_TOP_AHB, "vout_top_ahb", 0, JH7110_SYSCLK_AHB1), + JH71X0_GATE(JH7110_SYSCLK_VOUT_TOP_AXI, "vout_top_axi", 0, JH7110_SYSCLK_VOUT_AXI), + JH71X0_GATE(JH7110_SYSCLK_VOUT_TOP_HDMITX0_MCLK, "vout_top_hdmitx0_mclk", 0, + JH7110_SYSCLK_MCLK), + JH71X0__DIV(JH7110_SYSCLK_VOUT_TOP_MIPIPHY_REF, "vout_top_mipiphy_ref", 2, + JH7110_SYSCLK_OSC), + /* jpegc */ + JH71X0__DIV(JH7110_SYSCLK_JPEGC_AXI, "jpegc_axi", 16, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GATE(JH7110_SYSCLK_CODAJ12_AXI, "codaj12_axi", 0, JH7110_SYSCLK_JPEGC_AXI), + JH71X0_GDIV(JH7110_SYSCLK_CODAJ12_CORE, "codaj12_core", 0, 16, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GATE(JH7110_SYSCLK_CODAJ12_APB, "codaj12_apb", 0, JH7110_SYSCLK_APB_BUS), + /* vdec */ + JH71X0__DIV(JH7110_SYSCLK_VDEC_AXI, "vdec_axi", 7, JH7110_SYSCLK_BUS_ROOT), + JH71X0_GATE(JH7110_SYSCLK_WAVE511_AXI, "wave511_axi", 0, JH7110_SYSCLK_VDEC_AXI), + JH71X0_GDIV(JH7110_SYSCLK_WAVE511_BPU, "wave511_bpu", 0, 7, JH7110_SYSCLK_BUS_ROOT), + JH71X0_GDIV(JH7110_SYSCLK_WAVE511_VCE, "wave511_vce", 0, 7, JH7110_SYSCLK_PLL0_OUT), + JH71X0_GATE(JH7110_SYSCLK_WAVE511_APB, "wave511_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_VDEC_JPG, "vdec_jpg", 0, JH7110_SYSCLK_JPEGC_AXI), + JH71X0_GATE(JH7110_SYSCLK_VDEC_MAIN, "vdec_main", 0, JH7110_SYSCLK_VDEC_AXI), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_VDEC_AXI, "noc_bus_vdec_axi", 0, JH7110_SYSCLK_VDEC_AXI), + /* venc */ + JH71X0__DIV(JH7110_SYSCLK_VENC_AXI, "venc_axi", 15, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GATE(JH7110_SYSCLK_WAVE420L_AXI, "wave420l_axi", 0, JH7110_SYSCLK_VENC_AXI), + JH71X0_GDIV(JH7110_SYSCLK_WAVE420L_BPU, "wave420l_bpu", 0, 15, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GDIV(JH7110_SYSCLK_WAVE420L_VCE, "wave420l_vce", 0, 15, JH7110_SYSCLK_PLL2_OUT), + JH71X0_GATE(JH7110_SYSCLK_WAVE420L_APB, "wave420l_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_VENC_AXI, "noc_bus_venc_axi", 0, JH7110_SYSCLK_VENC_AXI), + /* axi_cfg0 */ + JH71X0_GATE(JH7110_SYSCLK_AXI_CFG0_MAIN_DIV, "axi_cfg0_main_div", CLK_IS_CRITICAL, + JH7110_SYSCLK_AHB1), + JH71X0_GATE(JH7110_SYSCLK_AXI_CFG0_MAIN, "axi_cfg0_main", CLK_IS_CRITICAL, + JH7110_SYSCLK_AXI_CFG0), + JH71X0_GATE(JH7110_SYSCLK_AXI_CFG0_HIFI4, "axi_cfg0_hifi4", CLK_IS_CRITICAL, + JH7110_SYSCLK_HIFI4_AXI), + /* intmem */ + JH71X0_GATE(JH7110_SYSCLK_AXIMEM2_AXI, "aximem2_axi", 0, JH7110_SYSCLK_AXI_CFG0), + /* qspi */ + JH71X0_GATE(JH7110_SYSCLK_QSPI_AHB, "qspi_ahb", 0, JH7110_SYSCLK_AHB1), + JH71X0_GATE(JH7110_SYSCLK_QSPI_APB, "qspi_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0__DIV(JH7110_SYSCLK_QSPI_REF_SRC, "qspi_ref_src", 16, JH7110_SYSCLK_PLL0_OUT), + JH71X0_GMUX(JH7110_SYSCLK_QSPI_REF, "qspi_ref", 0, 2, + JH7110_SYSCLK_OSC, + JH7110_SYSCLK_QSPI_REF_SRC), + /* sdio */ + JH71X0_GATE(JH7110_SYSCLK_SDIO0_AHB, "sdio0_ahb", 0, JH7110_SYSCLK_AHB0), + JH71X0_GATE(JH7110_SYSCLK_SDIO1_AHB, "sdio1_ahb", 0, JH7110_SYSCLK_AHB0), + JH71X0_GDIV(JH7110_SYSCLK_SDIO0_SDCARD, "sdio0_sdcard", 0, 15, JH7110_SYSCLK_AXI_CFG0), + JH71X0_GDIV(JH7110_SYSCLK_SDIO1_SDCARD, "sdio1_sdcard", 0, 15, JH7110_SYSCLK_AXI_CFG0), + /* stg */ + JH71X0__DIV(JH7110_SYSCLK_USB_125M, "usb_125m", 15, JH7110_SYSCLK_PLL0_OUT), + JH71X0_GATE(JH7110_SYSCLK_NOC_BUS_STG_AXI, "noc_bus_stg_axi", CLK_IS_CRITICAL, + JH7110_SYSCLK_NOCSTG_BUS), + /* gmac1 */ + JH71X0_GATE(JH7110_SYSCLK_GMAC1_AHB, "gmac1_ahb", 0, JH7110_SYSCLK_AHB0), + JH71X0_GATE(JH7110_SYSCLK_GMAC1_AXI, "gmac1_axi", 0, JH7110_SYSCLK_STG_AXIAHB), + JH71X0__DIV(JH7110_SYSCLK_GMAC_SRC, "gmac_src", 7, JH7110_SYSCLK_PLL0_OUT), + JH71X0__DIV(JH7110_SYSCLK_GMAC1_GTXCLK, "gmac1_gtxclk", 15, JH7110_SYSCLK_PLL0_OUT), + JH71X0__DIV(JH7110_SYSCLK_GMAC1_RMII_RTX, "gmac1_rmii_rtx", 30, + JH7110_SYSCLK_GMAC1_RMII_REFIN), + JH71X0_GDIV(JH7110_SYSCLK_GMAC1_PTP, "gmac1_ptp", 0, 31, JH7110_SYSCLK_GMAC_SRC), + JH71X0__MUX(JH7110_SYSCLK_GMAC1_RX, "gmac1_rx", 2, + JH7110_SYSCLK_GMAC1_RGMII_RXIN, + JH7110_SYSCLK_GMAC1_RMII_RTX), + JH71X0__INV(JH7110_SYSCLK_GMAC1_RX_INV, "gmac1_rx_inv", JH7110_SYSCLK_GMAC1_RX), + JH71X0_GMUX(JH7110_SYSCLK_GMAC1_TX, "gmac1_tx", + CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT, 2, + JH7110_SYSCLK_GMAC1_GTXCLK, + JH7110_SYSCLK_GMAC1_RMII_RTX), + JH71X0__INV(JH7110_SYSCLK_GMAC1_TX_INV, "gmac1_tx_inv", JH7110_SYSCLK_GMAC1_TX), + JH71X0_GATE(JH7110_SYSCLK_GMAC1_GTXC, "gmac1_gtxc", 0, JH7110_SYSCLK_GMAC1_GTXCLK), + /* gmac0 */ + JH71X0_GDIV(JH7110_SYSCLK_GMAC0_GTXCLK, "gmac0_gtxclk", 0, 15, JH7110_SYSCLK_PLL0_OUT), + JH71X0_GDIV(JH7110_SYSCLK_GMAC0_PTP, "gmac0_ptp", 0, 31, JH7110_SYSCLK_GMAC_SRC), + JH71X0_GDIV(JH7110_SYSCLK_GMAC_PHY, "gmac_phy", 0, 31, JH7110_SYSCLK_GMAC_SRC), + JH71X0_GATE(JH7110_SYSCLK_GMAC0_GTXC, "gmac0_gtxc", 0, JH7110_SYSCLK_GMAC0_GTXCLK), + /* apb misc */ + JH71X0_GATE(JH7110_SYSCLK_IOMUX_APB, "iomux_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_MAILBOX_APB, "mailbox_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_INT_CTRL_APB, "int_ctrl_apb", 0, JH7110_SYSCLK_APB_BUS), + /* can0 */ + JH71X0_GATE(JH7110_SYSCLK_CAN0_APB, "can0_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GDIV(JH7110_SYSCLK_CAN0_TIMER, "can0_timer", 0, 24, JH7110_SYSCLK_OSC), + JH71X0_GDIV(JH7110_SYSCLK_CAN0_CAN, "can0_can", 0, 63, JH7110_SYSCLK_PERH_ROOT), + /* can1 */ + JH71X0_GATE(JH7110_SYSCLK_CAN1_APB, "can1_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GDIV(JH7110_SYSCLK_CAN1_TIMER, "can1_timer", 0, 24, JH7110_SYSCLK_OSC), + JH71X0_GDIV(JH7110_SYSCLK_CAN1_CAN, "can1_can", 0, 63, JH7110_SYSCLK_PERH_ROOT), + /* pwm */ + JH71X0_GATE(JH7110_SYSCLK_PWM_APB, "pwm_apb", 0, JH7110_SYSCLK_APB_BUS), + /* wdt */ + JH71X0_GATE(JH7110_SYSCLK_WDT_APB, "wdt_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_WDT_CORE, "wdt_core", 0, JH7110_SYSCLK_OSC), + /* timer */ + JH71X0_GATE(JH7110_SYSCLK_TIMER_APB, "timer_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_TIMER0, "timer0", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_TIMER1, "timer1", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_TIMER2, "timer2", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_TIMER3, "timer3", 0, JH7110_SYSCLK_OSC), + /* temp sensor */ + JH71X0_GATE(JH7110_SYSCLK_TEMP_APB, "temp_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GDIV(JH7110_SYSCLK_TEMP_CORE, "temp_core", 0, 24, JH7110_SYSCLK_OSC), + /* spi */ + JH71X0_GATE(JH7110_SYSCLK_SPI0_APB, "spi0_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_SPI1_APB, "spi1_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_SPI2_APB, "spi2_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_SPI3_APB, "spi3_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_SPI4_APB, "spi4_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_SPI5_APB, "spi5_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_SPI6_APB, "spi6_apb", 0, JH7110_SYSCLK_APB_BUS), + /* i2c */ + JH71X0_GATE(JH7110_SYSCLK_I2C0_APB, "i2c0_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_I2C1_APB, "i2c1_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_I2C2_APB, "i2c2_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_I2C3_APB, "i2c3_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_I2C4_APB, "i2c4_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_I2C5_APB, "i2c5_apb", 0, JH7110_SYSCLK_APB_BUS), + JH71X0_GATE(JH7110_SYSCLK_I2C6_APB, "i2c6_apb", 0, JH7110_SYSCLK_APB_BUS), + /* uart */ + JH71X0_GATE(JH7110_SYSCLK_UART0_APB, "uart0_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_UART0_CORE, "uart0_core", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_UART1_APB, "uart1_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_UART1_CORE, "uart1_core", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_UART2_APB, "uart2_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_UART2_CORE, "uart2_core", 0, JH7110_SYSCLK_OSC), + JH71X0_GATE(JH7110_SYSCLK_UART3_APB, "uart3_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_UART3_CORE, "uart3_core", 0, 10, JH7110_SYSCLK_PERH_ROOT), + JH71X0_GATE(JH7110_SYSCLK_UART4_APB, "uart4_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_UART4_CORE, "uart4_core", 0, 10, JH7110_SYSCLK_PERH_ROOT), + JH71X0_GATE(JH7110_SYSCLK_UART5_APB, "uart5_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_UART5_CORE, "uart5_core", 0, 10, JH7110_SYSCLK_PERH_ROOT), + /* pwmdac */ + JH71X0_GATE(JH7110_SYSCLK_PWMDAC_APB, "pwmdac_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_PWMDAC_CORE, "pwmdac_core", 0, 256, JH7110_SYSCLK_AUDIO_ROOT), + /* spdif */ + JH71X0_GATE(JH7110_SYSCLK_SPDIF_APB, "spdif_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GATE(JH7110_SYSCLK_SPDIF_CORE, "spdif_core", 0, JH7110_SYSCLK_MCLK), + /* i2stx0 */ + JH71X0_GATE(JH7110_SYSCLK_I2STX0_APB, "i2stx0_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_I2STX0_BCLK_MST, "i2stx0_bclk_mst", 0, 32, JH7110_SYSCLK_MCLK), + JH71X0__INV(JH7110_SYSCLK_I2STX0_BCLK_MST_INV, "i2stx0_bclk_mst_inv", + JH7110_SYSCLK_I2STX0_BCLK_MST), + JH71X0_MDIV(JH7110_SYSCLK_I2STX0_LRCK_MST, "i2stx0_lrck_mst", 64, 2, + JH7110_SYSCLK_I2STX0_BCLK_MST_INV, + JH7110_SYSCLK_I2STX0_BCLK_MST), + JH71X0__MUX(JH7110_SYSCLK_I2STX0_BCLK, "i2stx0_bclk", 2, + JH7110_SYSCLK_I2STX0_BCLK_MST, + JH7110_SYSCLK_I2STX_BCLK_EXT), + JH71X0__INV(JH7110_SYSCLK_I2STX0_BCLK_INV, "i2stx0_bclk_inv", JH7110_SYSCLK_I2STX0_BCLK), + JH71X0__MUX(JH7110_SYSCLK_I2STX0_LRCK, "i2stx0_lrck", 2, + JH7110_SYSCLK_I2STX0_LRCK_MST, + JH7110_SYSCLK_I2STX_LRCK_EXT), + /* i2stx1 */ + JH71X0_GATE(JH7110_SYSCLK_I2STX1_APB, "i2stx1_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_I2STX1_BCLK_MST, "i2stx1_bclk_mst", 0, 32, JH7110_SYSCLK_MCLK), + JH71X0__INV(JH7110_SYSCLK_I2STX1_BCLK_MST_INV, "i2stx1_bclk_mst_inv", + JH7110_SYSCLK_I2STX1_BCLK_MST), + JH71X0_MDIV(JH7110_SYSCLK_I2STX1_LRCK_MST, "i2stx1_lrck_mst", 64, 2, + JH7110_SYSCLK_I2STX1_BCLK_MST_INV, + JH7110_SYSCLK_I2STX1_BCLK_MST), + JH71X0__MUX(JH7110_SYSCLK_I2STX1_BCLK, "i2stx1_bclk", 2, + JH7110_SYSCLK_I2STX1_BCLK_MST, + JH7110_SYSCLK_I2STX_BCLK_EXT), + JH71X0__INV(JH7110_SYSCLK_I2STX1_BCLK_INV, "i2stx1_bclk_inv", JH7110_SYSCLK_I2STX1_BCLK), + JH71X0__MUX(JH7110_SYSCLK_I2STX1_LRCK, "i2stx1_lrck", 2, + JH7110_SYSCLK_I2STX1_LRCK_MST, + JH7110_SYSCLK_I2STX_LRCK_EXT), + /* i2srx */ + JH71X0_GATE(JH7110_SYSCLK_I2SRX_APB, "i2srx_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_I2SRX_BCLK_MST, "i2srx_bclk_mst", 0, 32, JH7110_SYSCLK_MCLK), + JH71X0__INV(JH7110_SYSCLK_I2SRX_BCLK_MST_INV, "i2srx_bclk_mst_inv", + JH7110_SYSCLK_I2SRX_BCLK_MST), + JH71X0_MDIV(JH7110_SYSCLK_I2SRX_LRCK_MST, "i2srx_lrck_mst", 64, 2, + JH7110_SYSCLK_I2SRX_BCLK_MST_INV, + JH7110_SYSCLK_I2SRX_BCLK_MST), + JH71X0__MUX(JH7110_SYSCLK_I2SRX_BCLK, "i2srx_bclk", 2, + JH7110_SYSCLK_I2SRX_BCLK_MST, + JH7110_SYSCLK_I2SRX_BCLK_EXT), + JH71X0__INV(JH7110_SYSCLK_I2SRX_BCLK_INV, "i2srx_bclk_inv", JH7110_SYSCLK_I2SRX_BCLK), + JH71X0__MUX(JH7110_SYSCLK_I2SRX_LRCK, "i2srx_lrck", 2, + JH7110_SYSCLK_I2SRX_LRCK_MST, + JH7110_SYSCLK_I2SRX_LRCK_EXT), + /* pdm */ + JH71X0_GDIV(JH7110_SYSCLK_PDM_DMIC, "pdm_dmic", 0, 64, JH7110_SYSCLK_MCLK), + JH71X0_GATE(JH7110_SYSCLK_PDM_APB, "pdm_apb", 0, JH7110_SYSCLK_APB0), + /* tdm */ + JH71X0_GATE(JH7110_SYSCLK_TDM_AHB, "tdm_ahb", 0, JH7110_SYSCLK_AHB0), + JH71X0_GATE(JH7110_SYSCLK_TDM_APB, "tdm_apb", 0, JH7110_SYSCLK_APB0), + JH71X0_GDIV(JH7110_SYSCLK_TDM_INTERNAL, "tdm_internal", 0, 64, JH7110_SYSCLK_MCLK), + JH71X0__MUX(JH7110_SYSCLK_TDM_TDM, "tdm_tdm", 2, + JH7110_SYSCLK_TDM_INTERNAL, + JH7110_SYSCLK_TDM_EXT), + JH71X0__INV(JH7110_SYSCLK_TDM_TDM_INV, "tdm_tdm_inv", JH7110_SYSCLK_TDM_TDM), + /* jtag */ + JH71X0__DIV(JH7110_SYSCLK_JTAG_CERTIFICATION_TRNG, "jtag_certification_trng", 4, + JH7110_SYSCLK_OSC), +}; + +static struct clk_hw *jh7110_sysclk_get(struct of_phandle_args *clkspec, void *data) +{ + struct jh71x0_clk_priv *priv = data; + unsigned int idx = clkspec->args[0]; + + if (idx < JH7110_SYSCLK_END) + return &priv->reg[idx].hw; + + return ERR_PTR(-EINVAL); +} + +static void jh7110_reset_unregister_adev(void *_adev) +{ + struct auxiliary_device *adev = _adev; + + auxiliary_device_delete(adev); +} + +static void jh7110_reset_adev_release(struct device *dev) +{ + struct auxiliary_device *adev = to_auxiliary_dev(dev); + + auxiliary_device_uninit(adev); +} + +int jh7110_reset_controller_register(struct jh71x0_clk_priv *priv, + const char *adev_name, + u32 adev_id) +{ + struct auxiliary_device *adev; + int ret; + + adev = devm_kzalloc(priv->dev, sizeof(*adev), GFP_KERNEL); + if (!adev) + return -ENOMEM; + + adev->name = adev_name; + adev->dev.parent = priv->dev; + adev->dev.release = jh7110_reset_adev_release; + adev->id = adev_id; + + ret = auxiliary_device_init(adev); + if (ret) + return ret; + + ret = auxiliary_device_add(adev); + if (ret) { + auxiliary_device_uninit(adev); + return ret; + } + + return devm_add_action_or_reset(priv->dev, + jh7110_reset_unregister_adev, adev); +} +EXPORT_SYMBOL_GPL(jh7110_reset_controller_register); + +static int __init jh7110_syscrg_probe(struct platform_device *pdev) +{ + struct jh71x0_clk_priv *priv; + unsigned int idx; + int ret; + + priv = devm_kzalloc(&pdev->dev, + struct_size(priv, reg, JH7110_SYSCLK_END), + GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->rmw_lock); + priv->dev = &pdev->dev; + priv->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + dev_set_drvdata(priv->dev, (void *)(&priv->base)); + + /* + * These PLL clocks are not actually fixed factor clocks and can be + * controlled by the syscon registers of JH7110. They will be dropped + * and registered in the PLL clock driver instead. + */ + /* 24MHz -> 1000.0MHz */ + priv->pll[0] = devm_clk_hw_register_fixed_factor(priv->dev, "pll0_out", + "osc", 0, 125, 3); + if (IS_ERR(priv->pll[0])) + return PTR_ERR(priv->pll[0]); + + /* 24MHz -> 1066.0MHz */ + priv->pll[1] = devm_clk_hw_register_fixed_factor(priv->dev, "pll1_out", + "osc", 0, 533, 12); + if (IS_ERR(priv->pll[1])) + return PTR_ERR(priv->pll[1]); + + /* 24MHz -> 1188.0MHz */ + priv->pll[2] = devm_clk_hw_register_fixed_factor(priv->dev, "pll2_out", + "osc", 0, 99, 2); + if (IS_ERR(priv->pll[2])) + return PTR_ERR(priv->pll[2]); + + for (idx = 0; idx < JH7110_SYSCLK_END; idx++) { + u32 max = jh7110_sysclk_data[idx].max; + struct clk_parent_data parents[4] = {}; + struct clk_init_data init = { + .name = jh7110_sysclk_data[idx].name, + .ops = starfive_jh71x0_clk_ops(max), + .parent_data = parents, + .num_parents = + ((max & JH71X0_CLK_MUX_MASK) >> JH71X0_CLK_MUX_SHIFT) + 1, + .flags = jh7110_sysclk_data[idx].flags, + }; + struct jh71x0_clk *clk = &priv->reg[idx]; + unsigned int i; + + for (i = 0; i < init.num_parents; i++) { + unsigned int pidx = jh7110_sysclk_data[idx].parents[i]; + + if (pidx < JH7110_SYSCLK_END) + parents[i].hw = &priv->reg[pidx].hw; + else if (pidx == JH7110_SYSCLK_OSC) + parents[i].fw_name = "osc"; + else if (pidx == JH7110_SYSCLK_GMAC1_RMII_REFIN) + parents[i].fw_name = "gmac1_rmii_refin"; + else if (pidx == JH7110_SYSCLK_GMAC1_RGMII_RXIN) + parents[i].fw_name = "gmac1_rgmii_rxin"; + else if (pidx == JH7110_SYSCLK_I2STX_BCLK_EXT) + parents[i].fw_name = "i2stx_bclk_ext"; + else if (pidx == JH7110_SYSCLK_I2STX_LRCK_EXT) + parents[i].fw_name = "i2stx_lrck_ext"; + else if (pidx == JH7110_SYSCLK_I2SRX_BCLK_EXT) + parents[i].fw_name = "i2srx_bclk_ext"; + else if (pidx == JH7110_SYSCLK_I2SRX_LRCK_EXT) + parents[i].fw_name = "i2srx_lrck_ext"; + else if (pidx == JH7110_SYSCLK_TDM_EXT) + parents[i].fw_name = "tdm_ext"; + else if (pidx == JH7110_SYSCLK_MCLK_EXT) + parents[i].fw_name = "mclk_ext"; + else + parents[i].hw = priv->pll[pidx - JH7110_SYSCLK_PLL0_OUT]; + } + + clk->hw.init = &init; + clk->idx = idx; + clk->max_div = max & JH71X0_CLK_DIV_MASK; + + ret = devm_clk_hw_register(&pdev->dev, &clk->hw); + if (ret) + return ret; + } + + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_sysclk_get, priv); + if (ret) + return ret; + + return jh7110_reset_controller_register(priv, "rst-sys", 0); +} + +static const struct of_device_id jh7110_syscrg_match[] = { + { .compatible = "starfive,jh7110-syscrg" }, + { /* sentinel */ } +}; + +static struct platform_driver jh7110_syscrg_driver = { + .driver = { + .name = "clk-starfive-jh7110-sys", + .of_match_table = jh7110_syscrg_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver_probe(jh7110_syscrg_driver, jh7110_syscrg_probe); diff --git a/drivers/clk/starfive/clk-starfive-jh7110.h b/drivers/clk/starfive/clk-starfive-jh7110.h new file mode 100644 index 000000000000..f29682b8d400 --- /dev/null +++ b/drivers/clk/starfive/clk-starfive-jh7110.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CLK_STARFIVE_JH7110_H +#define __CLK_STARFIVE_JH7110_H + +#include "clk-starfive-jh71x0.h" + +int jh7110_reset_controller_register(struct jh71x0_clk_priv *priv, + const char *adev_name, + u32 adev_id); + +#endif -- GitLab From b2ab3c94f41f888f9bec6ac6bf75935e2e2e253a Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 1 Apr 2023 19:19:26 +0800 Subject: [PATCH 2094/5631] clk: starfive: Add StarFive JH7110 always-on clock driver Add driver for the StarFive JH7110 always-on clock controller and register an auxiliary device for always-on reset controller which is named as "rst-aon". Tested-by: Tommaso Merciai Reviewed-by: Emil Renner Berthing Signed-off-by: Emil Renner Berthing Co-developed-by: Hal Feng Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/clk/starfive/Kconfig | 11 ++ drivers/clk/starfive/Makefile | 1 + .../clk/starfive/clk-starfive-jh7110-aon.c | 156 ++++++++++++++++++ 3 files changed, 168 insertions(+) create mode 100644 drivers/clk/starfive/clk-starfive-jh7110-aon.c diff --git a/drivers/clk/starfive/Kconfig b/drivers/clk/starfive/Kconfig index 670c5084aeb8..71c1148ee5f6 100644 --- a/drivers/clk/starfive/Kconfig +++ b/drivers/clk/starfive/Kconfig @@ -31,3 +31,14 @@ config CLK_STARFIVE_JH7110_SYS help Say yes here to support the system clock controller on the StarFive JH7110 SoC. + +config CLK_STARFIVE_JH7110_AON + tristate "StarFive JH7110 always-on clock support" + depends on CLK_STARFIVE_JH7110_SYS + select AUXILIARY_BUS + select CLK_STARFIVE_JH71X0 + select RESET_STARFIVE_JH7110 + default m if ARCH_STARFIVE + help + Say yes here to support the always-on clock controller on the + StarFive JH7110 SoC. diff --git a/drivers/clk/starfive/Makefile b/drivers/clk/starfive/Makefile index 5ca4e887fb9c..f3df7d957b1e 100644 --- a/drivers/clk/starfive/Makefile +++ b/drivers/clk/starfive/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_CLK_STARFIVE_JH7100) += clk-starfive-jh7100.o obj-$(CONFIG_CLK_STARFIVE_JH7100_AUDIO) += clk-starfive-jh7100-audio.o obj-$(CONFIG_CLK_STARFIVE_JH7110_SYS) += clk-starfive-jh7110-sys.o +obj-$(CONFIG_CLK_STARFIVE_JH7110_AON) += clk-starfive-jh7110-aon.o diff --git a/drivers/clk/starfive/clk-starfive-jh7110-aon.c b/drivers/clk/starfive/clk-starfive-jh7110-aon.c new file mode 100644 index 000000000000..a2799fe8a234 --- /dev/null +++ b/drivers/clk/starfive/clk-starfive-jh7110-aon.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * StarFive JH7110 Always-On Clock Driver + * + * Copyright (C) 2022 Emil Renner Berthing + * Copyright (C) 2022 StarFive Technology Co., Ltd. + */ + +#include +#include +#include + +#include + +#include "clk-starfive-jh7110.h" + +/* external clocks */ +#define JH7110_AONCLK_OSC (JH7110_AONCLK_END + 0) +#define JH7110_AONCLK_GMAC0_RMII_REFIN (JH7110_AONCLK_END + 1) +#define JH7110_AONCLK_GMAC0_RGMII_RXIN (JH7110_AONCLK_END + 2) +#define JH7110_AONCLK_STG_AXIAHB (JH7110_AONCLK_END + 3) +#define JH7110_AONCLK_APB_BUS (JH7110_AONCLK_END + 4) +#define JH7110_AONCLK_GMAC0_GTXCLK (JH7110_AONCLK_END + 5) +#define JH7110_AONCLK_RTC_OSC (JH7110_AONCLK_END + 6) + +static const struct jh71x0_clk_data jh7110_aonclk_data[] = { + /* source */ + JH71X0__DIV(JH7110_AONCLK_OSC_DIV4, "osc_div4", 4, JH7110_AONCLK_OSC), + JH71X0__MUX(JH7110_AONCLK_APB_FUNC, "apb_func", 2, + JH7110_AONCLK_OSC_DIV4, + JH7110_AONCLK_OSC), + /* gmac0 */ + JH71X0_GATE(JH7110_AONCLK_GMAC0_AHB, "gmac0_ahb", 0, JH7110_AONCLK_STG_AXIAHB), + JH71X0_GATE(JH7110_AONCLK_GMAC0_AXI, "gmac0_axi", 0, JH7110_AONCLK_STG_AXIAHB), + JH71X0__DIV(JH7110_AONCLK_GMAC0_RMII_RTX, "gmac0_rmii_rtx", 30, + JH7110_AONCLK_GMAC0_RMII_REFIN), + JH71X0_GMUX(JH7110_AONCLK_GMAC0_TX, "gmac0_tx", + CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT, 2, + JH7110_AONCLK_GMAC0_GTXCLK, + JH7110_AONCLK_GMAC0_RMII_RTX), + JH71X0__INV(JH7110_AONCLK_GMAC0_TX_INV, "gmac0_tx_inv", JH7110_AONCLK_GMAC0_TX), + JH71X0__MUX(JH7110_AONCLK_GMAC0_RX, "gmac0_rx", 2, + JH7110_AONCLK_GMAC0_RGMII_RXIN, + JH7110_AONCLK_GMAC0_RMII_RTX), + JH71X0__INV(JH7110_AONCLK_GMAC0_RX_INV, "gmac0_rx_inv", JH7110_AONCLK_GMAC0_RX), + /* otpc */ + JH71X0_GATE(JH7110_AONCLK_OTPC_APB, "otpc_apb", 0, JH7110_AONCLK_APB_BUS), + /* rtc */ + JH71X0_GATE(JH7110_AONCLK_RTC_APB, "rtc_apb", 0, JH7110_AONCLK_APB_BUS), + JH71X0__DIV(JH7110_AONCLK_RTC_INTERNAL, "rtc_internal", 1022, JH7110_AONCLK_OSC), + JH71X0__MUX(JH7110_AONCLK_RTC_32K, "rtc_32k", 2, + JH7110_AONCLK_RTC_OSC, + JH7110_AONCLK_RTC_INTERNAL), + JH71X0_GATE(JH7110_AONCLK_RTC_CAL, "rtc_cal", 0, JH7110_AONCLK_OSC), +}; + +static struct clk_hw *jh7110_aonclk_get(struct of_phandle_args *clkspec, void *data) +{ + struct jh71x0_clk_priv *priv = data; + unsigned int idx = clkspec->args[0]; + + if (idx < JH7110_AONCLK_END) + return &priv->reg[idx].hw; + + return ERR_PTR(-EINVAL); +} + +static int jh7110_aoncrg_probe(struct platform_device *pdev) +{ + struct jh71x0_clk_priv *priv; + unsigned int idx; + int ret; + + priv = devm_kzalloc(&pdev->dev, + struct_size(priv, reg, JH7110_AONCLK_END), + GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->rmw_lock); + priv->dev = &pdev->dev; + priv->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + dev_set_drvdata(priv->dev, (void *)(&priv->base)); + + for (idx = 0; idx < JH7110_AONCLK_END; idx++) { + u32 max = jh7110_aonclk_data[idx].max; + struct clk_parent_data parents[4] = {}; + struct clk_init_data init = { + .name = jh7110_aonclk_data[idx].name, + .ops = starfive_jh71x0_clk_ops(max), + .parent_data = parents, + .num_parents = + ((max & JH71X0_CLK_MUX_MASK) >> JH71X0_CLK_MUX_SHIFT) + 1, + .flags = jh7110_aonclk_data[idx].flags, + }; + struct jh71x0_clk *clk = &priv->reg[idx]; + unsigned int i; + + for (i = 0; i < init.num_parents; i++) { + unsigned int pidx = jh7110_aonclk_data[idx].parents[i]; + + if (pidx < JH7110_AONCLK_END) + parents[i].hw = &priv->reg[pidx].hw; + else if (pidx == JH7110_AONCLK_OSC) + parents[i].fw_name = "osc"; + else if (pidx == JH7110_AONCLK_GMAC0_RMII_REFIN) + parents[i].fw_name = "gmac0_rmii_refin"; + else if (pidx == JH7110_AONCLK_GMAC0_RGMII_RXIN) + parents[i].fw_name = "gmac0_rgmii_rxin"; + else if (pidx == JH7110_AONCLK_STG_AXIAHB) + parents[i].fw_name = "stg_axiahb"; + else if (pidx == JH7110_AONCLK_APB_BUS) + parents[i].fw_name = "apb_bus"; + else if (pidx == JH7110_AONCLK_GMAC0_GTXCLK) + parents[i].fw_name = "gmac0_gtxclk"; + else if (pidx == JH7110_AONCLK_RTC_OSC) + parents[i].fw_name = "rtc_osc"; + } + + clk->hw.init = &init; + clk->idx = idx; + clk->max_div = max & JH71X0_CLK_DIV_MASK; + + ret = devm_clk_hw_register(&pdev->dev, &clk->hw); + if (ret) + return ret; + } + + ret = devm_of_clk_add_hw_provider(&pdev->dev, jh7110_aonclk_get, priv); + if (ret) + return ret; + + return jh7110_reset_controller_register(priv, "rst-aon", 1); +} + +static const struct of_device_id jh7110_aoncrg_match[] = { + { .compatible = "starfive,jh7110-aoncrg" }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, jh7110_aoncrg_match); + +static struct platform_driver jh7110_aoncrg_driver = { + .probe = jh7110_aoncrg_probe, + .driver = { + .name = "clk-starfive-jh7110-aon", + .of_match_table = jh7110_aoncrg_match, + }, +}; +module_platform_driver(jh7110_aoncrg_driver); + +MODULE_AUTHOR("Emil Renner Berthing"); +MODULE_DESCRIPTION("StarFive JH7110 always-on clock driver"); +MODULE_LICENSE("GPL"); -- GitLab From 82327b127d4117e5b867cca945f97a5074aef786 Mon Sep 17 00:00:00 2001 From: Hal Feng Date: Sat, 1 Apr 2023 19:19:27 +0800 Subject: [PATCH 2095/5631] reset: starfive: Add StarFive JH7110 reset driver Add auxiliary driver to support StarFive JH7110 system and always-on resets. Tested-by: Tommaso Merciai Reviewed-by: Emil Renner Berthing Signed-off-by: Hal Feng Signed-off-by: Conor Dooley --- drivers/reset/starfive/Kconfig | 8 +++ drivers/reset/starfive/Makefile | 1 + .../reset/starfive/reset-starfive-jh7110.c | 70 +++++++++++++++++++ 3 files changed, 79 insertions(+) create mode 100644 drivers/reset/starfive/reset-starfive-jh7110.c diff --git a/drivers/reset/starfive/Kconfig b/drivers/reset/starfive/Kconfig index 1927a5a3b53a..1fa706a2c3dc 100644 --- a/drivers/reset/starfive/Kconfig +++ b/drivers/reset/starfive/Kconfig @@ -10,3 +10,11 @@ config RESET_STARFIVE_JH7100 default ARCH_STARFIVE help This enables the reset controller driver for the StarFive JH7100 SoC. + +config RESET_STARFIVE_JH7110 + bool "StarFive JH7110 Reset Driver" + depends on AUXILIARY_BUS && CLK_STARFIVE_JH7110_SYS + select RESET_STARFIVE_JH71X0 + default ARCH_STARFIVE + help + This enables the reset controller driver for the StarFive JH7110 SoC. diff --git a/drivers/reset/starfive/Makefile b/drivers/reset/starfive/Makefile index f6aa12466fad..7a44b66fb9d5 100644 --- a/drivers/reset/starfive/Makefile +++ b/drivers/reset/starfive/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_RESET_STARFIVE_JH71X0) += reset-starfive-jh71x0.o obj-$(CONFIG_RESET_STARFIVE_JH7100) += reset-starfive-jh7100.o +obj-$(CONFIG_RESET_STARFIVE_JH7110) += reset-starfive-jh7110.o diff --git a/drivers/reset/starfive/reset-starfive-jh7110.c b/drivers/reset/starfive/reset-starfive-jh7110.c new file mode 100644 index 000000000000..c1b3a490d951 --- /dev/null +++ b/drivers/reset/starfive/reset-starfive-jh7110.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Reset driver for the StarFive JH7110 SoC + * + * Copyright (C) 2022 StarFive Technology Co., Ltd. + */ + +#include + +#include "reset-starfive-jh71x0.h" + +#include + +struct jh7110_reset_info { + unsigned int nr_resets; + unsigned int assert_offset; + unsigned int status_offset; +}; + +static const struct jh7110_reset_info jh7110_sys_info = { + .nr_resets = JH7110_SYSRST_END, + .assert_offset = 0x2F8, + .status_offset = 0x308, +}; + +static const struct jh7110_reset_info jh7110_aon_info = { + .nr_resets = JH7110_AONRST_END, + .assert_offset = 0x38, + .status_offset = 0x3C, +}; + +static int jh7110_reset_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct jh7110_reset_info *info = (struct jh7110_reset_info *)(id->driver_data); + void __iomem **base = (void __iomem **)dev_get_drvdata(adev->dev.parent); + + if (!info || !base) + return -ENODEV; + + return reset_starfive_jh71x0_register(&adev->dev, adev->dev.parent->of_node, + *base + info->assert_offset, + *base + info->status_offset, + NULL, + info->nr_resets, + NULL); +} + +static const struct auxiliary_device_id jh7110_reset_ids[] = { + { + .name = "clk_starfive_jh7110_sys.rst-sys", + .driver_data = (kernel_ulong_t)&jh7110_sys_info, + }, + { + .name = "clk_starfive_jh7110_sys.rst-aon", + .driver_data = (kernel_ulong_t)&jh7110_aon_info, + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(auxiliary, jh7110_reset_ids); + +static struct auxiliary_driver jh7110_reset_driver = { + .probe = jh7110_reset_probe, + .id_table = jh7110_reset_ids, +}; +module_auxiliary_driver(jh7110_reset_driver); + +MODULE_AUTHOR("Hal Feng "); +MODULE_DESCRIPTION("StarFive JH7110 reset driver"); +MODULE_LICENSE("GPL"); -- GitLab From 63a30e1f44d5e3afbb47efe8a15fd86feeb62b4b Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sun, 2 Apr 2023 19:40:43 +0100 Subject: [PATCH 2096/5631] MAINTAINERS: generalise StarFive clk/reset entries Update the MAINTAINERS entry for StarFive's clock and reset drivers to account for the addition of JH7110 support and Hal's role in that. Signed-off-by: Emil Renner Berthing Signed-off-by: Hal Feng Reviewed-by: Emil Renner Berthing [conor: split this out from the binding patch, since it touches more than the binding; resort the entries per Hal's request] Signed-off-by: Conor Dooley --- MAINTAINERS | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index ec57c42ed544..0a701632b0b5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19907,19 +19907,20 @@ M: Emil Renner Berthing S: Maintained F: arch/riscv/boot/dts/starfive/ -STARFIVE JH7100 CLOCK DRIVERS -M: Emil Renner Berthing -S: Maintained -F: Documentation/devicetree/bindings/clock/starfive,jh7100-*.yaml -F: drivers/clk/starfive/clk-starfive-jh7100* -F: include/dt-bindings/clock/starfive-jh7100*.h - STARFIVE JH7110 MMC/SD/SDIO DRIVER M: William Qiu S: Supported F: Documentation/devicetree/bindings/mmc/starfive* F: drivers/mmc/host/dw_mmc-starfive.c +STARFIVE JH71X0 CLOCK DRIVERS +M: Emil Renner Berthing +M: Hal Feng +S: Maintained +F: Documentation/devicetree/bindings/clock/starfive,jh71*.yaml +F: drivers/clk/starfive/clk-starfive-jh71* +F: include/dt-bindings/clock/starfive?jh71*.h + STARFIVE JH71X0 PINCTRL DRIVERS M: Emil Renner Berthing M: Jianlong Huang @@ -19930,12 +19931,13 @@ F: drivers/pinctrl/starfive/pinctrl-starfive-jh71* F: include/dt-bindings/pinctrl/pinctrl-starfive-jh7100.h F: include/dt-bindings/pinctrl/starfive,jh7110-pinctrl.h -STARFIVE JH7100 RESET CONTROLLER DRIVER +STARFIVE JH71X0 RESET CONTROLLER DRIVERS M: Emil Renner Berthing +M: Hal Feng S: Maintained F: Documentation/devicetree/bindings/reset/starfive,jh7100-reset.yaml -F: drivers/reset/reset-starfive-jh7100.c -F: include/dt-bindings/reset/starfive-jh7100.h +F: drivers/reset/starfive/reset-starfive-jh71* +F: include/dt-bindings/reset/starfive?jh71*.h STARFIVE JH71XX PMU CONTROLLER DRIVER M: Walker Chen -- GitLab From c1087c29e96a48e9080377e168d35dcb52fb068b Mon Sep 17 00:00:00 2001 From: "H. Nikolaus Schaller" Date: Sun, 2 Apr 2023 13:12:59 +0200 Subject: [PATCH 2097/5631] leds: tca6507: Fix error handling of using fwnode_property_read_string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 96f524105b9c ("leds: tca6507: use fwnode API instead of OF") changed to fwnode API but did not take into account that a missing property "linux,default-trigger" now seems to return an error and as a side effect sets value to -1. This seems to be different from of_get_property() which always returned NULL in any case of error. Neglecting this side-effect leads to [ 11.201965] Unable to handle kernel paging request at virtual address ffffffff when read in the strcmp() of led_trigger_set_default() if there is no led-trigger defined in the DTS. I don't know if this was recently introduced somewhere in the fwnode lib or if the effect was missed in initial testing. Anyways it seems to be a bug to ignore the error return value of an optional value here in the driver. Fixes: 96f524105b9c ("leds: tca6507: use fwnode API instead of OF") Signed-off-by: H. Nikolaus Schaller Acked-by: Pavel Machek Reviewed-by: Marek Behún Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/cbae7617db83113de726fcc423a805ebaa1bfca6.1680433978.git.hns@goldelico.com --- drivers/leds/leds-tca6507.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c index 07dd12686a69..634cabd5bb79 100644 --- a/drivers/leds/leds-tca6507.c +++ b/drivers/leds/leds-tca6507.c @@ -691,8 +691,9 @@ tca6507_led_dt_init(struct device *dev) if (fwnode_property_read_string(child, "label", &led.name)) led.name = fwnode_get_name(child); - fwnode_property_read_string(child, "linux,default-trigger", - &led.default_trigger); + if (fwnode_property_read_string(child, "linux,default-trigger", + &led.default_trigger)) + led.default_trigger = NULL; led.flags = 0; if (fwnode_device_is_compatible(child, "gpio")) -- GitLab From a9042796f9d00643856c31bd3f216305cc5d9dfa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:00 +0200 Subject: [PATCH 2098/5631] usb: musb: da8xx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-2-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/da8xx.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c index d47e5c94587b..912e32b78ac6 100644 --- a/drivers/usb/musb/da8xx.c +++ b/drivers/usb/musb/da8xx.c @@ -576,14 +576,12 @@ static int da8xx_probe(struct platform_device *pdev) return ret; } -static int da8xx_remove(struct platform_device *pdev) +static void da8xx_remove(struct platform_device *pdev) { struct da8xx_glue *glue = platform_get_drvdata(pdev); platform_device_unregister(glue->musb); usb_phy_generic_unregister(glue->usb_phy); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -626,7 +624,7 @@ MODULE_DEVICE_TABLE(of, da8xx_id_table); static struct platform_driver da8xx_driver = { .probe = da8xx_probe, - .remove = da8xx_remove, + .remove_new = da8xx_remove, .driver = { .name = "musb-da8xx", .pm = &da8xx_pm_ops, -- GitLab From c5477ce3bc3d137c553180eaccf88f4b85fa70fc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:01 +0200 Subject: [PATCH 2099/5631] usb: musb: jz4740: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Paul Cercueil Link: https://lore.kernel.org/r/20230405141009.3400693-3-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/jz4740.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c index c7b1d2a394d9..5aabdd7e2511 100644 --- a/drivers/usb/musb/jz4740.c +++ b/drivers/usb/musb/jz4740.c @@ -308,14 +308,12 @@ static int jz4740_probe(struct platform_device *pdev) return ret; } -static int jz4740_remove(struct platform_device *pdev) +static void jz4740_remove(struct platform_device *pdev) { struct jz4740_glue *glue = platform_get_drvdata(pdev); platform_device_unregister(glue->pdev); clk_disable_unprepare(glue->clk); - - return 0; } static const struct of_device_id jz4740_musb_of_match[] = { @@ -327,7 +325,7 @@ MODULE_DEVICE_TABLE(of, jz4740_musb_of_match); static struct platform_driver jz4740_driver = { .probe = jz4740_probe, - .remove = jz4740_remove, + .remove_new = jz4740_remove, .driver = { .name = "musb-jz4740", .of_match_table = jz4740_musb_of_match, -- GitLab From ace4e2637c016d0e693a15760df9f4add1bcbe9c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:02 +0200 Subject: [PATCH 2100/5631] usb: musb: mediatek: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-4-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/mediatek.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/mediatek.c b/drivers/usb/musb/mediatek.c index 27b9bd258340..598ee5c0bf34 100644 --- a/drivers/usb/musb/mediatek.c +++ b/drivers/usb/musb/mediatek.c @@ -508,15 +508,13 @@ static int mtk_musb_probe(struct platform_device *pdev) return ret; } -static int mtk_musb_remove(struct platform_device *pdev) +static void mtk_musb_remove(struct platform_device *pdev) { struct mtk_glue *glue = platform_get_drvdata(pdev); struct platform_device *usb_phy = glue->usb_phy; platform_device_unregister(glue->musb_pdev); usb_phy_generic_unregister(usb_phy); - - return 0; } #ifdef CONFIG_OF @@ -529,7 +527,7 @@ MODULE_DEVICE_TABLE(of, mtk_musb_match); static struct platform_driver mtk_musb_driver = { .probe = mtk_musb_probe, - .remove = mtk_musb_remove, + .remove_new = mtk_musb_remove, .driver = { .name = "musb-mtk", .of_match_table = of_match_ptr(mtk_musb_match), -- GitLab From 37e7750091ad5f3911a8266564e89394c6ac94a1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:03 +0200 Subject: [PATCH 2101/5631] usb: musb: mpfs: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230405141009.3400693-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/mpfs.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/mpfs.c b/drivers/usb/musb/mpfs.c index cea2e8108867..24b98716f7fc 100644 --- a/drivers/usb/musb/mpfs.c +++ b/drivers/usb/musb/mpfs.c @@ -235,15 +235,13 @@ static int mpfs_probe(struct platform_device *pdev) return ret; } -static int mpfs_remove(struct platform_device *pdev) +static void mpfs_remove(struct platform_device *pdev) { struct mpfs_glue *glue = platform_get_drvdata(pdev); clk_disable_unprepare(glue->clk); platform_device_unregister(glue->musb); usb_phy_generic_unregister(pdev); - - return 0; } #ifdef CONFIG_OF @@ -256,7 +254,7 @@ MODULE_DEVICE_TABLE(of, mpfs_id_table); static struct platform_driver mpfs_musb_driver = { .probe = mpfs_probe, - .remove = mpfs_remove, + .remove_new = mpfs_remove, .driver = { .name = "mpfs-musb", .of_match_table = of_match_ptr(mpfs_id_table) -- GitLab From aa846a29e1cc733e6c966bde918bdd1d3a5c5e8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:04 +0200 Subject: [PATCH 2102/5631] usb: musb: musb_core: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_core.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 648bb6021c5e..d162afbbe19f 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2621,7 +2621,7 @@ static int musb_probe(struct platform_device *pdev) return musb_init_controller(dev, irq, base); } -static int musb_remove(struct platform_device *pdev) +static void musb_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct musb *musb = dev_to_musb(dev); @@ -2657,7 +2657,6 @@ static int musb_remove(struct platform_device *pdev) usb_phy_shutdown(musb->xceiv); musb_free(musb); device_init_wakeup(dev, 0); - return 0; } #ifdef CONFIG_PM @@ -2955,7 +2954,7 @@ static struct platform_driver musb_driver = { .dev_groups = musb_groups, }, .probe = musb_probe, - .remove = musb_remove, + .remove_new = musb_remove, }; module_platform_driver(musb_driver); -- GitLab From e6547b5e5c2c493bbd3b6add3177e8498ff0e063 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:05 +0200 Subject: [PATCH 2103/5631] usb: musb: musb_dsps: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-7-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_dsps.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index f75cde0f2b43..9119b1d51370 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -915,7 +915,7 @@ static int dsps_probe(struct platform_device *pdev) return ret; } -static int dsps_remove(struct platform_device *pdev) +static void dsps_remove(struct platform_device *pdev) { struct dsps_glue *glue = platform_get_drvdata(pdev); @@ -923,8 +923,6 @@ static int dsps_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); iounmap(glue->usbss_base); - - return 0; } static const struct dsps_musb_wrapper am33xx_driver_data = { @@ -1036,7 +1034,7 @@ static SIMPLE_DEV_PM_OPS(dsps_pm_ops, dsps_suspend, dsps_resume); static struct platform_driver dsps_usbss_driver = { .probe = dsps_probe, - .remove = dsps_remove, + .remove_new = dsps_remove, .driver = { .name = "musb-dsps", .pm = &dsps_pm_ops, -- GitLab From cb020bf52253327fe382e10bcae02a4f1da33c04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:06 +0200 Subject: [PATCH 2104/5631] usb: musb: omap2430: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-8-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/omap2430.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 7f305b352591..b4a4c1df4e0d 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -471,14 +471,12 @@ static int omap2430_probe(struct platform_device *pdev) return ret; } -static int omap2430_remove(struct platform_device *pdev) +static void omap2430_remove(struct platform_device *pdev) { struct omap2430_glue *glue = platform_get_drvdata(pdev); platform_device_unregister(glue->musb); pm_runtime_disable(glue->dev); - - return 0; } #ifdef CONFIG_PM @@ -610,7 +608,7 @@ MODULE_DEVICE_TABLE(of, omap2430_id_table); static struct platform_driver omap2430_driver = { .probe = omap2430_probe, - .remove = omap2430_remove, + .remove_new = omap2430_remove, .driver = { .name = "musb-omap2430", .pm = DEV_PM_OPS, -- GitLab From 2a21aceed2fe94816d596969a761f6829954d879 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:07 +0200 Subject: [PATCH 2105/5631] usb: musb: sunxi: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Acked-by: Jernej Skrabec Link: https://lore.kernel.org/r/20230405141009.3400693-9-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/sunxi.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/sunxi.c b/drivers/usb/musb/sunxi.c index 9b622cd9b2bd..c5c6c4e09300 100644 --- a/drivers/usb/musb/sunxi.c +++ b/drivers/usb/musb/sunxi.c @@ -805,15 +805,13 @@ static int sunxi_musb_probe(struct platform_device *pdev) return ret; } -static int sunxi_musb_remove(struct platform_device *pdev) +static void sunxi_musb_remove(struct platform_device *pdev) { struct sunxi_glue *glue = platform_get_drvdata(pdev); struct platform_device *usb_phy = glue->usb_phy; platform_device_unregister(glue->musb_pdev); usb_phy_generic_unregister(usb_phy); - - return 0; } static const struct sunxi_musb_cfg sun4i_a10_musb_cfg = { @@ -862,7 +860,7 @@ MODULE_DEVICE_TABLE(of, sunxi_musb_match); static struct platform_driver sunxi_musb_driver = { .probe = sunxi_musb_probe, - .remove = sunxi_musb_remove, + .remove_new = sunxi_musb_remove, .driver = { .name = "musb-sunxi", .of_match_table = sunxi_musb_match, -- GitLab From 969c9528ad05763f468a60b7287486afa62deb23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:08 +0200 Subject: [PATCH 2106/5631] usb: musb: tusb6010: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-10-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/tusb6010.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c index 5609b4e84d40..a1f29dbc62e6 100644 --- a/drivers/usb/musb/tusb6010.c +++ b/drivers/usb/musb/tusb6010.c @@ -1258,19 +1258,17 @@ static int tusb_probe(struct platform_device *pdev) return 0; } -static int tusb_remove(struct platform_device *pdev) +static void tusb_remove(struct platform_device *pdev) { struct tusb6010_glue *glue = platform_get_drvdata(pdev); platform_device_unregister(glue->musb); usb_phy_generic_unregister(glue->phy); - - return 0; } static struct platform_driver tusb_driver = { .probe = tusb_probe, - .remove = tusb_remove, + .remove_new = tusb_remove, .driver = { .name = "musb-tusb", }, -- GitLab From 8000540218439e06ee1161b039a1472718798646 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 5 Apr 2023 16:10:09 +0200 Subject: [PATCH 2107/5631] usb: musb: ux500: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230405141009.3400693-11-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/ux500.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c index 8ea62c344328..c8d9d2a1d2f0 100644 --- a/drivers/usb/musb/ux500.c +++ b/drivers/usb/musb/ux500.c @@ -303,14 +303,12 @@ static int ux500_probe(struct platform_device *pdev) return ret; } -static int ux500_remove(struct platform_device *pdev) +static void ux500_remove(struct platform_device *pdev) { struct ux500_glue *glue = platform_get_drvdata(pdev); platform_device_unregister(glue->musb); clk_disable_unprepare(glue->clk); - - return 0; } #ifdef CONFIG_PM_SLEEP @@ -357,7 +355,7 @@ MODULE_DEVICE_TABLE(of, ux500_match); static struct platform_driver ux500_driver = { .probe = ux500_probe, - .remove = ux500_remove, + .remove_new = ux500_remove, .driver = { .name = "musb-ux500", .pm = &ux500_pm_ops, -- GitLab From d56de8c9a17d8f5202d0f37dd06ce186cc512586 Mon Sep 17 00:00:00 2001 From: Li Jun Date: Tue, 28 Mar 2023 16:23:04 +0800 Subject: [PATCH 2108/5631] usb: typec: tcpm: try to get role switch from tcpc fwnode Try to get usb role switch from tcpc fwnode if failed to get role switch from port dev, this is for case the port for role switch endpoint is located in connector node, as per connector binding doc, port@0 for HS is required. ptn5110: tcpc@50 { compatible = "nxp,ptn5110"; ... status = "okay"; connector { compatible = "usb-c-connector"; label = "USB-C"; ... ports { #address-cells = <1>; #size-cells = <0>; port@0 { reg = <0>; typec_conn: endpoint { remote-endpoint = <&usb2_controller>; }; }; }; }; }; Signed-off-by: Li Jun Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/1679991784-25500-1-git-send-email-jun.li@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index ab3a54662ed9..4e276d2f15d1 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -6577,6 +6577,8 @@ struct tcpm_port *tcpm_register_port(struct device *dev, struct tcpc_dev *tcpc) port->port_type = port->typec_caps.type; port->role_sw = usb_role_switch_get(port->dev); + if (!port->role_sw) + port->role_sw = fwnode_usb_role_switch_get(tcpc->fwnode); if (IS_ERR(port->role_sw)) { err = PTR_ERR(port->role_sw); goto out_destroy_wq; -- GitLab From be15c65ad027f467c856ae9d2cbabaa62680506a Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 30 Mar 2023 17:17:36 +0800 Subject: [PATCH 2109/5631] dt-bindings: usb: typec-tcpci: convert to DT schema format Convert the binding to DT schema format, and rename it to nxp,ptn5110.yaml Signed-off-by: Peng Fan Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230330091736.1873121-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/nxp,ptn5110.yaml | 72 +++++++++++++++++++ .../devicetree/bindings/usb/typec-tcpci.txt | 49 ------------- 2 files changed, 72 insertions(+), 49 deletions(-) create mode 100644 Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml delete mode 100644 Documentation/devicetree/bindings/usb/typec-tcpci.txt diff --git a/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml new file mode 100644 index 000000000000..28eb25ecba74 --- /dev/null +++ b/Documentation/devicetree/bindings/usb/nxp,ptn5110.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/usb/nxp,ptn5110.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP PTN5110 Typec Port Cotroller + +maintainers: + - Li Jun + +properties: + compatible: + const: nxp,ptn5110 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + connector: + type: object + $ref: /schemas/connector/usb-connector.yaml# + unevaluatedProperties: false + +required: + - compatible + - reg + - interrupts + - connector + +additionalProperties: false + +examples: + - | + #include + #include + i2c { + #address-cells = <1>; + #size-cells = <0>; + + tcpci@50 { + compatible = "nxp,ptn5110"; + reg = <0x50>; + interrupt-parent = <&gpio3>; + interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + + usb_con: connector { + compatible = "usb-c-connector"; + label = "USB-C"; + data-role = "dual"; + power-role = "dual"; + try-power-role = "sink"; + source-pdos = ; + sink-pdos = ; + op-sink-microwatt = <10000000>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + typec1_dr_sw: endpoint { + remote-endpoint = <&usb1_drd_sw>; + }; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/usb/typec-tcpci.txt b/Documentation/devicetree/bindings/usb/typec-tcpci.txt deleted file mode 100644 index 2082522b1c32..000000000000 --- a/Documentation/devicetree/bindings/usb/typec-tcpci.txt +++ /dev/null @@ -1,49 +0,0 @@ -TCPCI(Typec port cotroller interface) binding ---------------------------------------------- - -Required properties: -- compatible: should be set one of following: - - "nxp,ptn5110" for NXP USB PD TCPC PHY IC ptn5110. - -- reg: the i2c slave address of typec port controller device. -- interrupt-parent: the phandle to the interrupt controller which provides - the interrupt. -- interrupts: interrupt specification for tcpci alert. - -Required sub-node: -- connector: The "usb-c-connector" attached to the tcpci chip, the bindings - of connector node are specified in - Documentation/devicetree/bindings/connector/usb-connector.yaml - -Example: - -ptn5110@50 { - compatible = "nxp,ptn5110"; - reg = <0x50>; - interrupt-parent = <&gpio3>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; - - usb_con: connector { - compatible = "usb-c-connector"; - label = "USB-C"; - data-role = "dual"; - power-role = "dual"; - try-power-role = "sink"; - source-pdos = ; - sink-pdos = ; - op-sink-microwatt = <10000000>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@1 { - reg = <1>; - usb_con_ss: endpoint { - remote-endpoint = <&usb3_data_ss>; - }; - }; - }; - }; -}; -- GitLab From 03f009a9d41f902e4e9e2dd618b35b712e4b67df Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 24 Mar 2023 15:37:41 +0200 Subject: [PATCH 2110/5631] dt-bindings: usb: tps6598x: make interrupts optional The driver can poll for interrupt status so interrupts can be optional. It is still recommended to use the interrupt line. Polling should only be used for debug and prototyping. Signed-off-by: Roger Quadros Acked-by: Heikki Krogerus Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230324133741.43408-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/ti,tps6598x.yaml | 2 -- 1 file changed, 2 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml index 7d9c5e786e42..39f8d8a5780a 100644 --- a/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml +++ b/Documentation/devicetree/bindings/usb/ti,tps6598x.yaml @@ -35,8 +35,6 @@ properties: required: - compatible - reg - - interrupts - - interrupt-names additionalProperties: true -- GitLab From 917dc99b659114a4aad2ee8b20bcdc05c80e5f09 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 5 Apr 2023 14:20:01 +0300 Subject: [PATCH 2111/5631] usb: dwc3: pci: Change PCI device macros Use PCI_DEVICE_DATA() macro. No functional changes are expected. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230405112001.39695-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-pci.c | 132 ++++++++++-------------------------- 1 file changed, 34 insertions(+), 98 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index a23ddbb81979..a97a6d346665 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -387,104 +387,40 @@ static void dwc3_pci_remove(struct pci_dev *pci) } static const struct pci_device_id dwc3_pci_id_table[] = { - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BSW), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BYT), - (kernel_ulong_t) &dwc3_pci_intel_byt_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), - (kernel_ulong_t) &dwc3_pci_intel_mrfld_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SPTLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SPTH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BXT), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BXT_M), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_APL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_KBP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_GLK), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CNPLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CNPH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CNPV), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICLLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_EHL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGPLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGPH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_JSP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADL_PCH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLN), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLN_PCH), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLM), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTLP), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MTL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, - - { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_NL_USB), - (kernel_ulong_t) &dwc3_pci_amd_swnode, }, - - { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_MR), - (kernel_ulong_t)&dwc3_pci_amd_mr_swnode, }, + { PCI_DEVICE_DATA(INTEL, BSW, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, BYT, &dwc3_pci_intel_byt_swnode) }, + { PCI_DEVICE_DATA(INTEL, MRFLD, &dwc3_pci_intel_mrfld_swnode) }, + { PCI_DEVICE_DATA(INTEL, CMLLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, CMLH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, SPTLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, SPTH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, BXT, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, BXT_M, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, APL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, KBP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, GLK, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, CNPLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, CNPH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, CNPV, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ICLLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, EHL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, TGPLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, TGPH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, JSP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ADL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ADL_PCH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ADLN, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ADLN_PCH, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, ADLS, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, RPL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, RPLS, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, MTLM, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, MTLP, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, MTL, &dwc3_pci_intel_swnode) }, + { PCI_DEVICE_DATA(INTEL, TGL, &dwc3_pci_intel_swnode) }, + + { PCI_DEVICE_DATA(AMD, NL_USB, &dwc3_pci_amd_swnode) }, + { PCI_DEVICE_DATA(AMD, MR, &dwc3_pci_amd_mr_swnode) }, { } /* Terminating Entry */ }; -- GitLab From 326e1c208f3f24d14b93f910b8ae32c94923d22c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Samuel=20=C4=8Cavoj?= Date: Wed, 5 Apr 2023 16:44:56 +0300 Subject: [PATCH 2112/5631] usb: typec: ucsi: acpi: add quirk for ASUS Zenbook UM325 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On some ACPI platforms (namely the ASUS Zenbook UM325) the _DSM method must not be called after a notification is received but instead the mailbox should be read immediately from RAM. This is because the ACPI interrupt handler destroys the CCI in ERAM after copying to system memory, and when _DSM is later called to perform a second copy, it retrieves a garbage value. Instead, the _DSM(read) method should only be called when necessary, i.e. for polling the state after reset and for retrieving the version. Other reads should not call _DSM and only peek into the RAM region. This adds a separate read operation for the Zenbook that syncs the ACPI mailbox only with polled commands. Link: https://lore.kernel.org/linux-usb/20210823180626.tb6m7h5tp6adhvt2@fastboi.localdomain/ Signed-off-by: Samuel Čavoj [ heikki : handling everything in ucsi_acpi.c with DMI quirk ] Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230405134456.49607-1-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/ucsi_acpi.c | 44 ++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c index 62206a6b8ea7..217355f1f9b9 100644 --- a/drivers/usb/typec/ucsi/ucsi_acpi.c +++ b/drivers/usb/typec/ucsi/ucsi_acpi.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "ucsi.h" @@ -23,6 +24,7 @@ struct ucsi_acpi { struct completion complete; unsigned long flags; guid_t guid; + u64 cmd; }; static int ucsi_acpi_dsm(struct ucsi_acpi *ua, int func) @@ -62,6 +64,7 @@ static int ucsi_acpi_async_write(struct ucsi *ucsi, unsigned int offset, struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); memcpy(ua->base + offset, val, val_len); + ua->cmd = *(u64 *)val; return ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_WRITE); } @@ -93,13 +96,46 @@ static const struct ucsi_operations ucsi_acpi_ops = { .async_write = ucsi_acpi_async_write }; +static int +ucsi_zenbook_read(struct ucsi *ucsi, unsigned int offset, void *val, size_t val_len) +{ + struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi); + int ret; + + if (offset == UCSI_VERSION || UCSI_COMMAND(ua->cmd) == UCSI_PPM_RESET) { + ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ); + if (ret) + return ret; + } + + memcpy(val, ua->base + offset, val_len); + + return 0; +} + +static const struct ucsi_operations ucsi_zenbook_ops = { + .read = ucsi_zenbook_read, + .sync_write = ucsi_acpi_sync_write, + .async_write = ucsi_acpi_async_write +}; + +static const struct dmi_system_id zenbook_dmi_id[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ZenBook UX325UA_UM325UA"), + }, + }, + { } +}; + static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) { struct ucsi_acpi *ua = data; u32 cci; int ret; - ret = ucsi_acpi_read(ua->ucsi, UCSI_CCI, &cci, sizeof(cci)); + ret = ua->ucsi->ops->read(ua->ucsi, UCSI_CCI, &cci, sizeof(cci)); if (ret) return; @@ -114,6 +150,7 @@ static void ucsi_acpi_notify(acpi_handle handle, u32 event, void *data) static int ucsi_acpi_probe(struct platform_device *pdev) { struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); + const struct ucsi_operations *ops = &ucsi_acpi_ops; struct ucsi_acpi *ua; struct resource *res; acpi_status status; @@ -143,7 +180,10 @@ static int ucsi_acpi_probe(struct platform_device *pdev) init_completion(&ua->complete); ua->dev = &pdev->dev; - ua->ucsi = ucsi_create(&pdev->dev, &ucsi_acpi_ops); + if (dmi_check_system(zenbook_dmi_id)) + ops = &ucsi_zenbook_ops; + + ua->ucsi = ucsi_create(&pdev->dev, ops); if (IS_ERR(ua->ucsi)) return PTR_ERR(ua->ucsi); -- GitLab From c336fae2c5be3689a7a74562458a23afb88b655e Mon Sep 17 00:00:00 2001 From: Thomas Ballasi Date: Thu, 30 Mar 2023 18:16:37 -0400 Subject: [PATCH 2113/5631] usb: chipidea: imx: avoid unnecessary probe defer The changes brought by commit 73de93440186 have been inadvertidly removed, causing ci_hdrc_imx's probe to be loaded before usbmisc_imx's, despite ci_hdrc_imx needing usbmisc_imx. This condition may cause unexpected behaviors, especially when the ChipIdea node is being referred to under /sys/class/udc/: $ ls -l /sys/class/udc/ $ when it should show as the following: $ ls -l /sys/class/udc/ ci_hdrc.0 -> ../../devices/[...]/ci_hdrc.0/udc/ci_hdrc.0 Some userspace tools may depend on this feature[1]. [1]: https://github.com/nxp-imx/imx-uuc/blob/69029e71b0642ded83a6c9bfa03102bb310c88ed/linuxrc#L148 Fixes: 95caa2ae70fd ("usb: chipidea: allow disabling glue drivers if EMBEDDED") Signed-off-by: Thomas Ballasi Link: https://lore.kernel.org/r/20230330221637.1605161-1-thomas.ballasi@savoirfairelinux.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile index 6f4a3deced35..71afeab97e83 100644 --- a/drivers/usb/chipidea/Makefile +++ b/drivers/usb/chipidea/Makefile @@ -14,5 +14,5 @@ ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o obj-$(CONFIG_USB_CHIPIDEA_GENERIC) += ci_hdrc_usb2.o obj-$(CONFIG_USB_CHIPIDEA_MSM) += ci_hdrc_msm.o obj-$(CONFIG_USB_CHIPIDEA_PCI) += ci_hdrc_pci.o -obj-$(CONFIG_USB_CHIPIDEA_IMX) += ci_hdrc_imx.o usbmisc_imx.o +obj-$(CONFIG_USB_CHIPIDEA_IMX) += usbmisc_imx.o ci_hdrc_imx.o obj-$(CONFIG_USB_CHIPIDEA_TEGRA) += ci_hdrc_tegra.o -- GitLab From 72958d337859626c8538fcd3a5f905825820b72e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 3 Apr 2023 21:18:48 +0200 Subject: [PATCH 2114/5631] dt-bindings: usb: mediatek,mtk-xhci: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230403191850.374839-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/mediatek,mtk-xhci.yaml | 8 -------- 1 file changed, 8 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml index 556bedb96165..72639c6b4e1c 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml @@ -87,14 +87,6 @@ properties: - const: dma_ck - const: xhci_ck - assigned-clocks: - minItems: 1 - maxItems: 5 - - assigned-clock-parents: - minItems: 1 - maxItems: 5 - phys: description: List of all PHYs used on this HCD, it's better to keep PHYs in order -- GitLab From d024ebb274573baaf999914ba33a361141b66bef Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 3 Apr 2023 21:18:49 +0200 Subject: [PATCH 2115/5631] dt-bindings: usb: ti,j721e-usb: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230403191850.374839-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml | 6 ------ 1 file changed, 6 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml index fd36dd02fe74..95ff9791baea 100644 --- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml +++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml @@ -53,12 +53,6 @@ properties: VBUS pin of the SoC via a 1/3 voltage divider. type: boolean - assigned-clocks: - maxItems: 1 - - assigned-clock-parents: - maxItems: 1 - '#address-cells': const: 2 -- GitLab From 0246b15bbb43404d8d6f0ec86121c05515e0ed0b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 3 Apr 2023 21:18:50 +0200 Subject: [PATCH 2116/5631] dt-bindings: usb: ti,keystone-dwc3: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230403191850.374839-3-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/usb/ti,keystone-dwc3.yaml | 8 -------- 1 file changed, 8 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml b/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml index c1f0194ad0d5..9252d893f694 100644 --- a/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml @@ -34,14 +34,6 @@ properties: minItems: 1 maxItems: 2 - assigned-clocks: - minItems: 1 - maxItems: 2 - - assigned-clock-parents: - minItems: 1 - maxItems: 2 - power-domains: maxItems: 1 description: Should contain a phandle to a PM domain provider node -- GitLab From 86c276b91c4a4faea90e8399b1aba580e9df1cb5 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Tue, 28 Mar 2023 13:43:55 +0800 Subject: [PATCH 2117/5631] dt-bindings: serial: fsl-lpuart: add optional power-domains property Add optional power-domains property for i.MX8 usage. Signed-off-by: Peng Fan Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230328054355.1973397-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/fsl-lpuart.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/serial/fsl-lpuart.yaml b/Documentation/devicetree/bindings/serial/fsl-lpuart.yaml index ab81722293d3..93062403276b 100644 --- a/Documentation/devicetree/bindings/serial/fsl-lpuart.yaml +++ b/Documentation/devicetree/bindings/serial/fsl-lpuart.yaml @@ -65,6 +65,9 @@ properties: - const: rx - const: tx + power-domains: + maxItems: 1 + required: - compatible - reg -- GitLab From b2ea273a477cd6e83daedbfa1981cd1a7468f73a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Hanno=20B=C3=B6ck?= Date: Thu, 30 Mar 2023 21:35:57 +0200 Subject: [PATCH 2118/5631] tty: Fix typo in LEGACY_TIOCSTI Kconfig description MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix typo in LEGACY_TIOCSTI Kconfig description There is a stray ' in the description before the Y. It appears this was meant as a quote for the 'Y'. However, it is more common to use unquoted Y in Kconfig descriptions. Signed-off-by: Hanno Böck Link: https://lore.kernel.org/r/20230330213557.60cf1533.hanno@hboeck.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig index d35fc068da74..84caac32f0fd 100644 --- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -160,7 +160,7 @@ config LEGACY_TIOCSTI a dangerous legacy operation, and can be disabled on most systems. - Say 'Y here only if you have confirmed that your system's + Say Y here only if you have confirmed that your system's userspace depends on this functionality to continue operating normally. -- GitLab From ae13381da5ff0e8e084c0323c3cc0a945e43e9c7 Mon Sep 17 00:00:00 2001 From: "Dae R. Jeong" Date: Mon, 27 Mar 2023 21:01:53 +0900 Subject: [PATCH 2119/5631] vmci_host: fix a race condition in vmci_host_poll() causing GPF During fuzzing, a general protection fault is observed in vmci_host_poll(). general protection fault, probably for non-canonical address 0xdffffc0000000019: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x00000000000000c8-0x00000000000000cf] RIP: 0010:__lock_acquire+0xf3/0x5e00 kernel/locking/lockdep.c:4926 <- omitting registers -> Call Trace: lock_acquire+0x1a4/0x4a0 kernel/locking/lockdep.c:5672 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline] _raw_spin_lock_irqsave+0xb3/0x100 kernel/locking/spinlock.c:162 add_wait_queue+0x3d/0x260 kernel/sched/wait.c:22 poll_wait include/linux/poll.h:49 [inline] vmci_host_poll+0xf8/0x2b0 drivers/misc/vmw_vmci/vmci_host.c:174 vfs_poll include/linux/poll.h:88 [inline] do_pollfd fs/select.c:873 [inline] do_poll fs/select.c:921 [inline] do_sys_poll+0xc7c/0x1aa0 fs/select.c:1015 __do_sys_ppoll fs/select.c:1121 [inline] __se_sys_ppoll+0x2cc/0x330 fs/select.c:1101 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x4e/0xa0 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Example thread interleaving that causes the general protection fault is as follows: CPU1 (vmci_host_poll) CPU2 (vmci_host_do_init_context) ----- ----- // Read uninitialized context context = vmci_host_dev->context; // Initialize context vmci_host_dev->context = vmci_ctx_create(); vmci_host_dev->ct_type = VMCIOBJ_CONTEXT; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { // Dereferencing the wrong pointer poll_wait(..., &context->host_context); } In this scenario, vmci_host_poll() reads vmci_host_dev->context first, and then reads vmci_host_dev->ct_type to check that vmci_host_dev->context is initialized. However, since these two reads are not atomically executed, there is a chance of a race condition as described above. To fix this race condition, read vmci_host_dev->context after checking the value of vmci_host_dev->ct_type so that vmci_host_poll() always reads an initialized context. Reported-by: Dae R. Jeong Fixes: 8bf503991f87 ("VMCI: host side driver implementation.") Signed-off-by: Dae R. Jeong Link: https://lore.kernel.org/r/ZCGFsdBAU4cYww5l@dragonet Signed-off-by: Greg Kroah-Hartman --- drivers/misc/vmw_vmci/vmci_host.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c index 857b9851402a..abe79f6fd2a7 100644 --- a/drivers/misc/vmw_vmci/vmci_host.c +++ b/drivers/misc/vmw_vmci/vmci_host.c @@ -165,10 +165,16 @@ static int vmci_host_close(struct inode *inode, struct file *filp) static __poll_t vmci_host_poll(struct file *filp, poll_table *wait) { struct vmci_host_dev *vmci_host_dev = filp->private_data; - struct vmci_ctx *context = vmci_host_dev->context; + struct vmci_ctx *context; __poll_t mask = 0; if (vmci_host_dev->ct_type == VMCIOBJ_CONTEXT) { + /* + * Read context only if ct_type == VMCIOBJ_CONTEXT to make + * sure that context is initialized + */ + context = vmci_host_dev->context; + /* Check for VMCI calls to this VM context. */ if (wait) poll_wait(filp, &context->host_context.wait_queue, -- GitLab From b19a4266c52de78496fe40f0b37580a3b762e67d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:09 +0100 Subject: [PATCH 2120/5631] of: Fix modalias string generation The helper generating an OF based modalias (of_device_get_modalias()) works fine, but due to the use of snprintf() internally it needs a buffer one byte longer than what should be needed just for the entire string (excluding the '\0'). Most users of this helper are sysfs hooks providing the modalias string to users. They all provide a PAGE_SIZE buffer which is way above the number of bytes required to fit the modalias string and hence do not suffer from this issue. There is another user though, of_device_request_module(), which is only called by drivers/usb/common/ulpi.c. This request module function is faulty, but maybe because in most cases there is an alternative, ULPI driver users have not noticed it. In this function, of_device_get_modalias() is called twice. The first time without buffer just to get the number of bytes required by the modalias string (excluding the null byte), and a second time, after buffer allocation, to fill the buffer. The allocation asks for an additional byte, in order to store the trailing '\0'. However, the buffer *length* provided to of_device_get_modalias() excludes this extra byte. The internal use of snprintf() with a length that is exactly the number of bytes to be written has the effect of using the last available byte to store a '\0', which then smashes the last character of the modalias string. Provide the actual size of the buffer to of_device_get_modalias() to fix this issue. Note: the "str[size - 1] = '\0';" line is not really needed as snprintf will anyway end the string with a null byte, but there is a possibility that this function might be called on a struct device_node without compatible, in this case snprintf() would not be executed. So we keep it just to avoid possible unbounded strings. Cc: Stephen Boyd Cc: Peter Chen Fixes: 9c829c097f2f ("of: device: Support loading a module with OF based modalias") Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-2-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/device.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 955bfb3d1a83..c91bb5899256 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -297,12 +297,15 @@ int of_device_request_module(struct device *dev) if (size < 0) return size; - str = kmalloc(size + 1, GFP_KERNEL); + /* Reserve an additional byte for the trailing '\0' */ + size++; + + str = kmalloc(size, GFP_KERNEL); if (!str) return -ENOMEM; of_device_get_modalias(dev, str, size); - str[size] = '\0'; + str[size - 1] = '\0'; ret = request_module(str); kfree(str); -- GitLab From 1ca28dc907b3725940fe88bfd91bc3a53081e2d3 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 18:21:10 +0100 Subject: [PATCH 2121/5631] dt-bindings: nvmem: qcom,spmi-sdam: fix example 'reg' property The SPMI PMIC register region width is fixed and should not be encoded in the devicetree. Amend the example with a parent pmic node with the expected '#address-cells' and '#size-cells' and fix up the 'reg' property. Fixes: 9664a6b54c57 ("dt-bindings: nvmem: add binding for QTI SPMI SDAM") Signed-off-by: Johan Hovold Reviewed-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-3-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../bindings/nvmem/qcom,spmi-sdam.yaml | 31 +++++++++++-------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml b/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml index e08504ef3b6e..4702f10ecca2 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml @@ -42,17 +42,22 @@ unevaluatedProperties: false examples: - | - sdam_1: nvram@b000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "qcom,spmi-sdam"; - reg = <0xb000 0x100>; - ranges = <0 0xb000 0x100>; - - /* Data cells */ - restart_reason: restart@50 { - reg = <0x50 0x1>; - bits = <6 2>; - }; - }; + pmic { + #address-cells = <1>; + #size-cells = <0>; + + sdam_1: nvram@b000 { + compatible = "qcom,spmi-sdam"; + reg = <0xb000>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0xb000 0x100>; + + /* Data cells */ + restart_reason: restart@50 { + reg = <0x50 0x1>; + bits = <6 2>; + }; + }; + }; ... -- GitLab From bcd1fe07def0f070eb5f31594620aaee6f81d31a Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 4 Apr 2023 18:21:11 +0100 Subject: [PATCH 2122/5631] nvmem: xilinx: zynqmp: make modular This driver has a MODULE_LICENSE but is not tristate so cannot be built as a module, unlike all its peers: make it modular to match. Signed-off-by: Nick Alcock Suggested-by: Michal Simek Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Srinivas Kandagatla Cc: Michal Simek Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-4-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index 6dec38805041..3b3832f4dfad 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -368,7 +368,7 @@ config NVMEM_VF610_OCOTP be called nvmem-vf610-ocotp. config NVMEM_ZYNQMP - bool "Xilinx ZYNQMP SoC nvmem firmware support" + tristate "Xilinx ZYNQMP SoC nvmem firmware support" depends on ARCH_ZYNQMP help This is a driver to access hardware related data like -- GitLab From 9f4615338a35dd0f882cc385a8f960191ce0cc82 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 4 Apr 2023 18:21:12 +0100 Subject: [PATCH 2123/5631] dt-bindings: nvmem: convert amlogic-meson-mx-efuse.txt to dt-schema Convert the Amlogic Meson6 eFuse bindings to dt-schema. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Neil Armstrong Reviewed-by: Martin Blumenstingl Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-5-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../bindings/nvmem/amlogic,meson6-efuse.yaml | 57 +++++++++++++++++++ .../bindings/nvmem/amlogic-meson-mx-efuse.txt | 22 ------- 2 files changed, 57 insertions(+), 22 deletions(-) create mode 100644 Documentation/devicetree/bindings/nvmem/amlogic,meson6-efuse.yaml delete mode 100644 Documentation/devicetree/bindings/nvmem/amlogic-meson-mx-efuse.txt diff --git a/Documentation/devicetree/bindings/nvmem/amlogic,meson6-efuse.yaml b/Documentation/devicetree/bindings/nvmem/amlogic,meson6-efuse.yaml new file mode 100644 index 000000000000..84b3dfd21e09 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/amlogic,meson6-efuse.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/amlogic,meson6-efuse.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson6 eFuse + +maintainers: + - Neil Armstrong + - Martin Blumenstingl + +allOf: + - $ref: nvmem.yaml# + +properties: + compatible: + enum: + - amlogic,meson6-efuse + - amlogic,meson8-efuse + - amlogic,meson8b-efuse + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: core + +required: + - compatible + - reg + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + efuse: efuse@0 { + compatible = "amlogic,meson6-efuse"; + reg = <0x0 0x2000>; + clocks = <&clk_efuse>; + clock-names = "core"; + #address-cells = <1>; + #size-cells = <1>; + + ethernet_mac_address: mac@1b4 { + reg = <0x1b4 0x6>; + }; + + temperature_calib: calib@1f4 { + reg = <0x1f4 0x4>; + }; + }; diff --git a/Documentation/devicetree/bindings/nvmem/amlogic-meson-mx-efuse.txt b/Documentation/devicetree/bindings/nvmem/amlogic-meson-mx-efuse.txt deleted file mode 100644 index a3c63954a1a4..000000000000 --- a/Documentation/devicetree/bindings/nvmem/amlogic-meson-mx-efuse.txt +++ /dev/null @@ -1,22 +0,0 @@ -Amlogic Meson6/Meson8/Meson8b efuse - -Required Properties: -- compatible: depending on the SoC this should be one of: - - "amlogic,meson6-efuse" - - "amlogic,meson8-efuse" - - "amlogic,meson8b-efuse" -- reg: base address and size of the efuse registers -- clocks: a reference to the efuse core gate clock -- clock-names: must be "core" - -All properties and sub-nodes as well as the consumer bindings -defined in nvmem.txt in this directory are also supported. - - -Example: - efuse: nvmem@0 { - compatible = "amlogic,meson8-efuse"; - reg = <0x0 0x2000>; - clocks = <&clkc CLKID_EFUSE>; - clock-names = "core"; - }; -- GitLab From ce030eb191b7bf4af32fd76f7456d2291e292e2e Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Tue, 4 Apr 2023 18:21:13 +0100 Subject: [PATCH 2124/5631] dt-bindings: nvmem: convert amlogic-efuse.txt to dt-schema Convert the Amlogic Meson GX eFuse bindings to dt-schema. Take in account the used variant with amlogic,meson-gx-efuse. Reviewed-by: Krzysztof Kozlowski Reviewed-by: Martin Blumenstingl Signed-off-by: Neil Armstrong Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-6-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../nvmem/amlogic,meson-gxbb-efuse.yaml | 57 +++++++++++++++++++ .../bindings/nvmem/amlogic-efuse.txt | 48 ---------------- 2 files changed, 57 insertions(+), 48 deletions(-) create mode 100644 Documentation/devicetree/bindings/nvmem/amlogic,meson-gxbb-efuse.yaml delete mode 100644 Documentation/devicetree/bindings/nvmem/amlogic-efuse.txt diff --git a/Documentation/devicetree/bindings/nvmem/amlogic,meson-gxbb-efuse.yaml b/Documentation/devicetree/bindings/nvmem/amlogic,meson-gxbb-efuse.yaml new file mode 100644 index 000000000000..e49c2754ff55 --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/amlogic,meson-gxbb-efuse.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/nvmem/amlogic,meson-gxbb-efuse.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic Meson GX eFuse + +maintainers: + - Neil Armstrong + +allOf: + - $ref: nvmem.yaml# + +properties: + compatible: + oneOf: + - const: amlogic,meson-gxbb-efuse + - items: + - const: amlogic,meson-gx-efuse + - const: amlogic,meson-gxbb-efuse + + clocks: + maxItems: 1 + + secure-monitor: + description: phandle to the secure-monitor node + $ref: /schemas/types.yaml#/definitions/phandle + +required: + - compatible + - clocks + - secure-monitor + +unevaluatedProperties: false + +examples: + - | + efuse: efuse { + compatible = "amlogic,meson-gxbb-efuse"; + clocks = <&clk_efuse>; + #address-cells = <1>; + #size-cells = <1>; + secure-monitor = <&sm>; + + sn: sn@14 { + reg = <0x14 0x10>; + }; + + eth_mac: mac@34 { + reg = <0x34 0x10>; + }; + + bid: bid@46 { + reg = <0x46 0x30>; + }; + }; diff --git a/Documentation/devicetree/bindings/nvmem/amlogic-efuse.txt b/Documentation/devicetree/bindings/nvmem/amlogic-efuse.txt deleted file mode 100644 index f7b3ed74db54..000000000000 --- a/Documentation/devicetree/bindings/nvmem/amlogic-efuse.txt +++ /dev/null @@ -1,48 +0,0 @@ -= Amlogic Meson GX eFuse device tree bindings = - -Required properties: -- compatible: should be "amlogic,meson-gxbb-efuse" -- clocks: phandle to the efuse peripheral clock provided by the - clock controller. -- secure-monitor: phandle to the secure-monitor node - -= Data cells = -Are child nodes of eFuse, bindings of which as described in -bindings/nvmem/nvmem.txt - -Example: - - efuse: efuse { - compatible = "amlogic,meson-gxbb-efuse"; - clocks = <&clkc CLKID_EFUSE>; - #address-cells = <1>; - #size-cells = <1>; - secure-monitor = <&sm>; - - sn: sn@14 { - reg = <0x14 0x10>; - }; - - eth_mac: eth_mac@34 { - reg = <0x34 0x10>; - }; - - bid: bid@46 { - reg = <0x46 0x30>; - }; - }; - - sm: secure-monitor { - compatible = "amlogic,meson-gxbb-sm"; - }; - -= Data consumers = -Are device nodes which consume nvmem data cells. - -For example: - - eth_mac { - ... - nvmem-cells = <ð_mac>; - nvmem-cell-names = "eth_mac"; - }; -- GitLab From 2187af84e5d0062090f5e0e89281a00d0b8afa40 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 4 Apr 2023 18:21:14 +0100 Subject: [PATCH 2125/5631] dt-bindings: nvmem: Fix spelling mistake "platforn" -> "platform" There is a spelling mistake in platforn-name. Fix it. Signed-off-by: Colin Ian King Signed-off-by: Miquel Raynal Acked-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-7-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml b/Documentation/devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml index 5a0e7671aa3f..714a6538cc7c 100644 --- a/Documentation/devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml +++ b/Documentation/devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml @@ -61,7 +61,7 @@ properties: type: object additionalProperties: false - platforn-name: + platform-name: type: object additionalProperties: false -- GitLab From 5c3d15e127ebfc0754cd18def7124633b6d46672 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:15 +0100 Subject: [PATCH 2126/5631] of: Update of_device_get_modalias() This function only needs a "struct device_node" to work, but for convenience the author (and only user) of this helper did use a "struct device" and put it in device.c. Let's convert this helper to take a "struct device node" instead. This change asks for two additional changes: renaming it "of_modalias()" to fit the current naming, and moving it outside of device.c which will be done in a follow-up commit. Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-8-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/device.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index c91bb5899256..351c505ecb50 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -248,7 +248,7 @@ const void *of_device_get_match_data(const struct device *dev) } EXPORT_SYMBOL(of_device_get_match_data); -static ssize_t of_device_get_modalias(const struct device *dev, char *str, ssize_t len) +static ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) { const char *compat; char *c; @@ -256,19 +256,16 @@ static ssize_t of_device_get_modalias(const struct device *dev, char *str, ssize ssize_t csize; ssize_t tsize; - if ((!dev) || (!dev->of_node) || dev->of_node_reused) - return -ENODEV; - /* Name & Type */ /* %p eats all alphanum characters, so %c must be used here */ - csize = snprintf(str, len, "of:N%pOFn%c%s", dev->of_node, 'T', - of_node_get_device_type(dev->of_node)); + csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', + of_node_get_device_type(np)); tsize = csize; len -= csize; if (str) str += csize; - of_property_for_each_string(dev->of_node, "compatible", p, compat) { + of_property_for_each_string(np, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; if (csize > len) @@ -293,7 +290,10 @@ int of_device_request_module(struct device *dev) ssize_t size; int ret; - size = of_device_get_modalias(dev, NULL, 0); + if (!dev || !dev->of_node) + return -ENODEV; + + size = of_modalias(dev->of_node, NULL, 0); if (size < 0) return size; @@ -304,7 +304,7 @@ int of_device_request_module(struct device *dev) if (!str) return -ENOMEM; - of_device_get_modalias(dev, str, size); + of_modalias(dev->of_node, str, size); str[size - 1] = '\0'; ret = request_module(str); kfree(str); @@ -321,7 +321,12 @@ EXPORT_SYMBOL_GPL(of_device_request_module); */ ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len) { - ssize_t sl = of_device_get_modalias(dev, str, len - 2); + ssize_t sl; + + if (!dev || !dev->of_node || dev->of_node_reused) + return -ENODEV; + + sl = of_modalias(dev->of_node, str, len - 2); if (sl < 0) return sl; if (sl > len - 2) @@ -386,8 +391,8 @@ int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env * if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; - sl = of_device_get_modalias(dev, &env->buf[env->buflen-1], - sizeof(env->buf) - env->buflen); + sl = of_modalias(dev->of_node, &env->buf[env->buflen-1], + sizeof(env->buf) - env->buflen); if (sl < 0) return sl; if (sl >= (sizeof(env->buf) - env->buflen)) -- GitLab From 673aa1ed1c9b6710bf24e3f0957d85e2f46c77db Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:16 +0100 Subject: [PATCH 2127/5631] of: Rename of_modalias_node() This helper does not produce a real modalias, but tries to get the "product" compatible part of the "vendor,product" compatibles only. It is far from creating a purely useful modalias string and does not seem to be used like that directly anyway, so let's try to give this helper a more meaningful name before moving there a real modalias helper (already existing under of/device.c). Also update the various documentations to refer to the strings as "aliases" rather than "modaliases" which has a real meaning in the Linux kernel. There is no functional change. Cc: Rafael J. Wysocki Cc: Len Brown Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: Sebastian Reichel Cc: Wolfram Sang Cc: Mark Brown Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Acked-by: Mark Brown Signed-off-by: Srinivas Kandagatla Acked-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230404172148.82422-9-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/bus.c | 7 ++++--- drivers/gpu/drm/drm_mipi_dsi.c | 2 +- drivers/hsi/hsi_core.c | 2 +- drivers/i2c/busses/i2c-powermac.c | 2 +- drivers/i2c/i2c-core-of.c | 2 +- drivers/of/base.c | 18 +++++++++++------- drivers/spi/spi.c | 4 ++-- include/linux/of.h | 3 ++- 8 files changed, 23 insertions(+), 17 deletions(-) diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 9531dd0fef50..fc74c786a867 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -817,9 +817,10 @@ static bool acpi_of_modalias(struct acpi_device *adev, * @modalias: Pointer to buffer that modalias value will be copied into * @len: Length of modalias buffer * - * This is a counterpart of of_modalias_node() for struct acpi_device objects. - * If there is a compatible string for @adev, it will be copied to @modalias - * with the vendor prefix stripped; otherwise, @default_id will be used. + * This is a counterpart of of_alias_from_compatible() for struct acpi_device + * objects. If there is a compatible string for @adev, it will be copied to + * @modalias with the vendor prefix stripped; otherwise, @default_id will be + * used. */ void acpi_set_modalias(struct acpi_device *adev, const char *default_id, char *modalias, size_t len) diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index b41aaf2bb9f1..b62f5e4425f4 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -160,7 +160,7 @@ of_mipi_dsi_device_add(struct mipi_dsi_host *host, struct device_node *node) int ret; u32 reg; - if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) { + if (of_alias_from_compatible(node, info.type, sizeof(info.type)) < 0) { drm_err(host, "modalias failure on %pOF\n", node); return ERR_PTR(-EINVAL); } diff --git a/drivers/hsi/hsi_core.c b/drivers/hsi/hsi_core.c index 8fda8f1d064d..acbf82f755a8 100644 --- a/drivers/hsi/hsi_core.c +++ b/drivers/hsi/hsi_core.c @@ -207,7 +207,7 @@ static void hsi_add_client_from_dt(struct hsi_port *port, if (!cl) return; - err = of_modalias_node(client, name, sizeof(name)); + err = of_alias_from_compatible(client, name, sizeof(name)); if (err) goto err; diff --git a/drivers/i2c/busses/i2c-powermac.c b/drivers/i2c/busses/i2c-powermac.c index 2e74747eec9c..ec706a3aba26 100644 --- a/drivers/i2c/busses/i2c-powermac.c +++ b/drivers/i2c/busses/i2c-powermac.c @@ -284,7 +284,7 @@ static bool i2c_powermac_get_type(struct i2c_adapter *adap, */ /* First try proper modalias */ - if (of_modalias_node(node, tmp, sizeof(tmp)) >= 0) { + if (of_alias_from_compatible(node, tmp, sizeof(tmp)) >= 0) { snprintf(type, type_size, "MAC,%s", tmp); return true; } diff --git a/drivers/i2c/i2c-core-of.c b/drivers/i2c/i2c-core-of.c index bce6b796e04c..8941a30574e3 100644 --- a/drivers/i2c/i2c-core-of.c +++ b/drivers/i2c/i2c-core-of.c @@ -27,7 +27,7 @@ int of_i2c_get_board_info(struct device *dev, struct device_node *node, memset(info, 0, sizeof(*info)); - if (of_modalias_node(node, info->type, sizeof(info->type)) < 0) { + if (of_alias_from_compatible(node, info->type, sizeof(info->type)) < 0) { dev_err(dev, "of_i2c: modalias failure on %pOF\n", node); return -EINVAL; } diff --git a/drivers/of/base.c b/drivers/of/base.c index ac6fde53342f..161fe3192c46 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1208,19 +1208,23 @@ struct device_node *of_find_matching_node_and_match(struct device_node *from, EXPORT_SYMBOL(of_find_matching_node_and_match); /** - * of_modalias_node - Lookup appropriate modalias for a device node + * of_alias_from_compatible - Lookup appropriate alias for a device node + * depending on compatible * @node: pointer to a device tree node - * @modalias: Pointer to buffer that modalias value will be copied into - * @len: Length of modalias value + * @alias: Pointer to buffer that alias value will be copied into + * @len: Length of alias value * * Based on the value of the compatible property, this routine will attempt - * to choose an appropriate modalias value for a particular device tree node. + * to choose an appropriate alias value for a particular device tree node. * It does this by stripping the manufacturer prefix (as delimited by a ',') * from the first entry in the compatible list property. * + * Note: The matching on just the "product" side of the compatible is a relic + * from I2C and SPI. Please do not add any new user. + * * Return: This routine returns 0 on success, <0 on failure. */ -int of_modalias_node(struct device_node *node, char *modalias, int len) +int of_alias_from_compatible(const struct device_node *node, char *alias, int len) { const char *compatible, *p; int cplen; @@ -1229,10 +1233,10 @@ int of_modalias_node(struct device_node *node, char *modalias, int len) if (!compatible || strlen(compatible) > cplen) return -ENODEV; p = strchr(compatible, ','); - strscpy(modalias, p ? p + 1 : compatible, len); + strscpy(alias, p ? p + 1 : compatible, len); return 0; } -EXPORT_SYMBOL_GPL(of_modalias_node); +EXPORT_SYMBOL_GPL(of_alias_from_compatible); /** * of_find_node_by_phandle - Find a node given a phandle diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 44b85a8d47f1..3bbdc5fe3b99 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2354,8 +2354,8 @@ of_register_spi_device(struct spi_controller *ctlr, struct device_node *nc) } /* Select device driver */ - rc = of_modalias_node(nc, spi->modalias, - sizeof(spi->modalias)); + rc = of_alias_from_compatible(nc, spi->modalias, + sizeof(spi->modalias)); if (rc < 0) { dev_err(&ctlr->dev, "cannot find modalias for %pOF\n", nc); goto err_out; diff --git a/include/linux/of.h b/include/linux/of.h index 0af611307db2..b1eea8569043 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -373,7 +373,8 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); -extern int of_modalias_node(struct device_node *node, char *modalias, int len); +extern int of_alias_from_compatible(const struct device_node *node, char *alias, + int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); extern int __of_parse_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name, int cell_count, -- GitLab From bd7a7ed774afd1a4174df34227626c95573be517 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:17 +0100 Subject: [PATCH 2128/5631] of: Move of_modalias() to module.c Create a specific .c file for OF related module handling. Move of_modalias() inside as a first step. The helper is exposed through of.h even though it is only used by core files because the users from device.c will soon be split into an OF-only helper in module.c as well as a device-oriented inline helper in of_device.h. Putting this helper in of_private.h would require to include of_private.h from of_device.h, which is not acceptable. Suggested-by: Rob Herring Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-10-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/Makefile | 2 +- drivers/of/device.c | 37 ------------------------------------- drivers/of/module.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/of.h | 9 +++++++++ 4 files changed, 54 insertions(+), 38 deletions(-) create mode 100644 drivers/of/module.c diff --git a/drivers/of/Makefile b/drivers/of/Makefile index e0360a44306e..ae9923fd2940 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y = base.o device.o platform.o property.o +obj-y = base.o device.o module.o platform.o property.o obj-$(CONFIG_OF_KOBJ) += kobj.o obj-$(CONFIG_OF_DYNAMIC) += dynamic.o obj-$(CONFIG_OF_FLATTREE) += fdt.o diff --git a/drivers/of/device.c b/drivers/of/device.c index 351c505ecb50..7183cfd754db 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#include #include #include #include @@ -248,42 +247,6 @@ const void *of_device_get_match_data(const struct device *dev) } EXPORT_SYMBOL(of_device_get_match_data); -static ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) -{ - const char *compat; - char *c; - struct property *p; - ssize_t csize; - ssize_t tsize; - - /* Name & Type */ - /* %p eats all alphanum characters, so %c must be used here */ - csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', - of_node_get_device_type(np)); - tsize = csize; - len -= csize; - if (str) - str += csize; - - of_property_for_each_string(np, "compatible", p, compat) { - csize = strlen(compat) + 1; - tsize += csize; - if (csize > len) - continue; - - csize = snprintf(str, len, "C%s", compat); - for (c = str; c; ) { - c = strchr(c, ' '); - if (c) - *c++ = '_'; - } - len -= csize; - str += csize; - } - - return tsize; -} - int of_device_request_module(struct device *dev) { char *str; diff --git a/drivers/of/module.c b/drivers/of/module.c new file mode 100644 index 000000000000..4c59752bc8d6 --- /dev/null +++ b/drivers/of/module.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Linux kernel module helpers. + */ + +#include +#include +#include + +ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) +{ + const char *compat; + char *c; + struct property *p; + ssize_t csize; + ssize_t tsize; + + /* Name & Type */ + /* %p eats all alphanum characters, so %c must be used here */ + csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T', + of_node_get_device_type(np)); + tsize = csize; + len -= csize; + if (str) + str += csize; + + of_property_for_each_string(np, "compatible", p, compat) { + csize = strlen(compat) + 1; + tsize += csize; + if (csize > len) + continue; + + csize = snprintf(str, len, "C%s", compat); + for (c = str; c; ) { + c = strchr(c, ' '); + if (c) + *c++ = '_'; + } + len -= csize; + str += csize; + } + + return tsize; +} diff --git a/include/linux/of.h b/include/linux/of.h index b1eea8569043..be26c7e8ef9e 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -385,6 +385,9 @@ extern int of_parse_phandle_with_args_map(const struct device_node *np, extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); +/* module functions */ +extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); + /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, @@ -742,6 +745,12 @@ static inline int of_count_phandle_with_args(const struct device_node *np, return -ENOSYS; } +static inline ssize_t of_modalias(const struct device_node *np, char *str, + ssize_t len) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, -- GitLab From e6506f06d5e82765666902ccf9e9162f3e31d518 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:18 +0100 Subject: [PATCH 2129/5631] of: Move the request module helper logic to module.c Depending on device.c for pure OF handling is considered backwards. Let's extract the content of of_device_request_module() to have the real logic under module.c. The next step will be to convert users of of_device_request_module() to use the new helper. Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-11-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/device.c | 25 ++----------------------- drivers/of/module.c | 30 ++++++++++++++++++++++++++++++ include/linux/of.h | 6 ++++++ 3 files changed, 38 insertions(+), 23 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 7183cfd754db..874a2e1f6308 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -8,7 +8,6 @@ #include /* for bus_dma_region */ #include #include -#include #include #include #include @@ -249,30 +248,10 @@ EXPORT_SYMBOL(of_device_get_match_data); int of_device_request_module(struct device *dev) { - char *str; - ssize_t size; - int ret; - - if (!dev || !dev->of_node) + if (!dev) return -ENODEV; - size = of_modalias(dev->of_node, NULL, 0); - if (size < 0) - return size; - - /* Reserve an additional byte for the trailing '\0' */ - size++; - - str = kmalloc(size, GFP_KERNEL); - if (!str) - return -ENOMEM; - - of_modalias(dev->of_node, str, size); - str[size - 1] = '\0'; - ret = request_module(str); - kfree(str); - - return ret; + return of_request_module(dev->of_node); } EXPORT_SYMBOL_GPL(of_device_request_module); diff --git a/drivers/of/module.c b/drivers/of/module.c index 4c59752bc8d6..0e8aa974f0f2 100644 --- a/drivers/of/module.c +++ b/drivers/of/module.c @@ -4,6 +4,7 @@ */ #include +#include #include #include @@ -42,3 +43,32 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len) return tsize; } + +int of_request_module(const struct device_node *np) +{ + char *str; + ssize_t size; + int ret; + + if (!np) + return -ENODEV; + + size = of_modalias(np, NULL, 0); + if (size < 0) + return size; + + /* Reserve an additional byte for the trailing '\0' */ + size++; + + str = kmalloc(size, GFP_KERNEL); + if (!str) + return -ENOMEM; + + of_modalias(np, str, size); + str[size - 1] = '\0'; + ret = request_module(str); + kfree(str); + + return ret; +} +EXPORT_SYMBOL_GPL(of_request_module); diff --git a/include/linux/of.h b/include/linux/of.h index be26c7e8ef9e..9b7a99499ef3 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -387,6 +387,7 @@ extern int of_count_phandle_with_args(const struct device_node *np, /* module functions */ extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); +extern int of_request_module(const struct device_node *np); /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, @@ -751,6 +752,11 @@ static inline ssize_t of_modalias(const struct device_node *np, char *str, return -ENODEV; } +static inline int of_request_module(const struct device_node *np) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, -- GitLab From 19697537708643091d64c8ec9a809883166dcb3f Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:19 +0100 Subject: [PATCH 2130/5631] usb: ulpi: Use of_request_module() There is a new helper supposed to replace of_device_request_module(), called of_request_module(). They are both strictly equivalent, besides the fact the latter receives a "struct device_node" directly. Use it. Cc: Heikki Krogerus Cc: Greg Kroah-Hartman Signed-off-by: Miquel Raynal Acked-by: Rob Herring Acked-by: Heikki Krogerus Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-12-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/common/ulpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index a98b2108376a..6977cf380838 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -229,7 +229,7 @@ static int ulpi_read_id(struct ulpi *ulpi) request_module("ulpi:v%04xp%04x", ulpi->id.vendor, ulpi->id.product); return 0; err: - of_device_request_module(&ulpi->dev); + of_request_module(ulpi->dev.of_node); return 0; } -- GitLab From 2f555f58f5ce33b201235e104823662d5573c4a5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:20 +0100 Subject: [PATCH 2131/5631] of: device: Kill of_device_request_module() A new helper has been introduced, of_request_module(). Users have been converted, this helper can now be deleted. Signed-off-by: Miquel Raynal Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-13-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/of/device.c | 9 --------- include/linux/of_device.h | 6 ------ 2 files changed, 15 deletions(-) diff --git a/drivers/of/device.c b/drivers/of/device.c index 874a2e1f6308..0f00f1b80708 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -246,15 +246,6 @@ const void *of_device_get_match_data(const struct device *dev) } EXPORT_SYMBOL(of_device_get_match_data); -int of_device_request_module(struct device *dev) -{ - if (!dev) - return -ENODEV; - - return of_request_module(dev->of_node); -} -EXPORT_SYMBOL_GPL(of_device_request_module); - /** * of_device_modalias - Fill buffer with newline terminated modalias string * @dev: Calling device diff --git a/include/linux/of_device.h b/include/linux/of_device.h index f4b57614979d..ce20d8b00b3e 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -33,7 +33,6 @@ extern void of_device_unregister(struct platform_device *ofdev); extern const void *of_device_get_match_data(const struct device *dev); extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); -extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); @@ -78,11 +77,6 @@ static inline int of_device_modalias(struct device *dev, return -ENODEV; } -static inline int of_device_request_module(struct device *dev) -{ - return -ENODEV; -} - static inline int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { -- GitLab From 266570f496b90dea8fda893c2cf7c28d63ae2bd9 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:21 +0100 Subject: [PATCH 2132/5631] nvmem: core: introduce NVMEM layouts NVMEM layouts are used to generate NVMEM cells during runtime. Think of an EEPROM with a well-defined conent. For now, the content can be described by a device tree or a board file. But this only works if the offsets and lengths are static and don't change. One could also argue that putting the layout of the EEPROM in the device tree is the wrong place. Instead, the device tree should just have a specific compatible string. Right now there are two use cases: (1) The NVMEM cell needs special processing. E.g. if it only specifies a base MAC address offset and you need to add an offset, or it needs to parse a MAC from ASCII format or some proprietary format. (Post processing of cells is added in a later commit). (2) u-boot environment parsing. The cells don't have a particular offset but it needs parsing the content to determine the offsets and length. Co-developed-by: Miquel Raynal Signed-off-by: Miquel Raynal Signed-off-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-14-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/nvmem.rst | 15 ++++ drivers/nvmem/Kconfig | 4 + drivers/nvmem/Makefile | 1 + drivers/nvmem/core.c | 120 +++++++++++++++++++++++++++++ drivers/nvmem/layouts/Kconfig | 5 ++ drivers/nvmem/layouts/Makefile | 4 + include/linux/nvmem-consumer.h | 7 ++ include/linux/nvmem-provider.h | 51 ++++++++++++ 8 files changed, 207 insertions(+) create mode 100644 drivers/nvmem/layouts/Kconfig create mode 100644 drivers/nvmem/layouts/Makefile diff --git a/Documentation/driver-api/nvmem.rst b/Documentation/driver-api/nvmem.rst index e3366322d46c..de221e91c8e3 100644 --- a/Documentation/driver-api/nvmem.rst +++ b/Documentation/driver-api/nvmem.rst @@ -185,3 +185,18 @@ ex:: ===================== See Documentation/devicetree/bindings/nvmem/nvmem.txt + +8. NVMEM layouts +================ + +NVMEM layouts are yet another mechanism to create cells. With the device +tree binding it is possible to specify simple cells by using an offset +and a length. Sometimes, the cells doesn't have a static offset, but +the content is still well defined, e.g. tag-length-values. In this case, +the NVMEM device content has to be first parsed and the cells need to +be added accordingly. Layouts let you read the content of the NVMEM device +and let you add cells dynamically. + +Another use case for layouts is the post processing of cells. With layouts, +it is possible to associate a custom post processing hook to a cell. It +even possible to add this hook to cells not created by the layout itself. diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index 3b3832f4dfad..a2afba11c890 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -21,6 +21,10 @@ config NVMEM_SYSFS This interface is mostly used by userspace applications to read/write directly into nvmem. +# Layouts + +source "drivers/nvmem/layouts/Kconfig" + # Devices config NVMEM_APPLE_EFUSES diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile index 6a1efffa88f0..f82431ec8aef 100644 --- a/drivers/nvmem/Makefile +++ b/drivers/nvmem/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_NVMEM) += nvmem_core.o nvmem_core-y := core.o +obj-y += layouts/ # Devices obj-$(CONFIG_NVMEM_APPLE_EFUSES) += nvmem-apple-efuses.o diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 22024b830788..b9be1faeb7be 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -40,6 +40,7 @@ struct nvmem_device { nvmem_reg_write_t reg_write; nvmem_cell_post_process_t cell_post_process; struct gpio_desc *wp_gpio; + struct nvmem_layout *layout; void *priv; }; @@ -74,6 +75,9 @@ static LIST_HEAD(nvmem_lookup_list); static BLOCKING_NOTIFIER_HEAD(nvmem_notifier); +static DEFINE_SPINLOCK(nvmem_layout_lock); +static LIST_HEAD(nvmem_layouts); + static int __nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset, void *val, size_t bytes) { @@ -728,6 +732,101 @@ static int nvmem_add_cells_from_of(struct nvmem_device *nvmem) return 0; } +int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner) +{ + layout->owner = owner; + + spin_lock(&nvmem_layout_lock); + list_add(&layout->node, &nvmem_layouts); + spin_unlock(&nvmem_layout_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(__nvmem_layout_register); + +void nvmem_layout_unregister(struct nvmem_layout *layout) +{ + spin_lock(&nvmem_layout_lock); + list_del(&layout->node); + spin_unlock(&nvmem_layout_lock); +} +EXPORT_SYMBOL_GPL(nvmem_layout_unregister); + +static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem) +{ + struct device_node *layout_np, *np = nvmem->dev.of_node; + struct nvmem_layout *l, *layout = NULL; + + layout_np = of_get_child_by_name(np, "nvmem-layout"); + if (!layout_np) + return NULL; + + spin_lock(&nvmem_layout_lock); + + list_for_each_entry(l, &nvmem_layouts, node) { + if (of_match_node(l->of_match_table, layout_np)) { + if (try_module_get(l->owner)) + layout = l; + + break; + } + } + + spin_unlock(&nvmem_layout_lock); + of_node_put(layout_np); + + return layout; +} + +static void nvmem_layout_put(struct nvmem_layout *layout) +{ + if (layout) + module_put(layout->owner); +} + +static int nvmem_add_cells_from_layout(struct nvmem_device *nvmem) +{ + struct nvmem_layout *layout = nvmem->layout; + int ret; + + if (layout && layout->add_cells) { + ret = layout->add_cells(&nvmem->dev, nvmem, layout); + if (ret) + return ret; + } + + return 0; +} + +#if IS_ENABLED(CONFIG_OF) +/** + * of_nvmem_layout_get_container() - Get OF node to layout container. + * + * @nvmem: nvmem device. + * + * Return: a node pointer with refcount incremented or NULL if no + * container exists. Use of_node_put() on it when done. + */ +struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem) +{ + return of_get_child_by_name(nvmem->dev.of_node, "nvmem-layout"); +} +EXPORT_SYMBOL_GPL(of_nvmem_layout_get_container); +#endif + +const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + struct device_node __maybe_unused *layout_np; + const struct of_device_id *match; + + layout_np = of_nvmem_layout_get_container(nvmem); + match = of_match_node(layout->of_match_table, layout_np); + + return match ? match->data : NULL; +} +EXPORT_SYMBOL_GPL(nvmem_layout_get_match_data); + /** * nvmem_register() - Register a nvmem device for given nvmem_config. * Also creates a binary entry in /sys/bus/nvmem/devices/dev-name/nvmem @@ -834,6 +933,12 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) goto err_put_device; } + /* + * If the driver supplied a layout by config->layout, the module + * pointer will be NULL and nvmem_layout_put() will be a noop. + */ + nvmem->layout = config->layout ?: nvmem_layout_get(nvmem); + if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) @@ -854,12 +959,17 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + rval = nvmem_add_cells_from_layout(nvmem); + if (rval) + goto err_remove_cells; + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; err_remove_cells: nvmem_device_remove_all_cells(nvmem); + nvmem_layout_put(nvmem->layout); if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); err_put_device: @@ -881,6 +991,7 @@ static void nvmem_device_release(struct kref *kref) device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom); nvmem_device_remove_all_cells(nvmem); + nvmem_layout_put(nvmem->layout); device_unregister(&nvmem->dev); } @@ -1246,6 +1357,15 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) return ERR_PTR(-EINVAL); } + /* nvmem layouts produce cells within the nvmem-layout container */ + if (of_node_name_eq(nvmem_np, "nvmem-layout")) { + nvmem_np = of_get_next_parent(nvmem_np); + if (!nvmem_np) { + of_node_put(cell_np); + return ERR_PTR(-EINVAL); + } + } + nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); if (IS_ERR(nvmem)) { diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig new file mode 100644 index 000000000000..9ad3911d1605 --- /dev/null +++ b/drivers/nvmem/layouts/Kconfig @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Layout Types" + +endmenu diff --git a/drivers/nvmem/layouts/Makefile b/drivers/nvmem/layouts/Makefile new file mode 100644 index 000000000000..6fdb3c60a4fa --- /dev/null +++ b/drivers/nvmem/layouts/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for nvmem layouts. +# diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 1f62f7ba71ca..fa030d93b768 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -239,6 +239,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); +struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) @@ -251,6 +252,12 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct device_node * +of_nvmem_layout_get_container(struct nvmem_device *nvmem) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_NVMEM && CONFIG_OF */ #endif /* ifndef _LINUX_NVMEM_CONSUMER_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0262b86194eb..535c5f9f3309 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -88,6 +88,7 @@ struct nvmem_cell_info { * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. * @ignore_wp: Write Protect pin is managed by the provider. + * @layout: Fixed layout associated with this nvmem device. * * Note: A default "nvmem" name will be assigned to the device if * no name is specified in its configuration. In such case "" is @@ -109,6 +110,7 @@ struct nvmem_config { bool read_only; bool root_only; bool ignore_wp; + struct nvmem_layout *layout; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; @@ -142,6 +144,33 @@ struct nvmem_cell_table { struct list_head node; }; +/** + * struct nvmem_layout - NVMEM layout definitions + * + * @name: Layout name. + * @of_match_table: Open firmware match table. + * @add_cells: Will be called if a nvmem device is found which + * has this layout. The function will add layout + * specific cells with nvmem_add_one_cell(). + * @owner: Pointer to struct module. + * @node: List node. + * + * A nvmem device can hold a well defined structure which can just be + * evaluated during runtime. For example a TLV list, or a list of "name=val" + * pairs. A nvmem layout can parse the nvmem device and add appropriate + * cells. + */ +struct nvmem_layout { + const char *name; + const struct of_device_id *of_match_table; + int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout); + + /* private */ + struct module *owner; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -156,6 +185,14 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); int nvmem_add_one_cell(struct nvmem_device *nvmem, const struct nvmem_cell_info *info); +int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner); +#define nvmem_layout_register(layout) \ + __nvmem_layout_register(layout, THIS_MODULE) +void nvmem_layout_unregister(struct nvmem_layout *layout); + +const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -179,5 +216,19 @@ static inline int nvmem_add_one_cell(struct nvmem_device *nvmem, return -EOPNOTSUPP; } +static inline int nvmem_layout_register(struct nvmem_layout *layout) +{ + return -EOPNOTSUPP; +} + +static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} + +static inline const void * +nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- GitLab From 6468a6f45148fb5e95c86b4efebf63f9abcd2137 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:22 +0100 Subject: [PATCH 2133/5631] nvmem: core: handle the absence of expected layouts Make nvmem_layout_get() return -EPROBE_DEFER while the expected layout is not available. This condition cannot be triggered today as nvmem layout drivers are initialed as part of an early init call, but soon these drivers will be converted into modules and be initialized with a standard priority, so the unavailability of the drivers might become a reality that must be taken care of. Let's anticipate this by telling the caller the layout might not yet be available. A probe deferral is requested in this case. Please note this does not affect any nvmem device not using layouts, because an early check against the "nvmem-layout" container presence will return NULL in this case. Signed-off-by: Miquel Raynal Tested-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-15-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index b9be1faeb7be..51fd792b8d70 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -755,7 +755,7 @@ EXPORT_SYMBOL_GPL(nvmem_layout_unregister); static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem) { struct device_node *layout_np, *np = nvmem->dev.of_node; - struct nvmem_layout *l, *layout = NULL; + struct nvmem_layout *l, *layout = ERR_PTR(-EPROBE_DEFER); layout_np = of_get_child_by_name(np, "nvmem-layout"); if (!layout_np) @@ -938,6 +938,13 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) * pointer will be NULL and nvmem_layout_put() will be a noop. */ nvmem->layout = config->layout ?: nvmem_layout_get(nvmem); + if (IS_ERR(nvmem->layout)) { + rval = PTR_ERR(nvmem->layout); + nvmem->layout = NULL; + + if (rval == -EPROBE_DEFER) + goto err_teardown_compat; + } if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); @@ -970,6 +977,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) err_remove_cells: nvmem_device_remove_all_cells(nvmem); nvmem_layout_put(nvmem->layout); +err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); err_put_device: -- GitLab From b1c37bec1ccfe5ccab72bc0ddc0dfa45c43e2de2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:23 +0100 Subject: [PATCH 2134/5631] nvmem: core: request layout modules loading When a storage device like an eeprom or an mtd device probes, it registers an nvmem device if the nvmem subsystem has been enabled (bool symbol). During nvmem registration, if the device is using layouts to expose dynamic nvmem cells, the core will first try to get a reference over the layout driver callbacks. In practice there is not relationship that can be described between the storage driver and the nvmem layout. So there is no way we can enforce both drivers will be built-in or both will be modules. If the storage device driver is built-in but the layout is built as a module, instead of badly failing with an endless probe deferral loop, lets just make a modprobe call in case the driver was made available in an initramfs with of_device_node_request_module(), and offer a fully functional system to the user. Signed-off-by: Miquel Raynal Tested-by: Michael Walle Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-16-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 51fd792b8d70..49b4bbaf59e8 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -17,6 +17,7 @@ #include #include #include +#include #include struct nvmem_device { @@ -761,6 +762,13 @@ static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem) if (!layout_np) return NULL; + /* + * In case the nvmem device was built-in while the layout was built as a + * module, we shall manually request the layout driver loading otherwise + * we'll never have any match. + */ + of_request_module(layout_np); + spin_lock(&nvmem_layout_lock); list_for_each_entry(l, &nvmem_layouts, node) { -- GitLab From 345ec382cd4b736c36e01f155d08c913b225b736 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:24 +0100 Subject: [PATCH 2135/5631] nvmem: core: add per-cell post processing Instead of relying on the name the consumer is using for the cell, like it is done for the nvmem .cell_post_process configuration parameter, provide a per-cell post processing hook. This can then be populated by the NVMEM provider (or the NVMEM layout) when adding the cell. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-17-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 17 +++++++++++++++++ include/linux/nvmem-provider.h | 3 +++ 2 files changed, 20 insertions(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 49b4bbaf59e8..0708f9f27898 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -54,6 +54,7 @@ struct nvmem_cell_entry { int bytes; int bit_offset; int nbits; + nvmem_cell_post_process_t read_post_process; struct device_node *np; struct nvmem_device *nvmem; struct list_head node; @@ -470,6 +471,7 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem, cell->offset = info->offset; cell->bytes = info->bytes; cell->name = info->name; + cell->read_post_process = info->read_post_process; cell->bit_offset = info->bit_offset; cell->nbits = info->nbits; @@ -1563,6 +1565,13 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, if (cell->bit_offset || cell->nbits) nvmem_shift_read_buffer_in_place(cell, buf); + if (cell->read_post_process) { + rc = cell->read_post_process(nvmem->priv, id, index, + cell->offset, buf, cell->bytes); + if (rc) + return rc; + } + if (nvmem->cell_post_process) { rc = nvmem->cell_post_process(nvmem->priv, id, index, cell->offset, buf, cell->bytes); @@ -1671,6 +1680,14 @@ static int __nvmem_cell_entry_write(struct nvmem_cell_entry *cell, void *buf, si (cell->bit_offset == 0 && len != cell->bytes)) return -EINVAL; + /* + * Any cells which have a read_post_process hook are read-only because + * we cannot reverse the operation and it might affect other cells, + * too. + */ + if (cell->read_post_process) + return -EINVAL; + if (cell->bit_offset || cell->nbits) { buf = nvmem_cell_prepare_write_buffer(cell, buf, len); if (IS_ERR(buf)) diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 535c5f9f3309..3bfc23553a9e 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -54,6 +54,8 @@ struct nvmem_keepout { * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. * @np: Optional device_node pointer. + * @read_post_process: Callback for optional post processing of cell data + * on reads. */ struct nvmem_cell_info { const char *name; @@ -62,6 +64,7 @@ struct nvmem_cell_info { unsigned int bit_offset; unsigned int nbits; struct device_node *np; + nvmem_cell_post_process_t read_post_process; }; /** -- GitLab From de12c9691501ccba41a154c223869f82be4c12fd Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:25 +0100 Subject: [PATCH 2136/5631] nvmem: core: allow to modify a cell before adding it Provide a way to modify a cell before it will get added. This is useful to attach a custom post processing hook via a layout. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-18-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 4 ++++ include/linux/nvmem-provider.h | 5 +++++ 2 files changed, 9 insertions(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 0708f9f27898..f43025ad315b 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -695,6 +695,7 @@ static int nvmem_validate_keepouts(struct nvmem_device *nvmem) static int nvmem_add_cells_from_of(struct nvmem_device *nvmem) { + struct nvmem_layout *layout = nvmem->layout; struct device *dev = &nvmem->dev; struct device_node *child; const __be32 *addr; @@ -724,6 +725,9 @@ static int nvmem_add_cells_from_of(struct nvmem_device *nvmem) info.np = of_node_get(child); + if (layout && layout->fixup_cell_info) + layout->fixup_cell_info(nvmem, layout, &info); + ret = nvmem_add_one_cell(nvmem, &info); kfree(info.name); if (ret) { diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 3bfc23553a9e..be81cc88eabc 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -155,6 +155,8 @@ struct nvmem_cell_table { * @add_cells: Will be called if a nvmem device is found which * has this layout. The function will add layout * specific cells with nvmem_add_one_cell(). + * @fixup_cell_info: Will be called before a cell is added. Can be + * used to modify the nvmem_cell_info. * @owner: Pointer to struct module. * @node: List node. * @@ -168,6 +170,9 @@ struct nvmem_layout { const struct of_device_id *of_match_table; int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, struct nvmem_layout *layout); + void (*fixup_cell_info)(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell); /* private */ struct module *owner; -- GitLab From 6c56a82d7895a213a43182a5d01a21a906a79847 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:26 +0100 Subject: [PATCH 2137/5631] nvmem: imx-ocotp: replace global post processing with layouts In preparation of retiring the global post processing hook change this driver to use layouts. The layout will be supplied during registration and will be used to add the post processing hook to all added cells. Signed-off-by: Michael Walle Tested-by: Michael Walle # on kontron-pitx-imx8m Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-19-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/imx-ocotp.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index e9b52ecb3f72..ac0edb6398f1 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -225,18 +225,13 @@ static int imx_ocotp_read(void *context, unsigned int offset, static int imx_ocotp_cell_pp(void *context, const char *id, int index, unsigned int offset, void *data, size_t bytes) { - struct ocotp_priv *priv = context; + u8 *buf = data; + int i; /* Deal with some post processing of nvmem cell data */ - if (id && !strcmp(id, "mac-address")) { - if (priv->params->reverse_mac_address) { - u8 *buf = data; - int i; - - for (i = 0; i < bytes/2; i++) - swap(buf[i], buf[bytes - i - 1]); - } - } + if (id && !strcmp(id, "mac-address")) + for (i = 0; i < bytes / 2; i++) + swap(buf[i], buf[bytes - i - 1]); return 0; } @@ -488,7 +483,6 @@ static struct nvmem_config imx_ocotp_nvmem_config = { .stride = 1, .reg_read = imx_ocotp_read, .reg_write = imx_ocotp_write, - .cell_post_process = imx_ocotp_cell_pp, }; static const struct ocotp_params imx6q_params = { @@ -595,6 +589,17 @@ static const struct of_device_id imx_ocotp_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids); +static void imx_ocotp_fixup_cell_info(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell) +{ + cell->read_post_process = imx_ocotp_cell_pp; +} + +struct nvmem_layout imx_ocotp_layout = { + .fixup_cell_info = imx_ocotp_fixup_cell_info, +}; + static int imx_ocotp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -619,6 +624,9 @@ static int imx_ocotp_probe(struct platform_device *pdev) imx_ocotp_nvmem_config.size = 4 * priv->params->nregs; imx_ocotp_nvmem_config.dev = dev; imx_ocotp_nvmem_config.priv = priv; + if (priv->params->reverse_mac_address) + imx_ocotp_nvmem_config.layout = &imx_ocotp_layout; + priv->config = &imx_ocotp_nvmem_config; clk_prepare_enable(priv->clk); -- GitLab From 011e40a166fdaa65fb9946b7cd91efec85b70dbb Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:27 +0100 Subject: [PATCH 2138/5631] nvmem: cell: drop global cell_post_process There are no users anymore for the global cell_post_process callback anymore. New users should use proper nvmem layouts. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-20-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 9 --------- include/linux/nvmem-provider.h | 2 -- 2 files changed, 11 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index f43025ad315b..fccb2728193a 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -39,7 +39,6 @@ struct nvmem_device { unsigned int nkeepout; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; - nvmem_cell_post_process_t cell_post_process; struct gpio_desc *wp_gpio; struct nvmem_layout *layout; void *priv; @@ -903,7 +902,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->type = config->type; nvmem->reg_read = config->reg_read; nvmem->reg_write = config->reg_write; - nvmem->cell_post_process = config->cell_post_process; nvmem->keepout = config->keepout; nvmem->nkeepout = config->nkeepout; if (config->of_node) @@ -1576,13 +1574,6 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, return rc; } - if (nvmem->cell_post_process) { - rc = nvmem->cell_post_process(nvmem->priv, id, index, - cell->offset, buf, cell->bytes); - if (rc) - return rc; - } - if (len) *len = cell->bytes; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index be81cc88eabc..d3d7af86a283 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -85,7 +85,6 @@ struct nvmem_cell_info { * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. - * @cell_post_process: Callback for vendor specific post processing of cell data * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. @@ -118,7 +117,6 @@ struct nvmem_config { bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; - nvmem_cell_post_process_t cell_post_process; int size; int word_size; int stride; -- GitLab From 8a134fd9f9323f4c39ec27055b3d3723cfb5c1e9 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:28 +0100 Subject: [PATCH 2139/5631] nvmem: core: provide own priv pointer in post process callback It doesn't make any more sense to have a opaque pointer set up by the nvmem device. Usually, the layout isn't associated with a particular nvmem device. Instead, let the caller who set the post process callback provide the priv pointer. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-21-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 4 +++- include/linux/nvmem-provider.h | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index fccb2728193a..212c5ba5789f 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -54,6 +54,7 @@ struct nvmem_cell_entry { int bit_offset; int nbits; nvmem_cell_post_process_t read_post_process; + void *priv; struct device_node *np; struct nvmem_device *nvmem; struct list_head node; @@ -471,6 +472,7 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem, cell->bytes = info->bytes; cell->name = info->name; cell->read_post_process = info->read_post_process; + cell->priv = info->priv; cell->bit_offset = info->bit_offset; cell->nbits = info->nbits; @@ -1568,7 +1570,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, nvmem_shift_read_buffer_in_place(cell, buf); if (cell->read_post_process) { - rc = cell->read_post_process(nvmem->priv, id, index, + rc = cell->read_post_process(cell->priv, id, index, cell->offset, buf, cell->bytes); if (rc) return rc; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index d3d7af86a283..0cf9f9490514 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -20,7 +20,8 @@ typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); /* used for vendor specific post processing of cell data */ typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, int index, - unsigned int offset, void *buf, size_t bytes); + unsigned int offset, void *buf, + size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, @@ -56,6 +57,7 @@ struct nvmem_keepout { * @np: Optional device_node pointer. * @read_post_process: Callback for optional post processing of cell data * on reads. + * @priv: Opaque data passed to the read_post_process hook. */ struct nvmem_cell_info { const char *name; @@ -65,6 +67,7 @@ struct nvmem_cell_info { unsigned int nbits; struct device_node *np; nvmem_cell_post_process_t read_post_process; + void *priv; }; /** -- GitLab From d9fae023fe86069750092fc1c2f3a73e2fb18512 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:29 +0100 Subject: [PATCH 2140/5631] nvmem: layouts: sl28vpd: Add new layout driver This layout applies to the VPD of the Kontron sl28 boards. The VPD only contains a base MAC address. Therefore, we have to add an individual offset to it. This is done by taking the second argument of the nvmem phandle into account. Also this let us checking the VPD version and the checksum. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-22-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/Kconfig | 9 ++ drivers/nvmem/layouts/Makefile | 2 + drivers/nvmem/layouts/sl28vpd.c | 165 ++++++++++++++++++++++++++++++++ 3 files changed, 176 insertions(+) create mode 100644 drivers/nvmem/layouts/sl28vpd.c diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig index 9ad3911d1605..fd161347c129 100644 --- a/drivers/nvmem/layouts/Kconfig +++ b/drivers/nvmem/layouts/Kconfig @@ -2,4 +2,13 @@ menu "Layout Types" +config NVMEM_LAYOUT_SL28_VPD + tristate "Kontron sl28 VPD layout support" + select CRC8 + help + Say Y here if you want to support the VPD layout of the Kontron + SMARC-sAL28 boards. + + If unsure, say N. + endmenu diff --git a/drivers/nvmem/layouts/Makefile b/drivers/nvmem/layouts/Makefile index 6fdb3c60a4fa..fc617b9e87d0 100644 --- a/drivers/nvmem/layouts/Makefile +++ b/drivers/nvmem/layouts/Makefile @@ -2,3 +2,5 @@ # # Makefile for nvmem layouts. # + +obj-$(CONFIG_NVMEM_LAYOUT_SL28_VPD) += sl28vpd.o diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c new file mode 100644 index 000000000000..9370e41bad73 --- /dev/null +++ b/drivers/nvmem/layouts/sl28vpd.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include + +#define SL28VPD_MAGIC 'V' + +struct sl28vpd_header { + u8 magic; + u8 version; +} __packed; + +struct sl28vpd_v1 { + struct sl28vpd_header header; + char serial_number[15]; + u8 base_mac_address[ETH_ALEN]; + u8 crc8; +} __packed; + +static int sl28vpd_mac_address_pp(void *priv, const char *id, int index, + unsigned int offset, void *buf, + size_t bytes) +{ + if (bytes != ETH_ALEN) + return -EINVAL; + + if (index < 0) + return -EINVAL; + + if (!is_valid_ether_addr(buf)) + return -EINVAL; + + eth_addr_add(buf, index); + + return 0; +} + +static const struct nvmem_cell_info sl28vpd_v1_entries[] = { + { + .name = "serial-number", + .offset = offsetof(struct sl28vpd_v1, serial_number), + .bytes = sizeof_field(struct sl28vpd_v1, serial_number), + }, + { + .name = "base-mac-address", + .offset = offsetof(struct sl28vpd_v1, base_mac_address), + .bytes = sizeof_field(struct sl28vpd_v1, base_mac_address), + .read_post_process = sl28vpd_mac_address_pp, + }, +}; + +static int sl28vpd_v1_check_crc(struct device *dev, struct nvmem_device *nvmem) +{ + struct sl28vpd_v1 data_v1; + u8 table[CRC8_TABLE_SIZE]; + int ret; + u8 crc; + + crc8_populate_msb(table, 0x07); + + ret = nvmem_device_read(nvmem, 0, sizeof(data_v1), &data_v1); + if (ret < 0) + return ret; + else if (ret != sizeof(data_v1)) + return -EIO; + + crc = crc8(table, (void *)&data_v1, sizeof(data_v1) - 1, 0); + + if (crc != data_v1.crc8) { + dev_err(dev, + "Checksum is invalid (got %02x, expected %02x).\n", + crc, data_v1.crc8); + return -EINVAL; + } + + return 0; +} + +static int sl28vpd_add_cells(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + const struct nvmem_cell_info *pinfo; + struct nvmem_cell_info info = {0}; + struct device_node *layout_np; + struct sl28vpd_header hdr; + int ret, i; + + /* check header */ + ret = nvmem_device_read(nvmem, 0, sizeof(hdr), &hdr); + if (ret < 0) + return ret; + else if (ret != sizeof(hdr)) + return -EIO; + + if (hdr.magic != SL28VPD_MAGIC) { + dev_err(dev, "Invalid magic value (%02x)\n", hdr.magic); + return -EINVAL; + } + + if (hdr.version != 1) { + dev_err(dev, "Version %d is unsupported.\n", hdr.version); + return -EINVAL; + } + + ret = sl28vpd_v1_check_crc(dev, nvmem); + if (ret) + return ret; + + layout_np = of_nvmem_layout_get_container(nvmem); + if (!layout_np) + return -ENOENT; + + for (i = 0; i < ARRAY_SIZE(sl28vpd_v1_entries); i++) { + pinfo = &sl28vpd_v1_entries[i]; + + info.name = pinfo->name; + info.offset = pinfo->offset; + info.bytes = pinfo->bytes; + info.read_post_process = pinfo->read_post_process; + info.np = of_get_child_by_name(layout_np, pinfo->name); + + ret = nvmem_add_one_cell(nvmem, &info); + if (ret) { + of_node_put(layout_np); + return ret; + } + } + + of_node_put(layout_np); + + return 0; +} + +static const struct of_device_id sl28vpd_of_match_table[] = { + { .compatible = "kontron,sl28-vpd" }, + {}, +}; +MODULE_DEVICE_TABLE(of, sl28vpd_of_match_table); + +struct nvmem_layout sl28vpd_layout = { + .name = "sl28-vpd", + .of_match_table = sl28vpd_of_match_table, + .add_cells = sl28vpd_add_cells, +}; + +static int __init sl28vpd_init(void) +{ + return nvmem_layout_register(&sl28vpd_layout); +} + +static void __exit sl28vpd_exit(void) +{ + nvmem_layout_unregister(&sl28vpd_layout); +} + +module_init(sl28vpd_init); +module_exit(sl28vpd_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Michael Walle "); +MODULE_DESCRIPTION("NVMEM layout driver for the VPD of Kontron sl28 boards"); -- GitLab From fe191489d66f2bcd7be3cd78645bcefea5a3f68d Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 4 Apr 2023 18:21:30 +0100 Subject: [PATCH 2141/5631] MAINTAINERS: add myself as sl28vpd nvmem layout driver Add myself as a maintainer for the new sl28vpd nvmem layout driver. Signed-off-by: Michael Walle Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-23-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 4d4f778ede5d..a7763063ffa3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19175,6 +19175,12 @@ F: drivers/irqchip/irq-sl28cpld.c F: drivers/pwm/pwm-sl28cpld.c F: drivers/watchdog/sl28cpld_wdt.c +SL28 VPD NVMEM LAYOUT DRIVER +M: Michael Walle +S: Maintained +F: Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml +F: drivers/nvmem/layouts/sl28vpd.c + SLAB ALLOCATOR M: Christoph Lameter M: Pekka Enberg -- GitLab From d3c0d12f6474216bf386101e2449cc73e5c5b61d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:31 +0100 Subject: [PATCH 2142/5631] nvmem: layouts: onie-tlv: Add new layout driver This layout applies on top of any non volatile storage device containing an ONIE table factory flashed. This table follows the tlv (type-length-value) organization described in the link below. We cannot afford using regular parsers because the content of these tables is manufacturer specific and must be dynamically discovered. Link: https://opencomputeproject.github.io/onie/design-spec/hw_requirements.html Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-24-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/Kconfig | 9 ++ drivers/nvmem/layouts/Makefile | 1 + drivers/nvmem/layouts/onie-tlv.c | 257 +++++++++++++++++++++++++++++++ 3 files changed, 267 insertions(+) create mode 100644 drivers/nvmem/layouts/onie-tlv.c diff --git a/drivers/nvmem/layouts/Kconfig b/drivers/nvmem/layouts/Kconfig index fd161347c129..7ff1ee1c1f05 100644 --- a/drivers/nvmem/layouts/Kconfig +++ b/drivers/nvmem/layouts/Kconfig @@ -11,4 +11,13 @@ config NVMEM_LAYOUT_SL28_VPD If unsure, say N. +config NVMEM_LAYOUT_ONIE_TLV + tristate "ONIE tlv support" + select CRC32 + help + Say Y here if you want to support the Open Compute Project ONIE + Type-Length-Value standard table. + + If unsure, say N. + endmenu diff --git a/drivers/nvmem/layouts/Makefile b/drivers/nvmem/layouts/Makefile index fc617b9e87d0..2974bd7d33ed 100644 --- a/drivers/nvmem/layouts/Makefile +++ b/drivers/nvmem/layouts/Makefile @@ -4,3 +4,4 @@ # obj-$(CONFIG_NVMEM_LAYOUT_SL28_VPD) += sl28vpd.o +obj-$(CONFIG_NVMEM_LAYOUT_ONIE_TLV) += onie-tlv.o diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c new file mode 100644 index 000000000000..d45b7301a69d --- /dev/null +++ b/drivers/nvmem/layouts/onie-tlv.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ONIE tlv NVMEM cells provider + * + * Copyright (C) 2022 Open Compute Group ONIE + * Author: Miquel Raynal + * Based on the nvmem driver written by: Vadym Kochan + * Inspired by the first layout written by: Rafał Miłecki + */ + +#include +#include +#include +#include +#include + +#define ONIE_TLV_MAX_LEN 2048 +#define ONIE_TLV_CRC_FIELD_SZ 6 +#define ONIE_TLV_CRC_SZ 4 +#define ONIE_TLV_HDR_ID "TlvInfo" + +struct onie_tlv_hdr { + u8 id[8]; + u8 version; + __be16 data_len; +} __packed; + +struct onie_tlv { + u8 type; + u8 len; +} __packed; + +static const char *onie_tlv_cell_name(u8 type) +{ + switch (type) { + case 0x21: + return "product-name"; + case 0x22: + return "part-number"; + case 0x23: + return "serial-number"; + case 0x24: + return "mac-address"; + case 0x25: + return "manufacture-date"; + case 0x26: + return "device-version"; + case 0x27: + return "label-revision"; + case 0x28: + return "platform-name"; + case 0x29: + return "onie-version"; + case 0x2A: + return "num-macs"; + case 0x2B: + return "manufacturer"; + case 0x2C: + return "country-code"; + case 0x2D: + return "vendor"; + case 0x2E: + return "diag-version"; + case 0x2F: + return "service-tag"; + case 0xFD: + return "vendor-extension"; + case 0xFE: + return "crc32"; + default: + break; + } + + return NULL; +} + +static int onie_tlv_mac_read_cb(void *priv, const char *id, int index, + unsigned int offset, void *buf, + size_t bytes) +{ + eth_addr_add(buf, index); + + return 0; +} + +static nvmem_cell_post_process_t onie_tlv_read_cb(u8 type, u8 *buf) +{ + switch (type) { + case 0x24: + return &onie_tlv_mac_read_cb; + default: + break; + } + + return NULL; +} + +static int onie_tlv_add_cells(struct device *dev, struct nvmem_device *nvmem, + size_t data_len, u8 *data) +{ + struct nvmem_cell_info cell = {}; + struct device_node *layout; + struct onie_tlv tlv; + unsigned int hdr_len = sizeof(struct onie_tlv_hdr); + unsigned int offset = 0; + int ret; + + layout = of_nvmem_layout_get_container(nvmem); + if (!layout) + return -ENOENT; + + while (offset < data_len) { + memcpy(&tlv, data + offset, sizeof(tlv)); + if (offset + tlv.len >= data_len) { + dev_err(dev, "Out of bounds field (0x%x bytes at 0x%x)\n", + tlv.len, hdr_len + offset); + break; + } + + cell.name = onie_tlv_cell_name(tlv.type); + if (!cell.name) + continue; + + cell.offset = hdr_len + offset + sizeof(tlv.type) + sizeof(tlv.len); + cell.bytes = tlv.len; + cell.np = of_get_child_by_name(layout, cell.name); + cell.read_post_process = onie_tlv_read_cb(tlv.type, data + offset + sizeof(tlv)); + + ret = nvmem_add_one_cell(nvmem, &cell); + if (ret) { + of_node_put(layout); + return ret; + } + + offset += sizeof(tlv) + tlv.len; + } + + of_node_put(layout); + + return 0; +} + +static bool onie_tlv_hdr_is_valid(struct device *dev, struct onie_tlv_hdr *hdr) +{ + if (memcmp(hdr->id, ONIE_TLV_HDR_ID, sizeof(hdr->id))) { + dev_err(dev, "Invalid header\n"); + return false; + } + + if (hdr->version != 0x1) { + dev_err(dev, "Invalid version number\n"); + return false; + } + + return true; +} + +static bool onie_tlv_crc_is_valid(struct device *dev, size_t table_len, u8 *table) +{ + struct onie_tlv crc_hdr; + u32 read_crc, calc_crc; + __be32 crc_be; + + memcpy(&crc_hdr, table + table_len - ONIE_TLV_CRC_FIELD_SZ, sizeof(crc_hdr)); + if (crc_hdr.type != 0xfe || crc_hdr.len != ONIE_TLV_CRC_SZ) { + dev_err(dev, "Invalid CRC field\n"); + return false; + } + + /* The table contains a JAMCRC, which is XOR'ed compared to the original + * CRC32 implementation as known in the Ethernet world. + */ + memcpy(&crc_be, table + table_len - ONIE_TLV_CRC_SZ, ONIE_TLV_CRC_SZ); + read_crc = be32_to_cpu(crc_be); + calc_crc = crc32(~0, table, table_len - ONIE_TLV_CRC_SZ) ^ 0xFFFFFFFF; + if (read_crc != calc_crc) { + dev_err(dev, "Invalid CRC read: 0x%08x, expected: 0x%08x\n", + read_crc, calc_crc); + return false; + } + + return true; +} + +static int onie_tlv_parse_table(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + struct onie_tlv_hdr hdr; + size_t table_len, data_len, hdr_len; + u8 *table, *data; + int ret; + + ret = nvmem_device_read(nvmem, 0, sizeof(hdr), &hdr); + if (ret < 0) + return ret; + + if (!onie_tlv_hdr_is_valid(dev, &hdr)) { + dev_err(dev, "Invalid ONIE TLV header\n"); + return -EINVAL; + } + + hdr_len = sizeof(hdr.id) + sizeof(hdr.version) + sizeof(hdr.data_len); + data_len = be16_to_cpu(hdr.data_len); + table_len = hdr_len + data_len; + if (table_len > ONIE_TLV_MAX_LEN) { + dev_err(dev, "Invalid ONIE TLV data length\n"); + return -EINVAL; + } + + table = devm_kmalloc(dev, table_len, GFP_KERNEL); + if (!table) + return -ENOMEM; + + ret = nvmem_device_read(nvmem, 0, table_len, table); + if (ret != table_len) + return ret; + + if (!onie_tlv_crc_is_valid(dev, table_len, table)) + return -EINVAL; + + data = table + hdr_len; + ret = onie_tlv_add_cells(dev, nvmem, data_len, data); + if (ret) + return ret; + + return 0; +} + +static const struct of_device_id onie_tlv_of_match_table[] = { + { .compatible = "onie,tlv-layout", }, + {}, +}; +MODULE_DEVICE_TABLE(of, onie_tlv_of_match_table); + +static struct nvmem_layout onie_tlv_layout = { + .name = "ONIE tlv layout", + .of_match_table = onie_tlv_of_match_table, + .add_cells = onie_tlv_parse_table, +}; + +static int __init onie_tlv_init(void) +{ + return nvmem_layout_register(&onie_tlv_layout); +} + +static void __exit onie_tlv_exit(void) +{ + nvmem_layout_unregister(&onie_tlv_layout); +} + +module_init(onie_tlv_init); +module_exit(onie_tlv_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Miquel Raynal "); +MODULE_DESCRIPTION("NVMEM layout driver for Onie TLV table parsing"); +MODULE_ALIAS("NVMEM layout driver for Onie TLV table parsing"); -- GitLab From f126612181fbd706c7a43d6c7d0758898815ad38 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:32 +0100 Subject: [PATCH 2143/5631] MAINTAINERS: Add myself as ONIE tlv NVMEM layout maintainer Following the introduction of the bindings for this NVMEM parser and the layout driver, add myself as maintainer. Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-25-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index a7763063ffa3..de05ac9b58ca 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15547,6 +15547,12 @@ L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/oxp-sensors.c +ONIE TLV NVMEM LAYOUT DRIVER +M: Miquel Raynal +S: Maintained +F: Documentation/devicetree/bindings/nvmem/layouts/onie,tlv-layout.yaml +F: drivers/nvmem/layouts/onie-tlv.c + ONION OMEGA2+ BOARD M: Harvey Hunt L: linux-mips@vger.kernel.org -- GitLab From d14d9f0e737e0602c17f416c26e56e57df4985b1 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 4 Apr 2023 18:21:33 +0100 Subject: [PATCH 2144/5631] dt-bindings: nvmem: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Acked-by: Jernej Skrabec Reviewed-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-26-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml | 2 +- Documentation/devicetree/bindings/nvmem/apple,efuses.yaml | 2 +- Documentation/devicetree/bindings/nvmem/brcm,nvram.yaml | 2 +- Documentation/devicetree/bindings/nvmem/fsl,layerscape-sfp.yaml | 2 +- Documentation/devicetree/bindings/nvmem/imx-iim.yaml | 2 +- Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml | 2 +- .../devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml | 2 +- Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml | 2 +- .../devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml | 2 +- Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml | 2 +- Documentation/devicetree/bindings/nvmem/nintendo-otp.yaml | 2 +- Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml | 2 +- Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml | 2 +- Documentation/devicetree/bindings/nvmem/rmem.yaml | 2 +- Documentation/devicetree/bindings/nvmem/rockchip-efuse.yaml | 2 +- .../devicetree/bindings/nvmem/socionext,uniphier-efuse.yaml | 2 +- Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml | 2 +- .../devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml | 2 +- 18 files changed, 18 insertions(+), 18 deletions(-) diff --git a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml index 14c170c6a86e..296001e7f498 100644 --- a/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml +++ b/Documentation/devicetree/bindings/nvmem/allwinner,sun4i-a10-sid.yaml @@ -11,7 +11,7 @@ maintainers: - Maxime Ripard allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/apple,efuses.yaml b/Documentation/devicetree/bindings/nvmem/apple,efuses.yaml index 5ec8f2bdb3a5..e0860b6b85f3 100644 --- a/Documentation/devicetree/bindings/nvmem/apple,efuses.yaml +++ b/Documentation/devicetree/bindings/nvmem/apple,efuses.yaml @@ -15,7 +15,7 @@ maintainers: - Sven Peter allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/brcm,nvram.yaml b/Documentation/devicetree/bindings/nvmem/brcm,nvram.yaml index 25033de3ef6b..36def7128fca 100644 --- a/Documentation/devicetree/bindings/nvmem/brcm,nvram.yaml +++ b/Documentation/devicetree/bindings/nvmem/brcm,nvram.yaml @@ -20,7 +20,7 @@ maintainers: - Rafał Miłecki allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/fsl,layerscape-sfp.yaml b/Documentation/devicetree/bindings/nvmem/fsl,layerscape-sfp.yaml index 3b4e6e94cb81..70fb2ad25103 100644 --- a/Documentation/devicetree/bindings/nvmem/fsl,layerscape-sfp.yaml +++ b/Documentation/devicetree/bindings/nvmem/fsl,layerscape-sfp.yaml @@ -14,7 +14,7 @@ description: | unique identifier per part. allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/imx-iim.yaml b/Documentation/devicetree/bindings/nvmem/imx-iim.yaml index 7aac1995cfaf..e9d9d8df4811 100644 --- a/Documentation/devicetree/bindings/nvmem/imx-iim.yaml +++ b/Documentation/devicetree/bindings/nvmem/imx-iim.yaml @@ -14,7 +14,7 @@ description: | i.MX25, i.MX27, i.MX31, i.MX35, i.MX51 and i.MX53 SoCs. allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml index d0a239d7e199..9876243ff1e8 100644 --- a/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/imx-ocotp.yaml @@ -15,7 +15,7 @@ description: | i.MX7D/S, i.MX7ULP, i.MX8MQ, i.MX8MM, i.MX8MN and i.MX8MP SoCs. allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml b/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml index fe2cd7f1afba..e89fd879c968 100644 --- a/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml +++ b/Documentation/devicetree/bindings/nvmem/ingenic,jz4780-efuse.yaml @@ -10,7 +10,7 @@ maintainers: - PrasannaKumar Muralidharan allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml index 75e0a516e59a..d16d42fb98b6 100644 --- a/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml +++ b/Documentation/devicetree/bindings/nvmem/mediatek,efuse.yaml @@ -15,7 +15,7 @@ maintainers: - Lala Lin allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: $nodename: diff --git a/Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml b/Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml index c3c96fd0baac..a296d348adb4 100644 --- a/Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml +++ b/Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml @@ -15,7 +15,7 @@ description: | settings, chip identifiers) or user specific data could be stored. allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml index ff317fd7c15b..8938eec22b52 100644 --- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml @@ -10,7 +10,7 @@ maintainers: - Anson Huang allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/nintendo-otp.yaml b/Documentation/devicetree/bindings/nvmem/nintendo-otp.yaml index f93bc50c40d7..6c26800f8b79 100644 --- a/Documentation/devicetree/bindings/nvmem/nintendo-otp.yaml +++ b/Documentation/devicetree/bindings/nvmem/nintendo-otp.yaml @@ -17,7 +17,7 @@ maintainers: - Emmanuel Gil Peyrot allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index 2173fe82317d..e952907ad1d5 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -10,7 +10,7 @@ maintainers: - Srinivas Kandagatla allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml b/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml index 4702f10ecca2..dce0c7d84ce7 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,spmi-sdam.yaml @@ -15,7 +15,7 @@ description: | to/from the PBUS. allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/rmem.yaml b/Documentation/devicetree/bindings/nvmem/rmem.yaml index a4a755dcfc43..38a39c9b8c1c 100644 --- a/Documentation/devicetree/bindings/nvmem/rmem.yaml +++ b/Documentation/devicetree/bindings/nvmem/rmem.yaml @@ -10,7 +10,7 @@ maintainers: - Nicolas Saenz Julienne allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/rockchip-efuse.yaml b/Documentation/devicetree/bindings/nvmem/rockchip-efuse.yaml index febee8129aa9..c5403e149080 100644 --- a/Documentation/devicetree/bindings/nvmem/rockchip-efuse.yaml +++ b/Documentation/devicetree/bindings/nvmem/rockchip-efuse.yaml @@ -10,7 +10,7 @@ maintainers: - Heiko Stuebner allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/socionext,uniphier-efuse.yaml b/Documentation/devicetree/bindings/nvmem/socionext,uniphier-efuse.yaml index dc790d2cd9f0..b8bca0599c45 100644 --- a/Documentation/devicetree/bindings/nvmem/socionext,uniphier-efuse.yaml +++ b/Documentation/devicetree/bindings/nvmem/socionext,uniphier-efuse.yaml @@ -11,7 +11,7 @@ maintainers: - Kunihiko Hayashi allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: "#address-cells": true diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml index 172597cc5c63..a69de3e92282 100644 --- a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml +++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml @@ -16,7 +16,7 @@ maintainers: - Fabrice Gasnier allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: diff --git a/Documentation/devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml index a7644ebbc2ca..8877c2283e9e 100644 --- a/Documentation/devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml @@ -11,7 +11,7 @@ maintainers: - Vincent Shih allOf: - - $ref: "nvmem.yaml#" + - $ref: nvmem.yaml# properties: compatible: -- GitLab From a4fb434ef96ace5af758ca2c52c3a3f8f3abc87c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 18:21:34 +0100 Subject: [PATCH 2145/5631] nvmem: stm32-romem: mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/nvmem/stm32-romem.c:271:34: error: ‘stm32_romem_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-27-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/stm32-romem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvmem/stm32-romem.c b/drivers/nvmem/stm32-romem.c index ba779e26937a..38d0bf557129 100644 --- a/drivers/nvmem/stm32-romem.c +++ b/drivers/nvmem/stm32-romem.c @@ -268,7 +268,7 @@ static const struct stm32_romem_cfg stm32mp13_bsec_cfg = { .ta = true, }; -static const struct of_device_id stm32_romem_of_match[] = { +static const struct of_device_id stm32_romem_of_match[] __maybe_unused = { { .compatible = "st,stm32f4-otp", }, { .compatible = "st,stm32mp15-bsec", .data = (void *)&stm32mp15_bsec_cfg, -- GitLab From de6e05097f7db066afb0ad4c88b730949f7b7749 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Tue, 4 Apr 2023 18:21:35 +0100 Subject: [PATCH 2146/5631] nvmem: mtk-efuse: Support postprocessing for GPU speed binning data On some MediaTek SoCs GPU speed binning data is available for read in the SoC's eFuse array but it has a format that is incompatible with what the OPP API expects, as we read a number from 0 to 7 but opp-supported-hw is expecting a bitmask to enable an OPP entry: being what we read limited to 0-7, it's straightforward to simply convert the value to BIT(value) as a post-processing action. So, introduce post-processing support and enable it by evaluating the newly introduced platform data's `uses_post_processing` member, currently enabled only for MT8186. Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-28-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/mtk-efuse.c | 53 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 51 insertions(+), 2 deletions(-) diff --git a/drivers/nvmem/mtk-efuse.c b/drivers/nvmem/mtk-efuse.c index a08e0aedd21c..b36cd0dcc8c7 100644 --- a/drivers/nvmem/mtk-efuse.c +++ b/drivers/nvmem/mtk-efuse.c @@ -10,6 +10,11 @@ #include #include #include +#include + +struct mtk_efuse_pdata { + bool uses_post_processing; +}; struct mtk_efuse_priv { void __iomem *base; @@ -29,6 +34,37 @@ static int mtk_reg_read(void *context, return 0; } +static int mtk_efuse_gpu_speedbin_pp(void *context, const char *id, int index, + unsigned int offset, void *data, size_t bytes) +{ + u8 *val = data; + + if (val[0] < 8) + val[0] = BIT(val[0]); + + return 0; +} + +static void mtk_efuse_fixup_cell_info(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell) +{ + size_t sz = strlen(cell->name); + + /* + * On some SoCs, the GPU speedbin is not read as bitmask but as + * a number with range [0-7] (max 3 bits): post process to use + * it in OPP tables to describe supported-hw. + */ + if (cell->nbits <= 3 && + strncmp(cell->name, "gpu-speedbin", min(sz, strlen("gpu-speedbin"))) == 0) + cell->read_post_process = mtk_efuse_gpu_speedbin_pp; +} + +static struct nvmem_layout mtk_efuse_layout = { + .fixup_cell_info = mtk_efuse_fixup_cell_info, +}; + static int mtk_efuse_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -36,6 +72,7 @@ static int mtk_efuse_probe(struct platform_device *pdev) struct nvmem_device *nvmem; struct nvmem_config econfig = {}; struct mtk_efuse_priv *priv; + const struct mtk_efuse_pdata *pdata; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -45,20 +82,32 @@ static int mtk_efuse_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); + pdata = device_get_match_data(dev); econfig.stride = 1; econfig.word_size = 1; econfig.reg_read = mtk_reg_read; econfig.size = resource_size(res); econfig.priv = priv; econfig.dev = dev; + if (pdata->uses_post_processing) + econfig.layout = &mtk_efuse_layout; nvmem = devm_nvmem_register(dev, &econfig); return PTR_ERR_OR_ZERO(nvmem); } +static const struct mtk_efuse_pdata mtk_mt8186_efuse_pdata = { + .uses_post_processing = true, +}; + +static const struct mtk_efuse_pdata mtk_efuse_pdata = { + .uses_post_processing = false, +}; + static const struct of_device_id mtk_efuse_of_match[] = { - { .compatible = "mediatek,mt8173-efuse",}, - { .compatible = "mediatek,efuse",}, + { .compatible = "mediatek,mt8173-efuse", .data = &mtk_efuse_pdata }, + { .compatible = "mediatek,mt8186-efuse", .data = &mtk_mt8186_efuse_pdata }, + { .compatible = "mediatek,efuse", .data = &mtk_efuse_pdata }, {/* sentinel */}, }; MODULE_DEVICE_TABLE(of, mtk_efuse_of_match); -- GitLab From 796d160c4ed032c66415120d67aea8ecd502879f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 4 Apr 2023 18:21:36 +0100 Subject: [PATCH 2147/5631] dt-bindings: nvmem: Add compatible for SM6350 Docuemnt the QFPROM on SM6350. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-29-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index e952907ad1d5..c20bd9bdcea4 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -32,6 +32,7 @@ properties: - qcom,sdm670-qfprom - qcom,sdm845-qfprom - qcom,sm6115-qfprom + - qcom,sm6350-qfprom - qcom,sm8150-qfprom - qcom,sm8250-qfprom - const: qcom,qfprom -- GitLab From cc25eba0b88200730ce03b066f7569ca6c29605d Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 4 Apr 2023 18:21:37 +0100 Subject: [PATCH 2148/5631] dt-bindings: nvmem: Add compatible for SM6375 Docuemnt the QFPROM on SM6375. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-30-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index c20bd9bdcea4..8d8503dd934b 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -33,6 +33,7 @@ properties: - qcom,sdm845-qfprom - qcom,sm6115-qfprom - qcom,sm6350-qfprom + - qcom,sm6375-qfprom - qcom,sm8150-qfprom - qcom,sm8250-qfprom - const: qcom,qfprom -- GitLab From 1dc552fa33cf98af3e784dbc0500da93cae3b24a Mon Sep 17 00:00:00 2001 From: Yang Li Date: Tue, 4 Apr 2023 18:21:38 +0100 Subject: [PATCH 2149/5631] nvmem: bcm-ocotp: Use devm_platform_ioremap_resource() According to commit 7945f929f1a7 ("drivers: provide devm_platform_ioremap_resource()"), convert platform_get_resource(), devm_ioremap_resource() to a single call to use devm_platform_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Yang Li Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-31-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/bcm-ocotp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvmem/bcm-ocotp.c b/drivers/nvmem/bcm-ocotp.c index a128c7f5e351..0c1fa0c4feb2 100644 --- a/drivers/nvmem/bcm-ocotp.c +++ b/drivers/nvmem/bcm-ocotp.c @@ -244,7 +244,6 @@ MODULE_DEVICE_TABLE(acpi, bcm_otpc_acpi_ids); static int bcm_otpc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct otpc_priv *priv; struct nvmem_device *nvmem; int err; @@ -259,8 +258,7 @@ static int bcm_otpc_probe(struct platform_device *pdev) return -ENODEV; /* Get OTP base address register. */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(dev, res); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { dev_err(dev, "unable to map I/O memory\n"); return PTR_ERR(priv->base); -- GitLab From 649409990d2e93fac657be7c6960c28a2c601d65 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Tue, 4 Apr 2023 18:21:39 +0100 Subject: [PATCH 2150/5631] nvmem: nintendo-otp: Use devm_platform_ioremap_resource() According to commit 7945f929f1a7 ("drivers: provide devm_platform_ioremap_resource()"), convert platform_get_resource(), devm_ioremap_resource() to a single call to use devm_platform_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Yang Li Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-32-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/nintendo-otp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvmem/nintendo-otp.c b/drivers/nvmem/nintendo-otp.c index 33961b17f9f1..355e7f1fc6d5 100644 --- a/drivers/nvmem/nintendo-otp.c +++ b/drivers/nvmem/nintendo-otp.c @@ -76,7 +76,6 @@ static int nintendo_otp_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; const struct of_device_id *of_id = of_match_device(nintendo_otp_of_table, dev); - struct resource *res; struct nvmem_device *nvmem; struct nintendo_otp_priv *priv; @@ -92,8 +91,7 @@ static int nintendo_otp_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = devm_ioremap_resource(dev, res); + priv->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs)) return PTR_ERR(priv->regs); -- GitLab From c2367aa60d5e34d48582362c6de34b4131d92be7 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Tue, 4 Apr 2023 18:21:40 +0100 Subject: [PATCH 2151/5631] nvmem: vf610-ocotp: Use devm_platform_get_and_ioremap_resource() According to commit 890cc39a8799 ("drivers: provide devm_platform_get_and_ioremap_resource()"), convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Yang Li Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-33-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/vf610-ocotp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvmem/vf610-ocotp.c b/drivers/nvmem/vf610-ocotp.c index 5b6cad16892f..ee9c61ae727d 100644 --- a/drivers/nvmem/vf610-ocotp.c +++ b/drivers/nvmem/vf610-ocotp.c @@ -219,8 +219,7 @@ static int vf610_ocotp_probe(struct platform_device *pdev) if (!ocotp_dev) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ocotp_dev->base = devm_ioremap_resource(dev, res); + ocotp_dev->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(ocotp_dev->base)) return PTR_ERR(ocotp_dev->base); -- GitLab From 7e2805c203a6c8dc85c1cfda205161ed39ae82d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 4 Apr 2023 18:21:41 +0100 Subject: [PATCH 2152/5631] dt-bindings: nvmem: u-boot,env: add MAC's #nvmem-cell-cells MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit U-Boot's "ethaddr" environment variable is very often used to store *base* MAC address. It's used as a base for calculating addresses for multiple interfaces. It's done by adding proper values. Actual offsets are picked by manufacturers and vary across devices. Signed-off-by: Rafał Miłecki Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-34-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/u-boot,env.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/nvmem/u-boot,env.yaml b/Documentation/devicetree/bindings/nvmem/u-boot,env.yaml index cbc5c69fd405..36d97fb87865 100644 --- a/Documentation/devicetree/bindings/nvmem/u-boot,env.yaml +++ b/Documentation/devicetree/bindings/nvmem/u-boot,env.yaml @@ -50,7 +50,11 @@ properties: ethaddr: type: object - description: Ethernet interface's MAC address + description: Ethernet interfaces base MAC address. + properties: + "#nvmem-cell-cells": + description: The first argument is a MAC address offset. + const: 1 additionalProperties: false @@ -72,6 +76,7 @@ examples: reg = <0x40000 0x10000>; mac: ethaddr { + #nvmem-cell-cells = <1>; }; }; }; -- GitLab From 55d4980ce55b6bb4be66877de4dbec513911b988 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 4 Apr 2023 18:21:42 +0100 Subject: [PATCH 2153/5631] nvmem: core: support specifying both: cell raw data & post read lengths MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Callback .read_post_process() is designed to modify raw cell content before providing it to the consumer. So far we were dealing with modifications that didn't affect cell size (length). In some cases however cell content needs to be reformatted and resized. It's required e.g. to provide properly formatted MAC address in case it's stored in a non-binary format (e.g. using ASCII). There were few discussions how to optimally handle that. Following possible solutions were considered: 1. Allow .read_post_process() to realloc (resize) content buffer 2. Allow .read_post_process() to adjust (decrease) just buffer length 3. Register NVMEM cells using post-read sizes The preferred solution was the last one. The problem is that simply adjusting "bytes" in NVMEM providers would result in core code NOT passing whole raw data to .read_post_process() callbacks. It means callback functions couldn't do their job without somehow manually reading original cell content on their own. This patch deals with that by registering NVMEM cells with both lengths: raw content one and post read one. It allows: 1. Core code to read whole raw cell content 2. Callbacks to return content they want Signed-off-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-35-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 11 +++++++---- include/linux/nvmem-provider.h | 2 ++ 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 212c5ba5789f..a62973d010ff 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -50,6 +50,7 @@ struct nvmem_device { struct nvmem_cell_entry { const char *name; int offset; + size_t raw_len; int bytes; int bit_offset; int nbits; @@ -469,6 +470,7 @@ static int nvmem_cell_info_to_nvmem_cell_entry_nodup(struct nvmem_device *nvmem, { cell->nvmem = nvmem; cell->offset = info->offset; + cell->raw_len = info->raw_len ?: info->bytes; cell->bytes = info->bytes; cell->name = info->name; cell->read_post_process = info->read_post_process; @@ -1560,7 +1562,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, { int rc; - rc = nvmem_reg_read(nvmem, cell->offset, buf, cell->bytes); + rc = nvmem_reg_read(nvmem, cell->offset, buf, cell->raw_len); if (rc) return rc; @@ -1571,7 +1573,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, if (cell->read_post_process) { rc = cell->read_post_process(cell->priv, id, index, - cell->offset, buf, cell->bytes); + cell->offset, buf, cell->raw_len); if (rc) return rc; } @@ -1594,14 +1596,15 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, */ void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len) { - struct nvmem_device *nvmem = cell->entry->nvmem; + struct nvmem_cell_entry *entry = cell->entry; + struct nvmem_device *nvmem = entry->nvmem; u8 *buf; int rc; if (!nvmem) return ERR_PTR(-EINVAL); - buf = kzalloc(cell->entry->bytes, GFP_KERNEL); + buf = kzalloc(max_t(size_t, entry->raw_len, entry->bytes), GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0cf9f9490514..8ffb42ba0f62 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -51,6 +51,7 @@ struct nvmem_keepout { * struct nvmem_cell_info - NVMEM cell description * @name: Name. * @offset: Offset within the NVMEM device. + * @raw_len: Length of raw data (without post processing). * @bytes: Length of the cell. * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. @@ -62,6 +63,7 @@ struct nvmem_keepout { struct nvmem_cell_info { const char *name; unsigned int offset; + size_t raw_len; unsigned int bytes; unsigned int bit_offset; unsigned int nbits; -- GitLab From c49f1a8af6bcf6d18576bca898f8083ca4b129e1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Tue, 4 Apr 2023 18:21:43 +0100 Subject: [PATCH 2154/5631] nvmem: u-boot-env: post-process "ethaddr" env variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit U-Boot environment variables are stored in ASCII format so "ethaddr" requires parsing into binary to make it work with Ethernet interfaces. This includes support for indexes to support #nvmem-cell-cells = <1>. Signed-off-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-36-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/Kconfig | 1 + drivers/nvmem/u-boot-env.c | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index a2afba11c890..b291b27048c7 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -340,6 +340,7 @@ config NVMEM_U_BOOT_ENV tristate "U-Boot environment variables support" depends on OF && MTD select CRC32 + select GENERIC_NET_UTILS help U-Boot stores its setup as environment variables. This driver adds support for verifying & exporting such data. It also exposes variables diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c index 29b1d87a3c51..ee9fd9989b6e 100644 --- a/drivers/nvmem/u-boot-env.c +++ b/drivers/nvmem/u-boot-env.c @@ -4,6 +4,8 @@ */ #include +#include +#include #include #include #include @@ -70,6 +72,25 @@ static int u_boot_env_read(void *context, unsigned int offset, void *val, return 0; } +static int u_boot_env_read_post_process_ethaddr(void *context, const char *id, int index, + unsigned int offset, void *buf, size_t bytes) +{ + u8 mac[ETH_ALEN]; + + if (bytes != 3 * ETH_ALEN - 1) + return -EINVAL; + + if (!mac_pton(buf, mac)) + return -EINVAL; + + if (index) + eth_addr_add(mac, index); + + ether_addr_copy(buf, mac); + + return 0; +} + static int u_boot_env_add_cells(struct u_boot_env *priv, uint8_t *buf, size_t data_offset, size_t data_len) { @@ -101,6 +122,11 @@ static int u_boot_env_add_cells(struct u_boot_env *priv, uint8_t *buf, priv->cells[idx].offset = data_offset + value - data; priv->cells[idx].bytes = strlen(value); priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name); + if (!strcmp(var, "ethaddr")) { + priv->cells[idx].raw_len = strlen(value); + priv->cells[idx].bytes = ETH_ALEN; + priv->cells[idx].read_post_process = u_boot_env_read_post_process_ethaddr; + } } if (WARN_ON(idx != priv->ncells)) -- GitLab From 814c978f02db17f16e6aa2efa2a929372f06da09 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:44 +0100 Subject: [PATCH 2155/5631] nvmem: Add macro to register nvmem layout drivers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide a module_nvmem_layout_driver() macro at the end of the nvmem-provider.h header to reduce the boilerplate when registering nvmem layout drivers. Suggested-by: Srinivas Kandagatla Signed-off-by: Miquel Raynal Acked-by: Rafał Miłecki Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-37-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-provider.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 8ffb42ba0f62..dae26295e6be 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -9,6 +9,7 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include #include #include #include @@ -242,4 +243,9 @@ nvmem_layout_get_match_data(struct nvmem_device *nvmem, } #endif /* CONFIG_NVMEM */ + +#define module_nvmem_layout_driver(__layout_driver) \ + module_driver(__layout_driver, nvmem_layout_register, \ + nvmem_layout_unregister) + #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ -- GitLab From 0abdf99fe0c86252ba274703425f8d543d7e7f0d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:45 +0100 Subject: [PATCH 2156/5631] nvmem: layouts: sl28vpd: Use module_nvmem_layout_driver() Stop open-coding the module init/exit functions. Use the module_nvmem_layout_driver() instead. Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-38-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/sl28vpd.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c index 9370e41bad73..9cc1715c2fd5 100644 --- a/drivers/nvmem/layouts/sl28vpd.c +++ b/drivers/nvmem/layouts/sl28vpd.c @@ -146,19 +146,7 @@ struct nvmem_layout sl28vpd_layout = { .of_match_table = sl28vpd_of_match_table, .add_cells = sl28vpd_add_cells, }; - -static int __init sl28vpd_init(void) -{ - return nvmem_layout_register(&sl28vpd_layout); -} - -static void __exit sl28vpd_exit(void) -{ - nvmem_layout_unregister(&sl28vpd_layout); -} - -module_init(sl28vpd_init); -module_exit(sl28vpd_exit); +module_nvmem_layout_driver(sl28vpd_layout); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael Walle "); -- GitLab From d119eb38faab61125aaa4f63c74eef61585cf34c Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:46 +0100 Subject: [PATCH 2157/5631] nvmem: layouts: onie-tlv: Use module_nvmem_layout_driver() Stop open-coding the module init/exit functions. Use the module_nvmem_layout_driver() instead. Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-39-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/onie-tlv.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c index d45b7301a69d..661093de33b4 100644 --- a/drivers/nvmem/layouts/onie-tlv.c +++ b/drivers/nvmem/layouts/onie-tlv.c @@ -237,19 +237,7 @@ static struct nvmem_layout onie_tlv_layout = { .of_match_table = onie_tlv_of_match_table, .add_cells = onie_tlv_parse_table, }; - -static int __init onie_tlv_init(void) -{ - return nvmem_layout_register(&onie_tlv_layout); -} - -static void __exit onie_tlv_exit(void) -{ - nvmem_layout_unregister(&onie_tlv_layout); -} - -module_init(onie_tlv_init); -module_exit(onie_tlv_exit); +module_nvmem_layout_driver(onie_tlv_layout); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Miquel Raynal "); -- GitLab From 6b13e4b6a9a45028ac730e550380077df1845912 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 4 Apr 2023 18:21:47 +0100 Subject: [PATCH 2158/5631] nvmem: layouts: onie-tlv: Drop wrong module alias The MODULE_ALIAS macro is misused here as it carries the description. There is currently no relevant alias to provide so let's just drop it. Signed-off-by: Miquel Raynal Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-40-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/onie-tlv.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvmem/layouts/onie-tlv.c b/drivers/nvmem/layouts/onie-tlv.c index 661093de33b4..59fc87ccfcff 100644 --- a/drivers/nvmem/layouts/onie-tlv.c +++ b/drivers/nvmem/layouts/onie-tlv.c @@ -242,4 +242,3 @@ module_nvmem_layout_driver(onie_tlv_layout); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Miquel Raynal "); MODULE_DESCRIPTION("NVMEM layout driver for Onie TLV table parsing"); -MODULE_ALIAS("NVMEM layout driver for Onie TLV table parsing"); -- GitLab From a8642cd11635a35a5f1dc31857887900d6610778 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 4 Apr 2023 18:21:48 +0100 Subject: [PATCH 2159/5631] nvmem: layouts: sl28vpd: set varaiable sl28vpd_layout storage-class-specifier to static smatch reports drivers/nvmem/layouts/sl28vpd.c:144:21: warning: symbol 'sl28vpd_layout' was not declared. Should it be static? This variable is only used in one file so it should be static. Signed-off-by: Tom Rix Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20230404172148.82422-41-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/layouts/sl28vpd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvmem/layouts/sl28vpd.c b/drivers/nvmem/layouts/sl28vpd.c index 9cc1715c2fd5..05671371f631 100644 --- a/drivers/nvmem/layouts/sl28vpd.c +++ b/drivers/nvmem/layouts/sl28vpd.c @@ -141,7 +141,7 @@ static const struct of_device_id sl28vpd_of_match_table[] = { }; MODULE_DEVICE_TABLE(of, sl28vpd_of_match_table); -struct nvmem_layout sl28vpd_layout = { +static struct nvmem_layout sl28vpd_layout = { .name = "sl28-vpd", .of_match_table = sl28vpd_of_match_table, .add_cells = sl28vpd_add_cells, -- GitLab From 0e5c9a9d6548e9b178d4696c696ae4a21c39ae58 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 5 Apr 2023 12:48:58 +0100 Subject: [PATCH 2160/5631] KVM: arm64: Expose SMC/HVC width to userspace When returning to userspace to handle a SMCCC call, we consistently set PC to point to the instruction immediately after the HVC/SMC. However, should userspace need to know the exact address of the trapping instruction, it needs to know about the *size* of that instruction. For AArch64, this is pretty easy. For AArch32, this is a bit more funky, as Thumb has 16bit encodings for both HVC and SMC. Expose this to userspace with a new flag that directly derives from ESR_EL2.IL. Also update the documentation to reflect the PC state at the point of exit. Finally, this fixes a small buglet where the hypercall.{args,ret} fields would not be cleared on exit, and could contain some random junk. Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/86pm8iv8tj.wl-maz@kernel.org --- Documentation/virt/kvm/api.rst | 8 ++++++++ arch/arm64/include/uapi/asm/kvm.h | 3 ++- arch/arm64/kvm/hypercalls.c | 16 +++++++++++----- 3 files changed, 21 insertions(+), 6 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c8ab2f730945..103f945959ed 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6244,6 +6244,14 @@ Definition of ``flags``: conduit to initiate the SMCCC call. If this bit is 0 then the guest used the HVC conduit for the SMCCC call. + - ``KVM_HYPERCALL_EXIT_16BIT``: Indicates that the guest used a 16bit + instruction to initiate the SMCCC call. If this bit is 0 then the + guest used a 32bit instruction. An AArch64 guest always has this + bit set to 0. + +At the point of exit, PC points to the instruction immediately following +the trapping instruction. + :: /* KVM_EXIT_TPR_ACCESS */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3dcfa4bfdf83..b1c1edf85480 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -491,7 +491,8 @@ struct kvm_smccc_filter { }; /* arm64-specific KVM_EXIT_HYPERCALL flags */ -#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) #endif diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 9a35d6d18193..3b6523f25afc 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -222,13 +222,19 @@ static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id) { u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); struct kvm_run *run = vcpu->run; - - run->exit_reason = KVM_EXIT_HYPERCALL; - run->hypercall.nr = func_id; - run->hypercall.flags = 0; + u64 flags = 0; if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64) - run->hypercall.flags |= KVM_HYPERCALL_EXIT_SMC; + flags |= KVM_HYPERCALL_EXIT_SMC; + + if (!kvm_vcpu_trap_il_is32bit(vcpu)) + flags |= KVM_HYPERCALL_EXIT_16BIT; + + run->exit_reason = KVM_EXIT_HYPERCALL; + run->hypercall = (typeof(run->hypercall)) { + .nr = func_id, + .flags = flags, + }; } int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) -- GitLab From 548bd27428b924cb725ab7c1418c0203e61f9ed7 Mon Sep 17 00:00:00 2001 From: Binbin Wu Date: Tue, 4 Apr 2023 11:25:02 +0800 Subject: [PATCH 2161/5631] KVM: VMX: Use is_64_bit_mode() to check 64-bit mode in SGX handler sgx_get_encls_gva() uses is_long_mode() to check 64-bit mode, however, SGX system leaf instructions are valid in compatibility mode, should use is_64_bit_mode() instead. Fixes: 70210c044b4e ("KVM: VMX: Add SGX ENCLS[ECREATE] handler to enforce CPUID restrictions") Signed-off-by: Binbin Wu Reviewed-by: Kai Huang Link: https://lore.kernel.org/r/20230404032502.27798-1-binbin.wu@linux.intel.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/sgx.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index aa53c98034bf..0574030b071f 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -29,14 +29,14 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, /* Skip vmcs.GUEST_DS retrieval for 64-bit mode to avoid VMREADs. */ *gva = offset; - if (!is_long_mode(vcpu)) { + if (!is_64_bit_mode(vcpu)) { vmx_get_segment(vcpu, &s, VCPU_SREG_DS); *gva += s.base; } if (!IS_ALIGNED(*gva, alignment)) { fault = true; - } else if (likely(is_long_mode(vcpu))) { + } else if (likely(is_64_bit_mode(vcpu))) { fault = is_noncanonical_address(*gva, vcpu); } else { *gva &= 0xffffffff; -- GitLab From 141b3251c526797769f541b660ed198138f5b23a Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 2 Apr 2023 11:42:04 +0200 Subject: [PATCH 2162/5631] clk: Compute masks for fractional_divider clk when needed. There is no real need to pre-compute mmask and nmask when handling fractional_divider clk. They can be computed when needed. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/0fd6357242c974259c9e034c6e28a0391c480bf0.1680423909.git.christophe.jaillet@wanadoo.fr Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- drivers/clk/clk-fractional-divider.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/clk/clk-fractional-divider.c b/drivers/clk/clk-fractional-divider.c index 6affe3565025..479297763e70 100644 --- a/drivers/clk/clk-fractional-divider.c +++ b/drivers/clk/clk-fractional-divider.c @@ -71,6 +71,7 @@ static void clk_fd_get_div(struct clk_hw *hw, struct u32_fract *fract) struct clk_fractional_divider *fd = to_clk_fd(hw); unsigned long flags = 0; unsigned long m, n; + u32 mmask, nmask; u32 val; if (fd->lock) @@ -85,8 +86,11 @@ static void clk_fd_get_div(struct clk_hw *hw, struct u32_fract *fract) else __release(fd->lock); - m = (val & fd->mmask) >> fd->mshift; - n = (val & fd->nmask) >> fd->nshift; + mmask = GENMASK(fd->mwidth - 1, 0) << fd->mshift; + nmask = GENMASK(fd->nwidth - 1, 0) << fd->nshift; + + m = (val & mmask) >> fd->mshift; + n = (val & nmask) >> fd->nshift; if (fd->flags & CLK_FRAC_DIVIDER_ZERO_BASED) { m++; @@ -166,6 +170,7 @@ static int clk_fd_set_rate(struct clk_hw *hw, unsigned long rate, struct clk_fractional_divider *fd = to_clk_fd(hw); unsigned long flags = 0; unsigned long m, n; + u32 mmask, nmask; u32 val; rational_best_approximation(rate, parent_rate, @@ -182,8 +187,11 @@ static int clk_fd_set_rate(struct clk_hw *hw, unsigned long rate, else __acquire(fd->lock); + mmask = GENMASK(fd->mwidth - 1, 0) << fd->mshift; + nmask = GENMASK(fd->nwidth - 1, 0) << fd->nshift; + val = clk_fd_readl(fd); - val &= ~(fd->mmask | fd->nmask); + val &= ~(mmask | nmask); val |= (m << fd->mshift) | (n << fd->nshift); clk_fd_writel(fd, val); @@ -260,10 +268,8 @@ struct clk_hw *clk_hw_register_fractional_divider(struct device *dev, fd->reg = reg; fd->mshift = mshift; fd->mwidth = mwidth; - fd->mmask = GENMASK(mwidth - 1, 0) << mshift; fd->nshift = nshift; fd->nwidth = nwidth; - fd->nmask = GENMASK(nwidth - 1, 0) << nshift; fd->flags = clk_divider_flags; fd->lock = lock; fd->hw.init = &init; -- GitLab From c1e0e392d65dc38e0bf61b6df2f02b9c9e7046a2 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 2 Apr 2023 11:42:05 +0200 Subject: [PATCH 2163/5631] clk: imx: Remove values for mmask and nmask in struct clk_fractional_divider Now that fractional_divider clk computes mmask and nmask when needed, there is no more need to provide them explicitly anymore. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/187a2266c3a034a593a151d6e5e6b21118043b5d.1680423909.git.christophe.jaillet@wanadoo.fr Reviewed-by: Abel Vesa Signed-off-by: Stephen Boyd --- drivers/clk/imx/clk-composite-7ulp.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c index 4eedd45dbaa8..e208ddc51133 100644 --- a/drivers/clk/imx/clk-composite-7ulp.c +++ b/drivers/clk/imx/clk-composite-7ulp.c @@ -19,10 +19,8 @@ #define PCG_CGC_SHIFT 30 #define PCG_FRAC_SHIFT 3 #define PCG_FRAC_WIDTH 1 -#define PCG_FRAC_MASK BIT(3) #define PCG_PCD_SHIFT 0 #define PCG_PCD_WIDTH 3 -#define PCG_PCD_MASK 0x7 #define SW_RST BIT(28) @@ -102,10 +100,8 @@ static struct clk_hw *imx_ulp_clk_hw_composite(const char *name, fd->reg = reg; fd->mshift = PCG_FRAC_SHIFT; fd->mwidth = PCG_FRAC_WIDTH; - fd->mmask = PCG_FRAC_MASK; fd->nshift = PCG_PCD_SHIFT; fd->nwidth = PCG_PCD_WIDTH; - fd->nmask = PCG_PCD_MASK; fd->flags = CLK_FRAC_DIVIDER_ZERO_BASED; if (has_swrst) fd->lock = &imx_ccm_lock; -- GitLab From 645a5198ddba6d6b2dea8346ca796064e931a0c3 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 2 Apr 2023 11:42:06 +0200 Subject: [PATCH 2164/5631] clk: rockchip: Remove values for mmask and nmask in struct clk_fractional_divider Now that fractional_divider clk computes mmask and nmask when needed, there is no more need to provide them explicitly anymore. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/58e1950566e40e2fbb31004baee57a164ca6a390.1680423909.git.christophe.jaillet@wanadoo.fr Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- drivers/clk/rockchip/clk.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index a8646794575a..4059d9365ae6 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -244,10 +244,8 @@ static struct clk *rockchip_clk_register_frac_branch( div->reg = base + muxdiv_offset; div->mshift = 16; div->mwidth = 16; - div->mmask = GENMASK(div->mwidth - 1, 0) << div->mshift; div->nshift = 0; div->nwidth = 16; - div->nmask = GENMASK(div->nwidth - 1, 0) << div->nshift; div->lock = lock; div->approximation = rockchip_fractional_approximation; div_ops = &clk_fractional_divider_ops; -- GitLab From 14e985482111a2c6bc75a0348701a4acdc5558d8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 2 Apr 2023 11:42:07 +0200 Subject: [PATCH 2165/5631] clk: Remove mmask and nmask fields in struct clk_fractional_divider All users of these fields have been removed. They are now computed when needed with [mn]shift and [mn]width. This shrinks the size of struct clk_fractional_divider from 72 to 56 bytes. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/680357e5acb338433bfc94114b65b4a4ce2c99e2.1680423909.git.christophe.jaillet@wanadoo.fr Reviewed-by: Heiko Stuebner Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..3271a2bc352f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1135,10 +1135,8 @@ struct clk_fractional_divider { void __iomem *reg; u8 mshift; u8 mwidth; - u32 mmask; u8 nshift; u8 nwidth; - u32 nmask; u8 flags; void (*approximation)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate, -- GitLab From 7e768ce8278bafe43e2a4771a82b61856190a3fc Mon Sep 17 00:00:00 2001 From: Like Xu Date: Tue, 4 Apr 2023 15:17:59 +0800 Subject: [PATCH 2166/5631] KVM: x86/pmu: Zero out pmu->all_valid_pmc_idx each time it's refreshed The kvm_pmu_refresh() may be called repeatedly (e.g. configure guest CPUID repeatedly or update MSR_IA32_PERF_CAPABILITIES) and each call will use the last pmu->all_valid_pmc_idx value, with the residual bits introducing additional overhead later in the vPMU emulation. Fixes: b35e5548b411 ("KVM: x86/vPMU: Add lazy mechanism to release perf_event per vPMC") Suggested-by: Sean Christopherson Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230404071759.75376-1-likexu@tencent.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 612e6c70ce2e..29492c2a0c82 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -589,6 +589,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); static_call(kvm_x86_pmu_refresh)(vcpu); } -- GitLab From 944a8dad8b4eb0b565cc36600ee1339c21278d76 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 3 Apr 2023 21:01:41 -0400 Subject: [PATCH 2167/5631] KVM: x86: set "mitigate_smt_rsb" storage-class-specifier to static smatch reports arch/x86/kvm/x86.c:199:20: warning: symbol 'mitigate_smt_rsb' was not declared. Should it be static? This variable is only used in one file so it should be static. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230404010141.1913667-1-trix@redhat.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2e0933f510ee..1b74da8682a0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -194,7 +194,7 @@ bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); /* Enable/disable SMT_RSB bug mitigation */ -bool __read_mostly mitigate_smt_rsb; +static bool __read_mostly mitigate_smt_rsb; module_param(mitigate_smt_rsb, bool, 0444); /* -- GitLab From 098f4c061ea10b777033b71c10bd9fd706820ee9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Sat, 28 Jan 2023 00:14:27 +0000 Subject: [PATCH 2168/5631] KVM: x86/pmu: Disallow legacy LBRs if architectural LBRs are available Disallow enabling LBR support if the CPU supports architectural LBRs. Traditional LBR support is absent on CPU models that have architectural LBRs, and KVM doesn't yet support arch LBRs, i.e. KVM will pass through non-existent MSRs if userspace enables LBRs for the guest. Cc: stable@vger.kernel.org Cc: Yang Weijiang Cc: Like Xu Reported-by: Paolo Bonzini Fixes: be635e34c284 ("KVM: vmx/pmu: Expose LBR_FMT in the MSR_IA32_PERF_CAPABILITIES") Tested-by: Like Xu Link: https://lore.kernel.org/r/20230128001427.2548858-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/vmx.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7bf14abdba1..c18f74899f01 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7793,9 +7793,11 @@ static u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - x86_perf_get_lbr(&lbr); - if (lbr.nr) - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { + x86_perf_get_lbr(&lbr); + if (lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; -- GitLab From 7712145073876092e9aa81f0b836fef8b5694b14 Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Wed, 5 Apr 2023 18:13:50 +0800 Subject: [PATCH 2169/5631] KVM: selftests: Close opened file descriptor in stable_tsc_check_supported() Close the "current_clocksource" file descriptor before returning or exiting from stable_tsc_check_supported() in vmx_nested_tsc_scaling_test. Signed-off-by: Hao Ge Reviewed-by: Vipin Sharma Link: https://lore.kernel.org/r/20230405101350.259000-1-gehao@kylinos.cn Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c index d427eb146bc5..fa03c8d1ce4e 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c @@ -126,12 +126,16 @@ static void stable_tsc_check_supported(void) goto skip_test; if (fgets(buf, sizeof(buf), fp) == NULL) - goto skip_test; + goto close_fp; if (strncmp(buf, "tsc", sizeof(buf))) - goto skip_test; + goto close_fp; + fclose(fp); return; + +close_fp: + fclose(fp); skip_test: print_skip("Kernel does not use TSC clocksource - assuming that host TSC is not stable"); exit(KSFT_SKIP); -- GitLab From def8574308edbc3bca821fb965e429a2fe5f4971 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:14 -0800 Subject: [PATCH 2170/5631] dmapool: add alloc/free performance test Patch series "dmapool enhancements", v4. Time spent in dma_pool alloc/free increases linearly with the number of pages backing the pool. We can reduce this to constant time with minor changes to how free pages are tracked. This patch (of 12): Provide a module that allocates and frees many blocks of various sizes and report how long it takes. This is intended to provide a consistent way to measure how changes to the dma_pool_alloc/free routines affect timing. Link: https://lkml.kernel.org/r/20230126215125.4069751-1-kbusch@meta.com Link: https://lkml.kernel.org/r/20230126215125.4069751-2-kbusch@meta.com Signed-off-by: Keith Busch Cc: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/Kconfig | 9 +++ mm/Makefile | 1 + mm/dmapool_test.c | 147 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 157 insertions(+) create mode 100644 mm/dmapool_test.c diff --git a/mm/Kconfig b/mm/Kconfig index 4751031f3f05..ca98b2072df5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1100,6 +1100,15 @@ comment "GUP_TEST needs to have DEBUG_FS enabled" config GUP_GET_PXX_LOW_HIGH bool +config DMAPOOL_TEST + tristate "Enable a module to run time tests on dma_pool" + depends on HAS_DMA + help + Provides a test module that will allocate and free many blocks of + various sizes and report how long it takes. This is intended to + provide a consistent way to measure how changes to the + dma_pool_alloc/free routines affect performance. + config ARCH_HAS_PTE_SPECIAL bool diff --git a/mm/Makefile b/mm/Makefile index 8e105e5b3e29..3a08f5d7b178 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -103,6 +103,7 @@ obj-$(CONFIG_MEMCG) += swap_cgroup.o endif obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_GUP_TEST) += gup_test.o +obj-$(CONFIG_DMAPOOL_TEST) += dmapool_test.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o diff --git a/mm/dmapool_test.c b/mm/dmapool_test.c new file mode 100644 index 000000000000..370fb9e209ef --- /dev/null +++ b/mm/dmapool_test.c @@ -0,0 +1,147 @@ +#include +#include +#include +#include +#include +#include +#include + +#define NR_TESTS (100) + +struct dma_pool_pair { + dma_addr_t dma; + void *v; +}; + +struct dmapool_parms { + size_t size; + size_t align; + size_t boundary; +}; + +static const struct dmapool_parms pool_parms[] = { + { .size = 16, .align = 16, .boundary = 0 }, + { .size = 64, .align = 64, .boundary = 0 }, + { .size = 256, .align = 256, .boundary = 0 }, + { .size = 1024, .align = 1024, .boundary = 0 }, + { .size = 4096, .align = 4096, .boundary = 0 }, + { .size = 68, .align = 32, .boundary = 4096 }, +}; + +static struct dma_pool *pool; +static struct device test_dev; +static u64 dma_mask; + +static inline int nr_blocks(int size) +{ + return clamp_t(int, (PAGE_SIZE / size) * 512, 1024, 8192); +} + +static int dmapool_test_alloc(struct dma_pool_pair *p, int blocks) +{ + int i; + + for (i = 0; i < blocks; i++) { + p[i].v = dma_pool_alloc(pool, GFP_KERNEL, + &p[i].dma); + if (!p[i].v) + goto pool_fail; + } + + for (i = 0; i < blocks; i++) + dma_pool_free(pool, p[i].v, p[i].dma); + + return 0; + +pool_fail: + for (--i; i >= 0; i--) + dma_pool_free(pool, p[i].v, p[i].dma); + return -ENOMEM; +} + +static int dmapool_test_block(const struct dmapool_parms *parms) +{ + int blocks = nr_blocks(parms->size); + ktime_t start_time, end_time; + struct dma_pool_pair *p; + int i, ret; + + p = kcalloc(blocks, sizeof(*p), GFP_KERNEL); + if (!p) + return -ENOMEM; + + pool = dma_pool_create("test pool", &test_dev, parms->size, + parms->align, parms->boundary); + if (!pool) { + ret = -ENOMEM; + goto free_pairs; + } + + start_time = ktime_get(); + for (i = 0; i < NR_TESTS; i++) { + ret = dmapool_test_alloc(p, blocks); + if (ret) + goto free_pool; + if (need_resched()) + cond_resched(); + } + end_time = ktime_get(); + + printk("dmapool test: size:%-4zu align:%-4zu blocks:%-4d time:%llu\n", + parms->size, parms->align, blocks, + ktime_us_delta(end_time, start_time)); + +free_pool: + dma_pool_destroy(pool); +free_pairs: + kfree(p); + return ret; +} + +static void dmapool_test_release(struct device *dev) +{ +} + +static int dmapool_checks(void) +{ + int i, ret; + + ret = dev_set_name(&test_dev, "dmapool-test"); + if (ret) + return ret; + + ret = device_register(&test_dev); + if (ret) { + printk("%s: register failed:%d\n", __func__, ret); + goto put_device; + } + + test_dev.release = dmapool_test_release; + set_dma_ops(&test_dev, NULL); + test_dev.dma_mask = &dma_mask; + ret = dma_set_mask_and_coherent(&test_dev, DMA_BIT_MASK(64)); + if (ret) { + printk("%s: mask failed:%d\n", __func__, ret); + goto del_device; + } + + for (i = 0; i < ARRAY_SIZE(pool_parms); i++) { + ret = dmapool_test_block(&pool_parms[i]); + if (ret) + break; + } + +del_device: + device_del(&test_dev); +put_device: + put_device(&test_dev); + return ret; +} + +static void dmapool_exit(void) +{ +} + +module_init(dmapool_checks); +module_exit(dmapool_exit); +MODULE_LICENSE("GPL"); -- GitLab From 7f796d141c07c6d1984d17885d2276980726ba64 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:15 -0800 Subject: [PATCH 2171/5631] dmapool: remove checks for dev == NULL dmapool originally tried to support pools without a device because dma_alloc_coherent() supports allocations without a device. But nobody ended up using dma pools without a device, and trying to do so will result in an oops. So remove the checks for pool->dev == NULL since they are unneeded bloat. [kbusch@kernel.org: add check for null dev on create] Link: https://lkml.kernel.org/r/20230126215125.4069751-3-kbusch@meta.com Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 45 ++++++++++++++------------------------------- 1 file changed, 14 insertions(+), 31 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index a7eb5d0eb2da..559207e1c333 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -134,6 +134,9 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, size_t allocation; bool empty = false; + if (!dev) + return NULL; + if (align == 0) align = 1; else if (align & (align - 1)) @@ -275,7 +278,7 @@ void dma_pool_destroy(struct dma_pool *pool) mutex_lock(&pools_reg_lock); mutex_lock(&pools_lock); list_del(&pool->pools); - if (pool->dev && list_empty(&pool->dev->dma_pools)) + if (list_empty(&pool->dev->dma_pools)) empty = true; mutex_unlock(&pools_lock); if (empty) @@ -284,12 +287,8 @@ void dma_pool_destroy(struct dma_pool *pool) list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { if (is_page_busy(page)) { - if (pool->dev) - dev_err(pool->dev, "%s %s, %p busy\n", __func__, - pool->name, page->vaddr); - else - pr_err("%s %s, %p busy\n", __func__, - pool->name, page->vaddr); + dev_err(pool->dev, "%s %s, %p busy\n", __func__, + pool->name, page->vaddr); /* leak the still-in-use consistent memory */ list_del(&page->page_list); kfree(page); @@ -351,12 +350,8 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, for (i = sizeof(page->offset); i < pool->size; i++) { if (data[i] == POOL_POISON_FREED) continue; - if (pool->dev) - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); - else - pr_err("%s %s, %p (corrupted)\n", - __func__, pool->name, retval); + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); /* * Dump the first 4 bytes even if they are not @@ -411,12 +406,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) page = pool_find_page(pool, dma); if (!page) { spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); - else - pr_err("%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); return; } @@ -426,12 +417,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) #ifdef DMAPOOL_DEBUG if ((dma - page->dma) != offset) { spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); - else - pr_err("%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); return; } { @@ -442,12 +429,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) continue; } spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, dma %pad already free\n", - __func__, pool->name, &dma); - else - pr_err("%s %s, dma %pad already free\n", - __func__, pool->name, &dma); + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); return; } } -- GitLab From 65216545436bb072b1ab575aa37173a05f3993c0 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:16 -0800 Subject: [PATCH 2172/5631] dmapool: use sysfs_emit() instead of scnprintf() Use sysfs_emit instead of scnprintf, snprintf or sprintf. Link: https://lkml.kernel.org/r/20230126215125.4069751-4-kbusch@meta.com Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 559207e1c333..20616b760bb9 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -64,18 +64,11 @@ static DEFINE_MUTEX(pools_reg_lock); static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned temp; - unsigned size; - char *next; + int size; struct dma_page *page; struct dma_pool *pool; - next = buf; - size = PAGE_SIZE; - - temp = scnprintf(next, size, "poolinfo - 0.1\n"); - size -= temp; - next += temp; + size = sysfs_emit(buf, "poolinfo - 0.1\n"); mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { @@ -90,16 +83,14 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ - temp = scnprintf(next, size, "%-16s %4u %4zu %4zu %2u\n", - pool->name, blocks, - pages * (pool->allocation / pool->size), - pool->size, pages); - size -= temp; - next += temp; + size += sysfs_emit_at(buf, size, "%-16s %4u %4zu %4zu %2u\n", + pool->name, blocks, + pages * (pool->allocation / pool->size), + pool->size, pages); } mutex_unlock(&pools_lock); - return PAGE_SIZE - size; + return size; } static DEVICE_ATTR_RO(pools); -- GitLab From 347e4e44c0a98abcee3caadd222e3e3896c6d2a8 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:17 -0800 Subject: [PATCH 2173/5631] dmapool: cleanup integer types To represent the size of a single allocation, dmapool currently uses 'unsigned int' in some places and 'size_t' in other places. Standardize on 'unsigned int' to reduce overhead, but use 'size_t' when counting all the blocks in the entire pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-5-kbusch@meta.com Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 20616b760bb9..ee993bb59fc2 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -43,10 +43,10 @@ struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; - size_t size; struct device *dev; - size_t allocation; - size_t boundary; + unsigned int size; + unsigned int allocation; + unsigned int boundary; char name[32]; struct list_head pools; }; @@ -73,7 +73,7 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { unsigned pages = 0; - unsigned blocks = 0; + size_t blocks = 0; spin_lock_irq(&pool->lock); list_for_each_entry(page, &pool->page_list, page_list) { @@ -83,9 +83,10 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ - size += sysfs_emit_at(buf, size, "%-16s %4u %4zu %4zu %2u\n", + size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2u\n", pool->name, blocks, - pages * (pool->allocation / pool->size), + (size_t) pages * + (pool->allocation / pool->size), pool->size, pages); } mutex_unlock(&pools_lock); @@ -133,7 +134,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, else if (align & (align - 1)) return NULL; - if (size == 0) + if (size == 0 || size > INT_MAX) return NULL; else if (size < 4) size = 4; @@ -146,6 +147,8 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, else if ((boundary < size) || (boundary & (boundary - 1))) return NULL; + boundary = min(boundary, allocation); + retval = kmalloc(sizeof(*retval), GFP_KERNEL); if (!retval) return retval; @@ -306,7 +309,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, { unsigned long flags; struct dma_page *page; - size_t offset; + unsigned int offset; void *retval; might_alloc(mem_flags); -- GitLab From 19f504584038f6d27846b19ee413a6ac1ee0f765 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:18 -0800 Subject: [PATCH 2174/5631] dmapool: speedup DMAPOOL_DEBUG with init_on_alloc Avoid double-memset of the same allocated memory in dma_pool_alloc() when both DMAPOOL_DEBUG is enabled and init_on_alloc=1. Link: https://lkml.kernel.org/r/20230126215125.4069751-6-kbusch@meta.com Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index ee993bb59fc2..eaed3ffb42aa 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -356,7 +356,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, break; } } - if (!(mem_flags & __GFP_ZERO)) + if (!want_init_on_alloc(mem_flags)) memset(retval, POOL_POISON_ALLOCATED, pool->size); #endif spin_unlock_irqrestore(&pool->lock, flags); -- GitLab From 52e7d56539794b20fb9458c06292dfd24bba6a2d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:19 -0800 Subject: [PATCH 2175/5631] dmapool: move debug code to own functions Clean up the normal path by moving the debug code outside it. Link: https://lkml.kernel.org/r/20230126215125.4069751-7-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 128 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 77 insertions(+), 51 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index eaed3ffb42aa..30b069e99996 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -96,6 +96,78 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha static DEVICE_ATTR_RO(pools); +#ifdef DMAPOOL_DEBUG +static void pool_check_block(struct dma_pool *pool, void *retval, + unsigned int offset, gfp_t mem_flags) +{ + int i; + u8 *data = retval; + /* page->offset is stored in first 4 bytes */ + for (i = sizeof(offset); i < pool->size; i++) { + if (data[i] == POOL_POISON_FREED) + continue; + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + + /* + * Dump the first 4 bytes even if they are not + * POOL_POISON_FREED + */ + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, + data, pool->size, 1); + break; + } + if (!want_init_on_alloc(mem_flags)) + memset(retval, POOL_POISON_ALLOCATED, pool->size); +} + +static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, + void *vaddr, dma_addr_t dma) +{ + unsigned int offset = vaddr - page->vaddr; + unsigned int chain = page->offset; + + if ((dma - page->dma) != offset) { + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + return true; + } + + while (chain < pool->allocation) { + if (chain != offset) { + chain = *(int *)(page->vaddr + chain); + continue; + } + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + return true; + } + memset(vaddr, POOL_POISON_FREED, pool->size); + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +} +#else +static void pool_check_block(struct dma_pool *pool, void *retval, + unsigned int offset, gfp_t mem_flags) + +{ +} + +static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, + void *vaddr, dma_addr_t dma) +{ + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ +} +#endif + /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. * @name: name of pool, for diagnostics @@ -223,9 +295,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); if (page->vaddr) { -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif + pool_init_page(pool, page); pool_initialise_page(pool, page); page->in_use = 0; page->offset = 0; @@ -245,9 +315,7 @@ static void pool_free_page(struct dma_pool *pool, struct dma_page *page) { dma_addr_t dma = page->dma; -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif + pool_init_page(pool, page); dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); list_del(&page->page_list); kfree(page); @@ -336,29 +404,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, page->offset = *(int *)(page->vaddr + offset); retval = offset + page->vaddr; *handle = offset + page->dma; -#ifdef DMAPOOL_DEBUG - { - int i; - u8 *data = retval; - /* page->offset is stored in first 4 bytes */ - for (i = sizeof(page->offset); i < pool->size; i++) { - if (data[i] == POOL_POISON_FREED) - continue; - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); - - /* - * Dump the first 4 bytes even if they are not - * POOL_POISON_FREED - */ - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, - data, pool->size, 1); - break; - } - } - if (!want_init_on_alloc(mem_flags)) - memset(retval, POOL_POISON_ALLOCATED, pool->size); -#endif + pool_check_block(pool, retval, offset, mem_flags); spin_unlock_irqrestore(&pool->lock, flags); if (want_init_on_alloc(mem_flags)) @@ -394,7 +440,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { struct dma_page *page; unsigned long flags; - unsigned int offset; spin_lock_irqsave(&pool->lock, flags); page = pool_find_page(pool, dma); @@ -405,35 +450,16 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) return; } - offset = vaddr - page->vaddr; if (want_init_on_free()) memset(vaddr, 0, pool->size); -#ifdef DMAPOOL_DEBUG - if ((dma - page->dma) != offset) { + if (pool_page_err(pool, page, vaddr, dma)) { spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); return; } - { - unsigned int chain = page->offset; - while (chain < pool->allocation) { - if (chain != offset) { - chain = *(int *)(page->vaddr + chain); - continue; - } - spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, dma %pad already free\n", - __func__, pool->name, &dma); - return; - } - } - memset(vaddr, POOL_POISON_FREED, pool->size); -#endif page->in_use--; *(int *)vaddr = page->offset; - page->offset = offset; + page->offset = vaddr - page->vaddr; /* * Resist a temptation to do * if (!is_page_busy(page)) pool_free_page(pool, page); -- GitLab From 36d1a28921a4012288e17ef5ac98329ce440d410 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:20 -0800 Subject: [PATCH 2176/5631] dmapool: rearrange page alloc failure handling Handle the error in a condition so the good path can be in the normal flow. Link: https://lkml.kernel.org/r/20230126215125.4069751-8-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 30b069e99996..900f2afa363a 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -292,17 +292,19 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) page = kmalloc(sizeof(*page), mem_flags); if (!page) return NULL; + page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); - if (page->vaddr) { - pool_init_page(pool, page); - pool_initialise_page(pool, page); - page->in_use = 0; - page->offset = 0; - } else { + if (!page->vaddr) { kfree(page); - page = NULL; + return NULL; } + + pool_init_page(pool, page); + pool_initialise_page(pool, page); + page->in_use = 0; + page->offset = 0; + return page; } -- GitLab From 2591b516533ba2564f086bd88f1f5e97084e4b1c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:21 -0800 Subject: [PATCH 2177/5631] dmapool: consolidate page initialization Various fields of the dma pool are set in different places. Move it all to one function. Link: https://lkml.kernel.org/r/20230126215125.4069751-9-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 900f2afa363a..9e98065a68b1 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -274,6 +274,9 @@ static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) unsigned int offset = 0; unsigned int next_boundary = pool->boundary; + pool_init_page(pool, page); + page->in_use = 0; + page->offset = 0; do { unsigned int next = offset + pool->size; if (unlikely((next + pool->size) >= next_boundary)) { @@ -300,11 +303,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) return NULL; } - pool_init_page(pool, page); pool_initialise_page(pool, page); - page->in_use = 0; - page->offset = 0; - return page; } -- GitLab From 887aef615818dba18333be6f08de1922a475a15b Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:22 -0800 Subject: [PATCH 2178/5631] dmapool: simplify freeing The actions for busy and not busy are mostly the same, so combine these and remove the unnecessary function. Also, the pool is about to be freed so there's no need to poison the page data since we only check for poison on alloc, which can't be done on a freed pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-10-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 9e98065a68b1..4dea2a0dbd33 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -312,16 +312,6 @@ static inline bool is_page_busy(struct dma_page *page) return page->in_use != 0; } -static void pool_free_page(struct dma_pool *pool, struct dma_page *page) -{ - dma_addr_t dma = page->dma; - - pool_init_page(pool, page); - dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); - list_del(&page->page_list); - kfree(page); -} - /** * dma_pool_destroy - destroys a pool of dma memory blocks. * @pool: dma pool that will be destroyed @@ -349,14 +339,14 @@ void dma_pool_destroy(struct dma_pool *pool) mutex_unlock(&pools_reg_lock); list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { - if (is_page_busy(page)) { + if (!is_page_busy(page)) + dma_free_coherent(pool->dev, pool->allocation, + page->vaddr, page->dma); + else dev_err(pool->dev, "%s %s, %p busy\n", __func__, pool->name, page->vaddr); - /* leak the still-in-use consistent memory */ - list_del(&page->page_list); - kfree(page); - } else - pool_free_page(pool, page); + list_del(&page->page_list); + kfree(page); } kfree(pool); -- GitLab From 9d062a8a4c6d5e6d1591cde41ac844d11f953ad8 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:23 -0800 Subject: [PATCH 2179/5631] dmapool: don't memset on free twice If debug is enabled, dmapool will poison the range, so no need to clear it to 0 immediately before writing over it. Link: https://lkml.kernel.org/r/20230126215125.4069751-11-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 4dea2a0dbd33..21e6d362c726 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -160,6 +160,8 @@ static void pool_check_block(struct dma_pool *pool, void *retval, static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, void *vaddr, dma_addr_t dma) { + if (want_init_on_free()) + memset(vaddr, 0, pool->size); return false; } @@ -441,8 +443,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) return; } - if (want_init_on_free()) - memset(vaddr, 0, pool->size); if (pool_page_err(pool, page, vaddr, dma)) { spin_unlock_irqrestore(&pool->lock, flags); return; -- GitLab From a4de12a032fa6d0670aa0bb43a2bf9f812680d0f Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:24 -0800 Subject: [PATCH 2180/5631] dmapool: link blocks across pages The allocated dmapool pages are never freed for the lifetime of the pool. There is no need for the two level list+stack lookup for finding a free block since nothing is ever removed from the list. Just use a simple stack, reducing time complexity to constant. The implementation inserts the stack linking elements and the dma handle of the block within itself when freed. This means the smallest possible dmapool block is increased to at most 16 bytes to accommodate these fields, but there are no exisiting users requesting a dma pool smaller than that anyway. Removing the list has a significant change in performance. Using the kernel's micro-benchmarking self test: Before: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:57282 dmapool test: size:64 blocks:8192 time:172562 dmapool test: size:256 blocks:8192 time:789247 dmapool test: size:1024 blocks:2048 time:371823 dmapool test: size:4096 blocks:1024 time:362237 After: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:24997 dmapool test: size:64 blocks:8192 time:26584 dmapool test: size:256 blocks:8192 time:33542 dmapool test: size:1024 blocks:2048 time:9022 dmapool test: size:4096 blocks:1024 time:6045 The module test allocates quite a few blocks that may not accurately represent how these pools are used in real life. For a more marco level benchmark, running fio high-depth + high-batched on nvme, this patch shows submission and completion latency reduced by ~100usec each, 1% IOPs improvement, and perf record's time spent in dma_pool_alloc/free were reduced by half. [kbusch@kernel.org: push new blocks in ascending order] Link: https://lkml.kernel.org/r/20230221165400.1595247-1-kbusch@meta.com Link: https://lkml.kernel.org/r/20230126215125.4069751-12-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Tested-by: Bryan O'Donoghue Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 257 ++++++++++++++++++++++++++------------------------- 1 file changed, 130 insertions(+), 127 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 21e6d362c726..d2b0f8fc9649 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -15,7 +15,7 @@ * represented by the 'struct dma_pool' which keeps a doubly-linked list of * allocated pages. Each page in the page_list is split into blocks of at * least 'size' bytes. Free blocks are tracked in an unsorted singly-linked - * list of free blocks within the page. Used blocks aren't tracked, but we + * list of free blocks across all pages. Used blocks aren't tracked, but we * keep a count of how many are currently allocated from each page. */ @@ -40,9 +40,18 @@ #define DMAPOOL_DEBUG 1 #endif +struct dma_block { + struct dma_block *next_block; + dma_addr_t dma; +}; + struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; + struct dma_block *next_block; + size_t nr_blocks; + size_t nr_active; + size_t nr_pages; struct device *dev; unsigned int size; unsigned int allocation; @@ -55,8 +64,6 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ struct list_head page_list; void *vaddr; dma_addr_t dma; - unsigned int in_use; - unsigned int offset; }; static DEFINE_MUTEX(pools_lock); @@ -64,30 +71,18 @@ static DEFINE_MUTEX(pools_reg_lock); static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - int size; - struct dma_page *page; struct dma_pool *pool; + unsigned size; size = sysfs_emit(buf, "poolinfo - 0.1\n"); mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { - unsigned pages = 0; - size_t blocks = 0; - - spin_lock_irq(&pool->lock); - list_for_each_entry(page, &pool->page_list, page_list) { - pages++; - blocks += page->in_use; - } - spin_unlock_irq(&pool->lock); - /* per-pool info, no real statistics yet */ - size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2u\n", - pool->name, blocks, - (size_t) pages * - (pool->allocation / pool->size), - pool->size, pages); + size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2zu\n", + pool->name, pool->nr_active, + pool->nr_blocks, pool->size, + pool->nr_pages); } mutex_unlock(&pools_lock); @@ -97,17 +92,17 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha static DEVICE_ATTR_RO(pools); #ifdef DMAPOOL_DEBUG -static void pool_check_block(struct dma_pool *pool, void *retval, - unsigned int offset, gfp_t mem_flags) +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) { + u8 *data = (void *)block; int i; - u8 *data = retval; - /* page->offset is stored in first 4 bytes */ - for (i = sizeof(offset); i < pool->size; i++) { + + for (i = sizeof(struct dma_block); i < pool->size; i++) { if (data[i] == POOL_POISON_FREED) continue; - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); + dev_err(pool->dev, "%s %s, %p (corrupted)\n", __func__, + pool->name, block); /* * Dump the first 4 bytes even if they are not @@ -117,31 +112,46 @@ static void pool_check_block(struct dma_pool *pool, void *retval, data, pool->size, 1); break; } + if (!want_init_on_alloc(mem_flags)) - memset(retval, POOL_POISON_ALLOCATED, pool->size); + memset(block, POOL_POISON_ALLOCATED, pool->size); } -static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, - void *vaddr, dma_addr_t dma) +static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) { - unsigned int offset = vaddr - page->vaddr; - unsigned int chain = page->offset; + struct dma_page *page; - if ((dma - page->dma) != offset) { - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + list_for_each_entry(page, &pool->page_list, page_list) { + if (dma < page->dma) + continue; + if ((dma - page->dma) < pool->allocation) + return page; + } + return NULL; +} + +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) +{ + struct dma_block *block = pool->next_block; + struct dma_page *page; + + page = pool_find_page(pool, dma); + if (!page) { + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", __func__, pool->name, vaddr, &dma); return true; } - while (chain < pool->allocation) { - if (chain != offset) { - chain = *(int *)(page->vaddr + chain); + while (block) { + if (block != vaddr) { + block = block->next_block; continue; } dev_err(pool->dev, "%s %s, dma %pad already free\n", __func__, pool->name, &dma); return true; } + memset(vaddr, POOL_POISON_FREED, pool->size); return false; } @@ -151,14 +161,12 @@ static void pool_init_page(struct dma_pool *pool, struct dma_page *page) memset(page->vaddr, POOL_POISON_FREED, pool->allocation); } #else -static void pool_check_block(struct dma_pool *pool, void *retval, - unsigned int offset, gfp_t mem_flags) - +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) { } -static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, - void *vaddr, dma_addr_t dma) +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { if (want_init_on_free()) memset(vaddr, 0, pool->size); @@ -170,6 +178,26 @@ static void pool_init_page(struct dma_pool *pool, struct dma_page *page) } #endif +static struct dma_block *pool_block_pop(struct dma_pool *pool) +{ + struct dma_block *block = pool->next_block; + + if (block) { + pool->next_block = block->next_block; + pool->nr_active++; + } + return block; +} + +static void pool_block_push(struct dma_pool *pool, struct dma_block *block, + dma_addr_t dma) +{ + block->dma = dma; + block->next_block = pool->next_block; + pool->next_block = block; +} + + /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. * @name: name of pool, for diagnostics @@ -210,8 +238,8 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, if (size == 0 || size > INT_MAX) return NULL; - else if (size < 4) - size = 4; + if (size < sizeof(struct dma_block)) + size = sizeof(struct dma_block); size = ALIGN(size, align); allocation = max_t(size_t, size, PAGE_SIZE); @@ -223,7 +251,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, boundary = min(boundary, allocation); - retval = kmalloc(sizeof(*retval), GFP_KERNEL); + retval = kzalloc(sizeof(*retval), GFP_KERNEL); if (!retval) return retval; @@ -236,7 +264,6 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->size = size; retval->boundary = boundary; retval->allocation = allocation; - INIT_LIST_HEAD(&retval->pools); /* @@ -273,21 +300,36 @@ EXPORT_SYMBOL(dma_pool_create); static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) { - unsigned int offset = 0; - unsigned int next_boundary = pool->boundary; + unsigned int next_boundary = pool->boundary, offset = 0; + struct dma_block *block, *first = NULL, *last = NULL; pool_init_page(pool, page); - page->in_use = 0; - page->offset = 0; - do { - unsigned int next = offset + pool->size; - if (unlikely((next + pool->size) >= next_boundary)) { - next = next_boundary; + while (offset + pool->size <= pool->allocation) { + if (offset + pool->size > next_boundary) { + offset = next_boundary; next_boundary += pool->boundary; + continue; } - *(int *)(page->vaddr + offset) = next; - offset = next; - } while (offset < pool->allocation); + + block = page->vaddr + offset; + block->dma = page->dma + offset; + block->next_block = NULL; + + if (last) + last->next_block = block; + else + first = block; + last = block; + + offset += pool->size; + pool->nr_blocks++; + } + + last->next_block = pool->next_block; + pool->next_block = first; + + list_add(&page->page_list, &pool->page_list); + pool->nr_pages++; } static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) @@ -305,15 +347,9 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) return NULL; } - pool_initialise_page(pool, page); return page; } -static inline bool is_page_busy(struct dma_page *page) -{ - return page->in_use != 0; -} - /** * dma_pool_destroy - destroys a pool of dma memory blocks. * @pool: dma pool that will be destroyed @@ -325,7 +361,7 @@ static inline bool is_page_busy(struct dma_page *page) void dma_pool_destroy(struct dma_pool *pool) { struct dma_page *page, *tmp; - bool empty = false; + bool empty = false, busy = false; if (unlikely(!pool)) return; @@ -340,13 +376,15 @@ void dma_pool_destroy(struct dma_pool *pool) device_remove_file(pool->dev, &dev_attr_pools); mutex_unlock(&pools_reg_lock); + if (pool->nr_active) { + dev_err(pool->dev, "%s %s busy\n", __func__, pool->name); + busy = true; + } + list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { - if (!is_page_busy(page)) + if (!busy) dma_free_coherent(pool->dev, pool->allocation, page->vaddr, page->dma); - else - dev_err(pool->dev, "%s %s, %p busy\n", __func__, - pool->name, page->vaddr); list_del(&page->page_list); kfree(page); } @@ -368,58 +406,40 @@ EXPORT_SYMBOL(dma_pool_destroy); void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle) { - unsigned long flags; + struct dma_block *block; struct dma_page *page; - unsigned int offset; - void *retval; + unsigned long flags; might_alloc(mem_flags); spin_lock_irqsave(&pool->lock, flags); - list_for_each_entry(page, &pool->page_list, page_list) { - if (page->offset < pool->allocation) - goto ready; - } - - /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */ - spin_unlock_irqrestore(&pool->lock, flags); - - page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); - if (!page) - return NULL; + block = pool_block_pop(pool); + if (!block) { + /* + * pool_alloc_page() might sleep, so temporarily drop + * &pool->lock + */ + spin_unlock_irqrestore(&pool->lock, flags); - spin_lock_irqsave(&pool->lock, flags); + page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); + if (!page) + return NULL; - list_add(&page->page_list, &pool->page_list); - ready: - page->in_use++; - offset = page->offset; - page->offset = *(int *)(page->vaddr + offset); - retval = offset + page->vaddr; - *handle = offset + page->dma; - pool_check_block(pool, retval, offset, mem_flags); + spin_lock_irqsave(&pool->lock, flags); + pool_initialise_page(pool, page); + block = pool_block_pop(pool); + } spin_unlock_irqrestore(&pool->lock, flags); + *handle = block->dma; + pool_check_block(pool, block, mem_flags); if (want_init_on_alloc(mem_flags)) - memset(retval, 0, pool->size); + memset(block, 0, pool->size); - return retval; + return block; } EXPORT_SYMBOL(dma_pool_alloc); -static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) -{ - struct dma_page *page; - - list_for_each_entry(page, &pool->page_list, page_list) { - if (dma < page->dma) - continue; - if ((dma - page->dma) < pool->allocation) - return page; - } - return NULL; -} - /** * dma_pool_free - put block back into dma pool * @pool: the dma pool holding the block @@ -431,31 +451,14 @@ static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) */ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { - struct dma_page *page; + struct dma_block *block = vaddr; unsigned long flags; spin_lock_irqsave(&pool->lock, flags); - page = pool_find_page(pool, dma); - if (!page) { - spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); - return; - } - - if (pool_page_err(pool, page, vaddr, dma)) { - spin_unlock_irqrestore(&pool->lock, flags); - return; + if (!pool_block_err(pool, vaddr, dma)) { + pool_block_push(pool, block, dma); + pool->nr_active--; } - - page->in_use--; - *(int *)vaddr = page->offset; - page->offset = vaddr - page->vaddr; - /* - * Resist a temptation to do - * if (!is_page_busy(page)) pool_free_page(pool, page); - * Better have a few empty pages hang around. - */ spin_unlock_irqrestore(&pool->lock, flags); } EXPORT_SYMBOL(dma_pool_free); -- GitLab From 2d55c16c0c54325bf15286cfa6ba6c268036b9e4 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:25 -0800 Subject: [PATCH 2181/5631] dmapool: create/destroy cleanup Set the 'empty' bool directly from the result of the function that determines its value instead of adding additional logic. Link: https://lkml.kernel.org/r/20230126215125.4069751-13-kbusch@meta.com Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 407 ++++++++++++++++++++++++++------------------------- 1 file changed, 205 insertions(+), 202 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index d2b0f8fc9649..a7eb5d0eb2da 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -15,7 +15,7 @@ * represented by the 'struct dma_pool' which keeps a doubly-linked list of * allocated pages. Each page in the page_list is split into blocks of at * least 'size' bytes. Free blocks are tracked in an unsorted singly-linked - * list of free blocks across all pages. Used blocks aren't tracked, but we + * list of free blocks within the page. Used blocks aren't tracked, but we * keep a count of how many are currently allocated from each page. */ @@ -40,22 +40,13 @@ #define DMAPOOL_DEBUG 1 #endif -struct dma_block { - struct dma_block *next_block; - dma_addr_t dma; -}; - struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; - struct dma_block *next_block; - size_t nr_blocks; - size_t nr_active; - size_t nr_pages; + size_t size; struct device *dev; - unsigned int size; - unsigned int allocation; - unsigned int boundary; + size_t allocation; + size_t boundary; char name[32]; struct list_head pools; }; @@ -64,6 +55,8 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ struct list_head page_list; void *vaddr; dma_addr_t dma; + unsigned int in_use; + unsigned int offset; }; static DEFINE_MUTEX(pools_lock); @@ -71,132 +64,45 @@ static DEFINE_MUTEX(pools_reg_lock); static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct dma_pool *pool; + unsigned temp; unsigned size; - - size = sysfs_emit(buf, "poolinfo - 0.1\n"); - - mutex_lock(&pools_lock); - list_for_each_entry(pool, &dev->dma_pools, pools) { - /* per-pool info, no real statistics yet */ - size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2zu\n", - pool->name, pool->nr_active, - pool->nr_blocks, pool->size, - pool->nr_pages); - } - mutex_unlock(&pools_lock); - - return size; -} - -static DEVICE_ATTR_RO(pools); - -#ifdef DMAPOOL_DEBUG -static void pool_check_block(struct dma_pool *pool, struct dma_block *block, - gfp_t mem_flags) -{ - u8 *data = (void *)block; - int i; - - for (i = sizeof(struct dma_block); i < pool->size; i++) { - if (data[i] == POOL_POISON_FREED) - continue; - dev_err(pool->dev, "%s %s, %p (corrupted)\n", __func__, - pool->name, block); - - /* - * Dump the first 4 bytes even if they are not - * POOL_POISON_FREED - */ - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, - data, pool->size, 1); - break; - } - - if (!want_init_on_alloc(mem_flags)) - memset(block, POOL_POISON_ALLOCATED, pool->size); -} - -static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) -{ + char *next; struct dma_page *page; + struct dma_pool *pool; - list_for_each_entry(page, &pool->page_list, page_list) { - if (dma < page->dma) - continue; - if ((dma - page->dma) < pool->allocation) - return page; - } - return NULL; -} + next = buf; + size = PAGE_SIZE; -static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) -{ - struct dma_block *block = pool->next_block; - struct dma_page *page; + temp = scnprintf(next, size, "poolinfo - 0.1\n"); + size -= temp; + next += temp; - page = pool_find_page(pool, dma); - if (!page) { - dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); - return true; - } + mutex_lock(&pools_lock); + list_for_each_entry(pool, &dev->dma_pools, pools) { + unsigned pages = 0; + unsigned blocks = 0; - while (block) { - if (block != vaddr) { - block = block->next_block; - continue; + spin_lock_irq(&pool->lock); + list_for_each_entry(page, &pool->page_list, page_list) { + pages++; + blocks += page->in_use; } - dev_err(pool->dev, "%s %s, dma %pad already free\n", - __func__, pool->name, &dma); - return true; - } + spin_unlock_irq(&pool->lock); - memset(vaddr, POOL_POISON_FREED, pool->size); - return false; -} - -static void pool_init_page(struct dma_pool *pool, struct dma_page *page) -{ - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -} -#else -static void pool_check_block(struct dma_pool *pool, struct dma_block *block, - gfp_t mem_flags) -{ -} - -static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) -{ - if (want_init_on_free()) - memset(vaddr, 0, pool->size); - return false; -} - -static void pool_init_page(struct dma_pool *pool, struct dma_page *page) -{ -} -#endif - -static struct dma_block *pool_block_pop(struct dma_pool *pool) -{ - struct dma_block *block = pool->next_block; - - if (block) { - pool->next_block = block->next_block; - pool->nr_active++; + /* per-pool info, no real statistics yet */ + temp = scnprintf(next, size, "%-16s %4u %4zu %4zu %2u\n", + pool->name, blocks, + pages * (pool->allocation / pool->size), + pool->size, pages); + size -= temp; + next += temp; } - return block; -} + mutex_unlock(&pools_lock); -static void pool_block_push(struct dma_pool *pool, struct dma_block *block, - dma_addr_t dma) -{ - block->dma = dma; - block->next_block = pool->next_block; - pool->next_block = block; + return PAGE_SIZE - size; } +static DEVICE_ATTR_RO(pools); /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. @@ -228,18 +134,15 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, size_t allocation; bool empty = false; - if (!dev) - return NULL; - if (align == 0) align = 1; else if (align & (align - 1)) return NULL; - if (size == 0 || size > INT_MAX) + if (size == 0) return NULL; - if (size < sizeof(struct dma_block)) - size = sizeof(struct dma_block); + else if (size < 4) + size = 4; size = ALIGN(size, align); allocation = max_t(size_t, size, PAGE_SIZE); @@ -249,9 +152,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, else if ((boundary < size) || (boundary & (boundary - 1))) return NULL; - boundary = min(boundary, allocation); - - retval = kzalloc(sizeof(*retval), GFP_KERNEL); + retval = kmalloc(sizeof(*retval), GFP_KERNEL); if (!retval) return retval; @@ -264,6 +165,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->size = size; retval->boundary = boundary; retval->allocation = allocation; + INIT_LIST_HEAD(&retval->pools); /* @@ -300,36 +202,18 @@ EXPORT_SYMBOL(dma_pool_create); static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) { - unsigned int next_boundary = pool->boundary, offset = 0; - struct dma_block *block, *first = NULL, *last = NULL; + unsigned int offset = 0; + unsigned int next_boundary = pool->boundary; - pool_init_page(pool, page); - while (offset + pool->size <= pool->allocation) { - if (offset + pool->size > next_boundary) { - offset = next_boundary; + do { + unsigned int next = offset + pool->size; + if (unlikely((next + pool->size) >= next_boundary)) { + next = next_boundary; next_boundary += pool->boundary; - continue; } - - block = page->vaddr + offset; - block->dma = page->dma + offset; - block->next_block = NULL; - - if (last) - last->next_block = block; - else - first = block; - last = block; - - offset += pool->size; - pool->nr_blocks++; - } - - last->next_block = pool->next_block; - pool->next_block = first; - - list_add(&page->page_list, &pool->page_list); - pool->nr_pages++; + *(int *)(page->vaddr + offset) = next; + offset = next; + } while (offset < pool->allocation); } static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) @@ -339,17 +223,39 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) page = kmalloc(sizeof(*page), mem_flags); if (!page) return NULL; - page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); - if (!page->vaddr) { + if (page->vaddr) { +#ifdef DMAPOOL_DEBUG + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +#endif + pool_initialise_page(pool, page); + page->in_use = 0; + page->offset = 0; + } else { kfree(page); - return NULL; + page = NULL; } - return page; } +static inline bool is_page_busy(struct dma_page *page) +{ + return page->in_use != 0; +} + +static void pool_free_page(struct dma_pool *pool, struct dma_page *page) +{ + dma_addr_t dma = page->dma; + +#ifdef DMAPOOL_DEBUG + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +#endif + dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); + list_del(&page->page_list); + kfree(page); +} + /** * dma_pool_destroy - destroys a pool of dma memory blocks. * @pool: dma pool that will be destroyed @@ -361,7 +267,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) void dma_pool_destroy(struct dma_pool *pool) { struct dma_page *page, *tmp; - bool empty = false, busy = false; + bool empty = false; if (unlikely(!pool)) return; @@ -369,24 +275,26 @@ void dma_pool_destroy(struct dma_pool *pool) mutex_lock(&pools_reg_lock); mutex_lock(&pools_lock); list_del(&pool->pools); - if (list_empty(&pool->dev->dma_pools)) + if (pool->dev && list_empty(&pool->dev->dma_pools)) empty = true; mutex_unlock(&pools_lock); if (empty) device_remove_file(pool->dev, &dev_attr_pools); mutex_unlock(&pools_reg_lock); - if (pool->nr_active) { - dev_err(pool->dev, "%s %s busy\n", __func__, pool->name); - busy = true; - } - list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { - if (!busy) - dma_free_coherent(pool->dev, pool->allocation, - page->vaddr, page->dma); - list_del(&page->page_list); - kfree(page); + if (is_page_busy(page)) { + if (pool->dev) + dev_err(pool->dev, "%s %s, %p busy\n", __func__, + pool->name, page->vaddr); + else + pr_err("%s %s, %p busy\n", __func__, + pool->name, page->vaddr); + /* leak the still-in-use consistent memory */ + list_del(&page->page_list); + kfree(page); + } else + pool_free_page(pool, page); } kfree(pool); @@ -406,40 +314,84 @@ EXPORT_SYMBOL(dma_pool_destroy); void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle) { - struct dma_block *block; - struct dma_page *page; unsigned long flags; + struct dma_page *page; + size_t offset; + void *retval; might_alloc(mem_flags); spin_lock_irqsave(&pool->lock, flags); - block = pool_block_pop(pool); - if (!block) { - /* - * pool_alloc_page() might sleep, so temporarily drop - * &pool->lock - */ - spin_unlock_irqrestore(&pool->lock, flags); + list_for_each_entry(page, &pool->page_list, page_list) { + if (page->offset < pool->allocation) + goto ready; + } - page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); - if (!page) - return NULL; + /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */ + spin_unlock_irqrestore(&pool->lock, flags); - spin_lock_irqsave(&pool->lock, flags); - pool_initialise_page(pool, page); - block = pool_block_pop(pool); + page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); + if (!page) + return NULL; + + spin_lock_irqsave(&pool->lock, flags); + + list_add(&page->page_list, &pool->page_list); + ready: + page->in_use++; + offset = page->offset; + page->offset = *(int *)(page->vaddr + offset); + retval = offset + page->vaddr; + *handle = offset + page->dma; +#ifdef DMAPOOL_DEBUG + { + int i; + u8 *data = retval; + /* page->offset is stored in first 4 bytes */ + for (i = sizeof(page->offset); i < pool->size; i++) { + if (data[i] == POOL_POISON_FREED) + continue; + if (pool->dev) + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + else + pr_err("%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + + /* + * Dump the first 4 bytes even if they are not + * POOL_POISON_FREED + */ + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, + data, pool->size, 1); + break; + } } + if (!(mem_flags & __GFP_ZERO)) + memset(retval, POOL_POISON_ALLOCATED, pool->size); +#endif spin_unlock_irqrestore(&pool->lock, flags); - *handle = block->dma; - pool_check_block(pool, block, mem_flags); if (want_init_on_alloc(mem_flags)) - memset(block, 0, pool->size); + memset(retval, 0, pool->size); - return block; + return retval; } EXPORT_SYMBOL(dma_pool_alloc); +static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) +{ + struct dma_page *page; + + list_for_each_entry(page, &pool->page_list, page_list) { + if (dma < page->dma) + continue; + if ((dma - page->dma) < pool->allocation) + return page; + } + return NULL; +} + /** * dma_pool_free - put block back into dma pool * @pool: the dma pool holding the block @@ -451,14 +403,65 @@ EXPORT_SYMBOL(dma_pool_alloc); */ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { - struct dma_block *block = vaddr; + struct dma_page *page; unsigned long flags; + unsigned int offset; spin_lock_irqsave(&pool->lock, flags); - if (!pool_block_err(pool, vaddr, dma)) { - pool_block_push(pool, block, dma); - pool->nr_active--; + page = pool_find_page(pool, dma); + if (!page) { + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); + else + pr_err("%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); + return; + } + + offset = vaddr - page->vaddr; + if (want_init_on_free()) + memset(vaddr, 0, pool->size); +#ifdef DMAPOOL_DEBUG + if ((dma - page->dma) != offset) { + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + else + pr_err("%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + return; } + { + unsigned int chain = page->offset; + while (chain < pool->allocation) { + if (chain != offset) { + chain = *(int *)(page->vaddr + chain); + continue; + } + spin_unlock_irqrestore(&pool->lock, flags); + if (pool->dev) + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + else + pr_err("%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + return; + } + } + memset(vaddr, POOL_POISON_FREED, pool->size); +#endif + + page->in_use--; + *(int *)vaddr = page->offset; + page->offset = offset; + /* + * Resist a temptation to do + * if (!is_page_busy(page)) pool_free_page(pool, page); + * Better have a few empty pages hang around. + */ spin_unlock_irqrestore(&pool->lock, flags); } EXPORT_SYMBOL(dma_pool_free); -- GitLab From 1fb130b226a6385362899381e0025ba413cb27e6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:04 +0100 Subject: [PATCH 2182/5631] mm: don't look at xarray value entries in split_huge_pages_in_file Patch series "return an ERR_PTR from __filemap_get_folio", v3. __filemap_get_folio and its wrappers can return NULL for three different conditions, which in some cases requires the caller to reverse engineer the decision making. This is fixed by returning an ERR_PTR instead of NULL and thus transporting the reason for the failure. But to make that work we first need to ensure that no xa_value special case is returned and thus return the FGP_ENTRY flag. It turns out that flag is barely used and can usually be deal with in a better way. This patch (of 7): split_huge_pages_in_file never wants to do anything with the special value enties. Switch to using filemap_get_folio to not even see them. Link: https://lkml.kernel.org/r/20230307143410.28031-1-hch@lst.de Link: https://lkml.kernel.org/r/20230307143410.28031-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Cc: Hugh Dickins Cc: Andreas Gruenbacher Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- mm/huge_memory.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index cbf095e7f059..70008dd7f215 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3089,11 +3089,10 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, mapping = candidate->f_mapping; for (index = off_start; index < off_end; index += nr_pages) { - struct folio *folio = __filemap_get_folio(mapping, index, - FGP_ENTRY, 0); + struct folio *folio = filemap_get_folio(mapping, index); nr_pages = 1; - if (xa_is_value(folio) || !folio) + if (!folio) continue; if (!folio_test_large(folio)) -- GitLab From 263e721e3ba1f3b42ad61aed3d504f3c8c9c0eb6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:05 +0100 Subject: [PATCH 2183/5631] mm: make mapping_get_entry available outside of filemap.c mapping_get_entry is useful for page cache API users that need to know about xa_value internals. Rename it and make it available in pagemap.h. Link: https://lkml.kernel.org/r/20230307143410.28031-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 1 + mm/filemap.c | 6 +++--- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 853184a46411..bcfd798ce0b9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -507,6 +507,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_ENTRY 0x00000080 #define FGP_STABLE 0x00000100 +void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, diff --git a/mm/filemap.c b/mm/filemap.c index 2723104cc06a..a674108a4d52 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1836,7 +1836,7 @@ EXPORT_SYMBOL(page_cache_prev_miss); */ /* - * mapping_get_entry - Get a page cache entry. + * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * @@ -1847,7 +1847,7 @@ EXPORT_SYMBOL(page_cache_prev_miss); * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ -static void *mapping_get_entry(struct address_space *mapping, pgoff_t index) +void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; @@ -1917,7 +1917,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, struct folio *folio; repeat: - folio = mapping_get_entry(mapping, index); + folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) { if (fgp_flags & FGP_ENTRY) return folio; -- GitLab From 097b3e59b25e61481d93c6da5472319c0b7249e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:06 +0100 Subject: [PATCH 2184/5631] mm: use filemap_get_entry in filemap_get_incore_folio filemap_get_incore_folio wants to look at the details of xa_is_value entries, but doesn't need any of the other logic in filemap_get_folio. Switch it to use the lower-level filemap_get_entry interface. Link: https://lkml.kernel.org/r/20230307143410.28031-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- mm/swap_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/swap_state.c b/mm/swap_state.c index 7a003d8abb37..92234f4b51d2 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -386,7 +386,7 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping, { swp_entry_t swp; struct swap_info_struct *si; - struct folio *folio = __filemap_get_folio(mapping, index, FGP_ENTRY, 0); + struct folio *folio = filemap_get_entry(mapping, index); if (!xa_is_value(folio)) goto out; -- GitLab From 81914aff84e83561ab556dab380e7bbe9c2102b1 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 19 Mar 2023 22:19:21 -0700 Subject: [PATCH 2185/5631] shmem: shmem_get_partial_folio use filemap_get_entry To avoid use of the FGP_ENTRY flag, adapt shmem_get_partial_folio() to use filemap_get_entry() and folio_lock() instead of __filemap_get_folio(). Update "page" in the comments there to "folio". Link: https://lkml.kernel.org/r/9d1aaa4-1337-fb81-6f37-74ebc96f9ef@google.com Signed-off-by: Hugh Dickins Cc: Andreas Gruenbacher Cc: Christoph Hellwig Cc: Matthew Wilcox (Oracle) Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- mm/shmem.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 787e83791eb5..1549866c208f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -885,14 +885,21 @@ static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) /* * At first avoid shmem_get_folio(,,,SGP_READ): that fails - * beyond i_size, and reports fallocated pages as holes. + * beyond i_size, and reports fallocated folios as holes. */ - folio = __filemap_get_folio(inode->i_mapping, index, - FGP_ENTRY | FGP_LOCK, 0); - if (!xa_is_value(folio)) + folio = filemap_get_entry(inode->i_mapping, index); + if (!folio) return folio; + if (!xa_is_value(folio)) { + folio_lock(folio); + if (folio->mapping == inode->i_mapping) + return folio; + /* The folio has been swapped out */ + folio_unlock(folio); + folio_put(folio); + } /* - * But read a page back from swap if any of it is within i_size + * But read a folio back from swap if any of it is within i_size * (although in some cases this is just a waste of time). */ folio = NULL; -- GitLab From aaeb94eb86c58a89e70ae2dda46e137a72508ae3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:08 +0100 Subject: [PATCH 2186/5631] shmem: open code the page cache lookup in shmem_get_folio_gfp Use the very low level filemap_get_entry helper to look up the entry in the xarray, and then: - don't bother locking the folio if only doing a userfault notification - open code locking the page and checking for truncation in a related code block This will allow to eventually remove the FGP_ENTRY flag. [hughd@google.com: adjust the new comment line] Link: https://lkml.kernel.org/r/af178ebb-1076-a38c-1dc1-2a37ccce4a3@google.com Link: https://lkml.kernel.org/r/20230307143410.28031-6-hch@lst.de Signed-off-by: Christoph Hellwig Signed-off-by: Hugh Dickins Acked-by: Hugh Dickins Cc: Andreas Gruenbacher Cc: Matthew Wilcox (Oracle) Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- mm/shmem.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 1549866c208f..93cb39852a16 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1880,12 +1880,10 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : NULL; - folio = __filemap_get_folio(mapping, index, FGP_ENTRY | FGP_LOCK, 0); + folio = filemap_get_entry(mapping, index); if (folio && vma && userfaultfd_minor(vma)) { - if (!xa_is_value(folio)) { - folio_unlock(folio); + if (!xa_is_value(folio)) folio_put(folio); - } *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); return 0; } @@ -1901,6 +1899,14 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, } if (folio) { + folio_lock(folio); + + /* Has the folio been truncated or swapped out? */ + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); + goto repeat; + } if (sgp == SGP_WRITE) folio_mark_accessed(folio); if (folio_test_uptodate(folio)) -- GitLab From 48c9d11375fc66f1e59d0e9b27d121e015a50904 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:09 +0100 Subject: [PATCH 2187/5631] mm: remove FGP_ENTRY FGP_ENTRY is unused now, so remove it. Link: https://lkml.kernel.org/r/20230307143410.28031-7-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Ryusuke Konishi Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 3 +-- mm/filemap.c | 7 +------ mm/folio-compat.c | 4 ++-- 3 files changed, 4 insertions(+), 10 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bcfd798ce0b9..306a0f63cea8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -504,8 +504,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 -#define FGP_ENTRY 0x00000080 -#define FGP_STABLE 0x00000100 +#define FGP_STABLE 0x00000080 void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, diff --git a/mm/filemap.c b/mm/filemap.c index a674108a4d52..ac161b50f5bc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1891,8 +1891,6 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) * * * %FGP_ACCESSED - The folio will be marked accessed. * * %FGP_LOCK - The folio is returned locked. - * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it - * instead of allocating a new folio to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. @@ -1918,11 +1916,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, repeat: folio = filemap_get_entry(mapping, index); - if (xa_is_value(folio)) { - if (fgp_flags & FGP_ENTRY) - return folio; + if (xa_is_value(folio)) folio = NULL; - } if (!folio) goto no_page; diff --git a/mm/folio-compat.c b/mm/folio-compat.c index cabcd1de9ecb..1754daa85d35 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -97,8 +97,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, struct folio *folio; folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); - if (!folio || xa_is_value(folio)) - return &folio->page; + if (!folio) + return NULL; return folio_file_page(folio, index); } EXPORT_SYMBOL(pagecache_get_page); -- GitLab From 66dabbb65d673aef40dd17bf62c042be8f6d4a4b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Mar 2023 15:34:10 +0100 Subject: [PATCH 2188/5631] mm: return an ERR_PTR from __filemap_get_folio Instead of returning NULL for all errors, distinguish between: - no entry found and not asked to allocated (-ENOENT) - failed to allocate memory (-ENOMEM) - would block (-EAGAIN) so that callers don't have to guess the error based on the passed in flags. Also pass through the error through the direct callers: filemap_get_folio, filemap_lock_folio filemap_grab_folio and filemap_get_incore_folio. [hch@lst.de: fix null-pointer deref] Link: https://lkml.kernel.org/r/20230310070023.GA13563@lst.de Link: https://lkml.kernel.org/r/20230310043137.GA1624890@u2004 Link: https://lkml.kernel.org/r/20230307143410.28031-8-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Ryusuke Konishi [nilfs2] Cc: Andreas Gruenbacher Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- fs/afs/dir.c | 10 +++++----- fs/afs/dir_edit.c | 2 +- fs/afs/write.c | 4 ++-- fs/ext4/inode.c | 2 +- fs/ext4/move_extent.c | 8 ++++---- fs/hugetlbfs/inode.c | 2 +- fs/iomap/buffered-io.c | 11 ++--------- fs/netfs/buffered_read.c | 4 ++-- fs/nfs/file.c | 4 ++-- fs/nilfs2/page.c | 6 +++--- include/linux/pagemap.h | 11 ++++++----- mm/filemap.c | 14 ++++++++------ mm/folio-compat.c | 2 +- mm/huge_memory.c | 2 +- mm/hugetlb.c | 6 ++++-- mm/memcontrol.c | 2 +- mm/mincore.c | 2 +- mm/shmem.c | 4 ++-- mm/swap_state.c | 17 ++++++++++------- mm/swapfile.c | 4 ++-- mm/truncate.c | 15 ++++++++------- 21 files changed, 67 insertions(+), 65 deletions(-) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 82690d1dd49a..f92b9e62d567 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -319,16 +319,16 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) struct folio *folio; folio = filemap_get_folio(mapping, i); - if (!folio) { + if (IS_ERR(folio)) { if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_stat_v(dvnode, n_inval); - - ret = -ENOMEM; folio = __filemap_get_folio(mapping, i, FGP_LOCK | FGP_CREAT, mapping->gfp_mask); - if (!folio) + if (IS_ERR(folio)) { + ret = PTR_ERR(folio); goto error; + } folio_attach_private(folio, (void *)1); folio_unlock(folio); } @@ -524,7 +524,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, */ folio = __filemap_get_folio(dir->i_mapping, ctx->pos / PAGE_SIZE, FGP_ACCESSED, 0); - if (!folio) { + if (IS_ERR(folio)) { ret = afs_bad(dvnode, afs_file_error_dir_missing_page); break; } diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 0ab7752d1b75..f0eddccbdd95 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -115,7 +115,7 @@ static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping->gfp_mask); - if (!folio) + if (IS_ERR(folio)) clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); else if (folio && !folio_test_private(folio)) folio_attach_private(folio, (void *)1); diff --git a/fs/afs/write.c b/fs/afs/write.c index 571f3b9a417e..c822d6006033 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -232,7 +232,7 @@ static void afs_kill_pages(struct address_space *mapping, _debug("kill %lx (to %lx)", index, last); folio = filemap_get_folio(mapping, index); - if (!folio) { + if (IS_ERR(folio)) { next = index + 1; continue; } @@ -270,7 +270,7 @@ static void afs_redirty_pages(struct writeback_control *wbc, _debug("redirty %llx @%llx", len, start); folio = filemap_get_folio(mapping, index); - if (!folio) { + if (IS_ERR(folio)) { next = index + 1; continue; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bf0b7dea4900..d7973743417b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5395,7 +5395,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) while (1) { struct folio *folio = filemap_lock_folio(inode->i_mapping, inode->i_size >> PAGE_SHIFT); - if (!folio) + if (IS_ERR(folio)) return; ret = __ext4_journalled_invalidate_folio(folio, offset, folio_size(folio) - offset); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 2de9829aed63..7bf6d069199c 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -141,18 +141,18 @@ mext_folio_double_lock(struct inode *inode1, struct inode *inode2, flags = memalloc_nofs_save(); folio[0] = __filemap_get_folio(mapping[0], index1, fgp_flags, mapping_gfp_mask(mapping[0])); - if (!folio[0]) { + if (IS_ERR(folio[0])) { memalloc_nofs_restore(flags); - return -ENOMEM; + return PTR_ERR(folio[0]); } folio[1] = __filemap_get_folio(mapping[1], index2, fgp_flags, mapping_gfp_mask(mapping[1])); memalloc_nofs_restore(flags); - if (!folio[1]) { + if (IS_ERR(folio[1])) { folio_unlock(folio[0]); folio_put(folio[0]); - return -ENOMEM; + return PTR_ERR(folio[1]); } /* * __filemap_get_folio() may not wait on folio's writeback if diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9062da6da567..702d79639c0d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -697,7 +697,7 @@ static void hugetlbfs_zero_partial_page(struct hstate *h, struct folio *folio; folio = filemap_lock_folio(mapping, idx); - if (!folio) + if (IS_ERR(folio)) return; start = start & ~huge_page_mask(h); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 6f4c97a6d7e9..96bb56c203f4 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -468,19 +468,12 @@ EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate); struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos) { unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS; - struct folio *folio; if (iter->flags & IOMAP_NOWAIT) fgp |= FGP_NOWAIT; - folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, + return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT, fgp, mapping_gfp_mask(iter->inode->i_mapping)); - if (folio) - return folio; - - if (iter->flags & IOMAP_NOWAIT) - return ERR_PTR(-EAGAIN); - return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(iomap_get_folio); @@ -911,7 +904,7 @@ static int iomap_write_delalloc_scan(struct inode *inode, /* grab locked page */ folio = filemap_lock_folio(inode->i_mapping, start_byte >> PAGE_SHIFT); - if (!folio) { + if (IS_ERR(folio)) { start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) + PAGE_SIZE; continue; diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7679a68e8193..209726a9cfdb 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -350,8 +350,8 @@ int netfs_write_begin(struct netfs_inode *ctx, retry: folio = __filemap_get_folio(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); - if (!folio) - return -ENOMEM; + if (IS_ERR(folio)) + return PTR_ERR(folio); if (ctx->ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 893625eacab9..1d03406e6c03 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -336,8 +336,8 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, start: folio = nfs_folio_grab_cache_write_begin(mapping, pos >> PAGE_SHIFT); - if (!folio) - return -ENOMEM; + if (IS_ERR(folio)) + return PTR_ERR(folio); *pagep = &folio->page; ret = nfs_flush_incompatible(file, folio); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 41ccd43cd979..5cf30827f244 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -259,10 +259,10 @@ int nilfs_copy_dirty_pages(struct address_space *dmap, NILFS_PAGE_BUG(&folio->page, "inconsistent dirty state"); dfolio = filemap_grab_folio(dmap, folio->index); - if (unlikely(!dfolio)) { + if (unlikely(IS_ERR(dfolio))) { /* No empty page is added to the page cache */ - err = -ENOMEM; folio_unlock(folio); + err = PTR_ERR(dfolio); break; } if (unlikely(!folio_buffers(folio))) @@ -311,7 +311,7 @@ void nilfs_copy_back_pages(struct address_space *dmap, folio_lock(folio); dfolio = filemap_lock_folio(dmap, index); - if (dfolio) { + if (!IS_ERR(dfolio)) { /* overwrite existing folio in the destination cache */ WARN_ON(folio_test_dirty(dfolio)); nilfs_copy_page(&dfolio->page, &folio->page, 0); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 306a0f63cea8..fdcd595d2294 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -520,7 +520,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * - * Otherwise, %NULL is returned. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) @@ -537,8 +538,8 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, * present, it is returned locked with an increased refcount. * * Context: May sleep. - * Return: A folio or %NULL if there is no folio in the cache for this - * index. Will not return a shadow, swap or DAX entry. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) @@ -555,8 +556,8 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, * a new folio is created. The folio is locked, marked as accessed, and * returned. * - * Return: A found or created folio. NULL if no folio is found and failed to - * create a folio. + * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found + * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) diff --git a/mm/filemap.c b/mm/filemap.c index ac161b50f5bc..a34abfe8c654 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1907,7 +1907,7 @@ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) * * If there is a page cache page, it is returned with an increased refcount. * - * Return: The found folio or %NULL otherwise. + * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp) @@ -1925,7 +1925,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); - return NULL; + return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); @@ -1964,7 +1964,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, folio = filemap_alloc_folio(gfp, 0); if (!folio) - return NULL; + return ERR_PTR(-ENOMEM); if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; @@ -1989,6 +1989,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, folio_unlock(folio); } + if (!folio) + return ERR_PTR(-ENOENT); return folio; } EXPORT_SYMBOL(__filemap_get_folio); @@ -3258,7 +3260,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); - if (likely(folio)) { + if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. @@ -3287,7 +3289,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); - if (!folio) { + if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); @@ -3638,7 +3640,7 @@ static struct folio *do_read_cache_folio(struct address_space *mapping, filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); - if (!folio) { + if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, 0); if (!folio) return ERR_PTR(-ENOMEM); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 1754daa85d35..2511c055a35f 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -97,7 +97,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, struct folio *folio; folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); - if (!folio) + if (IS_ERR(folio)) return NULL; return folio_file_page(folio, index); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 70008dd7f215..2d860e70fe88 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3092,7 +3092,7 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, struct folio *folio = filemap_get_folio(mapping, index); nr_pages = 1; - if (!folio) + if (IS_ERR(folio)) continue; if (!folio_test_large(folio)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 07abcb6eb203..712e32b38295 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5780,7 +5780,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, */ new_folio = false; folio = filemap_lock_folio(mapping, idx); - if (!folio) { + if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; @@ -6071,6 +6071,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, vma_end_reservation(h, vma, haddr); pagecache_folio = filemap_lock_folio(mapping, idx); + if (IS_ERR(pagecache_folio)) + pagecache_folio = NULL; } ptl = huge_pte_lock(h, mm, ptep); @@ -6182,7 +6184,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, if (is_continue) { ret = -EFAULT; folio = filemap_lock_folio(mapping, idx); - if (!folio) + if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*pagep) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 13ec89c45389..0524add35cae 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5705,7 +5705,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, /* shmem/tmpfs may report page out on swap: account for that too. */ index = linear_page_index(vma, addr); folio = filemap_get_incore_folio(vma->vm_file->f_mapping, index); - if (!folio) + if (IS_ERR(folio)) return NULL; return folio_file_page(folio, index); } diff --git a/mm/mincore.c b/mm/mincore.c index d359650b0f75..2d5be013a25a 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -61,7 +61,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t index) * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ folio = filemap_get_incore_folio(mapping, index); - if (folio) { + if (!IS_ERR(folio)) { present = folio_test_uptodate(folio); folio_put(folio); } diff --git a/mm/shmem.c b/mm/shmem.c index 93cb39852a16..fa6e38f2f55f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -605,7 +605,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, index = (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT; folio = filemap_get_folio(inode->i_mapping, index); - if (!folio) + if (IS_ERR(folio)) goto drop; /* No huge page at the end of the file: nothing to split */ @@ -3214,7 +3214,7 @@ static const char *shmem_get_link(struct dentry *dentry, if (!dentry) { folio = filemap_get_folio(inode->i_mapping, 0); - if (!folio) + if (IS_ERR(folio)) return ERR_PTR(-ECHILD); if (PageHWPoison(folio_page(folio, 0)) || !folio_test_uptodate(folio)) { diff --git a/mm/swap_state.c b/mm/swap_state.c index 92234f4b51d2..b76a65ac28b3 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -336,7 +336,7 @@ struct folio *swap_cache_get_folio(swp_entry_t entry, struct folio *folio; folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry)); - if (folio) { + if (!IS_ERR(folio)) { bool vma_ra = swap_use_vma_readahead(); bool readahead; @@ -366,6 +366,8 @@ struct folio *swap_cache_get_folio(swp_entry_t entry, if (!vma || !vma_ra) atomic_inc(&swapin_readahead_hits); } + } else { + folio = NULL; } return folio; @@ -388,23 +390,24 @@ struct folio *filemap_get_incore_folio(struct address_space *mapping, struct swap_info_struct *si; struct folio *folio = filemap_get_entry(mapping, index); + if (!folio) + return ERR_PTR(-ENOENT); if (!xa_is_value(folio)) - goto out; + return folio; if (!shmem_mapping(mapping)) - return NULL; + return ERR_PTR(-ENOENT); swp = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (non_swap_entry(swp)) - return NULL; + return ERR_PTR(-ENOENT); /* Prevent swapoff from happening to us */ si = get_swap_device(swp); if (!si) - return NULL; + return ERR_PTR(-ENOENT); index = swp_offset(swp); folio = filemap_get_folio(swap_address_space(swp), index); put_swap_device(si); -out: return folio; } @@ -431,7 +434,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); - if (folio) + if (!IS_ERR(folio)) return folio_file_page(folio, swp_offset(entry)); /* diff --git a/mm/swapfile.c b/mm/swapfile.c index c1b97436f811..00b3e46becad 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -136,7 +136,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si, int ret = 0; folio = filemap_get_folio(swap_address_space(entry), offset); - if (!folio) + if (IS_ERR(folio)) return 0; /* * When this function is called from scan_swap_map_slots() and it's @@ -2095,7 +2095,7 @@ static int try_to_unuse(unsigned int type) entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), i); - if (!folio) + if (IS_ERR(folio)) continue; /* diff --git a/mm/truncate.c b/mm/truncate.c index 7b4ea4c4a46b..86de31ed4d32 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -375,7 +375,7 @@ void truncate_inode_pages_range(struct address_space *mapping, same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = __filemap_get_folio(mapping, lstart >> PAGE_SHIFT, FGP_LOCK, 0); - if (folio) { + if (!IS_ERR(folio)) { same_folio = lend < folio_pos(folio) + folio_size(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio->index + folio_nr_pages(folio); @@ -387,14 +387,15 @@ void truncate_inode_pages_range(struct address_space *mapping, folio = NULL; } - if (!same_folio) + if (!same_folio) { folio = __filemap_get_folio(mapping, lend >> PAGE_SHIFT, FGP_LOCK, 0); - if (folio) { - if (!truncate_inode_partial_folio(folio, lstart, lend)) - end = folio->index; - folio_unlock(folio); - folio_put(folio); + if (!IS_ERR(folio)) { + if (!truncate_inode_partial_folio(folio, lstart, lend)) + end = folio->index; + folio_unlock(folio); + folio_put(folio); + } } index = start; -- GitLab From e34f1e2ee0982a0ebed9e71f18d1b9529df43cd5 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 11 Mar 2023 00:43:29 +0100 Subject: [PATCH 2189/5631] kasan: drop empty tagging-related defines mm/kasan/kasan.h provides a number of empty defines for a few arch-specific tagging-related routines, in case the architecture code didn't define them. The original idea was to simplify integration in case another architecture starts supporting memory tagging. However, right now, if any of those routines are not provided by an architecture, Hardware Tag-Based KASAN won't work. Drop the empty defines, as it would be better to get compiler errors rather than runtime crashes when adding support for a new architecture. Also drop empty hw_enable_tagging_sync/async/asymm defines for !CONFIG_KASAN_HW_TAGS case, as those are only used in mm/kasan/hw_tags.c. Link: https://lkml.kernel.org/r/bc919c144f8684a7fd9ba70c356ac2a75e775e29.1678491668.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas [arm64] Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Marco Elver Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Weizhao Ouyang Cc: Will Deacon Signed-off-by: Andrew Morton --- mm/kasan/kasan.h | 26 -------------------------- 1 file changed, 26 deletions(-) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index a61eeee3095a..b1895526d02f 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -395,28 +395,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifdef CONFIG_KASAN_HW_TAGS -#ifndef arch_enable_tagging_sync -#define arch_enable_tagging_sync() -#endif -#ifndef arch_enable_tagging_async -#define arch_enable_tagging_async() -#endif -#ifndef arch_enable_tagging_asymm -#define arch_enable_tagging_asymm() -#endif -#ifndef arch_force_async_tag_fault -#define arch_force_async_tag_fault() -#endif -#ifndef arch_get_random_tag -#define arch_get_random_tag() (0xFF) -#endif -#ifndef arch_get_mem_tag -#define arch_get_mem_tag(addr) (0xFF) -#endif -#ifndef arch_set_mem_tag_range -#define arch_set_mem_tag_range(addr, size, tag, init) ((void *)(addr)) -#endif - #define hw_enable_tagging_sync() arch_enable_tagging_sync() #define hw_enable_tagging_async() arch_enable_tagging_async() #define hw_enable_tagging_asymm() arch_enable_tagging_asymm() @@ -430,10 +408,6 @@ void kasan_enable_tagging(void); #else /* CONFIG_KASAN_HW_TAGS */ -#define hw_enable_tagging_sync() -#define hw_enable_tagging_async() -#define hw_enable_tagging_asymm() - static inline void kasan_enable_tagging(void) { } #endif /* CONFIG_KASAN_HW_TAGS */ -- GitLab From 0eafff1c5a56893ca9708fb8ff1327a738b242e9 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 11 Mar 2023 00:43:30 +0100 Subject: [PATCH 2190/5631] kasan, arm64: rename tagging-related routines Rename arch_enable_tagging_sync/async/asymm to arch_enable_tag_checks_sync/async/asymm, as the new name better reflects their function. Also rename kasan_enable_tagging to kasan_enable_hw_tags for the same reason. Link: https://lkml.kernel.org/r/069ef5b77715c1ac8d69b186725576c32b149491.1678491668.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Marco Elver Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Weizhao Ouyang Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/memory.h | 6 +++--- mm/kasan/hw_tags.c | 12 ++++++------ mm/kasan/kasan.h | 10 +++++----- mm/kasan/kasan_test.c | 2 +- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 78e5163836a0..faf42bff9a60 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -261,9 +261,9 @@ static inline const void *__tag_set(const void *addr, u8 tag) } #ifdef CONFIG_KASAN_HW_TAGS -#define arch_enable_tagging_sync() mte_enable_kernel_sync() -#define arch_enable_tagging_async() mte_enable_kernel_async() -#define arch_enable_tagging_asymm() mte_enable_kernel_asymm() +#define arch_enable_tag_checks_sync() mte_enable_kernel_sync() +#define arch_enable_tag_checks_async() mte_enable_kernel_async() +#define arch_enable_tag_checks_asymm() mte_enable_kernel_asymm() #define arch_force_async_tag_fault() mte_check_tfsr_exit() #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index bb4f56e5bdec..f98b9f4d9d3e 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -205,7 +205,7 @@ void kasan_init_hw_tags_cpu(void) * Enable async or asymm modes only when explicitly requested * through the command line. */ - kasan_enable_tagging(); + kasan_enable_hw_tags(); } /* kasan_init_hw_tags() is called once on boot CPU. */ @@ -373,19 +373,19 @@ void __kasan_poison_vmalloc(const void *start, unsigned long size) #endif -void kasan_enable_tagging(void) +void kasan_enable_hw_tags(void) { if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC) - hw_enable_tagging_async(); + hw_enable_tag_checks_async(); else if (kasan_arg_mode == KASAN_ARG_MODE_ASYMM) - hw_enable_tagging_asymm(); + hw_enable_tag_checks_asymm(); else - hw_enable_tagging_sync(); + hw_enable_tag_checks_sync(); } #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) -EXPORT_SYMBOL_GPL(kasan_enable_tagging); +EXPORT_SYMBOL_GPL(kasan_enable_hw_tags); void kasan_force_async_fault(void) { diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index b1895526d02f..a1613f5d7608 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -395,20 +395,20 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #ifdef CONFIG_KASAN_HW_TAGS -#define hw_enable_tagging_sync() arch_enable_tagging_sync() -#define hw_enable_tagging_async() arch_enable_tagging_async() -#define hw_enable_tagging_asymm() arch_enable_tagging_asymm() +#define hw_enable_tag_checks_sync() arch_enable_tag_checks_sync() +#define hw_enable_tag_checks_async() arch_enable_tag_checks_async() +#define hw_enable_tag_checks_asymm() arch_enable_tag_checks_asymm() #define hw_force_async_tag_fault() arch_force_async_tag_fault() #define hw_get_random_tag() arch_get_random_tag() #define hw_get_mem_tag(addr) arch_get_mem_tag(addr) #define hw_set_mem_tag_range(addr, size, tag, init) \ arch_set_mem_tag_range((addr), (size), (tag), (init)) -void kasan_enable_tagging(void); +void kasan_enable_hw_tags(void); #else /* CONFIG_KASAN_HW_TAGS */ -static inline void kasan_enable_tagging(void) { } +static inline void kasan_enable_hw_tags(void) { } #endif /* CONFIG_KASAN_HW_TAGS */ diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index 627eaf1ee1db..a375776f9896 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -148,7 +148,7 @@ static void kasan_test_exit(struct kunit *test) kasan_sync_fault_possible()) { \ if (READ_ONCE(test_status.report_found) && \ !READ_ONCE(test_status.async_fault)) \ - kasan_enable_tagging(); \ + kasan_enable_hw_tags(); \ migrate_enable(); \ } \ WRITE_ONCE(test_status.report_found, false); \ -- GitLab From 2cc029a08493b08581a2f12a584b9e0ef6d7891e Mon Sep 17 00:00:00 2001 From: Vincenzo Frascino Date: Sat, 11 Mar 2023 00:43:31 +0100 Subject: [PATCH 2191/5631] arm64: mte: rename TCO routines The TCO related routines are used in uaccess methods and load_unaligned_zeropad() but are unrelated to both even if the naming suggest otherwise. Improve the readability of the code moving the away from uaccess.h and pre-pending them with "mte". [andreyknvl@google.com: drop __ from mte_disable/enable_tco names] Link: https://lkml.kernel.org/r/74d26337b2360733956114069e96ff11c296a944.1680114854.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/a48e7adce1248c0f9603a457776d59daa0ef734b.1678491668.git.andreyknvl@google.com Signed-off-by: Vincenzo Frascino Signed-off-by: Catalin Marinas Signed-off-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Marco Elver Cc: Peter Collingbourne Cc: Weizhao Ouyang Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/mte-kasan.h | 81 +++++++++++++++++++++++++ arch/arm64/include/asm/mte.h | 12 ---- arch/arm64/include/asm/uaccess.h | 66 +++----------------- arch/arm64/include/asm/word-at-a-time.h | 4 +- 4 files changed, 93 insertions(+), 70 deletions(-) diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index 9f79425fc65a..2e98028c1965 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -13,8 +13,73 @@ #include +#ifdef CONFIG_KASAN_HW_TAGS + +/* Whether the MTE asynchronous mode is enabled. */ +DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); + +static inline bool system_uses_mte_async_or_asymm_mode(void) +{ + return static_branch_unlikely(&mte_async_or_asymm_mode); +} + +#else /* CONFIG_KASAN_HW_TAGS */ + +static inline bool system_uses_mte_async_or_asymm_mode(void) +{ + return false; +} + +#endif /* CONFIG_KASAN_HW_TAGS */ + #ifdef CONFIG_ARM64_MTE +/* + * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0 + * affects EL0 and TCF affects EL1 irrespective of which TTBR is + * used. + * The kernel accesses TTBR0 usually with LDTR/STTR instructions + * when UAO is available, so these would act as EL0 accesses using + * TCF0. + * However futex.h code uses exclusives which would be executed as + * EL1, this can potentially cause a tag check fault even if the + * user disables TCF0. + * + * To address the problem we set the PSTATE.TCO bit in uaccess_enable() + * and reset it in uaccess_disable(). + * + * The Tag check override (TCO) bit disables temporarily the tag checking + * preventing the issue. + */ +static inline void mte_disable_tco(void) +{ + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +static inline void mte_enable_tco(void) +{ + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +/* + * These functions disable tag checking only if in MTE async mode + * since the sync mode generates exceptions synchronously and the + * nofault or load_unaligned_zeropad can handle them. + */ +static inline void __mte_disable_tco_async(void) +{ + if (system_uses_mte_async_or_asymm_mode()) + mte_disable_tco(); +} + +static inline void __mte_enable_tco_async(void) +{ + if (system_uses_mte_async_or_asymm_mode()) + mte_enable_tco(); +} + /* * These functions are meant to be only used from KASAN runtime through * the arch_*() interface defined in asm/memory.h. @@ -138,6 +203,22 @@ void mte_enable_kernel_asymm(void); #else /* CONFIG_ARM64_MTE */ +static inline void mte_disable_tco(void) +{ +} + +static inline void mte_enable_tco(void) +{ +} + +static inline void __mte_disable_tco_async(void) +{ +} + +static inline void __mte_enable_tco_async(void) +{ +} + static inline u8 mte_get_ptr_tag(void *ptr) { return 0xFF; diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h index 20dd06d70af5..c028afb1cd0b 100644 --- a/arch/arm64/include/asm/mte.h +++ b/arch/arm64/include/asm/mte.h @@ -178,14 +178,6 @@ static inline void mte_disable_tco_entry(struct task_struct *task) } #ifdef CONFIG_KASAN_HW_TAGS -/* Whether the MTE asynchronous mode is enabled. */ -DECLARE_STATIC_KEY_FALSE(mte_async_or_asymm_mode); - -static inline bool system_uses_mte_async_or_asymm_mode(void) -{ - return static_branch_unlikely(&mte_async_or_asymm_mode); -} - void mte_check_tfsr_el1(void); static inline void mte_check_tfsr_entry(void) @@ -212,10 +204,6 @@ static inline void mte_check_tfsr_exit(void) mte_check_tfsr_el1(); } #else -static inline bool system_uses_mte_async_or_asymm_mode(void) -{ - return false; -} static inline void mte_check_tfsr_el1(void) { } diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 5c7b2f9d5913..30ea7b5c3ccb 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -136,55 +136,9 @@ static inline void __uaccess_enable_hw_pan(void) CONFIG_ARM64_PAN)); } -/* - * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0 - * affects EL0 and TCF affects EL1 irrespective of which TTBR is - * used. - * The kernel accesses TTBR0 usually with LDTR/STTR instructions - * when UAO is available, so these would act as EL0 accesses using - * TCF0. - * However futex.h code uses exclusives which would be executed as - * EL1, this can potentially cause a tag check fault even if the - * user disables TCF0. - * - * To address the problem we set the PSTATE.TCO bit in uaccess_enable() - * and reset it in uaccess_disable(). - * - * The Tag check override (TCO) bit disables temporarily the tag checking - * preventing the issue. - */ -static inline void __uaccess_disable_tco(void) -{ - asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0), - ARM64_MTE, CONFIG_KASAN_HW_TAGS)); -} - -static inline void __uaccess_enable_tco(void) -{ - asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), - ARM64_MTE, CONFIG_KASAN_HW_TAGS)); -} - -/* - * These functions disable tag checking only if in MTE async mode - * since the sync mode generates exceptions synchronously and the - * nofault or load_unaligned_zeropad can handle them. - */ -static inline void __uaccess_disable_tco_async(void) -{ - if (system_uses_mte_async_or_asymm_mode()) - __uaccess_disable_tco(); -} - -static inline void __uaccess_enable_tco_async(void) -{ - if (system_uses_mte_async_or_asymm_mode()) - __uaccess_enable_tco(); -} - static inline void uaccess_disable_privileged(void) { - __uaccess_disable_tco(); + mte_disable_tco(); if (uaccess_ttbr0_disable()) return; @@ -194,7 +148,7 @@ static inline void uaccess_disable_privileged(void) static inline void uaccess_enable_privileged(void) { - __uaccess_enable_tco(); + mte_enable_tco(); if (uaccess_ttbr0_enable()) return; @@ -302,8 +256,8 @@ do { \ #define get_user __get_user /* - * We must not call into the scheduler between __uaccess_enable_tco_async() and - * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * We must not call into the scheduler between __mte_enable_tco_async() and + * __mte_disable_tco_async(). As `dst` and `src` may contain blocking * functions, we must evaluate these outside of the critical section. */ #define __get_kernel_nofault(dst, src, type, err_label) \ @@ -312,10 +266,10 @@ do { \ __typeof__(src) __gkn_src = (src); \ int __gkn_err = 0; \ \ - __uaccess_enable_tco_async(); \ + __mte_enable_tco_async(); \ __raw_get_mem("ldr", *((type *)(__gkn_dst)), \ (__force type *)(__gkn_src), __gkn_err, K); \ - __uaccess_disable_tco_async(); \ + __mte_disable_tco_async(); \ \ if (unlikely(__gkn_err)) \ goto err_label; \ @@ -388,8 +342,8 @@ do { \ #define put_user __put_user /* - * We must not call into the scheduler between __uaccess_enable_tco_async() and - * __uaccess_disable_tco_async(). As `dst` and `src` may contain blocking + * We must not call into the scheduler between __mte_enable_tco_async() and + * __mte_disable_tco_async(). As `dst` and `src` may contain blocking * functions, we must evaluate these outside of the critical section. */ #define __put_kernel_nofault(dst, src, type, err_label) \ @@ -398,10 +352,10 @@ do { \ __typeof__(src) __pkn_src = (src); \ int __pkn_err = 0; \ \ - __uaccess_enable_tco_async(); \ + __mte_enable_tco_async(); \ __raw_put_mem("str", *((type *)(__pkn_src)), \ (__force type *)(__pkn_dst), __pkn_err, K); \ - __uaccess_disable_tco_async(); \ + __mte_disable_tco_async(); \ \ if (unlikely(__pkn_err)) \ goto err_label; \ diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index 1c8e4f2490bf..f3b151ed0d7a 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -55,7 +55,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; - __uaccess_enable_tco_async(); + __mte_enable_tco_async(); /* Load word from unaligned pointer addr */ asm( @@ -65,7 +65,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) : "=&r" (ret) : "r" (addr), "Q" (*(unsigned long *)addr)); - __uaccess_disable_tco_async(); + __mte_disable_tco_async(); return ret; } -- GitLab From 0d3c9468bef98f703c369ced4ec61b0d4a5210ee Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 11 Mar 2023 00:43:32 +0100 Subject: [PATCH 2192/5631] kasan, arm64: add arch_suppress_tag_checks_start/stop Add two new tagging-related routines arch_suppress_tag_checks_start/stop that suppress MTE tag checking via the TCO register. These rouines are used in the next patch. [andreyknvl@google.com: drop __ from mte_disable/enable_tco names] Link: https://lkml.kernel.org/r/7ad5e5a9db79e3aba08d8f43aca24350b04080f6.1680114854.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/75a362551c3c54b70ae59a3492cabb51c105fa6b.1678491668.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Marco Elver Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Weizhao Ouyang Cc: Will Deacon Signed-off-by: Andrew Morton --- arch/arm64/include/asm/memory.h | 2 ++ mm/kasan/kasan.h | 2 ++ 2 files changed, 4 insertions(+) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index faf42bff9a60..05e42bd3555f 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -264,6 +264,8 @@ static inline const void *__tag_set(const void *addr, u8 tag) #define arch_enable_tag_checks_sync() mte_enable_kernel_sync() #define arch_enable_tag_checks_async() mte_enable_kernel_async() #define arch_enable_tag_checks_asymm() mte_enable_kernel_asymm() +#define arch_suppress_tag_checks_start() mte_enable_tco() +#define arch_suppress_tag_checks_stop() mte_disable_tco() #define arch_force_async_tag_fault() mte_check_tfsr_exit() #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index a1613f5d7608..f5e4f5f2ba20 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -398,6 +398,8 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) #define hw_enable_tag_checks_sync() arch_enable_tag_checks_sync() #define hw_enable_tag_checks_async() arch_enable_tag_checks_async() #define hw_enable_tag_checks_asymm() arch_enable_tag_checks_asymm() +#define hw_suppress_tag_checks_start() arch_suppress_tag_checks_start() +#define hw_suppress_tag_checks_stop() arch_suppress_tag_checks_stop() #define hw_force_async_tag_fault() arch_force_async_tag_fault() #define hw_get_random_tag() arch_get_random_tag() #define hw_get_mem_tag(addr) arch_get_mem_tag(addr) -- GitLab From c6a690e0c978bda8106e7a489c13323f90b087d0 Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Sat, 11 Mar 2023 00:43:33 +0100 Subject: [PATCH 2193/5631] kasan: suppress recursive reports for HW_TAGS KASAN suppresses reports for bad accesses done by the KASAN reporting code. The reporting code might access poisoned memory for reporting purposes. Software KASAN modes do this by suppressing reports during reporting via current->kasan_depth, the same way they suppress reports during accesses to poisoned slab metadata. Hardware Tag-Based KASAN does not use current->kasan_depth, and instead resets pointer tags for accesses to poisoned memory done by the reporting code. Despite that, a recursive report can still happen: 1. On hardware with faulty MTE support. This was observed by Weizhao Ouyang on a faulty hardware that caused memory tags to randomly change from time to time. 2. Theoretically, due to a previous MTE-undetected memory corruption. A recursive report can happen via: 1. Accessing a pointer with a non-reset tag in the reporting code, e.g. slab->slab_cache, which is what Weizhao Ouyang observed. 2. Theoretically, via external non-annotated routines, e.g. stackdepot. To resolve this issue, resetting tags for all of the pointers in the reporting code and all the used external routines would be impractical. Instead, disable tag checking done by the CPU for the duration of KASAN reporting for Hardware Tag-Based KASAN. Without this fix, Hardware Tag-Based KASAN reporting code might deadlock. [andreyknvl@google.com: disable preemption instead of migration, fix comment typo] Link: https://lkml.kernel.org/r/d14417c8bc5eea7589e99381203432f15c0f9138.1680114854.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/59f433e00f7fa985e8bf9f7caf78574db16b67ab.1678491668.git.andreyknvl@google.com Fixes: 2e903b914797 ("kasan, arm64: implement HW_TAGS runtime") Signed-off-by: Andrey Konovalov Reported-by: Weizhao Ouyang Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Evgenii Stepanov Cc: Peter Collingbourne Cc: Vincenzo Frascino Cc: Will Deacon Signed-off-by: Andrew Morton --- mm/kasan/report.c | 59 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 48 insertions(+), 11 deletions(-) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 89078f912827..892a9dc9d4d3 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -72,10 +72,18 @@ static int __init kasan_set_multi_shot(char *str) __setup("kasan_multi_shot", kasan_set_multi_shot); /* - * Used to suppress reports within kasan_disable/enable_current() critical - * sections, which are used for marking accesses to slab metadata. + * This function is used to check whether KASAN reports are suppressed for + * software KASAN modes via kasan_disable/enable_current() critical sections. + * + * This is done to avoid: + * 1. False-positive reports when accessing slab metadata, + * 2. Deadlocking when poisoned memory is accessed by the reporting code. + * + * Hardware Tag-Based KASAN instead relies on: + * For #1: Resetting tags via kasan_reset_tag(). + * For #2: Suppression of tag checks via CPU, see report_suppress_start/end(). */ -static bool report_suppressed(void) +static bool report_suppressed_sw(void) { #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) if (current->kasan_depth) @@ -84,6 +92,30 @@ static bool report_suppressed(void) return false; } +static void report_suppress_start(void) +{ +#ifdef CONFIG_KASAN_HW_TAGS + /* + * Disable preemption for the duration of printing a KASAN report, as + * hw_suppress_tag_checks_start() disables checks on the current CPU. + */ + preempt_disable(); + hw_suppress_tag_checks_start(); +#else + kasan_disable_current(); +#endif +} + +static void report_suppress_stop(void) +{ +#ifdef CONFIG_KASAN_HW_TAGS + hw_suppress_tag_checks_stop(); + preempt_enable(); +#else + kasan_enable_current(); +#endif +} + /* * Used to avoid reporting more than one KASAN bug unless kasan_multi_shot * is enabled. Note that KASAN tests effectively enable kasan_multi_shot @@ -174,7 +206,7 @@ static void start_report(unsigned long *flags, bool sync) /* Do not allow LOCKDEP mangling KASAN reports. */ lockdep_off(); /* Make sure we don't end up in loop. */ - kasan_disable_current(); + report_suppress_start(); spin_lock_irqsave(&report_lock, *flags); pr_err("==================================================================\n"); } @@ -192,7 +224,7 @@ static void end_report(unsigned long *flags, void *addr) panic("kasan.fault=panic set ...\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); lockdep_on(); - kasan_enable_current(); + report_suppress_stop(); } static void print_error_description(struct kasan_report_info *info) @@ -480,9 +512,13 @@ void kasan_report_invalid_free(void *ptr, unsigned long ip, enum kasan_report_ty struct kasan_report_info info; /* - * Do not check report_suppressed(), as an invalid-free cannot be - * caused by accessing slab metadata and thus should not be - * suppressed by kasan_disable/enable_current() critical sections. + * Do not check report_suppressed_sw(), as an invalid-free cannot be + * caused by accessing poisoned memory and thus should not be suppressed + * by kasan_disable/enable_current() critical sections. + * + * Note that for Hardware Tag-Based KASAN, kasan_report_invalid_free() + * is triggered by explicit tag checks and not by the ones performed by + * the CPU. Thus, reporting invalid-free is not suppressed as well. */ if (unlikely(!report_enabled())) return; @@ -517,7 +553,7 @@ bool kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long irq_flags; struct kasan_report_info info; - if (unlikely(report_suppressed()) || unlikely(!report_enabled())) { + if (unlikely(report_suppressed_sw()) || unlikely(!report_enabled())) { ret = false; goto out; } @@ -549,8 +585,9 @@ void kasan_report_async(void) unsigned long flags; /* - * Do not check report_suppressed(), as kasan_disable/enable_current() - * critical sections do not affect Hardware Tag-Based KASAN. + * Do not check report_suppressed_sw(), as + * kasan_disable/enable_current() critical sections do not affect + * Hardware Tag-Based KASAN. */ if (unlikely(!report_enabled())) return; -- GitLab From 2bad466cc9d9b4c3b4b16eb9c03c919b59561316 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 9 Mar 2023 17:37:10 -0500 Subject: [PATCH 2194/5631] mm/uffd: UFFD_FEATURE_WP_UNPOPULATED Patch series "mm/uffd: Add feature bit UFFD_FEATURE_WP_UNPOPULATED", v4. The new feature bit makes anonymous memory acts the same as file memory on userfaultfd-wp in that it'll also wr-protect none ptes. It can be useful in two cases: (1) Uffd-wp app that needs to wr-protect none ptes like QEMU snapshot, so pre-fault can be replaced by enabling this flag and speed up protections (2) It helps to implement async uffd-wp mode that Muhammad is working on [1] It's debatable whether this is the most ideal solution because with the new feature bit set, wr-protect none pte needs to pre-populate the pgtables to the last level (PAGE_SIZE). But it seems fine so far to service either purpose above, so we can leave optimizations for later. The series brings pte markers to anonymous memory too. There's some change in the common mm code path in the 1st patch, great to have some eye looking at it, but hopefully they're still relatively straightforward. This patch (of 2): This is a new feature that controls how uffd-wp handles none ptes. When it's set, the kernel will handle anonymous memory the same way as file memory, by allowing the user to wr-protect unpopulated ptes. File memories handles none ptes consistently by allowing wr-protecting of none ptes because of the unawareness of page cache being exist or not. For anonymous it was not as persistent because we used to assume that we don't need protections on none ptes or known zero pages. One use case of such a feature bit was VM live snapshot, where if without wr-protecting empty ptes the snapshot can contain random rubbish in the holes of the anonymous memory, which can cause misbehave of the guest when the guest OS assumes the pages should be all zeros. QEMU worked it around by pre-populate the section with reads to fill in zero page entries before starting the whole snapshot process [1]. Recently there's another need raised on using userfaultfd wr-protect for detecting dirty pages (to replace soft-dirty in some cases) [2]. In that case if without being able to wr-protect none ptes by default, the dirty info can get lost, since we cannot treat every none pte to be dirty (the current design is identify a page dirty based on uffd-wp bit being cleared). In general, we want to be able to wr-protect empty ptes too even for anonymous. This patch implements UFFD_FEATURE_WP_UNPOPULATED so that it'll make uffd-wp handling on none ptes being consistent no matter what the memory type is underneath. It doesn't have any impact on file memories so far because we already have pte markers taking care of that. So it only affects anonymous. The feature bit is by default off, so the old behavior will be maintained. Sometimes it may be wanted because the wr-protect of none ptes will contain overheads not only during UFFDIO_WRITEPROTECT (by applying pte markers to anonymous), but also on creating the pgtables to store the pte markers. So there's potentially less chance of using thp on the first fault for a none pmd or larger than a pmd. The major implementation part is teaching the whole kernel to understand pte markers even for anonymously mapped ranges, meanwhile allowing the UFFDIO_WRITEPROTECT ioctl to apply pte markers for anonymous too when the new feature bit is set. Note that even if the patch subject starts with mm/uffd, there're a few small refactors to major mm path of handling anonymous page faults. But they should be straightforward. With WP_UNPOPUATED, application like QEMU can avoid pre-read faults all the memory before wr-protect during taking a live snapshot. Quotting from Muhammad's test result here [3] based on a simple program [4]: (1) With huge page disabled echo madvise > /sys/kernel/mm/transparent_hugepage/enabled ./uffd_wp_perf Test DEFAULT: 4 Test PRE-READ: 1111453 (pre-fault 1101011) Test MADVISE: 278276 (pre-fault 266378) Test WP-UNPOPULATE: 11712 (2) With Huge page enabled echo always > /sys/kernel/mm/transparent_hugepage/enabled ./uffd_wp_perf Test DEFAULT: 4 Test PRE-READ: 22521 (pre-fault 22348) Test MADVISE: 4909 (pre-fault 4743) Test WP-UNPOPULATE: 14448 There'll be a great perf boost for no-thp case, while for thp enabled with extreme case of all-thp-zero WP_UNPOPULATED can be slower than MADVISE, but that's low possibility in reality, also the overhead was not reduced but postponed until a follow up write on any huge zero thp, so potentially it is faster by making the follow up writes slower. [1] https://lore.kernel.org/all/20210401092226.102804-4-andrey.gruzdev@virtuozzo.com/ [2] https://lore.kernel.org/all/Y+v2HJ8+3i%2FKzDBu@x1n/ [3] https://lore.kernel.org/all/d0eb0a13-16dc-1ac1-653a-78b7273781e3@collabora.com/ [4] https://github.com/xzpeter/clibs/blob/master/uffd-test/uffd-wp-perf.c [peterx@redhat.com: comment changes, oneliner fix to khugepaged] Link: https://lkml.kernel.org/r/ZB2/8jPhD3fpx5U8@x1n Link: https://lkml.kernel.org/r/20230309223711.823547-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20230309223711.823547-2-peterx@redhat.com Signed-off-by: Peter Xu Acked-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mike Rapoport Cc: Muhammad Usama Anjum Cc: Nadav Amit Cc: Paul Gofman Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/userfaultfd.rst | 17 ++++++ fs/userfaultfd.c | 16 ++++++ include/linux/mm_inline.h | 6 +++ include/linux/userfaultfd_k.h | 23 ++++++++ include/uapi/linux/userfaultfd.h | 10 +++- mm/khugepaged.c | 2 +- mm/memory.c | 56 +++++++++++++++----- mm/mprotect.c | 51 ++++++++++++++---- 8 files changed, 155 insertions(+), 26 deletions(-) diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst index 7dc823b56ca4..bd2226299583 100644 --- a/Documentation/admin-guide/mm/userfaultfd.rst +++ b/Documentation/admin-guide/mm/userfaultfd.rst @@ -219,6 +219,23 @@ former will have ``UFFD_PAGEFAULT_FLAG_WP`` set, the latter you still need to supply a page when ``UFFDIO_REGISTER_MODE_MISSING`` was used. +Userfaultfd write-protect mode currently behave differently on none ptes +(when e.g. page is missing) over different types of memories. + +For anonymous memory, ``ioctl(UFFDIO_WRITEPROTECT)`` will ignore none ptes +(e.g. when pages are missing and not populated). For file-backed memories +like shmem and hugetlbfs, none ptes will be write protected just like a +present pte. In other words, there will be a userfaultfd write fault +message generated when writing to a missing page on file typed memories, +as long as the page range was write-protected before. Such a message will +not be generated on anonymous memories by default. + +If the application wants to be able to write protect none ptes on anonymous +memory, one can pre-populate the memory with e.g. MADV_POPULATE_READ. On +newer kernels, one can also detect the feature UFFD_FEATURE_WP_UNPOPULATED +and set the feature bit in advance to make sure none ptes will also be +write protected even upon anonymous memory. + QEMU/KVM ======== diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 44d1ee429eb0..881e9c82b9d1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) return ctx->features & UFFD_FEATURE_INITIALIZED; } +/* + * Whether WP_UNPOPULATED is enabled on the uffd context. It is only + * meaningful when userfaultfd_wp()==true on the vma and when it's + * anonymous. + */ +bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) +{ + struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; + + if (!ctx) + return false; + + return ctx->features & UFFD_FEATURE_WP_UNPOPULATED; +} + static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, vm_flags_t flags) { @@ -1971,6 +1986,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, #endif #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; + uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED; #endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index de1e622dd366..0e1d239a882c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -557,6 +557,12 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(*pte)); + /* + * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole + * thing, because when zapping either it means it's dropping the + * page, or in TTU where the present pte will be quickly replaced + * with a swap pte. There's no way of leaking the bit. + */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..0cf8880219da 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -179,6 +179,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); +extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -274,8 +275,30 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) +{ + /* Only wr-protect mode uses pte markers */ + if (!userfaultfd_wp(vma)) + return false; + + /* File-based uffd-wp always need markers */ + if (!vma_is_anonymous(vma)) + return true; + + /* + * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED + * enabled (to apply markers on zero pages). + */ + return userfaultfd_wp_unpopulated(vma); +} + static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 005e5e306266..90c958952bfc 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -38,7 +38,8 @@ UFFD_FEATURE_MINOR_HUGETLBFS | \ UFFD_FEATURE_MINOR_SHMEM | \ UFFD_FEATURE_EXACT_ADDRESS | \ - UFFD_FEATURE_WP_HUGETLBFS_SHMEM) + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ + UFFD_FEATURE_WP_UNPOPULATED) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -203,6 +204,12 @@ struct uffdio_api { * * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd * write-protection mode is supported on both shmem and hugetlbfs. + * + * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd + * write-protection mode will always apply to unpopulated pages + * (i.e. empty ptes). This will be the default behavior for shmem + * & hugetlbfs, so this flag only affects anonymous memory behavior + * when userfault write-protection mode is registered. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -217,6 +224,7 @@ struct uffdio_api { #define UFFD_FEATURE_MINOR_SHMEM (1<<10) #define UFFD_FEATURE_EXACT_ADDRESS (1<<11) #define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) +#define UFFD_FEATURE_WP_UNPOPULATED (1<<13) __u64 features; __u64 ioctls; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 074ea534f786..c7317678cb10 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1177,7 +1177,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ - if (pte_swp_uffd_wp(pteval)) { + if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } diff --git a/mm/memory.c b/mm/memory.c index 6285cad1f4fb..a890b2951b53 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -104,6 +104,20 @@ EXPORT_SYMBOL(mem_map); #endif static vm_fault_t do_fault(struct vm_fault *vmf); +static vm_fault_t do_anonymous_page(struct vm_fault *vmf); +static bool vmf_pte_changed(struct vm_fault *vmf); + +/* + * Return true if the original pte was a uffd-wp pte marker (so the pte was + * wr-protected). + */ +static bool vmf_orig_pte_uffd_wp(struct vm_fault *vmf) +{ + if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) + return false; + + return pte_marker_uffd_wp(vmf->orig_pte); +} /* * A number of key systems in x86 including ioremap() rely on the assumption @@ -1346,6 +1360,10 @@ zap_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, struct zap_details *details, pte_t pteval) { + /* Zap on anonymous always means dropping everything */ + if (vma_is_anonymous(vma)) + return; + if (zap_drop_file_uffd_wp(details)) return; @@ -1452,8 +1470,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; rss[mm_counter(page)]--; } else if (pte_marker_entry_uffd_wp(entry)) { - /* Only drop the uffd-wp marker if explicitly requested */ - if (!zap_drop_file_uffd_wp(details)) + /* + * For anon: always drop the marker; for file: only + * drop the marker if explicitly requested. + */ + if (!vma_is_anonymous(vma) && + !zap_drop_file_uffd_wp(details)) continue; } else if (is_hwpoison_entry(entry) || is_swapin_error_entry(entry)) { @@ -3620,6 +3642,14 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf) return 0; } +static vm_fault_t do_pte_missing(struct vm_fault *vmf) +{ + if (vma_is_anonymous(vmf->vma)) + return do_anonymous_page(vmf); + else + return do_fault(vmf); +} + /* * This is actually a page-missing access, but with uffd-wp special pte * installed. It means this pte was wr-protected before being unmapped. @@ -3630,11 +3660,10 @@ static vm_fault_t pte_marker_handle_uffd_wp(struct vm_fault *vmf) * Just in case there're leftover special ptes even after the region * got unregistered - we can simply clear them. */ - if (unlikely(!userfaultfd_wp(vmf->vma) || vma_is_anonymous(vmf->vma))) + if (unlikely(!userfaultfd_wp(vmf->vma))) return pte_marker_clear(vmf); - /* do_fault() can handle pte markers too like none pte */ - return do_fault(vmf); + return do_pte_missing(vmf); } static vm_fault_t handle_pte_marker(struct vm_fault *vmf) @@ -3999,6 +4028,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { + bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); struct vm_area_struct *vma = vmf->vma; struct folio *folio; vm_fault_t ret = 0; @@ -4032,7 +4062,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) { + if (vmf_pte_changed(vmf)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } @@ -4072,7 +4102,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); - if (!pte_none(*vmf->pte)) { + if (vmf_pte_changed(vmf)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto release; } @@ -4092,6 +4122,8 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) folio_add_new_anon_rmap(folio, vma, vmf->address); folio_add_lru_vma(folio, vma); setpte: + if (uffd_wp) + entry = pte_mkuffd_wp(entry); set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ @@ -4259,7 +4291,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; - bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte); + bool uffd_wp = vmf_orig_pte_uffd_wp(vmf); bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = vmf->address != addr; pte_t entry; @@ -4903,12 +4935,8 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) } } - if (!vmf->pte) { - if (vma_is_anonymous(vmf->vma)) - return do_anonymous_page(vmf); - else - return do_fault(vmf); - } + if (!vmf->pte) + return do_pte_missing(vmf); if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); diff --git a/mm/mprotect.c b/mm/mprotect.c index 13e84d8c0797..b9da9a5f87fe 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -276,7 +276,15 @@ static long change_pte_range(struct mmu_gather *tlb, } else { /* It must be an none page, or what else?.. */ WARN_ON_ONCE(!pte_none(oldpte)); - if (unlikely(uffd_wp && !vma_is_anonymous(vma))) { + + /* + * Nobody plays with any none ptes besides + * userfaultfd when applying the protections. + */ + if (likely(!uffd_wp)) + continue; + + if (userfaultfd_wp_use_markers(vma)) { /* * For file-backed mem, we need to be able to * wr-protect a none pte, because even if the @@ -320,23 +328,46 @@ static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd) return 0; } -/* Return true if we're uffd wr-protecting file-backed memory, or false */ +/* + * Return true if we want to split THPs into PTE mappings in change + * protection procedure, false otherwise. + */ static inline bool -uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags) +pgtable_split_needed(struct vm_area_struct *vma, unsigned long cp_flags) { + /* + * pte markers only resides in pte level, if we need pte markers, + * we need to split. We cannot wr-protect shmem thp because file + * thp is handled differently when split by erasing the pmd so far. + */ return (cp_flags & MM_CP_UFFD_WP) && !vma_is_anonymous(vma); } /* - * If wr-protecting the range for file-backed, populate pgtable for the case - * when pgtable is empty but page cache exists. When {pte|pmd|...}_alloc() - * failed we treat it the same way as pgtable allocation failures during - * page faults by kicking OOM and returning error. + * Return true if we want to populate pgtables in change protection + * procedure, false otherwise + */ +static inline bool +pgtable_populate_needed(struct vm_area_struct *vma, unsigned long cp_flags) +{ + /* If not within ioctl(UFFDIO_WRITEPROTECT), then don't bother */ + if (!(cp_flags & MM_CP_UFFD_WP)) + return false; + + /* Populate if the userfaultfd mode requires pte markers */ + return userfaultfd_wp_use_markers(vma); +} + +/* + * Populate the pgtable underneath for whatever reason if requested. + * When {pte|pmd|...}_alloc() failed we treat it the same way as pgtable + * allocation failures during page faults by kicking OOM and returning + * error. */ #define change_pmd_prepare(vma, pmd, cp_flags) \ ({ \ long err = 0; \ - if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ + if (unlikely(pgtable_populate_needed(vma, cp_flags))) { \ if (pte_alloc(vma->vm_mm, pmd)) \ err = -ENOMEM; \ } \ @@ -351,7 +382,7 @@ uffd_wp_protect_file(struct vm_area_struct *vma, unsigned long cp_flags) #define change_prepare(vma, high, low, addr, cp_flags) \ ({ \ long err = 0; \ - if (unlikely(uffd_wp_protect_file(vma, cp_flags))) { \ + if (unlikely(pgtable_populate_needed(vma, cp_flags))) { \ low##_t *p = low##_alloc(vma->vm_mm, high, addr); \ if (p == NULL) \ err = -ENOMEM; \ @@ -404,7 +435,7 @@ static inline long change_pmd_range(struct mmu_gather *tlb, if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if ((next - addr != HPAGE_PMD_SIZE) || - uffd_wp_protect_file(vma, cp_flags)) { + pgtable_split_needed(vma, cp_flags)) { __split_huge_pmd(vma, pmd, addr, false, NULL); /* * For file-backed, the pmd could have been -- GitLab From 47fba2b6d5bae89df5b1434bfdad4a56c7e88059 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 9 Mar 2023 17:37:11 -0500 Subject: [PATCH 2195/5631] selftests/mm: smoke test UFFD_FEATURE_WP_UNPOPULATED Enable it by default on the stress test, and add some smoke tests for the pte markers on anonymous. Link: https://lkml.kernel.org/r/20230309223711.823547-3-peterx@redhat.com Signed-off-by: Peter Xu Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Mike Rapoport Cc: Muhammad Usama Anjum Cc: Nadav Amit Cc: Paul Gofman Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/userfaultfd.c | 45 ++++++++++++++++++++++-- 1 file changed, 43 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 7f22844ed704..e030d63c031a 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -1444,6 +1444,43 @@ static int pagemap_test_fork(bool present) return result; } +static void userfaultfd_wp_unpopulated_test(int pagemap_fd) +{ + uint64_t value; + + /* Test applying pte marker to anon unpopulated */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + + /* Test unprotect on anon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test zap on anon marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test fault in after marker removed */ + *area_dst = 1; + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + + /* Test read-zero-page upon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + *(volatile char *)area_dst; + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); +} + static void userfaultfd_pagemap_test(unsigned int test_pgsize) { struct uffdio_register uffdio_register; @@ -1462,7 +1499,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) /* Flush so it doesn't flush twice in parent/child later */ fflush(stdout); - uffd_test_ctx_init(0); + uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); if (test_pgsize > page_size) { /* This is a thp test */ @@ -1482,6 +1519,10 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) pagemap_fd = pagemap_open(); + /* Smoke test WP_UNPOPULATED first when it's still empty */ + if (test_pgsize == page_size) + userfaultfd_wp_unpopulated_test(pagemap_fd); + /* Touch the page */ *area_dst = 1; wp_range(uffd, (uint64_t)area_dst, test_pgsize, true); @@ -1526,7 +1567,7 @@ static int userfaultfd_stress(void) struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; - uffd_test_ctx_init(0); + uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); if (posix_memalign(&area, page_size, page_size)) err("out of memory"); -- GitLab From 75558ad315488d40a18cb2c230ccacee24d20526 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:24 +0300 Subject: [PATCH 2196/5631] sparc/mm: fix MAX_ORDER usage in tsb_grow() Patch series "Fix confusion around MAX_ORDER". MAX_ORDER currently defined as number of orders page allocator supports: user can ask buddy allocator for page order between 0 and MAX_ORDER-1. This definition is counter-intuitive and lead to number of bugs all over the kernel. Fix the bugs and then change the definition of MAX_ORDER to be inclusive: the range of orders user can ask from buddy allocator is 0..MAX_ORDER now. This patch (of 10): MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in tsb_grow(). Link: https://lkml.kernel.org/r/20230315113133.11326-1-kirill.shutemov@linux.intel.com Link: https://lkml.kernel.org/r/20230315113133.11326-2-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Mike Kravetz Acked-by: Mike Rapoport (IBM) Cc: David Miller Cc: David Hildenbrand Cc: Kirill A. Shutemov Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- arch/sparc/mm/tsb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 912205787161..dba8dffe2113 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss) unsigned long new_rss_limit; gfp_t gfp_flags; - if (max_tsb_size > (PAGE_SIZE << MAX_ORDER)) - max_tsb_size = (PAGE_SIZE << MAX_ORDER); + if (max_tsb_size > (PAGE_SIZE << (MAX_ORDER - 1))) + max_tsb_size = (PAGE_SIZE << (MAX_ORDER - 1)); new_cache_index = 0; for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) { -- GitLab From 254ca6d261d4b6ce00591de110f6f96c3556dfbe Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:25 +0300 Subject: [PATCH 2197/5631] um: fix MAX_ORDER usage in linux_main() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in linux_main(). Link: https://lkml.kernel.org/r/20230315113133.11326-3-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Mike Rapoport (IBM) Cc: Richard Weinberger Cc: Anton Ivanov Cc: Johannes Berg Signed-off-by: Andrew Morton --- arch/um/kernel/um_arch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8dcda617b8bf..5e5a9c8e0e5d 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -368,10 +368,10 @@ int __init linux_main(int argc, char **argv) max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC; /* - * Zones have to begin on a 1 << MAX_ORDER page boundary, + * Zones have to begin on a 1 << MAX_ORDER-1 page boundary, * so this makes sure that's true for highmem */ - max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER)) - 1); + max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER - 1)) - 1); if (physmem_size + iomem_size > max_physmem) { highmem = physmem_size + iomem_size - max_physmem; physmem_size -= highmem; -- GitLab From 5f29298fba1ad1e7139381e19e09c272db337b13 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:26 +0300 Subject: [PATCH 2198/5631] floppy: fix MAX_ORDER usage MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in floppy code. Also allocation buffer exactly PAGE_SIZE << MAX_ORDER bytes is okay. Fix MAX_LEN check. Link: https://lkml.kernel.org/r/20230315113133.11326-4-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Mike Rapoport (IBM) Cc: Denis Efremov Signed-off-by: Andrew Morton --- drivers/block/floppy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 487840e3564d..90d2dfb6448e 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3079,7 +3079,7 @@ static void raw_cmd_free(struct floppy_raw_cmd **ptr) } } -#define MAX_LEN (1UL << MAX_ORDER << PAGE_SHIFT) +#define MAX_LEN (1UL << (MAX_ORDER - 1) << PAGE_SHIFT) static int raw_cmd_copyin(int cmd, void __user *param, struct floppy_raw_cmd **rcmd) @@ -3108,7 +3108,7 @@ static int raw_cmd_copyin(int cmd, void __user *param, ptr->resultcode = 0; if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) { - if (ptr->length <= 0 || ptr->length >= MAX_LEN) + if (ptr->length <= 0 || ptr->length > MAX_LEN) return -EINVAL; ptr->kernel_data = (char *)fd_dma_mem_alloc(ptr->length); fallback_on_nodma_alloc(&ptr->kernel_data, ptr->length); -- GitLab From 50c00d2c686e52c0dd9b5bddc6727f6c442cbcc0 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:27 +0300 Subject: [PATCH 2199/5631] drm/i915: fix MAX_ORDER usage in i915_gem_object_get_pages_internal() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in i915_gem_object_get_pages_internal(). Link: https://lkml.kernel.org/r/20230315113133.11326-5-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Tvrtko Ursulin Cc: Jani Nikula Cc: Joonas Lahtinen Cc: Rodrigo Vivi Signed-off-by: Andrew Morton --- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index 6bc26b4b06b8..eae9e9f6d3bf 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -36,7 +36,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct sg_table *st; struct scatterlist *sg; unsigned int npages; /* restricted by sg_alloc_table */ - int max_order = MAX_ORDER; + int max_order = MAX_ORDER - 1; unsigned int max_segment; gfp_t gfp; -- GitLab From fd54349ddb61445a8a42459b3dc09237c55e6f78 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:28 +0300 Subject: [PATCH 2200/5631] genwqe: fix MAX_ORDER usage MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in genwqe driver. Link: https://lkml.kernel.org/r/20230315113133.11326-6-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Frank Haverkamp Signed-off-by: Andrew Morton --- drivers/misc/genwqe/card_dev.c | 2 +- drivers/misc/genwqe/card_utils.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c index 55fc5b80e649..d0e27438a73c 100644 --- a/drivers/misc/genwqe/card_dev.c +++ b/drivers/misc/genwqe/card_dev.c @@ -443,7 +443,7 @@ static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma) if (vsize == 0) return -EINVAL; - if (get_order(vsize) > MAX_ORDER) + if (get_order(vsize) >= MAX_ORDER) return -ENOMEM; dma_map = kzalloc(sizeof(struct dma_mapping), GFP_KERNEL); diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c index f778e11237a6..ac29698d085a 100644 --- a/drivers/misc/genwqe/card_utils.c +++ b/drivers/misc/genwqe/card_utils.c @@ -308,7 +308,7 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl, sgl->write = write; sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages); - if (get_order(sgl->sgl_size) > MAX_ORDER) { + if (get_order(sgl->sgl_size) >= MAX_ORDER) { dev_err(&pci_dev->dev, "[%s] err: too much memory requested!\n", __func__); return ret; -- GitLab From 934487e98fdd2d7762e893af7cbe788cfd39ff84 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:29 +0300 Subject: [PATCH 2201/5631] perf/core: fix MAX_ORDER usage in rb_alloc_aux_page() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in rb_alloc_aux_page(). Link: https://lkml.kernel.org/r/20230315113133.11326-7-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Ian Rogers Cc: Adrian Hunter Signed-off-by: Andrew Morton --- kernel/events/ring_buffer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 273a0fe7910a..d6bbdb7830b2 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -609,8 +609,8 @@ static struct page *rb_alloc_aux_page(int node, int order) { struct page *page; - if (order > MAX_ORDER) - order = MAX_ORDER; + if (order >= MAX_ORDER) + order = MAX_ORDER - 1; do { page = alloc_pages_node(node, PERF_AUX_GFP, order); -- GitLab From 668a89907c6b908c4a72ef22e70bbc95efca2000 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:30 +0300 Subject: [PATCH 2202/5631] mm/page_reporting: fix MAX_ORDER usage in page_reporting_register() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in page_reporting_register(). Link: https://lkml.kernel.org/r/20230315113133.11326-8-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Alexander Duyck Signed-off-by: Andrew Morton --- mm/page_reporting.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page_reporting.c b/mm/page_reporting.c index c65813a9dc78..275b466de37b 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -370,7 +370,7 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) */ if (page_reporting_order == -1) { - if (prdev->order > 0 && prdev->order <= MAX_ORDER) + if (prdev->order > 0 && prdev->order < MAX_ORDER) page_reporting_order = prdev->order; else page_reporting_order = pageblock_order; -- GitLab From 7a16d7c7619b26e5e9bfc1360de0d02a94f7d9eb Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:31 +0300 Subject: [PATCH 2203/5631] mm/slub: fix MAX_ORDER usage in calculate_order() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in calculate_order(). Link: https://lkml.kernel.org/r/20230315113133.11326-9-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Vlastimil Babka Cc: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Andrew Morton --- mm/slub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/slub.c b/mm/slub.c index 39327e98fce3..32eb6b50fe18 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4171,7 +4171,7 @@ static inline int calculate_order(unsigned int size) /* * Doh this slab cannot be placed using slub_max_order. */ - order = calc_slab_order(size, 1, MAX_ORDER, 1); + order = calc_slab_order(size, 1, MAX_ORDER - 1, 1); if (order < MAX_ORDER) return order; return -ENOSYS; -- GitLab From 61883d3c32418f16e35e030ca0cfd5d2de95a649 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:32 +0300 Subject: [PATCH 2204/5631] iommu: fix MAX_ORDER usage in __iommu_dma_alloc_pages() MAX_ORDER is not inclusive: the maximum allocation order buddy allocator can deliver is MAX_ORDER-1. Fix MAX_ORDER usage in __iommu_dma_alloc_pages(). Also use GENMASK() instead of hard to read "(2U << order) - 1" magic. Link: https://lkml.kernel.org/r/20230315113133.11326-10-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Acked-by: Robin Murphy Reviewed-by: Jacob Pan Acked-by: Joerg Roedel Signed-off-by: Andrew Morton --- drivers/iommu/dma-iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 99b2646cb5c7..ac996fd6bd9c 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -736,7 +736,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, struct page **pages; unsigned int i = 0, nid = dev_to_node(dev); - order_mask &= (2U << MAX_ORDER) - 1; + order_mask &= GENMASK(MAX_ORDER - 1, 0); if (!order_mask) return NULL; @@ -756,7 +756,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, * than a necessity, hence using __GFP_NORETRY until * falling back to minimum-order allocations. */ - for (order_mask &= (2U << __fls(count)) - 1; + for (order_mask &= GENMASK(__fls(count), 0); order_mask; order_mask &= ~order_size) { unsigned int order = __fls(order_mask); gfp_t alloc_flags = gfp; -- GitLab From 23baf831a32c04f9a968812511540b1b3e648bf5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 15 Mar 2023 14:31:33 +0300 Subject: [PATCH 2205/5631] mm, treewide: redefine MAX_ORDER sanely MAX_ORDER currently defined as number of orders page allocator supports: user can ask buddy allocator for page order between 0 and MAX_ORDER-1. This definition is counter-intuitive and lead to number of bugs all over the kernel. Change the definition of MAX_ORDER to be inclusive: the range of orders user can ask from buddy allocator is 0..MAX_ORDER now. [kirill@shutemov.name: fix min() warning] Link: https://lkml.kernel.org/r/20230315153800.32wib3n5rickolvh@box [akpm@linux-foundation.org: fix another min_t warning] [kirill@shutemov.name: fixups per Zi Yan] Link: https://lkml.kernel.org/r/20230316232144.b7ic4cif4kjiabws@box.shutemov.name [akpm@linux-foundation.org: fix underlining in docs] Link: https://lore.kernel.org/oe-kbuild-all/202303191025.VRCTk6mP-lkp@intel.com/ Link: https://lkml.kernel.org/r/20230315113133.11326-11-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Michael Ellerman [powerpc] Cc: "Kirill A. Shutemov" Cc: Zi Yan Signed-off-by: Andrew Morton --- .../admin-guide/kdump/vmcoreinfo.rst | 6 +-- .../admin-guide/kernel-parameters.txt | 2 +- arch/arc/Kconfig | 4 +- arch/arm/Kconfig | 9 ++--- arch/arm/configs/imx_v6_v7_defconfig | 2 +- arch/arm/configs/milbeaut_m10v_defconfig | 2 +- arch/arm/configs/oxnas_v6_defconfig | 2 +- arch/arm/configs/pxa_defconfig | 2 +- arch/arm/configs/sama7_defconfig | 2 +- arch/arm/configs/sp7021_defconfig | 2 +- arch/arm64/Kconfig | 27 ++++++------- arch/arm64/include/asm/sparsemem.h | 2 +- arch/arm64/kvm/hyp/include/nvhe/gfp.h | 2 +- arch/arm64/kvm/hyp/nvhe/page_alloc.c | 10 ++--- arch/csky/Kconfig | 2 +- arch/ia64/Kconfig | 8 ++-- arch/ia64/include/asm/sparsemem.h | 4 +- arch/ia64/mm/hugetlbpage.c | 2 +- arch/loongarch/Kconfig | 15 +++----- arch/m68k/Kconfig.cpu | 5 +-- arch/mips/Kconfig | 19 ++++------ arch/nios2/Kconfig | 7 +--- arch/powerpc/Kconfig | 27 ++++++------- arch/powerpc/configs/85xx/ge_imp3a_defconfig | 2 +- arch/powerpc/configs/fsl-emb-nonhw.config | 2 +- arch/powerpc/mm/book3s64/iommu_api.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/sh/configs/ecovec24_defconfig | 2 +- arch/sh/mm/Kconfig | 17 ++++----- arch/sparc/Kconfig | 5 +-- arch/sparc/kernel/pci_sun4v.c | 2 +- arch/sparc/kernel/traps_64.c | 2 +- arch/sparc/mm/tsb.c | 4 +- arch/um/kernel/um_arch.c | 4 +- arch/xtensa/Kconfig | 5 +-- drivers/base/regmap/regmap-debugfs.c | 8 ++-- drivers/block/floppy.c | 2 +- drivers/crypto/ccp/sev-dev.c | 2 +- drivers/crypto/hisilicon/sgl.c | 6 +-- drivers/gpu/drm/i915/gem/i915_gem_internal.c | 2 +- .../gpu/drm/i915/gem/selftests/huge_pages.c | 2 +- drivers/gpu/drm/ttm/ttm_pool.c | 22 +++++------ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 2 +- drivers/iommu/dma-iommu.c | 2 +- drivers/irqchip/irq-gic-v3-its.c | 4 +- drivers/md/dm-bufio.c | 2 +- drivers/misc/genwqe/card_dev.c | 2 +- drivers/misc/genwqe/card_utils.c | 4 +- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/ibm/ibmvnic.h | 2 +- drivers/video/fbdev/hyperv_fb.c | 4 +- drivers/video/fbdev/vermilion/vermilion.c | 2 +- drivers/virtio/virtio_balloon.c | 2 +- drivers/virtio/virtio_mem.c | 12 +++--- fs/ramfs/file-nommu.c | 2 +- include/drm/ttm/ttm_pool.h | 2 +- include/linux/hugetlb.h | 2 +- include/linux/mmzone.h | 10 ++--- include/linux/pageblock-flags.h | 4 +- include/linux/slab.h | 6 +-- kernel/crash_core.c | 2 +- kernel/dma/pool.c | 6 +-- kernel/events/ring_buffer.c | 6 +-- mm/Kconfig | 10 ++--- mm/compaction.c | 8 ++-- mm/debug_vm_pgtable.c | 4 +- mm/huge_memory.c | 2 +- mm/hugetlb.c | 4 +- mm/kmsan/init.c | 6 +-- mm/memblock.c | 2 +- mm/memory_hotplug.c | 4 +- mm/page_alloc.c | 38 +++++++++---------- mm/page_isolation.c | 12 +++--- mm/page_owner.c | 6 +-- mm/page_reporting.c | 6 +-- mm/shuffle.h | 2 +- mm/slab.c | 2 +- mm/slub.c | 6 +-- mm/vmscan.c | 2 +- mm/vmstat.c | 14 +++---- net/smc/smc_ib.c | 2 +- security/integrity/ima/ima_crypto.c | 2 +- tools/testing/memblock/linux/mmzone.h | 6 +-- 84 files changed, 223 insertions(+), 253 deletions(-) diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst index 86fd88492870..c18d94fa6470 100644 --- a/Documentation/admin-guide/kdump/vmcoreinfo.rst +++ b/Documentation/admin-guide/kdump/vmcoreinfo.rst @@ -172,7 +172,7 @@ variables. Offset of the free_list's member. This value is used to compute the number of free pages. -Each zone has a free_area structure array called free_area[MAX_ORDER]. +Each zone has a free_area structure array called free_area[MAX_ORDER + 1]. The free_list represents a linked list of free page blocks. (list_head, next|prev) @@ -189,8 +189,8 @@ Offsets of the vmap_area's members. They carry vmalloc-specific information. Makedumpfile gets the start address of the vmalloc region from this. -(zone.free_area, MAX_ORDER) ---------------------------- +(zone.free_area, MAX_ORDER + 1) +------------------------------- Free areas descriptor. User-space tools use this value to iterate the free_area ranges. MAX_ORDER is used by the zone buddy allocator. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..50da4f26fad5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3969,7 +3969,7 @@ [KNL] Minimal page reporting order Format: Adjust the minimal page reporting order. The page - reporting is disabled when it exceeds (MAX_ORDER-1). + reporting is disabled when it exceeds MAX_ORDER. panic= [KNL] Kernel behaviour on panic: delay timeout > 0: seconds before rebooting diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index d9a13ccf89a3..ab6d701365bb 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -556,7 +556,7 @@ endmenu # "ARC Architecture Configuration" config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - default "12" if ARC_HUGEPAGE_16M - default "11" + default "11" if ARC_HUGEPAGE_16M + default "10" source "kernel/power/Kconfig" diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e24a9820e12f..929e646e84b9 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1355,9 +1355,9 @@ config ARM_MODULE_PLTS config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - default "12" if SOC_AM33XX - default "9" if SA1111 - default "11" + default "11" if SOC_AM33XX + default "8" if SA1111 + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -1366,9 +1366,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - config ALIGNMENT_TRAP def_bool CPU_CP15_MMU select HAVE_PROC_CPU if PROC_FS diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 6dc6fed12af8..345a67e67dbd 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -31,7 +31,7 @@ CONFIG_SOC_VF610=y CONFIG_SMP=y CONFIG_ARM_PSCI=y CONFIG_HIGHMEM=y -CONFIG_ARCH_FORCE_MAX_ORDER=14 +CONFIG_ARCH_FORCE_MAX_ORDER=13 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200" CONFIG_KEXEC=y CONFIG_CPU_FREQ=y diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig index bd29e5012cb0..385ad0f391a8 100644 --- a/arch/arm/configs/milbeaut_m10v_defconfig +++ b/arch/arm/configs/milbeaut_m10v_defconfig @@ -26,7 +26,7 @@ CONFIG_THUMB2_KERNEL=y # CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11 is not set # CONFIG_ARM_PATCH_IDIV is not set CONFIG_HIGHMEM=y -CONFIG_ARCH_FORCE_MAX_ORDER=12 +CONFIG_ARCH_FORCE_MAX_ORDER=11 CONFIG_SECCOMP=y CONFIG_KEXEC=y CONFIG_EFI=y diff --git a/arch/arm/configs/oxnas_v6_defconfig b/arch/arm/configs/oxnas_v6_defconfig index 70a67b3fc91b..90779812c6dd 100644 --- a/arch/arm/configs/oxnas_v6_defconfig +++ b/arch/arm/configs/oxnas_v6_defconfig @@ -12,7 +12,7 @@ CONFIG_ARCH_OXNAS=y CONFIG_MACH_OX820=y CONFIG_SMP=y CONFIG_NR_CPUS=16 -CONFIG_ARCH_FORCE_MAX_ORDER=12 +CONFIG_ARCH_FORCE_MAX_ORDER=11 CONFIG_SECCOMP=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index e656d3af2266..b46e39369dbb 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -20,7 +20,7 @@ CONFIG_PXA_SHARPSL=y CONFIG_MACH_AKITA=y CONFIG_MACH_BORZOI=y CONFIG_AEABI=y -CONFIG_ARCH_FORCE_MAX_ORDER=9 +CONFIG_ARCH_FORCE_MAX_ORDER=8 CONFIG_CMDLINE="root=/dev/ram0 ro" CONFIG_KEXEC=y CONFIG_CPU_FREQ=y diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig index 0d964c613d71..954112041403 100644 --- a/arch/arm/configs/sama7_defconfig +++ b/arch/arm/configs/sama7_defconfig @@ -19,7 +19,7 @@ CONFIG_ATMEL_CLOCKSOURCE_TCB=y # CONFIG_CACHE_L2X0 is not set # CONFIG_ARM_PATCH_IDIV is not set # CONFIG_CPU_SW_DOMAIN_PAN is not set -CONFIG_ARCH_FORCE_MAX_ORDER=15 +CONFIG_ARCH_FORCE_MAX_ORDER=14 CONFIG_UACCESS_WITH_MEMCPY=y # CONFIG_ATAGS is not set CONFIG_CMDLINE="console=ttyS0,115200 earlyprintk ignore_loglevel" diff --git a/arch/arm/configs/sp7021_defconfig b/arch/arm/configs/sp7021_defconfig index 5bca2eb59b86..c6448ac860b6 100644 --- a/arch/arm/configs/sp7021_defconfig +++ b/arch/arm/configs/sp7021_defconfig @@ -17,7 +17,7 @@ CONFIG_ARCH_SUNPLUS=y # CONFIG_VDSO is not set CONFIG_SMP=y CONFIG_THUMB2_KERNEL=y -CONFIG_ARCH_FORCE_MAX_ORDER=12 +CONFIG_ARCH_FORCE_MAX_ORDER=11 CONFIG_VFP=y CONFIG_NEON=y CONFIG_MODULES=y diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1023e896d46b..cb5c6aa3254e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1476,22 +1476,22 @@ config XEN # include/linux/mmzone.h requires the following to be true: # -# MAX_ORDER - 1 + PAGE_SHIFT <= SECTION_SIZE_BITS +# MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS # -# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS + 1 - PAGE_SHIFT: +# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT: # # | SECTION_SIZE_BITS | PAGE_SHIFT | max MAX_ORDER | default MAX_ORDER | # ----+-------------------+--------------+-----------------+--------------------+ -# 4K | 27 | 12 | 16 | 11 | -# 16K | 27 | 14 | 14 | 12 | -# 64K | 29 | 16 | 14 | 14 | +# 4K | 27 | 12 | 15 | 10 | +# 16K | 27 | 14 | 13 | 11 | +# 64K | 29 | 16 | 13 | 13 | config ARCH_FORCE_MAX_ORDER int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES - default "14" if ARM64_64K_PAGES - range 12 14 if ARM64_16K_PAGES - default "12" if ARM64_16K_PAGES - range 11 16 if ARM64_4K_PAGES - default "11" + default "13" if ARM64_64K_PAGES + range 11 13 if ARM64_16K_PAGES + default "11" if ARM64_16K_PAGES + range 10 15 if ARM64_4K_PAGES + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -1500,14 +1500,11 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - We make sure that we can allocate up to a HugePage size for each configuration. Hence we have : - MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2 + MAX_ORDER = PMD_SHIFT - PAGE_SHIFT => PAGE_SHIFT - 3 - However for 4K, we choose a higher default value, 11 as opposed to 10, giving us + However for 4K, we choose a higher default value, 10 as opposed to 9, giving us 4M allocations matching the default size used by generic code. config UNMAP_KERNEL_AT_EL0 diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 4b73463423c3..5f5437621029 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -10,7 +10,7 @@ /* * Section size must be at least 512MB for 64K base * page size config. Otherwise it will be less than - * (MAX_ORDER - 1) and the build process will fail. + * MAX_ORDER and the build process will fail. */ #ifdef CONFIG_ARM64_64K_PAGES #define SECTION_SIZE_BITS 29 diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h index 0a048dc06a7d..fe5472a184a3 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h @@ -16,7 +16,7 @@ struct hyp_pool { * API at EL2. */ hyp_spinlock_t lock; - struct list_head free_area[MAX_ORDER]; + struct list_head free_area[MAX_ORDER + 1]; phys_addr_t range_start; phys_addr_t range_end; unsigned short max_order; diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c index 803ba3222e75..b1e392186a0f 100644 --- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -110,7 +110,7 @@ static void __hyp_attach_page(struct hyp_pool *pool, * after coalescing, so make sure to mark it HYP_NO_ORDER proactively. */ p->order = HYP_NO_ORDER; - for (; (order + 1) < pool->max_order; order++) { + for (; (order + 1) <= pool->max_order; order++) { buddy = __find_buddy_avail(pool, p, order); if (!buddy) break; @@ -203,9 +203,9 @@ void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order) hyp_spin_lock(&pool->lock); /* Look for a high-enough-order page */ - while (i < pool->max_order && list_empty(&pool->free_area[i])) + while (i <= pool->max_order && list_empty(&pool->free_area[i])) i++; - if (i >= pool->max_order) { + if (i > pool->max_order) { hyp_spin_unlock(&pool->lock); return NULL; } @@ -228,8 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages, int i; hyp_spin_lock_init(&pool->lock); - pool->max_order = min(MAX_ORDER, get_order((nr_pages + 1) << PAGE_SHIFT)); - for (i = 0; i < pool->max_order; i++) + pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT)); + for (i = 0; i <= pool->max_order; i++) INIT_LIST_HEAD(&pool->free_area[i]); pool->range_start = phys; pool->range_end = phys + (nr_pages << PAGE_SHIFT); diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index dba02da6fa34..c694fac43bed 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -334,7 +334,7 @@ config HIGHMEM config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - default "11" + default "10" config DRAM_BASE hex "DRAM start addr (the same with memory-section in dts)" diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index d7e4a24e8644..0d2f41fa56ee 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -202,10 +202,10 @@ config IA64_CYCLONE If you're unsure, answer N. config ARCH_FORCE_MAX_ORDER - int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE - range 11 17 if !HUGETLB_PAGE - default "17" if HUGETLB_PAGE - default "11" + int "MAX_ORDER (10 - 16)" if !HUGETLB_PAGE + range 10 16 if !HUGETLB_PAGE + default "16" if HUGETLB_PAGE + default "10" config SMP bool "Symmetric multi-processing support" diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index 84e8ce387b69..a58f8b466d96 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -12,9 +12,9 @@ #define SECTION_SIZE_BITS (30) #define MAX_PHYSMEM_BITS (50) #ifdef CONFIG_ARCH_FORCE_MAX_ORDER -#if ((CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS) +#if (CONFIG_ARCH_FORCE_MAX_ORDER + PAGE_SHIFT > SECTION_SIZE_BITS) #undef SECTION_SIZE_BITS -#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT) +#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER + PAGE_SHIFT) #endif #endif diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 380d2f3966c9..e8dd4323fb86 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -170,7 +170,7 @@ static int __init hugetlb_setup_sz(char *str) size = memparse(str, &str); if (*str || !is_power_of_2(size) || !(tr_pages & size) || size <= PAGE_SIZE || - size >= (1UL << PAGE_SHIFT << MAX_ORDER)) { + size > (1UL << PAGE_SHIFT << MAX_ORDER)) { printk(KERN_WARNING "Invalid huge page size specified\n"); return 1; } diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 7fd51257e0ed..272a3a12c98d 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -420,12 +420,12 @@ config NODES_SHIFT config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 14 64 if PAGE_SIZE_64KB - default "14" if PAGE_SIZE_64KB - range 12 64 if PAGE_SIZE_16KB - default "12" if PAGE_SIZE_16KB - range 11 64 - default "11" + range 13 63 if PAGE_SIZE_64KB + default "13" if PAGE_SIZE_64KB + range 11 63 if PAGE_SIZE_16KB + default "11" if PAGE_SIZE_16KB + range 10 63 + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -434,9 +434,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - The page size is not necessarily 4KB. Keep this in mind when choosing a value for this option. diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index 9380f6e3bb66..c9df6572133f 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -400,7 +400,7 @@ config SINGLE_MEMORY_CHUNK config ARCH_FORCE_MAX_ORDER int "Maximum zone order" if ADVANCED depends on !SINGLE_MEMORY_CHUNK - default "11" + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -413,9 +413,6 @@ config ARCH_FORCE_MAX_ORDER value also defines the minimal size of the hole that allows freeing unused memory map. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - config 060_WRITETHROUGH bool "Use write-through caching for 68060 supervisor accesses" depends on ADVANCED && M68060 diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e2f3ca73f40d..3e8b765b8c7b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2137,14 +2137,14 @@ endchoice config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB - default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB - range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB - default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB - range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB - default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB - range 0 64 - default "11" + range 13 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB + default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB + range 12 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB + default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB + range 11 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB + default "11" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB + range 0 63 + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -2153,9 +2153,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - The page size is not necessarily 4KB. Keep this in mind when choosing a value for this option. diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index a582f72104f3..89708b95978c 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -46,8 +46,8 @@ source "kernel/Kconfig.hz" config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 9 20 - default "11" + range 8 19 + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -56,9 +56,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - endmenu source "arch/nios2/platform/Kconfig.platform" diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 49c6d36b2b3e..24d56536b269 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -897,18 +897,18 @@ config DATA_SHIFT config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 8 9 if PPC64 && PPC_64K_PAGES - default "9" if PPC64 && PPC_64K_PAGES - range 13 13 if PPC64 && !PPC_64K_PAGES - default "13" if PPC64 && !PPC_64K_PAGES - range 9 64 if PPC32 && PPC_16K_PAGES - default "9" if PPC32 && PPC_16K_PAGES - range 7 64 if PPC32 && PPC_64K_PAGES - default "7" if PPC32 && PPC_64K_PAGES - range 5 64 if PPC32 && PPC_256K_PAGES - default "5" if PPC32 && PPC_256K_PAGES - range 11 64 - default "11" + range 7 8 if PPC64 && PPC_64K_PAGES + default "8" if PPC64 && PPC_64K_PAGES + range 12 12 if PPC64 && !PPC_64K_PAGES + default "12" if PPC64 && !PPC_64K_PAGES + range 8 63 if PPC32 && PPC_16K_PAGES + default "8" if PPC32 && PPC_16K_PAGES + range 6 63 if PPC32 && PPC_64K_PAGES + default "6" if PPC32 && PPC_64K_PAGES + range 4 63 if PPC32 && PPC_256K_PAGES + default "4" if PPC32 && PPC_256K_PAGES + range 10 63 + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -917,9 +917,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - The page size is not necessarily 4KB. For example, on 64-bit systems, 64KB pages can be enabled via CONFIG_PPC_64K_PAGES. Keep this in mind when choosing a value for this option. diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig index ea719898b581..6cb7e90d52c1 100644 --- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig +++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig @@ -30,7 +30,7 @@ CONFIG_PREEMPT=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y -CONFIG_ARCH_FORCE_MAX_ORDER=17 +CONFIG_ARCH_FORCE_MAX_ORDER=16 CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_MSI=y diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config index ab8a8c4530d9..3009b0efaf34 100644 --- a/arch/powerpc/configs/fsl-emb-nonhw.config +++ b/arch/powerpc/configs/fsl-emb-nonhw.config @@ -41,7 +41,7 @@ CONFIG_FIXED_PHY=y CONFIG_FONT_8x16=y CONFIG_FONT_8x8=y CONFIG_FONTS=y -CONFIG_ARCH_FORCE_MAX_ORDER=13 +CONFIG_ARCH_FORCE_MAX_ORDER=12 CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAME_WARN=1024 CONFIG_FTL=y diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index 7fcfba162e0d..81d7185e2ae8 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -97,7 +97,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, } mmap_read_lock(mm); - chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) / + chunk = (1UL << (PAGE_SHIFT + MAX_ORDER)) / sizeof(struct vm_area_struct *); chunk = min(chunk, entries); for (entry = 0; entry < entries; entry += chunk) { diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index f1ba8d1e8c1a..b900933507da 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -615,7 +615,7 @@ void __init gigantic_hugetlb_cma_reserve(void) order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; if (order) { - VM_WARN_ON(order < MAX_ORDER); + VM_WARN_ON(order <= MAX_ORDER); hugetlb_cma_reserve(order); } } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 4f6e20a35aa1..5a81f106068e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1740,7 +1740,7 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) * DMA window can be larger than available memory, which will * cause errors later. */ - const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER - 1); + const u64 maxblock = 1UL << (PAGE_SHIFT + MAX_ORDER); /* * We create the default window as big as we can. The constraint is diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig index b52e14ccb450..4d655e8d4d74 100644 --- a/arch/sh/configs/ecovec24_defconfig +++ b/arch/sh/configs/ecovec24_defconfig @@ -8,7 +8,7 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH7724=y -CONFIG_ARCH_FORCE_MAX_ORDER=12 +CONFIG_ARCH_FORCE_MAX_ORDER=11 CONFIG_MEMORY_SIZE=0x10000000 CONFIG_FLATMEM_MANUAL=y CONFIG_SH_ECOVEC=y diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 411fdc0901f7..40271090bd7d 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -20,13 +20,13 @@ config PAGE_OFFSET config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 9 64 if PAGE_SIZE_16KB - default "9" if PAGE_SIZE_16KB - range 7 64 if PAGE_SIZE_64KB - default "7" if PAGE_SIZE_64KB - range 11 64 - default "14" if !MMU - default "11" + range 8 63 if PAGE_SIZE_16KB + default "8" if PAGE_SIZE_16KB + range 6 63 if PAGE_SIZE_64KB + default "6" if PAGE_SIZE_64KB + range 10 63 + default "13" if !MMU + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -35,9 +35,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - The page size is not necessarily 4KB. Keep this in mind when choosing a value for this option. diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 84437a4c6545..e3242bf5a8df 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -271,7 +271,7 @@ config ARCH_SPARSEMEM_DEFAULT config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - default "13" + default "12" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -280,9 +280,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 13 means that the largest free memory block is 2^12 pages. - if SPARC64 || COMPILE_TEST source "kernel/power/Kconfig" endif diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 384480971805..7d91ca6aa675 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -193,7 +193,7 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size, size = IO_PAGE_ALIGN(size); order = get_order(size); - if (unlikely(order >= MAX_ORDER)) + if (unlikely(order > MAX_ORDER)) return NULL; npages = size >> IO_PAGE_SHIFT; diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 5b4de4a89dec..08ffd17d5ec3 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -897,7 +897,7 @@ void __init cheetah_ecache_flush_init(void) /* Now allocate error trap reporting scoreboard. */ sz = NR_CPUS * (2 * sizeof(struct cheetah_err_info)); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { if ((PAGE_SIZE << order) >= sz) break; } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index dba8dffe2113..5e2931a18409 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss) unsigned long new_rss_limit; gfp_t gfp_flags; - if (max_tsb_size > (PAGE_SIZE << (MAX_ORDER - 1))) - max_tsb_size = (PAGE_SIZE << (MAX_ORDER - 1)); + if (max_tsb_size > PAGE_SIZE << MAX_ORDER) + max_tsb_size = PAGE_SIZE << MAX_ORDER; new_cache_index = 0; for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 5e5a9c8e0e5d..8dcda617b8bf 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -368,10 +368,10 @@ int __init linux_main(int argc, char **argv) max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC; /* - * Zones have to begin on a 1 << MAX_ORDER-1 page boundary, + * Zones have to begin on a 1 << MAX_ORDER page boundary, * so this makes sure that's true for highmem */ - max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER - 1)) - 1); + max_physmem &= ~((1 << (PAGE_SHIFT + MAX_ORDER)) - 1); if (physmem_size + iomem_size > max_physmem) { highmem = physmem_size + iomem_size - max_physmem; physmem_size -= highmem; diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index bcb0c5d2abc2..3eee334ba873 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -773,7 +773,7 @@ config HIGHMEM config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - default "11" + default "10" help The kernel memory allocator divides physically contiguous memory blocks into "zones", where each zone is a power of two number of @@ -782,9 +782,6 @@ config ARCH_FORCE_MAX_ORDER blocks of physically contiguous memory, then you may need to increase this value. - This config option is actually maximum order plus one. For example, - a value of 11 means that the largest free memory block is 2^10 pages. - endmenu menu "Power management options" diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index 817eda2075aa..c491fabe3617 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -226,8 +226,8 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from, if (*ppos < 0 || !count) return -EINVAL; - if (count > (PAGE_SIZE << (MAX_ORDER - 1))) - count = PAGE_SIZE << (MAX_ORDER - 1); + if (count > (PAGE_SIZE << MAX_ORDER)) + count = PAGE_SIZE << MAX_ORDER; buf = kmalloc(count, GFP_KERNEL); if (!buf) @@ -373,8 +373,8 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file, if (*ppos < 0 || !count) return -EINVAL; - if (count > (PAGE_SIZE << (MAX_ORDER - 1))) - count = PAGE_SIZE << (MAX_ORDER - 1); + if (count > (PAGE_SIZE << MAX_ORDER)) + count = PAGE_SIZE << MAX_ORDER; buf = kmalloc(count, GFP_KERNEL); if (!buf) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 90d2dfb6448e..cec2c20f5e59 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3079,7 +3079,7 @@ static void raw_cmd_free(struct floppy_raw_cmd **ptr) } } -#define MAX_LEN (1UL << (MAX_ORDER - 1) << PAGE_SHIFT) +#define MAX_LEN (1UL << MAX_ORDER << PAGE_SHIFT) static int raw_cmd_copyin(int cmd, void __user *param, struct floppy_raw_cmd **rcmd) diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index e2f25926eb51..bf095baca244 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -886,7 +886,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) /* * The length of the ID shouldn't be assumed by software since * it may change in the future. The allocation size is limited - * to 1 << (PAGE_SHIFT + MAX_ORDER - 1) by the page allocator. + * to 1 << (PAGE_SHIFT + MAX_ORDER) by the page allocator. * If the allocation fails, simply return ENOMEM rather than * warning in the kernel log. */ diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 09586a837b1e..3df7a256e919 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -70,11 +70,11 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, HISI_ACC_SGL_ALIGN_SIZE); /* - * the pool may allocate a block of memory of size PAGE_SIZE * 2^(MAX_ORDER - 1), + * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_ORDER, * block size may exceed 2^31 on ia64, so the max of block size is 2^31 */ - block_size = 1 << (PAGE_SHIFT + MAX_ORDER <= 32 ? - PAGE_SHIFT + MAX_ORDER - 1 : 31); + block_size = 1 << (PAGE_SHIFT + MAX_ORDER < 32 ? + PAGE_SHIFT + MAX_ORDER : 31); sgl_num_per_block = block_size / sgl_size; block_num = count / sgl_num_per_block; remain_sgl = count % sgl_num_per_block; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index eae9e9f6d3bf..6bc26b4b06b8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -36,7 +36,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct sg_table *st; struct scatterlist *sg; unsigned int npages; /* restricted by sg_alloc_table */ - int max_order = MAX_ORDER - 1; + int max_order = MAX_ORDER; unsigned int max_segment; gfp_t gfp; diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index defece0bcb81..99f39a5feca1 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -115,7 +115,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj) do { struct page *page; - GEM_BUG_ON(order >= MAX_ORDER); + GEM_BUG_ON(order > MAX_ORDER); page = alloc_pages(GFP | __GFP_ZERO, order); if (!page) goto err; diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c index aa116a7bbae3..6c8585abe08d 100644 --- a/drivers/gpu/drm/ttm/ttm_pool.c +++ b/drivers/gpu/drm/ttm/ttm_pool.c @@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644); static atomic_long_t allocated_pages; -static struct ttm_pool_type global_write_combined[MAX_ORDER]; -static struct ttm_pool_type global_uncached[MAX_ORDER]; +static struct ttm_pool_type global_write_combined[MAX_ORDER + 1]; +static struct ttm_pool_type global_uncached[MAX_ORDER + 1]; -static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER]; -static struct ttm_pool_type global_dma32_uncached[MAX_ORDER]; +static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1]; +static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1]; static spinlock_t shrinker_lock; static struct list_head shrinker_list; @@ -405,7 +405,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt, else gfp_flags |= GFP_HIGHUSER; - for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages)); + for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages)); num_pages; order = min_t(unsigned int, order, __fls(num_pages))) { struct ttm_pool_type *pt; @@ -542,7 +542,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev, if (use_dma_alloc) { for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < MAX_ORDER; ++j) + for (j = 0; j <= MAX_ORDER; ++j) ttm_pool_type_init(&pool->caching[i].orders[j], pool, i, j); } @@ -562,7 +562,7 @@ void ttm_pool_fini(struct ttm_pool *pool) if (pool->use_dma_alloc) { for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) - for (j = 0; j < MAX_ORDER; ++j) + for (j = 0; j <= MAX_ORDER; ++j) ttm_pool_type_fini(&pool->caching[i].orders[j]); } @@ -616,7 +616,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m) unsigned int i; seq_puts(m, "\t "); - for (i = 0; i < MAX_ORDER; ++i) + for (i = 0; i <= MAX_ORDER; ++i) seq_printf(m, " ---%2u---", i); seq_puts(m, "\n"); } @@ -627,7 +627,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt, { unsigned int i; - for (i = 0; i < MAX_ORDER; ++i) + for (i = 0; i <= MAX_ORDER; ++i) seq_printf(m, " %8u", ttm_pool_type_count(&pt[i])); seq_puts(m, "\n"); } @@ -736,7 +736,7 @@ int ttm_pool_mgr_init(unsigned long num_pages) spin_lock_init(&shrinker_lock); INIT_LIST_HEAD(&shrinker_list); - for (i = 0; i < MAX_ORDER; ++i) { + for (i = 0; i <= MAX_ORDER; ++i) { ttm_pool_type_init(&global_write_combined[i], NULL, ttm_write_combined, i); ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i); @@ -769,7 +769,7 @@ void ttm_pool_mgr_fini(void) { unsigned int i; - for (i = 0; i < MAX_ORDER; ++i) { + for (i = 0; i <= MAX_ORDER; ++i) { ttm_pool_type_fini(&global_write_combined[i]); ttm_pool_type_fini(&global_uncached[i]); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 8d772ea8a583..b574c58a3487 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -182,7 +182,7 @@ #ifdef CONFIG_CMA_ALIGNMENT #define Q_MAX_SZ_SHIFT (PAGE_SHIFT + CONFIG_CMA_ALIGNMENT) #else -#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + MAX_ORDER - 1) +#define Q_MAX_SZ_SHIFT (PAGE_SHIFT + MAX_ORDER) #endif /* diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index ac996fd6bd9c..7a9f0b0bddbd 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -736,7 +736,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev, struct page **pages; unsigned int i = 0, nid = dev_to_node(dev); - order_mask &= GENMASK(MAX_ORDER - 1, 0); + order_mask &= GENMASK(MAX_ORDER, 0); if (!order_mask) return NULL; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 586271b8aa39..85790b870877 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2440,8 +2440,8 @@ static bool its_parse_indirect_baser(struct its_node *its, * feature is not supported by hardware. */ new_order = max_t(u32, get_order(esz << ids), new_order); - if (new_order >= MAX_ORDER) { - new_order = MAX_ORDER - 1; + if (new_order > MAX_ORDER) { + new_order = MAX_ORDER; ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz); pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n", &its->phys_base, its_base_type_string[type], diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index cf077f9b30c3..733053c2eaa0 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -408,7 +408,7 @@ static void __cache_size_refresh(void) * If the allocation may fail we use __get_free_pages. Memory fragmentation * won't have a fatal effect here, but it just causes flushes of some other * buffers and more I/O will be performed. Don't use __get_free_pages if it - * always fails (i.e. order >= MAX_ORDER). + * always fails (i.e. order > MAX_ORDER). * * If the allocation shouldn't fail we use __vmalloc. This is only for the * initial reserve allocation, so there's no risk of wasting all vmalloc diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c index d0e27438a73c..55fc5b80e649 100644 --- a/drivers/misc/genwqe/card_dev.c +++ b/drivers/misc/genwqe/card_dev.c @@ -443,7 +443,7 @@ static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma) if (vsize == 0) return -EINVAL; - if (get_order(vsize) >= MAX_ORDER) + if (get_order(vsize) > MAX_ORDER) return -ENOMEM; dma_map = kzalloc(sizeof(struct dma_mapping), GFP_KERNEL); diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c index ac29698d085a..1c798d6b2dfb 100644 --- a/drivers/misc/genwqe/card_utils.c +++ b/drivers/misc/genwqe/card_utils.c @@ -210,7 +210,7 @@ u32 genwqe_crc32(u8 *buff, size_t len, u32 init) void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size, dma_addr_t *dma_handle) { - if (get_order(size) >= MAX_ORDER) + if (get_order(size) > MAX_ORDER) return NULL; return dma_alloc_coherent(&cd->pci_dev->dev, size, dma_handle, @@ -308,7 +308,7 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl, sgl->write = write; sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages); - if (get_order(sgl->sgl_size) >= MAX_ORDER) { + if (get_order(sgl->sgl_size) > MAX_ORDER) { dev_err(&pci_dev->dev, "[%s] err: too much memory requested!\n", __func__); return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 25be7f8ac7cd..3973ca6adf4c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1041,7 +1041,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) return; order = get_order(alloc_size); - if (order >= MAX_ORDER) { + if (order > MAX_ORDER) { if (net_ratelimit()) dev_warn(ring_to_dev(ring), "failed to allocate tx spare buffer, exceed to max order\n"); return; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index b35c9b6f913b..4e18b4cefa97 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -75,7 +75,7 @@ * pool for the 4MB. Thus the 16 Rx and Tx queues require 32 * 5 = 160 * plus 16 for the TSO pools for a total of 176 LTB mappings per VNIC. */ -#define IBMVNIC_ONE_LTB_MAX ((u32)((1 << (MAX_ORDER - 1)) * PAGE_SIZE)) +#define IBMVNIC_ONE_LTB_MAX ((u32)((1 << MAX_ORDER) * PAGE_SIZE)) #define IBMVNIC_ONE_LTB_SIZE min((u32)(8 << 20), IBMVNIC_ONE_LTB_MAX) #define IBMVNIC_LTB_SET_SIZE (38 << 20) diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index ec3f6cf05f8c..34781dec3856 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -946,7 +946,7 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev, if (request_size == 0) return -1; - if (order < MAX_ORDER) { + if (order <= MAX_ORDER) { /* Call alloc_pages if the size is less than 2^MAX_ORDER */ page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (!page) @@ -977,7 +977,7 @@ static void hvfb_release_phymem(struct hv_device *hdev, { unsigned int order = get_order(size); - if (order < MAX_ORDER) + if (order <= MAX_ORDER) __free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order); else dma_free_coherent(&hdev->device, diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c index 0374ee6b6d03..32e74e02a02f 100644 --- a/drivers/video/fbdev/vermilion/vermilion.c +++ b/drivers/video/fbdev/vermilion/vermilion.c @@ -197,7 +197,7 @@ static int vmlfb_alloc_vram(struct vml_info *vinfo, va = &vinfo->vram[i]; order = 0; - while (requested > (PAGE_SIZE << order) && order < MAX_ORDER) + while (requested > (PAGE_SIZE << order) && order <= MAX_ORDER) order++; err = vmlfb_alloc_vram_area(va, order, 0); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 3f78a3a1eb75..5b15936a5214 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -33,7 +33,7 @@ #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \ __GFP_NOMEMALLOC) /* The order of free page blocks to report to host */ -#define VIRTIO_BALLOON_HINT_BLOCK_ORDER (MAX_ORDER - 1) +#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_ORDER /* The size of a free page block in bytes */ #define VIRTIO_BALLOON_HINT_BLOCK_BYTES \ (1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT)) diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 0c2892ec6817..835f6cc2fb66 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -1120,13 +1120,13 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn, */ static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages) { - unsigned long order = MAX_ORDER - 1; + unsigned long order = MAX_ORDER; unsigned long i; /* * We might get called for ranges that don't cover properly aligned - * MAX_ORDER - 1 pages; however, we can only online properly aligned - * pages with an order of MAX_ORDER - 1 at maximum. + * MAX_ORDER pages; however, we can only online properly aligned + * pages with an order of MAX_ORDER at maximum. */ while (!IS_ALIGNED(pfn | nr_pages, 1 << order)) order--; @@ -1237,9 +1237,9 @@ static void virtio_mem_online_page(struct virtio_mem *vm, bool do_online; /* - * We can get called with any order up to MAX_ORDER - 1. If our - * subblock size is smaller than that and we have a mixture of plugged - * and unplugged subblocks within such a page, we have to process in + * We can get called with any order up to MAX_ORDER. If our subblock + * size is smaller than that and we have a mixture of plugged and + * unplugged subblocks within such a page, we have to process in * smaller granularity. In that case we'll adjust the order exactly once * within the loop. */ diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 2f67516bb9bf..9fbb9b5256f7 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -70,7 +70,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* make various checks */ order = get_order(newsize); - if (unlikely(order >= MAX_ORDER)) + if (unlikely(order > MAX_ORDER)) return -EFBIG; ret = inode_newsize_ok(inode, newsize); diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h index ef09b23d29e3..8ce14f9d202a 100644 --- a/include/drm/ttm/ttm_pool.h +++ b/include/drm/ttm/ttm_pool.h @@ -72,7 +72,7 @@ struct ttm_pool { bool use_dma32; struct { - struct ttm_pool_type orders[MAX_ORDER]; + struct ttm_pool_type orders[MAX_ORDER + 1]; } caching[TTM_NUM_CACHING_TYPES]; }; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..8fb7d91cd0b1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -818,7 +818,7 @@ static inline unsigned huge_page_shift(struct hstate *h) static inline bool hstate_is_gigantic(struct hstate *h) { - return huge_page_order(h) >= MAX_ORDER; + return huge_page_order(h) > MAX_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bf8786d45b31..35b11cc210d9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -26,11 +26,11 @@ /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER -#define MAX_ORDER 11 +#define MAX_ORDER 10 #else #define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -93,7 +93,7 @@ static inline bool migratetype_is_mergeable(int mt) } #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order <= MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; @@ -922,7 +922,7 @@ struct zone { CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ - struct free_area free_area[MAX_ORDER]; + struct free_area free_area[MAX_ORDER + 1]; /* zone flags, see below */ unsigned long flags; @@ -1745,7 +1745,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS +#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 5f1ae07d724b..e83c4c095041 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -41,14 +41,14 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ #else /* CONFIG_HUGETLB_PAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ -#define pageblock_order (MAX_ORDER-1) +#define pageblock_order MAX_ORDER #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 45af70315a94..aa4575ef2965 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -284,7 +284,7 @@ static inline unsigned int arch_slab_minalign(void) * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif @@ -292,7 +292,7 @@ static inline unsigned int arch_slab_minalign(void) #ifdef CONFIG_SLUB #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif @@ -305,7 +305,7 @@ static inline unsigned int arch_slab_minalign(void) * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 755f5f08ab38..90ce1dfd591c 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -474,7 +474,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(list_head, prev); VMCOREINFO_OFFSET(vmap_area, va_start); VMCOREINFO_OFFSET(vmap_area, list); - VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER); + VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER + 1); log_buf_vmcoreinfo_setup(); VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); VMCOREINFO_NUMBER(NR_FREE_PAGES); diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 4d40dcce7604..1acec2e22827 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -84,8 +84,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, void *addr; int ret = -ENOMEM; - /* Cannot allocate larger than MAX_ORDER-1 */ - order = min(get_order(pool_size), MAX_ORDER-1); + /* Cannot allocate larger than MAX_ORDER */ + order = min(get_order(pool_size), MAX_ORDER); do { pool_size = 1 << (PAGE_SHIFT + order); @@ -190,7 +190,7 @@ static int __init dma_atomic_pool_init(void) /* * If coherent_pool was not used on the command line, default the pool - * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER-1. + * sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER. */ if (!atomic_pool_size) { unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index d6bbdb7830b2..a0433f37b024 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -609,8 +609,8 @@ static struct page *rb_alloc_aux_page(int node, int order) { struct page *page; - if (order >= MAX_ORDER) - order = MAX_ORDER - 1; + if (order > MAX_ORDER) + order = MAX_ORDER; do { page = alloc_pages_node(node, PERF_AUX_GFP, order); @@ -814,7 +814,7 @@ struct perf_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct perf_buffer); size += nr_pages * sizeof(void *); - if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER) + if (order_base_2(size) > PAGE_SHIFT+MAX_ORDER) goto fail; node = (cpu == -1) ? cpu : cpu_to_node(cpu); diff --git a/mm/Kconfig b/mm/Kconfig index ca98b2072df5..969286ab14a1 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -346,9 +346,9 @@ config SHUFFLE_PAGE_ALLOCATOR the presence of a memory-side-cache. There are also incidental security benefits as it reduces the predictability of page allocations to compliment SLAB_FREELIST_RANDOM, but the - default granularity of shuffling on the "MAX_ORDER - 1" i.e, - 10th order of pages is selected based on cache utilization - benefits on x86. + default granularity of shuffling on the MAX_ORDER i.e, 10th + order of pages is selected based on cache utilization benefits + on x86. While the randomization improves cache utilization it may negatively impact workloads on platforms without a cache. For @@ -666,8 +666,8 @@ config HUGETLB_PAGE_SIZE_VARIABLE HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available on a platform. - Note that the pageblock_order cannot exceed MAX_ORDER - 1 and will be - clamped down to MAX_ORDER - 1. + Note that the pageblock_order cannot exceed MAX_ORDER and will be + clamped down to MAX_ORDER. config CONTIG_ALLOC def_bool (MEMORY_ISOLATION && COMPACTION) || CMA diff --git a/mm/compaction.c b/mm/compaction.c index 5a9501e0ae01..709136556b9e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -583,7 +583,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (PageCompound(page)) { const unsigned int order = compound_order(page); - if (likely(order < MAX_ORDER)) { + if (likely(order <= MAX_ORDER)) { blockpfn += (1UL << order) - 1; cursor += (1UL << order) - 1; } @@ -938,7 +938,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * a valid page order. Consider only values in the * valid order range to prevent low_pfn overflow. */ - if (freepage_order > 0 && freepage_order < MAX_ORDER) + if (freepage_order > 0 && freepage_order <= MAX_ORDER) low_pfn += (1UL << freepage_order) - 1; continue; } @@ -954,7 +954,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (PageCompound(page) && !cc->alloc_contig) { const unsigned int order = compound_order(page); - if (likely(order < MAX_ORDER)) + if (likely(order <= MAX_ORDER)) low_pfn += (1UL << order) - 1; goto isolate_fail; } @@ -2124,7 +2124,7 @@ static enum compact_result __compact_finished(struct compact_control *cc) /* Direct compactor: Is a suitable page free? */ ret = COMPACT_NO_SUITABLE_PAGE; - for (order = cc->order; order < MAX_ORDER; order++) { + for (order = cc->order; order <= MAX_ORDER; order++) { struct free_area *area = &cc->zone->free_area[order]; bool can_steal; diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 4362021b1ce7..c54177aabebd 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -1086,7 +1086,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order) struct page *page = NULL; #ifdef CONFIG_CONTIG_ALLOC - if (order >= MAX_ORDER) { + if (order > MAX_ORDER) { page = alloc_contig_pages((1 << order), GFP_KERNEL, first_online_node, NULL); if (page) { @@ -1096,7 +1096,7 @@ debug_vm_pgtable_alloc_huge_page(struct pgtable_debug_args *args, int order) } #endif - if (order < MAX_ORDER) + if (order <= MAX_ORDER) page = alloc_pages(GFP_KERNEL, order); return page; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2d860e70fe88..1df386d13d24 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -467,7 +467,7 @@ static int __init hugepage_init(void) /* * hugepages can't be allocated by the buddy allocator */ - MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER >= MAX_ORDER); + MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_ORDER); /* * we use page->mapping and page->index in second tail page * as list_head: assuming THP order >= 2 diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 712e32b38295..9122e50ae02a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2090,7 +2090,7 @@ pgoff_t hugetlb_basepage_index(struct page *page) pgoff_t index = page_index(page_head); unsigned long compound_idx; - if (compound_order(page_head) >= MAX_ORDER) + if (compound_order(page_head) > MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else compound_idx = page - page_head; @@ -4497,7 +4497,7 @@ static int __init default_hugepagesz_setup(char *s) * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge - * page size is gigantic (>= MAX_ORDER), then the pages must be + * page size is gigantic (> MAX_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { diff --git a/mm/kmsan/init.c b/mm/kmsan/init.c index 7fb794242fad..ffedf4dbc49d 100644 --- a/mm/kmsan/init.c +++ b/mm/kmsan/init.c @@ -96,7 +96,7 @@ void __init kmsan_init_shadow(void) struct metadata_page_pair { struct page *shadow, *origin; }; -static struct metadata_page_pair held_back[MAX_ORDER] __initdata; +static struct metadata_page_pair held_back[MAX_ORDER + 1] __initdata; /* * Eager metadata allocation. When the memblock allocator is freeing pages to @@ -211,8 +211,8 @@ static void kmsan_memblock_discard(void) * order=N-1, * - repeat. */ - collect.order = MAX_ORDER - 1; - for (int i = MAX_ORDER - 1; i >= 0; i--) { + collect.order = MAX_ORDER; + for (int i = MAX_ORDER; i >= 0; i--) { if (held_back[i].shadow) smallstack_push(&collect, held_back[i].shadow); if (held_back[i].origin) diff --git a/mm/memblock.c b/mm/memblock.c index 25fd0626a9e7..7911224b1ed3 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2043,7 +2043,7 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) int order; while (start < end) { - order = min(MAX_ORDER - 1UL, __ffs(start)); + order = min_t(int, MAX_ORDER, __ffs(start)); while (start + (1UL << order) > end) order--; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index db3b270254f1..c8f0a8c2d049 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -596,7 +596,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) unsigned long pfn; /* - * Online the pages in MAX_ORDER - 1 aligned chunks. The callback might + * Online the pages in MAX_ORDER aligned chunks. The callback might * decide to not expose all pages to the buddy (e.g., expose them * later). We account all pages as being online and belonging to this * zone ("present"). @@ -605,7 +605,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * this and the first chunk to online will be pageblock_nr_pages. */ for (pfn = start_pfn; pfn < end_pfn;) { - int order = min(MAX_ORDER - 1UL, __ffs(pfn)); + int order = min_t(int, MAX_ORDER, __ffs(pfn)); (*online_page_callback)(pfn_to_page(pfn), order); pfn += (1UL << order); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0936bde1d486..c3e49d028a7a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1063,7 +1063,7 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, unsigned long higher_page_pfn; struct page *higher_page; - if (order >= MAX_ORDER - 2) + if (order >= MAX_ORDER - 1) return false; higher_page_pfn = buddy_pfn & pfn; @@ -1118,7 +1118,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(pfn & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); - while (order < MAX_ORDER - 1) { + while (order < MAX_ORDER) { if (compaction_capture(capc, page, order, migratetype)) { __mod_zone_freepage_state(zone, -(1 << order), migratetype); @@ -2499,7 +2499,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, struct page *page; /* Find a page of the appropriate size in the preferred list */ - for (current_order = order; current_order < MAX_ORDER; ++current_order) { + for (current_order = order; current_order <= MAX_ORDER; ++current_order) { area = &(zone->free_area[current_order]); page = get_page_from_free_area(area, migratetype); if (!page) @@ -2871,7 +2871,7 @@ static bool unreserve_highatomic_pageblock(const struct alloc_context *ac, continue; spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { struct free_area *area = &(zone->free_area[order]); page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC); @@ -2955,7 +2955,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, * approximates finding the pageblock with the most free pages, which * would be too costly to do exactly. */ - for (current_order = MAX_ORDER - 1; current_order >= min_order; + for (current_order = MAX_ORDER; current_order >= min_order; --current_order) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, @@ -2981,7 +2981,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, return false; find_smallest: - for (current_order = order; current_order < MAX_ORDER; + for (current_order = order; current_order <= MAX_ORDER; current_order++) { area = &(zone->free_area[current_order]); fallback_mt = find_suitable_fallback(area, current_order, @@ -2994,7 +2994,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype, * This should not happen - we already found a suitable fallback * when looking for the largest page. */ - VM_BUG_ON(current_order == MAX_ORDER); + VM_BUG_ON(current_order > MAX_ORDER); do_steal: page = get_page_from_free_area(area, fallback_mt); @@ -3955,7 +3955,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, return true; /* For a high-order request, check at least one suitable page is free */ - for (o = order; o < MAX_ORDER; o++) { + for (o = order; o <= MAX_ORDER; o++) { struct free_area *area = &z->free_area[o]; int mt; @@ -5475,7 +5475,7 @@ struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, * There are several places where we assume that the order value is sane * so bail out early if the request is out of bound. */ - if (WARN_ON_ONCE_GFP(order >= MAX_ORDER, gfp)) + if (WARN_ON_ONCE_GFP(order > MAX_ORDER, gfp)) return NULL; gfp &= gfp_allowed_mask; @@ -6205,8 +6205,8 @@ void __show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_i for_each_populated_zone(zone) { unsigned int order; - unsigned long nr[MAX_ORDER], flags, total = 0; - unsigned char types[MAX_ORDER]; + unsigned long nr[MAX_ORDER + 1], flags, total = 0; + unsigned char types[MAX_ORDER + 1]; if (zone_idx(zone) > max_zone_idx) continue; @@ -6216,7 +6216,7 @@ void __show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_i printk(KERN_CONT "%s: ", zone->name); spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { struct free_area *area = &zone->free_area[order]; int type; @@ -6230,7 +6230,7 @@ void __show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_i } } spin_unlock_irqrestore(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { printk(KERN_CONT "%lu*%lukB ", nr[order], K(1UL) << order); if (nr[order]) @@ -7581,7 +7581,7 @@ static inline void setup_usemap(struct zone *zone) {} /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ void __init set_pageblock_order(void) { - unsigned int order = MAX_ORDER - 1; + unsigned int order = MAX_ORDER; /* Check that pageblock_nr_pages has not already been setup */ if (pageblock_order) @@ -9076,7 +9076,7 @@ void *__init alloc_large_system_hash(const char *tablename, else table = memblock_alloc_raw(size, SMP_CACHE_BYTES); - } else if (get_order(size) >= MAX_ORDER || hashdist) { + } else if (get_order(size) > MAX_ORDER || hashdist) { table = vmalloc_huge(size, gfp_flags); virt = true; if (table) @@ -9290,7 +9290,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, order = 0; outer_start = start; while (!PageBuddy(pfn_to_page(outer_start))) { - if (++order >= MAX_ORDER) { + if (++order > MAX_ORDER) { outer_start = start; break; } @@ -9540,7 +9540,7 @@ bool is_free_buddy_page(struct page *page) unsigned long pfn = page_to_pfn(page); unsigned int order; - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); if (PageBuddy(page_head) && @@ -9548,7 +9548,7 @@ bool is_free_buddy_page(struct page *page) break; } - return order < MAX_ORDER; + return order <= MAX_ORDER; } EXPORT_SYMBOL(is_free_buddy_page); @@ -9599,7 +9599,7 @@ bool take_page_off_buddy(struct page *page) bool ret = false; spin_lock_irqsave(&zone->lock, flags); - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { struct page *page_head = page - (pfn & ((1 << order) - 1)); int page_order = buddy_order(page_head); diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 47fbc1696466..c6f3605e37ab 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -226,7 +226,7 @@ static void unset_migratetype_isolate(struct page *page, int migratetype) */ if (PageBuddy(page)) { order = buddy_order(page); - if (order >= pageblock_order && order < MAX_ORDER - 1) { + if (order >= pageblock_order && order < MAX_ORDER) { buddy = find_buddy_page_pfn(page, page_to_pfn(page), order, NULL); if (buddy && !is_migrate_isolate_page(buddy)) { @@ -290,11 +290,11 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * isolate_single_pageblock() * @migratetype: migrate type to set in error recovery. * - * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one + * Free and in-use pages can be as big as MAX_ORDER and contain more than one * pageblock. When not all pageblocks within a page are isolated at the same * time, free page accounting can go wrong. For example, in the case of - * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks. - * [ MAX_ORDER-1 ] + * MAX_ORDER = pageblock_order + 1, a MAX_ORDER page has two pagelbocks. + * [ MAX_ORDER ] * [ pageblock0 | pageblock1 ] * When either pageblock is isolated, if it is a free page, the page is not * split into separate migratetype lists, which is supposed to; if it is an @@ -451,7 +451,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, * the free page to the right migratetype list. * * head_pfn is not used here as a hugetlb page order - * can be bigger than MAX_ORDER-1, but after it is + * can be bigger than MAX_ORDER, but after it is * freed, the free page order is not. Use pfn within * the range to find the head of the free page. */ @@ -459,7 +459,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags, outer_pfn = pfn; while (!PageBuddy(pfn_to_page(outer_pfn))) { /* stop if we cannot find the free page */ - if (++order >= MAX_ORDER) + if (++order > MAX_ORDER) goto failed; outer_pfn &= ~0UL << order; } diff --git a/mm/page_owner.c b/mm/page_owner.c index 220cdeddc295..31169b3e7f06 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -315,7 +315,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, unsigned long freepage_order; freepage_order = buddy_order_unsafe(page); - if (freepage_order < MAX_ORDER) + if (freepage_order <= MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } @@ -549,7 +549,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); - if (freepage_order < MAX_ORDER) + if (freepage_order <= MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } @@ -657,7 +657,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) if (PageBuddy(page)) { unsigned long order = buddy_order_unsafe(page); - if (order > 0 && order < MAX_ORDER) + if (order > 0 && order <= MAX_ORDER) pfn += (1UL << order) - 1; continue; } diff --git a/mm/page_reporting.c b/mm/page_reporting.c index 275b466de37b..b021f482a4cb 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -20,7 +20,7 @@ static int page_order_update_notify(const char *val, const struct kernel_param * * If param is set beyond this limit, order is set to default * pageblock_order value */ - return param_set_uint_minmax(val, kp, 0, MAX_ORDER-1); + return param_set_uint_minmax(val, kp, 0, MAX_ORDER); } static const struct kernel_param_ops page_reporting_param_ops = { @@ -276,7 +276,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, return err; /* Process each free list starting from lowest order/mt */ - for (order = page_reporting_order; order < MAX_ORDER; order++) { + for (order = page_reporting_order; order <= MAX_ORDER; order++) { for (mt = 0; mt < MIGRATE_TYPES; mt++) { /* We do not pull pages from the isolate free list */ if (is_migrate_isolate(mt)) @@ -370,7 +370,7 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) */ if (page_reporting_order == -1) { - if (prdev->order > 0 && prdev->order < MAX_ORDER) + if (prdev->order > 0 && prdev->order <= MAX_ORDER) page_reporting_order = prdev->order; else page_reporting_order = pageblock_order; diff --git a/mm/shuffle.h b/mm/shuffle.h index cec62984f7d3..a6bdf54f96f1 100644 --- a/mm/shuffle.h +++ b/mm/shuffle.h @@ -4,7 +4,7 @@ #define _MM_SHUFFLE_H #include -#define SHUFFLE_ORDER (MAX_ORDER-1) +#define SHUFFLE_ORDER MAX_ORDER #ifdef CONFIG_SHUFFLE_PAGE_ALLOCATOR DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key); diff --git a/mm/slab.c b/mm/slab.c index edbe722fb906..6b7c172158e5 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -465,7 +465,7 @@ static int __init slab_max_order_setup(char *str) { get_option(&str, &slab_max_order); slab_max_order = slab_max_order < 0 ? 0 : - min(slab_max_order, MAX_ORDER - 1); + min(slab_max_order, MAX_ORDER); slab_max_order_set = true; return 1; diff --git a/mm/slub.c b/mm/slub.c index 32eb6b50fe18..f49d669ff604 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4171,8 +4171,8 @@ static inline int calculate_order(unsigned int size) /* * Doh this slab cannot be placed using slub_max_order. */ - order = calc_slab_order(size, 1, MAX_ORDER - 1, 1); - if (order < MAX_ORDER) + order = calc_slab_order(size, 1, MAX_ORDER, 1); + if (order <= MAX_ORDER) return order; return -ENOSYS; } @@ -4697,7 +4697,7 @@ __setup("slub_min_order=", setup_slub_min_order); static int __init setup_slub_max_order(char *str) { get_option(&str, (int *)&slub_max_order); - slub_max_order = min(slub_max_order, (unsigned int)MAX_ORDER - 1); + slub_max_order = min_t(unsigned int, slub_max_order, MAX_ORDER); return 1; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 8faac4310cb5..98719e72b5e2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -7002,7 +7002,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order, * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ - BUILD_BUG_ON(MAX_ORDER > S8_MAX); + BUILD_BUG_ON(MAX_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); diff --git a/mm/vmstat.c b/mm/vmstat.c index 1ea6a5ce1c41..b7307627772d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1055,7 +1055,7 @@ static void fill_contig_page_info(struct zone *zone, info->free_blocks_total = 0; info->free_blocks_suitable = 0; - for (order = 0; order < MAX_ORDER; order++) { + for (order = 0; order <= MAX_ORDER; order++) { unsigned long blocks; /* @@ -1088,7 +1088,7 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in { unsigned long requested = 1UL << order; - if (WARN_ON_ONCE(order >= MAX_ORDER)) + if (WARN_ON_ONCE(order > MAX_ORDER)) return 0; if (!info->free_blocks_total) @@ -1462,7 +1462,7 @@ static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, int order; seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) + for (order = 0; order <= MAX_ORDER; ++order) /* * Access to nr_free is lockless as nr_free is used only for * printing purposes. Use data_race to avoid KCSAN warning. @@ -1491,7 +1491,7 @@ static void pagetypeinfo_showfree_print(struct seq_file *m, pgdat->node_id, zone->name, migratetype_names[mtype]); - for (order = 0; order < MAX_ORDER; ++order) { + for (order = 0; order <= MAX_ORDER; ++order) { unsigned long freecount = 0; struct free_area *area; struct list_head *curr; @@ -1531,7 +1531,7 @@ static void pagetypeinfo_showfree(struct seq_file *m, void *arg) /* Print header */ seq_printf(m, "%-43s ", "Free pages count per migrate type at order"); - for (order = 0; order < MAX_ORDER; ++order) + for (order = 0; order <= MAX_ORDER; ++order) seq_printf(m, "%6d ", order); seq_putc(m, '\n'); @@ -2153,7 +2153,7 @@ static void unusable_show_print(struct seq_file *m, seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) { + for (order = 0; order <= MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); index = unusable_free_index(order, &info); seq_printf(m, "%d.%03d ", index / 1000, index % 1000); @@ -2205,7 +2205,7 @@ static void extfrag_show_print(struct seq_file *m, seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) { + for (order = 0; order <= MAX_ORDER; ++order) { fill_contig_page_info(zone, order, &info); index = __fragmentation_index(order, &info); seq_printf(m, "%2d.%03d ", index / 1000, index % 1000); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 854772dd52fd..9b66d6aeeb1a 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -843,7 +843,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) goto out; /* the calculated number of cq entries fits to mlx5 cq allocation */ cqe_size_order = cache_line_size() == 128 ? 7 : 6; - smc_order = MAX_ORDER - cqe_size_order - 1; + smc_order = MAX_ORDER - cqe_size_order; if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE) cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2; smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev, diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index 64499056648a..51ad29940f05 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -38,7 +38,7 @@ static int param_set_bufsize(const char *val, const struct kernel_param *kp) size = memparse(val, NULL); order = get_order(size); - if (order >= MAX_ORDER) + if (order > MAX_ORDER) return -EINVAL; ima_maxorder = order; ima_bufsize = PAGE_SIZE << order; diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h index e65f89b12f1c..134f8eab0768 100644 --- a/tools/testing/memblock/linux/mmzone.h +++ b/tools/testing/memblock/linux/mmzone.h @@ -17,10 +17,10 @@ enum zone_type { }; #define MAX_NR_ZONES __MAX_NR_ZONES -#define MAX_ORDER 11 -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER 10 +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) -#define pageblock_order (MAX_ORDER - 1) +#define pageblock_order MAX_ORDER #define pageblock_nr_pages BIT(pageblock_order) #define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) #define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) -- GitLab From 7ce6048d3a7d2f9b43f3d8a34a52e4122bdc2f23 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Wed, 22 Mar 2023 10:17:27 +0200 Subject: [PATCH 2206/5631] loongarch: drop ranges for definition of ARCH_FORCE_MAX_ORDER LoongArch defines insane ranges for ARCH_FORCE_MAX_ORDER allowing MAX_ORDER up to 63, which implies maximal contiguous allocation size of 2^63 pages. Drop bogus definitions of ranges for ARCH_FORCE_MAX_ORDER and leave it a simple integer with sensible defaults. Users that *really* need to change the value of ARCH_FORCE_MAX_ORDER will be able to do so but they won't be mislead by the bogus ranges. Link: https://lkml.kernel.org/r/20230322081727.2516291-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: David Hildenbrand Cc: Huacai Chen Cc: WANG Xuerui Signed-off-by: Andrew Morton --- arch/loongarch/Kconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 272a3a12c98d..e1e3a3828962 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -420,11 +420,8 @@ config NODES_SHIFT config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 13 63 if PAGE_SIZE_64KB default "13" if PAGE_SIZE_64KB - range 11 63 if PAGE_SIZE_16KB default "11" if PAGE_SIZE_16KB - range 10 63 default "10" help The kernel memory allocator divides physically contiguous memory -- GitLab From 60bcbe70bff5fa8a36bf2ed3a6629ea42e1c147d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Wed, 22 Mar 2023 10:15:20 +0200 Subject: [PATCH 2207/5631] mips: drop ranges for definition of ARCH_FORCE_MAX_ORDER MIPS defines insane ranges for ARCH_FORCE_MAX_ORDER allowing MAX_ORDER up to 63, which implies maximal contiguous allocation size of 2^63 pages. Drop bogus definitions of ranges for ARCH_FORCE_MAX_ORDER and leave it a simple integer with sensible defaults. Users that *really* need to change the value of ARCH_FORCE_MAX_ORDER will be able to do so but they won't be mislead by the bogus ranges. Link: https://lkml.kernel.org/r/20230322081520.2516226-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Thomas Bogendoerfer Acked-by: Kirill A. Shutemov Reviewed-by: David Hildenbrand Cc: Huacai Chen Cc: WANG Xuerui Signed-off-by: Andrew Morton --- arch/mips/Kconfig | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3e8b765b8c7b..a0f6e9d0a561 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2137,13 +2137,9 @@ endchoice config ARCH_FORCE_MAX_ORDER int "Maximum zone order" - range 13 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB - range 12 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB - range 11 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB default "11" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB - range 0 63 default "10" help The kernel memory allocator divides physically contiguous memory -- GitLab From a734991ccaec1985fff42fb26bb6d789d35defb4 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:47 -0700 Subject: [PATCH 2208/5631] mm: userfaultfd: rename functions for clarity + consistency Patch series "mm: userfaultfd: refactor and add UFFDIO_CONTINUE_MODE_WP", v5. - Commits 1-3 refactor userfaultfd ioctl code without behavior changes, with the main goal of improving consistency and reducing the number of function args. - Commit 4 adds UFFDIO_CONTINUE_MODE_WP. This patch (of 4): The basic problem is, over time we've added new userfaultfd ioctls, and we've refactored the code so functions which used to handle only one case are now re-used to deal with several cases. While this happened, we didn't bother to rename the functions. Similarly, as we added new functions, we cargo-culted pieces of the now-inconsistent naming scheme, so those functions too ended up with names that don't make a lot of sense. A key point here is, "copy" in most userfaultfd code refers specifically to UFFDIO_COPY, where we allocate a new page and copy its contents from userspace. There are many functions with "copy" in the name that don't actually do this (at least in some cases). So, rename things into a consistent scheme. The high level idea is that the call stack for userfaultfd ioctls becomes: userfaultfd_ioctl -> userfaultfd_(particular ioctl) -> mfill_atomic_(particular kind of fill operation) -> mfill_atomic /* loops over pages in range */ -> mfill_atomic_pte /* deals with single pages */ -> mfill_atomic_pte_(particular kind of fill operation) -> mfill_atomic_install_pte There are of course some special cases (shmem, hugetlb), but this is the general structure which all function names now adhere to. Link: https://lkml.kernel.org/r/20230314221250.682452-1-axelrasmussen@google.com Link: https://lkml.kernel.org/r/20230314221250.682452-2-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: James Houghton Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 18 +++---- include/linux/hugetlb.h | 30 +++++------ include/linux/userfaultfd_k.h | 18 +++---- mm/hugetlb.c | 20 +++---- mm/userfaultfd.c | 98 +++++++++++++++++------------------ 5 files changed, 92 insertions(+), 92 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 881e9c82b9d1..4aedfd98e3f5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1756,9 +1756,9 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (mmget_not_zero(ctx->mm)) { - ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len, &ctx->mmap_changing, - uffdio_copy.mode); + ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src, + uffdio_copy.len, &ctx->mmap_changing, + uffdio_copy.mode); mmput(ctx->mm); } else { return -ESRCH; @@ -1808,9 +1808,9 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, goto out; if (mmget_not_zero(ctx->mm)) { - ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, - uffdio_zeropage.range.len, - &ctx->mmap_changing); + ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start, + uffdio_zeropage.range.len, + &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; @@ -1918,9 +1918,9 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) goto out; if (mmget_not_zero(ctx->mm)) { - ret = mcopy_continue(ctx->mm, uffdio_continue.range.start, - uffdio_continue.range.len, - &ctx->mmap_changing); + ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start, + uffdio_continue.range.len, + &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8fb7d91cd0b1..152434396c48 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -158,13 +158,13 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); +int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -393,14 +393,14 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) +static inline int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy) { BUG(); return 0; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 0cf8880219da..ac178d810dc7 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -61,15 +61,15 @@ extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); -extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); -extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, - unsigned long dst_start, - unsigned long len, - atomic_t *mmap_changing); -extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); +extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, __u64 mode); +extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len, + atomic_t *mmap_changing); +extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, atomic_t *mmap_changing); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9122e50ae02a..b1e474aa2fc5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6156,17 +6156,17 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, #ifdef CONFIG_USERFAULTFD /* - * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with - * modifications for huge pages. + * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte + * with modifications for hugetlb pages. */ -int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) +int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, + pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + enum mcopy_atomic_mode mode, + struct page **pagep, + bool wp_copy) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct hstate *h = hstate_vma(dst_vma); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 23cabd02ac52..874379ce271f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -127,13 +127,13 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, return ret; } -static int mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep, - bool wp_copy) +static int mfill_atomic_pte_copy(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep, + bool wp_copy) { void *page_kaddr; int ret; @@ -204,10 +204,10 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out; } -static int mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr) +static int mfill_atomic_pte_zeropage(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) { pte_t _dst_pte, *dst_pte; spinlock_t *ptl; @@ -240,11 +240,11 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm, } /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ -static int mcontinue_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - bool wp_copy) +static int mfill_atomic_pte_continue(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + bool wp_copy) { struct inode *inode = file_inode(dst_vma->vm_file); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); @@ -307,10 +307,10 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) #ifdef CONFIG_HUGETLB_PAGE /* - * __mcopy_atomic processing for HUGETLB vmas. Note that this routine is + * mfill_atomic processing for HUGETLB vmas. Note that this routine is * called with mmap_lock held, it will release mmap_lock before returning. */ -static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, +static __always_inline ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, @@ -411,7 +411,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, goto out_unlock; } - err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, + err = hugetlb_mfill_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, src_addr, mode, &page, wp_copy); @@ -463,7 +463,7 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, } #else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ -extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, +extern ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, @@ -484,8 +484,8 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, ssize_t err; if (mode == MCOPY_ATOMIC_CONTINUE) { - return mcontinue_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, - wp_copy); + return mfill_atomic_pte_continue(dst_mm, dst_pmd, dst_vma, + dst_addr, wp_copy); } /* @@ -500,11 +500,11 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, */ if (!(dst_vma->vm_flags & VM_SHARED)) { if (mode == MCOPY_ATOMIC_NORMAL) - err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, page, - wp_copy); + err = mfill_atomic_pte_copy(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, page, + wp_copy); else - err = mfill_zeropage_pte(dst_mm, dst_pmd, + err = mfill_atomic_pte_zeropage(dst_mm, dst_pmd, dst_vma, dst_addr); } else { err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, @@ -516,13 +516,13 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, return err; } -static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, - unsigned long dst_start, - unsigned long src_start, - unsigned long len, - enum mcopy_atomic_mode mcopy_mode, - atomic_t *mmap_changing, - __u64 mode) +static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + enum mcopy_atomic_mode mcopy_mode, + atomic_t *mmap_changing, + __u64 mode) { struct vm_area_struct *dst_vma; ssize_t err; @@ -588,9 +588,9 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start, - src_start, len, mcopy_mode, - wp_copy); + return mfill_atomic_hugetlb(dst_mm, dst_vma, dst_start, + src_start, len, mcopy_mode, + wp_copy); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; @@ -688,26 +688,26 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, return copied ? copied : err; } -ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode) +ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, __u64 mode) { - return __mcopy_atomic(dst_mm, dst_start, src_start, len, - MCOPY_ATOMIC_NORMAL, mmap_changing, mode); + return mfill_atomic(dst_mm, dst_start, src_start, len, + MCOPY_ATOMIC_NORMAL, mmap_changing, mode); } -ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing) +ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, atomic_t *mmap_changing) { - return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, - mmap_changing, 0); + return mfill_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, + mmap_changing, 0); } -ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing) +ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start, + unsigned long len, atomic_t *mmap_changing) { - return __mcopy_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, - mmap_changing, 0); + return mfill_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, + mmap_changing, 0); } long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, -- GitLab From 61c5004022f56c443b86800e8985d8803f3a22aa Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:48 -0700 Subject: [PATCH 2209/5631] mm: userfaultfd: don't pass around both mm and vma Quite a few userfaultfd functions took both mm and vma pointers as arguments. Since the mm is trivially accessible via vma->vm_mm, there's no reason to pass both; it just needlessly extends the already long argument list. Get rid of the mm pointer, where possible, to shorten the argument list. Link: https://lkml.kernel.org/r/20230314221250.682452-3-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: James Houghton Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 2 +- include/linux/hugetlb.h | 5 ++- include/linux/shmem_fs.h | 4 +-- include/linux/userfaultfd_k.h | 4 +-- mm/hugetlb.c | 4 +-- mm/shmem.c | 7 ++-- mm/userfaultfd.c | 61 +++++++++++++++++------------------ 7 files changed, 41 insertions(+), 46 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 4aedfd98e3f5..d8d432ca81e6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1644,7 +1644,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, /* Reset ptes for the whole vma range if wr-protected */ if (userfaultfd_wp(vma)) - uffd_wp_range(mm, vma, start, vma_end - start, false); + uffd_wp_range(vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 152434396c48..3cb7cd853fa8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -158,7 +158,7 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, +int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -393,8 +393,7 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, +static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 50bf82b36995..922a2b45fe6f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -152,14 +152,14 @@ extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, bool zeropage, bool wp_copy, struct page **pagep); #else /* !CONFIG_SHMEM */ -#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ +#define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index ac178d810dc7..9458cd94a508 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -56,7 +56,7 @@ enum mcopy_atomic_mode { MCOPY_ATOMIC_CONTINUE, }; -extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); @@ -73,7 +73,7 @@ extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, +extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b1e474aa2fc5..6dc32cccbd9b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6159,8 +6159,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ -int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, +int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -6168,6 +6167,7 @@ int hugetlb_mfill_atomic_pte(struct mm_struct *dst_mm, struct page **pagep, bool wp_copy) { + struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; diff --git a/mm/shmem.c b/mm/shmem.c index fa6e38f2f55f..9d13b9a64144 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2429,8 +2429,7 @@ static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block } #ifdef CONFIG_USERFAULTFD -int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, +int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -2520,11 +2519,11 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, goto out_release; ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, - gfp & GFP_RECLAIM_MASK, dst_mm); + gfp & GFP_RECLAIM_MASK, dst_vma->vm_mm); if (ret) goto out_release; - ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, &folio->page, true, wp_copy); if (ret) goto out_delete_from_cache; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 874379ce271f..c3cc6cb04548 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -55,12 +55,13 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem * and anon, and for both shared and private VMAs. */ -int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy) { int ret; + struct mm_struct *dst_mm = dst_vma->vm_mm; pte_t _dst_pte, *dst_pte; bool writable = dst_vma->vm_flags & VM_WRITE; bool vm_shared = dst_vma->vm_flags & VM_SHARED; @@ -127,8 +128,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, return ret; } -static int mfill_atomic_pte_copy(struct mm_struct *dst_mm, - pmd_t *dst_pmd, +static int mfill_atomic_pte_copy(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -190,10 +190,10 @@ static int mfill_atomic_pte_copy(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), dst_vma->vm_mm, GFP_KERNEL)) goto out_release; - ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, page, true, wp_copy); if (ret) goto out_release; @@ -204,8 +204,7 @@ static int mfill_atomic_pte_copy(struct mm_struct *dst_mm, goto out; } -static int mfill_atomic_pte_zeropage(struct mm_struct *dst_mm, - pmd_t *dst_pmd, +static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { @@ -217,7 +216,7 @@ static int mfill_atomic_pte_zeropage(struct mm_struct *dst_mm, _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + dst_pte = pte_offset_map_lock(dst_vma->vm_mm, dst_pmd, dst_addr, &ptl); if (dst_vma->vm_file) { /* the shmem MAP_PRIVATE case requires checking the i_size */ inode = dst_vma->vm_file->f_inode; @@ -230,7 +229,7 @@ static int mfill_atomic_pte_zeropage(struct mm_struct *dst_mm, ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_unlock; - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + set_pte_at(dst_vma->vm_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); ret = 0; @@ -240,8 +239,7 @@ static int mfill_atomic_pte_zeropage(struct mm_struct *dst_mm, } /* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ -static int mfill_atomic_pte_continue(struct mm_struct *dst_mm, - pmd_t *dst_pmd, +static int mfill_atomic_pte_continue(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, bool wp_copy) @@ -269,7 +267,7 @@ static int mfill_atomic_pte_continue(struct mm_struct *dst_mm, goto out_release; } - ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, page, false, wp_copy); if (ret) goto out_release; @@ -310,7 +308,7 @@ static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) * mfill_atomic processing for HUGETLB vmas. Note that this routine is * called with mmap_lock held, it will release mmap_lock before returning. */ -static __always_inline ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, +static __always_inline ssize_t mfill_atomic_hugetlb( struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, @@ -318,6 +316,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, enum mcopy_atomic_mode mode, bool wp_copy) { + struct mm_struct *dst_mm = dst_vma->vm_mm; int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; @@ -411,7 +410,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, goto out_unlock; } - err = hugetlb_mfill_atomic_pte(dst_mm, dst_pte, dst_vma, + err = hugetlb_mfill_atomic_pte(dst_pte, dst_vma, dst_addr, src_addr, mode, &page, wp_copy); @@ -463,17 +462,15 @@ static __always_inline ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, } #else /* !CONFIG_HUGETLB_PAGE */ /* fail at build time if gcc attempts to use this */ -extern ssize_t mfill_atomic_hugetlb(struct mm_struct *dst_mm, - struct vm_area_struct *dst_vma, - unsigned long dst_start, - unsigned long src_start, - unsigned long len, - enum mcopy_atomic_mode mode, - bool wp_copy); +extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, + unsigned long dst_start, + unsigned long src_start, + unsigned long len, + enum mcopy_atomic_mode mode, + bool wp_copy); #endif /* CONFIG_HUGETLB_PAGE */ -static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, +static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, @@ -484,7 +481,7 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, ssize_t err; if (mode == MCOPY_ATOMIC_CONTINUE) { - return mfill_atomic_pte_continue(dst_mm, dst_pmd, dst_vma, + return mfill_atomic_pte_continue(dst_pmd, dst_vma, dst_addr, wp_copy); } @@ -500,14 +497,14 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, */ if (!(dst_vma->vm_flags & VM_SHARED)) { if (mode == MCOPY_ATOMIC_NORMAL) - err = mfill_atomic_pte_copy(dst_mm, dst_pmd, dst_vma, + err = mfill_atomic_pte_copy(dst_pmd, dst_vma, dst_addr, src_addr, page, wp_copy); else - err = mfill_atomic_pte_zeropage(dst_mm, dst_pmd, + err = mfill_atomic_pte_zeropage(dst_pmd, dst_vma, dst_addr); } else { - err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + err = shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, mode != MCOPY_ATOMIC_NORMAL, wp_copy, page); @@ -588,7 +585,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * If this is a HUGETLB vma, pass off to appropriate routine */ if (is_vm_hugetlb_page(dst_vma)) - return mfill_atomic_hugetlb(dst_mm, dst_vma, dst_start, + return mfill_atomic_hugetlb(dst_vma, dst_start, src_start, len, mcopy_mode, wp_copy); @@ -641,7 +638,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); - err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, &page, mcopy_mode, wp_copy); cond_resched(); @@ -710,7 +707,7 @@ ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start, mmap_changing, 0); } -long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, +long uffd_wp_range(struct vm_area_struct *dst_vma, unsigned long start, unsigned long len, bool enable_wp) { unsigned int mm_cp_flags; @@ -732,7 +729,7 @@ long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma, */ if (!enable_wp && vma_wants_manual_pte_write_upgrade(dst_vma)) mm_cp_flags |= MM_CP_TRY_CHANGE_WRITABLE; - tlb_gather_mmu(&tlb, dst_mm); + tlb_gather_mmu(&tlb, dst_vma->vm_mm); ret = change_protection(&tlb, dst_vma, start, start + len, mm_cp_flags); tlb_finish_mmu(&tlb); @@ -788,7 +785,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, _start = max(dst_vma->vm_start, start); _end = min(dst_vma->vm_end, end); - err = uffd_wp_range(dst_mm, dst_vma, _start, _end - _start, enable_wp); + err = uffd_wp_range(dst_vma, _start, _end - _start, enable_wp); /* Return 0 on success, <0 on failures */ if (err < 0) -- GitLab From d9712937037e0ce887920f321429826e9dbfd960 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:49 -0700 Subject: [PATCH 2210/5631] mm: userfaultfd: combine 'mode' and 'wp_copy' arguments Many userfaultfd ioctl functions take both a 'mode' and a 'wp_copy' argument. In future commits we plan to plumb the flags through to more places, so we'd be proliferating the very long argument list even further. Let's take the time to simplify the argument list. Combine the two arguments into one - and generalize, so when we add more flags in the future, it doesn't imply more function arguments. Since the modes (copy, zeropage, continue) are mutually exclusive, store them as an integer value (0, 1, 2) in the low bits. Place combine-able flag bits in the high bits. This is quite similar to an earlier patch proposed by Nadav Amit ("userfaultfd: introduce uffd_flags" [1]). The main difference is that patch only handled flags, whereas this patch *also* combines the "mode" argument into the same type to shorten the argument list. [1]: https://lore.kernel.org/all/20220619233449.181323-2-namit@vmware.com/ Link: https://lkml.kernel.org/r/20230314221250.682452-4-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: James Houghton Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Shuah Khan Signed-off-by: Andrew Morton --- fs/userfaultfd.c | 5 ++- include/linux/hugetlb.h | 10 ++--- include/linux/shmem_fs.h | 5 ++- include/linux/userfaultfd_k.h | 46 +++++++++++++-------- mm/hugetlb.c | 12 +++--- mm/shmem.c | 7 ++-- mm/userfaultfd.c | 76 ++++++++++++++++------------------- 7 files changed, 84 insertions(+), 77 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d8d432ca81e6..8971c3613cc6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1729,6 +1729,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; + uffd_flags_t flags = 0; user_uffdio_copy = (struct uffdio_copy __user *) arg; @@ -1755,10 +1756,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, goto out; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; + if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP) + flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, &ctx->mmap_changing, - uffdio_copy.mode); + flags); mmput(ctx->mm); } else { return -ESRCH; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cb7cd853fa8..2a758bcd6719 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -162,9 +162,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); + uffd_flags_t flags, + struct page **pagep); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -397,9 +396,8 @@ static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) + uffd_flags_t flags, + struct page **pagep) { BUG(); return 0; diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 922a2b45fe6f..3bb8d21edbb3 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -9,6 +9,7 @@ #include #include #include +#include /* inode in-kernel data */ @@ -156,11 +157,11 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, bool wp_copy, + uffd_flags_t flags, struct page **pagep); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) + src_addr, flags, pagep) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9458cd94a508..4c477dece540 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -40,30 +40,44 @@ extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); -/* - * The mode of operation for __mcopy_atomic and its helpers. - * - * This is almost an implementation detail (mcopy_atomic below doesn't take this - * as a parameter), but it's exposed here because memory-kind-specific - * implementations (e.g. hugetlbfs) need to know the mode of operation. - */ -enum mcopy_atomic_mode { - /* A normal copy_from_user into the destination range. */ - MCOPY_ATOMIC_NORMAL, - /* Don't copy; map the destination range to the zero page. */ - MCOPY_ATOMIC_ZEROPAGE, - /* Just install pte(s) with the existing page(s) in the page cache. */ - MCOPY_ATOMIC_CONTINUE, +/* A combined operation mode + behavior flags. */ +typedef unsigned int __bitwise uffd_flags_t; + +/* Mutually exclusive modes of operation. */ +enum mfill_atomic_mode { + MFILL_ATOMIC_COPY, + MFILL_ATOMIC_ZEROPAGE, + MFILL_ATOMIC_CONTINUE, + NR_MFILL_ATOMIC_MODES, }; +#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) +#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) +#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) +#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) + +static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) +{ + return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); +} + +static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) +{ + flags &= ~MFILL_ATOMIC_MODE_MASK; + return flags | ((__force uffd_flags_t) mode); +} + +/* Flags controlling behavior. These behavior changes are mode-independent. */ +#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) + extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, - bool newly_allocated, bool wp_copy); + bool newly_allocated, uffd_flags_t flags); extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); + atomic_t *mmap_changing, uffd_flags_t flags); extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long len, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6dc32cccbd9b..8bfd07f4c143 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6163,12 +6163,12 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) + uffd_flags_t flags, + struct page **pagep) { struct mm_struct *dst_mm = dst_vma->vm_mm; - bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); + bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); + bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); @@ -6303,7 +6303,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ - if (wp_copy || (is_continue && !vm_shared)) + if (wp_enabled || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; @@ -6318,7 +6318,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); - if (wp_copy) + if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); diff --git a/mm/shmem.c b/mm/shmem.c index 9d13b9a64144..b185c1db3009 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -76,7 +76,6 @@ static struct vfsmount *shm_mnt; #include #include #include -#include #include #include @@ -2433,7 +2432,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, bool wp_copy, + uffd_flags_t flags, struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); @@ -2465,7 +2464,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, if (!folio) goto out_unacct_blocks; - if (!zeropage) { /* COPY */ + if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) { page_kaddr = kmap_local_folio(folio, 0); /* * The read mmap_lock is held here. Despite the @@ -2524,7 +2523,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, goto out_release; ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, - &folio->page, true, wp_copy); + &folio->page, true, flags); if (ret) goto out_delete_from_cache; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c3cc6cb04548..a9b19b39413d 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -58,7 +58,7 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, - bool newly_allocated, bool wp_copy) + bool newly_allocated, uffd_flags_t flags) { int ret; struct mm_struct *dst_mm = dst_vma->vm_mm; @@ -77,7 +77,7 @@ int mfill_atomic_install_pte(pmd_t *dst_pmd, writable = false; if (writable) _dst_pte = pte_mkwrite(_dst_pte); - if (wp_copy) + if (flags & MFILL_ATOMIC_WP) _dst_pte = pte_mkuffd_wp(_dst_pte); dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); @@ -132,8 +132,8 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - struct page **pagep, - bool wp_copy) + uffd_flags_t flags, + struct page **pagep) { void *page_kaddr; int ret; @@ -194,7 +194,7 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, goto out_release; ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, - page, true, wp_copy); + page, true, flags); if (ret) goto out_release; out: @@ -242,7 +242,7 @@ static int mfill_atomic_pte_zeropage(pmd_t *dst_pmd, static int mfill_atomic_pte_continue(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, - bool wp_copy) + uffd_flags_t flags) { struct inode *inode = file_inode(dst_vma->vm_file); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); @@ -268,7 +268,7 @@ static int mfill_atomic_pte_continue(pmd_t *dst_pmd, } ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, - page, false, wp_copy); + page, false, flags); if (ret) goto out_release; @@ -313,8 +313,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( unsigned long dst_start, unsigned long src_start, unsigned long len, - enum mcopy_atomic_mode mode, - bool wp_copy) + uffd_flags_t flags) { struct mm_struct *dst_mm = dst_vma->vm_mm; int vm_shared = dst_vma->vm_flags & VM_SHARED; @@ -334,7 +333,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( * by THP. Since we can not reliably insert a zero page, this * feature is not supported. */ - if (mode == MCOPY_ATOMIC_ZEROPAGE) { + if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) { mmap_read_unlock(dst_mm); return -EINVAL; } @@ -402,7 +401,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out_unlock; } - if (mode != MCOPY_ATOMIC_CONTINUE && + if (!uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) && !huge_pte_none_mostly(huge_ptep_get(dst_pte))) { err = -EEXIST; hugetlb_vma_unlock_read(dst_vma); @@ -410,9 +409,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb( goto out_unlock; } - err = hugetlb_mfill_atomic_pte(dst_pte, dst_vma, - dst_addr, src_addr, mode, &page, - wp_copy); + err = hugetlb_mfill_atomic_pte(dst_pte, dst_vma, dst_addr, + src_addr, flags, &page); hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); @@ -466,23 +464,21 @@ extern ssize_t mfill_atomic_hugetlb(struct vm_area_struct *dst_vma, unsigned long dst_start, unsigned long src_start, unsigned long len, - enum mcopy_atomic_mode mode, - bool wp_copy); + uffd_flags_t flags); #endif /* CONFIG_HUGETLB_PAGE */ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - struct page **page, - enum mcopy_atomic_mode mode, - bool wp_copy) + uffd_flags_t flags, + struct page **pagep) { ssize_t err; - if (mode == MCOPY_ATOMIC_CONTINUE) { + if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE)) { return mfill_atomic_pte_continue(dst_pmd, dst_vma, - dst_addr, wp_copy); + dst_addr, flags); } /* @@ -496,18 +492,17 @@ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { - if (mode == MCOPY_ATOMIC_NORMAL) + if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) err = mfill_atomic_pte_copy(dst_pmd, dst_vma, - dst_addr, src_addr, page, - wp_copy); + dst_addr, src_addr, + flags, pagep); else err = mfill_atomic_pte_zeropage(dst_pmd, dst_vma, dst_addr); } else { err = shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, - mode != MCOPY_ATOMIC_NORMAL, - wp_copy, page); + flags, pagep); } return err; @@ -517,9 +512,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - enum mcopy_atomic_mode mcopy_mode, atomic_t *mmap_changing, - __u64 mode) + uffd_flags_t flags) { struct vm_area_struct *dst_vma; ssize_t err; @@ -527,7 +521,6 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, unsigned long src_addr, dst_addr; long copied; struct page *page; - bool wp_copy; /* * Sanitize the command parameters: @@ -577,8 +570,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, * validate 'mode' now that we know the dst_vma: don't allow * a wrprotect copy if the userfaultfd didn't register as WP. */ - wp_copy = mode & UFFDIO_COPY_MODE_WP; - if (wp_copy && !(dst_vma->vm_flags & VM_UFFD_WP)) + if ((flags & MFILL_ATOMIC_WP) && !(dst_vma->vm_flags & VM_UFFD_WP)) goto out_unlock; /* @@ -586,12 +578,12 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, */ if (is_vm_hugetlb_page(dst_vma)) return mfill_atomic_hugetlb(dst_vma, dst_start, - src_start, len, mcopy_mode, - wp_copy); + src_start, len, flags); if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; - if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE) + if (!vma_is_shmem(dst_vma) && + uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE)) goto out_unlock; /* @@ -639,7 +631,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, - src_addr, &page, mcopy_mode, wp_copy); + src_addr, flags, &page); cond_resched(); if (unlikely(err == -ENOENT)) { @@ -687,24 +679,24 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode) + atomic_t *mmap_changing, uffd_flags_t flags) { - return mfill_atomic(dst_mm, dst_start, src_start, len, - MCOPY_ATOMIC_NORMAL, mmap_changing, mode); + return mfill_atomic(dst_mm, dst_start, src_start, len, mmap_changing, + uffd_flags_set_mode(flags, MFILL_ATOMIC_COPY)); } ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start, unsigned long len, atomic_t *mmap_changing) { - return mfill_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_ZEROPAGE, - mmap_changing, 0); + return mfill_atomic(dst_mm, start, 0, len, mmap_changing, + uffd_flags_set_mode(0, MFILL_ATOMIC_ZEROPAGE)); } ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start, unsigned long len, atomic_t *mmap_changing) { - return mfill_atomic(dst_mm, start, 0, len, MCOPY_ATOMIC_CONTINUE, - mmap_changing, 0); + return mfill_atomic(dst_mm, start, 0, len, mmap_changing, + uffd_flags_set_mode(0, MFILL_ATOMIC_CONTINUE)); } long uffd_wp_range(struct vm_area_struct *dst_vma, -- GitLab From 0289184476c845968ad6ac9083c96cc0f75ca505 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 14 Mar 2023 15:12:50 -0700 Subject: [PATCH 2211/5631] mm: userfaultfd: add UFFDIO_CONTINUE_MODE_WP to install WP PTEs UFFDIO_COPY already has UFFDIO_COPY_MODE_WP, so when installing a new PTE to resolve a missing fault, one can install a write-protected one. This is useful when using UFFDIO_REGISTER_MODE_{MISSING,WP} in combination. This was motivated by testing HugeTLB HGM [1], and in particular its interaction with userfaultfd features. Existing userfaultfd code supports using WP and MINOR modes together (i.e. you can register an area with both enabled), but without this CONTINUE flag the combination is in practice unusable. So, add an analogous UFFDIO_CONTINUE_MODE_WP, which does the same thing as UFFDIO_COPY_MODE_WP, but for *minor* faults. Update the selftest to do some very basic exercising of the new flag. Update Documentation/ to describe how these flags are used (neither the COPY nor the new CONTINUE versions of this mode flag were described there before). [1]: https://patchwork.kernel.org/project/linux-mm/cover/20230218002819.1486479-1-jthoughton@google.com/ Link: https://lkml.kernel.org/r/20230314221250.682452-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Peter Xu Acked-by: Mike Rapoport (IBM) Cc: Al Viro Cc: Hugh Dickins Cc: Jan Kara Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Nadav Amit Cc: Shuah Khan Signed-off-by: Andrew Morton --- Documentation/admin-guide/mm/userfaultfd.rst | 8 ++++++++ fs/userfaultfd.c | 8 ++++++-- include/linux/userfaultfd_k.h | 3 ++- include/uapi/linux/userfaultfd.h | 7 +++++++ mm/userfaultfd.c | 5 +++-- tools/testing/selftests/mm/userfaultfd.c | 4 ++++ 6 files changed, 30 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst index bd2226299583..7c304e432205 100644 --- a/Documentation/admin-guide/mm/userfaultfd.rst +++ b/Documentation/admin-guide/mm/userfaultfd.rst @@ -236,6 +236,14 @@ newer kernels, one can also detect the feature UFFD_FEATURE_WP_UNPOPULATED and set the feature bit in advance to make sure none ptes will also be write protected even upon anonymous memory. +When using ``UFFDIO_REGISTER_MODE_WP`` in combination with either +``UFFDIO_REGISTER_MODE_MISSING`` or ``UFFDIO_REGISTER_MODE_MINOR``, when +resolving missing / minor faults with ``UFFDIO_COPY`` or ``UFFDIO_CONTINUE`` +respectively, it may be desirable for the new page / mapping to be +write-protected (so future writes will also result in a WP fault). These ioctls +support a mode flag (``UFFDIO_COPY_MODE_WP`` or ``UFFDIO_CONTINUE_MODE_WP`` +respectively) to configure the mapping this way. + QEMU/KVM ======== diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 8971c3613cc6..8395605790f6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1893,6 +1893,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; + uffd_flags_t flags = 0; user_uffdio_continue = (struct uffdio_continue __user *)arg; @@ -1917,13 +1918,16 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) uffdio_continue.range.start) { goto out; } - if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) + if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE | + UFFDIO_CONTINUE_MODE_WP)) goto out; + if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP) + flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len, - &ctx->mmap_changing); + &ctx->mmap_changing, flags); mmput(ctx->mm); } else { return -ESRCH; diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 4c477dece540..a2c53e98dfd6 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -83,7 +83,8 @@ extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long len, atomic_t *mmap_changing); extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 90c958952bfc..66dd4cd277bd 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -305,6 +305,13 @@ struct uffdio_writeprotect { struct uffdio_continue { struct uffdio_range range; #define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_CONTINUE_MODE_WP will map the page write protected on + * the fly. UFFDIO_CONTINUE_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_CONTINUE_MODE_WP ((__u64)1<<1) __u64 mode; /* diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index a9b19b39413d..7f1b5f8b712c 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -693,10 +693,11 @@ ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, unsigned long start, } ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long start, - unsigned long len, atomic_t *mmap_changing) + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags) { return mfill_atomic(dst_mm, start, 0, len, mmap_changing, - uffd_flags_set_mode(0, MFILL_ATOMIC_CONTINUE)); + uffd_flags_set_mode(flags, MFILL_ATOMIC_CONTINUE)); } long uffd_wp_range(struct vm_area_struct *dst_vma, diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index e030d63c031a..a96d126cb40e 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -585,6 +585,8 @@ static void continue_range(int ufd, __u64 start, __u64 len) req.range.start = start; req.range.len = len; req.mode = 0; + if (test_uffdio_wp) + req.mode |= UFFDIO_CONTINUE_MODE_WP; if (ioctl(ufd, UFFDIO_CONTINUE, &req)) err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, @@ -1332,6 +1334,8 @@ static int userfaultfd_minor_test(void) uffdio_register.range.start = (unsigned long)area_dst_alias; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR; + if (test_uffdio_wp) + uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) err("register failure"); -- GitLab From 50dac01113ad7ecac86384998103d6a98020d0c4 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:49 +0100 Subject: [PATCH 2212/5631] mm/mmap/vma_merge: use only primary pointers for preparing merge Patch series "cleanup vma_merge() and improve mergeability tests". My initial goal here was to try making the check for vm_ops->close in is_mergeable_vma() only be applied for vma's that would be truly removed as part of the merge (see Patch 9). This would then allow reverting the quick fix d014cd7c1c35 ("mm, mremap: fix mremap() expanding for vma's with vm_ops->close()"). This was successful enough to allow the revert (Patch 10). Checks using can_vma_merge_before() are still pessimistic about possible vma removal, and making them precise would probably complicate the vma_merge() code too much. Liam's 6.3-rc1 simplification of vma_merge() and removal of __vma_adjust() was very much helpful in understanding the vma_merge() implementation and especially when vma removals can happen, which is now very obvious. While studing the code, I've found ways to make it hopefully even more easy to follow, so that's the patches 1-8. That made me also notice a bug that's now already fixed in 6.3-rc1. This patch (of 10): In the merging preparation part of vma_merge(), some vma pointer variables are assigned for later execution of the merge, but also read from in the block itself. The code is easier follow and check against the cases diagram in the comment if the code reads only from the "primary" vma variables prev, mid, next instead. No functional change. Link: https://lkml.kernel.org/r/20230309111258.24079-1-vbabka@suse.cz Link: https://lkml.kernel.org/r/20230309111258.24079-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes ] Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index ad499f7b767f..bbb8d1226281 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -950,16 +950,16 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { remove = mid; /* case 1 */ vma_end = next->vm_end; - err = dup_anon_vma(res, remove); + err = dup_anon_vma(prev, mid); if (mid != next) { /* case 6 */ remove2 = next; - if (!remove->anon_vma) - err = dup_anon_vma(res, remove2); + if (!mid->anon_vma) + err = dup_anon_vma(prev, next); } } else if (merge_prev) { err = 0; /* case 2 */ if (mid && end > mid->vm_start) { - err = dup_anon_vma(res, mid); + err = dup_anon_vma(prev, mid); if (end == mid->vm_end) { /* case 7 */ remove = mid; } else { /* case 5 */ @@ -972,8 +972,8 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (prev && addr < prev->vm_end) { /* case 4 */ vma_end = addr; adjust = mid; - adj_next = -(vma->vm_end - addr); - err = dup_anon_vma(adjust, prev); + adj_next = -(prev->vm_end - addr); + err = dup_anon_vma(mid, prev); } else { vma = next; /* case 3 */ vma_start = addr; @@ -982,7 +982,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, err = 0; if (mid != next) { /* case 8 */ remove = mid; - err = dup_anon_vma(res, remove); + err = dup_anon_vma(next, mid); } } } -- GitLab From 097d70c6272f236eb4a29b3fb74b72df3a5344cf Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:50 +0100 Subject: [PATCH 2213/5631] mm/mmap/vma_merge: use the proper vma pointer in case 3 In case 3 we we use 'next' for everything but vma_pgoff. So use 'next' for that as well, instead of 'mid', for consistency. Then in case 8 we have to use 'mid' explicitly, which should also make the intent more obvious. Adjust the diagram for cases 1-3 in the comment to match the code - we are using 'next' for case 3 so mark the range with XXXX instead of NNNN. For case 2 that's a no-op as the code doesn't touch 'next' or 'mid'. For case 1 it's now wrong but that will be fixed next. No functional change. Link: https://lkml.kernel.org/r/20230309111258.24079-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index bbb8d1226281..be8338318cfb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -857,11 +857,11 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * mmap, brk or case 4 below case 5 below * mremap move: * AAAA AAAA - * PPPP NNNN PPPPNNNNXXXX + * PPPP XXXX PPPPNNNNXXXX * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or - * PPPPPPPPNNNN 2 or PPPPPPPPXXXX 7 or - * PPPPNNNNNNNN 3 PPPPXXXXXXXX 8 + * PPPPPPPPXXXX 2 or PPPPPPPPXXXX 7 or + * PPPPXXXXXXXX 3 PPPPXXXXXXXX 8 * * It is important for case 8 that the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must @@ -978,9 +978,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma = next; /* case 3 */ vma_start = addr; vma_end = next->vm_end; - vma_pgoff = mid->vm_pgoff; + vma_pgoff = next->vm_pgoff; err = 0; if (mid != next) { /* case 8 */ + vma_pgoff = mid->vm_pgoff; remove = mid; err = dup_anon_vma(next, mid); } -- GitLab From 5ff783f15176e85323e9d9349fefcd4de6e435bb Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:51 +0100 Subject: [PATCH 2214/5631] mm/mmap/vma_merge: use the proper vma pointers in cases 1 and 6 Case 1 is now shown in the comment as next vma being merged with prev, so use 'next' instead of 'mid'. In case 1 they both point to the same vma. As a consequence, in case 6, the dup_anon_vma() is now tried first on 'next' and then on 'mid', before it was the opposite order. This is not a functional change, as those two vma's cannnot have a different anon_vma, as that would have prevented the merging in the first place. Link: https://lkml.kernel.org/r/20230309111258.24079-4-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index be8338318cfb..d1352a653df5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -605,7 +605,7 @@ static inline void vma_complete(struct vma_prepare *vp, /* * In mprotect's case 6 (see comments on vma_merge), - * we must remove the one after next as well. + * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; @@ -948,13 +948,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { - remove = mid; /* case 1 */ + remove = next; /* case 1 */ vma_end = next->vm_end; - err = dup_anon_vma(prev, mid); + err = dup_anon_vma(prev, next); if (mid != next) { /* case 6 */ + remove = mid; remove2 = next; - if (!mid->anon_vma) - err = dup_anon_vma(prev, next); + if (!next->anon_vma) + err = dup_anon_vma(prev, mid); } } else if (merge_prev) { err = 0; /* case 2 */ -- GitLab From 183b7a60d349abeb3067867c8bdbdd6e0d3b7d86 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:52 +0100 Subject: [PATCH 2215/5631] mm/mmap/vma_merge: use the proper vma pointer in case 4 Almost all cases now use the 'next' pointer for the vma following the merged area, and the cases diagram shows it as XXXX. Case 4 is different as it uses 'mid' and NNNN, so change it for consistency. No functional change. Link: https://lkml.kernel.org/r/20230309111258.24079-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index d1352a653df5..8394901c35b4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -851,9 +851,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA - * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN + * PPPPPPNNNNNN PPPPPPXXXXXX PPPPPPNNNNNN * cannot merge might become might become - * PPNNNNNNNNNN PPPPPPPPPPNN + * PPXXXXXXXXXX PPPPPPPPPPNN * mmap, brk or case 4 below case 5 below * mremap move: * AAAA AAAA @@ -972,9 +972,9 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, res = next; if (prev && addr < prev->vm_end) { /* case 4 */ vma_end = addr; - adjust = mid; + adjust = next; adj_next = -(prev->vm_end - addr); - err = dup_anon_vma(mid, prev); + err = dup_anon_vma(next, prev); } else { vma = next; /* case 3 */ vma_start = addr; -- GitLab From 5cd70b96debbce9182e903cc6f4ed261ae55fa8b Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:53 +0100 Subject: [PATCH 2216/5631] mm/mmap/vma_merge: initialize mid and next in natural order It is more intuitive to go from prev to mid and then next. No functional change. Link: https://lkml.kernel.org/r/20230309111258.24079-6-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 8394901c35b4..d3765dcd9a15 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -912,10 +912,11 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vm_flags & VM_SPECIAL) return NULL; - next = find_vma(mm, prev ? prev->vm_end : 0); - mid = next; - if (next && next->vm_end == end) /* cases 6, 7, 8 */ - next = find_vma(mm, next->vm_end); + mid = find_vma(mm, prev ? prev->vm_end : 0); + if (mid && mid->vm_end == end) /* cases 6, 7, 8 */ + next = find_vma(mm, mid->vm_end); + else + next = mid; /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); -- GitLab From 9e8a39d2a9772aed7b97b58961e70701bd1d5899 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:54 +0100 Subject: [PATCH 2217/5631] mm/mmap/vma_merge: set mid to NULL if not applicable There are several places where we test if 'mid' is really the area NNNN in the diagram and the tests have two variants and are non-obvious to follow. Instead, set 'mid' to NULL up-front if it's not the NNNN area, and simplify the tests. Also update the description in comment accordingly. [vbabka@suse.cz: adjust/add comments as suggested by Lorenzo] Link: https://lkml.kernel.org/r/def43190-53f7-a607-d1b0-b657565f4288@suse.cz Link: https://lkml.kernel.org/r/20230309111258.24079-7-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index d3765dcd9a15..259b5e54baeb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -848,10 +848,12 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * * The following mprotect cases have to be considered, where AAAA is * the area passed down from mprotect_fixup, never extending beyond one - * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: + * vma, PPPP is the previous vma, NNNN is a vma that starts at the same + * address as AAAA and is of the same or larger span, and XXXX the next + * vma after AAAA: * * AAAA AAAA AAAA - * PPPPPPNNNNNN PPPPPPXXXXXX PPPPPPNNNNNN + * PPPPPPXXXXXX PPPPPPXXXXXX PPPPPPNNNNNN * cannot merge might become might become * PPXXXXXXXXXX PPPPPPPPPPNN * mmap, brk or case 4 below case 5 below @@ -879,9 +881,10 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * * In the code below: * PPPP is represented by *prev - * NNNN is represented by *mid (and possibly equal to *next) - * XXXX is represented by *next or not represented at all. - * AAAA is not represented - it will be merged or the function will return NULL + * NNNN is represented by *mid or not represented at all (NULL) + * XXXX is represented by *next or not represented at all (NULL) + * AAAA is not represented - it will be merged and the vma containing the + * area is returned, or the function will return NULL */ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, @@ -918,6 +921,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, else next = mid; + /* In cases 1 - 4 there's no NNNN vma */ + if (mid && end <= mid->vm_start) + mid = NULL; + /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(mid && end > mid->vm_end); @@ -952,7 +959,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, remove = next; /* case 1 */ vma_end = next->vm_end; err = dup_anon_vma(prev, next); - if (mid != next) { /* case 6 */ + if (mid) { /* case 6 */ remove = mid; remove2 = next; if (!next->anon_vma) @@ -960,7 +967,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, } } else if (merge_prev) { err = 0; /* case 2 */ - if (mid && end > mid->vm_start) { + if (mid) { err = dup_anon_vma(prev, mid); if (end == mid->vm_end) { /* case 7 */ remove = mid; @@ -982,7 +989,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_end = next->vm_end; vma_pgoff = next->vm_pgoff; err = 0; - if (mid != next) { /* case 8 */ + if (mid) { /* case 8 */ vma_pgoff = mid->vm_pgoff; remove = mid; err = dup_anon_vma(next, mid); -- GitLab From 1e76454f936178fd4e8052ddc92ce18c8937f043 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:55 +0100 Subject: [PATCH 2218/5631] mm/mmap/vma_merge: rename adj_next to adj_start The variable 'adj_next' holds the value by which we adjust vm_start of a vma in variable 'adjust', that's either 'next' or 'mid', so the current name is inaccurate. Rename it to 'adj_start'. Link: https://lkml.kernel.org/r/20230309111258.24079-8-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 259b5e54baeb..1dd9af58d08e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -904,7 +904,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, bool vma_expanded = false; struct vma_prepare vp; unsigned long vma_end = end; - long adj_next = 0; + long adj_start = 0; unsigned long vma_start = addr; validate_mm(mm); @@ -973,7 +973,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, remove = mid; } else { /* case 5 */ adjust = mid; - adj_next = (end - mid->vm_start); + adj_start = (end - mid->vm_start); } } } else if (merge_next) { @@ -981,7 +981,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (prev && addr < prev->vm_end) { /* case 4 */ vma_end = addr; adjust = next; - adj_next = -(prev->vm_end - addr); + adj_start = -(prev->vm_end - addr); err = dup_anon_vma(next, prev); } else { vma = next; /* case 3 */ @@ -1004,7 +1004,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vma_iter_prealloc(vmi)) return NULL; - vma_adjust_trans_huge(vma, vma_start, vma_end, adj_next); + vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); @@ -1020,10 +1020,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vma_expanded) vma_iter_store(vmi, vma); - if (adj_next) { - adjust->vm_start += adj_next; - adjust->vm_pgoff += adj_next >> PAGE_SHIFT; - if (adj_next < 0) { + if (adj_start) { + adjust->vm_start += adj_start; + adjust->vm_pgoff += adj_start >> PAGE_SHIFT; + if (adj_start < 0) { WARN_ON(vma_expanded); vma_iter_store(vmi, next); } -- GitLab From 2dbf401045038469e6afab1307a3cf9799c38425 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:56 +0100 Subject: [PATCH 2219/5631] mm/mmap/vma_merge: convert mergeability checks to return bool The comments already mention returning 'true' so make the code match them. Link: https://lkml.kernel.org/r/20230309111258.24079-9-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 53 +++++++++++++++++++++++++---------------------------- 1 file changed, 25 insertions(+), 28 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 1dd9af58d08e..6893eb8c66e5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -744,10 +744,10 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ -static inline int is_mergeable_vma(struct vm_area_struct *vma, - struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) +static inline bool is_mergeable_vma(struct vm_area_struct *vma, + struct file *file, unsigned long vm_flags, + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -758,21 +758,20 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) - return 0; + return false; if (vma->vm_file != file) - return 0; + return false; if (vma->vm_ops && vma->vm_ops->close) - return 0; + return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) - return 0; + return false; if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) - return 0; - return 1; + return false; + return true; } -static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, - struct anon_vma *anon_vma2, - struct vm_area_struct *vma) +static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, + struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from @@ -780,7 +779,7 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) - return 1; + return true; return anon_vma1 == anon_vma2; } @@ -795,19 +794,18 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ -static int +static bool can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) - return 1; + return true; } - return 0; + return false; } /* @@ -817,21 +815,20 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. */ -static int +static bool can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, - struct anon_vma *anon_vma, struct file *file, - pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) + struct anon_vma *anon_vma, struct file *file, + pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) - return 1; + return true; } - return 0; + return false; } /* -- GitLab From 714965ca8252f880d794f9524c6eae5f97f408c1 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:57 +0100 Subject: [PATCH 2220/5631] mm/mmap: start distinguishing if vma can be removed in mergeability test Since pre-git times, is_mergeable_vma() returns false for a vma with vm_ops->close, so that no owner assumptions are violated in case the vma is removed as part of the merge. This check is currently very conservative and can prevent merging even situations where vma can't be removed, such as simple expansion of previous vma, as evidenced by commit d014cd7c1c35 ("mm, mremap: fix mremap() expanding for vma's with vm_ops->close()") In order to allow more merging when appropriate and simplify the code that was made more complex by commit d014cd7c1c35, start distinguishing cases where the vma can be really removed, and allow merging with vm_ops->close otherwise. As a first step, add a may_remove_vma parameter to is_mergeable_vma(). can_vma_merge_before() sets it to true, because when called from vma_merge(), a removal of the vma is possible. In can_vma_merge_after(), pass the parameter as false, because no removal can occur in each of its callers: - vma_merge() calls it on the 'prev' vma, which is never removed - mmap_region() and do_brk_flags() call it to determine if it can expand a vma, which is not removed As a result, vma's with vm_ops->close may now merge with compatible ranges in more situations than previously. We can also revert commit d014cd7c1c35 as the next step to simplify mremap code again. [vbabka@suse.cz: adjust comment as suggested by Lorenzo] Link: https://lkml.kernel.org/r/74f2ea6c-f1a9-6dd7-260c-25e660f42379@suse.cz Link: https://lkml.kernel.org/r/20230309111258.24079-10-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 6893eb8c66e5..62dce9578242 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -742,12 +742,13 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, /* * If the vma has a ->close operation then the driver probably needs to release - * per-vma resources, so we don't attempt to merge those. + * per-vma resources, so we don't attempt to merge those if the caller indicates + * the current vma may be removed as part of the merge. */ static inline bool is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - struct anon_vma_name *anon_name) + struct anon_vma_name *anon_name, bool may_remove_vma) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -761,7 +762,7 @@ static inline bool is_mergeable_vma(struct vm_area_struct *vma, return false; if (vma->vm_file != file) return false; - if (vma->vm_ops && vma->vm_ops->close) + if (may_remove_vma && vma->vm_ops && vma->vm_ops->close) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return false; @@ -793,6 +794,8 @@ static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. + * + * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, @@ -800,7 +803,7 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, true) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return true; @@ -814,6 +817,8 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. + * + * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, @@ -821,7 +826,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name, false) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); -- GitLab From 4bfbe371dbc508411162d1a62e3211ed9f47f614 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 9 Mar 2023 12:12:58 +0100 Subject: [PATCH 2221/5631] mm/mremap: simplify vma expansion again This effectively reverts d014cd7c1c35 ("mm, mremap: fix mremap() expanding for vma's with vm_ops->close()"). After the recent changes, vma_merge() is able to handle the expansion properly even when the vma being expanded has a vm_ops->close operation, so we don't need to special case it anymore. Link: https://lkml.kernel.org/r/20230309111258.24079-11-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mremap.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/mm/mremap.c b/mm/mremap.c index 1ddf7beb62e9..0eaa11c845b9 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1040,23 +1040,11 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, * vma (expand operation itself) and possibly also with * the next vma if it becomes adjacent to the expanded * vma and otherwise compatible. - * - * However, vma_merge() can currently fail due to - * is_mergeable_vma() check for vm_ops->close (see the - * comment there). Yet this should not prevent vma - * expanding, so perform a simple expand for such vma. - * Ideally the check for close op should be only done - * when a vma would be actually removed due to a merge. */ - if (!vma->vm_ops || !vma->vm_ops->close) { - vma = vma_merge(&vmi, mm, vma, extension_start, - extension_end, vma->vm_flags, vma->anon_vma, - vma->vm_file, extension_pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, anon_vma_name(vma)); - } else if (vma_expand(&vmi, vma, vma->vm_start, - addr + new_len, vma->vm_pgoff, NULL)) { - vma = NULL; - } + vma = vma_merge(&vmi, mm, vma, extension_start, + extension_end, vma->vm_flags, vma->anon_vma, + vma->vm_file, extension_pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (!vma) { vm_unacct_memory(pages); ret = -ENOMEM; -- GitLab From 56d48d8dbefb1cae3aeae54284f7d6f52a41ec23 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 16 Mar 2023 19:06:46 +0800 Subject: [PATCH 2222/5631] mm: compaction: consider the number of scanning compound pages in isolate fail path commit b717d6b93b54 ("mm: compaction: include compound page count for scanning in pageblock isolation") added compound page statistics for scanning in pageblock isolation, to make sure the number of scanned pages is always larger than the number of isolated pages when isolating mirgratable or free pageblock. However, when failing to isolate the pages when scanning the migratable or free pageblocks, the isolation failure path did not consider the scanning statistics of the compound pages, which result in showing the incorrect number of scanned pages in tracepoints or in vmstats which will confuse people about the page scanning pressure in memory compaction. Thus we should take into account the number of scanning pages when failing to isolate the compound pages to make the statistics accurate. Link: https://lkml.kernel.org/r/73d6250a90707649cc010731aedc27f946d722ed.1678962352.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Vlastimil Babka Acked-by: Mel Gorman Cc: Mike Kravetz Cc: Oscar Salvador Cc: William Lam Signed-off-by: Andrew Morton --- mm/compaction.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 709136556b9e..0bddf869bbeb 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -586,6 +586,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, if (likely(order <= MAX_ORDER)) { blockpfn += (1UL << order) - 1; cursor += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; } goto isolate_fail; } @@ -904,6 +905,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (ret == -EBUSY) ret = 0; low_pfn += compound_nr(page) - 1; + nr_scanned += compound_nr(page) - 1; goto isolate_fail; } @@ -938,8 +940,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * a valid page order. Consider only values in the * valid order range to prevent low_pfn overflow. */ - if (freepage_order > 0 && freepage_order <= MAX_ORDER) + if (freepage_order > 0 && freepage_order <= MAX_ORDER) { low_pfn += (1UL << freepage_order) - 1; + nr_scanned += (1UL << freepage_order) - 1; + } continue; } @@ -954,8 +958,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (PageCompound(page) && !cc->alloc_contig) { const unsigned int order = compound_order(page); - if (likely(order <= MAX_ORDER)) + if (likely(order <= MAX_ORDER)) { low_pfn += (1UL << order) - 1; + nr_scanned += (1UL << order) - 1; + } goto isolate_fail; } @@ -1077,6 +1083,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, */ if (unlikely(PageCompound(page) && !cc->alloc_contig)) { low_pfn += compound_nr(page) - 1; + nr_scanned += compound_nr(page) - 1; SetPageLRU(page); goto isolate_fail_put; } -- GitLab From 1c06b6a599b5b7be74a6baffafa00b0f70cbe523 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 16 Mar 2023 19:06:47 +0800 Subject: [PATCH 2223/5631] mm: compaction: fix the possible deadlock when isolating hugetlb pages When trying to isolate a migratable pageblock, it can contain several normal pages or several hugetlb pages (e.g. CONT-PTE 64K hugetlb on arm64) in a pageblock. That means we may hold the lru lock of a normal page to continue to isolate the next hugetlb page by isolate_or_dissolve_huge_page() in the same migratable pageblock. However in the isolate_or_dissolve_huge_page(), it may allocate a new hugetlb page and dissolve the old one by alloc_and_dissolve_hugetlb_folio() if the hugetlb's refcount is zero. That means we can still enter the direct compaction path to allocate a new hugetlb page under the current lru lock, which may cause possible deadlock. To avoid this possible deadlock, we should release the lru lock when trying to isolate a hugetbl page. Moreover it does not make sense to take the lru lock to isolate a hugetlb, which is not in the lru list. Link: https://lkml.kernel.org/r/7ab3bffebe59fb419234a68dec1e4572a2518563.1678962352.git.baolin.wang@linux.alibaba.com Fixes: 369fa227c219 ("mm: make alloc_contig_range handle free hugetlb pages") Signed-off-by: Baolin Wang Reviewed-by: Vlastimil Babka Reviewed-by: Mike Kravetz Acked-by: Mel Gorman Cc: Oscar Salvador Cc: William Lam Signed-off-by: Andrew Morton --- mm/compaction.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/mm/compaction.c b/mm/compaction.c index 0bddf869bbeb..e689d66cedf4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -894,6 +894,11 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } if (PageHuge(page) && cc->alloc_contig) { + if (locked) { + unlock_page_lruvec_irqrestore(locked, flags); + locked = NULL; + } + ret = isolate_or_dissolve_huge_page(page, &cc->migratepages); /* -- GitLab From 9042599e81c295f0b12d940248d6608e87e7b6b6 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Fri, 17 Mar 2023 21:58:25 +0000 Subject: [PATCH 2224/5631] mm: refactor do_fault_around() Patch series "Refactor do_fault_around()" Refactor do_fault_around() to avoid bitwise tricks and rather difficult to follow logic. Additionally, prefer fault_around_pages to fault_around_bytes as the operations are performed at a base page granularity. This patch (of 2): The existing logic is confusing and fails to abstract a number of bitwise tricks. Use ALIGN_DOWN() to perform alignment, pte_index() to obtain a PTE index and represent the address range using PTE offsets, which naturally make it clear that the operation is intended to occur within only a single PTE and prevent spanning of more than one page table. We rely on the fact that fault_around_bytes will always be page-aligned, at least one page in size, a power of two and that it will not exceed PAGE_SIZE * PTRS_PER_PTE in size (i.e. the address space mapped by a PTE). These are all guaranteed by fault_around_bytes_set(). Link: https://lkml.kernel.org/r/cover.1679089214.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/d125db1c3665a63b80cea29d56407825482e2262.1679089214.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/memory.c | 38 ++++++++++++++++---------------------- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index a890b2951b53..9e6608b50261 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4449,8 +4449,8 @@ late_initcall(fault_around_debugfs); * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * - * This function doesn't cross the VMA boundaries, in order to call map_pages() - * only once. + * This function doesn't cross VMA or page table boundaries, in order to call + * map_pages() and acquire a PTE lock only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal @@ -4463,27 +4463,19 @@ late_initcall(fault_around_debugfs); */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { - unsigned long address = vmf->address, nr_pages, mask; - pgoff_t start_pgoff = vmf->pgoff; - pgoff_t end_pgoff; - int off; + pgoff_t nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; + pgoff_t pte_off = pte_index(vmf->address); + /* The page offset of vmf->address within the VMA. */ + pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; + pgoff_t from_pte, to_pte; - nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; - mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; + /* The PTE offset of the start address, clamped to the VMA. */ + from_pte = max(ALIGN_DOWN(pte_off, nr_pages), + pte_off - min(pte_off, vma_off)); - address = max(address & mask, vmf->vma->vm_start); - off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); - start_pgoff -= off; - - /* - * end_pgoff is either the end of the page table, the end of - * the vma or nr_pages from start_pgoff, depending what is nearest. - */ - end_pgoff = start_pgoff - - ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + - PTRS_PER_PTE - 1; - end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, - start_pgoff + nr_pages - 1); + /* The PTE offset of the end address, clamped to the VMA and PTE. */ + to_pte = min3(from_pte + nr_pages, (pgoff_t)PTRS_PER_PTE, + pte_off + vma_pages(vmf->vma) - vma_off) - 1; if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); @@ -4491,7 +4483,9 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) return VM_FAULT_OOM; } - return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); + return vmf->vma->vm_ops->map_pages(vmf, + vmf->pgoff + from_pte - pte_off, + vmf->pgoff + to_pte - pte_off); } /* Return true if we should do read fault-around, false otherwise */ -- GitLab From 53d36a56d8c494554e816300ebc0f7c23274b3ae Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Fri, 17 Mar 2023 21:58:26 +0000 Subject: [PATCH 2225/5631] mm: prefer fault_around_pages to fault_around_bytes All use of this value is now at page granularity, so specify the variable as such too. This simplifies the logic. We maintain the debugfs entry to ensure that there are no user-visible changes. Link: https://lkml.kernel.org/r/4995bad07fe9baa51c786fa0d81819dddfb57654.1679089214.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/memory.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 9e6608b50261..0ee13d3de88c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4405,13 +4405,13 @@ vm_fault_t finish_fault(struct vm_fault *vmf) return ret; } -static unsigned long fault_around_bytes __read_mostly = - rounddown_pow_of_two(65536); +static unsigned long fault_around_pages __read_mostly = + 65536 >> PAGE_SHIFT; #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { - *val = fault_around_bytes; + *val = fault_around_pages << PAGE_SHIFT; return 0; } @@ -4423,10 +4423,13 @@ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; - if (val > PAGE_SIZE) - fault_around_bytes = rounddown_pow_of_two(val); - else - fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ + + /* + * The minimum value is 1 page, however this results in no fault-around + * at all. See should_fault_around(). + */ + fault_around_pages = max(rounddown_pow_of_two(val) >> PAGE_SHIFT, 1UL); + return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, @@ -4452,18 +4455,18 @@ late_initcall(fault_around_debugfs); * This function doesn't cross VMA or page table boundaries, in order to call * map_pages() and acquire a PTE lock only once. * - * fault_around_bytes defines how many bytes we'll try to map. + * fault_around_pages defines how many pages we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to - * fault_around_bytes rounded down to the machine page size + * fault_around_pages * PAGE_SIZE rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { - pgoff_t nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; + pgoff_t nr_pages = READ_ONCE(fault_around_pages); pgoff_t pte_off = pte_index(vmf->address); /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; @@ -4498,7 +4501,8 @@ static inline bool should_fault_around(struct vm_fault *vmf) if (uffd_disable_fault_around(vmf->vma)) return false; - return fault_around_bytes >> PAGE_SHIFT > 1; + /* A single page implies no faulting 'around' at all. */ + return fault_around_pages > 1; } static vm_fault_t do_read_fault(struct vm_fault *vmf) -- GitLab From 5d671eb4ef7e1423a78fc0c12dd419c1dc1f6967 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Sun, 19 Mar 2023 13:42:14 +0200 Subject: [PATCH 2226/5631] mm: move get_page_from_free_area() to mm/page_alloc.c The get_page_from_free_area() helper is only used in mm/page_alloc.c so move it there to reduce noise in include/linux/mmzone.h Link: https://lkml.kernel.org/r/20230319114214.2133332-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: Lorenzo Stoakes Acked-by: Kirill A. Shutemov Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 7 ------- mm/page_alloc.c | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 35b11cc210d9..2d3d78d01283 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -108,13 +108,6 @@ struct free_area { unsigned long nr_free; }; -static inline struct page *get_page_from_free_area(struct free_area *area, - int migratetype) -{ - return list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); -} - static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c3e49d028a7a..4b09711b6f0f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1048,6 +1048,13 @@ static inline void del_page_from_free_list(struct page *page, struct zone *zone, zone->free_area[order].nr_free--; } +static inline struct page *get_page_from_free_area(struct free_area *area, + int migratetype) +{ + return list_first_entry_or_null(&area->free_list[migratetype], + struct page, lru); +} + /* * If this is not the largest possible page, check if the buddy * of the next-highest order is free. If it is, it's possible -- GitLab From 307eecd5810cb71ddaac233eee8acb3bcac3a735 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 21 Mar 2023 18:09:55 +0000 Subject: [PATCH 2227/5631] MAINTAINERS: add Lorenzo as vmalloc reviewer I have recently been involved in both reviewing and submitting patches to the vmalloc code in mm and would be willing and happy to help out with review going forward if it would be helpful! Link: https://lkml.kernel.org/r/55f663af6100c84a71a0065ac0ed22463aa340de.1679421959.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Acked-by: Uladzislau Rezki (Sony) Cc: Baoquan He Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index a62ffb710b47..ad69fe845e6d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13418,6 +13418,7 @@ VMALLOC M: Andrew Morton R: Uladzislau Rezki R: Christoph Hellwig +R: Lorenzo Stoakes L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org -- GitLab From 12b9ac6d4385e6a2ffe08e94f810cd34ee53dcdb Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:00 +0200 Subject: [PATCH 2228/5631] mips: fix comment about pgtable_init() Patch series "mm: move core MM initialization to mm/mm_init.c", v2. This set moves most of the core MM initialization to mm/mm_init.c. This largely includes free_area_init() and its helpers, functions used at boot time, mm_init() from init/main.c and some of the functions it calls. Aside from gaining some more space before mm/page_alloc.c hits 10k lines, this makes mm/page_alloc.c to be mostly about buddy allocator and moves the init code out of the way, which IMO improves maintainability. Besides, this allows to move a couple of declarations out of include/linux and make them private to mm/. And as an added bonus there a slight decrease in vmlinux size. For tinyconfig and defconfig on x86 I've got tinyconfig: text data bss dec hex filename 853206 289376 1200128 2342710 23bf36 a/vmlinux 853198 289344 1200128 2342670 23bf0e b/vmlinux defconfig: text data bss dec hex filename 26152959 9730634 2170884 38054477 244aa4d a/vmlinux 26152945 9730602 2170884 38054431 244aa1f b/vmlinux This patch (of 14): Comment about fixrange_init() says that its called from pgtable_init() while the actual caller is pagetabe_init(). Update comment to match the code. Link: https://lkml.kernel.org/r/20230321170513.2401534-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20230321170513.2401534-2-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Philippe Mathieu-Daud Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- arch/mips/include/asm/fixmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h index beea14761cef..b037718d7e8b 100644 --- a/arch/mips/include/asm/fixmap.h +++ b/arch/mips/include/asm/fixmap.h @@ -70,7 +70,7 @@ enum fixed_addresses { #include /* - * Called from pgtable_init() + * Called from pagetable_init() */ extern void fixrange_init(unsigned long start, unsigned long end, pgd_t *pgd_base); -- GitLab From fce0b4213edb960859dcc65ea414c8efb11948e1 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:01 +0200 Subject: [PATCH 2229/5631] mm/page_alloc: add helper for checking if check_pages_enabled Instead of duplicating long static_branch_enabled(&check_pages_enabled) wrap it in a helper function is_check_pages_enabled() Link: https://lkml.kernel.org/r/20230321170513.2401534-3-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- mm/page_alloc.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4b09711b6f0f..33925488040f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -245,6 +245,11 @@ EXPORT_SYMBOL(init_on_free); /* perform sanity checks on struct pages being allocated or freed */ static DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); +static inline bool is_check_pages_enabled(void) +{ + return static_branch_unlikely(&check_pages_enabled); +} + static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -1450,7 +1455,7 @@ static __always_inline bool free_pages_prepare(struct page *page, for (i = 1; i < (1 << order); i++) { if (compound) bad += free_tail_pages_check(page, page + i); - if (static_branch_unlikely(&check_pages_enabled)) { + if (is_check_pages_enabled()) { if (unlikely(free_page_is_bad(page + i))) { bad++; continue; @@ -1463,7 +1468,7 @@ static __always_inline bool free_pages_prepare(struct page *page, page->mapping = NULL; if (memcg_kmem_online() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); - if (static_branch_unlikely(&check_pages_enabled)) { + if (is_check_pages_enabled()) { if (free_page_is_bad(page)) bad++; if (bad) @@ -2373,7 +2378,7 @@ static int check_new_page(struct page *page) static inline bool check_new_pages(struct page *page, unsigned int order) { - if (static_branch_unlikely(&check_pages_enabled)) { + if (is_check_pages_enabled()) { for (int i = 0; i < (1 << order); i++) { struct page *p = page + i; -- GitLab From 9420f89db2dd611c5b436a13e13f74d65ecc3a6a Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:02 +0200 Subject: [PATCH 2230/5631] mm: move most of core MM initialization to mm/mm_init.c The bulk of memory management initialization code is spread all over mm/page_alloc.c and makes navigating through page allocator functionality difficult. Move most of the functions marked __init and __meminit to mm/mm_init.c to make it better localized and allow some more spare room before mm/page_alloc.c reaches 10k lines. No functional changes. Link: https://lkml.kernel.org/r/20230321170513.2401534-4-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/gfp.h | 5 - mm/cma.c | 1 + mm/internal.h | 38 +- mm/mm_init.c | 2304 ++++++++++++++++++++++++++++++++++ mm/page_alloc.c | 2866 ++++--------------------------------------- 5 files changed, 2614 insertions(+), 2600 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 65a78773dcca..7c554e4bd49f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -361,9 +361,4 @@ extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); -#ifdef CONFIG_CMA -/* CMA stuff */ -extern void init_cma_reserved_pageblock(struct page *page); -#endif - #endif /* __LINUX_GFP_H */ diff --git a/mm/cma.c b/mm/cma.c index a7263aa02c92..6268d6620254 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -33,6 +33,7 @@ #include #include +#include "internal.h" #include "cma.h" struct cma cma_areas[MAX_CMA_AREAS]; diff --git a/mm/internal.h b/mm/internal.h index 2a7ffd9962c4..22f1410a0ee3 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -202,6 +202,8 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); * in mm/page_alloc.c */ +extern char * const zone_names[MAX_NR_ZONES]; + /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* @@ -366,7 +368,29 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); + +static inline void prep_compound_head(struct page *page, unsigned int order) +{ + struct folio *folio = (struct folio *)page; + + set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + set_compound_order(page, order); + atomic_set(&folio->_entire_mapcount, -1); + atomic_set(&folio->_nr_pages_mapped, 0); + atomic_set(&folio->_pincount, 0); +} + +static inline void prep_compound_tail(struct page *head, int tail_idx) +{ + struct page *p = head + tail_idx; + + p->mapping = TAIL_MAPPING; + set_compound_head(p, head); + set_page_private(p, 0); +} + extern void prep_compound_page(struct page *page, unsigned int order); + extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; @@ -377,6 +401,7 @@ extern void free_unref_page_list(struct list_head *list); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); +extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, @@ -474,7 +499,12 @@ isolate_migratepages_range(struct compact_control *cc, int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end); -#endif + +/* Free whole pageblock and set its migration type to MIGRATE_CMA. */ +void init_cma_reserved_pageblock(struct page *page); + +#endif /* CONFIG_COMPACTION || CONFIG_CMA */ + int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); @@ -658,6 +688,12 @@ static inline void vunmap_range_noflush(unsigned long start, unsigned long end) #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +DECLARE_STATIC_KEY_TRUE(deferred_pages); + +bool __init deferred_grow_zone(struct zone *zone, unsigned int order); +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, diff --git a/mm/mm_init.c b/mm/mm_init.c index c1883362e71d..68d0187c7886 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -14,7 +14,14 @@ #include #include #include +#include +#include +#include +#include +#include +#include #include "internal.h" +#include "shuffle.h" #ifdef CONFIG_DEBUG_MEMORY_INIT int __meminitdata mminit_loglevel; @@ -198,3 +205,2300 @@ static int __init mm_sysfs_init(void) return 0; } postcore_initcall(mm_sysfs_init); + +static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata; +static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata; +static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata; + +static unsigned long required_kernelcore __initdata; +static unsigned long required_kernelcore_percent __initdata; +static unsigned long required_movablecore __initdata; +static unsigned long required_movablecore_percent __initdata; + +static unsigned long nr_kernel_pages __initdata; +static unsigned long nr_all_pages __initdata; +static unsigned long dma_reserve __initdata; + +bool deferred_struct_pages __meminitdata; + +static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); + +static int __init cmdline_parse_core(char *p, unsigned long *core, + unsigned long *percent) +{ + unsigned long long coremem; + char *endptr; + + if (!p) + return -EINVAL; + + /* Value may be a percentage of total memory, otherwise bytes */ + coremem = simple_strtoull(p, &endptr, 0); + if (*endptr == '%') { + /* Paranoid check for percent values greater than 100 */ + WARN_ON(coremem > 100); + + *percent = coremem; + } else { + coremem = memparse(p, &p); + /* Paranoid check that UL is enough for the coremem value */ + WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX); + + *core = coremem >> PAGE_SHIFT; + *percent = 0UL; + } + return 0; +} + +/* + * kernelcore=size sets the amount of memory for use for allocations that + * cannot be reclaimed or migrated. + */ +static int __init cmdline_parse_kernelcore(char *p) +{ + /* parse kernelcore=mirror */ + if (parse_option_str(p, "mirror")) { + mirrored_kernelcore = true; + return 0; + } + + return cmdline_parse_core(p, &required_kernelcore, + &required_kernelcore_percent); +} +early_param("kernelcore", cmdline_parse_kernelcore); + +/* + * movablecore=size sets the amount of memory for use for allocations that + * can be reclaimed or migrated. + */ +static int __init cmdline_parse_movablecore(char *p) +{ + return cmdline_parse_core(p, &required_movablecore, + &required_movablecore_percent); +} +early_param("movablecore", cmdline_parse_movablecore); + +/* + * early_calculate_totalpages() + * Sum pages in active regions for movable zone. + * Populate N_MEMORY for calculating usable_nodes. + */ +static unsigned long __init early_calculate_totalpages(void) +{ + unsigned long totalpages = 0; + unsigned long start_pfn, end_pfn; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + unsigned long pages = end_pfn - start_pfn; + + totalpages += pages; + if (pages) + node_set_state(nid, N_MEMORY); + } + return totalpages; +} + +/* + * This finds a zone that can be used for ZONE_MOVABLE pages. The + * assumption is made that zones within a node are ordered in monotonic + * increasing memory addresses so that the "highest" populated zone is used + */ +static void __init find_usable_zone_for_movable(void) +{ + int zone_index; + for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) { + if (zone_index == ZONE_MOVABLE) + continue; + + if (arch_zone_highest_possible_pfn[zone_index] > + arch_zone_lowest_possible_pfn[zone_index]) + break; + } + + VM_BUG_ON(zone_index == -1); + movable_zone = zone_index; +} + +/* + * Find the PFN the Movable zone begins in each node. Kernel memory + * is spread evenly between nodes as long as the nodes have enough + * memory. When they don't, some nodes will have more kernelcore than + * others + */ +static void __init find_zone_movable_pfns_for_nodes(void) +{ + int i, nid; + unsigned long usable_startpfn; + unsigned long kernelcore_node, kernelcore_remaining; + /* save the state before borrow the nodemask */ + nodemask_t saved_node_state = node_states[N_MEMORY]; + unsigned long totalpages = early_calculate_totalpages(); + int usable_nodes = nodes_weight(node_states[N_MEMORY]); + struct memblock_region *r; + + /* Need to find movable_zone earlier when movable_node is specified. */ + find_usable_zone_for_movable(); + + /* + * If movable_node is specified, ignore kernelcore and movablecore + * options. + */ + if (movable_node_is_enabled()) { + for_each_mem_region(r) { + if (!memblock_is_hotpluggable(r)) + continue; + + nid = memblock_get_region_node(r); + + usable_startpfn = PFN_DOWN(r->base); + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + goto out2; + } + + /* + * If kernelcore=mirror is specified, ignore movablecore option + */ + if (mirrored_kernelcore) { + bool mem_below_4gb_not_mirrored = false; + + for_each_mem_region(r) { + if (memblock_is_mirror(r)) + continue; + + nid = memblock_get_region_node(r); + + usable_startpfn = memblock_region_memory_base_pfn(r); + + if (usable_startpfn < PHYS_PFN(SZ_4G)) { + mem_below_4gb_not_mirrored = true; + continue; + } + + zone_movable_pfn[nid] = zone_movable_pfn[nid] ? + min(usable_startpfn, zone_movable_pfn[nid]) : + usable_startpfn; + } + + if (mem_below_4gb_not_mirrored) + pr_warn("This configuration results in unmirrored kernel memory.\n"); + + goto out2; + } + + /* + * If kernelcore=nn% or movablecore=nn% was specified, calculate the + * amount of necessary memory. + */ + if (required_kernelcore_percent) + required_kernelcore = (totalpages * 100 * required_kernelcore_percent) / + 10000UL; + if (required_movablecore_percent) + required_movablecore = (totalpages * 100 * required_movablecore_percent) / + 10000UL; + + /* + * If movablecore= was specified, calculate what size of + * kernelcore that corresponds so that memory usable for + * any allocation type is evenly spread. If both kernelcore + * and movablecore are specified, then the value of kernelcore + * will be used for required_kernelcore if it's greater than + * what movablecore would have allowed. + */ + if (required_movablecore) { + unsigned long corepages; + + /* + * Round-up so that ZONE_MOVABLE is at least as large as what + * was requested by the user + */ + required_movablecore = + roundup(required_movablecore, MAX_ORDER_NR_PAGES); + required_movablecore = min(totalpages, required_movablecore); + corepages = totalpages - required_movablecore; + + required_kernelcore = max(required_kernelcore, corepages); + } + + /* + * If kernelcore was not specified or kernelcore size is larger + * than totalpages, there is no ZONE_MOVABLE. + */ + if (!required_kernelcore || required_kernelcore >= totalpages) + goto out; + + /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ + usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; + +restart: + /* Spread kernelcore memory as evenly as possible throughout nodes */ + kernelcore_node = required_kernelcore / usable_nodes; + for_each_node_state(nid, N_MEMORY) { + unsigned long start_pfn, end_pfn; + + /* + * Recalculate kernelcore_node if the division per node + * now exceeds what is necessary to satisfy the requested + * amount of memory for the kernel + */ + if (required_kernelcore < kernelcore_node) + kernelcore_node = required_kernelcore / usable_nodes; + + /* + * As the map is walked, we track how much memory is usable + * by the kernel using kernelcore_remaining. When it is + * 0, the rest of the node is usable by ZONE_MOVABLE + */ + kernelcore_remaining = kernelcore_node; + + /* Go through each range of PFNs within this node */ + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + unsigned long size_pages; + + start_pfn = max(start_pfn, zone_movable_pfn[nid]); + if (start_pfn >= end_pfn) + continue; + + /* Account for what is only usable for kernelcore */ + if (start_pfn < usable_startpfn) { + unsigned long kernel_pages; + kernel_pages = min(end_pfn, usable_startpfn) + - start_pfn; + + kernelcore_remaining -= min(kernel_pages, + kernelcore_remaining); + required_kernelcore -= min(kernel_pages, + required_kernelcore); + + /* Continue if range is now fully accounted */ + if (end_pfn <= usable_startpfn) { + + /* + * Push zone_movable_pfn to the end so + * that if we have to rebalance + * kernelcore across nodes, we will + * not double account here + */ + zone_movable_pfn[nid] = end_pfn; + continue; + } + start_pfn = usable_startpfn; + } + + /* + * The usable PFN range for ZONE_MOVABLE is from + * start_pfn->end_pfn. Calculate size_pages as the + * number of pages used as kernelcore + */ + size_pages = end_pfn - start_pfn; + if (size_pages > kernelcore_remaining) + size_pages = kernelcore_remaining; + zone_movable_pfn[nid] = start_pfn + size_pages; + + /* + * Some kernelcore has been met, update counts and + * break if the kernelcore for this node has been + * satisfied + */ + required_kernelcore -= min(required_kernelcore, + size_pages); + kernelcore_remaining -= size_pages; + if (!kernelcore_remaining) + break; + } + } + + /* + * If there is still required_kernelcore, we do another pass with one + * less node in the count. This will push zone_movable_pfn[nid] further + * along on the nodes that still have memory until kernelcore is + * satisfied + */ + usable_nodes--; + if (usable_nodes && required_kernelcore > usable_nodes) + goto restart; + +out2: + /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ + for (nid = 0; nid < MAX_NUMNODES; nid++) { + unsigned long start_pfn, end_pfn; + + zone_movable_pfn[nid] = + roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (zone_movable_pfn[nid] >= end_pfn) + zone_movable_pfn[nid] = 0; + } + +out: + /* restore the node_state */ + node_states[N_MEMORY] = saved_node_state; +} + +static void __meminit __init_single_page(struct page *page, unsigned long pfn, + unsigned long zone, int nid) +{ + mm_zero_struct_page(page); + set_page_links(page, zone, nid, pfn); + init_page_count(page); + page_mapcount_reset(page); + page_cpupid_reset_last(page); + page_kasan_tag_reset(page); + + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif +} + +#ifdef CONFIG_NUMA +/* + * During memory init memblocks map pfns to nids. The search is expensive and + * this caches recent lookups. The implementation of __early_pfn_to_nid + * treats start/end as pfns. + */ +struct mminit_pfnnid_cache { + unsigned long last_start; + unsigned long last_end; + int last_nid; +}; + +static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; + +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + */ +static int __meminit __early_pfn_to_nid(unsigned long pfn, + struct mminit_pfnnid_cache *state) +{ + unsigned long start_pfn, end_pfn; + int nid; + + if (state->last_start <= pfn && pfn < state->last_end) + return state->last_nid; + + nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); + if (nid != NUMA_NO_NODE) { + state->last_start = start_pfn; + state->last_end = end_pfn; + state->last_nid = nid; + } + + return nid; +} + +int __meminit early_pfn_to_nid(unsigned long pfn) +{ + static DEFINE_SPINLOCK(early_pfn_lock); + int nid; + + spin_lock(&early_pfn_lock); + nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); + if (nid < 0) + nid = first_online_node; + spin_unlock(&early_pfn_lock); + + return nid; +} +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static inline void pgdat_set_deferred_range(pg_data_t *pgdat) +{ + pgdat->first_deferred_pfn = ULONG_MAX; +} + +/* Returns true if the struct page for the pfn is initialised */ +static inline bool __meminit early_page_initialised(unsigned long pfn) +{ + int nid = early_pfn_to_nid(pfn); + + if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) + return false; + + return true; +} + +/* + * Returns true when the remaining initialisation should be deferred until + * later in the boot cycle when it can be parallelised. + */ +static bool __meminit +defer_init(int nid, unsigned long pfn, unsigned long end_pfn) +{ + static unsigned long prev_end_pfn, nr_initialised; + + if (early_page_ext_enabled()) + return false; + /* + * prev_end_pfn static that contains the end of previous zone + * No need to protect because called very early in boot before smp_init. + */ + if (prev_end_pfn != end_pfn) { + prev_end_pfn = end_pfn; + nr_initialised = 0; + } + + /* Always populate low zones for address-constrained allocations */ + if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) + return false; + + if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) + return true; + /* + * We start only with one section of pages, more pages are added as + * needed until the rest of deferred pages are initialized. + */ + nr_initialised++; + if ((nr_initialised > PAGES_PER_SECTION) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + NODE_DATA(nid)->first_deferred_pfn = pfn; + return true; + } + return false; +} + +static void __meminit init_reserved_page(unsigned long pfn) +{ + pg_data_t *pgdat; + int nid, zid; + + if (early_page_initialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + pgdat = NODE_DATA(nid); + + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + struct zone *zone = &pgdat->node_zones[zid]; + + if (zone_spans_pfn(zone, pfn)) + break; + } + __init_single_page(pfn_to_page(pfn), pfn, zid, nid); +} +#else +static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {} + +static inline bool early_page_initialised(unsigned long pfn) +{ + return true; +} + +static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) +{ + return false; +} + +static inline void init_reserved_page(unsigned long pfn) +{ +} +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +/* + * Initialised pages do not have PageReserved set. This function is + * called for each range allocated by the bootmem allocator and + * marks the pages PageReserved. The remaining valid pages are later + * sent to the buddy page allocator. + */ +void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) +{ + unsigned long start_pfn = PFN_DOWN(start); + unsigned long end_pfn = PFN_UP(end); + + for (; start_pfn < end_pfn; start_pfn++) { + if (pfn_valid(start_pfn)) { + struct page *page = pfn_to_page(start_pfn); + + init_reserved_page(start_pfn); + + /* Avoid false-positive PageTail() */ + INIT_LIST_HEAD(&page->lru); + + /* + * no need for atomic set_bit because the struct + * page is not visible yet so nobody should + * access it yet. + */ + __SetPageReserved(page); + } + } +} + +/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */ +static bool __meminit +overlap_memmap_init(unsigned long zone, unsigned long *pfn) +{ + static struct memblock_region *r; + + if (mirrored_kernelcore && zone == ZONE_MOVABLE) { + if (!r || *pfn >= memblock_region_memory_end_pfn(r)) { + for_each_mem_region(r) { + if (*pfn < memblock_region_memory_end_pfn(r)) + break; + } + } + if (*pfn >= memblock_region_memory_base_pfn(r) && + memblock_is_mirror(r)) { + *pfn = memblock_region_memory_end_pfn(r); + return true; + } + } + return false; +} + +/* + * Only struct pages that correspond to ranges defined by memblock.memory + * are zeroed and initialized by going through __init_single_page() during + * memmap_init_zone_range(). + * + * But, there could be struct pages that correspond to holes in + * memblock.memory. This can happen because of the following reasons: + * - physical memory bank size is not necessarily the exact multiple of the + * arbitrary section size + * - early reserved memory may not be listed in memblock.memory + * - memory layouts defined with memmap= kernel parameter may not align + * nicely with memmap sections + * + * Explicitly initialize those struct pages so that: + * - PG_Reserved is set + * - zone and node links point to zone and node that span the page if the + * hole is in the middle of a zone + * - zone and node links point to adjacent zone/node if the hole falls on + * the zone boundary; the pages in such holes will be prepended to the + * zone/node above the hole except for the trailing pages in the last + * section that will be appended to the zone/node below. + */ +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) +{ + unsigned long pfn; + u64 pgcnt = 0; + + for (pfn = spfn; pfn < epfn; pfn++) { + if (!pfn_valid(pageblock_start_pfn(pfn))) { + pfn = pageblock_end_pfn(pfn) - 1; + continue; + } + __init_single_page(pfn_to_page(pfn), pfn, zone, node); + __SetPageReserved(pfn_to_page(pfn)); + pgcnt++; + } + + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); +} + +/* + * Initially all pages are reserved - free ones are freed + * up by memblock_free_all() once the early boot process is + * done. Non-atomic initialization, single-pass. + * + * All aligned pageblocks are initialized to the specified migratetype + * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related + * zone stats (e.g., nr_isolate_pageblock) are touched. + */ +void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone, + unsigned long start_pfn, unsigned long zone_end_pfn, + enum meminit_context context, + struct vmem_altmap *altmap, int migratetype) +{ + unsigned long pfn, end_pfn = start_pfn + size; + struct page *page; + + if (highest_memmap_pfn < end_pfn - 1) + highest_memmap_pfn = end_pfn - 1; + +#ifdef CONFIG_ZONE_DEVICE + /* + * Honor reservation requested by the driver for this ZONE_DEVICE + * memory. We limit the total number of pages to initialize to just + * those that might contain the memory mapping. We will defer the + * ZONE_DEVICE page initialization until after we have released + * the hotplug lock. + */ + if (zone == ZONE_DEVICE) { + if (!altmap) + return; + + if (start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + } +#endif + + for (pfn = start_pfn; pfn < end_pfn; ) { + /* + * There can be holes in boot-time mem_map[]s handed to this + * function. They do not exist on hotplugged memory. + */ + if (context == MEMINIT_EARLY) { + if (overlap_memmap_init(zone, &pfn)) + continue; + if (defer_init(nid, pfn, zone_end_pfn)) { + deferred_struct_pages = true; + break; + } + } + + page = pfn_to_page(pfn); + __init_single_page(page, pfn, zone, nid); + if (context == MEMINIT_HOTPLUG) + __SetPageReserved(page); + + /* + * Usually, we want to mark the pageblock MIGRATE_MOVABLE, + * such that unmovable allocations won't be scattered all + * over the place during system boot. + */ + if (pageblock_aligned(pfn)) { + set_pageblock_migratetype(page, migratetype); + cond_resched(); + } + pfn++; + } +} + +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) +{ + unsigned long zone_start_pfn = zone->zone_start_pfn; + unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +static void __init memmap_init(void) +{ + unsigned long start_pfn, end_pfn; + unsigned long hole_pfn = 0; + int i, j, zone_id = 0, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); + + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; + + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } + } + +#ifdef CONFIG_SPARSEMEM + /* + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway + */ + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); + if (hole_pfn < end_pfn) +#endif + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); +} + +#ifdef CONFIG_ZONE_DEVICE +static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, + unsigned long zone_idx, int nid, + struct dev_pagemap *pgmap) +{ + + __init_single_page(page, pfn, zone_idx, nid); + + /* + * Mark page reserved as it will need to wait for onlining + * phase for it to be fully associated with a zone. + * + * We can use the non-atomic __set_bit operation for setting + * the flag as we are still initializing the pages. + */ + __SetPageReserved(page); + + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer + * and zone_device_data. It is a bug if a ZONE_DEVICE page is + * ever freed or placed on a driver-private list. + */ + page->pgmap = pgmap; + page->zone_device_data = NULL; + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. + * + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap + * because this is done early in section_activate() + */ + if (pageblock_aligned(pfn)) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); + } + + /* + * ZONE_DEVICE pages are released directly to the driver page allocator + * which will set the page count to 1 when allocating the page. + */ + if (pgmap->type == MEMORY_DEVICE_PRIVATE || + pgmap->type == MEMORY_DEVICE_COHERENT) + set_page_count(page, 0); +} + +/* + * With compound page geometry and when struct pages are stored in ram most + * tail pages are reused. Consequently, the amount of unique struct pages to + * initialize is a lot smaller that the total amount of struct pages being + * mapped. This is a paired / mild layering violation with explicit knowledge + * of how the sparse_vmemmap internals handle compound pages in the lack + * of an altmap. See vmemmap_populate_compound_pages(). + */ +static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap, + unsigned long nr_pages) +{ + return is_power_of_2(sizeof(struct page)) && + !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages; +} + +static void __ref memmap_init_compound(struct page *head, + unsigned long head_pfn, + unsigned long zone_idx, int nid, + struct dev_pagemap *pgmap, + unsigned long nr_pages) +{ + unsigned long pfn, end_pfn = head_pfn + nr_pages; + unsigned int order = pgmap->vmemmap_shift; + + __SetPageHead(head); + for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + prep_compound_tail(head, pfn - head_pfn); + set_page_count(page, 0); + + /* + * The first tail page stores important compound page info. + * Call prep_compound_head() after the first tail page has + * been initialized, to not have the data overwritten. + */ + if (pfn == head_pfn + 1) + prep_compound_head(head, order); + } +} + +void __ref memmap_init_zone_device(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages, + struct dev_pagemap *pgmap) +{ + unsigned long pfn, end_pfn = start_pfn + nr_pages; + struct pglist_data *pgdat = zone->zone_pgdat; + struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap); + unsigned long zone_idx = zone_idx(zone); + unsigned long start = jiffies; + int nid = pgdat->node_id; + + if (WARN_ON_ONCE(!pgmap || zone_idx != ZONE_DEVICE)) + return; + + /* + * The call to memmap_init should have already taken care + * of the pages reserved for the memmap, so we can just jump to + * the end of that region and start processing the device pages. + */ + if (altmap) { + start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + nr_pages = end_pfn - start_pfn; + } + + for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) { + struct page *page = pfn_to_page(pfn); + + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + + if (pfns_per_compound == 1) + continue; + + memmap_init_compound(page, pfn, zone_idx, nid, pgmap, + compound_nr_pages(altmap, pfns_per_compound)); + } + + pr_info("%s initialised %lu pages in %ums\n", __func__, + nr_pages, jiffies_to_msecs(jiffies - start)); +} +#endif + +/* + * The zone ranges provided by the architecture do not include ZONE_MOVABLE + * because it is sized independent of architecture. Unlike the other zones, + * the starting point for ZONE_MOVABLE is not fixed. It may be different + * in each node depending on the size of each node and how evenly kernelcore + * is distributed. This helper function adjusts the zone ranges + * provided by the architecture for a given node by using the end of the + * highest usable zone for ZONE_MOVABLE. This preserves the assumption that + * zones within a node are in order of monotonic increases memory addresses + */ +static void __init adjust_zone_range_for_zone_movable(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, + unsigned long *zone_start_pfn, + unsigned long *zone_end_pfn) +{ + /* Only adjust if ZONE_MOVABLE is on this node */ + if (zone_movable_pfn[nid]) { + /* Size ZONE_MOVABLE */ + if (zone_type == ZONE_MOVABLE) { + *zone_start_pfn = zone_movable_pfn[nid]; + *zone_end_pfn = min(node_end_pfn, + arch_zone_highest_possible_pfn[movable_zone]); + + /* Adjust for ZONE_MOVABLE starting within this range */ + } else if (!mirrored_kernelcore && + *zone_start_pfn < zone_movable_pfn[nid] && + *zone_end_pfn > zone_movable_pfn[nid]) { + *zone_end_pfn = zone_movable_pfn[nid]; + + /* Check if this whole range is within ZONE_MOVABLE */ + } else if (*zone_start_pfn >= zone_movable_pfn[nid]) + *zone_start_pfn = *zone_end_pfn; + } +} + +/* + * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, + * then all holes in the requested range will be accounted for. + */ +unsigned long __init __absent_pages_in_range(int nid, + unsigned long range_start_pfn, + unsigned long range_end_pfn) +{ + unsigned long nr_absent = range_end_pfn - range_start_pfn; + unsigned long start_pfn, end_pfn; + int i; + + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); + end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + nr_absent -= end_pfn - start_pfn; + } + return nr_absent; +} + +/** + * absent_pages_in_range - Return number of page frames in holes within a range + * @start_pfn: The start PFN to start searching for holes + * @end_pfn: The end PFN to stop searching for holes + * + * Return: the number of pages frames in memory holes within a range. + */ +unsigned long __init absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn) +{ + return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); +} + +/* Return the number of page frames in holes in a zone on a node */ +static unsigned long __init zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn) +{ + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; + unsigned long zone_start_pfn, zone_end_pfn; + unsigned long nr_absent; + + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); + + adjust_zone_range_for_zone_movable(nid, zone_type, + node_start_pfn, node_end_pfn, + &zone_start_pfn, &zone_end_pfn); + nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); + + /* + * ZONE_MOVABLE handling. + * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages + * and vice versa. + */ + if (mirrored_kernelcore && zone_movable_pfn[nid]) { + unsigned long start_pfn, end_pfn; + struct memblock_region *r; + + for_each_mem_region(r) { + start_pfn = clamp(memblock_region_memory_base_pfn(r), + zone_start_pfn, zone_end_pfn); + end_pfn = clamp(memblock_region_memory_end_pfn(r), + zone_start_pfn, zone_end_pfn); + + if (zone_type == ZONE_MOVABLE && + memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; + + if (zone_type == ZONE_NORMAL && + !memblock_is_mirror(r)) + nr_absent += end_pfn - start_pfn; + } + } + + return nr_absent; +} + +/* + * Return the number of pages a zone spans in a node, including holes + * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() + */ +static unsigned long __init zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long node_start_pfn, + unsigned long node_end_pfn, + unsigned long *zone_start_pfn, + unsigned long *zone_end_pfn) +{ + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; + /* When hotadd a new node from cpu_up(), the node should be empty */ + if (!node_start_pfn && !node_end_pfn) + return 0; + + /* Get the start and end of the zone */ + *zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + *zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); + adjust_zone_range_for_zone_movable(nid, zone_type, + node_start_pfn, node_end_pfn, + zone_start_pfn, zone_end_pfn); + + /* Check that this node has pages within the zone's required range */ + if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn) + return 0; + + /* Move the zone boundaries inside the node if necessary */ + *zone_end_pfn = min(*zone_end_pfn, node_end_pfn); + *zone_start_pfn = max(*zone_start_pfn, node_start_pfn); + + /* Return the spanned pages */ + return *zone_end_pfn - *zone_start_pfn; +} + +static void __init calculate_node_totalpages(struct pglist_data *pgdat, + unsigned long node_start_pfn, + unsigned long node_end_pfn) +{ + unsigned long realtotalpages = 0, totalpages = 0; + enum zone_type i; + + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + unsigned long zone_start_pfn, zone_end_pfn; + unsigned long spanned, absent; + unsigned long size, real_size; + + spanned = zone_spanned_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn, + &zone_start_pfn, + &zone_end_pfn); + absent = zone_absent_pages_in_node(pgdat->node_id, i, + node_start_pfn, + node_end_pfn); + + size = spanned; + real_size = size - absent; + + if (size) + zone->zone_start_pfn = zone_start_pfn; + else + zone->zone_start_pfn = 0; + zone->spanned_pages = size; + zone->present_pages = real_size; +#if defined(CONFIG_MEMORY_HOTPLUG) + zone->present_early_pages = real_size; +#endif + + totalpages += size; + realtotalpages += real_size; + } + + pgdat->node_spanned_pages = totalpages; + pgdat->node_present_pages = realtotalpages; + pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); +} + +static unsigned long __init calc_memmap_size(unsigned long spanned_pages, + unsigned long present_pages) +{ + unsigned long pages = spanned_pages; + + /* + * Provide a more accurate estimation if there are holes within + * the zone and SPARSEMEM is in use. If there are holes within the + * zone, each populated memory region may cost us one or two extra + * memmap pages due to alignment because memmap pages for each + * populated regions may not be naturally aligned on page boundary. + * So the (present_pages >> 4) heuristic is a tradeoff for that. + */ + if (spanned_pages > present_pages + (present_pages >> 4) && + IS_ENABLED(CONFIG_SPARSEMEM)) + pages = present_pages; + + return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static void pgdat_init_split_queue(struct pglist_data *pgdat) +{ + struct deferred_split *ds_queue = &pgdat->deferred_split_queue; + + spin_lock_init(&ds_queue->split_queue_lock); + INIT_LIST_HEAD(&ds_queue->split_queue); + ds_queue->split_queue_len = 0; +} +#else +static void pgdat_init_split_queue(struct pglist_data *pgdat) {} +#endif + +#ifdef CONFIG_COMPACTION +static void pgdat_init_kcompactd(struct pglist_data *pgdat) +{ + init_waitqueue_head(&pgdat->kcompactd_wait); +} +#else +static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} +#endif + +static void __meminit pgdat_init_internals(struct pglist_data *pgdat) +{ + int i; + + pgdat_resize_init(pgdat); + pgdat_kswapd_lock_init(pgdat); + + pgdat_init_split_queue(pgdat); + pgdat_init_kcompactd(pgdat); + + init_waitqueue_head(&pgdat->kswapd_wait); + init_waitqueue_head(&pgdat->pfmemalloc_wait); + + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + + pgdat_page_ext_init(pgdat); + lruvec_init(&pgdat->__lruvec); +} + +static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid, + unsigned long remaining_pages) +{ + atomic_long_set(&zone->managed_pages, remaining_pages); + zone_set_nid(zone, nid); + zone->name = zone_names[idx]; + zone->zone_pgdat = NODE_DATA(nid); + spin_lock_init(&zone->lock); + zone_seqlock_init(zone); + zone_pcp_init(zone); +} + +static void __meminit zone_init_free_lists(struct zone *zone) +{ + unsigned int order, t; + for_each_migratetype_order(order, t) { + INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); + zone->free_area[order].nr_free = 0; + } +} + +void __meminit init_currently_empty_zone(struct zone *zone, + unsigned long zone_start_pfn, + unsigned long size) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int zone_idx = zone_idx(zone) + 1; + + if (zone_idx > pgdat->nr_zones) + pgdat->nr_zones = zone_idx; + + zone->zone_start_pfn = zone_start_pfn; + + mminit_dprintk(MMINIT_TRACE, "memmap_init", + "Initialising map node %d zone %lu pfns %lu -> %lu\n", + pgdat->node_id, + (unsigned long)zone_idx(zone), + zone_start_pfn, (zone_start_pfn + size)); + + zone_init_free_lists(zone); + zone->initialized = 1; +} + +#ifndef CONFIG_SPARSEMEM +/* + * Calculate the size of the zone->blockflags rounded to an unsigned long + * Start by making sure zonesize is a multiple of pageblock_order by rounding + * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally + * round what is now in bits to nearest long in bits, then return it in + * bytes. + */ +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) +{ + unsigned long usemapsize; + + zonesize += zone_start_pfn & (pageblock_nr_pages-1); + usemapsize = roundup(zonesize, pageblock_nr_pages); + usemapsize = usemapsize >> pageblock_order; + usemapsize *= NR_PAGEBLOCK_BITS; + usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long)); + + return usemapsize / 8; +} + +static void __ref setup_usemap(struct zone *zone) +{ + unsigned long usemapsize = usemap_size(zone->zone_start_pfn, + zone->spanned_pages); + zone->pageblock_flags = NULL; + if (usemapsize) { + zone->pageblock_flags = + memblock_alloc_node(usemapsize, SMP_CACHE_BYTES, + zone_to_nid(zone)); + if (!zone->pageblock_flags) + panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n", + usemapsize, zone->name, zone_to_nid(zone)); + } +} +#else +static inline void setup_usemap(struct zone *zone) {} +#endif /* CONFIG_SPARSEMEM */ + +#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE + +/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ +void __init set_pageblock_order(void) +{ + unsigned int order = MAX_ORDER; + + /* Check that pageblock_nr_pages has not already been setup */ + if (pageblock_order) + return; + + /* Don't let pageblocks exceed the maximum allocation granularity. */ + if (HPAGE_SHIFT > PAGE_SHIFT && HUGETLB_PAGE_ORDER < order) + order = HUGETLB_PAGE_ORDER; + + /* + * Assume the largest contiguous order of interest is a huge page. + * This value may be variable depending on boot parameters on IA64 and + * powerpc. + */ + pageblock_order = order; +} +#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +/* + * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order() + * is unused as pageblock_order is set at compile-time. See + * include/linux/pageblock-flags.h for the values of pageblock_order based on + * the kernel config + */ +void __init set_pageblock_order(void) +{ +} + +#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ + +/* + * Set up the zone data structures + * - init pgdat internals + * - init all zones belonging to this node + * + * NOTE: this function is only called during memory hotplug + */ +#ifdef CONFIG_MEMORY_HOTPLUG +void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) +{ + int nid = pgdat->node_id; + enum zone_type z; + int cpu; + + pgdat_init_internals(pgdat); + + if (pgdat->per_cpu_nodestats == &boot_nodestats) + pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); + + /* + * Reset the nr_zones, order and highest_zoneidx before reuse. + * Note that kswapd will init kswapd_highest_zoneidx properly + * when it starts in the near future. + */ + pgdat->nr_zones = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_highest_zoneidx = 0; + pgdat->node_start_pfn = 0; + for_each_online_cpu(cpu) { + struct per_cpu_nodestat *p; + + p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); + memset(p, 0, sizeof(*p)); + } + + for (z = 0; z < MAX_NR_ZONES; z++) + zone_init_internals(&pgdat->node_zones[z], z, nid, 0); +} +#endif + +/* + * Set up the zone data structures: + * - mark all pages reserved + * - mark all memory queues empty + * - clear the memory bitmaps + * + * NOTE: pgdat should get zeroed by caller. + * NOTE: this function is only called during early init. + */ +static void __init free_area_init_core(struct pglist_data *pgdat) +{ + enum zone_type j; + int nid = pgdat->node_id; + + pgdat_init_internals(pgdat); + pgdat->per_cpu_nodestats = &boot_nodestats; + + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = pgdat->node_zones + j; + unsigned long size, freesize, memmap_pages; + + size = zone->spanned_pages; + freesize = zone->present_pages; + + /* + * Adjust freesize so that it accounts for how much memory + * is used by this zone for memmap. This affects the watermark + * and per-cpu initialisations + */ + memmap_pages = calc_memmap_size(size, freesize); + if (!is_highmem_idx(j)) { + if (freesize >= memmap_pages) { + freesize -= memmap_pages; + if (memmap_pages) + pr_debug(" %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); + } else + pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", + zone_names[j], memmap_pages, freesize); + } + + /* Account for reserved pages */ + if (j == 0 && freesize > dma_reserve) { + freesize -= dma_reserve; + pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); + } + + if (!is_highmem_idx(j)) + nr_kernel_pages += freesize; + /* Charge for highmem memmap if there are enough kernel pages */ + else if (nr_kernel_pages > memmap_pages * 2) + nr_kernel_pages -= memmap_pages; + nr_all_pages += freesize; + + /* + * Set an approximate value for lowmem here, it will be adjusted + * when the bootmem allocator frees pages into the buddy system. + * And all highmem pages will be managed by the buddy system. + */ + zone_init_internals(zone, j, nid, freesize); + + if (!size) + continue; + + set_pageblock_order(); + setup_usemap(zone); + init_currently_empty_zone(zone, zone->zone_start_pfn, size); + } +} + +void __init *memmap_alloc(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, int nid, bool exact_nid) +{ + void *ptr; + + if (exact_nid) + ptr = memblock_alloc_exact_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + else + ptr = memblock_alloc_try_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + +#ifdef CONFIG_FLATMEM +static void __init alloc_node_mem_map(struct pglist_data *pgdat) +{ + unsigned long __maybe_unused start = 0; + unsigned long __maybe_unused offset = 0; + + /* Skip empty nodes */ + if (!pgdat->node_spanned_pages) + return; + + start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); + offset = pgdat->node_start_pfn - start; + /* ia64 gets its own node_mem_map, before this, without bootmem */ + if (!pgdat->node_mem_map) { + unsigned long size, end; + struct page *map; + + /* + * The zone's endpoints aren't required to be MAX_ORDER + * aligned but the node_mem_map endpoints must be in order + * for the buddy allocator to function correctly. + */ + end = pgdat_end_pfn(pgdat); + end = ALIGN(end, MAX_ORDER_NR_PAGES); + size = (end - start) * sizeof(struct page); + map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, + pgdat->node_id, false); + if (!map) + panic("Failed to allocate %ld bytes for node %d memory map\n", + size, pgdat->node_id); + pgdat->node_mem_map = map + offset; + } + pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", + __func__, pgdat->node_id, (unsigned long)pgdat, + (unsigned long)pgdat->node_mem_map); +#ifndef CONFIG_NUMA + /* + * With no DISCONTIG, the global mem_map is just set as node 0's + */ + if (pgdat == NODE_DATA(0)) { + mem_map = NODE_DATA(0)->node_mem_map; + if (page_to_pfn(mem_map) != pgdat->node_start_pfn) + mem_map -= offset; + } +#endif +} +#else +static inline void alloc_node_mem_map(struct pglist_data *pgdat) { } +#endif /* CONFIG_FLATMEM */ + +/** + * get_pfn_range_for_nid - Return the start and end page frames for a node + * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. + * @start_pfn: Passed by reference. On return, it will have the node start_pfn. + * @end_pfn: Passed by reference. On return, it will have the node end_pfn. + * + * It returns the start and end page frame of a node based on information + * provided by memblock_set_node(). If called for a node + * with no available memory, a warning is printed and the start and end + * PFNs will be 0. + */ +void __init get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + unsigned long this_start_pfn, this_end_pfn; + int i; + + *start_pfn = -1UL; + *end_pfn = 0; + + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + *start_pfn = min(*start_pfn, this_start_pfn); + *end_pfn = max(*end_pfn, this_end_pfn); + } + + if (*start_pfn == -1UL) + *start_pfn = 0; +} + +static void __init free_area_init_node(int nid) +{ + pg_data_t *pgdat = NODE_DATA(nid); + unsigned long start_pfn = 0; + unsigned long end_pfn = 0; + + /* pg_data_t should be reset to zero when it's allocated */ + WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + + pgdat->node_id = nid; + pgdat->node_start_pfn = start_pfn; + pgdat->per_cpu_nodestats = NULL; + + if (start_pfn != end_pfn) { + pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); + } else { + pr_info("Initmem setup node %d as memoryless\n", nid); + } + + calculate_node_totalpages(pgdat, start_pfn, end_pfn); + + alloc_node_mem_map(pgdat); + pgdat_set_deferred_range(pgdat); + + free_area_init_core(pgdat); + lru_gen_init_pgdat(pgdat); +} + +/* Any regular or high memory on that node ? */ +static void check_for_memory(pg_data_t *pgdat, int nid) +{ + enum zone_type zone_type; + + for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { + struct zone *zone = &pgdat->node_zones[zone_type]; + if (populated_zone(zone)) { + if (IS_ENABLED(CONFIG_HIGHMEM)) + node_set_state(nid, N_HIGH_MEMORY); + if (zone_type <= ZONE_NORMAL) + node_set_state(nid, N_NORMAL_MEMORY); + break; + } + } +} + +#if MAX_NUMNODES > 1 +/* + * Figure out the number of possible node ids. + */ +void __init setup_nr_node_ids(void) +{ + unsigned int highest; + + highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES); + nr_node_ids = highest + 1; +} +#endif + +static void __init free_area_init_memoryless_node(int nid) +{ + free_area_init_node(nid); +} + +/* + * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For + * such cases we allow max_zone_pfn sorted in the descending order + */ +bool __weak arch_has_descending_max_zone_pfns(void) +{ + return false; +} + +/** + * free_area_init - Initialise all pg_data_t and zone data + * @max_zone_pfn: an array of max PFNs for each zone + * + * This will call free_area_init_node() for each active node in the system. + * Using the page ranges provided by memblock_set_node(), the size of each + * zone in each node and their holes is calculated. If the maximum PFN + * between two adjacent zones match, it is assumed that the zone is empty. + * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed + * that arch_max_dma32_pfn has no pages. It is also assumed that a zone + * starts where the previous one ended. For example, ZONE_DMA32 starts + * at arch_max_dma_pfn. + */ +void __init free_area_init(unsigned long *max_zone_pfn) +{ + unsigned long start_pfn, end_pfn; + int i, nid, zone; + bool descending; + + /* Record where the zone boundaries are */ + memset(arch_zone_lowest_possible_pfn, 0, + sizeof(arch_zone_lowest_possible_pfn)); + memset(arch_zone_highest_possible_pfn, 0, + sizeof(arch_zone_highest_possible_pfn)); + + start_pfn = PHYS_PFN(memblock_start_of_DRAM()); + descending = arch_has_descending_max_zone_pfns(); + + for (i = 0; i < MAX_NR_ZONES; i++) { + if (descending) + zone = MAX_NR_ZONES - i - 1; + else + zone = i; + + if (zone == ZONE_MOVABLE) + continue; + + end_pfn = max(max_zone_pfn[zone], start_pfn); + arch_zone_lowest_possible_pfn[zone] = start_pfn; + arch_zone_highest_possible_pfn[zone] = end_pfn; + + start_pfn = end_pfn; + } + + /* Find the PFNs that ZONE_MOVABLE begins at in each node */ + memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); + find_zone_movable_pfns_for_nodes(); + + /* Print out the zone ranges */ + pr_info("Zone ranges:\n"); + for (i = 0; i < MAX_NR_ZONES; i++) { + if (i == ZONE_MOVABLE) + continue; + pr_info(" %-8s ", zone_names[i]); + if (arch_zone_lowest_possible_pfn[i] == + arch_zone_highest_possible_pfn[i]) + pr_cont("empty\n"); + else + pr_cont("[mem %#018Lx-%#018Lx]\n", + (u64)arch_zone_lowest_possible_pfn[i] + << PAGE_SHIFT, + ((u64)arch_zone_highest_possible_pfn[i] + << PAGE_SHIFT) - 1); + } + + /* Print out the PFNs ZONE_MOVABLE begins at in each node */ + pr_info("Movable zone start for each node\n"); + for (i = 0; i < MAX_NUMNODES; i++) { + if (zone_movable_pfn[i]) + pr_info(" Node %d: %#018Lx\n", i, + (u64)zone_movable_pfn[i] << PAGE_SHIFT); + } + + /* + * Print out the early node map, and initialize the + * subsection-map relative to active online memory ranges to + * enable future "sub-section" extensions of the memory map. + */ + pr_info("Early memory node ranges\n"); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + ((u64)end_pfn << PAGE_SHIFT) - 1); + subsection_map_init(start_pfn, end_pfn - start_pfn); + } + + /* Initialise every node */ + mminit_verify_pageflags_layout(); + setup_nr_node_ids(); + for_each_node(nid) { + pg_data_t *pgdat; + + if (!node_online(nid)) { + pr_info("Initializing node %d as memoryless\n", nid); + + /* Allocator not initialized yet */ + pgdat = arch_alloc_nodedata(nid); + if (!pgdat) + panic("Cannot allocate %zuB for node %d.\n", + sizeof(*pgdat), nid); + arch_refresh_nodedata(nid, pgdat); + free_area_init_memoryless_node(nid); + + /* + * We do not want to confuse userspace by sysfs + * files/directories for node without any memory + * attached to it, so this node is not marked as + * N_MEMORY and not marked online so that no sysfs + * hierarchy will be created via register_one_node for + * it. The pgdat will get fully initialized by + * hotadd_init_pgdat() when memory is hotplugged into + * this node. + */ + continue; + } + + pgdat = NODE_DATA(nid); + free_area_init_node(nid); + + /* Any memory on that node */ + if (pgdat->node_present_pages) + node_set_state(nid, N_MEMORY); + check_for_memory(pgdat, nid); + } + + memmap_init(); +} + +/** + * node_map_pfn_alignment - determine the maximum internode alignment + * + * This function should be called after node map is populated and sorted. + * It calculates the maximum power of two alignment which can distinguish + * all the nodes. + * + * For example, if all nodes are 1GiB and aligned to 1GiB, the return value + * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the + * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is + * shifted, 1GiB is enough and this function will indicate so. + * + * This is used to test whether pfn -> nid mapping of the chosen memory + * model has fine enough granularity to avoid incorrect mapping for the + * populated node map. + * + * Return: the determined alignment in pfn's. 0 if there is no alignment + * requirement (single node). + */ +unsigned long __init node_map_pfn_alignment(void) +{ + unsigned long accl_mask = 0, last_end = 0; + unsigned long start, end, mask; + int last_nid = NUMA_NO_NODE; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { + if (!start || last_nid < 0 || last_nid == nid) { + last_nid = nid; + last_end = end; + continue; + } + + /* + * Start with a mask granular enough to pin-point to the + * start pfn and tick off bits one-by-one until it becomes + * too coarse to separate the current node from the last. + */ + mask = ~((1 << __ffs(start)) - 1); + while (mask && last_end <= (start & (mask << 1))) + mask <<= 1; + + /* accumulate all internode masks */ + accl_mask |= mask; + } + + /* convert mask to number of pages */ + return ~accl_mask + 1; +} + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +static void __init deferred_free_range(unsigned long pfn, + unsigned long nr_pages) +{ + struct page *page; + unsigned long i; + + if (!nr_pages) + return; + + page = pfn_to_page(pfn); + + /* Free a large naturally-aligned chunk if possible */ + if (nr_pages == pageblock_nr_pages && pageblock_aligned(pfn)) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_core(page, pageblock_order); + return; + } + + for (i = 0; i < nr_pages; i++, page++, pfn++) { + if (pageblock_aligned(pfn)) + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + __free_pages_core(page, 0); + } +} + +/* Completion tracking for deferred_init_memmap() threads */ +static atomic_t pgdat_init_n_undone __initdata; +static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); + +static inline void __init pgdat_init_report_one_done(void) +{ + if (atomic_dec_and_test(&pgdat_init_n_undone)) + complete(&pgdat_init_all_done_comp); +} + +/* + * Returns true if page needs to be initialized or freed to buddy allocator. + * + * We check if a current large page is valid by only checking the validity + * of the head pfn. + */ +static inline bool __init deferred_pfn_valid(unsigned long pfn) +{ + if (pageblock_aligned(pfn) && !pfn_valid(pfn)) + return false; + return true; +} + +/* + * Free pages to buddy allocator. Try to free aligned pages in + * pageblock_nr_pages sizes. + */ +static void __init deferred_free_pages(unsigned long pfn, + unsigned long end_pfn) +{ + unsigned long nr_free = 0; + + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(pfn)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 0; + } else if (pageblock_aligned(pfn)) { + deferred_free_range(pfn - nr_free, nr_free); + nr_free = 1; + } else { + nr_free++; + } + } + /* Free the last block of pages to allocator */ + deferred_free_range(pfn - nr_free, nr_free); +} + +/* + * Initialize struct pages. We minimize pfn page lookups and scheduler checks + * by performing it only once every pageblock_nr_pages. + * Return number of pages initialized. + */ +static unsigned long __init deferred_init_pages(struct zone *zone, + unsigned long pfn, + unsigned long end_pfn) +{ + int nid = zone_to_nid(zone); + unsigned long nr_pages = 0; + int zid = zone_idx(zone); + struct page *page = NULL; + + for (; pfn < end_pfn; pfn++) { + if (!deferred_pfn_valid(pfn)) { + page = NULL; + continue; + } else if (!page || pageblock_aligned(pfn)) { + page = pfn_to_page(pfn); + } else { + page++; + } + __init_single_page(page, pfn, zid, nid); + nr_pages++; + } + return (nr_pages); +} + +/* + * This function is meant to pre-load the iterator for the zone init. + * Specifically it walks through the ranges until we are caught up to the + * first_init_pfn value and exits there. If we never encounter the value we + * return false indicating there are no valid ranges left. + */ +static bool __init +deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone, + unsigned long *spfn, unsigned long *epfn, + unsigned long first_init_pfn) +{ + u64 j; + + /* + * Start out by walking through the ranges in this zone that have + * already been initialized. We don't need to do anything with them + * so we just need to flush them out of the system. + */ + for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) { + if (*epfn <= first_init_pfn) + continue; + if (*spfn < first_init_pfn) + *spfn = first_init_pfn; + *i = j; + return true; + } + + return false; +} + +/* + * Initialize and free pages. We do it in two loops: first we initialize + * struct page, then free to buddy allocator, because while we are + * freeing pages we can access pages that are ahead (computing buddy + * page in __free_one_page()). + * + * In order to try and keep some memory in the cache we have the loop + * broken along max page order boundaries. This way we will not cause + * any issues with the buddy page computation. + */ +static unsigned long __init +deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, + unsigned long *end_pfn) +{ + unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES); + unsigned long spfn = *start_pfn, epfn = *end_pfn; + unsigned long nr_pages = 0; + u64 j = *i; + + /* First we loop through and initialize the page values */ + for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) { + unsigned long t; + + if (mo_pfn <= *start_pfn) + break; + + t = min(mo_pfn, *end_pfn); + nr_pages += deferred_init_pages(zone, *start_pfn, t); + + if (mo_pfn < *end_pfn) { + *start_pfn = mo_pfn; + break; + } + } + + /* Reset values and now loop through freeing pages as needed */ + swap(j, *i); + + for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) { + unsigned long t; + + if (mo_pfn <= spfn) + break; + + t = min(mo_pfn, epfn); + deferred_free_pages(spfn, t); + + if (mo_pfn <= epfn) + break; + } + + return nr_pages; +} + +static void __init +deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, + void *arg) +{ + unsigned long spfn, epfn; + struct zone *zone = arg; + u64 i; + + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn); + + /* + * Initialize and free pages in MAX_ORDER sized increments so that we + * can avoid introducing any issues with the buddy allocator. + */ + while (spfn < end_pfn) { + deferred_init_maxorder(&i, zone, &spfn, &epfn); + cond_resched(); + } +} + +/* An arch may override for more concurrency. */ +__weak int __init +deferred_page_init_max_threads(const struct cpumask *node_cpumask) +{ + return 1; +} + +/* Initialise remaining memory on a node */ +static int __init deferred_init_memmap(void *data) +{ + pg_data_t *pgdat = data; + const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); + unsigned long spfn = 0, epfn = 0; + unsigned long first_init_pfn, flags; + unsigned long start = jiffies; + struct zone *zone; + int zid, max_threads; + u64 i; + + /* Bind memory initialisation thread to a local node if possible */ + if (!cpumask_empty(cpumask)) + set_cpus_allowed_ptr(current, cpumask); + + pgdat_resize_lock(pgdat, &flags); + first_init_pfn = pgdat->first_deferred_pfn; + if (first_init_pfn == ULONG_MAX) { + pgdat_resize_unlock(pgdat, &flags); + pgdat_init_report_one_done(); + return 0; + } + + /* Sanity check boundaries */ + BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); + BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); + pgdat->first_deferred_pfn = ULONG_MAX; + + /* + * Once we unlock here, the zone cannot be grown anymore, thus if an + * interrupt thread must allocate this early in boot, zone must be + * pre-grown prior to start of deferred page initialization. + */ + pgdat_resize_unlock(pgdat, &flags); + + /* Only the highest zone is deferred so find it */ + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + zone = pgdat->node_zones + zid; + if (first_init_pfn < zone_end_pfn(zone)) + break; + } + + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_init_pfn)) + goto zone_empty; + + max_threads = deferred_page_init_max_threads(cpumask); + + while (spfn < epfn) { + unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); + struct padata_mt_job job = { + .thread_fn = deferred_init_memmap_chunk, + .fn_arg = zone, + .start = spfn, + .size = epfn_align - spfn, + .align = PAGES_PER_SECTION, + .min_chunk = PAGES_PER_SECTION, + .max_threads = max_threads, + }; + + padata_do_multithreaded(&job); + deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + epfn_align); + } +zone_empty: + /* Sanity check that the next zone really is unpopulated */ + WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); + + pr_info("node %d deferred pages initialised in %ums\n", + pgdat->node_id, jiffies_to_msecs(jiffies - start)); + + pgdat_init_report_one_done(); + return 0; +} + +/* + * If this zone has deferred pages, try to grow it by initializing enough + * deferred pages to satisfy the allocation specified by order, rounded up to + * the nearest PAGES_PER_SECTION boundary. So we're adding memory in increments + * of SECTION_SIZE bytes by initializing struct pages in increments of + * PAGES_PER_SECTION * sizeof(struct page) bytes. + * + * Return true when zone was grown, otherwise return false. We return true even + * when we grow less than requested, to let the caller decide if there are + * enough pages to satisfy the allocation. + * + * Note: We use noinline because this function is needed only during boot, and + * it is called from a __ref function _deferred_grow_zone. This way we are + * making sure that it is not inlined into permanent text section. + */ +bool __init deferred_grow_zone(struct zone *zone, unsigned int order) +{ + unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION); + pg_data_t *pgdat = zone->zone_pgdat; + unsigned long first_deferred_pfn = pgdat->first_deferred_pfn; + unsigned long spfn, epfn, flags; + unsigned long nr_pages = 0; + u64 i; + + /* Only the last zone may have deferred pages */ + if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat)) + return false; + + pgdat_resize_lock(pgdat, &flags); + + /* + * If someone grew this zone while we were waiting for spinlock, return + * true, as there might be enough pages already. + */ + if (first_deferred_pfn != pgdat->first_deferred_pfn) { + pgdat_resize_unlock(pgdat, &flags); + return true; + } + + /* If the zone is empty somebody else may have cleared out the zone */ + if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, + first_deferred_pfn)) { + pgdat->first_deferred_pfn = ULONG_MAX; + pgdat_resize_unlock(pgdat, &flags); + /* Retry only once. */ + return first_deferred_pfn != ULONG_MAX; + } + + /* + * Initialize and free pages in MAX_ORDER sized increments so + * that we can avoid introducing any issues with the buddy + * allocator. + */ + while (spfn < epfn) { + /* update our first deferred PFN for this section */ + first_deferred_pfn = spfn; + + nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); + touch_nmi_watchdog(); + + /* We should only stop along section boundaries */ + if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION) + continue; + + /* If our quota has been met we can stop here */ + if (nr_pages >= nr_pages_needed) + break; + } + + pgdat->first_deferred_pfn = spfn; + pgdat_resize_unlock(pgdat, &flags); + + return nr_pages > 0; +} + +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ + +#ifdef CONFIG_CMA +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_pageblock_migratetype(page, MIGRATE_CMA); + set_page_refcounted(page); + __free_pages(page, pageblock_order); + + adjust_managed_page_count(page, pageblock_nr_pages); + page_zone(page)->cma_pages += pageblock_nr_pages; +} +#endif + +void __init page_alloc_init_late(void) +{ + struct zone *zone; + int nid; + +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT + + /* There will be num_node_state(N_MEMORY) threads */ + atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); + for_each_node_state(nid, N_MEMORY) { + kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); + } + + /* Block until all are initialised */ + wait_for_completion(&pgdat_init_all_done_comp); + + /* + * We initialized the rest of the deferred pages. Permanently disable + * on-demand struct page initialization. + */ + static_branch_disable(&deferred_pages); + + /* Reinit limits that are based on free pages after the kernel is up */ + files_maxfiles_init(); +#endif + + buffer_init(); + + /* Discard memblock private memory */ + memblock_discard(); + + for_each_node_state(nid, N_MEMORY) + shuffle_free_memory(NODE_DATA(nid)); + + for_each_populated_zone(zone) + set_zone_contiguous(zone); +} + +#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES +/* + * Returns the number of pages that arch has reserved but + * is not known to alloc_large_system_hash(). + */ +static unsigned long __init arch_reserved_kernel_pages(void) +{ + return 0; +} +#endif + +/* + * Adaptive scale is meant to reduce sizes of hash tables on large memory + * machines. As memory size is increased the scale is also increased but at + * slower pace. Starting from ADAPT_SCALE_BASE (64G), every time memory + * quadruples the scale is increased by one, which means the size of hash table + * only doubles, instead of quadrupling as well. + * Because 32-bit systems cannot have large physical memory, where this scaling + * makes sense, it is disabled on such platforms. + */ +#if __BITS_PER_LONG > 32 +#define ADAPT_SCALE_BASE (64ul << 30) +#define ADAPT_SCALE_SHIFT 2 +#define ADAPT_SCALE_NPAGES (ADAPT_SCALE_BASE >> PAGE_SHIFT) +#endif + +/* + * allocate a large system hash table from bootmem + * - it is assumed that the hash table must contain an exact power-of-2 + * quantity of entries + * - limit is the number of hash buckets, not the total allocation size + */ +void *__init alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit) +{ + unsigned long long max = high_limit; + unsigned long log2qty, size; + void *table; + gfp_t gfp_flags; + bool virt; + bool huge; + + /* allow the kernel cmdline to have a say */ + if (!numentries) { + /* round applicable memory size up to nearest megabyte */ + numentries = nr_kernel_pages; + numentries -= arch_reserved_kernel_pages(); + + /* It isn't necessary when PAGE_SIZE >= 1MB */ + if (PAGE_SIZE < SZ_1M) + numentries = round_up(numentries, SZ_1M / PAGE_SIZE); + +#if __BITS_PER_LONG > 32 + if (!high_limit) { + unsigned long adapt; + + for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries; + adapt <<= ADAPT_SCALE_SHIFT) + scale++; + } +#endif + + /* limit to 1 bucket per 2^scale bytes of low memory */ + if (scale > PAGE_SHIFT) + numentries >>= (scale - PAGE_SHIFT); + else + numentries <<= (PAGE_SHIFT - scale); + + /* Make sure we've got at least a 0-order allocation.. */ + if (unlikely(flags & HASH_SMALL)) { + /* Makes no sense without HASH_EARLY */ + WARN_ON(!(flags & HASH_EARLY)); + if (!(numentries >> *_hash_shift)) { + numentries = 1UL << *_hash_shift; + BUG_ON(!numentries); + } + } else if (unlikely((numentries * bucketsize) < PAGE_SIZE)) + numentries = PAGE_SIZE / bucketsize; + } + numentries = roundup_pow_of_two(numentries); + + /* limit allocation size to 1/16 total memory by default */ + if (max == 0) { + max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; + do_div(max, bucketsize); + } + max = min(max, 0x80000000ULL); + + if (numentries < low_limit) + numentries = low_limit; + if (numentries > max) + numentries = max; + + log2qty = ilog2(numentries); + + gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC; + do { + virt = false; + size = bucketsize << log2qty; + if (flags & HASH_EARLY) { + if (flags & HASH_ZERO) + table = memblock_alloc(size, SMP_CACHE_BYTES); + else + table = memblock_alloc_raw(size, + SMP_CACHE_BYTES); + } else if (get_order(size) > MAX_ORDER || hashdist) { + table = vmalloc_huge(size, gfp_flags); + virt = true; + if (table) + huge = is_vm_area_hugepages(table); + } else { + /* + * If bucketsize is not a power-of-two, we may free + * some pages at the end of hash table which + * alloc_pages_exact() automatically does + */ + table = alloc_pages_exact(size, gfp_flags); + kmemleak_alloc(table, size, 1, gfp_flags); + } + } while (!table && size > PAGE_SIZE && --log2qty); + + if (!table) + panic("Failed to allocate %s hash table\n", tablename); + + pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", + tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, + virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear"); + + if (_hash_shift) + *_hash_shift = log2qty; + if (_hash_mask) + *_hash_mask = (1 << log2qty) - 1; + + return table; +} + +/** + * set_dma_reserve - set the specified number of pages reserved in the first zone + * @new_dma_reserve: The number of pages to mark reserved + * + * The per-cpu batchsize and zone watermarks are determined by managed_pages. + * In the DMA zone, a significant percentage may be consumed by kernel image + * and other unfreeable allocations which can skew the watermarks badly. This + * function may optionally be used to account for unfreeable pages in the + * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and + * smaller per-cpu batchsize. + */ +void __init set_dma_reserve(unsigned long new_dma_reserve) +{ + dma_reserve = new_dma_reserve; +} + +void __init memblock_free_pages(struct page *page, unsigned long pfn, + unsigned int order) +{ + if (!early_page_initialised(pfn)) + return; + if (!kmsan_memblock_free_pages(page, order)) { + /* KMSAN will take care of these pages. */ + return; + } + __free_pages_core(page, order); +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 33925488040f..8adc70b6034d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -72,9 +72,7 @@ #include #include #include -#include #include -#include #include #include #include @@ -355,7 +353,7 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = { [ZONE_MOVABLE] = 0, }; -static char * const zone_names[MAX_NR_ZONES] = { +char * const zone_names[MAX_NR_ZONES] = { #ifdef CONFIG_ZONE_DMA "DMA", #endif @@ -401,17 +399,6 @@ int user_min_free_kbytes = -1; int watermark_boost_factor __read_mostly = 15000; int watermark_scale_factor = 10; -static unsigned long nr_kernel_pages __initdata; -static unsigned long nr_all_pages __initdata; -static unsigned long dma_reserve __initdata; - -static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata; -static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata; -static unsigned long required_kernelcore __initdata; -static unsigned long required_kernelcore_percent __initdata; -static unsigned long required_movablecore __initdata; -static unsigned long required_movablecore_percent __initdata; -static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata; bool mirrored_kernelcore __initdata_memblock; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ @@ -427,86 +414,36 @@ EXPORT_SYMBOL(nr_online_nodes); int page_group_by_mobility_disabled __read_mostly; -bool deferred_struct_pages __meminitdata; - #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * During boot we initialize deferred pages on-demand, as needed, but once * page_alloc_init_late() has finished, the deferred pages are all initialized, * and we can permanently disable that path. */ -static DEFINE_STATIC_KEY_TRUE(deferred_pages); +DEFINE_STATIC_KEY_TRUE(deferred_pages); static inline bool deferred_pages_enabled(void) { return static_branch_unlikely(&deferred_pages); } -/* Returns true if the struct page for the pfn is initialised */ -static inline bool __meminit early_page_initialised(unsigned long pfn) -{ - int nid = early_pfn_to_nid(pfn); - - if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn) - return false; - - return true; -} - /* - * Returns true when the remaining initialisation should be deferred until - * later in the boot cycle when it can be parallelised. + * deferred_grow_zone() is __init, but it is called from + * get_page_from_freelist() during early boot until deferred_pages permanently + * disables this call. This is why we have refdata wrapper to avoid warning, + * and to ensure that the function body gets unloaded. */ -static bool __meminit -defer_init(int nid, unsigned long pfn, unsigned long end_pfn) +static bool __ref +_deferred_grow_zone(struct zone *zone, unsigned int order) { - static unsigned long prev_end_pfn, nr_initialised; - - if (early_page_ext_enabled()) - return false; - /* - * prev_end_pfn static that contains the end of previous zone - * No need to protect because called very early in boot before smp_init. - */ - if (prev_end_pfn != end_pfn) { - prev_end_pfn = end_pfn; - nr_initialised = 0; - } - - /* Always populate low zones for address-constrained allocations */ - if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) - return false; - - if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX) - return true; - /* - * We start only with one section of pages, more pages are added as - * needed until the rest of deferred pages are initialized. - */ - nr_initialised++; - if ((nr_initialised > PAGES_PER_SECTION) && - (pfn & (PAGES_PER_SECTION - 1)) == 0) { - NODE_DATA(nid)->first_deferred_pfn = pfn; - return true; - } - return false; + return deferred_grow_zone(zone, order); } #else static inline bool deferred_pages_enabled(void) { return false; } - -static inline bool early_page_initialised(unsigned long pfn) -{ - return true; -} - -static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) -{ - return false; -} -#endif +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /* Return a pointer to the bitmap storing bits affecting a block of pages */ static inline unsigned long *get_pageblock_bitmap(const struct page *page, @@ -772,26 +709,6 @@ void free_compound_page(struct page *page) free_the_page(page, compound_order(page)); } -static void prep_compound_head(struct page *page, unsigned int order) -{ - struct folio *folio = (struct folio *)page; - - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); - set_compound_order(page, order); - atomic_set(&folio->_entire_mapcount, -1); - atomic_set(&folio->_nr_pages_mapped, 0); - atomic_set(&folio->_pincount, 0); -} - -static void prep_compound_tail(struct page *head, int tail_idx) -{ - struct page *p = head + tail_idx; - - p->mapping = TAIL_MAPPING; - set_compound_head(p, head); - set_page_private(p, 0); -} - void prep_compound_page(struct page *page, unsigned int order) { int i; @@ -1608,80 +1525,6 @@ static void free_one_page(struct zone *zone, spin_unlock_irqrestore(&zone->lock, flags); } -static void __meminit __init_single_page(struct page *page, unsigned long pfn, - unsigned long zone, int nid) -{ - mm_zero_struct_page(page); - set_page_links(page, zone, nid, pfn); - init_page_count(page); - page_mapcount_reset(page); - page_cpupid_reset_last(page); - page_kasan_tag_reset(page); - - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (!is_highmem_idx(zone)) - set_page_address(page, __va(pfn << PAGE_SHIFT)); -#endif -} - -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void __meminit init_reserved_page(unsigned long pfn) -{ - pg_data_t *pgdat; - int nid, zid; - - if (early_page_initialised(pfn)) - return; - - nid = early_pfn_to_nid(pfn); - pgdat = NODE_DATA(nid); - - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - struct zone *zone = &pgdat->node_zones[zid]; - - if (zone_spans_pfn(zone, pfn)) - break; - } - __init_single_page(pfn_to_page(pfn), pfn, zid, nid); -} -#else -static inline void init_reserved_page(unsigned long pfn) -{ -} -#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ - -/* - * Initialised pages do not have PageReserved set. This function is - * called for each range allocated by the bootmem allocator and - * marks the pages PageReserved. The remaining valid pages are later - * sent to the buddy page allocator. - */ -void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) -{ - unsigned long start_pfn = PFN_DOWN(start); - unsigned long end_pfn = PFN_UP(end); - - for (; start_pfn < end_pfn; start_pfn++) { - if (pfn_valid(start_pfn)) { - struct page *page = pfn_to_page(start_pfn); - - init_reserved_page(start_pfn); - - /* Avoid false-positive PageTail() */ - INIT_LIST_HEAD(&page->lru); - - /* - * no need for atomic set_bit because the struct - * page is not visible yet so nobody should - * access it yet. - */ - __SetPageReserved(page); - } - } -} - static void __free_pages_ok(struct page *page, unsigned int order, fpi_t fpi_flags) { @@ -1740,70 +1583,6 @@ void __free_pages_core(struct page *page, unsigned int order) __free_pages_ok(page, order, FPI_TO_TAIL); } -#ifdef CONFIG_NUMA - -/* - * During memory init memblocks map pfns to nids. The search is expensive and - * this caches recent lookups. The implementation of __early_pfn_to_nid - * treats start/end as pfns. - */ -struct mminit_pfnnid_cache { - unsigned long last_start; - unsigned long last_end; - int last_nid; -}; - -static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata; - -/* - * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. - */ -static int __meminit __early_pfn_to_nid(unsigned long pfn, - struct mminit_pfnnid_cache *state) -{ - unsigned long start_pfn, end_pfn; - int nid; - - if (state->last_start <= pfn && pfn < state->last_end) - return state->last_nid; - - nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != NUMA_NO_NODE) { - state->last_start = start_pfn; - state->last_end = end_pfn; - state->last_nid = nid; - } - - return nid; -} - -int __meminit early_pfn_to_nid(unsigned long pfn) -{ - static DEFINE_SPINLOCK(early_pfn_lock); - int nid; - - spin_lock(&early_pfn_lock); - nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache); - if (nid < 0) - nid = first_online_node; - spin_unlock(&early_pfn_lock); - - return nid; -} -#endif /* CONFIG_NUMA */ - -void __init memblock_free_pages(struct page *page, unsigned long pfn, - unsigned int order) -{ - if (!early_page_initialised(pfn)) - return; - if (!kmsan_memblock_free_pages(page, order)) { - /* KMSAN will take care of these pages. */ - return; - } - __free_pages_core(page, order); -} - /* * Check that the whole (or subset of) a pageblock given by the interval of * [start_pfn, end_pfn) is valid and within the same zone, before scanning it @@ -1874,570 +1653,131 @@ void clear_zone_contiguous(struct zone *zone) zone->contiguous = false; } -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void __init deferred_free_range(unsigned long pfn, - unsigned long nr_pages) -{ - struct page *page; - unsigned long i; - - if (!nr_pages) - return; - - page = pfn_to_page(pfn); - - /* Free a large naturally-aligned chunk if possible */ - if (nr_pages == pageblock_nr_pages && pageblock_aligned(pfn)) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_core(page, pageblock_order); - return; - } - - for (i = 0; i < nr_pages; i++, page++, pfn++) { - if (pageblock_aligned(pfn)) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_core(page, 0); - } -} - -/* Completion tracking for deferred_init_memmap() threads */ -static atomic_t pgdat_init_n_undone __initdata; -static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp); - -static inline void __init pgdat_init_report_one_done(void) -{ - if (atomic_dec_and_test(&pgdat_init_n_undone)) - complete(&pgdat_init_all_done_comp); -} - /* - * Returns true if page needs to be initialized or freed to buddy allocator. + * The order of subdivision here is critical for the IO subsystem. + * Please do not alter this order without good reasons and regression + * testing. Specifically, as large blocks of memory are subdivided, + * the order in which smaller blocks are delivered depends on the order + * they're subdivided in this function. This is the primary factor + * influencing the order in which pages are delivered to the IO + * subsystem according to empirical testing, and this is also justified + * by considering the behavior of a buddy system containing a single + * large block of memory acted on by a series of small allocations. + * This behavior is a critical factor in sglist merging's success. * - * We check if a current large page is valid by only checking the validity - * of the head pfn. + * -- nyc */ -static inline bool __init deferred_pfn_valid(unsigned long pfn) +static inline void expand(struct zone *zone, struct page *page, + int low, int high, int migratetype) { - if (pageblock_aligned(pfn) && !pfn_valid(pfn)) - return false; - return true; -} - -/* - * Free pages to buddy allocator. Try to free aligned pages in - * pageblock_nr_pages sizes. - */ -static void __init deferred_free_pages(unsigned long pfn, - unsigned long end_pfn) -{ - unsigned long nr_free = 0; - - for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(pfn)) { - deferred_free_range(pfn - nr_free, nr_free); - nr_free = 0; - } else if (pageblock_aligned(pfn)) { - deferred_free_range(pfn - nr_free, nr_free); - nr_free = 1; - } else { - nr_free++; - } - } - /* Free the last block of pages to allocator */ - deferred_free_range(pfn - nr_free, nr_free); -} + unsigned long size = 1 << high; -/* - * Initialize struct pages. We minimize pfn page lookups and scheduler checks - * by performing it only once every pageblock_nr_pages. - * Return number of pages initialized. - */ -static unsigned long __init deferred_init_pages(struct zone *zone, - unsigned long pfn, - unsigned long end_pfn) -{ - int nid = zone_to_nid(zone); - unsigned long nr_pages = 0; - int zid = zone_idx(zone); - struct page *page = NULL; + while (high > low) { + high--; + size >>= 1; + VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); - for (; pfn < end_pfn; pfn++) { - if (!deferred_pfn_valid(pfn)) { - page = NULL; + /* + * Mark as guard pages (or page), that will allow to + * merge back to allocator when buddy will be freed. + * Corresponding page table entries will not be touched, + * pages will stay not present in virtual address space + */ + if (set_page_guard(zone, &page[size], high, migratetype)) continue; - } else if (!page || pageblock_aligned(pfn)) { - page = pfn_to_page(pfn); - } else { - page++; - } - __init_single_page(page, pfn, zid, nid); - nr_pages++; + + add_to_free_list(&page[size], zone, high, migratetype); + set_buddy_order(&page[size], high); } - return (nr_pages); } -/* - * This function is meant to pre-load the iterator for the zone init. - * Specifically it walks through the ranges until we are caught up to the - * first_init_pfn value and exits there. If we never encounter the value we - * return false indicating there are no valid ranges left. - */ -static bool __init -deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone, - unsigned long *spfn, unsigned long *epfn, - unsigned long first_init_pfn) +static void check_new_page_bad(struct page *page) { - u64 j; - - /* - * Start out by walking through the ranges in this zone that have - * already been initialized. We don't need to do anything with them - * so we just need to flush them out of the system. - */ - for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) { - if (*epfn <= first_init_pfn) - continue; - if (*spfn < first_init_pfn) - *spfn = first_init_pfn; - *i = j; - return true; + if (unlikely(page->flags & __PG_HWPOISON)) { + /* Don't complain about hwpoisoned pages */ + page_mapcount_reset(page); /* remove PageBuddy */ + return; } - return false; + bad_page(page, + page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP)); } /* - * Initialize and free pages. We do it in two loops: first we initialize - * struct page, then free to buddy allocator, because while we are - * freeing pages we can access pages that are ahead (computing buddy - * page in __free_one_page()). - * - * In order to try and keep some memory in the cache we have the loop - * broken along max page order boundaries. This way we will not cause - * any issues with the buddy page computation. + * This page is about to be returned from the page allocator */ -static unsigned long __init -deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn, - unsigned long *end_pfn) +static int check_new_page(struct page *page) { - unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES); - unsigned long spfn = *start_pfn, epfn = *end_pfn; - unsigned long nr_pages = 0; - u64 j = *i; - - /* First we loop through and initialize the page values */ - for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) { - unsigned long t; + if (likely(page_expected_state(page, + PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) + return 0; - if (mo_pfn <= *start_pfn) - break; + check_new_page_bad(page); + return 1; +} - t = min(mo_pfn, *end_pfn); - nr_pages += deferred_init_pages(zone, *start_pfn, t); +static inline bool check_new_pages(struct page *page, unsigned int order) +{ + if (is_check_pages_enabled()) { + for (int i = 0; i < (1 << order); i++) { + struct page *p = page + i; - if (mo_pfn < *end_pfn) { - *start_pfn = mo_pfn; - break; + if (unlikely(check_new_page(p))) + return true; } } - /* Reset values and now loop through freeing pages as needed */ - swap(j, *i); - - for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) { - unsigned long t; - - if (mo_pfn <= spfn) - break; - - t = min(mo_pfn, epfn); - deferred_free_pages(spfn, t); - - if (mo_pfn <= epfn) - break; - } - - return nr_pages; + return false; } -static void __init -deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn, - void *arg) +static inline bool should_skip_kasan_unpoison(gfp_t flags) { - unsigned long spfn, epfn; - struct zone *zone = arg; - u64 i; + /* Don't skip if a software KASAN mode is enabled. */ + if (IS_ENABLED(CONFIG_KASAN_GENERIC) || + IS_ENABLED(CONFIG_KASAN_SW_TAGS)) + return false; - deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn); + /* Skip, if hardware tag-based KASAN is not enabled. */ + if (!kasan_hw_tags_enabled()) + return true; /* - * Initialize and free pages in MAX_ORDER sized increments so that we - * can avoid introducing any issues with the buddy allocator. + * With hardware tag-based KASAN enabled, skip if this has been + * requested via __GFP_SKIP_KASAN. */ - while (spfn < end_pfn) { - deferred_init_maxorder(&i, zone, &spfn, &epfn); - cond_resched(); - } + return flags & __GFP_SKIP_KASAN; } -/* An arch may override for more concurrency. */ -__weak int __init -deferred_page_init_max_threads(const struct cpumask *node_cpumask) +static inline bool should_skip_init(gfp_t flags) { - return 1; + /* Don't skip, if hardware tag-based KASAN is not enabled. */ + if (!kasan_hw_tags_enabled()) + return false; + + /* For hardware tag-based KASAN, skip if requested. */ + return (flags & __GFP_SKIP_ZERO); } -/* Initialise remaining memory on a node */ -static int __init deferred_init_memmap(void *data) +inline void post_alloc_hook(struct page *page, unsigned int order, + gfp_t gfp_flags) { - pg_data_t *pgdat = data; - const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); - unsigned long spfn = 0, epfn = 0; - unsigned long first_init_pfn, flags; - unsigned long start = jiffies; - struct zone *zone; - int zid, max_threads; - u64 i; - - /* Bind memory initialisation thread to a local node if possible */ - if (!cpumask_empty(cpumask)) - set_cpus_allowed_ptr(current, cpumask); - - pgdat_resize_lock(pgdat, &flags); - first_init_pfn = pgdat->first_deferred_pfn; - if (first_init_pfn == ULONG_MAX) { - pgdat_resize_unlock(pgdat, &flags); - pgdat_init_report_one_done(); - return 0; - } + bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && + !should_skip_init(gfp_flags); + bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); + int i; + + set_page_private(page, 0); + set_page_refcounted(page); - /* Sanity check boundaries */ - BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn); - BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat)); - pgdat->first_deferred_pfn = ULONG_MAX; + arch_alloc_page(page, order); + debug_pagealloc_map_pages(page, 1 << order); /* - * Once we unlock here, the zone cannot be grown anymore, thus if an - * interrupt thread must allocate this early in boot, zone must be - * pre-grown prior to start of deferred page initialization. + * Page unpoisoning must happen before memory initialization. + * Otherwise, the poison pattern will be overwritten for __GFP_ZERO + * allocations and the page unpoisoning code will complain. */ - pgdat_resize_unlock(pgdat, &flags); - - /* Only the highest zone is deferred so find it */ - for (zid = 0; zid < MAX_NR_ZONES; zid++) { - zone = pgdat->node_zones + zid; - if (first_init_pfn < zone_end_pfn(zone)) - break; - } - - /* If the zone is empty somebody else may have cleared out the zone */ - if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, - first_init_pfn)) - goto zone_empty; - - max_threads = deferred_page_init_max_threads(cpumask); - - while (spfn < epfn) { - unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION); - struct padata_mt_job job = { - .thread_fn = deferred_init_memmap_chunk, - .fn_arg = zone, - .start = spfn, - .size = epfn_align - spfn, - .align = PAGES_PER_SECTION, - .min_chunk = PAGES_PER_SECTION, - .max_threads = max_threads, - }; - - padata_do_multithreaded(&job); - deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, - epfn_align); - } -zone_empty: - /* Sanity check that the next zone really is unpopulated */ - WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone)); - - pr_info("node %d deferred pages initialised in %ums\n", - pgdat->node_id, jiffies_to_msecs(jiffies - start)); - - pgdat_init_report_one_done(); - return 0; -} - -/* - * If this zone has deferred pages, try to grow it by initializing enough - * deferred pages to satisfy the allocation specified by order, rounded up to - * the nearest PAGES_PER_SECTION boundary. So we're adding memory in increments - * of SECTION_SIZE bytes by initializing struct pages in increments of - * PAGES_PER_SECTION * sizeof(struct page) bytes. - * - * Return true when zone was grown, otherwise return false. We return true even - * when we grow less than requested, to let the caller decide if there are - * enough pages to satisfy the allocation. - * - * Note: We use noinline because this function is needed only during boot, and - * it is called from a __ref function _deferred_grow_zone. This way we are - * making sure that it is not inlined into permanent text section. - */ -static noinline bool __init -deferred_grow_zone(struct zone *zone, unsigned int order) -{ - unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION); - pg_data_t *pgdat = zone->zone_pgdat; - unsigned long first_deferred_pfn = pgdat->first_deferred_pfn; - unsigned long spfn, epfn, flags; - unsigned long nr_pages = 0; - u64 i; - - /* Only the last zone may have deferred pages */ - if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat)) - return false; - - pgdat_resize_lock(pgdat, &flags); - - /* - * If someone grew this zone while we were waiting for spinlock, return - * true, as there might be enough pages already. - */ - if (first_deferred_pfn != pgdat->first_deferred_pfn) { - pgdat_resize_unlock(pgdat, &flags); - return true; - } - - /* If the zone is empty somebody else may have cleared out the zone */ - if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, - first_deferred_pfn)) { - pgdat->first_deferred_pfn = ULONG_MAX; - pgdat_resize_unlock(pgdat, &flags); - /* Retry only once. */ - return first_deferred_pfn != ULONG_MAX; - } - - /* - * Initialize and free pages in MAX_ORDER sized increments so - * that we can avoid introducing any issues with the buddy - * allocator. - */ - while (spfn < epfn) { - /* update our first deferred PFN for this section */ - first_deferred_pfn = spfn; - - nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn); - touch_nmi_watchdog(); - - /* We should only stop along section boundaries */ - if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION) - continue; - - /* If our quota has been met we can stop here */ - if (nr_pages >= nr_pages_needed) - break; - } - - pgdat->first_deferred_pfn = spfn; - pgdat_resize_unlock(pgdat, &flags); - - return nr_pages > 0; -} - -/* - * deferred_grow_zone() is __init, but it is called from - * get_page_from_freelist() during early boot until deferred_pages permanently - * disables this call. This is why we have refdata wrapper to avoid warning, - * and to ensure that the function body gets unloaded. - */ -static bool __ref -_deferred_grow_zone(struct zone *zone, unsigned int order) -{ - return deferred_grow_zone(zone, order); -} - -#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ - -void __init page_alloc_init_late(void) -{ - struct zone *zone; - int nid; - -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT - - /* There will be num_node_state(N_MEMORY) threads */ - atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); - for_each_node_state(nid, N_MEMORY) { - kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); - } - - /* Block until all are initialised */ - wait_for_completion(&pgdat_init_all_done_comp); - - /* - * We initialized the rest of the deferred pages. Permanently disable - * on-demand struct page initialization. - */ - static_branch_disable(&deferred_pages); - - /* Reinit limits that are based on free pages after the kernel is up */ - files_maxfiles_init(); -#endif - - buffer_init(); - - /* Discard memblock private memory */ - memblock_discard(); - - for_each_node_state(nid, N_MEMORY) - shuffle_free_memory(NODE_DATA(nid)); - - for_each_populated_zone(zone) - set_zone_contiguous(zone); -} - -#ifdef CONFIG_CMA -/* Free whole pageblock and set its migration type to MIGRATE_CMA. */ -void __init init_cma_reserved_pageblock(struct page *page) -{ - unsigned i = pageblock_nr_pages; - struct page *p = page; - - do { - __ClearPageReserved(p); - set_page_count(p, 0); - } while (++p, --i); - - set_pageblock_migratetype(page, MIGRATE_CMA); - set_page_refcounted(page); - __free_pages(page, pageblock_order); - - adjust_managed_page_count(page, pageblock_nr_pages); - page_zone(page)->cma_pages += pageblock_nr_pages; -} -#endif - -/* - * The order of subdivision here is critical for the IO subsystem. - * Please do not alter this order without good reasons and regression - * testing. Specifically, as large blocks of memory are subdivided, - * the order in which smaller blocks are delivered depends on the order - * they're subdivided in this function. This is the primary factor - * influencing the order in which pages are delivered to the IO - * subsystem according to empirical testing, and this is also justified - * by considering the behavior of a buddy system containing a single - * large block of memory acted on by a series of small allocations. - * This behavior is a critical factor in sglist merging's success. - * - * -- nyc - */ -static inline void expand(struct zone *zone, struct page *page, - int low, int high, int migratetype) -{ - unsigned long size = 1 << high; - - while (high > low) { - high--; - size >>= 1; - VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]); - - /* - * Mark as guard pages (or page), that will allow to - * merge back to allocator when buddy will be freed. - * Corresponding page table entries will not be touched, - * pages will stay not present in virtual address space - */ - if (set_page_guard(zone, &page[size], high, migratetype)) - continue; - - add_to_free_list(&page[size], zone, high, migratetype); - set_buddy_order(&page[size], high); - } -} - -static void check_new_page_bad(struct page *page) -{ - if (unlikely(page->flags & __PG_HWPOISON)) { - /* Don't complain about hwpoisoned pages */ - page_mapcount_reset(page); /* remove PageBuddy */ - return; - } - - bad_page(page, - page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP)); -} - -/* - * This page is about to be returned from the page allocator - */ -static int check_new_page(struct page *page) -{ - if (likely(page_expected_state(page, - PAGE_FLAGS_CHECK_AT_PREP|__PG_HWPOISON))) - return 0; - - check_new_page_bad(page); - return 1; -} - -static inline bool check_new_pages(struct page *page, unsigned int order) -{ - if (is_check_pages_enabled()) { - for (int i = 0; i < (1 << order); i++) { - struct page *p = page + i; - - if (unlikely(check_new_page(p))) - return true; - } - } - - return false; -} - -static inline bool should_skip_kasan_unpoison(gfp_t flags) -{ - /* Don't skip if a software KASAN mode is enabled. */ - if (IS_ENABLED(CONFIG_KASAN_GENERIC) || - IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - return false; - - /* Skip, if hardware tag-based KASAN is not enabled. */ - if (!kasan_hw_tags_enabled()) - return true; - - /* - * With hardware tag-based KASAN enabled, skip if this has been - * requested via __GFP_SKIP_KASAN. - */ - return flags & __GFP_SKIP_KASAN; -} - -static inline bool should_skip_init(gfp_t flags) -{ - /* Don't skip, if hardware tag-based KASAN is not enabled. */ - if (!kasan_hw_tags_enabled()) - return false; - - /* For hardware tag-based KASAN, skip if requested. */ - return (flags & __GFP_SKIP_ZERO); -} - -inline void post_alloc_hook(struct page *page, unsigned int order, - gfp_t gfp_flags) -{ - bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && - !should_skip_init(gfp_flags); - bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); - int i; - - set_page_private(page, 0); - set_page_refcounted(page); - - arch_alloc_page(page, order); - debug_pagealloc_map_pages(page, 1 << order); - - /* - * Page unpoisoning must happen before memory initialization. - * Otherwise, the poison pattern will be overwritten for __GFP_ZERO - * allocations and the page unpoisoning code will complain. - */ - kernel_unpoison_pages(page, 1 << order); + kernel_unpoison_pages(page, 1 << order); /* * As memory initialization might be integrated into KASAN, @@ -6547,7 +5887,6 @@ static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonesta #define BOOT_PAGESET_BATCH 1 static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats); -static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void __build_all_zonelists(void *data) { @@ -6661,395 +6000,35 @@ void __ref build_all_zonelists(pg_data_t *pgdat) #endif } -/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */ -static bool __meminit -overlap_memmap_init(unsigned long zone, unsigned long *pfn) -{ - static struct memblock_region *r; - - if (mirrored_kernelcore && zone == ZONE_MOVABLE) { - if (!r || *pfn >= memblock_region_memory_end_pfn(r)) { - for_each_mem_region(r) { - if (*pfn < memblock_region_memory_end_pfn(r)) - break; - } - } - if (*pfn >= memblock_region_memory_base_pfn(r) && - memblock_is_mirror(r)) { - *pfn = memblock_region_memory_end_pfn(r); - return true; - } - } - return false; -} - -/* - * Initially all pages are reserved - free ones are freed - * up by memblock_free_all() once the early boot process is - * done. Non-atomic initialization, single-pass. - * - * All aligned pageblocks are initialized to the specified migratetype - * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related - * zone stats (e.g., nr_isolate_pageblock) are touched. - */ -void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, unsigned long zone_end_pfn, - enum meminit_context context, - struct vmem_altmap *altmap, int migratetype) +static int zone_batchsize(struct zone *zone) { - unsigned long pfn, end_pfn = start_pfn + size; - struct page *page; +#ifdef CONFIG_MMU + int batch; - if (highest_memmap_pfn < end_pfn - 1) - highest_memmap_pfn = end_pfn - 1; + /* + * The number of pages to batch allocate is either ~0.1% + * of the zone or 1MB, whichever is smaller. The batch + * size is striking a balance between allocation latency + * and zone lock contention. + */ + batch = min(zone_managed_pages(zone) >> 10, SZ_1M / PAGE_SIZE); + batch /= 4; /* We effectively *= 4 below */ + if (batch < 1) + batch = 1; -#ifdef CONFIG_ZONE_DEVICE /* - * Honor reservation requested by the driver for this ZONE_DEVICE - * memory. We limit the total number of pages to initialize to just - * those that might contain the memory mapping. We will defer the - * ZONE_DEVICE page initialization until after we have released - * the hotplug lock. + * Clamp the batch to a 2^n - 1 value. Having a power + * of 2 value was found to be more likely to have + * suboptimal cache aliasing properties in some cases. + * + * For example if 2 tasks are alternately allocating + * batches of pages, one task can end up with a lot + * of pages of one half of the possible page colors + * and the other with pages of the other colors. */ - if (zone == ZONE_DEVICE) { - if (!altmap) - return; + batch = rounddown_pow_of_two(batch + batch/2) - 1; - if (start_pfn == altmap->base_pfn) - start_pfn += altmap->reserve; - end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - } -#endif - - for (pfn = start_pfn; pfn < end_pfn; ) { - /* - * There can be holes in boot-time mem_map[]s handed to this - * function. They do not exist on hotplugged memory. - */ - if (context == MEMINIT_EARLY) { - if (overlap_memmap_init(zone, &pfn)) - continue; - if (defer_init(nid, pfn, zone_end_pfn)) { - deferred_struct_pages = true; - break; - } - } - - page = pfn_to_page(pfn); - __init_single_page(page, pfn, zone, nid); - if (context == MEMINIT_HOTPLUG) - __SetPageReserved(page); - - /* - * Usually, we want to mark the pageblock MIGRATE_MOVABLE, - * such that unmovable allocations won't be scattered all - * over the place during system boot. - */ - if (pageblock_aligned(pfn)) { - set_pageblock_migratetype(page, migratetype); - cond_resched(); - } - pfn++; - } -} - -#ifdef CONFIG_ZONE_DEVICE -static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, - unsigned long zone_idx, int nid, - struct dev_pagemap *pgmap) -{ - - __init_single_page(page, pfn, zone_idx, nid); - - /* - * Mark page reserved as it will need to wait for onlining - * phase for it to be fully associated with a zone. - * - * We can use the non-atomic __set_bit operation for setting - * the flag as we are still initializing the pages. - */ - __SetPageReserved(page); - - /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer - * and zone_device_data. It is a bug if a ZONE_DEVICE page is - * ever freed or placed on a driver-private list. - */ - page->pgmap = pgmap; - page->zone_device_data = NULL; - - /* - * Mark the block movable so that blocks are reserved for - * movable at startup. This will force kernel allocations - * to reserve their blocks rather than leaking throughout - * the address space during boot when many long-lived - * kernel allocations are made. - * - * Please note that MEMINIT_HOTPLUG path doesn't clear memmap - * because this is done early in section_activate() - */ - if (pageblock_aligned(pfn)) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - cond_resched(); - } - - /* - * ZONE_DEVICE pages are released directly to the driver page allocator - * which will set the page count to 1 when allocating the page. - */ - if (pgmap->type == MEMORY_DEVICE_PRIVATE || - pgmap->type == MEMORY_DEVICE_COHERENT) - set_page_count(page, 0); -} - -/* - * With compound page geometry and when struct pages are stored in ram most - * tail pages are reused. Consequently, the amount of unique struct pages to - * initialize is a lot smaller that the total amount of struct pages being - * mapped. This is a paired / mild layering violation with explicit knowledge - * of how the sparse_vmemmap internals handle compound pages in the lack - * of an altmap. See vmemmap_populate_compound_pages(). - */ -static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap, - unsigned long nr_pages) -{ - return is_power_of_2(sizeof(struct page)) && - !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages; -} - -static void __ref memmap_init_compound(struct page *head, - unsigned long head_pfn, - unsigned long zone_idx, int nid, - struct dev_pagemap *pgmap, - unsigned long nr_pages) -{ - unsigned long pfn, end_pfn = head_pfn + nr_pages; - unsigned int order = pgmap->vmemmap_shift; - - __SetPageHead(head); - for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) { - struct page *page = pfn_to_page(pfn); - - __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); - prep_compound_tail(head, pfn - head_pfn); - set_page_count(page, 0); - - /* - * The first tail page stores important compound page info. - * Call prep_compound_head() after the first tail page has - * been initialized, to not have the data overwritten. - */ - if (pfn == head_pfn + 1) - prep_compound_head(head, order); - } -} - -void __ref memmap_init_zone_device(struct zone *zone, - unsigned long start_pfn, - unsigned long nr_pages, - struct dev_pagemap *pgmap) -{ - unsigned long pfn, end_pfn = start_pfn + nr_pages; - struct pglist_data *pgdat = zone->zone_pgdat; - struct vmem_altmap *altmap = pgmap_altmap(pgmap); - unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap); - unsigned long zone_idx = zone_idx(zone); - unsigned long start = jiffies; - int nid = pgdat->node_id; - - if (WARN_ON_ONCE(!pgmap || zone_idx != ZONE_DEVICE)) - return; - - /* - * The call to memmap_init should have already taken care - * of the pages reserved for the memmap, so we can just jump to - * the end of that region and start processing the device pages. - */ - if (altmap) { - start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - nr_pages = end_pfn - start_pfn; - } - - for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) { - struct page *page = pfn_to_page(pfn); - - __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); - - if (pfns_per_compound == 1) - continue; - - memmap_init_compound(page, pfn, zone_idx, nid, pgmap, - compound_nr_pages(altmap, pfns_per_compound)); - } - - pr_info("%s initialised %lu pages in %ums\n", __func__, - nr_pages, jiffies_to_msecs(jiffies - start)); -} - -#endif -static void __meminit zone_init_free_lists(struct zone *zone) -{ - unsigned int order, t; - for_each_migratetype_order(order, t) { - INIT_LIST_HEAD(&zone->free_area[order].free_list[t]); - zone->free_area[order].nr_free = 0; - } -} - -/* - * Only struct pages that correspond to ranges defined by memblock.memory - * are zeroed and initialized by going through __init_single_page() during - * memmap_init_zone_range(). - * - * But, there could be struct pages that correspond to holes in - * memblock.memory. This can happen because of the following reasons: - * - physical memory bank size is not necessarily the exact multiple of the - * arbitrary section size - * - early reserved memory may not be listed in memblock.memory - * - memory layouts defined with memmap= kernel parameter may not align - * nicely with memmap sections - * - * Explicitly initialize those struct pages so that: - * - PG_Reserved is set - * - zone and node links point to zone and node that span the page if the - * hole is in the middle of a zone - * - zone and node links point to adjacent zone/node if the hole falls on - * the zone boundary; the pages in such holes will be prepended to the - * zone/node above the hole except for the trailing pages in the last - * section that will be appended to the zone/node below. - */ -static void __init init_unavailable_range(unsigned long spfn, - unsigned long epfn, - int zone, int node) -{ - unsigned long pfn; - u64 pgcnt = 0; - - for (pfn = spfn; pfn < epfn; pfn++) { - if (!pfn_valid(pageblock_start_pfn(pfn))) { - pfn = pageblock_end_pfn(pfn) - 1; - continue; - } - __init_single_page(pfn_to_page(pfn), pfn, zone, node); - __SetPageReserved(pfn_to_page(pfn)); - pgcnt++; - } - - if (pgcnt) - pr_info("On node %d, zone %s: %lld pages in unavailable ranges", - node, zone_names[zone], pgcnt); -} - -static void __init memmap_init_zone_range(struct zone *zone, - unsigned long start_pfn, - unsigned long end_pfn, - unsigned long *hole_pfn) -{ - unsigned long zone_start_pfn = zone->zone_start_pfn; - unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; - int nid = zone_to_nid(zone), zone_id = zone_idx(zone); - - start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); - end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); - - if (start_pfn >= end_pfn) - return; - - memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn, - zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); - - if (*hole_pfn < start_pfn) - init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); - - *hole_pfn = end_pfn; -} - -static void __init memmap_init(void) -{ - unsigned long start_pfn, end_pfn; - unsigned long hole_pfn = 0; - int i, j, zone_id = 0, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - struct pglist_data *node = NODE_DATA(nid); - - for (j = 0; j < MAX_NR_ZONES; j++) { - struct zone *zone = node->node_zones + j; - - if (!populated_zone(zone)) - continue; - - memmap_init_zone_range(zone, start_pfn, end_pfn, - &hole_pfn); - zone_id = j; - } - } - -#ifdef CONFIG_SPARSEMEM - /* - * Initialize the memory map for hole in the range [memory_end, - * section_end]. - * Append the pages in this hole to the highest zone in the last - * node. - * The call to init_unavailable_range() is outside the ifdef to - * silence the compiler warining about zone_id set but not used; - * for FLATMEM it is a nop anyway - */ - end_pfn = round_up(end_pfn, PAGES_PER_SECTION); - if (hole_pfn < end_pfn) -#endif - init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); -} - -void __init *memmap_alloc(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, int nid, bool exact_nid) -{ - void *ptr; - - if (exact_nid) - ptr = memblock_alloc_exact_nid_raw(size, align, min_addr, - MEMBLOCK_ALLOC_ACCESSIBLE, - nid); - else - ptr = memblock_alloc_try_nid_raw(size, align, min_addr, - MEMBLOCK_ALLOC_ACCESSIBLE, - nid); - - if (ptr && size > 0) - page_init_poison(ptr, size); - - return ptr; -} - -static int zone_batchsize(struct zone *zone) -{ -#ifdef CONFIG_MMU - int batch; - - /* - * The number of pages to batch allocate is either ~0.1% - * of the zone or 1MB, whichever is smaller. The batch - * size is striking a balance between allocation latency - * and zone lock contention. - */ - batch = min(zone_managed_pages(zone) >> 10, SZ_1M / PAGE_SIZE); - batch /= 4; /* We effectively *= 4 below */ - if (batch < 1) - batch = 1; - - /* - * Clamp the batch to a 2^n - 1 value. Having a power - * of 2 value was found to be more likely to have - * suboptimal cache aliasing properties in some cases. - * - * For example if 2 tasks are alternately allocating - * batches of pages, one task can end up with a lot - * of pages of one half of the possible page colors - * and the other with pages of the other colors. - */ - batch = rounddown_pow_of_two(batch + batch/2) - 1; - - return batch; + return batch; #else /* The deferral and batching of frees should be suppressed under NOMMU @@ -7071,1352 +6050,210 @@ static int zone_batchsize(struct zone *zone) static int zone_highsize(struct zone *zone, int batch, int cpu_online) { -#ifdef CONFIG_MMU - int high; - int nr_split_cpus; - unsigned long total_pages; - - if (!percpu_pagelist_high_fraction) { - /* - * By default, the high value of the pcp is based on the zone - * low watermark so that if they are full then background - * reclaim will not be started prematurely. - */ - total_pages = low_wmark_pages(zone); - } else { - /* - * If percpu_pagelist_high_fraction is configured, the high - * value is based on a fraction of the managed pages in the - * zone. - */ - total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; - } - - /* - * Split the high value across all online CPUs local to the zone. Note - * that early in boot that CPUs may not be online yet and that during - * CPU hotplug that the cpumask is not yet updated when a CPU is being - * onlined. For memory nodes that have no CPUs, split pcp->high across - * all online CPUs to mitigate the risk that reclaim is triggered - * prematurely due to pages stored on pcp lists. - */ - nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; - if (!nr_split_cpus) - nr_split_cpus = num_online_cpus(); - high = total_pages / nr_split_cpus; - - /* - * Ensure high is at least batch*4. The multiple is based on the - * historical relationship between high and batch. - */ - high = max(high, batch << 2); - - return high; -#else - return 0; -#endif -} - -/* - * pcp->high and pcp->batch values are related and generally batch is lower - * than high. They are also related to pcp->count such that count is lower - * than high, and as soon as it reaches high, the pcplist is flushed. - * - * However, guaranteeing these relations at all times would require e.g. write - * barriers here but also careful usage of read barriers at the read side, and - * thus be prone to error and bad for performance. Thus the update only prevents - * store tearing. Any new users of pcp->batch and pcp->high should ensure they - * can cope with those fields changing asynchronously, and fully trust only the - * pcp->count field on the local CPU with interrupts disabled. - * - * mutex_is_locked(&pcp_batch_high_lock) required when calling this function - * outside of boot time (or some other assurance that no concurrent updaters - * exist). - */ -static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, - unsigned long batch) -{ - WRITE_ONCE(pcp->batch, batch); - WRITE_ONCE(pcp->high, high); -} - -static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) -{ - int pindex; - - memset(pcp, 0, sizeof(*pcp)); - memset(pzstats, 0, sizeof(*pzstats)); - - spin_lock_init(&pcp->lock); - for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) - INIT_LIST_HEAD(&pcp->lists[pindex]); - - /* - * Set batch and high values safe for a boot pageset. A true percpu - * pageset's initialization will update them subsequently. Here we don't - * need to be as careful as pageset_update() as nobody can access the - * pageset yet. - */ - pcp->high = BOOT_PAGESET_HIGH; - pcp->batch = BOOT_PAGESET_BATCH; - pcp->free_factor = 0; -} - -static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, - unsigned long batch) -{ - struct per_cpu_pages *pcp; - int cpu; - - for_each_possible_cpu(cpu) { - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - pageset_update(pcp, high, batch); - } -} - -/* - * Calculate and set new high and batch values for all per-cpu pagesets of a - * zone based on the zone's size. - */ -static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) -{ - int new_high, new_batch; - - new_batch = max(1, zone_batchsize(zone)); - new_high = zone_highsize(zone, new_batch, cpu_online); - - if (zone->pageset_high == new_high && - zone->pageset_batch == new_batch) - return; - - zone->pageset_high = new_high; - zone->pageset_batch = new_batch; - - __zone_set_pageset_high_and_batch(zone, new_high, new_batch); -} - -void __meminit setup_zone_pageset(struct zone *zone) -{ - int cpu; - - /* Size may be 0 on !SMP && !NUMA */ - if (sizeof(struct per_cpu_zonestat) > 0) - zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); - - zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); - for_each_possible_cpu(cpu) { - struct per_cpu_pages *pcp; - struct per_cpu_zonestat *pzstats; - - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - per_cpu_pages_init(pcp, pzstats); - } - - zone_set_pageset_high_and_batch(zone, 0); -} - -/* - * The zone indicated has a new number of managed_pages; batch sizes and percpu - * page high values need to be recalculated. - */ -static void zone_pcp_update(struct zone *zone, int cpu_online) -{ - mutex_lock(&pcp_batch_high_lock); - zone_set_pageset_high_and_batch(zone, cpu_online); - mutex_unlock(&pcp_batch_high_lock); -} - -/* - * Allocate per cpu pagesets and initialize them. - * Before this call only boot pagesets were available. - */ -void __init setup_per_cpu_pageset(void) -{ - struct pglist_data *pgdat; - struct zone *zone; - int __maybe_unused cpu; - - for_each_populated_zone(zone) - setup_zone_pageset(zone); - -#ifdef CONFIG_NUMA - /* - * Unpopulated zones continue using the boot pagesets. - * The numa stats for these pagesets need to be reset. - * Otherwise, they will end up skewing the stats of - * the nodes these zones are associated with. - */ - for_each_possible_cpu(cpu) { - struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); - memset(pzstats->vm_numa_event, 0, - sizeof(pzstats->vm_numa_event)); - } -#endif - - for_each_online_pgdat(pgdat) - pgdat->per_cpu_nodestats = - alloc_percpu(struct per_cpu_nodestat); -} - -static __meminit void zone_pcp_init(struct zone *zone) -{ - /* - * per cpu subsystem is not up at this point. The following code - * relies on the ability of the linker to provide the - * offset of a (static) per cpu variable into the per cpu area. - */ - zone->per_cpu_pageset = &boot_pageset; - zone->per_cpu_zonestats = &boot_zonestats; - zone->pageset_high = BOOT_PAGESET_HIGH; - zone->pageset_batch = BOOT_PAGESET_BATCH; - - if (populated_zone(zone)) - pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, - zone->present_pages, zone_batchsize(zone)); -} - -void __meminit init_currently_empty_zone(struct zone *zone, - unsigned long zone_start_pfn, - unsigned long size) -{ - struct pglist_data *pgdat = zone->zone_pgdat; - int zone_idx = zone_idx(zone) + 1; - - if (zone_idx > pgdat->nr_zones) - pgdat->nr_zones = zone_idx; - - zone->zone_start_pfn = zone_start_pfn; - - mminit_dprintk(MMINIT_TRACE, "memmap_init", - "Initialising map node %d zone %lu pfns %lu -> %lu\n", - pgdat->node_id, - (unsigned long)zone_idx(zone), - zone_start_pfn, (zone_start_pfn + size)); - - zone_init_free_lists(zone); - zone->initialized = 1; -} - -/** - * get_pfn_range_for_nid - Return the start and end page frames for a node - * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. - * @start_pfn: Passed by reference. On return, it will have the node start_pfn. - * @end_pfn: Passed by reference. On return, it will have the node end_pfn. - * - * It returns the start and end page frame of a node based on information - * provided by memblock_set_node(). If called for a node - * with no available memory, a warning is printed and the start and end - * PFNs will be 0. - */ -void __init get_pfn_range_for_nid(unsigned int nid, - unsigned long *start_pfn, unsigned long *end_pfn) -{ - unsigned long this_start_pfn, this_end_pfn; - int i; - - *start_pfn = -1UL; - *end_pfn = 0; - - for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { - *start_pfn = min(*start_pfn, this_start_pfn); - *end_pfn = max(*end_pfn, this_end_pfn); - } - - if (*start_pfn == -1UL) - *start_pfn = 0; -} - -/* - * This finds a zone that can be used for ZONE_MOVABLE pages. The - * assumption is made that zones within a node are ordered in monotonic - * increasing memory addresses so that the "highest" populated zone is used - */ -static void __init find_usable_zone_for_movable(void) -{ - int zone_index; - for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) { - if (zone_index == ZONE_MOVABLE) - continue; - - if (arch_zone_highest_possible_pfn[zone_index] > - arch_zone_lowest_possible_pfn[zone_index]) - break; - } - - VM_BUG_ON(zone_index == -1); - movable_zone = zone_index; -} - -/* - * The zone ranges provided by the architecture do not include ZONE_MOVABLE - * because it is sized independent of architecture. Unlike the other zones, - * the starting point for ZONE_MOVABLE is not fixed. It may be different - * in each node depending on the size of each node and how evenly kernelcore - * is distributed. This helper function adjusts the zone ranges - * provided by the architecture for a given node by using the end of the - * highest usable zone for ZONE_MOVABLE. This preserves the assumption that - * zones within a node are in order of monotonic increases memory addresses - */ -static void __init adjust_zone_range_for_zone_movable(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zone_start_pfn, - unsigned long *zone_end_pfn) -{ - /* Only adjust if ZONE_MOVABLE is on this node */ - if (zone_movable_pfn[nid]) { - /* Size ZONE_MOVABLE */ - if (zone_type == ZONE_MOVABLE) { - *zone_start_pfn = zone_movable_pfn[nid]; - *zone_end_pfn = min(node_end_pfn, - arch_zone_highest_possible_pfn[movable_zone]); - - /* Adjust for ZONE_MOVABLE starting within this range */ - } else if (!mirrored_kernelcore && - *zone_start_pfn < zone_movable_pfn[nid] && - *zone_end_pfn > zone_movable_pfn[nid]) { - *zone_end_pfn = zone_movable_pfn[nid]; - - /* Check if this whole range is within ZONE_MOVABLE */ - } else if (*zone_start_pfn >= zone_movable_pfn[nid]) - *zone_start_pfn = *zone_end_pfn; - } -} - -/* - * Return the number of pages a zone spans in a node, including holes - * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() - */ -static unsigned long __init zone_spanned_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn, - unsigned long *zone_start_pfn, - unsigned long *zone_end_pfn) -{ - unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; - unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; - /* When hotadd a new node from cpu_up(), the node should be empty */ - if (!node_start_pfn && !node_end_pfn) - return 0; - - /* Get the start and end of the zone */ - *zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); - *zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); - adjust_zone_range_for_zone_movable(nid, zone_type, - node_start_pfn, node_end_pfn, - zone_start_pfn, zone_end_pfn); - - /* Check that this node has pages within the zone's required range */ - if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn) - return 0; - - /* Move the zone boundaries inside the node if necessary */ - *zone_end_pfn = min(*zone_end_pfn, node_end_pfn); - *zone_start_pfn = max(*zone_start_pfn, node_start_pfn); - - /* Return the spanned pages */ - return *zone_end_pfn - *zone_start_pfn; -} - -/* - * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, - * then all holes in the requested range will be accounted for. - */ -unsigned long __init __absent_pages_in_range(int nid, - unsigned long range_start_pfn, - unsigned long range_end_pfn) -{ - unsigned long nr_absent = range_end_pfn - range_start_pfn; - unsigned long start_pfn, end_pfn; - int i; - - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); - end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); - nr_absent -= end_pfn - start_pfn; - } - return nr_absent; -} - -/** - * absent_pages_in_range - Return number of page frames in holes within a range - * @start_pfn: The start PFN to start searching for holes - * @end_pfn: The end PFN to stop searching for holes - * - * Return: the number of pages frames in memory holes within a range. - */ -unsigned long __init absent_pages_in_range(unsigned long start_pfn, - unsigned long end_pfn) -{ - return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); -} - -/* Return the number of page frames in holes in a zone on a node */ -static unsigned long __init zone_absent_pages_in_node(int nid, - unsigned long zone_type, - unsigned long node_start_pfn, - unsigned long node_end_pfn) -{ - unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; - unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; - unsigned long zone_start_pfn, zone_end_pfn; - unsigned long nr_absent; - - /* When hotadd a new node from cpu_up(), the node should be empty */ - if (!node_start_pfn && !node_end_pfn) - return 0; - - zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); - zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); - - adjust_zone_range_for_zone_movable(nid, zone_type, - node_start_pfn, node_end_pfn, - &zone_start_pfn, &zone_end_pfn); - nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); - - /* - * ZONE_MOVABLE handling. - * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages - * and vice versa. - */ - if (mirrored_kernelcore && zone_movable_pfn[nid]) { - unsigned long start_pfn, end_pfn; - struct memblock_region *r; - - for_each_mem_region(r) { - start_pfn = clamp(memblock_region_memory_base_pfn(r), - zone_start_pfn, zone_end_pfn); - end_pfn = clamp(memblock_region_memory_end_pfn(r), - zone_start_pfn, zone_end_pfn); - - if (zone_type == ZONE_MOVABLE && - memblock_is_mirror(r)) - nr_absent += end_pfn - start_pfn; - - if (zone_type == ZONE_NORMAL && - !memblock_is_mirror(r)) - nr_absent += end_pfn - start_pfn; - } - } - - return nr_absent; -} - -static void __init calculate_node_totalpages(struct pglist_data *pgdat, - unsigned long node_start_pfn, - unsigned long node_end_pfn) -{ - unsigned long realtotalpages = 0, totalpages = 0; - enum zone_type i; - - for (i = 0; i < MAX_NR_ZONES; i++) { - struct zone *zone = pgdat->node_zones + i; - unsigned long zone_start_pfn, zone_end_pfn; - unsigned long spanned, absent; - unsigned long size, real_size; - - spanned = zone_spanned_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn, - &zone_start_pfn, - &zone_end_pfn); - absent = zone_absent_pages_in_node(pgdat->node_id, i, - node_start_pfn, - node_end_pfn); - - size = spanned; - real_size = size - absent; - - if (size) - zone->zone_start_pfn = zone_start_pfn; - else - zone->zone_start_pfn = 0; - zone->spanned_pages = size; - zone->present_pages = real_size; -#if defined(CONFIG_MEMORY_HOTPLUG) - zone->present_early_pages = real_size; -#endif - - totalpages += size; - realtotalpages += real_size; - } - - pgdat->node_spanned_pages = totalpages; - pgdat->node_present_pages = realtotalpages; - pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); -} - -#ifndef CONFIG_SPARSEMEM -/* - * Calculate the size of the zone->blockflags rounded to an unsigned long - * Start by making sure zonesize is a multiple of pageblock_order by rounding - * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally - * round what is now in bits to nearest long in bits, then return it in - * bytes. - */ -static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) -{ - unsigned long usemapsize; - - zonesize += zone_start_pfn & (pageblock_nr_pages-1); - usemapsize = roundup(zonesize, pageblock_nr_pages); - usemapsize = usemapsize >> pageblock_order; - usemapsize *= NR_PAGEBLOCK_BITS; - usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long)); - - return usemapsize / 8; -} - -static void __ref setup_usemap(struct zone *zone) -{ - unsigned long usemapsize = usemap_size(zone->zone_start_pfn, - zone->spanned_pages); - zone->pageblock_flags = NULL; - if (usemapsize) { - zone->pageblock_flags = - memblock_alloc_node(usemapsize, SMP_CACHE_BYTES, - zone_to_nid(zone)); - if (!zone->pageblock_flags) - panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n", - usemapsize, zone->name, zone_to_nid(zone)); - } -} -#else -static inline void setup_usemap(struct zone *zone) {} -#endif /* CONFIG_SPARSEMEM */ - -#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE - -/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */ -void __init set_pageblock_order(void) -{ - unsigned int order = MAX_ORDER; - - /* Check that pageblock_nr_pages has not already been setup */ - if (pageblock_order) - return; - - /* Don't let pageblocks exceed the maximum allocation granularity. */ - if (HPAGE_SHIFT > PAGE_SHIFT && HUGETLB_PAGE_ORDER < order) - order = HUGETLB_PAGE_ORDER; - - /* - * Assume the largest contiguous order of interest is a huge page. - * This value may be variable depending on boot parameters on IA64 and - * powerpc. - */ - pageblock_order = order; -} -#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ - -/* - * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order() - * is unused as pageblock_order is set at compile-time. See - * include/linux/pageblock-flags.h for the values of pageblock_order based on - * the kernel config - */ -void __init set_pageblock_order(void) -{ -} - -#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ - -static unsigned long __init calc_memmap_size(unsigned long spanned_pages, - unsigned long present_pages) -{ - unsigned long pages = spanned_pages; - - /* - * Provide a more accurate estimation if there are holes within - * the zone and SPARSEMEM is in use. If there are holes within the - * zone, each populated memory region may cost us one or two extra - * memmap pages due to alignment because memmap pages for each - * populated regions may not be naturally aligned on page boundary. - * So the (present_pages >> 4) heuristic is a tradeoff for that. - */ - if (spanned_pages > present_pages + (present_pages >> 4) && - IS_ENABLED(CONFIG_SPARSEMEM)) - pages = present_pages; - - return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; -} - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static void pgdat_init_split_queue(struct pglist_data *pgdat) -{ - struct deferred_split *ds_queue = &pgdat->deferred_split_queue; - - spin_lock_init(&ds_queue->split_queue_lock); - INIT_LIST_HEAD(&ds_queue->split_queue); - ds_queue->split_queue_len = 0; -} -#else -static void pgdat_init_split_queue(struct pglist_data *pgdat) {} -#endif - -#ifdef CONFIG_COMPACTION -static void pgdat_init_kcompactd(struct pglist_data *pgdat) -{ - init_waitqueue_head(&pgdat->kcompactd_wait); -} -#else -static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} -#endif - -static void __meminit pgdat_init_internals(struct pglist_data *pgdat) -{ - int i; - - pgdat_resize_init(pgdat); - pgdat_kswapd_lock_init(pgdat); - - pgdat_init_split_queue(pgdat); - pgdat_init_kcompactd(pgdat); - - init_waitqueue_head(&pgdat->kswapd_wait); - init_waitqueue_head(&pgdat->pfmemalloc_wait); - - for (i = 0; i < NR_VMSCAN_THROTTLE; i++) - init_waitqueue_head(&pgdat->reclaim_wait[i]); - - pgdat_page_ext_init(pgdat); - lruvec_init(&pgdat->__lruvec); -} - -static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid, - unsigned long remaining_pages) -{ - atomic_long_set(&zone->managed_pages, remaining_pages); - zone_set_nid(zone, nid); - zone->name = zone_names[idx]; - zone->zone_pgdat = NODE_DATA(nid); - spin_lock_init(&zone->lock); - zone_seqlock_init(zone); - zone_pcp_init(zone); -} - -/* - * Set up the zone data structures - * - init pgdat internals - * - init all zones belonging to this node - * - * NOTE: this function is only called during memory hotplug - */ -#ifdef CONFIG_MEMORY_HOTPLUG -void __ref free_area_init_core_hotplug(struct pglist_data *pgdat) -{ - int nid = pgdat->node_id; - enum zone_type z; - int cpu; - - pgdat_init_internals(pgdat); - - if (pgdat->per_cpu_nodestats == &boot_nodestats) - pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); - - /* - * Reset the nr_zones, order and highest_zoneidx before reuse. - * Note that kswapd will init kswapd_highest_zoneidx properly - * when it starts in the near future. - */ - pgdat->nr_zones = 0; - pgdat->kswapd_order = 0; - pgdat->kswapd_highest_zoneidx = 0; - pgdat->node_start_pfn = 0; - for_each_online_cpu(cpu) { - struct per_cpu_nodestat *p; - - p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu); - memset(p, 0, sizeof(*p)); - } - - for (z = 0; z < MAX_NR_ZONES; z++) - zone_init_internals(&pgdat->node_zones[z], z, nid, 0); -} -#endif - -/* - * Set up the zone data structures: - * - mark all pages reserved - * - mark all memory queues empty - * - clear the memory bitmaps - * - * NOTE: pgdat should get zeroed by caller. - * NOTE: this function is only called during early init. - */ -static void __init free_area_init_core(struct pglist_data *pgdat) -{ - enum zone_type j; - int nid = pgdat->node_id; - - pgdat_init_internals(pgdat); - pgdat->per_cpu_nodestats = &boot_nodestats; - - for (j = 0; j < MAX_NR_ZONES; j++) { - struct zone *zone = pgdat->node_zones + j; - unsigned long size, freesize, memmap_pages; - - size = zone->spanned_pages; - freesize = zone->present_pages; - - /* - * Adjust freesize so that it accounts for how much memory - * is used by this zone for memmap. This affects the watermark - * and per-cpu initialisations - */ - memmap_pages = calc_memmap_size(size, freesize); - if (!is_highmem_idx(j)) { - if (freesize >= memmap_pages) { - freesize -= memmap_pages; - if (memmap_pages) - pr_debug(" %s zone: %lu pages used for memmap\n", - zone_names[j], memmap_pages); - } else - pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", - zone_names[j], memmap_pages, freesize); - } - - /* Account for reserved pages */ - if (j == 0 && freesize > dma_reserve) { - freesize -= dma_reserve; - pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); - } - - if (!is_highmem_idx(j)) - nr_kernel_pages += freesize; - /* Charge for highmem memmap if there are enough kernel pages */ - else if (nr_kernel_pages > memmap_pages * 2) - nr_kernel_pages -= memmap_pages; - nr_all_pages += freesize; - - /* - * Set an approximate value for lowmem here, it will be adjusted - * when the bootmem allocator frees pages into the buddy system. - * And all highmem pages will be managed by the buddy system. - */ - zone_init_internals(zone, j, nid, freesize); - - if (!size) - continue; - - set_pageblock_order(); - setup_usemap(zone); - init_currently_empty_zone(zone, zone->zone_start_pfn, size); - } -} - -#ifdef CONFIG_FLATMEM -static void __init alloc_node_mem_map(struct pglist_data *pgdat) -{ - unsigned long __maybe_unused start = 0; - unsigned long __maybe_unused offset = 0; - - /* Skip empty nodes */ - if (!pgdat->node_spanned_pages) - return; - - start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); - offset = pgdat->node_start_pfn - start; - /* ia64 gets its own node_mem_map, before this, without bootmem */ - if (!pgdat->node_mem_map) { - unsigned long size, end; - struct page *map; - - /* - * The zone's endpoints aren't required to be MAX_ORDER - * aligned but the node_mem_map endpoints must be in order - * for the buddy allocator to function correctly. - */ - end = pgdat_end_pfn(pgdat); - end = ALIGN(end, MAX_ORDER_NR_PAGES); - size = (end - start) * sizeof(struct page); - map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, - pgdat->node_id, false); - if (!map) - panic("Failed to allocate %ld bytes for node %d memory map\n", - size, pgdat->node_id); - pgdat->node_mem_map = map + offset; - } - pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", - __func__, pgdat->node_id, (unsigned long)pgdat, - (unsigned long)pgdat->node_mem_map); -#ifndef CONFIG_NUMA - /* - * With no DISCONTIG, the global mem_map is just set as node 0's - */ - if (pgdat == NODE_DATA(0)) { - mem_map = NODE_DATA(0)->node_mem_map; - if (page_to_pfn(mem_map) != pgdat->node_start_pfn) - mem_map -= offset; - } -#endif -} -#else -static inline void alloc_node_mem_map(struct pglist_data *pgdat) { } -#endif /* CONFIG_FLATMEM */ - -#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static inline void pgdat_set_deferred_range(pg_data_t *pgdat) -{ - pgdat->first_deferred_pfn = ULONG_MAX; -} -#else -static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {} -#endif - -static void __init free_area_init_node(int nid) -{ - pg_data_t *pgdat = NODE_DATA(nid); - unsigned long start_pfn = 0; - unsigned long end_pfn = 0; - - /* pg_data_t should be reset to zero when it's allocated */ - WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx); - - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - - pgdat->node_id = nid; - pgdat->node_start_pfn = start_pfn; - pgdat->per_cpu_nodestats = NULL; - - if (start_pfn != end_pfn) { - pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, - (u64)start_pfn << PAGE_SHIFT, - end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0); - } else { - pr_info("Initmem setup node %d as memoryless\n", nid); - } - - calculate_node_totalpages(pgdat, start_pfn, end_pfn); - - alloc_node_mem_map(pgdat); - pgdat_set_deferred_range(pgdat); - - free_area_init_core(pgdat); - lru_gen_init_pgdat(pgdat); -} - -static void __init free_area_init_memoryless_node(int nid) -{ - free_area_init_node(nid); -} - -#if MAX_NUMNODES > 1 -/* - * Figure out the number of possible node ids. - */ -void __init setup_nr_node_ids(void) -{ - unsigned int highest; - - highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES); - nr_node_ids = highest + 1; -} -#endif - -/** - * node_map_pfn_alignment - determine the maximum internode alignment - * - * This function should be called after node map is populated and sorted. - * It calculates the maximum power of two alignment which can distinguish - * all the nodes. - * - * For example, if all nodes are 1GiB and aligned to 1GiB, the return value - * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the - * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is - * shifted, 1GiB is enough and this function will indicate so. - * - * This is used to test whether pfn -> nid mapping of the chosen memory - * model has fine enough granularity to avoid incorrect mapping for the - * populated node map. - * - * Return: the determined alignment in pfn's. 0 if there is no alignment - * requirement (single node). - */ -unsigned long __init node_map_pfn_alignment(void) -{ - unsigned long accl_mask = 0, last_end = 0; - unsigned long start, end, mask; - int last_nid = NUMA_NO_NODE; - int i, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { - if (!start || last_nid < 0 || last_nid == nid) { - last_nid = nid; - last_end = end; - continue; - } - - /* - * Start with a mask granular enough to pin-point to the - * start pfn and tick off bits one-by-one until it becomes - * too coarse to separate the current node from the last. - */ - mask = ~((1 << __ffs(start)) - 1); - while (mask && last_end <= (start & (mask << 1))) - mask <<= 1; - - /* accumulate all internode masks */ - accl_mask |= mask; - } - - /* convert mask to number of pages */ - return ~accl_mask + 1; -} - -/* - * early_calculate_totalpages() - * Sum pages in active regions for movable zone. - * Populate N_MEMORY for calculating usable_nodes. - */ -static unsigned long __init early_calculate_totalpages(void) -{ - unsigned long totalpages = 0; - unsigned long start_pfn, end_pfn; - int i, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - unsigned long pages = end_pfn - start_pfn; - - totalpages += pages; - if (pages) - node_set_state(nid, N_MEMORY); - } - return totalpages; -} - -/* - * Find the PFN the Movable zone begins in each node. Kernel memory - * is spread evenly between nodes as long as the nodes have enough - * memory. When they don't, some nodes will have more kernelcore than - * others - */ -static void __init find_zone_movable_pfns_for_nodes(void) -{ - int i, nid; - unsigned long usable_startpfn; - unsigned long kernelcore_node, kernelcore_remaining; - /* save the state before borrow the nodemask */ - nodemask_t saved_node_state = node_states[N_MEMORY]; - unsigned long totalpages = early_calculate_totalpages(); - int usable_nodes = nodes_weight(node_states[N_MEMORY]); - struct memblock_region *r; - - /* Need to find movable_zone earlier when movable_node is specified. */ - find_usable_zone_for_movable(); - - /* - * If movable_node is specified, ignore kernelcore and movablecore - * options. - */ - if (movable_node_is_enabled()) { - for_each_mem_region(r) { - if (!memblock_is_hotpluggable(r)) - continue; - - nid = memblock_get_region_node(r); - - usable_startpfn = PFN_DOWN(r->base); - zone_movable_pfn[nid] = zone_movable_pfn[nid] ? - min(usable_startpfn, zone_movable_pfn[nid]) : - usable_startpfn; - } - - goto out2; - } - - /* - * If kernelcore=mirror is specified, ignore movablecore option - */ - if (mirrored_kernelcore) { - bool mem_below_4gb_not_mirrored = false; - - for_each_mem_region(r) { - if (memblock_is_mirror(r)) - continue; - - nid = memblock_get_region_node(r); - - usable_startpfn = memblock_region_memory_base_pfn(r); - - if (usable_startpfn < PHYS_PFN(SZ_4G)) { - mem_below_4gb_not_mirrored = true; - continue; - } - - zone_movable_pfn[nid] = zone_movable_pfn[nid] ? - min(usable_startpfn, zone_movable_pfn[nid]) : - usable_startpfn; - } - - if (mem_below_4gb_not_mirrored) - pr_warn("This configuration results in unmirrored kernel memory.\n"); - - goto out2; - } - - /* - * If kernelcore=nn% or movablecore=nn% was specified, calculate the - * amount of necessary memory. - */ - if (required_kernelcore_percent) - required_kernelcore = (totalpages * 100 * required_kernelcore_percent) / - 10000UL; - if (required_movablecore_percent) - required_movablecore = (totalpages * 100 * required_movablecore_percent) / - 10000UL; - - /* - * If movablecore= was specified, calculate what size of - * kernelcore that corresponds so that memory usable for - * any allocation type is evenly spread. If both kernelcore - * and movablecore are specified, then the value of kernelcore - * will be used for required_kernelcore if it's greater than - * what movablecore would have allowed. - */ - if (required_movablecore) { - unsigned long corepages; - - /* - * Round-up so that ZONE_MOVABLE is at least as large as what - * was requested by the user - */ - required_movablecore = - roundup(required_movablecore, MAX_ORDER_NR_PAGES); - required_movablecore = min(totalpages, required_movablecore); - corepages = totalpages - required_movablecore; - - required_kernelcore = max(required_kernelcore, corepages); - } - - /* - * If kernelcore was not specified or kernelcore size is larger - * than totalpages, there is no ZONE_MOVABLE. - */ - if (!required_kernelcore || required_kernelcore >= totalpages) - goto out; - - /* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */ - usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone]; - -restart: - /* Spread kernelcore memory as evenly as possible throughout nodes */ - kernelcore_node = required_kernelcore / usable_nodes; - for_each_node_state(nid, N_MEMORY) { - unsigned long start_pfn, end_pfn; +#ifdef CONFIG_MMU + int high; + int nr_split_cpus; + unsigned long total_pages; + if (!percpu_pagelist_high_fraction) { /* - * Recalculate kernelcore_node if the division per node - * now exceeds what is necessary to satisfy the requested - * amount of memory for the kernel + * By default, the high value of the pcp is based on the zone + * low watermark so that if they are full then background + * reclaim will not be started prematurely. */ - if (required_kernelcore < kernelcore_node) - kernelcore_node = required_kernelcore / usable_nodes; - + total_pages = low_wmark_pages(zone); + } else { /* - * As the map is walked, we track how much memory is usable - * by the kernel using kernelcore_remaining. When it is - * 0, the rest of the node is usable by ZONE_MOVABLE + * If percpu_pagelist_high_fraction is configured, the high + * value is based on a fraction of the managed pages in the + * zone. */ - kernelcore_remaining = kernelcore_node; - - /* Go through each range of PFNs within this node */ - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - unsigned long size_pages; - - start_pfn = max(start_pfn, zone_movable_pfn[nid]); - if (start_pfn >= end_pfn) - continue; - - /* Account for what is only usable for kernelcore */ - if (start_pfn < usable_startpfn) { - unsigned long kernel_pages; - kernel_pages = min(end_pfn, usable_startpfn) - - start_pfn; - - kernelcore_remaining -= min(kernel_pages, - kernelcore_remaining); - required_kernelcore -= min(kernel_pages, - required_kernelcore); - - /* Continue if range is now fully accounted */ - if (end_pfn <= usable_startpfn) { - - /* - * Push zone_movable_pfn to the end so - * that if we have to rebalance - * kernelcore across nodes, we will - * not double account here - */ - zone_movable_pfn[nid] = end_pfn; - continue; - } - start_pfn = usable_startpfn; - } - - /* - * The usable PFN range for ZONE_MOVABLE is from - * start_pfn->end_pfn. Calculate size_pages as the - * number of pages used as kernelcore - */ - size_pages = end_pfn - start_pfn; - if (size_pages > kernelcore_remaining) - size_pages = kernelcore_remaining; - zone_movable_pfn[nid] = start_pfn + size_pages; - - /* - * Some kernelcore has been met, update counts and - * break if the kernelcore for this node has been - * satisfied - */ - required_kernelcore -= min(required_kernelcore, - size_pages); - kernelcore_remaining -= size_pages; - if (!kernelcore_remaining) - break; - } + total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; } /* - * If there is still required_kernelcore, we do another pass with one - * less node in the count. This will push zone_movable_pfn[nid] further - * along on the nodes that still have memory until kernelcore is - * satisfied + * Split the high value across all online CPUs local to the zone. Note + * that early in boot that CPUs may not be online yet and that during + * CPU hotplug that the cpumask is not yet updated when a CPU is being + * onlined. For memory nodes that have no CPUs, split pcp->high across + * all online CPUs to mitigate the risk that reclaim is triggered + * prematurely due to pages stored on pcp lists. */ - usable_nodes--; - if (usable_nodes && required_kernelcore > usable_nodes) - goto restart; - -out2: - /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ - for (nid = 0; nid < MAX_NUMNODES; nid++) { - unsigned long start_pfn, end_pfn; - - zone_movable_pfn[nid] = - roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); - - get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - if (zone_movable_pfn[nid] >= end_pfn) - zone_movable_pfn[nid] = 0; - } - -out: - /* restore the node_state */ - node_states[N_MEMORY] = saved_node_state; -} + nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; + if (!nr_split_cpus) + nr_split_cpus = num_online_cpus(); + high = total_pages / nr_split_cpus; -/* Any regular or high memory on that node ? */ -static void check_for_memory(pg_data_t *pgdat, int nid) -{ - enum zone_type zone_type; + /* + * Ensure high is at least batch*4. The multiple is based on the + * historical relationship between high and batch. + */ + high = max(high, batch << 2); - for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { - struct zone *zone = &pgdat->node_zones[zone_type]; - if (populated_zone(zone)) { - if (IS_ENABLED(CONFIG_HIGHMEM)) - node_set_state(nid, N_HIGH_MEMORY); - if (zone_type <= ZONE_NORMAL) - node_set_state(nid, N_NORMAL_MEMORY); - break; - } - } + return high; +#else + return 0; +#endif } /* - * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For - * such cases we allow max_zone_pfn sorted in the descending order + * pcp->high and pcp->batch values are related and generally batch is lower + * than high. They are also related to pcp->count such that count is lower + * than high, and as soon as it reaches high, the pcplist is flushed. + * + * However, guaranteeing these relations at all times would require e.g. write + * barriers here but also careful usage of read barriers at the read side, and + * thus be prone to error and bad for performance. Thus the update only prevents + * store tearing. Any new users of pcp->batch and pcp->high should ensure they + * can cope with those fields changing asynchronously, and fully trust only the + * pcp->count field on the local CPU with interrupts disabled. + * + * mutex_is_locked(&pcp_batch_high_lock) required when calling this function + * outside of boot time (or some other assurance that no concurrent updaters + * exist). */ -bool __weak arch_has_descending_max_zone_pfns(void) +static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, + unsigned long batch) { - return false; + WRITE_ONCE(pcp->batch, batch); + WRITE_ONCE(pcp->high, high); } -/** - * free_area_init - Initialise all pg_data_t and zone data - * @max_zone_pfn: an array of max PFNs for each zone - * - * This will call free_area_init_node() for each active node in the system. - * Using the page ranges provided by memblock_set_node(), the size of each - * zone in each node and their holes is calculated. If the maximum PFN - * between two adjacent zones match, it is assumed that the zone is empty. - * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed - * that arch_max_dma32_pfn has no pages. It is also assumed that a zone - * starts where the previous one ended. For example, ZONE_DMA32 starts - * at arch_max_dma_pfn. - */ -void __init free_area_init(unsigned long *max_zone_pfn) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - unsigned long start_pfn, end_pfn; - int i, nid, zone; - bool descending; - - /* Record where the zone boundaries are */ - memset(arch_zone_lowest_possible_pfn, 0, - sizeof(arch_zone_lowest_possible_pfn)); - memset(arch_zone_highest_possible_pfn, 0, - sizeof(arch_zone_highest_possible_pfn)); - - start_pfn = PHYS_PFN(memblock_start_of_DRAM()); - descending = arch_has_descending_max_zone_pfns(); - - for (i = 0; i < MAX_NR_ZONES; i++) { - if (descending) - zone = MAX_NR_ZONES - i - 1; - else - zone = i; - - if (zone == ZONE_MOVABLE) - continue; + int pindex; - end_pfn = max(max_zone_pfn[zone], start_pfn); - arch_zone_lowest_possible_pfn[zone] = start_pfn; - arch_zone_highest_possible_pfn[zone] = end_pfn; + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); - start_pfn = end_pfn; - } + spin_lock_init(&pcp->lock); + for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) + INIT_LIST_HEAD(&pcp->lists[pindex]); - /* Find the PFNs that ZONE_MOVABLE begins at in each node */ - memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); - find_zone_movable_pfns_for_nodes(); + /* + * Set batch and high values safe for a boot pageset. A true percpu + * pageset's initialization will update them subsequently. Here we don't + * need to be as careful as pageset_update() as nobody can access the + * pageset yet. + */ + pcp->high = BOOT_PAGESET_HIGH; + pcp->batch = BOOT_PAGESET_BATCH; + pcp->free_factor = 0; +} - /* Print out the zone ranges */ - pr_info("Zone ranges:\n"); - for (i = 0; i < MAX_NR_ZONES; i++) { - if (i == ZONE_MOVABLE) - continue; - pr_info(" %-8s ", zone_names[i]); - if (arch_zone_lowest_possible_pfn[i] == - arch_zone_highest_possible_pfn[i]) - pr_cont("empty\n"); - else - pr_cont("[mem %#018Lx-%#018Lx]\n", - (u64)arch_zone_lowest_possible_pfn[i] - << PAGE_SHIFT, - ((u64)arch_zone_highest_possible_pfn[i] - << PAGE_SHIFT) - 1); - } +static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, + unsigned long batch) +{ + struct per_cpu_pages *pcp; + int cpu; - /* Print out the PFNs ZONE_MOVABLE begins at in each node */ - pr_info("Movable zone start for each node\n"); - for (i = 0; i < MAX_NUMNODES; i++) { - if (zone_movable_pfn[i]) - pr_info(" Node %d: %#018Lx\n", i, - (u64)zone_movable_pfn[i] << PAGE_SHIFT); + for_each_possible_cpu(cpu) { + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high, batch); } +} - /* - * Print out the early node map, and initialize the - * subsection-map relative to active online memory ranges to - * enable future "sub-section" extensions of the memory map. - */ - pr_info("Early memory node ranges\n"); - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid, - (u64)start_pfn << PAGE_SHIFT, - ((u64)end_pfn << PAGE_SHIFT) - 1); - subsection_map_init(start_pfn, end_pfn - start_pfn); - } - - /* Initialise every node */ - mminit_verify_pageflags_layout(); - setup_nr_node_ids(); - for_each_node(nid) { - pg_data_t *pgdat; - - if (!node_online(nid)) { - pr_info("Initializing node %d as memoryless\n", nid); - - /* Allocator not initialized yet */ - pgdat = arch_alloc_nodedata(nid); - if (!pgdat) - panic("Cannot allocate %zuB for node %d.\n", - sizeof(*pgdat), nid); - arch_refresh_nodedata(nid, pgdat); - free_area_init_memoryless_node(nid); +/* + * Calculate and set new high and batch values for all per-cpu pagesets of a + * zone based on the zone's size. + */ +static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) +{ + int new_high, new_batch; - /* - * We do not want to confuse userspace by sysfs - * files/directories for node without any memory - * attached to it, so this node is not marked as - * N_MEMORY and not marked online so that no sysfs - * hierarchy will be created via register_one_node for - * it. The pgdat will get fully initialized by - * hotadd_init_pgdat() when memory is hotplugged into - * this node. - */ - continue; - } + new_batch = max(1, zone_batchsize(zone)); + new_high = zone_highsize(zone, new_batch, cpu_online); - pgdat = NODE_DATA(nid); - free_area_init_node(nid); + if (zone->pageset_high == new_high && + zone->pageset_batch == new_batch) + return; - /* Any memory on that node */ - if (pgdat->node_present_pages) - node_set_state(nid, N_MEMORY); - check_for_memory(pgdat, nid); - } + zone->pageset_high = new_high; + zone->pageset_batch = new_batch; - memmap_init(); + __zone_set_pageset_high_and_batch(zone, new_high, new_batch); } -static int __init cmdline_parse_core(char *p, unsigned long *core, - unsigned long *percent) +void __meminit setup_zone_pageset(struct zone *zone) { - unsigned long long coremem; - char *endptr; - - if (!p) - return -EINVAL; + int cpu; - /* Value may be a percentage of total memory, otherwise bytes */ - coremem = simple_strtoull(p, &endptr, 0); - if (*endptr == '%') { - /* Paranoid check for percent values greater than 100 */ - WARN_ON(coremem > 100); + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); - *percent = coremem; - } else { - coremem = memparse(p, &p); - /* Paranoid check that UL is enough for the coremem value */ - WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX); + zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); + for_each_possible_cpu(cpu) { + struct per_cpu_pages *pcp; + struct per_cpu_zonestat *pzstats; - *core = coremem >> PAGE_SHIFT; - *percent = 0UL; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); } - return 0; + + zone_set_pageset_high_and_batch(zone, 0); } /* - * kernelcore=size sets the amount of memory for use for allocations that - * cannot be reclaimed or migrated. + * The zone indicated has a new number of managed_pages; batch sizes and percpu + * page high values need to be recalculated. */ -static int __init cmdline_parse_kernelcore(char *p) +static void zone_pcp_update(struct zone *zone, int cpu_online) { - /* parse kernelcore=mirror */ - if (parse_option_str(p, "mirror")) { - mirrored_kernelcore = true; - return 0; - } - - return cmdline_parse_core(p, &required_kernelcore, - &required_kernelcore_percent); + mutex_lock(&pcp_batch_high_lock); + zone_set_pageset_high_and_batch(zone, cpu_online); + mutex_unlock(&pcp_batch_high_lock); } /* - * movablecore=size sets the amount of memory for use for allocations that - * can be reclaimed or migrated. + * Allocate per cpu pagesets and initialize them. + * Before this call only boot pagesets were available. */ -static int __init cmdline_parse_movablecore(char *p) +void __init setup_per_cpu_pageset(void) { - return cmdline_parse_core(p, &required_movablecore, - &required_movablecore_percent); + struct pglist_data *pgdat; + struct zone *zone; + int __maybe_unused cpu; + + for_each_populated_zone(zone) + setup_zone_pageset(zone); + +#ifdef CONFIG_NUMA + /* + * Unpopulated zones continue using the boot pagesets. + * The numa stats for these pagesets need to be reset. + * Otherwise, they will end up skewing the stats of + * the nodes these zones are associated with. + */ + for_each_possible_cpu(cpu) { + struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); + memset(pzstats->vm_numa_event, 0, + sizeof(pzstats->vm_numa_event)); + } +#endif + + for_each_online_pgdat(pgdat) + pgdat->per_cpu_nodestats = + alloc_percpu(struct per_cpu_nodestat); } -early_param("kernelcore", cmdline_parse_kernelcore); -early_param("movablecore", cmdline_parse_movablecore); +__meminit void zone_pcp_init(struct zone *zone) +{ + /* + * per cpu subsystem is not up at this point. The following code + * relies on the ability of the linker to provide the + * offset of a (static) per cpu variable into the per cpu area. + */ + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; + zone->pageset_high = BOOT_PAGESET_HIGH; + zone->pageset_batch = BOOT_PAGESET_BATCH; + + if (populated_zone(zone)) + pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, + zone->present_pages, zone_batchsize(zone)); +} void adjust_managed_page_count(struct page *page, long count) { @@ -8516,22 +6353,6 @@ void __init mem_init_print_info(void) ); } -/** - * set_dma_reserve - set the specified number of pages reserved in the first zone - * @new_dma_reserve: The number of pages to mark reserved - * - * The per-cpu batchsize and zone watermarks are determined by managed_pages. - * In the DMA zone, a significant percentage may be consumed by kernel image - * and other unfreeable allocations which can skew the watermarks badly. This - * function may optionally be used to account for unfreeable pages in the - * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and - * smaller per-cpu batchsize. - */ -void __init set_dma_reserve(unsigned long new_dma_reserve) -{ - dma_reserve = new_dma_reserve; -} - static int page_alloc_cpu_dead(unsigned int cpu) { struct zone *zone; @@ -8976,149 +6797,6 @@ int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table, return ret; } -#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES -/* - * Returns the number of pages that arch has reserved but - * is not known to alloc_large_system_hash(). - */ -static unsigned long __init arch_reserved_kernel_pages(void) -{ - return 0; -} -#endif - -/* - * Adaptive scale is meant to reduce sizes of hash tables on large memory - * machines. As memory size is increased the scale is also increased but at - * slower pace. Starting from ADAPT_SCALE_BASE (64G), every time memory - * quadruples the scale is increased by one, which means the size of hash table - * only doubles, instead of quadrupling as well. - * Because 32-bit systems cannot have large physical memory, where this scaling - * makes sense, it is disabled on such platforms. - */ -#if __BITS_PER_LONG > 32 -#define ADAPT_SCALE_BASE (64ul << 30) -#define ADAPT_SCALE_SHIFT 2 -#define ADAPT_SCALE_NPAGES (ADAPT_SCALE_BASE >> PAGE_SHIFT) -#endif - -/* - * allocate a large system hash table from bootmem - * - it is assumed that the hash table must contain an exact power-of-2 - * quantity of entries - * - limit is the number of hash buckets, not the total allocation size - */ -void *__init alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit) -{ - unsigned long long max = high_limit; - unsigned long log2qty, size; - void *table; - gfp_t gfp_flags; - bool virt; - bool huge; - - /* allow the kernel cmdline to have a say */ - if (!numentries) { - /* round applicable memory size up to nearest megabyte */ - numentries = nr_kernel_pages; - numentries -= arch_reserved_kernel_pages(); - - /* It isn't necessary when PAGE_SIZE >= 1MB */ - if (PAGE_SIZE < SZ_1M) - numentries = round_up(numentries, SZ_1M / PAGE_SIZE); - -#if __BITS_PER_LONG > 32 - if (!high_limit) { - unsigned long adapt; - - for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries; - adapt <<= ADAPT_SCALE_SHIFT) - scale++; - } -#endif - - /* limit to 1 bucket per 2^scale bytes of low memory */ - if (scale > PAGE_SHIFT) - numentries >>= (scale - PAGE_SHIFT); - else - numentries <<= (PAGE_SHIFT - scale); - - /* Make sure we've got at least a 0-order allocation.. */ - if (unlikely(flags & HASH_SMALL)) { - /* Makes no sense without HASH_EARLY */ - WARN_ON(!(flags & HASH_EARLY)); - if (!(numentries >> *_hash_shift)) { - numentries = 1UL << *_hash_shift; - BUG_ON(!numentries); - } - } else if (unlikely((numentries * bucketsize) < PAGE_SIZE)) - numentries = PAGE_SIZE / bucketsize; - } - numentries = roundup_pow_of_two(numentries); - - /* limit allocation size to 1/16 total memory by default */ - if (max == 0) { - max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; - do_div(max, bucketsize); - } - max = min(max, 0x80000000ULL); - - if (numentries < low_limit) - numentries = low_limit; - if (numentries > max) - numentries = max; - - log2qty = ilog2(numentries); - - gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC; - do { - virt = false; - size = bucketsize << log2qty; - if (flags & HASH_EARLY) { - if (flags & HASH_ZERO) - table = memblock_alloc(size, SMP_CACHE_BYTES); - else - table = memblock_alloc_raw(size, - SMP_CACHE_BYTES); - } else if (get_order(size) > MAX_ORDER || hashdist) { - table = vmalloc_huge(size, gfp_flags); - virt = true; - if (table) - huge = is_vm_area_hugepages(table); - } else { - /* - * If bucketsize is not a power-of-two, we may free - * some pages at the end of hash table which - * alloc_pages_exact() automatically does - */ - table = alloc_pages_exact(size, gfp_flags); - kmemleak_alloc(table, size, 1, gfp_flags); - } - } while (!table && size > PAGE_SIZE && --log2qty); - - if (!table) - panic("Failed to allocate %s hash table\n", tablename); - - pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n", - tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size, - virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear"); - - if (_hash_shift) - *_hash_shift = log2qty; - if (_hash_mask) - *_hash_mask = (1 << log2qty) - 1; - - return table; -} - #ifdef CONFIG_CONTIG_ALLOC #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -- GitLab From 534ef4e19160b1034430c4c4fbc1bf94c0253a51 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:03 +0200 Subject: [PATCH 2231/5631] mm: handle hashdist initialization in mm/mm_init.c The hashdist variable must be initialized before the first call to alloc_large_system_hash() and free_area_init() looks like a better place for it than page_alloc_init(). Move hashdist handling to mm/mm_init.c Link: https://lkml.kernel.org/r/20230321170513.2401534-5-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- mm/mm_init.c | 22 ++++++++++++++++++++++ mm/page_alloc.c | 18 ------------------ 2 files changed, 22 insertions(+), 18 deletions(-) diff --git a/mm/mm_init.c b/mm/mm_init.c index 68d0187c7886..2e60c7186132 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -607,6 +607,25 @@ int __meminit early_pfn_to_nid(unsigned long pfn) return nid; } + +int hashdist = HASHDIST_DEFAULT; + +static int __init set_hashdist(char *str) +{ + if (!str) + return 0; + hashdist = simple_strtoul(str, &str, 0); + return 1; +} +__setup("hashdist=", set_hashdist); + +static inline void fixup_hashdist(void) +{ + if (num_node_state(N_MEMORY) == 1) + hashdist = 0; +} +#else +static inline void fixup_hashdist(void) {} #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -1855,6 +1874,9 @@ void __init free_area_init(unsigned long *max_zone_pfn) } memmap_init(); + + /* disable hash distribution for systems with a single node */ + fixup_hashdist(); } /** diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8adc70b6034d..3abc994bcfa1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6393,28 +6393,10 @@ static int page_alloc_cpu_online(unsigned int cpu) return 0; } -#ifdef CONFIG_NUMA -int hashdist = HASHDIST_DEFAULT; - -static int __init set_hashdist(char *str) -{ - if (!str) - return 0; - hashdist = simple_strtoul(str, &str, 0); - return 1; -} -__setup("hashdist=", set_hashdist); -#endif - void __init page_alloc_init(void) { int ret; -#ifdef CONFIG_NUMA - if (num_node_state(N_MEMORY) == 1) - hashdist = 0; -#endif - ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, "mm/page_alloc:pcp", page_alloc_cpu_online, -- GitLab From c4fbed4b0284d91797ee3cf60983b94c84c396b6 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:04 +0200 Subject: [PATCH 2232/5631] mm/page_alloc: rename page_alloc_init() to page_alloc_init_cpuhp() The page_alloc_init() name is really misleading because all this function does is sets up CPU hotplug callbacks for the page allocator. Rename it to page_alloc_init_cpuhp() so that name will reflect what the function does. Link: https://lkml.kernel.org/r/20230321170513.2401534-6-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/gfp.h | 2 +- init/main.c | 2 +- mm/page_alloc.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 7c554e4bd49f..ed8cb537c6a7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -319,7 +319,7 @@ extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) -void page_alloc_init(void); +void page_alloc_init_cpuhp(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); diff --git a/init/main.c b/init/main.c index bb87b789c543..f285bc53c345 100644 --- a/init/main.c +++ b/init/main.c @@ -973,7 +973,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) boot_cpu_hotplug_init(); build_all_zonelists(NULL); - page_alloc_init(); + page_alloc_init_cpuhp(); pr_notice("Kernel command line: %s\n", saved_command_line); /* parameters may set static keys */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3abc994bcfa1..1131b87586d5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6393,7 +6393,7 @@ static int page_alloc_cpu_online(unsigned int cpu) return 0; } -void __init page_alloc_init(void) +void __init page_alloc_init_cpuhp(void) { int ret; -- GitLab From 9cca18390d8d7af387c57e7d13d6a58615ece6a0 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:05 +0200 Subject: [PATCH 2233/5631] init: fold build_all_zonelists() and page_alloc_init_cpuhp() to mm_init() Both build_all_zonelists() and page_alloc_init_cpuhp() must be called after SMP setup is complete but before the page allocator is set up. Still, they both are a part of memory management initialization, so move them to mm_init(). Link: https://lkml.kernel.org/r/20230321170513.2401534-7-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- init/main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/init/main.c b/init/main.c index f285bc53c345..c240cce5bc86 100644 --- a/init/main.c +++ b/init/main.c @@ -837,6 +837,10 @@ static void __init report_meminit(void) */ static void __init mm_init(void) { + /* Initializations relying on SMP setup */ + build_all_zonelists(NULL); + page_alloc_init_cpuhp(); + /* * page_ext requires contiguous pages, * bigger than MAX_ORDER unless SPARSEMEM. @@ -972,9 +976,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ boot_cpu_hotplug_init(); - build_all_zonelists(NULL); - page_alloc_init_cpuhp(); - pr_notice("Kernel command line: %s\n", saved_command_line); /* parameters may set static keys */ jump_label_init(); -- GitLab From b7ec1bf3e7b9dd9d3335c937f5d834680d74addf Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:06 +0200 Subject: [PATCH 2234/5631] init,mm: move mm_init() to mm/mm_init.c and rename it to mm_core_init() Make mm_init() a part of mm/ codebase. mm_core_init() better describes what the function does and does not clash with mm_init() in kernel/fork.c Link: https://lkml.kernel.org/r/20230321170513.2401534-8-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 + init/main.c | 71 ++------------------------------------------ mm/mm_init.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 76 insertions(+), 69 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..6be179cec081 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -38,6 +38,7 @@ struct pt_regs; extern int sysctl_page_lock_unfairness; +void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ diff --git a/init/main.c b/init/main.c index c240cce5bc86..f1b2d8d80987 100644 --- a/init/main.c +++ b/init/main.c @@ -807,73 +807,6 @@ static inline void initcall_debug_enable(void) } #endif -/* Report memory auto-initialization states for this boot. */ -static void __init report_meminit(void) -{ - const char *stack; - - if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN)) - stack = "all(pattern)"; - else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO)) - stack = "all(zero)"; - else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)) - stack = "byref_all(zero)"; - else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF)) - stack = "byref(zero)"; - else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER)) - stack = "__user(zero)"; - else - stack = "off"; - - pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", - stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", - want_init_on_free() ? "on" : "off"); - if (want_init_on_free()) - pr_info("mem auto-init: clearing system memory may take some time...\n"); -} - -/* - * Set up kernel memory allocators - */ -static void __init mm_init(void) -{ - /* Initializations relying on SMP setup */ - build_all_zonelists(NULL); - page_alloc_init_cpuhp(); - - /* - * page_ext requires contiguous pages, - * bigger than MAX_ORDER unless SPARSEMEM. - */ - page_ext_init_flatmem(); - init_mem_debugging_and_hardening(); - kfence_alloc_pool(); - report_meminit(); - kmsan_init_shadow(); - stack_depot_early_init(); - mem_init(); - mem_init_print_info(); - kmem_cache_init(); - /* - * page_owner must be initialized after buddy is ready, and also after - * slab is ready so that stack_depot_init() works properly - */ - page_ext_init_flatmem_late(); - kmemleak_init(); - pgtable_init(); - debug_objects_mem_init(); - vmalloc_init(); - /* If no deferred init page_ext now, as vmap is fully initialized */ - if (!deferred_struct_pages) - page_ext_init(); - /* Should be run before the first non-init thread is created */ - init_espfix_bsp(); - /* Should be run after espfix64 is set up. */ - pti_init(); - kmsan_init_runtime(); - mm_cache_init(); -} - #ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, randomize_kstack_offset); @@ -997,13 +930,13 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) /* * These use large bootmem allocations and must precede - * kmem_cache_init() + * initalization of page allocator */ setup_log_buf(0); vfs_caches_init_early(); sort_main_extable(); trap_init(); - mm_init(); + mm_core_init(); poking_init(); ftrace_init(); diff --git a/mm/mm_init.c b/mm/mm_init.c index 2e60c7186132..bba73f1fb277 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -20,9 +20,15 @@ #include #include #include +#include +#include +#include +#include #include "internal.h" #include "shuffle.h" +#include + #ifdef CONFIG_DEBUG_MEMORY_INIT int __meminitdata mminit_loglevel; @@ -2524,3 +2530,70 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, } __free_pages_core(page, order); } + +/* Report memory auto-initialization states for this boot. */ +static void __init report_meminit(void) +{ + const char *stack; + + if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN)) + stack = "all(pattern)"; + else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO)) + stack = "all(zero)"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)) + stack = "byref_all(zero)"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF)) + stack = "byref(zero)"; + else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER)) + stack = "__user(zero)"; + else + stack = "off"; + + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", + stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", + want_init_on_free() ? "on" : "off"); + if (want_init_on_free()) + pr_info("mem auto-init: clearing system memory may take some time...\n"); +} + +/* + * Set up kernel memory allocators + */ +void __init mm_core_init(void) +{ + /* Initializations relying on SMP setup */ + build_all_zonelists(NULL); + page_alloc_init_cpuhp(); + + /* + * page_ext requires contiguous pages, + * bigger than MAX_ORDER unless SPARSEMEM. + */ + page_ext_init_flatmem(); + init_mem_debugging_and_hardening(); + kfence_alloc_pool(); + report_meminit(); + kmsan_init_shadow(); + stack_depot_early_init(); + mem_init(); + mem_init_print_info(); + kmem_cache_init(); + /* + * page_owner must be initialized after buddy is ready, and also after + * slab is ready so that stack_depot_init() works properly + */ + page_ext_init_flatmem_late(); + kmemleak_init(); + pgtable_init(); + debug_objects_mem_init(); + vmalloc_init(); + /* If no deferred init page_ext now, as vmap is fully initialized */ + if (!deferred_struct_pages) + page_ext_init(); + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); + /* Should be run after espfix64 is set up. */ + pti_init(); + kmsan_init_runtime(); + mm_cache_init(); +} -- GitLab From 4cd1e9edf60efb20fad35cf5e9ade7ad75b34cd1 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:07 +0200 Subject: [PATCH 2235/5631] mm: call {ptlock,pgtable}_cache_init() directly from mm_core_init() and drop pgtable_init() as it has no real value and its name is misleading. Link: https://lkml.kernel.org/r/20230321170513.2401534-9-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Cc: Sergei Shtylyov Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ------ mm/mm_init.c | 3 ++- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 6be179cec081..dfff8bcaa766 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2637,12 +2637,6 @@ static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline void pgtable_init(void) -{ - ptlock_cache_init(); - pgtable_cache_init(); -} - static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) diff --git a/mm/mm_init.c b/mm/mm_init.c index bba73f1fb277..f1475413394d 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2584,7 +2584,8 @@ void __init mm_core_init(void) */ page_ext_init_flatmem_late(); kmemleak_init(); - pgtable_init(); + ptlock_cache_init(); + pgtable_cache_init(); debug_objects_mem_init(); vmalloc_init(); /* If no deferred init page_ext now, as vmap is fully initialized */ -- GitLab From f2fc4b44ec2bb94c51c7ae1af9b1177d72705992 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:08 +0200 Subject: [PATCH 2236/5631] mm: move init_mem_debugging_and_hardening() to mm/mm_init.c init_mem_debugging_and_hardening() is only called from mm_core_init(). Move it close to the caller, make it static and rename it to mem_debugging_and_hardening_init() for consistency with surrounding convention. Link: https://lkml.kernel.org/r/20230321170513.2401534-10-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - mm/internal.h | 8 ++++ mm/mm_init.c | 91 +++++++++++++++++++++++++++++++++++++++++++- mm/page_alloc.c | 95 ---------------------------------------------- 4 files changed, 98 insertions(+), 97 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index dfff8bcaa766..0fa6a6f94eda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3251,7 +3251,6 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); diff --git a/mm/internal.h b/mm/internal.h index 22f1410a0ee3..a2934c610182 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -204,6 +204,14 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); extern char * const zone_names[MAX_NR_ZONES]; +/* perform sanity checks on struct pages being allocated or freed */ +DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); + +static inline bool is_check_pages_enabled(void) +{ + return static_branch_unlikely(&check_pages_enabled); +} + /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* diff --git a/mm/mm_init.c b/mm/mm_init.c index f1475413394d..43f6d3ed24ef 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2531,6 +2531,95 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, __free_pages_core(page, order); } +static bool _init_on_alloc_enabled_early __read_mostly + = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); +static int __init early_init_on_alloc(char *buf) +{ + + return kstrtobool(buf, &_init_on_alloc_enabled_early); +} +early_param("init_on_alloc", early_init_on_alloc); + +static bool _init_on_free_enabled_early __read_mostly + = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON); +static int __init early_init_on_free(char *buf) +{ + return kstrtobool(buf, &_init_on_free_enabled_early); +} +early_param("init_on_free", early_init_on_free); + +DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); + +/* + * Enable static keys related to various memory debugging and hardening options. + * Some override others, and depend on early params that are evaluated in the + * order of appearance. So we need to first gather the full picture of what was + * enabled, and then make decisions. + */ +static void __init mem_debugging_and_hardening_init(void) +{ + bool page_poisoning_requested = false; + bool want_check_pages = false; + +#ifdef CONFIG_PAGE_POISONING + /* + * Page poisoning is debug page alloc for some arches. If + * either of those options are enabled, enable poisoning. + */ + if (page_poisoning_enabled() || + (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && + debug_pagealloc_enabled())) { + static_branch_enable(&_page_poisoning_enabled); + page_poisoning_requested = true; + want_check_pages = true; + } +#endif + + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && + page_poisoning_requested) { + pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " + "will take precedence over init_on_alloc and init_on_free\n"); + _init_on_alloc_enabled_early = false; + _init_on_free_enabled_early = false; + } + + if (_init_on_alloc_enabled_early) { + want_check_pages = true; + static_branch_enable(&init_on_alloc); + } else { + static_branch_disable(&init_on_alloc); + } + + if (_init_on_free_enabled_early) { + want_check_pages = true; + static_branch_enable(&init_on_free); + } else { + static_branch_disable(&init_on_free); + } + + if (IS_ENABLED(CONFIG_KMSAN) && + (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); + +#ifdef CONFIG_DEBUG_PAGEALLOC + if (debug_pagealloc_enabled()) { + want_check_pages = true; + static_branch_enable(&_debug_pagealloc_enabled); + + if (debug_guardpage_minorder()) + static_branch_enable(&_debug_guardpage_enabled); + } +#endif + + /* + * Any page debugging or hardening option also enables sanity checking + * of struct pages being allocated or freed. With CONFIG_DEBUG_VM it's + * enabled already. + */ + if (!IS_ENABLED(CONFIG_DEBUG_VM) && want_check_pages) + static_branch_enable(&check_pages_enabled); +} + /* Report memory auto-initialization states for this boot. */ static void __init report_meminit(void) { @@ -2570,7 +2659,7 @@ void __init mm_core_init(void) * bigger than MAX_ORDER unless SPARSEMEM. */ page_ext_init_flatmem(); - init_mem_debugging_and_hardening(); + mem_debugging_and_hardening_init(); kfence_alloc_pool(); report_meminit(); kmsan_init_shadow(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1131b87586d5..94bf3b7b5c49 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -240,31 +240,6 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); -/* perform sanity checks on struct pages being allocated or freed */ -static DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); - -static inline bool is_check_pages_enabled(void) -{ - return static_branch_unlikely(&check_pages_enabled); -} - -static bool _init_on_alloc_enabled_early __read_mostly - = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); -static int __init early_init_on_alloc(char *buf) -{ - - return kstrtobool(buf, &_init_on_alloc_enabled_early); -} -early_param("init_on_alloc", early_init_on_alloc); - -static bool _init_on_free_enabled_early __read_mostly - = IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON); -static int __init early_init_on_free(char *buf) -{ - return kstrtobool(buf, &_init_on_free_enabled_early); -} -early_param("init_on_free", early_init_on_free); - /* * A cached value of the page's pageblock's migratetype, used when the page is * put on a pcplist. Used to avoid the pageblock migratetype lookup when @@ -798,76 +773,6 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, unsigned int order, int migratetype) {} #endif -/* - * Enable static keys related to various memory debugging and hardening options. - * Some override others, and depend on early params that are evaluated in the - * order of appearance. So we need to first gather the full picture of what was - * enabled, and then make decisions. - */ -void __init init_mem_debugging_and_hardening(void) -{ - bool page_poisoning_requested = false; - bool want_check_pages = false; - -#ifdef CONFIG_PAGE_POISONING - /* - * Page poisoning is debug page alloc for some arches. If - * either of those options are enabled, enable poisoning. - */ - if (page_poisoning_enabled() || - (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && - debug_pagealloc_enabled())) { - static_branch_enable(&_page_poisoning_enabled); - page_poisoning_requested = true; - want_check_pages = true; - } -#endif - - if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && - page_poisoning_requested) { - pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc and init_on_free\n"); - _init_on_alloc_enabled_early = false; - _init_on_free_enabled_early = false; - } - - if (_init_on_alloc_enabled_early) { - want_check_pages = true; - static_branch_enable(&init_on_alloc); - } else { - static_branch_disable(&init_on_alloc); - } - - if (_init_on_free_enabled_early) { - want_check_pages = true; - static_branch_enable(&init_on_free); - } else { - static_branch_disable(&init_on_free); - } - - if (IS_ENABLED(CONFIG_KMSAN) && - (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) - pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); - -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { - want_check_pages = true; - static_branch_enable(&_debug_pagealloc_enabled); - - if (debug_guardpage_minorder()) - static_branch_enable(&_debug_guardpage_enabled); - } -#endif - - /* - * Any page debugging or hardening option also enables sanity checking - * of struct pages being allocated or freed. With CONFIG_DEBUG_VM it's - * enabled already. - */ - if (!IS_ENABLED(CONFIG_DEBUG_VM) && want_check_pages) - static_branch_enable(&check_pages_enabled); -} - static inline void set_buddy_order(struct page *page, unsigned int order) { set_page_private(page, order); -- GitLab From de57807e6f267a658a046dbca44dc40fe806d60f Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:09 +0200 Subject: [PATCH 2237/5631] init,mm: fold late call to page_ext_init() to page_alloc_init_late() When deferred initialization of struct pages is enabled, page_ext_init() must be called after all the deferred initialization is done, but there is no point to keep it a separate call from kernel_init_freeable() right after page_alloc_init_late(). Fold the call to page_ext_init() into page_alloc_init_late() and localize deferred_struct_pages variable. Link: https://lkml.kernel.org/r/20230321170513.2401534-11-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/page_ext.h | 2 -- init/main.c | 4 ---- mm/mm_init.c | 6 +++++- 3 files changed, 5 insertions(+), 7 deletions(-) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index bc2e39090a1f..67314f648aeb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -29,8 +29,6 @@ struct page_ext_operations { bool need_shared_flags; }; -extern bool deferred_struct_pages; - #ifdef CONFIG_PAGE_EXTENSION /* diff --git a/init/main.c b/init/main.c index f1b2d8d80987..43bc4c82dc58 100644 --- a/init/main.c +++ b/init/main.c @@ -62,7 +62,6 @@ #include #include #include -#include #include #include #include @@ -1565,9 +1564,6 @@ static noinline void __init kernel_init_freeable(void) padata_init(); page_alloc_init_late(); - /* Initialize page ext after all struct pages are initialized. */ - if (deferred_struct_pages) - page_ext_init(); do_basic_setup(); diff --git a/mm/mm_init.c b/mm/mm_init.c index 43f6d3ed24ef..ff70da11e797 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -225,7 +225,7 @@ static unsigned long nr_kernel_pages __initdata; static unsigned long nr_all_pages __initdata; static unsigned long dma_reserve __initdata; -bool deferred_struct_pages __meminitdata; +static bool deferred_struct_pages __meminitdata; static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); @@ -2358,6 +2358,10 @@ void __init page_alloc_init_late(void) for_each_populated_zone(zone) set_zone_contiguous(zone); + + /* Initialize page ext after all struct pages are initialized. */ + if (deferred_struct_pages) + page_ext_init(); } #ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES -- GitLab From eb8589b4f8c107c346421881963c0ee0b8367c2c Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:10 +0200 Subject: [PATCH 2238/5631] mm: move mem_init_print_info() to mm_init.c mem_init_print_info() is only called from mm_core_init(). Move it close to the caller and make it static. Link: https://lkml.kernel.org/r/20230321170513.2401534-12-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/mm.h | 1 - mm/internal.h | 1 + mm/mm_init.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++ mm/page_alloc.c | 53 ---------------------------------------------- 4 files changed, 54 insertions(+), 54 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 0fa6a6f94eda..c3abad7e6ccb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2780,7 +2780,6 @@ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); -extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); diff --git a/mm/internal.h b/mm/internal.h index a2934c610182..7cea7d833c50 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -201,6 +201,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ +#define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; diff --git a/mm/mm_init.c b/mm/mm_init.c index ff70da11e797..8adadf51bbd2 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -24,6 +24,8 @@ #include #include #include +#include +#include #include "internal.h" #include "shuffle.h" @@ -2649,6 +2651,57 @@ static void __init report_meminit(void) pr_info("mem auto-init: clearing system memory may take some time...\n"); } +static void __init mem_init_print_info(void) +{ + unsigned long physpages, codesize, datasize, rosize, bss_size; + unsigned long init_code_size, init_data_size; + + physpages = get_num_physpages(); + codesize = _etext - _stext; + datasize = _edata - _sdata; + rosize = __end_rodata - __start_rodata; + bss_size = __bss_stop - __bss_start; + init_data_size = __init_end - __init_begin; + init_code_size = _einittext - _sinittext; + + /* + * Detect special cases and adjust section sizes accordingly: + * 1) .init.* may be embedded into .data sections + * 2) .init.text.* may be out of [__init_begin, __init_end], + * please refer to arch/tile/kernel/vmlinux.lds.S. + * 3) .rodata.* may be embedded into .text or .data sections. + */ +#define adj_init_size(start, end, size, pos, adj) \ + do { \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ + size -= adj; \ + } while (0) + + adj_init_size(__init_begin, __init_end, init_data_size, + _sinittext, init_code_size); + adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); + adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); + adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); + adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); + +#undef adj_init_size + + pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" +#ifdef CONFIG_HIGHMEM + ", %luK highmem" +#endif + ")\n", + K(nr_free_pages()), K(physpages), + codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, + (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, + K(physpages - totalram_pages() - totalcma_pages), + K(totalcma_pages) +#ifdef CONFIG_HIGHMEM + , K(totalhigh_pages()) +#endif + ); +} + /* * Set up kernel memory allocators */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 94bf3b7b5c49..d0eb280ec7e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5246,8 +5246,6 @@ static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask return !node_isset(nid, *nodemask); } -#define K(x) ((x) << (PAGE_SHIFT-10)) - static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { @@ -6207,57 +6205,6 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char return pages; } -void __init mem_init_print_info(void) -{ - unsigned long physpages, codesize, datasize, rosize, bss_size; - unsigned long init_code_size, init_data_size; - - physpages = get_num_physpages(); - codesize = _etext - _stext; - datasize = _edata - _sdata; - rosize = __end_rodata - __start_rodata; - bss_size = __bss_stop - __bss_start; - init_data_size = __init_end - __init_begin; - init_code_size = _einittext - _sinittext; - - /* - * Detect special cases and adjust section sizes accordingly: - * 1) .init.* may be embedded into .data sections - * 2) .init.text.* may be out of [__init_begin, __init_end], - * please refer to arch/tile/kernel/vmlinux.lds.S. - * 3) .rodata.* may be embedded into .text or .data sections. - */ -#define adj_init_size(start, end, size, pos, adj) \ - do { \ - if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ - size -= adj; \ - } while (0) - - adj_init_size(__init_begin, __init_end, init_data_size, - _sinittext, init_code_size); - adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size); - adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size); - adj_init_size(_stext, _etext, codesize, __start_rodata, rosize); - adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize); - -#undef adj_init_size - - pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved" -#ifdef CONFIG_HIGHMEM - ", %luK highmem" -#endif - ")\n", - K(nr_free_pages()), K(physpages), - codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K, - (init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K, - K(physpages - totalram_pages() - totalcma_pages), - K(totalcma_pages) -#ifdef CONFIG_HIGHMEM - , K(totalhigh_pages()) -#endif - ); -} - static int page_alloc_cpu_dead(unsigned int cpu) { struct zone *zone; -- GitLab From d5d2c02a4980c2e22037679457bf2d921b86a503 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:11 +0200 Subject: [PATCH 2239/5631] mm: move kmem_cache_init() declaration to mm/slab.h kmem_cache_init() is called only from mm_core_init(), there is no need to declare it in include/linux/slab.h Move kmem_cache_init() declaration to mm/slab.h Link: https://lkml.kernel.org/r/20230321170513.2401534-13-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/slab.h | 1 - mm/mm_init.c | 1 + mm/slab.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/linux/slab.h b/include/linux/slab.h index aa4575ef2965..f8b1d63c63a3 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -167,7 +167,6 @@ struct mem_cgroup; /* * struct kmem_cache related prototypes */ -void __init kmem_cache_init(void); bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, diff --git a/mm/mm_init.c b/mm/mm_init.c index 8adadf51bbd2..53fb8e9d1e3b 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -27,6 +27,7 @@ #include #include #include "internal.h" +#include "slab.h" #include "shuffle.h" #include diff --git a/mm/slab.h b/mm/slab.h index 43966aa5fadf..3f8df2244f5a 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -4,6 +4,7 @@ /* * Internal slab definitions */ +void __init kmem_cache_init(void); /* Reuses the bits in struct page */ struct slab { -- GitLab From b671491199acd3609f87754d268f2f5cb10de18d Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:12 +0200 Subject: [PATCH 2240/5631] mm: move vmalloc_init() declaration to mm/internal.h vmalloc_init() is called only from mm_core_init(), there is no need to declare it in include/linux/vmalloc.h Move vmalloc_init() declaration to mm/internal.h Link: https://lkml.kernel.org/r/20230321170513.2401534-14-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Reviewed-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- include/linux/vmalloc.h | 4 ---- mm/internal.h | 5 +++++ 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 69250efa03d1..351fc7697214 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -131,12 +131,8 @@ extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -extern void __init vmalloc_init(void); extern unsigned long vmalloc_nr_pages(void); #else -static inline void vmalloc_init(void) -{ -} static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif diff --git a/mm/internal.h b/mm/internal.h index 7cea7d833c50..82ba61d0ed6a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -879,9 +879,14 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, * mm/vmalloc.c */ #ifdef CONFIG_MMU +void __init vmalloc_init(void); int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else +static inline void vmalloc_init(void) +{ +} + static inline int vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) -- GitLab From c9bb52738b39fabc8b6b9446f0d194eedb3e5a10 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Tue, 21 Mar 2023 19:05:13 +0200 Subject: [PATCH 2241/5631] MAINTAINERS: extend memblock entry to include MM initialization and add mm/mm_init.c to memblock entry in MAINTAINERS Link: https://lkml.kernel.org/r/20230321170513.2401534-15-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Doug Berger Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Thomas Bogendoerfer Signed-off-by: Andrew Morton --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index ad69fe845e6d..1b48ddff4159 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13368,13 +13368,14 @@ F: arch/powerpc/include/asm/membarrier.h F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c -MEMBLOCK +MEMBLOCK AND MEMORY MANAGEMENT INITIALIZATION M: Mike Rapoport L: linux-mm@kvack.org S: Maintained F: Documentation/core-api/boot-time-mm.rst F: include/linux/memblock.h F: mm/memblock.c +F: mm/mm_init.c F: tools/testing/memblock/ MEMORY CONTROLLER DRIVERS -- GitLab From bd23024b9774e681cbe6cc3afcb24244dfcb2390 Mon Sep 17 00:00:00 2001 From: Tomas Mudrunka Date: Tue, 21 Mar 2023 11:34:30 +0100 Subject: [PATCH 2242/5631] mm/memtest: add results of early memtest to /proc/meminfo Currently the memtest results were only presented in dmesg. When running a large fleet of devices without ECC RAM it's currently not easy to do bulk monitoring for memory corruption. You have to parse dmesg, but that's a ring buffer so the error might disappear after some time. In general I do not consider dmesg to be a great API to query RAM status. In several companies I've seen such errors remain undetected and cause issues for way too long. So I think it makes sense to provide a monitoring API, so that we can safely detect and act upon them. This adds /proc/meminfo entry which can be easily used by scripts. Link: https://lkml.kernel.org/r/20230321103430.7130-1-tomas.mudrunka@gmail.com Signed-off-by: Tomas Mudrunka Cc: Jonathan Corbet Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- Documentation/filesystems/proc.rst | 8 ++++++++ fs/proc/meminfo.c | 13 +++++++++++++ include/linux/memblock.h | 2 ++ mm/memtest.c | 6 ++++++ 4 files changed, 29 insertions(+) diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 9d5fd9424e8b..8740362f31c6 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -996,6 +996,7 @@ Example output. You may not have all of these fields. VmallocUsed: 40444 kB VmallocChunk: 0 kB Percpu: 29312 kB + EarlyMemtestBad: 0 kB HardwareCorrupted: 0 kB AnonHugePages: 4149248 kB ShmemHugePages: 0 kB @@ -1146,6 +1147,13 @@ VmallocChunk Percpu Memory allocated to the percpu allocator used to back percpu allocations. This stat excludes the cost of metadata. +EarlyMemtestBad + The amount of RAM/memory in kB, that was identified as corrupted + by early memtest. If memtest was not run, this field will not + be displayed at all. Size is never rounded down to 0 kB. + That means if 0 kB is reported, you can safely assume + there was at least one pass of memtest and none of the passes + found a single faulty byte of RAM. HardwareCorrupted The amount of RAM/memory in KB, the kernel identifies as corrupted. diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 440960110a42..b43d0bd42762 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -131,6 +132,18 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "VmallocChunk: ", 0ul); show_val_kb(m, "Percpu: ", pcpu_nr_pages()); +#ifdef CONFIG_MEMTEST + if (early_memtest_done) { + unsigned long early_memtest_bad_size_kb; + + early_memtest_bad_size_kb = early_memtest_bad_size>>10; + if (early_memtest_bad_size && !early_memtest_bad_size_kb) + early_memtest_bad_size_kb = 1; + /* When 0 is reported, it means there actually was a successful test */ + seq_printf(m, "EarlyMemtestBad: %5lu kB\n", early_memtest_bad_size_kb); + } +#endif + #ifdef CONFIG_MEMORY_FAILURE seq_printf(m, "HardwareCorrupted: %5lu kB\n", atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a32..f82ee3fac1cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -597,6 +597,8 @@ extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif #ifdef CONFIG_MEMTEST +extern phys_addr_t early_memtest_bad_size; /* Size of faulty ram found by memtest */ +extern bool early_memtest_done; /* Was early memtest done? */ extern void early_memtest(phys_addr_t start, phys_addr_t end); #else static inline void early_memtest(phys_addr_t start, phys_addr_t end) diff --git a/mm/memtest.c b/mm/memtest.c index f53ace709ccd..57149dfee438 100644 --- a/mm/memtest.c +++ b/mm/memtest.c @@ -4,6 +4,9 @@ #include #include +bool early_memtest_done; +phys_addr_t early_memtest_bad_size; + static u64 patterns[] __initdata = { /* The first entry has to be 0 to leave memtest with zeroed memory */ 0, @@ -30,6 +33,7 @@ static void __init reserve_bad_mem(u64 pattern, phys_addr_t start_bad, phys_addr pr_info(" %016llx bad mem addr %pa - %pa reserved\n", cpu_to_be64(pattern), &start_bad, &end_bad); memblock_reserve(start_bad, end_bad - start_bad); + early_memtest_bad_size += (end_bad - start_bad); } static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size) @@ -61,6 +65,8 @@ static void __init memtest(u64 pattern, phys_addr_t start_phys, phys_addr_t size } if (start_bad) reserve_bad_mem(pattern, start_bad, last_bad + incr); + + early_memtest_done = true; } static void __init do_one_pass(u64 pattern, phys_addr_t start, phys_addr_t end) -- GitLab From 28d8b812e97b31231e95864f36a6b32f4b307daa Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 12 Mar 2023 23:40:13 +0000 Subject: [PATCH 2243/5631] mm: remove unused vmf_insert_mixed_prot() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Remove drm/ttm-specific mm changes". Functionality was added specifically for the DRM TTM driver to support mapping memory for VM_MIXEDMAP VMAs with customised protection flags, however this has now been rolled back as issues were found with this approach. This series removes the mm changes too, retaining some of the useful comments. This patch (of 3): The sole user of vmf_insert_mixed_prot(), the drm ttm module, stopped using this in commit f91142c62161 ("drm/ttm: nuke VM_MIXEDMAP on BO mappings v3") citing use of VM_MIXEDMAP in this case being terribly broken. Remove this now-dead code and references to it, but retain the useful description of the prot != vma->vm_page_prot case, moving it to vmf_insert_pfn_prot() instead. Link: https://lkml.kernel.org/r/cover.1678661628.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/a069644388e6f1593a7020d15840e6fc9f39bcaf.1678661628.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: Christian König Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Thomas Hellström Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Marcelo Tosatti Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 -- include/linux/mm_types.h | 7 +---- mm/memory.c | 57 +++++++++++++--------------------------- 3 files changed, 19 insertions(+), 47 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index c3abad7e6ccb..55d02356146c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3179,8 +3179,6 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); -vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..651a5c256732 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -485,12 +485,7 @@ struct vm_area_struct { within vm_mm. */ struct mm_struct *vm_mm; /* The address space we belong to. */ - - /* - * Access permissions of this VMA. - * See vmf_insert_mixed_prot() for discussion. - */ - pgprot_t vm_page_prot; + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. diff --git a/mm/memory.c b/mm/memory.c index 0ee13d3de88c..7716f2cc4b68 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2165,8 +2165,20 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * - * See vmf_insert_mixed_prot() for a discussion of the implication of using - * a value of @pgprot different from that of @vma->vm_page_prot. + * pgprot typically only differs from @vma->vm_page_prot when drivers set + * caching- and encryption bits different than those of @vma->vm_page_prot, + * because the caching- or encryption mode may not be known at mmap() time. + * + * This is ok as long as @vma->vm_page_prot is not used by the core vm + * to set caching and encryption bits for those vmas (except for COW pages). + * This is ensured by core vm only modifying these page table entries using + * functions that don't touch caching- or encryption bits, using pte_modify() + * if needed. (See for example mprotect()). + * + * Also when new page-table entries are created, this is only done using the + * fault() callback, and never using the value of vma->vm_page_prot, + * except for page-table entries that point to anonymous pages as the result + * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. @@ -2241,9 +2253,9 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn, pgprot_t pgprot, - bool mkwrite) + unsigned long addr, pfn_t pfn, bool mkwrite) { + pgprot_t pgprot = vma->vm_page_prot; int err; BUG_ON(!vm_mixed_ok(vma, pfn)); @@ -2286,43 +2298,10 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -/** - * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * @pgprot: pgprot flags for the inserted page - * - * This is exactly like vmf_insert_mixed(), except that it allows drivers - * to override pgprot on a per-page basis. - * - * Typically this function should be used by drivers to set caching- and - * encryption bits different than those of @vma->vm_page_prot, because - * the caching- or encryption mode may not be known at mmap() time. - * This is ok as long as @vma->vm_page_prot is not used by the core vm - * to set caching and encryption bits for those vmas (except for COW pages). - * This is ensured by core vm only modifying these page table entries using - * functions that don't touch caching- or encryption bits, using pte_modify() - * if needed. (See for example mprotect()). - * Also when new page-table entries are created, this is only done using the - * fault() callback, and never using the value of vma->vm_page_prot, - * except for page-table entries that point to anonymous pages as the result - * of COW. - * - * Context: Process context. May allocate using %GFP_KERNEL. - * Return: vm_fault_t value. - */ -vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t pgprot) -{ - return __vm_insert_mixed(vma, addr, pfn, pgprot, false); -} -EXPORT_SYMBOL(vmf_insert_mixed_prot); - vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { - return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); + return __vm_insert_mixed(vma, addr, pfn, false); } EXPORT_SYMBOL(vmf_insert_mixed); @@ -2334,7 +2313,7 @@ EXPORT_SYMBOL(vmf_insert_mixed); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { - return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); + return __vm_insert_mixed(vma, addr, pfn, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); -- GitLab From 7b806d229ef151c2997c041b791dfa89593e0e1b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 12 Mar 2023 23:40:14 +0000 Subject: [PATCH 2244/5631] mm: remove vmf_insert_pfn_xxx_prot() for huge page-table entries MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This functionality's sole user, the drm ttm module, removed support for it in commit 0d979509539e ("drm/ttm: remove ttm_bo_vm_insert_huge()") as the whole approach is currently unworkable without a PMD/PUD special bit and updates to GUP. Link: https://lkml.kernel.org/r/604c2ad79659d4b8a6e3e1611c6219d5d3233988.1678661628.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: Christian König Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Thomas Hellström Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Marcelo Tosatti Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 39 ++------------------------------------- mm/huge_memory.c | 31 +++++++++++++------------------ 2 files changed, 15 insertions(+), 55 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 9a3a3af2dd80..20284387b841 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,44 +39,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); -/** - * vmf_insert_pfn_pmd - insert a pmd size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); - -/** - * vmf_insert_pfn_pud - insert a pud size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1df386d13d24..81a5689806af 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -885,23 +885,20 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, } /** - * vmf_insert_pfn_pmd_prot - insert a pmd size pfn + * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert - * @pgprot: page protection to use * @write: whether it's a write fault * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info and - * also consult the vmf_insert_mixed_prot() documentation when - * @pgprot != @vmf->vma->vm_page_prot. + * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write) +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) { unsigned long addr = vmf->address & PMD_MASK; struct vm_area_struct *vma = vmf->vma; + pgprot_t pgprot = vma->vm_page_prot; pgtable_t pgtable = NULL; /* @@ -929,7 +926,7 @@ vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } -EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd_prot); +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) @@ -940,9 +937,10 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) } static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, pfn_t pfn, pgprot_t prot, bool write) + pud_t *pud, pfn_t pfn, bool write) { struct mm_struct *mm = vma->vm_mm; + pgprot_t prot = vma->vm_page_prot; pud_t entry; spinlock_t *ptl; @@ -976,23 +974,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, } /** - * vmf_insert_pfn_pud_prot - insert a pud size pfn + * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert - * @pgprot: page protection to use * @write: whether it's a write fault * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info and - * also consult the vmf_insert_mixed_prot() documentation when - * @pgprot != @vmf->vma->vm_page_prot. + * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write) +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) { unsigned long addr = vmf->address & PUD_MASK; struct vm_area_struct *vma = vmf->vma; + pgprot_t pgprot = vma->vm_page_prot; /* * If we had pud_special, we could avoid all these restrictions, @@ -1010,10 +1005,10 @@ vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, track_pfn_insert(vma, &pgprot, pfn); - insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write); + insert_pfn_pud(vma, addr, vmf->pud, pfn, write); return VM_FAULT_NOPAGE; } -EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud_prot); +EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, -- GitLab From 4a06f6f3d395d15eb285606f28b74ce5dbc77e52 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 12 Mar 2023 23:40:15 +0000 Subject: [PATCH 2245/5631] drm/ttm: remove comment referencing now-removed vmf_insert_mixed_prot() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function no longer exists, however the prot != vma->vm_page_prot case discussion has been retained and moved to vmf_insert_pfn_prot() so refer to this instead. Link: https://lkml.kernel.org/r/db403b3622b94a87bd93528cc1d6b44ae88adcdd.1678661628.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Christian König Cc: Dan Williams Cc: Jason Gunthorpe Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Thomas Hellström Cc: Aaron Tomlin Cc: Christoph Lameter Cc: Frederic Weisbecker Cc: Heiko Carstens Cc: Huacai Chen Cc: Marcelo Tosatti Cc: Peter Xu Cc: "Russell King (Oracle)" Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- drivers/gpu/drm/ttm/ttm_bo_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index ca7744b852f5..5df3edadb808 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -254,7 +254,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf, * encryption bits. This is because the exact location of the * data may not be known at mmap() time and may also change * at arbitrary times while the data is mmap'ed. - * See vmf_insert_mixed_prot() for a discussion. + * See vmf_insert_pfn_prot() for a discussion. */ ret = vmf_insert_pfn_prot(vma, address, pfn, prot); -- GitLab From 3f6dac0fd1b83178137e7b4e722d8f29612cbec1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 21 Mar 2023 03:24:15 +0300 Subject: [PATCH 2246/5631] mm/page_alloc: make deferred page init free pages in MAX_ORDER blocks Normal page init path frees pages during the boot in MAX_ORDER chunks, but deferred page init path does it in pageblock blocks. Change deferred page init path to work in MAX_ORDER blocks. For cases when MAX_ORDER is larger than pageblock, set migrate type to MIGRATE_MOVABLE for all pageblocks covered by the page. Link: https://lkml.kernel.org/r/20230321002415.20843-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Vlastimil Babka Acked-by: David Hildenbrand Acked-by: Mel Gorman Acked-by: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 2 ++ mm/mm_init.c | 19 ++++++++++--------- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2d3d78d01283..2d22e47dc1eb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -32,6 +32,8 @@ #endif #define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) + /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should diff --git a/mm/mm_init.c b/mm/mm_init.c index 53fb8e9d1e3b..c88fbe74137c 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1951,9 +1951,10 @@ static void __init deferred_free_range(unsigned long pfn, page = pfn_to_page(pfn); /* Free a large naturally-aligned chunk if possible */ - if (nr_pages == pageblock_nr_pages && pageblock_aligned(pfn)) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_core(page, pageblock_order); + if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) { + for (i = 0; i < nr_pages; i += pageblock_nr_pages) + set_pageblock_migratetype(page + i, MIGRATE_MOVABLE); + __free_pages_core(page, MAX_ORDER); return; } @@ -1977,19 +1978,19 @@ static inline void __init pgdat_init_report_one_done(void) /* * Returns true if page needs to be initialized or freed to buddy allocator. * - * We check if a current large page is valid by only checking the validity + * We check if a current MAX_ORDER block is valid by only checking the validity * of the head pfn. */ static inline bool __init deferred_pfn_valid(unsigned long pfn) { - if (pageblock_aligned(pfn) && !pfn_valid(pfn)) + if (IS_MAX_ORDER_ALIGNED(pfn) && !pfn_valid(pfn)) return false; return true; } /* * Free pages to buddy allocator. Try to free aligned pages in - * pageblock_nr_pages sizes. + * MAX_ORDER_NR_PAGES sizes. */ static void __init deferred_free_pages(unsigned long pfn, unsigned long end_pfn) @@ -2000,7 +2001,7 @@ static void __init deferred_free_pages(unsigned long pfn, if (!deferred_pfn_valid(pfn)) { deferred_free_range(pfn - nr_free, nr_free); nr_free = 0; - } else if (pageblock_aligned(pfn)) { + } else if (IS_MAX_ORDER_ALIGNED(pfn)) { deferred_free_range(pfn - nr_free, nr_free); nr_free = 1; } else { @@ -2013,7 +2014,7 @@ static void __init deferred_free_pages(unsigned long pfn, /* * Initialize struct pages. We minimize pfn page lookups and scheduler checks - * by performing it only once every pageblock_nr_pages. + * by performing it only once every MAX_ORDER_NR_PAGES. * Return number of pages initialized. */ static unsigned long __init deferred_init_pages(struct zone *zone, @@ -2029,7 +2030,7 @@ static unsigned long __init deferred_init_pages(struct zone *zone, if (!deferred_pfn_valid(pfn)) { page = NULL; continue; - } else if (!page || pageblock_aligned(pfn)) { + } else if (!page || IS_MAX_ORDER_ALIGNED(pfn)) { page = pfn_to_page(pfn); } else { page++; -- GitLab From 2e1c0170771e6bf31bc785ea43a44e6e85e36268 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:01 +0000 Subject: [PATCH 2247/5631] fs/proc/kcore: avoid bounce buffer for ktext data Patch series "convert read_kcore(), vread() to use iterators", v8. While reviewing Baoquan's recent changes to permit vread() access to vm_map_ram regions of vmalloc allocations, Willy pointed out [1] that it would be nice to refactor vread() as a whole, since its only user is read_kcore() and the existing form of vread() necessitates the use of a bounce buffer. This patch series does exactly that, as well as adjusting how we read the kernel text section to avoid the use of a bounce buffer in this case as well. This has been tested against the test case which motivated Baoquan's changes in the first place [2] which continues to function correctly, as do the vmalloc self tests. This patch (of 4): Commit df04abfd181a ("fs/proc/kcore.c: Add bounce buffer for ktext data") introduced the use of a bounce buffer to retrieve kernel text data for /proc/kcore in order to avoid failures arising from hardened user copies enabled by CONFIG_HARDENED_USERCOPY in check_kernel_text_object(). We can avoid doing this if instead of copy_to_user() we use _copy_to_user() which bypasses the hardening check. This is more efficient than using a bounce buffer and simplifies the code. We do so as part an overall effort to eliminate bounce buffer usage in the function with an eye to converting it an iterator read. Link: https://lkml.kernel.org/r/cover.1679566220.git.lstoakes@gmail.com Link: https://lore.kernel.org/all/Y8WfDSRkc%2FOHP3oD@casper.infradead.org/ [1] Link: https://lore.kernel.org/all/87ilk6gos2.fsf@oracle.com/T/#u [2] Link: https://lkml.kernel.org/r/fd39b0bfa7edc76d360def7d034baaee71d90158.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: David Hildenbrand Reviewed-by: Baoquan He Cc: Alexander Viro Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- fs/proc/kcore.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 71157ee35c1a..556f310d6aa4 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -541,19 +541,12 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) case KCORE_VMEMMAP: case KCORE_TEXT: /* - * Using bounce buffer to bypass the - * hardened user copy kernel text checks. + * We use _copy_to_user() to bypass usermode hardening + * which would otherwise prevent this operation. */ - if (copy_from_kernel_nofault(buf, (void *)start, tsz)) { - if (clear_user(buffer, tsz)) { - ret = -EFAULT; - goto out; - } - } else { - if (copy_to_user(buffer, buf, tsz)) { - ret = -EFAULT; - goto out; - } + if (_copy_to_user(buffer, (char *)start, tsz)) { + ret = -EFAULT; + goto out; } break; default: -- GitLab From 46c0d6d0904a10785faabee53fe53ee1aa718fea Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:02 +0000 Subject: [PATCH 2248/5631] fs/proc/kcore: convert read_kcore() to read_kcore_iter() For the time being we still use a bounce buffer for vread(), however in the next patch we will convert this to interact directly with the iterator and eliminate the bounce buffer altogether. Link: https://lkml.kernel.org/r/ebe12c8d70eebd71f487d80095605f3ad0d1489c.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: David Hildenbrand Reviewed-by: Baoquan He Cc: Alexander Viro Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- fs/proc/kcore.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 556f310d6aa4..08b795fd80b4 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include #include @@ -308,9 +308,12 @@ static void append_kcore_note(char *notes, size_t *i, const char *name, } static ssize_t -read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) +read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) { + struct file *file = iocb->ki_filp; char *buf = file->private_data; + loff_t *fpos = &iocb->ki_pos; + size_t phdrs_offset, notes_offset, data_offset; size_t page_offline_frozen = 1; size_t phdrs_len, notes_len; @@ -318,6 +321,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) size_t tsz; int nphdr; unsigned long start; + size_t buflen = iov_iter_count(iter); size_t orig_buflen = buflen; int ret = 0; @@ -356,12 +360,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) }; tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos); - if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) { + if (copy_to_iter((char *)&ehdr + *fpos, tsz, iter) != tsz) { ret = -EFAULT; goto out; } - buffer += tsz; buflen -= tsz; *fpos += tsz; } @@ -398,15 +401,14 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) } tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos); - if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset, - tsz)) { + if (copy_to_iter((char *)phdrs + *fpos - phdrs_offset, tsz, + iter) != tsz) { kfree(phdrs); ret = -EFAULT; goto out; } kfree(phdrs); - buffer += tsz; buflen -= tsz; *fpos += tsz; } @@ -448,14 +450,13 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) min(vmcoreinfo_size, notes_len - i)); tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos); - if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) { + if (copy_to_iter(notes + *fpos - notes_offset, tsz, iter) != tsz) { kfree(notes); ret = -EFAULT; goto out; } kfree(notes); - buffer += tsz; buflen -= tsz; *fpos += tsz; } @@ -497,7 +498,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) } if (!m) { - if (clear_user(buffer, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -508,14 +509,14 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) case KCORE_VMALLOC: vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ - if (copy_to_user(buffer, buf, tsz)) { + if (copy_to_iter(buf, tsz, iter) != tsz) { ret = -EFAULT; goto out; } break; case KCORE_USER: /* User page is handled prior to normal kernel page: */ - if (copy_to_user(buffer, (char *)start, tsz)) { + if (copy_to_iter((char *)start, tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -531,7 +532,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) */ if (!page || PageOffline(page) || is_page_hwpoison(page) || !pfn_is_ram(pfn)) { - if (clear_user(buffer, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -541,17 +542,17 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) case KCORE_VMEMMAP: case KCORE_TEXT: /* - * We use _copy_to_user() to bypass usermode hardening + * We use _copy_to_iter() to bypass usermode hardening * which would otherwise prevent this operation. */ - if (_copy_to_user(buffer, (char *)start, tsz)) { + if (_copy_to_iter((char *)start, tsz, iter) != tsz) { ret = -EFAULT; goto out; } break; default: pr_warn_once("Unhandled KCORE type: %d\n", m->type); - if (clear_user(buffer, tsz)) { + if (iov_iter_zero(tsz, iter) != tsz) { ret = -EFAULT; goto out; } @@ -559,7 +560,6 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) skip: buflen -= tsz; *fpos += tsz; - buffer += tsz; start += tsz; tsz = (buflen > PAGE_SIZE ? PAGE_SIZE : buflen); } @@ -603,7 +603,7 @@ static int release_kcore(struct inode *inode, struct file *file) } static const struct proc_ops kcore_proc_ops = { - .proc_read = read_kcore, + .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, .proc_release = release_kcore, .proc_lseek = default_llseek, -- GitLab From 4f80818b4a58c9458dce0df7cce9abe107da445e Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:03 +0000 Subject: [PATCH 2249/5631] iov_iter: add copy_page_to_iter_nofault() Provide a means to copy a page to user space from an iterator, aborting if a page fault would occur. This supports compound pages, but may be passed a tail page with an offset extending further into the compound page, so we cannot pass a folio. This allows for this function to be called from atomic context and _try_ to user pages if they are faulted in, aborting if not. The function does not use _copy_to_iter() in order to not specify might_fault(), this is similar to copy_page_from_iter_atomic(). This is being added in order that an iteratable form of vread() can be implemented while holding spinlocks. Link: https://lkml.kernel.org/r/19734729defb0f498a76bdec1bef3ac48a3af3e8.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Baoquan He Cc: Alexander Viro Cc: David Hildenbrand Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- include/linux/uio.h | 2 ++ lib/iov_iter.c | 48 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) diff --git a/include/linux/uio.h b/include/linux/uio.h index 27e3fd942960..29eb18bb6feb 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -173,6 +173,8 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, { return copy_page_to_iter(&folio->page, offset, bytes, i); } +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 274014e4eafe..34dd6bdf2fba 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -172,6 +172,18 @@ static int copyout(void __user *to, const void *from, size_t n) return n; } +static int copyout_nofault(void __user *to, const void *from, size_t n) +{ + long res; + + if (should_fail_usercopy()) + return n; + + res = copy_to_user_nofault(to, from, n); + + return res < 0 ? n : res; +} + static int copyin(void *to, const void __user *from, size_t n) { size_t res = n; @@ -734,6 +746,42 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, } EXPORT_SYMBOL(copy_page_to_iter); +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, + struct iov_iter *i) +{ + size_t res = 0; + + if (!page_copy_sane(page, offset, bytes)) + return 0; + if (WARN_ON_ONCE(i->data_source)) + return 0; + if (unlikely(iov_iter_is_pipe(i))) + return copy_page_to_iter_pipe(page, offset, bytes, i); + page += offset / PAGE_SIZE; // first subpage + offset %= PAGE_SIZE; + while (1) { + void *kaddr = kmap_local_page(page); + size_t n = min(bytes, (size_t)PAGE_SIZE - offset); + + iterate_and_advance(i, n, base, len, off, + copyout_nofault(base, kaddr + offset + off, len), + memcpy(base, kaddr + offset + off, len) + ) + kunmap_local(kaddr); + res += n; + bytes -= n; + if (!bytes || !n) + break; + offset += n; + if (offset == PAGE_SIZE) { + page++; + offset = 0; + } + } + return res; +} +EXPORT_SYMBOL(copy_page_to_iter_nofault); + size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { -- GitLab From 4c91c07c93bbbdd7f2d9de2beb7ee5c2a48ad8e7 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 18:57:04 +0000 Subject: [PATCH 2250/5631] mm: vmalloc: convert vread() to vread_iter() Having previously laid the foundation for converting vread() to an iterator function, pull the trigger and do so. This patch attempts to provide minimal refactoring and to reflect the existing logic as best we can, for example we continue to zero portions of memory not read, as before. Overall, there should be no functional difference other than a performance improvement in /proc/kcore access to vmalloc regions. Now we have eliminated the need for a bounce buffer in read_kcore_iter(), we dispense with it, and try to write to user memory optimistically but with faults disabled via copy_page_to_iter_nofault(). We already have preemption disabled by holding a spin lock. We continue faulting in until the operation is complete. Additionally, we must account for the fact that at any point a copy may fail (most likely due to a fault not being able to occur), we exit indicating fewer bytes retrieved than expected. [sfr@canb.auug.org.au: fix sparc64 warning] Link: https://lkml.kernel.org/r/20230320144721.663280c3@canb.auug.org.au [lstoakes@gmail.com: redo Stephen's sparc build fix] Link: https://lkml.kernel.org/r/8506cbc667c39205e65a323f750ff9c11a463798.1679566220.git.lstoakes@gmail.com [akpm@linux-foundation.org: unbreak uio.h includes] Link: https://lkml.kernel.org/r/941f88bc5ab928e6656e1e2593b91bf0f8c81e1b.1679511146.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Signed-off-by: Stephen Rothwell Reviewed-by: Baoquan He Cc: Alexander Viro Cc: David Hildenbrand Cc: Jens Axboe Cc: Jiri Olsa Cc: Liu Shixin Cc: Matthew Wilcox (Oracle) Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- fs/proc/kcore.c | 44 ++++---- include/linux/vmalloc.h | 3 +- mm/nommu.c | 10 +- mm/vmalloc.c | 235 +++++++++++++++++++++++++--------------- 4 files changed, 177 insertions(+), 115 deletions(-) diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 08b795fd80b4..25b44b303b35 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -307,13 +307,9 @@ static void append_kcore_note(char *notes, size_t *i, const char *name, *i = ALIGN(*i + descsz, 4); } -static ssize_t -read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) +static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) { - struct file *file = iocb->ki_filp; - char *buf = file->private_data; loff_t *fpos = &iocb->ki_pos; - size_t phdrs_offset, notes_offset, data_offset; size_t page_offline_frozen = 1; size_t phdrs_len, notes_len; @@ -507,13 +503,30 @@ read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter) switch (m->type) { case KCORE_VMALLOC: - vread(buf, (char *)start, tsz); - /* we have to zero-fill user buffer even if no read */ - if (copy_to_iter(buf, tsz, iter) != tsz) { - ret = -EFAULT; - goto out; + { + const char *src = (char *)start; + size_t read = 0, left = tsz; + + /* + * vmalloc uses spinlocks, so we optimistically try to + * read memory. If this fails, fault pages in and try + * again until we are done. + */ + while (true) { + read += vread_iter(iter, src, left); + if (read == tsz) + break; + + src += read; + left -= read; + + if (fault_in_iov_iter_writeable(iter, left)) { + ret = -EFAULT; + goto out; + } } break; + } case KCORE_USER: /* User page is handled prior to normal kernel page: */ if (copy_to_iter((char *)start, tsz, iter) != tsz) { @@ -582,10 +595,6 @@ static int open_kcore(struct inode *inode, struct file *filp) if (ret) return ret; - filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!filp->private_data) - return -ENOMEM; - if (kcore_need_update) kcore_update_ram(); if (i_size_read(inode) != proc_root_kcore->size) { @@ -596,16 +605,9 @@ static int open_kcore(struct inode *inode, struct file *filp) return 0; } -static int release_kcore(struct inode *inode, struct file *file) -{ - kfree(file->private_data); - return 0; -} - static const struct proc_ops kcore_proc_ops = { .proc_read_iter = read_kcore_iter, .proc_open = open_kcore, - .proc_release = release_kcore, .proc_lseek = default_llseek, }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 351fc7697214..c720be70c8dd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,6 +14,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ +struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ @@ -247,7 +248,7 @@ static inline void set_vm_flush_reset_perms(void *addr) #endif /* for /proc/kcore */ -extern long vread(char *buf, char *addr, unsigned long count); +extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. diff --git a/mm/nommu.c b/mm/nommu.c index 57ba243c6a37..f670d9979a26 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -36,6 +36,7 @@ #include #include +#include #include #include #include @@ -198,14 +199,13 @@ unsigned long vmalloc_to_pfn(const void *addr) } EXPORT_SYMBOL(vmalloc_to_pfn); -long vread(char *buf, char *addr, unsigned long count) +long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { /* Don't allow overflow */ - if ((unsigned long) buf + count < count) - count = -(unsigned long) buf; + if ((unsigned long) addr + count < count) + count = -(unsigned long) addr; - memcpy(buf, addr, count); - return count; + return copy_to_iter(addr, count, iter); } /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 978194dc2bb8..5291c6f02cf7 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -33,11 +33,11 @@ #include #include #include +#include #include #include #include #include -#include #include #include #include @@ -3442,62 +3442,96 @@ void *vmalloc_32_user(unsigned long size) EXPORT_SYMBOL(vmalloc_32_user); /* - * small helper routine , copy contents to buf from addr. - * If the page is not present, fill zero. + * Atomically zero bytes in the iterator. + * + * Returns the number of zeroed bytes. */ +static size_t zero_iter(struct iov_iter *iter, size_t count) +{ + size_t remains = count; + + while (remains > 0) { + size_t num, copied; + + num = remains < PAGE_SIZE ? remains : PAGE_SIZE; + copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); + remains -= copied; + + if (copied < num) + break; + } -static int aligned_vread(char *buf, char *addr, unsigned long count) + return count - remains; +} + +/* + * small helper routine, copy contents to iter from addr. + * If the page is not present, fill zero. + * + * Returns the number of copied bytes. + */ +static size_t aligned_vread_iter(struct iov_iter *iter, + const char *addr, size_t count) { - struct page *p; - int copied = 0; + size_t remains = count; + struct page *page; - while (count) { + while (remains > 0) { unsigned long offset, length; + size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; - if (length > count) - length = count; - p = vmalloc_to_page(addr); + if (length > remains) + length = remains; + page = vmalloc_to_page(addr); /* - * To do safe access to this _mapped_ area, we need - * lock. But adding lock here means that we need to add - * overhead of vmalloc()/vfree() calls for this _debug_ - * interface, rarely used. Instead of that, we'll use - * kmap() and get small overhead in this access function. + * To do safe access to this _mapped_ area, we need lock. But + * adding lock here means that we need to add overhead of + * vmalloc()/vfree() calls for this _debug_ interface, rarely + * used. Instead of that, we'll use an local mapping via + * copy_page_to_iter_nofault() and accept a small overhead in + * this access function. */ - if (p) { - /* We can expect USER0 is not used -- see vread() */ - void *map = kmap_atomic(p); - memcpy(buf, map + offset, length); - kunmap_atomic(map); - } else - memset(buf, 0, length); + if (page) + copied = copy_page_to_iter_nofault(page, offset, + length, iter); + else + copied = zero_iter(iter, length); - addr += length; - buf += length; - copied += length; - count -= length; + addr += copied; + remains -= copied; + + if (copied != length) + break; } - return copied; + + return count - remains; } -static void vmap_ram_vread(char *buf, char *addr, int count, unsigned long flags) +/* + * Read from a vm_map_ram region of memory. + * + * Returns the number of copied bytes. + */ +static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, + size_t count, unsigned long flags) { char *start; struct vmap_block *vb; unsigned long offset; - unsigned int rs, re, n; + unsigned int rs, re; + size_t remains, n; /* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here. */ - if (!(flags & VMAP_BLOCK)) { - aligned_vread(buf, addr, count); - return; - } + if (!(flags & VMAP_BLOCK)) + return aligned_vread_iter(iter, addr, count); + + remains = count; /* * Area is split into regions and tracked with vmap_block, read out @@ -3505,50 +3539,64 @@ static void vmap_ram_vread(char *buf, char *addr, int count, unsigned long flags */ vb = xa_load(&vmap_blocks, addr_to_vb_idx((unsigned long)addr)); if (!vb) - goto finished; + goto finished_zero; spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { spin_unlock(&vb->lock); - goto finished; + goto finished_zero; } + for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { - if (!count) - break; + size_t copied; + + if (remains == 0) + goto finished; + start = vmap_block_vaddr(vb->va->va_start, rs); - while (addr < start) { - if (count == 0) - goto unlock; - *buf = '\0'; - buf++; - addr++; - count--; + + if (addr < start) { + size_t to_zero = min_t(size_t, start - addr, remains); + size_t zeroed = zero_iter(iter, to_zero); + + addr += zeroed; + remains -= zeroed; + + if (remains == 0 || zeroed != to_zero) + goto finished; } + /*it could start reading from the middle of used region*/ offset = offset_in_page(addr); n = ((re - rs + 1) << PAGE_SHIFT) - offset; - if (n > count) - n = count; - aligned_vread(buf, start+offset, n); + if (n > remains) + n = remains; + + copied = aligned_vread_iter(iter, start + offset, n); - buf += n; - addr += n; - count -= n; + addr += copied; + remains -= copied; + + if (copied != n) + goto finished; } -unlock: + spin_unlock(&vb->lock); -finished: +finished_zero: /* zero-fill the left dirty or free regions */ - if (count) - memset(buf, 0, count); + return count - remains + zero_iter(iter, remains); +finished: + /* We couldn't copy/zero everything */ + spin_unlock(&vb->lock); + return count - remains; } /** - * vread() - read vmalloc area in a safe way. - * @buf: buffer for reading data - * @addr: vm address. - * @count: number of bytes to be read. + * vread_iter() - read vmalloc area in a safe way to an iterator. + * @iter: the iterator to which data should be written. + * @addr: vm address. + * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range @@ -3568,13 +3616,12 @@ static void vmap_ram_vread(char *buf, char *addr, int count, unsigned long flags * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ -long vread(char *buf, char *addr, unsigned long count) +long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { struct vmap_area *va; struct vm_struct *vm; - char *vaddr, *buf_start = buf; - unsigned long buflen = count; - unsigned long n, size, flags; + char *vaddr; + size_t n, size, flags, remains; addr = kasan_reset_tag(addr); @@ -3582,18 +3629,22 @@ long vread(char *buf, char *addr, unsigned long count) if ((unsigned long) addr + count < count) count = -(unsigned long) addr; + remains = count; + spin_lock(&vmap_area_lock); va = find_vmap_area_exceed_addr((unsigned long)addr); if (!va) - goto finished; + goto finished_zero; /* no intersects with alive vmap_area */ - if ((unsigned long)addr + count <= va->va_start) - goto finished; + if ((unsigned long)addr + remains <= va->va_start) + goto finished_zero; list_for_each_entry_from(va, &vmap_area_list, list) { - if (!count) - break; + size_t copied; + + if (remains == 0) + goto finished; vm = va->vm; flags = va->flags & VMAP_FLAGS_MASK; @@ -3608,6 +3659,7 @@ long vread(char *buf, char *addr, unsigned long count) if (vm && (vm->flags & VM_UNINITIALIZED)) continue; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); @@ -3616,38 +3668,45 @@ long vread(char *buf, char *addr, unsigned long count) if (addr >= vaddr + size) continue; - while (addr < vaddr) { - if (count == 0) + + if (addr < vaddr) { + size_t to_zero = min_t(size_t, vaddr - addr, remains); + size_t zeroed = zero_iter(iter, to_zero); + + addr += zeroed; + remains -= zeroed; + + if (remains == 0 || zeroed != to_zero) goto finished; - *buf = '\0'; - buf++; - addr++; - count--; } + n = vaddr + size - addr; - if (n > count) - n = count; + if (n > remains) + n = remains; if (flags & VMAP_RAM) - vmap_ram_vread(buf, addr, n, flags); + copied = vmap_ram_vread_iter(iter, addr, n, flags); else if (!(vm->flags & VM_IOREMAP)) - aligned_vread(buf, addr, n); + copied = aligned_vread_iter(iter, addr, n); else /* IOREMAP area is treated as memory hole */ - memset(buf, 0, n); - buf += n; - addr += n; - count -= n; + copied = zero_iter(iter, n); + + addr += copied; + remains -= copied; + + if (copied != n) + goto finished; } -finished: - spin_unlock(&vmap_area_lock); - if (buf == buf_start) - return 0; +finished_zero: + spin_unlock(&vmap_area_lock); /* zero-fill memory holes */ - if (buf != buf_start + buflen) - memset(buf, 0, buflen - (buf - buf_start)); + return count - remains + zero_iter(iter, remains); +finished: + /* Nothing remains, or We couldn't copy/zero everything. */ + spin_unlock(&vmap_area_lock); - return buflen; + return count - remains; } /** -- GitLab From fcfccd91841c6f3faf561a45f56bc381ab631956 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Tue, 21 Mar 2023 20:45:55 +0000 Subject: [PATCH 2251/5631] mm/mmap/vma_merge: further improve prev/next VMA naming Patch series "further cleanup of vma_merge()", v2. Following on from Vlastimil Babka's patch series "cleanup vma_merge() and improve mergeability tests" which was in turn based on Liam's prior cleanups, this patch series introduces changes discussed in review of Vlastimil's series and goes further in attempting to make the logic as clear as possible. Nearly all of this should have absolutely no functional impact, however it does add a singular VM_WARN_ON() case. With many thanks to Vernon for helping kick start the discussion around simplification - abstract use of vma did indeed turn out not to be necessary - and to Liam for his excellent suggestions which greatly simplified things. This patch (of 4): Previously the ASCII diagram above vma_merge() and the accompanying variable naming was rather confusing, however recent efforts by Liam Howlett and Vlastimil Babka have significantly improved matters. This patch goes a little further - replacing 'X' with 'N' which feels a lot more natural and replacing what was 'N' with 'C' which stands for 'concurrent' VMA. No word quite describes a VMA that has coincident start as the input span, concurrent, abbreviated to 'curr' (and which can be thought of also as 'current') however fits intuitions well alongside prev and next. This has no functional impact. Link: https://lkml.kernel.org/r/cover.1679431180.git.lstoakes@gmail.com Link: https://lkml.kernel.org/r/6001e08fa7e119470cbb1d2b6275ad8d742ff9a7.1679431180.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Cc: David Hildenbrand Cc: Liam Howlett Cc: Matthew Wilcox (Oracle) Cc: Vernon Yang Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/mmap.c | 86 +++++++++++++++++++++++++++---------------------------- 1 file changed, 43 insertions(+), 43 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 62dce9578242..030715027249 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -848,44 +848,44 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * - * The following mprotect cases have to be considered, where AAAA is + * The following mprotect cases have to be considered, where **** is * the area passed down from mprotect_fixup, never extending beyond one - * vma, PPPP is the previous vma, NNNN is a vma that starts at the same - * address as AAAA and is of the same or larger span, and XXXX the next - * vma after AAAA: + * vma, PPPP is the previous vma, CCCC is a concurrent vma that starts + * at the same address as **** and is of the same or larger span, and + * NNNN the next vma after ****: * - * AAAA AAAA AAAA - * PPPPPPXXXXXX PPPPPPXXXXXX PPPPPPNNNNNN + * **** **** **** + * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPCCCCCC * cannot merge might become might become - * PPXXXXXXXXXX PPPPPPPPPPNN + * PPNNNNNNNNNN PPPPPPPPPPCC * mmap, brk or case 4 below case 5 below * mremap move: - * AAAA AAAA - * PPPP XXXX PPPPNNNNXXXX + * **** **** + * PPPP NNNN PPPPCCCCNNNN * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or - * PPPPPPPPXXXX 2 or PPPPPPPPXXXX 7 or - * PPPPXXXXXXXX 3 PPPPXXXXXXXX 8 + * PPPPPPPPNNNN 2 or PPPPPPPPNNNN 7 or + * PPPPNNNNNNNN 3 PPPPNNNNNNNN 8 * - * It is important for case 8 that the vma NNNN overlapping the - * region AAAA is never going to extended over XXXX. Instead XXXX must - * be extended in region AAAA and NNNN must be removed. This way in + * It is important for case 8 that the vma CCCC overlapping the + * region **** is never going to extended over NNNN. Instead NNNN must + * be extended in region **** and CCCC must be removed. This way in * all cases where vma_merge succeeds, the moment vma_merge drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the - * rmap_locks are released. Otherwise if XXXX would be removed and - * NNNN would be extended over the XXXX range, remove_migration_ptes + * rmap_locks are released. Otherwise if NNNN would be removed and + * CCCC would be extended over the NNNN range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" - * parameter) may establish ptes with the wrong permissions of NNNN - * instead of the right permissions of XXXX. + * parameter) may establish ptes with the wrong permissions of CCCC + * instead of the right permissions of NNNN. * * In the code below: * PPPP is represented by *prev - * NNNN is represented by *mid or not represented at all (NULL) - * XXXX is represented by *next or not represented at all (NULL) - * AAAA is not represented - it will be merged and the vma containing the + * CCCC is represented by *curr or not represented at all (NULL) + * NNNN is represented by *next or not represented at all (NULL) + * **** is not represented - it will be merged and the vma containing the * area is returned, or the function will return NULL */ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, @@ -898,7 +898,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; pgoff_t vma_pgoff; - struct vm_area_struct *mid, *next, *res = NULL; + struct vm_area_struct *curr, *next, *res = NULL; struct vm_area_struct *vma, *adjust, *remove, *remove2; int err = -1; bool merge_prev = false; @@ -917,19 +917,19 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vm_flags & VM_SPECIAL) return NULL; - mid = find_vma(mm, prev ? prev->vm_end : 0); - if (mid && mid->vm_end == end) /* cases 6, 7, 8 */ - next = find_vma(mm, mid->vm_end); + curr = find_vma(mm, prev ? prev->vm_end : 0); + if (curr && curr->vm_end == end) /* cases 6, 7, 8 */ + next = find_vma(mm, curr->vm_end); else - next = mid; + next = curr; - /* In cases 1 - 4 there's no NNNN vma */ - if (mid && end <= mid->vm_start) - mid = NULL; + /* In cases 1 - 4 there's no CCCC vma */ + if (curr && end <= curr->vm_start) + curr = NULL; /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); - VM_WARN_ON(mid && end > mid->vm_end); + VM_WARN_ON(curr && end > curr->vm_end); VM_WARN_ON(addr >= end); if (prev) { @@ -961,21 +961,21 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, remove = next; /* case 1 */ vma_end = next->vm_end; err = dup_anon_vma(prev, next); - if (mid) { /* case 6 */ - remove = mid; + if (curr) { /* case 6 */ + remove = curr; remove2 = next; if (!next->anon_vma) - err = dup_anon_vma(prev, mid); + err = dup_anon_vma(prev, curr); } } else if (merge_prev) { err = 0; /* case 2 */ - if (mid) { - err = dup_anon_vma(prev, mid); - if (end == mid->vm_end) { /* case 7 */ - remove = mid; + if (curr) { + err = dup_anon_vma(prev, curr); + if (end == curr->vm_end) { /* case 7 */ + remove = curr; } else { /* case 5 */ - adjust = mid; - adj_start = (end - mid->vm_start); + adjust = curr; + adj_start = (end - curr->vm_start); } } } else if (merge_next) { @@ -991,10 +991,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_end = next->vm_end; vma_pgoff = next->vm_pgoff; err = 0; - if (mid) { /* case 8 */ - vma_pgoff = mid->vm_pgoff; - remove = mid; - err = dup_anon_vma(next, mid); + if (curr) { /* case 8 */ + vma_pgoff = curr->vm_pgoff; + remove = curr; + err = dup_anon_vma(next, curr); } } } -- GitLab From 00cd00a6a2b1cc0b7d35e56444dab96879def809 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 20:18:58 +0000 Subject: [PATCH 2252/5631] mm/mmap/vma_merge: fold curr, next assignment logic Use find_vma_intersection() and vma_lookup() to both simplify the logic and to fold the end == next->vm_start condition into one block. This groups all of the simple range checks together and establishes the invariant that, if prev, curr or next are non-NULL then their positions are as expected. This has no functional impact. Link: https://lkml.kernel.org/r/c6d960641b4ba58fa6ad3d07bf68c27d847963c8.1679516210.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Vernon Yang Signed-off-by: Andrew Morton --- mm/mmap.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 030715027249..e2e2c970374a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -917,15 +917,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vm_flags & VM_SPECIAL) return NULL; - curr = find_vma(mm, prev ? prev->vm_end : 0); - if (curr && curr->vm_end == end) /* cases 6, 7, 8 */ - next = find_vma(mm, curr->vm_end); - else - next = curr; + /* Does the input range span an existing VMA? (cases 5 - 8) */ + curr = find_vma_intersection(mm, prev ? prev->vm_end : 0, end); - /* In cases 1 - 4 there's no CCCC vma */ - if (curr && end <= curr->vm_start) - curr = NULL; + if (!curr || /* cases 1 - 4 */ + end == curr->vm_end) /* cases 6 - 8, adjacent VMA */ + next = vma_lookup(mm, end); + else + next = NULL; /* case 5 */ /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); @@ -946,11 +945,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, } } /* Can we merge the successor? */ - if (next && end == next->vm_start && - mpol_equal(policy, vma_policy(next)) && - can_vma_merge_before(next, vm_flags, - anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx, anon_name)) { + if (next && mpol_equal(policy, vma_policy(next)) && + can_vma_merge_before(next, vm_flags, + anon_vma, file, pgoff+pglen, + vm_userfaultfd_ctx, anon_name)) { merge_next = true; } -- GitLab From b0729ae0ae67a1a001e8d577b8be9ba44c4bdb26 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 20:18:59 +0000 Subject: [PATCH 2253/5631] mm/mmap/vma_merge: explicitly assign res, vma, extend invariants Previously, vma was an uninitialised variable which was only definitely assigned as a result of the logic covering all possible input cases - for it to have remained uninitialised, prev would have to be NULL, and next would _have_ to be mergeable. The value of res defaults to NULL, so we can neatly eliminate the assignment to res and vma in the if (prev) block and ensure that both res and vma are both explicitly assigned, by just setting both to prev. In addition we add an explanation as to under what circumstances both might change, and since we absolutely do rely on addr == curr->vm_start should curr exist, assert that this is the case. Link: https://lkml.kernel.org/r/83938bed24422cbe5954bbf491341674becfe567.1679516210.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Reviewed-by: Liam R. Howlett Cc: David Hildenbrand Cc: Matthew Wilcox (Oracle) Cc: Vernon Yang Signed-off-by: Andrew Morton --- mm/mmap.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index e2e2c970374a..343859b1190d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -898,7 +898,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; pgoff_t vma_pgoff; - struct vm_area_struct *curr, *next, *res = NULL; + struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; int err = -1; bool merge_prev = false; @@ -926,14 +926,18 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, else next = NULL; /* case 5 */ - /* verify some invariant that must be enforced by the caller */ + /* + * By default, we return prev. Cases 3, 4, 8 will instead return next + * and cases 3, 8 will also update vma to point at next. + */ + res = vma = prev; + + /* Verify some invariant that must be enforced by the caller. */ VM_WARN_ON(prev && addr <= prev->vm_start); - VM_WARN_ON(curr && end > curr->vm_end); + VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); VM_WARN_ON(addr >= end); if (prev) { - res = prev; - vma = prev; vma_start = prev->vm_start; vma_pgoff = prev->vm_pgoff; /* Can we merge the predecessor? */ @@ -944,6 +948,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_prev(vmi); } } + /* Can we merge the successor? */ if (next && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, @@ -984,6 +989,10 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, adj_start = -(prev->vm_end - addr); err = dup_anon_vma(next, prev); } else { + /* + * Note that cases 3 and 8 are the ONLY ones where prev + * is permitted to be (but is not necessarily) NULL. + */ vma = next; /* case 3 */ vma_start = addr; vma_end = next->vm_end; -- GitLab From 0173db4f7f526540e2cc0a6a61e42771acd4c197 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Wed, 22 Mar 2023 20:19:00 +0000 Subject: [PATCH 2254/5631] mm/mmap/vma_merge: init cleanup, be explicit about the non-mergeable case Rather than setting err = -1 and only resetting if we hit merge cases, explicitly check the non-mergeable case to make it abundantly clear that we only proceed with the rest if something is mergeable, default err to 0 and only update if an error might occur. Move the merge_prev, merge_next cases closer to the logic determining curr, next and reorder initial variables so they are more logically grouped. This has no functional impact. Link: https://lkml.kernel.org/r/99259fbc6403e80e270e1cc4612abbc8620b121b.1679516210.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Vlastimil Babka Cc: David Hildenbrand Cc: Liam R. Howlett Cc: Matthew Wilcox (Oracle) Cc: Vernon Yang Signed-off-by: Andrew Morton --- mm/mmap.c | 47 ++++++++++++++++++++++------------------------- 1 file changed, 22 insertions(+), 25 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 343859b1190d..6c326002184d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -896,18 +896,18 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { - pgoff_t pglen = (end - addr) >> PAGE_SHIFT; - pgoff_t vma_pgoff; struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; - int err = -1; + struct vma_prepare vp; + pgoff_t vma_pgoff; + int err = 0; bool merge_prev = false; bool merge_next = false; bool vma_expanded = false; - struct vma_prepare vp; + unsigned long vma_start = addr; unsigned long vma_end = end; + pgoff_t pglen = (end - addr) >> PAGE_SHIFT; long adj_start = 0; - unsigned long vma_start = addr; validate_mm(mm); /* @@ -926,24 +926,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, else next = NULL; /* case 5 */ - /* - * By default, we return prev. Cases 3, 4, 8 will instead return next - * and cases 3, 8 will also update vma to point at next. - */ - res = vma = prev; - - /* Verify some invariant that must be enforced by the caller. */ - VM_WARN_ON(prev && addr <= prev->vm_start); - VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); - VM_WARN_ON(addr >= end); - if (prev) { vma_start = prev->vm_start; vma_pgoff = prev->vm_pgoff; + /* Can we merge the predecessor? */ - if (prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) + if (addr == prev->vm_end && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, - pgoff, vm_userfaultfd_ctx, anon_name)) { + pgoff, vm_userfaultfd_ctx, anon_name)) { merge_prev = true; vma_prev(vmi); } @@ -951,13 +941,22 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, /* Can we merge the successor? */ if (next && mpol_equal(policy, vma_policy(next)) && - can_vma_merge_before(next, vm_flags, - anon_vma, file, pgoff+pglen, + can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx, anon_name)) { merge_next = true; } + if (!merge_prev && !merge_next) + return NULL; /* Not mergeable. */ + + res = vma = prev; remove = remove2 = adjust = NULL; + + /* Verify some invariant that must be enforced by the caller. */ + VM_WARN_ON(prev && addr <= prev->vm_start); + VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); + VM_WARN_ON(addr >= end); + /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { @@ -970,8 +969,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (!next->anon_vma) err = dup_anon_vma(prev, curr); } - } else if (merge_prev) { - err = 0; /* case 2 */ + } else if (merge_prev) { /* case 2 */ if (curr) { err = dup_anon_vma(prev, curr); if (end == curr->vm_end) { /* case 7 */ @@ -981,7 +979,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, adj_start = (end - curr->vm_start); } } - } else if (merge_next) { + } else { /* merge_next */ res = next; if (prev && addr < prev->vm_end) { /* case 4 */ vma_end = addr; @@ -997,7 +995,6 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_start = addr; vma_end = next->vm_end; vma_pgoff = next->vm_pgoff; - err = 0; if (curr) { /* case 8 */ vma_pgoff = curr->vm_pgoff; remove = curr; @@ -1006,7 +1003,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, } } - /* Cannot merge or error in anon_vma clone */ + /* Error in anon_vma clone. */ if (err) return NULL; -- GitLab From dd31bad21980990d903133d2855ea0e2eccade5e Mon Sep 17 00:00:00 2001 From: Tomas Krcka Date: Thu, 23 Mar 2023 17:43:49 +0000 Subject: [PATCH 2255/5631] mm: be less noisy during memory hotplug MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Turn a pr_info() into a pr_debug() to prevent dmesg spamming on systems where memory hotplug is a frequent operation. Link: https://lkml.kernel.org/r/20230323174349.35990-1-krckatom@amazon.de Signed-off-by: Tomas Krcka Suggested-by: Jan H. Schönherr Acked-by: David Hildenbrand Reviewed-by: Pasha Tatashin Signed-off-by: Andrew Morton --- mm/mm_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mm_init.c b/mm/mm_init.c index c88fbe74137c..dd3a6ed9663f 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1086,7 +1086,7 @@ void __ref memmap_init_zone_device(struct zone *zone, compound_nr_pages(altmap, pfns_per_compound)); } - pr_info("%s initialised %lu pages in %ums\n", __func__, + pr_debug("%s initialised %lu pages in %ums\n", __func__, nr_pages, jiffies_to_msecs(jiffies - start)); } #endif -- GitLab From c710fac6bfc8c2bcfedbaba27e31524c98eb6188 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Thu, 23 Mar 2023 19:41:36 +0800 Subject: [PATCH 2256/5631] trace: cma: remove unnecessary event class cma_alloc_class After commit cb6c33d4dc09 ("cma: tracing: print alloc result in trace_cma_alloc_finish"), cma_alloc_class has only one event which is cma_alloc_busy_retry. So we can remove the cma_alloc_class. Link: https://lkml.kernel.org/r/20230323114136.177677-1-haowenchao2@huawei.com Signed-off-by: Wenchao Hao Acked-by: Steven Rostedt (Google) Cc: Feilong Lin Cc: Hongxiang Lou Cc: Masami Hiramatsu Signed-off-by: Andrew Morton --- include/trace/events/cma.h | 58 ++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 33 deletions(-) diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index ef75ea606ab2..25103e67737c 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -8,37 +8,6 @@ #include #include -DECLARE_EVENT_CLASS(cma_alloc_class, - - TP_PROTO(const char *name, unsigned long pfn, const struct page *page, - unsigned long count, unsigned int align), - - TP_ARGS(name, pfn, page, count, align), - - TP_STRUCT__entry( - __string(name, name) - __field(unsigned long, pfn) - __field(const struct page *, page) - __field(unsigned long, count) - __field(unsigned int, align) - ), - - TP_fast_assign( - __assign_str(name, name); - __entry->pfn = pfn; - __entry->page = page; - __entry->count = count; - __entry->align = align; - ), - - TP_printk("name=%s pfn=0x%lx page=%p count=%lu align=%u", - __get_str(name), - __entry->pfn, - __entry->page, - __entry->count, - __entry->align) -); - TRACE_EVENT(cma_release, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, @@ -125,12 +94,35 @@ TRACE_EVENT(cma_alloc_finish, __entry->errorno) ); -DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry, +TRACE_EVENT(cma_alloc_busy_retry, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, unsigned long count, unsigned int align), - TP_ARGS(name, pfn, page, count, align) + TP_ARGS(name, pfn, page, count, align), + + TP_STRUCT__entry( + __string(name, name) + __field(unsigned long, pfn) + __field(const struct page *, page) + __field(unsigned long, count) + __field(unsigned int, align) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->pfn = pfn; + __entry->page = page; + __entry->count = count; + __entry->align = align; + ), + + TP_printk("name=%s pfn=0x%lx page=%p count=%lu align=%u", + __get_str(name), + __entry->pfn, + __entry->page, + __entry->count, + __entry->align) ); #endif /* _TRACE_CMA_H */ -- GitLab From 3cce258ea4009992b7b4b64c2bebaf98948180ae Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 11:31:19 +0530 Subject: [PATCH 2257/5631] selftests/mm: change MAP_CHUNK_SIZE Patch series "selftests: Fix virtual address range for arm64", v2. When the virtual address range selftest is run on arm64 and x86 platforms, it is observed that both the low and high VA range iterations are skipped when the MAP_CHUNK_SIZE is set to 16GB. The MAP_CHUNK_SIZE is changed to 1GB to resolve this issue, following which support for arm64 platform is added by changing the NR_CHUNKS_HIGH for aarch64 to accommodate up to 4PB of virtual address space allocation requests. Dynamic memory allocation of array holding addresses is introduced to prevent overflow of the stack. Finally, the overcommit_policy is set as OVERCOMMIT_ALWAYS to prevent the kernel from denying a memory allocation request based on a platform's physical memory availability. This patch (of 3): mmap() fails to allocate 16GB virtual space chunk, skipping both low and high VA range iterations. Hence, reduce MAP_CHUNK_SIZE to 1GB and update relevant macros as required. Link: https://lkml.kernel.org/r/20230323060121.1175830-1-chaitanyas.prakash@arm.com Link: https://lkml.kernel.org/r/20230323060121.1175830-2-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: David Hildenbrand Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/virtual_address_range.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index c0592646ed93..50564512c5ee 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -15,11 +15,15 @@ /* * Maximum address range mapped with a single mmap() - * call is little bit more than 16GB. Hence 16GB is + * call is little bit more than 1GB. Hence 1GB is * chosen as the single chunk size for address space * mapping. */ -#define MAP_CHUNK_SIZE 17179869184UL /* 16GB */ + +#define SZ_1GB (1024 * 1024 * 1024UL) +#define SZ_1TB (1024 * 1024 * 1024 * 1024UL) + +#define MAP_CHUNK_SIZE SZ_1GB /* * Address space till 128TB is mapped without any hint @@ -36,7 +40,7 @@ * are supported so far. */ -#define NR_CHUNKS_128TB 8192UL /* Number of 16GB chunks for 128TB */ +#define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) -- GitLab From 3f9bea2b8a7e4952f03582d8137ab8bf6e96985b Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 11:31:20 +0530 Subject: [PATCH 2258/5631] selftests/mm: change NR_CHUNKS_HIGH for aarch64 Although there is a provision for 52 bit VA on arm64 platform, it remains unutilised and higher addresses are not allocated. In order to accommodate 4PB [2^52] virtual address space where supported, NR_CHUNKS_HIGH is changed accordingly. Array holding addresses is changed from static allocation to dynamic allocation to accommodate its voluminous nature which otherwise might overflow the stack. Link: https://lkml.kernel.org/r/20230323060121.1175830-3-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: David Hildenbrand Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/virtual_address_range.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 50564512c5ee..bae0ceaf95b1 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -36,13 +36,15 @@ * till it reaches 512TB. One with size 128TB and the * other being 384TB. * - * On Arm64 the address space is 256TB and no high mappings - * are supported so far. + * On Arm64 the address space is 256TB and support for + * high mappings up to 4PB virtual address space has + * been added. */ #define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) +#define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ #define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ @@ -51,7 +53,7 @@ #define HIGH_ADDR_MARK ADDR_MARK_256TB #define HIGH_ADDR_SHIFT 49 #define NR_CHUNKS_LOW NR_CHUNKS_256TB -#define NR_CHUNKS_HIGH 0 +#define NR_CHUNKS_HIGH NR_CHUNKS_3840TB #else #define HIGH_ADDR_MARK ADDR_MARK_128TB #define HIGH_ADDR_SHIFT 48 @@ -101,7 +103,7 @@ static int validate_lower_address_hint(void) int main(int argc, char *argv[]) { char *ptr[NR_CHUNKS_LOW]; - char *hptr[NR_CHUNKS_HIGH]; + char **hptr; char *hint; unsigned long i, lchunks, hchunks; @@ -119,6 +121,9 @@ int main(int argc, char *argv[]) return 1; } lchunks = i; + hptr = (char **) calloc(NR_CHUNKS_HIGH, sizeof(char *)); + if (hptr == NULL) + return 1; for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); @@ -139,5 +144,6 @@ int main(int argc, char *argv[]) for (i = 0; i < hchunks; i++) munmap(hptr[i], MAP_CHUNK_SIZE); + free(hptr); return 0; } -- GitLab From d6c2789778c59c1768567099eb2fdd32d790c38a Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 11:31:21 +0530 Subject: [PATCH 2259/5631] selftests/mm: set overcommit_policy as OVERCOMMIT_ALWAYS The kernel's default behaviour is to obstruct the allocation of high virtual address as it handles memory overcommit in a heuristic manner. Setting the parameter as OVERCOMMIT_ALWAYS, ensures kernel isn't susceptible to the availability of a platform's physical memory when denying a memory allocation request. Link: https://lkml.kernel.org/r/20230323060121.1175830-4-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: David Hildenbrand Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 8984e0bb58c7..c0f93b668c0c 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,15 @@ CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen if [ $VADDR64 -ne 0 ]; then + + # set overcommit_policy as OVERCOMMIT_ALWAYS so that kernel + # allows high virtual address allocation requests independent + # of platform's physical memory. + + prev_policy=$(cat /proc/sys/vm/overcommit_memory) + echo 1 > /proc/sys/vm/overcommit_memory CATEGORY="hugevm" run_test ./virtual_address_range + echo $prev_policy > /proc/sys/vm/overcommit_memory # virtual address 128TB switch test CATEGORY="hugevm" run_test ./va_128TBswitch.sh -- GitLab From 02cd4eb81c14ee64b062383c7e25fd8599b18f3d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Fri, 24 Mar 2023 15:35:27 +0000 Subject: [PATCH 2260/5631] mm/damon/sysfs: make more kobj_type structures constant MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit ee6d3dd4ed48 ("driver core: make kobj_type constant.") the driver core allows the usage of const struct kobj_type. Take advantage of this to constify the structure definition to prevent modification at runtime. These structures were not constified in commit e56397e8c40d ("mm/damon/sysfs: make kobj_type structures constant") as they didn't exist when that patch was written. Link: https://lkml.kernel.org/r/20230324-b4-kobj_type-damon2-v1-1-48ddbf1c8fcf@weissschuh.net Signed-off-by: Thomas Weißschuh Reviewed-by: SeongJae Park Reviewed-by: Muhammad Usama Anjum Signed-off-by: Andrew Morton --- mm/damon/sysfs-schemes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 3cdad5a7f936..50cf89dcd898 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -384,7 +384,7 @@ static struct attribute *damon_sysfs_scheme_filter_attrs[] = { }; ATTRIBUTE_GROUPS(damon_sysfs_scheme_filter); -static struct kobj_type damon_sysfs_scheme_filter_ktype = { +static const struct kobj_type damon_sysfs_scheme_filter_ktype = { .release = damon_sysfs_scheme_filter_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = damon_sysfs_scheme_filter_groups, @@ -503,7 +503,7 @@ static struct attribute *damon_sysfs_scheme_filters_attrs[] = { }; ATTRIBUTE_GROUPS(damon_sysfs_scheme_filters); -static struct kobj_type damon_sysfs_scheme_filters_ktype = { +static const struct kobj_type damon_sysfs_scheme_filters_ktype = { .release = damon_sysfs_scheme_filters_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = damon_sysfs_scheme_filters_groups, -- GitLab From 945ea457b5a57cd34cbacce6f1f9e4a2e88432c2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Mar 2023 18:45:13 +0100 Subject: [PATCH 2261/5631] xfs: remove xfs_filemap_map_pages() wrapper Patch series "Prevent ->map_pages from sleeping", v2. In preparation for a larger patch series which will handle (some, easy) page faults protected only by RCU, change the two filesystems which have sleeping locks to not take them and hold the RCU lock around calls to ->map_page to prevent other filesystems from adding sleeping locks. This patch (of 3): XFS doesn't actually need to be holding the XFS_MMAPLOCK_SHARED to do this. filemap_map_pages() cannot bring new folios into the page cache and the folio lock is taken during filemap_map_pages() which provides sufficient protection against a truncation or hole punch. Link: https://lkml.kernel.org/r/20230327174515.1811532-1-willy@infradead.org Link: https://lkml.kernel.org/r/20230327174515.1811532-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Dave Chinner Cc: Darrick J. Wong Cc: David Howells Signed-off-by: Andrew Morton --- fs/xfs/xfs_file.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 705250f9f90a..528fc538b6b9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1388,25 +1388,10 @@ xfs_filemap_pfn_mkwrite( return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } -static vm_fault_t -xfs_filemap_map_pages( - struct vm_fault *vmf, - pgoff_t start_pgoff, - pgoff_t end_pgoff) -{ - struct inode *inode = file_inode(vmf->vma->vm_file); - vm_fault_t ret; - - xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = filemap_map_pages(vmf, start_pgoff, end_pgoff); - xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - return ret; -} - static const struct vm_operations_struct xfs_file_vm_ops = { .fault = xfs_filemap_fault, .huge_fault = xfs_filemap_huge_fault, - .map_pages = xfs_filemap_map_pages, + .map_pages = filemap_map_pages, .page_mkwrite = xfs_filemap_page_mkwrite, .pfn_mkwrite = xfs_filemap_pfn_mkwrite, }; -- GitLab From 0050d7f5ee532f92e8ab1efcec6547bfac527973 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Mar 2023 18:45:14 +0100 Subject: [PATCH 2262/5631] afs: split afs_pagecache_valid() out of afs_validate() For the map_pages() method, we need a test that does not sleep. The page fault handler will continue to call the fault() method where we can sleep and do the full revalidation there. Link: https://lkml.kernel.org/r/20230327174515.1811532-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: David Howells Tested-by: David Howells Cc: Darrick J. Wong Cc: Dave Chinner Signed-off-by: Andrew Morton --- fs/afs/file.c | 14 ++------------ fs/afs/inode.c | 27 +++++++++++++++++++-------- fs/afs/internal.h | 1 + 3 files changed, 22 insertions(+), 20 deletions(-) diff --git a/fs/afs/file.c b/fs/afs/file.c index 68d6d5dc608d..719b31374879 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -569,20 +569,10 @@ static void afs_vm_close(struct vm_area_struct *vma) static vm_fault_t afs_vm_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct afs_vnode *vnode = AFS_FS_I(file_inode(vmf->vma->vm_file)); - struct afs_file *af = vmf->vma->vm_file->private_data; - switch (afs_validate(vnode, af->key)) { - case 0: + if (afs_pagecache_valid(vnode)) return filemap_map_pages(vmf, start_pgoff, end_pgoff); - case -ENOMEM: - return VM_FAULT_OOM; - case -EINTR: - case -ERESTARTSYS: - return VM_FAULT_RETRY; - case -ESTALE: - default: - return VM_FAULT_SIGBUS; - } + return 0; } static ssize_t afs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0167e96e5198..b1bdffd5e888 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -667,6 +667,24 @@ bool afs_check_validity(struct afs_vnode *vnode) return false; } +/* + * Returns true if the pagecache is still valid. Does not sleep. + */ +bool afs_pagecache_valid(struct afs_vnode *vnode) +{ + if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) { + if (vnode->netfs.inode.i_nlink) + clear_nlink(&vnode->netfs.inode); + return true; + } + + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) && + afs_check_validity(vnode)) + return true; + + return false; +} + /* * validate a vnode/inode * - there are several things we need to check @@ -684,14 +702,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->fid.vid, vnode->fid.vnode, vnode->flags, key_serial(key)); - if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) { - if (vnode->netfs.inode.i_nlink) - clear_nlink(&vnode->netfs.inode); - goto valid; - } - - if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags) && - afs_check_validity(vnode)) + if (afs_pagecache_valid(vnode)) goto valid; down_write(&vnode->validate_lock); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index ad8523d0d038..5c95df6621f9 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1171,6 +1171,7 @@ extern struct inode *afs_iget(struct afs_operation *, struct afs_vnode_param *); extern struct inode *afs_root_iget(struct super_block *, struct key *); extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); +bool afs_pagecache_valid(struct afs_vnode *); extern int afs_getattr(struct mnt_idmap *idmap, const struct path *, struct kstat *, u32, unsigned int); extern int afs_setattr(struct mnt_idmap *idmap, struct dentry *, struct iattr *); -- GitLab From 58ef47ef7db9dfc2730dc039498cc76130ea3c3d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Mar 2023 18:45:15 +0100 Subject: [PATCH 2263/5631] mm: hold the RCU read lock over calls to ->map_pages Prevent filesystems from doing things which sleep in their map_pages method. This is in preparation for a pagefault path protected only by RCU. Link: https://lkml.kernel.org/r/20230327174515.1811532-4-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Darrick J. Wong Cc: Dave Chinner Cc: David Howells Signed-off-by: Andrew Morton --- Documentation/filesystems/locking.rst | 4 ++-- mm/memory.c | 11 ++++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 7de7a7272a5e..aa1a233b0fa8 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -645,7 +645,7 @@ ops mmap_lock PageLocked(page) open: yes close: yes fault: yes can return with page locked -map_pages: yes +map_pages: read page_mkwrite: yes can return with page locked pfn_mkwrite: yes access: yes @@ -661,7 +661,7 @@ locked. The VM will unlock the page. ->map_pages() is called when VM asks to map easy accessible pages. Filesystem should find and map pages associated with offsets from "start_pgoff" -till "end_pgoff". ->map_pages() is called with page table locked and must +till "end_pgoff". ->map_pages() is called with the RCU lock held and must not block. If it's not possible to reach a page without blocking, filesystem should skip it. Filesystem should use do_set_pte() to setup page table entry. Pointer to entry associated with the page is passed in diff --git a/mm/memory.c b/mm/memory.c index 7716f2cc4b68..ec7e89cc0532 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4450,6 +4450,7 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) /* The page offset of vmf->address within the VMA. */ pgoff_t vma_off = vmf->pgoff - vmf->vma->vm_pgoff; pgoff_t from_pte, to_pte; + vm_fault_t ret; /* The PTE offset of the start address, clamped to the VMA. */ from_pte = max(ALIGN_DOWN(pte_off, nr_pages), @@ -4465,9 +4466,13 @@ static vm_fault_t do_fault_around(struct vm_fault *vmf) return VM_FAULT_OOM; } - return vmf->vma->vm_ops->map_pages(vmf, - vmf->pgoff + from_pte - pte_off, - vmf->pgoff + to_pte - pte_off); + rcu_read_lock(); + ret = vmf->vma->vm_ops->map_pages(vmf, + vmf->pgoff + from_pte - pte_off, + vmf->pgoff + to_pte - pte_off); + rcu_read_unlock(); + + return ret; } /* Return true if we should do read fault-around, false otherwise */ -- GitLab From 0b6cc04f3db3604c1485049bc9582523c2b44b75 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:08 -0800 Subject: [PATCH 2264/5631] mm: introduce CONFIG_PER_VMA_LOCK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "Per-VMA locks", v4. LWN article describing the feature: https://lwn.net/Articles/906852/ Per-vma locks idea that was discussed during SPF [1] discussion at LSF/MM last year [2], which concluded with suggestion that “a reader/writer semaphore could be put into the VMA itself; that would have the effect of using the VMA as a sort of range lock. There would still be contention at the VMA level, but it would be an improvement.” This patchset implements this suggested approach. When handling page faults we lookup the VMA that contains the faulting page under RCU protection and try to acquire its lock. If that fails we fall back to using mmap_lock, similar to how SPF handled this situation. One notable way the implementation deviates from the proposal is the way VMAs are read-locked. During some of mm updates, multiple VMAs need to be locked until the end of the update (e.g. vma_merge, split_vma, etc). Tracking all the locked VMAs, avoiding recursive locks, figuring out when it's safe to unlock previously locked VMAs would make the code more complex. So, instead of the usual lock/unlock pattern, the proposed solution marks a VMA as locked and provides an efficient way to: 1. Identify locked VMAs. 2. Unlock all locked VMAs in bulk. We also postpone unlocking the locked VMAs until the end of the update, when we do mmap_write_unlock. Potentially this keeps a VMA locked for longer than is absolutely necessary but it results in a big reduction of code complexity. Read-locking a VMA is done using two sequence numbers - one in the vm_area_struct and one in the mm_struct. VMA is considered read-locked when these sequence numbers are equal. To read-lock a VMA we set the sequence number in vm_area_struct to be equal to the sequence number in mm_struct. To unlock all VMAs we increment mm_struct's seq number. This allows for an efficient way to track locked VMAs and to drop the locks on all VMAs at the end of the update. The patchset implements per-VMA locking only for anonymous pages which are not in swap and avoids userfaultfs as their implementation is more complex. Additional support for file-back page faults, swapped and user pages can be added incrementally. Performance benchmarks show similar although slightly smaller benefits as with SPF patchset (~75% of SPF benefits). Still, with lower complexity this approach might be more desirable. Since RFC was posted in September 2022, two separate Google teams outside of Android evaluated the patchset and confirmed positive results. Here are the known usecases when per-VMA locks show benefits: Android: Apps with high number of threads (~100) launch times improve by up to 20%. Each thread mmaps several areas upon startup (Stack and Thread-local storage (TLS), thread signal stack, indirect ref table), which requires taking mmap_lock in write mode. Page faults take mmap_lock in read mode. During app launch, both thread creation and page faults establishing the active workinget are happening in parallel and that causes lock contention between mm writers and readers even if updates and page faults are happening in different VMAs. Per-vma locks prevent this contention by providing more granular lock. Google Fibers: We have several dynamically sized thread pools that spawn new threads under increased load and reduce their number when idling. For example, Google's in-process scheduling/threading framework, UMCG/Fibers, is backed by such a thread pool. When idling, only a small number of idle worker threads are available; when a spike of incoming requests arrive, each request is handled in its own "fiber", which is a work item posted onto a UMCG worker thread; quite often these spikes lead to a number of new threads spawning. Each new thread needs to allocate and register an RSEQ section on its TLS, then register itself with the kernel as a UMCG worker thread, and only after that it can be considered by the in-process UMCG/Fiber scheduler as available to do useful work. In short, during an incoming workload spike new threads have to be spawned, and they perform several syscalls (RSEQ registration, UMCG worker registration, memory allocations) before they can actually start doing useful work. Removing any bottlenecks on this thread startup path will greatly improve our services' latencies when faced with request/workload spikes. At high scale, mmap_lock contention during thread creation and stack page faults leads to user-visible multi-second serving latencies in a similar pattern to Android app startup. Per-VMA locking patchset has been run successfully in limited experiments with user-facing production workloads. In these experiments, we observed that the peak thread creation rate was high enough that thread creation is no longer a bottleneck. TCP zerocopy receive: From the point of view of TCP zerocopy receive, the per-vma lock patch is massively beneficial. In today's implementation, a process with N threads where N - 1 are performing zerocopy receive and 1 thread is performing madvise() with the write lock taken (e.g. needs to change vm_flags) will result in all N -1 receive threads blocking until the madvise is done. Conversely, on a busy process receiving a lot of data, an madvise operation that does need to take the mmap lock in write mode will need to wait for all of the receives to be done - a lose:lose proposition. Per-VMA locking _removes_ by definition this source of contention entirely. There are other benefits for receive as well, chiefly a reduction in cacheline bouncing across receiving threads for locking/unlocking the single mmap lock. On an RPC style synthetic workload with 4KB RPCs: 1a) The find+lock+unlock VMA path in the base case, without the per-vma lock patchset, is about 0.7% of cycles as measured by perf. 1b) mmap_read_lock + mmap_read_unlock in the base case is about 0.5% cycles overall - most of this is within the TCP read hotpath (a small fraction is 'other' usage in the system). 2a) The find+lock+unlock VMA path, with the per-vma patchset and a trivial patch written to take advantage of it in TCP, is about 0.4% of cycles (down from 0.7% above) 2b) mmap_read_lock + mmap_read_unlock in the per-vma patchset is < 0.1% cycles and is out of the TCP read hotpath entirely (down from 0.5% before, the remaining usage is the 'other' usage in the system). So, in addition to entirely removing an onerous source of contention, it also reduces the CPU cycles of TCP receive zerocopy by about 0.5%+ (compared to overall cycles in perf) for the 'small' RPC scenario. In https://lkml.kernel.org/r/87fsaqouyd.fsf_-_@stealth, Punit demonstrated throughput improvements of as much as 188% from this patchset. This patch (of 25): This configuration variable will be used to build the support for VMA locking during page fault handling. This is enabled on supported architectures with SMP and MMU set. The architecture support is needed since the page fault handler is called from the architecture's page faulting code which needs modifications to handle faults under VMA lock. Link: https://lkml.kernel.org/r/20230227173632.3292573-1-surenb@google.com Link: https://lkml.kernel.org/r/20230227173632.3292573-10-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/Kconfig | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/Kconfig b/mm/Kconfig index 969286ab14a1..6ee3b48ed298 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1211,6 +1211,18 @@ config LRU_GEN_STATS This option has a per-memcg and per-node memory overhead. # } +config ARCH_SUPPORTS_PER_VMA_LOCK + def_bool n + +config PER_VMA_LOCK + def_bool y + depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP + help + Allow per-vma locking during page fault handling. + + This feature allows locking each virtual memory area separately when + handling page faults instead of taking mmap_lock. + source "mm/damon/Kconfig" endmenu -- GitLab From 20cce633f4254cc0df39665449726e3172518f6c Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Mon, 27 Feb 2023 09:36:09 -0800 Subject: [PATCH 2265/5631] mm: rcu safe VMA freeing This prepares for page faults handling under VMA lock, looking up VMAs under protection of an rcu read lock, instead of the usual mmap read lock. Link: https://lkml.kernel.org/r/20230227173632.3292573-11-surenb@google.com Signed-off-by: Michel Lespinasse Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm_types.h | 13 ++++++++++--- kernel/fork.c | 20 +++++++++++++++++++- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 651a5c256732..f203e2562e00 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -480,9 +480,16 @@ struct anon_vma_name { struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ - unsigned long vm_start; /* Our start address within vm_mm. */ - unsigned long vm_end; /* The first byte after our end address - within vm_mm. */ + union { + struct { + /* VMA covers [vm_start; vm_end) addresses within mm */ + unsigned long vm_start; + unsigned long vm_end; + }; +#ifdef CONFIG_PER_VMA_LOCK + struct rcu_head vm_rcu; /* Used for deferred freeing. */ +#endif + }; struct mm_struct *vm_mm; /* The address space we belong to. */ pgprot_t vm_page_prot; /* Access permissions of this VMA. */ diff --git a/kernel/fork.c b/kernel/fork.c index cea99f003f24..93ec6e14bb65 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -479,12 +479,30 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) return new; } -void vm_area_free(struct vm_area_struct *vma) +static void __vm_area_free(struct vm_area_struct *vma) { free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); } +#ifdef CONFIG_PER_VMA_LOCK +static void vm_area_free_rcu_cb(struct rcu_head *head) +{ + struct vm_area_struct *vma = container_of(head, struct vm_area_struct, + vm_rcu); + __vm_area_free(vma); +} +#endif + +void vm_area_free(struct vm_area_struct *vma) +{ +#ifdef CONFIG_PER_VMA_LOCK + call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); +#else + __vm_area_free(vma); +#endif +} + static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { -- GitLab From 438b6e12cd603a9416ca7c5462ab75b2a8c4d5b9 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:10 -0800 Subject: [PATCH 2266/5631] mm: move mmap_lock assert function definitions Move mmap_lock assert function definitions up so that they can be used by other mmap_lock routines. Link: https://lkml.kernel.org/r/20230227173632.3292573-12-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mmap_lock.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 96e113e23d04..e49ba91bb1f0 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,6 +60,18 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -150,18 +162,6 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_lock); } -static inline void mmap_assert_locked(struct mm_struct *mm) -{ - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - -static inline void mmap_assert_write_locked(struct mm_struct *mm) -{ - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); -- GitLab From 5e31275cc997f8ec5d9e8d65fe9840ebed89db19 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:11 -0800 Subject: [PATCH 2267/5631] mm: add per-VMA lock and helper functions to control it Introduce per-VMA locking. The lock implementation relies on a per-vma and per-mm sequence counters to note exclusive locking: - read lock - (implemented by vma_start_read) requires the vma (vm_lock_seq) and mm (mm_lock_seq) sequence counters to differ. If they match then there must be a vma exclusive lock held somewhere. - read unlock - (implemented by vma_end_read) is a trivial vma->lock unlock. - write lock - (vma_start_write) requires the mmap_lock to be held exclusively and the current mm counter is assigned to the vma counter. This will allow multiple vmas to be locked under a single mmap_lock write lock (e.g. during vma merging). The vma counter is modified under exclusive vma lock. - write unlock - (vma_end_write_all) is a batch release of all vma locks held. It doesn't pair with a specific vma_start_write! It is done before exclusive mmap_lock is released by incrementing mm sequence counter (mm_lock_seq). - write downgrade - if the mmap_lock is downgraded to the read lock, all vma write locks are released as well (effectivelly same as write unlock). Link: https://lkml.kernel.org/r/20230227173632.3292573-13-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 82 +++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 8 ++++ include/linux/mmap_lock.h | 13 +++++++ kernel/fork.c | 4 ++ mm/init-mm.c | 3 ++ 5 files changed, 110 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 55d02356146c..53bfb42663ea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -624,6 +624,87 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_init_lock(struct vm_area_struct *vma) +{ + init_rwsem(&vma->lock); + vma->vm_lock_seq = -1; +} + +/* + * Try to read-lock a vma. The function is allowed to occasionally yield false + * locked result to avoid performance overhead, in which case we fall back to + * using mmap_lock. The function should never yield false unlocked result. + */ +static inline bool vma_start_read(struct vm_area_struct *vma) +{ + /* Check before locking. A race might cause false locked result. */ + if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) + return false; + + if (unlikely(down_read_trylock(&vma->lock) == 0)) + return false; + + /* + * Overflow might produce false locked result. + * False unlocked result is impossible because we modify and check + * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq + * modification invalidates all existing locks. + */ + if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { + up_read(&vma->lock); + return false; + } + return true; +} + +static inline void vma_end_read(struct vm_area_struct *vma) +{ + rcu_read_lock(); /* keeps vma alive till the end of up_read */ + up_read(&vma->lock); + rcu_read_unlock(); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + mmap_assert_write_locked(vma->vm_mm); + + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + if (vma->vm_lock_seq == mm_lock_seq) + return; + + down_write(&vma->lock); + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->lock); +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ + mmap_assert_write_locked(vma->vm_mm); + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma); +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void vma_init_lock(struct vm_area_struct *vma) {} +static inline bool vma_start_read(struct vm_area_struct *vma) + { return false; } +static inline void vma_end_read(struct vm_area_struct *vma) {} +static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} + +#endif /* CONFIG_PER_VMA_LOCK */ + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -632,6 +713,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_init_lock(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f203e2562e00..843a45893991 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -503,6 +503,11 @@ struct vm_area_struct { vm_flags_t __private __vm_flags; }; +#ifdef CONFIG_PER_VMA_LOCK + int vm_lock_seq; + struct rw_semaphore lock; +#endif + /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. @@ -639,6 +644,9 @@ struct mm_struct { * init_mm.mmlist, and are protected * by mmlist_lock */ +#ifdef CONFIG_PER_VMA_LOCK + int mm_lock_seq; +#endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index e49ba91bb1f0..aab8f1b28d26 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -72,6 +72,17 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm) VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_end_write_all(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + /* No races during update due to exclusive mmap_lock being held */ + WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1); +} +#else +static inline void vma_end_write_all(struct mm_struct *mm) {} +#endif + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -114,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm) static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); + vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); + vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } diff --git a/kernel/fork.c b/kernel/fork.c index 93ec6e14bb65..0907776d8ed4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -474,6 +474,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) */ data_race(memcpy(new, orig, sizeof(*new))); INIT_LIST_HEAD(&new->anon_vma_chain); + vma_init_lock(new); dup_anon_vma_name(orig, new); } return new; @@ -1208,6 +1209,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); +#ifdef CONFIG_PER_VMA_LOCK + mm->mm_lock_seq = 0; +#endif mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; diff --git a/mm/init-mm.c b/mm/init-mm.c index c9327abb771c..33269314e060 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -37,6 +37,9 @@ struct mm_struct init_mm = { .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), +#ifdef CONFIG_PER_VMA_LOCK + .mm_lock_seq = 0, +#endif .user_ns = &init_user_ns, .cpu_bitmap = CPU_BITS_NONE, #ifdef CONFIG_IOMMU_SVA -- GitLab From c732293331a22187d59cd485879276a1da398387 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:12 -0800 Subject: [PATCH 2268/5631] mm: mark VMA as being written when changing vm_flags Updates to vm_flags have to be done with VMA marked as being written for preventing concurrent page faults or other modifications. Link: https://lkml.kernel.org/r/20230227173632.3292573-14-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 53bfb42663ea..d0a6c99aba09 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -727,28 +727,28 @@ static inline void vm_flags_init(struct vm_area_struct *vma, static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } @@ -769,7 +769,7 @@ static inline void __vm_flags_mod(struct vm_area_struct *vma, static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); __vm_flags_mod(vma, set, clear); } -- GitLab From ccf1d78d8b86e28502fa1b575a459a402177def4 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:13 -0800 Subject: [PATCH 2269/5631] mm/mmap: move vma_prepare before vma_adjust_trans_huge vma_prepare() acquires all locks required before VMA modifications. Move vma_prepare() before vma_adjust_trans_huge() so that VMA is locked before any modification. Link: https://lkml.kernel.org/r/20230227173632.3292573-15-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 6c326002184d..e8f019eecd0f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -683,12 +683,12 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, if (vma_iter_prealloc(vmi)) goto nomem; + vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); /* VMA iterator points to previous, so set to start if necessary */ if (vma_iter_addr(vmi) != start) vma_iter_set(vmi, start); - vma_prepare(&vp); vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; @@ -723,8 +723,8 @@ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, return -ENOMEM; init_vma_prep(&vp, vma); - vma_adjust_trans_huge(vma, start, end, 0); vma_prepare(&vp); + vma_adjust_trans_huge(vma, start, end, 0); if (vma->vm_start < start) vma_iter_clear(vmi, vma->vm_start, start); @@ -1010,12 +1010,12 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, if (vma_iter_prealloc(vmi)) return NULL; - vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); vma_prepare(&vp); + vma_adjust_trans_huge(vma, vma_start, vma_end, adj_start); if (vma_start < vma->vm_start || vma_end > vma->vm_end) vma_expanded = true; @@ -2214,10 +2214,10 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); - vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); + vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); if (new_below) { vma->vm_start = addr; @@ -2920,9 +2920,9 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, if (vma_iter_prealloc(vmi)) goto unacct_fail; - vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); init_vma_prep(&vp, vma); vma_prepare(&vp); + vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); vma->vm_end = addr + len; vm_flags_set(vma, VM_SOFTDIRTY); vma_iter_store(vmi, vma); -- GitLab From 55fd6fccad3172c0feaaa817f0a1283629ff183e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:14 -0800 Subject: [PATCH 2270/5631] mm/khugepaged: write-lock VMA while collapsing a huge page Protect VMA from concurrent page fault handler while collapsing a huge page. Page fault handler needs a stable PMD to use PTL and relies on per-VMA lock to prevent concurrent PMD changes. pmdp_collapse_flush(), set_huge_pmd() and collapse_and_free_pmd() can modify a PMD, which will not be detected by a page fault handler without proper locking. Before this patch, page tables can be walked under any one of the mmap_lock, the mapping lock, and the anon_vma lock; so when khugepaged unlinks and frees page tables, it must ensure that all of those either are locked or don't exist. This patch adds a fourth lock under which page tables can be traversed, and so khugepaged must also lock out that one. [surenb@google.com: vm_lock/i_mmap_rwsem inversion in retract_page_tables] Link: https://lkml.kernel.org/r/20230303213250.3555716-1-surenb@google.com [surenb@google.com: build fix] Link: https://lkml.kernel.org/r/CAJuCfpFjWhtzRE1X=J+_JjgJzNKhq-=JT8yTBSTHthwp0pqWZw@mail.gmail.com Link: https://lkml.kernel.org/r/20230227173632.3292573-16-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 41 ++++++++++++++++++++++++++++++----------- mm/khugepaged.c | 8 ++++++++ mm/rmap.c | 31 ++++++++++++++++--------------- 3 files changed, 54 insertions(+), 26 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index d0a6c99aba09..d6a2abc51e3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -665,18 +665,23 @@ static inline void vma_end_read(struct vm_area_struct *vma) rcu_read_unlock(); } -static inline void vma_start_write(struct vm_area_struct *vma) +static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) { - int mm_lock_seq; - mmap_assert_write_locked(vma->vm_mm); /* * current task is holding mmap_write_lock, both vma->vm_lock_seq and * mm->mm_lock_seq can't be concurrently modified. */ - mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); - if (vma->vm_lock_seq == mm_lock_seq) + *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + return (vma->vm_lock_seq == *mm_lock_seq); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) return; down_write(&vma->lock); @@ -684,14 +689,26 @@ static inline void vma_start_write(struct vm_area_struct *vma) up_write(&vma->lock); } +static inline bool vma_try_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return true; + + if (!down_write_trylock(&vma->vm_lock->lock)) + return false; + + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); + return true; +} + static inline void vma_assert_write_locked(struct vm_area_struct *vma) { - mmap_assert_write_locked(vma->vm_mm); - /* - * current task is holding mmap_write_lock, both vma->vm_lock_seq and - * mm->mm_lock_seq can't be concurrently modified. - */ - VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma); + int mm_lock_seq; + + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } #else /* CONFIG_PER_VMA_LOCK */ @@ -701,6 +718,8 @@ static inline bool vma_start_read(struct vm_area_struct *vma) { return false; } static inline void vma_end_read(struct vm_area_struct *vma) {} static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline bool vma_try_start_write(struct vm_area_struct *vma) + { return true; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c7317678cb10..bee7fd7db380 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1056,6 +1056,7 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; + vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, @@ -1517,6 +1518,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, goto drop_hpage; } + /* Lock the vma before taking i_mmap and page table locks */ + vma_start_write(vma); + /* * We need to lock the mapping so that from here on, only GUP-fast and * hardware page walks can access the parts of the page tables that @@ -1694,6 +1698,10 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, result = SCAN_PTE_MAPPED_HUGEPAGE; if ((cc->is_khugepaged || is_target) && mmap_write_trylock(mm)) { + /* trylock for the same lock inversion as above */ + if (!vma_try_start_write(vma)) + goto unlock_next; + /* * Re-check whether we have an ->anon_vma, because * collapse_and_free_pmd() requires that either no diff --git a/mm/rmap.c b/mm/rmap.c index 1ea2756b2797..ba901c416785 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -25,21 +25,22 @@ * mapping->invalidate_lock (in filemap_fault) * page->flags PG_locked (lock_page) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) - * mapping->i_mmap_rwsem - * anon_vma->rwsem - * mm->page_table_lock or pte_lock - * swap_lock (in swap_duplicate, swap_info_get) - * mmlist_lock (in mmput, drain_mmlist and others) - * mapping->private_lock (in block_dirty_folio) - * folio_lock_memcg move_lock (in block_dirty_folio) - * i_pages lock (widely used) - * lruvec->lru_lock (in folio_lruvec_lock_irq) - * inode->i_lock (in set_page_dirty's __mark_inode_dirty) - * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) - * i_pages lock (widely used, in set_page_dirty, - * in arch-dependent flush_dcache_mmap_lock, - * within bdi.wb->list_lock in __sync_single_inode) + * vma_start_write + * mapping->i_mmap_rwsem + * anon_vma->rwsem + * mm->page_table_lock or pte_lock + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in block_dirty_folio) + * folio_lock_memcg move_lock (in block_dirty_folio) + * i_pages lock (widely used) + * lruvec->lru_lock (in folio_lruvec_lock_irq) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * i_pages lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock -- GitLab From 10fca64a661199910c7d13077e9678c9a06bf285 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:15 -0800 Subject: [PATCH 2271/5631] mm/mmap: write-lock VMAs in vma_prepare before modifying them Write-lock all VMAs which might be affected by a merge, split, expand or shrink operations. All these operations use vma_prepare() before making the modifications, therefore it provides a centralized place to perform VMA locking. [surenb@google.com: remove unnecessary vp->vma check in vma_prepare] Link: https://lkml.kernel.org/r/20230301022720.1380780-1-surenb@google.com Link: https://lore.kernel.org/r/202302281802.J93Nma7q-lkp@intel.com/ Link: https://lkml.kernel.org/r/20230227173632.3292573-17-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: David Hildenbrand Reviewed-by: Liam R. Howlett Cc: David Howells Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Laurent Dufour Cc: Mathieu Desnoyers Cc: Matthew Wilcox Cc: Pavel Tatashin Cc: Stephen Rothwell Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/mmap.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/mmap.c b/mm/mmap.c index e8f019eecd0f..82999e0c3c31 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -502,6 +502,15 @@ static inline void init_vma_prep(struct vma_prepare *vp, */ static inline void vma_prepare(struct vma_prepare *vp) { + vma_start_write(vp->vma); + if (vp->adj_next) + vma_start_write(vp->adj_next); + /* vp->insert is always a newly created VMA, no need for locking */ + if (vp->remove) + vma_start_write(vp->remove); + if (vp->remove2) + vma_start_write(vp->remove2); + if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); -- GitLab From d6ac235de4ba6dc659eebb5f4e5ba0a8523d8424 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:16 -0800 Subject: [PATCH 2272/5631] mm/mremap: write-lock VMA while remapping it to a new address range Write-lock VMA as locked before copying it and when copy_vma produces a new VMA. Link: https://lkml.kernel.org/r/20230227173632.3292573-18-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Laurent Dufour Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton --- mm/mmap.c | 1 + mm/mremap.c | 1 + 2 files changed, 2 insertions(+) diff --git a/mm/mmap.c b/mm/mmap.c index 82999e0c3c31..8ba51e73f626 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3197,6 +3197,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); + vma_start_write(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; diff --git a/mm/mremap.c b/mm/mremap.c index 0eaa11c845b9..b11ce6c92099 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -623,6 +623,7 @@ static unsigned long move_vma(struct vm_area_struct *vma, return -ENOMEM; } + vma_start_write(vma); new_pgoff = vma->vm_pgoff + ((old_addr - vma->vm_start) >> PAGE_SHIFT); new_vma = copy_vma(&vma, new_addr, new_len, new_pgoff, &need_rmap_locks); -- GitLab From 73046fd00b069ffd198eda099dae966e152fae39 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:17 -0800 Subject: [PATCH 2273/5631] mm: write-lock VMAs before removing them from VMA tree Write-locking VMAs before isolating them ensures that page fault handlers don't operate on isolated VMAs. [surenb@google.com: mm/nommu: remove unnecessary VMA locking] Link: https://lkml.kernel.org/r/20230301190457.1498985-1-surenb@google.com Link: https://lore.kernel.org/all/Y%2F8CJQGNuMUTdLwP@localhost/ Link: https://lkml.kernel.org/r/20230227173632.3292573-19-surenb@google.com Signed-off-by: Suren Baghdasaryan Cc: David Hildenbrand Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton --- mm/mmap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/mmap.c b/mm/mmap.c index 8ba51e73f626..83adf86fd62b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2270,6 +2270,7 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, static inline int munmap_sidetree(struct vm_area_struct *vma, struct ma_state *mas_detach) { + vma_start_write(vma); mas_set_range(mas_detach, vma->vm_start, vma->vm_end - 1); if (mas_store_gfp(mas_detach, vma, GFP_KERNEL)) return -ENOMEM; -- GitLab From 98e51a2239d9d419d819cd61a2e720ebf19a8b0a Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:18 -0800 Subject: [PATCH 2274/5631] mm: conditionally write-lock VMA in free_pgtables Normally free_pgtables needs to lock affected VMAs except for the case when VMAs were isolated under VMA write-lock. munmap() does just that, isolating while holding appropriate locks and then downgrading mmap_lock and dropping per-VMA locks before freeing page tables. Add a parameter to free_pgtables for such scenario. Link: https://lkml.kernel.org/r/20230227173632.3292573-20-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/internal.h | 2 +- mm/memory.c | 6 +++++- mm/mmap.c | 5 +++-- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 82ba61d0ed6a..73b167b59cc5 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -105,7 +105,7 @@ void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long floor, - unsigned long ceiling); + unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; diff --git a/mm/memory.c b/mm/memory.c index ec7e89cc0532..8ca78ae8bba7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -362,7 +362,7 @@ void free_pgd_range(struct mmu_gather *tlb, void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *vma, unsigned long floor, - unsigned long ceiling) + unsigned long ceiling, bool mm_wr_locked) { MA_STATE(mas, mt, vma->vm_end, vma->vm_end); @@ -380,6 +380,8 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ + if (mm_wr_locked) + vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma(vma); @@ -394,6 +396,8 @@ void free_pgtables(struct mmu_gather *tlb, struct maple_tree *mt, && !is_vm_hugetlb_page(next)) { vma = next; next = mas_find(&mas, ceiling - 1); + if (mm_wr_locked) + vma_start_write(vma); unlink_anon_vmas(vma); unlink_file_vma(vma); } diff --git a/mm/mmap.c b/mm/mmap.c index 83adf86fd62b..58704ca5acd2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2167,7 +2167,8 @@ static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, update_hiwater_rss(mm); unmap_vmas(&tlb, mt, vma, start, end, mm_wr_locked); free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, - next ? next->vm_start : USER_PGTABLES_CEILING); + next ? next->vm_start : USER_PGTABLES_CEILING, + mm_wr_locked); tlb_finish_mmu(&tlb); } @@ -3064,7 +3065,7 @@ void exit_mmap(struct mm_struct *mm) set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, - USER_PGTABLES_CEILING); + USER_PGTABLES_CEILING, true); tlb_finish_mmu(&tlb); /* -- GitLab From f2e13784c16a98e269b3111ac02ae44446dd589c Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:19 -0800 Subject: [PATCH 2275/5631] kernel/fork: assert no VMA readers during its destruction Assert there are no holders of VMA lock for reading when it is about to be destroyed. Link: https://lkml.kernel.org/r/20230227173632.3292573-21-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- kernel/fork.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/fork.c b/kernel/fork.c index 0907776d8ed4..76fcc08984d4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -491,6 +491,9 @@ static void vm_area_free_rcu_cb(struct rcu_head *head) { struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); + + /* The vma should not be locked while being destroyed. */ + VM_BUG_ON_VMA(rwsem_is_locked(&vma->lock), vma); __vm_area_free(vma); } #endif -- GitLab From eeff9a5d47f89bc641034fea05501c8a6de131cb Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:20 -0800 Subject: [PATCH 2276/5631] mm/mmap: prevent pagefault handler from racing with mmu_notifier registration Page fault handlers might need to fire MMU notifications while a new notifier is being registered. Modify mm_take_all_locks to write-lock all VMAs and prevent this race with page fault handlers that would hold VMA locks. VMAs are locked before i_mmap_rwsem and anon_vma to keep the same locking order as in page fault handlers. Link: https://lkml.kernel.org/r/20230227173632.3292573-22-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- mm/mmap.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/mmap.c b/mm/mmap.c index 58704ca5acd2..18aed0ea6bd3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3494,6 +3494,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); + * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * @@ -3516,6 +3517,13 @@ int mm_take_all_locks(struct mm_struct *mm) mutex_lock(&mm_all_locks_mutex); + mas_for_each(&mas, vma, ULONG_MAX) { + if (signal_pending(current)) + goto out_unlock; + vma_start_write(vma); + } + + mas_set(&mas, 0); mas_for_each(&mas, vma, ULONG_MAX) { if (signal_pending(current)) goto out_unlock; @@ -3605,6 +3613,7 @@ void mm_drop_all_locks(struct mm_struct *mm) if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } + vma_end_write_all(mm); mutex_unlock(&mm_all_locks_mutex); } -- GitLab From 457f67be5910a2b5f1fda8af06bfe4d3492a0a4f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:21 -0800 Subject: [PATCH 2277/5631] mm: introduce vma detached flag Per-vma locking mechanism will search for VMA under RCU protection and then after locking it, has to ensure it was not removed from the VMA tree after we found it. To make this check efficient, introduce a vma->detached flag to mark VMAs which were removed from the VMA tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-23-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 11 +++++++++++ include/linux/mm_types.h | 3 +++ mm/mmap.c | 2 ++ 3 files changed, 16 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index d6a2abc51e3d..d0f289bfef01 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -711,6 +711,14 @@ static inline void vma_assert_write_locked(struct vm_area_struct *vma) VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); } +static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +{ + /* When detaching vma should be write-locked */ + if (detached) + vma_assert_write_locked(vma); + vma->detached = detached; +} + #else /* CONFIG_PER_VMA_LOCK */ static inline void vma_init_lock(struct vm_area_struct *vma) {} @@ -721,6 +729,8 @@ static inline void vma_start_write(struct vm_area_struct *vma) {} static inline bool vma_try_start_write(struct vm_area_struct *vma) { return true; } static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma, + bool detached) {} #endif /* CONFIG_PER_VMA_LOCK */ @@ -732,6 +742,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_mark_detached(vma, false); vma_init_lock(vma); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 843a45893991..3248ae45cb2e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -506,6 +506,9 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK int vm_lock_seq; struct rw_semaphore lock; + + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; #endif /* diff --git a/mm/mmap.c b/mm/mmap.c index 18aed0ea6bd3..b42f58591b9a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -599,6 +599,7 @@ static inline void vma_complete(struct vma_prepare *vp, if (vp->remove) { again: + vma_mark_detached(vp->remove, true); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); @@ -2276,6 +2277,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma, if (mas_store_gfp(mas_detach, vma, GFP_KERNEL)) return -ENOMEM; + vma_mark_detached(vma, true); if (vma->vm_flags & VM_LOCKED) vma->vm_mm->locked_vm -= vma_pages(vma); -- GitLab From 50ee32537206140e4cf6e47024be29a84d458d49 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:22 -0800 Subject: [PATCH 2278/5631] mm: introduce lock_vma_under_rcu to be used from arch-specific code Introduce lock_vma_under_rcu function to lookup and lock a VMA during page fault handling. When VMA is not found, can't be locked or changes after being locked, the function returns NULL. The lookup is performed under RCU protection to prevent the found VMA from being destroyed before the VMA lock is acquired. VMA lock statistics are updated according to the results. For now only anonymous VMAs can be searched this way. In other cases the function returns NULL. Link: https://lkml.kernel.org/r/20230227173632.3292573-24-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 +++ mm/memory.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index d0f289bfef01..0619f9fa7581 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -719,6 +719,9 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) vma->detached = detached; } +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address); + #else /* CONFIG_PER_VMA_LOCK */ static inline void vma_init_lock(struct vm_area_struct *vma) {} diff --git a/mm/memory.c b/mm/memory.c index 8ca78ae8bba7..1235de20af73 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5232,6 +5232,52 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL_GPL(handle_mm_fault); +#ifdef CONFIG_PER_VMA_LOCK +/* + * Lookup and lock a VMA under RCU protection. Returned VMA is guaranteed to be + * stable and not isolated. If the VMA is not found or is being modified the + * function returns NULL. + */ +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address) +{ + MA_STATE(mas, &mm->mm_mt, address, address); + struct vm_area_struct *vma; + + rcu_read_lock(); +retry: + vma = mas_walk(&mas); + if (!vma) + goto inval; + + /* Only anonymous vmas are supported for now */ + if (!vma_is_anonymous(vma)) + goto inval; + + if (!vma_start_read(vma)) + goto inval; + + /* Check since vm_start/vm_end might change before we lock the VMA */ + if (unlikely(address < vma->vm_start || address >= vma->vm_end)) { + vma_end_read(vma); + goto inval; + } + + /* Check if the VMA got isolated after we found it */ + if (vma->detached) { + vma_end_read(vma); + /* The area was replaced with another one */ + goto retry; + } + + rcu_read_unlock(); + return vma; +inval: + rcu_read_unlock(); + return NULL; +} +#endif /* CONFIG_PER_VMA_LOCK */ + #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. -- GitLab From 2ac0af1b66e3b66307f53b1cc446514308ec466d Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:23 -0800 Subject: [PATCH 2279/5631] mm: fall back to mmap_lock if vma->anon_vma is not yet set When vma->anon_vma is not set, page fault handler will set it by either reusing anon_vma of an adjacent VMA if VMAs are compatible or by allocating a new one. find_mergeable_anon_vma() walks VMA tree to find a compatible adjacent VMA and that requires not only the faulting VMA to be stable but also the tree structure and other VMAs inside that tree. Therefore locking just the faulting VMA is not enough for this search. Fall back to taking mmap_lock when vma->anon_vma is not set. This situation happens only on the first page fault and should not affect overall performance. Link: https://lkml.kernel.org/r/20230227173632.3292573-25-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Signed-off-by: Andrew Morton --- mm/memory.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/memory.c b/mm/memory.c index 1235de20af73..10d497a5296c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5254,6 +5254,10 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, if (!vma_is_anonymous(vma)) goto inval; + /* find_mergeable_anon_vma uses adjacent vmas which are not locked */ + if (!vma->anon_vma) + goto inval; + if (!vma_start_read(vma)) goto inval; -- GitLab From 55324e46eb8b886ecd08c9a089d3a694c705b3b0 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:24 -0800 Subject: [PATCH 2280/5631] mm: add FAULT_FLAG_VMA_LOCK flag Add a new flag to distinguish page faults handled under protection of per-vma lock. [surenb@google.com: document FAULT_FLAG_VMA_LOCK flag] Link: https://lkml.kernel.org/r/20230301022720.1380780-2-surenb@google.com Link: https://lore.kernel.org/all/20230301113648.7c279865@canb.auug.org.au/ Link: https://lkml.kernel.org/r/20230227173632.3292573-26-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Laurent Dufour Cc: Dan Carpenter Cc: David Hildenbrand Cc: David Howells Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Liam R. Howlett Cc: Mathieu Desnoyers Cc: Matthew Wilcox Cc: Pavel Tatashin Cc: Yu Zhao Signed-off-by: Andrew Morton --- include/linux/mm.h | 3 ++- include/linux/mm_types.h | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 0619f9fa7581..1876825d6700 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -479,7 +479,8 @@ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3248ae45cb2e..3a6cf4c2edd0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1049,6 +1049,7 @@ typedef struct { * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. + * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -1086,6 +1087,7 @@ enum fault_flag { FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, + FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; -- GitLab From 17c05f18e54158a3eed0c22c85b7a756b63dcc01 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:25 -0800 Subject: [PATCH 2281/5631] mm: prevent do_swap_page from handling page faults under VMA lock Due to the possibility of do_swap_page dropping mmap_lock, abort fault handling under VMA lock and retry holding mmap_lock. This can be handled more gracefully in the future. Link: https://lkml.kernel.org/r/20230227173632.3292573-27-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Laurent Dufour Signed-off-by: Andrew Morton --- mm/memory.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/mm/memory.c b/mm/memory.c index 10d497a5296c..70f4b1222e5d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3697,6 +3697,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!pte_unmap_same(vmf)) goto out; + if (vmf->flags & FAULT_FLAG_VMA_LOCK) { + ret = VM_FAULT_RETRY; + goto out; + } + entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { -- GitLab From 444eeb17437a0ef526c606e9141a415d3b7dfddd Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:26 -0800 Subject: [PATCH 2282/5631] mm: prevent userfaults to be handled under per-vma lock Due to the possibility of handle_userfault dropping mmap_lock, avoid fault handling under VMA lock and retry holding mmap_lock. This can be handled more gracefully in the future. Link: https://lkml.kernel.org/r/20230227173632.3292573-28-surenb@google.com Signed-off-by: Suren Baghdasaryan Suggested-by: Peter Xu Signed-off-by: Andrew Morton --- mm/memory.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/memory.c b/mm/memory.c index 70f4b1222e5d..55ac9cdfd398 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5266,6 +5266,15 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, if (!vma_start_read(vma)) goto inval; + /* + * Due to the possibility of userfault handler dropping mmap_lock, avoid + * it for now and fall back to page fault handling under mmap_lock. + */ + if (userfaultfd_armed(vma)) { + vma_end_read(vma); + goto inval; + } + /* Check since vm_start/vm_end might change before we lock the VMA */ if (unlikely(address < vma->vm_start || address >= vma->vm_end)) { vma_end_read(vma); -- GitLab From 52f238653e452e0fda61e880f263a173d219acd1 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:27 -0800 Subject: [PATCH 2283/5631] mm: introduce per-VMA lock statistics Add a new CONFIG_PER_VMA_LOCK_STATS config option to dump extra statistics about handling page fault under VMA lock. Link: https://lkml.kernel.org/r/20230227173632.3292573-29-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/vm_event_item.h | 6 ++++++ include/linux/vmstat.h | 6 ++++++ mm/Kconfig.debug | 6 ++++++ mm/memory.c | 2 ++ mm/vmstat.c | 6 ++++++ 5 files changed, 26 insertions(+) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 7f5d1caf5890..8abfa1240040 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -149,6 +149,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, +#endif +#ifdef CONFIG_PER_VMA_LOCK_STATS + VMA_LOCK_SUCCESS, + VMA_LOCK_ABORT, + VMA_LOCK_RETRY, + VMA_LOCK_MISS, #endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 19cf5b6892ce..fed855bae6d8 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,6 +125,12 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS +#define count_vm_vma_lock_event(x) count_vm_event(x) +#else +#define count_vm_vma_lock_event(x) do {} while (0) +#endif + #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index c3547a373c9c..4965a7333a3f 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -279,3 +279,9 @@ config DEBUG_KMEMLEAK_AUTO_SCAN If unsure, say Y. +config PER_VMA_LOCK_STATS + bool "Statistics for per-vma locks" + depends on PER_VMA_LOCK + default y + help + Statistics for per-vma locks. diff --git a/mm/memory.c b/mm/memory.c index 55ac9cdfd398..9999574a9636 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5284,6 +5284,7 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, /* Check if the VMA got isolated after we found it */ if (vma->detached) { vma_end_read(vma); + count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ goto retry; } @@ -5292,6 +5293,7 @@ struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, return vma; inval: rcu_read_unlock(); + count_vm_vma_lock_event(VMA_LOCK_ABORT); return NULL; } #endif /* CONFIG_PER_VMA_LOCK */ diff --git a/mm/vmstat.c b/mm/vmstat.c index b7307627772d..c28046371b45 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1399,6 +1399,12 @@ const char * const vmstat_text[] = { "direct_map_level2_splits", "direct_map_level3_splits", #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS + "vma_lock_success", + "vma_lock_abort", + "vma_lock_retry", + "vma_lock_miss", +#endif #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ -- GitLab From 0bff0aaea03e2a3ed6bfa302155cca8a432a1829 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:28 -0800 Subject: [PATCH 2284/5631] x86/mm: try VMA lock-based page fault handling first Attempt VMA lock-based page fault handling first, and fall back to the existing mmap_lock-based handling if that fails. Link: https://lkml.kernel.org/r/20230227173632.3292573-30-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/x86/Kconfig | 1 + arch/x86/mm/fault.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a825bf031f49..df21fba77db1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -27,6 +27,7 @@ config X86_64 # Options that are inherently 64-bit kernel only: select ARCH_HAS_GIGANTIC_PAGE select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 + select ARCH_SUPPORTS_PER_VMA_LOCK select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_SOFT_DIRTY select MODULES_USE_ELF_RELA diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a498ae1fbe66..e4399983c50c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -19,6 +19,7 @@ #include /* faulthandler_disabled() */ #include /* efi_crash_gracefully_on_page_fault()*/ #include +#include /* find_and_lock_vma() */ #include /* boot_cpu_has, ... */ #include /* dotraplinkage, ... */ @@ -1333,6 +1334,38 @@ void do_user_addr_fault(struct pt_regs *regs, } #endif +#ifdef CONFIG_PER_VMA_LOCK + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, address); + if (!vma) + goto lock_mmap; + + if (unlikely(access_error(error_code, vma))) { + vma_end_read(vma); + goto lock_mmap; + } + fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR, + ARCH_DEFAULT_PKEY); + return; + } +lock_mmap: +#endif /* CONFIG_PER_VMA_LOCK */ + /* * Kernel-mode access to the user address space should only occur * on well-defined single instructions listed in the exception @@ -1433,6 +1466,9 @@ void do_user_addr_fault(struct pt_regs *regs, } mmap_read_unlock(mm); +#ifdef CONFIG_PER_VMA_LOCK +done: +#endif if (likely(!(fault & VM_FAULT_ERROR))) return; -- GitLab From cd7f176aea5f5929a09a91c661a26912cc995d1b Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:29 -0800 Subject: [PATCH 2285/5631] arm64/mm: try VMA lock-based page fault handling first Attempt VMA lock-based page fault handling first, and fall back to the existing mmap_lock-based handling if that fails. Link: https://lkml.kernel.org/r/20230227173632.3292573-31-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 1 + arch/arm64/mm/fault.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index cb5c6aa3254e..e60baf7859d1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -95,6 +95,7 @@ config ARM64 select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_SUPPORTS_PAGE_TABLE_CHECK + select ARCH_SUPPORTS_PER_VMA_LOCK select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index f4cb0f85ccf4..9e0db5c387e3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -535,6 +535,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, unsigned long vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); +#ifdef CONFIG_PER_VMA_LOCK + struct vm_area_struct *vma; +#endif if (kprobe_page_fault(regs, esr)) return 0; @@ -585,6 +588,36 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); +#ifdef CONFIG_PER_VMA_LOCK + if (!(mm_flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, addr); + if (!vma) + goto lock_mmap; + + if (!(vma->vm_flags & vm_flags)) { + vma_end_read(vma); + goto lock_mmap; + } + fault = handle_mm_fault(vma, addr & PAGE_MASK, + mm_flags | FAULT_FLAG_VMA_LOCK, regs); + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto no_context; + return 0; + } +lock_mmap: +#endif /* CONFIG_PER_VMA_LOCK */ /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -628,6 +661,9 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, } mmap_read_unlock(mm); +#ifdef CONFIG_PER_VMA_LOCK +done: +#endif /* * Handle the "normal" (no error) case first. */ -- GitLab From 70d4cbc80c88251de0a5b3e8df3275901f1fa99a Mon Sep 17 00:00:00 2001 From: Laurent Dufour Date: Mon, 27 Feb 2023 09:36:30 -0800 Subject: [PATCH 2286/5631] powerc/mm: try VMA lock-based page fault handling first Attempt VMA lock-based page fault handling first, and fall back to the existing mmap_lock-based handling if that fails. Copied from "x86/mm: try VMA lock-based page fault handling first" [ldufour@linux.ibm.com: powerpc/mm: fix mmap_lock bad unlock] Link: https://lkml.kernel.org/r/20230306154244.17560-1-ldufour@linux.ibm.com Link: https://lore.kernel.org/linux-mm/842502FB-F99C-417C-9648-A37D0ECDC9CE@linux.ibm.com Link: https://lkml.kernel.org/r/20230227173632.3292573-32-surenb@google.com Signed-off-by: Laurent Dufour Signed-off-by: Suren Baghdasaryan Cc: Sachin Sant Signed-off-by: Andrew Morton --- arch/powerpc/mm/fault.c | 37 ++++++++++++++++++++++++++ arch/powerpc/platforms/powernv/Kconfig | 1 + arch/powerpc/platforms/pseries/Kconfig | 1 + 3 files changed, 39 insertions(+) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index af46aa88422b..531177a4ee08 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -474,6 +474,40 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, if (is_exec) flags |= FAULT_FLAG_INSTRUCTION; +#ifdef CONFIG_PER_VMA_LOCK + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, address); + if (!vma) + goto lock_mmap; + + if (unlikely(access_pkey_error(is_write, is_exec, + (error_code & DSISR_KEYFAULT), vma))) { + vma_end_read(vma); + goto lock_mmap; + } + + if (unlikely(access_error(is_write, is_exec, vma))) { + vma_end_read(vma); + goto lock_mmap; + } + + fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + + if (fault_signal_pending(fault, regs)) + return user_mode(regs) ? 0 : SIGBUS; + +lock_mmap: +#endif /* CONFIG_PER_VMA_LOCK */ + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -550,6 +584,9 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address, mmap_read_unlock(current->mm); +#ifdef CONFIG_PER_VMA_LOCK +done: +#endif if (unlikely(fault & VM_FAULT_ERROR)) return mm_fault_error(regs, address, fault); diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index ae248a161b43..70a46acc70d6 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -16,6 +16,7 @@ config PPC_POWERNV select PPC_DOORBELL select MMU_NOTIFIER select FORCE_SMP + select ARCH_SUPPORTS_PER_VMA_LOCK default y config OPAL_PRD diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 21b22bf16ce6..4ebf2ef2845d 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -22,6 +22,7 @@ config PPC_PSERIES select HOTPLUG_CPU select FORCE_SMP select SWIOTLB + select ARCH_SUPPORTS_PER_VMA_LOCK default y config PARAVIRT -- GitLab From 0d2ebf9c3f7822e7ba3e4792ea3b6b19aa2da34a Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:31 -0800 Subject: [PATCH 2287/5631] mm/mmap: free vm_area_struct without call_rcu in exit_mmap call_rcu() can take a long time when callback offloading is enabled. Its use in the vm_area_free can cause regressions in the exit path when multiple VMAs are being freed. Because exit_mmap() is called only after the last mm user drops its refcount, the page fault handlers can't be racing with it. Any other possible user like oom-reaper or process_mrelease are already synchronized using mmap_lock. Therefore exit_mmap() can free VMAs directly, without the use of call_rcu(). Expose __vm_area_free() and use it from exit_mmap() to avoid possible call_rcu() floods and performance regressions caused by it. Link: https://lkml.kernel.org/r/20230227173632.3292573-33-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 ++ kernel/fork.c | 2 +- mm/mmap.c | 11 +++++++---- 3 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1876825d6700..f31c75dc190e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -257,6 +257,8 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); +/* Use only if VMA has no other users */ +void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; diff --git a/kernel/fork.c b/kernel/fork.c index 76fcc08984d4..f86f7e917954 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -480,7 +480,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) return new; } -static void __vm_area_free(struct vm_area_struct *vma) +void __vm_area_free(struct vm_area_struct *vma) { free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); diff --git a/mm/mmap.c b/mm/mmap.c index b42f58591b9a..511f656eb423 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -133,7 +133,7 @@ void unlink_file_vma(struct vm_area_struct *vma) /* * Close a vm structure and free it. */ -static void remove_vma(struct vm_area_struct *vma) +static void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); if (vma->vm_ops && vma->vm_ops->close) @@ -141,7 +141,10 @@ static void remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); - vm_area_free(vma); + if (unreachable) + __vm_area_free(vma); + else + vm_area_free(vma); } static inline struct vm_area_struct *vma_prev_limit(struct vma_iterator *vmi, @@ -2145,7 +2148,7 @@ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas) if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, -nrpages); - remove_vma(vma); + remove_vma(vma, false); } vm_unacct_memory(nr_accounted); validate_mm(mm); @@ -3078,7 +3081,7 @@ void exit_mmap(struct mm_struct *mm) do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); - remove_vma(vma); + remove_vma(vma, true); count++; cond_resched(); } while ((vma = mas_find(&mas, ULONG_MAX)) != NULL); -- GitLab From c7f8f31c00d187a2c71a241c7f2bd6aa102a4e6f Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Mon, 27 Feb 2023 09:36:32 -0800 Subject: [PATCH 2288/5631] mm: separate vma->lock from vm_area_struct vma->lock being part of the vm_area_struct causes performance regression during page faults because during contention its count and owner fields are constantly updated and having other parts of vm_area_struct used during page fault handling next to them causes constant cache line bouncing. Fix that by moving the lock outside of the vm_area_struct. All attempts to keep vma->lock inside vm_area_struct in a separate cache line still produce performance regression especially on NUMA machines. Smallest regression was achieved when lock is placed in the fourth cache line but that bloats vm_area_struct to 256 bytes. Considering performance and memory impact, separate lock looks like the best option. It increases memory footprint of each VMA but that can be optimized later if the new size causes issues. Note that after this change vma_init() does not allocate or initialize vma->lock anymore. A number of drivers allocate a pseudo VMA on the stack but they never use the VMA's lock, therefore it does not need to be allocated. The future drivers which might need the VMA lock should use vm_area_alloc()/vm_area_free() to allocate the VMA. Link: https://lkml.kernel.org/r/20230227173632.3292573-34-surenb@google.com Signed-off-by: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mm.h | 23 ++++++------- include/linux/mm_types.h | 6 +++- kernel/fork.c | 73 ++++++++++++++++++++++++++++++++-------- 3 files changed, 74 insertions(+), 28 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index f31c75dc190e..f5487a86b154 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -628,12 +628,6 @@ struct vm_operations_struct { }; #ifdef CONFIG_PER_VMA_LOCK -static inline void vma_init_lock(struct vm_area_struct *vma) -{ - init_rwsem(&vma->lock); - vma->vm_lock_seq = -1; -} - /* * Try to read-lock a vma. The function is allowed to occasionally yield false * locked result to avoid performance overhead, in which case we fall back to @@ -645,17 +639,17 @@ static inline bool vma_start_read(struct vm_area_struct *vma) if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) return false; - if (unlikely(down_read_trylock(&vma->lock) == 0)) + if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) return false; /* * Overflow might produce false locked result. * False unlocked result is impossible because we modify and check - * vma->vm_lock_seq under vma->lock protection and mm->mm_lock_seq + * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq * modification invalidates all existing locks. */ if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { - up_read(&vma->lock); + up_read(&vma->vm_lock->lock); return false; } return true; @@ -664,7 +658,7 @@ static inline bool vma_start_read(struct vm_area_struct *vma) static inline void vma_end_read(struct vm_area_struct *vma) { rcu_read_lock(); /* keeps vma alive till the end of up_read */ - up_read(&vma->lock); + up_read(&vma->vm_lock->lock); rcu_read_unlock(); } @@ -687,9 +681,9 @@ static inline void vma_start_write(struct vm_area_struct *vma) if (__is_vma_write_locked(vma, &mm_lock_seq)) return; - down_write(&vma->lock); + down_write(&vma->vm_lock->lock); vma->vm_lock_seq = mm_lock_seq; - up_write(&vma->lock); + up_write(&vma->vm_lock->lock); } static inline bool vma_try_start_write(struct vm_area_struct *vma) @@ -740,6 +734,10 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, #endif /* CONFIG_PER_VMA_LOCK */ +/* + * WARNING: vma_init does not initialize vma->vm_lock. + * Use vm_area_alloc()/vm_area_free() if vma needs locking. + */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -749,7 +747,6 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); - vma_init_lock(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3a6cf4c2edd0..1b3031e95215 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -471,6 +471,10 @@ struct anon_vma_name { char name[]; }; +struct vma_lock { + struct rw_semaphore lock; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -505,7 +509,7 @@ struct vm_area_struct { #ifdef CONFIG_PER_VMA_LOCK int vm_lock_seq; - struct rw_semaphore lock; + struct vma_lock *vm_lock; /* Flag to indicate areas detached from the mm->mm_mt tree */ bool detached; diff --git a/kernel/fork.c b/kernel/fork.c index f86f7e917954..c75088367bb4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -451,13 +451,49 @@ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; +#ifdef CONFIG_PER_VMA_LOCK + +/* SLAB cache for vm_area_struct.lock */ +static struct kmem_cache *vma_lock_cachep; + +static bool vma_lock_alloc(struct vm_area_struct *vma) +{ + vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); + if (!vma->vm_lock) + return false; + + init_rwsem(&vma->vm_lock->lock); + vma->vm_lock_seq = -1; + + return true; +} + +static inline void vma_lock_free(struct vm_area_struct *vma) +{ + kmem_cache_free(vma_lock_cachep, vma->vm_lock); +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } +static inline void vma_lock_free(struct vm_area_struct *vma) {} + +#endif /* CONFIG_PER_VMA_LOCK */ + struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); - if (vma) - vma_init(vma, mm); + if (!vma) + return NULL; + + vma_init(vma, mm); + if (!vma_lock_alloc(vma)) { + kmem_cache_free(vm_area_cachep, vma); + return NULL; + } + return vma; } @@ -465,24 +501,30 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); - if (new) { - ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); - ASSERT_EXCLUSIVE_WRITER(orig->vm_file); - /* - * orig->shared.rb may be modified concurrently, but the clone - * will be reinitialized. - */ - data_race(memcpy(new, orig, sizeof(*new))); - INIT_LIST_HEAD(&new->anon_vma_chain); - vma_init_lock(new); - dup_anon_vma_name(orig, new); + if (!new) + return NULL; + + ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); + ASSERT_EXCLUSIVE_WRITER(orig->vm_file); + /* + * orig->shared.rb may be modified concurrently, but the clone + * will be reinitialized. + */ + data_race(memcpy(new, orig, sizeof(*new))); + if (!vma_lock_alloc(new)) { + kmem_cache_free(vm_area_cachep, new); + return NULL; } + INIT_LIST_HEAD(&new->anon_vma_chain); + dup_anon_vma_name(orig, new); + return new; } void __vm_area_free(struct vm_area_struct *vma) { free_anon_vma_name(vma); + vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } @@ -493,7 +535,7 @@ static void vm_area_free_rcu_cb(struct rcu_head *head) vm_rcu); /* The vma should not be locked while being destroyed. */ - VM_BUG_ON_VMA(rwsem_is_locked(&vma->lock), vma); + VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); __vm_area_free(vma); } #endif @@ -3152,6 +3194,9 @@ void __init proc_caches_init(void) NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); +#ifdef CONFIG_PER_VMA_LOCK + vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT); +#endif mmap_init(); nsproxy_cache_init(); } -- GitLab From e06f47a16573decc57498f2d02f9af3bb3e84cf2 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 14 Mar 2023 14:28:08 +0100 Subject: [PATCH 2289/5631] s390/mm: try VMA lock-based page fault handling first Attempt VMA lock-based page fault handling first, and fall back to the existing mmap_lock-based handling if that fails. This is the s390 variant of "x86/mm: try VMA lock-based page fault handling first". Link: https://lkml.kernel.org/r/20230314132808.1266335-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens Cc: Alexander Gordeev Cc: Christian Borntraeger Cc: Gerald Schaefer Cc: Suren Baghdasaryan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- arch/s390/Kconfig | 1 + arch/s390/mm/fault.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9809c74e1240..548b5b587003 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -120,6 +120,7 @@ config S390 select ARCH_SUPPORTS_DEBUG_PAGEALLOC select ARCH_SUPPORTS_HUGETLBFS select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_PER_VMA_LOCK select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index a2632fd97d00..b65144c392b0 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -407,6 +407,30 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access) access = VM_WRITE; if (access == VM_WRITE) flags |= FAULT_FLAG_WRITE; +#ifdef CONFIG_PER_VMA_LOCK + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + vma = lock_vma_under_rcu(mm, address); + if (!vma) + goto lock_mmap; + if (!(vma->vm_flags & access)) { + vma_end_read(vma); + goto lock_mmap; + } + fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); + vma_end_read(vma); + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto out; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + /* Quick path to respond to signals */ + if (fault_signal_pending(fault, regs)) { + fault = VM_FAULT_SIGNAL; + goto out; + } +lock_mmap: +#endif /* CONFIG_PER_VMA_LOCK */ mmap_read_lock(mm); gmap = NULL; -- GitLab From ef6a22b70f6d90449a5c797b8968a682824e2011 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 1 Mar 2023 17:49:00 +0530 Subject: [PATCH 2290/5631] sched/numa: apply the scan delay to every new vma Pach series "sched/numa: Enhance vma scanning", v3. The patchset proposes one of the enhancements to numa vma scanning suggested by Mel. This is continuation of [3]. Reposting the rebased patchset to akpm mm-unstable tree (March 1) Existing mechanism of scan period involves, scan period derived from per-thread stats. Process Adaptive autoNUMA [1] proposed to gather NUMA fault stats at per-process level to capture aplication behaviour better. During that course of discussion, Mel proposed several ideas to enhance current numa balancing. One of the suggestion was below Track what threads access a VMA. The suggestion was to use an unsigned long pid_mask and use the lower bits to tag approximately what threads access a VMA. Skip VMAs that did not trap a fault. This would be approximate because of PID collisions but would reduce scanning of areas the thread is not interested in. The above suggestion intends not to penalize threads that has no interest in the vma, thus reduce scanning overhead. V3 changes are mostly based on PeterZ comments (details below in changes) Summary of patchset: Current patchset implements: 1. Delay the vma scanning logic for newly created VMA's so that additional overhead of scanning is not incurred for short lived tasks (implementation by Mel) 2. Store the information of tasks accessing VMA in 2 windows. It is regularly cleared in (4*sysctl_numa_balancing_scan_delay) interval. The above time is derived from experimenting (Suggested by PeterZ) to balance between frequent clearing vs obsolete access data 3. hash_32 used to encode task index accessing VMA information 4. VMA's acess information is used to skip scanning for the tasks which had not accessed VMA Changes since V2: patch1: - Renaming of structure, macro to function, - Add explanation to heuristics - Adding more details from result (PeterZ) Patch2: - Usage of test and set bit (PeterZ) - Move storing access PID info to numa_migrate_prep() - Add a note on fainess among tasks allowed to scan (PeterZ) Patch3: - Maintain two windows of access PID information (PeterZ supported implementation and Gave idea to extend to N if needed) Patch4: - Apply hash_32 function to track VMA accessing PIDs (PeterZ) Changes since RFC V1: - Include Mel's vma scan delay patch - Change the accessing pid store logic (Thanks Mel) - Fencing structure / code to NUMA_BALANCING (David, Mel) - Adding clearing access PID logic (Mel) - Descriptive change log ( Mike Rapoport) Things to ponder over: ========================================== - Improvement to clearing accessing PIDs logic (discussed in-detail in patch3 itself (Done in this patchset by implementing 2 window history) - Current scan period is not changed in the patchset, so we do see frequent tries to scan. Relaxing scan period dynamically could improve results further. [1] sched/numa: Process Adaptive autoNUMA Link: https://lore.kernel.org/lkml/20220128052851.17162-1-bharata@amd.com/T/ [2] RFC V1 Link: https://lore.kernel.org/all/cover.1673610485.git.raghavendra.kt@amd.com/ [3] V2 Link: https://lore.kernel.org/lkml/cover.1675159422.git.raghavendra.kt@amd.com/ Results: Summary: Huge autonuma cost reduction seen in mmtest. Kernbench improvement is more than 5% and huge system time (80%+) improvement from mmtest autonuma. (dbench had huge std deviation to post) kernbench =========== 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Amean user-256 22002.51 ( 0.00%) 22649.95 * -2.94%* Amean syst-256 10162.78 ( 0.00%) 8214.13 * 19.17%* Amean elsp-256 160.74 ( 0.00%) 156.92 * 2.38%* Duration User 66017.43 67959.84 Duration System 30503.15 24657.03 Duration Elapsed 504.61 493.12 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Ops NUMA alloc hit 1738835089.00 1738780310.00 Ops NUMA alloc local 1738834448.00 1738779711.00 Ops NUMA base-page range updates 477310.00 392566.00 Ops NUMA PTE updates 477310.00 392566.00 Ops NUMA hint faults 96817.00 87555.00 Ops NUMA hint local faults % 10150.00 2192.00 Ops NUMA hint local percent 10.48 2.50 Ops NUMA pages migrated 86660.00 85363.00 Ops AutoNUMA cost 489.07 442.14 autonumabench =============== 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Amean syst-NUMA01 399.50 ( 0.00%) 52.05 * 86.97%* Amean syst-NUMA01_THREADLOCAL 0.21 ( 0.00%) 0.22 * -5.41%* Amean syst-NUMA02 0.80 ( 0.00%) 0.78 * 2.68%* Amean syst-NUMA02_SMT 0.65 ( 0.00%) 0.68 * -3.95%* Amean elsp-NUMA01 313.26 ( 0.00%) 313.11 * 0.05%* Amean elsp-NUMA01_THREADLOCAL 1.06 ( 0.00%) 1.08 * -1.76%* Amean elsp-NUMA02 3.19 ( 0.00%) 3.24 * -1.52%* Amean elsp-NUMA02_SMT 3.72 ( 0.00%) 3.61 * 2.92%* Duration User 396433.47 324835.96 Duration System 2808.70 376.66 Duration Elapsed 2258.61 2258.12 6.2.0-mmunstable-base 6.2.0-mmunstable-patched Ops NUMA alloc hit 59921806.00 49623489.00 Ops NUMA alloc miss 0.00 0.00 Ops NUMA interleave hit 0.00 0.00 Ops NUMA alloc local 59920880.00 49622594.00 Ops NUMA base-page range updates 152259275.00 50075.00 Ops NUMA PTE updates 152259275.00 50075.00 Ops NUMA PMD updates 0.00 0.00 Ops NUMA hint faults 154660352.00 39014.00 Ops NUMA hint local faults % 138550501.00 23139.00 Ops NUMA hint local percent 89.58 59.31 Ops NUMA pages migrated 8179067.00 14147.00 Ops AutoNUMA cost 774522.98 195.69 This patch (of 4): Currently whenever a new task is created we wait for sysctl_numa_balancing_scan_delay to avoid unnessary scanning overhead. Extend the same logic to new or very short-lived VMAs. [raghavendra.kt@amd.com: add initialization in vm_area_dup())] Link: https://lkml.kernel.org/r/cover.1677672277.git.raghavendra.kt@amd.com Link: https://lkml.kernel.org/r/7a6fbba87c8b51e67efd3e74285bb4cb311a16ca.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Mel Gorman Signed-off-by: Raghavendra K T Cc: Bharata B Rao Cc: David Hildenbrand Cc: Ingo Molnar Cc: Mike Rapoport Cc: Peter Zijlstra Cc: Disha Talreja Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 ++++++++++++++++ include/linux/mm_types.h | 7 +++++++ kernel/fork.c | 2 ++ kernel/sched/fair.c | 19 +++++++++++++++++++ 4 files changed, 44 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index f5487a86b154..9f08a11b355c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -29,6 +29,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -627,6 +628,20 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_NUMA_BALANCING +static inline void vma_numab_state_init(struct vm_area_struct *vma) +{ + vma->numab_state = NULL; +} +static inline void vma_numab_state_free(struct vm_area_struct *vma) +{ + kfree(vma->numab_state); +} +#else +static inline void vma_numab_state_init(struct vm_area_struct *vma) {} +static inline void vma_numab_state_free(struct vm_area_struct *vma) {} +#endif /* CONFIG_NUMA_BALANCING */ + #ifdef CONFIG_PER_VMA_LOCK /* * Try to read-lock a vma. The function is allowed to occasionally yield false @@ -747,6 +762,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); vma_mark_detached(vma, false); + vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1b3031e95215..3e1a42673769 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -475,6 +475,10 @@ struct vma_lock { struct rw_semaphore lock; }; +struct vma_numab_state { + unsigned long next_scan; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -560,6 +564,9 @@ struct vm_area_struct { #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ +#endif +#ifdef CONFIG_NUMA_BALANCING + struct vma_numab_state *numab_state; /* NUMA Balancing state */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; diff --git a/kernel/fork.c b/kernel/fork.c index c75088367bb4..2bde99037652 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -516,6 +516,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) return NULL; } INIT_LIST_HEAD(&new->anon_vma_chain); + vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; @@ -523,6 +524,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) void __vm_area_free(struct vm_area_struct *vma) { + vma_numab_state_free(vma); free_anon_vma_name(vma); vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6986ea31c984..7072de1686d5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3027,6 +3027,25 @@ static void task_numa_work(struct callback_head *work) if (!vma_is_accessible(vma)) continue; + /* Initialise new per-VMA NUMAB state. */ + if (!vma->numab_state) { + vma->numab_state = kzalloc(sizeof(struct vma_numab_state), + GFP_KERNEL); + if (!vma->numab_state) + continue; + + vma->numab_state->next_scan = now + + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + } + + /* + * Scanning the VMA's of short lived tasks add more overhead. So + * delay the scan for new VMAs. + */ + if (mm->numa_scan_seq && time_before(jiffies, + vma->numab_state->next_scan)) + continue; + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); -- GitLab From fc137c0ddab29b591db6a091dc6d7ce20ccb73f2 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:01 +0530 Subject: [PATCH 2291/5631] sched/numa: enhance vma scanning logic During Numa scanning make sure only relevant vmas of the tasks are scanned. Before: All the tasks of a process participate in scanning the vma even if they do not access vma in it's lifespan. Now: Except cases of first few unconditional scans, if a process do not touch vma (exluding false positive cases of PID collisions) tasks no longer scan all vma Logic used: 1) 6 bits of PID used to mark active bit in vma numab status during fault to remember PIDs accessing vma. (Thanks Mel) 2) Subsequently in scan path, vma scanning is skipped if current PID had not accessed vma. 3) First two times we do allow unconditional scan to preserve earlier behaviour of scanning. Acknowledgement to Bharata B Rao for initial patch to store pid information and Peter Zijlstra (Usage of test and set bit) Link: https://lkml.kernel.org/r/092f03105c7c1d3450f4636b1ea350407f07640e.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Mel Gorman Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/linux/mm.h | 14 ++++++++++++++ include/linux/mm_types.h | 1 + kernel/sched/fair.c | 19 +++++++++++++++++++ mm/memory.c | 3 +++ 4 files changed, 37 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 9f08a11b355c..215327daffae 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1686,6 +1686,16 @@ static inline int xchg_page_access_time(struct page *page, int time) last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ + unsigned int pid_bit; + + pid_bit = current->pid % BITS_PER_LONG; + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) { + __set_bit(pid_bit, &vma->numab_state->access_pids); + } +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { @@ -1735,6 +1745,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3e1a42673769..f8cbd8efc7cb 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -477,6 +477,7 @@ struct vma_lock { struct vma_numab_state { unsigned long next_scan; + unsigned long access_pids; }; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7072de1686d5..ef27b5931480 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2928,6 +2928,21 @@ static void reset_ptenuma_scan(struct task_struct *p) p->mm->numa_scan_offset = 0; } +static bool vma_is_accessed(struct vm_area_struct *vma) +{ + /* + * Allow unconditional access first two times, so that all the (pages) + * of VMAs get prot_none fault introduced irrespective of accesses. + * This is also done to avoid any side effect of task scanning + * amplifying the unfairness of disjoint set of VMAs' access. + */ + if (READ_ONCE(current->mm->numa_scan_seq) < 2) + return true; + + return test_bit(current->pid % BITS_PER_LONG, + &vma->numab_state->access_pids); +} + /* * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). @@ -3046,6 +3061,10 @@ static void task_numa_work(struct callback_head *work) vma->numab_state->next_scan)) continue; + /* Do not scan the VMA if task has not accessed */ + if (!vma_is_accessed(vma)) + continue; + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); diff --git a/mm/memory.c b/mm/memory.c index 9999574a9636..f77fccb5310c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4661,6 +4661,9 @@ int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, { get_page(page); + /* Record the current PID acceesing VMA */ + vma_set_access_pid_bit(vma); + count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); -- GitLab From 20f586486b87dcfe10b8c79398e24e720885588a Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:02 +0530 Subject: [PATCH 2292/5631] sched/numa: implement access PID reset logic This helps to ensure that only recently accessed PIDs scan the VMAs. Current implementation: (idea supported by PeterZ) 1. Accessing PID information is maintained in two windows. access_pids[1] being newest. 2. Reset old access PID info i.e. access_pid[0] every (4 * sysctl_numa_balancing_scan_delay) interval after initial scan delay period expires. The above interval seemed to be experimentally optimum since it avoids frequent reset of access info as well as helps clearing the old access info regularly. The reset logic is implemented in scan path. Link: https://lkml.kernel.org/r/f7a675f66d1442d048b4216b2baf94515012c405.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Mel Gorman Cc: Bharata B Rao Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mike Rapoport Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++-- include/linux/mm_types.h | 3 ++- kernel/sched/fair.c | 23 +++++++++++++++++++++-- 3 files changed, 25 insertions(+), 5 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 215327daffae..e05a878e186e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1692,8 +1692,8 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) unsigned int pid_bit; pid_bit = current->pid % BITS_PER_LONG; - if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids)) { - __set_bit(pid_bit, &vma->numab_state->access_pids); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { + __set_bit(pid_bit, &vma->numab_state->access_pids[1]); } } #else /* !CONFIG_NUMA_BALANCING */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f8cbd8efc7cb..092f842a854f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -477,7 +477,8 @@ struct vma_lock { struct vma_numab_state { unsigned long next_scan; - unsigned long access_pids; + unsigned long next_pid_reset; + unsigned long access_pids[2]; }; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ef27b5931480..a962d4b60cd7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2930,6 +2930,7 @@ static void reset_ptenuma_scan(struct task_struct *p) static bool vma_is_accessed(struct vm_area_struct *vma) { + unsigned long pids; /* * Allow unconditional access first two times, so that all the (pages) * of VMAs get prot_none fault introduced irrespective of accesses. @@ -2939,10 +2940,12 @@ static bool vma_is_accessed(struct vm_area_struct *vma) if (READ_ONCE(current->mm->numa_scan_seq) < 2) return true; - return test_bit(current->pid % BITS_PER_LONG, - &vma->numab_state->access_pids); + pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1]; + return test_bit(current->pid % BITS_PER_LONG, &pids); } +#define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay) + /* * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). @@ -3051,6 +3054,10 @@ static void task_numa_work(struct callback_head *work) vma->numab_state->next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + + /* Reset happens after 4 times scan delay of scan start */ + vma->numab_state->next_pid_reset = vma->numab_state->next_scan + + msecs_to_jiffies(VMA_PID_RESET_PERIOD); } /* @@ -3065,6 +3072,18 @@ static void task_numa_work(struct callback_head *work) if (!vma_is_accessed(vma)) continue; + /* + * RESET access PIDs regularly for old VMAs. Resetting after checking + * vma for recent access to avoid clearing PID info before access.. + */ + if (mm->numa_scan_seq && + time_after(jiffies, vma->numab_state->next_pid_reset)) { + vma->numab_state->next_pid_reset = vma->numab_state->next_pid_reset + + msecs_to_jiffies(VMA_PID_RESET_PERIOD); + vma->numab_state->access_pids[0] = READ_ONCE(vma->numab_state->access_pids[1]); + vma->numab_state->access_pids[1] = 0; + } + do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); -- GitLab From d46031f40e0f7f7bf63914bb3f2e404ad3886ecd Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Wed, 1 Mar 2023 17:49:03 +0530 Subject: [PATCH 2293/5631] sched/numa: use hash_32 to mix up PIDs accessing VMA before: last 6 bits of PID is used as index to store information about tasks accessing VMA's. after: hash_32 is used to take of cases where tasks are created over a period of time, and thus improve collision probability. Result: The patch series overall improves autonuma cost. Kernbench around more than 5% improvement and system time in mmtest autonuma showed more than 80% improvement Link: https://lkml.kernel.org/r/d5a9f75513300caed74e5c8570bba9317b963c2b.1677672277.git.raghavendra.kt@amd.com Signed-off-by: Raghavendra K T Suggested-by: Peter Zijlstra Cc: Bharata B Rao Cc: David Hildenbrand Cc: Disha Talreja Cc: Ingo Molnar Cc: Mel Gorman Cc: Mike Rapoport Signed-off-by: Andrew Morton --- include/linux/mm.h | 2 +- kernel/sched/fair.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index e05a878e186e..e249208f8fbe 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1691,7 +1691,7 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) { unsigned int pid_bit; - pid_bit = current->pid % BITS_PER_LONG; + pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { __set_bit(pid_bit, &vma->numab_state->access_pids[1]); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a962d4b60cd7..db6fc9d978ae 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2941,7 +2941,7 @@ static bool vma_is_accessed(struct vm_area_struct *vma) return true; pids = vma->numab_state->access_pids[0] | vma->numab_state->access_pids[1]; - return test_bit(current->pid % BITS_PER_LONG, &pids); + return test_bit(hash_32(current->pid, ilog2(BITS_PER_LONG)), &pids); } #define VMA_PID_RESET_PERIOD (4 * sysctl_numa_balancing_scan_delay) -- GitLab From 74c53b5717ba762d8648ee9e3d961093df2d7300 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 30 Mar 2023 13:07:10 +0200 Subject: [PATCH 2294/5631] csky: remove obsolete config CPU_TLB_SIZE Commit 9d35dc3006a9 ("csky: Revert mmu ASID mechanism") removes the only use of CONFIG_CPU_TLB_SIZE. Since then, this config has no effect and can be deleted. Remove the obsolete config CPU_TLB_SIZE. Signed-off-by: Lukas Bulwahn Signed-off-by: Guo Ren --- arch/csky/Kconfig | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index dba02da6fa34..1fb5f066a885 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -166,11 +166,6 @@ config STACKTRACE_SUPPORT config TIME_LOW_RES def_bool y -config CPU_TLB_SIZE - int - default "128" if (CPU_CK610 || CPU_CK807 || CPU_CK810) - default "1024" if (CPU_CK860) - config CPU_ASID_BITS int default "8" if (CPU_CK610 || CPU_CK807 || CPU_CK810) -- GitLab From 430cac487400494c19a8b85299e979bb07b4671f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 4 Apr 2023 15:12:16 +0200 Subject: [PATCH 2295/5631] xfrm: don't check the default policy if the policy allows the packet The current code doesn't let a simple "allow" policy counteract a default policy blocking all incoming packets: ip x p setdefault in block ip x p a src 192.168.2.1/32 dst 192.168.2.2/32 dir in action allow At this stage, we have an allow policy (with or without transforms) for this packet. It doesn't matter what the default policy says, since the policy we looked up lets the packet through. The case of a blocking policy is already handled separately, so we can remove this check. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5c61ec04b839..62be042f2ebc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3712,12 +3712,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; - if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK && - !xfrm_nr) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); - goto reject; - } - if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; -- GitLab From b3ad52353f9ffd652c9ffff376697e3a07cbd309 Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Wed, 15 Feb 2023 13:34:39 +0000 Subject: [PATCH 2296/5631] dt-bindings: pwm: mediatek: Add mediatek,mt7986 compatible MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 241eab76657f ("pwm: mediatek: Add support for MT7986") support for the 2 PWM channels implemented in MediaTek MT7986 SoCs has been added. Also add the compatible string to dt-bindings now that they have been converted to YAML. Acked-by: Krzysztof Kozlowski Acked-by: Uwe Kleine-König Reviewed-by: Matthias Brugger Signed-off-by: Daniel Golle Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Thierry Reding --- Documentation/devicetree/bindings/pwm/mediatek,mt2712-pwm.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/pwm/mediatek,mt2712-pwm.yaml b/Documentation/devicetree/bindings/pwm/mediatek,mt2712-pwm.yaml index dbc974bff9e9..8e176ba7a525 100644 --- a/Documentation/devicetree/bindings/pwm/mediatek,mt2712-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/mediatek,mt2712-pwm.yaml @@ -22,6 +22,7 @@ properties: - mediatek,mt7623-pwm - mediatek,mt7628-pwm - mediatek,mt7629-pwm + - mediatek,mt7986-pwm - mediatek,mt8183-pwm - mediatek,mt8365-pwm - mediatek,mt8516-pwm -- GitLab From 43a1c4ff3977f0ccd1d99e36d74e525aced5bb3a Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 20 Feb 2023 22:19:30 +0100 Subject: [PATCH 2297/5631] dt-bindings: pwm: Convert Amlogic Meson PWM binding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert Amlogic Meson PWM binding to yaml. Reviewed-by: Rob Herring Signed-off-by: Heiner Kallweit Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- .../devicetree/bindings/pwm/pwm-amlogic.yaml | 70 +++++++++++++++++++ .../devicetree/bindings/pwm/pwm-meson.txt | 29 -------- 2 files changed, 70 insertions(+), 29 deletions(-) create mode 100644 Documentation/devicetree/bindings/pwm/pwm-amlogic.yaml delete mode 100644 Documentation/devicetree/bindings/pwm/pwm-meson.txt diff --git a/Documentation/devicetree/bindings/pwm/pwm-amlogic.yaml b/Documentation/devicetree/bindings/pwm/pwm-amlogic.yaml new file mode 100644 index 000000000000..527864a4d855 --- /dev/null +++ b/Documentation/devicetree/bindings/pwm/pwm-amlogic.yaml @@ -0,0 +1,70 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pwm/pwm-amlogic.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Amlogic PWM + +maintainers: + - Heiner Kallweit + +allOf: + - $ref: pwm.yaml# + +properties: + compatible: + oneOf: + - enum: + - amlogic,meson8b-pwm + - amlogic,meson-gxbb-pwm + - amlogic,meson-gxbb-ao-pwm + - amlogic,meson-axg-ee-pwm + - amlogic,meson-axg-ao-pwm + - amlogic,meson-g12a-ee-pwm + - amlogic,meson-g12a-ao-pwm-ab + - amlogic,meson-g12a-ao-pwm-cd + - amlogic,meson-s4-pwm + - items: + - const: amlogic,meson-gx-pwm + - const: amlogic,meson-gxbb-pwm + - items: + - const: amlogic,meson-gx-ao-pwm + - const: amlogic,meson-gxbb-ao-pwm + - items: + - const: amlogic,meson8-pwm + - const: amlogic,meson8b-pwm + + reg: + maxItems: 1 + + clocks: + minItems: 1 + maxItems: 2 + + clock-names: + oneOf: + - items: + - enum: [clkin0, clkin1] + - items: + - const: clkin0 + - const: clkin1 + + "#pwm-cells": + const: 3 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + pwm@8550 { + compatible = "amlogic,meson-gxbb-pwm"; + reg = <0x08550 0x10>; + clocks = <&xtal>, <&xtal>; + clock-names = "clkin0", "clkin1"; + #pwm-cells = <3>; + }; diff --git a/Documentation/devicetree/bindings/pwm/pwm-meson.txt b/Documentation/devicetree/bindings/pwm/pwm-meson.txt deleted file mode 100644 index bd02b0a1496f..000000000000 --- a/Documentation/devicetree/bindings/pwm/pwm-meson.txt +++ /dev/null @@ -1,29 +0,0 @@ -Amlogic Meson PWM Controller -============================ - -Required properties: -- compatible: Shall contain "amlogic,meson8b-pwm" - or "amlogic,meson-gxbb-pwm" - or "amlogic,meson-gxbb-ao-pwm" - or "amlogic,meson-axg-ee-pwm" - or "amlogic,meson-axg-ao-pwm" - or "amlogic,meson-g12a-ee-pwm" - or "amlogic,meson-g12a-ao-pwm-ab" - or "amlogic,meson-g12a-ao-pwm-cd" -- #pwm-cells: Should be 3. See pwm.yaml in this directory for a description of - the cells format. - -Optional properties: -- clocks: Could contain one or two parents clocks phandle for each of the two - PWM channels. -- clock-names: Could contain at least the "clkin0" and/or "clkin1" names. - -Example: - - pwm_ab: pwm@8550 { - compatible = "amlogic,meson-gxbb-pwm"; - reg = <0x0 0x08550 0x0 0x10>; - #pwm-cells = <3>; - clocks = <&xtal>, <&xtal>; - clock-names = "clkin0", "clkin1"; - } -- GitLab From d6a436c76dd5789a22b091c0a32dee72684f17ce Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:51:19 +0100 Subject: [PATCH 2298/5631] pwm: rcar: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes the following compiler warning: drivers/pwm/pwm-rcar.c:252:34: error: ‘rcar_pwm_of_table’ defined but not used [-Werror=unused-const-variable=] for builds with CONFIG_OF=n, CONFIG_PWM_RCAR=y and W=1. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Thierry Reding --- drivers/pwm/pwm-rcar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c index e9d8646dc331..5b5f357c44de 100644 --- a/drivers/pwm/pwm-rcar.c +++ b/drivers/pwm/pwm-rcar.c @@ -258,7 +258,7 @@ static struct platform_driver rcar_pwm_driver = { .remove_new = rcar_pwm_remove, .driver = { .name = "pwm-rcar", - .of_match_table = of_match_ptr(rcar_pwm_of_table), + .of_match_table = rcar_pwm_of_table, } }; module_platform_driver(rcar_pwm_driver); -- GitLab From fa359c1938adbd04cf7e68786ea58366dddc3ad7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 14:51:20 +0100 Subject: [PATCH 2299/5631] pwm: stm32-lp: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes the following compile error: drivers/pwm/pwm-stm32-lp.c:245:34: error: ‘stm32_pwm_lp_of_match’ defined but not used [-Werror=unused-const-variable=] for builds with CONFIG_OF=n, CONFIG_PWM_STM32_LP=y and W=1. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Thierry Reding --- drivers/pwm/pwm-stm32-lp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c index f315fa106be8..bb3a045a7334 100644 --- a/drivers/pwm/pwm-stm32-lp.c +++ b/drivers/pwm/pwm-stm32-lp.c @@ -252,7 +252,7 @@ static struct platform_driver stm32_pwm_lp_driver = { .probe = stm32_pwm_lp_probe, .driver = { .name = "stm32-pwm-lp", - .of_match_table = of_match_ptr(stm32_pwm_lp_of_match), + .of_match_table = stm32_pwm_lp_of_match, .pm = &stm32_pwm_lp_pm_ops, }, }; -- GitLab From 36dd7f530ae7d9ce9e853ffb8aa337de65c6600b Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 3 Apr 2023 15:30:53 +0200 Subject: [PATCH 2300/5631] pwm: mtk-disp: Disable shadow registers before setting backlight values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If shadow registers usage is not desired, disable that before performing any write to CON0/1 registers in the .apply() callback, otherwise we may lose clkdiv or period/width updates. Fixes: cd4b45ac449a ("pwm: Add MediaTek MT2701 display PWM driver support") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Nícolas F. R. A. Prado Tested-by: Nícolas F. R. A. Prado Reviewed-by: Alexandre Mergnat Tested-by: Alexandre Mergnat Signed-off-by: Thierry Reding --- drivers/pwm/pwm-mtk-disp.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index 4cfe88d54652..ea361976eb34 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -138,6 +138,19 @@ static int mtk_disp_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, high_width = mul_u64_u64_div_u64(state->duty_cycle, rate, div); value = period | (high_width << PWM_HIGH_WIDTH_SHIFT); + if (mdp->data->bls_debug && !mdp->data->has_commit) { + /* + * For MT2701, disable double buffer before writing register + * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. + */ + mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, + mdp->data->bls_debug_mask, + mdp->data->bls_debug_mask); + mtk_disp_pwm_update_bits(mdp, mdp->data->con0, + mdp->data->con0_sel, + mdp->data->con0_sel); + } + mtk_disp_pwm_update_bits(mdp, mdp->data->con0, PWM_CLKDIV_MASK, clk_div << PWM_CLKDIV_SHIFT); @@ -152,17 +165,6 @@ static int mtk_disp_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, mtk_disp_pwm_update_bits(mdp, mdp->data->commit, mdp->data->commit_mask, 0x0); - } else { - /* - * For MT2701, disable double buffer before writing register - * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH. - */ - mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, - mdp->data->bls_debug_mask, - mdp->data->bls_debug_mask); - mtk_disp_pwm_update_bits(mdp, mdp->data->con0, - mdp->data->con0_sel, - mdp->data->con0_sel); } mtk_disp_pwm_update_bits(mdp, DISP_PWM_EN, mdp->data->enable_mask, -- GitLab From b16c310115f2084b8826a35b77ef42bab6786d9f Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 3 Apr 2023 15:30:54 +0200 Subject: [PATCH 2301/5631] pwm: mtk-disp: Configure double buffering before reading in .get_state() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The DISP_PWM controller's default behavior is to always use register double buffering: all reads/writes are then performed on shadow registers instead of working registers and this becomes an issue in case our chosen configuration in Linux is different from the default (or from the one that was pre-applied by the bootloader). An example of broken behavior is when the controller is configured to use shadow registers, but this driver wants to configure it otherwise: what happens is that the .get_state() callback is called right after registering the pwmchip and checks whether the PWM is enabled by reading the DISP_PWM_EN register; At this point, if shadow registers are enabled but their content was not committed before booting Linux, we are *not* reading the current PWM enablement status, leading to the kernel knowing that the hardware is actually enabled when, in reality, it's not. The aforementioned issue emerged since this driver was fixed with commit 0b5ef3429d8f ("pwm: mtk-disp: Fix the parameters calculated by the enabled flag of disp_pwm") making it to read the enablement status from the right register. Configure the controller in the .get_state() callback to avoid this desync issue and get the backlight properly working again. Fixes: 3f2b16734914 ("pwm: mtk-disp: Implement atomic API .get_state()") Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Nícolas F. R. A. Prado Tested-by: Nícolas F. R. A. Prado Reviewed-by: Alexandre Mergnat Tested-by: Alexandre Mergnat Signed-off-by: Thierry Reding --- drivers/pwm/pwm-mtk-disp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c index ea361976eb34..79e321e96f56 100644 --- a/drivers/pwm/pwm-mtk-disp.c +++ b/drivers/pwm/pwm-mtk-disp.c @@ -196,6 +196,16 @@ static int mtk_disp_pwm_get_state(struct pwm_chip *chip, return err; } + /* + * Apply DISP_PWM_DEBUG settings to choose whether to enable or disable + * registers double buffer and manual commit to working register before + * performing any read/write operation + */ + if (mdp->data->bls_debug) + mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug, + mdp->data->bls_debug_mask, + mdp->data->bls_debug_mask); + rate = clk_get_rate(mdp->clk_main); con0 = readl(mdp->base + mdp->data->con0); con1 = readl(mdp->base + mdp->data->con1); -- GitLab From 87a3a3929c710b863c3a288f6b094edc97662858 Mon Sep 17 00:00:00 2001 From: Sasha Finkelstein Date: Mon, 3 Apr 2023 16:19:19 +0200 Subject: [PATCH 2302/5631] dt-bindings: pwm: Add Apple PWM controller Apple SoCs such as the M1 contain a PWM controller used among other things to control the keyboard backlight. Signed-off-by: Sasha Finkelstein Reviewed-by: Krzysztof Kozlowski Acked-by: Sven Peter Signed-off-by: Thierry Reding --- .../bindings/pwm/apple,s5l-fpwm.yaml | 51 +++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml diff --git a/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml b/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml new file mode 100644 index 000000000000..142157bff0cd --- /dev/null +++ b/Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/pwm/apple,s5l-fpwm.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Apple FPWM controller + +maintainers: + - asahi@lists.linux.dev + - Sasha Finkelstein + +description: PWM controller used for keyboard backlight on ARM Macs + +properties: + compatible: + items: + - enum: + - apple,t8103-fpwm + - apple,t6000-fpwm + - apple,t8112-fpwm + - const: apple,s5l-fpwm + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + power-domains: + maxItems: 1 + + "#pwm-cells": + const: 2 + +required: + - compatible + - reg + - clocks + +additionalProperties: false + +examples: + - | + pwm@235044000 { + compatible = "apple,t8103-fpwm", "apple,s5l-fpwm"; + reg = <0x35044000 0x4000>; + power-domains = <&ps_fpwm1>; + clocks = <&clkref>; + #pwm-cells = <2>; + }; -- GitLab From bafbbef85fd788074c27892c2391faf249eb7b29 Mon Sep 17 00:00:00 2001 From: Sasha Finkelstein Date: Mon, 3 Apr 2023 16:19:20 +0200 Subject: [PATCH 2303/5631] pwm: Add Apple PWM controller MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds the Apple PWM controller driver. Signed-off-by: Sasha Finkelstein Acked-by: Sven Peter Reviewed-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/Kconfig | 12 +++ drivers/pwm/Makefile | 1 + drivers/pwm/pwm-apple.c | 159 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 172 insertions(+) create mode 100644 drivers/pwm/pwm-apple.c diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig index dae023d783a2..8df861b1f4a3 100644 --- a/drivers/pwm/Kconfig +++ b/drivers/pwm/Kconfig @@ -51,6 +51,18 @@ config PWM_AB8500 To compile this driver as a module, choose M here: the module will be called pwm-ab8500. +config PWM_APPLE + tristate "Apple SoC PWM support" + depends on ARCH_APPLE || COMPILE_TEST + help + Generic PWM framework driver for PWM controller present on + Apple SoCs + + Say Y here if you have an ARM Apple laptop, otherwise say N + + To compile this driver as a module, choose M here: the module + will be called pwm-apple. + config PWM_ATMEL tristate "Atmel PWM support" depends on ARCH_AT91 || COMPILE_TEST diff --git a/drivers/pwm/Makefile b/drivers/pwm/Makefile index 7bf1a29f02b8..19899b912e00 100644 --- a/drivers/pwm/Makefile +++ b/drivers/pwm/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_PWM) += core.o obj-$(CONFIG_PWM_SYSFS) += sysfs.o obj-$(CONFIG_PWM_AB8500) += pwm-ab8500.o +obj-$(CONFIG_PWM_APPLE) += pwm-apple.o obj-$(CONFIG_PWM_ATMEL) += pwm-atmel.o obj-$(CONFIG_PWM_ATMEL_HLCDC_PWM) += pwm-atmel-hlcdc.o obj-$(CONFIG_PWM_ATMEL_TCB) += pwm-atmel-tcb.o diff --git a/drivers/pwm/pwm-apple.c b/drivers/pwm/pwm-apple.c new file mode 100644 index 000000000000..a38a62edd713 --- /dev/null +++ b/drivers/pwm/pwm-apple.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Driver for the Apple SoC PWM controller + * + * Copyright The Asahi Linux Contributors + * + * Limitations: + * - The writes to cycle registers are shadowed until a write to + * the control register. + * - If both OFF_CYCLES and ON_CYCLES are set to 0, the output + * is a constant off signal. + * - When APPLE_PWM_CTRL is set to 0, the output is constant low + */ + +#include +#include +#include +#include +#include +#include + +#define APPLE_PWM_CTRL 0x00 +#define APPLE_PWM_ON_CYCLES 0x1c +#define APPLE_PWM_OFF_CYCLES 0x18 + +#define APPLE_PWM_CTRL_ENABLE BIT(0) +#define APPLE_PWM_CTRL_MODE BIT(2) +#define APPLE_PWM_CTRL_UPDATE BIT(5) +#define APPLE_PWM_CTRL_TRIGGER BIT(9) +#define APPLE_PWM_CTRL_INVERT BIT(10) +#define APPLE_PWM_CTRL_OUTPUT_ENABLE BIT(14) + +struct apple_pwm { + struct pwm_chip chip; + void __iomem *base; + u64 clkrate; +}; + +static inline struct apple_pwm *to_apple_pwm(struct pwm_chip *chip) +{ + return container_of(chip, struct apple_pwm, chip); +} + +static int apple_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm, + const struct pwm_state *state) +{ + struct apple_pwm *fpwm; + + if (state->polarity == PWM_POLARITY_INVERSED) + return -EINVAL; + + fpwm = to_apple_pwm(chip); + if (state->enabled) { + u64 on_cycles, off_cycles; + + on_cycles = mul_u64_u64_div_u64(fpwm->clkrate, + state->duty_cycle, NSEC_PER_SEC); + if (on_cycles > 0xFFFFFFFF) + on_cycles = 0xFFFFFFFF; + + off_cycles = mul_u64_u64_div_u64(fpwm->clkrate, + state->period, NSEC_PER_SEC) - on_cycles; + if (off_cycles > 0xFFFFFFFF) + off_cycles = 0xFFFFFFFF; + + writel(on_cycles, fpwm->base + APPLE_PWM_ON_CYCLES); + writel(off_cycles, fpwm->base + APPLE_PWM_OFF_CYCLES); + writel(APPLE_PWM_CTRL_ENABLE | APPLE_PWM_CTRL_OUTPUT_ENABLE | APPLE_PWM_CTRL_UPDATE, + fpwm->base + APPLE_PWM_CTRL); + } else { + writel(0, fpwm->base + APPLE_PWM_CTRL); + } + return 0; +} + +static int apple_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_state *state) +{ + struct apple_pwm *fpwm; + u32 on_cycles, off_cycles, ctrl; + + fpwm = to_apple_pwm(chip); + + ctrl = readl(fpwm->base + APPLE_PWM_CTRL); + on_cycles = readl(fpwm->base + APPLE_PWM_ON_CYCLES); + off_cycles = readl(fpwm->base + APPLE_PWM_OFF_CYCLES); + + state->enabled = (ctrl & APPLE_PWM_CTRL_ENABLE) && (ctrl & APPLE_PWM_CTRL_OUTPUT_ENABLE); + state->polarity = PWM_POLARITY_NORMAL; + // on_cycles + off_cycles is 33 bits, NSEC_PER_SEC is 30, there is no overflow + state->duty_cycle = DIV64_U64_ROUND_UP((u64)on_cycles * NSEC_PER_SEC, fpwm->clkrate); + state->period = DIV64_U64_ROUND_UP(((u64)off_cycles + (u64)on_cycles) * + NSEC_PER_SEC, fpwm->clkrate); + + return 0; +} + +static const struct pwm_ops apple_pwm_ops = { + .apply = apple_pwm_apply, + .get_state = apple_pwm_get_state, + .owner = THIS_MODULE, +}; + +static int apple_pwm_probe(struct platform_device *pdev) +{ + struct apple_pwm *fpwm; + struct clk *clk; + int ret; + + fpwm = devm_kzalloc(&pdev->dev, sizeof(*fpwm), GFP_KERNEL); + if (!fpwm) + return -ENOMEM; + + fpwm->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(fpwm->base)) + return PTR_ERR(fpwm->base); + + clk = devm_clk_get_enabled(&pdev->dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(clk), "unable to get the clock"); + + /* + * Uses the 24MHz system clock on all existing devices, can only + * happen if the device tree is broken + * + * This check is done to prevent an overflow in .apply + */ + fpwm->clkrate = clk_get_rate(clk); + if (fpwm->clkrate > NSEC_PER_SEC) + return dev_err_probe(&pdev->dev, -EINVAL, "pwm clock out of range"); + + fpwm->chip.dev = &pdev->dev; + fpwm->chip.npwm = 1; + fpwm->chip.ops = &apple_pwm_ops; + + ret = devm_pwmchip_add(&pdev->dev, &fpwm->chip); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "unable to add pwm chip"); + + return 0; +} + +static const struct of_device_id apple_pwm_of_match[] = { + { .compatible = "apple,s5l-fpwm" }, + {} +}; +MODULE_DEVICE_TABLE(of, apple_pwm_of_match); + +static struct platform_driver apple_pwm_driver = { + .probe = apple_pwm_probe, + .driver = { + .name = "apple-pwm", + .of_match_table = apple_pwm_of_match, + }, +}; +module_platform_driver(apple_pwm_driver); + +MODULE_DESCRIPTION("Apple SoC PWM driver"); +MODULE_LICENSE("Dual MIT/GPL"); -- GitLab From de614ac31955fe20f71021fd5f4a9a811e90028f Mon Sep 17 00:00:00 2001 From: Sasha Finkelstein Date: Mon, 3 Apr 2023 16:19:23 +0200 Subject: [PATCH 2304/5631] MAINTAINERS: Add entries for Apple PWM driver Add the MAINTAINERS entries for the driver Signed-off-by: Sasha Finkelstein Acked-by: Sven Peter Signed-off-by: Thierry Reding --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..7c0b7c2bb55f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1955,6 +1955,7 @@ F: Documentation/devicetree/bindings/nvmem/apple,efuses.yaml F: Documentation/devicetree/bindings/pci/apple,pcie.yaml F: Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml F: Documentation/devicetree/bindings/power/apple* +F: Documentation/devicetree/bindings/pwm/pwm-apple.yaml F: Documentation/devicetree/bindings/watchdog/apple,wdt.yaml F: arch/arm64/boot/dts/apple/ F: drivers/bluetooth/hci_bcm4377.c @@ -1970,6 +1971,7 @@ F: drivers/mailbox/apple-mailbox.c F: drivers/nvme/host/apple.c F: drivers/nvmem/apple-efuses.c F: drivers/pinctrl/pinctrl-apple-gpio.c +F: drivers/pwm/pwm-apple.c F: drivers/soc/apple/* F: drivers/watchdog/apple_wdt.c F: include/dt-bindings/interrupt-controller/apple-aic.h -- GitLab From d0a4564bd024eaa81cab8c7255e7c44230bdd8a2 Mon Sep 17 00:00:00 2001 From: Olivier Moysan Date: Tue, 13 Dec 2022 11:27:07 +0100 Subject: [PATCH 2305/5631] pwm: stm32: Enforce settings for PWM capture MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The PWM capture assumes that the input selector is set to default input and that the slave mode is disabled. Force reset state for TISEL and SMCR registers to match this requirement. Note that slave mode disabling is not a pre-requisite by itself for capture mode, as hardware supports it for PWM capture. However, the current implementation of the driver does not allow slave mode for PWM capture. Setting slave mode for PWM capture results in wrong capture values. Signed-off-by: Olivier Moysan Acked-by: Lee Jones Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/pwm-stm32.c | 4 ++++ include/linux/mfd/stm32-timers.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c index a482f7e0e4ab..62e397aeb9aa 100644 --- a/drivers/pwm/pwm-stm32.c +++ b/drivers/pwm/pwm-stm32.c @@ -207,6 +207,10 @@ static int stm32_pwm_capture(struct pwm_chip *chip, struct pwm_device *pwm, regmap_write(priv->regmap, TIM_ARR, priv->max_arr); regmap_write(priv->regmap, TIM_PSC, psc); + /* Reset input selector to its default input and disable slave mode */ + regmap_write(priv->regmap, TIM_TISEL, 0x0); + regmap_write(priv->regmap, TIM_SMCR, 0x0); + /* Map TI1 or TI2 PWM input to IC1 & IC2 (or TI3/4 to IC3 & IC4) */ regmap_update_bits(priv->regmap, pwm->hwpwm < 2 ? TIM_CCMR1 : TIM_CCMR2, diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index 5f5c43fd69dd..1b94325febb3 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -31,6 +31,7 @@ #define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ #define TIM_DCR 0x48 /* DMA control register */ #define TIM_DMAR 0x4C /* DMA register for transfer */ +#define TIM_TISEL 0x68 /* Input Selection */ #define TIM_CR1_CEN BIT(0) /* Counter Enable */ #define TIM_CR1_DIR BIT(4) /* Counter Direction */ -- GitLab From 52887af5650e35ea78b37602722313ff7b3c0c30 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:35 -0700 Subject: [PATCH 2306/5631] KVM: x86: Revert MSR_IA32_FLUSH_CMD.FLUSH_L1D enabling Revert the recently added virtualizing of MSR_IA32_FLUSH_CMD, as both the VMX and SVM are fatally buggy to guests that use MSR_IA32_FLUSH_CMD or MSR_IA32_PRED_CMD, and because the entire foundation of the logic is flawed. The most immediate problem is an inverted check on @cmd that results in rejecting legal values. SVM doubles down on bugs and drops the error, i.e. silently breaks all guest mitigations based on the command MSRs. The next issue is that neither VMX nor SVM was updated to mark MSR_IA32_FLUSH_CMD as being a possible passthrough MSR, which isn't hugely problematic, but does break MSR filtering and triggers a WARN on VMX designed to catch this exact bug. The foundational issues stem from the MSR_IA32_FLUSH_CMD code reusing logic from MSR_IA32_PRED_CMD, which in turn was likely copied from KVM's support for MSR_IA32_SPEC_CTRL. The copy+paste from MSR_IA32_SPEC_CTRL was misguided as MSR_IA32_PRED_CMD (and MSR_IA32_FLUSH_CMD) is a write-only MSR, i.e. doesn't need the same "deferred passthrough" shenanigans as MSR_IA32_SPEC_CTRL. Revert all MSR_IA32_FLUSH_CMD enabling in one fell swoop so that there is no point where KVM advertises, but does not support, L1D_FLUSH. This reverts commits 45cf86f26148e549c5ba4a8ab32a390e4bde216e, 723d5fb0ffe4c02bd4edf47ea02c02e454719f28, and a807b78ad04b2eaa348f52f5cc7702385b6de1ee. Reported-by: Nathan Chancellor Link: https://lkml.kernel.org/r/20230317190432.GA863767%40dev-arch.thelio-3990X Cc: Emanuele Giuseppe Esposito Cc: Pawan Gupta Cc: Jim Mattson Signed-off-by: Sean Christopherson Tested-by: Mathias Krause Message-Id: <20230322011440.2195485-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/svm/svm.c | 43 ++++++++----------------- arch/x86/kvm/vmx/nested.c | 3 -- arch/x86/kvm/vmx/vmx.c | 68 ++++++++++++++------------------------- 4 files changed, 39 insertions(+), 77 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9583a110cf5f..599aebec2d52 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -653,7 +653,7 @@ void kvm_set_cpu_caps(void) F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | - F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) + F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 70183d2271b5..252e7f37e4e2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2869,28 +2869,6 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) return 0; } -static int svm_set_msr_ia32_cmd(struct kvm_vcpu *vcpu, struct msr_data *msr, - bool guest_has_feat, u64 cmd, - int x86_feature_bit) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (!msr->host_initiated && !guest_has_feat) - return 1; - - if (!(msr->data & ~cmd)) - return 1; - if (!boot_cpu_has(x86_feature_bit)) - return 1; - if (!msr->data) - return 0; - - wrmsrl(msr->index, cmd); - set_msr_interception(vcpu, svm->msrpm, msr->index, 0, 1); - - return 0; -} - static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2965,14 +2943,19 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); break; case MSR_IA32_PRED_CMD: - r = svm_set_msr_ia32_cmd(vcpu, msr, - guest_has_pred_cmd_msr(vcpu), - PRED_CMD_IBPB, X86_FEATURE_IBPB); - break; - case MSR_IA32_FLUSH_CMD: - r = svm_set_msr_ia32_cmd(vcpu, msr, - guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D), - L1D_FLUSH, X86_FEATURE_FLUSH_L1D); + if (!msr->host_initiated && + !guest_has_pred_cmd_msr(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + if (!boot_cpu_has(X86_FEATURE_IBPB)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f63b28f46a71..1bc2b80273c9 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -654,9 +654,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PRED_CMD, MSR_TYPE_W); - nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_FLUSH_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); vmx->nested.force_msr_bitmap_recalc = false; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7bf14abdba1..f777509ecf17 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2133,39 +2133,6 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated return debugctl; } -static int vmx_set_msr_ia32_cmd(struct kvm_vcpu *vcpu, - struct msr_data *msr_info, - bool guest_has_feat, u64 cmd, - int x86_feature_bit) -{ - if (!msr_info->host_initiated && !guest_has_feat) - return 1; - - if (!(msr_info->data & ~cmd)) - return 1; - if (!boot_cpu_has(x86_feature_bit)) - return 1; - if (!msr_info->data) - return 0; - - wrmsrl(msr_info->index, cmd); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vcpu, msr_info->index, MSR_TYPE_W); - - return 0; -} - /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2319,16 +2286,31 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; goto find_uret_msr; case MSR_IA32_PRED_CMD: - ret = vmx_set_msr_ia32_cmd(vcpu, msr_info, - guest_has_pred_cmd_msr(vcpu), - PRED_CMD_IBPB, - X86_FEATURE_IBPB); - break; - case MSR_IA32_FLUSH_CMD: - ret = vmx_set_msr_ia32_cmd(vcpu, msr_info, - guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D), - L1D_FLUSH, - X86_FEATURE_FLUSH_L1D); + if (!msr_info->host_initiated && + !guest_has_pred_cmd_msr(vcpu)) + return 1; + + if (data & ~PRED_CMD_IBPB) + return 1; + if (!boot_cpu_has(X86_FEATURE_IBPB)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_vmx_prepare_msr_bitmap. We should not touch the + * vmcs02.msr_bitmap here since it gets completely overwritten + * in the merging. + */ + vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) -- GitLab From 9a4c4850137e929d49958fb62d4275bd2f5b8c7a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:36 -0700 Subject: [PATCH 2307/5631] KVM: VMX: Passthrough MSR_IA32_PRED_CMD based purely on host+guest CPUID Passthrough MSR_IA32_PRED_CMD based purely on whether or not the MSR is supported and enabled, i.e. don't wait until the first write. There's no benefit to deferred passthrough, and the extra logic only adds complexity. Signed-off-by: Sean Christopherson Reviewed-by: Xiaoyao Li Message-Id: <20230322011440.2195485-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/vmx.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f777509ecf17..5c01c76c0d45 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2298,19 +2298,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W); break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) @@ -7743,6 +7730,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + if (boot_cpu_has(X86_FEATURE_IBPB)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, + !guest_has_pred_cmd_msr(vcpu)); set_cr4_guest_host_mask(vmx); -- GitLab From bff903e8cd743cddb42ef1690edd33130f12c40a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:37 -0700 Subject: [PATCH 2308/5631] KVM: SVM: Passthrough MSR_IA32_PRED_CMD based purely on host+guest CPUID Passthrough MSR_IA32_PRED_CMD based purely on whether or not the MSR is supported and enabled, i.e. don't wait until the first write. There's no benefit to deferred passthrough, and the extra logic only adds complexity. Signed-off-by: Sean Christopherson Message-Id: <20230322011440.2195485-4-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 252e7f37e4e2..f757b436ffae 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2955,7 +2955,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && @@ -4151,6 +4150,10 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm_recalc_instruction_intercepts(vcpu, svm); + if (boot_cpu_has(X86_FEATURE_IBPB)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, + !!guest_has_pred_cmd_msr(vcpu)); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { best = kvm_find_cpuid_entry(vcpu, 0x8000001F); -- GitLab From 903358c7eddb9a8a83013f967909805e6af050d4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:38 -0700 Subject: [PATCH 2309/5631] KVM: x86: Move MSR_IA32_PRED_CMD WRMSR emulation to common code Dedup the handling of MSR_IA32_PRED_CMD across VMX and SVM by moving the logic to kvm_set_msr_common(). Now that the MSR interception toggling is handled as part of setting guest CPUID, the VMX and SVM paths are identical. Opportunistically massage the code to make it a wee bit denser. Signed-off-by: Sean Christopherson Reviewed-by: Xiaoyao Li Message-Id: <20230322011440.2195485-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 14 -------------- arch/x86/kvm/vmx/vmx.c | 14 -------------- arch/x86/kvm/x86.c | 11 +++++++++++ 3 files changed, 11 insertions(+), 28 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index f757b436ffae..85bb535fc321 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2942,20 +2942,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) */ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); break; - case MSR_IA32_PRED_CMD: - if (!msr->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5c01c76c0d45..29807be219b9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2285,20 +2285,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) return 1; goto find_uret_msr; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) return 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..c83ec88da043 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3617,6 +3617,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); return 0; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) + return 1; + + if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: -- GitLab From da3db168fb671f15e393b227f5c312c698ecb6ea Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:39 -0700 Subject: [PATCH 2310/5631] KVM: x86: Virtualize FLUSH_L1D and passthrough MSR_IA32_FLUSH_CMD Virtualize FLUSH_L1D so that the guest can use the performant L1D flush if one of the many mitigations might require a flush in the guest, e.g. Linux provides an option to flush the L1D when switching mms. Passthrough MSR_IA32_FLUSH_CMD for write when it's supported in hardware and exposed to the guest, i.e. always let the guest write it directly if FLUSH_L1D is fully supported. Forward writes to hardware in host context on the off chance that KVM ends up emulating a WRMSR, or in the really unlikely scenario where userspace wants to force a flush. Restrict these forwarded WRMSRs to the known command out of an abundance of caution. Passing through the MSR means the guest can throw any and all values at hardware, but doing so in host context is arguably a bit more dangerous. Link: https://lkml.kernel.org/r/CALMp9eTt3xzAEoQ038bJQ9LN0ZOXrSWsN7xnNUD%2B0SS%3DWwF7Pg%40mail.gmail.com Link: https://lore.kernel.org/all/20230201132905.549148-2-eesposit@redhat.com Signed-off-by: Sean Christopherson Message-Id: <20230322011440.2195485-6-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/svm/svm.c | 5 +++++ arch/x86/kvm/vmx/nested.c | 3 +++ arch/x86/kvm/vmx/vmx.c | 5 +++++ arch/x86/kvm/vmx/vmx.h | 2 +- arch/x86/kvm/x86.c | 12 ++++++++++++ 6 files changed, 27 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 599aebec2d52..9583a110cf5f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -653,7 +653,7 @@ void kvm_set_cpu_caps(void) F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | - F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) + F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 85bb535fc321..b32edaf5a74b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -95,6 +95,7 @@ static const struct svm_direct_access_msrs { #endif { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, + { .index = MSR_IA32_FLUSH_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -4140,6 +4141,10 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, !!guest_has_pred_cmd_msr(vcpu)); + if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, + !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { best = kvm_find_cpuid_entry(vcpu, 0x8000001F); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1bc2b80273c9..f63b28f46a71 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -654,6 +654,9 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PRED_CMD, MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_FLUSH_CMD, MSR_TYPE_W); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); vmx->nested.force_msr_bitmap_recalc = false; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 29807be219b9..56e0c7ae961d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -164,6 +164,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, MSR_IA32_PRED_CMD, + MSR_IA32_FLUSH_CMD, MSR_IA32_TSC, #ifdef CONFIG_X86_64 MSR_FS_BASE, @@ -7720,6 +7721,10 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, !guest_has_pred_cmd_msr(vcpu)); + if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, + !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 2acdc54bc34b..cb766f65a3eb 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -369,7 +369,7 @@ struct vcpu_vmx { struct lbr_desc lbr_desc; /* Save desired MSR intercept (read: pass-through) state */ -#define MAX_POSSIBLE_PASSTHROUGH_MSRS 15 +#define MAX_POSSIBLE_PASSTHROUGH_MSRS 16 struct { DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c83ec88da043..3c58dbae7b4c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3628,6 +3628,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); break; + case MSR_IA32_FLUSH_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) + return 1; + + if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: -- GitLab From 400d2132288edbd6d500f45eab5d85526ca94e46 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 21 Mar 2023 18:14:40 -0700 Subject: [PATCH 2311/5631] KVM: SVM: Return the local "r" variable from svm_set_msr() Rename "r" to "ret" and actually return it from svm_set_msr() to reduce the probability of repeating the mistake of commit 723d5fb0ffe4 ("kvm: svm: Add IA32_FLUSH_CMD guest support"), which set "r" thinking that it would be propagated to the caller. Alternatively, the declaration of "r" could be moved into the handling of MSR_TSC_AUX, but that risks variable shadowing in the future. A wrapper for kvm_set_user_return_msr() would allow eliding a local variable, but that feels like delaying the inevitable. No functional change intended. Signed-off-by: Sean Christopherson Message-Id: <20230322011440.2195485-7-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b32edaf5a74b..57f241c5a371 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2873,7 +2873,7 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); - int r; + int ret = 0; u32 ecx = msr->index; u64 data = msr->data; @@ -2995,10 +2995,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * guest via direct_access_msrs, and switch it via user return. */ preempt_disable(); - r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); + ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); preempt_enable(); - if (r) - return 1; + if (ret) + break; svm->tsc_aux = data; break; @@ -3056,7 +3056,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) default: return kvm_set_msr_common(vcpu, msr); } - return 0; + return ret; } static int msr_interception(struct kvm_vcpu *vcpu) -- GitLab From fca1fdd2b0a6fcd491ec520afac80bc72b4c811e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 3 Apr 2023 14:10:19 +0300 Subject: [PATCH 2312/5631] x86/mm/iommu/sva: Fix error code for LAM enabling failure due to SVA Normally, LAM and SVA are mutually exclusive. LAM enabling will fail if SVA is already in use. Correct error code for the failure. EINTR is nonsensical there. Fixes: 23e5d9ec2bab ("x86/mm/iommu/sva: Make LAM and SVA mutually exclusive") Reported-by: Dmitry Vyukov Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/all/CACT4Y+YfqSMsZArhh25TESmG-U4jO5Hjphz87wKSnTiaw2Wrfw@mail.gmail.com Link: https://lore.kernel.org/all/20230403111020.3136-2-kirill.shutemov%40linux.intel.com --- arch/x86/kernel/process_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b46924c9e46d..bc2ac5652f88 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -758,7 +758,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits) if (mm_valid_pasid(mm) && !test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags)) - return -EINTR; + return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; -- GitLab From 97740266de26e5dfe6e4fbecacb6995b66c2e378 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 3 Apr 2023 14:10:20 +0300 Subject: [PATCH 2313/5631] x86/mm/iommu/sva: Do not allow to set FORCE_TAGGED_SVA bit from outside arch_prctl(ARCH_FORCE_TAGGED_SVA) overrides the default and allows LAM and SVA to co-exist in the process. It is expected by called by the process when it knows what it is doing. arch_prctl() operates on the current process, but the same code is reachable from ptrace where it can be called on arbitrary task. Make it strict and only allow to set MM_CONTEXT_FORCE_TAGGED_SVA for the current process. Fixes: 23e5d9ec2bab ("x86/mm/iommu/sva: Make LAM and SVA mutually exclusive") Suggested-by: Dmitry Vyukov Signed-off-by: Kirill A. Shutemov Signed-off-by: Dave Hansen Reviewed-by: Dmitry Vyukov Link: https://lore.kernel.org/all/20230403111020.3136-3-kirill.shutemov%40linux.intel.com --- arch/x86/kernel/process_64.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index bc2ac5652f88..223b223f713f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -883,6 +883,8 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) case ARCH_ENABLE_TAGGED_ADDR: return prctl_enable_tagged_addr(task->mm, arg2); case ARCH_FORCE_TAGGED_SVA: + if (current != task) + return -EINVAL; set_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &task->mm->context.flags); return 0; case ARCH_GET_MAX_TAG_BITS: -- GitLab From b1932c5c19ddcbe9140b0583a0931b620c21ca02 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:45:58 -0800 Subject: [PATCH 2314/5631] KVM: x86: Rename kvm_init_msr_list() to clarify it inits multiple lists Rename kvm_init_msr_list() to kvm_init_msr_lists() to clarify that it initializes multiple lists: MSRs to save, emulated MSRs, and feature MSRs. No functional change intended. Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20230311004618.920745-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..087497aebded 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7084,7 +7084,7 @@ static void kvm_probe_msr_to_save(u32 msr_index) msrs_to_save[num_msrs_to_save++] = msr_index; } -static void kvm_init_msr_list(void) +static void kvm_init_msr_lists(void) { unsigned i; @@ -9452,7 +9452,7 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_caps.max_guest_tsc_khz = max; } kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; - kvm_init_msr_list(); + kvm_init_msr_lists(); return 0; out_unwind_ops: -- GitLab From fb3146b4dc3bc6d0c0402a75f21d628eccf9bf8c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:45:59 -0800 Subject: [PATCH 2315/5631] KVM: x86: Add a helper to query whether or not a vCPU has ever run Add a helper to query if a vCPU has run so that KVM doesn't have to open code the check on last_vmentry_cpu being set to a magic value. No functional change intended. Suggested-by: Xiaoyao Li Cc: Like Xu Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20230311004618.920745-3-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.h | 5 +++++ 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9583a110cf5f..b736ddb42088 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -420,7 +420,7 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ - if (vcpu->arch.last_vmentry_cpu != -1) { + if (kvm_vcpu_has_run(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) return r; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 144c5a01cd77..8ced48797d59 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5393,7 +5393,7 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * Changing guest CPUID after KVM_RUN is forbidden, see the comment in * kvm_arch_vcpu_ioctl(). */ - KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); + KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a8167b47b8c8..754190af1791 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -83,6 +83,11 @@ static inline unsigned int __shrink_ple_window(unsigned int val, void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.last_vmentry_cpu != -1; +} + static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu) { return vcpu->arch.exception.pending || -- GitLab From 5757f5b9562244e4b63f65576c16ca9eb21f81d2 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:00 -0800 Subject: [PATCH 2316/5631] KVM: x86: Add macros to track first...last VMX feature MSRs Add macros to track the range of VMX feature MSRs that are emulated by KVM to reduce the maintenance cost of extending the set of emulated MSRs. Note, KVM doesn't necessarily emulate all known/consumed VMX MSRs, e.g. PROCBASED_CTLS3 is consumed by KVM to enable IPI virtualization, but is not emulated as KVM doesn't emulate/virtualize IPI virtualization for nested guests. No functional change intended. Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20230311004618.920745-4-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/svm/svm.c | 2 +- arch/x86/kvm/vmx/vmx.c | 8 ++++---- arch/x86/kvm/x86.h | 8 ++++++++ 3 files changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 70183d2271b5..7584eb85410b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4124,7 +4124,7 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_MCG_EXT_CTL: - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return false; case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM)) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c18f74899f01..e89340dfa322 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1945,7 +1945,7 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, static int vmx_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); @@ -2030,7 +2030,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested_vmx_allowed(vcpu)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, @@ -2384,7 +2384,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->msr_ia32_sgxlepubkeyhash [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ if (!nested_vmx_allowed(vcpu)) @@ -6974,7 +6974,7 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: case MSR_AMD64_TSC_RATIO: diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 754190af1791..4bc483d082ee 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -40,6 +40,14 @@ void kvm_spurious_fault(void); failed; \ }) +/* + * The first...last VMX feature MSRs that are emulated by KVM. This may or may + * not cover all known VMX MSRs, as KVM doesn't emulate an MSR until there's an + * associated feature that KVM supports for nested virtualization. + */ +#define KVM_FIRST_EMULATED_VMX_MSR MSR_IA32_VMX_BASIC +#define KVM_LAST_EMULATED_VMX_MSR MSR_IA32_VMX_VMFUNC + #define KVM_DEFAULT_PLE_GAP 128 #define KVM_VMX_DEFAULT_PLE_WINDOW 4096 #define KVM_DEFAULT_PLE_WINDOW_GROW 2 -- GitLab From 9eb6ba31db27253a11441368d2801c1eedc48b4f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:01 -0800 Subject: [PATCH 2317/5631] KVM: x86: Generate set of VMX feature MSRs using first/last definitions Add VMX MSRs to the runtime list of feature MSRs by iterating over the range of emulated MSRs instead of manually defining each MSR in the "all" list. Using the range definition reduces the cost of emulating a new VMX MSR, e.g. prevents forgetting to add an MSR to the list. Extracting the VMX MSRs from the "all" list, which is a compile-time constant, also shrinks the list to the point where the compiler can heavily optimize code that iterates over the list. No functional change intended. Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20230311004618.920745-5-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 53 +++++++++++++++++++--------------------------- 1 file changed, 22 insertions(+), 31 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 087497aebded..6b667c651951 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1543,36 +1543,19 @@ static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* - * List of msr numbers which are used to expose MSR-based features that - * can be used by a hypervisor to validate requested CPU features. + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. */ -static const u32 msr_based_features_all[] = { - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR0_FIXED1, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_CR4_FIXED1, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - +static const u32 msr_based_features_all_except_vmx[] = { MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, }; -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; static unsigned int num_msr_based_features; /* @@ -7009,6 +6992,18 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return r; } +static void kvm_probe_feature_msr(u32 msr_index) +{ + struct kvm_msr_entry msr = { + .index = msr_index, + }; + + if (kvm_get_msr_feature(&msr)) + return; + + msr_based_features[num_msr_based_features++] = msr_index; +} + static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; @@ -7110,15 +7105,11 @@ static void kvm_init_msr_lists(void) emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { - struct kvm_msr_entry msr; + for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++) + kvm_probe_feature_msr(i); - msr.index = msr_based_features_all[i]; - if (kvm_get_msr_feature(&msr)) - continue; - - msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; - } + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) + kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]); } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, -- GitLab From e4d86fb910dfdeb4320d5a7b9ebf6e81f10b1380 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:02 -0800 Subject: [PATCH 2318/5631] KVM: selftests: Split PMU caps sub-tests to avoid writing MSR after KVM_RUN Split the PERF_CAPABILITIES subtests into two parts so that the LBR format testcases don't execute after KVM_RUN. Similar to the guest CPUID model, KVM will soon disallow changing PERF_CAPABILITIES after KVM_RUN, at which point attempting to set the MSR after KVM_RUN will yield false positives and/or false negatives depending on what the test is trying to do. Land the LBR format test in a more generic "immutable features" test in anticipation of expanding its scope to other immutable features. Link: https://lore.kernel.org/r/20230311004618.920745-6-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 51 +++++++++++-------- 1 file changed, 31 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index c280ba1e6572..ac08c0fdd84d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -41,24 +41,10 @@ static void guest_code(void) wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); } -int main(int argc, char *argv[]) +static void test_fungible_perf_capabilities(union perf_capabilities host_cap) { - struct kvm_vm *vm; struct kvm_vcpu *vcpu; - int ret; - union perf_capabilities host_cap; - uint64_t val; - - host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); - host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); - - /* Create VM */ - vm = vm_create_with_one_vcpu(&vcpu, guest_code); - - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); - - TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); - TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* testcase 1, set capabilities when we have PDCM bit */ vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); @@ -70,7 +56,16 @@ int main(int argc, char *argv[]) vcpu_run(vcpu); ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); - /* testcase 2, check valid LBR formats are accepted */ + kvm_vm_free(vm); +} + +static void test_immutable_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); + uint64_t val; + int ret; + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); @@ -78,8 +73,8 @@ int main(int argc, char *argv[]) ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); /* - * Testcase 3, check that an "invalid" LBR format is rejected. Only an - * exact match of the host's format (and 0/disabled) is allowed. + * KVM only supports the host's native LBR format, as well as '0' (to + * disable LBR support). Verify KVM rejects all other LBR formats. */ for (val = 1; val <= PMU_CAP_LBR_FMT; val++) { if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) @@ -88,7 +83,23 @@ int main(int argc, char *argv[]) ret = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); TEST_ASSERT(!ret, "Bad LBR FMT = 0x%lx didn't fail", val); } + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + union perf_capabilities host_cap; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM)); + + TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION)); + TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); + + host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); + host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); + + test_fungible_perf_capabilities(host_cap); + test_immutable_perf_capabilities(host_cap); printf("Completed perf capability tests.\n"); - kvm_vm_free(vm); } -- GitLab From 0094f62c7eaaaf53a011a4e46f9f32e5f3295e8c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:03 -0800 Subject: [PATCH 2319/5631] KVM: x86: Disallow writes to immutable feature MSRs after KVM_RUN Disallow writes to feature MSRs after KVM_RUN to prevent userspace from changing the vCPU model after running the vCPU. Similar to guest CPUID, KVM uses feature MSRs to configure intercepts, determine what operations are/aren't allowed, etc. Changing the capabilities while the vCPU is active will at best yield unpredictable guest behavior, and at worst could be dangerous to KVM. Allow writing the current value, e.g. so that userspace can blindly set all MSRs when emulating RESET, and unconditionally allow writes to MSR_IA32_UCODE_REV so that userspace can emulate patch loads. Special case the VMX MSRs to keep the generic list small, i.e. so that KVM can do a linear walk of the generic list without incurring meaningful overhead. Cc: Like Xu Cc: Yu Zhang Reviewed-by: Xiaoyao Li Link: https://lore.kernel.org/r/20230311004618.920745-7-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6b667c651951..cf33b7d910a6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1558,6 +1558,25 @@ static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; static unsigned int num_msr_based_features; +/* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. + */ +static bool kvm_is_immutable_feature_msr(u32 msr) +{ + int i; + + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) + return true; + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + /* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: @@ -2175,6 +2194,22 @@ static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { + u64 val; + + /* + * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does + * not support modifying the guest vCPU model on the fly, e.g. changing + * the nVMX capabilities while L2 is running is nonsensical. Ignore + * writes of the same value, e.g. to allow userspace to blindly stuff + * all MSRs when emulating RESET. + */ + if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) { + if (do_get_msr(vcpu, index, &val) || *data != val) + return -EINVAL; + + return 0; + } + return kvm_set_msr_ignored_check(vcpu, index, *data, true); } -- GitLab From 3a6de51a437fb4d2433f8a99fb59f43866cdbb98 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:04 -0800 Subject: [PATCH 2320/5631] KVM: x86/pmu: WARN and bug the VM if PMU is refreshed after vCPU has run Now that KVM disallows changing feature MSRs, i.e. PERF_CAPABILITIES, after running a vCPU, WARN and bug the VM if the PMU is refreshed after the vCPU has run. Note, KVM has disallowed CPUID updates after running a vCPU since commit feb627e8d6f6 ("KVM: x86: Forbid KVM_SET_CPUID{,2} after KVM_RUN"), i.e. PERF_CAPABILITIES was the only remaining way to trigger a PMU refresh after KVM_RUN. Cc: Like Xu Link: https://lore.kernel.org/r/20230311004618.920745-8-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 3 +++ arch/x86/kvm/x86.c | 10 +++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 29492c2a0c82..136184fe9e92 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -589,6 +589,9 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) + return; + bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); static_call(kvm_x86_pmu_refresh)(vcpu); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cf33b7d910a6..a86ad45a53b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3632,9 +3632,17 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~kvm_caps.supported_perf_cap) return 1; + /* + * Note, this is not just a performance optimization! KVM + * disallows changing feature MSRs after the vCPU has run; PMU + * refresh will bug the VM if called after the vCPU has run. + */ + if (vcpu->arch.perf_capabilities == data) + break; + vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); - return 0; + break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: -- GitLab From 957d0f70e97bb2257d8bf746ff2f524b793751b3 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:05 -0800 Subject: [PATCH 2321/5631] KVM: x86/pmu: Zero out LBR capabilities during PMU refresh Zero out the LBR capabilities during PMU refresh to avoid exposing LBRs to the guest against userspace's wishes. If userspace modifies the guest's CPUID model or invokes KVM_CAP_PMU_CAPABILITY to disable vPMU after an initial KVM_SET_CPUID2, but before the first KVM_RUN, KVM will retain the previous LBR info due to bailing before refreshing the LBR descriptor. Note, this is a very theoretical bug, there is no known use case where a VMM would deliberately enable the vPMU via KVM_SET_CPUID2, and then later disable the vPMU. Link: https://lore.kernel.org/r/20230311004618.920745-9-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/pmu_intel.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index e8a3be0b9df9..d889bb2a1de5 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -531,6 +531,16 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_enable_mask = ~0ull; pmu->pebs_data_cfg_mask = ~0ull; + memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); + + /* + * Setting passthrough of LBR MSRs is done only in the VM-Entry loop, + * and PMU refresh is disallowed after the vCPU has run, i.e. this code + * should never be reached while KVM is passing through MSRs. + */ + if (KVM_BUG_ON(lbr_desc->msr_passthrough, vcpu->kvm)) + return; + entry = kvm_find_cpuid_entry(vcpu, 0xa); if (!entry || !vcpu->kvm->arch.enable_pmu) return; -- GitLab From 710fb612672e0c05fe3f56fb4e81fae22ef492a2 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:06 -0800 Subject: [PATCH 2322/5631] KVM: selftests: Move 0/initial value PERF_CAPS checks to dedicated sub-test Use a separate sub-test to verify userspace can clear PERF_CAPABILITIES and restore it to the KVM-supported value, as the testcase isn't unique to the LBR format. Link: https://lore.kernel.org/r/20230311004618.920745-10-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 25 ++++++++++++++----- 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index ac08c0fdd84d..c3b0738e361b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -41,6 +41,24 @@ static void guest_code(void) wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); } +/* + * Verify KVM allows writing PERF_CAPABILITIES with all KVM-supported features + * enabled, as well as '0' (to disable all features). + */ +static void test_basic_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); + + kvm_vm_free(vm); +} + static void test_fungible_perf_capabilities(union perf_capabilities host_cap) { struct kvm_vcpu *vcpu; @@ -66,12 +84,6 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) uint64_t val; int ret; - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); - - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.lbr_format); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), (u64)host_cap.lbr_format); - /* * KVM only supports the host's native LBR format, as well as '0' (to * disable LBR support). Verify KVM rejects all other LBR formats. @@ -98,6 +110,7 @@ int main(int argc, char *argv[]) host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); + test_basic_perf_capabilities(host_cap); test_fungible_perf_capabilities(host_cap); test_immutable_perf_capabilities(host_cap); -- GitLab From b1b705627cb3c23333e04637d7a90833b560584e Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:07 -0800 Subject: [PATCH 2323/5631] KVM: selftests: Assert that full-width PMC writes are supported if PDCM=1 KVM emulates full-width PMC writes in software, assert that KVM reports full-width writes as supported if PERF_CAPABILITIES is supported. Link: https://lore.kernel.org/r/20230311004618.920745-11-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index c3b0738e361b..035470b38400 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -110,6 +110,9 @@ int main(int argc, char *argv[]) host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); + TEST_ASSERT(host_cap.full_width_write, + "Full-width writes should always be supported"); + test_basic_perf_capabilities(host_cap); test_fungible_perf_capabilities(host_cap); test_immutable_perf_capabilities(host_cap); -- GitLab From 22234c2495eafd6b8f1f26c6c6adc12aca60fd7f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:08 -0800 Subject: [PATCH 2324/5631] KVM: selftests: Print out failing MSR and value in vcpu_set_msr() Reimplement vcpu_set_msr() as a macro and pretty print the failing MSR (when possible) and the value if KVM_SET_MSRS fails instead of using the using the standard KVM_IOCTL_ERROR(). KVM_SET_MSRS is somewhat odd in that it returns the index of the last successful write, i.e. will be '0' on failure barring an entirely different KVM bug. And for writing MSRs, the MSR being written and the value being written are almost always relevant to the failure, i.e. just saying "failed!" doesn't help debug. Place the string goo in a separate macro in anticipation of using it to further expand MSR testing. Link: https://lore.kernel.org/r/20230311004618.920745-12-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 32 ++++++++++++++----- 1 file changed, 24 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 90387ddcb2a9..293a9085311d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -928,14 +928,30 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu, uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index); int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value); -static inline void vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, - uint64_t msr_value) -{ - int r = _vcpu_set_msr(vcpu, msr_index, msr_value); - - TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r)); -} - +/* + * Assert on an MSR access(es) and pretty print the MSR name when possible. + * Note, the caller provides the stringified name so that the name of macro is + * printed, not the value the macro resolves to (due to macro expansion). + */ +#define TEST_ASSERT_MSR(cond, fmt, msr, str, args...) \ +do { \ + if (__builtin_constant_p(msr)) { \ + TEST_ASSERT(cond, fmt, str, args); \ + } else if (!(cond)) { \ + char buf[16]; \ + \ + snprintf(buf, sizeof(buf), "MSR 0x%x", msr); \ + TEST_ASSERT(cond, fmt, buf, args); \ + } \ +} while (0) + +#define vcpu_set_msr(vcpu, msr, val) \ +do { \ + uint64_t v = val; \ + \ + TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \ + "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \ +} while (0) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); bool vm_is_unrestricted_guest(struct kvm_vm *vm); -- GitLab From f138258565d18f0f9a8d07f04162c68eee997ce6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:09 -0800 Subject: [PATCH 2325/5631] KVM: selftests: Verify KVM preserves userspace writes to "durable" MSRs Assert that KVM provides "read what you wrote" semantics for all "durable" MSRs (for lack of a better name). The extra coverage is cheap from a runtime performance perspective, and verifying the behavior in the common helper avoids gratuitous copy+paste in individual tests. Note, this affects all tests that set MSRs from userspace! Link: https://lore.kernel.org/r/20230311004618.920745-13-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 293a9085311d..e1d65d933310 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -945,12 +945,27 @@ do { \ } \ } while (0) +/* + * Returns true if KVM should return the last written value when reading an MSR + * from userspace, e.g. the MSR isn't a command MSR, doesn't emulate state that + * is changing, etc. This is NOT an exhaustive list! The intent is to filter + * out MSRs that are not durable _and_ that a selftest wants to write. + */ +static inline bool is_durable_msr(uint32_t msr) +{ + return msr != MSR_IA32_TSC; +} + #define vcpu_set_msr(vcpu, msr, val) \ do { \ - uint64_t v = val; \ + uint64_t r, v = val; \ \ TEST_ASSERT_MSR(_vcpu_set_msr(vcpu, msr, v) == 1, \ "KVM_SET_MSRS failed on %s, value = 0x%lx", msr, #msr, v); \ + if (!is_durable_msr(msr)) \ + break; \ + r = vcpu_get_msr(vcpu, msr); \ + TEST_ASSERT_MSR(r == v, "Set %s to '0x%lx', got back '0x%lx'", msr, #msr, v, r);\ } while (0) void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); -- GitLab From 69713940d2b4de34a6923fc202e1796dc2f79604 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:10 -0800 Subject: [PATCH 2326/5631] KVM: selftests: Drop now-redundant checks on PERF_CAPABILITIES writes Now that vcpu_set_msr() verifies the expected "read what was wrote" semantics of all durable MSRs, including PERF_CAPABILITIES, drop the now-redundant manual checks in the VMX PMU caps test. Link: https://lore.kernel.org/r/20230311004618.920745-14-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 035470b38400..f7a27b5c949b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -51,10 +51,7 @@ static void test_basic_perf_capabilities(union perf_capabilities host_cap) struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), 0); - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); kvm_vm_free(vm); } @@ -67,9 +64,6 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) /* testcase 1, set capabilities when we have PDCM bit */ vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); - /* check capabilities can be retrieved with KVM_GET_MSR */ - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); - /* check whatever we write with KVM_SET_MSR is _not_ modified */ vcpu_run(vcpu); ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); -- GitLab From 37f4e79c43e5750e75b3de8726b4c21bae6ab7aa Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:11 -0800 Subject: [PATCH 2327/5631] KVM: selftests: Test all fungible features in PERF_CAPABILITIES Verify that userspace can set all fungible features in PERF_CAPABILITIES. Drop the now unused #define of the "full-width writes" flag. Link: https://lore.kernel.org/r/20230311004618.920745-15-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 29 +++++++++++++++---- 1 file changed, 24 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index f7a27b5c949b..2647282ff380 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -14,10 +14,11 @@ #define _GNU_SOURCE /* for program_invocation_short_name */ #include +#include + #include "kvm_util.h" #include "vmx.h" -#define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f union perf_capabilities { @@ -36,6 +37,18 @@ union perf_capabilities { u64 capabilities; }; +/* + * The LBR format and most PEBS features are immutable, all other features are + * fungible (if supported by the host and KVM). + */ +static const union perf_capabilities immutable_caps = { + .lbr_format = -1, + .pebs_trap = 1, + .pebs_arch_reg = 1, + .pebs_format = -1, + .pebs_baseline = 1, +}; + static void guest_code(void) { wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); @@ -58,15 +71,22 @@ static void test_basic_perf_capabilities(union perf_capabilities host_cap) static void test_fungible_perf_capabilities(union perf_capabilities host_cap) { + const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; + struct kvm_vcpu *vcpu; struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); + int bit; - /* testcase 1, set capabilities when we have PDCM bit */ - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES); + for_each_set_bit(bit, &fungible_caps, 64) { + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, BIT_ULL(bit)); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities & ~BIT_ULL(bit)); + } + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); /* check whatever we write with KVM_SET_MSR is _not_ modified */ vcpu_run(vcpu); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), PMU_CAP_FW_WRITES); + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); kvm_vm_free(vm); } @@ -102,7 +122,6 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0); host_cap.capabilities = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); - host_cap.capabilities &= (PMU_CAP_FW_WRITES | PMU_CAP_LBR_FMT); TEST_ASSERT(host_cap.full_width_write, "Full-width writes should always be supported"); -- GitLab From a2a34d148e75c242fd059e8c7ab31e88396013b6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:12 -0800 Subject: [PATCH 2328/5631] KVM: selftests: Test all immutable non-format bits in PERF_CAPABILITIES Add negative testing of all immutable bits in PERF_CAPABILITIES, i.e. single bits that are reserved-0 or are effectively reserved-1 by KVM. Omit LBR and PEBS format bits from the test as it's easier to test them manually than it is to add safeguards to the comment path, e.g. toggling a single bit can yield a format of '0', which is legal as a "disable" value. Link: https://lore.kernel.org/r/20230311004618.920745-16-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 30 +++++++++++++++++-- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 2647282ff380..d91bf44a2e39 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -49,6 +49,11 @@ static const union perf_capabilities immutable_caps = { .pebs_baseline = 1, }; +static const union perf_capabilities format_caps = { + .lbr_format = -1, + .pebs_format = -1, +}; + static void guest_code(void) { wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); @@ -91,12 +96,30 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) kvm_vm_free(vm); } +/* + * Verify KVM rejects attempts to set unsupported and/or immutable features in + * PERF_CAPABILITIES. Note, LBR format and PEBS format need to be validated + * separately as they are multi-bit values, e.g. toggling or setting a single + * bit can generate a false positive without dedicated safeguards. + */ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) { + const uint64_t reserved_caps = (~host_cap.capabilities | + immutable_caps.capabilities) & + ~format_caps.capabilities; + struct kvm_vcpu *vcpu; struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); uint64_t val; - int ret; + int r, bit; + + for_each_set_bit(bit, &reserved_caps, 64) { + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities ^ BIT_ULL(bit)); + TEST_ASSERT(!r, "%s immutable feature 0x%llx (bit %d) didn't fail", + host_cap.capabilities & BIT_ULL(bit) ? "Setting" : "Clearing", + BIT_ULL(bit), bit); + } /* * KVM only supports the host's native LBR format, as well as '0' (to @@ -106,9 +129,10 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) continue; - ret = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); - TEST_ASSERT(!ret, "Bad LBR FMT = 0x%lx didn't fail", val); + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); + TEST_ASSERT(!r, "Bad LBR FMT = 0x%lx didn't fail", val); } + kvm_vm_free(vm); } -- GitLab From baa36dac6ca8ecd709dafb87a79d3bead40e48fe Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:13 -0800 Subject: [PATCH 2329/5631] KVM: selftests: Expand negative testing of guest writes to PERF_CAPABILITIES Test that the guest can't write 0 to PERF_CAPABILITIES, can't write the current value, and can't toggle _any_ bits. There is no reason to special case the LBR format. Link: https://lore.kernel.org/r/20230311004618.920745-17-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 61 ++++++++++++++++--- 1 file changed, 54 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index d91bf44a2e39..44fc6101a547 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -54,9 +54,59 @@ static const union perf_capabilities format_caps = { .pebs_format = -1, }; -static void guest_code(void) +static void guest_code(uint64_t current_val) { - wrmsr(MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT); + uint8_t vector; + int i; + + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, current_val); + GUEST_ASSERT_2(vector == GP_VECTOR, current_val, vector); + + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, 0); + GUEST_ASSERT_2(vector == GP_VECTOR, 0, vector); + + for (i = 0; i < 64; i++) { + vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, + current_val ^ BIT_ULL(i)); + GUEST_ASSERT_2(vector == GP_VECTOR, + current_val ^ BIT_ULL(i), vector); + } + + GUEST_DONE(); +} + +/* + * Verify that guest WRMSRs to PERF_CAPABILITIES #GP regardless of the value + * written, that the guest always sees the userspace controlled value, and that + * PERF_CAPABILITIES is immutable after KVM_RUN. + */ +static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); + struct ucall uc; + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + + vcpu_args_set(vcpu, 1, host_cap.capabilities); + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "val = 0x%lx, vector = %lu"); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } + + ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); + + kvm_vm_free(vm); } /* @@ -79,7 +129,7 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities; struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); + struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); int bit; for_each_set_bit(bit, &fungible_caps, 64) { @@ -89,10 +139,6 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap) } vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); - /* check whatever we write with KVM_SET_MSR is _not_ modified */ - vcpu_run(vcpu); - ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); - kvm_vm_free(vm); } @@ -153,6 +199,7 @@ int main(int argc, char *argv[]) test_basic_perf_capabilities(host_cap); test_fungible_perf_capabilities(host_cap); test_immutable_perf_capabilities(host_cap); + test_guest_wrmsr_perf_capabilities(host_cap); printf("Completed perf capability tests.\n"); } -- GitLab From 81fd92411264e4f7b982bb6066b4bc04311bc48a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:14 -0800 Subject: [PATCH 2330/5631] KVM: selftests: Test post-KVM_RUN writes to PERF_CAPABILITIES Now that KVM disallows changing PERF_CAPABILITIES after KVM_RUN, expand the host side checks to verify KVM rejects any attempts to change bits from userspace. Link: https://lore.kernel.org/r/20230311004618.920745-18-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 44fc6101a547..6fc86f5eba0b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -85,6 +85,7 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) struct kvm_vcpu *vcpu; struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code); struct ucall uc; + int r, i; vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); @@ -106,6 +107,18 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap) ASSERT_EQ(vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES), host_cap.capabilities); + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0); + TEST_ASSERT(!r, "Post-KVM_RUN write '0' didn't fail"); + + for (i = 0; i < 64; i++) { + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, + host_cap.capabilities ^ BIT_ULL(i)); + TEST_ASSERT(!r, "Post-KVM_RUN write '0x%llx'didn't fail", + host_cap.capabilities ^ BIT_ULL(i)); + } + kvm_vm_free(vm); } -- GitLab From bc7bb0082960d030171e11ed4e4b518950415625 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:15 -0800 Subject: [PATCH 2331/5631] KVM: selftests: Drop "all done!" printf() from PERF_CAPABILITIES test Drop the arbitrary "done" message from the VMX PMU caps test, it's pretty obvious the test is done when the process exits. Link: https://lore.kernel.org/r/20230311004618.920745-19-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 6fc86f5eba0b..6733d879a00b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -213,6 +213,4 @@ int main(int argc, char *argv[]) test_fungible_perf_capabilities(host_cap); test_immutable_perf_capabilities(host_cap); test_guest_wrmsr_perf_capabilities(host_cap); - - printf("Completed perf capability tests.\n"); } -- GitLab From 8ac2f774b9ead749720fe7a648e6c6ada57e01f3 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:16 -0800 Subject: [PATCH 2332/5631] KVM: selftests: Refactor LBR_FMT test to avoid use of separate macro Rework the LBR format test to use the bitfield instead of a separate mask macro, mainly so that adding a nearly-identical PEBS format test doesn't have to copy-paste-tweak the macro too. No functional change intended. Link: https://lore.kernel.org/r/20230311004618.920745-20-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 6733d879a00b..38aec88d733b 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -19,8 +19,6 @@ #include "kvm_util.h" #include "vmx.h" -#define PMU_CAP_LBR_FMT 0x3f - union perf_capabilities { struct { u64 lbr_format:6; @@ -169,7 +167,7 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) struct kvm_vcpu *vcpu; struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL); - uint64_t val; + union perf_capabilities val = host_cap; int r, bit; for_each_set_bit(bit, &reserved_caps, 64) { @@ -184,12 +182,13 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) * KVM only supports the host's native LBR format, as well as '0' (to * disable LBR support). Verify KVM rejects all other LBR formats. */ - for (val = 1; val <= PMU_CAP_LBR_FMT; val++) { - if (val == (host_cap.capabilities & PMU_CAP_LBR_FMT)) + for (val.lbr_format = 1; val.lbr_format; val.lbr_format++) { + if (val.lbr_format == host_cap.lbr_format) continue; - r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val); - TEST_ASSERT(!r, "Bad LBR FMT = 0x%lx didn't fail", val); + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val.capabilities); + TEST_ASSERT(!r, "Bad LBR FMT = 0x%x didn't fail, host = 0x%x", + val.lbr_format, host_cap.lbr_format); } kvm_vm_free(vm); -- GitLab From 8b95b4155523dcb5412a73c631c680098bcbbb40 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:17 -0800 Subject: [PATCH 2333/5631] KVM: selftests: Add negative testcase for PEBS format in PERF_CAPABILITIES Expand the immutable features sub-test for PERF_CAPABILITIES to verify KVM rejects any attempt to use a PEBS format other than the host's. Link: https://lore.kernel.org/r/20230311004618.920745-21-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 38aec88d733b..29aaa0419294 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -191,6 +191,16 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) val.lbr_format, host_cap.lbr_format); } + /* Ditto for the PEBS format. */ + for (val.pebs_format = 1; val.pebs_format; val.pebs_format++) { + if (val.pebs_format == host_cap.pebs_format) + continue; + + r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, val.capabilities); + TEST_ASSERT(!r, "Bad PEBS FMT = 0x%x didn't fail, host = 0x%x", + val.pebs_format, host_cap.pebs_format); + } + kvm_vm_free(vm); } -- GitLab From d8f992e9fde8dc23b6fe649fa1b0ed5c123738fe Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Mar 2023 16:46:18 -0800 Subject: [PATCH 2334/5631] KVM: selftests: Verify LBRs are disabled if vPMU is disabled Verify that disabling the guest's vPMU via CPUID also disables LBRs. KVM has had at least one bug where LBRs would remain enabled even though the intent was to disable everything PMU related. Link: https://lore.kernel.org/r/20230311004618.920745-22-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/vmx_pmu_caps_test.c | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index 29aaa0419294..3009b3e5254d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -204,6 +204,34 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap) kvm_vm_free(vm); } +/* + * Test that LBR MSRs are writable when LBRs are enabled, and then verify that + * disabling the vPMU via CPUID also disables LBR support. Set bits 2:0 of + * LBR_TOS as those bits are writable across all uarch implementations (arch + * LBRs will need to poke a different MSR). + */ +static void test_lbr_perf_capabilities(union perf_capabilities host_cap) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int r; + + if (!host_cap.lbr_format) + return; + + vm = vm_create_with_one_vcpu(&vcpu, NULL); + + vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); + vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); + + vcpu_clear_cpuid_entry(vcpu, X86_PROPERTY_PMU_VERSION.function); + + r = _vcpu_set_msr(vcpu, MSR_LBR_TOS, 7); + TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU"); + + kvm_vm_free(vm); +} + int main(int argc, char *argv[]) { union perf_capabilities host_cap; @@ -222,4 +250,5 @@ int main(int argc, char *argv[]) test_fungible_perf_capabilities(host_cap); test_immutable_perf_capabilities(host_cap); test_guest_wrmsr_perf_capabilities(host_cap); + test_lbr_perf_capabilities(host_cap); } -- GitLab From cdd2fbf6360e84c02ac4cea11733083c2ca8dace Mon Sep 17 00:00:00 2001 From: Like Xu Date: Tue, 14 Feb 2023 13:07:46 +0800 Subject: [PATCH 2335/5631] KVM: x86/pmu: Rename pmc_is_enabled() to pmc_is_globally_enabled() The name of function pmc_is_enabled() is a bit misleading. A PMC can be disabled either by PERF_CLOBAL_CTRL or by its corresponding EVTSEL. Append global semantics to its name. Suggested-by: Jim Mattson Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230214050757.9623-2-likexu@tencent.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 136184fe9e92..35d80151b853 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,7 +93,7 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static inline bool pmc_is_enabled(struct kvm_pmc *pmc) +static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) { return static_call(kvm_x86_pmu_pmc_is_enabled)(pmc); } @@ -409,7 +409,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) pmc_pause_counter(pmc); - if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc)) + if (!pmc_speculative_in_use(pmc) || !pmc_is_globally_enabled(pmc)) goto reprogram_complete; if (!check_pmu_event_filter(pmc)) @@ -688,7 +688,7 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - if (!pmc || !pmc_is_enabled(pmc) || !pmc_speculative_in_use(pmc)) + if (!pmc || !pmc_is_globally_enabled(pmc) || !pmc_speculative_in_use(pmc)) continue; /* Ignore checks for edge detect, pin control, invert and CMASK bits */ -- GitLab From 8bca8c5ce40b03862d782b9991da146909199327 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 26 Jan 2023 17:08:03 -0800 Subject: [PATCH 2336/5631] KVM: VMX: Refactor intel_pmu_{g,}set_msr() to align with other helpers Invert the flows in intel_pmu_{g,s}et_msr()'s case statements so that they follow the kernel's preferred style of: if () return return which is also the style used by every other {g,s}et_msr() helper (except AMD's PMU variant, which doesn't use a switch statement). Modify the "set" paths with costly side effects, i.e. that reprogram counters, to skip only the side effects, i.e. to perform reserved bits checks even if the value is unchanged. None of the reserved bits checks are expensive, so there's no strong justification for skipping them, and guarding only the side effect makes it slightly more obvious what is being skipped and why. No functional change intended (assuming no reserved bit bugs). Link: https://lkml.kernel.org/r/Y%2B6cfen%2FCpO3%2FdLO%40google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/pmu_intel.c | 109 ++++++++++++++++++----------------- 1 file changed, 57 insertions(+), 52 deletions(-) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index d889bb2a1de5..c45bd10f80a1 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -351,45 +351,47 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: msr_info->data = pmu->fixed_ctr_ctrl; - return 0; + break; case MSR_CORE_PERF_GLOBAL_STATUS: msr_info->data = pmu->global_status; - return 0; + break; case MSR_CORE_PERF_GLOBAL_CTRL: msr_info->data = pmu->global_ctrl; - return 0; + break; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: msr_info->data = 0; - return 0; + break; case MSR_IA32_PEBS_ENABLE: msr_info->data = pmu->pebs_enable; - return 0; + break; case MSR_IA32_DS_AREA: msr_info->data = pmu->ds_area; - return 0; + break; case MSR_PEBS_DATA_CFG: msr_info->data = pmu->pebs_data_cfg; - return 0; + break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { u64 val = pmc_read_counter(pmc); msr_info->data = val & pmu->counter_bitmask[KVM_PMC_GP]; - return 0; + break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { u64 val = pmc_read_counter(pmc); msr_info->data = val & pmu->counter_bitmask[KVM_PMC_FIXED]; - return 0; + break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { msr_info->data = pmc->eventsel; - return 0; - } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) - return 0; + break; + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) { + break; + } + return 1; } - return 1; + return 0; } static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -402,44 +404,43 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (pmu->fixed_ctr_ctrl == data) - return 0; - if (!(data & pmu->fixed_ctr_ctrl_mask)) { + if (data & pmu->fixed_ctr_ctrl_mask) + return 1; + + if (pmu->fixed_ctr_ctrl != data) reprogram_fixed_counters(pmu, data); - return 0; - } break; case MSR_CORE_PERF_GLOBAL_STATUS: - if (msr_info->host_initiated) { - pmu->global_status = data; - return 0; - } - break; /* RO MSR */ + if (!msr_info->host_initiated) + return 1; /* RO MSR */ + + pmu->global_status = data; + break; case MSR_CORE_PERF_GLOBAL_CTRL: - if (pmu->global_ctrl == data) - return 0; - if (kvm_valid_perf_global_ctrl(pmu, data)) { + if (!kvm_valid_perf_global_ctrl(pmu, data)) + return 1; + + if (pmu->global_ctrl != data) { diff = pmu->global_ctrl ^ data; pmu->global_ctrl = data; reprogram_counters(pmu, diff); - return 0; } break; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (!(data & pmu->global_ovf_ctrl_mask)) { - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - return 0; - } + if (data & pmu->global_ovf_ctrl_mask) + return 1; + + if (!msr_info->host_initiated) + pmu->global_status &= ~data; break; case MSR_IA32_PEBS_ENABLE: - if (pmu->pebs_enable == data) - return 0; - if (!(data & pmu->pebs_enable_mask)) { + if (data & pmu->pebs_enable_mask) + return 1; + + if (pmu->pebs_enable != data) { diff = pmu->pebs_enable ^ data; pmu->pebs_enable = data; reprogram_counters(pmu, diff); - return 0; } break; case MSR_IA32_DS_AREA: @@ -447,15 +448,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (is_noncanonical_address(data, vcpu)) return 1; + pmu->ds_area = data; - return 0; + break; case MSR_PEBS_DATA_CFG: - if (pmu->pebs_data_cfg == data) - return 0; - if (!(data & pmu->pebs_data_cfg_mask)) { - pmu->pebs_data_cfg = data; - return 0; - } + if (data & pmu->pebs_data_cfg_mask) + return 1; + + pmu->pebs_data_cfg = data; break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || @@ -463,33 +463,38 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((msr & MSR_PMC_FULL_WIDTH_BIT) && (data & ~pmu->counter_bitmask[KVM_PMC_GP])) return 1; + if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); pmc_update_sample_period(pmc); - return 0; + break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); pmc_update_sample_period(pmc); - return 0; + break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { - if (data == pmc->eventsel) - return 0; reserved_bits = pmu->reserved_bits; if ((pmc->idx == 2) && (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED)) reserved_bits ^= HSW_IN_TX_CHECKPOINTED; - if (!(data & reserved_bits)) { + if (data & reserved_bits) + return 1; + + if (data != pmc->eventsel) { pmc->eventsel = data; kvm_pmu_request_counter_reprogam(pmc); - return 0; } - } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) - return 0; + break; + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) { + break; + } + /* Not a known PMU MSR. */ + return 1; } - return 1; + return 0; } static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) -- GitLab From 649bccd7fac98225525c79cf4b1cecc4bafdfc54 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Tue, 14 Feb 2023 13:07:48 +0800 Subject: [PATCH 2337/5631] KVM: x86/pmu: Rewrite reprogram_counters() to improve performance A valid pmc is always tested before using pmu->reprogram_pmi. Eliminate this part of the redundancy by setting the counter's bitmask directly, and in addition, trigger KVM_REQ_PMU only once to save more cpu cycles. Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230214050757.9623-4-likexu@tencent.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/pmu_intel.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index c45bd10f80a1..eb291dfbe4aa 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -76,13 +76,13 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) { int bit; - struct kvm_pmc *pmc; - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) { - pmc = intel_pmc_idx_to_pmc(pmu, bit); - if (pmc) - kvm_pmu_request_counter_reprogam(pmc); - } + if (!diff) + return; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + set_bit(bit, pmu->reprogram_pmi); + kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu)); } static bool intel_hw_event_available(struct kvm_pmc *pmc) -- GitLab From 3d88aec0d42eec26b633fb2a473e294a1125bbd7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 5 Apr 2023 23:52:23 -0700 Subject: [PATCH 2338/5631] perf pmu: Make parser reentrant By default bison uses global state for compatibility with yacc. Make the parser reentrant so that it may be used in asynchronous and multithreaded situations. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Gaosheng Cui Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Link: https://lore.kernel.org/r/20230406065224.2553640-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 26 ++++++++++++++++++++------ tools/perf/util/pmu.h | 2 +- tools/perf/util/pmu.l | 17 ++++++++++++----- tools/perf/util/pmu.y | 5 ++++- 4 files changed, 37 insertions(+), 13 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 78a407b42ad1..96ef317bac41 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -24,6 +24,8 @@ #include "evsel.h" #include "pmu.h" #include "pmus.h" +#include "pmu-bison.h" +#include "pmu-flex.h" #include "parse-events.h" #include "print-events.h" #include "header.h" @@ -57,9 +59,6 @@ struct perf_pmu_format { struct list_head list; }; -int perf_pmu_parse(struct list_head *list, char *name); -extern FILE *perf_pmu_in; - static bool hybrid_scanned; static struct perf_pmu *perf_pmu__find2(int dirfd, const char *name); @@ -81,6 +80,8 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head) while (!ret && (evt_ent = readdir(format_dir))) { char *name = evt_ent->d_name; int fd; + void *scanner; + FILE *file; if (!strcmp(name, ".") || !strcmp(name, "..")) continue; @@ -91,9 +92,22 @@ int perf_pmu__format_parse(int dirfd, struct list_head *head) if (fd < 0) break; - perf_pmu_in = fdopen(fd, "r"); - ret = perf_pmu_parse(head, name); - fclose(perf_pmu_in); + file = fdopen(fd, "r"); + if (!file) { + close(fd); + break; + } + + ret = perf_pmu_lex_init(&scanner); + if (ret) { + fclose(file); + break; + } + + perf_pmu_set_in(file, scanner); + ret = perf_pmu_parse(head, name, scanner); + perf_pmu_lex_destroy(scanner); + fclose(file); } closedir(format_dir); diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 32c3a75bca0e..d53618c65c92 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -206,7 +206,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, struct perf_pmu_info *info); struct list_head *perf_pmu__alias(struct perf_pmu *pmu, struct list_head *head_terms); -void perf_pmu_error(struct list_head *list, char *name, char const *msg); +void perf_pmu_error(struct list_head *list, char *name, void *scanner, char const *msg); int perf_pmu__new_format(struct list_head *list, char *name, int config, unsigned long *bits); diff --git a/tools/perf/util/pmu.l b/tools/perf/util/pmu.l index 58b4926cfaca..67b247be693b 100644 --- a/tools/perf/util/pmu.l +++ b/tools/perf/util/pmu.l @@ -1,4 +1,6 @@ %option prefix="perf_pmu_" +%option reentrant +%option bison-bridge %{ #include @@ -6,16 +8,21 @@ #include "pmu.h" #include "pmu-bison.h" -static int value(int base) +char *perf_pmu_get_text(yyscan_t yyscanner); +YYSTYPE *perf_pmu_get_lval(yyscan_t yyscanner); + +static int value(yyscan_t scanner, int base) { + YYSTYPE *yylval = perf_pmu_get_lval(scanner); + char *text = perf_pmu_get_text(scanner); long num; errno = 0; - num = strtoul(perf_pmu_text, NULL, base); + num = strtoul(text, NULL, base); if (errno) return PP_ERROR; - perf_pmu_lval.num = num; + yylval->num = num; return PP_VALUE; } @@ -25,7 +32,7 @@ num_dec [0-9]+ %% -{num_dec} { return value(10); } +{num_dec} { return value(yyscanner, 10); } config { return PP_CONFIG; } - { return '-'; } : { return ':'; } @@ -35,7 +42,7 @@ config { return PP_CONFIG; } %% -int perf_pmu_wrap(void) +int perf_pmu_wrap(void *scanner __maybe_unused) { return 1; } diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index e675d79a0274..dff4e892ac4d 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -1,6 +1,8 @@ - +%define api.pure full %parse-param {struct list_head *format} %parse-param {char *name} +%parse-param {void *scanner} +%lex-param {void* scanner} %{ @@ -78,6 +80,7 @@ PP_VALUE void perf_pmu_error(struct list_head *list __maybe_unused, char *name __maybe_unused, + void *scanner __maybe_unused, char const *msg __maybe_unused) { } -- GitLab From 0ea8920e86e3232c56dc812c1f363fd20fce46c6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 5 Apr 2023 23:52:24 -0700 Subject: [PATCH 2339/5631] perf pmu: Fix a few potential fd leaks Ensure fd is closed on error paths. Signed-off-by: Ian Rogers Acked-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Gaosheng Cui Cc: German Gomez Cc: Ingo Molnar Cc: James Clark Cc: Jing Zhang Cc: Leo Yan Cc: Mark Rutland Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Link: https://lore.kernel.org/r/20230406065224.2553640-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 96ef317bac41..9eedbfc9e863 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -494,9 +494,13 @@ static int pmu_aliases_parse(int dirfd, struct list_head *head) continue; fd = openat(dirfd, name, O_RDONLY); + if (fd == -1) { + pr_debug("Cannot open %s\n", name); + continue; + } file = fdopen(fd, "r"); if (!file) { - pr_debug("Cannot open %s\n", name); + close(fd); continue; } @@ -1882,9 +1886,13 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) continue; fd = openat(caps_fd, name, O_RDONLY); + if (fd == -1) + continue; file = fdopen(fd, "r"); - if (!file) + if (!file) { + close(fd); continue; + } if (!fgets(value, sizeof(value), file) || (perf_pmu__new_caps(&pmu->caps, name, value) < 0)) { -- GitLab From f7a858bffcddaaf70c71b6b656e7cc21b6107cec Mon Sep 17 00:00:00 2001 From: Liam Howlett Date: Fri, 25 Nov 2022 15:50:16 +0000 Subject: [PATCH 2340/5631] tools: Rename __fallthrough to fallthrough MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename the fallthrough attribute to better align with the kernel version. Copy the definition from include/linux/compiler_attributes.h including the #else clause. Adding the #else clause allows the tools compiler.h header to drop the check for a definition entirely and keeps both definitions together. Change any __fallthrough statements to fallthrough anywhere it was used within perf. This allows other tools to use the same key word as the kernel. Committer notes: Did some missing conversions to: builtin-list.c Also included gtk.h before the 'fallthrough' definition in: tools/perf/ui/gtk/hists.c tools/perf/ui/gtk/helpline.c tools/perf/ui/gtk/browser.c As it is the arg name for a macro in glib.h: /var/home/acme/git/perf-tools-next/tools/include/linux/compiler-gcc.h:16:55: error: missing binary operator before token "(" 16 | # define fallthrough __attribute__((__fallthrough__)) | ^ /usr/include/glib-2.0/glib/gmacros.h:637:28: note: in expansion of macro ‘fallthrough’ 637 | #if g_macro__has_attribute(fallthrough) Reviewed-by: Miguel Ojeda Signed-off-by: Liam Howlett Cc: Ingo Molnar Cc: Mark Rutland Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Tom Rix Cc: linux-sparse@vger.kernel.org Cc: llvm@lists.linux.dev Link: https://lore.kernel.org/r/20221125154947.2163498-1-Liam.Howlett@oracle.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/compiler-gcc.h | 6 ++++-- tools/include/linux/compiler.h | 4 ---- tools/perf/builtin-list.c | 4 ++-- tools/perf/builtin-probe.c | 2 +- tools/perf/builtin-stat.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/ui/gtk/browser.c | 2 +- tools/perf/ui/gtk/helpline.c | 2 +- tools/perf/ui/gtk/hists.c | 2 +- tools/perf/util/callchain.c | 4 ++-- tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 6 +++--- tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c | 2 +- tools/perf/util/ordered-events.c | 2 +- tools/perf/util/strfilter.c | 2 +- tools/perf/util/string.c | 2 +- 15 files changed, 21 insertions(+), 23 deletions(-) diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 8816f06fc6c7..62e7c901ac28 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -12,8 +12,10 @@ + __GNUC_PATCHLEVEL__) #endif -#if GCC_VERSION >= 70000 && !defined(__CHECKER__) -# define __fallthrough __attribute__ ((fallthrough)) +#if __has_attribute(__fallthrough__) +# define fallthrough __attribute__((__fallthrough__)) +#else +# define fallthrough do {} while (0) /* fallthrough */ #endif #if __has_attribute(__error__) diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index 90ba44a99199..9d36c8ce1fe7 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -186,10 +186,6 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s }) -#ifndef __fallthrough -# define __fallthrough -#endif - /* Indirect macros required for expanded argument pasting, eg. __LINE__. */ #define ___PASTE(a, b) a##b #define __PASTE(a, b) ___PASTE(a, b) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 76e1d31a68ee..29f09cefed88 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -278,10 +278,10 @@ static void fix_escape_printf(struct strbuf *buf, const char *fmt, ...) strbuf_addstr(buf, "\\n"); break; case '\\': - __fallthrough; + fallthrough; case '\"': strbuf_addch(buf, '\\'); - __fallthrough; + fallthrough; default: strbuf_addch(buf, s[s_pos]); break; diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index e72f6cea76f7..4df05b992093 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -715,7 +715,7 @@ __cmd_probe(int argc, const char **argv) pr_err(" Error: --bootconfig doesn't support uprobes.\n"); return -EINVAL; } - __fallthrough; + fallthrough; case 'a': /* Ensure the last given target is used */ diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 7ef565ae7265..38133afda7fc 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -549,7 +549,7 @@ static void process_evlist(struct evlist *evlist, unsigned int interval) if (evlist__ctlfd_process(evlist, &cmd) > 0) { switch (cmd) { case EVLIST_CTL_CMD_ENABLE: - __fallthrough; + fallthrough; case EVLIST_CTL_CMD_DISABLE: if (interval) process_interval(); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b803af4329d1..3162bad0d17d 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -709,7 +709,7 @@ static void *display_thread(void *arg) case -1: if (errno == EINTR) continue; - __fallthrough; + fallthrough; default: c = getc(stdin); tcsetattr(0, TCSAFLUSH, &save); diff --git a/tools/perf/ui/gtk/browser.c b/tools/perf/ui/gtk/browser.c index 8f3e43d148a8..d2dadf3873fb 100644 --- a/tools/perf/ui/gtk/browser.c +++ b/tools/perf/ui/gtk/browser.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include "gtk.h" #include "../evsel.h" #include "../sort.h" #include "../hist.h" #include "../helpline.h" -#include "gtk.h" #include diff --git a/tools/perf/ui/gtk/helpline.c b/tools/perf/ui/gtk/helpline.c index e40a006aead8..8ea95898a5bd 100644 --- a/tools/perf/ui/gtk/helpline.c +++ b/tools/perf/ui/gtk/helpline.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include "gtk.h" #include #include #include -#include "gtk.h" #include "../ui.h" #include "../helpline.h" diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index c83be2d57f7e..bae21f336ae6 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include "gtk.h" #include "../evlist.h" #include "../callchain.h" #include "../evsel.h" @@ -6,7 +7,6 @@ #include "../hist.h" #include "../helpline.h" #include "../string2.h" -#include "gtk.h" #include #include #include diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 9e9c39dd9d2b..8e7c29836765 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -724,7 +724,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (match != MATCH_ERROR) break; /* otherwise fall-back to symbol-based comparison below */ - __fallthrough; + fallthrough; case CCKEY_FUNCTION: if (node->ms.sym && cnode->ms.sym) { /* @@ -745,7 +745,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, } } /* otherwise fall-back to IP-based comparison below */ - __fallthrough; + fallthrough; case CCKEY_ADDRESS: default: match = match_chain_dso_addresses(cnode->ms.map, cnode->ip, node->ms.map, node->ip); diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 7145c5890de0..b450178e3420 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -3546,7 +3546,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) switch (decoder->packet.type) { case INTEL_PT_TIP_PGD: decoder->continuous_period = false; - __fallthrough; + fallthrough; case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: case INTEL_PT_PTWRITE: @@ -3616,7 +3616,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) decoder->pge = false; decoder->continuous_period = false; intel_pt_clear_tx_flags(decoder); - __fallthrough; + fallthrough; case INTEL_PT_TNT: decoder->have_tma = false; @@ -3980,7 +3980,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) decoder->have_last_ip = false; decoder->last_ip = 0; decoder->ip = 0; - __fallthrough; + fallthrough; case INTEL_PT_STATE_ERR_RESYNC: err = intel_pt_sync_ip(decoder); break; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index 18f97f43e01a..af9710622a1f 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -730,7 +730,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf, case INTEL_PT_FUP: if (!(packet->count)) return snprintf(buf, buf_len, "%s no ip", name); - __fallthrough; + fallthrough; case INTEL_PT_CYC: case INTEL_PT_VMCS: case INTEL_PT_MTC: diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index b887dfeea673..8c62611f10aa 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -284,7 +284,7 @@ static int __ordered_events__flush(struct ordered_events *oe, enum oe_flush how, switch (how) { case OE_FLUSH__FINAL: show_progress = true; - __fallthrough; + fallthrough; case OE_FLUSH__TOP: oe->next_flush = ULLONG_MAX; break; diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c index 78aa4c3b990d..02807b9d4122 100644 --- a/tools/perf/util/strfilter.c +++ b/tools/perf/util/strfilter.c @@ -274,7 +274,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf) len = strfilter_node__sprint_pt(node->l, buf); if (len < 0) return len; - __fallthrough; + fallthrough; case '!': if (buf) { *(buf + len++) = *node->p; diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index 4f12a96f33cc..cf05b0b56c57 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -35,7 +35,7 @@ s64 perf_atoll(const char *str) if (*p) goto out_err; - __fallthrough; + fallthrough; case '\0': return length; default: -- GitLab From d783ea8f62c4e58cea1d04567048368691128d5e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:05 -0700 Subject: [PATCH 2341/5631] perf lock contention: Simplify parse_lock_type() The get_type_flag() should check both str and name fields in the lock_type_table so that it can find the appropriate flag without retrying with ':R' or ':W' suffix from the caller. Also fix a typo in the rt-mutex. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 43 ++++++++------------------------------- 1 file changed, 8 insertions(+), 35 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 32ec58fb80e4..695ce6bd64f7 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1557,7 +1557,7 @@ static const struct { { LCB_F_SPIN | LCB_F_WRITE, "rwlock:W", "rwlock" }, { LCB_F_READ, "rwsem:R", "rwsem" }, { LCB_F_WRITE, "rwsem:W", "rwsem" }, - { LCB_F_RT, "rt=mutex", "rt-mutex" }, + { LCB_F_RT, "rt-mutex", "rt-mutex" }, { LCB_F_RT | LCB_F_READ, "rwlock-rt:R", "rwlock-rt" }, { LCB_F_RT | LCB_F_WRITE, "rwlock-rt:W", "rwlock-rt" }, { LCB_F_PERCPU | LCB_F_READ, "pcpu-sem:R", "percpu-rwsem" }, @@ -1596,6 +1596,10 @@ static unsigned int get_type_flag(const char *str) if (!strcmp(lock_type_table[i].name, str)) return lock_type_table[i].flags; } + for (unsigned int i = 0; i < ARRAY_SIZE(lock_type_table); i++) { + if (!strcmp(lock_type_table[i].str, str)) + return lock_type_table[i].flags; + } return UINT_MAX; } @@ -2121,46 +2125,15 @@ static int parse_lock_type(const struct option *opt __maybe_unused, const char * unsigned int flags = get_type_flag(tok); if (flags == -1U) { - char buf[32]; - - if (strchr(tok, ':')) - continue; - - /* try :R and :W suffixes for rwlock, rwsem, ... */ - scnprintf(buf, sizeof(buf), "%s:R", tok); - flags = get_type_flag(buf); - if (flags != UINT_MAX) { - if (!add_lock_type(flags)) { - ret = -1; - break; - } - } - - scnprintf(buf, sizeof(buf), "%s:W", tok); - flags = get_type_flag(buf); - if (flags != UINT_MAX) { - if (!add_lock_type(flags)) { - ret = -1; - break; - } - } - continue; + pr_err("Unknown lock flags: %s\n", tok); + ret = -1; + break; } if (!add_lock_type(flags)) { ret = -1; break; } - - if (!strcmp(tok, "mutex")) { - flags = get_type_flag("mutex-spin"); - if (flags != UINT_MAX) { - if (!add_lock_type(flags)) { - ret = -1; - break; - } - } - } } free(s); -- GitLab From 84b91920304f5e640ac922cb721f5c70617a83e8 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:06 -0700 Subject: [PATCH 2342/5631] perf lock contention: Use -M for --map-nr-entries Users often want to change the map size, let's add a short option (-M) for that. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-lock.txt | 1 + tools/perf/builtin-lock.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 37aae194a2a1..b5e5d088d51c 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -155,6 +155,7 @@ CONTENTION OPTIONS --tid=:: Record events on existing thread ID (comma separated list). +-M:: --map-nr-entries=:: Maximum number of BPF map entries (default: 10240). diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 695ce6bd64f7..ef56bf90058d 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2294,7 +2294,7 @@ int cmd_lock(int argc, const char **argv) "Trace on existing process id"), OPT_STRING(0, "tid", &target.tid, "tid", "Trace on existing thread id (exclusive to --pid)"), - OPT_CALLBACK(0, "map-nr-entries", &bpf_map_entries, "num", + OPT_CALLBACK('M', "map-nr-entries", &bpf_map_entries, "num", "Max number of BPF map entries", parse_map_entry), OPT_CALLBACK(0, "max-stack", &max_stack_depth, "num", "Set the maximum stack depth when collecting lopck contention, " -- GitLab From 2d8d016527928ad65ad1fe11c9943d8b81f05d18 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:07 -0700 Subject: [PATCH 2343/5631] perf lock contention: Update default map size to 16384 The BPF hash map will align the map size to a power of 2. So 10k would be 16k anyway. Let's have the actual size to avoid confusions. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-lock.txt | 3 ++- tools/perf/builtin-lock.c | 2 +- tools/perf/util/bpf_skel/lock_contention.bpf.c | 5 +---- tools/perf/util/bpf_skel/lock_data.h | 3 +++ 4 files changed, 7 insertions(+), 6 deletions(-) diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index b5e5d088d51c..6e5ba3cd2b72 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -157,7 +157,8 @@ CONTENTION OPTIONS -M:: --map-nr-entries=:: - Maximum number of BPF map entries (default: 10240). + Maximum number of BPF map entries (default: 16384). + This will be aligned to a power of 2. --max-stack=:: Maximum stack depth when collecting lock contention (default: 8). diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ef56bf90058d..9b92c7a5aefb 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -60,7 +60,7 @@ static bool show_thread_stats; static bool show_lock_addrs; static bool show_lock_owner; static bool use_bpf; -static unsigned long bpf_map_entries = 10240; +static unsigned long bpf_map_entries = MAX_ENTRIES; static int max_stack_depth = CONTENTION_STACK_DEPTH; static int stack_skip = CONTENTION_STACK_SKIP; static int print_nr_entries = INT_MAX / 2; diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 3f4ee3992e81..f9d2d792ccc8 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -7,9 +7,6 @@ #include "lock_data.h" -/* default buffer size */ -#define MAX_ENTRIES 10240 - /* for collect_lock_syms(). 4096 was rejected by the verifier */ #define MAX_CPUS 1024 @@ -63,7 +60,7 @@ struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(key_size, sizeof(__u64)); __uint(value_size, sizeof(__u32)); - __uint(max_entries, 16384); + __uint(max_entries, MAX_ENTRIES); } lock_syms SEC(".maps"); struct { diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index 1ba61cb4d480..260062a9f2ab 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -15,6 +15,9 @@ struct contention_task_data { char comm[TASK_COMM_LEN]; }; +/* default buffer size */ +#define MAX_ENTRIES 16384 + /* * Upper bits of the flags in the contention_data are used to identify * some well-known locks which do not have symbols (non-global locks). -- GitLab From 954cdac74e1e7aca518c8ef49d4fa70c8ae72d7b Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:08 -0700 Subject: [PATCH 2344/5631] perf lock contention: Add data failure stat It's possible to fail to update the data when the lock_stat map is full. We should check that case and show the number at the end. $ sudo ./perf lock con -ablv -E3 -- ./perf bench sched messaging ... contended total wait max wait avg wait address symbol 6157 208.48 ms 69.29 us 33.86 us ffff934c001c1f00 (spinlock) 4030 72.04 ms 61.84 us 17.88 us ffff934c000415c0 (spinlock) 3201 50.30 ms 47.73 us 15.71 us ffff934c2eead850 (spinlock) === output for debug === bad: 0, total: 13388 bad rate: 0.00 % histogram of failure reasons task: 0 stack: 0 time: 0 data: 0 <----- added Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 4 +++- tools/perf/util/bpf_lock_contention.c | 1 + tools/perf/util/bpf_skel/lock_contention.bpf.c | 4 +++- tools/perf/util/lock-contention.h | 1 + 4 files changed, 8 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 9b92c7a5aefb..01b318d6c80a 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1626,7 +1626,7 @@ static void sort_contention_result(void) static void print_bpf_events(int total, struct lock_contention_fails *fails) { /* Output for debug, this have to be removed */ - int broken = fails->task + fails->stack + fails->time; + int broken = fails->task + fails->stack + fails->time + fails->data; if (quiet || total == 0 || (broken == 0 && verbose <= 0)) return; @@ -1640,7 +1640,9 @@ static void print_bpf_events(int total, struct lock_contention_fails *fails) pr_info(" %10s: %d\n", "task", fails->task); pr_info(" %10s: %d\n", "stack", fails->stack); pr_info(" %10s: %d\n", "time", fails->time); + pr_info(" %10s: %d\n", "data", fails->data); } + static void print_contention_result(struct lock_contention *con) { struct lock_stat *st; diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 8a5d0eb44189..0071058ac3d2 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -262,6 +262,7 @@ int lock_contention_read(struct lock_contention *con) con->fails.task = skel->bss->task_fail; con->fails.stack = skel->bss->stack_fail; con->fails.time = skel->bss->time_fail; + con->fails.data = skel->bss->data_fail; stack_trace = zalloc(stack_size); if (stack_trace == NULL) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index f9d2d792ccc8..cb87c98e5340 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -124,6 +124,7 @@ int aggr_mode; int task_fail; int stack_fail; int time_fail; +int data_fail; static inline int can_record(u64 *ctx) { @@ -380,7 +381,8 @@ int contention_end(u64 *ctx) if (aggr_mode == LOCK_AGGR_ADDR) first.flags |= check_lock_type(pelem->lock, pelem->flags); - bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); + if (bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST) < 0) + __sync_fetch_and_add(&data_fail, 1); bpf_map_delete_elem(&tstamp, &pid); return 0; } diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index 10c28302420c..3ed1cad370fc 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -126,6 +126,7 @@ struct lock_contention_fails { int task; int stack; int time; + int data; }; struct lock_contention { -- GitLab From aae7e4534adbd96598d06e449d4f05867b0ed23f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:09 -0700 Subject: [PATCH 2345/5631] perf lock contention: Update total/bad stats for hidden entries When -E option is used, it only prints the given number of entries but the event stat at the end should have the numbers for entire entries. Likewise, -S option will hide entries that don't have the named function in the callstack. Also update event stat for them. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 11 +++++++++++ tools/perf/util/bpf_lock_contention.c | 4 +++- tools/perf/util/lock-contention.h | 1 + 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 01b318d6c80a..7742fa255c44 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1726,6 +1726,17 @@ static void print_contention_result(struct lock_contention *con) break; } + if (print_nr_entries) { + /* update the total/bad stats */ + while ((st = pop_from_result())) { + total += use_bpf ? st->nr_contended : 1; + if (st->broken) + bad++; + } + } + /* some entries are collected but hidden by the callstack filter */ + total += con->nr_filtered; + if (use_bpf) print_bpf_events(total, &con->fails); else diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 0071058ac3d2..ea4f697d2a9f 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -299,8 +299,10 @@ int lock_contention_read(struct lock_contention *con) if (con->save_callstack) { bpf_map_lookup_elem(stack, &key.stack_id, stack_trace); - if (!match_callstack_filter(machine, stack_trace)) + if (!match_callstack_filter(machine, stack_trace)) { + con->nr_filtered += data.count; goto next; + } } switch (con->aggr_mode) { diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index 3ed1cad370fc..fa16532c971c 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -141,6 +141,7 @@ struct lock_contention { int stack_skip; int aggr_mode; int owner; + int nr_filtered; bool save_callstack; }; -- GitLab From 0fba226548501099616b7f1cc73c853ffd560511 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:10 -0700 Subject: [PATCH 2346/5631] perf lock contention: Revise needs_callstack() condition It needs callstacks for two reasons: * for stack aggregation mode, the map key is the stack id and it can also show the full stack traces when -v is used * for other aggregation modes, the stack filter can be used to limit lock contentions from known call paths The -v option is meaningful (in terms of stack trace) only for stack aggregation mode, so it should not set the save_callstack for other mode like with -t or -l options. I've noticed this with the following command line: $ sudo ./perf lock con -ablv -E 3 -M 16 -- ./perf bench sched messaging ... contended total wait max wait avg wait address symbol 88 4.59 ms 108.07 us 52.13 us ffff935757f46ec0 (spinlock) 33 905.22 us 73.67 us 27.43 us ffff935757f41700 (spinlock) 28 703.69 us 79.28 us 25.13 us ffff938a3d9b0c80 rq_lock (spinlock) === output for debug === bad: 12272, total: 12421 bad rate: 98.80 % histogram of failure reasons task: 8285 stack: 3987 <---------- here time: 0 data: 0 It should not have any failure on stacks since it doesn't use it. No functional change intended. Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-lock.c | 2 +- tools/perf/util/bpf_lock_contention.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 7742fa255c44..4e24351b18bd 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -77,7 +77,7 @@ static enum lock_aggr_mode aggr_mode = LOCK_AGGR_ADDR; static bool needs_callstack(void) { - return verbose > 0 || !list_empty(&callstack_filters); + return !list_empty(&callstack_filters); } static struct thread_stat *thread_stat_find(u32 tid) diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index ea4f697d2a9f..9e20fa8ade09 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -346,7 +346,7 @@ int lock_contention_read(struct lock_contention *con) if (data.count) st->avg_wait_time = data.total_time / data.count; - if (con->save_callstack) { + if (con->aggr_mode == LOCK_AGGR_CALLER && verbose > 0) { st->callstack = memdup(stack_trace, stack_size); if (st->callstack == NULL) break; -- GitLab From 222de5e53926252bf8815751ba555778cf8ff6ca Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 6 Apr 2023 14:06:11 -0700 Subject: [PATCH 2347/5631] perf lock contention: Do not try to update if hash map is full It doesn't delete data in the task_data and lock_stat maps. The data is kept there until it's consumed by userspace at the end. But it calls bpf_map_update_elem() again and again, and the data will be discarded if the map is full. This is not good. Worse, in the bpf_map_update_elem(), it keeps trying to get a new node even if the map was full. I guess it makes sense if it deletes some node like in the tstamp map (that's why I didn't make the change there). In a pre-allocated hash map, that means it'd iterate all CPU to check the freelist. And it has a bad performance impact on large machines. I've checked it on my 64 CPU machine with this. $ perf bench sched messaging -g 1000 # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 1000 groups == 40000 processes run Total time: 2.825 [sec] And I used the task mode, so that it can guarantee the map is full. The default map entry size is 16K and this workload has 40K tasks. Before: $ sudo ./perf lock con -abt -E3 -- perf bench sched messaging -g 1000 # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 1000 groups == 40000 processes run Total time: 11.299 [sec] contended total wait max wait avg wait pid comm 19284 3.51 s 3.70 ms 181.91 us 1305863 sched-messaging 243 84.09 ms 466.67 us 346.04 us 1336608 sched-messaging 177 66.35 ms 12.08 ms 374.88 us 1220416 node For some reason, it didn't report the data failures. But you can see the total time in the workload is increased a lot (2.8 -> 11.3). If it fails early when the map is full, it goes back to normal. After: $ sudo ./perf lock con -abt -E3 -- perf bench sched messaging -g 1000 # Running 'sched/messaging' benchmark: # 20 sender and receiver processes per group # 1000 groups == 40000 processes run Total time: 3.044 [sec] contended total wait max wait avg wait pid comm 18743 591.92 ms 442.96 us 31.58 us 1431454 sched-messaging 51 210.64 ms 207.45 ms 4.13 ms 1468724 sched-messaging 81 68.61 ms 65.79 ms 847.07 us 1463183 sched-messaging === output for debug === bad: 1164137, total: 2253341 bad rate: 51.66 % histogram of failure reasons task: 0 stack: 0 time: 0 data: 1164137 Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Hao Luo Cc: Ingo Molnar Cc: Jiri Olsa Cc: Juri Lelli Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230406210611.1622492-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- .../perf/util/bpf_skel/lock_contention.bpf.c | 22 ++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index cb87c98e5340..23f6e63544ed 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "lock_data.h" @@ -126,6 +127,9 @@ int stack_fail; int time_fail; int data_fail; +int task_map_full; +int data_map_full; + static inline int can_record(u64 *ctx) { if (has_cpu) { @@ -177,11 +181,12 @@ static inline int update_task_data(struct task_struct *task) return -1; p = bpf_map_lookup_elem(&task_data, &pid); - if (p == NULL) { + if (p == NULL && !task_map_full) { struct contention_task_data data = {}; BPF_CORE_READ_STR_INTO(&data.comm, task, comm); - bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST); + if (bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST) == -E2BIG) + task_map_full = 1; } return 0; @@ -370,6 +375,12 @@ int contention_end(u64 *ctx) data = bpf_map_lookup_elem(&lock_stat, &key); if (!data) { + if (data_map_full) { + bpf_map_delete_elem(&tstamp, &pid); + __sync_fetch_and_add(&data_fail, 1); + return 0; + } + struct contention_data first = { .total_time = duration, .max_time = duration, @@ -377,12 +388,17 @@ int contention_end(u64 *ctx) .count = 1, .flags = pelem->flags, }; + int err; if (aggr_mode == LOCK_AGGR_ADDR) first.flags |= check_lock_type(pelem->lock, pelem->flags); - if (bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST) < 0) + err = bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST); + if (err < 0) { + if (err == -E2BIG) + data_map_full = 1; __sync_fetch_and_add(&data_fail, 1); + } bpf_map_delete_elem(&tstamp, &pid); return 0; } -- GitLab From 330f40a0d951d7f23995ccbfeea9be7282942e93 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 16:52:54 -0700 Subject: [PATCH 2348/5631] perf pmu: Fewer const casts struct pmu_event has const char*s, only unit needs to be non-const for the sake of passing as an out argument to strtod(). Reduce the const casts from 4 down to 1. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Link: https://lore.kernel.org/r/20230406235256.2768773-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 9eedbfc9e863..d033343f75f9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -352,16 +352,16 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, struct perf_pmu_alias *alias; int ret; char newval[256]; - char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL; + const char *long_desc = NULL, *topic = NULL, *unit = NULL, *pmu_name = NULL; bool deprecated = false, perpkg = false; if (pe) { - long_desc = (char *)pe->long_desc; - topic = (char *)pe->topic; - unit = (char *)pe->unit; + long_desc = pe->long_desc; + topic = pe->topic; + unit = pe->unit; perpkg = pe->perpkg; deprecated = pe->deprecated; - pmu_name = (char *)pe->pmu; + pmu_name = pe->pmu; } alias = malloc(sizeof(*alias)); @@ -419,7 +419,7 @@ static int __perf_pmu__new_alias(struct list_head *list, int dirfd, char *name, desc ? strdup(desc) : NULL; alias->topic = topic ? strdup(topic) : NULL; if (unit) { - if (perf_pmu__convert_scale(unit, &unit, &alias->scale) < 0) + if (perf_pmu__convert_scale(unit, (char **)&unit, &alias->scale) < 0) return -1; snprintf(alias->unit, sizeof(alias->unit), "%s", unit); } -- GitLab From 240e6fd0a923933493192e71f191d9326ba53f0b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 16:52:55 -0700 Subject: [PATCH 2349/5631] perf pmu: Improve name/comments, avoid a memory allocation Improve documentation around perf_pmu_alias pmu_name and on functions. Reduce the scope of pmu_uncore_alias_match to just file. Rename perf_pmu__valid_suffix to the more revealing perf_pmu__match_ignoring_suffix. Add a short-cut to perf_pmu__match_ignoring_suffix for PMU names that don't also have a socket value, and can therefore avoid a memory allocation. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Link: https://lore.kernel.org/r/20230406235256.2768773-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 27 ++++++++++++++++++++------- tools/perf/util/pmu.h | 8 +++++--- 2 files changed, 25 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d033343f75f9..2e4f60b49959 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -686,11 +686,14 @@ __weak const struct pmu_metrics_table *pmu_metrics_table__find(void) return perf_pmu__find_metrics_table(NULL); } -/* - * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name - * to be valid. +/** + * perf_pmu__match_ignoring_suffix - Does the pmu_name match tok ignoring any + * trailing suffix? The Suffix must be in form + * tok_{digits}, or tok{digits}. + * @pmu_name: The pmu_name with possible suffix. + * @tok: The possible match to pmu_name without suffix. */ -static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok) +static bool perf_pmu__match_ignoring_suffix(const char *pmu_name, const char *tok) { const char *p; @@ -715,11 +718,21 @@ static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok) return true; } -bool pmu_uncore_alias_match(const char *pmu_name, const char *name) +/** + * pmu_uncore_alias_match - does name match the PMU name? + * @pmu_name: the json struct pmu_event name. This may lack a suffix (which + * matches) or be of the form "socket,pmuname" which will match + * "socketX_pmunameY". + * @name: a real full PMU name as from sysfs. + */ +static bool pmu_uncore_alias_match(const char *pmu_name, const char *name) { char *tmp = NULL, *tok, *str; bool res; + if (strchr(pmu_name, ',') == NULL) + return perf_pmu__match_ignoring_suffix(name, pmu_name); + str = strdup(pmu_name); if (!str) return false; @@ -746,7 +759,7 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name) name = strstr(name, tok); if (!name || - (!next_tok && !perf_pmu__valid_suffix(name, tok))) { + (!next_tok && !perf_pmu__match_ignoring_suffix(name, tok))) { res = false; goto out; } @@ -1961,7 +1974,7 @@ int perf_pmu__match(char *pattern, char *name, char *tok) if (fnmatch(pattern, name, 0)) return -1; - if (tok && !perf_pmu__valid_suffix(name, tok)) + if (tok && !perf_pmu__match_ignoring_suffix(name, tok)) return -1; return 0; diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index d53618c65c92..b9a02dedd473 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -35,7 +35,7 @@ struct perf_pmu_caps { }; /** - * struct perf_pmu - hi + * struct perf_pmu */ struct perf_pmu { /** @name: The name of the PMU such as "cpu". */ @@ -186,7 +186,10 @@ struct perf_pmu_alias { * default. */ bool deprecated; - /** @pmu_name: The name copied from struct perf_pmu. */ + /** + * @pmu_name: The name copied from the json struct pmu_event. This can + * differ from the PMU name as it won't have suffixes. + */ char *pmu_name; }; @@ -238,7 +241,6 @@ void pmu_add_cpu_aliases_table(struct list_head *head, struct perf_pmu *pmu, char *perf_pmu__getcpuid(struct perf_pmu *pmu); const struct pmu_events_table *pmu_events_table__find(void); const struct pmu_metrics_table *pmu_metrics_table__find(void); -bool pmu_uncore_alias_match(const char *pmu_name, const char *name); void perf_pmu_free_alias(struct perf_pmu_alias *alias); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); -- GitLab From 3f980eab56d1c4226bcb91a5f21c9c32a56edb5a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 16:52:56 -0700 Subject: [PATCH 2350/5631] perf pmu: Sort and remove duplicates using JSON PMU name We may have a lot of copies of a particular uncore PMU, such as uncore_cha_0 to uncore_cha_59 on Intel sapphirerapids. The JSON events may match each of PMUs and so the events are copied to it. In 'perf list' this means we see the same JSON event 60 times as events on different PMUs don't have duplicates removed. There are 284 uncore_cha events on sapphirerapids. Rather than use the PMU's name to sort and remove duplicates, use the JSON PMU name. This reduces the 60 copies back down to 1 and has the side effect of speeding things like the "perf all PMU test" shell test. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Link: https://lore.kernel.org/r/20230406235256.2768773-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 47 ++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 16 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 2e4f60b49959..91cccfb3c515 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1574,7 +1574,7 @@ static int cmp_sevent(const void *a, const void *b) { const struct sevent *as = a; const struct sevent *bs = b; - const char *a_pmu_name, *b_pmu_name; + const char *a_pmu_name = NULL, *b_pmu_name = NULL; const char *a_name = "//", *a_desc = NULL, *a_topic = ""; const char *b_name = "//", *b_desc = NULL, *b_topic = ""; int ret; @@ -1583,11 +1583,13 @@ static int cmp_sevent(const void *a, const void *b) a_name = as->event->name; a_desc = as->event->desc; a_topic = as->event->topic ?: ""; + a_pmu_name = as->event->pmu_name; } if (bs->event) { b_name = bs->event->name; b_desc = bs->event->desc; b_topic = bs->event->topic ?: ""; + b_pmu_name = bs->event->pmu_name; } /* Put extra events last. */ if (!!a_desc != !!b_desc) @@ -1603,11 +1605,13 @@ static int cmp_sevent(const void *a, const void *b) return as->is_cpu ? -1 : 1; /* Order by PMU name. */ - a_pmu_name = as->pmu->name ?: ""; - b_pmu_name = bs->pmu->name ?: ""; - ret = strcmp(a_pmu_name, b_pmu_name); - if (ret) - return ret; + if (as->pmu != bs->pmu) { + a_pmu_name = a_pmu_name ?: (as->pmu->name ?: ""); + b_pmu_name = b_pmu_name ?: (bs->pmu->name ?: ""); + ret = strcmp(a_pmu_name, b_pmu_name); + if (ret) + return ret; + } /* Order by event name. */ return strcmp(a_name, b_name); @@ -1621,17 +1625,26 @@ bool is_pmu_core(const char *name) static bool pmu_alias_is_duplicate(struct sevent *alias_a, struct sevent *alias_b) { - const char *a_pmu_name, *b_pmu_name; - const char *a_name = alias_a->event ? alias_a->event->name : "//"; - const char *b_name = alias_b->event ? alias_b->event->name : "//"; + const char *a_pmu_name = NULL, *b_pmu_name = NULL; + const char *a_name = "//", *b_name = "//"; + + + if (alias_a->event) { + a_name = alias_a->event->name; + a_pmu_name = alias_a->event->pmu_name; + } + if (alias_b->event) { + b_name = alias_b->event->name; + b_pmu_name = alias_b->event->pmu_name; + } /* Different names -> never duplicates */ if (strcmp(a_name, b_name)) return false; /* Don't remove duplicates for different PMUs */ - a_pmu_name = alias_a->pmu->name ?: ""; - b_pmu_name = alias_b->pmu->name ?: ""; + a_pmu_name = a_pmu_name ?: (alias_a->pmu->name ?: ""); + b_pmu_name = b_pmu_name ?: (alias_b->pmu->name ?: ""); return strcmp(a_pmu_name, b_pmu_name) == 0; } @@ -1680,7 +1693,8 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) for (j = 0; j < len; j++) { const char *name, *alias = NULL, *scale_unit = NULL, *desc = NULL, *long_desc = NULL, - *encoding_desc = NULL, *topic = NULL; + *encoding_desc = NULL, *topic = NULL, + *pmu_name = NULL; bool deprecated = false; size_t buf_used; @@ -1690,7 +1704,8 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) if (!aliases[j].event) { /* A selectable event. */ - buf_used = snprintf(buf, sizeof(buf), "%s//", aliases[j].pmu->name) + 1; + pmu_name = aliases[j].pmu->name; + buf_used = snprintf(buf, sizeof(buf), "%s//", pmu_name) + 1; name = buf; } else { if (aliases[j].event->desc) { @@ -1705,6 +1720,7 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) } buf_used = strlen(buf) + 1; } + pmu_name = aliases[j].event->pmu_name ?: (aliases[j].pmu->name ?: ""); if (strlen(aliases[j].event->unit) || aliases[j].event->scale != 1.0) { scale_unit = buf + buf_used; buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, @@ -1716,12 +1732,11 @@ void print_pmu_events(const struct print_callbacks *print_cb, void *print_state) topic = aliases[j].event->topic; encoding_desc = buf + buf_used; buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, - "%s/%s/", aliases[j].pmu->name, - aliases[j].event->str) + 1; + "%s/%s/", pmu_name, aliases[j].event->str) + 1; deprecated = aliases[j].event->deprecated; } print_cb->print_event(print_state, - aliases[j].pmu->name, + pmu_name, topic, name, alias, -- GitLab From 2e4555b015de6b1429f70263633c622c06c5c6eb Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 17:13:18 -0700 Subject: [PATCH 2351/5631] perf vendor events intel: Update free running alderlake events Fix the PMU name, event code and umask. These updates were generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py with this PR: https://github.com/intel/perfmon/pull/66 Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230407001322.2776268-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlake/uncore-memory.json | 16 ++++++++++++---- .../arch/x86/alderlaken/uncore-memory.json | 16 ++++++++++++---- 2 files changed, 24 insertions(+), 8 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-memory.json index 2ccd9cf96957..163d7e7755c4 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-memory.json @@ -1,29 +1,37 @@ [ { "BriefDescription": "Counts every 64B read request entering the Memory Controller 0 to DRAM (sum of all channels).", + "EventCode": "0xff", "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", "PerPkg": "1", "PublicDescription": "Counts every 64B read request entering the Memory Controller 0 to DRAM (sum of all channels).", - "Unit": "iMC" + "UMask": "0x20", + "Unit": "imc_free_running_0" }, { "BriefDescription": "Counts every 64B write request entering the Memory Controller 0 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", "PerPkg": "1", - "Unit": "iMC" + "UMask": "0x30", + "Unit": "imc_free_running_0" }, { "BriefDescription": "Counts every 64B read request entering the Memory Controller 1 to DRAM (sum of all channels).", + "EventCode": "0xff", "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", "PerPkg": "1", "PublicDescription": "Counts every 64B read entering the Memory Controller 1 to DRAM (sum of all channels).", - "Unit": "iMC" + "UMask": "0x20", + "Unit": "imc_free_running_1" }, { "BriefDescription": "Counts every 64B write request entering the Memory Controller 1 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", "PerPkg": "1", - "Unit": "iMC" + "UMask": "0x30", + "Unit": "imc_free_running_1" }, { "BriefDescription": "ACT command for a read request sent to DRAM", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-memory.json index 2ccd9cf96957..163d7e7755c4 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-memory.json @@ -1,29 +1,37 @@ [ { "BriefDescription": "Counts every 64B read request entering the Memory Controller 0 to DRAM (sum of all channels).", + "EventCode": "0xff", "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", "PerPkg": "1", "PublicDescription": "Counts every 64B read request entering the Memory Controller 0 to DRAM (sum of all channels).", - "Unit": "iMC" + "UMask": "0x20", + "Unit": "imc_free_running_0" }, { "BriefDescription": "Counts every 64B write request entering the Memory Controller 0 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", "PerPkg": "1", - "Unit": "iMC" + "UMask": "0x30", + "Unit": "imc_free_running_0" }, { "BriefDescription": "Counts every 64B read request entering the Memory Controller 1 to DRAM (sum of all channels).", + "EventCode": "0xff", "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", "PerPkg": "1", "PublicDescription": "Counts every 64B read entering the Memory Controller 1 to DRAM (sum of all channels).", - "Unit": "iMC" + "UMask": "0x20", + "Unit": "imc_free_running_1" }, { "BriefDescription": "Counts every 64B write request entering the Memory Controller 1 to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", "PerPkg": "1", - "Unit": "iMC" + "UMask": "0x30", + "Unit": "imc_free_running_1" }, { "BriefDescription": "ACT command for a read request sent to DRAM", -- GitLab From 5a45940b56fe0c67674ffa964b85f44b4fbb4e38 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 17:13:19 -0700 Subject: [PATCH 2352/5631] perf vendor events intel: Update free running icelakex events Fix the PMU names, event code and umask. Remove UNC_IIO_BANDWIDTH_OUT events that aren't supported. These updates were generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py with this PR: https://github.com/intel/perfmon/pull/66 Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230407001322.2776268-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/icelakex/uncore-memory.json | 4 +- .../arch/x86/icelakex/uncore-other.json | 84 ++++++------------- 2 files changed, 30 insertions(+), 58 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json index 66bb4538c6f2..814d9599474d 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-memory.json @@ -106,9 +106,11 @@ }, { "BriefDescription": "Free running counter that increments for the Memory Controller", + "EventCode": "0xff", "EventName": "UNC_M_CLOCKTICKS_FREERUN", "PerPkg": "1", - "Unit": "iMC" + "UMask": "0x10", + "Unit": "imc_free_running" }, { "BriefDescription": "DRAM Precharge All Commands", diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json index b1d29877c141..8210e286eec1 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json @@ -9859,99 +9859,67 @@ }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x20", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x21", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x22", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x23", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x24", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x25", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x26", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART0_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART1_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART2_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART3_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART4_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART5_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART6_FREERUN", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART7_FREERUN", - "PerPkg": "1", - "Unit": "IIO" + "UMask": "0x27", + "Unit": "iio_free_running" }, { "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", @@ -9963,10 +9931,12 @@ }, { "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", "PerPkg": "1", "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", - "Unit": "IIO" + "UMask": "0x10", + "Unit": "iio_free_running" }, { "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", -- GitLab From 54bc363afa5bbc97d9ce3423ec54ac907a95c669 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 17:13:20 -0700 Subject: [PATCH 2353/5631] perf vendor events intel: Correct knightslanding memory topic Correct the memory topic of events for the imc related PMUs. These updates were generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py with this PR: https://github.com/intel/perfmon/pull/66 Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230407001322.2776268-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../x86/knightslanding/uncore-memory.json | 38 +++++++++++++++++++ .../arch/x86/knightslanding/uncore-other.json | 36 ------------------ 2 files changed, 38 insertions(+), 36 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json new file mode 100644 index 000000000000..47da947b1a6e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json @@ -0,0 +1,38 @@ +[ + { + "BriefDescription": "CAS All", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC_DCLK" + }, + { + "BriefDescription": "CAS Reads", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC_DCLK" + }, + { + "BriefDescription": "CAS Writes", + "EventCode": "0x03", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC_DCLK" + }, + { + "BriefDescription": "DCLK count", + "EventName": "UNC_M_D_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC_DCLK" + }, + { + "BriefDescription": "UCLK count", + "EventName": "UNC_M_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "iMC_UCLK" + } +] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json index 491cb37ddab0..fc85e0c95318 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json @@ -3621,41 +3621,5 @@ "PerPkg": "1", "UMask": "0x4", "Unit": "M2PCIe" - }, - { - "BriefDescription": "CAS All", - "EventCode": "0x03", - "EventName": "UNC_M_CAS_COUNT.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "iMC_DCLK" - }, - { - "BriefDescription": "CAS Reads", - "EventCode": "0x03", - "EventName": "UNC_M_CAS_COUNT.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "iMC_DCLK" - }, - { - "BriefDescription": "CAS Writes", - "EventCode": "0x03", - "EventName": "UNC_M_CAS_COUNT.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "iMC_DCLK" - }, - { - "BriefDescription": "DCLK count", - "EventName": "UNC_M_D_CLOCKTICKS", - "PerPkg": "1", - "Unit": "iMC_DCLK" - }, - { - "BriefDescription": "UCLK count", - "EventName": "UNC_M_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "iMC_UCLK" } ] -- GitLab From 4781f1f270fea983a6579ddad5e8dc8ad33f1fed Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 17:13:21 -0700 Subject: [PATCH 2354/5631] perf vendor events intel: Update free running snowridgex events Fix the PMU names, event code and umask. Remove UNC_IIO_BANDWIDTH_OUT events that aren't supported. These updates were generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py with this PR: https://github.com/intel/perfmon/pull/66 Signed-off-by: Ian Rogers : Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230407001322.2776268-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/snowridgex/uncore-memory.json | 4 +- .../arch/x86/snowridgex/uncore-other.json | 92 ++++++------------- 2 files changed, 30 insertions(+), 66 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json index 7dc0910694ed..530e9b71b92a 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-memory.json @@ -127,10 +127,12 @@ }, { "BriefDescription": "Free running counter that increments for the Memory Controller", + "EventCode": "0xff", "EventName": "UNC_M_CLOCKTICKS_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_M_CLOCKTICKS_FREERUN", - "Unit": "iMC" + "UMask": "0x10", + "Unit": "imc_free_running" }, { "BriefDescription": "DRAM Precharge All Commands", diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json index 3b35e08e24d6..8bd041bc0c57 100644 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json @@ -7129,115 +7129,75 @@ }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", - "Unit": "IIO" + "UMask": "0x20", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", - "Unit": "IIO" + "UMask": "0x21", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", - "Unit": "IIO" + "UMask": "0x22", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", - "Unit": "IIO" + "UMask": "0x23", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", - "Unit": "IIO" + "UMask": "0x24", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", - "Unit": "IIO" + "UMask": "0x25", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", - "Unit": "IIO" + "UMask": "0x26", + "Unit": "iio_free_running" }, { "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", "PerPkg": "1", "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART0_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART0_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART1_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART1_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART2_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART2_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART3_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART3_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART4_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART4_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART5_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART5_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART6_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART6_FREERUN", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventName": "UNC_IIO_BANDWIDTH_OUT.PART7_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_OUT.PART7_FREERUN", - "Unit": "IIO" + "UMask": "0x27", + "Unit": "iio_free_running" }, { "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", @@ -7248,10 +7208,12 @@ }, { "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", "PerPkg": "1", "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", - "Unit": "IIO" + "UMask": "0x10", + "Unit": "iio_free_running" }, { "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", -- GitLab From 5a4f5be9c91ab79762747f39c14ad43d27a389dc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 6 Apr 2023 17:13:22 -0700 Subject: [PATCH 2355/5631] perf vendor events intel: Update free running tigerlake events Fix the topic, PMU name, event code and umask. These updates were generated by: https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py with this PR: https://github.com/intel/perfmon/pull/66 Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230407001322.2776268-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/tigerlake/uncore-memory.json | 50 +++++++++++++++++++ .../arch/x86/tigerlake/uncore-other.json | 36 ------------- 2 files changed, 50 insertions(+), 36 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json new file mode 100644 index 000000000000..99fb5259fd25 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-memory.json @@ -0,0 +1,50 @@ +[ + { + "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "imc_free_running_0" + }, + { + "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "imc_free_running_1" + }, + { + "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", + "EventCode": "0xff", + "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "imc_free_running_1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json index a5a254327ae9..6e43aaf64e28 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json @@ -93,41 +93,5 @@ "EventName": "UNC_CLOCK.SOCKET", "PerPkg": "1", "Unit": "CLOCK" - }, - { - "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", - "EventName": "UNC_MC0_RDCAS_COUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" - }, - { - "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", - "EventName": "UNC_MC0_TOTAL_REQCOUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" - }, - { - "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", - "EventName": "UNC_MC0_WRCAS_COUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" - }, - { - "BriefDescription": "Counts every read (RdCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", - "EventName": "UNC_MC1_RDCAS_COUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" - }, - { - "BriefDescription": "Counts every 64B read and write request entering the Memory Controller to DRAM (sum of all channels). Each write request counts as a new request incrementing this counter. However, same cache line write requests (both full and partial) are combined to a single 64 byte data transfer to DRAM.", - "EventName": "UNC_MC1_TOTAL_REQCOUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" - }, - { - "BriefDescription": "Counts every write (WrCAS) issued by the Memory Controller to DRAM (sum of all channels). All requests result in 64 byte data transfers from DRAM.", - "EventName": "UNC_MC1_WRCAS_COUNT_FREERUN", - "PerPkg": "1", - "Unit": "imc" } ] -- GitLab From 0e6aa013bbc545f3ac04ba79c884466e47136d5d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:43 -0700 Subject: [PATCH 2356/5631] perf map: Rename map_ip() and unmap_ip() Add dso to match comment. This avoids a naming conflict with later added accessor functions for variables in struct map. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-kmem.c | 2 +- tools/perf/builtin-script.c | 4 ++-- tools/perf/util/machine.c | 4 ++-- tools/perf/util/map.c | 8 ++++---- tools/perf/util/map.h | 4 ++-- tools/perf/util/symbol-elf.c | 4 ++-- 6 files changed, 13 insertions(+), 13 deletions(-) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index f3029742b800..4d4b770a401c 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -423,7 +423,7 @@ static u64 find_callsite(struct evsel *evsel, struct perf_sample *sample) if (!caller) { /* found */ if (node->ms.map) - addr = map__unmap_ip(node->ms.map, node->ip); + addr = map__dso_unmap_ip(node->ms.map, node->ip); else addr = node->ip; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 1d078106abc4..af0a69c7f41f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1012,11 +1012,11 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, if (thread__find_map_fb(thread, sample->cpumode, from, &alf) && !map__dso(alf.map)->adjust_symbols) - from = map__map_ip(alf.map, from); + from = map__dso_map_ip(alf.map, from); if (thread__find_map_fb(thread, sample->cpumode, to, &alt) && !map__dso(alt.map)->adjust_symbols) - to = map__map_ip(alt.map, to); + to = map__dso_map_ip(alt.map, to); printed += fprintf(fp, " 0x%"PRIx64, from); if (PRINT_FIELD(DSO)) { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7852b97da10a..9d24980a0a93 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -3058,7 +3058,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms if (!symbol_conf.inline_name || !map || !sym) return ret; - addr = map__map_ip(map, ip); + addr = map__dso_map_ip(map, ip); addr = map__rip_2objdump(map, addr); dso = map__dso(map); @@ -3103,7 +3103,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) * its corresponding binary. */ if (entry->ms.map) - addr = map__map_ip(entry->ms.map, entry->ip); + addr = map__dso_map_ip(entry->ms.map, entry->ip); srcline = callchain_srcline(&entry->ms, addr); return callchain_cursor_append(cursor, entry->ip, &entry->ms, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 416fc449bde8..d97a6d20626f 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -109,8 +109,8 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map->pgoff = pgoff; map->reloc = 0; map->dso = dso__get(dso); - map->map_ip = map__map_ip; - map->unmap_ip = map__unmap_ip; + map->map_ip = map__dso_map_ip; + map->unmap_ip = map__dso_unmap_ip; map->erange_warned = false; refcount_set(&map->refcnt, 1); } @@ -590,12 +590,12 @@ struct maps *map__kmaps(struct map *map) return kmap->kmaps; } -u64 map__map_ip(const struct map *map, u64 ip) +u64 map__dso_map_ip(const struct map *map, u64 ip) { return ip - map__start(map) + map->pgoff; } -u64 map__unmap_ip(const struct map *map, u64 ip) +u64 map__dso_unmap_ip(const struct map *map, u64 ip) { return ip + map__start(map) - map->pgoff; } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 16646b94fa3a..9b0a84e46e48 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -41,9 +41,9 @@ struct kmap *map__kmap(struct map *map); struct maps *map__kmaps(struct map *map); /* ip -> dso rip */ -u64 map__map_ip(const struct map *map, u64 ip); +u64 map__dso_map_ip(const struct map *map, u64 ip); /* dso rip -> ip */ -u64 map__unmap_ip(const struct map *map, u64 ip); +u64 map__dso_unmap_ip(const struct map *map, u64 ip); /* Returns ip */ u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index e715869eab8a..c55981116f68 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1357,8 +1357,8 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map->start = shdr->sh_addr + ref_reloc(kmap); map->end = map__start(map) + shdr->sh_size; map->pgoff = shdr->sh_offset; - map->map_ip = map__map_ip; - map->unmap_ip = map__unmap_ip; + map->map_ip = map__dso_map_ip; + map->unmap_ip = map__dso_unmap_ip; /* Ensure maps are correctly ordered */ if (kmaps) { int err; -- GitLab From 78a1f7cd9000d5d633268a2acb2d9b62d41a2f2c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:44 -0700 Subject: [PATCH 2357/5631] perf map: Add helper for ->map_ip() and ->unmap_ip() Later changes will add reference count checking for struct map, add a helper function to invoke the map_ip and unmap_ip function pointers. The helper allows the reference count check to be in fewer places. Committer notes: Add missing conversions to: tools/perf/util/map.c tools/perf/util/cs-etm.c tools/perf/util/annotate.c tools/perf/arch/powerpc/util/sym-handling.c tools/perf/arch/s390/annotate/instructions.c Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/powerpc/util/sym-handling.c | 2 +- tools/perf/arch/s390/annotate/instructions.c | 2 +- tools/perf/builtin-kallsyms.c | 2 +- tools/perf/builtin-kmem.c | 2 +- tools/perf/builtin-lock.c | 4 ++-- tools/perf/builtin-script.c | 2 +- tools/perf/tests/vmlinux-kallsyms.c | 10 +++++----- tools/perf/util/annotate.c | 14 +++++++------- tools/perf/util/bpf_lock_contention.c | 4 ++-- tools/perf/util/cs-etm.c | 2 +- tools/perf/util/dlfilter.c | 2 +- tools/perf/util/dso.c | 6 ++++-- tools/perf/util/event.c | 8 ++++---- tools/perf/util/evsel_fprintf.c | 2 +- tools/perf/util/intel-pt.c | 10 +++++----- tools/perf/util/machine.c | 16 ++++++++-------- tools/perf/util/map.c | 12 ++++++------ tools/perf/util/map.h | 10 ++++++++++ tools/perf/util/maps.c | 8 ++++---- tools/perf/util/probe-event.c | 8 ++++---- .../util/scripting-engines/trace-event-python.c | 2 +- tools/perf/util/sort.c | 12 ++++++------ tools/perf/util/symbol.c | 4 ++-- tools/perf/util/thread.c | 2 +- tools/perf/util/unwind-libdw.c | 2 +- tools/perf/util/unwind-libunwind-local.c | 2 +- 26 files changed, 81 insertions(+), 69 deletions(-) diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 9f99fc88dbff..947bfad7aa59 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -131,7 +131,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev, for (i = 0; i < ntevs; i++) { tev = &pev->tevs[i]; map__for_each_symbol(map, sym, tmp) { - if (map->unmap_ip(map, sym->start) == tev->point.address) { + if (map__unmap_ip(map, sym->start) == tev->point.address) { arch__fix_tev_from_maps(pev, tev, map, sym); break; } diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c index 0e136630659e..de925b0e35ce 100644 --- a/tools/perf/arch/s390/annotate/instructions.c +++ b/tools/perf/arch/s390/annotate/instructions.c @@ -39,7 +39,7 @@ static int s390_call__parse(struct arch *arch, struct ins_operands *ops, target.addr = map__objdump_2mem(map, ops->target.addr); if (maps__find_ams(ms->maps, &target) == 0 && - map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; return 0; diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c index 5638ca4dbd8e..3751df744577 100644 --- a/tools/perf/builtin-kallsyms.c +++ b/tools/perf/builtin-kallsyms.c @@ -39,7 +39,7 @@ static int __cmd_kallsyms(int argc, const char **argv) dso = map__dso(map); printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n", symbol->name, dso->short_name, dso->long_name, - map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end), + map__unmap_ip(map, symbol->start), map__unmap_ip(map, symbol->end), symbol->start, symbol->end); } diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 4d4b770a401c..fcd2ef3bd3f5 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1024,7 +1024,7 @@ static void __print_slab_result(struct rb_root *root, if (sym != NULL) snprintf(buf, sizeof(buf), "%s+%" PRIx64 "", sym->name, - addr - map->unmap_ip(map, sym->start)); + addr - map__unmap_ip(map, sym->start)); else snprintf(buf, sizeof(buf), "%#" PRIx64 "", addr); printf(" %-34s |", buf); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 4e24351b18bd..ecb1fac8ba3c 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -900,7 +900,7 @@ static int get_symbol_name_offset(struct map *map, struct symbol *sym, u64 ip, return 0; } - offset = map->map_ip(map, ip) - sym->start; + offset = map__map_ip(map, ip) - sym->start; if (offset) return scnprintf(buf, size, "%s+%#lx", sym->name, offset); @@ -1070,7 +1070,7 @@ static int report_lock_contention_begin_event(struct evsel *evsel, return -ENOMEM; } - addrs[filters.nr_addrs++] = kmap->unmap_ip(kmap, sym->start); + addrs[filters.nr_addrs++] = map__unmap_ip(kmap, sym->start); filters.addrs = addrs; } } diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index af0a69c7f41f..8fba247b798c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1088,7 +1088,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, /* Load maps to ensure dso->is_64_bit has been updated */ map__load(al.map); - offset = al.map->map_ip(al.map, start); + offset = map__map_ip(al.map, start); len = dso__data_read_offset(dso, machine, offset, (u8 *)buffer, end - start + MAXINSN); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 0a75623172c2..05a322ea3f9f 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -13,7 +13,7 @@ #include "debug.h" #include "machine.h" -#define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) +#define UM(x) map__unmap_ip(kallsyms_map, (x)) static bool is_ignored_symbol(const char *name, char type) { @@ -221,8 +221,8 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused if (sym->start == sym->end) continue; - mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start); - mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end); + mem_start = map__unmap_ip(vmlinux_map, sym->start); + mem_end = map__unmap_ip(vmlinux_map, sym->end); first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL); pair = first_pair; @@ -319,8 +319,8 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused maps__for_each_entry(maps, rb_node) { struct map *pair, *map = rb_node->map; - mem_start = vmlinux_map->unmap_ip(vmlinux_map, map__start(map)); - mem_end = vmlinux_map->unmap_ip(vmlinux_map, map__end(map)); + mem_start = map__unmap_ip(vmlinux_map, map__start(map)); + mem_end = map__unmap_ip(vmlinux_map, map__end(map)); pair = maps__find(kallsyms.kmaps, mem_start); if (pair == NULL || pair->priv) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index b9cff782d7df..55f2e3a7577e 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -272,7 +272,7 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_s target.addr = map__objdump_2mem(map, ops->target.addr); if (maps__find_ams(ms->maps, &target) == 0 && - map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; return 0; @@ -376,8 +376,8 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s } target.addr = map__objdump_2mem(map, ops->target.addr); - start = map->unmap_ip(map, sym->start), - end = map->unmap_ip(map, sym->end); + start = map__unmap_ip(map, sym->start); + end = map__unmap_ip(map, sym->end); ops->target.outside = target.addr < start || target.addr > end; @@ -400,7 +400,7 @@ static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_s * the symbol searching and disassembly should be done. */ if (maps__find_ams(ms->maps, &target) == 0 && - map__rip_2objdump(target.ms.map, map->map_ip(target.ms.map, target.addr)) == ops->target.addr) + map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr) ops->target.sym = target.ms.sym; if (!ops->target.outside) { @@ -881,7 +881,7 @@ static int __symbol__inc_addr_samples(struct map_symbol *ms, unsigned offset; struct sym_hist *h; - pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, ms->map->unmap_ip(ms->map, addr)); + pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map__unmap_ip(ms->map, addr)); if ((addr < sym->start || addr >= sym->end) && (addr != sym->end || sym->start != sym->end)) { @@ -1977,8 +1977,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) return err; pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__, - symfs_filename, sym->name, map->unmap_ip(map, sym->start), - map->unmap_ip(map, sym->end)); + symfs_filename, sym->name, map__unmap_ip(map, sym->start), + map__unmap_ip(map, sym->end)); pr_debug("annotating [%p] %30s : [%p] %30s\n", dso, dso->long_name, sym, sym->name); diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index 9e20fa8ade09..e7dddf0127bc 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -74,7 +74,7 @@ int lock_contention_prepare(struct lock_contention *con) continue; } - addrs[con->filters->nr_addrs++] = kmap->unmap_ip(kmap, sym->start); + addrs[con->filters->nr_addrs++] = map__unmap_ip(kmap, sym->start); con->filters->addrs = addrs; } naddrs = con->filters->nr_addrs; @@ -233,7 +233,7 @@ static const char *lock_contention_get_name(struct lock_contention *con, if (sym) { unsigned long offset; - offset = kmap->map_ip(kmap, addr) - sym->start; + offset = map__map_ip(kmap, addr) - sym->start; if (offset == 0) return sym->name; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 528a7fb066cf..944835e16430 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -893,7 +893,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) return 0; - offset = al.map->map_ip(al.map, address); + offset = map__map_ip(al.map, address); map__load(al.map); diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index fe401fa4be02..16238f823a5e 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -278,7 +278,7 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) map = a.map; have_map: - offset = map->map_ip(map, ip); + offset = map__map_ip(map, ip); if (ip + len >= map__end(map)) len = map__end(map) - ip; return dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index f1a14c0ad26d..e36b418df2c6 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1122,7 +1122,8 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, u8 *data, ssize_t size) { - u64 offset = map->map_ip(map, addr); + u64 offset = map__map_ip(map, addr); + return dso__data_read_offset(dso, machine, offset, data, size); } @@ -1162,7 +1163,8 @@ ssize_t dso__data_write_cache_addr(struct dso *dso, struct map *map, struct machine *machine, u64 addr, const u8 *data, ssize_t size) { - u64 offset = map->map_ip(map, addr); + u64 offset = map__map_ip(map, addr); + return dso__data_write_cache_offs(dso, machine, offset, data, size); } diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2ddc75dee019..2712d1a8264e 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -487,7 +487,7 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma al.map = maps__find(machine__kernel_maps(machine), tp->addr); if (al.map && map__load(al.map) >= 0) { - al.addr = al.map->map_ip(al.map, tp->addr); + al.addr = map__map_ip(al.map, tp->addr); al.sym = map__find_symbol(al.map, al.addr); if (al.sym) ret += symbol__fprintf_symname_offs(al.sym, &al, fp); @@ -622,7 +622,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, */ if (load_map) map__load(al->map); - al->addr = al->map->map_ip(al->map, al->addr); + al->addr = map__map_ip(al->map, al->addr); } return al->map; @@ -743,12 +743,12 @@ int machine__resolve(struct machine *machine, struct addr_location *al, } if (!ret && al->sym) { snprintf(al_addr_str, sz, "0x%"PRIx64, - al->map->unmap_ip(al->map, al->sym->start)); + map__unmap_ip(al->map, al->sym->start)); ret = strlist__has_entry(symbol_conf.sym_list, al_addr_str); } if (!ret && symbol_conf.addr_list && al->map) { - unsigned long addr = al->map->unmap_ip(al->map, al->addr); + unsigned long addr = map__unmap_ip(al->map, al->addr); ret = intlist__has_entry(symbol_conf.addr_list, addr); if (!ret && symbol_conf.addr_range) { diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index dff5d8c4b06d..a09ac00810b7 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -151,7 +151,7 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, printed += fprintf(fp, " <-"); if (map) - addr = map->map_ip(map, node->ip); + addr = map__map_ip(map, node->ip); if (print_ip) { /* Show binary offset for userspace addr */ diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index a2e62daa708e..fe893c9bab3f 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -816,7 +816,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn, dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE)) return -ENOENT; - offset = al.map->map_ip(al.map, *ip); + offset = map__map_ip(al.map, *ip); if (!to_ip && one_map) { struct intel_pt_cache_entry *e; @@ -987,7 +987,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data) if (!thread__find_map(thread, cpumode, ip, &al) || !map__dso(al.map)) return -EINVAL; - offset = al.map->map_ip(al.map, ip); + offset = map__map_ip(al.map, ip); return intel_pt_match_pgd_ip(ptq->pt, ip, offset, map__dso(al.map)->long_name); } @@ -2749,7 +2749,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) for (sym = start; sym; sym = dso__next_symbol(sym)) { if (sym->binding == STB_GLOBAL && !strcmp(sym->name, "__switch_to")) { - ip = map->unmap_ip(map, sym->start); + ip = map__unmap_ip(map, sym->start); if (ip >= map__start(map) && ip < map__end(map)) { switch_ip = ip; break; @@ -2767,7 +2767,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip) for (sym = start; sym; sym = dso__next_symbol(sym)) { if (!strcmp(sym->name, ptss)) { - ip = map->unmap_ip(map, sym->start); + ip = map__unmap_ip(map, sym->start); if (ip >= map__start(map) && ip < map__end(map)) { *ptss_ip = ip; break; @@ -3393,7 +3393,7 @@ static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event) if (!dso || !dso->auxtrace_cache) continue; - offset = al.map->map_ip(al.map, addr); + offset = map__map_ip(al.map, addr); e = intel_pt_cache_lookup(dso, machine, offset); if (!e) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 9d24980a0a93..d29ec4a04488 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -919,7 +919,7 @@ static int machine__process_ksymbol_register(struct machine *machine, dso = map__dso(map); } - sym = symbol__new(map->map_ip(map, map__start(map)), + sym = symbol__new(map__map_ip(map, map__start(map)), event->ksymbol.len, 0, 0, event->ksymbol.name); if (!sym) @@ -944,7 +944,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine, else { struct dso *dso = map__dso(map); - sym = dso__find_symbol(dso, map->map_ip(map, map__start(map))); + sym = dso__find_symbol(dso, map__map_ip(map, map__start(map))); if (sym) dso__delete_symbol(dso, sym); } @@ -1279,7 +1279,7 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, dest_map = maps__find(kmaps, map->pgoff); if (dest_map != map) - map->pgoff = dest_map->map_ip(dest_map, map->pgoff); + map->pgoff = map__map_ip(dest_map, map->pgoff); found = true; } if (found || machine->trampolines_mapped) @@ -3345,7 +3345,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch return NULL; *modp = __map__is_kmodule(map) ? (char *)map__dso(map)->short_name : NULL; - *addrp = map->unmap_ip(map, sym->start); + *addrp = map__unmap_ip(map, sym->start); return sym->name; } @@ -3388,17 +3388,17 @@ bool machine__is_lock_function(struct machine *machine, u64 addr) return false; } - machine->sched.text_start = kmap->unmap_ip(kmap, sym->start); + machine->sched.text_start = map__unmap_ip(kmap, sym->start); /* should not fail from here */ sym = machine__find_kernel_symbol_by_name(machine, "__sched_text_end", &kmap); - machine->sched.text_end = kmap->unmap_ip(kmap, sym->start); + machine->sched.text_end = map__unmap_ip(kmap, sym->start); sym = machine__find_kernel_symbol_by_name(machine, "__lock_text_start", &kmap); - machine->lock.text_start = kmap->unmap_ip(kmap, sym->start); + machine->lock.text_start = map__unmap_ip(kmap, sym->start); sym = machine__find_kernel_symbol_by_name(machine, "__lock_text_end", &kmap); - machine->lock.text_end = kmap->unmap_ip(kmap, sym->start); + machine->lock.text_end = map__unmap_ip(kmap, sym->start); } /* failed to get kernel symbols */ diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index d97a6d20626f..a55aef4b1310 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -519,7 +519,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) if (dso->kernel == DSO_SPACE__USER) return rip + dso->text_offset; - return map->unmap_ip(map, rip) - map->reloc; + return map__unmap_ip(map, rip) - map->reloc; } /** @@ -530,7 +530,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) * Closely related to map__rip_2objdump(), this function takes an address from * objdump and converts it to a memory address. Note this assumes that @map * contains the address. To be sure the result is valid, check it forwards - * e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip + * e.g. map__rip_2objdump(map__map_ip(map, map__objdump_2mem(map, ip))) == ip * * Return: Memory address. */ @@ -539,24 +539,24 @@ u64 map__objdump_2mem(struct map *map, u64 ip) const struct dso *dso = map__dso(map); if (!dso->adjust_symbols) - return map->unmap_ip(map, ip); + return map__unmap_ip(map, ip); if (dso->rel) - return map->unmap_ip(map, ip + map->pgoff); + return map__unmap_ip(map, ip + map->pgoff); /* * kernel modules also have DSO_TYPE_USER in dso->kernel, * but all kernel modules are ET_REL, so won't get here. */ if (dso->kernel == DSO_SPACE__USER) - return map->unmap_ip(map, ip - dso->text_offset); + return map__unmap_ip(map, ip - dso->text_offset); return ip + map->reloc; } bool map__contains_symbol(const struct map *map, const struct symbol *sym) { - u64 ip = map->unmap_ip(map, sym->start); + u64 ip = map__unmap_ip(map, sym->start); return ip >= map__start(map) && ip < map__end(map); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9b0a84e46e48..9118eba71032 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -52,6 +52,16 @@ static inline struct dso *map__dso(const struct map *map) return map->dso; } +static inline u64 map__map_ip(const struct map *map, u64 ip) +{ + return map->map_ip(map, ip); +} + +static inline u64 map__unmap_ip(const struct map *map, u64 ip) +{ + return map->unmap_ip(map, ip); +} + static inline u64 map__start(const struct map *map) { return map->start; diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 21010a2b8e16..0eee27e24c33 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -194,7 +194,7 @@ struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) if (map != NULL && map__load(map) >= 0) { if (mapp != NULL) *mapp = map; - return map__find_symbol(map, map->map_ip(map, addr)); + return map__find_symbol(map, map__map_ip(map, addr)); } return NULL; @@ -237,7 +237,7 @@ int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams) return -1; } - ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr); + ams->al_addr = map__map_ip(ams->ms.map, ams->addr); ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr); return ams->ms.sym ? 0 : -1; @@ -349,8 +349,8 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) after->start = map__end(map); after->pgoff += map__end(map) - map__start(pos->map); - assert(pos->map->map_ip(pos->map, map__end(map)) == - after->map_ip(after, map__end(map))); + assert(map__map_ip(pos->map, map__end(map)) == + map__map_ip(after, map__end(map))); err = __maps__insert(maps, after); if (err) goto put_map; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 4d9dbeeb6014..bb44a3798df8 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -141,7 +141,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, sym = machine__find_kernel_symbol_by_name(host_machine, name, &map); if (!sym) return -ENOENT; - *addr = map->unmap_ip(map, sym->start) - + *addr = map__unmap_ip(map, sym->start) - ((reloc) ? 0 : map->reloc) - ((reladdr) ? map__start(map) : 0); } @@ -400,7 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, "Consider identifying the final function used at run time and set the probe directly on that.\n", pp->function); } else - address = map->unmap_ip(map, sym->start) - map->reloc; + address = map__unmap_ip(map, sym->start) - map->reloc; break; } if (!address) { @@ -2249,7 +2249,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp, goto out; pp->retprobe = tp->retprobe; - pp->offset = addr - map->unmap_ip(map, sym->start); + pp->offset = addr - map__unmap_ip(map, sym->start); pp->function = strdup(sym->name); ret = pp->function ? 0 : -ENOMEM; @@ -3123,7 +3123,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev, goto err_out; } /* Add one probe point */ - tp->address = map->unmap_ip(map, sym->start) + pp->offset; + tp->address = map__unmap_ip(map, sym->start) + pp->offset; /* Check the kprobe (not in module) is within .text */ if (!pev->uprobes && !pev->target && diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index cbf09eaf3734..41d4f9e6a8b7 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -471,7 +471,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample, struct addr_location node_al; unsigned long offset; - node_al.addr = map->map_ip(map, node->ip); + node_al.addr = map__map_ip(map, node->ip); node_al.map = map; offset = get_offset(node->ms.sym, &node_al); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index f161589aefda..87a3ba584af5 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -364,7 +364,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms, u64 rip = ip; if (dso && dso->kernel && dso->adjust_symbols) - rip = map->unmap_ip(map, ip); + rip = map__unmap_ip(map, ip); ret += repsep_snprintf(bf, size, "%-#*llx %c ", BITS_PER_LONG / 4 + 2, rip, o); @@ -375,7 +375,7 @@ static int _hist_entry__sym_snprintf(struct map_symbol *ms, if (sym->type == STT_OBJECT) { ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", - ip - map->unmap_ip(map, sym->start)); + ip - map__unmap_ip(map, sym->start)); } else { ret += repsep_snprintf(bf + ret, size - ret, "%.*s", width - ret, @@ -1147,7 +1147,7 @@ static int _hist_entry__addr_snprintf(struct map_symbol *ms, if (sym->type == STT_OBJECT) { ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name); ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx", - ip - map->unmap_ip(map, sym->start)); + ip - map__unmap_ip(map, sym->start)); } else { ret += repsep_snprintf(bf + ret, size - ret, "%.*s", width - ret, @@ -2104,9 +2104,9 @@ sort__addr_cmp(struct hist_entry *left, struct hist_entry *right) struct map *right_map = right->ms.map; if (left_map) - left_ip = left_map->unmap_ip(left_map, left_ip); + left_ip = map__unmap_ip(left_map, left_ip); if (right_map) - right_ip = right_map->unmap_ip(right_map, right_ip); + right_ip = map__unmap_ip(right_map, right_ip); return _sort__addr_cmp(left_ip, right_ip); } @@ -2118,7 +2118,7 @@ static int hist_entry__addr_snprintf(struct hist_entry *he, char *bf, struct map *map = he->ms.map; if (map) - ip = map->unmap_ip(map, ip); + ip = map__unmap_ip(map, ip); return repsep_snprintf(bf, size, "%-#*llx", width, ip); } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index b91deb177091..9ba49c1ef6ef 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -896,8 +896,8 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, * So that we look just like we get from .ko files, * i.e. not prelinked, relative to initial_map->start. */ - pos->start = curr_map->map_ip(curr_map, pos->start); - pos->end = curr_map->map_ip(curr_map, pos->end); + pos->start = map__map_ip(curr_map, pos->start); + pos->end = map__map_ip(curr_map, pos->end); } else if (x86_64 && is_entry_trampoline(pos->name)) { /* * These symbols are not needed anymore since the diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index bb7a2ce82d46..4b5bdc277baa 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -464,7 +464,7 @@ int thread__memcpy(struct thread *thread, struct machine *machine, if( !dso || dso->data.status == DSO_DATA_STATUS_ERROR || map__load(al.map) < 0) return -1; - offset = al.map->map_ip(al.map, ip); + offset = map__map_ip(al.map, ip); if (is64bit) *is64bit = dso->is_64_bit; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index b79f57e5648f..538320e4260c 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -115,7 +115,7 @@ static int entry(u64 ip, struct unwind_info *ui) pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", ip, - al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + al.map ? map__map_ip(al.map, ip) : (u64) 0); return 0; } diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 1c13f43e7d22..f9a52af48de4 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -640,7 +640,7 @@ static int entry(u64 ip, struct thread *thread, pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", ip, - al.map ? al.map->map_ip(al.map, ip) : (u64) 0); + al.map ? map__map_ip(al.map, ip) : (u64) 0); return cb(&e, arg); } -- GitLab From ddee3f2bddc11f850f7f6fcfc04bc26ceeab23ce Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:45 -0700 Subject: [PATCH 2358/5631] perf map: Add accessors for ->prot, ->priv and ->flags Later changes will add reference count checking for 'struct map'. Add an accessor so that the reference count check is only necessary in one place. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 2 +- tools/perf/builtin-report.c | 9 +++++---- tools/perf/tests/vmlinux-kallsyms.c | 4 ++-- tools/perf/util/map.h | 15 +++++++++++++++ tools/perf/util/sort.c | 6 +++--- tools/perf/util/symbol.c | 4 ++-- 6 files changed, 28 insertions(+), 12 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 8f6909dd8a54..fd2b38458a5d 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -758,7 +758,7 @@ int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event, if (!dso->hit) { dso->hit = 1; dso__inject_build_id(dso, tool, machine, - sample->cpumode, al.map->flags); + sample->cpumode, map__flags(al.map)); } } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2a6e2cee5e0d..c066452219c8 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -849,13 +849,14 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) maps__for_each_entry(maps, rb_node) { struct map *map = rb_node->map; const struct dso *dso = map__dso(map); + u32 prot = map__prot(map); printed += fprintf(fp, "%*s %" PRIx64 "-%" PRIx64 " %c%c%c%c %08" PRIx64 " %" PRIu64 " %s\n", indent, "", map__start(map), map__end(map), - map->prot & PROT_READ ? 'r' : '-', - map->prot & PROT_WRITE ? 'w' : '-', - map->prot & PROT_EXEC ? 'x' : '-', - map->flags & MAP_SHARED ? 's' : 'p', + prot & PROT_READ ? 'r' : '-', + prot & PROT_WRITE ? 'w' : '-', + prot & PROT_EXEC ? 'x' : '-', + map__flags(map) ? 's' : 'p', map->pgoff, dso->id.ino, dso->name); } diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 05a322ea3f9f..7db102868bc2 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -323,7 +323,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused mem_end = map__unmap_ip(vmlinux_map, map__end(map)); pair = maps__find(kallsyms.kmaps, mem_start); - if (pair == NULL || pair->priv) + if (pair == NULL || map__priv(pair)) continue; if (map__start(pair) == mem_start) { @@ -351,7 +351,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused maps__for_each_entry(maps, rb_node) { struct map *map = rb_node->map; - if (!map->priv) { + if (!map__priv(map)) { if (!header_printed) { pr_info("WARN: Maps only in kallsyms:\n"); header_printed = true; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 9118eba71032..fd440c9c279e 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -72,6 +72,21 @@ static inline u64 map__end(const struct map *map) return map->end; } +static inline u32 map__flags(const struct map *map) +{ + return map->flags; +} + +static inline u32 map__prot(const struct map *map) +{ + return map->prot; +} + +static inline bool map__priv(const struct map *map) +{ + return map->priv; +} + static inline size_t map__size(const struct map *map) { return map__end(map) - map__start(map); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 87a3ba584af5..80c9960c37e5 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1540,7 +1540,7 @@ sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right) */ if ((left->cpumode != PERF_RECORD_MISC_KERNEL) && - (!(l_map->flags & MAP_SHARED)) && !l_dso->id.maj && !l_dso->id.min && + (!(map__flags(l_map) & MAP_SHARED)) && !l_dso->id.maj && !l_dso->id.min && !l_dso->id.ino && !l_dso->id.ino_generation) { /* userspace anonymous */ @@ -1576,8 +1576,8 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, /* print [s] for shared data mmaps */ if ((he->cpumode != PERF_RECORD_MISC_KERNEL) && - map && !(map->prot & PROT_EXEC) && - (map->flags & MAP_SHARED) && + map && !(map__prot(map) & PROT_EXEC) && + (map__flags(map) & MAP_SHARED) && (dso->id.maj || dso->id.min || dso->id.ino || dso->id.ino_generation)) level = 's'; else if (!map) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 9ba49c1ef6ef..5c075d77a792 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1396,7 +1396,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, } /* Read new maps into temporary lists */ - err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md, + err = file__read_maps(fd, map__prot(map) & PROT_EXEC, kcore_mapfn, &md, &is_64_bit); if (err) goto out_err; @@ -1509,7 +1509,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, close(fd); - if (map->prot & PROT_EXEC) + if (map__prot(map) & PROT_EXEC) pr_debug("Using %s for kernel object code\n", kcore_filename); else pr_debug("Using %s for kernel data\n", kcore_filename); -- GitLab From 2a6e5e8a2ab68c9048f80d174d1698427fbd9c8c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:46 -0700 Subject: [PATCH 2359/5631] perf map: Add accessors for ->pgoff and ->reloc Later changes will add reference count checking for 'struct map'. Add accessors so that the reference count check is only necessary in one place. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/event.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/tests/vmlinux-kallsyms.c | 4 ++-- tools/perf/util/machine.c | 4 ++-- tools/perf/util/map.c | 14 +++++++------- tools/perf/util/map.h | 10 ++++++++++ tools/perf/util/probe-event.c | 8 ++++---- tools/perf/util/symbol.c | 6 +++--- tools/perf/util/unwind-libdw.c | 6 +++--- 9 files changed, 33 insertions(+), 23 deletions(-) diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index 3b2475707756..5741ffe47312 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -61,7 +61,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, event->mmap.start = map__start(map); event->mmap.len = map__size(map); - event->mmap.pgoff = map->pgoff; + event->mmap.pgoff = map__pgoff(map); event->mmap.pid = machine->pid; strlcpy(event->mmap.filename, kmap->name, PATH_MAX); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index c066452219c8..92c6797e7cba 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -857,7 +857,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp) prot & PROT_WRITE ? 'w' : '-', prot & PROT_EXEC ? 'x' : '-', map__flags(map) ? 's' : 'p', - map->pgoff, + map__pgoff(map), dso->id.ino, dso->name); } diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index 7db102868bc2..af511233c764 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -335,10 +335,10 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused } pr_info("WARN: %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as", - map__start(map), map__end(map), map->pgoff, dso->name); + map__start(map), map__end(map), map__pgoff(map), dso->name); if (mem_end != map__end(pair)) pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, - map__start(pair), map__end(pair), pair->pgoff); + map__start(pair), map__end(pair), map__pgoff(pair)); pr_info(" %s\n", dso->name); pair->priv = 1; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index d29ec4a04488..1ea6f6c06bbb 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1277,9 +1277,9 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, if (!kmap || !is_entry_trampoline(kmap->name)) continue; - dest_map = maps__find(kmaps, map->pgoff); + dest_map = maps__find(kmaps, map__pgoff(map)); if (dest_map != map) - map->pgoff = map__map_ip(dest_map, map->pgoff); + map->pgoff = map__map_ip(dest_map, map__pgoff(map)); found = true; } if (found || machine->trampolines_mapped) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index a55aef4b1310..6426af6882c2 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -421,7 +421,7 @@ size_t map__fprintf(struct map *map, FILE *fp) const struct dso *dso = map__dso(map); return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n", - map__start(map), map__end(map), map->pgoff, dso->name); + map__start(map), map__end(map), map__pgoff(map), dso->name); } size_t map__fprintf_dsoname(struct map *map, FILE *fp) @@ -510,7 +510,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) return rip; if (dso->rel) - return rip - map->pgoff; + return rip - map__pgoff(map); /* * kernel modules also have DSO_TYPE_USER in dso->kernel, @@ -519,7 +519,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip) if (dso->kernel == DSO_SPACE__USER) return rip + dso->text_offset; - return map__unmap_ip(map, rip) - map->reloc; + return map__unmap_ip(map, rip) - map__reloc(map); } /** @@ -542,7 +542,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) return map__unmap_ip(map, ip); if (dso->rel) - return map__unmap_ip(map, ip + map->pgoff); + return map__unmap_ip(map, ip + map__pgoff(map)); /* * kernel modules also have DSO_TYPE_USER in dso->kernel, @@ -551,7 +551,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip) if (dso->kernel == DSO_SPACE__USER) return map__unmap_ip(map, ip - dso->text_offset); - return ip + map->reloc; + return ip + map__reloc(map); } bool map__contains_symbol(const struct map *map, const struct symbol *sym) @@ -592,12 +592,12 @@ struct maps *map__kmaps(struct map *map) u64 map__dso_map_ip(const struct map *map, u64 ip) { - return ip - map__start(map) + map->pgoff; + return ip - map__start(map) + map__pgoff(map); } u64 map__dso_unmap_ip(const struct map *map, u64 ip) { - return ip + map__start(map) - map->pgoff; + return ip + map__start(map) - map__pgoff(map); } u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index fd440c9c279e..102485699aa8 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -72,6 +72,16 @@ static inline u64 map__end(const struct map *map) return map->end; } +static inline u64 map__pgoff(const struct map *map) +{ + return map->pgoff; +} + +static inline u64 map__reloc(const struct map *map) +{ + return map->reloc; +} + static inline u32 map__flags(const struct map *map) { return map->flags; diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index bb44a3798df8..6e2110d605fb 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -135,14 +135,14 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr, /* ref_reloc_sym is just a label. Need a special fix*/ reloc_sym = kernel_get_ref_reloc_sym(&map); if (reloc_sym && strcmp(name, reloc_sym->name) == 0) - *addr = (!map->reloc || reloc) ? reloc_sym->addr : + *addr = (!map__reloc(map) || reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr; else { sym = machine__find_kernel_symbol_by_name(host_machine, name, &map); if (!sym) return -ENOENT; *addr = map__unmap_ip(map, sym->start) - - ((reloc) ? 0 : map->reloc) - + ((reloc) ? 0 : map__reloc(map)) - ((reladdr) ? map__start(map) : 0); } return 0; @@ -400,7 +400,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, "Consider identifying the final function used at run time and set the probe directly on that.\n", pp->function); } else - address = map__unmap_ip(map, sym->start) - map->reloc; + address = map__unmap_ip(map, sym->start) - map__reloc(map); break; } if (!address) { @@ -866,7 +866,7 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, free(tevs[i].point.symbol); tevs[i].point.symbol = tmp; tevs[i].point.offset = tevs[i].point.address - - (map->reloc ? reloc_sym->unrelocated_addr : + (map__reloc(map) ? reloc_sym->unrelocated_addr : reloc_sym->addr); } return skipped; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 5c075d77a792..7282119c2990 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -810,11 +810,11 @@ static int maps__split_kallsyms_for_kcore(struct maps *kmaps, struct dso *dso) continue; } curr_map_dso = map__dso(curr_map); - pos->start -= map__start(curr_map) - curr_map->pgoff; + pos->start -= map__start(curr_map) - map__pgoff(curr_map); if (pos->end > map__end(curr_map)) pos->end = map__end(curr_map); if (pos->end) - pos->end -= map__start(curr_map) - curr_map->pgoff; + pos->end -= map__start(curr_map) - map__pgoff(curr_map); symbols__insert(&curr_map_dso->symbols, pos); ++count; } @@ -1459,7 +1459,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, if (new_map == replacement_map) { map->start = map__start(new_map); map->end = map__end(new_map); - map->pgoff = new_map->pgoff; + map->pgoff = map__pgoff(new_map); map->map_ip = new_map->map_ip; map->unmap_ip = new_map->unmap_ip; /* Ensure maps are correctly ordered */ diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 538320e4260c..9565f9906e5d 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -62,19 +62,19 @@ static int __report_module(struct addr_location *al, u64 ip, Dwarf_Addr s; dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL); - if (s != map__start(al->map) - al->map->pgoff) + if (s != map__start(al->map) - map__pgoff(al->map)) mod = 0; } if (!mod) mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1, - map__start(al->map) - al->map->pgoff, false); + map__start(al->map) - map__pgoff(al->map), false); if (!mod) { char filename[PATH_MAX]; if (dso__build_id_filename(dso, filename, sizeof(filename), false)) mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1, - map__start(al->map) - al->map->pgoff, false); + map__start(al->map) - map__pgoff(al->map), false); } if (mod) { -- GitLab From 93c9f1c287d00ab396f76955a79beac46efca2d5 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:47 -0700 Subject: [PATCH 2360/5631] perf test: Add extra diagnostics to maps test Dump the resultant and comparison maps on failure. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/maps.c | 51 +++++++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 15 deletions(-) diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index fd0c464fcf95..1c7293476aca 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include "tests.h" @@ -17,22 +18,42 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma { struct map_rb_node *rb_node; unsigned int i = 0; - - maps__for_each_entry(maps, rb_node) { - struct map *map = rb_node->map; - - if (i > 0) - TEST_ASSERT_VAL("less maps expected", (map && i < size) || (!map && i == size)); - - TEST_ASSERT_VAL("wrong map start", map__start(map) == merged[i].start); - TEST_ASSERT_VAL("wrong map end", map__end(map) == merged[i].end); - TEST_ASSERT_VAL("wrong map name", !strcmp(map__dso(map)->name, merged[i].name)); - TEST_ASSERT_VAL("wrong map refcnt", refcount_read(&map->refcnt) == 1); - - i++; + bool failed = false; + + if (maps__nr_maps(maps) != size) { + pr_debug("Expected %d maps, got %d", size, maps__nr_maps(maps)); + failed = true; + } else { + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; + + if (map__start(map) != merged[i].start || + map__end(map) != merged[i].end || + strcmp(map__dso(map)->name, merged[i].name) || + refcount_read(&map->refcnt) != 1) { + failed = true; + } + i++; + } } - - return TEST_OK; + if (failed) { + pr_debug("Expected:\n"); + for (i = 0; i < size; i++) { + pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: 1\n", + merged[i].start, merged[i].end, merged[i].name); + } + pr_debug("Got:\n"); + maps__for_each_entry(maps, rb_node) { + struct map *map = rb_node->map; + + pr_debug("\tstart: %" PRIu64 " end: %" PRIu64 " name: '%s' refcnt: %d\n", + map__start(map), + map__end(map), + map__dso(map)->name, + refcount_read(&map->refcnt)); + } + } + return failed ? TEST_FAIL : TEST_OK; } static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest __maybe_unused) -- GitLab From 392cf49ec54f0c7ba825ce9b04bf32bb85998135 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:48 -0700 Subject: [PATCH 2361/5631] perf maps: Modify maps_by_name to hold a reference to a map To make it clearer about the ownership of a reference count split the by-name case from the regular start-address sorted tree. Put the reference count when maps_by_name is freed, which requires moving a decrement to nr_maps in maps__remove. Add two missing map puts in maps__fixup_overlappings in the event maps__insert fails. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/maps.c | 30 ++++++++++++++++-------------- tools/perf/util/symbol.c | 21 +++++++++++++++++---- 2 files changed, 33 insertions(+), 18 deletions(-) diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 0eee27e24c33..5afed53ea0b4 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -26,6 +26,9 @@ static void __maps__free_maps_by_name(struct maps *maps) /* * Free everything to try to do it from the rbtree in the next search */ + for (unsigned int i = 0; i < maps__nr_maps(maps); i++) + map__put(maps__maps_by_name(maps)[i]); + zfree(&maps->maps_by_name); maps->nr_maps_allocated = 0; } @@ -42,7 +45,7 @@ static int __maps__insert(struct maps *maps, struct map *map) return -ENOMEM; RB_CLEAR_NODE(&new_rb_node->rb_node); - new_rb_node->map = map; + new_rb_node->map = map__get(map); while (*p != NULL) { parent = *p; @@ -55,7 +58,6 @@ static int __maps__insert(struct maps *maps, struct map *map) rb_link_node(&new_rb_node->rb_node, parent, p); rb_insert_color(&new_rb_node->rb_node, maps__entries(maps)); - map__get(map); return 0; } @@ -100,7 +102,7 @@ int maps__insert(struct maps *maps, struct map *map) maps->maps_by_name = maps_by_name; maps->nr_maps_allocated = nr_allocate; } - maps__maps_by_name(maps)[maps__nr_maps(maps) - 1] = map; + maps__maps_by_name(maps)[maps__nr_maps(maps) - 1] = map__get(map); __maps__sort_by_name(maps); } out: @@ -126,9 +128,9 @@ void maps__remove(struct maps *maps, struct map *map) rb_node = maps__find_node(maps, map); assert(rb_node->map == map); __maps__remove(maps, rb_node); - --maps->nr_maps; if (maps__maps_by_name(maps)) __maps__free_maps_by_name(maps); + --maps->nr_maps; up_write(maps__lock(maps)); } @@ -136,6 +138,9 @@ static void __maps__purge(struct maps *maps) { struct map_rb_node *pos, *next; + if (maps__maps_by_name(maps)) + __maps__free_maps_by_name(maps); + maps__for_each_entry_safe(maps, pos, next) { rb_erase_init(&pos->rb_node, maps__entries(maps)); map__put(pos->map); @@ -293,7 +298,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) } next = first; - while (next) { + while (next && !err) { struct map_rb_node *pos = rb_entry(next, struct map_rb_node, rb_node); next = rb_next(&pos->rb_node); @@ -331,8 +336,10 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) before->end = map__start(map); err = __maps__insert(maps, before); - if (err) + if (err) { + map__put(before); goto put_map; + } if (verbose >= 2 && !use_browser) map__fprintf(before, fp); @@ -352,22 +359,17 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) assert(map__map_ip(pos->map, map__end(map)) == map__map_ip(after, map__end(map))); err = __maps__insert(maps, after); - if (err) + if (err) { + map__put(after); goto put_map; - + } if (verbose >= 2 && !use_browser) map__fprintf(after, fp); map__put(after); } put_map: map__put(pos->map); - - if (err) - goto out; } - - err = 0; -out: up_write(maps__lock(maps)); return err; } diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 7282119c2990..91ebf93e0c20 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2053,10 +2053,23 @@ int dso__load(struct dso *dso, struct map *map) static int map__strcmp(const void *a, const void *b) { - const struct dso *dso_a = map__dso(*(const struct map **)a); - const struct dso *dso_b = map__dso(*(const struct map **)b); + const struct map *map_a = *(const struct map **)a; + const struct map *map_b = *(const struct map **)b; + const struct dso *dso_a = map__dso(map_a); + const struct dso *dso_b = map__dso(map_b); + int ret = strcmp(dso_a->short_name, dso_b->short_name); - return strcmp(dso_a->short_name, dso_b->short_name); + if (ret == 0 && map_a != map_b) { + /* + * Ensure distinct but name equal maps have an order in part to + * aid reference counting. + */ + ret = (int)map__start(map_a) - (int)map__start(map_b); + if (ret == 0) + ret = (int)((intptr_t)map_a - (intptr_t)map_b); + } + + return ret; } static int map__strcmp_name(const void *name, const void *b) @@ -2088,7 +2101,7 @@ static int map__groups__sort_by_name_from_rbtree(struct maps *maps) maps->nr_maps_allocated = maps__nr_maps(maps); maps__for_each_entry(maps, rb_node) - maps_by_name[i++] = rb_node->map; + maps_by_name[i++] = map__get(rb_node->map); __maps__sort_by_name(maps); -- GitLab From ec417ad4c691b5d90ab13cf26789e8719468ae39 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 4 Apr 2023 13:59:49 -0700 Subject: [PATCH 2362/5631] perf map: Changes to reference counting When a pointer to a map exists do a get, when that pointer is overwritten or freed, put the map. This avoids issues with gets and puts being inconsistently used causing, use after puts, etc. For example, the map in struct addr_location is changed to hold a reference count. Reference count checking and address sanitizer were used to identify issues. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: https://lore.kernel.org/r/20230404205954.2245628-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/code-reading.c | 1 + tools/perf/tests/hists_cumulate.c | 10 ++++ tools/perf/tests/hists_filter.c | 10 ++++ tools/perf/tests/hists_link.c | 18 +++++- tools/perf/tests/hists_output.c | 10 ++++ tools/perf/tests/mmap-thread-lookup.c | 1 + tools/perf/util/callchain.c | 9 +-- tools/perf/util/event.c | 6 +- tools/perf/util/hist.c | 10 ++-- tools/perf/util/machine.c | 79 ++++++++++++++++----------- tools/perf/util/map.c | 2 +- 11 files changed, 112 insertions(+), 44 deletions(-) diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index 1545fcaa95c6..efe026a35010 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -366,6 +366,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, } pr_debug("Bytes read match those read by objdump\n"); out: + map__put(al.map); return err; } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index f00ec9abdbcd..8c0e3f334747 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -112,6 +112,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) } fake_samples[i].thread = al.thread; + map__put(fake_samples[i].map); fake_samples[i].map = al.map; fake_samples[i].sym = al.sym; } @@ -147,6 +148,14 @@ static void del_hist_entries(struct hists *hists) } } +static void put_fake_samples(void) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) + map__put(fake_samples[i].map); +} + typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) @@ -733,6 +742,7 @@ static int test__hists_cumulate(struct test_suite *test __maybe_unused, int subt /* tear down everything */ evlist__delete(evlist); machines__exit(&machines); + put_fake_samples(); return err; } diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 7c552549f4a4..98eff5935a1c 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -89,6 +89,7 @@ static int add_hist_entries(struct evlist *evlist, } fake_samples[i].thread = al.thread; + map__put(fake_samples[i].map); fake_samples[i].map = al.map; fake_samples[i].sym = al.sym; } @@ -101,6 +102,14 @@ static int add_hist_entries(struct evlist *evlist, return TEST_FAIL; } +static void put_fake_samples(void) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) + map__put(fake_samples[i].map); +} + static int test__hists_filter(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { int err = TEST_FAIL; @@ -322,6 +331,7 @@ static int test__hists_filter(struct test_suite *test __maybe_unused, int subtes evlist__delete(evlist); reset_output_field(); machines__exit(&machines); + put_fake_samples(); return err; } diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index e7e4ee57ce04..64ce8097889c 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -6,6 +6,7 @@ #include "evsel.h" #include "evlist.h" #include "machine.h" +#include "map.h" #include "parse-events.h" #include "hists_common.h" #include "util/mmap.h" @@ -94,6 +95,7 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) } fake_common_samples[k].thread = al.thread; + map__put(fake_common_samples[k].map); fake_common_samples[k].map = al.map; fake_common_samples[k].sym = al.sym; } @@ -126,11 +128,24 @@ static int add_hist_entries(struct evlist *evlist, struct machine *machine) return -1; } +static void put_fake_samples(void) +{ + size_t i, j; + + for (i = 0; i < ARRAY_SIZE(fake_common_samples); i++) + map__put(fake_common_samples[i].map); + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) { + for (j = 0; j < ARRAY_SIZE(fake_samples[0]); j++) + map__put(fake_samples[i][j].map); + } +} + static int find_sample(struct sample *samples, size_t nr_samples, struct thread *t, struct map *m, struct symbol *s) { while (nr_samples--) { - if (samples->thread == t && samples->map == m && + if (samples->thread == t && + samples->map == m && samples->sym == s) return 1; samples++; @@ -336,6 +351,7 @@ static int test__hists_link(struct test_suite *test __maybe_unused, int subtest evlist__delete(evlist); reset_output_field(); machines__exit(&machines); + put_fake_samples(); return err; } diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 428d11a938f2..cebd5226bb12 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -78,6 +78,7 @@ static int add_hist_entries(struct hists *hists, struct machine *machine) } fake_samples[i].thread = al.thread; + map__put(fake_samples[i].map); fake_samples[i].map = al.map; fake_samples[i].sym = al.sym; } @@ -113,6 +114,14 @@ static void del_hist_entries(struct hists *hists) } } +static void put_fake_samples(void) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(fake_samples); i++) + map__put(fake_samples[i].map); +} + typedef int (*test_fn_t)(struct evsel *, struct machine *); #define COMM(he) (thread__comm_str(he->thread)) @@ -620,6 +629,7 @@ static int test__hists_output(struct test_suite *test __maybe_unused, int subtes /* tear down everything */ evlist__delete(evlist); machines__exit(&machines); + put_fake_samples(); return err; } diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 5cc4644e353d..898eda55b7a8 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -203,6 +203,7 @@ static int mmap_events(synth_cb synth) } pr_debug("map %p, addr %" PRIx64 "\n", al.map, map__start(al.map)); + map__put(al.map); } machine__delete_threads(machine); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 8e7c29836765..b0dafc758173 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -589,7 +589,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) } call->ip = cursor_node->ip; call->ms = cursor_node->ms; - map__get(call->ms.map); + call->ms.map = map__get(call->ms.map); call->srcline = cursor_node->srcline; if (cursor_node->branch) { @@ -1067,7 +1067,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, node->ip = ip; map__zput(node->ms.map); node->ms = *ms; - map__get(node->ms.map); + node->ms.map = map__get(node->ms.map); node->branch = branch; node->nr_loop_iter = nr_loop_iter; node->iter_cycles = iter_cycles; @@ -1115,7 +1115,8 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * struct machine *machine = maps__machine(node->ms.maps); al->maps = node->ms.maps; - al->map = node->ms.map; + map__put(al->map); + al->map = map__get(node->ms.map); al->sym = node->ms.sym; al->srcline = node->srcline; al->addr = node->ip; @@ -1528,7 +1529,7 @@ int callchain_node__make_parent_list(struct callchain_node *node) goto out; *new = *chain; new->has_children = false; - map__get(new->ms.map); + new->ms.map = map__get(new->ms.map); list_add_tail(&new->list, &head); } parent = parent->parent; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 2712d1a8264e..13f7f85e92e1 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -485,13 +485,14 @@ size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *ma if (machine) { struct addr_location al; - al.map = maps__find(machine__kernel_maps(machine), tp->addr); + al.map = map__get(maps__find(machine__kernel_maps(machine), tp->addr)); if (al.map && map__load(al.map) >= 0) { al.addr = map__map_ip(al.map, tp->addr); al.sym = map__find_symbol(al.map, al.addr); if (al.sym) ret += symbol__fprintf_symname_offs(al.sym, &al, fp); } + map__put(al.map); } ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len); old = true; @@ -614,7 +615,7 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr, return NULL; } - al->map = maps__find(maps, al->addr); + al->map = map__get(maps__find(maps, al->addr)); if (al->map != NULL) { /* * Kernel maps might be changed when loading symbols so loading @@ -773,6 +774,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al, */ void addr_location__put(struct addr_location *al) { + map__zput(al->map); thread__zput(al->thread); } diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index e494425cad06..51020da15ffc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -450,7 +450,7 @@ static int hist_entry__init(struct hist_entry *he, memset(&he->stat, 0, sizeof(he->stat)); } - map__get(he->ms.map); + he->ms.map = map__get(he->ms.map); if (he->branch_info) { /* @@ -465,13 +465,13 @@ static int hist_entry__init(struct hist_entry *he, memcpy(he->branch_info, template->branch_info, sizeof(*he->branch_info)); - map__get(he->branch_info->from.ms.map); - map__get(he->branch_info->to.ms.map); + he->branch_info->from.ms.map = map__get(he->branch_info->from.ms.map); + he->branch_info->to.ms.map = map__get(he->branch_info->to.ms.map); } if (he->mem_info) { - map__get(he->mem_info->iaddr.ms.map); - map__get(he->mem_info->daddr.ms.map); + he->mem_info->iaddr.ms.map = map__get(he->mem_info->iaddr.ms.map); + he->mem_info->daddr.ms.map = map__get(he->mem_info->daddr.ms.map); } if (hist_entry__has_callchains(he) && symbol_conf.use_callchain) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 1ea6f6c06bbb..25738775834e 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -881,21 +881,29 @@ static int machine__process_ksymbol_register(struct machine *machine, struct symbol *sym; struct dso *dso; struct map *map = maps__find(machine__kernel_maps(machine), event->ksymbol.addr); + bool put_map = false; + int err = 0; if (!map) { - int err; - dso = dso__new(event->ksymbol.name); - if (dso) { - dso->kernel = DSO_SPACE__KERNEL; - map = map__new2(0, dso); - dso__put(dso); - } - if (!dso || !map) { - return -ENOMEM; + if (!dso) { + err = -ENOMEM; + goto out; } - + dso->kernel = DSO_SPACE__KERNEL; + map = map__new2(0, dso); + dso__put(dso); + if (!map) { + err = -ENOMEM; + goto out; + } + /* + * The inserted map has a get on it, we need to put to release + * the reference count here, but do it after all accesses are + * done. + */ + put_map = true; if (event->ksymbol.ksym_type == PERF_RECORD_KSYMBOL_TYPE_OOL) { dso->binary_type = DSO_BINARY_TYPE__OOL; dso->data.file_size = event->ksymbol.len; @@ -905,9 +913,10 @@ static int machine__process_ksymbol_register(struct machine *machine, map->start = event->ksymbol.addr; map->end = map__start(map) + event->ksymbol.len; err = maps__insert(machine__kernel_maps(machine), map); - map__put(map); - if (err) - return err; + if (err) { + err = -ENOMEM; + goto out; + } dso__set_loaded(dso); @@ -922,10 +931,15 @@ static int machine__process_ksymbol_register(struct machine *machine, sym = symbol__new(map__map_ip(map, map__start(map)), event->ksymbol.len, 0, 0, event->ksymbol.name); - if (!sym) - return -ENOMEM; + if (!sym) { + err = -ENOMEM; + goto out; + } dso__insert_symbol(dso, sym); - return 0; +out: + if (put_map) + map__put(map); + return err; } static int machine__process_ksymbol_unregister(struct machine *machine, @@ -1027,13 +1041,11 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start goto out; err = maps__insert(machine__kernel_maps(machine), map); - - /* Put the map here because maps__insert already got it */ - map__put(map); - /* If maps__insert failed, return NULL. */ - if (err) + if (err) { + map__put(map); map = NULL; + } out: /* put the dso here, corresponding to machine__findnew_module_dso */ dso__put(dso); @@ -1325,6 +1337,7 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) /* In case of renewal the kernel map, destroy previous one */ machine__destroy_kernel_maps(machine); + map__put(machine->vmlinux_map); machine->vmlinux_map = map__new2(0, kernel); if (machine->vmlinux_map == NULL) return -ENOMEM; @@ -1613,7 +1626,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, map->end = start + size; dso__kernel_module_get_build_id(map__dso(map), machine->root_dir); - + map__put(map); return 0; } @@ -1659,16 +1672,18 @@ static void machine__set_kernel_mmap(struct machine *machine, static int machine__update_kernel_mmap(struct machine *machine, u64 start, u64 end) { - struct map *map = machine__kernel_map(machine); + struct map *orig, *updated; int err; - map__get(map); - maps__remove(machine__kernel_maps(machine), map); + orig = machine->vmlinux_map; + updated = map__get(orig); + machine->vmlinux_map = updated; machine__set_kernel_mmap(machine, start, end); + maps__remove(machine__kernel_maps(machine), orig); + err = maps__insert(machine__kernel_maps(machine), updated); + map__put(orig); - err = maps__insert(machine__kernel_maps(machine), map); - map__put(map); return err; } @@ -2295,7 +2310,7 @@ static int add_callchain_ip(struct thread *thread, { struct map_symbol ms; struct addr_location al; - int nr_loop_iter = 0; + int nr_loop_iter = 0, err; u64 iter_cycles = 0; const char *srcline = NULL; @@ -2360,9 +2375,11 @@ static int add_callchain_ip(struct thread *thread, return 0; srcline = callchain_srcline(&ms, al.addr); - return callchain_cursor_append(cursor, ip, &ms, - branch, flags, nr_loop_iter, - iter_cycles, branch_from, srcline); + err = callchain_cursor_append(cursor, ip, &ms, + branch, flags, nr_loop_iter, + iter_cycles, branch_from, srcline); + map__put(al.map); + return err; } struct branch_info *sample__resolve_bstack(struct perf_sample *sample, diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 6426af6882c2..d81b6ca18ee9 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -410,7 +410,7 @@ struct map *map__clone(struct map *from) map = memdup(from, size); if (map != NULL) { refcount_set(&map->refcnt, 1); - dso__get(dso); + map->dso = dso__get(dso); } return map; -- GitLab From fe4e5efa401fe15eab9259e358730145449e83a2 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 1 Apr 2023 10:15:29 +0100 Subject: [PATCH 2363/5631] dma-mapping: provide a fallback dma_default_coherent dma_default_coherent was decleared unconditionally at kernel/dma/mapping.c but only decleared when any of non-coherent options is enabled in dma-map-ops.h. Guard the declaration in mapping.c with non-coherent options and provide a fallback definition. Signed-off-by: Jiaxun Yang Signed-off-by: Christoph Hellwig --- include/linux/dma-map-ops.h | 2 ++ kernel/dma/mapping.c | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 41bf4bdb117a..31f114f486c4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -269,6 +269,8 @@ static inline bool dev_is_dma_coherent(struct device *dev) return dev->dma_coherent; } #else +#define dma_default_coherent true + static inline bool dev_is_dma_coherent(struct device *dev) { return true; diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 68106e3791f6..80f9663ffe26 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -17,7 +17,11 @@ #include "debug.h" #include "direct.h" +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_default_coherent; +#endif /* * Managed DMA API -- GitLab From 1d3f56b295302fdb4ac9caf6ce09f5ae7d2e651a Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 1 Apr 2023 10:15:30 +0100 Subject: [PATCH 2364/5631] dma-mapping: provide CONFIG_ARCH_DMA_DEFAULT_COHERENT Provide a kconfig option to allow arches to manipulate default value of dma_default_coherent in Kconfig. Signed-off-by: Jiaxun Yang Signed-off-by: Christoph Hellwig --- kernel/dma/Kconfig | 7 +++++++ kernel/dma/mapping.c | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 56866aaa2ae1..6677d0e64d27 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -76,6 +76,13 @@ config ARCH_HAS_DMA_PREP_COHERENT config ARCH_HAS_FORCE_DMA_UNENCRYPTED bool +# +# Select this option if the architecture assumes DMA devices are coherent +# by default. +# +config ARCH_DMA_DEFAULT_COHERENT + bool + config SWIOTLB bool select NEED_DMA_MAP_STATE diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 80f9663ffe26..9a4db5cce600 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -20,7 +20,7 @@ #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -bool dma_default_coherent; +bool dma_default_coherent = IS_ENABLED(CONFIG_ARCH_DMA_DEFAULT_COHERENT); #endif /* -- GitLab From c00a60d6f4a14b06264bb6f9fcc754b8ddbf67e3 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Sat, 1 Apr 2023 10:15:31 +0100 Subject: [PATCH 2365/5631] of: address: always use dma_default_coherent for default coherency As for now all arches have dma_default_coherent reflecting default DMA coherency for of devices, so there is no need to have a standalone config option. Signed-off-by: Jiaxun Yang Reviewed-by: Rob Herring Acked-by: Michael Ellerman (powerpc) Signed-off-by: Christoph Hellwig --- arch/powerpc/Kconfig | 2 +- arch/riscv/Kconfig | 2 +- drivers/of/Kconfig | 4 ---- drivers/of/address.c | 2 +- 4 files changed, 3 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a6c4407d3ec8..f4269f5109c7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -113,6 +113,7 @@ config PPC # select ARCH_32BIT_OFF_T if PPC32 select ARCH_DISABLE_KASAN_INLINE if PPC_RADIX_MMU + select ARCH_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_COPY_MC if PPC64 @@ -272,7 +273,6 @@ config PPC select NEED_PER_CPU_PAGE_FIRST_CHUNK if PPC64 select NEED_SG_DMA_LENGTH select OF - select OF_DMA_DEFAULT_COHERENT if !NOT_COHERENT_CACHE select OF_EARLY_FLATTREE select OLD_SIGACTION if PPC32 select OLD_SIGSUSPEND diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..30727eb63688 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -12,6 +12,7 @@ config 32BIT config RISCV def_bool y + select ARCH_DMA_DEFAULT_COHERENT select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE @@ -121,7 +122,6 @@ config RISCV select MODULES_USE_ELF_RELA if MODULES select MODULE_SECTIONS if MODULES select OF - select OF_DMA_DEFAULT_COHERENT select OF_EARLY_FLATTREE select OF_IRQ select PCI_DOMAINS_GENERIC if PCI diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 644386833a7b..e40f10bf2ba4 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -102,8 +102,4 @@ config OF_OVERLAY config OF_NUMA bool -config OF_DMA_DEFAULT_COHERENT - # arches should select this if DMA is coherent by default for OF devices - bool - endif # OF diff --git a/drivers/of/address.c b/drivers/of/address.c index 4c0b169ef9bf..23ade4919853 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -1103,7 +1103,7 @@ phys_addr_t __init of_dma_get_max_cpu_address(struct device_node *np) bool of_dma_is_coherent(struct device_node *np) { struct device_node *node; - bool is_coherent = IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT); + bool is_coherent = dma_default_coherent; node = of_node_get(np); -- GitLab From 4fa5843d81fdce9ba7e03f8a666e2f8e592aec2b Mon Sep 17 00:00:00 2001 From: Like Xu Date: Fri, 10 Mar 2023 19:33:49 +0800 Subject: [PATCH 2366/5631] KVM: x86/pmu: Fix a typo in kvm_pmu_request_counter_reprogam() Fix a "reprogam" => "reprogram" typo in kvm_pmu_request_counter_reprogam(). Fixes: 68fb4757e867 ("KVM: x86/pmu: Defer reprogram_counter() to kvm_pmu_handle_event()") Signed-off-by: Like Xu Link: https://lore.kernel.org/r/20230310113349.31799-1-likexu@tencent.com [sean: trim the changelog] Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 2 +- arch/x86/kvm/pmu.h | 2 +- arch/x86/kvm/svm/pmu.c | 2 +- arch/x86/kvm/vmx/pmu_intel.c | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 35d80151b853..2226db9601e2 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -650,7 +650,7 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { pmc->prev_counter = pmc->counter; pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index be62c16f2265..5c7bbf03b599 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -195,7 +195,7 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) KVM_PMC_MAX_FIXED); } -static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc) +static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) { set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cc77a0681800..5fa939e411d8 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -161,7 +161,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~pmu->reserved_bits; if (data != pmc->eventsel) { pmc->eventsel = data; - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } return 0; } diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index eb291dfbe4aa..741efe2c497b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -57,7 +57,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } } @@ -484,7 +484,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data != pmc->eventsel) { pmc->eventsel = data; - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } break; } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) { -- GitLab From 996c32b745a15a637e8244a25f06b74acce98976 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 5 Apr 2023 00:47:19 +0200 Subject: [PATCH 2367/5631] clk: qcom: gcc-sm6115: Mark RCGs shared where applicable The vast majority of shared RCGs were not marked as such. Fix it. Fixes: cbe63bfdc54f ("clk: qcom: Add Global Clock controller (GCC) driver for SM6115") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230404224719.909746-1-konrad.dybcio@linaro.org --- drivers/clk/qcom/gcc-sm6115.c | 50 +++++++++++++++++------------------ 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/clk/qcom/gcc-sm6115.c b/drivers/clk/qcom/gcc-sm6115.c index 5b8222fea2f7..5f09aefa7fb9 100644 --- a/drivers/clk/qcom/gcc-sm6115.c +++ b/drivers/clk/qcom/gcc-sm6115.c @@ -694,7 +694,7 @@ static struct clk_rcg2 gcc_camss_axi_clk_src = { .parent_data = gcc_parents_7, .num_parents = ARRAY_SIZE(gcc_parents_7), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -715,7 +715,7 @@ static struct clk_rcg2 gcc_camss_cci_clk_src = { .parent_data = gcc_parents_9, .num_parents = ARRAY_SIZE(gcc_parents_9), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -738,7 +738,7 @@ static struct clk_rcg2 gcc_camss_csi0phytimer_clk_src = { .parent_data = gcc_parents_4, .num_parents = ARRAY_SIZE(gcc_parents_4), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -753,7 +753,7 @@ static struct clk_rcg2 gcc_camss_csi1phytimer_clk_src = { .parent_data = gcc_parents_4, .num_parents = ARRAY_SIZE(gcc_parents_4), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -768,7 +768,7 @@ static struct clk_rcg2 gcc_camss_csi2phytimer_clk_src = { .parent_data = gcc_parents_4, .num_parents = ARRAY_SIZE(gcc_parents_4), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -790,7 +790,7 @@ static struct clk_rcg2 gcc_camss_mclk0_clk_src = { .parent_data = gcc_parents_3, .num_parents = ARRAY_SIZE(gcc_parents_3), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -805,7 +805,7 @@ static struct clk_rcg2 gcc_camss_mclk1_clk_src = { .parent_data = gcc_parents_3, .num_parents = ARRAY_SIZE(gcc_parents_3), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -820,7 +820,7 @@ static struct clk_rcg2 gcc_camss_mclk2_clk_src = { .parent_data = gcc_parents_3, .num_parents = ARRAY_SIZE(gcc_parents_3), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -835,7 +835,7 @@ static struct clk_rcg2 gcc_camss_mclk3_clk_src = { .parent_data = gcc_parents_3, .num_parents = ARRAY_SIZE(gcc_parents_3), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -857,7 +857,7 @@ static struct clk_rcg2 gcc_camss_ope_ahb_clk_src = { .parent_data = gcc_parents_8, .num_parents = ARRAY_SIZE(gcc_parents_8), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -881,7 +881,7 @@ static struct clk_rcg2 gcc_camss_ope_clk_src = { .parent_data = gcc_parents_8, .num_parents = ARRAY_SIZE(gcc_parents_8), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -916,7 +916,7 @@ static struct clk_rcg2 gcc_camss_tfe_0_clk_src = { .parent_data = gcc_parents_5, .num_parents = ARRAY_SIZE(gcc_parents_5), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -941,7 +941,7 @@ static struct clk_rcg2 gcc_camss_tfe_0_csid_clk_src = { .parent_data = gcc_parents_6, .num_parents = ARRAY_SIZE(gcc_parents_6), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -956,7 +956,7 @@ static struct clk_rcg2 gcc_camss_tfe_1_clk_src = { .parent_data = gcc_parents_5, .num_parents = ARRAY_SIZE(gcc_parents_5), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -971,7 +971,7 @@ static struct clk_rcg2 gcc_camss_tfe_1_csid_clk_src = { .parent_data = gcc_parents_6, .num_parents = ARRAY_SIZE(gcc_parents_6), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -986,7 +986,7 @@ static struct clk_rcg2 gcc_camss_tfe_2_clk_src = { .parent_data = gcc_parents_5, .num_parents = ARRAY_SIZE(gcc_parents_5), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1001,7 +1001,7 @@ static struct clk_rcg2 gcc_camss_tfe_2_csid_clk_src = { .parent_data = gcc_parents_6, .num_parents = ARRAY_SIZE(gcc_parents_6), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1024,7 +1024,7 @@ static struct clk_rcg2 gcc_camss_tfe_cphy_rx_clk_src = { .parent_data = gcc_parents_10, .num_parents = ARRAY_SIZE(gcc_parents_10), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1046,7 +1046,7 @@ static struct clk_rcg2 gcc_camss_top_ahb_clk_src = { .parent_data = gcc_parents_7, .num_parents = ARRAY_SIZE(gcc_parents_7), .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1116,7 +1116,7 @@ static struct clk_rcg2 gcc_pdm2_clk_src = { .name = "gcc_pdm2_clk_src", .parent_data = gcc_parents_0, .num_parents = ARRAY_SIZE(gcc_parents_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1329,7 +1329,7 @@ static struct clk_rcg2 gcc_ufs_phy_axi_clk_src = { .name = "gcc_ufs_phy_axi_clk_src", .parent_data = gcc_parents_0, .num_parents = ARRAY_SIZE(gcc_parents_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1351,7 +1351,7 @@ static struct clk_rcg2 gcc_ufs_phy_ice_core_clk_src = { .name = "gcc_ufs_phy_ice_core_clk_src", .parent_data = gcc_parents_0, .num_parents = ARRAY_SIZE(gcc_parents_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1392,7 +1392,7 @@ static struct clk_rcg2 gcc_ufs_phy_unipro_core_clk_src = { .name = "gcc_ufs_phy_unipro_core_clk_src", .parent_data = gcc_parents_0, .num_parents = ARRAY_SIZE(gcc_parents_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1414,7 +1414,7 @@ static struct clk_rcg2 gcc_usb30_prim_master_clk_src = { .name = "gcc_usb30_prim_master_clk_src", .parent_data = gcc_parents_0, .num_parents = ARRAY_SIZE(gcc_parents_0), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -1483,7 +1483,7 @@ static struct clk_rcg2 gcc_video_venus_clk_src = { .parent_data = gcc_parents_13, .num_parents = ARRAY_SIZE(gcc_parents_13), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; -- GitLab From dfdeda67ea2dac57d2d7506d65cfe5a0878ad285 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 7 Mar 2023 14:13:56 +0000 Subject: [PATCH 2368/5631] KVM: x86/pmu: Prevent the PMU from counting disallowed events When counting "Instructions Retired" (0xc0) in a guest, KVM will occasionally increment the PMU counter regardless of if that event is being filtered. This is because some PMU events are incremented via kvm_pmu_trigger_event(), which doesn't know about the event filter. Add the event filter to kvm_pmu_trigger_event(), so events that are disallowed do not increment their counters. Fixes: 9cd803d496e7 ("KVM: x86: Update vPMCs when retiring instructions") Signed-off-by: Aaron Lewis Reviewed-by: Like Xu Link: https://lore.kernel.org/r/20230307141400.1486314-2-aaronlewis@google.com [sean: prepend "pmc" to the new function] Signed-off-by: Sean Christopherson --- arch/x86/kvm/pmu.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 2226db9601e2..597a8f8f90b9 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -400,6 +400,12 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) return is_fixed_event_allowed(filter, pmc->idx); } +static bool pmc_event_is_allowed(struct kvm_pmc *pmc) +{ + return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) && + check_pmu_event_filter(pmc); +} + static void reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -409,10 +415,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) pmc_pause_counter(pmc); - if (!pmc_speculative_in_use(pmc) || !pmc_is_globally_enabled(pmc)) - goto reprogram_complete; - - if (!check_pmu_event_filter(pmc)) + if (!pmc_event_is_allowed(pmc)) goto reprogram_complete; if (pmc->counter < pmc->prev_counter) @@ -688,7 +691,7 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - if (!pmc || !pmc_is_globally_enabled(pmc) || !pmc_speculative_in_use(pmc)) + if (!pmc || !pmc_event_is_allowed(pmc)) continue; /* Ignore checks for edge detect, pin control, invert and CMASK bits */ -- GitLab From 93f21d925f787eb4a91e7ade77a544df30be0605 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 29 Mar 2023 16:01:35 +0200 Subject: [PATCH 2369/5631] clk: qcom: gpucc-sm6375: Configure CX_GDSC disable wait value Configure the disable wait value on the CX GDSC to ensure we don't get any undefined behavior. This was omitted when first adding the driver. Fixes: 8397e24278b3 ("clk: qcom: Add GPU clock controller driver for SM6375") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230329140135.2178957-1-konrad.dybcio@linaro.org --- drivers/clk/qcom/gpucc-sm6375.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/qcom/gpucc-sm6375.c b/drivers/clk/qcom/gpucc-sm6375.c index d8f4c4b59f1b..d3620344a009 100644 --- a/drivers/clk/qcom/gpucc-sm6375.c +++ b/drivers/clk/qcom/gpucc-sm6375.c @@ -358,6 +358,7 @@ static struct clk_branch gpucc_sleep_clk = { static struct gdsc gpu_cx_gdsc = { .gdscr = 0x106c, .gds_hw_ctrl = 0x1540, + .clk_dis_wait_val = 8, .pd = { .name = "gpu_cx_gdsc", }, -- GitLab From d75b82cff48883b5e75abfd3930afa7a148ab440 Mon Sep 17 00:00:00 2001 From: Devi Priya Date: Thu, 16 Mar 2023 12:59:36 +0530 Subject: [PATCH 2370/5631] clk: qcom: Add Global Clock Controller driver for IPQ9574 Add Global Clock Controller (GCC) driver for ipq9574 based devices Co-developed-by: Anusha Rao Signed-off-by: Anusha Rao Signed-off-by: Devi Priya Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230316072940.29137-3-quic_devipriy@quicinc.com --- drivers/clk/qcom/Kconfig | 8 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gcc-ipq9574.c | 4248 ++++++++++++++++++++++++++++++++ 3 files changed, 4257 insertions(+) create mode 100644 drivers/clk/qcom/gcc-ipq9574.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index 449bc8314d21..d71c9d6036bb 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -181,6 +181,14 @@ config IPQ_GCC_8074 i2c, USB, SD/eMMC, etc. Select this for the root clock of ipq8074. +config IPQ_GCC_9574 + tristate "IPQ9574 Global Clock Controller" + help + Support for global clock controller on ipq9574 devices. + Say Y if you want to use peripheral devices such as UART, SPI, + i2c, USB, SD/eMMC, etc. Select this for the root clock + of ipq9574. + config MSM_GCC_8660 tristate "MSM8660 Global Clock Controller" help diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index c1adb427d1ef..b54085e579a0 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_IPQ_GCC_5332) += gcc-ipq5332.o obj-$(CONFIG_IPQ_GCC_6018) += gcc-ipq6018.o obj-$(CONFIG_IPQ_GCC_806X) += gcc-ipq806x.o obj-$(CONFIG_IPQ_GCC_8074) += gcc-ipq8074.o +obj-$(CONFIG_IPQ_GCC_9574) += gcc-ipq9574.o obj-$(CONFIG_IPQ_LCC_806X) += lcc-ipq806x.o obj-$(CONFIG_MDM_GCC_9607) += gcc-mdm9607.o obj-$(CONFIG_MDM_GCC_9615) += gcc-mdm9615.o diff --git a/drivers/clk/qcom/gcc-ipq9574.c b/drivers/clk/qcom/gcc-ipq9574.c new file mode 100644 index 000000000000..b2a2d618a5ec --- /dev/null +++ b/drivers/clk/qcom/gcc-ipq9574.c @@ -0,0 +1,4248 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Copyright (c) 2023 The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "clk-rcg.h" +#include "clk-branch.h" +#include "clk-alpha-pll.h" +#include "clk-regmap-divider.h" +#include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" +#include "reset.h" + +/* Need to match the order of clocks in DT binding */ +enum { + DT_XO, + DT_SLEEP_CLK, + DT_BIAS_PLL_UBI_NC_CLK, + DT_PCIE30_PHY0_PIPE_CLK, + DT_PCIE30_PHY1_PIPE_CLK, + DT_PCIE30_PHY2_PIPE_CLK, + DT_PCIE30_PHY3_PIPE_CLK, + DT_USB3PHY_0_CC_PIPE_CLK, +}; + +enum { + P_XO, + P_PCIE30_PHY0_PIPE, + P_PCIE30_PHY1_PIPE, + P_PCIE30_PHY2_PIPE, + P_PCIE30_PHY3_PIPE, + P_USB3PHY_0_PIPE, + P_GPLL0, + P_GPLL0_DIV2, + P_GPLL0_OUT_AUX, + P_GPLL2, + P_GPLL4, + P_PI_SLEEP, + P_BIAS_PLL_UBI_NC_CLK, +}; + +static const struct parent_map gcc_xo_map[] = { + { P_XO, 0 }, +}; + +static const struct clk_parent_data gcc_xo_data[] = { + { .index = DT_XO }, +}; + +static const struct clk_parent_data gcc_sleep_clk_data[] = { + { .index = DT_SLEEP_CLK }, +}; + +static struct clk_alpha_pll gpll0_main = { + .offset = 0x20000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x0b000, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gpll0_main", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_fixed_factor gpll0_out_main_div2 = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "gpll0_out_main_div2", + .parent_hws = (const struct clk_hw *[]) { + &gpll0_main.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_alpha_pll_postdiv gpll0 = { + .offset = 0x20000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll0", + .parent_hws = (const struct clk_hw *[]) { + &gpll0_main.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_alpha_pll_postdiv_ro_ops, + }, +}; + +static struct clk_alpha_pll gpll4_main = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x0b000, + .enable_mask = BIT(2), + .hw.init = &(struct clk_init_data) { + .name = "gpll4_main", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll4 = { + .offset = 0x22000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll4", + .parent_hws = (const struct clk_hw *[]) { + &gpll4_main.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_alpha_pll_postdiv_ro_ops, + }, +}; + +static struct clk_alpha_pll gpll2_main = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .clkr = { + .enable_reg = 0x0b000, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gpll2_main", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .ops = &clk_alpha_pll_ops, + }, + }, +}; + +static struct clk_alpha_pll_postdiv gpll2 = { + .offset = 0x21000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT], + .width = 4, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gpll2", + .parent_hws = (const struct clk_hw *[]) { + &gpll2_main.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_alpha_pll_postdiv_ro_ops, + }, +}; + +static struct clk_branch gcc_sleep_clk_src = { + .halt_reg = 0x3400c, + .clkr = { + .enable_reg = 0x3400c, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sleep_clk_src", + .parent_data = gcc_sleep_clk_data, + .num_parents = ARRAY_SIZE(gcc_sleep_clk_data), + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll0_out_main_div2[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll0_out_main_div2_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll4[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll4_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL4, 2 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll0_div2_gpll0[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, + { .hw = &gpll0.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll0_div2_gpll0_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_DIV2, 4 }, + { P_GPLL0, 5 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll0_sleep_clk[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll0_sleep_clk_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_DIV2, 4 }, + { P_PI_SLEEP, 6 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_xo_gpll0_core_pi_sleep_clk_map[] = { + { P_XO, 0 }, + { P_GPLL0, 2 }, + { P_PI_SLEEP, 6 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .index = DT_BIAS_PLL_UBI_NC_CLK }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL4, 2 }, + { P_BIAS_PLL_UBI_NC_CLK, 3 }, +}; + +static const struct clk_parent_data + gcc_xo_gpll0_gpll0_aux_core_pi_sleep_clk[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map + gcc_xo_gpll0_gpll0_aux_core_pi_sleep_clk_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_OUT_AUX, 2 }, + { P_PI_SLEEP, 6 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_out_main_div2_gpll0[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_out_main_div2_gpll0_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data + gcc_xo_gpll4_gpll0_gpll0_out_main_div2[] = { + { .index = DT_XO }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll4_gpll0_gpll0_out_main_div2_map[] = { + { P_XO, 0 }, + { P_GPLL4, 1 }, + { P_GPLL0, 3 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data gcc_usb3phy_0_cc_pipe_clk_xo[] = { + { .index = DT_USB3PHY_0_CC_PIPE_CLK }, + { .index = DT_XO }, +}; + +static const struct parent_map gcc_usb3phy_0_cc_pipe_clk_xo_map[] = { + { P_USB3PHY_0_PIPE, 0 }, + { P_XO, 2 }, +}; + +static const struct clk_parent_data + gcc_xo_gpll0_gpll2_gpll0_out_main_div2[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL2, 2 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll4_gpll0_div2[] = { + { .index = DT_XO}, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll4_gpll0_div2_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL4, 2 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data gcc_xo_gpll4_gpll0_gpll0_div2[] = { + { .index = DT_XO }, + { .hw = &gpll4.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0_out_main_div2.hw }, +}; + +static const struct parent_map gcc_xo_gpll4_gpll0_gpll0_div2_map[] = { + { P_XO, 0 }, + { P_GPLL4, 1 }, + { P_GPLL0, 2 }, + { P_GPLL0_DIV2, 4 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll2[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll2_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL2, 2 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll2_gpll4_pi_sleep[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, + { .hw = &gpll4.clkr.hw }, + { .index = DT_SLEEP_CLK }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll2_gpll4_pi_sleep_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL2, 2 }, + { P_GPLL4, 3 }, + { P_PI_SLEEP, 6 }, +}; + +static const struct clk_parent_data gcc_xo_gpll0_gpll0_aux_gpll2[] = { + { .index = DT_XO }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll0.clkr.hw }, + { .hw = &gpll2.clkr.hw }, +}; + +static const struct parent_map gcc_xo_gpll0_gpll0_aux_gpll2_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL0_OUT_AUX, 2 }, + { P_GPLL2, 3 }, +}; + +static const struct freq_tbl ftbl_apss_ahb_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + { } +}; + +static struct clk_rcg2 apss_ahb_clk_src = { + .cmd_rcgr = 0x2400c, + .freq_tbl = ftbl_apss_ahb_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "apss_ahb_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_apss_axi_clk_src[] = { + F(533000000, P_GPLL0, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 apss_axi_clk_src = { + .cmd_rcgr = 0x24004, + .freq_tbl = ftbl_apss_axi_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_div2_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "apss_axi_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_div2_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_div2_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_blsp1_qup_i2c_apps_clk_src[] = { + F(9600000, P_XO, 2.5, 0, 0), + F(24000000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + { } +}; + +static struct clk_rcg2 blsp1_qup1_i2c_apps_clk_src = { + .cmd_rcgr = 0x02018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup1_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_blsp1_qup_spi_apps_clk_src[] = { + F(960000, P_XO, 10, 2, 5), + F(4800000, P_XO, 5, 0, 0), + F(9600000, P_XO, 2, 4, 5), + F(16000000, P_GPLL0, 10, 1, 5), + F(24000000, P_XO, 1, 0, 0), + F(25000000, P_GPLL0, 16, 1, 2), + F(50000000, P_GPLL0, 16, 0, 0), + { } +}; + +static struct clk_rcg2 blsp1_qup1_spi_apps_clk_src = { + .cmd_rcgr = 0x02004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup1_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup2_i2c_apps_clk_src = { + .cmd_rcgr = 0x03018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup2_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup2_spi_apps_clk_src = { + .cmd_rcgr = 0x03004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup2_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup3_i2c_apps_clk_src = { + .cmd_rcgr = 0x04018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup3_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup3_spi_apps_clk_src = { + .cmd_rcgr = 0x04004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup3_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup4_i2c_apps_clk_src = { + .cmd_rcgr = 0x05018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup4_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup4_spi_apps_clk_src = { + .cmd_rcgr = 0x05004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup4_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup5_i2c_apps_clk_src = { + .cmd_rcgr = 0x06018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup5_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup5_spi_apps_clk_src = { + .cmd_rcgr = 0x06004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup5_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup6_i2c_apps_clk_src = { + .cmd_rcgr = 0x07018, + .freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup6_i2c_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_qup6_spi_apps_clk_src = { + .cmd_rcgr = 0x07004, + .freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_qup6_spi_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_blsp1_uart_apps_clk_src[] = { + F(3686400, P_GPLL0_DIV2, 1, 144, 15625), + F(7372800, P_GPLL0_DIV2, 1, 288, 15625), + F(14745600, P_GPLL0_DIV2, 1, 576, 15625), + F(24000000, P_XO, 1, 0, 0), + F(25000000, P_GPLL0, 16, 1, 2), + F(32000000, P_GPLL0, 1, 1, 25), + F(40000000, P_GPLL0, 1, 1, 20), + F(46400000, P_GPLL0, 1, 29, 500), + F(48000000, P_GPLL0, 1, 3, 50), + F(51200000, P_GPLL0, 1, 8, 125), + F(56000000, P_GPLL0, 1, 7, 100), + F(58982400, P_GPLL0, 1, 1152, 15625), + F(60000000, P_GPLL0, 1, 3, 40), + F(64000000, P_GPLL0, 12.5, 0, 0), + { } +}; + +static struct clk_rcg2 blsp1_uart1_apps_clk_src = { + .cmd_rcgr = 0x0202c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart1_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_uart2_apps_clk_src = { + .cmd_rcgr = 0x0302c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart2_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_uart3_apps_clk_src = { + .cmd_rcgr = 0x0402c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart3_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_uart4_apps_clk_src = { + .cmd_rcgr = 0x0502c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart4_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_uart5_apps_clk_src = { + .cmd_rcgr = 0x0602c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart5_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 blsp1_uart6_apps_clk_src = { + .cmd_rcgr = 0x0702c, + .freq_tbl = ftbl_blsp1_uart_apps_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "blsp1_uart6_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_apss_ahb_clk = { + .halt_reg = 0x24018, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x0b004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_apss_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &apss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_apss_axi_clk = { + .halt_reg = 0x2401c, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x0b004, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_apss_axi_clk", + .parent_hws = (const struct clk_hw *[]) { + &apss_axi_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = { + .halt_reg = 0x2024, + .clkr = { + .enable_reg = 0x2024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup1_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup1_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = { + .halt_reg = 0x02020, + .clkr = { + .enable_reg = 0x02020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup1_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup1_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = { + .halt_reg = 0x03024, + .clkr = { + .enable_reg = 0x03024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup2_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup2_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = { + .halt_reg = 0x03020, + .clkr = { + .enable_reg = 0x03020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup2_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup2_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = { + .halt_reg = 0x04024, + .clkr = { + .enable_reg = 0x04024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup3_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup3_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = { + .halt_reg = 0x04020, + .clkr = { + .enable_reg = 0x04020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup3_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup3_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup4_i2c_apps_clk = { + .halt_reg = 0x05024, + .clkr = { + .enable_reg = 0x05024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup4_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup4_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup4_spi_apps_clk = { + .halt_reg = 0x05020, + .clkr = { + .enable_reg = 0x05020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup4_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup4_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup5_i2c_apps_clk = { + .halt_reg = 0x06024, + .clkr = { + .enable_reg = 0x06024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup5_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup5_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup5_spi_apps_clk = { + .halt_reg = 0x06020, + .clkr = { + .enable_reg = 0x06020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup5_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup5_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup6_i2c_apps_clk = { + .halt_reg = 0x07024, + .clkr = { + .enable_reg = 0x07024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup6_i2c_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup6_i2c_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_qup6_spi_apps_clk = { + .halt_reg = 0x07020, + .clkr = { + .enable_reg = 0x07020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_qup6_spi_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_qup6_spi_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart1_apps_clk = { + .halt_reg = 0x02040, + .clkr = { + .enable_reg = 0x02040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart1_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart1_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart2_apps_clk = { + .halt_reg = 0x03040, + .clkr = { + .enable_reg = 0x03040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart2_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart2_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart3_apps_clk = { + .halt_reg = 0x04054, + .clkr = { + .enable_reg = 0x04054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart3_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart3_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart4_apps_clk = { + .halt_reg = 0x05040, + .clkr = { + .enable_reg = 0x05040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart4_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart4_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart5_apps_clk = { + .halt_reg = 0x06040, + .clkr = { + .enable_reg = 0x06040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart5_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart5_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_uart6_apps_clk = { + .halt_reg = 0x07040, + .clkr = { + .enable_reg = 0x07040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_uart6_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &blsp1_uart6_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_pcie0_axi_m_clk_src[] = { + F(240000000, P_GPLL4, 5, 0, 0), + { } +}; + +static struct clk_rcg2 pcie0_axi_m_clk_src = { + .cmd_rcgr = 0x28018, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie0_axi_m_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie0_axi_m_clk = { + .halt_reg = 0x28038, + .clkr = { + .enable_reg = 0x28038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_axi_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_anoc_pcie0_1lane_m_clk = { + .halt_reg = 0x2e07c, + .clkr = { + .enable_reg = 0x2e07c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_pcie0_1lane_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie1_axi_m_clk_src = { + .cmd_rcgr = 0x29018, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie1_axi_m_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie1_axi_m_clk = { + .halt_reg = 0x29038, + .clkr = { + .enable_reg = 0x29038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_axi_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_anoc_pcie1_1lane_m_clk = { + .halt_reg = 0x2e08c, + .clkr = { + .enable_reg = 0x2e08c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_pcie1_1lane_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_pcie2_axi_m_clk_src[] = { + F(342857143, P_GPLL4, 3.5, 0, 0), + { } +}; + +static struct clk_rcg2 pcie2_axi_m_clk_src = { + .cmd_rcgr = 0x2a018, + .freq_tbl = ftbl_pcie2_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie2_axi_m_clk_src", + .parent_data = gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie2_axi_m_clk = { + .halt_reg = 0x2a038, + .clkr = { + .enable_reg = 0x2a038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_axi_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_anoc_pcie2_2lane_m_clk = { + .halt_reg = 0x2e080, + .clkr = { + .enable_reg = 0x2e080, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_pcie2_2lane_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie3_axi_m_clk_src = { + .cmd_rcgr = 0x2b018, + .freq_tbl = ftbl_pcie2_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie3_axi_m_clk_src", + .parent_data = gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3_axi_m_clk = { + .halt_reg = 0x2b038, + .clkr = { + .enable_reg = 0x2b038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_axi_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_anoc_pcie3_2lane_m_clk = { + .halt_reg = 0x2e090, + .clkr = { + .enable_reg = 0x2e090, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_pcie3_2lane_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie0_axi_s_clk_src = { + .cmd_rcgr = 0x28020, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie0_axi_s_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie0_axi_s_clk = { + .halt_reg = 0x2803c, + .clkr = { + .enable_reg = 0x2803c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_axi_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie0_axi_s_bridge_clk = { + .halt_reg = 0x28040, + .clkr = { + .enable_reg = 0x28040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie0_1lane_s_clk = { + .halt_reg = 0x2e048, + .clkr = { + .enable_reg = 0x2e048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_snoc_pcie0_1lane_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie1_axi_s_clk_src = { + .cmd_rcgr = 0x29020, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie1_axi_s_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie1_axi_s_clk = { + .halt_reg = 0x2903c, + .clkr = { + .enable_reg = 0x2903c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_axi_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie1_axi_s_bridge_clk = { + .halt_reg = 0x29040, + .clkr = { + .enable_reg = 0x29040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie1_1lane_s_clk = { + .halt_reg = 0x2e04c, + .clkr = { + .enable_reg = 0x2e04c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_snoc_pcie1_1lane_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie2_axi_s_clk_src = { + .cmd_rcgr = 0x2a020, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie2_axi_s_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie2_axi_s_clk = { + .halt_reg = 0x2a03c, + .clkr = { + .enable_reg = 0x2a03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_axi_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie2_axi_s_bridge_clk = { + .halt_reg = 0x2a040, + .clkr = { + .enable_reg = 0x2a040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie2_2lane_s_clk = { + .halt_reg = 0x2e050, + .clkr = { + .enable_reg = 0x2e050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_snoc_pcie2_2lane_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie3_axi_s_clk_src = { + .cmd_rcgr = 0x2b020, + .freq_tbl = ftbl_pcie0_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie3_axi_s_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3_axi_s_clk = { + .halt_reg = 0x2b03c, + .clkr = { + .enable_reg = 0x2b03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_axi_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3_axi_s_bridge_clk = { + .halt_reg = 0x2b040, + .clkr = { + .enable_reg = 0x2b040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_axi_s_bridge_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_pcie3_2lane_s_clk = { + .halt_reg = 0x2e054, + .clkr = { + .enable_reg = 0x2e054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_snoc_pcie3_2lane_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_axi_s_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux pcie0_pipe_clk_src = { + .reg = 0x28064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "pcie0_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE30_PHY0_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux pcie1_pipe_clk_src = { + .reg = 0x29064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "pcie1_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE30_PHY1_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux pcie2_pipe_clk_src = { + .reg = 0x2a064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "pcie2_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE30_PHY2_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static struct clk_regmap_phy_mux pcie3_pipe_clk_src = { + .reg = 0x2b064, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "pcie3_pipe_clk_src", + .parent_data = &(const struct clk_parent_data) { + .index = DT_PCIE30_PHY3_PIPE_CLK, + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_pcie_rchng_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + { } +}; + +static struct clk_rcg2 pcie0_rchng_clk_src = { + .cmd_rcgr = 0x28028, + .freq_tbl = ftbl_pcie_rchng_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie0_rchng_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie0_rchng_clk = { + .halt_reg = 0x28028, + .clkr = { + .enable_reg = 0x28028, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_rchng_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie0_rchng_clk_src.clkr.hw + + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie1_rchng_clk_src = { + .cmd_rcgr = 0x29028, + .freq_tbl = ftbl_pcie_rchng_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie1_rchng_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie1_rchng_clk = { + .halt_reg = 0x29028, + .clkr = { + .enable_reg = 0x29028, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_rchng_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie1_rchng_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie2_rchng_clk_src = { + .cmd_rcgr = 0x2a028, + .freq_tbl = ftbl_pcie_rchng_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie2_rchng_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie2_rchng_clk = { + .halt_reg = 0x2a028, + .clkr = { + .enable_reg = 0x2a028, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_rchng_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie2_rchng_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_rcg2 pcie3_rchng_clk_src = { + .cmd_rcgr = 0x2b028, + .freq_tbl = ftbl_pcie_rchng_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie3_rchng_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie3_rchng_clk = { + .halt_reg = 0x2b028, + .clkr = { + .enable_reg = 0x2b028, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_rchng_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie3_rchng_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_pcie_aux_clk_src[] = { + F(20000000, P_GPLL0, 10, 1, 4), + { } +}; + +static struct clk_rcg2 pcie_aux_clk_src = { + .cmd_rcgr = 0x28004, + .freq_tbl = ftbl_pcie_aux_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_aux_core_pi_sleep_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcie_aux_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_aux_core_pi_sleep_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_aux_core_pi_sleep_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_pcie0_aux_clk = { + .halt_reg = 0x28034, + .clkr = { + .enable_reg = 0x28034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_aux_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie_aux_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie1_aux_clk = { + .halt_reg = 0x29034, + .clkr = { + .enable_reg = 0x29034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_aux_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie_aux_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie2_aux_clk = { + .halt_reg = 0x2a034, + .clkr = { + .enable_reg = 0x2a034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_aux_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie_aux_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3_aux_clk = { + .halt_reg = 0x2b034, + .clkr = { + .enable_reg = 0x2b034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_aux_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcie_aux_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_usb_aux_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 usb0_aux_clk_src = { + .cmd_rcgr = 0x2c018, + .freq_tbl = ftbl_usb_aux_clk_src, + .mnd_width = 16, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_core_pi_sleep_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "usb0_aux_clk_src", + .parent_data = gcc_xo_gpll0_core_pi_sleep_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_core_pi_sleep_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_usb0_aux_clk = { + .halt_reg = 0x2c048, + .clkr = { + .enable_reg = 0x2c048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_aux_clk", + .parent_hws = (const struct clk_hw *[]) { + &usb0_aux_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_usb0_master_clk_src[] = { + F(100000000, P_GPLL0, 8, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 usb0_master_clk_src = { + .cmd_rcgr = 0x2c004, + .freq_tbl = ftbl_usb0_master_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_out_main_div2_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "usb0_master_clk_src", + .parent_data = gcc_xo_gpll0_out_main_div2_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_out_main_div2_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_usb0_master_clk = { + .halt_reg = 0x2c044, + .clkr = { + .enable_reg = 0x2c044, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_master_clk", + .parent_hws = (const struct clk_hw *[]) { + &usb0_master_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_snoc_usb_clk = { + .halt_reg = 0x2e058, + .clkr = { + .enable_reg = 0x2e058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_snoc_usb_clk", + .parent_hws = (const struct clk_hw *[]) { + &usb0_master_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_anoc_usb_axi_clk = { + .halt_reg = 0x2e084, + .clkr = { + .enable_reg = 0x2e084, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_usb_axi_clk", + .parent_hws = (const struct clk_hw *[]) { + &usb0_master_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_usb0_mock_utmi_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(60000000, P_GPLL4, 10, 1, 2), + { } +}; + +static struct clk_rcg2 usb0_mock_utmi_clk_src = { + .cmd_rcgr = 0x2c02c, + .freq_tbl = ftbl_usb0_mock_utmi_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll4_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "usb0_mock_utmi_clk_src", + .parent_data = gcc_xo_gpll4_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll4_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_regmap_div usb0_mock_utmi_div_clk_src = { + .reg = 0x2c040, + .shift = 0, + .width = 2, + .clkr.hw.init = &(struct clk_init_data) { + .name = "usb0_mock_utmi_div_clk_src", + .parent_data = &(const struct clk_parent_data) { + .hw = &usb0_mock_utmi_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch gcc_usb0_mock_utmi_clk = { + .halt_reg = 0x2c04c, + .clkr = { + .enable_reg = 0x2c04c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_mock_utmi_clk", + .parent_hws = (const struct clk_hw *[]) { + &usb0_mock_utmi_div_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap_mux usb0_pipe_clk_src = { + .reg = 0x2C074, + .shift = 8, + .width = 2, + .parent_map = gcc_usb3phy_0_cc_pipe_clk_xo_map, + .clkr = { + .hw.init = &(struct clk_init_data) { + .name = "usb0_pipe_clk_src", + .parent_data = gcc_usb3phy_0_cc_pipe_clk_xo, + .num_parents = ARRAY_SIZE(gcc_usb3phy_0_cc_pipe_clk_xo), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_mux_closest_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_sdcc_apps_clk_src[] = { + F(144000, P_XO, 16, 12, 125), + F(400000, P_XO, 12, 1, 5), + F(24000000, P_GPLL2, 12, 1, 4), + F(48000000, P_GPLL2, 12, 1, 2), + F(96000000, P_GPLL2, 12, 0, 0), + F(177777778, P_GPLL0, 4.5, 0, 0), + F(192000000, P_GPLL2, 6, 0, 0), + F(384000000, P_GPLL2, 3, 0, 0), + F(400000000, P_GPLL0, 2, 0, 0), + { } +}; + +static struct clk_rcg2 sdcc1_apps_clk_src = { + .cmd_rcgr = 0x33004, + .freq_tbl = ftbl_sdcc_apps_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "sdcc1_apps_clk_src", + .parent_data = gcc_xo_gpll0_gpll2_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll2_gpll0_out_main_div2), + .ops = &clk_rcg2_floor_ops, + }, +}; + +static struct clk_branch gcc_sdcc1_apps_clk = { + .halt_reg = 0x3302c, + .clkr = { + .enable_reg = 0x3302c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_apps_clk", + .parent_hws = (const struct clk_hw *[]) { + &sdcc1_apps_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = { + F(150000000, P_GPLL4, 8, 0, 0), + F(300000000, P_GPLL4, 4, 0, 0), +}; + +static struct clk_rcg2 sdcc1_ice_core_clk_src = { + .cmd_rcgr = 0x33018, + .freq_tbl = ftbl_sdcc_ice_core_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_gpll0_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "sdcc1_ice_core_clk_src", + .parent_data = gcc_xo_gpll0_gpll4_gpll0_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4_gpll0_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_sdcc1_ice_core_clk = { + .halt_reg = 0x33030, + .clkr = { + .enable_reg = 0x33030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_ice_core_clk", + .parent_hws = (const struct clk_hw *[]) { + &sdcc1_ice_core_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_pcnoc_bfdcd_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(50000000, P_GPLL0, 16, 0, 0), + F(80000000, P_GPLL0, 10, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + { } +}; + +static struct clk_rcg2 pcnoc_bfdcd_clk_src = { + .cmd_rcgr = 0x31004, + .freq_tbl = ftbl_pcnoc_bfdcd_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "pcnoc_bfdcd_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .flags = CLK_IS_CRITICAL, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_nsscfg_clk = { + .halt_reg = 0x1702c, + .clkr = { + .enable_reg = 0x1702c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nsscfg_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_nsscc_clk = { + .halt_reg = 0x17030, + .clkr = { + .enable_reg = 0x17030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_nsscc_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nsscc_clk = { + .halt_reg = 0x17034, + .clkr = { + .enable_reg = 0x17034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nsscc_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_pcnoc_1_clk = { + .halt_reg = 0x17080, + .clkr = { + .enable_reg = 0x17080, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_pcnoc_1_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_dap_ahb_clk = { + .halt_reg = 0x2d064, + .clkr = { + .enable_reg = 0x2d064, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_dap_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_cfg_ahb_clk = { + .halt_reg = 0x2d068, + .clkr = { + .enable_reg = 0x2d068, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_cfg_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_ahb_clk = { + .halt_reg = 0x32010, + .clkr = { + .enable_reg = 0x32010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qpic_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qpic_clk = { + .halt_reg = 0x32014, + .clkr = { + .enable_reg = 0x32014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qpic_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_blsp1_ahb_clk = { + .halt_reg = 0x01004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x0b004, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data) { + .name = "gcc_blsp1_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mdio_ahb_clk = { + .halt_reg = 0x17040, + .clkr = { + .enable_reg = 0x17040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mdio_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_prng_ahb_clk = { + .halt_reg = 0x13024, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x0b004, + .enable_mask = BIT(10), + .hw.init = &(struct clk_init_data) { + .name = "gcc_prng_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy0_ahb_clk = { + .halt_reg = 0x1704c, + .clkr = { + .enable_reg = 0x1704c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy0_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy1_ahb_clk = { + .halt_reg = 0x1705c, + .clkr = { + .enable_reg = 0x1705c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy1_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy2_ahb_clk = { + .halt_reg = 0x1706c, + .clkr = { + .enable_reg = 0x1706c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy2_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_ahb_clk = { + .halt_reg = 0x3a004, + .clkr = { + .enable_reg = 0x3a004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_cmn_12gpll_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_apu_clk = { + .halt_reg = 0x3a00c, + .clkr = { + .enable_reg = 0x3a00c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_cmn_12gpll_apu_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie0_ahb_clk = { + .halt_reg = 0x28030, + .clkr = { + .enable_reg = 0x28030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie0_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie1_ahb_clk = { + .halt_reg = 0x29030, + .clkr = { + .enable_reg = 0x29030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie1_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie2_ahb_clk = { + .halt_reg = 0x2a030, + .clkr = { + .enable_reg = 0x2a030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie2_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcie3_ahb_clk = { + .halt_reg = 0x2b030, + .clkr = { + .enable_reg = 0x2b030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcie3_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_usb0_phy_cfg_ahb_clk = { + .halt_reg = 0x2c05c, + .clkr = { + .enable_reg = 0x2c05c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_phy_cfg_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sdcc1_ahb_clk = { + .halt_reg = 0x33034, + .clkr = { + .enable_reg = 0x33034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sdcc1_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &pcnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_system_noc_bfdcd_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(133333333, P_GPLL0, 6, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(342850000, P_GPLL4, 3.5, 0, 0), + { } +}; + +static struct clk_rcg2 system_noc_bfdcd_clk_src = { + .cmd_rcgr = 0x2e004, + .freq_tbl = ftbl_system_noc_bfdcd_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "system_noc_bfdcd_clk_src", + .parent_data = gcc_xo_gpll0_gpll4, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4), + .flags = CLK_IS_CRITICAL, + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_q6ss_boot_clk = { + .halt_reg = 0x25080, + .halt_check = BRANCH_HALT_SKIP, + .clkr = { + .enable_reg = 0x25080, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6ss_boot_clk", + .parent_hws = (const struct clk_hw *[]) { + &system_noc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_snoc_clk = { + .halt_reg = 0x17028, + .clkr = { + .enable_reg = 0x17028, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_snoc_clk", + .parent_hws = (const struct clk_hw *[]) { + &system_noc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_snoc_1_clk = { + .halt_reg = 0x1707c, + .clkr = { + .enable_reg = 0x1707c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_snoc_1_clk", + .parent_hws = (const struct clk_hw *[]) { + &system_noc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_etr_usb_clk = { + .halt_reg = 0x2d060, + .clkr = { + .enable_reg = 0x2d060, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_etr_usb_clk", + .parent_hws = (const struct clk_hw *[]) { + &system_noc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_wcss_ahb_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(133333333, P_GPLL0, 6, 0, 0), + { } +}; + +static struct clk_rcg2 wcss_ahb_clk_src = { + .cmd_rcgr = 0x25030, + .freq_tbl = ftbl_wcss_ahb_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "wcss_ahb_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_q6_ahb_clk = { + .halt_reg = 0x25014, + .clkr = { + .enable_reg = 0x25014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6_ahb_s_clk = { + .halt_reg = 0x25018, + .clkr = { + .enable_reg = 0x25018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6_ahb_s_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_ecahb_clk = { + .halt_reg = 0x25058, + .clkr = { + .enable_reg = 0x25058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_ecahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_acmt_clk = { + .halt_reg = 0x2505c, + .clkr = { + .enable_reg = 0x2505c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_acmt_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_wcss_ahb_clk = { + .halt_reg = 0x2e030, + .clkr = { + .enable_reg = 0x2e030, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sys_noc_wcss_ahb_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_ahb_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_wcss_axi_m_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(133333333, P_GPLL0, 6, 0, 0), + F(266666667, P_GPLL0, 3, 0, 0), + { } +}; + +static struct clk_rcg2 wcss_axi_m_clk_src = { + .cmd_rcgr = 0x25078, + .freq_tbl = ftbl_wcss_axi_m_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "wcss_axi_m_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_anoc_wcss_axi_m_clk = { + .halt_reg = 0x2e0a8, + .clkr = { + .enable_reg = 0x2e0a8, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_anoc_wcss_axi_m_clk", + .parent_hws = (const struct clk_hw *[]) { + &wcss_axi_m_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_qdss_at_clk_src[] = { + F(240000000, P_GPLL4, 5, 0, 0), + { } +}; + +static struct clk_rcg2 qdss_at_clk_src = { + .cmd_rcgr = 0x2d004, + .freq_tbl = ftbl_qdss_at_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll4_gpll0_gpll0_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "qdss_at_clk_src", + .parent_data = gcc_xo_gpll4_gpll0_gpll0_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll4_gpll0_gpll0_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_q6ss_atbm_clk = { + .halt_reg = 0x2501c, + .clkr = { + .enable_reg = 0x2501c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6ss_atbm_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_atb_clk = { + .halt_reg = 0x2503c, + .clkr = { + .enable_reg = 0x2503c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_atb_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_atb_clk = { + .halt_reg = 0x17014, + .clkr = { + .enable_reg = 0x17014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_atb_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_at_clk = { + .halt_reg = 0x2d038, + .clkr = { + .enable_reg = 0x2d038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_at_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_at_clk = { + .halt_reg = 0x2e038, + .clkr = { + .enable_reg = 0x2e038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sys_noc_at_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_pcnoc_at_clk = { + .halt_reg = 0x31024, + .clkr = { + .enable_reg = 0x31024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_pcnoc_at_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor gcc_eud_at_div_clk_src = { + .mult = 1, + .div = 6, + .hw.init = &(struct clk_init_data) { + .name = "gcc_eud_at_div_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_at_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_usb0_eud_at_clk = { + .halt_reg = 0x30004, + .clkr = { + .enable_reg = 0x30004, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_usb0_eud_at_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_eud_at_div_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_eud_at_clk = { + .halt_reg = 0x2d06c, + .clkr = { + .enable_reg = 0x2d06c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_eud_at_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_eud_at_div_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_qdss_stm_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 qdss_stm_clk_src = { + .cmd_rcgr = 0x2d00c, + .freq_tbl = ftbl_qdss_stm_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "qdss_stm_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_out_main_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_out_main_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_qdss_stm_clk = { + .halt_reg = 0x2d03c, + .clkr = { + .enable_reg = 0x2d03c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_stm_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_stm_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_sys_noc_qdss_stm_axi_clk = { + .halt_reg = 0x2e034, + .clkr = { + .enable_reg = 0x2e034, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_sys_noc_qdss_stm_axi_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_stm_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_qdss_traceclkin_clk_src[] = { + F(300000000, P_GPLL4, 4, 0, 0), + { } +}; + +static struct clk_rcg2 qdss_traceclkin_clk_src = { + .cmd_rcgr = 0x2d014, + .freq_tbl = ftbl_qdss_traceclkin_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll4_gpll0_gpll0_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "qdss_traceclkin_clk_src", + .parent_data = gcc_xo_gpll4_gpll0_gpll0_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll4_gpll0_gpll0_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_qdss_traceclkin_clk = { + .halt_reg = 0x2d040, + .clkr = { + .enable_reg = 0x2d040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_traceclkin_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_traceclkin_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_qdss_tsctr_clk_src[] = { + F(600000000, P_GPLL4, 2, 0, 0), + { } +}; + +static struct clk_rcg2 qdss_tsctr_clk_src = { + .cmd_rcgr = 0x2d01c, + .freq_tbl = ftbl_qdss_tsctr_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll4_gpll0_gpll0_div2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "qdss_tsctr_clk_src", + .parent_data = gcc_xo_gpll4_gpll0_gpll0_div2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll4_gpll0_gpll0_div2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_fixed_factor qdss_tsctr_div2_clk_src = { + .mult = 1, + .div = 2, + .hw.init = &(struct clk_init_data) { + .name = "qdss_tsctr_div2_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_q6_tsctr_1to2_clk = { + .halt_reg = 0x25020, + .clkr = { + .enable_reg = 0x25020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6_tsctr_1to2_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div2_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_nts_clk = { + .halt_reg = 0x25040, + .clkr = { + .enable_reg = 0x25040, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_nts_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div2_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_tsctr_div2_clk = { + .halt_reg = 0x2d044, + .clkr = { + .enable_reg = 0x2d044, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div2_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div2_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_uniphy_sys_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 uniphy_sys_clk_src = { + .cmd_rcgr = 0x17090, + .freq_tbl = ftbl_uniphy_sys_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "uniphy_sys_clk_src", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 nss_ts_clk_src = { + .cmd_rcgr = 0x17088, + .freq_tbl = ftbl_uniphy_sys_clk_src, + .mnd_width = 8, + .hid_width = 5, + .parent_map = gcc_xo_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "nss_ts_clk_src", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_qdss_ts_clk = { + .halt_reg = 0x2d078, + .clkr = { + .enable_reg = 0x2d078, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_ts_clk", + .parent_hws = (const struct clk_hw *[]) { + &nss_ts_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor qdss_dap_sync_clk_src = { + .mult = 1, + .div = 4, + .hw.init = &(struct clk_init_data) { + .name = "qdss_dap_sync_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_clk_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_qdss_tsctr_div4_clk = { + .halt_reg = 0x2d04c, + .clkr = { + .enable_reg = 0x2d04c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div4_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor qdss_tsctr_div8_clk_src = { + .mult = 1, + .div = 8, + .hw.init = &(struct clk_init_data) { + .name = "qdss_tsctr_div8_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_clk_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_nss_ts_clk = { + .halt_reg = 0x17018, + .clkr = { + .enable_reg = 0x17018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nss_ts_clk", + .parent_hws = (const struct clk_hw *[]) { + &nss_ts_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_tsctr_div8_clk = { + .halt_reg = 0x2d050, + .clkr = { + .enable_reg = 0x2d050, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div8_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div8_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor qdss_tsctr_div16_clk_src = { + .mult = 1, + .div = 16, + .hw.init = &(struct clk_init_data) { + .name = "qdss_tsctr_div16_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_clk_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_qdss_tsctr_div16_clk = { + .halt_reg = 0x2d054, + .clkr = { + .enable_reg = 0x2d054, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div16_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div16_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6ss_pclkdbg_clk = { + .halt_reg = 0x25024, + .clkr = { + .enable_reg = 0x25024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6ss_pclkdbg_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_q6ss_trig_clk = { + .halt_reg = 0x25068, + .clkr = { + .enable_reg = 0x25068, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6ss_trig_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_apb_clk = { + .halt_reg = 0x25038, + .clkr = { + .enable_reg = 0x25038, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_apb_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_dbg_ifc_dapbus_clk = { + .halt_reg = 0x25044, + .clkr = { + .enable_reg = 0x25044, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_dbg_ifc_dapbus_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_dap_clk = { + .halt_reg = 0x2d058, + .clkr = { + .enable_reg = 0x2d058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_dap_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_qdss_apb2jtag_clk = { + .halt_reg = 0x2d05c, + .clkr = { + .enable_reg = 0x2d05c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_apb2jtag_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_dap_sync_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor qdss_tsctr_div3_clk_src = { + .mult = 1, + .div = 3, + .hw.init = &(struct clk_init_data) { + .name = "qdss_tsctr_div3_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_clk_src.clkr.hw + }, + .num_parents = 1, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_qdss_tsctr_div3_clk = { + .halt_reg = 0x2d048, + .clkr = { + .enable_reg = 0x2d048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_qdss_tsctr_div3_clk", + .parent_hws = (const struct clk_hw *[]) { + &qdss_tsctr_div3_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_qpic_io_macro_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + F(320000000, P_GPLL0, 2.5, 0, 0), + F(400000000, P_GPLL0, 2, 0, 0), + { } +}; + +static struct clk_rcg2 qpic_io_macro_clk_src = { + .cmd_rcgr = 0x32004, + .freq_tbl = ftbl_qpic_io_macro_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "qpic_io_macro_clk_src", + .parent_data = gcc_xo_gpll0_gpll2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_qpic_io_macro_clk = { + .halt_reg = 0x3200c, + .clkr = { + .enable_reg = 0x3200c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data){ + .name = "gcc_qpic_io_macro_clk", + .parent_hws = (const struct clk_hw *[]){ + &qpic_io_macro_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_q6_axi_clk_src[] = { + F(533333333, P_GPLL0, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 q6_axi_clk_src = { + .cmd_rcgr = 0x25004, + .freq_tbl = ftbl_q6_axi_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll2_gpll4_pi_sleep_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "q6_axi_clk_src", + .parent_data = gcc_xo_gpll0_gpll2_gpll4_pi_sleep, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll2_gpll4_pi_sleep), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_q6_axim_clk = { + .halt_reg = 0x2500c, + .clkr = { + .enable_reg = 0x2500c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_q6_axim_clk", + .parent_hws = (const struct clk_hw *[]) { + &q6_axi_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_wcss_q6_tbu_clk = { + .halt_reg = 0x12050, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0xb00c, + .enable_mask = BIT(6), + .hw.init = &(struct clk_init_data) { + .name = "gcc_wcss_q6_tbu_clk", + .parent_hws = (const struct clk_hw *[]) { + &q6_axi_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_q6_axi_clk = { + .halt_reg = 0x19010, + .clkr = { + .enable_reg = 0x19010, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mem_noc_q6_axi_clk", + .parent_hws = (const struct clk_hw *[]) { + &q6_axi_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_q6_axim2_clk_src[] = { + F(342857143, P_GPLL4, 3.5, 0, 0), + { } +}; + +static const struct parent_map gcc_xo_gpll0_gpll4_bias_pll_ubinc_clk_map[] = { + { P_XO, 0 }, + { P_GPLL0, 1 }, + { P_GPLL4, 2 }, + { P_BIAS_PLL_UBI_NC_CLK, 4 }, +}; + +static struct clk_rcg2 q6_axim2_clk_src = { + .cmd_rcgr = 0x25028, + .freq_tbl = ftbl_q6_axim2_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll4_bias_pll_ubinc_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "q6_axim2_clk_src", + .parent_data = gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll4_bias_pll_ubi_nc_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_nssnoc_memnoc_bfdcd_clk_src[] = { + F(533333333, P_GPLL0, 1.5, 0, 0), + { } +}; + +static struct clk_rcg2 nssnoc_memnoc_bfdcd_clk_src = { + .cmd_rcgr = 0x17004, + .freq_tbl = ftbl_nssnoc_memnoc_bfdcd_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_aux_gpll2_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "nssnoc_memnoc_bfdcd_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_aux_gpll2, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_aux_gpll2), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_nssnoc_memnoc_clk = { + .halt_reg = 0x17024, + .clkr = { + .enable_reg = 0x17024, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_memnoc_clk", + .parent_hws = (const struct clk_hw *[]) { + &nssnoc_memnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_mem_noc_1_clk = { + .halt_reg = 0x17084, + .clkr = { + .enable_reg = 0x17084, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_mem_noc_1_clk", + .parent_hws = (const struct clk_hw *[]) { + &nssnoc_memnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nss_tbu_clk = { + .halt_reg = 0x12040, + .clkr = { + .enable_reg = 0xb00c, + .enable_mask = BIT(4), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nss_tbu_clk", + .parent_hws = (const struct clk_hw *[]) { + &nssnoc_memnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_mem_noc_nssnoc_clk = { + .halt_reg = 0x19014, + .clkr = { + .enable_reg = 0x19014, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_mem_noc_nssnoc_clk", + .parent_hws = (const struct clk_hw *[]) { + &nssnoc_memnoc_bfdcd_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_lpass_axim_clk_src[] = { + F(133333333, P_GPLL0, 6, 0, 0), + { } +}; + +static struct clk_rcg2 lpass_axim_clk_src = { + .cmd_rcgr = 0x2700c, + .freq_tbl = ftbl_lpass_axim_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "lpass_axim_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 lpass_sway_clk_src = { + .cmd_rcgr = 0x27004, + .freq_tbl = ftbl_lpass_axim_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "lpass_sway_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_adss_pwm_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(100000000, P_GPLL0, 8, 0, 0), + { } +}; + +static struct clk_rcg2 adss_pwm_clk_src = { + .cmd_rcgr = 0x1c004, + .freq_tbl = ftbl_adss_pwm_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "adss_pwm_clk_src", + .parent_data = gcc_xo_gpll0, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_adss_pwm_clk = { + .halt_reg = 0x1c00c, + .clkr = { + .enable_reg = 0x1c00c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_adss_pwm_clk", + .parent_hws = (const struct clk_hw *[]) { + &adss_pwm_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static const struct freq_tbl ftbl_gp1_clk_src[] = { + F(24000000, P_XO, 1, 0, 0), + F(200000000, P_GPLL0, 4, 0, 0), + { } +}; + +static struct clk_rcg2 gp1_clk_src = { + .cmd_rcgr = 0x8004, + .freq_tbl = ftbl_gp1_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_sleep_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp1_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_sleep_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_sleep_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gp2_clk_src = { + .cmd_rcgr = 0x9004, + .freq_tbl = ftbl_gp1_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_sleep_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp2_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_sleep_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_sleep_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_rcg2 gp3_clk_src = { + .cmd_rcgr = 0xa004, + .freq_tbl = ftbl_gp1_clk_src, + .hid_width = 5, + .parent_map = gcc_xo_gpll0_gpll0_sleep_clk_map, + .clkr.hw.init = &(struct clk_init_data) { + .name = "gp3_clk_src", + .parent_data = gcc_xo_gpll0_gpll0_sleep_clk, + .num_parents = ARRAY_SIZE(gcc_xo_gpll0_gpll0_sleep_clk), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_branch gcc_xo_clk_src = { + .halt_reg = 0x34004, + .clkr = { + .enable_reg = 0x34004, + .enable_mask = BIT(1), + .hw.init = &(struct clk_init_data) { + .name = "gcc_xo_clk_src", + .parent_data = gcc_xo_data, + .num_parents = ARRAY_SIZE(gcc_xo_data), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_xo_dcd_clk = { + .halt_reg = 0x17074, + .clkr = { + .enable_reg = 0x17074, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_xo_dcd_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_xo_clk = { + .halt_reg = 0x34018, + .clkr = { + .enable_reg = 0x34018, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_xo_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy0_sys_clk = { + .halt_reg = 0x17048, + .clkr = { + .enable_reg = 0x17048, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy0_sys_clk", + .parent_hws = (const struct clk_hw *[]) { + &uniphy_sys_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy1_sys_clk = { + .halt_reg = 0x17058, + .clkr = { + .enable_reg = 0x17058, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy1_sys_clk", + .parent_hws = (const struct clk_hw *[]) { + &uniphy_sys_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_uniphy2_sys_clk = { + .halt_reg = 0x17068, + .clkr = { + .enable_reg = 0x17068, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_uniphy2_sys_clk", + .parent_hws = (const struct clk_hw *[]) { + &uniphy_sys_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_cmn_12gpll_sys_clk = { + .halt_reg = 0x3a008, + .clkr = { + .enable_reg = 0x3a008, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_cmn_12gpll_sys_clk", + .parent_hws = (const struct clk_hw *[]) { + &uniphy_sys_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_fixed_factor gcc_xo_div4_clk_src = { + .mult = 1, + .div = 4, + .hw.init = &(struct clk_init_data) { + .name = "gcc_xo_div4_clk_src", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_clk_src.clkr.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_fixed_factor_ops, + }, +}; + +static struct clk_branch gcc_nssnoc_qosgen_ref_clk = { + .halt_reg = 0x1701c, + .clkr = { + .enable_reg = 0x1701c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_qosgen_ref_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_div4_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_nssnoc_timeout_ref_clk = { + .halt_reg = 0x17020, + .clkr = { + .enable_reg = 0x17020, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_nssnoc_timeout_ref_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_div4_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gcc_xo_div4_clk = { + .halt_reg = 0x3401c, + .clkr = { + .enable_reg = 0x3401c, + .enable_mask = BIT(0), + .hw.init = &(struct clk_init_data) { + .name = "gcc_xo_div4_clk", + .parent_hws = (const struct clk_hw *[]) { + &gcc_xo_div4_clk_src.hw + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_hw *gcc_ipq9574_hws[] = { + &gpll0_out_main_div2.hw, + &gcc_xo_div4_clk_src.hw, + &qdss_dap_sync_clk_src.hw, + &qdss_tsctr_div2_clk_src.hw, + &qdss_tsctr_div8_clk_src.hw, + &qdss_tsctr_div16_clk_src.hw, + &qdss_tsctr_div3_clk_src.hw, + &gcc_eud_at_div_clk_src.hw, +}; + +static struct clk_regmap *gcc_ipq9574_clks[] = { + [GPLL0_MAIN] = &gpll0_main.clkr, + [GPLL0] = &gpll0.clkr, + [GPLL4_MAIN] = &gpll4_main.clkr, + [GPLL4] = &gpll4.clkr, + [GPLL2_MAIN] = &gpll2_main.clkr, + [GPLL2] = &gpll2.clkr, + [GCC_SLEEP_CLK_SRC] = &gcc_sleep_clk_src.clkr, + [APSS_AHB_CLK_SRC] = &apss_ahb_clk_src.clkr, + [APSS_AXI_CLK_SRC] = &apss_axi_clk_src.clkr, + [BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr, + [BLSP1_QUP1_SPI_APPS_CLK_SRC] = &blsp1_qup1_spi_apps_clk_src.clkr, + [BLSP1_QUP2_I2C_APPS_CLK_SRC] = &blsp1_qup2_i2c_apps_clk_src.clkr, + [BLSP1_QUP2_SPI_APPS_CLK_SRC] = &blsp1_qup2_spi_apps_clk_src.clkr, + [BLSP1_QUP3_I2C_APPS_CLK_SRC] = &blsp1_qup3_i2c_apps_clk_src.clkr, + [BLSP1_QUP3_SPI_APPS_CLK_SRC] = &blsp1_qup3_spi_apps_clk_src.clkr, + [BLSP1_QUP4_I2C_APPS_CLK_SRC] = &blsp1_qup4_i2c_apps_clk_src.clkr, + [BLSP1_QUP4_SPI_APPS_CLK_SRC] = &blsp1_qup4_spi_apps_clk_src.clkr, + [BLSP1_QUP5_I2C_APPS_CLK_SRC] = &blsp1_qup5_i2c_apps_clk_src.clkr, + [BLSP1_QUP5_SPI_APPS_CLK_SRC] = &blsp1_qup5_spi_apps_clk_src.clkr, + [BLSP1_QUP6_I2C_APPS_CLK_SRC] = &blsp1_qup6_i2c_apps_clk_src.clkr, + [BLSP1_QUP6_SPI_APPS_CLK_SRC] = &blsp1_qup6_spi_apps_clk_src.clkr, + [BLSP1_UART1_APPS_CLK_SRC] = &blsp1_uart1_apps_clk_src.clkr, + [BLSP1_UART2_APPS_CLK_SRC] = &blsp1_uart2_apps_clk_src.clkr, + [BLSP1_UART3_APPS_CLK_SRC] = &blsp1_uart3_apps_clk_src.clkr, + [BLSP1_UART4_APPS_CLK_SRC] = &blsp1_uart4_apps_clk_src.clkr, + [BLSP1_UART5_APPS_CLK_SRC] = &blsp1_uart5_apps_clk_src.clkr, + [BLSP1_UART6_APPS_CLK_SRC] = &blsp1_uart6_apps_clk_src.clkr, + [GCC_APSS_AHB_CLK] = &gcc_apss_ahb_clk.clkr, + [GCC_APSS_AXI_CLK] = &gcc_apss_axi_clk.clkr, + [GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr, + [GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr, + [GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr, + [GCC_BLSP1_QUP4_I2C_APPS_CLK] = &gcc_blsp1_qup4_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP4_SPI_APPS_CLK] = &gcc_blsp1_qup4_spi_apps_clk.clkr, + [GCC_BLSP1_QUP5_I2C_APPS_CLK] = &gcc_blsp1_qup5_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP5_SPI_APPS_CLK] = &gcc_blsp1_qup5_spi_apps_clk.clkr, + [GCC_BLSP1_QUP6_I2C_APPS_CLK] = &gcc_blsp1_qup6_i2c_apps_clk.clkr, + [GCC_BLSP1_QUP6_SPI_APPS_CLK] = &gcc_blsp1_qup6_spi_apps_clk.clkr, + [GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr, + [GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr, + [GCC_BLSP1_UART3_APPS_CLK] = &gcc_blsp1_uart3_apps_clk.clkr, + [GCC_BLSP1_UART4_APPS_CLK] = &gcc_blsp1_uart4_apps_clk.clkr, + [GCC_BLSP1_UART5_APPS_CLK] = &gcc_blsp1_uart5_apps_clk.clkr, + [GCC_BLSP1_UART6_APPS_CLK] = &gcc_blsp1_uart6_apps_clk.clkr, + [PCIE0_AXI_M_CLK_SRC] = &pcie0_axi_m_clk_src.clkr, + [GCC_PCIE0_AXI_M_CLK] = &gcc_pcie0_axi_m_clk.clkr, + [PCIE1_AXI_M_CLK_SRC] = &pcie1_axi_m_clk_src.clkr, + [GCC_PCIE1_AXI_M_CLK] = &gcc_pcie1_axi_m_clk.clkr, + [PCIE2_AXI_M_CLK_SRC] = &pcie2_axi_m_clk_src.clkr, + [GCC_PCIE2_AXI_M_CLK] = &gcc_pcie2_axi_m_clk.clkr, + [PCIE3_AXI_M_CLK_SRC] = &pcie3_axi_m_clk_src.clkr, + [GCC_PCIE3_AXI_M_CLK] = &gcc_pcie3_axi_m_clk.clkr, + [PCIE0_AXI_S_CLK_SRC] = &pcie0_axi_s_clk_src.clkr, + [GCC_PCIE0_AXI_S_BRIDGE_CLK] = &gcc_pcie0_axi_s_bridge_clk.clkr, + [GCC_PCIE0_AXI_S_CLK] = &gcc_pcie0_axi_s_clk.clkr, + [PCIE1_AXI_S_CLK_SRC] = &pcie1_axi_s_clk_src.clkr, + [GCC_PCIE1_AXI_S_BRIDGE_CLK] = &gcc_pcie1_axi_s_bridge_clk.clkr, + [GCC_PCIE1_AXI_S_CLK] = &gcc_pcie1_axi_s_clk.clkr, + [PCIE2_AXI_S_CLK_SRC] = &pcie2_axi_s_clk_src.clkr, + [GCC_PCIE2_AXI_S_BRIDGE_CLK] = &gcc_pcie2_axi_s_bridge_clk.clkr, + [GCC_PCIE2_AXI_S_CLK] = &gcc_pcie2_axi_s_clk.clkr, + [PCIE3_AXI_S_CLK_SRC] = &pcie3_axi_s_clk_src.clkr, + [GCC_PCIE3_AXI_S_BRIDGE_CLK] = &gcc_pcie3_axi_s_bridge_clk.clkr, + [GCC_PCIE3_AXI_S_CLK] = &gcc_pcie3_axi_s_clk.clkr, + [PCIE0_PIPE_CLK_SRC] = &pcie0_pipe_clk_src.clkr, + [PCIE1_PIPE_CLK_SRC] = &pcie1_pipe_clk_src.clkr, + [PCIE2_PIPE_CLK_SRC] = &pcie2_pipe_clk_src.clkr, + [PCIE3_PIPE_CLK_SRC] = &pcie3_pipe_clk_src.clkr, + [PCIE_AUX_CLK_SRC] = &pcie_aux_clk_src.clkr, + [GCC_PCIE0_AUX_CLK] = &gcc_pcie0_aux_clk.clkr, + [GCC_PCIE1_AUX_CLK] = &gcc_pcie1_aux_clk.clkr, + [GCC_PCIE2_AUX_CLK] = &gcc_pcie2_aux_clk.clkr, + [GCC_PCIE3_AUX_CLK] = &gcc_pcie3_aux_clk.clkr, + [PCIE0_RCHNG_CLK_SRC] = &pcie0_rchng_clk_src.clkr, + [GCC_PCIE0_RCHNG_CLK] = &gcc_pcie0_rchng_clk.clkr, + [PCIE1_RCHNG_CLK_SRC] = &pcie1_rchng_clk_src.clkr, + [GCC_PCIE1_RCHNG_CLK] = &gcc_pcie1_rchng_clk.clkr, + [PCIE2_RCHNG_CLK_SRC] = &pcie2_rchng_clk_src.clkr, + [GCC_PCIE2_RCHNG_CLK] = &gcc_pcie2_rchng_clk.clkr, + [PCIE3_RCHNG_CLK_SRC] = &pcie3_rchng_clk_src.clkr, + [GCC_PCIE3_RCHNG_CLK] = &gcc_pcie3_rchng_clk.clkr, + [GCC_PCIE0_AHB_CLK] = &gcc_pcie0_ahb_clk.clkr, + [GCC_PCIE1_AHB_CLK] = &gcc_pcie1_ahb_clk.clkr, + [GCC_PCIE2_AHB_CLK] = &gcc_pcie2_ahb_clk.clkr, + [GCC_PCIE3_AHB_CLK] = &gcc_pcie3_ahb_clk.clkr, + [USB0_AUX_CLK_SRC] = &usb0_aux_clk_src.clkr, + [GCC_USB0_AUX_CLK] = &gcc_usb0_aux_clk.clkr, + [USB0_MASTER_CLK_SRC] = &usb0_master_clk_src.clkr, + [GCC_USB0_MASTER_CLK] = &gcc_usb0_master_clk.clkr, + [GCC_SNOC_USB_CLK] = &gcc_snoc_usb_clk.clkr, + [GCC_ANOC_USB_AXI_CLK] = &gcc_anoc_usb_axi_clk.clkr, + [USB0_MOCK_UTMI_CLK_SRC] = &usb0_mock_utmi_clk_src.clkr, + [USB0_MOCK_UTMI_DIV_CLK_SRC] = &usb0_mock_utmi_div_clk_src.clkr, + [GCC_USB0_MOCK_UTMI_CLK] = &gcc_usb0_mock_utmi_clk.clkr, + [USB0_PIPE_CLK_SRC] = &usb0_pipe_clk_src.clkr, + [GCC_USB0_PHY_CFG_AHB_CLK] = &gcc_usb0_phy_cfg_ahb_clk.clkr, + [SDCC1_APPS_CLK_SRC] = &sdcc1_apps_clk_src.clkr, + [GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr, + [SDCC1_ICE_CORE_CLK_SRC] = &sdcc1_ice_core_clk_src.clkr, + [GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr, + [GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr, + [PCNOC_BFDCD_CLK_SRC] = &pcnoc_bfdcd_clk_src.clkr, + [GCC_NSSCFG_CLK] = &gcc_nsscfg_clk.clkr, + [GCC_NSSNOC_NSSCC_CLK] = &gcc_nssnoc_nsscc_clk.clkr, + [GCC_NSSCC_CLK] = &gcc_nsscc_clk.clkr, + [GCC_NSSNOC_PCNOC_1_CLK] = &gcc_nssnoc_pcnoc_1_clk.clkr, + [GCC_QDSS_DAP_AHB_CLK] = &gcc_qdss_dap_ahb_clk.clkr, + [GCC_QDSS_CFG_AHB_CLK] = &gcc_qdss_cfg_ahb_clk.clkr, + [GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr, + [GCC_QPIC_CLK] = &gcc_qpic_clk.clkr, + [GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr, + [GCC_MDIO_AHB_CLK] = &gcc_mdio_ahb_clk.clkr, + [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + [GCC_UNIPHY0_AHB_CLK] = &gcc_uniphy0_ahb_clk.clkr, + [GCC_UNIPHY1_AHB_CLK] = &gcc_uniphy1_ahb_clk.clkr, + [GCC_UNIPHY2_AHB_CLK] = &gcc_uniphy2_ahb_clk.clkr, + [GCC_CMN_12GPLL_AHB_CLK] = &gcc_cmn_12gpll_ahb_clk.clkr, + [GCC_CMN_12GPLL_APU_CLK] = &gcc_cmn_12gpll_apu_clk.clkr, + [SYSTEM_NOC_BFDCD_CLK_SRC] = &system_noc_bfdcd_clk_src.clkr, + [GCC_NSSNOC_SNOC_CLK] = &gcc_nssnoc_snoc_clk.clkr, + [GCC_NSSNOC_SNOC_1_CLK] = &gcc_nssnoc_snoc_1_clk.clkr, + [GCC_QDSS_ETR_USB_CLK] = &gcc_qdss_etr_usb_clk.clkr, + [WCSS_AHB_CLK_SRC] = &wcss_ahb_clk_src.clkr, + [GCC_Q6_AHB_CLK] = &gcc_q6_ahb_clk.clkr, + [GCC_Q6_AHB_S_CLK] = &gcc_q6_ahb_s_clk.clkr, + [GCC_WCSS_ECAHB_CLK] = &gcc_wcss_ecahb_clk.clkr, + [GCC_WCSS_ACMT_CLK] = &gcc_wcss_acmt_clk.clkr, + [GCC_SYS_NOC_WCSS_AHB_CLK] = &gcc_sys_noc_wcss_ahb_clk.clkr, + [WCSS_AXI_M_CLK_SRC] = &wcss_axi_m_clk_src.clkr, + [GCC_ANOC_WCSS_AXI_M_CLK] = &gcc_anoc_wcss_axi_m_clk.clkr, + [QDSS_AT_CLK_SRC] = &qdss_at_clk_src.clkr, + [GCC_Q6SS_ATBM_CLK] = &gcc_q6ss_atbm_clk.clkr, + [GCC_WCSS_DBG_IFC_ATB_CLK] = &gcc_wcss_dbg_ifc_atb_clk.clkr, + [GCC_NSSNOC_ATB_CLK] = &gcc_nssnoc_atb_clk.clkr, + [GCC_QDSS_AT_CLK] = &gcc_qdss_at_clk.clkr, + [GCC_SYS_NOC_AT_CLK] = &gcc_sys_noc_at_clk.clkr, + [GCC_PCNOC_AT_CLK] = &gcc_pcnoc_at_clk.clkr, + [GCC_USB0_EUD_AT_CLK] = &gcc_usb0_eud_at_clk.clkr, + [GCC_QDSS_EUD_AT_CLK] = &gcc_qdss_eud_at_clk.clkr, + [QDSS_STM_CLK_SRC] = &qdss_stm_clk_src.clkr, + [GCC_QDSS_STM_CLK] = &gcc_qdss_stm_clk.clkr, + [GCC_SYS_NOC_QDSS_STM_AXI_CLK] = &gcc_sys_noc_qdss_stm_axi_clk.clkr, + [QDSS_TRACECLKIN_CLK_SRC] = &qdss_traceclkin_clk_src.clkr, + [GCC_QDSS_TRACECLKIN_CLK] = &gcc_qdss_traceclkin_clk.clkr, + [QDSS_TSCTR_CLK_SRC] = &qdss_tsctr_clk_src.clkr, + [GCC_Q6_TSCTR_1TO2_CLK] = &gcc_q6_tsctr_1to2_clk.clkr, + [GCC_WCSS_DBG_IFC_NTS_CLK] = &gcc_wcss_dbg_ifc_nts_clk.clkr, + [GCC_QDSS_TSCTR_DIV2_CLK] = &gcc_qdss_tsctr_div2_clk.clkr, + [GCC_QDSS_TS_CLK] = &gcc_qdss_ts_clk.clkr, + [GCC_QDSS_TSCTR_DIV4_CLK] = &gcc_qdss_tsctr_div4_clk.clkr, + [GCC_NSS_TS_CLK] = &gcc_nss_ts_clk.clkr, + [GCC_QDSS_TSCTR_DIV8_CLK] = &gcc_qdss_tsctr_div8_clk.clkr, + [GCC_QDSS_TSCTR_DIV16_CLK] = &gcc_qdss_tsctr_div16_clk.clkr, + [GCC_Q6SS_PCLKDBG_CLK] = &gcc_q6ss_pclkdbg_clk.clkr, + [GCC_Q6SS_TRIG_CLK] = &gcc_q6ss_trig_clk.clkr, + [GCC_WCSS_DBG_IFC_APB_CLK] = &gcc_wcss_dbg_ifc_apb_clk.clkr, + [GCC_WCSS_DBG_IFC_DAPBUS_CLK] = &gcc_wcss_dbg_ifc_dapbus_clk.clkr, + [GCC_QDSS_DAP_CLK] = &gcc_qdss_dap_clk.clkr, + [GCC_QDSS_APB2JTAG_CLK] = &gcc_qdss_apb2jtag_clk.clkr, + [GCC_QDSS_TSCTR_DIV3_CLK] = &gcc_qdss_tsctr_div3_clk.clkr, + [QPIC_IO_MACRO_CLK_SRC] = &qpic_io_macro_clk_src.clkr, + [GCC_QPIC_IO_MACRO_CLK] = &gcc_qpic_io_macro_clk.clkr, + [Q6_AXI_CLK_SRC] = &q6_axi_clk_src.clkr, + [GCC_Q6_AXIM_CLK] = &gcc_q6_axim_clk.clkr, + [GCC_WCSS_Q6_TBU_CLK] = &gcc_wcss_q6_tbu_clk.clkr, + [GCC_MEM_NOC_Q6_AXI_CLK] = &gcc_mem_noc_q6_axi_clk.clkr, + [Q6_AXIM2_CLK_SRC] = &q6_axim2_clk_src.clkr, + [NSSNOC_MEMNOC_BFDCD_CLK_SRC] = &nssnoc_memnoc_bfdcd_clk_src.clkr, + [GCC_NSSNOC_MEMNOC_CLK] = &gcc_nssnoc_memnoc_clk.clkr, + [GCC_NSSNOC_MEM_NOC_1_CLK] = &gcc_nssnoc_mem_noc_1_clk.clkr, + [GCC_NSS_TBU_CLK] = &gcc_nss_tbu_clk.clkr, + [GCC_MEM_NOC_NSSNOC_CLK] = &gcc_mem_noc_nssnoc_clk.clkr, + [LPASS_AXIM_CLK_SRC] = &lpass_axim_clk_src.clkr, + [LPASS_SWAY_CLK_SRC] = &lpass_sway_clk_src.clkr, + [ADSS_PWM_CLK_SRC] = &adss_pwm_clk_src.clkr, + [GCC_ADSS_PWM_CLK] = &gcc_adss_pwm_clk.clkr, + [GP1_CLK_SRC] = &gp1_clk_src.clkr, + [GP2_CLK_SRC] = &gp2_clk_src.clkr, + [GP3_CLK_SRC] = &gp3_clk_src.clkr, + [GCC_XO_CLK_SRC] = &gcc_xo_clk_src.clkr, + [GCC_NSSNOC_XO_DCD_CLK] = &gcc_nssnoc_xo_dcd_clk.clkr, + [GCC_XO_CLK] = &gcc_xo_clk.clkr, + [GCC_NSSNOC_QOSGEN_REF_CLK] = &gcc_nssnoc_qosgen_ref_clk.clkr, + [GCC_NSSNOC_TIMEOUT_REF_CLK] = &gcc_nssnoc_timeout_ref_clk.clkr, + [GCC_XO_DIV4_CLK] = &gcc_xo_div4_clk.clkr, + [GCC_UNIPHY0_SYS_CLK] = &gcc_uniphy0_sys_clk.clkr, + [GCC_UNIPHY1_SYS_CLK] = &gcc_uniphy1_sys_clk.clkr, + [GCC_UNIPHY2_SYS_CLK] = &gcc_uniphy2_sys_clk.clkr, + [GCC_CMN_12GPLL_SYS_CLK] = &gcc_cmn_12gpll_sys_clk.clkr, + [GCC_Q6SS_BOOT_CLK] = &gcc_q6ss_boot_clk.clkr, + [UNIPHY_SYS_CLK_SRC] = &uniphy_sys_clk_src.clkr, + [NSS_TS_CLK_SRC] = &nss_ts_clk_src.clkr, + [GCC_ANOC_PCIE0_1LANE_M_CLK] = &gcc_anoc_pcie0_1lane_m_clk.clkr, + [GCC_ANOC_PCIE1_1LANE_M_CLK] = &gcc_anoc_pcie1_1lane_m_clk.clkr, + [GCC_ANOC_PCIE2_2LANE_M_CLK] = &gcc_anoc_pcie2_2lane_m_clk.clkr, + [GCC_ANOC_PCIE3_2LANE_M_CLK] = &gcc_anoc_pcie3_2lane_m_clk.clkr, + [GCC_SNOC_PCIE0_1LANE_S_CLK] = &gcc_snoc_pcie0_1lane_s_clk.clkr, + [GCC_SNOC_PCIE1_1LANE_S_CLK] = &gcc_snoc_pcie1_1lane_s_clk.clkr, + [GCC_SNOC_PCIE2_2LANE_S_CLK] = &gcc_snoc_pcie2_2lane_s_clk.clkr, + [GCC_SNOC_PCIE3_2LANE_S_CLK] = &gcc_snoc_pcie3_2lane_s_clk.clkr, +}; + +static const struct qcom_reset_map gcc_ipq9574_resets[] = { + [GCC_ADSS_BCR] = { 0x1c000, 0 }, + [GCC_ANOC0_TBU_BCR] = { 0x1203c, 0 }, + [GCC_ANOC1_TBU_BCR] = { 0x1204c, 0 }, + [GCC_ANOC_BCR] = { 0x2e074, 0 }, + [GCC_APC0_VOLTAGE_DROOP_DETECTOR_BCR] = { 0x38000, 0 }, + [GCC_APSS_TCU_BCR] = { 0x12014, 0 }, + [GCC_BLSP1_BCR] = { 0x01000, 0 }, + [GCC_BLSP1_QUP1_BCR] = { 0x02000, 0 }, + [GCC_BLSP1_QUP2_BCR] = { 0x03000, 0 }, + [GCC_BLSP1_QUP3_BCR] = { 0x04000, 0 }, + [GCC_BLSP1_QUP4_BCR] = { 0x05000, 0 }, + [GCC_BLSP1_QUP5_BCR] = { 0x06000, 0 }, + [GCC_BLSP1_QUP6_BCR] = { 0x07000, 0 }, + [GCC_BLSP1_UART1_BCR] = { 0x02028, 0 }, + [GCC_BLSP1_UART2_BCR] = { 0x03028, 0 }, + [GCC_BLSP1_UART3_BCR] = { 0x04028, 0 }, + [GCC_BLSP1_UART4_BCR] = { 0x05028, 0 }, + [GCC_BLSP1_UART5_BCR] = { 0x06028, 0 }, + [GCC_BLSP1_UART6_BCR] = { 0x07028, 0 }, + [GCC_BOOT_ROM_BCR] = { 0x13028, 0 }, + [GCC_CMN_BLK_BCR] = { 0x3a000, 0 }, + [GCC_CMN_BLK_AHB_ARES] = { 0x3a010, 0 }, + [GCC_CMN_BLK_SYS_ARES] = { 0x3a010, 1 }, + [GCC_CMN_BLK_APU_ARES] = { 0x3a010, 2 }, + [GCC_DCC_BCR] = { 0x35000, 0 }, + [GCC_DDRSS_BCR] = { 0x11000, 0 }, + [GCC_IMEM_BCR] = { 0x0e000, 0 }, + [GCC_LPASS_BCR] = { 0x27000, 0 }, + [GCC_MDIO_BCR] = { 0x1703c, 0 }, + [GCC_MPM_BCR] = { 0x37000, 0 }, + [GCC_MSG_RAM_BCR] = { 0x26000, 0 }, + [GCC_NSS_BCR] = { 0x17000, 0 }, + [GCC_NSS_TBU_BCR] = { 0x12044, 0 }, + [GCC_NSSNOC_MEMNOC_1_ARES] = { 0x17038, 13 }, + [GCC_NSSNOC_PCNOC_1_ARES] = { 0x17038, 12 }, + [GCC_NSSNOC_SNOC_1_ARES] = { 0x17038, 11 }, + [GCC_NSSNOC_XO_DCD_ARES] = { 0x17038, 10 }, + [GCC_NSSNOC_TS_ARES] = { 0x17038, 9 }, + [GCC_NSSCC_ARES] = { 0x17038, 8 }, + [GCC_NSSNOC_NSSCC_ARES] = { 0x17038, 7 }, + [GCC_NSSNOC_ATB_ARES] = { 0x17038, 6 }, + [GCC_NSSNOC_MEMNOC_ARES] = { 0x17038, 5 }, + [GCC_NSSNOC_QOSGEN_REF_ARES] = { 0x17038, 4 }, + [GCC_NSSNOC_SNOC_ARES] = { 0x17038, 3 }, + [GCC_NSSNOC_TIMEOUT_REF_ARES] = { 0x17038, 2 }, + [GCC_NSS_CFG_ARES] = { 0x17038, 1 }, + [GCC_UBI0_DBG_ARES] = { 0x17038, 0 }, + [GCC_PCIE0PHY_PHY_BCR] = { 0x2805c, 0 }, + [GCC_PCIE0_AHB_ARES] = { 0x28058, 7 }, + [GCC_PCIE0_AUX_ARES] = { 0x28058, 6 }, + [GCC_PCIE0_AXI_M_ARES] = { 0x28058, 5 }, + [GCC_PCIE0_AXI_M_STICKY_ARES] = { 0x28058, 4 }, + [GCC_PCIE0_AXI_S_ARES] = { 0x28058, 3 }, + [GCC_PCIE0_AXI_S_STICKY_ARES] = { 0x28058, 2 }, + [GCC_PCIE0_CORE_STICKY_ARES] = { 0x28058, 1 }, + [GCC_PCIE0_PIPE_ARES] = { 0x28058, 0 }, + [GCC_PCIE1_AHB_ARES] = { 0x29058, 7 }, + [GCC_PCIE1_AUX_ARES] = { 0x29058, 6 }, + [GCC_PCIE1_AXI_M_ARES] = { 0x29058, 5 }, + [GCC_PCIE1_AXI_M_STICKY_ARES] = { 0x29058, 4 }, + [GCC_PCIE1_AXI_S_ARES] = { 0x29058, 3 }, + [GCC_PCIE1_AXI_S_STICKY_ARES] = { 0x29058, 2 }, + [GCC_PCIE1_CORE_STICKY_ARES] = { 0x29058, 1 }, + [GCC_PCIE1_PIPE_ARES] = { 0x29058, 0 }, + [GCC_PCIE2_AHB_ARES] = { 0x2a058, 7 }, + [GCC_PCIE2_AUX_ARES] = { 0x2a058, 6 }, + [GCC_PCIE2_AXI_M_ARES] = { 0x2a058, 5 }, + [GCC_PCIE2_AXI_M_STICKY_ARES] = { 0x2a058, 4 }, + [GCC_PCIE2_AXI_S_ARES] = { 0x2a058, 3 }, + [GCC_PCIE2_AXI_S_STICKY_ARES] = { 0x2a058, 2 }, + [GCC_PCIE2_CORE_STICKY_ARES] = { 0x2a058, 1 }, + [GCC_PCIE2_PIPE_ARES] = { 0x2a058, 0 }, + [GCC_PCIE3_AHB_ARES] = { 0x2b058, 7 }, + [GCC_PCIE3_AUX_ARES] = { 0x2b058, 6 }, + [GCC_PCIE3_AXI_M_ARES] = { 0x2b058, 5 }, + [GCC_PCIE3_AXI_M_STICKY_ARES] = { 0x2b058, 4 }, + [GCC_PCIE3_AXI_S_ARES] = { 0x2b058, 3 }, + [GCC_PCIE3_AXI_S_STICKY_ARES] = { 0x2b058, 2 }, + [GCC_PCIE3_CORE_STICKY_ARES] = { 0x2b058, 1 }, + [GCC_PCIE3_PIPE_ARES] = { 0x2b058, 0 }, + [GCC_PCIE0_BCR] = { 0x28000, 0 }, + [GCC_PCIE0_LINK_DOWN_BCR] = { 0x28054, 0 }, + [GCC_PCIE0_PHY_BCR] = { 0x28060, 0 }, + [GCC_PCIE1_BCR] = { 0x29000, 0 }, + [GCC_PCIE1_LINK_DOWN_BCR] = { 0x29054, 0 }, + [GCC_PCIE1_PHY_BCR] = { 0x29060, 0 }, + [GCC_PCIE1PHY_PHY_BCR] = { 0x2905c, 0 }, + [GCC_PCIE2_BCR] = { 0x2a000, 0 }, + [GCC_PCIE2_LINK_DOWN_BCR] = { 0x2a054, 0 }, + [GCC_PCIE2_PHY_BCR] = { 0x2a060, 0 }, + [GCC_PCIE2PHY_PHY_BCR] = { 0x2a05c, 0 }, + [GCC_PCIE3_BCR] = { 0x2b000, 0 }, + [GCC_PCIE3_LINK_DOWN_BCR] = { 0x2b054, 0 }, + [GCC_PCIE3PHY_PHY_BCR] = { 0x2b05c, 0 }, + [GCC_PCIE3_PHY_BCR] = { 0x2b060, 0 }, + [GCC_PCNOC_BCR] = { 0x31000, 0 }, + [GCC_PCNOC_BUS_TIMEOUT0_BCR] = { 0x31030, 0 }, + [GCC_PCNOC_BUS_TIMEOUT1_BCR] = { 0x31038, 0 }, + [GCC_PCNOC_BUS_TIMEOUT2_BCR] = { 0x31040, 0 }, + [GCC_PCNOC_BUS_TIMEOUT3_BCR] = { 0x31048, 0 }, + [GCC_PCNOC_BUS_TIMEOUT4_BCR] = { 0x31050, 0 }, + [GCC_PCNOC_BUS_TIMEOUT5_BCR] = { 0x31058, 0 }, + [GCC_PCNOC_BUS_TIMEOUT6_BCR] = { 0x31060, 0 }, + [GCC_PCNOC_BUS_TIMEOUT7_BCR] = { 0x31068, 0 }, + [GCC_PCNOC_BUS_TIMEOUT8_BCR] = { 0x31070, 0 }, + [GCC_PCNOC_BUS_TIMEOUT9_BCR] = { 0x31078, 0 }, + [GCC_PCNOC_TBU_BCR] = { 0x12034, 0 }, + [GCC_PRNG_BCR] = { 0x13020, 0 }, + [GCC_Q6SS_DBG_ARES] = { 0x2506c, 4 }, + [GCC_Q6_AHB_ARES] = { 0x2506c, 3 }, + [GCC_Q6_AHB_S_ARES] = { 0x2506c, 2 }, + [GCC_Q6_AXIM2_ARES] = { 0x2506c, 1 }, + [GCC_Q6_AXIM_ARES] = { 0x2506c, 0 }, + [GCC_QDSS_BCR] = { 0x2d000, 0 }, + [GCC_QPIC_BCR] = { 0x32000, 0 }, + [GCC_QPIC_AHB_ARES] = { 0x3201c, 1 }, + [GCC_QPIC_ARES] = { 0x3201c, 0 }, + [GCC_QUSB2_0_PHY_BCR] = { 0x2c068, 0 }, + [GCC_RBCPR_BCR] = { 0x39000, 0 }, + [GCC_RBCPR_MX_BCR] = { 0x39014, 0 }, + [GCC_SDCC_BCR] = { 0x33000, 0 }, + [GCC_SEC_CTRL_BCR] = { 0x1a000, 0 }, + [GCC_SMMU_CFG_BCR] = { 0x1202c, 0 }, + [GCC_SNOC_BCR] = { 0x2e000, 0 }, + [GCC_SPDM_BCR] = { 0x36000, 0 }, + [GCC_TCSR_BCR] = { 0x3d000, 0 }, + [GCC_TLMM_BCR] = { 0x3e000, 0 }, + [GCC_TME_BCR] = { 0x10000, 0 }, + [GCC_UNIPHY0_BCR] = { 0x17044, 0 }, + [GCC_UNIPHY0_SYS_RESET] = { 0x17050, 0 }, + [GCC_UNIPHY0_AHB_RESET] = { 0x17050, 1 }, + [GCC_UNIPHY0_XPCS_RESET] = { 0x17050, 2 }, + [GCC_UNIPHY1_SYS_RESET] = { 0x17060, 0 }, + [GCC_UNIPHY1_AHB_RESET] = { 0x17060, 1 }, + [GCC_UNIPHY1_XPCS_RESET] = { 0x17060, 2 }, + [GCC_UNIPHY2_SYS_RESET] = { 0x17070, 0 }, + [GCC_UNIPHY2_AHB_RESET] = { 0x17070, 1 }, + [GCC_UNIPHY2_XPCS_RESET] = { 0x17070, 2 }, + [GCC_UNIPHY1_BCR] = { 0x17054, 0 }, + [GCC_UNIPHY2_BCR] = { 0x17064, 0 }, + [GCC_USB0_PHY_BCR] = { 0x2c06c, 0 }, + [GCC_USB3PHY_0_PHY_BCR] = { 0x2c070, 0 }, + [GCC_USB_BCR] = { 0x2c000, 0 }, + [GCC_USB_MISC_RESET] = { 0x2c064, 0 }, + [GCC_WCSSAON_RESET] = { 0x25074, 0 }, + [GCC_WCSS_ACMT_ARES] = { 0x25070, 5 }, + [GCC_WCSS_AHB_S_ARES] = { 0x25070, 4 }, + [GCC_WCSS_AXI_M_ARES] = { 0x25070, 3 }, + [GCC_WCSS_BCR] = { 0x18004, 0 }, + [GCC_WCSS_DBG_ARES] = { 0x25070, 2 }, + [GCC_WCSS_DBG_BDG_ARES] = { 0x25070, 1 }, + [GCC_WCSS_ECAHB_ARES] = { 0x25070, 0 }, + [GCC_WCSS_Q6_BCR] = { 0x18000, 0 }, + [GCC_WCSS_Q6_TBU_BCR] = { 0x12054, 0 }, +}; + +static const struct of_device_id gcc_ipq9574_match_table[] = { + { .compatible = "qcom,ipq9574-gcc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gcc_ipq9574_match_table); + +static const struct regmap_config gcc_ipq9574_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x7fffc, + .fast_io = true, +}; + +static const struct qcom_cc_desc gcc_ipq9574_desc = { + .config = &gcc_ipq9574_regmap_config, + .clks = gcc_ipq9574_clks, + .num_clks = ARRAY_SIZE(gcc_ipq9574_clks), + .resets = gcc_ipq9574_resets, + .num_resets = ARRAY_SIZE(gcc_ipq9574_resets), + .clk_hws = gcc_ipq9574_hws, + .num_clk_hws = ARRAY_SIZE(gcc_ipq9574_hws), +}; + +static int gcc_ipq9574_probe(struct platform_device *pdev) +{ + return qcom_cc_probe(pdev, &gcc_ipq9574_desc); +} + +static struct platform_driver gcc_ipq9574_driver = { + .probe = gcc_ipq9574_probe, + .driver = { + .name = "qcom,gcc-ipq9574", + .of_match_table = gcc_ipq9574_match_table, + }, +}; + +static int __init gcc_ipq9574_init(void) +{ + return platform_driver_register(&gcc_ipq9574_driver); +} +core_initcall(gcc_ipq9574_init); + +static void __exit gcc_ipq9574_exit(void) +{ + platform_driver_unregister(&gcc_ipq9574_driver); +} +module_exit(gcc_ipq9574_exit); + +MODULE_DESCRIPTION("Qualcomm Technologies, Inc. GCC IPQ9574 Driver"); +MODULE_LICENSE("GPL"); -- GitLab From 528bd42615f4bb564613cc76dead90d7fbae76ba Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Fri, 7 Apr 2023 11:18:26 -0500 Subject: [PATCH 2371/5631] power: supply: rk817: Drop unneeded debugging code Some code was left over from debugging the driver while it was in development. Remove this code as it's not needed. Signed-off-by: Chris Morgan Signed-off-by: Sebastian Reichel --- drivers/power/supply/rk817_charger.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index 36f807b5ec44..eba9a17d991b 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -816,19 +816,6 @@ rk817_read_or_set_full_charge_on_boot(struct rk817_charger *charger, } } - regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_PWRON_VOL_H, - bulk_reg, 2); - tmp = get_unaligned_be16(bulk_reg); - boot_voltage = (charger->voltage_k * tmp) + 1000 * charger->voltage_b; - regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_Q_PRES_H3, - bulk_reg, 4); - tmp = get_unaligned_be32(bulk_reg); - boot_charge_mah = ADC_TO_CHARGE_UAH(tmp, charger->res_div) / 1000; - regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_OCV_VOL_H, - bulk_reg, 2); - tmp = get_unaligned_be16(bulk_reg); - boot_voltage = (charger->voltage_k * tmp) + 1000 * charger->voltage_b; - /* * Now we have our full charge capacity and soc, init the columb * counter. -- GitLab From baba1315a74d12772d4940a05d58dc03e6ec0635 Mon Sep 17 00:00:00 2001 From: Chris Morgan Date: Fri, 7 Apr 2023 11:18:27 -0500 Subject: [PATCH 2372/5631] power: supply: rk817: Fix low SOC bugs When the SOC approaches zero, an integer overflows in the columb counter causing the driver to react poorly. This makes the driver think it's at (above) the fully charged capacity when in fact it's zero. It would then write this full capacity to NVRAM which would be used on boot if the device remained off for less than 5 hours and not plugged in. This can be fixed and guarded against by doing the following: - Changing the type of tmp in rk817_read_or_set_full_charge_on_boot() to be an int instead of a u32. That way we can account for negative numbers. - Guard against negative values for the full charge on boot by setting the charge to 0 if the system charge reports less than 0. - Catch scenarios where the battery voltage is below the design minimum voltage and set the system SOC to 0 at that time and update the columb counter with a charge level of 0. - Change the off time value from 5 hours to 30 minutes before we recalculate the current capacity based on the OCV tables. These changes allow the driver to operate better at low voltage/low capacity conditions. Fixes: 3268a4d9b0b8 ("power: supply: rk817: Fix unsigned comparison with less than zero") Fixes: 11cb8da0189b ("power: supply: Add charger driver for Rockchip RK817") Signed-off-by: Chris Morgan Signed-off-by: Sebastian Reichel --- drivers/power/supply/rk817_charger.c | 33 ++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/drivers/power/supply/rk817_charger.c b/drivers/power/supply/rk817_charger.c index eba9a17d991b..1a2143641e66 100644 --- a/drivers/power/supply/rk817_charger.c +++ b/drivers/power/supply/rk817_charger.c @@ -335,6 +335,20 @@ static int rk817_bat_calib_cap(struct rk817_charger *charger) charger->fcc_mah * 1000); } + /* + * Set the SOC to 0 if we are below the minimum system voltage. + */ + if (volt_avg <= charger->bat_voltage_min_design_uv) { + charger->soc = 0; + charge_now_adc = CHARGE_TO_ADC(0, charger->res_div); + put_unaligned_be32(charge_now_adc, bulk_reg); + regmap_bulk_write(rk808->regmap, + RK817_GAS_GAUGE_Q_INIT_H3, bulk_reg, 4); + dev_warn(charger->dev, + "Battery voltage %d below minimum voltage %d\n", + volt_avg, charger->bat_voltage_min_design_uv); + } + rk817_record_battery_nvram_values(charger); return 0; @@ -710,9 +724,10 @@ static int rk817_read_battery_nvram_values(struct rk817_charger *charger) /* * Read the nvram for state of charge. Sanity check for values greater - * than 100 (10000). If the value is off it should get corrected - * automatically when the voltage drops to the min (soc is 0) or when - * the battery is full (soc is 100). + * than 100 (10000) or less than 0, because other things (BSP kernels, + * U-Boot, or even i2cset) can write to this register. If the value is + * off it should get corrected automatically when the voltage drops to + * the min (soc is 0) or when the battery is full (soc is 100). */ ret = regmap_bulk_read(charger->rk808->regmap, RK817_GAS_GAUGE_BAT_R1, bulk_reg, 3); @@ -721,6 +736,8 @@ static int rk817_read_battery_nvram_values(struct rk817_charger *charger) charger->soc = get_unaligned_le24(bulk_reg); if (charger->soc > 10000) charger->soc = 10000; + if (charger->soc < 0) + charger->soc = 0; return 0; } @@ -731,8 +748,8 @@ rk817_read_or_set_full_charge_on_boot(struct rk817_charger *charger, { struct rk808 *rk808 = charger->rk808; u8 bulk_reg[4]; - u32 boot_voltage, boot_charge_mah, tmp; - int ret, reg, off_time; + u32 boot_voltage, boot_charge_mah; + int ret, reg, off_time, tmp; bool first_boot; /* @@ -785,10 +802,12 @@ rk817_read_or_set_full_charge_on_boot(struct rk817_charger *charger, regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_Q_PRES_H3, bulk_reg, 4); tmp = get_unaligned_be32(bulk_reg); + if (tmp < 0) + tmp = 0; boot_charge_mah = ADC_TO_CHARGE_UAH(tmp, charger->res_div) / 1000; /* - * Check if the columb counter has been off for more than 300 + * Check if the columb counter has been off for more than 30 * minutes as it tends to drift downward. If so, re-init soc * with the boot voltage instead. Note the unit values for the * OFF_CNT register appear to be in decaminutes and stops @@ -799,7 +818,7 @@ rk817_read_or_set_full_charge_on_boot(struct rk817_charger *charger, * than 0 on a reboot anyway. */ regmap_read(rk808->regmap, RK817_GAS_GAUGE_OFF_CNT, &off_time); - if (off_time >= 30) { + if (off_time >= 3) { regmap_bulk_read(rk808->regmap, RK817_GAS_GAUGE_PWRON_VOL_H, bulk_reg, 2); -- GitLab From 5a23ad6510c82049f5ab3795841c30e8f3ca324d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Sat, 8 Apr 2023 12:17:31 +0000 Subject: [PATCH 2373/5631] KVM: arm64: Prevent userspace from handling SMC64 arch range Though presently unused, there is an SMC64 view of the Arm architecture calls defined by the SMCCC. The documentation of the SMCCC filter states that the SMC64 range is reserved, but nothing actually prevents userspace from applying a filter to the range. Insert a range with the HANDLE action for the SMC64 arch range, thereby preventing userspace from imposing filtering/forwarding on it. Fixes: fb88707dd39b ("KVM: arm64: Use a maple tree to represent the SMCCC filter") Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230408121732.3411329-2-oliver.upton@linux.dev --- arch/arm64/kvm/hypercalls.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 3b6523f25afc..47254a361295 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -121,11 +121,17 @@ static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) } } -#define SMCCC_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID -#define SMCCC_ARCH_RANGE_END \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ - ARM_SMCCC_SMC_32, \ - 0, ARM_SMCCC_FUNC_MASK) +#define SMC32_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID +#define SMC32_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, ARM_SMCCC_FUNC_MASK) + +#define SMC64_ARCH_RANGE_BEGIN ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + 0, 0) +#define SMC64_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + 0, ARM_SMCCC_FUNC_MASK) static void init_smccc_filter(struct kvm *kvm) { @@ -139,10 +145,17 @@ static void init_smccc_filter(struct kvm *kvm) * to the guest. */ r = mtree_insert_range(&kvm->arch.smccc_filter, - SMCCC_ARCH_RANGE_BEGIN, SMCCC_ARCH_RANGE_END, + SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); WARN_ON_ONCE(r); + + r = mtree_insert_range(&kvm->arch.smccc_filter, + SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END, + xa_mk_value(KVM_SMCCC_FILTER_HANDLE), + GFP_KERNEL_ACCOUNT); + WARN_ON_ONCE(r); + } static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) -- GitLab From 00e0c947118f456b622c1f2ca316c116dfb4e12c Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Sat, 8 Apr 2023 12:17:32 +0000 Subject: [PATCH 2374/5631] KVM: arm64: Test that SMC64 arch calls are reserved Assert that the SMC64 view of the Arm architecture range is reserved by KVM and cannot be filtered by userspace. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230408121732.3411329-3-oliver.upton@linux.dev --- tools/testing/selftests/kvm/aarch64/smccc_filter.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c index 0f9db0641847..dab671fdf239 100644 --- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c +++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c @@ -99,6 +99,7 @@ static void test_filter_reserved_range(void) { struct kvm_vcpu *vcpu; struct kvm_vm *vm = setup_vm(&vcpu); + uint32_t smc64_fn; int r; r = __set_smccc_filter(vm, ARM_SMCCC_ARCH_WORKAROUND_1, @@ -106,6 +107,13 @@ static void test_filter_reserved_range(void) TEST_ASSERT(r < 0 && errno == EEXIST, "Attempt to filter reserved range should return EEXIST"); + smc64_fn = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, + 0, 0); + + r = __set_smccc_filter(vm, smc64_fn, 1, KVM_SMCCC_FILTER_DENY); + TEST_ASSERT(r < 0 && errno == EEXIST, + "Attempt to filter reserved range should return EEXIST"); + kvm_vm_free(vm); } -- GitLab From c5284f6d8ce2b9cf96643da441862434233a4ea3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 6 Apr 2023 09:02:26 +0100 Subject: [PATCH 2375/5631] KVM: selftests: Fix spelling mistake "KVM_HYPERCAL_EXIT_SMC" -> "KVM_HYPERCALL_EXIT_SMC" There is a spelling mistake in a test assert message. Fix it. Signed-off-by: Colin Ian King Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230406080226.122955-1-colin.i.king@gmail.com --- tools/testing/selftests/kvm/aarch64/smccc_filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/aarch64/smccc_filter.c index dab671fdf239..f4ceae9c8925 100644 --- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c +++ b/tools/testing/selftests/kvm/aarch64/smccc_filter.c @@ -219,7 +219,7 @@ static void expect_call_fwd_to_user(struct kvm_vcpu *vcpu, uint32_t func_id, "KVM_HYPERCALL_EXIT_SMC is not set"); else TEST_ASSERT(!(run->hypercall.flags & KVM_HYPERCALL_EXIT_SMC), - "KVM_HYPERCAL_EXIT_SMC is set"); + "KVM_HYPERCALL_EXIT_SMC is set"); } /* SMCCC calls forwarded to userspace cause KVM_EXIT_HYPERCALL exits */ -- GitLab From eca7de7cdc382eb6e0d344c07b1449ed75f5b435 Mon Sep 17 00:00:00 2001 From: Wang Yong Date: Mon, 13 Feb 2023 14:08:08 +0800 Subject: [PATCH 2376/5631] delayacct: improve the average delay precision of getdelay tool to microsecond Improve the average delay precision of getdelay tool to microsecond. When using the getdelay tool, it is sometimes found that the average delay except CPU is not 0, but display is 0, because the precison is too low. For example, see delay average of SWAP below when using ZRAM. print delayacct stats ON PID 32915 CPU count real total virtual total delay total delay average 339202 2793871936 9233585504 7951112 0.000ms IO count delay total delay average 41 419296904 10ms SWAP count delay total delay average 242589 1045792384 0ms This wrong display is misleading, so improve the millisecond precision of the average delay to microsecond just like CPU. Then user would get more accurate information of delay time. Link: https://lkml.kernel.org/r/202302131408087983857@zte.com.cn Signed-off-by: Wang Yong Reviewed-by: Yang Yang Cc: David Hildenbrand Signed-off-by: Andrew Morton --- Documentation/accounting/delay-accounting.rst | 14 +++++------ .../zh_CN/accounting/delay-accounting.rst | 10 ++++---- tools/accounting/getdelays.c | 24 +++++++++---------- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index 7103b62ba6d7..79f537c9f160 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -109,17 +109,17 @@ Get sum of delays, since system boot, for all pids with tgid 5:: CPU count real total virtual total delay total delay average 8 7000000 6872122 3382277 0.423ms IO count delay total delay average - 0 0 0ms + 0 0 0.000ms SWAP count delay total delay average - 0 0 0ms + 0 0 0.000ms RECLAIM count delay total delay average - 0 0 0ms + 0 0 0.000ms THRASHING count delay total delay average - 0 0 0ms + 0 0 0.000ms COMPACT count delay total delay average - 0 0 0ms - WPCOPY count delay total delay average - 0 0 0ms + 0 0 0.000ms + WPCOPY count delay total delay average + 0 0 0.000ms Get IO accounting for pid 1, it works only with -p:: diff --git a/Documentation/translations/zh_CN/accounting/delay-accounting.rst b/Documentation/translations/zh_CN/accounting/delay-accounting.rst index a01dc3d5b0db..7b8693ccf80a 100644 --- a/Documentation/translations/zh_CN/accounting/delay-accounting.rst +++ b/Documentation/translations/zh_CN/accounting/delay-accounting.rst @@ -92,15 +92,15 @@ getdelays命令的一般格式:: CPU count real total virtual total delay total delay average 8 7000000 6872122 3382277 0.423ms IO count delay total delay average - 0 0 0ms + 0 0 0.000ms SWAP count delay total delay average - 0 0 0ms + 0 0 0.000ms RECLAIM count delay total delay average - 0 0 0ms + 0 0 0.000ms THRASHING count delay total delay average - 0 0 0ms + 0 0 0.000ms COMPACT count delay total delay average - 0 0 0ms + 0 0 0.000ms WPCOPY count delay total delay average 0 0 0ms diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 938dec0dfaad..23a15d8f2bf4 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -198,17 +198,17 @@ static void print_delayacct(struct taskstats *t) printf("\n\nCPU %15s%15s%15s%15s%15s\n" " %15llu%15llu%15llu%15llu%15.3fms\n" "IO %15s%15s%15s\n" - " %15llu%15llu%15llums\n" + " %15llu%15llu%15.3fms\n" "SWAP %15s%15s%15s\n" - " %15llu%15llu%15llums\n" + " %15llu%15llu%15.3fms\n" "RECLAIM %12s%15s%15s\n" - " %15llu%15llu%15llums\n" + " %15llu%15llu%15.3fms\n" "THRASHING%12s%15s%15s\n" - " %15llu%15llu%15llums\n" + " %15llu%15llu%15.3fms\n" "COMPACT %12s%15s%15s\n" - " %15llu%15llu%15llums\n" + " %15llu%15llu%15.3fms\n" "WPCOPY %12s%15s%15s\n" - " %15llu%15llu%15llums\n", + " %15llu%15llu%15.3fms\n", "count", "real total", "virtual total", "delay total", "delay average", (unsigned long long)t->cpu_count, @@ -219,27 +219,27 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->blkio_count, (unsigned long long)t->blkio_delay_total, - average_ms(t->blkio_delay_total, t->blkio_count), + average_ms((double)t->blkio_delay_total, t->blkio_count), "count", "delay total", "delay average", (unsigned long long)t->swapin_count, (unsigned long long)t->swapin_delay_total, - average_ms(t->swapin_delay_total, t->swapin_count), + average_ms((double)t->swapin_delay_total, t->swapin_count), "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count), + average_ms((double)t->freepages_delay_total, t->freepages_count), "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms(t->thrashing_delay_total, t->thrashing_count), + average_ms((double)t->thrashing_delay_total, t->thrashing_count), "count", "delay total", "delay average", (unsigned long long)t->compact_count, (unsigned long long)t->compact_delay_total, - average_ms(t->compact_delay_total, t->compact_count), + average_ms((double)t->compact_delay_total, t->compact_count), "count", "delay total", "delay average", (unsigned long long)t->wpcopy_count, (unsigned long long)t->wpcopy_delay_total, - average_ms(t->wpcopy_delay_total, t->wpcopy_count)); + average_ms((double)t->wpcopy_delay_total, t->wpcopy_count)); } static void task_context_switch_counts(struct taskstats *t) -- GitLab From 58deeb4ef3b054498747d0929d94ac53ab90981f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 19:42:58 -0800 Subject: [PATCH 2377/5631] ia64: mm/contig: fix section mismatch warning/error alloc_per_cpu_data() is called by find_memory(), which is marked as __init. Therefore alloc_per_cpu_data() can also be marked as __init to remedy this modpost problem. WARNING: modpost: vmlinux.o: section mismatch in reference: alloc_per_cpu_data (section: .text) -> memblock_alloc_try_nid (section: .init.text) Link: https://lkml.kernel.org/r/20230223034258.12917-1-rdunlap@infradead.org Fixes: 4b9ddc7cf272 ("[IA64] Fix section mismatch in contig.c version of per_cpu_init()") Signed-off-by: Randy Dunlap Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- arch/ia64/mm/contig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 24901d809301..1e9eaa107eb7 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -77,7 +77,7 @@ void *per_cpu_init(void) return __per_cpu_start + __per_cpu_offset[smp_processor_id()]; } -static inline void +static inline __init void alloc_per_cpu_data(void) { size_t size = PERCPU_PAGE_SIZE * num_possible_cpus(); -- GitLab From 0de155752b152d6bcd96b5b5bf20af336abd183a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Feb 2023 19:43:09 -0800 Subject: [PATCH 2378/5631] ia64: salinfo: placate defined-but-not-used warning When CONFIG_PROC_FS is not set, proc_salinfo_show() is not used. Mark the function as __maybe_unused to quieten the warning message. ../arch/ia64/kernel/salinfo.c:584:12: warning: 'proc_salinfo_show' defined but not used [-Wunused-function] 584 | static int proc_salinfo_show(struct seq_file *m, void *v) | ^~~~~~~~~~~~~~~~~ Link: https://lkml.kernel.org/r/20230223034309.13375-1-rdunlap@infradead.org Fixes: 3f3942aca6da ("proc: introduce proc_create_single{,_data}") Signed-off-by: Randy Dunlap Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- arch/ia64/kernel/salinfo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index bd3ba276e69c..03b632c56899 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -581,7 +581,7 @@ static int salinfo_cpu_pre_down(unsigned int cpu) * 'data' contains an integer that corresponds to the feature we're * testing */ -static int proc_salinfo_show(struct seq_file *m, void *v) +static int __maybe_unused proc_salinfo_show(struct seq_file *m, void *v) { unsigned long data = (unsigned long)v; seq_puts(m, (sal_platform_features & data) ? "1\n" : "0\n"); -- GitLab From b99b258899d7a59e60169f402e5bce6b8272ce97 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Tue, 31 Jan 2023 23:08:40 +0800 Subject: [PATCH 2379/5631] proc: remove mark_inode_dirty() in .setattr() procfs' .setattr() has updated i_uid, i_gid and i_mode into proc dirent, we don't need to call mark_inode_dirty() for delayed update, remove it. Link: https://lkml.kernel.org/r/20230131150840.34726-1-chao@kernel.org Signed-off-by: Chao Yu Reviewed-by: Alexey Dobriyan Signed-off-by: Andrew Morton --- fs/proc/base.c | 1 - fs/proc/generic.c | 1 - fs/proc/proc_sysctl.c | 1 - 3 files changed, 3 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 5e0e0ccd47aa..e34e06091775 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -699,7 +699,6 @@ int proc_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return error; setattr_copy(&nop_mnt_idmap, inode, attr); - mark_inode_dirty(inode); return 0; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8379593fa4bb..42ae38ff6e7e 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -127,7 +127,6 @@ static int proc_notify_change(struct mnt_idmap *idmap, return error; setattr_copy(&nop_mnt_idmap, inode, iattr); - mark_inode_dirty(inode); proc_set_user(de, inode->i_uid, inode->i_gid); de->mode = inode->i_mode; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5851eb5bc726..875771bf1f93 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -841,7 +841,6 @@ static int proc_sys_setattr(struct mnt_idmap *idmap, return error; setattr_copy(&nop_mnt_idmap, inode, attr); - mark_inode_dirty(inode); return 0; } -- GitLab From f9641a36d38daee3ccf2f3d832cbc9c3442b6078 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 30 Nov 2022 16:12:31 +0100 Subject: [PATCH 2380/5631] nfs: remove empty if statement from nfs3_prepare_get_acl Remove empty if statement from nfs3_prepare_get_acl and update comment to follow the one from the referred fs/posix_acl.c:get_acl(). No functional change intended. Link: https://lkml.kernel.org/r/20221130151231.3654-1-ubizjak@gmail.com Signed-off-by: Uros Bizjak Cc: Trond Myklebust Cc: Anna Schumaker Signed-off-by: Andrew Morton --- fs/nfs/nfs3acl.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 1247f544a440..ccc4da54cc93 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -21,9 +21,8 @@ static void nfs3_prepare_get_acl(struct posix_acl **p) { struct posix_acl *sentinel = uncached_acl_sentinel(current); - if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) { - /* Not the first reader or sentinel already in place. */ - } + /* If the ACL isn't being read yet, set our sentinel. */ + cmpxchg(p, ACL_NOT_CACHED, sentinel); } static void nfs3_complete_get_acl(struct posix_acl **p, struct posix_acl *acl) -- GitLab From 7b32137bc027701cc9c57967af64fcdea0ef113b Mon Sep 17 00:00:00 2001 From: Andrey Konovalov Date: Mon, 27 Feb 2023 18:17:03 +0100 Subject: [PATCH 2381/5631] kcov: improve documentation Improve KCOV documentation: - Use KCOV instead of kcov, as the former is more widely-used. - Mention Clang in compiler requirements. - Use ``annotations`` for inline code. - Rework remote coverage collection documentation for better clarity. - Various smaller changes. [andreyknvl@google.com: v2] Link: https://lkml.kernel.org/r/583f41c49eef15210fa813e8229730d11427efa7.1677614637.git.andreyknvl@google.com [andreyknvl@google.com: fix ``annotation`` for KCOV_REMOTE_ENABLE] Link: https://lkml.kernel.org/r/72be5c215c275f35891229b90622ed859f196a46.1677684837.git.andreyknvl@google.com Link: https://lkml.kernel.org/r/0b5efd70e31bba7912cf9a6c951f0e76a8df27df.1677517724.git.andreyknvl@google.com Signed-off-by: Andrey Konovalov Reviewed-by: Dmitry Vyukov Reviewed-by: Bagas Sanjaya Cc: Alexander Potapenko Cc: Marco Elver Signed-off-by: Andrew Morton --- Documentation/dev-tools/kcov.rst | 169 +++++++++++++++++++------------ 1 file changed, 102 insertions(+), 67 deletions(-) diff --git a/Documentation/dev-tools/kcov.rst b/Documentation/dev-tools/kcov.rst index d83c9ab49427..6611434e2dd2 100644 --- a/Documentation/dev-tools/kcov.rst +++ b/Documentation/dev-tools/kcov.rst @@ -1,42 +1,50 @@ -kcov: code coverage for fuzzing +KCOV: code coverage for fuzzing =============================== -kcov exposes kernel code coverage information in a form suitable for coverage- -guided fuzzing (randomized testing). Coverage data of a running kernel is -exported via the "kcov" debugfs file. Coverage collection is enabled on a task -basis, and thus it can capture precise coverage of a single system call. +KCOV collects and exposes kernel code coverage information in a form suitable +for coverage-guided fuzzing. Coverage data of a running kernel is exported via +the ``kcov`` debugfs file. Coverage collection is enabled on a task basis, and +thus KCOV can capture precise coverage of a single system call. -Note that kcov does not aim to collect as much coverage as possible. It aims -to collect more or less stable coverage that is function of syscall inputs. -To achieve this goal it does not collect coverage in soft/hard interrupts -and instrumentation of some inherently non-deterministic parts of kernel is -disabled (e.g. scheduler, locking). +Note that KCOV does not aim to collect as much coverage as possible. It aims +to collect more or less stable coverage that is a function of syscall inputs. +To achieve this goal, it does not collect coverage in soft/hard interrupts +(unless remove coverage collection is enabled, see below) and from some +inherently non-deterministic parts of the kernel (e.g. scheduler, locking). -kcov is also able to collect comparison operands from the instrumented code -(this feature currently requires that the kernel is compiled with clang). +Besides collecting code coverage, KCOV can also collect comparison operands. +See the "Comparison operands collection" section for details. + +Besides collecting coverage data from syscall handlers, KCOV can also collect +coverage for annotated parts of the kernel executing in background kernel +tasks or soft interrupts. See the "Remote coverage collection" section for +details. Prerequisites ------------- -Configure the kernel with:: +KCOV relies on compiler instrumentation and requires GCC 6.1.0 or later +or any Clang version supported by the kernel. - CONFIG_KCOV=y +Collecting comparison operands is supported with GCC 8+ or with Clang. -CONFIG_KCOV requires gcc 6.1.0 or later. +To enable KCOV, configure the kernel with:: -If the comparison operands need to be collected, set:: + CONFIG_KCOV=y + +To enable comparison operands collection, set:: CONFIG_KCOV_ENABLE_COMPARISONS=y -Profiling data will only become accessible once debugfs has been mounted:: +Coverage data only becomes accessible once debugfs has been mounted:: mount -t debugfs none /sys/kernel/debug Coverage collection ------------------- -The following program demonstrates coverage collection from within a test -program using kcov: +The following program demonstrates how to use KCOV to collect coverage for a +single syscall from within a test program: .. code-block:: c @@ -84,7 +92,7 @@ program using kcov: perror("ioctl"), exit(1); /* Reset coverage from the tail of the ioctl() call. */ __atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED); - /* That's the target syscal call. */ + /* Call the target syscall call. */ read(-1, NULL, 0); /* Read number of PCs collected. */ n = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); @@ -103,7 +111,7 @@ program using kcov: return 0; } -After piping through addr2line output of the program looks as follows:: +After piping through ``addr2line`` the output of the program looks as follows:: SyS_read fs/read_write.c:562 @@ -121,12 +129,13 @@ After piping through addr2line output of the program looks as follows:: fs/read_write.c:562 If a program needs to collect coverage from several threads (independently), -it needs to open /sys/kernel/debug/kcov in each thread separately. +it needs to open ``/sys/kernel/debug/kcov`` in each thread separately. The interface is fine-grained to allow efficient forking of test processes. -That is, a parent process opens /sys/kernel/debug/kcov, enables trace mode, -mmaps coverage buffer and then forks child processes in a loop. Child processes -only need to enable coverage (disable happens automatically on thread end). +That is, a parent process opens ``/sys/kernel/debug/kcov``, enables trace mode, +mmaps coverage buffer, and then forks child processes in a loop. The child +processes only need to enable coverage (it gets disabled automatically when +a thread exits). Comparison operands collection ------------------------------ @@ -205,52 +214,78 @@ Comparison operands collection is similar to coverage collection: return 0; } -Note that the kcov modes (coverage collection or comparison operands) are -mutually exclusive. +Note that the KCOV modes (collection of code coverage or comparison operands) +are mutually exclusive. Remote coverage collection -------------------------- -With KCOV_ENABLE coverage is collected only for syscalls that are issued -from the current process. With KCOV_REMOTE_ENABLE it's possible to collect -coverage for arbitrary parts of the kernel code, provided that those parts -are annotated with kcov_remote_start()/kcov_remote_stop(). - -This allows to collect coverage from two types of kernel background -threads: the global ones, that are spawned during kernel boot in a limited -number of instances (e.g. one USB hub_event() worker thread is spawned per -USB HCD); and the local ones, that are spawned when a user interacts with -some kernel interface (e.g. vhost workers); as well as from soft -interrupts. - -To enable collecting coverage from a global background thread or from a -softirq, a unique global handle must be assigned and passed to the -corresponding kcov_remote_start() call. Then a userspace process can pass -a list of such handles to the KCOV_REMOTE_ENABLE ioctl in the handles -array field of the kcov_remote_arg struct. This will attach the used kcov -device to the code sections, that are referenced by those handles. - -Since there might be many local background threads spawned from different -userspace processes, we can't use a single global handle per annotation. -Instead, the userspace process passes a non-zero handle through the -common_handle field of the kcov_remote_arg struct. This common handle gets -saved to the kcov_handle field in the current task_struct and needs to be -passed to the newly spawned threads via custom annotations. Those threads -should in turn be annotated with kcov_remote_start()/kcov_remote_stop(). - -Internally kcov stores handles as u64 integers. The top byte of a handle -is used to denote the id of a subsystem that this handle belongs to, and -the lower 4 bytes are used to denote the id of a thread instance within -that subsystem. A reserved value 0 is used as a subsystem id for common -handles as they don't belong to a particular subsystem. The bytes 4-7 are -currently reserved and must be zero. In the future the number of bytes -used for the subsystem or handle ids might be increased. - -When a particular userspace process collects coverage via a common -handle, kcov will collect coverage for each code section that is annotated -to use the common handle obtained as kcov_handle from the current -task_struct. However non common handles allow to collect coverage -selectively from different subsystems. +Besides collecting coverage data from handlers of syscalls issued from a +userspace process, KCOV can also collect coverage for parts of the kernel +executing in other contexts - so-called "remote" coverage. + +Using KCOV to collect remote coverage requires: + +1. Modifying kernel code to annotate the code section from where coverage + should be collected with ``kcov_remote_start`` and ``kcov_remote_stop``. + +2. Using ``KCOV_REMOTE_ENABLE`` instead of ``KCOV_ENABLE`` in the userspace + process that collects coverage. + +Both ``kcov_remote_start`` and ``kcov_remote_stop`` annotations and the +``KCOV_REMOTE_ENABLE`` ioctl accept handles that identify particular coverage +collection sections. The way a handle is used depends on the context where the +matching code section executes. + +KCOV supports collecting remote coverage from the following contexts: + +1. Global kernel background tasks. These are the tasks that are spawned during + kernel boot in a limited number of instances (e.g. one USB ``hub_event`` + worker is spawned per one USB HCD). + +2. Local kernel background tasks. These are spawned when a userspace process + interacts with some kernel interface and are usually killed when the process + exits (e.g. vhost workers). + +3. Soft interrupts. + +For #1 and #3, a unique global handle must be chosen and passed to the +corresponding ``kcov_remote_start`` call. Then a userspace process must pass +this handle to ``KCOV_REMOTE_ENABLE`` in the ``handles`` array field of the +``kcov_remote_arg`` struct. This will attach the used KCOV device to the code +section referenced by this handle. Multiple global handles identifying +different code sections can be passed at once. + +For #2, the userspace process instead must pass a non-zero handle through the +``common_handle`` field of the ``kcov_remote_arg`` struct. This common handle +gets saved to the ``kcov_handle`` field in the current ``task_struct`` and +needs to be passed to the newly spawned local tasks via custom kernel code +modifications. Those tasks should in turn use the passed handle in their +``kcov_remote_start`` and ``kcov_remote_stop`` annotations. + +KCOV follows a predefined format for both global and common handles. Each +handle is a ``u64`` integer. Currently, only the one top and the lower 4 bytes +are used. Bytes 4-7 are reserved and must be zero. + +For global handles, the top byte of the handle denotes the id of a subsystem +this handle belongs to. For example, KCOV uses ``1`` as the USB subsystem id. +The lower 4 bytes of a global handle denote the id of a task instance within +that subsystem. For example, each ``hub_event`` worker uses the USB bus number +as the task instance id. + +For common handles, a reserved value ``0`` is used as a subsystem id, as such +handles don't belong to a particular subsystem. The lower 4 bytes of a common +handle identify a collective instance of all local tasks spawned by the +userspace process that passed a common handle to ``KCOV_REMOTE_ENABLE``. + +In practice, any value can be used for common handle instance id if coverage +is only collected from a single userspace process on the system. However, if +common handles are used by multiple processes, unique instance ids must be +used for each process. One option is to use the process id as the common +handle instance id. + +The following program demonstrates using KCOV to collect coverage from both +local tasks spawned by the process and the global task that handles USB bus #1: .. code-block:: c -- GitLab From 3ac39d208d485ef5f5518b96f23ec9ade077683f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 27 Feb 2023 13:06:12 +0300 Subject: [PATCH 2382/5631] dca: delete unnecessary variable It's more readable to just pass NULL directly instead of using a variable for that. Link: https://lkml.kernel.org/r/Y/yAlDytLH0ZNLNz@kili Signed-off-by: Dan Carpenter Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton --- drivers/dca/dca-core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c index c40c2ebfdae9..ed3dac546dd6 100644 --- a/drivers/dca/dca-core.c +++ b/drivers/dca/dca-core.c @@ -294,9 +294,7 @@ EXPORT_SYMBOL_GPL(dca3_get_tag); */ u8 dca_get_tag(int cpu) { - struct device *dev = NULL; - - return dca_common_get_tag(dev, cpu); + return dca_common_get_tag(NULL, cpu); } EXPORT_SYMBOL_GPL(dca_get_tag); -- GitLab From 56fe487062b5561ceabb9f866327cd0b041f3a09 Mon Sep 17 00:00:00 2001 From: Glenn Washburn Date: Sun, 26 Feb 2023 22:05:59 -0600 Subject: [PATCH 2383/5631] scripts/gdb: correct indentation in get_current_task Patch series "scripts/gdb: Support getting current task struct in UML", v3. A running x86 UML kernel reports with architecture "i386:x86-64" as it is a sub-architecture. However, a difference with bare-metal x86 kernels is in how it manages tasks and the current task struct. To identify that the inferior is a UML kernel and not bare-metal, check for the existence of the UML specific symbol "cpu_tasks" which contains the current task struct. This patch (of 3): There is an extra space in a couple blocks in get_current_task. Though python does not care, let's make the spacing consistent. Also, format better an if expression, removing unneeded parenthesis. Link: https://lkml.kernel.org/r/cover.1677469905.git.development@efficientek.com Link: https://lkml.kernel.org/r/2e117b82240de6893f27cb6507242ce455ed7b5b.1677469905.git.development@efficientek.com Signed-off-by: Glenn Washburn Reviewed-by: Jan Kiszka Cc: Anton Ivanov Cc: Johannes Berg Cc: Kieran Bingham Cc: Richard Weinberger Signed-off-by: Andrew Morton --- scripts/gdb/linux/cpus.py | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 9ee99f9fae8d..e8d2a62ff119 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -163,16 +163,16 @@ def get_current_task(cpu): task_ptr_type = task_type.get_type().pointer() if utils.is_target_arch("x86"): - var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") - return per_cpu(var_ptr, cpu).dereference() + var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") + return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): - current_task_addr = gdb.parse_and_eval("$SP_EL0") - if((current_task_addr >> 63) != 0): - current_task = current_task_addr.cast(task_ptr_type) - return current_task.dereference() - else: - raise gdb.GdbError("Sorry, obtaining the current task is not allowed " - "while running in userspace(EL0)") + current_task_addr = gdb.parse_and_eval("$SP_EL0") + if (current_task_addr >> 63) != 0: + current_task = current_task_addr.cast(task_ptr_type) + return current_task.dereference() + else: + raise gdb.GdbError("Sorry, obtaining the current task is not allowed " + "while running in userspace(EL0)") else: raise gdb.GdbError("Sorry, obtaining the current task is not yet " "supported with this arch") -- GitLab From 6d51363d53db4f5f11a13509ef28e917b97eb2b3 Mon Sep 17 00:00:00 2001 From: Glenn Washburn Date: Sun, 26 Feb 2023 22:06:00 -0600 Subject: [PATCH 2384/5631] scripts/gdb: support getting current task struct in UML A running x86 UML kernel reports with architecture "i386:x86-64" as it is a sub-architecture. However, a difference with bare-metal x86 kernels is in how it manages tasks and the current task struct. To identify that the inferior is a UML kernel and not bare-metal, check for the existence of the UML specific symbol "cpu_tasks" which contains the current task struct. Link: https://lkml.kernel.org/r/b839d611e2906ccef2725c34d8e353fab35fe75e.1677469905.git.development@efficientek.com Signed-off-by: Glenn Washburn Reviewed-by: Jan Kiszka Cc: Anton Ivanov Cc: Johannes Berg Cc: Kieran Bingham Cc: Richard Weinberger Signed-off-by: Andrew Morton --- scripts/gdb/linux/cpus.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index e8d2a62ff119..255dc18cb9da 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -163,8 +163,14 @@ def get_current_task(cpu): task_ptr_type = task_type.get_type().pointer() if utils.is_target_arch("x86"): - var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") - return per_cpu(var_ptr, cpu).dereference() + if gdb.lookup_global_symbol("cpu_tasks"): + # This is a UML kernel, which stores the current task + # differently than other x86 sub architectures + var_ptr = gdb.parse_and_eval("(struct task_struct *)cpu_tasks[0].task") + return var_ptr.dereference() + else: + var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") + return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): current_task_addr = gdb.parse_and_eval("$SP_EL0") if (current_task_addr >> 63) != 0: -- GitLab From 2a6772ebf05a9b6bc450e42bbb459f6327f68aca Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 28 Feb 2023 18:34:38 +0300 Subject: [PATCH 2385/5631] mm: uninline kstrdup() gcc inlines kstrdup into kstrdup_const() but it can very efficiently tail call into it instead: $ ./scripts/bloat-o-meter ../vmlinux-000 ../obj/vmlinux add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-84 (-84) Function old new delta kstrdup_const 119 35 -84 Link: https://lkml.kernel.org/r/Y/4fDlbIhTLNLFHz@p183 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton --- mm/util.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/util.c b/mm/util.c index b8ed9dbc7fd5..dd12b9531ac4 100644 --- a/mm/util.c +++ b/mm/util.c @@ -49,6 +49,7 @@ EXPORT_SYMBOL(kfree_const); * * Return: newly allocated copy of @s or %NULL in case of error */ +noinline char *kstrdup(const char *s, gfp_t gfp) { size_t len; -- GitLab From 70e79866ab36feaaed8ef26dacfbcbac6a0631c9 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 28 Feb 2023 15:14:17 +0300 Subject: [PATCH 2386/5631] ELF: fix all "Elf" typos ELF is acronym and therefore should be spelled in all caps. I left one exception at Documentation/arm/nwfpe/nwfpe.rst which looks like being written in the first person. Link: https://lkml.kernel.org/r/Y/3wGWQviIOkyLJW@p183 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton --- arch/mips/boot/tools/relocs.c | 2 +- arch/um/os-Linux/elf_aux.c | 2 +- arch/x86/tools/relocs.c | 2 +- drivers/remoteproc/remoteproc_coredump.c | 4 ++-- drivers/remoteproc/remoteproc_elf_loader.c | 4 ++-- fs/binfmt_elf.c | 2 +- fs/binfmt_elf_fdpic.c | 2 +- fs/proc/vmcore.c | 22 +++++++++++----------- lib/buildid.c | 2 +- sound/soc/codecs/rt5677.c | 2 +- tools/bpf/resolve_btfids/main.c | 2 +- tools/lib/bpf/libbpf.c | 2 +- tools/lib/bpf/usdt.c | 2 +- tools/perf/util/symbol-elf.c | 2 +- 14 files changed, 26 insertions(+), 26 deletions(-) diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c index 02fc85f3e8ff..a88d66c46d7f 100644 --- a/arch/mips/boot/tools/relocs.c +++ b/arch/mips/boot/tools/relocs.c @@ -245,7 +245,7 @@ static void read_ehdr(FILE *fp) die("Unknown ELF version\n"); if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) - die("Bad Elf header size\n"); + die("Bad ELF header size\n"); if (ehdr.e_phentsize != sizeof(Elf_Phdr)) die("Bad program header entry\n"); diff --git a/arch/um/os-Linux/elf_aux.c b/arch/um/os-Linux/elf_aux.c index 77a9321379b7..344ac403fb5d 100644 --- a/arch/um/os-Linux/elf_aux.c +++ b/arch/um/os-Linux/elf_aux.c @@ -2,7 +2,7 @@ /* * arch/um/kernel/elf_aux.c * - * Scan the Elf auxiliary vector provided by the host to extract + * Scan the ELF auxiliary vector provided by the host to extract * information about vsyscall-page, etc. * * Copyright (C) 2004 Fujitsu Siemens Computers GmbH diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 2925074b9a58..d30949e25ebd 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -406,7 +406,7 @@ static void read_ehdr(FILE *fp) if (ehdr.e_version != EV_CURRENT) die("Unknown ELF version\n"); if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) - die("Bad Elf header size\n"); + die("Bad ELF header size\n"); if (ehdr.e_phentsize != sizeof(Elf_Phdr)) die("Bad program header entry\n"); if (ehdr.e_shentsize != sizeof(Elf_Shdr)) diff --git a/drivers/remoteproc/remoteproc_coredump.c b/drivers/remoteproc/remoteproc_coredump.c index 4b093420d98a..bc0e1603a7a3 100644 --- a/drivers/remoteproc/remoteproc_coredump.c +++ b/drivers/remoteproc/remoteproc_coredump.c @@ -249,7 +249,7 @@ void rproc_coredump(struct rproc *rproc) return; if (class == ELFCLASSNONE) { - dev_err(&rproc->dev, "Elf class is not set\n"); + dev_err(&rproc->dev, "ELF class is not set\n"); return; } @@ -361,7 +361,7 @@ void rproc_coredump_using_sections(struct rproc *rproc) return; if (class == ELFCLASSNONE) { - dev_err(&rproc->dev, "Elf class is not set\n"); + dev_err(&rproc->dev, "ELF class is not set\n"); return; } diff --git a/drivers/remoteproc/remoteproc_elf_loader.c b/drivers/remoteproc/remoteproc_elf_loader.c index 5a412d7b6e0b..94177e416047 100644 --- a/drivers/remoteproc/remoteproc_elf_loader.c +++ b/drivers/remoteproc/remoteproc_elf_loader.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Remote Processor Framework Elf loader + * Remote Processor Framework ELF loader * * Copyright (C) 2011 Texas Instruments, Inc. * Copyright (C) 2011 Google, Inc. @@ -39,7 +39,7 @@ int rproc_elf_sanity_check(struct rproc *rproc, const struct firmware *fw) const char *name = rproc->firmware; struct device *dev = &rproc->dev; /* - * Elf files are beginning with the same structure. Thus, to simplify + * ELF files are beginning with the same structure. Thus, to simplify * header parsing, we can use the elf32_hdr one for both elf64 and * elf32. */ diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8a884e795f6a..a5b054fdb331 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2058,7 +2058,7 @@ static int elf_core_dump(struct coredump_params *cprm) has_dumped = 1; - offset += sizeof(elf); /* Elf header */ + offset += sizeof(elf); /* ELF header */ offset += segs * sizeof(struct elf_phdr); /* Program headers */ /* Write notes phdr entry */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index a05eafcacfb2..05a1471d5283 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1540,7 +1540,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) fill_note(&auxv_note, "CORE", NT_AUXV, i * sizeof(elf_addr_t), auxv); thread_status_size += notesize(&auxv_note); - offset = sizeof(*elf); /* Elf header */ + offset = sizeof(*elf); /* ELF header */ offset += segs * sizeof(struct elf_phdr); /* Program headers */ /* Write notes phdr entry */ diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 12af614f33ce..03f5963914a1 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -339,7 +339,7 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) return acc; } - /* Read Elf note segment */ + /* Read ELF note segment */ if (*fpos < elfcorebuf_sz + elfnotes_sz) { void *kaddr; @@ -1109,7 +1109,7 @@ static int __init process_ptload_program_headers_elf64(char *elfptr, ehdr_ptr = (Elf64_Ehdr *)elfptr; phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */ - /* Skip Elf header, program headers and Elf note segment. */ + /* Skip ELF header, program headers and ELF note segment. */ vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { @@ -1152,7 +1152,7 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, ehdr_ptr = (Elf32_Ehdr *)elfptr; phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */ - /* Skip Elf header, program headers and Elf note segment. */ + /* Skip ELF header, program headers and ELF note segment. */ vmcore_off = elfsz + elfnotes_sz; for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { @@ -1188,7 +1188,7 @@ static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, loff_t vmcore_off; struct vmcore *m; - /* Skip Elf header, program headers and Elf note segment. */ + /* Skip ELF header, program headers and ELF note segment. */ vmcore_off = elfsz + elfnotes_sz; list_for_each_entry(m, vc_list, list) { @@ -1213,7 +1213,7 @@ static int __init parse_crash_elf64_headers(void) addr = elfcorehdr_addr; - /* Read Elf header */ + /* Read ELF header */ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr); if (rc < 0) return rc; @@ -1269,7 +1269,7 @@ static int __init parse_crash_elf32_headers(void) addr = elfcorehdr_addr; - /* Read Elf header */ + /* Read ELF header */ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr); if (rc < 0) return rc; @@ -1376,12 +1376,12 @@ static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data, } /** - * vmcoredd_update_program_headers - Update all Elf program headers + * vmcoredd_update_program_headers - Update all ELF program headers * @elfptr: Pointer to elf header * @elfnotesz: Size of elf notes aligned to page size * @vmcoreddsz: Size of device dumps to be added to elf note header * - * Determine type of Elf header (Elf64 or Elf32) and update the elf note size. + * Determine type of ELF header (Elf64 or Elf32) and update the elf note size. * Also update the offsets of all the program headers after the elf note header. */ static void vmcoredd_update_program_headers(char *elfptr, size_t elfnotesz, @@ -1439,10 +1439,10 @@ static void vmcoredd_update_program_headers(char *elfptr, size_t elfnotesz, /** * vmcoredd_update_size - Update the total size of the device dumps and update - * Elf header + * ELF header * @dump_size: Size of the current device dump to be added to total size * - * Update the total size of all the device dumps and update the Elf program + * Update the total size of all the device dumps and update the ELF program * headers. Calculate the new offsets for the vmcore list and update the * total vmcore size. */ @@ -1466,7 +1466,7 @@ static void vmcoredd_update_size(size_t dump_size) * @data: dump info. * * Allocate a buffer and invoke the calling driver's dump collect routine. - * Write Elf note at the beginning of the buffer to indicate vmcore device + * Write ELF note at the beginning of the buffer to indicate vmcore device * dump and add the dump to global list. */ int vmcore_add_device_dump(struct vmcoredd_data *data) diff --git a/lib/buildid.c b/lib/buildid.c index dfc62625cae4..e3a7acdeef0e 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -163,7 +163,7 @@ int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, /** * build_id_parse_buf - Get build ID from a buffer - * @buf: Elf note section(s) to parse + * @buf: ELF note section(s) to parse * @buf_size: Size of @buf in bytes * @build_id: Build ID parsed from @buf, at least BUILD_ID_SIZE_MAX long * diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index c26395f42d8e..3bf019b3f700 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -829,7 +829,7 @@ static int rt5677_parse_and_load_dsp(struct rt5677_priv *rt5677, const u8 *buf, if (strncmp(elf_hdr->e_ident, ELFMAG, sizeof(ELFMAG) - 1)) dev_err(component->dev, "Wrong ELF header prefix\n"); if (elf_hdr->e_ehsize != sizeof(Elf32_Ehdr)) - dev_err(component->dev, "Wrong Elf header size\n"); + dev_err(component->dev, "Wrong ELF header size\n"); if (elf_hdr->e_machine != EM_XTENSA) dev_err(component->dev, "Wrong DSP code file\n"); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 77058174082d..27a23196d58e 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* - * resolve_btfids scans Elf object for .BTF_ids section and resolves + * resolve_btfids scans ELF object for .BTF_ids section and resolves * its symbols with BTF ID values. * * Each symbol points to 4 bytes data and is expected to have diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 05c4db355f28..67b2f5ff185d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1334,7 +1334,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) goto errout; } - /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + /* ELF is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) { pr_warn("elf: failed to get section names strings from %s: %s\n", obj->path, elf_errmsg(-1)); diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 75b411fc2c77..3496df332e8e 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -771,7 +771,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * target->rel_ip = usdt_rel_ip; target->sema_off = usdt_sema_off; - /* notes.args references strings from Elf itself, so they can + /* notes.args references strings from ELF itself, so they can * be referenced safely until elf_end() call */ target->spec_str = note.args; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 41882ae8452e..554289fd6df9 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -213,7 +213,7 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep, Elf_Scn *sec = NULL; size_t cnt = 1; - /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + /* ELF is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) return NULL; -- GitLab From 4b3d049f1c567560191884d4bd8f6e99ab885e20 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Mon, 6 Mar 2023 13:32:53 -0800 Subject: [PATCH 2387/5631] scripts/link-vmlinux.sh: fix error message presentation This comes out as Try make KALLSYMS_EXTRA_PASS=1 as a workaround but we want quotes: Try "make KALLSYMS_EXTRA_PASS=1" as a workaround Link: https://lkml.kernel.org/r/202303042034.Cjc7JTd0-lkp@intel.com Cc: kernel test robot Signed-off-by: Andrew Morton --- scripts/link-vmlinux.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 32e573943cf0..0512c313a590 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -291,7 +291,7 @@ fi if is_enabled CONFIG_KALLSYMS; then if ! cmp -s System.map ${kallsyms_vmlinux}.syms; then echo >&2 Inconsistent kallsyms data - echo >&2 Try "make KALLSYMS_EXTRA_PASS=1" as a workaround + echo >&2 'Try "make KALLSYMS_EXTRA_PASS=1" as a workaround' exit 1 fi fi -- GitLab From d99a4158c4483c7f47274937deb142cd8c461b77 Mon Sep 17 00:00:00 2001 From: Gerhard Engleder Date: Wed, 4 Jan 2023 21:15:24 +0100 Subject: [PATCH 2388/5631] checkpatch: ignore ETHTOOL_LINK_MODE_ enum values Since commit 4104a20646 ("checkpatch: ignore generated CamelCase defines and enum values") enum values like ETHTOOL_LINK_MODE_Asym_Pause_BIT are ignored. But there are other enums like ETHTOOL_LINK_MODE_1000baseT_Full_BIT, which are not ignored because of the not matching '1000baseT' substring. Add regex to match all ETHTOOL_LINK_MODE enums. Link: https://lkml.kernel.org/r/20230104201524.28078-1-gerhard@engleder-embedded.com Signed-off-by: Gerhard Engleder Cc: Andy Whitcroft Cc: Dwaipayan Ray Cc: Gerhard Engleder Cc: Joe Perches Cc: Lukas Bulwahn Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index bd44d12965c9..c7cd0750b41e 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5809,6 +5809,8 @@ sub process { $var !~ /^(?:[A-Z]+_){1,5}[A-Z]{1,3}[a-z]/ && #Ignore Page variants $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && +#Ignore ETHTOOL_LINK_MODE_ variants + $var !~ /^ETHTOOL_LINK_MODE_/ && #Ignore SI style variants like nS, mV and dB #(ie: max_uV, regulator_min_uA_show, RANGE_mA_VALUE) $var !~ /^(?:[a-z0-9_]*|[A-Z0-9_]*)?_?[a-z][A-Z](?:_[a-z0-9_]+|_[A-Z0-9_]+)?$/ && -- GitLab From 725e374050ab0b4aa3663807a597773db30f1ae8 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 8 Mar 2023 16:06:25 +0100 Subject: [PATCH 2389/5631] MAINTAINERS: remove the obsolete section EMBEDDED LINUX By now, many developers are working on Linux for embedded systems. There is no need to point out single developers. The linux-embedded mailing list has only little traffic, and most of it is just spam. Remove this obsolete section. Link: https://lkml.kernel.org/r/20230308150625.28732-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Acked-by: David Woodhouse Cc: Olivia Mackall Signed-off-by: Andrew Morton --- MAINTAINERS | 6 ------ 1 file changed, 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 90abe83c02f3..63cba614d233 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7525,12 +7525,6 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/admin-guide/media/em28xx* F: drivers/media/usb/em28xx/ -EMBEDDED LINUX -M: Olivia Mackall -M: David Woodhouse -L: linux-embedded@vger.kernel.org -S: Maintained - EMMC CMDQ HOST CONTROLLER INTERFACE (CQHCI) DRIVER M: Adrian Hunter M: Ritesh Harjani -- GitLab From 882c5b261f404ebdfe69dcc055bfffc39f80c5a6 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 12 Mar 2023 12:46:45 -0400 Subject: [PATCH 2390/5631] kernel/hung_task.c: set some hung_task.c variables storage-class-specifier to static smatch reports several warnings kernel/hung_task.c:31:19: warning: symbol 'sysctl_hung_task_check_count' was not declared. Should it be static? kernel/hung_task.c:50:29: warning: symbol 'sysctl_hung_task_check_interval_secs' was not declared. Should it be static? kernel/hung_task.c:52:19: warning: symbol 'sysctl_hung_task_warnings' was not declared. Should it be static? kernel/hung_task.c:75:28: warning: symbol 'sysctl_hung_task_panic' was not declared. Should it be static? These variables are only used in hung_task.c, so they should be static Link: https://lkml.kernel.org/r/20230312164645.471259-1-trix@redhat.com Signed-off-by: Tom Rix Cc: Ben Dooks Cc: fuyuanli Cc: John Ogness Cc: Peter Zijlstra Cc: Petr Mladek Cc: Rafael J. Wysocki Cc: Rasmus Villemoes Signed-off-by: Andrew Morton --- kernel/hung_task.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 322813366c6c..9a24574988d2 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -28,7 +28,7 @@ /* * The number of tasks checked: */ -int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; +static int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; /* * Limit number of tasks checked in a batch. @@ -47,9 +47,9 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_ /* * Zero (default value) means use sysctl_hung_task_timeout_secs: */ -unsigned long __read_mostly sysctl_hung_task_check_interval_secs; +static unsigned long __read_mostly sysctl_hung_task_check_interval_secs; -int __read_mostly sysctl_hung_task_warnings = 10; +static int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; static bool hung_task_show_lock; @@ -72,8 +72,8 @@ static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; * Should we panic (and reboot, if panic_timeout= is set) when a * hung task is detected: */ -unsigned int __read_mostly sysctl_hung_task_panic = - IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); +static unsigned int __read_mostly sysctl_hung_task_panic = + IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); static int hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) -- GitLab From f4708a82dc45fbf08bd3c68fc3eb32397e9121a1 Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Tue, 14 Mar 2023 17:00:58 -0300 Subject: [PATCH 2391/5631] notifiers: add tracepoints to the notifiers infrastructure Currently there is no way to show the callback names for registered, unregistered or executed notifiers. This is very useful for debug purposes, hence add this functionality here in the form of notifiers' tracepoints, one per operation. [akpm@linux-foundation.org: coding-style cleanups] Link: https://lkml.kernel.org/r/20230314200058.1326909-1-gpiccoli@igalia.com Signed-off-by: Guilherme G. Piccoli Cc: Arjan van de Ven Cc: Michael Kelley Cc: Steven Rostedt Cc: Xiaoming Ni Cc: Baoquan He Cc: Cong Wang Cc: Dmitry Osipenko Cc: Guilherme G. Piccoli Cc: Guilherme G. Piccoli Cc: Petr Mladek Cc: Rafael J. Wysocki Cc: Sebastian Andrzej Siewior Cc: Valentin Schneider Signed-off-by: Andrew Morton --- include/trace/events/notifier.h | 69 +++++++++++++++++++++++++++++++++ kernel/notifier.c | 6 +++ 2 files changed, 75 insertions(+) create mode 100644 include/trace/events/notifier.h diff --git a/include/trace/events/notifier.h b/include/trace/events/notifier.h new file mode 100644 index 000000000000..26b298a31950 --- /dev/null +++ b/include/trace/events/notifier.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM notifier + +#if !defined(_TRACE_NOTIFIERS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NOTIFIERS_H + +#include + +DECLARE_EVENT_CLASS(notifier_info, + + TP_PROTO(void *cb), + + TP_ARGS(cb), + + TP_STRUCT__entry( + __field(void *, cb) + ), + + TP_fast_assign( + __entry->cb = cb; + ), + + TP_printk("%ps", __entry->cb) +); + +/* + * notifier_register - called upon notifier callback registration + * + * @cb: callback pointer + * + */ +DEFINE_EVENT(notifier_info, notifier_register, + + TP_PROTO(void *cb), + + TP_ARGS(cb) +); + +/* + * notifier_unregister - called upon notifier callback unregistration + * + * @cb: callback pointer + * + */ +DEFINE_EVENT(notifier_info, notifier_unregister, + + TP_PROTO(void *cb), + + TP_ARGS(cb) +); + +/* + * notifier_run - called upon notifier callback execution + * + * @cb: callback pointer + * + */ +DEFINE_EVENT(notifier_info, notifier_run, + + TP_PROTO(void *cb), + + TP_ARGS(cb) +); + +#endif /* _TRACE_NOTIFIERS_H */ + +/* This part must be outside protection */ +#include diff --git a/kernel/notifier.c b/kernel/notifier.c index d353e4b5402d..b3ce28f39eb6 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -7,6 +7,9 @@ #include #include +#define CREATE_TRACE_POINTS +#include + /* * Notifier list for kernel code which wants to be called * at shutdown. This is used to stop any idling DMA operations @@ -37,6 +40,7 @@ static int notifier_chain_register(struct notifier_block **nl, } n->next = *nl; rcu_assign_pointer(*nl, n); + trace_notifier_register((void *)n->notifier_call); return 0; } @@ -46,6 +50,7 @@ static int notifier_chain_unregister(struct notifier_block **nl, while ((*nl) != NULL) { if ((*nl) == n) { rcu_assign_pointer(*nl, n->next); + trace_notifier_unregister((void *)n->notifier_call); return 0; } nl = &((*nl)->next); @@ -84,6 +89,7 @@ static int notifier_call_chain(struct notifier_block **nl, continue; } #endif + trace_notifier_run((void *)nb->notifier_call); ret = nb->notifier_call(nb, val, v); if (nr_calls) -- GitLab From 58c9b016e12855286370dfb704c08498edbc857a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 22 Mar 2023 17:57:02 +0100 Subject: [PATCH 2392/5631] epoll: use refcount to reduce ep_mutex contention We are observing huge contention on the epmutex during an http connection/rate test: 83.17% 0.25% nginx [kernel.kallsyms] [k] entry_SYSCALL_64_after_hwframe [...] |--66.96%--__fput |--60.04%--eventpoll_release_file |--58.41%--__mutex_lock.isra.6 |--56.56%--osq_lock The application is multi-threaded, creates a new epoll entry for each incoming connection, and does not delete it before the connection shutdown - that is, before the connection's fd close(). Many different threads compete frequently for the epmutex lock, affecting the overall performance. To reduce the contention this patch introduces explicit reference counting for the eventpoll struct. Each registered event acquires a reference, and references are released at ep_remove() time. The eventpoll struct is released by whoever - among EP file close() and and the monitored file close() drops its last reference. Additionally, this introduces a new 'dying' flag to prevent races between the EP file close() and the monitored file close(). ep_eventpoll_release() marks, under f_lock spinlock, each epitem as dying before removing it, while EP file close() does not touch dying epitems. The above is needed as both close operations could run concurrently and drop the EP reference acquired via the epitem entry. Without the above flag, the monitored file close() could reach the EP struct via the epitem list while the epitem is still listed and then try to put it after its disposal. An alternative could be avoiding touching the references acquired via the epitems at EP file close() time, but that could leave the EP struct alive for potentially unlimited time after EP file close(), with nasty side effects. With all the above in place, we can drop the epmutex usage at disposal time. Overall this produces a significant performance improvement in the mentioned connection/rate scenario: the mutex operations disappear from the topmost offenders in the perf report, and the measured connections/rate grows by ~60%. To make the change more readable this additionally renames ep_free() to ep_clear_and_put(), and moves the actual memory cleanup in a separate ep_free() helper. Link: https://lkml.kernel.org/r/4a57788dcaf28f5eb4f8dfddcc3a8b172a7357bb.1679504153.git.pabeni@redhat.com Signed-off-by: Paolo Abeni Co-developed-by: Eric Dumazet Signed-off-by: Eric Dumazet Tested-by: Xiumei Mu Acked-by: Soheil Hassas Yeganeh Reviewed-by: Davidlohr Bueso Cc: Alexander Viro Cc: Carlos Maiolino Cc: Christian Brauner Cc: Eric Biggers Cc: Jacob Keller Cc: Jens Axboe Signed-off-by: Andrew Morton --- fs/eventpoll.c | 195 +++++++++++++++++++++++++++++++------------------ 1 file changed, 123 insertions(+), 72 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 64659b110973..0ecdfd3043a3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -57,13 +57,7 @@ * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). - * Then we also need a global mutex to serialize eventpoll_release_file() - * and ep_free(). - * This mutex is acquired by ep_free() during the epoll file - * cleanup path and it is also acquired by eventpoll_release_file() - * if a file has been pushed inside an epoll set and it is then - * close()d without a previous call to epoll_ctl(EPOLL_CTL_DEL). - * It is also acquired when inserting an epoll fd onto another epoll + * The epmutex is acquired when inserting an epoll fd onto another epoll * fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two @@ -153,6 +147,13 @@ struct epitem { /* The file descriptor information this item refers to */ struct epoll_filefd ffd; + /* + * Protected by file->f_lock, true for to-be-released epitem already + * removed from the "struct file" items list; together with + * eventpoll->refcount orchestrates "struct eventpoll" disposal + */ + bool dying; + /* List containing poll wait queues */ struct eppoll_entry *pwqlist; @@ -217,6 +218,12 @@ struct eventpoll { u64 gen; struct hlist_head refs; + /* + * usage count, used together with epitem->dying to + * orchestrate the disposal of this struct + */ + refcount_t refcount; + #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; @@ -240,9 +247,7 @@ struct ep_pqueue { /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; -/* - * This mutex is used to serialize ep_free() and eventpoll_release_file(). - */ +/* Used for cycles detection */ static DEFINE_MUTEX(epmutex); static u64 loop_check_gen = 0; @@ -557,8 +562,7 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq) /* * This function unregisters poll callbacks from the associated file - * descriptor. Must be called with "mtx" held (or "epmutex" if called from - * ep_free). + * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { @@ -681,11 +685,40 @@ static void epi_rcu_free(struct rcu_head *head) kmem_cache_free(epi_cache, epi); } +static void ep_get(struct eventpoll *ep) +{ + refcount_inc(&ep->refcount); +} + +/* + * Returns true if the event poll can be disposed + */ +static bool ep_refcount_dec_and_test(struct eventpoll *ep) +{ + if (!refcount_dec_and_test(&ep->refcount)) + return false; + + WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); + return true; +} + +static void ep_free(struct eventpoll *ep) +{ + mutex_destroy(&ep->mtx); + free_uid(ep->user); + wakeup_source_unregister(ep->ws); + kfree(ep); +} + /* * Removes a "struct epitem" from the eventpoll RB tree and deallocates * all the associated resources. Must be called with "mtx" held. + * If the dying flag is set, do the removal only if force is true. + * This prevents ep_clear_and_put() from dropping all the ep references + * while running concurrently with eventpoll_release_file(). + * Returns true if the eventpoll can be disposed. */ -static int ep_remove(struct eventpoll *ep, struct epitem *epi) +static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; struct epitems_head *to_free; @@ -700,6 +733,11 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) /* Remove the current item from the list of epoll hooks */ spin_lock(&file->f_lock); + if (epi->dying && !force) { + spin_unlock(&file->f_lock); + return false; + } + to_free = NULL; head = file->f_ep; if (head->first == &epi->fllink && !epi->fllink.next) { @@ -733,28 +771,28 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) call_rcu(&epi->rcu, epi_rcu_free); percpu_counter_dec(&ep->user->epoll_watches); + return ep_refcount_dec_and_test(ep); +} - return 0; +/* + * ep_remove variant for callers owing an additional reference to the ep + */ +static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi) +{ + WARN_ON_ONCE(__ep_remove(ep, epi, false)); } -static void ep_free(struct eventpoll *ep) +static void ep_clear_and_put(struct eventpoll *ep) { - struct rb_node *rbp; + struct rb_node *rbp, *next; struct epitem *epi; + bool dispose; /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); - /* - * We need to lock this because we could be hit by - * eventpoll_release_file() while we're freeing the "struct eventpoll". - * We do not need to hold "ep->mtx" here because the epoll file - * is on the way to be removed and no one has references to it - * anymore. The only hit might come from eventpoll_release_file() but - * holding "epmutex" is sufficient here. - */ - mutex_lock(&epmutex); + mutex_lock(&ep->mtx); /* * Walks through the whole tree by unregistering poll callbacks. @@ -767,26 +805,25 @@ static void ep_free(struct eventpoll *ep) } /* - * Walks through the whole tree by freeing each "struct epitem". At this - * point we are sure no poll callbacks will be lingering around, and also by - * holding "epmutex" we can be sure that no file cleanup code will hit - * us during this operation. So we can avoid the lock on "ep->lock". - * We do not need to lock ep->mtx, either, we only do it to prevent - * a lockdep warning. + * Walks through the whole tree and try to free each "struct epitem". + * Note that ep_remove_safe() will not remove the epitem in case of a + * racing eventpoll_release_file(); the latter will do the removal. + * At this point we are sure no poll callbacks will be lingering around. + * Since we still own a reference to the eventpoll struct, the loop can't + * dispose it. */ - mutex_lock(&ep->mtx); - while ((rbp = rb_first_cached(&ep->rbr)) != NULL) { + for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { + next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); - ep_remove(ep, epi); + ep_remove_safe(ep, epi); cond_resched(); } + + dispose = ep_refcount_dec_and_test(ep); mutex_unlock(&ep->mtx); - mutex_unlock(&epmutex); - mutex_destroy(&ep->mtx); - free_uid(ep->user); - wakeup_source_unregister(ep->ws); - kfree(ep); + if (dispose) + ep_free(ep); } static int ep_eventpoll_release(struct inode *inode, struct file *file) @@ -794,7 +831,7 @@ static int ep_eventpoll_release(struct inode *inode, struct file *file) struct eventpoll *ep = file->private_data; if (ep) - ep_free(ep); + ep_clear_and_put(ep); return 0; } @@ -906,33 +943,34 @@ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; - struct hlist_node *next; + bool dispose; /* - * We don't want to get "file->f_lock" because it is not - * necessary. It is not necessary because we're in the "struct file" - * cleanup path, and this means that no one is using this file anymore. - * So, for example, epoll_ctl() cannot hit here since if we reach this - * point, the file counter already went to zero and fget() would fail. - * The only hit might come from ep_free() but by holding the mutex - * will correctly serialize the operation. We do need to acquire - * "ep->mtx" after "epmutex" because ep_remove() requires it when called - * from anywhere but ep_free(). - * - * Besides, ep_remove() acquires the lock, so we can't hold it here. + * Use the 'dying' flag to prevent a concurrent ep_clear_and_put() from + * touching the epitems list before eventpoll_release_file() can access + * the ep->mtx. */ - mutex_lock(&epmutex); - if (unlikely(!file->f_ep)) { - mutex_unlock(&epmutex); - return; - } - hlist_for_each_entry_safe(epi, next, file->f_ep, fllink) { +again: + spin_lock(&file->f_lock); + if (file->f_ep && file->f_ep->first) { + epi = hlist_entry(file->f_ep->first, struct epitem, fllink); + epi->dying = true; + spin_unlock(&file->f_lock); + + /* + * ep access is safe as we still own a reference to the ep + * struct + */ ep = epi->ep; - mutex_lock_nested(&ep->mtx, 0); - ep_remove(ep, epi); + mutex_lock(&ep->mtx); + dispose = __ep_remove(ep, epi, true); mutex_unlock(&ep->mtx); + + if (dispose) + ep_free(ep); + goto again; } - mutex_unlock(&epmutex); + spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) @@ -955,6 +993,7 @@ static int ep_alloc(struct eventpoll **pep) ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = user; + refcount_set(&ep->refcount, 1); *pep = ep; @@ -1223,10 +1262,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v */ list_del_init(&wait->entry); /* - * ->whead != NULL protects us from the race with ep_free() - * or ep_remove(), ep_remove_wait_queue() takes whead->lock - * held by the caller. Once we nullify it, nothing protects - * ep/epi or even wait. + * ->whead != NULL protects us from the race with + * ep_clear_and_put() or ep_remove(), ep_remove_wait_queue() + * takes whead->lock held by the caller. Once we nullify it, + * nothing protects ep/epi or even wait. */ smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } @@ -1496,16 +1535,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (tep) mutex_unlock(&tep->mtx); + /* + * ep_remove_safe() calls in the later error paths can't lead to + * ep_free() as the ep file itself still holds an ep reference. + */ + ep_get(ep); + /* now check if we've created too many backpaths */ if (unlikely(full_check && reverse_path_check())) { - ep_remove(ep, epi); + ep_remove_safe(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { - ep_remove(ep, epi); + ep_remove_safe(ep, epi); return error; } } @@ -1529,7 +1574,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, * high memory pressure. */ if (unlikely(!epq.epi)) { - ep_remove(ep, epi); + ep_remove_safe(ep, epi); return -ENOMEM; } @@ -2025,7 +2070,7 @@ static int do_epoll_create(int flags) out_free_fd: put_unused_fd(fd); out_free_ep: - ep_free(ep); + ep_clear_and_put(ep); return error; } @@ -2167,10 +2212,16 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, error = -EEXIST; break; case EPOLL_CTL_DEL: - if (epi) - error = ep_remove(ep, epi); - else + if (epi) { + /* + * The eventpoll itself is still alive: the refcount + * can't go to zero here. + */ + ep_remove_safe(ep, epi); + error = 0; + } else { error = -ENOENT; + } break; case EPOLL_CTL_MOD: if (epi) { -- GitLab From 890a3ee3ce416e2f1aed41718a8c1d42c82cf1b2 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 23 Mar 2023 17:50:29 +0200 Subject: [PATCH 2393/5631] kernel.h: split the hexadecimal related helpers to hex.h For the sake of cleaning up the kernel.h split the hexadecimal related helpers to own header called 'hex.h'. Link: https://lkml.kernel.org/r/20230323155029.40000-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Rasmus Villemoes Signed-off-by: Andrew Morton --- include/linux/hex.h | 35 +++++++++++++++++++++++++++++++++++ include/linux/kernel.h | 29 +---------------------------- 2 files changed, 36 insertions(+), 28 deletions(-) create mode 100644 include/linux/hex.h diff --git a/include/linux/hex.h b/include/linux/hex.h new file mode 100644 index 000000000000..2618382e5b0c --- /dev/null +++ b/include/linux/hex.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HEX_H +#define _LINUX_HEX_H + +#include + +extern const char hex_asc[]; +#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] +#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack(char *buf, u8 byte) +{ + *buf++ = hex_asc_hi(byte); + *buf++ = hex_asc_lo(byte); + return buf; +} + +extern const char hex_asc_upper[]; +#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] +#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack_upper(char *buf, u8 byte) +{ + *buf++ = hex_asc_upper_hi(byte); + *buf++ = hex_asc_upper_lo(byte); + return buf; +} + +extern int hex_to_bin(unsigned char ch); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); +extern char *bin2hex(char *dst, const void *src, size_t count); + +bool mac_pton(const char *s, u8 *mac); + +#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 40bce7495af8..0d91e0af0125 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -263,34 +264,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -extern const char hex_asc[]; -#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] -#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack(char *buf, u8 byte) -{ - *buf++ = hex_asc_hi(byte); - *buf++ = hex_asc_lo(byte); - return buf; -} - -extern const char hex_asc_upper[]; -#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] -#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack_upper(char *buf, u8 byte) -{ - *buf++ = hex_asc_upper_hi(byte); - *buf++ = hex_asc_upper_lo(byte); - return buf; -} - -extern int hex_to_bin(unsigned char ch); -extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); -extern char *bin2hex(char *dst, const void *src, size_t count); - -bool mac_pton(const char *s, u8 *mac); - /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop -- GitLab From a74d9a3f4fc96520c8f85cd372a16a0b29430701 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Thu, 23 Mar 2023 19:37:09 +0800 Subject: [PATCH 2394/5631] rapidio/tsi721: remove redundant pci_clear_master Remove pci_clear_master to simplify the code, the bus-mastering is also cleared in do_pci_disable_device, like this: ./drivers/pci/pci.c:2197 static void do_pci_disable_device(struct pci_dev *dev) { u16 pci_command; pci_read_config_word(dev, PCI_COMMAND, &pci_command); if (pci_command & PCI_COMMAND_MASTER) { pci_command &= ~PCI_COMMAND_MASTER; pci_write_config_word(dev, PCI_COMMAND, pci_command); } pcibios_disable_device(dev); }. And dev->is_busmaster is set to 0 in pci_disable_device. Link: https://lkml.kernel.org/r/20230323113711.10523-1-cai.huoqing@linux.dev Signed-off-by: Cai Huoqing Cc: Alexandre Bounine Cc: Matt Porter Cc: Tetsuo Handa Signed-off-by: Andrew Morton --- drivers/rapidio/devices/tsi721.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 0a42d6a2af24..83323c3d10af 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -2924,7 +2924,6 @@ static int tsi721_probe(struct pci_dev *pdev, iounmap(priv->odb_base); err_free_res: pci_release_regions(pdev); - pci_clear_master(pdev); err_disable_pdev: pci_disable_device(pdev); err_clean: @@ -2962,7 +2961,6 @@ static void tsi721_remove(struct pci_dev *pdev) pci_disable_msi(priv->pdev); #endif pci_release_regions(pdev); - pci_clear_master(pdev); pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); kfree(priv); @@ -2977,7 +2975,6 @@ static void tsi721_shutdown(struct pci_dev *pdev) tsi721_disable_ints(priv); tsi721_dma_stop_all(priv); - pci_clear_master(pdev); pci_disable_device(pdev); } -- GitLab From 7982722ff7286596a1e2f343ec4219e309ddc82a Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 16:44:15 -0600 Subject: [PATCH 2395/5631] x86/kexec: remove unnecessary arch_kexec_kernel_image_load() Patch series "kexec: Remove unnecessary arch hook", v2. There are no arch-specific things in arch_kexec_kernel_image_load(), so remove it and just use the generic version. This patch (of 2): The x86 implementation of arch_kexec_kernel_image_load() is functionally identical to the generic arch_kexec_kernel_image_load(): arch_kexec_kernel_image_load # x86 if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); return image->fops->load(image, image->kernel_buf, ...) arch_kexec_kernel_image_load # generic kexec_image_load_default if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); return image->fops->load(image, image->kernel_buf, ...) Remove the x86-specific version and use the generic arch_kexec_kernel_image_load(). No functional change intended. Link: https://lkml.kernel.org/r/20230307224416.907040-1-helgaas@kernel.org Link: https://lkml.kernel.org/r/20230307224416.907040-2-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- arch/x86/include/asm/kexec.h | 3 --- arch/x86/kernel/machine_kexec_64.c | 11 ----------- include/linux/kexec.h | 2 -- 3 files changed, 16 deletions(-) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index a3760ca796aa..5b77bbc28f96 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -200,9 +200,6 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, const Elf_Shdr *symtab); #define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add -void *arch_kexec_kernel_image_load(struct kimage *image); -#define arch_kexec_kernel_image_load arch_kexec_kernel_image_load - int arch_kimage_file_post_load_cleanup(struct kimage *image); #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup #endif diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 0611fd83858e..1a3e2c05a8a5 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -374,17 +374,6 @@ void machine_kexec(struct kimage *image) /* arch-dependent functionality related to kexec file-based syscall */ #ifdef CONFIG_KEXEC_FILE -void *arch_kexec_kernel_image_load(struct kimage *image) -{ - if (!image->fops || !image->fops->load) - return ERR_PTR(-ENOEXEC); - - return image->fops->load(image, image->kernel_buf, - image->kernel_buf_len, image->initrd_buf, - image->initrd_buf_len, image->cmdline_buf, - image->cmdline_buf_len); -} - /* * Apply purgatory relocations. * diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6883c5922701..4746bc9d39c9 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -207,12 +207,10 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -#ifndef arch_kexec_kernel_image_load static inline void *arch_kexec_kernel_image_load(struct kimage *image) { return kexec_image_load_default(image); } -#endif #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION -- GitLab From fb15abdca64503511bb32cb6ff70da306f24fa06 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 7 Mar 2023 16:44:16 -0600 Subject: [PATCH 2396/5631] kexec: remove unnecessary arch_kexec_kernel_image_load() arch_kexec_kernel_image_load() only calls kexec_image_load_default(), and there are no arch-specific implementations. Remove the unnecessary arch_kexec_kernel_image_load() and make kexec_image_load_default() static. No functional change intended. Link: https://lkml.kernel.org/r/20230307224416.907040-3-helgaas@kernel.org Signed-off-by: Bjorn Helgaas Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Borislav Petkov (AMD) Cc: Dave Hansen Cc: Eric Biederman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton --- include/linux/kexec.h | 6 ------ kernel/kexec_file.c | 6 +++--- 2 files changed, 3 insertions(+), 9 deletions(-) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 4746bc9d39c9..22b5cd24f581 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -190,7 +190,6 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); -void *kexec_image_load_default(struct kimage *image); #ifndef arch_kexec_kernel_image_probe static inline int @@ -207,11 +206,6 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -static inline void *arch_kexec_kernel_image_load(struct kimage *image) -{ - return kexec_image_load_default(image); -} - #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f1a0e4e3fb5c..f989f5f1933b 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -65,7 +65,7 @@ int kexec_image_probe_default(struct kimage *image, void *buf, return ret; } -void *kexec_image_load_default(struct kimage *image) +static void *kexec_image_load_default(struct kimage *image) { if (!image->fops || !image->fops->load) return ERR_PTR(-ENOEXEC); @@ -249,8 +249,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, /* IMA needs to pass the measurement list to the next kernel. */ ima_add_kexec_buffer(image); - /* Call arch image load handlers */ - ldata = arch_kexec_kernel_image_load(image); + /* Call image load handler */ + ldata = kexec_image_load_default(image); if (IS_ERR(ldata)) { ret = PTR_ERR(ldata); -- GitLab From 1d7adbc74c009057ed9dc3112f388e91a9c79acc Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 23 Mar 2023 15:52:45 -0700 Subject: [PATCH 2397/5631] scripts/gdb: bail early if there are no clocks Avoid generating an exception if there are no clocks registered: (gdb) lx-clk-summary enable prepare protect clock count count count rate ------------------------------------------------------------------------ Python Exception : No symbol "clk_root_list" in current context. Error occurred in Python: No symbol "clk_root_list" in current context. Link: https://lkml.kernel.org/r/20230323225246.3302977-1-f.fainelli@gmail.com Fixes: d1e9710b63d8 ("scripts/gdb: initial clk support: lx-clk-summary") Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Cc: Leonard Crestez Cc: Stephen Boyd Signed-off-by: Andrew Morton --- scripts/gdb/linux/clk.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/gdb/linux/clk.py b/scripts/gdb/linux/clk.py index 061aecfa294e..7a01fdc3e844 100644 --- a/scripts/gdb/linux/clk.py +++ b/scripts/gdb/linux/clk.py @@ -41,6 +41,8 @@ are cached and potentially out of date""" self.show_subtree(child, level + 1) def invoke(self, arg, from_tty): + if utils.gdb_eval_or_none("clk_root_list") is None: + raise gdb.GdbError("No clocks registered") gdb.write(" enable prepare protect \n") gdb.write(" clock count count count rate \n") gdb.write("------------------------------------------------------------------------\n") -- GitLab From f19c3c2959e465209ade1a7a699e6cbf4359ce78 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 23 Mar 2023 16:16:57 -0700 Subject: [PATCH 2398/5631] scripts/gdb: bail early if there are no generic PD Avoid generating an exception if there are no generic power domain(s) registered: (gdb) lx-genpd-summary domain status children /device runtime status ---------------------------------------------------------------------- Python Exception : No symbol "gpd_list" in current context. Error occurred in Python: No symbol "gpd_list" in current context. (gdb) quit [f.fainelli@gmail.com: correctly invoke gdb_eval_or_none] Link: https://lkml.kernel.org/r/20230327185746.3856407-1-f.fainelli@gmail.com Link: https://lkml.kernel.org/r/20230323231659.3319941-1-f.fainelli@gmail.com Fixes: 8207d4a88e1e ("scripts/gdb: add lx-genpd-summary command") Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Cc: Leonard Crestez Cc: Stephen Boyd Signed-off-by: Andrew Morton --- scripts/gdb/linux/genpd.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scripts/gdb/linux/genpd.py b/scripts/gdb/linux/genpd.py index 39cd1abd8559..b53649c0a77a 100644 --- a/scripts/gdb/linux/genpd.py +++ b/scripts/gdb/linux/genpd.py @@ -5,7 +5,7 @@ import gdb import sys -from linux.utils import CachedType +from linux.utils import CachedType, gdb_eval_or_none from linux.lists import list_for_each_entry generic_pm_domain_type = CachedType('struct generic_pm_domain') @@ -70,6 +70,8 @@ Output is similar to /sys/kernel/debug/pm_genpd/pm_genpd_summary''' gdb.write(' %-50s %s\n' % (kobj_path, rtpm_status_str(dev))) def invoke(self, arg, from_tty): + if gdb_eval_or_none("&gpd_list") is None: + raise gdb.GdbError("No power domain(s) registered") gdb.write('domain status children\n'); gdb.write(' /device runtime status\n'); gdb.write('----------------------------------------------------------------------\n'); -- GitLab From ef55ef3e6400ede7d4020f5fd0bc7aeac4de1ceb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 27 Mar 2023 17:26:04 +0300 Subject: [PATCH 2399/5631] lib/test-string_helpers: replace UNESCAPE_ANY by UNESCAPE_ALL_MASK When we get a random number to generate a flag in the valid range of UNESCAPE flags, use UNESCAPE_ALL_MASK, It's more correct and prevents from missed updates of the test coverage in the future if any. Link: https://lkml.kernel.org/r/20230327142604.48213-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Rasmus Villemoes Signed-off-by: Andrew Morton --- lib/test-string_helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 41d3447bc3b4..9a68849a5d55 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -587,7 +587,7 @@ static int __init test_string_helpers_init(void) for (i = 0; i < UNESCAPE_ALL_MASK + 1; i++) test_string_unescape("unescape", i, false); test_string_unescape("unescape inplace", - get_random_u32_below(UNESCAPE_ANY + 1), true); + get_random_u32_below(UNESCAPE_ALL_MASK + 1), true); /* Without dictionary */ for (i = 0; i < ESCAPE_ALL_MASK + 1; i++) -- GitLab From bd9de1badac7e4ff6780365d4aa38983f5e2a436 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Thu, 30 Mar 2023 10:23:51 +0300 Subject: [PATCH 2400/5631] RDMA/cm: Trace icm_send_rej event before the cm state is reset Trace icm_send_rej event before the cm state is reset to idle, so that correct cm state will be logged. For example when an incoming request is rejected, the old trace log was: icm_send_rej: local_id=961102742 remote_id=3829151631 state=IDLE reason=REJ_CONSUMER_DEFINED With this patch: icm_send_rej: local_id=312971016 remote_id=3778819983 state=MRA_REQ_SENT reason=REJ_CONSUMER_DEFINED Fixes: 8dc105befe16 ("RDMA/cm: Add tracepoints to track MAD send operations") Signed-off-by: Mark Zhang Link: https://lore.kernel.org/r/20230330072351.481200-1-markzhang@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/core/cm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 603c0aecc361..ff58058aeadc 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2912,6 +2912,8 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, (ari && ari_length > IB_CM_REJ_ARI_LENGTH)) return -EINVAL; + trace_icm_send_rej(&cm_id_priv->id, reason); + switch (state) { case IB_CM_REQ_SENT: case IB_CM_MRA_REQ_RCVD: @@ -2942,7 +2944,6 @@ static int cm_send_rej_locked(struct cm_id_private *cm_id_priv, return -EINVAL; } - trace_icm_send_rej(&cm_id_priv->id, reason); ret = ib_post_send_mad(msg, NULL); if (ret) { cm_free_msg(msg); -- GitLab From eca5cd9474cd26d62f9756f536e2e656d3f62f3a Mon Sep 17 00:00:00 2001 From: Saravanan Vajravel Date: Wed, 5 Apr 2023 21:25:49 -0700 Subject: [PATCH 2401/5631] RDMA/srpt: Add a check for valid 'mad_agent' pointer When unregistering MAD agent, srpt module has a non-null check for 'mad_agent' pointer before invoking ib_unregister_mad_agent(). This check can pass if 'mad_agent' variable holds an error value. The 'mad_agent' can have an error value for a short window when srpt_add_one() and srpt_remove_one() is executed simultaneously. In srpt module, added a valid pointer check for 'sport->mad_agent' before unregistering MAD agent. This issue can hit when RoCE driver unregisters ib_device Stack Trace: ------------ BUG: kernel NULL pointer dereference, address: 000000000000004d PGD 145003067 P4D 145003067 PUD 2324fe067 PMD 0 Oops: 0002 [#1] PREEMPT SMP NOPTI CPU: 10 PID: 4459 Comm: kworker/u80:0 Kdump: loaded Tainted: P Hardware name: Dell Inc. PowerEdge R640/06NR82, BIOS 2.5.4 01/13/2020 Workqueue: bnxt_re bnxt_re_task [bnxt_re] RIP: 0010:_raw_spin_lock_irqsave+0x19/0x40 Call Trace: ib_unregister_mad_agent+0x46/0x2f0 [ib_core] IPv6: ADDRCONF(NETDEV_CHANGE): bond0: link becomes ready ? __schedule+0x20b/0x560 srpt_unregister_mad_agent+0x93/0xd0 [ib_srpt] srpt_remove_one+0x20/0x150 [ib_srpt] remove_client_context+0x88/0xd0 [ib_core] bond0: (slave p2p1): link status definitely up, 100000 Mbps full duplex disable_device+0x8a/0x160 [ib_core] bond0: active interface up! ? kernfs_name_hash+0x12/0x80 (NULL device *): Bonding Info Received: rdev: 000000006c0b8247 __ib_unregister_device+0x42/0xb0 [ib_core] (NULL device *): Master: mode: 4 num_slaves:2 ib_unregister_device+0x22/0x30 [ib_core] (NULL device *): Slave: id: 105069936 name:p2p1 link:0 state:0 bnxt_re_stopqps_and_ib_uninit+0x83/0x90 [bnxt_re] bnxt_re_alloc_lag+0x12e/0x4e0 [bnxt_re] Fixes: a42d985bd5b2 ("ib_srpt: Initial SRP Target merge for v3.3-rc1") Reviewed-by: Selvin Xavier Reviewed-by: Kashyap Desai Signed-off-by: Saravanan Vajravel Link: https://lore.kernel.org/r/20230406042549.507328-1-saravanan.vajravel@broadcom.com Reviewed-by: Bart Van Assche Signed-off-by: Leon Romanovsky --- drivers/infiniband/ulp/srpt/ib_srpt.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 3c3fae738c3e..25e799dba999 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -549,6 +549,7 @@ static int srpt_format_guid(char *buf, unsigned int size, const __be64 *guid) */ static int srpt_refresh_port(struct srpt_port *sport) { + struct ib_mad_agent *mad_agent; struct ib_mad_reg_req reg_req; struct ib_port_modify port_modify; struct ib_port_attr port_attr; @@ -593,24 +594,26 @@ static int srpt_refresh_port(struct srpt_port *sport) set_bit(IB_MGMT_METHOD_GET, reg_req.method_mask); set_bit(IB_MGMT_METHOD_SET, reg_req.method_mask); - sport->mad_agent = ib_register_mad_agent(sport->sdev->device, - sport->port, - IB_QPT_GSI, - ®_req, 0, - srpt_mad_send_handler, - srpt_mad_recv_handler, - sport, 0); - if (IS_ERR(sport->mad_agent)) { + mad_agent = ib_register_mad_agent(sport->sdev->device, + sport->port, + IB_QPT_GSI, + ®_req, 0, + srpt_mad_send_handler, + srpt_mad_recv_handler, + sport, 0); + if (IS_ERR(mad_agent)) { pr_err("%s-%d: MAD agent registration failed (%ld). Note: this is expected if SR-IOV is enabled.\n", dev_name(&sport->sdev->device->dev), sport->port, - PTR_ERR(sport->mad_agent)); + PTR_ERR(mad_agent)); sport->mad_agent = NULL; memset(&port_modify, 0, sizeof(port_modify)); port_modify.clr_port_cap_mask = IB_PORT_DEVICE_MGMT_SUP; ib_modify_port(sport->sdev->device, sport->port, 0, &port_modify); - + return 0; } + + sport->mad_agent = mad_agent; } return 0; -- GitLab From d2590edc93e894137e29d3fa1b5db6a2ecc14b69 Mon Sep 17 00:00:00 2001 From: Dean Luick Date: Fri, 7 Apr 2023 12:52:29 -0400 Subject: [PATCH 2402/5631] IB/hfi1: Remove trace newlines The hfi1_cdbg trace mechanism appends a newline. Remove trailing newlines from all format strings. Signed-off-by: Dean Luick Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088634897.3027109.10401662436950683555.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/chip.c | 18 +++++++++--------- drivers/infiniband/hw/hfi1/driver.c | 2 +- drivers/infiniband/hw/hfi1/file_ops.c | 2 +- drivers/infiniband/hw/hfi1/init.c | 12 ++++++------ drivers/infiniband/hw/hfi1/pio.c | 2 +- 5 files changed, 18 insertions(+), 18 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 90b672feed83..9dbb89e9f4af 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12135,7 +12135,7 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op, set_intr_bits(dd, IS_RCVURGENT_START + rcd->ctxt, IS_RCVURGENT_START + rcd->ctxt, false); - hfi1_cdbg(RCVCTRL, "ctxt %d rcvctrl 0x%llx\n", ctxt, rcvctrl); + hfi1_cdbg(RCVCTRL, "ctxt %d rcvctrl 0x%llx", ctxt, rcvctrl); write_kctxt_csr(dd, ctxt, RCV_CTXT_CTRL, rcvctrl); /* work around sticky RcvCtxtStatus.BlockedRHQFull */ @@ -12205,10 +12205,10 @@ u32 hfi1_read_cntrs(struct hfi1_devdata *dd, char **namep, u64 **cntrp) hfi1_cdbg(CNTR, "reading %s", entry->name); if (entry->flags & CNTR_DISABLED) { /* Nothing */ - hfi1_cdbg(CNTR, "\tDisabled\n"); + hfi1_cdbg(CNTR, "\tDisabled"); } else { if (entry->flags & CNTR_VL) { - hfi1_cdbg(CNTR, "\tPer VL\n"); + hfi1_cdbg(CNTR, "\tPer VL"); for (j = 0; j < C_VL_COUNT; j++) { val = entry->rw_cntr(entry, dd, j, @@ -12216,21 +12216,21 @@ u32 hfi1_read_cntrs(struct hfi1_devdata *dd, char **namep, u64 **cntrp) 0); hfi1_cdbg( CNTR, - "\t\tRead 0x%llx for %d\n", + "\t\tRead 0x%llx for %d", val, j); dd->cntrs[entry->offset + j] = val; } } else if (entry->flags & CNTR_SDMA) { hfi1_cdbg(CNTR, - "\t Per SDMA Engine\n"); + "\t Per SDMA Engine"); for (j = 0; j < chip_sdma_engines(dd); j++) { val = entry->rw_cntr(entry, dd, j, CNTR_MODE_R, 0); hfi1_cdbg(CNTR, - "\t\tRead 0x%llx for %d\n", + "\t\tRead 0x%llx for %d", val, j); dd->cntrs[entry->offset + j] = val; @@ -12271,7 +12271,7 @@ u32 hfi1_read_portcntrs(struct hfi1_pportdata *ppd, char **namep, u64 **cntrp) hfi1_cdbg(CNTR, "reading %s", entry->name); if (entry->flags & CNTR_DISABLED) { /* Nothing */ - hfi1_cdbg(CNTR, "\tDisabled\n"); + hfi1_cdbg(CNTR, "\tDisabled"); continue; } @@ -12513,7 +12513,7 @@ static void do_update_synth_timer(struct work_struct *work) hfi1_cdbg( CNTR, - "[%d] curr tx=0x%llx rx=0x%llx :: last tx=0x%llx rx=0x%llx\n", + "[%d] curr tx=0x%llx rx=0x%llx :: last tx=0x%llx rx=0x%llx", dd->unit, cur_tx, cur_rx, dd->last_tx, dd->last_rx); if ((cur_tx < dd->last_tx) || (cur_rx < dd->last_rx)) { @@ -12527,7 +12527,7 @@ static void do_update_synth_timer(struct work_struct *work) } else { total_flits = (cur_tx - dd->last_tx) + (cur_rx - dd->last_rx); hfi1_cdbg(CNTR, - "[%d] total flits 0x%llx limit 0x%llx\n", dd->unit, + "[%d] total flits 0x%llx limit 0x%llx", dd->unit, total_flits, (u64)CNTR_32BIT_MAX); if (total_flits >= CNTR_32BIT_MAX) { hfi1_cdbg(CNTR, "[%d] 32bit limit hit, updating", diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index bcc6bc0540f0..f4492fa407e0 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -1597,7 +1597,7 @@ static int hfi1_setup_bypass_packet(struct hfi1_packet *packet) return 0; drop: - hfi1_cdbg(PKT, "%s: packet dropped\n", __func__); + hfi1_cdbg(PKT, "%s: packet dropped", __func__); ibp->rvp.n_pkt_drops++; return -EINVAL; } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index b1d6ca7e9708..acbc52bdf841 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -977,7 +977,7 @@ static int allocate_ctxt(struct hfi1_filedata *fd, struct hfi1_devdata *dd, ret = -ENOMEM; goto ctxdata_free; } - hfi1_cdbg(PROC, "allocated send context %u(%u)\n", uctxt->sc->sw_index, + hfi1_cdbg(PROC, "allocated send context %u(%u)", uctxt->sc->sw_index, uctxt->sc->hw_context); ret = sc_enable(uctxt->sc); if (ret) diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 62b6c5020039..6de37c5d7d27 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -342,7 +342,7 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa, INIT_LIST_HEAD(&rcd->flow_queue.queue_head); INIT_LIST_HEAD(&rcd->rarr_queue.queue_head); - hfi1_cdbg(PROC, "setting up context %u\n", rcd->ctxt); + hfi1_cdbg(PROC, "setting up context %u", rcd->ctxt); /* * Calculate the context's RcvArray entry starting point. @@ -400,7 +400,7 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa, rcd->egrbufs.count = MAX_EAGER_ENTRIES; } hfi1_cdbg(PROC, - "ctxt%u: max Eager buffer RcvArray entries: %u\n", + "ctxt%u: max Eager buffer RcvArray entries: %u", rcd->ctxt, rcd->egrbufs.count); /* @@ -432,7 +432,7 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa, if (rcd->egrbufs.size < hfi1_max_mtu) { rcd->egrbufs.size = __roundup_pow_of_two(hfi1_max_mtu); hfi1_cdbg(PROC, - "ctxt%u: eager bufs size too small. Adjusting to %u\n", + "ctxt%u: eager bufs size too small. Adjusting to %u", rcd->ctxt, rcd->egrbufs.size); } rcd->egrbufs.rcvtid_size = HFI1_MAX_EAGER_BUFFER_SIZE; @@ -1920,7 +1920,7 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd) rcd->egrbufs.size = alloced_bytes; hfi1_cdbg(PROC, - "ctxt%u: Alloced %u rcv tid entries @ %uKB, total %uKB\n", + "ctxt%u: Alloced %u rcv tid entries @ %uKB, total %uKB", rcd->ctxt, rcd->egrbufs.alloced, rcd->egrbufs.rcvtid_size / 1024, rcd->egrbufs.size / 1024); @@ -1943,13 +1943,13 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd) rcd->expected_count = MAX_TID_PAIR_ENTRIES * 2; rcd->expected_base = rcd->eager_base + egrtop; - hfi1_cdbg(PROC, "ctxt%u: eager:%u, exp:%u, egrbase:%u, expbase:%u\n", + hfi1_cdbg(PROC, "ctxt%u: eager:%u, exp:%u, egrbase:%u, expbase:%u", rcd->ctxt, rcd->egrbufs.alloced, rcd->expected_count, rcd->eager_base, rcd->expected_base); if (!hfi1_rcvbuf_validate(rcd->egrbufs.rcvtid_size, PT_EAGER, &order)) { hfi1_cdbg(PROC, - "ctxt%u: current Eager buffer size is invalid %u\n", + "ctxt%u: current Eager buffer size is invalid %u", rcd->ctxt, rcd->egrbufs.rcvtid_size); ret = -EINVAL; goto bail_rcvegrbuf_phys; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 51ae58c02b15..62e7dc9bea7b 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -820,7 +820,7 @@ struct send_context *sc_alloc(struct hfi1_devdata *dd, int type, } hfi1_cdbg(PIO, - "Send context %u(%u) %s group %u credits %u credit_ctrl 0x%llx threshold %u\n", + "Send context %u(%u) %s group %u credits %u credit_ctrl 0x%llx threshold %u", sw_index, hw_context, sc_type_name(type), -- GitLab From cf0455f1a92b7eb3075f84c7c086207ced08e0f5 Mon Sep 17 00:00:00 2001 From: Ehab Ababneh Date: Fri, 7 Apr 2023 12:52:34 -0400 Subject: [PATCH 2403/5631] IB/hfi1: Suppress useless compiler warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These warnings can cause build failure: In file included from ./include/trace/define_trace.h:102, from drivers/infiniband/hw/hfi1/trace_dbg.h:111, from drivers/infiniband/hw/hfi1/trace.h:15, from drivers/infiniband/hw/hfi1/trace.c:6: drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘trace_event_get_offsets_hfi1_trace_template’: ./include/trace/trace_events.h:261:9: warning: function ‘trace_event_get_offsets_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] struct trace_event_raw_##call __maybe_unused *entry; \ ^~~~~~~~~~~~~~~~ drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’ DECLARE_EVENT_CLASS(hfi1_trace_template, ^~~~~~~~~~~~~~~~~~~ In file included from ./include/trace/define_trace.h:102, from drivers/infiniband/hw/hfi1/trace_dbg.h:111, from drivers/infiniband/hw/hfi1/trace.h:15, from drivers/infiniband/hw/hfi1/trace.c:6: drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘trace_event_raw_event_hfi1_trace_template’: ./include/trace/trace_events.h:386:9: warning: function ‘trace_event_raw_event_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] struct trace_event_raw_##call *entry; \ ^~~~~~~~~~~~~~~~ drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’ DECLARE_EVENT_CLASS(hfi1_trace_template, ^~~~~~~~~~~~~~~~~~~ In file included from ./include/trace/define_trace.h:103, from drivers/infiniband/hw/hfi1/trace_dbg.h:111, from drivers/infiniband/hw/hfi1/trace.h:15, from drivers/infiniband/hw/hfi1/trace.c:6: drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘perf_trace_hfi1_trace_template’: ./include/trace/perf.h:70:9: warning: function ‘perf_trace_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format] struct hlist_head *head; \ ^~~~~~~~~~ drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’ DECLARE_EVENT_CLASS(hfi1_trace_template, ^~~~~~~~~~~~~~~~~~~ Solution adapted here is similar to the one in fbbc95a49d5b0 Signed-off-by: Ehab Ababneh Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088635415.3027109.5711716700328939402.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/trace_dbg.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/infiniband/hw/hfi1/trace_dbg.h b/drivers/infiniband/hw/hfi1/trace_dbg.h index 582b6f68df3d..489395bfb5b3 100644 --- a/drivers/infiniband/hw/hfi1/trace_dbg.h +++ b/drivers/infiniband/hw/hfi1/trace_dbg.h @@ -22,6 +22,11 @@ #define MAX_MSG_LEN 512 +#pragma GCC diagnostic push +#ifndef __clang__ +#pragma GCC diagnostic ignored "-Wsuggest-attribute=format" +#endif + DECLARE_EVENT_CLASS(hfi1_trace_template, TP_PROTO(const char *function, struct va_format *vaf), TP_ARGS(function, vaf), @@ -36,6 +41,8 @@ DECLARE_EVENT_CLASS(hfi1_trace_template, __get_str(msg)) ); +#pragma GCC diagnostic pop + /* * It may be nice to macroize the __hfi1_trace but the va_* stuff requires an * actual function to work and can not be in a macro. -- GitLab From 9fe8fec5e43d5a80f43cbf61aaada1b047a1eb61 Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Fri, 7 Apr 2023 12:52:39 -0400 Subject: [PATCH 2404/5631] IB/hfi1: Fix SDMA mmu_rb_node not being evicted in LRU order hfi1_mmu_rb_remove_unless_exact() did not move mmu_rb_node objects in mmu_rb_handler->lru_list after getting a cache hit on an mmu_rb_node. As a result, hfi1_mmu_rb_evict() was not guaranteed to evict truly least-recently used nodes. This could be a performance issue for an application when that application: - Uses some long-lived buffers frequently. - Uses a large number of buffers once. - Hits the mmu_rb_handler cache size or pinned-page limits, forcing mmu_rb_handler cache entries to be evicted. In this case, the one-time use buffers cause the long-lived buffer entries to eventually filter to the end of the LRU list where hfi1_mmu_rb_evict() will consider evicting a frequently-used long-lived entry instead of evicting one of the one-time use entries. Fix this by inserting new mmu_rb_node at the tail of mmu_rb_handler->lru_list and move mmu_rb_ndoe to the tail of mmu_rb_handler->lru_list when the mmu_rb_node is a hit in hfi1_mmu_rb_remove_unless_exact(). Change hfi1_mmu_rb_evict() to evict from the head of mmu_rb_handler->lru_list instead of the tail. Fixes: 0636e9ab8355 ("IB/hfi1: Add cache evict LRU list") Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088635931.3027109.10423156330761536044.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/mmu_rb.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 7333646021bb..af46ff203342 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -130,7 +130,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, goto unlock; } __mmu_int_rb_insert(mnode, &handler->root); - list_add(&mnode->list, &handler->lru_list); + list_add_tail(&mnode->list, &handler->lru_list); ret = handler->ops->insert(handler->ops_arg, mnode); if (ret) { @@ -181,8 +181,10 @@ bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, addr, len); if (node) { - if (node->addr == addr && node->len == len) + if (node->addr == addr && node->len == len) { + list_move_tail(&node->list, &handler->lru_list); goto unlock; + } __mmu_int_rb_remove(node, &handler->root); list_del(&node->list); /* remove from LRU list */ ret = true; @@ -206,8 +208,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) INIT_LIST_HEAD(&del_list); spin_lock_irqsave(&handler->lock, flags); - list_for_each_entry_safe_reverse(rbnode, ptr, &handler->lru_list, - list) { + list_for_each_entry_safe(rbnode, ptr, &handler->lru_list, list) { if (handler->ops->evict(handler->ops_arg, rbnode, evict_arg, &stop)) { __mmu_int_rb_remove(rbnode, &handler->root); @@ -219,9 +220,7 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) } spin_unlock_irqrestore(&handler->lock, flags); - while (!list_empty(&del_list)) { - rbnode = list_first_entry(&del_list, struct mmu_rb_node, list); - list_del(&rbnode->list); + list_for_each_entry_safe(rbnode, ptr, &del_list, list) { handler->ops->remove(handler->ops_arg, rbnode); } } -- GitLab From 00cbce5cbf88459cd1aa1d60d0f1df15477df127 Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Fri, 7 Apr 2023 12:52:44 -0400 Subject: [PATCH 2405/5631] IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests hfi1 user SDMA request processing has two bugs that can cause data corruption for user SDMA requests that have multiple payload iovecs where an iovec other than the tail iovec does not run up to the page boundary for the buffer pointed to by that iovec.a Here are the specific bugs: 1. user_sdma_txadd() does not use struct user_sdma_iovec->iov.iov_len. Rather, user_sdma_txadd() will add up to PAGE_SIZE bytes from iovec to the packet, even if some of those bytes are past iovec->iov.iov_len and are thus not intended to be in the packet. 2. user_sdma_txadd() and user_sdma_send_pkts() fail to advance to the next iovec in user_sdma_request->iovs when the current iovec is not PAGE_SIZE and does not contain enough data to complete the packet. The transmitted packet will contain the wrong data from the iovec pages. This has not been an issue with SDMA packets from hfi1 Verbs or PSM2 because they only produce iovecs that end short of PAGE_SIZE as the tail iovec of an SDMA request. Fixing these bugs exposes other bugs with the SDMA pin cache (struct mmu_rb_handler) that get in way of supporting user SDMA requests with multiple payload iovecs whose buffers do not end at PAGE_SIZE. So this commit fixes those issues as well. Here are the mmu_rb_handler bugs that non-PAGE_SIZE-end multi-iovec payload user SDMA requests can hit: 1. Overlapping memory ranges in mmu_rb_handler will result in duplicate pinnings. 2. When extending an existing mmu_rb_handler entry (struct mmu_rb_node), the mmu_rb code (1) removes the existing entry under a lock, (2) releases that lock, pins the new pages, (3) then reacquires the lock to insert the extended mmu_rb_node. If someone else comes in and inserts an overlapping entry between (2) and (3), insert in (3) will fail. The failure path code in this case unpins _all_ pages in either the original mmu_rb_node or the new mmu_rb_node that was inserted between (2) and (3). 3. In hfi1_mmu_rb_remove_unless_exact(), mmu_rb_node->refcount is incremented outside of mmu_rb_handler->lock. As a result, mmu_rb_node could be evicted by another thread that gets mmu_rb_handler->lock and checks mmu_rb_node->refcount before mmu_rb_node->refcount is incremented. 4. Related to #2 above, SDMA request submission failure path does not check mmu_rb_node->refcount before freeing mmu_rb_node object. If there are other SDMA requests in progress whose iovecs have pointers to the now-freed mmu_rb_node(s), those pointers to the now-freed mmu_rb nodes will be dereferenced when those SDMA requests complete. Fixes: 7be85676f1d1 ("IB/hfi1: Don't remove RB entry when not needed.") Fixes: 7724105686e7 ("IB/hfi1: add driver files") Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088636445.3027109.10054635277810177889.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/ipoib_tx.c | 1 + drivers/infiniband/hw/hfi1/mmu_rb.c | 66 +-- drivers/infiniband/hw/hfi1/mmu_rb.h | 8 +- drivers/infiniband/hw/hfi1/sdma.c | 21 +- drivers/infiniband/hw/hfi1/sdma.h | 16 +- drivers/infiniband/hw/hfi1/sdma_txreq.h | 1 + drivers/infiniband/hw/hfi1/trace_mmu.h | 4 - drivers/infiniband/hw/hfi1/user_sdma.c | 600 +++++++++++++++--------- drivers/infiniband/hw/hfi1/user_sdma.h | 5 - drivers/infiniband/hw/hfi1/verbs.c | 4 +- drivers/infiniband/hw/hfi1/vnic_sdma.c | 1 + 11 files changed, 423 insertions(+), 304 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index 349eb4139136..8973a081d641 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -215,6 +215,7 @@ static int hfi1_ipoib_build_ulp_payload(struct ipoib_txreq *tx, const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; ret = sdma_txadd_page(dd, + NULL, txreq, skb_frag_page(frag), frag->bv_offset, diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index af46ff203342..71b9ac018887 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -126,7 +126,7 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, spin_lock_irqsave(&handler->lock, flags); node = __mmu_rb_search(handler, mnode->addr, mnode->len); if (node) { - ret = -EINVAL; + ret = -EEXIST; goto unlock; } __mmu_int_rb_insert(mnode, &handler->root); @@ -143,6 +143,19 @@ int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, return ret; } +/* Caller must hold handler lock */ +struct mmu_rb_node *hfi1_mmu_rb_get_first(struct mmu_rb_handler *handler, + unsigned long addr, unsigned long len) +{ + struct mmu_rb_node *node; + + trace_hfi1_mmu_rb_search(addr, len); + node = __mmu_int_rb_iter_first(&handler->root, addr, (addr + len) - 1); + if (node) + list_move_tail(&node->list, &handler->lru_list); + return node; +} + /* Caller must hold handler lock */ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, unsigned long addr, @@ -167,34 +180,6 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } -bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len, - struct mmu_rb_node **rb_node) -{ - struct mmu_rb_node *node; - unsigned long flags; - bool ret = false; - - if (current->mm != handler->mn.mm) - return ret; - - spin_lock_irqsave(&handler->lock, flags); - node = __mmu_rb_search(handler, addr, len); - if (node) { - if (node->addr == addr && node->len == len) { - list_move_tail(&node->list, &handler->lru_list); - goto unlock; - } - __mmu_int_rb_remove(node, &handler->root); - list_del(&node->list); /* remove from LRU list */ - ret = true; - } -unlock: - spin_unlock_irqrestore(&handler->lock, flags); - *rb_node = node; - return ret; -} - void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) { struct mmu_rb_node *rbnode, *ptr; @@ -225,29 +210,6 @@ void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg) } } -/* - * It is up to the caller to ensure that this function does not race with the - * mmu invalidate notifier which may be calling the users remove callback on - * 'node'. - */ -void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *node) -{ - unsigned long flags; - - if (current->mm != handler->mn.mm) - return; - - /* Validity of handler and node pointers has been checked by caller. */ - trace_hfi1_mmu_rb_remove(node->addr, node->len); - spin_lock_irqsave(&handler->lock, flags); - __mmu_int_rb_remove(node, &handler->root); - list_del(&node->list); /* remove from LRU list */ - spin_unlock_irqrestore(&handler->lock, flags); - - handler->ops->remove(handler->ops_arg, node); -} - static int mmu_notifier_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index 7417be2b9dc8..ed75acdb7b83 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -52,10 +52,8 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler); int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, struct mmu_rb_node *mnode); void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg); -void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *mnode); -bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler, - unsigned long addr, unsigned long len, - struct mmu_rb_node **rb_node); +struct mmu_rb_node *hfi1_mmu_rb_get_first(struct mmu_rb_handler *handler, + unsigned long addr, + unsigned long len); #endif /* _HFI1_MMU_RB_H */ diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 8ed20392e9f0..bb2552dd29c1 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -1593,22 +1593,7 @@ static inline void sdma_unmap_desc( struct hfi1_devdata *dd, struct sdma_desc *descp) { - switch (sdma_mapping_type(descp)) { - case SDMA_MAP_SINGLE: - dma_unmap_single( - &dd->pcidev->dev, - sdma_mapping_addr(descp), - sdma_mapping_len(descp), - DMA_TO_DEVICE); - break; - case SDMA_MAP_PAGE: - dma_unmap_page( - &dd->pcidev->dev, - sdma_mapping_addr(descp), - sdma_mapping_len(descp), - DMA_TO_DEVICE); - break; - } + system_descriptor_complete(dd, descp); } /* @@ -3128,7 +3113,7 @@ int ext_coal_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx, /* Add descriptor for coalesce buffer */ tx->desc_limit = MAX_DESC; - return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, tx, + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, addr, tx->tlen); } @@ -3167,10 +3152,12 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) return rval; } } + /* finish the one just added */ make_tx_sdma_desc( tx, SDMA_MAP_NONE, + NULL, dd->sdma_pad_phys, sizeof(u32) - (tx->packet_len & (sizeof(u32) - 1))); tx->num_desc++; diff --git a/drivers/infiniband/hw/hfi1/sdma.h b/drivers/infiniband/hw/hfi1/sdma.h index b023fc461bd5..95aaec14c6c2 100644 --- a/drivers/infiniband/hw/hfi1/sdma.h +++ b/drivers/infiniband/hw/hfi1/sdma.h @@ -594,6 +594,7 @@ static inline dma_addr_t sdma_mapping_addr(struct sdma_desc *d) static inline void make_tx_sdma_desc( struct sdma_txreq *tx, int type, + void *pinning_ctx, dma_addr_t addr, size_t len) { @@ -612,6 +613,7 @@ static inline void make_tx_sdma_desc( << SDMA_DESC0_PHY_ADDR_SHIFT) | (((u64)len & SDMA_DESC0_BYTE_COUNT_MASK) << SDMA_DESC0_BYTE_COUNT_SHIFT); + desc->pinning_ctx = pinning_ctx; } /* helper to extend txreq */ @@ -643,6 +645,7 @@ static inline void _sdma_close_tx(struct hfi1_devdata *dd, static inline int _sdma_txadd_daddr( struct hfi1_devdata *dd, int type, + void *pinning_ctx, struct sdma_txreq *tx, dma_addr_t addr, u16 len) @@ -652,6 +655,7 @@ static inline int _sdma_txadd_daddr( make_tx_sdma_desc( tx, type, + pinning_ctx, addr, len); WARN_ON(len > tx->tlen); tx->num_desc++; @@ -672,6 +676,7 @@ static inline int _sdma_txadd_daddr( /** * sdma_txadd_page() - add a page to the sdma_txreq * @dd: the device to use for mapping + * @pinning_ctx: context to be released at descriptor retirement * @tx: tx request to which the page is added * @page: page to map * @offset: offset within the page @@ -687,6 +692,7 @@ static inline int _sdma_txadd_daddr( */ static inline int sdma_txadd_page( struct hfi1_devdata *dd, + void *pinning_ctx, struct sdma_txreq *tx, struct page *page, unsigned long offset, @@ -714,8 +720,7 @@ static inline int sdma_txadd_page( return -ENOSPC; } - return _sdma_txadd_daddr( - dd, SDMA_MAP_PAGE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_PAGE, pinning_ctx, tx, addr, len); } /** @@ -749,7 +754,8 @@ static inline int sdma_txadd_daddr( return rval; } - return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_NONE, NULL, tx, + addr, len); } /** @@ -795,8 +801,7 @@ static inline int sdma_txadd_kvaddr( return -ENOSPC; } - return _sdma_txadd_daddr( - dd, SDMA_MAP_SINGLE, tx, addr, len); + return _sdma_txadd_daddr(dd, SDMA_MAP_SINGLE, NULL, tx, addr, len); } struct iowait_work; @@ -1030,4 +1035,5 @@ extern uint mod_num_sdma; void sdma_update_lmc(struct hfi1_devdata *dd, u64 mask, u32 lid); +void system_descriptor_complete(struct hfi1_devdata *dd, struct sdma_desc *descp); #endif diff --git a/drivers/infiniband/hw/hfi1/sdma_txreq.h b/drivers/infiniband/hw/hfi1/sdma_txreq.h index e262fb5c5ec6..fad946cb5e0d 100644 --- a/drivers/infiniband/hw/hfi1/sdma_txreq.h +++ b/drivers/infiniband/hw/hfi1/sdma_txreq.h @@ -19,6 +19,7 @@ struct sdma_desc { /* private: don't use directly */ u64 qw[2]; + void *pinning_ctx; }; /** diff --git a/drivers/infiniband/hw/hfi1/trace_mmu.h b/drivers/infiniband/hw/hfi1/trace_mmu.h index 187e9244fe5e..57900ebb7702 100644 --- a/drivers/infiniband/hw/hfi1/trace_mmu.h +++ b/drivers/infiniband/hw/hfi1/trace_mmu.h @@ -37,10 +37,6 @@ DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_search, TP_PROTO(unsigned long addr, unsigned long len), TP_ARGS(addr, len)); -DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_rb_remove, - TP_PROTO(unsigned long addr, unsigned long len), - TP_ARGS(addr, len)); - DEFINE_EVENT(hfi1_mmu_rb_template, hfi1_mmu_mem_invalidate, TP_PROTO(unsigned long addr, unsigned long len), TP_ARGS(addr, len)); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index a71c5a36ceba..ae58b48afe07 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -24,7 +24,6 @@ #include "hfi.h" #include "sdma.h" -#include "mmu_rb.h" #include "user_sdma.h" #include "verbs.h" /* for the headers */ #include "common.h" /* for struct hfi1_tid_info */ @@ -39,11 +38,7 @@ static unsigned initial_pkt_count = 8; static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts); static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status); static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq); -static void user_sdma_free_request(struct user_sdma_request *req, bool unpin); -static int pin_vector_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec); -static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned start, unsigned npages); +static void user_sdma_free_request(struct user_sdma_request *req); static int check_header_template(struct user_sdma_request *req, struct hfi1_pkt_header *hdr, u32 lrhlen, u32 datalen); @@ -81,6 +76,11 @@ static struct mmu_rb_ops sdma_rb_ops = { .invalidate = sdma_rb_invalidate }; +static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + u32 *pkt_remaining); + static int defer_packet_queue( struct sdma_engine *sde, struct iowait_work *wait, @@ -410,6 +410,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, ret = -EINVAL; goto free_req; } + /* Copy the header from the user buffer */ ret = copy_from_user(&req->hdr, iovec[idx].iov_base + sizeof(info), sizeof(req->hdr)); @@ -484,9 +485,8 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, memcpy(&req->iovs[i].iov, iovec + idx++, sizeof(req->iovs[i].iov)); - ret = pin_vector_pages(req, &req->iovs[i]); - if (ret) { - req->data_iovs = i; + if (req->iovs[i].iov.iov_len == 0) { + ret = -EINVAL; goto free_req; } req->data_len += req->iovs[i].iov.iov_len; @@ -584,7 +584,7 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, if (req->seqsubmitted) wait_event(pq->busy.wait_dma, (req->seqcomp == req->seqsubmitted - 1)); - user_sdma_free_request(req, true); + user_sdma_free_request(req); pq_update(pq); set_comp_state(pq, cq, info.comp_idx, ERROR, ret); } @@ -696,48 +696,6 @@ static int user_sdma_txadd_ahg(struct user_sdma_request *req, return ret; } -static int user_sdma_txadd(struct user_sdma_request *req, - struct user_sdma_txreq *tx, - struct user_sdma_iovec *iovec, u32 datalen, - u32 *queued_ptr, u32 *data_sent_ptr, - u64 *iov_offset_ptr) -{ - int ret; - unsigned int pageidx, len; - unsigned long base, offset; - u64 iov_offset = *iov_offset_ptr; - u32 queued = *queued_ptr, data_sent = *data_sent_ptr; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - - base = (unsigned long)iovec->iov.iov_base; - offset = offset_in_page(base + iovec->offset + iov_offset); - pageidx = (((iovec->offset + iov_offset + base) - (base & PAGE_MASK)) >> - PAGE_SHIFT); - len = offset + req->info.fragsize > PAGE_SIZE ? - PAGE_SIZE - offset : req->info.fragsize; - len = min((datalen - queued), len); - ret = sdma_txadd_page(pq->dd, &tx->txreq, iovec->pages[pageidx], - offset, len); - if (ret) { - SDMA_DBG(req, "SDMA txreq add page failed %d\n", ret); - return ret; - } - iov_offset += len; - queued += len; - data_sent += len; - if (unlikely(queued < datalen && pageidx == iovec->npages && - req->iov_idx < req->data_iovs - 1)) { - iovec->offset += iov_offset; - iovec = &req->iovs[++req->iov_idx]; - iov_offset = 0; - } - - *queued_ptr = queued; - *data_sent_ptr = data_sent; - *iov_offset_ptr = iov_offset; - return ret; -} - static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) { int ret = 0; @@ -769,8 +727,7 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) maxpkts = req->info.npkts - req->seqnum; while (npkts < maxpkts) { - u32 datalen = 0, queued = 0, data_sent = 0; - u64 iov_offset = 0; + u32 datalen = 0; /* * Check whether any of the completions have come back @@ -863,27 +820,17 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) goto free_txreq; } - /* - * If the request contains any data vectors, add up to - * fragsize bytes to the descriptor. - */ - while (queued < datalen && - (req->sent + data_sent) < req->data_len) { - ret = user_sdma_txadd(req, tx, iovec, datalen, - &queued, &data_sent, &iov_offset); - if (ret) - goto free_txreq; - } - /* - * The txreq was submitted successfully so we can update - * the counters. - */ req->koffset += datalen; if (req_opcode(req->info.ctrl) == EXPECTED) req->tidoffset += datalen; - req->sent += data_sent; - if (req->data_len) - iovec->offset += iov_offset; + req->sent += datalen; + while (datalen) { + ret = add_system_pages_to_sdma_packet(req, tx, iovec, + &datalen); + if (ret) + goto free_txreq; + iovec = &req->iovs[req->iov_idx]; + } list_add_tail(&tx->txreq.list, &req->txps); /* * It is important to increment this here as it is used to @@ -920,133 +867,14 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, u16 maxpkts) static u32 sdma_cache_evict(struct hfi1_user_sdma_pkt_q *pq, u32 npages) { struct evict_data evict_data; + struct mmu_rb_handler *handler = pq->handler; evict_data.cleared = 0; evict_data.target = npages; - hfi1_mmu_rb_evict(pq->handler, &evict_data); + hfi1_mmu_rb_evict(handler, &evict_data); return evict_data.cleared; } -static int pin_sdma_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec, - struct sdma_mmu_node *node, - int npages) -{ - int pinned, cleared; - struct page **pages; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - - pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); - if (!pages) - return -ENOMEM; - memcpy(pages, node->pages, node->npages * sizeof(*pages)); - - npages -= node->npages; -retry: - if (!hfi1_can_pin_pages(pq->dd, current->mm, - atomic_read(&pq->n_locked), npages)) { - cleared = sdma_cache_evict(pq, npages); - if (cleared >= npages) - goto retry; - } - pinned = hfi1_acquire_user_pages(current->mm, - ((unsigned long)iovec->iov.iov_base + - (node->npages * PAGE_SIZE)), npages, 0, - pages + node->npages); - if (pinned < 0) { - kfree(pages); - return pinned; - } - if (pinned != npages) { - unpin_vector_pages(current->mm, pages, node->npages, pinned); - return -EFAULT; - } - kfree(node->pages); - node->rb.len = iovec->iov.iov_len; - node->pages = pages; - atomic_add(pinned, &pq->n_locked); - return pinned; -} - -static void unpin_sdma_pages(struct sdma_mmu_node *node) -{ - if (node->npages) { - unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, - node->npages); - atomic_sub(node->npages, &node->pq->n_locked); - } -} - -static int pin_vector_pages(struct user_sdma_request *req, - struct user_sdma_iovec *iovec) -{ - int ret = 0, pinned, npages; - struct hfi1_user_sdma_pkt_q *pq = req->pq; - struct sdma_mmu_node *node = NULL; - struct mmu_rb_node *rb_node; - struct iovec *iov; - bool extracted; - - extracted = - hfi1_mmu_rb_remove_unless_exact(pq->handler, - (unsigned long) - iovec->iov.iov_base, - iovec->iov.iov_len, &rb_node); - if (rb_node) { - node = container_of(rb_node, struct sdma_mmu_node, rb); - if (!extracted) { - atomic_inc(&node->refcount); - iovec->pages = node->pages; - iovec->npages = node->npages; - iovec->node = node; - return 0; - } - } - - if (!node) { - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return -ENOMEM; - - node->rb.addr = (unsigned long)iovec->iov.iov_base; - node->pq = pq; - atomic_set(&node->refcount, 0); - } - - iov = &iovec->iov; - npages = num_user_pages((unsigned long)iov->iov_base, iov->iov_len); - if (node->npages < npages) { - pinned = pin_sdma_pages(req, iovec, node, npages); - if (pinned < 0) { - ret = pinned; - goto bail; - } - node->npages += pinned; - npages = node->npages; - } - iovec->pages = node->pages; - iovec->npages = npages; - iovec->node = node; - - ret = hfi1_mmu_rb_insert(req->pq->handler, &node->rb); - if (ret) { - iovec->node = NULL; - goto bail; - } - return 0; -bail: - unpin_sdma_pages(node); - kfree(node); - return ret; -} - -static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned start, unsigned npages) -{ - hfi1_release_user_pages(mm, pages + start, npages, false); - kfree(pages); -} - static int check_header_template(struct user_sdma_request *req, struct hfi1_pkt_header *hdr, u32 lrhlen, u32 datalen) @@ -1388,7 +1216,7 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status) if (req->seqcomp != req->info.npkts - 1) return; - user_sdma_free_request(req, false); + user_sdma_free_request(req); set_comp_state(pq, cq, req->info.comp_idx, state, status); pq_update(pq); } @@ -1399,10 +1227,8 @@ static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq) wake_up(&pq->wait); } -static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) +static void user_sdma_free_request(struct user_sdma_request *req) { - int i; - if (!list_empty(&req->txps)) { struct sdma_txreq *t, *p; @@ -1415,21 +1241,6 @@ static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) } } - for (i = 0; i < req->data_iovs; i++) { - struct sdma_mmu_node *node = req->iovs[i].node; - - if (!node) - continue; - - req->iovs[i].node = NULL; - - if (unpin) - hfi1_mmu_rb_remove(req->pq->handler, - &node->rb); - else - atomic_dec(&node->refcount); - } - kfree(req->tids); clear_bit(req->info.comp_idx, req->pq->req_in_use); } @@ -1447,6 +1258,368 @@ static inline void set_comp_state(struct hfi1_user_sdma_pkt_q *pq, idx, state, ret); } +static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, + unsigned int start, unsigned int npages) +{ + hfi1_release_user_pages(mm, pages + start, npages, false); + kfree(pages); +} + +static void free_system_node(struct sdma_mmu_node *node) +{ + if (node->npages) { + unpin_vector_pages(mm_from_sdma_node(node), node->pages, 0, + node->npages); + atomic_sub(node->npages, &node->pq->n_locked); + } + kfree(node); +} + +static inline void acquire_node(struct sdma_mmu_node *node) +{ + atomic_inc(&node->refcount); + WARN_ON(atomic_read(&node->refcount) < 0); +} + +static inline void release_node(struct mmu_rb_handler *handler, + struct sdma_mmu_node *node) +{ + atomic_dec(&node->refcount); + WARN_ON(atomic_read(&node->refcount) < 0); +} + +static struct sdma_mmu_node *find_system_node(struct mmu_rb_handler *handler, + unsigned long start, + unsigned long end) +{ + struct mmu_rb_node *rb_node; + struct sdma_mmu_node *node; + unsigned long flags; + + spin_lock_irqsave(&handler->lock, flags); + rb_node = hfi1_mmu_rb_get_first(handler, start, (end - start)); + if (!rb_node) { + spin_unlock_irqrestore(&handler->lock, flags); + return NULL; + } + node = container_of(rb_node, struct sdma_mmu_node, rb); + acquire_node(node); + spin_unlock_irqrestore(&handler->lock, flags); + + return node; +} + +static int pin_system_pages(struct user_sdma_request *req, + uintptr_t start_address, size_t length, + struct sdma_mmu_node *node, int npages) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + int pinned, cleared; + struct page **pages; + + pages = kcalloc(npages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + +retry: + if (!hfi1_can_pin_pages(pq->dd, current->mm, atomic_read(&pq->n_locked), + npages)) { + SDMA_DBG(req, "Evicting: nlocked %u npages %u", + atomic_read(&pq->n_locked), npages); + cleared = sdma_cache_evict(pq, npages); + if (cleared >= npages) + goto retry; + } + + SDMA_DBG(req, "Acquire user pages start_address %lx node->npages %u npages %u", + start_address, node->npages, npages); + pinned = hfi1_acquire_user_pages(current->mm, start_address, npages, 0, + pages); + + if (pinned < 0) { + kfree(pages); + SDMA_DBG(req, "pinned %d", pinned); + return pinned; + } + if (pinned != npages) { + unpin_vector_pages(current->mm, pages, node->npages, pinned); + SDMA_DBG(req, "npages %u pinned %d", npages, pinned); + return -EFAULT; + } + node->rb.addr = start_address; + node->rb.len = length; + node->pages = pages; + node->npages = npages; + atomic_add(pinned, &pq->n_locked); + SDMA_DBG(req, "done. pinned %d", pinned); + return 0; +} + +static int add_system_pinning(struct user_sdma_request *req, + struct sdma_mmu_node **node_p, + unsigned long start, unsigned long len) + +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + struct sdma_mmu_node *node; + int ret; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + + node->pq = pq; + ret = pin_system_pages(req, start, len, node, PFN_DOWN(len)); + if (ret == 0) { + ret = hfi1_mmu_rb_insert(pq->handler, &node->rb); + if (ret) + free_system_node(node); + else + *node_p = node; + + return ret; + } + + kfree(node); + return ret; +} + +static int get_system_cache_entry(struct user_sdma_request *req, + struct sdma_mmu_node **node_p, + size_t req_start, size_t req_len) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + u64 start = ALIGN_DOWN(req_start, PAGE_SIZE); + u64 end = PFN_ALIGN(req_start + req_len); + struct mmu_rb_handler *handler = pq->handler; + int ret; + + if ((end - start) == 0) { + SDMA_DBG(req, + "Request for empty cache entry req_start %lx req_len %lx start %llx end %llx", + req_start, req_len, start, end); + return -EINVAL; + } + + SDMA_DBG(req, "req_start %lx req_len %lu", req_start, req_len); + + while (1) { + struct sdma_mmu_node *node = + find_system_node(handler, start, end); + u64 prepend_len = 0; + + SDMA_DBG(req, "node %p start %llx end %llu", node, start, end); + if (!node) { + ret = add_system_pinning(req, node_p, start, + end - start); + if (ret == -EEXIST) { + /* + * Another execution context has inserted a + * conficting entry first. + */ + continue; + } + return ret; + } + + if (node->rb.addr <= start) { + /* + * This entry covers at least part of the region. If it doesn't extend + * to the end, then this will be called again for the next segment. + */ + *node_p = node; + return 0; + } + + SDMA_DBG(req, "prepend: node->rb.addr %lx, node->refcount %d", + node->rb.addr, atomic_read(&node->refcount)); + prepend_len = node->rb.addr - start; + + /* + * This node will not be returned, instead a new node + * will be. So release the reference. + */ + release_node(handler, node); + + /* Prepend a node to cover the beginning of the allocation */ + ret = add_system_pinning(req, node_p, start, prepend_len); + if (ret == -EEXIST) { + /* Another execution context has inserted a conficting entry first. */ + continue; + } + return ret; + } +} + +static int add_mapping_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct sdma_mmu_node *cache_entry, + size_t start, + size_t from_this_cache_entry) +{ + struct hfi1_user_sdma_pkt_q *pq = req->pq; + unsigned int page_offset; + unsigned int from_this_page; + size_t page_index; + void *ctx; + int ret; + + /* + * Because the cache may be more fragmented than the memory that is being accessed, + * it's not strictly necessary to have a descriptor per cache entry. + */ + + while (from_this_cache_entry) { + page_index = PFN_DOWN(start - cache_entry->rb.addr); + + if (page_index >= cache_entry->npages) { + SDMA_DBG(req, + "Request for page_index %zu >= cache_entry->npages %u", + page_index, cache_entry->npages); + return -EINVAL; + } + + page_offset = start - ALIGN_DOWN(start, PAGE_SIZE); + from_this_page = PAGE_SIZE - page_offset; + + if (from_this_page < from_this_cache_entry) { + ctx = NULL; + } else { + /* + * In the case they are equal the next line has no practical effect, + * but it's better to do a register to register copy than a conditional + * branch. + */ + from_this_page = from_this_cache_entry; + ctx = cache_entry; + } + + ret = sdma_txadd_page(pq->dd, ctx, &tx->txreq, + cache_entry->pages[page_index], + page_offset, from_this_page); + if (ret) { + /* + * When there's a failure, the entire request is freed by + * user_sdma_send_pkts(). + */ + SDMA_DBG(req, + "sdma_txadd_page failed %d page_index %lu page_offset %u from_this_page %u", + ret, page_index, page_offset, from_this_page); + return ret; + } + start += from_this_page; + from_this_cache_entry -= from_this_page; + } + return 0; +} + +static int add_system_iovec_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + size_t from_this_iovec) +{ + struct mmu_rb_handler *handler = req->pq->handler; + + while (from_this_iovec > 0) { + struct sdma_mmu_node *cache_entry; + size_t from_this_cache_entry; + size_t start; + int ret; + + start = (uintptr_t)iovec->iov.iov_base + iovec->offset; + ret = get_system_cache_entry(req, &cache_entry, start, + from_this_iovec); + if (ret) { + SDMA_DBG(req, "pin system segment failed %d", ret); + return ret; + } + + from_this_cache_entry = cache_entry->rb.len - (start - cache_entry->rb.addr); + if (from_this_cache_entry > from_this_iovec) + from_this_cache_entry = from_this_iovec; + + ret = add_mapping_to_sdma_packet(req, tx, cache_entry, start, + from_this_cache_entry); + if (ret) { + /* + * We're guaranteed that there will be no descriptor + * completion callback that releases this node + * because only the last descriptor referencing it + * has a context attached, and a failure means the + * last descriptor was never added. + */ + release_node(handler, cache_entry); + SDMA_DBG(req, "add system segment failed %d", ret); + return ret; + } + + iovec->offset += from_this_cache_entry; + from_this_iovec -= from_this_cache_entry; + } + + return 0; +} + +static int add_system_pages_to_sdma_packet(struct user_sdma_request *req, + struct user_sdma_txreq *tx, + struct user_sdma_iovec *iovec, + u32 *pkt_data_remaining) +{ + size_t remaining_to_add = *pkt_data_remaining; + /* + * Walk through iovec entries, ensure the associated pages + * are pinned and mapped, add data to the packet until no more + * data remains to be added. + */ + while (remaining_to_add > 0) { + struct user_sdma_iovec *cur_iovec; + size_t from_this_iovec; + int ret; + + cur_iovec = iovec; + from_this_iovec = iovec->iov.iov_len - iovec->offset; + + if (from_this_iovec > remaining_to_add) { + from_this_iovec = remaining_to_add; + } else { + /* The current iovec entry will be consumed by this pass. */ + req->iov_idx++; + iovec++; + } + + ret = add_system_iovec_to_sdma_packet(req, tx, cur_iovec, + from_this_iovec); + if (ret) + return ret; + + remaining_to_add -= from_this_iovec; + } + *pkt_data_remaining = remaining_to_add; + + return 0; +} + +void system_descriptor_complete(struct hfi1_devdata *dd, + struct sdma_desc *descp) +{ + switch (sdma_mapping_type(descp)) { + case SDMA_MAP_SINGLE: + dma_unmap_single(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + case SDMA_MAP_PAGE: + dma_unmap_page(&dd->pcidev->dev, sdma_mapping_addr(descp), + sdma_mapping_len(descp), DMA_TO_DEVICE); + break; + } + + if (descp->pinning_ctx) { + struct sdma_mmu_node *node = descp->pinning_ctx; + + release_node(node->rb.handler, node); + } +} + static bool sdma_rb_filter(struct mmu_rb_node *node, unsigned long addr, unsigned long len) { @@ -1493,8 +1666,7 @@ static void sdma_rb_remove(void *arg, struct mmu_rb_node *mnode) struct sdma_mmu_node *node = container_of(mnode, struct sdma_mmu_node, rb); - unpin_sdma_pages(node); - kfree(node); + free_system_node(node); } static int sdma_rb_invalidate(void *arg, struct mmu_rb_node *mnode) diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index ea56eb57e656..a241836371dc 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -112,16 +112,11 @@ struct sdma_mmu_node { struct user_sdma_iovec { struct list_head list; struct iovec iov; - /* number of pages in this vector */ - unsigned int npages; - /* array of pinned pages for this vector */ - struct page **pages; /* * offset into the virtual address space of the vector at * which we last left off. */ u64 offset; - struct sdma_mmu_node *node; }; /* evict operation argument */ diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 7f6d7fc7951d..fbdcfecb1768 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -778,8 +778,8 @@ static int build_verbs_tx_desc( /* add icrc, lt byte, and padding to flit */ if (extra_bytes) - ret = sdma_txadd_daddr(sde->dd, &tx->txreq, - sde->dd->sdma_pad_phys, extra_bytes); + ret = sdma_txadd_daddr(sde->dd, &tx->txreq, sde->dd->sdma_pad_phys, + extra_bytes); bail_txadd: return ret; diff --git a/drivers/infiniband/hw/hfi1/vnic_sdma.c b/drivers/infiniband/hw/hfi1/vnic_sdma.c index c3f0f8d877c3..727eedfba332 100644 --- a/drivers/infiniband/hw/hfi1/vnic_sdma.c +++ b/drivers/infiniband/hw/hfi1/vnic_sdma.c @@ -64,6 +64,7 @@ static noinline int build_vnic_ulp_payload(struct sdma_engine *sde, /* combine physically continuous fragments later? */ ret = sdma_txadd_page(sde->dd, + NULL, &tx->txreq, skb_frag_page(frag), skb_frag_off(frag), -- GitLab From 866694afd644cd5ee32411713c3d802fcca22ebb Mon Sep 17 00:00:00 2001 From: Patrick Kelsey Date: Fri, 7 Apr 2023 12:52:49 -0400 Subject: [PATCH 2406/5631] IB/hfi1: Place struct mmu_rb_handler on cache line start Place struct mmu_rb_handler on cache line start like so: struct mmu_rb_handler *h; void *free_ptr; int ret; free_ptr = kzalloc(sizeof(*h) + cache_line_size() - 1, GFP_KERNEL); if (!free_ptr) return -ENOMEM; h = PTR_ALIGN(free_ptr, cache_line_size()); Additionally, move struct mmu_rb_handler fields "root" and "ops_args" to start after the next cacheline using the "____cacheline_aligned_in_smp" annotation. Allocating an additional cache_line_size() - 1 bytes to place struct mmu_rb_handler on a cache line start does increase memory consumption. However, few struct mmu_rb_handler are created when hfi1 is in use. As mmu_rb_handler->root and mmu_rb_handler->ops_args are accessed frequently, the advantage of having them both within a cache line is expected to outweigh the disadvantage of the additional memory consumption per struct mmu_rb_handler. Signed-off-by: Brendan Cunningham Signed-off-by: Patrick Kelsey Signed-off-by: Dennis Dalessandro Link: https://lore.kernel.org/r/168088636963.3027109.16959757980497822530.stgit@252.162.96.66.static.eigbox.net Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hfi1/mmu_rb.c | 11 +++++++---- drivers/infiniband/hw/hfi1/mmu_rb.h | 14 ++++++++++++-- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 71b9ac018887..1cea8b0c78e0 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -46,12 +46,14 @@ int hfi1_mmu_rb_register(void *ops_arg, struct mmu_rb_handler **handler) { struct mmu_rb_handler *h; + void *free_ptr; int ret; - h = kzalloc(sizeof(*h), GFP_KERNEL); - if (!h) + free_ptr = kzalloc(sizeof(*h) + cache_line_size() - 1, GFP_KERNEL); + if (!free_ptr) return -ENOMEM; + h = PTR_ALIGN(free_ptr, cache_line_size()); h->root = RB_ROOT_CACHED; h->ops = ops; h->ops_arg = ops_arg; @@ -62,10 +64,11 @@ int hfi1_mmu_rb_register(void *ops_arg, INIT_LIST_HEAD(&h->del_list); INIT_LIST_HEAD(&h->lru_list); h->wq = wq; + h->free_ptr = free_ptr; ret = mmu_notifier_register(&h->mn, current->mm); if (ret) { - kfree(h); + kfree(free_ptr); return ret; } @@ -108,7 +111,7 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) /* Now the mm may be freed. */ mmdrop(handler->mn.mm); - kfree(handler); + kfree(handler->free_ptr); } int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler, diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.h b/drivers/infiniband/hw/hfi1/mmu_rb.h index ed75acdb7b83..c4da064188c9 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.h +++ b/drivers/infiniband/hw/hfi1/mmu_rb.h @@ -33,15 +33,25 @@ struct mmu_rb_ops { }; struct mmu_rb_handler { + /* + * struct mmu_notifier is 56 bytes, and spinlock_t is 4 bytes, so + * they fit together in one cache line. mn is relatively rarely + * accessed, so co-locating the spinlock with it achieves much of + * the cacheline contention reduction of giving the spinlock its own + * cacheline without the overhead of doing so. + */ struct mmu_notifier mn; - struct rb_root_cached root; - void *ops_arg; spinlock_t lock; /* protect the RB tree */ + + /* Begin on a new cachline boundary here */ + struct rb_root_cached root ____cacheline_aligned_in_smp; + void *ops_arg; struct mmu_rb_ops *ops; struct list_head lru_list; struct work_struct del_work; struct list_head del_list; struct workqueue_struct *wq; + void *free_ptr; }; int hfi1_mmu_rb_register(void *ops_arg, -- GitLab From 3ea7c4c907119eb369d6b4cdec22af0434eb5304 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:46:30 +0800 Subject: [PATCH 2407/5631] clk: imx: imx8mp: correct DISP2 pixel clock type The MEDIA_DISP2_CLK_ROOT use ccm_ahb_channel, it is bus type. Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403094633.3366446-1-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8mp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 3253589851ff..4a0f1b739fd4 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -554,7 +554,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100); hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200); - hws[IMX8MP_CLK_MEDIA_DISP2_PIX] = imx8m_clk_hw_composite("media_disp2_pix", imx8mp_media_disp_pix_sels, ccm_base + 0x9300); + hws[IMX8MP_CLK_MEDIA_DISP2_PIX] = imx8m_clk_hw_composite_bus("media_disp2_pix", imx8mp_media_disp_pix_sels, ccm_base + 0x9300); hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1); -- GitLab From 79643567cc34ebd0743f4da3ac8f853e26202453 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:46:31 +0800 Subject: [PATCH 2408/5631] dt-bindings: clock: imx8mp: Add LDB clock entry Add LDB clock entry for i.MX8MP Signed-off-by: Peng Fan Acked-by: Krzysztof Kozlowski Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403094633.3366446-2-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx8mp-clock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h index ede1f65a3147..3f28ce685f41 100644 --- a/include/dt-bindings/clock/imx8mp-clock.h +++ b/include/dt-bindings/clock/imx8mp-clock.h @@ -334,8 +334,8 @@ #define IMX8MP_CLK_SAI6_ROOT 326 #define IMX8MP_CLK_SAI7_ROOT 327 #define IMX8MP_CLK_PDM_ROOT 328 - -#define IMX8MP_CLK_END 329 +#define IMX8MP_CLK_MEDIA_LDB_ROOT 329 +#define IMX8MP_CLK_END 330 #define IMX8MP_CLK_AUDIOMIX_SAI1_IPG 0 #define IMX8MP_CLK_AUDIOMIX_SAI1_MCLK1 1 -- GitLab From 82afc344d795cb467a646a2873573298162f01b9 Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Mon, 3 Apr 2023 17:46:32 +0800 Subject: [PATCH 2409/5631] clk: imx: imx8mp: Add LDB root clock This patch adds "media_ldb_root_clk" clock for the LDB in the MEDIAMIX subsystem. Reviewed-by: Sandor Yu Signed-off-by: Liu Ying Signed-off-by: Dong Aisheng Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230403094633.3366446-3-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8mp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 4a0f1b739fd4..8dcaeb213277 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -696,6 +696,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_disp1_pix_root_clk", "media_disp1_pix", ccm_base + 0x45d0, 0, &share_count_media); hws[IMX8MP_CLK_MEDIA_DISP2_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_disp2_pix_root_clk", "media_disp2_pix", ccm_base + 0x45d0, 0, &share_count_media); hws[IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT] = imx_clk_hw_gate2_shared2("media_mipi_phy1_ref_root", "media_mipi_phy1_ref", ccm_base + 0x45d0, 0, &share_count_media); + hws[IMX8MP_CLK_MEDIA_LDB_ROOT] = imx_clk_hw_gate2_shared2("media_ldb_root_clk", "media_ldb", ccm_base + 0x45d0, 0, &share_count_media); hws[IMX8MP_CLK_MEDIA_ISP_ROOT] = imx_clk_hw_gate2_shared2("media_isp_root_clk", "media_isp", ccm_base + 0x45d0, 0, &share_count_media); hws[IMX8MP_CLK_USDHC3_ROOT] = imx_clk_hw_gate4("usdhc3_root_clk", "usdhc3", ccm_base + 0x45e0, 0); -- GitLab From 7875ee29f877dc76dae2d04648b95811f6a05b41 Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Mon, 3 Apr 2023 17:46:33 +0800 Subject: [PATCH 2410/5631] clk: imx: imx8mp: change the 'nand_usdhc_bus' clock to non-critical The 'nand_usdhc_bus' clock is only need to be enabled when usdhc or nand module is active, so change it to non-critical clock type. Signed-off-by: Haibo Chen Signed-off-by: Peng Fan Link: https://lore.kernel.org/r/20230403094633.3366446-4-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8mp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 8dcaeb213277..f26ae8de4cc6 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -538,7 +538,7 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880); - hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); + hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980); hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00); hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80); -- GitLab From cf8dccfedce848f67eaa42e8839305d028319161 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:52:54 +0800 Subject: [PATCH 2411/5631] clk: imx: fracn-gppll: fix the rate table The Fvco should be range 2.4GHz to 5GHz, the original table voilate the spec, so update the table to fix it. Fixes: c196175acdd3 ("clk: imx: clk-fracn-gppll: Add more freq config for video pll") Fixes: 044034efbeea ("clk: imx: clk-fracn-gppll: fix mfd value") Fixes: 1b26cb8a77a4 ("clk: imx: support fracn gppll") Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-2-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-fracn-gppll.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index a2aaa14fc1ae..ec50c41e2a4c 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -60,18 +60,20 @@ struct clk_fracn_gppll { }; /* - * Fvco = Fref * (MFI + MFN / MFD) - * Fout = Fvco / (rdiv * odiv) + * Fvco = (Fref / rdiv) * (MFI + MFN / MFD) + * Fout = Fvco / odiv + * The (Fref / rdiv) should be in range 20MHz to 40MHz + * The Fvco should be in range 2.5Ghz to 5Ghz */ static const struct imx_fracn_gppll_rate_table fracn_tbl[] = { - PLL_FRACN_GP(650000000U, 81, 0, 1, 0, 3), + PLL_FRACN_GP(650000000U, 162, 50, 100, 0, 6), PLL_FRACN_GP(594000000U, 198, 0, 1, 0, 8), - PLL_FRACN_GP(560000000U, 70, 0, 1, 0, 3), - PLL_FRACN_GP(498000000U, 83, 0, 1, 0, 4), + PLL_FRACN_GP(560000000U, 140, 0, 1, 0, 6), + PLL_FRACN_GP(498000000U, 166, 0, 1, 0, 8), PLL_FRACN_GP(484000000U, 121, 0, 1, 0, 6), PLL_FRACN_GP(445333333U, 167, 0, 1, 0, 9), - PLL_FRACN_GP(400000000U, 50, 0, 1, 0, 3), - PLL_FRACN_GP(393216000U, 81, 92, 100, 0, 5) + PLL_FRACN_GP(400000000U, 200, 0, 1, 0, 12), + PLL_FRACN_GP(393216000U, 163, 84, 100, 0, 10) }; struct imx_fracn_gppll_clk imx_fracn_gppll = { -- GitLab From 4435467b15b069e5a6f50ca9a9260e86b74dbc13 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:52:55 +0800 Subject: [PATCH 2412/5631] clk: imx: fracn-gppll: disable hardware select control When programming PLL, should disable Hardware control select to make PLL controlled by register, not hardware inputs through OSCPLL. Fixes: 1b26cb8a77a4 ("clk: imx: support fracn gppll") Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-3-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-fracn-gppll.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index ec50c41e2a4c..f6674110a88e 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -15,6 +15,7 @@ #include "clk.h" #define PLL_CTRL 0x0 +#define HW_CTRL_SEL BIT(16) #define CLKMUX_BYPASS BIT(2) #define CLKMUX_EN BIT(1) #define POWERUP_MASK BIT(0) @@ -193,6 +194,11 @@ static int clk_fracn_gppll_set_rate(struct clk_hw *hw, unsigned long drate, rate = imx_get_pll_settings(pll, drate); + /* Hardware control select disable. PLL is control by register */ + tmp = readl_relaxed(pll->base + PLL_CTRL); + tmp &= ~HW_CTRL_SEL; + writel_relaxed(tmp, pll->base + PLL_CTRL); + /* Disable output */ tmp = readl_relaxed(pll->base + PLL_CTRL); tmp &= ~CLKMUX_EN; -- GitLab From 56b8d0bf3ea8b0db8543e04a6b97348a543405ab Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:52:56 +0800 Subject: [PATCH 2413/5631] clk: imx: fracn-gppll: support integer pll The fracn gppll could be configured in FRAC or INTEGER mode during hardware design. The current driver only support FRAC mode, while this patch introduces INTEGER support. When the PLL is INTEGER pll, there is no mfn, mfd, the calculation is as below: Fvco_clk = (Fref / DIV[RDIV] ) * DIV[MFI] Fclko_odiv = Fvco_clk / DIV[ODIV] In this patch, we reuse the FRAC pll logic with some condition check to simplify the driver Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-4-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-fracn-gppll.c | 68 +++++++++++++++++++++++++++---- drivers/clk/imx/clk.h | 7 ++++ 2 files changed, 68 insertions(+), 7 deletions(-) diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index f6674110a88e..e2633ad94640 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -53,11 +53,22 @@ .odiv = (_odiv), \ } +#define PLL_FRACN_GP_INTEGER(_rate, _mfi, _rdiv, _odiv) \ + { \ + .rate = (_rate), \ + .mfi = (_mfi), \ + .mfn = 0, \ + .mfd = 0, \ + .rdiv = (_rdiv), \ + .odiv = (_odiv), \ + } + struct clk_fracn_gppll { struct clk_hw hw; void __iomem *base; const struct imx_fracn_gppll_rate_table *rate_table; int rate_count; + u32 flags; }; /* @@ -83,6 +94,24 @@ struct imx_fracn_gppll_clk imx_fracn_gppll = { }; EXPORT_SYMBOL_GPL(imx_fracn_gppll); +/* + * Fvco = (Fref / rdiv) * MFI + * Fout = Fvco / odiv + * The (Fref / rdiv) should be in range 20MHz to 40MHz + * The Fvco should be in range 2.5Ghz to 5Ghz + */ +static const struct imx_fracn_gppll_rate_table int_tbl[] = { + PLL_FRACN_GP_INTEGER(1700000000U, 141, 1, 2), + PLL_FRACN_GP_INTEGER(1400000000U, 175, 1, 3), + PLL_FRACN_GP_INTEGER(900000000U, 150, 1, 4), +}; + +struct imx_fracn_gppll_clk imx_fracn_gppll_integer = { + .rate_table = int_tbl, + .rate_count = ARRAY_SIZE(int_tbl), +}; +EXPORT_SYMBOL_GPL(imx_fracn_gppll_integer); + static inline struct clk_fracn_gppll *to_clk_fracn_gppll(struct clk_hw *hw) { return container_of(hw, struct clk_fracn_gppll, hw); @@ -169,9 +198,15 @@ static unsigned long clk_fracn_gppll_recalc_rate(struct clk_hw *hw, unsigned lon break; } - /* Fvco = Fref * (MFI + MFN / MFD) */ - fvco = fvco * mfi * mfd + fvco * mfn; - do_div(fvco, mfd * rdiv * odiv); + if (pll->flags & CLK_FRACN_GPPLL_INTEGER) { + /* Fvco = (Fref / rdiv) * MFI */ + fvco = fvco * mfi; + do_div(fvco, rdiv * odiv); + } else { + /* Fvco = (Fref / rdiv) * (MFI + MFN / MFD) */ + fvco = fvco * mfi * mfd + fvco * mfn; + do_div(fvco, mfd * rdiv * odiv); + } return (unsigned long)fvco; } @@ -215,8 +250,10 @@ static int clk_fracn_gppll_set_rate(struct clk_hw *hw, unsigned long drate, pll_div = FIELD_PREP(PLL_RDIV_MASK, rate->rdiv) | rate->odiv | FIELD_PREP(PLL_MFI_MASK, rate->mfi); writel_relaxed(pll_div, pll->base + PLL_DIV); - writel_relaxed(rate->mfd, pll->base + PLL_DENOMINATOR); - writel_relaxed(FIELD_PREP(PLL_MFN_MASK, rate->mfn), pll->base + PLL_NUMERATOR); + if (pll->flags & CLK_FRACN_GPPLL_FRACN) { + writel_relaxed(rate->mfd, pll->base + PLL_DENOMINATOR); + writel_relaxed(FIELD_PREP(PLL_MFN_MASK, rate->mfn), pll->base + PLL_NUMERATOR); + } /* Wait for 5us according to fracn mode pll doc */ udelay(5); @@ -300,8 +337,10 @@ static const struct clk_ops clk_fracn_gppll_ops = { .set_rate = clk_fracn_gppll_set_rate, }; -struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, - const struct imx_fracn_gppll_clk *pll_clk) +static struct clk_hw *_imx_clk_fracn_gppll(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk, + u32 pll_flags) { struct clk_fracn_gppll *pll; struct clk_hw *hw; @@ -322,6 +361,7 @@ struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, vo pll->hw.init = &init; pll->rate_table = pll_clk->rate_table; pll->rate_count = pll_clk->rate_count; + pll->flags = pll_flags; hw = &pll->hw; @@ -334,4 +374,18 @@ struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, vo return hw; } + +struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk) +{ + return _imx_clk_fracn_gppll(name, parent_name, base, pll_clk, CLK_FRACN_GPPLL_FRACN); +} EXPORT_SYMBOL_GPL(imx_clk_fracn_gppll); + +struct clk_hw *imx_clk_fracn_gppll_integer(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk) +{ + return _imx_clk_fracn_gppll(name, parent_name, base, pll_clk, CLK_FRACN_GPPLL_INTEGER); +} +EXPORT_SYMBOL_GPL(imx_clk_fracn_gppll_integer); diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index ecce45b0dd70..c8db0c8d4c5d 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -73,6 +73,9 @@ extern struct imx_pll14xx_clk imx_1416x_pll; extern struct imx_pll14xx_clk imx_1443x_pll; extern struct imx_pll14xx_clk imx_1443x_dram_pll; +#define CLK_FRACN_GPPLL_INTEGER BIT(0) +#define CLK_FRACN_GPPLL_FRACN BIT(1) + /* NOTE: Rate table should be kept sorted in descending order. */ struct imx_fracn_gppll_rate_table { unsigned int rate; @@ -91,8 +94,12 @@ struct imx_fracn_gppll_clk { struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, const struct imx_fracn_gppll_clk *pll_clk); +struct clk_hw *imx_clk_fracn_gppll_integer(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk); extern struct imx_fracn_gppll_clk imx_fracn_gppll; +extern struct imx_fracn_gppll_clk imx_fracn_gppll_integer; #define imx_clk_cpu(name, parent_name, div, mux, pll, step) \ to_clk(imx_clk_hw_cpu(name, parent_name, div, mux, pll, step)) -- GitLab From e040897111a12b7647b8f758336b2f14991e9371 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Mon, 3 Apr 2023 17:52:57 +0800 Subject: [PATCH 2414/5631] clk: imx: fracn-gppll: Add 300MHz freq support for imx9 Add 300MHz frequency config support on i.MX93 PLL. Reviewed-by: Ye Li Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-5-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-fracn-gppll.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index e2633ad94640..c54f9999da04 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -85,7 +85,8 @@ static const struct imx_fracn_gppll_rate_table fracn_tbl[] = { PLL_FRACN_GP(484000000U, 121, 0, 1, 0, 6), PLL_FRACN_GP(445333333U, 167, 0, 1, 0, 9), PLL_FRACN_GP(400000000U, 200, 0, 1, 0, 12), - PLL_FRACN_GP(393216000U, 163, 84, 100, 0, 10) + PLL_FRACN_GP(393216000U, 163, 84, 100, 0, 10), + PLL_FRACN_GP(300000000U, 150, 0, 1, 0, 12) }; struct imx_fracn_gppll_clk imx_fracn_gppll = { -- GitLab From a740d7350ff77ce1ebbdc3b9c548dd3bcaf39b31 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:52:58 +0800 Subject: [PATCH 2415/5631] clk: imx: imx93: add mcore_booted module paratemter Add mcore_booted boot parameter which could simplify AMP clock management. To i.MX93, there is CCM(clock control Module) to generate clock root clock, anatop(analog PLL module) to generate PLL, and LPCG (clock gating) to gate clocks to peripherals. As below: anatop->ccm->lpcg->peripheral Linux handles the clock management and the auxiliary core is under control of Linux. Although there is per hardware domain control for LPCG and CCM, auxiliary core normally only use LPCG hardware domain control to avoid linux gate off the clk to peripherals and leave CCM ana anatop to Linux. Reviewed-by: Ye Li Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-6-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-composite-93.c | 8 +++++++- drivers/clk/imx/clk-imx93.c | 2 ++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-composite-93.c b/drivers/clk/imx/clk-composite-93.c index 74a66b0203e4..81164bdcd6cc 100644 --- a/drivers/clk/imx/clk-composite-93.c +++ b/drivers/clk/imx/clk-composite-93.c @@ -222,7 +222,7 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, &clk_mux_ro_ops, div_hw, &clk_divider_ro_ops, NULL, NULL, flags); - } else { + } else if (!mcore_booted) { gate = kzalloc(sizeof(*gate), GFP_KERNEL); if (!gate) goto fail; @@ -238,6 +238,12 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p &imx93_clk_composite_divider_ops, gate_hw, &imx93_clk_composite_gate_ops, flags | CLK_SET_RATE_NO_REPARENT); + } else { + hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, + mux_hw, &imx93_clk_composite_mux_ops, div_hw, + &imx93_clk_composite_divider_ops, NULL, + &imx93_clk_composite_gate_ops, + flags | CLK_SET_RATE_NO_REPARENT); } if (IS_ERR(hw)) diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index 8d0974db6bfd..de1ed1d8ba54 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -352,6 +352,8 @@ static struct platform_driver imx93_clk_driver = { }, }; module_platform_driver(imx93_clk_driver); +module_param(mcore_booted, bool, 0444); +MODULE_PARM_DESC(mcore_booted, "See Cortex-M core is booted or not"); MODULE_DESCRIPTION("NXP i.MX93 clock driver"); MODULE_LICENSE("GPL v2"); -- GitLab From 5fd7b00ca2361c81f2026f82dff93e52afd97a0b Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:52:59 +0800 Subject: [PATCH 2416/5631] dt-bindings: clock: imx93: add NIC, A55 and ARM PLL CLK Add i.MX93 NIC, A55 and ARM PLL CLK. Signed-off-by: Peng Fan Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230403095300.3386988-7-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- include/dt-bindings/clock/imx93-clock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/include/dt-bindings/clock/imx93-clock.h b/include/dt-bindings/clock/imx93-clock.h index 8e02859d8ce2..35a1f62053a5 100644 --- a/include/dt-bindings/clock/imx93-clock.h +++ b/include/dt-bindings/clock/imx93-clock.h @@ -199,6 +199,10 @@ #define IMX93_CLK_MU1_B_GATE 194 #define IMX93_CLK_MU2_A_GATE 195 #define IMX93_CLK_MU2_B_GATE 196 -#define IMX93_CLK_END 197 +#define IMX93_CLK_NIC_AXI 197 +#define IMX93_CLK_ARM_PLL 198 +#define IMX93_CLK_A55_SEL 199 +#define IMX93_CLK_A55_CORE 200 +#define IMX93_CLK_END 201 #endif -- GitLab From 6b60c3ae3e98d036945f2d5c11d35b4c178ea423 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Mon, 3 Apr 2023 17:53:00 +0800 Subject: [PATCH 2417/5631] clk: imx: imx93: Add nic and A55 clk The A55 clock logic as below: A55_PLL ----------------->\ A55_SEL-->A55_CORE A55_CCM_ROOT--->A55_GATE->/ Add A55 CPU clk to support freq change. Add NIC CLK to reflect the clk status Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230403095300.3386988-8-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx93.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/clk-imx93.c b/drivers/clk/imx/clk-imx93.c index de1ed1d8ba54..07b4a043e449 100644 --- a/drivers/clk/imx/clk-imx93.c +++ b/drivers/clk/imx/clk-imx93.c @@ -33,6 +33,7 @@ static u32 share_count_sai2; static u32 share_count_sai3; static u32 share_count_mub; +static const char * const a55_core_sels[] = {"a55_alt", "arm_pll"}; static const char *parent_names[MAX_SEL][4] = { {"osc_24m", "sys_pll_pfd0_div2", "sys_pll_pfd1_div2", "video_pll"}, {"osc_24m", "sys_pll_pfd0_div2", "sys_pll_pfd1_div2", "sys_pll_pfd2_div2"}, @@ -55,7 +56,7 @@ static const struct imx93_clk_root { /* a55/m33/bus critical clk for system run */ { IMX93_CLK_A55_PERIPH, "a55_periph_root", 0x0000, FAST_SEL, CLK_IS_CRITICAL }, { IMX93_CLK_A55_MTR_BUS, "a55_mtr_bus_root", 0x0080, LOW_SPEED_IO_SEL, CLK_IS_CRITICAL }, - { IMX93_CLK_A55, "a55_root", 0x0100, FAST_SEL, CLK_IS_CRITICAL }, + { IMX93_CLK_A55, "a55_alt_root", 0x0100, FAST_SEL, CLK_IS_CRITICAL }, { IMX93_CLK_M33, "m33_root", 0x0180, LOW_SPEED_IO_SEL, CLK_IS_CRITICAL }, { IMX93_CLK_BUS_WAKEUP, "bus_wakeup_root", 0x0280, LOW_SPEED_IO_SEL, CLK_IS_CRITICAL }, { IMX93_CLK_BUS_AON, "bus_aon_root", 0x0300, LOW_SPEED_IO_SEL, CLK_IS_CRITICAL }, @@ -117,6 +118,7 @@ static const struct imx93_clk_root { { IMX93_CLK_HSIO_USB_TEST_60M, "hsio_usb_test_60m_root", 0x1f00, LOW_SPEED_IO_SEL, }, { IMX93_CLK_HSIO_ACSCAN_80M, "hsio_acscan_80m_root", 0x1f80, LOW_SPEED_IO_SEL, }, { IMX93_CLK_HSIO_ACSCAN_480M, "hsio_acscan_480m_root", 0x2000, MISC_SEL, }, + { IMX93_CLK_NIC_AXI, "nic_axi_root", 0x2080, FAST_SEL, CLK_IS_CRITICAL, }, { IMX93_CLK_ML_APB, "ml_apb_root", 0x2180, LOW_SPEED_IO_SEL, }, { IMX93_CLK_ML, "ml_root", 0x2200, FAST_SEL, }, { IMX93_CLK_MEDIA_AXI, "media_axi_root", 0x2280, FAST_SEL, }, @@ -153,7 +155,7 @@ static const struct imx93_clk_ccgr { unsigned long flags; u32 *shared_count; } ccgr_array[] = { - { IMX93_CLK_A55_GATE, "a55", "a55_root", 0x8000, }, + { IMX93_CLK_A55_GATE, "a55_alt", "a55_alt_root", 0x8000, }, /* M33 critical clk for system run */ { IMX93_CLK_CM33_GATE, "cm33", "m33_root", 0x8040, CLK_IS_CRITICAL }, { IMX93_CLK_ADC1_GATE, "adc1", "adc_root", 0x82c0, }, @@ -291,6 +293,9 @@ static int imx93_clocks_probe(struct platform_device *pdev) if (WARN_ON(!anatop_base)) return -ENOMEM; + clks[IMX93_CLK_ARM_PLL] = imx_clk_fracn_gppll_integer("arm_pll", "osc_24m", + anatop_base + 0x1000, + &imx_fracn_gppll_integer); clks[IMX93_CLK_AUDIO_PLL] = imx_clk_fracn_gppll("audio_pll", "osc_24m", anatop_base + 0x1200, &imx_fracn_gppll); clks[IMX93_CLK_VIDEO_PLL] = imx_clk_fracn_gppll("video_pll", "osc_24m", anatop_base + 0x1400, @@ -318,6 +323,14 @@ static int imx93_clocks_probe(struct platform_device *pdev) ccgr->shared_count); } + clks[IMX93_CLK_A55_SEL] = imx_clk_hw_mux2("a55_sel", base + 0x4820, 0, 1, a55_core_sels, + ARRAY_SIZE(a55_core_sels)); + clks[IMX93_CLK_A55_CORE] = imx_clk_hw_cpu("a55_core", "a55_sel", + clks[IMX93_CLK_A55_SEL]->clk, + clks[IMX93_CLK_A55_SEL]->clk, + clks[IMX93_CLK_ARM_PLL]->clk, + clks[IMX93_CLK_A55_GATE]->clk); + imx_check_clk_hws(clks, IMX93_CLK_END); ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data); -- GitLab From d608c18018c897b88d66f1340fe274b7181817fa Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 31 Mar 2023 14:38:10 +0800 Subject: [PATCH 2418/5631] clk: imx: imx8ulp: Fix XBAR_DIVBUS and AD_SLOW clock parents XBAR_DIVBUS and AD_SLOW should set parent to XBAR_AD_DIVPLAT and XBAR_DIVBUS respectively, not the NIC_AD. otherwise we will get wrong clock rate. Fixes: c43a801a5789 ("clk: imx: Add clock driver for imx8ulp") Reviewed-by: Jacky Bai Signed-off-by: Ye Li Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230331063814.2462059-2-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8ulp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index a07df3b44703..89121037a8f0 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -200,8 +200,8 @@ static int imx8ulp_clk_cgc1_init(struct platform_device *pdev) clks[IMX8ULP_CLK_NIC_AD_DIVPLAT] = imx_clk_hw_divider_flags("nic_ad_divplat", "nic_sel", base + 0x34, 21, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); clks[IMX8ULP_CLK_NIC_PER_DIVPLAT] = imx_clk_hw_divider_flags("nic_per_divplat", "nic_ad_divplat", base + 0x34, 14, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); clks[IMX8ULP_CLK_XBAR_AD_DIVPLAT] = imx_clk_hw_divider_flags("xbar_ad_divplat", "nic_ad_divplat", base + 0x38, 14, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_XBAR_DIVBUS] = imx_clk_hw_divider_flags("xbar_divbus", "nic_ad_divplat", base + 0x38, 7, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_XBAR_AD_SLOW] = imx_clk_hw_divider_flags("xbar_ad_slow", "nic_ad_divplat", base + 0x38, 0, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); + clks[IMX8ULP_CLK_XBAR_DIVBUS] = imx_clk_hw_divider_flags("xbar_divbus", "xbar_ad_divplat", base + 0x38, 7, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); + clks[IMX8ULP_CLK_XBAR_AD_SLOW] = imx_clk_hw_divider_flags("xbar_ad_slow", "xbar_divbus", base + 0x38, 0, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); clks[IMX8ULP_CLK_SOSC_DIV1_GATE] = imx_clk_hw_gate_dis("sosc_div1_gate", "sosc", base + 0x108, 7); clks[IMX8ULP_CLK_SOSC_DIV2_GATE] = imx_clk_hw_gate_dis("sosc_div2_gate", "sosc", base + 0x108, 15); -- GitLab From 335aee51ffc72149ddf99755ba629f981f20e6b6 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Fri, 31 Mar 2023 14:38:11 +0800 Subject: [PATCH 2419/5631] clk: imx: imx8ulp: Add divider closest support to get more accurate clock rate If a divider's parent clock has fractional part, it will hard to round out a more accurate clock rate for this divider, add the 'CLK_DIVIDER_ROUND_CLOSEST' flags for such divider to get a more accurate clock rate. Reviewed-by: Peng Fan Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230331063814.2462059-3-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8ulp.c | 16 ++++++++-------- drivers/clk/imx/clk.h | 9 +++++++++ 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index 89121037a8f0..3cf4b094dfff 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -275,14 +275,14 @@ static int imx8ulp_clk_cgc2_init(struct platform_device *pdev) clks[IMX8ULP_CLK_PLL4_PFD2_DIV2_GATE] = imx_clk_hw_gate_dis("pll4_pfd2_div2_gate", "pll4_pfd2", base + 0x60c, 15); clks[IMX8ULP_CLK_PLL4_PFD3_DIV1_GATE] = imx_clk_hw_gate_dis("pll4_pfd3_div1_gate", "pll4_pfd3", base + 0x60c, 23); clks[IMX8ULP_CLK_PLL4_PFD3_DIV2_GATE] = imx_clk_hw_gate_dis("pll4_pfd3_div2_gate", "pll4_pfd3", base + 0x60c, 31); - clks[IMX8ULP_CLK_PLL4_PFD0_DIV1] = imx_clk_hw_divider("pll4_pfd0_div1", "pll4_pfd0_div1_gate", base + 0x608, 0, 6); - clks[IMX8ULP_CLK_PLL4_PFD0_DIV2] = imx_clk_hw_divider("pll4_pfd0_div2", "pll4_pfd0_div2_gate", base + 0x608, 8, 6); - clks[IMX8ULP_CLK_PLL4_PFD1_DIV1] = imx_clk_hw_divider("pll4_pfd1_div1", "pll4_pfd1_div1_gate", base + 0x608, 16, 6); - clks[IMX8ULP_CLK_PLL4_PFD1_DIV2] = imx_clk_hw_divider("pll4_pfd1_div2", "pll4_pfd1_div2_gate", base + 0x608, 24, 6); - clks[IMX8ULP_CLK_PLL4_PFD2_DIV1] = imx_clk_hw_divider("pll4_pfd2_div1", "pll4_pfd2_div1_gate", base + 0x60c, 0, 6); - clks[IMX8ULP_CLK_PLL4_PFD2_DIV2] = imx_clk_hw_divider("pll4_pfd2_div2", "pll4_pfd2_div2_gate", base + 0x60c, 8, 6); - clks[IMX8ULP_CLK_PLL4_PFD3_DIV1] = imx_clk_hw_divider("pll4_pfd3_div1", "pll4_pfd3_div1_gate", base + 0x60c, 16, 6); - clks[IMX8ULP_CLK_PLL4_PFD3_DIV2] = imx_clk_hw_divider("pll4_pfd3_div2", "pll4_pfd3_div2_gate", base + 0x60c, 24, 6); + clks[IMX8ULP_CLK_PLL4_PFD0_DIV1] = imx_clk_hw_divider_closest("pll4_pfd0_div1", "pll4_pfd0_div1_gate", base + 0x608, 0, 6); + clks[IMX8ULP_CLK_PLL4_PFD0_DIV2] = imx_clk_hw_divider_closest("pll4_pfd0_div2", "pll4_pfd0_div2_gate", base + 0x608, 8, 6); + clks[IMX8ULP_CLK_PLL4_PFD1_DIV1] = imx_clk_hw_divider_closest("pll4_pfd1_div1", "pll4_pfd1_div1_gate", base + 0x608, 16, 6); + clks[IMX8ULP_CLK_PLL4_PFD1_DIV2] = imx_clk_hw_divider_closest("pll4_pfd1_div2", "pll4_pfd1_div2_gate", base + 0x608, 24, 6); + clks[IMX8ULP_CLK_PLL4_PFD2_DIV1] = imx_clk_hw_divider_closest("pll4_pfd2_div1", "pll4_pfd2_div1_gate", base + 0x60c, 0, 6); + clks[IMX8ULP_CLK_PLL4_PFD2_DIV2] = imx_clk_hw_divider_closest("pll4_pfd2_div2", "pll4_pfd2_div2_gate", base + 0x60c, 8, 6); + clks[IMX8ULP_CLK_PLL4_PFD3_DIV1] = imx_clk_hw_divider_closest("pll4_pfd3_div1", "pll4_pfd3_div1_gate", base + 0x60c, 16, 6); + clks[IMX8ULP_CLK_PLL4_PFD3_DIV2] = imx_clk_hw_divider_closest("pll4_pfd3_div2", "pll4_pfd3_div2_gate", base + 0x60c, 24, 6); clks[IMX8ULP_CLK_CGC2_SOSC_DIV1_GATE] = imx_clk_hw_gate_dis("cgc2_sosc_div1_gate", "sosc", base + 0x108, 7); clks[IMX8ULP_CLK_CGC2_SOSC_DIV2_GATE] = imx_clk_hw_gate_dis("cgc2_sosc_div2_gate", "sosc", base + 0x108, 15); diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index c8db0c8d4c5d..1031468701d7 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -353,6 +353,15 @@ static inline struct clk_hw *imx_clk_hw_fixed_factor(const char *name, CLK_SET_RATE_PARENT, mult, div); } +static inline struct clk_hw *imx_clk_hw_divider_closest(const char *name, + const char *parent, + void __iomem *reg, u8 shift, + u8 width) +{ + return clk_hw_register_divider(NULL, name, parent, 0, + reg, shift, width, CLK_DIVIDER_ROUND_CLOSEST, &imx_ccm_lock); +} + static inline struct clk_hw *__imx_clk_hw_divider(const char *name, const char *parent, void __iomem *reg, u8 shift, -- GitLab From 4883200d8c0b20cc3bf90fcd3b837a344a31ac66 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Fri, 31 Mar 2023 14:38:12 +0800 Subject: [PATCH 2420/5631] clk: imx: imx8ulp: keep MU0_B clock enabled always Keep the A35<->M33 MU0_B clock enabled always for low power communication. Reviewed-by: Peng Fan Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230331063814.2462059-4-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8ulp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index 3cf4b094dfff..0dd48e8159ee 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -376,7 +376,7 @@ static int imx8ulp_clk_pcc3_init(struct platform_device *pdev) clks[IMX8ULP_CLK_DMA1_CH29] = imx_clk_hw_gate("pcc_dma1_ch29", "xbar_ad_divplat", base + 0x7c, 30); clks[IMX8ULP_CLK_DMA1_CH30] = imx_clk_hw_gate("pcc_dma1_ch30", "xbar_ad_divplat", base + 0x80, 30); clks[IMX8ULP_CLK_DMA1_CH31] = imx_clk_hw_gate("pcc_dma1_ch31", "xbar_ad_divplat", base + 0x84, 30); - clks[IMX8ULP_CLK_MU0_B] = imx_clk_hw_gate("mu0_b", "xbar_ad_divplat", base + 0x88, 30); + clks[IMX8ULP_CLK_MU0_B] = imx_clk_hw_gate_flags("mu0_b", "xbar_ad_divplat", base + 0x88, 30, CLK_IS_CRITICAL); clks[IMX8ULP_CLK_MU3_A] = imx_clk_hw_gate("mu3_a", "xbar_ad_divplat", base + 0x8c, 30); imx_check_clk_hws(clks, clk_data->num); -- GitLab From 66d72c62d20eb571b7ab624813b1b98b626ab493 Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Fri, 31 Mar 2023 14:38:13 +0800 Subject: [PATCH 2421/5631] clk: imx: imx8ulp: Add tpm5 clock as critical gate clock The TPM5 is used for broadcast timer purpose and registered with TIMER_OF_DECLARE. As the clock driver is not ready at that stage, so the TPM5 clock is configured in bootloader(TF-A). if we just remove the TPM5 clock from linux will introduce a risk that the TPM5's parent clock will be gated, then lead to TPM's channel control config can NOT be written into register successfully. Due to the above reason, we still need to add the TPM5 clock into linux clock but register it as a simple critical gate clock to make sure its parent is always on. Reviewed-by: Peng Fan Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230331063814.2462059-5-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8ulp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index 0dd48e8159ee..6a8a9e50d826 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -333,7 +333,6 @@ static int imx8ulp_clk_pcc3_init(struct platform_device *pdev) clks[IMX8ULP_CLK_WDOG4] = imx8ulp_clk_hw_composite("wdog4", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xac, 1); clks[IMX8ULP_CLK_LPIT1] = imx8ulp_clk_hw_composite("lpit1", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xc8, 1); clks[IMX8ULP_CLK_TPM4] = imx8ulp_clk_hw_composite("tpm4", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xcc, 1); - clks[IMX8ULP_CLK_TPM5] = imx8ulp_clk_hw_composite("tpm5", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xd0, 1); clks[IMX8ULP_CLK_FLEXIO1] = imx8ulp_clk_hw_composite("flexio1", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xd4, 1); clks[IMX8ULP_CLK_I3C2] = imx8ulp_clk_hw_composite("i3c2", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xd8, 1); clks[IMX8ULP_CLK_LPI2C4] = imx8ulp_clk_hw_composite("lpi2c4", pcc3_periph_bus_sels, ARRAY_SIZE(pcc3_periph_bus_sels), true, true, true, base + 0xdc, 1); @@ -378,6 +377,7 @@ static int imx8ulp_clk_pcc3_init(struct platform_device *pdev) clks[IMX8ULP_CLK_DMA1_CH31] = imx_clk_hw_gate("pcc_dma1_ch31", "xbar_ad_divplat", base + 0x84, 30); clks[IMX8ULP_CLK_MU0_B] = imx_clk_hw_gate_flags("mu0_b", "xbar_ad_divplat", base + 0x88, 30, CLK_IS_CRITICAL); clks[IMX8ULP_CLK_MU3_A] = imx_clk_hw_gate("mu3_a", "xbar_ad_divplat", base + 0x8c, 30); + clks[IMX8ULP_CLK_TPM5] = imx_clk_hw_gate_flags("tpm5", "sosc_div2", base + 0xd0, 30, CLK_IS_CRITICAL); imx_check_clk_hws(clks, clk_data->num); -- GitLab From 8a05f5cccdbe851265bf513643ada48c26b1267f Mon Sep 17 00:00:00 2001 From: Jacky Bai Date: Fri, 31 Mar 2023 14:38:14 +0800 Subject: [PATCH 2422/5631] clk: imx: imx8ulp: update clk flag for system critical clock In order to support bus fabric clock frequency changed on the fly, need to update some bus clocks'flags to make sure these clocks'frequency and parent can be changed on the fly. For these clocks, HW can make sure no glitch will be introduced when changing on the fly. In order to support DDR DFS, the HW register bit for DDR_SEL and DDR_DIV clock will be modified by TF-A. So need to update these two clock's flag to make sure that the linux kernel side can correct these clocks' SW state to reflect the actual HW state. Reviewed-by: Ye Li Signed-off-by: Jacky Bai Signed-off-by: Peng Fan Reviewed-by: Abel Vesa Link: https://lore.kernel.org/r/20230331063814.2462059-6-peng.fan@oss.nxp.com Signed-off-by: Abel Vesa --- drivers/clk/imx/clk-imx8ulp.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/clk/imx/clk-imx8ulp.c b/drivers/clk/imx/clk-imx8ulp.c index 6a8a9e50d826..e308c88cb801 100644 --- a/drivers/clk/imx/clk-imx8ulp.c +++ b/drivers/clk/imx/clk-imx8ulp.c @@ -198,10 +198,10 @@ static int imx8ulp_clk_cgc1_init(struct platform_device *pdev) clks[IMX8ULP_CLK_NIC_SEL] = imx_clk_hw_mux2("nic_sel", base + 0x34, 28, 2, nic_sels, ARRAY_SIZE(nic_sels)); clks[IMX8ULP_CLK_NIC_AD_DIVPLAT] = imx_clk_hw_divider_flags("nic_ad_divplat", "nic_sel", base + 0x34, 21, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_NIC_PER_DIVPLAT] = imx_clk_hw_divider_flags("nic_per_divplat", "nic_ad_divplat", base + 0x34, 14, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_XBAR_AD_DIVPLAT] = imx_clk_hw_divider_flags("xbar_ad_divplat", "nic_ad_divplat", base + 0x38, 14, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_XBAR_DIVBUS] = imx_clk_hw_divider_flags("xbar_divbus", "xbar_ad_divplat", base + 0x38, 7, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_XBAR_AD_SLOW] = imx_clk_hw_divider_flags("xbar_ad_slow", "xbar_divbus", base + 0x38, 0, 6, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL); + clks[IMX8ULP_CLK_NIC_PER_DIVPLAT] = imx_clk_hw_divider_flags("nic_per_divplat", "nic_ad_divplat", base + 0x34, 14, 6, CLK_SET_RATE_PARENT); + clks[IMX8ULP_CLK_XBAR_AD_DIVPLAT] = imx_clk_hw_divider_flags("xbar_ad_divplat", "nic_ad_divplat", base + 0x38, 14, 6, CLK_SET_RATE_PARENT); + clks[IMX8ULP_CLK_XBAR_DIVBUS] = imx_clk_hw_divider_flags("xbar_divbus", "xbar_ad_divplat", base + 0x38, 7, 6, CLK_SET_RATE_PARENT); + clks[IMX8ULP_CLK_XBAR_AD_SLOW] = imx_clk_hw_divider_flags("xbar_ad_slow", "xbar_divbus", base + 0x38, 0, 6, CLK_SET_RATE_PARENT); clks[IMX8ULP_CLK_SOSC_DIV1_GATE] = imx_clk_hw_gate_dis("sosc_div1_gate", "sosc", base + 0x108, 7); clks[IMX8ULP_CLK_SOSC_DIV2_GATE] = imx_clk_hw_gate_dis("sosc_div2_gate", "sosc", base + 0x108, 15); @@ -255,9 +255,9 @@ static int imx8ulp_clk_cgc2_init(struct platform_device *pdev) clks[IMX8ULP_CLK_HIFI_DIVCORE] = imx_clk_hw_divider("hifi_core_div", "hifi_sel", base + 0x14, 21, 6); clks[IMX8ULP_CLK_HIFI_DIVPLAT] = imx_clk_hw_divider("hifi_plat_div", "hifi_core_div", base + 0x14, 14, 6); - clks[IMX8ULP_CLK_DDR_SEL] = imx_clk_hw_mux_flags("ddr_sel", base + 0x40, 28, 3, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_SET_PARENT_GATE); - clks[IMX8ULP_CLK_DDR_DIV] = imx_clk_hw_divider_flags("ddr_div", "ddr_sel", base + 0x40, 21, 6, CLK_IS_CRITICAL); - clks[IMX8ULP_CLK_LPAV_AXI_SEL] = imx_clk_hw_mux("lpav_sel", base + 0x3c, 28, 2, lpav_sels, ARRAY_SIZE(lpav_sels)); + clks[IMX8ULP_CLK_DDR_SEL] = imx_clk_hw_mux_flags("ddr_sel", base + 0x40, 28, 3, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_GET_RATE_NOCACHE); + clks[IMX8ULP_CLK_DDR_DIV] = imx_clk_hw_divider_flags("ddr_div", "ddr_sel", base + 0x40, 21, 6, CLK_IS_CRITICAL | CLK_GET_RATE_NOCACHE); + clks[IMX8ULP_CLK_LPAV_AXI_SEL] = imx_clk_hw_mux2("lpav_sel", base + 0x3c, 28, 2, lpav_sels, ARRAY_SIZE(lpav_sels)); clks[IMX8ULP_CLK_LPAV_AXI_DIV] = imx_clk_hw_divider_flags("lpav_axi_div", "lpav_sel", base + 0x3c, 21, 6, CLK_IS_CRITICAL); clks[IMX8ULP_CLK_LPAV_AHB_DIV] = imx_clk_hw_divider_flags("lpav_ahb_div", "lpav_axi_div", base + 0x3c, 14, 6, CLK_IS_CRITICAL); clks[IMX8ULP_CLK_LPAV_BUS_DIV] = imx_clk_hw_divider_flags("lpav_bus_div", "lpav_axi_div", base + 0x3c, 7, 6, CLK_IS_CRITICAL); -- GitLab From 4eb3117888a923f6b9b1ad2dd093641c49a63ae5 Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Mon, 27 Mar 2023 01:53:10 +0000 Subject: [PATCH 2423/5631] fs/9p: Rework cache modes and add new options to Documentation Switch cache modes to a bit-mask and use legacy cache names as shortcuts. Update documentation to include information on both shortcuts and bitmasks. This patch also fixes missing guards related to fscache. Update the documentation for new mount flags and cache modes. Signed-off-by: Eric Van Hensbergen --- Documentation/filesystems/9p.rst | 50 +++++++++++++++++------- fs/9p/cache.h | 3 +- fs/9p/fid.h | 4 +- fs/9p/v9fs.c | 34 ++++++---------- fs/9p/v9fs.h | 67 ++++++++++++++++++++------------ fs/9p/vfs_addr.c | 28 +++++++------ fs/9p/vfs_file.c | 10 ++--- fs/9p/vfs_inode.c | 34 ++++++++++------ fs/9p/vfs_inode_dotl.c | 26 +++++++------ fs/9p/vfs_super.c | 4 +- 10 files changed, 153 insertions(+), 107 deletions(-) diff --git a/Documentation/filesystems/9p.rst b/Documentation/filesystems/9p.rst index 0e800b8f73cc..1b5f0cc3e4ca 100644 --- a/Documentation/filesystems/9p.rst +++ b/Documentation/filesystems/9p.rst @@ -78,19 +78,39 @@ Options offering several exported file systems. cache=mode specifies a caching policy. By default, no caches are used. - - none - default no cache policy, metadata and data - alike are synchronous. - loose - no attempts are made at consistency, - intended for exclusive, read-only mounts - fscache - use FS-Cache for a persistent, read-only - cache backend. - mmap - minimal cache that is only used for read-write - mmap. Northing else is cached, like cache=none + The mode can be specified as a bitmask or by using one of the + prexisting common 'shortcuts'. + The bitmask is described below: (unspecified bits are reserved) + + ========== ==================================================== + 0b00000000 all caches disabled, mmap disabled + 0b00000001 file caches enabled + 0b00000010 meta-data caches enabled + 0b00000100 writeback behavior (as opposed to writethrough) + 0b00001000 loose caches (no explicit consistency with server) + 0b10000000 fscache enabled for persistent caching + ========== ==================================================== + + The current shortcuts and their associated bitmask are: + + ========= ==================================================== + none 0b00000000 (no caching) + readahead 0b00000001 (only read-ahead file caching) + mmap 0b00000101 (read-ahead + writeback file cache) + loose 0b00001111 (non-coherent file and meta-data caches) + fscache 0b10001111 (persistent loose cache) + ========= ==================================================== + + NOTE: only these shortcuts are tested modes of operation at the + moment, so using other combinations of bit-patterns is not + known to work. Work on better cache support is in progress. + + IMPORTANT: loose caches (and by extension at the moment fscache) + do not necessarily validate cached values on the server. In other + words changes on the server are not guaranteed to be reflected + on the client system. Only use this mode of operation if you + have an exclusive mount and the server will modify the filesystem + underneath you. debug=n specifies debug level. The debug level is a bitmask. @@ -137,6 +157,10 @@ Options This can be used to share devices/named pipes/sockets between hosts. This functionality will be expanded in later versions. + directio bypass page cache on all read/write operations + + ignoreqv ignore qid.version==0 as a marker to ignore cache + noxattr do not offer xattr functions on this mount. access there are four access modes. diff --git a/fs/9p/cache.h b/fs/9p/cache.h index 1923affcdc62..ee1b6b06a2fd 100644 --- a/fs/9p/cache.h +++ b/fs/9p/cache.h @@ -8,9 +8,8 @@ #ifndef _9P_CACHE_H #define _9P_CACHE_H -#include - #ifdef CONFIG_9P_FSCACHE +#include extern int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, const char *dev_name); diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 11576e1364bf..0c51889a60b3 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -56,11 +56,9 @@ static inline void v9fs_fid_add_modes(struct p9_fid *fid, int s_flags, ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { fid->mode |= P9L_DIRECT; /* no read or write cache */ - } else if ((s_cache < CACHE_WRITEBACK) || + } else if ((!(s_cache & CACHE_WRITEBACK)) || (f_flags & O_DSYNC) | (s_flags & V9FS_SYNC)) { fid->mode |= P9L_NOWRITECACHE; - } else if (s_cache == CACHE_LOOSE) { - fid->mode |= P9L_LOOSE; /* noncoherent cache */ } } #endif diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 43d3806150a9..c7f774fe398f 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -66,40 +66,30 @@ static const match_table_t tokens = { {Opt_err, NULL} }; -static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { - [CACHE_NONE] = "none", - [CACHE_READAHEAD] = "readahead", - [CACHE_WRITEBACK] = "writeback", - [CACHE_MMAP] = "mmap", - [CACHE_LOOSE] = "loose", - [CACHE_FSCACHE] = "fscache", -}; - /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { int version = -EINVAL; if (!strcmp(s, "loose")) { - version = CACHE_LOOSE; + version = CACHE_SC_LOOSE; p9_debug(P9_DEBUG_9P, "Cache mode: loose\n"); } else if (!strcmp(s, "fscache")) { - version = CACHE_FSCACHE; + version = CACHE_SC_FSCACHE; p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n"); } else if (!strcmp(s, "mmap")) { - version = CACHE_MMAP; + version = CACHE_SC_MMAP; p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n"); - } else if (!strcmp(s, "writeback")) { - version = CACHE_WRITEBACK; - p9_debug(P9_DEBUG_9P, "Cache mode: writeback\n"); } else if (!strcmp(s, "readahead")) { - version = CACHE_READAHEAD; + version = CACHE_SC_READAHEAD; p9_debug(P9_DEBUG_9P, "Cache mode: readahead\n"); } else if (!strcmp(s, "none")) { - version = CACHE_NONE; + version = CACHE_SC_NONE; p9_debug(P9_DEBUG_9P, "Cache mode: none\n"); - } else - pr_info("Unknown Cache mode %s\n", s); + } else if (kstrtoint(s, 0, &version) != 0) { + version = -EINVAL; + pr_info("Unknown Cache mode or invalid value %s\n", s); + } return version; } @@ -127,9 +117,9 @@ int v9fs_show_options(struct seq_file *m, struct dentry *root) if (v9ses->nodev) seq_puts(m, ",nodevmap"); if (v9ses->cache) - seq_printf(m, ",cache=%s", v9fs_cache_modes[v9ses->cache]); + seq_printf(m, ",cache=%x", v9ses->cache); #ifdef CONFIG_9P_FSCACHE - if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) + if (v9ses->cachetag && (v9ses->cache & CACHE_FSCACHE)) seq_printf(m, ",cachetag=%s", v9ses->cachetag); #endif @@ -481,7 +471,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, #ifdef CONFIG_9P_FSCACHE /* register the session for caching */ - if (v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & CACHE_FSCACHE) { rc = v9fs_cache_session_get_cookie(v9ses, dev_name); if (rc < 0) goto err_clnt; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 999cdbcbfed9..06a2514f0d88 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -31,35 +31,54 @@ #define V9FS_ACL_MASK V9FS_POSIX_ACL enum p9_session_flags { - V9FS_PROTO_2000U = 0x01, - V9FS_PROTO_2000L = 0x02, - V9FS_ACCESS_SINGLE = 0x04, - V9FS_ACCESS_USER = 0x08, - V9FS_ACCESS_CLIENT = 0x10, - V9FS_POSIX_ACL = 0x20, - V9FS_NO_XATTR = 0x40, - V9FS_IGNORE_QV = 0x80, /* ignore qid.version for cache hints */ - V9FS_DIRECT_IO = 0x100, - V9FS_SYNC = 0x200 + V9FS_PROTO_2000U = 0x01, + V9FS_PROTO_2000L = 0x02, + V9FS_ACCESS_SINGLE = 0x04, + V9FS_ACCESS_USER = 0x08, + V9FS_ACCESS_CLIENT = 0x10, + V9FS_POSIX_ACL = 0x20, + V9FS_NO_XATTR = 0x40, + V9FS_IGNORE_QV = 0x80, /* ignore qid.version for cache hints */ + V9FS_DIRECT_IO = 0x100, + V9FS_SYNC = 0x200 }; -/* possible values of ->cache */ /** - * enum p9_cache_modes - user specified cache preferences - * @CACHE_NONE: do not cache data, dentries, or directory contents (default) - * @CACHE_LOOSE: cache data, dentries, and directory contents w/no consistency + * enum p9_cache_shortcuts - human readable cache preferences + * @CACHE_SC_NONE: disable all caches + * @CACHE_SC_READAHEAD: only provide caching for readahead + * @CACHE_SC_MMAP: provide caching to enable mmap + * @CACHE_SC_LOOSE: non-coherent caching for files and meta data + * @CACHE_SC_FSCACHE: persistent non-coherent caching for files and meta-data * - * eventually support loose, tight, time, session, default always none */ -enum p9_cache_modes { - CACHE_NONE, - CACHE_READAHEAD, - CACHE_WRITEBACK, - CACHE_MMAP, - CACHE_LOOSE, - CACHE_FSCACHE, - nr__p9_cache_modes +enum p9_cache_shortcuts { + CACHE_SC_NONE = 0b00000000, + CACHE_SC_READAHEAD = 0b00000001, + CACHE_SC_MMAP = 0b00000101, + CACHE_SC_LOOSE = 0b00001111, + CACHE_SC_FSCACHE = 0b10001111, +}; + +/** + * enum p9_cache_bits - possible values of ->cache + * @CACHE_NONE: caches disabled + * @CACHE_FILE: file caching (open to close) + * @CACHE_META: meta-data and directory caching + * @CACHE_WRITEBACK: write-back caching for files + * @CACHE_LOOSE: don't check cache consistency + * @CACHE_FSCACHE: local persistent caches + * + */ + +enum p9_cache_bits { + CACHE_NONE = 0b00000000, + CACHE_FILE = 0b00000001, + CACHE_META = 0b00000010, + CACHE_WRITEBACK = 0b00000100, + CACHE_LOOSE = 0b00001000, + CACHE_FSCACHE = 0b10000000, }; /** @@ -68,7 +87,7 @@ enum p9_cache_modes { * @nodev: set to 1 to disable device mapping * @debug: debug level * @afid: authentication handle - * @cache: cache mode of type &p9_cache_modes + * @cache: cache mode of type &p9_cache_bits * @cachetag: the tag of the cache associated with this session * @fscache: session cookie associated with FS-Cache * @uname: string user name to mount hierarchy as diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 211165430a8a..9239a049f736 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -115,8 +115,6 @@ const struct netfs_request_ops v9fs_req_ops = { static bool v9fs_release_folio(struct folio *folio, gfp_t gfp) { - struct inode *inode = folio_inode(folio); - if (folio_test_private(folio)) return false; #ifdef CONFIG_9P_FSCACHE @@ -125,8 +123,8 @@ static bool v9fs_release_folio(struct folio *folio, gfp_t gfp) return false; folio_wait_fscache(folio); } + fscache_note_page_release(v9fs_inode_cookie(V9FS_I(folio_inode(folio)))); #endif - fscache_note_page_release(v9fs_inode_cookie(V9FS_I(inode))); return true; } @@ -136,6 +134,7 @@ static void v9fs_invalidate_folio(struct folio *folio, size_t offset, folio_wait_fscache(folio); } +#ifdef CONFIG_9P_FSCACHE static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error, bool was_async) { @@ -149,18 +148,19 @@ static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error, i_size_read(&v9inode->netfs.inode), 0); } } +#endif static int v9fs_vfs_write_folio_locked(struct folio *folio) { struct inode *inode = folio_inode(folio); - struct v9fs_inode *v9inode = V9FS_I(inode); - struct fscache_cookie *cookie = v9fs_inode_cookie(v9inode); loff_t start = folio_pos(folio); loff_t i_size = i_size_read(inode); struct iov_iter from; size_t len = folio_size(folio); struct p9_fid *writeback_fid; int err; + struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); + struct fscache_cookie __maybe_unused *cookie = v9fs_inode_cookie(v9inode); if (start >= i_size) return 0; /* Simultaneous truncation occurred */ @@ -181,15 +181,17 @@ static int v9fs_vfs_write_folio_locked(struct folio *folio) p9_client_write(writeback_fid, start, &from, &err); +#ifdef CONFIG_9P_FSCACHE if (err == 0 && - fscache_cookie_enabled(cookie) && - test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) { + fscache_cookie_enabled(cookie) && + test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) { folio_start_fscache(folio); fscache_write_to_cache(v9fs_inode_cookie(v9inode), - folio_mapping(folio), start, len, i_size, - v9fs_write_to_cache_done, v9inode, - true); + folio_mapping(folio), start, len, i_size, + v9fs_write_to_cache_done, v9inode, + true); } +#endif folio_end_writeback(folio); p9_fid_put(writeback_fid); @@ -300,7 +302,6 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, loff_t last_pos = pos + copied; struct folio *folio = page_folio(subpage); struct inode *inode = mapping->host; - struct v9fs_inode *v9inode = V9FS_I(inode); p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); @@ -320,7 +321,10 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, if (last_pos > inode->i_size) { inode_add_bytes(inode, last_pos - inode->i_size); i_size_write(inode, last_pos); - fscache_update_cookie(v9fs_inode_cookie(v9inode), NULL, &last_pos); +#ifdef CONFIG_9P_FSCACHE + fscache_update_cookie(v9fs_inode_cookie(V9FS_I(inode)), NULL, + &last_pos); +#endif } folio_mark_dirty(folio); out: diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 9f1d464bc1b5..07a67ac37ce2 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -41,13 +41,11 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops; int v9fs_file_open(struct inode *inode, struct file *file) { int err; - struct v9fs_inode *v9inode; struct v9fs_session_info *v9ses; struct p9_fid *fid; int omode; p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file); - v9inode = V9FS_I(inode); v9ses = v9fs_inode2v9ses(inode); if (v9fs_proto_dotl(v9ses)) omode = v9fs_open_to_dotl_flags(file->f_flags); @@ -60,7 +58,7 @@ int v9fs_file_open(struct inode *inode, struct file *file) if (IS_ERR(fid)) return PTR_ERR(fid); - if ((v9ses->cache >= CACHE_WRITEBACK) && (omode & P9_OWRITE)) { + if ((v9ses->cache & CACHE_WRITEBACK) && (omode & P9_OWRITE)) { int writeback_omode = (omode & ~P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, try opening O_RDWR\n"); @@ -85,8 +83,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) } #ifdef CONFIG_9P_FSCACHE - if (v9ses->cache == CACHE_FSCACHE) - fscache_use_cookie(v9fs_inode_cookie(v9inode), + if (v9ses->cache & CACHE_FSCACHE) + fscache_use_cookie(v9fs_inode_cookie(V9FS_I(inode)), file->f_mode & FMODE_WRITE); #endif v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags); @@ -485,7 +483,7 @@ v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) p9_debug(P9_DEBUG_MMAP, "filp :%p\n", filp); - if (v9ses->cache < CACHE_MMAP) { + if (!(v9ses->cache & CACHE_WRITEBACK)) { p9_debug(P9_DEBUG_CACHE, "(no mmap mode)"); if (vma->vm_flags & VM_MAYSHARE) return -ENODEV; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index fb5e5c0e41e4..54dfe4f10f43 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -371,17 +371,23 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) */ void v9fs_evict_inode(struct inode *inode) { - struct v9fs_inode *v9inode = V9FS_I(inode); - __le32 version; + struct v9fs_inode __maybe_unused *v9inode = V9FS_I(inode); + __le32 __maybe_unused version; truncate_inode_pages_final(&inode->i_data); + +#ifdef CONFIG_9P_FSCACHE version = cpu_to_le32(v9inode->qid.version); fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode, &version); +#endif + clear_inode(inode); filemap_fdatawrite(&inode->i_data); +#ifdef CONFIG_9P_FSCACHE fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); +#endif } static int v9fs_test_inode(struct inode *inode, void *data) @@ -761,7 +767,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, inode = NULL; else if (IS_ERR(fid)) inode = ERR_CAST(fid); - else if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) + else if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb); else inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); @@ -790,7 +796,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, { int err; u32 perm; - struct v9fs_inode *v9inode; + struct v9fs_inode __maybe_unused *v9inode; struct v9fs_session_info *v9ses; struct p9_fid *fid; struct dentry *res = NULL; @@ -816,7 +822,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, perm = unixmode2p9mode(v9ses, mode); p9_omode = v9fs_uflags2omode(flags, v9fs_proto_dotu(v9ses)); - if ((v9ses->cache >= CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { + if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); @@ -835,9 +841,11 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, goto error; file->private_data = fid; - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cache & CACHE_FSCACHE) fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); +#endif v9fs_fid_add_modes(fid, v9ses->flags, v9ses->cache, file->f_flags); v9fs_open_fid_add(inode, &fid); @@ -1008,10 +1016,10 @@ v9fs_vfs_getattr(struct mnt_idmap *idmap, const struct path *path, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; - } else if (v9ses->cache >= CACHE_WRITEBACK) { + } else if (v9ses->cache & CACHE_WRITEBACK) { if (S_ISREG(inode->i_mode)) { int retval = filemap_fdatawrite(inode->i_mapping); @@ -1050,7 +1058,6 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, { int retval, use_dentry = 0; struct inode *inode = d_inode(dentry); - struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_wstat wstat; @@ -1115,8 +1122,13 @@ static int v9fs_vfs_setattr(struct mnt_idmap *idmap, truncate_setsize(inode, iattr->ia_size); truncate_pagecache(inode, iattr->ia_size); - if (v9ses->cache == CACHE_FSCACHE) +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cache & CACHE_FSCACHE) { + struct v9fs_inode *v9inode = V9FS_I(inode); + fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); + } +#endif } v9fs_invalidate_inode_attr(inode); @@ -1400,7 +1412,7 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) * We don't want to refresh inode->i_size, * because we may have cached data */ - flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + flags = (v9ses->cache & CACHE_LOOSE) ? V9FS_STAT2INODE_KEEP_ISIZE : 0; v9fs_stat2inode(st, inode, inode->i_sb, flags); out: diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 4b9488cb7a56..f9371b5b70ea 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -287,7 +287,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, goto out; } - if ((v9ses->cache >= CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { + if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); @@ -325,7 +325,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, goto out; file->private_data = ofid; #ifdef CONFIG_9P_FSCACHE - if (v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & CACHE_FSCACHE) { struct v9fs_inode *v9inode = V9FS_I(inode); fscache_use_cookie(v9fs_inode_cookie(v9inode), file->f_mode & FMODE_WRITE); @@ -403,7 +403,7 @@ static int v9fs_vfs_mkdir_dotl(struct mnt_idmap *idmap, } /* instantiate inode and assign the unopened fid to the dentry */ - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); @@ -451,7 +451,7 @@ v9fs_vfs_getattr_dotl(struct mnt_idmap *idmap, p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry); v9ses = v9fs_dentry2v9ses(dentry); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { generic_fillattr(&nop_mnt_idmap, inode, stat); return 0; } else if (v9ses->cache) { @@ -538,8 +538,7 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, { int retval, use_dentry = 0; struct inode *inode = d_inode(dentry); - struct v9fs_inode *v9inode = V9FS_I(inode); - struct v9fs_session_info *v9ses; + struct v9fs_session_info __maybe_unused *v9ses; struct p9_fid *fid = NULL; struct p9_iattr_dotl p9attr = { .uid = INVALID_UID, @@ -603,8 +602,11 @@ int v9fs_vfs_setattr_dotl(struct mnt_idmap *idmap, truncate_setsize(inode, iattr->ia_size); truncate_pagecache(inode, iattr->ia_size); - if (v9ses->cache == CACHE_FSCACHE) - fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cache & CACHE_FSCACHE) + fscache_resize_cookie(v9fs_inode_cookie(V9FS_I(inode)), + iattr->ia_size); +#endif } v9fs_invalidate_inode_attr(inode); @@ -732,7 +734,7 @@ v9fs_vfs_symlink_dotl(struct mnt_idmap *idmap, struct inode *dir, } v9fs_invalidate_inode_attr(dir); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { /* Now walk from the parent so we can get an unopened fid. */ fid = p9_client_walk(dfid, 1, &name, 1); if (IS_ERR(fid)) { @@ -809,7 +811,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, } v9fs_invalidate_inode_attr(dir); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { /* Get the latest stat info from server. */ struct p9_fid *fid; @@ -886,7 +888,7 @@ v9fs_vfs_mknod_dotl(struct mnt_idmap *idmap, struct inode *dir, } /* instantiate inode and assign the unopened fid to the dentry */ - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) { inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); @@ -971,7 +973,7 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) * We don't want to refresh inode->i_size, * because we may have cached data */ - flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + flags = (v9ses->cache & CACHE_LOOSE) ? V9FS_STAT2INODE_KEEP_ISIZE : 0; v9fs_stat2inode_dotl(st, inode, flags); out: diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index af83b39e340c..c6cbc666a4c1 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -136,7 +136,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, if (retval) goto release_sb; - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) sb->s_d_op = &v9fs_cached_dentry_operations; else sb->s_d_op = &v9fs_dentry_operations; @@ -277,7 +277,7 @@ static int v9fs_drop_inode(struct inode *inode) struct v9fs_session_info *v9ses; v9ses = v9fs_inode2v9ses(inode); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) + if (v9ses->cache & (CACHE_META|CACHE_LOOSE)) return generic_drop_inode(inode); /* * in case of non cached mode always drop the -- GitLab From cd7cd6f386df21725eeab5d803226d4f74177203 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Sun, 9 Apr 2023 19:10:24 -0700 Subject: [PATCH 2424/5631] Input: cma3000_d0x - remove unneeded code Function input_set_abs_params() has already set EV_ABS bit for us. drivers/input/misc/cma3000_d0x.c:328 cma3000_init() warn: inconsistent indenting. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Link: https://lore.kernel.org/r/20230407021343.63512-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Dmitry Torokhov --- drivers/input/misc/cma3000_d0x.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/input/misc/cma3000_d0x.c b/drivers/input/misc/cma3000_d0x.c index e6feb73bb52b..1772846708d2 100644 --- a/drivers/input/misc/cma3000_d0x.c +++ b/drivers/input/misc/cma3000_d0x.c @@ -325,8 +325,6 @@ struct cma3000_accl_data *cma3000_init(struct device *dev, int irq, input_dev->open = cma3000_open; input_dev->close = cma3000_close; - __set_bit(EV_ABS, input_dev->evbit); - input_set_abs_params(input_dev, ABS_X, -data->g_range, data->g_range, pdata->fuzz_x, 0); input_set_abs_params(input_dev, ABS_Y, -- GitLab From 00140a8308367208d56e93cf08fa1636202a0dc7 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 7 Feb 2023 10:52:15 -0800 Subject: [PATCH 2425/5631] rust: sync: impl {Debug,Display} for {Unique,}Arc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows printing the inner data of `Arc` and its friends if the inner data implements `Display` or `Debug`. It's useful for logging and debugging purpose. Signed-off-by: Boqun Feng Reviewed-by: Vincenzo Palazzo Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Reviewed-by: Björn Roy Baron Link: https://lore.kernel.org/r/20230207185216.1314638-2-boqun.feng@gmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/sync/arc.rs | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index f2f1c83d72ba..a94e303217c6 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -22,6 +22,7 @@ use crate::{ }; use alloc::boxed::Box; use core::{ + fmt, marker::{PhantomData, Unsize}, mem::{ManuallyDrop, MaybeUninit}, ops::{Deref, DerefMut}, @@ -522,3 +523,27 @@ impl DerefMut for UniqueArc { unsafe { &mut self.inner.ptr.as_mut().data } } } + +impl fmt::Display for UniqueArc { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(self.deref(), f) + } +} + +impl fmt::Display for Arc { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(self.deref(), f) + } +} + +impl fmt::Debug for UniqueArc { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(self.deref(), f) + } +} + +impl fmt::Debug for Arc { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(self.deref(), f) + } +} -- GitLab From f431c5c581fa176f608ba3fdebb3c1051bad5774 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 7 Feb 2023 10:52:16 -0800 Subject: [PATCH 2426/5631] samples: rust: print: Add sample code for Arc printing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This both demonstrates the usage of different print format in Rust and serves as a selftest for the `Display` and `Debug` implementation of `Arc` and its friends. Signed-off-by: Boqun Feng Reviewed-by: Björn Roy Baron Reviewed-by: Finn Behrens Reviewed-by: Vincenzo Palazzo Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230207185216.1314638-3-boqun.feng@gmail.com [ Applied suggestions and reworded for fixing title typos. ] Signed-off-by: Miguel Ojeda --- samples/rust/rust_print.rs | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/samples/rust/rust_print.rs b/samples/rust/rust_print.rs index 8b39d9cef6d1..67ed8ebf8e8e 100644 --- a/samples/rust/rust_print.rs +++ b/samples/rust/rust_print.rs @@ -15,6 +15,30 @@ module! { struct RustPrint; +fn arc_print() -> Result { + use kernel::sync::*; + + let a = Arc::try_new(1)?; + let b = UniqueArc::try_new("hello, world")?; + + // Prints the value of data in `a`. + pr_info!("{}", a); + + // Uses ":?" to print debug fmt of `b`. + pr_info!("{:?}", b); + + let a: Arc<&str> = b.into(); + let c = a.clone(); + + // Uses `dbg` to print, will move `c` (for temporary debugging purposes). + dbg!(c); + + // Pretty-prints the debug formatting with lower-case hexadecimal integers. + pr_info!("{:#x?}", a); + + Ok(()) +} + impl kernel::Module for RustPrint { fn init(_module: &'static ThisModule) -> Result { pr_info!("Rust printing macros sample (init)\n"); @@ -43,6 +67,8 @@ impl kernel::Module for RustPrint { pr_cont!(" is {}", "continued"); pr_cont!(" with {}\n", "args"); + arc_print()?; + Ok(RustPrint) } } -- GitLab From 3c01a424a37fe625052c68c8620f6aa701f77769 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Fri, 24 Feb 2023 17:09:47 +0900 Subject: [PATCH 2427/5631] rust: Enable the new_uninit feature for kernel and driver crates The unstable new_uninit feature enables various library APIs to create uninitialized containers, such as `Box::assume_init()`. This is necessary to build abstractions that directly initialize memory at the target location, instead of doing copies through the stack. Will be used by the DRM scheduler abstraction in the kernel crate, and by field-wise initialization (e.g. using `place!()` or a future replacement macro which may itself live in `kernel`) in driver crates. Link: https://github.com/Rust-for-Linux/linux/issues/879 Link: https://github.com/Rust-for-Linux/linux/issues/2 Link: https://github.com/rust-lang/rust/issues/63291 Signed-off-by: Asahi Lina Reviewed-by: Martin Rodriguez Reboredo Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Reviewed-by: Vincenzo Palazzo Link: https://lore.kernel.org/r/20230224-rust-new_uninit-v1-1-c951443d9e26@asahilina.net [ Reworded to use `Link` tags. ] Signed-off-by: Miguel Ojeda --- rust/kernel/lib.rs | 1 + scripts/Makefile.build | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 223564f9f0cc..1118cd3e0b5f 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -17,6 +17,7 @@ #![feature(core_ffi_c)] #![feature(dispatch_from_dyn)] #![feature(generic_associated_types)] +#![feature(new_uninit)] #![feature(receiver_trait)] #![feature(unsize)] diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 76323201232a..1364e3d905fc 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -277,7 +277,7 @@ $(obj)/%.lst: $(src)/%.c FORCE # Compile Rust sources (.rs) # --------------------------------------------------------------------------- -rust_allowed_features := core_ffi_c +rust_allowed_features := core_ffi_c,new_uninit rust_common_cmd = \ RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ -- GitLab From 65b571afdfdcefa09508274488086b218e34906d Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Fri, 24 Feb 2023 18:11:47 +0900 Subject: [PATCH 2428/5631] rust: Import upstream `alloc::vec::set_len_on_drop` module This is a subset of the Rust standard library `alloc` crate, version 1.62.0, licensed under "Apache-2.0 OR MIT", from: https://github.com/rust-lang/rust/tree/1.62.0/library/alloc/src The file is copied as-is, with no modifications whatsoever (not even adding the SPDX identifiers). For copyright details, please see: https://github.com/rust-lang/rust/blob/1.62.0/COPYRIGHT Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-vec-v1-1-733b5b5a57c5@asahilina.net [ Import version 1.62.0 instead, to match the one in mainline. ] Signed-off-by: Miguel Ojeda --- rust/alloc/vec/set_len_on_drop.rs | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 rust/alloc/vec/set_len_on_drop.rs diff --git a/rust/alloc/vec/set_len_on_drop.rs b/rust/alloc/vec/set_len_on_drop.rs new file mode 100644 index 000000000000..8b66bc812129 --- /dev/null +++ b/rust/alloc/vec/set_len_on_drop.rs @@ -0,0 +1,28 @@ +// Set the length of the vec when the `SetLenOnDrop` value goes out of scope. +// +// The idea is: The length field in SetLenOnDrop is a local variable +// that the optimizer will see does not alias with any stores through the Vec's data +// pointer. This is a workaround for alias analysis issue #32155 +pub(super) struct SetLenOnDrop<'a> { + len: &'a mut usize, + local_len: usize, +} + +impl<'a> SetLenOnDrop<'a> { + #[inline] + pub(super) fn new(len: &'a mut usize) -> Self { + SetLenOnDrop { local_len: *len, len } + } + + #[inline] + pub(super) fn increment_len(&mut self, increment: usize) { + self.local_len += increment; + } +} + +impl Drop for SetLenOnDrop<'_> { + #[inline] + fn drop(&mut self) { + *self.len = self.local_len; + } +} -- GitLab From ae12ae137270e2e8890dd375aeca6d90556d2629 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Fri, 24 Feb 2023 18:11:48 +0900 Subject: [PATCH 2429/5631] rust: Import upstream `alloc::vec::spec_extend` module This is a subset of the Rust standard library `alloc` crate, version 1.62.0, licensed under "Apache-2.0 OR MIT", from: https://github.com/rust-lang/rust/tree/1.62.0/library/alloc/src The file is copied as-is, with no modifications whatsoever (not even adding the SPDX identifiers). For copyright details, please see: https://github.com/rust-lang/rust/blob/1.62.0/COPYRIGHT Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-vec-v1-2-733b5b5a57c5@asahilina.net [ Import version 1.62.0 instead, to match the one in mainline. ] Signed-off-by: Miguel Ojeda --- rust/alloc/vec/spec_extend.rs | 87 +++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) create mode 100644 rust/alloc/vec/spec_extend.rs diff --git a/rust/alloc/vec/spec_extend.rs b/rust/alloc/vec/spec_extend.rs new file mode 100644 index 000000000000..506ee0ecfa27 --- /dev/null +++ b/rust/alloc/vec/spec_extend.rs @@ -0,0 +1,87 @@ +use crate::alloc::Allocator; +use core::iter::TrustedLen; +use core::ptr::{self}; +use core::slice::{self}; + +use super::{IntoIter, SetLenOnDrop, Vec}; + +// Specialization trait used for Vec::extend +pub(super) trait SpecExtend { + fn spec_extend(&mut self, iter: I); +} + +impl SpecExtend for Vec +where + I: Iterator, +{ + default fn spec_extend(&mut self, iter: I) { + self.extend_desugared(iter) + } +} + +impl SpecExtend for Vec +where + I: TrustedLen, +{ + default fn spec_extend(&mut self, iterator: I) { + // This is the case for a TrustedLen iterator. + let (low, high) = iterator.size_hint(); + if let Some(additional) = high { + debug_assert_eq!( + low, + additional, + "TrustedLen iterator's size hint is not exact: {:?}", + (low, high) + ); + self.reserve(additional); + unsafe { + let mut ptr = self.as_mut_ptr().add(self.len()); + let mut local_len = SetLenOnDrop::new(&mut self.len); + iterator.for_each(move |element| { + ptr::write(ptr, element); + ptr = ptr.offset(1); + // Since the loop executes user code which can panic we have to bump the pointer + // after each step. + // NB can't overflow since we would have had to alloc the address space + local_len.increment_len(1); + }); + } + } else { + // Per TrustedLen contract a `None` upper bound means that the iterator length + // truly exceeds usize::MAX, which would eventually lead to a capacity overflow anyway. + // Since the other branch already panics eagerly (via `reserve()`) we do the same here. + // This avoids additional codegen for a fallback code path which would eventually + // panic anyway. + panic!("capacity overflow"); + } + } +} + +impl SpecExtend> for Vec { + fn spec_extend(&mut self, mut iterator: IntoIter) { + unsafe { + self.append_elements(iterator.as_slice() as _); + } + iterator.forget_remaining_elements(); + } +} + +impl<'a, T: 'a, I, A: Allocator + 'a> SpecExtend<&'a T, I> for Vec +where + I: Iterator, + T: Clone, +{ + default fn spec_extend(&mut self, iterator: I) { + self.spec_extend(iterator.cloned()) + } +} + +impl<'a, T: 'a, A: Allocator + 'a> SpecExtend<&'a T, slice::Iter<'a, T>> for Vec +where + T: Copy, +{ + fn spec_extend(&mut self, iterator: slice::Iter<'a, T>) { + let slice = iterator.as_slice(); + unsafe { self.append_elements(slice) }; + } +} -- GitLab From c4351b646123536048ea71cbcabe1cbd7f4e40c8 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 23 Mar 2023 18:23:56 +0300 Subject: [PATCH 2430/5631] iio: adc: ti-ads1100: fix error code in probe() This code has a copy and paste bug so it accidentally returns "PTR_ERR(data->reg_vdd)" which is a valid pointer cast to int. It should return "ret" instead. Fixes: 541880542f2b ("iio: adc: Add TI ADS1100 and ADS1000") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/36fa2aeb-f392-4793-8b38-ae15514033c8@kili.mountain Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti-ads1100.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/adc/ti-ads1100.c b/drivers/iio/adc/ti-ads1100.c index 6a478efb108b..6b5aebb82455 100644 --- a/drivers/iio/adc/ti-ads1100.c +++ b/drivers/iio/adc/ti-ads1100.c @@ -344,7 +344,7 @@ static int ads1100_probe(struct i2c_client *client) ret = regulator_enable(data->reg_vdd); if (ret < 0) - return dev_err_probe(dev, PTR_ERR(data->reg_vdd), + return dev_err_probe(dev, ret, "Failed to enable vdd regulator\n"); ret = devm_add_action_or_reset(dev, ads1100_reg_disable, data->reg_vdd); -- GitLab From 87441b31232577050a55503362bba4aad439db48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Mon, 27 Mar 2023 16:54:14 +0200 Subject: [PATCH 2431/5631] staging: iio: resolver: ads1210: fix config mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As stated in the device datasheet [1], bits a0 and a1 have to be set to 1 for the configuration mode. [1]: https://www.analog.com/media/en/technical-documentation/data-sheets/ad2s1210.pdf Fixes: b19e9ad5e2cb9 ("staging:iio:resolver:ad2s1210 general driver cleanup") Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20230327145414.1505537-1-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- drivers/staging/iio/resolver/ad2s1210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/resolver/ad2s1210.c b/drivers/staging/iio/resolver/ad2s1210.c index e4cf42438487..636c45b12843 100644 --- a/drivers/staging/iio/resolver/ad2s1210.c +++ b/drivers/staging/iio/resolver/ad2s1210.c @@ -101,7 +101,7 @@ struct ad2s1210_state { static const int ad2s1210_mode_vals[4][2] = { [MOD_POS] = { 0, 0 }, [MOD_VEL] = { 0, 1 }, - [MOD_CONFIG] = { 1, 0 }, + [MOD_CONFIG] = { 1, 1 }, }; static inline void ad2s1210_set_mode(enum ad2s1210_mode mode, -- GitLab From 86fb8b3aebd7f2236c11521ee0c460cceb0e4d6f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 29 Mar 2023 09:46:14 +0200 Subject: [PATCH 2432/5631] dt-bindings: iio: st-sensors: Fix repeated text The description oddly contains a copy of the initial paragraph. Let's not repeat ourselves. Suggested-by: Diederik de Haas Signed-off-by: Linus Walleij Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230329074614.1037625-1-linus.walleij@linaro.org Signed-off-by: Jonathan Cameron --- Documentation/devicetree/bindings/iio/st,st-sensors.yaml | 3 --- 1 file changed, 3 deletions(-) diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index 5eb71b24a7cb..1ff3afca9149 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -11,9 +11,6 @@ description: The STMicroelectronics sensor devices are pretty straight-forward what type of sensor it is. Note that whilst this covers many STMicro MEMs sensors, some more complex IMUs need their own bindings. - The STMicroelectronics sensor devices are pretty straight-forward I2C or - SPI devices, all sharing the same device tree descriptions no matter what - type of sensor it is. maintainers: - Denis Ciocca -- GitLab From 9740827468cea80c42db29e7171a50e99acf7328 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:10 -0400 Subject: [PATCH 2433/5631] iio: addac: stx104: Fix race condition for stx104_write_raw() The priv->chan_out_states array and actual DAC value can become mismatched if stx104_write_raw() is called concurrently. Prevent such a race condition by utilizing a mutex. Fixes: 97a445dad37a ("iio: Add IIO support for the DAC on the Apex Embedded Systems STX104") Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/c95c9a77fcef36b2a052282146950f23bbc1ebdc.1680790580.git.william.gray@linaro.org Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index e45b70aa5bb7..4239aafe42fc 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -69,10 +70,12 @@ struct stx104_reg { /** * struct stx104_iio - IIO device private data structure + * @lock: synchronization lock to prevent I/O race conditions * @chan_out_states: channels' output states * @reg: I/O address offset for the device registers */ struct stx104_iio { + struct mutex lock; unsigned int chan_out_states[STX104_NUM_OUT_CHAN]; struct stx104_reg __iomem *reg; }; @@ -178,9 +181,12 @@ static int stx104_write_raw(struct iio_dev *indio_dev, if ((unsigned int)val > 65535) return -EINVAL; + mutex_lock(&priv->lock); + priv->chan_out_states[chan->channel] = val; iowrite16(val, &priv->reg->dac[chan->channel]); + mutex_unlock(&priv->lock); return 0; } return -EINVAL; @@ -351,6 +357,8 @@ static int stx104_probe(struct device *dev, unsigned int id) indio_dev->name = dev_name(dev); + mutex_init(&priv->lock); + /* configure device for software trigger operation */ iowrite8(0, &priv->reg->acr); -- GitLab From 4f9b80aefb9e2f542a49d9ec087cf5919730e1dd Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:11 -0400 Subject: [PATCH 2434/5631] iio: addac: stx104: Fix race condition when converting analog-to-digital The ADC conversion procedure requires several device I/O operations performed in a particular sequence. If stx104_read_raw() is called concurrently, the ADC conversion procedure could be clobbered. Prevent such a race condition by utilizing a mutex. Fixes: 4075a283ae83 ("iio: stx104: Add IIO support for the ADC channels") Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/2ae5e40eed5006ca735e4c12181a9ff5ced65547.1680790580.git.william.gray@linaro.org Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 4239aafe42fc..8730b79e921c 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -117,6 +117,8 @@ static int stx104_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; } + mutex_lock(&priv->lock); + /* select ADC channel */ iowrite8(chan->channel | (chan->channel << 4), ®->achan); @@ -127,6 +129,8 @@ static int stx104_read_raw(struct iio_dev *indio_dev, while (ioread8(®->cir_asr) & BIT(7)); *val = ioread16(®->ssr_ad); + + mutex_unlock(&priv->lock); return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: /* get ADC bipolar/unipolar configuration */ -- GitLab From 46a4cac7f841a2a2cb397bcb2fd24324004c853e Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:12 -0400 Subject: [PATCH 2435/5631] iio: addac: stx104: Use define rather than hardcoded limit for write val The DAC register is 16 bits wide, so the value passed by write_raw() should be checked against that limit. Rather than hardcoding the 16-bit maximum value limit, use a define to improve readability and make the intention of the code clearer. The explicit cast is also avoided by instead explicitly checking for negative values. Suggested-by: Andy Shevchenko Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/4c9f4f1b4a270d133be70c82a091351b531b5e3e.1680790580.git.william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 8730b79e921c..0ed5f71b18cb 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -181,8 +182,7 @@ static int stx104_write_raw(struct iio_dev *indio_dev, return 0; case IIO_CHAN_INFO_RAW: if (chan->output) { - /* DAC can only accept up to a 16-bit value */ - if ((unsigned int)val > 65535) + if (val < 0 || val > U16_MAX) return -EINVAL; mutex_lock(&priv->lock); -- GitLab From a94abc74c5248d3c09bb18aa8437e85a6a31eadd Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:13 -0400 Subject: [PATCH 2436/5631] iio: addac: stx104: Improve indentation in stx104_write_raw() By bailing out early if chan->output is false for the IIO_CHAN_INFO_RAW, indentation can be decreased by a tab and code readability improved. Suggested-by: Andy Shevchenko Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/487d17da9e2612f3e6b2bd1c3def2fa1b955db9b.1680790580.git.william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 0ed5f71b18cb..81020b710195 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -181,19 +181,19 @@ static int stx104_write_raw(struct iio_dev *indio_dev, return 0; case IIO_CHAN_INFO_RAW: - if (chan->output) { - if (val < 0 || val > U16_MAX) - return -EINVAL; + if (!chan->output) + return -EINVAL; - mutex_lock(&priv->lock); + if (val < 0 || val > U16_MAX) + return -EINVAL; - priv->chan_out_states[chan->channel] = val; - iowrite16(val, &priv->reg->dac[chan->channel]); + mutex_lock(&priv->lock); - mutex_unlock(&priv->lock); - return 0; - } - return -EINVAL; + priv->chan_out_states[chan->channel] = val; + iowrite16(val, &priv->reg->dac[chan->channel]); + + mutex_unlock(&priv->lock); + return 0; } return -EINVAL; -- GitLab From c7301b848191f18719c5a6247300998269059c0b Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:14 -0400 Subject: [PATCH 2437/5631] iio: addac: stx104: Migrate to the regmap API The regmap API supports IO port accessors so we can take advantage of regmap abstractions rather than handling access to the device registers directly in the driver. In addition, to improve code organization in stx104_probe(), the devm_iio_device_register() call is moved above GPIO configuration in order to keep relevant code closer together. Suggested-by: Andy Shevchenko Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/0bcdfc4738cc019fb2ff83f61eb46a3488bc166d.1680790580.git.william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/addac/Kconfig | 2 + drivers/iio/addac/stx104.c | 438 ++++++++++++++++++++----------------- 2 files changed, 245 insertions(+), 195 deletions(-) diff --git a/drivers/iio/addac/Kconfig b/drivers/iio/addac/Kconfig index 2843fcb70e24..877f9124803c 100644 --- a/drivers/iio/addac/Kconfig +++ b/drivers/iio/addac/Kconfig @@ -35,7 +35,9 @@ config STX104 tristate "Apex Embedded Systems STX104 driver" depends on PC104 && X86 select ISA_BUS_API + select REGMAP_MMIO select GPIOLIB + select GPIO_REGMAP help Say yes here to build support for the Apex Embedded Systems STX104 integrated analog PC/104 card. diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 81020b710195..798f98a8872e 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -3,21 +3,20 @@ * IIO driver for the Apex Embedded Systems STX104 * Copyright (C) 2016 William Breathitt Gray */ +#include #include #include -#include -#include +#include +#include #include #include -#include -#include #include #include #include #include #include #include -#include +#include #include #define STX104_OUT_CHAN(chan) { \ @@ -47,107 +46,207 @@ static unsigned int num_stx104; module_param_hw_array(base, uint, ioport, &num_stx104, 0); MODULE_PARM_DESC(base, "Apex Embedded Systems STX104 base addresses"); -/** - * struct stx104_reg - device register structure - * @ssr_ad: Software Strobe Register and ADC Data - * @achan: ADC Channel - * @dio: Digital I/O - * @dac: DAC Channels - * @cir_asr: Clear Interrupts and ADC Status - * @acr: ADC Control - * @pccr_fsh: Pacer Clock Control and FIFO Status MSB - * @acfg: ADC Configuration - */ -struct stx104_reg { - u16 ssr_ad; - u8 achan; - u8 dio; - u16 dac[2]; - u8 cir_asr; - u8 acr; - u8 pccr_fsh; - u8 acfg; -}; +#define STX104_AIO_BASE 0x0 +#define STX104_SOFTWARE_STROBE STX104_AIO_BASE +#define STX104_ADC_DATA STX104_AIO_BASE +#define STX104_ADC_CHANNEL (STX104_AIO_BASE + 0x2) +#define STX104_DIO_REG (STX104_AIO_BASE + 0x3) +#define STX104_DAC_BASE (STX104_AIO_BASE + 0x4) +#define STX104_ADC_STATUS (STX104_AIO_BASE + 0x8) +#define STX104_ADC_CONTROL (STX104_AIO_BASE + 0x9) +#define STX104_ADC_CONFIGURATION (STX104_AIO_BASE + 0x11) + +#define STX104_AIO_DATA_STRIDE 2 +#define STX104_DAC_OFFSET(_channel) (STX104_DAC_BASE + STX104_AIO_DATA_STRIDE * (_channel)) + +/* ADC Channel */ +#define STX104_FC GENMASK(3, 0) +#define STX104_LC GENMASK(7, 4) +#define STX104_SINGLE_CHANNEL(_channel) \ + (u8_encode_bits(_channel, STX104_FC) | u8_encode_bits(_channel, STX104_LC)) + +/* ADC Status */ +#define STX104_SD BIT(5) +#define STX104_CNV BIT(7) +#define STX104_DIFFERENTIAL 1 + +/* ADC Control */ +#define STX104_ALSS GENMASK(1, 0) +#define STX104_SOFTWARE_TRIGGER u8_encode_bits(0x0, STX104_ALSS) + +/* ADC Configuration */ +#define STX104_GAIN GENMASK(1, 0) +#define STX104_ADBU BIT(2) +#define STX104_BIPOLAR 0 +#define STX104_GAIN_X1 0 +#define STX104_GAIN_X2 1 +#define STX104_GAIN_X4 2 +#define STX104_GAIN_X8 3 /** * struct stx104_iio - IIO device private data structure * @lock: synchronization lock to prevent I/O race conditions - * @chan_out_states: channels' output states - * @reg: I/O address offset for the device registers + * @aio_data_map: Regmap for analog I/O data + * @aio_ctl_map: Regmap for analog I/O control */ struct stx104_iio { struct mutex lock; - unsigned int chan_out_states[STX104_NUM_OUT_CHAN]; - struct stx104_reg __iomem *reg; + struct regmap *aio_data_map; + struct regmap *aio_ctl_map; }; -/** - * struct stx104_gpio - GPIO device private data structure - * @chip: instance of the gpio_chip - * @lock: synchronization lock to prevent I/O race conditions - * @base: base port address of the GPIO device - * @out_state: output bits state - */ -struct stx104_gpio { - struct gpio_chip chip; - spinlock_t lock; - u8 __iomem *base; - unsigned int out_state; +static const struct regmap_range aio_ctl_wr_ranges[] = { + regmap_reg_range(0x0, 0x0), regmap_reg_range(0x2, 0x2), regmap_reg_range(0x9, 0x9), + regmap_reg_range(0x11, 0x11), +}; +static const struct regmap_range aio_ctl_rd_ranges[] = { + regmap_reg_range(0x2, 0x2), regmap_reg_range(0x8, 0x9), regmap_reg_range(0x11, 0x11), +}; +static const struct regmap_range aio_ctl_volatile_ranges[] = { + regmap_reg_range(0x8, 0x8), +}; +static const struct regmap_access_table aio_ctl_wr_table = { + .yes_ranges = aio_ctl_wr_ranges, + .n_yes_ranges = ARRAY_SIZE(aio_ctl_wr_ranges), +}; +static const struct regmap_access_table aio_ctl_rd_table = { + .yes_ranges = aio_ctl_rd_ranges, + .n_yes_ranges = ARRAY_SIZE(aio_ctl_rd_ranges), +}; +static const struct regmap_access_table aio_ctl_volatile_table = { + .yes_ranges = aio_ctl_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(aio_ctl_volatile_ranges), +}; + +static const struct regmap_config aio_ctl_regmap_config = { + .name = "aio_ctl", + .reg_bits = 8, + .reg_stride = 1, + .reg_base = STX104_AIO_BASE, + .val_bits = 8, + .io_port = true, + .wr_table = &aio_ctl_wr_table, + .rd_table = &aio_ctl_rd_table, + .volatile_table = &aio_ctl_volatile_table, + .cache_type = REGCACHE_FLAT, +}; + +static const struct regmap_range aio_data_wr_ranges[] = { + regmap_reg_range(0x4, 0x6), +}; +static const struct regmap_range aio_data_rd_ranges[] = { + regmap_reg_range(0x0, 0x0), +}; +static const struct regmap_access_table aio_data_wr_table = { + .yes_ranges = aio_data_wr_ranges, + .n_yes_ranges = ARRAY_SIZE(aio_data_wr_ranges), +}; +static const struct regmap_access_table aio_data_rd_table = { + .yes_ranges = aio_data_rd_ranges, + .n_yes_ranges = ARRAY_SIZE(aio_data_rd_ranges), +}; + +static const struct regmap_config aio_data_regmap_config = { + .name = "aio_data", + .reg_bits = 16, + .reg_stride = STX104_AIO_DATA_STRIDE, + .reg_base = STX104_AIO_BASE, + .val_bits = 16, + .io_port = true, + .wr_table = &aio_data_wr_table, + .rd_table = &aio_data_rd_table, + .volatile_table = &aio_data_rd_table, + .cache_type = REGCACHE_FLAT, +}; + +static const struct regmap_config dio_regmap_config = { + .name = "dio", + .reg_bits = 8, + .reg_stride = 1, + .reg_base = STX104_DIO_REG, + .val_bits = 8, + .io_port = true, }; static int stx104_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { struct stx104_iio *const priv = iio_priv(indio_dev); - struct stx104_reg __iomem *const reg = priv->reg; + int err; unsigned int adc_config; - int adbu; - int gain; + unsigned int value; + unsigned int adc_status; switch (mask) { case IIO_CHAN_INFO_HARDWAREGAIN: - /* get gain configuration */ - adc_config = ioread8(®->acfg); - gain = adc_config & 0x3; + err = regmap_read(priv->aio_ctl_map, STX104_ADC_CONFIGURATION, &adc_config); + if (err) + return err; - *val = 1 << gain; + *val = BIT(u8_get_bits(adc_config, STX104_GAIN)); return IIO_VAL_INT; case IIO_CHAN_INFO_RAW: if (chan->output) { - *val = priv->chan_out_states[chan->channel]; + err = regmap_read(priv->aio_data_map, STX104_DAC_OFFSET(chan->channel), + &value); + if (err) + return err; + *val = value; return IIO_VAL_INT; } mutex_lock(&priv->lock); /* select ADC channel */ - iowrite8(chan->channel | (chan->channel << 4), ®->achan); + err = regmap_write(priv->aio_ctl_map, STX104_ADC_CHANNEL, + STX104_SINGLE_CHANNEL(chan->channel)); + if (err) { + mutex_unlock(&priv->lock); + return err; + } /* trigger ADC sample capture by writing to the 8-bit * Software Strobe Register and wait for completion */ - iowrite8(0, ®->ssr_ad); - while (ioread8(®->cir_asr) & BIT(7)); - - *val = ioread16(®->ssr_ad); + err = regmap_write(priv->aio_ctl_map, STX104_SOFTWARE_STROBE, 0); + if (err) { + mutex_unlock(&priv->lock); + return err; + } + do { + err = regmap_read(priv->aio_ctl_map, STX104_ADC_STATUS, &adc_status); + if (err) { + mutex_unlock(&priv->lock); + return err; + } + } while (u8_get_bits(adc_status, STX104_CNV)); + + err = regmap_read(priv->aio_data_map, STX104_ADC_DATA, &value); + if (err) { + mutex_unlock(&priv->lock); + return err; + } + *val = value; mutex_unlock(&priv->lock); return IIO_VAL_INT; case IIO_CHAN_INFO_OFFSET: /* get ADC bipolar/unipolar configuration */ - adc_config = ioread8(®->acfg); - adbu = !(adc_config & BIT(2)); + err = regmap_read(priv->aio_ctl_map, STX104_ADC_CONFIGURATION, &adc_config); + if (err) + return err; - *val = -32768 * adbu; + *val = (u8_get_bits(adc_config, STX104_ADBU) == STX104_BIPOLAR) ? -32768 : 0; return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: /* get ADC bipolar/unipolar and gain configuration */ - adc_config = ioread8(®->acfg); - adbu = !(adc_config & BIT(2)); - gain = adc_config & 0x3; + err = regmap_read(priv->aio_ctl_map, STX104_ADC_CONFIGURATION, &adc_config); + if (err) + return err; *val = 5; - *val2 = 15 - adbu + gain; + *val2 = (u8_get_bits(adc_config, STX104_ADBU) == STX104_BIPOLAR) ? 14 : 15; + *val2 += u8_get_bits(adc_config, STX104_GAIN); return IIO_VAL_FRACTIONAL_LOG2; } @@ -158,28 +257,29 @@ static int stx104_write_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int val, int val2, long mask) { struct stx104_iio *const priv = iio_priv(indio_dev); + u8 gain; switch (mask) { case IIO_CHAN_INFO_HARDWAREGAIN: /* Only four gain states (x1, x2, x4, x8) */ switch (val) { case 1: - iowrite8(0, &priv->reg->acfg); + gain = STX104_GAIN_X1; break; case 2: - iowrite8(1, &priv->reg->acfg); + gain = STX104_GAIN_X2; break; case 4: - iowrite8(2, &priv->reg->acfg); + gain = STX104_GAIN_X4; break; case 8: - iowrite8(3, &priv->reg->acfg); + gain = STX104_GAIN_X8; break; default: return -EINVAL; } - return 0; + return regmap_write(priv->aio_ctl_map, STX104_ADC_CONFIGURATION, gain); case IIO_CHAN_INFO_RAW: if (!chan->output) return -EINVAL; @@ -187,13 +287,7 @@ static int stx104_write_raw(struct iio_dev *indio_dev, if (val < 0 || val > U16_MAX) return -EINVAL; - mutex_lock(&priv->lock); - - priv->chan_out_states[chan->channel] = val; - iowrite16(val, &priv->reg->dac[chan->channel]); - - mutex_unlock(&priv->lock); - return 0; + return regmap_write(priv->aio_data_map, STX104_DAC_OFFSET(chan->channel), val); } return -EINVAL; @@ -222,119 +316,66 @@ static const struct iio_chan_spec stx104_channels_diff[] = { STX104_IN_CHAN(6, 1), STX104_IN_CHAN(7, 1) }; -static int stx104_gpio_get_direction(struct gpio_chip *chip, - unsigned int offset) -{ - /* GPIO 0-3 are input only, while the rest are output only */ - if (offset < 4) - return 1; - - return 0; -} - -static int stx104_gpio_direction_input(struct gpio_chip *chip, - unsigned int offset) -{ - if (offset >= 4) - return -EINVAL; - - return 0; -} - -static int stx104_gpio_direction_output(struct gpio_chip *chip, - unsigned int offset, int value) +static int stx104_reg_mask_xlate(struct gpio_regmap *const gpio, const unsigned int base, + unsigned int offset, unsigned int *const reg, + unsigned int *const mask) { - if (offset < 4) - return -EINVAL; - - chip->set(chip, offset, value); - return 0; -} - -static int stx104_gpio_get(struct gpio_chip *chip, unsigned int offset) -{ - struct stx104_gpio *const stx104gpio = gpiochip_get_data(chip); - + /* Output lines are located at same register bit offsets as input lines */ if (offset >= 4) - return -EINVAL; + offset -= 4; - return !!(ioread8(stx104gpio->base) & BIT(offset)); -} - -static int stx104_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask, - unsigned long *bits) -{ - struct stx104_gpio *const stx104gpio = gpiochip_get_data(chip); - - *bits = ioread8(stx104gpio->base); + *reg = base; + *mask = BIT(offset); return 0; } -static void stx104_gpio_set(struct gpio_chip *chip, unsigned int offset, - int value) -{ - struct stx104_gpio *const stx104gpio = gpiochip_get_data(chip); - const unsigned int mask = BIT(offset) >> 4; - unsigned long flags; - - if (offset < 4) - return; - - spin_lock_irqsave(&stx104gpio->lock, flags); - - if (value) - stx104gpio->out_state |= mask; - else - stx104gpio->out_state &= ~mask; - - iowrite8(stx104gpio->out_state, stx104gpio->base); - - spin_unlock_irqrestore(&stx104gpio->lock, flags); -} - #define STX104_NGPIO 8 static const char *stx104_names[STX104_NGPIO] = { "DIN0", "DIN1", "DIN2", "DIN3", "DOUT0", "DOUT1", "DOUT2", "DOUT3" }; -static void stx104_gpio_set_multiple(struct gpio_chip *chip, - unsigned long *mask, unsigned long *bits) +static int stx104_init_hw(struct stx104_iio *const priv) { - struct stx104_gpio *const stx104gpio = gpiochip_get_data(chip); - unsigned long flags; - - /* verify masked GPIO are output */ - if (!(*mask & 0xF0)) - return; + int err; - *mask >>= 4; - *bits >>= 4; + /* configure device for software trigger operation */ + err = regmap_write(priv->aio_ctl_map, STX104_ADC_CONTROL, STX104_SOFTWARE_TRIGGER); + if (err) + return err; - spin_lock_irqsave(&stx104gpio->lock, flags); + /* initialize gain setting to x1 */ + err = regmap_write(priv->aio_ctl_map, STX104_ADC_CONFIGURATION, STX104_GAIN_X1); + if (err) + return err; - stx104gpio->out_state &= ~*mask; - stx104gpio->out_state |= *mask & *bits; - iowrite8(stx104gpio->out_state, stx104gpio->base); + /* initialize DAC outputs to 0V */ + err = regmap_write(priv->aio_data_map, STX104_DAC_BASE, 0); + if (err) + return err; + err = regmap_write(priv->aio_data_map, STX104_DAC_BASE + STX104_AIO_DATA_STRIDE, 0); + if (err) + return err; - spin_unlock_irqrestore(&stx104gpio->lock, flags); + return 0; } static int stx104_probe(struct device *dev, unsigned int id) { struct iio_dev *indio_dev; struct stx104_iio *priv; - struct stx104_gpio *stx104gpio; + struct gpio_regmap_config gpio_config; + void __iomem *stx104_base; + struct regmap *aio_ctl_map; + struct regmap *aio_data_map; + struct regmap *dio_map; int err; + unsigned int adc_status; indio_dev = devm_iio_device_alloc(dev, sizeof(*priv)); if (!indio_dev) return -ENOMEM; - stx104gpio = devm_kzalloc(dev, sizeof(*stx104gpio), GFP_KERNEL); - if (!stx104gpio) - return -ENOMEM; - if (!devm_request_region(dev, base[id], STX104_EXTENT, dev_name(dev))) { dev_err(dev, "Unable to lock port addresses (0x%X-0x%X)\n", @@ -342,16 +383,37 @@ static int stx104_probe(struct device *dev, unsigned int id) return -EBUSY; } - priv = iio_priv(indio_dev); - priv->reg = devm_ioport_map(dev, base[id], STX104_EXTENT); - if (!priv->reg) + stx104_base = devm_ioport_map(dev, base[id], STX104_EXTENT); + if (!stx104_base) return -ENOMEM; + aio_ctl_map = devm_regmap_init_mmio(dev, stx104_base, &aio_ctl_regmap_config); + if (IS_ERR(aio_ctl_map)) + return dev_err_probe(dev, PTR_ERR(aio_ctl_map), + "Unable to initialize aio_ctl register map\n"); + + aio_data_map = devm_regmap_init_mmio(dev, stx104_base, &aio_data_regmap_config); + if (IS_ERR(aio_data_map)) + return dev_err_probe(dev, PTR_ERR(aio_data_map), + "Unable to initialize aio_data register map\n"); + + dio_map = devm_regmap_init_mmio(dev, stx104_base, &dio_regmap_config); + if (IS_ERR(dio_map)) + return dev_err_probe(dev, PTR_ERR(dio_map), + "Unable to initialize dio register map\n"); + + priv = iio_priv(indio_dev); + priv->aio_ctl_map = aio_ctl_map; + priv->aio_data_map = aio_data_map; + indio_dev->info = &stx104_info; indio_dev->modes = INDIO_DIRECT_MODE; - /* determine if differential inputs */ - if (ioread8(&priv->reg->cir_asr) & BIT(5)) { + err = regmap_read(aio_ctl_map, STX104_ADC_STATUS, &adc_status); + if (err) + return err; + + if (u8_get_bits(adc_status, STX104_SD) == STX104_DIFFERENTIAL) { indio_dev->num_channels = ARRAY_SIZE(stx104_channels_diff); indio_dev->channels = stx104_channels_diff; } else { @@ -363,41 +425,27 @@ static int stx104_probe(struct device *dev, unsigned int id) mutex_init(&priv->lock); - /* configure device for software trigger operation */ - iowrite8(0, &priv->reg->acr); + err = stx104_init_hw(priv); + if (err) + return err; - /* initialize gain setting to x1 */ - iowrite8(0, &priv->reg->acfg); - - /* initialize DAC output to 0V */ - iowrite16(0, &priv->reg->dac[0]); - iowrite16(0, &priv->reg->dac[1]); - - stx104gpio->chip.label = dev_name(dev); - stx104gpio->chip.parent = dev; - stx104gpio->chip.owner = THIS_MODULE; - stx104gpio->chip.base = -1; - stx104gpio->chip.ngpio = STX104_NGPIO; - stx104gpio->chip.names = stx104_names; - stx104gpio->chip.get_direction = stx104_gpio_get_direction; - stx104gpio->chip.direction_input = stx104_gpio_direction_input; - stx104gpio->chip.direction_output = stx104_gpio_direction_output; - stx104gpio->chip.get = stx104_gpio_get; - stx104gpio->chip.get_multiple = stx104_gpio_get_multiple; - stx104gpio->chip.set = stx104_gpio_set; - stx104gpio->chip.set_multiple = stx104_gpio_set_multiple; - stx104gpio->base = &priv->reg->dio; - stx104gpio->out_state = 0x0; - - spin_lock_init(&stx104gpio->lock); - - err = devm_gpiochip_add_data(dev, &stx104gpio->chip, stx104gpio); - if (err) { - dev_err(dev, "GPIO registering failed (%d)\n", err); + err = devm_iio_device_register(dev, indio_dev); + if (err) return err; - } - return devm_iio_device_register(dev, indio_dev); + gpio_config = (struct gpio_regmap_config) { + .parent = dev, + .regmap = dio_map, + .ngpio = STX104_NGPIO, + .names = stx104_names, + .reg_dat_base = GPIO_REGMAP_ADDR(STX104_DIO_REG), + .reg_set_base = GPIO_REGMAP_ADDR(STX104_DIO_REG), + .ngpio_per_reg = STX104_NGPIO, + .reg_mask_xlate = stx104_reg_mask_xlate, + .drvdata = dio_map, + }; + + return PTR_ERR_OR_ZERO(devm_gpio_regmap_register(dev, &gpio_config)); } static struct isa_driver stx104_driver = { -- GitLab From 7c95a3f51a54db694d3eeef60e77e3a8558ef25e Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 6 Apr 2023 10:40:15 -0400 Subject: [PATCH 2438/5631] iio: addac: stx104: Use regmap_read_poll_timeout() for conversion poll ADC sample captures take a certain amount of time to complete after initiated; this conversion time range can be anywhere from 5 microseconds to 53.68 seconds depending on the configuration of the Analog Input Frame Timer register. When the conversion is in progress, the ADC Status register CNV bit is high. Call regmap_read_poll_timeout() to poll until the ADC conversion is completed (or timeout if more than 53.68 seconds passes). Suggested-by: Jonathan Cameron Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/9ef433f107afd1d4dcd2d97ef0e932d7045c2bbd.1680790580.git.william.gray@linaro.org Signed-off-by: Jonathan Cameron --- drivers/iio/addac/stx104.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/iio/addac/stx104.c b/drivers/iio/addac/stx104.c index 798f98a8872e..d1f7ce033b46 100644 --- a/drivers/iio/addac/stx104.c +++ b/drivers/iio/addac/stx104.c @@ -205,21 +205,25 @@ static int stx104_read_raw(struct iio_dev *indio_dev, return err; } - /* trigger ADC sample capture by writing to the 8-bit - * Software Strobe Register and wait for completion + /* + * Trigger ADC sample capture by writing to the 8-bit Software Strobe Register and + * wait for completion; the conversion time range is 5 microseconds to 53.68 seconds + * in steps of 25 nanoseconds. The actual Analog Input Frame Timer time interval is + * calculated as: + * ai_time_frame_ns = ( AIFT + 1 ) * ( 25 nanoseconds ). + * Where 0 <= AIFT <= 2147483648. */ err = regmap_write(priv->aio_ctl_map, STX104_SOFTWARE_STROBE, 0); if (err) { mutex_unlock(&priv->lock); return err; } - do { - err = regmap_read(priv->aio_ctl_map, STX104_ADC_STATUS, &adc_status); - if (err) { - mutex_unlock(&priv->lock); - return err; - } - } while (u8_get_bits(adc_status, STX104_CNV)); + err = regmap_read_poll_timeout(priv->aio_ctl_map, STX104_ADC_STATUS, adc_status, + !u8_get_bits(adc_status, STX104_CNV), 0, 53687092); + if (err) { + mutex_unlock(&priv->lock); + return err; + } err = regmap_read(priv->aio_data_map, STX104_ADC_DATA, &value); if (err) { -- GitLab From 543c8f2f3cc4706ab0dd2e70dc87bdcbcf8126b3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 4 Apr 2023 15:50:13 -0500 Subject: [PATCH 2439/5631] dt-bindings: iio: temperature: ltc2983: Fix child node unevaluated properties The child node schemas are missing 'unevaluatedProperties' constraints, so any unknown properties are allowed. The current structure with multiple patternProperties schemas doesn't work for unevaluatedProperties as each sub-schema is evaluated independently. To fix this, move the sub-schema for all child nodes to a $defs entry and reference it from each named child node. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230404205014.644336-1-robh@kernel.org Signed-off-by: Jonathan Cameron --- .../bindings/iio/temperature/adi,ltc2983.yaml | 65 +++++++++++-------- 1 file changed, 38 insertions(+), 27 deletions(-) diff --git a/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml b/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml index f44fc32ce87e..e04f961ab92c 100644 --- a/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml +++ b/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml @@ -18,6 +18,28 @@ description: | https://www.analog.com/media/en/technical-documentation/data-sheets/29861fa.pdf https://www.analog.com/media/en/technical-documentation/data-sheets/ltm2985.pdf +$defs: + sensor-node: + type: object + description: Sensor node common constraints + + properties: + reg: + description: + Channel number. Connects the sensor to the channel with this number + of the device. + minimum: 1 + maximum: 20 + + adi,sensor-type: + description: Type of sensor connected to the device. + $ref: /schemas/types.yaml#/definitions/uint32 + + required: + - reg + - adi,sensor-type + + properties: compatible: oneOf: @@ -64,28 +86,10 @@ properties: const: 0 patternProperties: - "@([0-9a-f]+)$": - type: object - description: Sensor. - - properties: - reg: - description: - Channel number. Connects the sensor to the channel with this number - of the device. - minimum: 1 - maximum: 20 - - adi,sensor-type: - description: Type of sensor connected to the device. - $ref: /schemas/types.yaml#/definitions/uint32 - - required: - - reg - - adi,sensor-type - "^thermocouple@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false + description: Thermocouple sensor. properties: @@ -141,7 +145,9 @@ patternProperties: - adi,custom-thermocouple "^diode@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false + description: Diode sensor. properties: @@ -184,7 +190,8 @@ patternProperties: default: 0 "^rtd@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false description: RTD sensor. properties: @@ -282,7 +289,8 @@ patternProperties: - adi,custom-rtd "^thermistor@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false description: Thermistor sensor. properties: @@ -383,7 +391,8 @@ patternProperties: - adi,custom-thermistor "^adc@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false description: Direct ADC sensor. properties: @@ -397,7 +406,8 @@ patternProperties: type: boolean "^temp@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false description: Active analog temperature sensor. properties: @@ -426,7 +436,8 @@ patternProperties: - adi,custom-temp "^rsense@": - type: object + $ref: '#/$defs/sensor-node' + unevaluatedProperties: false description: Sense resistor sensor. properties: -- GitLab From ac2babe70a9b8ab11a408481cad69b71a8b5fa91 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 4 Apr 2023 15:50:14 -0500 Subject: [PATCH 2440/5631] dt-bindings: iio: temperature: ltc2983: Make 'adi,custom-thermocouple' signed The 'adi,custom-thermocouple' property is signed based on the example and driver, so it's type should be int64-matrix rather than uint64-matrix. Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230404205014.644336-2-robh@kernel.org Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/temperature/adi,ltc2983.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml b/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml index e04f961ab92c..dbb85135fd66 100644 --- a/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml +++ b/Documentation/devicetree/bindings/iio/temperature/adi,ltc2983.yaml @@ -127,7 +127,7 @@ patternProperties: description: Used for digitizing custom thermocouples. See Page 59 of the datasheet. - $ref: /schemas/types.yaml#/definitions/uint64-matrix + $ref: /schemas/types.yaml#/definitions/int64-matrix minItems: 3 maxItems: 64 items: -- GitLab From f1caa90085ef31078076990c2ac64d05dd035278 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 3 Apr 2023 21:38:28 -0400 Subject: [PATCH 2441/5631] iio: dac: set variable max5522_channels storage-class-specifier to static smatch reports drivers/iio/dac/max5522.c:55:28: warning: symbol 'max5522_channels' was not declared. Should it be static? This variable is only used in one file so it should be static. Signed-off-by: Tom Rix Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230404013828.1914523-1-trix@redhat.com Signed-off-by: Jonathan Cameron --- drivers/iio/dac/max5522.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/dac/max5522.c b/drivers/iio/dac/max5522.c index 00ba4e98fb9c..05034a306597 100644 --- a/drivers/iio/dac/max5522.c +++ b/drivers/iio/dac/max5522.c @@ -52,7 +52,7 @@ struct max5522_state { } \ } -const struct iio_chan_spec max5522_channels[] = { +static const struct iio_chan_spec max5522_channels[] = { MAX5522_CHANNEL(0), MAX5522_CHANNEL(1), }; -- GitLab From b27f0b40e49f4b109353c62e8eae74f96f842745 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Sat, 25 Feb 2023 15:56:16 +0200 Subject: [PATCH 2442/5631] doc: Make sysfs-bus-iio doc more exact A few IIC channel descriptions explained used units as: data is in foo "that can be processed into an" [unit] value. The "can be processed into" is quite broad statement as it does not really explain what this processing means. This makes units pretty much useless. After discussion with Jonathan, it seems the units for these channels should also be well-defined as for all other channels. The processing means the standard scale and offset application that is used throughout the IIO. Let's make it more obvious by stating that the units are [unit] after scale ane offset are applied. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/41eafb0caa510cddf650cf5ff940639a184f3005.1677331779.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 6ba34c0d9789..7140e8e7313f 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1807,8 +1807,8 @@ What: /sys/bus/iio/devices/iio:deviceX/out_resistanceX_raw KernelVersion: 4.3 Contact: linux-iio@vger.kernel.org Description: - Raw (unscaled no offset etc.) resistance reading that can be processed - into an ohm value. + Raw (unscaled no offset etc.) resistance reading. + Units after application of scale and offset are ohms. What: /sys/bus/iio/devices/iio:deviceX/heater_enable KernelVersion: 4.1.0 @@ -1894,8 +1894,9 @@ What: /sys/bus/iio/devices/iio:deviceX/in_electricalconductivity_raw KernelVersion: 4.8 Contact: linux-iio@vger.kernel.org Description: - Raw (unscaled no offset etc.) electric conductivity reading that - can be processed to siemens per meter. + Raw (unscaled no offset etc.) electric conductivity reading. + Units after application of scale and offset are siemens per + meter. What: /sys/bus/iio/devices/iio:deviceX/in_countY_raw KernelVersion: 4.10 @@ -1951,8 +1952,8 @@ What: /sys/bus/iio/devices/iio:deviceX/in_phaseY_raw KernelVersion: 4.18 Contact: linux-iio@vger.kernel.org Description: - Raw (unscaled) phase difference reading from channel Y - that can be processed to radians. + Raw (unscaled) phase difference reading from channel Y. + Units after application of scale and offset are radians. What: /sys/bus/iio/devices/iio:deviceX/in_massconcentration_pm1_input What: /sys/bus/iio/devices/iio:deviceX/in_massconcentrationY_pm1_input -- GitLab From 38416c28e16890b52fdd5eb73479299ec3f062f3 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:40:28 +0300 Subject: [PATCH 2443/5631] iio: light: Add gain-time-scale helpers Some light sensors can adjust both the HW-gain and integration time. There are cases where adjusting the integration time has similar impact to the scale of the reported values as gain setting has. IIO users do typically expect to handle scale by a single writable 'scale' entry. Driver should then adjust the gain/time accordingly. It however is difficult for a driver to know whether it should change gain or integration time to meet the requested scale. Usually it is preferred to have longer integration time which usually improves accuracy, but there may be use-cases where long measurement times can be an issue. Thus it can be preferable to allow also changing the integration time - but mitigate the scale impact by also changing the gain underneath. Eg, if integration time change doubles the measured values, the driver can reduce the HW-gain to half. The theory of the computations of gain-time-scale is simple. However, some people (undersigned) got that implemented wrong for more than once. Add some gain-time-scale helpers in order to not dublicate errors in all drivers needing these computations. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/268d418e7cffcdaa2ece6738478bbc57692c213e.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/Kconfig | 3 + drivers/iio/Makefile | 1 + drivers/iio/industrialio-gts-helper.c | 1077 +++++++++++++++++++++++++ include/linux/iio/iio-gts-helper.h | 206 +++++ 4 files changed, 1287 insertions(+) create mode 100644 drivers/iio/industrialio-gts-helper.c create mode 100644 include/linux/iio/iio-gts-helper.h diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index b190846c3dc2..52eb46ef84c1 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -30,6 +30,9 @@ config IIO_CONFIGFS (e.g. software triggers). For more info see Documentation/iio/iio_configfs.rst. +config IIO_GTS_HELPER + tristate + config IIO_TRIGGER bool "Enable triggered sampling support" help diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile index 3be08cdadd7e..9622347a1c1b 100644 --- a/drivers/iio/Makefile +++ b/drivers/iio/Makefile @@ -9,6 +9,7 @@ industrialio-$(CONFIG_IIO_BUFFER) += industrialio-buffer.o industrialio-$(CONFIG_IIO_TRIGGER) += industrialio-trigger.o obj-$(CONFIG_IIO_CONFIGFS) += industrialio-configfs.o +obj-$(CONFIG_IIO_GTS_HELPER) += industrialio-gts-helper.o obj-$(CONFIG_IIO_SW_DEVICE) += industrialio-sw-device.o obj-$(CONFIG_IIO_SW_TRIGGER) += industrialio-sw-trigger.o obj-$(CONFIG_IIO_TRIGGERED_EVENT) += industrialio-triggered-event.o diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c new file mode 100644 index 000000000000..8bb68975b259 --- /dev/null +++ b/drivers/iio/industrialio-gts-helper.c @@ -0,0 +1,1077 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* gain-time-scale conversion helpers for IIO light sensors + * + * Copyright (c) 2023 Matti Vaittinen + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +/** + * iio_gts_get_gain - Convert scale to total gain + * + * Internal helper for converting scale to total gain. + * + * @max: Maximum linearized scale. As an example, when scale is created + * in magnitude of NANOs and max scale is 64.1 - The linearized + * scale is 64 100 000 000. + * @scale: Linearized scale to compute the gain for. + * + * Return: (floored) gain corresponding to the scale. -EINVAL if scale + * is invalid. + */ +static int iio_gts_get_gain(const u64 max, const u64 scale) +{ + u64 full = max; + int tmp = 1; + + if (scale > full || !scale) + return -EINVAL; + + if (U64_MAX - full < scale) { + /* Risk of overflow */ + if (full - scale < scale) + return 1; + + full -= scale; + tmp++; + } + + while (full > scale * (u64)tmp) + tmp++; + + return tmp; +} + +/** + * gain_get_scale_fraction - get the gain or time based on scale and known one + * + * @max: Maximum linearized scale. As an example, when scale is created + * in magnitude of NANOs and max scale is 64.1 - The linearized + * scale is 64 100 000 000. + * @scale: Linearized scale to compute the gain/time for. + * @known: Either integration time or gain depending on which one is known + * @unknown: Pointer to variable where the computed gain/time is stored + * + * Internal helper for computing unknown fraction of total gain. + * Compute either gain or time based on scale and either the gain or time + * depending on which one is known. + * + * Return: 0 on success. + */ +static int gain_get_scale_fraction(const u64 max, u64 scale, int known, + int *unknown) +{ + int tot_gain; + + tot_gain = iio_gts_get_gain(max, scale); + if (tot_gain < 0) + return tot_gain; + + *unknown = tot_gain / known; + + /* We require total gain to be exact multiple of known * unknown */ + if (!*unknown || *unknown * known != tot_gain) + return -EINVAL; + + return 0; +} + +static int iio_gts_delinearize(u64 lin_scale, unsigned long scaler, + int *scale_whole, int *scale_nano) +{ + int frac; + + if (scaler > NANO) + return -EOVERFLOW; + + if (!scaler) + return -EINVAL; + + frac = do_div(lin_scale, scaler); + + *scale_whole = lin_scale; + *scale_nano = frac * (NANO / scaler); + + return 0; +} + +static int iio_gts_linearize(int scale_whole, int scale_nano, + unsigned long scaler, u64 *lin_scale) +{ + /* + * Expect scale to be (mostly) NANO or MICRO. Divide divider instead of + * multiplication followed by division to avoid overflow. + */ + if (scaler > NANO || !scaler) + return -EINVAL; + + *lin_scale = (u64)scale_whole * (u64)scaler + + (u64)(scale_nano / (NANO / scaler)); + + return 0; +} + +/** + * iio_gts_total_gain_to_scale - convert gain to scale + * @gts: Gain time scale descriptor + * @total_gain: the gain to be converted + * @scale_int: Pointer to integral part of the scale (typically val1) + * @scale_nano: Pointer to fractional part of the scale (nano or ppb) + * + * Convert the total gain value to scale. NOTE: This does not separate gain + * generated by HW-gain or integration time. It is up to caller to decide what + * part of the total gain is due to integration time and what due to HW-gain. + * + * Return: 0 on success. Negative errno on failure. + */ +int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, + int *scale_int, int *scale_nano) +{ + u64 tmp; + + tmp = gts->max_scale; + + do_div(tmp, total_gain); + + return iio_gts_delinearize(tmp, NANO, scale_int, scale_nano); +} +EXPORT_SYMBOL_NS_GPL(iio_gts_total_gain_to_scale, IIO_GTS_HELPER); + +/** + * iio_gts_purge_avail_scale_table - free-up the available scale tables + * @gts: Gain time scale descriptor + * + * Free the space reserved by iio_gts_build_avail_scale_table(). + */ +static void iio_gts_purge_avail_scale_table(struct iio_gts *gts) +{ + int i; + + if (gts->per_time_avail_scale_tables) { + for (i = 0; i < gts->num_itime; i++) + kfree(gts->per_time_avail_scale_tables[i]); + + kfree(gts->per_time_avail_scale_tables); + gts->per_time_avail_scale_tables = NULL; + } + + kfree(gts->avail_all_scales_table); + gts->avail_all_scales_table = NULL; + + gts->num_avail_all_scales = 0; +} + +static int iio_gts_gain_cmp(const void *a, const void *b) +{ + return *(int *)a - *(int *)b; +} + +static int gain_to_scaletables(struct iio_gts *gts, int **gains, int **scales) +{ + int ret, i, j, new_idx, time_idx; + int *all_gains; + size_t gain_bytes; + + for (i = 0; i < gts->num_itime; i++) { + /* + * Sort the tables for nice output and for easier finding of + * unique values. + */ + sort(gains[i], gts->num_hwgain, sizeof(int), iio_gts_gain_cmp, + NULL); + + /* Convert gains to scales */ + for (j = 0; j < gts->num_hwgain; j++) { + ret = iio_gts_total_gain_to_scale(gts, gains[i][j], + &scales[i][2 * j], + &scales[i][2 * j + 1]); + if (ret) + return ret; + } + } + + gain_bytes = array_size(gts->num_hwgain, sizeof(int)); + all_gains = kcalloc(gts->num_itime, gain_bytes, GFP_KERNEL); + if (!all_gains) + return -ENOMEM; + + /* + * We assume all the gains for same integration time were unique. + * It is likely the first time table had greatest time multiplier as + * the times are in the order of preference and greater times are + * usually preferred. Hence we start from the last table which is likely + * to have the smallest total gains. + */ + time_idx = gts->num_itime - 1; + memcpy(all_gains, gains[time_idx], gain_bytes); + new_idx = gts->num_hwgain; + + while (time_idx--) { + for (j = 0; j < gts->num_hwgain; j++) { + int candidate = gains[time_idx][j]; + int chk; + + if (candidate > all_gains[new_idx - 1]) { + all_gains[new_idx] = candidate; + new_idx++; + + continue; + } + for (chk = 0; chk < new_idx; chk++) + if (candidate <= all_gains[chk]) + break; + + if (candidate == all_gains[chk]) + continue; + + memmove(&all_gains[chk + 1], &all_gains[chk], + (new_idx - chk) * sizeof(int)); + all_gains[chk] = candidate; + new_idx++; + } + } + + gts->avail_all_scales_table = kcalloc(new_idx, 2 * sizeof(int), + GFP_KERNEL); + if (!gts->avail_all_scales_table) { + ret = -ENOMEM; + goto free_out; + } + gts->num_avail_all_scales = new_idx; + + for (i = 0; i < gts->num_avail_all_scales; i++) { + ret = iio_gts_total_gain_to_scale(gts, all_gains[i], + >s->avail_all_scales_table[i * 2], + >s->avail_all_scales_table[i * 2 + 1]); + + if (ret) { + kfree(gts->avail_all_scales_table); + gts->num_avail_all_scales = 0; + goto free_out; + } + } + +free_out: + kfree(all_gains); + + return ret; +} + +/** + * iio_gts_build_avail_scale_table - create tables of available scales + * @gts: Gain time scale descriptor + * + * Build the tables which can represent the available scales based on the + * originally given gain and time tables. When both time and gain tables are + * given this results: + * 1. A set of tables representing available scales for each supported + * integration time. + * 2. A single table listing all the unique scales that any combination of + * supported gains and times can provide. + * + * NOTE: Space allocated for the tables must be freed using + * iio_gts_purge_avail_scale_table() when the tables are no longer needed. + * + * Return: 0 on success. + */ +static int iio_gts_build_avail_scale_table(struct iio_gts *gts) +{ + int **per_time_gains, **per_time_scales, i, j, ret = -ENOMEM; + + per_time_gains = kcalloc(gts->num_itime, sizeof(*per_time_gains), GFP_KERNEL); + if (!per_time_gains) + return ret; + + per_time_scales = kcalloc(gts->num_itime, sizeof(*per_time_scales), GFP_KERNEL); + if (!per_time_scales) + goto free_gains; + + for (i = 0; i < gts->num_itime; i++) { + per_time_scales[i] = kcalloc(gts->num_hwgain, 2 * sizeof(int), + GFP_KERNEL); + if (!per_time_scales[i]) + goto err_free_out; + + per_time_gains[i] = kcalloc(gts->num_hwgain, sizeof(int), + GFP_KERNEL); + if (!per_time_gains[i]) { + kfree(per_time_scales[i]); + goto err_free_out; + } + + for (j = 0; j < gts->num_hwgain; j++) + per_time_gains[i][j] = gts->hwgain_table[j].gain * + gts->itime_table[i].mul; + } + + ret = gain_to_scaletables(gts, per_time_gains, per_time_scales); + if (ret) + goto err_free_out; + + kfree(per_time_gains); + gts->per_time_avail_scale_tables = per_time_scales; + + return 0; + +err_free_out: + for (i--; i; i--) { + kfree(per_time_scales[i]); + kfree(per_time_gains[i]); + } + kfree(per_time_scales); +free_gains: + kfree(per_time_gains); + + return ret; +} + +/** + * iio_gts_build_avail_time_table - build table of available integration times + * @gts: Gain time scale descriptor + * + * Build the table which can represent the available times to be returned + * to users using the read_avail-callback. + * + * NOTE: Space allocated for the tables must be freed using + * iio_gts_purge_avail_time_table() when the tables are no longer needed. + * + * Return: 0 on success. + */ +static int iio_gts_build_avail_time_table(struct iio_gts *gts) +{ + int *times, i, j, idx = 0; + + if (!gts->num_itime) + return 0; + + times = kcalloc(gts->num_itime, sizeof(int), GFP_KERNEL); + if (!times) + return -ENOMEM; + + /* Sort times from all tables to one and remove duplicates */ + for (i = gts->num_itime - 1; i >= 0; i--) { + int new = gts->itime_table[i].time_us; + + if (times[idx] < new) { + times[idx++] = new; + continue; + } + + for (j = 0; j <= idx; j++) { + if (times[j] > new) { + memmove(×[j + 1], ×[j], + (idx - j) * sizeof(int)); + times[j] = new; + idx++; + } + } + } + gts->avail_time_tables = times; + /* + * This is just to survive a unlikely corner-case where times in the + * given time table were not unique. Else we could just trust the + * gts->num_itime. + */ + gts->num_avail_time_tables = idx; + + return 0; +} + +/** + * iio_gts_purge_avail_time_table - free-up the available integration time table + * @gts: Gain time scale descriptor + * + * Free the space reserved by iio_gts_build_avail_time_table(). + */ +static void iio_gts_purge_avail_time_table(struct iio_gts *gts) +{ + if (gts->num_avail_time_tables) { + kfree(gts->avail_time_tables); + gts->avail_time_tables = NULL; + gts->num_avail_time_tables = 0; + } +} + +/** + * iio_gts_build_avail_tables - create tables of available scales and int times + * @gts: Gain time scale descriptor + * + * Build the tables which can represent the available scales and available + * integration times. Availability tables are built based on the originally + * given gain and given time tables. + * + * When both time and gain tables are + * given this results: + * 1. A set of sorted tables representing available scales for each supported + * integration time. + * 2. A single sorted table listing all the unique scales that any combination + * of supported gains and times can provide. + * 3. A sorted table of supported integration times + * + * After these tables are built one can use the iio_gts_all_avail_scales(), + * iio_gts_avail_scales_for_time() and iio_gts_avail_times() helpers to + * implement the read_avail operations. + * + * NOTE: Space allocated for the tables must be freed using + * iio_gts_purge_avail_tables() when the tables are no longer needed. + * + * Return: 0 on success. + */ +static int iio_gts_build_avail_tables(struct iio_gts *gts) +{ + int ret; + + ret = iio_gts_build_avail_scale_table(gts); + if (ret) + return ret; + + ret = iio_gts_build_avail_time_table(gts); + if (ret) + iio_gts_purge_avail_scale_table(gts); + + return ret; +} + +/** + * iio_gts_purge_avail_tables - free-up the availability tables + * @gts: Gain time scale descriptor + * + * Free the space reserved by iio_gts_build_avail_tables(). Frees both the + * integration time and scale tables. + */ +static void iio_gts_purge_avail_tables(struct iio_gts *gts) +{ + iio_gts_purge_avail_time_table(gts); + iio_gts_purge_avail_scale_table(gts); +} + +static void devm_iio_gts_avail_all_drop(void *res) +{ + iio_gts_purge_avail_tables(res); +} + +/** + * devm_iio_gts_build_avail_tables - manged add availability tables + * @dev: Pointer to the device whose lifetime tables are bound + * @gts: Gain time scale descriptor + * + * Build the tables which can represent the available scales and available + * integration times. Availability tables are built based on the originally + * given gain and given time tables. + * + * When both time and gain tables are given this results: + * 1. A set of sorted tables representing available scales for each supported + * integration time. + * 2. A single sorted table listing all the unique scales that any combination + * of supported gains and times can provide. + * 3. A sorted table of supported integration times + * + * After these tables are built one can use the iio_gts_all_avail_scales(), + * iio_gts_avail_scales_for_time() and iio_gts_avail_times() helpers to + * implement the read_avail operations. + * + * The tables are automatically released upon device detach. + * + * Return: 0 on success. + */ +static int devm_iio_gts_build_avail_tables(struct device *dev, + struct iio_gts *gts) +{ + int ret; + + ret = iio_gts_build_avail_tables(gts); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_iio_gts_avail_all_drop, gts); +} + +static int sanity_check_time(const struct iio_itime_sel_mul *t) +{ + if (t->sel < 0 || t->time_us < 0 || t->mul <= 0) + return -EINVAL; + + return 0; +} + +static int sanity_check_gain(const struct iio_gain_sel_pair *g) +{ + if (g->sel < 0 || g->gain <= 0) + return -EINVAL; + + return 0; +} + +static int iio_gts_sanity_check(struct iio_gts *gts) +{ + int g, t, ret; + + if (!gts->num_hwgain && !gts->num_itime) + return -EINVAL; + + for (t = 0; t < gts->num_itime; t++) { + ret = sanity_check_time(>s->itime_table[t]); + if (ret) + return ret; + } + + for (g = 0; g < gts->num_hwgain; g++) { + ret = sanity_check_gain(>s->hwgain_table[g]); + if (ret) + return ret; + } + + for (g = 0; g < gts->num_hwgain; g++) { + for (t = 0; t < gts->num_itime; t++) { + int gain, mul, res; + + gain = gts->hwgain_table[g].gain; + mul = gts->itime_table[t].mul; + + if (check_mul_overflow(gain, mul, &res)) + return -EOVERFLOW; + } + } + + return 0; +} + +static int iio_init_iio_gts(int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts) +{ + int ret; + + memset(gts, 0, sizeof(*gts)); + + ret = iio_gts_linearize(max_scale_int, max_scale_nano, NANO, + >s->max_scale); + if (ret) + return ret; + + gts->hwgain_table = gain_tbl; + gts->num_hwgain = num_gain; + gts->itime_table = tim_tbl; + gts->num_itime = num_times; + + return iio_gts_sanity_check(gts); +} + +/** + * devm_iio_init_iio_gts - Initialize the gain-time-scale helper + * @dev: Pointer to the device whose lifetime gts resources are + * bound + * @max_scale_int: integer part of the maximum scale value + * @max_scale_nano: fraction part of the maximum scale value + * @gain_tbl: table describing supported gains + * @num_gain: number of gains in the gain table + * @tim_tbl: table describing supported integration times. Provide + * the integration time table sorted so that the preferred + * integration time is in the first array index. The search + * functions like the + * iio_gts_find_time_and_gain_sel_for_scale() start search + * from first provided time. + * @num_times: number of times in the time table + * @gts: pointer to the helper struct + * + * Initialize the gain-time-scale helper for use. Note, gains, times, selectors + * and multipliers must be positive. Negative values are reserved for error + * checking. The total gain (maximum gain * maximum time multiplier) must not + * overflow int. The allocated resources will be released upon device detach. + * + * Return: 0 on success. + */ +int devm_iio_init_iio_gts(struct device *dev, int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts) +{ + int ret; + + ret = iio_init_iio_gts(max_scale_int, max_scale_nano, gain_tbl, + num_gain, tim_tbl, num_times, gts); + if (ret) + return ret; + + return devm_iio_gts_build_avail_tables(dev, gts); +} +EXPORT_SYMBOL_NS_GPL(devm_iio_init_iio_gts, IIO_GTS_HELPER); + +/** + * iio_gts_all_avail_scales - helper for listing all available scales + * @gts: Gain time scale descriptor + * @vals: Returned array of supported scales + * @type: Type of returned scale values + * @length: Amount of returned values in array + * + * Return: a value suitable to be returned from read_avail or a negative error. + */ +int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, + int *length) +{ + if (!gts->num_avail_all_scales) + return -EINVAL; + + *vals = gts->avail_all_scales_table; + *type = IIO_VAL_INT_PLUS_NANO; + *length = gts->num_avail_all_scales * 2; + + return IIO_AVAIL_LIST; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_all_avail_scales, IIO_GTS_HELPER); + +/** + * iio_gts_avail_scales_for_time - list scales for integration time + * @gts: Gain time scale descriptor + * @time: Integration time for which the scales are listed + * @vals: Returned array of supported scales + * @type: Type of returned scale values + * @length: Amount of returned values in array + * + * Drivers which do not allow scale setting to change integration time can + * use this helper to list only the scales which are valid for given integration + * time. + * + * Return: a value suitable to be returned from read_avail or a negative error. + */ +int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, + const int **vals, int *type, int *length) +{ + int i; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].time_us == time) + break; + + if (i == gts->num_itime) + return -EINVAL; + + *vals = gts->per_time_avail_scale_tables[i]; + *type = IIO_VAL_INT_PLUS_NANO; + *length = gts->num_hwgain * 2; + + return IIO_AVAIL_LIST; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_avail_scales_for_time, IIO_GTS_HELPER); + +/** + * iio_gts_avail_times - helper for listing available integration times + * @gts: Gain time scale descriptor + * @vals: Returned array of supported times + * @type: Type of returned scale values + * @length: Amount of returned values in array + * + * Return: a value suitable to be returned from read_avail or a negative error. + */ +int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, + int *length) +{ + if (!gts->num_avail_time_tables) + return -EINVAL; + + *vals = gts->avail_time_tables; + *type = IIO_VAL_INT; + *length = gts->num_avail_time_tables; + + return IIO_AVAIL_LIST; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_avail_times, IIO_GTS_HELPER); + +/** + * iio_gts_find_sel_by_gain - find selector corresponding to a HW-gain + * @gts: Gain time scale descriptor + * @gain: HW-gain for which matching selector is searched for + * + * Return: a selector matching given HW-gain or -EINVAL if selector was + * not found. + */ +int iio_gts_find_sel_by_gain(struct iio_gts *gts, int gain) +{ + int i; + + for (i = 0; i < gts->num_hwgain; i++) + if (gts->hwgain_table[i].gain == gain) + return gts->hwgain_table[i].sel; + + return -EINVAL; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_sel_by_gain, IIO_GTS_HELPER); + +/** + * iio_gts_find_gain_by_sel - find HW-gain corresponding to a selector + * @gts: Gain time scale descriptor + * @sel: selector for which matching HW-gain is searched for + * + * Return: a HW-gain matching given selector or -EINVAL if HW-gain was not + * found. + */ +int iio_gts_find_gain_by_sel(struct iio_gts *gts, int sel) +{ + int i; + + for (i = 0; i < gts->num_hwgain; i++) + if (gts->hwgain_table[i].sel == sel) + return gts->hwgain_table[i].gain; + + return -EINVAL; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_by_sel, IIO_GTS_HELPER); + +/** + * iio_gts_get_min_gain - find smallest valid HW-gain + * @gts: Gain time scale descriptor + * + * Return: The smallest HW-gain -EINVAL if no HW-gains were in the tables. + */ +int iio_gts_get_min_gain(struct iio_gts *gts) +{ + int i, min = -EINVAL; + + for (i = 0; i < gts->num_hwgain; i++) { + int gain = gts->hwgain_table[i].gain; + + if (min == -EINVAL) + min = gain; + else + min = min(min, gain); + } + + return min; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_get_min_gain, IIO_GTS_HELPER); + +/** + * iio_find_closest_gain_low - Find the closest lower matching gain + * @gts: Gain time scale descriptor + * @gain: HW-gain for which the closest match is searched + * @in_range: indicate if the @gain was actually in the range of + * supported gains. + * + * Search for closest supported gain that is lower than or equal to the + * gain given as a parameter. This is usable for drivers which do not require + * user to request exact matching gain but rather for rounding to a supported + * gain value which is equal or lower (setting lower gain is typical for + * avoiding saturation) + * + * Return: The closest matching supported gain or -EINVAL if @gain + * was smaller than the smallest supported gain. + */ +int iio_find_closest_gain_low(struct iio_gts *gts, int gain, bool *in_range) +{ + int i, diff = 0; + int best = -1; + + *in_range = false; + + for (i = 0; i < gts->num_hwgain; i++) { + if (gain == gts->hwgain_table[i].gain) { + *in_range = true; + return gain; + } + + if (gain > gts->hwgain_table[i].gain) { + if (!diff) { + diff = gain - gts->hwgain_table[i].gain; + best = i; + } else { + int tmp = gain - gts->hwgain_table[i].gain; + + if (tmp < diff) { + diff = tmp; + best = i; + } + } + } else { + /* + * We found valid HW-gain which is greater than + * reference. So, unless we return a failure below we + * will have found an in-range gain + */ + *in_range = true; + } + } + /* The requested gain was smaller than anything we support */ + if (!diff) { + *in_range = false; + + return -EINVAL; + } + + return gts->hwgain_table[best].gain; +} +EXPORT_SYMBOL_NS_GPL(iio_find_closest_gain_low, IIO_GTS_HELPER); + +static int iio_gts_get_int_time_gain_multiplier_by_sel(struct iio_gts *gts, + int sel) +{ + const struct iio_itime_sel_mul *time; + + time = iio_gts_find_itime_by_sel(gts, sel); + if (!time) + return -EINVAL; + + return time->mul; +} + +/** + * iio_gts_find_gain_for_scale_using_time - Find gain by time and scale + * @gts: Gain time scale descriptor + * @time_sel: Integration time selector corresponding to the time gain is + * searched for + * @scale_int: Integral part of the scale (typically val1) + * @scale_nano: Fractional part of the scale (nano or ppb) + * @gain: Pointer to value where gain is stored. + * + * In some cases the light sensors may want to find a gain setting which + * corresponds given scale and integration time. Sensors which fill the + * gain and time tables may use this helper to retrieve the gain. + * + * Return: 0 on success. -EINVAL if gain matching the parameters is not + * found. + */ +static int iio_gts_find_gain_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain) +{ + u64 scale_linear; + int ret, mul; + + ret = iio_gts_linearize(scale_int, scale_nano, NANO, &scale_linear); + if (ret) + return ret; + + ret = iio_gts_get_int_time_gain_multiplier_by_sel(gts, time_sel); + if (ret < 0) + return ret; + + mul = ret; + + ret = gain_get_scale_fraction(gts->max_scale, scale_linear, mul, gain); + if (ret) + return ret; + + if (!iio_gts_valid_gain(gts, *gain)) + return -EINVAL; + + return 0; +} + +/** + * iio_gts_find_gain_sel_for_scale_using_time - Fetch gain selector. + * @gts: Gain time scale descriptor + * @time_sel: Integration time selector corresponding to the time gain is + * searched for + * @scale_int: Integral part of the scale (typically val1) + * @scale_nano: Fractional part of the scale (nano or ppb) + * @gain_sel: Pointer to value where gain selector is stored. + * + * See iio_gts_find_gain_for_scale_using_time() for more information + */ +int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain_sel) +{ + int gain, ret; + + ret = iio_gts_find_gain_for_scale_using_time(gts, time_sel, scale_int, + scale_nano, &gain); + if (ret) + return ret; + + ret = iio_gts_find_sel_by_gain(gts, gain); + if (ret < 0) + return ret; + + *gain_sel = ret; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_gain_sel_for_scale_using_time, IIO_GTS_HELPER); + +static int iio_gts_get_total_gain(struct iio_gts *gts, int gain, int time) +{ + const struct iio_itime_sel_mul *itime; + + if (!iio_gts_valid_gain(gts, gain)) + return -EINVAL; + + if (!gts->num_itime) + return gain; + + itime = iio_gts_find_itime_by_time(gts, time); + if (!itime) + return -EINVAL; + + return gain * itime->mul; +} + +static int iio_gts_get_scale_linear(struct iio_gts *gts, int gain, int time, + u64 *scale) +{ + int total_gain; + u64 tmp; + + total_gain = iio_gts_get_total_gain(gts, gain, time); + if (total_gain < 0) + return total_gain; + + tmp = gts->max_scale; + + do_div(tmp, total_gain); + + *scale = tmp; + + return 0; +} + +/** + * iio_gts_get_scale - get scale based on integration time and HW-gain + * @gts: Gain time scale descriptor + * @gain: HW-gain for which the scale is computed + * @time: Integration time for which the scale is computed + * @scale_int: Integral part of the scale (typically val1) + * @scale_nano: Fractional part of the scale (nano or ppb) + * + * Compute scale matching the integration time and HW-gain given as parameter. + * + * Return: 0 on success. + */ +int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, + int *scale_nano) +{ + u64 lin_scale; + int ret; + + ret = iio_gts_get_scale_linear(gts, gain, time, &lin_scale); + if (ret) + return ret; + + return iio_gts_delinearize(lin_scale, NANO, scale_int, scale_nano); +} +EXPORT_SYMBOL_NS_GPL(iio_gts_get_scale, IIO_GTS_HELPER); + +/** + * iio_gts_find_new_gain_sel_by_old_gain_time - compensate for time change + * @gts: Gain time scale descriptor + * @old_gain: Previously set gain + * @old_time_sel: Selector corresponding previously set time + * @new_time_sel: Selector corresponding new time to be set + * @new_gain: Pointer to value where new gain is to be written + * + * We may want to mitigate the scale change caused by setting a new integration + * time (for a light sensor) by also updating the (HW)gain. This helper computes + * new gain value to maintain the scale with new integration time. + * + * Return: 0 if an exactly matching supported new gain was found. When a + * non-zero value is returned, the @new_gain will be set to a negative or + * positive value. The negative value means that no gain could be computed. + * Positive value will be the "best possible new gain there could be". There + * can be two reasons why finding the "best possible" new gain is not deemed + * successful. 1) This new value cannot be supported by the hardware. 2) The new + * gain required to maintain the scale would not be an integer. In this case, + * the "best possible" new gain will be a floored optimal gain, which may or + * may not be supported by the hardware. + */ +int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, + int old_gain, int old_time_sel, + int new_time_sel, int *new_gain) +{ + const struct iio_itime_sel_mul *itime_old, *itime_new; + u64 scale; + int ret; + + *new_gain = -1; + + itime_old = iio_gts_find_itime_by_sel(gts, old_time_sel); + if (!itime_old) + return -EINVAL; + + itime_new = iio_gts_find_itime_by_sel(gts, new_time_sel); + if (!itime_new) + return -EINVAL; + + ret = iio_gts_get_scale_linear(gts, old_gain, itime_old->time_us, + &scale); + if (ret) + return ret; + + ret = gain_get_scale_fraction(gts->max_scale, scale, itime_new->mul, + new_gain); + if (ret) + return ret; + + if (!iio_gts_valid_gain(gts, *new_gain)) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_sel_by_old_gain_time, IIO_GTS_HELPER); + +/** + * iio_gts_find_new_gain_by_old_gain_time - compensate for time change + * @gts: Gain time scale descriptor + * @old_gain: Previously set gain + * @old_time: Selector corresponding previously set time + * @new_time: Selector corresponding new time to be set + * @new_gain: Pointer to value where new gain is to be written + * + * We may want to mitigate the scale change caused by setting a new integration + * time (for a light sensor) by also updating the (HW)gain. This helper computes + * new gain value to maintain the scale with new integration time. + * + * Return: 0 if an exactly matching supported new gain was found. When a + * non-zero value is returned, the @new_gain will be set to a negative or + * positive value. The negative value means that no gain could be computed. + * Positive value will be the "best possible new gain there could be". There + * can be two reasons why finding the "best possible" new gain is not deemed + * successful. 1) This new value cannot be supported by the hardware. 2) The new + * gain required to maintain the scale would not be an integer. In this case, + * the "best possible" new gain will be a floored optimal gain, which may or + * may not be supported by the hardware. + */ +int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain) +{ + const struct iio_itime_sel_mul *itime_new; + u64 scale; + int ret; + + *new_gain = -1; + + itime_new = iio_gts_find_itime_by_time(gts, new_time); + if (!itime_new) + return -EINVAL; + + ret = iio_gts_get_scale_linear(gts, old_gain, old_time, &scale); + if (ret) + return ret; + + ret = gain_get_scale_fraction(gts->max_scale, scale, itime_new->mul, + new_gain); + if (ret) + return ret; + + if (!iio_gts_valid_gain(gts, *new_gain)) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(iio_gts_find_new_gain_by_old_gain_time, IIO_GTS_HELPER); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Matti Vaittinen "); +MODULE_DESCRIPTION("IIO light sensor gain-time-scale helpers"); diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h new file mode 100644 index 000000000000..dd64e544a3da --- /dev/null +++ b/include/linux/iio/iio-gts-helper.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* gain-time-scale conversion helpers for IIO light sensors + * + * Copyright (c) 2023 Matti Vaittinen + */ + +#ifndef __IIO_GTS_HELPER__ +#define __IIO_GTS_HELPER__ + +#include + +struct device; + +/** + * struct iio_gain_sel_pair - gain - selector values + * + * In many cases devices like light sensors allow setting signal amplification + * (gain) using a register interface. This structure describes amplification + * and corresponding selector (register value) + * + * @gain: Gain (multiplication) value. Gain must be positive, negative + * values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this gain. + * NOTE: Only selectors >= 0 supported. + */ +struct iio_gain_sel_pair { + int gain; + int sel; +}; + +/** + * struct iio_itime_sel_mul - integration time description + * + * In many cases devices like light sensors allow setting the duration of + * collecting data. Typically this duration has also an impact to the magnitude + * of measured values (gain). This structure describes the relation of + * integration time and amplification as well as corresponding selector + * (register value). + * + * An example could be a sensor allowing 50, 100, 200 and 400 mS times. The + * respective multiplication values could be 50 mS => 1, 100 mS => 2, + * 200 mS => 4 and 400 mS => 8 assuming the impact of integration time would be + * linear in a way that when collecting data for 50 mS caused value X, doubling + * the data collection time caused value 2X etc. + * + * @time_us: Integration time in microseconds. Time values must be positive, + * negative values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this time + * NOTE: Only selectors >= 0 supported. + * @mul: Multiplication to the values caused by this time. + * NOTE: Only multipliers > 0 supported. + */ +struct iio_itime_sel_mul { + int time_us; + int sel; + int mul; +}; + +struct iio_gts { + u64 max_scale; + const struct iio_gain_sel_pair *hwgain_table; + int num_hwgain; + const struct iio_itime_sel_mul *itime_table; + int num_itime; + int **per_time_avail_scale_tables; + int *avail_all_scales_table; + int num_avail_all_scales; + int *avail_time_tables; + int num_avail_time_tables; +}; + +#define GAIN_SCALE_GAIN(_gain, _sel) \ +{ \ + .gain = (_gain), \ + .sel = (_sel), \ +} + +#define GAIN_SCALE_ITIME_US(_itime, _sel, _mul) \ +{ \ + .time_us = (_itime), \ + .sel = (_sel), \ + .mul = (_mul), \ +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_time(struct iio_gts *gts, int time) +{ + int i; + + if (!gts->num_itime) + return NULL; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].time_us == time) + return >s->itime_table[i]; + + return NULL; +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_sel(struct iio_gts *gts, int sel) +{ + int i; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].sel == sel) + return >s->itime_table[i]; + + return NULL; +} + +int devm_iio_init_iio_gts(struct device *dev, int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts); +/** + * iio_gts_find_int_time_by_sel - find integration time matching a selector + * @gts: Gain time scale descriptor + * @sel: selector for which matching integration time is searched for + * + * Return: integration time matching given selector or -EINVAL if + * integration time was not found. + */ +static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_sel(gts, sel); + if (!itime) + return -EINVAL; + + return itime->time_us; +} + +/** + * iio_gts_find_sel_by_int_time - find selector matching integration time + * @gts: Gain time scale descriptor + * @gain: HW-gain for which matching selector is searched for + * + * Return: a selector matching given integration time or -EINVAL if + * selector was not found. + */ +static inline int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_time(gts, time); + if (!itime) + return -EINVAL; + + return itime->sel; +} + +/** + * iio_gts_valid_time - check if given integration time is valid + * @gts: Gain time scale descriptor + * @time_us: Integration time to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_time(struct iio_gts *gts, int time_us) +{ + return iio_gts_find_itime_by_time(gts, time_us) != NULL; +} + +int iio_gts_find_sel_by_gain(struct iio_gts *gts, int gain); + +/** + * iio_gts_valid_gain - check if given HW-gain is valid + * @gts: Gain time scale descriptor + * @gain: HW-gain to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_gain(struct iio_gts *gts, int gain) +{ + return iio_gts_find_sel_by_gain(gts, gain) >= 0; +} + +int iio_find_closest_gain_low(struct iio_gts *gts, int gain, bool *in_range); +int iio_gts_find_gain_by_sel(struct iio_gts *gts, int sel); +int iio_gts_get_min_gain(struct iio_gts *gts); +int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel); +int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time); + +int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, + int *scale_int, int *scale_nano); +int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain_sel); +int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, + int *scale_nano); +int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, + int old_gain, int old_time_sel, + int new_time_sel, int *new_gain); +int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain); +int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, + const int **vals, int *type, int *length); + +#endif -- GitLab From ca11e4a3515430a083fd59822bce0d418f6b6541 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:41:06 +0300 Subject: [PATCH 2444/5631] MAINTAINERS: Add IIO gain-time-scale helpers Add myself as a maintainer for IIO light sensor helpers (helpers for maintaining the scale while adjusting intergration time or gain) and related Kunit tests. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/d46414eabe8dd4cd3edb15f859f3b93cd406d9aa.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..169d1dd45c1a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9938,6 +9938,13 @@ F: Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector F: Documentation/devicetree/bindings/iio/adc/envelope-detector.yaml F: drivers/iio/adc/envelope-detector.c +IIO LIGHT SENSOR GAIN-TIME-SCALE HELPERS +M: Matti Vaittinen +L: linux-iio@vger.kernel.org +S: Maintained +F: drivers/iio/light/gain-time-scale-helper.c +F: drivers/iio/light/gain-time-scale-helper.h + IIO MULTIPLEXER M: Peter Rosin L: linux-iio@vger.kernel.org -- GitLab From 0dca5c9730dcfcf9ba05362e5e36b1ea0c85066d Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:41:33 +0300 Subject: [PATCH 2445/5631] dt-bindings: iio: light: Support ROHM BU27034 ROHM BU27034 is an ambient light sesnor with 3 channels and 3 photo diodes capable of detecting a very wide range of illuminance. Typical application is adjusting LCD and backlight power of TVs and mobile phones. Add dt-bindings. Signed-off-by: Matti Vaittinen Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/66a222574176ee2adbfccf6d9a591c04571a18d9.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- .../bindings/iio/light/rohm,bu27034.yaml | 46 +++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 Documentation/devicetree/bindings/iio/light/rohm,bu27034.yaml diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27034.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27034.yaml new file mode 100644 index 000000000000..30a109a1bf3b --- /dev/null +++ b/Documentation/devicetree/bindings/iio/light/rohm,bu27034.yaml @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/iio/light/rohm,bu27034.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ROHM BU27034 ambient light sensor + +maintainers: + - Matti Vaittinen + +description: | + ROHM BU27034 is an ambient light sesnor with 3 channels and 3 photo diodes + capable of detecting a very wide range of illuminance. Typical application + is adjusting LCD and backlight power of TVs and mobile phones. + https://fscdn.rohm.com/en/products/databook/datasheet/ic/sensor/light/bu27034nuc-e.pdf + +properties: + compatible: + const: rohm,bu27034 + + reg: + maxItems: 1 + + vdd-supply: true + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + light-sensor@38 { + compatible = "rohm,bu27034"; + reg = <0x38>; + vdd-supply = <&vdd>; + }; + }; + +... -- GitLab From e52afbd61039e2c5a4e611e23b4aa963d34a4aef Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:41:58 +0300 Subject: [PATCH 2446/5631] iio: light: ROHM BU27034 Ambient Light Sensor ROHM BU27034 is an ambient light sensor with 3 channels and 3 photo diodes capable of detecting a very wide range of illuminance. Typical application is adjusting LCD and backlight power of TVs and mobile phones. Add initial support for the ROHM BU27034 ambient light sensor. NOTE: - Driver exposes 4 channels. One IIO_LIGHT channel providing the calculated lux values based on measured data from diodes #0 and #1. In addition, 3 IIO_INTENSITY channels are emitting the raw register data from all diodes for more intense user-space computations. - Sensor has GAIN values that can be adjusted from 1x to 4096x. - Sensor has adjustible measurement times of 5, 55, 100, 200 and 400 mS. Driver does not support 5 mS which has special limitations. - Driver exposes standard 'scale' adjustment which is implemented by: 1) Trying to adjust only the GAIN 2) If GAIN adjustment alone can't provide requested scale, adjusting both the time and the gain is attempted. - Driver exposes writable INT_TIME property that can be used for adjusting the measurement time. Time adjustment will also cause the driver to try to adjust the GAIN so that the overall scale is kept as close to the original as possible. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/2a7efb6f335da5526fbe34b95137c5e45db5c5d3.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/light/Kconfig | 14 + drivers/iio/light/Makefile | 1 + drivers/iio/light/rohm-bu27034.c | 1497 ++++++++++++++++++++++++++++++ 3 files changed, 1512 insertions(+) create mode 100644 drivers/iio/light/rohm-bu27034.c diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig index 0d4447df7200..6fa31fcd71a1 100644 --- a/drivers/iio/light/Kconfig +++ b/drivers/iio/light/Kconfig @@ -289,6 +289,20 @@ config JSA1212 To compile this driver as a module, choose M here: the module will be called jsa1212. +config ROHM_BU27034 + tristate "ROHM BU27034 ambient light sensor" + depends on I2C + select REGMAP_I2C + select IIO_GTS_HELPER + select IIO_BUFFER + select IIO_KFIFO_BUF + help + Enable support for the ROHM BU27034 ambient light sensor. ROHM BU27034 + is an ambient light sesnor with 3 channels and 3 photo diodes capable + of detecting a very wide range of illuminance. + Typical application is adjusting LCD and backlight power of TVs and + mobile phones. + config RPR0521 tristate "ROHM RPR0521 ALS and proximity sensor driver" depends on I2C diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile index d74d2b5ff14c..985f6feaccd4 100644 --- a/drivers/iio/light/Makefile +++ b/drivers/iio/light/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_MAX44009) += max44009.o obj-$(CONFIG_NOA1305) += noa1305.o obj-$(CONFIG_OPT3001) += opt3001.o obj-$(CONFIG_PA12203001) += pa12203001.o +obj-$(CONFIG_ROHM_BU27034) += rohm-bu27034.o obj-$(CONFIG_RPR0521) += rpr0521.o obj-$(CONFIG_SI1133) += si1133.o obj-$(CONFIG_SI1145) += si1145.o diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c new file mode 100644 index 000000000000..e486dcf35eba --- /dev/null +++ b/drivers/iio/light/rohm-bu27034.c @@ -0,0 +1,1497 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * BU27034 ROHM Ambient Light Sensor + * + * Copyright (c) 2023, ROHM Semiconductor. + * https://fscdn.rohm.com/en/products/databook/datasheet/ic/sensor/light/bu27034nuc-e.pdf + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#define BU27034_REG_SYSTEM_CONTROL 0x40 +#define BU27034_MASK_SW_RESET BIT(7) +#define BU27034_MASK_PART_ID GENMASK(5, 0) +#define BU27034_ID 0x19 +#define BU27034_REG_MODE_CONTROL1 0x41 +#define BU27034_MASK_MEAS_MODE GENMASK(2, 0) + +#define BU27034_REG_MODE_CONTROL2 0x42 +#define BU27034_MASK_D01_GAIN GENMASK(7, 3) +#define BU27034_MASK_D2_GAIN_HI GENMASK(7, 6) +#define BU27034_MASK_D2_GAIN_LO GENMASK(2, 0) + +#define BU27034_REG_MODE_CONTROL3 0x43 +#define BU27034_REG_MODE_CONTROL4 0x44 +#define BU27034_MASK_MEAS_EN BIT(0) +#define BU27034_MASK_VALID BIT(7) +#define BU27034_REG_DATA0_LO 0x50 +#define BU27034_REG_DATA1_LO 0x52 +#define BU27034_REG_DATA2_LO 0x54 +#define BU27034_REG_DATA2_HI 0x55 +#define BU27034_REG_MANUFACTURER_ID 0x92 +#define BU27034_REG_MAX BU27034_REG_MANUFACTURER_ID + +/* + * The BU27034 does not have interrupt to trigger the data read when a + * measurement has finished. Hence we poll the VALID bit in a thread. We will + * try to wake the thread BU27034_MEAS_WAIT_PREMATURE_MS milliseconds before + * the expected sampling time to prevent the drifting. + * + * If we constantly wake up a bit too late we would eventually skip a sample. + * And because the sleep can't wake up _exactly_ at given time this would be + * inevitable even if the sensor clock would be perfectly phase-locked to CPU + * clock - which we can't say is the case. + * + * This is still fragile. No matter how big advance do we have, we will still + * risk of losing a sample because things can in a rainy-day scenario be + * delayed a lot. Yet, more we reserve the time for polling, more we also lose + * the performance by spending cycles polling the register. So, selecting this + * value is a balancing dance between severity of wasting CPU time and severity + * of losing samples. + * + * In most cases losing the samples is not _that_ crucial because light levels + * tend to change slowly. + * + * Other option that was pointed to me would be always sleeping 1/2 of the + * measurement time, checking the VALID bit and just sleeping again if the bit + * was not set. That should be pretty tolerant against missing samples due to + * the scheduling delays while also not wasting much of cycles for polling. + * Downside is that the time-stamps would be very inaccurate as the wake-up + * would not really be tied to the sensor toggling the valid bit. This would also + * result 'jumps' in the time-stamps when the delay drifted so that wake-up was + * performed during the consecutive wake-ups (Or, when sensor and CPU clocks + * were very different and scheduling the wake-ups was very close to given + * timeout - and when the time-outs were very close to the actual sensor + * sampling, Eg. once in a blue moon, two consecutive time-outs would occur + * without having a sample ready). + */ +#define BU27034_MEAS_WAIT_PREMATURE_MS 5 +#define BU27034_DATA_WAIT_TIME_US 1000 +#define BU27034_TOTAL_DATA_WAIT_TIME_US (BU27034_MEAS_WAIT_PREMATURE_MS * 1000) + +#define BU27034_RETRY_LIMIT 18 + +enum { + BU27034_CHAN_ALS, + BU27034_CHAN_DATA0, + BU27034_CHAN_DATA1, + BU27034_CHAN_DATA2, + BU27034_NUM_CHANS +}; + +static const unsigned long bu27034_scan_masks[] = { + GENMASK(BU27034_CHAN_DATA2, BU27034_CHAN_ALS), 0 +}; + +/* + * Available scales with gain 1x - 4096x, timings 55, 100, 200, 400 mS + * Time impacts to gain: 1x, 2x, 4x, 8x. + * + * => Max total gain is HWGAIN * gain by integration time (8 * 4096) = 32768 + * + * Using NANO precision for scale we must use scale 64x corresponding gain 1x + * to avoid precision loss. (32x would result scale 976 562.5(nanos). + */ +#define BU27034_SCALE_1X 64 + +/* See the data sheet for the "Gain Setting" table */ +#define BU27034_GSEL_1X 0x00 /* 00000 */ +#define BU27034_GSEL_4X 0x08 /* 01000 */ +#define BU27034_GSEL_16X 0x0a /* 01010 */ +#define BU27034_GSEL_32X 0x0b /* 01011 */ +#define BU27034_GSEL_64X 0x0c /* 01100 */ +#define BU27034_GSEL_256X 0x18 /* 11000 */ +#define BU27034_GSEL_512X 0x19 /* 11001 */ +#define BU27034_GSEL_1024X 0x1a /* 11010 */ +#define BU27034_GSEL_2048X 0x1b /* 11011 */ +#define BU27034_GSEL_4096X 0x1c /* 11100 */ + +/* Available gain settings */ +static const struct iio_gain_sel_pair bu27034_gains[] = { + GAIN_SCALE_GAIN(1, BU27034_GSEL_1X), + GAIN_SCALE_GAIN(4, BU27034_GSEL_4X), + GAIN_SCALE_GAIN(16, BU27034_GSEL_16X), + GAIN_SCALE_GAIN(32, BU27034_GSEL_32X), + GAIN_SCALE_GAIN(64, BU27034_GSEL_64X), + GAIN_SCALE_GAIN(256, BU27034_GSEL_256X), + GAIN_SCALE_GAIN(512, BU27034_GSEL_512X), + GAIN_SCALE_GAIN(1024, BU27034_GSEL_1024X), + GAIN_SCALE_GAIN(2048, BU27034_GSEL_2048X), + GAIN_SCALE_GAIN(4096, BU27034_GSEL_4096X), +}; + +/* + * The IC has 5 modes for sampling time. 5 mS mode is exceptional as it limits + * the data collection to data0-channel only and cuts the supported range to + * 10 bit. It is not supported by the driver. + * + * "normal" modes are 55, 100, 200 and 400 mS modes - which do have direct + * multiplying impact to the register values (similar to gain). + * + * This means that if meas-mode is changed for example from 400 => 200, + * the scale is doubled. Eg, time impact to total gain is x1, x2, x4, x8. + */ +#define BU27034_MEAS_MODE_100MS 0 +#define BU27034_MEAS_MODE_55MS 1 +#define BU27034_MEAS_MODE_200MS 2 +#define BU27034_MEAS_MODE_400MS 4 + +static const struct iio_itime_sel_mul bu27034_itimes[] = { + GAIN_SCALE_ITIME_US(400000, BU27034_MEAS_MODE_400MS, 8), + GAIN_SCALE_ITIME_US(200000, BU27034_MEAS_MODE_200MS, 4), + GAIN_SCALE_ITIME_US(100000, BU27034_MEAS_MODE_100MS, 2), + GAIN_SCALE_ITIME_US(55000, BU27034_MEAS_MODE_55MS, 1), +}; + +#define BU27034_CHAN_DATA(_name, _ch2) \ +{ \ + .type = IIO_INTENSITY, \ + .channel = BU27034_CHAN_##_name, \ + .channel2 = (_ch2), \ + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ + BIT(IIO_CHAN_INFO_SCALE), \ + .info_mask_separate_available = BIT(IIO_CHAN_INFO_SCALE), \ + .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_INT_TIME), \ + .info_mask_shared_by_all_available = \ + BIT(IIO_CHAN_INFO_INT_TIME), \ + .address = BU27034_REG_##_name##_LO, \ + .scan_index = BU27034_CHAN_##_name, \ + .scan_type = { \ + .sign = 'u', \ + .realbits = 16, \ + .storagebits = 16, \ + .endianness = IIO_LE, \ + }, \ + .indexed = 1, \ +} + +static const struct iio_chan_spec bu27034_channels[] = { + { + .type = IIO_LIGHT, + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_SCALE), + .channel = BU27034_CHAN_ALS, + .scan_index = BU27034_CHAN_ALS, + .scan_type = { + .sign = 'u', + .realbits = 32, + .storagebits = 32, + .endianness = IIO_CPU, + }, + }, + /* + * The BU27034 DATA0 and DATA1 channels are both on the visible light + * area (mostly). The data0 sensitivity peaks at 500nm, DATA1 at 600nm. + * These wave lengths are pretty much on the border of colours making + * these a poor candidates for R/G/B standardization. Hence they're both + * marked as clear channels + */ + BU27034_CHAN_DATA(DATA0, IIO_MOD_LIGHT_CLEAR), + BU27034_CHAN_DATA(DATA1, IIO_MOD_LIGHT_CLEAR), + BU27034_CHAN_DATA(DATA2, IIO_MOD_LIGHT_IR), + IIO_CHAN_SOFT_TIMESTAMP(4), +}; + +struct bu27034_data { + struct regmap *regmap; + struct device *dev; + /* + * Protect gain and time during scale adjustment and data reading. + * Protect measurement enabling/disabling. + */ + struct mutex mutex; + struct iio_gts gts; + struct task_struct *task; + __le16 raw[3]; + struct { + u32 mlux; + __le16 channels[3]; + s64 ts __aligned(8); + } scan; +}; + +struct bu27034_result { + u16 ch0; + u16 ch1; + u16 ch2; +}; + +static const struct regmap_range bu27034_volatile_ranges[] = { + { + .range_min = BU27034_REG_MODE_CONTROL4, + .range_max = BU27034_REG_MODE_CONTROL4, + }, { + .range_min = BU27034_REG_DATA0_LO, + .range_max = BU27034_REG_DATA2_HI, + }, +}; + +static const struct regmap_access_table bu27034_volatile_regs = { + .yes_ranges = &bu27034_volatile_ranges[0], + .n_yes_ranges = ARRAY_SIZE(bu27034_volatile_ranges), +}; + +static const struct regmap_range bu27034_read_only_ranges[] = { + { + .range_min = BU27034_REG_DATA0_LO, + .range_max = BU27034_REG_DATA2_HI, + }, { + .range_min = BU27034_REG_MANUFACTURER_ID, + .range_max = BU27034_REG_MANUFACTURER_ID, + } +}; + +static const struct regmap_access_table bu27034_ro_regs = { + .no_ranges = &bu27034_read_only_ranges[0], + .n_no_ranges = ARRAY_SIZE(bu27034_read_only_ranges), +}; + +static const struct regmap_config bu27034_regmap = { + .reg_bits = 8, + .val_bits = 8, + .max_register = BU27034_REG_MAX, + .cache_type = REGCACHE_RBTREE, + .volatile_table = &bu27034_volatile_regs, + .wr_table = &bu27034_ro_regs, +}; + +struct bu27034_gain_check { + int old_gain; + int new_gain; + int chan; +}; + +static int bu27034_get_gain_sel(struct bu27034_data *data, int chan) +{ + int ret, val; + + switch (chan) { + case BU27034_CHAN_DATA0: + case BU27034_CHAN_DATA1: + { + int reg[] = { + [BU27034_CHAN_DATA0] = BU27034_REG_MODE_CONTROL2, + [BU27034_CHAN_DATA1] = BU27034_REG_MODE_CONTROL3, + }; + ret = regmap_read(data->regmap, reg[chan], &val); + if (ret) + return ret; + + return FIELD_GET(BU27034_MASK_D01_GAIN, val); + } + case BU27034_CHAN_DATA2: + { + int d2_lo_bits = fls(BU27034_MASK_D2_GAIN_LO); + + ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL2, &val); + if (ret) + return ret; + + /* + * The data2 channel gain is composed by 5 non continuous bits + * [7:6], [2:0]. Thus when we combine the 5-bit 'selector' + * from register value we must right shift the high bits by 3. + */ + return FIELD_GET(BU27034_MASK_D2_GAIN_HI, val) << d2_lo_bits | + FIELD_GET(BU27034_MASK_D2_GAIN_LO, val); + } + default: + return -EINVAL; + } +} + +static int bu27034_get_gain(struct bu27034_data *data, int chan, int *gain) +{ + int ret, sel; + + ret = bu27034_get_gain_sel(data, chan); + if (ret < 0) + return ret; + + sel = ret; + + ret = iio_gts_find_gain_by_sel(&data->gts, sel); + if (ret < 0) { + dev_err(data->dev, "chan %u: unknown gain value 0x%x\n", chan, + sel); + + return ret; + } + + *gain = ret; + + return 0; +} + +static int bu27034_get_int_time(struct bu27034_data *data) +{ + int ret, sel; + + ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL1, &sel); + if (ret) + return ret; + + return iio_gts_find_int_time_by_sel(&data->gts, + sel & BU27034_MASK_MEAS_MODE); +} + +static int _bu27034_get_scale(struct bu27034_data *data, int channel, int *val, + int *val2) +{ + int gain, ret; + + ret = bu27034_get_gain(data, channel, &gain); + if (ret) + return ret; + + ret = bu27034_get_int_time(data); + if (ret < 0) + return ret; + + return iio_gts_get_scale(&data->gts, gain, ret, val, val2); +} + +static int bu27034_get_scale(struct bu27034_data *data, int channel, int *val, + int *val2) +{ + int ret; + + if (channel == BU27034_CHAN_ALS) { + *val = 0; + *val2 = 1000; + return IIO_VAL_INT_PLUS_MICRO; + } + + mutex_lock(&data->mutex); + ret = _bu27034_get_scale(data, channel, val, val2); + mutex_unlock(&data->mutex); + if (ret) + return ret; + + return IIO_VAL_INT_PLUS_NANO; +} + +/* Caller should hold the lock to protect lux reading */ +static int bu27034_write_gain_sel(struct bu27034_data *data, int chan, int sel) +{ + static const int reg[] = { + [BU27034_CHAN_DATA0] = BU27034_REG_MODE_CONTROL2, + [BU27034_CHAN_DATA1] = BU27034_REG_MODE_CONTROL3, + }; + int mask, val; + + if (chan != BU27034_CHAN_DATA0 && chan != BU27034_CHAN_DATA1) + return -EINVAL; + + val = FIELD_PREP(BU27034_MASK_D01_GAIN, sel); + + mask = BU27034_MASK_D01_GAIN; + + if (chan == BU27034_CHAN_DATA0) { + /* + * We keep the same gain for channel 2 as we set for channel 0 + * We can't allow them to be individually controlled because + * setting one will impact also the other. Also, if we don't + * always update both gains we may result unsupported bit + * combinations. + * + * This is not nice but this is yet another place where the + * user space must be prepared to surprizes. Namely, see chan 2 + * gain changed when chan 0 gain is changed. + * + * This is not fatal for most users though. I don't expect the + * channel 2 to be used in any generic cases - the intensity + * values provided by the sensor for IR area are not openly + * documented. Also, channel 2 is not used for visible light. + * + * So, if there is application which is written to utilize the + * channel 2 - then it is probably specifically targeted to this + * sensor and knows how to utilize those values. It is safe to + * hope such user can also cope with the gain changes. + */ + mask |= BU27034_MASK_D2_GAIN_LO; + + /* + * The D2 gain bits are directly the lowest bits of selector. + * Just do add those bits to the value + */ + val |= sel & BU27034_MASK_D2_GAIN_LO; + } + + return regmap_update_bits(data->regmap, reg[chan], mask, val); +} + +static int bu27034_set_gain(struct bu27034_data *data, int chan, int gain) +{ + int ret; + + /* + * We don't allow setting channel 2 gain as it messes up the + * gain for channel 0 - which shares the high bits + */ + if (chan != BU27034_CHAN_DATA0 && chan != BU27034_CHAN_DATA1) + return -EINVAL; + + ret = iio_gts_find_sel_by_gain(&data->gts, gain); + if (ret < 0) + return ret; + + return bu27034_write_gain_sel(data, chan, ret); +} + +/* Caller should hold the lock to protect data->int_time */ +static int bu27034_set_int_time(struct bu27034_data *data, int time) +{ + int ret; + + ret = iio_gts_find_sel_by_int_time(&data->gts, time); + if (ret < 0) + return ret; + + return regmap_update_bits(data->regmap, BU27034_REG_MODE_CONTROL1, + BU27034_MASK_MEAS_MODE, ret); +} + +/* + * We try to change the time in such way that the scale is maintained for + * given channels by adjusting gain so that it compensates the time change. + */ +static int bu27034_try_set_int_time(struct bu27034_data *data, int time_us) +{ + struct bu27034_gain_check gains[] = { + { .chan = BU27034_CHAN_DATA0 }, + { .chan = BU27034_CHAN_DATA1 }, + }; + int numg = ARRAY_SIZE(gains); + int ret, int_time_old, i; + + mutex_lock(&data->mutex); + ret = bu27034_get_int_time(data); + if (ret < 0) + goto unlock_out; + + int_time_old = ret; + + if (!iio_gts_valid_time(&data->gts, time_us)) { + dev_err(data->dev, "Unsupported integration time %u\n", + time_us); + ret = -EINVAL; + + goto unlock_out; + } + + if (time_us == int_time_old) { + ret = 0; + goto unlock_out; + } + + for (i = 0; i < numg; i++) { + ret = bu27034_get_gain(data, gains[i].chan, &gains[i].old_gain); + if (ret) + goto unlock_out; + + ret = iio_gts_find_new_gain_by_old_gain_time(&data->gts, + gains[i].old_gain, + int_time_old, time_us, + &gains[i].new_gain); + if (ret) { + int scale1, scale2; + bool ok; + + _bu27034_get_scale(data, gains[i].chan, &scale1, &scale2); + dev_dbg(data->dev, + "chan %u, can't support time %u with scale %u %u\n", + gains[i].chan, time_us, scale1, scale2); + + if (gains[i].new_gain < 0) + goto unlock_out; + + /* + * If caller requests for integration time change and we + * can't support the scale - then the caller should be + * prepared to 'pick up the pieces and deal with the + * fact that the scale changed'. + */ + ret = iio_find_closest_gain_low(&data->gts, + gains[i].new_gain, &ok); + + if (!ok) + dev_dbg(data->dev, + "optimal gain out of range for chan %u\n", + gains[i].chan); + + if (ret < 0) { + dev_dbg(data->dev, + "Total gain increase. Risk of saturation"); + ret = iio_gts_get_min_gain(&data->gts); + if (ret < 0) + goto unlock_out; + } + dev_dbg(data->dev, "chan %u scale changed\n", + gains[i].chan); + gains[i].new_gain = ret; + dev_dbg(data->dev, "chan %u new gain %u\n", + gains[i].chan, gains[i].new_gain); + } + } + + for (i = 0; i < numg; i++) { + ret = bu27034_set_gain(data, gains[i].chan, gains[i].new_gain); + if (ret) + goto unlock_out; + } + + ret = bu27034_set_int_time(data, time_us); + +unlock_out: + mutex_unlock(&data->mutex); + + return ret; +} + +static int bu27034_set_scale(struct bu27034_data *data, int chan, + int val, int val2) +{ + int ret, time_sel, gain_sel, i; + bool found = false; + + if (chan == BU27034_CHAN_DATA2) + return -EINVAL; + + if (chan == BU27034_CHAN_ALS) { + if (val == 0 && val2 == 1000) + return 0; + + return -EINVAL; + } + + mutex_lock(&data->mutex); + ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL1, &time_sel); + if (ret) + goto unlock_out; + + ret = iio_gts_find_gain_sel_for_scale_using_time(&data->gts, time_sel, + val, val2 * 1000, &gain_sel); + if (ret) { + /* + * Could not support scale with given time. Need to change time. + * We still want to maintain the scale for all channels + */ + struct bu27034_gain_check gain; + int new_time_sel; + + /* + * Populate information for the other channel which should also + * maintain the scale. (Due to the HW limitations the chan2 + * gets the same gain as chan0, so we only need to explicitly + * set the chan 0 and 1). + */ + if (chan == BU27034_CHAN_DATA0) + gain.chan = BU27034_CHAN_DATA1; + else if (chan == BU27034_CHAN_DATA1) + gain.chan = BU27034_CHAN_DATA0; + + ret = bu27034_get_gain(data, gain.chan, &gain.old_gain); + if (ret) + goto unlock_out; + + /* + * Iterate through all the times to see if we find one which + * can support requested scale for requested channel, while + * maintaining the scale for other channels + */ + for (i = 0; i < data->gts.num_itime; i++) { + new_time_sel = data->gts.itime_table[i].sel; + + if (new_time_sel == time_sel) + continue; + + /* Can we provide requested scale with this time? */ + ret = iio_gts_find_gain_sel_for_scale_using_time( + &data->gts, new_time_sel, val, val2 * 1000, + &gain_sel); + if (ret) + continue; + + /* Can the other channel(s) maintain scale? */ + ret = iio_gts_find_new_gain_sel_by_old_gain_time( + &data->gts, gain.old_gain, time_sel, + new_time_sel, &gain.new_gain); + if (!ret) { + /* Yes - we found suitable time */ + found = true; + break; + } + } + if (!found) { + dev_dbg(data->dev, + "Can't set scale maintaining other channels\n"); + ret = -EINVAL; + + goto unlock_out; + } + + ret = bu27034_set_gain(data, gain.chan, gain.new_gain); + if (ret) + goto unlock_out; + + ret = regmap_update_bits(data->regmap, BU27034_REG_MODE_CONTROL1, + BU27034_MASK_MEAS_MODE, new_time_sel); + if (ret) + goto unlock_out; + } + + ret = bu27034_write_gain_sel(data, chan, gain_sel); +unlock_out: + mutex_unlock(&data->mutex); + + return ret; +} + +/* + * for (D1/D0 < 0.87): + * lx = 0.004521097 * D1 - 0.002663996 * D0 + + * 0.00012213 * D1 * D1 / D0 + * + * => 115.7400832 * ch1 / gain1 / mt - + * 68.1982976 * ch0 / gain0 / mt + + * 0.00012213 * 25600 * (ch1 / gain1 / mt) * 25600 * + * (ch1 /gain1 / mt) / (25600 * ch0 / gain0 / mt) + * + * A = 0.00012213 * 25600 * (ch1 /gain1 / mt) * 25600 * + * (ch1 /gain1 / mt) / (25600 * ch0 / gain0 / mt) + * => 0.00012213 * 25600 * (ch1 /gain1 / mt) * + * (ch1 /gain1 / mt) / (ch0 / gain0 / mt) + * => 0.00012213 * 25600 * (ch1 / gain1) * (ch1 /gain1 / mt) / + * (ch0 / gain0) + * => 0.00012213 * 25600 * (ch1 / gain1) * (ch1 /gain1 / mt) * + * gain0 / ch0 + * => 3.126528 * ch1 * ch1 * gain0 / gain1 / gain1 / mt /ch0 + * + * lx = (115.7400832 * ch1 / gain1 - 68.1982976 * ch0 / gain0) / + * mt + A + * => (115.7400832 * ch1 / gain1 - 68.1982976 * ch0 / gain0) / + * mt + 3.126528 * ch1 * ch1 * gain0 / gain1 / gain1 / mt / + * ch0 + * + * => (115.7400832 * ch1 / gain1 - 68.1982976 * ch0 / gain0 + + * 3.126528 * ch1 * ch1 * gain0 / gain1 / gain1 / ch0) / + * mt + * + * For (0.87 <= D1/D0 < 1.00) + * lx = (0.001331* D0 + 0.0000354 * D1) * ((D1/D0 – 0.87) * (0.385) + 1) + * => (0.001331 * 256 * 100 * ch0 / gain0 / mt + 0.0000354 * 256 * + * 100 * ch1 / gain1 / mt) * ((D1/D0 - 0.87) * (0.385) + 1) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * ((D1/D0 - 0.87) * (0.385) + 1) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * (0.385 * D1/D0 - 0.66505) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * (0.385 * 256 * 100 * ch1 / gain1 / mt / (256 * 100 * ch0 / gain0 / mt) - 0.66505) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * (9856 * ch1 / gain1 / mt / (25600 * ch0 / gain0 / mt) + 0.66505) + * => 13.118336 * ch1 / (gain1 * mt) + * + 22.66064768 * ch0 / (gain0 * mt) + * + 8931.90144 * ch1 * ch1 * gain0 / + * (25600 * ch0 * gain1 * gain1 * mt) + * + 0.602694912 * ch1 / (gain1 * mt) + * + * => [0.3489024 * ch1 * ch1 * gain0 / (ch0 * gain1 * gain1) + * + 22.66064768 * ch0 / gain0 + * + 13.721030912 * ch1 / gain1 + * ] / mt + * + * For (D1/D0 >= 1.00) + * + * lx = (0.001331* D0 + 0.0000354 * D1) * ((D1/D0 – 2.0) * (-0.05) + 1) + * => (0.001331* D0 + 0.0000354 * D1) * (-0.05D1/D0 + 1.1) + * => (0.001331 * 256 * 100 * ch0 / gain0 / mt + 0.0000354 * 256 * + * 100 * ch1 / gain1 / mt) * (-0.05D1/D0 + 1.1) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * (-0.05 * 256 * 100 * ch1 / gain1 / mt / (256 * 100 * ch0 / gain0 / mt) + 1.1) + * => (34.0736 * ch0 / gain0 / mt + 0.90624 * ch1 / gain1 / mt) * + * (-1280 * ch1 / (gain1 * mt * 25600 * ch0 / gain0 / mt) + 1.1) + * => (34.0736 * ch0 * -1280 * ch1 * gain0 * mt /( gain0 * mt * gain1 * mt * 25600 * ch0) + * + 34.0736 * 1.1 * ch0 / (gain0 * mt) + * + 0.90624 * ch1 * -1280 * ch1 *gain0 * mt / (gain1 * mt *gain1 * mt * 25600 * ch0) + * + 1.1 * 0.90624 * ch1 / (gain1 * mt) + * => -43614.208 * ch1 / (gain1 * mt * 25600) + * + 37.48096 ch0 / (gain0 * mt) + * - 1159.9872 * ch1 * ch1 * gain0 / (gain1 * gain1 * mt * 25600 * ch0) + * + 0.996864 ch1 / (gain1 * mt) + * => [ + * - 0.045312 * ch1 * ch1 * gain0 / (gain1 * gain1 * ch0) + * - 0.706816 * ch1 / gain1 + * + 37.48096 ch0 /gain0 + * ] * mt + * + * + * So, the first case (D1/D0 < 0.87) can be computed to a form: + * + * lx = (3.126528 * ch1 * ch1 * gain0 / (ch0 * gain1 * gain1) + + * 115.7400832 * ch1 / gain1 + + * -68.1982976 * ch0 / gain0 + * / mt + * + * Second case (0.87 <= D1/D0 < 1.00) goes to form: + * + * => [0.3489024 * ch1 * ch1 * gain0 / (ch0 * gain1 * gain1) + + * 13.721030912 * ch1 / gain1 + + * 22.66064768 * ch0 / gain0 + * ] / mt + * + * Third case (D1/D0 >= 1.00) goes to form: + * => [-0.045312 * ch1 * ch1 * gain0 / (ch0 * gain1 * gain1) + + * -0.706816 * ch1 / gain1 + + * 37.48096 ch0 /(gain0 + * ] / mt + * + * This can be unified to format: + * lx = [ + * A * ch1 * ch1 * gain0 / (ch0 * gain1 * gain1) + + * B * ch1 / gain1 + + * C * ch0 / gain0 + * ] / mt + * + * For case 1: + * A = 3.126528, + * B = 115.7400832 + * C = -68.1982976 + * + * For case 2: + * A = 0.3489024 + * B = 13.721030912 + * C = 22.66064768 + * + * For case 3: + * A = -0.045312 + * B = -0.706816 + * C = 37.48096 + */ + +struct bu27034_lx_coeff { + unsigned int A; + unsigned int B; + unsigned int C; + /* Indicate which of the coefficients above are negative */ + bool is_neg[3]; +}; + +static inline u64 gain_mul_div_helper(u64 val, unsigned int gain, + unsigned int div) +{ + /* + * Max gain for a channel is 4096. The max u64 (0xffffffffffffffffULL) + * divided by 4096 is 0xFFFFFFFFFFFFF (GENMASK_ULL(51, 0)) (floored). + * Thus, the 0xFFFFFFFFFFFFF is the largest value we can safely multiply + * with the gain, no matter what gain is set. + * + * So, multiplication with max gain may overflow if val is greater than + * 0xFFFFFFFFFFFFF (52 bits set).. + * + * If this is the case we divide first. + */ + if (val < GENMASK_ULL(51, 0)) { + val *= gain; + do_div(val, div); + } else { + do_div(val, div); + val *= gain; + } + + return val; +} + +static u64 bu27034_fixp_calc_t1_64bit(unsigned int coeff, unsigned int ch0, + unsigned int ch1, unsigned int gain0, + unsigned int gain1) +{ + unsigned int helper; + u64 helper64; + + helper64 = (u64)coeff * (u64)ch1 * (u64)ch1; + + helper = gain1 * gain1; + if (helper > ch0) { + do_div(helper64, helper); + + return gain_mul_div_helper(helper64, gain0, ch0); + } + + do_div(helper64, ch0); + + return gain_mul_div_helper(helper64, gain0, helper); + +} + +static u64 bu27034_fixp_calc_t1(unsigned int coeff, unsigned int ch0, + unsigned int ch1, unsigned int gain0, + unsigned int gain1) +{ + unsigned int helper, tmp; + + /* + * Here we could overflow even the 64bit value. Hence we + * multiply with gain0 only after the divisions - even though + * it may result loss of accuracy + */ + helper = coeff * ch1 * ch1; + tmp = helper * gain0; + + helper = ch1 * ch1; + + if (check_mul_overflow(helper, coeff, &helper)) + return bu27034_fixp_calc_t1_64bit(coeff, ch0, ch1, gain0, gain1); + + if (check_mul_overflow(helper, gain0, &tmp)) + return bu27034_fixp_calc_t1_64bit(coeff, ch0, ch1, gain0, gain1); + + return tmp / (gain1 * gain1) / ch0; + +} + +static u64 bu27034_fixp_calc_t23(unsigned int coeff, unsigned int ch, + unsigned int gain) +{ + unsigned int helper; + u64 helper64; + + if (!check_mul_overflow(coeff, ch, &helper)) + return helper / gain; + + helper64 = (u64)coeff * (u64)ch; + do_div(helper64, gain); + + return helper64; +} + +static int bu27034_fixp_calc_lx(unsigned int ch0, unsigned int ch1, + unsigned int gain0, unsigned int gain1, + unsigned int meastime, int coeff_idx) +{ + static const struct bu27034_lx_coeff coeff[] = { + { + .A = 31265280, /* 3.126528 */ + .B = 1157400832, /*115.7400832 */ + .C = 681982976, /* -68.1982976 */ + .is_neg = {false, false, true}, + }, { + .A = 3489024, /* 0.3489024 */ + .B = 137210309, /* 13.721030912 */ + .C = 226606476, /* 22.66064768 */ + /* All terms positive */ + }, { + .A = 453120, /* -0.045312 */ + .B = 7068160, /* -0.706816 */ + .C = 374809600, /* 37.48096 */ + .is_neg = {true, true, false}, + } + }; + const struct bu27034_lx_coeff *c = &coeff[coeff_idx]; + u64 res = 0, terms[3]; + int i; + + if (coeff_idx >= ARRAY_SIZE(coeff)) + return -EINVAL; + + terms[0] = bu27034_fixp_calc_t1(c->A, ch0, ch1, gain0, gain1); + terms[1] = bu27034_fixp_calc_t23(c->B, ch1, gain1); + terms[2] = bu27034_fixp_calc_t23(c->C, ch0, gain0); + + /* First, add positive terms */ + for (i = 0; i < 3; i++) + if (!c->is_neg[i]) + res += terms[i]; + + /* No positive term => zero lux */ + if (!res) + return 0; + + /* Then, subtract negative terms (if any) */ + for (i = 0; i < 3; i++) + if (c->is_neg[i]) { + /* + * If the negative term is greater than positive - then + * the darkness has taken over and we are all doomed! Eh, + * I mean, then we can just return 0 lx and go out + */ + if (terms[i] >= res) + return 0; + + res -= terms[i]; + } + + meastime *= 10; + do_div(res, meastime); + + return (int) res; +} + +static bool bu27034_has_valid_sample(struct bu27034_data *data) +{ + int ret, val; + + ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL4, &val); + if (ret) { + dev_err(data->dev, "Read failed %d\n", ret); + + return false; + } + + return val & BU27034_MASK_VALID; +} + +/* + * Reading the register where VALID bit is clears this bit. (So does changing + * any gain / integration time configuration registers) The bit gets + * set when we have acquired new data. We use this bit to indicate data + * validity. + */ +static void bu27034_invalidate_read_data(struct bu27034_data *data) +{ + bu27034_has_valid_sample(data); +} + +static int bu27034_read_result(struct bu27034_data *data, int chan, int *res) +{ + int reg[] = { + [BU27034_CHAN_DATA0] = BU27034_REG_DATA0_LO, + [BU27034_CHAN_DATA1] = BU27034_REG_DATA1_LO, + [BU27034_CHAN_DATA2] = BU27034_REG_DATA2_LO, + }; + int valid, ret; + __le16 val; + + ret = regmap_read_poll_timeout(data->regmap, BU27034_REG_MODE_CONTROL4, + valid, (valid & BU27034_MASK_VALID), + BU27034_DATA_WAIT_TIME_US, 0); + if (ret) + return ret; + + ret = regmap_bulk_read(data->regmap, reg[chan], &val, sizeof(val)); + if (ret) + return ret; + + *res = le16_to_cpu(val); + + return 0; +} + +static int bu27034_get_result_unlocked(struct bu27034_data *data, __le16 *res, + int size) +{ + int ret = 0, retry_cnt = 0; + +retry: + /* Get new value from sensor if data is ready */ + if (bu27034_has_valid_sample(data)) { + ret = regmap_bulk_read(data->regmap, BU27034_REG_DATA0_LO, + res, size); + if (ret) + return ret; + + bu27034_invalidate_read_data(data); + } else { + /* No new data in sensor. Wait and retry */ + retry_cnt++; + + if (retry_cnt > BU27034_RETRY_LIMIT) { + dev_err(data->dev, "No data from sensor\n"); + + return -ETIMEDOUT; + } + + msleep(25); + + goto retry; + } + + return ret; +} + +static int bu27034_meas_set(struct bu27034_data *data, bool en) +{ + if (en) + return regmap_set_bits(data->regmap, BU27034_REG_MODE_CONTROL4, + BU27034_MASK_MEAS_EN); + + return regmap_clear_bits(data->regmap, BU27034_REG_MODE_CONTROL4, + BU27034_MASK_MEAS_EN); +} + +static int bu27034_get_single_result(struct bu27034_data *data, int chan, + int *val) +{ + int ret; + + if (chan < BU27034_CHAN_DATA0 || chan > BU27034_CHAN_DATA2) + return -EINVAL; + + ret = bu27034_meas_set(data, true); + if (ret) + return ret; + + ret = bu27034_get_int_time(data); + if (ret < 0) + return ret; + + msleep(ret / 1000); + + return bu27034_read_result(data, chan, val); +} + +/* + * The formula given by vendor for computing luxes out of data0 and data1 + * (in open air) is as follows: + * + * Let's mark: + * D0 = data0/ch0_gain/meas_time_ms * 25600 + * D1 = data1/ch1_gain/meas_time_ms * 25600 + * + * Then: + * if (D1/D0 < 0.87) + * lx = (0.001331 * D0 + 0.0000354 * D1) * ((D1 / D0 - 0.87) * 3.45 + 1) + * else if (D1/D0 < 1) + * lx = (0.001331 * D0 + 0.0000354 * D1) * ((D1 / D0 - 0.87) * 0.385 + 1) + * else + * lx = (0.001331 * D0 + 0.0000354 * D1) * ((D1 / D0 - 2) * -0.05 + 1) + * + * We use it here. Users who have for example some colored lens + * need to modify the calculation but I hope this gives a starting point for + * those working with such devices. + */ + +static int bu27034_calc_mlux(struct bu27034_data *data, __le16 *res, int *val) +{ + unsigned int gain0, gain1, meastime; + unsigned int d1_d0_ratio_scaled; + u16 ch0, ch1; + u64 helper64; + int ret; + + /* + * We return 0 lux if calculation fails. This should be reasonably + * easy to spot from the buffers especially if raw-data channels show + * valid values + */ + *val = 0; + + ch0 = max_t(u16, 1, le16_to_cpu(res[0])); + ch1 = max_t(u16, 1, le16_to_cpu(res[1])); + + ret = bu27034_get_gain(data, BU27034_CHAN_DATA0, &gain0); + if (ret) + return ret; + + ret = bu27034_get_gain(data, BU27034_CHAN_DATA1, &gain1); + if (ret) + return ret; + + ret = bu27034_get_int_time(data); + if (ret < 0) + return ret; + + meastime = ret; + + d1_d0_ratio_scaled = (unsigned int)ch1 * (unsigned int)gain0 * 100; + helper64 = (u64)ch1 * (u64)gain0 * 100LLU; + + if (helper64 != d1_d0_ratio_scaled) { + unsigned int div = (unsigned int)ch0 * gain1; + + do_div(helper64, div); + d1_d0_ratio_scaled = helper64; + } else { + d1_d0_ratio_scaled /= ch0 * gain1; + } + + if (d1_d0_ratio_scaled < 87) + ret = bu27034_fixp_calc_lx(ch0, ch1, gain0, gain1, meastime, 0); + else if (d1_d0_ratio_scaled < 100) + ret = bu27034_fixp_calc_lx(ch0, ch1, gain0, gain1, meastime, 1); + else + ret = bu27034_fixp_calc_lx(ch0, ch1, gain0, gain1, meastime, 2); + + if (ret < 0) + return ret; + + *val = ret; + + return 0; + +} + +static int bu27034_get_mlux(struct bu27034_data *data, int chan, int *val) +{ + __le16 res[3]; + int ret; + + ret = bu27034_meas_set(data, true); + if (ret) + return ret; + + ret = bu27034_get_result_unlocked(data, &res[0], sizeof(res)); + if (ret) + return ret; + + ret = bu27034_calc_mlux(data, res, val); + if (ret) + return ret; + + ret = bu27034_meas_set(data, false); + if (ret) + dev_err(data->dev, "failed to disable measurement\n"); + + return 0; +} + +static int bu27034_read_raw(struct iio_dev *idev, + struct iio_chan_spec const *chan, + int *val, int *val2, long mask) +{ + struct bu27034_data *data = iio_priv(idev); + int ret; + + switch (mask) { + case IIO_CHAN_INFO_INT_TIME: + *val = bu27034_get_int_time(data); + if (*val < 0) + return *val; + + return IIO_VAL_INT; + + case IIO_CHAN_INFO_SCALE: + return bu27034_get_scale(data, chan->channel, val, val2); + + case IIO_CHAN_INFO_RAW: + { + int (*result_get)(struct bu27034_data *data, int chan, int *val); + + if (chan->type == IIO_INTENSITY) + result_get = bu27034_get_single_result; + else if (chan->type == IIO_LIGHT) + result_get = bu27034_get_mlux; + else + return -EINVAL; + + /* Don't mess with measurement enabling while buffering */ + ret = iio_device_claim_direct_mode(idev); + if (ret) + return ret; + + mutex_lock(&data->mutex); + /* + * Reading one channel at a time is inefficient but we + * don't care here. Buffered version should be used if + * performance is an issue. + */ + ret = result_get(data, chan->channel, val); + + mutex_unlock(&data->mutex); + iio_device_release_direct_mode(idev); + + if (ret) + return ret; + + return IIO_VAL_INT; + } + default: + return -EINVAL; + } +} + +static int bu27034_write_raw(struct iio_dev *idev, + struct iio_chan_spec const *chan, + int val, int val2, long mask) +{ + struct bu27034_data *data = iio_priv(idev); + int ret; + + ret = iio_device_claim_direct_mode(idev); + if (ret) + return ret; + + switch (mask) { + case IIO_CHAN_INFO_SCALE: + ret = bu27034_set_scale(data, chan->channel, val, val2); + break; + case IIO_CHAN_INFO_INT_TIME: + ret = bu27034_try_set_int_time(data, val); + break; + default: + ret = -EINVAL; + break; + } + + iio_device_release_direct_mode(idev); + + return ret; +} + +static int bu27034_read_avail(struct iio_dev *idev, + struct iio_chan_spec const *chan, const int **vals, + int *type, int *length, long mask) +{ + struct bu27034_data *data = iio_priv(idev); + + switch (mask) { + case IIO_CHAN_INFO_INT_TIME: + return iio_gts_avail_times(&data->gts, vals, type, length); + case IIO_CHAN_INFO_SCALE: + return iio_gts_all_avail_scales(&data->gts, vals, type, length); + default: + return -EINVAL; + } +} + +static const struct iio_info bu27034_info = { + .read_raw = &bu27034_read_raw, + .write_raw = &bu27034_write_raw, + .read_avail = &bu27034_read_avail, +}; + +static int bu27034_chip_init(struct bu27034_data *data) +{ + int ret, sel; + + /* Reset */ + ret = regmap_update_bits(data->regmap, BU27034_REG_SYSTEM_CONTROL, + BU27034_MASK_SW_RESET, BU27034_MASK_SW_RESET); + if (ret) + return dev_err_probe(data->dev, ret, "Sensor reset failed\n"); + + msleep(1); + /* + * Read integration time here to ensure it is in regmap cache. We do + * this to speed-up the int-time acquisition in the start of the buffer + * handling thread where longer delays could make it more likely we end + * up skipping a sample, and where the longer delays make timestamps + * less accurate. + */ + ret = regmap_read(data->regmap, BU27034_REG_MODE_CONTROL1, &sel); + if (ret) + dev_err(data->dev, "reading integration time failed\n"); + + return 0; +} + +static int bu27034_wait_for_data(struct bu27034_data *data) +{ + int ret, val; + + ret = regmap_read_poll_timeout(data->regmap, BU27034_REG_MODE_CONTROL4, + val, val & BU27034_MASK_VALID, + BU27034_DATA_WAIT_TIME_US, + BU27034_TOTAL_DATA_WAIT_TIME_US); + if (ret) { + dev_err(data->dev, "data polling %s\n", + !(val & BU27034_MASK_VALID) ? "timeout" : "fail"); + + return ret; + } + + ret = regmap_bulk_read(data->regmap, BU27034_REG_DATA0_LO, + &data->scan.channels[0], + sizeof(data->scan.channels)); + if (ret) + return ret; + + bu27034_invalidate_read_data(data); + + return 0; +} + +static int bu27034_buffer_thread(void *arg) +{ + struct iio_dev *idev = arg; + struct bu27034_data *data; + int wait_ms; + + data = iio_priv(idev); + + wait_ms = bu27034_get_int_time(data); + wait_ms /= 1000; + + wait_ms -= BU27034_MEAS_WAIT_PREMATURE_MS; + + while (!kthread_should_stop()) { + int ret; + int64_t tstamp; + + msleep(wait_ms); + ret = bu27034_wait_for_data(data); + if (ret) + continue; + + tstamp = iio_get_time_ns(idev); + + if (test_bit(BU27034_CHAN_ALS, idev->active_scan_mask)) { + int mlux; + + ret = bu27034_calc_mlux(data, &data->scan.channels[0], + &mlux); + if (ret) + dev_err(data->dev, "failed to calculate lux\n"); + + /* + * The maximum Milli lux value we get with gain 1x time + * 55mS data ch0 = 0xffff ch1 = 0xffff fits in 26 bits + * so there should be no problem returning int from + * computations and casting it to u32 + */ + data->scan.mlux = (u32)mlux; + } + iio_push_to_buffers_with_timestamp(idev, &data->scan, tstamp); + } + + return 0; +} + +static int bu27034_buffer_enable(struct iio_dev *idev) +{ + struct bu27034_data *data = iio_priv(idev); + struct task_struct *task; + int ret; + + mutex_lock(&data->mutex); + ret = bu27034_meas_set(data, true); + if (ret) + goto unlock_out; + + task = kthread_run(bu27034_buffer_thread, idev, + "bu27034-buffering-%u", + iio_device_id(idev)); + if (IS_ERR(task)) { + ret = PTR_ERR(task); + goto unlock_out; + } + + data->task = task; + +unlock_out: + mutex_unlock(&data->mutex); + + return ret; +} + +static int bu27034_buffer_disable(struct iio_dev *idev) +{ + struct bu27034_data *data = iio_priv(idev); + int ret; + + mutex_lock(&data->mutex); + if (data->task) { + kthread_stop(data->task); + data->task = NULL; + } + + ret = bu27034_meas_set(data, false); + mutex_unlock(&data->mutex); + + return ret; +} + +static const struct iio_buffer_setup_ops bu27034_buffer_ops = { + .postenable = &bu27034_buffer_enable, + .predisable = &bu27034_buffer_disable, +}; + +static int bu27034_probe(struct i2c_client *i2c) +{ + struct device *dev = &i2c->dev; + struct bu27034_data *data; + struct regmap *regmap; + struct iio_dev *idev; + unsigned int part_id, reg; + int ret; + + regmap = devm_regmap_init_i2c(i2c, &bu27034_regmap); + if (IS_ERR(regmap)) + return dev_err_probe(dev, PTR_ERR(regmap), + "Failed to initialize Regmap\n"); + + idev = devm_iio_device_alloc(dev, sizeof(*data)); + if (!idev) + return -ENOMEM; + + ret = devm_regulator_get_enable(dev, "vdd"); + if (ret) + return dev_err_probe(dev, ret, "Failed to get regulator\n"); + + data = iio_priv(idev); + + ret = regmap_read(regmap, BU27034_REG_SYSTEM_CONTROL, ®); + if (ret) + return dev_err_probe(dev, ret, "Failed to access sensor\n"); + + part_id = FIELD_GET(BU27034_MASK_PART_ID, reg); + + if (part_id != BU27034_ID) + dev_warn(dev, "unknown device 0x%x\n", part_id); + + ret = devm_iio_init_iio_gts(dev, BU27034_SCALE_1X, 0, bu27034_gains, + ARRAY_SIZE(bu27034_gains), bu27034_itimes, + ARRAY_SIZE(bu27034_itimes), &data->gts); + if (ret) + return ret; + + mutex_init(&data->mutex); + data->regmap = regmap; + data->dev = dev; + + idev->channels = bu27034_channels; + idev->num_channels = ARRAY_SIZE(bu27034_channels); + idev->name = "bu27034"; + idev->info = &bu27034_info; + + idev->modes = INDIO_DIRECT_MODE | INDIO_BUFFER_SOFTWARE; + idev->available_scan_masks = bu27034_scan_masks; + + ret = bu27034_chip_init(data); + if (ret) + return ret; + + ret = devm_iio_kfifo_buffer_setup(dev, idev, &bu27034_buffer_ops); + if (ret) + return dev_err_probe(dev, ret, "buffer setup failed\n"); + + ret = devm_iio_device_register(dev, idev); + if (ret < 0) + return dev_err_probe(dev, ret, + "Unable to register iio device\n"); + + return ret; +} + +static const struct of_device_id bu27034_of_match[] = { + { .compatible = "rohm,bu27034" }, + { } +}; +MODULE_DEVICE_TABLE(of, bu27034_of_match); + +static struct i2c_driver bu27034_i2c_driver = { + .driver = { + .name = "bu27034-als", + .of_match_table = bu27034_of_match, + }, + .probe_new = bu27034_probe, +}; +module_i2c_driver(bu27034_i2c_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Matti Vaittinen "); +MODULE_DESCRIPTION("ROHM BU27034 ambient light sensor driver"); +MODULE_IMPORT_NS(IIO_GTS_HELPER); -- GitLab From c86b0e73f0bebbb0245ef2bac4cf269d61ff828c Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 31 Mar 2023 15:42:17 +0300 Subject: [PATCH 2447/5631] MAINTAINERS: Add ROHM BU27034 Add myself as a maintainer for ROHM BU27034 ALS driver. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/eac4b5f7fc8adcaac59ffa73e46cd7bb9c90edfa.1680263956.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 169d1dd45c1a..7b9c0c841884 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18098,6 +18098,12 @@ S: Maintained F: Documentation/devicetree/bindings/iio/light/bh1750.yaml F: drivers/iio/light/bh1750.c +ROHM BU27034 AMBIENT LIGHT SENSOR DRIVER +M: Matti Vaittinen +L: linux-iio@vger.kernel.org +S: Supported +F: drivers/iio/light/rohm-bu27034.c + ROHM MULTIFUNCTION BD9571MWV-M PMIC DEVICE DRIVERS M: Marek Vasut L: linux-kernel@vger.kernel.org -- GitLab From 4308c6878acfb58eda46483644b516abd732b6dd Mon Sep 17 00:00:00 2001 From: Vivek Pernamitta Date: Tue, 4 Apr 2023 15:14:16 +0530 Subject: [PATCH 2448/5631] bus: mhi: host: Avoid ringing EV DB if there are no elements to process Currently, mhi_process_data_event_ring()/mhi_process_ctrl_ev_ring() APIs are ringing DB even if there are no ring elements to process. This could cause the device to process the DB event in the absence of ring elements. So to avoid this unnecessary device processing, let's ring event DB only if there are any ring elements to process. Signed-off-by: Vivek Pernamitta Reviewed-by: Jeffrey Hugo Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1680601458-9105-1-git-send-email-quic_vpernami@quicinc.com [mani: massaged the commit message a bit] Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index 4fa0969472fc..c7eb7b8be9d6 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -961,7 +961,9 @@ int mhi_process_ctrl_ev_ring(struct mhi_controller *mhi_cntrl, } read_lock_bh(&mhi_cntrl->pm_lock); - if (likely(MHI_DB_ACCESS_VALID(mhi_cntrl))) + + /* Ring EV DB only if there is any pending element to process */ + if (likely(MHI_DB_ACCESS_VALID(mhi_cntrl)) && count) mhi_ring_er_db(mhi_event); read_unlock_bh(&mhi_cntrl->pm_lock); @@ -1031,7 +1033,9 @@ int mhi_process_data_event_ring(struct mhi_controller *mhi_cntrl, count++; } read_lock_bh(&mhi_cntrl->pm_lock); - if (likely(MHI_DB_ACCESS_VALID(mhi_cntrl))) + + /* Ring EV DB only if there is any pending element to process */ + if (likely(MHI_DB_ACCESS_VALID(mhi_cntrl)) && count) mhi_ring_er_db(mhi_event); read_unlock_bh(&mhi_cntrl->pm_lock); -- GitLab From 1db6b0a4246ce708b89f5136571130b9987741d1 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 31 Mar 2023 18:12:49 +0300 Subject: [PATCH 2449/5631] phy: qcom-qmp-pcie: sc8180x PCIe PHY has 2 lanes All PCIe PHYs on sc8180x platform have 2 lanes, so change the number of lanes to 2. Fixes: f839f14e24f2 ("phy: qcom-qmp: Add sc8180x PCIe support") Cc: stable@vger.kernel.org # 5.15 Sgned-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230331151250.4049-1-dmitry.baryshkov@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index b1e81530d551..f378c1ebefd7 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -2331,7 +2331,7 @@ static const struct qmp_phy_cfg msm8998_pciephy_cfg = { }; static const struct qmp_phy_cfg sc8180x_pciephy_cfg = { - .lanes = 1, + .lanes = 2, .tbls = { .serdes = sc8180x_qmp_pcie_serdes_tbl, -- GitLab From 813a2398907c2f8b94afc5d5f80e0f581b585a45 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Fri, 31 Mar 2023 18:12:50 +0300 Subject: [PATCH 2450/5631] phy: qcom-qmp-pcie: drop sdm845_qhp_pcie_rx_tbl The SDM845 QHP PHY doesn't have designated RX region. Corresponding RX table is empty, so we can drop it completely. Signed-off-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230331151250.4049-2-dmitry.baryshkov@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index f378c1ebefd7..df505279edfd 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -725,9 +725,6 @@ static const struct qmp_phy_init_tbl sdm845_qhp_pcie_tx_tbl[] = { QMP_PHY_INIT_CFG(PCIE_GEN3_QHP_L0_RSM_START, 0x01), }; -static const struct qmp_phy_init_tbl sdm845_qhp_pcie_rx_tbl[] = { -}; - static const struct qmp_phy_init_tbl sdm845_qhp_pcie_pcs_tbl[] = { QMP_PHY_INIT_CFG(PCIE_GEN3_QHP_PHY_POWER_STATE_CONFIG, 0x3f), QMP_PHY_INIT_CFG(PCIE_GEN3_QHP_PHY_PCS_TX_RX_CONFIG, 0x50), @@ -2212,8 +2209,6 @@ static const struct qmp_phy_cfg sdm845_qhp_pciephy_cfg = { .serdes_num = ARRAY_SIZE(sdm845_qhp_pcie_serdes_tbl), .tx = sdm845_qhp_pcie_tx_tbl, .tx_num = ARRAY_SIZE(sdm845_qhp_pcie_tx_tbl), - .rx = sdm845_qhp_pcie_rx_tbl, - .rx_num = ARRAY_SIZE(sdm845_qhp_pcie_rx_tbl), .pcs = sdm845_qhp_pcie_pcs_tbl, .pcs_num = ARRAY_SIZE(sdm845_qhp_pcie_pcs_tbl), }, -- GitLab From d469d9448a0f1a33c175d3280b1542fa0158ad7a Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 10 Apr 2023 09:58:11 -0600 Subject: [PATCH 2451/5631] bus: mhi: host: Remove duplicate ee check for syserr If we detect a system error via intvec, we only process the syserr if the current ee is different than the last observed ee. The reason for this check is to prevent bhie from running multiple times, but with the single queue handling syserr, that is not possible. The check can cause an issue with device recovery. If PBL loads a bad SBL via BHI, but that SBL hangs before notifying the host of an ee change, then issuing soc_reset to crash the device and retry (after supplying a fixed SBL) will not recover the device as the host will observe a PBL->PBL transition and not process the syserr. The device will be stuck until either the driver is reloaded, or the host is rebooted. Instead, remove the check so that we can attempt to recover the device. Fixes: ef2126c4e2ea ("bus: mhi: core: Process execution environment changes serially") Cc: stable@vger.kernel.org Signed-off-by: Jeffrey Hugo Reviewed-by: Carl Vanderlip Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1681142292-27571-2-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/mhi/host/main.c b/drivers/bus/mhi/host/main.c index c7eb7b8be9d6..74a75439c713 100644 --- a/drivers/bus/mhi/host/main.c +++ b/drivers/bus/mhi/host/main.c @@ -503,7 +503,7 @@ irqreturn_t mhi_intvec_threaded_handler(int irq_number, void *priv) } write_unlock_irq(&mhi_cntrl->pm_lock); - if (pm_state != MHI_PM_SYS_ERR_DETECT || ee == mhi_cntrl->ee) + if (pm_state != MHI_PM_SYS_ERR_DETECT) goto exit_intvec; switch (ee) { -- GitLab From 1d1493bdc25f498468a606a4ece947d155cfa3a9 Mon Sep 17 00:00:00 2001 From: Jeffrey Hugo Date: Mon, 10 Apr 2023 09:58:12 -0600 Subject: [PATCH 2452/5631] bus: mhi: host: Use mhi_tryset_pm_state() for setting fw error state If firmware loading fails, the controller's pm_state is updated to MHI_PM_FW_DL_ERR unconditionally. This can corrupt the pm_state as the update is not done under the proper lock, and also does not validate the state transition. The firmware loading can fail due to a detected syserr, but if MHI_PM_FW_DL_ERR is unconditionally set as the pm_state, the handling of the syserr can break when it attempts to transition from syserr detect, to syserr process. By grabbing the lock, we ensure we don't race with some other pm_state update. By using mhi_try_set_pm_state(), we check that the transition to MHI_PM_FW_DL_ERR is valid via the state machine logic. If it is not valid, then some other transition is occurring like syserr processing, and we assume that will resolve the firmware loading error. Fixes: 12e050c77be0 ("bus: mhi: core: Move to an error state on any firmware load failure") Cc: stable@vger.kernel.org Signed-off-by: Jeffrey Hugo Reviewed-by: Carl Vanderlip Reviewed-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/1681142292-27571-3-git-send-email-quic_jhugo@quicinc.com Signed-off-by: Manivannan Sadhasivam --- drivers/bus/mhi/host/boot.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c index 1c69feee1703..d2a19b07ccb8 100644 --- a/drivers/bus/mhi/host/boot.c +++ b/drivers/bus/mhi/host/boot.c @@ -391,6 +391,7 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl) { const struct firmware *firmware = NULL; struct device *dev = &mhi_cntrl->mhi_dev->dev; + enum mhi_pm_state new_state; const char *fw_name; void *buf; dma_addr_t dma_addr; @@ -508,14 +509,18 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl) } error_fw_load: - mhi_cntrl->pm_state = MHI_PM_FW_DL_ERR; - wake_up_all(&mhi_cntrl->state_event); + write_lock_irq(&mhi_cntrl->pm_lock); + new_state = mhi_tryset_pm_state(mhi_cntrl, MHI_PM_FW_DL_ERR); + write_unlock_irq(&mhi_cntrl->pm_lock); + if (new_state == MHI_PM_FW_DL_ERR) + wake_up_all(&mhi_cntrl->state_event); } int mhi_download_amss_image(struct mhi_controller *mhi_cntrl) { struct image_info *image_info = mhi_cntrl->fbc_image; struct device *dev = &mhi_cntrl->mhi_dev->dev; + enum mhi_pm_state new_state; int ret; if (!image_info) @@ -526,8 +531,11 @@ int mhi_download_amss_image(struct mhi_controller *mhi_cntrl) &image_info->mhi_buf[image_info->entries - 1]); if (ret) { dev_err(dev, "MHI did not load AMSS, ret:%d\n", ret); - mhi_cntrl->pm_state = MHI_PM_FW_DL_ERR; - wake_up_all(&mhi_cntrl->state_event); + write_lock_irq(&mhi_cntrl->pm_lock); + new_state = mhi_tryset_pm_state(mhi_cntrl, MHI_PM_FW_DL_ERR); + write_unlock_irq(&mhi_cntrl->pm_lock); + if (new_state == MHI_PM_FW_DL_ERR) + wake_up_all(&mhi_cntrl->state_event); } return ret; -- GitLab From a301528f79d1ec27cd34122d655e0200a950f960 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:52 -0700 Subject: [PATCH 2453/5631] clk: axi-clkgen: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-1-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-axi-clkgen.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/clk-axi-clkgen.c b/drivers/clk/clk-axi-clkgen.c index 671bee55ceb3..a04a3d38c76e 100644 --- a/drivers/clk/clk-axi-clkgen.c +++ b/drivers/clk/clk-axi-clkgen.c @@ -553,13 +553,8 @@ static int axi_clkgen_probe(struct platform_device *pdev) if (ret) return ret; - return of_clk_add_hw_provider(pdev->dev.of_node, of_clk_hw_simple_get, - &axi_clkgen->clk_hw); -} - -static void axi_clkgen_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); + return devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_simple_get, + &axi_clkgen->clk_hw); } static const struct of_device_id axi_clkgen_ids[] = { @@ -581,7 +576,6 @@ static struct platform_driver axi_clkgen_driver = { .of_match_table = axi_clkgen_ids, }, .probe = axi_clkgen_probe, - .remove_new = axi_clkgen_remove, }; module_platform_driver(axi_clkgen_driver); -- GitLab From f042ebcfccaa9761b4f36ffa33b0663d6f6eaaa4 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:53 -0700 Subject: [PATCH 2454/5631] clk: axm5516: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-2-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-axm5516.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/clk/clk-axm5516.c b/drivers/clk/clk-axm5516.c index 1dff2017ad9d..1afcfdf2e6f9 100644 --- a/drivers/clk/clk-axm5516.c +++ b/drivers/clk/clk-axm5516.c @@ -569,17 +569,11 @@ static int axmclk_probe(struct platform_device *pdev) return ret; } - return of_clk_add_hw_provider(dev->of_node, of_clk_axmclk_get, NULL); -} - -static void axmclk_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); + return devm_of_clk_add_hw_provider(dev, of_clk_axmclk_get, NULL); } static struct platform_driver axmclk_driver = { .probe = axmclk_probe, - .remove_new = axmclk_remove, .driver = { .name = "clk-axm5516", .of_match_table = axmclk_match_table, -- GitLab From 7bed704f803cabfd7d5c3e92b0e8ecd29eefe5a3 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:54 -0700 Subject: [PATCH 2455/5631] clk: axs10x: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-3-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/axs10x/pll_clock.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/axs10x/pll_clock.c b/drivers/clk/axs10x/pll_clock.c index dbbfa12e530d..242bf5d75bab 100644 --- a/drivers/clk/axs10x/pll_clock.c +++ b/drivers/clk/axs10x/pll_clock.c @@ -253,13 +253,8 @@ static int axs10x_pll_clk_probe(struct platform_device *pdev) return ret; } - return of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, - &pll_clk->hw); -} - -static void axs10x_pll_clk_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); + return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, + &pll_clk->hw); } static void __init of_axs10x_pll_clk_setup(struct device_node *node) @@ -331,7 +326,6 @@ static struct platform_driver axs10x_pll_clk_driver = { .of_match_table = axs10x_pll_clk_id, }, .probe = axs10x_pll_clk_probe, - .remove_new = axs10x_pll_clk_remove, }; builtin_platform_driver(axs10x_pll_clk_driver); -- GitLab From c2e59c7f27c8a001eba725ba48e6d647d7b1f3d0 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:55 -0700 Subject: [PATCH 2456/5631] clk: cdce706: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-4-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-cdce706.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/clk/clk-cdce706.c b/drivers/clk/clk-cdce706.c index 1449d0537674..d8bee8180a6b 100644 --- a/drivers/clk/clk-cdce706.c +++ b/drivers/clk/clk-cdce706.c @@ -661,16 +661,10 @@ static int cdce706_probe(struct i2c_client *client) ret = cdce706_register_clkouts(cdce); if (ret < 0) return ret; - return of_clk_add_hw_provider(client->dev.of_node, of_clk_cdce_get, - cdce); + return devm_of_clk_add_hw_provider(&client->dev, of_clk_cdce_get, + cdce); } -static void cdce706_remove(struct i2c_client *client) -{ - of_clk_del_provider(client->dev.of_node); -} - - #ifdef CONFIG_OF static const struct of_device_id cdce706_dt_match[] = { { .compatible = "ti,cdce706" }, @@ -691,7 +685,6 @@ static struct i2c_driver cdce706_i2c_driver = { .of_match_table = of_match_ptr(cdce706_dt_match), }, .probe_new = cdce706_probe, - .remove = cdce706_remove, .id_table = cdce706_id, }; module_i2c_driver(cdce706_i2c_driver); -- GitLab From 56d144d0344aaa3810e2d18229f315480fc72a89 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:56 -0700 Subject: [PATCH 2457/5631] clk: hsdk-pll: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-5-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-hsdk-pll.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/clk-hsdk-pll.c b/drivers/clk/clk-hsdk-pll.c index 766e139972fe..33b48ea5ea3d 100644 --- a/drivers/clk/clk-hsdk-pll.c +++ b/drivers/clk/clk-hsdk-pll.c @@ -346,13 +346,8 @@ static int hsdk_pll_clk_probe(struct platform_device *pdev) return ret; } - return of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, - &pll_clk->hw); -} - -static void hsdk_pll_clk_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); + return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, + &pll_clk->hw); } static void __init of_hsdk_pll_clk_setup(struct device_node *node) @@ -431,6 +426,5 @@ static struct platform_driver hsdk_pll_clk_driver = { .of_match_table = hsdk_pll_clk_id, }, .probe = hsdk_pll_clk_probe, - .remove_new = hsdk_pll_clk_remove, }; builtin_platform_driver(hsdk_pll_clk_driver); -- GitLab From 56fc9a343a2001bf64a7370b3e3cf2256c60af3e Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:57 -0700 Subject: [PATCH 2458/5631] clk: lmk04832: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-6-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-lmk04832.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/clk/clk-lmk04832.c b/drivers/clk/clk-lmk04832.c index 57485356de4c..afdfee3b365f 100644 --- a/drivers/clk/clk-lmk04832.c +++ b/drivers/clk/clk-lmk04832.c @@ -1522,8 +1522,8 @@ static int lmk04832_probe(struct spi_device *spi) } lmk->clk_data->num = info->num_channels; - ret = of_clk_add_hw_provider(lmk->dev->of_node, of_clk_hw_onecell_get, - lmk->clk_data); + ret = devm_of_clk_add_hw_provider(lmk->dev, of_clk_hw_onecell_get, + lmk->clk_data); if (ret) { dev_err(lmk->dev, "failed to add provider (%d)\n", ret); goto err_disable_vco; @@ -1547,7 +1547,6 @@ static void lmk04832_remove(struct spi_device *spi) struct lmk04832 *lmk = spi_get_drvdata(spi); clk_disable_unprepare(lmk->oscin); - of_clk_del_provider(spi->dev.of_node); } static const struct spi_device_id lmk04832_id[] = { -- GitLab From 40882deb83c29d8df4470d4e5e7f137b6acf7ad1 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 13 Mar 2023 18:45:53 -0400 Subject: [PATCH 2459/5631] NFSv4.1: Always send a RECLAIM_COMPLETE after establishing lease The spec requires that we always at least send a RECLAIM_COMPLETE when we're done establishing the lease and recovering any state. Fixes: fce5c838e133 ("nfs41: RECLAIM_COMPLETE functionality") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4state.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 2a0ca5c7f082..660ccfaf463e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -67,6 +67,8 @@ #define OPENOWNER_POOL_SIZE 8 +static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp); + const nfs4_stateid zero_stateid = { { .data = { 0 } }, .type = NFS4_SPECIAL_STATEID_TYPE, @@ -330,6 +332,8 @@ int nfs41_init_clientid(struct nfs_client *clp, const struct cred *cred) status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)) + nfs4_state_start_reclaim_reboot(clp); nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: -- GitLab From a7f3b6757acde808e1558ffa23b4a80f6831a081 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:59 -0700 Subject: [PATCH 2460/5631] clk: si514: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-8-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-si514.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/clk-si514.c b/drivers/clk/clk-si514.c index c028fa103bed..cabdd8e8f4db 100644 --- a/drivers/clk/clk-si514.c +++ b/drivers/clk/clk-si514.c @@ -360,8 +360,8 @@ static int si514_probe(struct i2c_client *client) dev_err(&client->dev, "clock registration failed\n"); return err; } - err = of_clk_add_hw_provider(client->dev.of_node, of_clk_hw_simple_get, - &data->hw); + err = devm_of_clk_add_hw_provider(&client->dev, of_clk_hw_simple_get, + &data->hw); if (err) { dev_err(&client->dev, "unable to add clk provider\n"); return err; @@ -370,11 +370,6 @@ static int si514_probe(struct i2c_client *client) return 0; } -static void si514_remove(struct i2c_client *client) -{ - of_clk_del_provider(client->dev.of_node); -} - static const struct i2c_device_id si514_id[] = { { "si514", 0 }, { } @@ -393,7 +388,6 @@ static struct i2c_driver si514_driver = { .of_match_table = clk_si514_of_match, }, .probe_new = si514_probe, - .remove = si514_remove, .id_table = si514_id, }; module_i2c_driver(si514_driver); -- GitLab From bda73391c8efea9de9d69503c9ab5a1ecabb1786 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:45:00 -0700 Subject: [PATCH 2461/5631] clk: si570: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-9-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-si570.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/clk/clk-si570.c b/drivers/clk/clk-si570.c index 0a6d70c49726..0b834e9efb4b 100644 --- a/drivers/clk/clk-si570.c +++ b/drivers/clk/clk-si570.c @@ -474,8 +474,8 @@ static int si570_probe(struct i2c_client *client) dev_err(&client->dev, "clock registration failed\n"); return err; } - err = of_clk_add_hw_provider(client->dev.of_node, of_clk_hw_simple_get, - &data->hw); + err = devm_of_clk_add_hw_provider(&client->dev, of_clk_hw_simple_get, + &data->hw); if (err) { dev_err(&client->dev, "unable to add clk provider\n"); return err; @@ -485,10 +485,8 @@ static int si570_probe(struct i2c_client *client) if (!of_property_read_u32(client->dev.of_node, "clock-frequency", &initial_fout)) { err = clk_set_rate(data->hw.clk, initial_fout); - if (err) { - of_clk_del_provider(client->dev.of_node); + if (err) return err; - } } /* Display a message indicating that we've successfully registered */ @@ -498,11 +496,6 @@ static int si570_probe(struct i2c_client *client) return 0; } -static void si570_remove(struct i2c_client *client) -{ - of_clk_del_provider(client->dev.of_node); -} - static const struct of_device_id clk_si570_of_match[] = { { .compatible = "silabs,si570" }, { .compatible = "silabs,si571" }, @@ -518,7 +511,6 @@ static struct i2c_driver si570_driver = { .of_match_table = clk_si570_of_match, }, .probe_new = si570_probe, - .remove = si570_remove, .id_table = si570_id, }; module_i2c_driver(si570_driver); -- GitLab From 361dde3c283324b71494dec4f51e829054d0822f Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:45:01 -0700 Subject: [PATCH 2462/5631] clk: si5351: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-10-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/clk-si5351.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/clk-si5351.c b/drivers/clk/clk-si5351.c index 9e939c98a455..4fcf7056717e 100644 --- a/drivers/clk/clk-si5351.c +++ b/drivers/clk/clk-si5351.c @@ -1641,8 +1641,8 @@ static int si5351_i2c_probe(struct i2c_client *client) } } - ret = of_clk_add_hw_provider(client->dev.of_node, si53351_of_clk_get, - drvdata); + ret = devm_of_clk_add_hw_provider(&client->dev, si53351_of_clk_get, + drvdata); if (ret) { dev_err(&client->dev, "unable to add clk provider\n"); return ret; @@ -1651,18 +1651,12 @@ static int si5351_i2c_probe(struct i2c_client *client) return 0; } -static void si5351_i2c_remove(struct i2c_client *client) -{ - of_clk_del_provider(client->dev.of_node); -} - static struct i2c_driver si5351_driver = { .driver = { .name = "si5351", .of_match_table = of_match_ptr(si5351_dt_ids), }, .probe_new = si5351_i2c_probe, - .remove = si5351_i2c_remove, .id_table = si5351_i2c_ids, }; module_i2c_driver(si5351_driver); -- GitLab From c0e19528439db9051c7847f1c91f22bd1e87e0ce Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:45:02 -0700 Subject: [PATCH 2463/5631] clk: uniphier: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230410014502.27929-11-lars@metafoo.de Signed-off-by: Stephen Boyd --- drivers/clk/uniphier/clk-uniphier-core.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c index 92f4ddc593db..a61213311d6c 100644 --- a/drivers/clk/uniphier/clk-uniphier-core.c +++ b/drivers/clk/uniphier/clk-uniphier-core.c @@ -87,13 +87,8 @@ static int uniphier_clk_probe(struct platform_device *pdev) hw_data->hws[p->idx] = hw; } - return of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get, - hw_data); -} - -static void uniphier_clk_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); + return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, + hw_data); } static const struct of_device_id uniphier_clk_match[] = { @@ -218,7 +213,6 @@ static const struct of_device_id uniphier_clk_match[] = { static struct platform_driver uniphier_clk_driver = { .probe = uniphier_clk_probe, - .remove_new = uniphier_clk_remove, .driver = { .name = "uniphier-clk", .of_match_table = uniphier_clk_match, -- GitLab From fb8b9d23f15f1440671d0127f7ad68d679fd29a3 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 6 Apr 2023 21:57:47 +0100 Subject: [PATCH 2464/5631] clk: sifive: make SiFive clk drivers depend on ARCH_ symbols As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the use of such symbols on other architectures, convert the SiFive clk drivers to use the new symbol. Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230406-groovy-trustable-15853ac0a130@spud Signed-off-by: Stephen Boyd --- drivers/clk/sifive/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/sifive/Kconfig b/drivers/clk/sifive/Kconfig index b7fde0aadfcb..2322f634a910 100644 --- a/drivers/clk/sifive/Kconfig +++ b/drivers/clk/sifive/Kconfig @@ -2,8 +2,8 @@ menuconfig CLK_SIFIVE bool "SiFive SoC driver support" - depends on SOC_SIFIVE || COMPILE_TEST - default SOC_SIFIVE + depends on ARCH_SIFIVE || COMPILE_TEST + default ARCH_SIFIVE help SoC drivers for SiFive Linux-capable SoCs. @@ -11,7 +11,7 @@ if CLK_SIFIVE config CLK_SIFIVE_PRCI bool "PRCI driver for SiFive SoCs" - default SOC_SIFIVE + default ARCH_SIFIVE select RESET_CONTROLLER select RESET_SIMPLE select CLK_ANALOGBITS_WRPLL_CLN28HPC -- GitLab From 0c1228486befa3d6e943488406f1e3c05679721b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 22:52:07 -0700 Subject: [PATCH 2465/5631] perf lock contention: Support pre-5.14 kernels 'struct rq's member '__lock' was renamed from 'lock' in 5.14. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230408055208.1283832-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 23f6e63544ed..8911e2a077d8 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -418,6 +418,14 @@ int contention_end(u64 *ctx) extern struct rq runqueues __ksym; +struct rq__old { + raw_spinlock_t lock; +} __attribute__((preserve_access_index)); + +struct rq__new { + raw_spinlock_t __lock; +} __attribute__((preserve_access_index)); + SEC("raw_tp/bpf_test_finish") int BPF_PROG(collect_lock_syms) { @@ -426,11 +434,16 @@ int BPF_PROG(collect_lock_syms) for (int i = 0; i < MAX_CPUS; i++) { struct rq *rq = bpf_per_cpu_ptr(&runqueues, i); + struct rq__new *rq_new = (void *)rq; + struct rq__old *rq_old = (void *)rq; if (rq == NULL) break; - lock_addr = (__u64)&rq->__lock; + if (bpf_core_field_exists(rq_new->__lock)) + lock_addr = (__u64)&rq_new->__lock; + else + lock_addr = (__u64)&rq_old->lock; lock_flag = LOCK_CLASS_RQLOCK; bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); } -- GitLab From 3dcb652a3afc4b32cf8d3c1605c8cf22ad174a07 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Fri, 24 Feb 2023 18:11:49 +0900 Subject: [PATCH 2466/5631] rust: Add SPDX headers to alloc::vec::{spec_extend, set_len_on_drop} Add the missing SPDX headers to these modules, which were just imported from the Rust stdlib. Doing this in a separate commit makes it easier to audit that the files have not been modified in the original import. See the preceding two commits for attribution and licensing details. Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-vec-v1-3-733b5b5a57c5@asahilina.net [ Reworded for typo. ] Signed-off-by: Miguel Ojeda --- rust/alloc/vec/set_len_on_drop.rs | 2 ++ rust/alloc/vec/spec_extend.rs | 2 ++ 2 files changed, 4 insertions(+) diff --git a/rust/alloc/vec/set_len_on_drop.rs b/rust/alloc/vec/set_len_on_drop.rs index 8b66bc812129..448bf5076a0b 100644 --- a/rust/alloc/vec/set_len_on_drop.rs +++ b/rust/alloc/vec/set_len_on_drop.rs @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + // Set the length of the vec when the `SetLenOnDrop` value goes out of scope. // // The idea is: The length field in SetLenOnDrop is a local variable diff --git a/rust/alloc/vec/spec_extend.rs b/rust/alloc/vec/spec_extend.rs index 506ee0ecfa27..7bb3abb7ee71 100644 --- a/rust/alloc/vec/spec_extend.rs +++ b/rust/alloc/vec/spec_extend.rs @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + use crate::alloc::Allocator; use core::iter::TrustedLen; use core::ptr::{self}; -- GitLab From 318c3cc8e107c2b36108132057ca90d0d56d1bd9 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 24 Feb 2023 18:11:50 +0900 Subject: [PATCH 2467/5631] rust: alloc: vec: Add some try_* methods we need Add some missing fallible methods that we need. They are all marked as: #[stable(feature = "kernel", since = "1.0.0")] for easy identification. Lina: Extracted from commit 487d7578bd03 ("rust: alloc: add some `try_*` methods we need") in rust-for-linux/rust. Signed-off-by: Miguel Ojeda Signed-off-by: Asahi Lina Link: https://github.com/Rust-for-Linux/linux/commit/487d7578bd03 Link: https://lore.kernel.org/r/20230224-rust-vec-v1-4-733b5b5a57c5@asahilina.net [ Match the non-fallible methods from version 1.62.0, since those in commit 487d7578bd03 were written for 1.54.0-beta.1. ] Signed-off-by: Miguel Ojeda --- rust/alloc/vec/mod.rs | 137 +++++++++++++++++++++++++++++++++- rust/alloc/vec/spec_extend.rs | 85 +++++++++++++++++++++ 2 files changed, 219 insertions(+), 3 deletions(-) diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs index f77c7368d534..fe4fff5064bc 100644 --- a/rust/alloc/vec/mod.rs +++ b/rust/alloc/vec/mod.rs @@ -122,10 +122,8 @@ use self::spec_from_elem::SpecFromElem; #[cfg(not(no_global_oom_handling))] mod spec_from_elem; -#[cfg(not(no_global_oom_handling))] use self::set_len_on_drop::SetLenOnDrop; -#[cfg(not(no_global_oom_handling))] mod set_len_on_drop; #[cfg(not(no_global_oom_handling))] @@ -149,7 +147,8 @@ mod spec_from_iter; #[cfg(not(no_global_oom_handling))] use self::spec_extend::SpecExtend; -#[cfg(not(no_global_oom_handling))] +use self::spec_extend::TrySpecExtend; + mod spec_extend; /// A contiguous growable array type, written as `Vec`, short for 'vector'. @@ -1919,6 +1918,17 @@ impl Vec { self.len += count; } + /// Tries to append elements to `self` from other buffer. + #[inline] + unsafe fn try_append_elements(&mut self, other: *const [T]) -> Result<(), TryReserveError> { + let count = unsafe { (*other).len() }; + self.try_reserve(count)?; + let len = self.len(); + unsafe { ptr::copy_nonoverlapping(other as *const T, self.as_mut_ptr().add(len), count) }; + self.len += count; + Ok(()) + } + /// Removes the specified range from the vector in bulk, returning all /// removed elements as an iterator. If the iterator is dropped before /// being fully consumed, it drops the remaining removed elements. @@ -2340,6 +2350,45 @@ impl Vec { } } + /// Tries to resize the `Vec` in-place so that `len` is equal to `new_len`. + /// + /// If `new_len` is greater than `len`, the `Vec` is extended by the + /// difference, with each additional slot filled with `value`. + /// If `new_len` is less than `len`, the `Vec` is simply truncated. + /// + /// This method requires `T` to implement [`Clone`], + /// in order to be able to clone the passed value. + /// If you need more flexibility (or want to rely on [`Default`] instead of + /// [`Clone`]), use [`Vec::resize_with`]. + /// If you only need to resize to a smaller size, use [`Vec::truncate`]. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec!["hello"]; + /// vec.try_resize(3, "world").unwrap(); + /// assert_eq!(vec, ["hello", "world", "world"]); + /// + /// let mut vec = vec![1, 2, 3, 4]; + /// vec.try_resize(2, 0).unwrap(); + /// assert_eq!(vec, [1, 2]); + /// + /// let mut vec = vec![42]; + /// let result = vec.try_resize(usize::MAX, 0); + /// assert!(result.is_err()); + /// ``` + #[stable(feature = "kernel", since = "1.0.0")] + pub fn try_resize(&mut self, new_len: usize, value: T) -> Result<(), TryReserveError> { + let len = self.len(); + + if new_len > len { + self.try_extend_with(new_len - len, ExtendElement(value)) + } else { + self.truncate(new_len); + Ok(()) + } + } + /// Clones and appends all elements in a slice to the `Vec`. /// /// Iterates over the slice `other`, clones each element, and then appends @@ -2365,6 +2414,30 @@ impl Vec { self.spec_extend(other.iter()) } + /// Tries to clone and append all elements in a slice to the `Vec`. + /// + /// Iterates over the slice `other`, clones each element, and then appends + /// it to this `Vec`. The `other` slice is traversed in-order. + /// + /// Note that this function is same as [`extend`] except that it is + /// specialized to work with slices instead. If and when Rust gets + /// specialization this function will likely be deprecated (but still + /// available). + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1]; + /// vec.try_extend_from_slice(&[2, 3, 4]).unwrap(); + /// assert_eq!(vec, [1, 2, 3, 4]); + /// ``` + /// + /// [`extend`]: Vec::extend + #[stable(feature = "kernel", since = "1.0.0")] + pub fn try_extend_from_slice(&mut self, other: &[T]) -> Result<(), TryReserveError> { + self.try_spec_extend(other.iter()) + } + /// Copies elements from `src` range to the end of the vector. /// /// # Panics @@ -2504,6 +2577,36 @@ impl Vec { // len set by scope guard } } + + /// Try to extend the vector by `n` values, using the given generator. + fn try_extend_with>(&mut self, n: usize, mut value: E) -> Result<(), TryReserveError> { + self.try_reserve(n)?; + + unsafe { + let mut ptr = self.as_mut_ptr().add(self.len()); + // Use SetLenOnDrop to work around bug where compiler + // might not realize the store through `ptr` through self.set_len() + // don't alias. + let mut local_len = SetLenOnDrop::new(&mut self.len); + + // Write all elements except the last one + for _ in 1..n { + ptr::write(ptr, value.next()); + ptr = ptr.offset(1); + // Increment the length in every step in case next() panics + local_len.increment_len(1); + } + + if n > 0 { + // We can write the last element directly without cloning needlessly + ptr::write(ptr, value.last()); + local_len.increment_len(1); + } + + // len set by scope guard + Ok(()) + } + } } impl Vec { @@ -2838,6 +2941,34 @@ impl Vec { } } + // leaf method to which various SpecFrom/SpecExtend implementations delegate when + // they have no further optimizations to apply + fn try_extend_desugared>(&mut self, mut iterator: I) -> Result<(), TryReserveError> { + // This is the case for a general iterator. + // + // This function should be the moral equivalent of: + // + // for item in iterator { + // self.push(item); + // } + while let Some(element) = iterator.next() { + let len = self.len(); + if len == self.capacity() { + let (lower, _) = iterator.size_hint(); + self.try_reserve(lower.saturating_add(1))?; + } + unsafe { + ptr::write(self.as_mut_ptr().add(len), element); + // Since next() executes user code which can panic we have to bump the length + // after each step. + // NB can't overflow since we would have had to alloc the address space + self.set_len(len + 1); + } + } + + Ok(()) + } + /// Creates a splicing iterator that replaces the specified range in the vector /// with the given `replace_with` iterator and yields the removed items. /// `replace_with` does not need to be the same length as `range`. diff --git a/rust/alloc/vec/spec_extend.rs b/rust/alloc/vec/spec_extend.rs index 7bb3abb7ee71..5ce2d00991bc 100644 --- a/rust/alloc/vec/spec_extend.rs +++ b/rust/alloc/vec/spec_extend.rs @@ -1,6 +1,7 @@ // SPDX-License-Identifier: Apache-2.0 OR MIT use crate::alloc::Allocator; +use crate::collections::{TryReserveError, TryReserveErrorKind}; use core::iter::TrustedLen; use core::ptr::{self}; use core::slice::{self}; @@ -8,10 +9,17 @@ use core::slice::{self}; use super::{IntoIter, SetLenOnDrop, Vec}; // Specialization trait used for Vec::extend +#[cfg(not(no_global_oom_handling))] pub(super) trait SpecExtend { fn spec_extend(&mut self, iter: I); } +// Specialization trait used for Vec::try_extend +pub(super) trait TrySpecExtend { + fn try_spec_extend(&mut self, iter: I) -> Result<(), TryReserveError>; +} + +#[cfg(not(no_global_oom_handling))] impl SpecExtend for Vec where I: Iterator, @@ -21,6 +29,16 @@ where } } +impl TrySpecExtend for Vec +where + I: Iterator, +{ + default fn try_spec_extend(&mut self, iter: I) -> Result<(), TryReserveError> { + self.try_extend_desugared(iter) + } +} + +#[cfg(not(no_global_oom_handling))] impl SpecExtend for Vec where I: TrustedLen, @@ -59,6 +77,41 @@ where } } +impl TrySpecExtend for Vec +where + I: TrustedLen, +{ + default fn try_spec_extend(&mut self, iterator: I) -> Result<(), TryReserveError> { + // This is the case for a TrustedLen iterator. + let (low, high) = iterator.size_hint(); + if let Some(additional) = high { + debug_assert_eq!( + low, + additional, + "TrustedLen iterator's size hint is not exact: {:?}", + (low, high) + ); + self.try_reserve(additional)?; + unsafe { + let mut ptr = self.as_mut_ptr().add(self.len()); + let mut local_len = SetLenOnDrop::new(&mut self.len); + iterator.for_each(move |element| { + ptr::write(ptr, element); + ptr = ptr.offset(1); + // Since the loop executes user code which can panic we have to bump the pointer + // after each step. + // NB can't overflow since we would have had to alloc the address space + local_len.increment_len(1); + }); + } + Ok(()) + } else { + Err(TryReserveErrorKind::CapacityOverflow.into()) + } + } +} + +#[cfg(not(no_global_oom_handling))] impl SpecExtend> for Vec { fn spec_extend(&mut self, mut iterator: IntoIter) { unsafe { @@ -68,6 +121,17 @@ impl SpecExtend> for Vec { } } +impl TrySpecExtend> for Vec { + fn try_spec_extend(&mut self, mut iterator: IntoIter) -> Result<(), TryReserveError> { + unsafe { + self.try_append_elements(iterator.as_slice() as _)?; + } + iterator.forget_remaining_elements(); + Ok(()) + } +} + +#[cfg(not(no_global_oom_handling))] impl<'a, T: 'a, I, A: Allocator + 'a> SpecExtend<&'a T, I> for Vec where I: Iterator, @@ -78,6 +142,17 @@ where } } +impl<'a, T: 'a, I, A: Allocator + 'a> TrySpecExtend<&'a T, I> for Vec +where + I: Iterator, + T: Clone, +{ + default fn try_spec_extend(&mut self, iterator: I) -> Result<(), TryReserveError> { + self.try_spec_extend(iterator.cloned()) + } +} + +#[cfg(not(no_global_oom_handling))] impl<'a, T: 'a, A: Allocator + 'a> SpecExtend<&'a T, slice::Iter<'a, T>> for Vec where T: Copy, @@ -87,3 +162,13 @@ where unsafe { self.append_elements(slice) }; } } + +impl<'a, T: 'a, A: Allocator + 'a> TrySpecExtend<&'a T, slice::Iter<'a, T>> for Vec +where + T: Copy, +{ + fn try_spec_extend(&mut self, iterator: slice::Iter<'a, T>) -> Result<(), TryReserveError> { + let slice = iterator.as_slice(); + unsafe { self.try_append_elements(slice) } + } +} -- GitLab From 39867fec2855cf37e5542dc6a972bce8ee191a9c Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Thu, 23 Mar 2023 21:35:10 +0900 Subject: [PATCH 2468/5631] rust: macros: Allow specifying multiple module aliases Modules can (and usually do) have multiple alias tags, in order to specify multiple possible device matches for autoloading. Allow this by changing the alias ModuleInfo field to an Option>. Note: For normal device IDs this is autogenerated by modpost (which is not properly integrated with Rust support yet), so it is useful to be able to manually add device match aliases for now, and should still be useful in the future for corner cases that modpost does not handle. This pulls in the expect_group() helper from the rfl/rust branch (with credit to authors). Co-developed-by: Miguel Ojeda Signed-off-by: Miguel Ojeda Co-developed-by: Finn Behrens Signed-off-by: Finn Behrens Co-developed-by: Sumera Priyadarsini Signed-off-by: Sumera Priyadarsini Reviewed-by: Vincenzo Palazzo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-macros-v2-1-7396e8b7018d@asahilina.net Signed-off-by: Miguel Ojeda --- rust/macros/helpers.rs | 10 +++++++++- rust/macros/module.rs | 30 +++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs index cf7ad950dc1e..b2bdd4d8c958 100644 --- a/rust/macros/helpers.rs +++ b/rust/macros/helpers.rs @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -use proc_macro::{token_stream, TokenTree}; +use proc_macro::{token_stream, Group, TokenTree}; pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option { if let Some(TokenTree::Ident(ident)) = it.next() { @@ -56,6 +56,14 @@ pub(crate) fn expect_string_ascii(it: &mut token_stream::IntoIter) -> String { string } +pub(crate) fn expect_group(it: &mut token_stream::IntoIter) -> Group { + if let TokenTree::Group(group) = it.next().expect("Reached end of token stream for Group") { + group + } else { + panic!("Expected Group"); + } +} + pub(crate) fn expect_end(it: &mut token_stream::IntoIter) { if it.next().is_some() { panic!("Expected end"); diff --git a/rust/macros/module.rs b/rust/macros/module.rs index a7e363c2b044..5e7ab83908a0 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -1,9 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 use crate::helpers::*; -use proc_macro::{token_stream, Literal, TokenStream, TokenTree}; +use proc_macro::{token_stream, Delimiter, Literal, TokenStream, TokenTree}; use std::fmt::Write; +fn expect_string_array(it: &mut token_stream::IntoIter) -> Vec { + let group = expect_group(it); + assert_eq!(group.delimiter(), Delimiter::Bracket); + let mut values = Vec::new(); + let mut it = group.stream().into_iter(); + + while let Some(val) = try_string(&mut it) { + assert!(val.is_ascii(), "Expected ASCII string"); + values.push(val); + match it.next() { + Some(TokenTree::Punct(punct)) => assert_eq!(punct.as_char(), ','), + None => break, + _ => panic!("Expected ',' or end of array"), + } + } + values +} + struct ModInfoBuilder<'a> { module: &'a str, counter: usize, @@ -78,7 +96,7 @@ struct ModuleInfo { name: String, author: Option, description: Option, - alias: Option, + alias: Option>, } impl ModuleInfo { @@ -112,7 +130,7 @@ impl ModuleInfo { "author" => info.author = Some(expect_string(it)), "description" => info.description = Some(expect_string(it)), "license" => info.license = expect_string_ascii(it), - "alias" => info.alias = Some(expect_string_ascii(it)), + "alias" => info.alias = Some(expect_string_array(it)), _ => panic!( "Unknown key \"{}\". Valid keys are: {:?}.", key, EXPECTED_KEYS @@ -163,8 +181,10 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { modinfo.emit("description", &description); } modinfo.emit("license", &info.license); - if let Some(alias) = info.alias { - modinfo.emit("alias", &alias); + if let Some(aliases) = info.alias { + for alias in aliases { + modinfo.emit("alias", &alias); + } } // Built-in modules also export the `file` modinfo string. -- GitLab From 1edd03378e50ff1071004c80cb878e4bad73a68f Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 19:01:11 +0900 Subject: [PATCH 2469/5631] rust: sync: arc: Implement Arc::downcast() This mirrors the standard library's alloc::sync::Arc::downcast(). Based on the Rust standard library implementation, ver 1.62.0, licensed under "Apache-2.0 OR MIT", from: https://github.com/rust-lang/rust/tree/1.62.0/library/alloc/src For copyright details, please see: https://github.com/rust-lang/rust/blob/1.62.0/COPYRIGHT Reviewed-by: Martin Rodriguez Reboredo Reviewed-by: Andreas Hindborg Reviewed-by: Vincenzo Palazzo Reviewed-by: Gary Guo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-arc-v2-1-5c97a865b276@asahilina.net [ Moved `mod std_vendor;` up. ] Signed-off-by: Miguel Ojeda --- rust/kernel/sync/arc.rs | 2 ++ rust/kernel/sync/arc/std_vendor.rs | 28 ++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) create mode 100644 rust/kernel/sync/arc/std_vendor.rs diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index a94e303217c6..4ab9b280cb3d 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -30,6 +30,8 @@ use core::{ ptr::NonNull, }; +mod std_vendor; + /// A reference-counted pointer to an instance of `T`. /// /// The reference count is incremented when new instances of [`Arc`] are created, and decremented diff --git a/rust/kernel/sync/arc/std_vendor.rs b/rust/kernel/sync/arc/std_vendor.rs new file mode 100644 index 000000000000..a66a0c2831b3 --- /dev/null +++ b/rust/kernel/sync/arc/std_vendor.rs @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! The contents of this file come from the Rust standard library, hosted in +//! the repository, licensed under +//! "Apache-2.0 OR MIT" and adapted for kernel use. For copyright details, +//! see . + +use crate::sync::{arc::ArcInner, Arc}; +use core::any::Any; + +impl Arc { + /// Attempt to downcast the `Arc` to a concrete type. + pub fn downcast(self) -> core::result::Result, Self> + where + T: Any + Send + Sync, + { + if (*self).is::() { + // SAFETY: We have just checked that the type is correct, so we can cast the pointer. + unsafe { + let ptr = self.ptr.cast::>(); + core::mem::forget(self); + Ok(Arc::from_inner(ptr)) + } + } else { + Err(self) + } + } +} -- GitLab From 3a8b8fc3174891c4c12f5766d82184a82d4b2e3e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 22:52:08 -0700 Subject: [PATCH 2470/5631] perf bpf filter: Support pre-5.16 kernels where 'mem_hops' isn't in 'union perf_mem_data_src' The 'mem_hops' bits were added in 5.16 with no prior equivalent. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230408055208.1283832-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/sample_filter.bpf.c | 28 ++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c index 57e3c67d6d37..cffe493af1ed 100644 --- a/tools/perf/util/bpf_skel/sample_filter.bpf.c +++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c @@ -24,6 +24,24 @@ struct perf_sample_data___new { __u64 sample_flags; } __attribute__((preserve_access_index)); +/* new kernel perf_mem_data_src definition */ +union perf_mem_data_src__new { + __u64 val; + struct { + __u64 mem_op:5, /* type of opcode */ + mem_lvl:14, /* memory hierarchy level */ + mem_snoop:5, /* snoop mode */ + mem_lock:2, /* lock instr */ + mem_dtlb:7, /* tlb access */ + mem_lvl_num:4, /* memory hierarchy level number */ + mem_remote:1, /* remote */ + mem_snoopx:2, /* snoop mode, ext */ + mem_blk:3, /* access blocked */ + mem_hops:3, /* hop level */ + mem_rsvd:18; + }; +}; + /* helper function to return the given perf sample data */ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, struct perf_bpf_filter_entry *entry) @@ -89,8 +107,14 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx, return kctx->data->data_src.mem_dtlb; if (entry->part == 7) return kctx->data->data_src.mem_blk; - if (entry->part == 8) - return kctx->data->data_src.mem_hops; + if (entry->part == 8) { + union perf_mem_data_src__new *data = (void *)&kctx->data->data_src; + + if (bpf_core_field_exists(data->mem_hops)) + return data->mem_hops; + + return 0; + } /* return the whole word */ return kctx->data->data_src.val; default: -- GitLab From fd9820d86d78e2dda3e709a645a7955a5370167c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 27 Mar 2023 14:53:10 +0200 Subject: [PATCH 2471/5631] dt-bindings: pinctrl: qcom,pmic-gpio: add compatible for pmm8654au-gpio Add a new compatible for the GPIO controller on the pm8654au PMIC. It has 12 pins with no holes. Signed-off-by: Bartosz Golaszewski Cc: Linus Walleij Acked-by: Rob Herring Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20230327125316.210812-13-brgl@bgdev.pl Signed-off-by: Linus Walleij --- Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml index 1096655961f7..36c6435cfd0a 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml @@ -58,6 +58,7 @@ properties: - qcom,pmk8350-gpio - qcom,pmk8550-gpio - qcom,pmm8155au-gpio + - qcom,pmm8654au-gpio - qcom,pmp8074-gpio - qcom,pmr735a-gpio - qcom,pmr735b-gpio @@ -439,6 +440,7 @@ $defs: - gpio1-gpio4 for pmk8350 - gpio1-gpio6 for pmk8550 - gpio1-gpio10 for pmm8155au + - gpio1-gpio12 for pmm8654au - gpio1-gpio12 for pmp8074 (holes on gpio1 and gpio12) - gpio1-gpio4 for pmr735a - gpio1-gpio4 for pmr735b -- GitLab From 0538897a01a15c4eff15ee7a06caf5a45480d043 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 27 Mar 2023 14:53:11 +0200 Subject: [PATCH 2472/5631] pinctrl: qcom: spmi-gpio: add support for pmm8654au-gpio Add support for the GPIO controller present on the pmm8654au PMIC. Signed-off-by: Bartosz Golaszewski Cc: Linus Walleij Reviewed-by: Konrad Dybcio Acked-by: Linus Walleij Link: https://lore.kernel.org/r/20230327125316.210812-14-brgl@bgdev.pl Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index ea3485344f06..0d94175b34f8 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1238,6 +1238,7 @@ static const struct of_device_id pmic_gpio_of_match[] = { { .compatible = "qcom,pmk8350-gpio", .data = (void *) 4 }, { .compatible = "qcom,pmk8550-gpio", .data = (void *) 6 }, { .compatible = "qcom,pmm8155au-gpio", .data = (void *) 10 }, + { .compatible = "qcom,pmm8654au-gpio", .data = (void *) 12 }, /* pmp8074 has 12 GPIOs with holes on 1 and 12 */ { .compatible = "qcom,pmp8074-gpio", .data = (void *) 12 }, { .compatible = "qcom,pmr735a-gpio", .data = (void *) 4 }, -- GitLab From 220368293a010d39fe41f130b99b666394034b08 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 22:44:54 -0700 Subject: [PATCH 2473/5631] perf test stat+csv_output: Write CSV output to a file Write the CSV output to a file, then sanity check this output. This avoids problems with debug/warning/error output corrupting the file format. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sumanth Korikkar Cc: Thomas Richter Link: https://lore.kernel.org/r/20230408054456.3001367-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat+csv_output.sh | 58 ++++++++++++++++------- 1 file changed, 42 insertions(+), 16 deletions(-) diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index 324fc9e6edd7..fb78b6251a4e 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -9,6 +9,20 @@ set -e skip_test=0 csv_sep=@ +stat_output=$(mktemp /tmp/__perf_test.stat_output.csv.XXXXX) + +cleanup() { + rm -f "${stat_output}" + + trap - EXIT TERM INT +} + +trap_cleanup() { + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + function commachecker() { local -i cnt=0 @@ -30,9 +44,11 @@ function commachecker() while read line do - # Check for lines beginning with Failed - x=${line:0:6} - [ "$x" = "Failed" ] && continue + # Ignore initial "started on" comment. + x=${line:0:1} + [ "$x" = "#" ] && continue + # Ignore initial blank line. + [ "$line" = "" ] && continue # Count the number of commas x=$(echo $line | tr -d -c $csv_sep) @@ -42,7 +58,7 @@ function commachecker() echo "wrong number of fields. expected $exp in $line" 1>&2 exit 1; } - done + done < "${stat_output}" return 0 } @@ -55,7 +71,8 @@ function ParanoidAndNotRoot() check_no_args() { echo -n "Checking CSV output: no args " - perf stat -x$csv_sep true 2>&1 | commachecker --no-args + perf stat -x$csv_sep -o "${stat_output}" true + commachecker --no-args echo "[Success]" } @@ -67,27 +84,29 @@ check_system_wide() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep -a true 2>&1 | commachecker --system-wide + perf stat -x$csv_sep -a -o "${stat_output}" true + commachecker --system-wide echo "[Success]" } check_system_wide_no_aggr() { - echo -n "Checking CSV output: system wide " + echo -n "Checking CSV output: system wide no aggregation " if ParanoidAndNotRoot 0 then echo "[Skip] paranoid and not root" return fi - echo -n "Checking CSV output: system wide no aggregation " - perf stat -x$csv_sep -A -a --no-merge true 2>&1 | commachecker --system-wide-no-aggr + perf stat -x$csv_sep -A -a --no-merge -o "${stat_output}" true + commachecker --system-wide-no-aggr echo "[Success]" } check_interval() { echo -n "Checking CSV output: interval " - perf stat -x$csv_sep -I 1000 true 2>&1 | commachecker --interval + perf stat -x$csv_sep -I 1000 -o "${stat_output}" true + commachecker --interval echo "[Success]" } @@ -95,7 +114,8 @@ check_interval() check_event() { echo -n "Checking CSV output: event " - perf stat -x$csv_sep -e cpu-clock true 2>&1 | commachecker --event + perf stat -x$csv_sep -e cpu-clock -o "${stat_output}" true + commachecker --event echo "[Success]" } @@ -107,7 +127,8 @@ check_per_core() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep --per-core -a true 2>&1 | commachecker --per-core + perf stat -x$csv_sep --per-core -a -o "${stat_output}" true + commachecker --per-core echo "[Success]" } @@ -119,7 +140,8 @@ check_per_thread() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep --per-thread -a true 2>&1 | commachecker --per-thread + perf stat -x$csv_sep --per-thread -a -o "${stat_output}" true + commachecker --per-thread echo "[Success]" } @@ -131,7 +153,8 @@ check_per_die() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep --per-die -a true 2>&1 | commachecker --per-die + perf stat -x$csv_sep --per-die -a -o "${stat_output}" true + commachecker --per-die echo "[Success]" } @@ -143,7 +166,8 @@ check_per_node() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep --per-node -a true 2>&1 | commachecker --per-node + perf stat -x$csv_sep --per-node -a -o "${stat_output}" true + commachecker --per-node echo "[Success]" } @@ -155,7 +179,8 @@ check_per_socket() echo "[Skip] paranoid and not root" return fi - perf stat -x$csv_sep --per-socket -a true 2>&1 | commachecker --per-socket + perf stat -x$csv_sep --per-socket -a -o "${stat_output}" true + commachecker --per-socket echo "[Success]" } @@ -202,4 +227,5 @@ then else echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" fi +cleanup exit 0 -- GitLab From 4228df84f952ff12540510a5c6cd00e976d992ab Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 22:44:55 -0700 Subject: [PATCH 2474/5631] perf stat: Don't write invalid "started on" comment for JSON output JSON files don't support comments. Disable the "started on" comment when writing json output to file. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sumanth Korikkar Cc: Thomas Richter Link: https://lore.kernel.org/r/20230408054456.3001367-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 38133afda7fc..40770926a230 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2272,8 +2272,10 @@ int cmd_stat(int argc, const char **argv) perror("failed to create output file"); return -1; } - clock_gettime(CLOCK_REALTIME, &tm); - fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); + if (!stat_config.json_output) { + clock_gettime(CLOCK_REALTIME, &tm); + fprintf(output, "# started on %s\n", ctime(&tm.tv_sec)); + } } else if (output_fd > 0) { mode = append_file ? "a" : "w"; output = fdopen(output_fd, mode); -- GitLab From 760eafb2a3dd568a8eec519bf21c9a24582930f3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 22:44:56 -0700 Subject: [PATCH 2475/5631] perf test stat+json_output: Write JSON output to a file Write the JSON output to a file, then sanity check this output. This avoids problems with debug/warning/error output corrupting the file format. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sumanth Korikkar Cc: Thomas Richter Link: https://lore.kernel.org/r/20230408054456.3001367-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../tests/shell/lib/perf_json_output_lint.py | 3 +- tools/perf/tests/shell/stat+json_output.sh | 48 ++++++++++++++----- 2 files changed, 38 insertions(+), 13 deletions(-) diff --git a/tools/perf/tests/shell/lib/perf_json_output_lint.py b/tools/perf/tests/shell/lib/perf_json_output_lint.py index 97598d14e532..61f3059ca54b 100644 --- a/tools/perf/tests/shell/lib/perf_json_output_lint.py +++ b/tools/perf/tests/shell/lib/perf_json_output_lint.py @@ -17,9 +17,10 @@ ap.add_argument('--per-thread', action='store_true') ap.add_argument('--per-die', action='store_true') ap.add_argument('--per-node', action='store_true') ap.add_argument('--per-socket', action='store_true') +ap.add_argument('--file', type=argparse.FileType('r'), default=sys.stdin) args = ap.parse_args() -Lines = sys.stdin.readlines() +Lines = args.file.readlines() def isfloat(num): try: diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh index 2c4212c641ed..f3e4967cc72e 100755 --- a/tools/perf/tests/shell/stat+json_output.sh +++ b/tools/perf/tests/shell/stat+json_output.sh @@ -23,6 +23,20 @@ then fi fi +stat_output=$(mktemp /tmp/__perf_test.stat_output.json.XXXXX) + +cleanup() { + rm -f "${stat_output}" + + trap - EXIT TERM INT +} + +trap_cleanup() { + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + # Return true if perf_event_paranoid is > $1 and not running as root. function ParanoidAndNotRoot() { @@ -32,7 +46,8 @@ function ParanoidAndNotRoot() check_no_args() { echo -n "Checking json output: no args " - perf stat -j true 2>&1 | $PYTHON $pythonchecker --no-args + perf stat -j -o "${stat_output}" true + $PYTHON $pythonchecker --no-args --file "${stat_output}" echo "[Success]" } @@ -44,27 +59,29 @@ check_system_wide() echo "[Skip] paranoia and not root" return fi - perf stat -j -a true 2>&1 | $PYTHON $pythonchecker --system-wide + perf stat -j -a -o "${stat_output}" true + $PYTHON $pythonchecker --system-wide --file "${stat_output}" echo "[Success]" } check_system_wide_no_aggr() { - echo -n "Checking json output: system wide " + echo -n "Checking json output: system wide no aggregation " if ParanoidAndNotRoot 0 then echo "[Skip] paranoia and not root" return fi - echo -n "Checking json output: system wide no aggregation " - perf stat -j -A -a --no-merge true 2>&1 | $PYTHON $pythonchecker --system-wide-no-aggr + perf stat -j -A -a --no-merge -o "${stat_output}" true + $PYTHON $pythonchecker --system-wide-no-aggr --file "${stat_output}" echo "[Success]" } check_interval() { echo -n "Checking json output: interval " - perf stat -j -I 1000 true 2>&1 | $PYTHON $pythonchecker --interval + perf stat -j -I 1000 -o "${stat_output}" true + $PYTHON $pythonchecker --interval --file "${stat_output}" echo "[Success]" } @@ -72,7 +89,8 @@ check_interval() check_event() { echo -n "Checking json output: event " - perf stat -j -e cpu-clock true 2>&1 | $PYTHON $pythonchecker --event + perf stat -j -e cpu-clock -o "${stat_output}" true + $PYTHON $pythonchecker --event --file "${stat_output}" echo "[Success]" } @@ -84,7 +102,8 @@ check_per_core() echo "[Skip] paranoia and not root" return fi - perf stat -j --per-core -a true 2>&1 | $PYTHON $pythonchecker --per-core + perf stat -j --per-core -a -o "${stat_output}" true + $PYTHON $pythonchecker --per-core --file "${stat_output}" echo "[Success]" } @@ -96,7 +115,8 @@ check_per_thread() echo "[Skip] paranoia and not root" return fi - perf stat -j --per-thread -a true 2>&1 | $PYTHON $pythonchecker --per-thread + perf stat -j --per-thread -a -o "${stat_output}" true + $PYTHON $pythonchecker --per-thread --file "${stat_output}" echo "[Success]" } @@ -108,7 +128,8 @@ check_per_die() echo "[Skip] paranoia and not root" return fi - perf stat -j --per-die -a true 2>&1 | $PYTHON $pythonchecker --per-die + perf stat -j --per-die -a -o "${stat_output}" true + $PYTHON $pythonchecker --per-die --file "${stat_output}" echo "[Success]" } @@ -120,7 +141,8 @@ check_per_node() echo "[Skip] paranoia and not root" return fi - perf stat -j --per-node -a true 2>&1 | $PYTHON $pythonchecker --per-node + perf stat -j --per-node -a -o "${stat_output}" true + $PYTHON $pythonchecker --per-node --file "${stat_output}" echo "[Success]" } @@ -132,7 +154,8 @@ check_per_socket() echo "[Skip] paranoia and not root" return fi - perf stat -j --per-socket -a true 2>&1 | $PYTHON $pythonchecker --per-socket + perf stat -j --per-socket -a -o "${stat_output}" true + $PYTHON $pythonchecker --per-socket --file "${stat_output}" echo "[Success]" } @@ -179,4 +202,5 @@ then else echo "[Skip] Skipping tests for system_wide_no_aggr, per_core, per_die and per_socket since socket id exposed via topology is invalid" fi +cleanup exit 0 -- GitLab From 8a1300ff95185b23baff9c226a001c269108f9ea Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:31:32 -0700 Subject: [PATCH 2476/5631] KVM: x86: Rename Hyper-V remote TLB hooks to match established scheme Rename the Hyper-V hooks for TLB flushing to match the naming scheme used by all the other TLB flushing hooks, e.g. in kvm_x86_ops, vendor code, arch hooks from common code, etc. Reviewed-by: David Matlack Reviewed-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/20230405003133.419177-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm-x86-ops.h | 4 ++-- arch/x86/include/asm/kvm_host.h | 10 +++++----- arch/x86/kvm/kvm_onhyperv.c | 13 ++++++------- arch/x86/kvm/kvm_onhyperv.h | 5 ++--- arch/x86/kvm/mmu/mmu.c | 12 ++++++------ arch/x86/kvm/svm/svm_onhyperv.h | 5 ++--- arch/x86/kvm/vmx/vmx.c | 5 ++--- 7 files changed, 25 insertions(+), 29 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 8dc345cc6318..430ca22170e0 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -54,8 +54,8 @@ KVM_X86_OP(set_rflags) KVM_X86_OP(get_if_flag) KVM_X86_OP(flush_tlb_all) KVM_X86_OP(flush_tlb_current) -KVM_X86_OP_OPTIONAL(tlb_remote_flush) -KVM_X86_OP_OPTIONAL(tlb_remote_flush_with_range) +KVM_X86_OP_OPTIONAL(flush_remote_tlbs) +KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range) KVM_X86_OP(flush_tlb_gva) KVM_X86_OP(flush_tlb_guest) KVM_X86_OP(vcpu_pre_run) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 991296a2f807..ec22101410ee 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1588,9 +1588,9 @@ struct kvm_x86_ops { void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); - int (*tlb_remote_flush)(struct kvm *kvm); - int (*tlb_remote_flush_with_range)(struct kvm *kvm, - struct kvm_tlb_range *range); + int (*flush_remote_tlbs)(struct kvm *kvm); + int (*flush_remote_tlbs_range)(struct kvm *kvm, + struct kvm_tlb_range *range); /* * Flush any TLB entries associated with the given GVA. @@ -1794,8 +1794,8 @@ void kvm_arch_free_vm(struct kvm *kvm); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) { - if (kvm_x86_ops.tlb_remote_flush && - !static_call(kvm_x86_tlb_remote_flush)(kvm)) + if (kvm_x86_ops.flush_remote_tlbs && + !static_call(kvm_x86_flush_remote_tlbs)(kvm)) return 0; else return -ENOTSUPP; diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index 482d6639ef88..2e2d08da8a3f 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -29,8 +29,7 @@ static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, return hyperv_flush_guest_mapping(root_tdp); } -int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) +int hv_flush_remote_tlbs_range(struct kvm *kvm, struct kvm_tlb_range *range) { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; @@ -86,19 +85,19 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, spin_unlock(&kvm_arch->hv_root_tdp_lock); return ret; } -EXPORT_SYMBOL_GPL(hv_remote_flush_tlb_with_range); +EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs_range); -int hv_remote_flush_tlb(struct kvm *kvm) +int hv_flush_remote_tlbs(struct kvm *kvm) { - return hv_remote_flush_tlb_with_range(kvm, NULL); + return hv_flush_remote_tlbs_range(kvm, NULL); } -EXPORT_SYMBOL_GPL(hv_remote_flush_tlb); +EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) { struct kvm_arch *kvm_arch = &vcpu->kvm->arch; - if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { + if (kvm_x86_ops.flush_remote_tlbs == hv_flush_remote_tlbs) { spin_lock(&kvm_arch->hv_root_tdp_lock); vcpu->arch.hv_root_tdp = root_tdp; if (root_tdp != kvm_arch->hv_root_tdp) diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index 287e98ef9df3..55d7fcb84cc1 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -7,9 +7,8 @@ #define __ARCH_X86_KVM_KVM_ONHYPERV_H__ #if IS_ENABLED(CONFIG_HYPERV) -int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range); -int hv_remote_flush_tlb(struct kvm *kvm); +int hv_flush_remote_tlbs_range(struct kvm *kvm, struct kvm_tlb_range *range); +int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); #else /* !CONFIG_HYPERV */ static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4c874d4ec68f..7654be48ff69 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -270,9 +270,9 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, return mmu->get_guest_pgd(vcpu); } -static inline bool kvm_available_flush_tlb_with_range(void) +static inline bool kvm_available_flush_remote_tlbs_range(void) { - return kvm_x86_ops.tlb_remote_flush_with_range; + return kvm_x86_ops.flush_remote_tlbs_range; } void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, @@ -284,8 +284,8 @@ void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, range.start_gfn = start_gfn; range.pages = nr_pages; - if (kvm_x86_ops.tlb_remote_flush_with_range) - ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, &range); + if (kvm_x86_ops.flush_remote_tlbs_range) + ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, &range); if (ret) kvm_flush_remote_tlbs(kvm); @@ -1498,7 +1498,7 @@ static bool kvm_set_pte_rmap(struct kvm *kvm, struct kvm_rmap_head *rmap_head, } } - if (need_flush && kvm_available_flush_tlb_with_range()) { + if (need_flush && kvm_available_flush_remote_tlbs_range()) { kvm_flush_remote_tlbs_gfn(kvm, gfn, level); return false; } @@ -6623,7 +6623,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, PG_LEVEL_NUM)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); - if (kvm_available_flush_tlb_with_range()) + if (kvm_available_flush_remote_tlbs_range()) kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index cff838f15db5..823001033539 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -35,9 +35,8 @@ static inline __init void svm_hv_hardware_setup(void) if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n"); - svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - svm_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + svm_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + svm_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7bf14abdba1..8031bded75cc 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8432,9 +8432,8 @@ static __init int hardware_setup(void) #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - vmx_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif -- GitLab From 9ed3bf411226f446a9795f2b49a15b9df98d7cf5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:31:33 -0700 Subject: [PATCH 2477/5631] KVM: x86/mmu: Move filling of Hyper-V's TLB range struct into Hyper-V code Refactor Hyper-V's range-based TLB flushing API to take a gfn+nr_pages pair instead of a struct, and bury said struct in Hyper-V specific code. Passing along two params generates much better code for the common case where KVM is _not_ running on Hyper-V, as forwarding the flush on to Hyper-V's hv_flush_remote_tlbs_range() from kvm_flush_remote_tlbs_range() becomes a tail call. Cc: David Matlack Reviewed-by: David Matlack Reviewed-by: Vitaly Kuznetsov Link: https://lore.kernel.org/r/20230405003133.419177-3-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 9 ++------- arch/x86/kvm/kvm_onhyperv.c | 24 ++++++++++++++++++++---- arch/x86/kvm/kvm_onhyperv.h | 2 +- arch/x86/kvm/mmu/mmu.c | 8 ++------ 4 files changed, 25 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index ec22101410ee..09eb37853cb1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -482,11 +482,6 @@ struct kvm_mmu { u64 pdptrs[4]; /* pae */ }; -struct kvm_tlb_range { - u64 start_gfn; - u64 pages; -}; - enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, @@ -1589,8 +1584,8 @@ struct kvm_x86_ops { void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); int (*flush_remote_tlbs)(struct kvm *kvm); - int (*flush_remote_tlbs_range)(struct kvm *kvm, - struct kvm_tlb_range *range); + int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, + gfn_t nr_pages); /* * Flush any TLB entries associated with the given GVA. diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index 2e2d08da8a3f..ded0bd688c65 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -10,17 +10,22 @@ #include "hyperv.h" #include "kvm_onhyperv.h" +struct kvm_hv_tlb_range { + u64 start_gfn; + u64 pages; +}; + static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, void *data) { - struct kvm_tlb_range *range = data; + struct kvm_hv_tlb_range *range = data; return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, range->pages); } static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, - struct kvm_tlb_range *range) + struct kvm_hv_tlb_range *range) { if (range) return hyperv_flush_guest_mapping_range(root_tdp, @@ -29,7 +34,8 @@ static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, return hyperv_flush_guest_mapping(root_tdp); } -int hv_flush_remote_tlbs_range(struct kvm *kvm, struct kvm_tlb_range *range) +static int __hv_flush_remote_tlbs_range(struct kvm *kvm, + struct kvm_hv_tlb_range *range) { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; @@ -85,11 +91,21 @@ int hv_flush_remote_tlbs_range(struct kvm *kvm, struct kvm_tlb_range *range) spin_unlock(&kvm_arch->hv_root_tdp_lock); return ret; } + +int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, gfn_t nr_pages) +{ + struct kvm_hv_tlb_range range = { + .start_gfn = start_gfn, + .pages = nr_pages, + }; + + return __hv_flush_remote_tlbs_range(kvm, &range); +} EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs_range); int hv_flush_remote_tlbs(struct kvm *kvm) { - return hv_flush_remote_tlbs_range(kvm, NULL); + return __hv_flush_remote_tlbs_range(kvm, NULL); } EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs); diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index 55d7fcb84cc1..ff127d313242 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -7,7 +7,7 @@ #define __ARCH_X86_KVM_KVM_ONHYPERV_H__ #if IS_ENABLED(CONFIG_HYPERV) -int hv_flush_remote_tlbs_range(struct kvm *kvm, struct kvm_tlb_range *range); +int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); #else /* !CONFIG_HYPERV */ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7654be48ff69..a7adbac0855c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -278,15 +278,11 @@ static inline bool kvm_available_flush_remote_tlbs_range(void) void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, gfn_t nr_pages) { - struct kvm_tlb_range range; int ret = -EOPNOTSUPP; - range.start_gfn = start_gfn; - range.pages = nr_pages; - if (kvm_x86_ops.flush_remote_tlbs_range) - ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, &range); - + ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn, + nr_pages); if (ret) kvm_flush_remote_tlbs(kvm); } -- GitLab From 000602e6d9b0fe3d441234d28c8a7297fd783727 Mon Sep 17 00:00:00 2001 From: Alexandre Mergnat Date: Tue, 4 Apr 2023 18:29:49 +0200 Subject: [PATCH 2478/5631] dt-bindings: pinctrl: mediatek: deprecate custom drive strength property Deprecate mediatek,drive-strength-adv which shall not exist, that was an unnecessary property that leaked upstream from downstream kernels and there's no reason to use it. The generic property drive-strength-microamp should be used instead. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Alexandre Mergnat Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230327-cleanup-pinctrl-binding-v3-1-6f56d5c7a8de@baylibre.com Signed-off-by: Linus Walleij --- .../bindings/pinctrl/mediatek,mt8183-pinctrl.yaml | 8 ++++++-- .../bindings/pinctrl/mediatek,mt8365-pinctrl.yaml | 6 +++++- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml index bf67d4672455..ff24cf29eea7 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml @@ -110,8 +110,13 @@ patternProperties: drive-strength: enum: [2, 4, 6, 8, 10, 12, 14, 16] + drive-strength-microamp: + enum: [125, 250, 500, 1000] + mediatek,drive-strength-adv: + deprecated: true description: | + DEPRECATED: Please use drive-strength-microamp instead. Describe the specific driving setup property. For I2C pins, the existing generic driving setup can only support 2/4/6/8/10/12/14/16mA driving. But in specific driving setup, they @@ -217,7 +222,7 @@ examples: pinmux = , ; mediatek,pull-up-adv = <3>; - mediatek,drive-strength-adv = <7>; + drive-strength-microamp = <1000>; }; }; @@ -226,7 +231,6 @@ examples: pinmux = , ; mediatek,pull-down-adv = <2>; - mediatek,drive-strength-adv = <4>; }; }; }; diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml index 5aa8ba4cb547..dce9fd1a6a72 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml @@ -91,8 +91,13 @@ patternProperties: input-schmitt-disable: true + drive-strength-microamp: + enum: [125, 250, 500, 1000] + mediatek,drive-strength-adv: + deprecated: true description: | + DEPRECATED: Please use drive-strength-microamp instead. Describe the specific driving setup property. For I2C pins, the existing generic driving setup can only support 2/4/6/8/10/12/14/16mA driving. But in specific driving setup, they @@ -191,7 +196,6 @@ examples: pins { pinmux = , ; mediatek,pull-up-adv = <3>; - mediatek,drive-strength-adv = <00>; bias-pull-up; }; }; -- GitLab From e34bdc71ee5b6db9810dbd7f5b36409cb7be2ca9 Mon Sep 17 00:00:00 2001 From: Alexandre Mergnat Date: Tue, 4 Apr 2023 18:29:50 +0200 Subject: [PATCH 2479/5631] dt-bindings: pinctrl: mediatek: deprecate custom bias pull properties for mt8365 In order to be more generic, "mediatek,pull-up-adv" and "mediatek,pull-down-adv" should be deprecated. Use "bias-pull-up" and "bias-pull-down" instead. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Alexandre Mergnat Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230327-cleanup-pinctrl-binding-v3-2-6f56d5c7a8de@baylibre.com Signed-off-by: Linus Walleij --- .../pinctrl/mediatek,mt8365-pinctrl.yaml | 36 +++++++++++++++---- 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml index dce9fd1a6a72..75d74b92c767 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml @@ -72,12 +72,32 @@ patternProperties: bias-disable: true bias-pull-up: - description: - Besides generic pinconfig options, it can be used as the pull up - settings for 2 pull resistors, R0 and R1. User can configure those - special pins. - - bias-pull-down: true + oneOf: + - type: boolean + - enum: [100, 101, 102, 103] + description: Pull up R1/R0 type define value. + description: | + For pull up type is normal, it don't need add R1/R0 define. + For pull up type is R1/R0 type, it can add value to set different + resistance. Valid arguments are described as below: + 100: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. + 101: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. + 102: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. + 103: (R1, R0) = (1, 1) which means R1 enabled and R0 enabled. + + bias-pull-down: + oneOf: + - type: boolean + - enum: [100, 101, 102, 103] + description: Pull down R1/R0 type define value. + description: | + For pull down type is normal, it don't need add R1/R0 define. + For pull down type is R1/R0 type, it can add value to set + different resistance. Valid arguments are described as below: + 100: (R1, R0) = (0, 0) which means R1 disabled and R0 disabled. + 101: (R1, R0) = (0, 1) which means R1 disabled and R0 enabled. + 102: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. + 103: (R1, R0) = (1, 1) which means R1 enabled and R0 enabled. input-enable: true @@ -123,7 +143,9 @@ patternProperties: enum: [0, 1, 2, 3, 4, 5, 6, 7] mediatek,pull-up-adv: + deprecated: true description: | + DEPRECATED: Please use bias-pull-up instead. Pull up setings for 2 pull resistors, R0 and R1. User can configure those special pins. Valid arguments are described as below: @@ -135,7 +157,9 @@ patternProperties: enum: [0, 1, 2, 3] mediatek,pull-down-adv: + deprecated: true description: | + DEPRECATED: Please use bias-pull-down instead. Pull down settings for 2 pull resistors, R0 and R1. User can configure those special pins. Valid arguments are described as below: -- GitLab From 29a66a6c71d6fdec7786fdeff0209f64998bcbe3 Mon Sep 17 00:00:00 2001 From: Alexandre Mergnat Date: Tue, 4 Apr 2023 18:29:51 +0200 Subject: [PATCH 2480/5631] dt-bindings: pinctrl: mediatek,mt8365-pinctrl: add drive strength property This SoC is able to drive the following output current: - 2 mA - 4 mA - 6 mA - 8 mA - 10 mA - 12 mA - 14 mA - 16 mA Then drive-strength property is set with enum to reflect its HW capability. Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Acked-by: Krzysztof Kozlowski Signed-off-by: Alexandre Mergnat Link: https://lore.kernel.org/r/20230327-cleanup-pinctrl-binding-v3-3-6f56d5c7a8de@baylibre.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml index 75d74b92c767..61b33b5416f5 100644 --- a/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/mediatek,mt8365-pinctrl.yaml @@ -99,6 +99,9 @@ patternProperties: 102: (R1, R0) = (1, 0) which means R1 enabled and R0 disabled. 103: (R1, R0) = (1, 1) which means R1 enabled and R0 enabled. + drive-strength: + enum: [2, 4, 6, 8, 10, 12, 14, 16] + input-enable: true input-disable: true -- GitLab From cd8ef949203c0fe88b031530cb5b63afd582e0f7 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:06 -0700 Subject: [PATCH 2481/5631] perf ui: Move window resize signal functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move under tools/perf/ui rather than in perf.c. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/perf.c | 18 ------------------ tools/perf/perf.h | 2 -- tools/perf/ui/setup.c | 19 +++++++++++++++++++ tools/perf/ui/tui/setup.c | 1 - tools/perf/ui/ui.h | 3 +++ 5 files changed, 22 insertions(+), 21 deletions(-) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 82bbe0ca858b..4b1b31e78332 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -432,24 +432,6 @@ static int run_argv(int *argcp, const char ***argv) return 0; } -static void pthread__block_sigwinch(void) -{ - sigset_t set; - - sigemptyset(&set); - sigaddset(&set, SIGWINCH); - pthread_sigmask(SIG_BLOCK, &set, NULL); -} - -void pthread__unblock_sigwinch(void) -{ - sigset_t set; - - sigemptyset(&set); - sigaddset(&set, SIGWINCH); - pthread_sigmask(SIG_UNBLOCK, &set, NULL); -} - static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 74014033df60..e21a7e15a34c 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -12,8 +12,6 @@ extern const char *input_name; extern bool perf_host, perf_guest; extern const char perf_version_string[]; -void pthread__unblock_sigwinch(void); - enum perf_affinity { PERF_AFFINITY_SYS = 0, PERF_AFFINITY_NODE, diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c index 25ded88801a3..ff800047e697 100644 --- a/tools/perf/ui/setup.c +++ b/tools/perf/ui/setup.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include #include #include @@ -120,3 +121,21 @@ void exit_browser(bool wait_for_ok) } mutex_destroy(&ui__lock); } + +void pthread__block_sigwinch(void) +{ + sigset_t set; + + sigemptyset(&set); + sigaddset(&set, SIGWINCH); + pthread_sigmask(SIG_BLOCK, &set, NULL); +} + +void pthread__unblock_sigwinch(void) +{ + sigset_t set; + + sigemptyset(&set); + sigaddset(&set, SIGWINCH); + pthread_sigmask(SIG_UNBLOCK, &set, NULL); +} diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c index a3b8c397c24d..c1886aa184b3 100644 --- a/tools/perf/ui/tui/setup.c +++ b/tools/perf/ui/tui/setup.c @@ -9,7 +9,6 @@ #endif #include "../../util/debug.h" -#include "../../perf.h" #include "../browser.h" #include "../helpline.h" #include "../ui.h" diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h index 99f8d2fe9bc5..d8e911205582 100644 --- a/tools/perf/ui/ui.h +++ b/tools/perf/ui/ui.h @@ -31,4 +31,7 @@ struct option; int stdio__config_color(const struct option *opt, const char *mode, int unset); +void pthread__block_sigwinch(void); +void pthread__unblock_sigwinch(void); + #endif /* _PERF_UI_H_ */ -- GitLab From 0adea51ab2e6a0d9c8336673c7c07abb7a8b858a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:07 -0700 Subject: [PATCH 2482/5631] perf usage: Move usage strings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The usage function is part of util.h, move the usage strings there too. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-help.c | 1 + tools/perf/builtin.h | 3 --- tools/perf/perf.c | 6 ------ tools/perf/util/usage.c | 6 ++++++ tools/perf/util/util.h | 3 +++ 5 files changed, 10 insertions(+), 9 deletions(-) diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index 3976aebe3677..3e7f52054fac 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -14,6 +14,7 @@ #include #include #include "util/debug.h" +#include "util/util.h" #include #include #include diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index d03afea86217..f2ab5bae2150 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -2,9 +2,6 @@ #ifndef BUILTIN_H #define BUILTIN_H -extern const char perf_usage_string[]; -extern const char perf_more_info_string[]; - void list_common_cmds_help(void); const char *help_unknown_cmd(const char *cmd); diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 4b1b31e78332..997bb9ea5ebc 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -39,12 +39,6 @@ #include #include -const char perf_usage_string[] = - "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; - -const char perf_more_info_string[] = - "See 'perf help COMMAND' for more information on a specific command."; - static int use_pager = -1; const char *input_name; diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c index 196438ee4c9d..4c8ffbad2323 100644 --- a/tools/perf/util/usage.c +++ b/tools/perf/util/usage.c @@ -12,6 +12,12 @@ #include #include +const char perf_usage_string[] = + "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; + +const char perf_more_info_string[] = + "See 'perf help COMMAND' for more information on a specific command."; + static __noreturn void usage_builtin(const char *err) { fprintf(stderr, "\n Usage: %s\n", err); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 1d3b300af5a1..5010abf9e01e 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -15,6 +15,9 @@ #include #endif +extern const char perf_usage_string[]; +extern const char perf_more_info_string[]; + /* General helper functions */ void usage(const char *err) __noreturn; void die(const char *err, ...) __noreturn __printf(1, 2); -- GitLab From 8641661cb7ee90f623276511ddb9ba901b15f904 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:08 -0700 Subject: [PATCH 2483/5631] perf header: Move perf_version_string declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move to match the definition in header.c. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-version.c | 2 +- tools/perf/perf.h | 1 - tools/perf/util/header.h | 2 ++ 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index c5d03a11e565..4a43043ca8ef 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" -#include "perf.h" #include "color.h" +#include "util/header.h" #include #include #include diff --git a/tools/perf/perf.h b/tools/perf/perf.h index e21a7e15a34c..20e9b93f8a39 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -10,7 +10,6 @@ extern const char *input_name; extern bool perf_host, perf_guest; -extern const char perf_version_string[]; enum perf_affinity { PERF_AFFINITY_SYS = 0, diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index e3861ae62172..59eeb4a32ac5 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -115,6 +115,8 @@ struct perf_session; struct perf_tool; union perf_event; +extern const char perf_version_string[]; + int perf_session__read_header(struct perf_session *session, int repipe_fd); int perf_session__write_header(struct perf_session *session, struct evlist *evlist, -- GitLab From 2176f9e21cc5cf4c1e7c9f5772625755dcb32d7b Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:09 -0700 Subject: [PATCH 2484/5631] perf version: Use regular verbose flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove additional version_verbose flag by using the existing verbose variable. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-version.c | 5 ++--- tools/perf/perf.c | 2 +- tools/perf/perf.h | 1 - 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 4a43043ca8ef..1872c90a6667 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" #include "color.h" +#include "util/debug.h" #include "util/header.h" #include #include @@ -8,8 +9,6 @@ #include #include -int version_verbose; - struct version { bool build_options; }; @@ -92,7 +91,7 @@ int cmd_version(int argc, const char **argv) printf("perf version %s\n", perf_version_string); - if (version.build_options || version_verbose == 1) + if (version.build_options || verbose > 0) library_status(); return 0; diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 997bb9ea5ebc..441c354b8304 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -212,7 +212,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) if (!strcmp(cmd, "-vv")) { (*argv)[0] = "version"; - version_verbose = 1; + verbose = 1; break; } diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 20e9b93f8a39..989eb17ec474 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -18,5 +18,4 @@ enum perf_affinity { PERF_AFFINITY_MAX }; -extern int version_verbose; #endif -- GitLab From f12ad2727bbed890cbc2890470fb00c95b089b28 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:10 -0700 Subject: [PATCH 2485/5631] perf util: Move input_name to util MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 'input_name' is the name of the input perf.data file, it is used by data convert and ui code. Move it to util to make it more consistent with other global state. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-buildid-list.c | 2 +- tools/perf/builtin-c2c.c | 2 +- tools/perf/builtin-data.c | 2 +- tools/perf/builtin-evlist.c | 2 +- tools/perf/builtin-kmem.c | 2 +- tools/perf/builtin-kwork.c | 2 +- tools/perf/builtin-mem.c | 2 +- tools/perf/builtin-sched.c | 2 +- tools/perf/builtin-stat.c | 2 +- tools/perf/builtin-timechart.c | 2 +- tools/perf/perf.c | 1 - tools/perf/perf.h | 1 - tools/perf/ui/browsers/hists.c | 2 +- tools/perf/util/util.c | 2 ++ tools/perf/util/util.h | 2 ++ 16 files changed, 16 insertions(+), 14 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 63fd2080b803..63cdf6ea6f6d 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -15,7 +15,6 @@ #include #include "util/symbol.h" -#include "perf.h" #include "util/debug.h" #include "util/evlist.h" @@ -36,6 +35,7 @@ #include "util/block-range.h" #include "util/map_symbol.h" #include "util/branch.h" +#include "util/util.h" #include #include diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index eea28cbcc0b7..c9037477865a 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -8,7 +8,6 @@ * Copyright (C) 2009, Arnaldo Carvalho de Melo */ #include "builtin.h" -#include "perf.h" #include "util/build-id.h" #include "util/debug.h" #include "util/dso.h" @@ -18,6 +17,7 @@ #include "util/session.h" #include "util/symbol.h" #include "util/data.h" +#include "util/util.h" #include #include #include diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index d3181fee4d3d..6c12f0865860 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -41,10 +41,10 @@ #include "symbol.h" #include "ui/ui.h" #include "ui/progress.h" -#include "../perf.h" #include "pmu.h" #include "pmu-hybrid.h" #include "string2.h" +#include "util/util.h" struct c2c_hists { struct hists hists; diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index b2a9a3b7f68d..ce51cbf6dc97 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -3,10 +3,10 @@ #include #include #include "builtin.h" -#include "perf.h" #include "debug.h" #include #include "data-convert.h" +#include "util/util.h" typedef int (*data_cmd_fn_t)(int argc, const char **argv); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index b1076177c37f..7117656939e7 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -7,7 +7,6 @@ #include -#include "perf.h" #include "util/evlist.h" #include "util/evsel.h" #include "util/evsel_fprintf.h" @@ -18,6 +17,7 @@ #include "util/debug.h" #include #include "util/tool.h" +#include "util/util.h" static int process_header_feature(struct perf_session *session __maybe_unused, union perf_event *event __maybe_unused) diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index fcd2ef3bd3f5..2150eeced892 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" -#include "perf.h" #include "util/dso.h" #include "util/evlist.h" @@ -24,6 +23,7 @@ #include "util/debug.h" #include "util/string2.h" +#include "util/util.h" #include #include diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index dc59d75180d1..a9395c52b23b 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -6,7 +6,6 @@ */ #include "builtin.h" -#include "perf.h" #include "util/data.h" #include "util/evlist.h" @@ -20,6 +19,7 @@ #include "util/string2.h" #include "util/callchain.h" #include "util/evsel_fprintf.h" +#include "util/util.h" #include #include diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 1e27188b0de1..65465930ef8e 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -4,7 +4,6 @@ #include #include #include "builtin.h" -#include "perf.h" #include #include "util/auxtrace.h" @@ -22,6 +21,7 @@ #include "util/pmu-hybrid.h" #include "util/sample.h" #include "util/string2.h" +#include "util/util.h" #include #define MEM_OPERATION_LOAD 0x1 diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 86e18575c9be..96a0dceadeff 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include "builtin.h" -#include "perf.h" #include "perf-sys.h" #include "util/cpumap.h" @@ -27,6 +26,7 @@ #include "util/debug.h" #include "util/event.h" +#include "util/util.h" #include #include diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 40770926a230..d3cbee7460fc 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -41,7 +41,6 @@ */ #include "builtin.h" -#include "perf.h" #include "util/cgroup.h" #include #include "util/parse-events.h" @@ -71,6 +70,7 @@ #include "util/bpf_counter.h" #include "util/iostat.h" #include "util/pmu-hybrid.h" +#include "util/util.h" #include "asm/bug.h" #include diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 6c629e7d370a..bce1cf896f9c 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -24,7 +24,6 @@ #include "util/thread.h" #include "util/callchain.h" -#include "perf.h" #include "util/header.h" #include #include @@ -37,6 +36,7 @@ #include "util/debug.h" #include "util/string2.h" #include "util/tracepoint.h" +#include "util/util.h" #include #include diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 441c354b8304..38cae4721583 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -40,7 +40,6 @@ #include static int use_pager = -1; -const char *input_name; struct cmd_struct { const char *cmd; diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 989eb17ec474..49e15e2be49e 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -8,7 +8,6 @@ #define MAX_NR_CPUS 2048 #endif -extern const char *input_name; extern bool perf_host, perf_guest; enum perf_affinity { diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 9f9f622325ae..ab70e5f5fad2 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -29,8 +29,8 @@ #include "../../util/top.h" #include "../../util/thread.h" #include "../../util/block-info.h" +#include "../../util/util.h" #include "../../arch/common.h" -#include "../../perf.h" #include "../browsers/hists.h" #include "../helpline.h" diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 089208b51e68..c1fd9ba6d697 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -28,6 +28,8 @@ * XXX We need to find a better place for these things... */ +const char *input_name; + bool perf_singlethreaded = true; void perf_set_singlethreaded(void) diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 5010abf9e01e..8bd515b67739 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -18,6 +18,8 @@ extern const char perf_usage_string[]; extern const char perf_more_info_string[]; +extern const char *input_name; + /* General helper functions */ void usage(const char *err) __noreturn; void die(const char *err, ...) __noreturn __printf(1, 2); -- GitLab From ea0c52399d99d2e48cafdf97e2d8589bf8beb7c2 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:25:11 -0700 Subject: [PATCH 2486/5631] perf util: Move perf_guest/host declarations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The definitions are in util.c so move the declarations to match. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Rajeev Cc: Chengdong Li Cc: Denis Nikitin Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Martin Liška Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Raul Silvera Cc: Ravi Bangoria Cc: Rob Herring Cc: Sean Christopherson Cc: Suzuki Poulouse Cc: Will Deacon Cc: Xing Zhengjun Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230410162511.3055900-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-kvm.c | 1 + tools/perf/perf.h | 4 ---- tools/perf/ui/hist.c | 2 +- tools/perf/util/cs-etm.c | 1 + tools/perf/util/event.c | 2 +- tools/perf/util/evlist.c | 1 + tools/perf/util/parse-events.c | 2 +- tools/perf/util/session.c | 2 +- tools/perf/util/top.c | 2 +- tools/perf/util/util.h | 3 +++ 11 files changed, 12 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 22b526766e14..dbb0562d6a4f 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -6,7 +6,6 @@ * DSOs and symbol information, sort them and produce a diff. */ #include "builtin.h" -#include "perf.h" #include "util/debug.h" #include "util/event.h" @@ -26,6 +25,7 @@ #include "util/spark.h" #include "util/block-info.h" #include "util/stream.h" +#include "util/util.h" #include #include #include diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index fb9dc0dc46f9..747d19336340 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -23,6 +23,7 @@ #include "util/data.h" #include "util/ordered-events.h" #include "util/kvm-stat.h" +#include "util/util.h" #include "ui/browsers/hists.h" #include "ui/progress.h" #include "ui/ui.h" diff --git a/tools/perf/perf.h b/tools/perf/perf.h index 49e15e2be49e..c004dd4e65a3 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -2,14 +2,10 @@ #ifndef _PERF_PERF_H #define _PERF_PERF_H -#include - #ifndef MAX_NR_CPUS #define MAX_NR_CPUS 2048 #endif -extern bool perf_host, perf_guest; - enum perf_affinity { PERF_AFFINITY_SYS = 0, PERF_AFFINITY_NODE, diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 5075ecead5f3..f164bd26fc41 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -11,7 +11,7 @@ #include "../util/sort.h" #include "../util/evsel.h" #include "../util/evlist.h" -#include "../perf.h" +#include "../util/util.h" /* hist period print (hpp) functions */ diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 944835e16430..103865968700 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -38,6 +38,7 @@ #include "tsc.h" #include #include "util/synthetic-events.h" +#include "util/util.h" struct cs_etm_auxtrace { struct auxtrace auxtrace; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 13f7f85e92e1..8ae742e32e3c 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -33,7 +33,7 @@ #include "bpf-event.h" #include "print_binary.h" #include "tool.h" -#include "../perf.h" +#include "util.h" static const char *perf_event__names[] = { [0] = "TOTAL", diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index cc491a037836..df6af38ca22e 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -32,6 +32,7 @@ #include "util/pmu.h" #include "util/sample.h" #include "util/bpf-filter.h" +#include "util/util.h" #include #include #include diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 0010e5e0ee68..f341995cb04e 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -25,10 +25,10 @@ #include "util/parse-branch-options.h" #include "util/evsel_config.h" #include "util/event.h" -#include "perf.h" #include "util/parse-events-hybrid.h" #include "util/pmu-hybrid.h" #include "util/bpf-filter.h" +#include "util/util.h" #include "tracepoint.h" #include "thread_map.h" diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 7d8d057d1772..e2806791c76a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -33,7 +33,7 @@ #include "stat.h" #include "tsc.h" #include "ui/progress.h" -#include "../perf.h" +#include "util.h" #include "arch/common.h" #include "units.h" #include diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c index b8b32431d2f7..be7157de0451 100644 --- a/tools/perf/util/top.c +++ b/tools/perf/util/top.c @@ -11,7 +11,7 @@ #include "parse-events.h" #include "symbol.h" #include "top.h" -#include "../perf.h" +#include "util.h" #include #define SNPRINTF(buf, size, fmt, args...) \ diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 8bd515b67739..7c8915d92dca 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -20,6 +20,9 @@ extern const char perf_more_info_string[]; extern const char *input_name; +extern bool perf_host; +extern bool perf_guest; + /* General helper functions */ void usage(const char *err) __noreturn; void die(const char *err, ...) __noreturn __printf(1, 2); -- GitLab From b391efeeaf0b47966137ef93be430fda4486ada9 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 7 Apr 2023 14:29:14 -0700 Subject: [PATCH 2487/5631] pinctrl: qcom: Add "and" to PIN_CONFIG_INPUT_ENABLE comment The comment recently added talking about PIN_CONFIG_INPUT_ENABLE is clearly missing the word "and". Comments live forever, so let's fix it. Fixes: e49eabe3e13f ("pinctrl: qcom: Support OUTPUT_ENABLE; deprecate INPUT_ENABLE") Reported-by: Stephen Boyd Link: https://chromium-review.googlesource.com/c/chromiumos/third_party/kernel/+/4409769/comment/9a1d5def_e1e71db7/ Signed-off-by: Douglas Anderson Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20230407142859.1.Ia5d70e320b60d6707c6182879097708e49b8b519@changeid Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-msm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 65a172786ae0..c5f52d4f7781 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -517,7 +517,7 @@ static int msm_config_group_set(struct pinctrl_dev *pctldev, * The points above, explain why this _should_ be a * no-op. However, for historical reasons and to * support old device trees, we'll violate the docs - * still affect the output. + * and still affect the output. * * It should further be noted that this old historical * behavior actually overrides arg to 0. That means -- GitLab From 51924ae69eea5bc90b5da525fbcf4bbd5f8551b3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 09:09:05 -0700 Subject: [PATCH 2488/5631] perf build: Warn for BPF skeletons if endian mismatches Done as a warning as I'm not fully confident of the test's robustness of comparing the macro definition of __BYTE_ORDER__. v2. Is a rebase following patch 1 being merged. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230410160905.3052640-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 16bea51f0bcd..71442c54c25f 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -663,14 +663,17 @@ ifndef NO_BPF_SKEL $(call feature_check,clang-bpf-co-re) ifeq ($(feature-clang-bpf-co-re), 0) dummy := $(error: ERROR: BPF skeletons unsupported. clang too old/not installed or build with NO_BPF_SKEL=1.) - else - ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) - else - $(call detected,CONFIG_PERF_BPF_SKEL) - CFLAGS += -DHAVE_BPF_SKEL - endif endif + ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) + dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) + endif + host_byte_order=$(echo ""|$(HOSTCC) -dM -E -|grep __BYTE_ORDER__) + target_byte_order=$(echo ""|$(CC) -dM -E -|grep __BYTE_ORDER__) + ifneq ($(host_byte_order), $(target_byte_order)) + $(warning Possibly mismatched host and target endianness may break BPF skeletons) + endif + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL endif dwarf-post-unwind := 1 -- GitLab From e0999b0e2149a0ec97f88547ab3658032d8ed70d Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:54 +0530 Subject: [PATCH 2489/5631] tools include UAPI: Sync uapi/linux/perf_event.h with the kernel sources ... to bring PERF_MEM_LVLNUM_UNC definition to userspace Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 37675437b768..39c6a250dd1b 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1339,7 +1339,8 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x8 available */ +/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -- GitLab From cf9f4c0eb1699d306e348b1fd0225af7b2c282d3 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:26:08 -0700 Subject: [PATCH 2490/5631] KVM: x86/mmu: Refresh CR0.WP prior to checking for emulated permission faults Refresh the MMU's snapshot of the vCPU's CR0.WP prior to checking for permission faults when emulating a guest memory access and CR0.WP may be guest owned. If the guest toggles only CR0.WP and triggers emulation of a supervisor write, e.g. when KVM is emulating UMIP, KVM may consume a stale CR0.WP, i.e. use stale protection bits metadata. Note, KVM passes through CR0.WP if and only if EPT is enabled as CR0.WP is part of the MMU role for legacy shadow paging, and SVM (NPT) doesn't support per-bit interception controls for CR0. Don't bother checking for EPT vs. NPT as the "old == new" check will always be true under NPT, i.e. the only cost is the read of vcpu->arch.cr4 (SVM unconditionally grabs CR0 from the VMCB on VM-Exit). Reported-by: Mathias Krause Link: https://lkml.kernel.org/r/677169b4-051f-fcae-756b-9a3e1bb9f8fe%40grsecurity.net Fixes: fb509f76acc8 ("KVM: VMX: Make CR0.WP a guest owned bit") Tested-by: Mathias Krause Link: https://lore.kernel.org/r/20230405002608.418442-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu.h | 26 +++++++++++++++++++++++++- arch/x86/kvm/mmu/mmu.c | 15 +++++++++++++++ 2 files changed, 40 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 89f532516a45..92d5a1924fc1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -113,6 +113,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); @@ -153,6 +155,24 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_role.level); } +static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + /* + * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. + * @mmu's snapshot of CR0.WP and thus all related paging metadata may + * be stale. Refresh CR0.WP and the metadata on-demand when checking + * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing + * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does + * need to refresh nested_mmu, a.k.a. the walker used to translate L2 + * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. + */ + if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) + return; + + __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); +} + /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -184,8 +204,12 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; - bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; + bool fault; + + kvm_mmu_refresh_passthrough_bits(vcpu, mmu); + + fault = (mmu->permissions[index] >> pte_access) & 1; WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 144c5a01cd77..4544605272e2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5112,6 +5112,21 @@ kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) return role; } +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + const bool cr0_wp = kvm_is_cr0_bit_set(vcpu, X86_CR0_WP); + + BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); + BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); + + if (is_cr0_wp(mmu) == cr0_wp) + return; + + mmu->cpu_role.base.cr0_wp = cr0_wp; + reset_guest_paging_metadata(vcpu, mmu); +} + static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { /* tdp_root_level is architecture forced level, use it if nonzero */ -- GitLab From fd359ec81399f5cec92ac774df1c3b95f4d699a6 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:55 +0530 Subject: [PATCH 2491/5631] perf mem: Add PERF_MEM_LVLNUM_NA to PERF_MEM_DATA_SRC_NONE Add PERF_MEM_LVLNUM_NA wherever PERF_MEM_DATA_SRC_NONE is used to set default values. Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/event.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 6663a676eadc..de20e01c9d72 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -89,7 +89,8 @@ enum { PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ - PERF_MEM_S(TLB, NA)) + PERF_MEM_S(TLB, NA) |\ + PERF_MEM_S(LVLNUM, NA)) /* Attribute type for custom synthesized events */ #define PERF_TYPE_SYNTH (INT_MAX + 1U) -- GitLab From d5fa7e9d0c13d67be30305dff689811478ae53cb Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:56 +0530 Subject: [PATCH 2492/5631] perf mem: Add support for printing PERF_MEM_LVLNUM_UNC Add support for printing PERF_MEM_LVLNUM_UNC in perf mem report. Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mem-events.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index b3a91093069a..3a7c72be8326 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -295,6 +295,7 @@ static const char * const mem_lvl[] = { }; static const char * const mem_lvlnum[] = { + [PERF_MEM_LVLNUM_UNC] = "Uncached", [PERF_MEM_LVLNUM_CXL] = "CXL", [PERF_MEM_LVLNUM_IO] = "I/O", [PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache", -- GitLab From ddeac198e1990715a162bf14faeab6000376ed1e Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:57 +0530 Subject: [PATCH 2493/5631] perf mem: Refactor perf_mem__lvl_scnprintf() to process 'union perf_mem_data_src' more intuitively Interpretation of 'union perf_mem_data_src' by perf_mem__lvl_scnprintf() is non-intuitive. For ex, it ignores 'mem_lvl' when 'mem_hops' is set but considers it otherwise. It prints both 'mem_lvl_num' and 'mem_lvl' when 'mem_hops' is not set. Refactor this function such that it behaves more intuitively: Use new API 'mem_lvl_num'|'mem_remote'|'mem_hops' if 'mem_lvl_num' contains value other than PERF_MEM_LVLNUM_NA. Otherwise, fallback to old API 'mem_lvl'. Since new API has no way to indicate MISS, use it from old api, otherwise don't club old and new APIs while parsing as well as printing. Before: $ sudo ./perf mem report -F sample,mem --stdio # Samples Memory access # ............ ........................ # 250097 N/A 188907 L1 hit 4116 L2 hit 3496 Remote Cache (1 hop) hit 3271 Remote Cache (2 hops) hit 873 L3 hit 598 Local RAM hit 438 Remote RAM (1 hop) hit 1 Uncached hit After: $ sudo ./perf mem report -F sample,mem --stdio # Samples Memory access # ............ ....................................... # 255517 N/A 189989 L1 hit 4541 L2 hit 3363 Remote core, same node Any cache hit 3336 Remote node, same socket Any cache hit 1275 L3 hit 743 RAM hit 545 Remote node, same socket RAM hit 4 Uncached hit Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/mem-events.c | 89 +++++++++++++++++++----------------- 1 file changed, 47 insertions(+), 42 deletions(-) diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 3a7c72be8326..ed1ee4b05356 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -344,66 +344,71 @@ static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_inf int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) { - size_t i, l = 0; - u64 m = PERF_MEM_LVL_NA; - u64 hit, miss; + union perf_mem_data_src data_src; int printed = 0; - - if (mem_info) - m = mem_info->data_src.mem_lvl; + size_t l = 0; + size_t i; + int lvl; + char hit_miss[5] = {0}; sz -= 1; /* -1 for null termination */ out[0] = '\0'; - hit = m & PERF_MEM_LVL_HIT; - miss = m & PERF_MEM_LVL_MISS; + if (!mem_info) + goto na; - /* already taken care of */ - m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); + data_src = mem_info->data_src; - if (mem_info && mem_info->data_src.mem_remote) { - strcat(out, "Remote "); - l += 7; - } + if (data_src.mem_lvl & PERF_MEM_LVL_HIT) + memcpy(hit_miss, "hit", 3); + else if (data_src.mem_lvl & PERF_MEM_LVL_MISS) + memcpy(hit_miss, "miss", 4); - /* - * Incase mem_hops field is set, we can skip printing data source via - * PERF_MEM_LVL namespace. - */ - if (mem_info && mem_info->data_src.mem_hops) { - l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]); - } else { - for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) { - if (!(m & 0x1)) - continue; - if (printed++) { - strcat(out, " or "); - l += 4; - } - l += scnprintf(out + l, sz - l, mem_lvl[i]); + lvl = data_src.mem_lvl_num; + if (lvl && lvl != PERF_MEM_LVLNUM_NA) { + if (data_src.mem_remote) { + strcat(out, "Remote "); + l += 7; } + + if (data_src.mem_hops) + l += scnprintf(out + l, sz - l, "%s ", mem_hops[data_src.mem_hops]); + + if (mem_lvlnum[lvl]) + l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]); + else + l += scnprintf(out + l, sz - l, "L%d", lvl); + + l += scnprintf(out + l, sz - l, " %s", hit_miss); + return l; } - if (mem_info && mem_info->data_src.mem_lvl_num) { - int lvl = mem_info->data_src.mem_lvl_num; + lvl = data_src.mem_lvl; + if (!lvl) + goto na; + + lvl &= ~(PERF_MEM_LVL_NA | PERF_MEM_LVL_HIT | PERF_MEM_LVL_MISS); + if (!lvl) + goto na; + + for (i = 0; lvl && i < ARRAY_SIZE(mem_lvl); i++, lvl >>= 1) { + if (!(lvl & 0x1)) + continue; if (printed++) { strcat(out, " or "); l += 4; } - if (mem_lvlnum[lvl]) - l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]); - else - l += scnprintf(out + l, sz - l, "L%d", lvl); + l += scnprintf(out + l, sz - l, mem_lvl[i]); } - if (l == 0) - l += scnprintf(out + l, sz - l, "N/A"); - if (hit) - l += scnprintf(out + l, sz - l, " hit"); - if (miss) - l += scnprintf(out + l, sz - l, " miss"); + if (printed) { + l += scnprintf(out + l, sz - l, " %s", hit_miss); + return l; + } - return l; +na: + strcat(out, "N/A"); + return 3; } static const char * const snoop_access[] = { -- GitLab From 4953c8979d19a34fa98f4e8e55eae603cffe128a Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:58 +0530 Subject: [PATCH 2494/5631] perf mem: Increase HISTC_MEM_LVL column size to 39 chars 39 is taken from the length of longest printable new API string: "Remote socket, same board Any cache hit". Although, using old API can result into even longer strings, let's not overkill by making it dynamic length. Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 51020da15ffc..3c9301a26dfc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -208,7 +208,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_MEM_LOCKED, 6); hists__new_col_len(hists, HISTC_MEM_TLB, 22); hists__new_col_len(hists, HISTC_MEM_SNOOP, 12); - hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3); + hists__new_col_len(hists, HISTC_MEM_LVL, 36 + 3); hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10); -- GitLab From 3d3a3a49e20f006fa88e4fec5ad236864faa3a35 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Fri, 7 Apr 2023 16:54:59 +0530 Subject: [PATCH 2495/5631] perf script ibs: Change bit description according to latest AMD PPR ("Processor Programming Reference") Some of the IBS_OP_DATA2 bit descriptions were stale (taken from old version of PPR). Change it according to latest PPR. Signed-off-by: Ravi Bangoria Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Peter Zijlstra Cc: Sandipan Das Cc: Santosh Shukla Cc: Stephane Eranian Link: https://lore.kernel.org/r/20230407112459.548-5-ravi.bangoria@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/amd-sample-raw.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c index b0e70ce9d87a..6a6ddba76c75 100644 --- a/tools/perf/util/amd-sample-raw.c +++ b/tools/perf/util/amd-sample-raw.c @@ -105,17 +105,17 @@ static void pr_ibs_op_data2_extended(union ibs_op_data2 reg) static const char * const data_src_str[] = { "", " DataSrc 1=Local L3 or other L1/L2 in CCX", - " DataSrc 2=A peer cache in a near CCX", - " DataSrc 3=Data returned from DRAM", + " DataSrc 2=Another CCX cache in the same NUMA node", + " DataSrc 3=DRAM", " DataSrc 4=(reserved)", - " DataSrc 5=A peer cache in a far CCX", - " DataSrc 6=DRAM address map with \"long latency\" bit set", - " DataSrc 7=Data returned from MMIO/Config/PCI/APIC", - " DataSrc 8=Extension Memory (S-Link, GenZ, etc)", + " DataSrc 5=Another CCX cache in a different NUMA node", + " DataSrc 6=Long-latency DIMM", + " DataSrc 7=MMIO/Config/PCI/APIC", + " DataSrc 8=Extension Memory", " DataSrc 9=(reserved)", " DataSrc 10=(reserved)", " DataSrc 11=(reserved)", - " DataSrc 12=Peer Agent Memory", + " DataSrc 12=Coherent Memory of a different processor type", /* 13 to 31 are reserved. Avoid printing them. */ }; int data_src = (reg.data_src_hi << 3) | reg.data_src_lo; -- GitLab From 210f8cab0751eb95dc56453e3dbf8a962d4d1e17 Mon Sep 17 00:00:00 2001 From: JungHoon Hyun Date: Sun, 9 Apr 2023 19:36:57 -0700 Subject: [PATCH 2496/5631] Input: melfas_mip4 - report palm touches The driver had the code to differentiate between finger and palm touches, but did not use this information when reporting contacts. Change it so that proper "tool" type is assigned to reported contacts. Signed-off-by: JungHoon Hyun Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/melfas_mip4.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c index acdfbdea2b6e..89b6020a9a61 100644 --- a/drivers/input/touchscreen/melfas_mip4.c +++ b/drivers/input/touchscreen/melfas_mip4.c @@ -466,7 +466,7 @@ static void mip4_report_touch(struct mip4_ts *ts, u8 *packet) { int id; bool __always_unused hover; - bool __always_unused palm; + bool palm; bool state; u16 x, y; u8 __always_unused pressure_stage = 0; @@ -522,21 +522,21 @@ static void mip4_report_touch(struct mip4_ts *ts, u8 *packet) if (unlikely(id < 0 || id >= MIP4_MAX_FINGERS)) { dev_err(&ts->client->dev, "Screen - invalid slot ID: %d\n", id); - } else if (state) { - /* Press or Move event */ - input_mt_slot(ts->input, id); - input_mt_report_slot_state(ts->input, MT_TOOL_FINGER, true); + goto out; + } + + input_mt_slot(ts->input, id); + if (input_mt_report_slot_state(ts->input, + palm ? MT_TOOL_PALM : MT_TOOL_FINGER, + state)) { input_report_abs(ts->input, ABS_MT_POSITION_X, x); input_report_abs(ts->input, ABS_MT_POSITION_Y, y); input_report_abs(ts->input, ABS_MT_PRESSURE, pressure); input_report_abs(ts->input, ABS_MT_TOUCH_MAJOR, touch_major); input_report_abs(ts->input, ABS_MT_TOUCH_MINOR, touch_minor); - } else { - /* Release event */ - input_mt_slot(ts->input, id); - input_mt_report_slot_inactive(ts->input); } +out: input_mt_sync_frame(ts->input); } @@ -1483,6 +1483,7 @@ static int mip4_probe(struct i2c_client *client) input->keycodesize = sizeof(*ts->key_code); input->keycodemax = ts->key_num; + input_set_abs_params(input, ABS_MT_TOOL_TYPE, 0, MT_TOOL_PALM, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_X, 0, ts->max_x, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_Y, 0, ts->max_y, 0, 0); input_set_abs_params(input, ABS_MT_PRESSURE, -- GitLab From 483a14418661878d89216be0f02918892227833b Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Mon, 10 Apr 2023 16:55:44 -0700 Subject: [PATCH 2497/5631] Input: edt-ft5x06 - select REGMAP_I2C After starting to use regmap API to access registers the edt-ft5x06 driver depends on symbols provided by REGMAP_I2C: edt-ft5x06.o: in function `edt_ft5x06_ts_probe': edt-ft5x06.c:1154: undefined reference to `__regmap_init_i2c' edt-ft5x06.o: in function `edt_ft5x06_ts_identify': edt-ft5x06.c:897: undefined reference to `__regmap_init_i2c' Make sure support for I2C regmap is actually selected by adding this dependency to Kconfig. Fixes: 9dfd9708ffba ("Input: edt-ft5x06 - convert to use regmap API") Signed-off-by: Daniel Golle Link: https://lore.kernel.org/r/ZDRBExF1xmxalMZc@makrotopia.org Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 1feecd7ed3cb..143ff43c67ae 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -768,6 +768,7 @@ config TOUCHSCREEN_PENMOUNT config TOUCHSCREEN_EDT_FT5X06 tristate "EDT FocalTech FT5x06 I2C Touchscreen support" depends on I2C + select REGMAP_I2C help Say Y here if you have an EDT "Polytouch" touchscreen based on the FocalTech FT5x06 family of controllers connected to -- GitLab From cb9eee590a77320b997a47cae18662af23dcb726 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 5 Apr 2023 21:09:35 -0400 Subject: [PATCH 2498/5631] clk: mediatek: fhctl: Mark local variables static smatch reports drivers/clk/mediatek/clk-fhctl.c:17:27: warning: symbol 'fhctl_offset_v1' was not declared. Should it be static? drivers/clk/mediatek/clk-fhctl.c:30:27: warning: symbol 'fhctl_offset_v2' was not declared. Should it be static? These variables are only used in one file so should be static. Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230406010935.1944976-1-trix@redhat.com Fixes: 8da312d6574c ("clk: mediatek: fhctl: Add support for older fhctl register layout") Signed-off-by: Stephen Boyd --- drivers/clk/mediatek/clk-fhctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/mediatek/clk-fhctl.c b/drivers/clk/mediatek/clk-fhctl.c index 45e4842cbf04..33b6ad8fdc2e 100644 --- a/drivers/clk/mediatek/clk-fhctl.c +++ b/drivers/clk/mediatek/clk-fhctl.c @@ -14,7 +14,7 @@ #define PERCENT_TO_DDSLMT(dds, percent_m10) \ ((((dds) * (percent_m10)) >> 5) / 100) -const struct fhctl_offset fhctl_offset_v1 = { +static const struct fhctl_offset fhctl_offset_v1 = { .offset_hp_en = 0x0, .offset_clk_con = 0x4, .offset_rst_con = 0x8, @@ -27,7 +27,7 @@ const struct fhctl_offset fhctl_offset_v1 = { .offset_mon = 0x10, }; -const struct fhctl_offset fhctl_offset_v2 = { +static const struct fhctl_offset fhctl_offset_v2 = { .offset_hp_en = 0x0, .offset_clk_con = 0x8, .offset_rst_con = 0xc, -- GitLab From cf57cf51d7c63595a50359694537b41aa05dda7e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 13:56:59 -0700 Subject: [PATCH 2499/5631] perf evsel: Avoid SEGV if delete is called on NULL Seen in "perf stat --bpf-counters --for-each-cgroup test" running in a container: libbpf: Failed to bump RLIMIT_MEMLOCK (err = -1), you might need to do it explicitly! libbpf: Error in bpf_object__probe_loading():Operation not permitted(1). Couldn't load trivial BPF program. Make sure your kernel supports BPF (CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is set to big enough value. libbpf: failed to load object 'bperf_cgroup_bpf' libbpf: failed to load BPF skeleton 'bperf_cgroup_bpf': -1 Failed to load cgroup skeleton #0 0x55f28a650981 in list_empty tools/include/linux/list.h:189 #1 0x55f28a6593b4 in evsel__exit util/evsel.c:1518 #2 0x55f28a6596af in evsel__delete util/evsel.c:1544 #3 0x55f28a89d166 in bperf_cgrp__destroy util/bpf_counter_cgroup.c:283 #4 0x55f28a899e9a in bpf_counter__destroy util/bpf_counter.c:816 #5 0x55f28a659455 in evsel__exit util/evsel.c:1520 #6 0x55f28a6596af in evsel__delete util/evsel.c:1544 #7 0x55f28a640d4d in evlist__purge util/evlist.c:148 #8 0x55f28a640ea6 in evlist__delete util/evlist.c:169 #9 0x55f28a4efbf2 in cmd_stat tools/perf/builtin-stat.c:2598 #10 0x55f28a6050c2 in run_builtin tools/perf/perf.c:330 #11 0x55f28a605633 in handle_internal_command tools/perf/perf.c:384 #12 0x55f28a6059fb in run_argv tools/perf/perf.c:428 #13 0x55f28a6061d3 in main tools/perf/perf.c:562 Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Florian Fischer Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230410205659.3131608-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index dc3faf005c3b..fe3ce765a4f3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1541,6 +1541,9 @@ void evsel__exit(struct evsel *evsel) void evsel__delete(struct evsel *evsel) { + if (!evsel) + return; + evsel__exit(evsel); free(evsel); } -- GitLab From e013733612854f446fae9193a42addfe7a926b9c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 10 Apr 2023 22:17:18 -0700 Subject: [PATCH 2500/5631] perf bperf: Avoid use after free via unrelated 'struct evsel' anonymous union field If bperf (perf tools that use BPF skels) sets evsel->leader_skel or evsel->follower_skel then it appears that evsel->bpf_skel is set and can trigger the following use-after-free: ==13575==ERROR: AddressSanitizer: heap-use-after-free on address 0x60c000014080 at pc 0x55684b939880 bp 0x7ffdfcf30d70 sp 0x7ffdfcf30d68 READ of size 8 at 0x60c000014080 thread T0 #0 0x55684b93987f in sample_filter_bpf__destroy tools/perf/bpf_skel/sample_filter.skel.h:44:11 #1 0x55684b93987f in perf_bpf_filter__destroy tools/perf/util/bpf-filter.c:155:2 #2 0x55684b98f71e in evsel__exit tools/perf/util/evsel.c:1521:2 #3 0x55684b98a352 in evsel__delete tools/perf/util/evsel.c:1547:2 #4 0x55684b981918 in evlist__purge tools/perf/util/evlist.c:148:3 #5 0x55684b981918 in evlist__delete tools/perf/util/evlist.c:169:2 #6 0x55684b887d60 in cmd_stat tools/perf/builtin-stat.c:2598:2 .. 0x60c000014080 is located 0 bytes inside of 128-byte region [0x60c000014080,0x60c000014100) freed by thread T0 here: #0 0x55684b780e86 in free compiler-rt/lib/asan/asan_malloc_linux.cpp:52:3 #1 0x55684b9462da in bperf_cgroup_bpf__destroy tools/perf/bpf_skel/bperf_cgroup.skel.h:61:2 #2 0x55684b9462da in bperf_cgrp__destroy tools/perf/util/bpf_counter_cgroup.c:282:2 #3 0x55684b944c75 in bpf_counter__destroy tools/perf/util/bpf_counter.c:819:2 #4 0x55684b98f716 in evsel__exit tools/perf/util/evsel.c:1520:2 #5 0x55684b98a352 in evsel__delete tools/perf/util/evsel.c:1547:2 #6 0x55684b981918 in evlist__purge tools/perf/util/evlist.c:148:3 #7 0x55684b981918 in evlist__delete tools/perf/util/evlist.c:169:2 #8 0x55684b887d60 in cmd_stat tools/perf/builtin-stat.c:2598:2 ... previously allocated by thread T0 here: #0 0x55684b781338 in calloc compiler-rt/lib/asan/asan_malloc_linux.cpp:77:3 #1 0x55684b944e25 in bperf_cgroup_bpf__open_opts tools/perf/bpf_skel/bperf_cgroup.skel.h:73:35 #2 0x55684b944e25 in bperf_cgroup_bpf__open tools/perf/bpf_skel/bperf_cgroup.skel.h:97:9 #3 0x55684b944e25 in bperf_load_program tools/perf/util/bpf_counter_cgroup.c:55:9 #4 0x55684b944e25 in bperf_cgrp__load tools/perf/util/bpf_counter_cgroup.c:178:23 #5 0x55684b889289 in __run_perf_stat tools/perf/builtin-stat.c:713:7 #6 0x55684b889289 in run_perf_stat tools/perf/builtin-stat.c:949:8 #7 0x55684b888029 in cmd_stat tools/perf/builtin-stat.c:2537:12 Resolve by clearing 'evsel->bpf_skel' as part of bpf_counter__destroy(). Suggested-by: Namhyung Kim Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: http://lore.kernel.org/lkml/20230411051718.267228-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_counter.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 76ee3e86824a..6732cbbcf9b3 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -815,4 +815,5 @@ void bpf_counter__destroy(struct evsel *evsel) return; evsel->bpf_counter_ops->destroy(evsel); evsel->bpf_counter_ops = NULL; + evsel->bpf_skel = NULL; } -- GitLab From 78f0929884d4811c225fd2c57ecc602c84c07392 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 4 Apr 2023 20:28:47 +1000 Subject: [PATCH 2501/5631] powerpc/64: Always build with 128-bit long double The amdgpu driver builds some of its code with hard-float enabled, whereas the rest of the kernel is built with soft-float. When building with 64-bit long double, if soft-float and hard-float objects are linked together, the build fails due to incompatible ABI tags. In the past there have been build errors in the amdgpu driver caused by this, some of those were due to bad intermingling of soft & hard-float code, but those issues have now all been fixed since commit 58ddbecb14c7 ("drm/amd/display: move remaining FPU code to dml folder"). However it's still possible for soft & hard-float objects to end up linked together, if the amdgpu driver is built-in to the kernel along with the test_emulate_step.c code, which uses soft-float. That happens in an allyesconfig build. Currently those build errors are avoided because the amdgpu driver is gated on 128-bit long double being enabled. But that's not a detail the amdgpu driver should need to be aware of, and if another driver starts using hard-float the same problem would occur. All versions of the 64-bit ABI specify that long-double is 128-bits. However some compilers, notably the kernel.org ones, are built to use 64-bit long double by default. Apart from this issue of soft vs hard-float, the kernel doesn't care what size long double is. In particular the kernel using 128-bit long double doesn't impact userspace's ability to use 64-bit long double, as musl does. So always build the 64-bit kernel with 128-bit long double. That should avoid any build errors due to the incompatible ABI tags. Excluding the code that uses soft/hard-float, the vmlinux is identical with/without the flag. It does mean any code which is incorrectly intermingling soft & hard-float code will build without error, so those bugs will need to be caught by testing rather than at build time. For more background see: - commit d11219ad53dc ("amdgpu: disable powerpc support for the newer display engine") - commit c653c591789b ("drm/amdgpu: Re-enable DCN for 64-bit powerpc") - https://lore.kernel.org/r/dab9cbd8-2626-4b99-8098-31fe76397d2d@app.fastmail.com Signed-off-by: Michael Ellerman Reviewed-by: Segher Boessenkool Link: https://msgid.link/20230404102847.3303623-1-mpe@ellerman.id.au --- arch/powerpc/Kconfig | 4 ---- arch/powerpc/Makefile | 1 + drivers/gpu/drm/amd/display/Kconfig | 2 +- 3 files changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index fc4e81dafca7..3fb2c2766139 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -291,10 +291,6 @@ config PPC # Please keep this list sorted alphabetically. # -config PPC_LONG_DOUBLE_128 - depends on PPC64 && ALTIVEC - def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1) - config PPC_BARRIER_NOSPEC bool default y diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 12447b2361e4..4343cca57cb3 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -133,6 +133,7 @@ endif endif CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) +CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mlong-double-128) # Clang unconditionally reserves r2 on ppc32 and does not support the flag # https://bugs.llvm.org/show_bug.cgi?id=39555 diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 0c9bd0a53e60..e36261d546af 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -8,7 +8,7 @@ config DRM_AMD_DC depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64 select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 - select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128 || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG)) + select DRM_AMD_DC_DCN if (X86 || (PPC64 && ALTIVEC) || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG)) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and -- GitLab From c013e9f2bbe1d2be5e1c7f4a84216cd10837f20d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:28:57 +1000 Subject: [PATCH 2502/5631] powerpc: copy_thread remove unused pkey code The pkey registers (AMR, IAMR) do not get loaded from the switch frame so it is pointless to save anything there. Remove the dead code. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-2-npiggin@gmail.com --- arch/powerpc/kernel/process.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a7f9f3f85e20..7fe700309151 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1813,6 +1813,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) sp -= STACK_SWITCH_FRAME_SIZE; ((unsigned long *)sp)[0] = sp + STACK_SWITCH_FRAME_SIZE; kregs = (struct pt_regs *)(sp + STACK_SWITCH_FRAME_REGS); + kregs->nip = ppc_function_entry(f); p->thread.ksp = sp; #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -1845,17 +1846,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.tidr = 0; #endif - /* - * Run with the current AMR value of the kernel - */ -#ifdef CONFIG_PPC_PKEY - if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) - kregs->amr = AMR_KUAP_BLOCKED; - - if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) - kregs->iamr = AMR_KUEP_BLOCKED; -#endif - kregs->nip = ppc_function_entry(f); return 0; } -- GitLab From 959791e45fd2a580403e03611a5aefb9e7abcfc0 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:28:58 +1000 Subject: [PATCH 2503/5631] powerpc: copy_thread make ret_from_fork register setup consistent The ret_from_fork code for 64e and 32-bit set r3 for syscall_exit_prepare the same way that 64s does, so there should be no need to special-case them in copy_thread. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-3-npiggin@gmail.com --- arch/powerpc/kernel/entry_32.S | 2 +- arch/powerpc/kernel/process.c | 3 --- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 5604c9a1ac22..755408c63be8 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -183,7 +183,7 @@ syscall_exit_finish: ret_from_fork: REST_NVGPRS(r1) bl schedule_tail - li r3,0 + li r3,0 /* fork() return value */ b ret_from_syscall .globl ret_from_kernel_thread diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7fe700309151..18f697112193 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1784,9 +1784,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->gpr[1] = usp; ((unsigned long *)sp)[0] = childregs->gpr[1]; p->thread.regs = childregs; - /* 64s sets this in ret_from_fork */ - if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64)) - childregs->gpr[3] = 0; /* Result from fork() */ if (clone_flags & CLONE_SETTLS) { if (!is_32bit_task()) childregs->gpr[13] = tls; -- GitLab From af5ca9d5c8b45244b237d7a5534e1ec2d01cce8e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:28:59 +1000 Subject: [PATCH 2504/5631] powerpc: use switch frame for ret_from_kernel_thread parameters The kernel thread path in copy_thread creates a user interrupt frame on stack and stores the function and arg parameters there, and ret_from_kernel_thread loads them. This is a slightly confusing way to overload that frame. Non-volatile registers are loaded from the switch frame, so the parameters can be stored there. The user interrupt frame is now only used by user threads when they return to user. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-4-npiggin@gmail.com --- arch/powerpc/kernel/entry_32.S | 1 - arch/powerpc/kernel/interrupt_64.S | 1 - arch/powerpc/kernel/process.c | 13 +++++++++---- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 755408c63be8..c3fdb3081d3d 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -188,7 +188,6 @@ ret_from_fork: .globl ret_from_kernel_thread ret_from_kernel_thread: - REST_NVGPRS(r1) bl schedule_tail mtctr r14 mr r3,r15 diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index fccc34489add..d60e7e7564df 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -741,7 +741,6 @@ _GLOBAL(ret_from_fork) _GLOBAL(ret_from_kernel_thread) bl schedule_tail - REST_NVGPRS(r1) mtctr r14 mr r3,r15 #ifdef CONFIG_PPC64_ELF_ABI_V2 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 18f697112193..3b34bd9a6dff 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1765,14 +1765,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ((unsigned long *)sp)[0] = 0; memset(childregs, 0, sizeof(struct pt_regs)); childregs->gpr[1] = sp + STACK_USER_INT_FRAME_SIZE; - /* function */ - if (args->fn) - childregs->gpr[14] = ppc_function_entry((void *)args->fn); #ifdef CONFIG_PPC64 clear_tsk_thread_flag(p, TIF_32BIT); childregs->softe = IRQS_ENABLED; #endif - childregs->gpr[15] = (unsigned long)args->fn_arg; p->thread.regs = NULL; /* no user register state */ ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_thread; @@ -1811,6 +1807,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) ((unsigned long *)sp)[0] = sp + STACK_SWITCH_FRAME_SIZE; kregs = (struct pt_regs *)(sp + STACK_SWITCH_FRAME_REGS); kregs->nip = ppc_function_entry(f); + if (unlikely(args->fn)) { + /* + * Put kthread fn, arg parameters in non-volatile GPRs in the + * switch frame so they are loaded by _switch before it returns + * to ret_from_kernel_thread. + */ + kregs->gpr[14] = ppc_function_entry((void *)args->fn); + kregs->gpr[15] = (unsigned long)args->fn_arg; + } p->thread.ksp = sp; #ifdef CONFIG_HAVE_HW_BREAKPOINT -- GitLab From 5088a6246bd3dcfea504376f356683f750136f7f Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:29:00 +1000 Subject: [PATCH 2505/5631] powerpc/64: ret_from_fork avoid restoring regs twice If the system call return path always restores NVGPRs then there is no need for ret_from_fork to do it. The HANDLER_RESTORE_NVGPRS does the right thing for this. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-5-npiggin@gmail.com --- arch/powerpc/kernel/interrupt_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index d60e7e7564df..bac1f89501ac 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -728,14 +728,14 @@ DEFINE_FIXED_SYMBOL(__end_soft_masked, text) #ifdef CONFIG_PPC_BOOK3S _GLOBAL(ret_from_fork_scv) bl schedule_tail - REST_NVGPRS(r1) + HANDLER_RESTORE_NVGPRS() li r3,0 /* fork() return value */ b .Lsyscall_vectored_common_exit #endif _GLOBAL(ret_from_fork) bl schedule_tail - REST_NVGPRS(r1) + HANDLER_RESTORE_NVGPRS() li r3,0 /* fork() return value */ b .Lsyscall_exit -- GitLab From eed7c420aac7fde5e5915d2747c3ebbbda225835 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:29:01 +1000 Subject: [PATCH 2506/5631] powerpc: copy_thread differentiate kthreads and user mode threads When copy_thread is given a kernel function to run in arg->fn, this does not necessarily mean it is a kernel thread. User threads can be created this way (e.g., kernel_init, see also x86's copy_thread()). These threads run a kernel function which may call kernel_execve() and return, which returns like a userspace exec(2) syscall. Kernel threads are to be differentiated with PF_KTHREAD, will always have arg->fn set, and should never return from that function, instead calling kthread_exit() to exit. Create separate paths for the kthread and user kernel thread creation logic. The kthread path will never exit and does not require a user interrupt frame, so it gets a minimal stack frame. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-6-npiggin@gmail.com --- arch/powerpc/include/asm/thread_info.h | 2 + arch/powerpc/kernel/process.c | 98 ++++++++++++++++---------- 2 files changed, 64 insertions(+), 36 deletions(-) diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index cf13d84c4eb9..bf5dde1a4114 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -176,9 +176,11 @@ static inline bool test_thread_local_flags(unsigned int flags) #ifdef CONFIG_COMPAT #define is_32bit_task() (test_thread_flag(TIF_32BIT)) #define is_tsk_32bit_task(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT)) +#define clear_tsk_compat_task(tsk) (clear_tsk_thread_flag(p, TIF_32BIT)) #else #define is_32bit_task() (IS_ENABLED(CONFIG_PPC32)) #define is_tsk_32bit_task(tsk) (IS_ENABLED(CONFIG_PPC32)) +#define clear_tsk_compat_task(tsk) do { } while (0) #endif #if defined(CONFIG_PPC64) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 3b34bd9a6dff..88898ca7ab0b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1738,10 +1738,7 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp) */ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { - unsigned long clone_flags = args->flags; - unsigned long usp = args->stack; - unsigned long tls = args->tls; - struct pt_regs *childregs, *kregs; + struct pt_regs *kregs; /* Switch frame regs */ extern void ret_from_fork(void); extern void ret_from_fork_scv(void); extern void ret_from_kernel_thread(void); @@ -1754,45 +1751,76 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) klp_init_thread_info(p); - /* Create initial stack frame. */ - sp -= STACK_USER_INT_FRAME_SIZE; - *(unsigned long *)(sp + STACK_INT_FRAME_MARKER) = STACK_FRAME_REGS_MARKER; - - /* Copy registers */ - childregs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS); - if (unlikely(args->fn)) { + if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ + + /* Create initial minimum stack frame. */ + sp -= STACK_FRAME_MIN_SIZE; ((unsigned long *)sp)[0] = 0; - memset(childregs, 0, sizeof(struct pt_regs)); - childregs->gpr[1] = sp + STACK_USER_INT_FRAME_SIZE; -#ifdef CONFIG_PPC64 - clear_tsk_thread_flag(p, TIF_32BIT); - childregs->softe = IRQS_ENABLED; -#endif - p->thread.regs = NULL; /* no user register state */ - ti->flags |= _TIF_RESTOREALL; + f = ret_from_kernel_thread; + p->thread.regs = NULL; /* no user register state */ + clear_tsk_compat_task(p); } else { /* user thread */ - struct pt_regs *regs = current_pt_regs(); - *childregs = *regs; - if (usp) - childregs->gpr[1] = usp; - ((unsigned long *)sp)[0] = childregs->gpr[1]; - p->thread.regs = childregs; - if (clone_flags & CLONE_SETTLS) { - if (!is_32bit_task()) - childregs->gpr[13] = tls; + struct pt_regs *childregs; + + /* Create initial user return stack frame. */ + sp -= STACK_USER_INT_FRAME_SIZE; + *(unsigned long *)(sp + STACK_INT_FRAME_MARKER) = STACK_FRAME_REGS_MARKER; + + childregs = (struct pt_regs *)(sp + STACK_INT_FRAME_REGS); + + if (unlikely(args->fn)) { + /* + * A user space thread, but it first runs a kernel + * thread, and then returns as though it had called + * execve rather than fork, so user regs will be + * filled in (e.g., by kernel_execve()). + */ + ((unsigned long *)sp)[0] = 0; + memset(childregs, 0, sizeof(struct pt_regs)); +#ifdef CONFIG_PPC64 + childregs->softe = IRQS_ENABLED; +#endif + ti->flags |= _TIF_RESTOREALL; + f = ret_from_kernel_thread; + } else { + struct pt_regs *regs = current_pt_regs(); + unsigned long clone_flags = args->flags; + unsigned long usp = args->stack; + + /* Copy registers */ + *childregs = *regs; + if (usp) + childregs->gpr[1] = usp; + ((unsigned long *)sp)[0] = childregs->gpr[1]; +#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG + WARN_ON_ONCE(childregs->softe != IRQS_ENABLED); +#endif + if (clone_flags & CLONE_SETTLS) { + unsigned long tls = args->tls; + + if (!is_32bit_task()) + childregs->gpr[13] = tls; + else + childregs->gpr[2] = tls; + } + + if (trap_is_scv(regs)) + f = ret_from_fork_scv; else - childregs->gpr[2] = tls; + f = ret_from_fork; } - if (trap_is_scv(regs)) - f = ret_from_fork_scv; - else - f = ret_from_fork; +#ifdef CONFIG_PPC64 + if (cpu_has_feature(CPU_FTR_HAS_PPR)) + childregs->ppr = DEFAULT_PPR; +#endif + + childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); + p->thread.regs = childregs; } - childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); /* * The way this works is that at some point in the future @@ -1843,8 +1871,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.dscr_inherit = current->thread.dscr_inherit; p->thread.dscr = mfspr(SPRN_DSCR); } - if (cpu_has_feature(CPU_FTR_HAS_PPR)) - childregs->ppr = DEFAULT_PPR; p->thread.tidr = 0; #endif -- GitLab From b504b6aade0403eaffa9ce51b8207d710705beaf Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:29:02 +1000 Subject: [PATCH 2507/5631] powerpc: differentiate kthread from user kernel thread start Kernel created user threads start similarly to kernel threads in that they call a kernel function after first returning from _switch, so they share ret_from_kernel_thread for this. Kernel threads never return from that function though, whereas user threads often do (although some don't, e.g., IO threads). Split these startup functions in two, and catch kernel threads that improperly return from their function. This is intended to make the complicated code a little bit easier to understand. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-7-npiggin@gmail.com --- arch/powerpc/kernel/entry_32.S | 20 ++++++++++++++++++-- arch/powerpc/kernel/interrupt_64.S | 18 +++++++++++++++++- arch/powerpc/kernel/process.c | 7 ++++--- 3 files changed, 39 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index c3fdb3081d3d..47f0dd9a45ad 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -186,8 +186,8 @@ ret_from_fork: li r3,0 /* fork() return value */ b ret_from_syscall - .globl ret_from_kernel_thread -ret_from_kernel_thread: + .globl ret_from_kernel_user_thread +ret_from_kernel_user_thread: bl schedule_tail mtctr r14 mr r3,r15 @@ -196,6 +196,22 @@ ret_from_kernel_thread: li r3,0 b ret_from_syscall + .globl start_kernel_thread +start_kernel_thread: + bl schedule_tail + mtctr r14 + mr r3,r15 + PPC440EP_ERR42 + bctrl + /* + * This must not return. We actually want to BUG here, not WARN, + * because BUG will exit the process which is what the kernel thread + * should have done, which may give some hope of continuing. + */ +100: trap + EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0 + + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index bac1f89501ac..a44c8aab63ec 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -739,7 +739,7 @@ _GLOBAL(ret_from_fork) li r3,0 /* fork() return value */ b .Lsyscall_exit -_GLOBAL(ret_from_kernel_thread) +_GLOBAL(ret_from_kernel_user_thread) bl schedule_tail mtctr r14 mr r3,r15 @@ -749,3 +749,19 @@ _GLOBAL(ret_from_kernel_thread) bctrl li r3,0 b .Lsyscall_exit + +_GLOBAL(start_kernel_thread) + bl schedule_tail + mtctr r14 + mr r3,r15 +#ifdef CONFIG_PPC64_ELF_ABI_V2 + mr r12,r14 +#endif + bctrl + /* + * This must not return. We actually want to BUG here, not WARN, + * because BUG will exit the process which is what the kernel thread + * should have done, which may give some hope of continuing. + */ +100: trap + EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 88898ca7ab0b..14fe4702a098 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1741,7 +1741,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) struct pt_regs *kregs; /* Switch frame regs */ extern void ret_from_fork(void); extern void ret_from_fork_scv(void); - extern void ret_from_kernel_thread(void); + extern void ret_from_kernel_user_thread(void); + extern void start_kernel_thread(void); void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; struct thread_info *ti = task_thread_info(p); @@ -1758,7 +1759,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) sp -= STACK_FRAME_MIN_SIZE; ((unsigned long *)sp)[0] = 0; - f = ret_from_kernel_thread; + f = start_kernel_thread; p->thread.regs = NULL; /* no user register state */ clear_tsk_compat_task(p); } else { @@ -1784,7 +1785,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->softe = IRQS_ENABLED; #endif ti->flags |= _TIF_RESTOREALL; - f = ret_from_kernel_thread; + f = ret_from_kernel_user_thread; } else { struct pt_regs *regs = current_pt_regs(); unsigned long clone_flags = args->flags; -- GitLab From d195ce4695ca1061993424e2d6c8995e5fc81606 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:29:03 +1000 Subject: [PATCH 2508/5631] powerpc: copy_thread don't set _TIF_RESTOREALL In the kernel user thread path, don't set _TIF_RESTOREALL because the thread is required to call kernel_execve() before it returns, which will set _TIF_RESTOREALL if necessary via start_thread(). Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-8-npiggin@gmail.com --- arch/powerpc/kernel/interrupt_64.S | 5 +++++ arch/powerpc/kernel/process.c | 2 -- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index a44c8aab63ec..2a059214c1a9 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -748,6 +748,11 @@ _GLOBAL(ret_from_kernel_user_thread) #endif bctrl li r3,0 + /* + * It does not matter whether this returns via the scv or sc path + * because it returns as execve() and therefore has no calling ABI + * (i.e., it sets registers according to the exec()ed entry point). + */ b .Lsyscall_exit _GLOBAL(start_kernel_thread) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 14fe4702a098..2d90f39581fa 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1745,7 +1745,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) extern void start_kernel_thread(void); void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; - struct thread_info *ti = task_thread_info(p); #ifdef CONFIG_HAVE_HW_BREAKPOINT int i; #endif @@ -1784,7 +1783,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) #ifdef CONFIG_PPC64 childregs->softe = IRQS_ENABLED; #endif - ti->flags |= _TIF_RESTOREALL; f = ret_from_kernel_user_thread; } else { struct pt_regs *regs = current_pt_regs(); -- GitLab From 89fb39134ae3b1e1f207af44a037721d92b32f70 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 25 Mar 2023 22:29:04 +1000 Subject: [PATCH 2509/5631] powerpc: copy_thread don't set PPR in user interrupt frame regs syscalls do not set the PPR field in their interrupt frame and return from syscall always sets the default PPR for userspace, so setting the value in the ret_from_fork frame is not necessary and mildly inconsistent. Remove it. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230325122904.2375060-9-npiggin@gmail.com --- arch/powerpc/kernel/process.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 2d90f39581fa..1fefafb2b29b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1812,11 +1812,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) f = ret_from_fork; } -#ifdef CONFIG_PPC64 - if (cpu_has_feature(CPU_FTR_HAS_PPR)) - childregs->ppr = DEFAULT_PPR; -#endif - childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); p->thread.regs = childregs; } -- GitLab From 8002725b9e3369ce8616d32dc2e7a57870475142 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 6 Apr 2023 10:51:30 -0700 Subject: [PATCH 2510/5631] powerpc/32: Include thread_info.h in head_booke.h When building with W=1 after commit 80b6093b55e3 ("kbuild: add -Wundef to KBUILD_CPPFLAGS for W=1 builds"), the following warning occurs. In file included from arch/powerpc/kvm/bookehv_interrupts.S:26: arch/powerpc/kvm/../kernel/head_booke.h:20:6: warning: "THREAD_SHIFT" is not defined, evaluates to 0 [-Wundef] 20 | #if (THREAD_SHIFT < 15) | ^~~~~~~~~~~~ THREAD_SHIFT is defined in thread_info.h but it is not directly included in head_booke.h, so it is possible for THREAD_SHIFT to be undefined. Add the include to ensure that THREAD_SHIFT is always defined. Reported-by: kernel test robot Link: https://lore.kernel.org/202304050954.yskLdczH-lkp@intel.com/ Signed-off-by: Nathan Chancellor Reviewed-by: Masahiro Yamada Reviewed-by: Nick Desaulniers Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406-wundef-thread_shift_booke-v1-1-8deffa4d84f9@kernel.org --- arch/powerpc/kernel/head_booke.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 37d43c172676..b6b5b01a173c 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -5,6 +5,7 @@ #include /* for STACK_FRAME_REGS_MARKER */ #include #include +#include /* for THREAD_SHIFT */ #ifdef __ASSEMBLY__ -- GitLab From c1d889cf99b8f9b548f45d0d15b7d4108bbc715f Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 14:58:40 -0800 Subject: [PATCH 2511/5631] lockd: simplify two-level sysctl registration for nlm_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/lockd/svc.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a47303b2cba..bb94949bc223 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -510,24 +510,6 @@ static struct ctl_table nlm_sysctls[] = { { } }; -static struct ctl_table nlm_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nlm_sysctls, - }, - { } -}; - -static struct ctl_table nlm_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nlm_sysctl_dir, - }, - { } -}; - #endif /* CONFIG_SYSCTL */ /* @@ -644,7 +626,7 @@ static int __init init_nlm(void) #ifdef CONFIG_SYSCTL err = -ENOMEM; - nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root); + nlm_sysctl_table = register_sysctl("fs/nfs", nlm_sysctls); if (nlm_sysctl_table == NULL) goto err_sysctl; #endif -- GitLab From a2183160ca7e2bcb210954ad69d7cbf012fea0f1 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 14:58:41 -0800 Subject: [PATCH 2512/5631] nfs: simplify two-level sysctl registration for nfs4_cb_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/nfs4sysctl.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index c394e4447100..e776200e9a11 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -37,27 +37,10 @@ static struct ctl_table nfs4_cb_sysctls[] = { { } }; -static struct ctl_table nfs4_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs4_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs4_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs4_cb_sysctl_dir, - }, - { } -}; - int nfs4_register_sysctl(void) { - nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root); + nfs4_callback_sysctl_table = register_sysctl("fs/nfs", + nfs4_cb_sysctls); if (nfs4_callback_sysctl_table == NULL) return -ENOMEM; return 0; -- GitLab From 39724217447fc3b3ca76ff6fd5086e26165ba6d8 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 14:58:42 -0800 Subject: [PATCH 2513/5631] nfs: simplify two-level sysctl registration for nfs_cb_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- fs/nfs/sysctl.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index 7aea195ddb35..f39e2089bc4c 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -32,27 +32,9 @@ static struct ctl_table nfs_cb_sysctls[] = { { } }; -static struct ctl_table nfs_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs_cb_sysctl_dir, - }, - { } -}; - int nfs_register_sysctl(void) { - nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root); + nfs_callback_sysctl_table = register_sysctl("fs/nfs", nfs_cb_sysctls); if (nfs_callback_sysctl_table == NULL) return -ENOMEM; return 0; -- GitLab From 9c2598d43510eff09c658f9c0e0f921ba1871c4b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Mon, 3 Apr 2023 08:52:07 +0200 Subject: [PATCH 2514/5631] riscv: entry: Save a0 prior syscall_enter_from_user_mode() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The RISC-V calling convention passes the first argument, and the return value in the a0 register. For this reason, the a0 register needs some extra care; When handling syscalls, the a0 register is saved into regs->orig_a0, so a0 can be properly restored for, e.g. interrupted syscalls. This functionality was broken with the introduction of the generic entry patches. Here, a0 was saved into orig_a0 after calling syscall_enter_from_user_mode(), which can change regs->a0 for some paths, incorrectly restoring a0. This is resolved, by saving a0 prior doing the syscall_enter_from_user_mode() call. Fixes: f0bddf50586d ("riscv: entry: Convert to generic entry") Reviewed-by: Heiko Stuebner Tested-by: Heiko Stuebner Signed-off-by: Björn Töpel Reported-by: Conor Dooley Reviewed-by: Conor Dooley Tested-by: Conor Dooley Tested-by: Geert Uytterhoeven Tested-by: Andy Chiu Link: https://lore.kernel.org/r/20230403065207.1070974-1-bjorn@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/traps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 1f4e37be7eb3..8c258b78c925 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -270,11 +270,11 @@ asmlinkage __visible __trap_section void do_trap_ecall_u(struct pt_regs *regs) if (user_mode(regs)) { ulong syscall = regs->a7; - syscall = syscall_enter_from_user_mode(regs, syscall); - regs->epc += 4; regs->orig_a0 = regs->a0; + syscall = syscall_enter_from_user_mode(regs, syscall); + if (syscall < NR_syscalls) syscall_handler(regs, syscall); else -- GitLab From 4984563823f0034d3533854c1b50e729f5191089 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:23:59 -0700 Subject: [PATCH 2515/5631] KVM: nVMX: Emulate NOPs in L2, and PAUSE if it's not intercepted Extend VMX's nested intercept logic for emulated instructions to handle "pause" interception, in quotes because KVM's emulator doesn't filter out NOPs when checking for nested intercepts. Failure to allow emulation of NOPs results in KVM injecting a #UD into L2 on any NOP that collides with the emulator's definition of PAUSE, i.e. on all single-byte NOPs. For PAUSE itself, honor L1's PAUSE-exiting control, but ignore PLE to avoid unnecessarily injecting a #UD into L2. Per the SDM, the first execution of PAUSE after VM-Entry is treated as the beginning of a new loop, i.e. will never trigger a PLE VM-Exit, and so L1 can't expect any given execution of PAUSE to deterministically exit. ... the processor considers this execution to be the first execution of PAUSE in a loop. (It also does so for the first execution of PAUSE at CPL 0 after VM entry.) All that said, the PLE side of things is currently a moot point, as KVM doesn't expose PLE to L1. Note, vmx_check_intercept() is still wildly broken when L1 wants to intercept an instruction, as KVM injects a #UD instead of synthesizing a nested VM-Exit. That issue extends far beyond NOP/PAUSE and needs far more effort to fix, i.e. is a problem for the future. Fixes: 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode") Cc: Mathias Krause Cc: stable@vger.kernel.org Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20230405002359.418138-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/vmx/vmx.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d7bf14abdba1..e06fcd6144b0 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7935,6 +7935,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; -- GitLab From 17c6d0ce83406aebc98f8ce16c66f5416106963d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sat, 11 Mar 2023 15:39:41 -0800 Subject: [PATCH 2516/5631] sunrpc: simplify one-level sysctl registration for xr_tunables_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/transport.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 10bb2b929c6d..29b0562d62e7 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -140,15 +140,6 @@ static struct ctl_table xr_tunables_table[] = { { }, }; -static struct ctl_table sunrpc_table[] = { - { - .procname = "sunrpc", - .mode = 0555, - .child = xr_tunables_table - }, - { }, -}; - #endif static const struct rpc_xprt_ops xprt_rdma_procs; @@ -799,7 +790,7 @@ int xprt_rdma_init(void) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) - sunrpc_table_header = register_sysctl_table(sunrpc_table); + sunrpc_table_header = register_sysctl("sunrpc", xr_tunables_table); #endif return 0; } -- GitLab From c946cb69f238b2bd3e42790b8450f76b62b491f4 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sat, 11 Mar 2023 15:39:42 -0800 Subject: [PATCH 2517/5631] sunrpc: simplify one-level sysctl registration for xs_tunables_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- net/sunrpc/xprtsock.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 6cacd70a15ff..5f9030b81c9e 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -78,7 +78,7 @@ static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; /* * We can register our own files under /proc/sys/sunrpc by - * calling register_sysctl_table() again. The files in that + * calling register_sysctl() again. The files in that * directory become the union of all files registered there. * * We simply need to make sure that we don't collide with @@ -158,15 +158,6 @@ static struct ctl_table xs_tunables_table[] = { { }, }; -static struct ctl_table sunrpc_table[] = { - { - .procname = "sunrpc", - .mode = 0555, - .child = xs_tunables_table - }, - { }, -}; - /* * Wait duration for a reply from the RPC portmapper. */ @@ -3178,7 +3169,7 @@ static struct xprt_class xs_bc_tcp_transport = { int init_socket_xprt(void) { if (!sunrpc_table_header) - sunrpc_table_header = register_sysctl_table(sunrpc_table); + sunrpc_table_header = register_sysctl("sunrpc", xs_tunables_table); xprt_register_transport(&xs_local_transport); xprt_register_transport(&xs_udp_transport); -- GitLab From 32e356be32b6676d2d641ed4a4fe088c6d211d92 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sat, 11 Mar 2023 15:39:43 -0800 Subject: [PATCH 2518/5631] sunrpc: move sunrpc_table and proc routines above No need to do a forward declaration for sunrpc_table, just move the sysctls up as everyone else does it. This will make the next change easier to read. This change produces no functional changes. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- net/sunrpc/sysctl.c | 35 ++++++++++++++++------------------- 1 file changed, 16 insertions(+), 19 deletions(-) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 3aad6ef18504..afdfcc5403af 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -40,25 +40,6 @@ EXPORT_SYMBOL_GPL(nlm_debug); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -static struct ctl_table_header *sunrpc_table_header; -static struct ctl_table sunrpc_table[]; - -void -rpc_register_sysctl(void) -{ - if (!sunrpc_table_header) - sunrpc_table_header = register_sysctl_table(sunrpc_table); -} - -void -rpc_unregister_sysctl(void) -{ - if (sunrpc_table_header) { - unregister_sysctl_table(sunrpc_table_header); - sunrpc_table_header = NULL; - } -} - static int proc_do_xprt(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -142,6 +123,7 @@ proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp, return 0; } +static struct ctl_table_header *sunrpc_table_header; static struct ctl_table debug_table[] = { { @@ -190,4 +172,19 @@ static struct ctl_table sunrpc_table[] = { { } }; +void +rpc_register_sysctl(void) +{ + if (!sunrpc_table_header) + sunrpc_table_header = register_sysctl_table(sunrpc_table); +} + +void +rpc_unregister_sysctl(void) +{ + if (sunrpc_table_header) { + unregister_sysctl_table(sunrpc_table_header); + sunrpc_table_header = NULL; + } +} #endif -- GitLab From 703c6d03f165183b97526c182aa1d701b40f0453 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sat, 11 Mar 2023 15:39:44 -0800 Subject: [PATCH 2519/5631] sunrpc: simplify one-level sysctl registration for debug_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- net/sunrpc/sysctl.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index afdfcc5403af..93941ab12549 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -163,20 +163,11 @@ static struct ctl_table debug_table[] = { { } }; -static struct ctl_table sunrpc_table[] = { - { - .procname = "sunrpc", - .mode = 0555, - .child = debug_table - }, - { } -}; - void rpc_register_sysctl(void) { if (!sunrpc_table_header) - sunrpc_table_header = register_sysctl_table(sunrpc_table); + sunrpc_table_header = register_sysctl("sunrpc", debug_table); } void -- GitLab From 01c3a40084a42b7a242776d1e9f8e10d4e96c6ef Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:04 -0500 Subject: [PATCH 2520/5631] NFS: Rename readpage_async_filler to nfs_read_add_folio Rename readpage_async_filler to nfs_read_add_folio to better reflect what this function does (add a folio to the nfs_pageio_descriptor), and simplify arguments to this function by removing struct nfs_readdesc. Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- fs/nfs/read.c | 54 +++++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/fs/nfs/read.c b/fs/nfs/read.c index e90988591df4..8cb9e8d3c51d 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -127,11 +127,6 @@ static void nfs_readpage_release(struct nfs_page *req, int error) nfs_release_request(req); } -struct nfs_readdesc { - struct nfs_pageio_descriptor pgio; - struct nfs_open_context *ctx; -}; - static void nfs_page_group_set_uptodate(struct nfs_page *req) { if (nfs_page_group_sync_on_bit(req, PG_UPTODATE)) @@ -153,7 +148,8 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { /* note: regions of the page not covered by a - * request are zeroed in readpage_async_filler */ + * request are zeroed in nfs_read_add_folio + */ if (bytes > hdr->good_bytes) { /* nothing in this request was good, so zero * the full extent of the request */ @@ -281,7 +277,9 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } -static int readpage_async_filler(struct nfs_readdesc *desc, struct folio *folio) +static int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, + struct nfs_open_context *ctx, + struct folio *folio) { struct inode *inode = folio_file_mapping(folio)->host; struct nfs_server *server = NFS_SERVER(inode); @@ -303,15 +301,15 @@ static int readpage_async_filler(struct nfs_readdesc *desc, struct folio *folio) goto out_unlock; } - new = nfs_page_create_from_folio(desc->ctx, folio, 0, aligned_len); + new = nfs_page_create_from_folio(ctx, folio, 0, aligned_len); if (IS_ERR(new)) goto out_error; if (len < fsize) folio_zero_segment(folio, len, fsize); - if (!nfs_pageio_add_request(&desc->pgio, new)) { + if (!nfs_pageio_add_request(pgio, new)) { nfs_list_remove_request(new); - error = desc->pgio.pg_error; + error = pgio->pg_error; nfs_readpage_release(new, error); goto out; } @@ -332,8 +330,9 @@ static int readpage_async_filler(struct nfs_readdesc *desc, struct folio *folio) */ int nfs_read_folio(struct file *file, struct folio *folio) { - struct nfs_readdesc desc; struct inode *inode = file_inode(file); + struct nfs_pageio_descriptor pgio; + struct nfs_open_context *ctx; int ret; trace_nfs_aop_readpage(inode, folio); @@ -357,25 +356,25 @@ int nfs_read_folio(struct file *file, struct folio *folio) if (NFS_STALE(inode)) goto out_unlock; - desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); + ctx = get_nfs_open_context(nfs_file_open_context(file)); - xchg(&desc.ctx->error, 0); - nfs_pageio_init_read(&desc.pgio, inode, false, + xchg(&ctx->error, 0); + nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); - ret = readpage_async_filler(&desc, folio); + ret = nfs_read_add_folio(&pgio, ctx, folio); if (ret) goto out; - nfs_pageio_complete_read(&desc.pgio); - ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; + nfs_pageio_complete_read(&pgio); + ret = pgio.pg_error < 0 ? pgio.pg_error : 0; if (!ret) { ret = folio_wait_locked_killable(folio); if (!folio_test_uptodate(folio) && !ret) - ret = xchg(&desc.ctx->error, 0); + ret = xchg(&ctx->error, 0); } out: - put_nfs_open_context(desc.ctx); + put_nfs_open_context(ctx); trace_nfs_aop_readpage_done(inode, folio, ret); return ret; out_unlock: @@ -386,9 +385,10 @@ int nfs_read_folio(struct file *file, struct folio *folio) void nfs_readahead(struct readahead_control *ractl) { + struct nfs_pageio_descriptor pgio; + struct nfs_open_context *ctx; unsigned int nr_pages = readahead_count(ractl); struct file *file = ractl->file; - struct nfs_readdesc desc; struct inode *inode = ractl->mapping->host; struct folio *folio; int ret; @@ -403,24 +403,24 @@ void nfs_readahead(struct readahead_control *ractl) if (file == NULL) { ret = -EBADF; - desc.ctx = nfs_find_open_context(inode, NULL, FMODE_READ); - if (desc.ctx == NULL) + ctx = nfs_find_open_context(inode, NULL, FMODE_READ); + if (ctx == NULL) goto out; } else - desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); + ctx = get_nfs_open_context(nfs_file_open_context(file)); - nfs_pageio_init_read(&desc.pgio, inode, false, + nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); while ((folio = readahead_folio(ractl)) != NULL) { - ret = readpage_async_filler(&desc, folio); + ret = nfs_read_add_folio(&pgio, ctx, folio); if (ret) break; } - nfs_pageio_complete_read(&desc.pgio); + nfs_pageio_complete_read(&pgio); - put_nfs_open_context(desc.ctx); + put_nfs_open_context(ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); } -- GitLab From 88a4d7bdeec97890cd543b58dd3588f1f879f51b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:05 -0500 Subject: [PATCH 2521/5631] NFS: Configure support for netfs when NFS fscache is configured As first steps for support of the netfs library when NFS_FSCACHE is configured, add NETFS_SUPPORT to Kconfig and add the required netfs_inode into struct nfs_inode. Using netfs requires we move the VFS inode structure to be stored inside struct netfs_inode, along with the fscache_cookie. Thus, if NFS_FSCACHE is configured, place netfs_inode inside an anonymous union so the vfs_inode memory is the same and we do not need to modify other non-fscache areas of NFS. In addition, inside the NFS fscache code, use the new helpers, netfs_inode() and netfs_i_cookie() helpers, and remove our own helper, nfs_i_fscache(). Later patches will convert NFS fscache to fully use netfs. Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- fs/nfs/Kconfig | 1 + fs/nfs/fscache.c | 20 +++++++++----------- fs/nfs/fscache.h | 15 ++++++--------- include/linux/nfs_fs.h | 24 ++++++++++-------------- 4 files changed, 26 insertions(+), 34 deletions(-) diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index c1c7ed2fd860..b6fc169be1b1 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -170,6 +170,7 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y + select NETFS_SUPPORT help Say Y here if you want NFS data to be cached locally on disc through the general filesystem cache manager diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index ea5f2976dfab..3b4dafa771bd 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -163,13 +163,14 @@ void nfs_fscache_init_inode(struct inode *inode) struct nfs_server *nfss = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); - nfsi->fscache = NULL; + netfs_inode(inode)->cache = NULL; if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; nfs_fscache_update_auxdata(&auxdata, inode); - nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, + netfs_inode(inode)->cache = fscache_acquire_cookie( + nfss->fscache, 0, nfsi->fh.data, /* index_key */ nfsi->fh.size, @@ -183,11 +184,8 @@ void nfs_fscache_init_inode(struct inode *inode) */ void nfs_fscache_clear_inode(struct inode *inode) { - struct nfs_inode *nfsi = NFS_I(inode); - struct fscache_cookie *cookie = nfs_i_fscache(inode); - - fscache_relinquish_cookie(cookie, false); - nfsi->fscache = NULL; + fscache_relinquish_cookie(netfs_i_cookie(netfs_inode(inode)), false); + netfs_inode(inode)->cache = NULL; } /* @@ -212,7 +210,7 @@ void nfs_fscache_clear_inode(struct inode *inode) void nfs_fscache_open_file(struct inode *inode, struct file *filp) { struct nfs_fscache_inode_auxdata auxdata; - struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode)); bool open_for_write = inode_is_open_for_write(inode); if (!fscache_cookie_valid(cookie)) @@ -230,7 +228,7 @@ EXPORT_SYMBOL_GPL(nfs_fscache_open_file); void nfs_fscache_release_file(struct inode *inode, struct file *filp) { struct nfs_fscache_inode_auxdata auxdata; - struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct fscache_cookie *cookie = netfs_i_cookie(netfs_inode(inode)); loff_t i_size = i_size_read(inode); nfs_fscache_update_auxdata(&auxdata, inode); @@ -243,7 +241,7 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) static int fscache_fallback_read_page(struct inode *inode, struct page *page) { struct netfs_cache_resources cres; - struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct fscache_cookie *cookie = netfs_i_cookie(&NFS_I(inode)->netfs); struct iov_iter iter; struct bio_vec bvec; int ret; @@ -269,7 +267,7 @@ static int fscache_fallback_write_page(struct inode *inode, struct page *page, bool no_space_allocated_yet) { struct netfs_cache_resources cres; - struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct fscache_cookie *cookie = netfs_i_cookie(&NFS_I(inode)->netfs); struct iov_iter iter; struct bio_vec bvec; loff_t start = page_offset(page); diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 2a37af880978..38614ed8f951 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -54,7 +54,7 @@ static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) if (current_is_kswapd() || !(gfp & __GFP_FS)) return false; folio_wait_fscache(folio); - fscache_note_page_release(nfs_i_fscache(folio->mapping->host)); + fscache_note_page_release(netfs_i_cookie(&NFS_I(folio->mapping->host)->netfs)); nfs_inc_fscache_stats(folio->mapping->host, NFSIOS_FSCACHE_PAGES_UNCACHED); } @@ -66,7 +66,7 @@ static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) */ static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) { - if (nfs_i_fscache(inode)) + if (netfs_inode(inode)->cache) return __nfs_fscache_read_page(inode, page); return -ENOBUFS; } @@ -78,7 +78,7 @@ static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) { - if (nfs_i_fscache(inode)) + if (netfs_inode(inode)->cache) __nfs_fscache_write_page(inode, page); } @@ -101,13 +101,10 @@ static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata * static inline void nfs_fscache_invalidate(struct inode *inode, int flags) { struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = NFS_I(inode); + struct fscache_cookie *cookie = netfs_i_cookie(&NFS_I(inode)->netfs); - if (nfsi->fscache) { - nfs_fscache_update_auxdata(&auxdata, inode); - fscache_invalidate(nfsi->fscache, &auxdata, - i_size_read(inode), flags); - } + nfs_fscache_update_auxdata(&auxdata, inode); + fscache_invalidate(cookie, &auxdata, i_size_read(inode), flags); } /* diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf89fe6fc3ba..041e79a48f7a 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include #include +#ifdef CONFIG_NFS_FSCACHE +#include +#endif + #include #include #include @@ -204,14 +208,15 @@ struct nfs_inode { /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; - #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif + union { + struct inode vfs_inode; +#ifdef CONFIG_NFS_FSCACHE + struct netfs_inode netfs; /* netfs context and VFS inode */ +#endif + }; }; struct nfs4_copy_state { @@ -329,15 +334,6 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } -static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode) -{ -#ifdef CONFIG_NFS_FSCACHE - return NFS_I(inode)->fscache; -#else - return NULL; -#endif -} - static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; -- GitLab From 000dbe0bec058cbf2ca9e156e4a5584f5158b0f9 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:06 -0500 Subject: [PATCH 2522/5631] NFS: Convert buffered read paths to use netfs when fscache is enabled Convert the NFS buffered read code paths to corresponding netfs APIs, but only when fscache is configured and enabled. The netfs API defines struct netfs_request_ops which must be filled in by the network filesystem. For NFS, we only need to define 5 of the functions, the main one being the issue_read() function. The issue_read() function is called by the netfs layer when a read cannot be fulfilled locally, and must be sent to the server (either the cache is not active, or it is active but the data is not available). Once the read from the server is complete, netfs requires a call to netfs_subreq_terminated() which conveys either how many bytes were read successfully, or an error. Note that issue_read() is called with a structure, netfs_io_subrequest, which defines the IO requested, and contains a start and a length (both in bytes), and assumes the underlying netfs will return a either an error on the whole region, or the number of bytes successfully read. The NFS IO path is page based and the main APIs are the pgio APIs defined in pagelist.c. For the pgio APIs, there is no way for the caller to know how many RPCs will be sent and how the pages will be broken up into underlying RPCs, each of which will have their own completion and return code. In contrast, netfs is subrequest based, a single subrequest may contain multiple pages, and a single subrequest is initiated with issue_read() and terminated with netfs_subreq_terminated(). Thus, to utilze the netfs APIs, NFS needs some way to accommodate the netfs API requirement on the single response to the whole subrequest, while also minimizing disruptive changes to the NFS pgio layer. The approach taken with this patch is to allocate a small structure for each nfs_netfs_issue_read() call, store the final error and number of bytes successfully transferred in the structure, and update these values as each RPC completes. The refcount on the structure is used as a marker for the last RPC completion, is incremented in nfs_netfs_read_initiate(), and decremented inside nfs_netfs_read_completion(), when a nfs_pgio_header contains a valid pointer to the data. On the final put (which signals the final outstanding RPC is complete) in nfs_netfs_read_completion(), call netfs_subreq_terminated() with either the final error value (if one or more READs complete with an error) or the number of bytes successfully transferred (if all RPCs complete successfully). Note that when all RPCs complete successfully, the number of bytes transferred is capped to the length of the subrequest. Capping the transferred length to the subrequest length prevents "Subreq overread" warnings from netfs. This is due to the "aligned_len" in nfs_pageio_add_page(), and the corner case where NFS requests a full page at the end of the file, even when i_size reflects only a partial page (NFS overread). Signed-off-by: Dave Wysochanski Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- fs/nfs/fscache.c | 222 ++++++++++++++++++++++++--------------- fs/nfs/fscache.h | 122 +++++++++++++++------ fs/nfs/inode.c | 2 + fs/nfs/internal.h | 9 ++ fs/nfs/pagelist.c | 4 + fs/nfs/read.c | 61 +++++------ include/linux/nfs_page.h | 3 + include/linux/nfs_xdr.h | 3 + 8 files changed, 274 insertions(+), 152 deletions(-) diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 3b4dafa771bd..95c2b3056e2b 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -15,6 +15,9 @@ #include #include #include +#include +#include +#include #include "internal.h" #include "iostat.h" @@ -235,108 +238,153 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) fscache_unuse_cookie(cookie, &auxdata, &i_size); } -/* - * Fallback page reading interface. - */ -static int fscache_fallback_read_page(struct inode *inode, struct page *page) +int nfs_netfs_read_folio(struct file *file, struct folio *folio) { - struct netfs_cache_resources cres; - struct fscache_cookie *cookie = netfs_i_cookie(&NFS_I(inode)->netfs); - struct iov_iter iter; - struct bio_vec bvec; - int ret; - - memset(&cres, 0, sizeof(cres)); - bvec_set_page(&bvec, page, PAGE_SIZE, 0); - iov_iter_bvec(&iter, ITER_DEST, &bvec, 1, PAGE_SIZE); - - ret = fscache_begin_read_operation(&cres, cookie); - if (ret < 0) - return ret; - - ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, - NULL, NULL); - fscache_end_operation(&cres); - return ret; + if (!netfs_inode(folio_inode(folio))->cache) + return -ENOBUFS; + + return netfs_read_folio(file, folio); } -/* - * Fallback page writing interface. - */ -static int fscache_fallback_write_page(struct inode *inode, struct page *page, - bool no_space_allocated_yet) +int nfs_netfs_readahead(struct readahead_control *ractl) { - struct netfs_cache_resources cres; - struct fscache_cookie *cookie = netfs_i_cookie(&NFS_I(inode)->netfs); - struct iov_iter iter; - struct bio_vec bvec; - loff_t start = page_offset(page); - size_t len = PAGE_SIZE; - int ret; - - memset(&cres, 0, sizeof(cres)); - bvec_set_page(&bvec, page, PAGE_SIZE, 0); - iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); - - ret = fscache_begin_write_operation(&cres, cookie); - if (ret < 0) - return ret; - - ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), - no_space_allocated_yet); - if (ret == 0) - ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); - fscache_end_operation(&cres); - return ret; + struct inode *inode = ractl->mapping->host; + + if (!netfs_inode(inode)->cache) + return -ENOBUFS; + + netfs_readahead(ractl); + return 0; } -/* - * Retrieve a page from fscache - */ -int __nfs_fscache_read_page(struct inode *inode, struct page *page) +atomic_t nfs_netfs_debug_id; +static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { - int ret; + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); + rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); - trace_nfs_fscache_read_page(inode, page); - if (PageChecked(page)) { - ClearPageChecked(page); - ret = 1; - goto out; - } + return 0; +} - ret = fscache_fallback_read_page(inode, page); - if (ret < 0) { - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - SetPageChecked(page); - goto out; - } +static void nfs_netfs_free_request(struct netfs_io_request *rreq) +{ + put_nfs_open_context(rreq->netfs_priv); +} - /* Read completed synchronously */ - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); - SetPageUptodate(page); - ret = 0; -out: - trace_nfs_fscache_read_page_exit(inode, page, ret); - return ret; +static inline int nfs_netfs_begin_cache_operation(struct netfs_io_request *rreq) +{ + return fscache_begin_read_operation(&rreq->cache_resources, + netfs_i_cookie(netfs_inode(rreq->inode))); } -/* - * Store a newly fetched page in fscache. We can be certain there's no page - * stored in the cache as yet otherwise we would've read it from there. - */ -void __nfs_fscache_write_page(struct inode *inode, struct page *page) +static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) { - int ret; + struct nfs_netfs_io_data *netfs; + + netfs = kzalloc(sizeof(*netfs), GFP_KERNEL_ACCOUNT); + if (!netfs) + return NULL; + netfs->sreq = sreq; + refcount_set(&netfs->refcount, 1); + return netfs; +} - trace_nfs_fscache_write_page(inode, page); +static bool nfs_netfs_clamp_length(struct netfs_io_subrequest *sreq) +{ + size_t rsize = NFS_SB(sreq->rreq->inode->i_sb)->rsize; - ret = fscache_fallback_write_page(inode, page, true); + sreq->len = min(sreq->len, rsize); + return true; +} - if (ret != 0) { - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); - } else { - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); +static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) +{ + struct nfs_netfs_io_data *netfs; + struct nfs_pageio_descriptor pgio; + struct inode *inode = sreq->rreq->inode; + struct nfs_open_context *ctx = sreq->rreq->netfs_priv; + struct page *page; + int err; + pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; + pgoff_t last = ((sreq->start + sreq->len - + sreq->transferred - 1) >> PAGE_SHIFT); + XA_STATE(xas, &sreq->rreq->mapping->i_pages, start); + + nfs_pageio_init_read(&pgio, inode, false, + &nfs_async_read_completion_ops); + + netfs = nfs_netfs_alloc(sreq); + if (!netfs) + return netfs_subreq_terminated(sreq, -ENOMEM, false); + + pgio.pg_netfs = netfs; /* used in completion */ + + xas_lock(&xas); + xas_for_each(&xas, page, last) { + /* nfs_read_add_folio() may schedule() due to pNFS layout and other RPCs */ + xas_pause(&xas); + xas_unlock(&xas); + err = nfs_read_add_folio(&pgio, ctx, page_folio(page)); + if (err < 0) { + netfs->error = err; + goto out; + } + xas_lock(&xas); } - trace_nfs_fscache_write_page_exit(inode, page, ret); + xas_unlock(&xas); +out: + nfs_pageio_complete_read(&pgio); + nfs_netfs_put(netfs); } + +void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr) +{ + struct nfs_netfs_io_data *netfs = hdr->netfs; + + if (!netfs) + return; + + nfs_netfs_get(netfs); +} + +int nfs_netfs_folio_unlock(struct folio *folio) +{ + struct inode *inode = folio_file_mapping(folio)->host; + + /* + * If fscache is enabled, netfs will unlock pages. + */ + if (netfs_inode(inode)->cache) + return 0; + + return 1; +} + +void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) +{ + struct nfs_netfs_io_data *netfs = hdr->netfs; + struct netfs_io_subrequest *sreq; + + if (!netfs) + return; + + sreq = netfs->sreq; + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags); + + if (hdr->error) + netfs->error = hdr->error; + else + atomic64_add(hdr->res.count, &netfs->transferred); + + nfs_netfs_put(netfs); + hdr->netfs = NULL; +} + +const struct netfs_request_ops nfs_netfs_ops = { + .init_request = nfs_netfs_init_request, + .free_request = nfs_netfs_free_request, + .begin_cache_operation = nfs_netfs_begin_cache_operation, + .issue_read = nfs_netfs_issue_read, + .clamp_length = nfs_netfs_clamp_length +}; diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 38614ed8f951..e1706e736c64 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -34,6 +34,58 @@ struct nfs_fscache_inode_auxdata { u64 change_attr; }; +struct nfs_netfs_io_data { + /* + * NFS may split a netfs_io_subrequest into multiple RPCs, each + * with their own read completion. In netfs, we can only call + * netfs_subreq_terminated() once for each subrequest. Use the + * refcount here to double as a marker of the last RPC completion, + * and only call netfs via netfs_subreq_terminated() once. + */ + refcount_t refcount; + struct netfs_io_subrequest *sreq; + + /* + * Final disposition of the netfs_io_subrequest, sent in + * netfs_subreq_terminated() + */ + atomic64_t transferred; + int error; +}; + +static inline void nfs_netfs_get(struct nfs_netfs_io_data *netfs) +{ + refcount_inc(&netfs->refcount); +} + +static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) +{ + ssize_t final_len; + + /* Only the last RPC completion should call netfs_subreq_terminated() */ + if (!refcount_dec_and_test(&netfs->refcount)) + return; + + /* + * The NFS pageio interface may read a complete page, even when netfs + * only asked for a partial page. Specifically, this may be seen when + * one thread is truncating a file while another one is reading the last + * page of the file. + * Correct the final length here to be no larger than the netfs subrequest + * length, and thus avoid netfs's "Subreq overread" warning message. + */ + final_len = min_t(s64, netfs->sreq->len, atomic64_read(&netfs->transferred)); + netfs_subreq_terminated(netfs->sreq, netfs->error ?: final_len, false); + kfree(netfs); +} +static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) +{ + netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops); +} +extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); +extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); +extern int nfs_netfs_folio_unlock(struct folio *folio); + /* * fscache.c */ @@ -44,9 +96,8 @@ extern void nfs_fscache_init_inode(struct inode *); extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); extern void nfs_fscache_release_file(struct inode *, struct file *); - -extern int __nfs_fscache_read_page(struct inode *, struct page *); -extern void __nfs_fscache_write_page(struct inode *, struct page *); +extern int nfs_netfs_readahead(struct readahead_control *ractl); +extern int nfs_netfs_read_folio(struct file *file, struct folio *folio); static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) { @@ -54,34 +105,11 @@ static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) if (current_is_kswapd() || !(gfp & __GFP_FS)) return false; folio_wait_fscache(folio); - fscache_note_page_release(netfs_i_cookie(&NFS_I(folio->mapping->host)->netfs)); - nfs_inc_fscache_stats(folio->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); } + fscache_note_page_release(netfs_i_cookie(netfs_inode(folio->mapping->host))); return true; } -/* - * Retrieve a page from an inode data storage object. - */ -static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) -{ - if (netfs_inode(inode)->cache) - return __nfs_fscache_read_page(inode, page); - return -ENOBUFS; -} - -/* - * Store a page newly fetched from the server in an inode data storage object - * in the cache. - */ -static inline void nfs_fscache_write_page(struct inode *inode, - struct page *page) -{ - if (netfs_inode(inode)->cache) - __nfs_fscache_write_page(inode, page); -} - static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, struct inode *inode) { @@ -117,7 +145,28 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server) return "no "; } +static inline void nfs_netfs_set_pgio_header(struct nfs_pgio_header *hdr, + struct nfs_pageio_descriptor *desc) +{ + hdr->netfs = desc->pg_netfs; +} +static inline void nfs_netfs_set_pageio_descriptor(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + desc->pg_netfs = hdr->netfs; +} +static inline void nfs_netfs_reset_pageio_descriptor(struct nfs_pageio_descriptor *desc) +{ + desc->pg_netfs = NULL; +} #else /* CONFIG_NFS_FSCACHE */ +static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) {} +static inline void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr) {} +static inline void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) {} +static inline int nfs_netfs_folio_unlock(struct folio *folio) +{ + return 1; +} static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode(struct inode *inode) {} @@ -125,22 +174,29 @@ static inline void nfs_fscache_clear_inode(struct inode *inode) {} static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} - -static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) +static inline int nfs_netfs_readahead(struct readahead_control *ractl) { - return true; /* may release folio */ + return -ENOBUFS; } -static inline int nfs_fscache_read_page(struct inode *inode, struct page *page) +static inline int nfs_netfs_read_folio(struct file *file, struct folio *folio) { return -ENOBUFS; } -static inline void nfs_fscache_write_page(struct inode *inode, struct page *page) {} + +static inline bool nfs_fscache_release_folio(struct folio *folio, gfp_t gfp) +{ + return true; /* may release folio */ +} static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) { return "no "; } - +static inline void nfs_netfs_set_pgio_header(struct nfs_pgio_header *hdr, + struct nfs_pageio_descriptor *desc) {} +static inline void nfs_netfs_set_pageio_descriptor(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) {} +static inline void nfs_netfs_reset_pageio_descriptor(struct nfs_pageio_descriptor *desc) {} #endif /* CONFIG_NFS_FSCACHE */ #endif /* _NFS_FSCACHE_H */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 222a28320e1c..5c8027e3c961 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2254,6 +2254,8 @@ struct inode *nfs_alloc_inode(struct super_block *sb) #ifdef CONFIG_NFS_V4_2 nfsi->xattr_cache = NULL; #endif + nfs_netfs_inode_init(nfsi); + return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2a65fe2a63ab..9ba07553eab8 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -452,6 +452,10 @@ extern void nfs_sb_deactive(struct super_block *sb); extern int nfs_client_for_each_server(struct nfs_client *clp, int (*fn)(struct nfs_server *, void *), void *data); +#ifdef CONFIG_NFS_FSCACHE +extern const struct netfs_request_ops nfs_netfs_ops; +#endif + /* io.c */ extern void nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); @@ -481,9 +485,14 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool struct nfs_pgio_completion_ops; /* read.c */ +extern const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, bool force_mds, const struct nfs_pgio_completion_ops *compl_ops); +extern int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, + struct nfs_open_context *ctx, + struct folio *folio); +extern void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 64fa8de199de..6efb5068c116 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -26,6 +26,7 @@ #include "internal.h" #include "pnfs.h" #include "nfstrace.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -105,6 +106,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->good_bytes = mirror->pg_count; hdr->io_completion = desc->pg_io_completion; hdr->dreq = desc->pg_dreq; + nfs_netfs_set_pgio_header(hdr, desc); hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -941,6 +943,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_lseg = NULL; desc->pg_io_completion = NULL; desc->pg_dreq = NULL; + nfs_netfs_reset_pageio_descriptor(desc); desc->pg_bsize = bsize; desc->pg_mirror_count = 1; @@ -1477,6 +1480,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, desc->pg_io_completion = hdr->io_completion; desc->pg_dreq = hdr->dreq; + nfs_netfs_set_pageio_descriptor(desc, hdr); list_splice_init(&hdr->pages, &pages); while (!list_empty(&pages)) { struct nfs_page *req = nfs_list_entry(pages.next); diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 8cb9e8d3c51d..f71eeee67e20 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -31,7 +31,7 @@ #define NFSDBG_FACILITY NFSDBG_PAGECACHE -static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; +const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; static const struct nfs_rw_ops nfs_rw_read_ops; static struct kmem_cache *nfs_rdata_cachep; @@ -74,7 +74,7 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); -static void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio) +void nfs_pageio_complete_read(struct nfs_pageio_descriptor *pgio) { struct nfs_pgio_mirror *pgm; unsigned long npages; @@ -110,20 +110,14 @@ EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); static void nfs_readpage_release(struct nfs_page *req, int error) { - struct inode *inode = d_inode(nfs_req_openctx(req)->dentry); struct folio *folio = nfs_page_to_folio(req); - dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id, - (unsigned long long)NFS_FILEID(inode), req->wb_bytes, - (long long)req_offset(req)); - if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT) folio_set_error(folio); - if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) { - if (folio_test_uptodate(folio)) - nfs_fscache_write_page(inode, &folio->page); - folio_unlock(folio); - } + if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) + if (nfs_netfs_folio_unlock(folio)) + folio_unlock(folio); + nfs_release_request(req); } @@ -177,6 +171,8 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); nfs_readpage_release(req, error); } + nfs_netfs_read_completion(hdr); + out: hdr->release(hdr); } @@ -187,6 +183,7 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, struct rpc_task_setup *task_setup_data, int how) { rpc_ops->read_setup(hdr, msg); + nfs_netfs_initiate_read(hdr); trace_nfs_initiate_read(hdr); } @@ -202,7 +199,7 @@ nfs_async_read_error(struct list_head *head, int error) } } -static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { +const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { .error_cleanup = nfs_async_read_error, .completion = nfs_read_completion, }; @@ -277,9 +274,9 @@ static void nfs_readpage_result(struct rpc_task *task, nfs_readpage_retry(task, hdr); } -static int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, - struct nfs_open_context *ctx, - struct folio *folio) +int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, + struct nfs_open_context *ctx, + struct folio *folio) { struct inode *inode = folio_file_mapping(folio)->host; struct nfs_server *server = NFS_SERVER(inode); @@ -295,15 +292,11 @@ static int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, aligned_len = min_t(unsigned int, ALIGN(len, rsize), fsize); - if (!IS_SYNC(inode)) { - error = nfs_fscache_read_page(inode, &folio->page); - if (error == 0) - goto out_unlock; - } - new = nfs_page_create_from_folio(ctx, folio, 0, aligned_len); - if (IS_ERR(new)) - goto out_error; + if (IS_ERR(new)) { + error = PTR_ERR(new); + goto out; + } if (len < fsize) folio_zero_segment(folio, len, fsize); @@ -314,10 +307,6 @@ static int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, goto out; } return 0; -out_error: - error = PTR_ERR(new); -out_unlock: - folio_unlock(folio); out: return error; } @@ -356,6 +345,10 @@ int nfs_read_folio(struct file *file, struct folio *folio) if (NFS_STALE(inode)) goto out_unlock; + ret = nfs_netfs_read_folio(file, folio); + if (!ret) + goto out; + ctx = get_nfs_open_context(nfs_file_open_context(file)); xchg(&ctx->error, 0); @@ -364,7 +357,7 @@ int nfs_read_folio(struct file *file, struct folio *folio) ret = nfs_read_add_folio(&pgio, ctx, folio); if (ret) - goto out; + goto out_put; nfs_pageio_complete_read(&pgio); ret = pgio.pg_error < 0 ? pgio.pg_error : 0; @@ -373,14 +366,14 @@ int nfs_read_folio(struct file *file, struct folio *folio) if (!folio_test_uptodate(folio) && !ret) ret = xchg(&ctx->error, 0); } -out: +out_put: put_nfs_open_context(ctx); +out: trace_nfs_aop_readpage_done(inode, folio, ret); return ret; out_unlock: folio_unlock(folio); - trace_nfs_aop_readpage_done(inode, folio, ret); - return ret; + goto out; } void nfs_readahead(struct readahead_control *ractl) @@ -401,6 +394,10 @@ void nfs_readahead(struct readahead_control *ractl) if (NFS_STALE(inode)) goto out; + ret = nfs_netfs_readahead(ractl); + if (!ret) + goto out; + if (file == NULL) { ret = -EBADF; ctx = nfs_find_open_context(inode, NULL, FMODE_READ); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index a2f1ca657623..aa9f4c6ebe26 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -105,6 +105,9 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; +#ifdef CONFIG_NFS_FSCACHE + void *pg_netfs; +#endif unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..e196ef595908 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1619,6 +1619,9 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; +#ifdef CONFIG_NFS_FSCACHE + void *netfs; +#endif int pnfs_error; int error; /* merge with pnfs_error */ -- GitLab From 0631d5e02a1c722b90c11a47dcb6d83ef88ab47b Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:07 -0500 Subject: [PATCH 2523/5631] NFS: Remove all NFSIOS_FSCACHE counters due to conversion to netfs API The old NFSIOS_FSCACHE counters are no longer accurate or useful with the conversion to the new netfs API. The new API does not have a page based interface, and so the counters in nfs_stat_fscachecounters are no longer obtainable. The new netfs the API has extensive statistics inside /proc/fs/fscache/stats so we no longer need NFS specific fscache stats. Note this also removes the 'fsc:' line from /proc/self/mountstats so it will be a user-visible change. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- fs/nfs/iostat.h | 17 ----------------- fs/nfs/super.c | 11 ----------- include/linux/nfs_iostat.h | 12 ------------ 3 files changed, 40 deletions(-) diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h index 2ddaab1ac653..5aa776b5a3e7 100644 --- a/fs/nfs/iostat.h +++ b/fs/nfs/iostat.h @@ -17,9 +17,6 @@ struct nfs_iostats { unsigned long long bytes[__NFSIOS_BYTESMAX]; -#ifdef CONFIG_NFS_FSCACHE - unsigned long long fscache[__NFSIOS_FSCACHEMAX]; -#endif unsigned long events[__NFSIOS_COUNTSMAX]; } ____cacheline_aligned; @@ -49,20 +46,6 @@ static inline void nfs_add_stats(const struct inode *inode, nfs_add_server_stats(NFS_SERVER(inode), stat, addend); } -#ifdef CONFIG_NFS_FSCACHE -static inline void nfs_add_fscache_stats(struct inode *inode, - enum nfs_stat_fscachecounters stat, - long addend) -{ - this_cpu_add(NFS_SERVER(inode)->io_stats->fscache[stat], addend); -} -static inline void nfs_inc_fscache_stats(struct inode *inode, - enum nfs_stat_fscachecounters stat) -{ - this_cpu_inc(NFS_SERVER(inode)->io_stats->fscache[stat]); -} -#endif - static inline struct nfs_iostats __percpu *nfs_alloc_iostats(void) { return alloc_percpu(struct nfs_iostats); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 05ae23657527..90796db8c205 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -692,10 +692,6 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) totals.events[i] += stats->events[i]; for (i = 0; i < __NFSIOS_BYTESMAX; i++) totals.bytes[i] += stats->bytes[i]; -#ifdef CONFIG_NFS_FSCACHE - for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) - totals.fscache[i] += stats->fscache[i]; -#endif preempt_enable(); } @@ -706,13 +702,6 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) seq_puts(m, "\n\tbytes:\t"); for (i = 0; i < __NFSIOS_BYTESMAX; i++) seq_printf(m, "%Lu ", totals.bytes[i]); -#ifdef CONFIG_NFS_FSCACHE - if (nfss->options & NFS_OPTION_FSCACHE) { - seq_puts(m, "\n\tfsc:\t"); - for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) - seq_printf(m, "%Lu ", totals.fscache[i]); - } -#endif seq_putc(m, '\n'); rpc_clnt_show_stats(m, nfss->client); diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 027874c36c88..8d946089d151 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -119,16 +119,4 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; -/* - * NFS local caching servicing counters - */ -enum nfs_stat_fscachecounters { - NFSIOS_FSCACHE_PAGES_READ_OK, - NFSIOS_FSCACHE_PAGES_READ_FAIL, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, - NFSIOS_FSCACHE_PAGES_UNCACHED, - __NFSIOS_FSCACHEMAX, -}; - #endif /* _LINUX_NFS_IOSTAT */ -- GitLab From 03f5bd75a4c19714a929a0f4e7bbf36b49e874c1 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Mon, 20 Feb 2023 08:43:08 -0500 Subject: [PATCH 2524/5631] NFS: Remove fscache specific trace points and NFS_INO_FSCACHE bit The NFS specific trace points are no longer needed as tracing is well covered by netfs and fscache. Signed-off-by: Dave Wysochanski Reviewed-by: Jeff Layton Tested-by: Daire Byrne Signed-off-by: Anna Schumaker --- fs/nfs/nfstrace.h | 91 ------------------------------------------ include/linux/nfs_fs.h | 1 - 2 files changed, 92 deletions(-) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index a778713343df..4e90ca531176 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -39,7 +39,6 @@ { BIT(NFS_INO_STALE), "STALE" }, \ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ - { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ @@ -1243,96 +1242,6 @@ TRACE_EVENT(nfs_readpage_short, ) ); -DECLARE_EVENT_CLASS(nfs_fscache_page_event, - TP_PROTO( - const struct inode *inode, - struct page *page - ), - - TP_ARGS(inode, page), - - TP_STRUCT__entry( - __field(dev_t, dev) - __field(u32, fhandle) - __field(u64, fileid) - __field(loff_t, offset) - ), - - TP_fast_assign( - const struct nfs_inode *nfsi = NFS_I(inode); - const struct nfs_fh *fh = &nfsi->fh; - - __entry->offset = page_index(page) << PAGE_SHIFT; - __entry->dev = inode->i_sb->s_dev; - __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(fh); - ), - - TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld", - MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long long)__entry->fileid, - __entry->fhandle, - (long long)__entry->offset - ) -); -DECLARE_EVENT_CLASS(nfs_fscache_page_event_done, - TP_PROTO( - const struct inode *inode, - struct page *page, - int error - ), - - TP_ARGS(inode, page, error), - - TP_STRUCT__entry( - __field(int, error) - __field(dev_t, dev) - __field(u32, fhandle) - __field(u64, fileid) - __field(loff_t, offset) - ), - - TP_fast_assign( - const struct nfs_inode *nfsi = NFS_I(inode); - const struct nfs_fh *fh = &nfsi->fh; - - __entry->offset = page_index(page) << PAGE_SHIFT; - __entry->dev = inode->i_sb->s_dev; - __entry->fileid = nfsi->fileid; - __entry->fhandle = nfs_fhandle_hash(fh); - __entry->error = error; - ), - - TP_printk( - "fileid=%02x:%02x:%llu fhandle=0x%08x " - "offset=%lld error=%d", - MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long long)__entry->fileid, - __entry->fhandle, - (long long)__entry->offset, __entry->error - ) -); -#define DEFINE_NFS_FSCACHE_PAGE_EVENT(name) \ - DEFINE_EVENT(nfs_fscache_page_event, name, \ - TP_PROTO( \ - const struct inode *inode, \ - struct page *page \ - ), \ - TP_ARGS(inode, page)) -#define DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(name) \ - DEFINE_EVENT(nfs_fscache_page_event_done, name, \ - TP_PROTO( \ - const struct inode *inode, \ - struct page *page, \ - int error \ - ), \ - TP_ARGS(inode, page, error)) -DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_read_page); -DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_read_page_exit); -DEFINE_NFS_FSCACHE_PAGE_EVENT(nfs_fscache_write_page); -DEFINE_NFS_FSCACHE_PAGE_EVENT_DONE(nfs_fscache_write_page_exit); TRACE_EVENT(nfs_pgio_error, TP_PROTO( diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 041e79a48f7a..12bb868f9a18 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -281,7 +281,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ -#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- GitLab From 6be3ae45f567cdebb5b9938137bf3445ceacf9fb Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 4 Apr 2023 17:45:15 -0700 Subject: [PATCH 2525/5631] KVM: x86: Add a helper to handle filtering of unpermitted XCR0 features Add a helper, kvm_get_filtered_xcr0(), to dedup code that needs to account for XCR0 features that require explicit opt-in on a per-process basis. In addition to documenting when KVM should/shouldn't consult xstate_get_guest_group_perm(), the helper will also allow sanitizing the filtered XCR0 to avoid enumerating architecturally illegal XCR0 values, e.g. XTILE_CFG without XTILE_DATA. No functional changes intended. Signed-off-by: Aaron Lewis Reviewed-by: Mingwei Zhang [sean: rename helper, move to x86.h, massage changelog] Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/cpuid.c | 2 +- arch/x86/kvm/x86.c | 4 +--- arch/x86/kvm/x86.h | 13 +++++++++++++ 3 files changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 9583a110cf5f..1daf0df6a9b8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1002,7 +1002,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { - u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xcr0 = kvm_get_filtered_xcr0(); u64 permitted_xss = kvm_caps.supported_xss; entry->eax &= permitted_xcr0; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 237c483b1230..181f155933cf 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4531,9 +4531,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 0; break; case KVM_CAP_XSAVE2: { - u64 guest_perm = xstate_get_guest_group_perm(); - - r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false); + r = xstate_required_size(kvm_get_filtered_xcr0(), false); if (r < sizeof(struct kvm_xsave)) r = sizeof(struct kvm_xsave); break; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a8167b47b8c8..9589c86812eb 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -315,6 +315,19 @@ extern struct kvm_caps kvm_caps; extern bool enable_pmu; +/* + * Get a filtered version of KVM's supported XCR0 that strips out dynamic + * features for which the current process doesn't (yet) have permission to use. + * This is intended to be used only when enumerating support to userspace, + * e.g. in KVM_GET_SUPPORTED_CPUID and KVM_CAP_XSAVE2, it does NOT need to be + * used to check/restrict guest behavior as KVM rejects KVM_SET_CPUID{2} if + * userspace attempts to enable unpermitted features. + */ +static inline u64 kvm_get_filtered_xcr0(void) +{ + return kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); +} + static inline bool kvm_mpx_supported(void) { return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) -- GitLab From 55cd57b596e86140503214eafc8fb62c9c544e8f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:45:16 -0700 Subject: [PATCH 2526/5631] KVM: x86: Filter out XTILE_CFG if XTILE_DATA isn't permitted Filter out XTILE_CFG from the supported XCR0 reported to userspace if the current process doesn't have access to XTILE_DATA. Attempting to set XTILE_CFG in XCR0 will #GP if XTILE_DATA is also not set, and so keeping XTILE_CFG as supported results in explosions if userspace feeds KVM_GET_SUPPORTED_CPUID back into KVM and the guest doesn't sanity check CPUID. Fixes: 445ecdf79be0 ("kvm: x86: Exclude unpermitted xfeatures at KVM_GET_SUPPORTED_CPUID") Reported-by: Aaron Lewis Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-3-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 9589c86812eb..bca706406189 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -3,6 +3,7 @@ #define ARCH_X86_KVM_X86_H #include +#include #include #include #include "kvm_cache_regs.h" @@ -325,7 +326,22 @@ extern bool enable_pmu; */ static inline u64 kvm_get_filtered_xcr0(void) { - return kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xcr0 = kvm_caps.supported_xcr0; + + BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA); + + if (permitted_xcr0 & XFEATURE_MASK_USER_DYNAMIC) { + permitted_xcr0 &= xstate_get_guest_group_perm(); + + /* + * Treat XTILE_CFG as unsupported if the current process isn't + * allowed to use XTILE_DATA, as attempting to set XTILE_CFG in + * XCR0 without setting XTILE_DATA is architecturally illegal. + */ + if (!(permitted_xcr0 & XFEATURE_MASK_XTILE_DATA)) + permitted_xcr0 &= ~XFEATURE_MASK_XTILE_CFG; + } + return permitted_xcr0; } static inline bool kvm_mpx_supported(void) -- GitLab From b213812d3f4c29502d46f82e40a82cf959670e58 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 4 Apr 2023 17:45:17 -0700 Subject: [PATCH 2527/5631] KVM: selftests: Move XGETBV and XSETBV helpers to common code The instructions XGETBV and XSETBV are useful to other tests. Move them to processor.h to make them more broadly available. No functional change intended. Reviewed-by: Jim Mattson Signed-off-by: Aaron Lewis Reviewed-by: Mingwei Zhang [sean: reword shortlog] Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-4-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 18 ++++++++++++++ tools/testing/selftests/kvm/x86_64/amx_test.c | 24 +++---------------- 2 files changed, 21 insertions(+), 21 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 3538fa6db72d..f6061fe7057f 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -510,6 +510,24 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + __asm__ __volatile__("xgetbv;" + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax | ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + __asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 5c82d7e6f552..af1ef6f79d32 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -65,24 +65,6 @@ struct xtile_info { static struct xtile_info xtile; -static inline u64 __xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile("xgetbv;" - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void __xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); -} - static inline void __ldtilecfg(void *cfg) { asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00" @@ -160,10 +142,10 @@ static void init_regs(void) set_cr4(cr4); GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); - xcr0 = __xgetbv(0); + xcr0 = xgetbv(0); xcr0 |= XFEATURE_MASK_XTILE; - __xsetbv(0x0, xcr0); - GUEST_ASSERT((__xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE); + xsetbv(0x0, xcr0); + GUEST_ASSERT((xgetbv(0) & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE); } static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, -- GitLab From 7040e54fddf681758800d7375e728557213366f9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 4 Apr 2023 17:45:18 -0700 Subject: [PATCH 2528/5631] KVM: selftests: Rework dynamic XFeature helper to take mask, not bit Take the XFeature mask in __vm_xsave_require_permission() instead of the bit so that there's no need to define macros for both the bit and the mask. Asserting that only a single bit is set and retrieving said bit is easy enough via log2 helpers. Opportunistically clean up the error message for the ARCH_REQ_XCOMP_GUEST_PERM sanity check. Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-5-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 6 +++--- .../selftests/kvm/lib/x86_64/processor.c | 17 ++++++++++------- tools/testing/selftests/kvm/x86_64/amx_test.c | 2 +- 3 files changed, 14 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index f6061fe7057f..41d798375570 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -1098,10 +1098,10 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); -void __vm_xsave_require_permission(int bit, const char *name); +void __vm_xsave_require_permission(uint64_t xfeature, const char *name); -#define vm_xsave_require_permission(perm) \ - __vm_xsave_require_permission(perm, #perm) +#define vm_xsave_require_permission(xfeature) \ + __vm_xsave_require_permission(xfeature, #xfeature) enum pg_level { PG_LEVEL_NONE, diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index a12b21a2ef37..898b30096c80 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -697,7 +697,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index) return buffer.entry.data; } -void __vm_xsave_require_permission(int bit, const char *name) +void __vm_xsave_require_permission(uint64_t xfeature, const char *name) { int kvm_fd; u64 bitmask; @@ -705,12 +705,15 @@ void __vm_xsave_require_permission(int bit, const char *name) struct kvm_device_attr attr = { .group = 0, .attr = KVM_X86_XCOMP_GUEST_SUPP, - .addr = (unsigned long) &bitmask + .addr = (unsigned long) &bitmask, }; TEST_ASSERT(!kvm_supported_cpuid, "kvm_get_supported_cpuid() cannot be used before ARCH_REQ_XCOMP_GUEST_PERM"); + TEST_ASSERT(is_power_of_2(xfeature), + "Dynamic XFeatures must be enabled one at a time"); + kvm_fd = open_kvm_dev_path_or_exit(); rc = __kvm_ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); close(kvm_fd); @@ -720,16 +723,16 @@ void __vm_xsave_require_permission(int bit, const char *name) TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); - __TEST_REQUIRE(bitmask & (1ULL << bit), + __TEST_REQUIRE(bitmask & xfeature, "Required XSAVE feature '%s' not supported", name); - TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit)); + TEST_REQUIRE(!syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, ilog2(xfeature))); rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); - TEST_ASSERT(bitmask & (1ULL << bit), - "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", - bitmask); + TEST_ASSERT(bitmask & xfeature, + "'%s' (0x%lx) not permitted after prctl(ARCH_REQ_XCOMP_GUEST_PERM) perrmited=0x%lx", + name, xfeature, bitmask); } void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid) diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index af1ef6f79d32..a0f74f5121a6 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -233,7 +233,7 @@ int main(int argc, char *argv[]) * Note, all off-by-default features must be enabled before anything * caches KVM_GET_SUPPORTED_CPUID, e.g. before using kvm_cpu_has(). */ - vm_xsave_require_permission(XSTATE_XTILE_DATA_BIT); + vm_xsave_require_permission(XFEATURE_MASK_XTILEDATA); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); -- GitLab From 28f2302584af8ed60e2108bf40762a5c40ecb372 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 4 Apr 2023 17:45:19 -0700 Subject: [PATCH 2529/5631] KVM: selftests: Add all known XFEATURE masks to common code Add all known XFEATURE masks to processor.h to make them more broadly available in KVM selftests. Relocate and clean up the exiting AMX (XTILE) defines in processor.h, e.g. drop the intermediate define and use BIT_ULL. Signed-off-by: Aaron Lewis Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-6-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/include/x86_64/processor.h | 25 ++++++++---- tools/testing/selftests/kvm/x86_64/amx_test.c | 38 ++++++++----------- 2 files changed, 33 insertions(+), 30 deletions(-) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 41d798375570..187309f3e7e9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -60,6 +60,23 @@ struct xstate { u8 extended_state_area[0]; } __attribute__ ((packed, aligned (64))); +#define XFEATURE_MASK_FP BIT_ULL(0) +#define XFEATURE_MASK_SSE BIT_ULL(1) +#define XFEATURE_MASK_YMM BIT_ULL(2) +#define XFEATURE_MASK_BNDREGS BIT_ULL(3) +#define XFEATURE_MASK_BNDCSR BIT_ULL(4) +#define XFEATURE_MASK_OPMASK BIT_ULL(5) +#define XFEATURE_MASK_ZMM_Hi256 BIT_ULL(6) +#define XFEATURE_MASK_Hi16_ZMM BIT_ULL(7) +#define XFEATURE_MASK_XTILE_CFG BIT_ULL(17) +#define XFEATURE_MASK_XTILE_DATA BIT_ULL(18) + +#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM) +#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA | \ + XFEATURE_MASK_XTILE_CFG) + /* Note, these are ordered alphabetically to match kvm_cpuid_entry2. Eww. */ enum cpuid_output_regs { KVM_CPUID_EAX, @@ -1138,14 +1155,6 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, #define X86_CR0_CD (1UL<<30) /* Cache Disable */ #define X86_CR0_PG (1UL<<31) /* Paging */ -#define XSTATE_XTILE_CFG_BIT 17 -#define XSTATE_XTILE_DATA_BIT 18 - -#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT) -#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT) -#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \ - XSTATE_XTILE_DATA_MASK) - #define PFERR_PRESENT_BIT 0 #define PFERR_WRITE_BIT 1 #define PFERR_USER_BIT 2 diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index a0f74f5121a6..11329e5ff945 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -34,12 +34,6 @@ #define MAX_TILES 16 #define RESERVED_BYTES 14 -#define XFEATURE_XTILECFG 17 -#define XFEATURE_XTILEDATA 18 -#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG) -#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA) -#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA) - #define XSAVE_HDR_OFFSET 512 struct tile_config { @@ -172,25 +166,25 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, * After XSAVEC, XTILEDATA is cleared in the xstate_bv but is set in * the xcomp_bv. */ - xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; - __xsavec(xstate, XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); - GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILEDATA); + xstate->header.xstate_bv = XFEATURE_MASK_XTILE_DATA; + __xsavec(xstate, XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); + GUEST_ASSERT(xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA); /* xfd=0x40000, disable amx tiledata */ - wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA); + wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILE_DATA); /* * XTILEDATA is cleared in xstate_bv but set in xcomp_bv, this property * remains the same even when amx tiledata is disabled by IA32_XFD. */ - xstate->header.xstate_bv = XFEATURE_MASK_XTILEDATA; - __xsavec(xstate, XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILEDATA)); - GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILEDATA)); + xstate->header.xstate_bv = XFEATURE_MASK_XTILE_DATA; + __xsavec(xstate, XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(!(xstate->header.xstate_bv & XFEATURE_MASK_XTILE_DATA)); + GUEST_ASSERT((xstate->header.xcomp_bv & XFEATURE_MASK_XTILE_DATA)); GUEST_SYNC(6); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); set_tilecfg(amx_cfg); __ldtilecfg(amx_cfg); /* Trigger #NM exception */ @@ -202,14 +196,14 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg, void guest_nm_handler(struct ex_regs *regs) { - /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */ + /* Check if #NM is triggered by XFEATURE_MASK_XTILE_DATA */ GUEST_SYNC(7); GUEST_ASSERT(!(get_cr0() & X86_CR0_TS)); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); GUEST_SYNC(8); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA); - GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILE_DATA); + GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILE_DATA); /* Clear xfd_err */ wrmsr(MSR_IA32_XFD_ERR, 0); /* xfd=0, enable amx */ @@ -233,7 +227,7 @@ int main(int argc, char *argv[]) * Note, all off-by-default features must be enabled before anything * caches KVM_GET_SUPPORTED_CPUID, e.g. before using kvm_cpu_has(). */ - vm_xsave_require_permission(XFEATURE_MASK_XTILEDATA); + vm_xsave_require_permission(XFEATURE_MASK_XTILE_DATA); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XFD)); TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); -- GitLab From 03a405b7a522700a654b79903312d0a305bdce0d Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Tue, 4 Apr 2023 17:45:20 -0700 Subject: [PATCH 2530/5631] KVM: selftests: Add test to verify KVM's supported XCR0 Check both architectural rules and KVM's ABI for KVM_GET_SUPPORTED_CPUID to ensure the supported xfeatures[1] don't violate any of them. The architectural rules[2] and KVM's contract with userspace ensure for a given feature, e.g. sse, avx, amx, etc... their associated xfeatures are either all sets or none of them are set, and any dependencies are enabled if needed. [1] EDX:EAX of CPUID.(EAX=0DH,ECX=0) [2] SDM vol 1, 13.3 ENABLING THE XSAVE FEATURE SET AND XSAVE-ENABLED FEATURES Cc: Mingwei Zhang Signed-off-by: Aaron Lewis [sean: expand comments, use a fancy X86_PROPERTY] Reviewed-by: Aaron Lewis Tested-by: Aaron Lewis Link: https://lore.kernel.org/r/20230405004520.421768-7-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 20 +++ .../selftests/kvm/x86_64/xcr0_cpuid_test.c | 132 ++++++++++++++++++ 3 files changed, 153 insertions(+) create mode 100644 tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 84a627c43795..18cadc669798 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -105,6 +105,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test +TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 187309f3e7e9..70c5469e4023 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -241,8 +241,11 @@ struct kvm_x86_cpu_property { #define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15) #define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31) +#define X86_PROPERTY_SUPPORTED_XCR0_LO KVM_X86_CPU_PROPERTY(0xd, 0, EAX, 0, 31) #define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0 KVM_X86_CPU_PROPERTY(0xd, 0, EBX, 0, 31) #define X86_PROPERTY_XSTATE_MAX_SIZE KVM_X86_CPU_PROPERTY(0xd, 0, ECX, 0, 31) +#define X86_PROPERTY_SUPPORTED_XCR0_HI KVM_X86_CPU_PROPERTY(0xd, 0, EDX, 0, 31) + #define X86_PROPERTY_XSTATE_TILE_SIZE KVM_X86_CPU_PROPERTY(0xd, 18, EAX, 0, 31) #define X86_PROPERTY_XSTATE_TILE_OFFSET KVM_X86_CPU_PROPERTY(0xd, 18, EBX, 0, 31) #define X86_PROPERTY_AMX_MAX_PALETTE_TABLES KVM_X86_CPU_PROPERTY(0x1d, 0, EAX, 0, 31) @@ -681,6 +684,15 @@ static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature) !this_cpu_has(feature.anti_feature); } +static __always_inline uint64_t this_cpu_supported_xcr0(void) +{ + if (!this_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) + return 0; + + return this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | + ((uint64_t)this_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); +} + typedef u32 __attribute__((vector_size(16))) sse128_t; #define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; } #define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; }) @@ -1104,6 +1116,14 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val) return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr)); } +static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value) +{ + u32 eax = value; + u32 edx = value >> 32; + + return kvm_asm_safe("xsetbv", "a" (eax), "d" (edx), "c" (index)); +} + bool kvm_is_tdp_enabled(void); uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c new file mode 100644 index 000000000000..905bd5ae4431 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XCR0 cpuid test + * + * Copyright (C) 2022, Google LLC. + */ + +#include +#include +#include +#include +#include + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +/* + * Assert that architectural dependency rules are satisfied, e.g. that AVX is + * supported if and only if SSE is supported. + */ +#define ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, xfeatures, dependencies) \ +do { \ + uint64_t __supported = (supported_xcr0) & ((xfeatures) | (dependencies)); \ + \ + GUEST_ASSERT_3((__supported & (xfeatures)) != (xfeatures) || \ + __supported == ((xfeatures) | (dependencies)), \ + __supported, (xfeatures), (dependencies)); \ +} while (0) + +/* + * Assert that KVM reports a sane, usable as-is XCR0. Architecturally, a CPU + * isn't strictly required to _support_ all XFeatures related to a feature, but + * at the same time XSETBV will #GP if bundled XFeatures aren't enabled and + * disabled coherently. E.g. a CPU can technically enumerate supported for + * XTILE_CFG but not XTILE_DATA, but attempting to enable XTILE_CFG without + * XTILE_DATA will #GP. + */ +#define ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, xfeatures) \ +do { \ + uint64_t __supported = (supported_xcr0) & (xfeatures); \ + \ + GUEST_ASSERT_2(!__supported || __supported == (xfeatures), \ + __supported, (xfeatures)); \ +} while (0) + +static void guest_code(void) +{ + uint64_t xcr0_reset; + uint64_t supported_xcr0; + int i, vector; + + set_cr4(get_cr4() | X86_CR4_OSXSAVE); + + xcr0_reset = xgetbv(0); + supported_xcr0 = this_cpu_supported_xcr0(); + + GUEST_ASSERT(xcr0_reset == XFEATURE_MASK_FP); + + /* Check AVX */ + ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, + XFEATURE_MASK_YMM, + XFEATURE_MASK_SSE); + + /* Check MPX */ + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + + /* Check AVX-512 */ + ASSERT_XFEATURE_DEPENDENCIES(supported_xcr0, + XFEATURE_MASK_AVX512, + XFEATURE_MASK_SSE | XFEATURE_MASK_YMM); + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_AVX512); + + /* Check AMX */ + ASSERT_ALL_OR_NONE_XFEATURE(supported_xcr0, + XFEATURE_MASK_XTILE); + + vector = xsetbv_safe(0, supported_xcr0); + GUEST_ASSERT_2(!vector, supported_xcr0, vector); + + for (i = 0; i < 64; i++) { + if (supported_xcr0 & BIT_ULL(i)) + continue; + + vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); + GUEST_ASSERT_3(vector == GP_VECTOR, supported_xcr0, vector, BIT_ULL(i)); + } + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + + TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + + while (1) { + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_3(uc, "0x%lx 0x%lx 0x%lx"); + break; + case UCALL_DONE: + goto done; + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + } + +done: + kvm_vm_free(vm); + return 0; +} -- GitLab From 3db63daabe210af32a09533fe7d8d47c711a103c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 22 Mar 2023 09:27:04 +1100 Subject: [PATCH 2531/5631] NFSv3: handle out-of-order write replies. NFSv3 includes pre/post wcc attributes which allow the client to determine if all changes to the file have been made by the client itself, or if any might have been made by some other client. If there are gaps in the pre/post ctime sequence it must be assumed that some other client changed the file in that gap and the local cache must be suspect. The next time the file is opened the cache should be invalidated. Since Commit 1c341b777501 ("NFS: Add deferred cache invalidation for close-to-open consistency violations") in linux 5.3 the Linux client has been triggering this invalidation. The chunk in nfs_update_inode() in particularly triggers. Unfortunately Linux NFS assumes that all replies will be processed in the order sent, and will arrive in the order processed. This is not true in general. Consequently Linux NFS might ignore the wcc info in a WRITE reply because the reply is in response to a WRITE that was sent before some other request for which a reply has already been seen. This is detected by Linux using the gencount tests in nfs_inode_attr_cmp(). Also, when the gencount tests pass it is still possible that the request were processed on the server in a different order, and a gap seen in the ctime sequence might be filled in by a subsequent reply, so gaps should not immediately trigger delayed invalidation. The net result is that writing to a server and then reading the file back can result in going to the server for the read rather than serving it from cache - all because a couple of replies arrived out-of-order. This is a performance regression over kernels before 5.3, though the change in 5.3 is a correctness improvement. This has been seen with Linux writing to a Netapp server which occasionally re-orders requests. In testing the majority of requests were in-order, but a few (maybe 2 or three at a time) could be re-ordered. This patch addresses the problem by recording any gaps seen in the pre/post ctime sequence and not triggering invalidation until either there are too many gaps to fit in the table, or until there are no more active writes and the remaining gaps cannot be resolved. We allocate a table of 16 gaps on demand. If the allocation fails we revert to current behaviour which is of little cost as we are unlikely to be able to cache the writes anyway. In the table we store "start->end" pair when iversion is updated and "end<-start" pairs pre/post pairs reported by the server. Usually these exactly cancel out and so nothing is stored. When there are out-of-order replies we do store gaps and these will eventually be cancelled against later replies when this client is the only writer. If the final write is out-of-order there may be one gap remaining when the file is closed. This will be noticed and if there is precisely on gap and if the iversion can be advanced to match it, then we do so. This patch makes no attempt to handle directories correctly. The same problem potentially exists in the out-of-order replies to create/unlink requests can cause future lookup requires to be sent to the server unnecessarily. A similar scheme using the same primitives could be used to notice and handle out-of-order replies. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/inode.c | 112 +++++++++++++++++++++++++++++++++++------ include/linux/nfs_fs.h | 47 +++++++++++++++++ 2 files changed, 144 insertions(+), 15 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 5c8027e3c961..eb8af1e404d9 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -208,11 +208,12 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) nfsi->cache_validity |= flags; - if (inode->i_mapping->nrpages == 0) - nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA | - NFS_INO_DATA_INVAL_DEFER); - else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) - nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + if (inode->i_mapping->nrpages == 0) { + nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; + nfs_ooo_clear(nfsi); + } else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { + nfs_ooo_clear(nfsi); + } trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); @@ -677,9 +678,10 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset) trace_nfs_size_truncate(inode, offset); i_size_write(inode, offset); /* Optimisation */ - if (offset == 0) - NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_DATA | - NFS_INO_DATA_INVAL_DEFER); + if (offset == 0) { + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; + nfs_ooo_clear(NFS_I(inode)); + } NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; spin_unlock(&inode->i_lock); @@ -1109,7 +1111,7 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) spin_lock(&inode->i_lock); if (list_empty(&nfsi->open_files) && - (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) + nfs_ooo_test(nfsi)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); @@ -1353,8 +1355,8 @@ int nfs_clear_invalid_mapping(struct address_space *mapping) set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); - nfsi->cache_validity &= - ~(NFS_INO_INVALID_DATA | NFS_INO_DATA_INVAL_DEFER); + nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; + nfs_ooo_clear(nfsi); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); @@ -1816,6 +1818,66 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, return 0; } +static void nfs_ooo_merge(struct nfs_inode *nfsi, + u64 start, u64 end) +{ + int i, cnt; + + if (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) + /* No point merging anything */ + return; + + if (!nfsi->ooo) { + nfsi->ooo = kmalloc(sizeof(*nfsi->ooo), GFP_ATOMIC); + if (!nfsi->ooo) { + nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; + return; + } + nfsi->ooo->cnt = 0; + } + + /* add this range, merging if possible */ + cnt = nfsi->ooo->cnt; + for (i = 0; i < cnt; i++) { + if (end == nfsi->ooo->gap[i].start) + end = nfsi->ooo->gap[i].end; + else if (start == nfsi->ooo->gap[i].end) + start = nfsi->ooo->gap[i].start; + else + continue; + /* Remove 'i' from table and loop to insert the new range */ + cnt -= 1; + nfsi->ooo->gap[i] = nfsi->ooo->gap[cnt]; + i = -1; + } + if (start != end) { + if (cnt >= ARRAY_SIZE(nfsi->ooo->gap)) { + nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; + return; + } + nfsi->ooo->gap[cnt].start = start; + nfsi->ooo->gap[cnt].end = end; + cnt += 1; + } + nfsi->ooo->cnt = cnt; +} + +static void nfs_ooo_record(struct nfs_inode *nfsi, + struct nfs_fattr *fattr) +{ + /* This reply was out-of-order, so record in the + * pre/post change id, possibly cancelling + * gaps created when iversion was jumpped forward. + */ + if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) && + (fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) + nfs_ooo_merge(nfsi, + fattr->change_attr, + fattr->pre_change_attr); +} + static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { @@ -1826,8 +1888,12 @@ static int nfs_refresh_inode_locked(struct inode *inode, if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode)) ret = nfs_update_inode(inode, fattr); - else if (attr_cmp == 0) - ret = nfs_check_inode_attributes(inode, fattr); + else { + nfs_ooo_record(NFS_I(inode), fattr); + + if (attr_cmp == 0) + ret = nfs_check_inode_attributes(inode, fattr); + } trace_nfs_refresh_inode_exit(inode, ret); return ret; @@ -1918,6 +1984,8 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa if (attr_cmp < 0) return 0; if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) { + /* Record the pre/post change info before clearing PRECHANGE */ + nfs_ooo_record(NFS_I(inode), fattr); fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PRESIZE | NFS_ATTR_FATTR_PREMTIME @@ -2072,6 +2140,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { + if (!have_writers && nfsi->ooo && nfsi->ooo->cnt == 1 && + nfsi->ooo->gap[0].end == inode_peek_iversion_raw(inode)) { + /* There is one remaining gap that hasn't been + * merged into iversion - do that now. + */ + inode_set_iversion_raw(inode, nfsi->ooo->gap[0].start); + kfree(nfsi->ooo); + nfsi->ooo = NULL; + } if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { /* Could it be a race with writeback? */ if (!(have_writers || have_delegation)) { @@ -2093,8 +2170,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); - } else if (!have_delegation) - nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; + } else if (!have_delegation) { + nfs_ooo_record(nfsi, fattr); + nfs_ooo_merge(nfsi, inode_peek_iversion_raw(inode), + fattr->change_attr); + } inode_set_iversion_raw(inode, fattr->change_attr); } } else { @@ -2248,6 +2328,7 @@ struct inode *nfs_alloc_inode(struct super_block *sb) return NULL; nfsi->flags = 0UL; nfsi->cache_validity = 0UL; + nfsi->ooo = NULL; #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ @@ -2262,6 +2343,7 @@ EXPORT_SYMBOL_GPL(nfs_alloc_inode); void nfs_free_inode(struct inode *inode) { + kfree(NFS_I(inode)->ooo); kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } EXPORT_SYMBOL_GPL(nfs_free_inode); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 12bb868f9a18..279262057a92 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -195,6 +195,39 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Keep track of out-of-order replies. + * The ooo array contains start/end pairs of + * numbers from the changeid sequence when + * the inode's iversion has been updated. + * It also contains end/start pair (i.e. reverse order) + * of sections of the changeid sequence that have + * been seen in replies from the server. + * Normally these should match and when both + * A:B and B:A are found in ooo, they are both removed. + * And if a reply with A:B causes an iversion update + * of A:B, then neither are added. + * When a reply has pre_change that doesn't match + * iversion, then the changeid pair and any consequent + * change in iversion ARE added. Later replies + * might fill in the gaps, or possibly a gap is caused + * by a change from another client. + * When a file or directory is opened, if the ooo table + * is not empty, then we assume the gaps were due to + * another client and we invalidate the cached data. + * + * We can only track a limited number of concurrent gaps. + * Currently that limit is 16. + * We allocate the table on demand. If there is insufficient + * memory, then we probably cannot cache the file anyway + * so there is no loss. + */ + struct { + int cnt; + struct { + u64 start, end; + } gap[16]; + } *ooo; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -612,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } +static inline void nfs_ooo_clear(struct nfs_inode *nfsi) +{ + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; +} + +static inline bool nfs_ooo_test(struct nfs_inode *nfsi) +{ + return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || + (nfsi->ooo && nfsi->ooo->cnt > 0); + +} + #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. -- GitLab From 6a24915145c922b79d3ac78f681137a4c14a6d6b Mon Sep 17 00:00:00 2001 From: Song Shuai Date: Wed, 8 Mar 2023 14:47:34 +0800 Subject: [PATCH 2532/5631] Revert "riscv: Set more data to cacheinfo" This reverts commit baf7cbd94b5688f167443a2cc3dcea3300132099. There are some duplicate cache attributes populations executed in both ci_leaf_init() and later cache_setup_properties(). Revert the commit baf7cbd94b56 ("riscv: Set more data to cacheinfo") to setup only the level and type attributes at this early place. Signed-off-by: Song Shuai Acked-by: Sudeep Holla Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20230308064734.512457-1-suagrfillet@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cacheinfo.c | 66 ++++++++--------------------------- 1 file changed, 15 insertions(+), 51 deletions(-) diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index 3a13113f1b29..305ebbdc780d 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -64,53 +64,12 @@ uintptr_t get_cache_geometry(u32 level, enum cache_type type) 0; } -static void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type, - unsigned int level, unsigned int size, - unsigned int sets, unsigned int line_size) +static void ci_leaf_init(struct cacheinfo *this_leaf, + struct device_node *node, + enum cache_type type, unsigned int level) { this_leaf->level = level; this_leaf->type = type; - this_leaf->size = size; - this_leaf->number_of_sets = sets; - this_leaf->coherency_line_size = line_size; - - /* - * If the cache is fully associative, there is no need to - * check the other properties. - */ - if (sets == 1) - return; - - /* - * Set the ways number for n-ways associative, make sure - * all properties are big than zero. - */ - if (sets > 0 && size > 0 && line_size > 0) - this_leaf->ways_of_associativity = (size / sets) / line_size; -} - -static void fill_cacheinfo(struct cacheinfo **this_leaf, - struct device_node *node, unsigned int level) -{ - unsigned int size, sets, line_size; - - if (!of_property_read_u32(node, "cache-size", &size) && - !of_property_read_u32(node, "cache-block-size", &line_size) && - !of_property_read_u32(node, "cache-sets", &sets)) { - ci_leaf_init((*this_leaf)++, CACHE_TYPE_UNIFIED, level, size, sets, line_size); - } - - if (!of_property_read_u32(node, "i-cache-size", &size) && - !of_property_read_u32(node, "i-cache-sets", &sets) && - !of_property_read_u32(node, "i-cache-block-size", &line_size)) { - ci_leaf_init((*this_leaf)++, CACHE_TYPE_INST, level, size, sets, line_size); - } - - if (!of_property_read_u32(node, "d-cache-size", &size) && - !of_property_read_u32(node, "d-cache-sets", &sets) && - !of_property_read_u32(node, "d-cache-block-size", &line_size)) { - ci_leaf_init((*this_leaf)++, CACHE_TYPE_DATA, level, size, sets, line_size); - } } int populate_cache_leaves(unsigned int cpu) @@ -121,24 +80,29 @@ int populate_cache_leaves(unsigned int cpu) struct device_node *prev = NULL; int levels = 1, level = 1; - /* Level 1 caches in cpu node */ - fill_cacheinfo(&this_leaf, np, level); + if (of_property_read_bool(np, "cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level); + if (of_property_read_bool(np, "i-cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level); + if (of_property_read_bool(np, "d-cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level); - /* Next level caches in cache nodes */ prev = np; while ((np = of_find_next_cache_node(np))) { of_node_put(prev); prev = np; - if (!of_device_is_compatible(np, "cache")) break; if (of_property_read_u32(np, "cache-level", &level)) break; if (level <= levels) break; - - fill_cacheinfo(&this_leaf, np, level); - + if (of_property_read_bool(np, "cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_UNIFIED, level); + if (of_property_read_bool(np, "i-cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_INST, level); + if (of_property_read_bool(np, "d-cache-size")) + ci_leaf_init(this_leaf++, np, CACHE_TYPE_DATA, level); levels = level; } of_node_put(np); -- GitLab From cd99dac6ec5fff763852d8ccb8a79f5de50ed830 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 7 Apr 2023 14:09:24 +1000 Subject: [PATCH 2533/5631] powerpc/boot: Fix crt0.S current address branch form Use the preferred form of branch-and-link for finding the current address so objtool doesn't think it is an unannotated intra-function call. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230407040924.231023-1-npiggin@gmail.com --- arch/powerpc/boot/crt0.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 44544720daae..121cab9d579b 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -51,7 +51,7 @@ _zimage_start: _zimage_start_lib: /* Work out the offset between the address we were linked at and the address where we're running. */ - bl .+4 + bcl 20,31,.+4 p_base: mflr r10 /* r10 now points to runtime addr of p_base */ #ifndef __powerpc64__ /* grab the link address of the dynamic section in r11 */ @@ -274,7 +274,7 @@ prom: mtsrr1 r10 /* Load FW address, set LR to label 1, and jump to FW */ - bl 0f + bcl 20,31,0f 0: mflr r10 addi r11,r10,(1f-0b) mtlr r11 -- GitLab From a8f6c2e54ddc1f1bedf3dfc92407e2b6678dd109 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:45 -0700 Subject: [PATCH 2534/5631] xfs: document the motivation for online fsck design Start the first chapter of the online fsck design documentation. This covers the motivations for creating this in the first place. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- Documentation/filesystems/index.rst | 1 + .../filesystems/xfs-online-fsck-design.rst | 212 ++++++++++++++++++ 2 files changed, 213 insertions(+) create mode 100644 Documentation/filesystems/xfs-online-fsck-design.rst diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index bee63d42e5ec..fbb2b5ada95b 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -123,4 +123,5 @@ Documentation for filesystem implementations. vfat xfs-delayed-logging-design xfs-self-describing-metadata + xfs-online-fsck-design zonefs diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst new file mode 100644 index 000000000000..07c7b4cde18f --- /dev/null +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -0,0 +1,212 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. _xfs_online_fsck_design: + +.. + Mapping of heading styles within this document: + Heading 1 uses "====" above and below + Heading 2 uses "====" + Heading 3 uses "----" + Heading 4 uses "````" + Heading 5 uses "^^^^" + Heading 6 uses "~~~~" + Heading 7 uses "...." + + Sections are manually numbered because apparently that's what everyone + does in the kernel. + +====================== +XFS Online Fsck Design +====================== + +This document captures the design of the online filesystem check feature for +XFS. +The purpose of this document is threefold: + +- To help kernel distributors understand exactly what the XFS online fsck + feature is, and issues about which they should be aware. + +- To help people reading the code to familiarize themselves with the relevant + concepts and design points before they start digging into the code. + +- To help developers maintaining the system by capturing the reasons + supporting higher level decision making. + +As the online fsck code is merged, the links in this document to topic branches +will be replaced with links to code. + +This document is licensed under the terms of the GNU Public License, v2. +The primary author is Darrick J. Wong. + +This design document is split into seven parts. +Part 1 defines what fsck tools are and the motivations for writing a new one. +Parts 2 and 3 present a high level overview of how online fsck process works +and how it is tested to ensure correct functionality. +Part 4 discusses the user interface and the intended usage modes of the new +program. +Parts 5 and 6 show off the high level components and how they fit together, and +then present case studies of how each repair function actually works. +Part 7 sums up what has been discussed so far and speculates about what else +might be built atop online fsck. + +.. contents:: Table of Contents + :local: + +1. What is a Filesystem Check? +============================== + +A Unix filesystem has four main responsibilities: + +- Provide a hierarchy of names through which application programs can associate + arbitrary blobs of data for any length of time, + +- Virtualize physical storage media across those names, and + +- Retrieve the named data blobs at any time. + +- Examine resource usage. + +Metadata directly supporting these functions (e.g. files, directories, space +mappings) are sometimes called primary metadata. +Secondary metadata (e.g. reverse mapping and directory parent pointers) support +operations internal to the filesystem, such as internal consistency checking +and reorganization. +Summary metadata, as the name implies, condense information contained in +primary metadata for performance reasons. + +The filesystem check (fsck) tool examines all the metadata in a filesystem +to look for errors. +In addition to looking for obvious metadata corruptions, fsck also +cross-references different types of metadata records with each other to look +for inconsistencies. +People do not like losing data, so most fsck tools also contains some ability +to correct any problems found. +As a word of caution -- the primary goal of most Linux fsck tools is to restore +the filesystem metadata to a consistent state, not to maximize the data +recovered. +That precedent will not be challenged here. + +Filesystems of the 20th century generally lacked any redundancy in the ondisk +format, which means that fsck can only respond to errors by erasing files until +errors are no longer detected. +More recent filesystem designs contain enough redundancy in their metadata that +it is now possible to regenerate data structures when non-catastrophic errors +occur; this capability aids both strategies. + ++--------------------------------------------------------------------------+ +| **Note**: | ++--------------------------------------------------------------------------+ +| System administrators avoid data loss by increasing the number of | +| separate storage systems through the creation of backups; and they avoid | +| downtime by increasing the redundancy of each storage system through the | +| creation of RAID arrays. | +| fsck tools address only the first problem. | ++--------------------------------------------------------------------------+ + +TLDR; Show Me the Code! +----------------------- + +Code is posted to the kernel.org git trees as follows: +`kernel changes `_, +`userspace changes `_, and +`QA test changes `_. +Each kernel patchset adding an online repair function will use the same branch +name across the kernel, xfsprogs, and fstests git repos. + +Existing Tools +-------------- + +The online fsck tool described here will be the third tool in the history of +XFS (on Linux) to check and repair filesystems. +Two programs precede it: + +The first program, ``xfs_check``, was created as part of the XFS debugger +(``xfs_db``) and can only be used with unmounted filesystems. +It walks all metadata in the filesystem looking for inconsistencies in the +metadata, though it lacks any ability to repair what it finds. +Due to its high memory requirements and inability to repair things, this +program is now deprecated and will not be discussed further. + +The second program, ``xfs_repair``, was created to be faster and more robust +than the first program. +Like its predecessor, it can only be used with unmounted filesystems. +It uses extent-based in-memory data structures to reduce memory consumption, +and tries to schedule readahead IO appropriately to reduce I/O waiting time +while it scans the metadata of the entire filesystem. +The most important feature of this tool is its ability to respond to +inconsistencies in file metadata and directory tree by erasing things as needed +to eliminate problems. +Space usage metadata are rebuilt from the observed file metadata. + +Problem Statement +----------------- + +The current XFS tools leave several problems unsolved: + +1. **User programs** suddenly **lose access** to the filesystem when unexpected + shutdowns occur as a result of silent corruptions in the metadata. + These occur **unpredictably** and often without warning. + +2. **Users** experience a **total loss of service** during the recovery period + after an **unexpected shutdown** occurs. + +3. **Users** experience a **total loss of service** if the filesystem is taken + offline to **look for problems** proactively. + +4. **Data owners** cannot **check the integrity** of their stored data without + reading all of it. + This may expose them to substantial billing costs when a linear media scan + performed by the storage system administrator might suffice. + +5. **System administrators** cannot **schedule** a maintenance window to deal + with corruptions if they **lack the means** to assess filesystem health + while the filesystem is online. + +6. **Fleet monitoring tools** cannot **automate periodic checks** of filesystem + health when doing so requires **manual intervention** and downtime. + +7. **Users** can be tricked into **doing things they do not desire** when + malicious actors **exploit quirks of Unicode** to place misleading names + in directories. + +Given this definition of the problems to be solved and the actors who would +benefit, the proposed solution is a third fsck tool that acts on a running +filesystem. + +This new third program has three components: an in-kernel facility to check +metadata, an in-kernel facility to repair metadata, and a userspace driver +program to drive fsck activity on a live filesystem. +``xfs_scrub`` is the name of the driver program. +The rest of this document presents the goals and use cases of the new fsck +tool, describes its major design points in connection to those goals, and +discusses the similarities and differences with existing tools. + ++--------------------------------------------------------------------------+ +| **Note**: | ++--------------------------------------------------------------------------+ +| Throughout this document, the existing offline fsck tool can also be | +| referred to by its current name "``xfs_repair``". | +| The userspace driver program for the new online fsck tool can be | +| referred to as "``xfs_scrub``". | +| The kernel portion of online fsck that validates metadata is called | +| "online scrub", and portion of the kernel that fixes metadata is called | +| "online repair". | ++--------------------------------------------------------------------------+ + +The naming hierarchy is broken up into objects known as directories and files +and the physical space is split into pieces known as allocation groups. +Sharding enables better performance on highly parallel systems and helps to +contain the damage when corruptions occur. +The division of the filesystem into principal objects (allocation groups and +inodes) means that there are ample opportunities to perform targeted checks and +repairs on a subset of the filesystem. + +While this is going on, other parts continue processing IO requests. +Even if a piece of filesystem metadata can only be regenerated by scanning the +entire system, the scan can still be done in the background while other file +operations continue. + +In summary, online fsck takes advantage of resource sharding and redundant +metadata to enable targeted checking and repair operations while the system +is running. +This capability will be coupled to automatic system management so that +autonomous self-healing of XFS maximizes service availability. -- GitLab From 88757e04c985271b593fe298855a048ca0e9907f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:45 -0700 Subject: [PATCH 2535/5631] xfs: document the general theory underlying online fsck design Start the second chapter of the online fsck design documentation. This covers the general theory underlying how online fsck works. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 404 ++++++++++++++++++ 1 file changed, 404 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 07c7b4cde18f..0846935325b2 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -210,3 +210,407 @@ metadata to enable targeted checking and repair operations while the system is running. This capability will be coupled to automatic system management so that autonomous self-healing of XFS maximizes service availability. + +2. Theory of Operation +====================== + +Because it is necessary for online fsck to lock and scan live metadata objects, +online fsck consists of three separate code components. +The first is the userspace driver program ``xfs_scrub``, which is responsible +for identifying individual metadata items, scheduling work items for them, +reacting to the outcomes appropriately, and reporting results to the system +administrator. +The second and third are in the kernel, which implements functions to check +and repair each type of online fsck work item. + ++------------------------------------------------------------------+ +| **Note**: | ++------------------------------------------------------------------+ +| For brevity, this document shortens the phrase "online fsck work | +| item" to "scrub item". | ++------------------------------------------------------------------+ + +Scrub item types are delineated in a manner consistent with the Unix design +philosophy, which is to say that each item should handle one aspect of a +metadata structure, and handle it well. + +Scope +----- + +In principle, online fsck should be able to check and to repair everything that +the offline fsck program can handle. +However, online fsck cannot be running 100% of the time, which means that +latent errors may creep in after a scrub completes. +If these errors cause the next mount to fail, offline fsck is the only +solution. +This limitation means that maintenance of the offline fsck tool will continue. +A second limitation of online fsck is that it must follow the same resource +sharing and lock acquisition rules as the regular filesystem. +This means that scrub cannot take *any* shortcuts to save time, because doing +so could lead to concurrency problems. +In other words, online fsck is not a complete replacement for offline fsck, and +a complete run of online fsck may take longer than online fsck. +However, both of these limitations are acceptable tradeoffs to satisfy the +different motivations of online fsck, which are to **minimize system downtime** +and to **increase predictability of operation**. + +.. _scrubphases: + +Phases of Work +-------------- + +The userspace driver program ``xfs_scrub`` splits the work of checking and +repairing an entire filesystem into seven phases. +Each phase concentrates on checking specific types of scrub items and depends +on the success of all previous phases. +The seven phases are as follows: + +1. Collect geometry information about the mounted filesystem and computer, + discover the online fsck capabilities of the kernel, and open the + underlying storage devices. + +2. Check allocation group metadata, all realtime volume metadata, and all quota + files. + Each metadata structure is scheduled as a separate scrub item. + If corruption is found in the inode header or inode btree and ``xfs_scrub`` + is permitted to perform repairs, then those scrub items are repaired to + prepare for phase 3. + Repairs are implemented by using the information in the scrub item to + resubmit the kernel scrub call with the repair flag enabled; this is + discussed in the next section. + Optimizations and all other repairs are deferred to phase 4. + +3. Check all metadata of every file in the filesystem. + Each metadata structure is also scheduled as a separate scrub item. + If repairs are needed and ``xfs_scrub`` is permitted to perform repairs, + and there were no problems detected during phase 2, then those scrub items + are repaired immediately. + Optimizations, deferred repairs, and unsuccessful repairs are deferred to + phase 4. + +4. All remaining repairs and scheduled optimizations are performed during this + phase, if the caller permits them. + Before starting repairs, the summary counters are checked and any necessary + repairs are performed so that subsequent repairs will not fail the resource + reservation step due to wildly incorrect summary counters. + Unsuccesful repairs are requeued as long as forward progress on repairs is + made somewhere in the filesystem. + Free space in the filesystem is trimmed at the end of phase 4 if the + filesystem is clean. + +5. By the start of this phase, all primary and secondary filesystem metadata + must be correct. + Summary counters such as the free space counts and quota resource counts + are checked and corrected. + Directory entry names and extended attribute names are checked for + suspicious entries such as control characters or confusing Unicode sequences + appearing in names. + +6. If the caller asks for a media scan, read all allocated and written data + file extents in the filesystem. + The ability to use hardware-assisted data file integrity checking is new + to online fsck; neither of the previous tools have this capability. + If media errors occur, they will be mapped to the owning files and reported. + +7. Re-check the summary counters and presents the caller with a summary of + space usage and file counts. + +Steps for Each Scrub Item +------------------------- + +The kernel scrub code uses a three-step strategy for checking and repairing +the one aspect of a metadata object represented by a scrub item: + +1. The scrub item of interest is checked for corruptions; opportunities for + optimization; and for values that are directly controlled by the system + administrator but look suspicious. + If the item is not corrupt or does not need optimization, resource are + released and the positive scan results are returned to userspace. + If the item is corrupt or could be optimized but the caller does not permit + this, resources are released and the negative scan results are returned to + userspace. + Otherwise, the kernel moves on to the second step. + +2. The repair function is called to rebuild the data structure. + Repair functions generally choose rebuild a structure from other metadata + rather than try to salvage the existing structure. + If the repair fails, the scan results from the first step are returned to + userspace. + Otherwise, the kernel moves on to the third step. + +3. In the third step, the kernel runs the same checks over the new metadata + item to assess the efficacy of the repairs. + The results of the reassessment are returned to userspace. + +Classification of Metadata +-------------------------- + +Each type of metadata object (and therefore each type of scrub item) is +classified as follows: + +Primary Metadata +```````````````` + +Metadata structures in this category should be most familiar to filesystem +users either because they are directly created by the user or they index +objects created by the user +Most filesystem objects fall into this class: + +- Free space and reference count information + +- Inode records and indexes + +- Storage mapping information for file data + +- Directories + +- Extended attributes + +- Symbolic links + +- Quota limits + +Scrub obeys the same rules as regular filesystem accesses for resource and lock +acquisition. + +Primary metadata objects are the simplest for scrub to process. +The principal filesystem object (either an allocation group or an inode) that +owns the item being scrubbed is locked to guard against concurrent updates. +The check function examines every record associated with the type for obvious +errors and cross-references healthy records against other metadata to look for +inconsistencies. +Repairs for this class of scrub item are simple, since the repair function +starts by holding all the resources acquired in the previous step. +The repair function scans available metadata as needed to record all the +observations needed to complete the structure. +Next, it stages the observations in a new ondisk structure and commits it +atomically to complete the repair. +Finally, the storage from the old data structure are carefully reaped. + +Because ``xfs_scrub`` locks a primary object for the duration of the repair, +this is effectively an offline repair operation performed on a subset of the +filesystem. +This minimizes the complexity of the repair code because it is not necessary to +handle concurrent updates from other threads, nor is it necessary to access +any other part of the filesystem. +As a result, indexed structures can be rebuilt very quickly, and programs +trying to access the damaged structure will be blocked until repairs complete. +The only infrastructure needed by the repair code are the staging area for +observations and a means to write new structures to disk. +Despite these limitations, the advantage that online repair holds is clear: +targeted work on individual shards of the filesystem avoids total loss of +service. + +This mechanism is described in section 2.1 ("Off-Line Algorithm") of +V. Srinivasan and M. J. Carey, `"Performance of On-Line Index Construction +Algorithms" `_, +*Extending Database Technology*, pp. 293-309, 1992. + +Most primary metadata repair functions stage their intermediate results in an +in-memory array prior to formatting the new ondisk structure, which is very +similar to the list-based algorithm discussed in section 2.3 ("List-Based +Algorithms") of Srinivasan. +However, any data structure builder that maintains a resource lock for the +duration of the repair is *always* an offline algorithm. + +Secondary Metadata +`````````````````` + +Metadata structures in this category reflect records found in primary metadata, +but are only needed for online fsck or for reorganization of the filesystem. + +Secondary metadata include: + +- Reverse mapping information + +- Directory parent pointers + +This class of metadata is difficult for scrub to process because scrub attaches +to the secondary object but needs to check primary metadata, which runs counter +to the usual order of resource acquisition. +Frequently, this means that full filesystems scans are necessary to rebuild the +metadata. +Check functions can be limited in scope to reduce runtime. +Repairs, however, require a full scan of primary metadata, which can take a +long time to complete. +Under these conditions, ``xfs_scrub`` cannot lock resources for the entire +duration of the repair. + +Instead, repair functions set up an in-memory staging structure to store +observations. +Depending on the requirements of the specific repair function, the staging +index will either have the same format as the ondisk structure or a design +specific to that repair function. +The next step is to release all locks and start the filesystem scan. +When the repair scanner needs to record an observation, the staging data are +locked long enough to apply the update. +While the filesystem scan is in progress, the repair function hooks the +filesystem so that it can apply pending filesystem updates to the staging +information. +Once the scan is done, the owning object is re-locked, the live data is used to +write a new ondisk structure, and the repairs are committed atomically. +The hooks are disabled and the staging staging area is freed. +Finally, the storage from the old data structure are carefully reaped. + +Introducing concurrency helps online repair avoid various locking problems, but +comes at a high cost to code complexity. +Live filesystem code has to be hooked so that the repair function can observe +updates in progress. +The staging area has to become a fully functional parallel structure so that +updates can be merged from the hooks. +Finally, the hook, the filesystem scan, and the inode locking model must be +sufficiently well integrated that a hook event can decide if a given update +should be applied to the staging structure. + +In theory, the scrub implementation could apply these same techniques for +primary metadata, but doing so would make it massively more complex and less +performant. +Programs attempting to access the damaged structures are not blocked from +operation, which may cause application failure or an unplanned filesystem +shutdown. + +Inspiration for the secondary metadata repair strategy was drawn from section +2.4 of Srinivasan above, and sections 2 ("NSF: Inded Build Without Side-File") +and 3.1.1 ("Duplicate Key Insert Problem") in C. Mohan, `"Algorithms for +Creating Indexes for Very Large Tables Without Quiescing Updates" +`_, 1992. + +The sidecar index mentioned above bears some resemblance to the side file +method mentioned in Srinivasan and Mohan. +Their method consists of an index builder that extracts relevant record data to +build the new structure as quickly as possible; and an auxiliary structure that +captures all updates that would be committed to the index by other threads were +the new index already online. +After the index building scan finishes, the updates recorded in the side file +are applied to the new index. +To avoid conflicts between the index builder and other writer threads, the +builder maintains a publicly visible cursor that tracks the progress of the +scan through the record space. +To avoid duplication of work between the side file and the index builder, side +file updates are elided when the record ID for the update is greater than the +cursor position within the record ID space. + +To minimize changes to the rest of the codebase, XFS online repair keeps the +replacement index hidden until it's completely ready to go. +In other words, there is no attempt to expose the keyspace of the new index +while repair is running. +The complexity of such an approach would be very high and perhaps more +appropriate to building *new* indices. + +**Future Work Question**: Can the full scan and live update code used to +facilitate a repair also be used to implement a comprehensive check? + +*Answer*: In theory, yes. Check would be much stronger if each scrub function +employed these live scans to build a shadow copy of the metadata and then +compared the shadow records to the ondisk records. +However, doing that is a fair amount more work than what the checking functions +do now. +The live scans and hooks were developed much later. +That in turn increases the runtime of those scrub functions. + +Summary Information +``````````````````` + +Metadata structures in this last category summarize the contents of primary +metadata records. +These are often used to speed up resource usage queries, and are many times +smaller than the primary metadata which they represent. + +Examples of summary information include: + +- Summary counts of free space and inodes + +- File link counts from directories + +- Quota resource usage counts + +Check and repair require full filesystem scans, but resource and lock +acquisition follow the same paths as regular filesystem accesses. + +The superblock summary counters have special requirements due to the underlying +implementation of the incore counters, and will be treated separately. +Check and repair of the other types of summary counters (quota resource counts +and file link counts) employ the same filesystem scanning and hooking +techniques as outlined above, but because the underlying data are sets of +integer counters, the staging data need not be a fully functional mirror of the +ondisk structure. + +Inspiration for quota and file link count repair strategies were drawn from +sections 2.12 ("Online Index Operations") through 2.14 ("Incremental View +Maintenace") of G. Graefe, `"Concurrent Queries and Updates in Summary Views +and Their Indexes" +`_, 2011. + +Since quotas are non-negative integer counts of resource usage, online +quotacheck can use the incremental view deltas described in section 2.14 to +track pending changes to the block and inode usage counts in each transaction, +and commit those changes to a dquot side file when the transaction commits. +Delta tracking is necessary for dquots because the index builder scans inodes, +whereas the data structure being rebuilt is an index of dquots. +Link count checking combines the view deltas and commit step into one because +it sets attributes of the objects being scanned instead of writing them to a +separate data structure. +Each online fsck function will be discussed as case studies later in this +document. + +Risk Management +--------------- + +During the development of online fsck, several risk factors were identified +that may make the feature unsuitable for certain distributors and users. +Steps can be taken to mitigate or eliminate those risks, though at a cost to +functionality. + +- **Decreased performance**: Adding metadata indices to the filesystem + increases the time cost of persisting changes to disk, and the reverse space + mapping and directory parent pointers are no exception. + System administrators who require the maximum performance can disable the + reverse mapping features at format time, though this choice dramatically + reduces the ability of online fsck to find inconsistencies and repair them. + +- **Incorrect repairs**: As with all software, there might be defects in the + software that result in incorrect repairs being written to the filesystem. + Systematic fuzz testing (detailed in the next section) is employed by the + authors to find bugs early, but it might not catch everything. + The kernel build system provides Kconfig options (``CONFIG_XFS_ONLINE_SCRUB`` + and ``CONFIG_XFS_ONLINE_REPAIR``) to enable distributors to choose not to + accept this risk. + The xfsprogs build system has a configure option (``--enable-scrub=no``) that + disables building of the ``xfs_scrub`` binary, though this is not a risk + mitigation if the kernel functionality remains enabled. + +- **Inability to repair**: Sometimes, a filesystem is too badly damaged to be + repairable. + If the keyspaces of several metadata indices overlap in some manner but a + coherent narrative cannot be formed from records collected, then the repair + fails. + To reduce the chance that a repair will fail with a dirty transaction and + render the filesystem unusable, the online repair functions have been + designed to stage and validate all new records before committing the new + structure. + +- **Misbehavior**: Online fsck requires many privileges -- raw IO to block + devices, opening files by handle, ignoring Unix discretionary access control, + and the ability to perform administrative changes. + Running this automatically in the background scares people, so the systemd + background service is configured to run with only the privileges required. + Obviously, this cannot address certain problems like the kernel crashing or + deadlocking, but it should be sufficient to prevent the scrub process from + escaping and reconfiguring the system. + The cron job does not have this protection. + +- **Fuzz Kiddiez**: There are many people now who seem to think that running + automated fuzz testing of ondisk artifacts to find mischevious behavior and + spraying exploit code onto the public mailing list for instant zero-day + disclosure is somehow of some social benefit. + In the view of this author, the benefit is realized only when the fuzz + operators help to **fix** the flaws, but this opinion apparently is not + widely shared among security "researchers". + The XFS maintainers' continuing ability to manage these events presents an + ongoing risk to the stability of the development process. + Automated testing should front-load some of the risk while the feature is + considered EXPERIMENTAL. + +Many of these risks are inherent to software programming. +Despite this, it is hoped that this new functionality will prove useful in +reducing unexpected downtime. -- GitLab From 9a30b5b52180bc37c7b3cf0efb57ba1297178856 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:46 -0700 Subject: [PATCH 2536/5631] xfs: document the testing plan for online fsck Start the third chapter of the online fsck design documentation. This covers the testing plan to make sure that both online and offline fsck can detect arbitrary problems and correct them without making things worse. Signed-off-by: Darrick J. Wong Reviewed-by: Allison Henderson Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 186 ++++++++++++++++++ 1 file changed, 186 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 0846935325b2..ed9b83c4dbf7 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -614,3 +614,189 @@ functionality. Many of these risks are inherent to software programming. Despite this, it is hoped that this new functionality will prove useful in reducing unexpected downtime. + +3. Testing Plan +=============== + +As stated before, fsck tools have three main goals: + +1. Detect inconsistencies in the metadata; + +2. Eliminate those inconsistencies; and + +3. Minimize further loss of data. + +Demonstrations of correct operation are necessary to build users' confidence +that the software behaves within expectations. +Unfortunately, it was not really feasible to perform regular exhaustive testing +of every aspect of a fsck tool until the introduction of low-cost virtual +machines with high-IOPS storage. +With ample hardware availability in mind, the testing strategy for the online +fsck project involves differential analysis against the existing fsck tools and +systematic testing of every attribute of every type of metadata object. +Testing can be split into four major categories, as discussed below. + +Integrated Testing with fstests +------------------------------- + +The primary goal of any free software QA effort is to make testing as +inexpensive and widespread as possible to maximize the scaling advantages of +community. +In other words, testing should maximize the breadth of filesystem configuration +scenarios and hardware setups. +This improves code quality by enabling the authors of online fsck to find and +fix bugs early, and helps developers of new features to find integration +issues earlier in their development effort. + +The Linux filesystem community shares a common QA testing suite, +`fstests `_, for +functional and regression testing. +Even before development work began on online fsck, fstests (when run on XFS) +would run both the ``xfs_check`` and ``xfs_repair -n`` commands on the test and +scratch filesystems between each test. +This provides a level of assurance that the kernel and the fsck tools stay in +alignment about what constitutes consistent metadata. +During development of the online checking code, fstests was modified to run +``xfs_scrub -n`` between each test to ensure that the new checking code +produces the same results as the two existing fsck tools. + +To start development of online repair, fstests was modified to run +``xfs_repair`` to rebuild the filesystem's metadata indices between tests. +This ensures that offline repair does not crash, leave a corrupt filesystem +after it exists, or trigger complaints from the online check. +This also established a baseline for what can and cannot be repaired offline. +To complete the first phase of development of online repair, fstests was +modified to be able to run ``xfs_scrub`` in a "force rebuild" mode. +This enables a comparison of the effectiveness of online repair as compared to +the existing offline repair tools. + +General Fuzz Testing of Metadata Blocks +--------------------------------------- + +XFS benefits greatly from having a very robust debugging tool, ``xfs_db``. + +Before development of online fsck even began, a set of fstests were created +to test the rather common fault that entire metadata blocks get corrupted. +This required the creation of fstests library code that can create a filesystem +containing every possible type of metadata object. +Next, individual test cases were created to create a test filesystem, identify +a single block of a specific type of metadata object, trash it with the +existing ``blocktrash`` command in ``xfs_db``, and test the reaction of a +particular metadata validation strategy. + +This earlier test suite enabled XFS developers to test the ability of the +in-kernel validation functions and the ability of the offline fsck tool to +detect and eliminate the inconsistent metadata. +This part of the test suite was extended to cover online fsck in exactly the +same manner. + +In other words, for a given fstests filesystem configuration: + +* For each metadata object existing on the filesystem: + + * Write garbage to it + + * Test the reactions of: + + 1. The kernel verifiers to stop obviously bad metadata + 2. Offline repair (``xfs_repair``) to detect and fix + 3. Online repair (``xfs_scrub``) to detect and fix + +Targeted Fuzz Testing of Metadata Records +----------------------------------------- + +The testing plan for online fsck includes extending the existing fs testing +infrastructure to provide a much more powerful facility: targeted fuzz testing +of every metadata field of every metadata object in the filesystem. +``xfs_db`` can modify every field of every metadata structure in every +block in the filesystem to simulate the effects of memory corruption and +software bugs. +Given that fstests already contains the ability to create a filesystem +containing every metadata format known to the filesystem, ``xfs_db`` can be +used to perform exhaustive fuzz testing! + +For a given fstests filesystem configuration: + +* For each metadata object existing on the filesystem... + + * For each record inside that metadata object... + + * For each field inside that record... + + * For each conceivable type of transformation that can be applied to a bit field... + + 1. Clear all bits + 2. Set all bits + 3. Toggle the most significant bit + 4. Toggle the middle bit + 5. Toggle the least significant bit + 6. Add a small quantity + 7. Subtract a small quantity + 8. Randomize the contents + + * ...test the reactions of: + + 1. The kernel verifiers to stop obviously bad metadata + 2. Offline checking (``xfs_repair -n``) + 3. Offline repair (``xfs_repair``) + 4. Online checking (``xfs_scrub -n``) + 5. Online repair (``xfs_scrub``) + 6. Both repair tools (``xfs_scrub`` and then ``xfs_repair`` if online repair doesn't succeed) + +This is quite the combinatoric explosion! + +Fortunately, having this much test coverage makes it easy for XFS developers to +check the responses of XFS' fsck tools. +Since the introduction of the fuzz testing framework, these tests have been +used to discover incorrect repair code and missing functionality for entire +classes of metadata objects in ``xfs_repair``. +The enhanced testing was used to finalize the deprecation of ``xfs_check`` by +confirming that ``xfs_repair`` could detect at least as many corruptions as +the older tool. + +These tests have been very valuable for ``xfs_scrub`` in the same ways -- they +allow the online fsck developers to compare online fsck against offline fsck, +and they enable XFS developers to find deficiencies in the code base. + +Proposed patchsets include +`general fuzzer improvements +`_, +`fuzzing baselines +`_, +and `improvements in fuzz testing comprehensiveness +`_. + +Stress Testing +-------------- + +A unique requirement to online fsck is the ability to operate on a filesystem +concurrently with regular workloads. +Although it is of course impossible to run ``xfs_scrub`` with *zero* observable +impact on the running system, the online repair code should never introduce +inconsistencies into the filesystem metadata, and regular workloads should +never notice resource starvation. +To verify that these conditions are being met, fstests has been enhanced in +the following ways: + +* For each scrub item type, create a test to exercise checking that item type + while running ``fsstress``. +* For each scrub item type, create a test to exercise repairing that item type + while running ``fsstress``. +* Race ``fsstress`` and ``xfs_scrub -n`` to ensure that checking the whole + filesystem doesn't cause problems. +* Race ``fsstress`` and ``xfs_scrub`` in force-rebuild mode to ensure that + force-repairing the whole filesystem doesn't cause problems. +* Race ``xfs_scrub`` in check and force-repair mode against ``fsstress`` while + freezing and thawing the filesystem. +* Race ``xfs_scrub`` in check and force-repair mode against ``fsstress`` while + remounting the filesystem read-only and read-write. +* The same, but running ``fsx`` instead of ``fsstress``. (Not done yet?) + +Success is defined by the ability to run all of these tests without observing +any unexpected filesystem shutdowns due to corrupted metadata, kernel hang +check warnings, or any other sort of mischief. + +Proposed patchsets include `general stress testing +`_ +and the `evolution of existing per-function stress testing +`_. -- GitLab From 4f7f64697025cd738685a3497e7d5252f3adf825 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:47 -0700 Subject: [PATCH 2537/5631] xfs: document the user interface for online fsck Start the fourth chapter of the online fsck design documentation, which discusses the user interface and the background scrubbing service. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 113 ++++++++++++++++++ 1 file changed, 113 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index ed9b83c4dbf7..1411c09b9677 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -800,3 +800,116 @@ Proposed patchsets include `general stress testing `_ and the `evolution of existing per-function stress testing `_. + +4. User Interface +================= + +The primary user of online fsck is the system administrator, just like offline +repair. +Online fsck presents two modes of operation to administrators: +A foreground CLI process for online fsck on demand, and a background service +that performs autonomous checking and repair. + +Checking on Demand +------------------ + +For administrators who want the absolute freshest information about the +metadata in a filesystem, ``xfs_scrub`` can be run as a foreground process on +a command line. +The program checks every piece of metadata in the filesystem while the +administrator waits for the results to be reported, just like the existing +``xfs_repair`` tool. +Both tools share a ``-n`` option to perform a read-only scan, and a ``-v`` +option to increase the verbosity of the information reported. + +A new feature of ``xfs_scrub`` is the ``-x`` option, which employs the error +correction capabilities of the hardware to check data file contents. +The media scan is not enabled by default because it may dramatically increase +program runtime and consume a lot of bandwidth on older storage hardware. + +The output of a foreground invocation is captured in the system log. + +The ``xfs_scrub_all`` program walks the list of mounted filesystems and +initiates ``xfs_scrub`` for each of them in parallel. +It serializes scans for any filesystems that resolve to the same top level +kernel block device to prevent resource overconsumption. + +Background Service +------------------ + +To reduce the workload of system administrators, the ``xfs_scrub`` package +provides a suite of `systemd `_ timers and services that +run online fsck automatically on weekends by default. +The background service configures scrub to run with as little privilege as +possible, the lowest CPU and IO priority, and in a CPU-constrained single +threaded mode. +This can be tuned by the systemd administrator at any time to suit the latency +and throughput requirements of customer workloads. + +The output of the background service is also captured in the system log. +If desired, reports of failures (either due to inconsistencies or mere runtime +errors) can be emailed automatically by setting the ``EMAIL_ADDR`` environment +variable in the following service files: + +* ``xfs_scrub_fail@.service`` +* ``xfs_scrub_media_fail@.service`` +* ``xfs_scrub_all_fail.service`` + +The decision to enable the background scan is left to the system administrator. +This can be done by enabling either of the following services: + +* ``xfs_scrub_all.timer`` on systemd systems +* ``xfs_scrub_all.cron`` on non-systemd systems + +This automatic weekly scan is configured out of the box to perform an +additional media scan of all file data once per month. +This is less foolproof than, say, storing file data block checksums, but much +more performant if application software provides its own integrity checking, +redundancy can be provided elsewhere above the filesystem, or the storage +device's integrity guarantees are deemed sufficient. + +The systemd unit file definitions have been subjected to a security audit +(as of systemd 249) to ensure that the xfs_scrub processes have as little +access to the rest of the system as possible. +This was performed via ``systemd-analyze security``, after which privileges +were restricted to the minimum required, sandboxing was set up to the maximal +extent possible with sandboxing and system call filtering; and access to the +filesystem tree was restricted to the minimum needed to start the program and +access the filesystem being scanned. +The service definition files restrict CPU usage to 80% of one CPU core, and +apply as nice of a priority to IO and CPU scheduling as possible. +This measure was taken to minimize delays in the rest of the filesystem. +No such hardening has been performed for the cron job. + +Proposed patchset: +`Enabling the xfs_scrub background service +`_. + +Health Reporting +---------------- + +XFS caches a summary of each filesystem's health status in memory. +The information is updated whenever ``xfs_scrub`` is run, or whenever +inconsistencies are detected in the filesystem metadata during regular +operations. +System administrators should use the ``health`` command of ``xfs_spaceman`` to +download this information into a human-readable format. +If problems have been observed, the administrator can schedule a reduced +service window to run the online repair tool to correct the problem. +Failing that, the administrator can decide to schedule a maintenance window to +run the traditional offline repair tool to correct the problem. + +**Future Work Question**: Should the health reporting integrate with the new +inotify fs error notification system? +Would it be helpful for sysadmins to have a daemon to listen for corruption +notifications and initiate a repair? + +*Answer*: These questions remain unanswered, but should be a part of the +conversation with early adopters and potential downstream users of XFS. + +Proposed patchsets include +`wiring up health reports to correction returns +`_ +and +`preservation of sickness info during memory reclaim +`_. -- GitLab From e5edad526262d4ce389f7259396184975a9bc14e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:47 -0700 Subject: [PATCH 2538/5631] xfs: document the filesystem metadata checking strategy Begin the fifth chapter of the online fsck design documentation, where we discuss the details of the data structures and algorithms used by the kernel to examine filesystem metadata and cross-reference it around the filesystem. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 587 ++++++++++++++++++ .../xfs-self-describing-metadata.rst | 1 + 2 files changed, 588 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 1411c09b9677..4a19c70434aa 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -913,3 +913,590 @@ Proposed patchsets include and `preservation of sickness info during memory reclaim `_. + +5. Kernel Algorithms and Data Structures +======================================== + +This section discusses the key algorithms and data structures of the kernel +code that provide the ability to check and repair metadata while the system +is running. +The first chapters in this section reveal the pieces that provide the +foundation for checking metadata. +The remainder of this section presents the mechanisms through which XFS +regenerates itself. + +Self Describing Metadata +------------------------ + +Starting with XFS version 5 in 2012, XFS updated the format of nearly every +ondisk block header to record a magic number, a checksum, a universally +"unique" identifier (UUID), an owner code, the ondisk address of the block, +and a log sequence number. +When loading a block buffer from disk, the magic number, UUID, owner, and +ondisk address confirm that the retrieved block matches the specific owner of +the current filesystem, and that the information contained in the block is +supposed to be found at the ondisk address. +The first three components enable checking tools to disregard alleged metadata +that doesn't belong to the filesystem, and the fourth component enables the +filesystem to detect lost writes. + +Whenever a file system operation modifies a block, the change is submitted +to the log as part of a transaction. +The log then processes these transactions marking them done once they are +safely persisted to storage. +The logging code maintains the checksum and the log sequence number of the last +transactional update. +Checksums are useful for detecting torn writes and other discrepancies that can +be introduced between the computer and its storage devices. +Sequence number tracking enables log recovery to avoid applying out of date +log updates to the filesystem. + +These two features improve overall runtime resiliency by providing a means for +the filesystem to detect obvious corruption when reading metadata blocks from +disk, but these buffer verifiers cannot provide any consistency checking +between metadata structures. + +For more information, please see the documentation for +Documentation/filesystems/xfs-self-describing-metadata.rst + +Reverse Mapping +--------------- + +The original design of XFS (circa 1993) is an improvement upon 1980s Unix +filesystem design. +In those days, storage density was expensive, CPU time was scarce, and +excessive seek time could kill performance. +For performance reasons, filesystem authors were reluctant to add redundancy to +the filesystem, even at the cost of data integrity. +Filesystems designers in the early 21st century choose different strategies to +increase internal redundancy -- either storing nearly identical copies of +metadata, or more space-efficient encoding techniques. + +For XFS, a different redundancy strategy was chosen to modernize the design: +a secondary space usage index that maps allocated disk extents back to their +owners. +By adding a new index, the filesystem retains most of its ability to scale +well to heavily threaded workloads involving large datasets, since the primary +file metadata (the directory tree, the file block map, and the allocation +groups) remain unchanged. +Like any system that improves redundancy, the reverse-mapping feature increases +overhead costs for space mapping activities. +However, it has two critical advantages: first, the reverse index is key to +enabling online fsck and other requested functionality such as free space +defragmentation, better media failure reporting, and filesystem shrinking. +Second, the different ondisk storage format of the reverse mapping btree +defeats device-level deduplication because the filesystem requires real +redundancy. + ++--------------------------------------------------------------------------+ +| **Sidebar**: | ++--------------------------------------------------------------------------+ +| A criticism of adding the secondary index is that it does nothing to | +| improve the robustness of user data storage itself. | +| This is a valid point, but adding a new index for file data block | +| checksums increases write amplification by turning data overwrites into | +| copy-writes, which age the filesystem prematurely. | +| In keeping with thirty years of precedent, users who want file data | +| integrity can supply as powerful a solution as they require. | +| As for metadata, the complexity of adding a new secondary index of space | +| usage is much less than adding volume management and storage device | +| mirroring to XFS itself. | +| Perfection of RAID and volume management are best left to existing | +| layers in the kernel. | ++--------------------------------------------------------------------------+ + +The information captured in a reverse space mapping record is as follows: + +.. code-block:: c + + struct xfs_rmap_irec { + xfs_agblock_t rm_startblock; /* extent start block */ + xfs_extlen_t rm_blockcount; /* extent length */ + uint64_t rm_owner; /* extent owner */ + uint64_t rm_offset; /* offset within the owner */ + unsigned int rm_flags; /* state flags */ + }; + +The first two fields capture the location and size of the physical space, +in units of filesystem blocks. +The owner field tells scrub which metadata structure or file inode have been +assigned this space. +For space allocated to files, the offset field tells scrub where the space was +mapped within the file fork. +Finally, the flags field provides extra information about the space usage -- +is this an attribute fork extent? A file mapping btree extent? Or an +unwritten data extent? + +Online filesystem checking judges the consistency of each primary metadata +record by comparing its information against all other space indices. +The reverse mapping index plays a key role in the consistency checking process +because it contains a centralized alternate copy of all space allocation +information. +Program runtime and ease of resource acquisition are the only real limits to +what online checking can consult. +For example, a file data extent mapping can be checked against: + +* The absence of an entry in the free space information. +* The absence of an entry in the inode index. +* The absence of an entry in the reference count data if the file is not + marked as having shared extents. +* The correspondence of an entry in the reverse mapping information. + +There are several observations to make about reverse mapping indices: + +1. Reverse mappings can provide a positive affirmation of correctness if any of + the above primary metadata are in doubt. + The checking code for most primary metadata follows a path similar to the + one outlined above. + +2. Proving the consistency of secondary metadata with the primary metadata is + difficult because that requires a full scan of all primary space metadata, + which is very time intensive. + For example, checking a reverse mapping record for a file extent mapping + btree block requires locking the file and searching the entire btree to + confirm the block. + Instead, scrub relies on rigorous cross-referencing during the primary space + mapping structure checks. + +3. Consistency scans must use non-blocking lock acquisition primitives if the + required locking order is not the same order used by regular filesystem + operations. + For example, if the filesystem normally takes a file ILOCK before taking + the AGF buffer lock but scrub wants to take a file ILOCK while holding + an AGF buffer lock, scrub cannot block on that second acquisition. + This means that forward progress during this part of a scan of the reverse + mapping data cannot be guaranteed if system load is heavy. + +In summary, reverse mappings play a key role in reconstruction of primary +metadata. +The details of how these records are staged, written to disk, and committed +into the filesystem are covered in subsequent sections. + +Checking and Cross-Referencing +------------------------------ + +The first step of checking a metadata structure is to examine every record +contained within the structure and its relationship with the rest of the +system. +XFS contains multiple layers of checking to try to prevent inconsistent +metadata from wreaking havoc on the system. +Each of these layers contributes information that helps the kernel to make +three decisions about the health of a metadata structure: + +- Is a part of this structure obviously corrupt (``XFS_SCRUB_OFLAG_CORRUPT``) ? +- Is this structure inconsistent with the rest of the system + (``XFS_SCRUB_OFLAG_XCORRUPT``) ? +- Is there so much damage around the filesystem that cross-referencing is not + possible (``XFS_SCRUB_OFLAG_XFAIL``) ? +- Can the structure be optimized to improve performance or reduce the size of + metadata (``XFS_SCRUB_OFLAG_PREEN``) ? +- Does the structure contain data that is not inconsistent but deserves review + by the system administrator (``XFS_SCRUB_OFLAG_WARNING``) ? + +The following sections describe how the metadata scrubbing process works. + +Metadata Buffer Verification +```````````````````````````` + +The lowest layer of metadata protection in XFS are the metadata verifiers built +into the buffer cache. +These functions perform inexpensive internal consistency checking of the block +itself, and answer these questions: + +- Does the block belong to this filesystem? + +- Does the block belong to the structure that asked for the read? + This assumes that metadata blocks only have one owner, which is always true + in XFS. + +- Is the type of data stored in the block within a reasonable range of what + scrub is expecting? + +- Does the physical location of the block match the location it was read from? + +- Does the block checksum match the data? + +The scope of the protections here are very limited -- verifiers can only +establish that the filesystem code is reasonably free of gross corruption bugs +and that the storage system is reasonably competent at retrieval. +Corruption problems observed at runtime cause the generation of health reports, +failed system calls, and in the extreme case, filesystem shutdowns if the +corrupt metadata force the cancellation of a dirty transaction. + +Every online fsck scrubbing function is expected to read every ondisk metadata +block of a structure in the course of checking the structure. +Corruption problems observed during a check are immediately reported to +userspace as corruption; during a cross-reference, they are reported as a +failure to cross-reference once the full examination is complete. +Reads satisfied by a buffer already in cache (and hence already verified) +bypass these checks. + +Internal Consistency Checks +``````````````````````````` + +After the buffer cache, the next level of metadata protection is the internal +record verification code built into the filesystem. +These checks are split between the buffer verifiers, the in-filesystem users of +the buffer cache, and the scrub code itself, depending on the amount of higher +level context required. +The scope of checking is still internal to the block. +These higher level checking functions answer these questions: + +- Does the type of data stored in the block match what scrub is expecting? + +- Does the block belong to the owning structure that asked for the read? + +- If the block contains records, do the records fit within the block? + +- If the block tracks internal free space information, is it consistent with + the record areas? + +- Are the records contained inside the block free of obvious corruptions? + +Record checks in this category are more rigorous and more time-intensive. +For example, block pointers and inumbers are checked to ensure that they point +within the dynamically allocated parts of an allocation group and within +the filesystem. +Names are checked for invalid characters, and flags are checked for invalid +combinations. +Other record attributes are checked for sensible values. +Btree records spanning an interval of the btree keyspace are checked for +correct order and lack of mergeability (except for file fork mappings). +For performance reasons, regular code may skip some of these checks unless +debugging is enabled or a write is about to occur. +Scrub functions, of course, must check all possible problems. + +Validation of Userspace-Controlled Record Attributes +```````````````````````````````````````````````````` + +Various pieces of filesystem metadata are directly controlled by userspace. +Because of this nature, validation work cannot be more precise than checking +that a value is within the possible range. +These fields include: + +- Superblock fields controlled by mount options +- Filesystem labels +- File timestamps +- File permissions +- File size +- File flags +- Names present in directory entries, extended attribute keys, and filesystem + labels +- Extended attribute key namespaces +- Extended attribute values +- File data block contents +- Quota limits +- Quota timer expiration (if resource usage exceeds the soft limit) + +Cross-Referencing Space Metadata +```````````````````````````````` + +After internal block checks, the next higher level of checking is +cross-referencing records between metadata structures. +For regular runtime code, the cost of these checks is considered to be +prohibitively expensive, but as scrub is dedicated to rooting out +inconsistencies, it must pursue all avenues of inquiry. +The exact set of cross-referencing is highly dependent on the context of the +data structure being checked. + +The XFS btree code has keyspace scanning functions that online fsck uses to +cross reference one structure with another. +Specifically, scrub can scan the key space of an index to determine if that +keyspace is fully, sparsely, or not at all mapped to records. +For the reverse mapping btree, it is possible to mask parts of the key for the +purposes of performing a keyspace scan so that scrub can decide if the rmap +btree contains records mapping a certain extent of physical space without the +sparsenses of the rest of the rmap keyspace getting in the way. + +Btree blocks undergo the following checks before cross-referencing: + +- Does the type of data stored in the block match what scrub is expecting? + +- Does the block belong to the owning structure that asked for the read? + +- Do the records fit within the block? + +- Are the records contained inside the block free of obvious corruptions? + +- Are the name hashes in the correct order? + +- Do node pointers within the btree point to valid block addresses for the type + of btree? + +- Do child pointers point towards the leaves? + +- Do sibling pointers point across the same level? + +- For each node block record, does the record key accurate reflect the contents + of the child block? + +Space allocation records are cross-referenced as follows: + +1. Any space mentioned by any metadata structure are cross-referenced as + follows: + + - Does the reverse mapping index list only the appropriate owner as the + owner of each block? + + - Are none of the blocks claimed as free space? + + - If these aren't file data blocks, are none of the blocks claimed as space + shared by different owners? + +2. Btree blocks are cross-referenced as follows: + + - Everything in class 1 above. + + - If there's a parent node block, do the keys listed for this block match the + keyspace of this block? + + - Do the sibling pointers point to valid blocks? Of the same level? + + - Do the child pointers point to valid blocks? Of the next level down? + +3. Free space btree records are cross-referenced as follows: + + - Everything in class 1 and 2 above. + + - Does the reverse mapping index list no owners of this space? + + - Is this space not claimed by the inode index for inodes? + + - Is it not mentioned by the reference count index? + + - Is there a matching record in the other free space btree? + +4. Inode btree records are cross-referenced as follows: + + - Everything in class 1 and 2 above. + + - Is there a matching record in free inode btree? + + - Do cleared bits in the holemask correspond with inode clusters? + + - Do set bits in the freemask correspond with inode records with zero link + count? + +5. Inode records are cross-referenced as follows: + + - Everything in class 1. + + - Do all the fields that summarize information about the file forks actually + match those forks? + + - Does each inode with zero link count correspond to a record in the free + inode btree? + +6. File fork space mapping records are cross-referenced as follows: + + - Everything in class 1 and 2 above. + + - Is this space not mentioned by the inode btrees? + + - If this is a CoW fork mapping, does it correspond to a CoW entry in the + reference count btree? + +7. Reference count records are cross-referenced as follows: + + - Everything in class 1 and 2 above. + + - Within the space subkeyspace of the rmap btree (that is to say, all + records mapped to a particular space extent and ignoring the owner info), + are there the same number of reverse mapping records for each block as the + reference count record claims? + +Proposed patchsets are the series to find gaps in +`refcount btree +`_, +`inode btree +`_, and +`rmap btree +`_ records; +to find +`mergeable records +`_; +and to +`improve cross referencing with rmap +`_ +before starting a repair. + +Checking Extended Attributes +```````````````````````````` + +Extended attributes implement a key-value store that enable fragments of data +to be attached to any file. +Both the kernel and userspace can access the keys and values, subject to +namespace and privilege restrictions. +Most typically these fragments are metadata about the file -- origins, security +contexts, user-supplied labels, indexing information, etc. + +Names can be as long as 255 bytes and can exist in several different +namespaces. +Values can be as large as 64KB. +A file's extended attributes are stored in blocks mapped by the attr fork. +The mappings point to leaf blocks, remote value blocks, or dabtree blocks. +Block 0 in the attribute fork is always the top of the structure, but otherwise +each of the three types of blocks can be found at any offset in the attr fork. +Leaf blocks contain attribute key records that point to the name and the value. +Names are always stored elsewhere in the same leaf block. +Values that are less than 3/4 the size of a filesystem block are also stored +elsewhere in the same leaf block. +Remote value blocks contain values that are too large to fit inside a leaf. +If the leaf information exceeds a single filesystem block, a dabtree (also +rooted at block 0) is created to map hashes of the attribute names to leaf +blocks in the attr fork. + +Checking an extended attribute structure is not so straightfoward due to the +lack of separation between attr blocks and index blocks. +Scrub must read each block mapped by the attr fork and ignore the non-leaf +blocks: + +1. Walk the dabtree in the attr fork (if present) to ensure that there are no + irregularities in the blocks or dabtree mappings that do not point to + attr leaf blocks. + +2. Walk the blocks of the attr fork looking for leaf blocks. + For each entry inside a leaf: + + a. Validate that the name does not contain invalid characters. + + b. Read the attr value. + This performs a named lookup of the attr name to ensure the correctness + of the dabtree. + If the value is stored in a remote block, this also validates the + integrity of the remote value block. + +Checking and Cross-Referencing Directories +`````````````````````````````````````````` + +The filesystem directory tree is a directed acylic graph structure, with files +constituting the nodes, and directory entries (dirents) constituting the edges. +Directories are a special type of file containing a set of mappings from a +255-byte sequence (name) to an inumber. +These are called directory entries, or dirents for short. +Each directory file must have exactly one directory pointing to the file. +A root directory points to itself. +Directory entries point to files of any type. +Each non-directory file may have multiple directories point to it. + +In XFS, directories are implemented as a file containing up to three 32GB +partitions. +The first partition contains directory entry data blocks. +Each data block contains variable-sized records associating a user-provided +name with an inumber and, optionally, a file type. +If the directory entry data grows beyond one block, the second partition (which +exists as post-EOF extents) is populated with a block containing free space +information and an index that maps hashes of the dirent names to directory data +blocks in the first partition. +This makes directory name lookups very fast. +If this second partition grows beyond one block, the third partition is +populated with a linear array of free space information for faster +expansions. +If the free space has been separated and the second partition grows again +beyond one block, then a dabtree is used to map hashes of dirent names to +directory data blocks. + +Checking a directory is pretty straightfoward: + +1. Walk the dabtree in the second partition (if present) to ensure that there + are no irregularities in the blocks or dabtree mappings that do not point to + dirent blocks. + +2. Walk the blocks of the first partition looking for directory entries. + Each dirent is checked as follows: + + a. Does the name contain no invalid characters? + + b. Does the inumber correspond to an actual, allocated inode? + + c. Does the child inode have a nonzero link count? + + d. If a file type is included in the dirent, does it match the type of the + inode? + + e. If the child is a subdirectory, does the child's dotdot pointer point + back to the parent? + + f. If the directory has a second partition, perform a named lookup of the + dirent name to ensure the correctness of the dabtree. + +3. Walk the free space list in the third partition (if present) to ensure that + the free spaces it describes are really unused. + +Checking operations involving :ref:`parents ` and +:ref:`file link counts ` are discussed in more detail in later +sections. + +Checking Directory/Attribute Btrees +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +As stated in previous sections, the directory/attribute btree (dabtree) index +maps user-provided names to improve lookup times by avoiding linear scans. +Internally, it maps a 32-bit hash of the name to a block offset within the +appropriate file fork. + +The internal structure of a dabtree closely resembles the btrees that record +fixed-size metadata records -- each dabtree block contains a magic number, a +checksum, sibling pointers, a UUID, a tree level, and a log sequence number. +The format of leaf and node records are the same -- each entry points to the +next level down in the hierarchy, with dabtree node records pointing to dabtree +leaf blocks, and dabtree leaf records pointing to non-dabtree blocks elsewhere +in the fork. + +Checking and cross-referencing the dabtree is very similar to what is done for +space btrees: + +- Does the type of data stored in the block match what scrub is expecting? + +- Does the block belong to the owning structure that asked for the read? + +- Do the records fit within the block? + +- Are the records contained inside the block free of obvious corruptions? + +- Are the name hashes in the correct order? + +- Do node pointers within the dabtree point to valid fork offsets for dabtree + blocks? + +- Do leaf pointers within the dabtree point to valid fork offsets for directory + or attr leaf blocks? + +- Do child pointers point towards the leaves? + +- Do sibling pointers point across the same level? + +- For each dabtree node record, does the record key accurate reflect the + contents of the child dabtree block? + +- For each dabtree leaf record, does the record key accurate reflect the + contents of the directory or attr block? + +Cross-Referencing Summary Counters +`````````````````````````````````` + +XFS maintains three classes of summary counters: available resources, quota +resource usage, and file link counts. + +In theory, the amount of available resources (data blocks, inodes, realtime +extents) can be found by walking the entire filesystem. +This would make for very slow reporting, so a transactional filesystem can +maintain summaries of this information in the superblock. +Cross-referencing these values against the filesystem metadata should be a +simple matter of walking the free space and inode metadata in each AG and the +realtime bitmap, but there are complications that will be discussed in +:ref:`more detail ` later. + +:ref:`Quota usage ` and :ref:`file link count ` +checking are sufficiently complicated to warrant separate sections. + +Post-Repair Reverification +`````````````````````````` + +After performing a repair, the checking code is run a second time to validate +the new structure, and the results of the health assessment are recorded +internally and returned to the calling process. +This step is critical for enabling system administrator to monitor the status +of the filesystem and the progress of any repairs. +For developers, it is a useful means to judge the efficacy of error detection +and correction in the online and offline checking tools. diff --git a/Documentation/filesystems/xfs-self-describing-metadata.rst b/Documentation/filesystems/xfs-self-describing-metadata.rst index b79dbf36dc94..a10c4ae6955e 100644 --- a/Documentation/filesystems/xfs-self-describing-metadata.rst +++ b/Documentation/filesystems/xfs-self-describing-metadata.rst @@ -1,4 +1,5 @@ .. SPDX-License-Identifier: GPL-2.0 +.. _xfs_self_describing_metadata: ============================ XFS Self Describing Metadata -- GitLab From bae43864c08884bacde35c5aba36d0335f659868 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:48 -0700 Subject: [PATCH 2539/5631] xfs: document how online fsck deals with eventual consistency Writes to an XFS filesystem employ an eventual consistency update model to break up complex multistep metadata updates into small chained transactions. This is generally good for performance and scalability because XFS doesn't need to prepare for enormous transactions, but it also means that online fsck must be careful not to attempt a fsck action unless it can be shown that there are no other threads processing a transaction chain. This part of the design documentation covers the thinking behind the consistency model and how scrub deals with it. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 332 ++++++++++++++++++ 1 file changed, 332 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 4a19c70434aa..9232b2e442c8 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -1500,3 +1500,335 @@ This step is critical for enabling system administrator to monitor the status of the filesystem and the progress of any repairs. For developers, it is a useful means to judge the efficacy of error detection and correction in the online and offline checking tools. + +Eventual Consistency vs. Online Fsck +------------------------------------ + +Complex operations can make modifications to multiple per-AG data structures +with a chain of transactions. +These chains, once committed to the log, are restarted during log recovery if +the system crashes while processing the chain. +Because the AG header buffers are unlocked between transactions within a chain, +online checking must coordinate with chained operations that are in progress to +avoid incorrectly detecting inconsistencies due to pending chains. +Furthermore, online repair must not run when operations are pending because +the metadata are temporarily inconsistent with each other, and rebuilding is +not possible. + +Only online fsck has this requirement of total consistency of AG metadata, and +should be relatively rare as compared to filesystem change operations. +Online fsck coordinates with transaction chains as follows: + +* For each AG, maintain a count of intent items targetting that AG. + The count should be bumped whenever a new item is added to the chain. + The count should be dropped when the filesystem has locked the AG header + buffers and finished the work. + +* When online fsck wants to examine an AG, it should lock the AG header + buffers to quiesce all transaction chains that want to modify that AG. + If the count is zero, proceed with the checking operation. + If it is nonzero, cycle the buffer locks to allow the chain to make forward + progress. + +This may lead to online fsck taking a long time to complete, but regular +filesystem updates take precedence over background checking activity. +Details about the discovery of this situation are presented in the +:ref:`next section `, and details about the solution +are presented :ref:`after that`. + +.. _chain_coordination: + +Discovery of the Problem +```````````````````````` + +Midway through the development of online scrubbing, the fsstress tests +uncovered a misinteraction between online fsck and compound transaction chains +created by other writer threads that resulted in false reports of metadata +inconsistency. +The root cause of these reports is the eventual consistency model introduced by +the expansion of deferred work items and compound transaction chains when +reverse mapping and reflink were introduced. + +Originally, transaction chains were added to XFS to avoid deadlocks when +unmapping space from files. +Deadlock avoidance rules require that AGs only be locked in increasing order, +which makes it impossible (say) to use a single transaction to free a space +extent in AG 7 and then try to free a now superfluous block mapping btree block +in AG 3. +To avoid these kinds of deadlocks, XFS creates Extent Freeing Intent (EFI) log +items to commit to freeing some space in one transaction while deferring the +actual metadata updates to a fresh transaction. +The transaction sequence looks like this: + +1. The first transaction contains a physical update to the file's block mapping + structures to remove the mapping from the btree blocks. + It then attaches to the in-memory transaction an action item to schedule + deferred freeing of space. + Concretely, each transaction maintains a list of ``struct + xfs_defer_pending`` objects, each of which maintains a list of ``struct + xfs_extent_free_item`` objects. + Returning to the example above, the action item tracks the freeing of both + the unmapped space from AG 7 and the block mapping btree (BMBT) block from + AG 3. + Deferred frees recorded in this manner are committed in the log by creating + an EFI log item from the ``struct xfs_extent_free_item`` object and + attaching the log item to the transaction. + When the log is persisted to disk, the EFI item is written into the ondisk + transaction record. + EFIs can list up to 16 extents to free, all sorted in AG order. + +2. The second transaction contains a physical update to the free space btrees + of AG 3 to release the former BMBT block and a second physical update to the + free space btrees of AG 7 to release the unmapped file space. + Observe that the the physical updates are resequenced in the correct order + when possible. + Attached to the transaction is a an extent free done (EFD) log item. + The EFD contains a pointer to the EFI logged in transaction #1 so that log + recovery can tell if the EFI needs to be replayed. + +If the system goes down after transaction #1 is written back to the filesystem +but before #2 is committed, a scan of the filesystem metadata would show +inconsistent filesystem metadata because there would not appear to be any owner +of the unmapped space. +Happily, log recovery corrects this inconsistency for us -- when recovery finds +an intent log item but does not find a corresponding intent done item, it will +reconstruct the incore state of the intent item and finish it. +In the example above, the log must replay both frees described in the recovered +EFI to complete the recovery phase. + +There are subtleties to XFS' transaction chaining strategy to consider: + +* Log items must be added to a transaction in the correct order to prevent + conflicts with principal objects that are not held by the transaction. + In other words, all per-AG metadata updates for an unmapped block must be + completed before the last update to free the extent, and extents should not + be reallocated until that last update commits to the log. + +* AG header buffers are released between each transaction in a chain. + This means that other threads can observe an AG in an intermediate state, + but as long as the first subtlety is handled, this should not affect the + correctness of filesystem operations. + +* Unmounting the filesystem flushes all pending work to disk, which means that + offline fsck never sees the temporary inconsistencies caused by deferred + work item processing. + +In this manner, XFS employs a form of eventual consistency to avoid deadlocks +and increase parallelism. + +During the design phase of the reverse mapping and reflink features, it was +decided that it was impractical to cram all the reverse mapping updates for a +single filesystem change into a single transaction because a single file +mapping operation can explode into many small updates: + +* The block mapping update itself +* A reverse mapping update for the block mapping update +* Fixing the freelist +* A reverse mapping update for the freelist fix + +* A shape change to the block mapping btree +* A reverse mapping update for the btree update +* Fixing the freelist (again) +* A reverse mapping update for the freelist fix + +* An update to the reference counting information +* A reverse mapping update for the refcount update +* Fixing the freelist (a third time) +* A reverse mapping update for the freelist fix + +* Freeing any space that was unmapped and not owned by any other file +* Fixing the freelist (a fourth time) +* A reverse mapping update for the freelist fix + +* Freeing the space used by the block mapping btree +* Fixing the freelist (a fifth time) +* A reverse mapping update for the freelist fix + +Free list fixups are not usually needed more than once per AG per transaction +chain, but it is theoretically possible if space is very tight. +For copy-on-write updates this is even worse, because this must be done once to +remove the space from a staging area and again to map it into the file! + +To deal with this explosion in a calm manner, XFS expands its use of deferred +work items to cover most reverse mapping updates and all refcount updates. +This reduces the worst case size of transaction reservations by breaking the +work into a long chain of small updates, which increases the degree of eventual +consistency in the system. +Again, this generally isn't a problem because XFS orders its deferred work +items carefully to avoid resource reuse conflicts between unsuspecting threads. + +However, online fsck changes the rules -- remember that although physical +updates to per-AG structures are coordinated by locking the buffers for AG +headers, buffer locks are dropped between transactions. +Once scrub acquires resources and takes locks for a data structure, it must do +all the validation work without releasing the lock. +If the main lock for a space btree is an AG header buffer lock, scrub may have +interrupted another thread that is midway through finishing a chain. +For example, if a thread performing a copy-on-write has completed a reverse +mapping update but not the corresponding refcount update, the two AG btrees +will appear inconsistent to scrub and an observation of corruption will be +recorded. This observation will not be correct. +If a repair is attempted in this state, the results will be catastrophic! + +Several other solutions to this problem were evaluated upon discovery of this +flaw and rejected: + +1. Add a higher level lock to allocation groups and require writer threads to + acquire the higher level lock in AG order before making any changes. + This would be very difficult to implement in practice because it is + difficult to determine which locks need to be obtained, and in what order, + without simulating the entire operation. + Performing a dry run of a file operation to discover necessary locks would + make the filesystem very slow. + +2. Make the deferred work coordinator code aware of consecutive intent items + targeting the same AG and have it hold the AG header buffers locked across + the transaction roll between updates. + This would introduce a lot of complexity into the coordinator since it is + only loosely coupled with the actual deferred work items. + It would also fail to solve the problem because deferred work items can + generate new deferred subtasks, but all subtasks must be complete before + work can start on a new sibling task. + +3. Teach online fsck to walk all transactions waiting for whichever lock(s) + protect the data structure being scrubbed to look for pending operations. + The checking and repair operations must factor these pending operations into + the evaluations being performed. + This solution is a nonstarter because it is *extremely* invasive to the main + filesystem. + +.. _intent_drains: + +Intent Drains +````````````` + +Online fsck uses an atomic intent item counter and lock cycling to coordinate +with transaction chains. +There are two key properties to the drain mechanism. +First, the counter is incremented when a deferred work item is *queued* to a +transaction, and it is decremented after the associated intent done log item is +*committed* to another transaction. +The second property is that deferred work can be added to a transaction without +holding an AG header lock, but per-AG work items cannot be marked done without +locking that AG header buffer to log the physical updates and the intent done +log item. +The first property enables scrub to yield to running transaction chains, which +is an explicit deprioritization of online fsck to benefit file operations. +The second property of the drain is key to the correct coordination of scrub, +since scrub will always be able to decide if a conflict is possible. + +For regular filesystem code, the drain works as follows: + +1. Call the appropriate subsystem function to add a deferred work item to a + transaction. + +2. The function calls ``xfs_defer_drain_bump`` to increase the counter. + +3. When the deferred item manager wants to finish the deferred work item, it + calls ``->finish_item`` to complete it. + +4. The ``->finish_item`` implementation logs some changes and calls + ``xfs_defer_drain_drop`` to decrease the sloppy counter and wake up any threads + waiting on the drain. + +5. The subtransaction commits, which unlocks the resource associated with the + intent item. + +For scrub, the drain works as follows: + +1. Lock the resource(s) associated with the metadata being scrubbed. + For example, a scan of the refcount btree would lock the AGI and AGF header + buffers. + +2. If the counter is zero (``xfs_defer_drain_busy`` returns false), there are no + chains in progress and the operation may proceed. + +3. Otherwise, release the resources grabbed in step 1. + +4. Wait for the intent counter to reach zero (``xfs_defer_drain_intents``), then go + back to step 1 unless a signal has been caught. + +To avoid polling in step 4, the drain provides a waitqueue for scrub threads to +be woken up whenever the intent count drops to zero. + +The proposed patchset is the +`scrub intent drain series +`_. + +.. _jump_labels: + +Static Keys (aka Jump Label Patching) +````````````````````````````````````` + +Online fsck for XFS separates the regular filesystem from the checking and +repair code as much as possible. +However, there are a few parts of online fsck (such as the intent drains, and +later, live update hooks) where it is useful for the online fsck code to know +what's going on in the rest of the filesystem. +Since it is not expected that online fsck will be constantly running in the +background, it is very important to minimize the runtime overhead imposed by +these hooks when online fsck is compiled into the kernel but not actively +running on behalf of userspace. +Taking locks in the hot path of a writer thread to access a data structure only +to find that no further action is necessary is expensive -- on the author's +computer, this have an overhead of 40-50ns per access. +Fortunately, the kernel supports dynamic code patching, which enables XFS to +replace a static branch to hook code with ``nop`` sleds when online fsck isn't +running. +This sled has an overhead of however long it takes the instruction decoder to +skip past the sled, which seems to be on the order of less than 1ns and +does not access memory outside of instruction fetching. + +When online fsck enables the static key, the sled is replaced with an +unconditional branch to call the hook code. +The switchover is quite expensive (~22000ns) but is paid entirely by the +program that invoked online fsck, and can be amortized if multiple threads +enter online fsck at the same time, or if multiple filesystems are being +checked at the same time. +Changing the branch direction requires taking the CPU hotplug lock, and since +CPU initialization requires memory allocation, online fsck must be careful not +to change a static key while holding any locks or resources that could be +accessed in the memory reclaim paths. +To minimize contention on the CPU hotplug lock, care should be taken not to +enable or disable static keys unnecessarily. + +Because static keys are intended to minimize hook overhead for regular +filesystem operations when xfs_scrub is not running, the intended usage +patterns are as follows: + +- The hooked part of XFS should declare a static-scoped static key that + defaults to false. + The ``DEFINE_STATIC_KEY_FALSE`` macro takes care of this. + The static key itself should be declared as a ``static`` variable. + +- When deciding to invoke code that's only used by scrub, the regular + filesystem should call the ``static_branch_unlikely`` predicate to avoid the + scrub-only hook code if the static key is not enabled. + +- The regular filesystem should export helper functions that call + ``static_branch_inc`` to enable and ``static_branch_dec`` to disable the + static key. + Wrapper functions make it easy to compile out the relevant code if the kernel + distributor turns off online fsck at build time. + +- Scrub functions wanting to turn on scrub-only XFS functionality should call + the ``xchk_fsgates_enable`` from the setup function to enable a specific + hook. + This must be done before obtaining any resources that are used by memory + reclaim. + Callers had better be sure they really need the functionality gated by the + static key; the ``TRY_HARDER`` flag is useful here. + +Online scrub has resource acquisition helpers (e.g. ``xchk_perag_lock``) to +handle locking AGI and AGF buffers for all scrubber functions. +If it detects a conflict between scrub and the running transactions, it will +try to wait for intents to complete. +If the caller of the helper has not enabled the static key, the helper will +return -EDEADLOCK, which should result in the scrub being restarted with the +``TRY_HARDER`` flag set. +The scrub setup function should detect that flag, enable the static key, and +try the scrub again. +Scrub teardown disables all static keys obtained by ``xchk_fsgates_enable``. + +For more information, please see the kernel documentation of +Documentation/staging/static-keys.rst. -- GitLab From 5f658dad233b2c92afddc011565d7e337d527a37 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:48 -0700 Subject: [PATCH 2540/5631] xfs: document pageable kernel memory Add a discussion of pageable kernel memory, since online fsck needs quite a bit more memory than most other parts of the filesystem to stage records and other information. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 500 ++++++++++++++++++ 1 file changed, 500 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 9232b2e442c8..39c394530958 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -413,6 +413,8 @@ Algorithms") of Srinivasan. However, any data structure builder that maintains a resource lock for the duration of the repair is *always* an offline algorithm. +.. _secondary_metadata: + Secondary Metadata `````````````````` @@ -1832,3 +1834,501 @@ Scrub teardown disables all static keys obtained by ``xchk_fsgates_enable``. For more information, please see the kernel documentation of Documentation/staging/static-keys.rst. + +.. _xfile: + +Pageable Kernel Memory +---------------------- + +Some online checking functions work by scanning the filesystem to build a +shadow copy of an ondisk metadata structure in memory and comparing the two +copies. +For online repair to rebuild a metadata structure, it must compute the record +set that will be stored in the new structure before it can persist that new +structure to disk. +Ideally, repairs complete with a single atomic commit that introduces +a new data structure. +To meet these goals, the kernel needs to collect a large amount of information +in a place that doesn't require the correct operation of the filesystem. + +Kernel memory isn't suitable because: + +* Allocating a contiguous region of memory to create a C array is very + difficult, especially on 32-bit systems. + +* Linked lists of records introduce double pointer overhead which is very high + and eliminate the possibility of indexed lookups. + +* Kernel memory is pinned, which can drive the system into OOM conditions. + +* The system might not have sufficient memory to stage all the information. + +At any given time, online fsck does not need to keep the entire record set in +memory, which means that individual records can be paged out if necessary. +Continued development of online fsck demonstrated that the ability to perform +indexed data storage would also be very useful. +Fortunately, the Linux kernel already has a facility for byte-addressable and +pageable storage: tmpfs. +In-kernel graphics drivers (most notably i915) take advantage of tmpfs files +to store intermediate data that doesn't need to be in memory at all times, so +that usage precedent is already established. +Hence, the ``xfile`` was born! + ++--------------------------------------------------------------------------+ +| **Historical Sidebar**: | ++--------------------------------------------------------------------------+ +| The first edition of online repair inserted records into a new btree as | +| it found them, which failed because filesystem could shut down with a | +| built data structure, which would be live after recovery finished. | +| | +| The second edition solved the half-rebuilt structure problem by storing | +| everything in memory, but frequently ran the system out of memory. | +| | +| The third edition solved the OOM problem by using linked lists, but the | +| memory overhead of the list pointers was extreme. | ++--------------------------------------------------------------------------+ + +xfile Access Models +``````````````````` + +A survey of the intended uses of xfiles suggested these use cases: + +1. Arrays of fixed-sized records (space management btrees, directory and + extended attribute entries) + +2. Sparse arrays of fixed-sized records (quotas and link counts) + +3. Large binary objects (BLOBs) of variable sizes (directory and extended + attribute names and values) + +4. Staging btrees in memory (reverse mapping btrees) + +5. Arbitrary contents (realtime space management) + +To support the first four use cases, high level data structures wrap the xfile +to share functionality between online fsck functions. +The rest of this section discusses the interfaces that the xfile presents to +four of those five higher level data structures. +The fifth use case is discussed in the :ref:`realtime summary ` case +study. + +The most general storage interface supported by the xfile enables the reading +and writing of arbitrary quantities of data at arbitrary offsets in the xfile. +This capability is provided by ``xfile_pread`` and ``xfile_pwrite`` functions, +which behave similarly to their userspace counterparts. +XFS is very record-based, which suggests that the ability to load and store +complete records is important. +To support these cases, a pair of ``xfile_obj_load`` and ``xfile_obj_store`` +functions are provided to read and persist objects into an xfile. +They are internally the same as pread and pwrite, except that they treat any +error as an out of memory error. +For online repair, squashing error conditions in this manner is an acceptable +behavior because the only reaction is to abort the operation back to userspace. +All five xfile usecases can be serviced by these four functions. + +However, no discussion of file access idioms is complete without answering the +question, "But what about mmap?" +It is convenient to access storage directly with pointers, just like userspace +code does with regular memory. +Online fsck must not drive the system into OOM conditions, which means that +xfiles must be responsive to memory reclamation. +tmpfs can only push a pagecache folio to the swap cache if the folio is neither +pinned nor locked, which means the xfile must not pin too many folios. + +Short term direct access to xfile contents is done by locking the pagecache +folio and mapping it into kernel address space. +Programmatic access (e.g. pread and pwrite) uses this mechanism. +Folio locks are not supposed to be held for long periods of time, so long +term direct access to xfile contents is done by bumping the folio refcount, +mapping it into kernel address space, and dropping the folio lock. +These long term users *must* be responsive to memory reclaim by hooking into +the shrinker infrastructure to know when to release folios. + +The ``xfile_get_page`` and ``xfile_put_page`` functions are provided to +retrieve the (locked) folio that backs part of an xfile and to release it. +The only code to use these folio lease functions are the xfarray +:ref:`sorting` algorithms and the :ref:`in-memory +btrees`. + +xfile Access Coordination +````````````````````````` + +For security reasons, xfiles must be owned privately by the kernel. +They are marked ``S_PRIVATE`` to prevent interference from the security system, +must never be mapped into process file descriptor tables, and their pages must +never be mapped into userspace processes. + +To avoid locking recursion issues with the VFS, all accesses to the shmfs file +are performed by manipulating the page cache directly. +xfile writers call the ``->write_begin`` and ``->write_end`` functions of the +xfile's address space to grab writable pages, copy the caller's buffer into the +page, and release the pages. +xfile readers call ``shmem_read_mapping_page_gfp`` to grab pages directly +before copying the contents into the caller's buffer. +In other words, xfiles ignore the VFS read and write code paths to avoid +having to create a dummy ``struct kiocb`` and to avoid taking inode and +freeze locks. +tmpfs cannot be frozen, and xfiles must not be exposed to userspace. + +If an xfile is shared between threads to stage repairs, the caller must provide +its own locks to coordinate access. +For example, if a scrub function stores scan results in an xfile and needs +other threads to provide updates to the scanned data, the scrub function must +provide a lock for all threads to share. + +.. _xfarray: + +Arrays of Fixed-Sized Records +````````````````````````````` + +In XFS, each type of indexed space metadata (free space, inodes, reference +counts, file fork space, and reverse mappings) consists of a set of fixed-size +records indexed with a classic B+ tree. +Directories have a set of fixed-size dirent records that point to the names, +and extended attributes have a set of fixed-size attribute keys that point to +names and values. +Quota counters and file link counters index records with numbers. +During a repair, scrub needs to stage new records during the gathering step and +retrieve them during the btree building step. + +Although this requirement can be satisfied by calling the read and write +methods of the xfile directly, it is simpler for callers for there to be a +higher level abstraction to take care of computing array offsets, to provide +iterator functions, and to deal with sparse records and sorting. +The ``xfarray`` abstraction presents a linear array for fixed-size records atop +the byte-accessible xfile. + +.. _xfarray_access_patterns: + +Array Access Patterns +^^^^^^^^^^^^^^^^^^^^^ + +Array access patterns in online fsck tend to fall into three categories. +Iteration of records is assumed to be necessary for all cases and will be +covered in the next section. + +The first type of caller handles records that are indexed by position. +Gaps may exist between records, and a record may be updated multiple times +during the collection step. +In other words, these callers want a sparse linearly addressed table file. +The typical use case are quota records or file link count records. +Access to array elements is performed programmatically via ``xfarray_load`` and +``xfarray_store`` functions, which wrap the similarly-named xfile functions to +provide loading and storing of array elements at arbitrary array indices. +Gaps are defined to be null records, and null records are defined to be a +sequence of all zero bytes. +Null records are detected by calling ``xfarray_element_is_null``. +They are created either by calling ``xfarray_unset`` to null out an existing +record or by never storing anything to an array index. + +The second type of caller handles records that are not indexed by position +and do not require multiple updates to a record. +The typical use case here is rebuilding space btrees and key/value btrees. +These callers can add records to the array without caring about array indices +via the ``xfarray_append`` function, which stores a record at the end of the +array. +For callers that require records to be presentable in a specific order (e.g. +rebuilding btree data), the ``xfarray_sort`` function can arrange the sorted +records; this function will be covered later. + +The third type of caller is a bag, which is useful for counting records. +The typical use case here is constructing space extent reference counts from +reverse mapping information. +Records can be put in the bag in any order, they can be removed from the bag +at any time, and uniqueness of records is left to callers. +The ``xfarray_store_anywhere`` function is used to insert a record in any +null record slot in the bag; and the ``xfarray_unset`` function removes a +record from the bag. + +The proposed patchset is the +`big in-memory array +`_. + +Iterating Array Elements +^^^^^^^^^^^^^^^^^^^^^^^^ + +Most users of the xfarray require the ability to iterate the records stored in +the array. +Callers can probe every possible array index with the following: + +.. code-block:: c + + xfarray_idx_t i; + foreach_xfarray_idx(array, i) { + xfarray_load(array, i, &rec); + + /* do something with rec */ + } + +All users of this idiom must be prepared to handle null records or must already +know that there aren't any. + +For xfarray users that want to iterate a sparse array, the ``xfarray_iter`` +function ignores indices in the xfarray that have never been written to by +calling ``xfile_seek_data`` (which internally uses ``SEEK_DATA``) to skip areas +of the array that are not populated with memory pages. +Once it finds a page, it will skip the zeroed areas of the page. + +.. code-block:: c + + xfarray_idx_t i = XFARRAY_CURSOR_INIT; + while ((ret = xfarray_iter(array, &i, &rec)) == 1) { + /* do something with rec */ + } + +.. _xfarray_sort: + +Sorting Array Elements +^^^^^^^^^^^^^^^^^^^^^^ + +During the fourth demonstration of online repair, a community reviewer remarked +that for performance reasons, online repair ought to load batches of records +into btree record blocks instead of inserting records into a new btree one at a +time. +The btree insertion code in XFS is responsible for maintaining correct ordering +of the records, so naturally the xfarray must also support sorting the record +set prior to bulk loading. + +Case Study: Sorting xfarrays +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The sorting algorithm used in the xfarray is actually a combination of adaptive +quicksort and a heapsort subalgorithm in the spirit of +`Sedgewick `_ and +`pdqsort `_, with customizations for the Linux +kernel. +To sort records in a reasonably short amount of time, ``xfarray`` takes +advantage of the binary subpartitioning offered by quicksort, but it also uses +heapsort to hedge aginst performance collapse if the chosen quicksort pivots +are poor. +Both algorithms are (in general) O(n * lg(n)), but there is a wide performance +gulf between the two implementations. + +The Linux kernel already contains a reasonably fast implementation of heapsort. +It only operates on regular C arrays, which limits the scope of its usefulness. +There are two key places where the xfarray uses it: + +* Sorting any record subset backed by a single xfile page. + +* Loading a small number of xfarray records from potentially disparate parts + of the xfarray into a memory buffer, and sorting the buffer. + +In other words, ``xfarray`` uses heapsort to constrain the nested recursion of +quicksort, thereby mitigating quicksort's worst runtime behavior. + +Choosing a quicksort pivot is a tricky business. +A good pivot splits the set to sort in half, leading to the divide and conquer +behavior that is crucial to O(n * lg(n)) performance. +A poor pivot barely splits the subset at all, leading to O(n\ :sup:`2`) +runtime. +The xfarray sort routine tries to avoid picking a bad pivot by sampling nine +records into a memory buffer and using the kernel heapsort to identify the +median of the nine. + +Most modern quicksort implementations employ Tukey's "ninther" to select a +pivot from a classic C array. +Typical ninther implementations pick three unique triads of records, sort each +of the triads, and then sort the middle value of each triad to determine the +ninther value. +As stated previously, however, xfile accesses are not entirely cheap. +It turned out to be much more performant to read the nine elements into a +memory buffer, run the kernel's in-memory heapsort on the buffer, and choose +the 4th element of that buffer as the pivot. +Tukey's ninthers are described in J. W. Tukey, `The ninther, a technique for +low-effort robust (resistant) location in large samples`, in *Contributions to +Survey Sampling and Applied Statistics*, edited by H. David, (Academic Press, +1978), pp. 251–257. + +The partitioning of quicksort is fairly textbook -- rearrange the record +subset around the pivot, then set up the current and next stack frames to +sort with the larger and the smaller halves of the pivot, respectively. +This keeps the stack space requirements to log2(record count). + +As a final performance optimization, the hi and lo scanning phase of quicksort +keeps examined xfile pages mapped in the kernel for as long as possible to +reduce map/unmap cycles. +Surprisingly, this reduces overall sort runtime by nearly half again after +accounting for the application of heapsort directly onto xfile pages. + +Blob Storage +```````````` + +Extended attributes and directories add an additional requirement for staging +records: arbitrary byte sequences of finite length. +Each directory entry record needs to store entry name, +and each extended attribute needs to store both the attribute name and value. +The names, keys, and values can consume a large amount of memory, so the +``xfblob`` abstraction was created to simplify management of these blobs +atop an xfile. + +Blob arrays provide ``xfblob_load`` and ``xfblob_store`` functions to retrieve +and persist objects. +The store function returns a magic cookie for every object that it persists. +Later, callers provide this cookie to the ``xblob_load`` to recall the object. +The ``xfblob_free`` function frees a specific blob, and the ``xfblob_truncate`` +function frees them all because compaction is not needed. + +The details of repairing directories and extended attributes will be discussed +in a subsequent section about atomic extent swapping. +However, it should be noted that these repair functions only use blob storage +to cache a small number of entries before adding them to a temporary ondisk +file, which is why compaction is not required. + +The proposed patchset is at the start of the +`extended attribute repair +`_ series. + +.. _xfbtree: + +In-Memory B+Trees +````````````````` + +The chapter about :ref:`secondary metadata` mentioned that +checking and repairing of secondary metadata commonly requires coordination +between a live metadata scan of the filesystem and writer threads that are +updating that metadata. +Keeping the scan data up to date requires requires the ability to propagate +metadata updates from the filesystem into the data being collected by the scan. +This *can* be done by appending concurrent updates into a separate log file and +applying them before writing the new metadata to disk, but this leads to +unbounded memory consumption if the rest of the system is very busy. +Another option is to skip the side-log and commit live updates from the +filesystem directly into the scan data, which trades more overhead for a lower +maximum memory requirement. +In both cases, the data structure holding the scan results must support indexed +access to perform well. + +Given that indexed lookups of scan data is required for both strategies, online +fsck employs the second strategy of committing live updates directly into +scan data. +Because xfarrays are not indexed and do not enforce record ordering, they +are not suitable for this task. +Conveniently, however, XFS has a library to create and maintain ordered reverse +mapping records: the existing rmap btree code! +If only there was a means to create one in memory. + +Recall that the :ref:`xfile ` abstraction represents memory pages as a +regular file, which means that the kernel can create byte or block addressable +virtual address spaces at will. +The XFS buffer cache specializes in abstracting IO to block-oriented address +spaces, which means that adaptation of the buffer cache to interface with +xfiles enables reuse of the entire btree library. +Btrees built atop an xfile are collectively known as ``xfbtrees``. +The next few sections describe how they actually work. + +The proposed patchset is the +`in-memory btree +`_ +series. + +Using xfiles as a Buffer Cache Target +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Two modifications are necessary to support xfiles as a buffer cache target. +The first is to make it possible for the ``struct xfs_buftarg`` structure to +host the ``struct xfs_buf`` rhashtable, because normally those are held by a +per-AG structure. +The second change is to modify the buffer ``ioapply`` function to "read" cached +pages from the xfile and "write" cached pages back to the xfile. +Multiple access to individual buffers is controlled by the ``xfs_buf`` lock, +since the xfile does not provide any locking on its own. +With this adaptation in place, users of the xfile-backed buffer cache use +exactly the same APIs as users of the disk-backed buffer cache. +The separation between xfile and buffer cache implies higher memory usage since +they do not share pages, but this property could some day enable transactional +updates to an in-memory btree. +Today, however, it simply eliminates the need for new code. + +Space Management with an xfbtree +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Space management for an xfile is very simple -- each btree block is one memory +page in size. +These blocks use the same header format as an on-disk btree, but the in-memory +block verifiers ignore the checksums, assuming that xfile memory is no more +corruption-prone than regular DRAM. +Reusing existing code here is more important than absolute memory efficiency. + +The very first block of an xfile backing an xfbtree contains a header block. +The header describes the owner, height, and the block number of the root +xfbtree block. + +To allocate a btree block, use ``xfile_seek_data`` to find a gap in the file. +If there are no gaps, create one by extending the length of the xfile. +Preallocate space for the block with ``xfile_prealloc``, and hand back the +location. +To free an xfbtree block, use ``xfile_discard`` (which internally uses +``FALLOC_FL_PUNCH_HOLE``) to remove the memory page from the xfile. + +Populating an xfbtree +^^^^^^^^^^^^^^^^^^^^^ + +An online fsck function that wants to create an xfbtree should proceed as +follows: + +1. Call ``xfile_create`` to create an xfile. + +2. Call ``xfs_alloc_memory_buftarg`` to create a buffer cache target structure + pointing to the xfile. + +3. Pass the buffer cache target, buffer ops, and other information to + ``xfbtree_create`` to write an initial tree header and root block to the + xfile. + Each btree type should define a wrapper that passes necessary arguments to + the creation function. + For example, rmap btrees define ``xfs_rmapbt_mem_create`` to take care of + all the necessary details for callers. + A ``struct xfbtree`` object will be returned. + +4. Pass the xfbtree object to the btree cursor creation function for the + btree type. + Following the example above, ``xfs_rmapbt_mem_cursor`` takes care of this + for callers. + +5. Pass the btree cursor to the regular btree functions to make queries against + and to update the in-memory btree. + For example, a btree cursor for an rmap xfbtree can be passed to the + ``xfs_rmap_*`` functions just like any other btree cursor. + See the :ref:`next section` for information on dealing with + xfbtree updates that are logged to a transaction. + +6. When finished, delete the btree cursor, destroy the xfbtree object, free the + buffer target, and the destroy the xfile to release all resources. + +.. _xfbtree_commit: + +Committing Logged xfbtree Buffers +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Although it is a clever hack to reuse the rmap btree code to handle the staging +structure, the ephemeral nature of the in-memory btree block storage presents +some challenges of its own. +The XFS transaction manager must not commit buffer log items for buffers backed +by an xfile because the log format does not understand updates for devices +other than the data device. +An ephemeral xfbtree probably will not exist by the time the AIL checkpoints +log transactions back into the filesystem, and certainly won't exist during +log recovery. +For these reasons, any code updating an xfbtree in transaction context must +remove the buffer log items from the transaction and write the updates into the +backing xfile before committing or cancelling the transaction. + +The ``xfbtree_trans_commit`` and ``xfbtree_trans_cancel`` functions implement +this functionality as follows: + +1. Find each buffer log item whose buffer targets the xfile. + +2. Record the dirty/ordered status of the log item. + +3. Detach the log item from the buffer. + +4. Queue the buffer to a special delwri list. + +5. Clear the transaction dirty flag if the only dirty log items were the ones + that were detached in step 3. + +6. Submit the delwri list to commit the changes to the xfile, if the updates + are being committed. + +After removing xfile logged buffers from the transaction in this manner, the +transaction can be committed or cancelled. -- GitLab From 7fb8ccffd36946a055cc89b8f0acf49cb59403b1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:49 -0700 Subject: [PATCH 2541/5631] xfs: document btree bulk loading Add a discussion of the btree bulk loading code, which makes it easy to take an in-memory recordset and write it out to disk in an efficient manner. This also enables atomic switchover from the old to the new structure with minimal potential for leaking the old blocks. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 665 ++++++++++++++++++ 1 file changed, 665 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 39c394530958..e57d01924515 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -2332,3 +2332,668 @@ this functionality as follows: After removing xfile logged buffers from the transaction in this manner, the transaction can be committed or cancelled. + +Bulk Loading of Ondisk B+Trees +------------------------------ + +As mentioned previously, early iterations of online repair built new btree +structures by creating a new btree and adding observations individually. +Loading a btree one record at a time had a slight advantage of not requiring +the incore records to be sorted prior to commit, but was very slow and leaked +blocks if the system went down during a repair. +Loading records one at a time also meant that repair could not control the +loading factor of the blocks in the new btree. + +Fortunately, the venerable ``xfs_repair`` tool had a more efficient means for +rebuilding a btree index from a collection of records -- bulk btree loading. +This was implemented rather inefficiently code-wise, since ``xfs_repair`` +had separate copy-pasted implementations for each btree type. + +To prepare for online fsck, each of the four bulk loaders were studied, notes +were taken, and the four were refactored into a single generic btree bulk +loading mechanism. +Those notes in turn have been refreshed and are presented below. + +Geometry Computation +```````````````````` + +The zeroth step of bulk loading is to assemble the entire record set that will +be stored in the new btree, and sort the records. +Next, call ``xfs_btree_bload_compute_geometry`` to compute the shape of the +btree from the record set, the type of btree, and any load factor preferences. +This information is required for resource reservation. + +First, the geometry computation computes the minimum and maximum records that +will fit in a leaf block from the size of a btree block and the size of the +block header. +Roughly speaking, the maximum number of records is:: + + maxrecs = (block_size - header_size) / record_size + +The XFS design specifies that btree blocks should be merged when possible, +which means the minimum number of records is half of maxrecs:: + + minrecs = maxrecs / 2 + +The next variable to determine is the desired loading factor. +This must be at least minrecs and no more than maxrecs. +Choosing minrecs is undesirable because it wastes half the block. +Choosing maxrecs is also undesirable because adding a single record to each +newly rebuilt leaf block will cause a tree split, which causes a noticeable +drop in performance immediately afterwards. +The default loading factor was chosen to be 75% of maxrecs, which provides a +reasonably compact structure without any immediate split penalties:: + + default_load_factor = (maxrecs + minrecs) / 2 + +If space is tight, the loading factor will be set to maxrecs to try to avoid +running out of space:: + + leaf_load_factor = enough space ? default_load_factor : maxrecs + +Load factor is computed for btree node blocks using the combined size of the +btree key and pointer as the record size:: + + maxrecs = (block_size - header_size) / (key_size + ptr_size) + minrecs = maxrecs / 2 + node_load_factor = enough space ? default_load_factor : maxrecs + +Once that's done, the number of leaf blocks required to store the record set +can be computed as:: + + leaf_blocks = ceil(record_count / leaf_load_factor) + +The number of node blocks needed to point to the next level down in the tree +is computed as:: + + n_blocks = (n == 0 ? leaf_blocks : node_blocks[n]) + node_blocks[n + 1] = ceil(n_blocks / node_load_factor) + +The entire computation is performed recursively until the current level only +needs one block. +The resulting geometry is as follows: + +- For AG-rooted btrees, this level is the root level, so the height of the new + tree is ``level + 1`` and the space needed is the summation of the number of + blocks on each level. + +- For inode-rooted btrees where the records in the top level do not fit in the + inode fork area, the height is ``level + 2``, the space needed is the + summation of the number of blocks on each level, and the inode fork points to + the root block. + +- For inode-rooted btrees where the records in the top level can be stored in + the inode fork area, then the root block can be stored in the inode, the + height is ``level + 1``, and the space needed is one less than the summation + of the number of blocks on each level. + This only becomes relevant when non-bmap btrees gain the ability to root in + an inode, which is a future patchset and only included here for completeness. + +.. _newbt: + +Reserving New B+Tree Blocks +``````````````````````````` + +Once repair knows the number of blocks needed for the new btree, it allocates +those blocks using the free space information. +Each reserved extent is tracked separately by the btree builder state data. +To improve crash resilience, the reservation code also logs an Extent Freeing +Intent (EFI) item in the same transaction as each space allocation and attaches +its in-memory ``struct xfs_extent_free_item`` object to the space reservation. +If the system goes down, log recovery will use the unfinished EFIs to free the +unused space, the free space, leaving the filesystem unchanged. + +Each time the btree builder claims a block for the btree from a reserved +extent, it updates the in-memory reservation to reflect the claimed space. +Block reservation tries to allocate as much contiguous space as possible to +reduce the number of EFIs in play. + +While repair is writing these new btree blocks, the EFIs created for the space +reservations pin the tail of the ondisk log. +It's possible that other parts of the system will remain busy and push the head +of the log towards the pinned tail. +To avoid livelocking the filesystem, the EFIs must not pin the tail of the log +for too long. +To alleviate this problem, the dynamic relogging capability of the deferred ops +mechanism is reused here to commit a transaction at the log head containing an +EFD for the old EFI and new EFI at the head. +This enables the log to release the old EFI to keep the log moving forwards. + +EFIs have a role to play during the commit and reaping phases; please see the +next section and the section about :ref:`reaping` for more details. + +Proposed patchsets are the +`bitmap rework +`_ +and the +`preparation for bulk loading btrees +`_. + + +Writing the New Tree +```````````````````` + +This part is pretty simple -- the btree builder (``xfs_btree_bulkload``) claims +a block from the reserved list, writes the new btree block header, fills the +rest of the block with records, and adds the new leaf block to a list of +written blocks:: + + ┌────┐ + │leaf│ + │RRR │ + └────┘ + +Sibling pointers are set every time a new block is added to the level:: + + ┌────┐ ┌────┐ ┌────┐ ┌────┐ + │leaf│→│leaf│→│leaf│→│leaf│ + │RRR │←│RRR │←│RRR │←│RRR │ + └────┘ └────┘ └────┘ └────┘ + +When it finishes writing the record leaf blocks, it moves on to the node +blocks +To fill a node block, it walks each block in the next level down in the tree +to compute the relevant keys and write them into the parent node:: + + ┌────┐ ┌────┐ + │node│──────→│node│ + │PP │←──────│PP │ + └────┘ └────┘ + ↙ ↘ ↙ ↘ + ┌────┐ ┌────┐ ┌────┐ ┌────┐ + │leaf│→│leaf│→│leaf│→│leaf│ + │RRR │←│RRR │←│RRR │←│RRR │ + └────┘ └────┘ └────┘ └────┘ + +When it reaches the root level, it is ready to commit the new btree!:: + + ┌─────────┐ + │ root │ + │ PP │ + └─────────┘ + ↙ ↘ + ┌────┐ ┌────┐ + │node│──────→│node│ + │PP │←──────│PP │ + └────┘ └────┘ + ↙ ↘ ↙ ↘ + ┌────┐ ┌────┐ ┌────┐ ┌────┐ + │leaf│→│leaf│→│leaf│→│leaf│ + │RRR │←│RRR │←│RRR │←│RRR │ + └────┘ └────┘ └────┘ └────┘ + +The first step to commit the new btree is to persist the btree blocks to disk +synchronously. +This is a little complicated because a new btree block could have been freed +in the recent past, so the builder must use ``xfs_buf_delwri_queue_here`` to +remove the (stale) buffer from the AIL list before it can write the new blocks +to disk. +Blocks are queued for IO using a delwri list and written in one large batch +with ``xfs_buf_delwri_submit``. + +Once the new blocks have been persisted to disk, control returns to the +individual repair function that called the bulk loader. +The repair function must log the location of the new root in a transaction, +clean up the space reservations that were made for the new btree, and reap the +old metadata blocks: + +1. Commit the location of the new btree root. + +2. For each incore reservation: + + a. Log Extent Freeing Done (EFD) items for all the space that was consumed + by the btree builder. The new EFDs must point to the EFIs attached to + the reservation to prevent log recovery from freeing the new blocks. + + b. For unclaimed portions of incore reservations, create a regular deferred + extent free work item to be free the unused space later in the + transaction chain. + + c. The EFDs and EFIs logged in steps 2a and 2b must not overrun the + reservation of the committing transaction. + If the btree loading code suspects this might be about to happen, it must + call ``xrep_defer_finish`` to clear out the deferred work and obtain a + fresh transaction. + +3. Clear out the deferred work a second time to finish the commit and clean + the repair transaction. + +The transaction rolling in steps 2c and 3 represent a weakness in the repair +algorithm, because a log flush and a crash before the end of the reap step can +result in space leaking. +Online repair functions minimize the chances of this occuring by using very +large transactions, which each can accomodate many thousands of block freeing +instructions. +Repair moves on to reaping the old blocks, which will be presented in a +subsequent :ref:`section` after a few case studies of bulk loading. + +Case Study: Rebuilding the Inode Index +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The high level process to rebuild the inode index btree is: + +1. Walk the reverse mapping records to generate ``struct xfs_inobt_rec`` + records from the inode chunk information and a bitmap of the old inode btree + blocks. + +2. Append the records to an xfarray in inode order. + +3. Use the ``xfs_btree_bload_compute_geometry`` function to compute the number + of blocks needed for the inode btree. + If the free space inode btree is enabled, call it again to estimate the + geometry of the finobt. + +4. Allocate the number of blocks computed in the previous step. + +5. Use ``xfs_btree_bload`` to write the xfarray records to btree blocks and + generate the internal node blocks. + If the free space inode btree is enabled, call it again to load the finobt. + +6. Commit the location of the new btree root block(s) to the AGI. + +7. Reap the old btree blocks using the bitmap created in step 1. + +Details are as follows. + +The inode btree maps inumbers to the ondisk location of the associated +inode records, which means that the inode btrees can be rebuilt from the +reverse mapping information. +Reverse mapping records with an owner of ``XFS_RMAP_OWN_INOBT`` marks the +location of the old inode btree blocks. +Each reverse mapping record with an owner of ``XFS_RMAP_OWN_INODES`` marks the +location of at least one inode cluster buffer. +A cluster is the smallest number of ondisk inodes that can be allocated or +freed in a single transaction; it is never smaller than 1 fs block or 4 inodes. + +For the space represented by each inode cluster, ensure that there are no +records in the free space btrees nor any records in the reference count btree. +If there are, the space metadata inconsistencies are reason enough to abort the +operation. +Otherwise, read each cluster buffer to check that its contents appear to be +ondisk inodes and to decide if the file is allocated +(``xfs_dinode.i_mode != 0``) or free (``xfs_dinode.i_mode == 0``). +Accumulate the results of successive inode cluster buffer reads until there is +enough information to fill a single inode chunk record, which is 64 consecutive +numbers in the inumber keyspace. +If the chunk is sparse, the chunk record may include holes. + +Once the repair function accumulates one chunk's worth of data, it calls +``xfarray_append`` to add the inode btree record to the xfarray. +This xfarray is walked twice during the btree creation step -- once to populate +the inode btree with all inode chunk records, and a second time to populate the +free inode btree with records for chunks that have free non-sparse inodes. +The number of records for the inode btree is the number of xfarray records, +but the record count for the free inode btree has to be computed as inode chunk +records are stored in the xfarray. + +The proposed patchset is the +`AG btree repair +`_ +series. + +Case Study: Rebuilding the Space Reference Counts +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Reverse mapping records are used to rebuild the reference count information. +Reference counts are required for correct operation of copy on write for shared +file data. +Imagine the reverse mapping entries as rectangles representing extents of +physical blocks, and that the rectangles can be laid down to allow them to +overlap each other. +From the diagram below, it is apparent that a reference count record must start +or end wherever the height of the stack changes. +In other words, the record emission stimulus is level-triggered:: + + █ ███ + ██ █████ ████ ███ ██████ + ██ ████ ███████████ ████ █████████ + ████████████████████████████████ ███████████ + ^ ^ ^^ ^^ ^ ^^ ^^^ ^^^^ ^ ^^ ^ ^ ^ + 2 1 23 21 3 43 234 2123 1 01 2 3 0 + +The ondisk reference count btree does not store the refcount == 0 cases because +the free space btree already records which blocks are free. +Extents being used to stage copy-on-write operations should be the only records +with refcount == 1. +Single-owner file blocks aren't recorded in either the free space or the +reference count btrees. + +The high level process to rebuild the reference count btree is: + +1. Walk the reverse mapping records to generate ``struct xfs_refcount_irec`` + records for any space having more than one reverse mapping and add them to + the xfarray. + Any records owned by ``XFS_RMAP_OWN_COW`` are also added to the xfarray + because these are extents allocated to stage a copy on write operation and + are tracked in the refcount btree. + + Use any records owned by ``XFS_RMAP_OWN_REFC`` to create a bitmap of old + refcount btree blocks. + +2. Sort the records in physical extent order, putting the CoW staging extents + at the end of the xfarray. + This matches the sorting order of records in the refcount btree. + +3. Use the ``xfs_btree_bload_compute_geometry`` function to compute the number + of blocks needed for the new tree. + +4. Allocate the number of blocks computed in the previous step. + +5. Use ``xfs_btree_bload`` to write the xfarray records to btree blocks and + generate the internal node blocks. + +6. Commit the location of new btree root block to the AGF. + +7. Reap the old btree blocks using the bitmap created in step 1. + +Details are as follows; the same algorithm is used by ``xfs_repair`` to +generate refcount information from reverse mapping records. + +- Until the reverse mapping btree runs out of records: + + - Retrieve the next record from the btree and put it in a bag. + + - Collect all records with the same starting block from the btree and put + them in the bag. + + - While the bag isn't empty: + + - Among the mappings in the bag, compute the lowest block number where the + reference count changes. + This position will be either the starting block number of the next + unprocessed reverse mapping or the next block after the shortest mapping + in the bag. + + - Remove all mappings from the bag that end at this position. + + - Collect all reverse mappings that start at this position from the btree + and put them in the bag. + + - If the size of the bag changed and is greater than one, create a new + refcount record associating the block number range that we just walked to + the size of the bag. + +The bag-like structure in this case is a type 2 xfarray as discussed in the +:ref:`xfarray access patterns` section. +Reverse mappings are added to the bag using ``xfarray_store_anywhere`` and +removed via ``xfarray_unset``. +Bag members are examined through ``xfarray_iter`` loops. + +The proposed patchset is the +`AG btree repair +`_ +series. + +Case Study: Rebuilding File Fork Mapping Indices +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The high level process to rebuild a data/attr fork mapping btree is: + +1. Walk the reverse mapping records to generate ``struct xfs_bmbt_rec`` + records from the reverse mapping records for that inode and fork. + Append these records to an xfarray. + Compute the bitmap of the old bmap btree blocks from the ``BMBT_BLOCK`` + records. + +2. Use the ``xfs_btree_bload_compute_geometry`` function to compute the number + of blocks needed for the new tree. + +3. Sort the records in file offset order. + +4. If the extent records would fit in the inode fork immediate area, commit the + records to that immediate area and skip to step 8. + +5. Allocate the number of blocks computed in the previous step. + +6. Use ``xfs_btree_bload`` to write the xfarray records to btree blocks and + generate the internal node blocks. + +7. Commit the new btree root block to the inode fork immediate area. + +8. Reap the old btree blocks using the bitmap created in step 1. + +There are some complications here: +First, it's possible to move the fork offset to adjust the sizes of the +immediate areas if the data and attr forks are not both in BMBT format. +Second, if there are sufficiently few fork mappings, it may be possible to use +EXTENTS format instead of BMBT, which may require a conversion. +Third, the incore extent map must be reloaded carefully to avoid disturbing +any delayed allocation extents. + +The proposed patchset is the +`file mapping repair +`_ +series. + +.. _reaping: + +Reaping Old Metadata Blocks +--------------------------- + +Whenever online fsck builds a new data structure to replace one that is +suspect, there is a question of how to find and dispose of the blocks that +belonged to the old structure. +The laziest method of course is not to deal with them at all, but this slowly +leads to service degradations as space leaks out of the filesystem. +Hopefully, someone will schedule a rebuild of the free space information to +plug all those leaks. +Offline repair rebuilds all space metadata after recording the usage of +the files and directories that it decides not to clear, hence it can build new +structures in the discovered free space and avoid the question of reaping. + +As part of a repair, online fsck relies heavily on the reverse mapping records +to find space that is owned by the corresponding rmap owner yet truly free. +Cross referencing rmap records with other rmap records is necessary because +there may be other data structures that also think they own some of those +blocks (e.g. crosslinked trees). +Permitting the block allocator to hand them out again will not push the system +towards consistency. + +For space metadata, the process of finding extents to dispose of generally +follows this format: + +1. Create a bitmap of space used by data structures that must be preserved. + The space reservations used to create the new metadata can be used here if + the same rmap owner code is used to denote all of the objects being rebuilt. + +2. Survey the reverse mapping data to create a bitmap of space owned by the + same ``XFS_RMAP_OWN_*`` number for the metadata that is being preserved. + +3. Use the bitmap disunion operator to subtract (1) from (2). + The remaining set bits represent candidate extents that could be freed. + The process moves on to step 4 below. + +Repairs for file-based metadata such as extended attributes, directories, +symbolic links, quota files and realtime bitmaps are performed by building a +new structure attached to a temporary file and swapping the forks. +Afterward, the mappings in the old file fork are the candidate blocks for +disposal. + +The process for disposing of old extents is as follows: + +4. For each candidate extent, count the number of reverse mapping records for + the first block in that extent that do not have the same rmap owner for the + data structure being repaired. + + - If zero, the block has a single owner and can be freed. + + - If not, the block is part of a crosslinked structure and must not be + freed. + +5. Starting with the next block in the extent, figure out how many more blocks + have the same zero/nonzero other owner status as that first block. + +6. If the region is crosslinked, delete the reverse mapping entry for the + structure being repaired and move on to the next region. + +7. If the region is to be freed, mark any corresponding buffers in the buffer + cache as stale to prevent log writeback. + +8. Free the region and move on. + +However, there is one complication to this procedure. +Transactions are of finite size, so the reaping process must be careful to roll +the transactions to avoid overruns. +Overruns come from two sources: + +a. EFIs logged on behalf of space that is no longer occupied + +b. Log items for buffer invalidations + +This is also a window in which a crash during the reaping process can leak +blocks. +As stated earlier, online repair functions use very large transactions to +minimize the chances of this occurring. + +The proposed patchset is the +`preparation for bulk loading btrees +`_ +series. + +Case Study: Reaping After a Regular Btree Repair +```````````````````````````````````````````````` + +Old reference count and inode btrees are the easiest to reap because they have +rmap records with special owner codes: ``XFS_RMAP_OWN_REFC`` for the refcount +btree, and ``XFS_RMAP_OWN_INOBT`` for the inode and free inode btrees. +Creating a list of extents to reap the old btree blocks is quite simple, +conceptually: + +1. Lock the relevant AGI/AGF header buffers to prevent allocation and frees. + +2. For each reverse mapping record with an rmap owner corresponding to the + metadata structure being rebuilt, set the corresponding range in a bitmap. + +3. Walk the current data structures that have the same rmap owner. + For each block visited, clear that range in the above bitmap. + +4. Each set bit in the bitmap represents a block that could be a block from the + old data structures and hence is a candidate for reaping. + In other words, ``(rmap_records_owned_by & ~blocks_reachable_by_walk)`` + are the blocks that might be freeable. + +If it is possible to maintain the AGF lock throughout the repair (which is the +common case), then step 2 can be performed at the same time as the reverse +mapping record walk that creates the records for the new btree. + +Case Study: Rebuilding the Free Space Indices +````````````````````````````````````````````` + +The high level process to rebuild the free space indices is: + +1. Walk the reverse mapping records to generate ``struct xfs_alloc_rec_incore`` + records from the gaps in the reverse mapping btree. + +2. Append the records to an xfarray. + +3. Use the ``xfs_btree_bload_compute_geometry`` function to compute the number + of blocks needed for each new tree. + +4. Allocate the number of blocks computed in the previous step from the free + space information collected. + +5. Use ``xfs_btree_bload`` to write the xfarray records to btree blocks and + generate the internal node blocks for the free space by length index. + Call it again for the free space by block number index. + +6. Commit the locations of the new btree root blocks to the AGF. + +7. Reap the old btree blocks by looking for space that is not recorded by the + reverse mapping btree, the new free space btrees, or the AGFL. + +Repairing the free space btrees has three key complications over a regular +btree repair: + +First, free space is not explicitly tracked in the reverse mapping records. +Hence, the new free space records must be inferred from gaps in the physical +space component of the keyspace of the reverse mapping btree. + +Second, free space repairs cannot use the common btree reservation code because +new blocks are reserved out of the free space btrees. +This is impossible when repairing the free space btrees themselves. +However, repair holds the AGF buffer lock for the duration of the free space +index reconstruction, so it can use the collected free space information to +supply the blocks for the new free space btrees. +It is not necessary to back each reserved extent with an EFI because the new +free space btrees are constructed in what the ondisk filesystem thinks is +unowned space. +However, if reserving blocks for the new btrees from the collected free space +information changes the number of free space records, repair must re-estimate +the new free space btree geometry with the new record count until the +reservation is sufficient. +As part of committing the new btrees, repair must ensure that reverse mappings +are created for the reserved blocks and that unused reserved blocks are +inserted into the free space btrees. +Deferrred rmap and freeing operations are used to ensure that this transition +is atomic, similar to the other btree repair functions. + +Third, finding the blocks to reap after the repair is not overly +straightforward. +Blocks for the free space btrees and the reverse mapping btrees are supplied by +the AGFL. +Blocks put onto the AGFL have reverse mapping records with the owner +``XFS_RMAP_OWN_AG``. +This ownership is retained when blocks move from the AGFL into the free space +btrees or the reverse mapping btrees. +When repair walks reverse mapping records to synthesize free space records, it +creates a bitmap (``ag_owner_bitmap``) of all the space claimed by +``XFS_RMAP_OWN_AG`` records. +The repair context maintains a second bitmap corresponding to the rmap btree +blocks and the AGFL blocks (``rmap_agfl_bitmap``). +When the walk is complete, the bitmap disunion operation ``(ag_owner_bitmap & +~rmap_agfl_bitmap)`` computes the extents that are used by the old free space +btrees. +These blocks can then be reaped using the methods outlined above. + +The proposed patchset is the +`AG btree repair +`_ +series. + +.. _rmap_reap: + +Case Study: Reaping After Repairing Reverse Mapping Btrees +`````````````````````````````````````````````````````````` + +Old reverse mapping btrees are less difficult to reap after a repair. +As mentioned in the previous section, blocks on the AGFL, the two free space +btree blocks, and the reverse mapping btree blocks all have reverse mapping +records with ``XFS_RMAP_OWN_AG`` as the owner. +The full process of gathering reverse mapping records and building a new btree +are described in the case study of +:ref:`live rebuilds of rmap data `, but a crucial point from that +discussion is that the new rmap btree will not contain any records for the old +rmap btree, nor will the old btree blocks be tracked in the free space btrees. +The list of candidate reaping blocks is computed by setting the bits +corresponding to the gaps in the new rmap btree records, and then clearing the +bits corresponding to extents in the free space btrees and the current AGFL +blocks. +The result ``(new_rmapbt_gaps & ~(agfl | bnobt_records))`` are reaped using the +methods outlined above. + +The rest of the process of rebuildng the reverse mapping btree is discussed +in a separate :ref:`case study`. + +The proposed patchset is the +`AG btree repair +`_ +series. + +Case Study: Rebuilding the AGFL +``````````````````````````````` + +The allocation group free block list (AGFL) is repaired as follows: + +1. Create a bitmap for all the space that the reverse mapping data claims is + owned by ``XFS_RMAP_OWN_AG``. + +2. Subtract the space used by the two free space btrees and the rmap btree. + +3. Subtract any space that the reverse mapping data claims is owned by any + other owner, to avoid re-adding crosslinked blocks to the AGFL. + +4. Once the AGFL is full, reap any blocks leftover. + +5. The next operation to fix the freelist will right-size the list. + +See `fs/xfs/scrub/agheader_repair.c `_ for more details. -- GitLab From d697887193ef25df3d6e6a77d4108e7924eba2ca Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:49 -0700 Subject: [PATCH 2542/5631] xfs: document online file metadata repair code Add to the fifth chapter of the online fsck design documentation, where we discuss the details of the data structures and algorithms used by the kernel to repair file metadata. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 154 ++++++++++++++++++ 1 file changed, 154 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index e57d01924515..a047fc772a62 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -2997,3 +2997,157 @@ The allocation group free block list (AGFL) is repaired as follows: 5. The next operation to fix the freelist will right-size the list. See `fs/xfs/scrub/agheader_repair.c `_ for more details. + +Inode Record Repairs +-------------------- + +Inode records must be handled carefully, because they have both ondisk records +("dinodes") and an in-memory ("cached") representation. +There is a very high potential for cache coherency issues if online fsck is not +careful to access the ondisk metadata *only* when the ondisk metadata is so +badly damaged that the filesystem cannot load the in-memory representation. +When online fsck wants to open a damaged file for scrubbing, it must use +specialized resource acquisition functions that return either the in-memory +representation *or* a lock on whichever object is necessary to prevent any +update to the ondisk location. + +The only repairs that should be made to the ondisk inode buffers are whatever +is necessary to get the in-core structure loaded. +This means fixing whatever is caught by the inode cluster buffer and inode fork +verifiers, and retrying the ``iget`` operation. +If the second ``iget`` fails, the repair has failed. + +Once the in-memory representation is loaded, repair can lock the inode and can +subject it to comprehensive checks, repairs, and optimizations. +Most inode attributes are easy to check and constrain, or are user-controlled +arbitrary bit patterns; these are both easy to fix. +Dealing with the data and attr fork extent counts and the file block counts is +more complicated, because computing the correct value requires traversing the +forks, or if that fails, leaving the fields invalid and waiting for the fork +fsck functions to run. + +The proposed patchset is the +`inode +`_ +repair series. + +Quota Record Repairs +-------------------- + +Similar to inodes, quota records ("dquots") also have both ondisk records and +an in-memory representation, and hence are subject to the same cache coherency +issues. +Somewhat confusingly, both are known as dquots in the XFS codebase. + +The only repairs that should be made to the ondisk quota record buffers are +whatever is necessary to get the in-core structure loaded. +Once the in-memory representation is loaded, the only attributes needing +checking are obviously bad limits and timer values. + +Quota usage counters are checked, repaired, and discussed separately in the +section about :ref:`live quotacheck `. + +The proposed patchset is the +`quota +`_ +repair series. + +.. _fscounters: + +Freezing to Fix Summary Counters +-------------------------------- + +Filesystem summary counters track availability of filesystem resources such +as free blocks, free inodes, and allocated inodes. +This information could be compiled by walking the free space and inode indexes, +but this is a slow process, so XFS maintains a copy in the ondisk superblock +that should reflect the ondisk metadata, at least when the filesystem has been +unmounted cleanly. +For performance reasons, XFS also maintains incore copies of those counters, +which are key to enabling resource reservations for active transactions. +Writer threads reserve the worst-case quantities of resources from the +incore counter and give back whatever they don't use at commit time. +It is therefore only necessary to serialize on the superblock when the +superblock is being committed to disk. + +The lazy superblock counter feature introduced in XFS v5 took this even further +by training log recovery to recompute the summary counters from the AG headers, +which eliminated the need for most transactions even to touch the superblock. +The only time XFS commits the summary counters is at filesystem unmount. +To reduce contention even further, the incore counter is implemented as a +percpu counter, which means that each CPU is allocated a batch of blocks from a +global incore counter and can satisfy small allocations from the local batch. + +The high-performance nature of the summary counters makes it difficult for +online fsck to check them, since there is no way to quiesce a percpu counter +while the system is running. +Although online fsck can read the filesystem metadata to compute the correct +values of the summary counters, there's no way to hold the value of a percpu +counter stable, so it's quite possible that the counter will be out of date by +the time the walk is complete. +Earlier versions of online scrub would return to userspace with an incomplete +scan flag, but this is not a satisfying outcome for a system administrator. +For repairs, the in-memory counters must be stabilized while walking the +filesystem metadata to get an accurate reading and install it in the percpu +counter. + +To satisfy this requirement, online fsck must prevent other programs in the +system from initiating new writes to the filesystem, it must disable background +garbage collection threads, and it must wait for existing writer programs to +exit the kernel. +Once that has been established, scrub can walk the AG free space indexes, the +inode btrees, and the realtime bitmap to compute the correct value of all +four summary counters. +This is very similar to a filesystem freeze, though not all of the pieces are +necessary: + +- The final freeze state is set one higher than ``SB_FREEZE_COMPLETE`` to + prevent other threads from thawing the filesystem, or other scrub threads + from initiating another fscounters freeze. + +- It does not quiesce the log. + +With this code in place, it is now possible to pause the filesystem for just +long enough to check and correct the summary counters. + ++--------------------------------------------------------------------------+ +| **Historical Sidebar**: | ++--------------------------------------------------------------------------+ +| The initial implementation used the actual VFS filesystem freeze | +| mechanism to quiesce filesystem activity. | +| With the filesystem frozen, it is possible to resolve the counter values | +| with exact precision, but there are many problems with calling the VFS | +| methods directly: | +| | +| - Other programs can unfreeze the filesystem without our knowledge. | +| This leads to incorrect scan results and incorrect repairs. | +| | +| - Adding an extra lock to prevent others from thawing the filesystem | +| required the addition of a ``->freeze_super`` function to wrap | +| ``freeze_fs()``. | +| This in turn caused other subtle problems because it turns out that | +| the VFS ``freeze_super`` and ``thaw_super`` functions can drop the | +| last reference to the VFS superblock, and any subsequent access | +| becomes a UAF bug! | +| This can happen if the filesystem is unmounted while the underlying | +| block device has frozen the filesystem. | +| This problem could be solved by grabbing extra references to the | +| superblock, but it felt suboptimal given the other inadequacies of | +| this approach. | +| | +| - The log need not be quiesced to check the summary counters, but a VFS | +| freeze initiates one anyway. | +| This adds unnecessary runtime to live fscounter fsck operations. | +| | +| - Quiescing the log means that XFS flushes the (possibly incorrect) | +| counters to disk as part of cleaning the log. | +| | +| - A bug in the VFS meant that freeze could complete even when | +| sync_filesystem fails to flush the filesystem and returns an error. | +| This bug was fixed in Linux 5.17. | ++--------------------------------------------------------------------------+ + +The proposed patchset is the +`summary counter cleanup +`_ +series. -- GitLab From a0d856eede5a3ccfc7f0a4e02ee2e91ffab7f784 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:50 -0700 Subject: [PATCH 2543/5631] xfs: document full filesystem scans for online fsck Certain parts of the online fsck code need to scan every file in the entire filesystem. It is not acceptable to block the entire filesystem while this happens, which means that we need to be clever in allowing scans to coordinate with ongoing filesystem updates. We also need to hook the filesystem so that regular updates propagate to the staging records. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 681 ++++++++++++++++++ 1 file changed, 681 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index a047fc772a62..a768dfbbc4a5 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -3151,3 +3151,684 @@ The proposed patchset is the `summary counter cleanup `_ series. + +Full Filesystem Scans +--------------------- + +Certain types of metadata can only be checked by walking every file in the +entire filesystem to record observations and comparing the observations against +what's recorded on disk. +Like every other type of online repair, repairs are made by writing those +observations to disk in a replacement structure and committing it atomically. +However, it is not practical to shut down the entire filesystem to examine +hundreds of billions of files because the downtime would be excessive. +Therefore, online fsck must build the infrastructure to manage a live scan of +all the files in the filesystem. +There are two questions that need to be solved to perform a live walk: + +- How does scrub manage the scan while it is collecting data? + +- How does the scan keep abreast of changes being made to the system by other + threads? + +.. _iscan: + +Coordinated Inode Scans +``````````````````````` + +In the original Unix filesystems of the 1970s, each directory entry contained +an index number (*inumber*) which was used as an index into on ondisk array +(*itable*) of fixed-size records (*inodes*) describing a file's attributes and +its data block mapping. +This system is described by J. Lions, `"inode (5659)" +`_ in *Lions' Commentary on +UNIX, 6th Edition*, (Dept. of Computer Science, the University of New South +Wales, November 1977), pp. 18-2; and later by D. Ritchie and K. Thompson, +`"Implementation of the File System" +`_, from *The UNIX +Time-Sharing System*, (The Bell System Technical Journal, July 1978), pp. +1913-4. + +XFS retains most of this design, except now inumbers are search keys over all +the space in the data section filesystem. +They form a continuous keyspace that can be expressed as a 64-bit integer, +though the inodes themselves are sparsely distributed within the keyspace. +Scans proceed in a linear fashion across the inumber keyspace, starting from +``0x0`` and ending at ``0xFFFFFFFFFFFFFFFF``. +Naturally, a scan through a keyspace requires a scan cursor object to track the +scan progress. +Because this keyspace is sparse, this cursor contains two parts. +The first part of this scan cursor object tracks the inode that will be +examined next; call this the examination cursor. +Somewhat less obviously, the scan cursor object must also track which parts of +the keyspace have already been visited, which is critical for deciding if a +concurrent filesystem update needs to be incorporated into the scan data. +Call this the visited inode cursor. + +Advancing the scan cursor is a multi-step process encapsulated in +``xchk_iscan_iter``: + +1. Lock the AGI buffer of the AG containing the inode pointed to by the visited + inode cursor. + This guarantee that inodes in this AG cannot be allocated or freed while + advancing the cursor. + +2. Use the per-AG inode btree to look up the next inumber after the one that + was just visited, since it may not be keyspace adjacent. + +3. If there are no more inodes left in this AG: + + a. Move the examination cursor to the point of the inumber keyspace that + corresponds to the start of the next AG. + + b. Adjust the visited inode cursor to indicate that it has "visited" the + last possible inode in the current AG's inode keyspace. + XFS inumbers are segmented, so the cursor needs to be marked as having + visited the entire keyspace up to just before the start of the next AG's + inode keyspace. + + c. Unlock the AGI and return to step 1 if there are unexamined AGs in the + filesystem. + + d. If there are no more AGs to examine, set both cursors to the end of the + inumber keyspace. + The scan is now complete. + +4. Otherwise, there is at least one more inode to scan in this AG: + + a. Move the examination cursor ahead to the next inode marked as allocated + by the inode btree. + + b. Adjust the visited inode cursor to point to the inode just prior to where + the examination cursor is now. + Because the scanner holds the AGI buffer lock, no inodes could have been + created in the part of the inode keyspace that the visited inode cursor + just advanced. + +5. Get the incore inode for the inumber of the examination cursor. + By maintaining the AGI buffer lock until this point, the scanner knows that + it was safe to advance the examination cursor across the entire keyspace, + and that it has stabilized this next inode so that it cannot disappear from + the filesystem until the scan releases the incore inode. + +6. Drop the AGI lock and return the incore inode to the caller. + +Online fsck functions scan all files in the filesystem as follows: + +1. Start a scan by calling ``xchk_iscan_start``. + +2. Advance the scan cursor (``xchk_iscan_iter``) to get the next inode. + If one is provided: + + a. Lock the inode to prevent updates during the scan. + + b. Scan the inode. + + c. While still holding the inode lock, adjust the visited inode cursor + (``xchk_iscan_mark_visited``) to point to this inode. + + d. Unlock and release the inode. + +8. Call ``xchk_iscan_teardown`` to complete the scan. + +There are subtleties with the inode cache that complicate grabbing the incore +inode for the caller. +Obviously, it is an absolute requirement that the inode metadata be consistent +enough to load it into the inode cache. +Second, if the incore inode is stuck in some intermediate state, the scan +coordinator must release the AGI and push the main filesystem to get the inode +back into a loadable state. + +The proposed patches are the +`inode scanner +`_ +series. +The first user of the new functionality is the +`online quotacheck +`_ +series. + +Inode Management +```````````````` + +In regular filesystem code, references to allocated XFS incore inodes are +always obtained (``xfs_iget``) outside of transaction context because the +creation of the incore context for an existing file does not require metadata +updates. +However, it is important to note that references to incore inodes obtained as +part of file creation must be performed in transaction context because the +filesystem must ensure the atomicity of the ondisk inode btree index updates +and the initialization of the actual ondisk inode. + +References to incore inodes are always released (``xfs_irele``) outside of +transaction context because there are a handful of activities that might +require ondisk updates: + +- The VFS may decide to kick off writeback as part of a ``DONTCACHE`` inode + release. + +- Speculative preallocations need to be unreserved. + +- An unlinked file may have lost its last reference, in which case the entire + file must be inactivated, which involves releasing all of its resources in + the ondisk metadata and freeing the inode. + +These activities are collectively called inode inactivation. +Inactivation has two parts -- the VFS part, which initiates writeback on all +dirty file pages, and the XFS part, which cleans up XFS-specific information +and frees the inode if it was unlinked. +If the inode is unlinked (or unconnected after a file handle operation), the +kernel drops the inode into the inactivation machinery immediately. + +During normal operation, resource acquisition for an update follows this order +to avoid deadlocks: + +1. Inode reference (``iget``). + +2. Filesystem freeze protection, if repairing (``mnt_want_write_file``). + +3. Inode ``IOLOCK`` (VFS ``i_rwsem``) lock to control file IO. + +4. Inode ``MMAPLOCK`` (page cache ``invalidate_lock``) lock for operations that + can update page cache mappings. + +5. Log feature enablement. + +6. Transaction log space grant. + +7. Space on the data and realtime devices for the transaction. + +8. Incore dquot references, if a file is being repaired. + Note that they are not locked, merely acquired. + +9. Inode ``ILOCK`` for file metadata updates. + +10. AG header buffer locks / Realtime metadata inode ILOCK. + +11. Realtime metadata buffer locks, if applicable. + +12. Extent mapping btree blocks, if applicable. + +Resources are often released in the reverse order, though this is not required. +However, online fsck differs from regular XFS operations because it may examine +an object that normally is acquired in a later stage of the locking order, and +then decide to cross-reference the object with an object that is acquired +earlier in the order. +The next few sections detail the specific ways in which online fsck takes care +to avoid deadlocks. + +iget and irele During a Scrub +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +An inode scan performed on behalf of a scrub operation runs in transaction +context, and possibly with resources already locked and bound to it. +This isn't much of a problem for ``iget`` since it can operate in the context +of an existing transaction, as long as all of the bound resources are acquired +before the inode reference in the regular filesystem. + +When the VFS ``iput`` function is given a linked inode with no other +references, it normally puts the inode on an LRU list in the hope that it can +save time if another process re-opens the file before the system runs out +of memory and frees it. +Filesystem callers can short-circuit the LRU process by setting a ``DONTCACHE`` +flag on the inode to cause the kernel to try to drop the inode into the +inactivation machinery immediately. + +In the past, inactivation was always done from the process that dropped the +inode, which was a problem for scrub because scrub may already hold a +transaction, and XFS does not support nesting transactions. +On the other hand, if there is no scrub transaction, it is desirable to drop +otherwise unused inodes immediately to avoid polluting caches. +To capture these nuances, the online fsck code has a separate ``xchk_irele`` +function to set or clear the ``DONTCACHE`` flag to get the required release +behavior. + +Proposed patchsets include fixing +`scrub iget usage +`_ and +`dir iget usage +`_. + +Locking Inodes +^^^^^^^^^^^^^^ + +In regular filesystem code, the VFS and XFS will acquire multiple IOLOCK locks +in a well-known order: parent → child when updating the directory tree, and +in numerical order of the addresses of their ``struct inode`` object otherwise. +For regular files, the MMAPLOCK can be acquired after the IOLOCK to stop page +faults. +If two MMAPLOCKs must be acquired, they are acquired in numerical order of +the addresses of their ``struct address_space`` objects. +Due to the structure of existing filesystem code, IOLOCKs and MMAPLOCKs must be +acquired before transactions are allocated. +If two ILOCKs must be acquired, they are acquired in inumber order. + +Inode lock acquisition must be done carefully during a coordinated inode scan. +Online fsck cannot abide these conventions, because for a directory tree +scanner, the scrub process holds the IOLOCK of the file being scanned and it +needs to take the IOLOCK of the file at the other end of the directory link. +If the directory tree is corrupt because it contains a cycle, ``xfs_scrub`` +cannot use the regular inode locking functions and avoid becoming trapped in an +ABBA deadlock. + +Solving both of these problems is straightforward -- any time online fsck +needs to take a second lock of the same class, it uses trylock to avoid an ABBA +deadlock. +If the trylock fails, scrub drops all inode locks and use trylock loops to +(re)acquire all necessary resources. +Trylock loops enable scrub to check for pending fatal signals, which is how +scrub avoids deadlocking the filesystem or becoming an unresponsive process. +However, trylock loops means that online fsck must be prepared to measure the +resource being scrubbed before and after the lock cycle to detect changes and +react accordingly. + +.. _dirparent: + +Case Study: Finding a Directory Parent +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Consider the directory parent pointer repair code as an example. +Online fsck must verify that the dotdot dirent of a directory points up to a +parent directory, and that the parent directory contains exactly one dirent +pointing down to the child directory. +Fully validating this relationship (and repairing it if possible) requires a +walk of every directory on the filesystem while holding the child locked, and +while updates to the directory tree are being made. +The coordinated inode scan provides a way to walk the filesystem without the +possibility of missing an inode. +The child directory is kept locked to prevent updates to the dotdot dirent, but +if the scanner fails to lock a parent, it can drop and relock both the child +and the prospective parent. +If the dotdot entry changes while the directory is unlocked, then a move or +rename operation must have changed the child's parentage, and the scan can +exit early. + +The proposed patchset is the +`directory repair +`_ +series. + +.. _fshooks: + +Filesystem Hooks +````````````````` + +The second piece of support that online fsck functions need during a full +filesystem scan is the ability to stay informed about updates being made by +other threads in the filesystem, since comparisons against the past are useless +in a dynamic environment. +Two pieces of Linux kernel infrastructure enable online fsck to monitor regular +filesystem operations: filesystem hooks and :ref:`static keys`. + +Filesystem hooks convey information about an ongoing filesystem operation to +a downstream consumer. +In this case, the downstream consumer is always an online fsck function. +Because multiple fsck functions can run in parallel, online fsck uses the Linux +notifier call chain facility to dispatch updates to any number of interested +fsck processes. +Call chains are a dynamic list, which means that they can be configured at +run time. +Because these hooks are private to the XFS module, the information passed along +contains exactly what the checking function needs to update its observations. + +The current implementation of XFS hooks uses SRCU notifier chains to reduce the +impact to highly threaded workloads. +Regular blocking notifier chains use a rwsem and seem to have a much lower +overhead for single-threaded applications. +However, it may turn out that the combination of blocking chains and static +keys are a more performant combination; more study is needed here. + +The following pieces are necessary to hook a certain point in the filesystem: + +- A ``struct xfs_hooks`` object must be embedded in a convenient place such as + a well-known incore filesystem object. + +- Each hook must define an action code and a structure containing more context + about the action. + +- Hook providers should provide appropriate wrapper functions and structs + around the ``xfs_hooks`` and ``xfs_hook`` objects to take advantage of type + checking to ensure correct usage. + +- A callsite in the regular filesystem code must be chosen to call + ``xfs_hooks_call`` with the action code and data structure. + This place should be adjacent to (and not earlier than) the place where + the filesystem update is committed to the transaction. + In general, when the filesystem calls a hook chain, it should be able to + handle sleeping and should not be vulnerable to memory reclaim or locking + recursion. + However, the exact requirements are very dependent on the context of the hook + caller and the callee. + +- The online fsck function should define a structure to hold scan data, a lock + to coordinate access to the scan data, and a ``struct xfs_hook`` object. + The scanner function and the regular filesystem code must acquire resources + in the same order; see the next section for details. + +- The online fsck code must contain a C function to catch the hook action code + and data structure. + If the object being updated has already been visited by the scan, then the + hook information must be applied to the scan data. + +- Prior to unlocking inodes to start the scan, online fsck must call + ``xfs_hooks_setup`` to initialize the ``struct xfs_hook``, and + ``xfs_hooks_add`` to enable the hook. + +- Online fsck must call ``xfs_hooks_del`` to disable the hook once the scan is + complete. + +The number of hooks should be kept to a minimum to reduce complexity. +Static keys are used to reduce the overhead of filesystem hooks to nearly +zero when online fsck is not running. + +.. _liveupdate: + +Live Updates During a Scan +`````````````````````````` + +The code paths of the online fsck scanning code and the :ref:`hooked` +filesystem code look like this:: + + other program + ↓ + inode lock ←────────────────────┐ + ↓ │ + AG header lock │ + ↓ │ + filesystem function │ + ↓ │ + notifier call chain │ same + ↓ ├─── inode + scrub hook function │ lock + ↓ │ + scan data mutex ←──┐ same │ + ↓ ├─── scan │ + update scan data │ lock │ + ↑ │ │ + scan data mutex ←──┘ │ + ↑ │ + inode lock ←────────────────────┘ + ↑ + scrub function + ↑ + inode scanner + ↑ + xfs_scrub + +These rules must be followed to ensure correct interactions between the +checking code and the code making an update to the filesystem: + +- Prior to invoking the notifier call chain, the filesystem function being + hooked must acquire the same lock that the scrub scanning function acquires + to scan the inode. + +- The scanning function and the scrub hook function must coordinate access to + the scan data by acquiring a lock on the scan data. + +- Scrub hook function must not add the live update information to the scan + observations unless the inode being updated has already been scanned. + The scan coordinator has a helper predicate (``xchk_iscan_want_live_update``) + for this. + +- Scrub hook functions must not change the caller's state, including the + transaction that it is running. + They must not acquire any resources that might conflict with the filesystem + function being hooked. + +- The hook function can abort the inode scan to avoid breaking the other rules. + +The inode scan APIs are pretty simple: + +- ``xchk_iscan_start`` starts a scan + +- ``xchk_iscan_iter`` grabs a reference to the next inode in the scan or + returns zero if there is nothing left to scan + +- ``xchk_iscan_want_live_update`` to decide if an inode has already been + visited in the scan. + This is critical for hook functions to decide if they need to update the + in-memory scan information. + +- ``xchk_iscan_mark_visited`` to mark an inode as having been visited in the + scan + +- ``xchk_iscan_teardown`` to finish the scan + +This functionality is also a part of the +`inode scanner +`_ +series. + +.. _quotacheck: + +Case Study: Quota Counter Checking +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +It is useful to compare the mount time quotacheck code to the online repair +quotacheck code. +Mount time quotacheck does not have to contend with concurrent operations, so +it does the following: + +1. Make sure the ondisk dquots are in good enough shape that all the incore + dquots will actually load, and zero the resource usage counters in the + ondisk buffer. + +2. Walk every inode in the filesystem. + Add each file's resource usage to the incore dquot. + +3. Walk each incore dquot. + If the incore dquot is not being flushed, add the ondisk buffer backing the + incore dquot to a delayed write (delwri) list. + +4. Write the buffer list to disk. + +Like most online fsck functions, online quotacheck can't write to regular +filesystem objects until the newly collected metadata reflect all filesystem +state. +Therefore, online quotacheck records file resource usage to a shadow dquot +index implemented with a sparse ``xfarray``, and only writes to the real dquots +once the scan is complete. +Handling transactional updates is tricky because quota resource usage updates +are handled in phases to minimize contention on dquots: + +1. The inodes involved are joined and locked to a transaction. + +2. For each dquot attached to the file: + + a. The dquot is locked. + + b. A quota reservation is added to the dquot's resource usage. + The reservation is recorded in the transaction. + + c. The dquot is unlocked. + +3. Changes in actual quota usage are tracked in the transaction. + +4. At transaction commit time, each dquot is examined again: + + a. The dquot is locked again. + + b. Quota usage changes are logged and unused reservation is given back to + the dquot. + + c. The dquot is unlocked. + +For online quotacheck, hooks are placed in steps 2 and 4. +The step 2 hook creates a shadow version of the transaction dquot context +(``dqtrx``) that operates in a similar manner to the regular code. +The step 4 hook commits the shadow ``dqtrx`` changes to the shadow dquots. +Notice that both hooks are called with the inode locked, which is how the +live update coordinates with the inode scanner. + +The quotacheck scan looks like this: + +1. Set up a coordinated inode scan. + +2. For each inode returned by the inode scan iterator: + + a. Grab and lock the inode. + + b. Determine that inode's resource usage (data blocks, inode counts, + realtime blocks) and add that to the shadow dquots for the user, group, + and project ids associated with the inode. + + c. Unlock and release the inode. + +3. For each dquot in the system: + + a. Grab and lock the dquot. + + b. Check the dquot against the shadow dquots created by the scan and updated + by the live hooks. + +Live updates are key to being able to walk every quota record without +needing to hold any locks for a long duration. +If repairs are desired, the real and shadow dquots are locked and their +resource counts are set to the values in the shadow dquot. + +The proposed patchset is the +`online quotacheck +`_ +series. + +.. _nlinks: + +Case Study: File Link Count Checking +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +File link count checking also uses live update hooks. +The coordinated inode scanner is used to visit all directories on the +filesystem, and per-file link count records are stored in a sparse ``xfarray`` +indexed by inumber. +During the scanning phase, each entry in a directory generates observation +data as follows: + +1. If the entry is a dotdot (``'..'``) entry of the root directory, the + directory's parent link count is bumped because the root directory's dotdot + entry is self referential. + +2. If the entry is a dotdot entry of a subdirectory, the parent's backref + count is bumped. + +3. If the entry is neither a dot nor a dotdot entry, the target file's parent + count is bumped. + +4. If the target is a subdirectory, the parent's child link count is bumped. + +A crucial point to understand about how the link count inode scanner interacts +with the live update hooks is that the scan cursor tracks which *parent* +directories have been scanned. +In other words, the live updates ignore any update about ``A → B`` when A has +not been scanned, even if B has been scanned. +Furthermore, a subdirectory A with a dotdot entry pointing back to B is +accounted as a backref counter in the shadow data for A, since child dotdot +entries affect the parent's link count. +Live update hooks are carefully placed in all parts of the filesystem that +create, change, or remove directory entries, since those operations involve +bumplink and droplink. + +For any file, the correct link count is the number of parents plus the number +of child subdirectories. +Non-directories never have children of any kind. +The backref information is used to detect inconsistencies in the number of +links pointing to child subdirectories and the number of dotdot entries +pointing back. + +After the scan completes, the link count of each file can be checked by locking +both the inode and the shadow data, and comparing the link counts. +A second coordinated inode scan cursor is used for comparisons. +Live updates are key to being able to walk every inode without needing to hold +any locks between inodes. +If repairs are desired, the inode's link count is set to the value in the +shadow information. +If no parents are found, the file must be :ref:`reparented ` to the +orphanage to prevent the file from being lost forever. + +The proposed patchset is the +`file link count repair +`_ +series. + +.. _rmap_repair: + +Case Study: Rebuilding Reverse Mapping Records +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Most repair functions follow the same pattern: lock filesystem resources, +walk the surviving ondisk metadata looking for replacement metadata records, +and use an :ref:`in-memory array ` to store the gathered observations. +The primary advantage of this approach is the simplicity and modularity of the +repair code -- code and data are entirely contained within the scrub module, +do not require hooks in the main filesystem, and are usually the most efficient +in memory use. +A secondary advantage of this repair approach is atomicity -- once the kernel +decides a structure is corrupt, no other threads can access the metadata until +the kernel finishes repairing and revalidating the metadata. + +For repairs going on within a shard of the filesystem, these advantages +outweigh the delays inherent in locking the shard while repairing parts of the +shard. +Unfortunately, repairs to the reverse mapping btree cannot use the "standard" +btree repair strategy because it must scan every space mapping of every fork of +every file in the filesystem, and the filesystem cannot stop. +Therefore, rmap repair foregoes atomicity between scrub and repair. +It combines a :ref:`coordinated inode scanner `, :ref:`live update hooks +`, and an :ref:`in-memory rmap btree ` to complete the +scan for reverse mapping records. + +1. Set up an xfbtree to stage rmap records. + +2. While holding the locks on the AGI and AGF buffers acquired during the + scrub, generate reverse mappings for all AG metadata: inodes, btrees, CoW + staging extents, and the internal log. + +3. Set up an inode scanner. + +4. Hook into rmap updates for the AG being repaired so that the live scan data + can receive updates to the rmap btree from the rest of the filesystem during + the file scan. + +5. For each space mapping found in either fork of each file scanned, + decide if the mapping matches the AG of interest. + If so: + + a. Create a btree cursor for the in-memory btree. + + b. Use the rmap code to add the record to the in-memory btree. + + c. Use the :ref:`special commit function ` to write the + xfbtree changes to the xfile. + +6. For each live update received via the hook, decide if the owner has already + been scanned. + If so, apply the live update into the scan data: + + a. Create a btree cursor for the in-memory btree. + + b. Replay the operation into the in-memory btree. + + c. Use the :ref:`special commit function ` to write the + xfbtree changes to the xfile. + This is performed with an empty transaction to avoid changing the + caller's state. + +7. When the inode scan finishes, create a new scrub transaction and relock the + two AG headers. + +8. Compute the new btree geometry using the number of rmap records in the + shadow btree, like all other btree rebuilding functions. + +9. Allocate the number of blocks computed in the previous step. + +10. Perform the usual btree bulk loading and commit to install the new rmap + btree. + +11. Reap the old rmap btree blocks as discussed in the case study about how + to :ref:`reap after rmap btree repair `. + +12. Free the xfbtree now that it not needed. + +The proposed patchset is the +`rmap repair +`_ +series. -- GitLab From 2f754f7fb9fdd4e051cb273010c4244f95095835 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:50 -0700 Subject: [PATCH 2544/5631] xfs: document metadata file repair File-based metadata (such as xattrs and directories) can be extremely large. To reduce the memory requirements and maximize code reuse, it is very convenient to create a temporary file, use the regular dir/attr code to store salvaged information, and then atomically swap the extents between the file being repaired and the temporary file. Record the high level concepts behind how temporary files and atomic content swapping should work, and then present some case studies of what the actual repair functions do. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 536 ++++++++++++++++++ 1 file changed, 536 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index a768dfbbc4a5..facfde07e569 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -3389,6 +3389,8 @@ Proposed patchsets include fixing `dir iget usage `_. +.. _ilocking: + Locking Inodes ^^^^^^^^^^^^^^ @@ -3832,3 +3834,537 @@ The proposed patchset is the `rmap repair `_ series. + +Staging Repairs with Temporary Files on Disk +-------------------------------------------- + +XFS stores a substantial amount of metadata in file forks: directories, +extended attributes, symbolic link targets, free space bitmaps and summary +information for the realtime volume, and quota records. +File forks map 64-bit logical file fork space extents to physical storage space +extents, similar to how a memory management unit maps 64-bit virtual addresses +to physical memory addresses. +Therefore, file-based tree structures (such as directories and extended +attributes) use blocks mapped in the file fork offset address space that point +to other blocks mapped within that same address space, and file-based linear +structures (such as bitmaps and quota records) compute array element offsets in +the file fork offset address space. + +Because file forks can consume as much space as the entire filesystem, repairs +cannot be staged in memory, even when a paging scheme is available. +Therefore, online repair of file-based metadata createas a temporary file in +the XFS filesystem, writes a new structure at the correct offsets into the +temporary file, and atomically swaps the fork mappings (and hence the fork +contents) to commit the repair. +Once the repair is complete, the old fork can be reaped as necessary; if the +system goes down during the reap, the iunlink code will delete the blocks +during log recovery. + +**Note**: All space usage and inode indices in the filesystem *must* be +consistent to use a temporary file safely! +This dependency is the reason why online repair can only use pageable kernel +memory to stage ondisk space usage information. + +Swapping metadata extents with a temporary file requires the owner field of the +block headers to match the file being repaired and not the temporary file. The +directory, extended attribute, and symbolic link functions were all modified to +allow callers to specify owner numbers explicitly. + +There is a downside to the reaping process -- if the system crashes during the +reap phase and the fork extents are crosslinked, the iunlink processing will +fail because freeing space will find the extra reverse mappings and abort. + +Temporary files created for repair are similar to ``O_TMPFILE`` files created +by userspace. +They are not linked into a directory and the entire file will be reaped when +the last reference to the file is lost. +The key differences are that these files must have no access permission outside +the kernel at all, they must be specially marked to prevent them from being +opened by handle, and they must never be linked into the directory tree. + ++--------------------------------------------------------------------------+ +| **Historical Sidebar**: | ++--------------------------------------------------------------------------+ +| In the initial iteration of file metadata repair, the damaged metadata | +| blocks would be scanned for salvageable data; the extents in the file | +| fork would be reaped; and then a new structure would be built in its | +| place. | +| This strategy did not survive the introduction of the atomic repair | +| requirement expressed earlier in this document. | +| | +| The second iteration explored building a second structure at a high | +| offset in the fork from the salvage data, reaping the old extents, and | +| using a ``COLLAPSE_RANGE`` operation to slide the new extents into | +| place. | +| | +| This had many drawbacks: | +| | +| - Array structures are linearly addressed, and the regular filesystem | +| codebase does not have the concept of a linear offset that could be | +| applied to the record offset computation to build an alternate copy. | +| | +| - Extended attributes are allowed to use the entire attr fork offset | +| address space. | +| | +| - Even if repair could build an alternate copy of a data structure in a | +| different part of the fork address space, the atomic repair commit | +| requirement means that online repair would have to be able to perform | +| a log assisted ``COLLAPSE_RANGE`` operation to ensure that the old | +| structure was completely replaced. | +| | +| - A crash after construction of the secondary tree but before the range | +| collapse would leave unreachable blocks in the file fork. | +| This would likely confuse things further. | +| | +| - Reaping blocks after a repair is not a simple operation, and | +| initiating a reap operation from a restarted range collapse operation | +| during log recovery is daunting. | +| | +| - Directory entry blocks and quota records record the file fork offset | +| in the header area of each block. | +| An atomic range collapse operation would have to rewrite this part of | +| each block header. | +| Rewriting a single field in block headers is not a huge problem, but | +| it's something to be aware of. | +| | +| - Each block in a directory or extended attributes btree index contains | +| sibling and child block pointers. | +| Were the atomic commit to use a range collapse operation, each block | +| would have to be rewritten very carefully to preserve the graph | +| structure. | +| Doing this as part of a range collapse means rewriting a large number | +| of blocks repeatedly, which is not conducive to quick repairs. | +| | +| This lead to the introduction of temporary file staging. | ++--------------------------------------------------------------------------+ + +Using a Temporary File +`````````````````````` + +Online repair code should use the ``xrep_tempfile_create`` function to create a +temporary file inside the filesystem. +This allocates an inode, marks the in-core inode private, and attaches it to +the scrub context. +These files are hidden from userspace, may not be added to the directory tree, +and must be kept private. + +Temporary files only use two inode locks: the IOLOCK and the ILOCK. +The MMAPLOCK is not needed here, because there must not be page faults from +userspace for data fork blocks. +The usage patterns of these two locks are the same as for any other XFS file -- +access to file data are controlled via the IOLOCK, and access to file metadata +are controlled via the ILOCK. +Locking helpers are provided so that the temporary file and its lock state can +be cleaned up by the scrub context. +To comply with the nested locking strategy laid out in the :ref:`inode +locking` section, it is recommended that scrub functions use the +xrep_tempfile_ilock*_nowait lock helpers. + +Data can be written to a temporary file by two means: + +1. ``xrep_tempfile_copyin`` can be used to set the contents of a regular + temporary file from an xfile. + +2. The regular directory, symbolic link, and extended attribute functions can + be used to write to the temporary file. + +Once a good copy of a data file has been constructed in a temporary file, it +must be conveyed to the file being repaired, which is the topic of the next +section. + +The proposed patches are in the +`repair temporary files +`_ +series. + +Atomic Extent Swapping +---------------------- + +Once repair builds a temporary file with a new data structure written into +it, it must commit the new changes into the existing file. +It is not possible to swap the inumbers of two files, so instead the new +metadata must replace the old. +This suggests the need for the ability to swap extents, but the existing extent +swapping code used by the file defragmenting tool ``xfs_fsr`` is not sufficient +for online repair because: + +a. When the reverse-mapping btree is enabled, the swap code must keep the + reverse mapping information up to date with every exchange of mappings. + Therefore, it can only exchange one mapping per transaction, and each + transaction is independent. + +b. Reverse-mapping is critical for the operation of online fsck, so the old + defragmentation code (which swapped entire extent forks in a single + operation) is not useful here. + +c. Defragmentation is assumed to occur between two files with identical + contents. + For this use case, an incomplete exchange will not result in a user-visible + change in file contents, even if the operation is interrupted. + +d. Online repair needs to swap the contents of two files that are by definition + *not* identical. + For directory and xattr repairs, the user-visible contents might be the + same, but the contents of individual blocks may be very different. + +e. Old blocks in the file may be cross-linked with another structure and must + not reappear if the system goes down mid-repair. + +These problems are overcome by creating a new deferred operation and a new type +of log intent item to track the progress of an operation to exchange two file +ranges. +The new deferred operation type chains together the same transactions used by +the reverse-mapping extent swap code. +The new log item records the progress of the exchange to ensure that once an +exchange begins, it will always run to completion, even there are +interruptions. +The new ``XFS_SB_FEAT_INCOMPAT_LOG_ATOMIC_SWAP`` log-incompatible feature flag +in the superblock protects these new log item records from being replayed on +old kernels. + +The proposed patchset is the +`atomic extent swap +`_ +series. + ++--------------------------------------------------------------------------+ +| **Sidebar: Using Log-Incompatible Feature Flags** | ++--------------------------------------------------------------------------+ +| Starting with XFS v5, the superblock contains a | +| ``sb_features_log_incompat`` field to indicate that the log contains | +| records that might not readable by all kernels that could mount this | +| filesystem. | +| In short, log incompat features protect the log contents against kernels | +| that will not understand the contents. | +| Unlike the other superblock feature bits, log incompat bits are | +| ephemeral because an empty (clean) log does not need protection. | +| The log cleans itself after its contents have been committed into the | +| filesystem, either as part of an unmount or because the system is | +| otherwise idle. | +| Because upper level code can be working on a transaction at the same | +| time that the log cleans itself, it is necessary for upper level code to | +| communicate to the log when it is going to use a log incompatible | +| feature. | +| | +| The log coordinates access to incompatible features through the use of | +| one ``struct rw_semaphore`` for each feature. | +| The log cleaning code tries to take this rwsem in exclusive mode to | +| clear the bit; if the lock attempt fails, the feature bit remains set. | +| Filesystem code signals its intention to use a log incompat feature in a | +| transaction by calling ``xlog_use_incompat_feat``, which takes the rwsem | +| in shared mode. | +| The code supporting a log incompat feature should create wrapper | +| functions to obtain the log feature and call | +| ``xfs_add_incompat_log_feature`` to set the feature bits in the primary | +| superblock. | +| The superblock update is performed transactionally, so the wrapper to | +| obtain log assistance must be called just prior to the creation of the | +| transaction that uses the functionality. | +| For a file operation, this step must happen after taking the IOLOCK | +| and the MMAPLOCK, but before allocating the transaction. | +| When the transaction is complete, the ``xlog_drop_incompat_feat`` | +| function is called to release the feature. | +| The feature bit will not be cleared from the superblock until the log | +| becomes clean. | +| | +| Log-assisted extended attribute updates and atomic extent swaps both use | +| log incompat features and provide convenience wrappers around the | +| functionality. | ++--------------------------------------------------------------------------+ + +Mechanics of an Atomic Extent Swap +`````````````````````````````````` + +Swapping entire file forks is a complex task. +The goal is to exchange all file fork mappings between two file fork offset +ranges. +There are likely to be many extent mappings in each fork, and the edges of +the mappings aren't necessarily aligned. +Furthermore, there may be other updates that need to happen after the swap, +such as exchanging file sizes, inode flags, or conversion of fork data to local +format. +This is roughly the format of the new deferred extent swap work item: + +.. code-block:: c + + struct xfs_swapext_intent { + /* Inodes participating in the operation. */ + struct xfs_inode *sxi_ip1; + struct xfs_inode *sxi_ip2; + + /* File offset range information. */ + xfs_fileoff_t sxi_startoff1; + xfs_fileoff_t sxi_startoff2; + xfs_filblks_t sxi_blockcount; + + /* Set these file sizes after the operation, unless negative. */ + xfs_fsize_t sxi_isize1; + xfs_fsize_t sxi_isize2; + + /* XFS_SWAP_EXT_* log operation flags */ + uint64_t sxi_flags; + }; + +The new log intent item contains enough information to track two logical fork +offset ranges: ``(inode1, startoff1, blockcount)`` and ``(inode2, startoff2, +blockcount)``. +Each step of a swap operation exchanges the largest file range mapping possible +from one file to the other. +After each step in the swap operation, the two startoff fields are incremented +and the blockcount field is decremented to reflect the progress made. +The flags field captures behavioral parameters such as swapping the attr fork +instead of the data fork and other work to be done after the extent swap. +The two isize fields are used to swap the file size at the end of the operation +if the file data fork is the target of the swap operation. + +When the extent swap is initiated, the sequence of operations is as follows: + +1. Create a deferred work item for the extent swap. + At the start, it should contain the entirety of the file ranges to be + swapped. + +2. Call ``xfs_defer_finish`` to process the exchange. + This is encapsulated in ``xrep_tempswap_contents`` for scrub operations. + This will log an extent swap intent item to the transaction for the deferred + extent swap work item. + +3. Until ``sxi_blockcount`` of the deferred extent swap work item is zero, + + a. Read the block maps of both file ranges starting at ``sxi_startoff1`` and + ``sxi_startoff2``, respectively, and compute the longest extent that can + be swapped in a single step. + This is the minimum of the two ``br_blockcount`` s in the mappings. + Keep advancing through the file forks until at least one of the mappings + contains written blocks. + Mutual holes, unwritten extents, and extent mappings to the same physical + space are not exchanged. + + For the next few steps, this document will refer to the mapping that came + from file 1 as "map1", and the mapping that came from file 2 as "map2". + + b. Create a deferred block mapping update to unmap map1 from file 1. + + c. Create a deferred block mapping update to unmap map2 from file 2. + + d. Create a deferred block mapping update to map map1 into file 2. + + e. Create a deferred block mapping update to map map2 into file 1. + + f. Log the block, quota, and extent count updates for both files. + + g. Extend the ondisk size of either file if necessary. + + h. Log an extent swap done log item for the extent swap intent log item + that was read at the start of step 3. + + i. Compute the amount of file range that has just been covered. + This quantity is ``(map1.br_startoff + map1.br_blockcount - + sxi_startoff1)``, because step 3a could have skipped holes. + + j. Increase the starting offsets of ``sxi_startoff1`` and ``sxi_startoff2`` + by the number of blocks computed in the previous step, and decrease + ``sxi_blockcount`` by the same quantity. + This advances the cursor. + + k. Log a new extent swap intent log item reflecting the advanced state of + the work item. + + l. Return the proper error code (EAGAIN) to the deferred operation manager + to inform it that there is more work to be done. + The operation manager completes the deferred work in steps 3b-3e before + moving back to the start of step 3. + +4. Perform any post-processing. + This will be discussed in more detail in subsequent sections. + +If the filesystem goes down in the middle of an operation, log recovery will +find the most recent unfinished extent swap log intent item and restart from +there. +This is how extent swapping guarantees that an outside observer will either see +the old broken structure or the new one, and never a mismash of both. + +Preparation for Extent Swapping +``````````````````````````````` + +There are a few things that need to be taken care of before initiating an +atomic extent swap operation. +First, regular files require the page cache to be flushed to disk before the +operation begins, and directio writes to be quiesced. +Like any filesystem operation, extent swapping must determine the maximum +amount of disk space and quota that can be consumed on behalf of both files in +the operation, and reserve that quantity of resources to avoid an unrecoverable +out of space failure once it starts dirtying metadata. +The preparation step scans the ranges of both files to estimate: + +- Data device blocks needed to handle the repeated updates to the fork + mappings. +- Change in data and realtime block counts for both files. +- Increase in quota usage for both files, if the two files do not share the + same set of quota ids. +- The number of extent mappings that will be added to each file. +- Whether or not there are partially written realtime extents. + User programs must never be able to access a realtime file extent that maps + to different extents on the realtime volume, which could happen if the + operation fails to run to completion. + +The need for precise estimation increases the run time of the swap operation, +but it is very important to maintain correct accounting. +The filesystem must not run completely out of free space, nor can the extent +swap ever add more extent mappings to a fork than it can support. +Regular users are required to abide the quota limits, though metadata repairs +may exceed quota to resolve inconsistent metadata elsewhere. + +Special Features for Swapping Metadata File Extents +``````````````````````````````````````````````````` + +Extended attributes, symbolic links, and directories can set the fork format to +"local" and treat the fork as a literal area for data storage. +Metadata repairs must take extra steps to support these cases: + +- If both forks are in local format and the fork areas are large enough, the + swap is performed by copying the incore fork contents, logging both forks, + and committing. + The atomic extent swap mechanism is not necessary, since this can be done + with a single transaction. + +- If both forks map blocks, then the regular atomic extent swap is used. + +- Otherwise, only one fork is in local format. + The contents of the local format fork are converted to a block to perform the + swap. + The conversion to block format must be done in the same transaction that + logs the initial extent swap intent log item. + The regular atomic extent swap is used to exchange the mappings. + Special flags are set on the swap operation so that the transaction can be + rolled one more time to convert the second file's fork back to local format + so that the second file will be ready to go as soon as the ILOCK is dropped. + +Extended attributes and directories stamp the owning inode into every block, +but the buffer verifiers do not actually check the inode number! +Although there is no verification, it is still important to maintain +referential integrity, so prior to performing the extent swap, online repair +builds every block in the new data structure with the owner field of the file +being repaired. + +After a successful swap operation, the repair operation must reap the old fork +blocks by processing each fork mapping through the standard :ref:`file extent +reaping ` mechanism that is done post-repair. +If the filesystem should go down during the reap part of the repair, the +iunlink processing at the end of recovery will free both the temporary file and +whatever blocks were not reaped. +However, this iunlink processing omits the cross-link detection of online +repair, and is not completely foolproof. + +Swapping Temporary File Extents +``````````````````````````````` + +To repair a metadata file, online repair proceeds as follows: + +1. Create a temporary repair file. + +2. Use the staging data to write out new contents into the temporary repair + file. + The same fork must be written to as is being repaired. + +3. Commit the scrub transaction, since the swap estimation step must be + completed before transaction reservations are made. + +4. Call ``xrep_tempswap_trans_alloc`` to allocate a new scrub transaction with + the appropriate resource reservations, locks, and fill out a ``struct + xfs_swapext_req`` with the details of the swap operation. + +5. Call ``xrep_tempswap_contents`` to swap the contents. + +6. Commit the transaction to complete the repair. + +.. _rtsummary: + +Case Study: Repairing the Realtime Summary File +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In the "realtime" section of an XFS filesystem, free space is tracked via a +bitmap, similar to Unix FFS. +Each bit in the bitmap represents one realtime extent, which is a multiple of +the filesystem block size between 4KiB and 1GiB in size. +The realtime summary file indexes the number of free extents of a given size to +the offset of the block within the realtime free space bitmap where those free +extents begin. +In other words, the summary file helps the allocator find free extents by +length, similar to what the free space by count (cntbt) btree does for the data +section. + +The summary file itself is a flat file (with no block headers or checksums!) +partitioned into ``log2(total rt extents)`` sections containing enough 32-bit +counters to match the number of blocks in the rt bitmap. +Each counter records the number of free extents that start in that bitmap block +and can satisfy a power-of-two allocation request. + +To check the summary file against the bitmap: + +1. Take the ILOCK of both the realtime bitmap and summary files. + +2. For each free space extent recorded in the bitmap: + + a. Compute the position in the summary file that contains a counter that + represents this free extent. + + b. Read the counter from the xfile. + + c. Increment it, and write it back to the xfile. + +3. Compare the contents of the xfile against the ondisk file. + +To repair the summary file, write the xfile contents into the temporary file +and use atomic extent swap to commit the new contents. +The temporary file is then reaped. + +The proposed patchset is the +`realtime summary repair +`_ +series. + +Case Study: Salvaging Extended Attributes +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In XFS, extended attributes are implemented as a namespaced name-value store. +Values are limited in size to 64KiB, but there is no limit in the number of +names. +The attribute fork is unpartitioned, which means that the root of the attribute +structure is always in logical block zero, but attribute leaf blocks, dabtree +index blocks, and remote value blocks are intermixed. +Attribute leaf blocks contain variable-sized records that associate +user-provided names with the user-provided values. +Values larger than a block are allocated separate extents and written there. +If the leaf information expands beyond a single block, a directory/attribute +btree (``dabtree``) is created to map hashes of attribute names to entries +for fast lookup. + +Salvaging extended attributes is done as follows: + +1. Walk the attr fork mappings of the file being repaired to find the attribute + leaf blocks. + When one is found, + + a. Walk the attr leaf block to find candidate keys. + When one is found, + + 1. Check the name for problems, and ignore the name if there are. + + 2. Retrieve the value. + If that succeeds, add the name and value to the staging xfarray and + xfblob. + +2. If the memory usage of the xfarray and xfblob exceed a certain amount of + memory or there are no more attr fork blocks to examine, unlock the file and + add the staged extended attributes to the temporary file. + +3. Use atomic extent swapping to exchange the new and old extended attribute + structures. + The old attribute blocks are now attached to the temporary file. + +4. Reap the temporary file. + +The proposed patchset is the +`extended attribute repair +`_ +series. -- GitLab From a26aa25247bc91fefa08e4127a16046135f30a5f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:51 -0700 Subject: [PATCH 2545/5631] xfs: document directory tree repairs Directory tree repairs are the least complete part of online fsck, due to the lack of directory parent pointers. However, even without that feature, we can still make some corrections to the directory tree -- we can salvage as many directory entries as we can from a damaged directory, and we can reattach orphaned inodes to the lost+found, just as xfs_repair does now. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 419 ++++++++++++++++++ 1 file changed, 419 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index facfde07e569..6be097aa623b 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -2150,6 +2150,8 @@ reduce map/unmap cycles. Surprisingly, this reduces overall sort runtime by nearly half again after accounting for the application of heapsort directly onto xfile pages. +.. _xfblob: + Blob Storage ```````````` @@ -4368,3 +4370,420 @@ The proposed patchset is the `extended attribute repair `_ series. + +Fixing Directories +------------------ + +Fixing directories is difficult with currently available filesystem features, +since directory entries are not redundant. +The offline repair tool scans all inodes to find files with nonzero link count, +and then it scans all directories to establish parentage of those linked files. +Damaged files and directories are zapped, and files with no parent are +moved to the ``/lost+found`` directory. +It does not try to salvage anything. + +The best that online repair can do at this time is to read directory data +blocks and salvage any dirents that look plausible, correct link counts, and +move orphans back into the directory tree. +The salvage process is discussed in the case study at the end of this section. +The :ref:`file link count fsck ` code takes care of fixing link counts +and moving orphans to the ``/lost+found`` directory. + +Case Study: Salvaging Directories +````````````````````````````````` + +Unlike extended attributes, directory blocks are all the same size, so +salvaging directories is straightforward: + +1. Find the parent of the directory. + If the dotdot entry is not unreadable, try to confirm that the alleged + parent has a child entry pointing back to the directory being repaired. + Otherwise, walk the filesystem to find it. + +2. Walk the first partition of data fork of the directory to find the directory + entry data blocks. + When one is found, + + a. Walk the directory data block to find candidate entries. + When an entry is found: + + i. Check the name for problems, and ignore the name if there are. + + ii. Retrieve the inumber and grab the inode. + If that succeeds, add the name, inode number, and file type to the + staging xfarray and xblob. + +3. If the memory usage of the xfarray and xfblob exceed a certain amount of + memory or there are no more directory data blocks to examine, unlock the + directory and add the staged dirents into the temporary directory. + Truncate the staging files. + +4. Use atomic extent swapping to exchange the new and old directory structures. + The old directory blocks are now attached to the temporary file. + +5. Reap the temporary file. + +**Future Work Question**: Should repair revalidate the dentry cache when +rebuilding a directory? + +*Answer*: Yes, it should. + +In theory it is necessary to scan all dentry cache entries for a directory to +ensure that one of the following apply: + +1. The cached dentry reflects an ondisk dirent in the new directory. + +2. The cached dentry no longer has a corresponding ondisk dirent in the new + directory and the dentry can be purged from the cache. + +3. The cached dentry no longer has an ondisk dirent but the dentry cannot be + purged. + This is the problem case. + +Unfortunately, the current dentry cache design doesn't provide a means to walk +every child dentry of a specific directory, which makes this a hard problem. +There is no known solution. + +The proposed patchset is the +`directory repair +`_ +series. + +Parent Pointers +``````````````` + +A parent pointer is a piece of file metadata that enables a user to locate the +file's parent directory without having to traverse the directory tree from the +root. +Without them, reconstruction of directory trees is hindered in much the same +way that the historic lack of reverse space mapping information once hindered +reconstruction of filesystem space metadata. +The parent pointer feature, however, makes total directory reconstruction +possible. + +XFS parent pointers include the dirent name and location of the entry within +the parent directory. +In other words, child files use extended attributes to store pointers to +parents in the form ``(parent_inum, parent_gen, dirent_pos) → (dirent_name)``. +The directory checking process can be strengthened to ensure that the target of +each dirent also contains a parent pointer pointing back to the dirent. +Likewise, each parent pointer can be checked by ensuring that the target of +each parent pointer is a directory and that it contains a dirent matching +the parent pointer. +Both online and offline repair can use this strategy. + +**Note**: The ondisk format of parent pointers is not yet finalized. + ++--------------------------------------------------------------------------+ +| **Historical Sidebar**: | ++--------------------------------------------------------------------------+ +| Directory parent pointers were first proposed as an XFS feature more | +| than a decade ago by SGI. | +| Each link from a parent directory to a child file is mirrored with an | +| extended attribute in the child that could be used to identify the | +| parent directory. | +| Unfortunately, this early implementation had major shortcomings and was | +| never merged into Linux XFS: | +| | +| 1. The XFS codebase of the late 2000s did not have the infrastructure to | +| enforce strong referential integrity in the directory tree. | +| It did not guarantee that a change in a forward link would always be | +| followed up with the corresponding change to the reverse links. | +| | +| 2. Referential integrity was not integrated into offline repair. | +| Checking and repairs were performed on mounted filesystems without | +| taking any kernel or inode locks to coordinate access. | +| It is not clear how this actually worked properly. | +| | +| 3. The extended attribute did not record the name of the directory entry | +| in the parent, so the SGI parent pointer implementation cannot be | +| used to reconnect the directory tree. | +| | +| 4. Extended attribute forks only support 65,536 extents, which means | +| that parent pointer attribute creation is likely to fail at some | +| point before the maximum file link count is achieved. | +| | +| The original parent pointer design was too unstable for something like | +| a file system repair to depend on. | +| Allison Henderson, Chandan Babu, and Catherine Hoang are working on a | +| second implementation that solves all shortcomings of the first. | +| During 2022, Allison introduced log intent items to track physical | +| manipulations of the extended attribute structures. | +| This solves the referential integrity problem by making it possible to | +| commit a dirent update and a parent pointer update in the same | +| transaction. | +| Chandan increased the maximum extent counts of both data and attribute | +| forks, thereby ensuring that the extended attribute structure can grow | +| to handle the maximum hardlink count of any file. | ++--------------------------------------------------------------------------+ + +Case Study: Repairing Directories with Parent Pointers +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Directory rebuilding uses a :ref:`coordinated inode scan ` and +a :ref:`directory entry live update hook ` as follows: + +1. Set up a temporary directory for generating the new directory structure, + an xfblob for storing entry names, and an xfarray for stashing directory + updates. + +2. Set up an inode scanner and hook into the directory entry code to receive + updates on directory operations. + +3. For each parent pointer found in each file scanned, decide if the parent + pointer references the directory of interest. + If so: + + a. Stash an addname entry for this dirent in the xfarray for later. + + b. When finished scanning that file, flush the stashed updates to the + temporary directory. + +4. For each live directory update received via the hook, decide if the child + has already been scanned. + If so: + + a. Stash an addname or removename entry for this dirent update in the + xfarray for later. + We cannot write directly to the temporary directory because hook + functions are not allowed to modify filesystem metadata. + Instead, we stash updates in the xfarray and rely on the scanner thread + to apply the stashed updates to the temporary directory. + +5. When the scan is complete, atomically swap the contents of the temporary + directory and the directory being repaired. + The temporary directory now contains the damaged directory structure. + +6. Reap the temporary directory. + +7. Update the dirent position field of parent pointers as necessary. + This may require the queuing of a substantial number of xattr log intent + items. + +The proposed patchset is the +`parent pointers directory repair +`_ +series. + +**Unresolved Question**: How will repair ensure that the ``dirent_pos`` fields +match in the reconstructed directory? + +*Answer*: There are a few ways to solve this problem: + +1. The field could be designated advisory, since the other three values are + sufficient to find the entry in the parent. + However, this makes indexed key lookup impossible while repairs are ongoing. + +2. We could allow creating directory entries at specified offsets, which solves + the referential integrity problem but runs the risk that dirent creation + will fail due to conflicts with the free space in the directory. + + These conflicts could be resolved by appending the directory entry and + amending the xattr code to support updating an xattr key and reindexing the + dabtree, though this would have to be performed with the parent directory + still locked. + +3. Same as above, but remove the old parent pointer entry and add a new one + atomically. + +4. Change the ondisk xattr format to ``(parent_inum, name) → (parent_gen)``, + which would provide the attr name uniqueness that we require, without + forcing repair code to update the dirent position. + Unfortunately, this requires changes to the xattr code to support attr + names as long as 263 bytes. + +5. Change the ondisk xattr format to ``(parent_inum, hash(name)) → + (name, parent_gen)``. + If the hash is sufficiently resistant to collisions (e.g. sha256) then + this should provide the attr name uniqueness that we require. + Names shorter than 247 bytes could be stored directly. + +Discussion is ongoing under the `parent pointers patch deluge +`_. + +Case Study: Repairing Parent Pointers +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Online reconstruction of a file's parent pointer information works similarly to +directory reconstruction: + +1. Set up a temporary file for generating a new extended attribute structure, + an `xfblob` for storing parent pointer names, and an xfarray for + stashing parent pointer updates. + +2. Set up an inode scanner and hook into the directory entry code to receive + updates on directory operations. + +3. For each directory entry found in each directory scanned, decide if the + dirent references the file of interest. + If so: + + a. Stash an addpptr entry for this parent pointer in the xfblob and xfarray + for later. + + b. When finished scanning the directory, flush the stashed updates to the + temporary directory. + +4. For each live directory update received via the hook, decide if the parent + has already been scanned. + If so: + + a. Stash an addpptr or removepptr entry for this dirent update in the + xfarray for later. + We cannot write parent pointers directly to the temporary file because + hook functions are not allowed to modify filesystem metadata. + Instead, we stash updates in the xfarray and rely on the scanner thread + to apply the stashed parent pointer updates to the temporary file. + +5. Copy all non-parent pointer extended attributes to the temporary file. + +6. When the scan is complete, atomically swap the attribute fork of the + temporary file and the file being repaired. + The temporary file now contains the damaged extended attribute structure. + +7. Reap the temporary file. + +The proposed patchset is the +`parent pointers repair +`_ +series. + +Digression: Offline Checking of Parent Pointers +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Examining parent pointers in offline repair works differently because corrupt +files are erased long before directory tree connectivity checks are performed. +Parent pointer checks are therefore a second pass to be added to the existing +connectivity checks: + +1. After the set of surviving files has been established (i.e. phase 6), + walk the surviving directories of each AG in the filesystem. + This is already performed as part of the connectivity checks. + +2. For each directory entry found, record the name in an xfblob, and store + ``(child_ag_inum, parent_inum, parent_gen, dirent_pos)`` tuples in a + per-AG in-memory slab. + +3. For each AG in the filesystem, + + a. Sort the per-AG tuples in order of child_ag_inum, parent_inum, and + dirent_pos. + + b. For each inode in the AG, + + 1. Scan the inode for parent pointers. + Record the names in a per-file xfblob, and store ``(parent_inum, + parent_gen, dirent_pos)`` tuples in a per-file slab. + + 2. Sort the per-file tuples in order of parent_inum, and dirent_pos. + + 3. Position one slab cursor at the start of the inode's records in the + per-AG tuple slab. + This should be trivial since the per-AG tuples are in child inumber + order. + + 4. Position a second slab cursor at the start of the per-file tuple slab. + + 5. Iterate the two cursors in lockstep, comparing the parent_ino and + dirent_pos fields of the records under each cursor. + + a. Tuples in the per-AG list but not the per-file list are missing and + need to be written to the inode. + + b. Tuples in the per-file list but not the per-AG list are dangling + and need to be removed from the inode. + + c. For tuples in both lists, update the parent_gen and name components + of the parent pointer if necessary. + +4. Move on to examining link counts, as we do today. + +The proposed patchset is the +`offline parent pointers repair +`_ +series. + +Rebuilding directories from parent pointers in offline repair is very +challenging because it currently uses a single-pass scan of the filesystem +during phase 3 to decide which files are corrupt enough to be zapped. +This scan would have to be converted into a multi-pass scan: + +1. The first pass of the scan zaps corrupt inodes, forks, and attributes + much as it does now. + Corrupt directories are noted but not zapped. + +2. The next pass records parent pointers pointing to the directories noted + as being corrupt in the first pass. + This second pass may have to happen after the phase 4 scan for duplicate + blocks, if phase 4 is also capable of zapping directories. + +3. The third pass resets corrupt directories to an empty shortform directory. + Free space metadata has not been ensured yet, so repair cannot yet use the + directory building code in libxfs. + +4. At the start of phase 6, space metadata have been rebuilt. + Use the parent pointer information recorded during step 2 to reconstruct + the dirents and add them to the now-empty directories. + +This code has not yet been constructed. + +.. _orphanage: + +The Orphanage +------------- + +Filesystems present files as a directed, and hopefully acyclic, graph. +In other words, a tree. +The root of the filesystem is a directory, and each entry in a directory points +downwards either to more subdirectories or to non-directory files. +Unfortunately, a disruption in the directory graph pointers result in a +disconnected graph, which makes files impossible to access via regular path +resolution. + +Without parent pointers, the directory parent pointer online scrub code can +detect a dotdot entry pointing to a parent directory that doesn't have a link +back to the child directory and the file link count checker can detect a file +that isn't pointed to by any directory in the filesystem. +If such a file has a positive link count, the file is an orphan. + +With parent pointers, directories can be rebuilt by scanning parent pointers +and parent pointers can be rebuilt by scanning directories. +This should reduce the incidence of files ending up in ``/lost+found``. + +When orphans are found, they should be reconnected to the directory tree. +Offline fsck solves the problem by creating a directory ``/lost+found`` to +serve as an orphanage, and linking orphan files into the orphanage by using the +inumber as the name. +Reparenting a file to the orphanage does not reset any of its permissions or +ACLs. + +This process is more involved in the kernel than it is in userspace. +The directory and file link count repair setup functions must use the regular +VFS mechanisms to create the orphanage directory with all the necessary +security attributes and dentry cache entries, just like a regular directory +tree modification. + +Orphaned files are adopted by the orphanage as follows: + +1. Call ``xrep_orphanage_try_create`` at the start of the scrub setup function + to try to ensure that the lost and found directory actually exists. + This also attaches the orphanage directory to the scrub context. + +2. If the decision is made to reconnect a file, take the IOLOCK of both the + orphanage and the file being reattached. + The ``xrep_orphanage_iolock_two`` function follows the inode locking + strategy discussed earlier. + +3. Call ``xrep_orphanage_compute_blkres`` and ``xrep_orphanage_compute_name`` + to compute the new name in the orphanage and the block reservation required. + +4. Use ``xrep_orphanage_adoption_prep`` to reserve resources to the repair + transaction. + +5. Call ``xrep_orphanage_adopt`` to reparent the orphaned file into the lost + and found, and update the kernel dentry cache. + +The proposed patches are in the +`orphanage adoption +`_ +series. -- GitLab From af051dfb81111610eed89a1098874932d59e7d8f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:51 -0700 Subject: [PATCH 2546/5631] xfs: document the userspace fsck driver program Add the sixth chapter of the online fsck design documentation, where we discuss the details of the data structures and algorithms used by the driver program xfs_scrub. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 316 ++++++++++++++++++ 1 file changed, 316 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 6be097aa623b..6dcdf70626f0 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -315,6 +315,9 @@ The seven phases are as follows: 7. Re-check the summary counters and presents the caller with a summary of space usage and file counts. +This allocation of responsibilities will be :ref:`revisited ` +later in this document. + Steps for Each Scrub Item ------------------------- @@ -4787,3 +4790,316 @@ The proposed patches are in the `orphanage adoption `_ series. + +6. Userspace Algorithms and Data Structures +=========================================== + +This section discusses the key algorithms and data structures of the userspace +program, ``xfs_scrub``, that provide the ability to drive metadata checks and +repairs in the kernel, verify file data, and look for other potential problems. + +.. _scrubcheck: + +Checking Metadata +----------------- + +Recall the :ref:`phases of fsck work` outlined earlier. +That structure follows naturally from the data dependencies designed into the +filesystem from its beginnings in 1993. +In XFS, there are several groups of metadata dependencies: + +a. Filesystem summary counts depend on consistency within the inode indices, + the allocation group space btrees, and the realtime volume space + information. + +b. Quota resource counts depend on consistency within the quota file data + forks, inode indices, inode records, and the forks of every file on the + system. + +c. The naming hierarchy depends on consistency within the directory and + extended attribute structures. + This includes file link counts. + +d. Directories, extended attributes, and file data depend on consistency within + the file forks that map directory and extended attribute data to physical + storage media. + +e. The file forks depends on consistency within inode records and the space + metadata indices of the allocation groups and the realtime volume. + This includes quota and realtime metadata files. + +f. Inode records depends on consistency within the inode metadata indices. + +g. Realtime space metadata depend on the inode records and data forks of the + realtime metadata inodes. + +h. The allocation group metadata indices (free space, inodes, reference count, + and reverse mapping btrees) depend on consistency within the AG headers and + between all the AG metadata btrees. + +i. ``xfs_scrub`` depends on the filesystem being mounted and kernel support + for online fsck functionality. + +Therefore, a metadata dependency graph is a convenient way to schedule checking +operations in the ``xfs_scrub`` program: + +- Phase 1 checks that the provided path maps to an XFS filesystem and detect + the kernel's scrubbing abilities, which validates group (i). + +- Phase 2 scrubs groups (g) and (h) in parallel using a threaded workqueue. + +- Phase 3 scans inodes in parallel. + For each inode, groups (f), (e), and (d) are checked, in that order. + +- Phase 4 repairs everything in groups (i) through (d) so that phases 5 and 6 + may run reliably. + +- Phase 5 starts by checking groups (b) and (c) in parallel before moving on + to checking names. + +- Phase 6 depends on groups (i) through (b) to find file data blocks to verify, + to read them, and to report which blocks of which files are affected. + +- Phase 7 checks group (a), having validated everything else. + +Notice that the data dependencies between groups are enforced by the structure +of the program flow. + +Parallel Inode Scans +-------------------- + +An XFS filesystem can easily contain hundreds of millions of inodes. +Given that XFS targets installations with large high-performance storage, +it is desirable to scrub inodes in parallel to minimize runtime, particularly +if the program has been invoked manually from a command line. +This requires careful scheduling to keep the threads as evenly loaded as +possible. + +Early iterations of the ``xfs_scrub`` inode scanner naïvely created a single +workqueue and scheduled a single workqueue item per AG. +Each workqueue item walked the inode btree (with ``XFS_IOC_INUMBERS``) to find +inode chunks and then called bulkstat (``XFS_IOC_BULKSTAT``) to gather enough +information to construct file handles. +The file handle was then passed to a function to generate scrub items for each +metadata object of each inode. +This simple algorithm leads to thread balancing problems in phase 3 if the +filesystem contains one AG with a few large sparse files and the rest of the +AGs contain many smaller files. +The inode scan dispatch function was not sufficiently granular; it should have +been dispatching at the level of individual inodes, or, to constrain memory +consumption, inode btree records. + +Thanks to Dave Chinner, bounded workqueues in userspace enable ``xfs_scrub`` to +avoid this problem with ease by adding a second workqueue. +Just like before, the first workqueue is seeded with one workqueue item per AG, +and it uses INUMBERS to find inode btree chunks. +The second workqueue, however, is configured with an upper bound on the number +of items that can be waiting to be run. +Each inode btree chunk found by the first workqueue's workers are queued to the +second workqueue, and it is this second workqueue that queries BULKSTAT, +creates a file handle, and passes it to a function to generate scrub items for +each metadata object of each inode. +If the second workqueue is too full, the workqueue add function blocks the +first workqueue's workers until the backlog eases. +This doesn't completely solve the balancing problem, but reduces it enough to +move on to more pressing issues. + +The proposed patchsets are the scrub +`performance tweaks +`_ +and the +`inode scan rebalance +`_ +series. + +.. _scrubrepair: + +Scheduling Repairs +------------------ + +During phase 2, corruptions and inconsistencies reported in any AGI header or +inode btree are repaired immediately, because phase 3 relies on proper +functioning of the inode indices to find inodes to scan. +Failed repairs are rescheduled to phase 4. +Problems reported in any other space metadata are deferred to phase 4. +Optimization opportunities are always deferred to phase 4, no matter their +origin. + +During phase 3, corruptions and inconsistencies reported in any part of a +file's metadata are repaired immediately if all space metadata were validated +during phase 2. +Repairs that fail or cannot be repaired immediately are scheduled for phase 4. + +In the original design of ``xfs_scrub``, it was thought that repairs would be +so infrequent that the ``struct xfs_scrub_metadata`` objects used to +communicate with the kernel could also be used as the primary object to +schedule repairs. +With recent increases in the number of optimizations possible for a given +filesystem object, it became much more memory-efficient to track all eligible +repairs for a given filesystem object with a single repair item. +Each repair item represents a single lockable object -- AGs, metadata files, +individual inodes, or a class of summary information. + +Phase 4 is responsible for scheduling a lot of repair work in as quick a +manner as is practical. +The :ref:`data dependencies ` outlined earlier still apply, which +means that ``xfs_scrub`` must try to complete the repair work scheduled by +phase 2 before trying repair work scheduled by phase 3. +The repair process is as follows: + +1. Start a round of repair with a workqueue and enough workers to keep the CPUs + as busy as the user desires. + + a. For each repair item queued by phase 2, + + i. Ask the kernel to repair everything listed in the repair item for a + given filesystem object. + + ii. Make a note if the kernel made any progress in reducing the number + of repairs needed for this object. + + iii. If the object no longer requires repairs, revalidate all metadata + associated with this object. + If the revalidation succeeds, drop the repair item. + If not, requeue the item for more repairs. + + b. If any repairs were made, jump back to 1a to retry all the phase 2 items. + + c. For each repair item queued by phase 3, + + i. Ask the kernel to repair everything listed in the repair item for a + given filesystem object. + + ii. Make a note if the kernel made any progress in reducing the number + of repairs needed for this object. + + iii. If the object no longer requires repairs, revalidate all metadata + associated with this object. + If the revalidation succeeds, drop the repair item. + If not, requeue the item for more repairs. + + d. If any repairs were made, jump back to 1c to retry all the phase 3 items. + +2. If step 1 made any repair progress of any kind, jump back to step 1 to start + another round of repair. + +3. If there are items left to repair, run them all serially one more time. + Complain if the repairs were not successful, since this is the last chance + to repair anything. + +Corruptions and inconsistencies encountered during phases 5 and 7 are repaired +immediately. +Corrupt file data blocks reported by phase 6 cannot be recovered by the +filesystem. + +The proposed patchsets are the +`repair warning improvements +`_, +refactoring of the +`repair data dependency +`_ +and +`object tracking +`_, +and the +`repair scheduling +`_ +improvement series. + +Checking Names for Confusable Unicode Sequences +----------------------------------------------- + +If ``xfs_scrub`` succeeds in validating the filesystem metadata by the end of +phase 4, it moves on to phase 5, which checks for suspicious looking names in +the filesystem. +These names consist of the filesystem label, names in directory entries, and +the names of extended attributes. +Like most Unix filesystems, XFS imposes the sparest of constraints on the +contents of a name: + +- Slashes and null bytes are not allowed in directory entries. + +- Null bytes are not allowed in userspace-visible extended attributes. + +- Null bytes are not allowed in the filesystem label. + +Directory entries and attribute keys store the length of the name explicitly +ondisk, which means that nulls are not name terminators. +For this section, the term "naming domain" refers to any place where names are +presented together -- all the names in a directory, or all the attributes of a +file. + +Although the Unix naming constraints are very permissive, the reality of most +modern-day Linux systems is that programs work with Unicode character code +points to support international languages. +These programs typically encode those code points in UTF-8 when interfacing +with the C library because the kernel expects null-terminated names. +In the common case, therefore, names found in an XFS filesystem are actually +UTF-8 encoded Unicode data. + +To maximize its expressiveness, the Unicode standard defines separate control +points for various characters that render similarly or identically in writing +systems around the world. +For example, the character "Cyrillic Small Letter A" U+0430 "а" often renders +identically to "Latin Small Letter A" U+0061 "a". + +The standard also permits characters to be constructed in multiple ways -- +either by using a defined code point, or by combining one code point with +various combining marks. +For example, the character "Angstrom Sign U+212B "Å" can also be expressed +as "Latin Capital Letter A" U+0041 "A" followed by "Combining Ring Above" +U+030A "◌̊". +Both sequences render identically. + +Like the standards that preceded it, Unicode also defines various control +characters to alter the presentation of text. +For example, the character "Right-to-Left Override" U+202E can trick some +programs into rendering "moo\\xe2\\x80\\xaegnp.txt" as "mootxt.png". +A second category of rendering problems involves whitespace characters. +If the character "Zero Width Space" U+200B is encountered in a file name, the +name will render identically to a name that does not have the zero width +space. + +If two names within a naming domain have different byte sequences but render +identically, a user may be confused by it. +The kernel, in its indifference to upper level encoding schemes, permits this. +Most filesystem drivers persist the byte sequence names that are given to them +by the VFS. + +Techniques for detecting confusable names are explained in great detail in +sections 4 and 5 of the +`Unicode Security Mechanisms `_ +document. +When ``xfs_scrub`` detects UTF-8 encoding in use on a system, it uses the +Unicode normalization form NFD in conjunction with the confusable name +detection component of +`libicu `_ +to identify names with a directory or within a file's extended attributes that +could be confused for each other. +Names are also checked for control characters, non-rendering characters, and +mixing of bidirectional characters. +All of these potential issues are reported to the system administrator during +phase 5. + +Media Verification of File Data Extents +--------------------------------------- + +The system administrator can elect to initiate a media scan of all file data +blocks. +This scan after validation of all filesystem metadata (except for the summary +counters) as phase 6. +The scan starts by calling ``FS_IOC_GETFSMAP`` to scan the filesystem space map +to find areas that are allocated to file data fork extents. +Gaps betweeen data fork extents that are smaller than 64k are treated as if +they were data fork extents to reduce the command setup overhead. +When the space map scan accumulates a region larger than 32MB, a media +verification request is sent to the disk as a directio read of the raw block +device. + +If the verification read fails, ``xfs_scrub`` retries with single-block reads +to narrow down the failure to the specific region of the media and recorded. +When it has finished issuing verification requests, it again uses the space +mapping ioctl to map the recorded media errors back to metadata structures +and report what has been lost. +For media errors in blocks owned by files, parent pointers can be used to +construct file paths from inode numbers for user-friendly reporting. -- GitLab From 03786f0afb2ed5705a0478e14fea50a7f1a44f7e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:52 -0700 Subject: [PATCH 2547/5631] xfs: document future directions of online fsck Add the seventh and final chapter of the online fsck documentation, where we talk about future functionality that can tie in with the functionality provided by the online fsck patchset. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- .../filesystems/xfs-online-fsck-design.rst | 210 ++++++++++++++++++ 1 file changed, 210 insertions(+) diff --git a/Documentation/filesystems/xfs-online-fsck-design.rst b/Documentation/filesystems/xfs-online-fsck-design.rst index 6dcdf70626f0..791ab264b77e 100644 --- a/Documentation/filesystems/xfs-online-fsck-design.rst +++ b/Documentation/filesystems/xfs-online-fsck-design.rst @@ -5103,3 +5103,213 @@ mapping ioctl to map the recorded media errors back to metadata structures and report what has been lost. For media errors in blocks owned by files, parent pointers can be used to construct file paths from inode numbers for user-friendly reporting. + +7. Conclusion and Future Work +============================= + +It is hoped that the reader of this document has followed the designs laid out +in this document and now has some familiarity with how XFS performs online +rebuilding of its metadata indices, and how filesystem users can interact with +that functionality. +Although the scope of this work is daunting, it is hoped that this guide will +make it easier for code readers to understand what has been built, for whom it +has been built, and why. +Please feel free to contact the XFS mailing list with questions. + +FIEXCHANGE_RANGE +---------------- + +As discussed earlier, a second frontend to the atomic extent swap mechanism is +a new ioctl call that userspace programs can use to commit updates to files +atomically. +This frontend has been out for review for several years now, though the +necessary refinements to online repair and lack of customer demand mean that +the proposal has not been pushed very hard. + +Extent Swapping with Regular User Files +``````````````````````````````````````` + +As mentioned earlier, XFS has long had the ability to swap extents between +files, which is used almost exclusively by ``xfs_fsr`` to defragment files. +The earliest form of this was the fork swap mechanism, where the entire +contents of data forks could be exchanged between two files by exchanging the +raw bytes in each inode fork's immediate area. +When XFS v5 came along with self-describing metadata, this old mechanism grew +some log support to continue rewriting the owner fields of BMBT blocks during +log recovery. +When the reverse mapping btree was later added to XFS, the only way to maintain +the consistency of the fork mappings with the reverse mapping index was to +develop an iterative mechanism that used deferred bmap and rmap operations to +swap mappings one at a time. +This mechanism is identical to steps 2-3 from the procedure above except for +the new tracking items, because the atomic extent swap mechanism is an +iteration of an existing mechanism and not something totally novel. +For the narrow case of file defragmentation, the file contents must be +identical, so the recovery guarantees are not much of a gain. + +Atomic extent swapping is much more flexible than the existing swapext +implementations because it can guarantee that the caller never sees a mix of +old and new contents even after a crash, and it can operate on two arbitrary +file fork ranges. +The extra flexibility enables several new use cases: + +- **Atomic commit of file writes**: A userspace process opens a file that it + wants to update. + Next, it opens a temporary file and calls the file clone operation to reflink + the first file's contents into the temporary file. + Writes to the original file should instead be written to the temporary file. + Finally, the process calls the atomic extent swap system call + (``FIEXCHANGE_RANGE``) to exchange the file contents, thereby committing all + of the updates to the original file, or none of them. + +.. _swapext_if_unchanged: + +- **Transactional file updates**: The same mechanism as above, but the caller + only wants the commit to occur if the original file's contents have not + changed. + To make this happen, the calling process snapshots the file modification and + change timestamps of the original file before reflinking its data to the + temporary file. + When the program is ready to commit the changes, it passes the timestamps + into the kernel as arguments to the atomic extent swap system call. + The kernel only commits the changes if the provided timestamps match the + original file. + +- **Emulation of atomic block device writes**: Export a block device with a + logical sector size matching the filesystem block size to force all writes + to be aligned to the filesystem block size. + Stage all writes to a temporary file, and when that is complete, call the + atomic extent swap system call with a flag to indicate that holes in the + temporary file should be ignored. + This emulates an atomic device write in software, and can support arbitrary + scattered writes. + +Vectorized Scrub +---------------- + +As it turns out, the :ref:`refactoring ` of repair items mentioned +earlier was a catalyst for enabling a vectorized scrub system call. +Since 2018, the cost of making a kernel call has increased considerably on some +systems to mitigate the effects of speculative execution attacks. +This incentivizes program authors to make as few system calls as possible to +reduce the number of times an execution path crosses a security boundary. + +With vectorized scrub, userspace pushes to the kernel the identity of a +filesystem object, a list of scrub types to run against that object, and a +simple representation of the data dependencies between the selected scrub +types. +The kernel executes as much of the caller's plan as it can until it hits a +dependency that cannot be satisfied due to a corruption, and tells userspace +how much was accomplished. +It is hoped that ``io_uring`` will pick up enough of this functionality that +online fsck can use that instead of adding a separate vectored scrub system +call to XFS. + +The relevant patchsets are the +`kernel vectorized scrub +`_ +and +`userspace vectorized scrub +`_ +series. + +Quality of Service Targets for Scrub +------------------------------------ + +One serious shortcoming of the online fsck code is that the amount of time that +it can spend in the kernel holding resource locks is basically unbounded. +Userspace is allowed to send a fatal signal to the process which will cause +``xfs_scrub`` to exit when it reaches a good stopping point, but there's no way +for userspace to provide a time budget to the kernel. +Given that the scrub codebase has helpers to detect fatal signals, it shouldn't +be too much work to allow userspace to specify a timeout for a scrub/repair +operation and abort the operation if it exceeds budget. +However, most repair functions have the property that once they begin to touch +ondisk metadata, the operation cannot be cancelled cleanly, after which a QoS +timeout is no longer useful. + +Defragmenting Free Space +------------------------ + +Over the years, many XFS users have requested the creation of a program to +clear a portion of the physical storage underlying a filesystem so that it +becomes a contiguous chunk of free space. +Call this free space defragmenter ``clearspace`` for short. + +The first piece the ``clearspace`` program needs is the ability to read the +reverse mapping index from userspace. +This already exists in the form of the ``FS_IOC_GETFSMAP`` ioctl. +The second piece it needs is a new fallocate mode +(``FALLOC_FL_MAP_FREE_SPACE``) that allocates the free space in a region and +maps it to a file. +Call this file the "space collector" file. +The third piece is the ability to force an online repair. + +To clear all the metadata out of a portion of physical storage, clearspace +uses the new fallocate map-freespace call to map any free space in that region +to the space collector file. +Next, clearspace finds all metadata blocks in that region by way of +``GETFSMAP`` and issues forced repair requests on the data structure. +This often results in the metadata being rebuilt somewhere that is not being +cleared. +After each relocation, clearspace calls the "map free space" function again to +collect any newly freed space in the region being cleared. + +To clear all the file data out of a portion of the physical storage, clearspace +uses the FSMAP information to find relevant file data blocks. +Having identified a good target, it uses the ``FICLONERANGE`` call on that part +of the file to try to share the physical space with a dummy file. +Cloning the extent means that the original owners cannot overwrite the +contents; any changes will be written somewhere else via copy-on-write. +Clearspace makes its own copy of the frozen extent in an area that is not being +cleared, and uses ``FIEDEUPRANGE`` (or the :ref:`atomic extent swap +` feature) to change the target file's data extent +mapping away from the area being cleared. +When all other mappings have been moved, clearspace reflinks the space into the +space collector file so that it becomes unavailable. + +There are further optimizations that could apply to the above algorithm. +To clear a piece of physical storage that has a high sharing factor, it is +strongly desirable to retain this sharing factor. +In fact, these extents should be moved first to maximize sharing factor after +the operation completes. +To make this work smoothly, clearspace needs a new ioctl +(``FS_IOC_GETREFCOUNTS``) to report reference count information to userspace. +With the refcount information exposed, clearspace can quickly find the longest, +most shared data extents in the filesystem, and target them first. + +**Future Work Question**: How might the filesystem move inode chunks? + +*Answer*: To move inode chunks, Dave Chinner constructed a prototype program +that creates a new file with the old contents and then locklessly runs around +the filesystem updating directory entries. +The operation cannot complete if the filesystem goes down. +That problem isn't totally insurmountable: create an inode remapping table +hidden behind a jump label, and a log item that tracks the kernel walking the +filesystem to update directory entries. +The trouble is, the kernel can't do anything about open files, since it cannot +revoke them. + +**Future Work Question**: Can static keys be used to minimize the cost of +supporting ``revoke()`` on XFS files? + +*Answer*: Yes. +Until the first revocation, the bailout code need not be in the call path at +all. + +The relevant patchsets are the +`kernel freespace defrag +`_ +and +`userspace freespace defrag +`_ +series. + +Shrinking Filesystems +--------------------- + +Removing the end of the filesystem ought to be a simple matter of evacuating +the data and metadata at the end of the filesystem, and handing the freed space +to the shrink code. +That requires an evacuation of the space at end of the filesystem, which is a +use of free space defragmentation! -- GitLab From 774a99b47b588bf0bd9f65d3b241d5bba0b2fcb0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:53 -0700 Subject: [PATCH 2548/5631] xfs: give xfs_bmap_intent its own perag reference Give the xfs_bmap_intent an active reference to the perag structure data. This reference will be used to enable scrub intent draining functionality in subsequent patches. Later, shrink will use these passive references to know if an AG is quiesced or not. The reason why we take a passive ref for a file mapping operation is simple: we're committing to some sort of action involving space in an AG, so we want to indicate our interest in that AG. The space is already allocated, so we need to be able to operate on AGs that are offline or being shrunk. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 1 + fs/xfs/libxfs/xfs_bmap.h | 4 ++++ fs/xfs/xfs_bmap_item.c | 29 ++++++++++++++++++++++++++++- 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 34de6e6898c4..0b4fb3979bdc 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -6075,6 +6075,7 @@ __xfs_bmap_add( bi->bi_whichfork = whichfork; bi->bi_bmap = *bmap; + xfs_bmap_update_get_group(tp->t_mountp, bi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list); return 0; } diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index dd08361ca5a6..e5a492027aea 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -238,9 +238,13 @@ struct xfs_bmap_intent { enum xfs_bmap_intent_type bi_type; int bi_whichfork; struct xfs_inode *bi_owner; + struct xfs_perag *bi_pag; struct xfs_bmbt_irec bi_bmap; }; +void xfs_bmap_update_get_group(struct xfs_mount *mp, + struct xfs_bmap_intent *bi); + int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi); void xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip, struct xfs_bmbt_irec *imap); diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 6e2f0013380a..8f0f33d07d2c 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -24,6 +24,7 @@ #include "xfs_error.h" #include "xfs_log_priv.h" #include "xfs_log_recover.h" +#include "xfs_ag.h" struct kmem_cache *xfs_bui_cache; struct kmem_cache *xfs_bud_cache; @@ -363,6 +364,26 @@ xfs_bmap_update_create_done( return &xfs_trans_get_bud(tp, BUI_ITEM(intent))->bud_item; } +/* Take a passive ref to the AG containing the space we're mapping. */ +void +xfs_bmap_update_get_group( + struct xfs_mount *mp, + struct xfs_bmap_intent *bi) +{ + xfs_agnumber_t agno; + + agno = XFS_FSB_TO_AGNO(mp, bi->bi_bmap.br_startblock); + bi->bi_pag = xfs_perag_get(mp, agno); +} + +/* Release a passive AG ref after finishing mapping work. */ +static inline void +xfs_bmap_update_put_group( + struct xfs_bmap_intent *bi) +{ + xfs_perag_put(bi->bi_pag); +} + /* Process a deferred rmap update. */ STATIC int xfs_bmap_update_finish_item( @@ -381,6 +402,8 @@ xfs_bmap_update_finish_item( ASSERT(bi->bi_type == XFS_BMAP_UNMAP); return -EAGAIN; } + + xfs_bmap_update_put_group(bi); kmem_cache_free(xfs_bmap_intent_cache, bi); return error; } @@ -393,7 +416,7 @@ xfs_bmap_update_abort_intent( xfs_bui_release(BUI_ITEM(intent)); } -/* Cancel a deferred rmap update. */ +/* Cancel a deferred bmap update. */ STATIC void xfs_bmap_update_cancel_item( struct list_head *item) @@ -401,6 +424,8 @@ xfs_bmap_update_cancel_item( struct xfs_bmap_intent *bi; bi = container_of(item, struct xfs_bmap_intent, bi_list); + + xfs_bmap_update_put_group(bi); kmem_cache_free(xfs_bmap_intent_cache, bi); } @@ -509,10 +534,12 @@ xfs_bui_item_recover( fake.bi_bmap.br_state = (map->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM; + xfs_bmap_update_get_group(mp, &fake); error = xfs_trans_log_finish_bmap_update(tp, budp, &fake); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, map, sizeof(*map)); + xfs_bmap_update_put_group(&fake); if (error) goto err_cancel; -- GitLab From b2ccab3199aa7cea9154d80ea2585312c5f6eba0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:53 -0700 Subject: [PATCH 2549/5631] xfs: pass per-ag references to xfs_free_extent Pass a reference to the per-AG structure to xfs_free_extent. Most callers already have one, so we can eliminate unnecessary lookups. The one exception to this is the EFI code, which the next patch will fix. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ag.c | 6 ++---- fs/xfs/libxfs/xfs_alloc.c | 15 +++++---------- fs/xfs/libxfs/xfs_alloc.h | 8 +++++--- fs/xfs/libxfs/xfs_ialloc_btree.c | 7 +++++-- fs/xfs/libxfs/xfs_refcount_btree.c | 5 +++-- fs/xfs/scrub/repair.c | 3 ++- fs/xfs/xfs_extfree_item.c | 8 ++++++-- 7 files changed, 28 insertions(+), 24 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 86696a1c6891..ae45f546ed86 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -1043,10 +1043,8 @@ xfs_ag_extend_space( if (error) return error; - error = xfs_free_extent(tp, XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno, - be32_to_cpu(agf->agf_length) - len), - len, &XFS_RMAP_OINFO_SKIP_UPDATE, - XFS_AG_RESV_NONE); + error = xfs_free_extent(tp, pag, be32_to_cpu(agf->agf_length) - len, + len, &XFS_RMAP_OINFO_SKIP_UPDATE, XFS_AG_RESV_NONE); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 203f16c48c19..ea9ac2ad9d36 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -3596,7 +3596,8 @@ xfs_free_extent_fix_freelist( int __xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type, @@ -3604,12 +3605,9 @@ __xfs_free_extent( { struct xfs_mount *mp = tp->t_mountp; struct xfs_buf *agbp; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, bno); - xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, bno); struct xfs_agf *agf; int error; unsigned int busy_flags = 0; - struct xfs_perag *pag; ASSERT(len != 0); ASSERT(type != XFS_AG_RESV_AGFL); @@ -3618,10 +3616,9 @@ __xfs_free_extent( XFS_ERRTAG_FREE_EXTENT)) return -EIO; - pag = xfs_perag_get(mp, agno); error = xfs_free_extent_fix_freelist(tp, pag, &agbp); if (error) - goto err; + return error; agf = agbp->b_addr; if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) { @@ -3635,20 +3632,18 @@ __xfs_free_extent( goto err_release; } - error = xfs_free_ag_extent(tp, agbp, agno, agbno, len, oinfo, type); + error = xfs_free_ag_extent(tp, agbp, pag->pag_agno, agbno, len, oinfo, + type); if (error) goto err_release; if (skip_discard) busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD; xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags); - xfs_perag_put(pag); return 0; err_release: xfs_trans_brelse(tp, agbp); -err: - xfs_perag_put(pag); return error; } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 2b246d74c189..e12d86e3aeec 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -141,7 +141,8 @@ int xfs_alloc_vextent_first_ag(struct xfs_alloc_arg *args, int /* error */ __xfs_free_extent( struct xfs_trans *tp, /* transaction pointer */ - xfs_fsblock_t bno, /* starting block number of extent */ + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, /* length of extent */ const struct xfs_owner_info *oinfo, /* extent owner */ enum xfs_ag_resv_type type, /* block reservation type */ @@ -150,12 +151,13 @@ __xfs_free_extent( static inline int xfs_free_extent( struct xfs_trans *tp, - xfs_fsblock_t bno, + struct xfs_perag *pag, + xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type) { - return __xfs_free_extent(tp, bno, len, oinfo, type, false); + return __xfs_free_extent(tp, pag, agbno, len, oinfo, type, false); } int /* error */ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 9b28211d5a4c..1d2af50ac95b 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -156,9 +156,12 @@ __xfs_inobt_free_block( struct xfs_buf *bp, enum xfs_ag_resv_type resv) { + xfs_fsblock_t fsbno; + xfs_inobt_mod_blockcount(cur, -1); - return xfs_free_extent(cur->bc_tp, - XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)), 1, + fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); + return xfs_free_extent(cur->bc_tp, cur->bc_ag.pag, + XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1, &XFS_RMAP_OINFO_INOBT, resv); } diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index f3b860970b26..749e837de98d 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -112,8 +112,9 @@ xfs_refcountbt_free_block( XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1); be32_add_cpu(&agf->agf_refcount_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS); - error = xfs_free_extent(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC, - XFS_AG_RESV_METADATA); + error = xfs_free_extent(cur->bc_tp, cur->bc_ag.pag, + XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1, + &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA); if (error) return error; diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1b71174ec0d6..e12058a5f22e 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -598,7 +598,8 @@ xrep_reap_block( else if (resv == XFS_AG_RESV_AGFL) error = xrep_put_freelist(sc, agbno); else - error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv); + error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, oinfo, + resv); if (agf_bp != sc->sa.agf_bp) xfs_trans_brelse(sc->tp, agf_bp); if (error) diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 011b50469301..c1aae07467c9 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -350,6 +350,7 @@ xfs_trans_free_extent( struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_extent *extp; + struct xfs_perag *pag; uint next_extent; xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock); @@ -366,9 +367,12 @@ xfs_trans_free_extent( trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, xefi->xefi_blockcount); - error = __xfs_free_extent(tp, xefi->xefi_startblock, - xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE, + pag = xfs_perag_get(mp, agno); + error = __xfs_free_extent(tp, pag, agbno, xefi->xefi_blockcount, + &oinfo, XFS_AG_RESV_NONE, xefi->xefi_flags & XFS_EFI_SKIP_DISCARD); + xfs_perag_put(pag); + /* * Mark the transaction dirty, even on error. This ensures the * transaction is aborted, which: -- GitLab From f6b384631e1e3482c24e35b53adbd3da50e47e8f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:54 -0700 Subject: [PATCH 2550/5631] xfs: give xfs_extfree_intent its own perag reference Give the xfs_extfree_intent an passive reference to the perag structure data. This reference will be used to enable scrub intent draining functionality in subsequent patches. The space being freed must already be allocated, so we need to able to run even if the AG is being offlined or shrunk. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 7 +++-- fs/xfs/libxfs/xfs_alloc.h | 4 +++ fs/xfs/xfs_extfree_item.c | 58 +++++++++++++++++++++++++-------------- 3 files changed, 47 insertions(+), 22 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index ea9ac2ad9d36..d72483013b7d 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2405,6 +2405,7 @@ xfs_defer_agfl_block( trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); + xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list); } @@ -2421,8 +2422,8 @@ __xfs_free_extent_later( bool skip_discard) { struct xfs_extent_free_item *xefi; -#ifdef DEBUG struct xfs_mount *mp = tp->t_mountp; +#ifdef DEBUG xfs_agnumber_t agno; xfs_agblock_t agbno; @@ -2456,9 +2457,11 @@ __xfs_free_extent_later( } else { xefi->xefi_owner = XFS_RMAP_OWN_NULL; } - trace_xfs_bmap_free_defer(tp->t_mountp, + trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0, XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len); + + xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list); } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index e12d86e3aeec..5569cb2ede0d 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -237,9 +237,13 @@ struct xfs_extent_free_item { uint64_t xefi_owner; xfs_fsblock_t xefi_startblock;/* starting fs block number */ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ + struct xfs_perag *xefi_pag; unsigned int xefi_flags; }; +void xfs_extent_free_get_group(struct xfs_mount *mp, + struct xfs_extent_free_item *xefi); + #define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */ #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index c1aae07467c9..38b66fcfddc8 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -350,10 +350,7 @@ xfs_trans_free_extent( struct xfs_owner_info oinfo = { }; struct xfs_mount *mp = tp->t_mountp; struct xfs_extent *extp; - struct xfs_perag *pag; uint next_extent; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, - xefi->xefi_startblock); xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock); int error; @@ -364,14 +361,12 @@ xfs_trans_free_extent( if (xefi->xefi_flags & XFS_EFI_BMBT_BLOCK) oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK; - trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, - xefi->xefi_blockcount); + trace_xfs_bmap_free_deferred(tp->t_mountp, xefi->xefi_pag->pag_agno, 0, + agbno, xefi->xefi_blockcount); - pag = xfs_perag_get(mp, agno); - error = __xfs_free_extent(tp, pag, agbno, xefi->xefi_blockcount, - &oinfo, XFS_AG_RESV_NONE, + error = __xfs_free_extent(tp, xefi->xefi_pag, agbno, + xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE, xefi->xefi_flags & XFS_EFI_SKIP_DISCARD); - xfs_perag_put(pag); /* * Mark the transaction dirty, even on error. This ensures the @@ -400,14 +395,13 @@ xfs_extent_free_diff_items( const struct list_head *a, const struct list_head *b) { - struct xfs_mount *mp = priv; struct xfs_extent_free_item *ra; struct xfs_extent_free_item *rb; ra = container_of(a, struct xfs_extent_free_item, xefi_list); rb = container_of(b, struct xfs_extent_free_item, xefi_list); - return XFS_FSB_TO_AGNO(mp, ra->xefi_startblock) - - XFS_FSB_TO_AGNO(mp, rb->xefi_startblock); + + return ra->xefi_pag->pag_agno - rb->xefi_pag->pag_agno; } /* Log a free extent to the intent item. */ @@ -466,6 +460,26 @@ xfs_extent_free_create_done( return &xfs_trans_get_efd(tp, EFI_ITEM(intent), count)->efd_item; } +/* Take a passive ref to the AG containing the space we're freeing. */ +void +xfs_extent_free_get_group( + struct xfs_mount *mp, + struct xfs_extent_free_item *xefi) +{ + xfs_agnumber_t agno; + + agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock); + xefi->xefi_pag = xfs_perag_get(mp, agno); +} + +/* Release a passive AG ref after some freeing work. */ +static inline void +xfs_extent_free_put_group( + struct xfs_extent_free_item *xefi) +{ + xfs_perag_put(xefi->xefi_pag); +} + /* Process a free extent. */ STATIC int xfs_extent_free_finish_item( @@ -480,6 +494,8 @@ xfs_extent_free_finish_item( xefi = container_of(item, struct xfs_extent_free_item, xefi_list); error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi); + + xfs_extent_free_put_group(xefi); kmem_cache_free(xfs_extfree_item_cache, xefi); return error; } @@ -500,6 +516,8 @@ xfs_extent_free_cancel_item( struct xfs_extent_free_item *xefi; xefi = container_of(item, struct xfs_extent_free_item, xefi_list); + + xfs_extent_free_put_group(xefi); kmem_cache_free(xfs_extfree_item_cache, xefi); } @@ -530,24 +548,21 @@ xfs_agfl_free_finish_item( struct xfs_extent *extp; struct xfs_buf *agbp; int error; - xfs_agnumber_t agno; xfs_agblock_t agbno; uint next_extent; - struct xfs_perag *pag; xefi = container_of(item, struct xfs_extent_free_item, xefi_list); ASSERT(xefi->xefi_blockcount == 1); - agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock); agbno = XFS_FSB_TO_AGBNO(mp, xefi->xefi_startblock); oinfo.oi_owner = xefi->xefi_owner; - trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, xefi->xefi_blockcount); + trace_xfs_agfl_free_deferred(mp, xefi->xefi_pag->pag_agno, 0, agbno, + xefi->xefi_blockcount); - pag = xfs_perag_get(mp, agno); - error = xfs_alloc_read_agf(pag, tp, 0, &agbp); + error = xfs_alloc_read_agf(xefi->xefi_pag, tp, 0, &agbp); if (!error) - error = xfs_free_agfl_block(tp, agno, agbno, agbp, &oinfo); - xfs_perag_put(pag); + error = xfs_free_agfl_block(tp, xefi->xefi_pag->pag_agno, + agbno, agbp, &oinfo); /* * Mark the transaction dirty, even on error. This ensures the @@ -566,6 +581,7 @@ xfs_agfl_free_finish_item( extp->ext_len = xefi->xefi_blockcount; efdp->efd_next_extent++; + xfs_extent_free_put_group(xefi); kmem_cache_free(xfs_extfree_item_cache, xefi); return error; } @@ -636,7 +652,9 @@ xfs_efi_item_recover( fake.xefi_startblock = extp->ext_start; fake.xefi_blockcount = extp->ext_len; + xfs_extent_free_get_group(mp, &fake); error = xfs_trans_free_extent(tp, efdp, &fake); + xfs_extent_free_put_group(&fake); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, extp, sizeof(*extp)); -- GitLab From c13418e8eb375872ad297aeec5fa26277febc155 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:54 -0700 Subject: [PATCH 2551/5631] xfs: give xfs_rmap_intent its own perag reference Give the xfs_rmap_intent a passive reference to the perag structure data. This reference will be used to enable scrub intent draining functionality in subsequent patches. The space we're (reverse) mapping is already allocated, so we need to be able to operate even if the AG is being shrunk or offlined. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 29 +++++++++++------------------ fs/xfs/libxfs/xfs_rmap.h | 4 ++++ fs/xfs/xfs_rmap_item.c | 32 +++++++++++++++++++++++++++++--- 3 files changed, 44 insertions(+), 21 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index df720041cd3d..c2624d11f041 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2394,7 +2394,6 @@ xfs_rmap_finish_one( struct xfs_btree_cur **pcur) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_perag *pag; struct xfs_btree_cur *rcur; struct xfs_buf *agbp = NULL; int error = 0; @@ -2402,26 +2401,22 @@ xfs_rmap_finish_one( xfs_agblock_t bno; bool unwritten; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock)); bno = XFS_FSB_TO_AGBNO(mp, ri->ri_bmap.br_startblock); - trace_xfs_rmap_deferred(mp, pag->pag_agno, ri->ri_type, bno, + trace_xfs_rmap_deferred(mp, ri->ri_pag->pag_agno, ri->ri_type, bno, ri->ri_owner, ri->ri_whichfork, ri->ri_bmap.br_startoff, ri->ri_bmap.br_blockcount, ri->ri_bmap.br_state); - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE)) { - error = -EIO; - goto out_drop; - } - + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE)) + return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ rcur = *pcur; - if (rcur != NULL && rcur->bc_ag.pag != pag) { + if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) { xfs_rmap_finish_one_cleanup(tp, rcur, 0); rcur = NULL; *pcur = NULL; @@ -2432,15 +2427,13 @@ xfs_rmap_finish_one( * rmapbt, because a shape change could cause us to * allocate blocks. */ - error = xfs_free_extent_fix_freelist(tp, pag, &agbp); + error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp); if (error) - goto out_drop; - if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) { - error = -EFSCORRUPTED; - goto out_drop; - } + return error; + if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) + return -EFSCORRUPTED; - rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag); + rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag); } *pcur = rcur; @@ -2480,8 +2473,7 @@ xfs_rmap_finish_one( ASSERT(0); error = -EFSCORRUPTED; } -out_drop: - xfs_perag_put(pag); + return error; } @@ -2526,6 +2518,7 @@ __xfs_rmap_add( ri->ri_whichfork = whichfork; ri->ri_bmap = *bmap; + xfs_rmap_update_get_group(tp->t_mountp, ri); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list); } diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 2dac88cea28d..1472ae570a8a 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -162,8 +162,12 @@ struct xfs_rmap_intent { int ri_whichfork; uint64_t ri_owner; struct xfs_bmbt_irec ri_bmap; + struct xfs_perag *ri_pag; }; +void xfs_rmap_update_get_group(struct xfs_mount *mp, + struct xfs_rmap_intent *ri); + /* functions for updating the rmapbt based on bmbt map/unmap operations */ void xfs_rmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *imap); diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index a1619d67015f..739ddbd04a17 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -20,6 +20,7 @@ #include "xfs_error.h" #include "xfs_log_priv.h" #include "xfs_log_recover.h" +#include "xfs_ag.h" struct kmem_cache *xfs_rui_cache; struct kmem_cache *xfs_rud_cache; @@ -320,14 +321,13 @@ xfs_rmap_update_diff_items( const struct list_head *a, const struct list_head *b) { - struct xfs_mount *mp = priv; struct xfs_rmap_intent *ra; struct xfs_rmap_intent *rb; ra = container_of(a, struct xfs_rmap_intent, ri_list); rb = container_of(b, struct xfs_rmap_intent, ri_list); - return XFS_FSB_TO_AGNO(mp, ra->ri_bmap.br_startblock) - - XFS_FSB_TO_AGNO(mp, rb->ri_bmap.br_startblock); + + return ra->ri_pag->pag_agno - rb->ri_pag->pag_agno; } /* Log rmap updates in the intent item. */ @@ -390,6 +390,26 @@ xfs_rmap_update_create_done( return &xfs_trans_get_rud(tp, RUI_ITEM(intent))->rud_item; } +/* Take a passive ref to the AG containing the space we're rmapping. */ +void +xfs_rmap_update_get_group( + struct xfs_mount *mp, + struct xfs_rmap_intent *ri) +{ + xfs_agnumber_t agno; + + agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock); + ri->ri_pag = xfs_perag_get(mp, agno); +} + +/* Release a passive AG ref after finishing rmapping work. */ +static inline void +xfs_rmap_update_put_group( + struct xfs_rmap_intent *ri) +{ + xfs_perag_put(ri->ri_pag); +} + /* Process a deferred rmap update. */ STATIC int xfs_rmap_update_finish_item( @@ -405,6 +425,8 @@ xfs_rmap_update_finish_item( error = xfs_trans_log_finish_rmap_update(tp, RUD_ITEM(done), ri, state); + + xfs_rmap_update_put_group(ri); kmem_cache_free(xfs_rmap_intent_cache, ri); return error; } @@ -425,6 +447,8 @@ xfs_rmap_update_cancel_item( struct xfs_rmap_intent *ri; ri = container_of(item, struct xfs_rmap_intent, ri_list); + + xfs_rmap_update_put_group(ri); kmem_cache_free(xfs_rmap_intent_cache, ri); } @@ -559,11 +583,13 @@ xfs_rui_item_recover( fake.ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ? XFS_EXT_UNWRITTEN : XFS_EXT_NORM; + xfs_rmap_update_get_group(mp, &fake); error = xfs_trans_log_finish_rmap_update(tp, rudp, &fake, &rcur); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, map, sizeof(*map)); + xfs_rmap_update_put_group(&fake); if (error) goto abort_error; -- GitLab From 00e7b3bac1dc8961bd5aa9d39e79131c6bd81181 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:55 -0700 Subject: [PATCH 2552/5631] xfs: give xfs_refcount_intent its own perag reference Give the xfs_refcount_intent a passive reference to the perag structure data. This reference will be used to enable scrub intent draining functionality in subsequent patches. Any space being modified by a refcount intent is already allocated, so we need to be able to operate even if the AG is being shrunk or offlined. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_refcount.c | 33 ++++++++++++++------------------- fs/xfs/libxfs/xfs_refcount.h | 4 ++++ fs/xfs/xfs_refcount_item.c | 36 ++++++++++++++++++++++++++++++++---- 3 files changed, 50 insertions(+), 23 deletions(-) diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index bcf46aa0d08b..6dc968618e66 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1332,26 +1332,22 @@ xfs_refcount_finish_one( xfs_agblock_t bno; unsigned long nr_ops = 0; int shape_changes = 0; - struct xfs_perag *pag; - pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock)); bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock); trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock), ri->ri_type, XFS_FSB_TO_AGBNO(mp, ri->ri_startblock), ri->ri_blockcount); - if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) { - error = -EIO; - goto out_drop; - } + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE)) + return -EIO; /* * If we haven't gotten a cursor or the cursor AG doesn't match * the startblock, get one now. */ rcur = *pcur; - if (rcur != NULL && rcur->bc_ag.pag != pag) { + if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) { nr_ops = rcur->bc_ag.refc.nr_ops; shape_changes = rcur->bc_ag.refc.shape_changes; xfs_refcount_finish_one_cleanup(tp, rcur, 0); @@ -1359,12 +1355,12 @@ xfs_refcount_finish_one( *pcur = NULL; } if (rcur == NULL) { - error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING, - &agbp); + error = xfs_alloc_read_agf(ri->ri_pag, tp, + XFS_ALLOC_FLAG_FREEING, &agbp); if (error) - goto out_drop; + return error; - rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); + rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, ri->ri_pag); rcur->bc_ag.refc.nr_ops = nr_ops; rcur->bc_ag.refc.shape_changes = shape_changes; } @@ -1375,7 +1371,7 @@ xfs_refcount_finish_one( error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_INCREASE); if (error) - goto out_drop; + return error; if (ri->ri_blockcount > 0) error = xfs_refcount_continue_op(rcur, ri, bno); break; @@ -1383,31 +1379,29 @@ xfs_refcount_finish_one( error = xfs_refcount_adjust(rcur, &bno, &ri->ri_blockcount, XFS_REFCOUNT_ADJUST_DECREASE); if (error) - goto out_drop; + return error; if (ri->ri_blockcount > 0) error = xfs_refcount_continue_op(rcur, ri, bno); break; case XFS_REFCOUNT_ALLOC_COW: error = __xfs_refcount_cow_alloc(rcur, bno, ri->ri_blockcount); if (error) - goto out_drop; + return error; ri->ri_blockcount = 0; break; case XFS_REFCOUNT_FREE_COW: error = __xfs_refcount_cow_free(rcur, bno, ri->ri_blockcount); if (error) - goto out_drop; + return error; ri->ri_blockcount = 0; break; default: ASSERT(0); - error = -EFSCORRUPTED; + return -EFSCORRUPTED; } if (!error && ri->ri_blockcount > 0) - trace_xfs_refcount_finish_one_leftover(mp, pag->pag_agno, + trace_xfs_refcount_finish_one_leftover(mp, ri->ri_pag->pag_agno, ri->ri_type, bno, ri->ri_blockcount); -out_drop: - xfs_perag_put(pag); return error; } @@ -1435,6 +1429,7 @@ __xfs_refcount_add( ri->ri_startblock = startblock; ri->ri_blockcount = blockcount; + xfs_refcount_update_get_group(tp->t_mountp, ri); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list); } diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index c633477ce3ce..c89f0fcd1ee3 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -50,6 +50,7 @@ enum xfs_refcount_intent_type { struct xfs_refcount_intent { struct list_head ri_list; + struct xfs_perag *ri_pag; enum xfs_refcount_intent_type ri_type; xfs_extlen_t ri_blockcount; xfs_fsblock_t ri_startblock; @@ -67,6 +68,9 @@ xfs_refcount_check_domain( return true; } +void xfs_refcount_update_get_group(struct xfs_mount *mp, + struct xfs_refcount_intent *ri); + void xfs_refcount_increase_extent(struct xfs_trans *tp, struct xfs_bmbt_irec *irec); void xfs_refcount_decrease_extent(struct xfs_trans *tp, diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 48d771a76add..7edee9590ed6 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -20,6 +20,7 @@ #include "xfs_error.h" #include "xfs_log_priv.h" #include "xfs_log_recover.h" +#include "xfs_ag.h" struct kmem_cache *xfs_cui_cache; struct kmem_cache *xfs_cud_cache; @@ -279,14 +280,13 @@ xfs_refcount_update_diff_items( const struct list_head *a, const struct list_head *b) { - struct xfs_mount *mp = priv; struct xfs_refcount_intent *ra; struct xfs_refcount_intent *rb; ra = container_of(a, struct xfs_refcount_intent, ri_list); rb = container_of(b, struct xfs_refcount_intent, ri_list); - return XFS_FSB_TO_AGNO(mp, ra->ri_startblock) - - XFS_FSB_TO_AGNO(mp, rb->ri_startblock); + + return ra->ri_pag->pag_agno - rb->ri_pag->pag_agno; } /* Set the phys extent flags for this reverse mapping. */ @@ -365,6 +365,26 @@ xfs_refcount_update_create_done( return &xfs_trans_get_cud(tp, CUI_ITEM(intent))->cud_item; } +/* Take a passive ref to the AG containing the space we're refcounting. */ +void +xfs_refcount_update_get_group( + struct xfs_mount *mp, + struct xfs_refcount_intent *ri) +{ + xfs_agnumber_t agno; + + agno = XFS_FSB_TO_AGNO(mp, ri->ri_startblock); + ri->ri_pag = xfs_perag_get(mp, agno); +} + +/* Release a passive AG ref after finishing refcounting work. */ +static inline void +xfs_refcount_update_put_group( + struct xfs_refcount_intent *ri) +{ + xfs_perag_put(ri->ri_pag); +} + /* Process a deferred refcount update. */ STATIC int xfs_refcount_update_finish_item( @@ -386,6 +406,8 @@ xfs_refcount_update_finish_item( ri->ri_type == XFS_REFCOUNT_DECREASE); return -EAGAIN; } + + xfs_refcount_update_put_group(ri); kmem_cache_free(xfs_refcount_intent_cache, ri); return error; } @@ -406,6 +428,8 @@ xfs_refcount_update_cancel_item( struct xfs_refcount_intent *ri; ri = container_of(item, struct xfs_refcount_intent, ri_list); + + xfs_refcount_update_put_group(ri); kmem_cache_free(xfs_refcount_intent_cache, ri); } @@ -520,9 +544,13 @@ xfs_cui_item_recover( fake.ri_startblock = pmap->pe_startblock; fake.ri_blockcount = pmap->pe_len; - if (!requeue_only) + + if (!requeue_only) { + xfs_refcount_update_get_group(mp, &fake); error = xfs_trans_log_finish_refcount_update(tp, cudp, &fake, &rcur); + xfs_refcount_update_put_group(&fake); + } if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, &cuip->cui_format, -- GitLab From 9b2e5a234c89f097ec36f922763dfa1465dc06f8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:55 -0700 Subject: [PATCH 2553/5631] xfs: create traced helper to get extra perag references There are a few places in the XFS codebase where a caller has either an active or a passive reference to a perag structure and wants to give a passive reference to some other piece of code. Btree cursor creation and inode walks are good examples of this. Replace the open-coded logic with a helper to do this. The new function adds a few safeguards -- it checks that there's at least one reference to the perag structure passed in, and it records the refcount bump in the ftrace information. This makes it much easier to debug perag refcounting problems. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ag.c | 13 +++++++++++++ fs/xfs/libxfs/xfs_ag.h | 1 + fs/xfs/libxfs/xfs_alloc_btree.c | 4 +--- fs/xfs/libxfs/xfs_ialloc_btree.c | 4 +--- fs/xfs/libxfs/xfs_refcount_btree.c | 5 +---- fs/xfs/libxfs/xfs_rmap_btree.c | 5 +---- fs/xfs/xfs_iunlink_item.c | 4 +--- fs/xfs/xfs_iwalk.c | 5 ++--- fs/xfs/xfs_trace.h | 1 + 9 files changed, 22 insertions(+), 20 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index ae45f546ed86..2d8910046ed9 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -81,6 +81,19 @@ xfs_perag_get_tag( return pag; } +/* Get a passive reference to the given perag. */ +struct xfs_perag * +xfs_perag_hold( + struct xfs_perag *pag) +{ + ASSERT(atomic_read(&pag->pag_ref) > 0 || + atomic_read(&pag->pag_active_ref) > 0); + + trace_xfs_perag_hold(pag, _RET_IP_); + atomic_inc(&pag->pag_ref); + return pag; +} + void xfs_perag_put( struct xfs_perag *pag) diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 5e18536dfdce..8092eaba977d 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -134,6 +134,7 @@ void xfs_free_perag(struct xfs_mount *mp); struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno); struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno, unsigned int tag); +struct xfs_perag *xfs_perag_hold(struct xfs_perag *pag); void xfs_perag_put(struct xfs_perag *pag); /* Active AG references */ diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 0f29c7b1b39f..8e8416c14cec 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -492,9 +492,7 @@ xfs_allocbt_init_common( cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2); } - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; + cur->bc_ag.pag = xfs_perag_hold(pag); if (xfs_has_crc(mp)) cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 1d2af50ac95b..ad6c521f05eb 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -450,9 +450,7 @@ xfs_inobt_init_common( if (xfs_has_crc(mp)) cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; + cur->bc_ag.pag = xfs_perag_hold(pag); return cur; } diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 749e837de98d..03d2b01487a1 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -340,10 +340,7 @@ xfs_refcountbt_init_common( cur->bc_flags |= XFS_BTREE_CRC_BLOCKS; - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; - + cur->bc_ag.pag = xfs_perag_hold(pag); cur->bc_ag.refc.nr_ops = 0; cur->bc_ag.refc.shape_changes = 0; cur->bc_ops = &xfs_refcountbt_ops; diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index d3285684bb5e..56d074b42660 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -460,10 +460,7 @@ xfs_rmapbt_init_common( cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2); cur->bc_ops = &xfs_rmapbt_ops; - /* take a reference for the cursor */ - atomic_inc(&pag->pag_ref); - cur->bc_ag.pag = pag; - + cur->bc_ag.pag = xfs_perag_hold(pag); return cur; } diff --git a/fs/xfs/xfs_iunlink_item.c b/fs/xfs/xfs_iunlink_item.c index 43005ce8bd48..2ddccb172fa0 100644 --- a/fs/xfs/xfs_iunlink_item.c +++ b/fs/xfs/xfs_iunlink_item.c @@ -168,9 +168,7 @@ xfs_iunlink_log_inode( iup->ip = ip; iup->next_agino = next_agino; iup->old_agino = ip->i_next_unlinked; - - atomic_inc(&pag->pag_ref); - iup->pag = pag; + iup->pag = xfs_perag_hold(pag); xfs_trans_add_item(tp, &iup->item); tp->t_flags |= XFS_TRANS_DIRTY; diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index 21be93bf006d..b3275e8d47b6 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -667,11 +667,10 @@ xfs_iwalk_threaded( iwag->mp = mp; /* - * perag is being handed off to async work, so take another + * perag is being handed off to async work, so take a passive * reference for the async work to release. */ - atomic_inc(&pag->pag_ref); - iwag->pag = pag; + iwag->pag = xfs_perag_hold(pag); iwag->iwalk_fn = iwalk_fn; iwag->data = data; iwag->startino = startino; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 9c0006c55fec..db09bb771765 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -190,6 +190,7 @@ DEFINE_EVENT(xfs_perag_class, name, \ TP_ARGS(pag, caller_ip)) DEFINE_PERAG_REF_EVENT(xfs_perag_get); DEFINE_PERAG_REF_EVENT(xfs_perag_get_tag); +DEFINE_PERAG_REF_EVENT(xfs_perag_hold); DEFINE_PERAG_REF_EVENT(xfs_perag_put); DEFINE_PERAG_REF_EVENT(xfs_perag_grab); DEFINE_PERAG_REF_EVENT(xfs_perag_grab_tag); -- GitLab From 739a2fe0428f24c11fe652252c2f19ef7a697209 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:56 -0700 Subject: [PATCH 2554/5631] xfs: fix author and spdx headers on scrub/ files Fix the spdx tags to match current practice, and update the author contact information. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/agheader.c | 4 ++-- fs/xfs/scrub/agheader_repair.c | 4 ++-- fs/xfs/scrub/alloc.c | 4 ++-- fs/xfs/scrub/attr.c | 4 ++-- fs/xfs/scrub/attr.h | 2 +- fs/xfs/scrub/bitmap.c | 4 ++-- fs/xfs/scrub/bitmap.h | 4 ++-- fs/xfs/scrub/bmap.c | 4 ++-- fs/xfs/scrub/btree.c | 4 ++-- fs/xfs/scrub/btree.h | 4 ++-- fs/xfs/scrub/common.c | 4 ++-- fs/xfs/scrub/common.h | 4 ++-- fs/xfs/scrub/dabtree.c | 4 ++-- fs/xfs/scrub/dabtree.h | 4 ++-- fs/xfs/scrub/dir.c | 4 ++-- fs/xfs/scrub/fscounters.c | 2 +- fs/xfs/scrub/health.c | 4 ++-- fs/xfs/scrub/health.h | 4 ++-- fs/xfs/scrub/ialloc.c | 4 ++-- fs/xfs/scrub/inode.c | 4 ++-- fs/xfs/scrub/parent.c | 4 ++-- fs/xfs/scrub/quota.c | 4 ++-- fs/xfs/scrub/refcount.c | 4 ++-- fs/xfs/scrub/repair.c | 4 ++-- fs/xfs/scrub/repair.h | 4 ++-- fs/xfs/scrub/rmap.c | 4 ++-- fs/xfs/scrub/rtbitmap.c | 4 ++-- fs/xfs/scrub/scrub.c | 4 ++-- fs/xfs/scrub/scrub.h | 4 ++-- fs/xfs/scrub/symlink.c | 4 ++-- fs/xfs/scrub/trace.c | 4 ++-- fs/xfs/scrub/trace.h | 4 ++-- fs/xfs/scrub/xfs_scrub.h | 4 ++-- 33 files changed, 64 insertions(+), 64 deletions(-) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 4dd52b15f09c..ad8c592e11cf 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index c37e6d72760b..703e27cec327 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2018 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 3b38f4e2a537..16c4d57992b9 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 31529b9bf389..e0ed2123b5e2 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index 3590e10e3e62..f9680cb02a30 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2019 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_ATTR_H__ #define __XFS_SCRUB_ATTR_H__ diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index a255f09e9f0a..55b2af10aae9 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2018 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 900646b72de1..c5db165d397e 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2018 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_BITMAP_H__ #define __XFS_SCRUB_BITMAP_H__ diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index dbbc7037074c..d7a941936ceb 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 0fd36d5b4646..1a32b1fb75a2 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h index da61a53a0b61..1e3093d340c1 100644 --- a/fs/xfs/scrub/btree.h +++ b/fs/xfs/scrub/btree.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_BTREE_H__ #define __XFS_SCRUB_BTREE_H__ diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 848a8e32e56f..6eec71f92310 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index b73648d81d23..5fc0faeef18b 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_COMMON_H__ #define __XFS_SCRUB_COMMON_H__ diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index d17cee177085..245971a7bb1d 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h index 1f3515c6d5a8..a7ac9bf16db9 100644 --- a/fs/xfs/scrub/dabtree.h +++ b/fs/xfs/scrub/dabtree.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_DABTREE_H__ #define __XFS_SCRUB_DABTREE_H__ diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index d1b0f23c2c59..24c6a967c67d 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index f0c7f41897b9..df57e0314b46 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2019 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index aa65ec88a0c0..d416b8701c9a 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2019 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h index d0b938d3d028..2ef83db88a72 100644 --- a/fs/xfs/scrub/health.h +++ b/fs/xfs/scrub/health.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2019 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_HEALTH_H__ #define __XFS_SCRUB_HEALTH_H__ diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index e312be7cd375..9d5a51b4af4b 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 7a2f38e5202c..0d8d697ca265 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index d8dff3fd8053..c641b7d55a1d 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 9eeac8565394..a79e4c2cbd61 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index d9c1b3cea4a5..2db52a56c38e 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index e12058a5f22e..0b740f533959 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2018 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 840f74ec431c..b86cdfe506d8 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2018 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_REPAIR_H__ #define __XFS_SCRUB_REPAIR_H__ diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 229826b2e1c0..2b16c9192447 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 0a3bde64c675..924a45778a0f 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 07a7a75f987f..67dcc5efcbb1 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index b4d391b4c938..d72f2ccda091 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_SCRUB_H__ #define __XFS_SCRUB_SCRUB_H__ diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c index c1c99ffe7408..624f5e864c6f 100644 --- a/fs/xfs/scrub/symlink.c +++ b/fs/xfs/scrub/symlink.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index b5f94676c37c..315f872e1c91 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #include "xfs.h" #include "xfs_fs.h" diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 93ece6df02e3..9679ef7c3f01 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. See xfs_trace.h for documentation of diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h index 2ceae614ade8..76c209c74fff 100644 --- a/fs/xfs/scrub/xfs_scrub.h +++ b/fs/xfs/scrub/xfs_scrub.h @@ -1,7 +1,7 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017 Oracle. All Rights Reserved. - * Author: Darrick J. Wong + * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_H__ #define __XFS_SCRUB_H__ -- GitLab From ecc73f8a58c7844b04186726f8699ba97cec2ef9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:57 -0700 Subject: [PATCH 2555/5631] xfs: update copyright years for scrub/ files Update the copyright years in the scrub/ source code files. This isn't required, but it's helpful to remind myself just how long it's taken to develop this feature. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/agheader.c | 2 +- fs/xfs/scrub/agheader_repair.c | 2 +- fs/xfs/scrub/alloc.c | 2 +- fs/xfs/scrub/attr.c | 2 +- fs/xfs/scrub/attr.h | 2 +- fs/xfs/scrub/bitmap.c | 2 +- fs/xfs/scrub/bitmap.h | 2 +- fs/xfs/scrub/bmap.c | 2 +- fs/xfs/scrub/btree.c | 2 +- fs/xfs/scrub/btree.h | 2 +- fs/xfs/scrub/common.c | 2 +- fs/xfs/scrub/common.h | 2 +- fs/xfs/scrub/dabtree.c | 2 +- fs/xfs/scrub/dabtree.h | 2 +- fs/xfs/scrub/dir.c | 2 +- fs/xfs/scrub/fscounters.c | 2 +- fs/xfs/scrub/health.c | 2 +- fs/xfs/scrub/health.h | 2 +- fs/xfs/scrub/ialloc.c | 2 +- fs/xfs/scrub/inode.c | 2 +- fs/xfs/scrub/parent.c | 2 +- fs/xfs/scrub/quota.c | 2 +- fs/xfs/scrub/refcount.c | 2 +- fs/xfs/scrub/repair.c | 2 +- fs/xfs/scrub/repair.h | 2 +- fs/xfs/scrub/rmap.c | 2 +- fs/xfs/scrub/rtbitmap.c | 2 +- fs/xfs/scrub/scrub.c | 2 +- fs/xfs/scrub/scrub.h | 2 +- fs/xfs/scrub/symlink.c | 2 +- fs/xfs/scrub/trace.c | 2 +- fs/xfs/scrub/trace.h | 2 +- fs/xfs/scrub/xfs_scrub.h | 2 +- 33 files changed, 33 insertions(+), 33 deletions(-) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index ad8c592e11cf..c91819da1f5f 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 703e27cec327..edfb1dfb80a9 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2018 Oracle. All Rights Reserved. + * Copyright (C) 2018-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 16c4d57992b9..39e79b9536bc 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index e0ed2123b5e2..5573be3a3dfe 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index f9680cb02a30..bc6321552251 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * Copyright (C) 2019 Oracle. All Rights Reserved. + * Copyright (C) 2019-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_ATTR_H__ diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index 55b2af10aae9..ce8b17d76c0b 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2018 Oracle. All Rights Reserved. + * Copyright (C) 2018-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index c5db165d397e..85ec0e2792c5 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2018 Oracle. All Rights Reserved. + * Copyright (C) 2018-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_BITMAP_H__ diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index d7a941936ceb..f6d8cb938a02 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 1a32b1fb75a2..e54c1cfe64bf 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h index 1e3093d340c1..70461885c6c7 100644 --- a/fs/xfs/scrub/btree.h +++ b/fs/xfs/scrub/btree.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_BTREE_H__ diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 6eec71f92310..597e6aca8628 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 5fc0faeef18b..273a4331da05 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_COMMON_H__ diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 245971a7bb1d..c392c0765e5c 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h index a7ac9bf16db9..4f8c2138a1ec 100644 --- a/fs/xfs/scrub/dabtree.h +++ b/fs/xfs/scrub/dabtree.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_DABTREE_H__ diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 24c6a967c67d..b6081a3e1b91 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index df57e0314b46..a38006c71bff 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * Copyright (C) 2019 Oracle. All Rights Reserved. + * Copyright (C) 2019-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index d416b8701c9a..66e99b0f6049 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2019 Oracle. All Rights Reserved. + * Copyright (C) 2019-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/health.h b/fs/xfs/scrub/health.h index 2ef83db88a72..66a273f8585b 100644 --- a/fs/xfs/scrub/health.h +++ b/fs/xfs/scrub/health.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2019 Oracle. All Rights Reserved. + * Copyright (C) 2019-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_HEALTH_H__ diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 9d5a51b4af4b..b14270bd1c62 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 0d8d697ca265..dc66a1465f1b 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index c641b7d55a1d..d1db18250ee3 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index a79e4c2cbd61..b019c70c065a 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 2db52a56c38e..a5005b1d010d 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 0b740f533959..b800341aae69 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2018 Oracle. All Rights Reserved. + * Copyright (C) 2018-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index b86cdfe506d8..4fbb52228c48 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2018 Oracle. All Rights Reserved. + * Copyright (C) 2018-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_REPAIR_H__ diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 2b16c9192447..4dc79e1a675d 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index 924a45778a0f..e7dace7b4be8 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 67dcc5efcbb1..e8e2bee001e5 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index d72f2ccda091..72a5a8a64a87 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_SCRUB_H__ diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c index 624f5e864c6f..38708fb9a5d7 100644 --- a/fs/xfs/scrub/symlink.c +++ b/fs/xfs/scrub/symlink.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 315f872e1c91..0a975439d2b6 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #include "xfs.h" diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 9679ef7c3f01..81f7c3051a1a 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong * * NOTE: none of these tracepoints shall be considered a stable kernel ABI diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h index 76c209c74fff..a39befa743ce 100644 --- a/fs/xfs/scrub/xfs_scrub.h +++ b/fs/xfs/scrub/xfs_scrub.h @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Copyright (C) 2017 Oracle. All Rights Reserved. + * Copyright (C) 2017-2023 Oracle. All Rights Reserved. * Author: Darrick J. Wong */ #ifndef __XFS_SCRUB_H__ -- GitLab From 901489030441f30970f507b071a2f7ac3b194499 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:58 -0700 Subject: [PATCH 2556/5631] xfs: add a tracepoint to report incorrect extent refcounts Add a new tracepoint so that I can see exactly what and where we failed the refcount check. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/refcount.c | 5 ++++- fs/xfs/scrub/trace.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index a5005b1d010d..aaad13b1871f 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -13,6 +13,7 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" +#include "scrub/trace.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_ag.h" @@ -300,8 +301,10 @@ xchk_refcountbt_xref_rmap( goto out_free; xchk_refcountbt_process_rmap_fragments(&refchk); - if (irec->rc_refcount != refchk.seen) + if (irec->rc_refcount != refchk.seen) { + trace_xchk_refcount_incorrect(sc->sa.pag, irec, refchk.seen); xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + } out_free: list_for_each_entry_safe(frag, n, &refchk.fragments, list) { diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 81f7c3051a1a..ad25ae88fce1 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -30,6 +30,9 @@ TRACE_DEFINE_ENUM(XFS_BTNUM_FINOi); TRACE_DEFINE_ENUM(XFS_BTNUM_RMAPi); TRACE_DEFINE_ENUM(XFS_BTNUM_REFCi); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); + TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_PROBE); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_SB); TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_AGF); @@ -657,6 +660,38 @@ TRACE_EVENT(xchk_fscounters_within_range, __entry->old_value) ) +TRACE_EVENT(xchk_refcount_incorrect, + TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *irec, + xfs_nlink_t seen), + TP_ARGS(pag, irec, seen), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, domain) + __field(xfs_agblock_t, startblock) + __field(xfs_extlen_t, blockcount) + __field(xfs_nlink_t, refcount) + __field(xfs_nlink_t, seen) + ), + TP_fast_assign( + __entry->dev = pag->pag_mount->m_super->s_dev; + __entry->agno = pag->pag_agno; + __entry->domain = irec->rc_domain; + __entry->startblock = irec->rc_startblock; + __entry->blockcount = irec->rc_blockcount; + __entry->refcount = irec->rc_refcount; + __entry->seen = seen; + ), + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u seen %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), + __entry->startblock, + __entry->blockcount, + __entry->refcount, + __entry->seen) +) + /* repair tracepoints */ #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR) -- GitLab From d5c88131dbf01a30a222ad82d58e0c21a15f0d8e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:58 -0700 Subject: [PATCH 2557/5631] xfs: allow queued AG intents to drain before scrubbing When a writer thread executes a chain of log intent items, the AG header buffer locks will cycle during a transaction roll to get from one intent item to the next in a chain. Although scrub takes all AG header buffer locks, this isn't sufficient to guard against scrub checking an AG while that writer thread is in the middle of finishing a chain because there's no higher level locking primitive guarding allocation groups. When there's a collision, cross-referencing between data structures (e.g. rmapbt and refcountbt) yields false corruption events; if repair is running, this results in incorrect repairs, which is catastrophic. Fix this by adding to the perag structure the count of active intents and make scrub wait until it has both AG header buffer locks and the intent counter reaches zero. One quirk of the drain code is that deferred bmap updates also bump and drop the intent counter. A fundamental decision made during the design phase of the reverse mapping feature is that updates to the rmapbt records are always made by the same code that updates the primary metadata. In other words, callers of bmapi functions expect that the bmapi functions will queue deferred rmap updates. Some parts of the reflink code queue deferred refcount (CUI) and bmap (BUI) updates in the same head transaction, but the deferred work manager completely finishes the CUI before the BUI work is started. As a result, the CUI drops the intent count long before the deferred rmap (RUI) update even has a chance to bump the intent count. The only way to keep the intent count elevated between the CUI and RUI is for the BUI to bump the counter until the RUI has been created. A second quirk of the intent drain code is that deferred work items must increment the intent counter as soon as the work item is added to the transaction. When a BUI completes and queues an RUI, the RUI must increment the counter before the BUI decrements it. The only way to accomplish this is to require that the counter be bumped as soon as the deferred work item is created in memory. In the next patches we'll improve on this facility, but this patch provides the basic functionality. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/Kconfig | 4 ++ fs/xfs/Makefile | 2 + fs/xfs/libxfs/xfs_ag.c | 4 ++ fs/xfs/libxfs/xfs_ag.h | 8 +++ fs/xfs/libxfs/xfs_defer.c | 6 +- fs/xfs/scrub/common.c | 111 ++++++++++++++++++++++++++--- fs/xfs/scrub/health.c | 2 + fs/xfs/scrub/refcount.c | 2 + fs/xfs/xfs_bmap_item.c | 12 +++- fs/xfs/xfs_drain.c | 140 +++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_drain.h | 84 ++++++++++++++++++++++ fs/xfs/xfs_extfree_item.c | 4 +- fs/xfs/xfs_linux.h | 1 + fs/xfs/xfs_refcount_item.c | 4 +- fs/xfs/xfs_rmap_item.c | 4 +- fs/xfs/xfs_trace.h | 71 +++++++++++++++++++ 16 files changed, 438 insertions(+), 21 deletions(-) create mode 100644 fs/xfs/xfs_drain.c create mode 100644 fs/xfs/xfs_drain.h diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 9fac5ea8d0e4..ab24e683b440 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -93,10 +93,14 @@ config XFS_RT If unsure, say N. +config XFS_DRAIN_INTENTS + bool + config XFS_ONLINE_SCRUB bool "XFS online metadata check support" default n depends on XFS_FS + select XFS_DRAIN_INTENTS help If you say Y here you will be able to check metadata on a mounted XFS filesystem. This feature is intended to reduce diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 92d88dc3c9f7..3bdbc838c4d1 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -136,6 +136,8 @@ ifeq ($(CONFIG_MEMORY_FAILURE),y) xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o endif +xfs-$(CONFIG_XFS_DRAIN_INTENTS) += xfs_drain.o + # online scrub/repair ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 2d8910046ed9..1b078bbbf225 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -260,6 +260,7 @@ xfs_free_perag( spin_unlock(&mp->m_perag_lock); ASSERT(pag); XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0); + xfs_defer_drain_free(&pag->pag_intents_drain); cancel_delayed_work_sync(&pag->pag_blockgc_work); xfs_buf_hash_destroy(pag); @@ -385,6 +386,7 @@ xfs_initialize_perag( spin_lock_init(&pag->pag_state_lock); INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); + xfs_defer_drain_init(&pag->pag_intents_drain); init_waitqueue_head(&pag->pagb_wait); init_waitqueue_head(&pag->pag_active_wq); pag->pagb_count = 0; @@ -421,6 +423,7 @@ xfs_initialize_perag( return 0; out_remove_pag: + xfs_defer_drain_free(&pag->pag_intents_drain); radix_tree_delete(&mp->m_perag_tree, index); out_free_pag: kmem_free(pag); @@ -431,6 +434,7 @@ xfs_initialize_perag( if (!pag) break; xfs_buf_hash_destroy(pag); + xfs_defer_drain_free(&pag->pag_intents_drain); kmem_free(pag); } return error; diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 8092eaba977d..2e0aef87d633 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -101,6 +101,14 @@ struct xfs_perag { /* background prealloc block trimming */ struct delayed_work pag_blockgc_work; + /* + * We use xfs_drain to track the number of deferred log intent items + * that have been queued (but not yet processed) so that waiters (e.g. + * scrub) will not lock resources when other threads are in the middle + * of processing a chain of intent items only to find momentary + * inconsistencies. + */ + struct xfs_defer_drain pag_intents_drain; #endif /* __KERNEL__ */ }; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 5a321b783398..bcfb6a4203cd 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -397,6 +397,7 @@ xfs_defer_cancel_list( list_for_each_safe(pwi, n, &dfp->dfp_work) { list_del(pwi); dfp->dfp_count--; + trace_xfs_defer_cancel_item(mp, dfp, pwi); ops->cancel_item(pwi); } ASSERT(dfp->dfp_count == 0); @@ -476,6 +477,7 @@ xfs_defer_finish_one( list_for_each_safe(li, n, &dfp->dfp_work) { list_del(li); dfp->dfp_count--; + trace_xfs_defer_finish_item(tp->t_mountp, dfp, li); error = ops->finish_item(tp, dfp->dfp_done, li, &state); if (error == -EAGAIN) { int ret; @@ -623,7 +625,7 @@ xfs_defer_add( struct list_head *li) { struct xfs_defer_pending *dfp = NULL; - const struct xfs_defer_op_type *ops; + const struct xfs_defer_op_type *ops = defer_op_types[type]; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX); @@ -636,7 +638,6 @@ xfs_defer_add( if (!list_empty(&tp->t_dfops)) { dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending, dfp_list); - ops = defer_op_types[dfp->dfp_type]; if (dfp->dfp_type != type || (ops->max_items && dfp->dfp_count >= ops->max_items)) dfp = NULL; @@ -653,6 +654,7 @@ xfs_defer_add( } list_add_tail(li, &dfp->dfp_work); + trace_xfs_defer_add_item(tp->t_mountp, dfp, li); dfp->dfp_count++; } diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 597e6aca8628..2a496d1699a3 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -396,26 +396,19 @@ want_ag_read_header_failure( } /* - * Grab the perag structure and all the headers for an AG. + * Grab the AG header buffers for the attached perag structure. * * The headers should be released by xchk_ag_free, but as a fail safe we attach * all the buffers we grab to the scrub transaction so they'll all be freed - * when we cancel it. Returns ENOENT if we can't grab the perag structure. + * when we cancel it. */ -int -xchk_ag_read_headers( +static inline int +xchk_perag_read_headers( struct xfs_scrub *sc, - xfs_agnumber_t agno, struct xchk_ag *sa) { - struct xfs_mount *mp = sc->mp; int error; - ASSERT(!sa->pag); - sa->pag = xfs_perag_get(mp, agno); - if (!sa->pag) - return -ENOENT; - error = xfs_ialloc_read_agi(sa->pag, sc->tp, &sa->agi_bp); if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI)) return error; @@ -427,6 +420,102 @@ xchk_ag_read_headers( return 0; } +/* + * Grab the AG headers for the attached perag structure and wait for pending + * intents to drain. + */ +static int +xchk_perag_drain_and_lock( + struct xfs_scrub *sc) +{ + struct xchk_ag *sa = &sc->sa; + int error = 0; + + ASSERT(sa->pag != NULL); + ASSERT(sa->agi_bp == NULL); + ASSERT(sa->agf_bp == NULL); + + do { + if (xchk_should_terminate(sc, &error)) + return error; + + error = xchk_perag_read_headers(sc, sa); + if (error) + return error; + + /* + * If we've grabbed an inode for scrubbing then we assume that + * holding its ILOCK will suffice to coordinate with any intent + * chains involving this inode. + */ + if (sc->ip) + return 0; + + /* + * Decide if this AG is quiet enough for all metadata to be + * consistent with each other. XFS allows the AG header buffer + * locks to cycle across transaction rolls while processing + * chains of deferred ops, which means that there could be + * other threads in the middle of processing a chain of + * deferred ops. For regular operations we are careful about + * ordering operations to prevent collisions between threads + * (which is why we don't need a per-AG lock), but scrub and + * repair have to serialize against chained operations. + * + * We just locked all the AG headers buffers; now take a look + * to see if there are any intents in progress. If there are, + * drop the AG headers and wait for the intents to drain. + * Since we hold all the AG header locks for the duration of + * the scrub, this is the only time we have to sample the + * intents counter; any threads increasing it after this point + * can't possibly be in the middle of a chain of AG metadata + * updates. + * + * Obviously, this should be slanted against scrub and in favor + * of runtime threads. + */ + if (!xfs_perag_intent_busy(sa->pag)) + return 0; + + if (sa->agf_bp) { + xfs_trans_brelse(sc->tp, sa->agf_bp); + sa->agf_bp = NULL; + } + + if (sa->agi_bp) { + xfs_trans_brelse(sc->tp, sa->agi_bp); + sa->agi_bp = NULL; + } + + error = xfs_perag_intent_drain(sa->pag); + if (error == -ERESTARTSYS) + error = -EINTR; + } while (!error); + + return error; +} + +/* + * Grab the per-AG structure, grab all AG header buffers, and wait until there + * aren't any pending intents. Returns -ENOENT if we can't grab the perag + * structure. + */ +int +xchk_ag_read_headers( + struct xfs_scrub *sc, + xfs_agnumber_t agno, + struct xchk_ag *sa) +{ + struct xfs_mount *mp = sc->mp; + + ASSERT(!sa->pag); + sa->pag = xfs_perag_get(mp, agno); + if (!sa->pag) + return -ENOENT; + + return xchk_perag_drain_and_lock(sc); +} + /* Release all the AG btree cursors. */ void xchk_ag_btcur_free( diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index 66e99b0f6049..d2b2a1cb6533 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -7,6 +7,8 @@ #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index aaad13b1871f..756066f3dea2 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -7,6 +7,8 @@ #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_refcount.h" diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 8f0f33d07d2c..7551c3ec4ea5 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -373,7 +373,15 @@ xfs_bmap_update_get_group( xfs_agnumber_t agno; agno = XFS_FSB_TO_AGNO(mp, bi->bi_bmap.br_startblock); - bi->bi_pag = xfs_perag_get(mp, agno); + + /* + * Bump the intent count on behalf of the deferred rmap and refcount + * intent items that that we can queue when we finish this bmap work. + * This new intent item will bump the intent count before the bmap + * intent drops the intent count, ensuring that the intent count + * remains nonzero across the transaction roll. + */ + bi->bi_pag = xfs_perag_intent_get(mp, agno); } /* Release a passive AG ref after finishing mapping work. */ @@ -381,7 +389,7 @@ static inline void xfs_bmap_update_put_group( struct xfs_bmap_intent *bi) { - xfs_perag_put(bi->bi_pag); + xfs_perag_intent_put(bi->bi_pag); } /* Process a deferred rmap update. */ diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c new file mode 100644 index 000000000000..b431abdf0af1 --- /dev/null +++ b/fs/xfs/xfs_drain.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022-2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_ag.h" +#include "xfs_trace.h" + +void +xfs_defer_drain_init( + struct xfs_defer_drain *dr) +{ + atomic_set(&dr->dr_count, 0); + init_waitqueue_head(&dr->dr_waiters); +} + +void +xfs_defer_drain_free(struct xfs_defer_drain *dr) +{ + ASSERT(atomic_read(&dr->dr_count) == 0); +} + +/* Increase the pending intent count. */ +static inline void xfs_defer_drain_grab(struct xfs_defer_drain *dr) +{ + atomic_inc(&dr->dr_count); +} + +static inline bool has_waiters(struct wait_queue_head *wq_head) +{ + /* + * This memory barrier is paired with the one in set_current_state on + * the waiting side. + */ + smp_mb__after_atomic(); + return waitqueue_active(wq_head); +} + +/* Decrease the pending intent count, and wake any waiters, if appropriate. */ +static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr) +{ + if (atomic_dec_and_test(&dr->dr_count) && + has_waiters(&dr->dr_waiters)) + wake_up(&dr->dr_waiters); +} + +/* Are there intents pending? */ +static inline bool xfs_defer_drain_busy(struct xfs_defer_drain *dr) +{ + return atomic_read(&dr->dr_count) > 0; +} + +/* + * Wait for the pending intent count for a drain to hit zero. + * + * Callers must not hold any locks that would prevent intents from being + * finished. + */ +static inline int xfs_defer_drain_wait(struct xfs_defer_drain *dr) +{ + return wait_event_killable(dr->dr_waiters, !xfs_defer_drain_busy(dr)); +} + +/* + * Get a passive reference to an AG and declare an intent to update its + * metadata. + */ +struct xfs_perag * +xfs_perag_intent_get( + struct xfs_mount *mp, + xfs_agnumber_t agno) +{ + struct xfs_perag *pag; + + pag = xfs_perag_get(mp, agno); + if (!pag) + return NULL; + + xfs_perag_intent_hold(pag); + return pag; +} + +/* + * Release our intent to update this AG's metadata, and then release our + * passive ref to the AG. + */ +void +xfs_perag_intent_put( + struct xfs_perag *pag) +{ + xfs_perag_intent_rele(pag); + xfs_perag_put(pag); +} + +/* + * Declare an intent to update AG metadata. Other threads that need exclusive + * access can decide to back off if they see declared intentions. + */ +void +xfs_perag_intent_hold( + struct xfs_perag *pag) +{ + trace_xfs_perag_intent_hold(pag, __return_address); + xfs_defer_drain_grab(&pag->pag_intents_drain); +} + +/* Release our intent to update this AG's metadata. */ +void +xfs_perag_intent_rele( + struct xfs_perag *pag) +{ + trace_xfs_perag_intent_rele(pag, __return_address); + xfs_defer_drain_rele(&pag->pag_intents_drain); +} + +/* + * Wait for the intent update count for this AG to hit zero. + * Callers must not hold any AG header buffers. + */ +int +xfs_perag_intent_drain( + struct xfs_perag *pag) +{ + trace_xfs_perag_wait_intents(pag, __return_address); + return xfs_defer_drain_wait(&pag->pag_intents_drain); +} + +/* Has anyone declared an intent to update this AG? */ +bool +xfs_perag_intent_busy( + struct xfs_perag *pag) +{ + return xfs_defer_drain_busy(&pag->pag_intents_drain); +} diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h new file mode 100644 index 000000000000..9b16df3cc7dc --- /dev/null +++ b/fs/xfs/xfs_drain.h @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022-2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef XFS_DRAIN_H_ +#define XFS_DRAIN_H_ + +struct xfs_perag; + +#ifdef CONFIG_XFS_DRAIN_INTENTS +/* + * Passive drain mechanism. This data structure tracks a count of some items + * and contains a waitqueue for callers who would like to wake up when the + * count hits zero. + */ +struct xfs_defer_drain { + /* Number of items pending in some part of the filesystem. */ + atomic_t dr_count; + + /* Queue to wait for dri_count to go to zero */ + struct wait_queue_head dr_waiters; +}; + +void xfs_defer_drain_init(struct xfs_defer_drain *dr); +void xfs_defer_drain_free(struct xfs_defer_drain *dr); + +/* + * Deferred Work Intent Drains + * =========================== + * + * When a writer thread executes a chain of log intent items, the AG header + * buffer locks will cycle during a transaction roll to get from one intent + * item to the next in a chain. Although scrub takes all AG header buffer + * locks, this isn't sufficient to guard against scrub checking an AG while + * that writer thread is in the middle of finishing a chain because there's no + * higher level locking primitive guarding allocation groups. + * + * When there's a collision, cross-referencing between data structures (e.g. + * rmapbt and refcountbt) yields false corruption events; if repair is running, + * this results in incorrect repairs, which is catastrophic. + * + * The solution is to the perag structure the count of active intents and make + * scrub wait until it has both AG header buffer locks and the intent counter + * reaches zero. It is therefore critical that deferred work threads hold the + * AGI or AGF buffers when decrementing the intent counter. + * + * Given a list of deferred work items, the deferred work manager will complete + * a work item and all the sub-items that the parent item creates before moving + * on to the next work item in the list. This is also true for all levels of + * sub-items. Writer threads are permitted to queue multiple work items + * targetting the same AG, so a deferred work item (such as a BUI) that creates + * sub-items (such as RUIs) must bump the intent counter and maintain it until + * the sub-items can themselves bump the intent counter. + * + * Therefore, the intent count tracks entire lifetimes of deferred work items. + * All functions that create work items must increment the intent counter as + * soon as the item is added to the transaction and cannot drop the counter + * until the item is finished or cancelled. + */ +struct xfs_perag *xfs_perag_intent_get(struct xfs_mount *mp, + xfs_agnumber_t agno); +void xfs_perag_intent_put(struct xfs_perag *pag); + +void xfs_perag_intent_hold(struct xfs_perag *pag); +void xfs_perag_intent_rele(struct xfs_perag *pag); + +int xfs_perag_intent_drain(struct xfs_perag *pag); +bool xfs_perag_intent_busy(struct xfs_perag *pag); +#else +struct xfs_defer_drain { /* empty */ }; + +#define xfs_defer_drain_free(dr) ((void)0) +#define xfs_defer_drain_init(dr) ((void)0) + +#define xfs_perag_intent_get(mp, agno) xfs_perag_get((mp), (agno)) +#define xfs_perag_intent_put(pag) xfs_perag_put(pag) + +static inline void xfs_perag_intent_hold(struct xfs_perag *pag) { } +static inline void xfs_perag_intent_rele(struct xfs_perag *pag) { } + +#endif /* CONFIG_XFS_DRAIN_INTENTS */ + +#endif /* XFS_DRAIN_H_ */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 38b66fcfddc8..f9e36b810663 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -469,7 +469,7 @@ xfs_extent_free_get_group( xfs_agnumber_t agno; agno = XFS_FSB_TO_AGNO(mp, xefi->xefi_startblock); - xefi->xefi_pag = xfs_perag_get(mp, agno); + xefi->xefi_pag = xfs_perag_intent_get(mp, agno); } /* Release a passive AG ref after some freeing work. */ @@ -477,7 +477,7 @@ static inline void xfs_extent_free_put_group( struct xfs_extent_free_item *xefi) { - xfs_perag_put(xefi->xefi_pag); + xfs_perag_intent_put(xefi->xefi_pag); } /* Process a free extent. */ diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index e88f18f85e4b..74dcb05069e8 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -80,6 +80,7 @@ typedef __u32 xfs_nlink_t; #include "xfs_cksum.h" #include "xfs_buf.h" #include "xfs_message.h" +#include "xfs_drain.h" #ifdef __BIG_ENDIAN #define XFS_NATIVE_HOST 1 diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 7edee9590ed6..edd8587658d5 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -374,7 +374,7 @@ xfs_refcount_update_get_group( xfs_agnumber_t agno; agno = XFS_FSB_TO_AGNO(mp, ri->ri_startblock); - ri->ri_pag = xfs_perag_get(mp, agno); + ri->ri_pag = xfs_perag_intent_get(mp, agno); } /* Release a passive AG ref after finishing refcounting work. */ @@ -382,7 +382,7 @@ static inline void xfs_refcount_update_put_group( struct xfs_refcount_intent *ri) { - xfs_perag_put(ri->ri_pag); + xfs_perag_intent_put(ri->ri_pag); } /* Process a deferred refcount update. */ diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 739ddbd04a17..520c7ebdfed8 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -399,7 +399,7 @@ xfs_rmap_update_get_group( xfs_agnumber_t agno; agno = XFS_FSB_TO_AGNO(mp, ri->ri_bmap.br_startblock); - ri->ri_pag = xfs_perag_get(mp, agno); + ri->ri_pag = xfs_perag_intent_get(mp, agno); } /* Release a passive AG ref after finishing rmapping work. */ @@ -407,7 +407,7 @@ static inline void xfs_rmap_update_put_group( struct xfs_rmap_intent *ri) { - xfs_perag_put(ri->ri_pag); + xfs_perag_intent_put(ri->ri_pag); } /* Process a deferred rmap update. */ diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index db09bb771765..cd4ca5b1fcb0 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -2687,6 +2687,44 @@ DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_bmap_free_deferred); DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_defer); DEFINE_BMAP_FREE_DEFERRED_EVENT(xfs_agfl_free_deferred); +DECLARE_EVENT_CLASS(xfs_defer_pending_item_class, + TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp, + void *item), + TP_ARGS(mp, dfp, item), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(int, type) + __field(void *, intent) + __field(void *, item) + __field(char, committed) + __field(int, nr) + ), + TP_fast_assign( + __entry->dev = mp ? mp->m_super->s_dev : 0; + __entry->type = dfp->dfp_type; + __entry->intent = dfp->dfp_intent; + __entry->item = item; + __entry->committed = dfp->dfp_done != NULL; + __entry->nr = dfp->dfp_count; + ), + TP_printk("dev %d:%d optype %d intent %p item %p committed %d nr %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->type, + __entry->intent, + __entry->item, + __entry->committed, + __entry->nr) +) +#define DEFINE_DEFER_PENDING_ITEM_EVENT(name) \ +DEFINE_EVENT(xfs_defer_pending_item_class, name, \ + TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp, \ + void *item), \ + TP_ARGS(mp, dfp, item)) + +DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_add_item); +DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_cancel_item); +DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item); + /* rmap tracepoints */ DECLARE_EVENT_CLASS(xfs_rmap_class, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, @@ -4326,6 +4364,39 @@ TRACE_EVENT(xfs_force_shutdown, __entry->line_num) ); +#ifdef CONFIG_XFS_DRAIN_INTENTS +DECLARE_EVENT_CLASS(xfs_perag_intents_class, + TP_PROTO(struct xfs_perag *pag, void *caller_ip), + TP_ARGS(pag, caller_ip), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(long, nr_intents) + __field(void *, caller_ip) + ), + TP_fast_assign( + __entry->dev = pag->pag_mount->m_super->s_dev; + __entry->agno = pag->pag_agno; + __entry->nr_intents = atomic_read(&pag->pag_intents_drain.dr_count); + __entry->caller_ip = caller_ip; + ), + TP_printk("dev %d:%d agno 0x%x intents %ld caller %pS", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->agno, + __entry->nr_intents, + __entry->caller_ip) +); + +#define DEFINE_PERAG_INTENTS_EVENT(name) \ +DEFINE_EVENT(xfs_perag_intents_class, name, \ + TP_PROTO(struct xfs_perag *pag, void *caller_ip), \ + TP_ARGS(pag, caller_ip)) +DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_hold); +DEFINE_PERAG_INTENTS_EVENT(xfs_perag_intent_rele); +DEFINE_PERAG_INTENTS_EVENT(xfs_perag_wait_intents); + +#endif /* CONFIG_XFS_DRAIN_INTENTS */ + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH -- GitLab From 3f64c718d06eae168208faaadb522007e0048e7b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:59 -0700 Subject: [PATCH 2558/5631] xfs: clean up scrub context if scrub setup returns -EDEADLOCK It has been a longstanding convention that online scrub and repair functions can return -EDEADLOCK to signal that they weren't able to obtain some necessary resource. When this happens, the scrub framework is supposed to release all resources attached to the scrub context, set the TRY_HARDER flag in the scrub context flags, and try again. In this context, individual scrub functions are supposed to take all the resources they (incorrectly) speculated were not necessary. We're about to make it so that the functions that lock and wait for a filesystem AG can also return EDEADLOCK to signal that we need to try again with the drain waiters enabled. Therefore, refactor xfs_scrub_metadata to support this behavior for ->setup() functions. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/scrub.c | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index e8e2bee001e5..9364fe7d07b4 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -491,23 +491,16 @@ xfs_scrub_metadata( /* Set up for the operation. */ error = sc->ops->setup(sc); + if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER)) + goto try_harder; if (error) goto out_teardown; /* Scrub for errors. */ error = sc->ops->scrub(sc); - if (!(sc->flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) { - /* - * Scrubbers return -EDEADLOCK to mean 'try harder'. - * Tear down everything we hold, then set up again with - * preparation for worst-case scenarios. - */ - error = xchk_teardown(sc, 0); - if (error) - goto out_sc; - sc->flags |= XCHK_TRY_HARDER; - goto retry_op; - } else if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)) + if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER)) + goto try_harder; + if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)) goto out_teardown; xchk_update_health(sc); @@ -565,4 +558,15 @@ xfs_scrub_metadata( error = 0; } return error; +try_harder: + /* + * Scrubbers return -EDEADLOCK to mean 'try harder'. Tear down + * everything we hold, then set up again with preparation for + * worst-case scenarios. + */ + error = xchk_teardown(sc, 0); + if (error) + goto out_sc; + sc->flags |= XCHK_TRY_HARDER; + goto retry_op; } -- GitLab From 466c525d6d35e69115852c004f405f0711b8f91a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:59 -0700 Subject: [PATCH 2559/5631] xfs: minimize overhead of drain wakeups by using jump labels To reduce the runtime overhead even further when online fsck isn't running, use a static branch key to decide if we call wake_up on the drain. For compilers that support jump labels, the call to wake_up is replaced by a nop sled when nobody is waiting for intents to drain. From my initial microbenchmarking, every transition of the static key between the on and off states takes about 22000ns to complete; this is paid entirely by the xfs_scrub process. When the static key is off (which it should be when fsck isn't running), the nop sled adds an overhead of approximately 0.36ns to runtime code. The post-atomic lockless waiter check adds about 0.03ns, which is basically free. For the few compilers that don't support jump labels, runtime code pays the cost of calling wake_up on an empty waitqueue, which was observed to be about 30ns. However, most architectures that have sufficient memory and CPU capacity to run XFS also support jump labels, so this is not much of a worry. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/Kconfig | 1 + fs/xfs/scrub/agheader.c | 9 +++++++++ fs/xfs/scrub/alloc.c | 3 +++ fs/xfs/scrub/bmap.c | 3 +++ fs/xfs/scrub/common.c | 24 ++++++++++++++++++++++++ fs/xfs/scrub/common.h | 15 +++++++++++++++ fs/xfs/scrub/fscounters.c | 7 +++++++ fs/xfs/scrub/ialloc.c | 2 ++ fs/xfs/scrub/inode.c | 3 +++ fs/xfs/scrub/quota.c | 3 +++ fs/xfs/scrub/refcount.c | 2 ++ fs/xfs/scrub/rmap.c | 3 +++ fs/xfs/scrub/scrub.c | 25 +++++++++++++++++++++---- fs/xfs/scrub/scrub.h | 11 ++++++++++- fs/xfs/scrub/trace.h | 33 +++++++++++++++++++++++++++++++++ fs/xfs/xfs_drain.c | 26 ++++++++++++++++++++++++++ fs/xfs/xfs_drain.h | 3 +++ 17 files changed, 168 insertions(+), 5 deletions(-) diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index ab24e683b440..05bc865142b8 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -95,6 +95,7 @@ config XFS_RT config XFS_DRAIN_INTENTS bool + select JUMP_LABEL if HAVE_ARCH_JUMP_LABEL config XFS_ONLINE_SCRUB bool "XFS online metadata check support" diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index c91819da1f5f..87cb13a6e84a 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -18,6 +18,15 @@ #include "scrub/scrub.h" #include "scrub/common.h" +int +xchk_setup_agheader( + struct xfs_scrub *sc) +{ + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + return xchk_setup_fs(sc); +} + /* Superblock */ /* Cross-reference with the other btrees. */ diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 39e79b9536bc..de313df2b15b 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -24,6 +24,9 @@ int xchk_setup_ag_allocbt( struct xfs_scrub *sc) { + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + return xchk_setup_ag_btree(sc, false); } diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index f6d8cb938a02..a5078d63808f 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -31,6 +31,9 @@ xchk_setup_inode_bmap( { int error; + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + error = xchk_get_inode(sc); if (error) goto out; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 2a496d1699a3..87649facbbde 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -487,6 +487,8 @@ xchk_perag_drain_and_lock( sa->agi_bp = NULL; } + if (!(sc->flags & XCHK_FSGATES_DRAIN)) + return -EDEADLOCK; error = xfs_perag_intent_drain(sa->pag); if (error == -ERESTARTSYS) error = -EINTR; @@ -1005,3 +1007,25 @@ xchk_start_reaping( } sc->flags &= ~XCHK_REAPING_DISABLED; } + +/* + * Enable filesystem hooks (i.e. runtime code patching) before starting a scrub + * operation. Callers must not hold any locks that intersect with the CPU + * hotplug lock (e.g. writeback locks) because code patching must halt the CPUs + * to change kernel code. + */ +void +xchk_fsgates_enable( + struct xfs_scrub *sc, + unsigned int scrub_fsgates) +{ + ASSERT(!(scrub_fsgates & ~XCHK_FSGATES_ALL)); + ASSERT(!(sc->flags & scrub_fsgates)); + + trace_xchk_fsgates_enable(sc, scrub_fsgates); + + if (scrub_fsgates & XCHK_FSGATES_DRAIN) + xfs_drain_wait_enable(); + + sc->flags |= scrub_fsgates; +} diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 273a4331da05..4714e8a43094 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -72,6 +72,7 @@ bool xchk_should_check_xref(struct xfs_scrub *sc, int *error, struct xfs_btree_cur **curpp); /* Setup functions */ +int xchk_setup_agheader(struct xfs_scrub *sc); int xchk_setup_fs(struct xfs_scrub *sc); int xchk_setup_ag_allocbt(struct xfs_scrub *sc); int xchk_setup_ag_iallocbt(struct xfs_scrub *sc); @@ -151,4 +152,18 @@ int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode); void xchk_stop_reaping(struct xfs_scrub *sc); void xchk_start_reaping(struct xfs_scrub *sc); +/* + * Setting up a hook to wait for intents to drain is costly -- we have to take + * the CPU hotplug lock and force an i-cache flush on all CPUs once to set it + * up, and again to tear it down. These costs add up quickly, so we only want + * to enable the drain waiter if the drain actually detected a conflict with + * running intent chains. + */ +static inline bool xchk_need_intent_drain(struct xfs_scrub *sc) +{ + return sc->flags & XCHK_TRY_HARDER; +} + +void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks); + #endif /* __XFS_SCRUB_COMMON_H__ */ diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index a38006c71bff..faa315be7978 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -130,6 +130,13 @@ xchk_setup_fscounters( struct xchk_fscounters *fsc; int error; + /* + * If the AGF doesn't track btreeblks, we have to lock the AGF to count + * btree block usage by walking the actual btrees. + */ + if (!xfs_has_lazysbcount(sc->mp)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + sc->buf = kzalloc(sizeof(struct xchk_fscounters), XCHK_GFP_FLAGS); if (!sc->buf) return -ENOMEM; diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index b14270bd1c62..9563769a8881 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -32,6 +32,8 @@ int xchk_setup_ag_iallocbt( struct xfs_scrub *sc) { + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); return xchk_setup_ag_btree(sc, sc->flags & XCHK_TRY_HARDER); } diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index dc66a1465f1b..bbf9432c02c2 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -32,6 +32,9 @@ xchk_setup_inode( { int error; + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + /* * Try to get the inode. If the verifiers fail, we try again * in raw mode. diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index b019c70c065a..e6caa358cbda 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -53,6 +53,9 @@ xchk_setup_quota( if (!xfs_this_quota_on(sc->mp, dqtype)) return -ENOENT; + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + error = xchk_setup_fs(sc); if (error) return error; diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 756066f3dea2..6f649cc01310 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -27,6 +27,8 @@ int xchk_setup_ag_refcountbt( struct xfs_scrub *sc) { + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); return xchk_setup_ag_btree(sc, false); } diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 4dc79e1a675d..c6e47ef4c79b 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -24,6 +24,9 @@ int xchk_setup_ag_rmapbt( struct xfs_scrub *sc) { + if (xchk_need_intent_drain(sc)) + xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + return xchk_setup_ag_btree(sc, false); } diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 9364fe7d07b4..bd5d4357cd64 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -145,6 +145,21 @@ xchk_probe( /* Scrub setup and teardown */ +static inline void +xchk_fsgates_disable( + struct xfs_scrub *sc) +{ + if (!(sc->flags & XCHK_FSGATES_ALL)) + return; + + trace_xchk_fsgates_disable(sc, sc->flags & XCHK_FSGATES_ALL); + + if (sc->flags & XCHK_FSGATES_DRAIN) + xfs_drain_wait_disable(); + + sc->flags &= ~XCHK_FSGATES_ALL; +} + /* Free all the resources and finish the transactions. */ STATIC int xchk_teardown( @@ -177,6 +192,8 @@ xchk_teardown( kvfree(sc->buf); sc->buf = NULL; } + + xchk_fsgates_disable(sc); return error; } @@ -191,25 +208,25 @@ static const struct xchk_meta_ops meta_scrub_ops[] = { }, [XFS_SCRUB_TYPE_SB] = { /* superblock */ .type = ST_PERAG, - .setup = xchk_setup_fs, + .setup = xchk_setup_agheader, .scrub = xchk_superblock, .repair = xrep_superblock, }, [XFS_SCRUB_TYPE_AGF] = { /* agf */ .type = ST_PERAG, - .setup = xchk_setup_fs, + .setup = xchk_setup_agheader, .scrub = xchk_agf, .repair = xrep_agf, }, [XFS_SCRUB_TYPE_AGFL]= { /* agfl */ .type = ST_PERAG, - .setup = xchk_setup_fs, + .setup = xchk_setup_agheader, .scrub = xchk_agfl, .repair = xrep_agfl, }, [XFS_SCRUB_TYPE_AGI] = { /* agi */ .type = ST_PERAG, - .setup = xchk_setup_fs, + .setup = xchk_setup_agheader, .scrub = xchk_agi, .repair = xrep_agi, }, diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 72a5a8a64a87..4fdb6017f820 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -96,9 +96,18 @@ struct xfs_scrub { /* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */ #define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */ -#define XCHK_REAPING_DISABLED (1 << 2) /* background block reaping paused */ +#define XCHK_REAPING_DISABLED (1 << 1) /* background block reaping paused */ +#define XCHK_FSGATES_DRAIN (1 << 2) /* defer ops draining enabled */ #define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */ +/* + * The XCHK_FSGATES* flags reflect functionality in the main filesystem that + * are only enabled for this particular online fsck. When not in use, the + * features are gated off via dynamic code patching, which is why the state + * must be enabled during scrub setup and can only be torn down afterwards. + */ +#define XCHK_FSGATES_ALL (XCHK_FSGATES_DRAIN) + /* Metadata scrubbers */ int xchk_tester(struct xfs_scrub *sc); int xchk_superblock(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index ad25ae88fce1..304c55192c90 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -96,6 +96,12 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS); { XFS_SCRUB_OFLAG_WARNING, "warning" }, \ { XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED, "norepair" } +#define XFS_SCRUB_STATE_STRINGS \ + { XCHK_TRY_HARDER, "try_harder" }, \ + { XCHK_REAPING_DISABLED, "reaping_disabled" }, \ + { XCHK_FSGATES_DRAIN, "fsgates_drain" }, \ + { XREP_ALREADY_FIXED, "already_fixed" } + DECLARE_EVENT_CLASS(xchk_class, TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm, int error), @@ -142,6 +148,33 @@ DEFINE_SCRUB_EVENT(xchk_deadlock_retry); DEFINE_SCRUB_EVENT(xrep_attempt); DEFINE_SCRUB_EVENT(xrep_done); +DECLARE_EVENT_CLASS(xchk_fsgate_class, + TP_PROTO(struct xfs_scrub *sc, unsigned int fsgate_flags), + TP_ARGS(sc, fsgate_flags), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, type) + __field(unsigned int, fsgate_flags) + ), + TP_fast_assign( + __entry->dev = sc->mp->m_super->s_dev; + __entry->type = sc->sm->sm_type; + __entry->fsgate_flags = fsgate_flags; + ), + TP_printk("dev %d:%d type %s fsgates '%s'", + MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XFS_SCRUB_TYPE_STRINGS), + __print_flags(__entry->fsgate_flags, "|", XFS_SCRUB_STATE_STRINGS)) +) + +#define DEFINE_SCRUB_FSHOOK_EVENT(name) \ +DEFINE_EVENT(xchk_fsgate_class, name, \ + TP_PROTO(struct xfs_scrub *sc, unsigned int fsgates_flags), \ + TP_ARGS(sc, fsgates_flags)) + +DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_enable); +DEFINE_SCRUB_FSHOOK_EVENT(xchk_fsgates_disable); + TRACE_EVENT(xchk_op_error, TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno, xfs_agblock_t bno, int error, void *ret_ip), diff --git a/fs/xfs/xfs_drain.c b/fs/xfs/xfs_drain.c index b431abdf0af1..005a66be44a2 100644 --- a/fs/xfs/xfs_drain.c +++ b/fs/xfs/xfs_drain.c @@ -12,6 +12,31 @@ #include "xfs_ag.h" #include "xfs_trace.h" +/* + * Use a static key here to reduce the overhead of xfs_drain_rele. If the + * compiler supports jump labels, the static branch will be replaced by a nop + * sled when there are no xfs_drain_wait callers. Online fsck is currently + * the only caller, so this is a reasonable tradeoff. + * + * Note: Patching the kernel code requires taking the cpu hotplug lock. Other + * parts of the kernel allocate memory with that lock held, which means that + * XFS callers cannot hold any locks that might be used by memory reclaim or + * writeback when calling the static_branch_{inc,dec} functions. + */ +static DEFINE_STATIC_KEY_FALSE(xfs_drain_waiter_gate); + +void +xfs_drain_wait_disable(void) +{ + static_branch_dec(&xfs_drain_waiter_gate); +} + +void +xfs_drain_wait_enable(void) +{ + static_branch_inc(&xfs_drain_waiter_gate); +} + void xfs_defer_drain_init( struct xfs_defer_drain *dr) @@ -46,6 +71,7 @@ static inline bool has_waiters(struct wait_queue_head *wq_head) static inline void xfs_defer_drain_rele(struct xfs_defer_drain *dr) { if (atomic_dec_and_test(&dr->dr_count) && + static_branch_unlikely(&xfs_drain_waiter_gate) && has_waiters(&dr->dr_waiters)) wake_up(&dr->dr_waiters); } diff --git a/fs/xfs/xfs_drain.h b/fs/xfs/xfs_drain.h index 9b16df3cc7dc..50a5772a8296 100644 --- a/fs/xfs/xfs_drain.h +++ b/fs/xfs/xfs_drain.h @@ -25,6 +25,9 @@ struct xfs_defer_drain { void xfs_defer_drain_init(struct xfs_defer_drain *dr); void xfs_defer_drain_free(struct xfs_defer_drain *dr); +void xfs_drain_wait_disable(void); +void xfs_drain_wait_enable(void); + /* * Deferred Work Intent Drains * =========================== -- GitLab From 88accf17226733088923635b580779a3c86b6f23 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:00 -0700 Subject: [PATCH 2560/5631] xfs: scrub should use ECHRNG to signal that the drain is needed In the previous patch, we added jump labels to the intent drain code so that regular filesystem operations need not pay the price of checking for someone (scrub) waiting on intents to drain from some part of the filesystem when that someone isn't running. However, I observed that xfs/285 now spends a lot more time pushing the AIL from the inode btree scrubber than it used to. This is because the inobt scrubber will try push the AIL to try to get logged inode cores written to the filesystem when it sees a weird discrepancy between the ondisk inode and the inobt records. This AIL push is triggered when the setup function sees TRY_HARDER is set; and the requisite EDEADLOCK return is initiated when the discrepancy is seen. The solution to this performance slow down is to use a different result code (ECHRNG) for scrub code to signal that it needs to wait for deferred intent work items to drain out of some part of the filesystem. When this happens, set a new scrub state flag (XCHK_NEED_DRAIN) so that setup functions will activate the jump label. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/btree.c | 1 + fs/xfs/scrub/common.c | 4 +++- fs/xfs/scrub/common.h | 2 +- fs/xfs/scrub/dabtree.c | 1 + fs/xfs/scrub/repair.c | 3 +++ fs/xfs/scrub/scrub.c | 10 ++++++++++ fs/xfs/scrub/scrub.h | 1 + fs/xfs/scrub/trace.h | 1 + 8 files changed, 21 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index e54c1cfe64bf..626282dbe2e3 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -36,6 +36,7 @@ __xchk_btree_process_error( switch (*error) { case -EDEADLOCK: + case -ECHRNG: /* Used to restart an op with deadlock avoidance. */ trace_xchk_deadlock_retry(sc->ip, sc->sm, *error); break; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 87649facbbde..dcfe66044d4a 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -75,6 +75,7 @@ __xchk_process_error( case 0: return true; case -EDEADLOCK: + case -ECHRNG: /* Used to restart an op with deadlock avoidance. */ trace_xchk_deadlock_retry( sc->ip ? sc->ip : XFS_I(file_inode(sc->file)), @@ -130,6 +131,7 @@ __xchk_fblock_process_error( case 0: return true; case -EDEADLOCK: + case -ECHRNG: /* Used to restart an op with deadlock avoidance. */ trace_xchk_deadlock_retry(sc->ip, sc->sm, *error); break; @@ -488,7 +490,7 @@ xchk_perag_drain_and_lock( } if (!(sc->flags & XCHK_FSGATES_DRAIN)) - return -EDEADLOCK; + return -ECHRNG; error = xfs_perag_intent_drain(sa->pag); if (error == -ERESTARTSYS) error = -EINTR; diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 4714e8a43094..83b1a392930a 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -161,7 +161,7 @@ void xchk_start_reaping(struct xfs_scrub *sc); */ static inline bool xchk_need_intent_drain(struct xfs_scrub *sc) { - return sc->flags & XCHK_TRY_HARDER; + return sc->flags & XCHK_NEED_DRAIN; } void xchk_fsgates_enable(struct xfs_scrub *sc, unsigned int scrub_fshooks); diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index c392c0765e5c..82b150d3b8b7 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -39,6 +39,7 @@ xchk_da_process_error( switch (*error) { case -EDEADLOCK: + case -ECHRNG: /* Used to restart an op with deadlock avoidance. */ trace_xchk_deadlock_retry(sc->ip, sc->sm, *error); break; diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index b800341aae69..ab0758308f57 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -60,6 +60,9 @@ xrep_attempt( sc->sm->sm_flags &= ~XFS_SCRUB_FLAGS_OUT; sc->flags |= XREP_ALREADY_FIXED; return -EAGAIN; + case -ECHRNG: + sc->flags |= XCHK_NEED_DRAIN; + return -EAGAIN; case -EDEADLOCK: /* Tell the caller to try again having grabbed all the locks. */ if (!(sc->flags & XCHK_TRY_HARDER)) { diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index bd5d4357cd64..787a9096ddef 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -510,6 +510,8 @@ xfs_scrub_metadata( error = sc->ops->setup(sc); if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER)) goto try_harder; + if (error == -ECHRNG && !(sc->flags & XCHK_NEED_DRAIN)) + goto need_drain; if (error) goto out_teardown; @@ -517,6 +519,8 @@ xfs_scrub_metadata( error = sc->ops->scrub(sc); if (error == -EDEADLOCK && !(sc->flags & XCHK_TRY_HARDER)) goto try_harder; + if (error == -ECHRNG && !(sc->flags & XCHK_NEED_DRAIN)) + goto need_drain; if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE)) goto out_teardown; @@ -575,6 +579,12 @@ xfs_scrub_metadata( error = 0; } return error; +need_drain: + error = xchk_teardown(sc, 0); + if (error) + goto out_sc; + sc->flags |= XCHK_NEED_DRAIN; + goto retry_op; try_harder: /* * Scrubbers return -EDEADLOCK to mean 'try harder'. Tear down diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index 4fdb6017f820..d85c3b883b4c 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -98,6 +98,7 @@ struct xfs_scrub { #define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */ #define XCHK_REAPING_DISABLED (1 << 1) /* background block reaping paused */ #define XCHK_FSGATES_DRAIN (1 << 2) /* defer ops draining enabled */ +#define XCHK_NEED_DRAIN (1 << 3) /* scrub needs to drain defer ops */ #define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */ /* diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 304c55192c90..68efd6fda61c 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -100,6 +100,7 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS); { XCHK_TRY_HARDER, "try_harder" }, \ { XCHK_REAPING_DISABLED, "reaping_disabled" }, \ { XCHK_FSGATES_DRAIN, "fsgates_drain" }, \ + { XCHK_NEED_DRAIN, "need_drain" }, \ { XREP_ALREADY_FIXED, "already_fixed" } DECLARE_EVENT_CLASS(xchk_class, -- GitLab From 35e3b9a11740b53387e7af151768c13700f80696 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:01 -0700 Subject: [PATCH 2561/5631] xfs: standardize ondisk to incore conversion for free space btrees Create a xfs_alloc_btrec_to_irec function to convert an ondisk record to an incore record, and a xfs_alloc_check_irec function to detect corruption. Replace all the open-coded logic with calls to the new helpers and bubble up corruption reports. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 56 ++++++++++++++++++++++++++++++--------- fs/xfs/libxfs/xfs_alloc.h | 6 +++++ fs/xfs/scrub/alloc.c | 24 ++++++++--------- 3 files changed, 61 insertions(+), 25 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index d72483013b7d..89c935cbcc4d 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -233,6 +233,34 @@ xfs_alloc_update( return xfs_btree_update(cur, &rec); } +/* Convert the ondisk btree record to its incore representation. */ +void +xfs_alloc_btrec_to_irec( + const union xfs_btree_rec *rec, + struct xfs_alloc_rec_incore *irec) +{ + irec->ar_startblock = be32_to_cpu(rec->alloc.ar_startblock); + irec->ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount); +} + +/* Simple checks for free space records. */ +xfs_failaddr_t +xfs_alloc_check_irec( + struct xfs_btree_cur *cur, + const struct xfs_alloc_rec_incore *irec) +{ + struct xfs_perag *pag = cur->bc_ag.pag; + + if (irec->ar_blockcount == 0) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_agbext(pag, irec->ar_startblock, irec->ar_blockcount)) + return __this_address; + + return NULL; +} + /* * Get the data from the pointed-to record. */ @@ -243,34 +271,34 @@ xfs_alloc_get_rec( xfs_extlen_t *len, /* output: length of extent */ int *stat) /* output: success/failure */ { + struct xfs_alloc_rec_incore irec; struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - *bno = be32_to_cpu(rec->alloc.ar_startblock); - *len = be32_to_cpu(rec->alloc.ar_blockcount); - - if (*len == 0) - goto out_bad_rec; - - /* check for valid extent range, including overflow */ - if (!xfs_verify_agbext(pag, *bno, *len)) + xfs_alloc_btrec_to_irec(rec, &irec); + fa = xfs_alloc_check_irec(cur, &irec); + if (fa) goto out_bad_rec; + *bno = irec.ar_startblock; + *len = irec.ar_blockcount; return 0; out_bad_rec: xfs_warn(mp, - "%s Freespace BTree record corruption in AG %d detected!", + "%s Freespace BTree record corruption in AG %d detected at %pS!", cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", - pag->pag_agno); + pag->pag_agno, fa); xfs_warn(mp, - "start block 0x%x block count 0x%x", *bno, *len); + "start block 0x%x block count 0x%x", irec.ar_startblock, + irec.ar_blockcount); return -EFSCORRUPTED; } @@ -3665,8 +3693,10 @@ xfs_alloc_query_range_helper( struct xfs_alloc_query_range_info *query = priv; struct xfs_alloc_rec_incore irec; - irec.ar_startblock = be32_to_cpu(rec->alloc.ar_startblock); - irec.ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount); + xfs_alloc_btrec_to_irec(rec, &irec); + if (xfs_alloc_check_irec(cur, &irec) != NULL) + return -EFSCORRUPTED; + return query->fn(cur, &irec, query->priv); } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 5569cb2ede0d..56bd05900b35 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -181,6 +181,12 @@ xfs_alloc_get_rec( xfs_extlen_t *len, /* output: length of extent */ int *stat); /* output: success/failure */ +union xfs_btree_rec; +void xfs_alloc_btrec_to_irec(const union xfs_btree_rec *rec, + struct xfs_alloc_rec_incore *irec); +xfs_failaddr_t xfs_alloc_check_irec(struct xfs_btree_cur *cur, + const struct xfs_alloc_rec_incore *irec); + int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, struct xfs_buf **agfbpp); int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags, diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index de313df2b15b..53de04c6027c 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -78,9 +78,11 @@ xchk_allocbt_xref_other( STATIC void xchk_allocbt_xref( struct xfs_scrub *sc, - xfs_agblock_t agbno, - xfs_extlen_t len) + const struct xfs_alloc_rec_incore *irec) { + xfs_agblock_t agbno = irec->ar_startblock; + xfs_extlen_t len = irec->ar_blockcount; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; @@ -93,20 +95,18 @@ xchk_allocbt_xref( /* Scrub a bnobt/cntbt record. */ STATIC int xchk_allocbt_rec( - struct xchk_btree *bs, - const union xfs_btree_rec *rec) + struct xchk_btree *bs, + const union xfs_btree_rec *rec) { - struct xfs_perag *pag = bs->cur->bc_ag.pag; - xfs_agblock_t bno; - xfs_extlen_t len; + struct xfs_alloc_rec_incore irec; - bno = be32_to_cpu(rec->alloc.ar_startblock); - len = be32_to_cpu(rec->alloc.ar_blockcount); - - if (!xfs_verify_agbext(pag, bno, len)) + xfs_alloc_btrec_to_irec(rec, &irec); + if (xfs_alloc_check_irec(bs->cur, &irec) != NULL) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } - xchk_allocbt_xref(bs->sc, bno, len); + xchk_allocbt_xref(bs->sc, &irec); return 0; } -- GitLab From 366a0b8d49c3a7edcb5331f254af195716ba4bdf Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:01 -0700 Subject: [PATCH 2562/5631] xfs: standardize ondisk to incore conversion for inode btrees Create a xfs_inobt_check_irec function to detect corruption in btree records. Fix all xfs_inobt_btrec_to_irec callsites to call the new helper and bubble up corruption reports. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ialloc.c | 53 +++++++++++++++++++++----------- fs/xfs/libxfs/xfs_ialloc.h | 2 ++ fs/xfs/libxfs/xfs_ialloc_btree.c | 2 +- fs/xfs/libxfs/xfs_ialloc_btree.h | 2 +- fs/xfs/scrub/ialloc.c | 24 +++------------ 5 files changed, 43 insertions(+), 40 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 7ee292aecbeb..32af8326ad76 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -95,6 +95,33 @@ xfs_inobt_btrec_to_irec( irec->ir_free = be64_to_cpu(rec->inobt.ir_free); } +/* Simple checks for inode records. */ +xfs_failaddr_t +xfs_inobt_check_irec( + struct xfs_btree_cur *cur, + const struct xfs_inobt_rec_incore *irec) +{ + uint64_t realfree; + + if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino)) + return __this_address; + if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || + irec->ir_count > XFS_INODES_PER_CHUNK) + return __this_address; + if (irec->ir_freecount > XFS_INODES_PER_CHUNK) + return __this_address; + + /* if there are no holes, return the first available offset */ + if (!xfs_inobt_issparse(irec->ir_holemask)) + realfree = irec->ir_free; + else + realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec); + if (hweight64(realfree) != irec->ir_freecount) + return __this_address; + + return NULL; +} + /* * Get the data from the pointed-to record. */ @@ -106,38 +133,25 @@ xfs_inobt_get_rec( { struct xfs_mount *mp = cur->bc_mp; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; - uint64_t realfree; error = xfs_btree_get_rec(cur, &rec, stat); if (error || *stat == 0) return error; xfs_inobt_btrec_to_irec(mp, rec, irec); - - if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino)) - goto out_bad_rec; - if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || - irec->ir_count > XFS_INODES_PER_CHUNK) - goto out_bad_rec; - if (irec->ir_freecount > XFS_INODES_PER_CHUNK) - goto out_bad_rec; - - /* if there are no holes, return the first available offset */ - if (!xfs_inobt_issparse(irec->ir_holemask)) - realfree = irec->ir_free; - else - realfree = irec->ir_free & xfs_inobt_irec_to_allocmask(irec); - if (hweight64(realfree) != irec->ir_freecount) + fa = xfs_inobt_check_irec(cur, irec); + if (fa) goto out_bad_rec; return 0; out_bad_rec: xfs_warn(mp, - "%s Inode BTree record corruption in AG %d detected!", + "%s Inode BTree record corruption in AG %d detected at %pS!", cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", - cur->bc_ag.pag->pag_agno); + cur->bc_ag.pag->pag_agno, fa); xfs_warn(mp, "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", irec->ir_startino, irec->ir_count, irec->ir_freecount, @@ -2690,6 +2704,9 @@ xfs_ialloc_count_inodes_rec( struct xfs_ialloc_count_inodes *ci = priv; xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec); + if (xfs_inobt_check_irec(cur, &irec) != NULL) + return -EFSCORRUPTED; + ci->count += irec.ir_count; ci->freecount += irec.ir_freecount; diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index ab8c30b4ec22..90b0e5079338 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -93,6 +93,8 @@ union xfs_btree_rec; void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, const union xfs_btree_rec *rec, struct xfs_inobt_rec_incore *irec); +xfs_failaddr_t xfs_inobt_check_irec(struct xfs_btree_cur *cur, + const struct xfs_inobt_rec_incore *irec); int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, bool *exists); int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low, diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index ad6c521f05eb..f900c056b82c 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -608,7 +608,7 @@ xfs_iallocbt_maxlevels_ondisk(void) */ uint64_t xfs_inobt_irec_to_allocmask( - struct xfs_inobt_rec_incore *rec) + const struct xfs_inobt_rec_incore *rec) { uint64_t bitmap = 0; uint64_t inodespbit; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h index e859a6e05230..3262c3fe5ebe 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.h +++ b/fs/xfs/libxfs/xfs_ialloc_btree.h @@ -53,7 +53,7 @@ struct xfs_btree_cur *xfs_inobt_stage_cursor(struct xfs_perag *pag, extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int); /* ir_holemask to inode allocation bitmap conversion */ -uint64_t xfs_inobt_irec_to_allocmask(struct xfs_inobt_rec_incore *); +uint64_t xfs_inobt_irec_to_allocmask(const struct xfs_inobt_rec_incore *irec); #if defined(DEBUG) || defined(XFS_WARN) int xfs_inobt_rec_check_count(struct xfs_mount *, diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 9563769a8881..11afb4c5a161 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -119,15 +119,6 @@ xchk_iallocbt_chunk( return true; } -/* Count the number of free inodes. */ -static unsigned int -xchk_iallocbt_freecount( - xfs_inofree_t freemask) -{ - BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64)); - return hweight64(freemask); -} - /* * Check that an inode's allocation status matches ir_free in the inobt * record. First we try querying the in-core inode state, and if the inode @@ -431,24 +422,17 @@ xchk_iallocbt_rec( int holecount; int i; int error = 0; - unsigned int real_freecount; uint16_t holemask; xfs_inobt_btrec_to_irec(mp, rec, &irec); - - if (irec.ir_count > XFS_INODES_PER_CHUNK || - irec.ir_freecount > XFS_INODES_PER_CHUNK) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - real_freecount = irec.ir_freecount + - (XFS_INODES_PER_CHUNK - irec.ir_count); - if (real_freecount != xchk_iallocbt_freecount(irec.ir_free)) + if (xfs_inobt_check_irec(bs->cur, &irec) != NULL) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } agino = irec.ir_startino; /* Record has to be properly aligned within the AG. */ - if (!xfs_verify_agino(pag, agino) || - !xfs_verify_agino(pag, agino + XFS_INODES_PER_CHUNK - 1)) { + if (!xfs_verify_agino(pag, agino + XFS_INODES_PER_CHUNK - 1)) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); goto out; } -- GitLab From 2b30cc0bf0589d1ea0506c019b9b81de77535c87 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:02 -0700 Subject: [PATCH 2563/5631] xfs: standardize ondisk to incore conversion for refcount btrees Create a xfs_refcount_check_irec function to detect corruption in btree records. Fix all xfs_refcount_btrec_to_irec callsites to call the new helper and bubble up corruption reports. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_refcount.c | 45 +++++++++++++++++++++++++----------- fs/xfs/libxfs/xfs_refcount.h | 2 ++ fs/xfs/scrub/refcount.c | 14 +++-------- 3 files changed, 36 insertions(+), 25 deletions(-) diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 6dc968618e66..b77dea10c8bd 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -120,6 +120,30 @@ xfs_refcount_btrec_to_irec( irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); } +/* Simple checks for refcount records. */ +xfs_failaddr_t +xfs_refcount_check_irec( + struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec) +{ + struct xfs_perag *pag = cur->bc_ag.pag; + + if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) + return __this_address; + + if (!xfs_refcount_check_domain(irec)) + return __this_address; + + /* check for valid extent range, including overflow */ + if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) + return __this_address; + + if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) + return __this_address; + + return NULL; +} + /* * Get the data from the pointed-to record. */ @@ -132,6 +156,7 @@ xfs_refcount_get_rec( struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); @@ -139,17 +164,8 @@ xfs_refcount_get_rec( return error; xfs_refcount_btrec_to_irec(rec, irec); - if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) - goto out_bad_rec; - - if (!xfs_refcount_check_domain(irec)) - goto out_bad_rec; - - /* check for valid extent range, including overflow */ - if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) - goto out_bad_rec; - - if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) + fa = xfs_refcount_check_irec(cur, irec); + if (fa) goto out_bad_rec; trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec); @@ -157,8 +173,8 @@ xfs_refcount_get_rec( out_bad_rec: xfs_warn(mp, - "Refcount BTree record corruption in AG %d detected!", - pag->pag_agno); + "Refcount BTree record corruption in AG %d detected at %pS!", + pag->pag_agno, fa); xfs_warn(mp, "Start block 0x%x, block count 0x%x, references 0x%x", irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); @@ -1871,7 +1887,8 @@ xfs_refcount_recover_extent( INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - if (XFS_IS_CORRUPT(cur->bc_mp, + if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL || + XFS_IS_CORRUPT(cur->bc_mp, rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { kfree(rr); return -EFSCORRUPTED; diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index c89f0fcd1ee3..fc0b58d4c379 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -117,6 +117,8 @@ extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); +xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur, + const struct xfs_refcount_irec *irec); extern int xfs_refcount_insert(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 6f649cc01310..4d77049dfce2 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -340,24 +340,16 @@ xchk_refcountbt_rec( { struct xfs_refcount_irec irec; xfs_agblock_t *cow_blocks = bs->private; - struct xfs_perag *pag = bs->cur->bc_ag.pag; xfs_refcount_btrec_to_irec(rec, &irec); - - /* Check the domain and refcount are not incompatible. */ - if (!xfs_refcount_check_domain(&irec)) + if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } if (irec.rc_domain == XFS_REFC_DOMAIN_COW) (*cow_blocks) += irec.rc_blockcount; - /* Check the extent. */ - if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount)) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - if (irec.rc_refcount == 0) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - xchk_refcountbt_xref(bs->sc, &irec); return 0; -- GitLab From 39ab26d59f039c6190bbaa8118a8f0ffed84492a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:02 -0700 Subject: [PATCH 2564/5631] xfs: return a failure address from xfs_rmap_irec_offset_unpack Currently, xfs_rmap_irec_offset_unpack returns only 0 or -EFSCORRUPTED. Change this function to return the code address of a failed conversion in preparation for the next patch, which standardizes localized record checking and reporting code. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 9 ++++----- fs/xfs/libxfs/xfs_rmap.h | 9 +++++---- fs/xfs/scrub/rmap.c | 11 +++++------ 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index c2624d11f041..830b38337cd5 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -193,7 +193,7 @@ xfs_rmap_delete( } /* Convert an internal btree record to an rmap record. */ -int +xfs_failaddr_t xfs_rmap_btrec_to_irec( const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec) @@ -2320,11 +2320,10 @@ xfs_rmap_query_range_helper( { struct xfs_rmap_query_range_info *query = priv; struct xfs_rmap_irec irec; - int error; - error = xfs_rmap_btrec_to_irec(rec, &irec); - if (error) - return error; + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) + return -EFSCORRUPTED; + return query->fn(cur, &irec, query->priv); } diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 1472ae570a8a..6a08c403e8b7 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -62,13 +62,14 @@ xfs_rmap_irec_offset_pack( return x; } -static inline int +static inline xfs_failaddr_t xfs_rmap_irec_offset_unpack( __u64 offset, struct xfs_rmap_irec *irec) { if (offset & ~(XFS_RMAP_OFF_MASK | XFS_RMAP_OFF_FLAGS)) - return -EFSCORRUPTED; + return __this_address; + irec->rm_offset = XFS_RMAP_OFF(offset); irec->rm_flags = 0; if (offset & XFS_RMAP_OFF_ATTR_FORK) @@ -77,7 +78,7 @@ xfs_rmap_irec_offset_unpack( irec->rm_flags |= XFS_RMAP_BMBT_BLOCK; if (offset & XFS_RMAP_OFF_UNWRITTEN) irec->rm_flags |= XFS_RMAP_UNWRITTEN; - return 0; + return NULL; } static inline void @@ -192,7 +193,7 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno, int xfs_rmap_compare(const struct xfs_rmap_irec *a, const struct xfs_rmap_irec *b); union xfs_btree_rec; -int xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, +xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, bool *exists); diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index c6e47ef4c79b..9f661c487beb 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -100,11 +100,11 @@ xchk_rmapbt_rec( bool is_unwritten; bool is_bmbt; bool is_attr; - int error; - error = xfs_rmap_btrec_to_irec(rec, &irec); - if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error)) - goto out; + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) { + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + return 0; + } /* Check extent. */ if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock) @@ -159,8 +159,7 @@ xchk_rmapbt_rec( } xchk_rmapbt_xref(bs->sc, &irec); -out: - return error; + return 0; } /* Scrub the rmap btree for some AG. */ -- GitLab From c4e34172da26cb57f56c471728853d3a428ec832 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:03 -0700 Subject: [PATCH 2565/5631] xfs: standardize ondisk to incore conversion for rmap btrees Create a xfs_rmap_check_irec function to detect corruption in btree records. Fix all xfs_rmap_btrec_to_irec callsites to call the new helper and bubble up corruption reports. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 62 +++++++++++++++++++++++++--------------- fs/xfs/libxfs/xfs_rmap.h | 3 ++ fs/xfs/scrub/rmap.c | 39 ++----------------------- 3 files changed, 44 insertions(+), 60 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 830b38337cd5..5c7b081cef87 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -205,6 +205,36 @@ xfs_rmap_btrec_to_irec( irec); } +/* Simple checks for rmap records. */ +xfs_failaddr_t +xfs_rmap_check_irec( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + if (irec->rm_blockcount == 0) + return __this_address; + if (irec->rm_startblock <= XFS_AGFL_BLOCK(mp)) { + if (irec->rm_owner != XFS_RMAP_OWN_FS) + return __this_address; + if (irec->rm_blockcount != XFS_AGFL_BLOCK(mp) + 1) + return __this_address; + } else { + /* check for valid extent range, including overflow */ + if (!xfs_verify_agbext(cur->bc_ag.pag, irec->rm_startblock, + irec->rm_blockcount)) + return __this_address; + } + + if (!(xfs_verify_ino(mp, irec->rm_owner) || + (irec->rm_owner <= XFS_RMAP_OWN_FS && + irec->rm_owner >= XFS_RMAP_OWN_MIN))) + return __this_address; + + return NULL; +} + /* * Get the data from the pointed-to record. */ @@ -217,39 +247,24 @@ xfs_rmap_get_rec( struct xfs_mount *mp = cur->bc_mp; struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; + xfs_failaddr_t fa; int error; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !*stat) return error; - if (xfs_rmap_btrec_to_irec(rec, irec)) - goto out_bad_rec; - - if (irec->rm_blockcount == 0) - goto out_bad_rec; - if (irec->rm_startblock <= XFS_AGFL_BLOCK(mp)) { - if (irec->rm_owner != XFS_RMAP_OWN_FS) - goto out_bad_rec; - if (irec->rm_blockcount != XFS_AGFL_BLOCK(mp) + 1) - goto out_bad_rec; - } else { - /* check for valid extent range, including overflow */ - if (!xfs_verify_agbext(pag, irec->rm_startblock, - irec->rm_blockcount)) - goto out_bad_rec; - } - - if (!(xfs_verify_ino(mp, irec->rm_owner) || - (irec->rm_owner <= XFS_RMAP_OWN_FS && - irec->rm_owner >= XFS_RMAP_OWN_MIN))) + fa = xfs_rmap_btrec_to_irec(rec, irec); + if (!fa) + fa = xfs_rmap_check_irec(cur, irec); + if (fa) goto out_bad_rec; return 0; out_bad_rec: xfs_warn(mp, - "Reverse Mapping BTree record corruption in AG %d detected!", - pag->pag_agno); + "Reverse Mapping BTree record corruption in AG %d detected at %pS!", + pag->pag_agno, fa); xfs_warn(mp, "Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x", irec->rm_owner, irec->rm_flags, irec->rm_startblock, @@ -2321,7 +2336,8 @@ xfs_rmap_query_range_helper( struct xfs_rmap_query_range_info *query = priv; struct xfs_rmap_irec irec; - if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || + xfs_rmap_check_irec(cur, &irec) != NULL) return -EFSCORRUPTED; return query->fn(cur, &irec, query->priv); diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 6a08c403e8b7..7fb298bcc15f 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -195,6 +195,9 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a, union xfs_btree_rec; xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_rmap_irec *irec); +xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *irec); + int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, bool *exists); int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno, diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 9f661c487beb..353cf9d90027 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -93,43 +93,18 @@ xchk_rmapbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { - struct xfs_mount *mp = bs->cur->bc_mp; struct xfs_rmap_irec irec; - struct xfs_perag *pag = bs->cur->bc_ag.pag; bool non_inode; bool is_unwritten; bool is_bmbt; bool is_attr; - if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL) { + if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || + xfs_rmap_check_irec(bs->cur, &irec) != NULL) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); return 0; } - /* Check extent. */ - if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - if (irec.rm_owner == XFS_RMAP_OWN_FS) { - /* - * xfs_verify_agbno returns false for static fs metadata. - * Since that only exists at the start of the AG, validate - * that by hand. - */ - if (irec.rm_startblock != 0 || - irec.rm_blockcount != XFS_AGFL_BLOCK(mp) + 1) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - } else { - /* - * Otherwise we must point somewhere past the static metadata - * but before the end of the FS. Run the regular check. - */ - if (!xfs_verify_agbno(pag, irec.rm_startblock) || - !xfs_verify_agbno(pag, irec.rm_startblock + - irec.rm_blockcount - 1)) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - } - /* Check flags. */ non_inode = XFS_RMAP_NON_INODE_OWNER(irec.rm_owner); is_bmbt = irec.rm_flags & XFS_RMAP_BMBT_BLOCK; @@ -148,16 +123,6 @@ xchk_rmapbt_rec( if (non_inode && (is_bmbt || is_unwritten || is_attr)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (!non_inode) { - if (!xfs_verify_ino(mp, irec.rm_owner)) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - } else { - /* Non-inode owner within the magic values? */ - if (irec.rm_owner <= XFS_RMAP_OWN_MIN || - irec.rm_owner > XFS_RMAP_OWN_FS) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - } - xchk_rmapbt_xref(bs->sc, &irec); return 0; } -- GitLab From 69010fe3ac1fe9932a64268c32b67964fe5c06a8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:04 -0700 Subject: [PATCH 2566/5631] xfs: standardize ondisk to incore conversion for bmap btrees Fix all xfs_bmbt_disk_get_all callsites to call xfs_bmap_validate_extent and bubble up corruption reports. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index a5078d63808f..6188eba672e5 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -471,6 +471,12 @@ xchk_bmapbt_rec( return 0; xfs_bmbt_disk_get_all(&rec->bmbt, &irec); + if (xfs_bmap_validate_extent(ip, info->whichfork, &irec) != NULL) { + xchk_fblock_set_corrupt(bs->sc, info->whichfork, + irec.br_startoff); + return 0; + } + if (!xfs_iext_lookup_extent(ip, ifp, irec.br_startoff, &icur, &iext_irec) || irec.br_startoff != iext_irec.br_startoff || -- GitLab From ee12eaaa435a7be17152ac50943ee77249de624a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:04 -0700 Subject: [PATCH 2567/5631] xfs: complain about bad records in query_range helpers For every btree type except for the bmbt, refactor the code that complains about bad records into a helper and make the ->query_range helpers call it so that corruptions found via that avenue are logged. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 38 ++++++++++++++++++++-------------- fs/xfs/libxfs/xfs_ialloc.c | 38 +++++++++++++++++++++------------- fs/xfs/libxfs/xfs_refcount.c | 32 +++++++++++++++++------------ fs/xfs/libxfs/xfs_rmap.c | 40 ++++++++++++++++++++++-------------- 4 files changed, 91 insertions(+), 57 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 89c935cbcc4d..23f0acfc2a64 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -261,6 +261,24 @@ xfs_alloc_check_irec( return NULL; } +static inline int +xfs_alloc_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_alloc_rec_incore *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "%s Freespace BTree record corruption in AG %d detected at %pS!", + cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", + cur->bc_ag.pag->pag_agno, fa); + xfs_warn(mp, + "start block 0x%x block count 0x%x", irec->ar_startblock, + irec->ar_blockcount); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -272,8 +290,6 @@ xfs_alloc_get_rec( int *stat) /* output: success/failure */ { struct xfs_alloc_rec_incore irec; - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; xfs_failaddr_t fa; int error; @@ -285,21 +301,11 @@ xfs_alloc_get_rec( xfs_alloc_btrec_to_irec(rec, &irec); fa = xfs_alloc_check_irec(cur, &irec); if (fa) - goto out_bad_rec; + return xfs_alloc_complain_bad_rec(cur, fa, &irec); *bno = irec.ar_startblock; *len = irec.ar_blockcount; return 0; - -out_bad_rec: - xfs_warn(mp, - "%s Freespace BTree record corruption in AG %d detected at %pS!", - cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", - pag->pag_agno, fa); - xfs_warn(mp, - "start block 0x%x block count 0x%x", irec.ar_startblock, - irec.ar_blockcount); - return -EFSCORRUPTED; } /* @@ -3692,10 +3698,12 @@ xfs_alloc_query_range_helper( { struct xfs_alloc_query_range_info *query = priv; struct xfs_alloc_rec_incore irec; + xfs_failaddr_t fa; xfs_alloc_btrec_to_irec(rec, &irec); - if (xfs_alloc_check_irec(cur, &irec) != NULL) - return -EFSCORRUPTED; + fa = xfs_alloc_check_irec(cur, &irec); + if (fa) + return xfs_alloc_complain_bad_rec(cur, fa, &irec); return query->fn(cur, &irec, query->priv); } diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 32af8326ad76..b7dc8b81a133 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -122,6 +122,25 @@ xfs_inobt_check_irec( return NULL; } +static inline int +xfs_inobt_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_inobt_rec_incore *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "%s Inode BTree record corruption in AG %d detected at %pS!", + cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", + cur->bc_ag.pag->pag_agno, fa); + xfs_warn(mp, +"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", + irec->ir_startino, irec->ir_count, irec->ir_freecount, + irec->ir_free, irec->ir_holemask); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -143,20 +162,9 @@ xfs_inobt_get_rec( xfs_inobt_btrec_to_irec(mp, rec, irec); fa = xfs_inobt_check_irec(cur, irec); if (fa) - goto out_bad_rec; + return xfs_inobt_complain_bad_rec(cur, fa, irec); return 0; - -out_bad_rec: - xfs_warn(mp, - "%s Inode BTree record corruption in AG %d detected at %pS!", - cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", - cur->bc_ag.pag->pag_agno, fa); - xfs_warn(mp, -"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x", - irec->ir_startino, irec->ir_count, irec->ir_freecount, - irec->ir_free, irec->ir_holemask); - return -EFSCORRUPTED; } /* @@ -2702,10 +2710,12 @@ xfs_ialloc_count_inodes_rec( { struct xfs_inobt_rec_incore irec; struct xfs_ialloc_count_inodes *ci = priv; + xfs_failaddr_t fa; xfs_inobt_btrec_to_irec(cur->bc_mp, rec, &irec); - if (xfs_inobt_check_irec(cur, &irec) != NULL) - return -EFSCORRUPTED; + fa = xfs_inobt_check_irec(cur, &irec); + if (fa) + return xfs_inobt_complain_bad_rec(cur, fa, &irec); ci->count += irec.ir_count; ci->freecount += irec.ir_freecount; diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index b77dea10c8bd..335f84bef81c 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -144,6 +144,23 @@ xfs_refcount_check_irec( return NULL; } +static inline int +xfs_refcount_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_refcount_irec *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "Refcount BTree record corruption in AG %d detected at %pS!", + cur->bc_ag.pag->pag_agno, fa); + xfs_warn(mp, + "Start block 0x%x, block count 0x%x, references 0x%x", + irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -153,8 +170,6 @@ xfs_refcount_get_rec( struct xfs_refcount_irec *irec, int *stat) { - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; xfs_failaddr_t fa; int error; @@ -166,19 +181,10 @@ xfs_refcount_get_rec( xfs_refcount_btrec_to_irec(rec, irec); fa = xfs_refcount_check_irec(cur, irec); if (fa) - goto out_bad_rec; + return xfs_refcount_complain_bad_rec(cur, fa, irec); - trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec); + trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); return 0; - -out_bad_rec: - xfs_warn(mp, - "Refcount BTree record corruption in AG %d detected at %pS!", - pag->pag_agno, fa); - xfs_warn(mp, - "Start block 0x%x, block count 0x%x, references 0x%x", - irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount); - return -EFSCORRUPTED; } /* diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 5c7b081cef87..641114a023f2 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -235,6 +235,24 @@ xfs_rmap_check_irec( return NULL; } +static inline int +xfs_rmap_complain_bad_rec( + struct xfs_btree_cur *cur, + xfs_failaddr_t fa, + const struct xfs_rmap_irec *irec) +{ + struct xfs_mount *mp = cur->bc_mp; + + xfs_warn(mp, + "Reverse Mapping BTree record corruption in AG %d detected at %pS!", + cur->bc_ag.pag->pag_agno, fa); + xfs_warn(mp, + "Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x", + irec->rm_owner, irec->rm_flags, irec->rm_startblock, + irec->rm_blockcount); + return -EFSCORRUPTED; +} + /* * Get the data from the pointed-to record. */ @@ -244,8 +262,6 @@ xfs_rmap_get_rec( struct xfs_rmap_irec *irec, int *stat) { - struct xfs_mount *mp = cur->bc_mp; - struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; xfs_failaddr_t fa; int error; @@ -258,18 +274,9 @@ xfs_rmap_get_rec( if (!fa) fa = xfs_rmap_check_irec(cur, irec); if (fa) - goto out_bad_rec; + return xfs_rmap_complain_bad_rec(cur, fa, irec); return 0; -out_bad_rec: - xfs_warn(mp, - "Reverse Mapping BTree record corruption in AG %d detected at %pS!", - pag->pag_agno, fa); - xfs_warn(mp, - "Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x", - irec->rm_owner, irec->rm_flags, irec->rm_startblock, - irec->rm_blockcount); - return -EFSCORRUPTED; } struct xfs_find_left_neighbor_info { @@ -2335,10 +2342,13 @@ xfs_rmap_query_range_helper( { struct xfs_rmap_query_range_info *query = priv; struct xfs_rmap_irec irec; + xfs_failaddr_t fa; - if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || - xfs_rmap_check_irec(cur, &irec) != NULL) - return -EFSCORRUPTED; + fa = xfs_rmap_btrec_to_irec(rec, &irec); + if (!fa) + fa = xfs_rmap_check_irec(cur, &irec); + if (fa) + return xfs_rmap_complain_bad_rec(cur, fa, &irec); return query->fn(cur, &irec, query->priv); } -- GitLab From 7d7d6d2fd0444904f12e70d9c930556c4eb44337 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:05 -0700 Subject: [PATCH 2568/5631] xfs: hoist rmap record flag checks from scrub Move the rmap record flag checks from xchk_rmapbt_rec into xfs_rmap_check_irec so that they are applied everywhere. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 22 ++++++++++++++++++++++ fs/xfs/scrub/rmap.c | 22 ---------------------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 641114a023f2..e66ecd794a84 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -212,6 +212,10 @@ xfs_rmap_check_irec( const struct xfs_rmap_irec *irec) { struct xfs_mount *mp = cur->bc_mp; + bool is_inode; + bool is_unwritten; + bool is_bmbt; + bool is_attr; if (irec->rm_blockcount == 0) return __this_address; @@ -232,6 +236,24 @@ xfs_rmap_check_irec( irec->rm_owner >= XFS_RMAP_OWN_MIN))) return __this_address; + /* Check flags. */ + is_inode = !XFS_RMAP_NON_INODE_OWNER(irec->rm_owner); + is_bmbt = irec->rm_flags & XFS_RMAP_BMBT_BLOCK; + is_attr = irec->rm_flags & XFS_RMAP_ATTR_FORK; + is_unwritten = irec->rm_flags & XFS_RMAP_UNWRITTEN; + + if (is_bmbt && irec->rm_offset != 0) + return __this_address; + + if (!is_inode && irec->rm_offset != 0) + return __this_address; + + if (is_unwritten && (is_bmbt || !is_inode || is_attr)) + return __this_address; + + if (!is_inode && (is_bmbt || is_unwritten || is_attr)) + return __this_address; + return NULL; } diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 353cf9d90027..ef6e4b8546a6 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -94,10 +94,6 @@ xchk_rmapbt_rec( const union xfs_btree_rec *rec) { struct xfs_rmap_irec irec; - bool non_inode; - bool is_unwritten; - bool is_bmbt; - bool is_attr; if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || xfs_rmap_check_irec(bs->cur, &irec) != NULL) { @@ -105,24 +101,6 @@ xchk_rmapbt_rec( return 0; } - /* Check flags. */ - non_inode = XFS_RMAP_NON_INODE_OWNER(irec.rm_owner); - is_bmbt = irec.rm_flags & XFS_RMAP_BMBT_BLOCK; - is_attr = irec.rm_flags & XFS_RMAP_ATTR_FORK; - is_unwritten = irec.rm_flags & XFS_RMAP_UNWRITTEN; - - if (is_bmbt && irec.rm_offset != 0) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - if (non_inode && irec.rm_offset != 0) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - if (is_unwritten && (is_bmbt || non_inode || is_attr)) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - - if (non_inode && (is_bmbt || is_unwritten || is_attr)) - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - xchk_rmapbt_xref(bs->sc, &irec); return 0; } -- GitLab From 6a3bd8fcf9afb47c703cb268f30f60aa2e7af86a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:05 -0700 Subject: [PATCH 2569/5631] xfs: complain about bad file mapping records in the ondisk bmbt Similar to what we've just done for the other btrees, create a function to log corrupt bmbt records and call it whenever we encounter a bad record in the ondisk btree. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 31 ++++++++++++++++++++++++++++++- fs/xfs/libxfs/xfs_bmap.h | 2 ++ fs/xfs/libxfs/xfs_inode_fork.c | 3 ++- 3 files changed, 34 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 0b4fb3979bdc..5e66807737c5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1083,6 +1083,34 @@ struct xfs_iread_state { xfs_extnum_t loaded; }; +int +xfs_bmap_complain_bad_rec( + struct xfs_inode *ip, + int whichfork, + xfs_failaddr_t fa, + const struct xfs_bmbt_irec *irec) +{ + struct xfs_mount *mp = ip->i_mount; + const char *forkname; + + switch (whichfork) { + case XFS_DATA_FORK: forkname = "data"; break; + case XFS_ATTR_FORK: forkname = "attr"; break; + case XFS_COW_FORK: forkname = "CoW"; break; + default: forkname = "???"; break; + } + + xfs_warn(mp, + "Bmap BTree record corruption in inode 0x%llx %s fork detected at %pS!", + ip->i_ino, forkname, fa); + xfs_warn(mp, + "Offset 0x%llx, start block 0x%llx, block count 0x%llx state 0x%x", + irec->br_startoff, irec->br_startblock, irec->br_blockcount, + irec->br_state); + + return -EFSCORRUPTED; +} + /* Stuff every bmbt record from this block into the incore extent map. */ static int xfs_iread_bmbt_block( @@ -1125,7 +1153,8 @@ xfs_iread_bmbt_block( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iread_extents(2)", frp, sizeof(*frp), fa); - return -EFSCORRUPTED; + return xfs_bmap_complain_bad_rec(ip, whichfork, fa, + &new); } xfs_iext_insert(ip, &ir->icur, &new, xfs_bmap_fork_to_state(whichfork)); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e5a492027aea..9ff030d12981 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -265,6 +265,8 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork) xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *irec); +int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork, + xfs_failaddr_t fa, const struct xfs_bmbt_irec *irec); int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock, diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 6b21760184d9..ff37eecec4b0 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -140,7 +140,8 @@ xfs_iformat_extents( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_extents(2)", dp, sizeof(*dp), fa); - return -EFSCORRUPTED; + return xfs_bmap_complain_bad_rec(ip, whichfork, + fa, &new); } xfs_iext_insert(ip, &icur, &new, state); -- GitLab From e774b2ea0bb130d00e3cb1c29cd91028d0c0c83d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:06 -0700 Subject: [PATCH 2570/5631] xfs: hoist rmap record flag checks from scrub Move the rmap record flag checks from xchk_rmapbt_rec into xfs_rmap_check_irec so that they are applied everywhere. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index e66ecd794a84..da008d317f83 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -254,6 +254,11 @@ xfs_rmap_check_irec( if (!is_inode && (is_bmbt || is_unwritten || is_attr)) return __this_address; + /* Check for a valid fork offset, if applicable. */ + if (is_inode && !is_bmbt && + !xfs_verify_fileext(mp, irec->rm_offset, irec->rm_blockcount)) + return __this_address; + return NULL; } -- GitLab From de1a9ce225e93b22d189f8ffbce20074bc803121 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:06 -0700 Subject: [PATCH 2571/5631] xfs: hoist inode record alignment checks from scrub Move the inobt record alignment checks from xchk_iallocbt_rec into xfs_inobt_check_irec so that they are applied everywhere. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ialloc.c | 4 ++++ fs/xfs/scrub/ialloc.c | 6 ------ 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index b7dc8b81a133..0d2980accd3c 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -103,8 +103,12 @@ xfs_inobt_check_irec( { uint64_t realfree; + /* Record has to be properly aligned within the AG. */ if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino)) return __this_address; + if (!xfs_verify_agino(cur->bc_ag.pag, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1)) + return __this_address; if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT || irec->ir_count > XFS_INODES_PER_CHUNK) return __this_address; diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 11afb4c5a161..ca5a7e0f5451 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -413,7 +413,6 @@ xchk_iallocbt_rec( const union xfs_btree_rec *rec) { struct xfs_mount *mp = bs->cur->bc_mp; - struct xfs_perag *pag = bs->cur->bc_ag.pag; struct xchk_iallocbt *iabt = bs->private; struct xfs_inobt_rec_incore irec; uint64_t holes; @@ -431,11 +430,6 @@ xchk_iallocbt_rec( } agino = irec.ir_startino; - /* Record has to be properly aligned within the AG. */ - if (!xfs_verify_agino(pag, agino + XFS_INODES_PER_CHUNK - 1)) { - xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - goto out; - } xchk_iallocbt_rec_alignment(bs, &irec); if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) -- GitLab From 08c987deca56687c0930f308f5148ef1af38dc14 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:07 -0700 Subject: [PATCH 2572/5631] xfs: fix rm_offset flag handling in rmap keys Keys for extent interval records in the reverse mapping btree are supposed to be computed as follows: (physical block, owner, fork, is_btree, offset) This provides users the ability to look up a reverse mapping from a file block mapping record -- start with the physical block; then if there are multiple records for the same block, move on to the owner; then the inode fork type; and so on to the file offset. Unfortunately, the code that creates rmap lookup keys from rmap records forgot to mask off the record attribute flags, leading to ondisk keys that look like this: (physical block, owner, fork, is_btree, unwritten state, offset) Fortunately, this has all worked ok for the past six years because the key comparison functions incorrectly ignore the fork/bmbt/unwritten information that's encoded in the on-disk offset. This means that lookup comparisons are only done with: (physical block, owner, offset) Queries can (theoretically) return incorrect results because of this omission. On consistent filesystems this isn't an issue because xattr and bmbt blocks cannot be shared and hence the comparisons succeed purely on the contents of the rm_startblock field. For the one case where we support sharing (written data fork blocks) all flag bits are zero, so the omission in the comparison has no ill effects. Unfortunately, this bug prevents scrub from detecting incorrect fork and bmbt flag bits in the rmap btree, so we really do need to fix the compare code. Old filesystems with the unwritten bit erroneously set in the rmap key struct will work fine on new kernels since we still ignore the unwritten bit. New filesystems on older kernels will work fine since the old kernels never paid attention to the unwritten bit. A previous version of this patch forgot to keep the (un)written state flag masked during the comparison and caused a major regression in 5.9.x since unwritten extent conversion can update an rmap record without requiring key updates. Note that blocks cannot go directly from data fork to attr fork without being deallocated and reallocated, nor can they be added to or removed from a bmbt without a free/alloc cycle, so this should not cause any regressions. Found by fuzzing keys[1].attrfork = ones on xfs/371. Fixes: 4b8ed67794fe ("xfs: add rmap btree operations") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap_btree.c | 40 +++++++++++++++++++++++++--------- 1 file changed, 30 insertions(+), 10 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 56d074b42660..84e2b692f034 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -156,6 +156,16 @@ xfs_rmapbt_get_maxrecs( return cur->bc_mp->m_rmap_mxr[level != 0]; } +/* + * Convert the ondisk record's offset field into the ondisk key's offset field. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline __be64 ondisk_rec_offset_to_key(const union xfs_btree_rec *rec) +{ + return rec->rmap.rm_offset & ~cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); +} + STATIC void xfs_rmapbt_init_key_from_rec( union xfs_btree_key *key, @@ -163,7 +173,7 @@ xfs_rmapbt_init_key_from_rec( { key->rmap.rm_startblock = rec->rmap.rm_startblock; key->rmap.rm_owner = rec->rmap.rm_owner; - key->rmap.rm_offset = rec->rmap.rm_offset; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); } /* @@ -186,7 +196,7 @@ xfs_rmapbt_init_high_key_from_rec( key->rmap.rm_startblock = rec->rmap.rm_startblock; be32_add_cpu(&key->rmap.rm_startblock, adj); key->rmap.rm_owner = rec->rmap.rm_owner; - key->rmap.rm_offset = rec->rmap.rm_offset; + key->rmap.rm_offset = ondisk_rec_offset_to_key(rec); if (XFS_RMAP_NON_INODE_OWNER(be64_to_cpu(rec->rmap.rm_owner)) || XFS_RMAP_IS_BMBT_BLOCK(be64_to_cpu(rec->rmap.rm_offset))) return; @@ -219,6 +229,16 @@ xfs_rmapbt_init_ptr_from_cur( ptr->s = agf->agf_roots[cur->bc_btnum]; } +/* + * Mask the appropriate parts of the ondisk key field for a key comparison. + * Fork and bmbt are significant parts of the rmap record key, but written + * status is merely a record attribute. + */ +static inline uint64_t offset_keymask(uint64_t offset) +{ + return offset & ~XFS_RMAP_OFF_UNWRITTEN; +} + STATIC int64_t xfs_rmapbt_key_diff( struct xfs_btree_cur *cur, @@ -240,8 +260,8 @@ xfs_rmapbt_key_diff( else if (y > x) return -1; - x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset)); - y = rec->rm_offset; + x = offset_keymask(be64_to_cpu(kp->rm_offset)); + y = offset_keymask(xfs_rmap_irec_offset_pack(rec)); if (x > y) return 1; else if (y > x) @@ -272,8 +292,8 @@ xfs_rmapbt_diff_two_keys( else if (y > x) return -1; - x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset)); - y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset)); + x = offset_keymask(be64_to_cpu(kp1->rm_offset)); + y = offset_keymask(be64_to_cpu(kp2->rm_offset)); if (x > y) return 1; else if (y > x) @@ -387,8 +407,8 @@ xfs_rmapbt_keys_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset)); + a = offset_keymask(be64_to_cpu(k1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(k2->rmap.rm_offset)); if (a <= b) return 1; return 0; @@ -417,8 +437,8 @@ xfs_rmapbt_recs_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset)); + a = offset_keymask(be64_to_cpu(r1->rmap.rm_offset)); + b = offset_keymask(be64_to_cpu(r2->rmap.rm_offset)); if (a <= b) return 1; return 0; -- GitLab From 38384569a2a8a721623d80c5ae3bcf80614ab792 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:07 -0700 Subject: [PATCH 2573/5631] xfs: detect unwritten bit set in rmapbt node block keys In the last patch, we changed the rmapbt code to remove the UNWRITTEN bit when creating an rmapbt key from an rmapbt record, and we changed the rmapbt key comparison code to start considering the ATTR and BMBT flags during lookup. This brought the behavior of the rmapbt implementation in line with its specification. However, there may exist filesystems that have the unwritten bit still set in the rmapbt keys. We should detect these situations and flag the rmapbt as one that would benefit from optimization. Eventually, online repair will be able to do something in response to this. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/btree.c | 10 +++++++++ fs/xfs/scrub/btree.h | 2 ++ fs/xfs/scrub/rmap.c | 53 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 65 insertions(+) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 626282dbe2e3..de4b29ae0839 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -119,6 +119,16 @@ xchk_btree_xref_set_corrupt( __return_address); } +void +xchk_btree_set_preen( + struct xfs_scrub *sc, + struct xfs_btree_cur *cur, + int level) +{ + __xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_PREEN, + __return_address); +} + /* * Make sure this record is in order and doesn't stray outside of the parent * keys. diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h index 70461885c6c7..639e44e7544f 100644 --- a/fs/xfs/scrub/btree.h +++ b/fs/xfs/scrub/btree.h @@ -19,6 +19,8 @@ bool xchk_btree_xref_process_error(struct xfs_scrub *sc, /* Check for btree corruption. */ void xchk_btree_set_corrupt(struct xfs_scrub *sc, struct xfs_btree_cur *cur, int level); +void xchk_btree_set_preen(struct xfs_scrub *sc, struct xfs_btree_cur *cur, + int level); /* Check for btree xref discrepancies. */ void xchk_btree_xref_set_corrupt(struct xfs_scrub *sc, diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index ef6e4b8546a6..8e78e1bc9eef 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -87,6 +87,58 @@ xchk_rmapbt_xref( xchk_rmapbt_xref_refc(sc, irec); } +/* + * Check for bogus UNWRITTEN flags in the rmapbt node block keys. + * + * In reverse mapping records, the file mapping extent state + * (XFS_RMAP_OFF_UNWRITTEN) is a record attribute, not a key field. It is not + * involved in lookups in any way. In older kernels, the functions that + * convert rmapbt records to keys forgot to filter out the extent state bit, + * even though the key comparison functions have filtered the flag correctly. + * If we spot an rmap key with the unwritten bit set in rm_offset, we should + * mark the btree as needing optimization to rebuild the btree without those + * flags. + */ +STATIC void +xchk_rmapbt_check_unwritten_in_keyflags( + struct xchk_btree *bs) +{ + struct xfs_scrub *sc = bs->sc; + struct xfs_btree_cur *cur = bs->cur; + struct xfs_btree_block *keyblock; + union xfs_btree_key *lkey, *hkey; + __be64 badflag = cpu_to_be64(XFS_RMAP_OFF_UNWRITTEN); + unsigned int level; + + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_PREEN) + return; + + for (level = 1; level < cur->bc_nlevels; level++) { + struct xfs_buf *bp; + unsigned int ptr; + + /* Only check the first time we've seen this node block. */ + if (cur->bc_levels[level].ptr > 1) + continue; + + keyblock = xfs_btree_get_block(cur, level, &bp); + for (ptr = 1; ptr <= be16_to_cpu(keyblock->bb_numrecs); ptr++) { + lkey = xfs_btree_key_addr(cur, ptr, keyblock); + + if (lkey->rmap.rm_offset & badflag) { + xchk_btree_set_preen(sc, cur, level); + break; + } + + hkey = xfs_btree_high_key_addr(cur, ptr, keyblock); + if (hkey->rmap.rm_offset & badflag) { + xchk_btree_set_preen(sc, cur, level); + break; + } + } + } +} + /* Scrub an rmapbt record. */ STATIC int xchk_rmapbt_rec( @@ -101,6 +153,7 @@ xchk_rmapbt_rec( return 0; } + xchk_rmapbt_check_unwritten_in_keyflags(bs); xchk_rmapbt_xref(bs->sc, &irec); return 0; } -- GitLab From c99f99fa3eafc824ea6859590f5d2e4c6a7f4359 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:08 -0700 Subject: [PATCH 2574/5631] xfs: check btree keys reflect the child block When scrub is checking a non-root btree block, it should make sure that the keys in the parent btree block accurately capture the keyspace that the child block stores. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Dave Chinner --- fs/xfs/scrub/btree.c | 49 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 48 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index de4b29ae0839..d9ab280eb6c4 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -529,6 +529,48 @@ xchk_btree_check_minrecs( xchk_btree_set_corrupt(bs->sc, cur, level); } +/* + * If this btree block has a parent, make sure that the parent's keys capture + * the keyspace contained in this block. + */ +STATIC void +xchk_btree_block_check_keys( + struct xchk_btree *bs, + int level, + struct xfs_btree_block *block) +{ + union xfs_btree_key block_key; + union xfs_btree_key *block_high_key; + union xfs_btree_key *parent_low_key, *parent_high_key; + struct xfs_btree_cur *cur = bs->cur; + struct xfs_btree_block *parent_block; + struct xfs_buf *bp; + + if (level == cur->bc_nlevels - 1) + return; + + xfs_btree_get_keys(cur, block, &block_key); + + /* Make sure the low key of this block matches the parent. */ + parent_block = xfs_btree_get_block(cur, level + 1, &bp); + parent_low_key = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, + parent_block); + if (cur->bc_ops->diff_two_keys(cur, &block_key, parent_low_key)) { + xchk_btree_set_corrupt(bs->sc, bs->cur, level); + return; + } + + if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) + return; + + /* Make sure the high key of this block matches the parent. */ + parent_high_key = xfs_btree_high_key_addr(cur, + cur->bc_levels[level + 1].ptr, parent_block); + block_high_key = xfs_btree_high_key_from_key(cur, &block_key); + if (cur->bc_ops->diff_two_keys(cur, block_high_key, parent_high_key)) + xchk_btree_set_corrupt(bs->sc, bs->cur, level); +} + /* * Grab and scrub a btree block given a btree pointer. Returns block * and buffer pointers (if applicable) if they're ok to use. @@ -580,7 +622,12 @@ xchk_btree_get_block( * Check the block's siblings; this function absorbs error codes * for us. */ - return xchk_btree_block_check_siblings(bs, *pblock); + error = xchk_btree_block_check_siblings(bs, *pblock); + if (error) + return error; + + xchk_btree_block_check_keys(bs, level, *pblock); + return 0; } /* -- GitLab From ee5fe8ff6d19b35e7547af789cba877dbf04517b Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:09 -0700 Subject: [PATCH 2575/5631] xfs: refactor converting btree irec to btree key We keep doing these conversions to support btree queries, so refactor this into a helper. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index c4649cc624e1..5ea1c27e2be6 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4937,6 +4937,19 @@ xfs_btree_overlapped_query_range( return error; } +static inline void +xfs_btree_key_from_irec( + struct xfs_btree_cur *cur, + union xfs_btree_key *key, + const union xfs_btree_irec *irec) +{ + union xfs_btree_rec rec; + + cur->bc_rec = *irec; + cur->bc_ops->init_rec_from_cur(cur, &rec); + cur->bc_ops->init_key_from_rec(key, &rec); +} + /* * Query a btree for all records overlapping a given interval of keys. The * supplied function will be called with each record found; return one of the @@ -4951,18 +4964,12 @@ xfs_btree_query_range( xfs_btree_query_range_fn fn, void *priv) { - union xfs_btree_rec rec; union xfs_btree_key low_key; union xfs_btree_key high_key; /* Find the keys of both ends of the interval. */ - cur->bc_rec = *high_rec; - cur->bc_ops->init_rec_from_cur(cur, &rec); - cur->bc_ops->init_key_from_rec(&high_key, &rec); - - cur->bc_rec = *low_rec; - cur->bc_ops->init_rec_from_cur(cur, &rec); - cur->bc_ops->init_key_from_rec(&low_key, &rec); + xfs_btree_key_from_irec(cur, &high_key, high_rec); + xfs_btree_key_from_irec(cur, &low_key, low_rec); /* Enforce low key < high key. */ if (cur->bc_ops->diff_two_keys(cur, &low_key, &high_key) > 0) -- GitLab From 2bea8df0a52b05bc0dddd54e950ae37c83533b03 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:09 -0700 Subject: [PATCH 2576/5631] xfs: always scrub record/key order of interior records In commit d47fef9342d0, we removed the firstrec and firstkey fields of struct xchk_btree because Christoph thought they were unnecessary because we could use the record index in the btree cursor. This is incorrect because bc_ptrs (now bc_levels[].ptr) tracks the cursor position within a specific btree block, not within the entire level. The end result is that scrub no longer detects situations where the rightmost record of a block is identical to the leftmost record of that block's right sibling. Fix this regression by reintroducing record validity booleans so that order checking skips *only* the leftmost record/key in each level. Fixes: d47fef9342d0 ("xfs: don't track firstrec/firstkey separately in xchk_btree") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/btree.c | 14 ++++++++------ fs/xfs/scrub/btree.h | 8 +++++++- 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index d9ab280eb6c4..4ec3b1cab018 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -151,11 +151,12 @@ xchk_btree_rec( trace_xchk_btree_rec(bs->sc, cur, 0); - /* If this isn't the first record, are they in order? */ - if (cur->bc_levels[0].ptr > 1 && + /* Are all records across all record blocks in order? */ + if (bs->lastrec_valid && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec)) xchk_btree_set_corrupt(bs->sc, cur, 0); memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len); + bs->lastrec_valid = true; if (cur->bc_nlevels == 1) return; @@ -198,11 +199,12 @@ xchk_btree_key( trace_xchk_btree_key(bs->sc, cur, level); - /* If this isn't the first key, are they in order? */ - if (cur->bc_levels[level].ptr > 1 && - !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level - 1], key)) + /* Are all low keys across all node blocks in order? */ + if (bs->lastkey[level - 1].valid && + !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level - 1].key, key)) xchk_btree_set_corrupt(bs->sc, cur, level); - memcpy(&bs->lastkey[level - 1], key, cur->bc_ops->key_len); + memcpy(&bs->lastkey[level - 1].key, key, cur->bc_ops->key_len); + bs->lastkey[level - 1].valid = true; if (level + 1 >= cur->bc_nlevels) return; diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h index 639e44e7544f..9d7b9ee8bef4 100644 --- a/fs/xfs/scrub/btree.h +++ b/fs/xfs/scrub/btree.h @@ -31,6 +31,11 @@ typedef int (*xchk_btree_rec_fn)( struct xchk_btree *bs, const union xfs_btree_rec *rec); +struct xchk_btree_key { + union xfs_btree_key key; + bool valid; +}; + struct xchk_btree { /* caller-provided scrub state */ struct xfs_scrub *sc; @@ -40,11 +45,12 @@ struct xchk_btree { void *private; /* internal scrub state */ + bool lastrec_valid; union xfs_btree_rec lastrec; struct list_head to_check; /* this element must come last! */ - union xfs_btree_key lastkey[]; + struct xchk_btree_key lastkey[]; }; /* -- GitLab From bd7e795108ccd8d0f3dc34e16957cbba7e89f342 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:10 -0700 Subject: [PATCH 2577/5631] xfs: refactor ->diff_two_keys callsites Create wrapper functions around ->diff_two_keys so that we don't have to remember what the return values mean, and adjust some of the code comments to reflect the longtime code behavior. We're going to introduce more uses of ->diff_two_keys in the next patch, so reduce the cognitive load for readers by doing this refactoring now. Suggested-by: Dave Chinner Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_btree.c | 57 +++++++++++++++++---------------------- fs/xfs/libxfs/xfs_btree.h | 55 +++++++++++++++++++++++++++++++++++++ fs/xfs/scrub/btree.c | 24 ++++++++--------- 3 files changed, 91 insertions(+), 45 deletions(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5ea1c27e2be6..92c610850fac 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -2067,8 +2067,7 @@ xfs_btree_get_leaf_keys( for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { rec = xfs_btree_rec_addr(cur, n, block); cur->bc_ops->init_high_key_from_rec(&hkey, rec); - if (cur->bc_ops->diff_two_keys(cur, &hkey, &max_hkey) - > 0) + if (xfs_btree_keycmp_gt(cur, &hkey, &max_hkey)) max_hkey = hkey; } @@ -2096,7 +2095,7 @@ xfs_btree_get_node_keys( max_hkey = xfs_btree_high_key_addr(cur, 1, block); for (n = 2; n <= xfs_btree_get_numrecs(block); n++) { hkey = xfs_btree_high_key_addr(cur, n, block); - if (cur->bc_ops->diff_two_keys(cur, hkey, max_hkey) > 0) + if (xfs_btree_keycmp_gt(cur, hkey, max_hkey)) max_hkey = hkey; } @@ -2183,8 +2182,8 @@ __xfs_btree_updkeys( nlkey = xfs_btree_key_addr(cur, ptr, block); nhkey = xfs_btree_high_key_addr(cur, ptr, block); if (!force_all && - !(cur->bc_ops->diff_two_keys(cur, nlkey, lkey) != 0 || - cur->bc_ops->diff_two_keys(cur, nhkey, hkey) != 0)) + xfs_btree_keycmp_eq(cur, nlkey, lkey) && + xfs_btree_keycmp_eq(cur, nhkey, hkey)) break; xfs_btree_copy_keys(cur, nlkey, lkey, 1); xfs_btree_log_keys(cur, bp, ptr, ptr); @@ -4716,7 +4715,6 @@ xfs_btree_simple_query_range( { union xfs_btree_rec *recp; union xfs_btree_key rec_key; - int64_t diff; int stat; bool firstrec = true; int error; @@ -4746,20 +4744,17 @@ xfs_btree_simple_query_range( if (error || !stat) break; - /* Skip if high_key(rec) < low_key. */ + /* Skip if low_key > high_key(rec). */ if (firstrec) { cur->bc_ops->init_high_key_from_rec(&rec_key, recp); firstrec = false; - diff = cur->bc_ops->diff_two_keys(cur, low_key, - &rec_key); - if (diff > 0) + if (xfs_btree_keycmp_gt(cur, low_key, &rec_key)) goto advloop; } - /* Stop if high_key < low_key(rec). */ + /* Stop if low_key(rec) > high_key. */ cur->bc_ops->init_key_from_rec(&rec_key, recp); - diff = cur->bc_ops->diff_two_keys(cur, &rec_key, high_key); - if (diff > 0) + if (xfs_btree_keycmp_gt(cur, &rec_key, high_key)) break; /* Callback */ @@ -4813,8 +4808,6 @@ xfs_btree_overlapped_query_range( union xfs_btree_key *hkp; union xfs_btree_rec *recp; struct xfs_btree_block *block; - int64_t ldiff; - int64_t hdiff; int level; struct xfs_buf *bp; int i; @@ -4854,25 +4847,23 @@ xfs_btree_overlapped_query_range( block); cur->bc_ops->init_high_key_from_rec(&rec_hkey, recp); - ldiff = cur->bc_ops->diff_two_keys(cur, &rec_hkey, - low_key); - cur->bc_ops->init_key_from_rec(&rec_key, recp); - hdiff = cur->bc_ops->diff_two_keys(cur, high_key, - &rec_key); /* + * If (query's high key < record's low key), then there + * are no more interesting records in this block. Pop + * up to the leaf level to find more record blocks. + * * If (record's high key >= query's low key) and * (query's high key >= record's low key), then * this record overlaps the query range; callback. */ - if (ldiff >= 0 && hdiff >= 0) { + if (xfs_btree_keycmp_lt(cur, high_key, &rec_key)) + goto pop_up; + if (xfs_btree_keycmp_ge(cur, &rec_hkey, low_key)) { error = fn(cur, recp, priv); if (error) break; - } else if (hdiff < 0) { - /* Record is larger than high key; pop. */ - goto pop_up; } cur->bc_levels[level].ptr++; continue; @@ -4884,15 +4875,18 @@ xfs_btree_overlapped_query_range( block); pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block); - ldiff = cur->bc_ops->diff_two_keys(cur, hkp, low_key); - hdiff = cur->bc_ops->diff_two_keys(cur, high_key, lkp); - /* + * If (query's high key < pointer's low key), then there are no + * more interesting keys in this block. Pop up one leaf level + * to continue looking for records. + * * If (pointer's high key >= query's low key) and * (query's high key >= pointer's low key), then * this record overlaps the query range; follow pointer. */ - if (ldiff >= 0 && hdiff >= 0) { + if (xfs_btree_keycmp_lt(cur, high_key, lkp)) + goto pop_up; + if (xfs_btree_keycmp_ge(cur, hkp, low_key)) { level--; error = xfs_btree_lookup_get_block(cur, level, pp, &block); @@ -4907,9 +4901,6 @@ xfs_btree_overlapped_query_range( #endif cur->bc_levels[level].ptr = 1; continue; - } else if (hdiff < 0) { - /* The low key is larger than the upper range; pop. */ - goto pop_up; } cur->bc_levels[level].ptr++; } @@ -4971,8 +4962,8 @@ xfs_btree_query_range( xfs_btree_key_from_irec(cur, &high_key, high_rec); xfs_btree_key_from_irec(cur, &low_key, low_rec); - /* Enforce low key < high key. */ - if (cur->bc_ops->diff_two_keys(cur, &low_key, &high_key) > 0) + /* Enforce low key <= high key. */ + if (!xfs_btree_keycmp_le(cur, &low_key, &high_key)) return -EINVAL; if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 29c4b4ccb909..f5aa4b893ee7 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -546,6 +546,61 @@ int xfs_btree_has_record(struct xfs_btree_cur *cur, bool xfs_btree_has_more_records(struct xfs_btree_cur *cur); struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur); +/* Key comparison helpers */ +static inline bool +xfs_btree_keycmp_lt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->diff_two_keys(cur, key1, key2) < 0; +} + +static inline bool +xfs_btree_keycmp_gt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->diff_two_keys(cur, key1, key2) > 0; +} + +static inline bool +xfs_btree_keycmp_eq( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return cur->bc_ops->diff_two_keys(cur, key1, key2) == 0; +} + +static inline bool +xfs_btree_keycmp_le( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_gt(cur, key1, key2); +} + +static inline bool +xfs_btree_keycmp_ge( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_lt(cur, key1, key2); +} + +static inline bool +xfs_btree_keycmp_ne( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return !xfs_btree_keycmp_eq(cur, key1, key2); +} + /* Does this cursor point to the last block in the given level? */ static inline bool xfs_btree_islastblock( diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 4ec3b1cab018..1165dc05a179 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -161,20 +161,20 @@ xchk_btree_rec( if (cur->bc_nlevels == 1) return; - /* Is this at least as large as the parent low key? */ + /* Is low_key(rec) at least as large as the parent low key? */ cur->bc_ops->init_key_from_rec(&key, rec); keyblock = xfs_btree_get_block(cur, 1, &bp); keyp = xfs_btree_key_addr(cur, cur->bc_levels[1].ptr, keyblock); - if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0) + if (xfs_btree_keycmp_lt(cur, &key, keyp)) xchk_btree_set_corrupt(bs->sc, cur, 1); if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) return; - /* Is this no larger than the parent high key? */ + /* Is high_key(rec) no larger than the parent high key? */ cur->bc_ops->init_high_key_from_rec(&hkey, rec); keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[1].ptr, keyblock); - if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0) + if (xfs_btree_keycmp_lt(cur, keyp, &hkey)) xchk_btree_set_corrupt(bs->sc, cur, 1); } @@ -209,20 +209,20 @@ xchk_btree_key( if (level + 1 >= cur->bc_nlevels) return; - /* Is this at least as large as the parent low key? */ + /* Is this block's low key at least as large as the parent low key? */ keyblock = xfs_btree_get_block(cur, level + 1, &bp); keyp = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, keyblock); - if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0) + if (xfs_btree_keycmp_lt(cur, key, keyp)) xchk_btree_set_corrupt(bs->sc, cur, level); if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) return; - /* Is this no larger than the parent high key? */ + /* Is this block's high key no larger than the parent high key? */ key = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr, block); keyp = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr, keyblock); - if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0) + if (xfs_btree_keycmp_lt(cur, keyp, key)) xchk_btree_set_corrupt(bs->sc, cur, level); } @@ -557,7 +557,7 @@ xchk_btree_block_check_keys( parent_block = xfs_btree_get_block(cur, level + 1, &bp); parent_low_key = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, parent_block); - if (cur->bc_ops->diff_two_keys(cur, &block_key, parent_low_key)) { + if (xfs_btree_keycmp_ne(cur, &block_key, parent_low_key)) { xchk_btree_set_corrupt(bs->sc, bs->cur, level); return; } @@ -569,7 +569,7 @@ xchk_btree_block_check_keys( parent_high_key = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr, parent_block); block_high_key = xfs_btree_high_key_from_key(cur, &block_key); - if (cur->bc_ops->diff_two_keys(cur, block_high_key, parent_high_key)) + if (xfs_btree_keycmp_ne(cur, block_high_key, parent_high_key)) xchk_btree_set_corrupt(bs->sc, bs->cur, level); } @@ -661,7 +661,7 @@ xchk_btree_block_keys( parent_keys = xfs_btree_key_addr(cur, cur->bc_levels[level + 1].ptr, parent_block); - if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0) + if (xfs_btree_keycmp_ne(cur, &block_keys, parent_keys)) xchk_btree_set_corrupt(bs->sc, cur, 1); if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING)) @@ -672,7 +672,7 @@ xchk_btree_block_keys( high_pk = xfs_btree_high_key_addr(cur, cur->bc_levels[level + 1].ptr, parent_block); - if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0) + if (xfs_btree_keycmp_ne(cur, high_bk, high_pk)) xchk_btree_set_corrupt(bs->sc, cur, 1); } -- GitLab From 6abc7aef85b1f42cb39a3149f4ab64ca255e41e6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:10 -0700 Subject: [PATCH 2578/5631] xfs: replace xfs_btree_has_record with a general keyspace scanner The current implementation of xfs_btree_has_record returns true if it finds /any/ record within the given range. Unfortunately, that's not sufficient for scrub. We want to be able to tell if a range of keyspace for a btree is devoid of records, is totally mapped to records, or is somewhere in between. By forcing this to be a boolean, we conflated sparseness and fullness, which caused scrub to return incorrect results. Fix the API so that we can tell the caller which of those three is the current state. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 11 +-- fs/xfs/libxfs/xfs_alloc.h | 4 +- fs/xfs/libxfs/xfs_alloc_btree.c | 12 ++++ fs/xfs/libxfs/xfs_bmap_btree.c | 11 +++ fs/xfs/libxfs/xfs_btree.c | 108 +++++++++++++++++++++++++---- fs/xfs/libxfs/xfs_btree.h | 44 +++++++++++- fs/xfs/libxfs/xfs_ialloc_btree.c | 12 ++++ fs/xfs/libxfs/xfs_refcount.c | 11 +-- fs/xfs/libxfs/xfs_refcount.h | 4 +- fs/xfs/libxfs/xfs_refcount_btree.c | 11 +++ fs/xfs/libxfs/xfs_rmap.c | 12 ++-- fs/xfs/libxfs/xfs_rmap.h | 4 +- fs/xfs/libxfs/xfs_rmap_btree.c | 16 +++++ fs/xfs/libxfs/xfs_types.h | 12 ++++ fs/xfs/scrub/alloc.c | 6 +- fs/xfs/scrub/refcount.c | 8 +-- fs/xfs/scrub/rmap.c | 6 +- 17 files changed, 249 insertions(+), 43 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 23f0acfc2a64..34c8501d86d0 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -3745,13 +3745,16 @@ xfs_alloc_query_all( return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query); } -/* Is there a record covering a given extent? */ +/* + * Scan part of the keyspace of the free space and tell us if the area has no + * records, is fully mapped by records, or is partially filled. + */ int -xfs_alloc_has_record( +xfs_alloc_has_records( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; @@ -3761,7 +3764,7 @@ xfs_alloc_has_record( memset(&high, 0xFF, sizeof(high)); high.a.ar_startblock = bno + len - 1; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, outcome); } /* diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 56bd05900b35..5dbb25546d0b 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -213,8 +213,8 @@ int xfs_alloc_query_range(struct xfs_btree_cur *cur, int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn, void *priv); -int xfs_alloc_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, - xfs_extlen_t len, bool *exist); +int xfs_alloc_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, + xfs_extlen_t len, enum xbtree_recpacking *outcome); typedef int (*xfs_agfl_walk_fn)(struct xfs_mount *mp, xfs_agblock_t bno, void *priv); diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 8e8416c14cec..be80c57aeddc 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -423,6 +423,16 @@ xfs_cntbt_recs_inorder( be32_to_cpu(r2->alloc.ar_startblock)); } +STATIC enum xbtree_key_contig +xfs_allocbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return xbtree_key_contig(be32_to_cpu(key1->alloc.ar_startblock), + be32_to_cpu(key2->alloc.ar_startblock)); +} + static const struct xfs_btree_ops xfs_bnobt_ops = { .rec_len = sizeof(xfs_alloc_rec_t), .key_len = sizeof(xfs_alloc_key_t), @@ -443,6 +453,7 @@ static const struct xfs_btree_ops xfs_bnobt_ops = { .diff_two_keys = xfs_bnobt_diff_two_keys, .keys_inorder = xfs_bnobt_keys_inorder, .recs_inorder = xfs_bnobt_recs_inorder, + .keys_contiguous = xfs_allocbt_keys_contiguous, }; static const struct xfs_btree_ops xfs_cntbt_ops = { @@ -465,6 +476,7 @@ static const struct xfs_btree_ops xfs_cntbt_ops = { .diff_two_keys = xfs_cntbt_diff_two_keys, .keys_inorder = xfs_cntbt_keys_inorder, .recs_inorder = xfs_cntbt_recs_inorder, + .keys_contiguous = NULL, /* not needed right now */ }; /* Allocate most of a new allocation btree cursor. */ diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index b8ad95050c9b..3edf314a55e2 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -500,6 +500,16 @@ xfs_bmbt_recs_inorder( xfs_bmbt_disk_get_startoff(&r2->bmbt); } +STATIC enum xbtree_key_contig +xfs_bmbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return xbtree_key_contig(be64_to_cpu(key1->bmbt.br_startoff), + be64_to_cpu(key2->bmbt.br_startoff)); +} + static const struct xfs_btree_ops xfs_bmbt_ops = { .rec_len = sizeof(xfs_bmbt_rec_t), .key_len = sizeof(xfs_bmbt_key_t), @@ -520,6 +530,7 @@ static const struct xfs_btree_ops xfs_bmbt_ops = { .buf_ops = &xfs_bmbt_buf_ops, .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, + .keys_contiguous = xfs_bmbt_keys_contiguous, }; /* diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 92c610850fac..afbd3bcdf567 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -5025,34 +5025,116 @@ xfs_btree_diff_two_ptrs( return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s); } -/* If there's an extent, we're done. */ +struct xfs_btree_has_records { + /* Keys for the start and end of the range we want to know about. */ + union xfs_btree_key start_key; + union xfs_btree_key end_key; + + /* Highest record key we've seen so far. */ + union xfs_btree_key high_key; + + enum xbtree_recpacking outcome; +}; + STATIC int -xfs_btree_has_record_helper( +xfs_btree_has_records_helper( struct xfs_btree_cur *cur, const union xfs_btree_rec *rec, void *priv) { - return -ECANCELED; + union xfs_btree_key rec_key; + union xfs_btree_key rec_high_key; + struct xfs_btree_has_records *info = priv; + enum xbtree_key_contig key_contig; + + cur->bc_ops->init_key_from_rec(&rec_key, rec); + + if (info->outcome == XBTREE_RECPACKING_EMPTY) { + info->outcome = XBTREE_RECPACKING_SPARSE; + + /* + * If the first record we find does not overlap the start key, + * then there is a hole at the start of the search range. + * Classify this as sparse and stop immediately. + */ + if (xfs_btree_keycmp_lt(cur, &info->start_key, &rec_key)) + return -ECANCELED; + } else { + /* + * If a subsequent record does not overlap with the any record + * we've seen so far, there is a hole in the middle of the + * search range. Classify this as sparse and stop. + * If the keys overlap and this btree does not allow overlap, + * signal corruption. + */ + key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key, + &rec_key); + if (key_contig == XBTREE_KEY_OVERLAP && + !(cur->bc_flags & XFS_BTREE_OVERLAPPING)) + return -EFSCORRUPTED; + if (key_contig == XBTREE_KEY_GAP) + return -ECANCELED; + } + + /* + * If high_key(rec) is larger than any other high key we've seen, + * remember it for later. + */ + cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec); + if (xfs_btree_keycmp_gt(cur, &rec_high_key, &info->high_key)) + info->high_key = rec_high_key; /* struct copy */ + + return 0; } -/* Is there a record covering a given range of keys? */ +/* + * Scan part of the keyspace of a btree and tell us if that keyspace does not + * map to any records; is fully mapped to records; or is partially mapped to + * records. This is the btree record equivalent to determining if a file is + * sparse. + */ int -xfs_btree_has_record( +xfs_btree_has_records( struct xfs_btree_cur *cur, const union xfs_btree_irec *low, const union xfs_btree_irec *high, - bool *exists) + enum xbtree_recpacking *outcome) { + struct xfs_btree_has_records info = { + .outcome = XBTREE_RECPACKING_EMPTY, + }; int error; - error = xfs_btree_query_range(cur, low, high, - &xfs_btree_has_record_helper, NULL); - if (error == -ECANCELED) { - *exists = true; - return 0; + /* Not all btrees support this operation. */ + if (!cur->bc_ops->keys_contiguous) { + ASSERT(0); + return -EOPNOTSUPP; } - *exists = false; - return error; + + xfs_btree_key_from_irec(cur, &info.start_key, low); + xfs_btree_key_from_irec(cur, &info.end_key, high); + + error = xfs_btree_query_range(cur, low, high, + xfs_btree_has_records_helper, &info); + if (error == -ECANCELED) + goto out; + if (error) + return error; + + if (info.outcome == XBTREE_RECPACKING_EMPTY) + goto out; + + /* + * If the largest high_key(rec) we saw during the walk is greater than + * the end of the search range, classify this as full. Otherwise, + * there is a hole at the end of the search range. + */ + if (xfs_btree_keycmp_ge(cur, &info.high_key, &info.end_key)) + info.outcome = XBTREE_RECPACKING_FULL; + +out: + *outcome = info.outcome; + return 0; } /* Are there more records in this btree? */ diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index f5aa4b893ee7..66431f351bb2 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -90,6 +90,27 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); #define XFS_BTREE_STATS_ADD(cur, stat, val) \ XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val) +enum xbtree_key_contig { + XBTREE_KEY_GAP = 0, + XBTREE_KEY_CONTIGUOUS, + XBTREE_KEY_OVERLAP, +}; + +/* + * Decide if these two numeric btree key fields are contiguous, overlapping, + * or if there's a gap between them. @x should be the field from the high + * key and @y should be the field from the low key. + */ +static inline enum xbtree_key_contig xbtree_key_contig(uint64_t x, uint64_t y) +{ + x++; + if (x < y) + return XBTREE_KEY_GAP; + if (x == y) + return XBTREE_KEY_CONTIGUOUS; + return XBTREE_KEY_OVERLAP; +} + struct xfs_btree_ops { /* size of the key and record structures */ size_t key_len; @@ -157,6 +178,19 @@ struct xfs_btree_ops { int (*recs_inorder)(struct xfs_btree_cur *cur, const union xfs_btree_rec *r1, const union xfs_btree_rec *r2); + + /* + * Are these two btree keys immediately adjacent? + * + * Given two btree keys @key1 and @key2, decide if it is impossible for + * there to be a third btree key K satisfying the relationship + * @key1 < K < @key2. To determine if two btree records are + * immediately adjacent, @key1 should be the high key of the first + * record and @key2 should be the low key of the second record. + */ + enum xbtree_key_contig (*keys_contiguous)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2); }; /* @@ -540,9 +574,15 @@ void xfs_btree_get_keys(struct xfs_btree_cur *cur, struct xfs_btree_block *block, union xfs_btree_key *key); union xfs_btree_key *xfs_btree_high_key_from_key(struct xfs_btree_cur *cur, union xfs_btree_key *key); -int xfs_btree_has_record(struct xfs_btree_cur *cur, +typedef bool (*xfs_btree_key_gap_fn)(struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2); + +int xfs_btree_has_records(struct xfs_btree_cur *cur, const union xfs_btree_irec *low, - const union xfs_btree_irec *high, bool *exists); + const union xfs_btree_irec *high, + enum xbtree_recpacking *outcome); + bool xfs_btree_has_more_records(struct xfs_btree_cur *cur); struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur); diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index f900c056b82c..dd1fad8c3304 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -383,6 +383,16 @@ xfs_inobt_recs_inorder( be32_to_cpu(r2->inobt.ir_startino); } +STATIC enum xbtree_key_contig +xfs_inobt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return xbtree_key_contig(be32_to_cpu(key1->inobt.ir_startino), + be32_to_cpu(key2->inobt.ir_startino)); +} + static const struct xfs_btree_ops xfs_inobt_ops = { .rec_len = sizeof(xfs_inobt_rec_t), .key_len = sizeof(xfs_inobt_key_t), @@ -402,6 +412,7 @@ static const struct xfs_btree_ops xfs_inobt_ops = { .diff_two_keys = xfs_inobt_diff_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, + .keys_contiguous = xfs_inobt_keys_contiguous, }; static const struct xfs_btree_ops xfs_finobt_ops = { @@ -423,6 +434,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = { .diff_two_keys = xfs_inobt_diff_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, + .keys_contiguous = xfs_inobt_keys_contiguous, }; /* diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 335f84bef81c..94377b59ba44 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1998,14 +1998,17 @@ xfs_refcount_recover_cow_leftovers( return error; } -/* Is there a record covering a given extent? */ +/* + * Scan part of the keyspace of the refcount records and tell us if the area + * has no records, is fully mapped by records, or is partially filled. + */ int -xfs_refcount_has_record( +xfs_refcount_has_records( struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; @@ -2016,7 +2019,7 @@ xfs_refcount_has_record( high.rc.rc_startblock = bno + len - 1; low.rc.rc_domain = high.rc.rc_domain = domain; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, outcome); } int __init diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index fc0b58d4c379..783cd89ca195 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -111,9 +111,9 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, */ #define XFS_REFCOUNT_ITEM_OVERHEAD 32 -extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, +extern int xfs_refcount_has_records(struct xfs_btree_cur *cur, enum xfs_refc_domain domain, xfs_agblock_t bno, - xfs_extlen_t len, bool *exists); + xfs_extlen_t len, enum xbtree_recpacking *outcome); union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 03d2b01487a1..1628eecb53fd 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -300,6 +300,16 @@ xfs_refcountbt_recs_inorder( be32_to_cpu(r2->refc.rc_startblock); } +STATIC enum xbtree_key_contig +xfs_refcountbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), + be32_to_cpu(key2->refc.rc_startblock)); +} + static const struct xfs_btree_ops xfs_refcountbt_ops = { .rec_len = sizeof(struct xfs_refcount_rec), .key_len = sizeof(struct xfs_refcount_key), @@ -319,6 +329,7 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = { .diff_two_keys = xfs_refcountbt_diff_two_keys, .keys_inorder = xfs_refcountbt_keys_inorder, .recs_inorder = xfs_refcountbt_recs_inorder, + .keys_contiguous = xfs_refcountbt_keys_contiguous, }; /* diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index da008d317f83..e616b964f11c 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2709,13 +2709,17 @@ xfs_rmap_compare( return 0; } -/* Is there a record covering a given extent? */ +/* + * Scan the physical storage part of the keyspace of the reverse mapping index + * and tell us if the area has no records, is fully mapped by records, or is + * partially filled. + */ int -xfs_rmap_has_record( +xfs_rmap_has_records( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { union xfs_btree_irec low; union xfs_btree_irec high; @@ -2725,7 +2729,7 @@ xfs_rmap_has_record( memset(&high, 0xFF, sizeof(high)); high.r.rm_startblock = bno + len - 1; - return xfs_btree_has_record(cur, &low, &high, exists); + return xfs_btree_has_records(cur, &low, &high, outcome); } /* diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 7fb298bcc15f..4cbe50cf522e 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -198,8 +198,8 @@ xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec, xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur, const struct xfs_rmap_irec *irec); -int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno, - xfs_extlen_t len, bool *exists); +int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, + xfs_extlen_t len, enum xbtree_recpacking *outcome); int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, bool *has_rmap); diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 84e2b692f034..66beb87caf1a 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -444,6 +444,21 @@ xfs_rmapbt_recs_inorder( return 0; } +STATIC enum xbtree_key_contig +xfs_rmapbt_keys_contiguous( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2) +{ + /* + * We only support checking contiguity of the physical space component. + * If any callers ever need more specificity than that, they'll have to + * implement it here. + */ + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), + be32_to_cpu(key2->rmap.rm_startblock)); +} + static const struct xfs_btree_ops xfs_rmapbt_ops = { .rec_len = sizeof(struct xfs_rmap_rec), .key_len = 2 * sizeof(struct xfs_rmap_key), @@ -463,6 +478,7 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = { .diff_two_keys = xfs_rmapbt_diff_two_keys, .keys_inorder = xfs_rmapbt_keys_inorder, .recs_inorder = xfs_rmapbt_recs_inorder, + .keys_contiguous = xfs_rmapbt_keys_contiguous, }; static struct xfs_btree_cur * diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 5ebdda7e1078..851220021484 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -204,6 +204,18 @@ enum xfs_ag_resv_type { XFS_AG_RESV_RMAPBT, }; +/* Results of scanning a btree keyspace to check occupancy. */ +enum xbtree_recpacking { + /* None of the keyspace maps to records. */ + XBTREE_RECPACKING_EMPTY = 0, + + /* Some, but not all, of the keyspace maps to records. */ + XBTREE_RECPACKING_SPARSE, + + /* The entire keyspace maps to records. */ + XBTREE_RECPACKING_FULL, +}; + /* * Type verifier functions */ diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 53de04c6027c..5920fe051543 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -144,15 +144,15 @@ xchk_xref_is_used_space( xfs_agblock_t agbno, xfs_extlen_t len) { - bool is_freesp; + enum xbtree_recpacking outcome; int error; if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp); + error = xfs_alloc_has_records(sc->sa.bno_cur, agbno, len, &outcome); if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur)) return; - if (is_freesp) + if (outcome != XBTREE_RECPACKING_EMPTY) xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0); } diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 4d77049dfce2..ed47c570c658 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -457,16 +457,16 @@ xchk_xref_is_not_shared( xfs_agblock_t agbno, xfs_extlen_t len) { - bool shared; + enum xbtree_recpacking outcome; int error; if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED, - agbno, len, &shared); + error = xfs_refcount_has_records(sc->sa.refc_cur, + XFS_REFC_DOMAIN_SHARED, agbno, len, &outcome); if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) return; - if (shared) + if (outcome != XBTREE_RECPACKING_EMPTY) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); } diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 8e78e1bc9eef..2f9e4f77db6b 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -219,15 +219,15 @@ xchk_xref_has_no_owner( xfs_agblock_t bno, xfs_extlen_t len) { - bool has_rmap; + enum xbtree_recpacking outcome; int error; if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap); + error = xfs_rmap_has_records(sc->sa.rmap_cur, bno, len, &outcome); if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) return; - if (has_rmap) + if (outcome != XBTREE_RECPACKING_EMPTY) xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); } -- GitLab From 4a200a0978288f919aba3f015f374f6ed279e658 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:11 -0700 Subject: [PATCH 2579/5631] xfs: implement masked btree key comparisons for _has_records scans For keyspace fullness scans, we want to be able to mask off the parts of the key that we don't care about. For most btree types we /do/ want the full keyspace, but for checking that a given space usage also has a full complement of rmapbt records (even if different/multiple owners) we need this masking so that we only track sparseness of rm_startblock, not the whole keyspace (which is extremely sparse). Augment the ->diff_two_keys and ->keys_contiguous helpers to take a third union xfs_btree_key argument, and wire up xfs_rmap_has_records to pass this through. This third "mask" argument should contain a nonzero value in each structure field that should be used in the key comparisons done during the scan. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_alloc.c | 2 +- fs/xfs/libxfs/xfs_alloc_btree.c | 18 ++++++++--- fs/xfs/libxfs/xfs_bmap_btree.c | 10 ++++-- fs/xfs/libxfs/xfs_btree.c | 24 +++++++++++--- fs/xfs/libxfs/xfs_btree.h | 50 ++++++++++++++++++++++++++---- fs/xfs/libxfs/xfs_ialloc_btree.c | 12 +++++-- fs/xfs/libxfs/xfs_refcount.c | 2 +- fs/xfs/libxfs/xfs_refcount_btree.c | 12 +++++-- fs/xfs/libxfs/xfs_rmap.c | 5 ++- fs/xfs/libxfs/xfs_rmap_btree.c | 47 +++++++++++++++++++--------- 10 files changed, 142 insertions(+), 40 deletions(-) diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 34c8501d86d0..fdfa08cbf4db 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -3764,7 +3764,7 @@ xfs_alloc_has_records( memset(&high, 0xFF, sizeof(high)); high.a.ar_startblock = bno + len - 1; - return xfs_btree_has_records(cur, &low, &high, outcome); + return xfs_btree_has_records(cur, &low, &high, NULL, outcome); } /* diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index be80c57aeddc..c65228efed4a 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -260,20 +260,27 @@ STATIC int64_t xfs_bnobt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->alloc.ar_startblock); + return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) - - be32_to_cpu(k2->alloc.ar_startblock); + be32_to_cpu(k2->alloc.ar_startblock); } STATIC int64_t xfs_cntbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { int64_t diff; + ASSERT(!mask || (mask->alloc.ar_blockcount && + mask->alloc.ar_startblock)); + diff = be32_to_cpu(k1->alloc.ar_blockcount) - be32_to_cpu(k2->alloc.ar_blockcount); if (diff) @@ -427,8 +434,11 @@ STATIC enum xbtree_key_contig xfs_allocbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2) + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->alloc.ar_startblock); + return xbtree_key_contig(be32_to_cpu(key1->alloc.ar_startblock), be32_to_cpu(key2->alloc.ar_startblock)); } diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 3edf314a55e2..1b40e5f8b1ec 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -382,11 +382,14 @@ STATIC int64_t xfs_bmbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { uint64_t a = be64_to_cpu(k1->bmbt.br_startoff); uint64_t b = be64_to_cpu(k2->bmbt.br_startoff); + ASSERT(!mask || mask->bmbt.br_startoff); + /* * Note: This routine previously casted a and b to int64 and subtracted * them to generate a result. This lead to problems if b was the @@ -504,8 +507,11 @@ STATIC enum xbtree_key_contig xfs_bmbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2) + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->bmbt.br_startoff); + return xbtree_key_contig(be64_to_cpu(key1->bmbt.br_startoff), be64_to_cpu(key2->bmbt.br_startoff)); } diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index afbd3bcdf567..6a6503ab0cd7 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -5030,6 +5030,9 @@ struct xfs_btree_has_records { union xfs_btree_key start_key; union xfs_btree_key end_key; + /* Mask for key comparisons, if desired. */ + const union xfs_btree_key *key_mask; + /* Highest record key we've seen so far. */ union xfs_btree_key high_key; @@ -5057,7 +5060,8 @@ xfs_btree_has_records_helper( * then there is a hole at the start of the search range. * Classify this as sparse and stop immediately. */ - if (xfs_btree_keycmp_lt(cur, &info->start_key, &rec_key)) + if (xfs_btree_masked_keycmp_lt(cur, &info->start_key, &rec_key, + info->key_mask)) return -ECANCELED; } else { /* @@ -5068,7 +5072,7 @@ xfs_btree_has_records_helper( * signal corruption. */ key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key, - &rec_key); + &rec_key, info->key_mask); if (key_contig == XBTREE_KEY_OVERLAP && !(cur->bc_flags & XFS_BTREE_OVERLAPPING)) return -EFSCORRUPTED; @@ -5081,7 +5085,8 @@ xfs_btree_has_records_helper( * remember it for later. */ cur->bc_ops->init_high_key_from_rec(&rec_high_key, rec); - if (xfs_btree_keycmp_gt(cur, &rec_high_key, &info->high_key)) + if (xfs_btree_masked_keycmp_gt(cur, &rec_high_key, &info->high_key, + info->key_mask)) info->high_key = rec_high_key; /* struct copy */ return 0; @@ -5092,16 +5097,26 @@ xfs_btree_has_records_helper( * map to any records; is fully mapped to records; or is partially mapped to * records. This is the btree record equivalent to determining if a file is * sparse. + * + * For most btree types, the record scan should use all available btree key + * fields to compare the keys encountered. These callers should pass NULL for + * @mask. However, some callers (e.g. scanning physical space in the rmapbt) + * want to ignore some part of the btree record keyspace when performing the + * comparison. These callers should pass in a union xfs_btree_key object with + * the fields that *should* be a part of the comparison set to any nonzero + * value, and the rest zeroed. */ int xfs_btree_has_records( struct xfs_btree_cur *cur, const union xfs_btree_irec *low, const union xfs_btree_irec *high, + const union xfs_btree_key *mask, enum xbtree_recpacking *outcome) { struct xfs_btree_has_records info = { .outcome = XBTREE_RECPACKING_EMPTY, + .key_mask = mask, }; int error; @@ -5129,7 +5144,8 @@ xfs_btree_has_records( * the end of the search range, classify this as full. Otherwise, * there is a hole at the end of the search range. */ - if (xfs_btree_keycmp_ge(cur, &info.high_key, &info.end_key)) + if (xfs_btree_masked_keycmp_ge(cur, &info.high_key, &info.end_key, + mask)) info.outcome = XBTREE_RECPACKING_FULL; out: diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 66431f351bb2..a2aa36b23e25 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -161,11 +161,14 @@ struct xfs_btree_ops { /* * Difference between key2 and key1 -- positive if key1 > key2, - * negative if key1 < key2, and zero if equal. + * negative if key1 < key2, and zero if equal. If the @mask parameter + * is non NULL, each key field to be used in the comparison must + * contain a nonzero value. */ int64_t (*diff_two_keys)(struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2); + const union xfs_btree_key *key2, + const union xfs_btree_key *mask); const struct xfs_buf_ops *buf_ops; @@ -187,10 +190,13 @@ struct xfs_btree_ops { * @key1 < K < @key2. To determine if two btree records are * immediately adjacent, @key1 should be the high key of the first * record and @key2 should be the low key of the second record. + * If the @mask parameter is non NULL, each key field to be used in the + * comparison must contain a nonzero value. */ enum xbtree_key_contig (*keys_contiguous)(struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2); + const union xfs_btree_key *key2, + const union xfs_btree_key *mask); }; /* @@ -581,6 +587,7 @@ typedef bool (*xfs_btree_key_gap_fn)(struct xfs_btree_cur *cur, int xfs_btree_has_records(struct xfs_btree_cur *cur, const union xfs_btree_irec *low, const union xfs_btree_irec *high, + const union xfs_btree_key *mask, enum xbtree_recpacking *outcome); bool xfs_btree_has_more_records(struct xfs_btree_cur *cur); @@ -593,7 +600,7 @@ xfs_btree_keycmp_lt( const union xfs_btree_key *key1, const union xfs_btree_key *key2) { - return cur->bc_ops->diff_two_keys(cur, key1, key2) < 0; + return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) < 0; } static inline bool @@ -602,7 +609,7 @@ xfs_btree_keycmp_gt( const union xfs_btree_key *key1, const union xfs_btree_key *key2) { - return cur->bc_ops->diff_two_keys(cur, key1, key2) > 0; + return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) > 0; } static inline bool @@ -611,7 +618,7 @@ xfs_btree_keycmp_eq( const union xfs_btree_key *key1, const union xfs_btree_key *key2) { - return cur->bc_ops->diff_two_keys(cur, key1, key2) == 0; + return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) == 0; } static inline bool @@ -641,6 +648,37 @@ xfs_btree_keycmp_ne( return !xfs_btree_keycmp_eq(cur, key1, key2); } +/* Masked key comparison helpers */ +static inline bool +xfs_btree_masked_keycmp_lt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) < 0; +} + +static inline bool +xfs_btree_masked_keycmp_gt( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) > 0; +} + +static inline bool +xfs_btree_masked_keycmp_ge( + struct xfs_btree_cur *cur, + const union xfs_btree_key *key1, + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) +{ + return !xfs_btree_masked_keycmp_lt(cur, key1, key2, mask); +} + /* Does this cursor point to the last block in the given level? */ static inline bool xfs_btree_islastblock( diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index dd1fad8c3304..5a945ae21b5d 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -269,10 +269,13 @@ STATIC int64_t xfs_inobt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->inobt.ir_startino); + return (int64_t)be32_to_cpu(k1->inobt.ir_startino) - - be32_to_cpu(k2->inobt.ir_startino); + be32_to_cpu(k2->inobt.ir_startino); } static xfs_failaddr_t @@ -387,8 +390,11 @@ STATIC enum xbtree_key_contig xfs_inobt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2) + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->inobt.ir_startino); + return xbtree_key_contig(be32_to_cpu(key1->inobt.ir_startino), be32_to_cpu(key2->inobt.ir_startino)); } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 94377b59ba44..c1c65774dcc2 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -2019,7 +2019,7 @@ xfs_refcount_has_records( high.rc.rc_startblock = bno + len - 1; low.rc.rc_domain = high.rc.rc_domain = domain; - return xfs_btree_has_records(cur, &low, &high, outcome); + return xfs_btree_has_records(cur, &low, &high, NULL, outcome); } int __init diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 1628eecb53fd..d4afc5f4e6a5 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -202,10 +202,13 @@ STATIC int64_t xfs_refcountbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->refc.rc_startblock); + return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - - be32_to_cpu(k2->refc.rc_startblock); + be32_to_cpu(k2->refc.rc_startblock); } STATIC xfs_failaddr_t @@ -304,8 +307,11 @@ STATIC enum xbtree_key_contig xfs_refcountbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2) + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->refc.rc_startblock); + return xbtree_key_contig(be32_to_cpu(key1->refc.rc_startblock), be32_to_cpu(key2->refc.rc_startblock)); } diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index e616b964f11c..308b81f321eb 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2721,6 +2721,9 @@ xfs_rmap_has_records( xfs_extlen_t len, enum xbtree_recpacking *outcome) { + union xfs_btree_key mask = { + .rmap.rm_startblock = cpu_to_be32(-1U), + }; union xfs_btree_irec low; union xfs_btree_irec high; @@ -2729,7 +2732,7 @@ xfs_rmap_has_records( memset(&high, 0xFF, sizeof(high)); high.r.rm_startblock = bno + len - 1; - return xfs_btree_has_records(cur, &low, &high, outcome); + return xfs_btree_has_records(cur, &low, &high, &mask, outcome); } /* diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 66beb87caf1a..6c81b20e97d2 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -273,31 +273,43 @@ STATIC int64_t xfs_rmapbt_diff_two_keys( struct xfs_btree_cur *cur, const union xfs_btree_key *k1, - const union xfs_btree_key *k2) + const union xfs_btree_key *k2, + const union xfs_btree_key *mask) { const struct xfs_rmap_key *kp1 = &k1->rmap; const struct xfs_rmap_key *kp2 = &k2->rmap; int64_t d; __u64 x, y; + /* Doesn't make sense to mask off the physical space part */ + ASSERT(!mask || mask->rmap.rm_startblock); + d = (int64_t)be32_to_cpu(kp1->rm_startblock) - - be32_to_cpu(kp2->rm_startblock); + be32_to_cpu(kp2->rm_startblock); if (d) return d; - x = be64_to_cpu(kp1->rm_owner); - y = be64_to_cpu(kp2->rm_owner); - if (x > y) - return 1; - else if (y > x) - return -1; + if (!mask || mask->rmap.rm_owner) { + x = be64_to_cpu(kp1->rm_owner); + y = be64_to_cpu(kp2->rm_owner); + if (x > y) + return 1; + else if (y > x) + return -1; + } + + if (!mask || mask->rmap.rm_offset) { + /* Doesn't make sense to allow offset but not owner */ + ASSERT(!mask || mask->rmap.rm_owner); + + x = offset_keymask(be64_to_cpu(kp1->rm_offset)); + y = offset_keymask(be64_to_cpu(kp2->rm_offset)); + if (x > y) + return 1; + else if (y > x) + return -1; + } - x = offset_keymask(be64_to_cpu(kp1->rm_offset)); - y = offset_keymask(be64_to_cpu(kp2->rm_offset)); - if (x > y) - return 1; - else if (y > x) - return -1; return 0; } @@ -448,13 +460,18 @@ STATIC enum xbtree_key_contig xfs_rmapbt_keys_contiguous( struct xfs_btree_cur *cur, const union xfs_btree_key *key1, - const union xfs_btree_key *key2) + const union xfs_btree_key *key2, + const union xfs_btree_key *mask) { + ASSERT(!mask || mask->rmap.rm_startblock); + /* * We only support checking contiguity of the physical space component. * If any callers ever need more specificity than that, they'll have to * implement it here. */ + ASSERT(!mask || (!mask->rmap.rm_owner && !mask->rmap.rm_offset)); + return xbtree_key_contig(be32_to_cpu(key1->rmap.rm_startblock), be32_to_cpu(key2->rmap.rm_startblock)); } -- GitLab From 7ad9ea6398feae3ae4ce79fe08457f93b79a9a43 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:12 -0700 Subject: [PATCH 2580/5631] xfs: check the reference counts of gaps in the refcount btree Gaps in the reference count btree are also significant -- for these regions, there must not be any overlapping reverse mappings. We don't currently check this, so make the refcount scrubber more complete. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Dave Chinner --- fs/xfs/scrub/refcount.c | 95 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 90 insertions(+), 5 deletions(-) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index ed47c570c658..771a591a4aeb 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -332,6 +332,64 @@ xchk_refcountbt_xref( xchk_refcountbt_xref_rmap(sc, irec); } +struct xchk_refcbt_records { + /* The next AG block where we aren't expecting shared extents. */ + xfs_agblock_t next_unshared_agbno; + + /* Number of CoW blocks we expect. */ + xfs_agblock_t cow_blocks; + + /* Was the last record a shared or CoW staging extent? */ + enum xfs_refc_domain prev_domain; +}; + +STATIC int +xchk_refcountbt_rmap_check_gap( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + xfs_agblock_t *next_bno = priv; + + if (*next_bno != NULLAGBLOCK && rec->rm_startblock < *next_bno) + return -ECANCELED; + + *next_bno = rec->rm_startblock + rec->rm_blockcount; + return 0; +} + +/* + * Make sure that a gap in the reference count records does not correspond to + * overlapping records (i.e. shared extents) in the reverse mappings. + */ +static inline void +xchk_refcountbt_xref_gaps( + struct xfs_scrub *sc, + struct xchk_refcbt_records *rrc, + xfs_agblock_t bno) +{ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + xfs_agblock_t next_bno = NULLAGBLOCK; + int error; + + if (bno <= rrc->next_unshared_agbno || !sc->sa.rmap_cur || + xchk_skip_xref(sc->sm)) + return; + + memset(&low, 0, sizeof(low)); + low.rm_startblock = rrc->next_unshared_agbno; + memset(&high, 0xFF, sizeof(high)); + high.rm_startblock = bno - 1; + + error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high, + xchk_refcountbt_rmap_check_gap, &next_bno); + if (error == -ECANCELED) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + else + xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur); +} + /* Scrub a refcountbt record. */ STATIC int xchk_refcountbt_rec( @@ -339,7 +397,7 @@ xchk_refcountbt_rec( const union xfs_btree_rec *rec) { struct xfs_refcount_irec irec; - xfs_agblock_t *cow_blocks = bs->private; + struct xchk_refcbt_records *rrc = bs->private; xfs_refcount_btrec_to_irec(rec, &irec); if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) { @@ -348,10 +406,27 @@ xchk_refcountbt_rec( } if (irec.rc_domain == XFS_REFC_DOMAIN_COW) - (*cow_blocks) += irec.rc_blockcount; + rrc->cow_blocks += irec.rc_blockcount; + + /* Shared records always come before CoW records. */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED && + rrc->prev_domain == XFS_REFC_DOMAIN_COW) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + rrc->prev_domain = irec.rc_domain; xchk_refcountbt_xref(bs->sc, &irec); + /* + * If this is a record for a shared extent, check that all blocks + * between the previous record and this one have at most one reverse + * mapping. + */ + if (irec.rc_domain == XFS_REFC_DOMAIN_SHARED) { + xchk_refcountbt_xref_gaps(bs->sc, rrc, irec.rc_startblock); + rrc->next_unshared_agbno = irec.rc_startblock + + irec.rc_blockcount; + } + return 0; } @@ -393,15 +468,25 @@ int xchk_refcountbt( struct xfs_scrub *sc) { - xfs_agblock_t cow_blocks = 0; + struct xchk_refcbt_records rrc = { + .cow_blocks = 0, + .next_unshared_agbno = 0, + .prev_domain = XFS_REFC_DOMAIN_SHARED, + }; int error; error = xchk_btree(sc, sc->sa.refc_cur, xchk_refcountbt_rec, - &XFS_RMAP_OINFO_REFC, &cow_blocks); + &XFS_RMAP_OINFO_REFC, &rrc); if (error) return error; - xchk_refcount_xref_rmap(sc, cow_blocks); + /* + * Check that all blocks between the last refcount > 1 record and the + * end of the AG have at most one reverse mapping. + */ + xchk_refcountbt_xref_gaps(sc, &rrc, sc->mp->m_sb.sb_agblocks); + + xchk_refcount_xref_rmap(sc, rrc.cow_blocks); return 0; } -- GitLab From 7ac14fa2bd22e99a06ae16382b394f697cfe2b8a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:12 -0700 Subject: [PATCH 2581/5631] xfs: ensure that all metadata and data blocks are not cow staging extents Make sure that all filesystem metadata blocks and file data blocks are not also marked as CoW staging extents. The extra checking added here was inspired by an actual VM host filesystem corruption incident due to bugs in the CoW handling of 4.x kernels. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Reviewed-by: Dave Chinner --- fs/xfs/scrub/agheader.c | 5 +++++ fs/xfs/scrub/alloc.c | 1 + fs/xfs/scrub/bmap.c | 11 ++++++++--- fs/xfs/scrub/ialloc.c | 2 +- fs/xfs/scrub/inode.c | 1 + fs/xfs/scrub/refcount.c | 21 +++++++++++++++++++++ fs/xfs/scrub/scrub.h | 2 ++ 7 files changed, 39 insertions(+), 4 deletions(-) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 87cb13a6e84a..1a84153afa91 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -53,6 +53,7 @@ xchk_superblock_xref( xchk_xref_is_not_inode_chunk(sc, agbno, 1); xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); /* scrub teardown will take care of sc->sa for us */ } @@ -517,6 +518,7 @@ xchk_agf_xref( xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_agf_xref_btreeblks(sc); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); xchk_agf_xref_refcblks(sc); /* scrub teardown will take care of sc->sa for us */ @@ -644,6 +646,7 @@ xchk_agfl_block_xref( xchk_xref_is_not_inode_chunk(sc, agbno, 1); xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_AG); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); } /* Scrub an AGFL block. */ @@ -700,6 +703,7 @@ xchk_agfl_xref( xchk_xref_is_not_inode_chunk(sc, agbno, 1); xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); /* * Scrub teardown will take care of sc->sa for us. Leave sc->sa @@ -855,6 +859,7 @@ xchk_agi_xref( xchk_agi_xref_icounts(sc); xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); xchk_agi_xref_fiblocks(sc); /* scrub teardown will take care of sc->sa for us */ diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 5920fe051543..12dd55ac2a4f 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -90,6 +90,7 @@ xchk_allocbt_xref( xchk_xref_is_not_inode_chunk(sc, agbno, len); xchk_xref_has_no_owner(sc, agbno, len); xchk_xref_is_not_shared(sc, agbno, len); + xchk_xref_is_not_cow_staging(sc, agbno, len); } /* Scrub a bnobt/cntbt record. */ diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 6188eba672e5..be2c4da2808b 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -328,12 +328,17 @@ xchk_bmap_iextent_xref( xchk_bmap_xref_rmap(info, irec, agbno); switch (info->whichfork) { case XFS_DATA_FORK: - if (xfs_is_reflink_inode(info->sc->ip)) - break; - fallthrough; + if (!xfs_is_reflink_inode(info->sc->ip)) + xchk_xref_is_not_shared(info->sc, agbno, + irec->br_blockcount); + xchk_xref_is_not_cow_staging(info->sc, agbno, + irec->br_blockcount); + break; case XFS_ATTR_FORK: xchk_xref_is_not_shared(info->sc, agbno, irec->br_blockcount); + xchk_xref_is_not_cow_staging(info->sc, agbno, + irec->br_blockcount); break; case XFS_COW_FORK: xchk_xref_is_cow_staging(info->sc, agbno, diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index ca5a7e0f5451..6d08613db32f 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -115,7 +115,7 @@ xchk_iallocbt_chunk( xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len); - + xchk_xref_is_not_cow_staging(bs->sc, bno, len); return true; } diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index bbf9432c02c2..50ebd72f6d95 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -558,6 +558,7 @@ xchk_inode_xref( xchk_inode_xref_finobt(sc, ino); xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_INODES); xchk_xref_is_not_shared(sc, agbno, 1); + xchk_xref_is_not_cow_staging(sc, agbno, 1); xchk_inode_xref_bmap(sc, dip); out_free: diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 771a591a4aeb..db9e46a4f8d4 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -555,3 +555,24 @@ xchk_xref_is_not_shared( if (outcome != XBTREE_RECPACKING_EMPTY) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); } + +/* xref check that the extent is not being used for CoW staging. */ +void +xchk_xref_is_not_cow_staging( + struct xfs_scrub *sc, + xfs_agblock_t agbno, + xfs_extlen_t len) +{ + enum xbtree_recpacking outcome; + int error; + + if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_refcount_has_records(sc->sa.refc_cur, XFS_REFC_DOMAIN_COW, + agbno, len, &outcome); + if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) + return; + if (outcome != XBTREE_RECPACKING_EMPTY) + xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); +} diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index d85c3b883b4c..b6f452eb9645 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -172,6 +172,8 @@ void xchk_xref_is_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno, xfs_extlen_t len); void xchk_xref_is_not_shared(struct xfs_scrub *sc, xfs_agblock_t bno, xfs_extlen_t len); +void xchk_xref_is_not_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno, + xfs_extlen_t len); #ifdef CONFIG_XFS_RT void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno, xfs_extlen_t len); -- GitLab From cc1207662d1a08e253520654e956f5e699826caa Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:13 -0700 Subject: [PATCH 2582/5631] xfs: remove pointless shadow variable from xfs_difree_inobt In xfs_difree_inobt, the pag passed in was previously used to look up the AGI buffer. There's no need to extract it again, so remove the shadow variable and shut up -Wshadow. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ialloc.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 0d2980accd3c..be952bd37a61 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1978,8 +1978,6 @@ xfs_difree_inobt( */ if (!xfs_has_ikeep(mp) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { - struct xfs_perag *pag = agbp->b_pag; - xic->deleted = true; xic->first_ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, rec.ir_startino); -- GitLab From c01868b60e8c19888572f90fd3426c0652c0e2a9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:13 -0700 Subject: [PATCH 2583/5631] xfs: clean up broken eearly-exit code in the inode btree scrubber Corrupt inode chunks should cause us to exit early after setting the CORRUPT flag on the scrub state. While we're at it, collapse trivial helpers. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/ialloc.c | 42 +++++++++++++++++------------------------- 1 file changed, 17 insertions(+), 25 deletions(-) diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 6d08613db32f..3f0994166173 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -79,25 +79,7 @@ xchk_iallocbt_chunk_xref_other( xchk_btree_xref_set_corrupt(sc, *pcur, 0); } -/* Cross-reference with the other btrees. */ -STATIC void -xchk_iallocbt_chunk_xref( - struct xfs_scrub *sc, - struct xfs_inobt_rec_incore *irec, - xfs_agino_t agino, - xfs_agblock_t agbno, - xfs_extlen_t len) -{ - if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - return; - - xchk_xref_is_used_space(sc, agbno, len); - xchk_iallocbt_chunk_xref_other(sc, irec, agino); - xchk_xref_is_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES); - xchk_xref_is_not_shared(sc, agbno, len); -} - -/* Is this chunk worth checking? */ +/* Is this chunk worth checking and cross-referencing? */ STATIC bool xchk_iallocbt_chunk( struct xchk_btree *bs, @@ -105,17 +87,24 @@ xchk_iallocbt_chunk( xfs_agino_t agino, xfs_extlen_t len) { + struct xfs_scrub *sc = bs->sc; struct xfs_mount *mp = bs->cur->bc_mp; struct xfs_perag *pag = bs->cur->bc_ag.pag; - xfs_agblock_t bno; + xfs_agblock_t agbno; - bno = XFS_AGINO_TO_AGBNO(mp, agino); + agbno = XFS_AGINO_TO_AGBNO(mp, agino); - if (!xfs_verify_agbext(pag, bno, len)) + if (!xfs_verify_agbext(pag, agbno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len); - xchk_xref_is_not_cow_staging(bs->sc, bno, len); + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return false; + + xchk_xref_is_used_space(sc, agbno, len); + xchk_iallocbt_chunk_xref_other(sc, irec, agino); + xchk_xref_is_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES); + xchk_xref_is_not_shared(sc, agbno, len); + xchk_xref_is_not_cow_staging(sc, agbno, len); return true; } @@ -463,7 +452,7 @@ xchk_iallocbt_rec( if (holemask & 1) holecount += XFS_INODES_PER_HOLEMASK_BIT; else if (!xchk_iallocbt_chunk(bs, &irec, agino, len)) - break; + goto out; holemask >>= 1; agino += XFS_INODES_PER_HOLEMASK_BIT; } @@ -473,6 +462,9 @@ xchk_iallocbt_rec( xchk_btree_set_corrupt(bs->sc, bs->cur, 0); check_clusters: + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + goto out; + error = xchk_iallocbt_check_clusters(bs, &irec); if (error) goto out; -- GitLab From bc0f3b55467e1b5833bebae011a07e72a35afc2e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:14 -0700 Subject: [PATCH 2584/5631] xfs: directly cross-reference the inode btrees with each other Improve the cross-referencing of the two inode btrees by directly checking the free and hole state of each inode with the other btree. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/ialloc.c | 225 +++++++++++++++++++++++++++++++++++++----- 1 file changed, 198 insertions(+), 27 deletions(-) diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 3f0994166173..3a37c3dc0fae 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -51,32 +51,201 @@ struct xchk_iallocbt { }; /* - * If we're checking the finobt, cross-reference with the inobt. - * Otherwise we're checking the inobt; if there is an finobt, make sure - * we have a record or not depending on freecount. + * Does the finobt have a record for this inode with the same hole/free state? + * This is a bit complicated because of the following: + * + * - The finobt need not have a record if all inodes in the inobt record are + * allocated. + * - The finobt need not have a record if all inodes in the inobt record are + * free. + * - The finobt need not have a record if the inobt record says this is a hole. + * This likely doesn't happen in practice. */ -static inline void -xchk_iallocbt_chunk_xref_other( +STATIC int +xchk_inobt_xref_finobt( + struct xfs_scrub *sc, + struct xfs_inobt_rec_incore *irec, + xfs_agino_t agino, + bool free, + bool hole) +{ + struct xfs_inobt_rec_incore frec; + struct xfs_btree_cur *cur = sc->sa.fino_cur; + bool ffree, fhole; + unsigned int frec_idx, fhole_idx; + int has_record; + int error; + + ASSERT(cur->bc_btnum == XFS_BTNUM_FINO); + + error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has_record); + if (error) + return error; + if (!has_record) + goto no_record; + + error = xfs_inobt_get_rec(cur, &frec, &has_record); + if (!has_record) + return -EFSCORRUPTED; + + if (frec.ir_startino + XFS_INODES_PER_CHUNK <= agino) + goto no_record; + + /* There's a finobt record; free and hole status must match. */ + frec_idx = agino - frec.ir_startino; + ffree = frec.ir_free & (1ULL << frec_idx); + fhole_idx = frec_idx / XFS_INODES_PER_HOLEMASK_BIT; + fhole = frec.ir_holemask & (1U << fhole_idx); + + if (ffree != free) + xchk_btree_xref_set_corrupt(sc, cur, 0); + if (fhole != hole) + xchk_btree_xref_set_corrupt(sc, cur, 0); + return 0; + +no_record: + /* inobt record is fully allocated */ + if (irec->ir_free == 0) + return 0; + + /* inobt record is totally unallocated */ + if (irec->ir_free == XFS_INOBT_ALL_FREE) + return 0; + + /* inobt record says this is a hole */ + if (hole) + return 0; + + /* finobt doesn't care about allocated inodes */ + if (!free) + return 0; + + xchk_btree_xref_set_corrupt(sc, cur, 0); + return 0; +} + +/* + * Make sure that each inode of this part of an inobt record has the same + * sparse and free status as the finobt. + */ +STATIC void +xchk_inobt_chunk_xref_finobt( struct xfs_scrub *sc, struct xfs_inobt_rec_incore *irec, - xfs_agino_t agino) + xfs_agino_t agino, + unsigned int nr_inodes) { - struct xfs_btree_cur **pcur; - bool has_irec; + xfs_agino_t i; + unsigned int rec_idx; int error; - if (sc->sm->sm_type == XFS_SCRUB_TYPE_FINOBT) - pcur = &sc->sa.ino_cur; - else - pcur = &sc->sa.fino_cur; - if (!(*pcur)) + ASSERT(sc->sm->sm_type == XFS_SCRUB_TYPE_INOBT); + + if (!sc->sa.fino_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_ialloc_has_inode_record(*pcur, agino, agino, &has_irec); - if (!xchk_should_check_xref(sc, &error, pcur)) + + for (i = agino, rec_idx = agino - irec->ir_startino; + i < agino + nr_inodes; + i++, rec_idx++) { + bool free, hole; + unsigned int hole_idx; + + free = irec->ir_free & (1ULL << rec_idx); + hole_idx = rec_idx / XFS_INODES_PER_HOLEMASK_BIT; + hole = irec->ir_holemask & (1U << hole_idx); + + error = xchk_inobt_xref_finobt(sc, irec, i, free, hole); + if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur)) + return; + } +} + +/* + * Does the inobt have a record for this inode with the same hole/free state? + * The inobt must always have a record if there's a finobt record. + */ +STATIC int +xchk_finobt_xref_inobt( + struct xfs_scrub *sc, + struct xfs_inobt_rec_incore *frec, + xfs_agino_t agino, + bool ffree, + bool fhole) +{ + struct xfs_inobt_rec_incore irec; + struct xfs_btree_cur *cur = sc->sa.ino_cur; + bool free, hole; + unsigned int rec_idx, hole_idx; + int has_record; + int error; + + ASSERT(cur->bc_btnum == XFS_BTNUM_INO); + + error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has_record); + if (error) + return error; + if (!has_record) + goto no_record; + + error = xfs_inobt_get_rec(cur, &irec, &has_record); + if (!has_record) + return -EFSCORRUPTED; + + if (irec.ir_startino + XFS_INODES_PER_CHUNK <= agino) + goto no_record; + + /* There's an inobt record; free and hole status must match. */ + rec_idx = agino - irec.ir_startino; + free = irec.ir_free & (1ULL << rec_idx); + hole_idx = rec_idx / XFS_INODES_PER_HOLEMASK_BIT; + hole = irec.ir_holemask & (1U << hole_idx); + + if (ffree != free) + xchk_btree_xref_set_corrupt(sc, cur, 0); + if (fhole != hole) + xchk_btree_xref_set_corrupt(sc, cur, 0); + return 0; + +no_record: + /* finobt should never have a record for which the inobt does not */ + xchk_btree_xref_set_corrupt(sc, cur, 0); + return 0; +} + +/* + * Make sure that each inode of this part of an finobt record has the same + * sparse and free status as the inobt. + */ +STATIC void +xchk_finobt_chunk_xref_inobt( + struct xfs_scrub *sc, + struct xfs_inobt_rec_incore *frec, + xfs_agino_t agino, + unsigned int nr_inodes) +{ + xfs_agino_t i; + unsigned int rec_idx; + int error; + + ASSERT(sc->sm->sm_type == XFS_SCRUB_TYPE_FINOBT); + + if (!sc->sa.ino_cur || xchk_skip_xref(sc->sm)) return; - if (((irec->ir_freecount > 0 && !has_irec) || - (irec->ir_freecount == 0 && has_irec))) - xchk_btree_xref_set_corrupt(sc, *pcur, 0); + + for (i = agino, rec_idx = agino - frec->ir_startino; + i < agino + nr_inodes; + i++, rec_idx++) { + bool ffree, fhole; + unsigned int hole_idx; + + ffree = frec->ir_free & (1ULL << rec_idx); + hole_idx = rec_idx / XFS_INODES_PER_HOLEMASK_BIT; + fhole = frec->ir_holemask & (1U << hole_idx); + + error = xchk_finobt_xref_inobt(sc, frec, i, ffree, fhole); + if (!xchk_should_check_xref(sc, &error, &sc->sa.ino_cur)) + return; + } } /* Is this chunk worth checking and cross-referencing? */ @@ -85,14 +254,16 @@ xchk_iallocbt_chunk( struct xchk_btree *bs, struct xfs_inobt_rec_incore *irec, xfs_agino_t agino, - xfs_extlen_t len) + unsigned int nr_inodes) { struct xfs_scrub *sc = bs->sc; struct xfs_mount *mp = bs->cur->bc_mp; struct xfs_perag *pag = bs->cur->bc_ag.pag; xfs_agblock_t agbno; + xfs_extlen_t len; agbno = XFS_AGINO_TO_AGBNO(mp, agino); + len = XFS_B_TO_FSB(mp, nr_inodes * mp->m_sb.sb_inodesize); if (!xfs_verify_agbext(pag, agbno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); @@ -101,7 +272,10 @@ xchk_iallocbt_chunk( return false; xchk_xref_is_used_space(sc, agbno, len); - xchk_iallocbt_chunk_xref_other(sc, irec, agino); + if (sc->sm->sm_type == XFS_SCRUB_TYPE_INOBT) + xchk_inobt_chunk_xref_finobt(sc, irec, agino, nr_inodes); + else + xchk_finobt_chunk_xref_inobt(sc, irec, agino, nr_inodes); xchk_xref_is_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES); xchk_xref_is_not_shared(sc, agbno, len); xchk_xref_is_not_cow_staging(sc, agbno, len); @@ -406,7 +580,6 @@ xchk_iallocbt_rec( struct xfs_inobt_rec_incore irec; uint64_t holes; xfs_agino_t agino; - xfs_extlen_t len; int holecount; int i; int error = 0; @@ -428,12 +601,11 @@ xchk_iallocbt_rec( /* Handle non-sparse inodes */ if (!xfs_inobt_issparse(irec.ir_holemask)) { - len = XFS_B_TO_FSB(mp, - XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize); if (irec.ir_count != XFS_INODES_PER_CHUNK) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (!xchk_iallocbt_chunk(bs, &irec, agino, len)) + if (!xchk_iallocbt_chunk(bs, &irec, agino, + XFS_INODES_PER_CHUNK)) goto out; goto check_clusters; } @@ -441,8 +613,6 @@ xchk_iallocbt_rec( /* Check each chunk of a sparse inode cluster. */ holemask = irec.ir_holemask; holecount = 0; - len = XFS_B_TO_FSB(mp, - XFS_INODES_PER_HOLEMASK_BIT * mp->m_sb.sb_inodesize); holes = ~xfs_inobt_irec_to_allocmask(&irec); if ((holes & irec.ir_free) != holes || irec.ir_freecount > irec.ir_count) @@ -451,7 +621,8 @@ xchk_iallocbt_rec( for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) { if (holemask & 1) holecount += XFS_INODES_PER_HOLEMASK_BIT; - else if (!xchk_iallocbt_chunk(bs, &irec, agino, len)) + else if (!xchk_iallocbt_chunk(bs, &irec, agino, + XFS_INODES_PER_HOLEMASK_BIT)) goto out; holemask >>= 1; agino += XFS_INODES_PER_HOLEMASK_BIT; -- GitLab From 69115f775f6e8e972a40aa6aa1523bcb0b252b1c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:15 -0700 Subject: [PATCH 2585/5631] xfs: teach scrub to check for sole ownership of metadata objects Strengthen online scrub's checking even further by enabling us to check that a range of blocks are owned solely by a given owner. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_rmap.c | 192 +++++++++++++++++++++++++++------------ fs/xfs/libxfs/xfs_rmap.h | 18 +++- fs/xfs/scrub/agheader.c | 10 +- fs/xfs/scrub/btree.c | 2 +- fs/xfs/scrub/ialloc.c | 4 +- fs/xfs/scrub/inode.c | 2 +- fs/xfs/scrub/rmap.c | 45 ++++----- fs/xfs/scrub/scrub.h | 2 +- 8 files changed, 182 insertions(+), 93 deletions(-) diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 308b81f321eb..f4dc23b3b837 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2735,65 +2735,141 @@ xfs_rmap_has_records( return xfs_btree_has_records(cur, &low, &high, &mask, outcome); } -/* - * Is there a record for this owner completely covering a given physical - * extent? If so, *has_rmap will be set to true. If there is no record - * or the record only covers part of the range, we set *has_rmap to false. - * This function doesn't perform range lookups or offset checks, so it is - * not suitable for checking data fork blocks. - */ -int -xfs_rmap_record_exists( - struct xfs_btree_cur *cur, +struct xfs_rmap_ownercount { + /* Owner that we're looking for. */ + struct xfs_rmap_irec good; + + /* rmap search keys */ + struct xfs_rmap_irec low; + struct xfs_rmap_irec high; + + struct xfs_rmap_matches *results; + + /* Stop early if we find a nonmatch? */ + bool stop_on_nonmatch; +}; + +/* Does this rmap represent space that can have multiple owners? */ +static inline bool +xfs_rmap_shareable( + struct xfs_mount *mp, + const struct xfs_rmap_irec *rmap) +{ + if (!xfs_has_reflink(mp)) + return false; + if (XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner)) + return false; + if (rmap->rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK)) + return false; + return true; +} + +static inline void +xfs_rmap_ownercount_init( + struct xfs_rmap_ownercount *roc, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap) + struct xfs_rmap_matches *results) { - uint64_t owner; - uint64_t offset; - unsigned int flags; - int has_record; - struct xfs_rmap_irec irec; - int error; + memset(roc, 0, sizeof(*roc)); + roc->results = results; + + roc->low.rm_startblock = bno; + memset(&roc->high, 0xFF, sizeof(roc->high)); + roc->high.rm_startblock = bno + len - 1; + + memset(results, 0, sizeof(*results)); + roc->good.rm_startblock = bno; + roc->good.rm_blockcount = len; + roc->good.rm_owner = oinfo->oi_owner; + roc->good.rm_offset = oinfo->oi_offset; + if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK) + roc->good.rm_flags |= XFS_RMAP_ATTR_FORK; + if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK) + roc->good.rm_flags |= XFS_RMAP_BMBT_BLOCK; +} - xfs_owner_info_unpack(oinfo, &owner, &offset, &flags); - ASSERT(XFS_RMAP_NON_INODE_OWNER(owner) || - (flags & XFS_RMAP_BMBT_BLOCK)); +/* Figure out if this is a match for the owner. */ +STATIC int +xfs_rmap_count_owners_helper( + struct xfs_btree_cur *cur, + const struct xfs_rmap_irec *rec, + void *priv) +{ + struct xfs_rmap_ownercount *roc = priv; + struct xfs_rmap_irec check = *rec; + unsigned int keyflags; + bool filedata; + int64_t delta; + + filedata = !XFS_RMAP_NON_INODE_OWNER(check.rm_owner) && + !(check.rm_flags & XFS_RMAP_BMBT_BLOCK); + + /* Trim the part of check that comes before the comparison range. */ + delta = (int64_t)roc->good.rm_startblock - check.rm_startblock; + if (delta > 0) { + check.rm_startblock += delta; + check.rm_blockcount -= delta; + if (filedata) + check.rm_offset += delta; + } - error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &irec, - &has_record); - if (error) - return error; - if (!has_record) { - *has_rmap = false; - return 0; + /* Trim the part of check that comes after the comparison range. */ + delta = (check.rm_startblock + check.rm_blockcount) - + (roc->good.rm_startblock + roc->good.rm_blockcount); + if (delta > 0) + check.rm_blockcount -= delta; + + /* Don't care about unwritten status for establishing ownership. */ + keyflags = check.rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK); + + if (check.rm_startblock == roc->good.rm_startblock && + check.rm_blockcount == roc->good.rm_blockcount && + check.rm_owner == roc->good.rm_owner && + check.rm_offset == roc->good.rm_offset && + keyflags == roc->good.rm_flags) { + roc->results->matches++; + } else { + roc->results->non_owner_matches++; + if (xfs_rmap_shareable(cur->bc_mp, &roc->good) ^ + xfs_rmap_shareable(cur->bc_mp, &check)) + roc->results->bad_non_owner_matches++; } - *has_rmap = (irec.rm_owner == owner && irec.rm_startblock <= bno && - irec.rm_startblock + irec.rm_blockcount >= bno + len); + if (roc->results->non_owner_matches && roc->stop_on_nonmatch) + return -ECANCELED; + return 0; } -struct xfs_rmap_key_state { - uint64_t owner; - uint64_t offset; - unsigned int flags; -}; - -/* For each rmap given, figure out if it doesn't match the key we want. */ -STATIC int -xfs_rmap_has_other_keys_helper( +/* Count the number of owners and non-owners of this range of blocks. */ +int +xfs_rmap_count_owners( struct xfs_btree_cur *cur, - const struct xfs_rmap_irec *rec, - void *priv) + xfs_agblock_t bno, + xfs_extlen_t len, + const struct xfs_owner_info *oinfo, + struct xfs_rmap_matches *results) { - struct xfs_rmap_key_state *rks = priv; + struct xfs_rmap_ownercount roc; + int error; - if (rks->owner == rec->rm_owner && rks->offset == rec->rm_offset && - ((rks->flags & rec->rm_flags) & XFS_RMAP_KEY_FLAGS) == rks->flags) - return 0; - return -ECANCELED; + xfs_rmap_ownercount_init(&roc, bno, len, oinfo, results); + error = xfs_rmap_query_range(cur, &roc.low, &roc.high, + xfs_rmap_count_owners_helper, &roc); + if (error) + return error; + + /* + * There can't be any non-owner rmaps that conflict with the given + * owner if we didn't find any rmaps matching the owner. + */ + if (!results->matches) + results->bad_non_owner_matches = 0; + + return 0; } /* @@ -2806,28 +2882,26 @@ xfs_rmap_has_other_keys( xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap) + bool *has_other) { - struct xfs_rmap_irec low = {0}; - struct xfs_rmap_irec high; - struct xfs_rmap_key_state rks; + struct xfs_rmap_matches res; + struct xfs_rmap_ownercount roc; int error; - xfs_owner_info_unpack(oinfo, &rks.owner, &rks.offset, &rks.flags); - *has_rmap = false; - - low.rm_startblock = bno; - memset(&high, 0xFF, sizeof(high)); - high.rm_startblock = bno + len - 1; + xfs_rmap_ownercount_init(&roc, bno, len, oinfo, &res); + roc.stop_on_nonmatch = true; - error = xfs_rmap_query_range(cur, &low, &high, - xfs_rmap_has_other_keys_helper, &rks); + error = xfs_rmap_query_range(cur, &roc.low, &roc.high, + xfs_rmap_count_owners_helper, &roc); if (error == -ECANCELED) { - *has_rmap = true; + *has_other = true; return 0; } + if (error) + return error; - return error; + *has_other = false; + return 0; } const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE = { diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 4cbe50cf522e..3c98d9d50afb 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -200,12 +200,24 @@ xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur, int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, enum xbtree_recpacking *outcome); -int xfs_rmap_record_exists(struct xfs_btree_cur *cur, xfs_agblock_t bno, + +struct xfs_rmap_matches { + /* Number of owner matches. */ + unsigned long long matches; + + /* Number of non-owner matches. */ + unsigned long long non_owner_matches; + + /* Number of non-owner matches that conflict with the owner matches. */ + unsigned long long bad_non_owner_matches; +}; + +int xfs_rmap_count_owners(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap); + struct xfs_rmap_matches *rmatch); int xfs_rmap_has_other_keys(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, const struct xfs_owner_info *oinfo, - bool *has_rmap); + bool *has_other); int xfs_rmap_map_raw(struct xfs_btree_cur *cur, struct xfs_rmap_irec *rmap); extern const struct xfs_owner_info XFS_RMAP_OINFO_SKIP_UPDATE; diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 1a84153afa91..6c6e5eba42c8 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -51,7 +51,7 @@ xchk_superblock_xref( xchk_xref_is_used_space(sc, agbno, 1); xchk_xref_is_not_inode_chunk(sc, agbno, 1); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); @@ -515,7 +515,7 @@ xchk_agf_xref( xchk_agf_xref_freeblks(sc); xchk_agf_xref_cntbt(sc); xchk_xref_is_not_inode_chunk(sc, agbno, 1); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_agf_xref_btreeblks(sc); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); @@ -644,7 +644,7 @@ xchk_agfl_block_xref( xchk_xref_is_used_space(sc, agbno, 1); xchk_xref_is_not_inode_chunk(sc, agbno, 1); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_AG); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_AG); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); } @@ -701,7 +701,7 @@ xchk_agfl_xref( xchk_xref_is_used_space(sc, agbno, 1); xchk_xref_is_not_inode_chunk(sc, agbno, 1); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); @@ -857,7 +857,7 @@ xchk_agi_xref( xchk_xref_is_used_space(sc, agbno, 1); xchk_xref_is_not_inode_chunk(sc, agbno, 1); xchk_agi_xref_icounts(sc); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_FS); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); xchk_agi_xref_fiblocks(sc); diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 1165dc05a179..1935b9ce1885 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -402,7 +402,7 @@ xchk_btree_check_block_owner( if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO) bs->cur = NULL; - xchk_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo); + xchk_xref_is_only_owned_by(bs->sc, agbno, 1, bs->oinfo); if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP) bs->cur = NULL; diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index fda96b536730..575f22a02ebe 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -276,7 +276,7 @@ xchk_iallocbt_chunk( xchk_inobt_chunk_xref_finobt(sc, irec, agino, nr_inodes); else xchk_finobt_chunk_xref_inobt(sc, irec, agino, nr_inodes); - xchk_xref_is_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES); + xchk_xref_is_only_owned_by(sc, agbno, len, &XFS_RMAP_OINFO_INODES); xchk_xref_is_not_shared(sc, agbno, len); xchk_xref_is_not_cow_staging(sc, agbno, len); return true; @@ -428,7 +428,7 @@ xchk_iallocbt_check_cluster( return 0; } - xchk_xref_is_owned_by(bs->sc, agbno, M_IGEO(mp)->blocks_per_cluster, + xchk_xref_is_only_owned_by(bs->sc, agbno, M_IGEO(mp)->blocks_per_cluster, &XFS_RMAP_OINFO_INODES); /* Grab the inode cluster buffer. */ diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 50ebd72f6d95..2db96c8a71dc 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -556,7 +556,7 @@ xchk_inode_xref( xchk_xref_is_used_space(sc, agbno, 1); xchk_inode_xref_finobt(sc, ino); - xchk_xref_is_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_INODES); + xchk_xref_is_only_owned_by(sc, agbno, 1, &XFS_RMAP_OINFO_INODES); xchk_xref_is_not_shared(sc, agbno, 1); xchk_xref_is_not_cow_staging(sc, agbno, 1); xchk_inode_xref_bmap(sc, dip); diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 2f9e4f77db6b..18b64287158e 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -167,38 +167,29 @@ xchk_rmapbt( &XFS_RMAP_OINFO_AG, NULL); } -/* xref check that the extent is owned by a given owner */ -static inline void -xchk_xref_check_owner( +/* xref check that the extent is owned only by a given owner */ +void +xchk_xref_is_only_owned_by( struct xfs_scrub *sc, xfs_agblock_t bno, xfs_extlen_t len, - const struct xfs_owner_info *oinfo, - bool should_have_rmap) + const struct xfs_owner_info *oinfo) { - bool has_rmap; + struct xfs_rmap_matches res; int error; if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo, - &has_rmap); + error = xfs_rmap_count_owners(sc->sa.rmap_cur, bno, len, oinfo, &res); if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) return; - if (has_rmap != should_have_rmap) + if (res.matches != 1) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + if (res.bad_non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + if (res.non_owner_matches) xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); -} - -/* xref check that the extent is owned by a given owner */ -void -xchk_xref_is_owned_by( - struct xfs_scrub *sc, - xfs_agblock_t bno, - xfs_extlen_t len, - const struct xfs_owner_info *oinfo) -{ - xchk_xref_check_owner(sc, bno, len, oinfo, true); } /* xref check that the extent is not owned by a given owner */ @@ -209,7 +200,19 @@ xchk_xref_is_not_owned_by( xfs_extlen_t len, const struct xfs_owner_info *oinfo) { - xchk_xref_check_owner(sc, bno, len, oinfo, false); + struct xfs_rmap_matches res; + int error; + + if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm)) + return; + + error = xfs_rmap_count_owners(sc->sa.rmap_cur, bno, len, oinfo, &res); + if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur)) + return; + if (res.matches != 0) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); + if (res.bad_non_owner_matches) + xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); } /* xref check that the extent has no reverse mapping at all */ diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index b6f452eb9645..c519927355fe 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -162,7 +162,7 @@ void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno, xfs_extlen_t len); void xchk_xref_is_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno, xfs_extlen_t len); -void xchk_xref_is_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno, +void xchk_xref_is_only_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo); void xchk_xref_is_not_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno, xfs_extlen_t len, const struct xfs_owner_info *oinfo); -- GitLab From efc0845f5d3e253f7f46a60b66a94c3164d76ee3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:15 -0700 Subject: [PATCH 2586/5631] xfs: convert xfs_ialloc_has_inodes_at_extent to return keyfill scan results Convert the xfs_ialloc_has_inodes_at_extent function to return keyfill scan results because for a given range of inode numbers, we might have no indexed inodes at all; the entire region might be allocated ondisk inodes; or there might be a mix of the two. Unfortunately, sparse inodes adds to the complexity, because each inode record can have holes, which means that we cannot use the generic btree _scan_keyfill function because we must look for holes in individual records to decide the result. On the plus side, online fsck can now detect sub-chunk discrepancies in the inobt. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_ialloc.c | 82 +++++++++++++++++++++++--------------- fs/xfs/libxfs/xfs_ialloc.h | 5 +-- fs/xfs/scrub/ialloc.c | 17 ++++---- 3 files changed, 62 insertions(+), 42 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index be952bd37a61..a16d5de16933 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -2641,44 +2641,50 @@ xfs_ialloc_read_agi( return 0; } -/* Is there an inode record covering a given range of inode numbers? */ -int -xfs_ialloc_has_inode_record( - struct xfs_btree_cur *cur, - xfs_agino_t low, - xfs_agino_t high, - bool *exists) +/* How many inodes are backed by inode clusters ondisk? */ +STATIC int +xfs_ialloc_count_ondisk( + struct xfs_btree_cur *cur, + xfs_agino_t low, + xfs_agino_t high, + unsigned int *allocated) { struct xfs_inobt_rec_incore irec; - xfs_agino_t agino; - uint16_t holemask; - int has_record; - int i; - int error; + unsigned int ret = 0; + int has_record; + int error; - *exists = false; error = xfs_inobt_lookup(cur, low, XFS_LOOKUP_LE, &has_record); - while (error == 0 && has_record) { + if (error) + return error; + + while (has_record) { + unsigned int i, hole_idx; + error = xfs_inobt_get_rec(cur, &irec, &has_record); - if (error || irec.ir_startino > high) + if (error) + return error; + if (irec.ir_startino > high) break; - agino = irec.ir_startino; - holemask = irec.ir_holemask; - for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; holemask >>= 1, - i++, agino += XFS_INODES_PER_HOLEMASK_BIT) { - if (holemask & 1) + for (i = 0; i < XFS_INODES_PER_CHUNK; i++) { + if (irec.ir_startino + i < low) continue; - if (agino + XFS_INODES_PER_HOLEMASK_BIT > low && - agino <= high) { - *exists = true; - return 0; - } + if (irec.ir_startino + i > high) + break; + + hole_idx = i / XFS_INODES_PER_HOLEMASK_BIT; + if (!(irec.ir_holemask & (1U << hole_idx))) + ret++; } error = xfs_btree_increment(cur, 0, &has_record); + if (error) + return error; } - return error; + + *allocated = ret; + return 0; } /* Is there an inode record covering a given extent? */ @@ -2687,15 +2693,27 @@ xfs_ialloc_has_inodes_at_extent( struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, - bool *exists) + enum xbtree_recpacking *outcome) { - xfs_agino_t low; - xfs_agino_t high; + xfs_agino_t agino; + xfs_agino_t last_agino; + unsigned int allocated; + int error; - low = XFS_AGB_TO_AGINO(cur->bc_mp, bno); - high = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1; + agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno); + last_agino = XFS_AGB_TO_AGINO(cur->bc_mp, bno + len) - 1; - return xfs_ialloc_has_inode_record(cur, low, high, exists); + error = xfs_ialloc_count_ondisk(cur, agino, last_agino, &allocated); + if (error) + return error; + + if (allocated == 0) + *outcome = XBTREE_RECPACKING_EMPTY; + else if (allocated == last_agino - agino + 1) + *outcome = XBTREE_RECPACKING_FULL; + else + *outcome = XBTREE_RECPACKING_SPARSE; + return 0; } struct xfs_ialloc_count_inodes { diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 90b0e5079338..fe824bb04a09 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -96,9 +96,8 @@ void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, xfs_failaddr_t xfs_inobt_check_irec(struct xfs_btree_cur *cur, const struct xfs_inobt_rec_incore *irec); int xfs_ialloc_has_inodes_at_extent(struct xfs_btree_cur *cur, - xfs_agblock_t bno, xfs_extlen_t len, bool *exists); -int xfs_ialloc_has_inode_record(struct xfs_btree_cur *cur, xfs_agino_t low, - xfs_agino_t high, bool *exists); + xfs_agblock_t bno, xfs_extlen_t len, + enum xbtree_recpacking *outcome); int xfs_ialloc_count_inodes(struct xfs_btree_cur *cur, xfs_agino_t *count, xfs_agino_t *freecount); int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask, diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 3a37c3dc0fae..fda96b536730 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -765,18 +765,18 @@ xchk_xref_inode_check( xfs_agblock_t agbno, xfs_extlen_t len, struct xfs_btree_cur **icur, - bool should_have_inodes) + enum xbtree_recpacking expected) { - bool has_inodes; + enum xbtree_recpacking outcome; int error; if (!(*icur) || xchk_skip_xref(sc->sm)) return; - error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes); + error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &outcome); if (!xchk_should_check_xref(sc, &error, icur)) return; - if (has_inodes != should_have_inodes) + if (outcome != expected) xchk_btree_xref_set_corrupt(sc, *icur, 0); } @@ -787,8 +787,10 @@ xchk_xref_is_not_inode_chunk( xfs_agblock_t agbno, xfs_extlen_t len) { - xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false); - xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false); + xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, + XBTREE_RECPACKING_EMPTY); + xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, + XBTREE_RECPACKING_EMPTY); } /* xref check that the extent is covered by inodes */ @@ -798,5 +800,6 @@ xchk_xref_is_inode_chunk( xfs_agblock_t agbno, xfs_extlen_t len) { - xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true); + xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, + XBTREE_RECPACKING_FULL); } -- GitLab From 9dceccc5822f2ecea12a89f24d7cad1f3e5eab7c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:16 -0700 Subject: [PATCH 2587/5631] xfs: use the directory name hash function for dir scrubbing The directory code has a directory-specific hash computation function that includes a modified hash function for case-insensitive lookups. Hence we must use that function (and not the raw da_hashname) when checking the dabtree structure. Found by accidentally breaking xfs/188 to create an abnormally huge case-insensitive directory and watching scrub break. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Dave Chinner --- fs/xfs/scrub/dir.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index b6081a3e1b91..1b1830576dcd 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -201,6 +201,7 @@ xchk_dir_rec( struct xchk_da_btree *ds, int level) { + struct xfs_name dname = { }; struct xfs_da_state_blk *blk = &ds->state->path.blk[level]; struct xfs_mount *mp = ds->state->mp; struct xfs_inode *dp = ds->dargs.dp; @@ -297,7 +298,11 @@ xchk_dir_rec( xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno); goto out_relse; } - calc_hash = xfs_da_hashname(dent->name, dent->namelen); + + /* Does the directory hash match? */ + dname.name = dent->name; + dname.len = dent->namelen; + calc_hash = xfs_dir2_hashname(mp, &dname); if (calc_hash != hash) xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno); -- GitLab From 30f8ee5e7e0ccce396dff209c6cbce49d0d7e167 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:16 -0700 Subject: [PATCH 2588/5631] xfs: ensure that single-owner file blocks are not owned by others For any file fork mapping that can only have a single owner, make sure that there are no other rmap owners for that mapping. This patch requires the more detailed checking provided by xfs_rmap_count_owners so that we can know how many rmap records for a given range of space had a matching owner, how many had a non-matching owner, and how many conflicted with the records that have a matching owner. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index be2c4da2808b..2412dcf0fa9a 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -308,6 +308,7 @@ xchk_bmap_iextent_xref( struct xchk_bmap_info *info, struct xfs_bmbt_irec *irec) { + struct xfs_owner_info oinfo; struct xfs_mount *mp = info->sc->mp; xfs_agnumber_t agno; xfs_agblock_t agbno; @@ -328,19 +329,30 @@ xchk_bmap_iextent_xref( xchk_bmap_xref_rmap(info, irec, agbno); switch (info->whichfork) { case XFS_DATA_FORK: - if (!xfs_is_reflink_inode(info->sc->ip)) + if (!xfs_is_reflink_inode(info->sc->ip)) { + xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, + info->whichfork, irec->br_startoff); + xchk_xref_is_only_owned_by(info->sc, agbno, + irec->br_blockcount, &oinfo); xchk_xref_is_not_shared(info->sc, agbno, irec->br_blockcount); + } xchk_xref_is_not_cow_staging(info->sc, agbno, irec->br_blockcount); break; case XFS_ATTR_FORK: + xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, + info->whichfork, irec->br_startoff); + xchk_xref_is_only_owned_by(info->sc, agbno, irec->br_blockcount, + &oinfo); xchk_xref_is_not_shared(info->sc, agbno, irec->br_blockcount); xchk_xref_is_not_cow_staging(info->sc, agbno, irec->br_blockcount); break; case XFS_COW_FORK: + xchk_xref_is_only_owned_by(info->sc, agbno, irec->br_blockcount, + &XFS_RMAP_OINFO_COW); xchk_xref_is_cow_staging(info->sc, agbno, irec->br_blockcount); xchk_xref_is_not_shared(info->sc, agbno, -- GitLab From 4c233b5c4f29dff11eeb64b2b1cc0831b9904a4f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:17 -0700 Subject: [PATCH 2589/5631] xfs: streamline the directory iteration code for scrub Currently, online scrub reuses the xfs_readdir code to walk every entry in a directory. This isn't awesome for performance, since we end up cycling the directory ILOCK needlessly and coding around the particular quirks of the VFS dir_context interface. Create a streamlined version of readdir that keeps the ILOCK (since the walk function isn't going to copy stuff to userspace), skips a whole lot of directory walk cursor checks (since we start at 0 and walk to the end) and has a sane way to return error codes. Note: Porting the dotdot checking code is left for a subsequent patch. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/Makefile | 1 + fs/xfs/scrub/dir.c | 188 +++++++-------------- fs/xfs/scrub/parent.c | 73 +++----- fs/xfs/scrub/readdir.c | 375 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/scrub/readdir.h | 19 +++ 5 files changed, 473 insertions(+), 183 deletions(-) create mode 100644 fs/xfs/scrub/readdir.c create mode 100644 fs/xfs/scrub/readdir.h diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 3bdbc838c4d1..ac9d03cd2623 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -158,6 +158,7 @@ xfs-y += $(addprefix scrub/, \ ialloc.o \ inode.o \ parent.o \ + readdir.o \ refcount.o \ rmap.o \ scrub.o \ diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 1b1830576dcd..f1cbe7b22688 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -18,6 +18,7 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/dabtree.h" +#include "scrub/readdir.h" /* Set us up to scrub directories. */ int @@ -31,30 +32,21 @@ xchk_setup_directory( /* Scrub a directory entry. */ -struct xchk_dir_ctx { - /* VFS fill-directory iterator */ - struct dir_context dir_iter; - - struct xfs_scrub *sc; -}; - -/* Check that an inode's mode matches a given DT_ type. */ +/* Check that an inode's mode matches a given XFS_DIR3_FT_* type. */ STATIC int xchk_dir_check_ftype( - struct xchk_dir_ctx *sdc, + struct xfs_scrub *sc, xfs_fileoff_t offset, xfs_ino_t inum, - int dtype) + int ftype) { - struct xfs_mount *mp = sdc->sc->mp; + struct xfs_mount *mp = sc->mp; struct xfs_inode *ip; - int ino_dtype; int error = 0; if (!xfs_has_ftype(mp)) { - if (dtype != DT_UNKNOWN && dtype != DT_DIR) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, - offset); + if (ftype != XFS_DIR3_FT_UNKNOWN && ftype != XFS_DIR3_FT_DIR) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); goto out; } @@ -71,21 +63,17 @@ xchk_dir_check_ftype( * -EFSCORRUPTED or -EFSBADCRC then the child is corrupt which is a * cross referencing error. Any other error is an operational error. */ - error = xfs_iget(mp, sdc->sc->tp, inum, 0, 0, &ip); + error = xfs_iget(mp, sc->tp, inum, 0, 0, &ip); if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; - xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, 0, &error); + xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); goto out; } - if (!xchk_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset, - &error)) + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, offset, &error)) goto out; - /* Convert mode to the DT_* values that dir_emit uses. */ - ino_dtype = xfs_dir3_get_dtype(mp, - xfs_mode_to_ftype(VFS_I(ip)->i_mode)); - if (ino_dtype != dtype) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset); + if (xfs_mode_to_ftype(VFS_I(ip)->i_mode) != ftype) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); xfs_irele(ip); out: return error; @@ -94,105 +82,85 @@ xchk_dir_check_ftype( /* * Scrub a single directory entry. * - * We use the VFS directory iterator (i.e. readdir) to call this - * function for every directory entry in a directory. Once we're here, - * we check the inode number to make sure it's sane, then we check that - * we can look up this filename. Finally, we check the ftype. + * Check the inode number to make sure it's sane, then we check that we can + * look up this filename. Finally, we check the ftype. */ -STATIC bool +STATIC int xchk_dir_actor( - struct dir_context *dir_iter, - const char *name, - int namelen, - loff_t pos, - u64 ino, - unsigned type) + struct xfs_scrub *sc, + struct xfs_inode *dp, + xfs_dir2_dataptr_t dapos, + const struct xfs_name *name, + xfs_ino_t ino, + void *priv) { - struct xfs_mount *mp; - struct xfs_inode *ip; - struct xchk_dir_ctx *sdc; - struct xfs_name xname; + struct xfs_mount *mp = dp->i_mount; xfs_ino_t lookup_ino; xfs_dablk_t offset; bool checked_ftype = false; int error = 0; - sdc = container_of(dir_iter, struct xchk_dir_ctx, dir_iter); - ip = sdc->sc->ip; - mp = ip->i_mount; offset = xfs_dir2_db_to_da(mp->m_dir_geo, - xfs_dir2_dataptr_to_db(mp->m_dir_geo, pos)); + xfs_dir2_dataptr_to_db(mp->m_dir_geo, dapos)); - if (xchk_should_terminate(sdc->sc, &error)) - return !error; + if (xchk_should_terminate(sc, &error)) + return error; /* Does this inode number make sense? */ if (!xfs_verify_dir_ino(mp, ino)) { - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset); - goto out; + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + return -ECANCELED; } /* Does this name make sense? */ - if (!xfs_dir2_namecheck(name, namelen)) { - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset); - goto out; + if (!xfs_dir2_namecheck(name->name, name->len)) { + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + return -ECANCELED; } - if (!strncmp(".", name, namelen)) { + if (!strncmp(".", name->name, name->len)) { /* If this is "." then check that the inum matches the dir. */ - if (xfs_has_ftype(mp) && type != DT_DIR) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, - offset); + if (xfs_has_ftype(mp) && name->type != XFS_DIR3_FT_DIR) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); checked_ftype = true; - if (ino != ip->i_ino) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, - offset); - } else if (!strncmp("..", name, namelen)) { + if (ino != dp->i_ino) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + } else if (!strncmp("..", name->name, name->len)) { /* * If this is ".." in the root inode, check that the inum * matches this dir. */ - if (xfs_has_ftype(mp) && type != DT_DIR) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, - offset); + if (xfs_has_ftype(mp) && name->type != XFS_DIR3_FT_DIR) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); checked_ftype = true; - if (ip->i_ino == mp->m_sb.sb_rootino && ino != ip->i_ino) - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, - offset); + if (dp->i_ino == mp->m_sb.sb_rootino && ino != dp->i_ino) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); } /* Verify that we can look up this name by hash. */ - xname.name = name; - xname.len = namelen; - xname.type = XFS_DIR3_FT_UNKNOWN; - - error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL); + error = xchk_dir_lookup(sc, dp, name, &lookup_ino); /* ENOENT means the hash lookup failed and the dir is corrupt */ if (error == -ENOENT) error = -EFSCORRUPTED; - if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset, - &error)) + if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) goto out; if (lookup_ino != ino) { - xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset); - goto out; + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); + return -ECANCELED; } /* Verify the file type. This function absorbs error codes. */ if (!checked_ftype) { - error = xchk_dir_check_ftype(sdc, offset, lookup_ino, type); + error = xchk_dir_check_ftype(sc, offset, lookup_ino, + name->type); if (error) goto out; } + out: - /* - * A negative error code returned here is supposed to cause the - * dir_emit caller (xfs_readdir) to abort the directory iteration - * and return zero to xchk_directory. - */ - if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - return false; - return !error; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return -ECANCELED; + return error; } /* Scrub a directory btree record. */ @@ -808,14 +776,7 @@ int xchk_directory( struct xfs_scrub *sc) { - struct xchk_dir_ctx sdc = { - .dir_iter.actor = xchk_dir_actor, - .dir_iter.pos = 0, - .sc = sc, - }; - size_t bufsize; - loff_t oldpos; - int error = 0; + int error; if (!S_ISDIR(VFS_I(sc->ip)->i_mode)) return -ENOENT; @@ -823,7 +784,7 @@ xchk_directory( /* Plausible size? */ if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) { xchk_ino_set_corrupt(sc, sc->ip->i_ino); - goto out; + return 0; } /* Check directory tree structure */ @@ -832,7 +793,7 @@ xchk_directory( return error; if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - return error; + return 0; /* Check the freespace. */ error = xchk_directory_blocks(sc); @@ -840,44 +801,11 @@ xchk_directory( return error; if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - return error; - - /* - * Check that every dirent we see can also be looked up by hash. - * Userspace usually asks for a 32k buffer, so we will too. - */ - bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, - sc->ip->i_disk_size); - - /* - * Look up every name in this directory by hash. - * - * Use the xfs_readdir function to call xchk_dir_actor on - * every directory entry in this directory. In _actor, we check - * the name, inode number, and ftype (if applicable) of the - * entry. xfs_readdir uses the VFS filldir functions to provide - * iteration context. - * - * The VFS grabs a read or write lock via i_rwsem before it reads - * or writes to a directory. If we've gotten this far we've - * already obtained IOLOCK_EXCL, which (since 4.10) is the same as - * getting a write lock on i_rwsem. Therefore, it is safe for us - * to drop the ILOCK here in order to reuse the _readdir and - * _dir_lookup routines, which do their own ILOCK locking. - */ - oldpos = 0; - sc->ilock_flags &= ~XFS_ILOCK_EXCL; - xfs_iunlock(sc->ip, XFS_ILOCK_EXCL); - while (true) { - error = xfs_readdir(sc->tp, sc->ip, &sdc.dir_iter, bufsize); - if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, - &error)) - goto out; - if (oldpos == sdc.dir_iter.pos) - break; - oldpos = sdc.dir_iter.pos; - } + return 0; -out: + /* Look up every name in this directory by hash. */ + error = xchk_dir_walk(sc, sc->ip, xchk_dir_actor, NULL); + if (error == -ECANCELED) + error = 0; return error; } diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index d1db18250ee3..af351c4ee6ec 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -16,6 +16,7 @@ #include "xfs_dir2_priv.h" #include "scrub/scrub.h" #include "scrub/common.h" +#include "scrub/readdir.h" /* Set us up to scrub parents. */ int @@ -30,39 +31,36 @@ xchk_setup_parent( /* Look for an entry in a parent pointing to this inode. */ struct xchk_parent_ctx { - struct dir_context dc; struct xfs_scrub *sc; - xfs_ino_t ino; xfs_nlink_t nlink; - bool cancelled; }; /* Look for a single entry in a directory pointing to an inode. */ -STATIC bool +STATIC int xchk_parent_actor( - struct dir_context *dc, - const char *name, - int namelen, - loff_t pos, - u64 ino, - unsigned type) + struct xfs_scrub *sc, + struct xfs_inode *dp, + xfs_dir2_dataptr_t dapos, + const struct xfs_name *name, + xfs_ino_t ino, + void *priv) { - struct xchk_parent_ctx *spc; + struct xchk_parent_ctx *spc = priv; int error = 0; - spc = container_of(dc, struct xchk_parent_ctx, dc); - if (spc->ino == ino) + /* Does this name make sense? */ + if (!xfs_dir2_namecheck(name->name, name->len)) + error = -EFSCORRUPTED; + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) + return error; + + if (sc->ip->i_ino == ino) spc->nlink++; - /* - * If we're facing a fatal signal, bail out. Store the cancellation - * status separately because the VFS readdir code squashes error codes - * into short directory reads. - */ if (xchk_should_terminate(spc->sc, &error)) - spc->cancelled = true; + return error; - return !error; + return 0; } /* Count the number of dentries in the parent dir that point to this inode. */ @@ -73,50 +71,19 @@ xchk_parent_count_parent_dentries( xfs_nlink_t *nlink) { struct xchk_parent_ctx spc = { - .dc.actor = xchk_parent_actor, - .ino = sc->ip->i_ino, .sc = sc, + .nlink = 0, }; - size_t bufsize; - loff_t oldpos; uint lock_mode; int error = 0; - /* - * If there are any blocks, read-ahead block 0 as we're almost - * certain to have the next operation be a read there. This is - * how we guarantee that the parent's extent map has been loaded, - * if there is one. - */ lock_mode = xfs_ilock_data_map_shared(parent); - if (parent->i_df.if_nextents > 0) - error = xfs_dir3_data_readahead(parent, 0, 0); + error = xchk_dir_walk(sc, parent, xchk_parent_actor, &spc); xfs_iunlock(parent, lock_mode); if (error) return error; - /* - * Iterate the parent dir to confirm that there is - * exactly one entry pointing back to the inode being - * scanned. - */ - bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, - parent->i_disk_size); - oldpos = 0; - while (true) { - error = xfs_readdir(sc->tp, parent, &spc.dc, bufsize); - if (error) - goto out; - if (spc.cancelled) { - error = -EAGAIN; - goto out; - } - if (oldpos == spc.dc.pos) - break; - oldpos = spc.dc.pos; - } *nlink = spc.nlink; -out: return error; } diff --git a/fs/xfs/scrub/readdir.c b/fs/xfs/scrub/readdir.c new file mode 100644 index 000000000000..e51c1544be63 --- /dev/null +++ b/fs/xfs/scrub/readdir.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2022-2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_dir2.h" +#include "xfs_dir2_priv.h" +#include "xfs_trace.h" +#include "xfs_bmap.h" +#include "xfs_trans.h" +#include "xfs_error.h" +#include "scrub/scrub.h" +#include "scrub/readdir.h" + +/* Call a function for every entry in a shortform directory. */ +STATIC int +xchk_dir_walk_sf( + struct xfs_scrub *sc, + struct xfs_inode *dp, + xchk_dirent_fn dirent_fn, + void *priv) +{ + struct xfs_name name = { + .name = ".", + .len = 1, + .type = XFS_DIR3_FT_DIR, + }; + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_geometry *geo = mp->m_dir_geo; + struct xfs_dir2_sf_entry *sfep; + struct xfs_dir2_sf_hdr *sfp; + xfs_ino_t ino; + xfs_dir2_dataptr_t dapos; + unsigned int i; + int error; + + ASSERT(dp->i_df.if_bytes == dp->i_disk_size); + ASSERT(dp->i_df.if_u1.if_data != NULL); + + sfp = (struct xfs_dir2_sf_hdr *)dp->i_df.if_u1.if_data; + + /* dot entry */ + dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, + geo->data_entry_offset); + + error = dirent_fn(sc, dp, dapos, &name, dp->i_ino, priv); + if (error) + return error; + + /* dotdot entry */ + dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, + geo->data_entry_offset + + xfs_dir2_data_entsize(mp, sizeof(".") - 1)); + ino = xfs_dir2_sf_get_parent_ino(sfp); + name.name = ".."; + name.len = 2; + + error = dirent_fn(sc, dp, dapos, &name, ino, priv); + if (error) + return error; + + /* iterate everything else */ + sfep = xfs_dir2_sf_firstentry(sfp); + for (i = 0; i < sfp->count; i++) { + dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, + xfs_dir2_sf_get_offset(sfep)); + ino = xfs_dir2_sf_get_ino(mp, sfp, sfep); + name.name = sfep->name; + name.len = sfep->namelen; + name.type = xfs_dir2_sf_get_ftype(mp, sfep); + + error = dirent_fn(sc, dp, dapos, &name, ino, priv); + if (error) + return error; + + sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep); + } + + return 0; +} + +/* Call a function for every entry in a block directory. */ +STATIC int +xchk_dir_walk_block( + struct xfs_scrub *sc, + struct xfs_inode *dp, + xchk_dirent_fn dirent_fn, + void *priv) +{ + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_geometry *geo = mp->m_dir_geo; + struct xfs_buf *bp; + unsigned int off, next_off, end; + int error; + + error = xfs_dir3_block_read(sc->tp, dp, &bp); + if (error) + return error; + + /* Walk each directory entry. */ + end = xfs_dir3_data_end_offset(geo, bp->b_addr); + for (off = geo->data_entry_offset; off < end; off = next_off) { + struct xfs_name name = { }; + struct xfs_dir2_data_unused *dup = bp->b_addr + off; + struct xfs_dir2_data_entry *dep = bp->b_addr + off; + xfs_ino_t ino; + xfs_dir2_dataptr_t dapos; + + /* Skip an empty entry. */ + if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { + next_off = off + be16_to_cpu(dup->length); + continue; + } + + /* Otherwise, find the next entry and report it. */ + next_off = off + xfs_dir2_data_entsize(mp, dep->namelen); + if (next_off > end) + break; + + dapos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, off); + ino = be64_to_cpu(dep->inumber); + name.name = dep->name; + name.len = dep->namelen; + name.type = xfs_dir2_data_get_ftype(mp, dep); + + error = dirent_fn(sc, dp, dapos, &name, ino, priv); + if (error) + break; + } + + xfs_trans_brelse(sc->tp, bp); + return error; +} + +/* Read a leaf-format directory buffer. */ +STATIC int +xchk_read_leaf_dir_buf( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_da_geometry *geo, + xfs_dir2_off_t *curoff, + struct xfs_buf **bpp) +{ + struct xfs_iext_cursor icur; + struct xfs_bmbt_irec map; + struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK); + xfs_dablk_t last_da; + xfs_dablk_t map_off; + xfs_dir2_off_t new_off; + + *bpp = NULL; + + /* + * Look for mapped directory blocks at or above the current offset. + * Truncate down to the nearest directory block to start the scanning + * operation. + */ + last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET); + map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *curoff)); + + if (!xfs_iext_lookup_extent(dp, ifp, map_off, &icur, &map)) + return 0; + if (map.br_startoff >= last_da) + return 0; + xfs_trim_extent(&map, map_off, last_da - map_off); + + /* Read the directory block of that first mapping. */ + new_off = xfs_dir2_da_to_byte(geo, map.br_startoff); + if (new_off > *curoff) + *curoff = new_off; + + return xfs_dir3_data_read(tp, dp, map.br_startoff, 0, bpp); +} + +/* Call a function for every entry in a leaf directory. */ +STATIC int +xchk_dir_walk_leaf( + struct xfs_scrub *sc, + struct xfs_inode *dp, + xchk_dirent_fn dirent_fn, + void *priv) +{ + struct xfs_mount *mp = dp->i_mount; + struct xfs_da_geometry *geo = mp->m_dir_geo; + struct xfs_buf *bp = NULL; + xfs_dir2_off_t curoff = 0; + unsigned int offset = 0; + int error; + + /* Iterate every directory offset in this directory. */ + while (curoff < XFS_DIR2_LEAF_OFFSET) { + struct xfs_name name = { }; + struct xfs_dir2_data_unused *dup; + struct xfs_dir2_data_entry *dep; + xfs_ino_t ino; + unsigned int length; + xfs_dir2_dataptr_t dapos; + + /* + * If we have no buffer, or we're off the end of the + * current buffer, need to get another one. + */ + if (!bp || offset >= geo->blksize) { + if (bp) { + xfs_trans_brelse(sc->tp, bp); + bp = NULL; + } + + error = xchk_read_leaf_dir_buf(sc->tp, dp, geo, &curoff, + &bp); + if (error || !bp) + break; + + /* + * Find our position in the block. + */ + offset = geo->data_entry_offset; + curoff += geo->data_entry_offset; + } + + /* Skip an empty entry. */ + dup = bp->b_addr + offset; + if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { + length = be16_to_cpu(dup->length); + offset += length; + curoff += length; + continue; + } + + /* Otherwise, find the next entry and report it. */ + dep = bp->b_addr + offset; + length = xfs_dir2_data_entsize(mp, dep->namelen); + + dapos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff; + ino = be64_to_cpu(dep->inumber); + name.name = dep->name; + name.len = dep->namelen; + name.type = xfs_dir2_data_get_ftype(mp, dep); + + error = dirent_fn(sc, dp, dapos, &name, ino, priv); + if (error) + break; + + /* Advance to the next entry. */ + offset += length; + curoff += length; + } + + if (bp) + xfs_trans_brelse(sc->tp, bp); + return error; +} + +/* + * Call a function for every entry in a directory. + * + * Callers must hold the ILOCK. File types are XFS_DIR3_FT_*. + */ +int +xchk_dir_walk( + struct xfs_scrub *sc, + struct xfs_inode *dp, + xchk_dirent_fn dirent_fn, + void *priv) +{ + struct xfs_da_args args = { + .dp = dp, + .geo = dp->i_mount->m_dir_geo, + .trans = sc->tp, + }; + bool isblock; + int error; + + if (xfs_is_shutdown(dp->i_mount)) + return -EIO; + + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); + ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + + if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) + return xchk_dir_walk_sf(sc, dp, dirent_fn, priv); + + /* dir2 functions require that the data fork is loaded */ + error = xfs_iread_extents(sc->tp, dp, XFS_DATA_FORK); + if (error) + return error; + + error = xfs_dir2_isblock(&args, &isblock); + if (error) + return error; + + if (isblock) + return xchk_dir_walk_block(sc, dp, dirent_fn, priv); + + return xchk_dir_walk_leaf(sc, dp, dirent_fn, priv); +} + +/* + * Look up the inode number for an exact name in a directory. + * + * Callers must hold the ILOCK. File types are XFS_DIR3_FT_*. Names are not + * checked for correctness. + */ +int +xchk_dir_lookup( + struct xfs_scrub *sc, + struct xfs_inode *dp, + const struct xfs_name *name, + xfs_ino_t *ino) +{ + struct xfs_da_args args = { + .dp = dp, + .geo = dp->i_mount->m_dir_geo, + .trans = sc->tp, + .name = name->name, + .namelen = name->len, + .filetype = name->type, + .hashval = xfs_dir2_hashname(dp->i_mount, name), + .whichfork = XFS_DATA_FORK, + .op_flags = XFS_DA_OP_OKNOENT, + }; + bool isblock, isleaf; + int error; + + if (xfs_is_shutdown(dp->i_mount)) + return -EIO; + + ASSERT(S_ISDIR(VFS_I(dp)->i_mode)); + ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + + if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL) { + error = xfs_dir2_sf_lookup(&args); + goto out_check_rval; + } + + /* dir2 functions require that the data fork is loaded */ + error = xfs_iread_extents(sc->tp, dp, XFS_DATA_FORK); + if (error) + return error; + + error = xfs_dir2_isblock(&args, &isblock); + if (error) + return error; + + if (isblock) { + error = xfs_dir2_block_lookup(&args); + goto out_check_rval; + } + + error = xfs_dir2_isleaf(&args, &isleaf); + if (error) + return error; + + if (isleaf) { + error = xfs_dir2_leaf_lookup(&args); + goto out_check_rval; + } + + error = xfs_dir2_node_lookup(&args); + +out_check_rval: + if (error == -EEXIST) + error = 0; + if (!error) + *ino = args.inumber; + return error; +} diff --git a/fs/xfs/scrub/readdir.h b/fs/xfs/scrub/readdir.h new file mode 100644 index 000000000000..55787f4df123 --- /dev/null +++ b/fs/xfs/scrub/readdir.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2022-2023 Oracle. All Rights Reserved. + * Author: Darrick J. Wong + */ +#ifndef __XFS_SCRUB_READDIR_H__ +#define __XFS_SCRUB_READDIR_H__ + +typedef int (*xchk_dirent_fn)(struct xfs_scrub *sc, struct xfs_inode *dp, + xfs_dir2_dataptr_t dapos, const struct xfs_name *name, + xfs_ino_t ino, void *priv); + +int xchk_dir_walk(struct xfs_scrub *sc, struct xfs_inode *dp, + xchk_dirent_fn dirent_fn, void *priv); + +int xchk_dir_lookup(struct xfs_scrub *sc, struct xfs_inode *dp, + const struct xfs_name *name, xfs_ino_t *ino); + +#endif /* __XFS_SCRUB_READDIR_H__ */ -- GitLab From d9a94480f978d5fbf1235a12a476f9f39a029ea5 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:17 -0700 Subject: [PATCH 2590/5631] xfs: xfs_iget in the directory scrubber needs to use UNTRUSTED In commit 4b80ac64450f, we tried to strengthen the directory scrubber by using the iget call to detect directory entries that point to unallocated inodes. Unfortunately, that commit neglected to pass XFS_IGET_UNTRUSTED to xfs_iget, so we don't check the inode btree first. If the inode number points to something that isn't even an inode cluster, iget will throw corruption errors and return -EFSCORRUPTED, which means that we fail to mark the directory corrupt. Fixes: 4b80ac64450f ("xfs: scrub should mark a directory corrupt if any entries cannot be iget'd") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/dir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index f1cbe7b22688..41f10e1c580c 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -57,13 +57,15 @@ xchk_dir_check_ftype( * eofblocks cleanup (which allocates what would be a nested * transaction), we can't use DONTCACHE here because DONTCACHE * inodes can trigger immediate inactive cleanup of the inode. + * Use UNTRUSTED here to check the allocation status of the inode in + * the inode btrees. * * If _iget returns -EINVAL or -ENOENT then the child inode number is * garbage and the directory is corrupt. If the _iget returns * -EFSCORRUPTED or -EFSBADCRC then the child is corrupt which is a * cross referencing error. Any other error is an operational error. */ - error = xfs_iget(mp, sc->tp, inum, 0, 0, &ip); + error = xfs_iget(mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, &ip); if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); -- GitLab From 6bb9209ceebb07fd07cec25af04eed1809c654de Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:18 -0700 Subject: [PATCH 2591/5631] xfs: always check the existence of a dirent's child inode When we're scrubbing directory entries, we always need to iget the child inode to make sure that the inode pointer points to a valid inode. The original directory scrub code (commit a5c4) only set us up to do this for ftype=1 filesystems, which is not sufficient; and then commit 4b80 made it worse by exempting the dot and dotdot entries. Sorta-fixes: a5c46e5e8912 ("xfs: scrub directory metadata") Sorta-fixes: 4b80ac64450f ("xfs: scrub should mark a directory corrupt if any entries cannot be iget'd") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/dir.c | 73 ++++++++++++++++++---------------------------- 1 file changed, 28 insertions(+), 45 deletions(-) diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 41f10e1c580c..6404201d3d36 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -33,52 +33,23 @@ xchk_setup_directory( /* Scrub a directory entry. */ /* Check that an inode's mode matches a given XFS_DIR3_FT_* type. */ -STATIC int +STATIC void xchk_dir_check_ftype( struct xfs_scrub *sc, xfs_fileoff_t offset, - xfs_ino_t inum, + struct xfs_inode *ip, int ftype) { struct xfs_mount *mp = sc->mp; - struct xfs_inode *ip; - int error = 0; if (!xfs_has_ftype(mp)) { if (ftype != XFS_DIR3_FT_UNKNOWN && ftype != XFS_DIR3_FT_DIR) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); - goto out; - } - - /* - * Grab the inode pointed to by the dirent. We release the - * inode before we cancel the scrub transaction. Since we're - * don't know a priori that releasing the inode won't trigger - * eofblocks cleanup (which allocates what would be a nested - * transaction), we can't use DONTCACHE here because DONTCACHE - * inodes can trigger immediate inactive cleanup of the inode. - * Use UNTRUSTED here to check the allocation status of the inode in - * the inode btrees. - * - * If _iget returns -EINVAL or -ENOENT then the child inode number is - * garbage and the directory is corrupt. If the _iget returns - * -EFSCORRUPTED or -EFSBADCRC then the child is corrupt which is a - * cross referencing error. Any other error is an operational error. - */ - error = xfs_iget(mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, &ip); - if (error == -EINVAL || error == -ENOENT) { - error = -EFSCORRUPTED; - xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); - goto out; + return; } - if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, offset, &error)) - goto out; if (xfs_mode_to_ftype(VFS_I(ip)->i_mode) != ftype) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); - xfs_irele(ip); -out: - return error; } /* @@ -97,9 +68,9 @@ xchk_dir_actor( void *priv) { struct xfs_mount *mp = dp->i_mount; + struct xfs_inode *ip; xfs_ino_t lookup_ino; xfs_dablk_t offset; - bool checked_ftype = false; int error = 0; offset = xfs_dir2_db_to_da(mp->m_dir_geo, @@ -122,9 +93,6 @@ xchk_dir_actor( if (!strncmp(".", name->name, name->len)) { /* If this is "." then check that the inum matches the dir. */ - if (xfs_has_ftype(mp) && name->type != XFS_DIR3_FT_DIR) - xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); - checked_ftype = true; if (ino != dp->i_ino) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); } else if (!strncmp("..", name->name, name->len)) { @@ -132,9 +100,6 @@ xchk_dir_actor( * If this is ".." in the root inode, check that the inum * matches this dir. */ - if (xfs_has_ftype(mp) && name->type != XFS_DIR3_FT_DIR) - xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); - checked_ftype = true; if (dp->i_ino == mp->m_sb.sb_rootino && ino != dp->i_ino) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); } @@ -151,14 +116,32 @@ xchk_dir_actor( return -ECANCELED; } - /* Verify the file type. This function absorbs error codes. */ - if (!checked_ftype) { - error = xchk_dir_check_ftype(sc, offset, lookup_ino, - name->type); - if (error) - goto out; + /* + * Grab the inode pointed to by the dirent. We release the + * inode before we cancel the scrub transaction. Since we're + * don't know a priori that releasing the inode won't trigger + * eofblocks cleanup (which allocates what would be a nested + * transaction), we can't use DONTCACHE here because DONTCACHE + * inodes can trigger immediate inactive cleanup of the inode. + * Use UNTRUSTED here to check the allocation status of the inode in + * the inode btrees. + * + * If _iget returns -EINVAL or -ENOENT then the child inode number is + * garbage and the directory is corrupt. If the _iget returns + * -EFSCORRUPTED or -EFSBADCRC then the child is corrupt which is a + * cross referencing error. Any other error is an operational error. + */ + error = xfs_iget(mp, sc->tp, ino, XFS_IGET_UNTRUSTED, 0, &ip); + if (error == -EINVAL || error == -ENOENT) { + error = -EFSCORRUPTED; + xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); + goto out; } + if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, offset, &error)) + goto out; + xchk_dir_check_ftype(sc, offset, ip, name->type); + xfs_irele(ip); out: if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return -ECANCELED; -- GitLab From cbab28f4c0719c956fa7b83613a3591c361126c7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:19 -0700 Subject: [PATCH 2592/5631] xfs: remove xchk_parent_count_parent_dentries This helper is now trivial, so get rid of it. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/parent.c | 42 +++++++++++++----------------------------- 1 file changed, 13 insertions(+), 29 deletions(-) diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index af351c4ee6ec..bbf6492c8e8e 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -63,30 +63,6 @@ xchk_parent_actor( return 0; } -/* Count the number of dentries in the parent dir that point to this inode. */ -STATIC int -xchk_parent_count_parent_dentries( - struct xfs_scrub *sc, - struct xfs_inode *parent, - xfs_nlink_t *nlink) -{ - struct xchk_parent_ctx spc = { - .sc = sc, - .nlink = 0, - }; - uint lock_mode; - int error = 0; - - lock_mode = xfs_ilock_data_map_shared(parent); - error = xchk_dir_walk(sc, parent, xchk_parent_actor, &spc); - xfs_iunlock(parent, lock_mode); - if (error) - return error; - - *nlink = spc.nlink; - return error; -} - /* * Given the inode number of the alleged parent of the inode being * scrubbed, try to validate that the parent has exactly one directory @@ -98,10 +74,14 @@ xchk_parent_validate( xfs_ino_t dnum, bool *try_again) { + struct xchk_parent_ctx spc = { + .sc = sc, + .nlink = 0, + }; struct xfs_mount *mp = sc->mp; struct xfs_inode *dp = NULL; xfs_nlink_t expected_nlink; - xfs_nlink_t nlink; + uint lock_mode; int error = 0; *try_again = false; @@ -156,11 +136,13 @@ xchk_parent_validate( * the child inodes. */ if (xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) { - error = xchk_parent_count_parent_dentries(sc, dp, &nlink); + lock_mode = xfs_ilock_data_map_shared(dp); + error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc); + xfs_iunlock(dp, lock_mode); if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) goto out_unlock; - if (nlink != expected_nlink) + if (spc.nlink != expected_nlink) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); goto out_unlock; } @@ -178,7 +160,9 @@ xchk_parent_validate( goto out_rele; /* Go looking for our dentry. */ - error = xchk_parent_count_parent_dentries(sc, dp, &nlink); + lock_mode = xfs_ilock_data_map_shared(dp); + error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc); + xfs_iunlock(dp, lock_mode); if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) goto out_unlock; @@ -213,7 +197,7 @@ xchk_parent_validate( * '..' didn't change, so check that there was only one entry * for us in the parent. */ - if (nlink != expected_nlink) + if (spc.nlink != expected_nlink) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); return error; -- GitLab From b049962c0f6eb6fb17e8294721f948285a44a672 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:19 -0700 Subject: [PATCH 2593/5631] xfs: simplify xchk_parent_validate This function is unnecessarily long because it contains code to revalidate a dotdot entry after cycling locks to try to confirm a subdirectory parent pointer. Shorten the codebase by making the parent's lookup call do double duty as the revalidation code. This weakeans the efficacy of this scrub function temporarily, but the next patch will resolve this as part of fixing an unhandled race that is the result of the VFS rename locking model not working the way Darrick thought it did. Rename this stupid 'dnum' variable too. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/parent.c | 100 ++++++++++-------------------------------- 1 file changed, 23 insertions(+), 77 deletions(-) diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index bbf6492c8e8e..50dc423041ee 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -71,7 +71,7 @@ xchk_parent_actor( STATIC int xchk_parent_validate( struct xfs_scrub *sc, - xfs_ino_t dnum, + xfs_ino_t parent_ino, bool *try_again) { struct xchk_parent_ctx spc = { @@ -86,11 +86,16 @@ xchk_parent_validate( *try_again = false; - if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + /* Is this the root dir? Then '..' must point to itself. */ + if (sc->ip == mp->m_rootip) { + if (sc->ip->i_ino != mp->m_sb.sb_rootino || + sc->ip->i_ino != parent_ino) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); goto out; + } /* '..' must not point to ourselves. */ - if (sc->ip->i_ino == dnum) { + if (sc->ip->i_ino == parent_ino) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); goto out; } @@ -115,7 +120,7 @@ xchk_parent_validate( * -EFSCORRUPTED or -EFSBADCRC then the parent is corrupt which is a * cross referencing error. Any other error is an operational error. */ - error = xfs_iget(mp, sc->tp, dnum, XFS_IGET_UNTRUSTED, 0, &dp); + error = xfs_iget(mp, sc->tp, parent_ino, XFS_IGET_UNTRUSTED, 0, &dp); if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); @@ -135,71 +140,19 @@ xchk_parent_validate( * use nowait here to avoid an ABBA deadlock on the parent and * the child inodes. */ - if (xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) { - lock_mode = xfs_ilock_data_map_shared(dp); - error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc); - xfs_iunlock(dp, lock_mode); - if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, - &error)) - goto out_unlock; - if (spc.nlink != expected_nlink) - xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out_unlock; - } - - /* - * The game changes if we get here. We failed to lock the parent, - * so we're going to try to verify both pointers while only holding - * one lock so as to avoid deadlocking with something that's actually - * trying to traverse down the directory tree. - */ - xfs_iunlock(sc->ip, sc->ilock_flags); - sc->ilock_flags = 0; - error = xchk_ilock_inverted(dp, XFS_IOLOCK_SHARED); - if (error) + if (!xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) { + *try_again = true; goto out_rele; + } - /* Go looking for our dentry. */ lock_mode = xfs_ilock_data_map_shared(dp); error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc); xfs_iunlock(dp, lock_mode); if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) goto out_unlock; - /* Drop the parent lock, relock this inode. */ - xfs_iunlock(dp, XFS_IOLOCK_SHARED); - error = xchk_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL); - if (error) - goto out_rele; - sc->ilock_flags = XFS_IOLOCK_EXCL; - - /* - * If we're an unlinked directory, the parent /won't/ have a link - * to us. Otherwise, it should have one link. We have to re-set - * it here because we dropped the lock on sc->ip. - */ - expected_nlink = VFS_I(sc->ip)->i_nlink == 0 ? 0 : 1; - - /* Look up '..' to see if the inode changed. */ - error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL); - if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) - goto out_rele; - - /* Drat, parent changed. Try again! */ - if (dnum != dp->i_ino) { - xfs_irele(dp); - *try_again = true; - return 0; - } - xfs_irele(dp); - - /* - * '..' didn't change, so check that there was only one entry - * for us in the parent. - */ if (spc.nlink != expected_nlink) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - return error; out_unlock: xfs_iunlock(dp, XFS_IOLOCK_SHARED); @@ -215,7 +168,7 @@ xchk_parent( struct xfs_scrub *sc) { struct xfs_mount *mp = sc->mp; - xfs_ino_t dnum; + xfs_ino_t parent_ino; bool try_again; int tries = 0; int error = 0; @@ -243,25 +196,18 @@ xchk_parent( sc->ilock_flags &= ~(XFS_ILOCK_EXCL | XFS_MMAPLOCK_EXCL); xfs_iunlock(sc->ip, XFS_ILOCK_EXCL | XFS_MMAPLOCK_EXCL); - /* Look up '..' */ - error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL); - if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) - goto out; - if (!xfs_verify_dir_ino(mp, dnum)) { - xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; - } - - /* Is this the root dir? Then '..' must point to itself. */ - if (sc->ip == mp->m_rootip) { - if (sc->ip->i_ino != mp->m_sb.sb_rootino || - sc->ip->i_ino != dnum) + do { + /* Look up '..' */ + error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, + &parent_ino, NULL); + if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) + goto out; + if (!xfs_verify_dir_ino(mp, parent_ino)) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; - } + goto out; + } - do { - error = xchk_parent_validate(sc, dnum, &try_again); + error = xchk_parent_validate(sc, parent_ino, &try_again); if (error) goto out; } while (try_again && ++tries < 20); -- GitLab From a03297a0ca9f21800c9b88028a3722715b2eb5ba Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:20 -0700 Subject: [PATCH 2594/5631] xfs: manage inode DONTCACHE status at irele time Right now, there are statements scattered all over the online fsck codebase about how we can't use XFS_IGET_DONTCACHE because of concerns about scrub's unusual practice of releasing inodes with transactions held. However, iget is the wrong place to handle this -- the DONTCACHE state doesn't matter at all until we try to *release* the inode, and here we get things wrong in multiple ways: First, if we /do/ have a transaction, we must NOT drop the inode, because the inode could have dirty pages, dropping the inode will trigger writeback, and writeback can trigger a nested transaction. Second, if the inode already had an active reference and the DONTCACHE flag set, the icache hit when scrub grabs another ref will not clear DONTCACHE. This is sort of by design, since DONTCACHE is now used to initiate cache drops so that sysadmins can change a file's access mode between pagecache and DAX. Third, if we do actually have the last active reference to the inode, we can set DONTCACHE to avoid polluting the cache. This is the /one/ case where we actually want that flag. Create an xchk_irele helper to encode all that logic and switch the online fsck code to use it. Since this now means that nearly all scrubbers use the same xfs_iget flags, we can wrap them too. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/common.c | 52 +++++++++++++++++++++++++++++++++++++++---- fs/xfs/scrub/common.h | 3 +++ fs/xfs/scrub/dir.c | 14 ++++-------- fs/xfs/scrub/parent.c | 13 ++++------- fs/xfs/scrub/scrub.c | 2 +- 5 files changed, 60 insertions(+), 24 deletions(-) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 813ded91661b..9af653a1d351 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -718,6 +718,16 @@ xchk_checkpoint_log( return 0; } +/* Verify that an inode is allocated ondisk, then return its cached inode. */ +int +xchk_iget( + struct xfs_scrub *sc, + xfs_ino_t inum, + struct xfs_inode **ipp) +{ + return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp); +} + /* * Given an inode and the scrub control structure, grab either the * inode referenced in the control structure or the inode passed in. @@ -743,8 +753,7 @@ xchk_get_inode( /* Look up the inode, see if the generation number matches. */ if (xfs_internal_inum(mp, sc->sm->sm_ino)) return -ENOENT; - error = xfs_iget(mp, NULL, sc->sm->sm_ino, - XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, &ip); + error = xchk_iget(sc, sc->sm->sm_ino, &ip); switch (error) { case -ENOENT: /* Inode doesn't exist, just bail out. */ @@ -768,7 +777,7 @@ xchk_get_inode( pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino)); if (pag) { error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap, - XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE); + XFS_IGET_UNTRUSTED); xfs_perag_put(pag); if (error) return -ENOENT; @@ -783,7 +792,7 @@ xchk_get_inode( return error; } if (VFS_I(ip)->i_generation != sc->sm->sm_gen) { - xfs_irele(ip); + xchk_irele(sc, ip); return -ENOENT; } @@ -791,6 +800,41 @@ xchk_get_inode( return 0; } +/* Release an inode, possibly dropping it in the process. */ +void +xchk_irele( + struct xfs_scrub *sc, + struct xfs_inode *ip) +{ + if (current->journal_info != NULL) { + ASSERT(current->journal_info == sc->tp); + + /* + * If we are in a transaction, we /cannot/ drop the inode + * ourselves, because the VFS will trigger writeback, which + * can require a transaction. Clear DONTCACHE to force the + * inode to the LRU, where someone else can take care of + * dropping it. + * + * Note that when we grabbed our reference to the inode, it + * could have had an active ref and DONTCACHE set if a sysadmin + * is trying to coerce a change in file access mode. icache + * hits do not clear DONTCACHE, so we must do it here. + */ + spin_lock(&VFS_I(ip)->i_lock); + VFS_I(ip)->i_state &= ~I_DONTCACHE; + spin_unlock(&VFS_I(ip)->i_lock); + } else if (atomic_read(&VFS_I(ip)->i_count) == 1) { + /* + * If this is the last reference to the inode and the caller + * permits it, set DONTCACHE to avoid thrashing. + */ + d_mark_dontcache(VFS_I(ip)); + } + + xfs_irele(ip); +} + /* Set us up to scrub a file's contents. */ int xchk_setup_inode_contents( diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 544f86ff8d1d..7e9e8b7b6cb0 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -137,6 +137,9 @@ int xchk_get_inode(struct xfs_scrub *sc); int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks); void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp); +int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp); +void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip); + /* * Don't bother cross-referencing if we already found corruption or cross * referencing discrepancies. diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 6404201d3d36..0b491784b759 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -117,21 +117,15 @@ xchk_dir_actor( } /* - * Grab the inode pointed to by the dirent. We release the - * inode before we cancel the scrub transaction. Since we're - * don't know a priori that releasing the inode won't trigger - * eofblocks cleanup (which allocates what would be a nested - * transaction), we can't use DONTCACHE here because DONTCACHE - * inodes can trigger immediate inactive cleanup of the inode. - * Use UNTRUSTED here to check the allocation status of the inode in - * the inode btrees. + * Grab the inode pointed to by the dirent. We release the inode + * before we cancel the scrub transaction. * * If _iget returns -EINVAL or -ENOENT then the child inode number is * garbage and the directory is corrupt. If the _iget returns * -EFSCORRUPTED or -EFSBADCRC then the child is corrupt which is a * cross referencing error. Any other error is an operational error. */ - error = xfs_iget(mp, sc->tp, ino, XFS_IGET_UNTRUSTED, 0, &ip); + error = xchk_iget(sc, ino, &ip); if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); @@ -141,7 +135,7 @@ xchk_dir_actor( goto out; xchk_dir_check_ftype(sc, offset, ip, name->type); - xfs_irele(ip); + xchk_irele(sc, ip); out: if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return -ECANCELED; diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index b6c8f6dccc8f..58d5dfb7ea21 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -127,20 +127,15 @@ xchk_parent_validate( expected_nlink = VFS_I(sc->ip)->i_nlink == 0 ? 0 : 1; /* - * Grab this parent inode. We release the inode before we - * cancel the scrub transaction. Since we're don't know a - * priori that releasing the inode won't trigger eofblocks - * cleanup (which allocates what would be a nested transaction) - * if the parent pointer erroneously points to a file, we - * can't use DONTCACHE here because DONTCACHE inodes can trigger - * immediate inactive cleanup of the inode. + * Grab the parent directory inode. This must be released before we + * cancel the scrub transaction. * * If _iget returns -EINVAL or -ENOENT then the parent inode number is * garbage and the directory is corrupt. If the _iget returns * -EFSCORRUPTED or -EFSBADCRC then the parent is corrupt which is a * cross referencing error. Any other error is an operational error. */ - error = xfs_iget(mp, sc->tp, parent_ino, XFS_IGET_UNTRUSTED, 0, &dp); + error = xchk_iget(sc, parent_ino, &dp); if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); @@ -176,7 +171,7 @@ xchk_parent_validate( out_unlock: xfs_iunlock(dp, lock_mode); out_rele: - xfs_irele(dp); + xchk_irele(sc, dp); return error; } diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 787a9096ddef..03ec455318f4 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -181,7 +181,7 @@ xchk_teardown( xfs_iunlock(sc->ip, sc->ilock_flags); if (sc->ip != ip_in && !xfs_internal_inum(sc->mp, sc->ip->i_ino)) - xfs_irele(sc->ip); + xchk_irele(sc, sc->ip); sc->ip = NULL; } if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) -- GitLab From 0916056eba4fd816f8042a3960597c316ea10256 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:20 -0700 Subject: [PATCH 2595/5631] xfs: fix parent pointer scrub racing with subdirectory reparenting Jan Kara pointed out that rename() doesn't lock a subdirectory that is being moved from one parent to another, even though the move requires an update to the subdirectory's dotdot entry. This means that it's *not* sufficient to hold a directory's IOLOCK to stabilize the dotdot entry. We must hold the ILOCK of both the child and the alleged parent, and there's no use in holding the parent's IOLOCK. With that in mind, we can get rid of all the messy code that tries to grab the parent's IOLOCK, which means we don't need to let go of the ILOCK of the directory whose parent we are checking. We still have to use nonblocking mode to take the ILOCK of the alleged parent, so the revalidation loop has to stay. However, we can remove the retry counter, since threads aren't supposed to hold the ILOCK for long periods of time. Remove the inverted ilock helper from the common code since nobody uses it. Remove the entire source of -EDEADLOCK-based "retry harder" scrub executions. Link: https://lore.kernel.org/linux-xfs/20230117123735.un7wbamlbdihninm@quack3/ Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/common.c | 22 -------- fs/xfs/scrub/common.h | 1 - fs/xfs/scrub/parent.c | 118 ++++++++++++++++++++---------------------- 3 files changed, 57 insertions(+), 84 deletions(-) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index dcfe66044d4a..813ded91661b 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -962,28 +962,6 @@ xchk_metadata_inode_forks( return 0; } -/* - * Try to lock an inode in violation of the usual locking order rules. For - * example, trying to get the IOLOCK while in transaction context, or just - * plain breaking AG-order or inode-order inode locking rules. Either way, - * the only way to avoid an ABBA deadlock is to use trylock and back off if - * we can't. - */ -int -xchk_ilock_inverted( - struct xfs_inode *ip, - uint lock_mode) -{ - int i; - - for (i = 0; i < 20; i++) { - if (xfs_ilock_nowait(ip, lock_mode)) - return 0; - delay(1); - } - return -EDEADLOCK; -} - /* Pause background reaping of resources. */ void xchk_stop_reaping( diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 83b1a392930a..544f86ff8d1d 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -148,7 +148,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) } int xchk_metadata_inode_forks(struct xfs_scrub *sc); -int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode); void xchk_stop_reaping(struct xfs_scrub *sc); void xchk_start_reaping(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index 50dc423041ee..b6c8f6dccc8f 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -64,15 +64,37 @@ xchk_parent_actor( } /* - * Given the inode number of the alleged parent of the inode being - * scrubbed, try to validate that the parent has exactly one directory - * entry pointing back to the inode being scrubbed. + * Try to lock a parent directory for checking dirents. Returns the inode + * flags for the locks we now hold, or zero if we failed. + */ +STATIC unsigned int +xchk_parent_ilock_dir( + struct xfs_inode *dp) +{ + if (!xfs_ilock_nowait(dp, XFS_ILOCK_SHARED)) + return 0; + + if (!xfs_need_iread_extents(&dp->i_df)) + return XFS_ILOCK_SHARED; + + xfs_iunlock(dp, XFS_ILOCK_SHARED); + + if (!xfs_ilock_nowait(dp, XFS_ILOCK_EXCL)) + return 0; + + return XFS_ILOCK_EXCL; +} + +/* + * Given the inode number of the alleged parent of the inode being scrubbed, + * try to validate that the parent has exactly one directory entry pointing + * back to the inode being scrubbed. Returns -EAGAIN if we need to revalidate + * the dotdot entry. */ STATIC int xchk_parent_validate( struct xfs_scrub *sc, - xfs_ino_t parent_ino, - bool *try_again) + xfs_ino_t parent_ino) { struct xchk_parent_ctx spc = { .sc = sc, @@ -81,23 +103,21 @@ xchk_parent_validate( struct xfs_mount *mp = sc->mp; struct xfs_inode *dp = NULL; xfs_nlink_t expected_nlink; - uint lock_mode; + unsigned int lock_mode; int error = 0; - *try_again = false; - /* Is this the root dir? Then '..' must point to itself. */ if (sc->ip == mp->m_rootip) { if (sc->ip->i_ino != mp->m_sb.sb_rootino || sc->ip->i_ino != parent_ino) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; + return 0; } /* '..' must not point to ourselves. */ if (sc->ip->i_ino == parent_ino) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; + return 0; } /* @@ -124,41 +144,39 @@ xchk_parent_validate( if (error == -EINVAL || error == -ENOENT) { error = -EFSCORRUPTED; xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error); - goto out; + return error; } if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) - goto out; + return error; if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); goto out_rele; } - /* - * We prefer to keep the inode locked while we lock and search - * its alleged parent for a forward reference. If we can grab - * the iolock, validate the pointers and we're done. We must - * use nowait here to avoid an ABBA deadlock on the parent and - * the child inodes. - */ - if (!xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) { - *try_again = true; + lock_mode = xchk_parent_ilock_dir(dp); + if (!lock_mode) { + xfs_iunlock(sc->ip, XFS_ILOCK_EXCL); + xfs_ilock(sc->ip, XFS_ILOCK_EXCL); + error = -EAGAIN; goto out_rele; } - lock_mode = xfs_ilock_data_map_shared(dp); + /* Look for a directory entry in the parent pointing to the child. */ error = xchk_dir_walk(sc, dp, xchk_parent_actor, &spc); - xfs_iunlock(dp, lock_mode); if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error)) goto out_unlock; + /* + * Ensure that the parent has as many links to the child as the child + * thinks it has to the parent. + */ if (spc.nlink != expected_nlink) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); out_unlock: - xfs_iunlock(dp, XFS_IOLOCK_SHARED); + xfs_iunlock(dp, lock_mode); out_rele: xfs_irele(dp); -out: return error; } @@ -169,8 +187,6 @@ xchk_parent( { struct xfs_mount *mp = sc->mp; xfs_ino_t parent_ino; - bool try_again; - int tries = 0; int error = 0; /* @@ -183,49 +199,29 @@ xchk_parent( /* We're not a special inode, are we? */ if (!xfs_verify_dir_ino(mp, sc->ip->i_ino)) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; + return 0; } - /* - * The VFS grabs a read or write lock via i_rwsem before it reads - * or writes to a directory. If we've gotten this far we've - * already obtained IOLOCK_EXCL, which (since 4.10) is the same as - * getting a write lock on i_rwsem. Therefore, it is safe for us - * to drop the ILOCK here in order to do directory lookups. - */ - sc->ilock_flags &= ~(XFS_ILOCK_EXCL | XFS_MMAPLOCK_EXCL); - xfs_iunlock(sc->ip, XFS_ILOCK_EXCL | XFS_MMAPLOCK_EXCL); - do { + if (xchk_should_terminate(sc, &error)) + break; + /* Look up '..' */ - error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, - &parent_ino, NULL); + error = xchk_dir_lookup(sc, sc->ip, &xfs_name_dotdot, + &parent_ino); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error)) - goto out; + return error; if (!xfs_verify_dir_ino(mp, parent_ino)) { xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0); - goto out; + return 0; } - error = xchk_parent_validate(sc, parent_ino, &try_again); - if (error) - goto out; - } while (try_again && ++tries < 20); + /* + * Check that the dotdot entry points to a parent directory + * containing a dirent pointing to this subdirectory. + */ + error = xchk_parent_validate(sc, parent_ino); + } while (error == -EAGAIN); - /* - * We gave it our best shot but failed, so mark this scrub - * incomplete. Userspace can decide if it wants to try again. - */ - if (try_again && tries == 20) - xchk_set_incomplete(sc); -out: - /* - * If we failed to lock the parent inode even after a retry, just mark - * this scrub incomplete and return. - */ - if ((sc->flags & XCHK_TRY_HARDER) && error == -EDEADLOCK) { - error = 0; - xchk_set_incomplete(sc); - } return error; } -- GitLab From 302436c27c3fc61c1dab83f4c995dec12eb43161 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:21 -0700 Subject: [PATCH 2596/5631] xfs: fix an inode lookup race in xchk_get_inode In commit d658e, we tried to improve the robustnes of xchk_get_inode in the face of EINVAL returns from iget by calling xfs_imap to see if the inobt itself thinks that the inode is allocated. Unfortunately, that commit didn't consider the possibility that the inode gets allocated after iget but before imap. In this case, the imap call will succeed, but we turn that into a corruption error and tell userspace the inode is corrupt. Avoid this false corruption report by grabbing the AGI header and retrying the iget before calling imap. If the iget succeeds, we can proceed with the usual scrub-by-handle code. Fix all the incorrect comments too, since unreadable/corrupt inodes no longer result in EINVAL returns. Fixes: d658e72b4a09 ("xfs: distinguish between corrupt inode and invalid inum in xfs_scrub_get_inode") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/common.c | 233 ++++++++++++++++++++++++++++++++++-------- fs/xfs/scrub/common.h | 4 + fs/xfs/xfs_icache.c | 3 +- fs/xfs/xfs_icache.h | 11 +- 4 files changed, 205 insertions(+), 46 deletions(-) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 9af653a1d351..3fd437430cad 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -643,6 +643,14 @@ xchk_ag_init( /* Per-scrubber setup functions */ +void +xchk_trans_cancel( + struct xfs_scrub *sc) +{ + xfs_trans_cancel(sc->tp); + sc->tp = NULL; +} + /* * Grab an empty transaction so that we can re-grab locked buffers if * one of our btrees turns out to be cyclic. @@ -728,6 +736,101 @@ xchk_iget( return xfs_iget(sc->mp, sc->tp, inum, XFS_IGET_UNTRUSTED, 0, ipp); } +/* + * Try to grab an inode in a manner that avoids races with physical inode + * allocation. If we can't, return the locked AGI buffer so that the caller + * can single-step the loading process to see where things went wrong. + * Callers must have a valid scrub transaction. + * + * If the iget succeeds, return 0, a NULL AGI, and the inode. + * + * If the iget fails, return the error, the locked AGI, and a NULL inode. This + * can include -EINVAL and -ENOENT for invalid inode numbers or inodes that are + * no longer allocated; or any other corruption or runtime error. + * + * If the AGI read fails, return the error, a NULL AGI, and NULL inode. + * + * If a fatal signal is pending, return -EINTR, a NULL AGI, and a NULL inode. + */ +int +xchk_iget_agi( + struct xfs_scrub *sc, + xfs_ino_t inum, + struct xfs_buf **agi_bpp, + struct xfs_inode **ipp) +{ + struct xfs_mount *mp = sc->mp; + struct xfs_trans *tp = sc->tp; + struct xfs_perag *pag; + int error; + + ASSERT(sc->tp != NULL); + +again: + *agi_bpp = NULL; + *ipp = NULL; + error = 0; + + if (xchk_should_terminate(sc, &error)) + return error; + + /* + * Attach the AGI buffer to the scrub transaction to avoid deadlocks + * in the iget cache miss path. + */ + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum)); + error = xfs_ialloc_read_agi(pag, tp, agi_bpp); + xfs_perag_put(pag); + if (error) + return error; + + error = xfs_iget(mp, tp, inum, + XFS_IGET_NORETRY | XFS_IGET_UNTRUSTED, 0, ipp); + if (error == -EAGAIN) { + /* + * The inode may be in core but temporarily unavailable and may + * require the AGI buffer before it can be returned. Drop the + * AGI buffer and retry the lookup. + * + * Incore lookup will fail with EAGAIN on a cache hit if the + * inode is queued to the inactivation list. The inactivation + * worker may remove the inode from the unlinked list and hence + * needs the AGI. + * + * Hence xchk_iget_agi() needs to drop the AGI lock on EAGAIN + * to allow inodegc to make progress and move the inode to + * IRECLAIMABLE state where xfs_iget will be able to return it + * again if it can lock the inode. + */ + xfs_trans_brelse(tp, *agi_bpp); + delay(1); + goto again; + } + if (error) + return error; + + /* We got the inode, so we can release the AGI. */ + ASSERT(*ipp != NULL); + xfs_trans_brelse(tp, *agi_bpp); + *agi_bpp = NULL; + return 0; +} + +/* Install an inode that we opened by handle for scrubbing. */ +static int +xchk_install_handle_inode( + struct xfs_scrub *sc, + struct xfs_inode *ip) +{ + if (VFS_I(ip)->i_generation != sc->sm->sm_gen) { + xchk_irele(sc, ip); + return -ENOENT; + } + + sc->ip = ip; + return 0; +} + /* * Given an inode and the scrub control structure, grab either the * inode referenced in the control structure or the inode passed in. @@ -740,64 +843,112 @@ xchk_get_inode( struct xfs_imap imap; struct xfs_mount *mp = sc->mp; struct xfs_perag *pag; + struct xfs_buf *agi_bp; struct xfs_inode *ip_in = XFS_I(file_inode(sc->file)); struct xfs_inode *ip = NULL; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, sc->sm->sm_ino); int error; + ASSERT(sc->tp == NULL); + /* We want to scan the inode we already had opened. */ if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) { sc->ip = ip_in; return 0; } - /* Look up the inode, see if the generation number matches. */ + /* Reject internal metadata files and obviously bad inode numbers. */ if (xfs_internal_inum(mp, sc->sm->sm_ino)) return -ENOENT; + if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino)) + return -ENOENT; + + /* Try a regular untrusted iget. */ error = xchk_iget(sc, sc->sm->sm_ino, &ip); - switch (error) { - case -ENOENT: - /* Inode doesn't exist, just bail out. */ - return error; - case 0: - /* Got an inode, continue. */ - break; - case -EINVAL: - /* - * -EINVAL with IGET_UNTRUSTED could mean one of several - * things: userspace gave us an inode number that doesn't - * correspond to fs space, or doesn't have an inobt entry; - * or it could simply mean that the inode buffer failed the - * read verifiers. - * - * Try just the inode mapping lookup -- if it succeeds, then - * the inode buffer verifier failed and something needs fixing. - * Otherwise, we really couldn't find it so tell userspace - * that it no longer exists. - */ - pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino)); - if (pag) { - error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap, - XFS_IGET_UNTRUSTED); - xfs_perag_put(pag); - if (error) - return -ENOENT; - } - error = -EFSCORRUPTED; - fallthrough; - default: - trace_xchk_op_error(sc, - XFS_INO_TO_AGNO(mp, sc->sm->sm_ino), - XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino), - error, __return_address); + if (!error) + return xchk_install_handle_inode(sc, ip); + if (error == -ENOENT) return error; + if (error != -EINVAL) + goto out_error; + + /* + * EINVAL with IGET_UNTRUSTED probably means one of several things: + * userspace gave us an inode number that doesn't correspond to fs + * space; the inode btree lacks a record for this inode; or there is a + * record, and it says this inode is free. + * + * We want to look up this inode in the inobt to distinguish two + * scenarios: (1) the inobt says the inode is free, in which case + * there's nothing to do; and (2) the inobt says the inode is + * allocated, but loading it failed due to corruption. + * + * Allocate a transaction and grab the AGI to prevent inobt activity + * in this AG. Retry the iget in case someone allocated a new inode + * after the first iget failed. + */ + error = xchk_trans_alloc(sc, 0); + if (error) + goto out_error; + + error = xchk_iget_agi(sc, sc->sm->sm_ino, &agi_bp, &ip); + if (error == 0) { + /* Actually got the inode, so install it. */ + xchk_trans_cancel(sc); + return xchk_install_handle_inode(sc, ip); } - if (VFS_I(ip)->i_generation != sc->sm->sm_gen) { - xchk_irele(sc, ip); - return -ENOENT; + if (error == -ENOENT) + goto out_gone; + if (error != -EINVAL) + goto out_cancel; + + /* Ensure that we have protected against inode allocation/freeing. */ + if (agi_bp == NULL) { + ASSERT(agi_bp != NULL); + error = -ECANCELED; + goto out_cancel; } - sc->ip = ip; - return 0; + /* + * Untrusted iget failed a second time. Let's try an inobt lookup. + * If the inobt thinks this the inode neither can exist inside the + * filesystem nor is allocated, return ENOENT to signal that the check + * can be skipped. + * + * If the lookup returns corruption, we'll mark this inode corrupt and + * exit to userspace. There's little chance of fixing anything until + * the inobt is straightened out, but there's nothing we can do here. + * + * If the lookup encounters any other error, exit to userspace. + * + * If the lookup succeeds, something else must be very wrong in the fs + * such that setting up the incore inode failed in some strange way. + * Treat those as corruptions. + */ + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino)); + if (!pag) { + error = -EFSCORRUPTED; + goto out_cancel; + } + + error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap, + XFS_IGET_UNTRUSTED); + xfs_perag_put(pag); + if (error == -EINVAL || error == -ENOENT) + goto out_gone; + if (!error) + error = -EFSCORRUPTED; + +out_cancel: + xchk_trans_cancel(sc); +out_error: + trace_xchk_op_error(sc, agno, XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino), + error, __return_address); + return error; +out_gone: + /* The file is gone, so there's nothing to check. */ + xchk_trans_cancel(sc); + return -ENOENT; } /* Release an inode, possibly dropping it in the process. */ diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 7e9e8b7b6cb0..5c76614c2c04 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -32,6 +32,8 @@ xchk_should_terminate( } int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks); +void xchk_trans_cancel(struct xfs_scrub *sc); + bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno, xfs_agblock_t bno, int *error); bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork, @@ -138,6 +140,8 @@ int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks); void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp); int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp); +int xchk_iget_agi(struct xfs_scrub *sc, xfs_ino_t inum, + struct xfs_buf **agi_bpp, struct xfs_inode **ipp); void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip); /* diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index c9a7e270a428..351849fc18ff 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -767,7 +767,8 @@ xfs_iget( return 0; out_error_or_again: - if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) { + if (!(flags & (XFS_IGET_INCORE | XFS_IGET_NORETRY)) && + error == -EAGAIN) { delay(1); goto again; } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 6cd180721659..87910191a9dd 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -34,10 +34,13 @@ struct xfs_icwalk { /* * Flags for xfs_iget() */ -#define XFS_IGET_CREATE 0x1 -#define XFS_IGET_UNTRUSTED 0x2 -#define XFS_IGET_DONTCACHE 0x4 -#define XFS_IGET_INCORE 0x8 /* don't read from disk or reinit */ +#define XFS_IGET_CREATE (1U << 0) +#define XFS_IGET_UNTRUSTED (1U << 1) +#define XFS_IGET_DONTCACHE (1U << 2) +/* don't read from disk or reinit */ +#define XFS_IGET_INCORE (1U << 3) +/* Return -EAGAIN immediately if the inode is unavailable. */ +#define XFS_IGET_NORETRY (1U << 4) int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino, uint flags, uint lock_flags, xfs_inode_t **ipp); -- GitLab From 46e0dd89659923dd02cfa45080675fc4f0926528 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:21 -0700 Subject: [PATCH 2597/5631] xfs: rename xchk_get_inode -> xchk_iget_for_scrubbing Dave Chinner suggested renaming this function to make more obvious what it does. The function returns an incore inode to callers that want to scrub a metadata structure that hangs off an inode. If the iget fails with EINVAL, it will single-step the loading process to distinguish between actually free inodes or impossible inumbers (ENOENT); discrepancies between the inobt freemask and the free status in the inode record (EFSCORRUPTED). Any other negative errno is returned unchanged. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 2 +- fs/xfs/scrub/common.c | 12 +++++++----- fs/xfs/scrub/common.h | 2 +- fs/xfs/scrub/inode.c | 2 +- 4 files changed, 10 insertions(+), 8 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 2412dcf0fa9a..9cf66a5c2376 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -34,7 +34,7 @@ xchk_setup_inode_bmap( if (xchk_need_intent_drain(sc)) xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); - error = xchk_get_inode(sc); + error = xchk_iget_for_scrubbing(sc); if (error) goto out; diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 3fd437430cad..8dd9ab31ebc6 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -832,12 +832,14 @@ xchk_install_handle_inode( } /* - * Given an inode and the scrub control structure, grab either the - * inode referenced in the control structure or the inode passed in. - * The inode is not locked. + * In preparation to scrub metadata structures that hang off of an inode, + * grab either the inode referenced in the scrub control structure or the + * inode passed in. If the inumber does not reference an allocated inode + * record, the function returns ENOENT to end the scrub early. The inode + * is not locked. */ int -xchk_get_inode( +xchk_iget_for_scrubbing( struct xfs_scrub *sc) { struct xfs_imap imap; @@ -994,7 +996,7 @@ xchk_setup_inode_contents( { int error; - error = xchk_get_inode(sc); + error = xchk_iget_for_scrubbing(sc); if (error) return error; diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 5c76614c2c04..bfe4deb2c33d 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -135,7 +135,7 @@ int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur, const struct xfs_owner_info *oinfo, xfs_filblks_t *blocks); int xchk_setup_ag_btree(struct xfs_scrub *sc, bool force_log); -int xchk_get_inode(struct xfs_scrub *sc); +int xchk_iget_for_scrubbing(struct xfs_scrub *sc); int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks); void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp); diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 2db96c8a71dc..424a35766732 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -39,7 +39,7 @@ xchk_setup_inode( * Try to get the inode. If the verifiers fail, we try again * in raw mode. */ - error = xchk_get_inode(sc); + error = xchk_iget_for_scrubbing(sc); switch (error) { case 0: break; -- GitLab From 38bb13108479f5cac955bb291ea6aa6d24268f4f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:22 -0700 Subject: [PATCH 2598/5631] xfs: retain the AGI when we can't iget an inode to scrub the core xchk_get_inode is not quite the right function to be calling from the inode scrubber setup function. The common get_inode function either gets an inode and installs it in the scrub context, or it returns an error code explaining what happened. This is acceptable for most file scrubbers because it is not in their scope to fix corruptions in the inode core and fork areas that cause iget to fail. Dealing with these problems is within the scope of the inode scrubber, however. If iget fails with EFSCORRUPTED, we need to xchk_inode to flag that as corruption. Since we can't get our hands on an incore inode, we need to hold the AGI to prevent inode allocation activity so that nothing changes in the inode metadata. Looking ahead to the inode core repair patches, we will also need to hold the AGI buffer into xrep_inode so that we can make modifications to the xfs_dinode structure without any other thread swooping in to allocate or free the inode. Adapt the xchk_get_inode into xchk_setup_inode since this is a one-off use case where the error codes we check for are a little different, and the return state is much different from the common function. xchk_setup_inode prepares to check or repair an inode record, so it must continue the scrub operation even if the inode/inobt verifiers cause xfs_iget to return EFSCORRUPTED. This is done by attaching the locked AGI buffer to the scrub transaction and returning 0 to move on to the actual scrub. (Later, the online inode repair code will also want the xfs_imap structure so that it can reset the ondisk xfs_dinode structure.) xchk_get_inode retrieves an inode on behalf of a scrubber that operates on an incore inode -- data/attr/cow forks, directories, xattrs, symlinks, parent pointers, etc. If the inode/inobt verifiers fail and xfs_iget returns EFSCORRUPTED, we want to exit to userspace (because the caller should be fix the inode first) and drop everything we acquired along the way. A behavior common to both functions is that it's possible that xfs_scrub asked for a scrub-by-handle concurrent with the inode being freed or the passed-in inumber is invalid. In this case, we call xfs_imap to see if the inobt index thinks the inode is allocated, and return ENOENT ("nothing to check here") to userspace if this is not the case. The imap lookup is why both functions call xchk_iget_agi. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/common.c | 2 +- fs/xfs/scrub/common.h | 1 + fs/xfs/scrub/inode.c | 177 ++++++++++++++++++++++++++++++++++++------ 3 files changed, 156 insertions(+), 24 deletions(-) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 8dd9ab31ebc6..b3ba87c4bc79 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -817,7 +817,7 @@ xchk_iget_agi( } /* Install an inode that we opened by handle for scrubbing. */ -static int +int xchk_install_handle_inode( struct xfs_scrub *sc, struct xfs_inode *ip) diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index bfe4deb2c33d..18b5f2b62f13 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -143,6 +143,7 @@ int xchk_iget(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_inode **ipp); int xchk_iget_agi(struct xfs_scrub *sc, xfs_ino_t inum, struct xfs_buf **agi_bpp, struct xfs_inode **ipp); void xchk_irele(struct xfs_scrub *sc, struct xfs_inode *ip); +int xchk_install_handle_inode(struct xfs_scrub *sc, struct xfs_inode *ip); /* * Don't bother cross-referencing if we already found corruption or cross diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 424a35766732..74ded772cb8f 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -11,8 +11,11 @@ #include "xfs_mount.h" #include "xfs_btree.h" #include "xfs_log_format.h" +#include "xfs_trans.h" +#include "xfs_ag.h" #include "xfs_inode.h" #include "xfs_ialloc.h" +#include "xfs_icache.h" #include "xfs_da_format.h" #include "xfs_reflink.h" #include "xfs_rmap.h" @@ -20,48 +23,176 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" +#include "scrub/trace.h" + +/* Prepare the attached inode for scrubbing. */ +static inline int +xchk_prepare_iscrub( + struct xfs_scrub *sc) +{ + int error; + + sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; + xfs_ilock(sc->ip, sc->ilock_flags); + + error = xchk_trans_alloc(sc, 0); + if (error) + return error; + + sc->ilock_flags |= XFS_ILOCK_EXCL; + xfs_ilock(sc->ip, XFS_ILOCK_EXCL); + return 0; +} + +/* Install this scrub-by-handle inode and prepare it for scrubbing. */ +static inline int +xchk_install_handle_iscrub( + struct xfs_scrub *sc, + struct xfs_inode *ip) +{ + int error; + + error = xchk_install_handle_inode(sc, ip); + if (error) + return error; + + return xchk_prepare_iscrub(sc); +} /* - * Grab total control of the inode metadata. It doesn't matter here if - * the file data is still changing; exclusive access to the metadata is - * the goal. + * Grab total control of the inode metadata. In the best case, we grab the + * incore inode and take all locks on it. If the incore inode cannot be + * constructed due to corruption problems, lock the AGI so that we can single + * step the loading process to fix everything that can go wrong. */ int xchk_setup_inode( struct xfs_scrub *sc) { + struct xfs_imap imap; + struct xfs_inode *ip; + struct xfs_mount *mp = sc->mp; + struct xfs_inode *ip_in = XFS_I(file_inode(sc->file)); + struct xfs_buf *agi_bp; + struct xfs_perag *pag; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, sc->sm->sm_ino); int error; if (xchk_need_intent_drain(sc)) xchk_fsgates_enable(sc, XCHK_FSGATES_DRAIN); + /* We want to scan the opened inode, so lock it and exit. */ + if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) { + sc->ip = ip_in; + return xchk_prepare_iscrub(sc); + } + + /* Reject internal metadata files and obviously bad inode numbers. */ + if (xfs_internal_inum(mp, sc->sm->sm_ino)) + return -ENOENT; + if (!xfs_verify_ino(sc->mp, sc->sm->sm_ino)) + return -ENOENT; + + /* Try a regular untrusted iget. */ + error = xchk_iget(sc, sc->sm->sm_ino, &ip); + if (!error) + return xchk_install_handle_iscrub(sc, ip); + if (error == -ENOENT) + return error; + if (error != -EFSCORRUPTED && error != -EFSBADCRC && error != -EINVAL) + goto out_error; + /* - * Try to get the inode. If the verifiers fail, we try again - * in raw mode. + * EINVAL with IGET_UNTRUSTED probably means one of several things: + * userspace gave us an inode number that doesn't correspond to fs + * space; the inode btree lacks a record for this inode; or there is + * a record, and it says this inode is free. + * + * EFSCORRUPTED/EFSBADCRC could mean that the inode was mappable, but + * some other metadata corruption (e.g. inode forks) prevented + * instantiation of the incore inode. Or it could mean the inobt is + * corrupt. + * + * We want to look up this inode in the inobt directly to distinguish + * three different scenarios: (1) the inobt says the inode is free, + * in which case there's nothing to do; (2) the inobt is corrupt so we + * should flag the corruption and exit to userspace to let it fix the + * inobt; and (3) the inobt says the inode is allocated, but loading it + * failed due to corruption. + * + * Allocate a transaction and grab the AGI to prevent inobt activity in + * this AG. Retry the iget in case someone allocated a new inode after + * the first iget failed. */ - error = xchk_iget_for_scrubbing(sc); - switch (error) { - case 0: - break; - case -EFSCORRUPTED: - case -EFSBADCRC: - return xchk_trans_alloc(sc, 0); - default: - return error; + error = xchk_trans_alloc(sc, 0); + if (error) + goto out_error; + + error = xchk_iget_agi(sc, sc->sm->sm_ino, &agi_bp, &ip); + if (error == 0) { + /* Actually got the incore inode, so install it and proceed. */ + xchk_trans_cancel(sc); + return xchk_install_handle_iscrub(sc, ip); + } + if (error == -ENOENT) + goto out_gone; + if (error != -EFSCORRUPTED && error != -EFSBADCRC && error != -EINVAL) + goto out_cancel; + + /* Ensure that we have protected against inode allocation/freeing. */ + if (agi_bp == NULL) { + ASSERT(agi_bp != NULL); + error = -ECANCELED; + goto out_cancel; } - /* Got the inode, lock it and we're ready to go. */ - sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; - xfs_ilock(sc->ip, sc->ilock_flags); - error = xchk_trans_alloc(sc, 0); + /* + * Untrusted iget failed a second time. Let's try an inobt lookup. + * If the inobt doesn't think this is an allocated inode then we'll + * return ENOENT to signal that the check can be skipped. + * + * If the lookup signals corruption, we'll mark this inode corrupt and + * exit to userspace. There's little chance of fixing anything until + * the inobt is straightened out, but there's nothing we can do here. + * + * If the lookup encounters a runtime error, exit to userspace. + */ + pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, sc->sm->sm_ino)); + if (!pag) { + error = -EFSCORRUPTED; + goto out_cancel; + } + + error = xfs_imap(pag, sc->tp, sc->sm->sm_ino, &imap, + XFS_IGET_UNTRUSTED); + xfs_perag_put(pag); + if (error == -EINVAL || error == -ENOENT) + goto out_gone; if (error) - goto out; - sc->ilock_flags |= XFS_ILOCK_EXCL; - xfs_ilock(sc->ip, XFS_ILOCK_EXCL); + goto out_cancel; -out: - /* scrub teardown will unlock and release the inode for us */ + /* + * The lookup succeeded. Chances are the ondisk inode is corrupt and + * preventing iget from reading it. Retain the scrub transaction and + * the AGI buffer to prevent anyone from allocating or freeing inodes. + * This ensures that we preserve the inconsistency between the inobt + * saying the inode is allocated and the icache being unable to load + * the inode until we can flag the corruption in xchk_inode. The + * scrub function has to note the corruption, since we're not really + * supposed to do that from the setup function. + */ + return 0; + +out_cancel: + xchk_trans_cancel(sc); +out_error: + trace_xchk_op_error(sc, agno, XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino), + error, __return_address); return error; +out_gone: + /* The file is gone, so there's nothing to check. */ + xchk_trans_cancel(sc); + return -ENOENT; } /* Inode core */ -- GitLab From 1fc7a0597d237c17b6501f8c33b76d3eaaae9079 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:22 -0700 Subject: [PATCH 2599/5631] xfs: don't take the MMAPLOCK when scrubbing file metadata The MMAPLOCK stabilizes mappings in a file's pagecache. Therefore, we do not need it to check directories, symlinks, extended attributes, or file-based metadata. Reduce its usage to the one case that requires it, which is when we want to scrub the data fork of a regular file. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 7 +++++-- fs/xfs/scrub/common.c | 11 ++++++++--- fs/xfs/scrub/inode.c | 2 +- 3 files changed, 14 insertions(+), 6 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 9cf66a5c2376..e485a546a758 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -38,8 +38,8 @@ xchk_setup_inode_bmap( if (error) goto out; - sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; - xfs_ilock(sc->ip, sc->ilock_flags); + sc->ilock_flags = XFS_IOLOCK_EXCL; + xfs_ilock(sc->ip, XFS_IOLOCK_EXCL); /* * We don't want any ephemeral data fork updates sitting around @@ -50,6 +50,9 @@ xchk_setup_inode_bmap( sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) { struct address_space *mapping = VFS_I(sc->ip)->i_mapping; + sc->ilock_flags |= XFS_MMAPLOCK_EXCL; + xfs_ilock(sc->ip, XFS_MMAPLOCK_EXCL); + inode_dio_wait(VFS_I(sc->ip)); /* diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index b3ba87c4bc79..9aa79665c608 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -988,7 +988,11 @@ xchk_irele( xfs_irele(ip); } -/* Set us up to scrub a file's contents. */ +/* + * Set us up to scrub metadata mapped by a file's fork. Callers must not use + * this to operate on user-accessible regular file data because the MMAPLOCK is + * not taken. + */ int xchk_setup_inode_contents( struct xfs_scrub *sc, @@ -1000,9 +1004,10 @@ xchk_setup_inode_contents( if (error) return error; - /* Got the inode, lock it and we're ready to go. */ - sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; + /* Lock the inode so the VFS cannot touch this file. */ + sc->ilock_flags = XFS_IOLOCK_EXCL; xfs_ilock(sc->ip, sc->ilock_flags); + error = xchk_trans_alloc(sc, resblks); if (error) goto out; diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index 74ded772cb8f..3e1e02e340a6 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -32,7 +32,7 @@ xchk_prepare_iscrub( { int error; - sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; + sc->ilock_flags = XFS_IOLOCK_EXCL; xfs_ilock(sc->ip, sc->ilock_flags); error = xchk_trans_alloc(sc, 0); -- GitLab From 971ee3a6706abf1074349c124922e4e4d513fa45 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:23 -0700 Subject: [PATCH 2600/5631] xfs: change bmap scrubber to store the previous mapping Convert the inode data/attr/cow fork scrubber to remember the entire previous mapping, not just the next expected offset. No behavior changes here, but this will enable some better checking in subsequent patches. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index e485a546a758..7b4d0e2736a2 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -96,11 +96,23 @@ xchk_setup_inode_bmap( struct xchk_bmap_info { struct xfs_scrub *sc; + + /* Incore extent tree cursor */ struct xfs_iext_cursor icur; - xfs_fileoff_t lastoff; + + /* Previous fork mapping that we examined */ + struct xfs_bmbt_irec prev_rec; + + /* Is this a realtime fork? */ bool is_rt; + + /* May mappings point to shared space? */ bool is_shared; + + /* Was the incore extent tree loaded? */ bool was_loaded; + + /* Which inode fork are we checking? */ int whichfork; }; @@ -405,7 +417,8 @@ xchk_bmap_iextent( * Check for out-of-order extents. This record could have come * from the incore list, for which there is no ordering check. */ - if (irec->br_startoff < info->lastoff) + if (irec->br_startoff < info->prev_rec.br_startoff + + info->prev_rec.br_blockcount) xchk_fblock_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -712,7 +725,8 @@ xchk_bmap_iextent_delalloc( * Check for out-of-order extents. This record could have come * from the incore list, for which there is no ordering check. */ - if (irec->br_startoff < info->lastoff) + if (irec->br_startoff < info->prev_rec.br_startoff + + info->prev_rec.br_blockcount) xchk_fblock_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -806,7 +820,6 @@ xchk_bmap( goto out; /* Scrub extent records. */ - info.lastoff = 0; ifp = xfs_ifork_ptr(ip, whichfork); for_each_xfs_iext(ifp, &info.icur, &irec) { if (xchk_should_terminate(sc, &error) || @@ -823,7 +836,7 @@ xchk_bmap( xchk_bmap_iextent_delalloc(ip, &info, &irec); else xchk_bmap_iextent(ip, &info, &irec); - info.lastoff = irec.br_startoff + irec.br_blockcount; + memcpy(&info.prev_rec, &irec, sizeof(struct xfs_bmbt_irec)); } error = xchk_bmap_check_rmaps(sc, whichfork); -- GitLab From 634d4a79e76691020ba73f50416da37a30779e9e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:24 -0700 Subject: [PATCH 2601/5631] xfs: accumulate iextent records when checking bmap Currently, the bmap scrubber checks file fork mappings individually. In the case that the file uses multiple mappings to a single contiguous piece of space, the scrubber repeatedly locks the AG to check the existence of a reverse mapping that overlaps this file mapping. If the reverse mapping starts before or ends after the mapping we're checking, it will also crawl around in the bmbt checking correspondence for adjacent extents. This is not very time efficient because it does the crawling while holding the AGF buffer, and checks the middle mappings multiple times. Instead, create a custom iextent record iterator function that combines multiple adjacent allocated mappings into one large incore bmbt record. This is feasible because the incore bmbt record length is 64-bits wide. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.h | 2 +- fs/xfs/scrub/bmap.c | 183 +++++++++++++++++++++++---------------- 2 files changed, 107 insertions(+), 78 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index 9ff030d12981..e33470e39728 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -145,7 +145,7 @@ static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags) { BMAP_COWFORK, "COW" } /* Return true if the extent is an allocated extent, written or not. */ -static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec) +static inline bool xfs_bmap_is_real_extent(const struct xfs_bmbt_irec *irec) { return irec->br_startblock != HOLESTARTBLOCK && irec->br_startblock != DELAYSTARTBLOCK && diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 7b4d0e2736a2..4bda1b0ee122 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -165,48 +165,6 @@ xchk_bmap_get_rmap( return has_rmap; } -static inline bool -xchk_bmap_has_prev( - struct xchk_bmap_info *info, - struct xfs_bmbt_irec *irec) -{ - struct xfs_bmbt_irec got; - struct xfs_ifork *ifp; - - ifp = xfs_ifork_ptr(info->sc->ip, info->whichfork); - - if (!xfs_iext_peek_prev_extent(ifp, &info->icur, &got)) - return false; - if (got.br_startoff + got.br_blockcount != irec->br_startoff) - return false; - if (got.br_startblock + got.br_blockcount != irec->br_startblock) - return false; - if (got.br_state != irec->br_state) - return false; - return true; -} - -static inline bool -xchk_bmap_has_next( - struct xchk_bmap_info *info, - struct xfs_bmbt_irec *irec) -{ - struct xfs_bmbt_irec got; - struct xfs_ifork *ifp; - - ifp = xfs_ifork_ptr(info->sc->ip, info->whichfork); - - if (!xfs_iext_peek_next_extent(ifp, &info->icur, &got)) - return false; - if (irec->br_startoff + irec->br_blockcount != got.br_startoff) - return false; - if (irec->br_startblock + irec->br_blockcount != got.br_startblock) - return false; - if (got.br_state != irec->br_state) - return false; - return true; -} - /* Make sure that we have rmapbt records for this extent. */ STATIC void xchk_bmap_xref_rmap( @@ -277,31 +235,20 @@ xchk_bmap_xref_rmap( irec->br_startoff); /* - * If the rmap starts before this bmbt record, make sure there's a bmbt - * record for the previous offset that is contiguous with this mapping. - * Skip this for CoW fork extents because the refcount btree (and not - * the inode) is the ondisk owner for those extents. - */ - if (info->whichfork != XFS_COW_FORK && rmap.rm_startblock < agbno && - !xchk_bmap_has_prev(info, irec)) { - xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); - return; - } - - /* - * If the rmap ends after this bmbt record, make sure there's a bmbt - * record for the next offset that is contiguous with this mapping. - * Skip this for CoW fork extents because the refcount btree (and not - * the inode) is the ondisk owner for those extents. + * The rmap must correspond exactly with this bmbt record. Skip this + * for CoW fork extents because the refcount btree (and not the inode) + * is the ondisk owner for those extents. */ - rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (info->whichfork != XFS_COW_FORK && - rmap_end > agbno + irec->br_blockcount && - !xchk_bmap_has_next(info, irec)) { - xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); - return; + if (info->whichfork != XFS_COW_FORK) { + if (rmap.rm_startblock != agbno) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + + rmap_end = (unsigned long long)rmap.rm_startblock + + rmap.rm_blockcount; + if (rmap_end != agbno + irec->br_blockcount) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); } } @@ -428,15 +375,7 @@ xchk_bmap_iextent( xchk_bmap_dirattr_extent(ip, info, irec); - /* There should never be a "hole" extent in either extent list. */ - if (irec->br_startblock == HOLESTARTBLOCK) - xchk_fblock_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); - /* Make sure the extent points to a valid place. */ - if (irec->br_blockcount > XFS_MAX_BMBT_EXTLEN) - xchk_fblock_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); if (info->is_rt && !xfs_verify_rtext(mp, irec->br_startblock, irec->br_blockcount)) xchk_fblock_set_corrupt(info->sc, info->whichfork, @@ -740,6 +679,90 @@ xchk_bmap_iextent_delalloc( irec->br_startoff); } +/* Decide if this individual fork mapping is ok. */ +static bool +xchk_bmap_iext_mapping( + struct xchk_bmap_info *info, + const struct xfs_bmbt_irec *irec) +{ + /* There should never be a "hole" extent in either extent list. */ + if (irec->br_startblock == HOLESTARTBLOCK) + return false; + if (irec->br_blockcount > XFS_MAX_BMBT_EXTLEN) + return false; + return true; +} + +/* Are these two mappings contiguous with each other? */ +static inline bool +xchk_are_bmaps_contiguous( + const struct xfs_bmbt_irec *b1, + const struct xfs_bmbt_irec *b2) +{ + /* Don't try to combine unallocated mappings. */ + if (!xfs_bmap_is_real_extent(b1)) + return false; + if (!xfs_bmap_is_real_extent(b2)) + return false; + + /* Does b2 come right after b1 in the logical and physical range? */ + if (b1->br_startoff + b1->br_blockcount != b2->br_startoff) + return false; + if (b1->br_startblock + b1->br_blockcount != b2->br_startblock) + return false; + if (b1->br_state != b2->br_state) + return false; + return true; +} + +/* + * Walk the incore extent records, accumulating consecutive contiguous records + * into a single incore mapping. Returns true if @irec has been set to a + * mapping or false if there are no more mappings. Caller must ensure that + * @info.icur is zeroed before the first call. + */ +static int +xchk_bmap_iext_iter( + struct xchk_bmap_info *info, + struct xfs_bmbt_irec *irec) +{ + struct xfs_bmbt_irec got; + struct xfs_ifork *ifp; + + ifp = xfs_ifork_ptr(info->sc->ip, info->whichfork); + + /* Advance to the next iextent record and check the mapping. */ + xfs_iext_next(ifp, &info->icur); + if (!xfs_iext_get_extent(ifp, &info->icur, irec)) + return false; + + if (!xchk_bmap_iext_mapping(info, irec)) { + xchk_fblock_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + return false; + } + + /* + * Iterate subsequent iextent records and merge them with the one + * that we just read, if possible. + */ + while (xfs_iext_peek_next_extent(ifp, &info->icur, &got)) { + if (!xchk_are_bmaps_contiguous(irec, &got)) + break; + + if (!xchk_bmap_iext_mapping(info, &got)) { + xchk_fblock_set_corrupt(info->sc, info->whichfork, + got.br_startoff); + return false; + } + + irec->br_blockcount += got.br_blockcount; + xfs_iext_next(ifp, &info->icur); + } + + return true; +} + /* * Scrub an inode fork's block mappings. * @@ -819,9 +842,15 @@ xchk_bmap( if (!xchk_fblock_process_error(sc, whichfork, 0, &error)) goto out; - /* Scrub extent records. */ - ifp = xfs_ifork_ptr(ip, whichfork); - for_each_xfs_iext(ifp, &info.icur, &irec) { + /* + * Scrub extent records. We use a special iterator function here that + * combines adjacent mappings if they are logically and physically + * contiguous. For large allocations that require multiple bmbt + * records, this reduces the number of cross-referencing calls, which + * reduces runtime. Cross referencing with the rmap is simpler because + * the rmap must match the combined mapping exactly. + */ + while (xchk_bmap_iext_iter(&info, &irec)) { if (xchk_should_terminate(sc, &error) || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) goto out; -- GitLab From c0d5a92f7aaf41b1ab70869358d534757b569a1f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:24 -0700 Subject: [PATCH 2602/5631] xfs: split xchk_bmap_xref_rmap into two functions There's more special-cased functionality than not in this function. Split it into two so that each can be far more cohesive. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 116 +++++++++++++++++++++++++++++--------------- 1 file changed, 76 insertions(+), 40 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 4bda1b0ee122..912b67d2321b 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -165,7 +165,7 @@ xchk_bmap_get_rmap( return has_rmap; } -/* Make sure that we have rmapbt records for this extent. */ +/* Make sure that we have rmapbt records for this data/attr fork extent. */ STATIC void xchk_bmap_xref_rmap( struct xchk_bmap_info *info, @@ -174,41 +174,39 @@ xchk_bmap_xref_rmap( { struct xfs_rmap_irec rmap; unsigned long long rmap_end; - uint64_t owner; + uint64_t owner = info->sc->ip->i_ino; if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) return; - if (info->whichfork == XFS_COW_FORK) - owner = XFS_RMAP_OWN_COW; - else - owner = info->sc->ip->i_ino; - /* Find the rmap record for this irec. */ if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) return; - /* Check the rmap. */ + /* + * The rmap must be an exact match for this incore file mapping record, + * which may have arisen from multiple ondisk records. + */ + if (rmap.rm_startblock != agbno) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; - if (rmap.rm_startblock > agbno || - agbno + irec->br_blockcount > rmap_end) + if (rmap_end != agbno + irec->br_blockcount) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - /* - * Check the logical offsets if applicable. CoW staging extents - * don't track logical offsets since the mappings only exist in - * memory. - */ - if (info->whichfork != XFS_COW_FORK) { - rmap_end = (unsigned long long)rmap.rm_offset + - rmap.rm_blockcount; - if (rmap.rm_offset > irec->br_startoff || - irec->br_startoff + irec->br_blockcount > rmap_end) - xchk_fblock_xref_set_corrupt(info->sc, - info->whichfork, irec->br_startoff); - } + /* Check the logical offsets. */ + if (rmap.rm_offset != irec->br_startoff) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + + rmap_end = (unsigned long long)rmap.rm_offset + rmap.rm_blockcount; + if (rmap_end != irec->br_startoff + irec->br_blockcount) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + /* Check the owner */ if (rmap.rm_owner != owner) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -220,8 +218,7 @@ xchk_bmap_xref_rmap( * records because the blocks are owned (on-disk) by the refcountbt, * which doesn't track unwritten state. */ - if (owner != XFS_RMAP_OWN_COW && - !!(irec->br_state == XFS_EXT_UNWRITTEN) != + if (!!(irec->br_state == XFS_EXT_UNWRITTEN) != !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); @@ -233,23 +230,60 @@ xchk_bmap_xref_rmap( if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); +} + +/* Make sure that we have rmapbt records for this COW fork extent. */ +STATIC void +xchk_bmap_xref_rmap_cow( + struct xchk_bmap_info *info, + struct xfs_bmbt_irec *irec, + xfs_agblock_t agbno) +{ + struct xfs_rmap_irec rmap; + unsigned long long rmap_end; + uint64_t owner = XFS_RMAP_OWN_COW; + + if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm)) + return; + + /* Find the rmap record for this irec. */ + if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap)) + return; /* - * The rmap must correspond exactly with this bmbt record. Skip this - * for CoW fork extents because the refcount btree (and not the inode) - * is the ondisk owner for those extents. + * CoW staging extents are owned by the refcount btree, so the rmap + * can start before and end after the physical space allocated to this + * mapping. There are no offsets to check. */ - if (info->whichfork != XFS_COW_FORK) { - if (rmap.rm_startblock != agbno) - xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); - - rmap_end = (unsigned long long)rmap.rm_startblock + - rmap.rm_blockcount; - if (rmap_end != agbno + irec->br_blockcount) - xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, - irec->br_startoff); - } + if (rmap.rm_startblock > agbno) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + + rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount; + if (rmap_end < agbno + irec->br_blockcount) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + + /* Check the owner */ + if (rmap.rm_owner != owner) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + + /* + * No flags allowed. Note that the (in-memory) CoW fork distinguishes + * between unwritten and written extents, but we don't track that in + * the rmap records because the blocks are owned (on-disk) by the + * refcountbt, which doesn't track unwritten state. + */ + if (rmap.rm_flags & XFS_RMAP_ATTR_FORK) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); + if (rmap.rm_flags & XFS_RMAP_UNWRITTEN) + xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, + irec->br_startoff); } /* Cross-reference a single rtdev extent record. */ @@ -288,9 +322,9 @@ xchk_bmap_iextent_xref( xchk_xref_is_used_space(info->sc, agbno, len); xchk_xref_is_not_inode_chunk(info->sc, agbno, len); - xchk_bmap_xref_rmap(info, irec, agbno); switch (info->whichfork) { case XFS_DATA_FORK: + xchk_bmap_xref_rmap(info, irec, agbno); if (!xfs_is_reflink_inode(info->sc->ip)) { xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, info->whichfork, irec->br_startoff); @@ -303,6 +337,7 @@ xchk_bmap_iextent_xref( irec->br_blockcount); break; case XFS_ATTR_FORK: + xchk_bmap_xref_rmap(info, irec, agbno); xfs_rmap_ino_owner(&oinfo, info->sc->ip->i_ino, info->whichfork, irec->br_startoff); xchk_xref_is_only_owned_by(info->sc, agbno, irec->br_blockcount, @@ -313,6 +348,7 @@ xchk_bmap_iextent_xref( irec->br_blockcount); break; case XFS_COW_FORK: + xchk_bmap_xref_rmap_cow(info, irec, agbno); xchk_xref_is_only_owned_by(info->sc, agbno, irec->br_blockcount, &XFS_RMAP_OINFO_COW); xchk_xref_is_cow_staging(info->sc, agbno, -- GitLab From 336642f79283715e4535bfaa05f5593dd91da6e8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:25 -0700 Subject: [PATCH 2603/5631] xfs: alert the user about data/attr fork mappings that could be merged If the data or attr forks have mappings that could be merged, let the user know that the structure could be optimized. This isn't a filesystem corruption since the regular filesystem does not try to be smart about merging bmbt records. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 912b67d2321b..a2edcf8cc779 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -764,6 +764,7 @@ xchk_bmap_iext_iter( { struct xfs_bmbt_irec got; struct xfs_ifork *ifp; + xfs_filblks_t prev_len; ifp = xfs_ifork_ptr(info->sc->ip, info->whichfork); @@ -782,6 +783,7 @@ xchk_bmap_iext_iter( * Iterate subsequent iextent records and merge them with the one * that we just read, if possible. */ + prev_len = irec->br_blockcount; while (xfs_iext_peek_next_extent(ifp, &info->icur, &got)) { if (!xchk_are_bmaps_contiguous(irec, &got)) break; @@ -792,7 +794,16 @@ xchk_bmap_iext_iter( return false; } + /* + * Notify the user of mergeable records in the data or attr + * forks. CoW forks only exist in memory so we ignore them. + */ + if (info->whichfork != XFS_COW_FORK && + prev_len + got.br_blockcount > BMBT_BLOCKCOUNT_MASK) + xchk_ino_set_preen(info->sc, info->sc->ip->i_ino); + irec->br_blockcount += got.br_blockcount; + prev_len = got.br_blockcount; xfs_iext_next(ifp, &info->icur); } -- GitLab From e8882f69b941b20704ea509ebfca2d8a123ad6e3 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:25 -0700 Subject: [PATCH 2604/5631] xfs: split the xchk_bmap_check_rmaps into a predicate This function has two parts: the second part scans every reverse mapping record for this file fork to make sure that there's a corresponding mapping in the fork, and the first part decides if we even want to do that. Split the first part into a separate predicate so that we can make more changes to it in the next patch. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 60 ++++++++++++++++++++++++++++----------------- 1 file changed, 38 insertions(+), 22 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index a2edcf8cc779..64ed5b6585d5 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -635,28 +635,28 @@ xchk_bmap_check_ag_rmaps( return error; } -/* Make sure each rmap has a corresponding bmbt entry. */ -STATIC int -xchk_bmap_check_rmaps( - struct xfs_scrub *sc, - int whichfork) +/* + * Decide if we want to walk every rmap btree in the fs to make sure that each + * rmap for this file fork has corresponding bmbt entries. + */ +static bool +xchk_bmap_want_check_rmaps( + struct xchk_bmap_info *info) { - struct xfs_ifork *ifp = xfs_ifork_ptr(sc->ip, whichfork); - struct xfs_perag *pag; - xfs_agnumber_t agno; + struct xfs_scrub *sc = info->sc; + struct xfs_ifork *ifp; bool zero_size; - int error; - if (!xfs_has_rmapbt(sc->mp) || - whichfork == XFS_COW_FORK || - (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) - return 0; + if (!xfs_has_rmapbt(sc->mp)) + return false; + if (info->whichfork == XFS_COW_FORK) + return false; + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return false; /* Don't support realtime rmap checks yet. */ - if (XFS_IS_REALTIME_INODE(sc->ip) && whichfork == XFS_DATA_FORK) - return 0; - - ASSERT(xfs_ifork_ptr(sc->ip, whichfork) != NULL); + if (info->is_rt) + return false; /* * Only do this for complex maps that are in btree format, or for @@ -666,14 +666,28 @@ xchk_bmap_check_rmaps( * reattached. */ - if (whichfork == XFS_DATA_FORK) + if (info->whichfork == XFS_DATA_FORK) zero_size = i_size_read(VFS_I(sc->ip)) == 0; else zero_size = false; + ifp = xfs_ifork_ptr(sc->ip, info->whichfork); if (ifp->if_format != XFS_DINODE_FMT_BTREE && (zero_size || ifp->if_nextents > 0)) - return 0; + return false; + + return true; +} + +/* Make sure each rmap has a corresponding bmbt entry. */ +STATIC int +xchk_bmap_check_rmaps( + struct xfs_scrub *sc, + int whichfork) +{ + struct xfs_perag *pag; + xfs_agnumber_t agno; + int error; for_each_perag(sc->mp, agno, pag) { error = xchk_bmap_check_ag_rmaps(sc, whichfork, pag); @@ -915,9 +929,11 @@ xchk_bmap( memcpy(&info.prev_rec, &irec, sizeof(struct xfs_bmbt_irec)); } - error = xchk_bmap_check_rmaps(sc, whichfork); - if (!xchk_fblock_xref_process_error(sc, whichfork, 0, &error)) - goto out; + if (xchk_bmap_want_check_rmaps(&info)) { + error = xchk_bmap_check_rmaps(sc, whichfork); + if (!xchk_fblock_xref_process_error(sc, whichfork, 0, &error)) + goto out; + } out: return error; } -- GitLab From d5784ae82778d94a18aba25ccbddc16f8ae13001 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:26 -0700 Subject: [PATCH 2605/5631] xfs: flag free space btree records that could be merged Complain if we encounter free space btree records that could be merged. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/alloc.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 12dd55ac2a4f..279af72b1671 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -31,6 +31,12 @@ xchk_setup_ag_allocbt( } /* Free space btree scrubber. */ + +struct xchk_alloc { + /* Previous free space extent. */ + struct xfs_alloc_rec_incore prev; +}; + /* * Ensure there's a corresponding cntbt/bnobt record matching this * bnobt/cntbt record, respectively. @@ -93,6 +99,24 @@ xchk_allocbt_xref( xchk_xref_is_not_cow_staging(sc, agbno, len); } +/* Flag failures for records that could be merged. */ +STATIC void +xchk_allocbt_mergeable( + struct xchk_btree *bs, + struct xchk_alloc *ca, + const struct xfs_alloc_rec_incore *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (ca->prev.ar_blockcount > 0 && + ca->prev.ar_startblock + ca->prev.ar_blockcount == irec->ar_startblock && + ca->prev.ar_blockcount + irec->ar_blockcount < (uint32_t)~0U) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&ca->prev, irec, sizeof(*irec)); +} + /* Scrub a bnobt/cntbt record. */ STATIC int xchk_allocbt_rec( @@ -100,6 +124,7 @@ xchk_allocbt_rec( const union xfs_btree_rec *rec) { struct xfs_alloc_rec_incore irec; + struct xchk_alloc *ca = bs->private; xfs_alloc_btrec_to_irec(rec, &irec); if (xfs_alloc_check_irec(bs->cur, &irec) != NULL) { @@ -107,6 +132,7 @@ xchk_allocbt_rec( return 0; } + xchk_allocbt_mergeable(bs, ca, &irec); xchk_allocbt_xref(bs->sc, &irec); return 0; @@ -118,10 +144,11 @@ xchk_allocbt( struct xfs_scrub *sc, xfs_btnum_t which) { + struct xchk_alloc ca = { }; struct xfs_btree_cur *cur; cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur; - return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, NULL); + return xchk_btree(sc, cur, xchk_allocbt_rec, &XFS_RMAP_OINFO_AG, &ca); } int -- GitLab From 1e59fdb7d6157ff685a250e0873a015a2b16a4f2 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:26 -0700 Subject: [PATCH 2606/5631] xfs: don't call xchk_bmap_check_rmaps for btree-format file forks The logic at the end of xchk_bmap_want_check_rmaps tries to detect a file fork that has been zapped by what will become the online inode repair code. Zapped forks are in FMT_EXTENTS with zero extents, and some sort of hint that there's supposed to be data somewhere in the filesystem. Unfortunately, the inverted logic here is confusing and has the effect that we always call xchk_bmap_check_rmaps for FMT_BTREE forks. This is horribly inefficient and unnecessary, so invert the logic to get rid of this performance problem. This has caused 8h delays in generic/333 and generic/334. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 64ed5b6585d5..87ab9f95a487 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -645,7 +645,6 @@ xchk_bmap_want_check_rmaps( { struct xfs_scrub *sc = info->sc; struct xfs_ifork *ifp; - bool zero_size; if (!xfs_has_rmapbt(sc->mp)) return false; @@ -659,24 +658,23 @@ xchk_bmap_want_check_rmaps( return false; /* - * Only do this for complex maps that are in btree format, or for - * situations where we would seem to have a size but zero extents. - * The inode repair code can zap broken iforks, which means we have - * to flag this bmap as corrupt if there are rmaps that need to be - * reattached. + * The inode repair code zaps broken inode forks by resetting them back + * to EXTENTS format and zero extent records. If we encounter a fork + * in this state along with evidence that the fork isn't supposed to be + * empty, we need to scan the reverse mappings to decide if we're going + * to rebuild the fork. Data forks with nonzero file size are scanned. + * xattr forks are never empty of content, so they are always scanned. */ - - if (info->whichfork == XFS_DATA_FORK) - zero_size = i_size_read(VFS_I(sc->ip)) == 0; - else - zero_size = false; - ifp = xfs_ifork_ptr(sc->ip, info->whichfork); - if (ifp->if_format != XFS_DINODE_FMT_BTREE && - (zero_size || ifp->if_nextents > 0)) - return false; + if (ifp->if_format == XFS_DINODE_FMT_EXTENTS && ifp->if_nextents == 0) { + if (info->whichfork == XFS_DATA_FORK && + i_size_read(VFS_I(sc->ip)) == 0) + return false; - return true; + return true; + } + + return false; } /* Make sure each rmap has a corresponding bmbt entry. */ -- GitLab From db0502b39c21d1cab6b6778a416a5b407170be90 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:27 -0700 Subject: [PATCH 2607/5631] xfs: flag refcount btree records that could be merged Complain if we encounter refcount btree records that could be merged. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/refcount.c | 44 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index db9e46a4f8d4..ed5eb367ce49 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -333,6 +333,9 @@ xchk_refcountbt_xref( } struct xchk_refcbt_records { + /* Previous refcount record. */ + struct xfs_refcount_irec prev_rec; + /* The next AG block where we aren't expecting shared extents. */ xfs_agblock_t next_unshared_agbno; @@ -390,6 +393,46 @@ xchk_refcountbt_xref_gaps( xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur); } +static inline bool +xchk_refcount_mergeable( + struct xchk_refcbt_records *rrc, + const struct xfs_refcount_irec *r2) +{ + const struct xfs_refcount_irec *r1 = &rrc->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (r1->rc_blockcount > 0) + return false; + + if (r1->rc_domain != r2->rc_domain) + return false; + if (r1->rc_startblock + r1->rc_blockcount != r2->rc_startblock) + return false; + if (r1->rc_refcount != r2->rc_refcount) + return false; + if ((unsigned long long)r1->rc_blockcount + r2->rc_blockcount > + MAXREFCEXTLEN) + return false; + + return true; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_refcountbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_refcbt_records *rrc, + const struct xfs_refcount_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_refcount_mergeable(rrc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&rrc->prev_rec, irec, sizeof(struct xfs_refcount_irec)); +} + /* Scrub a refcountbt record. */ STATIC int xchk_refcountbt_rec( @@ -414,6 +457,7 @@ xchk_refcountbt_rec( xchk_btree_set_corrupt(bs->sc, bs->cur, 0); rrc->prev_domain = irec.rc_domain; + xchk_refcountbt_check_mergeable(bs, rrc, &irec); xchk_refcountbt_xref(bs->sc, &irec); /* -- GitLab From 29ab991b4fe9df3cb6f943bea9e256fbdfa93589 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:27 -0700 Subject: [PATCH 2608/5631] xfs: check overlapping rmap btree records The rmap btree scrubber doesn't contain sufficient checking for records that cannot overlap but do anyway. For the other btrees, this is enforced by the inorder checks in xchk_btree_rec, but the rmap btree is special because it allows overlapping records to handle shared data extents. Therefore, enhance the rmap btree record check function to compare each record against the previous one so that we can detect overlapping rmap records for space allocations that do not allow sharing. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/rmap.c | 74 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 72 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 18b64287158e..f7e0384a0e69 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -32,6 +32,15 @@ xchk_setup_ag_rmapbt( /* Reverse-mapping scrubber. */ +struct xchk_rmap { + /* + * The furthest-reaching of the rmapbt records that we've already + * processed. This enables us to detect overlapping records for space + * allocations that cannot be shared. + */ + struct xfs_rmap_irec overlap_rec; +}; + /* Cross-reference a rmap against the refcount btree. */ STATIC void xchk_rmapbt_xref_refc( @@ -139,12 +148,63 @@ xchk_rmapbt_check_unwritten_in_keyflags( } } +static inline bool +xchk_rmapbt_is_shareable( + struct xfs_scrub *sc, + const struct xfs_rmap_irec *irec) +{ + if (!xfs_has_reflink(sc->mp)) + return false; + if (XFS_RMAP_NON_INODE_OWNER(irec->rm_owner)) + return false; + if (irec->rm_flags & (XFS_RMAP_BMBT_BLOCK | XFS_RMAP_ATTR_FORK | + XFS_RMAP_UNWRITTEN)) + return false; + return true; +} + +/* Flag failures for records that overlap but cannot. */ +STATIC void +xchk_rmapbt_check_overlapping( + struct xchk_btree *bs, + struct xchk_rmap *cr, + const struct xfs_rmap_irec *irec) +{ + xfs_agblock_t pnext, inext; + + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + /* No previous record? */ + if (cr->overlap_rec.rm_blockcount == 0) + goto set_prev; + + /* Do overlap_rec and irec overlap? */ + pnext = cr->overlap_rec.rm_startblock + cr->overlap_rec.rm_blockcount; + if (pnext <= irec->rm_startblock) + goto set_prev; + + /* Overlap is only allowed if both records are data fork mappings. */ + if (!xchk_rmapbt_is_shareable(bs->sc, &cr->overlap_rec) || + !xchk_rmapbt_is_shareable(bs->sc, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + /* Save whichever rmap record extends furthest. */ + inext = irec->rm_startblock + irec->rm_blockcount; + if (pnext > inext) + return; + +set_prev: + memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec)); +} + /* Scrub an rmapbt record. */ STATIC int xchk_rmapbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { + struct xchk_rmap *cr = bs->private; struct xfs_rmap_irec irec; if (xfs_rmap_btrec_to_irec(rec, &irec) != NULL || @@ -154,6 +214,7 @@ xchk_rmapbt_rec( } xchk_rmapbt_check_unwritten_in_keyflags(bs); + xchk_rmapbt_check_overlapping(bs, cr, &irec); xchk_rmapbt_xref(bs->sc, &irec); return 0; } @@ -163,8 +224,17 @@ int xchk_rmapbt( struct xfs_scrub *sc) { - return xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec, - &XFS_RMAP_OINFO_AG, NULL); + struct xchk_rmap *cr; + int error; + + cr = kzalloc(sizeof(struct xchk_rmap), XCHK_GFP_FLAGS); + if (!cr) + return -ENOMEM; + + error = xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec, + &XFS_RMAP_OINFO_AG, cr); + kfree(cr); + return error; } /* xref check that the extent is owned only by a given owner */ -- GitLab From 1c1646afc96783702f92356846d6e47e0bbd6b11 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:28 -0700 Subject: [PATCH 2609/5631] xfs: check for reverse mapping records that could be merged Enhance the rmap scrubber to flag adjacent records that could be merged. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/rmap.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index f7e0384a0e69..6d7e294110a2 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -39,6 +39,12 @@ struct xchk_rmap { * allocations that cannot be shared. */ struct xfs_rmap_irec overlap_rec; + + /* + * The previous rmapbt record, so that we can check for two records + * that could be one. + */ + struct xfs_rmap_irec prev_rec; }; /* Cross-reference a rmap against the refcount btree. */ @@ -198,6 +204,51 @@ xchk_rmapbt_check_overlapping( memcpy(&cr->overlap_rec, irec, sizeof(struct xfs_rmap_irec)); } +/* Decide if two reverse-mapping records can be merged. */ +static inline bool +xchk_rmap_mergeable( + struct xchk_rmap *cr, + const struct xfs_rmap_irec *r2) +{ + const struct xfs_rmap_irec *r1 = &cr->prev_rec; + + /* Ignore if prev_rec is not yet initialized. */ + if (cr->prev_rec.rm_blockcount == 0) + return false; + + if (r1->rm_owner != r2->rm_owner) + return false; + if (r1->rm_startblock + r1->rm_blockcount != r2->rm_startblock) + return false; + if ((unsigned long long)r1->rm_blockcount + r2->rm_blockcount > + XFS_RMAP_LEN_MAX) + return false; + if (XFS_RMAP_NON_INODE_OWNER(r2->rm_owner)) + return true; + /* must be an inode owner below here */ + if (r1->rm_flags != r2->rm_flags) + return false; + if (r1->rm_flags & XFS_RMAP_BMBT_BLOCK) + return true; + return r1->rm_offset + r1->rm_blockcount == r2->rm_offset; +} + +/* Flag failures for records that could be merged. */ +STATIC void +xchk_rmapbt_check_mergeable( + struct xchk_btree *bs, + struct xchk_rmap *cr, + const struct xfs_rmap_irec *irec) +{ + if (bs->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return; + + if (xchk_rmap_mergeable(cr, irec)) + xchk_btree_set_corrupt(bs->sc, bs->cur, 0); + + memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec)); +} + /* Scrub an rmapbt record. */ STATIC int xchk_rmapbt_rec( @@ -214,6 +265,7 @@ xchk_rmapbt_rec( } xchk_rmapbt_check_unwritten_in_keyflags(bs); + xchk_rmapbt_check_mergeable(bs, cr, &irec); xchk_rmapbt_check_overlapping(bs, cr, &irec); xchk_rmapbt_xref(bs->sc, &irec); return 0; -- GitLab From c12ad41468a5f4112b98566dcb1ee9096579106a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:29 -0700 Subject: [PATCH 2610/5631] xfs: xattr scrub should ensure one namespace bit per name Check that each extended attribute exists in only one namespace. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 5573be3a3dfe..f6def9c864ab 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -128,10 +128,16 @@ xchk_xattr_listent( return; } + /* Only one namespace bit allowed. */ + if (hweight32(flags & XFS_ATTR_NSP_ONDISK_MASK) > 1) { + xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno); + goto fail_xref; + } + /* Does this name make sense? */ if (!xfs_attr_namecheck(name, namelen)) { xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK, args.blkno); - return; + goto fail_xref; } /* -- GitLab From ee366fe4f519f0739a2c62cf998f58932e77c6a9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:29 -0700 Subject: [PATCH 2611/5631] xfs: don't shadow @leaf in xchk_xattr_block Don't shadow the leaf variable here, because it's misleading to have one place in the codebase where two variables with different types have the same name. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index f6def9c864ab..6bb0256d0689 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -342,10 +342,10 @@ xchk_xattr_block( /* Check all the padding. */ if (xfs_has_crc(ds->sc->mp)) { - struct xfs_attr3_leafblock *leaf = bp->b_addr; + struct xfs_attr3_leafblock *leaf3 = bp->b_addr; - if (leaf->hdr.pad1 != 0 || leaf->hdr.pad2 != 0 || - leaf->hdr.info.hdr.pad != 0) + if (leaf3->hdr.pad1 != 0 || leaf3->hdr.pad2 != 0 || + leaf3->hdr.info.hdr.pad != 0) xchk_da_set_corrupt(ds, level); } else { if (leaf->hdr.pad1 != 0 || leaf->hdr.info.pad != 0) -- GitLab From 4cb76025208925f697de66ac4d2d821cafabd367 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:30 -0700 Subject: [PATCH 2612/5631] xfs: remove unnecessary dstmap in xattr scrubber Replace bitmap_and with bitmap_intersects in the xattr leaf block scrubber, since we only care if there's overlap between the used space bitmap and the free space bitmap. This means we don't need dstmap any more, and can thus reduce the memory requirements. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 7 +++---- fs/xfs/scrub/attr.h | 12 +----------- 2 files changed, 4 insertions(+), 15 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 6bb0256d0689..45fa8a5967de 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -36,10 +36,10 @@ xchk_setup_xattr_buf( /* * We need enough space to read an xattr value from the file or enough - * space to hold three copies of the xattr free space bitmap. We don't + * space to hold two copies of the xattr free space bitmap. We don't * need the buffer space for both purposes at the same time. */ - sz = 3 * sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); + sz = 2 * sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); sz = max_t(size_t, sz, value_size); /* @@ -223,7 +223,6 @@ xchk_xattr_check_freemap( struct xfs_attr3_icleaf_hdr *leafhdr) { unsigned long *freemap = xchk_xattr_freemap(sc); - unsigned long *dstmap = xchk_xattr_dstmap(sc); unsigned int mapsize = sc->mp->m_attr_geo->blksize; int i; @@ -237,7 +236,7 @@ xchk_xattr_check_freemap( } /* Look for bits that are set in freemap and are marked in use. */ - return bitmap_and(dstmap, freemap, map, mapsize) == 0; + return !bitmap_intersects(freemap, map, mapsize); } /* diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index bc6321552251..daf354a581bb 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -21,8 +21,7 @@ struct xchk_xattr_buf { * Each bitmap contains enough bits to track every byte in an attr * block (rounded up to the size of an unsigned long). The attr block * used space bitmap starts at the beginning of the buffer; the free - * space bitmap follows immediately after; and we have a third buffer - * for storing intermediate bitmap results. + * space bitmap follows immediately after. */ uint8_t buf[]; }; @@ -56,13 +55,4 @@ xchk_xattr_freemap( BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); } -/* A bitmap used to hold temporary results. */ -static inline unsigned long * -xchk_xattr_dstmap( - struct xfs_scrub *sc) -{ - return xchk_xattr_freemap(sc) + - BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); -} - #endif /* __XFS_SCRUB_ATTR_H__ */ -- GitLab From 91781ff549379a867d8fbe588a4c95f6598b1fa9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:30 -0700 Subject: [PATCH 2613/5631] xfs: split freemap from xchk_xattr_buf.buf Move the free space bitmap from somewhere in xchk_xattr_buf.buf[] to an explicit pointer. This is the start of removing the complex overloaded memory buffer that is the source of weird memory misuse bugs. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 40 ++++++++++++++++++++++++++++++++-------- fs/xfs/scrub/attr.h | 15 ++++----------- fs/xfs/scrub/scrub.c | 3 +++ fs/xfs/scrub/scrub.h | 10 ++++++++++ 4 files changed, 49 insertions(+), 19 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 45fa8a5967de..bc529b53a84f 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -20,6 +20,17 @@ #include "scrub/dabtree.h" #include "scrub/attr.h" +/* Free the buffers linked from the xattr buffer. */ +static void +xchk_xattr_buf_cleanup( + void *priv) +{ + struct xchk_xattr_buf *ab = priv; + + kvfree(ab->freemap); + ab->freemap = NULL; +} + /* * Allocate enough memory to hold an attr value and attr block bitmaps, * reallocating the buffer if necessary. Buffer contents are not preserved @@ -32,15 +43,18 @@ xchk_setup_xattr_buf( gfp_t flags) { size_t sz; + size_t bmp_sz; struct xchk_xattr_buf *ab = sc->buf; + unsigned long *old_freemap = NULL; + + bmp_sz = sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); /* * We need enough space to read an xattr value from the file or enough - * space to hold two copies of the xattr free space bitmap. We don't + * space to hold one copy of the xattr free space bitmap. We don't * need the buffer space for both purposes at the same time. */ - sz = 2 * sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); - sz = max_t(size_t, sz, value_size); + sz = max_t(size_t, bmp_sz, value_size); /* * If there's already a buffer, figure out if we need to reallocate it @@ -49,6 +63,7 @@ xchk_setup_xattr_buf( if (ab) { if (sz <= ab->sz) return 0; + old_freemap = ab->freemap; kvfree(ab); sc->buf = NULL; } @@ -60,9 +75,18 @@ xchk_setup_xattr_buf( ab = kvmalloc(sizeof(*ab) + sz, flags); if (!ab) return -ENOMEM; - ab->sz = sz; sc->buf = ab; + sc->buf_cleanup = xchk_xattr_buf_cleanup; + + if (old_freemap) { + ab->freemap = old_freemap; + } else { + ab->freemap = kvmalloc(bmp_sz, flags); + if (!ab->freemap) + return -ENOMEM; + } + return 0; } @@ -222,21 +246,21 @@ xchk_xattr_check_freemap( unsigned long *map, struct xfs_attr3_icleaf_hdr *leafhdr) { - unsigned long *freemap = xchk_xattr_freemap(sc); + struct xchk_xattr_buf *ab = sc->buf; unsigned int mapsize = sc->mp->m_attr_geo->blksize; int i; /* Construct bitmap of freemap contents. */ - bitmap_zero(freemap, mapsize); + bitmap_zero(ab->freemap, mapsize); for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { - if (!xchk_xattr_set_map(sc, freemap, + if (!xchk_xattr_set_map(sc, ab->freemap, leafhdr->freemap[i].base, leafhdr->freemap[i].size)) return false; } /* Look for bits that are set in freemap and are marked in use. */ - return !bitmap_intersects(freemap, map, mapsize); + return !bitmap_intersects(ab->freemap, map, mapsize); } /* diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index daf354a581bb..341855b3201b 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -10,6 +10,9 @@ * Temporary storage for online scrub and repair of extended attributes. */ struct xchk_xattr_buf { + /* Bitmap of free space in xattr leaf blocks. */ + unsigned long *freemap; + /* Size of @buf, in bytes. */ size_t sz; @@ -20,8 +23,7 @@ struct xchk_xattr_buf { * * Each bitmap contains enough bits to track every byte in an attr * block (rounded up to the size of an unsigned long). The attr block - * used space bitmap starts at the beginning of the buffer; the free - * space bitmap follows immediately after. + * used space bitmap starts at the beginning of the buffer. */ uint8_t buf[]; }; @@ -46,13 +48,4 @@ xchk_xattr_usedmap( return (unsigned long *)ab->buf; } -/* A bitmap of free space computed by walking attr leaf block free info. */ -static inline unsigned long * -xchk_xattr_freemap( - struct xfs_scrub *sc) -{ - return xchk_xattr_usedmap(sc) + - BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); -} - #endif /* __XFS_SCRUB_ATTR_H__ */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 03ec455318f4..02819bedc5b1 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -189,7 +189,10 @@ xchk_teardown( if (sc->flags & XCHK_REAPING_DISABLED) xchk_start_reaping(sc); if (sc->buf) { + if (sc->buf_cleanup) + sc->buf_cleanup(sc->buf); kvfree(sc->buf); + sc->buf_cleanup = NULL; sc->buf = NULL; } diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index c519927355fe..e71903474cd7 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -77,7 +77,17 @@ struct xfs_scrub { */ struct xfs_inode *ip; + /* Kernel memory buffer used by scrubbers; freed at teardown. */ void *buf; + + /* + * Clean up resources owned by whatever is in the buffer. Cleanup can + * be deferred with this hook as a means for scrub functions to pass + * data to repair functions. This function must not free the buffer + * itself. + */ + void (*buf_cleanup)(void *buf); + uint ilock_flags; /* See the XCHK/XREP state flags below. */ -- GitLab From 80069284b5eb63e48bc7cb9d4bd179711ae6e77a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:31 -0700 Subject: [PATCH 2614/5631] xfs: split usedmap from xchk_xattr_buf.buf Move the used space bitmap from somewhere in xchk_xattr_buf.buf[] to an explicit pointer. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 39 +++++++++++++++++++++------------------ fs/xfs/scrub/attr.h | 22 +++++----------------- 2 files changed, 26 insertions(+), 35 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index bc529b53a84f..65ec503c8a38 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -29,6 +29,8 @@ xchk_xattr_buf_cleanup( kvfree(ab->freemap); ab->freemap = NULL; + kvfree(ab->usedmap); + ab->usedmap = NULL; } /* @@ -42,20 +44,14 @@ xchk_setup_xattr_buf( size_t value_size, gfp_t flags) { - size_t sz; + size_t sz = value_size; size_t bmp_sz; struct xchk_xattr_buf *ab = sc->buf; + unsigned long *old_usedmap = NULL; unsigned long *old_freemap = NULL; bmp_sz = sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); - /* - * We need enough space to read an xattr value from the file or enough - * space to hold one copy of the xattr free space bitmap. We don't - * need the buffer space for both purposes at the same time. - */ - sz = max_t(size_t, bmp_sz, value_size); - /* * If there's already a buffer, figure out if we need to reallocate it * to accommodate a larger size. @@ -64,6 +60,7 @@ xchk_setup_xattr_buf( if (sz <= ab->sz) return 0; old_freemap = ab->freemap; + old_usedmap = ab->usedmap; kvfree(ab); sc->buf = NULL; } @@ -79,6 +76,14 @@ xchk_setup_xattr_buf( sc->buf = ab; sc->buf_cleanup = xchk_xattr_buf_cleanup; + if (old_usedmap) { + ab->usedmap = old_usedmap; + } else { + ab->usedmap = kvmalloc(bmp_sz, flags); + if (!ab->usedmap) + return -ENOMEM; + } + if (old_freemap) { ab->freemap = old_freemap; } else { @@ -243,7 +248,6 @@ xchk_xattr_set_map( STATIC bool xchk_xattr_check_freemap( struct xfs_scrub *sc, - unsigned long *map, struct xfs_attr3_icleaf_hdr *leafhdr) { struct xchk_xattr_buf *ab = sc->buf; @@ -260,7 +264,7 @@ xchk_xattr_check_freemap( } /* Look for bits that are set in freemap and are marked in use. */ - return !bitmap_intersects(ab->freemap, map, mapsize); + return !bitmap_intersects(ab->freemap, ab->usedmap, mapsize); } /* @@ -280,7 +284,7 @@ xchk_xattr_entry( __u32 *last_hashval) { struct xfs_mount *mp = ds->state->mp; - unsigned long *usedmap = xchk_xattr_usedmap(ds->sc); + struct xchk_xattr_buf *ab = ds->sc->buf; char *name_end; struct xfs_attr_leaf_name_local *lentry; struct xfs_attr_leaf_name_remote *rentry; @@ -320,7 +324,7 @@ xchk_xattr_entry( if (name_end > buf_end) xchk_da_set_corrupt(ds, level); - if (!xchk_xattr_set_map(ds->sc, usedmap, nameidx, namesize)) + if (!xchk_xattr_set_map(ds->sc, ab->usedmap, nameidx, namesize)) xchk_da_set_corrupt(ds, level); if (!(ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) *usedbytes += namesize; @@ -340,7 +344,7 @@ xchk_xattr_block( struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *ent; struct xfs_attr_leaf_entry *entries; - unsigned long *usedmap; + struct xchk_xattr_buf *ab = ds->sc->buf; char *buf_end; size_t off; __u32 last_hashval = 0; @@ -358,10 +362,9 @@ xchk_xattr_block( return -EDEADLOCK; if (error) return error; - usedmap = xchk_xattr_usedmap(ds->sc); *last_checked = blk->blkno; - bitmap_zero(usedmap, mp->m_attr_geo->blksize); + bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize); /* Check all the padding. */ if (xfs_has_crc(ds->sc->mp)) { @@ -385,7 +388,7 @@ xchk_xattr_block( xchk_da_set_corrupt(ds, level); if (leafhdr.firstused < hdrsize) xchk_da_set_corrupt(ds, level); - if (!xchk_xattr_set_map(ds->sc, usedmap, 0, hdrsize)) + if (!xchk_xattr_set_map(ds->sc, ab->usedmap, 0, hdrsize)) xchk_da_set_corrupt(ds, level); if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) @@ -399,7 +402,7 @@ xchk_xattr_block( for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) { /* Mark the leaf entry itself. */ off = (char *)ent - (char *)leaf; - if (!xchk_xattr_set_map(ds->sc, usedmap, off, + if (!xchk_xattr_set_map(ds->sc, ab->usedmap, off, sizeof(xfs_attr_leaf_entry_t))) { xchk_da_set_corrupt(ds, level); goto out; @@ -413,7 +416,7 @@ xchk_xattr_block( goto out; } - if (!xchk_xattr_check_freemap(ds->sc, usedmap, &leafhdr)) + if (!xchk_xattr_check_freemap(ds->sc, &leafhdr)) xchk_da_set_corrupt(ds, level); if (leafhdr.usedbytes != usedbytes) diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index 341855b3201b..525f45815526 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -10,6 +10,9 @@ * Temporary storage for online scrub and repair of extended attributes. */ struct xchk_xattr_buf { + /* Bitmap of used space in xattr leaf blocks. */ + unsigned long *usedmap; + /* Bitmap of free space in xattr leaf blocks. */ unsigned long *freemap; @@ -17,13 +20,8 @@ struct xchk_xattr_buf { size_t sz; /* - * Memory buffer -- either used for extracting attr values while - * walking the attributes; or for computing attr block bitmaps when - * checking the attribute tree. - * - * Each bitmap contains enough bits to track every byte in an attr - * block (rounded up to the size of an unsigned long). The attr block - * used space bitmap starts at the beginning of the buffer. + * Memory buffer -- used for extracting attr values while walking the + * attributes. */ uint8_t buf[]; }; @@ -38,14 +36,4 @@ xchk_xattr_valuebuf( return ab->buf; } -/* A bitmap of space usage computed by walking an attr leaf block. */ -static inline unsigned long * -xchk_xattr_usedmap( - struct xfs_scrub *sc) -{ - struct xchk_xattr_buf *ab = sc->buf; - - return (unsigned long *)ab->buf; -} - #endif /* __XFS_SCRUB_ATTR_H__ */ -- GitLab From b996c9a80664b970b73961c83bede243b999341e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:31 -0700 Subject: [PATCH 2615/5631] xfs: split valuebuf from xchk_xattr_buf.buf Move the xattr value buffer from somewhere in xchk_xattr_buf.buf[] to an explicit pointer. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 89 ++++++++++++++++++++++----------------------- fs/xfs/scrub/attr.h | 21 ++--------- 2 files changed, 46 insertions(+), 64 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 65ec503c8a38..7f723f206146 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -31,6 +31,9 @@ xchk_xattr_buf_cleanup( ab->freemap = NULL; kvfree(ab->usedmap); ab->usedmap = NULL; + kvfree(ab->value); + ab->value = NULL; + ab->value_sz = 0; } /* @@ -44,54 +47,45 @@ xchk_setup_xattr_buf( size_t value_size, gfp_t flags) { - size_t sz = value_size; size_t bmp_sz; struct xchk_xattr_buf *ab = sc->buf; - unsigned long *old_usedmap = NULL; - unsigned long *old_freemap = NULL; + void *new_val; bmp_sz = sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); - /* - * If there's already a buffer, figure out if we need to reallocate it - * to accommodate a larger size. - */ - if (ab) { - if (sz <= ab->sz) - return 0; - old_freemap = ab->freemap; - old_usedmap = ab->usedmap; - kvfree(ab); - sc->buf = NULL; - } + if (ab) + goto resize_value; - /* - * Don't zero the buffer upon allocation to avoid runtime overhead. - * All users must be careful never to read uninitialized contents. - */ - ab = kvmalloc(sizeof(*ab) + sz, flags); + ab = kvzalloc(sizeof(struct xchk_xattr_buf), flags); if (!ab) return -ENOMEM; - ab->sz = sz; sc->buf = ab; sc->buf_cleanup = xchk_xattr_buf_cleanup; - if (old_usedmap) { - ab->usedmap = old_usedmap; - } else { - ab->usedmap = kvmalloc(bmp_sz, flags); - if (!ab->usedmap) - return -ENOMEM; - } + ab->usedmap = kvmalloc(bmp_sz, flags); + if (!ab->usedmap) + return -ENOMEM; - if (old_freemap) { - ab->freemap = old_freemap; - } else { - ab->freemap = kvmalloc(bmp_sz, flags); - if (!ab->freemap) - return -ENOMEM; + ab->freemap = kvmalloc(bmp_sz, flags); + if (!ab->freemap) + return -ENOMEM; + +resize_value: + if (ab->value_sz >= value_size) + return 0; + + if (ab->value) { + kvfree(ab->value); + ab->value = NULL; + ab->value_sz = 0; } + new_val = kvmalloc(value_size, flags); + if (!new_val) + return -ENOMEM; + + ab->value = new_val; + ab->value_sz = value_size; return 0; } @@ -140,11 +134,24 @@ xchk_xattr_listent( int namelen, int valuelen) { + struct xfs_da_args args = { + .op_flags = XFS_DA_OP_NOTIME, + .attr_filter = flags & XFS_ATTR_NSP_ONDISK_MASK, + .geo = context->dp->i_mount->m_attr_geo, + .whichfork = XFS_ATTR_FORK, + .dp = context->dp, + .name = name, + .namelen = namelen, + .hashval = xfs_da_hashname(name, namelen), + .trans = context->tp, + .valuelen = valuelen, + }; + struct xchk_xattr_buf *ab; struct xchk_xattr *sx; - struct xfs_da_args args = { NULL }; int error = 0; sx = container_of(context, struct xchk_xattr, context); + ab = sx->sc->buf; if (xchk_should_terminate(sx->sc, &error)) { context->seen_enough = error; @@ -182,17 +189,7 @@ xchk_xattr_listent( return; } - args.op_flags = XFS_DA_OP_NOTIME; - args.attr_filter = flags & XFS_ATTR_NSP_ONDISK_MASK; - args.geo = context->dp->i_mount->m_attr_geo; - args.whichfork = XFS_ATTR_FORK; - args.dp = context->dp; - args.name = name; - args.namelen = namelen; - args.hashval = xfs_da_hashname(args.name, args.namelen); - args.trans = context->tp; - args.value = xchk_xattr_valuebuf(sx->sc); - args.valuelen = valuelen; + args.value = ab->value; error = xfs_attr_get_ilocked(&args); /* ENODATA means the hash lookup failed and the attr is bad */ diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index 525f45815526..3c764722da61 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -16,24 +16,9 @@ struct xchk_xattr_buf { /* Bitmap of free space in xattr leaf blocks. */ unsigned long *freemap; - /* Size of @buf, in bytes. */ - size_t sz; - - /* - * Memory buffer -- used for extracting attr values while walking the - * attributes. - */ - uint8_t buf[]; + /* Memory buffer used to extract xattr values. */ + void *value; + size_t value_sz; }; -/* A place to store attribute values. */ -static inline uint8_t * -xchk_xattr_valuebuf( - struct xfs_scrub *sc) -{ - struct xchk_xattr_buf *ab = sc->buf; - - return ab->buf; -} - #endif /* __XFS_SCRUB_ATTR_H__ */ -- GitLab From f58977edc0b50bf6aee5a63bff34581b22b2ce63 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:32 -0700 Subject: [PATCH 2616/5631] xfs: remove flags argument from xchk_setup_xattr_buf All callers pass XCHK_GFP_FLAGS as the flags argument to xchk_setup_xattr_buf, so get rid of the argument. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 7f723f206146..420166336f56 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -44,8 +44,7 @@ xchk_xattr_buf_cleanup( static int xchk_setup_xattr_buf( struct xfs_scrub *sc, - size_t value_size, - gfp_t flags) + size_t value_size) { size_t bmp_sz; struct xchk_xattr_buf *ab = sc->buf; @@ -56,17 +55,17 @@ xchk_setup_xattr_buf( if (ab) goto resize_value; - ab = kvzalloc(sizeof(struct xchk_xattr_buf), flags); + ab = kvzalloc(sizeof(struct xchk_xattr_buf), XCHK_GFP_FLAGS); if (!ab) return -ENOMEM; sc->buf = ab; sc->buf_cleanup = xchk_xattr_buf_cleanup; - ab->usedmap = kvmalloc(bmp_sz, flags); + ab->usedmap = kvmalloc(bmp_sz, XCHK_GFP_FLAGS); if (!ab->usedmap) return -ENOMEM; - ab->freemap = kvmalloc(bmp_sz, flags); + ab->freemap = kvmalloc(bmp_sz, XCHK_GFP_FLAGS); if (!ab->freemap) return -ENOMEM; @@ -80,7 +79,7 @@ xchk_setup_xattr_buf( ab->value_sz = 0; } - new_val = kvmalloc(value_size, flags); + new_val = kvmalloc(value_size, XCHK_GFP_FLAGS); if (!new_val) return -ENOMEM; @@ -102,8 +101,7 @@ xchk_setup_xattr( * without the inode lock held, which means we can sleep. */ if (sc->flags & XCHK_TRY_HARDER) { - error = xchk_setup_xattr_buf(sc, XATTR_SIZE_MAX, - XCHK_GFP_FLAGS); + error = xchk_setup_xattr_buf(sc, XATTR_SIZE_MAX); if (error) return error; } @@ -181,7 +179,7 @@ xchk_xattr_listent( * doesn't work, we overload the seen_enough variable to convey * the error message back to the main scrub function. */ - error = xchk_setup_xattr_buf(sx->sc, valuelen, XCHK_GFP_FLAGS); + error = xchk_setup_xattr_buf(sx->sc, valuelen); if (error == -ENOMEM) error = -EDEADLOCK; if (error) { @@ -354,7 +352,7 @@ xchk_xattr_block( return 0; /* Allocate memory for block usage checking. */ - error = xchk_setup_xattr_buf(ds->sc, 0, XCHK_GFP_FLAGS); + error = xchk_setup_xattr_buf(ds->sc, 0); if (error == -ENOMEM) return -EDEADLOCK; if (error) -- GitLab From 5b02a3e8391c703638c5a97513c353aa0c3fd5b0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:32 -0700 Subject: [PATCH 2617/5631] xfs: move xattr scrub buffer allocation to top level function Move the xchk_setup_xattr_buf call from xchk_xattr_block to xchk_xattr, since we only need to set up the leaf block bitmaps once. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 420166336f56..b37de9459dc0 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -346,18 +346,10 @@ xchk_xattr_block( unsigned int usedbytes = 0; unsigned int hdrsize; int i; - int error; if (*last_checked == blk->blkno) return 0; - /* Allocate memory for block usage checking. */ - error = xchk_setup_xattr_buf(ds->sc, 0); - if (error == -ENOMEM) - return -EDEADLOCK; - if (error) - return error; - *last_checked = blk->blkno; bitmap_zero(ab->usedmap, mp->m_attr_geo->blksize); @@ -507,6 +499,13 @@ xchk_xattr( if (!xfs_inode_hasattr(sc->ip)) return -ENOENT; + /* Allocate memory for xattr checking. */ + error = xchk_setup_xattr_buf(sc, 0); + if (error == -ENOMEM) + return -EDEADLOCK; + if (error) + return error; + memset(&sx, 0, sizeof(sx)); /* Check attribute tree structure */ error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec, -- GitLab From ae0506eba78fd1d6236b46ca5aa089c8fc6050cf Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:33 -0700 Subject: [PATCH 2618/5631] xfs: check used space of shortform xattr structures Make sure that the records used inside a shortform xattr structure do not overlap. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 79 ++++++++++++++++++++++++++++++++++++++++++--- fs/xfs/scrub/attr.h | 2 +- 2 files changed, 76 insertions(+), 5 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index b37de9459dc0..a49048f2a3db 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -15,6 +15,7 @@ #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" +#include "xfs_attr_sf.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/dabtree.h" @@ -487,6 +488,73 @@ xchk_xattr_rec( return error; } +/* Check space usage of shortform attrs. */ +STATIC int +xchk_xattr_check_sf( + struct xfs_scrub *sc) +{ + struct xchk_xattr_buf *ab = sc->buf; + struct xfs_attr_shortform *sf; + struct xfs_attr_sf_entry *sfe; + struct xfs_attr_sf_entry *next; + struct xfs_ifork *ifp; + unsigned char *end; + int i; + int error = 0; + + ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK); + + bitmap_zero(ab->usedmap, ifp->if_bytes); + sf = (struct xfs_attr_shortform *)sc->ip->i_af.if_u1.if_data; + end = (unsigned char *)ifp->if_u1.if_data + ifp->if_bytes; + xchk_xattr_set_map(sc, ab->usedmap, 0, sizeof(sf->hdr)); + + sfe = &sf->list[0]; + if ((unsigned char *)sfe > end) { + xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0); + return 0; + } + + for (i = 0; i < sf->hdr.count; i++) { + unsigned char *name = sfe->nameval; + unsigned char *value = &sfe->nameval[sfe->namelen]; + + if (xchk_should_terminate(sc, &error)) + return error; + + next = xfs_attr_sf_nextentry(sfe); + if ((unsigned char *)next > end) { + xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0); + break; + } + + if (!xchk_xattr_set_map(sc, ab->usedmap, + (char *)sfe - (char *)sf, + sizeof(struct xfs_attr_sf_entry))) { + xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0); + break; + } + + if (!xchk_xattr_set_map(sc, ab->usedmap, + (char *)name - (char *)sf, + sfe->namelen)) { + xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0); + break; + } + + if (!xchk_xattr_set_map(sc, ab->usedmap, + (char *)value - (char *)sf, + sfe->valuelen)) { + xchk_fblock_set_corrupt(sc, XFS_ATTR_FORK, 0); + break; + } + + sfe = next; + } + + return 0; +} + /* Scrub the extended attribute metadata. */ int xchk_xattr( @@ -506,10 +574,12 @@ xchk_xattr( if (error) return error; - memset(&sx, 0, sizeof(sx)); - /* Check attribute tree structure */ - error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec, - &last_checked); + /* Check the physical structure of the xattr. */ + if (sc->ip->i_af.if_format == XFS_DINODE_FMT_LOCAL) + error = xchk_xattr_check_sf(sc); + else + error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec, + &last_checked); if (error) goto out; @@ -517,6 +587,7 @@ xchk_xattr( goto out; /* Check that every attr key can also be looked up by hash. */ + memset(&sx, 0, sizeof(sx)); sx.context.dp = sc->ip; sx.context.resynch = 1; sx.context.put_listent = xchk_xattr_listent; diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h index 3c764722da61..48fd9402c432 100644 --- a/fs/xfs/scrub/attr.h +++ b/fs/xfs/scrub/attr.h @@ -10,7 +10,7 @@ * Temporary storage for online scrub and repair of extended attributes. */ struct xchk_xattr_buf { - /* Bitmap of used space in xattr leaf blocks. */ + /* Bitmap of used space in xattr leaf blocks and shortform forks. */ unsigned long *usedmap; /* Bitmap of free space in xattr leaf blocks. */ -- GitLab From 6cee51e6d02bac7ee72969aa23e32c9bdcd7bb6e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:34 -0700 Subject: [PATCH 2619/5631] xfs: clean up xattr scrub initialization Clean up local variable initialization and error returns in xchk_xattr. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index a49048f2a3db..d2e1856beeb6 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -560,7 +560,16 @@ int xchk_xattr( struct xfs_scrub *sc) { - struct xchk_xattr sx; + struct xchk_xattr sx = { + .sc = sc, + .context = { + .dp = sc->ip, + .tp = sc->tp, + .resynch = 1, + .put_listent = xchk_xattr_listent, + .allow_incomplete = true, + }, + }; xfs_dablk_t last_checked = -1U; int error = 0; @@ -581,22 +590,13 @@ xchk_xattr( error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec, &last_checked); if (error) - goto out; + return error; if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - goto out; - - /* Check that every attr key can also be looked up by hash. */ - memset(&sx, 0, sizeof(sx)); - sx.context.dp = sc->ip; - sx.context.resynch = 1; - sx.context.put_listent = xchk_xattr_listent; - sx.context.tp = sc->tp; - sx.context.allow_incomplete = true; - sx.sc = sc; + return 0; /* - * Look up every xattr in this file by name. + * Look up every xattr in this file by name and hash. * * Use the backend implementation of xfs_attr_list to call * xchk_xattr_listent on every attribute key in this inode. @@ -613,11 +613,11 @@ xchk_xattr( */ error = xfs_attr_list_ilocked(&sx.context); if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error)) - goto out; + return error; /* Did our listent function try to return any errors? */ if (sx.context.seen_enough < 0) - error = sx.context.seen_enough; -out: - return error; + return sx.context.seen_enough; + + return 0; } -- GitLab From 674f0d0dc6b5b2228c4e9d597a62d5aa6b54a9c5 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:34 -0700 Subject: [PATCH 2620/5631] xfs: only allocate free space bitmap for xattr scrub if needed The free space bitmap is only required if we're going to check the bestfree space at the end of an xattr leaf block. Therefore, we can reduce the memory requirements of this scrubber if we can determine that the xattr is in short format. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index d2e1856beeb6..2445fe2860ff 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -37,6 +37,29 @@ xchk_xattr_buf_cleanup( ab->value_sz = 0; } +/* + * Allocate the free space bitmap if we're trying harder; there are leaf blocks + * in the attr fork; or we can't tell if there are leaf blocks. + */ +static inline bool +xchk_xattr_want_freemap( + struct xfs_scrub *sc) +{ + struct xfs_ifork *ifp; + + if (sc->flags & XCHK_TRY_HARDER) + return true; + + if (!sc->ip) + return true; + + ifp = xfs_ifork_ptr(sc->ip, XFS_ATTR_FORK); + if (!ifp) + return false; + + return xfs_ifork_has_extents(ifp); +} + /* * Allocate enough memory to hold an attr value and attr block bitmaps, * reallocating the buffer if necessary. Buffer contents are not preserved @@ -66,9 +89,11 @@ xchk_setup_xattr_buf( if (!ab->usedmap) return -ENOMEM; - ab->freemap = kvmalloc(bmp_sz, XCHK_GFP_FLAGS); - if (!ab->freemap) - return -ENOMEM; + if (xchk_xattr_want_freemap(sc)) { + ab->freemap = kvmalloc(bmp_sz, XCHK_GFP_FLAGS); + if (!ab->freemap) + return -ENOMEM; + } resize_value: if (ab->value_sz >= value_size) -- GitLab From 178b48d588ea5424a54423dc9c406416de0547c8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:35 -0700 Subject: [PATCH 2621/5631] xfs: remove the for_each_xbitmap_ helpers Remove the for_each_xbitmap_ macros in favor of proper iterator functions. We'll soon be switching this data structure over to an interval tree implementation, which means that we can't allow callers to modify the bitmap during iteration without telling us. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/agheader_repair.c | 89 +++++++++++++++------------- fs/xfs/scrub/bitmap.c | 59 +++++++++++++++++++ fs/xfs/scrub/bitmap.h | 22 ++++--- fs/xfs/scrub/repair.c | 104 ++++++++++++++++++--------------- 4 files changed, 180 insertions(+), 94 deletions(-) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index edfb1dfb80a9..997ddcd1f124 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -487,10 +487,11 @@ xrep_agfl_walk_rmap( /* Strike out the blocks that are cross-linked according to the rmapbt. */ STATIC int xrep_agfl_check_extent( - struct xrep_agfl *ra, uint64_t start, - uint64_t len) + uint64_t len, + void *priv) { + struct xrep_agfl *ra = priv; xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(ra->sc->mp, start); xfs_agblock_t last_agbno = agbno + len - 1; int error; @@ -538,7 +539,6 @@ xrep_agfl_collect_blocks( struct xrep_agfl ra; struct xfs_mount *mp = sc->mp; struct xfs_btree_cur *cur; - struct xbitmap_range *br, *n; int error; ra.sc = sc; @@ -579,11 +579,7 @@ xrep_agfl_collect_blocks( /* Strike out the blocks that are cross-linked. */ ra.rmap_cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.pag); - for_each_xbitmap_extent(br, n, agfl_extents) { - error = xrep_agfl_check_extent(&ra, br->start, br->len); - if (error) - break; - } + error = xbitmap_walk(agfl_extents, xrep_agfl_check_extent, &ra); xfs_btree_del_cursor(ra.rmap_cur, error); if (error) goto out_bmp; @@ -629,6 +625,43 @@ xrep_agfl_update_agf( XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT); } +struct xrep_agfl_fill { + struct xbitmap used_extents; + struct xfs_scrub *sc; + __be32 *agfl_bno; + xfs_agblock_t flcount; + unsigned int fl_off; +}; + +/* Fill the AGFL with whatever blocks are in this extent. */ +static int +xrep_agfl_fill( + uint64_t start, + uint64_t len, + void *priv) +{ + struct xrep_agfl_fill *af = priv; + struct xfs_scrub *sc = af->sc; + xfs_fsblock_t fsbno = start; + int error; + + while (fsbno < start + len && af->fl_off < af->flcount) + af->agfl_bno[af->fl_off++] = + cpu_to_be32(XFS_FSB_TO_AGBNO(sc->mp, fsbno++)); + + trace_xrep_agfl_insert(sc->mp, sc->sa.pag->pag_agno, + XFS_FSB_TO_AGBNO(sc->mp, start), len); + + error = xbitmap_set(&af->used_extents, start, fsbno - 1); + if (error) + return error; + + if (af->fl_off == af->flcount) + return -ECANCELED; + + return 0; +} + /* Write out a totally new AGFL. */ STATIC void xrep_agfl_init_header( @@ -637,13 +670,12 @@ xrep_agfl_init_header( struct xbitmap *agfl_extents, xfs_agblock_t flcount) { + struct xrep_agfl_fill af = { + .sc = sc, + .flcount = flcount, + }; struct xfs_mount *mp = sc->mp; - __be32 *agfl_bno; - struct xbitmap_range *br; - struct xbitmap_range *n; struct xfs_agfl *agfl; - xfs_agblock_t agbno; - unsigned int fl_off; ASSERT(flcount <= xfs_agfl_size(mp)); @@ -662,36 +694,15 @@ xrep_agfl_init_header( * blocks than fit in the AGFL, they will be freed in a subsequent * step. */ - fl_off = 0; - agfl_bno = xfs_buf_to_agfl_bno(agfl_bp); - for_each_xbitmap_extent(br, n, agfl_extents) { - agbno = XFS_FSB_TO_AGBNO(mp, br->start); - - trace_xrep_agfl_insert(mp, sc->sa.pag->pag_agno, agbno, - br->len); - - while (br->len > 0 && fl_off < flcount) { - agfl_bno[fl_off] = cpu_to_be32(agbno); - fl_off++; - agbno++; - - /* - * We've now used br->start by putting it in the AGFL, - * so bump br so that we don't reap the block later. - */ - br->start++; - br->len--; - } - - if (br->len) - break; - list_del(&br->list); - kfree(br); - } + xbitmap_init(&af.used_extents); + af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp), + xbitmap_walk(agfl_extents, xrep_agfl_fill, &af); + xbitmap_disunion(agfl_extents, &af.used_extents); /* Write new AGFL to disk. */ xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); + xbitmap_destroy(&af.used_extents); } /* Repair the AGFL. */ diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index ce8b17d76c0b..315b7c5844a3 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -13,6 +13,9 @@ #include "scrub/scrub.h" #include "scrub/bitmap.h" +#define for_each_xbitmap_extent(bex, n, bitmap) \ + list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) + /* * Set a range of this bitmap. Caller must ensure the range is not set. * @@ -313,3 +316,59 @@ xbitmap_hweight( return ret; } + +/* Call a function for every run of set bits in this bitmap. */ +int +xbitmap_walk( + struct xbitmap *bitmap, + xbitmap_walk_fn fn, + void *priv) +{ + struct xbitmap_range *bex, *n; + int error = 0; + + for_each_xbitmap_extent(bex, n, bitmap) { + error = fn(bex->start, bex->len, priv); + if (error) + break; + } + + return error; +} + +struct xbitmap_walk_bits { + xbitmap_walk_bits_fn fn; + void *priv; +}; + +/* Walk all the bits in a run. */ +static int +xbitmap_walk_bits_in_run( + uint64_t start, + uint64_t len, + void *priv) +{ + struct xbitmap_walk_bits *wb = priv; + uint64_t i; + int error = 0; + + for (i = start; i < start + len; i++) { + error = wb->fn(i, wb->priv); + if (error) + break; + } + + return error; +} + +/* Call a function for every set bit in this bitmap. */ +int +xbitmap_walk_bits( + struct xbitmap *bitmap, + xbitmap_walk_bits_fn fn, + void *priv) +{ + struct xbitmap_walk_bits wb = {.fn = fn, .priv = priv}; + + return xbitmap_walk(bitmap, xbitmap_walk_bits_in_run, &wb); +} diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 85ec0e2792c5..01e37173dc34 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -19,13 +19,6 @@ struct xbitmap { void xbitmap_init(struct xbitmap *bitmap); void xbitmap_destroy(struct xbitmap *bitmap); -#define for_each_xbitmap_extent(bex, n, bitmap) \ - list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) - -#define for_each_xbitmap_block(b, bex, n, bitmap) \ - list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) \ - for ((b) = (bex)->start; (b) < (bex)->start + (bex)->len; (b)++) - int xbitmap_set(struct xbitmap *bitmap, uint64_t start, uint64_t len); int xbitmap_disunion(struct xbitmap *bitmap, struct xbitmap *sub); int xbitmap_set_btcur_path(struct xbitmap *bitmap, @@ -34,4 +27,19 @@ int xbitmap_set_btblocks(struct xbitmap *bitmap, struct xfs_btree_cur *cur); uint64_t xbitmap_hweight(struct xbitmap *bitmap); +/* + * Return codes for the bitmap iterator functions are 0 to continue iterating, + * and non-zero to stop iterating. Any non-zero value will be passed up to the + * iteration caller. The special value -ECANCELED can be used to stop + * iteration, because neither bitmap iterator ever generates that error code on + * its own. Callers must not modify the bitmap while walking it. + */ +typedef int (*xbitmap_walk_fn)(uint64_t start, uint64_t len, void *priv); +int xbitmap_walk(struct xbitmap *bitmap, xbitmap_walk_fn fn, + void *priv); + +typedef int (*xbitmap_walk_bits_fn)(uint64_t bit, void *priv); +int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn, + void *priv); + #endif /* __XFS_SCRUB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index ab0758308f57..ac6d8803e660 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -445,6 +445,30 @@ xrep_init_btblock( * buffers associated with @bitmap. */ +static int +xrep_invalidate_block( + uint64_t fsbno, + void *priv) +{ + struct xfs_scrub *sc = priv; + struct xfs_buf *bp; + int error; + + /* Skip AG headers and post-EOFS blocks */ + if (!xfs_verify_fsbno(sc->mp, fsbno)) + return 0; + + error = xfs_buf_incore(sc->mp->m_ddev_targp, + XFS_FSB_TO_DADDR(sc->mp, fsbno), + XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp); + if (error) + return 0; + + xfs_trans_bjoin(sc->tp, bp); + xfs_trans_binval(sc->tp, bp); + return 0; +} + /* * Invalidate buffers for per-AG btree blocks we're dumping. This function * is not intended for use with file data repairs; we have bunmapi for that. @@ -454,11 +478,6 @@ xrep_invalidate_blocks( struct xfs_scrub *sc, struct xbitmap *bitmap) { - struct xbitmap_range *bmr; - struct xbitmap_range *n; - struct xfs_buf *bp; - xfs_fsblock_t fsbno; - /* * For each block in each extent, see if there's an incore buffer for * exactly that block; if so, invalidate it. The buffer cache only @@ -467,23 +486,7 @@ xrep_invalidate_blocks( * because we never own those; and if we can't TRYLOCK the buffer we * assume it's owned by someone else. */ - for_each_xbitmap_block(fsbno, bmr, n, bitmap) { - int error; - - /* Skip AG headers and post-EOFS blocks */ - if (!xfs_verify_fsbno(sc->mp, fsbno)) - continue; - error = xfs_buf_incore(sc->mp->m_ddev_targp, - XFS_FSB_TO_DADDR(sc->mp, fsbno), - XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp); - if (error) - continue; - - xfs_trans_bjoin(sc->tp, bp); - xfs_trans_binval(sc->tp, bp); - } - - return 0; + return xbitmap_walk_bits(bitmap, xrep_invalidate_block, sc); } /* Ensure the freelist is the correct size. */ @@ -504,6 +507,15 @@ xrep_fix_freelist( can_shrink ? 0 : XFS_ALLOC_FLAG_NOSHRINK); } +/* Information about reaping extents after a repair. */ +struct xrep_reap_state { + struct xfs_scrub *sc; + + /* Reverse mapping owner and metadata reservation type. */ + const struct xfs_owner_info *oinfo; + enum xfs_ag_resv_type resv; +}; + /* * Put a block back on the AGFL. */ @@ -548,17 +560,23 @@ xrep_put_freelist( /* Dispose of a single block. */ STATIC int xrep_reap_block( - struct xfs_scrub *sc, - xfs_fsblock_t fsbno, - const struct xfs_owner_info *oinfo, - enum xfs_ag_resv_type resv) + uint64_t fsbno, + void *priv) { + struct xrep_reap_state *rs = priv; + struct xfs_scrub *sc = rs->sc; struct xfs_btree_cur *cur; struct xfs_buf *agf_bp = NULL; xfs_agblock_t agbno; bool has_other_rmap; int error; + ASSERT(sc->ip != NULL || + XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno); + trace_xrep_dispose_btree_extent(sc->mp, + XFS_FSB_TO_AGNO(sc->mp, fsbno), + XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1); + agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno); ASSERT(XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno); @@ -577,7 +595,8 @@ xrep_reap_block( cur = xfs_rmapbt_init_cursor(sc->mp, sc->tp, agf_bp, sc->sa.pag); /* Can we find any other rmappings? */ - error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap); + error = xfs_rmap_has_other_keys(cur, agbno, 1, rs->oinfo, + &has_other_rmap); xfs_btree_del_cursor(cur, error); if (error) goto out_free; @@ -597,12 +616,12 @@ xrep_reap_block( */ if (has_other_rmap) error = xfs_rmap_free(sc->tp, agf_bp, sc->sa.pag, agbno, - 1, oinfo); - else if (resv == XFS_AG_RESV_AGFL) + 1, rs->oinfo); + else if (rs->resv == XFS_AG_RESV_AGFL) error = xrep_put_freelist(sc, agbno); else - error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, oinfo, - resv); + error = xfs_free_extent(sc->tp, sc->sa.pag, agbno, 1, rs->oinfo, + rs->resv); if (agf_bp != sc->sa.agf_bp) xfs_trans_brelse(sc->tp, agf_bp); if (error) @@ -626,26 +645,15 @@ xrep_reap_extents( const struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type) { - struct xbitmap_range *bmr; - struct xbitmap_range *n; - xfs_fsblock_t fsbno; - int error = 0; + struct xrep_reap_state rs = { + .sc = sc, + .oinfo = oinfo, + .resv = type, + }; ASSERT(xfs_has_rmapbt(sc->mp)); - for_each_xbitmap_block(fsbno, bmr, n, bitmap) { - ASSERT(sc->ip != NULL || - XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.pag->pag_agno); - trace_xrep_dispose_btree_extent(sc->mp, - XFS_FSB_TO_AGNO(sc->mp, fsbno), - XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1); - - error = xrep_reap_block(sc, fsbno, oinfo, type); - if (error) - break; - } - - return error; + return xbitmap_walk_bits(bitmap, xrep_reap_block, &rs); } /* -- GitLab From 44af6c7e59b12d740809cf25a60c9f90f03e6d20 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:35 -0700 Subject: [PATCH 2622/5631] xfs: don't load local xattr values during scrub Local extended attributes store their values within the same leaf block. There's no header for the values themselves, nor are they separately checksummed. Hence we can save a bit of time in the attr scrubber by not wasting time retrieving the values. Regrettably, shortform attributes do not set XFS_ATTR_LOCAL so this offers us no advantage there, but at least there are very few attrs in that case. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/attr.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index 2445fe2860ff..6c16d9530cca 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -200,6 +200,14 @@ xchk_xattr_listent( goto fail_xref; } + /* + * Local xattr values are stored in the attr leaf block, so we don't + * need to retrieve the value from a remote block to detect corruption + * problems. + */ + if (flags & XFS_ATTR_LOCAL) + goto fail_xref; + /* * Try to allocate enough memory to extrat the attr value. If that * doesn't work, we overload the seen_enough variable to convey -- GitLab From 7296a6d6fb8fef515352dac5d8af2ffe7a78e5cf Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:36 -0700 Subject: [PATCH 2623/5631] xfs: drop the _safe behavior from the xbitmap foreach macro It's not safe to edit bitmap intervals while we're iterating them with for_each_xbitmap_extent. None of the existing callers actually need that ability anyway, so drop the safe variable. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bitmap.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index 315b7c5844a3..9927634a2c54 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -13,8 +13,9 @@ #include "scrub/scrub.h" #include "scrub/bitmap.h" -#define for_each_xbitmap_extent(bex, n, bitmap) \ - list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) +/* Iterate each interval of a bitmap. Do not change the bitmap. */ +#define for_each_xbitmap_extent(bex, bitmap) \ + list_for_each_entry((bex), &(bitmap)->list, list) /* * Set a range of this bitmap. Caller must ensure the range is not set. @@ -46,10 +47,9 @@ void xbitmap_destroy( struct xbitmap *bitmap) { - struct xbitmap_range *bmr; - struct xbitmap_range *n; + struct xbitmap_range *bmr, *n; - for_each_xbitmap_extent(bmr, n, bitmap) { + list_for_each_entry_safe(bmr, n, &bitmap->list, list) { list_del(&bmr->list); kfree(bmr); } @@ -308,10 +308,9 @@ xbitmap_hweight( struct xbitmap *bitmap) { struct xbitmap_range *bmr; - struct xbitmap_range *n; uint64_t ret = 0; - for_each_xbitmap_extent(bmr, n, bitmap) + for_each_xbitmap_extent(bmr, bitmap) ret += bmr->len; return ret; @@ -324,10 +323,10 @@ xbitmap_walk( xbitmap_walk_fn fn, void *priv) { - struct xbitmap_range *bex, *n; + struct xbitmap_range *bex; int error = 0; - for_each_xbitmap_extent(bex, n, bitmap) { + for_each_xbitmap_extent(bex, bitmap) { error = fn(bex->start, bex->len, priv); if (error) break; -- GitLab From 6772fcc8890ae34595253fcfb8196c1aea65e111 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:36 -0700 Subject: [PATCH 2624/5631] xfs: convert xbitmap to interval tree Convert the xbitmap code to use interval trees instead of linked lists. This reduces the amount of coding required to handle the disunion operation and in the future will make it easier to set bits in arbitrary order yet later be able to extract maximally sized extents, which we'll need for rebuilding certain structures. We define our own interval tree type so that it can deal with 64-bit indices even on 32-bit machines. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/agheader_repair.c | 12 +- fs/xfs/scrub/bitmap.c | 319 ++++++++++++++++++--------------- fs/xfs/scrub/bitmap.h | 11 +- 3 files changed, 185 insertions(+), 157 deletions(-) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 997ddcd1f124..bbaa65422c4f 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -663,7 +663,7 @@ xrep_agfl_fill( } /* Write out a totally new AGFL. */ -STATIC void +STATIC int xrep_agfl_init_header( struct xfs_scrub *sc, struct xfs_buf *agfl_bp, @@ -676,6 +676,7 @@ xrep_agfl_init_header( }; struct xfs_mount *mp = sc->mp; struct xfs_agfl *agfl; + int error; ASSERT(flcount <= xfs_agfl_size(mp)); @@ -697,12 +698,15 @@ xrep_agfl_init_header( xbitmap_init(&af.used_extents); af.agfl_bno = xfs_buf_to_agfl_bno(agfl_bp), xbitmap_walk(agfl_extents, xrep_agfl_fill, &af); - xbitmap_disunion(agfl_extents, &af.used_extents); + error = xbitmap_disunion(agfl_extents, &af.used_extents); + if (error) + return error; /* Write new AGFL to disk. */ xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF); xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1); xbitmap_destroy(&af.used_extents); + return 0; } /* Repair the AGFL. */ @@ -755,7 +759,9 @@ xrep_agfl( * buffers until we know that part works. */ xrep_agfl_update_agf(sc, agf_bp, flcount); - xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount); + error = xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount); + if (error) + goto err; /* * Ok, the AGFL should be ready to go now. Roll the transaction to diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index 9927634a2c54..dc139f0031dc 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -13,31 +13,160 @@ #include "scrub/scrub.h" #include "scrub/bitmap.h" -/* Iterate each interval of a bitmap. Do not change the bitmap. */ -#define for_each_xbitmap_extent(bex, bitmap) \ - list_for_each_entry((bex), &(bitmap)->list, list) +#include + +struct xbitmap_node { + struct rb_node bn_rbnode; + + /* First set bit of this interval and subtree. */ + uint64_t bn_start; + + /* Last set bit of this interval. */ + uint64_t bn_last; + + /* Last set bit of this subtree. Do not touch this. */ + uint64_t __bn_subtree_last; +}; + +/* Define our own interval tree type with uint64_t parameters. */ + +#define START(node) ((node)->bn_start) +#define LAST(node) ((node)->bn_last) /* - * Set a range of this bitmap. Caller must ensure the range is not set. - * - * This is the logical equivalent of bitmap |= mask(start, len). + * These functions are defined by the INTERVAL_TREE_DEFINE macro, but we'll + * forward-declare them anyway for clarity. */ +static inline void +xbitmap_tree_insert(struct xbitmap_node *node, struct rb_root_cached *root); + +static inline void +xbitmap_tree_remove(struct xbitmap_node *node, struct rb_root_cached *root); + +static inline struct xbitmap_node * +xbitmap_tree_iter_first(struct rb_root_cached *root, uint64_t start, + uint64_t last); + +static inline struct xbitmap_node * +xbitmap_tree_iter_next(struct xbitmap_node *node, uint64_t start, + uint64_t last); + +INTERVAL_TREE_DEFINE(struct xbitmap_node, bn_rbnode, uint64_t, + __bn_subtree_last, START, LAST, static inline, xbitmap_tree) + +/* Iterate each interval of a bitmap. Do not change the bitmap. */ +#define for_each_xbitmap_extent(bn, bitmap) \ + for ((bn) = rb_entry_safe(rb_first(&(bitmap)->xb_root.rb_root), \ + struct xbitmap_node, bn_rbnode); \ + (bn) != NULL; \ + (bn) = rb_entry_safe(rb_next(&(bn)->bn_rbnode), \ + struct xbitmap_node, bn_rbnode)) + +/* Clear a range of this bitmap. */ +int +xbitmap_clear( + struct xbitmap *bitmap, + uint64_t start, + uint64_t len) +{ + struct xbitmap_node *bn; + struct xbitmap_node *new_bn; + uint64_t last = start + len - 1; + + while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last))) { + if (bn->bn_start < start && bn->bn_last > last) { + uint64_t old_last = bn->bn_last; + + /* overlaps with the entire clearing range */ + xbitmap_tree_remove(bn, &bitmap->xb_root); + bn->bn_last = start - 1; + xbitmap_tree_insert(bn, &bitmap->xb_root); + + /* add an extent */ + new_bn = kmalloc(sizeof(struct xbitmap_node), + XCHK_GFP_FLAGS); + if (!new_bn) + return -ENOMEM; + new_bn->bn_start = last + 1; + new_bn->bn_last = old_last; + xbitmap_tree_insert(new_bn, &bitmap->xb_root); + } else if (bn->bn_start < start) { + /* overlaps with the left side of the clearing range */ + xbitmap_tree_remove(bn, &bitmap->xb_root); + bn->bn_last = start - 1; + xbitmap_tree_insert(bn, &bitmap->xb_root); + } else if (bn->bn_last > last) { + /* overlaps with the right side of the clearing range */ + xbitmap_tree_remove(bn, &bitmap->xb_root); + bn->bn_start = last + 1; + xbitmap_tree_insert(bn, &bitmap->xb_root); + break; + } else { + /* in the middle of the clearing range */ + xbitmap_tree_remove(bn, &bitmap->xb_root); + kfree(bn); + } + } + + return 0; +} + +/* Set a range of this bitmap. */ int xbitmap_set( struct xbitmap *bitmap, uint64_t start, uint64_t len) { - struct xbitmap_range *bmr; + struct xbitmap_node *left; + struct xbitmap_node *right; + uint64_t last = start + len - 1; + int error; - bmr = kmalloc(sizeof(struct xbitmap_range), XCHK_GFP_FLAGS); - if (!bmr) - return -ENOMEM; + /* Is this whole range already set? */ + left = xbitmap_tree_iter_first(&bitmap->xb_root, start, last); + if (left && left->bn_start <= start && left->bn_last >= last) + return 0; - INIT_LIST_HEAD(&bmr->list); - bmr->start = start; - bmr->len = len; - list_add_tail(&bmr->list, &bitmap->list); + /* Clear out everything in the range we want to set. */ + error = xbitmap_clear(bitmap, start, len); + if (error) + return error; + + /* Do we have a left-adjacent extent? */ + left = xbitmap_tree_iter_first(&bitmap->xb_root, start - 1, start - 1); + ASSERT(!left || left->bn_last + 1 == start); + + /* Do we have a right-adjacent extent? */ + right = xbitmap_tree_iter_first(&bitmap->xb_root, last + 1, last + 1); + ASSERT(!right || right->bn_start == last + 1); + + if (left && right) { + /* combine left and right adjacent extent */ + xbitmap_tree_remove(left, &bitmap->xb_root); + xbitmap_tree_remove(right, &bitmap->xb_root); + left->bn_last = right->bn_last; + xbitmap_tree_insert(left, &bitmap->xb_root); + kfree(right); + } else if (left) { + /* combine with left extent */ + xbitmap_tree_remove(left, &bitmap->xb_root); + left->bn_last = last; + xbitmap_tree_insert(left, &bitmap->xb_root); + } else if (right) { + /* combine with right extent */ + xbitmap_tree_remove(right, &bitmap->xb_root); + right->bn_start = start; + xbitmap_tree_insert(right, &bitmap->xb_root); + } else { + /* add an extent */ + left = kmalloc(sizeof(struct xbitmap_node), XCHK_GFP_FLAGS); + if (!left) + return -ENOMEM; + left->bn_start = start; + left->bn_last = last; + xbitmap_tree_insert(left, &bitmap->xb_root); + } return 0; } @@ -47,11 +176,11 @@ void xbitmap_destroy( struct xbitmap *bitmap) { - struct xbitmap_range *bmr, *n; + struct xbitmap_node *bn; - list_for_each_entry_safe(bmr, n, &bitmap->list, list) { - list_del(&bmr->list); - kfree(bmr); + while ((bn = xbitmap_tree_iter_first(&bitmap->xb_root, 0, -1ULL))) { + xbitmap_tree_remove(bn, &bitmap->xb_root); + kfree(bn); } } @@ -60,27 +189,7 @@ void xbitmap_init( struct xbitmap *bitmap) { - INIT_LIST_HEAD(&bitmap->list); -} - -/* Compare two btree extents. */ -static int -xbitmap_range_cmp( - void *priv, - const struct list_head *a, - const struct list_head *b) -{ - struct xbitmap_range *ap; - struct xbitmap_range *bp; - - ap = container_of(a, struct xbitmap_range, list); - bp = container_of(b, struct xbitmap_range, list); - - if (ap->start > bp->start) - return 1; - if (ap->start < bp->start) - return -1; - return 0; + bitmap->xb_root = RB_ROOT_CACHED; } /* @@ -97,118 +206,26 @@ xbitmap_range_cmp( * * This is the logical equivalent of bitmap &= ~sub. */ -#define LEFT_ALIGNED (1 << 0) -#define RIGHT_ALIGNED (1 << 1) int xbitmap_disunion( struct xbitmap *bitmap, struct xbitmap *sub) { - struct list_head *lp; - struct xbitmap_range *br; - struct xbitmap_range *new_br; - struct xbitmap_range *sub_br; - uint64_t sub_start; - uint64_t sub_len; - int state; - int error = 0; + struct xbitmap_node *bn; + int error; - if (list_empty(&bitmap->list) || list_empty(&sub->list)) + if (xbitmap_empty(bitmap) || xbitmap_empty(sub)) return 0; - ASSERT(!list_empty(&sub->list)); - - list_sort(NULL, &bitmap->list, xbitmap_range_cmp); - list_sort(NULL, &sub->list, xbitmap_range_cmp); - - /* - * Now that we've sorted both lists, we iterate bitmap once, rolling - * forward through sub and/or bitmap as necessary until we find an - * overlap or reach the end of either list. We do not reset lp to the - * head of bitmap nor do we reset sub_br to the head of sub. The - * list traversal is similar to merge sort, but we're deleting - * instead. In this manner we avoid O(n^2) operations. - */ - sub_br = list_first_entry(&sub->list, struct xbitmap_range, - list); - lp = bitmap->list.next; - while (lp != &bitmap->list) { - br = list_entry(lp, struct xbitmap_range, list); - - /* - * Advance sub_br and/or br until we find a pair that - * intersect or we run out of extents. - */ - while (sub_br->start + sub_br->len <= br->start) { - if (list_is_last(&sub_br->list, &sub->list)) - goto out; - sub_br = list_next_entry(sub_br, list); - } - if (sub_br->start >= br->start + br->len) { - lp = lp->next; - continue; - } - /* trim sub_br to fit the extent we have */ - sub_start = sub_br->start; - sub_len = sub_br->len; - if (sub_br->start < br->start) { - sub_len -= br->start - sub_br->start; - sub_start = br->start; - } - if (sub_len > br->len) - sub_len = br->len; - - state = 0; - if (sub_start == br->start) - state |= LEFT_ALIGNED; - if (sub_start + sub_len == br->start + br->len) - state |= RIGHT_ALIGNED; - switch (state) { - case LEFT_ALIGNED: - /* Coincides with only the left. */ - br->start += sub_len; - br->len -= sub_len; - break; - case RIGHT_ALIGNED: - /* Coincides with only the right. */ - br->len -= sub_len; - lp = lp->next; - break; - case LEFT_ALIGNED | RIGHT_ALIGNED: - /* Total overlap, just delete ex. */ - lp = lp->next; - list_del(&br->list); - kfree(br); - break; - case 0: - /* - * Deleting from the middle: add the new right extent - * and then shrink the left extent. - */ - new_br = kmalloc(sizeof(struct xbitmap_range), - XCHK_GFP_FLAGS); - if (!new_br) { - error = -ENOMEM; - goto out; - } - INIT_LIST_HEAD(&new_br->list); - new_br->start = sub_start + sub_len; - new_br->len = br->start + br->len - new_br->start; - list_add(&new_br->list, &br->list); - br->len = sub_start - br->start; - lp = lp->next; - break; - default: - ASSERT(0); - break; - } + for_each_xbitmap_extent(bn, sub) { + error = xbitmap_clear(bitmap, bn->bn_start, + bn->bn_last - bn->bn_start + 1); + if (error) + return error; } -out: - return error; + return 0; } -#undef LEFT_ALIGNED -#undef RIGHT_ALIGNED /* * Record all btree blocks seen while iterating all records of a btree. @@ -307,11 +324,11 @@ uint64_t xbitmap_hweight( struct xbitmap *bitmap) { - struct xbitmap_range *bmr; + struct xbitmap_node *bn; uint64_t ret = 0; - for_each_xbitmap_extent(bmr, bitmap) - ret += bmr->len; + for_each_xbitmap_extent(bn, bitmap) + ret += bn->bn_last - bn->bn_start + 1; return ret; } @@ -320,14 +337,14 @@ xbitmap_hweight( int xbitmap_walk( struct xbitmap *bitmap, - xbitmap_walk_fn fn, + xbitmap_walk_fn fn, void *priv) { - struct xbitmap_range *bex; + struct xbitmap_node *bn; int error = 0; - for_each_xbitmap_extent(bex, bitmap) { - error = fn(bex->start, bex->len, priv); + for_each_xbitmap_extent(bn, bitmap) { + error = fn(bn->bn_start, bn->bn_last - bn->bn_start + 1, priv); if (error) break; } @@ -371,3 +388,11 @@ xbitmap_walk_bits( return xbitmap_walk(bitmap, xbitmap_walk_bits_in_run, &wb); } + +/* Does this bitmap have no bits set at all? */ +bool +xbitmap_empty( + struct xbitmap *bitmap) +{ + return bitmap->xb_root.rb_root.rb_node == NULL; +} diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 01e37173dc34..2ec4e1f3f24c 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -6,19 +6,14 @@ #ifndef __XFS_SCRUB_BITMAP_H__ #define __XFS_SCRUB_BITMAP_H__ -struct xbitmap_range { - struct list_head list; - uint64_t start; - uint64_t len; -}; - struct xbitmap { - struct list_head list; + struct rb_root_cached xb_root; }; void xbitmap_init(struct xbitmap *bitmap); void xbitmap_destroy(struct xbitmap *bitmap); +int xbitmap_clear(struct xbitmap *bitmap, uint64_t start, uint64_t len); int xbitmap_set(struct xbitmap *bitmap, uint64_t start, uint64_t len); int xbitmap_disunion(struct xbitmap *bitmap, struct xbitmap *sub); int xbitmap_set_btcur_path(struct xbitmap *bitmap, @@ -42,4 +37,6 @@ typedef int (*xbitmap_walk_bits_fn)(uint64_t bit, void *priv); int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn, void *priv); +bool xbitmap_empty(struct xbitmap *bitmap); + #endif /* __XFS_SCRUB_BITMAP_H__ */ -- GitLab From a47bd1e0e690d0296c3e48fc3d6f2d359c222d6c Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:37 -0700 Subject: [PATCH 2625/5631] xfs: introduce bitmap type for AG blocks Create a typechecked bitmap for extents within an AG. Online repair uses bitmaps to store various different types of numbers, so let's make it obvious when we're storing xfs_agblock_t (and later xfs_fsblock_t) versus anything else. In subsequent patches, we're going to use agblock bitmaps to enhance the rmapbt checker to look for discrepancies between the rmapbt records and AG metadata block usage. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bitmap.h | 48 +++++++++++++++++++++++++++++++++++++++++++ fs/xfs/scrub/repair.h | 1 + 2 files changed, 49 insertions(+) diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 2ec4e1f3f24c..972d5445cdb6 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -39,4 +39,52 @@ int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn, bool xbitmap_empty(struct xbitmap *bitmap); +/* Bitmaps, but for type-checked for xfs_agblock_t */ + +struct xagb_bitmap { + struct xbitmap agbitmap; +}; + +static inline void xagb_bitmap_init(struct xagb_bitmap *bitmap) +{ + xbitmap_init(&bitmap->agbitmap); +} + +static inline void xagb_bitmap_destroy(struct xagb_bitmap *bitmap) +{ + xbitmap_destroy(&bitmap->agbitmap); +} + +static inline int xagb_bitmap_clear(struct xagb_bitmap *bitmap, + xfs_agblock_t start, xfs_extlen_t len) +{ + return xbitmap_clear(&bitmap->agbitmap, start, len); +} +static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap, + xfs_agblock_t start, xfs_extlen_t len) +{ + return xbitmap_set(&bitmap->agbitmap, start, len); +} + +static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap, + struct xagb_bitmap *sub) +{ + return xbitmap_disunion(&bitmap->agbitmap, &sub->agbitmap); +} + +static inline uint32_t xagb_bitmap_hweight(struct xagb_bitmap *bitmap) +{ + return xbitmap_hweight(&bitmap->agbitmap); +} +static inline bool xagb_bitmap_empty(struct xagb_bitmap *bitmap) +{ + return xbitmap_empty(&bitmap->agbitmap); +} + +static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap, + xbitmap_walk_fn fn, void *priv) +{ + return xbitmap_walk(&bitmap->agbitmap, fn, priv); +} + #endif /* __XFS_SCRUB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 4fbb52228c48..dce791c679ee 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -31,6 +31,7 @@ int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb, const struct xfs_buf_ops *ops); struct xbitmap; +struct xagb_bitmap; int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink); int xrep_invalidate_blocks(struct xfs_scrub *sc, struct xbitmap *btlist); -- GitLab From fed050f3452da070fa90fc1b02c2bc2219d687a7 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:38 -0700 Subject: [PATCH 2626/5631] xfs: cross-reference rmap records with ag btrees Strengthen the rmap btree record checker a little more by comparing OWN_FS and OWN_LOG reverse mappings against the AG headers and internal logs, respectively. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/Makefile | 2 +- fs/xfs/scrub/bitmap.c | 22 ++++++ fs/xfs/scrub/bitmap.h | 21 ++++++ fs/xfs/scrub/rmap.c | 159 +++++++++++++++++++++++++++++++++++++++++- 4 files changed, 202 insertions(+), 2 deletions(-) diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index ac9d03cd2623..16e4eb431230 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -148,6 +148,7 @@ xfs-y += $(addprefix scrub/, \ agheader.o \ alloc.o \ attr.o \ + bitmap.o \ bmap.o \ btree.o \ common.o \ @@ -172,7 +173,6 @@ xfs-$(CONFIG_XFS_QUOTA) += scrub/quota.o ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y) xfs-y += $(addprefix scrub/, \ agheader_repair.o \ - bitmap.o \ repair.o \ ) endif diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index dc139f0031dc..85e5beda186f 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -396,3 +396,25 @@ xbitmap_empty( { return bitmap->xb_root.rb_root.rb_node == NULL; } + +/* Is the start of the range set or clear? And for how long? */ +bool +xbitmap_test( + struct xbitmap *bitmap, + uint64_t start, + uint64_t *len) +{ + struct xbitmap_node *bn; + uint64_t last = start + *len - 1; + + bn = xbitmap_tree_iter_first(&bitmap->xb_root, start, last); + if (!bn) + return false; + if (bn->bn_start <= start) { + if (bn->bn_last < last) + *len = bn->bn_last - start + 1; + return true; + } + *len = bn->bn_start - start; + return false; +} diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 972d5445cdb6..55441feb039f 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -38,6 +38,7 @@ int xbitmap_walk_bits(struct xbitmap *bitmap, xbitmap_walk_bits_fn fn, void *priv); bool xbitmap_empty(struct xbitmap *bitmap); +bool xbitmap_test(struct xbitmap *bitmap, uint64_t start, uint64_t *len); /* Bitmaps, but for type-checked for xfs_agblock_t */ @@ -66,6 +67,26 @@ static inline int xagb_bitmap_set(struct xagb_bitmap *bitmap, return xbitmap_set(&bitmap->agbitmap, start, len); } +static inline bool +xagb_bitmap_test( + struct xagb_bitmap *bitmap, + xfs_agblock_t start, + xfs_extlen_t *len) +{ + uint64_t biglen = *len; + bool ret; + + ret = xbitmap_test(&bitmap->agbitmap, start, &biglen); + + if (start + biglen >= UINT_MAX) { + ASSERT(0); + biglen = UINT_MAX - start; + } + + *len = biglen; + return ret; +} + static inline int xagb_bitmap_disunion(struct xagb_bitmap *bitmap, struct xagb_bitmap *sub) { diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 6d7e294110a2..759349ccca26 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -12,10 +12,12 @@ #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_refcount.h" +#include "xfs_ag.h" +#include "xfs_bit.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "xfs_ag.h" +#include "scrub/bitmap.h" /* * Set us up to scrub reverse mapping btrees. @@ -45,6 +47,13 @@ struct xchk_rmap { * that could be one. */ struct xfs_rmap_irec prev_rec; + + /* Bitmaps containing all blocks for each type of AG metadata. */ + struct xagb_bitmap fs_owned; + struct xagb_bitmap log_owned; + + /* Did we complete the AG space metadata bitmaps? */ + bool bitmaps_complete; }; /* Cross-reference a rmap against the refcount btree. */ @@ -249,6 +258,68 @@ xchk_rmapbt_check_mergeable( memcpy(&cr->prev_rec, irec, sizeof(struct xfs_rmap_irec)); } +/* Compare an rmap for AG metadata against the metadata walk. */ +STATIC int +xchk_rmapbt_mark_bitmap( + struct xchk_btree *bs, + struct xchk_rmap *cr, + const struct xfs_rmap_irec *irec) +{ + struct xfs_scrub *sc = bs->sc; + struct xagb_bitmap *bmp = NULL; + xfs_extlen_t fsbcount = irec->rm_blockcount; + + /* + * Skip corrupt records. It is essential that we detect records in the + * btree that cannot overlap but do, flag those as CORRUPT, and skip + * the bitmap comparison to avoid generating false XCORRUPT reports. + */ + if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) + return 0; + + /* + * If the AG metadata walk didn't complete, there's no point in + * comparing against partial results. + */ + if (!cr->bitmaps_complete) + return 0; + + switch (irec->rm_owner) { + case XFS_RMAP_OWN_FS: + bmp = &cr->fs_owned; + break; + case XFS_RMAP_OWN_LOG: + bmp = &cr->log_owned; + break; + } + + if (!bmp) + return 0; + + if (xagb_bitmap_test(bmp, irec->rm_startblock, &fsbcount)) { + /* + * The start of this reverse mapping corresponds to a set + * region in the bitmap. If the mapping covers more area than + * the set region, then it covers space that wasn't found by + * the AG metadata walk. + */ + if (fsbcount < irec->rm_blockcount) + xchk_btree_xref_set_corrupt(bs->sc, + bs->sc->sa.rmap_cur, 0); + } else { + /* + * The start of this reverse mapping does not correspond to a + * completely set region in the bitmap. The region wasn't + * fully set by walking the AG metadata, so this is a + * cross-referencing corruption. + */ + xchk_btree_xref_set_corrupt(bs->sc, bs->sc->sa.rmap_cur, 0); + } + + /* Unset the region so that we can detect missing rmap records. */ + return xagb_bitmap_clear(bmp, irec->rm_startblock, irec->rm_blockcount); +} + /* Scrub an rmapbt record. */ STATIC int xchk_rmapbt_rec( @@ -268,9 +339,80 @@ xchk_rmapbt_rec( xchk_rmapbt_check_mergeable(bs, cr, &irec); xchk_rmapbt_check_overlapping(bs, cr, &irec); xchk_rmapbt_xref(bs->sc, &irec); + + return xchk_rmapbt_mark_bitmap(bs, cr, &irec); +} + +/* + * Set up bitmaps mapping all the AG metadata to compare with the rmapbt + * records. + */ +STATIC int +xchk_rmapbt_walk_ag_metadata( + struct xfs_scrub *sc, + struct xchk_rmap *cr) +{ + struct xfs_mount *mp = sc->mp; + int error; + + /* OWN_FS: AG headers */ + error = xagb_bitmap_set(&cr->fs_owned, XFS_SB_BLOCK(mp), + XFS_AGFL_BLOCK(mp) - XFS_SB_BLOCK(mp) + 1); + if (error) + goto out; + + /* OWN_LOG: Internal log */ + if (xfs_ag_contains_log(mp, sc->sa.pag->pag_agno)) { + error = xagb_bitmap_set(&cr->log_owned, + XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart), + mp->m_sb.sb_logblocks); + if (error) + goto out; + } + +out: + /* + * If there's an error, set XFAIL and disable the bitmap + * cross-referencing checks, but proceed with the scrub anyway. + */ + if (error) + xchk_btree_xref_process_error(sc, sc->sa.rmap_cur, + sc->sa.rmap_cur->bc_nlevels - 1, &error); + else + cr->bitmaps_complete = true; return 0; } +/* + * Check for set regions in the bitmaps; if there are any, the rmap records do + * not describe all the AG metadata. + */ +STATIC void +xchk_rmapbt_check_bitmaps( + struct xfs_scrub *sc, + struct xchk_rmap *cr) +{ + struct xfs_btree_cur *cur = sc->sa.rmap_cur; + unsigned int level; + + if (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | + XFS_SCRUB_OFLAG_XFAIL)) + return; + if (!cur) + return; + level = cur->bc_nlevels - 1; + + /* + * Any bitmap with bits still set indicates that the reverse mapping + * doesn't cover the entire primary structure. + */ + if (xagb_bitmap_hweight(&cr->fs_owned) != 0) + xchk_btree_xref_set_corrupt(sc, cur, level); + + if (xagb_bitmap_hweight(&cr->log_owned) != 0) + xchk_btree_xref_set_corrupt(sc, cur, level); +} + /* Scrub the rmap btree for some AG. */ int xchk_rmapbt( @@ -283,8 +425,23 @@ xchk_rmapbt( if (!cr) return -ENOMEM; + xagb_bitmap_init(&cr->fs_owned); + xagb_bitmap_init(&cr->log_owned); + + error = xchk_rmapbt_walk_ag_metadata(sc, cr); + if (error) + goto out; + error = xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec, &XFS_RMAP_OINFO_AG, cr); + if (error) + goto out; + + xchk_rmapbt_check_bitmaps(sc, cr); + +out: + xagb_bitmap_destroy(&cr->log_owned); + xagb_bitmap_destroy(&cr->fs_owned); kfree(cr); return error; } -- GitLab From 3a3108ea8c1d4f33ca49fa9fc80e6a6e450654cf Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:38 -0700 Subject: [PATCH 2627/5631] xfs: cross-reference rmap records with free space btrees Strengthen the rmap btree record checker a little more by comparing OWN_AG reverse mappings against the free space btrees, the rmap btree, and the AGFL. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/bitmap.c | 33 ++++++++++++++++++++++ fs/xfs/scrub/bitmap.h | 3 ++ fs/xfs/scrub/rmap.c | 66 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 102 insertions(+) diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index 85e5beda186f..0c959be396ea 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -6,6 +6,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" +#include "xfs_bit.h" #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" @@ -262,6 +263,38 @@ xbitmap_disunion( * For the 300th record we just exit, with the list being [1, 4, 2, 3]. */ +/* Mark a btree block to the agblock bitmap. */ +STATIC int +xagb_bitmap_visit_btblock( + struct xfs_btree_cur *cur, + int level, + void *priv) +{ + struct xagb_bitmap *bitmap = priv; + struct xfs_buf *bp; + xfs_fsblock_t fsbno; + xfs_agblock_t agbno; + + xfs_btree_get_block(cur, level, &bp); + if (!bp) + return 0; + + fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); + agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno); + + return xagb_bitmap_set(bitmap, agbno, 1); +} + +/* Mark all (per-AG) btree blocks in the agblock bitmap. */ +int +xagb_bitmap_set_btblocks( + struct xagb_bitmap *bitmap, + struct xfs_btree_cur *cur) +{ + return xfs_btree_visit_blocks(cur, xagb_bitmap_visit_btblock, + XFS_BTREE_VISIT_ALL, bitmap); +} + /* * Record all the buffers pointed to by the btree cursor. Callers already * engaged in a btree walk should call this function to capture the list of diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h index 55441feb039f..84981724ecaf 100644 --- a/fs/xfs/scrub/bitmap.h +++ b/fs/xfs/scrub/bitmap.h @@ -108,4 +108,7 @@ static inline int xagb_bitmap_walk(struct xagb_bitmap *bitmap, return xbitmap_walk(&bitmap->agbitmap, fn, priv); } +int xagb_bitmap_set_btblocks(struct xagb_bitmap *bitmap, + struct xfs_btree_cur *cur); + #endif /* __XFS_SCRUB_BITMAP_H__ */ diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 759349ccca26..1febadb269c5 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -7,13 +7,17 @@ #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" +#include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_trans.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_refcount.h" #include "xfs_ag.h" #include "xfs_bit.h" +#include "xfs_alloc.h" +#include "xfs_alloc_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -51,6 +55,7 @@ struct xchk_rmap { /* Bitmaps containing all blocks for each type of AG metadata. */ struct xagb_bitmap fs_owned; struct xagb_bitmap log_owned; + struct xagb_bitmap ag_owned; /* Did we complete the AG space metadata bitmaps? */ bool bitmaps_complete; @@ -291,6 +296,9 @@ xchk_rmapbt_mark_bitmap( case XFS_RMAP_OWN_LOG: bmp = &cr->log_owned; break; + case XFS_RMAP_OWN_AG: + bmp = &cr->ag_owned; + break; } if (!bmp) @@ -343,9 +351,26 @@ xchk_rmapbt_rec( return xchk_rmapbt_mark_bitmap(bs, cr, &irec); } +/* Add an AGFL block to the rmap list. */ +STATIC int +xchk_rmapbt_walk_agfl( + struct xfs_mount *mp, + xfs_agblock_t agbno, + void *priv) +{ + struct xagb_bitmap *bitmap = priv; + + return xagb_bitmap_set(bitmap, agbno, 1); +} + /* * Set up bitmaps mapping all the AG metadata to compare with the rmapbt * records. + * + * Grab our own btree cursors here if the scrub setup function didn't give us a + * btree cursor due to reports of poor health. We need to find out if the + * rmapbt disagrees with primary metadata btrees to tag the rmapbt as being + * XCORRUPT. */ STATIC int xchk_rmapbt_walk_ag_metadata( @@ -353,6 +378,9 @@ xchk_rmapbt_walk_ag_metadata( struct xchk_rmap *cr) { struct xfs_mount *mp = sc->mp; + struct xfs_buf *agfl_bp; + struct xfs_agf *agf = sc->sa.agf_bp->b_addr; + struct xfs_btree_cur *cur; int error; /* OWN_FS: AG headers */ @@ -370,6 +398,39 @@ xchk_rmapbt_walk_ag_metadata( goto out; } + /* OWN_AG: bnobt, cntbt, rmapbt, and AGFL */ + cur = sc->sa.bno_cur; + if (!cur) + cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp, + sc->sa.pag, XFS_BTNUM_BNO); + error = xagb_bitmap_set_btblocks(&cr->ag_owned, cur); + if (cur != sc->sa.bno_cur) + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + + cur = sc->sa.cnt_cur; + if (!cur) + cur = xfs_allocbt_init_cursor(sc->mp, sc->tp, sc->sa.agf_bp, + sc->sa.pag, XFS_BTNUM_CNT); + error = xagb_bitmap_set_btblocks(&cr->ag_owned, cur); + if (cur != sc->sa.cnt_cur) + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + + error = xagb_bitmap_set_btblocks(&cr->ag_owned, sc->sa.rmap_cur); + if (error) + goto out; + + error = xfs_alloc_read_agfl(sc->sa.pag, sc->tp, &agfl_bp); + if (error) + goto out; + + error = xfs_agfl_walk(sc->mp, agf, agfl_bp, xchk_rmapbt_walk_agfl, + &cr->ag_owned); + xfs_trans_brelse(sc->tp, agfl_bp); + out: /* * If there's an error, set XFAIL and disable the bitmap @@ -411,6 +472,9 @@ xchk_rmapbt_check_bitmaps( if (xagb_bitmap_hweight(&cr->log_owned) != 0) xchk_btree_xref_set_corrupt(sc, cur, level); + + if (xagb_bitmap_hweight(&cr->ag_owned) != 0) + xchk_btree_xref_set_corrupt(sc, cur, level); } /* Scrub the rmap btree for some AG. */ @@ -427,6 +491,7 @@ xchk_rmapbt( xagb_bitmap_init(&cr->fs_owned); xagb_bitmap_init(&cr->log_owned); + xagb_bitmap_init(&cr->ag_owned); error = xchk_rmapbt_walk_ag_metadata(sc, cr); if (error) @@ -440,6 +505,7 @@ xchk_rmapbt( xchk_rmapbt_check_bitmaps(sc, cr); out: + xagb_bitmap_destroy(&cr->ag_owned); xagb_bitmap_destroy(&cr->log_owned); xagb_bitmap_destroy(&cr->fs_owned); kfree(cr); -- GitLab From 0abe6fc53bdb10a5b0b5235043ca1acc749fe069 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:39 -0700 Subject: [PATCH 2628/5631] xfs: cross-reference rmap records with inode btrees Strengthen the rmap btree record checker a little more by comparing OWN_INOBT reverse mappings against the inode btrees. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/rmap.c | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 1febadb269c5..834b32063301 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -18,6 +18,7 @@ #include "xfs_bit.h" #include "xfs_alloc.h" #include "xfs_alloc_btree.h" +#include "xfs_ialloc_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -56,6 +57,7 @@ struct xchk_rmap { struct xagb_bitmap fs_owned; struct xagb_bitmap log_owned; struct xagb_bitmap ag_owned; + struct xagb_bitmap inobt_owned; /* Did we complete the AG space metadata bitmaps? */ bool bitmaps_complete; @@ -299,6 +301,9 @@ xchk_rmapbt_mark_bitmap( case XFS_RMAP_OWN_AG: bmp = &cr->ag_owned; break; + case XFS_RMAP_OWN_INOBT: + bmp = &cr->inobt_owned; + break; } if (!bmp) @@ -430,6 +435,31 @@ xchk_rmapbt_walk_ag_metadata( error = xfs_agfl_walk(sc->mp, agf, agfl_bp, xchk_rmapbt_walk_agfl, &cr->ag_owned); xfs_trans_brelse(sc->tp, agfl_bp); + if (error) + goto out; + + /* OWN_INOBT: inobt, finobt */ + cur = sc->sa.ino_cur; + if (!cur) + cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, sc->sa.agi_bp, + XFS_BTNUM_INO); + error = xagb_bitmap_set_btblocks(&cr->inobt_owned, cur); + if (cur != sc->sa.ino_cur) + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + + if (xfs_has_finobt(sc->mp)) { + cur = sc->sa.fino_cur; + if (!cur) + cur = xfs_inobt_init_cursor(sc->sa.pag, sc->tp, + sc->sa.agi_bp, XFS_BTNUM_FINO); + error = xagb_bitmap_set_btblocks(&cr->inobt_owned, cur); + if (cur != sc->sa.fino_cur) + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + } out: /* @@ -475,6 +505,9 @@ xchk_rmapbt_check_bitmaps( if (xagb_bitmap_hweight(&cr->ag_owned) != 0) xchk_btree_xref_set_corrupt(sc, cur, level); + + if (xagb_bitmap_hweight(&cr->inobt_owned) != 0) + xchk_btree_xref_set_corrupt(sc, cur, level); } /* Scrub the rmap btree for some AG. */ @@ -492,6 +525,7 @@ xchk_rmapbt( xagb_bitmap_init(&cr->fs_owned); xagb_bitmap_init(&cr->log_owned); xagb_bitmap_init(&cr->ag_owned); + xagb_bitmap_init(&cr->inobt_owned); error = xchk_rmapbt_walk_ag_metadata(sc, cr); if (error) @@ -505,6 +539,7 @@ xchk_rmapbt( xchk_rmapbt_check_bitmaps(sc, cr); out: + xagb_bitmap_destroy(&cr->inobt_owned); xagb_bitmap_destroy(&cr->ag_owned); xagb_bitmap_destroy(&cr->log_owned); xagb_bitmap_destroy(&cr->fs_owned); -- GitLab From 4f5e304248ab4939e9aef58244041c194f01f0b5 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:39 -0700 Subject: [PATCH 2629/5631] xfs: cross-reference rmap records with refcount btrees Strengthen the rmap btree record checker a little more by comparing OWN_REFCBT reverse mappings against the refcount btrees. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/scrub/rmap.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 834b32063301..d29a26ecddd6 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -19,6 +19,7 @@ #include "xfs_alloc.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc_btree.h" +#include "xfs_refcount_btree.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -58,6 +59,7 @@ struct xchk_rmap { struct xagb_bitmap log_owned; struct xagb_bitmap ag_owned; struct xagb_bitmap inobt_owned; + struct xagb_bitmap refcbt_owned; /* Did we complete the AG space metadata bitmaps? */ bool bitmaps_complete; @@ -304,6 +306,9 @@ xchk_rmapbt_mark_bitmap( case XFS_RMAP_OWN_INOBT: bmp = &cr->inobt_owned; break; + case XFS_RMAP_OWN_REFC: + bmp = &cr->refcbt_owned; + break; } if (!bmp) @@ -461,6 +466,19 @@ xchk_rmapbt_walk_ag_metadata( goto out; } + /* OWN_REFC: refcountbt */ + if (xfs_has_reflink(sc->mp)) { + cur = sc->sa.refc_cur; + if (!cur) + cur = xfs_refcountbt_init_cursor(sc->mp, sc->tp, + sc->sa.agf_bp, sc->sa.pag); + error = xagb_bitmap_set_btblocks(&cr->refcbt_owned, cur); + if (cur != sc->sa.refc_cur) + xfs_btree_del_cursor(cur, error); + if (error) + goto out; + } + out: /* * If there's an error, set XFAIL and disable the bitmap @@ -508,6 +526,9 @@ xchk_rmapbt_check_bitmaps( if (xagb_bitmap_hweight(&cr->inobt_owned) != 0) xchk_btree_xref_set_corrupt(sc, cur, level); + + if (xagb_bitmap_hweight(&cr->refcbt_owned) != 0) + xchk_btree_xref_set_corrupt(sc, cur, level); } /* Scrub the rmap btree for some AG. */ @@ -526,6 +547,7 @@ xchk_rmapbt( xagb_bitmap_init(&cr->log_owned); xagb_bitmap_init(&cr->ag_owned); xagb_bitmap_init(&cr->inobt_owned); + xagb_bitmap_init(&cr->refcbt_owned); error = xchk_rmapbt_walk_ag_metadata(sc, cr); if (error) @@ -539,6 +561,7 @@ xchk_rmapbt( xchk_rmapbt_check_bitmaps(sc, cr); out: + xagb_bitmap_destroy(&cr->refcbt_owned); xagb_bitmap_destroy(&cr->inobt_owned); xagb_bitmap_destroy(&cr->ag_owned); xagb_bitmap_destroy(&cr->log_owned); -- GitLab From a9248538facc3d9e769489e50a544509c2f9cebe Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:05:04 -0700 Subject: [PATCH 2630/5631] xfs: stabilize the dirent name transformation function used for ascii-ci dir hash computation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Back in the old days, the "ascii-ci" feature was created to implement case-insensitive directory entry lookups for latin1-encoded names and remove the large overhead of Samba's case-insensitive lookup code. UTF8 names were not allowed, but nobody explicitly wrote in the documentation that this was only expected to work if the system used latin1 names. The kernel tolower function was selected to prepare names for hashed lookups. There's a major discrepancy in the function that computes directory entry hashes for filesystems that have ASCII case-insensitive lookups enabled. The root of this is that the kernel and glibc's tolower implementations have differing behavior for extended ASCII accented characters. I wrote a program to spit out characters for which the tolower() return value is different from the input: glibc tolower: 65:A 66:B 67:C 68:D 69:E 70:F 71:G 72:H 73:I 74:J 75:K 76:L 77:M 78:N 79:O 80:P 81:Q 82:R 83:S 84:T 85:U 86:V 87:W 88:X 89:Y 90:Z kernel tolower: 65:A 66:B 67:C 68:D 69:E 70:F 71:G 72:H 73:I 74:J 75:K 76:L 77:M 78:N 79:O 80:P 81:Q 82:R 83:S 84:T 85:U 86:V 87:W 88:X 89:Y 90:Z 192:À 193:Á 194:Â 195:Ã 196:Ä 197:Å 198:Æ 199:Ç 200:È 201:É 202:Ê 203:Ë 204:Ì 205:Í 206:Î 207:Ï 208:Ð 209:Ñ 210:Ò 211:Ó 212:Ô 213:Õ 214:Ö 215:× 216:Ø 217:Ù 218:Ú 219:Û 220:Ü 221:Ý 222:Þ Which means that the kernel and userspace do not agree on the hash value for a directory filename that contains those higher values. The hash values are written into the leaf index block of directories that are larger than two blocks in size, which means that xfs_repair will flag these directories as having corrupted hash indexes and rewrite the index with hash values that the kernel now will not recognize. Because the ascii-ci feature is not frequently enabled and the kernel touches filesystems far more frequently than xfs_repair does, fix this by encoding the kernel's toupper predicate and tolower functions into libxfs. Give the new functions less provocative names to make it really obvious that this is a pre-hash name preparation function, and nothing else. This change makes userspace's behavior consistent with the kernel. Found by auditing obfuscate_name in xfs_metadump as part of working on parent pointers, wondering how it could possibly work correctly with ci filesystems, writing a test tool to create a directory with hash-colliding names, and watching xfs_repair flag it. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/libxfs/xfs_dir2.c | 5 +++-- fs/xfs/libxfs/xfs_dir2.h | 31 +++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 92bac3373f1f..f5462fd582d5 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -64,7 +64,7 @@ xfs_ascii_ci_hashname( int i; for (i = 0, hash = 0; i < name->len; i++) - hash = tolower(name->name[i]) ^ rol32(hash, 7); + hash = xfs_ascii_ci_xfrm(name->name[i]) ^ rol32(hash, 7); return hash; } @@ -85,7 +85,8 @@ xfs_ascii_ci_compname( for (i = 0; i < len; i++) { if (args->name[i] == name[i]) continue; - if (tolower(args->name[i]) != tolower(name[i])) + if (xfs_ascii_ci_xfrm(args->name[i]) != + xfs_ascii_ci_xfrm(name[i])) return XFS_CMP_DIFFERENT; result = XFS_CMP_CASE; } diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index dd39f17dd9a9..19af22a16c41 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -248,4 +248,35 @@ unsigned int xfs_dir3_data_end_offset(struct xfs_da_geometry *geo, struct xfs_dir2_data_hdr *hdr); bool xfs_dir2_namecheck(const void *name, size_t length); +/* + * The "ascii-ci" feature was created to speed up case-insensitive lookups for + * a Samba product. Because of the inherent problems with CI and UTF-8 + * encoding, etc, it was decided that Samba would be configured to export + * latin1/iso 8859-1 encodings as that covered >90% of the target markets for + * the product. Hence the "ascii-ci" casefolding code could be encoded into + * the XFS directory operations and remove all the overhead of casefolding from + * Samba. + * + * To provide consistent hashing behavior between the userspace and kernel, + * these functions prepare names for hashing by transforming specific bytes + * to other bytes. Robustness with other encodings is not guaranteed. + */ +static inline bool xfs_ascii_ci_need_xfrm(unsigned char c) +{ + if (c >= 0x41 && c <= 0x5a) /* A-Z */ + return true; + if (c >= 0xc0 && c <= 0xd6) /* latin A-O with accents */ + return true; + if (c >= 0xd8 && c <= 0xde) /* latin O-Y with accents */ + return true; + return false; +} + +static inline unsigned char xfs_ascii_ci_xfrm(unsigned char c) +{ + if (xfs_ascii_ci_need_xfrm(c)) + c -= 'A' - 'a'; + return c; +} + #endif /* __XFS_DIR2_H__ */ -- GitLab From 6db09a8d0377866b99882f8d44e4ba1a1bf6c6a1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:05:05 -0700 Subject: [PATCH 2631/5631] xfs: test the ascii case-insensitive hash Now that we've made kernel and userspace use the same tolower code for computing directory index hashes, add that to the selftest code. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_dahash_test.c | 211 ++++++++++++++++++++------------------- 1 file changed, 111 insertions(+), 100 deletions(-) diff --git a/fs/xfs/xfs_dahash_test.c b/fs/xfs/xfs_dahash_test.c index 230651ab5ce4..0dab5941e080 100644 --- a/fs/xfs/xfs_dahash_test.c +++ b/fs/xfs/xfs_dahash_test.c @@ -9,6 +9,9 @@ #include "xfs_format.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_dir2_priv.h" #include "xfs_dahash_test.h" /* 4096 random bytes */ @@ -533,108 +536,109 @@ static struct dahash_test { uint16_t start; /* random 12 bit offset in buf */ uint16_t length; /* random 8 bit length of test */ xfs_dahash_t dahash; /* expected dahash result */ + xfs_dahash_t ascii_ci_dahash; /* expected ascii-ci dahash result */ } test[] __initdata = { - {0x0567, 0x0097, 0x96951389}, - {0x0869, 0x0055, 0x6455ab4f}, - {0x0c51, 0x00be, 0x8663afde}, - {0x044a, 0x00fc, 0x98fbe432}, - {0x0f29, 0x0079, 0x42371997}, - {0x08ba, 0x0052, 0x942be4f7}, - {0x01f2, 0x0013, 0x5262687e}, - {0x09e3, 0x00e2, 0x8ffb0908}, - {0x007c, 0x0051, 0xb3158491}, - {0x0854, 0x001f, 0x83bb20d9}, - {0x031b, 0x0008, 0x98970bdf}, - {0x0de7, 0x0027, 0xbfbf6f6c}, - {0x0f76, 0x0005, 0x906a7105}, - {0x092e, 0x00d0, 0x86631850}, - {0x0233, 0x0082, 0xdbdd914e}, - {0x04c9, 0x0075, 0x5a400a9e}, - {0x0b66, 0x0099, 0xae128b45}, - {0x000d, 0x00ed, 0xe61c216a}, - {0x0a31, 0x003d, 0xf69663b9}, - {0x00a3, 0x0052, 0x643c39ae}, - {0x0125, 0x00d5, 0x7c310b0d}, - {0x0105, 0x004a, 0x06a77e74}, - {0x0858, 0x008e, 0x265bc739}, - {0x045e, 0x0095, 0x13d6b192}, - {0x0dab, 0x003c, 0xc4498704}, - {0x00cd, 0x00b5, 0x802a4e2d}, - {0x069b, 0x008c, 0x5df60f71}, - {0x0454, 0x006c, 0x5f03d8bb}, - {0x040e, 0x0032, 0x0ce513b5}, - {0x0874, 0x00e2, 0x6a811fb3}, - {0x0521, 0x00b4, 0x93296833}, - {0x0ddc, 0x00cf, 0xf9305338}, - {0x0a70, 0x0023, 0x239549ea}, - {0x083e, 0x0027, 0x2d88ba97}, - {0x0241, 0x00a7, 0xfe0b32e1}, - {0x0dfc, 0x0096, 0x1a11e815}, - {0x023e, 0x001e, 0xebc9a1f3}, - {0x067e, 0x0066, 0xb1067f81}, - {0x09ea, 0x000e, 0x46fd7247}, - {0x036b, 0x008c, 0x1a39acdf}, - {0x078f, 0x0030, 0x964042ab}, - {0x085c, 0x008f, 0x1829edab}, - {0x02ec, 0x009f, 0x6aefa72d}, - {0x043b, 0x00ce, 0x65642ff5}, - {0x0a32, 0x00b8, 0xbd82759e}, - {0x0d3c, 0x0087, 0xf4d66d54}, - {0x09ec, 0x008a, 0x06bfa1ff}, - {0x0902, 0x0015, 0x755025d2}, - {0x08fe, 0x000e, 0xf690ce2d}, - {0x00fb, 0x00dc, 0xe55f1528}, - {0x0eaa, 0x003a, 0x0fe0a8d7}, - {0x05fb, 0x0006, 0x86281cfb}, - {0x0dd1, 0x00a7, 0x60ab51b4}, - {0x0005, 0x001b, 0xf51d969b}, - {0x077c, 0x00dd, 0xc2fed268}, - {0x0575, 0x00f5, 0x432c0b1a}, - {0x05be, 0x0088, 0x78baa04b}, - {0x0c89, 0x0068, 0xeda9e428}, - {0x0f5c, 0x0068, 0xec143c76}, - {0x06a8, 0x0009, 0xd72651ce}, - {0x060f, 0x008e, 0x765426cd}, - {0x07b1, 0x0047, 0x2cfcfa0c}, - {0x04f1, 0x0041, 0x55b172f9}, - {0x0e05, 0x00ac, 0x61efde93}, - {0x0bf7, 0x0097, 0x05b83eee}, - {0x04e9, 0x00f3, 0x9928223a}, - {0x023a, 0x0005, 0xdfada9bc}, - {0x0acb, 0x000e, 0x2217cecd}, - {0x0148, 0x0060, 0xbc3f7405}, - {0x0764, 0x0059, 0xcbc201b1}, - {0x021f, 0x0059, 0x5d6b2256}, - {0x0f1e, 0x006c, 0xdefeeb45}, - {0x071c, 0x00b9, 0xb9b59309}, - {0x0564, 0x0063, 0xae064271}, - {0x0b14, 0x0044, 0xdb867d9b}, - {0x0e5a, 0x0055, 0xff06b685}, - {0x015e, 0x00ba, 0x1115ccbc}, - {0x0379, 0x00e6, 0x5f4e58dd}, - {0x013b, 0x0067, 0x4897427e}, - {0x0e64, 0x0071, 0x7af2b7a4}, - {0x0a11, 0x0050, 0x92105726}, - {0x0109, 0x0055, 0xd0d000f9}, - {0x00aa, 0x0022, 0x815d229d}, - {0x09ac, 0x004f, 0x02f9d985}, - {0x0e1b, 0x00ce, 0x5cf92ab4}, - {0x08af, 0x00d8, 0x17ca72d1}, - {0x0e33, 0x000a, 0xda2dba6b}, - {0x0ee3, 0x006a, 0xb00048e5}, - {0x0648, 0x001a, 0x2364b8cb}, - {0x0315, 0x0085, 0x0596fd0d}, - {0x0fbb, 0x003e, 0x298230ca}, - {0x0422, 0x006a, 0x78ada4ab}, - {0x04ba, 0x0073, 0xced1fbc2}, - {0x007d, 0x0061, 0x4b7ff236}, - {0x070b, 0x00d0, 0x261cf0ae}, - {0x0c1a, 0x0035, 0x8be92ee2}, - {0x0af8, 0x0063, 0x824dcf03}, - {0x08f8, 0x006d, 0xd289710c}, - {0x021b, 0x00ee, 0x6ac1c41d}, - {0x05b5, 0x00da, 0x8e52f0e2}, + {0x0567, 0x0097, 0x96951389, 0xc153aa0d}, + {0x0869, 0x0055, 0x6455ab4f, 0xd07f69bf}, + {0x0c51, 0x00be, 0x8663afde, 0xf9add90c}, + {0x044a, 0x00fc, 0x98fbe432, 0xbf2abb76}, + {0x0f29, 0x0079, 0x42371997, 0x282588b3}, + {0x08ba, 0x0052, 0x942be4f7, 0x2e023547}, + {0x01f2, 0x0013, 0x5262687e, 0x5266287e}, + {0x09e3, 0x00e2, 0x8ffb0908, 0x1da892f3}, + {0x007c, 0x0051, 0xb3158491, 0xb67f9e63}, + {0x0854, 0x001f, 0x83bb20d9, 0x22bb21db}, + {0x031b, 0x0008, 0x98970bdf, 0x9cd70adf}, + {0x0de7, 0x0027, 0xbfbf6f6c, 0xae3f296c}, + {0x0f76, 0x0005, 0x906a7105, 0x906a7105}, + {0x092e, 0x00d0, 0x86631850, 0xa3f6ac04}, + {0x0233, 0x0082, 0xdbdd914e, 0x5d8c7aac}, + {0x04c9, 0x0075, 0x5a400a9e, 0x12f60711}, + {0x0b66, 0x0099, 0xae128b45, 0x7551310d}, + {0x000d, 0x00ed, 0xe61c216a, 0xc22d3c4c}, + {0x0a31, 0x003d, 0xf69663b9, 0x51960bf8}, + {0x00a3, 0x0052, 0x643c39ae, 0xa93c73a8}, + {0x0125, 0x00d5, 0x7c310b0d, 0xf221cbb3}, + {0x0105, 0x004a, 0x06a77e74, 0xa4ef4561}, + {0x0858, 0x008e, 0x265bc739, 0xd6c36d9b}, + {0x045e, 0x0095, 0x13d6b192, 0x5f5c1d62}, + {0x0dab, 0x003c, 0xc4498704, 0x10414654}, + {0x00cd, 0x00b5, 0x802a4e2d, 0xfbd17c9d}, + {0x069b, 0x008c, 0x5df60f71, 0x91ddca5f}, + {0x0454, 0x006c, 0x5f03d8bb, 0x5c59fce0}, + {0x040e, 0x0032, 0x0ce513b5, 0xa8cd99b1}, + {0x0874, 0x00e2, 0x6a811fb3, 0xca028316}, + {0x0521, 0x00b4, 0x93296833, 0x2c4d4880}, + {0x0ddc, 0x00cf, 0xf9305338, 0x2c94210d}, + {0x0a70, 0x0023, 0x239549ea, 0x22b561aa}, + {0x083e, 0x0027, 0x2d88ba97, 0x5cd8bb9d}, + {0x0241, 0x00a7, 0xfe0b32e1, 0x17b506b8}, + {0x0dfc, 0x0096, 0x1a11e815, 0xee4141bd}, + {0x023e, 0x001e, 0xebc9a1f3, 0x5689a1f3}, + {0x067e, 0x0066, 0xb1067f81, 0xd9952571}, + {0x09ea, 0x000e, 0x46fd7247, 0x42b57245}, + {0x036b, 0x008c, 0x1a39acdf, 0x58bf1586}, + {0x078f, 0x0030, 0x964042ab, 0xb04218b9}, + {0x085c, 0x008f, 0x1829edab, 0x9ceca89c}, + {0x02ec, 0x009f, 0x6aefa72d, 0x634cc2a7}, + {0x043b, 0x00ce, 0x65642ff5, 0x6c8a584e}, + {0x0a32, 0x00b8, 0xbd82759e, 0x0f96a34f}, + {0x0d3c, 0x0087, 0xf4d66d54, 0xb71ba5f4}, + {0x09ec, 0x008a, 0x06bfa1ff, 0x576ca80f}, + {0x0902, 0x0015, 0x755025d2, 0x517225c2}, + {0x08fe, 0x000e, 0xf690ce2d, 0xf690cf3d}, + {0x00fb, 0x00dc, 0xe55f1528, 0x707d7d92}, + {0x0eaa, 0x003a, 0x0fe0a8d7, 0x87638cc5}, + {0x05fb, 0x0006, 0x86281cfb, 0x86281cf9}, + {0x0dd1, 0x00a7, 0x60ab51b4, 0xe28ef00c}, + {0x0005, 0x001b, 0xf51d969b, 0xe71dd6d3}, + {0x077c, 0x00dd, 0xc2fed268, 0xdc30c555}, + {0x0575, 0x00f5, 0x432c0b1a, 0x81dd7d16}, + {0x05be, 0x0088, 0x78baa04b, 0xd69b433e}, + {0x0c89, 0x0068, 0xeda9e428, 0xe9b4fa0a}, + {0x0f5c, 0x0068, 0xec143c76, 0x9947067a}, + {0x06a8, 0x0009, 0xd72651ce, 0xd72651ee}, + {0x060f, 0x008e, 0x765426cd, 0x2099626f}, + {0x07b1, 0x0047, 0x2cfcfa0c, 0x1a4baa07}, + {0x04f1, 0x0041, 0x55b172f9, 0x15331a79}, + {0x0e05, 0x00ac, 0x61efde93, 0x320568cc}, + {0x0bf7, 0x0097, 0x05b83eee, 0xc72fb7a3}, + {0x04e9, 0x00f3, 0x9928223a, 0xe8c77de2}, + {0x023a, 0x0005, 0xdfada9bc, 0xdfadb9be}, + {0x0acb, 0x000e, 0x2217cecd, 0x0017d6cd}, + {0x0148, 0x0060, 0xbc3f7405, 0xf5fd6615}, + {0x0764, 0x0059, 0xcbc201b1, 0xbb089bf4}, + {0x021f, 0x0059, 0x5d6b2256, 0xa16a0a59}, + {0x0f1e, 0x006c, 0xdefeeb45, 0xfc34f9d6}, + {0x071c, 0x00b9, 0xb9b59309, 0xb645eae2}, + {0x0564, 0x0063, 0xae064271, 0x954dc6d1}, + {0x0b14, 0x0044, 0xdb867d9b, 0xdf432309}, + {0x0e5a, 0x0055, 0xff06b685, 0xa65ff257}, + {0x015e, 0x00ba, 0x1115ccbc, 0x11c365f4}, + {0x0379, 0x00e6, 0x5f4e58dd, 0x2d176d31}, + {0x013b, 0x0067, 0x4897427e, 0xc40532fe}, + {0x0e64, 0x0071, 0x7af2b7a4, 0x1fb7bf43}, + {0x0a11, 0x0050, 0x92105726, 0xb1185e51}, + {0x0109, 0x0055, 0xd0d000f9, 0x60a60bfd}, + {0x00aa, 0x0022, 0x815d229d, 0x215d379c}, + {0x09ac, 0x004f, 0x02f9d985, 0x10b90b20}, + {0x0e1b, 0x00ce, 0x5cf92ab4, 0x6a477573}, + {0x08af, 0x00d8, 0x17ca72d1, 0x385af156}, + {0x0e33, 0x000a, 0xda2dba6b, 0xda2dbb69}, + {0x0ee3, 0x006a, 0xb00048e5, 0xa9a2decc}, + {0x0648, 0x001a, 0x2364b8cb, 0x3364b1cb}, + {0x0315, 0x0085, 0x0596fd0d, 0xa651740f}, + {0x0fbb, 0x003e, 0x298230ca, 0x7fc617c7}, + {0x0422, 0x006a, 0x78ada4ab, 0xc576ae2a}, + {0x04ba, 0x0073, 0xced1fbc2, 0xaac8455b}, + {0x007d, 0x0061, 0x4b7ff236, 0x347d5739}, + {0x070b, 0x00d0, 0x261cf0ae, 0xc7fb1c10}, + {0x0c1a, 0x0035, 0x8be92ee2, 0x8be9b4e1}, + {0x0af8, 0x0063, 0x824dcf03, 0x53010388}, + {0x08f8, 0x006d, 0xd289710c, 0x30418edd}, + {0x021b, 0x00ee, 0x6ac1c41d, 0x2557e9a3}, + {0x05b5, 0x00da, 0x8e52f0e2, 0x98531012}, }; int __init @@ -644,12 +648,19 @@ xfs_dahash_test(void) unsigned int errors = 0; for (i = 0; i < ARRAY_SIZE(test); i++) { + struct xfs_name xname = { }; xfs_dahash_t hash; hash = xfs_da_hashname(test_buf + test[i].start, test[i].length); if (hash != test[i].dahash) errors++; + + xname.name = test_buf + test[i].start; + xname.len = test[i].length; + hash = xfs_ascii_ci_hashname(&xname); + if (hash != test[i].ascii_ci_dahash) + errors++; } if (errors) { -- GitLab From 7ba83850ca2691865713b307ed001bde5fddb084 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:05:19 -0700 Subject: [PATCH 2632/5631] xfs: deprecate the ascii-ci feature This feature is a mess -- the hash function has been broken for the entire 15 years of its existence if you create names with extended ascii bytes; metadump name obfuscation has silently failed for just as long; and the feature clashes horribly with the UTF8 encodings that most systems use today. There is exactly one fstest for this feature. In other words, this feature is crap. Let's deprecate it now so we can remove it from the codebase in 2030. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig --- Documentation/admin-guide/xfs.rst | 1 + fs/xfs/Kconfig | 27 +++++++++++++++++++++++++++ fs/xfs/xfs_super.c | 13 +++++++++++++ 3 files changed, 41 insertions(+) diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst index e2561416391c..e85a9404d5c0 100644 --- a/Documentation/admin-guide/xfs.rst +++ b/Documentation/admin-guide/xfs.rst @@ -240,6 +240,7 @@ Deprecated Mount Options Name Removal Schedule =========================== ================ Mounting with V4 filesystem September 2030 +Mounting ascii-ci filesystem September 2030 ikeep/noikeep September 2025 attr2/noattr2 September 2025 =========================== ================ diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 05bc865142b8..52e1823241fb 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -47,6 +47,33 @@ config XFS_SUPPORT_V4 To continue supporting the old V4 format (crc=0), say Y. To close off an attack surface, say N. +config XFS_SUPPORT_ASCII_CI + bool "Support deprecated case-insensitive ascii (ascii-ci=1) format" + depends on XFS_FS + default y + help + The ASCII case insensitivity filesystem feature only works correctly + on systems that have been coerced into using ISO 8859-1, and it does + not work on extended attributes. The kernel has no visibility into + the locale settings in userspace, so it corrupts UTF-8 names. + Enabling this feature makes XFS vulnerable to mixed case sensitivity + attacks. Because of this, the feature is deprecated. All users + should upgrade by backing up their files, reformatting, and restoring + from the backup. + + Administrators and users can detect such a filesystem by running + xfs_info against a filesystem mountpoint and checking for a string + beginning with "ascii-ci=". If the string "ascii-ci=1" is found, the + filesystem is a case-insensitive filesystem. If no such string is + found, please upgrade xfsprogs to the latest version and try again. + + This option will become default N in September 2025. Support for the + feature will be removed entirely in September 2030. Distributors + can say N here to withdraw support earlier. + + To continue supporting case-insensitivity (ascii-ci=1), say Y. + To close off an attack surface, say N. + config XFS_QUOTA bool "XFS Quota support" depends on XFS_FS diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4f814f9e12ab..4d2e87462ac4 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1548,6 +1548,19 @@ xfs_fs_fill_super( #endif } + /* ASCII case insensitivity is undergoing deprecation. */ + if (xfs_has_asciici(mp)) { +#ifdef CONFIG_XFS_SUPPORT_ASCII_CI + xfs_warn_once(mp, + "Deprecated ASCII case-insensitivity feature (ascii-ci=1) will not be supported after September 2030."); +#else + xfs_warn(mp, + "Deprecated ASCII case-insensitivity feature (ascii-ci=1) not supported by kernel."); + error = -EINVAL; + goto out_free_sb; +#endif + } + /* Filesystem claims it needs repair, so refuse the mount. */ if (xfs_has_needsrepair(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); -- GitLab From aa88019851a85df80cb77f143758b13aee09e3d9 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 12 Apr 2023 15:48:50 +1000 Subject: [PATCH 2633/5631] xfs: don't consider future format versions valid In commit fe08cc504448 we reworked the valid superblock version checks. If it is a V5 filesystem, it is always valid, then we checked if the version was less than V4 (reject) and then checked feature fields in the V4 flags to determine if it was valid. What we missed was that if the version is not V4 at this point, we shoudl reject the fs. i.e. the check current treats V6+ filesystems as if it was a v4 filesystem. Fix this. cc: stable@vger.kernel.org Fixes: fe08cc504448 ("xfs: open code sb verifier feature checks") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_sb.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 99cc03a298e2..ba0f17bc1dc0 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -72,7 +72,8 @@ xfs_sb_validate_v5_features( } /* - * We support all XFS versions newer than a v4 superblock with V2 directories. + * We current support XFS v5 formats with known features and v4 superblocks with + * at least V2 directories. */ bool xfs_sb_good_version( @@ -86,16 +87,16 @@ xfs_sb_good_version( if (xfs_sb_is_v5(sbp)) return xfs_sb_validate_v5_features(sbp); + /* versions prior to v4 are not supported */ + if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_4) + return false; + /* We must not have any unknown v4 feature bits set */ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) || ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS))) return false; - /* versions prior to v4 are not supported */ - if (XFS_SB_VERSION_NUM(sbp) < XFS_SB_VERSION_4) - return false; - /* V4 filesystems need v2 directories and unwritten extents */ if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT)) return false; -- GitLab From 4b827b3f305d1fcf837265f1e12acc22ee84327c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 12 Apr 2023 15:48:59 +1000 Subject: [PATCH 2634/5631] xfs: remove WARN when dquot cache insertion fails It just creates unnecessary bot noise these days. Reported-by: syzbot+6ae213503fb12e87934f@syzkaller.appspotmail.com Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/xfs_dquot.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 8fb90da89787..7f071757f278 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -798,7 +798,6 @@ xfs_qm_dqget_cache_insert( error = radix_tree_insert(tree, id, dqp); if (unlikely(error)) { /* Duplicate found! Caller must try again. */ - WARN_ON(error != -EEXIST); mutex_unlock(&qi->qi_tree_lock); trace_xfs_dqget_dup(dqp); return error; -- GitLab From c95356ca884885db702670e24933ee7f2b9f1754 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Apr 2023 15:49:10 +1000 Subject: [PATCH 2635/5631] xfs: _{attr,data}_map_shared should take ILOCK_EXCL until iread_extents is completely done While fuzzing the data fork extent count on a btree-format directory with xfs/375, I observed the following (excerpted) splat: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/libxfs/xfs_bmap.c, line: 1208 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 43192 at fs/xfs/xfs_message.c:104 assfail+0x46/0x4a [xfs] Call Trace: xfs_iread_extents+0x1af/0x210 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_dir_walk+0xb8/0x190 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent_count_parent_dentries+0x41/0x80 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent_validate+0x199/0x2e0 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent+0xdf/0x130 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_scrub_metadata+0x2b8/0x730 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_scrubv_metadata+0x38b/0x4d0 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_ioc_scrubv_metadata+0x111/0x160 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_file_ioctl+0x367/0xf50 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] __x64_sys_ioctl+0x82/0xa0 do_syscall_64+0x2b/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The cause of this is a race condition in xfs_ilock_data_map_shared, which performs an unlocked access to the data fork to guess which lock mode it needs: Thread 0 Thread 1 xfs_need_iread_extents xfs_ilock(..., ILOCK_EXCL) xfs_iread_extents xfs_need_iread_extents xfs_ilock(..., ILOCK_SHARED) xfs_iunlock(..., ILOCK_EXCL) xfs_iread_extents *BOOM* Fix this race by adding a flag to the xfs_ifork structure to indicate that we have not yet read in the extent records and changing the predicate to look at the flag state, not if_height. The memory barrier ensures that the flag will not be set until the very end of the function. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 6 ++++++ fs/xfs/libxfs/xfs_inode_fork.c | 16 +++++++++++++++- fs/xfs/libxfs/xfs_inode_fork.h | 6 ++++-- 3 files changed, 25 insertions(+), 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 34de6e6898c4..f11ef331e5a4 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1171,6 +1171,12 @@ xfs_iread_extents( goto out; } ASSERT(ir.loaded == xfs_iext_count(ifp)); + /* + * Use release semantics so that we can use acquire semantics in + * xfs_need_iread_extents and be guaranteed to see a valid mapping tree + * after that load. + */ + smp_store_release(&ifp->if_needextents, 0); return 0; out: xfs_iext_destroy(ifp); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 6b21760184d9..1bbe5ea3f00b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -226,10 +226,15 @@ xfs_iformat_data_fork( /* * Initialize the extent count early, as the per-format routines may - * depend on it. + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. */ ip->i_df.if_format = dip->di_format; ip->i_df.if_nextents = xfs_dfork_data_extents(dip); + smp_store_release(&ip->i_df.if_needextents, + ip->i_df.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); switch (inode->i_mode & S_IFMT) { case S_IFIFO: @@ -282,8 +287,17 @@ xfs_ifork_init_attr( enum xfs_dinode_fmt format, xfs_extnum_t nextents) { + /* + * Initialize the extent count early, as the per-format routines may + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. + */ ip->i_af.if_format = format; ip->i_af.if_nextents = nextents; + smp_store_release(&ip->i_af.if_needextents, + ip->i_af.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); } void diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index d3943d6ad0b9..96d307784c85 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -24,6 +24,7 @@ struct xfs_ifork { xfs_extnum_t if_nextents; /* # of extents in this fork */ short if_broot_bytes; /* bytes allocated for root */ int8_t if_format; /* format of this fork */ + uint8_t if_needextents; /* extents have not been read */ }; /* @@ -260,9 +261,10 @@ int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip, uint nr_to_add); /* returns true if the fork has extents but they are not read in yet. */ -static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp) +static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp) { - return ifp->if_format == XFS_DINODE_FMT_BTREE && ifp->if_height == 0; + /* see xfs_iformat_{data,attr}_fork() for needextents semantics */ + return smp_load_acquire(&ifp->if_needextents) != 0; } #endif /* __XFS_INODE_FORK_H__ */ -- GitLab From 22ed903eee23a5b174e240f1cdfa9acf393a5210 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Apr 2023 15:49:23 +1000 Subject: [PATCH 2636/5631] xfs: verify buffer contents when we skip log replay syzbot detected a crash during log recovery: XFS (loop0): Mounting V5 Filesystem bfdc47fc-10d8-4eed-a562-11a831b3f791 XFS (loop0): Torn write (CRC failure) detected at log block 0x180. Truncating head block from 0x200. XFS (loop0): Starting recovery (logdev: internal) ================================================================== BUG: KASAN: slab-out-of-bounds in xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 Read of size 8 at addr ffff88807e89f258 by task syz-executor132/5074 CPU: 0 PID: 5074 Comm: syz-executor132 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 xfs_btree_lookup_get_block+0x15c/0x6d0 fs/xfs/libxfs/xfs_btree.c:1813 xfs_btree_lookup+0x346/0x12c0 fs/xfs/libxfs/xfs_btree.c:1913 xfs_btree_simple_query_range+0xde/0x6a0 fs/xfs/libxfs/xfs_btree.c:4713 xfs_btree_query_range+0x2db/0x380 fs/xfs/libxfs/xfs_btree.c:4953 xfs_refcount_recover_cow_leftovers+0x2d1/0xa60 fs/xfs/libxfs/xfs_refcount.c:1946 xfs_reflink_recover_cow+0xab/0x1b0 fs/xfs/xfs_reflink.c:930 xlog_recover_finish+0x824/0x920 fs/xfs/xfs_log_recover.c:3493 xfs_log_mount_finish+0x1ec/0x3d0 fs/xfs/xfs_log.c:829 xfs_mountfs+0x146a/0x1ef0 fs/xfs/xfs_mount.c:933 xfs_fs_fill_super+0xf95/0x11f0 fs/xfs/xfs_super.c:1666 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f89fa3f4aca Code: 83 c4 08 5b 5d c3 66 2e 0f 1f 84 00 00 00 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fffd5fb5ef8 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00646975756f6e2c RCX: 00007f89fa3f4aca RDX: 0000000020000100 RSI: 0000000020009640 RDI: 00007fffd5fb5f10 RBP: 00007fffd5fb5f10 R08: 00007fffd5fb5f50 R09: 000000000000970d R10: 0000000000200800 R11: 0000000000000206 R12: 0000000000000004 R13: 0000555556c6b2c0 R14: 0000000000200800 R15: 00007fffd5fb5f50 The fuzzed image contains an AGF with an obviously garbage agf_refcount_level value of 32, and a dirty log with a buffer log item for that AGF. The ondisk AGF has a higher LSN than the recovered log item. xlog_recover_buf_commit_pass2 reads the buffer, compares the LSNs, and decides to skip replay because the ondisk buffer appears to be newer. Unfortunately, the ondisk buffer is corrupt, but recovery just read the buffer with no buffer ops specified: error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, buf_flags, &bp, NULL); Skipping the buffer leaves its contents in memory unverified. This sets us up for a kernel crash because xfs_refcount_recover_cow_leftovers reads the buffer (which is still around in XBF_DONE state, so no read verification) and creates a refcountbt cursor of height 32. This is impossible so we run off the end of the cursor object and crash. Fix this by invoking the verifier on all skipped buffers and aborting log recovery if the ondisk buffer is corrupt. It might be smarter to force replay the log item atop the buffer and then see if it'll pass the write verifier (like ext4 does) but for now let's go with the conservative option where we stop immediately. Link: https://syzkaller.appspot.com/bug?extid=7e9494b8b399902e994e Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_buf_item_recover.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c index ffa94102094d..43167f543afc 100644 --- a/fs/xfs/xfs_buf_item_recover.c +++ b/fs/xfs/xfs_buf_item_recover.c @@ -943,6 +943,16 @@ xlog_recover_buf_commit_pass2( if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) { trace_xfs_log_recover_buf_skip(log, buf_f); xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN); + + /* + * We're skipping replay of this buffer log item due to the log + * item LSN being behind the ondisk buffer. Verify the buffer + * contents since we aren't going to run the write verifier. + */ + if (bp->b_ops) { + bp->b_ops->verify_read(bp); + error = bp->b_error; + } goto out_release; } -- GitLab From 8ee81ed581ff35882b006a5205100db0b57bf070 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Wed, 12 Apr 2023 15:49:44 +1000 Subject: [PATCH 2637/5631] xfs: fix BUG_ON in xfs_getbmap() There's issue as follows: XFS: Assertion failed: (bmv->bmv_iflags & BMV_IF_DELALLOC) != 0, file: fs/xfs/xfs_bmap_util.c, line: 329 ------------[ cut here ]------------ kernel BUG at fs/xfs/xfs_message.c:102! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 14612 Comm: xfs_io Not tainted 6.3.0-rc2-next-20230315-00006-g2729d23ddb3b-dirty #422 RIP: 0010:assfail+0x96/0xa0 RSP: 0018:ffffc9000fa178c0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff888179a18000 RDX: 0000000000000000 RSI: ffff888179a18000 RDI: 0000000000000002 RBP: 0000000000000000 R08: ffffffff8321aab6 R09: 0000000000000000 R10: 0000000000000001 R11: ffffed1105f85139 R12: ffffffff8aacc4c0 R13: 0000000000000149 R14: ffff888269f58000 R15: 000000000000000c FS: 00007f42f27a4740(0000) GS:ffff88882fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000b92388 CR3: 000000024f006000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: xfs_getbmap+0x1a5b/0x1e40 xfs_ioc_getbmap+0x1fd/0x5b0 xfs_file_ioctl+0x2cb/0x1d50 __x64_sys_ioctl+0x197/0x210 do_syscall_64+0x39/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Above issue may happen as follows: ThreadA ThreadB do_shared_fault __do_fault xfs_filemap_fault __xfs_filemap_fault filemap_fault xfs_ioc_getbmap -> Without BMV_IF_DELALLOC flag xfs_getbmap xfs_ilock(ip, XFS_IOLOCK_SHARED); filemap_write_and_wait do_page_mkwrite xfs_filemap_page_mkwrite __xfs_filemap_fault xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); iomap_page_mkwrite ... xfs_buffered_write_iomap_begin xfs_bmapi_reserve_delalloc -> Allocate delay extent xfs_ilock_data_map_shared(ip) xfs_getbmap_report_one ASSERT((bmv->bmv_iflags & BMV_IF_DELALLOC) != 0) -> trigger BUG_ON As xfs_filemap_page_mkwrite() only hold XFS_MMAPLOCK_SHARED lock, there's small window mkwrite can produce delay extent after file write in xfs_getbmap(). To solve above issue, just skip delalloc extents. Signed-off-by: Ye Bin Reviewed-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_bmap_util.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a09dd2606479..f032d3a4b727 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -314,15 +314,13 @@ xfs_getbmap_report_one( if (isnullstartblock(got->br_startblock) || got->br_startblock == DELAYSTARTBLOCK) { /* - * Delalloc extents that start beyond EOF can occur due to - * speculative EOF allocation when the delalloc extent is larger - * than the largest freespace extent at conversion time. These - * extents cannot be converted by data writeback, so can exist - * here even if we are not supposed to be finding delalloc - * extents. + * Take the flush completion as being a point-in-time snapshot + * where there are no delalloc extents, and if any new ones + * have been created racily, just skip them as being 'after' + * the flush and so don't get reported. */ - if (got->br_startoff < XFS_B_TO_FSB(ip->i_mount, XFS_ISIZE(ip))) - ASSERT((bmv->bmv_iflags & BMV_IF_DELALLOC) != 0); + if (!(bmv->bmv_iflags & BMV_IF_DELALLOC)) + return 0; p->bmv_oflags |= BMV_OF_DELALLOC; p->bmv_block = -2; -- GitLab From 2cf599ed720e353c1a4e7d7932d4252ce30360dd Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:07 +0200 Subject: [PATCH 2638/5631] dt-bindings: pinctrl: qcom,ipq5332-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,ipq5332-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml index 300747252a7b..3d3086ae1ba6 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq5332-tlmm.yaml @@ -56,6 +56,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -92,19 +93,9 @@ $defs: rx1, sdc_data, sdc_clk, sdc_cmd, tsens_max, wci_txd, wci_rxd, wsi_clk, wsi_clk3, wsi_data, wsi_data3, wsis_reset, xfem ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - required: - compatible - reg -- GitLab From b64e16983f8cfc9cdf8662f04f762a3e8498fcb0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:08 +0200 Subject: [PATCH 2639/5631] dt-bindings: pinctrl: qcom,ipq6018: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-2-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,ipq6018-pinctrl.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml index 28f1b6a07b70..7c3e5e043f07 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq6018-pinctrl.yaml @@ -43,6 +43,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -89,18 +90,9 @@ $defs: sd_write, sec_mi2s, smb_int, ssbi_wtr0, ssbi_wtr1, uim1, uim2, uim3, uim_batt, wcss_bt, wcss_fm, wcss_wlan, webcam1_rst ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 42842d91c0c582c252291fb63d1d9bf5940a7226 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:09 +0200 Subject: [PATCH 2640/5631] dt-bindings: pinctrl: qcom,ipq8074: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-3-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,ipq8074-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml index 3137db927fc0..e053fbd588b5 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -92,19 +93,9 @@ $defs: qdss_tracedata_b, qpic, rx0, rx1, rx2, sd_card, sd_write, tsens_max, wci2a, wci2b, wci2c, wci2d ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 867bf1502fbba5e505f055b47783f7236ac70985 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:11 +0200 Subject: [PATCH 2641/5631] dt-bindings: pinctrl: qcom,mdm9607-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-5-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,mdm9607-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml index 96b598bf9a76..2aedb7e7bc8b 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9607-tlmm.yaml @@ -54,6 +54,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -105,19 +106,9 @@ $defs: uim1_clk, uim1_data, uim1_present, uim1_reset, uim2_clk, uim2_data, uim2_present, uim2_reset, uim_batt, wlan_en1, ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From a64ad105c17e56975bd3a4bcc9c9bdec60299834 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:12 +0200 Subject: [PATCH 2642/5631] dt-bindings: pinctrl: qcom,mdm9615: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-6-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,mdm9615-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml index c7c94d742ed2..5885aee95c98 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.yaml @@ -51,6 +51,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -70,19 +71,9 @@ $defs: enum: [ gpio, gsbi2_i2c, gsbi3, gsbi4, gsbi5_i2c, gsbi5_uart, sdc2, ebi2_lcdc, ps_hold, prim_audio, sec_audio, cdc_mclk, ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - output-high: true - output-low: true - input-enable: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 34a433bf7f468b6cf9f4a927444698a34e31bc2d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:13 +0200 Subject: [PATCH 2643/5631] dt-bindings: pinctrl: qcom,msm8226: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-7-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8226-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml index 6cb667fa8665..9efb76509580 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8226-pinctrl.yaml @@ -48,6 +48,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -71,19 +72,9 @@ $defs: blsp_uart3, blsp_uart4, blsp_uart5, cam_mclk0, cam_mclk1, gp0_clk, gp1_clk, sdc3, wlan ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 1c53c43c4f89be48ccdfecefe45d19b600b4bfb2 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:14 +0200 Subject: [PATCH 2644/5631] dt-bindings: pinctrl: qcom,msm8660: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-8-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8660-pinctrl.yaml | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml index 348d84c3cd21..a05971611780 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -81,20 +82,9 @@ $defs: sdc5, tsif1, tsif2, usb_fs1, usb_fs1_oe_n, usb_fs2, usb_fs2_oe_n, vfe, vsens_alarm, ebi2, ebi2cs ] - - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 3a5dad993735e9acd7ffac8577e2b405b8334cbb Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:15 +0200 Subject: [PATCH 2645/5631] dt-bindings: pinctrl: qcom,msm8909-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-9-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8909-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml index 85082adc1811..5095e86fe9a2 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8909-tlmm.yaml @@ -55,6 +55,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -104,19 +105,9 @@ $defs: uim3_clk, uim3_data, uim3_present, uim3_reset, uim_batt, wcss_bt, wcss_fm, wcss_wlan ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 941f8b694051ce99fb079d503b8fbc979eeda2bf Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:16 +0200 Subject: [PATCH 2646/5631] dt-bindings: pinctrl: qcom,msm8916: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-10-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8916-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml index 633c9e5ed49e..063d004967bb 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -103,19 +104,9 @@ $defs: uim1, uim2, uim3, uim_batt, wcss_bt, wcss_fm, wcss_wlan, webcam1_rst ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 7d6154c728d86cdd2a5e753076c8e870b0c51efd Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:17 +0200 Subject: [PATCH 2647/5631] dt-bindings: pinctrl: qcom,msm8953: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-11-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8953-pinctrl.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml index ce219827ccc8..798aac9e6e31 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8953-pinctrl.yaml @@ -45,6 +45,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -106,18 +107,9 @@ $defs: uim_batt, us_emitter, us_euro, wcss_bt, wcss_fm, wcss_wlan, wcss_wlan0, wcss_wlan1, wcss_wlan2, wsa_en, wsa_io, wsa_irq ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From b066f2150028e36c7e52effb42ad76a4734e903e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:18 +0200 Subject: [PATCH 2648/5631] dt-bindings: pinctrl: qcom,msm8960: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-12-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8960-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml index cf386f644ccb..9172b50f7a98 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -97,19 +98,9 @@ $defs: vfe_camif_timer7_a, vfe_camif_timer7_b, vfe_camif_timer7_c, wlan ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 679b065e5ea942cd485b2258c35ecdd54c2ac40e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:19 +0200 Subject: [PATCH 2649/5631] dt-bindings: pinctrl: qcom,msm8974: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-13-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8974-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml index afe4a80f0b79..8a3be65c51ed 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -93,14 +94,6 @@ $defs: tsif1, tsif2, hsic, grfc, audio_ref_clk, qua_mi2s, pri_mi2s, spkr_mi2s, ter_mi2s, sec_mi2s, bt, fm, wlan, slimbus, hsic_ctl ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins @@ -124,8 +117,6 @@ $defs: output-high: false output-low: false - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 327a846dba7100b33fda682cb7caf2f647940d77 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:20 +0200 Subject: [PATCH 2650/5631] dt-bindings: pinctrl: qcom,msm8976: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-14-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8976-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml index 5dfcc3eadbb0..ca95de0b87a6 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8976-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Desired pin configuration for a device or its specific state (like sleep or active). $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -93,19 +94,9 @@ $defs: wsa_irq, blsp_i2c8, pa_indicator, modem_tsync, ssbi_wtr1, gsm1_tx, gsm0_tx, sdcard_det, sec_mi2s, ss_switch ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 6f65e8ca2832dc402f272012f2eabcb969fd2ace Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:21 +0200 Subject: [PATCH 2651/5631] dt-bindings: pinctrl: qcom,msm8994: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-15-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8994-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml index 0c4936fc35ef..41525ecfa8e3 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.yaml @@ -55,6 +55,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -103,19 +104,9 @@ $defs: pri_mi2s, sdc4, sec_mi2s, slimbus, spkr_i2s, ter_mi2s, tsif1, tsif2, uim_batt_alarm, uim1, uim2, uim3, uim4 ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 9de7c1721696af6387dc27661f957c58400ef763 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:22 +0200 Subject: [PATCH 2652/5631] dt-bindings: pinctrl: qcom,msm8996: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-16-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8996-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml index 047b4584e3c0..59d406b60957 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -122,19 +123,9 @@ $defs: modem_tsync, nav_dr, nav_pps, pci_e1, gsm_tx, qspi_cs, ssbi2, ssbi1, mss_lte, qspi_clk, qspi0, qspi1, qspi2, qspi3 ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 06a4b73fe94b4615dcc07b653b2c0c3239685740 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:23 +0200 Subject: [PATCH 2653/5631] dt-bindings: pinctrl: qcom,msm8998: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-17-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,msm8998-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml index c07ee9868046..bd6d7caf499a 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8998-pinctrl.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -107,19 +108,9 @@ $defs: vsense_clkout, vsense_data0, vsense_data1, vsense_mode, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1 ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 3b589a83c79e90a9587a7f491d98a71e402bb45b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:25 +0200 Subject: [PATCH 2654/5631] dt-bindings: pinctrl: qcom,qcs404: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-19-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,qcs404-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml index 20bc967a17b5..b1b9cd319e50 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,qcs404-pinctrl.yaml @@ -59,6 +59,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -119,19 +120,9 @@ $defs: spdifrx_opt, spi_lcd, spkr_dac0, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, wsa_en ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From c512c27ae0e65e74845c76ecdf47712ed7c1e2a7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:26 +0200 Subject: [PATCH 2655/5631] dt-bindings: pinctrl: qcom,qdu1000-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-20-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,qdu1000-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml index 7e5fb9a6e7d3..237cac4f6ce1 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,qdu1000-tlmm.yaml @@ -55,6 +55,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -93,19 +94,9 @@ $defs: usb2phy_ac, usb_con_det, usb_dfp_en, usb_phy, vfr_0, vfr_1, vsense_trigger ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - required: - compatible - reg -- GitLab From ece8e9affc942b4a04c41bc08aae2bd4488e6ba5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:27 +0200 Subject: [PATCH 2656/5631] dt-bindings: pinctrl: qcom,sa8775p-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-21-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sa8775p-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml index 70d9106ad83d..e608a4f1bcae 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sa8775p-tlmm.yaml @@ -58,6 +58,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -103,19 +104,9 @@ $defs: tgu_ch2, tgu_ch3, tgu_ch4, tgu_ch5, tsense_pwm1, tsense_pwm2, tsense_pwm3, tsense_pwm4, usb2phy_ac, vsense_trigger ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From ffa4c15883f0929ace6228e079e29766013d7da0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:28 +0200 Subject: [PATCH 2657/5631] dt-bindings: pinctrl: qcom,sc7180-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. This also fixes warnings like: c7180-trogdor-coachz-r1.dtb: pinctrl@3500000: qspi-sleep-state: 'oneOf' conditional failed, one must be fixed: 'output-disable' does not match any of the regexes: 'pinctrl-[0-9]+' Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-22-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sc7180-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml index f33792a1af6c..573e459b1c44 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7180-pinctrl.yaml @@ -59,6 +59,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -100,19 +101,9 @@ $defs: _V_GPIO, _V_PPS_IN, _V_PPS_OUT, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1 ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 64688acfac28ccd11b07cadca91041e9987a9361 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:29 +0200 Subject: [PATCH 2658/5631] dt-bindings: pinctrl: qcom,sc7280-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. This also fixes warnings like: sc7280-herobrine-evoker.dtb: pinctrl@f100000: qspi-sleep-state: 'oneOf' conditional failed, one must be fixed: 'output-disable' does not match any of the regexes: 'pinctrl-[0-9]+' Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-23-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sc7280-pinctrl.yaml | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml index 36502173cb79..368d44ff5468 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc7280-pinctrl.yaml @@ -62,6 +62,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -110,20 +111,9 @@ $defs: uim1_clk, uim1_data, uim1_present, uim1_reset, usb2phy_ac, usb_phy, vfr_0, vfr_1, vsense_trigger ] - bias-pull-down: true - bias-pull-up: true - bias-bus-hold: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 2eac142c941b7499451afc3dcdfce1ec9c9c4981 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:30 +0200 Subject: [PATCH 2659/5631] dt-bindings: pinctrl: qcom,sc8180x-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-24-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sc8180x-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml index 0ace55c9868e..b086a5184235 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sc8180x-tlmm.yaml @@ -62,6 +62,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -102,19 +103,9 @@ $defs: usb0_phy, usb1_phy, usb2phy_ac, vfr_1, vsense_trigger, wlan1_adc, wlan2_adc, wmss_reset ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 9d2b46e2787f051af2211748fc3a048b2452d170 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:32 +0200 Subject: [PATCH 2660/5631] dt-bindings: pinctrl: qcom,sdm630: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-26-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sdm630-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml index ea6bd0b44f56..508e0633b253 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm630-pinctrl.yaml @@ -65,6 +65,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -122,19 +123,9 @@ $defs: vsense_data0, vsense_data1, vsense_mode, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1 ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - required: - compatible - reg -- GitLab From 9703041392715d560966fdfdf2929f9cb48a8f60 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:33 +0200 Subject: [PATCH 2661/5631] dt-bindings: pinctrl: qcom,sdm670-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-27-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sdm670-tlmm.yaml | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml index f586b3aa138e..84a15f77e710 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm670-tlmm.yaml @@ -58,6 +58,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -94,20 +95,9 @@ $defs: uim1_reset, uim2_clk, uim2_data, uim2_present, uim2_reset, uim_batt, usb_phy, vfr_1, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, wsa_clk, wsa_data, ] - - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 5c9177c2a5efe9608fa414e40cb351e04398fe58 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:34 +0200 Subject: [PATCH 2662/5631] dt-bindings: pinctrl: qcom,sdm845: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. This also fixes warnings like: sdm845-cheza-r1.dtb: pinctrl@3400000: qspi-sleep-state: 'oneOf' conditional failed, one must be fixed: 'output-disable' does not match any of the regexes: 'pinctrl-[0-9]+' Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-28-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sdm845-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml index 23d7c030fec0..d301881ddfa8 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdm845-pinctrl.yaml @@ -61,6 +61,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -102,19 +103,9 @@ $defs: uim_batt, usb_phy, vfr_1, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - required: - compatible - reg -- GitLab From a38e276c27e77a7c5b802559c4d7865dcf1b0760 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:35 +0200 Subject: [PATCH 2663/5631] dt-bindings: pinctrl: qcom,sdx55: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-29-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sdx55-pinctrl.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml index a40175258495..67af99dd8f14 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx55-pinctrl.yaml @@ -48,6 +48,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -91,18 +92,9 @@ $defs: uim1_present, uim1_reset, uim2_clk, uim2_data, uim2_present, uim2_reset, usb2phy_ac, vsense_trigger ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 810e171ed033cfc771201ddf4f5781453847735c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:36 +0200 Subject: [PATCH 2664/5631] dt-bindings: pinctrl: qcom,sdx65-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-30-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml index 89c5562583d1..2ef793ae4038 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sdx65-tlmm.yaml @@ -47,6 +47,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -111,18 +112,9 @@ $defs: qspi_cs, ssbi2, ssbi1, mss_lte, qspi_clk, qspi0, qspi1, qspi2, qspi3, gpio ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 5c470d4e8bdbcb7cf39af5c1b850dc759d0259fa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:37 +0200 Subject: [PATCH 2665/5631] dt-bindings: pinctrl: qcom,sm6115-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-31-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml index 29325483cd2b..871df54f69a2 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6115-tlmm.yaml @@ -53,6 +53,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -85,18 +86,9 @@ $defs: uim2_present, uim2_reset, usb_phy, vfr_1, vsense_trigger, wlan1_adc0, elan1_adc1 ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 312f79584f632384d63972582d353c777d66dfab Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:38 +0200 Subject: [PATCH 2666/5631] dt-bindings: pinctrl: qcom,sm6125-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-32-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml index c9bc4893e8e8..8d77707b02b9 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6125-tlmm.yaml @@ -61,6 +61,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -101,19 +102,9 @@ $defs: wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, wsa_clk, wsa_data ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From ae4331560778a21ead4e910e3c3aa2516533f902 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:39 +0200 Subject: [PATCH 2667/5631] dt-bindings: pinctrl: qcom,sm6350-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-33-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sm6350-tlmm.yaml | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml index d95935fcc8b5..27af379cf791 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6350-tlmm.yaml @@ -63,6 +63,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -108,20 +109,9 @@ $defs: uim2_present, uim2_reset, usb_phy, vfr_1, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, ] - - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 13bb968b819061a0429d82c18133d7e5bdff3b93 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:40 +0200 Subject: [PATCH 2668/5631] dt-bindings: pinctrl: qcom,sm6375-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-34-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sm6375-tlmm.yaml | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml index 66cef48ed59b..6e02ba24825f 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm6375-tlmm.yaml @@ -55,6 +55,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -109,20 +110,9 @@ $defs: usb_phy, vfr_1, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1 ] - - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 5a81d7222ec84d1573685e7aa9e6c9453240f971 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:42 +0200 Subject: [PATCH 2669/5631] dt-bindings: pinctrl: qcom,sm8150: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-36-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sm8150-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml index 4376a9bd4d70..c5ffbea95957 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml @@ -60,6 +60,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -101,19 +102,9 @@ $defs: usb_phy, vfr_1, vsense_trigger, wlan1_adc0, wlan1_adc1, wlan2_adc0, wlan2_adc1, wmss_reset ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From 4134e65a6339d1f8991f59eb3cff98efb2ecb0e5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:43 +0200 Subject: [PATCH 2670/5631] dt-bindings: pinctrl: qcom,sm8250: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-37-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sm8250-pinctrl.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml index cf561dff8893..021c54708524 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8250-pinctrl.yaml @@ -58,6 +58,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -94,19 +95,9 @@ $defs: tsif0_en, tsif0_error, tsif0_sync, tsif1_clk, tsif1_data, tsif1_en, tsif1_error, tsif1_sync, usb2phy_ac, usb_phy, vsense_trigger ] - bias-pull-down: true - bias-pull-up: true - bias-disable: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - allOf: - $ref: /schemas/pinctrl/qcom,tlmm-common.yaml# -- GitLab From a3c355b59bfc1f33be343b581d1a4953fc802605 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:44 +0200 Subject: [PATCH 2671/5631] dt-bindings: pinctrl: qcom,sm8350-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-38-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pinctrl/qcom,sm8350-tlmm.yaml | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml index 797242f68b1c..6e8f41ff0a76 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8350-tlmm.yaml @@ -62,6 +62,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -104,21 +105,9 @@ $defs: uim0_present, uim0_reset, uim1_clk, uim1_data, uim1_present, uim1_reset, usb2phy_ac, usb_phy, vfr_0, vfr_1, vsense_trigger ] - - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-disable: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From ede4773a2fa9d380bc32e027710b874cce0dbc69 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:45 +0200 Subject: [PATCH 2672/5631] dt-bindings: pinctrl: qcom,sm8450-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-39-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml index 56c8046f1be0..5163fe3f5365 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8450-tlmm.yaml @@ -62,6 +62,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -103,19 +104,9 @@ $defs: uim0_reset, uim1_clk, uim1_data, uim1_present, uim1_reset, usb2phy_ac, usb_phy, vfr_0, vfr_1, vsense_trigger ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - examples: - | #include -- GitLab From 152674ab2e98bfd8677117314a77d223a2a1bedf Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 7 Apr 2023 20:45:46 +0200 Subject: [PATCH 2673/5631] dt-bindings: pinctrl: qcom,sm8550-tlmm: simplify with unevaluatedProperties All Qualcomm SoC Top Level Mode Multiplexer pin controllers have similar capabilities regarding pin properties, thus we can just accept entire set provided by qcom,tlmm-common.yaml schema. Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230407184546.161168-40-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml index a457425ba112..f789c7753a92 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8550-tlmm.yaml @@ -54,6 +54,7 @@ $defs: Pinctrl node's client devices use subnodes for desired pin configuration. Client device subnodes use below standard properties. $ref: qcom,tlmm-common.yaml#/$defs/qcom-tlmm-state + unevaluatedProperties: false properties: pins: @@ -109,19 +110,9 @@ $defs: uim1_clk, uim1_data, uim1_present, uim1_reset, usb1_hs, usb_phy, vfr_0, vfr_1, vsense_trigger_mirnat ] - bias-disable: true - bias-pull-down: true - bias-pull-up: true - drive-strength: true - input-enable: true - output-high: true - output-low: true - required: - pins - additionalProperties: false - required: - compatible - reg -- GitLab From bd934f77eeac377e81ddac8673803e7334b82d3d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 22 Feb 2023 15:03:43 +0100 Subject: [PATCH 2674/5631] soundwire: qcom: correct setting ignore bit on v1.5.1 According to the comment and to downstream sources, the SWRM_CONTINUE_EXEC_ON_CMD_IGNORE in SWRM_CMD_FIFO_CFG_ADDR register should be set for v1.5.1 and newer, so fix the >= operator. Fixes: 542d3491cdd7 ("soundwire: qcom: set continue execution flag for ignored commands") Cc: Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230222140343.188691-1-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/soundwire/qcom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 335424870290..ba502129150d 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -704,7 +704,7 @@ static int qcom_swrm_init(struct qcom_swrm_ctrl *ctrl) } /* Configure number of retries of a read/write cmd */ - if (ctrl->version > 0x01050001) { + if (ctrl->version >= 0x01050001) { /* Only for versions >= 1.5.1 */ ctrl->reg_write(ctrl, SWRM_CMD_FIFO_CFG_ADDR, SWRM_RD_WR_CMD_RETRIES | -- GitLab From 208a03ee9db815f28059d3399ee31577aeba0dd7 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 22 Feb 2023 15:44:11 +0100 Subject: [PATCH 2675/5631] soundwire: qcom: define hardcoded version magic numbers Use a define instead of hard-coded register values for Soundwire hardware version number, because it is a bit easier to read and allows to drop explaining comment. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Srinivas Kandagatla Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230222144412.237832-1-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/soundwire/qcom.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index ba502129150d..79bebcecde6d 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -28,6 +28,9 @@ #define SWRM_LINK_MANAGER_EE 0x018 #define SWRM_EE_CPU 1 #define SWRM_FRM_GEN_ENABLED BIT(0) +#define SWRM_VERSION_1_3_0 0x01030000 +#define SWRM_VERSION_1_5_1 0x01050001 +#define SWRM_VERSION_1_7_0 0x01070000 #define SWRM_COMP_HW_VERSION 0x00 #define SWRM_COMP_CFG_ADDR 0x04 #define SWRM_COMP_CFG_IRQ_LEVEL_OR_PULSE_MSK BIT(1) @@ -351,8 +354,7 @@ static int qcom_swrm_cmd_fifo_wr_cmd(struct qcom_swrm_ctrl *swrm, u8 cmd_data, /* Its assumed that write is okay as we do not get any status back */ swrm->reg_write(swrm, SWRM_CMD_FIFO_WR_CMD, val); - /* version 1.3 or less */ - if (swrm->version <= 0x01030000) + if (swrm->version <= SWRM_VERSION_1_3_0) usleep_range(150, 155); if (cmd_id == SWR_BROADCAST_CMD_ID) { @@ -695,7 +697,7 @@ static int qcom_swrm_init(struct qcom_swrm_ctrl *ctrl) u32p_replace_bits(&val, SWRM_DEF_CMD_NO_PINGS, SWRM_MCP_CFG_MAX_NUM_OF_CMD_NO_PINGS_BMSK); ctrl->reg_write(ctrl, SWRM_MCP_CFG_ADDR, val); - if (ctrl->version >= 0x01070000) { + if (ctrl->version >= SWRM_VERSION_1_7_0) { ctrl->reg_write(ctrl, SWRM_LINK_MANAGER_EE, SWRM_EE_CPU); ctrl->reg_write(ctrl, SWRM_MCP_BUS_CTRL, SWRM_MCP_BUS_CLK_START << SWRM_EE_CPU); @@ -704,8 +706,7 @@ static int qcom_swrm_init(struct qcom_swrm_ctrl *ctrl) } /* Configure number of retries of a read/write cmd */ - if (ctrl->version >= 0x01050001) { - /* Only for versions >= 1.5.1 */ + if (ctrl->version >= SWRM_VERSION_1_5_1) { ctrl->reg_write(ctrl, SWRM_CMD_FIFO_CFG_ADDR, SWRM_RD_WR_CMD_RETRIES | SWRM_CONTINUE_EXEC_ON_CMD_IGNORE); @@ -1239,7 +1240,7 @@ static int qcom_swrm_get_port_config(struct qcom_swrm_ctrl *ctrl) ret = of_property_read_u8_array(np, "qcom,ports-block-pack-mode", bp_mode, nports); if (ret) { - if (ctrl->version <= 0x01030000) + if (ctrl->version <= SWRM_VERSION_1_3_0) memset(bp_mode, SWR_INVALID_PARAM, QCOM_SDW_MAX_PORTS); else return ret; @@ -1442,7 +1443,7 @@ static int qcom_swrm_probe(struct platform_device *pdev) pm_runtime_enable(dev); /* Clk stop is not supported on WSA Soundwire masters */ - if (ctrl->version <= 0x01030000) { + if (ctrl->version <= SWRM_VERSION_1_3_0) { ctrl->clock_stop_not_supported = true; } else { ctrl->reg_read(ctrl, SWRM_COMP_MASTER_ID, &val); @@ -1527,7 +1528,7 @@ static int __maybe_unused swrm_runtime_resume(struct device *dev) } else { reset_control_reset(ctrl->audio_cgcr); - if (ctrl->version >= 0x01070000) { + if (ctrl->version >= SWRM_VERSION_1_7_0) { ctrl->reg_write(ctrl, SWRM_LINK_MANAGER_EE, SWRM_EE_CPU); ctrl->reg_write(ctrl, SWRM_MCP_BUS_CTRL, SWRM_MCP_BUS_CLK_START << SWRM_EE_CPU); -- GitLab From 2367e0ecb498764e95cfda691ff0828f7d25f9a4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 22 Feb 2023 15:44:12 +0100 Subject: [PATCH 2676/5631] soundwire: qcom: gracefully handle too many ports in DT There are two issues related to the number of ports coming from Devicetree when exceeding in total QCOM_SDW_MAX_PORTS. Both lead to incorrect memory accesses: 1. With DTS having too big value of input or output ports, the driver, when copying port parameters from local/stack arrays into 'pconfig' array in 'struct qcom_swrm_ctrl', will iterate over their sizes. 2. If DTS also has too many parameters for these ports (e.g. qcom,ports-sinterval-low), the driver will overflow buffers on the stack when reading these properties from DTS. Add a sanity check so incorrect DTS will not cause kernel memory corruption. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Srinivas Kandagatla Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230222144412.237832-2-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/soundwire/qcom.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 79bebcecde6d..c296e0bf897b 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1218,6 +1218,9 @@ static int qcom_swrm_get_port_config(struct qcom_swrm_ctrl *ctrl) ctrl->num_dout_ports = val; nports = ctrl->num_dout_ports + ctrl->num_din_ports; + if (nports > QCOM_SDW_MAX_PORTS) + return -EINVAL; + /* Valid port numbers are from 1-14, so mask out port 0 explicitly */ set_bit(0, &ctrl->dout_port_mask); set_bit(0, &ctrl->din_port_mask); -- GitLab From 9ddae9dad09e8bdaa33909bdcbb062c883c3c332 Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Wed, 15 Mar 2023 14:50:51 +0000 Subject: [PATCH 2677/5631] soundwire: bandwidth allocation: Use hweight32() to calculate set bits Replace the call to sdw_ch_mask_to_ch() with a call to hweight32(). sdw_ch_mask_to_ch() is counting the number of set bits. The hweight() family of functions already do this, and they have an advantage of using a bit-counting instruction if it is available on the target CPU. This also fixes a potential infinite loop bug in the implementation of sdw_ch_mask_to_ch(). Signed-off-by: Richard Fitzgerald Link: https://lore.kernel.org/r/20230315145051.2299822-1-rf@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.h | 11 ----------- drivers/soundwire/generic_bandwidth_allocation.c | 3 ++- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index 96927a143796..f0a59e5df631 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -158,17 +158,6 @@ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg); int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf); -/* Retrieve and return channel count from channel mask */ -static inline int sdw_ch_mask_to_ch(int ch_mask) -{ - int c = 0; - - for (c = 0; ch_mask; ch_mask >>= 1) - c += ch_mask & 1; - - return c; -} - /* Fill transport parameter data structure */ static inline void sdw_fill_xport_params(struct sdw_transport_params *params, int port_num, bool grp_ctrl_valid, diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c index f7c66083a4dd..ea3e8ef408e4 100644 --- a/drivers/soundwire/generic_bandwidth_allocation.c +++ b/drivers/soundwire/generic_bandwidth_allocation.c @@ -6,6 +6,7 @@ * */ +#include #include #include #include @@ -54,7 +55,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, slave_total_ch = 0; list_for_each_entry(p_rt, &s_rt->port_list, port_node) { - ch = sdw_ch_mask_to_ch(p_rt->ch_mask); + ch = hweight32(p_rt->ch_mask); sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, false, -- GitLab From acdae4632e40f05e0f0731c5a383e461324aea65 Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Thu, 16 Mar 2023 09:30:41 +0800 Subject: [PATCH 2678/5631] soundwire: stream: restore cumulative bus bandwidth when compute_params callback failed The _sdw_prepare_stream function just returns the error code when compute_params callback failed. The cumulative bus bandwidth will keep the value and won't be decreased by sdw_deprepare_stream function. We should restore the value of cumulative bus bandwidth when compute_params callback failed. Signed-off-by: Shuming Fan Reviewed-by: Paul Olaru Reviewed-by: Rander Wang Reviewed-by: Pierre-Louis Bossart Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230316013041.1008003-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 8c6da1739e3d..136b6850a3f0 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -1369,7 +1369,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream, if (ret < 0) { dev_err(bus->dev, "Compute params failed: %d\n", ret); - return ret; + goto restore_params; } } -- GitLab From f346fdf977209b1f2a6fd701a853372d398cce91 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:54 +0530 Subject: [PATCH 2679/5631] soundwire: export sdw_compute_slave_ports() function Export sdw_compute_slave_ports() function to use it in another soundwire manager module. Move sdw_transport_data structure to bus header file to export sdw_compute_slave_ports() function. Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230201165944.3169125-1-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-2-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.h | 9 +++++++++ drivers/soundwire/generic_bandwidth_allocation.c | 12 +++--------- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index f0a59e5df631..fda6b24ac2da 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -144,6 +144,13 @@ struct sdw_master_runtime { struct list_head bus_node; }; +struct sdw_transport_data { + int hstart; + int hstop; + int block_offset; + int sub_block_offset; +}; + struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave, enum sdw_data_direction direction, unsigned int port_num); @@ -201,5 +208,7 @@ int sdw_bwrite_no_pm_unlocked(struct sdw_bus *bus, u16 dev_num, u32 addr, u8 val void sdw_clear_slave_status(struct sdw_bus *bus, u32 request); int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size); +void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, + struct sdw_transport_data *t_data); #endif /* __SDW_BUS_H */ diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c index ea3e8ef408e4..325c475b6a66 100644 --- a/drivers/soundwire/generic_bandwidth_allocation.c +++ b/drivers/soundwire/generic_bandwidth_allocation.c @@ -29,15 +29,8 @@ struct sdw_group { unsigned int *rates; }; -struct sdw_transport_data { - int hstart; - int hstop; - int block_offset; - int sub_block_offset; -}; - -static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, - struct sdw_transport_data *t_data) +void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, + struct sdw_transport_data *t_data) { struct sdw_slave_runtime *s_rt = NULL; struct sdw_port_runtime *p_rt; @@ -86,6 +79,7 @@ static void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, } } } +EXPORT_SYMBOL(sdw_compute_slave_ports); static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt, struct sdw_group_params *params, -- GitLab From d8f48fbdfd9af268e92b33462472559d2840228c Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:55 +0530 Subject: [PATCH 2680/5631] soundwire: amd: Add support for AMD Manager driver AMD ACP(v6.x) IP block has two SoundWire manager devices. Add support for - Manager driver probe & remove sequence - Helper functions to enable/disable interrupts, Initialize sdw manager, enable sdw pads - Manager driver sdw_master_ops & port_ops callbacks Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230310162554.699766-3-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-3-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 670 ++++++++++++++++++++++++++++++ drivers/soundwire/amd_manager.h | 235 +++++++++++ include/linux/soundwire/sdw_amd.h | 67 +++ 3 files changed, 972 insertions(+) create mode 100644 drivers/soundwire/amd_manager.c create mode 100644 drivers/soundwire/amd_manager.h create mode 100644 include/linux/soundwire/sdw_amd.h diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c new file mode 100644 index 000000000000..f02522d11417 --- /dev/null +++ b/drivers/soundwire/amd_manager.c @@ -0,0 +1,670 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * SoundWire AMD Manager driver + * + * Copyright 2023 Advanced Micro Devices, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bus.h" +#include "amd_manager.h" + +#define DRV_NAME "amd_sdw_manager" + +#define to_amd_sdw(b) container_of(b, struct amd_sdw_manager, bus) + +static void amd_enable_sdw_pads(struct amd_sdw_manager *amd_manager) +{ + u32 sw_pad_pulldown_val; + u32 val; + + mutex_lock(amd_manager->acp_sdw_lock); + val = readl(amd_manager->acp_mmio + ACP_SW_PAD_KEEPER_EN); + val |= amd_manager->reg_mask->sw_pad_enable_mask; + writel(val, amd_manager->acp_mmio + ACP_SW_PAD_KEEPER_EN); + usleep_range(1000, 1500); + + sw_pad_pulldown_val = readl(amd_manager->acp_mmio + ACP_PAD_PULLDOWN_CTRL); + sw_pad_pulldown_val &= amd_manager->reg_mask->sw_pad_pulldown_mask; + writel(sw_pad_pulldown_val, amd_manager->acp_mmio + ACP_PAD_PULLDOWN_CTRL); + mutex_unlock(amd_manager->acp_sdw_lock); +} + +static int amd_init_sdw_manager(struct amd_sdw_manager *amd_manager) +{ + u32 val; + int ret; + + writel(AMD_SDW_ENABLE, amd_manager->mmio + ACP_SW_EN); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_EN_STATUS, val, val, ACP_DELAY_US, + AMD_SDW_TIMEOUT); + if (ret) + return ret; + + /* SoundWire manager bus reset */ + writel(AMD_SDW_BUS_RESET_REQ, amd_manager->mmio + ACP_SW_BUS_RESET_CTRL); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_BUS_RESET_CTRL, val, + (val & AMD_SDW_BUS_RESET_DONE), ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) + return ret; + + writel(AMD_SDW_BUS_RESET_CLEAR_REQ, amd_manager->mmio + ACP_SW_BUS_RESET_CTRL); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_BUS_RESET_CTRL, val, !val, + ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) { + dev_err(amd_manager->dev, "Failed to reset SoundWire manager instance%d\n", + amd_manager->instance); + return ret; + } + + writel(AMD_SDW_DISABLE, amd_manager->mmio + ACP_SW_EN); + return readl_poll_timeout(amd_manager->mmio + ACP_SW_EN_STATUS, val, !val, ACP_DELAY_US, + AMD_SDW_TIMEOUT); +} + +static int amd_enable_sdw_manager(struct amd_sdw_manager *amd_manager) +{ + u32 val; + + writel(AMD_SDW_ENABLE, amd_manager->mmio + ACP_SW_EN); + return readl_poll_timeout(amd_manager->mmio + ACP_SW_EN_STATUS, val, val, ACP_DELAY_US, + AMD_SDW_TIMEOUT); +} + +static int amd_disable_sdw_manager(struct amd_sdw_manager *amd_manager) +{ + u32 val; + + writel(AMD_SDW_DISABLE, amd_manager->mmio + ACP_SW_EN); + /* + * After invoking manager disable sequence, check whether + * manager has executed clock stop sequence. In this case, + * manager should ignore checking enable status register. + */ + val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + if (val) + return 0; + return readl_poll_timeout(amd_manager->mmio + ACP_SW_EN_STATUS, val, !val, ACP_DELAY_US, + AMD_SDW_TIMEOUT); +} + +static void amd_enable_sdw_interrupts(struct amd_sdw_manager *amd_manager) +{ + struct sdw_manager_reg_mask *reg_mask = amd_manager->reg_mask; + u32 val; + + mutex_lock(amd_manager->acp_sdw_lock); + val = readl(amd_manager->acp_mmio + ACP_EXTERNAL_INTR_CNTL(amd_manager->instance)); + val |= reg_mask->acp_sdw_intr_mask; + writel(val, amd_manager->acp_mmio + ACP_EXTERNAL_INTR_CNTL(amd_manager->instance)); + mutex_unlock(amd_manager->acp_sdw_lock); + + writel(AMD_SDW_IRQ_MASK_0TO7, amd_manager->mmio + + ACP_SW_STATE_CHANGE_STATUS_MASK_0TO7); + writel(AMD_SDW_IRQ_MASK_8TO11, amd_manager->mmio + + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + writel(AMD_SDW_IRQ_ERROR_MASK, amd_manager->mmio + ACP_SW_ERROR_INTR_MASK); +} + +static void amd_disable_sdw_interrupts(struct amd_sdw_manager *amd_manager) +{ + struct sdw_manager_reg_mask *reg_mask = amd_manager->reg_mask; + u32 val; + + mutex_lock(amd_manager->acp_sdw_lock); + val = readl(amd_manager->acp_mmio + ACP_EXTERNAL_INTR_CNTL(amd_manager->instance)); + val &= ~reg_mask->acp_sdw_intr_mask; + writel(val, amd_manager->acp_mmio + ACP_EXTERNAL_INTR_CNTL(amd_manager->instance)); + mutex_unlock(amd_manager->acp_sdw_lock); + + writel(0x00, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_0TO7); + writel(0x00, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + writel(0x00, amd_manager->mmio + ACP_SW_ERROR_INTR_MASK); +} + +static void amd_sdw_set_frameshape(struct amd_sdw_manager *amd_manager) +{ + u32 frame_size; + + frame_size = (amd_manager->rows_index << 3) | amd_manager->cols_index; + writel(frame_size, amd_manager->mmio + ACP_SW_FRAMESIZE); +} + +static void amd_sdw_ctl_word_prep(u32 *lower_word, u32 *upper_word, struct sdw_msg *msg, + int cmd_offset) +{ + u32 upper_data; + u32 lower_data = 0; + u16 addr; + u8 upper_addr, lower_addr; + u8 data = 0; + + addr = msg->addr + cmd_offset; + upper_addr = (addr & 0xFF00) >> 8; + lower_addr = addr & 0xFF; + + if (msg->flags == SDW_MSG_FLAG_WRITE) + data = msg->buf[cmd_offset]; + + upper_data = FIELD_PREP(AMD_SDW_MCP_CMD_DEV_ADDR, msg->dev_num); + upper_data |= FIELD_PREP(AMD_SDW_MCP_CMD_COMMAND, msg->flags + 2); + upper_data |= FIELD_PREP(AMD_SDW_MCP_CMD_REG_ADDR_HIGH, upper_addr); + lower_data |= FIELD_PREP(AMD_SDW_MCP_CMD_REG_ADDR_LOW, lower_addr); + lower_data |= FIELD_PREP(AMD_SDW_MCP_CMD_REG_DATA, data); + + *upper_word = upper_data; + *lower_word = lower_data; +} + +static u64 amd_sdw_send_cmd_get_resp(struct amd_sdw_manager *amd_manager, u32 lower_data, + u32 upper_data) +{ + u64 resp; + u32 lower_resp, upper_resp; + u32 sts; + int ret; + + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_IMM_CMD_STS, sts, + !(sts & AMD_SDW_IMM_CMD_BUSY), ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) { + dev_err(amd_manager->dev, "SDW%x previous cmd status clear failed\n", + amd_manager->instance); + return ret; + } + + if (sts & AMD_SDW_IMM_RES_VALID) { + dev_err(amd_manager->dev, "SDW%x manager is in bad state\n", amd_manager->instance); + writel(0x00, amd_manager->mmio + ACP_SW_IMM_CMD_STS); + } + writel(upper_data, amd_manager->mmio + ACP_SW_IMM_CMD_UPPER_WORD); + writel(lower_data, amd_manager->mmio + ACP_SW_IMM_CMD_LOWER_QWORD); + + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_IMM_CMD_STS, sts, + (sts & AMD_SDW_IMM_RES_VALID), ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) { + dev_err(amd_manager->dev, "SDW%x cmd response timeout occurred\n", + amd_manager->instance); + return ret; + } + upper_resp = readl(amd_manager->mmio + ACP_SW_IMM_RESP_UPPER_WORD); + lower_resp = readl(amd_manager->mmio + ACP_SW_IMM_RESP_LOWER_QWORD); + + writel(AMD_SDW_IMM_RES_VALID, amd_manager->mmio + ACP_SW_IMM_CMD_STS); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_IMM_CMD_STS, sts, + !(sts & AMD_SDW_IMM_RES_VALID), ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) { + dev_err(amd_manager->dev, "SDW%x cmd status retry failed\n", + amd_manager->instance); + return ret; + } + resp = upper_resp; + resp = (resp << 32) | lower_resp; + return resp; +} + +static enum sdw_command_response +amd_program_scp_addr(struct amd_sdw_manager *amd_manager, struct sdw_msg *msg) +{ + struct sdw_msg scp_msg = {0}; + u64 response_buf[2] = {0}; + u32 upper_data = 0, lower_data = 0; + int index; + + scp_msg.dev_num = msg->dev_num; + scp_msg.addr = SDW_SCP_ADDRPAGE1; + scp_msg.buf = &msg->addr_page1; + scp_msg.flags = SDW_MSG_FLAG_WRITE; + amd_sdw_ctl_word_prep(&lower_data, &upper_data, &scp_msg, 0); + response_buf[0] = amd_sdw_send_cmd_get_resp(amd_manager, lower_data, upper_data); + scp_msg.addr = SDW_SCP_ADDRPAGE2; + scp_msg.buf = &msg->addr_page2; + amd_sdw_ctl_word_prep(&lower_data, &upper_data, &scp_msg, 0); + response_buf[1] = amd_sdw_send_cmd_get_resp(amd_manager, lower_data, upper_data); + + for (index = 0; index < 2; index++) { + if (response_buf[index] == -ETIMEDOUT) { + dev_err_ratelimited(amd_manager->dev, + "SCP_addrpage command timeout for Slave %d\n", + msg->dev_num); + return SDW_CMD_TIMEOUT; + } else if (!(response_buf[index] & AMD_SDW_MCP_RESP_ACK)) { + if (response_buf[index] & AMD_SDW_MCP_RESP_NACK) { + dev_err_ratelimited(amd_manager->dev, + "SCP_addrpage NACKed for Slave %d\n", + msg->dev_num); + return SDW_CMD_FAIL; + } + dev_dbg_ratelimited(amd_manager->dev, "SCP_addrpage ignored for Slave %d\n", + msg->dev_num); + return SDW_CMD_IGNORED; + } + } + return SDW_CMD_OK; +} + +static int amd_prep_msg(struct amd_sdw_manager *amd_manager, struct sdw_msg *msg) +{ + int ret; + + if (msg->page) { + ret = amd_program_scp_addr(amd_manager, msg); + if (ret) { + msg->len = 0; + return ret; + } + } + switch (msg->flags) { + case SDW_MSG_FLAG_READ: + case SDW_MSG_FLAG_WRITE: + break; + default: + dev_err(amd_manager->dev, "Invalid msg cmd: %d\n", msg->flags); + return -EINVAL; + } + return 0; +} + +static enum sdw_command_response amd_sdw_fill_msg_resp(struct amd_sdw_manager *amd_manager, + struct sdw_msg *msg, u64 response, + int offset) +{ + if (response & AMD_SDW_MCP_RESP_ACK) { + if (msg->flags == SDW_MSG_FLAG_READ) + msg->buf[offset] = FIELD_GET(AMD_SDW_MCP_RESP_RDATA, response); + } else { + if (response == -ETIMEDOUT) { + dev_err_ratelimited(amd_manager->dev, "command timeout for Slave %d\n", + msg->dev_num); + return SDW_CMD_TIMEOUT; + } else if (response & AMD_SDW_MCP_RESP_NACK) { + dev_err_ratelimited(amd_manager->dev, + "command response NACK received for Slave %d\n", + msg->dev_num); + return SDW_CMD_FAIL; + } + dev_err_ratelimited(amd_manager->dev, "command is ignored for Slave %d\n", + msg->dev_num); + return SDW_CMD_IGNORED; + } + return SDW_CMD_OK; +} + +static unsigned int _amd_sdw_xfer_msg(struct amd_sdw_manager *amd_manager, struct sdw_msg *msg, + int cmd_offset) +{ + u64 response; + u32 upper_data = 0, lower_data = 0; + + amd_sdw_ctl_word_prep(&lower_data, &upper_data, msg, cmd_offset); + response = amd_sdw_send_cmd_get_resp(amd_manager, lower_data, upper_data); + return amd_sdw_fill_msg_resp(amd_manager, msg, response, cmd_offset); +} + +static enum sdw_command_response amd_sdw_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + int ret, i; + + ret = amd_prep_msg(amd_manager, msg); + if (ret) + return SDW_CMD_FAIL_OTHER; + for (i = 0; i < msg->len; i++) { + ret = _amd_sdw_xfer_msg(amd_manager, msg, i); + if (ret) + return ret; + } + return SDW_CMD_OK; +} + +static u32 amd_sdw_read_ping_status(struct sdw_bus *bus) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + u64 response; + u32 slave_stat; + + response = amd_sdw_send_cmd_get_resp(amd_manager, 0, 0); + /* slave status from ping response */ + slave_stat = FIELD_GET(AMD_SDW_MCP_SLAVE_STAT_0_3, response); + slave_stat |= FIELD_GET(AMD_SDW_MCP_SLAVE_STAT_4_11, response) << 8; + dev_dbg(amd_manager->dev, "slave_stat:0x%x\n", slave_stat); + return slave_stat; +} + +static int amd_sdw_compute_params(struct sdw_bus *bus) +{ + struct sdw_transport_data t_data = {0}; + struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; + struct sdw_bus_params *b_params = &bus->params; + int port_bo, hstart, hstop, sample_int; + unsigned int rate, bps; + + port_bo = 0; + hstart = 1; + hstop = bus->params.col - 1; + t_data.hstop = hstop; + t_data.hstart = hstart; + + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + rate = m_rt->stream->params.rate; + bps = m_rt->stream->params.bps; + sample_int = (bus->params.curr_dr_freq / rate); + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + port_bo = (p_rt->num * 64) + 1; + dev_dbg(bus->dev, "p_rt->num=%d hstart=%d hstop=%d port_bo=%d\n", + p_rt->num, hstart, hstop, port_bo); + sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, + false, SDW_BLK_GRP_CNT_1, sample_int, + port_bo, port_bo >> 8, hstart, hstop, + SDW_BLK_PKG_PER_PORT, 0x0); + + sdw_fill_port_params(&p_rt->port_params, + p_rt->num, bps, + SDW_PORT_FLOW_MODE_ISOCH, + b_params->m_data_mode); + t_data.hstart = hstart; + t_data.hstop = hstop; + t_data.block_offset = port_bo; + t_data.sub_block_offset = 0; + } + sdw_compute_slave_ports(m_rt, &t_data); + } + return 0; +} + +static int amd_sdw_port_params(struct sdw_bus *bus, struct sdw_port_params *p_params, + unsigned int bank) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + u32 frame_fmt_reg, dpn_frame_fmt; + + dev_dbg(amd_manager->dev, "p_params->num:0x%x\n", p_params->num); + switch (amd_manager->instance) { + case ACP_SDW0: + frame_fmt_reg = sdw0_manager_dp_reg[p_params->num].frame_fmt_reg; + break; + case ACP_SDW1: + frame_fmt_reg = sdw1_manager_dp_reg[p_params->num].frame_fmt_reg; + break; + default: + return -EINVAL; + } + + dpn_frame_fmt = readl(amd_manager->mmio + frame_fmt_reg); + u32p_replace_bits(&dpn_frame_fmt, p_params->flow_mode, AMD_DPN_FRAME_FMT_PFM); + u32p_replace_bits(&dpn_frame_fmt, p_params->data_mode, AMD_DPN_FRAME_FMT_PDM); + u32p_replace_bits(&dpn_frame_fmt, p_params->bps - 1, AMD_DPN_FRAME_FMT_WORD_LEN); + writel(dpn_frame_fmt, amd_manager->mmio + frame_fmt_reg); + return 0; +} + +static int amd_sdw_transport_params(struct sdw_bus *bus, + struct sdw_transport_params *params, + enum sdw_reg_bank bank) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + u32 dpn_frame_fmt; + u32 dpn_sampleinterval; + u32 dpn_hctrl; + u32 dpn_offsetctrl; + u32 dpn_lanectrl; + u32 frame_fmt_reg, sample_int_reg, hctrl_dp0_reg; + u32 offset_reg, lane_ctrl_ch_en_reg; + + switch (amd_manager->instance) { + case ACP_SDW0: + frame_fmt_reg = sdw0_manager_dp_reg[params->port_num].frame_fmt_reg; + sample_int_reg = sdw0_manager_dp_reg[params->port_num].sample_int_reg; + hctrl_dp0_reg = sdw0_manager_dp_reg[params->port_num].hctrl_dp0_reg; + offset_reg = sdw0_manager_dp_reg[params->port_num].offset_reg; + lane_ctrl_ch_en_reg = sdw0_manager_dp_reg[params->port_num].lane_ctrl_ch_en_reg; + break; + case ACP_SDW1: + frame_fmt_reg = sdw1_manager_dp_reg[params->port_num].frame_fmt_reg; + sample_int_reg = sdw1_manager_dp_reg[params->port_num].sample_int_reg; + hctrl_dp0_reg = sdw1_manager_dp_reg[params->port_num].hctrl_dp0_reg; + offset_reg = sdw1_manager_dp_reg[params->port_num].offset_reg; + lane_ctrl_ch_en_reg = sdw1_manager_dp_reg[params->port_num].lane_ctrl_ch_en_reg; + break; + default: + return -EINVAL; + } + writel(AMD_SDW_SSP_COUNTER_VAL, amd_manager->mmio + ACP_SW_SSP_COUNTER); + + dpn_frame_fmt = readl(amd_manager->mmio + frame_fmt_reg); + u32p_replace_bits(&dpn_frame_fmt, params->blk_pkg_mode, AMD_DPN_FRAME_FMT_BLK_PKG_MODE); + u32p_replace_bits(&dpn_frame_fmt, params->blk_grp_ctrl, AMD_DPN_FRAME_FMT_BLK_GRP_CTRL); + u32p_replace_bits(&dpn_frame_fmt, SDW_STREAM_PCM, AMD_DPN_FRAME_FMT_PCM_OR_PDM); + writel(dpn_frame_fmt, amd_manager->mmio + frame_fmt_reg); + + dpn_sampleinterval = params->sample_interval - 1; + writel(dpn_sampleinterval, amd_manager->mmio + sample_int_reg); + + dpn_hctrl = FIELD_PREP(AMD_DPN_HCTRL_HSTOP, params->hstop); + dpn_hctrl |= FIELD_PREP(AMD_DPN_HCTRL_HSTART, params->hstart); + writel(dpn_hctrl, amd_manager->mmio + hctrl_dp0_reg); + + dpn_offsetctrl = FIELD_PREP(AMD_DPN_OFFSET_CTRL_1, params->offset1); + dpn_offsetctrl |= FIELD_PREP(AMD_DPN_OFFSET_CTRL_2, params->offset2); + writel(dpn_offsetctrl, amd_manager->mmio + offset_reg); + + /* + * lane_ctrl_ch_en_reg will be used to program lane_ctrl and ch_mask + * parameters. + */ + dpn_lanectrl = readl(amd_manager->mmio + lane_ctrl_ch_en_reg); + u32p_replace_bits(&dpn_lanectrl, params->lane_ctrl, AMD_DPN_CH_EN_LCTRL); + writel(dpn_lanectrl, amd_manager->mmio + lane_ctrl_ch_en_reg); + return 0; +} + +static int amd_sdw_port_enable(struct sdw_bus *bus, + struct sdw_enable_ch *enable_ch, + unsigned int bank) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + u32 dpn_ch_enable; + u32 lane_ctrl_ch_en_reg; + + switch (amd_manager->instance) { + case ACP_SDW0: + lane_ctrl_ch_en_reg = sdw0_manager_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg; + break; + case ACP_SDW1: + lane_ctrl_ch_en_reg = sdw1_manager_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg; + break; + default: + return -EINVAL; + } + + /* + * lane_ctrl_ch_en_reg will be used to program lane_ctrl and ch_mask + * parameters. + */ + dpn_ch_enable = readl(amd_manager->mmio + lane_ctrl_ch_en_reg); + u32p_replace_bits(&dpn_ch_enable, enable_ch->ch_mask, AMD_DPN_CH_EN_CHMASK); + if (enable_ch->enable) + writel(dpn_ch_enable, amd_manager->mmio + lane_ctrl_ch_en_reg); + else + writel(0, amd_manager->mmio + lane_ctrl_ch_en_reg); + return 0; +} + +static int sdw_master_read_amd_prop(struct sdw_bus *bus) +{ + struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); + struct fwnode_handle *link; + struct sdw_master_prop *prop; + u32 quirk_mask = 0; + u32 wake_en_mask = 0; + u32 power_mode_mask = 0; + char name[32]; + + prop = &bus->prop; + /* Find manager handle */ + snprintf(name, sizeof(name), "mipi-sdw-link-%d-subproperties", bus->link_id); + link = device_get_named_child_node(bus->dev, name); + if (!link) { + dev_err(bus->dev, "Manager node %s not found\n", name); + return -EIO; + } + fwnode_property_read_u32(link, "amd-sdw-enable", &quirk_mask); + if (!(quirk_mask & AMD_SDW_QUIRK_MASK_BUS_ENABLE)) + prop->hw_disabled = true; + prop->quirks = SDW_MASTER_QUIRKS_CLEAR_INITIAL_CLASH | + SDW_MASTER_QUIRKS_CLEAR_INITIAL_PARITY; + + fwnode_property_read_u32(link, "amd-sdw-wakeup-enable", &wake_en_mask); + amd_manager->wake_en_mask = wake_en_mask; + fwnode_property_read_u32(link, "amd-sdw-power-mode", &power_mode_mask); + amd_manager->power_mode_mask = power_mode_mask; + return 0; +} + +static int amd_prop_read(struct sdw_bus *bus) +{ + sdw_master_read_prop(bus); + sdw_master_read_amd_prop(bus); + return 0; +} + +static const struct sdw_master_port_ops amd_sdw_port_ops = { + .dpn_set_port_params = amd_sdw_port_params, + .dpn_set_port_transport_params = amd_sdw_transport_params, + .dpn_port_enable_ch = amd_sdw_port_enable, +}; + +static const struct sdw_master_ops amd_sdw_ops = { + .read_prop = amd_prop_read, + .xfer_msg = amd_sdw_xfer_msg, + .read_ping_status = amd_sdw_read_ping_status, +}; + +static void amd_sdw_probe_work(struct work_struct *work) +{ + struct amd_sdw_manager *amd_manager = container_of(work, struct amd_sdw_manager, + probe_work); + struct sdw_master_prop *prop; + int ret; + + prop = &amd_manager->bus.prop; + if (!prop->hw_disabled) { + amd_enable_sdw_pads(amd_manager); + ret = amd_init_sdw_manager(amd_manager); + if (ret) + return; + amd_enable_sdw_interrupts(amd_manager); + ret = amd_enable_sdw_manager(amd_manager); + if (ret) + return; + amd_sdw_set_frameshape(amd_manager); + } +} + +static int amd_sdw_manager_probe(struct platform_device *pdev) +{ + const struct acp_sdw_pdata *pdata = pdev->dev.platform_data; + struct resource *res; + struct device *dev = &pdev->dev; + struct sdw_master_prop *prop; + struct sdw_bus_params *params; + struct amd_sdw_manager *amd_manager; + int ret; + + amd_manager = devm_kzalloc(dev, sizeof(struct amd_sdw_manager), GFP_KERNEL); + if (!amd_manager) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -ENOMEM; + + amd_manager->acp_mmio = devm_ioremap(dev, res->start, resource_size(res)); + if (IS_ERR(amd_manager->mmio)) { + dev_err(dev, "mmio not found\n"); + return PTR_ERR(amd_manager->mmio); + } + amd_manager->instance = pdata->instance; + amd_manager->mmio = amd_manager->acp_mmio + + (amd_manager->instance * SDW_MANAGER_REG_OFFSET); + amd_manager->acp_sdw_lock = pdata->acp_sdw_lock; + amd_manager->cols_index = sdw_find_col_index(AMD_SDW_DEFAULT_COLUMNS); + amd_manager->rows_index = sdw_find_row_index(AMD_SDW_DEFAULT_ROWS); + amd_manager->dev = dev; + amd_manager->bus.ops = &amd_sdw_ops; + amd_manager->bus.port_ops = &amd_sdw_port_ops; + amd_manager->bus.compute_params = &amd_sdw_compute_params; + amd_manager->bus.clk_stop_timeout = 200; + amd_manager->bus.link_id = amd_manager->instance; + + switch (amd_manager->instance) { + case ACP_SDW0: + amd_manager->num_dout_ports = AMD_SDW0_MAX_TX_PORTS; + amd_manager->num_din_ports = AMD_SDW0_MAX_RX_PORTS; + break; + case ACP_SDW1: + amd_manager->num_dout_ports = AMD_SDW1_MAX_TX_PORTS; + amd_manager->num_din_ports = AMD_SDW1_MAX_RX_PORTS; + break; + default: + return -EINVAL; + } + + amd_manager->reg_mask = &sdw_manager_reg_mask_array[amd_manager->instance]; + params = &amd_manager->bus.params; + params->max_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2; + params->curr_dr_freq = AMD_SDW_DEFAULT_CLK_FREQ * 2; + params->col = AMD_SDW_DEFAULT_COLUMNS; + params->row = AMD_SDW_DEFAULT_ROWS; + prop = &amd_manager->bus.prop; + prop->clk_freq = &amd_sdw_freq_tbl[0]; + prop->mclk_freq = AMD_SDW_BUS_BASE_FREQ; + + ret = sdw_bus_master_add(&amd_manager->bus, dev, dev->fwnode); + if (ret) { + dev_err(dev, "Failed to register SoundWire manager(%d)\n", ret); + return ret; + } + dev_set_drvdata(dev, amd_manager); + INIT_WORK(&amd_manager->probe_work, amd_sdw_probe_work); + /* + * Instead of having lengthy probe sequence, use deferred probe. + */ + schedule_work(&amd_manager->probe_work); + return 0; +} + +static int amd_sdw_manager_remove(struct platform_device *pdev) +{ + struct amd_sdw_manager *amd_manager = dev_get_drvdata(&pdev->dev); + + cancel_work_sync(&amd_manager->probe_work); + amd_disable_sdw_interrupts(amd_manager); + sdw_bus_master_delete(&amd_manager->bus); + return amd_disable_sdw_manager(amd_manager); +} + +static struct platform_driver amd_sdw_driver = { + .probe = &amd_sdw_manager_probe, + .remove = &amd_sdw_manager_remove, + .driver = { + .name = "amd_sdw_manager", + } +}; +module_platform_driver(amd_sdw_driver); + +MODULE_AUTHOR("Vijendar.Mukunda@amd.com"); +MODULE_DESCRIPTION("AMD SoundWire driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h new file mode 100644 index 000000000000..f7106521b500 --- /dev/null +++ b/drivers/soundwire/amd_manager.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + */ + +#ifndef __AMD_MANAGER_H +#define __AMD_MANAGER_H + +#include + +#define SDW_MANAGER_REG_OFFSET 0xc00 +#define AMD_SDW_DEFAULT_ROWS 50 +#define AMD_SDW_DEFAULT_COLUMNS 10 +#define ACP_PAD_PULLDOWN_CTRL 0x0001448 +#define ACP_SW_PAD_KEEPER_EN 0x0001454 +#define ACP_SW0_WAKE_EN 0x0001458 +#define ACP_EXTERNAL_INTR_CNTL0 0x0001a04 +#define ACP_EXTERNAL_INTR_STAT0 0x0001a0c +#define ACP_EXTERNAL_INTR_CNTL(i) (ACP_EXTERNAL_INTR_CNTL0 + ((i) * 4)) +#define ACP_EXTERNAL_INTR_STAT(i) (ACP_EXTERNAL_INTR_STAT0 + ((i) * 4)) +#define ACP_SW_WAKE_EN(i) (ACP_SW0_WAKE_EN + ((i) * 8)) + +#define ACP_SW_EN 0x0003000 +#define ACP_SW_EN_STATUS 0x0003004 +#define ACP_SW_FRAMESIZE 0x0003008 +#define ACP_SW_SSP_COUNTER 0x000300c +#define ACP_SW_AUDIO0_TX_EN 0x0003010 +#define ACP_SW_AUDIO0_TX_EN_STATUS 0x0003014 +#define ACP_SW_AUDIO0_TX_FRAME_FORMAT 0x0003018 +#define ACP_SW_AUDIO0_TX_SAMPLEINTERVAL 0x000301c +#define ACP_SW_AUDIO0_TX_HCTRL_DP0 0x0003020 +#define ACP_SW_AUDIO0_TX_HCTRL_DP1 0x0003024 +#define ACP_SW_AUDIO0_TX_HCTRL_DP2 0x0003028 +#define ACP_SW_AUDIO0_TX_HCTRL_DP3 0x000302c +#define ACP_SW_AUDIO0_TX_OFFSET_DP0 0x0003030 +#define ACP_SW_AUDIO0_TX_OFFSET_DP1 0x0003034 +#define ACP_SW_AUDIO0_TX_OFFSET_DP2 0x0003038 +#define ACP_SW_AUDIO0_TX_OFFSET_DP3 0x000303c +#define ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP0 0x0003040 +#define ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP1 0x0003044 +#define ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP2 0x0003048 +#define ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP3 0x000304c +#define ACP_SW_AUDIO1_TX_EN 0x0003050 +#define ACP_SW_AUDIO1_TX_EN_STATUS 0x0003054 +#define ACP_SW_AUDIO1_TX_FRAME_FORMAT 0x0003058 +#define ACP_SW_AUDIO1_TX_SAMPLEINTERVAL 0x000305c +#define ACP_SW_AUDIO1_TX_HCTRL 0x0003060 +#define ACP_SW_AUDIO1_TX_OFFSET 0x0003064 +#define ACP_SW_AUDIO1_TX_CHANNEL_ENABLE_DP0 0x0003068 +#define ACP_SW_AUDIO2_TX_EN 0x000306c +#define ACP_SW_AUDIO2_TX_EN_STATUS 0x0003070 +#define ACP_SW_AUDIO2_TX_FRAME_FORMAT 0x0003074 +#define ACP_SW_AUDIO2_TX_SAMPLEINTERVAL 0x0003078 +#define ACP_SW_AUDIO2_TX_HCTRL 0x000307c +#define ACP_SW_AUDIO2_TX_OFFSET 0x0003080 +#define ACP_SW_AUDIO2_TX_CHANNEL_ENABLE_DP0 0x0003084 +#define ACP_SW_AUDIO0_RX_EN 0x0003088 +#define ACP_SW_AUDIO0_RX_EN_STATUS 0x000308c +#define ACP_SW_AUDIO0_RX_FRAME_FORMAT 0x0003090 +#define ACP_SW_AUDIO0_RX_SAMPLEINTERVAL 0x0003094 +#define ACP_SW_AUDIO0_RX_HCTRL_DP0 0x0003098 +#define ACP_SW_AUDIO0_RX_HCTRL_DP1 0x000309c +#define ACP_SW_AUDIO0_RX_HCTRL_DP2 0x0003100 +#define ACP_SW_AUDIO0_RX_HCTRL_DP3 0x0003104 +#define ACP_SW_AUDIO0_RX_OFFSET_DP0 0x0003108 +#define ACP_SW_AUDIO0_RX_OFFSET_DP1 0x000310c +#define ACP_SW_AUDIO0_RX_OFFSET_DP2 0x0003110 +#define ACP_SW_AUDIO0_RX_OFFSET_DP3 0x0003114 +#define ACP_SW_AUDIO0_RX_CHANNEL_ENABLE_DP0 0x0003118 +#define ACP_SW_AUDIO0_RX_CHANNEL_ENABLE_DP1 0x000311c +#define ACP_SW_AUDIO0_RX_CHANNEL_ENABLE_DP2 0x0003120 +#define ACP_SW_AUDIO0_RX_CHANNEL_ENABLE_DP3 0x0003124 +#define ACP_SW_AUDIO1_RX_EN 0x0003128 +#define ACP_SW_AUDIO1_RX_EN_STATUS 0x000312c +#define ACP_SW_AUDIO1_RX_FRAME_FORMAT 0x0003130 +#define ACP_SW_AUDIO1_RX_SAMPLEINTERVAL 0x0003134 +#define ACP_SW_AUDIO1_RX_HCTRL 0x0003138 +#define ACP_SW_AUDIO1_RX_OFFSET 0x000313c +#define ACP_SW_AUDIO1_RX_CHANNEL_ENABLE_DP0 0x0003140 +#define ACP_SW_AUDIO2_RX_EN 0x0003144 +#define ACP_SW_AUDIO2_RX_EN_STATUS 0x0003148 +#define ACP_SW_AUDIO2_RX_FRAME_FORMAT 0x000314c +#define ACP_SW_AUDIO2_RX_SAMPLEINTERVAL 0x0003150 +#define ACP_SW_AUDIO2_RX_HCTRL 0x0003154 +#define ACP_SW_AUDIO2_RX_OFFSET 0x0003158 +#define ACP_SW_AUDIO2_RX_CHANNEL_ENABLE_DP0 0x000315c +#define ACP_SW_BPT_PORT_EN 0x0003160 +#define ACP_SW_BPT_PORT_EN_STATUS 0x0003164 +#define ACP_SW_BPT_PORT_FRAME_FORMAT 0x0003168 +#define ACP_SW_BPT_PORT_SAMPLEINTERVAL 0x000316c +#define ACP_SW_BPT_PORT_HCTRL 0x0003170 +#define ACP_SW_BPT_PORT_OFFSET 0x0003174 +#define ACP_SW_BPT_PORT_CHANNEL_ENABLE 0x0003178 +#define ACP_SW_BPT_PORT_FIRST_BYTE_ADDR 0x000317c +#define ACP_SW_CLK_RESUME_CTRL 0x0003180 +#define ACP_SW_CLK_RESUME_DELAY_CNTR 0x0003184 +#define ACP_SW_BUS_RESET_CTRL 0x0003188 +#define ACP_SW_PRBS_ERR_STATUS 0x000318c +#define ACP_SW_IMM_CMD_UPPER_WORD 0x0003230 +#define ACP_SW_IMM_CMD_LOWER_QWORD 0x0003234 +#define ACP_SW_IMM_RESP_UPPER_WORD 0x0003238 +#define ACP_SW_IMM_RESP_LOWER_QWORD 0x000323c +#define ACP_SW_IMM_CMD_STS 0x0003240 +#define ACP_SW_BRA_BASE_ADDRESS 0x0003244 +#define ACP_SW_BRA_TRANSFER_SIZE 0x0003248 +#define ACP_SW_BRA_DMA_BUSY 0x000324c +#define ACP_SW_BRA_RESP 0x0003250 +#define ACP_SW_BRA_RESP_FRAME_ADDR 0x0003254 +#define ACP_SW_BRA_CURRENT_TRANSFER_SIZE 0x0003258 +#define ACP_SW_STATE_CHANGE_STATUS_0TO7 0x000325c +#define ACP_SW_STATE_CHANGE_STATUS_8TO11 0x0003260 +#define ACP_SW_STATE_CHANGE_STATUS_MASK_0TO7 0x0003264 +#define ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11 0x0003268 +#define ACP_SW_CLK_FREQUENCY_CTRL 0x000326c +#define ACP_SW_ERROR_INTR_MASK 0x0003270 +#define ACP_SW_PHY_TEST_MODE_DATA_OFF 0x0003274 + +#define ACP_DELAY_US 10 +#define AMD_SDW_TIMEOUT 1000 +#define AMD_SDW_DEFAULT_CLK_FREQ 12000000 + +#define AMD_SDW_MCP_RESP_ACK BIT(0) +#define AMD_SDW_MCP_RESP_NACK BIT(1) +#define AMD_SDW_MCP_RESP_RDATA GENMASK(14, 7) + +#define AMD_SDW_MCP_CMD_SSP_TAG BIT(31) +#define AMD_SDW_MCP_CMD_COMMAND GENMASK(14, 12) +#define AMD_SDW_MCP_CMD_DEV_ADDR GENMASK(11, 8) +#define AMD_SDW_MCP_CMD_REG_ADDR_HIGH GENMASK(7, 0) +#define AMD_SDW_MCP_CMD_REG_ADDR_LOW GENMASK(31, 24) +#define AMD_SDW_MCP_CMD_REG_DATA GENMASK(14, 7) +#define AMD_SDW_MCP_SLAVE_STAT_0_3 GENMASK(14, 7) +#define AMD_SDW_MCP_SLAVE_STAT_4_11 GENMASK_ULL(39, 24) +#define AMD_SDW_MCP_SLAVE_STATUS_MASK GENMASK(1, 0) +#define AMD_SDW_MCP_SLAVE_STATUS_BITS GENMASK(3, 2) +#define AMD_SDW_MCP_SLAVE_STATUS_8TO_11 GENMASK_ULL(15, 0) +#define AMD_SDW_MCP_SLAVE_STATUS_VALID_MASK(x) BIT(((x) * 4)) +#define AMD_SDW_MCP_SLAVE_STAT_SHIFT_MASK(x) (((x) * 4) + 1) + +#define AMD_SDW_MASTER_SUSPEND_DELAY_MS 2000 +#define AMD_SDW_QUIRK_MASK_BUS_ENABLE BIT(0) + +#define AMD_SDW_IMM_RES_VALID 1 +#define AMD_SDW_IMM_CMD_BUSY 2 +#define AMD_SDW_ENABLE 1 +#define AMD_SDW_DISABLE 0 +#define AMD_SDW_BUS_RESET_CLEAR_REQ 0 +#define AMD_SDW_BUS_RESET_REQ 1 +#define AMD_SDW_BUS_RESET_DONE 2 +#define AMD_SDW_BUS_BASE_FREQ 24000000 + +#define AMD_SDW0_EXT_INTR_MASK 0x200000 +#define AMD_SDW1_EXT_INTR_MASK 4 +#define AMD_SDW_IRQ_MASK_0TO7 0x77777777 +#define AMD_SDW_IRQ_MASK_8TO11 0x000d7777 +#define AMD_SDW_IRQ_ERROR_MASK 0xff +#define AMD_SDW_MAX_FREQ_NUM 1 +#define AMD_SDW0_MAX_TX_PORTS 3 +#define AMD_SDW0_MAX_RX_PORTS 3 +#define AMD_SDW1_MAX_TX_PORTS 1 +#define AMD_SDW1_MAX_RX_PORTS 1 +#define AMD_SDW0_MAX_DAI 6 +#define AMD_SDW1_MAX_DAI 2 +#define AMD_SDW_SLAVE_0_ATTACHED 5 +#define AMD_SDW_SSP_COUNTER_VAL 3 + +#define AMD_DPN_FRAME_FMT_PFM GENMASK(1, 0) +#define AMD_DPN_FRAME_FMT_PDM GENMASK(3, 2) +#define AMD_DPN_FRAME_FMT_BLK_PKG_MODE BIT(4) +#define AMD_DPN_FRAME_FMT_BLK_GRP_CTRL GENMASK(6, 5) +#define AMD_DPN_FRAME_FMT_WORD_LEN GENMASK(12, 7) +#define AMD_DPN_FRAME_FMT_PCM_OR_PDM BIT(13) +#define AMD_DPN_HCTRL_HSTOP GENMASK(3, 0) +#define AMD_DPN_HCTRL_HSTART GENMASK(7, 4) +#define AMD_DPN_OFFSET_CTRL_1 GENMASK(7, 0) +#define AMD_DPN_OFFSET_CTRL_2 GENMASK(15, 8) +#define AMD_DPN_CH_EN_LCTRL GENMASK(2, 0) +#define AMD_DPN_CH_EN_CHMASK GENMASK(10, 3) +#define AMD_SDW_STAT_MAX_RETRY_COUNT 100 +#define AMD_SDW0_PAD_PULLDOWN_CTRL_ENABLE_MASK 0x7f9f +#define AMD_SDW1_PAD_PULLDOWN_CTRL_ENABLE_MASK 0x7ffa +#define AMD_SDW0_PAD_PULLDOWN_CTRL_DISABLE_MASK 0x60 +#define AMD_SDW1_PAD_PULLDOWN_CTRL_DISABLE_MASK 5 +#define AMD_SDW0_PAD_KEEPER_EN_MASK 1 +#define AMD_SDW1_PAD_KEEPER_EN_MASK 0x10 +#define AMD_SDW0_PAD_KEEPER_DISABLE_MASK 0x1e +#define AMD_SDW1_PAD_KEEPER_DISABLE_MASK 0xf + +static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { + AMD_SDW_DEFAULT_CLK_FREQ, +}; + +struct sdw_manager_dp_reg { + u32 frame_fmt_reg; + u32 sample_int_reg; + u32 hctrl_dp0_reg; + u32 offset_reg; + u32 lane_ctrl_ch_en_reg; +}; + +static struct sdw_manager_dp_reg sdw0_manager_dp_reg[AMD_SDW0_MAX_DAI] = { + {ACP_SW_AUDIO0_TX_FRAME_FORMAT, ACP_SW_AUDIO0_TX_SAMPLEINTERVAL, ACP_SW_AUDIO0_TX_HCTRL_DP0, + ACP_SW_AUDIO0_TX_OFFSET_DP0, ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO1_TX_FRAME_FORMAT, ACP_SW_AUDIO1_TX_SAMPLEINTERVAL, ACP_SW_AUDIO1_TX_HCTRL, + ACP_SW_AUDIO1_TX_OFFSET, ACP_SW_AUDIO1_TX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO2_TX_FRAME_FORMAT, ACP_SW_AUDIO2_TX_SAMPLEINTERVAL, ACP_SW_AUDIO2_TX_HCTRL, + ACP_SW_AUDIO2_TX_OFFSET, ACP_SW_AUDIO2_TX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO0_RX_FRAME_FORMAT, ACP_SW_AUDIO0_RX_SAMPLEINTERVAL, ACP_SW_AUDIO0_RX_HCTRL_DP0, + ACP_SW_AUDIO0_RX_OFFSET_DP0, ACP_SW_AUDIO0_RX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO1_RX_FRAME_FORMAT, ACP_SW_AUDIO1_RX_SAMPLEINTERVAL, ACP_SW_AUDIO1_RX_HCTRL, + ACP_SW_AUDIO1_RX_OFFSET, ACP_SW_AUDIO1_RX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO2_RX_FRAME_FORMAT, ACP_SW_AUDIO2_RX_SAMPLEINTERVAL, ACP_SW_AUDIO2_RX_HCTRL, + ACP_SW_AUDIO2_RX_OFFSET, ACP_SW_AUDIO2_RX_CHANNEL_ENABLE_DP0}, +}; + +static struct sdw_manager_dp_reg sdw1_manager_dp_reg[AMD_SDW1_MAX_DAI] = { + {ACP_SW_AUDIO1_TX_FRAME_FORMAT, ACP_SW_AUDIO1_TX_SAMPLEINTERVAL, ACP_SW_AUDIO1_TX_HCTRL, + ACP_SW_AUDIO1_TX_OFFSET, ACP_SW_AUDIO1_TX_CHANNEL_ENABLE_DP0}, + {ACP_SW_AUDIO1_RX_FRAME_FORMAT, ACP_SW_AUDIO1_RX_SAMPLEINTERVAL, ACP_SW_AUDIO1_RX_HCTRL, + ACP_SW_AUDIO1_RX_OFFSET, ACP_SW_AUDIO1_RX_CHANNEL_ENABLE_DP0} +}; + +static struct sdw_manager_reg_mask sdw_manager_reg_mask_array[2] = { + { + AMD_SDW0_PAD_KEEPER_EN_MASK, + AMD_SDW0_PAD_PULLDOWN_CTRL_ENABLE_MASK, + AMD_SDW0_EXT_INTR_MASK + }, + { + AMD_SDW1_PAD_KEEPER_EN_MASK, + AMD_SDW1_PAD_PULLDOWN_CTRL_ENABLE_MASK, + AMD_SDW1_EXT_INTR_MASK + } +}; +#endif diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h new file mode 100644 index 000000000000..c14a291a40e8 --- /dev/null +++ b/include/linux/soundwire/sdw_amd.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2023 Advanced Micro Devices, Inc. All rights reserved. + */ + +#ifndef __SDW_AMD_H +#define __SDW_AMD_H + +#include + +#define ACP_SDW0 0 +#define ACP_SDW1 1 + +struct acp_sdw_pdata { + u16 instance; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; +}; + +struct sdw_manager_reg_mask { + u32 sw_pad_enable_mask; + u32 sw_pad_pulldown_mask; + u32 acp_sdw_intr_mask; +}; + +/** + * struct amd_sdw_manager - amd manager driver context + * @bus: bus handle + * @dev: linux device + * @mmio: SoundWire registers mmio base + * @acp_mmio: acp registers mmio base + * @reg_mask: register mask structure per manager instance + * @probe_work: SoundWire manager probe workqueue + * @acp_sdw_lock: mutex to protect acp share register access + * @num_din_ports: number of input ports + * @num_dout_ports: number of output ports + * @cols_index: Column index in frame shape + * @rows_index: Rows index in frame shape + * @instance: SoundWire manager instance + * @quirks: SoundWire manager quirks + * @wake_en_mask: wake enable mask per SoundWire manager + * @power_mode_mask: flag interprets amd SoundWire manager power mode + */ +struct amd_sdw_manager { + struct sdw_bus bus; + struct device *dev; + + void __iomem *mmio; + void __iomem *acp_mmio; + + struct sdw_manager_reg_mask *reg_mask; + struct work_struct probe_work; + /* mutex to protect acp common register access */ + struct mutex *acp_sdw_lock; + + int num_din_ports; + int num_dout_ports; + + int cols_index; + int rows_index; + + u32 instance; + u32 quirks; + u32 wake_en_mask; + u32 power_mode_mask; +}; +#endif -- GitLab From 2b13596f7c9c03b1653b21a440ce672c3d7e5233 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:56 +0530 Subject: [PATCH 2681/5631] soundwire: amd: register SoundWire manager dai ops Register dai ops for SoundWire manager instances. Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-4-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-4-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 178 ++++++++++++++++++++++++++++++ drivers/soundwire/amd_manager.h | 18 +++ include/linux/soundwire/sdw_amd.h | 18 +++ 3 files changed, 214 insertions(+) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index f02522d11417..f12dad6c3226 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -551,6 +551,178 @@ static const struct sdw_master_ops amd_sdw_ops = { .read_ping_status = amd_sdw_read_ping_status, }; +static int amd_sdw_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) +{ + struct amd_sdw_manager *amd_manager = snd_soc_dai_get_drvdata(dai); + struct sdw_amd_dai_runtime *dai_runtime; + struct sdw_stream_config sconfig; + struct sdw_port_config *pconfig; + int ch, dir; + int ret; + + dai_runtime = amd_manager->dai_runtime_array[dai->id]; + if (!dai_runtime) + return -EIO; + + ch = params_channels(params); + if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) + dir = SDW_DATA_DIR_RX; + else + dir = SDW_DATA_DIR_TX; + dev_dbg(amd_manager->dev, "dir:%d dai->id:0x%x\n", dir, dai->id); + + sconfig.direction = dir; + sconfig.ch_count = ch; + sconfig.frame_rate = params_rate(params); + sconfig.type = dai_runtime->stream_type; + + sconfig.bps = snd_pcm_format_width(params_format(params)); + + /* Port configuration */ + pconfig = kzalloc(sizeof(*pconfig), GFP_KERNEL); + if (!pconfig) { + ret = -ENOMEM; + goto error; + } + + pconfig->num = dai->id; + pconfig->ch_mask = (1 << ch) - 1; + ret = sdw_stream_add_master(&amd_manager->bus, &sconfig, + pconfig, 1, dai_runtime->stream); + if (ret) + dev_err(amd_manager->dev, "add manager to stream failed:%d\n", ret); + + kfree(pconfig); +error: + return ret; +} + +static int amd_sdw_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) +{ + struct amd_sdw_manager *amd_manager = snd_soc_dai_get_drvdata(dai); + struct sdw_amd_dai_runtime *dai_runtime; + int ret; + + dai_runtime = amd_manager->dai_runtime_array[dai->id]; + if (!dai_runtime) + return -EIO; + + ret = sdw_stream_remove_master(&amd_manager->bus, dai_runtime->stream); + if (ret < 0) + dev_err(dai->dev, "remove manager from stream %s failed: %d\n", + dai_runtime->stream->name, ret); + return ret; +} + +static int amd_set_sdw_stream(struct snd_soc_dai *dai, void *stream, int direction) +{ + struct amd_sdw_manager *amd_manager = snd_soc_dai_get_drvdata(dai); + struct sdw_amd_dai_runtime *dai_runtime; + + dai_runtime = amd_manager->dai_runtime_array[dai->id]; + if (stream) { + /* first paranoia check */ + if (dai_runtime) { + dev_err(dai->dev, "dai_runtime already allocated for dai %s\n", dai->name); + return -EINVAL; + } + + /* allocate and set dai_runtime info */ + dai_runtime = kzalloc(sizeof(*dai_runtime), GFP_KERNEL); + if (!dai_runtime) + return -ENOMEM; + + dai_runtime->stream_type = SDW_STREAM_PCM; + dai_runtime->bus = &amd_manager->bus; + dai_runtime->stream = stream; + amd_manager->dai_runtime_array[dai->id] = dai_runtime; + } else { + /* second paranoia check */ + if (!dai_runtime) { + dev_err(dai->dev, "dai_runtime not allocated for dai %s\n", dai->name); + return -EINVAL; + } + + /* for NULL stream we release allocated dai_runtime */ + kfree(dai_runtime); + amd_manager->dai_runtime_array[dai->id] = NULL; + } + return 0; +} + +static int amd_pcm_set_sdw_stream(struct snd_soc_dai *dai, void *stream, int direction) +{ + return amd_set_sdw_stream(dai, stream, direction); +} + +static void *amd_get_sdw_stream(struct snd_soc_dai *dai, int direction) +{ + struct amd_sdw_manager *amd_manager = snd_soc_dai_get_drvdata(dai); + struct sdw_amd_dai_runtime *dai_runtime; + + dai_runtime = amd_manager->dai_runtime_array[dai->id]; + if (!dai_runtime) + return ERR_PTR(-EINVAL); + + return dai_runtime->stream; +} + +static const struct snd_soc_dai_ops amd_sdw_dai_ops = { + .hw_params = amd_sdw_hw_params, + .hw_free = amd_sdw_hw_free, + .set_stream = amd_pcm_set_sdw_stream, + .get_stream = amd_get_sdw_stream, +}; + +static const struct snd_soc_component_driver amd_sdw_dai_component = { + .name = "soundwire", +}; + +static int amd_sdw_register_dais(struct amd_sdw_manager *amd_manager) +{ + struct sdw_amd_dai_runtime **dai_runtime_array; + struct snd_soc_dai_driver *dais; + struct snd_soc_pcm_stream *stream; + struct device *dev; + int i, num_dais; + + dev = amd_manager->dev; + num_dais = amd_manager->num_dout_ports + amd_manager->num_din_ports; + dais = devm_kcalloc(dev, num_dais, sizeof(*dais), GFP_KERNEL); + if (!dais) + return -ENOMEM; + + dai_runtime_array = devm_kcalloc(dev, num_dais, + sizeof(struct sdw_amd_dai_runtime *), + GFP_KERNEL); + if (!dai_runtime_array) + return -ENOMEM; + amd_manager->dai_runtime_array = dai_runtime_array; + for (i = 0; i < num_dais; i++) { + dais[i].name = devm_kasprintf(dev, GFP_KERNEL, "SDW%d Pin%d", amd_manager->instance, + i); + if (!dais[i].name) + return -ENOMEM; + if (i < amd_manager->num_dout_ports) + stream = &dais[i].playback; + else + stream = &dais[i].capture; + + stream->channels_min = 2; + stream->channels_max = 2; + stream->rates = SNDRV_PCM_RATE_48000; + stream->formats = SNDRV_PCM_FMTBIT_S16_LE; + + dais[i].ops = &amd_sdw_dai_ops; + dais[i].id = i; + } + + return devm_snd_soc_register_component(dev, &amd_sdw_dai_component, + dais, num_dais); +} + static void amd_sdw_probe_work(struct work_struct *work) { struct amd_sdw_manager *amd_manager = container_of(work, struct amd_sdw_manager, @@ -636,6 +808,12 @@ static int amd_sdw_manager_probe(struct platform_device *pdev) dev_err(dev, "Failed to register SoundWire manager(%d)\n", ret); return ret; } + ret = amd_sdw_register_dais(amd_manager); + if (ret) { + dev_err(dev, "CPU DAI registration failed\n"); + sdw_bus_master_delete(&amd_manager->bus); + return ret; + } dev_set_drvdata(dev, amd_manager); INIT_WORK(&amd_manager->probe_work, amd_sdw_probe_work); /* diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index f7106521b500..c92e0dee2cb1 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -198,6 +198,24 @@ struct sdw_manager_dp_reg { u32 lane_ctrl_ch_en_reg; }; +/* + * SDW0 Manager instance registers 6 CPU DAI (3 TX & 3 RX Ports) + * whereas SDW1 Manager Instance registers 2 CPU DAI (one TX & one RX port) + * Below is the CPU DAI <->Manager port number mapping + * i.e SDW0 Pin0 -> port number 0 -> AUDIO0 TX + * SDW0 Pin1 -> Port number 1 -> AUDIO1 TX + * SDW0 Pin2 -> Port number 2 -> AUDIO2 TX + * SDW0 Pin3 -> port number 3 -> AUDIO0 RX + * SDW0 Pin4 -> Port number 4 -> AUDIO1 RX + * SDW0 Pin5 -> Port number 5 -> AUDIO2 RX + * Whereas for SDW1 instance + * SDW1 Pin0 -> port number 0 -> AUDIO1 TX + * SDW1 Pin1 -> Port number 1 -> AUDIO1 RX + * Same mapping should be used for programming DMA controller registers in SoundWire DMA driver. + * i.e if AUDIO0 TX channel is selected then we need to use AUDIO0 TX registers for DMA programming + * in SoundWire DMA driver. + */ + static struct sdw_manager_dp_reg sdw0_manager_dp_reg[AMD_SDW0_MAX_DAI] = { {ACP_SW_AUDIO0_TX_FRAME_FORMAT, ACP_SW_AUDIO0_TX_SAMPLEINTERVAL, ACP_SW_AUDIO0_TX_HCTRL_DP0, ACP_SW_AUDIO0_TX_OFFSET_DP0, ACP_SW_AUDIO0_TX_CHANNEL_ENABLE_DP0}, diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index c14a291a40e8..ac537419301d 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -23,6 +23,21 @@ struct sdw_manager_reg_mask { u32 acp_sdw_intr_mask; }; +/** + * struct sdw_amd_dai_runtime: AMD sdw dai runtime data + * + * @name: SoundWire stream name + * @stream: stream runtime + * @bus: Bus handle + * @stream_type: Stream type + */ +struct sdw_amd_dai_runtime { + char *name; + struct sdw_stream_runtime *stream; + struct sdw_bus *bus; + enum sdw_stream_type stream_type; +}; + /** * struct amd_sdw_manager - amd manager driver context * @bus: bus handle @@ -40,6 +55,7 @@ struct sdw_manager_reg_mask { * @quirks: SoundWire manager quirks * @wake_en_mask: wake enable mask per SoundWire manager * @power_mode_mask: flag interprets amd SoundWire manager power mode + * @dai_runtime_array: dai runtime array */ struct amd_sdw_manager { struct sdw_bus bus; @@ -63,5 +79,7 @@ struct amd_sdw_manager { u32 quirks; u32 wake_en_mask; u32 power_mode_mask; + + struct sdw_amd_dai_runtime **dai_runtime_array; }; #endif -- GitLab From c0bf349ea95be03e9903381297b7ef4d8ce1053f Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:57 +0530 Subject: [PATCH 2682/5631] soundwire: amd: enable build for AMD SoundWire manager driver Enable build for SoundWire manager driver for AMD platforms. Signed-off-by: Vijendar Mukunda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230220100418.76754-5-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-5-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/Kconfig | 10 ++++++++++ drivers/soundwire/Makefile | 4 ++++ 2 files changed, 14 insertions(+) diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index 2b7795233282..fa71c9a36df7 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -18,6 +18,16 @@ if SOUNDWIRE comment "SoundWire Devices" +config SOUNDWIRE_AMD + tristate "AMD SoundWire Manager driver" + select SOUNDWIRE_GENERIC_ALLOCATION + depends on ACPI && SND_SOC + help + SoundWire AMD Manager driver. + If you have an AMD platform which has a SoundWire Manager then + enable this config option to get the SoundWire support for that + device. + config SOUNDWIRE_CADENCE tristate diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile index 8038e840ac5b..925566ff4272 100644 --- a/drivers/soundwire/Makefile +++ b/drivers/soundwire/Makefile @@ -15,6 +15,10 @@ ifdef CONFIG_DEBUG_FS soundwire-bus-y += debugfs.o endif +#AMD driver +soundwire-amd-y := amd_manager.o +obj-$(CONFIG_SOUNDWIRE_AMD) += soundwire-amd.o + #Cadence Objs soundwire-cadence-y := cadence_master.o obj-$(CONFIG_SOUNDWIRE_CADENCE) += soundwire-cadence.o -- GitLab From 65f93e4096a07abd41acf0d240715bd8c7ef7eeb Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:58 +0530 Subject: [PATCH 2683/5631] soundwire: amd: add SoundWire manager interrupt handling Add support for handling SoundWire manager interrupts. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-6-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-6-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 126 ++++++++++++++++++++++++++++++ drivers/soundwire/amd_manager.h | 1 + include/linux/soundwire/sdw_amd.h | 7 ++ 3 files changed, 134 insertions(+) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index f12dad6c3226..49b7133cb41f 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -327,6 +327,47 @@ static enum sdw_command_response amd_sdw_xfer_msg(struct sdw_bus *bus, struct sd return SDW_CMD_OK; } +static void amd_sdw_fill_slave_status(struct amd_sdw_manager *amd_manager, u16 index, u32 status) +{ + switch (status) { + case SDW_SLAVE_ATTACHED: + case SDW_SLAVE_UNATTACHED: + case SDW_SLAVE_ALERT: + amd_manager->status[index] = status; + break; + default: + amd_manager->status[index] = SDW_SLAVE_RESERVED; + break; + } +} + +static void amd_sdw_process_ping_status(u64 response, struct amd_sdw_manager *amd_manager) +{ + u64 slave_stat; + u32 val; + u16 dev_index; + + /* slave status response */ + slave_stat = FIELD_GET(AMD_SDW_MCP_SLAVE_STAT_0_3, response); + slave_stat |= FIELD_GET(AMD_SDW_MCP_SLAVE_STAT_4_11, response) << 8; + dev_dbg(amd_manager->dev, "slave_stat:0x%llx\n", slave_stat); + for (dev_index = 0; dev_index <= SDW_MAX_DEVICES; ++dev_index) { + val = (slave_stat >> (dev_index * 2)) & AMD_SDW_MCP_SLAVE_STATUS_MASK; + dev_dbg(amd_manager->dev, "val:0x%x\n", val); + amd_sdw_fill_slave_status(amd_manager, dev_index, val); + } +} + +static void amd_sdw_read_and_process_ping_status(struct amd_sdw_manager *amd_manager) +{ + u64 response; + + mutex_lock(&amd_manager->bus.msg_lock); + response = amd_sdw_send_cmd_get_resp(amd_manager, 0, 0); + mutex_unlock(&amd_manager->bus.msg_lock); + amd_sdw_process_ping_status(response, amd_manager); +} + static u32 amd_sdw_read_ping_status(struct sdw_bus *bus) { struct amd_sdw_manager *amd_manager = to_amd_sdw(bus); @@ -723,6 +764,89 @@ static int amd_sdw_register_dais(struct amd_sdw_manager *amd_manager) dais, num_dais); } +static void amd_sdw_update_slave_status_work(struct work_struct *work) +{ + struct amd_sdw_manager *amd_manager = + container_of(work, struct amd_sdw_manager, amd_sdw_work); + int retry_count = 0; + + if (amd_manager->status[0] == SDW_SLAVE_ATTACHED) { + writel(0, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_0TO7); + writel(0, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + } + +update_status: + sdw_handle_slave_status(&amd_manager->bus, amd_manager->status); + /* + * During the peripheral enumeration sequence, the SoundWire manager interrupts + * are masked. Once the device number programming is done for all peripherals, + * interrupts will be unmasked. Read the peripheral device status from ping command + * and process the response. This sequence will ensure all peripheral devices enumerated + * and initialized properly. + */ + if (amd_manager->status[0] == SDW_SLAVE_ATTACHED) { + if (retry_count++ < SDW_MAX_DEVICES) { + writel(AMD_SDW_IRQ_MASK_0TO7, amd_manager->mmio + + ACP_SW_STATE_CHANGE_STATUS_MASK_0TO7); + writel(AMD_SDW_IRQ_MASK_8TO11, amd_manager->mmio + + ACP_SW_STATE_CHANGE_STATUS_MASK_8TO11); + amd_sdw_read_and_process_ping_status(amd_manager); + goto update_status; + } else { + dev_err_ratelimited(amd_manager->dev, + "Device0 detected after %d iterations\n", + retry_count); + } + } +} + +static void amd_sdw_update_slave_status(u32 status_change_0to7, u32 status_change_8to11, + struct amd_sdw_manager *amd_manager) +{ + u64 slave_stat; + u32 val; + int dev_index; + + if (status_change_0to7 == AMD_SDW_SLAVE_0_ATTACHED) + memset(amd_manager->status, 0, sizeof(amd_manager->status)); + slave_stat = status_change_0to7; + slave_stat |= FIELD_GET(AMD_SDW_MCP_SLAVE_STATUS_8TO_11, status_change_8to11) << 32; + dev_dbg(amd_manager->dev, "status_change_0to7:0x%x status_change_8to11:0x%x\n", + status_change_0to7, status_change_8to11); + if (slave_stat) { + for (dev_index = 0; dev_index <= SDW_MAX_DEVICES; ++dev_index) { + if (slave_stat & AMD_SDW_MCP_SLAVE_STATUS_VALID_MASK(dev_index)) { + val = (slave_stat >> AMD_SDW_MCP_SLAVE_STAT_SHIFT_MASK(dev_index)) & + AMD_SDW_MCP_SLAVE_STATUS_MASK; + amd_sdw_fill_slave_status(amd_manager, dev_index, val); + } + } + } +} + +static void amd_sdw_irq_thread(struct work_struct *work) +{ + struct amd_sdw_manager *amd_manager = + container_of(work, struct amd_sdw_manager, amd_sdw_irq_thread); + u32 status_change_8to11; + u32 status_change_0to7; + + status_change_8to11 = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_8TO11); + status_change_0to7 = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_0TO7); + dev_dbg(amd_manager->dev, "[SDW%d] SDW INT: 0to7=0x%x, 8to11=0x%x\n", + amd_manager->instance, status_change_0to7, status_change_8to11); + if (status_change_8to11 & AMD_SDW_PREQ_INTR_STAT) { + amd_sdw_read_and_process_ping_status(amd_manager); + } else { + /* Check for the updated status on peripheral device */ + amd_sdw_update_slave_status(status_change_0to7, status_change_8to11, amd_manager); + } + if (status_change_8to11 || status_change_0to7) + schedule_work(&amd_manager->amd_sdw_work); + writel(0x00, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_8TO11); + writel(0x00, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_0TO7); +} + static void amd_sdw_probe_work(struct work_struct *work) { struct amd_sdw_manager *amd_manager = container_of(work, struct amd_sdw_manager, @@ -815,6 +939,8 @@ static int amd_sdw_manager_probe(struct platform_device *pdev) return ret; } dev_set_drvdata(dev, amd_manager); + INIT_WORK(&amd_manager->amd_sdw_irq_thread, amd_sdw_irq_thread); + INIT_WORK(&amd_manager->amd_sdw_work, amd_sdw_update_slave_status_work); INIT_WORK(&amd_manager->probe_work, amd_sdw_probe_work); /* * Instead of having lengthy probe sequence, use deferred probe. diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index c92e0dee2cb1..fca7d792bf5f 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -185,6 +185,7 @@ #define AMD_SDW1_PAD_KEEPER_EN_MASK 0x10 #define AMD_SDW0_PAD_KEEPER_DISABLE_MASK 0x1e #define AMD_SDW1_PAD_KEEPER_DISABLE_MASK 0xf +#define AMD_SDW_PREQ_INTR_STAT BIT(19) static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { AMD_SDW_DEFAULT_CLK_FREQ, diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index ac537419301d..df60bc0de6fc 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -45,8 +45,11 @@ struct sdw_amd_dai_runtime { * @mmio: SoundWire registers mmio base * @acp_mmio: acp registers mmio base * @reg_mask: register mask structure per manager instance + * @amd_sdw_irq_thread: SoundWire manager irq workqueue + * @amd_sdw_work: peripheral status work queue * @probe_work: SoundWire manager probe workqueue * @acp_sdw_lock: mutex to protect acp share register access + * @status: peripheral devices status array * @num_din_ports: number of input ports * @num_dout_ports: number of output ports * @cols_index: Column index in frame shape @@ -65,10 +68,14 @@ struct amd_sdw_manager { void __iomem *acp_mmio; struct sdw_manager_reg_mask *reg_mask; + struct work_struct amd_sdw_irq_thread; + struct work_struct amd_sdw_work; struct work_struct probe_work; /* mutex to protect acp common register access */ struct mutex *acp_sdw_lock; + enum sdw_slave_status status[SDW_MAX_DEVICES + 1]; + int num_din_ports; int num_dout_ports; -- GitLab From 81ff58ff71ad9dcddf5caffcf912cde6589d07bd Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:38:59 +0530 Subject: [PATCH 2684/5631] soundwire: amd: add runtime pm ops for AMD SoundWire manager driver Add support for runtime pm ops for AMD SoundWire manager driver. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-7-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-7-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 140 ++++++++++++++++++++++++++++++ drivers/soundwire/amd_manager.h | 3 + include/linux/soundwire/sdw_amd.h | 17 ++++ 3 files changed, 160 insertions(+) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 49b7133cb41f..6172b3cb84d4 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -133,6 +134,12 @@ static void amd_disable_sdw_interrupts(struct amd_sdw_manager *amd_manager) writel(0x00, amd_manager->mmio + ACP_SW_ERROR_INTR_MASK); } +static int amd_deinit_sdw_manager(struct amd_sdw_manager *amd_manager) +{ + amd_disable_sdw_interrupts(amd_manager); + return amd_disable_sdw_manager(amd_manager); +} + static void amd_sdw_set_frameshape(struct amd_sdw_manager *amd_manager) { u32 frame_size; @@ -866,6 +873,12 @@ static void amd_sdw_probe_work(struct work_struct *work) return; amd_sdw_set_frameshape(amd_manager); } + /* Enable runtime PM */ + pm_runtime_set_autosuspend_delay(amd_manager->dev, AMD_SDW_MASTER_SUSPEND_DELAY_MS); + pm_runtime_use_autosuspend(amd_manager->dev); + pm_runtime_mark_last_busy(amd_manager->dev); + pm_runtime_set_active(amd_manager->dev); + pm_runtime_enable(amd_manager->dev); } static int amd_sdw_manager_probe(struct platform_device *pdev) @@ -953,17 +966,144 @@ static int amd_sdw_manager_remove(struct platform_device *pdev) { struct amd_sdw_manager *amd_manager = dev_get_drvdata(&pdev->dev); + pm_runtime_disable(&pdev->dev); cancel_work_sync(&amd_manager->probe_work); amd_disable_sdw_interrupts(amd_manager); sdw_bus_master_delete(&amd_manager->bus); return amd_disable_sdw_manager(amd_manager); } +static int amd_sdw_clock_stop(struct amd_sdw_manager *amd_manager) +{ + u32 val; + int ret; + + ret = sdw_bus_prep_clk_stop(&amd_manager->bus); + if (ret < 0 && ret != -ENODATA) { + dev_err(amd_manager->dev, "prepare clock stop failed %d", ret); + return 0; + } + ret = sdw_bus_clk_stop(&amd_manager->bus); + if (ret < 0 && ret != -ENODATA) { + dev_err(amd_manager->dev, "bus clock stop failed %d", ret); + return 0; + } + + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL, val, + (val & AMD_SDW_CLK_STOP_DONE), ACP_DELAY_US, AMD_SDW_TIMEOUT); + if (ret) { + dev_err(amd_manager->dev, "SDW%x clock stop failed\n", amd_manager->instance); + return 0; + } + + amd_manager->clk_stopped = true; + if (amd_manager->wake_en_mask) + writel(0x01, amd_manager->acp_mmio + ACP_SW_WAKE_EN(amd_manager->instance)); + + dev_dbg(amd_manager->dev, "SDW%x clock stop successful\n", amd_manager->instance); + return 0; +} + +static int amd_sdw_clock_stop_exit(struct amd_sdw_manager *amd_manager) +{ + int ret; + u32 val; + + if (amd_manager->clk_stopped) { + val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + val |= AMD_SDW_CLK_RESUME_REQ; + writel(val, amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL, val, + (val & AMD_SDW_CLK_RESUME_DONE), ACP_DELAY_US, + AMD_SDW_TIMEOUT); + if (val & AMD_SDW_CLK_RESUME_DONE) { + writel(0, amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + ret = sdw_bus_exit_clk_stop(&amd_manager->bus); + if (ret < 0) + dev_err(amd_manager->dev, "bus failed to exit clock stop %d\n", + ret); + amd_manager->clk_stopped = false; + } + } + if (amd_manager->clk_stopped) { + dev_err(amd_manager->dev, "SDW%x clock stop exit failed\n", amd_manager->instance); + return 0; + } + dev_dbg(amd_manager->dev, "SDW%x clock stop exit successful\n", amd_manager->instance); + return 0; +} + +static int __maybe_unused amd_suspend_runtime(struct device *dev) +{ + struct amd_sdw_manager *amd_manager = dev_get_drvdata(dev); + struct sdw_bus *bus = &amd_manager->bus; + int ret; + + if (bus->prop.hw_disabled) { + dev_dbg(bus->dev, "SoundWire manager %d is disabled,\n", + bus->link_id); + return 0; + } + if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + return amd_sdw_clock_stop(amd_manager); + } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + ret = amd_sdw_clock_stop(amd_manager); + if (ret) + return ret; + return amd_deinit_sdw_manager(amd_manager); + } + return 0; +} + +static int __maybe_unused amd_resume_runtime(struct device *dev) +{ + struct amd_sdw_manager *amd_manager = dev_get_drvdata(dev); + struct sdw_bus *bus = &amd_manager->bus; + int ret; + u32 val; + + if (bus->prop.hw_disabled) { + dev_dbg(bus->dev, "SoundWire manager %d is disabled, ignoring\n", + bus->link_id); + return 0; + } + + if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + return amd_sdw_clock_stop_exit(amd_manager); + } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + if (val) { + val |= AMD_SDW_CLK_RESUME_REQ; + writel(val, amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + ret = readl_poll_timeout(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL, val, + (val & AMD_SDW_CLK_RESUME_DONE), ACP_DELAY_US, + AMD_SDW_TIMEOUT); + if (val & AMD_SDW_CLK_RESUME_DONE) { + writel(0, amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); + amd_manager->clk_stopped = false; + } + } + sdw_clear_slave_status(bus, SDW_UNATTACH_REQUEST_MASTER_RESET); + amd_init_sdw_manager(amd_manager); + amd_enable_sdw_interrupts(amd_manager); + ret = amd_enable_sdw_manager(amd_manager); + if (ret) + return ret; + amd_sdw_set_frameshape(amd_manager); + } + return 0; +} + +static const struct dev_pm_ops amd_pm = { + SET_RUNTIME_PM_OPS(amd_suspend_runtime, amd_resume_runtime, NULL) +}; + static struct platform_driver amd_sdw_driver = { .probe = &amd_sdw_manager_probe, .remove = &amd_sdw_manager_remove, .driver = { .name = "amd_sdw_manager", + .pm = &amd_pm, } }; module_platform_driver(amd_sdw_driver); diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index fca7d792bf5f..b101f4536230 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -186,6 +186,9 @@ #define AMD_SDW0_PAD_KEEPER_DISABLE_MASK 0x1e #define AMD_SDW1_PAD_KEEPER_DISABLE_MASK 0xf #define AMD_SDW_PREQ_INTR_STAT BIT(19) +#define AMD_SDW_CLK_STOP_DONE 1 +#define AMD_SDW_CLK_RESUME_REQ 2 +#define AMD_SDW_CLK_RESUME_DONE 3 static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { AMD_SDW_DEFAULT_CLK_FREQ, diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h index df60bc0de6fc..ceecad74aef9 100644 --- a/include/linux/soundwire/sdw_amd.h +++ b/include/linux/soundwire/sdw_amd.h @@ -8,6 +8,21 @@ #include +/* AMD pm_runtime quirk definitions */ + +/* + * Force the clock to stop(ClockStopMode0) when suspend callback + * is invoked. + */ +#define AMD_SDW_CLK_STOP_MODE 1 + +/* + * Stop the bus when runtime suspend/system level suspend callback + * is invoked. If set, a complete bus reset and re-enumeration will + * be performed when the bus restarts. In-band wake interrupts are + * not supported in this mode. + */ +#define AMD_SDW_POWER_OFF_MODE 2 #define ACP_SDW0 0 #define ACP_SDW1 1 @@ -57,6 +72,7 @@ struct sdw_amd_dai_runtime { * @instance: SoundWire manager instance * @quirks: SoundWire manager quirks * @wake_en_mask: wake enable mask per SoundWire manager + * @clk_stopped: flag set to true when clock is stopped * @power_mode_mask: flag interprets amd SoundWire manager power mode * @dai_runtime_array: dai runtime array */ @@ -86,6 +102,7 @@ struct amd_sdw_manager { u32 quirks; u32 wake_en_mask; u32 power_mode_mask; + bool clk_stopped; struct sdw_amd_dai_runtime **dai_runtime_array; }; -- GitLab From 66c878838f37912ba295c41e749a25fc356341ea Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:39:00 +0530 Subject: [PATCH 2685/5631] soundwire: amd: handle SoundWire wake enable interrupt Add wake enable interrupt support for both the SoundWire manager instances. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230227154801.50319-8-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-8-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 10 ++++++++++ drivers/soundwire/amd_manager.h | 1 + 2 files changed, 11 insertions(+) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 6172b3cb84d4..d55706e87d83 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -831,6 +831,13 @@ static void amd_sdw_update_slave_status(u32 status_change_0to7, u32 status_chang } } +static void amd_sdw_process_wake_event(struct amd_sdw_manager *amd_manager) +{ + pm_request_resume(amd_manager->dev); + writel(0x00, amd_manager->acp_mmio + ACP_SW_WAKE_EN(amd_manager->instance)); + writel(0x00, amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_8TO11); +} + static void amd_sdw_irq_thread(struct work_struct *work) { struct amd_sdw_manager *amd_manager = @@ -842,6 +849,9 @@ static void amd_sdw_irq_thread(struct work_struct *work) status_change_0to7 = readl(amd_manager->mmio + ACP_SW_STATE_CHANGE_STATUS_0TO7); dev_dbg(amd_manager->dev, "[SDW%d] SDW INT: 0to7=0x%x, 8to11=0x%x\n", amd_manager->instance, status_change_0to7, status_change_8to11); + if (status_change_8to11 & AMD_SDW_WAKE_STAT_MASK) + return amd_sdw_process_wake_event(amd_manager); + if (status_change_8to11 & AMD_SDW_PREQ_INTR_STAT) { amd_sdw_read_and_process_ping_status(amd_manager); } else { diff --git a/drivers/soundwire/amd_manager.h b/drivers/soundwire/amd_manager.h index b101f4536230..5f040151a259 100644 --- a/drivers/soundwire/amd_manager.h +++ b/drivers/soundwire/amd_manager.h @@ -189,6 +189,7 @@ #define AMD_SDW_CLK_STOP_DONE 1 #define AMD_SDW_CLK_RESUME_REQ 2 #define AMD_SDW_CLK_RESUME_DONE 3 +#define AMD_SDW_WAKE_STAT_MASK BIT(16) static u32 amd_sdw_freq_tbl[AMD_SDW_MAX_FREQ_NUM] = { AMD_SDW_DEFAULT_CLK_FREQ, -- GitLab From 9cf1efc5ed2dde138acee54c0d00cf3664e2f465 Mon Sep 17 00:00:00 2001 From: Vijendar Mukunda Date: Tue, 21 Mar 2023 10:39:01 +0530 Subject: [PATCH 2686/5631] soundwire: amd: add pm_prepare callback and pm ops support Add pm_prepare callback and System level pm ops support for AMD SoundWire manager driver. Signed-off-by: Vijendar Mukunda Signed-off-by: Mastan Katragadda Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/lkml/20230310162554.699766-9-Vijendar.Mukunda@amd.com Link: https://lore.kernel.org/r/20230321050901.115439-9-Vijendar.Mukunda@amd.com Signed-off-by: Vinod Koul --- drivers/soundwire/amd_manager.c | 84 +++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index d55706e87d83..9fb7f91ca182 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -1043,6 +1043,88 @@ static int amd_sdw_clock_stop_exit(struct amd_sdw_manager *amd_manager) return 0; } +static int amd_resume_child_device(struct device *dev, void *data) +{ + struct sdw_slave *slave = dev_to_sdw_dev(dev); + int ret; + + if (!slave->probed) { + dev_dbg(dev, "skipping device, no probed driver\n"); + return 0; + } + if (!slave->dev_num_sticky) { + dev_dbg(dev, "skipping device, never detected on bus\n"); + return 0; + } + ret = pm_request_resume(dev); + if (ret < 0) { + dev_err(dev, "pm_request_resume failed: %d\n", ret); + return ret; + } + return 0; +} + +static int __maybe_unused amd_pm_prepare(struct device *dev) +{ + struct amd_sdw_manager *amd_manager = dev_get_drvdata(dev); + struct sdw_bus *bus = &amd_manager->bus; + int ret; + + if (bus->prop.hw_disabled) { + dev_dbg(bus->dev, "SoundWire manager %d is disabled, ignoring\n", + bus->link_id); + return 0; + } + /* + * When multiple peripheral devices connected over the same link, if SoundWire manager + * device is not in runtime suspend state, observed that device alerts are missing + * without pm_prepare on AMD platforms in clockstop mode0. + */ + if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + ret = pm_request_resume(dev); + if (ret < 0) { + dev_err(bus->dev, "pm_request_resume failed: %d\n", ret); + return 0; + } + } + /* To force peripheral devices to system level suspend state, resume the devices + * from runtime suspend state first. Without that unable to dispatch the alert + * status to peripheral driver during system level resume as they are in runtime + * suspend state. + */ + ret = device_for_each_child(bus->dev, NULL, amd_resume_child_device); + if (ret < 0) + dev_err(dev, "amd_resume_child_device failed: %d\n", ret); + return 0; +} + +static int __maybe_unused amd_suspend(struct device *dev) +{ + struct amd_sdw_manager *amd_manager = dev_get_drvdata(dev); + struct sdw_bus *bus = &amd_manager->bus; + int ret; + + if (bus->prop.hw_disabled) { + dev_dbg(bus->dev, "SoundWire manager %d is disabled, ignoring\n", + bus->link_id); + return 0; + } + + if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + return amd_sdw_clock_stop(amd_manager); + } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + /* + * As per hardware programming sequence on AMD platforms, + * clock stop should be invoked first before powering-off + */ + ret = amd_sdw_clock_stop(amd_manager); + if (ret) + return ret; + return amd_deinit_sdw_manager(amd_manager); + } + return 0; +} + static int __maybe_unused amd_suspend_runtime(struct device *dev) { struct amd_sdw_manager *amd_manager = dev_get_drvdata(dev); @@ -1105,6 +1187,8 @@ static int __maybe_unused amd_resume_runtime(struct device *dev) } static const struct dev_pm_ops amd_pm = { + .prepare = amd_pm_prepare, + SET_SYSTEM_SLEEP_PM_OPS(amd_suspend, amd_resume_runtime) SET_RUNTIME_PM_OPS(amd_suspend_runtime, amd_resume_runtime, NULL) }; -- GitLab From d014688eb3734c4101e3f03e3dc90f557021b7e8 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 22 Mar 2023 11:55:23 +0800 Subject: [PATCH 2687/5631] soundwire: stream: remove bus->dev from logs on multiple buses A stream may depend on multiple managers/buses, e.g. for the multiple amplifier case. It's incorrect to use bus->dev in this case. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230322035524.1509029-2-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 136b6850a3f0..f903394ff2cf 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -1389,7 +1389,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream, ret = do_bank_switch(stream); if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d\n", ret); + pr_err("Bank switch failed: %d\n", ret); goto restore_params; } @@ -1497,7 +1497,7 @@ static int _sdw_enable_stream(struct sdw_stream_runtime *stream) ret = do_bank_switch(stream); if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d\n", ret); + pr_err("Bank switch failed: %d\n", ret); return ret; } -- GitLab From 68d9bfb668d6eecb37abf80b4c77aed7120a1376 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 22 Mar 2023 11:55:24 +0800 Subject: [PATCH 2688/5631] soundwire: stream: uniquify dev_err() logs There are a couple of duplicate logs which makes harder than needed to follow the error flows. Add __func__ or make the log unique. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230322035524.1509029-3-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index f903394ff2cf..c2191c07442b 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -1389,7 +1389,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream, ret = do_bank_switch(stream); if (ret < 0) { - pr_err("Bank switch failed: %d\n", ret); + pr_err("%s: do_bank_switch failed: %d\n", __func__, ret); goto restore_params; } @@ -1477,7 +1477,7 @@ static int _sdw_enable_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus, false); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d\n", ret); + dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret); return ret; } @@ -1497,7 +1497,7 @@ static int _sdw_enable_stream(struct sdw_stream_runtime *stream) ret = do_bank_switch(stream); if (ret < 0) { - pr_err("Bank switch failed: %d\n", ret); + pr_err("%s: do_bank_switch failed: %d\n", __func__, ret); return ret; } @@ -1567,14 +1567,14 @@ static int _sdw_disable_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus, false); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d\n", ret); + dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret); return ret; } } ret = do_bank_switch(stream); if (ret < 0) { - pr_err("Bank switch failed: %d\n", ret); + pr_err("%s: do_bank_switch failed: %d\n", __func__, ret); return ret; } @@ -1664,7 +1664,7 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus, false); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d\n", ret); + dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret); return ret; } } @@ -1893,7 +1893,8 @@ int sdw_stream_add_master(struct sdw_bus *bus, m_rt = sdw_master_rt_alloc(bus, stream); if (!m_rt) { - dev_err(bus->dev, "Master runtime alloc failed for stream:%s\n", stream->name); + dev_err(bus->dev, "%s: Master runtime alloc failed for stream:%s\n", + __func__, stream->name); ret = -ENOMEM; goto unlock; } @@ -2012,7 +2013,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, */ m_rt = sdw_master_rt_alloc(slave->bus, stream); if (!m_rt) { - dev_err(&slave->dev, "Master runtime alloc failed for stream:%s\n", stream->name); + dev_err(&slave->dev, "%s: Master runtime alloc failed for stream:%s\n", + __func__, stream->name); ret = -ENOMEM; goto unlock; } -- GitLab From ff9608c32e64da465c2939af261a3850fdb8ddbb Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 22 Mar 2023 16:49:46 +0000 Subject: [PATCH 2689/5631] soundwire: bus: Remove now outdated comments on no_pm IO Things have moved more towards end drivers using the no_pm versions of the IO functions. See commits: commit 167790abb90f ("soundwire: export sdw_write/read_no_pm functions") commit 62dc9f3f2fd0 ("soundwire: bus: export sdw_nwrite_no_pm and sdw_nread_no_pm functions") As such this comment is now misleading, so remove it. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20230322164948.566962-1-ckeepax@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index b6aca59c3130..3c67266f9483 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -384,9 +384,6 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, /* * Read/Write IO functions. - * no_pm versions can only be called by the bus, e.g. while enumerating or - * handling suspend-resume sequences. - * all clients need to use the pm versions */ int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) -- GitLab From d94e1e01c70375fcc102a8d09a00d28efeeef51c Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 22 Mar 2023 16:49:47 +0000 Subject: [PATCH 2690/5631] soundwire: bus: Update kernel doc for no_pm functions The kernel doc should really have been updated when the no_pm versions of the sdw_write/read functions were exported in commits: commit 167790abb90f ("soundwire: export sdw_write/read_no_pm functions") commit 62dc9f3f2fd0 ("soundwire: bus: export sdw_nwrite_no_pm and sdw_nread_no_pm functions") Add the missing kernel doc. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20230322164948.566962-2-ckeepax@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 3c67266f9483..f1ffb8e0839d 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -386,6 +386,13 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, * Read/Write IO functions. */ +/** + * sdw_nread_no_pm() - Read "n" contiguous SDW Slave registers with no PM + * @slave: SDW Slave + * @addr: Register address + * @count: length + * @val: Buffer for values to be read + */ int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { struct sdw_msg msg; @@ -403,6 +410,13 @@ int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) } EXPORT_SYMBOL(sdw_nread_no_pm); +/** + * sdw_nwrite_no_pm() - Write "n" contiguous SDW Slave registers with no PM + * @slave: SDW Slave + * @addr: Register address + * @count: length + * @val: Buffer for values to be written + */ int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { struct sdw_msg msg; @@ -420,6 +434,12 @@ int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 * } EXPORT_SYMBOL(sdw_nwrite_no_pm); +/** + * sdw_write_no_pm() - Write a SDW Slave register with no PM + * @slave: SDW Slave + * @addr: Register address + * @value: Register value + */ int sdw_write_no_pm(struct sdw_slave *slave, u32 addr, u8 value) { return sdw_nwrite_no_pm(slave, addr, 1, &value); @@ -492,6 +512,11 @@ int sdw_bwrite_no_pm_unlocked(struct sdw_bus *bus, u16 dev_num, u32 addr, u8 val } EXPORT_SYMBOL(sdw_bwrite_no_pm_unlocked); +/** + * sdw_read_no_pm() - Read a SDW Slave register with no PM + * @slave: SDW Slave + * @addr: Register address + */ int sdw_read_no_pm(struct sdw_slave *slave, u32 addr) { u8 buf; @@ -538,6 +563,9 @@ EXPORT_SYMBOL(sdw_update); * @addr: Register address * @count: length * @val: Buffer for values to be read + * + * This version of the function will take a PM reference to the slave + * device. */ int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { @@ -562,6 +590,9 @@ EXPORT_SYMBOL(sdw_nread); * @addr: Register address * @count: length * @val: Buffer for values to be written + * + * This version of the function will take a PM reference to the slave + * device. */ int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { @@ -584,6 +615,9 @@ EXPORT_SYMBOL(sdw_nwrite); * sdw_read() - Read a SDW Slave register * @slave: SDW Slave * @addr: Register address + * + * This version of the function will take a PM reference to the slave + * device. */ int sdw_read(struct sdw_slave *slave, u32 addr) { @@ -603,6 +637,9 @@ EXPORT_SYMBOL(sdw_read); * @slave: SDW Slave * @addr: Register address * @value: Register value + * + * This version of the function will take a PM reference to the slave + * device. */ int sdw_write(struct sdw_slave *slave, u32 addr, u8 value) { -- GitLab From d005ea713dd721c1ce9010e608eb416a3890d6b4 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 22 Mar 2023 16:49:48 +0000 Subject: [PATCH 2691/5631] soundwire: bus: Update sdw_nread/nwrite_no_pm to handle page boundaries Currently issuing a sdw_nread/nwrite_no_pm across a page boundary will silently fail to write correctly as nothing updates the page registers, meaning the same page of the chip will get rewritten with each successive page of data. As the sdw_msg structure contains page information it seems reasonable that a single sdw_msg should always be within one page. It is also mostly simpler to handle the paging at the bus level rather than each master having to handle it in their xfer_msg callback. As such add handling to the bus code to split up a transfer into multiple sdw_msg's when they go across page boundaries. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20230322164948.566962-3-ckeepax@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 63 +++++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 24 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index f1ffb8e0839d..e157a39a82ce 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -386,27 +386,46 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, * Read/Write IO functions. */ +static int sdw_ntransfer_no_pm(struct sdw_slave *slave, u32 addr, u8 flags, + size_t count, u8 *val) +{ + struct sdw_msg msg; + size_t size; + int ret; + + while (count) { + // Only handle bytes up to next page boundary + size = min_t(size_t, count, (SDW_REGADDR + 1) - (addr & SDW_REGADDR)); + + ret = sdw_fill_msg(&msg, slave, addr, size, slave->dev_num, flags, val); + if (ret < 0) + return ret; + + ret = sdw_transfer(slave->bus, &msg); + if (ret < 0 && !slave->is_mockup_device) + return ret; + + addr += size; + val += size; + count -= size; + } + + return 0; +} + /** * sdw_nread_no_pm() - Read "n" contiguous SDW Slave registers with no PM * @slave: SDW Slave * @addr: Register address * @count: length * @val: Buffer for values to be read + * + * Note that if the message crosses a page boundary each page will be + * transferred under a separate invocation of the msg_lock. */ int sdw_nread_no_pm(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { - struct sdw_msg msg; - int ret; - - ret = sdw_fill_msg(&msg, slave, addr, count, - slave->dev_num, SDW_MSG_FLAG_READ, val); - if (ret < 0) - return ret; - - ret = sdw_transfer(slave->bus, &msg); - if (slave->is_mockup_device) - ret = 0; - return ret; + return sdw_ntransfer_no_pm(slave, addr, SDW_MSG_FLAG_READ, count, val); } EXPORT_SYMBOL(sdw_nread_no_pm); @@ -416,21 +435,13 @@ EXPORT_SYMBOL(sdw_nread_no_pm); * @addr: Register address * @count: length * @val: Buffer for values to be written + * + * Note that if the message crosses a page boundary each page will be + * transferred under a separate invocation of the msg_lock. */ int sdw_nwrite_no_pm(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { - struct sdw_msg msg; - int ret; - - ret = sdw_fill_msg(&msg, slave, addr, count, - slave->dev_num, SDW_MSG_FLAG_WRITE, (u8 *)val); - if (ret < 0) - return ret; - - ret = sdw_transfer(slave->bus, &msg); - if (slave->is_mockup_device) - ret = 0; - return ret; + return sdw_ntransfer_no_pm(slave, addr, SDW_MSG_FLAG_WRITE, count, (u8 *)val); } EXPORT_SYMBOL(sdw_nwrite_no_pm); @@ -566,6 +577,8 @@ EXPORT_SYMBOL(sdw_update); * * This version of the function will take a PM reference to the slave * device. + * Note that if the message crosses a page boundary each page will be + * transferred under a separate invocation of the msg_lock. */ int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { @@ -593,6 +606,8 @@ EXPORT_SYMBOL(sdw_nread); * * This version of the function will take a PM reference to the slave * device. + * Note that if the message crosses a page boundary each page will be + * transferred under a separate invocation of the msg_lock. */ int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { -- GitLab From 0a0d1740bd8fd7dafb81fcb102fb5d0b83b1ce73 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 21 Mar 2023 10:26:42 +0800 Subject: [PATCH 2692/5631] soundwire: intel: don't save hw_params for use in prepare MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The existing code copies the hw_params pointer and reuses it later in .prepare, specifically to re-initialize the ALH DMA channel information that's lost in suspend-resume cycles. This is not needed, we can directly access the information from the substream/rtd - as done for the HDAudio DAIs in sound/soc/sof/intel/hda-dai.c In addition, using the saved pointer causes the suspend-resume test cases to fail on specific platforms, depending on which version of GCC is used. Péter Ujfalusi and I have spent long hours to root-cause this problem that was reported by the Intel CI first with 6.2-rc1 and again v6.3-rc1. In the latter case we were lucky that the problem was 100% reproducible on local test devices, and found out that adding a dev_dbg() or adding a call to usleep_range() just before accessing the saved pointer "fixed" the issue. With errors appearing just by changing the compiler version or minor changes in the code generated, clearly we have a memory management Heisenbug. The root-cause seems to be that the hw_params pointer is not persistent. The soc-pcm code allocates the hw_params structure on the stack, and passes it to the BE dailink hw_params and DAIs hw_params. Saving such a pointer and reusing it later during the .prepare stage cannot possibly work reliably, it's broken-by-design since v5.10. It's astonishing that the problem was not seen earlier. This simple fix will have to be back-ported to -stable, due to changes to avoid the use of the get/set_dmadata routines this patch will only apply on kernels older than v6.1. Fixes: a5a0239c27fe ("soundwire: intel: reinitialize IP+DSP in .prepare(), but only when resuming") Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Péter Ujfalusi Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230321022642.1426611-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.h | 2 -- drivers/soundwire/intel.c | 11 +++++++---- 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index b653734085d9..27c56274217f 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -84,7 +84,6 @@ struct sdw_cdns_stream_config { * @bus: Bus handle * @stream_type: Stream type * @link_id: Master link id - * @hw_params: hw_params to be applied in .prepare step * @suspended: status set when suspended, to be used in .prepare * @paused: status set in .trigger, to be used in suspend * @direction: stream direction @@ -96,7 +95,6 @@ struct sdw_cdns_dai_runtime { struct sdw_bus *bus; enum sdw_stream_type stream_type; int link_id; - struct snd_pcm_hw_params *hw_params; bool suspended; bool paused; int direction; diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 046c67a2a39b..238acf5c97a9 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -725,7 +725,6 @@ static int intel_hw_params(struct snd_pcm_substream *substream, dai_runtime->paused = false; dai_runtime->suspended = false; dai_runtime->pdi = pdi; - dai_runtime->hw_params = params; /* Inform DSP about PDI stream number */ ret = intel_params_stream(sdw, substream->stream, dai, params, @@ -778,6 +777,11 @@ static int intel_prepare(struct snd_pcm_substream *substream, } if (dai_runtime->suspended) { + struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); + struct snd_pcm_hw_params *hw_params; + + hw_params = &rtd->dpcm[substream->stream].hw_params; + dai_runtime->suspended = false; /* @@ -789,7 +793,7 @@ static int intel_prepare(struct snd_pcm_substream *substream, */ /* configure stream */ - ch = params_channels(dai_runtime->hw_params); + ch = params_channels(hw_params); if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) dir = SDW_DATA_DIR_RX; else @@ -801,7 +805,7 @@ static int intel_prepare(struct snd_pcm_substream *substream, /* Inform DSP about PDI stream number */ ret = intel_params_stream(sdw, substream->stream, dai, - dai_runtime->hw_params, + hw_params, sdw->instance, dai_runtime->pdi->intel_alh_id); } @@ -840,7 +844,6 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) return ret; } - dai_runtime->hw_params = NULL; dai_runtime->pdi = NULL; return 0; -- GitLab From e9537962519e88969f5f69cd0571eb4f6984403c Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Thu, 6 Apr 2023 14:46:40 +0100 Subject: [PATCH 2693/5631] soundwire: bus: Fix unbalanced pm_runtime_put() causing usage count underflow This reverts commit 443a98e649b4 ("soundwire: bus: use pm_runtime_resume_and_get()") Change calls to pm_runtime_resume_and_get() back to pm_runtime_get_sync(). This fixes a usage count underrun caused by doing a pm_runtime_put() even though pm_runtime_resume_and_get() returned an error. The three affected functions ignore -EACCES error from trying to get pm_runtime, and carry on, including a put at the end of the function. But pm_runtime_resume_and_get() does not increment the usage count if it returns an error. So in the -EACCES case you must not call pm_runtime_put(). The documentation for pm_runtime_get_sync() says: "Consider using pm_runtime_resume_and_get() ... as this is likely to result in cleaner code." In this case I don't think it results in cleaner code because the pm_runtime_put() at the end of the function would have to be conditional on the return value from pm_runtime_resume_and_get() at the top of the function. pm_runtime_get_sync() doesn't have this problem because it always increments the count, so always needs a put. The code can just flow through and do the pm_runtime_put() unconditionally. Signed-off-by: Richard Fitzgerald Reviewed-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230406134640.8582-1-rf@opensource.cirrus.com Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index e157a39a82ce..1ea6a64f8c4a 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -584,9 +584,11 @@ int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) { int ret; - ret = pm_runtime_resume_and_get(&slave->dev); - if (ret < 0 && ret != -EACCES) + ret = pm_runtime_get_sync(&slave->dev); + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_noidle(&slave->dev); return ret; + } ret = sdw_nread_no_pm(slave, addr, count, val); @@ -613,9 +615,11 @@ int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, const u8 *val) { int ret; - ret = pm_runtime_resume_and_get(&slave->dev); - if (ret < 0 && ret != -EACCES) + ret = pm_runtime_get_sync(&slave->dev); + if (ret < 0 && ret != -EACCES) { + pm_runtime_put_noidle(&slave->dev); return ret; + } ret = sdw_nwrite_no_pm(slave, addr, count, val); @@ -1590,9 +1594,10 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) sdw_modify_slave_status(slave, SDW_SLAVE_ALERT); - ret = pm_runtime_resume_and_get(&slave->dev); + ret = pm_runtime_get_sync(&slave->dev); if (ret < 0 && ret != -EACCES) { dev_err(&slave->dev, "Failed to resume device: %d\n", ret); + pm_runtime_put_noidle(&slave->dev); return ret; } -- GitLab From 67572c8dc64412880b81d4bbc2f354dd5eddaa7d Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Thu, 23 Mar 2023 10:52:28 +0800 Subject: [PATCH 2694/5631] soundwire: intel_auxdevice: improve pm_prepare step In the case where multiple peripherals are attached on the same link, it's possible that they are in different pm_runtime states. The device_for_each_child() loop to resume all devices before a system suspend would not work if one peripheral was active and others suspended. pm_runtime_resume() returns 1 in the former case, which is taken as a error. As a result, a pm_runtime suspended device might be skipped if the first device was active. This patch changes the behavior of the helper function to only return zero or a negative error. A Fixes tag is not provided since there are no existing configurations on Intel platforms with different types of devices on the same link. Amplifiers may be used on the same link, but they are used by the same dailink so their pm_runtime state is always matching. This assumption may not be true in the future, so we should improve the behavior and align with AMD. Reported-by: Mukunda,Vijendar Link: https://lore.kernel.org/lkml/4cbbff8a-c596-e9cc-a6cf-6f8b66607505@amd.com/ Signed-off-by: Pierre-Louis Bossart Reviewed-by: Rander Wang Signed-off-by: Bard Liao Link: https://lore.kernel.org/r/20230323025228.1537107-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/intel_auxdevice.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/intel_auxdevice.c b/drivers/soundwire/intel_auxdevice.c index 5021be0f4158..b21e86084f7b 100644 --- a/drivers/soundwire/intel_auxdevice.c +++ b/drivers/soundwire/intel_auxdevice.c @@ -358,10 +358,12 @@ static int intel_resume_child_device(struct device *dev, void *data) } ret = pm_request_resume(dev); - if (ret < 0) + if (ret < 0) { dev_err(dev, "%s: pm_request_resume failed: %d\n", __func__, ret); + return ret; + } - return ret; + return 0; } static int __maybe_unused intel_pm_prepare(struct device *dev) -- GitLab From 588c8a2da99eac937069a4189eba9f375e38e592 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 11 Apr 2023 16:44:38 -0700 Subject: [PATCH 2695/5631] perf vendor events: Update alderlake to v1.20 Update from v1.19 to v1.20 affecting the performance/goldencove events. Adds cmask=1 for ARITH.IDIV_ACTIVE, and updates event descriptions. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230411234440.3313680-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/alderlake/other.json | 3 ++- tools/perf/pmu-events/arch/x86/alderlake/pipeline.json | 4 +++- tools/perf/pmu-events/arch/x86/mapfile.csv | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/other.json b/tools/perf/pmu-events/arch/x86/alderlake/other.json index 329c611d7cf7..1db73e020215 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/other.json @@ -162,10 +162,11 @@ "Unit": "cpu_core" }, { - "BriefDescription": "XQ.FULL_CYCLES", + "BriefDescription": "Cycles the uncore cannot take further requests", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index f848530fbf07..cb5b8611064b 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -31,6 +31,7 @@ }, { "BriefDescription": "This event counts the cycles the integer divider is busy.", + "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", "SampleAfterValue": "1000003", @@ -1079,9 +1080,10 @@ "Unit": "cpu_core" }, { - "BriefDescription": "MISC2_RETIRED.LFENCE", + "BriefDescription": "LFENCE instructions retired", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 97b3ffc284a6..9e7545d09b23 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.19,alderlake,core -GenuineIntel-6-BE,v1.19,alderlaken,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.20,alderlake,core +GenuineIntel-6-BE,v1.20,alderlaken,core GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core GenuineIntel-6-(3D|47),v27,broadwell,core GenuineIntel-6-56,v9,broadwellde,core -- GitLab From f00e589228d1d60a664dc13fef53acbde4a1d941 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 11 Apr 2023 16:44:39 -0700 Subject: [PATCH 2696/5631] perf vendor events: Update icelakex to v1.20 Update from v1.19 to v1.20 affecting the uncore UNC_CHA_CORE_SNP.REMOTE_GTONE event's umask. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230411234440.3313680-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json | 2 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json index 8210e286eec1..134b54da0869 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json @@ -981,7 +981,7 @@ "EventName": "UNC_CHA_CORE_SNP.REMOTE_GTONE", "PerPkg": "1", "PublicDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x22", + "UMask": "0x12", "Unit": "CHA" }, { diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 9e7545d09b23..58faf18474b5 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -13,7 +13,7 @@ GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v27,haswellx,core GenuineIntel-6-(7D|7E|A7),v1.17,icelake,core -GenuineIntel-6-6[AC],v1.19,icelakex,core +GenuineIntel-6-6[AC],v1.20,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v23,ivytown,core GenuineIntel-6-2D,v23,jaketown,core -- GitLab From 79b40a1b182bcca381bb59d0219e1dd681a64981 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2697/5631] perf inject: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index fd2b38458a5d..76723ac314b6 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -1311,10 +1311,10 @@ static void guest_session__exit(struct guest_session *gs) if (gs->tmp_fd >= 0) close(gs->tmp_fd); unlink(gs->tmp_file_name); - free(gs->tmp_file_name); + zfree(&gs->tmp_file_name); } - free(gs->vcpu); - free(gs->perf_data_file); + zfree(&gs->vcpu); + zfree(&gs->perf_data_file); } static void get_tsc_conv(struct perf_tsc_conversion *tc, struct perf_record_time_conv *time_conv) -- GitLab From 49e5d16b6fc003407a33a9961b4bcbb970bd1c76 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Wed, 12 Apr 2023 06:27:33 +0000 Subject: [PATCH 2698/5631] KVM: arm64: vgic: Don't acquire its_lock before config_lock commit f00327731131 ("KVM: arm64: Use config_lock to protect vgic state") was meant to rectify a longstanding lock ordering issue in KVM where the kvm->lock is taken while holding vcpu->mutex. As it so happens, the aforementioned commit introduced yet another locking issue by acquiring the its_lock before acquiring the config lock. This is obviously wrong, especially considering that the lock ordering is well documented in vgic.c. Reshuffle the locks once more to take the config_lock before the its_lock. While at it, sprinkle in the lockdep hinting that has become popular as of late to keep lockdep apprised of our ordering. Cc: stable@vger.kernel.org Fixes: f00327731131 ("KVM: arm64: Use config_lock to protect vgic state") Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230412062733.988229-1-oliver.upton@linux.dev --- arch/arm64/kvm/vgic/vgic-its.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 7713cd06104e..750e51e3779a 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -1958,6 +1958,16 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) mutex_init(&its->its_lock); mutex_init(&its->cmd_lock); + /* Yep, even more trickery for lock ordering... */ +#ifdef CONFIG_LOCKDEP + mutex_lock(&dev->kvm->arch.config_lock); + mutex_lock(&its->cmd_lock); + mutex_lock(&its->its_lock); + mutex_unlock(&its->its_lock); + mutex_unlock(&its->cmd_lock); + mutex_unlock(&dev->kvm->arch.config_lock); +#endif + its->vgic_its_base = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&its->device_list); @@ -2752,15 +2762,14 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) return 0; mutex_lock(&kvm->lock); - mutex_lock(&its->its_lock); if (!lock_all_vcpus(kvm)) { - mutex_unlock(&its->its_lock); mutex_unlock(&kvm->lock); return -EBUSY; } mutex_lock(&kvm->arch.config_lock); + mutex_lock(&its->its_lock); switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: @@ -2774,9 +2783,9 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) break; } + mutex_unlock(&its->its_lock); mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); - mutex_unlock(&its->its_lock); mutex_unlock(&kvm->lock); return ret; } -- GitLab From 789eae7f203edc1301d7122ad9b3046e7c56937c Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2699/5631] perf daemon: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-daemon.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index 7036ec92d47d..34cbe3e959aa 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -193,7 +193,7 @@ static int session_config(struct daemon *daemon, const char *var, const char *va if (!same) { if (session->run) { - free(session->run); + zfree(&session->run); pr_debug("reconfig: session %s is changed\n", name); } @@ -924,9 +924,9 @@ static void daemon__signal(struct daemon *daemon, int sig) static void daemon_session__delete(struct daemon_session *session) { - free(session->base); - free(session->name); - free(session->run); + zfree(&session->base); + zfree(&session->name); + zfree(&session->run); free(session); } @@ -975,9 +975,9 @@ static void daemon__exit(struct daemon *daemon) list_for_each_entry_safe(session, h, &daemon->sessions, list) daemon_session__remove(session); - free(daemon->config_real); - free(daemon->config_base); - free(daemon->base); + zfree(&daemon->config_real); + zfree(&daemon->config_base); + zfree(&daemon->base); } static int daemon__reconfig(struct daemon *daemon) -- GitLab From 9997d5dd177c52017fa0541bf236a4232c8148e6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2700/5631] perf trace: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-trace.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 72ef0bebb06b..8ee3a45c3c54 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2288,7 +2288,7 @@ static void syscall__exit(struct syscall *sc) if (!sc) return; - free(sc->arg_fmt); + zfree(&sc->arg_fmt); } static int trace__sys_enter(struct trace *trace, struct evsel *evsel, @@ -3124,7 +3124,7 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist) if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls")) continue; - free(et->fmt); + zfree(&et->fmt); free(et); } } @@ -4670,11 +4670,11 @@ static void trace__exit(struct trace *trace) int i; strlist__delete(trace->ev_qualifier); - free(trace->ev_qualifier_ids.entries); + zfree(&trace->ev_qualifier_ids.entries); if (trace->syscalls.table) { for (i = 0; i <= trace->sctbl->syscalls.max_id; i++) syscall__exit(&trace->syscalls.table[i]); - free(trace->syscalls.table); + zfree(&trace->syscalls.table); } syscalltbl__delete(trace->sctbl); zfree(&trace->perfconfig_events); -- GitLab From 190de75481439205f3a9362bd0511fd48ad1a718 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2701/5631] perf c2c: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-c2c.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c index 6c12f0865860..08455e26b606 100644 --- a/tools/perf/builtin-c2c.c +++ b/tools/perf/builtin-c2c.c @@ -165,8 +165,8 @@ static void *c2c_he_zalloc(size_t size) return &c2c_he->he; out_free: - free(c2c_he->nodeset); - free(c2c_he->cpuset); + zfree(&c2c_he->nodeset); + zfree(&c2c_he->cpuset); free(c2c_he); return NULL; } @@ -178,13 +178,13 @@ static void c2c_he_free(void *he) c2c_he = container_of(he, struct c2c_hist_entry, he); if (c2c_he->hists) { hists__delete_entries(&c2c_he->hists->hists); - free(c2c_he->hists); + zfree(&c2c_he->hists); } - free(c2c_he->cpuset); - free(c2c_he->nodeset); - free(c2c_he->nodestr); - free(c2c_he->node_stats); + zfree(&c2c_he->cpuset); + zfree(&c2c_he->nodeset); + zfree(&c2c_he->nodestr); + zfree(&c2c_he->node_stats); free(c2c_he); } -- GitLab From b20c63084eb2c591006109aefbdeb3cad7a57d23 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2702/5631] perf list: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-list.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index 29f09cefed88..1f5dbd5f0ba4 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -127,7 +127,7 @@ static void default_print_event(void *ps, const char *pmu_name, const char *topi if (strcmp(print_state->last_topic, topic ?: "")) { if (topic) printf("\n%s:\n", topic); - free(print_state->last_topic); + zfree(&print_state->last_topic); print_state->last_topic = strdup(topic ?: ""); } @@ -197,7 +197,7 @@ static void default_print_metric(void *ps, else printf("%s\n", group); } - free(print_state->last_metricgroups); + zfree(&print_state->last_metricgroups); print_state->last_metricgroups = strdup(group ?: ""); } if (!print_state->metrics) -- GitLab From d729163d0641d8b4c50fdca1b2b9d5d24d9d376d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2703/5631] perf symbol: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index c55981116f68..35724f6a84fa 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -396,7 +396,7 @@ static bool get_ifunc_name(Elf *elf, struct dso *dso, GElf_Ehdr *ehdr, static void exit_rel(struct rel_info *ri) { - free(ri->sorted); + zfree(&ri->sorted); } static bool get_plt_sizes(struct dso *dso, GElf_Ehdr *ehdr, GElf_Shdr *shdr_plt, @@ -460,7 +460,7 @@ struct rela_dyn_info { static void exit_rela_dyn(struct rela_dyn_info *di) { - free(di->sorted); + zfree(&di->sorted); } static int cmp_offset(const void *a, const void *b) -- GitLab From 313b4c1ccdb273f6733e8c44948f8c7141f592a4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2704/5631] perf x86 iostat: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/iostat.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c index 7eb0a7b00b95..df7b5dfcc26a 100644 --- a/tools/perf/arch/x86/util/iostat.c +++ b/tools/perf/arch/x86/util/iostat.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -100,8 +101,8 @@ static void iio_root_ports_list_free(struct iio_root_ports_list *list) if (list) { for (idx = 0; idx < list->nr_entries; idx++) - free(list->rps[idx]); - free(list->rps); + zfree(&list->rps[idx]); + zfree(&list->rps); free(list); } } @@ -390,7 +391,7 @@ void iostat_release(struct evlist *evlist) evlist__for_each_entry(evlist, evsel) { if (rp != evsel->priv) { rp = evsel->priv; - free(evsel->priv); + zfree(&evsel->priv); } } } -- GitLab From 9fbde6c8002bce61acd0c2187cc41c43a7c99968 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2705/5631] perf env: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/env.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 5b8cf6a421a4..ebf2e801c275 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -149,7 +149,7 @@ static void perf_env__purge_bpf(struct perf_env *env) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next = rb_next(&node->rb_node); rb_erase(&node->rb_node, root); - free(node->info_linear); + zfree(&node->info_linear); free(node); } -- GitLab From 7fb6f7b0af6742601e0efe315c78c26e88d30ff1 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 5 Apr 2023 20:51:27 +0200 Subject: [PATCH 2706/5631] MIPS: Remove deprecated CONFIG_MIPS_CMP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 5cac93b35c14 ("MIPS: Deprecate CONFIG_MIPS_CMP") deprecated CONFIG_MIPS_CMP and after 9 years it's time to remove it. Signed-off-by: Thomas Bogendoerfer Reviewed-by: Jiaxun Yang Acked-by: Marc Zyngier Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 34 +---- arch/mips/include/asm/rtlx.h | 1 - arch/mips/include/asm/smp-ops.h | 16 --- arch/mips/include/asm/vpe.h | 4 - arch/mips/kernel/Makefile | 3 - arch/mips/kernel/rtlx-cmp.c | 122 ------------------ arch/mips/kernel/smp-cmp.c | 148 ---------------------- arch/mips/kernel/vpe-cmp.c | 180 --------------------------- arch/mips/kernel/vpe.c | 2 +- arch/mips/mti-malta/Makefile | 2 - arch/mips/mti-malta/malta-amon.c | 88 ------------- arch/mips/mti-malta/malta-init.c | 2 - arch/mips/mti-malta/malta-platform.c | 2 - arch/mips/ralink/mt7621.c | 2 - drivers/irqchip/irq-mips-gic.c | 26 ---- 15 files changed, 3 insertions(+), 629 deletions(-) delete mode 100644 arch/mips/kernel/rtlx-cmp.c delete mode 100644 arch/mips/kernel/smp-cmp.c delete mode 100644 arch/mips/kernel/vpe-cmp.c delete mode 100644 arch/mips/mti-malta/malta-amon.c diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index a975f140ae82..61fca312a2c5 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -568,7 +568,6 @@ config MIPS_MALTA select SYS_SUPPORTS_LITTLE_ENDIAN select SYS_SUPPORTS_MICROMIPS select SYS_SUPPORTS_MIPS16 - select SYS_SUPPORTS_MIPS_CMP select SYS_SUPPORTS_MIPS_CPS select SYS_SUPPORTS_MULTITHREADING select SYS_SUPPORTS_RELOCATABLE @@ -2270,15 +2269,10 @@ config MIPS_VPE_LOADER Includes a loader for loading an elf relocatable object onto another VPE and running it. -config MIPS_VPE_LOADER_CMP - bool - default "y" - depends on MIPS_VPE_LOADER && MIPS_CMP - config MIPS_VPE_LOADER_MT bool default "y" - depends on MIPS_VPE_LOADER && !MIPS_CMP + depends on MIPS_VPE_LOADER config MIPS_VPE_LOADER_TOM bool "Load VPE program into memory hidden from linux" @@ -2294,31 +2288,10 @@ config MIPS_VPE_APSP_API bool "Enable support for AP/SP API (RTLX)" depends on MIPS_VPE_LOADER -config MIPS_VPE_APSP_API_CMP - bool - default "y" - depends on MIPS_VPE_APSP_API && MIPS_CMP - config MIPS_VPE_APSP_API_MT bool default "y" - depends on MIPS_VPE_APSP_API && !MIPS_CMP - -config MIPS_CMP - bool "MIPS CMP framework support (DEPRECATED)" - depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select SMP - select SYNC_R4K - select SYS_SUPPORTS_SMP - select WEAK_ORDERING - default n - help - Select this if you are using a bootloader which implements the "CMP - framework" protocol (ie. YAMON) and want your kernel to make use of - its ability to start secondary CPUs. - - Unless you have a specific need, you should use CONFIG_MIPS_CPS - instead of this. + depends on MIPS_VPE_APSP_API config MIPS_CPS bool "MIPS Coherent Processing System support" @@ -2774,9 +2747,6 @@ config HOTPLUG_CPU config SMP_UP bool -config SYS_SUPPORTS_MIPS_CMP - bool - config SYS_SUPPORTS_MIPS_CPS bool diff --git a/arch/mips/include/asm/rtlx.h b/arch/mips/include/asm/rtlx.h index c1020654876e..a72785b4bbf4 100644 --- a/arch/mips/include/asm/rtlx.h +++ b/arch/mips/include/asm/rtlx.h @@ -81,7 +81,6 @@ struct rtlx_channel { extern struct rtlx_info { unsigned long id; enum rtlx_state state; - int ap_int_pending; /* Status of 0 or 1 for CONFIG_MIPS_CMP only */ struct rtlx_channel channel[RTLX_CHANNELS]; } *rtlx; diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h index 864aea803984..0145bbfb5efb 100644 --- a/arch/mips/include/asm/smp-ops.h +++ b/arch/mips/include/asm/smp-ops.h @@ -80,22 +80,6 @@ static inline int register_up_smp_ops(void) #endif } -static inline int register_cmp_smp_ops(void) -{ -#ifdef CONFIG_MIPS_CMP - extern const struct plat_smp_ops cmp_smp_ops; - - if (!mips_cm_present()) - return -ENODEV; - - register_smp_ops(&cmp_smp_ops); - - return 0; -#else - return -ENODEV; -#endif -} - static inline int register_vsmp_smp_ops(void) { #ifdef CONFIG_MIPS_MT_SMP diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h index ef7e07829607..61fd4d0aeda4 100644 --- a/arch/mips/include/asm/vpe.h +++ b/arch/mips/include/asm/vpe.h @@ -29,12 +29,8 @@ static inline int aprp_cpu_index(void) { -#ifdef CONFIG_MIPS_CMP - return setup_max_cpus; -#else extern int tclimit; return tclimit; -#endif } enum vpe_state { diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile index 5d1addac5e28..853a43ee4b44 100644 --- a/arch/mips/kernel/Makefile +++ b/arch/mips/kernel/Makefile @@ -58,16 +58,13 @@ obj-$(CONFIG_CPU_BMIPS) += smp-bmips.o bmips_vec.o bmips_5xxx_init.o obj-$(CONFIG_MIPS_MT) += mips-mt.o obj-$(CONFIG_MIPS_MT_FPAFF) += mips-mt-fpaff.o obj-$(CONFIG_MIPS_MT_SMP) += smp-mt.o -obj-$(CONFIG_MIPS_CMP) += smp-cmp.o obj-$(CONFIG_MIPS_CPS) += smp-cps.o cps-vec.o obj-$(CONFIG_MIPS_CPS_NS16550) += cps-vec-ns16550.o obj-$(CONFIG_MIPS_SPRAM) += spram.o obj-$(CONFIG_MIPS_VPE_LOADER) += vpe.o -obj-$(CONFIG_MIPS_VPE_LOADER_CMP) += vpe-cmp.o obj-$(CONFIG_MIPS_VPE_LOADER_MT) += vpe-mt.o obj-$(CONFIG_MIPS_VPE_APSP_API) += rtlx.o -obj-$(CONFIG_MIPS_VPE_APSP_API_CMP) += rtlx-cmp.o obj-$(CONFIG_MIPS_VPE_APSP_API_MT) += rtlx-mt.o obj-$(CONFIG_MIPS_MSC) += irq-msc01.o diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c deleted file mode 100644 index d26dcc4b46e7..000000000000 --- a/arch/mips/kernel/rtlx-cmp.c +++ /dev/null @@ -1,122 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2005 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - */ -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -static int major; - -static void rtlx_interrupt(void) -{ - int i; - struct rtlx_info *info; - struct rtlx_info **p = vpe_get_shared(aprp_cpu_index()); - - if (p == NULL || *p == NULL) - return; - - info = *p; - - if (info->ap_int_pending == 1 && smp_processor_id() == 0) { - for (i = 0; i < RTLX_CHANNELS; i++) { - wake_up(&channel_wqs[i].lx_queue); - wake_up(&channel_wqs[i].rt_queue); - } - info->ap_int_pending = 0; - } -} - -void _interrupt_sp(void) -{ - smp_send_reschedule(aprp_cpu_index()); -} - -int __init rtlx_module_init(void) -{ - struct device *dev; - int i, err; - - if (!cpu_has_mipsmt) { - pr_warn("VPE loader: not a MIPS MT capable processor\n"); - return -ENODEV; - } - - if (num_possible_cpus() - aprp_cpu_index() < 1) { - pr_warn("No TCs reserved for AP/SP, not initializing RTLX.\n" - "Pass maxcpus= argument as kernel argument\n"); - - return -ENODEV; - } - - major = register_chrdev(0, RTLX_MODULE_NAME, &rtlx_fops); - if (major < 0) { - pr_err("rtlx_module_init: unable to register device\n"); - return major; - } - - /* initialise the wait queues */ - for (i = 0; i < RTLX_CHANNELS; i++) { - init_waitqueue_head(&channel_wqs[i].rt_queue); - init_waitqueue_head(&channel_wqs[i].lx_queue); - atomic_set(&channel_wqs[i].in_open, 0); - mutex_init(&channel_wqs[i].mutex); - - dev = device_create(mt_class, NULL, MKDEV(major, i), NULL, - "%s%d", RTLX_MODULE_NAME, i); - if (IS_ERR(dev)) { - while (i--) - device_destroy(mt_class, MKDEV(major, i)); - - err = PTR_ERR(dev); - goto out_chrdev; - } - } - - /* set up notifiers */ - rtlx_notify.start = rtlx_starting; - rtlx_notify.stop = rtlx_stopping; - vpe_notify(aprp_cpu_index(), &rtlx_notify); - - if (cpu_has_vint) { - aprp_hook = rtlx_interrupt; - } else { - pr_err("APRP RTLX init on non-vectored-interrupt processor\n"); - err = -ENODEV; - goto out_class; - } - - return 0; - -out_class: - for (i = 0; i < RTLX_CHANNELS; i++) - device_destroy(mt_class, MKDEV(major, i)); -out_chrdev: - unregister_chrdev(major, RTLX_MODULE_NAME); - - return err; -} - -void __exit rtlx_module_exit(void) -{ - int i; - - for (i = 0; i < RTLX_CHANNELS; i++) - device_destroy(mt_class, MKDEV(major, i)); - - unregister_chrdev(major, RTLX_MODULE_NAME); - - aprp_hook = NULL; -} diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c deleted file mode 100644 index 76f5824cdb00..000000000000 --- a/arch/mips/kernel/smp-cmp.c +++ /dev/null @@ -1,148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * - * Copyright (C) 2007 MIPS Technologies, Inc. - * Chris Dearman (chris@mips.com) - */ - -#undef DEBUG - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static void cmp_init_secondary(void) -{ - struct cpuinfo_mips *c __maybe_unused = ¤t_cpu_data; - - /* Assume GIC is present */ - change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 | - STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7); - - /* Enable per-cpu interrupts: platform specific */ - -#ifdef CONFIG_MIPS_MT_SMP - if (cpu_has_mipsmt) - cpu_set_vpe_id(c, (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) & - TCBIND_CURVPE); -#endif -} - -static void cmp_smp_finish(void) -{ - pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__); - - /* CDFIXME: remove this? */ - write_c0_compare(read_c0_count() + (8 * mips_hpt_frequency / HZ)); - -#ifdef CONFIG_MIPS_MT_FPAFF - /* If we have an FPU, enroll ourselves in the FPU-full mask */ - if (cpu_has_fpu) - cpumask_set_cpu(smp_processor_id(), &mt_fpu_cpumask); -#endif /* CONFIG_MIPS_MT_FPAFF */ - - local_irq_enable(); -} - -/* - * Setup the PC, SP, and GP of a secondary processor and start it running - * smp_bootstrap is the place to resume from - * __KSTK_TOS(idle) is apparently the stack pointer - * (unsigned long)idle->thread_info the gp - */ -static int cmp_boot_secondary(int cpu, struct task_struct *idle) -{ - struct thread_info *gp = task_thread_info(idle); - unsigned long sp = __KSTK_TOS(idle); - unsigned long pc = (unsigned long)&smp_bootstrap; - unsigned long a0 = 0; - - pr_debug("SMPCMP: CPU%d: %s cpu %d\n", smp_processor_id(), - __func__, cpu); - -#if 0 - /* Needed? */ - flush_icache_range((unsigned long)gp, - (unsigned long)(gp + sizeof(struct thread_info))); -#endif - - amon_cpu_start(cpu, pc, sp, (unsigned long)gp, a0); - return 0; -} - -/* - * Common setup before any secondaries are started - */ -void __init cmp_smp_setup(void) -{ - int i; - int ncpu = 0; - - pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__); - -#ifdef CONFIG_MIPS_MT_FPAFF - /* If we have an FPU, enroll ourselves in the FPU-full mask */ - if (cpu_has_fpu) - cpumask_set_cpu(0, &mt_fpu_cpumask); -#endif /* CONFIG_MIPS_MT_FPAFF */ - - for (i = 1; i < NR_CPUS; i++) { - if (amon_cpu_avail(i)) { - set_cpu_possible(i, true); - __cpu_number_map[i] = ++ncpu; - __cpu_logical_map[ncpu] = i; - } - } - - if (cpu_has_mipsmt) { - unsigned int nvpe = 1; -#ifdef CONFIG_MIPS_MT_SMP - unsigned int mvpconf0 = read_c0_mvpconf0(); - - nvpe = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1; -#endif - smp_num_siblings = nvpe; - } - pr_info("Detected %i available secondary CPU(s)\n", ncpu); -} - -void __init cmp_prepare_cpus(unsigned int max_cpus) -{ - pr_debug("SMPCMP: CPU%d: %s max_cpus=%d\n", - smp_processor_id(), __func__, max_cpus); - -#ifdef CONFIG_MIPS_MT - /* - * FIXME: some of these options are per-system, some per-core and - * some per-cpu - */ - mips_mt_set_cpuoptions(); -#endif - -} - -const struct plat_smp_ops cmp_smp_ops = { - .send_ipi_single = mips_smp_send_ipi_single, - .send_ipi_mask = mips_smp_send_ipi_mask, - .init_secondary = cmp_init_secondary, - .smp_finish = cmp_smp_finish, - .boot_secondary = cmp_boot_secondary, - .smp_setup = cmp_smp_setup, - .prepare_cpus = cmp_prepare_cpus, -}; diff --git a/arch/mips/kernel/vpe-cmp.c b/arch/mips/kernel/vpe-cmp.c deleted file mode 100644 index 92140edb3ce3..000000000000 --- a/arch/mips/kernel/vpe-cmp.c +++ /dev/null @@ -1,180 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2004, 2005 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - */ -#include -#include -#include -#include -#include - -#include - -static int major; - -void cleanup_tc(struct tc *tc) -{ - -} - -static ssize_t store_kill(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - struct vpe_notifications *notifier; - - list_for_each_entry(notifier, &vpe->notify, list) - notifier->stop(aprp_cpu_index()); - - release_progmem(vpe->load_addr); - vpe->state = VPE_STATE_UNUSED; - - return len; -} -static DEVICE_ATTR(kill, S_IWUSR, NULL, store_kill); - -static ssize_t ntcs_show(struct device *cd, struct device_attribute *attr, - char *buf) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - - return sprintf(buf, "%d\n", vpe->ntcs); -} - -static ssize_t ntcs_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct vpe *vpe = get_vpe(aprp_cpu_index()); - unsigned long new; - int ret; - - ret = kstrtoul(buf, 0, &new); - if (ret < 0) - return ret; - - /* APRP can only reserve one TC in a VPE and no more. */ - if (new != 1) - return -EINVAL; - - vpe->ntcs = new; - - return len; -} -static DEVICE_ATTR_RW(ntcs); - -static struct attribute *vpe_attrs[] = { - &dev_attr_kill.attr, - &dev_attr_ntcs.attr, - NULL, -}; -ATTRIBUTE_GROUPS(vpe); - -static void vpe_device_release(struct device *cd) -{ -} - -static struct class vpe_class = { - .name = "vpe", - .owner = THIS_MODULE, - .dev_release = vpe_device_release, - .dev_groups = vpe_groups, -}; - -static struct device vpe_device; - -int __init vpe_module_init(void) -{ - struct vpe *v = NULL; - struct tc *t; - int err; - - if (!cpu_has_mipsmt) { - pr_warn("VPE loader: not a MIPS MT capable processor\n"); - return -ENODEV; - } - - if (num_possible_cpus() - aprp_cpu_index() < 1) { - pr_warn("No VPEs reserved for AP/SP, not initialize VPE loader\n" - "Pass maxcpus= argument as kernel argument\n"); - return -ENODEV; - } - - major = register_chrdev(0, VPE_MODULE_NAME, &vpe_fops); - if (major < 0) { - pr_warn("VPE loader: unable to register character device\n"); - return major; - } - - err = class_register(&vpe_class); - if (err) { - pr_err("vpe_class registration failed\n"); - goto out_chrdev; - } - - device_initialize(&vpe_device); - vpe_device.class = &vpe_class; - vpe_device.parent = NULL; - dev_set_name(&vpe_device, "vpe_sp"); - vpe_device.devt = MKDEV(major, VPE_MODULE_MINOR); - err = device_add(&vpe_device); - if (err) { - pr_err("Adding vpe_device failed\n"); - goto out_class; - } - - t = alloc_tc(aprp_cpu_index()); - if (!t) { - pr_warn("VPE: unable to allocate TC\n"); - err = -ENOMEM; - goto out_dev; - } - - /* VPE */ - v = alloc_vpe(aprp_cpu_index()); - if (v == NULL) { - pr_warn("VPE: unable to allocate VPE\n"); - kfree(t); - err = -ENOMEM; - goto out_dev; - } - - v->ntcs = 1; - - /* add the tc to the list of this vpe's tc's. */ - list_add(&t->tc, &v->tc); - - /* TC */ - t->pvpe = v; /* set the parent vpe */ - - return 0; - -out_dev: - device_del(&vpe_device); - -out_class: - put_device(&vpe_device); - class_unregister(&vpe_class); - -out_chrdev: - unregister_chrdev(major, VPE_MODULE_NAME); - - return err; -} - -void __exit vpe_module_exit(void) -{ - struct vpe *v, *n; - - device_unregister(&vpe_device); - class_unregister(&vpe_class); - unregister_chrdev(major, VPE_MODULE_NAME); - - /* No locking needed here */ - list_for_each_entry_safe(v, n, &vpecontrol.vpe_list, list) - if (v->state != VPE_STATE_UNUSED) - release_vpe(v); -} diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 13294972707b..343d2597ed76 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -795,7 +795,7 @@ static int vpe_open(struct inode *inode, struct file *filp) static int vpe_release(struct inode *inode, struct file *filp) { -#if defined(CONFIG_MIPS_VPE_LOADER_MT) || defined(CONFIG_MIPS_VPE_LOADER_CMP) +#ifdef CONFIG_MIPS_VPE_LOADER_MT struct vpe *v; Elf_Ehdr *hdr; int ret = 0; diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile index 13bbd12bfa65..bb2c706e11b0 100644 --- a/arch/mips/mti-malta/Makefile +++ b/arch/mips/mti-malta/Makefile @@ -14,6 +14,4 @@ obj-y += malta-platform.o obj-y += malta-setup.o obj-y += malta-time.o -obj-$(CONFIG_MIPS_CMP) += malta-amon.o - CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c deleted file mode 100644 index 84ac523b0ce0..000000000000 --- a/arch/mips/mti-malta/malta-amon.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2007 MIPS Technologies, Inc. All rights reserved. - * Copyright (C) 2013 Imagination Technologies Ltd. - * - * Arbitrary Monitor Interface - */ -#include -#include - -#include -#include -#include -#include - -int amon_cpu_avail(int cpu) -{ - struct cpulaunch *launch = (struct cpulaunch *)CKSEG0ADDR(CPULAUNCH); - - if (cpu < 0 || cpu >= NCPULAUNCH) { - pr_debug("avail: cpu%d is out of range\n", cpu); - return 0; - } - - launch += cpu; - if (!(launch->flags & LAUNCH_FREADY)) { - pr_debug("avail: cpu%d is not ready\n", cpu); - return 0; - } - if (launch->flags & (LAUNCH_FGO|LAUNCH_FGONE)) { - pr_debug("avail: too late.. cpu%d is already gone\n", cpu); - return 0; - } - - return 1; -} - -int amon_cpu_start(int cpu, - unsigned long pc, unsigned long sp, - unsigned long gp, unsigned long a0) -{ - volatile struct cpulaunch *launch = - (struct cpulaunch *)CKSEG0ADDR(CPULAUNCH); - - if (!amon_cpu_avail(cpu)) - return -1; - if (cpu == smp_processor_id()) { - pr_debug("launch: I am cpu%d!\n", cpu); - return -1; - } - launch += cpu; - - pr_debug("launch: starting cpu%d\n", cpu); - - launch->pc = pc; - launch->gp = gp; - launch->sp = sp; - launch->a0 = a0; - - smp_wmb(); /* Target must see parameters before go */ - launch->flags |= LAUNCH_FGO; - smp_wmb(); /* Target must see go before we poll */ - - while ((launch->flags & LAUNCH_FGONE) == 0) - ; - smp_rmb(); /* Target will be updating flags soon */ - pr_debug("launch: cpu%d gone!\n", cpu); - - return 0; -} - -#ifdef CONFIG_MIPS_VPE_LOADER_CMP -int vpe_run(struct vpe *v) -{ - struct vpe_notifications *n; - - if (amon_cpu_start(aprp_cpu_index(), v->__start, 0, 0, 0) < 0) - return -1; - - list_for_each_entry(n, &v->notify, list) - n->start(VPE_MODULE_MINOR); - - return 0; -} -#endif diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c index b03cac5fdc02..000d6d50520a 100644 --- a/arch/mips/mti-malta/malta-init.c +++ b/arch/mips/mti-malta/malta-init.c @@ -289,8 +289,6 @@ void __init prom_init(void) if (!register_cps_smp_ops()) return; - if (!register_cmp_smp_ops()) - return; if (!register_vsmp_smp_ops()) return; register_up_smp_ops(); diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c index 4ffbcc58c6f6..6961a23aefe9 100644 --- a/arch/mips/mti-malta/malta-platform.c +++ b/arch/mips/mti-malta/malta-platform.c @@ -43,7 +43,6 @@ static struct plat_serial8250_port uart8250_data[] = { SMC_PORT(0x3F8, 4), SMC_PORT(0x2F8, 3), -#ifndef CONFIG_MIPS_CMP { .mapbase = 0x1f000900, /* The CBUS UART */ .irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB2, @@ -53,7 +52,6 @@ static struct plat_serial8250_port uart8250_data[] = { .flags = CBUS_UART_FLAGS, .regshift = 3, }, -#endif { }, }; diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index bbf5811afbf2..c3fbab50b95c 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -217,8 +217,6 @@ void __init prom_soc_init(struct ralink_soc_info *soc_info) if (!register_cps_smp_ops()) return; - if (!register_cmp_smp_ops()) - return; if (!register_vsmp_smp_ops()) return; } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 1a6a7a672ad7..046c355e120b 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -54,7 +54,6 @@ static DEFINE_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; -static unsigned int timer_cpu_pin; static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller; #ifdef CONFIG_GENERIC_IRQ_IPI @@ -499,9 +498,6 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, */ switch (intr) { case GIC_LOCAL_INT_TIMER: - /* CONFIG_MIPS_CMP workaround (see __gic_init) */ - map = GIC_MAP_PIN_MAP_TO_PIN | timer_cpu_pin; - fallthrough; case GIC_LOCAL_INT_PERFCTR: case GIC_LOCAL_INT_FDC: /* @@ -795,34 +791,12 @@ static int __init gic_of_init(struct device_node *node, if (cpu_has_veic) { /* Always use vector 1 in EIC mode */ gic_cpu_pin = 0; - timer_cpu_pin = gic_cpu_pin; set_vi_handler(gic_cpu_pin + GIC_PIN_TO_VEC_OFFSET, __gic_irq_dispatch); } else { gic_cpu_pin = cpu_vec - GIC_CPU_PIN_OFFSET; irq_set_chained_handler(MIPS_CPU_IRQ_BASE + cpu_vec, gic_irq_dispatch); - /* - * With the CMP implementation of SMP (deprecated), other CPUs - * are started by the bootloader and put into a timer based - * waiting poll loop. We must not re-route those CPU's local - * timer interrupts as the wait instruction will never finish, - * so just handle whatever CPU interrupt it is routed to by - * default. - * - * This workaround should be removed when CMP support is - * dropped. - */ - if (IS_ENABLED(CONFIG_MIPS_CMP) && - gic_local_irq_is_routable(GIC_LOCAL_INT_TIMER)) { - timer_cpu_pin = read_gic_vl_timer_map() & GIC_MAP_PIN_MAP; - irq_set_chained_handler(MIPS_CPU_IRQ_BASE + - GIC_CPU_PIN_OFFSET + - timer_cpu_pin, - gic_irq_dispatch); - } else { - timer_cpu_pin = gic_cpu_pin; - } } gic_irq_domain = irq_domain_add_simple(node, GIC_NUM_LOCAL_INTRS + -- GitLab From efe98a7a39777ce266142159f303fb52c3b817c0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2707/5631] perf pmu: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 91cccfb3c515..01533302d5f9 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -972,8 +972,7 @@ static struct perf_pmu *pmu_lookup(int dirfd, const char *lookup_name) return pmu; err: - if (pmu->name) - free(pmu->name); + zfree(&pmu->name); free(pmu); return NULL; } @@ -1519,7 +1518,7 @@ void perf_pmu__del_formats(struct list_head *formats) list_for_each_entry_safe(fmt, tmp, formats, list) { list_del(&fmt->list); - free(fmt->name); + zfree(&fmt->name); free(fmt); } } @@ -1866,8 +1865,8 @@ static void perf_pmu__del_caps(struct perf_pmu *pmu) list_for_each_entry_safe(caps, tmp, &pmu->caps, list) { list_del(&caps->list); - free(caps->name); - free(caps->value); + zfree(&caps->name); + zfree(&caps->value); free(caps); } } @@ -2089,9 +2088,9 @@ static void perf_pmu__delete(struct perf_pmu *pmu) perf_cpu_map__put(pmu->cpus); - free(pmu->default_config); - free(pmu->name); - free(pmu->alias_name); + zfree(&pmu->default_config); + zfree(&pmu->name); + zfree(&pmu->alias_name); free(pmu); } -- GitLab From cdf13c0918c9b1b233d6db690fc4c06afbc29e57 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2708/5631] perf evsel: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Also remove one NULL test before free(), as it accepts a NULL arg and we get one line shaved not doing it explicitely. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index fe3ce765a4f3..a85a987128aa 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2917,8 +2917,7 @@ bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; - if (evsel->name) - free(evsel->name); + free(evsel->name); evsel->name = new_name; scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying " "to fall back to excluding kernel and hypervisor " @@ -3156,7 +3155,7 @@ void evsel__zero_per_pkg(struct evsel *evsel) if (evsel->per_pkg_mask) { hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt) - free((void *)cur->pkey); + zfree(&cur->pkey); hashmap__clear(evsel->per_pkg_mask); } -- GitLab From a77f8184a07cbe81cdee30582640ed1b412705fc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2709/5631] perf expr: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Also remove one NULL test before free(), as it accepts a NULL arg and we get one line shaved not doing it explicitely. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/expr.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index bb6ddad7e021..f4e52919324e 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -86,8 +86,8 @@ void ids__free(struct hashmap *ids) return; hashmap__for_each_entry(ids, cur, bkt) { - free((void *)cur->pkey); - free((void *)cur->pvalue); + zfree(&cur->pkey); + zfree(&cur->pvalue); } hashmap__free(ids); @@ -311,8 +311,8 @@ void expr__ctx_clear(struct expr_parse_ctx *ctx) size_t bkt; hashmap__for_each_entry(ctx->ids, cur, bkt) { - free((void *)cur->pkey); - free(cur->pvalue); + zfree(&cur->pkey); + zfree(&cur->pvalue); } hashmap__clear(ctx->ids); } @@ -325,10 +325,10 @@ void expr__ctx_free(struct expr_parse_ctx *ctx) if (!ctx) return; - free(ctx->sctx.user_requested_cpu_list); + zfree(&ctx->sctx.user_requested_cpu_list); hashmap__for_each_entry(ctx->ids, cur, bkt) { - free((void *)cur->pkey); - free(cur->pvalue); + zfree(&cur->pkey); + zfree(&cur->pvalue); } hashmap__free(ctx->ids); free(ctx); -- GitLab From 25feb605fe3b2674142d084379e0737a99945aba Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2710/5631] perf parse-events: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Also remove one NULL test before free(), as it accepts a NULL arg and we get one line shaved not doing it explicitely. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index f341995cb04e..d71019dcd614 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2020,7 +2020,7 @@ int perf_pmu__test_parse_init(void) err_free: for (j = 0, tmp = list; j < i; j++, tmp++) - free(tmp->symbol); + zfree(&tmp->symbol); free(list); return -ENOMEM; } -- GitLab From ee1809ed7bc456a72dc8410b475b73021a3a68d5 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 11 Apr 2023 12:14:26 +0100 Subject: [PATCH 2711/5631] MIPS: fw: Allow firmware to pass a empty env fw_getenv will use env entry to determine style of env, however it is legal for firmware to just pass a empty list. Check if first entry exist before running strchr to avoid null pointer dereference. Cc: stable@vger.kernel.org Link: https://github.com/clbr/n64bootloader/issues/5 Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/fw/lib/cmdline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/fw/lib/cmdline.c b/arch/mips/fw/lib/cmdline.c index f24cbb4a39b5..892765b742bb 100644 --- a/arch/mips/fw/lib/cmdline.c +++ b/arch/mips/fw/lib/cmdline.c @@ -53,7 +53,7 @@ char *fw_getenv(char *envname) { char *result = NULL; - if (_fw_envp != NULL) { + if (_fw_envp != NULL && fw_envp(0) != NULL) { /* * Return a pointer to the given environment variable. * YAMON uses "name", "value" pairs, while U-Boot uses -- GitLab From c77ceb2eb03eefd92e6b84a509ecec1db8d97858 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2712/5631] perf annotate: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Also include the missing linux/zalloc.h header directive. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/annotate.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 55f2e3a7577e..e2693a1c28d5 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1881,7 +1882,7 @@ symbol__disassemble_bpf_image(struct symbol *sym, if (dl) annotation_line__add(&dl->al, ¬es->src->source); - free(args->line); + zfree(&args->line); return 0; } -- GitLab From f5748b8c79d1eea924c50487bdb33351f58ef7bb Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 11 Apr 2023 15:17:47 +0800 Subject: [PATCH 2713/5631] MIPS: Use def_bool y for ARCH_SUPPORTS_UPROBES Like all the other archs, use def_bool y for ARCH_SUPPORTS_UPROBES, then no need to select ARCH_SUPPORTS_UPROBES. Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 61fca312a2c5..47944eb5d7e3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -16,7 +16,6 @@ config MIPS select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_KEEP_MEMBLOCK - select ARCH_SUPPORTS_UPROBES select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if 64BIT select ARCH_USE_MEMTEST @@ -1059,7 +1058,7 @@ config FW_CFE bool config ARCH_SUPPORTS_UPROBES - bool + def_bool y config DMA_NONCOHERENT bool -- GitLab From afa624ff96e8e79136a46ddaf6debb030546d7c6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Tue, 11 Apr 2023 15:17:48 +0800 Subject: [PATCH 2714/5631] MIPS: Remove set_swbp() in uprobes.c set_swbp() in arch/mips/kernel/uprobes.c is same with the weak version in kernel/events/uprobes.c, remove it. Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/uprobes.c | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c index 6c063aa188e6..6b630ed4438d 100644 --- a/arch/mips/kernel/uprobes.c +++ b/arch/mips/kernel/uprobes.c @@ -207,24 +207,6 @@ unsigned long arch_uretprobe_hijack_return_addr( return ra; } -/** - * set_swbp - store breakpoint at a given address. - * @auprobe: arch specific probepoint information. - * @mm: the probed process address space. - * @vaddr: the virtual address to insert the opcode. - * - * For mm @mm, store the breakpoint instruction at @vaddr. - * Return 0 (success) or a negative errno. - * - * This version overrides the weak version in kernel/events/uprobes.c. - * It is required to handle MIPS16 and microMIPS. - */ -int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, - unsigned long vaddr) -{ - return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); -} - void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { -- GitLab From 2bfc8134f95852bd8b0190641c2d2b059cb1c8cc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2715/5631] perf evlist: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index df6af38ca22e..2260e27adf44 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -2325,7 +2325,7 @@ int evlist__parse_event_enable_time(struct evlist *evlist, struct record_opts *o close_timerfd: close(eet->timerfd); free_eet_times: - free(eet->times); + zfree(&eet->times); free_eet: free(eet); return err; @@ -2407,7 +2407,7 @@ void event_enable_timer__exit(struct event_enable_timer **ep) { if (!ep || !*ep) return; - free((*ep)->times); + zfree(&(*ep)->times); zfree(ep); } -- GitLab From f0e7c06f2be9673d008e866bff1a97e1823637e9 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 11 Apr 2023 12:12:20 +0100 Subject: [PATCH 2716/5631] MIPS: loongson2ef: Add missing break in cs5536_isa Fixes build error: arch/mips/loongson2ef/common/cs5536/cs5536_isa.c:217:2: error: unannotated fall-through between switch labels [-Werror,-Wimplicit-fallthrough] default: ^ arch/mips/loongson2ef/common/cs5536/cs5536_isa.c:217:2: note: insert 'break;' to avoid fall-through default: ^ break; Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/loongson2ef/common/cs5536/cs5536_isa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c index 5ad38f86ee62..d60dd9992377 100644 --- a/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c +++ b/arch/mips/loongson2ef/common/cs5536/cs5536_isa.c @@ -213,7 +213,7 @@ void pci_isa_write_reg(int reg, u32 value) lo |= 0x00000063; _wrmsr(SB_MSR_REG(SB_ERROR), hi, lo); } - + break; default: /* ALL OTHER PCI CONFIG SPACE HEADER IS NOT IMPLEMENTED. */ break; -- GitLab From e413f9f13f6a8a591af0ac39ef50af02b42a0df8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2717/5631] perf genelf: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/genelf_debug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c index 8786c366566e..aa5dcc56b2ac 100644 --- a/tools/perf/util/genelf_debug.c +++ b/tools/perf/util/genelf_debug.c @@ -11,6 +11,7 @@ * @author Philippe Elie */ #include +#include #include #include #include @@ -90,7 +91,7 @@ buffer_ext_init(struct buffer_ext *be) static void buffer_ext_exit(struct buffer_ext *be) { - free(be->data); + zfree(&be->data); } static inline size_t -- GitLab From 97d0dd1e283a9a11ede495928c9c2a148b47cef4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2718/5631] perf bench inject-buildid: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/inject-buildid.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c index 4561bda0ce6a..49331743c743 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -122,7 +123,7 @@ static void release_dso(void) for (i = 0; i < nr_dsos; i++) { struct bench_dso *dso = &dsos[i]; - free(dso->name); + zfree(&dso->name); } free(dsos); } -- GitLab From 6ca176fa3a23652513a9d593a6742fb896c7c49f Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Tue, 11 Apr 2023 12:12:24 +0100 Subject: [PATCH 2719/5631] MIPS: octeon_switch: Remove duplicated labels EXPORT macro already have labels defined by itself. Remove duplicated labels outside to silent assembler warnings. Signed-off-by: Jiaxun Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/octeon_switch.S | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S index 896080b445c2..9b7c8ab6f08c 100644 --- a/arch/mips/kernel/octeon_switch.S +++ b/arch/mips/kernel/octeon_switch.S @@ -428,7 +428,6 @@ done_restore: jr ra nop .space 30 * 4, 0 -octeon_mult_save_end: EXPORT(octeon_mult_save_end) END(octeon_mult_save) @@ -448,7 +447,6 @@ octeon_mult_save_end: sd k0, PT_MPL+8(sp) /* PT_MPL+8 has MPL1 */ jr ra sd k1, PT_MPL+16(sp) /* PT_MPL+16 has MPL2 */ -octeon_mult_save2_end: EXPORT(octeon_mult_save2_end) END(octeon_mult_save2) @@ -480,7 +478,6 @@ octeon_mult_save2_end: sd $10, PT_MPL+(4*8)(sp) /* store MPL4 */ jr ra sd $11, PT_MPL+(5*8)(sp) /* store MPL5 */ -octeon_mult_save3_end: EXPORT(octeon_mult_save3_end) END(octeon_mult_save3) .set pop @@ -498,7 +495,6 @@ octeon_mult_save3_end: jr ra nop .space 30 * 4, 0 -octeon_mult_restore_end: EXPORT(octeon_mult_restore_end) END(octeon_mult_restore) @@ -517,7 +513,6 @@ octeon_mult_restore_end: mtp1 v0 /* P1 */ jr ra mtp0 v1 /* P0 */ -octeon_mult_restore2_end: EXPORT(octeon_mult_restore2_end) END(octeon_mult_restore2) @@ -548,7 +543,6 @@ octeon_mult_restore2_end: .word 0x714b000b /* mtp2 $10, $11 restore P2 and P5 */ -octeon_mult_restore3_end: EXPORT(octeon_mult_restore3_end) END(octeon_mult_restore3) .set pop -- GitLab From 9ccbc21166ce149c5f7429cad22f9073d3fab0b1 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2720/5631] perf tests api-io: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/api-io.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/api-io.c b/tools/perf/tests/api-io.c index 6aea84ca6673..0ba3d5ccebcf 100644 --- a/tools/perf/tests/api-io.c +++ b/tools/perf/tests/api-io.c @@ -12,6 +12,7 @@ #include "tests.h" #include #include +#include #define TEMPL "/tmp/perf-test-XXXXXX" @@ -79,7 +80,7 @@ static int setup_test(char path[PATH_MAX], const char *contents, static void cleanup_test(char path[PATH_MAX], struct io *io) { - free(io->buf); + zfree(&io->buf); close(io->fd); unlink(path); } -- GitLab From 2e384400549be734795072b1d904880efc0db2f9 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2721/5631] perf arm-spe: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/arm-spe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index d4c234076541..ef497a29e814 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -479,7 +479,7 @@ static void arm_spe_recording_free(struct auxtrace_record *itr) struct arm_spe_recording *sper = container_of(itr, struct arm_spe_recording, itr); - free(sper->wrapped); + zfree(&sper->wrapped); free(sper); } -- GitLab From 11ff9bcd7dfeefa6a9a9fcd4c7775b8066c46a31 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 09:50:08 -0300 Subject: [PATCH 2722/5631] perf metricgroups: Use zfree() to reduce chances of use after free Do defensive programming by using zfree() to initialize freed pointers to NULL, so that eventual use after free result in a NULL pointer deref instead of more subtle behaviour. This file already used zfree() in other places, so this just plugs some leftovers. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 5783f4c2d1ef..4b9a16291b96 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -90,9 +90,9 @@ static void metric_event_delete(struct rblist *rblist __maybe_unused, struct metric_expr *expr, *tmp; list_for_each_entry_safe(expr, tmp, &me->head, nd) { - free((char *)expr->metric_name); - free(expr->metric_refs); - free(expr->metric_events); + zfree(&expr->metric_name); + zfree(&expr->metric_refs); + zfree(&expr->metric_events); free(expr); } @@ -192,9 +192,9 @@ static void metric__free(struct metric *m) if (!m) return; - free(m->metric_refs); + zfree(&m->metric_refs); expr__ctx_free(m->pctx); - free((char *)m->modifier); + zfree(&m->modifier); evlist__delete(m->evlist); free(m); } @@ -617,7 +617,7 @@ static int decode_all_metric_ids(struct evlist *perf_evlist, const char *modifie if (strstr(ev->name, "metric-id=")) { bool has_slash = false; - free(ev->name); + zfree(&ev->name); for (cur = strchr(sb.buf, '@') ; cur; cur = strchr(++cur, '@')) { *cur = '/'; has_slash = true; @@ -1760,7 +1760,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, alloc_size = sizeof(*new_expr->metric_events); new_expr->metric_events = calloc(nr + 1, alloc_size); if (!new_expr->metric_events) { - free(new_expr->metric_refs); + zfree(&new_expr->metric_refs); free(new_expr); return -ENOMEM; } @@ -1770,8 +1770,8 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, evsel = old_expr->metric_events[idx]; evsel = evlist__find_evsel(evlist, evsel->core.idx); if (evsel == NULL) { - free(new_expr->metric_events); - free(new_expr->metric_refs); + zfree(&new_expr->metric_events); + zfree(&new_expr->metric_refs); free(new_expr); return -EINVAL; } -- GitLab From 57f14b5ae1a97537f2abd2828ee7212cada7036e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 10:23:35 -0300 Subject: [PATCH 2723/5631] perf pmu: zfree() expects a pointer to a pointer to zero it after freeing its contents An audit showed just this one problem with zfree(), fix it. Fixes: 9fbc61f832ebf432 ("perf pmu: Add support for PMU capabilities") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 01533302d5f9..561e2616861f 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1852,7 +1852,7 @@ static int perf_pmu__new_caps(struct list_head *list, char *name, char *value) return 0; free_name: - zfree(caps->name); + zfree(&caps->name); free_caps: free(caps); -- GitLab From 20470a68a049de3b118e31ab01474c622934c500 Mon Sep 17 00:00:00 2001 From: Thomas Bogendoerfer Date: Wed, 12 Apr 2023 15:21:38 +0200 Subject: [PATCH 2724/5631] Revert "MIPS: generic: Enable all CPUs supported by virt board in Kconfig" This reverts commit de34007751aaba992373f2d659001a846aeb8811. There are too many build errors, which needs to be sorted out first. Signed-off-by: Thomas Bogendoerfer --- arch/mips/Kconfig | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 47944eb5d7e3..7629e671381b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -152,16 +152,12 @@ config MIPS_GENERIC_KERNEL select PCI_DRIVERS_GENERIC select SMP_UP if SMP select SWAP_IO_SPACE - select SYS_HAS_CPU_CAVIUM_OCTEON - select SYS_HAS_CPU_LOONGSON2E - select SYS_HAS_CPU_LOONGSON2F select SYS_HAS_CPU_MIPS32_R1 select SYS_HAS_CPU_MIPS32_R2 select SYS_HAS_CPU_MIPS32_R6 select SYS_HAS_CPU_MIPS64_R1 select SYS_HAS_CPU_MIPS64_R2 select SYS_HAS_CPU_MIPS64_R6 - select SYS_HAS_CPU_R4X00 select SYS_SUPPORTS_32BIT_KERNEL select SYS_SUPPORTS_64BIT_KERNEL select SYS_SUPPORTS_BIG_ENDIAN -- GitLab From ed4da0d3de1e1781f8fbdc9cf1028b39cc658c7f Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 7 Apr 2023 10:21:30 +0800 Subject: [PATCH 2725/5631] tools headers: Remove s390 ptrace.h in check-headers.sh After commit 1f265d2aea0dff1f ("selftests/bpf: Remove not used headers"), tools/arch/s390/include/uapi/asm/ptrace.h has been removed, so remove it in check-headers.sh too, otherwise we can see the following build warning: diff: tools/arch/s390/include/uapi/asm/ptrace.h: No such file or directory Fixes: 1f265d2aea0dff1f ("selftests/bpf: Remove not used headers") Reported-by: kernel test robot Signed-off-by: Tiezhu Yang Acked-by: Daniel Borkmann Acked-by: Jiri Olsa Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Tiezhu Yang Cc: bpf@vger.kernel.org Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/oe-kbuild-all/202304050029.38NdbQPf-lkp@intel.com/ Link: https://lore.kernel.org/r/1680834090-2322-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/check-headers.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index eacca9a874e2..e4a8b5348678 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -52,7 +52,6 @@ arch/x86/include/uapi/asm/vmx.h arch/powerpc/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm_perf.h -arch/s390/include/uapi/asm/ptrace.h arch/s390/include/uapi/asm/sie.h arch/arm/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h -- GitLab From eab5051788f6111adb88268a784af0c981616579 Mon Sep 17 00:00:00 2001 From: Hangliang Lai Date: Tue, 11 Apr 2023 09:32:24 +0800 Subject: [PATCH 2726/5631] perf top: Expand the range of multithreaded phase In __cmd_top(), perf_set_multithreaded() is used to enable pthread_rwlock, thus down_read() and down_write () are not nops, handling concurrency problems Then 'perf top' uses perf_set_singlethreaded(), switching to the single threaded phase, assuming that no thread concurrency will happen later. However, a use after free problem could occur in the single threaded phase, the concurrent procedure is this: display_thread process_thread -------------- -------------- thread__comm_len -> thread__comm_str -> __thread__comm_str(thread) thread__delete -> comm__free -> comm_str__put -> zfree(&cs->str) -> thread->comm_len = strlen(comm); Since in single thread phase, perf_singlethreaded is true, down_read() and down_write() do nothing to avoid concurrency problems. This patch moves the perf_set_singlethreaded() call to the function tail to expand the multithreaded phase range, making display_thread() and process_thread() concurrency safe. Reviewed-by: Yunfeng Ye Signed-off-by: Hangliang Lai Co-developed-by: Wenyu Liu Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Christian Brauner Cc: Feilong Lin Cc: Hewenliang Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Link: https://lore.kernel.org/r/20230411013224.2079-1-laihangliang1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 3162bad0d17d..5d448c36ed22 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1276,8 +1276,7 @@ static int __cmd_top(struct perf_top *top) top->evlist->core.threads, true, false, top->nr_threads_synthesize); - if (top->nr_threads_synthesize > 1) - perf_set_singlethreaded(); + perf_set_multithreaded(); if (perf_hpp_list.socket) { ret = perf_env__read_cpu_topology_map(&perf_env); @@ -1355,6 +1354,7 @@ static int __cmd_top(struct perf_top *top) out_join_thread: cond_signal(&top->qe.cond); pthread_join(thread_process, NULL); + perf_set_singlethreaded(); return ret; } -- GitLab From 9b8e17813aeccc29c2f9f2e6e68997a6eac2d26d Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 11 Apr 2023 22:26:41 -0700 Subject: [PATCH 2727/5631] sched/core: Make sched_dynamic_mutex static The sched_dynamic_mutex is only used within the file. Make it static. Fixes: e3ff7c609f39 ("livepatch,sched: Add livepatch task switching to cond_resched()") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/oe-kbuild-all/202304062335.tNuUjgsl-lkp@intel.com/ --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b9616f153946..d861db8aa7ab 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8674,7 +8674,7 @@ int sched_dynamic_mode(const char *str) #error "Unsupported PREEMPT_DYNAMIC mechanism" #endif -DEFINE_MUTEX(sched_dynamic_mutex); +static DEFINE_MUTEX(sched_dynamic_mutex); static bool klp_override; static void __sched_dynamic_update(int mode) -- GitLab From 61f02e0ab81e7c9415dc32e36fe45fc380dce2f0 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 4 Apr 2023 12:05:22 -0400 Subject: [PATCH 2728/5631] NFS: Convert the readdir array-of-pages into an array-of-folios This patch only converts the actual array, but doesn't touch the individual nfs_cache_array pages and related functions (that will be done in the next patch). I also adjust the names of the fields in the nfs_readdir_descriptor to say "folio" instead of "page". Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 129 ++++++++++++++++++++++++++------------------------- 1 file changed, 65 insertions(+), 64 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 6fbcbb8d6587..9edb0584c6d1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -154,10 +154,10 @@ struct nfs_cache_array { struct nfs_readdir_descriptor { struct file *file; - struct page *page; + struct folio *folio; struct dir_context *ctx; - pgoff_t page_index; - pgoff_t page_index_max; + pgoff_t folio_index; + pgoff_t folio_index_max; u64 dir_cookie; u64 last_cookie; loff_t current_index; @@ -312,8 +312,8 @@ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array) } static int nfs_readdir_page_array_append(struct page *page, - const struct nfs_entry *entry, - u64 *cookie) + const struct nfs_entry *entry, + u64 *cookie) { struct nfs_cache_array *array; struct nfs_cache_array_entry *cache_entry; @@ -485,7 +485,7 @@ static void nfs_readdir_seek_next_array(struct nfs_cache_array *array, desc->last_cookie = array->last_cookie; desc->current_index += array->size; desc->cache_entry_index = 0; - desc->page_index++; + desc->folio_index++; } else desc->last_cookie = nfs_readdir_array_index_cookie(array); } @@ -494,7 +494,7 @@ static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc) { desc->current_index = 0; desc->last_cookie = 0; - desc->page_index = 0; + desc->folio_index = 0; } static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, @@ -568,7 +568,7 @@ static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc) struct nfs_cache_array *array; int status; - array = kmap_local_page(desc->page); + array = kmap_local_folio(desc->folio, 0); if (desc->dir_cookie == 0) status = nfs_readdir_search_for_pos(array, desc); @@ -819,16 +819,17 @@ static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc, } /* Perform conversion from xdr to cache array */ -static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, - struct nfs_entry *entry, - struct page **xdr_pages, unsigned int buflen, - struct page **arrays, size_t narrays, - u64 change_attr) +static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc, + struct nfs_entry *entry, + struct page **xdr_pages, unsigned int buflen, + struct folio **arrays, size_t narrays, + u64 change_attr) { struct address_space *mapping = desc->file->f_mapping; + struct folio *folio = *arrays; struct xdr_stream stream; + struct page *scratch, *new; struct xdr_buf buf; - struct page *scratch, *new, *page = *arrays; u64 cookie; int status; @@ -844,36 +845,36 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, if (status != 0) break; - status = nfs_readdir_page_array_append(page, entry, &cookie); + status = nfs_readdir_page_array_append(folio_page(folio, 0), entry, &cookie); if (status != -ENOSPC) continue; - if (page->mapping != mapping) { + if (folio->mapping != mapping) { if (!--narrays) break; new = nfs_readdir_page_array_alloc(cookie, GFP_KERNEL); if (!new) break; arrays++; - *arrays = page = new; + *arrays = folio = page_folio(new); } else { new = nfs_readdir_page_get_next(mapping, cookie, change_attr); if (!new) break; - if (page != *arrays) - nfs_readdir_page_unlock_and_put(page); - page = new; + if (folio != *arrays) + nfs_readdir_page_unlock_and_put(folio_page(folio, 0)); + folio = page_folio(new); } - desc->page_index_max++; - status = nfs_readdir_page_array_append(page, entry, &cookie); + desc->folio_index_max++; + status = nfs_readdir_page_array_append(folio_page(folio, 0), entry, &cookie); } while (!status && !entry->eof); switch (status) { case -EBADCOOKIE: if (!entry->eof) break; - nfs_readdir_page_set_eof(page); + nfs_readdir_page_set_eof(folio_page(folio, 0)); fallthrough; case -EAGAIN: status = 0; @@ -886,8 +887,8 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, ; } - if (page != *arrays) - nfs_readdir_page_unlock_and_put(page); + if (folio != *arrays) + nfs_readdir_page_unlock_and_put(folio_page(folio, 0)); put_page(scratch); return status; @@ -927,11 +928,11 @@ static struct page **nfs_readdir_alloc_pages(size_t npages) static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, __be32 *verf_arg, __be32 *verf_res, - struct page **arrays, size_t narrays) + struct folio **arrays, size_t narrays) { u64 change_attr; struct page **pages; - struct page *page = *arrays; + struct folio *folio = *arrays; struct nfs_entry *entry; size_t array_size; struct inode *inode = file_inode(desc->file); @@ -942,7 +943,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; - entry->cookie = nfs_readdir_page_last_cookie(page); + entry->cookie = nfs_readdir_page_last_cookie(folio_page(folio, 0)); entry->fh = nfs_alloc_fhandle(); entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); entry->server = NFS_SERVER(inode); @@ -962,10 +963,10 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, pglen = status; if (pglen != 0) - status = nfs_readdir_page_filler(desc, entry, pages, pglen, - arrays, narrays, change_attr); + status = nfs_readdir_folio_filler(desc, entry, pages, pglen, + arrays, narrays, change_attr); else - nfs_readdir_page_set_eof(page); + nfs_readdir_page_set_eof(folio_page(folio, 0)); desc->buffer_fills++; free_pages: @@ -977,21 +978,21 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, return status; } -static void nfs_readdir_page_put(struct nfs_readdir_descriptor *desc) +static void nfs_readdir_folio_put(struct nfs_readdir_descriptor *desc) { - put_page(desc->page); - desc->page = NULL; + folio_put(desc->folio); + desc->folio = NULL; } static void -nfs_readdir_page_unlock_and_put_cached(struct nfs_readdir_descriptor *desc) +nfs_readdir_folio_unlock_and_put_cached(struct nfs_readdir_descriptor *desc) { - unlock_page(desc->page); - nfs_readdir_page_put(desc); + folio_unlock(desc->folio); + nfs_readdir_folio_put(desc); } -static struct page * -nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc) +static struct folio * +nfs_readdir_folio_get_cached(struct nfs_readdir_descriptor *desc) { struct address_space *mapping = desc->file->f_mapping; u64 change_attr = inode_peek_iversion_raw(mapping->host); @@ -1003,7 +1004,7 @@ nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc) return NULL; if (desc->clear_cache && !nfs_readdir_page_needs_filling(page)) nfs_readdir_page_reinit_array(page, cookie, change_attr); - return page; + return page_folio(page); } /* @@ -1017,21 +1018,21 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) __be32 verf[NFS_DIR_VERIFIER_SIZE]; int res; - desc->page = nfs_readdir_page_get_cached(desc); - if (!desc->page) + desc->folio = nfs_readdir_folio_get_cached(desc); + if (!desc->folio) return -ENOMEM; - if (nfs_readdir_page_needs_filling(desc->page)) { + if (nfs_readdir_page_needs_filling(folio_page(desc->folio, 0))) { /* Grow the dtsize if we had to go back for more pages */ - if (desc->page_index == desc->page_index_max) + if (desc->folio_index == desc->folio_index_max) nfs_grow_dtsize(desc); - desc->page_index_max = desc->page_index; + desc->folio_index_max = desc->folio_index; trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf, desc->last_cookie, - desc->page->index, desc->dtsize); + desc->folio->index, desc->dtsize); res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf, - &desc->page, 1); + &desc->folio, 1); if (res < 0) { - nfs_readdir_page_unlock_and_put_cached(desc); + nfs_readdir_folio_unlock_and_put_cached(desc); trace_nfs_readdir_cache_fill_done(inode, res); if (res == -EBADCOOKIE || res == -ENOTSYNC) { invalidate_inode_pages2(desc->file->f_mapping); @@ -1059,7 +1060,7 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) res = nfs_readdir_search_array(desc); if (res == 0) return 0; - nfs_readdir_page_unlock_and_put_cached(desc); + nfs_readdir_folio_unlock_and_put_cached(desc); return res; } @@ -1087,7 +1088,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, unsigned int i; bool first_emit = !desc->dir_cookie; - array = kmap_local_page(desc->page); + array = kmap_local_folio(desc->folio, 0); for (i = desc->cache_entry_index; i < array->size; i++) { struct nfs_cache_array_entry *ent; @@ -1136,7 +1137,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, */ static int uncached_readdir(struct nfs_readdir_descriptor *desc) { - struct page **arrays; + struct folio **arrays; size_t i, sz = 512; __be32 verf[NFS_DIR_VERIFIER_SIZE]; int status = -ENOMEM; @@ -1147,14 +1148,14 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) arrays = kcalloc(sz, sizeof(*arrays), GFP_KERNEL); if (!arrays) goto out; - arrays[0] = nfs_readdir_page_array_alloc(desc->dir_cookie, GFP_KERNEL); + arrays[0] = page_folio(nfs_readdir_page_array_alloc(desc->dir_cookie, GFP_KERNEL)); if (!arrays[0]) goto out; - desc->page_index = 0; + desc->folio_index = 0; desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; - desc->page_index_max = 0; + desc->folio_index_max = 0; trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie, -1, desc->dtsize); @@ -1166,10 +1167,10 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) } for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { - desc->page = arrays[i]; + desc->folio = arrays[i]; nfs_do_filldir(desc, verf); } - desc->page = NULL; + desc->folio = NULL; /* * Grow the dtsize if we have to go back for more pages, @@ -1179,16 +1180,16 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) if (!desc->eob) nfs_grow_dtsize(desc); else if (desc->buffer_fills == 1 && - i < (desc->page_index_max >> 1)) + i < (desc->folio_index_max >> 1)) nfs_shrink_dtsize(desc); } out_free: for (i = 0; i < sz && arrays[i]; i++) - nfs_readdir_page_array_free(arrays[i]); + nfs_readdir_page_array_free(folio_page(arrays[i], 0)); out: if (!nfs_readdir_use_cookie(desc->file)) nfs_readdir_rewind_search(desc); - desc->page_index_max = -1; + desc->folio_index_max = -1; kfree(arrays); dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; @@ -1240,11 +1241,11 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) goto out; desc->file = file; desc->ctx = ctx; - desc->page_index_max = -1; + desc->folio_index_max = -1; spin_lock(&file->f_lock); desc->dir_cookie = dir_ctx->dir_cookie; - desc->page_index = dir_ctx->page_index; + desc->folio_index = dir_ctx->page_index; desc->last_cookie = dir_ctx->last_cookie; desc->attr_gencount = dir_ctx->attr_gencount; desc->eof = dir_ctx->eof; @@ -1291,8 +1292,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; nfs_do_filldir(desc, nfsi->cookieverf); - nfs_readdir_page_unlock_and_put_cached(desc); - if (desc->page_index == desc->page_index_max) + nfs_readdir_folio_unlock_and_put_cached(desc); + if (desc->folio_index == desc->folio_index_max) desc->clear_cache = force_clear; } while (!desc->eob && !desc->eof); @@ -1300,7 +1301,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->dir_cookie = desc->dir_cookie; dir_ctx->last_cookie = desc->last_cookie; dir_ctx->attr_gencount = desc->attr_gencount; - dir_ctx->page_index = desc->page_index; + dir_ctx->page_index = desc->folio_index; dir_ctx->force_clear = force_clear; dir_ctx->eof = desc->eof; dir_ctx->dtsize = desc->dtsize; -- GitLab From ec108d3cc7663db06dc3fe38a25391b3b7f925f6 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 4 Apr 2023 15:12:52 -0400 Subject: [PATCH 2729/5631] NFS: Convert readdir page array functions to use a folio Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 201 +++++++++++++++++++++++++-------------------------- 1 file changed, 99 insertions(+), 102 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 9edb0584c6d1..8257de6dba45 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -55,7 +55,7 @@ static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, struct dir_context *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); -static void nfs_readdir_free_folio(struct folio *); +static void nfs_readdir_clear_array(struct folio *); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, @@ -67,7 +67,7 @@ const struct file_operations nfs_dir_operations = { }; const struct address_space_operations nfs_dir_aops = { - .free_folio = nfs_readdir_free_folio, + .free_folio = nfs_readdir_clear_array, }; #define NFS_INIT_DTSIZE PAGE_SIZE @@ -146,8 +146,8 @@ struct nfs_cache_array { u64 change_attr; u64 last_cookie; unsigned int size; - unsigned char page_full : 1, - page_is_eof : 1, + unsigned char folio_full : 1, + folio_is_eof : 1, cookies_are_ordered : 1; struct nfs_cache_array_entry array[]; }; @@ -198,17 +198,17 @@ static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc) nfs_set_dtsize(desc, desc->dtsize << 1); } -static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie, - u64 change_attr) +static void nfs_readdir_folio_init_array(struct folio *folio, u64 last_cookie, + u64 change_attr) { struct nfs_cache_array *array; - array = kmap_local_page(page); + array = kmap_local_folio(folio, 0); array->change_attr = change_attr; array->last_cookie = last_cookie; array->size = 0; - array->page_full = 0; - array->page_is_eof = 0; + array->folio_full = 0; + array->folio_is_eof = 0; array->cookies_are_ordered = 1; kunmap_local(array); } @@ -216,44 +216,39 @@ static void nfs_readdir_page_init_array(struct page *page, u64 last_cookie, /* * we are freeing strings created by nfs_add_to_readdir_array() */ -static void nfs_readdir_clear_array(struct page *page) +static void nfs_readdir_clear_array(struct folio *folio) { struct nfs_cache_array *array; unsigned int i; - array = kmap_local_page(page); + array = kmap_local_folio(folio, 0); for (i = 0; i < array->size; i++) kfree(array->array[i].name); array->size = 0; kunmap_local(array); } -static void nfs_readdir_free_folio(struct folio *folio) +static void nfs_readdir_folio_reinit_array(struct folio *folio, u64 last_cookie, + u64 change_attr) { - nfs_readdir_clear_array(&folio->page); + nfs_readdir_clear_array(folio); + nfs_readdir_folio_init_array(folio, last_cookie, change_attr); } -static void nfs_readdir_page_reinit_array(struct page *page, u64 last_cookie, - u64 change_attr) -{ - nfs_readdir_clear_array(page); - nfs_readdir_page_init_array(page, last_cookie, change_attr); -} - -static struct page * -nfs_readdir_page_array_alloc(u64 last_cookie, gfp_t gfp_flags) +static struct folio * +nfs_readdir_folio_array_alloc(u64 last_cookie, gfp_t gfp_flags) { - struct page *page = alloc_page(gfp_flags); - if (page) - nfs_readdir_page_init_array(page, last_cookie, 0); - return page; + struct folio *folio = folio_alloc(gfp_flags, 0); + if (folio) + nfs_readdir_folio_init_array(folio, last_cookie, 0); + return folio; } -static void nfs_readdir_page_array_free(struct page *page) +static void nfs_readdir_folio_array_free(struct folio *folio) { - if (page) { - nfs_readdir_clear_array(page); - put_page(page); + if (folio) { + nfs_readdir_clear_array(folio); + folio_put(folio); } } @@ -264,13 +259,13 @@ static u64 nfs_readdir_array_index_cookie(struct nfs_cache_array *array) static void nfs_readdir_array_set_eof(struct nfs_cache_array *array) { - array->page_is_eof = 1; - array->page_full = 1; + array->folio_is_eof = 1; + array->folio_full = 1; } static bool nfs_readdir_array_is_full(struct nfs_cache_array *array) { - return array->page_full; + return array->folio_full; } /* @@ -302,16 +297,16 @@ static size_t nfs_readdir_array_maxentries(void) */ static int nfs_readdir_array_can_expand(struct nfs_cache_array *array) { - if (array->page_full) + if (array->folio_full) return -ENOSPC; if (array->size == nfs_readdir_array_maxentries()) { - array->page_full = 1; + array->folio_full = 1; return -ENOSPC; } return 0; } -static int nfs_readdir_page_array_append(struct page *page, +static int nfs_readdir_folio_array_append(struct folio *folio, const struct nfs_entry *entry, u64 *cookie) { @@ -322,7 +317,7 @@ static int nfs_readdir_page_array_append(struct page *page, name = nfs_readdir_copy_name(entry->name, entry->len); - array = kmap_atomic(page); + array = kmap_atomic(folio_page(folio, 0)); if (!name) goto out; ret = nfs_readdir_array_can_expand(array); @@ -361,17 +356,17 @@ static int nfs_readdir_page_array_append(struct page *page, * 127 readdir entries for a typical 64-bit system, that works out to a * cache of ~ 33 million entries per directory. */ -static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) +static pgoff_t nfs_readdir_folio_cookie_hash(u64 cookie) { if (cookie == 0) return 0; return hash_64(cookie, 18); } -static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, - u64 change_attr) +static bool nfs_readdir_folio_validate(struct folio *folio, u64 last_cookie, + u64 change_attr) { - struct nfs_cache_array *array = kmap_local_page(page); + struct nfs_cache_array *array = kmap_local_folio(folio, 0); int ret = true; if (array->change_attr != change_attr) @@ -382,81 +377,83 @@ static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, return ret; } -static void nfs_readdir_page_unlock_and_put(struct page *page) +static void nfs_readdir_folio_unlock_and_put(struct folio *folio) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); } -static void nfs_readdir_page_init_and_validate(struct page *page, u64 cookie, - u64 change_attr) +static void nfs_readdir_folio_init_and_validate(struct folio *folio, u64 cookie, + u64 change_attr) { - if (PageUptodate(page)) { - if (nfs_readdir_page_validate(page, cookie, change_attr)) + if (folio_test_uptodate(folio)) { + if (nfs_readdir_folio_validate(folio, cookie, change_attr)) return; - nfs_readdir_clear_array(page); + nfs_readdir_clear_array(folio); } - nfs_readdir_page_init_array(page, cookie, change_attr); - SetPageUptodate(page); + nfs_readdir_folio_init_array(folio, cookie, change_attr); + folio_mark_uptodate(folio); } -static struct page *nfs_readdir_page_get_locked(struct address_space *mapping, - u64 cookie, u64 change_attr) +static struct folio *nfs_readdir_folio_get_locked(struct address_space *mapping, + u64 cookie, u64 change_attr) { - pgoff_t index = nfs_readdir_page_cookie_hash(cookie); - struct page *page; + pgoff_t index = nfs_readdir_folio_cookie_hash(cookie); + struct folio *folio; - page = grab_cache_page(mapping, index); - if (!page) + folio = filemap_grab_folio(mapping, index); + if (!folio) return NULL; - nfs_readdir_page_init_and_validate(page, cookie, change_attr); - return page; + nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); + return folio; } -static u64 nfs_readdir_page_last_cookie(struct page *page) +static u64 nfs_readdir_folio_last_cookie(struct folio *folio) { struct nfs_cache_array *array; u64 ret; - array = kmap_local_page(page); + array = kmap_local_folio(folio, 0); ret = array->last_cookie; kunmap_local(array); return ret; } -static bool nfs_readdir_page_needs_filling(struct page *page) +static bool nfs_readdir_folio_needs_filling(struct folio *folio) { struct nfs_cache_array *array; bool ret; - array = kmap_local_page(page); + array = kmap_local_folio(folio, 0); ret = !nfs_readdir_array_is_full(array); kunmap_local(array); return ret; } -static void nfs_readdir_page_set_eof(struct page *page) +static void nfs_readdir_folio_set_eof(struct folio *folio) { struct nfs_cache_array *array; - array = kmap_local_page(page); + array = kmap_local_folio(folio, 0); nfs_readdir_array_set_eof(array); kunmap_local(array); } -static struct page *nfs_readdir_page_get_next(struct address_space *mapping, - u64 cookie, u64 change_attr) +static struct folio *nfs_readdir_folio_get_next(struct address_space *mapping, + u64 cookie, u64 change_attr) { - pgoff_t index = nfs_readdir_page_cookie_hash(cookie); - struct page *page; + pgoff_t index = nfs_readdir_folio_cookie_hash(cookie); + struct folio *folio; - page = grab_cache_page_nowait(mapping, index); - if (!page) + folio = __filemap_get_folio(mapping, index, + FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, + mapping_gfp_mask(mapping)); + if (!folio) return NULL; - nfs_readdir_page_init_and_validate(page, cookie, change_attr); - if (nfs_readdir_page_last_cookie(page) != cookie) - nfs_readdir_page_reinit_array(page, cookie, change_attr); - return page; + nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); + if (nfs_readdir_folio_last_cookie(folio) != cookie) + nfs_readdir_folio_reinit_array(folio, cookie, change_attr); + return folio; } static inline @@ -481,7 +478,7 @@ bool nfs_readdir_use_cookie(const struct file *filp) static void nfs_readdir_seek_next_array(struct nfs_cache_array *array, struct nfs_readdir_descriptor *desc) { - if (array->page_full) { + if (array->folio_full) { desc->last_cookie = array->last_cookie; desc->current_index += array->size; desc->cache_entry_index = 0; @@ -506,7 +503,7 @@ static int nfs_readdir_search_for_pos(struct nfs_cache_array *array, if (diff < 0) goto out_eof; if (diff >= array->size) { - if (array->page_is_eof) + if (array->folio_is_eof) goto out_eof; nfs_readdir_seek_next_array(array, desc); return -EAGAIN; @@ -554,7 +551,7 @@ static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, } } check_eof: - if (array->page_is_eof) { + if (array->folio_is_eof) { status = -EBADCOOKIE; if (desc->dir_cookie == array->last_cookie) desc->eof = true; @@ -826,9 +823,9 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc, u64 change_attr) { struct address_space *mapping = desc->file->f_mapping; - struct folio *folio = *arrays; + struct folio *new, *folio = *arrays; struct xdr_stream stream; - struct page *scratch, *new; + struct page *scratch; struct xdr_buf buf; u64 cookie; int status; @@ -845,36 +842,36 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc, if (status != 0) break; - status = nfs_readdir_page_array_append(folio_page(folio, 0), entry, &cookie); + status = nfs_readdir_folio_array_append(folio, entry, &cookie); if (status != -ENOSPC) continue; if (folio->mapping != mapping) { if (!--narrays) break; - new = nfs_readdir_page_array_alloc(cookie, GFP_KERNEL); + new = nfs_readdir_folio_array_alloc(cookie, GFP_KERNEL); if (!new) break; arrays++; - *arrays = folio = page_folio(new); + *arrays = folio = new; } else { - new = nfs_readdir_page_get_next(mapping, cookie, - change_attr); + new = nfs_readdir_folio_get_next(mapping, cookie, + change_attr); if (!new) break; if (folio != *arrays) - nfs_readdir_page_unlock_and_put(folio_page(folio, 0)); - folio = page_folio(new); + nfs_readdir_folio_unlock_and_put(folio); + folio = new; } desc->folio_index_max++; - status = nfs_readdir_page_array_append(folio_page(folio, 0), entry, &cookie); + status = nfs_readdir_folio_array_append(folio, entry, &cookie); } while (!status && !entry->eof); switch (status) { case -EBADCOOKIE: if (!entry->eof) break; - nfs_readdir_page_set_eof(folio_page(folio, 0)); + nfs_readdir_folio_set_eof(folio); fallthrough; case -EAGAIN: status = 0; @@ -888,7 +885,7 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc, } if (folio != *arrays) - nfs_readdir_page_unlock_and_put(folio_page(folio, 0)); + nfs_readdir_folio_unlock_and_put(folio); put_page(scratch); return status; @@ -943,7 +940,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; - entry->cookie = nfs_readdir_page_last_cookie(folio_page(folio, 0)); + entry->cookie = nfs_readdir_folio_last_cookie(folio); entry->fh = nfs_alloc_fhandle(); entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); entry->server = NFS_SERVER(inode); @@ -966,7 +963,7 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, status = nfs_readdir_folio_filler(desc, entry, pages, pglen, arrays, narrays, change_attr); else - nfs_readdir_page_set_eof(folio_page(folio, 0)); + nfs_readdir_folio_set_eof(folio); desc->buffer_fills++; free_pages: @@ -997,14 +994,14 @@ nfs_readdir_folio_get_cached(struct nfs_readdir_descriptor *desc) struct address_space *mapping = desc->file->f_mapping; u64 change_attr = inode_peek_iversion_raw(mapping->host); u64 cookie = desc->last_cookie; - struct page *page; + struct folio *folio; - page = nfs_readdir_page_get_locked(mapping, cookie, change_attr); - if (!page) + folio = nfs_readdir_folio_get_locked(mapping, cookie, change_attr); + if (!folio) return NULL; - if (desc->clear_cache && !nfs_readdir_page_needs_filling(page)) - nfs_readdir_page_reinit_array(page, cookie, change_attr); - return page_folio(page); + if (desc->clear_cache && !nfs_readdir_folio_needs_filling(folio)) + nfs_readdir_folio_reinit_array(folio, cookie, change_attr); + return folio; } /* @@ -1021,7 +1018,7 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) desc->folio = nfs_readdir_folio_get_cached(desc); if (!desc->folio) return -ENOMEM; - if (nfs_readdir_page_needs_filling(folio_page(desc->folio, 0))) { + if (nfs_readdir_folio_needs_filling(desc->folio)) { /* Grow the dtsize if we had to go back for more pages */ if (desc->folio_index == desc->folio_index_max) nfs_grow_dtsize(desc); @@ -1115,7 +1112,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, break; } } - if (array->page_is_eof) + if (array->folio_is_eof) desc->eof = !desc->eob; kunmap_local(array); @@ -1148,7 +1145,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) arrays = kcalloc(sz, sizeof(*arrays), GFP_KERNEL); if (!arrays) goto out; - arrays[0] = page_folio(nfs_readdir_page_array_alloc(desc->dir_cookie, GFP_KERNEL)); + arrays[0] = nfs_readdir_folio_array_alloc(desc->dir_cookie, GFP_KERNEL); if (!arrays[0]) goto out; @@ -1185,7 +1182,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) } out_free: for (i = 0; i < sz && arrays[i]; i++) - nfs_readdir_page_array_free(folio_page(arrays[i], 0)); + nfs_readdir_folio_array_free(arrays[i]); out: if (!nfs_readdir_use_cookie(desc->file)) nfs_readdir_rewind_search(desc); -- GitLab From 984abd349d0f76d4b267abc0d8e1a86af3ec2d84 Mon Sep 17 00:00:00 2001 From: Alexander Pantyukhin Date: Sat, 14 Jan 2023 18:05:33 +0500 Subject: [PATCH 2730/5631] perf scripts python intel-pt-events: Delete unused 'event_attr variable The 'event_attr' is never used later, the var is ok be deleted. Additional code simplification is to substitute string slice comparison with "substring" function. This case no need to know the length specific words. Signed-off-by: Alexander Pantyukhin Acked-by: Adrian Hunter Cc: Andrew Morton Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230114130533.2877-1-apantykhin@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/intel-pt-events.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py index 1c76368f13c1..346c89bd16d6 100644 --- a/tools/perf/scripts/python/intel-pt-events.py +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -340,7 +340,6 @@ def print_srccode(comm, param_dict, sample, symbol, dso, with_insn): print(start_str, src_str) def do_process_event(param_dict): - event_attr = param_dict["attr"] sample = param_dict["sample"] raw_buf = param_dict["raw_buf"] comm = param_dict["comm"] @@ -349,6 +348,7 @@ def do_process_event(param_dict): # callchain = param_dict["callchain"] # brstack = param_dict["brstack"] # brstacksym = param_dict["brstacksym"] + # event_attr = param_dict["attr"] # Symbol and dso info are not always resolved dso = get_optional(param_dict, "dso") @@ -359,13 +359,13 @@ def do_process_event(param_dict): print(glb_switch_str[cpu]) del glb_switch_str[cpu] - if name[0:12] == "instructions": + if name.startswith("instructions"): if glb_src: print_srccode(comm, param_dict, sample, symbol, dso, True) else: print_instructions_start(comm, sample) print_common_ip(param_dict, sample, symbol, dso) - elif name[0:8] == "branches": + elif name.startswith("branches"): if glb_src: print_srccode(comm, param_dict, sample, symbol, dso, False) else: -- GitLab From f1f67db9d64ffb85af04dbbf59e3f213fbf86add Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 18:44:58 -0700 Subject: [PATCH 2731/5631] clk: qcom: rpm: Use managed `of_clk_add_hw_provider()` Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()`. This makes sure the provider gets automatically removed on unbind and allows to completely eliminate the drivers `remove()` callback. Signed-off-by: Lars-Peter Clausen Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230410014502.27929-7-lars@metafoo.de --- drivers/clk/qcom/clk-rpm.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/clk/qcom/clk-rpm.c b/drivers/clk/qcom/clk-rpm.c index e723ddb99a44..cac623e27b0e 100644 --- a/drivers/clk/qcom/clk-rpm.c +++ b/drivers/clk/qcom/clk-rpm.c @@ -580,8 +580,8 @@ static int rpm_clk_probe(struct platform_device *pdev) goto err; } - ret = of_clk_add_hw_provider(pdev->dev.of_node, qcom_rpm_clk_hw_get, - rcc); + ret = devm_of_clk_add_hw_provider(&pdev->dev, qcom_rpm_clk_hw_get, + rcc); if (ret) goto err; @@ -591,18 +591,12 @@ static int rpm_clk_probe(struct platform_device *pdev) return ret; } -static void rpm_clk_remove(struct platform_device *pdev) -{ - of_clk_del_provider(pdev->dev.of_node); -} - static struct platform_driver rpm_clk_driver = { .driver = { .name = "qcom-clk-rpm", .of_match_table = rpm_clk_match_table, }, .probe = rpm_clk_probe, - .remove_new = rpm_clk_remove, }; static int __init rpm_clk_init(void) -- GitLab From 4e8db2d7520f780f86055465c680e20327008a34 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 12:36:58 -0300 Subject: [PATCH 2732/5631] perf map: Add map__refcnt() accessor to use in the maps test To remove one more direct access to 'struct map' so that we can intecept accesses to its instantiations and refcount check it to catch use after free, etc. Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/ZDbRIJknafLnDwtO@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/maps.c | 4 ++-- tools/perf/util/map.h | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index 1c7293476aca..a6278f9c8b71 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -30,7 +30,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma if (map__start(map) != merged[i].start || map__end(map) != merged[i].end || strcmp(map__dso(map)->name, merged[i].name) || - refcount_read(&map->refcnt) != 1) { + refcount_read(map__refcnt(map)) != 1) { failed = true; } i++; @@ -50,7 +50,7 @@ static int check_maps(struct map_def *merged, unsigned int size, struct maps *ma map__start(map), map__end(map), map__dso(map)->name, - refcount_read(&map->refcnt)); + refcount_read(map__refcnt(map))); } } return failed ? TEST_FAIL : TEST_OK; diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 102485699aa8..f89ab7c2d327 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -97,6 +97,11 @@ static inline bool map__priv(const struct map *map) return map->priv; } +static inline refcount_t *map__refcnt(struct map *map) +{ + return &map->refcnt; +} + static inline size_t map__size(const struct map *map) { return map__end(map) - map__start(map); -- GitLab From 67a00d29c360f4d7b2ca7b1ccf24b145f60d14b8 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Wed, 29 Mar 2023 14:33:09 -0500 Subject: [PATCH 2733/5631] RDMA/rxe: Fix incorrect TASKLET_STATE_SCHED check in rxe_task.c In a previous patch TASKLET_STATE_SCHED was used as a mask but it is a bit position instead. Add the missing shift. Link: https://lore.kernel.org/r/20230329193308.7489-1-rpearsonhpe@gmail.com Reported-by: Dan Carpenter Link: https://lore.kernel.org/linux-rdma/8a054b78-6d50-4bc6-8d8a-83f85fbdb82f@kili.mountain/ Fixes: d94671632572 ("RDMA/rxe: Rewrite rxe_task.c") Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_task.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c index fea9a517c8d9..fb9a6bc8e620 100644 --- a/drivers/infiniband/sw/rxe/rxe_task.c +++ b/drivers/infiniband/sw/rxe/rxe_task.c @@ -21,7 +21,7 @@ static bool __reserve_if_idle(struct rxe_task *task) { WARN_ON(rxe_read(task->qp) <= 0); - if (task->tasklet.state & TASKLET_STATE_SCHED) + if (task->tasklet.state & BIT(TASKLET_STATE_SCHED)) return false; if (task->state == TASK_STATE_IDLE) { @@ -46,7 +46,7 @@ static bool __reserve_if_idle(struct rxe_task *task) */ static bool __is_done(struct rxe_task *task) { - if (task->tasklet.state & TASKLET_STATE_SCHED) + if (task->tasklet.state & BIT(TASKLET_STATE_SCHED)) return false; if (task->state == TASK_STATE_IDLE || -- GitLab From e5796a9cdf73ed08f8d7fbca4749d7097ee2ca0b Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 11 Apr 2023 15:04:43 +0200 Subject: [PATCH 2734/5631] dt-bindings: phy: qmp-ufs: describe the UFS PHY for sa8775p Add a new compatible for the QMP UFS PHY found on sa8775p platforms and update the clocks property to accommodate three clocks. Signed-off-by: Bartosz Golaszewski Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230411130446.401440-3-brgl@bgdev.pl Signed-off-by: Vinod Koul --- .../phy/qcom,sc8280xp-qmp-ufs-phy.yaml | 26 ++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml index cd0fbbd3593d..94c0fab065a8 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-ufs-phy.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,sa8775p-qmp-ufs-phy - qcom,sc8280xp-qmp-ufs-phy - qcom,sm6125-qmp-ufs-phy - qcom,sm7150-qmp-ufs-phy @@ -25,12 +26,15 @@ properties: maxItems: 1 clocks: - maxItems: 2 + minItems: 2 + maxItems: 3 clock-names: + minItems: 2 items: - const: ref - const: ref_aux + - const: qref power-domains: maxItems: 1 @@ -64,6 +68,26 @@ required: - vdda-pll-supply - "#phy-cells" +allOf: + - if: + properties: + compatible: + contains: + enum: + - qcom,sa8775p-qmp-ufs-phy + then: + properties: + clocks: + maxItems: 3 + clock-names: + maxItems: 3 + else: + properties: + clocks: + maxItems: 2 + clock-names: + maxItems: 2 + additionalProperties: false examples: -- GitLab From 607c101fe9f2f618ef8db9f9b589a365125c16ee Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 11 Apr 2023 15:04:44 +0200 Subject: [PATCH 2735/5631] phy: qualcomm: phy-qcom-qmp-ufs: add definitions for sa8775p Add QMP PHY config for sa8775p and add support for the new compatible. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20230411130446.401440-4-brgl@bgdev.pl Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-ufs.c | 37 +++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c index d58822049211..8c877b668bb9 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-ufs.c @@ -853,6 +853,40 @@ static const struct qmp_phy_cfg msm8996_ufsphy_cfg = { .no_pcs_sw_reset = true, }; +static const struct qmp_phy_cfg sa8775p_ufsphy_cfg = { + .lanes = 2, + + .offsets = &qmp_ufs_offsets, + + .tbls = { + .serdes = sm8350_ufsphy_serdes, + .serdes_num = ARRAY_SIZE(sm8350_ufsphy_serdes), + .tx = sm8350_ufsphy_tx, + .tx_num = ARRAY_SIZE(sm8350_ufsphy_tx), + .rx = sm8350_ufsphy_rx, + .rx_num = ARRAY_SIZE(sm8350_ufsphy_rx), + .pcs = sm8350_ufsphy_pcs, + .pcs_num = ARRAY_SIZE(sm8350_ufsphy_pcs), + }, + .tbls_hs_b = { + .serdes = sm8350_ufsphy_hs_b_serdes, + .serdes_num = ARRAY_SIZE(sm8350_ufsphy_hs_b_serdes), + }, + .tbls_hs_g4 = { + .tx = sm8350_ufsphy_g4_tx, + .tx_num = ARRAY_SIZE(sm8350_ufsphy_g4_tx), + .rx = sm8350_ufsphy_g4_rx, + .rx_num = ARRAY_SIZE(sm8350_ufsphy_g4_rx), + .pcs = sm8350_ufsphy_g4_pcs, + .pcs_num = ARRAY_SIZE(sm8350_ufsphy_g4_pcs), + }, + .clk_list = sm8450_ufs_phy_clk_l, + .num_clks = ARRAY_SIZE(sm8450_ufs_phy_clk_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = ufsphy_v5_regs_layout, +}; + static const struct qmp_phy_cfg sc8280xp_ufsphy_cfg = { .lanes = 2, @@ -1600,6 +1634,9 @@ static const struct of_device_id qmp_ufs_of_match_table[] = { }, { .compatible = "qcom,msm8998-qmp-ufs-phy", .data = &sdm845_ufsphy_cfg, + }, { + .compatible = "qcom,sa8775p-qmp-ufs-phy", + .data = &sa8775p_ufsphy_cfg, }, { .compatible = "qcom,sc8180x-qmp-ufs-phy", .data = &sm8150_ufsphy_cfg, -- GitLab From 49e6833f9d65a3321021eb8827d0c4c0e1c0441d Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 24 Mar 2023 09:26:49 -0400 Subject: [PATCH 2736/5631] phy: rockchip: remove unused hw_to_inno function clang with W=1 reports drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c:284:36: error: unused function 'hw_to_inno' [-Werror,-Wunused-function] static inline struct inno_dsidphy *hw_to_inno(struct clk_hw *hw) ^ This function is not used so remove it. Signed-off-by: Tom Rix Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230324132649.2649166-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c index 726928ff1273..401b0aabb159 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-dsidphy.c @@ -281,11 +281,6 @@ struct inno_mipi_dphy_timing inno_mipi_dphy_timing_table_max_2_5ghz[] = { {2500000000, 0x15, 0x54, 0x7f, 0x15, 0x6a}, }; -static inline struct inno_dsidphy *hw_to_inno(struct clk_hw *hw) -{ - return container_of(hw, struct inno_dsidphy, pll.hw); -} - static void phy_update_bits(struct inno_dsidphy *inno, u8 first, u8 second, u8 mask, u8 val) { -- GitLab From 60671c4feee550e5597565866a9d8e1001ffa770 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 21:01:11 +0200 Subject: [PATCH 2737/5631] dt-bindings: phy: cadence-sierra: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here and a board could actually need more of clock assignments than the schema allows. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230404190115.546973-1-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/phy-cadence-sierra.yaml | 8 -------- 1 file changed, 8 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml index c3d1fa102798..37f028f7a095 100644 --- a/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml +++ b/Documentation/devicetree/bindings/phy/phy-cadence-sierra.yaml @@ -61,14 +61,6 @@ properties: - const: pll0_refclk - const: pll1_refclk - assigned-clocks: - minItems: 1 - maxItems: 2 - - assigned-clock-parents: - minItems: 1 - maxItems: 2 - cdns,autoconf: type: boolean description: -- GitLab From e458b7aa67cdaf3e63d6a1feecf4f52edb225561 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 21:01:12 +0200 Subject: [PATCH 2738/5631] dt-bindings: phy: cadence-torrent: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here and a board could actually need more of clock assignments than the schema allows. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230404190115.546973-2-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/phy-cadence-torrent.yaml | 6 ------ 1 file changed, 6 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml index dc92be05fe5f..dfb31314face 100644 --- a/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml +++ b/Documentation/devicetree/bindings/phy/phy-cadence-torrent.yaml @@ -44,12 +44,6 @@ properties: - const: refclk - const: phy_en_refclk - assigned-clocks: - maxItems: 3 - - assigned-clock-parents: - maxItems: 3 - reg: minItems: 1 items: -- GitLab From 1ca60781e387df1ca753117e2507eaf154057ff8 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 21:01:13 +0200 Subject: [PATCH 2739/5631] dt-bindings: phy: ti,phy-am654-serdes: drop assigned-clocks type The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. The specific parenting of the first input and output clock is apparently important, thus keep them as required, but without defining type. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230404190115.546973-3-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/ti,phy-am654-serdes.yaml | 5 ----- 1 file changed, 5 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml b/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml index 2a886b91bf2d..854e554eae67 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-am654-serdes.yaml @@ -34,11 +34,6 @@ properties: Three input clocks referring to left input reference clock, refclk and right input reference clock. - assigned-clocks: - $ref: /schemas/types.yaml#/definitions/phandle-array - assigned-clock-parents: - $ref: /schemas/types.yaml#/definitions/phandle-array - '#phy-cells': const: 2 description: -- GitLab From c042ea2a9ee2a41c45c0e70812a1e64ae38ed919 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 21:01:14 +0200 Subject: [PATCH 2740/5631] dt-bindings: phy: ti,phy-j721e-wiz: drop assigned-clocks The meta schema from DT schema already defines assigned-clocks, so there is no need for device schema to mention it at all. There are also no benefits of having it here and a board could actually need more of clock assignments than the schema allows. Keep however the assigned-clocks in children nodes, as apparently their proper parenting is required. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230404190115.546973-4-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/ti,phy-j721e-wiz.yaml | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index a55fc0f24533..051cf31c5eea 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -54,18 +54,6 @@ properties: ranges: true - assigned-clocks: - minItems: 1 - maxItems: 2 - - assigned-clock-parents: - minItems: 1 - maxItems: 2 - - assigned-clock-rates: - minItems: 1 - maxItems: 2 - typec-dir-gpios: maxItems: 1 description: -- GitLab From a50abe2e6d4906c4d83c6da155dc1fc4624e1280 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Tue, 4 Apr 2023 21:01:15 +0200 Subject: [PATCH 2741/5631] dt-bindings: phy: ti,phy-j721e-wiz: document clock-output-names Document the clock-output-names property of clock children, even though the nodes are actually deprecated, to fix dtbs_check warnings like: k3-j7200-common-proc-board.dtb: wiz@5060000: refclk-dig: 'clock-output-names' does not match any of the regexes: 'pinctrl-[0-9]+' Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230404190115.546973-5-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- .../devicetree/bindings/phy/ti,phy-j721e-wiz.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml index 051cf31c5eea..9ea30eaba314 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-j721e-wiz.yaml @@ -89,6 +89,9 @@ properties: "#clock-cells": const: 0 + clock-output-names: + maxItems: 1 + assigned-clocks: maxItems: 1 @@ -122,6 +125,9 @@ patternProperties: "#clock-cells": const: 0 + clock-output-names: + maxItems: 1 + assigned-clocks: maxItems: 1 @@ -150,6 +156,9 @@ patternProperties: "#clock-cells": const: 0 + clock-output-names: + maxItems: 1 + required: - clocks - "#clock-cells" -- GitLab From e024854048e733391b31fe5a398704b31b9af803 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Tue, 29 Nov 2022 19:16:34 +0800 Subject: [PATCH 2742/5631] phy: tegra: xusb: Add missing tegra_xusb_port_unregister for usb2_port and ulpi_port The tegra_xusb_port_unregister should be called when usb2_port and ulpi_port map fails in tegra_xusb_add_usb2_port() or in tegra_xusb_add_ulpi_port(), fix it. Fixes: 53d2a715c240 ("phy: Add Tegra XUSB pad controller support") Signed-off-by: Gaosheng Cui Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20221129111634.1547747-1-cuigaosheng1@huawei.com Signed-off-by: Vinod Koul --- drivers/phy/tegra/xusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index ec335668563d..b55d4e9f42b5 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -805,6 +805,7 @@ static int tegra_xusb_add_usb2_port(struct tegra_xusb_padctl *padctl, usb2->base.lane = usb2->base.ops->map(&usb2->base); if (IS_ERR(usb2->base.lane)) { err = PTR_ERR(usb2->base.lane); + tegra_xusb_port_unregister(&usb2->base); goto out; } @@ -871,6 +872,7 @@ static int tegra_xusb_add_ulpi_port(struct tegra_xusb_padctl *padctl, ulpi->base.lane = ulpi->base.ops->map(&ulpi->base); if (IS_ERR(ulpi->base.lane)) { err = PTR_ERR(ulpi->base.lane); + tegra_xusb_port_unregister(&ulpi->base); goto out; } -- GitLab From c78fe548b062db5a0c90390078601dfbc9b4daa9 Mon Sep 17 00:00:00 2001 From: Guillaume Ranquet Date: Thu, 16 Feb 2023 17:02:25 +0100 Subject: [PATCH 2743/5631] dt-bindings: phy: mediatek: hdmi-phy: Add mt8195 compatible Add a compatible for the HDMI PHY on MT8195 Acked-by: Krzysztof Kozlowski Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Signed-off-by: Guillaume Ranquet Link: https://lore.kernel.org/r/20220919-v8-1-a84c80468fe9@baylibre.com Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/phy/mediatek,hdmi-phy.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/phy/mediatek,hdmi-phy.yaml b/Documentation/devicetree/bindings/phy/mediatek,hdmi-phy.yaml index 6cfdaadec085..f3a8b0b745d1 100644 --- a/Documentation/devicetree/bindings/phy/mediatek,hdmi-phy.yaml +++ b/Documentation/devicetree/bindings/phy/mediatek,hdmi-phy.yaml @@ -28,6 +28,7 @@ properties: - const: mediatek,mt2701-hdmi-phy - const: mediatek,mt2701-hdmi-phy - const: mediatek,mt8173-hdmi-phy + - const: mediatek,mt8195-hdmi-phy reg: maxItems: 1 -- GitLab From 605b90371912edb2214088e69f5e7e1121507062 Mon Sep 17 00:00:00 2001 From: Guillaume Ranquet Date: Thu, 16 Feb 2023 17:02:26 +0100 Subject: [PATCH 2744/5631] phy: phy-mtk-hdmi: Add generic phy configure callback Some phys, such as mt8195, needs to have a configure callback defined. Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Matthias Brugger Signed-off-by: Guillaume Ranquet Link: https://lore.kernel.org/r/20220919-v8-2-a84c80468fe9@baylibre.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/phy-mtk-hdmi.c | 12 ++++++++++++ drivers/phy/mediatek/phy-mtk-hdmi.h | 1 + 2 files changed, 13 insertions(+) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.c b/drivers/phy/mediatek/phy-mtk-hdmi.c index b16d437d6721..32f713301768 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi.c @@ -8,10 +8,12 @@ static int mtk_hdmi_phy_power_on(struct phy *phy); static int mtk_hdmi_phy_power_off(struct phy *phy); +static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opts); static const struct phy_ops mtk_hdmi_phy_dev_ops = { .power_on = mtk_hdmi_phy_power_on, .power_off = mtk_hdmi_phy_power_off, + .configure = mtk_hdmi_phy_configure, .owner = THIS_MODULE, }; @@ -43,6 +45,16 @@ static int mtk_hdmi_phy_power_off(struct phy *phy) return 0; } +static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opts) +{ + struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy); + + if (hdmi_phy->conf->hdmi_phy_configure) + return hdmi_phy->conf->hdmi_phy_configure(phy, opts); + + return 0; +} + static const struct phy_ops * mtk_hdmi_phy_dev_get_ops(const struct mtk_hdmi_phy *hdmi_phy) { diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.h b/drivers/phy/mediatek/phy-mtk-hdmi.h index c7fa65cff989..f5aac9d352d8 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi.h @@ -24,6 +24,7 @@ struct mtk_hdmi_phy_conf { const struct clk_ops *hdmi_phy_clk_ops; void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy); void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy); + int (*hdmi_phy_configure)(struct phy *phy, union phy_configure_opts *opts); }; struct mtk_hdmi_phy { -- GitLab From 45810d486bb44bd60213d5f09a713df81b987972 Mon Sep 17 00:00:00 2001 From: Guillaume Ranquet Date: Thu, 16 Feb 2023 17:02:27 +0100 Subject: [PATCH 2745/5631] phy: mediatek: add support for phy-mtk-hdmi-mt8195 Add support for the mediatek hdmi phy on MT8195 SoC Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Guillaume Ranquet Link: https://lore.kernel.org/r/20220919-v8-3-a84c80468fe9@baylibre.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/Makefile | 1 + drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c | 495 +++++++++++++++++++++ drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h | 113 +++++ drivers/phy/mediatek/phy-mtk-hdmi.c | 3 + drivers/phy/mediatek/phy-mtk-hdmi.h | 2 + 5 files changed, 614 insertions(+) create mode 100644 drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c create mode 100644 drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h diff --git a/drivers/phy/mediatek/Makefile b/drivers/phy/mediatek/Makefile index fb1f8edaffa7..c9a50395533e 100644 --- a/drivers/phy/mediatek/Makefile +++ b/drivers/phy/mediatek/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_PHY_MTK_XSPHY) += phy-mtk-xsphy.o phy-mtk-hdmi-drv-y := phy-mtk-hdmi.o phy-mtk-hdmi-drv-y += phy-mtk-hdmi-mt2701.o phy-mtk-hdmi-drv-y += phy-mtk-hdmi-mt8173.o +phy-mtk-hdmi-drv-y += phy-mtk-hdmi-mt8195.o obj-$(CONFIG_PHY_MTK_HDMI) += phy-mtk-hdmi-drv.o phy-mtk-mipi-dsi-drv-y := phy-mtk-mipi-dsi.o diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c new file mode 100644 index 000000000000..abfc077fb0a8 --- /dev/null +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -0,0 +1,495 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 MediaTek Inc. + * Copyright (c) 2022 BayLibre, SAS + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "phy-mtk-io.h" +#include "phy-mtk-hdmi.h" +#include "phy-mtk-hdmi-mt8195.h" + +static void mtk_hdmi_ana_fifo_en(struct mtk_hdmi_phy *hdmi_phy) +{ + /* make data fifo writable for hdmi2.0 */ + mtk_phy_set_bits(hdmi_phy->regs + HDMI_ANA_CTL, REG_ANA_HDMI20_FIFO_EN); +} + +static void +mtk_phy_tmds_clk_ratio(struct mtk_hdmi_phy *hdmi_phy, bool enable) +{ + void __iomem *regs = hdmi_phy->regs; + + mtk_hdmi_ana_fifo_en(hdmi_phy); + + /* HDMI 2.0 specification, 3.4Gbps <= TMDS Bit Rate <= 6G, + * clock bit ratio 1:40, under 3.4Gbps, clock bit ratio 1:10 + */ + if (enable) + mtk_phy_update_field(regs + HDMI20_CLK_CFG, REG_TXC_DIV, 3); + else + mtk_phy_clear_bits(regs + HDMI20_CLK_CFG, REG_TXC_DIV); +} + +static void mtk_hdmi_pll_sel_src(struct clk_hw *hw) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + + mtk_phy_clear_bits(regs + HDMI_CTL_3, REG_HDMITX_REF_XTAL_SEL); + mtk_phy_clear_bits(regs + HDMI_CTL_3, REG_HDMITX_REF_RESPLL_SEL); + + /* DA_HDMITX21_REF_CK for TXPLL input source */ + mtk_phy_clear_bits(regs + HDMI_1_CFG_10, RG_HDMITXPLL_REF_CK_SEL); +} + +static void mtk_hdmi_pll_perf(struct clk_hw *hw) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_0, RG_HDMITXPLL_BP2); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_BC); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_IC, 0x1); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_BR, 0x2); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_IR, 0x2); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_BP); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_0, RG_HDMITXPLL_IBAND_FIX_EN); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT14); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_HIKVCO); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_0, RG_HDMITXPLL_HREN, 0x1); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_0, RG_HDMITXPLL_LVR_SEL, 0x1); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT12_11); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_0, RG_HDMITXPLL_TCL_EN); +} + +static int mtk_hdmi_pll_set_hw(struct clk_hw *hw, u8 prediv, + u8 fbkdiv_high, + u32 fbkdiv_low, + u8 fbkdiv_hs3, u8 posdiv1, + u8 posdiv2, u8 txprediv, + u8 txposdiv, + u8 digital_div) +{ + u8 txposdiv_value; + u8 div3_ctrl_value; + u8 posdiv_vallue; + u8 div_ctrl_value; + u8 reserve_3_2_value; + u8 prediv_value; + u8 reserve13_value; + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + + mtk_hdmi_pll_sel_src(hw); + + mtk_hdmi_pll_perf(hw); + + mtk_phy_update_field(regs + HDMI_1_CFG_10, RG_HDMITX21_BIAS_PE_BG_VREF_SEL, 0x2); + mtk_phy_clear_bits(regs + HDMI_1_CFG_10, RG_HDMITX21_VREF_SEL); + mtk_phy_update_field(regs + HDMI_1_CFG_9, RG_HDMITX21_SLDO_VREF_SEL, 0x2); + mtk_phy_clear_bits(regs + HDMI_1_CFG_10, RG_HDMITX21_BIAS_PE_VREF_SELB); + mtk_phy_set_bits(regs + HDMI_1_CFG_3, RG_HDMITX21_SLDOLPF_EN); + mtk_phy_update_field(regs + HDMI_1_CFG_6, RG_HDMITX21_INTR_CAL, 0x11); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_PWD); + + /* TXPOSDIV */ + txposdiv_value = ilog2(txposdiv); + + mtk_phy_update_field(regs + HDMI_1_CFG_6, RG_HDMITX21_TX_POSDIV, txposdiv_value); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_TX_POSDIV_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_FRL_EN); + + /* TXPREDIV */ + switch (txprediv) { + case 2: + div3_ctrl_value = 0x0; + posdiv_vallue = 0x0; + break; + case 4: + div3_ctrl_value = 0x0; + posdiv_vallue = 0x1; + break; + case 6: + div3_ctrl_value = 0x1; + posdiv_vallue = 0x0; + break; + case 12: + div3_ctrl_value = 0x1; + posdiv_vallue = 0x1; + break; + default: + return -EINVAL; + } + + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_4, RG_HDMITXPLL_POSDIV_DIV3_CTRL, div3_ctrl_value); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_4, RG_HDMITXPLL_POSDIV, posdiv_vallue); + + /* POSDIV1 */ + switch (posdiv1) { + case 5: + div_ctrl_value = 0x0; + break; + case 10: + div_ctrl_value = 0x1; + break; + case 12: + div_ctrl_value = 0x2; + break; + case 15: + div_ctrl_value = 0x3; + break; + default: + return -EINVAL; + } + + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_4, RG_HDMITXPLL_DIV_CTRL, div_ctrl_value); + + /* DE add new setting */ + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT14); + + /* POSDIV2 */ + switch (posdiv2) { + case 1: + reserve_3_2_value = 0x0; + break; + case 2: + reserve_3_2_value = 0x1; + break; + case 4: + reserve_3_2_value = 0x2; + break; + case 6: + reserve_3_2_value = 0x3; + break; + default: + return -EINVAL; + } + + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT3_2, reserve_3_2_value); + + /* DE add new setting */ + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT1_0, 0x2); + + /* PREDIV */ + prediv_value = ilog2(prediv); + + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_4, RG_HDMITXPLL_PREDIV, prediv_value); + + /* FBKDIV_HS3 */ + reserve13_value = ilog2(fbkdiv_hs3); + + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_1, RG_HDMITXPLL_RESERVE_BIT13, reserve13_value); + + /* FBDIV */ + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_4, RG_HDMITXPLL_FBKDIV_HIGH, fbkdiv_high); + mtk_phy_update_field(regs + HDMI_1_PLL_CFG_3, RG_HDMITXPLL_FBKDIV_LOW, fbkdiv_low); + + /* Digital DIVIDER */ + mtk_phy_clear_bits(regs + HDMI_CTL_3, REG_PIXEL_CLOCK_SEL); + + if (digital_div == 1) { + mtk_phy_clear_bits(regs + HDMI_CTL_3, REG_HDMITX_PIXEL_CLOCK); + } else { + mtk_phy_set_bits(regs + HDMI_CTL_3, REG_HDMITX_PIXEL_CLOCK); + mtk_phy_update_field(regs + HDMI_CTL_3, REG_HDMITXPLL_DIV, digital_div - 1); + } + + return 0; +} + +static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, + unsigned long rate, unsigned long parent_rate) +{ + u8 digital_div, txprediv, txposdiv, fbkdiv_high, posdiv1, posdiv2; + u64 tmds_clk, pixel_clk, da_hdmitx21_ref_ck, ns_hdmipll_ck, pcw; + u8 txpredivs[4] = { 2, 4, 6, 12 }; + u32 fbkdiv_low; + int i, ret; + + pixel_clk = rate; + tmds_clk = pixel_clk; + + if (tmds_clk < 25 * MEGA || tmds_clk > 594 * MEGA) + return -EINVAL; + + if (tmds_clk >= 340 * MEGA) + hdmi_phy->tmds_over_340M = true; + else + hdmi_phy->tmds_over_340M = false; + + /* in Hz */ + da_hdmitx21_ref_ck = 26 * MEGA; + + /* TXPOSDIV stage treatment: + * 0M < TMDS clk < 54M /8 + * 54M <= TMDS clk < 148.35M /4 + * 148.35M <=TMDS clk < 296.7M /2 + * 296.7 <=TMDS clk <= 594M /1 + */ + if (tmds_clk < 54 * MEGA) + txposdiv = 8; + else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + txposdiv = 4; + else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + txposdiv = 2; + else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + txposdiv = 1; + else + return -EINVAL; + + /* calculate txprediv: can be 2, 4, 6, 12 + * ICO clk = 5*TMDS_CLK*TXPOSDIV*TXPREDIV + * ICO clk constraint: 5G =< ICO clk <= 12G + */ + for (i = 0; i < ARRAY_SIZE(txpredivs); i++) { + ns_hdmipll_ck = 5 * tmds_clk * txposdiv * txpredivs[i]; + if (ns_hdmipll_ck >= 5 * GIGA && + ns_hdmipll_ck <= 1 * GIGA) + break; + } + if (i == (ARRAY_SIZE(txpredivs) - 1) && + (ns_hdmipll_ck < 5 * GIGA || ns_hdmipll_ck > 12 * GIGA)) { + return -EINVAL; + } + if (i == ARRAY_SIZE(txpredivs)) + return -EINVAL; + + txprediv = txpredivs[i]; + + /* PCW calculation: FBKDIV + * formula: pcw=(frequency_out*2^pcw_bit) / frequency_in / FBKDIV_HS3; + * RG_HDMITXPLL_FBKDIV[32:0]: + * [32,24] 9bit integer, [23,0]:24bit fraction + */ + pcw = div_u64(((u64)ns_hdmipll_ck) << PCW_DECIMAL_WIDTH, + da_hdmitx21_ref_ck / PLL_FBKDIV_HS3); + + if (pcw > GENMASK_ULL(32, 0)) + return -EINVAL; + + fbkdiv_high = FIELD_GET(GENMASK_ULL(63, 32), pcw); + fbkdiv_low = FIELD_GET(GENMASK(31, 0), pcw); + + /* posdiv1: + * posdiv1 stage treatment according to color_depth: + * 24bit -> posdiv1 /10, 30bit -> posdiv1 /12.5, + * 36bit -> posdiv1 /15, 48bit -> posdiv1 /10 + */ + posdiv1 = 10; + posdiv2 = 1; + + /* Digital clk divider, max /32 */ + digital_div = div_u64((u64)ns_hdmipll_ck, posdiv1 / posdiv2 / pixel_clk); + if (!(digital_div <= 32 && digital_div >= 1)) + return -EINVAL; + + mtk_hdmi_pll_set_hw(hw, PLL_PREDIV, fbkdiv_high, fbkdiv_low, + PLL_FBKDIV_HS3, posdiv1, posdiv2, txprediv, + txposdiv, digital_div); + if (ret) + return -EINVAL; + + return 0; +} + +static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + u8 data_channel_bias, clk_channel_bias; + u8 impedance, impedance_en; + u32 tmds_clk; + u32 pixel_clk = hdmi_phy->pll_rate; + + tmds_clk = pixel_clk; + + /* bias & impedance setting: + * 3G < data rate <= 6G: enable impedance 100ohm, + * data channel bias 24mA, clock channel bias 20mA + * pixel clk >= HD, 74.175MHZ <= pixel clk <= 300MHZ: + * enalbe impedance 100ohm + * data channel 20mA, clock channel 16mA + * 27M =< pixel clk < 74.175: disable impedance + * data channel & clock channel bias 10mA + */ + + /* 3G < data rate <= 6G, 300M < tmds rate <= 594M */ + if (tmds_clk > 300 * MEGA && tmds_clk <= 594 * MEGA) { + data_channel_bias = 0x3c; /* 24mA */ + clk_channel_bias = 0x34; /* 20mA */ + impedance_en = 0xf; + impedance = 0x36; /* 100ohm */ + } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + data_channel_bias = 0x34; /* 20mA */ + clk_channel_bias = 0x2c; /* 16mA */ + impedance_en = 0xf; + impedance = 0x36; /* 100ohm */ + } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + data_channel_bias = 0x14; /* 10mA */ + clk_channel_bias = 0x14; /* 10mA */ + impedance_en = 0x0; + impedance = 0x0; + } else { + return -EINVAL; + } + + /* bias */ + mtk_phy_update_field(regs + HDMI_1_CFG_1, RG_HDMITX21_DRV_IBIAS_D0, data_channel_bias); + mtk_phy_update_field(regs + HDMI_1_CFG_1, RG_HDMITX21_DRV_IBIAS_D1, data_channel_bias); + mtk_phy_update_field(regs + HDMI_1_CFG_1, RG_HDMITX21_DRV_IBIAS_D2, data_channel_bias); + mtk_phy_update_field(regs + HDMI_1_CFG_0, RG_HDMITX21_DRV_IBIAS_CLK, clk_channel_bias); + + /* impedance */ + mtk_phy_update_field(regs + HDMI_1_CFG_0, RG_HDMITX21_DRV_IMP_EN, impedance_en); + mtk_phy_update_field(regs + HDMI_1_CFG_2, RG_HDMITX21_DRV_IMP_D0_EN1, impedance); + mtk_phy_update_field(regs + HDMI_1_CFG_2, RG_HDMITX21_DRV_IMP_D1_EN1, impedance); + mtk_phy_update_field(regs + HDMI_1_CFG_2, RG_HDMITX21_DRV_IMP_D2_EN1, impedance); + mtk_phy_update_field(regs + HDMI_1_CFG_2, RG_HDMITX21_DRV_IMP_CLK_EN1, impedance); + + return 0; +} + +static int mtk_hdmi_pll_prepare(struct clk_hw *hw) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_TX_POSDIV_EN); + + mtk_phy_set_bits(regs + HDMI_1_CFG_0, RG_HDMITX21_SER_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_D0_DRV_OP_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_D1_DRV_OP_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_D2_DRV_OP_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_CK_DRV_OP_EN); + + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_FRL_D0_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_FRL_D1_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_FRL_D2_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_FRL_CK_EN); + + mtk_hdmi_pll_drv_setting(hw); + + mtk_phy_clear_bits(regs + HDMI_1_CFG_10, RG_HDMITX21_BG_PWD); + mtk_phy_set_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_BIAS_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_3, RG_HDMITX21_CKLDO_EN); + mtk_phy_set_bits(regs + HDMI_1_CFG_3, RG_HDMITX21_SLDO_EN); + + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_4, DA_HDMITXPLL_PWR_ON); + usleep_range(5, 10); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_4, DA_HDMITXPLL_ISO_EN); + usleep_range(5, 10); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_PWD); + usleep_range(30, 50); + return 0; +} + +static void mtk_hdmi_pll_unprepare(struct clk_hw *hw) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + void __iomem *regs = hdmi_phy->regs; + + mtk_phy_set_bits(regs + HDMI_1_CFG_10, RG_HDMITX21_BG_PWD); + mtk_phy_clear_bits(regs + HDMI_1_CFG_6, RG_HDMITX21_BIAS_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_3, RG_HDMITX21_CKLDO_EN); + mtk_phy_clear_bits(regs + HDMI_1_CFG_3, RG_HDMITX21_SLDO_EN); + + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_2, RG_HDMITXPLL_PWD); + usleep_range(10, 20); + mtk_phy_set_bits(regs + HDMI_1_PLL_CFG_4, DA_HDMITXPLL_ISO_EN); + usleep_range(10, 20); + mtk_phy_clear_bits(regs + HDMI_1_PLL_CFG_4, DA_HDMITXPLL_PWR_ON); +} + +static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + + dev_dbg(hdmi_phy->dev, "%s: %lu Hz, parent: %lu Hz\n", __func__, rate, + parent_rate); + + return mtk_hdmi_pll_calc(hdmi_phy, hw, rate, parent_rate); +} + +static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + + hdmi_phy->pll_rate = rate; + return rate; +} + +static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw); + + return hdmi_phy->pll_rate; +} + +static const struct clk_ops mtk_hdmi_pll_ops = { + .prepare = mtk_hdmi_pll_prepare, + .unprepare = mtk_hdmi_pll_unprepare, + .set_rate = mtk_hdmi_pll_set_rate, + .round_rate = mtk_hdmi_pll_round_rate, + .recalc_rate = mtk_hdmi_pll_recalc_rate, +}; + +static void vtx_signal_en(struct mtk_hdmi_phy *hdmi_phy, bool on) +{ + void __iomem *regs = hdmi_phy->regs; + + if (on) + mtk_phy_set_bits(regs + HDMI_1_CFG_0, RG_HDMITX21_DRV_EN); + else + mtk_phy_clear_bits(regs + HDMI_1_CFG_0, RG_HDMITX21_DRV_EN); +} + +static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy) +{ + vtx_signal_en(hdmi_phy, true); + usleep_range(100, 150); +} + +static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy) +{ + vtx_signal_en(hdmi_phy, false); +} + +static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opts) +{ + struct phy_configure_opts_dp *dp_opts = &opts->dp; + struct mtk_hdmi_phy *hdmi_phy = phy_get_drvdata(phy); + int ret; + + ret = clk_set_rate(hdmi_phy->pll, dp_opts->link_rate); + + if (ret) + return ret; + + mtk_phy_tmds_clk_ratio(hdmi_phy, hdmi_phy->tmds_over_340M); + + return ret; +} + +struct mtk_hdmi_phy_conf mtk_hdmi_phy_8195_conf = { + .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, + .hdmi_phy_clk_ops = &mtk_hdmi_pll_ops, + .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, + .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, + .hdmi_phy_configure = mtk_hdmi_phy_configure, +}; + +MODULE_AUTHOR("Can Zeng "); +MODULE_DESCRIPTION("MediaTek MT8195 HDMI PHY Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h new file mode 100644 index 000000000000..22a68dc9550c --- /dev/null +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2022 MediaTek Inc. + * Copyright (c) 2022 BayLibre, SAS + */ + +#ifndef _MTK_HDMI_PHY_8195_H +#define _MTK_HDMI_PHY_8195_H + +#include +#include +#include + +#define PCW_DECIMAL_WIDTH 24 +#define PLL_PREDIV 1 +#define PLL_FBKDIV_HS3 1 + +#define HDMI20_CLK_CFG 0x70 +#define REG_TXC_DIV GENMASK(31, 30) + +#define HDMI_1_CFG_0 0x00 +#define RG_HDMITX21_DRV_IBIAS_CLK GENMASK(10, 5) +#define RG_HDMITX21_DRV_IMP_EN GENMASK(23, 20) +#define RG_HDMITX21_DRV_EN GENMASK(27, 24) +#define RG_HDMITX21_SER_EN GENMASK(31, 28) + +#define HDMI_1_CFG_1 0x04 +#define RG_HDMITX21_DRV_IBIAS_D0 GENMASK(19, 14) +#define RG_HDMITX21_DRV_IBIAS_D1 GENMASK(25, 20) +#define RG_HDMITX21_DRV_IBIAS_D2 GENMASK(31, 26) + +#define HDMI_1_CFG_10 0x40 +#define RG_HDMITXPLL_REF_CK_SEL GENMASK(2, 1) +#define RG_HDMITX21_VREF_SEL BIT(4) +#define RG_HDMITX21_BIAS_PE_VREF_SELB BIT(10) +#define RG_HDMITX21_BIAS_PE_BG_VREF_SEL GENMASK(16, 15) +#define RG_HDMITX21_BG_PWD BIT(20) + +#define HDMI_1_CFG_2 0x08 +#define RG_HDMITX21_DRV_IMP_D0_EN1 GENMASK(13, 8) +#define RG_HDMITX21_DRV_IMP_D1_EN1 GENMASK(19, 14) +#define RG_HDMITX21_DRV_IMP_D2_EN1 GENMASK(25, 20) +#define RG_HDMITX21_DRV_IMP_CLK_EN1 GENMASK(31, 26) + +#define HDMI_1_CFG_3 0x0c +#define RG_HDMITX21_CKLDO_EN BIT(3) +#define RG_HDMITX21_SLDOLPF_EN BIT(7) +#define RG_HDMITX21_SLDO_EN GENMASK(11, 8) + +#define HDMI_1_CFG_6 0x18 +#define RG_HDMITX21_D2_DRV_OP_EN BIT(8) +#define RG_HDMITX21_D1_DRV_OP_EN BIT(9) +#define RG_HDMITX21_D0_DRV_OP_EN BIT(10) +#define RG_HDMITX21_CK_DRV_OP_EN BIT(11) +#define RG_HDMITX21_FRL_EN BIT(12) +#define RG_HDMITX21_FRL_CK_EN BIT(13) +#define RG_HDMITX21_FRL_D0_EN BIT(14) +#define RG_HDMITX21_FRL_D1_EN BIT(15) +#define RG_HDMITX21_FRL_D2_EN BIT(16) +#define RG_HDMITX21_INTR_CAL GENMASK(22, 18) +#define RG_HDMITX21_TX_POSDIV GENMASK(27, 26) +#define RG_HDMITX21_TX_POSDIV_EN BIT(28) +#define RG_HDMITX21_BIAS_EN BIT(29) + +#define HDMI_1_CFG_9 0x24 +#define RG_HDMITX21_SLDO_VREF_SEL GENMASK(5, 4) + +#define HDMI_1_PLL_CFG_0 0x44 +#define RG_HDMITXPLL_HREN GENMASK(13, 12) +#define RG_HDMITXPLL_IBAND_FIX_EN BIT(24) +#define RG_HDMITXPLL_LVR_SEL GENMASK(27, 26) +#define RG_HDMITXPLL_BP2 BIT(30) +#define RG_HDMITXPLL_TCL_EN BIT(31) + +#define HDMI_1_PLL_CFG_1 0x48 +#define RG_HDMITXPLL_RESERVE_BIT1_0 GENMASK(1, 0) +#define RG_HDMITXPLL_RESERVE_BIT3_2 GENMASK(3, 2) +#define RG_HDMITXPLL_RESERVE_BIT12_11 GENMASK(12, 11) +#define RG_HDMITXPLL_RESERVE_BIT13 BIT(13) +#define RG_HDMITXPLL_RESERVE_BIT14 BIT(14) + +#define HDMI_1_PLL_CFG_2 0x4c +#define RG_HDMITXPLL_BC GENMASK(28, 27) +#define RG_HDMITXPLL_IC GENMASK(26, 22) +#define RG_HDMITXPLL_BR GENMASK(21, 19) +#define RG_HDMITXPLL_IR GENMASK(18, 14) +#define RG_HDMITXPLL_BP GENMASK(13, 10) +#define RG_HDMITXPLL_HIKVCO BIT(29) +#define RG_HDMITXPLL_PWD BIT(31) + +#define HDMI_1_PLL_CFG_3 0x50 +#define RG_HDMITXPLL_FBKDIV_LOW GENMASK(31, 0) + +#define HDMI_1_PLL_CFG_4 0x54 +#define DA_HDMITXPLL_ISO_EN BIT(1) +#define DA_HDMITXPLL_PWR_ON BIT(2) +#define RG_HDMITXPLL_POSDIV_DIV3_CTRL BIT(21) +#define RG_HDMITXPLL_POSDIV GENMASK(23, 22) +#define RG_HDMITXPLL_DIV_CTRL GENMASK(25, 24) +#define RG_HDMITXPLL_PREDIV GENMASK(29, 28) +#define RG_HDMITXPLL_FBKDIV_HIGH BIT(31) + +#define HDMI_ANA_CTL 0x7c +#define REG_ANA_HDMI20_FIFO_EN BIT(16) + +#define HDMI_CTL_3 0xcc +#define REG_HDMITXPLL_DIV GENMASK(4, 0) +#define REG_HDMITX_REF_XTAL_SEL BIT(7) +#define REG_HDMITX_REF_RESPLL_SEL BIT(9) +#define REG_PIXEL_CLOCK_SEL BIT(10) +#define REG_HDMITX_PIXEL_CLOCK BIT(23) + +#endif /* MTK_HDMI_PHY_8195_H */ diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.c b/drivers/phy/mediatek/phy-mtk-hdmi.c index 32f713301768..d2e824771f9d 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi.c @@ -161,6 +161,9 @@ static const struct of_device_id mtk_hdmi_phy_match[] = { { .compatible = "mediatek,mt8173-hdmi-phy", .data = &mtk_hdmi_phy_8173_conf, }, + { .compatible = "mediatek,mt8195-hdmi-phy", + .data = &mtk_hdmi_phy_8195_conf, + }, {}, }; MODULE_DEVICE_TABLE(of, mtk_hdmi_phy_match); diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.h b/drivers/phy/mediatek/phy-mtk-hdmi.h index f5aac9d352d8..fc2ad6a0527f 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi.h @@ -40,10 +40,12 @@ struct mtk_hdmi_phy { unsigned char drv_imp_d0; unsigned int ibias; unsigned int ibias_up; + bool tmds_over_340M; }; struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw); +extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8195_conf; extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf; extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf; -- GitLab From 0cfa43ab46b577804a3e89cc5aa7922fe4d9b74f Mon Sep 17 00:00:00 2001 From: Swapnil Jakhade Date: Mon, 3 Apr 2023 10:56:44 +0200 Subject: [PATCH 2746/5631] phy: cadence: Sierra: Add PCIe + SGMII PHY multilink configuration Add register sequences for PCIe + SGMII PHY multilink configuration. This has been validated on TI J7 platforms. Signed-off-by: Swapnil Jakhade Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230403085644.10187-1-sjakhade@cadence.com Signed-off-by: Vinod Koul --- drivers/phy/cadence/phy-cadence-sierra.c | 141 ++++++++++++++++++++++- 1 file changed, 139 insertions(+), 2 deletions(-) diff --git a/drivers/phy/cadence/phy-cadence-sierra.c b/drivers/phy/cadence/phy-cadence-sierra.c index ab0a37618ef3..13fcd3a65fe9 100644 --- a/drivers/phy/cadence/phy-cadence-sierra.c +++ b/drivers/phy/cadence/phy-cadence-sierra.c @@ -24,7 +24,7 @@ #include #define NUM_SSC_MODE 3 -#define NUM_PHY_TYPE 4 +#define NUM_PHY_TYPE 5 /* PHY register offsets */ #define SIERRA_COMMON_CDB_OFFSET 0x0 @@ -46,7 +46,9 @@ #define SIERRA_CMN_REFRCV_PREG 0x98 #define SIERRA_CMN_REFRCV1_PREG 0xB8 #define SIERRA_CMN_PLLLC1_GEN_PREG 0xC2 +#define SIERRA_CMN_PLLLC1_FBDIV_INT_PREG 0xC3 #define SIERRA_CMN_PLLLC1_LF_COEFF_MODE0_PREG 0xCA +#define SIERRA_CMN_PLLLC1_CLK0_PREG 0xCE #define SIERRA_CMN_PLLLC1_BWCAL_MODE0_PREG 0xD0 #define SIERRA_CMN_PLLLC1_SS_TIME_STEPSIZE_MODE_PREG 0xE2 @@ -74,6 +76,7 @@ #define SIERRA_PSC_RX_A1_PREG 0x031 #define SIERRA_PSC_RX_A2_PREG 0x032 #define SIERRA_PSC_RX_A3_PREG 0x033 +#define SIERRA_PLLCTRL_FBDIV_MODE01_PREG 0x039 #define SIERRA_PLLCTRL_SUBRATE_PREG 0x03A #define SIERRA_PLLCTRL_GEN_A_PREG 0x03B #define SIERRA_PLLCTRL_GEN_D_PREG 0x03E @@ -305,6 +308,7 @@ enum cdns_sierra_phy_type { TYPE_NONE, TYPE_PCIE, TYPE_USB, + TYPE_SGMII, TYPE_QSGMII }; @@ -929,6 +933,9 @@ static int cdns_sierra_get_optional(struct cdns_sierra_inst *inst, case PHY_TYPE_USB3: inst->phy_type = TYPE_USB; break; + case PHY_TYPE_SGMII: + inst->phy_type = TYPE_SGMII; + break; case PHY_TYPE_QSGMII: inst->phy_type = TYPE_QSGMII; break; @@ -1316,7 +1323,7 @@ static int cdns_sierra_phy_configure_multilink(struct cdns_sierra_phy *sp) } } - if (phy_t1 == TYPE_QSGMII) + if (phy_t1 == TYPE_SGMII || phy_t1 == TYPE_QSGMII) reset_control_deassert(sp->phys[node].lnk_rst); } @@ -1514,6 +1521,71 @@ static void cdns_sierra_phy_remove(struct platform_device *pdev) cdns_sierra_clk_unregister(phy); } +/* SGMII PHY PMA lane configuration */ +static struct cdns_reg_pairs sgmii_phy_pma_ln_regs[] = { + {0x9010, SIERRA_PHY_PMA_XCVR_CTRL} +}; + +static struct cdns_sierra_vals sgmii_phy_pma_ln_vals = { + .reg_pairs = sgmii_phy_pma_ln_regs, + .num_regs = ARRAY_SIZE(sgmii_phy_pma_ln_regs), +}; + +/* SGMII refclk 100MHz, no ssc, opt3 and GE1 links using PLL LC1 */ +static const struct cdns_reg_pairs sgmii_100_no_ssc_plllc1_opt3_cmn_regs[] = { + {0x002D, SIERRA_CMN_PLLLC1_FBDIV_INT_PREG}, + {0x2085, SIERRA_CMN_PLLLC1_LF_COEFF_MODE0_PREG}, + {0x1005, SIERRA_CMN_PLLLC1_CLK0_PREG}, + {0x0000, SIERRA_CMN_PLLLC1_BWCAL_MODE0_PREG}, + {0x0800, SIERRA_CMN_PLLLC1_SS_TIME_STEPSIZE_MODE_PREG} +}; + +static const struct cdns_reg_pairs sgmii_100_no_ssc_plllc1_opt3_ln_regs[] = { + {0x688E, SIERRA_DET_STANDEC_D_PREG}, + {0x0004, SIERRA_PSC_LN_IDLE_PREG}, + {0x0FFE, SIERRA_PSC_RX_A0_PREG}, + {0x0106, SIERRA_PLLCTRL_FBDIV_MODE01_PREG}, + {0x0013, SIERRA_PLLCTRL_SUBRATE_PREG}, + {0x0003, SIERRA_PLLCTRL_GEN_A_PREG}, + {0x0106, SIERRA_PLLCTRL_GEN_D_PREG}, + {0x5231, SIERRA_PLLCTRL_CPGAIN_MODE_PREG }, + {0x0000, SIERRA_DRVCTRL_ATTEN_PREG}, + {0x9702, SIERRA_DRVCTRL_BOOST_PREG}, + {0x0051, SIERRA_RX_CREQ_FLTR_A_MODE0_PREG}, + {0x3C0E, SIERRA_CREQ_CCLKDET_MODE01_PREG}, + {0x3220, SIERRA_CREQ_FSMCLK_SEL_PREG}, + {0x0000, SIERRA_CREQ_EQ_CTRL_PREG}, + {0x0002, SIERRA_DEQ_PHALIGN_CTRL}, + {0x0186, SIERRA_DEQ_GLUT0}, + {0x0186, SIERRA_DEQ_GLUT1}, + {0x0186, SIERRA_DEQ_GLUT2}, + {0x0186, SIERRA_DEQ_GLUT3}, + {0x0186, SIERRA_DEQ_GLUT4}, + {0x0861, SIERRA_DEQ_ALUT0}, + {0x07E0, SIERRA_DEQ_ALUT1}, + {0x079E, SIERRA_DEQ_ALUT2}, + {0x071D, SIERRA_DEQ_ALUT3}, + {0x03F5, SIERRA_DEQ_DFETAP_CTRL_PREG}, + {0x0C01, SIERRA_DEQ_TAU_CTRL1_FAST_MAINT_PREG}, + {0x3C40, SIERRA_DEQ_TAU_CTRL1_SLOW_MAINT_PREG}, + {0x1C04, SIERRA_DEQ_TAU_CTRL2_PREG}, + {0x0033, SIERRA_DEQ_PICTRL_PREG}, + {0x0000, SIERRA_CPI_OUTBUF_RATESEL_PREG}, + {0x0B6D, SIERRA_CPI_RESBIAS_BIN_PREG}, + {0x0102, SIERRA_RXBUFFER_CTLECTRL_PREG}, + {0x0002, SIERRA_RXBUFFER_RCDFECTRL_PREG} +}; + +static struct cdns_sierra_vals sgmii_100_no_ssc_plllc1_opt3_cmn_vals = { + .reg_pairs = sgmii_100_no_ssc_plllc1_opt3_cmn_regs, + .num_regs = ARRAY_SIZE(sgmii_100_no_ssc_plllc1_opt3_cmn_regs), +}; + +static struct cdns_sierra_vals sgmii_100_no_ssc_plllc1_opt3_ln_vals = { + .reg_pairs = sgmii_100_no_ssc_plllc1_opt3_ln_regs, + .num_regs = ARRAY_SIZE(sgmii_100_no_ssc_plllc1_opt3_ln_regs), +}; + /* QSGMII PHY PMA lane configuration */ static struct cdns_reg_pairs qsgmii_phy_pma_ln_regs[] = { {0x9010, SIERRA_PHY_PMA_XCVR_CTRL} @@ -2340,6 +2412,11 @@ static const struct cdns_sierra_data cdns_map_sierra = { [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, [INTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &pcie_phy_pcs_cmn_vals, + [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, + [INTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &pcie_phy_pcs_cmn_vals, [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, @@ -2354,6 +2431,11 @@ static const struct cdns_sierra_data cdns_map_sierra = { [EXTERNAL_SSC] = &pcie_100_ext_ssc_cmn_vals, [INTERNAL_SSC] = &pcie_100_int_ssc_cmn_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &pcie_100_no_ssc_plllc_cmn_vals, + [EXTERNAL_SSC] = &pcie_100_ext_ssc_plllc_cmn_vals, + [INTERNAL_SSC] = &pcie_100_int_ssc_plllc_cmn_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &pcie_100_no_ssc_plllc_cmn_vals, [EXTERNAL_SSC] = &pcie_100_ext_ssc_plllc_cmn_vals, @@ -2365,6 +2447,13 @@ static const struct cdns_sierra_data cdns_map_sierra = { [EXTERNAL_SSC] = &usb_100_ext_ssc_cmn_vals, }, }, + [TYPE_SGMII] = { + [TYPE_PCIE] = { + [NO_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + [EXTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + [INTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + }, + }, [TYPE_QSGMII] = { [TYPE_PCIE] = { [NO_SSC] = &qsgmii_100_no_ssc_plllc1_cmn_vals, @@ -2380,6 +2469,11 @@ static const struct cdns_sierra_data cdns_map_sierra = { [EXTERNAL_SSC] = &pcie_100_ext_ssc_ln_vals, [INTERNAL_SSC] = &pcie_100_int_ssc_ln_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &ml_pcie_100_no_ssc_ln_vals, + [EXTERNAL_SSC] = &ml_pcie_100_ext_ssc_ln_vals, + [INTERNAL_SSC] = &ml_pcie_100_int_ssc_ln_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &ml_pcie_100_no_ssc_ln_vals, [EXTERNAL_SSC] = &ml_pcie_100_ext_ssc_ln_vals, @@ -2391,6 +2485,13 @@ static const struct cdns_sierra_data cdns_map_sierra = { [EXTERNAL_SSC] = &usb_100_ext_ssc_ln_vals, }, }, + [TYPE_SGMII] = { + [TYPE_PCIE] = { + [NO_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + [EXTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + [INTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + }, + }, [TYPE_QSGMII] = { [TYPE_PCIE] = { [NO_SSC] = &qsgmii_100_no_ssc_plllc1_ln_vals, @@ -2412,6 +2513,11 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, [INTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &pcie_phy_pcs_cmn_vals, + [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, + [INTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &pcie_phy_pcs_cmn_vals, [EXTERNAL_SSC] = &pcie_phy_pcs_cmn_vals, @@ -2420,6 +2526,13 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { }, }, .phy_pma_ln_vals = { + [TYPE_SGMII] = { + [TYPE_PCIE] = { + [NO_SSC] = &sgmii_phy_pma_ln_vals, + [EXTERNAL_SSC] = &sgmii_phy_pma_ln_vals, + [INTERNAL_SSC] = &sgmii_phy_pma_ln_vals, + }, + }, [TYPE_QSGMII] = { [TYPE_PCIE] = { [NO_SSC] = &qsgmii_phy_pma_ln_vals, @@ -2435,6 +2548,11 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { [EXTERNAL_SSC] = &pcie_100_ext_ssc_cmn_vals, [INTERNAL_SSC] = &pcie_100_int_ssc_cmn_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &pcie_100_no_ssc_plllc_cmn_vals, + [EXTERNAL_SSC] = &pcie_100_ext_ssc_plllc_cmn_vals, + [INTERNAL_SSC] = &pcie_100_int_ssc_plllc_cmn_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &pcie_100_no_ssc_plllc_cmn_vals, [EXTERNAL_SSC] = &pcie_100_ext_ssc_plllc_cmn_vals, @@ -2446,6 +2564,13 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { [EXTERNAL_SSC] = &usb_100_ext_ssc_cmn_vals, }, }, + [TYPE_SGMII] = { + [TYPE_PCIE] = { + [NO_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + [EXTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + [INTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_cmn_vals, + }, + }, [TYPE_QSGMII] = { [TYPE_PCIE] = { [NO_SSC] = &qsgmii_100_no_ssc_plllc1_cmn_vals, @@ -2461,6 +2586,11 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { [EXTERNAL_SSC] = &pcie_100_ext_ssc_ln_vals, [INTERNAL_SSC] = &pcie_100_int_ssc_ln_vals, }, + [TYPE_SGMII] = { + [NO_SSC] = &ti_ml_pcie_100_no_ssc_ln_vals, + [EXTERNAL_SSC] = &ti_ml_pcie_100_ext_ssc_ln_vals, + [INTERNAL_SSC] = &ti_ml_pcie_100_int_ssc_ln_vals, + }, [TYPE_QSGMII] = { [NO_SSC] = &ti_ml_pcie_100_no_ssc_ln_vals, [EXTERNAL_SSC] = &ti_ml_pcie_100_ext_ssc_ln_vals, @@ -2472,6 +2602,13 @@ static const struct cdns_sierra_data cdns_ti_map_sierra = { [EXTERNAL_SSC] = &usb_100_ext_ssc_ln_vals, }, }, + [TYPE_SGMII] = { + [TYPE_PCIE] = { + [NO_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + [EXTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + [INTERNAL_SSC] = &sgmii_100_no_ssc_plllc1_opt3_ln_vals, + }, + }, [TYPE_QSGMII] = { [TYPE_PCIE] = { [NO_SSC] = &qsgmii_100_no_ssc_plllc1_ln_vals, -- GitLab From 57c0e1362fdd57d0cea7ab1e583b58abf4bd8c2d Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Mon, 3 Apr 2023 15:15:52 +0530 Subject: [PATCH 2747/5631] phy: ti: j721e-wiz: Fix unreachable code in wiz_mode_select() In the wiz_mode_select() function, the configuration performed for PHY_TYPE_USXGMII is unreachable. Fix it. Fixes: b64a85fb8f53 ("phy: ti: phy-j721e-wiz.c: Add usxgmii support in wiz driver") Signed-off-by: Siddharth Vadapalli Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230403094552.929108-1-s-vadapalli@ti.com Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-j721e-wiz.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index d2fd2143450a..d59918457799 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -443,18 +443,17 @@ static int wiz_mode_select(struct wiz *wiz) int i; for (i = 0; i < num_lanes; i++) { - if (wiz->lane_phy_type[i] == PHY_TYPE_DP) + if (wiz->lane_phy_type[i] == PHY_TYPE_DP) { mode = LANE_MODE_GEN1; - else if (wiz->lane_phy_type[i] == PHY_TYPE_QSGMII) + } else if (wiz->lane_phy_type[i] == PHY_TYPE_QSGMII) { mode = LANE_MODE_GEN2; - else - continue; - - if (wiz->lane_phy_type[i] == PHY_TYPE_USXGMII) { + } else if (wiz->lane_phy_type[i] == PHY_TYPE_USXGMII) { ret = regmap_field_write(wiz->p0_mac_src_sel[i], 0x3); ret = regmap_field_write(wiz->p0_rxfclk_sel[i], 0x3); ret = regmap_field_write(wiz->p0_refclk_sel[i], 0x3); mode = LANE_MODE_GEN1; + } else { + continue; } ret = regmap_field_write(wiz->p_standard_mode[i], mode); -- GitLab From 73b46467cac027fe6cbe6585946726b53b80bfdb Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Wed, 15 Mar 2023 14:54:08 +0530 Subject: [PATCH 2748/5631] dt-bindings: phy: ti: phy-gmii-sel: Add support for J784S4 CPSW9G The CPSW9G instance of CPSW Ethernet Switch on TI's J784S4 SoC supports additional PHY modes like QSGMII. Add a compatible for it. Enable the use of "ti,qsgmii-main-ports" property for J784S4 CPSW9G. Signed-off-by: Siddharth Vadapalli Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230315092408.1722114-1-s-vadapalli@ti.com Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml b/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml index 3699a06bdf6e..be41b4547ec6 100644 --- a/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml +++ b/Documentation/devicetree/bindings/phy/ti,phy-gmii-sel.yaml @@ -55,6 +55,7 @@ properties: - ti,am654-phy-gmii-sel - ti,j7200-cpsw5g-phy-gmii-sel - ti,j721e-cpsw9g-phy-gmii-sel + - ti,j784s4-cpsw9g-phy-gmii-sel reg: maxItems: 1 @@ -87,6 +88,7 @@ allOf: - ti,am654-phy-gmii-sel - ti,j7200-cpsw5g-phy-gmii-sel - ti,j721e-cpsw9g-phy-gmii-sel + - ti,j784s4-cpsw9g-phy-gmii-sel then: properties: '#phy-cells': @@ -113,6 +115,7 @@ allOf: contains: enum: - ti,j721e-cpsw9g-phy-gmii-sel + - ti,j784s4-cpsw9g-phy-gmii-sel then: properties: ti,qsgmii-main-ports: @@ -130,6 +133,7 @@ allOf: enum: - ti,j7200-cpsw5g-phy-gmii-sel - ti,j721e-cpsw9g-phy-gmii-sel + - ti,j784s4-cpsw9g-phy-gmii-sel then: properties: ti,qsgmii-main-ports: false -- GitLab From 31d95c2f99bf16e59b996cf6a227e198a64e835c Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 19:01:12 +0900 Subject: [PATCH 2749/5631] rust: sync: arc: Add UniqueArc::assume_init() We can already create `UniqueArc>` instances with `UniqueArc::try_new_uninit()` and write to them with `write()`. Add the missing unsafe `assume_init()` function to promote it to `UniqueArc`, so users can do piece-wise initialization of the contents instead of doing it all at once as long as they keep the invariants (the same requirements as `MaybeUninit::assume_init()`). This mirrors the std `Arc::assume_init()` function. In the kernel, since we have `UniqueArc`, arguably this only belongs there since most use cases will initialize it immediately after creating it, before demoting it to `Arc` to share it. [ Miguel: The "Rust pin-init API for pinned initialization of structs" patch series [1] from Benno Lossin contains a very similar patch: rust: sync: add `assume_init` to `UniqueArc` Adds the `assume_init` function to `UniqueArc>` that unsafely assumes the value to be initialized and yields a value of type `UniqueArc`. This function is used when manually initializing the pointee of an `UniqueArc`. To make that patch a noop and thus drop it, I adjusted the `SAFETY` comment here to be the same as in the current latest version of that series (v7). I have also brought the `Reviewed-by`s there into here, and reworded the `Co-authored-by` into `Co-developed-by`. ] Link: https://lore.kernel.org/r/20230408122429.1103522-5-y86-dev@protonmail.com [1] Co-developed-by: Benno Lossin Signed-off-by: Benno Lossin Signed-off-by: Asahi Lina Reviewed-by: Gary Guo Reviewed-by: Wedson Almeida Filho Reviewed-by: Andreas Hindborg Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20230224-rust-arc-v2-2-5c97a865b276@asahilina.net Signed-off-by: Miguel Ojeda --- rust/kernel/sync/arc.rs | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 4ab9b280cb3d..8ce6d6bf478e 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -492,6 +492,17 @@ impl UniqueArc> { /// Converts a `UniqueArc>` into a `UniqueArc` by writing a value into it. pub fn write(mut self, value: T) -> UniqueArc { self.deref_mut().write(value); + // SAFETY: We just wrote the value to be initialized. + unsafe { self.assume_init() } + } + + /// Unsafely assume that `self` is initialized. + /// + /// # Safety + /// + /// The caller guarantees that the value behind this pointer has been initialized. It is + /// *immediate* UB to call this when the value is not initialized. + pub unsafe fn assume_init(self) -> UniqueArc { let inner = ManuallyDrop::new(self).inner.ptr; UniqueArc { // SAFETY: The new `Arc` is taking over `ptr` from `self.inner` (which won't be -- GitLab From 46384d0990bf99ed8b597e8794ea581e2a647710 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 18:48:10 +0900 Subject: [PATCH 2750/5631] rust: error: Rename to_kernel_errno() -> to_errno() This is kernel code, so specifying "kernel" is redundant. Let's simplify things and just call it to_errno(). Reviewed-by: Gary Guo Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-error-v3-1-03779bddc02b@asahilina.net Signed-off-by: Miguel Ojeda --- rust/kernel/error.rs | 2 +- rust/macros/module.rs | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 5b9751d7ff1d..35894fa35efe 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -73,7 +73,7 @@ pub struct Error(core::ffi::c_int); impl Error { /// Returns the kernel error code. - pub fn to_kernel_errno(self) -> core::ffi::c_int { + pub fn to_errno(self) -> core::ffi::c_int { self.0 } } diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 5e7ab83908a0..fb1244f8c2e6 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -278,7 +278,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { return 0; }} Err(e) => {{ - return e.to_kernel_errno(); + return e.to_errno(); }} }} }} -- GitLab From c7e20faa5fcad7a177cf6c306138010343dd6d3e Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 18:48:11 +0900 Subject: [PATCH 2751/5631] rust: error: Add Error::to_ptr() This is the Rust equivalent to ERR_PTR(), for use in C callbacks. Marked as #[allow(dead_code)] for now, since it does not have any consumers yet. Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Reviewed-by: Gary Guo Link: https://lore.kernel.org/r/20230224-rust-error-v3-2-03779bddc02b@asahilina.net Signed-off-by: Miguel Ojeda --- rust/helpers.c | 7 +++++++ rust/kernel/error.rs | 7 +++++++ 2 files changed, 14 insertions(+) diff --git a/rust/helpers.c b/rust/helpers.c index 09a4d93f9d62..89f4cd1e0df3 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -20,6 +20,7 @@ #include #include +#include #include __noreturn void rust_helper_BUG(void) @@ -46,6 +47,12 @@ bool rust_helper_refcount_dec_and_test(refcount_t *r) } EXPORT_SYMBOL_GPL(rust_helper_refcount_dec_and_test); +__force void *rust_helper_ERR_PTR(long err) +{ + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(rust_helper_ERR_PTR); + /* * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type * as the Rust `usize` type, so we can use it in contexts where Rust diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 35894fa35efe..154d0ca6e2dc 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -76,6 +76,13 @@ impl Error { pub fn to_errno(self) -> core::ffi::c_int { self.0 } + + /// Returns the error encoded as a pointer. + #[allow(dead_code)] + pub(crate) fn to_ptr(self) -> *mut T { + // SAFETY: self.0 is a valid error due to its invariant. + unsafe { bindings::ERR_PTR(self.0.into()) as *mut _ } + } } impl From for Error { -- GitLab From 6551a7fe0acbbc816802350414b37d9b42daccc8 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Apr 2023 18:48:12 +0900 Subject: [PATCH 2752/5631] rust: error: Add Error::from_errno{_unchecked}() Add a function to create `Error` values out of a kernel error return, which safely upholds the invariant that the error code is well-formed (negative and greater than -MAX_ERRNO). If a malformed code is passed in, it will be converted to EINVAL. Lina: Imported from rust-for-linux/rust as authored by Miguel and Fox with refactoring from Wedson, renamed from_kernel_errno() to from_errno(). Co-developed-by: Fox Chen Signed-off-by: Fox Chen Co-developed-by: Wedson Almeida Filho Signed-off-by: Wedson Almeida Filho Signed-off-by: Miguel Ojeda Reviewed-by: Andreas Hindborg Reviewed-by: Gary Guo Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-error-v3-3-03779bddc02b@asahilina.net [ Mark the new associated functions as `#[allow(dead_code)]`. ] Signed-off-by: Miguel Ojeda --- rust/kernel/error.rs | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 154d0ca6e2dc..0223d48ab43d 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -72,6 +72,38 @@ pub mod code { pub struct Error(core::ffi::c_int); impl Error { + /// Creates an [`Error`] from a kernel error code. + /// + /// It is a bug to pass an out-of-range `errno`. `EINVAL` would + /// be returned in such a case. + #[allow(dead_code)] + pub(crate) fn from_errno(errno: core::ffi::c_int) -> Error { + if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 { + // TODO: Make it a `WARN_ONCE` once available. + crate::pr_warn!( + "attempted to create `Error` with out of range `errno`: {}", + errno + ); + return code::EINVAL; + } + + // INVARIANT: The check above ensures the type invariant + // will hold. + Error(errno) + } + + /// Creates an [`Error`] from a kernel error code. + /// + /// # Safety + /// + /// `errno` must be within error code range (i.e. `>= -MAX_ERRNO && < 0`). + #[allow(dead_code)] + unsafe fn from_errno_unchecked(errno: core::ffi::c_int) -> Error { + // INVARIANT: The contract ensures the type invariant + // will hold. + Error(errno) + } + /// Returns the kernel error code. pub fn to_errno(self) -> core::ffi::c_int { self.0 -- GitLab From 086fbfa3b328901fa8b369093ba468864e20544e Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Mon, 3 Apr 2023 18:48:13 +0900 Subject: [PATCH 2753/5631] rust: error: Add to_result() helper Add a to_result() helper to convert kernel C return values to a Rust Result, mapping >=0 values to Ok(()) and negative values to Err(...), with Error::from_errno() ensuring that the errno is within range. Lina: Imported from rust-for-linux/rust, originally developed by Wedson as part of the AMBA device driver support. Signed-off-by: Wedson Almeida Filho Reviewed-by: Andreas Hindborg Reviewed-by: Gary Guo Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-error-v3-4-03779bddc02b@asahilina.net [ Add a removal of `#[allow(dead_code)]`. ] Signed-off-by: Miguel Ojeda --- rust/kernel/error.rs | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 0223d48ab43d..7e25871063df 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -76,7 +76,6 @@ impl Error { /// /// It is a bug to pass an out-of-range `errno`. `EINVAL` would /// be returned in such a case. - #[allow(dead_code)] pub(crate) fn from_errno(errno: core::ffi::c_int) -> Error { if errno < -(bindings::MAX_ERRNO as i32) || errno >= 0 { // TODO: Make it a `WARN_ONCE` once available. @@ -180,3 +179,13 @@ impl From for Error { /// it should still be modeled as returning a `Result` rather than /// just an [`Error`]. pub type Result = core::result::Result; + +/// Converts an integer as returned by a C kernel function to an error if it's negative, and +/// `Ok(())` otherwise. +pub fn to_result(err: core::ffi::c_int) -> Result { + if err < 0 { + Err(Error::from_errno(err)) + } else { + Ok(()) + } +} -- GitLab From 752417b3f0e7721f1d630f40da22d57e0dae043e Mon Sep 17 00:00:00 2001 From: Sven Van Asbroeck Date: Mon, 3 Apr 2023 18:48:14 +0900 Subject: [PATCH 2754/5631] rust: error: Add a helper to convert a C ERR_PTR to a `Result` Some kernel C API functions return a pointer which embeds an optional `errno`. Callers are supposed to check the returned pointer with `IS_ERR()` and if this returns `true`, retrieve the `errno` using `PTR_ERR()`. Create a Rust helper function to implement the Rust equivalent: transform a `*mut T` to `Result<*mut T>`. Lina: Imported from rust-for-linux/linux, with subsequent refactoring and contributions squashed in and attributed below. Renamed the function to from_err_ptr(). Co-developed-by: Boqun Feng Signed-off-by: Boqun Feng Co-developed-by: Miguel Ojeda Signed-off-by: Miguel Ojeda Co-developed-by: Fox Chen Signed-off-by: Fox Chen Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Sven Van Asbroeck Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-error-v3-5-03779bddc02b@asahilina.net [ Add a removal of `#[allow(dead_code)]`. ] Signed-off-by: Miguel Ojeda --- rust/helpers.c | 12 +++++++++++ rust/kernel/error.rs | 50 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 61 insertions(+), 1 deletion(-) diff --git a/rust/helpers.c b/rust/helpers.c index 89f4cd1e0df3..04b9be46e887 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -53,6 +53,18 @@ __force void *rust_helper_ERR_PTR(long err) } EXPORT_SYMBOL_GPL(rust_helper_ERR_PTR); +bool rust_helper_IS_ERR(__force const void *ptr) +{ + return IS_ERR(ptr); +} +EXPORT_SYMBOL_GPL(rust_helper_IS_ERR); + +long rust_helper_PTR_ERR(__force const void *ptr) +{ + return PTR_ERR(ptr); +} +EXPORT_SYMBOL_GPL(rust_helper_PTR_ERR); + /* * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type * as the Rust `usize` type, so we can use it in contexts where Rust diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 7e25871063df..67637b874267 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -96,7 +96,6 @@ impl Error { /// # Safety /// /// `errno` must be within error code range (i.e. `>= -MAX_ERRNO && < 0`). - #[allow(dead_code)] unsafe fn from_errno_unchecked(errno: core::ffi::c_int) -> Error { // INVARIANT: The contract ensures the type invariant // will hold. @@ -189,3 +188,52 @@ pub fn to_result(err: core::ffi::c_int) -> Result { Ok(()) } } + +/// Transform a kernel "error pointer" to a normal pointer. +/// +/// Some kernel C API functions return an "error pointer" which optionally +/// embeds an `errno`. Callers are supposed to check the returned pointer +/// for errors. This function performs the check and converts the "error pointer" +/// to a normal pointer in an idiomatic fashion. +/// +/// # Examples +/// +/// ```ignore +/// # use kernel::from_err_ptr; +/// # use kernel::bindings; +/// fn devm_platform_ioremap_resource( +/// pdev: &mut PlatformDevice, +/// index: u32, +/// ) -> Result<*mut core::ffi::c_void> { +/// // SAFETY: FFI call. +/// unsafe { +/// from_err_ptr(bindings::devm_platform_ioremap_resource( +/// pdev.to_ptr(), +/// index, +/// )) +/// } +/// } +/// ``` +// TODO: Remove `dead_code` marker once an in-kernel client is available. +#[allow(dead_code)] +pub(crate) fn from_err_ptr(ptr: *mut T) -> Result<*mut T> { + // CAST: Casting a pointer to `*const core::ffi::c_void` is always valid. + let const_ptr: *const core::ffi::c_void = ptr.cast(); + // SAFETY: The FFI function does not deref the pointer. + if unsafe { bindings::IS_ERR(const_ptr) } { + // SAFETY: The FFI function does not deref the pointer. + let err = unsafe { bindings::PTR_ERR(const_ptr) }; + // CAST: If `IS_ERR()` returns `true`, + // then `PTR_ERR()` is guaranteed to return a + // negative value greater-or-equal to `-bindings::MAX_ERRNO`, + // which always fits in an `i16`, as per the invariant above. + // And an `i16` always fits in an `i32`. So casting `err` to + // an `i32` can never overflow, and is always valid. + // + // SAFETY: `IS_ERR()` ensures `err` is a + // negative value greater-or-equal to `-bindings::MAX_ERRNO`. + #[allow(clippy::unnecessary_cast)] + return Err(unsafe { Error::from_errno_unchecked(err as core::ffi::c_int) }); + } + Ok(ptr) +} -- GitLab From ef4dc4cc7001e9cce8a3b556362171648be9ad92 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Mon, 3 Apr 2023 18:48:15 +0900 Subject: [PATCH 2755/5631] rust: error: Add from_result() helper Add a helper function to easily return C result codes from a Rust function that calls functions which return a Result. Lina: Imported from rust-for-linux/rust, originally developed by Wedson as part of file_operations.rs. Added the allow() flags since there is no user in the kernel crate yet and fixed a typo in a comment. Replaced the macro with a function taking a closure, per discussion on the ML. Co-developed-by: Fox Chen Signed-off-by: Fox Chen Co-developed-by: Miguel Ojeda Signed-off-by: Miguel Ojeda Signed-off-by: Wedson Almeida Filho Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230224-rust-error-v3-6-03779bddc02b@asahilina.net Signed-off-by: Miguel Ojeda --- rust/kernel/error.rs | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 67637b874267..5f4114b30b94 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -237,3 +237,42 @@ pub(crate) fn from_err_ptr(ptr: *mut T) -> Result<*mut T> { } Ok(ptr) } + +/// Calls a closure returning a [`crate::error::Result`] and converts the result to +/// a C integer result. +/// +/// This is useful when calling Rust functions that return [`crate::error::Result`] +/// from inside `extern "C"` functions that need to return an integer error result. +/// +/// `T` should be convertible from an `i16` via `From`. +/// +/// # Examples +/// +/// ```ignore +/// # use kernel::from_result; +/// # use kernel::bindings; +/// unsafe extern "C" fn probe_callback( +/// pdev: *mut bindings::platform_device, +/// ) -> core::ffi::c_int { +/// from_result(|| { +/// let ptr = devm_alloc(pdev)?; +/// bindings::platform_set_drvdata(pdev, ptr); +/// Ok(0) +/// }) +/// } +/// ``` +// TODO: Remove `dead_code` marker once an in-kernel client is available. +#[allow(dead_code)] +pub(crate) fn from_result(f: F) -> T +where + T: From, + F: FnOnce() -> Result, +{ + match f() { + Ok(v) => v, + // NO-OVERFLOW: negative `errno`s are no smaller than `-bindings::MAX_ERRNO`, + // `-bindings::MAX_ERRNO` fits in an `i16` as per invariant above, + // therefore a negative `errno` always fits in an `i16` and will not overflow. + Err(e) => T::from(e.to_errno() as i16), + } +} -- GitLab From 2d19d369c0c6dade11b8e3448c158655dbaa7b77 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:18 +0000 Subject: [PATCH 2756/5631] rust: enable the `pin_macro` feature This feature enables the use of the `pin!` macro for the `stack_pin_init!` macro. This feature is already stabilized in Rust version 1.68. Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Acked-by: Boqun Feng Link: https://lore.kernel.org/r/20230408122429.1103522-2-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/lib.rs | 1 + scripts/Makefile.build | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 1118cd3e0b5f..518559a0767e 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -18,6 +18,7 @@ #![feature(dispatch_from_dyn)] #![feature(generic_associated_types)] #![feature(new_uninit)] +#![feature(pin_macro)] #![feature(receiver_trait)] #![feature(unsize)] diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 1364e3d905fc..da70f68ba9e4 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -277,7 +277,7 @@ $(obj)/%.lst: $(src)/%.c FORCE # Compile Rust sources (.rs) # --------------------------------------------------------------------------- -rust_allowed_features := core_ffi_c,new_uninit +rust_allowed_features := core_ffi_c,new_uninit,pin_macro rust_common_cmd = \ RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ -- GitLab From 70a21e54a42232f1056db7f05a194f56e03e7d3e Mon Sep 17 00:00:00 2001 From: Gary Guo Date: Sat, 8 Apr 2023 12:25:23 +0000 Subject: [PATCH 2757/5631] rust: macros: add `quote!` macro Add the `quote!` macro for creating `TokenStream`s directly via the given Rust tokens. It also supports repetitions using iterators. It will be used by the pin-init API proc-macros to generate code. Signed-off-by: Gary Guo Signed-off-by: Benno Lossin Reviewed-by: Andreas Hindborg Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20230408122429.1103522-3-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/macros/lib.rs | 2 + rust/macros/quote.rs | 145 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 147 insertions(+) create mode 100644 rust/macros/quote.rs diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index c1d385e345b9..82b520f024dd 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -2,6 +2,8 @@ //! Crate for all kernel procedural macros. +#[macro_use] +mod quote; mod concat_idents; mod helpers; mod module; diff --git a/rust/macros/quote.rs b/rust/macros/quote.rs new file mode 100644 index 000000000000..94a6277182ee --- /dev/null +++ b/rust/macros/quote.rs @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use proc_macro::{TokenStream, TokenTree}; + +pub(crate) trait ToTokens { + fn to_tokens(&self, tokens: &mut TokenStream); +} + +impl ToTokens for Option { + fn to_tokens(&self, tokens: &mut TokenStream) { + if let Some(v) = self { + v.to_tokens(tokens); + } + } +} + +impl ToTokens for proc_macro::Group { + fn to_tokens(&self, tokens: &mut TokenStream) { + tokens.extend([TokenTree::from(self.clone())]); + } +} + +impl ToTokens for TokenTree { + fn to_tokens(&self, tokens: &mut TokenStream) { + tokens.extend([self.clone()]); + } +} + +impl ToTokens for TokenStream { + fn to_tokens(&self, tokens: &mut TokenStream) { + tokens.extend(self.clone()); + } +} + +/// Converts tokens into [`proc_macro::TokenStream`] and performs variable interpolations with +/// the given span. +/// +/// This is a similar to the +/// [`quote_spanned!`](https://docs.rs/quote/latest/quote/macro.quote_spanned.html) macro from the +/// `quote` crate but provides only just enough functionality needed by the current `macros` crate. +#[allow(unused_macros)] +macro_rules! quote_spanned { + ($span:expr => $($tt:tt)*) => { + #[allow(clippy::vec_init_then_push)] + { + let mut tokens = ::std::vec::Vec::new(); + let span = $span; + quote_spanned!(@proc tokens span $($tt)*); + ::proc_macro::TokenStream::from_iter(tokens) + }}; + (@proc $v:ident $span:ident) => {}; + (@proc $v:ident $span:ident #$id:ident $($tt:tt)*) => { + let mut ts = ::proc_macro::TokenStream::new(); + $crate::quote::ToTokens::to_tokens(&$id, &mut ts); + $v.extend(ts); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident #(#$id:ident)* $($tt:tt)*) => { + for token in $id { + let mut ts = ::proc_macro::TokenStream::new(); + $crate::quote::ToTokens::to_tokens(&token, &mut ts); + $v.extend(ts); + } + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident ( $($inner:tt)* ) $($tt:tt)*) => { + let mut tokens = ::std::vec::Vec::new(); + quote_spanned!(@proc tokens $span $($inner)*); + $v.push(::proc_macro::TokenTree::Group(::proc_macro::Group::new( + ::proc_macro::Delimiter::Parenthesis, + ::proc_macro::TokenStream::from_iter(tokens) + ))); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident [ $($inner:tt)* ] $($tt:tt)*) => { + let mut tokens = ::std::vec::Vec::new(); + quote_spanned!(@proc tokens $span $($inner)*); + $v.push(::proc_macro::TokenTree::Group(::proc_macro::Group::new( + ::proc_macro::Delimiter::Bracket, + ::proc_macro::TokenStream::from_iter(tokens) + ))); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident { $($inner:tt)* } $($tt:tt)*) => { + let mut tokens = ::std::vec::Vec::new(); + quote_spanned!(@proc tokens $span $($inner)*); + $v.push(::proc_macro::TokenTree::Group(::proc_macro::Group::new( + ::proc_macro::Delimiter::Brace, + ::proc_macro::TokenStream::from_iter(tokens) + ))); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident :: $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new(':', ::proc_macro::Spacing::Joint) + )); + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new(':', ::proc_macro::Spacing::Alone) + )); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident : $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new(':', ::proc_macro::Spacing::Alone) + )); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident , $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new(',', ::proc_macro::Spacing::Alone) + )); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident @ $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new('@', ::proc_macro::Spacing::Alone) + )); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident ! $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Punct( + ::proc_macro::Punct::new('!', ::proc_macro::Spacing::Alone) + )); + quote_spanned!(@proc $v $span $($tt)*); + }; + (@proc $v:ident $span:ident $id:ident $($tt:tt)*) => { + $v.push(::proc_macro::TokenTree::Ident(::proc_macro::Ident::new(stringify!($id), $span))); + quote_spanned!(@proc $v $span $($tt)*); + }; +} + +/// Converts tokens into [`proc_macro::TokenStream`] and performs variable interpolations with +/// mixed site span ([`Span::mixed_site()`]). +/// +/// This is a similar to the [`quote!`](https://docs.rs/quote/latest/quote/macro.quote.html) macro +/// from the `quote` crate but provides only just enough functionality needed by the current +/// `macros` crate. +/// +/// [`Span::mixed_site()`]: https://doc.rust-lang.org/proc_macro/struct.Span.html#method.mixed_site +#[allow(unused_macros)] +macro_rules! quote { + ($($tt:tt)*) => { + quote_spanned!(::proc_macro::Span::mixed_site() => $($tt)*) + } +} -- GitLab From d6dbca3592209d29c10e171224c34803805e88ca Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:29 +0000 Subject: [PATCH 2758/5631] rust: sync: change error type of constructor functions Change the error type of the constructors of `Arc` and `UniqueArc` to be `AllocError` instead of `Error`. This makes the API more clear as to what can go wrong when calling `try_new` or its variants. Signed-off-by: Benno Lossin Reviewed-by: Andreas Hindborg Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Link: https://lore.kernel.org/r/20230408122429.1103522-4-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/sync/arc.rs | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 8ce6d6bf478e..34d0e7cbe62e 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -17,11 +17,11 @@ use crate::{ bindings, - error::Result, types::{ForeignOwnable, Opaque}, }; use alloc::boxed::Box; use core::{ + alloc::AllocError, fmt, marker::{PhantomData, Unsize}, mem::{ManuallyDrop, MaybeUninit}, @@ -152,7 +152,7 @@ unsafe impl Sync for Arc {} impl Arc { /// Constructs a new reference counted instance of `T`. - pub fn try_new(contents: T) -> Result { + pub fn try_new(contents: T) -> Result { // INVARIANT: The refcount is initialised to a non-zero value. let value = ArcInner { // SAFETY: There are no safety requirements for this FFI call. @@ -472,7 +472,7 @@ pub struct UniqueArc { impl UniqueArc { /// Tries to allocate a new [`UniqueArc`] instance. - pub fn try_new(value: T) -> Result { + pub fn try_new(value: T) -> Result { Ok(Self { // INVARIANT: The newly-created object has a ref-count of 1. inner: Arc::try_new(value)?, @@ -480,7 +480,7 @@ impl UniqueArc { } /// Tries to allocate a new [`UniqueArc`] instance whose contents are not initialised yet. - pub fn try_new_uninit() -> Result>> { + pub fn try_new_uninit() -> Result>, AllocError> { Ok(UniqueArc::> { // INVARIANT: The newly-created object has a ref-count of 1. inner: Arc::try_new(MaybeUninit::uninit())?, -- GitLab From 3ff6e785ad99893f1d502156d23560efd30fec4d Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:39 +0000 Subject: [PATCH 2759/5631] rust: types: add `Opaque::raw_get` This function mirrors `UnsafeCell::raw_get`. It avoids creating a reference and allows solely using raw pointers. The `pin-init` API will be using this, since uninitialized memory requires raw pointers. Signed-off-by: Benno Lossin Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20230408122429.1103522-6-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/types.rs | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index 9d0fdbc55843..ff2b2fac951d 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -238,6 +238,14 @@ impl Opaque { pub fn get(&self) -> *mut T { UnsafeCell::raw_get(self.0.as_ptr()) } + + /// Gets the value behind `this`. + /// + /// This function is useful to get access to the value without creating intermediate + /// references. + pub const fn raw_get(this: *const Self) -> *mut T { + UnsafeCell::raw_get(this.cast::>()) + } } /// A sum type that always holds either a value of type `L` or `R`. -- GitLab From 90e53c5e70a69159ec255fec361f7dcf9cf36eae Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:45 +0000 Subject: [PATCH 2760/5631] rust: add pin-init API core This API is used to facilitate safe pinned initialization of structs. It replaces cumbersome `unsafe` manual initialization with elegant safe macro invocations. Due to the size of this change it has been split into six commits: 1. This commit introducing the basic public interface: traits and functions to represent and create initializers. 2. Adds the `#[pin_data]`, `pin_init!`, `try_pin_init!`, `init!` and `try_init!` macros along with their internal types. 3. Adds the `InPlaceInit` trait that allows using an initializer to create an object inside of a `Box` and other smart pointers. 4. Adds the `PinnedDrop` trait and adds macro support for it in the `#[pin_data]` macro. 5. Adds the `stack_pin_init!` macro allowing to pin-initialize a struct on the stack. 6. Adds the `Zeroable` trait and `init::zeroed` function to initialize types that have `0x00` in all bytes as a valid bit pattern. -- In this section the problem that the new pin-init API solves is outlined. This message describes the entirety of the API, not just the parts introduced in this commit. For a more granular explanation and additional information on pinning and this issue, view [1]. Pinning is Rust's way of enforcing the address stability of a value. When a value gets pinned it will be impossible for safe code to move it to another location. This is done by wrapping pointers to said object with `Pin

`. This wrapper prevents safe code from creating mutable references to the object, preventing mutable access, which is needed to move the value. `Pin

` provides `unsafe` functions to circumvent this and allow modifications regardless. It is then the programmer's responsibility to uphold the pinning guarantee. Many kernel data structures require a stable address, because there are foreign pointers to them which would get invalidated by moving the structure. Since these data structures are usually embedded in structs to use them, this pinning property propagates to the container struct. Resulting in most structs in both Rust and C code needing to be pinned. So if we want to have a `mutex` field in a Rust struct, this struct also needs to be pinned, because a `mutex` contains a `list_head`. Additionally initializing a `list_head` requires already having the final memory location available, because it is initialized by pointing it to itself. But this presents another challenge in Rust: values have to be initialized at all times. There is the `MaybeUninit` wrapper type, which allows handling uninitialized memory, but this requires using the `unsafe` raw pointers and a casting the type to the initialized variant. This problem gets exacerbated when considering encapsulation and the normal safety requirements of Rust code. The fields of the Rust `Mutex` should not be accessible to normal driver code. After all if anyone can modify the fields, there is no way to ensure the invariants of the `Mutex` are upheld. But if the fields are inaccessible, then initialization of a `Mutex` needs to be somehow achieved via a function or a macro. Because the `Mutex` must be pinned in memory, the function cannot return it by value. It also cannot allocate a `Box` to put the `Mutex` into, because that is an unnecessary allocation and indirection which would hurt performance. The solution in the rust tree (e.g. this commit: [2]) that is replaced by this API is to split this function into two parts: 1. A `new` function that returns a partially initialized `Mutex`, 2. An `init` function that requires the `Mutex` to be pinned and that fully initializes the `Mutex`. Both of these functions have to be marked `unsafe`, since a call to `new` needs to be accompanied with a call to `init`, otherwise using the `Mutex` could result in UB. And because calling `init` twice also is not safe. While `Mutex` initialization cannot fail, other structs might also have to allocate memory, which would result in conditional successful initialization requiring even more manual accommodation work. Combine this with the problem of pin-projections -- the way of accessing fields of a pinned struct -- which also have an `unsafe` API, pinned initialization is riddled with `unsafe` resulting in very poor ergonomics. Not only that, but also having to call two functions possibly multiple lines apart makes it very easy to forget it outright or during refactoring. Here is an example of the current way of initializing a struct with two synchronization primitives (see [3] for the full example): struct SharedState { state_changed: CondVar, inner: Mutex, } impl SharedState { fn try_new() -> Result> { let mut state = Pin::from(UniqueArc::try_new(Self { // SAFETY: `condvar_init!` is called below. state_changed: unsafe { CondVar::new() }, // SAFETY: `mutex_init!` is called below. inner: unsafe { Mutex::new(SharedStateInner { token_count: 0 }) }, })?); // SAFETY: `state_changed` is pinned when `state` is. let pinned = unsafe { state.as_mut().map_unchecked_mut(|s| &mut s.state_changed) }; kernel::condvar_init!(pinned, "SharedState::state_changed"); // SAFETY: `inner` is pinned when `state` is. let pinned = unsafe { state.as_mut().map_unchecked_mut(|s| &mut s.inner) }; kernel::mutex_init!(pinned, "SharedState::inner"); Ok(state.into()) } } The pin-init API of this patch solves this issue by providing a comprehensive solution comprised of macros and traits. Here is the example from above using the pin-init API: #[pin_data] struct SharedState { #[pin] state_changed: CondVar, #[pin] inner: Mutex, } impl SharedState { fn new() -> impl PinInit { pin_init!(Self { state_changed <- new_condvar!("SharedState::state_changed"), inner <- new_mutex!( SharedStateInner { token_count: 0 }, "SharedState::inner", ), }) } } Notably the way the macro is used here requires no `unsafe` and thus comes with the usual Rust promise of safe code not introducing any memory violations. Additionally it is now up to the caller of `new()` to decide the memory location of the `SharedState`. They can choose at the moment `Arc`, `Box` or the stack. -- The API has the following architecture: 1. Initializer traits `PinInit` and `Init` that act like closures. 2. Macros to create these initializer traits safely. 3. Functions to allow manually writing initializers. The initializers (an `impl PinInit`) receive a raw pointer pointing to uninitialized memory and their job is to fully initialize a `T` at that location. If initialization fails, they return an error (`E`) by value. This way of initializing cannot be safely exposed to the user, since it relies upon these properties outside of the control of the trait: - the memory location (slot) needs to be valid memory, - if initialization fails, the slot should not be read from, - the value in the slot should be pinned, so it cannot move and the memory cannot be deallocated until the value is dropped. This is why using an initializer is facilitated by another trait that ensures these requirements. These initializers can be created manually by just supplying a closure that fulfills the same safety requirements as `PinInit`. But this is an `unsafe` operation. To allow safe initializer creation, the `pin_init!` is provided along with three other variants: `try_pin_init!`, `try_init!` and `init!`. These take a modified struct initializer as a parameter and generate a closure that initializes the fields in sequence. The macros take great care in upholding the safety requirements: - A shadowed struct type is used as the return type of the closure instead of `()`. This is to prevent early returns, as these would prevent full initialization. - To ensure every field is only initialized once, a normal struct initializer is placed in unreachable code. The type checker will emit errors if a field is missing or specified multiple times. - When initializing a field fails, the whole initializer will fail and automatically drop fields that have been initialized earlier. - Only the correct initializer type is allowed for unpinned fields. You cannot use a `impl PinInit` to initialize a structurally not pinned field. To ensure the last point, an additional macro `#[pin_data]` is needed. This macro annotates the struct itself and the user specifies structurally pinned and not pinned fields. Because dropping a pinned struct is also not allowed to break the pinning invariants, another macro attribute `#[pinned_drop]` is needed. This macro is introduced in a following commit. These two macros also have mechanisms to ensure the overall safety of the API. Additionally, they utilize a combined proc-macro, declarative macro design: first a proc-macro enables the outer attribute syntax `#[...]` and does some important pre-parsing. Notably this prepares the generics such that the declarative macro can handle them using token trees. Then the actual parsing of the structure and the emission of code is handled by a declarative macro. For pin-projections the crates `pin-project` [4] and `pin-project-lite` [5] had been considered, but were ultimately rejected: - `pin-project` depends on `syn` [6] which is a very big dependency, around 50k lines of code. - `pin-project-lite` is a more reasonable 5k lines of code, but contains a very complex declarative macro to parse generics. On top of that it would require modification that would need to be maintained independently. Link: https://rust-for-linux.com/the-safe-pinned-initialization-problem [1] Link: https://github.com/Rust-for-Linux/linux/tree/0a04dc4ddd671efb87eef54dde0fb38e9074f4be [2] Link: https://github.com/Rust-for-Linux/linux/blob/f509ede33fc10a07eba3da14aa00302bd4b5dddd/samples/rust/rust_miscdev.rs [3] Link: https://crates.io/crates/pin-project [4] Link: https://crates.io/crates/pin-project-lite [5] Link: https://crates.io/crates/syn [6] Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Wedson Almeida Filho Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-7-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 187 +++++++++++++++++++++++++++++++++ rust/kernel/init/__internal.rs | 33 ++++++ rust/kernel/lib.rs | 6 ++ scripts/Makefile.build | 2 +- 4 files changed, 227 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/init.rs create mode 100644 rust/kernel/init/__internal.rs diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs new file mode 100644 index 000000000000..d041f0daf71e --- /dev/null +++ b/rust/kernel/init.rs @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! API to safely and fallibly initialize pinned `struct`s using in-place constructors. +//! +//! It also allows in-place initialization of big `struct`s that would otherwise produce a stack +//! overflow. +//! +//! Most `struct`s from the [`sync`] module need to be pinned, because they contain self-referential +//! `struct`s from C. [Pinning][pinning] is Rust's way of ensuring data does not move. +//! +//! # Overview +//! +//! To initialize a `struct` with an in-place constructor you will need two things: +//! - an in-place constructor, +//! - a memory location that can hold your `struct`. +//! +//! To get an in-place constructor there are generally two options: +//! - a custom function/macro returning an in-place constructor provided by someone else, +//! - using the unsafe function [`pin_init_from_closure()`] to manually create an initializer. +//! +//! Aside from pinned initialization, this API also supports in-place construction without pinning, +//! the macros/types/functions are generally named like the pinned variants without the `pin` +//! prefix. +//! +//! [`sync`]: kernel::sync +//! [pinning]: https://doc.rust-lang.org/std/pin/index.html +//! [structurally pinned fields]: +//! https://doc.rust-lang.org/std/pin/index.html#pinning-is-structural-for-field +//! [`Arc`]: crate::sync::Arc +//! [`impl PinInit`]: PinInit +//! [`impl PinInit`]: PinInit +//! [`impl Init`]: Init +//! [`Opaque`]: kernel::types::Opaque +//! [`pin_data`]: ::macros::pin_data +//! [`UniqueArc`]: kernel::sync::UniqueArc +//! [`Box`]: alloc::boxed::Box + +use core::{convert::Infallible, marker::PhantomData, mem::MaybeUninit}; + +#[doc(hidden)] +pub mod __internal; + +/// A pin-initializer for the type `T`. +/// +/// To use this initializer, you will need a suitable memory location that can hold a `T`. This can +/// be [`Box`], [`Arc`], [`UniqueArc`]. +/// +/// Also see the [module description](self). +/// +/// # Safety +/// +/// When implementing this type you will need to take great care. Also there are probably very few +/// cases where a manual implementation is necessary. Use [`pin_init_from_closure`] where possible. +/// +/// The [`PinInit::__pinned_init`] function +/// - returns `Ok(())` if it initialized every field of `slot`, +/// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means: +/// - `slot` can be deallocated without UB occurring, +/// - `slot` does not need to be dropped, +/// - `slot` is not partially initialized. +/// - while constructing the `T` at `slot` it upholds the pinning invariants of `T`. +/// +/// [`Arc`]: crate::sync::Arc +/// [`Arc::pin_init`]: crate::sync::Arc::pin_init +/// [`UniqueArc`]: kernel::sync::UniqueArc +/// [`Box`]: alloc::boxed::Box +#[must_use = "An initializer must be used in order to create its value."] +pub unsafe trait PinInit: Sized { + /// Initializes `slot`. + /// + /// # Safety + /// + /// - `slot` is a valid pointer to uninitialized memory. + /// - the caller does not touch `slot` when `Err` is returned, they are only permitted to + /// deallocate. + /// - `slot` will not move until it is dropped, i.e. it will be pinned. + unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E>; +} + +/// An initializer for `T`. +/// +/// To use this initializer, you will need a suitable memory location that can hold a `T`. This can +/// be [`Box`], [`Arc`], [`UniqueArc`]. Because [`PinInit`] is a super trait, you can +/// use every function that takes it as well. +/// +/// Also see the [module description](self). +/// +/// # Safety +/// +/// When implementing this type you will need to take great care. Also there are probably very few +/// cases where a manual implementation is necessary. Use [`init_from_closure`] where possible. +/// +/// The [`Init::__init`] function +/// - returns `Ok(())` if it initialized every field of `slot`, +/// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means: +/// - `slot` can be deallocated without UB occurring, +/// - `slot` does not need to be dropped, +/// - `slot` is not partially initialized. +/// - while constructing the `T` at `slot` it upholds the pinning invariants of `T`. +/// +/// The `__pinned_init` function from the supertrait [`PinInit`] needs to execute the exact same +/// code as `__init`. +/// +/// Contrary to its supertype [`PinInit`] the caller is allowed to +/// move the pointee after initialization. +/// +/// [`Arc`]: crate::sync::Arc +/// [`UniqueArc`]: kernel::sync::UniqueArc +/// [`Box`]: alloc::boxed::Box +#[must_use = "An initializer must be used in order to create its value."] +pub unsafe trait Init: Sized { + /// Initializes `slot`. + /// + /// # Safety + /// + /// - `slot` is a valid pointer to uninitialized memory. + /// - the caller does not touch `slot` when `Err` is returned, they are only permitted to + /// deallocate. + unsafe fn __init(self, slot: *mut T) -> Result<(), E>; +} + +// SAFETY: Every in-place initializer can also be used as a pin-initializer. +unsafe impl PinInit for I +where + I: Init, +{ + unsafe fn __pinned_init(self, slot: *mut T) -> Result<(), E> { + // SAFETY: `__init` meets the same requirements as `__pinned_init`, except that it does not + // require `slot` to not move after init. + unsafe { self.__init(slot) } + } +} + +/// Creates a new [`PinInit`] from the given closure. +/// +/// # Safety +/// +/// The closure: +/// - returns `Ok(())` if it initialized every field of `slot`, +/// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means: +/// - `slot` can be deallocated without UB occurring, +/// - `slot` does not need to be dropped, +/// - `slot` is not partially initialized. +/// - may assume that the `slot` does not move if `T: !Unpin`, +/// - while constructing the `T` at `slot` it upholds the pinning invariants of `T`. +#[inline] +pub const unsafe fn pin_init_from_closure( + f: impl FnOnce(*mut T) -> Result<(), E>, +) -> impl PinInit { + __internal::InitClosure(f, PhantomData) +} + +/// Creates a new [`Init`] from the given closure. +/// +/// # Safety +/// +/// The closure: +/// - returns `Ok(())` if it initialized every field of `slot`, +/// - returns `Err(err)` if it encountered an error and then cleaned `slot`, this means: +/// - `slot` can be deallocated without UB occurring, +/// - `slot` does not need to be dropped, +/// - `slot` is not partially initialized. +/// - the `slot` may move after initialization. +/// - while constructing the `T` at `slot` it upholds the pinning invariants of `T`. +#[inline] +pub const unsafe fn init_from_closure( + f: impl FnOnce(*mut T) -> Result<(), E>, +) -> impl Init { + __internal::InitClosure(f, PhantomData) +} + +/// An initializer that leaves the memory uninitialized. +/// +/// The initializer is a no-op. The `slot` memory is not changed. +#[inline] +pub fn uninit() -> impl Init, E> { + // SAFETY: The memory is allowed to be uninitialized. + unsafe { init_from_closure(|_| Ok(())) } +} + +// SAFETY: Every type can be initialized by-value. +unsafe impl Init for T { + unsafe fn __init(self, slot: *mut T) -> Result<(), Infallible> { + unsafe { slot.write(self) }; + Ok(()) + } +} diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs new file mode 100644 index 000000000000..08cbb5333438 --- /dev/null +++ b/rust/kernel/init/__internal.rs @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! This module contains API-internal items for pin-init. +//! +//! These items must not be used outside of +//! - `kernel/init.rs` +//! - `macros/pin_data.rs` +//! - `macros/pinned_drop.rs` + +use super::*; + +/// See the [nomicon] for what subtyping is. See also [this table]. +/// +/// [nomicon]: https://doc.rust-lang.org/nomicon/subtyping.html +/// [this table]: https://doc.rust-lang.org/nomicon/phantom-data.html#table-of-phantomdata-patterns +type Invariant = PhantomData *mut T>; + +/// This is the module-internal type implementing `PinInit` and `Init`. It is unsafe to create this +/// type, since the closure needs to fulfill the same safety requirement as the +/// `__pinned_init`/`__init` functions. +pub(crate) struct InitClosure(pub(crate) F, pub(crate) Invariant<(E, T)>); + +// SAFETY: While constructing the `InitClosure`, the user promised that it upholds the +// `__init` invariants. +unsafe impl Init for InitClosure +where + F: FnOnce(*mut T) -> Result<(), E>, +{ + #[inline] + unsafe fn __init(self, slot: *mut T) -> Result<(), E> { + (self.0)(slot) + } +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 518559a0767e..821bd067151c 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -16,6 +16,7 @@ #![feature(coerce_unsized)] #![feature(core_ffi_c)] #![feature(dispatch_from_dyn)] +#![feature(explicit_generic_args_with_impl_trait)] #![feature(generic_associated_types)] #![feature(new_uninit)] #![feature(pin_macro)] @@ -27,11 +28,16 @@ #[cfg(not(CONFIG_RUST))] compile_error!("Missing kernel configuration for conditional compilation"); +#[allow(unused_extern_crates)] +// Allow proc-macros to refer to `::kernel` inside the `kernel` crate (this crate). +extern crate self as kernel; + #[cfg(not(test))] #[cfg(not(testlib))] mod allocator; mod build_assert; pub mod error; +pub mod init; pub mod prelude; pub mod print; mod static_assert; diff --git a/scripts/Makefile.build b/scripts/Makefile.build index da70f68ba9e4..9f94fc83f086 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -277,7 +277,7 @@ $(obj)/%.lst: $(src)/%.c FORCE # Compile Rust sources (.rs) # --------------------------------------------------------------------------- -rust_allowed_features := core_ffi_c,new_uninit,pin_macro +rust_allowed_features := core_ffi_c,explicit_generic_args_with_impl_trait,new_uninit,pin_macro rust_common_cmd = \ RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ -- GitLab From fc6c6baa1f40ded13e539d0c1a17bcefc00abad9 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:51 +0000 Subject: [PATCH 2761/5631] rust: init: add initialization macros Add the following initializer macros: - `#[pin_data]` to annotate structurally pinned fields of structs, needed for `pin_init!` and `try_pin_init!` to select the correct initializer of fields. - `pin_init!` create a pin-initializer for a struct with the `Infallible` error type. - `try_pin_init!` create a pin-initializer for a struct with a custom error type (`kernel::error::Error` is the default). - `init!` create an in-place-initializer for a struct with the `Infallible` error type. - `try_init!` create an in-place-initializer for a struct with a custom error type (`kernel::error::Error` is the default). Also add their needed internal helper traits and structs. Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-8-y86-dev@protonmail.com [ Fixed three typos. ] Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 807 ++++++++++++++++++++++++++++++++- rust/kernel/init/__internal.rs | 130 ++++++ rust/kernel/init/macros.rs | 707 +++++++++++++++++++++++++++++ rust/macros/lib.rs | 29 ++ rust/macros/pin_data.rs | 79 ++++ rust/macros/quote.rs | 2 - 6 files changed, 1747 insertions(+), 7 deletions(-) create mode 100644 rust/kernel/init/macros.rs create mode 100644 rust/macros/pin_data.rs diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index d041f0daf71e..ecef0376d726 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -14,7 +14,8 @@ //! - an in-place constructor, //! - a memory location that can hold your `struct`. //! -//! To get an in-place constructor there are generally two options: +//! To get an in-place constructor there are generally three options: +//! - directly creating an in-place constructor using the [`pin_init!`] macro, //! - a custom function/macro returning an in-place constructor provided by someone else, //! - using the unsafe function [`pin_init_from_closure()`] to manually create an initializer. //! @@ -22,6 +23,87 @@ //! the macros/types/functions are generally named like the pinned variants without the `pin` //! prefix. //! +//! # Examples +//! +//! ## Using the [`pin_init!`] macro +//! +//! If you want to use [`PinInit`], then you will have to annotate your `struct` with +//! `#[`[`pin_data`]`]`. It is a macro that uses `#[pin]` as a marker for +//! [structurally pinned fields]. After doing this, you can then create an in-place constructor via +//! [`pin_init!`]. The syntax is almost the same as normal `struct` initializers. The difference is +//! that you need to write `<-` instead of `:` for fields that you want to initialize in-place. +//! +//! ```rust +//! # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +//! use kernel::{prelude::*, sync::Mutex, new_mutex}; +//! # use core::pin::Pin; +//! #[pin_data] +//! struct Foo { +//! #[pin] +//! a: Mutex, +//! b: u32, +//! } +//! +//! let foo = pin_init!(Foo { +//! a <- new_mutex!(42, "Foo::a"), +//! b: 24, +//! }); +//! ``` +//! +//! `foo` now is of the type [`impl PinInit`]. We can now use any smart pointer that we like +//! (or just the stack) to actually initialize a `Foo`: +//! +//! ```rust +//! # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +//! # use kernel::{prelude::*, sync::Mutex, new_mutex}; +//! # use core::pin::Pin; +//! # #[pin_data] +//! # struct Foo { +//! # #[pin] +//! # a: Mutex, +//! # b: u32, +//! # } +//! # let foo = pin_init!(Foo { +//! # a <- new_mutex!(42, "Foo::a"), +//! # b: 24, +//! # }); +//! let foo: Result>> = Box::pin_init(foo); +//! ``` +//! +//! For more information see the [`pin_init!`] macro. +//! +//! ## Using a custom function/macro that returns an initializer +//! +//! Many types from the kernel supply a function/macro that returns an initializer, because the +//! above method only works for types where you can access the fields. +//! +//! ```rust +//! # use kernel::{new_mutex, sync::{Arc, Mutex}}; +//! let mtx: Result>> = Arc::pin_init(new_mutex!(42, "example::mtx")); +//! ``` +//! +//! To declare an init macro/function you just return an [`impl PinInit`]: +//! +//! ```rust +//! # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +//! # use kernel::{sync::Mutex, prelude::*, new_mutex, init::PinInit, try_pin_init}; +//! #[pin_data] +//! struct DriverData { +//! #[pin] +//! status: Mutex, +//! buffer: Box<[u8; 1_000_000]>, +//! } +//! +//! impl DriverData { +//! fn new() -> impl PinInit { +//! try_pin_init!(Self { +//! status <- new_mutex!(0, "DriverData::status"), +//! buffer: Box::init(kernel::init::zeroed())?, +//! }) +//! } +//! } +//! ``` +//! //! [`sync`]: kernel::sync //! [pinning]: https://doc.rust-lang.org/std/pin/index.html //! [structurally pinned fields]: @@ -33,12 +115,729 @@ //! [`Opaque`]: kernel::types::Opaque //! [`pin_data`]: ::macros::pin_data //! [`UniqueArc`]: kernel::sync::UniqueArc -//! [`Box`]: alloc::boxed::Box -use core::{convert::Infallible, marker::PhantomData, mem::MaybeUninit}; +use alloc::boxed::Box; +use core::{cell::Cell, convert::Infallible, marker::PhantomData, mem::MaybeUninit, ptr}; #[doc(hidden)] pub mod __internal; +#[doc(hidden)] +pub mod macros; + +/// Construct an in-place, pinned initializer for `struct`s. +/// +/// This macro defaults the error to [`Infallible`]. If you need [`Error`], then use +/// [`try_pin_init!`]. +/// +/// The syntax is almost identical to that of a normal `struct` initializer: +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, macros::pin_data, init::*}; +/// # use core::pin::Pin; +/// #[pin_data] +/// struct Foo { +/// a: usize, +/// b: Bar, +/// } +/// +/// #[pin_data] +/// struct Bar { +/// x: u32, +/// } +/// +/// # fn demo() -> impl PinInit { +/// let a = 42; +/// +/// let initializer = pin_init!(Foo { +/// a, +/// b: Bar { +/// x: 64, +/// }, +/// }); +/// # initializer } +/// # Box::pin_init(demo()).unwrap(); +/// ``` +/// +/// Arbitrary Rust expressions can be used to set the value of a variable. +/// +/// The fields are initialized in the order that they appear in the initializer. So it is possible +/// to read already initialized fields using raw pointers. +/// +/// IMPORTANT: You are not allowed to create references to fields of the struct inside of the +/// initializer. +/// +/// # Init-functions +/// +/// When working with this API it is often desired to let others construct your types without +/// giving access to all fields. This is where you would normally write a plain function `new` +/// that would return a new instance of your type. With this API that is also possible. +/// However, there are a few extra things to keep in mind. +/// +/// To create an initializer function, simply declare it like this: +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, prelude::*, init::*}; +/// # use core::pin::Pin; +/// # #[pin_data] +/// # struct Foo { +/// # a: usize, +/// # b: Bar, +/// # } +/// # #[pin_data] +/// # struct Bar { +/// # x: u32, +/// # } +/// impl Foo { +/// fn new() -> impl PinInit { +/// pin_init!(Self { +/// a: 42, +/// b: Bar { +/// x: 64, +/// }, +/// }) +/// } +/// } +/// ``` +/// +/// Users of `Foo` can now create it like this: +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, macros::pin_data, init::*}; +/// # use core::pin::Pin; +/// # #[pin_data] +/// # struct Foo { +/// # a: usize, +/// # b: Bar, +/// # } +/// # #[pin_data] +/// # struct Bar { +/// # x: u32, +/// # } +/// # impl Foo { +/// # fn new() -> impl PinInit { +/// # pin_init!(Self { +/// # a: 42, +/// # b: Bar { +/// # x: 64, +/// # }, +/// # }) +/// # } +/// # } +/// let foo = Box::pin_init(Foo::new()); +/// ``` +/// +/// They can also easily embed it into their own `struct`s: +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, macros::pin_data, init::*}; +/// # use core::pin::Pin; +/// # #[pin_data] +/// # struct Foo { +/// # a: usize, +/// # b: Bar, +/// # } +/// # #[pin_data] +/// # struct Bar { +/// # x: u32, +/// # } +/// # impl Foo { +/// # fn new() -> impl PinInit { +/// # pin_init!(Self { +/// # a: 42, +/// # b: Bar { +/// # x: 64, +/// # }, +/// # }) +/// # } +/// # } +/// #[pin_data] +/// struct FooContainer { +/// #[pin] +/// foo1: Foo, +/// #[pin] +/// foo2: Foo, +/// other: u32, +/// } +/// +/// impl FooContainer { +/// fn new(other: u32) -> impl PinInit { +/// pin_init!(Self { +/// foo1 <- Foo::new(), +/// foo2 <- Foo::new(), +/// other, +/// }) +/// } +/// } +/// ``` +/// +/// Here we see that when using `pin_init!` with `PinInit`, one needs to write `<-` instead of `:`. +/// This signifies that the given field is initialized in-place. As with `struct` initializers, just +/// writing the field (in this case `other`) without `:` or `<-` means `other: other,`. +/// +/// # Syntax +/// +/// As already mentioned in the examples above, inside of `pin_init!` a `struct` initializer with +/// the following modifications is expected: +/// - Fields that you want to initialize in-place have to use `<-` instead of `:`. +/// - In front of the initializer you can write `&this in` to have access to a [`NonNull`] +/// pointer named `this` inside of the initializer. +/// +/// For instance: +/// +/// ```rust +/// # use kernel::pin_init; +/// # use macros::pin_data; +/// # use core::{ptr::addr_of_mut, marker::PhantomPinned}; +/// #[pin_data] +/// struct Buf { +/// // `ptr` points into `buf`. +/// ptr: *mut u8, +/// buf: [u8; 64], +/// #[pin] +/// pin: PhantomPinned, +/// } +/// pin_init!(&this in Buf { +/// buf: [0; 64], +/// ptr: unsafe { addr_of_mut!((*this.as_ptr()).buf).cast() }, +/// pin: PhantomPinned, +/// }); +/// ``` +/// +/// [`try_pin_init!`]: kernel::try_pin_init +/// [`NonNull`]: core::ptr::NonNull +/// [`Error`]: kernel::error::Error +// For a detailed example of how this macro works, see the module documentation of the hidden +// module `__internal` inside of `init/__internal.rs`. +#[macro_export] +macro_rules! pin_init { + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }) => { + $crate::try_pin_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)?), + @fields($($fields)*), + @error(::core::convert::Infallible), + ) + }; +} + +/// Construct an in-place, fallible pinned initializer for `struct`s. +/// +/// If the initialization can complete without error (or [`Infallible`]), then use [`pin_init!`]. +/// +/// You can use the `?` operator or use `return Err(err)` inside the initializer to stop +/// initialization and return the error. +/// +/// IMPORTANT: if you have `unsafe` code inside of the initializer you have to ensure that when +/// initialization fails, the memory can be safely deallocated without any further modifications. +/// +/// This macro defaults the error to [`Error`]. +/// +/// The syntax is identical to [`pin_init!`] with the following exception: you can append `? $type` +/// after the `struct` initializer to specify the error type you want to use. +/// +/// # Examples +/// +/// ```rust +/// # #![feature(new_uninit)] +/// use kernel::{init::{self, PinInit}, error::Error}; +/// #[pin_data] +/// struct BigBuf { +/// big: Box<[u8; 1024 * 1024 * 1024]>, +/// small: [u8; 1024 * 1024], +/// ptr: *mut u8, +/// } +/// +/// impl BigBuf { +/// fn new() -> impl PinInit { +/// try_pin_init!(Self { +/// big: Box::init(init::zeroed())?, +/// small: [0; 1024 * 1024], +/// ptr: core::ptr::null_mut(), +/// }? Error) +/// } +/// } +/// ``` +/// +/// [`Error`]: kernel::error::Error +// For a detailed example of how this macro works, see the module documentation of the hidden +// module `__internal` inside of `init/__internal.rs`. +#[macro_export] +macro_rules! try_pin_init { + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }) => { + $crate::try_pin_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)? ), + @fields($($fields)*), + @error($crate::error::Error), + ) + }; + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }? $err:ty) => { + $crate::try_pin_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)? ), + @fields($($fields)*), + @error($err), + ) + }; + ( + @this($($this:ident)?), + @typ($t:ident $(::<$($generics:ty),*>)?), + @fields($($fields:tt)*), + @error($err:ty), + ) => {{ + // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return + // type and shadow it later when we insert the arbitrary user code. That way there will be + // no possibility of returning without `unsafe`. + struct __InitOk; + // Get the pin data from the supplied type. + let data = unsafe { + use $crate::init::__internal::HasPinData; + $t$(::<$($generics),*>)?::__pin_data() + }; + // Ensure that `data` really is of type `PinData` and help with type inference: + let init = $crate::init::__internal::PinData::make_closure::<_, __InitOk, $err>( + data, + move |slot| { + { + // Shadow the structure so it cannot be used to return early. + struct __InitOk; + // Create the `this` so it can be referenced by the user inside of the + // expressions creating the individual fields. + $(let $this = unsafe { ::core::ptr::NonNull::new_unchecked(slot) };)? + // Initialize every field. + $crate::try_pin_init!(init_slot: + @data(data), + @slot(slot), + @munch_fields($($fields)*,), + ); + // We use unreachable code to ensure that all fields have been mentioned exactly + // once, this struct initializer will still be type-checked and complain with a + // very natural error message if a field is forgotten/mentioned more than once. + #[allow(unreachable_code, clippy::diverging_sub_expression)] + if false { + $crate::try_pin_init!(make_initializer: + @slot(slot), + @type_name($t), + @munch_fields($($fields)*,), + @acc(), + ); + } + // Forget all guards, since initialization was a success. + $crate::try_pin_init!(forget_guards: + @munch_fields($($fields)*,), + ); + } + Ok(__InitOk) + } + ); + let init = move |slot| -> ::core::result::Result<(), $err> { + init(slot).map(|__InitOk| ()) + }; + let init = unsafe { $crate::init::pin_init_from_closure::<_, $err>(init) }; + init + }}; + (init_slot: + @data($data:ident), + @slot($slot:ident), + @munch_fields($(,)?), + ) => { + // Endpoint of munching, no fields are left. + }; + (init_slot: + @data($data:ident), + @slot($slot:ident), + // In-place initialization syntax. + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + ) => { + let $field = $val; + // Call the initializer. + // + // SAFETY: `slot` is valid, because we are inside of an initializer closure, we + // return when an error/panic occurs. + // We also use the `data` to require the correct trait (`Init` or `PinInit`) for `$field`. + unsafe { $data.$field(::core::ptr::addr_of_mut!((*$slot).$field), $field)? }; + // Create the drop guard. + // + // We only give access to `&DropGuard`, so it cannot be forgotten via safe code. + // + // SAFETY: We forget the guard later when initialization has succeeded. + let $field = &unsafe { + $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + }; + + $crate::try_pin_init!(init_slot: + @data($data), + @slot($slot), + @munch_fields($($rest)*), + ); + }; + (init_slot: + @data($data:ident), + @slot($slot:ident), + // Direct value init, this is safe for every field. + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + ) => { + $(let $field = $val;)? + // Initialize the field. + // + // SAFETY: The memory at `slot` is uninitialized. + unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; + // Create the drop guard: + // + // We only give access to `&DropGuard`, so it cannot be accidentally forgotten. + // + // SAFETY: We forget the guard later when initialization has succeeded. + let $field = &unsafe { + $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + }; + + $crate::try_pin_init!(init_slot: + @data($data), + @slot($slot), + @munch_fields($($rest)*), + ); + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields($(,)?), + @acc($($acc:tt)*), + ) => { + // Endpoint, nothing more to munch, create the initializer. + // Since we are in the `if false` branch, this will never get executed. We abuse `slot` to + // get the correct type inference here: + unsafe { + ::core::ptr::write($slot, $t { + $($acc)* + }); + } + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + @acc($($acc:tt)*), + ) => { + $crate::try_pin_init!(make_initializer: + @slot($slot), + @type_name($t), + @munch_fields($($rest)*), + @acc($($acc)* $field: ::core::panic!(),), + ); + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + @acc($($acc:tt)*), + ) => { + $crate::try_pin_init!(make_initializer: + @slot($slot), + @type_name($t), + @munch_fields($($rest)*), + @acc($($acc)* $field: ::core::panic!(),), + ); + }; + (forget_guards: + @munch_fields($(,)?), + ) => { + // Munching finished. + }; + (forget_guards: + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + ) => { + unsafe { $crate::init::__internal::DropGuard::forget($field) }; + + $crate::try_pin_init!(forget_guards: + @munch_fields($($rest)*), + ); + }; + (forget_guards: + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + ) => { + unsafe { $crate::init::__internal::DropGuard::forget($field) }; + + $crate::try_pin_init!(forget_guards: + @munch_fields($($rest)*), + ); + }; +} + +/// Construct an in-place initializer for `struct`s. +/// +/// This macro defaults the error to [`Infallible`]. If you need [`Error`], then use +/// [`try_init!`]. +/// +/// The syntax is identical to [`pin_init!`] and its safety caveats also apply: +/// - `unsafe` code must guarantee either full initialization or return an error and allow +/// deallocation of the memory. +/// - the fields are initialized in the order given in the initializer. +/// - no references to fields are allowed to be created inside of the initializer. +/// +/// This initializer is for initializing data in-place that might later be moved. If you want to +/// pin-initialize, use [`pin_init!`]. +/// +/// [`Error`]: kernel::error::Error +// For a detailed example of how this macro works, see the module documentation of the hidden +// module `__internal` inside of `init/__internal.rs`. +#[macro_export] +macro_rules! init { + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }) => { + $crate::try_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)?), + @fields($($fields)*), + @error(::core::convert::Infallible), + ) + } +} + +/// Construct an in-place fallible initializer for `struct`s. +/// +/// This macro defaults the error to [`Error`]. If you need [`Infallible`], then use +/// [`init!`]. +/// +/// The syntax is identical to [`try_pin_init!`]. If you want to specify a custom error, +/// append `? $type` after the `struct` initializer. +/// The safety caveats from [`try_pin_init!`] also apply: +/// - `unsafe` code must guarantee either full initialization or return an error and allow +/// deallocation of the memory. +/// - the fields are initialized in the order given in the initializer. +/// - no references to fields are allowed to be created inside of the initializer. +/// +/// # Examples +/// +/// ```rust +/// use kernel::{init::PinInit, error::Error, InPlaceInit}; +/// struct BigBuf { +/// big: Box<[u8; 1024 * 1024 * 1024]>, +/// small: [u8; 1024 * 1024], +/// } +/// +/// impl BigBuf { +/// fn new() -> impl Init { +/// try_init!(Self { +/// big: Box::init(zeroed())?, +/// small: [0; 1024 * 1024], +/// }? Error) +/// } +/// } +/// ``` +/// +/// [`Error`]: kernel::error::Error +// For a detailed example of how this macro works, see the module documentation of the hidden +// module `__internal` inside of `init/__internal.rs`. +#[macro_export] +macro_rules! try_init { + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }) => { + $crate::try_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)?), + @fields($($fields)*), + @error($crate::error::Error), + ) + }; + ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { + $($fields:tt)* + }? $err:ty) => { + $crate::try_init!( + @this($($this)?), + @typ($t $(::<$($generics),*>)?), + @fields($($fields)*), + @error($err), + ) + }; + ( + @this($($this:ident)?), + @typ($t:ident $(::<$($generics:ty),*>)?), + @fields($($fields:tt)*), + @error($err:ty), + ) => {{ + // We do not want to allow arbitrary returns, so we declare this type as the `Ok` return + // type and shadow it later when we insert the arbitrary user code. That way there will be + // no possibility of returning without `unsafe`. + struct __InitOk; + // Get the init data from the supplied type. + let data = unsafe { + use $crate::init::__internal::HasInitData; + $t$(::<$($generics),*>)?::__init_data() + }; + // Ensure that `data` really is of type `InitData` and help with type inference: + let init = $crate::init::__internal::InitData::make_closure::<_, __InitOk, $err>( + data, + move |slot| { + { + // Shadow the structure so it cannot be used to return early. + struct __InitOk; + // Create the `this` so it can be referenced by the user inside of the + // expressions creating the individual fields. + $(let $this = unsafe { ::core::ptr::NonNull::new_unchecked(slot) };)? + // Initialize every field. + $crate::try_init!(init_slot: + @slot(slot), + @munch_fields($($fields)*,), + ); + // We use unreachable code to ensure that all fields have been mentioned exactly + // once, this struct initializer will still be type-checked and complain with a + // very natural error message if a field is forgotten/mentioned more than once. + #[allow(unreachable_code, clippy::diverging_sub_expression)] + if false { + $crate::try_init!(make_initializer: + @slot(slot), + @type_name($t), + @munch_fields($($fields)*,), + @acc(), + ); + } + // Forget all guards, since initialization was a success. + $crate::try_init!(forget_guards: + @munch_fields($($fields)*,), + ); + } + Ok(__InitOk) + } + ); + let init = move |slot| -> ::core::result::Result<(), $err> { + init(slot).map(|__InitOk| ()) + }; + let init = unsafe { $crate::init::init_from_closure::<_, $err>(init) }; + init + }}; + (init_slot: + @slot($slot:ident), + @munch_fields( $(,)?), + ) => { + // Endpoint of munching, no fields are left. + }; + (init_slot: + @slot($slot:ident), + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + ) => { + let $field = $val; + // Call the initializer. + // + // SAFETY: `slot` is valid, because we are inside of an initializer closure, we + // return when an error/panic occurs. + unsafe { + $crate::init::Init::__init($field, ::core::ptr::addr_of_mut!((*$slot).$field))?; + } + // Create the drop guard. + // + // We only give access to `&DropGuard`, so it cannot be accidentally forgotten. + // + // SAFETY: We forget the guard later when initialization has succeeded. + let $field = &unsafe { + $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + }; + + $crate::try_init!(init_slot: + @slot($slot), + @munch_fields($($rest)*), + ); + }; + (init_slot: + @slot($slot:ident), + // Direct value init. + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + ) => { + $(let $field = $val;)? + // Call the initializer. + // + // SAFETY: The memory at `slot` is uninitialized. + unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; + // Create the drop guard. + // + // We only give access to `&DropGuard`, so it cannot be accidentally forgotten. + // + // SAFETY: We forget the guard later when initialization has succeeded. + let $field = &unsafe { + $crate::init::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + }; + + $crate::try_init!(init_slot: + @slot($slot), + @munch_fields($($rest)*), + ); + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields( $(,)?), + @acc($($acc:tt)*), + ) => { + // Endpoint, nothing more to munch, create the initializer. + // Since we are in the `if false` branch, this will never get executed. We abuse `slot` to + // get the correct type inference here: + unsafe { + ::core::ptr::write($slot, $t { + $($acc)* + }); + } + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + @acc($($acc:tt)*), + ) => { + $crate::try_init!(make_initializer: + @slot($slot), + @type_name($t), + @munch_fields($($rest)*), + @acc($($acc)*$field: ::core::panic!(),), + ); + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:ident), + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + @acc($($acc:tt)*), + ) => { + $crate::try_init!(make_initializer: + @slot($slot), + @type_name($t), + @munch_fields($($rest)*), + @acc($($acc)*$field: ::core::panic!(),), + ); + }; + (forget_guards: + @munch_fields($(,)?), + ) => { + // Munching finished. + }; + (forget_guards: + @munch_fields($field:ident <- $val:expr, $($rest:tt)*), + ) => { + unsafe { $crate::init::__internal::DropGuard::forget($field) }; + + $crate::try_init!(forget_guards: + @munch_fields($($rest)*), + ); + }; + (forget_guards: + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + ) => { + unsafe { $crate::init::__internal::DropGuard::forget($field) }; + + $crate::try_init!(forget_guards: + @munch_fields($($rest)*), + ); + }; +} /// A pin-initializer for the type `T`. /// @@ -63,7 +862,6 @@ pub mod __internal; /// [`Arc`]: crate::sync::Arc /// [`Arc::pin_init`]: crate::sync::Arc::pin_init /// [`UniqueArc`]: kernel::sync::UniqueArc -/// [`Box`]: alloc::boxed::Box #[must_use = "An initializer must be used in order to create its value."] pub unsafe trait PinInit: Sized { /// Initializes `slot`. @@ -106,7 +904,6 @@ pub unsafe trait PinInit: Sized { /// /// [`Arc`]: crate::sync::Arc /// [`UniqueArc`]: kernel::sync::UniqueArc -/// [`Box`]: alloc::boxed::Box #[must_use = "An initializer must be used in order to create its value."] pub unsafe trait Init: Sized { /// Initializes `slot`. diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs index 08cbb5333438..a3389a684296 100644 --- a/rust/kernel/init/__internal.rs +++ b/rust/kernel/init/__internal.rs @@ -31,3 +31,133 @@ where (self.0)(slot) } } + +/// This trait is only implemented via the `#[pin_data]` proc-macro. It is used to facilitate +/// the pin projections within the initializers. +/// +/// # Safety +/// +/// Only the `init` module is allowed to use this trait. +pub unsafe trait HasPinData { + type PinData: PinData; + + unsafe fn __pin_data() -> Self::PinData; +} + +/// Marker trait for pinning data of structs. +/// +/// # Safety +/// +/// Only the `init` module is allowed to use this trait. +pub unsafe trait PinData: Copy { + type Datee: ?Sized + HasPinData; + + /// Type inference helper function. + fn make_closure(self, f: F) -> F + where + F: FnOnce(*mut Self::Datee) -> Result, + { + f + } +} + +/// This trait is automatically implemented for every type. It aims to provide the same type +/// inference help as `HasPinData`. +/// +/// # Safety +/// +/// Only the `init` module is allowed to use this trait. +pub unsafe trait HasInitData { + type InitData: InitData; + + unsafe fn __init_data() -> Self::InitData; +} + +/// Same function as `PinData`, but for arbitrary data. +/// +/// # Safety +/// +/// Only the `init` module is allowed to use this trait. +pub unsafe trait InitData: Copy { + type Datee: ?Sized + HasInitData; + + /// Type inference helper function. + fn make_closure(self, f: F) -> F + where + F: FnOnce(*mut Self::Datee) -> Result, + { + f + } +} + +pub struct AllData(PhantomData) -> Box>); + +impl Clone for AllData { + fn clone(&self) -> Self { + *self + } +} + +impl Copy for AllData {} + +unsafe impl InitData for AllData { + type Datee = T; +} + +unsafe impl HasInitData for T { + type InitData = AllData; + + unsafe fn __init_data() -> Self::InitData { + AllData(PhantomData) + } +} + +/// When a value of this type is dropped, it drops a `T`. +/// +/// Can be forgotten to prevent the drop. +pub struct DropGuard { + ptr: *mut T, + do_drop: Cell, +} + +impl DropGuard { + /// Creates a new [`DropGuard`]. It will [`ptr::drop_in_place`] `ptr` when it gets dropped. + /// + /// # Safety + /// + /// `ptr` must be a valid pointer. + /// + /// It is the callers responsibility that `self` will only get dropped if the pointee of `ptr`: + /// - has not been dropped, + /// - is not accessible by any other means, + /// - will not be dropped by any other means. + #[inline] + pub unsafe fn new(ptr: *mut T) -> Self { + Self { + ptr, + do_drop: Cell::new(true), + } + } + + /// Prevents this guard from dropping the supplied pointer. + /// + /// # Safety + /// + /// This function is unsafe in order to prevent safe code from forgetting this guard. It should + /// only be called by the macros in this module. + #[inline] + pub unsafe fn forget(&self) { + self.do_drop.set(false); + } +} + +impl Drop for DropGuard { + #[inline] + fn drop(&mut self) { + if self.do_drop.get() { + // SAFETY: A `DropGuard` can only be constructed using the unsafe `new` function + // ensuring that this operation is safe. + unsafe { ptr::drop_in_place(self.ptr) } + } + } +} diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs new file mode 100644 index 000000000000..9ef02f5411a6 --- /dev/null +++ b/rust/kernel/init/macros.rs @@ -0,0 +1,707 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! This module provides the macros that actually implement the proc-macros `pin_data` and +//! `pinned_drop`. +//! +//! These macros should never be called directly, since they expect their input to be +//! in a certain format which is internal. Use the proc-macros instead. +//! +//! This architecture has been chosen because the kernel does not yet have access to `syn` which +//! would make matters a lot easier for implementing these as proc-macros. +//! +//! # Macro expansion example +//! +//! This section is intended for readers trying to understand the macros in this module and the +//! `pin_init!` macros from `init.rs`. +//! +//! We will look at the following example: +//! +//! ```rust +//! # use kernel::init::*; +//! #[pin_data] +//! #[repr(C)] +//! struct Bar { +//! #[pin] +//! t: T, +//! pub x: usize, +//! } +//! +//! impl Bar { +//! fn new(t: T) -> impl PinInit { +//! pin_init!(Self { t, x: 0 }) +//! } +//! } +//! ``` +//! +//! This example includes the most common and important features of the pin-init API. +//! +//! Below you can find individual section about the different macro invocations. Here are some +//! general things we need to take into account when designing macros: +//! - use global paths, similarly to file paths, these start with the separator: `::core::panic!()` +//! this ensures that the correct item is used, since users could define their own `mod core {}` +//! and then their own `panic!` inside to execute arbitrary code inside of our macro. +//! - macro `unsafe` hygiene: we need to ensure that we do not expand arbitrary, user-supplied +//! expressions inside of an `unsafe` block in the macro, because this would allow users to do +//! `unsafe` operations without an associated `unsafe` block. +//! +//! ## `#[pin_data]` on `Bar` +//! +//! This macro is used to specify which fields are structurally pinned and which fields are not. It +//! is placed on the struct definition and allows `#[pin]` to be placed on the fields. +//! +//! Here is the definition of `Bar` from our example: +//! +//! ```rust +//! # use kernel::init::*; +//! #[pin_data] +//! #[repr(C)] +//! struct Bar { +//! t: T, +//! pub x: usize, +//! } +//! ``` +//! +//! This expands to the following code: +//! +//! ```rust +//! // Firstly the normal definition of the struct, attributes are preserved: +//! #[repr(C)] +//! struct Bar { +//! t: T, +//! pub x: usize, +//! } +//! // Then an anonymous constant is defined, this is because we do not want any code to access the +//! // types that we define inside: +//! const _: () = { +//! // We define the pin-data carrying struct, it is a ZST and needs to have the same generics, +//! // since we need to implement access functions for each field and thus need to know its +//! // type. +//! struct __ThePinData { +//! __phantom: ::core::marker::PhantomData) -> Bar>, +//! } +//! // We implement `Copy` for the pin-data struct, since all functions it defines will take +//! // `self` by value. +//! impl ::core::clone::Clone for __ThePinData { +//! fn clone(&self) -> Self { +//! *self +//! } +//! } +//! impl ::core::marker::Copy for __ThePinData {} +//! // For every field of `Bar`, the pin-data struct will define a function with the same name +//! // and accessor (`pub` or `pub(crate)` etc.). This function will take a pointer to the +//! // field (`slot`) and a `PinInit` or `Init` depending on the projection kind of the field +//! // (if pinning is structural for the field, then `PinInit` otherwise `Init`). +//! #[allow(dead_code)] +//! impl __ThePinData { +//! unsafe fn t( +//! self, +//! slot: *mut T, +//! init: impl ::kernel::init::Init, +//! ) -> ::core::result::Result<(), E> { +//! unsafe { ::kernel::init::Init::__init(init, slot) } +//! } +//! pub unsafe fn x( +//! self, +//! slot: *mut usize, +//! init: impl ::kernel::init::Init, +//! ) -> ::core::result::Result<(), E> { +//! unsafe { ::kernel::init::Init::__init(init, slot) } +//! } +//! } +//! // Implement the internal `HasPinData` trait that associates `Bar` with the pin-data struct +//! // that we constructed beforehand. +//! unsafe impl ::kernel::init::__internal::HasPinData for Bar { +//! type PinData = __ThePinData; +//! unsafe fn __pin_data() -> Self::PinData { +//! __ThePinData { +//! __phantom: ::core::marker::PhantomData, +//! } +//! } +//! } +//! // Implement the internal `PinData` trait that marks the pin-data struct as a pin-data +//! // struct. This is important to ensure that no user can implement a rouge `__pin_data` +//! // function without using `unsafe`. +//! unsafe impl ::kernel::init::__internal::PinData for __ThePinData { +//! type Datee = Bar; +//! } +//! // Now we only want to implement `Unpin` for `Bar` when every structurally pinned field is +//! // `Unpin`. In other words, whether `Bar` is `Unpin` only depends on structurally pinned +//! // fields (those marked with `#[pin]`). These fields will be listed in this struct, in our +//! // case no such fields exist, hence this is almost empty. The two phantomdata fields exist +//! // for two reasons: +//! // - `__phantom`: every generic must be used, since we cannot really know which generics +//! // are used, we declere all and then use everything here once. +//! // - `__phantom_pin`: uses the `'__pin` lifetime and ensures that this struct is invariant +//! // over it. The lifetime is needed to work around the limitation that trait bounds must +//! // not be trivial, e.g. the user has a `#[pin] PhantomPinned` field -- this is +//! // unconditionally `!Unpin` and results in an error. The lifetime tricks the compiler +//! // into accepting these bounds regardless. +//! #[allow(dead_code)] +//! struct __Unpin<'__pin, T> { +//! __phantom_pin: ::core::marker::PhantomData &'__pin ()>, +//! __phantom: ::core::marker::PhantomData) -> Bar>, +//! } +//! #[doc(hidden)] +//! impl<'__pin, T> +//! ::core::marker::Unpin for Bar where __Unpin<'__pin, T>: ::core::marker::Unpin {} +//! // Now we need to ensure that `Bar` does not implement `Drop`, since that would give users +//! // access to `&mut self` inside of `drop` even if the struct was pinned. This could lead to +//! // UB with only safe code, so we disallow this by giving a trait implementation error using +//! // a direct impl and a blanket implementation. +//! trait MustNotImplDrop {} +//! // Normally `Drop` bounds do not have the correct semantics, but for this purpose they do +//! // (normally people want to know if a type has any kind of drop glue at all, here we want +//! // to know if it has any kind of custom drop glue, which is exactly what this bound does). +//! #[allow(drop_bounds)] +//! impl MustNotImplDrop for T {} +//! impl MustNotImplDrop for Bar {} +//! }; +//! ``` +//! +//! ## `pin_init!` in `impl Bar` +//! +//! This macro creates an pin-initializer for the given struct. It requires that the struct is +//! annotated by `#[pin_data]`. +//! +//! Here is the impl on `Bar` defining the new function: +//! +//! ```rust +//! impl Bar { +//! fn new(t: T) -> impl PinInit { +//! pin_init!(Self { t, x: 0 }) +//! } +//! } +//! ``` +//! +//! This expands to the following code: +//! +//! ```rust +//! impl Bar { +//! fn new(t: T) -> impl PinInit { +//! { +//! // We do not want to allow arbitrary returns, so we declare this type as the `Ok` +//! // return type and shadow it later when we insert the arbitrary user code. That way +//! // there will be no possibility of returning without `unsafe`. +//! struct __InitOk; +//! // Get the pin-data type from the initialized type. +//! // - the function is unsafe, hence the unsafe block +//! // - we `use` the `HasPinData` trait in the block, it is only available in that +//! // scope. +//! let data = unsafe { +//! use ::kernel::init::__internal::HasPinData; +//! Self::__pin_data() +//! }; +//! // Use `data` to help with type inference, the closure supplied will have the type +//! // `FnOnce(*mut Self) -> Result<__InitOk, Infallible>`. +//! let init = ::kernel::init::__internal::PinData::make_closure::< +//! _, +//! __InitOk, +//! ::core::convert::Infallible, +//! >(data, move |slot| { +//! { +//! // Shadow the structure so it cannot be used to return early. If a user +//! // tries to write `return Ok(__InitOk)`, then they get a type error, since +//! // that will refer to this struct instead of the one defined above. +//! struct __InitOk; +//! // This is the expansion of `t,`, which is syntactic sugar for `t: t,`. +//! unsafe { ::core::ptr::write(&raw mut (*slot).t, t) }; +//! // Since initialization could fail later (not in this case, since the error +//! // type is `Infallible`) we will need to drop this field if it fails. This +//! // `DropGuard` will drop the field when it gets dropped and has not yet +//! // been forgotten. We make a reference to it, so users cannot `mem::forget` +//! // it from the initializer, since the name is the same as the field. +//! let t = &unsafe { +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).t) +//! }; +//! // Expansion of `x: 0,`: +//! // Since this can be an arbitrary expression we cannot place it inside of +//! // the `unsafe` block, so we bind it here. +//! let x = 0; +//! unsafe { ::core::ptr::write(&raw mut (*slot).x, x) }; +//! let x = &unsafe { +//! ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).x) +//! }; +//! +//! // Here we use the type checker to ensuer that every field has been +//! // initialized exactly once, since this is `if false` it will never get +//! // executed, but still type-checked. +//! // Additionally we abuse `slot` to automatically infer the correct type for +//! // the struct. This is also another check that every field is accessible +//! // from this scope. +//! #[allow(unreachable_code, clippy::diverging_sub_expression)] +//! if false { +//! unsafe { +//! ::core::ptr::write( +//! slot, +//! Self { +//! // We only care about typecheck finding every field here, +//! // the expression does not matter, just conjure one using +//! // `panic!()`: +//! t: ::core::panic!(), +//! x: ::core::panic!(), +//! }, +//! ); +//! }; +//! } +//! // Since initialization has successfully completed, we can now forget the +//! // guards. +//! unsafe { ::kernel::init::__internal::DropGuard::forget(t) }; +//! unsafe { ::kernel::init::__internal::DropGuard::forget(x) }; +//! } +//! // We leave the scope above and gain access to the previously shadowed +//! // `__InitOk` that we need to return. +//! Ok(__InitOk) +//! }); +//! // Change the return type of the closure. +//! let init = move |slot| -> ::core::result::Result<(), ::core::convert::Infallible> { +//! init(slot).map(|__InitOk| ()) +//! }; +//! // Construct the initializer. +//! let init = unsafe { +//! ::kernel::init::pin_init_from_closure::<_, ::core::convert::Infallible>(init) +//! }; +//! init +//! } +//! } +//! } +//! ``` + +/// This macro first parses the struct definition such that it separates pinned and not pinned +/// fields. Afterwards it declares the struct and implement the `PinData` trait safely. +#[doc(hidden)] +#[macro_export] +macro_rules! __pin_data { + // Proc-macro entry point, this is supplied by the proc-macro pre-parsing. + (parse_input: + @args($($pinned_drop:ident)?), + @sig( + $(#[$($struct_attr:tt)*])* + $vis:vis struct $name:ident + $(where $($whr:tt)*)? + ), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @body({ $($fields:tt)* }), + ) => { + // We now use token munching to iterate through all of the fields. While doing this we + // identify fields marked with `#[pin]`, these fields are the 'pinned fields'. The user + // wants these to be structurally pinned. The rest of the fields are the + // 'not pinned fields'. Additionally we collect all fields, since we need them in the right + // order to declare the struct. + // + // In this call we also put some explaining comments for the parameters. + $crate::__pin_data!(find_pinned_fields: + // Attributes on the struct itself, these will just be propagated to be put onto the + // struct definition. + @struct_attrs($(#[$($struct_attr)*])*), + // The visibility of the struct. + @vis($vis), + // The name of the struct. + @name($name), + // The 'impl generics', the generics that will need to be specified on the struct inside + // of an `impl<$ty_generics>` block. + @impl_generics($($impl_generics)*), + // The 'ty generics', the generics that will need to be specified on the impl blocks. + @ty_generics($($ty_generics)*), + // The where clause of any impl block and the declaration. + @where($($($whr)*)?), + // The remaining fields tokens that need to be processed. + // We add a `,` at the end to ensure correct parsing. + @fields_munch($($fields)* ,), + // The pinned fields. + @pinned(), + // The not pinned fields. + @not_pinned(), + // All fields. + @fields(), + // The accumulator containing all attributes already parsed. + @accum(), + // Contains `yes` or `` to indicate if `#[pin]` was found on the current field. + @is_pinned(), + // The proc-macro argument, this should be `PinnedDrop` or ``. + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We found a PhantomPinned field, this should generally be pinned! + @fields_munch($field:ident : $($($(::)?core::)?marker::)?PhantomPinned, $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + // This field is not pinned. + @is_pinned(), + @pinned_drop($($pinned_drop:ident)?), + ) => { + ::core::compile_error!(concat!( + "The field `", + stringify!($field), + "` of type `PhantomPinned` only has an effect, if it has the `#[pin]` attribute.", + )); + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($($rest)*), + @pinned($($pinned)* $($accum)* $field: ::core::marker::PhantomPinned,), + @not_pinned($($not_pinned)*), + @fields($($fields)* $($accum)* $field: ::core::marker::PhantomPinned,), + @accum(), + @is_pinned(), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We reached the field declaration. + @fields_munch($field:ident : $type:ty, $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + // This field is pinned. + @is_pinned(yes), + @pinned_drop($($pinned_drop:ident)?), + ) => { + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($($rest)*), + @pinned($($pinned)* $($accum)* $field: $type,), + @not_pinned($($not_pinned)*), + @fields($($fields)* $($accum)* $field: $type,), + @accum(), + @is_pinned(), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We reached the field declaration. + @fields_munch($field:ident : $type:ty, $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + // This field is not pinned. + @is_pinned(), + @pinned_drop($($pinned_drop:ident)?), + ) => { + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($($rest)*), + @pinned($($pinned)*), + @not_pinned($($not_pinned)* $($accum)* $field: $type,), + @fields($($fields)* $($accum)* $field: $type,), + @accum(), + @is_pinned(), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We found the `#[pin]` attr. + @fields_munch(#[pin] $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + @is_pinned($($is_pinned:ident)?), + @pinned_drop($($pinned_drop:ident)?), + ) => { + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($($rest)*), + // We do not include `#[pin]` in the list of attributes, since it is not actually an + // attribute that is defined somewhere. + @pinned($($pinned)*), + @not_pinned($($not_pinned)*), + @fields($($fields)*), + @accum($($accum)*), + // Set this to `yes`. + @is_pinned(yes), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We reached the field declaration with visibility, for simplicity we only munch the + // visibility and put it into `$accum`. + @fields_munch($fvis:vis $field:ident $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + @is_pinned($($is_pinned:ident)?), + @pinned_drop($($pinned_drop:ident)?), + ) => { + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($field $($rest)*), + @pinned($($pinned)*), + @not_pinned($($not_pinned)*), + @fields($($fields)*), + @accum($($accum)* $fvis), + @is_pinned($($is_pinned)?), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // Some other attribute, just put it into `$accum`. + @fields_munch(#[$($attr:tt)*] $($rest:tt)*), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum($($accum:tt)*), + @is_pinned($($is_pinned:ident)?), + @pinned_drop($($pinned_drop:ident)?), + ) => { + $crate::__pin_data!(find_pinned_fields: + @struct_attrs($($struct_attrs)*), + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @fields_munch($($rest)*), + @pinned($($pinned)*), + @not_pinned($($not_pinned)*), + @fields($($fields)*), + @accum($($accum)* #[$($attr)*]), + @is_pinned($($is_pinned)?), + @pinned_drop($($pinned_drop)?), + ); + }; + (find_pinned_fields: + @struct_attrs($($struct_attrs:tt)*), + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + // We reached the end of the fields, plus an optional additional comma, since we added one + // before and the user is also allowed to put a trailing comma. + @fields_munch($(,)?), + @pinned($($pinned:tt)*), + @not_pinned($($not_pinned:tt)*), + @fields($($fields:tt)*), + @accum(), + @is_pinned(), + @pinned_drop($($pinned_drop:ident)?), + ) => { + // Declare the struct with all fields in the correct order. + $($struct_attrs)* + $vis struct $name <$($impl_generics)*> + where $($whr)* + { + $($fields)* + } + + // We put the rest into this const item, because it then will not be accessible to anything + // outside. + const _: () = { + // We declare this struct which will host all of the projection function for our type. + // it will be invariant over all generic parameters which are inherited from the + // struct. + $vis struct __ThePinData<$($impl_generics)*> + where $($whr)* + { + __phantom: ::core::marker::PhantomData< + fn($name<$($ty_generics)*>) -> $name<$($ty_generics)*> + >, + } + + impl<$($impl_generics)*> ::core::clone::Clone for __ThePinData<$($ty_generics)*> + where $($whr)* + { + fn clone(&self) -> Self { *self } + } + + impl<$($impl_generics)*> ::core::marker::Copy for __ThePinData<$($ty_generics)*> + where $($whr)* + {} + + // Make all projection functions. + $crate::__pin_data!(make_pin_data: + @pin_data(__ThePinData), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @pinned($($pinned)*), + @not_pinned($($not_pinned)*), + ); + + // SAFETY: We have added the correct projection functions above to `__ThePinData` and + // we also use the least restrictive generics possible. + unsafe impl<$($impl_generics)*> + $crate::init::__internal::HasPinData for $name<$($ty_generics)*> + where $($whr)* + { + type PinData = __ThePinData<$($ty_generics)*>; + + unsafe fn __pin_data() -> Self::PinData { + __ThePinData { __phantom: ::core::marker::PhantomData } + } + } + + unsafe impl<$($impl_generics)*> + $crate::init::__internal::PinData for __ThePinData<$($ty_generics)*> + where $($whr)* + { + type Datee = $name<$($ty_generics)*>; + } + + // This struct will be used for the unpin analysis. Since only structurally pinned + // fields are relevant whether the struct should implement `Unpin`. + #[allow(dead_code)] + struct __Unpin <'__pin, $($impl_generics)*> + where $($whr)* + { + __phantom_pin: ::core::marker::PhantomData &'__pin ()>, + __phantom: ::core::marker::PhantomData< + fn($name<$($ty_generics)*>) -> $name<$($ty_generics)*> + >, + // Only the pinned fields. + $($pinned)* + } + + #[doc(hidden)] + impl<'__pin, $($impl_generics)*> ::core::marker::Unpin for $name<$($ty_generics)*> + where + __Unpin<'__pin, $($ty_generics)*>: ::core::marker::Unpin, + $($whr)* + {} + + // We need to disallow normal `Drop` implementation, the exact behavior depends on + // whether `PinnedDrop` was specified as the parameter. + $crate::__pin_data!(drop_prevention: + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @where($($whr)*), + @pinned_drop($($pinned_drop)?), + ); + }; + }; + // When no `PinnedDrop` was specified, then we have to prevent implementing drop. + (drop_prevention: + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + @pinned_drop(), + ) => { + // We prevent this by creating a trait that will be implemented for all types implementing + // `Drop`. Additionally we will implement this trait for the struct leading to a conflict, + // if it also implements `Drop` + trait MustNotImplDrop {} + #[allow(drop_bounds)] + impl MustNotImplDrop for T {} + impl<$($impl_generics)*> MustNotImplDrop for $name<$($ty_generics)*> + where $($whr)* {} + }; + // If some other parameter was specified, we emit a readable error. + (drop_prevention: + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + @pinned_drop($($rest:tt)*), + ) => { + compile_error!( + "Wrong parameters to `#[pin_data]`, expected nothing or `PinnedDrop`, got '{}'.", + stringify!($($rest)*), + ); + }; + (make_pin_data: + @pin_data($pin_data:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + @pinned($($(#[$($p_attr:tt)*])* $pvis:vis $p_field:ident : $p_type:ty),* $(,)?), + @not_pinned($($(#[$($attr:tt)*])* $fvis:vis $field:ident : $type:ty),* $(,)?), + ) => { + // For every field, we create a projection function according to its projection type. If a + // field is structurally pinned, then it must be initialized via `PinInit`, if it is not + // structurally pinned, then it can be initialized via `Init`. + // + // The functions are `unsafe` to prevent accidentally calling them. + #[allow(dead_code)] + impl<$($impl_generics)*> $pin_data<$($ty_generics)*> + where $($whr)* + { + $( + $pvis unsafe fn $p_field( + self, + slot: *mut $p_type, + init: impl $crate::init::PinInit<$p_type, E>, + ) -> ::core::result::Result<(), E> { + unsafe { $crate::init::PinInit::__pinned_init(init, slot) } + } + )* + $( + $fvis unsafe fn $field( + self, + slot: *mut $type, + init: impl $crate::init::Init<$type, E>, + ) -> ::core::result::Result<(), E> { + unsafe { $crate::init::Init::__init(init, slot) } + } + )* + } + }; +} diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 82b520f024dd..6d84f2fd0d77 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -7,6 +7,7 @@ mod quote; mod concat_idents; mod helpers; mod module; +mod pin_data; mod vtable; use proc_macro::TokenStream; @@ -168,3 +169,31 @@ pub fn vtable(attr: TokenStream, ts: TokenStream) -> TokenStream { pub fn concat_idents(ts: TokenStream) -> TokenStream { concat_idents::concat_idents(ts) } + +/// Used to specify the pinning information of the fields of a struct. +/// +/// This is somewhat similar in purpose as +/// [pin-project-lite](https://crates.io/crates/pin-project-lite). +/// Place this macro on a struct definition and then `#[pin]` in front of the attributes of each +/// field you want to structurally pin. +/// +/// This macro enables the use of the [`pin_init!`] macro. When pin-initializing a `struct`, +/// then `#[pin]` directs the type of initializer that is required. +/// +/// # Examples +/// +/// ```rust,ignore +/// #[pin_data] +/// struct DriverData { +/// #[pin] +/// queue: Mutex>, +/// buf: Box<[u8; 1024 * 1024]>, +/// } +/// ``` +/// +/// [`pin_init!`]: ../kernel/macro.pin_init.html +// ^ cannot use direct link, since `kernel` is not a dependency of `macros`. +#[proc_macro_attribute] +pub fn pin_data(inner: TokenStream, item: TokenStream) -> TokenStream { + pin_data::pin_data(inner, item) +} diff --git a/rust/macros/pin_data.rs b/rust/macros/pin_data.rs new file mode 100644 index 000000000000..954149d77181 --- /dev/null +++ b/rust/macros/pin_data.rs @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use proc_macro::{Punct, Spacing, TokenStream, TokenTree}; + +pub(crate) fn pin_data(args: TokenStream, input: TokenStream) -> TokenStream { + // This proc-macro only does some pre-parsing and then delegates the actual parsing to + // `kernel::__pin_data!`. + // + // In here we only collect the generics, since parsing them in declarative macros is very + // elaborate. We also do not need to analyse their structure, we only need to collect them. + + // `impl_generics`, the declared generics with their bounds. + let mut impl_generics = vec![]; + // Only the names of the generics, without any bounds. + let mut ty_generics = vec![]; + // Tokens not related to the generics e.g. the `impl` token. + let mut rest = vec![]; + // The current level of `<`. + let mut nesting = 0; + let mut toks = input.into_iter(); + // If we are at the beginning of a generic parameter. + let mut at_start = true; + for tt in &mut toks { + match tt.clone() { + TokenTree::Punct(p) if p.as_char() == '<' => { + if nesting >= 1 { + impl_generics.push(tt); + } + nesting += 1; + } + TokenTree::Punct(p) if p.as_char() == '>' => { + if nesting == 0 { + break; + } else { + nesting -= 1; + if nesting >= 1 { + impl_generics.push(tt); + } + if nesting == 0 { + break; + } + } + } + tt => { + if nesting == 1 { + match &tt { + TokenTree::Ident(i) if i.to_string() == "const" => {} + TokenTree::Ident(_) if at_start => { + ty_generics.push(tt.clone()); + ty_generics.push(TokenTree::Punct(Punct::new(',', Spacing::Alone))); + at_start = false; + } + TokenTree::Punct(p) if p.as_char() == ',' => at_start = true, + TokenTree::Punct(p) if p.as_char() == '\'' && at_start => { + ty_generics.push(tt.clone()); + } + _ => {} + } + } + if nesting >= 1 { + impl_generics.push(tt); + } else if nesting == 0 { + rest.push(tt); + } + } + } + } + rest.extend(toks); + // This should be the body of the struct `{...}`. + let last = rest.pop(); + quote!(::kernel::__pin_data! { + parse_input: + @args(#args), + @sig(#(#rest)*), + @impl_generics(#(#impl_generics)*), + @ty_generics(#(#ty_generics)*), + @body(#last), + }) +} diff --git a/rust/macros/quote.rs b/rust/macros/quote.rs index 94a6277182ee..c8e08b3c1e4c 100644 --- a/rust/macros/quote.rs +++ b/rust/macros/quote.rs @@ -38,7 +38,6 @@ impl ToTokens for TokenStream { /// This is a similar to the /// [`quote_spanned!`](https://docs.rs/quote/latest/quote/macro.quote_spanned.html) macro from the /// `quote` crate but provides only just enough functionality needed by the current `macros` crate. -#[allow(unused_macros)] macro_rules! quote_spanned { ($span:expr => $($tt:tt)*) => { #[allow(clippy::vec_init_then_push)] @@ -137,7 +136,6 @@ macro_rules! quote_spanned { /// `macros` crate. /// /// [`Span::mixed_site()`]: https://doc.rust-lang.org/proc_macro/struct.Span.html#method.mixed_site -#[allow(unused_macros)] macro_rules! quote { ($($tt:tt)*) => { quote_spanned!(::proc_macro::Span::mixed_site() => $($tt)*) -- GitLab From 92c4a1e7e81cc775b2ad6bedb348098230f7ed87 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:25:56 +0000 Subject: [PATCH 2762/5631] rust: init/sync: add `InPlaceInit` trait to pin-initialize smart pointers The `InPlaceInit` trait that provides two functions, for initializing using `PinInit` and `Init`. It is implemented by `Arc`, `UniqueArc` and `Box`. Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-9-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 128 ++++++++++++++++++++++++++++++++++++---- rust/kernel/sync/arc.rs | 24 ++++++++ 2 files changed, 139 insertions(+), 13 deletions(-) diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index ecef0376d726..6499cf5c9c20 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -114,10 +114,16 @@ //! [`impl Init`]: Init //! [`Opaque`]: kernel::types::Opaque //! [`pin_data`]: ::macros::pin_data -//! [`UniqueArc`]: kernel::sync::UniqueArc +use crate::{ + error::{self, Error}, + sync::UniqueArc, +}; use alloc::boxed::Box; -use core::{cell::Cell, convert::Infallible, marker::PhantomData, mem::MaybeUninit, ptr}; +use core::{ + alloc::AllocError, cell::Cell, convert::Infallible, marker::PhantomData, mem::MaybeUninit, + pin::Pin, ptr, +}; #[doc(hidden)] pub mod __internal; @@ -309,7 +315,6 @@ pub mod macros; /// /// [`try_pin_init!`]: kernel::try_pin_init /// [`NonNull`]: core::ptr::NonNull -/// [`Error`]: kernel::error::Error // For a detailed example of how this macro works, see the module documentation of the hidden // module `__internal` inside of `init/__internal.rs`. #[macro_export] @@ -363,8 +368,6 @@ macro_rules! pin_init { /// } /// } /// ``` -/// -/// [`Error`]: kernel::error::Error // For a detailed example of how this macro works, see the module documentation of the hidden // module `__internal` inside of `init/__internal.rs`. #[macro_export] @@ -586,8 +589,6 @@ macro_rules! try_pin_init { /// /// This initializer is for initializing data in-place that might later be moved. If you want to /// pin-initialize, use [`pin_init!`]. -/// -/// [`Error`]: kernel::error::Error // For a detailed example of how this macro works, see the module documentation of the hidden // module `__internal` inside of `init/__internal.rs`. #[macro_export] @@ -635,8 +636,6 @@ macro_rules! init { /// } /// } /// ``` -/// -/// [`Error`]: kernel::error::Error // For a detailed example of how this macro works, see the module documentation of the hidden // module `__internal` inside of `init/__internal.rs`. #[macro_export] @@ -842,7 +841,8 @@ macro_rules! try_init { /// A pin-initializer for the type `T`. /// /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can -/// be [`Box`], [`Arc`], [`UniqueArc`]. +/// be [`Box`], [`Arc`], [`UniqueArc`]. Use the [`InPlaceInit::pin_init`] function of a +/// smart pointer like [`Arc`] on this. /// /// Also see the [module description](self). /// @@ -861,7 +861,6 @@ macro_rules! try_init { /// /// [`Arc`]: crate::sync::Arc /// [`Arc::pin_init`]: crate::sync::Arc::pin_init -/// [`UniqueArc`]: kernel::sync::UniqueArc #[must_use = "An initializer must be used in order to create its value."] pub unsafe trait PinInit: Sized { /// Initializes `slot`. @@ -878,7 +877,8 @@ pub unsafe trait PinInit: Sized { /// An initializer for `T`. /// /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can -/// be [`Box`], [`Arc`], [`UniqueArc`]. Because [`PinInit`] is a super trait, you can +/// be [`Box`], [`Arc`], [`UniqueArc`]. Use the [`InPlaceInit::init`] function of a smart +/// pointer like [`Arc`] on this. Because [`PinInit`] is a super trait, you can /// use every function that takes it as well. /// /// Also see the [module description](self). @@ -903,7 +903,6 @@ pub unsafe trait PinInit: Sized { /// move the pointee after initialization. /// /// [`Arc`]: crate::sync::Arc -/// [`UniqueArc`]: kernel::sync::UniqueArc #[must_use = "An initializer must be used in order to create its value."] pub unsafe trait Init: Sized { /// Initializes `slot`. @@ -982,3 +981,106 @@ unsafe impl Init for T { Ok(()) } } + +/// Smart pointer that can initialize memory in-place. +pub trait InPlaceInit: Sized { + /// Use the given pin-initializer to pin-initialize a `T` inside of a new smart pointer of this + /// type. + /// + /// If `T: !Unpin` it will not be able to move afterwards. + fn try_pin_init(init: impl PinInit) -> Result, E> + where + E: From; + + /// Use the given pin-initializer to pin-initialize a `T` inside of a new smart pointer of this + /// type. + /// + /// If `T: !Unpin` it will not be able to move afterwards. + fn pin_init(init: impl PinInit) -> error::Result> + where + Error: From, + { + // SAFETY: We delegate to `init` and only change the error type. + let init = unsafe { + pin_init_from_closure(|slot| init.__pinned_init(slot).map_err(|e| Error::from(e))) + }; + Self::try_pin_init(init) + } + + /// Use the given initializer to in-place initialize a `T`. + fn try_init(init: impl Init) -> Result + where + E: From; + + /// Use the given initializer to in-place initialize a `T`. + fn init(init: impl Init) -> error::Result + where + Error: From, + { + // SAFETY: We delegate to `init` and only change the error type. + let init = unsafe { + init_from_closure(|slot| init.__pinned_init(slot).map_err(|e| Error::from(e))) + }; + Self::try_init(init) + } +} + +impl InPlaceInit for Box { + #[inline] + fn try_pin_init(init: impl PinInit) -> Result, E> + where + E: From, + { + let mut this = Box::try_new_uninit()?; + let slot = this.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid and will not be moved, because we pin it later. + unsafe { init.__pinned_init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { this.assume_init() }.into()) + } + + #[inline] + fn try_init(init: impl Init) -> Result + where + E: From, + { + let mut this = Box::try_new_uninit()?; + let slot = this.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid. + unsafe { init.__init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { this.assume_init() }) + } +} + +impl InPlaceInit for UniqueArc { + #[inline] + fn try_pin_init(init: impl PinInit) -> Result, E> + where + E: From, + { + let mut this = UniqueArc::try_new_uninit()?; + let slot = this.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid and will not be moved, because we pin it later. + unsafe { init.__pinned_init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { this.assume_init() }.into()) + } + + #[inline] + fn try_init(init: impl Init) -> Result + where + E: From, + { + let mut this = UniqueArc::try_new_uninit()?; + let slot = this.as_mut_ptr(); + // SAFETY: When init errors/panics, slot will get deallocated but not dropped, + // slot is valid. + unsafe { init.__init(slot)? }; + // SAFETY: All fields have been initialized. + Ok(unsafe { this.assume_init() }) + } +} diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index 34d0e7cbe62e..b45769a29541 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -17,6 +17,8 @@ use crate::{ bindings, + error::{self, Error}, + init::{InPlaceInit, Init, PinInit}, types::{ForeignOwnable, Opaque}, }; use alloc::boxed::Box; @@ -166,6 +168,28 @@ impl Arc { // `Arc` object. Ok(unsafe { Self::from_inner(Box::leak(inner).into()) }) } + + /// Use the given initializer to in-place initialize a `T`. + /// + /// If `T: !Unpin` it will not be able to move afterwards. + #[inline] + pub fn pin_init(init: impl PinInit) -> error::Result + where + Error: From, + { + UniqueArc::pin_init(init).map(|u| u.into()) + } + + /// Use the given initializer to in-place initialize a `T`. + /// + /// This is equivalent to [`pin_init`], since an [`Arc`] is always pinned. + #[inline] + pub fn init(init: impl Init) -> error::Result + where + Error: From, + { + UniqueArc::init(init).map(|u| u.into()) + } } impl Arc { -- GitLab From d0fdc3961270617826e4794fca1d092853847707 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:01 +0000 Subject: [PATCH 2763/5631] rust: init: add `PinnedDrop` trait and macros The `PinnedDrop` trait that facilitates destruction of pinned types. It has to be implemented via the `#[pinned_drop]` macro, since the `drop` function should not be called by normal code, only by other destructors. It also only works on structs that are annotated with `#[pin_data(PinnedDrop)]`. Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-10-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 111 ++++++++++++++ rust/kernel/init/__internal.rs | 15 ++ rust/kernel/init/macros.rs | 264 +++++++++++++++++++++++++++++++++ rust/macros/lib.rs | 49 ++++++ rust/macros/pinned_drop.rs | 49 ++++++ 5 files changed, 488 insertions(+) create mode 100644 rust/macros/pinned_drop.rs diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 6499cf5c9c20..37e8159df24d 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -104,6 +104,78 @@ //! } //! ``` //! +//! ## Manual creation of an initializer +//! +//! Often when working with primitives the previous approaches are not sufficient. That is where +//! [`pin_init_from_closure()`] comes in. This `unsafe` function allows you to create a +//! [`impl PinInit`] directly from a closure. Of course you have to ensure that the closure +//! actually does the initialization in the correct way. Here are the things to look out for +//! (we are calling the parameter to the closure `slot`): +//! - when the closure returns `Ok(())`, then it has completed the initialization successfully, so +//! `slot` now contains a valid bit pattern for the type `T`, +//! - when the closure returns `Err(e)`, then the caller may deallocate the memory at `slot`, so +//! you need to take care to clean up anything if your initialization fails mid-way, +//! - you may assume that `slot` will stay pinned even after the closure returns until `drop` of +//! `slot` gets called. +//! +//! ```rust +//! use kernel::{prelude::*, init}; +//! use core::{ptr::addr_of_mut, marker::PhantomPinned, pin::Pin}; +//! # mod bindings { +//! # pub struct foo; +//! # pub unsafe fn init_foo(_ptr: *mut foo) {} +//! # pub unsafe fn destroy_foo(_ptr: *mut foo) {} +//! # pub unsafe fn enable_foo(_ptr: *mut foo, _flags: u32) -> i32 { 0 } +//! # } +//! /// # Invariants +//! /// +//! /// `foo` is always initialized +//! #[pin_data(PinnedDrop)] +//! pub struct RawFoo { +//! #[pin] +//! foo: Opaque, +//! #[pin] +//! _p: PhantomPinned, +//! } +//! +//! impl RawFoo { +//! pub fn new(flags: u32) -> impl PinInit { +//! // SAFETY: +//! // - when the closure returns `Ok(())`, then it has successfully initialized and +//! // enabled `foo`, +//! // - when it returns `Err(e)`, then it has cleaned up before +//! unsafe { +//! init::pin_init_from_closure(move |slot: *mut Self| { +//! // `slot` contains uninit memory, avoid creating a reference. +//! let foo = addr_of_mut!((*slot).foo); +//! +//! // Initialize the `foo` +//! bindings::init_foo(Opaque::raw_get(foo)); +//! +//! // Try to enable it. +//! let err = bindings::enable_foo(Opaque::raw_get(foo), flags); +//! if err != 0 { +//! // Enabling has failed, first clean up the foo and then return the error. +//! bindings::destroy_foo(Opaque::raw_get(foo)); +//! return Err(Error::from_kernel_errno(err)); +//! } +//! +//! // All fields of `RawFoo` have been initialized, since `_p` is a ZST. +//! Ok(()) +//! }) +//! } +//! } +//! } +//! +//! #[pinned_drop] +//! impl PinnedDrop for RawFoo { +//! fn drop(self: Pin<&mut Self>) { +//! // SAFETY: Since `foo` is initialized, destroying is safe. +//! unsafe { bindings::destroy_foo(self.foo.get()) }; +//! } +//! } +//! ``` +//! //! [`sync`]: kernel::sync //! [pinning]: https://doc.rust-lang.org/std/pin/index.html //! [structurally pinned fields]: @@ -1084,3 +1156,42 @@ impl InPlaceInit for UniqueArc { Ok(unsafe { this.assume_init() }) } } + +/// Trait facilitating pinned destruction. +/// +/// Use [`pinned_drop`] to implement this trait safely: +/// +/// ```rust +/// # use kernel::sync::Mutex; +/// use kernel::macros::pinned_drop; +/// use core::pin::Pin; +/// #[pin_data(PinnedDrop)] +/// struct Foo { +/// #[pin] +/// mtx: Mutex, +/// } +/// +/// #[pinned_drop] +/// impl PinnedDrop for Foo { +/// fn drop(self: Pin<&mut Self>) { +/// pr_info!("Foo is being dropped!"); +/// } +/// } +/// ``` +/// +/// # Safety +/// +/// This trait must be implemented via the [`pinned_drop`] proc-macro attribute on the impl. +/// +/// [`pinned_drop`]: kernel::macros::pinned_drop +pub unsafe trait PinnedDrop: __internal::HasPinData { + /// Executes the pinned destructor of this type. + /// + /// While this function is marked safe, it is actually unsafe to call it manually. For this + /// reason it takes an additional parameter. This type can only be constructed by `unsafe` code + /// and thus prevents this function from being called where it should not. + /// + /// This extra parameter will be generated by the `#[pinned_drop]` proc-macro attribute + /// automatically. + fn drop(self: Pin<&mut Self>, only_call_from_drop: __internal::OnlyCallFromDrop); +} diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs index a3389a684296..774cb620afa7 100644 --- a/rust/kernel/init/__internal.rs +++ b/rust/kernel/init/__internal.rs @@ -161,3 +161,18 @@ impl Drop for DropGuard { } } } + +/// Token used by `PinnedDrop` to prevent calling the function without creating this unsafely +/// created struct. This is needed, because the `drop` function is safe, but should not be called +/// manually. +pub struct OnlyCallFromDrop(()); + +impl OnlyCallFromDrop { + /// # Safety + /// + /// This function should only be called from the [`Drop::drop`] function and only be used to + /// delegate the destruction to the pinned destructor [`PinnedDrop::drop`] of the same type. + pub unsafe fn new() -> Self { + Self(()) + } +} diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs index 9ef02f5411a6..541cfad1d8be 100644 --- a/rust/kernel/init/macros.rs +++ b/rust/kernel/init/macros.rs @@ -31,6 +31,26 @@ //! pin_init!(Self { t, x: 0 }) //! } //! } +//! +//! #[pin_data(PinnedDrop)] +//! struct Foo { +//! a: usize, +//! #[pin] +//! b: Bar, +//! } +//! +//! #[pinned_drop] +//! impl PinnedDrop for Foo { +//! fn drop(self: Pin<&mut Self>) { +//! println!("{self:p} is getting dropped."); +//! } +//! } +//! +//! let a = 42; +//! let initializer = pin_init!(Foo { +//! a, +//! b <- Bar::new(36), +//! }); //! ``` //! //! This example includes the most common and important features of the pin-init API. @@ -155,6 +175,14 @@ //! #[allow(drop_bounds)] //! impl MustNotImplDrop for T {} //! impl MustNotImplDrop for Bar {} +//! // Here comes a convenience check, if one implemented `PinnedDrop`, but forgot to add it to +//! // `#[pin_data]`, then this will error with the same mechanic as above, this is not needed +//! // for safety, but a good sanity check, since no normal code calls `PinnedDrop::drop`. +//! #[allow(non_camel_case_types)] +//! trait UselessPinnedDropImpl_you_need_to_specify_PinnedDrop {} +//! impl +//! UselessPinnedDropImpl_you_need_to_specify_PinnedDrop for T {} +//! impl UselessPinnedDropImpl_you_need_to_specify_PinnedDrop for Bar {} //! }; //! ``` //! @@ -265,6 +293,210 @@ //! } //! } //! ``` +//! +//! ## `#[pin_data]` on `Foo` +//! +//! Since we already took a look at `#[pin_data]` on `Bar`, this section will only explain the +//! differences/new things in the expansion of the `Foo` definition: +//! +//! ```rust +//! #[pin_data(PinnedDrop)] +//! struct Foo { +//! a: usize, +//! #[pin] +//! b: Bar, +//! } +//! ``` +//! +//! This expands to the following code: +//! +//! ```rust +//! struct Foo { +//! a: usize, +//! b: Bar, +//! } +//! const _: () = { +//! struct __ThePinData { +//! __phantom: ::core::marker::PhantomData Foo>, +//! } +//! impl ::core::clone::Clone for __ThePinData { +//! fn clone(&self) -> Self { +//! *self +//! } +//! } +//! impl ::core::marker::Copy for __ThePinData {} +//! #[allow(dead_code)] +//! impl __ThePinData { +//! unsafe fn b( +//! self, +//! slot: *mut Bar, +//! // Note that this is `PinInit` instead of `Init`, this is because `b` is +//! // structurally pinned, as marked by the `#[pin]` attribute. +//! init: impl ::kernel::init::PinInit, E>, +//! ) -> ::core::result::Result<(), E> { +//! unsafe { ::kernel::init::PinInit::__pinned_init(init, slot) } +//! } +//! unsafe fn a( +//! self, +//! slot: *mut usize, +//! init: impl ::kernel::init::Init, +//! ) -> ::core::result::Result<(), E> { +//! unsafe { ::kernel::init::Init::__init(init, slot) } +//! } +//! } +//! unsafe impl ::kernel::init::__internal::HasPinData for Foo { +//! type PinData = __ThePinData; +//! unsafe fn __pin_data() -> Self::PinData { +//! __ThePinData { +//! __phantom: ::core::marker::PhantomData, +//! } +//! } +//! } +//! unsafe impl ::kernel::init::__internal::PinData for __ThePinData { +//! type Datee = Foo; +//! } +//! #[allow(dead_code)] +//! struct __Unpin<'__pin> { +//! __phantom_pin: ::core::marker::PhantomData &'__pin ()>, +//! __phantom: ::core::marker::PhantomData Foo>, +//! // Since this field is `#[pin]`, it is listed here. +//! b: Bar, +//! } +//! #[doc(hidden)] +//! impl<'__pin> ::core::marker::Unpin for Foo where __Unpin<'__pin>: ::core::marker::Unpin {} +//! // Since we specified `PinnedDrop` as the argument to `#[pin_data]`, we expect `Foo` to +//! // implement `PinnedDrop`. Thus we do not need to prevent `Drop` implementations like +//! // before, instead we implement it here and delegate to `PinnedDrop`. +//! impl ::core::ops::Drop for Foo { +//! fn drop(&mut self) { +//! // Since we are getting dropped, no one else has a reference to `self` and thus we +//! // can assume that we never move. +//! let pinned = unsafe { ::core::pin::Pin::new_unchecked(self) }; +//! // Create the unsafe token that proves that we are inside of a destructor, this +//! // type is only allowed to be created in a destructor. +//! let token = unsafe { ::kernel::init::__internal::OnlyCallFromDrop::new() }; +//! ::kernel::init::PinnedDrop::drop(pinned, token); +//! } +//! } +//! }; +//! ``` +//! +//! ## `#[pinned_drop]` on `impl PinnedDrop for Foo` +//! +//! This macro is used to implement the `PinnedDrop` trait, since that trait is `unsafe` and has an +//! extra parameter that should not be used at all. The macro hides that parameter. +//! +//! Here is the `PinnedDrop` impl for `Foo`: +//! +//! ```rust +//! #[pinned_drop] +//! impl PinnedDrop for Foo { +//! fn drop(self: Pin<&mut Self>) { +//! println!("{self:p} is getting dropped."); +//! } +//! } +//! ``` +//! +//! This expands to the following code: +//! +//! ```rust +//! // `unsafe`, full path and the token parameter are added, everything else stays the same. +//! unsafe impl ::kernel::init::PinnedDrop for Foo { +//! fn drop(self: Pin<&mut Self>, _: ::kernel::init::__internal::OnlyCallFromDrop) { +//! println!("{self:p} is getting dropped."); +//! } +//! } +//! ``` +//! +//! ## `pin_init!` on `Foo` +//! +//! Since we already took a look at `pin_init!` on `Bar`, this section will only explain the +//! differences/new things in the expansion of `pin_init!` on `Foo`: +//! +//! ```rust +//! let a = 42; +//! let initializer = pin_init!(Foo { +//! a, +//! b <- Bar::new(36), +//! }); +//! ``` +//! +//! This expands to the following code: +//! +//! ```rust +//! let a = 42; +//! let initializer = { +//! struct __InitOk; +//! let data = unsafe { +//! use ::kernel::init::__internal::HasPinData; +//! Foo::__pin_data() +//! }; +//! let init = ::kernel::init::__internal::PinData::make_closure::< +//! _, +//! __InitOk, +//! ::core::convert::Infallible, +//! >(data, move |slot| { +//! { +//! struct __InitOk; +//! unsafe { ::core::ptr::write(&raw mut (*slot).a, a) }; +//! let a = &unsafe { ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).a) }; +//! let b = Bar::new(36); +//! // Here we use `data` to access the correct field and require that `b` is of type +//! // `PinInit, Infallible>`. +//! unsafe { data.b(&raw mut (*slot).b, b)? }; +//! let b = &unsafe { ::kernel::init::__internal::DropGuard::new(&raw mut (*slot).b) }; +//! +//! #[allow(unreachable_code, clippy::diverging_sub_expression)] +//! if false { +//! unsafe { +//! ::core::ptr::write( +//! slot, +//! Foo { +//! a: ::core::panic!(), +//! b: ::core::panic!(), +//! }, +//! ); +//! }; +//! } +//! unsafe { ::kernel::init::__internal::DropGuard::forget(a) }; +//! unsafe { ::kernel::init::__internal::DropGuard::forget(b) }; +//! } +//! Ok(__InitOk) +//! }); +//! let init = move |slot| -> ::core::result::Result<(), ::core::convert::Infallible> { +//! init(slot).map(|__InitOk| ()) +//! }; +//! let init = unsafe { +//! ::kernel::init::pin_init_from_closure::<_, ::core::convert::Infallible>(init) +//! }; +//! init +//! }; +//! ``` + +/// Creates a `unsafe impl<...> PinnedDrop for $type` block. +/// +/// See [`PinnedDrop`] for more information. +#[doc(hidden)] +#[macro_export] +macro_rules! __pinned_drop { + ( + @impl_sig($($impl_sig:tt)*), + @impl_body( + $(#[$($attr:tt)*])* + fn drop($($sig:tt)*) { + $($inner:tt)* + } + ), + ) => { + unsafe $($impl_sig)* { + // Inherit all attributes and the type/ident tokens for the signature. + $(#[$($attr)*])* + fn drop($($sig)*, _: $crate::init::__internal::OnlyCallFromDrop) { + $($inner)* + } + } + } +} /// This macro first parses the struct definition such that it separates pinned and not pinned /// fields. Afterwards it declares the struct and implement the `PinData` trait safely. @@ -653,6 +885,38 @@ macro_rules! __pin_data { impl MustNotImplDrop for T {} impl<$($impl_generics)*> MustNotImplDrop for $name<$($ty_generics)*> where $($whr)* {} + // We also take care to prevent users from writing a useless `PinnedDrop` implementation. + // They might implement `PinnedDrop` correctly for the struct, but forget to give + // `PinnedDrop` as the parameter to `#[pin_data]`. + #[allow(non_camel_case_types)] + trait UselessPinnedDropImpl_you_need_to_specify_PinnedDrop {} + impl + UselessPinnedDropImpl_you_need_to_specify_PinnedDrop for T {} + impl<$($impl_generics)*> + UselessPinnedDropImpl_you_need_to_specify_PinnedDrop for $name<$($ty_generics)*> + where $($whr)* {} + }; + // When `PinnedDrop` was specified we just implement `Drop` and delegate. + (drop_prevention: + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @where($($whr:tt)*), + @pinned_drop(PinnedDrop), + ) => { + impl<$($impl_generics)*> ::core::ops::Drop for $name<$($ty_generics)*> + where $($whr)* + { + fn drop(&mut self) { + // SAFETY: Since this is a destructor, `self` will not move after this function + // terminates, since it is inaccessible. + let pinned = unsafe { ::core::pin::Pin::new_unchecked(self) }; + // SAFETY: Since this is a drop function, we can create this token to call the + // pinned destructor of this type. + let token = unsafe { $crate::init::__internal::OnlyCallFromDrop::new() }; + $crate::init::PinnedDrop::drop(pinned, token); + } + } }; // If some other parameter was specified, we emit a readable error. (drop_prevention: diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs index 6d84f2fd0d77..3fc74cb4ea19 100644 --- a/rust/macros/lib.rs +++ b/rust/macros/lib.rs @@ -8,6 +8,7 @@ mod concat_idents; mod helpers; mod module; mod pin_data; +mod pinned_drop; mod vtable; use proc_macro::TokenStream; @@ -180,6 +181,10 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream { /// This macro enables the use of the [`pin_init!`] macro. When pin-initializing a `struct`, /// then `#[pin]` directs the type of initializer that is required. /// +/// If your `struct` implements `Drop`, then you need to add `PinnedDrop` as arguments to this +/// macro, and change your `Drop` implementation to `PinnedDrop` annotated with +/// `#[`[`macro@pinned_drop`]`]`, since dropping pinned values requires extra care. +/// /// # Examples /// /// ```rust,ignore @@ -191,9 +196,53 @@ pub fn concat_idents(ts: TokenStream) -> TokenStream { /// } /// ``` /// +/// ```rust,ignore +/// #[pin_data(PinnedDrop)] +/// struct DriverData { +/// #[pin] +/// queue: Mutex>, +/// buf: Box<[u8; 1024 * 1024]>, +/// raw_info: *mut Info, +/// } +/// +/// #[pinned_drop] +/// impl PinnedDrop for DriverData { +/// fn drop(self: Pin<&mut Self>) { +/// unsafe { bindings::destroy_info(self.raw_info) }; +/// } +/// } +/// ``` +/// /// [`pin_init!`]: ../kernel/macro.pin_init.html // ^ cannot use direct link, since `kernel` is not a dependency of `macros`. #[proc_macro_attribute] pub fn pin_data(inner: TokenStream, item: TokenStream) -> TokenStream { pin_data::pin_data(inner, item) } + +/// Used to implement `PinnedDrop` safely. +/// +/// Only works on structs that are annotated via `#[`[`macro@pin_data`]`]`. +/// +/// # Examples +/// +/// ```rust,ignore +/// #[pin_data(PinnedDrop)] +/// struct DriverData { +/// #[pin] +/// queue: Mutex>, +/// buf: Box<[u8; 1024 * 1024]>, +/// raw_info: *mut Info, +/// } +/// +/// #[pinned_drop] +/// impl PinnedDrop for DriverData { +/// fn drop(self: Pin<&mut Self>) { +/// unsafe { bindings::destroy_info(self.raw_info) }; +/// } +/// } +/// ``` +#[proc_macro_attribute] +pub fn pinned_drop(args: TokenStream, input: TokenStream) -> TokenStream { + pinned_drop::pinned_drop(args, input) +} diff --git a/rust/macros/pinned_drop.rs b/rust/macros/pinned_drop.rs new file mode 100644 index 000000000000..88fb72b20660 --- /dev/null +++ b/rust/macros/pinned_drop.rs @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use proc_macro::{TokenStream, TokenTree}; + +pub(crate) fn pinned_drop(_args: TokenStream, input: TokenStream) -> TokenStream { + let mut toks = input.into_iter().collect::>(); + assert!(!toks.is_empty()); + // Ensure that we have an `impl` item. + assert!(matches!(&toks[0], TokenTree::Ident(i) if i.to_string() == "impl")); + // Ensure that we are implementing `PinnedDrop`. + let mut nesting: usize = 0; + let mut pinned_drop_idx = None; + for (i, tt) in toks.iter().enumerate() { + match tt { + TokenTree::Punct(p) if p.as_char() == '<' => { + nesting += 1; + } + TokenTree::Punct(p) if p.as_char() == '>' => { + nesting = nesting.checked_sub(1).unwrap(); + continue; + } + _ => {} + } + if i >= 1 && nesting == 0 { + // Found the end of the generics, this should be `PinnedDrop`. + assert!( + matches!(tt, TokenTree::Ident(i) if i.to_string() == "PinnedDrop"), + "expected 'PinnedDrop', found: '{:?}'", + tt + ); + pinned_drop_idx = Some(i); + break; + } + } + let idx = pinned_drop_idx + .unwrap_or_else(|| panic!("Expected an `impl` block implementing `PinnedDrop`.")); + // Fully qualify the `PinnedDrop`, as to avoid any tampering. + toks.splice(idx..idx, quote!(::kernel::init::)); + // Take the `{}` body and call the declarative macro. + if let Some(TokenTree::Group(last)) = toks.pop() { + let last = last.stream(); + quote!(::kernel::__pinned_drop! { + @impl_sig(#(#toks)*), + @impl_body(#last), + }) + } else { + TokenStream::from_iter(toks) + } +} -- GitLab From 6841d45a303029c54d6ad1ebb5dc72f7b2a74700 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:07 +0000 Subject: [PATCH 2764/5631] rust: init: add `stack_pin_init!` macro The `stack_pin_init!` macro allows pin-initializing a value on the stack. It accepts a `impl PinInit` to initialize a `T`. It allows propagating any errors via `?` or handling it normally via `match`. Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Reviewed-by: Gary Guo Link: https://lore.kernel.org/r/20230408122429.1103522-11-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 140 +++++++++++++++++++++++++++++++-- rust/kernel/init/__internal.rs | 57 ++++++++++++++ 2 files changed, 191 insertions(+), 6 deletions(-) diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 37e8159df24d..99751375e7c8 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -12,7 +12,8 @@ //! //! To initialize a `struct` with an in-place constructor you will need two things: //! - an in-place constructor, -//! - a memory location that can hold your `struct`. +//! - a memory location that can hold your `struct` (this can be the [stack], an [`Arc`], +//! [`UniqueArc`], [`Box`] or any other smart pointer that implements [`InPlaceInit`]). //! //! To get an in-place constructor there are generally three options: //! - directly creating an in-place constructor using the [`pin_init!`] macro, @@ -180,6 +181,7 @@ //! [pinning]: https://doc.rust-lang.org/std/pin/index.html //! [structurally pinned fields]: //! https://doc.rust-lang.org/std/pin/index.html#pinning-is-structural-for-field +//! [stack]: crate::stack_pin_init //! [`Arc`]: crate::sync::Arc //! [`impl PinInit`]: PinInit //! [`impl PinInit`]: PinInit @@ -202,6 +204,132 @@ pub mod __internal; #[doc(hidden)] pub mod macros; +/// Initialize and pin a type directly on the stack. +/// +/// # Examples +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, stack_pin_init, init::*, sync::Mutex, new_mutex}; +/// # use macros::pin_data; +/// # use core::pin::Pin; +/// #[pin_data] +/// struct Foo { +/// #[pin] +/// a: Mutex, +/// b: Bar, +/// } +/// +/// #[pin_data] +/// struct Bar { +/// x: u32, +/// } +/// +/// stack_pin_init!(let foo = pin_init!(Foo { +/// a <- new_mutex!(42), +/// b: Bar { +/// x: 64, +/// }, +/// })); +/// let foo: Pin<&mut Foo> = foo; +/// pr_info!("a: {}", &*foo.a.lock()); +/// ``` +/// +/// # Syntax +/// +/// A normal `let` binding with optional type annotation. The expression is expected to implement +/// [`PinInit`]/[`Init`] with the error type [`Infallible`]. If you want to use a different error +/// type, then use [`stack_try_pin_init!`]. +#[macro_export] +macro_rules! stack_pin_init { + (let $var:ident $(: $t:ty)? = $val:expr) => { + let val = $val; + let mut $var = ::core::pin::pin!($crate::init::__internal::StackInit$(::<$t>)?::uninit()); + let mut $var = match $crate::init::__internal::StackInit::init($var, val) { + Ok(res) => res, + Err(x) => { + let x: ::core::convert::Infallible = x; + match x {} + } + }; + }; +} + +/// Initialize and pin a type directly on the stack. +/// +/// # Examples +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex}; +/// # use macros::pin_data; +/// # use core::{alloc::AllocError, pin::Pin}; +/// #[pin_data] +/// struct Foo { +/// #[pin] +/// a: Mutex, +/// b: Box, +/// } +/// +/// struct Bar { +/// x: u32, +/// } +/// +/// stack_try_pin_init!(let foo: Result, AllocError> = pin_init!(Foo { +/// a <- new_mutex!(42), +/// b: Box::try_new(Bar { +/// x: 64, +/// })?, +/// })); +/// let foo = foo.unwrap(); +/// pr_info!("a: {}", &*foo.a.lock()); +/// ``` +/// +/// ```rust +/// # #![allow(clippy::disallowed_names, clippy::new_ret_no_self)] +/// # use kernel::{init, pin_init, stack_try_pin_init, init::*, sync::Mutex, new_mutex}; +/// # use macros::pin_data; +/// # use core::{alloc::AllocError, pin::Pin}; +/// #[pin_data] +/// struct Foo { +/// #[pin] +/// a: Mutex, +/// b: Box, +/// } +/// +/// struct Bar { +/// x: u32, +/// } +/// +/// stack_try_pin_init!(let foo: Pin<&mut Foo> =? pin_init!(Foo { +/// a <- new_mutex!(42), +/// b: Box::try_new(Bar { +/// x: 64, +/// })?, +/// })); +/// pr_info!("a: {}", &*foo.a.lock()); +/// # Ok::<_, AllocError>(()) +/// ``` +/// +/// # Syntax +/// +/// A normal `let` binding with optional type annotation. The expression is expected to implement +/// [`PinInit`]/[`Init`]. This macro assigns a result to the given variable, adding a `?` after the +/// `=` will propagate this error. +#[macro_export] +macro_rules! stack_try_pin_init { + (let $var:ident $(: $t:ty)? = $val:expr) => { + let val = $val; + let mut $var = ::core::pin::pin!($crate::init::__internal::StackInit$(::<$t>)?::uninit()); + let mut $var = $crate::init::__internal::StackInit::init($var, val); + }; + (let $var:ident $(: $t:ty)? =? $val:expr) => { + let val = $val; + let mut $var = ::core::pin::pin!($crate::init::__internal::StackInit$(::<$t>)?::uninit()); + let mut $var = $crate::init::__internal::StackInit::init($var, val)?; + }; +} + /// Construct an in-place, pinned initializer for `struct`s. /// /// This macro defaults the error to [`Infallible`]. If you need [`Error`], then use @@ -913,8 +1041,8 @@ macro_rules! try_init { /// A pin-initializer for the type `T`. /// /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can -/// be [`Box`], [`Arc`], [`UniqueArc`]. Use the [`InPlaceInit::pin_init`] function of a -/// smart pointer like [`Arc`] on this. +/// be [`Box`], [`Arc`], [`UniqueArc`] or even the stack (see [`stack_pin_init!`]). Use the +/// [`InPlaceInit::pin_init`] function of a smart pointer like [`Arc`] on this. /// /// Also see the [module description](self). /// @@ -949,9 +1077,9 @@ pub unsafe trait PinInit: Sized { /// An initializer for `T`. /// /// To use this initializer, you will need a suitable memory location that can hold a `T`. This can -/// be [`Box`], [`Arc`], [`UniqueArc`]. Use the [`InPlaceInit::init`] function of a smart -/// pointer like [`Arc`] on this. Because [`PinInit`] is a super trait, you can -/// use every function that takes it as well. +/// be [`Box`], [`Arc`], [`UniqueArc`] or even the stack (see [`stack_pin_init!`]). Use the +/// [`InPlaceInit::init`] function of a smart pointer like [`Arc`] on this. Because +/// [`PinInit`] is a super trait, you can use every function that takes it as well. /// /// Also see the [module description](self). /// diff --git a/rust/kernel/init/__internal.rs b/rust/kernel/init/__internal.rs index 774cb620afa7..44751fb62b51 100644 --- a/rust/kernel/init/__internal.rs +++ b/rust/kernel/init/__internal.rs @@ -112,6 +112,63 @@ unsafe impl HasInitData for T { } } +/// Stack initializer helper type. Use [`stack_pin_init`] instead of this primitive. +/// +/// # Invariants +/// +/// If `self.is_init` is true, then `self.value` is initialized. +/// +/// [`stack_pin_init`]: kernel::stack_pin_init +pub struct StackInit { + value: MaybeUninit, + is_init: bool, +} + +impl Drop for StackInit { + #[inline] + fn drop(&mut self) { + if self.is_init { + // SAFETY: As we are being dropped, we only call this once. And since `self.is_init` is + // true, `self.value` is initialized. + unsafe { self.value.assume_init_drop() }; + } + } +} + +impl StackInit { + /// Creates a new [`StackInit`] that is uninitialized. Use [`stack_pin_init`] instead of this + /// primitive. + /// + /// [`stack_pin_init`]: kernel::stack_pin_init + #[inline] + pub fn uninit() -> Self { + Self { + value: MaybeUninit::uninit(), + is_init: false, + } + } + + /// Initializes the contents and returns the result. + #[inline] + pub fn init(self: Pin<&mut Self>, init: impl PinInit) -> Result, E> { + // SAFETY: We never move out of `this`. + let this = unsafe { Pin::into_inner_unchecked(self) }; + // The value is currently initialized, so it needs to be dropped before we can reuse + // the memory (this is a safety guarantee of `Pin`). + if this.is_init { + this.is_init = false; + // SAFETY: `this.is_init` was true and therefore `this.value` is initialized. + unsafe { this.value.assume_init_drop() }; + } + // SAFETY: The memory slot is valid and this type ensures that it will stay pinned. + unsafe { init.__pinned_init(this.value.as_mut_ptr())? }; + // INVARIANT: `this.value` is initialized above. + this.is_init = true; + // SAFETY: The slot is now pinned, since we will never give access to `&mut T`. + Ok(unsafe { Pin::new_unchecked(this.value.assume_init_mut()) }) + } +} + /// When a value of this type is dropped, it drops a `T`. /// /// Can be forgotten to prevent the drop. -- GitLab From 38cde0bd7b6772003a37b9aa6822568409556ee9 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:12 +0000 Subject: [PATCH 2765/5631] rust: init: add `Zeroable` trait and `init::zeroed` function Add the `Zeroable` trait which marks types that can be initialized by writing `0x00` to every byte of the type. Also add the `init::zeroed` function that creates an initializer for a `Zeroable` type that writes `0x00` to every byte. Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-12-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 97 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 95 insertions(+), 2 deletions(-) diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 99751375e7c8..ffd539e2f5ef 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -195,8 +195,14 @@ use crate::{ }; use alloc::boxed::Box; use core::{ - alloc::AllocError, cell::Cell, convert::Infallible, marker::PhantomData, mem::MaybeUninit, - pin::Pin, ptr, + alloc::AllocError, + cell::Cell, + convert::Infallible, + marker::PhantomData, + mem::MaybeUninit, + num::*, + pin::Pin, + ptr::{self, NonNull}, }; #[doc(hidden)] @@ -1323,3 +1329,90 @@ pub unsafe trait PinnedDrop: __internal::HasPinData { /// automatically. fn drop(self: Pin<&mut Self>, only_call_from_drop: __internal::OnlyCallFromDrop); } + +/// Marker trait for types that can be initialized by writing just zeroes. +/// +/// # Safety +/// +/// The bit pattern consisting of only zeroes is a valid bit pattern for this type. In other words, +/// this is not UB: +/// +/// ```rust,ignore +/// let val: Self = unsafe { core::mem::zeroed() }; +/// ``` +pub unsafe trait Zeroable {} + +/// Create a new zeroed T. +/// +/// The returned initializer will write `0x00` to every byte of the given `slot`. +#[inline] +pub fn zeroed() -> impl Init { + // SAFETY: Because `T: Zeroable`, all bytes zero is a valid bit pattern for `T` + // and because we write all zeroes, the memory is initialized. + unsafe { + init_from_closure(|slot: *mut T| { + slot.write_bytes(0, 1); + Ok(()) + }) + } +} + +macro_rules! impl_zeroable { + ($($({$($generics:tt)*})? $t:ty, )*) => { + $(unsafe impl$($($generics)*)? Zeroable for $t {})* + }; +} + +impl_zeroable! { + // SAFETY: All primitives that are allowed to be zero. + bool, + char, + u8, u16, u32, u64, u128, usize, + i8, i16, i32, i64, i128, isize, + f32, f64, + + // SAFETY: These are ZSTs, there is nothing to zero. + {} PhantomData, core::marker::PhantomPinned, Infallible, (), + + // SAFETY: Type is allowed to take any value, including all zeros. + {} MaybeUninit, + + // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee). + Option, Option, Option, Option, + Option, Option, + Option, Option, Option, Option, + Option, Option, + + // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee). + // + // In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant. + {} Option>, + {} Option>, + + // SAFETY: `null` pointer is valid. + // + // We cannot use `T: ?Sized`, since the VTABLE pointer part of fat pointers is not allowed to be + // null. + // + // When `Pointee` gets stabilized, we could use + // `T: ?Sized where ::Metadata: Zeroable` + {} *mut T, {} *const T, + + // SAFETY: `null` pointer is valid and the metadata part of these fat pointers is allowed to be + // zero. + {} *mut [T], {} *const [T], *mut str, *const str, + + // SAFETY: `T` is `Zeroable`. + {} [T; N], {} Wrapping, +} + +macro_rules! impl_tuple_zeroable { + ($(,)?) => {}; + ($first:ident, $($t:ident),* $(,)?) => { + // SAFETY: All elements are zeroable and padding can be zero. + unsafe impl<$first: Zeroable, $($t: Zeroable),*> Zeroable for ($first, $($t),*) {} + impl_tuple_zeroable!($($t),* ,); + } +} + +impl_tuple_zeroable!(A, B, C, D, E, F, G, H, I, J); -- GitLab From 8586f1acd314a47d68d189331606ca235a05b972 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:17 +0000 Subject: [PATCH 2766/5631] rust: prelude: add `pin-init` API items to prelude Add `pin-init` API macros and traits to the prelude. Signed-off-by: Benno Lossin Reviewed-by: Gary Guo Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-13-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/prelude.rs | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index 0bc1c97e5604..fcdc511d2ce8 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -18,7 +18,7 @@ pub use core::pin::Pin; pub use alloc::{boxed::Box, vec::Vec}; #[doc(no_inline)] -pub use macros::{module, vtable}; +pub use macros::{module, pin_data, pinned_drop, vtable}; pub use super::build_assert; @@ -27,8 +27,12 @@ pub use super::build_assert; pub use super::dbg; pub use super::{pr_alert, pr_crit, pr_debug, pr_emerg, pr_err, pr_info, pr_notice, pr_warn}; +pub use super::{init, pin_init, try_init, try_pin_init}; + pub use super::static_assert; pub use super::error::{code::*, Error, Result}; pub use super::{str::CStr, ThisModule}; + +pub use super::init::{InPlaceInit, Init, PinInit}; -- GitLab From 692e8935e23efab6c5d5fc4b003816b33c8082f7 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:22 +0000 Subject: [PATCH 2767/5631] rust: types: add `Opaque::ffi_init` This function allows to easily initialize `Opaque` with the pin-init API. `Opaque::ffi_init` takes a closure and returns a pin-initializer. This pin-initiailizer calls the given closure with a pointer to the inner `T`. Co-developed-by: Gary Guo Signed-off-by: Gary Guo Signed-off-by: Benno Lossin Reviewed-by: Andreas Hindborg Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20230408122429.1103522-14-y86-dev@protonmail.com [ Fixed typo. ] Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 9 +++++++++ rust/kernel/types.rs | 20 ++++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index ffd539e2f5ef..a1298c8bbda0 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -177,6 +177,14 @@ //! } //! ``` //! +//! For the special case where initializing a field is a single FFI-function call that cannot fail, +//! there exist the helper function [`Opaque::ffi_init`]. This function initialize a single +//! [`Opaque`] field by just delegating to the supplied closure. You can use these in combination +//! with [`pin_init!`]. +//! +//! For more information on how to use [`pin_init_from_closure()`], take a look at the uses inside +//! the `kernel` crate. The [`sync`] module is a good starting point. +//! //! [`sync`]: kernel::sync //! [pinning]: https://doc.rust-lang.org/std/pin/index.html //! [structurally pinned fields]: @@ -187,6 +195,7 @@ //! [`impl PinInit`]: PinInit //! [`impl Init`]: Init //! [`Opaque`]: kernel::types::Opaque +//! [`Opaque::ffi_init`]: kernel::types::Opaque::ffi_init //! [`pin_data`]: ::macros::pin_data use crate::{ diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index ff2b2fac951d..a4b1e3778da7 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -2,6 +2,7 @@ //! Kernel types. +use crate::init::{self, PinInit}; use alloc::boxed::Box; use core::{ cell::UnsafeCell, @@ -234,6 +235,25 @@ impl Opaque { Self(MaybeUninit::uninit()) } + /// Creates a pin-initializer from the given initializer closure. + /// + /// The returned initializer calls the given closure with the pointer to the inner `T` of this + /// `Opaque`. Since this memory is uninitialized, the closure is not allowed to read from it. + /// + /// This function is safe, because the `T` inside of an `Opaque` is allowed to be + /// uninitialized. Additionally, access to the inner `T` requires `unsafe`, so the caller needs + /// to verify at that point that the inner value is valid. + pub fn ffi_init(init_func: impl FnOnce(*mut T)) -> impl PinInit { + // SAFETY: We contain a `MaybeUninit`, so it is OK for the `init_func` to not fully + // initialize the `T`. + unsafe { + init::pin_init_from_closure::<_, ::core::convert::Infallible>(move |slot| { + init_func(Self::raw_get(slot)); + Ok(()) + }) + } + } + /// Returns a raw pointer to the opaque data. pub fn get(&self) -> *mut T { UnsafeCell::raw_get(self.0.as_ptr()) -- GitLab From 701608bd030a888f654862295a49c5d0f42f864c Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:27 +0000 Subject: [PATCH 2768/5631] rust: sync: reduce stack usage of `UniqueArc::try_new_uninit` `UniqueArc::try_new_uninit` calls `Arc::try_new(MaybeUninit::uninit())`. This results in the uninitialized memory being placed on the stack, which may be arbitrarily large due to the generic `T` and thus could cause a stack overflow for large types. Change the implementation to use the pin-init API which enables in-place initialization. In particular it avoids having to first construct and then move the uninitialized memory from the stack into the final location. Signed-off-by: Benno Lossin Reviewed-by: Alice Ryhl Reviewed-by: Gary Guo Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-15-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/lib.rs | 1 - rust/kernel/sync/arc.rs | 16 +++++++++++++--- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 821bd067151c..2d7606135ef6 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -28,7 +28,6 @@ #[cfg(not(CONFIG_RUST))] compile_error!("Missing kernel configuration for conditional compilation"); -#[allow(unused_extern_crates)] // Allow proc-macros to refer to `::kernel` inside the `kernel` crate (this crate). extern crate self as kernel; diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index b45769a29541..de36d55e81d8 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -18,7 +18,8 @@ use crate::{ bindings, error::{self, Error}, - init::{InPlaceInit, Init, PinInit}, + init::{self, InPlaceInit, Init, PinInit}, + try_init, types::{ForeignOwnable, Opaque}, }; use alloc::boxed::Box; @@ -31,6 +32,7 @@ use core::{ pin::Pin, ptr::NonNull, }; +use macros::pin_data; mod std_vendor; @@ -125,6 +127,7 @@ pub struct Arc { _p: PhantomData>, } +#[pin_data] #[repr(C)] struct ArcInner { refcount: Opaque, @@ -505,9 +508,16 @@ impl UniqueArc { /// Tries to allocate a new [`UniqueArc`] instance whose contents are not initialised yet. pub fn try_new_uninit() -> Result>, AllocError> { - Ok(UniqueArc::> { + // INVARIANT: The refcount is initialised to a non-zero value. + let inner = Box::try_init::(try_init!(ArcInner { + // SAFETY: There are no safety requirements for this FFI call. + refcount: Opaque::new(unsafe { bindings::REFCOUNT_INIT(1) }), + data <- init::uninit::(), + }? AllocError))?; + Ok(UniqueArc { // INVARIANT: The newly-created object has a ref-count of 1. - inner: Arc::try_new(MaybeUninit::uninit())?, + // SAFETY: The pointer from the `Box` is valid. + inner: unsafe { Arc::from_inner(Box::leak(inner).into()) }, }) } } -- GitLab From 1944caa8e8dcb2d93d99d8364719ad8d07aa163f Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Sat, 8 Apr 2023 12:26:33 +0000 Subject: [PATCH 2769/5631] rust: sync: add functions for initializing `UniqueArc>` Add two functions `init_with` and `pin_init_with` to `UniqueArc>` to initialize the memory of already allocated `UniqueArc`s. This is useful when you want to allocate memory check some condition inside of a context where allocation is forbidden and then conditionally initialize an object. Signed-off-by: Benno Lossin Reviewed-by: Gary Guo Reviewed-by: Alice Ryhl Reviewed-by: Andreas Hindborg Link: https://lore.kernel.org/r/20230408122429.1103522-16-y86-dev@protonmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/sync/arc.rs | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs index de36d55e81d8..e6d206242465 100644 --- a/rust/kernel/sync/arc.rs +++ b/rust/kernel/sync/arc.rs @@ -544,6 +544,30 @@ impl UniqueArc> { inner: unsafe { Arc::from_inner(inner.cast()) }, } } + + /// Initialize `self` using the given initializer. + pub fn init_with(mut self, init: impl Init) -> core::result::Result, E> { + // SAFETY: The supplied pointer is valid for initialization. + match unsafe { init.__init(self.as_mut_ptr()) } { + // SAFETY: Initialization completed successfully. + Ok(()) => Ok(unsafe { self.assume_init() }), + Err(err) => Err(err), + } + } + + /// Pin-initialize `self` using the given pin-initializer. + pub fn pin_init_with( + mut self, + init: impl PinInit, + ) -> core::result::Result>, E> { + // SAFETY: The supplied pointer is valid for initialization and we will later pin the value + // to ensure it does not move. + match unsafe { init.__pinned_init(self.as_mut_ptr()) } { + // SAFETY: Initialization completed successfully. + Ok(()) => Ok(unsafe { self.assume_init() }.into()), + Err(err) => Err(err), + } + } } impl From> for Pin> { -- GitLab From ec318c51b686841e36c924bc0e5a13a75e75b27b Mon Sep 17 00:00:00 2001 From: Siddharth Vadapalli Date: Thu, 9 Mar 2023 14:54:34 +0530 Subject: [PATCH 2770/5631] phy: ti: j721e-wiz: Add SGMII support in WIZ driver for J721E Enable full rate divider configuration support for J721E_WIZ_16G for SGMII. Signed-off-by: Siddharth Vadapalli Reviewed-by: Roger Quadros Link: https://lore.kernel.org/r/20230309092434.443550-1-s-vadapalli@ti.com Signed-off-by: Vinod Koul --- drivers/phy/ti/phy-j721e-wiz.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index d59918457799..d91923799df2 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1234,6 +1234,8 @@ static int wiz_phy_fullrt_div(struct wiz *wiz, int lane) if (wiz->lane_phy_type[lane] == PHY_TYPE_PCIE) return regmap_field_write(wiz->p0_fullrt_div[lane], 0x1); break; + + case J721E_WIZ_16G: case J721E_WIZ_10G: case J7200_WIZ_10G: case J721S2_WIZ_10G: -- GitLab From a0106132372120dd0abf5ad7636614e5aeb5da08 Mon Sep 17 00:00:00 2001 From: Sinthu Raja Date: Tue, 14 Mar 2023 13:01:37 +0530 Subject: [PATCH 2771/5631] phy: cadence: cdns-dphy-rx: Add common module reset support DPHY RX module has a common module reset (RSTB_CMN) which is expected to be released during configuration. In J721E SR1.0 the RSTB_CMN is internally tied to CSI_RX_RST and is hardware controlled, for all other newer platforms the common module reset is software controlled. Add support to control common module reset during configuration and also skip common module reset based on soc_device_match() for J721E SR1.0. Signed-off-by: Sinthu Raja Co-developed-by: Vaishnav Achath Signed-off-by: Vaishnav Achath Reviewed-by: Jai Luthra Link: https://lore.kernel.org/r/20230314073137.2153-1-vaishnav.a@ti.com Signed-off-by: Vinod Koul --- drivers/phy/cadence/cdns-dphy-rx.c | 32 ++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/phy/cadence/cdns-dphy-rx.c b/drivers/phy/cadence/cdns-dphy-rx.c index 572c70089a94..c05b043893a9 100644 --- a/drivers/phy/cadence/cdns-dphy-rx.c +++ b/drivers/phy/cadence/cdns-dphy-rx.c @@ -11,10 +11,12 @@ #include #include #include +#include #define DPHY_PMA_CMN(reg) (reg) #define DPHY_PCS(reg) (0xb00 + (reg)) #define DPHY_ISO(reg) (0xc00 + (reg)) +#define DPHY_WRAP(reg) (0x1000 + (reg)) #define DPHY_CMN_SSM DPHY_PMA_CMN(0x20) #define DPHY_CMN_RX_MODE_EN BIT(10) @@ -33,6 +35,9 @@ #define DPHY_POWER_ISLAND_EN_CLK DPHY_PCS(0xc) #define DPHY_POWER_ISLAND_EN_CLK_VAL 0xaa +#define DPHY_LANE DPHY_WRAP(0x0) +#define DPHY_LANE_RESET_CMN_EN BIT(23) + #define DPHY_ISO_CL_CTRL_L DPHY_ISO(0x10) #define DPHY_ISO_DL_CTRL_L0 DPHY_ISO(0x14) #define DPHY_ISO_DL_CTRL_L1 DPHY_ISO(0x20) @@ -57,6 +62,10 @@ struct cdns_dphy_rx_band { unsigned int max_rate; }; +struct cdns_dphy_soc_data { + bool has_hw_cmn_rstb; +}; + /* Order of bands is important since the index is the band number. */ static const struct cdns_dphy_rx_band bands[] = { { 80, 100 }, { 100, 120 }, { 120, 160 }, { 160, 200 }, { 200, 240 }, @@ -142,13 +151,36 @@ static int cdns_dphy_rx_wait_lane_ready(struct cdns_dphy_rx *dphy, return 0; } +static struct cdns_dphy_soc_data j721e_soc_data = { + .has_hw_cmn_rstb = true, +}; + +static const struct soc_device_attribute cdns_dphy_socinfo[] = { + { + .family = "J721E", + .revision = "SR1.0", + .data = &j721e_soc_data, + }, + {/* sentinel */} +}; + static int cdns_dphy_rx_configure(struct phy *phy, union phy_configure_opts *opts) { struct cdns_dphy_rx *dphy = phy_get_drvdata(phy); unsigned int reg, lanes = opts->mipi_dphy.lanes; + const struct cdns_dphy_soc_data *soc_data = NULL; + const struct soc_device_attribute *soc; int band_ctrl, ret; + soc = soc_device_match(cdns_dphy_socinfo); + if (soc && soc->data) + soc_data = soc->data; + if (!soc || (soc_data && !soc_data->has_hw_cmn_rstb)) { + reg = DPHY_LANE_RESET_CMN_EN; + writel(reg, dphy->regs + DPHY_LANE); + } + /* Data lanes. Minimum one lane is mandatory. */ if (lanes < DPHY_LANES_MIN || lanes > DPHY_LANES_MAX) return -EINVAL; -- GitLab From 91d6a468e335571f1e67e046050dea9af5fa4ebe Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Mon, 10 Apr 2023 02:33:55 +0300 Subject: [PATCH 2772/5631] dma: gpi: remove spurious unlock in gpi_ch_init gpi_ch_init() doesn't lock the ctrl_lock mutex, so there is no need to unlock it too. Instead the mutex is handled by the function gpi_alloc_chan_resources(), which properly locks and unlocks the mutex. ===================================== WARNING: bad unlock balance detected! 6.3.0-rc5-00253-g99792582ded1-dirty #15 Not tainted ------------------------------------- kworker/u16:0/9 is trying to release lock (&gpii->ctrl_lock) at: [] gpi_alloc_chan_resources+0x108/0x5bc but there are no more locks to release! other info that might help us debug this: 6 locks held by kworker/u16:0/9: #0: ffff575740010938 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x220/0x594 #1: ffff80000809bdd0 (deferred_probe_work){+.+.}-{0:0}, at: process_one_work+0x220/0x594 #2: ffff575740f2a0f8 (&dev->mutex){....}-{3:3}, at: __device_attach+0x38/0x188 #3: ffff57574b5570f8 (&dev->mutex){....}-{3:3}, at: __device_attach+0x38/0x188 #4: ffffb99d06a2f180 (of_dma_lock){+.+.}-{3:3}, at: of_dma_request_slave_channel+0x138/0x280 #5: ffffb99d06a2ee20 (dma_list_mutex){+.+.}-{3:3}, at: dma_get_slave_channel+0x28/0x10c stack backtrace: CPU: 7 PID: 9 Comm: kworker/u16:0 Not tainted 6.3.0-rc5-00253-g99792582ded1-dirty #15 Hardware name: Google Pixel 3 (DT) Workqueue: events_unbound deferred_probe_work_func Call trace: dump_backtrace+0xa0/0xfc show_stack+0x18/0x24 dump_stack_lvl+0x60/0xac dump_stack+0x18/0x24 print_unlock_imbalance_bug+0x130/0x148 lock_release+0x270/0x300 __mutex_unlock_slowpath+0x48/0x2cc mutex_unlock+0x20/0x2c gpi_alloc_chan_resources+0x108/0x5bc dma_chan_get+0x84/0x188 dma_get_slave_channel+0x5c/0x10c gpi_of_dma_xlate+0x110/0x1a0 of_dma_request_slave_channel+0x174/0x280 dma_request_chan+0x3c/0x2d4 geni_i2c_probe+0x544/0x63c platform_probe+0x68/0xc4 really_probe+0x148/0x2ac __driver_probe_device+0x78/0xe0 driver_probe_device+0x3c/0x160 __device_attach_driver+0xb8/0x138 bus_for_each_drv+0x84/0xe0 __device_attach+0x9c/0x188 device_initial_probe+0x14/0x20 bus_probe_device+0xac/0xb0 device_add+0x60c/0x7d8 of_device_add+0x44/0x60 of_platform_device_create_pdata+0x90/0x124 of_platform_bus_create+0x15c/0x3c8 of_platform_populate+0x58/0xf8 devm_of_platform_populate+0x58/0xbc geni_se_probe+0xf0/0x164 platform_probe+0x68/0xc4 really_probe+0x148/0x2ac __driver_probe_device+0x78/0xe0 driver_probe_device+0x3c/0x160 __device_attach_driver+0xb8/0x138 bus_for_each_drv+0x84/0xe0 __device_attach+0x9c/0x188 device_initial_probe+0x14/0x20 bus_probe_device+0xac/0xb0 deferred_probe_work_func+0x8c/0xc8 process_one_work+0x2bc/0x594 worker_thread+0x228/0x438 kthread+0x108/0x10c ret_from_fork+0x10/0x20 Fixes: 5d0c3533a19f ("dmaengine: qcom: Add GPI dma driver") Signed-off-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230409233355.453741-1-dmitry.baryshkov@linaro.org Signed-off-by: Vinod Koul --- drivers/dma/qcom/gpi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 59a36cbf9b5f..932628b319c8 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -1966,7 +1966,6 @@ static int gpi_ch_init(struct gchan *gchan) error_config_int: gpi_free_ring(&gpii->ev_ring, gpii); exit_gpi_init: - mutex_unlock(&gpii->ctrl_lock); return ret; } -- GitLab From 619d8ea96d984d007be88b1e7a4ff9159bf44594 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 10 Apr 2023 18:26:54 -0500 Subject: [PATCH 2773/5631] dmaengine: qcom_hidma: Add explicit platform_device.h and of_device.h includes qcom_hidma uses of_dma_configure() which is declared in of_device.h. platform_device.h and of_device.h get implicitly included by of_platform.h, but that is going to be removed soon. Signed-off-by: Rob Herring Acked-by: Sinan Kaya Link: https://lore.kernel.org/r/20230410232654.1561462-1-robh@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/qcom/hidma_mgmt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c index 62026607f3f8..05e96b31d871 100644 --- a/drivers/dma/qcom/hidma_mgmt.c +++ b/drivers/dma/qcom/hidma_mgmt.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include -- GitLab From a251994a441ee0a69ba7062c8cd2d08ead3db379 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 11 Apr 2023 19:17:57 +0900 Subject: [PATCH 2774/5631] dmaengine: dw-edma: Fix to change for continuous transfer The dw-edma driver stops after processing a DMA request even if a request remains in the issued queue, which is not the expected behavior. The DMA engine API requires continuous processing. Add a trigger to start after one processing finished if there are requests remain. Fixes: e63d79d1ffcd ("dmaengine: Add Synopsys eDMA IP core driver") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20230411101758.438472-1-mie@igel.co.jp Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-core.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index 1906a836f0aa..26a395d02f5d 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -181,7 +181,7 @@ static void vchan_free_desc(struct virt_dma_desc *vdesc) dw_edma_free_desc(vd2dw_edma_desc(vdesc)); } -static void dw_edma_start_transfer(struct dw_edma_chan *chan) +static int dw_edma_start_transfer(struct dw_edma_chan *chan) { struct dw_edma_chunk *child; struct dw_edma_desc *desc; @@ -189,16 +189,16 @@ static void dw_edma_start_transfer(struct dw_edma_chan *chan) vd = vchan_next_desc(&chan->vc); if (!vd) - return; + return 0; desc = vd2dw_edma_desc(vd); if (!desc) - return; + return 0; child = list_first_entry_or_null(&desc->chunk->list, struct dw_edma_chunk, list); if (!child) - return; + return 0; dw_edma_v0_core_start(child, !desc->xfer_sz); desc->xfer_sz += child->ll_region.sz; @@ -206,6 +206,8 @@ static void dw_edma_start_transfer(struct dw_edma_chan *chan) list_del(&child->list); kfree(child); desc->chunks_alloc--; + + return 1; } static void dw_edma_device_caps(struct dma_chan *dchan, @@ -602,14 +604,14 @@ static void dw_edma_done_interrupt(struct dw_edma_chan *chan) switch (chan->request) { case EDMA_REQ_NONE: desc = vd2dw_edma_desc(vd); - if (desc->chunks_alloc) { - chan->status = EDMA_ST_BUSY; - dw_edma_start_transfer(chan); - } else { + if (!desc->chunks_alloc) { list_del(&vd->node); vchan_cookie_complete(vd); - chan->status = EDMA_ST_IDLE; } + + /* Continue transferring if there are remaining chunks or issued requests. + */ + chan->status = dw_edma_start_transfer(chan) ? EDMA_ST_BUSY : EDMA_ST_IDLE; break; case EDMA_REQ_STOP: -- GitLab From 970b17dfe264a9085ba4e593730ecfd496b950ab Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Tue, 11 Apr 2023 19:17:58 +0900 Subject: [PATCH 2775/5631] dmaengine: dw-edma: Fix to enable to issue dma request on DMA processing The issue_pending request is ignored while driver is processing a DMA request. Fix to issue the pending requests on any dma channel status. Fixes: e63d79d1ffcd ("dmaengine: Add Synopsys eDMA IP core driver") Signed-off-by: Shunsuke Mie Link: https://lore.kernel.org/r/20230411101758.438472-2-mie@igel.co.jp Signed-off-by: Vinod Koul --- drivers/dma/dw-edma/dw-edma-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c index 26a395d02f5d..7d2b73ef0872 100644 --- a/drivers/dma/dw-edma/dw-edma-core.c +++ b/drivers/dma/dw-edma/dw-edma-core.c @@ -308,9 +308,12 @@ static void dw_edma_device_issue_pending(struct dma_chan *dchan) struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan); unsigned long flags; + if (!chan->configured) + return; + spin_lock_irqsave(&chan->vc.lock, flags); - if (chan->configured && chan->request == EDMA_REQ_NONE && - chan->status == EDMA_ST_IDLE && vchan_issue_pending(&chan->vc)) { + if (vchan_issue_pending(&chan->vc) && chan->request == EDMA_REQ_NONE && + chan->status == EDMA_ST_IDLE) { chan->status = EDMA_ST_BUSY; dw_edma_start_transfer(chan); } -- GitLab From 7bb1d048bdfe1c7d36fdd72be9abd5f552b6246a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 12 Apr 2023 12:45:45 -0300 Subject: [PATCH 2776/5631] perf cpumap: Use perf_cpu_map__nr(cpus) to access cpus->nr So that we can have a single point where to refcount check 'struct perf_cpu_map' instances for use after free, etc. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-3-irogers@google.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 5e564974fba4..c8484b75413e 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -239,7 +239,7 @@ struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, { int idx; struct perf_cpu cpu; - struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr); + struct cpu_aggr_map *c = cpu_aggr_map__empty_new(perf_cpu_map__nr(cpus)); if (!c) return NULL; @@ -263,7 +263,7 @@ struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus, } } /* Trim. */ - if (c->nr != cpus->nr) { + if (c->nr != perf_cpu_map__nr(cpus)) { struct cpu_aggr_map *trimmed_c = realloc(c, sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr); @@ -582,9 +582,9 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) #define COMMA first ? "" : "," - for (i = 0; i < map->nr + 1; i++) { + for (i = 0; i < perf_cpu_map__nr(map) + 1; i++) { struct perf_cpu cpu = { .cpu = INT_MAX }; - bool last = i == map->nr; + bool last = i == perf_cpu_map__nr(map); if (!last) cpu = map->map[i]; @@ -633,7 +633,7 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) int i, cpu; char *ptr = buf; unsigned char *bitmap; - struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1); + struct perf_cpu last_cpu = perf_cpu_map__cpu(map, perf_cpu_map__nr(map) - 1); if (buf == NULL) return 0; @@ -644,7 +644,7 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size) return 0; } - for (i = 0; i < map->nr; i++) { + for (i = 0; i < perf_cpu_map__nr(map); i++) { cpu = perf_cpu_map__cpu(map, i).cpu; bitmap[cpu / 8] |= 1 << (cpu % 8); } -- GitLab From 1f94479edb4decdcec3e902528abb47f0ccd5d16 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 12 Apr 2023 12:54:44 -0300 Subject: [PATCH 2777/5631] libperf: Make perf_cpu_map__alloc() available as an internal function for tools/perf to use We had the open coded equivalent in perf_cpu_map__empty_new(), so reuse what is in libperf. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-3-irogers@google.com [ Split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/cpumap.c | 2 +- tools/lib/perf/include/internal/cpumap.h | 1 + tools/perf/util/cpumap.c | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 6cd0be7c1bb4..0833423c243b 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,7 +10,7 @@ #include #include -static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) +struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) { struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 35dd29642296..f5bffb1f8674 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -24,6 +24,7 @@ struct perf_cpu_map { #define MAX_NR_CPUS 2048 #endif +struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus); int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index c8484b75413e..072831f0cad4 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -160,7 +160,7 @@ size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp) struct perf_cpu_map *perf_cpu_map__empty_new(int nr) { - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int) * nr); + struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr); if (cpus != NULL) { int i; -- GitLab From 790f3c8b8f9f63b1f5a3ffd06630ed3d0df9804c Mon Sep 17 00:00:00 2001 From: Walker Chen Date: Wed, 22 Mar 2023 17:48:18 +0800 Subject: [PATCH 2778/5631] dmaengine: dw-axi-dmac: Add support for StarFive JH7110 DMA Add DMA reset operation in device probe and use different configuration on CH_CFG registers according to match data. Update all uses of of_device_is_compatible with of_device_get_match_data. Signed-off-by: Walker Chen Reviewed-by: Emil Renner Berthing Link: https://lore.kernel.org/r/20230322094820.24738-3-walker.chen@starfivetech.com Signed-off-by: Vinod Koul --- .../dma/dw-axi-dmac/dw-axi-dmac-platform.c | 38 ++++++++++++++++--- drivers/dma/dw-axi-dmac/dw-axi-dmac.h | 1 + 2 files changed, 34 insertions(+), 5 deletions(-) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index 4169e1d7d5ca..6cfcb541d8c3 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -21,10 +21,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include @@ -46,6 +48,10 @@ DMA_SLAVE_BUSWIDTH_32_BYTES | \ DMA_SLAVE_BUSWIDTH_64_BYTES) +#define AXI_DMA_FLAG_HAS_APB_REGS BIT(0) +#define AXI_DMA_FLAG_HAS_RESETS BIT(1) +#define AXI_DMA_FLAG_USE_CFG2 BIT(2) + static inline void axi_dma_iowrite32(struct axi_dma_chip *chip, u32 reg, u32 val) { @@ -86,7 +92,8 @@ static inline void axi_chan_config_write(struct axi_dma_chan *chan, cfg_lo = (config->dst_multblk_type << CH_CFG_L_DST_MULTBLK_TYPE_POS | config->src_multblk_type << CH_CFG_L_SRC_MULTBLK_TYPE_POS); - if (chan->chip->dw->hdata->reg_map_8_channels) { + if (chan->chip->dw->hdata->reg_map_8_channels && + !chan->chip->dw->hdata->use_cfg2) { cfg_hi = config->tt_fc << CH_CFG_H_TT_FC_POS | config->hs_sel_src << CH_CFG_H_HS_SEL_SRC_POS | config->hs_sel_dst << CH_CFG_H_HS_SEL_DST_POS | @@ -1367,10 +1374,11 @@ static int parse_device_properties(struct axi_dma_chip *chip) static int dw_probe(struct platform_device *pdev) { - struct device_node *node = pdev->dev.of_node; struct axi_dma_chip *chip; struct dw_axi_dma *dw; struct dw_axi_dma_hcfg *hdata; + struct reset_control *resets; + unsigned int flags; u32 i; int ret; @@ -1398,12 +1406,25 @@ static int dw_probe(struct platform_device *pdev) if (IS_ERR(chip->regs)) return PTR_ERR(chip->regs); - if (of_device_is_compatible(node, "intel,kmb-axi-dma")) { + flags = (uintptr_t)of_device_get_match_data(&pdev->dev); + if (flags & AXI_DMA_FLAG_HAS_APB_REGS) { chip->apb_regs = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(chip->apb_regs)) return PTR_ERR(chip->apb_regs); } + if (flags & AXI_DMA_FLAG_HAS_RESETS) { + resets = devm_reset_control_array_get_exclusive(&pdev->dev); + if (IS_ERR(resets)) + return PTR_ERR(resets); + + ret = reset_control_deassert(resets); + if (ret) + return ret; + } + + chip->dw->hdata->use_cfg2 = !!(flags & AXI_DMA_FLAG_USE_CFG2); + chip->core_clk = devm_clk_get(chip->dev, "core-clk"); if (IS_ERR(chip->core_clk)) return PTR_ERR(chip->core_clk); @@ -1554,8 +1575,15 @@ static const struct dev_pm_ops dw_axi_dma_pm_ops = { }; static const struct of_device_id dw_dma_of_id_table[] = { - { .compatible = "snps,axi-dma-1.01a" }, - { .compatible = "intel,kmb-axi-dma" }, + { + .compatible = "snps,axi-dma-1.01a" + }, { + .compatible = "intel,kmb-axi-dma", + .data = (void *)AXI_DMA_FLAG_HAS_APB_REGS, + }, { + .compatible = "starfive,jh7110-axi-dma", + .data = (void *)(AXI_DMA_FLAG_HAS_RESETS | AXI_DMA_FLAG_USE_CFG2), + }, {} }; MODULE_DEVICE_TABLE(of, dw_dma_of_id_table); diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h index e9d5eb0fd594..eb267cb24f67 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h @@ -33,6 +33,7 @@ struct dw_axi_dma_hcfg { /* Register map for DMAX_NUM_CHANNELS <= 8 */ bool reg_map_8_channels; bool restrict_axi_burst_len; + bool use_cfg2; }; struct axi_dma_chan { -- GitLab From ce62432cb8bb56a5fde544d01213e952c3a92f8b Mon Sep 17 00:00:00 2001 From: Walker Chen Date: Wed, 22 Mar 2023 17:48:19 +0800 Subject: [PATCH 2779/5631] dmaengine: dw-axi-dmac: Increase polling time to DMA transmission completion status The bit DMAC_CHEN[0] is automatically cleared by hardware to disable the channel after the last AMBA transfer of the DMA transfer to the destination has completed. Software can therefore poll this bit to determine when this channel is free for a new DMA transfer. This time requires at least 40 milliseconds on JH7110 SoC, otherwise an error message 'failed to stop' will be reported. Signed-off-by: Walker Chen Link: https://lore.kernel.org/r/20230322094820.24738-4-walker.chen@starfivetech.com Signed-off-by: Vinod Koul --- drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index 6cfcb541d8c3..6937cc0c0b65 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -1147,7 +1147,7 @@ static int dma_chan_terminate_all(struct dma_chan *dchan) axi_chan_disable(chan); ret = readl_poll_timeout_atomic(chan->chip->regs + DMAC_CHEN, val, - !(val & chan_active), 1000, 10000); + !(val & chan_active), 1000, 50000); if (ret == -ETIMEDOUT) dev_warn(dchan2dev(dchan), "%s failed to stop\n", axi_chan_name(chan)); -- GitLab From 2de5ddb5e68c94b781b3789bca1ce52000d7d0e0 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:21 +0200 Subject: [PATCH 2780/5631] dmaengine: at_xdmac: disable/enable clock directly on suspend/resume Runtime PM APIs for at_xdmac just plays with clk_enable()/clk_disable() letting aside the clk_prepare()/clk_unprepare() that needs to be executed as the clock is also prepared on probe. Thus instead of using runtime PM force suspend/resume APIs use clk_disable_unprepare() + pm_runtime_put_noidle() on suspend and clk_prepare_enable() + pm_runtime_get_noresume() on resume. This approach as been chosen instead of using runtime PM force suspend/resume with clk_unprepare()/clk_prepare() as it looks simpler and the final code is better. While at it added the missing pm_runtime_mark_last_busy() on suspend before decrementing the reference counter. Fixes: 650b0e990cbd ("dmaengine: at_xdmac: add runtime pm support") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-2-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 1f0fab180f8f..f654ecaafb90 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -2130,7 +2130,11 @@ static int __maybe_unused atmel_xdmac_suspend(struct device *dev) atxdmac->save_gim = at_xdmac_read(atxdmac, AT_XDMAC_GIM); at_xdmac_off(atxdmac); - return pm_runtime_force_suspend(atxdmac->dev); + pm_runtime_mark_last_busy(atxdmac->dev); + pm_runtime_put_noidle(atxdmac->dev); + clk_disable_unprepare(atxdmac->clk); + + return 0; } static int __maybe_unused atmel_xdmac_resume(struct device *dev) @@ -2142,10 +2146,12 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) int i; int ret; - ret = pm_runtime_force_resume(atxdmac->dev); - if (ret < 0) + ret = clk_prepare_enable(atxdmac->clk); + if (ret) return ret; + pm_runtime_get_noresume(atxdmac->dev); + at_xdmac_axi_config(pdev); /* Clear pending interrupts. */ -- GitLab From e53957e1ec5196671e49a48f90a5c9555153189a Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:22 +0200 Subject: [PATCH 2781/5631] dmaengine: at_xdmac: fix imbalanced runtime PM reference counter In case there are channels not paused during suspend (which on AT91 case is valid for serial driver when no_console_suspend boot argument is used) the at_xdmac_runtime_suspend_descriptors() was called more than one time due to at_xdmac_off(). To fix this add a new argument to at_xdmac_off() to specify if runtime PM reference counter needs to be decremented for queued active descriptors. Along with it moved the at_xdmac_runtime_suspend_descriptors() call under at_xdmac_chan_is_paused() check on suspend path as for the rest of channels the suspend is delayed by atmel_xdmac_prepare() in case channel is enabled. Same approach has been applied on resume path. Fixes: 650b0e990cbd ("dmaengine: at_xdmac: add runtime pm support") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-3-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index f654ecaafb90..af3b494f9ba9 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -412,7 +412,7 @@ static bool at_xdmac_chan_is_enabled(struct at_xdmac_chan *atchan) return ret; } -static void at_xdmac_off(struct at_xdmac *atxdmac) +static void at_xdmac_off(struct at_xdmac *atxdmac, bool suspend_descriptors) { struct dma_chan *chan, *_chan; struct at_xdmac_chan *atchan; @@ -431,7 +431,7 @@ static void at_xdmac_off(struct at_xdmac *atxdmac) at_xdmac_write(atxdmac, AT_XDMAC_GID, -1L); /* Decrement runtime PM ref counter for each active descriptor. */ - if (!list_empty(&atxdmac->dma.channels)) { + if (!list_empty(&atxdmac->dma.channels) && suspend_descriptors) { list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) { atchan = to_at_xdmac_chan(chan); @@ -2118,18 +2118,18 @@ static int __maybe_unused atmel_xdmac_suspend(struct device *dev) atchan->save_cc = at_xdmac_chan_read(atchan, AT_XDMAC_CC); if (at_xdmac_chan_is_cyclic(atchan)) { - if (!at_xdmac_chan_is_paused(atchan)) + if (!at_xdmac_chan_is_paused(atchan)) { at_xdmac_device_pause(chan); + at_xdmac_runtime_suspend_descriptors(atchan); + } atchan->save_cim = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); atchan->save_cnda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA); atchan->save_cndc = at_xdmac_chan_read(atchan, AT_XDMAC_CNDC); } - - at_xdmac_runtime_suspend_descriptors(atchan); } atxdmac->save_gim = at_xdmac_read(atxdmac, AT_XDMAC_GIM); - at_xdmac_off(atxdmac); + at_xdmac_off(atxdmac, false); pm_runtime_mark_last_busy(atxdmac->dev); pm_runtime_put_noidle(atxdmac->dev); clk_disable_unprepare(atxdmac->clk); @@ -2165,14 +2165,14 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) list_for_each_entry_safe(chan, _chan, &atxdmac->dma.channels, device_node) { atchan = to_at_xdmac_chan(chan); - ret = at_xdmac_runtime_resume_descriptors(atchan); - if (ret < 0) - return ret; - at_xdmac_chan_write(atchan, AT_XDMAC_CC, atchan->save_cc); if (at_xdmac_chan_is_cyclic(atchan)) { - if (at_xdmac_chan_is_paused(atchan)) + if (at_xdmac_chan_is_paused(atchan)) { + ret = at_xdmac_runtime_resume_descriptors(atchan); + if (ret < 0) + return ret; at_xdmac_device_resume(chan); + } at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda); at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); @@ -2318,7 +2318,7 @@ static int at_xdmac_probe(struct platform_device *pdev) INIT_LIST_HEAD(&atxdmac->dma.channels); /* Disable all chans and interrupts. */ - at_xdmac_off(atxdmac); + at_xdmac_off(atxdmac, true); for (i = 0; i < nr_channels; i++) { struct at_xdmac_chan *atchan = &atxdmac->chan[i]; @@ -2382,7 +2382,7 @@ static int at_xdmac_remove(struct platform_device *pdev) struct at_xdmac *atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev); int i; - at_xdmac_off(atxdmac); + at_xdmac_off(atxdmac, true); of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&atxdmac->dma); pm_runtime_disable(atxdmac->dev); -- GitLab From 44fe8440bda545b5d167329df88c47609a645168 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:23 +0200 Subject: [PATCH 2782/5631] dmaengine: at_xdmac: do not resume channels paused by consumers In case there are DMA channels not paused by consumers in suspend process (valid on AT91 SoCs for serial driver when no_console_suspend) the driver pauses them (using at_xdmac_device_pause() which is also the same function called by dmaengine_pause()) and then in the resume process the driver resumes them calling at_xdmac_device_resume() which is the same function called by dmaengine_resume()). This is good for DMA channels not paused by consumers but for drivers that calls dmaengine_pause()/dmaegine_resume() on suspend/resume path this may lead to DMA channel being enabled before the IP is enabled. For IPs that needs strict ordering with regards to DMA channel enablement this will lead to wrong behavior. To fix this add a new set of functions at_xdmac_device_pause_internal()/at_xdmac_device_resume_internal() to be called only on suspend/resume. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-4-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 52 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 7 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index af3b494f9ba9..fa1e2e0da02f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -187,6 +187,7 @@ enum atc_status { AT_XDMAC_CHAN_IS_CYCLIC = 0, AT_XDMAC_CHAN_IS_PAUSED, + AT_XDMAC_CHAN_IS_PAUSED_INTERNAL, }; struct at_xdmac_layout { @@ -347,6 +348,11 @@ static inline int at_xdmac_chan_is_paused(struct at_xdmac_chan *atchan) return test_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); } +static inline int at_xdmac_chan_is_paused_internal(struct at_xdmac_chan *atchan) +{ + return test_bit(AT_XDMAC_CHAN_IS_PAUSED_INTERNAL, &atchan->status); +} + static inline bool at_xdmac_chan_is_peripheral_xfer(u32 cfg) { return cfg & AT_XDMAC_CC_TYPE_PER_TRAN; @@ -1898,6 +1904,26 @@ static int at_xdmac_device_config(struct dma_chan *chan, return ret; } +static void at_xdmac_device_pause_set(struct at_xdmac *atxdmac, + struct at_xdmac_chan *atchan) +{ + at_xdmac_write(atxdmac, atxdmac->layout->grws, atchan->mask); + while (at_xdmac_chan_read(atchan, AT_XDMAC_CC) & + (AT_XDMAC_CC_WRIP | AT_XDMAC_CC_RDIP)) + cpu_relax(); +} + +static void at_xdmac_device_pause_internal(struct at_xdmac_chan *atchan) +{ + struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); + unsigned long flags; + + spin_lock_irqsave(&atchan->lock, flags); + set_bit(AT_XDMAC_CHAN_IS_PAUSED_INTERNAL, &atchan->status); + at_xdmac_device_pause_set(atxdmac, atchan); + spin_unlock_irqrestore(&atchan->lock, flags); +} + static int at_xdmac_device_pause(struct dma_chan *chan) { struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); @@ -1915,11 +1941,8 @@ static int at_xdmac_device_pause(struct dma_chan *chan) return ret; spin_lock_irqsave(&atchan->lock, flags); - at_xdmac_write(atxdmac, atxdmac->layout->grws, atchan->mask); - while (at_xdmac_chan_read(atchan, AT_XDMAC_CC) - & (AT_XDMAC_CC_WRIP | AT_XDMAC_CC_RDIP)) - cpu_relax(); + at_xdmac_device_pause_set(atxdmac, atchan); /* Decrement runtime PM ref counter for each active descriptor. */ at_xdmac_runtime_suspend_descriptors(atchan); @@ -1931,6 +1954,17 @@ static int at_xdmac_device_pause(struct dma_chan *chan) return 0; } +static void at_xdmac_device_resume_internal(struct at_xdmac_chan *atchan) +{ + struct at_xdmac *atxdmac = to_at_xdmac(atchan->chan.device); + unsigned long flags; + + spin_lock_irqsave(&atchan->lock, flags); + at_xdmac_write(atxdmac, atxdmac->layout->grwr, atchan->mask); + clear_bit(AT_XDMAC_CHAN_IS_PAUSED_INTERNAL, &atchan->status); + spin_unlock_irqrestore(&atchan->lock, flags); +} + static int at_xdmac_device_resume(struct dma_chan *chan) { struct at_xdmac_chan *atchan = to_at_xdmac_chan(chan); @@ -2119,7 +2153,7 @@ static int __maybe_unused atmel_xdmac_suspend(struct device *dev) atchan->save_cc = at_xdmac_chan_read(atchan, AT_XDMAC_CC); if (at_xdmac_chan_is_cyclic(atchan)) { if (!at_xdmac_chan_is_paused(atchan)) { - at_xdmac_device_pause(chan); + at_xdmac_device_pause_internal(atchan); at_xdmac_runtime_suspend_descriptors(atchan); } atchan->save_cim = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); @@ -2167,11 +2201,15 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) at_xdmac_chan_write(atchan, AT_XDMAC_CC, atchan->save_cc); if (at_xdmac_chan_is_cyclic(atchan)) { - if (at_xdmac_chan_is_paused(atchan)) { + /* + * Resume only channels not explicitly paused by + * consumers. + */ + if (at_xdmac_chan_is_paused_internal(atchan)) { ret = at_xdmac_runtime_resume_descriptors(atchan); if (ret < 0) return ret; - at_xdmac_device_resume(chan); + at_xdmac_device_resume_internal(atchan); } at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda); at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); -- GitLab From 7c5eb63d16b01c202aaa95f374ae15a807745a73 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:24 +0200 Subject: [PATCH 2783/5631] dmaengine: at_xdmac: restore the content of grws register In case the system suspends to a deep sleep state where power to DMA controller is cut-off we need to restore the content of GRWS register. This is a write only register and writing bit X tells the controller to suspend read and write requests for channel X. Thus set GRWS before restoring the content of GE (Global Enable) regiter. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-5-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index fa1e2e0da02f..34c004a4b23c 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -2211,6 +2211,15 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) return ret; at_xdmac_device_resume_internal(atchan); } + + /* + * We may resume from a deep sleep state where power + * to DMA controller is cut-off. Thus, restore the + * suspend state of channels set though dmaengine API. + */ + else if (at_xdmac_chan_is_paused(atchan)) + at_xdmac_device_pause_set(atxdmac, atchan); + at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda); at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); -- GitLab From f8435befd81dd85b7b610598551fadf675849bc1 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:25 +0200 Subject: [PATCH 2784/5631] dmaengine: at_xdmac: do not enable all cyclic channels Do not global enable all the cyclic channels in at_xdmac_resume(). Instead save the global status in at_xdmac_suspend() and re-enable the cyclic channel only if it was active before suspend. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-6-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 34c004a4b23c..96f1b69f8a75 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -246,6 +246,7 @@ struct at_xdmac { int irq; struct clk *clk; u32 save_gim; + u32 save_gs; struct dma_pool *at_xdmac_desc_pool; const struct at_xdmac_layout *layout; struct at_xdmac_chan chan[]; @@ -2162,6 +2163,7 @@ static int __maybe_unused atmel_xdmac_suspend(struct device *dev) } } atxdmac->save_gim = at_xdmac_read(atxdmac, AT_XDMAC_GIM); + atxdmac->save_gs = at_xdmac_read(atxdmac, AT_XDMAC_GS); at_xdmac_off(atxdmac, false); pm_runtime_mark_last_busy(atxdmac->dev); @@ -2224,7 +2226,8 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); wmb(); - at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask); + if (atxdmac->save_gs & atchan->mask) + at_xdmac_write(atxdmac, AT_XDMAC_GE, atchan->mask); } } -- GitLab From 5056eae6c32d709bab506ca032ac4f7effc9db2f Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:26 +0200 Subject: [PATCH 2785/5631] dmaengine: at_xdmac: add a warning message regarding for unpaused channels Add a warning message on suspend to let the user that there are channels not paused by their consumers. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-7-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 96f1b69f8a75..7ff6ca01e0b5 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -2154,6 +2154,8 @@ static int __maybe_unused atmel_xdmac_suspend(struct device *dev) atchan->save_cc = at_xdmac_chan_read(atchan, AT_XDMAC_CC); if (at_xdmac_chan_is_cyclic(atchan)) { if (!at_xdmac_chan_is_paused(atchan)) { + dev_warn(chan2dev(chan), "%s: channel %d not paused\n", + __func__, chan->chan_id); at_xdmac_device_pause_internal(atchan); at_xdmac_runtime_suspend_descriptors(atchan); } -- GitLab From 09ebe227c2236c6d0ce427ce10da3e4d66946f57 Mon Sep 17 00:00:00 2001 From: Claudiu Beznea Date: Tue, 14 Feb 2023 17:18:27 +0200 Subject: [PATCH 2786/5631] dmaengine: at_xdmac: align declaration of ret with the rest of variables Align the declaration of ret in atmel_xdmac_resume() with the rest of variables. Do this by adding ret to the line with declaration for i variable. Signed-off-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230214151827.1050280-8-claudiu.beznea@microchip.com Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7ff6ca01e0b5..7da6d9b6098e 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -2181,8 +2181,7 @@ static int __maybe_unused atmel_xdmac_resume(struct device *dev) struct at_xdmac_chan *atchan; struct dma_chan *chan, *_chan; struct platform_device *pdev = container_of(dev, struct platform_device, dev); - int i; - int ret; + int i, ret; ret = clk_prepare_enable(atxdmac->clk); if (ret) -- GitLab From 894abe0dcfe2ad76dac25691264a85fdc2d524c3 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 31 Mar 2023 13:21:41 -0500 Subject: [PATCH 2787/5631] dt-bindings: dma: Drop unneeded quotes Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Acked-by: Peter Ujfalusi Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230331182141.1900348-1-robh@kernel.org Signed-off-by: Vinod Koul --- Documentation/devicetree/bindings/dma/ti/k3-udma.yaml | 2 +- .../devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml | 2 +- .../devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml index 97f6ae9b1236..22f6c5e2f7f4 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-udma.yaml @@ -43,7 +43,7 @@ description: | configuration of the legacy peripheral. allOf: - - $ref: "../dma-controller.yaml#" + - $ref: ../dma-controller.yaml# - $ref: /schemas/arm/keystone/ti,k3-sci-common.yaml# properties: diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml index c0a1408b12ec..23ada8f87526 100644 --- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml +++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml @@ -15,7 +15,7 @@ maintainers: - Michael Tretter allOf: - - $ref: "../dma-controller.yaml#" + - $ref: ../dma-controller.yaml# properties: "#dma-cells": diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml index 825294e3f0e8..d6cbd95ec26d 100644 --- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml +++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml @@ -16,7 +16,7 @@ maintainers: - Laurent Pinchart allOf: - - $ref: "../dma-controller.yaml#" + - $ref: ../dma-controller.yaml# properties: "#dma-cells": -- GitLab From c9566127f021c891e14c937b1b711874b7880e48 Mon Sep 17 00:00:00 2001 From: Walker Chen Date: Wed, 22 Mar 2023 17:48:17 +0800 Subject: [PATCH 2788/5631] dt-bindings: dma: snps,dw-axi-dmac: constrain the items of resets for JH7110 dma The DMA controller needs two reset items to work properly on JH7110 SoC, so there is need to constrain the items' value to 2, other platforms have 1 reset item at most. Reviewed-by: Rob Herring Signed-off-by: Walker Chen Link: https://lore.kernel.org/r/20230322094820.24738-2-walker.chen@starfivetech.com Signed-off-by: Vinod Koul --- .../bindings/dma/snps,dw-axi-dmac.yaml | 23 ++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml index 5c81194e2300..363cf8bd150d 100644 --- a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml +++ b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.yaml @@ -20,6 +20,7 @@ properties: enum: - snps,axi-dma-1.01a - intel,kmb-axi-dma + - starfive,jh7110-axi-dma reg: minItems: 1 @@ -58,7 +59,8 @@ properties: maximum: 8 resets: - maxItems: 1 + minItems: 1 + maxItems: 2 snps,dma-masters: description: | @@ -109,6 +111,25 @@ required: - snps,priority - snps,block-size +if: + properties: + compatible: + contains: + enum: + - starfive,jh7110-axi-dma +then: + properties: + resets: + minItems: 2 + items: + - description: AXI reset line + - description: AHB reset line + - description: module reset +else: + properties: + resets: + maxItems: 1 + additionalProperties: false examples: -- GitLab From 0c40bfb4c2dfad00a15337bb6213f92a797e3695 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:28 -0700 Subject: [PATCH 2789/5631] dmaengine: idxd: make misc interrupt one shot Current code continuously processes the interrupt as long as the hardware is setting the status bit. There's no reason to do that since the threaded handler will get called again if another interrupt is asserted. Also through testing, it has shown that if a misprogrammed (or malicious) agent can continuously submit descriptors with bad completion record and causes errors to be reported via the misc interrupt. Continuous processing by the thread can cause software hang watchdog to kick off since the thread isn't giving up the CPU. Reported-by: Sanjay Kumar Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-2-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/irq.c | 38 ++++++++++++-------------------------- 1 file changed, 12 insertions(+), 26 deletions(-) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index aa314ebec587..0d639303b515 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -217,13 +217,22 @@ static void idxd_int_handle_revoke(struct work_struct *work) kfree(revoke); } -static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) +irqreturn_t idxd_misc_thread(int vec, void *data) { + struct idxd_irq_entry *irq_entry = data; + struct idxd_device *idxd = ie_to_idxd(irq_entry); struct device *dev = &idxd->pdev->dev; union gensts_reg gensts; u32 val = 0; int i; bool err = false; + u32 cause; + + cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); + if (!cause) + return IRQ_NONE; + + iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); if (cause & IDXD_INTC_HALT_STATE) goto halt; @@ -301,7 +310,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) val); if (!err) - return 0; + goto out; halt: gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); @@ -324,33 +333,10 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) "idxd halted, need %s.\n", gensts.reset_type == IDXD_DEVICE_RESET_FLR ? "FLR" : "system reset"); - return -ENXIO; } } - return 0; -} - -irqreturn_t idxd_misc_thread(int vec, void *data) -{ - struct idxd_irq_entry *irq_entry = data; - struct idxd_device *idxd = ie_to_idxd(irq_entry); - int rc; - u32 cause; - - cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); - if (cause) - iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); - - while (cause) { - rc = process_misc_interrupts(idxd, cause); - if (rc < 0) - break; - cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); - if (cause) - iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); - } - +out: return IRQ_HANDLED; } -- GitLab From 1649091f9180470f96f001724a4902d5d82bbd75 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:29 -0700 Subject: [PATCH 2790/5631] dmaengine: idxd: add event log size sysfs attribute Add support for changing of the event log size. Event log is a feature added to DSA 2.0 hardware to improve error reporting. It supersedes the SWERROR register on DSA 1.0 hardware and hope to prevent loss of reported errors. The error log size determines how many error entries supported for the device. It can be configured by the user via sysfs attribute. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-3-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- .../ABI/stable/sysfs-driver-dma-idxd | 8 +++ drivers/dma/idxd/idxd.h | 5 ++ drivers/dma/idxd/init.c | 23 ++++++++ drivers/dma/idxd/registers.h | 7 ++- drivers/dma/idxd/sysfs.c | 52 +++++++++++++++++++ 5 files changed, 94 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index d5e3dd3d8434..e01916611452 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -144,6 +144,14 @@ Description: IAA (IAX) capability mask. Exported to user space for application consumption. This attribute should only be visible on IAA devices that are version 2 or later. +What: /sys/bus/dsa/devices/dsa/event_log_size +Date: Sept 14, 2022 +KernelVersion: 6.4.0 +Contact: dmaengine@vger.kernel.org +Description: The event log size to be configured. Default is 64 entries and + occupies 4k size if the evl entry is 64 bytes. It's visible + only on platforms that support the capability. + What: /sys/bus/dsa/devices/wq./block_on_fault Date: Oct 27, 2020 KernelVersion: 5.11.0 diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index eca2c9d76db6..2a71273f1822 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -261,6 +261,10 @@ struct idxd_driver_data { int align; }; +struct idxd_evl { + u16 size; +}; + struct idxd_device { struct idxd_dev idxd_dev; struct idxd_driver_data *data; @@ -317,6 +321,7 @@ struct idxd_device { struct idxd_pmu *idxd_pmu; unsigned long *opcap_bmap; + struct idxd_evl *evl; }; /* IDXD software descriptor */ diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index a78cfd361c04..525de59df82a 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -331,6 +331,23 @@ static void idxd_cleanup_internals(struct idxd_device *idxd) destroy_workqueue(idxd->wq); } +static int idxd_init_evl(struct idxd_device *idxd) +{ + struct device *dev = &idxd->pdev->dev; + struct idxd_evl *evl; + + if (idxd->hw.gen_cap.evl_support == 0) + return 0; + + evl = kzalloc_node(sizeof(*evl), GFP_KERNEL, dev_to_node(dev)); + if (!evl) + return -ENOMEM; + + evl->size = IDXD_EVL_SIZE_MIN; + idxd->evl = evl; + return 0; +} + static int idxd_setup_internals(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; @@ -356,8 +373,14 @@ static int idxd_setup_internals(struct idxd_device *idxd) goto err_wkq_create; } + rc = idxd_init_evl(idxd); + if (rc < 0) + goto err_evl; + return 0; + err_evl: + destroy_workqueue(idxd->wq); err_wkq_create: for (i = 0; i < idxd->max_groups; i++) put_device(group_confdev(idxd->groups[i])); diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 338289a66f00..ea3a499a3c3c 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -31,7 +31,9 @@ union gen_cap_reg { u64 rsvd:3; u64 dest_readback:1; u64 drain_readback:1; - u64 rsvd2:6; + u64 rsvd2:3; + u64 evl_support:2; + u64 rsvd4:1; u64 max_xfer_shift:5; u64 max_batch_shift:4; u64 max_ims_mult:6; @@ -297,6 +299,9 @@ union iaa_cap_reg { #define IDXD_IAACAP_OFFSET 0x180 +#define IDXD_EVL_SIZE_MIN 0x0040 +#define IDXD_EVL_SIZE_MAX 0xffff + union msix_perm { struct { u32 rsvd:2; diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 2eba8cab25a1..85644e5bde83 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1573,6 +1573,46 @@ static ssize_t iaa_cap_show(struct device *dev, } static DEVICE_ATTR_RO(iaa_cap); +static ssize_t event_log_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_device *idxd = confdev_to_idxd(dev); + + if (!idxd->evl) + return -EOPNOTSUPP; + + return sysfs_emit(buf, "%u\n", idxd->evl->size); +} + +static ssize_t event_log_size_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_device *idxd = confdev_to_idxd(dev); + unsigned long val; + int rc; + + if (!idxd->evl) + return -EOPNOTSUPP; + + rc = kstrtoul(buf, 10, &val); + if (rc < 0) + return -EINVAL; + + if (idxd->state == IDXD_DEV_ENABLED) + return -EPERM; + + if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) + return -EPERM; + + if (val < IDXD_EVL_SIZE_MIN || val > IDXD_EVL_SIZE_MAX) + return -EINVAL; + + idxd->evl->size = val; + return count; +} +static DEVICE_ATTR_RW(event_log_size); + static bool idxd_device_attr_max_batch_size_invisible(struct attribute *attr, struct idxd_device *idxd) { @@ -1603,6 +1643,13 @@ static bool idxd_device_attr_iaa_cap_invisible(struct attribute *attr, idxd->hw.version < DEVICE_VERSION_2); } +static bool idxd_device_attr_event_log_size_invisible(struct attribute *attr, + struct idxd_device *idxd) +{ + return (attr == &dev_attr_event_log_size.attr && + !idxd->hw.gen_cap.evl_support); +} + static umode_t idxd_device_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { @@ -1618,6 +1665,9 @@ static umode_t idxd_device_attr_visible(struct kobject *kobj, if (idxd_device_attr_iaa_cap_invisible(attr, idxd)) return 0; + if (idxd_device_attr_event_log_size_invisible(attr, idxd)) + return 0; + return attr->mode; } @@ -1644,6 +1694,7 @@ static struct attribute *idxd_device_attributes[] = { &dev_attr_cdev_major.attr, &dev_attr_cmd_status.attr, &dev_attr_iaa_cap.attr, + &dev_attr_event_log_size.attr, NULL, }; @@ -1665,6 +1716,7 @@ static void idxd_conf_device_release(struct device *dev) bitmap_free(idxd->wq_enable_map); kfree(idxd->wqs); kfree(idxd->engines); + kfree(idxd->evl); ida_free(&idxd_ida, idxd->id); bitmap_free(idxd->opcap_bmap); kfree(idxd); -- GitLab From 244da66cda359227d80ccb41dbcb99da40eae186 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:30 -0700 Subject: [PATCH 2791/5631] dmaengine: idxd: setup event log configuration Add setup of event log feature for supported device. Event log addresses error reporting that was lacking in gen 1 DSA devices where a second error event does not get reported when a first event is pending software handling. The event log allows a circular buffer that the device can push error events to. It is up to the user to create a large enough event log ring in order to capture the expected events. The evl size can be set in the device sysfs attribute. By default 64 entries are supported as minimal when event log is enabled. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-4-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/device.c | 89 +++++++++++++++++++++++++++++++++++- drivers/dma/idxd/idxd.h | 19 ++++++++ drivers/dma/idxd/init.c | 1 + drivers/dma/idxd/registers.h | 72 ++++++++++++++++++++++++++++- drivers/dma/idxd/sysfs.c | 3 +- include/uapi/linux/idxd.h | 1 + 6 files changed, 181 insertions(+), 4 deletions(-) diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 5f321f3b4242..230fe9bb56ae 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -752,6 +752,83 @@ void idxd_device_clear_state(struct idxd_device *idxd) spin_unlock(&idxd->dev_lock); } +static int idxd_device_evl_setup(struct idxd_device *idxd) +{ + union gencfg_reg gencfg; + union evlcfg_reg evlcfg; + union genctrl_reg genctrl; + struct device *dev = &idxd->pdev->dev; + void *addr; + dma_addr_t dma_addr; + int size; + struct idxd_evl *evl = idxd->evl; + + if (!evl) + return 0; + + size = evl_size(idxd); + /* + * Address needs to be page aligned. However, dma_alloc_coherent() provides + * at minimal page size aligned address. No manual alignment required. + */ + addr = dma_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL); + if (!addr) + return -ENOMEM; + + memset(addr, 0, size); + + spin_lock(&evl->lock); + evl->log = addr; + evl->dma = dma_addr; + evl->log_size = size; + + memset(&evlcfg, 0, sizeof(evlcfg)); + evlcfg.bits[0] = dma_addr & GENMASK(63, 12); + evlcfg.size = evl->size; + + iowrite64(evlcfg.bits[0], idxd->reg_base + IDXD_EVLCFG_OFFSET); + iowrite64(evlcfg.bits[1], idxd->reg_base + IDXD_EVLCFG_OFFSET + 8); + + genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET); + genctrl.evl_int_en = 1; + iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET); + + gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); + gencfg.evl_en = 1; + iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); + + spin_unlock(&evl->lock); + return 0; +} + +static void idxd_device_evl_free(struct idxd_device *idxd) +{ + union gencfg_reg gencfg; + union genctrl_reg genctrl; + struct device *dev = &idxd->pdev->dev; + struct idxd_evl *evl = idxd->evl; + + gencfg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET); + if (!gencfg.evl_en) + return; + + spin_lock(&evl->lock); + gencfg.evl_en = 0; + iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET); + + genctrl.bits = ioread32(idxd->reg_base + IDXD_GENCTRL_OFFSET); + genctrl.evl_int_en = 0; + iowrite32(genctrl.bits, idxd->reg_base + IDXD_GENCTRL_OFFSET); + + iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET); + iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8); + + dma_free_coherent(dev, evl->log_size, evl->log, evl->dma); + evl->log = NULL; + evl->size = IDXD_EVL_SIZE_MIN; + spin_unlock(&evl->lock); +} + static void idxd_group_config_write(struct idxd_group *group) { struct idxd_device *idxd = group->idxd; @@ -1451,15 +1528,24 @@ int idxd_device_drv_probe(struct idxd_dev *idxd_dev) if (rc < 0) return -ENXIO; + rc = idxd_device_evl_setup(idxd); + if (rc < 0) { + idxd->cmd_status = IDXD_SCMD_DEV_EVL_ERR; + return rc; + } + /* Start device */ rc = idxd_device_enable(idxd); - if (rc < 0) + if (rc < 0) { + idxd_device_evl_free(idxd); return rc; + } /* Setup DMA device without channels */ rc = idxd_register_dma_device(idxd); if (rc < 0) { idxd_device_disable(idxd); + idxd_device_evl_free(idxd); idxd->cmd_status = IDXD_SCMD_DEV_DMA_ERR; return rc; } @@ -1488,6 +1574,7 @@ void idxd_device_drv_remove(struct idxd_dev *idxd_dev) idxd_device_disable(idxd); if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) idxd_device_reset(idxd); + idxd_device_evl_free(idxd); } static enum idxd_dev_type dev_types[] = { diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 2a71273f1822..c74681f02b18 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -262,7 +262,15 @@ struct idxd_driver_data { }; struct idxd_evl { + /* Lock to protect event log access. */ + spinlock_t lock; + void *log; + dma_addr_t dma; + /* Total size of event log = number of entries * entry size. */ + unsigned int log_size; + /* The number of entries in the event log. */ u16 size; + u16 head; }; struct idxd_device { @@ -324,6 +332,17 @@ struct idxd_device { struct idxd_evl *evl; }; +static inline unsigned int evl_ent_size(struct idxd_device *idxd) +{ + return idxd->hw.gen_cap.evl_support ? + (32 * (1 << idxd->hw.gen_cap.evl_support)) : 0; +} + +static inline unsigned int evl_size(struct idxd_device *idxd) +{ + return idxd->evl->size * evl_ent_size(idxd); +} + /* IDXD software descriptor */ struct idxd_desc { union { diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 525de59df82a..f44719a11c95 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -343,6 +343,7 @@ static int idxd_init_evl(struct idxd_device *idxd) if (!evl) return -ENOMEM; + spin_lock_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; idxd->evl = evl; return 0; diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index ea3a499a3c3c..11bb97cf7481 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -3,6 +3,8 @@ #ifndef _IDXD_REGISTERS_H_ #define _IDXD_REGISTERS_H_ +#include + /* PCI Config */ #define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe @@ -119,7 +121,8 @@ union gencfg_reg { u32 rdbuf_limit:8; u32 rsvd:4; u32 user_int_en:1; - u32 rsvd2:19; + u32 evl_en:1; + u32 rsvd2:18; }; u32 bits; } __packed; @@ -129,7 +132,8 @@ union genctrl_reg { struct { u32 softerr_int_en:1; u32 halt_int_en:1; - u32 rsvd:30; + u32 evl_int_en:1; + u32 rsvd:29; }; u32 bits; } __packed; @@ -299,6 +303,21 @@ union iaa_cap_reg { #define IDXD_IAACAP_OFFSET 0x180 +#define IDXD_EVLCFG_OFFSET 0xe0 +union evlcfg_reg { + struct { + u64 pasid_en:1; + u64 priv:1; + u64 rsvd:10; + u64 base_addr:52; + + u64 size:16; + u64 pasid:20; + u64 rsvd2:28; + }; + u64 bits[2]; +} __packed; + #define IDXD_EVL_SIZE_MIN 0x0040 #define IDXD_EVL_SIZE_MAX 0xffff @@ -539,4 +558,53 @@ union filter_cfg { u64 val; } __packed; +struct __evl_entry { + u64 rsvd:2; + u64 desc_valid:1; + u64 wq_idx_valid:1; + u64 batch:1; + u64 fault_rw:1; + u64 priv:1; + u64 err_info_valid:1; + u64 error:8; + u64 wq_idx:8; + u64 batch_id:8; + u64 operation:8; + u64 pasid:20; + u64 rsvd2:4; + + u16 batch_idx; + u16 rsvd3; + union { + /* Invalid Flags 0x11 */ + u32 invalid_flags; + /* Invalid Int Handle 0x19 */ + /* Page fault 0x1a */ + /* Page fault 0x06, 0x1f, only operand_id */ + /* Page fault before drain or in batch, 0x26, 0x27 */ + struct { + u16 int_handle; + u16 rci:1; + u16 ims:1; + u16 rcr:1; + u16 first_err_in_batch:1; + u16 rsvd4_2:9; + u16 operand_id:3; + }; + }; + u64 fault_addr; + u64 rsvd5; +} __packed; + +struct dsa_evl_entry { + struct __evl_entry e; + struct dsa_completion_record cr; +} __packed; + +struct iax_evl_entry { + struct __evl_entry e; + u64 rsvd[4]; + struct iax_completion_record cr; +} __packed; + #endif diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 85644e5bde83..163fdfaa5022 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1605,7 +1605,8 @@ static ssize_t event_log_size_store(struct device *dev, if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; - if (val < IDXD_EVL_SIZE_MIN || val > IDXD_EVL_SIZE_MAX) + if (val < IDXD_EVL_SIZE_MIN || val > IDXD_EVL_SIZE_MAX || + (val * evl_ent_size(idxd) > ULONG_MAX - idxd->evl->dma)) return -EINVAL; idxd->evl->size = val; diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index fc47635b57dc..5d05bf12f2bd 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -30,6 +30,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, IDXD_SCMD_WQ_USER_NO_IOMMU = 0x80110000, + IDXD_SCMD_DEV_EVL_ERR = 0x80120000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 -- GitLab From 2f431ba908d2ef05da478d10925207728f1ff483 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:31 -0700 Subject: [PATCH 2792/5631] dmaengine: idxd: add interrupt handling for event log An event log interrupt is raised in the misc interrupt INTCAUSE register when an event is written by the hardware. Add basic event log processing support to the interrupt handler. The event log is a ring where the hardware owns the tail and the software owns the head. The hardware will advance the tail index when an additional event has been pushed to memory. The software will process the log entry and then advances the head. The log is full when (tail + 1) % log_size = head. The hardware will stop writing when the log is full. The user is expected to create a log size large enough to handle all the expected events. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-5-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/irq.c | 48 ++++++++++++++++++++++++++++++++++++ drivers/dma/idxd/registers.h | 19 ++++++++++++++ include/uapi/linux/idxd.h | 1 + 3 files changed, 68 insertions(+) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 0d639303b515..52b8b7d9db22 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -217,6 +217,49 @@ static void idxd_int_handle_revoke(struct work_struct *work) kfree(revoke); } +static void process_evl_entry(struct idxd_device *idxd, struct __evl_entry *entry_head) +{ + struct device *dev = &idxd->pdev->dev; + u8 status; + + status = DSA_COMP_STATUS(entry_head->error); + dev_warn_ratelimited(dev, "Device error %#x operation: %#x fault addr: %#llx\n", + status, entry_head->operation, entry_head->fault_addr); +} + +static void process_evl_entries(struct idxd_device *idxd) +{ + union evl_status_reg evl_status; + unsigned int h, t; + struct idxd_evl *evl = idxd->evl; + struct __evl_entry *entry_head; + unsigned int ent_size = evl_ent_size(idxd); + u32 size; + + evl_status.bits = 0; + evl_status.int_pending = 1; + + spin_lock(&evl->lock); + /* Clear interrupt pending bit */ + iowrite32(evl_status.bits_upper32, + idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); + h = evl->head; + evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); + t = evl_status.tail; + size = idxd->evl->size; + + while (h != t) { + entry_head = (struct __evl_entry *)(evl->log + (h * ent_size)); + process_evl_entry(idxd, entry_head); + h = (h + 1) % size; + } + + evl->head = h; + evl_status.head = h; + iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); + spin_unlock(&evl->lock); +} + irqreturn_t idxd_misc_thread(int vec, void *data) { struct idxd_irq_entry *irq_entry = data; @@ -304,6 +347,11 @@ irqreturn_t idxd_misc_thread(int vec, void *data) perfmon_counter_overflow(idxd); } + if (cause & IDXD_INTC_EVL) { + val |= IDXD_INTC_EVL; + process_evl_entries(idxd); + } + val ^= cause; if (val) dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n", diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 11bb97cf7481..148db94f9373 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -168,6 +168,7 @@ enum idxd_device_reset_type { #define IDXD_INTC_OCCUPY 0x04 #define IDXD_INTC_PERFMON_OVFL 0x08 #define IDXD_INTC_HALT_STATE 0x10 +#define IDXD_INTC_EVL 0x20 #define IDXD_INTC_INT_HANDLE_REVOKED 0x80000000 #define IDXD_CMD_OFFSET 0xa0 @@ -558,6 +559,24 @@ union filter_cfg { u64 val; } __packed; +#define IDXD_EVLSTATUS_OFFSET 0xf0 + +union evl_status_reg { + struct { + u32 head:16; + u32 rsvd:16; + u32 tail:16; + u32 rsvd2:14; + u32 int_pending:1; + u32 rsvd3:1; + }; + struct { + u32 bits_lower32; + u32 bits_upper32; + }; + u64 bits; +} __packed; + struct __evl_entry { u64 rsvd:2; u64 desc_valid:1; diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 5d05bf12f2bd..0bc8eea18586 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -170,6 +170,7 @@ enum iax_completion_status { #define DSA_COMP_STATUS_MASK 0x7f #define DSA_COMP_STATUS_WRITE 0x80 +#define DSA_COMP_STATUS(status) ((status) & DSA_COMP_STATUS_MASK) struct dsa_hw_desc { uint32_t pasid:20; -- GitLab From 5fbe6503b52f5665560584f62adab5db70ac910e Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:32 -0700 Subject: [PATCH 2793/5631] dmanegine: idxd: add debugfs for event log dump Add debugfs entry to dump the content of the event log for debugging. The function will dump all non-zero entries in the event log. It will note which entries are processed and which entries are still pending processing at the time of the dump. The entries may not always be in chronological order due to the log is a circular buffer. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-6-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/Makefile | 2 +- drivers/dma/idxd/debugfs.c | 138 +++++++++++++++++++++++++++++++++++++ drivers/dma/idxd/idxd.h | 9 +++ drivers/dma/idxd/init.c | 12 ++++ include/uapi/linux/idxd.h | 6 +- 5 files changed, 164 insertions(+), 3 deletions(-) create mode 100644 drivers/dma/idxd/debugfs.c diff --git a/drivers/dma/idxd/Makefile b/drivers/dma/idxd/Makefile index a1e9f2b3a37c..dc096839ac63 100644 --- a/drivers/dma/idxd/Makefile +++ b/drivers/dma/idxd/Makefile @@ -1,7 +1,7 @@ ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=IDXD obj-$(CONFIG_INTEL_IDXD) += idxd.o -idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o +idxd-y := init.o irq.o device.o sysfs.o submit.o dma.o cdev.o debugfs.o idxd-$(CONFIG_INTEL_IDXD_PERFMON) += perfmon.o diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c new file mode 100644 index 000000000000..9cfbd9b14c4c --- /dev/null +++ b/drivers/dma/idxd/debugfs.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2021 Intel Corporation. All rights rsvd. */ +#include +#include +#include +#include +#include +#include +#include +#include "idxd.h" +#include "registers.h" + +static struct dentry *idxd_debugfs_dir; + +static void dump_event_entry(struct idxd_device *idxd, struct seq_file *s, + u16 index, int *count, bool processed) +{ + struct idxd_evl *evl = idxd->evl; + struct dsa_evl_entry *entry; + struct dsa_completion_record *cr; + u64 *raw; + int i; + int evl_strides = evl_ent_size(idxd) / sizeof(u64); + + entry = (struct dsa_evl_entry *)evl->log + index; + + if (!entry->e.desc_valid) + return; + + seq_printf(s, "Event Log entry %d (real index %u) processed: %u\n", + *count, index, processed); + + seq_printf(s, "desc valid %u wq idx valid %u\n" + "batch %u fault rw %u priv %u error 0x%x\n" + "wq idx %u op %#x pasid %u batch idx %u\n" + "fault addr %#llx\n", + entry->e.desc_valid, entry->e.wq_idx_valid, + entry->e.batch, entry->e.fault_rw, entry->e.priv, + entry->e.error, entry->e.wq_idx, entry->e.operation, + entry->e.pasid, entry->e.batch_idx, entry->e.fault_addr); + + cr = &entry->cr; + seq_printf(s, "status %#x result %#x fault_info %#x bytes_completed %u\n" + "fault addr %#llx inv flags %#x\n\n", + cr->status, cr->result, cr->fault_info, cr->bytes_completed, + cr->fault_addr, cr->invalid_flags); + + raw = (u64 *)entry; + + for (i = 0; i < evl_strides; i++) + seq_printf(s, "entry[%d] = %#llx\n", i, raw[i]); + + seq_puts(s, "\n"); + *count += 1; +} + +static int debugfs_evl_show(struct seq_file *s, void *d) +{ + struct idxd_device *idxd = s->private; + struct idxd_evl *evl = idxd->evl; + union evl_status_reg evl_status; + u16 h, t, evl_size, i; + int count = 0; + bool processed = true; + + if (!evl || !evl->log) + return 0; + + spin_lock(&evl->lock); + + h = evl->head; + evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); + t = evl_status.tail; + evl_size = evl->size; + + seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n", + evl_status.head, evl_status.tail, evl_status.int_pending); + + i = t; + while (1) { + i = (i + 1) % evl_size; + if (i == t) + break; + + if (processed && i == h) + processed = false; + dump_event_entry(idxd, s, i, &count, processed); + } + + spin_unlock(&evl->lock); + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(debugfs_evl); + +int idxd_device_init_debugfs(struct idxd_device *idxd) +{ + if (IS_ERR_OR_NULL(idxd_debugfs_dir)) + return 0; + + idxd->dbgfs_dir = debugfs_create_dir(dev_name(idxd_confdev(idxd)), idxd_debugfs_dir); + if (IS_ERR(idxd->dbgfs_dir)) + return PTR_ERR(idxd->dbgfs_dir); + + if (idxd->evl) { + idxd->dbgfs_evl_file = debugfs_create_file("event_log", 0400, + idxd->dbgfs_dir, idxd, + &debugfs_evl_fops); + if (IS_ERR(idxd->dbgfs_evl_file)) { + debugfs_remove_recursive(idxd->dbgfs_dir); + idxd->dbgfs_dir = NULL; + return PTR_ERR(idxd->dbgfs_evl_file); + } + } + + return 0; +} + +void idxd_device_remove_debugfs(struct idxd_device *idxd) +{ + debugfs_remove_recursive(idxd->dbgfs_dir); +} + +int idxd_init_debugfs(void) +{ + if (!debugfs_initialized()) + return 0; + + idxd_debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); + if (IS_ERR(idxd_debugfs_dir)) + return PTR_ERR(idxd_debugfs_dir); + return 0; +} + +void idxd_remove_debugfs(void) +{ + debugfs_remove_recursive(idxd_debugfs_dir); +} diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index c74681f02b18..b923b90b7299 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -330,6 +330,9 @@ struct idxd_device { unsigned long *opcap_bmap; struct idxd_evl *evl; + + struct dentry *dbgfs_dir; + struct dentry *dbgfs_evl_file; }; static inline unsigned int evl_ent_size(struct idxd_device *idxd) @@ -704,4 +707,10 @@ static inline void perfmon_init(void) {} static inline void perfmon_exit(void) {} #endif +/* debugfs */ +int idxd_device_init_debugfs(struct idxd_device *idxd); +void idxd_device_remove_debugfs(struct idxd_device *idxd); +int idxd_init_debugfs(void); +void idxd_remove_debugfs(void); + #endif diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index f44719a11c95..e21c4b7a1d32 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -669,6 +669,10 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_dev_register; } + rc = idxd_device_init_debugfs(idxd); + if (rc) + dev_warn(dev, "IDXD debugfs failed to setup\n"); + dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); @@ -731,6 +735,7 @@ static void idxd_remove(struct pci_dev *pdev) idxd_shutdown(pdev); if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); + idxd_device_remove_debugfs(idxd); irq_entry = idxd_get_ie(idxd, 0); free_irq(irq_entry->vector, irq_entry); @@ -788,6 +793,10 @@ static int __init idxd_init_module(void) if (err) goto err_cdev_register; + err = idxd_init_debugfs(); + if (err) + goto err_debugfs; + err = pci_register_driver(&idxd_pci_driver); if (err) goto err_pci_register; @@ -795,6 +804,8 @@ static int __init idxd_init_module(void) return 0; err_pci_register: + idxd_remove_debugfs(); +err_debugfs: idxd_cdev_remove(); err_cdev_register: idxd_driver_unregister(&idxd_user_drv); @@ -815,5 +826,6 @@ static void __exit idxd_exit_module(void) pci_unregister_driver(&idxd_pci_driver); idxd_cdev_remove(); perfmon_exit(); + idxd_remove_debugfs(); } module_exit(idxd_exit_module); diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 0bc8eea18586..e86199d09a91 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -311,7 +311,8 @@ struct dsa_completion_record { uint8_t result; uint8_t dif_status; }; - uint16_t rsvd; + uint8_t fault_info; + uint8_t rsvd; uint32_t bytes_completed; uint64_t fault_addr; union { @@ -368,7 +369,8 @@ struct dsa_raw_completion_record { struct iax_completion_record { volatile uint8_t status; uint8_t error_code; - uint16_t rsvd; + uint8_t fault_info; + uint8_t rsvd; uint32_t bytes_completed; uint64_t fault_addr; uint32_t invalid_flags; -- GitLab From 2f30decd2f23a376d2ed73dfe4c601421edf501a Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:33 -0700 Subject: [PATCH 2794/5631] dmaengine: idxd: add per DSA wq workqueue for processing cr faults Add a workqueue for user submitted completion record fault processing. The workqueue creation and destruction lifetime will be tied to the user sub-driver since it will only be used when the wq is a user type. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-7-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 11 +++++++++++ drivers/dma/idxd/idxd.h | 1 + 2 files changed, 12 insertions(+) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 674bfefca088..cbe29e1a6a44 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -330,6 +330,13 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) } mutex_lock(&wq->wq_lock); + + wq->wq = create_workqueue(dev_name(wq_confdev(wq))); + if (!wq->wq) { + rc = -ENOMEM; + goto wq_err; + } + wq->type = IDXD_WQT_USER; rc = drv_enable_wq(wq); if (rc < 0) @@ -348,7 +355,9 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) err_cdev: drv_disable_wq(wq); err: + destroy_workqueue(wq->wq); wq->type = IDXD_WQT_NONE; +wq_err: mutex_unlock(&wq->wq_lock); return rc; } @@ -361,6 +370,8 @@ static void idxd_user_drv_remove(struct idxd_dev *idxd_dev) idxd_wq_del_cdev(wq); drv_disable_wq(wq); wq->type = IDXD_WQT_NONE; + destroy_workqueue(wq->wq); + wq->wq = NULL; mutex_unlock(&wq->wq_lock); } diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index b923b90b7299..6e56361ae658 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -185,6 +185,7 @@ struct idxd_wq { struct idxd_dev idxd_dev; struct idxd_cdev *idxd_cdev; struct wait_queue_head err_queue; + struct workqueue_struct *wq; struct idxd_device *idxd; int id; struct idxd_irq_entry ie; -- GitLab From c2f156bf168fb42cd6ecd0a8e2204dbe542b8516 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:34 -0700 Subject: [PATCH 2795/5631] dmaengine: idxd: create kmem cache for event log fault items Add a kmem cache per device for allocating event log fault context. The context allows an event log entry to be copied and passed to a software workqueue to be processed. Due to each device can have different sized event log entry depending on device type, it's not possible to have a global kmem cache. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-8-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/idxd.h | 10 ++++++++++ drivers/dma/idxd/init.c | 9 +++++++++ drivers/dma/idxd/sysfs.c | 1 + 3 files changed, 20 insertions(+) diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 6e56361ae658..c5d99c179902 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -274,6 +274,15 @@ struct idxd_evl { u16 head; }; +struct idxd_evl_fault { + struct work_struct work; + struct idxd_wq *wq; + u8 status; + + /* make this last member always */ + struct __evl_entry entry[]; +}; + struct idxd_device { struct idxd_dev idxd_dev; struct idxd_driver_data *data; @@ -331,6 +340,7 @@ struct idxd_device { unsigned long *opcap_bmap; struct idxd_evl *evl; + struct kmem_cache *evl_cache; struct dentry *dbgfs_dir; struct dentry *dbgfs_evl_file; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index e21c4b7a1d32..7828ac2d31aa 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -345,6 +345,15 @@ static int idxd_init_evl(struct idxd_device *idxd) spin_lock_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; + + idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)), + sizeof(struct idxd_evl_fault) + evl_ent_size(idxd), + 0, 0, NULL); + if (!idxd->evl_cache) { + kfree(evl); + return -ENOMEM; + } + idxd->evl = evl; return 0; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 163fdfaa5022..8b9dfa0d2b99 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1718,6 +1718,7 @@ static void idxd_conf_device_release(struct device *dev) kfree(idxd->wqs); kfree(idxd->engines); kfree(idxd->evl); + kmem_cache_destroy(idxd->evl_cache); ida_free(&idxd_ida, idxd->id); bitmap_free(idxd->opcap_bmap); kfree(idxd); -- GitLab From b022f59725f0ae846191abbd6d2e611d7f60f826 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 7 Apr 2023 13:31:35 -0700 Subject: [PATCH 2796/5631] dmaengine: idxd: add idxd_copy_cr() to copy user completion record during page fault handling Define idxd_copy_cr() to copy completion record to fault address in user address that is found by work queue (wq) and PASID. It will be used to write the user's completion record that the hardware device is not able to write due to user completion record page fault. An xarray is added to associate the PASID and mm with the struct idxd_user_context so mm can be found by PASID and wq. It is called when handling the completion record fault in a kernel thread context. Switch to the mm using kthread_use_vm() and copy the completion record to the mm via copy_to_user(). Once the copy is completed, switch back to the current mm using kthread_unuse_mm(). Suggested-by: Christoph Hellwig Suggested-by: Jason Gunthorpe Suggested-by: Tony Luck Tested-by: Tony Zhu Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230407203143.2189681-9-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 107 +++++++++++++++++++++++++++++++++++++-- drivers/dma/idxd/idxd.h | 6 +++ drivers/dma/idxd/init.c | 2 + drivers/dma/idxd/sysfs.c | 1 + 4 files changed, 111 insertions(+), 5 deletions(-) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index cbe29e1a6a44..8b8a0a0fb054 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -11,7 +11,9 @@ #include #include #include +#include #include +#include #include "registers.h" #include "idxd.h" @@ -34,6 +36,7 @@ struct idxd_user_context { struct idxd_wq *wq; struct task_struct *task; unsigned int pasid; + struct mm_struct *mm; unsigned int flags; struct iommu_sva *sva; }; @@ -68,6 +71,19 @@ static inline struct idxd_wq *inode_wq(struct inode *inode) return idxd_cdev->wq; } +static void idxd_xa_pasid_remove(struct idxd_user_context *ctx) +{ + struct idxd_wq *wq = ctx->wq; + void *ptr; + + mutex_lock(&wq->uc_lock); + ptr = xa_cmpxchg(&wq->upasid_xa, ctx->pasid, ctx, NULL, GFP_KERNEL); + if (ptr != (void *)ctx) + dev_warn(&wq->idxd->pdev->dev, "xarray cmpxchg failed for pasid %u\n", + ctx->pasid); + mutex_unlock(&wq->uc_lock); +} + static int idxd_cdev_open(struct inode *inode, struct file *filp) { struct idxd_user_context *ctx; @@ -108,20 +124,26 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) pasid = iommu_sva_get_pasid(sva); if (pasid == IOMMU_PASID_INVALID) { - iommu_sva_unbind_device(sva); rc = -EINVAL; - goto failed; + goto failed_get_pasid; } ctx->sva = sva; ctx->pasid = pasid; + ctx->mm = current->mm; + + mutex_lock(&wq->uc_lock); + rc = xa_insert(&wq->upasid_xa, pasid, ctx, GFP_KERNEL); + mutex_unlock(&wq->uc_lock); + if (rc < 0) + dev_warn(dev, "PASID entry already exist in xarray.\n"); if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); - goto failed; + goto failed_set_pasid; } } } @@ -130,7 +152,13 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) mutex_unlock(&wq->wq_lock); return 0; - failed: +failed_set_pasid: + if (device_user_pasid_enabled(idxd)) + idxd_xa_pasid_remove(ctx); +failed_get_pasid: + if (device_user_pasid_enabled(idxd)) + iommu_sva_unbind_device(sva); +failed: mutex_unlock(&wq->wq_lock); kfree(ctx); return rc; @@ -161,8 +189,10 @@ static int idxd_cdev_release(struct inode *node, struct file *filep) } } - if (ctx->sva) + if (ctx->sva) { iommu_sva_unbind_device(ctx->sva); + idxd_xa_pasid_remove(ctx); + } kfree(ctx); mutex_lock(&wq->wq_lock); idxd_wq_put(wq); @@ -418,3 +448,70 @@ void idxd_cdev_remove(void) ida_destroy(&ictx[i].minor_ida); } } + +/** + * idxd_copy_cr - copy completion record to user address space found by wq and + * PASID + * @wq: work queue + * @pasid: PASID + * @addr: user fault address to write + * @cr: completion record + * @len: number of bytes to copy + * + * This is called by a work that handles completion record fault. + * + * Return: number of bytes copied. + */ +int idxd_copy_cr(struct idxd_wq *wq, ioasid_t pasid, unsigned long addr, + void *cr, int len) +{ + struct device *dev = &wq->idxd->pdev->dev; + int left = len, status_size = 1; + struct idxd_user_context *ctx; + struct mm_struct *mm; + + mutex_lock(&wq->uc_lock); + + ctx = xa_load(&wq->upasid_xa, pasid); + if (!ctx) { + dev_warn(dev, "No user context\n"); + goto out; + } + + mm = ctx->mm; + /* + * The completion record fault handling work is running in kernel + * thread context. It temporarily switches to the mm to copy cr + * to addr in the mm. + */ + kthread_use_mm(mm); + left = copy_to_user((void __user *)addr + status_size, cr + status_size, + len - status_size); + /* + * Copy status only after the rest of completion record is copied + * successfully so that the user gets the complete completion record + * when a non-zero status is polled. + */ + if (!left) { + u8 status; + + /* + * Ensure that the completion record's status field is written + * after the rest of the completion record has been written. + * This ensures that the user receives the correct completion + * record information once polling for a non-zero status. + */ + wmb(); + status = *(u8 *)cr; + if (put_user(status, (u8 __user *)addr)) + left += status_size; + } else { + left += status_size; + } + kthread_unuse_mm(mm); + +out: + mutex_unlock(&wq->uc_lock); + + return len - left; +} diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index c5d99c179902..b3f9a12adce2 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -215,6 +215,10 @@ struct idxd_wq { char name[WQ_NAME_SIZE + 1]; u64 max_xfer_bytes; u32 max_batch_size; + + /* Lock to protect upasid_xa access. */ + struct mutex uc_lock; + struct xarray upasid_xa; }; struct idxd_engine { @@ -702,6 +706,8 @@ void idxd_cdev_remove(void); int idxd_cdev_get_major(struct idxd_device *idxd); int idxd_wq_add_cdev(struct idxd_wq *wq); void idxd_wq_del_cdev(struct idxd_wq *wq); +int idxd_copy_cr(struct idxd_wq *wq, ioasid_t pasid, unsigned long addr, + void *buf, int len); /* perfmon */ #if IS_ENABLED(CONFIG_INTEL_IDXD_PERFMON) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 7828ac2d31aa..e6faff58733d 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -199,6 +199,8 @@ static int idxd_setup_wqs(struct idxd_device *idxd) } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } + mutex_init(&wq->uc_lock); + xa_init(&wq->upasid_xa); idxd->wqs[i] = wq; } diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 8b9dfa0d2b99..465d2e7627e4 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1292,6 +1292,7 @@ static void idxd_conf_wq_release(struct device *dev) bitmap_free(wq->opcap_bmap); kfree(wq->wqcfg); + xa_destroy(&wq->upasid_xa); kfree(wq); } -- GitLab From c40bd7d9737bdcfb02d42765bc6c59b338151123 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:36 -0700 Subject: [PATCH 2797/5631] dmaengine: idxd: process user page faults for completion record DSA supports page fault handling through PRS. However, the DMA engine that's processing the descriptor is blocked until the PRS response is received. Other workqueues sharing the engine are also blocked. Page fault handing by the driver with PRS disabled can be used to mitigate the stalling. With PRS disabled while ATS remain enabled, DSA handles page faults on a completion record by reporting an event in the event log. In this instance, the descriptor is completed and the event log contains the completion record address and the contents of the completion record. Add support to the event log handling code to fault in the completion record and copy the content of the completion record to user memory. A bitmap is introduced to keep track of discarded event log entries. When the user process initiates ->release() of the char device, it no longer is interested in any remaining event log entries tied to the relevant wq and PASID. The driver will mark the event log entry index in the bitmap. Upon encountering the entries during processing, the event log handler will just clear the bitmap bit and skip the entry rather than attempt to process the event log entry. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-10-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 30 ++++++++++++++ drivers/dma/idxd/device.c | 22 +++++++++- drivers/dma/idxd/idxd.h | 2 + drivers/dma/idxd/init.c | 2 + drivers/dma/idxd/irq.c | 87 ++++++++++++++++++++++++++++++++++++--- include/uapi/linux/idxd.h | 1 + 6 files changed, 137 insertions(+), 7 deletions(-) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 8b8a0a0fb054..0a51c33198f6 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -164,6 +164,35 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) return rc; } +static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) +{ + struct idxd_device *idxd = wq->idxd; + struct idxd_evl *evl = idxd->evl; + union evl_status_reg status; + u16 h, t, size; + int ent_size = evl_ent_size(idxd); + struct __evl_entry *entry_head; + + if (!evl) + return; + + spin_lock(&evl->lock); + status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); + t = status.tail; + h = evl->head; + size = evl->size; + + while (h != t) { + entry_head = (struct __evl_entry *)(evl->log + (h * ent_size)); + if (entry_head->pasid == pasid && entry_head->wq_idx == wq->id) + set_bit(h, evl->bmap); + h = (h + 1) % size; + } + spin_unlock(&evl->lock); + + drain_workqueue(wq->wq); +} + static int idxd_cdev_release(struct inode *node, struct file *filep) { struct idxd_user_context *ctx = filep->private_data; @@ -190,6 +219,7 @@ static int idxd_cdev_release(struct inode *node, struct file *filep) } if (ctx->sva) { + idxd_cdev_evl_drain_pasid(wq, ctx->pasid); iommu_sva_unbind_device(ctx->sva); idxd_xa_pasid_remove(ctx); } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 230fe9bb56ae..fd97b2b58734 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -762,18 +762,29 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) dma_addr_t dma_addr; int size; struct idxd_evl *evl = idxd->evl; + unsigned long *bmap; + int rc; if (!evl) return 0; size = evl_size(idxd); + + bmap = bitmap_zalloc(size, GFP_KERNEL); + if (!bmap) { + rc = -ENOMEM; + goto err_bmap; + } + /* * Address needs to be page aligned. However, dma_alloc_coherent() provides * at minimal page size aligned address. No manual alignment required. */ addr = dma_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL); - if (!addr) - return -ENOMEM; + if (!addr) { + rc = -ENOMEM; + goto err_alloc; + } memset(addr, 0, size); @@ -781,6 +792,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) evl->log = addr; evl->dma = dma_addr; evl->log_size = size; + evl->bmap = bmap; memset(&evlcfg, 0, sizeof(evlcfg)); evlcfg.bits[0] = dma_addr & GENMASK(63, 12); @@ -799,6 +811,11 @@ static int idxd_device_evl_setup(struct idxd_device *idxd) spin_unlock(&evl->lock); return 0; + +err_alloc: + bitmap_free(bmap); +err_bmap: + return rc; } static void idxd_device_evl_free(struct idxd_device *idxd) @@ -824,6 +841,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd) iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8); dma_free_coherent(dev, evl->log_size, evl->log, evl->dma); + bitmap_free(evl->bmap); evl->log = NULL; evl->size = IDXD_EVL_SIZE_MIN; spin_unlock(&evl->lock); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index b3f9a12adce2..3963c83165a6 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -264,6 +264,7 @@ struct idxd_driver_data { struct device_type *dev_type; int compl_size; int align; + int evl_cr_off; }; struct idxd_evl { @@ -276,6 +277,7 @@ struct idxd_evl { /* The number of entries in the event log. */ u16 size; u16 head; + unsigned long *bmap; }; struct idxd_evl_fault { diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index e6faff58733d..18344593b83f 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -46,6 +46,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .compl_size = sizeof(struct dsa_completion_record), .align = 32, .dev_type = &dsa_device_type, + .evl_cr_off = offsetof(struct dsa_evl_entry, cr), }, [IDXD_TYPE_IAX] = { .name_prefix = "iax", @@ -53,6 +54,7 @@ static struct idxd_driver_data idxd_driver_data[] = { .compl_size = sizeof(struct iax_completion_record), .align = 64, .dev_type = &iax_device_type, + .evl_cr_off = offsetof(struct iax_evl_entry, cr), }, }; diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 52b8b7d9db22..96983975f974 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -7,6 +7,8 @@ #include #include #include +#include +#include #include #include "../dmaengine.h" #include "idxd.h" @@ -217,14 +219,89 @@ static void idxd_int_handle_revoke(struct work_struct *work) kfree(revoke); } -static void process_evl_entry(struct idxd_device *idxd, struct __evl_entry *entry_head) +static void idxd_evl_fault_work(struct work_struct *work) +{ + struct idxd_evl_fault *fault = container_of(work, struct idxd_evl_fault, work); + struct idxd_wq *wq = fault->wq; + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + struct __evl_entry *entry_head = fault->entry; + void *cr = (void *)entry_head + idxd->data->evl_cr_off; + int cr_size = idxd->data->compl_size, copied; + + switch (fault->status) { + case DSA_COMP_CRA_XLAT: + case DSA_COMP_DRAIN_EVL: + /* + * Copy completion record to fault_addr in user address space + * that is found by wq and PASID. + */ + copied = idxd_copy_cr(wq, entry_head->pasid, + entry_head->fault_addr, + cr, cr_size); + /* + * The task that triggered the page fault is unknown currently + * because multiple threads may share the user address + * space or the task exits already before this fault. + * So if the copy fails, SIGSEGV can not be sent to the task. + * Just print an error for the failure. The user application + * waiting for the completion record will time out on this + * failure. + */ + if (copied != cr_size) { + dev_dbg_ratelimited(dev, "Failed to write to completion record. (%d:%d)\n", + cr_size, copied); + } + break; + default: + dev_dbg_ratelimited(dev, "Unrecognized error code: %#x\n", + DSA_COMP_STATUS(entry_head->error)); + break; + } + + kmem_cache_free(idxd->evl_cache, fault); +} + +static void process_evl_entry(struct idxd_device *idxd, + struct __evl_entry *entry_head, unsigned int index) { struct device *dev = &idxd->pdev->dev; + struct idxd_evl *evl = idxd->evl; u8 status; - status = DSA_COMP_STATUS(entry_head->error); - dev_warn_ratelimited(dev, "Device error %#x operation: %#x fault addr: %#llx\n", - status, entry_head->operation, entry_head->fault_addr); + if (test_bit(index, evl->bmap)) { + clear_bit(index, evl->bmap); + } else { + status = DSA_COMP_STATUS(entry_head->error); + + if (status == DSA_COMP_CRA_XLAT || status == DSA_COMP_DRAIN_EVL) { + struct idxd_evl_fault *fault; + int ent_size = evl_ent_size(idxd); + + if (entry_head->rci) + dev_dbg(dev, "Completion Int Req set, ignoring!\n"); + + if (!entry_head->rcr && status == DSA_COMP_DRAIN_EVL) + return; + + fault = kmem_cache_alloc(idxd->evl_cache, GFP_ATOMIC); + if (fault) { + struct idxd_wq *wq = idxd->wqs[entry_head->wq_idx]; + + fault->wq = wq; + fault->status = status; + memcpy(&fault->entry, entry_head, ent_size); + INIT_WORK(&fault->work, idxd_evl_fault_work); + queue_work(wq->wq, &fault->work); + } else { + dev_warn(dev, "Failed to service fault work.\n"); + } + } else { + dev_warn_ratelimited(dev, "Device error %#x operation: %#x fault addr: %#llx\n", + status, entry_head->operation, + entry_head->fault_addr); + } + } } static void process_evl_entries(struct idxd_device *idxd) @@ -250,7 +327,7 @@ static void process_evl_entries(struct idxd_device *idxd) while (h != t) { entry_head = (struct __evl_entry *)(evl->log + (h * ent_size)); - process_evl_entry(idxd, entry_head); + process_evl_entry(idxd, entry_head, h); h = (h + 1) % size; } diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index e86199d09a91..4b584d5afd87 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -135,6 +135,7 @@ enum dsa_completion_status { DSA_COMP_HW_ERR1, DSA_COMP_HW_ERR_DRB, DSA_COMP_TRANSLATION_FAIL, + DSA_COMP_DRAIN_EVL = 0x26, }; enum iax_completion_status { -- GitLab From 6926987185a3ae92c31b99ce1bfdfb04e95057c0 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:37 -0700 Subject: [PATCH 2798/5631] dmaengine: idxd: add descs_completed field for completion record The descs_completed field for a completion record is part of a batch descriptor completion record. It takes the same location as bytes_completed in a normal descriptor field. Add to expose to user. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-11-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 4b584d5afd87..76ad71bf751e 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -314,7 +314,10 @@ struct dsa_completion_record { }; uint8_t fault_info; uint8_t rsvd; - uint32_t bytes_completed; + union { + uint32_t bytes_completed; + uint32_t descs_completed; + }; uint64_t fault_addr; union { /* common record */ -- GitLab From 2442b7473ad03671378d2d95651bd6bbe09a0943 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:38 -0700 Subject: [PATCH 2799/5631] dmaengine: idxd: process batch descriptor completion record faults Add event log processing for faulting of user batch descriptor completion record. When encountering an event log entry for a page fault on a completion record, the driver is expected to do the following: 1. If the "first error in batch" bit in event log entry error info is set, discard any previously recorded errors associated with the "batch identifier". 2. Fix the page fault according to the fault address in the event log. If successful, write the completion record to the fault address in user space. 3. If an error is encountered while writing the completion record and it is associated to a descriptor in the batch, the driver associates the error with the batch identifier of the event log entry and tracks it until the event log entry for the corresponding batch desc is encountered. While processing an event log entry for a batch descriptor with error indicating that one or more descs in the batch had event log entries, the driver will do the following before writing the batch completion record: 1. If the status field of the completion record is 0x1, the driver will change it to error code 0x5 (one or more operations in batch completed with status not successful) and changes the result field to 1. 2. If the status is error code 0x6 (page fault on batch descriptor list address), change the result field to 1. 3. If status is any other value, the completion record is not changed. 4. Clear the recorded error in preparation for next batch with same batch identifier. The result field is for user software to determine whether to set the "Batch Error" flag bit in the descriptor for continuation of partial batch descriptor completion. See DSA spec 2.0 for additional information. If no error has been recorded for the batch, the batch completion record is written to user space as is. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-12-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/idxd.h | 3 ++ drivers/dma/idxd/init.c | 4 ++ drivers/dma/idxd/irq.c | 91 ++++++++++++++++++++++++++---------- drivers/dma/idxd/registers.h | 4 +- include/uapi/linux/idxd.h | 1 + 5 files changed, 78 insertions(+), 25 deletions(-) diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 3963c83165a6..4c4baa80c731 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -265,6 +265,8 @@ struct idxd_driver_data { int compl_size; int align; int evl_cr_off; + int cr_status_off; + int cr_result_off; }; struct idxd_evl { @@ -278,6 +280,7 @@ struct idxd_evl { u16 size; u16 head; unsigned long *bmap; + bool batch_fail[IDXD_MAX_BATCH_IDENT]; }; struct idxd_evl_fault { diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 18344593b83f..92f60d364392 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -47,6 +47,8 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 32, .dev_type = &dsa_device_type, .evl_cr_off = offsetof(struct dsa_evl_entry, cr), + .cr_status_off = offsetof(struct dsa_completion_record, status), + .cr_result_off = offsetof(struct dsa_completion_record, result), }, [IDXD_TYPE_IAX] = { .name_prefix = "iax", @@ -55,6 +57,8 @@ static struct idxd_driver_data idxd_driver_data[] = { .align = 64, .dev_type = &iax_device_type, .evl_cr_off = offsetof(struct iax_evl_entry, cr), + .cr_status_off = offsetof(struct iax_completion_record, status), + .cr_result_off = offsetof(struct iax_completion_record, error_code), }, }; diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index 96983975f974..c660d63a3eb8 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -225,37 +225,79 @@ static void idxd_evl_fault_work(struct work_struct *work) struct idxd_wq *wq = fault->wq; struct idxd_device *idxd = wq->idxd; struct device *dev = &idxd->pdev->dev; + struct idxd_evl *evl = idxd->evl; struct __evl_entry *entry_head = fault->entry; void *cr = (void *)entry_head + idxd->data->evl_cr_off; - int cr_size = idxd->data->compl_size, copied; + int cr_size = idxd->data->compl_size; + u8 *status = (u8 *)cr + idxd->data->cr_status_off; + u8 *result = (u8 *)cr + idxd->data->cr_result_off; + int copied, copy_size; + bool *bf; switch (fault->status) { case DSA_COMP_CRA_XLAT: - case DSA_COMP_DRAIN_EVL: - /* - * Copy completion record to fault_addr in user address space - * that is found by wq and PASID. - */ - copied = idxd_copy_cr(wq, entry_head->pasid, - entry_head->fault_addr, - cr, cr_size); - /* - * The task that triggered the page fault is unknown currently - * because multiple threads may share the user address - * space or the task exits already before this fault. - * So if the copy fails, SIGSEGV can not be sent to the task. - * Just print an error for the failure. The user application - * waiting for the completion record will time out on this - * failure. - */ - if (copied != cr_size) { - dev_dbg_ratelimited(dev, "Failed to write to completion record. (%d:%d)\n", - cr_size, copied); + if (entry_head->batch && entry_head->first_err_in_batch) + evl->batch_fail[entry_head->batch_id] = false; + + copy_size = cr_size; + break; + case DSA_COMP_BATCH_EVL_ERR: + bf = &evl->batch_fail[entry_head->batch_id]; + + copy_size = entry_head->rcr || *bf ? cr_size : 0; + if (*bf) { + if (*status == DSA_COMP_SUCCESS) + *status = DSA_COMP_BATCH_FAIL; + *result = 1; + *bf = false; } break; + case DSA_COMP_DRAIN_EVL: + copy_size = cr_size; + break; default: - dev_dbg_ratelimited(dev, "Unrecognized error code: %#x\n", - DSA_COMP_STATUS(entry_head->error)); + copy_size = 0; + dev_dbg_ratelimited(dev, "Unrecognized error code: %#x\n", fault->status); + break; + } + + if (copy_size == 0) + return; + + /* + * Copy completion record to fault_addr in user address space + * that is found by wq and PASID. + */ + copied = idxd_copy_cr(wq, entry_head->pasid, entry_head->fault_addr, + cr, copy_size); + /* + * The task that triggered the page fault is unknown currently + * because multiple threads may share the user address + * space or the task exits already before this fault. + * So if the copy fails, SIGSEGV can not be sent to the task. + * Just print an error for the failure. The user application + * waiting for the completion record will time out on this + * failure. + */ + switch (fault->status) { + case DSA_COMP_CRA_XLAT: + if (copied != copy_size) { + dev_dbg_ratelimited(dev, "Failed to write to completion record: (%d:%d)\n", + copy_size, copied); + if (entry_head->batch) + evl->batch_fail[entry_head->batch_id] = true; + } + break; + case DSA_COMP_BATCH_EVL_ERR: + if (copied != copy_size) { + dev_dbg_ratelimited(dev, "Failed to write to batch completion record: (%d:%d)\n", + copy_size, copied); + } + break; + case DSA_COMP_DRAIN_EVL: + if (copied != copy_size) + dev_dbg_ratelimited(dev, "Failed to write to drain completion record: (%d:%d)\n", + copy_size, copied); break; } @@ -274,7 +316,8 @@ static void process_evl_entry(struct idxd_device *idxd, } else { status = DSA_COMP_STATUS(entry_head->error); - if (status == DSA_COMP_CRA_XLAT || status == DSA_COMP_DRAIN_EVL) { + if (status == DSA_COMP_CRA_XLAT || status == DSA_COMP_DRAIN_EVL || + status == DSA_COMP_BATCH_EVL_ERR) { struct idxd_evl_fault *fault; int ent_size = evl_ent_size(idxd); diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 148db94f9373..9f3959d001b6 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -35,7 +35,7 @@ union gen_cap_reg { u64 drain_readback:1; u64 rsvd2:3; u64 evl_support:2; - u64 rsvd4:1; + u64 batch_continuation:1; u64 max_xfer_shift:5; u64 max_batch_shift:4; u64 max_ims_mult:6; @@ -577,6 +577,8 @@ union evl_status_reg { u64 bits; } __packed; +#define IDXD_MAX_BATCH_IDENT 256 + struct __evl_entry { u64 rsvd:2; u64 desc_valid:1; diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 76ad71bf751e..606b52e88ce3 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -136,6 +136,7 @@ enum dsa_completion_status { DSA_COMP_HW_ERR_DRB, DSA_COMP_TRANSLATION_FAIL, DSA_COMP_DRAIN_EVL = 0x26, + DSA_COMP_BATCH_EVL_ERR, }; enum iax_completion_status { -- GitLab From fecae134ee10b7de69461c197450f7c05677e733 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:39 -0700 Subject: [PATCH 2800/5631] dmaengine: idxd: add per file user counters for completion record faults Add counters per opened file for the char device in order to keep track how many completion record faults occurred and how many of those faults failed the writeback by the driver after attempt to fault in the page. The counters are managed by xarray that associates the PASID with struct idxd_user_context. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-13-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 18 ++++++++++++++++++ drivers/dma/idxd/idxd.h | 7 +++++++ drivers/dma/idxd/irq.c | 4 ++++ 3 files changed, 29 insertions(+) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 0a51c33198f6..5c8e964e671b 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -39,6 +39,7 @@ struct idxd_user_context { struct mm_struct *mm; unsigned int flags; struct iommu_sva *sva; + u64 counters[COUNTER_MAX]; }; static void idxd_cdev_dev_release(struct device *dev) @@ -84,6 +85,23 @@ static void idxd_xa_pasid_remove(struct idxd_user_context *ctx) mutex_unlock(&wq->uc_lock); } +void idxd_user_counter_increment(struct idxd_wq *wq, u32 pasid, int index) +{ + struct idxd_user_context *ctx; + + if (index >= COUNTER_MAX) + return; + + mutex_lock(&wq->uc_lock); + ctx = xa_load(&wq->upasid_xa, pasid); + if (!ctx) { + mutex_unlock(&wq->uc_lock); + return; + } + ctx->counters[index]++; + mutex_unlock(&wq->uc_lock); +} + static int idxd_cdev_open(struct inode *inode, struct file *filp) { struct idxd_user_context *ctx; diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 4c4baa80c731..9fb26d017285 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -127,6 +127,12 @@ struct idxd_pmu { #define IDXD_MAX_PRIORITY 0xf +enum { + COUNTER_FAULTS = 0, + COUNTER_FAULT_FAILS, + COUNTER_MAX +}; + enum idxd_wq_state { IDXD_WQ_DISABLED = 0, IDXD_WQ_ENABLED, @@ -713,6 +719,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq); void idxd_wq_del_cdev(struct idxd_wq *wq); int idxd_copy_cr(struct idxd_wq *wq, ioasid_t pasid, unsigned long addr, void *buf, int len); +void idxd_user_counter_increment(struct idxd_wq *wq, u32 pasid, int index); /* perfmon */ #if IS_ENABLED(CONFIG_INTEL_IDXD_PERFMON) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index c660d63a3eb8..f4b0f59c95ba 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -240,6 +240,7 @@ static void idxd_evl_fault_work(struct work_struct *work) evl->batch_fail[entry_head->batch_id] = false; copy_size = cr_size; + idxd_user_counter_increment(wq, entry_head->pasid, COUNTER_FAULTS); break; case DSA_COMP_BATCH_EVL_ERR: bf = &evl->batch_fail[entry_head->batch_id]; @@ -251,6 +252,7 @@ static void idxd_evl_fault_work(struct work_struct *work) *result = 1; *bf = false; } + idxd_user_counter_increment(wq, entry_head->pasid, COUNTER_FAULTS); break; case DSA_COMP_DRAIN_EVL: copy_size = cr_size; @@ -282,6 +284,7 @@ static void idxd_evl_fault_work(struct work_struct *work) switch (fault->status) { case DSA_COMP_CRA_XLAT: if (copied != copy_size) { + idxd_user_counter_increment(wq, entry_head->pasid, COUNTER_FAULT_FAILS); dev_dbg_ratelimited(dev, "Failed to write to completion record: (%d:%d)\n", copy_size, copied); if (entry_head->batch) @@ -290,6 +293,7 @@ static void idxd_evl_fault_work(struct work_struct *work) break; case DSA_COMP_BATCH_EVL_ERR: if (copied != copy_size) { + idxd_user_counter_increment(wq, entry_head->pasid, COUNTER_FAULT_FAILS); dev_dbg_ratelimited(dev, "Failed to write to batch completion record: (%d:%d)\n", copy_size, copied); } -- GitLab From e6fd6d7e5f0fe4a17a08e892afb5db800e7794ec Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:40 -0700 Subject: [PATCH 2801/5631] dmaengine: idxd: add a device to represent the file opened Embed a struct device for the user file context in order to export sysfs attributes related with the opened file. Tie the lifetime of the file context to the device. The sysfs entry will be added under the char device. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-14-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 119 ++++++++++++++++++++++++++++++++-------- drivers/dma/idxd/idxd.h | 2 + 2 files changed, 97 insertions(+), 24 deletions(-) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 5c8e964e671b..e07411053e21 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -23,6 +23,13 @@ struct idxd_cdev_context { struct ida minor_ida; }; +/* + * Since user file names are global in DSA devices, define their ida's as + * global to avoid conflict file names. + */ +static DEFINE_IDA(file_ida); +static DEFINE_MUTEX(ida_lock); + /* * ictx is an array based off of accelerator types. enum idxd_type * is used as index @@ -39,7 +46,60 @@ struct idxd_user_context { struct mm_struct *mm; unsigned int flags; struct iommu_sva *sva; + struct idxd_dev idxd_dev; u64 counters[COUNTER_MAX]; + int id; +}; + +static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid); +static void idxd_xa_pasid_remove(struct idxd_user_context *ctx); + +static inline struct idxd_user_context *dev_to_uctx(struct device *dev) +{ + struct idxd_dev *idxd_dev = confdev_to_idxd_dev(dev); + + return container_of(idxd_dev, struct idxd_user_context, idxd_dev); +} + +static void idxd_file_dev_release(struct device *dev) +{ + struct idxd_user_context *ctx = dev_to_uctx(dev); + struct idxd_wq *wq = ctx->wq; + struct idxd_device *idxd = wq->idxd; + int rc; + + mutex_lock(&ida_lock); + ida_free(&file_ida, ctx->id); + mutex_unlock(&ida_lock); + + /* Wait for in-flight operations to complete. */ + if (wq_shared(wq)) { + idxd_device_drain_pasid(idxd, ctx->pasid); + } else { + if (device_user_pasid_enabled(idxd)) { + /* The wq disable in the disable pasid function will drain the wq */ + rc = idxd_wq_disable_pasid(wq); + if (rc < 0) + dev_err(dev, "wq disable pasid failed.\n"); + } else { + idxd_wq_drain(wq); + } + } + + if (ctx->sva) { + idxd_cdev_evl_drain_pasid(wq, ctx->pasid); + iommu_sva_unbind_device(ctx->sva); + idxd_xa_pasid_remove(ctx); + } + kfree(ctx); + mutex_lock(&wq->wq_lock); + idxd_wq_put(wq); + mutex_unlock(&wq->wq_lock); +} + +static struct device_type idxd_cdev_file_type = { + .name = "idxd_file", + .release = idxd_file_dev_release, }; static void idxd_cdev_dev_release(struct device *dev) @@ -107,10 +167,11 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) struct idxd_user_context *ctx; struct idxd_device *idxd; struct idxd_wq *wq; - struct device *dev; + struct device *dev, *fdev; int rc = 0; struct iommu_sva *sva; unsigned int pasid; + struct idxd_cdev *idxd_cdev; wq = inode_wq(inode); idxd = wq->idxd; @@ -166,10 +227,41 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) } } + idxd_cdev = wq->idxd_cdev; + mutex_lock(&ida_lock); + ctx->id = ida_alloc(&file_ida, GFP_KERNEL); + mutex_unlock(&ida_lock); + if (ctx->id < 0) { + dev_warn(dev, "ida alloc failure\n"); + goto failed_ida; + } + ctx->idxd_dev.type = IDXD_DEV_CDEV_FILE; + fdev = user_ctx_dev(ctx); + device_initialize(fdev); + fdev->parent = cdev_dev(idxd_cdev); + fdev->bus = &dsa_bus_type; + fdev->type = &idxd_cdev_file_type; + + rc = dev_set_name(fdev, "file%d", ctx->id); + if (rc < 0) { + dev_warn(dev, "set name failure\n"); + goto failed_dev_name; + } + + rc = device_add(fdev); + if (rc < 0) { + dev_warn(dev, "file device add failure\n"); + goto failed_dev_add; + } + idxd_wq_get(wq); mutex_unlock(&wq->wq_lock); return 0; +failed_dev_add: +failed_dev_name: + put_device(fdev); +failed_ida: failed_set_pasid: if (device_user_pasid_enabled(idxd)) idxd_xa_pasid_remove(ctx); @@ -217,34 +309,12 @@ static int idxd_cdev_release(struct inode *node, struct file *filep) struct idxd_wq *wq = ctx->wq; struct idxd_device *idxd = wq->idxd; struct device *dev = &idxd->pdev->dev; - int rc; dev_dbg(dev, "%s called\n", __func__); filep->private_data = NULL; - /* Wait for in-flight operations to complete. */ - if (wq_shared(wq)) { - idxd_device_drain_pasid(idxd, ctx->pasid); - } else { - if (device_user_pasid_enabled(idxd)) { - /* The wq disable in the disable pasid function will drain the wq */ - rc = idxd_wq_disable_pasid(wq); - if (rc < 0) - dev_err(dev, "wq disable pasid failed.\n"); - } else { - idxd_wq_drain(wq); - } - } + device_unregister(user_ctx_dev(ctx)); - if (ctx->sva) { - idxd_cdev_evl_drain_pasid(wq, ctx->pasid); - iommu_sva_unbind_device(ctx->sva); - idxd_xa_pasid_remove(ctx); - } - kfree(ctx); - mutex_lock(&wq->wq_lock); - idxd_wq_put(wq); - mutex_unlock(&wq->wq_lock); return 0; } @@ -375,6 +445,7 @@ void idxd_wq_del_cdev(struct idxd_wq *wq) struct idxd_cdev *idxd_cdev; idxd_cdev = wq->idxd_cdev; + ida_destroy(&file_ida); wq->idxd_cdev = NULL; cdev_device_del(&idxd_cdev->cdev, cdev_dev(idxd_cdev)); put_device(cdev_dev(idxd_cdev)); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 9fb26d017285..bd544eb2ddcb 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -32,6 +32,7 @@ enum idxd_dev_type { IDXD_DEV_GROUP, IDXD_DEV_ENGINE, IDXD_DEV_CDEV, + IDXD_DEV_CDEV_FILE, IDXD_DEV_MAX_TYPE, }; @@ -405,6 +406,7 @@ enum idxd_completion_status { #define engine_confdev(engine) &engine->idxd_dev.conf_dev #define group_confdev(group) &group->idxd_dev.conf_dev #define cdev_dev(cdev) &cdev->idxd_dev.conf_dev +#define user_ctx_dev(ctx) (&(ctx)->idxd_dev.conf_dev) #define confdev_to_idxd_dev(dev) container_of(dev, struct idxd_dev, conf_dev) #define idxd_dev_to_idxd(idxd_dev) container_of(idxd_dev, struct idxd_device, idxd_dev) -- GitLab From 244009b07e7d0728726f266cc3485d7fd400d0d5 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:41 -0700 Subject: [PATCH 2802/5631] dmaengine: idxd: expose fault counters to sysfs Expose cr_faults and cr_fault_failures counters to the user space. This allows a user app to keep track of how many fault the application is causing with the completion record (CR) and also the number of failures of the CR writeback. Having a high number of cr_fault_failures is bad as the app is submitting descriptors with the CR addresses that are bad. User monitoring daemon may want to consider killing the application as it may be malicious and attempting to flood the device event log. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-15-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- .../ABI/stable/sysfs-driver-dma-idxd | 17 +++++++ drivers/dma/idxd/cdev.c | 46 +++++++++++++++++++ 2 files changed, 63 insertions(+) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index e01916611452..73ab86196a41 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -318,3 +318,20 @@ Description: Allows control of the number of batch descriptors that can be 1 (1/2 of max value), 2 (1/4 of the max value), and 3 (1/8 of the max value). It's visible only on platforms that support the capability. + +What: /sys/bus/dsa/devices/wq./dsa\!wq./file/cr_faults +Date: Sept 14, 2022 +KernelVersion: 6.4.0 +Contact: dmaengine@vger.kernel.org +Description: Show the number of Completion Record (CR) faults this application + has caused. + +What: /sys/bus/dsa/devices/wq./dsa\!wq./file/cr_fault_failures +Date: Sept 14, 2022 +KernelVersion: 6.4.0 +Contact: dmaengine@vger.kernel.org +Description: Show the number of Completion Record (CR) faults failures that this + application has caused. The failure counter is incremented when the + driver cannot fault in the address for the CR. Typically this is caused + by a bad address programmed in the submitted descriptor or a malicious + submitter is using bad CR address on purpose. diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index e07411053e21..2fb905f2545b 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -61,6 +61,51 @@ static inline struct idxd_user_context *dev_to_uctx(struct device *dev) return container_of(idxd_dev, struct idxd_user_context, idxd_dev); } +static ssize_t cr_faults_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct idxd_user_context *ctx = dev_to_uctx(dev); + + return sysfs_emit(buf, "%llu\n", ctx->counters[COUNTER_FAULTS]); +} +static DEVICE_ATTR_RO(cr_faults); + +static ssize_t cr_fault_failures_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct idxd_user_context *ctx = dev_to_uctx(dev); + + return sysfs_emit(buf, "%llu\n", ctx->counters[COUNTER_FAULT_FAILS]); +} +static DEVICE_ATTR_RO(cr_fault_failures); + +static struct attribute *cdev_file_attributes[] = { + &dev_attr_cr_faults.attr, + &dev_attr_cr_fault_failures.attr, + NULL +}; + +static umode_t cdev_file_attr_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = container_of(kobj, typeof(*dev), kobj); + struct idxd_user_context *ctx = dev_to_uctx(dev); + struct idxd_wq *wq = ctx->wq; + + if (!wq_pasid_enabled(wq)) + return 0; + + return a->mode; +} + +static const struct attribute_group cdev_file_attribute_group = { + .attrs = cdev_file_attributes, + .is_visible = cdev_file_attr_visible, +}; + +static const struct attribute_group *cdev_file_attribute_groups[] = { + &cdev_file_attribute_group, + NULL +}; + static void idxd_file_dev_release(struct device *dev) { struct idxd_user_context *ctx = dev_to_uctx(dev); @@ -100,6 +145,7 @@ static void idxd_file_dev_release(struct device *dev) static struct device_type idxd_cdev_file_type = { .name = "idxd_file", .release = idxd_file_dev_release, + .groups = cdev_file_attribute_groups, }; static void idxd_cdev_dev_release(struct device *dev) -- GitLab From a62b8f87c770fa4109ce515e4d8a0d4701a4ca5f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:42 -0700 Subject: [PATCH 2803/5631] dmaengine: idxd: add pid to exported sysfs attribute for opened file Provide the pid of the application for the opened file. This allows the monitor daemon to easily correlate which app opened the file and easily kill the app by pid if that is desired action. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-16-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- Documentation/ABI/stable/sysfs-driver-dma-idxd | 8 ++++++++ drivers/dma/idxd/cdev.c | 11 +++++++++++ 2 files changed, 19 insertions(+) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index 73ab86196a41..5d0df57f5298 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -335,3 +335,11 @@ Description: Show the number of Completion Record (CR) faults failures that this driver cannot fault in the address for the CR. Typically this is caused by a bad address programmed in the submitted descriptor or a malicious submitter is using bad CR address on purpose. + +What: /sys/bus/dsa/devices/wq./dsa\!wq./file/pid +Date: Sept 14, 2022 +KernelVersion: 6.4.0 +Contact: dmaengine@vger.kernel.org +Description: Show the process id of the application that opened the file. This is + helpful information for a monitor daemon that wants to kill the + application that opened the file. diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 2fb905f2545b..ecbf67c2ad2b 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -49,6 +49,7 @@ struct idxd_user_context { struct idxd_dev idxd_dev; u64 counters[COUNTER_MAX]; int id; + pid_t pid; }; static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid); @@ -78,9 +79,18 @@ static ssize_t cr_fault_failures_show(struct device *dev, } static DEVICE_ATTR_RO(cr_fault_failures); +static ssize_t pid_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct idxd_user_context *ctx = dev_to_uctx(dev); + + return sysfs_emit(buf, "%u\n", ctx->pid); +} +static DEVICE_ATTR_RO(pid); + static struct attribute *cdev_file_attributes[] = { &dev_attr_cr_faults.attr, &dev_attr_cr_fault_failures.attr, + &dev_attr_pid.attr, NULL }; @@ -238,6 +248,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) ctx->wq = wq; filp->private_data = ctx; + ctx->pid = current->pid; if (device_user_pasid_enabled(idxd)) { sva = iommu_sva_bind_device(dev, current->mm); -- GitLab From f2dc327131b5cbb2cbb467cec23836f2e9d4cf46 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 7 Apr 2023 13:31:43 -0700 Subject: [PATCH 2804/5631] dmaengine: idxd: add per wq PRS disable Add sysfs knob for per wq Page Request Service disable. This knob disables PRS support for the specific wq. When this bit is set, it also overrides the wq's block on fault enabling. Tested-by: Tony Zhu Signed-off-by: Dave Jiang Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Link: https://lore.kernel.org/r/20230407203143.2189681-17-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- .../ABI/stable/sysfs-driver-dma-idxd | 10 ++++ drivers/dma/idxd/device.c | 6 +- drivers/dma/idxd/idxd.h | 1 + drivers/dma/idxd/registers.h | 5 +- drivers/dma/idxd/sysfs.c | 57 ++++++++++++++++++- 5 files changed, 74 insertions(+), 5 deletions(-) diff --git a/Documentation/ABI/stable/sysfs-driver-dma-idxd b/Documentation/ABI/stable/sysfs-driver-dma-idxd index 5d0df57f5298..534b7a3d59fc 100644 --- a/Documentation/ABI/stable/sysfs-driver-dma-idxd +++ b/Documentation/ABI/stable/sysfs-driver-dma-idxd @@ -235,6 +235,16 @@ Contact: dmaengine@vger.kernel.org Description: Indicate whether ATS disable is turned on for the workqueue. 0 indicates ATS is on, and 1 indicates ATS is off for the workqueue. +What: /sys/bus/dsa/devices/wq./prs_disable +Date: Sept 14, 2022 +KernelVersion: 6.4.0 +Contact: dmaengine@vger.kernel.org +Description: Controls whether PRS disable is turned on for the workqueue. + 0 indicates PRS is on, and 1 indicates PRS is off for the + workqueue. This option overrides block_on_fault attribute + if set. It's visible only on platforms that support the + capability. + What: /sys/bus/dsa/devices/wq./occupancy Date May 25, 2021 KernelVersion: 5.14.0 diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index fd97b2b58734..3c80b9681c72 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -967,12 +967,16 @@ static int idxd_wq_config_write(struct idxd_wq *wq) wq->wqcfg->priority = wq->priority; if (idxd->hw.gen_cap.block_on_fault && - test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags)) + test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags) && + !test_bit(WQ_FLAG_PRS_DISABLE, &wq->flags)) wq->wqcfg->bof = 1; if (idxd->hw.wq_cap.wq_ats_support) wq->wqcfg->wq_ats_disable = test_bit(WQ_FLAG_ATS_DISABLE, &wq->flags); + if (idxd->hw.wq_cap.wq_prs_support) + wq->wqcfg->wq_prs_disable = test_bit(WQ_FLAG_PRS_DISABLE, &wq->flags); + /* bytes 12-15 */ wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes); idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size)); diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index bd544eb2ddcb..e44b1d45ccd5 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -143,6 +143,7 @@ enum idxd_wq_flag { WQ_FLAG_DEDICATED = 0, WQ_FLAG_BLOCK_ON_FAULT, WQ_FLAG_ATS_DISABLE, + WQ_FLAG_PRS_DISABLE, }; enum idxd_wq_type { diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index 9f3959d001b6..7b54a3939ea1 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -59,7 +59,8 @@ union wq_cap_reg { u64 occupancy:1; u64 occupancy_int:1; u64 op_config:1; - u64 rsvd3:9; + u64 wq_prs_support:1; + u64 rsvd4:8; }; u64 bits; } __packed; @@ -371,7 +372,7 @@ union wqcfg { u32 mode:1; /* shared or dedicated */ u32 bof:1; /* block on fault */ u32 wq_ats_disable:1; - u32 rsvd2:1; + u32 wq_prs_disable:1; u32 priority:4; u32 pasid:20; u32 pasid_en:1; diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 465d2e7627e4..293739ac5596 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -822,10 +822,14 @@ static ssize_t wq_block_on_fault_store(struct device *dev, if (rc < 0) return rc; - if (bof) + if (bof) { + if (test_bit(WQ_FLAG_PRS_DISABLE, &wq->flags)) + return -EOPNOTSUPP; + set_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags); - else + } else { clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags); + } return count; } @@ -1109,6 +1113,44 @@ static ssize_t wq_ats_disable_store(struct device *dev, struct device_attribute static struct device_attribute dev_attr_wq_ats_disable = __ATTR(ats_disable, 0644, wq_ats_disable_show, wq_ats_disable_store); +static ssize_t wq_prs_disable_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + + return sysfs_emit(buf, "%u\n", test_bit(WQ_FLAG_PRS_DISABLE, &wq->flags)); +} + +static ssize_t wq_prs_disable_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct idxd_wq *wq = confdev_to_wq(dev); + struct idxd_device *idxd = wq->idxd; + bool prs_dis; + int rc; + + if (wq->state != IDXD_WQ_DISABLED) + return -EPERM; + + if (!idxd->hw.wq_cap.wq_prs_support) + return -EOPNOTSUPP; + + rc = kstrtobool(buf, &prs_dis); + if (rc < 0) + return rc; + + if (prs_dis) { + set_bit(WQ_FLAG_PRS_DISABLE, &wq->flags); + /* when PRS is disabled, BOF needs to be off as well */ + clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags); + } else { + clear_bit(WQ_FLAG_PRS_DISABLE, &wq->flags); + } + return count; +} + +static struct device_attribute dev_attr_wq_prs_disable = + __ATTR(prs_disable, 0644, wq_prs_disable_show, wq_prs_disable_store); + static ssize_t wq_occupancy_show(struct device *dev, struct device_attribute *attr, char *buf) { struct idxd_wq *wq = confdev_to_wq(dev); @@ -1239,6 +1281,7 @@ static struct attribute *idxd_wq_attributes[] = { &dev_attr_wq_max_transfer_size.attr, &dev_attr_wq_max_batch_size.attr, &dev_attr_wq_ats_disable.attr, + &dev_attr_wq_prs_disable.attr, &dev_attr_wq_occupancy.attr, &dev_attr_wq_enqcmds_retries.attr, &dev_attr_wq_op_config.attr, @@ -1260,6 +1303,13 @@ static bool idxd_wq_attr_max_batch_size_invisible(struct attribute *attr, idxd->data->type == IDXD_TYPE_IAX; } +static bool idxd_wq_attr_wq_prs_disable_invisible(struct attribute *attr, + struct idxd_device *idxd) +{ + return attr == &dev_attr_wq_prs_disable.attr && + !idxd->hw.wq_cap.wq_prs_support; +} + static umode_t idxd_wq_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { @@ -1273,6 +1323,9 @@ static umode_t idxd_wq_attr_visible(struct kobject *kobj, if (idxd_wq_attr_max_batch_size_invisible(attr, idxd)) return 0; + if (idxd_wq_attr_wq_prs_disable_invisible(attr, idxd)) + return 0; + return attr->mode; } -- GitLab From b277851417e0149aff5e6986e1ad6e2d8054e4a6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 14:53:35 -0300 Subject: [PATCH 2805/5631] libperf: Add a perf_cpu_map__set_nr() available as an internal function for tools/perf to use We'll need to reference count check 'struct perf_cpu_map', so wrap accesses to its internal state to allow intercepting accesses to its instances. Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/cpumap.c | 5 +++++ tools/lib/perf/include/internal/cpumap.h | 2 ++ 2 files changed, 7 insertions(+) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 0833423c243b..6bbcbb83eb14 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,6 +10,11 @@ #include #include +void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus) +{ + map->nr = nr_cpus; +} + struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) { struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index f5bffb1f8674..b82fd6607a00 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -28,4 +28,6 @@ struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus); int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); +void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus); + #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ -- GitLab From 9efe423e4387893498e11c75207bc9a1c9121246 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 12 Apr 2023 14:56:28 -0300 Subject: [PATCH 2806/5631] perf pmu: Use perf_cpu_map__set_nr() in perf_pmu__cpus_match() to allow for refcnt checking One more step to allow for checking reference counting, user after free, etc. Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/ZDb9dycHQ11UIXwx@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 561e2616861f..760c848c9fa2 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -2020,8 +2020,8 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, matched_cpus->map[matched_nr++] = cpu; } - unmatched_cpus->nr = unmatched_nr; - matched_cpus->nr = matched_nr; + perf_cpu_map__set_nr(unmatched_cpus, unmatched_nr); + perf_cpu_map__set_nr(matched_cpus, matched_nr); *mcpus_ptr = matched_cpus; *ucpus_ptr = unmatched_cpus; return 0; -- GitLab From bd66b6acd20ba72d1779fa1abe55eb0fcc20f2c3 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 30 Jan 2023 20:10:17 +0000 Subject: [PATCH 2807/5631] iio: imu: lsm6dsx: Support SMO8B30 ACPI ID for LSM6DS3TR-C ID seen in the wild and it is a valid ST micro ID. An offset of 1 for the device ID enum is needed when adding support for retrieving the ID from device_get_match_data() to allow detection of NULL pointer and fallback to i2c_device_id table. DSDT chunk cropped for relevant parts. Scope (_SB.PCI0.I2C5) { Device (DEV) { Name (_HID, EisaId ("SMO8B30")) // _HID: Hardware ID Name (_CID, EisaId ("SMO8B30")) // _CID: Compatible ID Name (_UID, Zero) // _UID: Unique ID Method (_CRS, 0, NotSerialized) // _CRS: Current Resource Settings { Name (RBUF, ResourceTemplate () { I2cSerialBusV2 (0x006A, ControllerInitiated, 0x00061A80, AddressingMode7Bit, "\\_SB.PCI0.I2C5", 0x00, ResourceConsumer, , Exclusive, ) }) Return (RBUF) /* \_SB_.PCI0.I2C5.DEV_._CRS.RBUF */ } Method (ROTM, 0, NotSerialized) { Name (RBUF, Package (0x03) { "0 -1 0", "1 0 0", "0 0 1" }) Return (RBUF) /* \_SB_.PCI0.I2C5.DEV_.ROTM.RBUF */ } ... Link: https://lore.kernel.org/all/20230129182441.082f29d0@jic23-huawei/ Reported-by: Darrell Kavanagh Tested-by: Darrell Kavanagh Signed-off-by: Jonathan Cameron Link: https://lore.kernel.org/r/20230130201018.981024-2-jic23@kernel.org --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h | 2 +- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c | 16 ++++++++++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h index 9dfe4917a386..c19237717e81 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h @@ -40,7 +40,7 @@ #define ST_ASM330LHB_DEV_NAME "asm330lhb" enum st_lsm6dsx_hw_id { - ST_LSM6DS3_ID, + ST_LSM6DS3_ID = 1, ST_LSM6DS3H_ID, ST_LSM6DSL_ID, ST_LSM6DSM_ID, diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c index ccdc4ceffd85..020717f92363 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_i2c.c @@ -23,10 +23,15 @@ static const struct regmap_config st_lsm6dsx_i2c_regmap_config = { static int st_lsm6dsx_i2c_probe(struct i2c_client *client) { - const struct i2c_device_id *id = i2c_client_get_device_id(client); - int hw_id = id->driver_data; + int hw_id; struct regmap *regmap; + hw_id = (kernel_ulong_t)device_get_match_data(&client->dev); + if (!hw_id) + hw_id = i2c_client_get_device_id(client)->driver_data; + if (!hw_id) + return -EINVAL; + regmap = devm_regmap_init_i2c(client, &st_lsm6dsx_i2c_regmap_config); if (IS_ERR(regmap)) { dev_err(&client->dev, "Failed to register i2c regmap %ld\n", PTR_ERR(regmap)); @@ -133,6 +138,12 @@ static const struct of_device_id st_lsm6dsx_i2c_of_match[] = { }; MODULE_DEVICE_TABLE(of, st_lsm6dsx_i2c_of_match); +static const struct acpi_device_id st_lsm6dsx_i2c_acpi_match[] = { + { "SMO8B30", ST_LSM6DS3TRC_ID, }, + {} +}; +MODULE_DEVICE_TABLE(acpi, st_lsm6dsx_i2c_acpi_match); + static const struct i2c_device_id st_lsm6dsx_i2c_id_table[] = { { ST_LSM6DS3_DEV_NAME, ST_LSM6DS3_ID }, { ST_LSM6DS3H_DEV_NAME, ST_LSM6DS3H_ID }, @@ -166,6 +177,7 @@ static struct i2c_driver st_lsm6dsx_driver = { .name = "st_lsm6dsx_i2c", .pm = pm_sleep_ptr(&st_lsm6dsx_pm_ops), .of_match_table = st_lsm6dsx_i2c_of_match, + .acpi_match_table = st_lsm6dsx_i2c_acpi_match, }, .probe_new = st_lsm6dsx_i2c_probe, .id_table = st_lsm6dsx_i2c_id_table, -- GitLab From 4453deacf44615b2d45a0b5226ff132e830bd03d Mon Sep 17 00:00:00 2001 From: Chunxin Zang Date: Tue, 28 Mar 2023 14:00:57 +0800 Subject: [PATCH 2808/5631] perf sched: Fix sched latency analysis incorrection when using 'sched:sched_wakeup' 'perf sched latency' is incorrect to get process schedule latency when it used 'sched:sched_wakeup' to analysis perf.data. Because 'perf record' prefers to use 'sched:sched_waking' to 'sched:sched_wakeup' since commit d566a9c2d482 ("perf sched: Prefer sched_waking event when it exists"). It's very reasonable to evaluate process schedule latency. Similarly, update sched latency/map/replay to use sched_waking events. Signed-off-by: Chunxin Zang Acked-by: Namhyung Kim Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230328060038.2346935-1-zangchunxin@lixiang.com Signed-off-by: Jerry Zhou Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-sched.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 96a0dceadeff..cc4ba506e119 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1516,6 +1516,14 @@ static int process_sched_wakeup_event(struct perf_tool *tool, return 0; } +static int process_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused, + struct evsel *evsel __maybe_unused, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + return 0; +} + union map_priv { void *ptr; bool color; @@ -1816,10 +1824,11 @@ static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused, static int perf_sched__read_events(struct perf_sched *sched) { - const struct evsel_str_handler handlers[] = { + struct evsel_str_handler handlers[] = { { "sched:sched_switch", process_sched_switch_event, }, { "sched:sched_stat_runtime", process_sched_runtime_event, }, { "sched:sched_wakeup", process_sched_wakeup_event, }, + { "sched:sched_waking", process_sched_wakeup_event, }, { "sched:sched_wakeup_new", process_sched_wakeup_event, }, { "sched:sched_migrate_task", process_sched_migrate_task_event, }, }; @@ -1839,6 +1848,10 @@ static int perf_sched__read_events(struct perf_sched *sched) symbol__init(&session->header.env); + /* prefer sched_waking if it is captured */ + if (evlist__find_tracepoint_by_name(session->evlist, "sched:sched_waking")) + handlers[2].handler = process_sched_wakeup_ignore; + if (perf_session__set_tracepoints_handlers(session, handlers)) goto out_delete; -- GitLab From 1f62ed00a56bf01becaccd81bf30f2fcb0322fd2 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Thu, 6 Apr 2023 04:46:49 -0400 Subject: [PATCH 2809/5631] csky: mmu: Prevent spurious page faults C-SKY MMU would pre-fetch invalid pte entries, and it could work with flush_tlb_fix_spurious_fault, but the additional page fault exceptions would reduce performance. So flushing the entry of the TLB would prevent the following spurious page faults. Here is the test code: define DATA_LEN 4096 define COPY_NUM (504*100) unsigned char src[DATA_LEN*COPY_NUM] = {0}; unsigned char dst[DATA_LEN*COPY_NUM] = {0}; unsigned char func_src[DATA_LEN*COPY_NUM] = {0}; unsigned char func_dst[DATA_LEN*COPY_NUM] = {0}; void main(void) { int j; for (j = 0; j < COPY_NUM; j++) memcpy(&dst[j*DATA_LEN], &src[j*DATA_LEN], 4); } perf stat -e page-faults ./main.elf The amount of page fault traps would be reduced in half with the patch. Signed-off-by: Guo Ren Signed-off-by: Guo Ren --- arch/csky/abiv1/cacheflush.c | 3 +++ arch/csky/abiv2/cacheflush.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c index fb91b069dc69..94fbc03cbe70 100644 --- a/arch/csky/abiv1/cacheflush.c +++ b/arch/csky/abiv1/cacheflush.c @@ -11,6 +11,7 @@ #include #include #include +#include #define PG_dcache_clean PG_arch_1 @@ -40,6 +41,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn = pte_pfn(*ptep); struct page *page; + flush_tlb_page(vma, addr); + if (!pfn_valid(pfn)) return; diff --git a/arch/csky/abiv2/cacheflush.c b/arch/csky/abiv2/cacheflush.c index 39c51399dd81..9923cd24db58 100644 --- a/arch/csky/abiv2/cacheflush.c +++ b/arch/csky/abiv2/cacheflush.c @@ -5,6 +5,7 @@ #include #include #include +#include void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *pte) @@ -12,6 +13,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, unsigned long addr; struct page *page; + flush_tlb_page(vma, address); + if (!pfn_valid(pte_pfn(*pte))) return; -- GitLab From 55b5bac15939dec3cbcbee1f6271bc3a4afd4534 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 8 Apr 2023 17:04:23 +0100 Subject: [PATCH 2810/5631] KVM: arm64: nvhe: Synchronise with page table walker on vcpu run When taking an exception between the EL1&0 translation regime and the EL2 translation regime, the page table walker is allowed to complete the walks started from EL0 or EL1 while running at EL2. It means that altering the system registers that define the EL1&0 translation regime is fraught with danger *unless* we wait for the completion of such walk with a DSB (R_LFHQG and subsequent statements in the ARM ARM). We already did the right thing for other external agents (SPE, TRBE), but not the PTW. Rework the existing SPE/TRBE synchronisation to include the PTW, and add the missing DSB on guest exit. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton --- arch/arm64/kvm/hyp/nvhe/debug-sr.c | 2 -- arch/arm64/kvm/hyp/nvhe/switch.c | 18 ++++++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index 2673bde62fad..d756b939f296 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -37,7 +37,6 @@ static void __debug_save_spe(u64 *pmscr_el1) /* Now drain all buffered data to memory */ psb_csync(); - dsb(nsh); } static void __debug_restore_spe(u64 pmscr_el1) @@ -69,7 +68,6 @@ static void __debug_save_trace(u64 *trfcr_el1) isb(); /* Drain the trace buffer to memory */ tsb_csync(); - dsb(nsh); } static void __debug_restore_trace(u64 trfcr_el1) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c2cb46ca4fb6..71fa16a0dc77 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -272,6 +272,17 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); + /* + * We're about to restore some new MMU state. Make sure + * ongoing page-table walks that have started before we + * trapped to EL2 have completed. This also synchronises the + * above disabling of SPE and TRBE. + * + * See DDI0487I.a D8.1.5 "Out-of-context translation regimes", + * rule R_LFHQG and subsequent information statements. + */ + dsb(nsh); + __kvm_adjust_pc(vcpu); /* @@ -306,6 +317,13 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) __timer_disable_traps(vcpu); __hyp_vgic_save_state(vcpu); + /* + * Same thing as before the guest run: we're about to switch + * the MMU context, so let's make sure we don't have any + * ongoing EL1&0 translations. + */ + dsb(nsh); + __deactivate_traps(vcpu); __load_host_stage2(); -- GitLab From 6539cffa94957241c096099a57d05fa4d8c7db8a Mon Sep 17 00:00:00 2001 From: Radu Rendec Date: Wed, 12 Apr 2023 14:57:57 -0400 Subject: [PATCH 2811/5631] cacheinfo: Add arch specific early level initializer This patch gives architecture specific code the ability to initialize the cache level and allocate cacheinfo memory early, when cache level initialization runs on the primary CPU for all possible CPUs. This is part of a patch series that attempts to further the work in commit 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU"). Previously, in the absence of any DT/ACPI cache info, architecture specific cache detection and info allocation for secondary CPUs would happen in non-preemptible context during early CPU initialization and trigger a "BUG: sleeping function called from invalid context" splat on an RT kernel. More specifically, this patch adds the early_cache_level() function, which is called by fetch_cache_info() as a fallback when the number of cache leaves cannot be extracted from DT/ACPI. In the default generic (weak) implementation, this new function returns -ENOENT, which preserves the original behavior for architectures that do not implement the function. Since early detection can get the number of cache leaves wrong in some cases*, additional logic is added to still call init_cache_level() later on the secondary CPU, therefore giving the architecture specific code an opportunity to go back and fix the initial guess. Again, the original behavior is preserved for architectures that do not implement the new function. * For example, on arm64, CLIDR_EL1 detection works only when it runs on the current CPU. In other words, a CPU cannot detect the cache depth for any other CPU than itself. Signed-off-by: Radu Rendec Reviewed-by: Pierre Gondois Link: https://lore.kernel.org/r/20230412185759.755408-2-rrendec@redhat.com Signed-off-by: Sudeep Holla --- drivers/base/cacheinfo.c | 75 +++++++++++++++++++++++++++------------ include/linux/cacheinfo.h | 2 ++ 2 files changed, 55 insertions(+), 22 deletions(-) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index f6573c335f4c..6e0a44bad305 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -398,6 +398,11 @@ static void free_cache_attributes(unsigned int cpu) cache_shared_cpu_map_remove(cpu); } +int __weak early_cache_level(unsigned int cpu) +{ + return -ENOENT; +} + int __weak init_cache_level(unsigned int cpu) { return -ENOENT; @@ -423,56 +428,82 @@ int allocate_cache_info(int cpu) int fetch_cache_info(unsigned int cpu) { - struct cpu_cacheinfo *this_cpu_ci; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); unsigned int levels = 0, split_levels = 0; int ret; if (acpi_disabled) { ret = init_of_cache_level(cpu); - if (ret < 0) - return ret; } else { ret = acpi_get_cache_info(cpu, &levels, &split_levels); - if (ret < 0) + if (!ret) { + this_cpu_ci->num_levels = levels; + /* + * This assumes that: + * - there cannot be any split caches (data/instruction) + * above a unified cache + * - data/instruction caches come by pair + */ + this_cpu_ci->num_leaves = levels + split_levels; + } + } + + if (ret || !cache_leaves(cpu)) { + ret = early_cache_level(cpu); + if (ret) return ret; - this_cpu_ci = get_cpu_cacheinfo(cpu); - this_cpu_ci->num_levels = levels; - /* - * This assumes that: - * - there cannot be any split caches (data/instruction) - * above a unified cache - * - data/instruction caches come by pair - */ - this_cpu_ci->num_leaves = levels + split_levels; + if (!cache_leaves(cpu)) + return -ENOENT; + + this_cpu_ci->early_ci_levels = true; } - if (!cache_leaves(cpu)) - return -ENOENT; return allocate_cache_info(cpu); } -int detect_cache_attributes(unsigned int cpu) +static inline int init_level_allocate_ci(unsigned int cpu) { - int ret; + unsigned int early_leaves = cache_leaves(cpu); /* Since early initialization/allocation of the cacheinfo is allowed * via fetch_cache_info() and this also gets called as CPU hotplug * callbacks via cacheinfo_cpu_online, the init/alloc can be skipped * as it will happen only once (the cacheinfo memory is never freed). - * Just populate the cacheinfo. + * Just populate the cacheinfo. However, if the cacheinfo has been + * allocated early through the arch-specific early_cache_level() call, + * there is a chance the info is wrong (this can happen on arm64). In + * that case, call init_cache_level() anyway to give the arch-specific + * code a chance to make things right. */ - if (per_cpu_cacheinfo(cpu)) - goto populate_leaves; + if (per_cpu_cacheinfo(cpu) && !ci_cacheinfo(cpu)->early_ci_levels) + return 0; if (init_cache_level(cpu) || !cache_leaves(cpu)) return -ENOENT; - ret = allocate_cache_info(cpu); + /* + * Now that we have properly initialized the cache level info, make + * sure we don't try to do that again the next time we are called + * (e.g. as CPU hotplug callbacks). + */ + ci_cacheinfo(cpu)->early_ci_levels = false; + + if (cache_leaves(cpu) <= early_leaves) + return 0; + + kfree(per_cpu_cacheinfo(cpu)); + return allocate_cache_info(cpu); +} + +int detect_cache_attributes(unsigned int cpu) +{ + int ret; + + ret = init_level_allocate_ci(cpu); if (ret) return ret; -populate_leaves: /* * populate_cache_leaves() may completely setup the cache leaves and * shared_cpu_map or it may leave it partially setup. diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 908e19d17f49..6147b2672555 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -76,9 +76,11 @@ struct cpu_cacheinfo { unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated; + bool early_ci_levels; }; struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); +int early_cache_level(unsigned int cpu); int init_cache_level(unsigned int cpu); int init_of_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); -- GitLab From c931680cfa958c8fe9ace31a1dbeefff75597d54 Mon Sep 17 00:00:00 2001 From: Radu Rendec Date: Wed, 12 Apr 2023 14:57:58 -0400 Subject: [PATCH 2812/5631] cacheinfo: Add arm64 early level initializer implementation This patch adds an architecture specific early cache level detection handler for arm64. This is basically the CLIDR_EL1 based detection that was previously done (only) in init_cache_level(). This is part of a patch series that attempts to further the work in commit 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU"). Previously, in the absence of any DT/ACPI cache info, architecture specific cache detection and info allocation for secondary CPUs would happen in non-preemptible context during early CPU initialization and trigger a "BUG: sleeping function called from invalid context" splat on an RT kernel. This patch does not solve the problem completely for RT kernels. It relies on the assumption that on most systems, the CPUs are symmetrical and therefore have the same number of cache leaves. The cacheinfo memory is allocated early (on the primary CPU), relying on the new handler. If later (when CLIDR_EL1 based detection runs again on the secondary CPU) the initial assumption proves to be wrong and the CPU has in fact more leaves, the cacheinfo memory is reallocated, and that still triggers a splat on an RT kernel. In other words, asymmetrical CPU systems *must* still provide cacheinfo data in DT/ACPI to avoid the splat on RT kernels (unless secondary CPUs happen to have less leaves than the primary CPU). But symmetrical CPU systems (the majority) can now get away without the additional DT/ACPI data and rely on CLIDR_EL1 based detection. Signed-off-by: Radu Rendec Reviewed-by: Pierre Gondois Link: https://lore.kernel.org/r/20230412185759.755408-3-rrendec@redhat.com Signed-off-by: Sudeep Holla --- arch/arm64/kernel/cacheinfo.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index c307f69e9b55..d9c9218fa1fd 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -38,11 +38,9 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, this_leaf->type = type; } -int init_cache_level(unsigned int cpu) +static void detect_cache_level(unsigned int *level_p, unsigned int *leaves_p) { unsigned int ctype, level, leaves; - int fw_level, ret; - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { ctype = get_cache_type(level); @@ -54,6 +52,27 @@ int init_cache_level(unsigned int cpu) leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; } + *level_p = level; + *leaves_p = leaves; +} + +int early_cache_level(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + + detect_cache_level(&this_cpu_ci->num_levels, &this_cpu_ci->num_leaves); + + return 0; +} + +int init_cache_level(unsigned int cpu) +{ + unsigned int level, leaves; + int fw_level, ret; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + + detect_cache_level(&level, &leaves); + if (acpi_disabled) { fw_level = of_find_last_cache_level(cpu); } else { -- GitLab From e103d55465db06c5344201fd5fa11bb19bc479c5 Mon Sep 17 00:00:00 2001 From: Radu Rendec Date: Wed, 12 Apr 2023 14:57:59 -0400 Subject: [PATCH 2813/5631] cacheinfo: Allow early level detection when DT/ACPI info is missing/broken Recent work enables cacheinfo memory for secondary CPUs to be allocated early, while still running on the primary CPU. That allows cacheinfo memory to be allocated safely on RT kernels. To make that work, the number of cache levels/leaves must be defined in the device tree or ACPI tables. Further work adds a path for early detection of the number of cache levels/leaves, which makes it possible to allocate the cacheinfo memory early without requiring extra DT/ACPI information. This patch addresses a specific issue with ACPI systems with no PPTT. In that case, parse_acpi_topology() returns an error code, which in turn makes init_cpu_topology() return early, before fetch_cache_info() is called. In that case, the early cache level detection doesn't run. The solution is to simply remove the "return" statement and let the code flow fall through to calling fetch_cache_info(). Signed-off-by: Radu Rendec Reported-by: Pierre Gondois Link: https://lore.kernel.org/all/dea94484-797f-3034-7b86-6d88801c0d91@arm.com/ Reviewed-by: Pierre Gondois Link: https://lore.kernel.org/r/20230412185759.755408-4-rrendec@redhat.com Signed-off-by: Sudeep Holla --- drivers/base/arch_topology.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index b1c1dd38ab01..147fb7d4af96 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -835,10 +835,10 @@ void __init init_cpu_topology(void) if (ret) { /* * Discard anything that was parsed if we hit an error so we - * don't use partial information. + * don't use partial information. But do not return yet to give + * arch-specific early cache level detection a chance to run. */ reset_cpu_topology(); - return; } for_each_possible_cpu(cpu) { -- GitLab From eb411c0cf59ae6344b34bc6f0d298a22b300627e Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Sun, 9 Apr 2023 17:15:52 +0200 Subject: [PATCH 2814/5631] pwm: meson: Fix axg ao mux parents This fix is basically the same as 9bce02ef0dfa ("pwm: meson: Fix the G12A AO clock parents order"). Vendor driver referenced there has xtal as first parent also for axg ao. In addition fix the name of the aoclk81 clock. Apparently name aoclk81 as used by the vendor driver was changed when mainlining the axg clock driver. Fixes: bccaa3f917c9 ("pwm: meson: Add clock source configuration for Meson-AXG") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Signed-off-by: Thierry Reding --- drivers/pwm/pwm-meson.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 5cd7b90872c6..028783088ce1 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -418,7 +418,7 @@ static const struct meson_pwm_data pwm_axg_ee_data = { }; static const char * const pwm_axg_ao_parent_names[] = { - "aoclk81", "xtal", "fclk_div4", "fclk_div5" + "xtal", "axg_ao_clk81", "fclk_div4", "fclk_div5" }; static const struct meson_pwm_data pwm_axg_ao_data = { -- GitLab From 9e4fa80ab7ef9eb4f7b1ea9fc31e0eb040e85e25 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Tue, 11 Apr 2023 07:34:11 +0200 Subject: [PATCH 2815/5631] pwm: meson: Fix g12a ao clk81 name Fix the name of the aoclk81 clock. Apparently name aoclk81 as used by the vendor driver was changed when mainlining the g12a clock driver. Fixes: f41efceb46e6 ("pwm: meson: Add clock source configuration for Meson G12A") Cc: stable@vger.kernel.org Signed-off-by: Heiner Kallweit Reviewed-by: Martin Blumenstingl Signed-off-by: Thierry Reding --- drivers/pwm/pwm-meson.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 028783088ce1..5732300eb004 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -427,7 +427,7 @@ static const struct meson_pwm_data pwm_axg_ao_data = { }; static const char * const pwm_g12a_ao_ab_parent_names[] = { - "xtal", "aoclk81", "fclk_div4", "fclk_div5" + "xtal", "g12a_ao_clk81", "fclk_div4", "fclk_div5" }; static const struct meson_pwm_data pwm_g12a_ao_ab_data = { @@ -436,7 +436,7 @@ static const struct meson_pwm_data pwm_g12a_ao_ab_data = { }; static const char * const pwm_g12a_ao_cd_parent_names[] = { - "xtal", "aoclk81", + "xtal", "g12a_ao_clk81", }; static const struct meson_pwm_data pwm_g12a_ao_cd_data = { -- GitLab From 5e799a7ceed815e71e364b22d0bc5efe3a9ed39f Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 26 Mar 2023 14:37:50 +0200 Subject: [PATCH 2816/5631] iommu/exynos: Use the devm_clk_get_optional() helper Use devm_clk_get_optional() instead of hand writing it. This saves some loC and improves the semantic. Signed-off-by: Christophe JAILLET Acked-by: Marek Szyprowski Link: https://lore.kernel.org/r/99c0d5ce643737ee0952df41fd60433a0bbeb447.1679834256.git.christophe.jaillet@wanadoo.fr Signed-off-by: Joerg Roedel --- drivers/iommu/exynos-iommu.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 483aaaeb6dae..867f409e0325 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -747,22 +747,16 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) return ret; } - data->clk = devm_clk_get(dev, "sysmmu"); - if (PTR_ERR(data->clk) == -ENOENT) - data->clk = NULL; - else if (IS_ERR(data->clk)) + data->clk = devm_clk_get_optional(dev, "sysmmu"); + if (IS_ERR(data->clk)) return PTR_ERR(data->clk); - data->aclk = devm_clk_get(dev, "aclk"); - if (PTR_ERR(data->aclk) == -ENOENT) - data->aclk = NULL; - else if (IS_ERR(data->aclk)) + data->aclk = devm_clk_get_optional(dev, "aclk"); + if (IS_ERR(data->aclk)) return PTR_ERR(data->aclk); - data->pclk = devm_clk_get(dev, "pclk"); - if (PTR_ERR(data->pclk) == -ENOENT) - data->pclk = NULL; - else if (IS_ERR(data->pclk)) + data->pclk = devm_clk_get_optional(dev, "pclk"); + if (IS_ERR(data->pclk)) return PTR_ERR(data->pclk); if (!data->clk && (!data->aclk || !data->pclk)) { @@ -770,10 +764,8 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) return -ENOSYS; } - data->clk_master = devm_clk_get(dev, "master"); - if (PTR_ERR(data->clk_master) == -ENOENT) - data->clk_master = NULL; - else if (IS_ERR(data->clk_master)) + data->clk_master = devm_clk_get_optional(dev, "master"); + if (IS_ERR(data->clk_master)) return PTR_ERR(data->clk_master); data->sysmmu = dev; -- GitLab From 25c2325575cc7f960c9f81f2b77606478f6b911f Mon Sep 17 00:00:00 2001 From: Steven Price Date: Fri, 31 Mar 2023 10:51:54 +0100 Subject: [PATCH 2817/5631] iommu/rockchip: Add missing set_platform_dma_ops callback Similar to exynos, we need a set_platform_dma_ops() callback for proper operation on ARM 32 bit after recent changes in the IOMMU framework (detach ops removal). But also the use of a NULL domain is confusing. Rework the code to add support for IOMMU_DOMAIN_IDENTITY and a singleton rk_identity_domain which is assigned to domain when using an identity mapping rather than "detaching". This makes the code easier to reason about. Signed-off-by: Steven Price Acked-by: Heiko Stuebner Tested-by: Heiko Stuebner Link: https://lore.kernel.org/r/20230331095154.2671129-1-steven.price@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/rockchip-iommu.c | 61 ++++++++++++++++++++++++++-------- 1 file changed, 47 insertions(+), 14 deletions(-) diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index f30db22ea5d7..ea5a3088bb7e 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -124,6 +124,7 @@ struct rk_iommudata { static struct device *dma_dev; static const struct rk_iommu_ops *rk_ops; +static struct iommu_domain rk_identity_domain; static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma, unsigned int count) @@ -646,7 +647,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) * Ignore the return code, though, since we always zap cache * and clear the page fault anyway. */ - if (iommu->domain) + if (iommu->domain != &rk_identity_domain) report_iommu_fault(iommu->domain, iommu->dev, iova, flags); else @@ -980,26 +981,27 @@ static int rk_iommu_enable(struct rk_iommu *iommu) return ret; } -static void rk_iommu_detach_device(struct iommu_domain *domain, - struct device *dev) +static int rk_iommu_identity_attach(struct iommu_domain *identity_domain, + struct device *dev) { struct rk_iommu *iommu; - struct rk_iommu_domain *rk_domain = to_rk_domain(domain); + struct rk_iommu_domain *rk_domain; unsigned long flags; int ret; /* Allow 'virtual devices' (eg drm) to detach from domain */ iommu = rk_iommu_from_dev(dev); if (!iommu) - return; + return -ENODEV; + + rk_domain = to_rk_domain(iommu->domain); dev_dbg(dev, "Detaching from iommu domain\n"); - /* iommu already detached */ - if (iommu->domain != domain) - return; + if (iommu->domain == identity_domain) + return 0; - iommu->domain = NULL; + iommu->domain = identity_domain; spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_del_init(&iommu->node); @@ -1011,8 +1013,31 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, rk_iommu_disable(iommu); pm_runtime_put(iommu->dev); } + + return 0; } +static void rk_iommu_identity_free(struct iommu_domain *domain) +{ +} + +static struct iommu_domain_ops rk_identity_ops = { + .attach_dev = rk_iommu_identity_attach, + .free = rk_iommu_identity_free, +}; + +static struct iommu_domain rk_identity_domain = { + .type = IOMMU_DOMAIN_IDENTITY, + .ops = &rk_identity_ops, +}; + +#ifdef CONFIG_ARM +static void rk_iommu_set_platform_dma(struct device *dev) +{ + WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev)); +} +#endif + static int rk_iommu_attach_device(struct iommu_domain *domain, struct device *dev) { @@ -1035,8 +1060,9 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, if (iommu->domain == domain) return 0; - if (iommu->domain) - rk_iommu_detach_device(iommu->domain, dev); + ret = rk_iommu_identity_attach(&rk_identity_domain, dev); + if (ret) + return ret; iommu->domain = domain; @@ -1050,7 +1076,7 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, ret = rk_iommu_enable(iommu); if (ret) - rk_iommu_detach_device(iommu->domain, dev); + WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev)); pm_runtime_put(iommu->dev); @@ -1061,6 +1087,9 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) { struct rk_iommu_domain *rk_domain; + if (type == IOMMU_DOMAIN_IDENTITY) + return &rk_identity_domain; + if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA) return NULL; @@ -1176,6 +1205,7 @@ static int rk_iommu_of_xlate(struct device *dev, iommu_dev = of_find_device_by_node(args->np); data->iommu = platform_get_drvdata(iommu_dev); + data->iommu->domain = &rk_identity_domain; dev_iommu_priv_set(dev, data); platform_device_put(iommu_dev); @@ -1188,6 +1218,9 @@ static const struct iommu_ops rk_iommu_ops = { .probe_device = rk_iommu_probe_device, .release_device = rk_iommu_release_device, .device_group = rk_iommu_device_group, +#ifdef CONFIG_ARM + .set_platform_dma_ops = rk_iommu_set_platform_dma, +#endif .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, .of_xlate = rk_iommu_of_xlate, .default_domain_ops = &(const struct iommu_domain_ops) { @@ -1343,7 +1376,7 @@ static int __maybe_unused rk_iommu_suspend(struct device *dev) { struct rk_iommu *iommu = dev_get_drvdata(dev); - if (!iommu->domain) + if (iommu->domain == &rk_identity_domain) return 0; rk_iommu_disable(iommu); @@ -1354,7 +1387,7 @@ static int __maybe_unused rk_iommu_resume(struct device *dev) { struct rk_iommu *iommu = dev_get_drvdata(dev); - if (!iommu->domain) + if (iommu->domain == &rk_identity_domain) return 0; return rk_iommu_enable(iommu); -- GitLab From 8f880d19e6ad645a4b8066d5ff091c980b3231e7 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Tue, 4 Apr 2023 00:27:42 -0700 Subject: [PATCH 2818/5631] iommu/amd: Set page size bitmap during V2 domain allocation With the addition of the V2 page table support, the domain page size bitmap needs to be set prior to iommu core setting up direct mappings for reserved regions. When reserved regions are mapped, if this is not done, it will be looking at the V1 page size bitmap when determining the page size to use in iommu_pgsize(). When it gets into the actual amd mapping code, a check of see if the page size is supported can fail, because at that point it is checking it against the V2 page size bitmap which only supports 4K, 2M, and 1G. Add a check to __iommu_domain_alloc() to not override the bitmap if it was already set by the iommu ops domain_alloc() code path. Cc: Vasant Hegde Cc: Suravee Suthikulpanit Cc: Robin Murphy Cc: Will Deacon Cc: Joerg Roedel Fixes: 4db6c41f0946 ("iommu/amd: Add support for using AMD IOMMU v2 page table for DMA-API") Signed-off-by: Jerry Snitselaar Reviewed-by: Vasant Hegde Link: https://lore.kernel.org/r/20230404072742.1895252-1-jsnitsel@redhat.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/iommu.c | 6 ++---- drivers/iommu/iommu.c | 9 +++++++-- 2 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 5a505ba5467e..167da5b1a5e3 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1666,10 +1666,6 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_iommu[iommu->index] += 1; domain->dev_cnt += 1; - /* Override supported page sizes */ - if (domain->flags & PD_GIOV_MASK) - domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2; - /* Update device table */ set_dte_entry(iommu, dev_data->devid, domain, ats, dev_data->iommu_v2); @@ -2048,6 +2044,8 @@ static int protection_domain_init_v2(struct protection_domain *domain) domain->flags |= PD_GIOV_MASK; + domain->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2; + if (domain_enable_v2(domain, 1)) { domain_id_free(domain->id); return -ENOMEM; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 10db680acaed..256a38371120 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1964,8 +1964,13 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, return NULL; domain->type = type; - /* Assume all sizes by default; the driver may override this later */ - domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + /* + * If not already set, assume all sizes by default; the driver + * may override this later + */ + if (!domain->pgsize_bitmap) + domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + if (!domain->ops) domain->ops = bus->iommu_ops->default_domain_ops; -- GitLab From ccc62b827775915a9b82db42a29813d04f92df7a Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Wed, 5 Apr 2023 13:03:17 +0000 Subject: [PATCH 2819/5631] iommu/amd: Fix "Guest Virtual APIC Table Root Pointer" configuration in IRTE commit b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") while refactoring guest virtual APIC activation/de-activation code, stored information for activate/de-activate in "struct amd_ir_data". It used 32-bit integer data type for storing the "Guest Virtual APIC Table Root Pointer" (ga_root_ptr), though the "ga_root_ptr" is actually a 40-bit field in IRTE (Interrupt Remapping Table Entry). This causes interrupts from PCIe devices to not reach the guest in the case of PCIe passthrough with SME (Secure Memory Encryption) enabled as _SME_ bit in the "ga_root_ptr" is lost before writing it to the IRTE. Fix it by using 64-bit data type for storing the "ga_root_ptr". While at that also change the data type of "ga_tag" to u32 in order to match the IOMMU spec. Fixes: b9c6ff94e43a ("iommu/amd: Re-factor guest virtual APIC (de-)activation code") Cc: stable@vger.kernel.org # v5.4+ Reported-by: Alejandro Jimenez Reviewed-by: Suravee Suthikulpanit Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20230405130317.9351-1-kvijayab@amd.com Signed-off-by: Joerg Roedel --- drivers/iommu/amd/amd_iommu_types.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 3d684190b4d5..f7cb1ce0f9bb 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -1001,8 +1001,8 @@ struct amd_ir_data { */ struct irq_cfg *cfg; int ga_vector; - int ga_root_ptr; - int ga_tag; + u64 ga_root_ptr; + u32 ga_tag; }; struct amd_irte_ops { -- GitLab From e494245c756e270e3450983b654c38e6f8aa0b18 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:31 +0800 Subject: [PATCH 2820/5631] dt-bindings: media: mediatek,vcodec: Remove dma-ranges property After commit f1ad5338a4d5 ("of: Fix "dma-ranges" handling for bus controllers"), the dma-ranges of the leaf node doesn't work. Remove it for vcodec here. For mediatek,vcodec-decoder.yaml and mediatek,vcodec-encoder.yaml, this property is in the leaf node, it is invalid as the above comment. Currently there is only mt8195 VENC node has this property in upstream. Indeed, VENC is affected, but it is not a fatal issue. Originally it expects its iova range locate at 4GB-8GB. However after that commit, its expectation doesn't come true, it will fall back to 0-4GB iova and also could work well. Cc: Tiffany Lin Cc: Andrew-CT Chen Cc: Yunfei Dong Cc: Mauro Carvalho Chehab Cc: Matthias Brugger Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Acked-by: Rob Herring Acked-by: Hans Verkuil Link: https://lore.kernel.org/r/20230411093144.2690-2-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/media/mediatek,vcodec-decoder.yaml | 5 ----- .../devicetree/bindings/media/mediatek,vcodec-encoder.yaml | 5 ----- 2 files changed, 10 deletions(-) diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml index aa55ca65d6ed..fad59b486d5d 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-decoder.yaml @@ -56,11 +56,6 @@ properties: List of the hardware port in respective IOMMU block for current Socs. Refer to bindings/iommu/mediatek,iommu.yaml. - dma-ranges: - maxItems: 1 - description: | - Describes the physical address space of IOMMU maps to memory. - mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle description: diff --git a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml index 0f2ea8d9a10c..a2051b31fa29 100644 --- a/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,vcodec-encoder.yaml @@ -49,11 +49,6 @@ properties: List of the hardware port in respective IOMMU block for current Socs. Refer to bindings/iommu/mediatek,iommu.yaml. - dma-ranges: - maxItems: 1 - description: | - Describes the physical address space of IOMMU maps to memory. - mediatek,vpu: $ref: /schemas/types.yaml#/definitions/phandle description: -- GitLab From 559549b1f250a1b5bec3c6c3a9354deead371bde Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:32 +0800 Subject: [PATCH 2821/5631] dt-bindings: media: mediatek,jpeg: Remove dma-ranges property After commit f1ad5338a4d5 ("of: Fix "dma-ranges" handling for bus controllers"), the dma-ranges of the leaf node doesn't work. Remove it for jpeg here. Currently there is only mt8195 jpeg node has this property in upstream, and it already uses parent-child node, this property did work. But instead, MediaTek iommu will control the masters' iova ranges by the master's larb/port id internally, then this property is unnecessary. Cc: Mauro Carvalho Chehab Cc: Matthias Brugger Cc: Bin Liu Cc: kyrie wu Cc: Xia Jiang Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Acked-by: Rob Herring Reviewed-by: Hans Verkuil Link: https://lore.kernel.org/r/20230411093144.2690-3-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../devicetree/bindings/media/mediatek,mt8195-jpegdec.yaml | 7 ------- .../devicetree/bindings/media/mediatek,mt8195-jpegenc.yaml | 7 ------- .../devicetree/bindings/media/mediatek-jpeg-encoder.yaml | 5 ----- 3 files changed, 19 deletions(-) diff --git a/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegdec.yaml b/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegdec.yaml index 71595c013dbb..e5448c60e3eb 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegdec.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegdec.yaml @@ -26,11 +26,6 @@ properties: Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml for details. Ports are according to the HW. - dma-ranges: - maxItems: 1 - description: | - Describes the physical address space of IOMMU maps to memory. - "#address-cells": const: 2 @@ -89,7 +84,6 @@ required: - compatible - power-domains - iommus - - dma-ranges - ranges additionalProperties: false @@ -115,7 +109,6 @@ examples: <&iommu_vpp M4U_PORT_L19_JPGDEC_BSDMA1>, <&iommu_vpp M4U_PORT_L19_JPGDEC_BUFF_OFFSET1>, <&iommu_vpp M4U_PORT_L19_JPGDEC_BUFF_OFFSET0>; - dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; #address-cells = <2>; #size-cells = <2>; ranges; diff --git a/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegenc.yaml b/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegenc.yaml index 95990539f7c0..596186497b68 100644 --- a/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegenc.yaml +++ b/Documentation/devicetree/bindings/media/mediatek,mt8195-jpegenc.yaml @@ -26,11 +26,6 @@ properties: Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml for details. Ports are according to the HW. - dma-ranges: - maxItems: 1 - description: | - Describes the physical address space of IOMMU maps to memory. - "#address-cells": const: 2 @@ -89,7 +84,6 @@ required: - compatible - power-domains - iommus - - dma-ranges - ranges additionalProperties: false @@ -113,7 +107,6 @@ examples: <&iommu_vpp M4U_PORT_L20_JPGENC_C_RDMA>, <&iommu_vpp M4U_PORT_L20_JPGENC_Q_TABLE>, <&iommu_vpp M4U_PORT_L20_JPGENC_BSDMA>; - dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; #address-cells = <2>; #size-cells = <2>; ranges; diff --git a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml index c8412e8ab353..37800e1908cc 100644 --- a/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml +++ b/Documentation/devicetree/bindings/media/mediatek-jpeg-encoder.yaml @@ -44,11 +44,6 @@ properties: Documentation/devicetree/bindings/iommu/mediatek,iommu.yaml for details. Ports are according to the HW. - dma-ranges: - maxItems: 1 - description: | - Describes the physical address space of IOMMU maps to memory. - required: - compatible - reg -- GitLab From ae6693453ac665015929d2b05104d5a2951375af Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:33 +0800 Subject: [PATCH 2822/5631] iommu/mediatek: Improve comment for the current region/bank No functional change. Just add more comment about the current region/bank in the code. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-4-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 6a00ce208dc2..efc247a3989e 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -197,12 +197,33 @@ struct mtk_iommu_plat_data { char *pericfg_comp_str; struct list_head *hw_list; - unsigned int iova_region_nr; - const struct mtk_iommu_iova_region *iova_region; - u8 banks_num; - bool banks_enable[MTK_IOMMU_BANK_MAX]; - unsigned int banks_portmsk[MTK_IOMMU_BANK_MAX]; + /* + * The IOMMU HW may support 16GB iova. In order to balance the IOVA ranges, + * different masters will be put in different iova ranges, for example vcodec + * is in 4G-8G and cam is in 8G-12G. Meanwhile, some masters may have the + * special IOVA range requirement, like CCU can only support the address + * 0x40000000-0x44000000. + * Here list the iova ranges this SoC supports and which larbs/ports are in + * which region. + * + * 16GB iova all use one pgtable, but each a region is a iommu group. + */ + struct { + unsigned int iova_region_nr; + const struct mtk_iommu_iova_region *iova_region; + }; + + /* + * The IOMMU HW may have 5 banks. Each bank has a independent pgtable. + * Here list how many banks this SoC supports/enables and which ports are in which bank. + */ + struct { + u8 banks_num; + bool banks_enable[MTK_IOMMU_BANK_MAX]; + unsigned int banks_portmsk[MTK_IOMMU_BANK_MAX]; + }; + unsigned char larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX]; }; -- GitLab From b2a6876d215b3e980d8ac89ccc704667ad266205 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:34 +0800 Subject: [PATCH 2823/5631] iommu/mediatek: Get regionid from larb/port id After commit f1ad5338a4d5 ("of: Fix "dma-ranges" handling for bus controllers"), the dma-ranges is not allowed for dts leaf node. but we still would like to separate to different masters into different iova regions. Thus we have to separate it by the HW larbid and portid. For example, larb1/2 are in region2 and larb3 is in region3. The problem is that some ports inside a larb are in region4 while some ports inside this larb are in region5. Therefore I define a "iova_region_larb_msk" to help record the information for each a port. Take a example for a larb: [1] = ~0: means all ports in this larb are in region1; [2] = BIT(3) | BIT(4): means port3/4 in this larb are region2; [3] = ~(BIT(3) | BIT(4)): means all the other ports except port3/4 in this larb are region3. This method also avoids the users forget/abuse the iova regions. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-5-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 45 ++++++++++++++++++++++----------------- 1 file changed, 26 insertions(+), 19 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index efc247a3989e..2bbcce783624 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include @@ -212,6 +211,15 @@ struct mtk_iommu_plat_data { struct { unsigned int iova_region_nr; const struct mtk_iommu_iova_region *iova_region; + /* + * Indicate the correspondance between larbs, ports and regions. + * + * The index is the same as iova_region and larb port numbers are + * described as bit positions. + * For example, storing BIT(0) at index 2,1 means "larb 1, port0 is in region 2". + * [2] = { [1] = BIT(0) } + */ + const u32 (*iova_region_larb_msk)[MTK_LARB_NR_MAX]; }; /* @@ -529,30 +537,29 @@ static unsigned int mtk_iommu_get_bank_id(struct device *dev, static int mtk_iommu_get_iova_region_id(struct device *dev, const struct mtk_iommu_plat_data *plat_data) { - const struct mtk_iommu_iova_region *rgn = plat_data->iova_region; - const struct bus_dma_region *dma_rgn = dev->dma_range_map; - int i, candidate = -1; - dma_addr_t dma_end; + struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + unsigned int portidmsk = 0, larbid; + const u32 *rgn_larb_msk; + int i; - if (!dma_rgn || plat_data->iova_region_nr == 1) + if (plat_data->iova_region_nr == 1) return 0; - dma_end = dma_rgn->dma_start + dma_rgn->size - 1; - for (i = 0; i < plat_data->iova_region_nr; i++, rgn++) { - /* Best fit. */ - if (dma_rgn->dma_start == rgn->iova_base && - dma_end == rgn->iova_base + rgn->size - 1) + larbid = MTK_M4U_TO_LARB(fwspec->ids[0]); + for (i = 0; i < fwspec->num_ids; i++) + portidmsk |= BIT(MTK_M4U_TO_PORT(fwspec->ids[i])); + + for (i = 0; i < plat_data->iova_region_nr; i++) { + rgn_larb_msk = plat_data->iova_region_larb_msk[i]; + if (!rgn_larb_msk) + continue; + + if ((rgn_larb_msk[larbid] & portidmsk) == portidmsk) return i; - /* ok if it is inside this region. */ - if (dma_rgn->dma_start >= rgn->iova_base && - dma_end < rgn->iova_base + rgn->size) - candidate = i; } - if (candidate >= 0) - return candidate; - dev_err(dev, "Can NOT find the iommu domain id(%pad 0x%llx).\n", - &dma_rgn->dma_start, dma_rgn->size); + dev_err(dev, "Can NOT find the region for larb(%d-%x).\n", + larbid, portidmsk); return -EINVAL; } -- GitLab From 6b1317f92874cc82719d9f38b7c298dadfc16a6b Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:35 +0800 Subject: [PATCH 2824/5631] iommu/mediatek: mt8192: Add iova_region_larb_msk Add iova_region_larb_msk for mt8192. We separate the 16GB iova regions by each device's larbid/portid. Note: larb3/6/8/10/12/15 connect nothing in this SoC. Refer to the comment in include/dt-bindings/memory/mt8192-larb-port.h Define a new macro MT8192_MULTI_REGION_NR_MAX to indicate the index of mt8xxx_larb_region_msk and "struct mtk_iommu_iova_region mt8192_multi_dom" are the same. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-6-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 2bbcce783624..ed692c2f51d2 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -336,7 +336,12 @@ static const struct mtk_iommu_iova_region single_domain[] = { {.iova_base = 0, .size = SZ_4G}, }; -static const struct mtk_iommu_iova_region mt8192_multi_dom[] = { +#define MT8192_MULTI_REGION_NR_MAX 6 + +#define MT8192_MULTI_REGION_NR (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) ? \ + MT8192_MULTI_REGION_NR_MAX : 1) + +static const struct mtk_iommu_iova_region mt8192_multi_dom[MT8192_MULTI_REGION_NR] = { { .iova_base = 0x0, .size = SZ_4G}, /* 0 ~ 4G */ #if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) { .iova_base = SZ_4G, .size = SZ_4G}, /* 4G ~ 8G */ @@ -1542,6 +1547,17 @@ static const struct mtk_iommu_plat_data mt8186_data_mm = { .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), }; +static const unsigned int mt8192_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0}, /* Region0: larb0/1 */ + [1] = {0, 0, 0, 0, ~0, ~0, 0, ~0}, /* Region1: larb4/5/7 */ + [2] = {0, 0, ~0, 0, 0, 0, 0, 0, /* Region2: larb2/9/11/13/14/16/17/18/19/20 */ + 0, ~0, 0, ~0, 0, ~(u32)(BIT(9) | BIT(10)), ~(u32)(BIT(4) | BIT(5)), 0, + ~0, ~0, ~0, ~0, ~0}, + [3] = {0}, + [4] = {[13] = BIT(9) | BIT(10)}, /* larb13 port9/10 */ + [5] = {[14] = BIT(4) | BIT(5)}, /* larb14 port4/5 */ +}; + static const struct mtk_iommu_plat_data mt8192_data = { .m4u_plat = M4U_MT8192, .flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | @@ -1551,6 +1567,7 @@ static const struct mtk_iommu_plat_data mt8192_data = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8192_larb_region_msk, .larbid_remap = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20}, {0, 14, 16}, {0, 13, 18, 17}}, }; -- GitLab From a43e767d4e1b913a22a80074a703bd29c644a41b Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:36 +0800 Subject: [PATCH 2825/5631] iommu/mediatek: mt8195: Add iova_region_larb_msk Add iova_region_larb_msk for mt8195. We separate the 16GB iova regions by each device's larbid/portid. Refer to include/dt-bindings/memory/mt8195-memory-port.h Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-7-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index ed692c2f51d2..35e64f65b164 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1587,6 +1587,21 @@ static const struct mtk_iommu_plat_data mt8195_data_infra = { .iova_region_nr = ARRAY_SIZE(single_domain), }; +static const unsigned int mt8195_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0, ~0, ~0}, /* Region0: all ports for larb0/1/2/3 */ + [1] = {0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, ~0, ~0, ~0, ~0, ~0, /* Region1: larb19/20/21/22/23/24 */ + ~0}, + [2] = {0, 0, 0, 0, ~0, ~0, ~0, ~0, /* Region2: the other larbs. */ + ~0, ~0, ~0, ~0, ~0, ~0, ~0, ~0, + ~0, ~0, 0, 0, 0, 0, 0, 0, + 0, ~0, ~0, ~0, ~0}, + [3] = {0}, + [4] = {[18] = BIT(0) | BIT(1)}, /* Only larb18 port0/1 */ + [5] = {[18] = BIT(2) | BIT(3)}, /* Only larb18 port2/3 */ +}; + static const struct mtk_iommu_plat_data mt8195_data_vdo = { .m4u_plat = M4U_MT8195, .flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | @@ -1597,6 +1612,7 @@ static const struct mtk_iommu_plat_data mt8195_data_vdo = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8195_larb_region_msk, .larbid_remap = {{2, 0}, {21}, {24}, {7}, {19}, {9, 10, 11}, {13, 17, 15/* 17b */, 25}, {5}}, }; @@ -1611,6 +1627,7 @@ static const struct mtk_iommu_plat_data mt8195_data_vpp = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8195_larb_region_msk, .larbid_remap = {{1}, {3}, {22, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 23}, {8}, {20}, {12}, -- GitLab From f5d4233ad373a1b0ab7c5d10f9b6e79619ecf194 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:37 +0800 Subject: [PATCH 2826/5631] iommu/mediatek: mt8186: Add iova_region_larb_msk Add iova_region_larb_msk for mt8186. We separate the 16GB iova regions by each device's larbid/portid. Note: larb5/6/10/12/14/15/18 connect nothing in this SoC. Refer to include/dt-bindings/memory/mt8186-memory-port.h Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-8-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 35e64f65b164..c8e2840cda15 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -1533,6 +1533,18 @@ static const struct mtk_iommu_plat_data mt8183_data = { .larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}}, }; +static const unsigned int mt8186_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { + [0] = {~0, ~0, ~0}, /* Region0: all ports for larb0/1/2 */ + [1] = {0, 0, 0, 0, ~0, 0, 0, ~0}, /* Region1: larb4/7 */ + [2] = {0, 0, 0, 0, 0, 0, 0, 0, /* Region2: larb8/9/11/13/16/17/19/20 */ + ~0, ~0, 0, ~0, 0, ~(u32)(BIT(9) | BIT(10)), 0, 0, + /* larb13: the other ports except port9/10 */ + ~0, ~0, 0, ~0, ~0}, + [3] = {0}, + [4] = {[13] = BIT(9) | BIT(10)}, /* larb13 port9/10 */ + [5] = {[14] = ~0}, /* larb14 */ +}; + static const struct mtk_iommu_plat_data mt8186_data_mm = { .m4u_plat = M4U_MT8186, .flags = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | @@ -1545,6 +1557,7 @@ static const struct mtk_iommu_plat_data mt8186_data_mm = { .banks_enable = {true}, .iova_region = mt8192_multi_dom, .iova_region_nr = ARRAY_SIZE(mt8192_multi_dom), + .iova_region_larb_msk = mt8186_larb_region_msk, }; static const unsigned int mt8192_larb_region_msk[MT8192_MULTI_REGION_NR_MAX][MTK_LARB_NR_MAX] = { -- GitLab From 3df9bdd4ae8e41b526906f2f6e9fa2470a9bbbe0 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:38 +0800 Subject: [PATCH 2827/5631] iommu/mediatek: Add a gap for the iova regions As the removed property in the vcodec dt-binding, the property is: dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; The length is 0xfff0_0000 rather than 0x1_0000_0000, this means it requires 1M as a gap. This is because the end address for some vcodec HW is (address + size). If the size is 4G, the end address may be 0x2_0000_0000, and the width for vcodec register only is 32, then the HW may get the ZERO address. Currently the consumer's dma-ranges property doesn't work, IOMMU has to consider this case. Add a bigger gap(8M) for all the regions to avoid it. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-9-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index c8e2840cda15..9fee4b6efb7b 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -332,8 +332,10 @@ static LIST_HEAD(m4ulist); /* List all the M4U HWs */ #define for_each_m4u(data, head) list_for_each_entry(data, head, list) +#define MTK_IOMMU_IOVA_SZ_4G (SZ_4G - SZ_8M) /* 8M as gap */ + static const struct mtk_iommu_iova_region single_domain[] = { - {.iova_base = 0, .size = SZ_4G}, + {.iova_base = 0, .size = MTK_IOMMU_IOVA_SZ_4G}, }; #define MT8192_MULTI_REGION_NR_MAX 6 @@ -342,11 +344,11 @@ static const struct mtk_iommu_iova_region single_domain[] = { MT8192_MULTI_REGION_NR_MAX : 1) static const struct mtk_iommu_iova_region mt8192_multi_dom[MT8192_MULTI_REGION_NR] = { - { .iova_base = 0x0, .size = SZ_4G}, /* 0 ~ 4G */ + { .iova_base = 0x0, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 0 ~ 4G, */ #if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) - { .iova_base = SZ_4G, .size = SZ_4G}, /* 4G ~ 8G */ - { .iova_base = SZ_4G * 2, .size = SZ_4G}, /* 8G ~ 12G */ - { .iova_base = SZ_4G * 3, .size = SZ_4G}, /* 12G ~ 16G */ + { .iova_base = SZ_4G, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 4G ~ 8G */ + { .iova_base = SZ_4G * 2, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 8G ~ 12G */ + { .iova_base = SZ_4G * 3, .size = MTK_IOMMU_IOVA_SZ_4G}, /* 12G ~ 16G */ { .iova_base = 0x240000000ULL, .size = 0x4000000}, /* CCU0 */ { .iova_base = 0x244000000ULL, .size = 0x4000000}, /* CCU1 */ -- GitLab From f7da2da8675b061f9397f2701c6cc21cb908291b Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:39 +0800 Subject: [PATCH 2828/5631] iommu/mediatek: Set dma_mask for the master devices MediaTek iommu arranges dma ranges for all the masters, this patch is to help them set dma mask. This is to avoid each master setting their own mask, but also to avoid a real issue, such as JPEG uses "mediatek,mtk-jpgenc" for 2701/8183/8186/8188, then JPEG could ignore its different dma_mask in different SoC to achieve common code. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-10-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/iommu/mtk_iommu.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index 9fee4b6efb7b..95b1bdb58cbe 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -738,6 +738,14 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain, } mutex_unlock(&data->mutex); + if (region_id > 0) { + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(34)); + if (ret) { + dev_err(m4udev, "Failed to set dma_mask for %s(%d).\n", dev_name(dev), ret); + return ret; + } + } + return mtk_iommu_config(data, dev, true, region_id); err_unlock: -- GitLab From 7d35584d9c6d2a78d8ab95450fafec40620ddf19 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:40 +0800 Subject: [PATCH 2829/5631] media: mtk-jpegdec: Remove the setting for dma_mask In order to simplify the masters to set their respective dma masks, MTK IOMMU helps to centralize the processing. Because all the dma ranges is set in IOMMU, IOMMU knows well the dma mask requirements of masters. After this patch, the masters code does not need care dma-ranges/dma_mask related information. Cc: Bin Liu Cc: Mauro Carvalho Chehab Cc: kyrie wu Signed-off-by: Yong Wu Acked-by: Hans Verkuil Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-11-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c index 969516a940ba..9b96d2436311 100644 --- a/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mediatek/jpeg/mtk_jpeg_core.c @@ -1757,9 +1757,6 @@ static int mtk_jpeg_probe(struct platform_device *pdev) jpeg->vdev->device_caps = V4L2_CAP_STREAMING | V4L2_CAP_VIDEO_M2M_MPLANE; - if (of_get_property(pdev->dev.of_node, "dma-ranges", NULL)) - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34)); - ret = video_register_device(jpeg->vdev, VFL_TYPE_VIDEO, -1); if (ret) { v4l2_err(&jpeg->v4l2_dev, "Failed to register video device\n"); -- GitLab From aa0ee7b4d5221127a0fe80afb716a1ac72473d72 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:41 +0800 Subject: [PATCH 2830/5631] media: mediatek: vcodec: Remove the setting for dma_mask In order to simplify the masters to set their respective dma masks, MTK IOMMU helps to centralize the processing. Because all the dma ranges is set in IOMMU, IOMMU knows well the dma mask requirements of masters. After this patch, the masters(codec here) code does not need care dma-ranges/dma_mask related information. Cc: Tiffany Lin Cc: Andrew-CT Chen Cc: Yunfei Dong Cc: Mauro Carvalho Chehab Cc: irui wang Signed-off-by: Yong Wu Acked-by: Hans Verkuil Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-12-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- .../media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c | 8 -------- .../media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c | 3 --- 2 files changed, 11 deletions(-) diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c index 174a6eec2f54..11583405cf61 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c @@ -321,14 +321,6 @@ static int mtk_vcodec_probe(struct platform_device *pdev) } } - if (of_get_property(pdev->dev.of_node, "dma-ranges", NULL)) { - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34)); - if (ret) { - mtk_v4l2_err("Failed to set mask"); - goto err_core_workq; - } - } - for (i = 0; i < MTK_VDEC_HW_MAX; i++) mutex_init(&dev->dec_mutex[i]); mutex_init(&dev->dev_mutex); diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c index 9095186d5495..50e5571608cd 100644 --- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c +++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c @@ -344,9 +344,6 @@ static int mtk_vcodec_probe(struct platform_device *pdev) goto err_event_workq; } - if (of_get_property(pdev->dev.of_node, "dma-ranges", NULL)) - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(34)); - ret = video_register_device(vfd_enc, VFL_TYPE_VIDEO, -1); if (ret) { mtk_v4l2_err("Failed to register video device"); -- GitLab From 2aa6e5f63ea2b1768afbde763a948534c190254e Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:42 +0800 Subject: [PATCH 2831/5631] arm64: dts: mt8195: Remove the unnecessary dma-ranges After we add the dma-ranges in the parent "soc" node, this property is unnecessary for the leaf node. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-13-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- arch/arm64/boot/dts/mediatek/mt8195.dtsi | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 8f1264d5290b..89f469ba9f6c 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -2299,7 +2299,6 @@ power-domains = <&spm MT8195_POWER_DOMAIN_VENC>; #address-cells = <2>; #size-cells = <2>; - dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; }; jpgdec-master { @@ -2311,7 +2310,6 @@ <&iommu_vdo M4U_PORT_L19_JPGDEC_BSDMA1>, <&iommu_vdo M4U_PORT_L19_JPGDEC_BUFF_OFFSET1>, <&iommu_vdo M4U_PORT_L19_JPGDEC_BUFF_OFFSET0>; - dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; #address-cells = <2>; #size-cells = <2>; ranges; @@ -2383,7 +2381,6 @@ <&iommu_vpp M4U_PORT_L20_JPGENC_C_RDMA>, <&iommu_vpp M4U_PORT_L20_JPGENC_Q_TABLE>, <&iommu_vpp M4U_PORT_L20_JPGENC_BSDMA>; - dma-ranges = <0x1 0x0 0x0 0x40000000 0x0 0xfff00000>; #address-cells = <2>; #size-cells = <2>; ranges; -- GitLab From 88c531b42a986c02a2630b84521d3dfe19b01686 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:43 +0800 Subject: [PATCH 2832/5631] arm64: dts: mt8195: Add dma-ranges for the parent "soc" node After commit f1ad5338a4d5 ("of: Fix "dma-ranges" handling for bus controllers"), the dma-ranges property is not allowed for the leaf node. But our iommu/dma-ranges is 16GB, we still expect separate the 16GB dma-range like: a) display is in 0 - 4GB; b) vcodec is in 4GB - 8GB; c) camera is in 8GB - 12GB. We can not expect all the masters add a parent node for them, especial for the existed drivers/nodes. Thus, we add whole the 16GB dma-ranges in the parent "soc" node. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-14-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- arch/arm64/boot/dts/mediatek/mt8195.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 89f469ba9f6c..7d87cbabc9f1 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -364,6 +364,7 @@ #size-cells = <2>; compatible = "simple-bus"; ranges; + dma-ranges = <0x0 0x0 0x0 0x0 0x4 0x0>; gic: interrupt-controller@c000000 { compatible = "arm,gic-v3"; -- GitLab From f543028451d1361b7e6ab45b42503a31047c3102 Mon Sep 17 00:00:00 2001 From: Yong Wu Date: Tue, 11 Apr 2023 17:31:44 +0800 Subject: [PATCH 2833/5631] arm64: dts: mt8186: Add dma-ranges for the parent "soc" node Prepare for the MM nodes whose dma-ranges(iova range) is 16GB. Signed-off-by: Yong Wu Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230411093144.2690-15-yong.wu@mediatek.com Signed-off-by: Joerg Roedel --- arch/arm64/boot/dts/mediatek/mt8186.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi index a0d3e1f731bd..251eace411c0 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi @@ -324,6 +324,7 @@ #address-cells = <2>; #size-cells = <2>; compatible = "simple-bus"; + dma-ranges = <0x0 0x0 0x0 0x0 0x4 0x0>; ranges; gic: interrupt-controller@c000000 { -- GitLab From 84c9ef72b64d9bd0d8a219a75019ec4c2da77a08 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:29 +0800 Subject: [PATCH 2834/5631] dmaengine: idxd: Add enable/disable device IOPF feature The iommu subsystem requires IOMMU_DEV_FEAT_IOPF must be enabled before and disabled after IOMMU_DEV_FEAT_SVA, if device's I/O page faults rely on the IOMMU. Add explicit IOMMU_DEV_FEAT_IOPF enabling/disabling in this driver. At present, missing IOPF enabling/disabling doesn't cause any real issue, because the IOMMU driver places the IOPF enabling/disabling in the path of SVA feature handling. But this may change. Reviewed-by: Dave Jiang Reviewed-by: Fenghua Yu Reviewed-by: Kevin Tian Acked-by: Vinod Koul Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/dma/idxd/init.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 640d3048368e..09ef62aa0635 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -516,6 +516,27 @@ static void idxd_disable_system_pasid(struct idxd_device *idxd) idxd->sva = NULL; } +static int idxd_enable_sva(struct pci_dev *pdev) +{ + int ret; + + ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF); + if (ret) + return ret; + + ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + if (ret) + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF); + + return ret; +} + +static void idxd_disable_sva(struct pci_dev *pdev) +{ + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF); +} + static int idxd_probe(struct idxd_device *idxd) { struct pci_dev *pdev = idxd->pdev; @@ -530,7 +551,7 @@ static int idxd_probe(struct idxd_device *idxd) dev_dbg(dev, "IDXD reset complete\n"); if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM) && sva) { - if (iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA)) { + if (idxd_enable_sva(pdev)) { dev_warn(dev, "Unable to turn on user SVA feature.\n"); } else { set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags); @@ -578,21 +599,19 @@ static int idxd_probe(struct idxd_device *idxd) if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); if (device_user_pasid_enabled(idxd)) - iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA); + idxd_disable_sva(pdev); return rc; } static void idxd_cleanup(struct idxd_device *idxd) { - struct device *dev = &idxd->pdev->dev; - perfmon_pmu_remove(idxd); idxd_cleanup_interrupts(idxd); idxd_cleanup_internals(idxd); if (device_pasid_enabled(idxd)) idxd_disable_system_pasid(idxd); if (device_user_pasid_enabled(idxd)) - iommu_dev_disable_feature(dev, IOMMU_DEV_FEAT_SVA); + idxd_disable_sva(idxd->pdev); } static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) @@ -710,7 +729,7 @@ static void idxd_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); pci_iounmap(pdev, idxd->reg_base); if (device_user_pasid_enabled(idxd)) - iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA); + idxd_disable_sva(pdev); pci_disable_device(pdev); destroy_workqueue(idxd->wq); perfmon_pmu_remove(idxd); -- GitLab From a86fb7717320bf2c05701cbcfaab5afc452d1480 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:30 +0800 Subject: [PATCH 2835/5631] iommu/vt-d: Allow SVA with device-specific IOPF Currently enabling SVA requires IOPF support from the IOMMU and device PCI PRI. However, some devices can handle IOPF by itself without ever sending PCI page requests nor advertising PRI capability. Allow SVA support with IOPF handled either by IOMMU (PCI PRI) or device driver (device-specific IOPF). As long as IOPF could be handled, SVA should continue to work. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 7c2f4bd33582..caf664448ee9 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4650,7 +4650,21 @@ static int intel_iommu_enable_sva(struct device *dev) if (!(iommu->flags & VTD_FLAG_SVM_CAPABLE)) return -ENODEV; - if (!info->pasid_enabled || !info->pri_enabled || !info->ats_enabled) + if (!info->pasid_enabled || !info->ats_enabled) + return -EINVAL; + + /* + * Devices having device-specific I/O fault handling should not + * support PCI/PRI. The IOMMU side has no means to check the + * capability of device-specific IOPF. Therefore, IOMMU can only + * default that if the device driver enables SVA on a non-PRI + * device, it will handle IOPF in its own way. + */ + if (!info->pri_supported) + return 0; + + /* Devices supporting PRI should have it enabled. */ + if (!info->pri_enabled) return -EINVAL; ret = iopf_queue_add_device(iommu->iopf_queue, dev); -- GitLab From 3d4c7cc3d168dc728dd3472688b2360b6db124e3 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:31 +0800 Subject: [PATCH 2836/5631] iommu/vt-d: Move iopf code from SVA to IOPF enabling path Generally enabling IOMMU_DEV_FEAT_SVA requires IOMMU_DEV_FEAT_IOPF, but some devices manage I/O Page Faults themselves instead of relying on the IOMMU. Move IOPF related code from SVA to IOPF enabling path. For the device drivers that relies on the IOMMU for IOPF through PCI/PRI, IOMMU_DEV_FEAT_IOPF must be enabled before and disabled after IOMMU_DEV_FEAT_SVA. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index caf664448ee9..a6f07c74da2d 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4638,7 +4638,6 @@ static int intel_iommu_enable_sva(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; - int ret; if (!info || dmar_disabled) return -EINVAL; @@ -4667,6 +4666,21 @@ static int intel_iommu_enable_sva(struct device *dev) if (!info->pri_enabled) return -EINVAL; + return 0; +} + +static int intel_iommu_enable_iopf(struct device *dev) +{ + struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu; + int ret; + + if (!info || !info->ats_enabled || !info->pri_enabled) + return -ENODEV; + iommu = info->iommu; + if (!iommu) + return -EINVAL; + ret = iopf_queue_add_device(iommu->iopf_queue, dev); if (ret) return ret; @@ -4678,7 +4692,7 @@ static int intel_iommu_enable_sva(struct device *dev) return ret; } -static int intel_iommu_disable_sva(struct device *dev) +static int intel_iommu_disable_iopf(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; @@ -4695,16 +4709,6 @@ static int intel_iommu_disable_sva(struct device *dev) return ret; } -static int intel_iommu_enable_iopf(struct device *dev) -{ - struct device_domain_info *info = dev_iommu_priv_get(dev); - - if (info && info->pri_supported) - return 0; - - return -ENODEV; -} - static int intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) { @@ -4725,10 +4729,10 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) { switch (feat) { case IOMMU_DEV_FEAT_IOPF: - return 0; + return intel_iommu_disable_iopf(dev); case IOMMU_DEV_FEAT_SVA: - return intel_iommu_disable_sva(dev); + return 0; default: return -ENODEV; -- GitLab From 5ae4008055fed503f7bf42aeed45d3b032a79876 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:32 +0800 Subject: [PATCH 2837/5631] iommu/vt-d: Move pfsid and ats_qdep calculation to device probe path They should be part of the per-device iommu private data initialization. Reviewed-by: Jacob Pan Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-5-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a6f07c74da2d..6d77b4072fdd 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1406,20 +1406,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) return; pdev = to_pci_dev(info->dev); - /* For IOMMU that supports device IOTLB throttling (DIT), we assign - * PFSID to the invalidation desc of a VF such that IOMMU HW can gauge - * queue depth at PF level. If DIT is not set, PFSID will be treated as - * reserved, which should be set to 0. - */ - if (!ecap_dit(info->iommu->ecap)) - info->pfsid = 0; - else { - struct pci_dev *pf_pdev; - - /* pdev will be returned if device is not a vf */ - pf_pdev = pci_physfn(pdev); - info->pfsid = pci_dev_id(pf_pdev); - } /* The PCIe spec, in its wisdom, declares that the behaviour of the device if you enable PASID support after ATS support is @@ -1438,7 +1424,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; domain_update_iotlb(info->domain); - info->ats_qdep = pci_ats_queue_depth(pdev); } } @@ -4521,6 +4506,17 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + + /* + * For IOMMU that supports device IOTLB throttling + * (DIT), we assign PFSID to the invalidation desc + * of a VF such that IOMMU HW can gauge queue depth + * at PF level. If DIT is not set, PFSID will be + * treated as reserved, which should be set to 0. + */ + if (ecap_dit(iommu->ecap)) + info->pfsid = pci_dev_id(pci_physfn(pdev)); + info->ats_qdep = pci_ats_queue_depth(pdev); } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { -- GitLab From fbcde5bb92bd3d299688d615dce26c59d3f63694 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:33 +0800 Subject: [PATCH 2838/5631] iommu/vt-d: Move PRI handling to IOPF feature path PRI is only used for IOPF. With this move, the PCI/PRI feature could be controlled by the device driver through iommu_dev_enable/disable_feature() interfaces. Reviewed-by: Jacob Pan Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 53 ++++++++++++++++++++++++++++--------- 1 file changed, 41 insertions(+), 12 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 6d77b4072fdd..cd3a3c4b5e64 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1415,11 +1415,6 @@ static void iommu_enable_pci_caps(struct device_domain_info *info) if (info->pasid_supported && !pci_enable_pasid(pdev, info->pasid_supported & ~1)) info->pasid_enabled = 1; - if (info->pri_supported && - (info->pasid_enabled ? pci_prg_resp_pasid_required(pdev) : 1) && - !pci_reset_pri(pdev) && !pci_enable_pri(pdev, PRQ_DEPTH)) - info->pri_enabled = 1; - if (info->ats_supported && pci_ats_page_aligned(pdev) && !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) { info->ats_enabled = 1; @@ -1442,11 +1437,6 @@ static void iommu_disable_pci_caps(struct device_domain_info *info) domain_update_iotlb(info->domain); } - if (info->pri_enabled) { - pci_disable_pri(pdev); - info->pri_enabled = 0; - } - if (info->pasid_enabled) { pci_disable_pasid(pdev); info->pasid_enabled = 0; @@ -4667,23 +4657,48 @@ static int intel_iommu_enable_sva(struct device *dev) static int intel_iommu_enable_iopf(struct device *dev) { + struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL; struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu; int ret; - if (!info || !info->ats_enabled || !info->pri_enabled) + if (!pdev || !info || !info->ats_enabled || !info->pri_supported) return -ENODEV; + + if (info->pri_enabled) + return -EBUSY; + iommu = info->iommu; if (!iommu) return -EINVAL; + /* PASID is required in PRG Response Message. */ + if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev)) + return -EINVAL; + + ret = pci_reset_pri(pdev); + if (ret) + return ret; + ret = iopf_queue_add_device(iommu->iopf_queue, dev); if (ret) return ret; ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); if (ret) - iopf_queue_remove_device(iommu->iopf_queue, dev); + goto iopf_remove_device; + + ret = pci_enable_pri(pdev, PRQ_DEPTH); + if (ret) + goto iopf_unregister_handler; + info->pri_enabled = 1; + + return 0; + +iopf_unregister_handler: + iommu_unregister_device_fault_handler(dev); +iopf_remove_device: + iopf_queue_remove_device(iommu->iopf_queue, dev); return ret; } @@ -4694,6 +4709,20 @@ static int intel_iommu_disable_iopf(struct device *dev) struct intel_iommu *iommu = info->iommu; int ret; + if (!info->pri_enabled) + return -EINVAL; + + /* + * PCIe spec states that by clearing PRI enable bit, the Page + * Request Interface will not issue new page requests, but has + * outstanding page requests that have been transmitted or are + * queued for transmission. This is supposed to be called after + * the device driver has stopped DMA, all PASIDs have been + * unbound and the outstanding PRQs have been drained. + */ + pci_disable_pri(to_pci_dev(dev)); + info->pri_enabled = 0; + ret = iommu_unregister_device_fault_handler(dev); if (ret) return ret; -- GitLab From 7b8aa998d627afeef576ab61bf8e286f56439bb2 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:34 +0800 Subject: [PATCH 2839/5631] iommu/vt-d: Remove unnecessary checks in iopf disabling path iommu_unregister_device_fault_handler() and iopf_queue_remove_device() are called after device has stopped issuing new page falut requests and all outstanding page requests have been drained. They should never fail. Trigger a warning if it happens unfortunately. Reviewed-by: Kevin Tian Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230324120234.313643-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index cd3a3c4b5e64..c771233d6f2a 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -4707,7 +4707,6 @@ static int intel_iommu_disable_iopf(struct device *dev) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_iommu *iommu = info->iommu; - int ret; if (!info->pri_enabled) return -EINVAL; @@ -4723,15 +4722,15 @@ static int intel_iommu_disable_iopf(struct device *dev) pci_disable_pri(to_pci_dev(dev)); info->pri_enabled = 0; - ret = iommu_unregister_device_fault_handler(dev); - if (ret) - return ret; - - ret = iopf_queue_remove_device(iommu->iopf_queue, dev); - if (ret) - iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev); + /* + * With PRI disabled and outstanding PRQs drained, unregistering + * fault handler and removing device from iopf queue should never + * fail. + */ + WARN_ON(iommu_unregister_device_fault_handler(dev)); + WARN_ON(iopf_queue_remove_device(iommu->iopf_queue, dev)); - return ret; + return 0; } static int -- GitLab From 41d71e09a155a05bd9bec08dd195d8d8e0146ad8 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 13 Apr 2023 12:06:35 +0800 Subject: [PATCH 2840/5631] iommu/vt-d: Do not use GFP_ATOMIC when not needed There is no need to use GFP_ATOMIC here. GFP_KERNEL is already used for some other memory allocations just a few lines above. Commit e3a981d61d15 ("iommu/vt-d: Convert allocations to GFP_KERNEL") has changed the other memory allocation flags. Signed-off-by: Christophe JAILLET Link: https://lore.kernel.org/r/e2a8a1019ffc8a86b4b4ed93def3623f60581274.1675542576.git.christophe.jaillet@wanadoo.fr Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/irq_remapping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 6d01fa078c36..013ccc25ee4f 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -552,7 +552,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) goto out_free_table; } - bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_ATOMIC); + bitmap = bitmap_zalloc(INTR_REMAP_TABLE_ENTRIES, GFP_KERNEL); if (bitmap == NULL) { pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id); goto out_free_pages; -- GitLab From a06c2ecec113fa882f48eb71e9d7e8fb520b1c78 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 13 Apr 2023 12:06:36 +0800 Subject: [PATCH 2841/5631] iommu/vt-d: Remove extern from function prototypes The kernel coding style does not require 'extern' in function prototypes in .h files, so remove them from drivers/iommu/intel/iommu.h as they are not needed. Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230331045452.500265-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.h | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..f843493dc4f2 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -796,18 +796,18 @@ static inline bool context_present(struct context_entry *context) return (context->lo & 1); } -extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); - -extern int dmar_enable_qi(struct intel_iommu *iommu); -extern void dmar_disable_qi(struct intel_iommu *iommu); -extern int dmar_reenable_qi(struct intel_iommu *iommu); -extern void qi_global_iec(struct intel_iommu *iommu); - -extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, - u8 fm, u64 type); -extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, - unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, +struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev); + +int dmar_enable_qi(struct intel_iommu *iommu); +void dmar_disable_qi(struct intel_iommu *iommu); +int dmar_reenable_qi(struct intel_iommu *iommu); +void qi_global_iec(struct intel_iommu *iommu); + +void qi_flush_context(struct intel_iommu *iommu, u16 did, + u16 sid, u8 fm, u64 type); +void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, + unsigned int size_order, u64 type); +void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, u16 qdep, u64 addr, unsigned mask); void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, @@ -830,7 +830,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc, */ #define QI_OPT_WAIT_DRAIN BIT(0) -extern int dmar_ir_support(void); +int dmar_ir_support(void); void *alloc_pgtable_page(int node, gfp_t gfp); void free_pgtable_page(void *vaddr); @@ -838,9 +838,9 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM -extern void intel_svm_check(struct intel_iommu *iommu); -extern int intel_svm_enable_prq(struct intel_iommu *iommu); -extern int intel_svm_finish_prq(struct intel_iommu *iommu); +void intel_svm_check(struct intel_iommu *iommu); +int intel_svm_enable_prq(struct intel_iommu *iommu); +int intel_svm_finish_prq(struct intel_iommu *iommu); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); struct iommu_domain *intel_svm_domain_alloc(void); @@ -887,8 +887,8 @@ extern const struct iommu_ops intel_iommu_ops; #ifdef CONFIG_INTEL_IOMMU extern int intel_iommu_sm; -extern int iommu_calculate_agaw(struct intel_iommu *iommu); -extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); +int iommu_calculate_agaw(struct intel_iommu *iommu); +int iommu_calculate_max_sagaw(struct intel_iommu *iommu); int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob); static inline bool ecmd_has_pmu_essential(struct intel_iommu *iommu) -- GitLab From a7050fbde36e0634f89d41e6384c140fe4ae011e Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 13 Apr 2023 12:06:37 +0800 Subject: [PATCH 2842/5631] iommu/vt-d: Use non-privileged mode for all PASIDs Supervisor Request Enable (SRE) bit in a PASID entry is for permission checking on DMA requests. When SRE = 0, DMA with supervisor privilege will be blocked. However, for in-kernel DMA this is not necessary in that we are targeting kernel memory anyway. There's no need to differentiate user and kernel for in-kernel DMA. Let's use non-privileged (user) permission for all PASIDs used in kernel, it will be consistent with DMA without PASID (RID_PASID) as well. Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230331231137.1947675-2-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c771233d6f2a..f4e536fd5a28 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2316,8 +2316,6 @@ static int domain_setup_first_level(struct intel_iommu *iommu, if (level != 4 && level != 5) return -EINVAL; - if (pasid != PASID_RID2PASID) - flags |= PASID_FLAG_SUPERVISOR_MODE; if (level == 5) flags |= PASID_FLAG_FL5LP; -- GitLab From 113a031becc8a1b904d7fd873fb3d329f203d2f0 Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Thu, 13 Apr 2023 12:06:38 +0800 Subject: [PATCH 2843/5631] iommu/vt-d: Remove PASID supervisor request support There's no more usage, remove PASID supervisor support. Suggested-by: Lu Baolu Reviewed-by: Lu Baolu Signed-off-by: Jacob Pan Link: https://lore.kernel.org/r/20230331231137.1947675-3-jacob.jun.pan@linux.intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/pasid.c | 43 ------------------------------------- drivers/iommu/intel/pasid.h | 7 ------ 2 files changed, 50 deletions(-) diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index 633e0a4a01e7..c5d479770e12 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -335,15 +335,6 @@ static inline void pasid_set_fault_enable(struct pasid_entry *pe) pasid_set_bits(&pe->val[0], 1 << 1, 0); } -/* - * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a - * scalable mode PASID entry. - */ -static inline void pasid_set_sre(struct pasid_entry *pe) -{ - pasid_set_bits(&pe->val[2], 1 << 0, 1); -} - /* * Setup the WPE(Write Protect Enable) field (Bit 132) of a * scalable mode PASID entry. @@ -521,23 +512,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, return -EINVAL; } - if (flags & PASID_FLAG_SUPERVISOR_MODE) { -#ifdef CONFIG_X86 - unsigned long cr0 = read_cr0(); - - /* CR0.WP is normally set but just to be sure */ - if (unlikely(!(cr0 & X86_CR0_WP))) { - pr_err("No CPU write protect!\n"); - return -EINVAL; - } -#endif - if (!ecap_srs(iommu->ecap)) { - pr_err("No supervisor request support on %s\n", - iommu->name); - return -EINVAL; - } - } - if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) { pr_err("No 5-level paging support for first-level on %s\n", iommu->name); @@ -560,10 +534,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu, /* Setup the first level page table pointer: */ pasid_set_flptr(pte, (u64)__pa(pgd)); - if (flags & PASID_FLAG_SUPERVISOR_MODE) { - pasid_set_sre(pte); - pasid_set_wpe(pte); - } if (flags & PASID_FLAG_FL5LP) pasid_set_flpm(pte, 1); @@ -658,12 +628,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - /* - * Since it is a second level only translation setup, we should - * set SRE bit as well (addresses are expected to be GPAs). - */ - if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -700,13 +664,6 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT); pasid_set_fault_enable(pte); pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap)); - - /* - * We should set SRE bit as well since the addresses are expected - * to be GPAs. - */ - if (ecap_srs(iommu->ecap)) - pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 20c54e50f533..d6b7d21244b1 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -41,13 +41,6 @@ #define FLPT_DEFAULT_DID 1 #define NUM_RESERVED_DID 2 -/* - * The SUPERVISOR_MODE flag indicates a first level translation which - * can be used for access to kernel addresses. It is valid only for - * access to the kernel's static 1:1 mapping of physical memory — not - * to vmalloc or even module mappings. - */ -#define PASID_FLAG_SUPERVISOR_MODE BIT(0) #define PASID_FLAG_NESTED BIT(1) #define PASID_FLAG_PAGE_SNOOP BIT(2) -- GitLab From b31064f881eec6047874ef58df4376b20432859c Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:39 +0800 Subject: [PATCH 2844/5631] iommu/vt-d: Make size of operands same in bitwise operations This addresses the following issue reported by klocwork tool: - operands of different size in bitwise operations Suggested-by: Yongwei Ma Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-2-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 +- drivers/iommu/intel/iommu.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 6acfe879589c..01d0ca0019f2 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1689,7 +1689,7 @@ static void __dmar_enable_qi(struct intel_iommu *iommu) * is present. */ if (ecap_smts(iommu->ecap)) - val |= (1 << 11) | 1; + val |= BIT_ULL(11) | BIT_ULL(0); raw_spin_lock_irqsave(&iommu->register_lock, flags); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f4e536fd5a28..acbf82fa90e7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1870,7 +1870,7 @@ context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid) */ static inline void context_set_sm_dte(struct context_entry *context) { - context->lo |= (1 << 2); + context->lo |= BIT_ULL(2); } /* @@ -1879,7 +1879,7 @@ static inline void context_set_sm_dte(struct context_entry *context) */ static inline void context_set_sm_pre(struct context_entry *context) { - context->lo |= (1 << 4); + context->lo |= BIT_ULL(4); } /* Convert value to context PASID directory size field coding. */ -- GitLab From 35dc5d8998efa0f87a25bb184a9c54c46100fec3 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:40 +0800 Subject: [PATCH 2845/5631] iommu/vt-d: Remove BUG_ON on checking valid pfn range When encountering an unexpected invalid pfn range, the kernel should attempt recovery and proceed with execution. Therefore, using WARN_ON to replace BUG_ON to avoid halting the machine. Besides, one redundant checking is reduced. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-3-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index acbf82fa90e7..c4847a5aaf52 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1005,9 +1005,9 @@ static void dma_pte_clear_range(struct dmar_domain *domain, unsigned int large_page; struct dma_pte *first_pte, *pte; - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ do { @@ -1166,9 +1166,9 @@ static void dma_pte_clear_level(struct dmar_domain *domain, int level, static void domain_unmap(struct dmar_domain *domain, unsigned long start_pfn, unsigned long last_pfn, struct list_head *freelist) { - BUG_ON(!domain_pfn_supported(domain, start_pfn)); - BUG_ON(!domain_pfn_supported(domain, last_pfn)); - BUG_ON(start_pfn > last_pfn); + if (WARN_ON(!domain_pfn_supported(domain, last_pfn)) || + WARN_ON(start_pfn > last_pfn)) + return; /* we don't need lock here; nobody else touches the iova range */ dma_pte_clear_level(domain, agaw_to_level(domain->agaw), -- GitLab From 4a627a2593b457336047c6803b5d5c097183a9ca Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:41 +0800 Subject: [PATCH 2846/5631] iommu/vt-d: Remove BUG_ON in handling iotlb cache invalidation VT-d iotlb cache invalidation request with unexpected type is considered as a bug to developers, which can be fixed. So, when such kind of issue comes out, it needs to be reported through the kernel log, instead of halting the system. Replacing BUG_ON with warning reporting. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-4-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index c4847a5aaf52..dd61bb554aa7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1272,7 +1272,9 @@ static void __iommu_flush_context(struct intel_iommu *iommu, | DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask); break; default: - BUG(); + pr_warn("%s: Unexpected context-cache invalidation type 0x%llx\n", + iommu->name, type); + return; } val |= DMA_CCMD_ICC; @@ -1308,7 +1310,9 @@ static void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, val_iva = size_order | addr; break; default: - BUG(); + pr_warn("%s: Unexpected iotlb invalidation type 0x%llx\n", + iommu->name, type); + return; } /* Note: set drain read/write */ #if 0 @@ -1483,7 +1487,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu, uint64_t addr = (uint64_t)pfn << VTD_PAGE_SHIFT; u16 did = domain_id_iommu(domain, iommu); - BUG_ON(pages == 0); + if (WARN_ON(!pages)) + return; if (ih) ih = 1 << 6; -- GitLab From 998d4c2db30c7279ce6070faf06b914c98f2ae30 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:42 +0800 Subject: [PATCH 2847/5631] iommu/vt-d: Remove BUG_ON when domain->pgd is NULL When performing domain_context_mapping or getting dma_pte of a pfn, the availability of the domain page table directory is ensured. Therefore, the domain->pgd checkings are unnecessary. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-5-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index dd61bb554aa7..f11347a590d7 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -915,8 +915,6 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, int level = agaw_to_level(domain->agaw); int offset; - BUG_ON(!domain->pgd); - if (!domain_pfn_supported(domain, pfn)) /* Address beyond IOMMU's addressing capabilities. */ return NULL; @@ -1910,8 +1908,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, pr_debug("Set context mapping for %02x:%02x.%d\n", bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); - BUG_ON(!domain->pgd); - spin_lock(&iommu->lock); ret = -ENOMEM; context = iommu_context_addr(iommu, bus, devfn, 1); -- GitLab From cbf2f9e8badd483e2ee17a56ad8dbd1cfdcead20 Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:43 +0800 Subject: [PATCH 2848/5631] iommu/vt-d: Remove BUG_ON in map/unmap() Domain map/unmap with invalid parameters shouldn't crash the kernel. Therefore, using if() replaces the BUG_ON. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-6-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index f11347a590d7..ab21ef1ddb3c 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2159,7 +2159,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, phys_addr_t pteval; u64 attr; - BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1)); + if (unlikely(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1))) + return -EINVAL; if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0) return -EINVAL; @@ -4314,8 +4315,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, /* Cope with horrid API which requires us to unmap more than the size argument if it happens to be a large-page mapping. */ - BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level, - GFP_ATOMIC)); + if (unlikely(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, + &level, GFP_ATOMIC))) + return 0; if (size < VTD_PAGE_SIZE << level_to_offset_bits(level)) size = VTD_PAGE_SIZE << level_to_offset_bits(level); -- GitLab From ff45ab96465f013bee39ac88b756bb1129a7bc9d Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:44 +0800 Subject: [PATCH 2849/5631] iommu/vt-d: Remove a useless BUG_ON(dev->is_virtfn) When dmar_alloc_pci_notify_info() is being invoked, the invoker has ensured the dev->is_virtfn is false. So, remove the useless BUG_ON in dmar_alloc_pci_notify_info(). Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-7-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 01d0ca0019f2..9684c96247f8 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -127,8 +127,6 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) struct pci_dev *tmp; struct dmar_pci_notify_info *info; - BUG_ON(dev->is_virtfn); - /* * Ignore devices that have a domain number higher than what can * be looked up in DMAR, e.g. VMD subdevices with domain 0x10000 -- GitLab From e60d63e32d239c4c20b370106b57079d7f0994cf Mon Sep 17 00:00:00 2001 From: Tina Zhang Date: Thu, 13 Apr 2023 12:06:45 +0800 Subject: [PATCH 2850/5631] iommu/vt-d: Remove BUG_ON in dmar_insert_dev_scope() The dmar_insert_dev_scope() could fail if any unexpected condition is encountered. However, in this situation, the kernel should attempt recovery and proceed with execution. Remove BUG_ON with WARN_ON, so that kernel can avoid being crashed when an unexpected condition occurs. Signed-off-by: Tina Zhang Link: https://lore.kernel.org/r/20230406065944.2773296-8-tina.zhang@intel.com Signed-off-by: Lu Baolu Signed-off-by: Joerg Roedel --- drivers/iommu/intel/dmar.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 9684c96247f8..7eceee081235 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -262,7 +262,8 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info, get_device(dev)); return 1; } - BUG_ON(i >= devices_cnt); + if (WARN_ON(i >= devices_cnt)) + return -EINVAL; } return 0; -- GitLab From dc3d25f22b889a326abc8331075849ea11b4f2bb Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Mon, 30 Jan 2023 20:10:18 +0000 Subject: [PATCH 2851/5631] iio: imu: lsm6dsx: Add ACPI mount matrix retrieval DSDT ROTM method seen in the wild with SMO8B30 _HID. Making assumption it is similar to that used for bmc150 plus information from Darrell that the rotation is out by 90 degrees at boot. Method (ROTM, 0, NotSerialized) { Name (RBUF, Package (0x03) { "0 -1 0", "1 0 0", "0 0 1" }) Return (RBUF) /* \_SB_.PCI0.I2C5.DEV_.ROTM.RBUF */ } Reported-by: Darrell Kavanagh Signed-off-by: Jonathan Cameron Tested-by: Darrell Kavanagh Link: https://lore.kernel.org/r/20230130201018.981024-3-jic23@kernel.org Signed-off-by: Jonathan Cameron --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 77 +++++++++++++++++++- 1 file changed, 74 insertions(+), 3 deletions(-) diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 455e5edd3a80..6a18b363cf73 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -56,6 +56,7 @@ #include #include +#include #include #include #include @@ -2624,6 +2625,73 @@ static int st_lsm6dsx_init_regulators(struct device *dev) return 0; } +#ifdef CONFIG_ACPI + +static int lsm6dsx_get_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + struct acpi_device *adev = ACPI_COMPANION(dev); + union acpi_object *obj, *elements; + acpi_status status; + int i, j, val[3]; + char *str; + + if (!has_acpi_companion(dev)) + return -EINVAL; + + if (!acpi_has_method(adev->handle, "ROTM")) + return -EINVAL; + + status = acpi_evaluate_object(adev->handle, "ROTM", NULL, &buffer); + if (ACPI_FAILURE(status)) { + dev_warn(dev, "Failed to get ACPI mount matrix: %d\n", status); + return -EINVAL; + } + + obj = buffer.pointer; + if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count != 3) + goto unknown_format; + + elements = obj->package.elements; + for (i = 0; i < 3; i++) { + if (elements[i].type != ACPI_TYPE_STRING) + goto unknown_format; + + str = elements[i].string.pointer; + if (sscanf(str, "%d %d %d", &val[0], &val[1], &val[2]) != 3) + goto unknown_format; + + for (j = 0; j < 3; j++) { + switch (val[j]) { + case -1: str = "-1"; break; + case 0: str = "0"; break; + case 1: str = "1"; break; + default: goto unknown_format; + } + orientation->rotation[i * 3 + j] = str; + } + } + + kfree(buffer.pointer); + return 0; + +unknown_format: + dev_warn(dev, "Unknown ACPI mount matrix format, ignoring\n"); + kfree(buffer.pointer); + return -EINVAL; +} + +#else + +static int lsm6dsx_get_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation) +{ + return false; +} + +#endif + int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, struct regmap *regmap) { @@ -2698,9 +2766,12 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, return err; } - err = iio_read_mount_matrix(hw->dev, &hw->orientation); - if (err) - return err; + err = lsm6dsx_get_acpi_mount_matrix(hw->dev, &hw->orientation); + if (err) { + err = iio_read_mount_matrix(hw->dev, &hw->orientation); + if (err) + return err; + } for (i = 0; i < ST_LSM6DSX_ID_MAX; i++) { if (!hw->iio_devs[i]) -- GitLab From 6d52b0e706989d48e1aa3b5263f6185770ab4af3 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sat, 18 Mar 2023 16:30:39 +0000 Subject: [PATCH 2852/5631] iio: adc: palmas: Take probe fully device managed. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Review of a recent fix highlighted that this driver could be trivially converted to be entirely devm managed. That fix should be applied to resolve the fix in a fashion easy to back port even though this change removes the relevant code. [1] https://patchwork.kernel.org/project/linux-iio/patch/20230313205029.1881745-1-risca@dalakolonin.se/ Signed-off-by: Jonathan Cameron Tested-by: Patrik Dahlström Reviewed-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230318163039.56115-1-jic23@kernel.org --- drivers/iio/adc/palmas_gpadc.c | 110 +++++++++++++-------------------- 1 file changed, 42 insertions(+), 68 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 849a697a467e..2921186458e0 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -493,6 +493,11 @@ static int palmas_gpadc_get_adc_dt_data(struct platform_device *pdev, return 0; } +static void palmas_disable_wakeup(void *dev) +{ + device_wakeup_disable(dev); +} + static int palmas_gpadc_probe(struct platform_device *pdev) { struct palmas_gpadc *adc; @@ -532,36 +537,30 @@ static int palmas_gpadc_probe(struct platform_device *pdev) adc->auto_conversion_period = gpadc_pdata->auto_conversion_period_ms; adc->irq = palmas_irq_get_virq(adc->palmas, PALMAS_GPADC_EOC_SW_IRQ); - if (adc->irq < 0) { - dev_err(adc->dev, - "get virq failed: %d\n", adc->irq); - ret = adc->irq; - goto out; - } - ret = request_threaded_irq(adc->irq, NULL, - palmas_gpadc_irq, - IRQF_ONESHOT, dev_name(adc->dev), - adc); - if (ret < 0) { - dev_err(adc->dev, - "request irq %d failed: %d\n", adc->irq, ret); - goto out; - } + if (adc->irq < 0) + return dev_err_probe(adc->dev, adc->irq, "get virq failed\n"); + + ret = devm_request_threaded_irq(&pdev->dev, adc->irq, NULL, + palmas_gpadc_irq, + IRQF_ONESHOT, dev_name(adc->dev), + adc); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "request irq %d failed\n", adc->irq); if (gpadc_pdata->adc_wakeup1_data) { memcpy(&adc->wakeup1_data, gpadc_pdata->adc_wakeup1_data, sizeof(adc->wakeup1_data)); adc->wakeup1_enable = true; adc->irq_auto_0 = platform_get_irq(pdev, 1); - ret = request_threaded_irq(adc->irq_auto_0, NULL, - palmas_gpadc_irq_auto, - IRQF_ONESHOT, - "palmas-adc-auto-0", adc); - if (ret < 0) { - dev_err(adc->dev, "request auto0 irq %d failed: %d\n", - adc->irq_auto_0, ret); - goto out_irq_free; - } + ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_0, + NULL, palmas_gpadc_irq_auto, + IRQF_ONESHOT, + "palmas-adc-auto-0", adc); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "request auto0 irq %d failed\n", + adc->irq_auto_0); } if (gpadc_pdata->adc_wakeup2_data) { @@ -569,15 +568,14 @@ static int palmas_gpadc_probe(struct platform_device *pdev) sizeof(adc->wakeup2_data)); adc->wakeup2_enable = true; adc->irq_auto_1 = platform_get_irq(pdev, 2); - ret = request_threaded_irq(adc->irq_auto_1, NULL, - palmas_gpadc_irq_auto, - IRQF_ONESHOT, - "palmas-adc-auto-1", adc); - if (ret < 0) { - dev_err(adc->dev, "request auto1 irq %d failed: %d\n", - adc->irq_auto_1, ret); - goto out_irq_auto0_free; - } + ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_1, + NULL, palmas_gpadc_irq_auto, + IRQF_ONESHOT, + "palmas-adc-auto-1", adc); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "request auto1 irq %d failed\n", + adc->irq_auto_1); } /* set the current source 0 (value 0/5/15/20 uA => 0..3) */ @@ -608,11 +606,10 @@ static int palmas_gpadc_probe(struct platform_device *pdev) indio_dev->channels = palmas_gpadc_iio_channel; indio_dev->num_channels = ARRAY_SIZE(palmas_gpadc_iio_channel); - ret = iio_device_register(indio_dev); - if (ret < 0) { - dev_err(adc->dev, "iio_device_register() failed: %d\n", ret); - goto out_irq_auto1_free; - } + ret = devm_iio_device_register(&pdev->dev, indio_dev); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "iio_device_register() failed\n"); device_set_wakeup_capable(&pdev->dev, 1); for (i = 0; i < PALMAS_ADC_CH_MAX; i++) { @@ -620,36 +617,14 @@ static int palmas_gpadc_probe(struct platform_device *pdev) palmas_gpadc_calibrate(adc, i); } - if (adc->wakeup1_enable || adc->wakeup2_enable) + if (adc->wakeup1_enable || adc->wakeup2_enable) { device_wakeup_enable(&pdev->dev); - - return 0; - -out_irq_auto1_free: - if (gpadc_pdata->adc_wakeup2_data) - free_irq(adc->irq_auto_1, adc); -out_irq_auto0_free: - if (gpadc_pdata->adc_wakeup1_data) - free_irq(adc->irq_auto_0, adc); -out_irq_free: - free_irq(adc->irq, adc); -out: - return ret; -} - -static int palmas_gpadc_remove(struct platform_device *pdev) -{ - struct iio_dev *indio_dev = dev_get_drvdata(&pdev->dev); - struct palmas_gpadc *adc = iio_priv(indio_dev); - - if (adc->wakeup1_enable || adc->wakeup2_enable) - device_wakeup_disable(&pdev->dev); - iio_device_unregister(indio_dev); - free_irq(adc->irq, adc); - if (adc->wakeup1_enable) - free_irq(adc->irq_auto_0, adc); - if (adc->wakeup2_enable) - free_irq(adc->irq_auto_1, adc); + ret = devm_add_action_or_reset(&pdev->dev, + palmas_disable_wakeup, + &pdev->dev); + if (ret) + return ret; + } return 0; } @@ -834,7 +809,6 @@ MODULE_DEVICE_TABLE(of, of_palmas_gpadc_match_tbl); static struct platform_driver palmas_gpadc_driver = { .probe = palmas_gpadc_probe, - .remove = palmas_gpadc_remove, .driver = { .name = MOD_NAME, .pm = pm_sleep_ptr(&palmas_pm_ops), -- GitLab From 79d9622d622d49d6c14c51edec2059b8591e7975 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:19 +0200 Subject: [PATCH 2853/5631] iio: adc: palmas: remove adc_wakeupX_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It does not seem to be used by anyone and later patches in this series are made simpler by first removing this. There is now a lot of dead code that cannot be reached, until later patches revive it. Arguably, this is preferred over removing the code only to add it again. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-4-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 50 ++++------------------------------ include/linux/mfd/palmas.h | 8 ------ 2 files changed, 6 insertions(+), 52 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 2921186458e0..03af6cd73ec8 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -76,6 +76,12 @@ static struct palmas_gpadc_info palmas_gpadc_info[] = { PALMAS_ADC_INFO(IN15, 0, 0, 0, 0, INVALID, INVALID, true), }; +struct palmas_adc_wakeup_property { + int adc_channel_number; + int adc_high_threshold; + int adc_low_threshold; +}; + /* * struct palmas_gpadc - the palmas_gpadc structure * @ch0_current: channel 0 current source setting @@ -493,11 +499,6 @@ static int palmas_gpadc_get_adc_dt_data(struct platform_device *pdev, return 0; } -static void palmas_disable_wakeup(void *dev) -{ - device_wakeup_disable(dev); -} - static int palmas_gpadc_probe(struct platform_device *pdev) { struct palmas_gpadc *adc; @@ -548,36 +549,6 @@ static int palmas_gpadc_probe(struct platform_device *pdev) return dev_err_probe(adc->dev, ret, "request irq %d failed\n", adc->irq); - if (gpadc_pdata->adc_wakeup1_data) { - memcpy(&adc->wakeup1_data, gpadc_pdata->adc_wakeup1_data, - sizeof(adc->wakeup1_data)); - adc->wakeup1_enable = true; - adc->irq_auto_0 = platform_get_irq(pdev, 1); - ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_0, - NULL, palmas_gpadc_irq_auto, - IRQF_ONESHOT, - "palmas-adc-auto-0", adc); - if (ret < 0) - return dev_err_probe(adc->dev, ret, - "request auto0 irq %d failed\n", - adc->irq_auto_0); - } - - if (gpadc_pdata->adc_wakeup2_data) { - memcpy(&adc->wakeup2_data, gpadc_pdata->adc_wakeup2_data, - sizeof(adc->wakeup2_data)); - adc->wakeup2_enable = true; - adc->irq_auto_1 = platform_get_irq(pdev, 2); - ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_1, - NULL, palmas_gpadc_irq_auto, - IRQF_ONESHOT, - "palmas-adc-auto-1", adc); - if (ret < 0) - return dev_err_probe(adc->dev, ret, - "request auto1 irq %d failed\n", - adc->irq_auto_1); - } - /* set the current source 0 (value 0/5/15/20 uA => 0..3) */ if (gpadc_pdata->ch0_current <= 1) adc->ch0_current = PALMAS_ADC_CH0_CURRENT_SRC_0; @@ -617,15 +588,6 @@ static int palmas_gpadc_probe(struct platform_device *pdev) palmas_gpadc_calibrate(adc, i); } - if (adc->wakeup1_enable || adc->wakeup2_enable) { - device_wakeup_enable(&pdev->dev); - ret = devm_add_action_or_reset(&pdev->dev, - palmas_disable_wakeup, - &pdev->dev); - if (ret) - return ret; - } - return 0; } diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 117d02708439..eda1ffd99c1a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -128,12 +128,6 @@ struct palmas_pmic_driver_data { struct regulator_config config); }; -struct palmas_adc_wakeup_property { - int adc_channel_number; - int adc_high_threshold; - int adc_low_threshold; -}; - struct palmas_gpadc_platform_data { /* Channel 3 current source is only enabled during conversion */ int ch3_current; /* 0: off; 1: 10uA; 2: 400uA; 3: 800 uA */ @@ -152,8 +146,6 @@ struct palmas_gpadc_platform_data { int start_polarity; int auto_conversion_period_ms; - struct palmas_adc_wakeup_property *adc_wakeup1_data; - struct palmas_adc_wakeup_property *adc_wakeup2_data; }; struct palmas_reg_init { -- GitLab From d2ab4eea732dd2e235ba2a488344612a07a20334 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:20 +0200 Subject: [PATCH 2854/5631] iio: adc: palmas: replace "wakeup" with "event" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The palmas gpadc block has support for monitoring up to 2 ADC channels and issue an interrupt if they reach past a set threshold. This is currently used to wake up the system from sleep, but the functionality is more generic than that. As such, change the naming of functions and variables to refer to it as events instead, except during suspend and resume where wakeup still make sense. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-5-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 50 +++++++++++++++++----------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 03af6cd73ec8..55fdf59ef711 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -76,7 +76,7 @@ static struct palmas_gpadc_info palmas_gpadc_info[] = { PALMAS_ADC_INFO(IN15, 0, 0, 0, 0, INVALID, INVALID, true), }; -struct palmas_adc_wakeup_property { +struct palmas_adc_event { int adc_channel_number; int adc_high_threshold; int adc_low_threshold; @@ -117,10 +117,10 @@ struct palmas_gpadc { int irq_auto_1; struct palmas_gpadc_info *adc_info; struct completion conv_completion; - struct palmas_adc_wakeup_property wakeup1_data; - struct palmas_adc_wakeup_property wakeup2_data; - bool wakeup1_enable; - bool wakeup2_enable; + struct palmas_adc_event event0; + struct palmas_adc_event event1; + bool event0_enable; + bool event1_enable; int auto_conversion_period; struct mutex lock; }; @@ -591,7 +591,7 @@ static int palmas_gpadc_probe(struct platform_device *pdev) return 0; } -static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) +static int palmas_adc_configure_events(struct palmas_gpadc *adc) { int adc_period, conv; int i; @@ -617,16 +617,16 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) } conv = 0; - if (adc->wakeup1_enable) { + if (adc->event0_enable) { int polarity; - ch0 = adc->wakeup1_data.adc_channel_number; + ch0 = adc->event0.adc_channel_number; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV0_EN; - if (adc->wakeup1_data.adc_high_threshold > 0) { - thres = adc->wakeup1_data.adc_high_threshold; + if (adc->event0.adc_high_threshold > 0) { + thres = adc->event0.adc_high_threshold; polarity = 0; } else { - thres = adc->wakeup1_data.adc_low_threshold; + thres = adc->event0.adc_low_threshold; polarity = PALMAS_GPADC_THRES_CONV0_MSB_THRES_CONV0_POL; } @@ -648,16 +648,16 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) } } - if (adc->wakeup2_enable) { + if (adc->event1_enable) { int polarity; - ch1 = adc->wakeup2_data.adc_channel_number; + ch1 = adc->event1.adc_channel_number; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV1_EN; - if (adc->wakeup2_data.adc_high_threshold > 0) { - thres = adc->wakeup2_data.adc_high_threshold; + if (adc->event1.adc_high_threshold > 0) { + thres = adc->event1.adc_high_threshold; polarity = 0; } else { - thres = adc->wakeup2_data.adc_low_threshold; + thres = adc->event1.adc_low_threshold; polarity = PALMAS_GPADC_THRES_CONV1_MSB_THRES_CONV1_POL; } @@ -696,7 +696,7 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) return ret; } -static int palmas_adc_wakeup_reset(struct palmas_gpadc *adc) +static int palmas_adc_reset_events(struct palmas_gpadc *adc) { int ret; @@ -718,20 +718,20 @@ static int palmas_gpadc_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->wakeup1_enable || adc->wakeup2_enable; + int wakeup = adc->event0_enable || adc->event1_enable; int ret; if (!device_may_wakeup(dev) || !wakeup) return 0; - ret = palmas_adc_wakeup_configure(adc); + ret = palmas_adc_configure_events(adc); if (ret < 0) return ret; - if (adc->wakeup1_enable) + if (adc->event0_enable) enable_irq_wake(adc->irq_auto_0); - if (adc->wakeup2_enable) + if (adc->event1_enable) enable_irq_wake(adc->irq_auto_1); return 0; @@ -741,20 +741,20 @@ static int palmas_gpadc_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->wakeup1_enable || adc->wakeup2_enable; + int wakeup = adc->event0_enable || adc->event1_enable; int ret; if (!device_may_wakeup(dev) || !wakeup) return 0; - ret = palmas_adc_wakeup_reset(adc); + ret = palmas_adc_reset_events(adc); if (ret < 0) return ret; - if (adc->wakeup1_enable) + if (adc->event0_enable) disable_irq_wake(adc->irq_auto_0); - if (adc->wakeup2_enable) + if (adc->event1_enable) disable_irq_wake(adc->irq_auto_1); return 0; -- GitLab From 7501a3a97e4f000c1881f228132ead7a2fa5725c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:21 +0200 Subject: [PATCH 2855/5631] iio: adc: palmas: use iio_event_direction for threshold polarity MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of having high_threshold > 0 as an indicator for upper threshold event and lower threshold event otherwise, use enum iio_event_direction instead. This is hopefully less ambiguous. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-6-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 36 ++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 13 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 55fdf59ef711..205a7628b235 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -77,9 +77,9 @@ static struct palmas_gpadc_info palmas_gpadc_info[] = { }; struct palmas_adc_event { - int adc_channel_number; - int adc_high_threshold; - int adc_low_threshold; + int channel; + int raw_thresh; + enum iio_event_direction direction; }; /* @@ -618,16 +618,21 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) conv = 0; if (adc->event0_enable) { + struct palmas_adc_event *ev = &adc->event0; int polarity; - ch0 = adc->event0.adc_channel_number; + ch0 = ev->channel; + thres = ev->raw_thresh; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV0_EN; - if (adc->event0.adc_high_threshold > 0) { - thres = adc->event0.adc_high_threshold; + switch (ev->direction) { + case IIO_EV_DIR_RISING: polarity = 0; - } else { - thres = adc->event0.adc_low_threshold; + break; + case IIO_EV_DIR_FALLING: polarity = PALMAS_GPADC_THRES_CONV0_MSB_THRES_CONV0_POL; + break; + default: + return -EINVAL; } ret = palmas_write(adc->palmas, PALMAS_GPADC_BASE, @@ -649,16 +654,21 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) } if (adc->event1_enable) { + struct palmas_adc_event *ev = &adc->event1; int polarity; - ch1 = adc->event1.adc_channel_number; + ch1 = ev->channel; + thres = ev->raw_thresh; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV1_EN; - if (adc->event1.adc_high_threshold > 0) { - thres = adc->event1.adc_high_threshold; + switch (ev->direction) { + case IIO_EV_DIR_RISING: polarity = 0; - } else { - thres = adc->event1.adc_low_threshold; + break; + case IIO_EV_DIR_FALLING: polarity = PALMAS_GPADC_THRES_CONV1_MSB_THRES_CONV1_POL; + break; + default: + return -EINVAL; } ret = palmas_write(adc->palmas, PALMAS_GPADC_BASE, -- GitLab From 2d48dbdfc7d4714973de48e601d69854b21b69de Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:22 +0200 Subject: [PATCH 2856/5631] iio: adc: palmas: move eventX_enable into palmas_adc_event MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It just makes more sense to have all information regarding adc events in one place. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-7-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 205a7628b235..8c6ea4a3cd2e 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -77,6 +77,7 @@ static struct palmas_gpadc_info palmas_gpadc_info[] = { }; struct palmas_adc_event { + bool enabled; int channel; int raw_thresh; enum iio_event_direction direction; @@ -119,8 +120,6 @@ struct palmas_gpadc { struct completion conv_completion; struct palmas_adc_event event0; struct palmas_adc_event event1; - bool event0_enable; - bool event1_enable; int auto_conversion_period; struct mutex lock; }; @@ -617,7 +616,7 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) } conv = 0; - if (adc->event0_enable) { + if (adc->event0.enabled) { struct palmas_adc_event *ev = &adc->event0; int polarity; @@ -653,7 +652,7 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) } } - if (adc->event1_enable) { + if (adc->event1.enabled) { struct palmas_adc_event *ev = &adc->event1; int polarity; @@ -728,7 +727,7 @@ static int palmas_gpadc_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->event0_enable || adc->event1_enable; + int wakeup = adc->event0.enabled || adc->event1.enabled; int ret; if (!device_may_wakeup(dev) || !wakeup) @@ -738,10 +737,10 @@ static int palmas_gpadc_suspend(struct device *dev) if (ret < 0) return ret; - if (adc->event0_enable) + if (adc->event0.enabled) enable_irq_wake(adc->irq_auto_0); - if (adc->event1_enable) + if (adc->event1.enabled) enable_irq_wake(adc->irq_auto_1); return 0; @@ -751,7 +750,7 @@ static int palmas_gpadc_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->event0_enable || adc->event1_enable; + int wakeup = adc->event0.enabled || adc->event1.enabled; int ret; if (!device_may_wakeup(dev) || !wakeup) @@ -761,10 +760,10 @@ static int palmas_gpadc_resume(struct device *dev) if (ret < 0) return ret; - if (adc->event0_enable) + if (adc->event0.enabled) disable_irq_wake(adc->irq_auto_0); - if (adc->event1_enable) + if (adc->event1.enabled) disable_irq_wake(adc->irq_auto_1); return 0; -- GitLab From 773597aeee455d646bff12ce68a68884bc2d9113 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:23 +0200 Subject: [PATCH 2857/5631] iio: adc: palmas: always reset events on unload MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This prevents leaving the adc in freerunning mode when removing the driver. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-8-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 8c6ea4a3cd2e..da4908608a27 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -498,6 +498,13 @@ static int palmas_gpadc_get_adc_dt_data(struct platform_device *pdev, return 0; } +static void palmas_gpadc_reset(void *data) +{ + struct palmas_gpadc *adc = data; + if (adc->event0.enabled || adc->event1.enabled) + palmas_adc_reset_events(adc); +} + static int palmas_gpadc_probe(struct platform_device *pdev) { struct palmas_gpadc *adc; @@ -587,6 +594,10 @@ static int palmas_gpadc_probe(struct platform_device *pdev) palmas_gpadc_calibrate(adc, i); } + ret = devm_add_action(&pdev->dev, palmas_gpadc_reset, adc); + if (ret) + return ret; + return 0; } -- GitLab From a99544c6c883f5fdd1b326b245572ca22cabc421 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:24 +0200 Subject: [PATCH 2858/5631] iio: adc: palmas: add support for iio threshold events MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The palmas gpadc block has support for monitoring up to 2 ADC channels and issue an interrupt if they reach past a set threshold. This change hooks into the IIO events system and exposes to userspace the ability to configure these threshold values for each channel, but only allow up to 2 such thresholds to be enabled at any given time. Trying to enable a third channel will result in an error. Userspace is expected to input calibrated, as opposed to raw, values as threshold. However, it is not enough to do the opposite of what is done when converting the other way around. To account for tolerances in the ADC, the calculated raw threshold should be adjusted based on the ADC specifications for the device. These specifications include the integral nonlinearity (INL), offset, and gain error. To adjust the high threshold, use the following equation: (calibrated value + INL) * Gain error + offset = maximum value [1] Likewise, use the following equation for the low threshold: (calibrated value - INL) * Gain error - offset = minimum value The gain error is a combination of gain error, as listed in the datasheet, and gain error drift due to temperature and supply. The exact values for these specifications vary between palmas devices. This patch sets the values found in TWL6035, TWL6037 datasheet. [1] TI Application Report, SLIA087A, Guide to Using the GPADC in TPS65903x, TPS65917-Q1, TPS65919-Q1, and TPS65916 Devices. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-9-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 443 +++++++++++++++++++++++++++++++-- 1 file changed, 419 insertions(+), 24 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index da4908608a27..071795c8de1d 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -79,10 +80,14 @@ static struct palmas_gpadc_info palmas_gpadc_info[] = { struct palmas_adc_event { bool enabled; int channel; - int raw_thresh; enum iio_event_direction direction; }; +struct palmas_gpadc_thresholds { + int high; + int low; +}; + /* * struct palmas_gpadc - the palmas_gpadc structure * @ch0_current: channel 0 current source setting @@ -120,10 +125,31 @@ struct palmas_gpadc { struct completion conv_completion; struct palmas_adc_event event0; struct palmas_adc_event event1; + struct palmas_gpadc_thresholds thresholds[PALMAS_ADC_CH_MAX]; int auto_conversion_period; struct mutex lock; }; +static struct palmas_adc_event *palmas_gpadc_get_event(struct palmas_gpadc *adc, + int adc_chan, + enum iio_event_direction dir) +{ + if (adc_chan == adc->event0.channel && dir == adc->event0.direction) + return &adc->event0; + + if (adc_chan == adc->event1.channel && dir == adc->event1.direction) + return &adc->event1; + + return NULL; +} + +static bool palmas_gpadc_channel_is_freerunning(struct palmas_gpadc *adc, + int adc_chan) +{ + return palmas_gpadc_get_event(adc, adc_chan, IIO_EV_DIR_RISING) || + palmas_gpadc_get_event(adc, adc_chan, IIO_EV_DIR_FALLING); +} + /* * GPADC lock issue in AUTO mode. * Impact: In AUTO mode, GPADC conversion can be locked after disabling AUTO @@ -193,11 +219,24 @@ static irqreturn_t palmas_gpadc_irq(int irq, void *data) static irqreturn_t palmas_gpadc_irq_auto(int irq, void *data) { - struct palmas_gpadc *adc = data; + struct iio_dev *indio_dev = data; + struct palmas_gpadc *adc = iio_priv(indio_dev); + struct palmas_adc_event *ev; dev_dbg(adc->dev, "Threshold interrupt %d occurs\n", irq); palmas_disable_auto_conversion(adc); + ev = (irq == adc->irq_auto_0) ? &adc->event0 : &adc->event1; + if (ev->channel != -1) { + enum iio_event_direction dir; + u64 code; + + dir = ev->direction; + code = IIO_UNMOD_EVENT_CODE(IIO_VOLTAGE, ev->channel, + IIO_EV_TYPE_THRESH, dir); + iio_push_event(indio_dev, code, iio_get_time_ns(indio_dev)); + } + return IRQ_HANDLED; } @@ -285,6 +324,9 @@ static int palmas_gpadc_read_prepare(struct palmas_gpadc *adc, int adc_chan) { int ret; + if (palmas_gpadc_channel_is_freerunning(adc, adc_chan)) + return 0; /* ADC already running */ + ret = palmas_gpadc_enable(adc, adc_chan, true); if (ret < 0) return ret; @@ -344,28 +386,43 @@ static int palmas_gpadc_start_conversion(struct palmas_gpadc *adc, int adc_chan) unsigned int val; int ret; - init_completion(&adc->conv_completion); - ret = palmas_update_bits(adc->palmas, PALMAS_GPADC_BASE, - PALMAS_GPADC_SW_SELECT, - PALMAS_GPADC_SW_SELECT_SW_START_CONV0, - PALMAS_GPADC_SW_SELECT_SW_START_CONV0); - if (ret < 0) { - dev_err(adc->dev, "SELECT_SW_START write failed: %d\n", ret); - return ret; - } + if (palmas_gpadc_channel_is_freerunning(adc, adc_chan)) { + int event = (adc_chan == adc->event0.channel) ? 0 : 1; + unsigned int reg = (event == 0) ? + PALMAS_GPADC_AUTO_CONV0_LSB : + PALMAS_GPADC_AUTO_CONV1_LSB; - ret = wait_for_completion_timeout(&adc->conv_completion, - PALMAS_ADC_CONVERSION_TIMEOUT); - if (ret == 0) { - dev_err(adc->dev, "conversion not completed\n"); - return -ETIMEDOUT; - } + ret = palmas_bulk_read(adc->palmas, PALMAS_GPADC_BASE, + reg, &val, 2); + if (ret < 0) { + dev_err(adc->dev, "AUTO_CONV%x_LSB read failed: %d\n", + event, ret); + return ret; + } + } else { + init_completion(&adc->conv_completion); + ret = palmas_update_bits(adc->palmas, PALMAS_GPADC_BASE, + PALMAS_GPADC_SW_SELECT, + PALMAS_GPADC_SW_SELECT_SW_START_CONV0, + PALMAS_GPADC_SW_SELECT_SW_START_CONV0); + if (ret < 0) { + dev_err(adc->dev, "SELECT_SW_START write failed: %d\n", ret); + return ret; + } - ret = palmas_bulk_read(adc->palmas, PALMAS_GPADC_BASE, - PALMAS_GPADC_SW_CONV0_LSB, &val, 2); - if (ret < 0) { - dev_err(adc->dev, "SW_CONV0_LSB read failed: %d\n", ret); - return ret; + ret = wait_for_completion_timeout(&adc->conv_completion, + PALMAS_ADC_CONVERSION_TIMEOUT); + if (ret == 0) { + dev_err(adc->dev, "conversion not completed\n"); + return -ETIMEDOUT; + } + + ret = palmas_bulk_read(adc->palmas, PALMAS_GPADC_BASE, + PALMAS_GPADC_SW_CONV0_LSB, &val, 2); + if (ret < 0) { + dev_err(adc->dev, "SW_CONV0_LSB read failed: %d\n", ret); + return ret; + } } ret = val & 0xFFF; @@ -391,6 +448,98 @@ static int palmas_gpadc_get_calibrated_code(struct palmas_gpadc *adc, return val; } +/* + * The high and low threshold values are calculated based on the advice given + * in TI Application Report SLIA087A, "Guide to Using the GPADC in PS65903x, + * TPS65917-Q1, TPS65919-Q1, and TPS65916 Devices". This document recommend + * taking ADC tolerances into account and is based on the device integral non- + * linearity (INL), offset error and gain error: + * + * raw high threshold = (ideal threshold + INL) * gain error + offset error + * + * The gain error include both gain error, as specified in the datasheet, and + * the gain error drift. These paramenters vary depending on device and whether + * the the channel is calibrated (trimmed) or not. + */ +static int palmas_gpadc_threshold_with_tolerance(int val, const int INL, + const int gain_error, + const int offset_error) +{ + val = ((val + INL) * (1000 + gain_error)) / 1000 + offset_error; + + return clamp(val, 0, 0xFFF); +} + +/* + * The values below are taken from the datasheet of TWL6035, TWL6037. + * todo: get max INL, gain error, and offset error from OF. + */ +static int palmas_gpadc_get_high_threshold_raw(struct palmas_gpadc *adc, + struct palmas_adc_event *ev) +{ + const int adc_chan = ev->channel; + int val = adc->thresholds[adc_chan].high; + /* integral nonlinearity, measured in LSB */ + const int max_INL = 2; + /* measured in LSB */ + int max_offset_error; + /* 0.2% when calibrated */ + int max_gain_error = 2; + + val = (val * 1000) / adc->adc_info[adc_chan].gain; + + if (adc->adc_info[adc_chan].is_uncalibrated) { + /* 2% worse */ + max_gain_error += 20; + max_offset_error = 36; + } else { + val = (val * adc->adc_info[adc_chan].gain_error + + adc->adc_info[adc_chan].offset) / + 1000; + max_offset_error = 2; + } + + return palmas_gpadc_threshold_with_tolerance(val, + max_INL, + max_gain_error, + max_offset_error); +} + +/* + * The values below are taken from the datasheet of TWL6035, TWL6037. + * todo: get min INL, gain error, and offset error from OF. + */ +static int palmas_gpadc_get_low_threshold_raw(struct palmas_gpadc *adc, + struct palmas_adc_event *ev) +{ + const int adc_chan = ev->channel; + int val = adc->thresholds[adc_chan].low; + /* integral nonlinearity, measured in LSB */ + const int min_INL = -2; + /* measured in LSB */ + int min_offset_error; + /* -0.6% when calibrated */ + int min_gain_error = -6; + + val = (val * 1000) / adc->adc_info[adc_chan].gain; + + if (adc->adc_info[adc_chan].is_uncalibrated) { + /* 2% worse */ + min_gain_error -= 20; + min_offset_error = -36; + } else { + val = (val * adc->adc_info[adc_chan].gain_error - + adc->adc_info[adc_chan].offset) / + 1000; + min_offset_error = -2; + } + + return palmas_gpadc_threshold_with_tolerance(val, + min_INL, + min_gain_error, + min_offset_error); +} + static int palmas_gpadc_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long mask) { @@ -437,8 +586,217 @@ static int palmas_gpadc_read_raw(struct iio_dev *indio_dev, return ret; } +static int palmas_gpadc_read_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir) +{ + struct palmas_gpadc *adc = iio_priv(indio_dev); + int adc_chan = chan->channel; + int ret = 0; + + if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + mutex_lock(&adc->lock); + + if (palmas_gpadc_get_event(adc, adc_chan, dir)) + ret = 1; + + mutex_unlock(&adc->lock); + + return ret; +} + +static int palmas_adc_configure_events(struct palmas_gpadc *adc); +static int palmas_adc_reset_events(struct palmas_gpadc *adc); + +static int palmas_gpadc_reconfigure_event_channels(struct palmas_gpadc *adc) +{ + return (adc->event0.enabled || adc->event1.enabled) ? + palmas_adc_configure_events(adc) : + palmas_adc_reset_events(adc); +} + +static int palmas_gpadc_enable_event_config(struct palmas_gpadc *adc, + const struct iio_chan_spec *chan, + enum iio_event_direction dir) +{ + struct palmas_adc_event *ev; + int adc_chan = chan->channel; + + if (palmas_gpadc_get_event(adc, adc_chan, dir)) + /* already enabled */ + return 0; + + if (adc->event0.channel == -1) { + ev = &adc->event0; + } else if (adc->event1.channel == -1) { + /* event0 has to be the lowest channel */ + if (adc_chan < adc->event0.channel) { + adc->event1 = adc->event0; + ev = &adc->event0; + } else { + ev = &adc->event1; + } + } else { /* both AUTO channels already in use */ + dev_warn(adc->dev, "event0 - %d, event1 - %d\n", + adc->event0.channel, adc->event1.channel); + return -EBUSY; + } + + ev->enabled = true; + ev->channel = adc_chan; + ev->direction = dir; + + return palmas_gpadc_reconfigure_event_channels(adc); +} + +static int palmas_gpadc_disable_event_config(struct palmas_gpadc *adc, + const struct iio_chan_spec *chan, + enum iio_event_direction dir) +{ + int adc_chan = chan->channel; + struct palmas_adc_event *ev = palmas_gpadc_get_event(adc, adc_chan, dir); + + if (!ev) + return 0; + + if (ev == &adc->event0) { + adc->event0 = adc->event1; + ev = &adc->event1; + } + + ev->enabled = false; + ev->channel = -1; + ev->direction = IIO_EV_DIR_NONE; + + return palmas_gpadc_reconfigure_event_channels(adc); +} + +static int palmas_gpadc_write_event_config(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + int state) +{ + struct palmas_gpadc *adc = iio_priv(indio_dev); + int adc_chan = chan->channel; + int ret; + + if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + mutex_lock(&adc->lock); + + if (state) + ret = palmas_gpadc_enable_event_config(adc, chan, dir); + else + ret = palmas_gpadc_disable_event_config(adc, chan, dir); + + mutex_unlock(&adc->lock); + + return ret; +} + +static int palmas_gpadc_read_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, + int *val, int *val2) +{ + struct palmas_gpadc *adc = iio_priv(indio_dev); + int adc_chan = chan->channel; + int ret; + + if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + mutex_lock(&adc->lock); + + switch (info) { + case IIO_EV_INFO_VALUE: + *val = (dir == IIO_EV_DIR_RISING) ? + adc->thresholds[adc_chan].high : + adc->thresholds[adc_chan].low; + ret = IIO_VAL_INT; + break; + default: + ret = -EINVAL; + break; + } + + mutex_unlock(&adc->lock); + + return ret; +} + +static int palmas_gpadc_write_event_value(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, + enum iio_event_type type, + enum iio_event_direction dir, + enum iio_event_info info, + int val, int val2) +{ + struct palmas_gpadc *adc = iio_priv(indio_dev); + int adc_chan = chan->channel; + int old; + int ret; + + if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + return -EINVAL; + + mutex_lock(&adc->lock); + switch (info) { + case IIO_EV_INFO_VALUE: + if (val < 0 || val > 0xFFF) { + ret = -EINVAL; + goto out_unlock; + } + if (dir == IIO_EV_DIR_RISING) { + old = adc->thresholds[adc_chan].high; + adc->thresholds[adc_chan].high = val; + } else { + old = adc->thresholds[adc_chan].low; + adc->thresholds[adc_chan].low = val; + } + ret = 0; + break; + default: + ret = -EINVAL; + goto out_unlock; + } + + if (val != old && palmas_gpadc_get_event(adc, adc_chan, dir)) + ret = palmas_gpadc_reconfigure_event_channels(adc); + +out_unlock: + mutex_unlock(&adc->lock); + + return ret; +} + static const struct iio_info palmas_gpadc_iio_info = { .read_raw = palmas_gpadc_read_raw, + .read_event_config = palmas_gpadc_read_event_config, + .write_event_config = palmas_gpadc_write_event_config, + .read_event_value = palmas_gpadc_read_event_value, + .write_event_value = palmas_gpadc_write_event_value, +}; + +static const struct iio_event_spec palmas_gpadc_events[] = { + { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_RISING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, { + .type = IIO_EV_TYPE_THRESH, + .dir = IIO_EV_DIR_FALLING, + .mask_separate = BIT(IIO_EV_INFO_VALUE) | + BIT(IIO_EV_INFO_ENABLE), + }, }; #define PALMAS_ADC_CHAN_IIO(chan, _type, chan_info) \ @@ -449,6 +807,8 @@ static const struct iio_info palmas_gpadc_iio_info = { BIT(chan_info), \ .indexed = 1, \ .channel = PALMAS_ADC_CH_##chan, \ + .event_spec = palmas_gpadc_events, \ + .num_event_specs = ARRAY_SIZE(palmas_gpadc_events) \ } static const struct iio_chan_spec palmas_gpadc_iio_channel[] = { @@ -555,6 +915,39 @@ static int palmas_gpadc_probe(struct platform_device *pdev) return dev_err_probe(adc->dev, ret, "request irq %d failed\n", adc->irq); + adc->irq_auto_0 = platform_get_irq(pdev, 1); + if (adc->irq_auto_0 < 0) + return dev_err_probe(adc->dev, adc->irq_auto_0, + "get auto0 irq failed\n"); + + ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_0, NULL, + palmas_gpadc_irq_auto, IRQF_ONESHOT, + "palmas-adc-auto-0", indio_dev); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "request auto0 irq %d failed\n", + adc->irq_auto_0); + + adc->irq_auto_1 = platform_get_irq(pdev, 2); + if (adc->irq_auto_1 < 0) + return dev_err_probe(adc->dev, adc->irq_auto_1, + "get auto1 irq failed\n"); + + ret = devm_request_threaded_irq(&pdev->dev, adc->irq_auto_1, NULL, + palmas_gpadc_irq_auto, IRQF_ONESHOT, + "palmas-adc-auto-1", indio_dev); + if (ret < 0) + return dev_err_probe(adc->dev, ret, + "request auto1 irq %d failed\n", + adc->irq_auto_1); + + adc->event0.enabled = false; + adc->event0.channel = -1; + adc->event0.direction = IIO_EV_DIR_NONE; + adc->event1.enabled = false; + adc->event1.channel = -1; + adc->event1.direction = IIO_EV_DIR_NONE; + /* set the current source 0 (value 0/5/15/20 uA => 0..3) */ if (gpadc_pdata->ch0_current <= 1) adc->ch0_current = PALMAS_ADC_CH0_CURRENT_SRC_0; @@ -632,13 +1025,14 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) int polarity; ch0 = ev->channel; - thres = ev->raw_thresh; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV0_EN; switch (ev->direction) { case IIO_EV_DIR_RISING: + thres = palmas_gpadc_get_high_threshold_raw(adc, ev); polarity = 0; break; case IIO_EV_DIR_FALLING: + thres = palmas_gpadc_get_low_threshold_raw(adc, ev); polarity = PALMAS_GPADC_THRES_CONV0_MSB_THRES_CONV0_POL; break; default: @@ -668,13 +1062,14 @@ static int palmas_adc_configure_events(struct palmas_gpadc *adc) int polarity; ch1 = ev->channel; - thres = ev->raw_thresh; conv |= PALMAS_GPADC_AUTO_CTRL_AUTO_CONV1_EN; switch (ev->direction) { case IIO_EV_DIR_RISING: + thres = palmas_gpadc_get_high_threshold_raw(adc, ev); polarity = 0; break; case IIO_EV_DIR_FALLING: + thres = palmas_gpadc_get_low_threshold_raw(adc, ev); polarity = PALMAS_GPADC_THRES_CONV1_MSB_THRES_CONV1_POL; break; default: -- GitLab From 52cc189b4fc6af6accc45fe7b7053d76d8724059 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Patrik=20Dahlstr=C3=B6m?= Date: Sat, 8 Apr 2023 13:48:25 +0200 Subject: [PATCH 2859/5631] iio: adc: palmas: don't alter event config on suspend/resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The event config is controlled through the IIO events subsystem and device wakeup is controlled by /sys/devices/.../power/wakeup. Let's keep those two knobs independent. Signed-off-by: Patrik Dahlström Link: https://lore.kernel.org/r/20230408114825.824505-10-risca@dalakolonin.se Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 071795c8de1d..c1c439215aeb 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -1133,16 +1133,10 @@ static int palmas_gpadc_suspend(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->event0.enabled || adc->event1.enabled; - int ret; - if (!device_may_wakeup(dev) || !wakeup) + if (!device_may_wakeup(dev)) return 0; - ret = palmas_adc_configure_events(adc); - if (ret < 0) - return ret; - if (adc->event0.enabled) enable_irq_wake(adc->irq_auto_0); @@ -1156,16 +1150,10 @@ static int palmas_gpadc_resume(struct device *dev) { struct iio_dev *indio_dev = dev_get_drvdata(dev); struct palmas_gpadc *adc = iio_priv(indio_dev); - int wakeup = adc->event0.enabled || adc->event1.enabled; - int ret; - if (!device_may_wakeup(dev) || !wakeup) + if (!device_may_wakeup(dev)) return 0; - ret = palmas_adc_reset_events(adc); - if (ret < 0) - return ret; - if (adc->event0.enabled) disable_irq_wake(adc->irq_auto_0); -- GitLab From 0af4d704ba8e5ee632b6e65015ffe4d229c1a9a9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 12 Apr 2023 13:56:36 +0200 Subject: [PATCH 2860/5631] pwm: Delete deprecated functions pwm_request() and pwm_free() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 5a7fbe452ad9 ("backlight: pwm_bl: Drop support for legacy PWM probing") the last user of pwm_request() and pwm_free() is gone. So remove these functions that were deprecated over 10 years ago in commit 8138d2ddbcca ("pwm: Add table-based lookup for static mappings"). Signed-off-by: Uwe Kleine-König [thierry.reding@gmail.com: clean up a bit after removal] Signed-off-by: Thierry Reding --- Documentation/driver-api/pwm.rst | 13 +++---- drivers/pwm/core.c | 58 ++------------------------------ include/linux/pwm.h | 13 ------- 3 files changed, 7 insertions(+), 77 deletions(-) diff --git a/Documentation/driver-api/pwm.rst b/Documentation/driver-api/pwm.rst index 8c71a2055d27..3fdc95f7a1d1 100644 --- a/Documentation/driver-api/pwm.rst +++ b/Documentation/driver-api/pwm.rst @@ -35,12 +35,9 @@ consumers to providers, as given in the following example:: Using PWMs ---------- -Legacy users can request a PWM device using pwm_request() and free it -after usage with pwm_free(). - -New users should use the pwm_get() function and pass to it the consumer -device or a consumer name. pwm_put() is used to free the PWM device. Managed -variants of the getter, devm_pwm_get() and devm_fwnode_pwm_get(), also exist. +Consumers use the pwm_get() function and pass to it the consumer device or a +consumer name. pwm_put() is used to free the PWM device. Managed variants of +the getter, devm_pwm_get() and devm_fwnode_pwm_get(), also exist. After being requested, a PWM has to be configured using:: @@ -165,8 +162,8 @@ consumers should implement it as described in the "Using PWMs" section. Locking ------- -The PWM core list manipulations are protected by a mutex, so pwm_request() -and pwm_free() may not be called from an atomic context. Currently the +The PWM core list manipulations are protected by a mutex, so pwm_get() +and pwm_put() may not be called from an atomic context. Currently the PWM core does not enforce any locking to pwm_enable(), pwm_disable() and pwm_config(), so the calling context is currently driver specific. This is an issue derived from the former barebone API and should be fixed soon. diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 474725714a05..9ce85c6157e4 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -35,11 +35,6 @@ static LIST_HEAD(pwm_chips); static DECLARE_BITMAP(allocated_pwms, MAX_PWMS); static RADIX_TREE(pwm_tree, GFP_KERNEL); -static struct pwm_device *pwm_to_device(unsigned int pwm) -{ - return radix_tree_lookup(&pwm_tree, pwm); -} - /* Called with pwm_lock held */ static int alloc_pwms(unsigned int count) { @@ -369,43 +364,6 @@ int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip) } EXPORT_SYMBOL_GPL(devm_pwmchip_add); -/** - * pwm_request() - request a PWM device - * @pwm: global PWM device index - * @label: PWM device label - * - * This function is deprecated, use pwm_get() instead. - * - * Returns: A pointer to a PWM device or an ERR_PTR()-encoded error code on - * failure. - */ -struct pwm_device *pwm_request(int pwm, const char *label) -{ - struct pwm_device *dev; - int err; - - if (pwm < 0 || pwm >= MAX_PWMS) - return ERR_PTR(-EINVAL); - - mutex_lock(&pwm_lock); - - dev = pwm_to_device(pwm); - if (!dev) { - dev = ERR_PTR(-EPROBE_DEFER); - goto out; - } - - err = pwm_device_request(dev, label); - if (err < 0) - dev = ERR_PTR(err); - -out: - mutex_unlock(&pwm_lock); - - return dev; -} -EXPORT_SYMBOL_GPL(pwm_request); - /** * pwm_request_from_chip() - request a PWM device relative to a PWM chip * @chip: PWM chip @@ -438,18 +396,6 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, } EXPORT_SYMBOL_GPL(pwm_request_from_chip); -/** - * pwm_free() - free a PWM device - * @pwm: PWM device - * - * This function is deprecated, use pwm_put() instead. - */ -void pwm_free(struct pwm_device *pwm) -{ - pwm_put(pwm); -} -EXPORT_SYMBOL_GPL(pwm_free); - static void pwm_apply_state_debug(struct pwm_device *pwm, const struct pwm_state *state) { @@ -790,7 +736,7 @@ static struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, dl = pwm_device_link_add(dev, pwm); if (IS_ERR(dl)) { /* of_xlate ended up calling pwm_request_from_chip() */ - pwm_free(pwm); + pwm_put(pwm); pwm = ERR_CAST(dl); goto put; } @@ -1014,7 +960,7 @@ struct pwm_device *pwm_get(struct device *dev, const char *con_id) dl = pwm_device_link_add(dev, pwm); if (IS_ERR(dl)) { - pwm_free(pwm); + pwm_put(pwm); return ERR_CAST(dl); } diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 7b7b93b6fb81..04ae1d9073a7 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -309,8 +309,6 @@ struct pwm_chip { #if IS_ENABLED(CONFIG_PWM) /* PWM user APIs */ -struct pwm_device *pwm_request(int pwm_id, const char *label); -void pwm_free(struct pwm_device *pwm); int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state); int pwm_adjust_config(struct pwm_device *pwm); @@ -410,17 +408,6 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id); #else -static inline struct pwm_device *pwm_request(int pwm_id, const char *label) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - -static inline void pwm_free(struct pwm_device *pwm) -{ - might_sleep(); -} - static inline int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) { -- GitLab From a6610435ac17de1ac727c90ad62c723d86c7ea36 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 13 Apr 2023 14:23:42 +0100 Subject: [PATCH 2861/5631] KVM: arm64: Handle 32bit CNTPCTSS traps When CNTPOFF isn't implemented and that we have a non-zero counter offset, CNTPCT and CNTPCTSS are trapped. We properly handle the former, but not the latter, as it is not present in the sysreg table (despite being actually handled in the code). Bummer. Just populate the cp15_64 table with the missing register. Reported-by: Reiji Watanabe Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/sysreg.h | 1 + arch/arm64/kvm/sys_regs.c | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index f8da9e1b0c11..a43f21559c3e 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -403,6 +403,7 @@ #define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1) #define SYS_AARCH32_CNTPCT sys_reg(0, 0, 0, 14, 0) #define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0) +#define SYS_AARCH32_CNTPCTSS sys_reg(0, 8, 0, 14, 0) #define __PMEV_op2(n) ((n) & 0x7) #define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3)) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index be7c2598e563..feca77083a5c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2538,6 +2538,7 @@ static const struct sys_reg_desc cp15_64_regs[] = { { Op1( 1), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_ASGI1R */ { Op1( 2), CRn( 0), CRm(12), Op2( 0), access_gic_sgi }, /* ICC_SGI0R */ { SYS_DESC(SYS_AARCH32_CNTP_CVAL), access_arch_timer }, + { SYS_DESC(SYS_AARCH32_CNTPCTSS), access_arch_timer }, }; static bool check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, -- GitLab From a2e20b29cf9ce6d2070a6e36666e2239f7f9625b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 2 Feb 2023 21:23:24 +0100 Subject: [PATCH 2862/5631] RDMA/irdma: Slightly optimize irdma_form_ah_cm_frame() There is no need to zero 'pktsize' bytes of 'buf', only the header needs to be cleared, to be safe. All the other bytes are already written with some memcpy() at the end of the function. Doing so also gives the opportunity to the compiler to avoid the memset() call. It can be inlined now that the length is known as compile time. Link: https://lore.kernel.org/r/098e3c397be0436f1867899245ecfe656c472110.1675369386.git.christophe.jaillet@wanadoo.fr Signed-off-by: Christophe JAILLET Reviewed-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/irdma/cm.c b/drivers/infiniband/hw/irdma/cm.c index 195aa9ea18b6..48c2a303e9ec 100644 --- a/drivers/infiniband/hw/irdma/cm.c +++ b/drivers/infiniband/hw/irdma/cm.c @@ -337,7 +337,7 @@ static struct irdma_puda_buf *irdma_form_ah_cm_frame(struct irdma_cm_node *cm_no pktsize = sizeof(*tcph) + opts_len + hdr_len + pd_len; - memset(buf, 0, pktsize); + memset(buf, 0, sizeof(*tcph)); sqbuf->totallen = pktsize; sqbuf->tcphlen = sizeof(*tcph) + opts_len; -- GitLab From e42ac7789df64120d7d3d57433dfc9f37ec0cb99 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 30 Mar 2023 12:55:46 +0200 Subject: [PATCH 2863/5631] s390/checksum: always use cksm instruction Commit dfe843dce775 ("s390/checksum: support GENERIC_CSUM, enable it for KASAN") switched s390 to use the generic checksum functions, so that KASAN instrumentation also works checksum functions by avoiding architecture specific inline assemblies. There is however the problem that the generic csum_partial() function returns a 32 bit value with a 16 bit folded checksum, while the original s390 variant does not fold to 16 bit. This in turn causes that the ipib_checksum in lowcore contains different values depending on kernel config options. The ipib_checksum is used by system dumpers to verify if pointers in lowcore point to valid data. Verification is done by comparing checksum values. The system dumpers still use 32 bit checksum values which are not folded, and therefore the checksum verification fails (incorrectly). Symptom is that reboot after dump does not work anymore when a KASAN instrumented kernel is dumped. Fix this by not using the generic checksum implementation. Instead add an explicit kasan_check_read() so that KASAN knows about the read access from within the inline assembly. Reported-by: Alexander Egorenkov Fixes: dfe843dce775 ("s390/checksum: support GENERIC_CSUM, enable it for KASAN") Tested-by: Alexander Egorenkov Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 4 ---- arch/s390/include/asm/checksum.h | 9 ++------- 2 files changed, 2 insertions(+), 11 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index d4db47b0610c..a7568449ca59 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -26,10 +26,6 @@ config GENERIC_BUG config GENERIC_BUG_RELATIVE_POINTERS def_bool y -config GENERIC_CSUM - bool - default y if KASAN - config GENERIC_LOCKBREAK def_bool y if PREEMPTION diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index d977a3a2f619..1b6b992cf18e 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -12,12 +12,7 @@ #ifndef _S390_CHECKSUM_H #define _S390_CHECKSUM_H -#ifdef CONFIG_GENERIC_CSUM - -#include - -#else /* CONFIG_GENERIC_CSUM */ - +#include #include #include @@ -40,6 +35,7 @@ static inline __wsum csum_partial(const void *buff, int len, __wsum sum) .odd = (unsigned long) len, }; + kasan_check_read(buff, len); asm volatile( "0: cksm %[sum],%[rp]\n" " jo 0b\n" @@ -135,5 +131,4 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, return csum_fold((__force __wsum)(sum >> 32)); } -#endif /* CONFIG_GENERIC_CSUM */ #endif /* _S390_CHECKSUM_H */ -- GitLab From 11018ef90ce73d9de8ac6e565c00cc8631b46328 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 30 Mar 2023 12:55:47 +0200 Subject: [PATCH 2864/5631] s390/checksum: remove not needed uaccess.h include Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/checksum.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 1b6b992cf18e..69837eec2ff5 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -13,7 +13,6 @@ #define _S390_CHECKSUM_H #include -#include #include /* -- GitLab From bb87190c9d46c4285696e071d5972a534bb107cc Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 31 Mar 2023 15:03:22 +0200 Subject: [PATCH 2865/5631] s390/kaslr: provide kaslr_enabled() function Just like other architectures provide a kaslr_enabled() function, instead of directly accessing a global variable. Also pass the renamed __kaslr_enabled variable from the decompressor to the kernel, so that kalsr_enabled() is available there too. This will be used by a subsequent patch which randomizes the module base load address. Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/boot/boot.h | 1 - arch/s390/boot/ipl_parm.c | 6 +++--- arch/s390/boot/pgm_check_info.c | 2 +- arch/s390/boot/startup.c | 6 +++--- arch/s390/include/asm/setup.h | 7 +++++++ arch/s390/kernel/setup.c | 1 + 6 files changed, 15 insertions(+), 8 deletions(-) diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 872963c8a0ab..5baa855c21cb 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -79,7 +79,6 @@ extern const char kernel_version[]; extern unsigned long memory_limit; extern unsigned long vmalloc_size; extern int vmalloc_size_set; -extern int kaslr_enabled; extern char __boot_data_start[], __boot_data_end[]; extern char __boot_data_preserved_start[], __boot_data_preserved_end[]; extern char _decompressor_syms_start[], _decompressor_syms_end[]; diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index c1f8f7999fed..8753cb0339e5 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -24,11 +24,11 @@ int __bootdata(noexec_disabled); unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL; struct ipl_parameter_block __bootdata_preserved(ipl_block); int __bootdata_preserved(ipl_block_valid); +int __bootdata_preserved(__kaslr_enabled); unsigned long vmalloc_size = VMALLOC_DEFAULT_SIZE; unsigned long memory_limit; int vmalloc_size_set; -int kaslr_enabled; static inline int __diag308(unsigned long subcode, void *addr) { @@ -264,7 +264,7 @@ void parse_boot_command_line(void) char *args; int rc; - kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE); + __kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE); args = strcpy(command_line_buf, early_command_line); while (*args) { args = next_arg(args, ¶m, &val); @@ -300,7 +300,7 @@ void parse_boot_command_line(void) modify_fac_list(val); if (!strcmp(param, "nokaslr")) - kaslr_enabled = 0; + __kaslr_enabled = 0; #if IS_ENABLED(CONFIG_KVM) if (!strcmp(param, "prot_virt")) { diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 0861e3c403f8..97244cd7a206 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -153,7 +153,7 @@ void print_pgm_check_info(void) decompressor_printk("Kernel command line: %s\n", early_command_line); decompressor_printk("Kernel fault: interruption code %04x ilc:%x\n", S390_lowcore.pgm_code, S390_lowcore.pgm_ilc >> 1); - if (kaslr_enabled) + if (kaslr_enabled()) decompressor_printk("Kernel random base: %lx\n", __kaslr_offset); decompressor_printk("PSW : %016lx %016lx (%pS)\n", S390_lowcore.psw_save_area.mask, diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index bdf305a93987..cc0ca7e0cd6d 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -160,10 +160,10 @@ static void setup_ident_map_size(unsigned long max_physmem_end) #ifdef CONFIG_CRASH_DUMP if (oldmem_data.start) { - kaslr_enabled = 0; + __kaslr_enabled = 0; ident_map_size = min(ident_map_size, oldmem_data.size); } else if (ipl_block_valid && is_ipl_block_dump()) { - kaslr_enabled = 0; + __kaslr_enabled = 0; if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) ident_map_size = min(ident_map_size, hsa_size); } @@ -315,7 +315,7 @@ void startup_kernel(void) save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) { + if (kaslr_enabled()) { random_lma = get_random_base(); if (random_lma) { __kaslr_offset = random_lma - vmlinux.default_lma; diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index b28d250efbaa..f191255c60db 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -146,6 +146,13 @@ static inline unsigned long kaslr_offset(void) return __kaslr_offset; } +extern int __kaslr_enabled; +static inline int kaslr_enabled(void) +{ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + return __kaslr_enabled; + return 0; +} struct oldmem_data { unsigned long start; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f2d0d52b3070..0903fe356634 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -150,6 +150,7 @@ unsigned long __bootdata(ident_map_size); struct physmem_info __bootdata(physmem_info); unsigned long __bootdata_preserved(__kaslr_offset); +int __bootdata_preserved(__kaslr_enabled); unsigned int __bootdata_preserved(zlib_dfltcc_support); EXPORT_SYMBOL(zlib_dfltcc_support); u64 __bootdata_preserved(stfle_fac_list[16]); -- GitLab From 34644cc2e15a7a91ec36b496e218694d17371589 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 31 Mar 2023 15:03:23 +0200 Subject: [PATCH 2866/5631] s390/kaslr: randomize module base load address Randomize the load address of modules in the kernel to make KASLR effective for modules. This is the s390 variant of commit e2b32e678513 ("x86, kaslr: randomize module base load address"). Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/module.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 2d159b32885b..6588f4efe378 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -26,6 +26,7 @@ #include #include #include +#include #if 0 #define DEBUGP printk @@ -35,6 +36,24 @@ #define PLT_ENTRY_SIZE 22 +static unsigned long get_module_load_offset(void) +{ + static DEFINE_MUTEX(module_kaslr_mutex); + static unsigned long module_load_offset; + + if (!kaslr_enabled()) + return 0; + /* + * Calculate the module_load_offset the first time this code + * is called. Once calculated it stays the same until reboot. + */ + mutex_lock(&module_kaslr_mutex); + if (!module_load_offset) + module_load_offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE; + mutex_unlock(&module_kaslr_mutex); + return module_load_offset; +} + void *module_alloc(unsigned long size) { gfp_t gfp_mask = GFP_KERNEL; @@ -42,7 +61,8 @@ void *module_alloc(unsigned long size) if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, + p = __vmalloc_node_range(size, MODULE_ALIGN, + MODULES_VADDR + get_module_load_offset(), MODULES_END, gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { -- GitLab From bac30ea9ef80624dfe4bf20c0fc2073dcc771a87 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Fri, 10 Mar 2023 12:52:37 +0100 Subject: [PATCH 2867/5631] s390/ipl: fix physical-virtual confusion for diag308 Diag 308 subcodes expect a physical address as their parameter. This currently is not a bug, but in the future physical and virtual addresses might differ. Fix the confusion by doing a virtual-to-physical conversion in the exported diag308() and leave the assembly wrapper __diag308() alone. Note that several callers pass NULL as addr, so check for the case when NULL is passed and pass 0 to hardware since virt_to_phys(0) might be nonzero. Suggested-by: Marc Hartmayer Signed-off-by: Nico Boehr Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ipl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 0f91cd401eef..43de939b7af1 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -176,11 +176,11 @@ static bool reipl_fcp_clear; static bool reipl_ccw_clear; static bool reipl_eckd_clear; -static inline int __diag308(unsigned long subcode, void *addr) +static inline int __diag308(unsigned long subcode, unsigned long addr) { union register_pair r1; - r1.even = (unsigned long) addr; + r1.even = addr; r1.odd = 0; asm volatile( " diag %[r1],%[subcode],0x308\n" @@ -195,7 +195,7 @@ static inline int __diag308(unsigned long subcode, void *addr) int diag308(unsigned long subcode, void *addr) { diag_stat_inc(DIAG_STAT_X308); - return __diag308(subcode, addr); + return __diag308(subcode, addr ? virt_to_phys(addr) : 0); } EXPORT_SYMBOL_GPL(diag308); -- GitLab From 22e99fa56443f19b96e2e888854bfc202dd97069 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 2 Apr 2023 20:55:16 +0200 Subject: [PATCH 2868/5631] s390/mm: implement set_memory_rox() Provide the s390 specific native set_memory_rox() implementation to avoid frequent set_memory_ro(); set_memory_x() call pairs. This is the s390 variant of commit 60463628c9e0 ("x86/mm: Implement native set_memory_rox()"). Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/set_memory.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index 950d87bd997a..f4362ce1e17a 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -34,6 +34,12 @@ static inline int set_memory_x(unsigned long addr, int numpages) return __set_memory(addr, numpages, SET_MEMORY_X); } +#define set_memory_rox set_memory_rox +static inline int set_memory_rox(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, SET_MEMORY_RO | SET_MEMORY_X); +} + static inline int set_memory_4k(unsigned long addr, int numpages) { return __set_memory(addr, numpages, SET_MEMORY_4K); -- GitLab From f0a2a7c527849bf1b112a43f0b8d0658a7b4e6ec Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 2 Apr 2023 20:55:17 +0200 Subject: [PATCH 2869/5631] s390/mm: implement set_memory_rwnx() Given that set_memory_rox() is implemented, provide also set_memory_rwnx(). This allows to get rid of all open coded __set_memory() usages in s390 architecture code. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/set_memory.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index f4362ce1e17a..25f2464dbb7e 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -40,6 +40,11 @@ static inline int set_memory_rox(unsigned long addr, int numpages) return __set_memory(addr, numpages, SET_MEMORY_RO | SET_MEMORY_X); } +static inline int set_memory_rwnx(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, SET_MEMORY_RW | SET_MEMORY_NX); +} + static inline int set_memory_4k(unsigned long addr, int numpages) { return __set_memory(addr, numpages, SET_MEMORY_4K); -- GitLab From f9b2d96c4fa4475929e26cbac4027801d93c6e53 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 2 Apr 2023 20:55:18 +0200 Subject: [PATCH 2870/5631] s390/mm: use set_memory_*() helpers instead of open coding Given that set_memory_rox() and set_memory_rwnx() exist, it is possible to get rid of all open coded __set_memory() usages and replace them with proper helper calls everywhere. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/kprobes.c | 2 +- arch/s390/mm/init.c | 5 ++--- arch/s390/mm/vmem.c | 34 ++++++++++++++-------------------- 3 files changed, 17 insertions(+), 24 deletions(-) diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 7b41ceecbb25..d4b863ed0aa7 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -41,7 +41,7 @@ void *alloc_insn_page(void) page = module_alloc(PAGE_SIZE); if (!page) return NULL; - __set_memory((unsigned long) page, 1, SET_MEMORY_RO | SET_MEMORY_X); + set_memory_rox((unsigned long)page, 1); return page; } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 144447d5cb4c..8d94e29adcdb 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -176,9 +176,8 @@ void __init mem_init(void) void free_initmem(void) { - __set_memory((unsigned long)_sinittext, - (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT, - SET_MEMORY_RW | SET_MEMORY_NX); + set_memory_rwnx((unsigned long)_sinittext, + (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT); free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 242f95aa9801..5b22c6e24528 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -732,30 +732,24 @@ void __init vmem_map_init(void) memblock_region_cmp, memblock_region_swap); __for_each_mem_range(i, &memblock.memory, &memory_rwx, NUMA_NO_NODE, MEMBLOCK_NONE, &base, &end, NULL) { - __set_memory((unsigned long)__va(base), - (end - base) >> PAGE_SHIFT, - SET_MEMORY_RW | SET_MEMORY_NX); + set_memory_rwnx((unsigned long)__va(base), + (end - base) >> PAGE_SHIFT); } #ifdef CONFIG_KASAN - for_each_mem_range(i, &base, &end) - __set_memory(__sha(base), - (__sha(end) - __sha(base)) >> PAGE_SHIFT, - SET_MEMORY_RW | SET_MEMORY_NX); + for_each_mem_range(i, &base, &end) { + set_memory_rwnx(__sha(base), + (__sha(end) - __sha(base)) >> PAGE_SHIFT); + } #endif - - __set_memory((unsigned long)_stext, - (unsigned long)(_etext - _stext) >> PAGE_SHIFT, - SET_MEMORY_RO | SET_MEMORY_X); - __set_memory((unsigned long)_etext, - (unsigned long)(__end_rodata - _etext) >> PAGE_SHIFT, - SET_MEMORY_RO); - __set_memory((unsigned long)_sinittext, - (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT, - SET_MEMORY_RO | SET_MEMORY_X); - __set_memory(__stext_amode31, - (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT, - SET_MEMORY_RO | SET_MEMORY_X); + set_memory_rox((unsigned long)_stext, + (unsigned long)(_etext - _stext) >> PAGE_SHIFT); + set_memory_ro((unsigned long)_etext, + (unsigned long)(__end_rodata - _etext) >> PAGE_SHIFT); + set_memory_rox((unsigned long)_sinittext, + (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT); + set_memory_rox(__stext_amode31, + (__etext_amode31 - __stext_amode31) >> PAGE_SHIFT); /* lowcore must be executable for LPSWE */ if (static_key_enabled(&cpu_has_bear)) -- GitLab From 7c7ab788c0959c363b5cb2ac5ff4822fc12ccba5 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 2 Apr 2023 20:55:19 +0200 Subject: [PATCH 2871/5631] s390/ftrace: do not assume module_alloc() returns executable memory The ftrace code assumes at two places that module_alloc() returns executable memory. While this is currently true, this will be changed with a subsequent patch to follow other architectures which implement ARCH_HAS_STRICT_MODULE_RWX. Acked-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/ftrace.c | 2 +- arch/s390/kernel/module.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 6f6c44b7af89..c46381ea04ec 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -226,7 +226,7 @@ static int __init ftrace_plt_init(void) start = ftrace_shared_hotpatch_trampoline(&end); memcpy(ftrace_plt, start, end - start); - set_memory_ro((unsigned long)ftrace_plt, 1); + set_memory_rox((unsigned long)ftrace_plt, 1); return 0; } device_initcall(ftrace_plt_init); diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 6588f4efe378..57c13e30e66d 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -509,7 +509,7 @@ static int module_alloc_ftrace_hotpatch_trampolines(struct module *me, start = module_alloc(numpages * PAGE_SIZE); if (!start) return -ENOMEM; - set_memory_ro((unsigned long)start, numpages); + set_memory_rox((unsigned long)start, numpages); end = start + size; me->arch.trampolines_start = (struct ftrace_hotpatch_trampoline *)start; -- GitLab From 1707c1165283a9634717971f17692535c21ab0eb Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 2 Apr 2023 20:55:21 +0200 Subject: [PATCH 2872/5631] s390/module: create module allocations without exec permissions This is the s390 variant of commit 7dfac3c5f40e ("arm64: module: create module allocations without exec permissions"): "The core code manages the executable permissions of code regions of modules explicitly. It is no longer necessary to create the module vmalloc regions with RWX permissions. So create them with RW- permissions instead, which is preferred from a security perspective." Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 57c13e30e66d..07a13546980d 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -63,7 +63,7 @@ void *module_alloc(unsigned long size) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), MODULES_END, - gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, + gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); -- GitLab From 3cdf0269cdc2c4728b71af4199823b6284379d42 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 24 Feb 2023 08:55:21 +0100 Subject: [PATCH 2873/5631] s390/cpum_cf: log bad return code of function cfset_all_copy When function cfset_all_copy() fails, also log the bad return code in the debug statement (when turned on). No functional change Signed-off-by: Thomas Richter Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index c9ab971498d6..0b134c220948 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -1290,7 +1290,7 @@ static size_t cfset_needspace(unsigned int sets) static int cfset_all_copy(unsigned long arg, cpumask_t *mask) { struct s390_ctrset_read __user *ctrset_read; - unsigned int cpu, cpus, rc; + unsigned int cpu, cpus, rc = 0; void __user *uptr; ctrset_read = (struct s390_ctrset_read __user *)arg; @@ -1304,17 +1304,20 @@ static int cfset_all_copy(unsigned long arg, cpumask_t *mask) rc |= put_user(cpuhw->sets, &ctrset_cpudata->no_sets); rc |= copy_to_user(ctrset_cpudata->data, cpuhw->data, cpuhw->used); - if (rc) - return -EFAULT; + if (rc) { + rc = -EFAULT; + goto out; + } uptr += sizeof(struct s390_ctrset_cpudata) + cpuhw->used; cond_resched(); } cpus = cpumask_weight(mask); if (put_user(cpus, &ctrset_read->no_cpus)) - return -EFAULT; - debug_sprintf_event(cf_dbg, 4, "%s copied %ld\n", __func__, + rc = -EFAULT; +out: + debug_sprintf_event(cf_dbg, 4, "%s rc %d copied %ld\n", __func__, rc, uptr - (void __user *)ctrset_read->data); - return 0; + return rc; } static size_t cfset_cpuset_read(struct s390_ctrset_setdata *p, int ctrset, -- GitLab From 26300860c2be489fa8c919e55fba28fa782cbb1e Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 31 Mar 2023 11:42:20 +0200 Subject: [PATCH 2874/5631] s390/cpum_cf: remove unnecessary copy_from_user call Struct s390_ctrset_read userdata is filled by ioctl_read operation using put_user/copy_to_user. However, the ctrset->data value access is not performed anywhere during the ioctl_read operation. Remove unnecessary copy_from_user() call. No functional change. Signed-off-by: Thomas Richter Suggested-by: Sumanth Korikkar Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 0b134c220948..4c158faa3075 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -1388,14 +1388,10 @@ static int cfset_all_read(unsigned long arg, struct cfset_request *req) static long cfset_ioctl_read(unsigned long arg, struct cfset_request *req) { - struct s390_ctrset_read read; int ret = -ENODATA; - if (req && req->ctrset) { - if (copy_from_user(&read, (char __user *)arg, sizeof(read))) - return -EFAULT; + if (req && req->ctrset) ret = cfset_all_read(arg, req); - } return ret; } -- GitLab From a1d2d9cbaf0512451471705264bee7b3f50d4c29 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 15 Mar 2023 10:19:57 +0100 Subject: [PATCH 2875/5631] s390/boot: do not change default_lma The current modification of the default_lma is illogical and should be avoided. It would be more appropriate to introduce and utilize a new variable vmlinux_lma instead, so that default_lma remains unchanged and at its original "default" value of 0x100000. Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index cc0ca7e0cd6d..e1edb6186bee 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -235,9 +235,9 @@ static unsigned long setup_kernel_memory_layout(void) /* * This function clears the BSS section of the decompressed Linux kernel and NOT the decompressor's. */ -static void clear_bss_section(void) +static void clear_bss_section(unsigned long vmlinux_lma) { - memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size); + memset((void *)vmlinux_lma + vmlinux.image_size, 0, vmlinux.bss_size); } /* @@ -256,7 +256,6 @@ static void setup_vmalloc_size(void) static void offset_vmlinux_info(unsigned long offset) { - vmlinux.default_lma += offset; *(unsigned long *)(&vmlinux.entry) += offset; vmlinux.bootdata_off += offset; vmlinux.bootdata_preserved_off += offset; @@ -278,7 +277,7 @@ static void offset_vmlinux_info(unsigned long offset) void startup_kernel(void) { unsigned long max_physmem_end; - unsigned long random_lma; + unsigned long vmlinux_lma = 0; unsigned long asce_limit; unsigned long safe_addr; void *img; @@ -316,26 +315,26 @@ void startup_kernel(void) rescue_initrd(safe_addr, ident_map_size); if (kaslr_enabled()) { - random_lma = get_random_base(); - if (random_lma) { - __kaslr_offset = random_lma - vmlinux.default_lma; - img = (void *)vmlinux.default_lma; + vmlinux_lma = get_random_base(); + if (vmlinux_lma) { + __kaslr_offset = vmlinux_lma - vmlinux.default_lma; offset_vmlinux_info(__kaslr_offset); } } + vmlinux_lma = vmlinux_lma ?: vmlinux.default_lma; + physmem_reserve(RR_VMLINUX, vmlinux_lma, vmlinux.image_size + vmlinux.bss_size); if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) { img = decompress_kernel(); - memmove((void *)vmlinux.default_lma, img, vmlinux.image_size); + memmove((void *)vmlinux_lma, img, vmlinux.image_size); } else if (__kaslr_offset) { - memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size); + img = (void *)vmlinux.default_lma; + memmove((void *)vmlinux_lma, img, vmlinux.image_size); memset(img, 0, vmlinux.image_size); } /* vmlinux decompression is done, shrink reserved low memory */ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); - if (!__kaslr_offset) - physmem_reserve(RR_VMLINUX, vmlinux.default_lma, vmlinux.image_size + vmlinux.bss_size); physmem_alloc_range(RR_AMODE31, vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G, true); /* @@ -351,7 +350,7 @@ void startup_kernel(void) * - copy_bootdata() must follow setup_vmem() to propagate changes to * bootdata made by setup_vmem() */ - clear_bss_section(); + clear_bss_section(vmlinux_lma); handle_relocs(__kaslr_offset); setup_vmem(asce_limit); copy_bootdata(); -- GitLab From 898435203c115b164b96f30be7d9c790bbb50338 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 15 Mar 2023 11:00:19 +0100 Subject: [PATCH 2876/5631] s390/boot: pin amode31 default lma The special amode31 part of the kernel must always remain below 2Gb. Place it just under vmlinux.default_lma by default, which makes it easier to debug amode31 as its default lma is known 0x10000 - 0x3000 (currently, amode31's size is 3 pages). This location is always available as it is originally occupied by the vmlinux archive. Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index e1edb6186bee..45c30c2b1a7a 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -278,6 +278,7 @@ void startup_kernel(void) { unsigned long max_physmem_end; unsigned long vmlinux_lma = 0; + unsigned long amode31_lma; unsigned long asce_limit; unsigned long safe_addr; void *img; @@ -335,7 +336,8 @@ void startup_kernel(void) /* vmlinux decompression is done, shrink reserved low memory */ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); - physmem_alloc_range(RR_AMODE31, vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G, true); + amode31_lma = vmlinux.default_lma - vmlinux.amode31_size; + physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size); /* * The order of the following operations is important: -- GitLab From 6e259bc5a15ec49693fa3d19fdd4511f7679a20d Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Tue, 21 Feb 2023 23:08:42 +0100 Subject: [PATCH 2877/5631] s390/kaslr: generalize and improve random base distribution Improve the distribution algorithm of random base address to ensure a uniformity among all suitable addresses. To generate a random value once, and to build a continuous range in which every value is suitable, count all the suitable addresses (referred to as positions) that can be used as a base address. The positions are counted by iterating over the usable memory ranges. For each range that is big enough to accommodate the image, count all the suitable addresses where the image can be placed, while taking reserved memory ranges into consideration. A new function "iterate_valid_positions()" has dual purpose. Firstly, it is called to count the positions in a given memory range, and secondly, to convert a random position back to an address. "get_random_base()" has been replaced with more generic "randomize_within_range()" which now could be called for randomizing base addresses not just for the kernel image. Acked-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/boot/boot.h | 4 +- arch/s390/boot/kaslr.c | 110 +++++++++++++++++++++++++++++++--- arch/s390/boot/physmem_info.c | 5 ++ arch/s390/boot/startup.c | 4 +- 4 files changed, 112 insertions(+), 11 deletions(-) diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 5baa855c21cb..222c6886acf6 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -54,6 +54,7 @@ unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned lon unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size, unsigned long align, unsigned long min, unsigned long max, bool die_on_oom); +unsigned long get_physmem_alloc_pos(void); bool ipl_report_certs_intersects(unsigned long addr, unsigned long size, unsigned long *intersection_start); bool is_ipl_block_dump(void); @@ -66,7 +67,8 @@ void verify_facilities(void); void print_missing_facilities(void); void sclp_early_setup_buffer(void); void print_pgm_check_info(void); -unsigned long get_random_base(void); +unsigned long randomize_within_range(unsigned long size, unsigned long align, + unsigned long min, unsigned long max); void setup_vmem(unsigned long asce_limit); void __printf(1, 2) decompressor_printk(const char *fmt, ...); void print_stacktrace(unsigned long sp); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index 71f75f03f800..90602101e2ae 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -91,16 +91,108 @@ static int get_random(unsigned long limit, unsigned long *value) return 0; } -unsigned long get_random_base(void) +static void sort_reserved_ranges(struct reserved_range *res, unsigned long size) { - unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long minimal_pos = vmlinux.default_lma + vmlinux_size; - unsigned long random; + struct reserved_range tmp; + int i, j; - /* [vmlinux.default_lma + vmlinux.image_size + vmlinux.bss_size : physmem_info.usable] */ - if (get_random(physmem_info.usable - minimal_pos, &random)) - return 0; + for (i = 1; i < size; i++) { + tmp = res[i]; + for (j = i - 1; j >= 0 && res[j].start > tmp.start; j--) + res[j + 1] = res[j]; + res[j + 1] = tmp; + } +} + +static unsigned long iterate_valid_positions(unsigned long size, unsigned long align, + unsigned long _min, unsigned long _max, + struct reserved_range *res, size_t res_count, + bool pos_count, unsigned long find_pos) +{ + unsigned long start, end, tmp_end, range_pos, pos = 0; + struct reserved_range *res_end = res + res_count; + struct reserved_range *skip_res; + int i; + + align = max(align, 8UL); + _min = round_up(_min, align); + for_each_physmem_usable_range(i, &start, &end) { + if (_min >= end) + continue; + start = round_up(start, align); + if (start >= _max) + break; + start = max(_min, start); + end = min(_max, end); + + while (start + size <= end) { + /* skip reserved ranges below the start */ + while (res && res->end <= start) { + res++; + if (res >= res_end) + res = NULL; + } + skip_res = NULL; + tmp_end = end; + /* has intersecting reserved range */ + if (res && res->start < end) { + skip_res = res; + tmp_end = res->start; + } + if (start + size <= tmp_end) { + range_pos = (tmp_end - start - size) / align + 1; + if (pos_count) { + pos += range_pos; + } else { + if (range_pos >= find_pos) + return start + (find_pos - 1) * align; + find_pos -= range_pos; + } + } + if (!skip_res) + break; + start = round_up(skip_res->end, align); + } + } - return physmem_alloc_range(RR_VMLINUX, vmlinux_size, THREAD_SIZE, - vmlinux.default_lma, minimal_pos + random, false); + return pos_count ? pos : 0; +} + +/* + * Two types of decompressor memory allocations/reserves are considered + * differently. + * + * "Static" or "single" allocations are done via physmem_alloc_range() and + * physmem_reserve(), and they are listed in physmem_info.reserved[]. Each + * type of "static" allocation can only have one allocation per type and + * cannot have chains. + * + * On the other hand, "dynamic" or "repetitive" allocations are done via + * physmem_alloc_top_down(). These allocations are tightly packed together + * top down from the end of online memory. physmem_alloc_pos represents + * current position where those allocations start. + * + * Functions randomize_within_range() and iterate_valid_positions() + * only consider "dynamic" allocations by never looking above + * physmem_alloc_pos. "Static" allocations, however, are explicitly + * considered by checking the "res" (reserves) array. The first + * reserved_range of a "dynamic" allocation may also be checked along the + * way, but it will always be above the maximum value anyway. + */ +unsigned long randomize_within_range(unsigned long size, unsigned long align, + unsigned long min, unsigned long max) +{ + struct reserved_range res[RR_MAX]; + unsigned long max_pos, pos; + + memcpy(res, physmem_info.reserved, sizeof(res)); + sort_reserved_ranges(res, ARRAY_SIZE(res)); + max = min(max, get_physmem_alloc_pos()); + + max_pos = iterate_valid_positions(size, align, min, max, res, ARRAY_SIZE(res), true, 0); + if (!max_pos) + return 0; + if (get_random(max_pos, &pos)) + return 0; + return iterate_valid_positions(size, align, min, max, res, ARRAY_SIZE(res), false, pos + 1); } diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 4ee9b7381142..0cf79826eef9 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -321,3 +321,8 @@ unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned lon physmem_alloc_ranges = ranges_left; return addr; } + +unsigned long get_physmem_alloc_pos(void) +{ + return physmem_alloc_pos; +} diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 45c30c2b1a7a..638a6cf8a075 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -316,7 +316,9 @@ void startup_kernel(void) rescue_initrd(safe_addr, ident_map_size); if (kaslr_enabled()) { - vmlinux_lma = get_random_base(); + vmlinux_lma = randomize_within_range(vmlinux.image_size + vmlinux.bss_size, + THREAD_SIZE, vmlinux.default_lma, + ident_map_size); if (vmlinux_lma) { __kaslr_offset = vmlinux_lma - vmlinux.default_lma; offset_vmlinux_info(__kaslr_offset); -- GitLab From b3e0423c4e76b19f04799e01b6443949f5fecbbc Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 15 Mar 2023 13:54:14 +0100 Subject: [PATCH 2878/5631] s390/kaslr: randomize amode31 base address When the KASLR is enabled, randomize the base address of the amode31 image within the first 2 GB, similar to the approach taken for the vmlinux image. This makes it harder to predict the location of amode31 data and code. Reviewed-by: Alexander Gordeev Signed-off-by: Vasily Gorbik --- arch/s390/boot/startup.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 638a6cf8a075..64bd7ac3e35d 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -278,7 +278,7 @@ void startup_kernel(void) { unsigned long max_physmem_end; unsigned long vmlinux_lma = 0; - unsigned long amode31_lma; + unsigned long amode31_lma = 0; unsigned long asce_limit; unsigned long safe_addr; void *img; @@ -338,7 +338,9 @@ void startup_kernel(void) /* vmlinux decompression is done, shrink reserved low memory */ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end); - amode31_lma = vmlinux.default_lma - vmlinux.amode31_size; + if (kaslr_enabled()) + amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G); + amode31_lma = amode31_lma ?: vmlinux.default_lma - vmlinux.amode31_size; physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size); /* -- GitLab From c01f2a5fe4e3df4ab846fcba5435ca9fdee4f583 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Fri, 24 Feb 2023 09:01:51 +0100 Subject: [PATCH 2879/5631] s390/cpum_cf: simplify pr_err() statement in cpumf_pmu_enable/disable Simplify pr_err() statement into one line and omit return statement. No functional change. Signed-off-by: Thomas Richter Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 4c158faa3075..96b581967334 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -471,13 +471,10 @@ static void cpumf_pmu_enable(struct pmu *pmu) return; err = lcctl(cpuhw->state | cpuhw->dev_state); - if (err) { - pr_err("Enabling the performance measuring unit " - "failed with rc=%x\n", err); - return; - } - - cpuhw->flags |= PMU_F_ENABLED; + if (err) + pr_err("Enabling the performance measuring unit failed with rc=%x\n", err); + else + cpuhw->flags |= PMU_F_ENABLED; } /* @@ -497,13 +494,10 @@ static void cpumf_pmu_disable(struct pmu *pmu) inactive = cpuhw->state & ~((1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1); inactive |= cpuhw->dev_state; err = lcctl(inactive); - if (err) { - pr_err("Disabling the performance measuring unit " - "failed with rc=%x\n", err); - return; - } - - cpuhw->flags &= ~PMU_F_ENABLED; + if (err) + pr_err("Disabling the performance measuring unit failed with rc=%x\n", err); + else + cpuhw->flags &= ~PMU_F_ENABLED; } #define PMC_INIT 0UL -- GitLab From d24e18ef7e13c9cd580ebee771f7ccb9d3f6ee42 Mon Sep 17 00:00:00 2001 From: Marc Hartmayer Date: Mon, 31 Jan 2022 13:22:31 +0000 Subject: [PATCH 2880/5631] s390/boot: improve install.sh script Use proper quoting for the variables and explicitly distinguish between command options and positional arguments. Acked-by: Heiko Carstens Signed-off-by: Marc Hartmayer Signed-off-by: Vasily Gorbik --- arch/s390/boot/install.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/s390/boot/install.sh b/arch/s390/boot/install.sh index 616ba1660f08..a13dd2f2aa1c 100755 --- a/arch/s390/boot/install.sh +++ b/arch/s390/boot/install.sh @@ -17,8 +17,8 @@ echo "Warning: '${INSTALLKERNEL}' command not available - additional " \ "bootloader config required" >&2 -if [ -f $4/vmlinuz-$1 ]; then mv $4/vmlinuz-$1 $4/vmlinuz-$1.old; fi -if [ -f $4/System.map-$1 ]; then mv $4/System.map-$1 $4/System.map-$1.old; fi +if [ -f "$4/vmlinuz-$1" ]; then mv -- "$4/vmlinuz-$1" "$4/vmlinuz-$1.old"; fi +if [ -f "$4/System.map-$1" ]; then mv -- "$4/System.map-$1" "$4/System.map-$1.old"; fi -cat $2 > $4/vmlinuz-$1 -cp $3 $4/System.map-$1 +cat -- "$2" > "$4/vmlinuz-$1" +cp -- "$3" "$4/System.map-$1" -- GitLab From 07fdd6627f7f9c72ed68d531653b56df81da9996 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 6 Apr 2023 13:31:28 +0200 Subject: [PATCH 2881/5631] s390/mm: rename POPULATE_ONE2ONE to POPULATE_DIRECT Architectures generally use the "direct map" wording for mapping the whole physical memory. Use that wording as well in arch/s390/boot/vmem.c, instead of "one to one" in order to avoid confusion. This also matches what is already done in arch/s390/mm/vmem.c. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/boot/vmem.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index b01ea2abda03..df91d9065f7e 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -19,7 +19,7 @@ unsigned long __bootdata_preserved(s390_invalid_asce); enum populate_mode { POPULATE_NONE, - POPULATE_ONE2ONE, + POPULATE_DIRECT, POPULATE_ABS_LOWCORE, #ifdef CONFIG_KASAN POPULATE_KASAN_MAP_SHADOW, @@ -237,7 +237,7 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m switch (mode) { case POPULATE_NONE: return -1; - case POPULATE_ONE2ONE: + case POPULATE_DIRECT: return addr; case POPULATE_ABS_LOWCORE: return __abs_lowcore_pa(addr); @@ -404,9 +404,9 @@ void setup_vmem(unsigned long asce_limit) * To prevent creation of a large page at address 0 first map * the lowcore and create the identity mapping only afterwards. */ - pgtable_populate(0, sizeof(struct lowcore), POPULATE_ONE2ONE); + pgtable_populate(0, sizeof(struct lowcore), POPULATE_DIRECT); for_each_physmem_usable_range(i, &start, &end) - pgtable_populate(start, end, POPULATE_ONE2ONE); + pgtable_populate(start, end, POPULATE_DIRECT); pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore), POPULATE_ABS_LOWCORE); pgtable_populate(__memcpy_real_area, __memcpy_real_area + PAGE_SIZE, -- GitLab From 81e8479649853ffafc714aca4a9c0262efd3160a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 6 Apr 2023 13:31:29 +0200 Subject: [PATCH 2882/5631] s390/mm: fix direct map accounting Commit bb1520d581a3 ("s390/mm: start kernel with DAT enabled") did not implement direct map accounting in the early page table setup code. In result the reported values are bogus now: $cat /proc/meminfo ... DirectMap4k: 5120 kB DirectMap1M: 18446744073709546496 kB DirectMap2G: 0 kB Fix this by adding the missing accounting. The result looks sane again: $cat /proc/meminfo ... DirectMap4k: 6156 kB DirectMap1M: 2091008 kB DirectMap2G: 6291456 kB Fixes: bb1520d581a3 ("s390/mm: start kernel with DAT enabled") Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/boot/vmem.c | 18 ++++++++++++++++-- arch/s390/include/asm/pgtable.h | 2 +- arch/s390/mm/pageattr.c | 2 +- 3 files changed, 18 insertions(+), 4 deletions(-) diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index df91d9065f7e..acb1f8b53105 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -13,6 +13,10 @@ unsigned long __bootdata_preserved(s390_invalid_asce); +#ifdef CONFIG_PROC_FS +atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); +#endif + #define init_mm (*(struct mm_struct *)vmlinux.init_mm_off) #define swapper_pg_dir vmlinux.swapper_pg_dir_off #define invalid_pg_dir vmlinux.invalid_pg_dir_off @@ -267,6 +271,7 @@ static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end) static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long pages = 0; pte_t *pte, entry; pte = pte_offset_kernel(pmd, addr); @@ -277,14 +282,17 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e entry = __pte(_pa(addr, PAGE_SIZE, mode)); entry = set_pte_bit(entry, PAGE_KERNEL_EXEC); set_pte(pte, entry); + pages++; } } + if (mode == POPULATE_DIRECT) + update_page_count(PG_DIRECT_MAP_4K, pages); } static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next; + unsigned long next, pages = 0; pmd_t *pmd, entry; pte_t *pte; @@ -298,6 +306,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode)); entry = set_pmd_bit(entry, SEGMENT_KERNEL_EXEC); set_pmd(pmd, entry); + pages++; continue; } pte = boot_pte_alloc(); @@ -307,12 +316,14 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } + if (mode == POPULATE_DIRECT) + update_page_count(PG_DIRECT_MAP_1M, pages); } static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next; + unsigned long next, pages = 0; pud_t *pud, entry; pmd_t *pmd; @@ -326,6 +337,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e entry = __pud(_pa(addr, _REGION3_SIZE, mode)); entry = set_pud_bit(entry, REGION3_KERNEL_EXEC); set_pud(pud, entry); + pages++; continue; } pmd = boot_crst_alloc(_SEGMENT_ENTRY_EMPTY); @@ -335,6 +347,8 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } + if (mode == POPULATE_DIRECT) + update_page_count(PG_DIRECT_MAP_2G, pages); } static void pgtable_p4d_populate(pgd_t *pgd, unsigned long addr, unsigned long end, diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2c70b4d1263d..acbe1ac2d571 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -34,7 +34,7 @@ enum { PG_DIRECT_MAP_MAX }; -extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX]; +extern atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); static inline void update_page_count(int level, long count) { diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 7838e9c70000..77f31791044d 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -41,7 +41,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end) } #ifdef CONFIG_PROC_FS -atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX]; +atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); void arch_report_meminfo(struct seq_file *m) { -- GitLab From 3071e9b39106e1b9576584a372f446c23b258e3f Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 6 Apr 2023 08:28:42 -0600 Subject: [PATCH 2883/5631] s390/diag: replace zero-length array with flexible-array member Zero-length arrays are deprecated [1] and have to be replaced by C99 flexible-array members. This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help to make progress towards globally enabling -fstrict-flex-arrays=3 [2] Link: https://github.com/KSPP/linux/issues/78 [1] Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [2] Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/ZC7XGpUtVhqlRLhH@work Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/diag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h index 674a939f16ee..902e0330dd91 100644 --- a/arch/s390/include/asm/diag.h +++ b/arch/s390/include/asm/diag.h @@ -90,7 +90,7 @@ struct diag8c { u8 num_partitions; u16 width; u16 height; - u8 data[0]; + u8 data[]; } __packed __aligned(4); extern int diag8c(struct diag8c *out, struct ccw_dev_id *devno); -- GitLab From 6ca87bc4c8eee464cc13259aaf6881d8df3f86f9 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Thu, 6 Apr 2023 08:29:35 -0600 Subject: [PATCH 2884/5631] s390/fcx: replace zero-length array with flexible-array member Zero-length arrays are deprecated [1] and have to be replaced by C99 flexible-array members. This helps with the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy() and help to make progress towards globally enabling -fstrict-flex-arrays=3 [2] Link: https://github.com/KSPP/linux/issues/78 [1] Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html [2] Signed-off-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/ZC7XT5prvoE4Yunm@work Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/fcx.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/include/asm/fcx.h b/arch/s390/include/asm/fcx.h index b8a028a36173..29784b4b44f6 100644 --- a/arch/s390/include/asm/fcx.h +++ b/arch/s390/include/asm/fcx.h @@ -286,7 +286,7 @@ struct tccb_tcat { */ struct tccb { struct tccb_tcah tcah; - u8 tca[0]; + u8 tca[]; } __attribute__ ((packed, aligned(8))); struct tcw *tcw_get_intrg(struct tcw *tcw); -- GitLab From ca1382eafae50377088772d6c485ab6b89da2e56 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Apr 2023 11:13:01 +0200 Subject: [PATCH 2885/5631] s390/debug: replace zero-length array with flexible-array member There are numerous patches which convert zero-length arrays with a flexible-array member. Convert the remaining s390 occurrences. Suggested-by: Gustavo A. R. Silva Link: https://github.com/KSPP/linux/issues/78 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 221c865785c2..a85e0c3e7027 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -60,7 +60,7 @@ typedef struct { * except of floats, and long long (32 bit) * */ - long args[0]; + long args[]; } debug_sprintf_entry_t; /* internal function prototyes */ -- GitLab From 469c701db198227c2354b7c37f2c73dbfee5e065 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Apr 2023 11:17:42 +0200 Subject: [PATCH 2886/5631] s390/sclp: replace zero-length array with flexible-array member There are numerous patches which convert zero-length arrays with a flexible-array member. Convert the remaining s390 occurrences. Suggested-by: Gustavo A. R. Silva Link: https://github.com/KSPP/linux/issues/78 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/char/sclp.h | 2 +- drivers/s390/char/sclp_cmd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h index 909ba7f08688..6a23ec286c70 100644 --- a/drivers/s390/char/sclp.h +++ b/drivers/s390/char/sclp.h @@ -204,7 +204,7 @@ struct read_storage_sccb { u16 assigned; u16 standby; u16 :16; - u32 entries[0]; + u32 entries[]; } __packed; static inline void sclp_fill_core_info(struct sclp_core_info *info, diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c index 15971997cfe2..3c87057436d5 100644 --- a/drivers/s390/char/sclp_cmd.c +++ b/drivers/s390/char/sclp_cmd.c @@ -241,7 +241,7 @@ struct attach_storage_sccb { u16 :16; u16 assigned; u32 :32; - u32 entries[0]; + u32 entries[]; } __packed; static int sclp_attach_storage(u8 id) -- GitLab From e20985a79643c701cae3a527b584b3722c53d951 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 11 Apr 2023 11:18:59 +0200 Subject: [PATCH 2887/5631] s390/cio: replace zero-length array with flexible-array member There are numerous patches which convert zero-length arrays with a flexible-array member. Convert the remaining s390 occurrences. Suggested-by: Gustavo A. R. Silva Link: https://github.com/KSPP/linux/issues/78 Link: https://gcc.gnu.org/pipermail/gcc-patches/2022-October/602902.html Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- drivers/s390/cio/chsc.c | 2 +- drivers/s390/cio/chsc.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 620a917cd3a1..0abd77f4b664 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1171,7 +1171,7 @@ int __init chsc_get_cssid_iid(int idx, u8 *cssid, u8 *iid) u8 cssid; u8 iid; u32 : 16; - } list[0]; + } list[]; } *sdcal_area; int ret; diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h index 32fa7faa5bf6..d1caacb08e67 100644 --- a/drivers/s390/cio/chsc.h +++ b/drivers/s390/cio/chsc.h @@ -120,7 +120,7 @@ struct chsc_scpd { u32 zeroes1; struct chsc_header response; u32:32; - u8 data[0]; + u8 data[]; } __packed __aligned(PAGE_SIZE); struct chsc_sda_area { -- GitLab From 67ff32289acad9ed338cd9f2351b44939e55163e Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:16 -0800 Subject: [PATCH 2888/5631] proc_sysctl: update docs for __register_sysctl_table() Update the docs for __register_sysctl_table() to make it clear no child entries can be passed. When the child is true these are non-leaf entries on the ctl table and sysctl treats these as directories. The point to __register_sysctl_table() is to deal only with directories not part of the ctl table where thay may riside, to be simple and avoid recursion. While at it, hint towards using long on extra1 and extra2 later. Cc: stable@vger.kernel.org # v5.17 Cc: Christian Brauner Cc: Kefeng Wang Signed-off-by: Luis Chamberlain --- fs/proc/proc_sysctl.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5851eb5bc726..1df0beb50dbe 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1287,7 +1287,7 @@ static int insert_links(struct ctl_table_header *head) * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure + * @table: the top-level table structure without any child * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. @@ -1308,9 +1308,12 @@ static int insert_links(struct ctl_table_header *head) * proc_handler - the text handler routine (described below) * * extra1, extra2 - extra pointers usable by the proc handler routines + * XXX: we should eventually modify these to use long min / max [0] + * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org * * Leaf nodes in the sysctl tree will be represented by a single file - * under /proc; non-leaf nodes will be represented by directories. + * under /proc; non-leaf nodes (where child is not NULL) are not allowed, + * sysctl_check_table() verifies this. * * There must be a proc_handler routine for any terminal nodes. * Several default handlers are available to cover common cases - @@ -1352,7 +1355,7 @@ struct ctl_table_header *__register_sysctl_table( spin_lock(&sysctl_lock); dir = &set->dir; - /* Reference moved down the diretory tree get_subdir */ + /* Reference moved down the directory tree get_subdir */ dir->header.nreg++; spin_unlock(&sysctl_lock); @@ -1369,6 +1372,11 @@ struct ctl_table_header *__register_sysctl_table( if (namelen == 0) continue; + /* + * namelen ensures if name is "foo/bar/yay" only foo is + * registered first. We traverse as if using mkdir -p and + * return a ctl_dir for the last directory entry. + */ dir = get_subdir(dir, name, namelen); if (IS_ERR(dir)) goto fail; -- GitLab From b2f56e5574eac0cf9e3dc382bef010298cb1f1e9 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:17 -0800 Subject: [PATCH 2889/5631] proc_sysctl: move helper which creates required subdirectories Move the code which creates the subdirectories for a ctl table into a helper routine so to make it easier to review. Document the goal. This creates no functional changes. Reviewed-by: John Johansen Signed-off-by: Luis Chamberlain --- fs/proc/proc_sysctl.c | 56 ++++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 24 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 1df0beb50dbe..6b9b2694d430 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1283,6 +1283,35 @@ static int insert_links(struct ctl_table_header *head) return err; } +/* Find the directory for the ctl_table. If one is not found create it. */ +static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path) +{ + const char *name, *nextname; + + for (name = path; name; name = nextname) { + int namelen; + nextname = strchr(name, '/'); + if (nextname) { + namelen = nextname - name; + nextname++; + } else { + namelen = strlen(name); + } + if (namelen == 0) + continue; + + /* + * namelen ensures if name is "foo/bar/yay" only foo is + * registered first. We traverse as if using mkdir -p and + * return a ctl_dir for the last directory entry. + */ + dir = get_subdir(dir, name, namelen); + if (IS_ERR(dir)) + break; + } + return dir; +} + /** * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on @@ -1334,7 +1363,6 @@ struct ctl_table_header *__register_sysctl_table( { struct ctl_table_root *root = set->dir.header.root; struct ctl_table_header *header; - const char *name, *nextname; struct ctl_dir *dir; struct ctl_table *entry; struct ctl_node *node; @@ -1359,29 +1387,9 @@ struct ctl_table_header *__register_sysctl_table( dir->header.nreg++; spin_unlock(&sysctl_lock); - /* Find the directory for the ctl_table */ - for (name = path; name; name = nextname) { - int namelen; - nextname = strchr(name, '/'); - if (nextname) { - namelen = nextname - name; - nextname++; - } else { - namelen = strlen(name); - } - if (namelen == 0) - continue; - - /* - * namelen ensures if name is "foo/bar/yay" only foo is - * registered first. We traverse as if using mkdir -p and - * return a ctl_dir for the last directory entry. - */ - dir = get_subdir(dir, name, namelen); - if (IS_ERR(dir)) - goto fail; - } - + dir = sysctl_mkdir_p(dir, path); + if (IS_ERR(dir)) + goto fail; spin_lock(&sysctl_lock); if (insert_header(dir, header)) goto fail_put_dir_locked; -- GitLab From 228b09de936395ddd740df3522ea35ae934830d8 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:18 -0800 Subject: [PATCH 2890/5631] sysctl: clarify register_sysctl_init() base directory order Relatively new docs which I added which hinted the base directories needed to be created before is wrong, remove that incorrect comment. This has been hinted before by Eric twice already [0] [1], I had just not verified that until now. Now that I've verified that updates the docs to relax the context described. [0] https://lkml.kernel.org/r/875ys0azt8.fsf@email.froward.int.ebiederm.org [1] https://lkml.kernel.org/r/87ftbiud6s.fsf@x220.int.ebiederm.org Cc: stable@vger.kernel.org # v5.17 Cc: Christian Brauner Cc: Kefeng Wang Suggested-by: Eric W. Biederman Signed-off-by: Luis Chamberlain --- fs/proc/proc_sysctl.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 6b9b2694d430..15d5e02f1ec0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1440,10 +1440,7 @@ EXPORT_SYMBOL(register_sysctl); * register_sysctl() failing on init are extremely low, and so for both reasons * this function does not return any error as it is used by initialization code. * - * Context: Can only be called after your respective sysctl base path has been - * registered. So for instance, most base directories are registered early on - * init before init levels are processed through proc_sys_init() and - * sysctl_init_bases(). + * Context: if your base directory does not exist it will be created for you. */ void __init __register_sysctl_init(const char *path, struct ctl_table *table, const char *table_name) -- GitLab From 96200952abeb35c4407851bfcdcbc144cc0d027d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:19 -0800 Subject: [PATCH 2891/5631] apparmor: simplify sysctls with register_sysctl_init() Using register_sysctl_paths() is really only needed if you have subdirectories with entries. We can use the simple register_sysctl() instead. Acked-by: John Johansen Reviewed-by: Georgia Garcia Signed-off-by: Luis Chamberlain --- security/apparmor/lsm.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index d6cc4812ca53..47c7ec7e5a80 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1764,11 +1764,6 @@ static int apparmor_dointvec(struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } -static struct ctl_path apparmor_sysctl_path[] = { - { .procname = "kernel", }, - { } -}; - static struct ctl_table apparmor_sysctl_table[] = { { .procname = "unprivileged_userns_apparmor_policy", @@ -1790,8 +1785,7 @@ static struct ctl_table apparmor_sysctl_table[] = { static int __init apparmor_init_sysctl(void) { - return register_sysctl_paths(apparmor_sysctl_path, - apparmor_sysctl_table) ? 0 : -ENOMEM; + return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM; } #else static inline int apparmor_init_sysctl(void) -- GitLab From 5df5bdc3c4733a47a818576c13a7bfd0f0715124 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:20 -0800 Subject: [PATCH 2892/5631] loadpin: simplify sysctls use with register_sysctl() register_sysctl_paths() is not required, we can just use register_sysctl() with the required path specified. Reviewed-by: John Johansen Acked-by: Kees Cook Signed-off-by: Luis Chamberlain --- security/loadpin/loadpin.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index d73a281adf86..c971464b4ad5 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -52,12 +52,6 @@ static bool deny_reading_verity_digests; #endif #ifdef CONFIG_SYSCTL -static struct ctl_path loadpin_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "loadpin", }, - { } -}; - static struct ctl_table loadpin_sysctl_table[] = { { .procname = "enforce", @@ -262,7 +256,7 @@ static int __init loadpin_init(void) enforce ? "" : "not "); parse_exclude(); #ifdef CONFIG_SYSCTL - if (!register_sysctl_paths(loadpin_sysctl_path, loadpin_sysctl_table)) + if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table)) pr_notice("sysctl registration failed!\n"); #endif security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks), "loadpin"); -- GitLab From 98cfeb8d540aa009cd5cb973def265b6c44afa00 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:21 -0800 Subject: [PATCH 2893/5631] yama: simplfy sysctls with register_sysctl() register_sysctl_paths() is only need if you have directories with entries, simplify this by using register_sysctl(). Acked-by: Kees Cook Signed-off-by: Luis Chamberlain --- security/yama/yama_lsm.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 06e226166aab..90dd012b0db5 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -447,12 +447,6 @@ static int yama_dointvec_minmax(struct ctl_table *table, int write, static int max_scope = YAMA_SCOPE_NO_ATTACH; -static struct ctl_path yama_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "yama", }, - { } -}; - static struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", @@ -467,7 +461,7 @@ static struct ctl_table yama_sysctl_table[] = { }; static void __init yama_init_sysctl(void) { - if (!register_sysctl_paths(yama_sysctl_path, yama_sysctl_table)) + if (!register_sysctl("kernel/yama", yama_sysctl_table)) panic("Yama: sysctl registration failed.\n"); } #else -- GitLab From 02a6b455fb35d29620ceaa0ed053ae9846f875ca Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:22 -0800 Subject: [PATCH 2894/5631] seccomp: simplify sysctls with register_sysctl_init() register_sysctl_paths() is only needed if you have childs (directories) with entries. Just use register_sysctl_init() as it also does the kmemleak check for you. Acked-by: Kees Cook Signed-off-by: Luis Chamberlain --- kernel/seccomp.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index cebf26445f9e..d3e584065c7f 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -2368,12 +2368,6 @@ static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, return ret; } -static struct ctl_path seccomp_sysctl_path[] = { - { .procname = "kernel", }, - { .procname = "seccomp", }, - { } -}; - static struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", @@ -2392,14 +2386,7 @@ static struct ctl_table seccomp_sysctl_table[] = { static int __init seccomp_sysctl_init(void) { - struct ctl_table_header *hdr; - - hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); - if (!hdr) - pr_warn("sysctl registration failed\n"); - else - kmemleak_not_leak(hdr); - + register_sysctl_init("kernel/seccomp", seccomp_sysctl_table); return 0; } -- GitLab From adf11ea8725bd7874b4aec6990c5807abcd5a00d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:25 -0800 Subject: [PATCH 2895/5631] csky: simplify alignment sysctl registration Using register_sysctl_paths() is only required if we are using leafs with entries but all we are doing is creates leafs with just one leaf and then entries and register_sysctl_init() works well with that already. The 555 permission is already retained by the new_dir() proc sysctl directory creator. Signed-off-by: Luis Chamberlain --- arch/csky/abiv1/alignment.c | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index 2df115d0e210..b60259daed1b 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -332,22 +332,9 @@ static struct ctl_table alignment_tbl[5] = { {} }; -static struct ctl_table sysctl_table[2] = { - { - .procname = "csky_alignment", - .mode = 0555, - .child = alignment_tbl}, - {} -}; - -static struct ctl_path sysctl_path[2] = { - {.procname = "csky"}, - {} -}; - static int __init csky_alignment_init(void) { - register_sysctl_paths(sysctl_path, sysctl_table); + register_sysctl_init("csky/csky_alignment", alignment_tbl); return 0; } -- GitLab From ca674057f36bcc42eea3832b8de5d0582615a472 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:06 -0800 Subject: [PATCH 2896/5631] scsi: simplify sysctl registration with register_sysctl() register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl() can do the directory creation for you so just use that. Signed-off-by: Luis Chamberlain --- drivers/scsi/scsi_sysctl.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 7259704a7f52..7f0914ea168f 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -21,25 +21,11 @@ static struct ctl_table scsi_table[] = { { } }; -static struct ctl_table scsi_dir_table[] = { - { .procname = "scsi", - .mode = 0555, - .child = scsi_table }, - { } -}; - -static struct ctl_table scsi_root_table[] = { - { .procname = "dev", - .mode = 0555, - .child = scsi_dir_table }, - { } -}; - static struct ctl_table_header *scsi_table_header; int __init scsi_init_sysctl(void) { - scsi_table_header = register_sysctl_table(scsi_root_table); + scsi_table_header = register_sysctl("dev/scsi", scsi_table); if (!scsi_table_header) return -ENOMEM; return 0; -- GitLab From 525f23fe58b59b3a78a7044916aed9fe26918296 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:08 -0800 Subject: [PATCH 2897/5631] hv: simplify sysctl registration register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl() can do the directory creation for you so just use that. Signed-off-by: Luis Chamberlain Reviewed-by: Michael Kelley Reviewed-by: Wei Liu --- drivers/hv/vmbus_drv.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index d24dd65b33d4..229353f1e9c2 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1460,15 +1460,6 @@ static struct ctl_table hv_ctl_table[] = { {} }; -static struct ctl_table hv_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = hv_ctl_table - }, - {} -}; - /* * vmbus_bus_init -Main vmbus driver initialization routine. * @@ -1547,7 +1538,7 @@ static int vmbus_bus_init(void) * message recording won't be available in isolated * guests should the following registration fail. */ - hv_ctl_table_hdr = register_sysctl_table(hv_root_table); + hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table); if (!hv_ctl_table_hdr) pr_err("Hyper-V: sysctl table register error"); -- GitLab From 9adcf9d3d5c9ed6bb9d493b59594501f79ae3bed Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:09 -0800 Subject: [PATCH 2898/5631] md: simplify sysctl registration register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl() can do the directory creation for you so just use that. Signed-off-by: Luis Chamberlain Acked-by: Song Liu --- drivers/md/md.c | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 39e49e5d7182..0dc01f834b62 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -322,26 +322,6 @@ static struct ctl_table raid_table[] = { { } }; -static struct ctl_table raid_dir_table[] = { - { - .procname = "raid", - .maxlen = 0, - .mode = S_IRUGO|S_IXUGO, - .child = raid_table, - }, - { } -}; - -static struct ctl_table raid_root_table[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = raid_dir_table, - }, - { } -}; - static int start_readonly; /* @@ -9649,7 +9629,7 @@ static int __init md_init(void) mdp_major = ret; register_reboot_notifier(&md_notifier); - raid_table_header = register_sysctl_table(raid_root_table); + raid_table_header = register_sysctl("dev/raid", raid_table); md_geninit(); return 0; -- GitLab From 9f17a75b2d10ddd786b3b2c4fd732356de4f483e Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:46:12 -0800 Subject: [PATCH 2899/5631] xen: simplify sysctl registration for balloon register_sysctl_table() is a deprecated compatibility wrapper. register_sysctl_init() can do the directory creation for you so just use that. Signed-off-by: Luis Chamberlain Reviewed-by: Juergen Gross --- drivers/xen/balloon.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 617a7f4f07a8..586a1673459e 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -97,24 +97,6 @@ static struct ctl_table balloon_table[] = { { } }; -static struct ctl_table balloon_root[] = { - { - .procname = "balloon", - .mode = 0555, - .child = balloon_table, - }, - { } -}; - -static struct ctl_table xen_root[] = { - { - .procname = "xen", - .mode = 0555, - .child = balloon_root, - }, - { } -}; - #else #define xen_hotplug_unpopulated 0 #endif @@ -747,7 +729,7 @@ static int __init balloon_init(void) #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG set_online_page_callback(&xen_online_page); register_memory_notifier(&xen_memory_nb); - register_sysctl_table(xen_root); + register_sysctl_init("xen/balloon", balloon_table); #endif balloon_add_regions(); -- GitLab From 1dc8689e4cc651e21566e10206a84c4006e81fb1 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 13:00:16 -0800 Subject: [PATCH 2900/5631] proc_sysctl: enhance documentation Expand documentation to clarify: o that paths don't need to exist for the new API callers o clarify that we *require* callers to keep the memory of the table around during the lifetime of the sysctls o annotate routines we are trying to deprecate and later remove Cc: stable@vger.kernel.org # v5.17 Cc: Christian Brauner Cc: Kefeng Wang Signed-off-by: Luis Chamberlain --- fs/proc/proc_sysctl.c | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 15d5e02f1ec0..7ad07435828f 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1316,7 +1316,10 @@ static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path) * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure without any child + * @table: the top-level table structure without any child. This table + * should not be free'd after registration. So it should not be + * used on stack. It can either be a global or dynamically allocated + * by the caller and free'd later after sysctl unregistration. * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. @@ -1410,8 +1413,15 @@ struct ctl_table_header *__register_sysctl_table( /** * register_sysctl - register a sysctl table - * @path: The path to the directory the sysctl table is in. - * @table: the table structure + * @path: The path to the directory the sysctl table is in. If the path + * doesn't exist we will create it for you. + * @table: the table structure. The calller must ensure the life of the @table + * will be kept during the lifetime use of the syctl. It must not be freed + * until unregister_sysctl_table() is called with the given returned table + * with this registration. If your code is non modular then you don't need + * to call unregister_sysctl_table() and can instead use something like + * register_sysctl_init() which does not care for the result of the syctl + * registration. * * Register a sysctl table. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. @@ -1427,8 +1437,11 @@ EXPORT_SYMBOL(register_sysctl); /** * __register_sysctl_init() - register sysctl table to path - * @path: path name for sysctl base - * @table: This is the sysctl table that needs to be registered to the path + * @path: path name for sysctl base. If that path doesn't exist we will create + * it for you. + * @table: This is the sysctl table that needs to be registered to the path. + * The caller must ensure the life of the @table will be kept during the + * lifetime use of the sysctl. * @table_name: The name of sysctl table, only used for log printing when * registration fails * @@ -1570,6 +1583,7 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. + * We are slowly deprecating this call so avoid its use. * * See __register_sysctl_table for more details. */ @@ -1641,6 +1655,7 @@ struct ctl_table_header *__register_sysctl_paths( * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. + * We are slowly deprecating this caller so avoid future uses of it. * * See __register_sysctl_paths for more details. */ -- GitLab From 37b768ce3d23f79cef906aaf7427dd345b57f477 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 00:37:19 -0800 Subject: [PATCH 2901/5631] lockd: simplify two-level sysctl registration for nlm_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Reviewed-by: Jeff Layton Signed-off-by: Luis Chamberlain --- fs/lockd/svc.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a47303b2cba..bb94949bc223 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -510,24 +510,6 @@ static struct ctl_table nlm_sysctls[] = { { } }; -static struct ctl_table nlm_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nlm_sysctls, - }, - { } -}; - -static struct ctl_table nlm_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nlm_sysctl_dir, - }, - { } -}; - #endif /* CONFIG_SYSCTL */ /* @@ -644,7 +626,7 @@ static int __init init_nlm(void) #ifdef CONFIG_SYSCTL err = -ENOMEM; - nlm_sysctl_table = register_sysctl_table(nlm_sysctl_root); + nlm_sysctl_table = register_sysctl("fs/nfs", nlm_sysctls); if (nlm_sysctl_table == NULL) goto err_sysctl; #endif -- GitLab From d2235a705b48a1a86e2b8ea15091d83f7f80503c Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 00:39:18 -0800 Subject: [PATCH 2902/5631] nfs: simplify two-level sysctl registration for nfs4_cb_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Reviewed-by: Jeff Layton Signed-off-by: Luis Chamberlain --- fs/nfs/nfs4sysctl.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index c394e4447100..e776200e9a11 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -37,27 +37,10 @@ static struct ctl_table nfs4_cb_sysctls[] = { { } }; -static struct ctl_table nfs4_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs4_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs4_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs4_cb_sysctl_dir, - }, - { } -}; - int nfs4_register_sysctl(void) { - nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root); + nfs4_callback_sysctl_table = register_sysctl("fs/nfs", + nfs4_cb_sysctls); if (nfs4_callback_sysctl_table == NULL) return -ENOMEM; return 0; -- GitLab From a2189b77676b256b6606612fd68ed493f7080929 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 00:40:35 -0800 Subject: [PATCH 2903/5631] nfs: simplify two-level sysctl registration for nfs_cb_sysctls There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Reviewed-by: Jeff Layton Signed-off-by: Luis Chamberlain --- fs/nfs/sysctl.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index 7aea195ddb35..f39e2089bc4c 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -32,27 +32,9 @@ static struct ctl_table nfs_cb_sysctls[] = { { } }; -static struct ctl_table nfs_cb_sysctl_dir[] = { - { - .procname = "nfs", - .mode = 0555, - .child = nfs_cb_sysctls, - }, - { } -}; - -static struct ctl_table nfs_cb_sysctl_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = nfs_cb_sysctl_dir, - }, - { } -}; - int nfs_register_sysctl(void) { - nfs_callback_sysctl_table = register_sysctl_table(nfs_cb_sysctl_root); + nfs_callback_sysctl_table = register_sysctl("fs/nfs", nfs_cb_sysctls); if (nfs_callback_sysctl_table == NULL) return -ENOMEM; return 0; -- GitLab From f5d2b92c85d420d0020163b9ad153962d8f9fcc7 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 00:42:26 -0800 Subject: [PATCH 2904/5631] xfs: simplify two-level sysctl registration for xfs_table There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Reviewed-by: Dave Chinner Signed-off-by: Luis Chamberlain --- fs/xfs/xfs_sysctl.c | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index 546a6cd96729..fade33735393 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -210,28 +210,10 @@ static struct ctl_table xfs_table[] = { {} }; -static struct ctl_table xfs_dir_table[] = { - { - .procname = "xfs", - .mode = 0555, - .child = xfs_table - }, - {} -}; - -static struct ctl_table xfs_root_table[] = { - { - .procname = "fs", - .mode = 0555, - .child = xfs_dir_table - }, - {} -}; - int xfs_sysctl_register(void) { - xfs_table_header = register_sysctl_table(xfs_root_table); + xfs_table_header = register_sysctl("fs/xfs", xfs_table); if (!xfs_table_header) return -ENOMEM; return 0; -- GitLab From 3d379b8d0de0492e86b93a1b8cd07403825fe23d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 13:46:23 -0800 Subject: [PATCH 2905/5631] fs/cachefiles: simplify one-level sysctl registration for cachefiles_sysctls There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain --- fs/cachefiles/error_inject.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c index 58f8aec964e4..18de8a876b02 100644 --- a/fs/cachefiles/error_inject.c +++ b/fs/cachefiles/error_inject.c @@ -22,18 +22,9 @@ static struct ctl_table cachefiles_sysctls[] = { {} }; -static struct ctl_table cachefiles_sysctls_root[] = { - { - .procname = "cachefiles", - .mode = 0555, - .child = cachefiles_sysctls, - }, - {} -}; - int __init cachefiles_register_error_injection(void) { - cachefiles_sysctl = register_sysctl_table(cachefiles_sysctls_root); + cachefiles_sysctl = register_sysctl("cachefiles", cachefiles_sysctls); if (!cachefiles_sysctl) return -ENOMEM; return 0; -- GitLab From 1119aaa823e6cc35f2e8c8793cfa58d923a15c1b Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 13:48:17 -0800 Subject: [PATCH 2906/5631] coda: simplify one-level sysctl registration for coda_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Acked-by: Jan Harkes Signed-off-by: Luis Chamberlain --- fs/coda/sysctl.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index fda3b702b1c5..a247c14aaab7 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -39,19 +39,10 @@ static struct ctl_table coda_table[] = { {} }; -static struct ctl_table fs_table[] = { - { - .procname = "coda", - .mode = 0555, - .child = coda_table - }, - {} -}; - void coda_sysctl_init(void) { if ( !fs_table_header ) - fs_table_header = register_sysctl_table(fs_table); + fs_table_header = register_sysctl("coda", coda_table); } void coda_sysctl_clean(void) -- GitLab From 02148ff371b276d664780de6d1f52d52074c3e25 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 13:49:40 -0800 Subject: [PATCH 2907/5631] ntfs: simplfy one-level sysctl registration for ntfs_sysctls There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain --- fs/ntfs/sysctl.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c index a030d00af90c..174fe536a1c0 100644 --- a/fs/ntfs/sysctl.c +++ b/fs/ntfs/sysctl.c @@ -31,16 +31,6 @@ static struct ctl_table ntfs_sysctls[] = { {} }; -/* Define the parent directory /proc/sys/fs. */ -static struct ctl_table sysctls_root[] = { - { - .procname = "fs", - .mode = 0555, - .child = ntfs_sysctls - }, - {} -}; - /* Storage for the sysctls header. */ static struct ctl_table_header *sysctls_root_table; @@ -54,7 +44,7 @@ int ntfs_sysctl(int add) { if (add) { BUG_ON(sysctls_root_table); - sysctls_root_table = register_sysctl_table(sysctls_root); + sysctls_root_table = register_sysctl("fs", ntfs_sysctls); if (!sysctls_root_table) return -ENOMEM; } else { -- GitLab From 3d51cd8ea3c832c50c22e46354ac89e0964ea2d8 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 01:24:10 -0800 Subject: [PATCH 2908/5631] utsname: simplify one-level sysctl registration for uts_kern_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Reviewed-by: Christian Brauner Signed-off-by: Luis Chamberlain --- kernel/utsname_sysctl.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index f50398cb790d..019e3a1566cf 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -123,15 +123,6 @@ static struct ctl_table uts_kern_table[] = { {} }; -static struct ctl_table uts_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = uts_kern_table, - }, - {} -}; - #ifdef CONFIG_PROC_SYSCTL /* * Notify userspace about a change in a certain entry of uts_kern_table, @@ -147,7 +138,7 @@ void uts_proc_notify(enum uts_proc proc) static int __init utsname_sysctl_init(void) { - register_sysctl_table(uts_root_table); + register_sysctl("kernel", uts_kern_table); return 0; } -- GitLab From 03860ef038e6435c5ea2bda24dc5698e0da60ebc Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 01:10:11 -0800 Subject: [PATCH 2909/5631] ia64: simplify one-level sysctl registration for kdump_ctl_table There is no need to declare an extra tables to just create directory, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain --- arch/ia64/kernel/crash.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 76730f34685c..88b3ce3e66cd 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -234,15 +234,6 @@ static struct ctl_table kdump_ctl_table[] = { }, { } }; - -static struct ctl_table sys_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kdump_ctl_table, - }, - { } -}; #endif static int @@ -257,7 +248,7 @@ machine_crash_setup(void) if((ret = register_die_notifier(&kdump_init_notifier_nb)) != 0) return ret; #ifdef CONFIG_SYSCTL - register_sysctl_table(sys_table); + register_sysctl("kernel", kdump_ctl_table); #endif return 0; } -- GitLab From ca14ccf310ee9d575c3bacbf1d61d9640d0025b6 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 00:50:50 -0800 Subject: [PATCH 2910/5631] arm: simplify two-level sysctl registration for ctl_isa_vars There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain --- arch/arm/kernel/isa.c | 18 +----------------- 1 file changed, 1 insertion(+), 17 deletions(-) diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index d8a509c5d5bd..20218876bef2 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -40,27 +40,11 @@ static struct ctl_table ctl_isa_vars[4] = { static struct ctl_table_header *isa_sysctl_header; -static struct ctl_table ctl_isa[2] = { - { - .procname = "isa", - .mode = 0555, - .child = ctl_isa_vars, - }, {} -}; - -static struct ctl_table ctl_bus[2] = { - { - .procname = "bus", - .mode = 0555, - .child = ctl_isa, - }, {} -}; - void __init register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int portshift) { isa_membase = membase; isa_portbase = portbase; isa_portshift = portshift; - isa_sysctl_header = register_sysctl_table(ctl_bus); + isa_sysctl_header = register_sysctl("bus/isa", ctl_isa_vars); } -- GitLab From 8cbc82f3ec0d58961cf9c1e5d99e56741f4bf134 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 20 Mar 2023 15:40:10 +0800 Subject: [PATCH 2911/5631] mm: memory-failure: Move memory failure sysctls to its own file The sysctl_memory_failure_early_kill and memory_failure_recovery are only used in memory-failure.c, move them to its own file. Acked-by: Naoya Horiguchi Signed-off-by: Kefeng Wang [mcgrof: fix by adding empty ctl entry, this caused a crash] Signed-off-by: Luis Chamberlain --- include/linux/mm.h | 2 -- kernel/sysctl.c | 20 -------------------- mm/memory-failure.c | 36 ++++++++++++++++++++++++++++++++++-- 3 files changed, 34 insertions(+), 24 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..98da268b834a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3442,8 +3442,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int sysctl_memory_failure_early_kill; -extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ce0297acf97c..0a8a3c9c82e4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2350,26 +2350,6 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec, .extra1 = SYSCTL_ZERO, }, -#endif -#ifdef CONFIG_MEMORY_FAILURE - { - .procname = "memory_failure_early_kill", - .data = &sysctl_memory_failure_early_kill, - .maxlen = sizeof(sysctl_memory_failure_early_kill), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "memory_failure_recovery", - .data = &sysctl_memory_failure_recovery, - .maxlen = sizeof(sysctl_memory_failure_recovery), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { .procname = "user_reserve_kbytes", diff --git a/mm/memory-failure.c b/mm/memory-failure.c index fae9baf3be16..10e60b6b2447 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -62,13 +62,14 @@ #include #include #include +#include #include "swap.h" #include "internal.h" #include "ras/ras_event.h" -int sysctl_memory_failure_early_kill __read_mostly = 0; +static int sysctl_memory_failure_early_kill __read_mostly; -int sysctl_memory_failure_recovery __read_mostly = 1; +static int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); @@ -122,6 +123,37 @@ const struct attribute_group memory_failure_attr_group = { .attrs = memory_failure_attr, }; +#ifdef CONFIG_SYSCTL +static struct ctl_table memory_failure_table[] = { + { + .procname = "memory_failure_early_kill", + .data = &sysctl_memory_failure_early_kill, + .maxlen = sizeof(sysctl_memory_failure_early_kill), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "memory_failure_recovery", + .data = &sysctl_memory_failure_recovery, + .maxlen = sizeof(sysctl_memory_failure_recovery), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static int __init memory_failure_sysctl_init(void) +{ + register_sysctl_init("vm", memory_failure_table); + return 0; +} +late_initcall(memory_failure_sysctl_init); +#endif /* CONFIG_SYSCTL */ + /* * Return values: * 1: the page is dissolved (if needed) and taken off from buddy, -- GitLab From 48fe8ab8d5a39c7bc49cb41d0ad92c75f48a9550 Mon Sep 17 00:00:00 2001 From: Minghao Chi Date: Tue, 28 Mar 2023 14:46:28 +0800 Subject: [PATCH 2912/5631] mm: compaction: move compaction sysctl to its own file This moves all compaction sysctls to its own file. Move sysctl to where the functionality truly belongs to improve readability, reduce merge conflicts, and facilitate maintenance. I use x86_defconfig and linux-next-20230327 branch $ make defconfig;make all -jn CONFIG_COMPACTION=y add/remove: 1/0 grow/shrink: 1/1 up/down: 350/-256 (94) Function old new delta vm_compaction - 320 +320 kcompactd_init 180 210 +30 vm_table 2112 1856 -256 Total: Before=21119987, After=21120081, chg +0.00% Despite the addition of 94 bytes the patch still seems a worthwile cleanup. Link: https://lore.kernel.org/lkml/067f7347-ba10-5405-920c-0f5f985c84f4@suse.cz/ Signed-off-by: Minghao Chi Acked-by: Vlastimil Babka Signed-off-by: Luis Chamberlain --- include/linux/compaction.h | 7 ---- kernel/sysctl.c | 59 -------------------------- mm/compaction.c | 84 ++++++++++++++++++++++++++++++++------ 3 files changed, 72 insertions(+), 78 deletions(-) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 52a9ff65faee..a6e512cfb670 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern unsigned int sysctl_compaction_proactiveness; -extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); -extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, - int write, void *buffer, size_t *length, loff_t *ppos); -extern int sysctl_extfrag_threshold; -extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 0a8a3c9c82e4..bfe53e835524 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include @@ -746,27 +745,6 @@ int proc_dointvec(struct ctl_table *table, int write, void *buffer, return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); } -#ifdef CONFIG_COMPACTION -static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, - int write, void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret, old; - - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - old = *(int *)table->data; - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret) - return ret; - if (old != *(int *)table->data) - pr_warn_once("sysctl attribute %s changed by %s[%d]\n", - table->procname, current->comm, - task_pid_nr(current)); - return ret; -} -#endif - /** * proc_douintvec - read a vector of unsigned integers * @table: the sysctl table @@ -2157,43 +2135,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_FOUR, }, -#ifdef CONFIG_COMPACTION - { - .procname = "compact_memory", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0200, - .proc_handler = sysctl_compaction_handler, - }, - { - .procname = "compaction_proactiveness", - .data = &sysctl_compaction_proactiveness, - .maxlen = sizeof(sysctl_compaction_proactiveness), - .mode = 0644, - .proc_handler = compaction_proactiveness_sysctl_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "extfrag_threshold", - .data = &sysctl_extfrag_threshold, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_THOUSAND, - }, - { - .procname = "compact_unevictable_allowed", - .data = &sysctl_compact_unevictable_allowed, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_warn_RT_change, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - -#endif /* CONFIG_COMPACTION */ { .procname = "min_free_kbytes", .data = &min_free_kbytes, diff --git a/mm/compaction.c b/mm/compaction.c index 5a9501e0ae01..f2ddfb1140e2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1716,7 +1716,14 @@ typedef enum { * Allow userspace to control policy on scanning the unevictable LRU for * compactable pages. */ -int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; +static int sysctl_compact_unevictable_allowed __read_mostly = CONFIG_COMPACT_UNEVICTABLE_DEFAULT; +/* + * Tunable for proactive compaction. It determines how + * aggressively the kernel should compact memory in the + * background. It takes values in the range [0, 100]. + */ +static unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +static int sysctl_extfrag_threshold = 500; static inline void update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) @@ -2572,8 +2579,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, return ret; } -int sysctl_extfrag_threshold = 500; - /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation * @gfp_mask: The GFP mask of the current allocation @@ -2730,14 +2735,7 @@ static void compact_nodes(void) compact_node(nid); } -/* - * Tunable for proactive compaction. It determines how - * aggressively the kernel should compact memory in the - * background. It takes values in the range [0, 100]. - */ -unsigned int __read_mostly sysctl_compaction_proactiveness = 20; - -int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, +static int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int rc, nid; @@ -2767,7 +2765,7 @@ int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory */ -int sysctl_compaction_handler(struct ctl_table *table, int write, +static int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { if (write) @@ -3063,6 +3061,65 @@ static int kcompactd_cpu_online(unsigned int cpu) return 0; } +static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, + int write, void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, old; + + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + old = *(int *)table->data; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret) + return ret; + if (old != *(int *)table->data) + pr_warn_once("sysctl attribute %s changed by %s[%d]\n", + table->procname, current->comm, + task_pid_nr(current)); + return ret; +} + +#ifdef CONFIG_SYSCTL +static struct ctl_table vm_compaction[] = { + { + .procname = "compact_memory", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = sysctl_compaction_handler, + }, + { + .procname = "compaction_proactiveness", + .data = &sysctl_compaction_proactiveness, + .maxlen = sizeof(sysctl_compaction_proactiveness), + .mode = 0644, + .proc_handler = compaction_proactiveness_sysctl_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_HUNDRED, + }, + { + .procname = "extfrag_threshold", + .data = &sysctl_extfrag_threshold, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE_THOUSAND, + }, + { + .procname = "compact_unevictable_allowed", + .data = &sysctl_compact_unevictable_allowed, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_warn_RT_change, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; +#endif + static int __init kcompactd_init(void) { int nid; @@ -3078,6 +3135,9 @@ static int __init kcompactd_init(void) for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); +#ifdef CONFIG_SYSCTL + register_sysctl_init("vm", vm_compaction); +#endif return 0; } subsys_initcall(kcompactd_init) -- GitLab From b3f312c4815d7acf6c7f88f921544626c31bd24a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 29 Mar 2023 10:02:41 +0200 Subject: [PATCH 2913/5631] mm: compaction: remove incorrect #ifdef checks Without CONFIG_SYSCTL, the compiler warns about a few unused functions: mm/compaction.c:3076:12: error: 'proc_dointvec_minmax_warn_RT_change' defined but not used [-Werror=unused-function] mm/compaction.c:2780:12: error: 'sysctl_compaction_handler' defined but not used [-Werror=unused-function] mm/compaction.c:2750:12: error: 'compaction_proactiveness_sysctl_handler' defined but not used [-Werror=unused-function] The #ifdef is actually not necessary here, as the alternative register_sysctl_init() stub function does not use its argument, which lets the compiler drop the rest implicitly, while avoiding the warning. Fixes: c521126610c3 ("mm: compaction: move compaction sysctl to its own file") Signed-off-by: Arnd Bergmann Signed-off-by: Luis Chamberlain --- mm/compaction.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index f2ddfb1140e2..9ff71239b1fc 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -3080,7 +3080,6 @@ static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, return ret; } -#ifdef CONFIG_SYSCTL static struct ctl_table vm_compaction[] = { { .procname = "compact_memory", @@ -3118,7 +3117,6 @@ static struct ctl_table vm_compaction[] = { }, { } }; -#endif static int __init kcompactd_init(void) { @@ -3135,9 +3133,7 @@ static int __init kcompactd_init(void) for_each_node_state(nid, N_MEMORY) kcompactd_run(nid); -#ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_compaction); -#endif return 0; } subsys_initcall(kcompactd_init) -- GitLab From e3184de9d46c2eebdb776face2e2662c6733331d Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 31 Mar 2023 16:45:02 +0800 Subject: [PATCH 2914/5631] fs: fix sysctls.c built 'obj-$(CONFIG_SYSCTL) += sysctls.o' must be moved after "obj-y :=", or it won't be built as it is overwrited. Note that there is nothing that is going to break by linking sysctl.o later, we were just being way to cautious and patches have been updated to reflect these considerations and sent for stable as well with the whole "base" stuff needing to be linked prior to child sysctl tables that use that directory. All of the kernel sysctl APIs always share the same directory, and races against using it should end up re-using the same single created directory. And so something we can do eventually is do away with all the base stuff. For now it's fine, it's not creating an issue. It is just a bit pedantic and careful. Fixes: ab171b952c6e ("fs: move namespace sysctls and declare fs base directory") Cc: stable@vger.kernel.org # v5.17 Cc: Christian Brauner Cc: Kefeng Wang Signed-off-by: Kefeng Wang [mcgrof: enhanced commit log for stable criteria and clarify base stuff ] Signed-off-by: Luis Chamberlain --- fs/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/Makefile b/fs/Makefile index 05f89b5c962f..8d4736fcc766 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -6,7 +6,6 @@ # Rewritten to use lists instead of if-statements. # -obj-$(CONFIG_SYSCTL) += sysctls.o obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ @@ -50,7 +49,7 @@ obj-$(CONFIG_FS_MBCACHE) += mbcache.o obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_COREDUMP) += coredump.o -obj-$(CONFIG_SYSCTL) += drop_caches.o +obj-$(CONFIG_SYSCTL) += drop_caches.o sysctls.o obj-$(CONFIG_FHANDLE) += fhandle.o obj-y += iomap/ -- GitLab From 066ff7dba151a725f38bdb7606e263a7e884f16c Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:12 +0000 Subject: [PATCH 2915/5631] soc: fujitsu: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- drivers/soc/fujitsu/a64fx-diag.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soc/fujitsu/a64fx-diag.c b/drivers/soc/fujitsu/a64fx-diag.c index d87f348427bf..524fbfeb94e3 100644 --- a/drivers/soc/fujitsu/a64fx-diag.c +++ b/drivers/soc/fujitsu/a64fx-diag.c @@ -149,6 +149,5 @@ static struct platform_driver a64fx_diag_driver = { module_platform_driver(a64fx_diag_driver); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Hitomi Hasegawa "); MODULE_DESCRIPTION("A64FX diag driver"); -- GitLab From 9e0d360fe059ddf6b90ab3baae6eae06a7cc3f01 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:13 +0000 Subject: [PATCH 2916/5631] mfd: altera-sysmgr: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Thor Thayer Cc: Lee Jones Signed-off-by: Luis Chamberlain --- drivers/mfd/altera-sysmgr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/altera-sysmgr.c b/drivers/mfd/altera-sysmgr.c index 5d3715a28b28..af205813b281 100644 --- a/drivers/mfd/altera-sysmgr.c +++ b/drivers/mfd/altera-sysmgr.c @@ -198,4 +198,3 @@ module_exit(altr_sysmgr_exit); MODULE_AUTHOR("Thor Thayer <>"); MODULE_DESCRIPTION("SOCFPGA System Manager driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 655cc3a64d5e8c162652eb193ed232b28e8d02a7 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:13 +0000 Subject: [PATCH 2917/5631] irqchip/al-fic: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Talel Shenhar Cc: Thomas Gleixner Cc: Marc Zyngier Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-al-fic.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/irqchip/irq-al-fic.c b/drivers/irqchip/irq-al-fic.c index 886de028a901..dfb761e86c9c 100644 --- a/drivers/irqchip/irq-al-fic.c +++ b/drivers/irqchip/irq-al-fic.c @@ -26,7 +26,6 @@ MODULE_AUTHOR("Talel Shenhar"); MODULE_DESCRIPTION("Amazon's Annapurna Labs Interrupt Controller Driver"); -MODULE_LICENSE("GPL v2"); enum al_fic_state { AL_FIC_UNCONFIGURED = 0, -- GitLab From 591396b933734ee7f1628156ccefdbd4adcde04d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:14 +0000 Subject: [PATCH 2918/5631] bus: arm-integrator-lm: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Linus Walleij Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/bus/arm-integrator-lm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/bus/arm-integrator-lm.c b/drivers/bus/arm-integrator-lm.c index 2344d560b144..b715c8ab36e8 100644 --- a/drivers/bus/arm-integrator-lm.c +++ b/drivers/bus/arm-integrator-lm.c @@ -126,4 +126,3 @@ static struct platform_driver integrator_ap_lm_driver = { module_platform_driver(integrator_ap_lm_driver); MODULE_AUTHOR("Linus Walleij "); MODULE_DESCRIPTION("Integrator AP Logical Module driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 9016c09e90157c50b50f6e536a1ae9c01f1ea796 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:14 +0000 Subject: [PATCH 2919/5631] drivers/perf: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Will Deacon Cc: Mark Rutland Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/perf/apple_m1_cpu_pmu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c index 979a7c2b4f56..7123beeb992f 100644 --- a/drivers/perf/apple_m1_cpu_pmu.c +++ b/drivers/perf/apple_m1_cpu_pmu.c @@ -581,4 +581,3 @@ static struct platform_driver m1_pmu_driver = { }; module_platform_driver(m1_pmu_driver); -MODULE_LICENSE("GPL v2"); -- GitLab From 0ba3f7977eb74edebcd06d93eb83bb872fe5c351 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:15 +0000 Subject: [PATCH 2920/5631] ARM: tegra: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Thierry Reding Cc: Jonathan Hunter Cc: linux-tegra@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/amba/tegra-ahb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/amba/tegra-ahb.c b/drivers/amba/tegra-ahb.c index 0b2c20fddb7c..c0e8b765522d 100644 --- a/drivers/amba/tegra-ahb.c +++ b/drivers/amba/tegra-ahb.c @@ -285,5 +285,4 @@ module_platform_driver(tegra_ahb_driver); MODULE_AUTHOR("Hiroshi DOYU "); MODULE_DESCRIPTION("Tegra AHB driver"); -MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:" DRV_NAME); -- GitLab From b9ef12eaa0039f383099c7b3a4798c5090679714 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:16 +0000 Subject: [PATCH 2921/5631] pinctrl: actions: remove MODULE_LICENSE in non-modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: "Andreas Färber" Cc: Manivannan Sadhasivam Cc: Linus Walleij Cc: linux-arm-kernel@lists.infradead.org Cc: linux-actions@lists.infradead.org Cc: linux-gpio@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/actions/pinctrl-s500.c | 1 - drivers/pinctrl/actions/pinctrl-s700.c | 1 - drivers/pinctrl/actions/pinctrl-s900.c | 1 - 3 files changed, 3 deletions(-) diff --git a/drivers/pinctrl/actions/pinctrl-s500.c b/drivers/pinctrl/actions/pinctrl-s500.c index ced778079b76..3bed4b8d08e6 100644 --- a/drivers/pinctrl/actions/pinctrl-s500.c +++ b/drivers/pinctrl/actions/pinctrl-s500.c @@ -1724,4 +1724,3 @@ module_exit(s500_pinctrl_exit); MODULE_AUTHOR("Actions Semi Inc."); MODULE_AUTHOR("Cristian Ciocaltea "); MODULE_DESCRIPTION("Actions Semi S500 SoC Pinctrl Driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/pinctrl/actions/pinctrl-s700.c b/drivers/pinctrl/actions/pinctrl-s700.c index fd00940a5799..c2b472660e53 100644 --- a/drivers/pinctrl/actions/pinctrl-s700.c +++ b/drivers/pinctrl/actions/pinctrl-s700.c @@ -1908,4 +1908,3 @@ module_exit(s700_pinctrl_exit); MODULE_AUTHOR("Actions Semi Inc."); MODULE_DESCRIPTION("Actions Semi S700 Soc Pinctrl Driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/pinctrl/actions/pinctrl-s900.c b/drivers/pinctrl/actions/pinctrl-s900.c index 811249a8011e..8638d3007cd9 100644 --- a/drivers/pinctrl/actions/pinctrl-s900.c +++ b/drivers/pinctrl/actions/pinctrl-s900.c @@ -1827,4 +1827,3 @@ module_exit(s900_pinctrl_exit); MODULE_AUTHOR("Actions Semi Inc."); MODULE_AUTHOR("Manivannan Sadhasivam "); MODULE_DESCRIPTION("Actions Semi S900 SoC Pinctrl Driver"); -MODULE_LICENSE("GPL"); -- GitLab From 87efd0d382aab4b9c0ec056159b7574960327505 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:16 +0000 Subject: [PATCH 2922/5631] soc: apple: apple-pmgr-pwrstate: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Eric Curtin Acked-by: Sven Peter Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Hector Martin Cc: Sven Peter Cc: Philipp Zabel Cc: asahi@lists.linux.dev Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/soc/apple/apple-pmgr-pwrstate.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soc/apple/apple-pmgr-pwrstate.c b/drivers/soc/apple/apple-pmgr-pwrstate.c index a3e2bc1d2686..d62a776c89a1 100644 --- a/drivers/soc/apple/apple-pmgr-pwrstate.c +++ b/drivers/soc/apple/apple-pmgr-pwrstate.c @@ -322,6 +322,5 @@ static struct platform_driver apple_pmgr_ps_driver = { MODULE_AUTHOR("Hector Martin "); MODULE_DESCRIPTION("PMGR power state driver for Apple SoCs"); -MODULE_LICENSE("GPL v2"); module_platform_driver(apple_pmgr_ps_driver); -- GitLab From f6f5f91cc89a1152c7b6def226fc8b84e624b31b Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:17 +0000 Subject: [PATCH 2923/5631] clk: bm1880: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Stephen Boyd Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Manivannan Sadhasivam Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-arm-kernel@lists.infradead.org Cc: linux-clk@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/clk/clk-bm1880.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/clk-bm1880.c b/drivers/clk/clk-bm1880.c index fad78a22218e..2a19e50fff68 100644 --- a/drivers/clk/clk-bm1880.c +++ b/drivers/clk/clk-bm1880.c @@ -949,4 +949,3 @@ module_platform_driver(bm1880_clk_driver); MODULE_AUTHOR("Manivannan Sadhasivam "); MODULE_DESCRIPTION("Clock driver for Bitmain BM1880 SoC"); -MODULE_LICENSE("GPL v2"); -- GitLab From 1739e4664e9fe8a1bfe23e2e74adc3c244639336 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:18 +0000 Subject: [PATCH 2924/5631] bus: ixp4xx: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Linus Walleij Cc: Imre Kaloz Cc: Krzysztof Halasa Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/bus/intel-ixp4xx-eb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/bus/intel-ixp4xx-eb.c b/drivers/bus/intel-ixp4xx-eb.c index 91db001eb69a..f5ba6bee6fd8 100644 --- a/drivers/bus/intel-ixp4xx-eb.c +++ b/drivers/bus/intel-ixp4xx-eb.c @@ -423,4 +423,3 @@ static struct platform_driver ixp4xx_exp_driver = { module_platform_driver(ixp4xx_exp_driver); MODULE_AUTHOR("Linus Walleij "); MODULE_DESCRIPTION("Intel IXP4xx external bus driver"); -MODULE_LICENSE("GPL"); -- GitLab From 1095ebc8d42bf5b35dc556b7f86f698c25d39923 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:19 +0000 Subject: [PATCH 2925/5631] pinctrl: nuvoton: npcm7xx: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Avi Fishman Cc: Tomer Maimon Cc: Tali Perry Cc: Linus Walleij Cc: openbmc@lists.ozlabs.org Cc: linux-gpio@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c index ff5bcea172e8..4e12b3768d65 100644 --- a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c +++ b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c @@ -2046,7 +2046,6 @@ static int __init npcm7xx_pinctrl_register(void) } arch_initcall(npcm7xx_pinctrl_register); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("jordan_hargrave@dell.com"); MODULE_AUTHOR("tomer.maimon@nuvoton.com"); MODULE_DESCRIPTION("Nuvoton NPCM7XX Pinctrl and GPIO driver"); -- GitLab From c592acf5a7522e8746c801734c42d64b19f733da Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:19 +0000 Subject: [PATCH 2926/5631] bus: qcom: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Andy Gross Cc: Bjorn Andersson Cc: linux-arm-msm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/bus/qcom-ebi2.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/bus/qcom-ebi2.c b/drivers/bus/qcom-ebi2.c index 663c82749222..c1fef1b4bd89 100644 --- a/drivers/bus/qcom-ebi2.c +++ b/drivers/bus/qcom-ebi2.c @@ -403,4 +403,3 @@ static struct platform_driver qcom_ebi2_driver = { module_platform_driver(qcom_ebi2_driver); MODULE_AUTHOR("Linus Walleij "); MODULE_DESCRIPTION("Qualcomm EBI2 driver"); -MODULE_LICENSE("GPL"); -- GitLab From e86c8a2d1b55cb3a69bdbc86bb8101cdd3067f3f Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:20 +0000 Subject: [PATCH 2927/5631] bus: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Andy Gross Cc: Bjorn Andersson Cc: Philipp Zabel Cc: linux-arm-msm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/bus/qcom-ssc-block-bus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/bus/qcom-ssc-block-bus.c b/drivers/bus/qcom-ssc-block-bus.c index eedeb29a5ff3..3fef18a43c01 100644 --- a/drivers/bus/qcom-ssc-block-bus.c +++ b/drivers/bus/qcom-ssc-block-bus.c @@ -386,4 +386,3 @@ module_platform_driver(qcom_ssc_block_bus_driver); MODULE_DESCRIPTION("A driver for handling the init sequence needed for accessing the SSC block on (some) qcom SoCs over AHB"); MODULE_AUTHOR("Michael Srba "); -MODULE_LICENSE("GPL v2"); -- GitLab From bb798d3061f17d5139d69eddb8c5f8ee8c4f4f86 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:21 +0000 Subject: [PATCH 2928/5631] EDAC, altera: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Dinh Nguyen Cc: Borislav Petkov Cc: Tony Luck Cc: linux-edac@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/edac/altera_edac.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index e7e8e624a436..ba325d4c5e83 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -2226,6 +2226,5 @@ static struct platform_driver altr_edac_a10_driver = { }; module_platform_driver(altr_edac_a10_driver); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Thor Thayer"); MODULE_DESCRIPTION("EDAC Driver for Altera Memories"); -- GitLab From 06538a04efadf5231f6e02e786126a7a9d6ee647 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:21 +0000 Subject: [PATCH 2929/5631] power: reset: keystone-reset: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Santosh Shilimkar Cc: Sebastian Reichel Cc: linux-pm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/power/reset/keystone-reset.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/power/reset/keystone-reset.c b/drivers/power/reset/keystone-reset.c index c720112db704..83a4e1c9bf94 100644 --- a/drivers/power/reset/keystone-reset.c +++ b/drivers/power/reset/keystone-reset.c @@ -169,5 +169,4 @@ module_platform_driver(rsctrl_driver); MODULE_AUTHOR("Ivan Khoronzhuk "); MODULE_DESCRIPTION("Texas Instruments keystone reset driver"); -MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:" KBUILD_MODNAME); -- GitLab From 6d398e69b9723cef9d9b1a735be34aef56e9e3a7 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:22 +0000 Subject: [PATCH 2930/5631] video: fbdev: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Helge Deller Cc: linux-arm-kernel@lists.infradead.org Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Signed-off-by: Luis Chamberlain --- drivers/video/fbdev/wm8505fb.c | 1 - drivers/video/fbdev/wmt_ge_rops.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/video/fbdev/wm8505fb.c b/drivers/video/fbdev/wm8505fb.c index 8f4d674fa0d0..2a2997c647f7 100644 --- a/drivers/video/fbdev/wm8505fb.c +++ b/drivers/video/fbdev/wm8505fb.c @@ -407,5 +407,4 @@ module_platform_driver(wm8505fb_driver); MODULE_AUTHOR("Ed Spiridonov "); MODULE_DESCRIPTION("Framebuffer driver for WMT WM8505"); -MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, wmt_dt_ids); diff --git a/drivers/video/fbdev/wmt_ge_rops.c b/drivers/video/fbdev/wmt_ge_rops.c index 42255d27a1db..c207fd917dce 100644 --- a/drivers/video/fbdev/wmt_ge_rops.c +++ b/drivers/video/fbdev/wmt_ge_rops.c @@ -170,5 +170,4 @@ module_platform_driver(wmt_ge_rops_driver); MODULE_AUTHOR("Alexey Charkov "); MODULE_DESCRIPTION("Accelerators for raster operations using " "WonderMedia Graphics Engine"); -MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, wmt_dt_ids); -- GitLab From 8a8dd17d2a2d86b23c7cb970ee0ff8f47f164d4b Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:22 +0000 Subject: [PATCH 2931/5631] KEYS: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: David Howells Cc: Herbert Xu Cc: "David S. Miller" Cc: keyrings@vger.kernel.org Cc: linux-crypto@vger.kernel.org Signed-off-by: Luis Chamberlain --- crypto/asymmetric_keys/asymmetric_type.c | 1 - 1 file changed, 1 deletion(-) diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index 41a2f0eb4ce4..a5da8ccd353e 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -17,7 +17,6 @@ #include #include "asymmetric_keys.h" -MODULE_LICENSE("GPL"); const char *const key_being_used_for[NR__KEY_BEING_USED_FOR] = { [VERIFYING_MODULE_SIGNATURE] = "mod sig", -- GitLab From c7b9975a443167a0059e3d4d6582cd2634e7485d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:24 +0000 Subject: [PATCH 2932/5631] pinctrl: bcm: ns: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Ray Jui Cc: Scott Branden Cc: Linus Walleij Cc: linux-arm-kernel@lists.infradead.org Cc: linux-gpio@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/bcm/pinctrl-ns.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/bcm/pinctrl-ns.c b/drivers/pinctrl/bcm/pinctrl-ns.c index 465cc96814a1..f80630a74d34 100644 --- a/drivers/pinctrl/bcm/pinctrl-ns.c +++ b/drivers/pinctrl/bcm/pinctrl-ns.c @@ -299,5 +299,4 @@ static struct platform_driver ns_pinctrl_driver = { module_platform_driver(ns_pinctrl_driver); MODULE_AUTHOR("Rafał Miłecki"); -MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(of, ns_pinctrl_of_match_table); -- GitLab From e518212eb6f3e70ab6b336b3ed66cc421b24032a Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:24 +0000 Subject: [PATCH 2933/5631] MIPS: BCM47XX: remove MODULE_LICENSE in non-modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Philippe Mathieu-Daudé Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: "Rafał Miłecki" Cc: linux-mips@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/firmware/broadcom/bcm47xx_nvram.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/firmware/broadcom/bcm47xx_nvram.c b/drivers/firmware/broadcom/bcm47xx_nvram.c index 5f47dbf4889a..0ea5206be4c9 100644 --- a/drivers/firmware/broadcom/bcm47xx_nvram.c +++ b/drivers/firmware/broadcom/bcm47xx_nvram.c @@ -255,4 +255,3 @@ char *bcm47xx_nvram_get_contents(size_t *nvram_size) } EXPORT_SYMBOL(bcm47xx_nvram_get_contents); -MODULE_LICENSE("GPL v2"); -- GitLab From bb177282c46089d7cc30c1020c6f404070b87310 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:25 +0000 Subject: [PATCH 2934/5631] clocksource: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Daniel Lezcano Cc: Thomas Gleixner Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: linux-stm32@st-md-mailman.stormreply.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/clocksource/timer-stm32-lp.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c index db2841d0beb8..4a10fb940de5 100644 --- a/drivers/clocksource/timer-stm32-lp.c +++ b/drivers/clocksource/timer-stm32-lp.c @@ -218,4 +218,3 @@ module_platform_driver(stm32_clkevent_lp_driver); MODULE_ALIAS("platform:stm32-lptimer-timer"); MODULE_DESCRIPTION("STMicroelectronics STM32 clockevent low power driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 1e64f2a7fef058fa206f09e9e3268049af5e21c4 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:25 +0000 Subject: [PATCH 2935/5631] clocksource/drivers/timer-tegra186: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Daniel Lezcano Cc: Thomas Gleixner Cc: Thierry Reding Cc: Jonathan Hunter Cc: linux-tegra@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/clocksource/timer-tegra186.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clocksource/timer-tegra186.c b/drivers/clocksource/timer-tegra186.c index ea742889ee06..0c52c0a21830 100644 --- a/drivers/clocksource/timer-tegra186.c +++ b/drivers/clocksource/timer-tegra186.c @@ -511,4 +511,3 @@ module_platform_driver(tegra186_wdt_driver); MODULE_AUTHOR("Thierry Reding "); MODULE_DESCRIPTION("NVIDIA Tegra186 timers driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 5ba4b11a8da728fe6e7c37a6799fd0cc1803157c Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:26 +0000 Subject: [PATCH 2936/5631] clocksource: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Daniel Lezcano Cc: Thomas Gleixner Signed-off-by: Luis Chamberlain --- drivers/clocksource/em_sti.c | 1 - drivers/clocksource/sh_cmt.c | 1 - drivers/clocksource/sh_mtu2.c | 1 - drivers/clocksource/sh_tmu.c | 1 - drivers/clocksource/timer-ti-dm.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c index c04b47bd4868..ca8d29ab70da 100644 --- a/drivers/clocksource/em_sti.c +++ b/drivers/clocksource/em_sti.c @@ -363,4 +363,3 @@ module_exit(em_sti_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("Renesas Emma Mobile STI Timer Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 8b2e079d9df2..e81c588d9afe 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -1174,4 +1174,3 @@ module_exit(sh_cmt_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("SuperH CMT Timer Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index 169a1fccc497..dd19553ef0b9 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -530,4 +530,3 @@ module_exit(sh_mtu2_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("SuperH MTU2 Timer Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c index 932f31a7c5be..beffff81c00f 100644 --- a/drivers/clocksource/sh_tmu.c +++ b/drivers/clocksource/sh_tmu.c @@ -674,4 +674,3 @@ module_exit(sh_tmu_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("SuperH TMU Timer Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index b24b903a8822..1eb39834bad4 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -1283,5 +1283,4 @@ static struct platform_driver omap_dm_timer_driver = { module_platform_driver(omap_dm_timer_driver); MODULE_DESCRIPTION("OMAP Dual-Mode Timer Driver"); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Texas Instruments Inc"); -- GitLab From 3714878005d3b7d78c096ad1f1f463887eb9b928 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:30 +0000 Subject: [PATCH 2937/5631] crypto: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Signed-off-by: Luis Chamberlain --- lib/crypto/blake2s-generic.c | 1 - lib/crypto/blake2s.c | 1 - 2 files changed, 2 deletions(-) diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c index 75ccb3e633e6..4ffe3d927920 100644 --- a/lib/crypto/blake2s-generic.c +++ b/lib/crypto/blake2s-generic.c @@ -110,6 +110,5 @@ void blake2s_compress_generic(struct blake2s_state *state, const u8 *block, EXPORT_SYMBOL(blake2s_compress_generic); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld "); diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index 98e688c6d891..71a316552cc5 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -67,6 +67,5 @@ static int __init blake2s_mod_init(void) } module_init(blake2s_mod_init); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld "); -- GitLab From ef5bbd1172f4bd7b9162654d9b167e89afe82867 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Mon, 20 Mar 2023 10:20:10 +0000 Subject: [PATCH 2938/5631] crypto: blake2s: remove module-related code Now blake2s-generic.c can no longer be a module, drop all remaining module-related code as well. Signed-off-by: Nick Alcock Requested-by: Herbert Xu Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Herbert Xu Cc: "David S. Miller" Cc: linux-crypto@vger.kernel.org Signed-off-by: Luis Chamberlain --- lib/crypto/blake2s-generic.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/lib/crypto/blake2s-generic.c b/lib/crypto/blake2s-generic.c index 4ffe3d927920..3b6dcfdd9628 100644 --- a/lib/crypto/blake2s-generic.c +++ b/lib/crypto/blake2s-generic.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -109,6 +108,3 @@ void blake2s_compress_generic(struct blake2s_state *state, const u8 *block, } EXPORT_SYMBOL(blake2s_compress_generic); - -MODULE_DESCRIPTION("BLAKE2s hash function"); -MODULE_AUTHOR("Jason A. Donenfeld "); -- GitLab From 41a98c68f2abc67b88568b7a25fd547989d2c92f Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:31 +0000 Subject: [PATCH 2939/5631] crypto: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Herbert Xu Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: linux-crypto@vger.kernel.org Signed-off-by: Luis Chamberlain --- arch/x86/crypto/blake2s-glue.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index aaba21230528..0df9ec15643a 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -74,4 +74,3 @@ static int __init blake2s_mod_init(void) module_init(blake2s_mod_init); -MODULE_LICENSE("GPL v2"); -- GitLab From b71e2a69d16c8d12c2b1aadeffd59ed1920d50e9 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Mon, 20 Mar 2023 10:24:35 +0000 Subject: [PATCH 2940/5631] crypto: blake2s: remove module_init and module.h inclusion Now this can no longer be built as a module, drop all remaining module-related code as well. Signed-off-by: Nick Alcock Suggested-by: Herbert Xu Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Herbert Xu Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: x86@kernel.org Cc: linux-crypto@vger.kernel.org Signed-off-by: Luis Chamberlain --- arch/x86/crypto/blake2s-glue.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 0df9ec15643a..0313f9673f56 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include @@ -72,5 +71,4 @@ static int __init blake2s_mod_init(void) return 0; } -module_init(blake2s_mod_init); - +subsys_initcall(blake2s_mod_init); -- GitLab From d69b1f0c03f61bbc6bcd57415f16cc855818ecac Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:32 +0000 Subject: [PATCH 2941/5631] dmaengine: stm32-mdma: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Vinod Koul Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: Philipp Zabel Cc: dmaengine@vger.kernel.org Cc: linux-stm32@st-md-mailman.stormreply.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/dma/stm32-dmamux.c | 1 - drivers/dma/stm32-mdma.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/dma/stm32-dmamux.c b/drivers/dma/stm32-dmamux.c index 46b884d46188..e415bd9f4f2b 100644 --- a/drivers/dma/stm32-dmamux.c +++ b/drivers/dma/stm32-dmamux.c @@ -398,4 +398,3 @@ arch_initcall(stm32_dmamux_init); MODULE_DESCRIPTION("DMA Router driver for STM32 DMA MUX"); MODULE_AUTHOR("M'boumba Cedric Madianga "); MODULE_AUTHOR("Pierre-Yves Mordret "); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 84e7f4f4a800..1d0e9dd72ab3 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1814,4 +1814,3 @@ subsys_initcall(stm32_mdma_init); MODULE_DESCRIPTION("Driver for STM32 MDMA controller"); MODULE_AUTHOR("M'boumba Cedric Madianga "); MODULE_AUTHOR("Pierre-Yves Mordret "); -MODULE_LICENSE("GPL v2"); -- GitLab From 3f0dedc39039a75670817a1afffa77b6cee077cb Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:33 +0000 Subject: [PATCH 2942/5631] dmaengine: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Vinod Koul Cc: dmaengine@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/dma/ep93xx_dma.c | 1 - drivers/dma/ipu/ipu_idmac.c | 1 - drivers/dma/mv_xor_v2.c | 1 - drivers/dma/sh/shdma-base.c | 1 - 4 files changed, 4 deletions(-) diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c index d19ea885c63e..5338a94f1a69 100644 --- a/drivers/dma/ep93xx_dma.c +++ b/drivers/dma/ep93xx_dma.c @@ -1431,4 +1431,3 @@ subsys_initcall(ep93xx_dma_module_init); MODULE_AUTHOR("Mika Westerberg "); MODULE_DESCRIPTION("EP93xx DMA driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c index baab1ca9f621..d799b99c18bd 100644 --- a/drivers/dma/ipu/ipu_idmac.c +++ b/drivers/dma/ipu/ipu_idmac.c @@ -1797,6 +1797,5 @@ static int __init ipu_init(void) subsys_initcall(ipu_init); MODULE_DESCRIPTION("IPU core driver"); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Guennadi Liakhovetski "); MODULE_ALIAS("platform:ipu-core"); diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c index 89790beba305..b4de7d4a3105 100644 --- a/drivers/dma/mv_xor_v2.c +++ b/drivers/dma/mv_xor_v2.c @@ -917,4 +917,3 @@ static struct platform_driver mv_xor_v2_driver = { module_platform_driver(mv_xor_v2_driver); MODULE_DESCRIPTION("DMA engine driver for Marvell's Version 2 of XOR engine"); -MODULE_LICENSE("GPL"); diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c index 158e5e7defae..588c5f409a80 100644 --- a/drivers/dma/sh/shdma-base.c +++ b/drivers/dma/sh/shdma-base.c @@ -1047,6 +1047,5 @@ static void __exit shdma_exit(void) } module_exit(shdma_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("SH-DMA driver base library"); MODULE_AUTHOR("Guennadi Liakhovetski "); -- GitLab From 114da4b026d39e36f6017b7ea534ffe5099f90be Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:34 +0000 Subject: [PATCH 2943/5631] dma-mapping: benchmark: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Christoph Hellwig Cc: Marek Szyprowski Cc: iommu@lists.linux.dev Signed-off-by: Luis Chamberlain --- kernel/dma/map_benchmark.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 0520a8f4fb1d..02205ab53b7e 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -356,4 +356,3 @@ module_exit(map_benchmark_cleanup); MODULE_AUTHOR("Barry Song "); MODULE_DESCRIPTION("dma_map benchmark driver"); -MODULE_LICENSE("GPL"); -- GitLab From 501e2c7d42d61bd5f473cc719db431973959e55a Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:34 +0000 Subject: [PATCH 2944/5631] dma-buf: heaps: remove MODULE_LICENSE in non-modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Luis Chamberlain --- drivers/dma-buf/heaps/cma_heap.c | 1 - drivers/dma-buf/heaps/system_heap.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 1131fb943992..a7f048048864 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -407,4 +407,3 @@ static int add_default_cma_heap(void) } module_init(add_default_cma_heap); MODULE_DESCRIPTION("DMA-BUF CMA Heap"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index e8bd10e60998..79c03f5b4e28 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -440,4 +440,3 @@ static int system_heap_create(void) return 0; } module_init(system_heap_create); -MODULE_LICENSE("GPL v2"); -- GitLab From 7435721a4a7b6f51b60c41a2e58075dec3cc0ca8 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:35 +0000 Subject: [PATCH 2945/5631] binfmt_elf: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Alexander Viro Cc: Christian Brauner Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Signed-off-by: Luis Chamberlain --- fs/binfmt_elf.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8a884e795f6a..0f0d10697240 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2174,7 +2174,6 @@ static void __exit exit_elf_binfmt(void) core_initcall(init_elf_binfmt); module_exit(exit_elf_binfmt); -MODULE_LICENSE("GPL"); #ifdef CONFIG_BINFMT_ELF_KUNIT_TEST #include "binfmt_elf_test.c" -- GitLab From 7540fb785b0464a98a7e7ec7ed44e4bbded8e1c8 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:37 +0000 Subject: [PATCH 2946/5631] phy: intel: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Vinod Koul Cc: Kishon Vijay Abraham I Cc: Philipp Zabel Cc: linux-phy@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/phy/intel/phy-intel-lgm-combo.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/phy/intel/phy-intel-lgm-combo.c b/drivers/phy/intel/phy-intel-lgm-combo.c index 6010e246d52e..8c764c457c1c 100644 --- a/drivers/phy/intel/phy-intel-lgm-combo.c +++ b/drivers/phy/intel/phy-intel-lgm-combo.c @@ -616,4 +616,3 @@ static struct platform_driver intel_cbphy_driver = { module_platform_driver(intel_cbphy_driver); MODULE_DESCRIPTION("Intel Combo-phy driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 8a0a6c9af053fb93c0edf4581518c77fd131803e Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:37 +0000 Subject: [PATCH 2947/5631] hwspinlock: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Ohad Ben-Cohen Cc: Bjorn Andersson Cc: linux-remoteproc@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/hwspinlock/hwspinlock_core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c index 22b8f2a70b3b..ada694ba9f95 100644 --- a/drivers/hwspinlock/hwspinlock_core.c +++ b/drivers/hwspinlock/hwspinlock_core.c @@ -949,6 +949,5 @@ struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, } EXPORT_SYMBOL_GPL(devm_hwspin_lock_request_specific); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Hardware spinlock interface"); MODULE_AUTHOR("Ohad Ben-Cohen "); -- GitLab From 48a3cbf1c566fd68a1a6dd3fc91b6a71dda42e23 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:38 +0000 Subject: [PATCH 2948/5631] iommu/sun50i: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Jernej Skrabec Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Joerg Roedel Cc: Will Deacon Cc: Chen-Yu Tsai Cc: Jernej Skrabec Cc: Samuel Holland Cc: Philipp Zabel Cc: iommu@lists.linux.dev Cc: linux-arm-kernel@lists.infradead.org Cc: linux-sunxi@lists.linux.dev Signed-off-by: Luis Chamberlain --- drivers/iommu/sun50i-iommu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c index 2d993d0cea7d..74c5cb93e900 100644 --- a/drivers/iommu/sun50i-iommu.c +++ b/drivers/iommu/sun50i-iommu.c @@ -1076,4 +1076,3 @@ builtin_platform_driver_probe(sun50i_iommu_driver, sun50i_iommu_probe); MODULE_DESCRIPTION("Allwinner H6 IOMMU driver"); MODULE_AUTHOR("Maxime Ripard "); MODULE_AUTHOR("zhuxianbin "); -MODULE_LICENSE("Dual BSD/GPL"); -- GitLab From 2752626e3eec0c11487b0a03152821f32fc88dfa Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:39 +0000 Subject: [PATCH 2949/5631] irqchip: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Thomas Gleixner Cc: Marc Zyngier Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-ls-scfg-msi.c | 1 - drivers/irqchip/irq-mbigen.c | 1 - drivers/irqchip/irq-renesas-intc-irqpin.c | 1 - drivers/irqchip/irq-renesas-irqc.c | 1 - drivers/irqchip/irq-renesas-rza1.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c index 527c90e0920e..f5ba3f9f8415 100644 --- a/drivers/irqchip/irq-ls-scfg-msi.c +++ b/drivers/irqchip/irq-ls-scfg-msi.c @@ -430,4 +430,3 @@ module_platform_driver(ls_scfg_msi_driver); MODULE_AUTHOR("Minghuan Lian "); MODULE_DESCRIPTION("Freescale Layerscape SCFG MSI controller driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index f3faf5c99770..d6763ea9f310 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -389,5 +389,4 @@ module_platform_driver(mbigen_platform_driver); MODULE_AUTHOR("Jun Ma "); MODULE_AUTHOR("Yun Wu "); -MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("HiSilicon MBI Generator driver"); diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c index e83756aca14e..26e4c17a7bf2 100644 --- a/drivers/irqchip/irq-renesas-intc-irqpin.c +++ b/drivers/irqchip/irq-renesas-intc-irqpin.c @@ -608,4 +608,3 @@ module_exit(intc_irqpin_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("Renesas INTC External IRQ Pin Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c index 1ee5e9941f67..49b446b396f9 100644 --- a/drivers/irqchip/irq-renesas-irqc.c +++ b/drivers/irqchip/irq-renesas-irqc.c @@ -270,4 +270,3 @@ module_exit(irqc_exit); MODULE_AUTHOR("Magnus Damm"); MODULE_DESCRIPTION("Renesas IRQC Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-renesas-rza1.c b/drivers/irqchip/irq-renesas-rza1.c index 72c06e883d1c..e4c99c2e0373 100644 --- a/drivers/irqchip/irq-renesas-rza1.c +++ b/drivers/irqchip/irq-renesas-rza1.c @@ -281,4 +281,3 @@ module_exit(rza1_irqc_exit); MODULE_AUTHOR("Geert Uytterhoeven "); MODULE_DESCRIPTION("Renesas RZ/A1 IRQC Driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From e3f1f02548adbf973af29c6ee6304a45121bff03 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:40 +0000 Subject: [PATCH 2950/5631] irqchip: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Thomas Gleixner Cc: Marc Zyngier Cc: Philipp Zabel Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-renesas-rzg2l.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c index 25fd8ee66565..4bbfa2b0a4df 100644 --- a/drivers/irqchip/irq-renesas-rzg2l.c +++ b/drivers/irqchip/irq-renesas-rzg2l.c @@ -390,4 +390,3 @@ IRQCHIP_MATCH("renesas,rzg2l-irqc", rzg2l_irqc_init) IRQCHIP_PLATFORM_DRIVER_END(rzg2l_irqc) MODULE_AUTHOR("Lad Prabhakar "); MODULE_DESCRIPTION("Renesas RZ/G2L IRQC Driver"); -MODULE_LICENSE("GPL"); -- GitLab From 7b51090edc1f5aeeac4d6f166ebd95f707eeb095 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:40 +0000 Subject: [PATCH 2951/5631] mailbox: rockchip: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Jassi Brar Cc: Heiko Stuebner Cc: linux-arm-kernel@lists.infradead.org Cc: linux-rockchip@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/mailbox/rockchip-mailbox.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index e02d3c9e3693..28d7bfee2641 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -254,7 +254,6 @@ static struct platform_driver rockchip_mbox_driver = { module_platform_driver(rockchip_mbox_driver); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Rockchip mailbox: communicate between CPU cores and MCU"); MODULE_AUTHOR("Addy Ke "); MODULE_AUTHOR("Caesar Wang "); -- GitLab From 4f2fe3964cf40c218e97de711646f4c608094749 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:40 +0000 Subject: [PATCH 2952/5631] mailbox: zynq: make modular This driver has a MODULE_LICENSE but is not tristate so cannot be built as a module, unlike all its peers: make it modular to match. Signed-off-by: Nick Alcock Suggested-by: Michal Simek Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Jassi Brar Cc: Michal Simek Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/mailbox/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 1495965bc394..af6b0f5b491d 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -259,7 +259,7 @@ config MTK_CMDQ_MBOX during the vblank. config ZYNQMP_IPI_MBOX - bool "Xilinx ZynqMP IPI Mailbox" + tristate "Xilinx ZynqMP IPI Mailbox" depends on ARCH_ZYNQMP && OF help Say yes here to add support for Xilinx IPI mailbox driver. -- GitLab From 268f4d5b63dbae4b289ccb17e3ad073934dee087 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:41 +0000 Subject: [PATCH 2953/5631] power: reset: mt6397: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Sean Wang Cc: Sebastian Reichel Cc: Matthias Brugger Cc: linux-pm@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mediatek@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/power/reset/mt6323-poweroff.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/power/reset/mt6323-poweroff.c b/drivers/power/reset/mt6323-poweroff.c index d90e76fcb938..108167f7738b 100644 --- a/drivers/power/reset/mt6323-poweroff.c +++ b/drivers/power/reset/mt6323-poweroff.c @@ -97,4 +97,3 @@ module_platform_driver(mt6323_pwrc_driver); MODULE_DESCRIPTION("Poweroff driver for MT6323 PMIC"); MODULE_AUTHOR("Sean Wang "); -MODULE_LICENSE("GPL v2"); -- GitLab From d829b836f2816abcb6bca4a036af53902a18fd74 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:44 +0000 Subject: [PATCH 2954/5631] irqchip/mchp-eic: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Claudiu Beznea Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Claudiu Beznea Cc: Thomas Gleixner Cc: Marc Zyngier Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-mchp-eic.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/irqchip/irq-mchp-eic.c b/drivers/irqchip/irq-mchp-eic.c index c726a19837d2..5dcd94c000a2 100644 --- a/drivers/irqchip/irq-mchp-eic.c +++ b/drivers/irqchip/irq-mchp-eic.c @@ -276,5 +276,4 @@ IRQCHIP_MATCH("microchip,sama7g5-eic", mchp_eic_init) IRQCHIP_PLATFORM_DRIVER_END(mchp_eic) MODULE_DESCRIPTION("Microchip External Interrupt Controller"); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Claudiu Beznea "); -- GitLab From 62d8cd5bfd58e48e4e76415fa9db6147b79cb064 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:46 +0000 Subject: [PATCH 2955/5631] NFSv4.2: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Trond Myklebust Cc: Anna Schumaker Cc: Chuck Lever Cc: Jeff Layton Cc: linux-nfs@vger.kernel.org Signed-off-by: Luis Chamberlain --- fs/nfs_common/nfs_ssc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/nfs_common/nfs_ssc.c b/fs/nfs_common/nfs_ssc.c index 7c1509e968c8..832246b22c51 100644 --- a/fs/nfs_common/nfs_ssc.c +++ b/fs/nfs_common/nfs_ssc.c @@ -12,7 +12,6 @@ #include #include "../nfs/nfs4_fs.h" -MODULE_LICENSE("GPL"); struct nfs_ssc_client_ops_tbl nfs_ssc_client_tbl; EXPORT_SYMBOL_GPL(nfs_ssc_client_tbl); -- GitLab From 83bc3f3cd81dd7f16c836b4f896df70015ae577c Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:47 +0000 Subject: [PATCH 2956/5631] nvmem: core: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Srinivas Kandagatla Signed-off-by: Luis Chamberlain --- drivers/nvmem/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 174ef3574e07..8de427d00150 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1958,4 +1958,3 @@ module_exit(nvmem_exit); MODULE_AUTHOR("Srinivas Kandagatla Date: Tue, 7 Mar 2023 18:01:49 +0000 Subject: [PATCH 2957/5631] perf/hw_breakpoint: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: linux-perf-users@vger.kernel.org Signed-off-by: Luis Chamberlain --- kernel/events/hw_breakpoint_test.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/events/hw_breakpoint_test.c b/kernel/events/hw_breakpoint_test.c index c57610f52bb4..2cfeeecf8de9 100644 --- a/kernel/events/hw_breakpoint_test.c +++ b/kernel/events/hw_breakpoint_test.c @@ -329,5 +329,4 @@ static struct kunit_suite hw_breakpoint_test_suite = { kunit_test_suites(&hw_breakpoint_test_suite); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marco Elver "); -- GitLab From feb7e8cba73abc1984937d3a8507c17d337c82ca Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:50 +0000 Subject: [PATCH 2958/5631] pinctrl: amd: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Basavaraj Natikar Cc: Shyam Sundar S K Cc: Linus Walleij Cc: linux-gpio@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/pinctrl-amd.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 9236a132c7ba..0cc00e9dbcf0 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -1213,6 +1213,5 @@ static struct platform_driver amd_gpio_driver = { module_platform_driver(amd_gpio_driver); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Ken Xue , Jeff Wu "); MODULE_DESCRIPTION("AMD GPIO pinctrl driver"); -- GitLab From 7da1628cf38f54f0d1044096f31b73f8c046aa8f Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:50 +0000 Subject: [PATCH 2959/5631] pinctrl: mediatek: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Sean Wang Cc: Linus Walleij Cc: Matthias Brugger Cc: linux-mediatek@lists.infradead.org Cc: linux-gpio@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/mediatek/pinctrl-mt8188.c | 1 - drivers/pinctrl/mediatek/pinctrl-mt8192.c | 1 - drivers/pinctrl/mediatek/pinctrl-mt8365.c | 1 - 3 files changed, 3 deletions(-) diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8188.c b/drivers/pinctrl/mediatek/pinctrl-mt8188.c index 6a3d0126288e..c067e043e619 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8188.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8188.c @@ -1670,5 +1670,4 @@ static int __init mt8188_pinctrl_init(void) arch_initcall(mt8188_pinctrl_init); -MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MediaTek MT8188 Pinctrl Driver"); diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8192.c b/drivers/pinctrl/mediatek/pinctrl-mt8192.c index 9695f4ec6aba..dee1b3aefd36 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8192.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8192.c @@ -1431,5 +1431,4 @@ static int __init mt8192_pinctrl_init(void) } arch_initcall(mt8192_pinctrl_init); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("MediaTek MT8192 Pinctrl Driver"); diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8365.c b/drivers/pinctrl/mediatek/pinctrl-mt8365.c index db4492e9ee67..75a505035e96 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8365.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8365.c @@ -495,6 +495,5 @@ static int __init mtk_pinctrl_init(void) } arch_initcall(mtk_pinctrl_init); -MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MediaTek MT8365 Pinctrl Driver"); MODULE_AUTHOR("Zhiyong Tao "); -- GitLab From b08401919cc1359095e9c03c52470f4b0e1097de Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:51 +0000 Subject: [PATCH 2960/5631] pinctrl: renesas: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Geert Uytterhoeven Cc: Linus Walleij Cc: linux-renesas-soc@vger.kernel.org Cc: linux-gpio@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/pinctrl/renesas/pinctrl-rza1.c | 1 - drivers/pinctrl/renesas/pinctrl-rza2.c | 1 - drivers/pinctrl/renesas/pinctrl-rzg2l.c | 1 - drivers/pinctrl/renesas/pinctrl-rzn1.c | 1 - drivers/pinctrl/renesas/pinctrl-rzv2m.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c index 529c0fc4ec06..48173355a040 100644 --- a/drivers/pinctrl/renesas/pinctrl-rza1.c +++ b/drivers/pinctrl/renesas/pinctrl-rza1.c @@ -1407,4 +1407,3 @@ core_initcall(rza1_pinctrl_init); MODULE_AUTHOR("Jacopo Mondi "); MODULE_DESCRIPTION("Pin and gpio controller driver for RZ/A2 SoC"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index 04b31f0c6b34..9511d920565e 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -1570,4 +1570,3 @@ core_initcall(rzg2l_pinctrl_init); MODULE_AUTHOR("Lad Prabhakar "); MODULE_DESCRIPTION("Pin and gpio controller driver for RZ/G2L family"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/renesas/pinctrl-rzn1.c b/drivers/pinctrl/renesas/pinctrl-rzn1.c index 9158c1757492..d73741651419 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzn1.c +++ b/drivers/pinctrl/renesas/pinctrl-rzn1.c @@ -952,4 +952,3 @@ subsys_initcall(_pinctrl_drv_register); MODULE_AUTHOR("Phil Edworthy "); MODULE_DESCRIPTION("Renesas RZ/N1 pinctrl driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index 3b65a71abd9a..e5472293bc7f 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -1117,4 +1117,3 @@ core_initcall(rzv2m_pinctrl_init); MODULE_AUTHOR("Phil Edworthy "); MODULE_DESCRIPTION("Pin and gpio controller driver for RZ/V2M"); -MODULE_LICENSE("GPL"); -- GitLab From 5e0266f0e5f57617472d5aac4013f58a3ef264ac Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:52 +0000 Subject: [PATCH 2961/5631] lib: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Jacob Keller Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Jacob Keller Signed-off-by: Luis Chamberlain --- lib/pldmfw/pldmfw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c index 6e77eb6d8e72..54e1809a38fd 100644 --- a/lib/pldmfw/pldmfw.c +++ b/lib/pldmfw/pldmfw.c @@ -875,5 +875,4 @@ int pldmfw_flash_image(struct pldmfw *context, const struct firmware *fw) EXPORT_SYMBOL(pldmfw_flash_image); MODULE_AUTHOR("Jacob Keller "); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("PLDM firmware flash update library"); -- GitLab From ec4f7b7fc9918bb8afca42b8e6847193b24ca944 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:52 +0000 Subject: [PATCH 2962/5631] power: supply: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Sebastian Reichel Cc: linux-pm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/power/supply/power_supply_core.c | 1 - drivers/power/supply/wm97xx_battery.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index f3d7c1da299f..8a6046d3808d 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1485,4 +1485,3 @@ MODULE_DESCRIPTION("Universal power supply monitor class"); MODULE_AUTHOR("Ian Molton , " "Szabolcs Gyurko, " "Anton Vorontsov "); -MODULE_LICENSE("GPL"); diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c index a0e1eaa25d93..f4b190adb335 100644 --- a/drivers/power/supply/wm97xx_battery.c +++ b/drivers/power/supply/wm97xx_battery.c @@ -271,6 +271,5 @@ static struct platform_driver wm97xx_bat_driver = { module_platform_driver(wm97xx_bat_driver); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marek Vasut "); MODULE_DESCRIPTION("WM97xx battery driver"); -- GitLab From cc9ab32b6885b62fd5a774d1149ccf037801b510 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:53 +0000 Subject: [PATCH 2963/5631] remoteproc: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Mathieu Poirier Acked-by: Mukesh Ojha Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Bjorn Andersson Cc: Mathieu Poirier Cc: linux-remoteproc@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/remoteproc/remoteproc_core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 80072b6b6283..695cce218e8c 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -2766,5 +2766,4 @@ static void __exit remoteproc_exit(void) } module_exit(remoteproc_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Generic Remote Processor Framework"); -- GitLab From 355a1a4b68d44384154e8fdb41861e053bb70d53 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:53 +0000 Subject: [PATCH 2964/5631] clk: renesas: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Geert Uytterhoeven Cc: Michael Turquette Cc: Stephen Boyd Cc: Philipp Zabel Cc: linux-renesas-soc@vger.kernel.org Cc: linux-clk@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/clk/renesas/renesas-cpg-mssr.c | 1 - drivers/clk/renesas/rzg2l-cpg.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/clk/renesas/renesas-cpg-mssr.c b/drivers/clk/renesas/renesas-cpg-mssr.c index b9f210437ddf..38c06f82b91d 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.c +++ b/drivers/clk/renesas/renesas-cpg-mssr.c @@ -1127,4 +1127,3 @@ void __init mssr_mod_nullify(struct mssr_mod_clk *mod_clks, } MODULE_DESCRIPTION("Renesas CPG/MSSR Driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/renesas/rzg2l-cpg.c b/drivers/clk/renesas/rzg2l-cpg.c index 4bf40f6ccd1d..93b02cdc98c2 100644 --- a/drivers/clk/renesas/rzg2l-cpg.c +++ b/drivers/clk/renesas/rzg2l-cpg.c @@ -1440,4 +1440,3 @@ static int __init rzg2l_cpg_init(void) subsys_initcall(rzg2l_cpg_init); MODULE_DESCRIPTION("Renesas RZ/G2L CPG Driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From c9698fd5b4550da9c5988c9501762cf1d7a752da Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:54 +0000 Subject: [PATCH 2965/5631] reset: mchp: sparx5: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Steen Hegelund Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Philipp Zabel Cc: Lars Povlsen Cc: Steen Hegelund Cc: Daniel Machon Cc: UNGLinuxDriver@microchip.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/reset/reset-microchip-sparx5.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/reset/reset-microchip-sparx5.c b/drivers/reset/reset-microchip-sparx5.c index f3528dd1d084..ead25942061d 100644 --- a/drivers/reset/reset-microchip-sparx5.c +++ b/drivers/reset/reset-microchip-sparx5.c @@ -179,4 +179,3 @@ postcore_initcall(mchp_sparx5_reset_init); MODULE_DESCRIPTION("Microchip Sparx5 switch reset driver"); MODULE_AUTHOR("Steen Hegelund "); -MODULE_LICENSE("Dual MIT/GPL"); -- GitLab From 7bd57c5a98aa89af63f55a744e99b6a1da6ea9dd Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:54 +0000 Subject: [PATCH 2966/5631] reset: lantiq: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Philipp Zabel Signed-off-by: Luis Chamberlain --- drivers/reset/reset-lantiq.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/reset/reset-lantiq.c b/drivers/reset/reset-lantiq.c index b936cfe85641..549ba45d8597 100644 --- a/drivers/reset/reset-lantiq.c +++ b/drivers/reset/reset-lantiq.c @@ -207,4 +207,3 @@ module_platform_driver(lantiq_rcu_reset_driver); MODULE_AUTHOR("Martin Blumenstingl "); MODULE_DESCRIPTION("Lantiq XWAY RCU Reset Controller Driver"); -MODULE_LICENSE("GPL"); -- GitLab From 00c8682a78f88e4eecdfbfb86a8f15d4c322a128 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:55 +0000 Subject: [PATCH 2967/5631] clk: microchip: mpfs: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Conor Dooley Cc: Daire McNamara Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-riscv@lists.infradead.org Cc: linux-clk@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/clk/microchip/clk-mpfs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index 4f0a19db7ed7..d85b345f4c08 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -513,4 +513,3 @@ MODULE_DESCRIPTION("Microchip PolarFire SoC Clock Driver"); MODULE_AUTHOR("Padmarao Begari "); MODULE_AUTHOR("Daire McNamara "); MODULE_AUTHOR("Conor Dooley "); -MODULE_LICENSE("GPL"); -- GitLab From 39b8452f9136850df00425028de1b28d65751523 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:55 +0000 Subject: [PATCH 2968/5631] reset: mpfs: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Reviewed-by: Conor Dooley Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Conor Dooley Cc: Daire McNamara Cc: Philipp Zabel Cc: linux-riscv@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/reset/reset-mpfs.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/reset/reset-mpfs.c b/drivers/reset/reset-mpfs.c index e003e50590ec..e71ab73092ab 100644 --- a/drivers/reset/reset-mpfs.c +++ b/drivers/reset/reset-mpfs.c @@ -153,5 +153,4 @@ module_auxiliary_driver(mpfs_reset_driver); MODULE_DESCRIPTION("Microchip PolarFire SoC Reset Driver"); MODULE_AUTHOR("Conor Dooley "); -MODULE_LICENSE("GPL"); MODULE_IMPORT_NS(MCHP_CLK_MPFS); -- GitLab From 2fd5ed8b65a62eaf78e30098cf95b9d58461a8a5 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:56 +0000 Subject: [PATCH 2969/5631] rv/reactor: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Daniel Bristot de Oliveira Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Daniel Bristot de Oliveira Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: linux-trace-devel@vger.kernel.org Cc: linux-trace-kernel@vger.kernel.org Signed-off-by: Luis Chamberlain --- kernel/trace/rv/reactor_panic.c | 1 - kernel/trace/rv/reactor_printk.c | 1 - 2 files changed, 2 deletions(-) diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c index d65f6c25a87c..0186ff4cbd0b 100644 --- a/kernel/trace/rv/reactor_panic.c +++ b/kernel/trace/rv/reactor_panic.c @@ -38,6 +38,5 @@ static void __exit unregister_react_panic(void) module_init(register_react_panic); module_exit(unregister_react_panic); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Bristot de Oliveira"); MODULE_DESCRIPTION("panic rv reactor: panic if an exception is found."); diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c index 4b6b7106a477..178759dbf89f 100644 --- a/kernel/trace/rv/reactor_printk.c +++ b/kernel/trace/rv/reactor_printk.c @@ -37,6 +37,5 @@ static void __exit unregister_react_printk(void) module_init(register_react_printk); module_exit(unregister_react_printk); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Bristot de Oliveira"); MODULE_DESCRIPTION("printk rv reactor: printk if an exception is hit."); -- GitLab From b00cf02386e4c82ebcde4bc2f6a6a802cea38c26 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:57 +0000 Subject: [PATCH 2970/5631] irqchip/irq-sl28cpld: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Michael Walle Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Michael Walle Cc: Thomas Gleixner Cc: Marc Zyngier Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-sl28cpld.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/irqchip/irq-sl28cpld.c b/drivers/irqchip/irq-sl28cpld.c index f2172240172c..e50f9eaba4cd 100644 --- a/drivers/irqchip/irq-sl28cpld.c +++ b/drivers/irqchip/irq-sl28cpld.c @@ -92,4 +92,3 @@ module_platform_driver(sl28cpld_intc_driver); MODULE_DESCRIPTION("sl28cpld Interrupt Controller Driver"); MODULE_AUTHOR("Michael Walle "); -MODULE_LICENSE("GPL"); -- GitLab From 24e4dba2a482111f66072f214be2a59762505db3 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:01:59 +0000 Subject: [PATCH 2971/5631] power: reset: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Sebastian Reichel Cc: linux-pm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/power/reset/as3722-poweroff.c | 1 - drivers/power/reset/gpio-poweroff.c | 1 - drivers/power/reset/gpio-restart.c | 1 - drivers/power/reset/ltc2952-poweroff.c | 1 - drivers/power/reset/regulator-poweroff.c | 1 - drivers/power/reset/restart-poweroff.c | 1 - drivers/power/reset/tps65086-restart.c | 1 - 7 files changed, 7 deletions(-) diff --git a/drivers/power/reset/as3722-poweroff.c b/drivers/power/reset/as3722-poweroff.c index 661e1c67f82e..80edff1a556f 100644 --- a/drivers/power/reset/as3722-poweroff.c +++ b/drivers/power/reset/as3722-poweroff.c @@ -84,4 +84,3 @@ module_platform_driver(as3722_poweroff_driver); MODULE_DESCRIPTION("Power off driver for ams AS3722 PMIC Device"); MODULE_ALIAS("platform:as3722-power-off"); MODULE_AUTHOR("Laxman Dewangan "); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/power/reset/gpio-poweroff.c b/drivers/power/reset/gpio-poweroff.c index 1c5af2fef142..84b3c3528afa 100644 --- a/drivers/power/reset/gpio-poweroff.c +++ b/drivers/power/reset/gpio-poweroff.c @@ -105,5 +105,4 @@ module_platform_driver(gpio_poweroff_driver); MODULE_AUTHOR("Jamie Lentin "); MODULE_DESCRIPTION("GPIO poweroff driver"); -MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:poweroff-gpio"); diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c index 5466eeea261c..35d981d5e6c8 100644 --- a/drivers/power/reset/gpio-restart.c +++ b/drivers/power/reset/gpio-restart.c @@ -139,4 +139,3 @@ module_platform_driver(gpio_restart_driver); MODULE_AUTHOR("David Riley "); MODULE_DESCRIPTION("GPIO restart driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c index 65d9528cc989..eea05921a054 100644 --- a/drivers/power/reset/ltc2952-poweroff.c +++ b/drivers/power/reset/ltc2952-poweroff.c @@ -317,4 +317,3 @@ module_platform_driver(ltc2952_poweroff_driver); MODULE_AUTHOR("René Moll "); MODULE_DESCRIPTION("LTC PowerPath power-off driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/power/reset/regulator-poweroff.c b/drivers/power/reset/regulator-poweroff.c index 20701203935f..7f87fbb8b051 100644 --- a/drivers/power/reset/regulator-poweroff.c +++ b/drivers/power/reset/regulator-poweroff.c @@ -79,5 +79,4 @@ module_platform_driver(regulator_poweroff_driver); MODULE_AUTHOR("Michael Klein "); MODULE_DESCRIPTION("Regulator poweroff driver"); -MODULE_LICENSE("GPL v2"); MODULE_ALIAS("platform:poweroff-regulator"); diff --git a/drivers/power/reset/restart-poweroff.c b/drivers/power/reset/restart-poweroff.c index 04d4228119b2..28f1822db162 100644 --- a/drivers/power/reset/restart-poweroff.c +++ b/drivers/power/reset/restart-poweroff.c @@ -59,5 +59,4 @@ module_platform_driver(restart_poweroff_driver); MODULE_AUTHOR("Andrew Lunn "); MODULE_DESCRIPTION("TPS65086 restart driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From 295ff94c888cb21de1e3d12b4252a5178c15e99d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:00 +0000 Subject: [PATCH 2972/5631] soc/tegra: cbb: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Thierry Reding Cc: Jonathan Hunter Cc: linux-tegra@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/soc/tegra/cbb/tegra194-cbb.c | 1 - drivers/soc/tegra/cbb/tegra234-cbb.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/soc/tegra/cbb/tegra194-cbb.c b/drivers/soc/tegra/cbb/tegra194-cbb.c index d4112b683f00..a2347e5b7c00 100644 --- a/drivers/soc/tegra/cbb/tegra194-cbb.c +++ b/drivers/soc/tegra/cbb/tegra194-cbb.c @@ -2359,4 +2359,3 @@ module_exit(tegra194_cbb_exit); MODULE_AUTHOR("Sumit Gupta "); MODULE_DESCRIPTION("Control Backbone error handling driver for Tegra194"); -MODULE_LICENSE("GPL"); diff --git a/drivers/soc/tegra/cbb/tegra234-cbb.c b/drivers/soc/tegra/cbb/tegra234-cbb.c index f33d094e5ea6..7268bb7ef448 100644 --- a/drivers/soc/tegra/cbb/tegra234-cbb.c +++ b/drivers/soc/tegra/cbb/tegra234-cbb.c @@ -1218,4 +1218,3 @@ static void __exit tegra234_cbb_exit(void) module_exit(tegra234_cbb_exit); MODULE_DESCRIPTION("Control Backbone 2.0 error handling driver for Tegra234"); -MODULE_LICENSE("GPL"); -- GitLab From a0d8881006d0ee96ff52b122b6bf98cc58eefe7c Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:00 +0000 Subject: [PATCH 2973/5631] irqchip: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Nishanth Menon Cc: Tero Kristo Cc: Santosh Shilimkar Cc: Thomas Gleixner Cc: Marc Zyngier Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/irqchip/irq-ti-sci-inta.c | 1 - drivers/irqchip/irq-ti-sci-intr.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index a6ecc53d055c..7133f9fa6fd9 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -743,4 +743,3 @@ module_platform_driver(ti_sci_inta_irq_domain_driver); MODULE_AUTHOR("Lokesh Vutla "); MODULE_DESCRIPTION("K3 Interrupt Aggregator driver over TI SCI protocol"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/irqchip/irq-ti-sci-intr.c b/drivers/irqchip/irq-ti-sci-intr.c index 020ddf29efb8..1186f1e431a3 100644 --- a/drivers/irqchip/irq-ti-sci-intr.c +++ b/drivers/irqchip/irq-ti-sci-intr.c @@ -303,4 +303,3 @@ module_platform_driver(ti_sci_intr_irq_domain_driver); MODULE_AUTHOR("Lokesh Vutla "); MODULE_DESCRIPTION("K3 Interrupt Router driver over TI SCI protocol"); -MODULE_LICENSE("GPL v2"); -- GitLab From 8493757372455f981d79a571487e85b8de80547b Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:01 +0000 Subject: [PATCH 2974/5631] bus: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Philipp Zabel Signed-off-by: Luis Chamberlain --- drivers/bus/bt1-apb.c | 1 - drivers/bus/bt1-axi.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/bus/bt1-apb.c b/drivers/bus/bt1-apb.c index 63b1b4a76671..e97c1d1c7578 100644 --- a/drivers/bus/bt1-apb.c +++ b/drivers/bus/bt1-apb.c @@ -416,4 +416,3 @@ module_platform_driver(bt1_apb_driver); MODULE_AUTHOR("Serge Semin "); MODULE_DESCRIPTION("Baikal-T1 APB-bus driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/bus/bt1-axi.c b/drivers/bus/bt1-axi.c index 70e49a6e5374..4007e7322cf2 100644 --- a/drivers/bus/bt1-axi.c +++ b/drivers/bus/bt1-axi.c @@ -309,4 +309,3 @@ module_platform_driver(bt1_axi_driver); MODULE_AUTHOR("Serge Semin "); MODULE_DESCRIPTION("Baikal-T1 AXI-bus driver"); -MODULE_LICENSE("GPL v2"); -- GitLab From ae6385af3740f2abb4b0ae8403af3de1a3c82725 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:01 +0000 Subject: [PATCH 2975/5631] braille_console: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- drivers/accessibility/braille/braille_console.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/accessibility/braille/braille_console.c b/drivers/accessibility/braille/braille_console.c index c4d54a5326b1..06b43b678d6e 100644 --- a/drivers/accessibility/braille/braille_console.c +++ b/drivers/accessibility/braille/braille_console.c @@ -24,7 +24,6 @@ MODULE_AUTHOR("samuel.thibault@ens-lyon.org"); MODULE_DESCRIPTION("braille device"); -MODULE_LICENSE("GPL"); /* * Braille device support part. -- GitLab From 92a72297821836b2f89153afdb8a8dcfa642084d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:02 +0000 Subject: [PATCH 2976/5631] drivers: bus: simple-pm-bus: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- drivers/bus/simple-pm-bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c index 7afe1947e1c0..4da77ca7b75a 100644 --- a/drivers/bus/simple-pm-bus.c +++ b/drivers/bus/simple-pm-bus.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Simple Power-Managed Bus Driver * @@ -138,4 +139,3 @@ module_platform_driver(simple_pm_bus_driver); MODULE_DESCRIPTION("Simple Power-Managed Bus Driver"); MODULE_AUTHOR("Geert Uytterhoeven "); -MODULE_LICENSE("GPL v2"); -- GitLab From 958adeefbd62d55fc1e68701dc2c9ef5a076615b Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:03 +0000 Subject: [PATCH 2977/5631] watch_queue: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- kernel/watch_queue.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index a6f9bdd956c3..5deed017bef4 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -29,7 +29,6 @@ MODULE_DESCRIPTION("Watch queue"); MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) -- GitLab From 0c9bf64c5b38ce4feb06a6d360ef0c9280340049 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:04 +0000 Subject: [PATCH 2978/5631] btree: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- lib/btree.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/btree.c b/lib/btree.c index a82100c73b55..49420cae3a83 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -794,4 +794,3 @@ module_exit(btree_module_exit); MODULE_AUTHOR("Joern Engel "); MODULE_AUTHOR("Johannes Berg "); -MODULE_LICENSE("GPL"); -- GitLab From 7f82b39dc3e41bc12a207101d961353875b05b7d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:05 +0000 Subject: [PATCH 2979/5631] treewide: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Signed-off-by: Luis Chamberlain --- lib/test_fprobe.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c index 1fb56cf5e5ce..fd6153800e56 100644 --- a/lib/test_fprobe.c +++ b/lib/test_fprobe.c @@ -168,4 +168,3 @@ static struct kunit_suite fprobe_test_suite = { kunit_test_suites(&fprobe_test_suite); -MODULE_LICENSE("GPL"); -- GitLab From 573858e85d7d390313fbc1f452ae764512f9819d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:06 +0000 Subject: [PATCH 2980/5631] unicode: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Acked-by: Gabriel Krisman Bertazi Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Gabriel Krisman Bertazi Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Luis Chamberlain --- fs/unicode/utf8-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index 67aaadc3ab07..8395066341a4 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -214,4 +214,3 @@ void utf8_unload(struct unicode_map *um) } EXPORT_SYMBOL(utf8_unload); -MODULE_LICENSE("GPL v2"); -- GitLab From be1c21f17ce2d1e8cdb6d27b88a5346cfebfae49 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:06 +0000 Subject: [PATCH 2981/5631] udmabuf: remove MODULE_LICENSE in non-modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Gerd Hoffmann Cc: Sumit Semwal Cc: "Christian König" Cc: dri-devel@lists.freedesktop.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Signed-off-by: Luis Chamberlain --- drivers/dma-buf/udmabuf.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index 740d6e426ee9..01f2e86f3f7c 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -430,4 +430,3 @@ module_init(udmabuf_dev_init) module_exit(udmabuf_dev_exit) MODULE_AUTHOR("Gerd Hoffmann "); -MODULE_LICENSE("GPL v2"); -- GitLab From 1c8744d83825e2dc5a773e321460030251d6925e Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:07 +0000 Subject: [PATCH 2982/5631] regulator: stm32-pwr: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Liam Girdwood Cc: Mark Brown Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: linux-stm32@st-md-mailman.stormreply.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Luis Chamberlain --- drivers/regulator/stm32-pwr.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/regulator/stm32-pwr.c b/drivers/regulator/stm32-pwr.c index 2a42acb7c24e..8711afd60ade 100644 --- a/drivers/regulator/stm32-pwr.c +++ b/drivers/regulator/stm32-pwr.c @@ -183,4 +183,3 @@ module_platform_driver(stm32_pwr_driver); MODULE_DESCRIPTION("STM32MP1 PWR voltage regulator driver"); MODULE_AUTHOR("Pascal Paillet "); -MODULE_LICENSE("GPL v2"); -- GitLab From 569e4d25f45ca4902566075e38a52eadd760b5da Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:08 +0000 Subject: [PATCH 2983/5631] x86/mm/dump_pagetables: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: x86@kernel.org Signed-off-by: Luis Chamberlain --- arch/x86/mm/debug_pagetables.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index 092ea436c7e6..b43301cb2a80 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -71,6 +71,5 @@ static void __exit pt_dump_debug_exit(void) module_init(pt_dump_debug_init); module_exit(pt_dump_debug_exit); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arjan van de Ven "); MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); -- GitLab From 68ac126576a5ac0986ca64fa96ad8648da3cb751 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:09 +0000 Subject: [PATCH 2984/5631] zpool: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Dan Streetman Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Luis Chamberlain --- mm/zpool.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/zpool.c b/mm/zpool.c index 571f5c5031dd..6a19c4a58f77 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -395,6 +395,5 @@ bool zpool_can_sleep_mapped(struct zpool *zpool) return zpool->driver->sleep_mapped; } -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dan Streetman "); MODULE_DESCRIPTION("Common API for compressed memory storage"); -- GitLab From 7e137102ae97c42099c90d01fa01a6c05bf742ab Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Tue, 7 Mar 2023 18:02:10 +0000 Subject: [PATCH 2985/5631] zswap: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Seth Jennings Cc: Dan Streetman Cc: Vitaly Wool Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Luis Chamberlain --- mm/zswap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/mm/zswap.c b/mm/zswap.c index f6c89049cf70..f2fc0373b967 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1540,6 +1540,5 @@ static int __init init_zswap(void) /* must be late so crypto has time to come up */ late_initcall(init_zswap); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Seth Jennings "); MODULE_DESCRIPTION("Compressed cache for swap pages"); -- GitLab From c0a8c5d04733a912e9fb4c5be6759e6708003ee6 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Mon, 20 Mar 2023 10:46:24 +0000 Subject: [PATCH 2986/5631] interconnect: remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Georgi Djakov Cc: linux-pm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/interconnect/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 0f392f59b135..7f4f9740b171 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1150,4 +1150,3 @@ device_initcall(icc_init); MODULE_AUTHOR("Georgi Djakov "); MODULE_DESCRIPTION("Interconnect Driver Core"); -MODULE_LICENSE("GPL v2"); -- GitLab From 560db7ccf96dda75592c6d2a604c1e296104fe7a Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Mon, 20 Mar 2023 10:48:10 +0000 Subject: [PATCH 2987/5631] interconnect: remove module-related code Now the interconnect core can no longer be a module, drop all remaining module-related code as well. Signed-off-by: Nick Alcock Requested-by: Georgi Djakov Cc: Luis Chamberlain Cc: linux-modules@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Hitomi Hasegawa Cc: Georgi Djakov Cc: linux-pm@vger.kernel.org Signed-off-by: Luis Chamberlain --- drivers/interconnect/core.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 7f4f9740b171..a112d7da43a7 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -1147,6 +1146,3 @@ static int __init icc_init(void) } device_initcall(icc_init); - -MODULE_AUTHOR("Georgi Djakov "); -MODULE_DESCRIPTION("Interconnect Driver Core"); -- GitLab From b4aff7513df323553de714dcf7b54e896577be1f Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Thu, 13 Apr 2023 14:00:55 -0700 Subject: [PATCH 2988/5631] scripts/gdb: use mem instead of core_layout to get the module address commit ac3b43283923 ("module: replace module_layout with module_memory") changed the struct module data structure from module_layout to module_memory. The core_layout member which is used while loading modules are not available anymore leading to the following error while running gdb: (gdb) lx-symbols loading vmlinux Python Exception : There is no member named core_layout. Error occurred in Python: There is no member named core_layout. Replace core_layout with its new counterpart mem[MOD_TEXT]. Fixes: ac3b43283923 ("module: replace module_layout with module_memory") Signed-off-by: Pankaj Raghav Signed-off-by: Luis Chamberlain --- scripts/gdb/linux/constants.py.in | 3 +++ scripts/gdb/linux/modules.py | 4 ++-- scripts/gdb/linux/symbols.py | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 2efbec6b6b8d..8085d3693a05 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -54,6 +54,9 @@ LX_VALUE(SB_NODIRATIME) /* linux/htimer.h */ LX_GDBPARSED(hrtimer_resolution) +/* linux/module.h */ +LX_GDBPARSED(MOD_TEXT) + /* linux/mount.h */ LX_VALUE(MNT_NOSUID) LX_VALUE(MNT_NODEV) diff --git a/scripts/gdb/linux/modules.py b/scripts/gdb/linux/modules.py index 441b23239896..261f28640f4c 100644 --- a/scripts/gdb/linux/modules.py +++ b/scripts/gdb/linux/modules.py @@ -13,7 +13,7 @@ import gdb -from linux import cpus, utils, lists +from linux import cpus, utils, lists, constants module_type = utils.CachedType("struct module") @@ -73,7 +73,7 @@ class LxLsmod(gdb.Command): " " if utils.get_long_type().sizeof == 8 else "")) for module in module_list(): - layout = module['core_layout'] + layout = module['mem'][constants.LX_MOD_TEXT] gdb.write("{address} {name:<19} {size:>8} {ref}".format( address=str(layout['base']).split()[0], name=module['name'].string(), diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index dc07b6d12e30..fdad3f32c747 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -15,7 +15,7 @@ import gdb import os import re -from linux import modules, utils +from linux import modules, utils, constants if hasattr(gdb, 'Breakpoint'): @@ -109,7 +109,7 @@ lx-symbols command.""" def load_module_symbols(self, module): module_name = module['name'].string() - module_addr = str(module['core_layout']['base']).split()[0] + module_addr = str(module['mem'][constants.LX_MOD_TEXT]['base']).split()[0] module_file = self._get_module_file(module_name) if not module_file and not self.module_files_updated: -- GitLab From 54f5de6f2998cfefbb68e7f6b2672f0b0ea5ab24 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:29 -0700 Subject: [PATCH 2989/5631] perf vendor events intel: Update sapphirerapids to v1.12 Summary from https://github.com/intel/perfmon/pull/68 - Numerous uncore event additions and changes. - Description updates for core events XQ.FULL_CYCLES and MISC2_RETIRED.LFENCE. - Update ARITH.IDIV_ACTIVE counter mask. This change also gets rid of uncore-other as a topic, derived from the file name, breaking it apart in to more specific topics. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- .../arch/x86/sapphirerapids/other.json | 3 +- .../arch/x86/sapphirerapids/pipeline.json | 4 +- .../arch/x86/sapphirerapids/uncore-cache.json | 5644 +++++++++++++++ .../arch/x86/sapphirerapids/uncore-cxl.json | 450 ++ .../sapphirerapids/uncore-interconnect.json | 6199 +++++++++++++++++ .../arch/x86/sapphirerapids/uncore-io.json | 3651 ++++++++++ .../x86/sapphirerapids/uncore-memory.json | 3283 ++++++++- .../arch/x86/sapphirerapids/uncore-other.json | 4525 ------------ .../arch/x86/sapphirerapids/uncore-power.json | 107 + 10 files changed, 19122 insertions(+), 4746 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json create mode 100644 tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cxl.json create mode 100644 tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 58faf18474b5..437eeecfaf64 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -22,7 +22,7 @@ GenuineIntel-6-A[AC],v1.01,meteorlake,core GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-(8F|CF),v1.11,sapphirerapids,core +GenuineIntel-6-(8F|CF),v1.12,sapphirerapids,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v55,skylake,core GenuineIntel-6-55-[01234],v1.29,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json index 5d4c15dbf4d3..31b6be9fb8c7 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/other.json @@ -331,10 +331,11 @@ "UMask": "0x7" }, { - "BriefDescription": "XQ.FULL_CYCLES", + "BriefDescription": "Cycles the uncore cannot take further requests", "CounterMask": "1", "EventCode": "0x2d", "EventName": "XQ.FULL_CYCLES", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json index 40e52357ade1..72e9bdfa9f80 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json @@ -44,6 +44,7 @@ }, { "BriefDescription": "This event counts the cycles the integer divider is busy.", + "CounterMask": "1", "EventCode": "0xb0", "EventName": "ARITH.IDIV_ACTIVE", "SampleAfterValue": "1000003", @@ -655,9 +656,10 @@ "UMask": "0x4" }, { - "BriefDescription": "MISC2_RETIRED.LFENCE", + "BriefDescription": "LFENCE instructions retired", "EventCode": "0xe0", "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", "SampleAfterValue": "400009", "UMask": "0x20" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json new file mode 100644 index 000000000000..b91cebf81f50 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json @@ -0,0 +1,5644 @@ +[ + { + "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA Clockticks", + "EventCode": "0x01", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of CHA clock cycles while the event is enabled", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x12", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : Shared hit and op is RdInvOwn, RdInv, Inv*", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : op is WbMtoE", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", + "EventCode": "0x5e", + "EventName": "UNC_CHA_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5e", + "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : No SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HitME$ on Reads without RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request : Received RspFwdI* for a local request, but converted HitME$ to SF entry", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache on RdInvOwn even if not RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request : Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache to SHARed", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued : ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1fffff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All transactions from Remote Agents", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All transactions from Remote Agents : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x17e0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local non-prefetch requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local non-prefetch requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, not including prefetch", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Request : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Read transactions.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand Data Reads, Core and LLC prefetches", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Demand Data Reads, Core and LLC prefetches : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fc101", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Exclusive State", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : F State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Forward State", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a44ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : I State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.I", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Miss", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local LLC prefetch requests (from LLC)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local LLC prefetch to the LLC", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCALLY_HOMED_ADDRESS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "UMask": "0xbdfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x19d0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x19c1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand CRd Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1850ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Demand Data Reads that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand RFO Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1848ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1844ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Prefetch requests to the LLC that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_LLC_PF", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x189dff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x199dff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1910ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1981ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1908ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x19c8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : M State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.M", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Modified State", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fe001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Write Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote non-snoop requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.PREF_OR_DMND_REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote non-snoop requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Remote non-snoop transactions to the LLC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTELY_HOMED_ADDRESS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "UMask": "0x15dfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1a10ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Requests that come from a Remote socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1a01ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a04ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache that come from a remote socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_OTHER", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x1a02ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1a08ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote snoop requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote snoop requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Remote snoop transactions to the LLC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1c19ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1bc8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally HOMed RFOs - Demand and Prefetches", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x9c8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Shared State", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - H State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit HitMe State", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit Shared State", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Writes", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Requests that install or change a line in the LLC. Examples: Writebacks from Core L2's and UPI. Prefetches into the LLC.", + "UMask": "0x842ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote Writes", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x17c2ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : IA traffic", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IA", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : IA traffic : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : IO traffic", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : IO traffic : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in E state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x12", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in F or S state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_FS", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1c", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in M state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in any state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_MESF", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x200f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x800f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in E state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in M state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in S state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Off", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.OFF_PWRHEURISTIC", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Off : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READINVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.RFO_HITS_SNP_BCAST", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near Memory set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", + "PerPkg": "1", + "PublicDescription": "Near Memory evictions due to another read to the same Near Memory set in the LLC.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near memory set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", + "PerPkg": "1", + "PublicDescription": "Near Memory evictions due to another read to the same Near Memory set in the SF", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near Memory set conflict in TOR", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", + "PerPkg": "1", + "PublicDescription": "No Reject in the CHA due to a pending read to the same Near Memory set in the TOR.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.REJ_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.REJ_IRQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "PerPkg": "1", + "PublicDescription": ": count # of FAST TOR Request inserted to ha_tor_req_fifo", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of SLOW TOR Request inserted to ha_pmm_tor_req_fifo", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Remote requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests made into the CHA", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a remote socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Write requests made into the CHA", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Write Requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Read and Write Requests; Writes Remote", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IPQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IPQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : RRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : RRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : WBQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : WBQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IPQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : ANY0", + "EventCode": "0x2d", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : HA", + "EventCode": "0x2d", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IPQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : IPQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : RRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : RRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : WBQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : WBQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Allow Snoop", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : ANY0", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : HA", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : SF Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : ANY0", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : HA", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : ANY0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Any condition listed in the RRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : HA", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : HA : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : SF Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : ANY0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : HA", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : HA : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : SF Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoop for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoop for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast or directed Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast or directed Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast or directed Snoops sent for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast or directed Snoops sent for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RSPCNFLCT*", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RSPCNFLCT* : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspFwd", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RspFwd : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*Fwd*WB", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*Fwd*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RspS Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspS Snoop Response was received which indicates when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*WB", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspCnflct", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspI", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspIFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspS", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspSFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*WB", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DDR Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DDR Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Hits", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from IA Cores", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlush from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlush events that are initiated from the Core", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlushOpt from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlushOpt events that are initiated from the Core", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read from local IA that hits in the snoop filter", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that hits in the snoop filter", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that hits in the snoop filter", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that hits in the snoop filter", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that hits in the snoop filter", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that hits in the snoop filter", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that hits in the snoop filter", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that hits in the snoop filter", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;ItoM from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; ItoM events that are initiated from the Core", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA.", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; misses from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for CRd misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode CRd", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "CRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c80b8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8138201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by IA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting local memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting local memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target local memory", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting remote memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target remote memory", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting remote memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and target remote memory", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that misses in the snoop filter", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC Prefetch Code transactions issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10cccf8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "RFO and L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFOMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8038201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;SpecItoM from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; SpecItoM events that are initiated from the Core", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc3fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc37ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc2fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc67ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoM from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO with the opcode ItoM", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoMCacheNears from IO devices.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO devices with the opcode ItoMCacheNears. This event indicates a partial write request.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for RdCur from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO with the opcode RdCur", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IPQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IPQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - Non iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just ISOC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Local Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Misses", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMCFG Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMIO Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMIO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMIO Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NonCoherent", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NotNearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PMM Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PM Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - Non IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Remote Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Remote Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All remote requests (e.g. snoops, writebacks) that came from remote sockets", + "UMask": "0xc001ffc8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All Snoops from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_SNPS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All Snoops from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All snoops to this LLC that came from remote sockets", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RRQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All Snoops from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.SNPS_FROM_REM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WBQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DDR Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DDR Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Hits", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that hits in the snoop filter", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that hits in the snoop filter", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that hits in the snoop filter", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that hits in the snoop filter", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that hits in the snoop filter", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that hits in the snoop filter", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that hits in the snoop filter", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that hits in the snoop filter", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for CRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c80b8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8138201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting local memory", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting remote memory", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target remote memory", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that misses in the snoop filter", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for LLC Prefetch Code transactions issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10cccf8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for RFO and L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFOMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8038201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ItoM from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IPQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IPQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - Non iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just ISOC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Local Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA and IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Misses", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMCFG Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMIO Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMIO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMIO Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NonCoherent", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NotNearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PMM Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PMM Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Remote Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Remote Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All remote requests (e.g. snoops, writebacks) that came from remote sockets", + "UMask": "0xc001ffc8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All Snoops from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_SNPS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All Snoops from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All snoops to this LLC that came from remote sockets", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RRQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All Snoops from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.SNPS_FROM_REM", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WBQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WBQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 0?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT0", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 1?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT1", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", + "UMask": "0x10", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cxl.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cxl.json new file mode 100644 index 000000000000..f3e84fd88de3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cxl.json @@ -0,0 +1,450 @@ +[ + { + "BriefDescription": "Counts the number of lfclk ticks", + "EventCode": "0x01", + "EventName": "UNC_CXLCM_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx AGF 0", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req AGF0", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_REQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_REQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_RSP0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_RSP1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req AGF 1", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with AK set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.AK_HDR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with BE set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.BE_HDR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of control flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.CTRL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Headerless flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.NO_HDR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of protocol flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.PROT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with SZ set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.SZ_HDR", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.VALID", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of valid messages in the flit", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.VALID_MSG", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of CRC errors detected", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.CRC_ERRORS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Init flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.INIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of LLCRD flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.LLCRD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Retry flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.RETRY", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Data Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Req Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Rsp Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Mem Data Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Mem Rxx Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with AK set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.AK_HDR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with BE set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.BE_HDR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of control flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.CTRL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Headerless flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.NO_HDR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of protocol flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.PROT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with SZ set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.SZ_HDR", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.VALID", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_REQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp1 Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_REQ1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp0 Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_RSP0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_RSP1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Counts the number of uclk ticks", + "EventCode": "0x01", + "EventName": "UNC_CXLDP_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to M2S Data AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to M2S Req AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Data AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Req AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Rsp AGF 0", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_RSP0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Rsp AGF 1", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_RSP1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLDP" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json new file mode 100644 index 000000000000..08faf38115d9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json @@ -0,0 +1,6199 @@ +[ + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", + "EventCode": "0x0f", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "IRP Clockticks", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of IRP clock cycles while the event is enabled", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF - request insert from TC.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF occupancy", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.EVICTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Lost Forward", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Invalid", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Valid", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0x0b", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x05", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x02", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x08", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x06", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x03", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x09", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x07", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x04", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0x0a", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "EventCode": "0x1c", + "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0AD1 both. Stalls on both AD0 and AD1 will count as 2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD0 Egress Credits Stalls", + "EventCode": "0x1a", + "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD1 Egress Credits Stalls", + "EventCode": "0x1b", + "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1d", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0d", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0e", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0x0c", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "M2M Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to memory (M2M)", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x17", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress", + "EventCode": "0x17", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress : Counts the number of time non cisgress D2C was not honoured by egress due to directory state constraints", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Counts the time when FM didn? do d2c for fill reads (cross tile case)", + "EventCode": "0x4a", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : Cisgress", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : 2LM Hit?", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE.PMM_HIT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1C", + "EventName": "UNC_M2M_DIRECT2UPITXN_OVERRIDE.PMM_HIT", + "PerPkg": "1", + "PublicDescription": "Number of times a direct to UPI transaction was overridden. : Counts the number of times D2K wasn't honored even though the incoming request had d2k set", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "EventCode": "0x1b", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "EventCode": "0x1a", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored : Counts cisgress d2K that was not honored due to directory constraints", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.EGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U : Counts the number of time D2K was not honoured by egress due to directory state constraints", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored : Counts non cisgress d2K that was not honored due to directory constraints", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "EventCode": "0x19", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times egress did D2K (Direct to KTI)", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "EventCode": "0x1c", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1C", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with any directory to non persistent memory", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory A to non persistent memory", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory I to non persistent memory", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory S to non persistent memory", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_I_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to I to non persistent memory (DRAM or HBM)", + "UMask": "0x120", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_I_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to I to non persistent memory (DRAM or HBM)", + "UMask": "0x220", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_S_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to S to non persistent memory (DRAM or HBM)", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_S_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to S to non persistent memory (DRAM or HBM)", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts any 1lm or 2lm hit data return that would result in directory update to non persistent memory (DRAM or HBM)", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_A_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to A to non persistent memory (DRAM or HBM)", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_A_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to A to non persistent memory (DRAM or HBM)", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_S_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to S to non persistent memory (DRAM or HBM)", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_S_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to S to non persistent memory (DRAM or HBM)", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts any 2lm miss data return that would result in directory update to non persistent memory (DRAM or HBM)", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_A_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to A to non persistent memory (DRAM or HBM)", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_A_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to A to non persistent memory (DRAM or HBM)", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_I_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to I to non persistent memory (DRAM or HBM)", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_I_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to I to non persistent memory (DRAM or HBM)", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000004", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000001", + "Unit": "M2M" + }, + { + "BriefDescription": "Count when Starve Glocab counter is at 7", + "EventCode": "0x44", + "EventName": "UNC_M2M_IGR_STARVE_WINNER.MASK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0.TO_NMCache", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0.TO_NMCache", + "PerPkg": "1", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x120", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1.TO_NMCache", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1.TO_NMCache", + "PerPkg": "1", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x220", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_NMCACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_NMCACHE", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_PMM", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2M" + }, + { + "BriefDescription": "All Writes - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1810", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_ALL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x810", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_FULL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x801", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x802", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x840", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x820", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "PMM - Ch0 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x880", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1010", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1001", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Full Line - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1004", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1002", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Partial - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1008", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x1040", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x1020", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "PMM - Ch1 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x1080", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Full Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1801", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Full Line - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1804", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1802", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Partial - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1808", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x1840", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x1820", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", + "PerPkg": "1", + "UMask": "0x1880", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", + "EventCode": "0x5c", + "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": ": UPI - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": ": XPT - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.RD_MERGED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.WR_MERGED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.WR_SQUASHED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "PublicDescription": "Prefetch CAM Inserts : XPT -All Channels", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "All Channels", + "EventCode": "0x5F", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x5f", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x5f", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", + "EventCode": "0x60", + "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x03", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Clean NearMem Read Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Counts clean full line read hits (reads and RFOs).", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Dirty NearMem Read Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Counts dirty full line read hits (reads and RFOs).", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Clean NearMem Underfill Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean underfill hits due to a partial write", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Dirty NearMem Underfill Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty underfill read hits due to a partial write", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_TAG_MISS", + "EventCode": "0x4b", + "EventName": "UNC_M2M_TAG_MISS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x2e", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x2f", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x42", + "EventName": "UNC_M2M_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x42", + "EventName": "UNC_M2M_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x37", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x37", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x38", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x38", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x40", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x40", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x4d", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x4d", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x4c", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x4c", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x48", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x48", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CBox AD Credits Empty : Requests", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Requests : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Snoops", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Snoops : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : VNA Messages", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : VNA Messages : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Writebacks", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Writebacks : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M3UPI Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of M2UPI clock cycles while the event is enabled", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M3UPI CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "EventCode": "0x2b", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "PublicDescription": "D2C Sent : Count cases BL sends direct to core", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "EventCode": "0x2a", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "PublicDescription": "D2U Sent : Cases where SMI3 sends D2U command", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO1_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only) : No vn0 and vna credits available to send to M2", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO2", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO2 : No vn0 and vna credits available to send to M2", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO3", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO3 : No vn0 and vna credits available to send to M2", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO4", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO4 : No vn0 and vna credits available to send to M2", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together : No vn0 and vna credits available to send to M2", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits : No vn0 and vna credits available to send to M2", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.UBOX_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 1", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 1 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 2", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 2", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : BL - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : BL - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : REQ on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : REQ on AD : VN0 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on AD : VN0 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : SNP on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : SNP on AD : VN0 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCB on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCB on BL : VN0 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCS on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCS on BL : VN0 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on BL : VN0 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : WB on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : WB on BL : VN0 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : REQ on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : REQ on AD : VN1 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on AD : VN1 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : SNP on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : SNP on AD : VN1 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCB on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCB on BL : VN1 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCS on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCS on BL : VN1 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on BL : VN1 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : WB on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : WB on BL : VN1 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : Max Parallel Win", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ALL_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : Max Parallel Win : VN0 and VN1 arbitration sub-pipelines both produced AD and BL winners (maximum possible parallel winners)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN0 : Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN1 : Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN0 : Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN1 : Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.VN01_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win : VN0 and VN1 arbitration sub-pipelines had parallel winners (at least one AD or BL on each side)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : REQ on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : REQ on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : SNP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : SNP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCS on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCS on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : WB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : WB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : REQ on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : REQ on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : SNP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : SNP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCS on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCS on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : WB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : WB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : REQ on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : REQ on AD : VN0 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : SNP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : SNP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCS on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCS on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on BL : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : WB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : WB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : REQ on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : REQ on AD : VN1 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : SNP on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : SNP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCB on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCS on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCS on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on BL : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : WB on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : WB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 1", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 1 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 2", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 2 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any In BGF FIFO", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any In BGF FIFO : Indication that at least one packet (flit) is in the bgf (fifo only)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any in BGF Path", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any in BGF Path : Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT1_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT2_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : No D2K For Arb", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN0_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : No D2K For Arb : VN0 BL RSP message was blocked from arbitration request due to lack of D2K CMP credit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN1_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Credits Consumed", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.CONSUMED", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Credits Consumed : number of remote vna credits consumed per cycle", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : D2K Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : D2K Credits : D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF FIFO", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF FIFO : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF Path", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF Path : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in completion fifo only", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in marker table and in fifo", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Transmit Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Transmit Credits : Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : VNA In Use", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : VNA In Use : Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : All", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : All : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but could not be sent for any reason, e.g. low credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No BGF Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_BGF", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No BGF Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No TxQ Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_TXQ", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No TxQ Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : TSV High", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : TSV High : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : Cycle valid for Flit", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : Cycle valid for Flit : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 0", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 0 : generating bl data flit sequence; waiting for data pump 0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is tracking at least one message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending completion fifo is full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : a bl message finished but is in limbo and moved to pump-1-pending logic", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 1", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 1 : generating bl data flit sequence; waiting for data pump 1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "PerPkg": "1", + "PublicDescription": ": slot 2 request naturally serviced during hold-off period", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "PerPkg": "1", + "PublicDescription": ": slot 2 request forcibly serviced during service window", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "PerPkg": "1", + "PublicDescription": ": slot 2 request received from link layer while idle (with no slot 2 request active immediately prior)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "PerPkg": "1", + "PublicDescription": ": slot 2 request withdrawn during hold-off period or service window", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : All", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Needs Data Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Needs Data Flit : BL message requires data flit sequence", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0 : Waiting for header pump 0", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 : Header pump 1 is not required for flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble : Header pump 1 is not required for flit but flit transmission delayed", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail : Header pump 1 is not required for flit and not available", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1 : Waiting for header pump 1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate : Events related to Header Flit Generation - Set 1 : Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Ready", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Ready : Events related to Header Flit Generation - Set 1 : header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Wasted", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Wasted : Events related to Header Flit Generation - Set 1 : Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked : Events related to Header Flit Generation - Set 1 : Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: message was slotted only after run-ahead was over; run-ahead mode definitely wasted", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Message", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_DURING", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Message : Events related to Header Flit Generation - Set 1 : run-ahead mode: one message slotted during run-ahead", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: second message slotted immediately after run-ahead; potential run-ahead success", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_SENT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: two (or three) message flit sent immediately after run-ahead; complete run-ahead success", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Ok", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Ok : Events related to Header Flit Generation - Set 2 : new header flit construction may proceed in parallel with data flit sequence", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Flit Finished", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_FLIT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Flit Finished : Events related to Header Flit Generation - Set 2 : header flit finished assembly in parallel with data flit sequence", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_MSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Message : Events related to Header Flit Generation - Set 2 : message is slotted into header flit in parallel with data flit sequence", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall : Events related to Header Flit Generation - Set 2 : Rate-matching stall injected", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message : Events related to Header Flit Generation - Set 2 : Rate matching stall injected, but no additional message slotted during stall cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message : One message in flit; VNA or non-VNA flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message in non-VNA", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG_VNX", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message in non-VNA : One message in flit; non-VNA flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.2_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Two Messages : Two messages in flit; VNA flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Three Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.3_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Three Messages : Three messages in flit; VNA flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Slot Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_2", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : All Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_3", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : All", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : All : header flit is ready for transmission but could not be sent : header flit is ready for transmission but could not be sent for any reason, e.g. no credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits : header flit is ready for transmission but could not be sent : No BGF credits available", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No BGF credits available; no additional message slotted into flit", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits : header flit is ready for transmission but could not be sent : No TxQ credits available", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No TxQ credits available; no additional message slotted into flit", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : TSV High", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : TSV High : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : Cycle valid for Flit", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : Cycle valid for Flit : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot AD : some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot BL : some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Attempt", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Attempt : ad and bl messages attempted to slot into the same flit in parallel", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Success", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN0", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN0", + "PerPkg": "1", + "PublicDescription": "Message Held : VN0 : vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN1", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN1", + "PerPkg": "1", + "PublicDescription": "Message Held : VN1 : vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : REQ on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : SNP on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCB on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCS on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : WB on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : REQ on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : SNP on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCB on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCS on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : WB on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Any In Use", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Any In Use : At least one remote vna credit is in use", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Corrected", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Corrected : Number of remote vna credits corrected (local return) per cycle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 1", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 1 : Remote vna credit level is less than 1 (i.e. no vna credits available)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 10", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT10", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 10 : remote vna credit level is less than 10; parallel vn0/vn1 arb not possible", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 4", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 4 : Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 5", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 5 : Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 5 and allocation to ad or bl messages was required", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 10 and allocation to vn0 or vn1 was required", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn0, not to vn1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn1, not to vn0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 REQ Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 SNP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 REQ Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 SNP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 REQ Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 SNP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 REQ Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 SNP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Inserts", + "EventCode": "0x2f", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Occupancy", + "EventCode": "0x1e", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCS Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 WB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCS Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCS Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_THROUGH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_WRPULL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_LOCAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_THROUGH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_WRPULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VNA", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VNA : No credits available to send to UPIs on the AD Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VNA", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VNA : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FlowQ Generated Prefetch", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : WB on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : WB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : NCB on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : NCB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : REQ on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : REQ on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : SNP on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : SNP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : WB on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : WB on BL : Number of Cycles there were no VN0 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : NCB on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : NCB on BL : Number of Cycles there were no VN0 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : REQ on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : REQ on AD : Number of Cycles there were no VN0 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on AD : Number of Cycles there were no VN0 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : SNP on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : SNP on AD : Number of Cycles there were no VN0 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on BL : Number of Cycles there were no VN0 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : WB on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : WB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : NCB on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : NCB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : REQ on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : REQ on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : SNP on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : SNP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : WB on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : WB on BL : Number of Cycles there were no VN1 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : NCB on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : NCB on BL : Number of Cycles there were no VN1 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : REQ on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : REQ on AD : Number of Cycles there were no VN1 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on AD : Number of Cycles there were no VN1 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : SNP on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : SNP on AD : Number of Cycles there were no VN1 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on BL : Number of Cycles there were no VN1 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xc0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message is making arbitration request", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message arrived in ingress pipeline", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message took bypass path", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was slotted into flit (non bypass)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message lost arbitration", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it became too old", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it was overwritten by new message while prefetch queue was full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AD Bouncable)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AD credited)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "AD credited : Number of allocations into the CRS Egress", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AK)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "AK : Number of allocations into the CRS Egress", + "UMask": "0x10", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AKC)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AKC", + "PerPkg": "1", + "PublicDescription": "AKC : Number of allocations into the CRS Egress", + "UMask": "0x40", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (BL Bouncable)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress", + "UMask": "0x4", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (BL credited)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "BL credited : Number of allocations into the CRS Egress", + "UMask": "0x8", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (IV)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "IV : Number of allocations into the CRS Egress", + "UMask": "0x20", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD", + "PerPkg": "1", + "PublicDescription": "AD : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK", + "PerPkg": "1", + "PublicDescription": "AK : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x4", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC", + "PerPkg": "1", + "PublicDescription": "AKC : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x10", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL", + "PerPkg": "1", + "PublicDescription": "BL : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV", + "PerPkg": "1", + "PublicDescription": "IV : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x8", + "Unit": "MDF" + }, + { + "BriefDescription": "Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "EventCode": "0x15", + "EventName": "UNC_MDF_FAST_ASSERTED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "AD bnc : Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "EventCode": "0x15", + "EventName": "UNC_MDF_FAST_ASSERTED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "BL bnc : Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "UPI Clockticks", + "EventCode": "0x01", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of UPI LL clock cycles while the event is enabled", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2C", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2C : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2K", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2K : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L1", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L1 : Number of UPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a UPI link. Use edge detect to count the number of instances when the UPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "EventCode": "0x16", + "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", + "EventCode": "0x20", + "EventName": "UNC_UPI_PHY_INIT_CYCLES", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req Nack", + "EventCode": "0x23", + "EventName": "UNC_UPI_POWER_L1_NACK", + "PerPkg": "1", + "PublicDescription": "L1 Req Nack : Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req (same as L1 Ack).", + "EventCode": "0x22", + "EventName": "UNC_UPI_POWER_L1_REQ", + "PerPkg": "1", + "PublicDescription": "L1 Req (same as L1 Ack). : Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x24", + "EventName": "UNC_UPI_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.DATA", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.LLCRD", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.LLCTRL", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.NULL", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.PROTHDR", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT0", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT1", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT2", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 0 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 1 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 2 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "CRC Errors Detected", + "EventCode": "0x0b", + "EventName": "UNC_UPI_RxL_CRC_ERRORS", + "PerPkg": "1", + "PublicDescription": "CRC Errors Detected : Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", + "Unit": "UPI" + }, + { + "BriefDescription": "LLR Requests Sent", + "EventCode": "0x08", + "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", + "PerPkg": "1", + "PublicDescription": "LLR Requests Sent : Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs..", + "Unit": "UPI" + }, + { + "BriefDescription": "VN0 Credit Consumed", + "EventCode": "0x39", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Consumed : Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN1 Credit Consumed", + "EventCode": "0x3a", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Consumed : Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x38", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Idle", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Idle : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCRD Not Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCTRL", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Non Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Protocol Header", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 0", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 1", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 2", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 0 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 1 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 2 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 0 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 1 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 2 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x26", + "EventName": "UNC_UPI_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.DATA", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.LLCRD", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.LLCTRL", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.NULL", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.PROTHDR", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT0", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT1", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT2", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Bypassed : Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the UPI Link. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Data : Counts number of data flits across this UPI link.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All LLCRD Not Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x17", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All LLCTRL", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All LLCTRL : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "All Null Flits", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Protocol Header", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All ProtDDR : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x87", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Idle", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Idle : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCTRL", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Non Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Protocol Header", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 0", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 1", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 2", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "EventCode": "0x45", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x44", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "VNA Credits Pending Return - Occupancy : Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Message Received : Doorbell", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Interrupt", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Message Received : Interrupt : Interrupts", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "EventCode": "0x4f", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "EventCode": "0x4f", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json new file mode 100644 index 000000000000..8b5f54fed103 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-io.json @@ -0,0 +1,3651 @@ +[ + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", + "PerPkg": "1", + "UMask": "0x23", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", + "PerPkg": "1", + "UMask": "0x25", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", + "PerPkg": "1", + "UMask": "0x26", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART0_FREERUN", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART1_FREERUN", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART2_FREERUN", + "PerPkg": "1", + "UMask": "0x32", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART3_FREERUN", + "PerPkg": "1", + "UMask": "0x33", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART4_FREERUN", + "PerPkg": "1", + "UMask": "0x34", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART5_FREERUN", + "PerPkg": "1", + "UMask": "0x35", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART6_FREERUN", + "PerPkg": "1", + "UMask": "0x36", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_OUT.PART7_FREERUN", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "IIO Clockticks", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "Number of IIO clock cycles while the event is enabled", + "Unit": "IIO" + }, + { + "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", + "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x7002004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x7004004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x7008004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x7010004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x7020004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x7040004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x7080004", + "Unit": "IIO" + }, + { + "BriefDescription": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 0", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7000001", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 1", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 1", + "UMask": "0x7000002", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 2", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7000004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 3", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 3", + "UMask": "0x7000008", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 4", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7000010", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 5", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 1", + "UMask": "0x7000020", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 6", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7000040", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 3", + "UMask": "0x7000080", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0-7", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080004", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0-7 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0100", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0200", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part1 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part2 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part3 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part1 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part2 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part3 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Passing data to be written", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Request Ownership", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Writing line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff002", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff001", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Request Ownership", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Writing line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache hits", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache lookups", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups first", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "IOTLB Fills (same as IOTLB miss)", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.MISSES", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOMMU memory access", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", + "PerPkg": "1", + "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", + "UMask": "0xc0", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWT Hit to a 256T page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_256T_HITS", + "PerPkg": "1", + "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 4K page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache fill", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache lookup", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_256T_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Global IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.PWT_OCCUPANCY_MSB", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : All", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0FFF", + "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Abort", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Memory", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : MsgB", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Ubox", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "ITC address map 1", + "EventCode": "0x8f", + "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", + "EventCode": "0xd0", + "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", + "EventCode": "0xd1", + "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PWT occupancy. Does not include 9th bit of occupancy (will undercount if PWT is greater than 255 per cycle).", + "EventCode": "0x42", + "EventName": "UNC_IIO_PWT_OCCUPANCY", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : PCIe Request complete", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : PCIe Request complete : Only for posted requests : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Writing line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Writing line : Only for posted requests : Only for posted requests", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Issuing final read or write of line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Issuing final read or write of line : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Passing data to be written", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Passing data to be written : Only for posted requests : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Passing data to be written", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Passing data to be written : Only for posted requests", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Issuing final read or write of line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x70ff002", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Request Ownership", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Request Ownership : Only for posted requests", + "UMask": "0x70ff001", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Writing line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Writing line : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Passing data to be written", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Request Ownership", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Writing line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x7004002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x7010002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x7020002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x7040002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x7080002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "M2P Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of M2P clock cycles while the event is enabled", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2P_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent0", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent1", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent2", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : All", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : All", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : All", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - DRS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCB", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PMM", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PMM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "M2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json index b77fd0f7ab50..225333561295 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-memory.json @@ -1,427 +1,3254 @@ [ + { + "BriefDescription": "Cycles - at UCLK", + "EventCode": "0x01", + "EventName": "UNC_M2HBM_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2HBM_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x17", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress", + "EventCode": "0x17", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Counts the number of time non cisgress D2C was not honoured by egress due to directory state constraints", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Counts the time when FM didn't do d2c for fill reads (cross tile case)", + "EventCode": "0x4a", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x18", + "EventName": "UNC_M2HBM_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : Cisgress", + "EventCode": "0x18", + "EventName": "UNC_M2HBM_DIRECT2CORE_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "EventCode": "0x1b", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "EventCode": "0x1a", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.CISGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts cisgress d2K that was not honored due to directory constraints", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.EGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of time D2K was not honoured by egress due to directory state constraints", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts non cisgress d2K that was not honored due to directory constraints", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "EventCode": "0x1c", + "EventName": "UNC_M2HBM_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1c", + "EventName": "UNC_M2HBM_DIRECT2UPI_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with any directory to non persistent memory", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory A to non persistent memory", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory I to non persistent memory", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory S to non persistent memory", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_I_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to I to non persistent memory", + "UMask": "0x120", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_I_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to I to non persistent memory", + "UMask": "0x220", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_S_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to S to non persistent memory", + "UMask": "0x140", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_S_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to S to non persistent memory", + "UMask": "0x240", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts any 1lm or 2lm hit data return that would result in directory update to non persistent memory", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_A_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to A to non persistent memory", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_A_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to A to non persistent memory", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_S_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to S to non persistent memory", + "UMask": "0x102", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_S_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to S to non persistent memory", + "UMask": "0x202", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts any 2lm miss data return that would result in directory update to non persistent memory", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_A_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to A to non persistent memory", + "UMask": "0x110", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_A_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to A to non persistent memory", + "UMask": "0x210", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_I_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to I to non persistent memory", + "UMask": "0x108", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_I_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to I to non persistent memory", + "UMask": "0x208", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on AkAd cmp message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.AD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on any packet type", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on Bl Cmp message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.BL_CMP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on NM fill write message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.CROSSTILE_NMWR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2Cha message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2CHA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2c message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2k message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2HBM_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000004", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2HBM_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count when Starve Glocab counter is at 7", + "EventCode": "0x44", + "EventName": "UNC_M2HBM_IGR_STARVE_WINNER.MASK7", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0.ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0.ALL", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0.NORMAL", + "PerPkg": "1", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - Ch0", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1.ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1.ALL", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1.NORMAL", + "PerPkg": "1", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - Ch1", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - All Channels", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.ALL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.ALL", + "PerPkg": "1", + "UMask": "0x810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.FULL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.FULL", + "PerPkg": "1", + "UMask": "0x801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.PARTIAL", + "PerPkg": "1", + "UMask": "0x802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_ALL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_FULL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.ALL", + "PerPkg": "1", + "UMask": "0x1010", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.FULL", + "PerPkg": "1", + "UMask": "0x1001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.PARTIAL", + "PerPkg": "1", + "UMask": "0x1002", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1010", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1004", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1002", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1008", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1804", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1808", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_CIS_DROPS", + "EventCode": "0x5c", + "EventName": "UNC_M2HBM_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": UPI - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_MERGE.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": XPT - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.RD_MERGED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.WR_MERGED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.WR_SQUASHED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "PublicDescription": "Prefetch CAM Inserts : XPT -All Channels", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Channels", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_OCCUPANCY", + "EventCode": "0x60", + "EventName": "UNC_M2HBM_PREFCAM_RxC_OCCUPANCY", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2HBM_RxC_AD.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2HBM_RxC_AD_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x03", + "EventName": "UNC_M2HBM_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) : BL Ingress (from CMS) Allocations", + "EventCode": "0x04", + "EventName": "UNC_M2HBM_RxC_BL.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts anytime a BL packet is added to Ingress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) : BL Ingress (from CMS) Allocations", + "EventCode": "0x04", + "EventName": "UNC_M2HBM_RxC_BL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts anytime a BL packet is added to Ingress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x05", + "EventName": "UNC_M2HBM_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x2e", + "EventName": "UNC_M2HBM_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x2f", + "EventName": "UNC_M2HBM_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x32", + "EventName": "UNC_M2HBM_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x32", + "EventName": "UNC_M2HBM_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x33", + "EventName": "UNC_M2HBM_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x33", + "EventName": "UNC_M2HBM_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) : AD Egress (to CMS) Allocations", + "EventCode": "0x06", + "EventName": "UNC_M2HBM_TxC_AD.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts anytime a AD packet is added to Egress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) : AD Egress (to CMS) Allocations", + "EventCode": "0x06", + "EventName": "UNC_M2HBM_TxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts anytime a AD packet is added to Egress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0x07", + "EventName": "UNC_M2HBM_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) : Inserts - CMS0 - Near Side", + "EventCode": "0x0E", + "EventName": "UNC_M2HBM_TxC_BL.INSERTS_CMS0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of BL transactions to CMS add port 0", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) : Inserts - CMS1 - Far Side", + "EventCode": "0x0E", + "EventName": "UNC_M2HBM_TxC_BL.INSERTS_CMS1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of BL transactions to CMS add port 1", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : All", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x42", + "EventName": "UNC_M2HBM_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x42", + "EventName": "UNC_M2HBM_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x37", + "EventName": "UNC_M2HBM_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x37", + "EventName": "UNC_M2HBM_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x38", + "EventName": "UNC_M2HBM_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x38", + "EventName": "UNC_M2HBM_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x40", + "EventName": "UNC_M2HBM_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x40", + "EventName": "UNC_M2HBM_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x4d", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x4d", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x4c", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x4c", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x48", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x48", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Activate due to read, write, underfill, or bypass", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Activate due to read", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x11", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Read in PCH0", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Read in PCH1", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x10", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Underfill Read transaction on Page Empty or Page Miss", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x44", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Activate due to write", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x22", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Write in PCH0", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Write in PCH1", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x20", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.ALL", + "PerPkg": "1", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.PCH0", + "PerPkg": "1", + "PublicDescription": "HBM RD_CAS and WR_CAS Commands", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.PCH1", + "PerPkg": "1", + "PublicDescription": "HBM RD_CAS and WR_CAS Commands", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS commands issued (regular and underfill)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0xcf", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Regular read CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill read CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Regular read CAS commands issued (does not include underfills)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_REG", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill read CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0xf0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM RD_CAS and WR_CAS Commands. : HBM WR_CAS commands w/o auto-pre", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR_NONPRE", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR_PRE", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.PCH0", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.PCH1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_32B", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_64B", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_UFILL_32B", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill Read CAS Command in Regular Mode (64B) in Pseudochannel 1", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_UFILL_64B", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.WR_32B", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.WR_64B", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "IMC Clockticks at DCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_MCHBM_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PREALL.PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the precharge all command was sent.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PREALL.PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the precharge all command was sent.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All Precharge Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PRE_ALL", + "PerPkg": "1", + "PublicDescription": "Precharge All Commands: Counts the number of times that the precharge all command was sent.", + "UMask": "0x3", + "Unit": "MCHBM" + }, + { + "BriefDescription": "IMC Clockticks at HCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_MCHBM_HCLOCKTICKS", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All precharge events", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge from MC page table", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x88", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharges from Page Table", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Equivalent to PAGE_EMPTY", + "UMask": "0x8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge due to read on page miss", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x11", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharge due to read", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Precharge from read bank scheduler", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x10", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x44", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge due to write on page miss", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x22", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharge due to write", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Precharge from write bank scheduler", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x20", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of cycles where the read buffer has greater than UMASK elements. NOTE: Umask must be set to the maximum number of elements in the queue (24 entries for SPR).", + "EventCode": "0x19", + "EventName": "UNC_MCHBM_RDB_FULL", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of inserts into the read buffer.", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of elements in the read buffer per cycle.", + "EventCode": "0x1a", + "EventName": "UNC_MCHBM_RDB_OCCUPANCY", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_MCHBM_RPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations: Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_MCHBM_RPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations: Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x80", + "EventName": "UNC_MCHBM_RPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy: Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x81", + "EventName": "UNC_MCHBM_RPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy: Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_MCHBM_WPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations: Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_MCHBM_WPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations: Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x82", + "EventName": "UNC_MCHBM_WPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy: Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to memory. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x83", + "EventName": "UNC_MCHBM_WPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy: Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to memory. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x2", + "Unit": "MCHBM" + }, { "BriefDescription": "Activate due to read, write, underfill, or bypass", "EventCode": "0x02", "EventName": "UNC_M_ACT_COUNT.ALL", "PerPkg": "1", - "PublicDescription": "DRAM Activate Count : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", - "UMask": "0xff", + "PublicDescription": "DRAM Activate Count : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : All DRAM Read and Write actions : DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM CAS commands issued on this channel.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0 : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1 : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (including underfills)", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Read CAS commands issued on this channel. This includes underfills.", + "UMask": "0xcf", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_REG", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc8", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (does not include underfills)", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS commands w/out auto-pre : DRAM RD_CAS and WR_CAS Commands : Counts the total number or DRAM Read CAS commands issued on this channel. This includes both regular RD CAS commands as well as those with implicit Precharge. We do not filter based on major mode, as RD_CAS is not issued during WMM (with the exception of underfills).", + "UMask": "0xc1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM underfill read CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Underfill Read Issued : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc4", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM write CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Write CAS commands issued on this channel.", + "UMask": "0xf0", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_NONPRE", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xd0", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_PRE", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xe0", + "Unit": "iMC" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.PCH0", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.PCH1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_32B", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_64B", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "iMC" + }, + { + "BriefDescription": "Underfill Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_UFILL_32B", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "iMC" + }, + { + "BriefDescription": "Underfill Read CAS Command in Regular Mode (64B) in Pseudochannel 1", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_UFILL_64B", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.WR_32B", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.WR_64B", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "iMC" + }, + { + "BriefDescription": "IMC Clockticks at DCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of DRAM DCLK clock cycles while the event is enabled", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_M_DRAM_PRE_ALL", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge All Commands : Counts the number of times that the precharge all command was sent.", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "IMC Clockticks at HCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_M_HCLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of DRAM HCLK clock cycles while the event is enabled", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.RD", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.RD", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.TOTAL", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.TOTAL", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.WR", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.WR", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue inserts", + "EventCode": "0xe3", + "EventName": "UNC_M_PMM_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts number of read requests allocated in the PMM Read Pending Queue.", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH0", + "PerPkg": "1", + "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH1", + "PerPkg": "1", + "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH0", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH1", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Queue Cycles Not Empty", + "EventCode": "0xe5", + "EventName": "UNC_M_PMM_WPQ_CYCLES_NE", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue inserts", + "EventCode": "0xe7", + "EventName": "UNC_M_PMM_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts number of write requests allocated in the PMM Write Pending Queue.", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the PMM DIMM.", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.CAS", + "PerPkg": "1", + "PublicDescription": "PMM (for IXP) Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the IXP DIMM.", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.PWR", + "PerPkg": "1", + "PublicDescription": "PMM (for IXP) Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the IXP DIMM.", + "UMask": "0x30", + "Unit": "iMC" + }, + { + "BriefDescription": "Channel PPD Cycles", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "PerPkg": "1", + "PublicDescription": "Channel PPD Cycles : Number of cycles when all the ranks in the channel are in PPD mode. If IBT=off is enabled, then this can be used to count those cycles. If it is not enabled, then this can count the number of cycles when that could have been taken advantage of.", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_0", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_1", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_2", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_3", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRIT_THROTTLE_CYCLES.SLOT0", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1. : Thermal throttling is performed per DIMM. We support 3 DIMMs per channel. This ID allows us to filter by ID.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRIT_THROTTLE_CYCLES.SLOT1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Clock-Enabled Self-Refresh", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "PerPkg": "1", + "PublicDescription": "Clock-Enabled Self-Refresh : Counts the number of cycles when the iMC is in self-refresh and the iMC still has a clock. This happens in some package C-states. For example, the PCU may ask the iMC to enter self-refresh even though some of the cores are still processing. One use of this is for Monroe technology. Self-refresh is required during package C3 and C6, but there is no clock in the iMC at this time, so it is not possible to count these cases.", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read, write, underfill, or PGT.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to (?)", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to (?) : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x88", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharges from Page Table", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharges from Page Table : Counts the number of DRAM Precharge commands sent on this channel. : Equivalent to PAGE_EMPTY", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read on page miss", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x11", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to read", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to read : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from read bank scheduler", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "All DRAM CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.ALL", + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH1", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : All DRAM Read and Write actions : DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM CAS commands issued on this channel.", - "UMask": "0xff", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x10", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.PCH0", + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0 : DRAM RD_CAS and WR_CAS Commands", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x44", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", "UMask": "0x40", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.PCH1", + "BriefDescription": "Precharge due to write on page miss", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x22", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to write", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to write : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from write bank scheduler", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where the read buffer has greater than UMASK elements. This includes reads to both DDR and PMEM. NOTE: Umask must be set to the maximum number of elements in the queue (24 entries for SPR).", + "EventCode": "0x19", + "EventName": "UNC_M_RDB_FULL", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of inserts into the read buffer destined for DDR. Does not count reads destined for PMEM.", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where there's at least one element in the read buffer. This includes reads to both DDR and PMEM.", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Not Empty", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Not Empty", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where there's at least one element in the read buffer. This includes reads to both DDR and PMEM.", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NOT_EMPTY", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of elements in the read buffer, including reads to both DDR and PMEM.", + "EventCode": "0x1a", + "EventName": "UNC_M_RDB_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x81", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.ACCEPTS", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Write Accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.FM_RD_CMPS", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Write Rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.FM_WR_CMPS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1 : DRAM RD_CAS and WR_CAS Commands", "UMask": "0x80", "Unit": "iMC" }, { - "BriefDescription": "All DRAM read CAS commands issued (including underfills)", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.RD", + "BriefDescription": "Scoreboard Accesses : FM read completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.NM_RD_CMPS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : FM write completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.NM_WR_CMPS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Read Accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.RD_ACCEPTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Read Rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.RD_REJECTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.REJECTS", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : NM read completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.WR_ACCEPTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : NM write completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.WR_REJECTS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Alloc", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.ALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": ": Dealloc", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.DEALLOC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Write Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_RD_STARVED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_TGR_WR_STARVED", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_WR_STARVED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": ": Valid", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.NM_RD_STARVED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.NM_WR_STARVED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Reject", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.VLD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Cycles Full", + "EventCode": "0xd1", + "EventName": "UNC_M_SB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Cycles Not-Empty", + "EventCode": "0xd0", + "EventName": "UNC_M_SB_CYCLES_NE", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Block region reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.BLOCK_RDS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Block region writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.BLOCK_WRS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Persistent Mem reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.PMM_RDS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Persistent Mem writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.PMM_WRS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Read CAS commands issued on this channel. This includes underfills.", - "UMask": "0xcf", + "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.RD_PRE_REG", + "BriefDescription": "Scoreboard Inserts : Reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.RDS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", - "UMask": "0xc2", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.RD_PRE_UNDERFILL", + "BriefDescription": "Scoreboard Inserts : Writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.WRS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", - "UMask": "0xc8", + "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "All DRAM read CAS commands issued (does not include underfills)", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.RD_REG", + "BriefDescription": "Scoreboard Occupancy : Block region reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.BLOCK_RDS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS commands w/out auto-pre : DRAM RD_CAS and WR_CAS Commands : Counts the total number or DRAM Read CAS commands issued on this channel. This includes both regular RD CAS commands as well as those with implicit Precharge. We do not filter based on major mode, as RD_CAS is not issued during WMM (with the exception of underfills).", - "UMask": "0xc1", + "UMask": "0x20", "Unit": "iMC" }, { - "BriefDescription": "DRAM underfill read CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "BriefDescription": "Scoreboard Occupancy : Block region writes", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.BLOCK_WRS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Underfill Read Issued : DRAM RD_CAS and WR_CAS Commands", - "UMask": "0xc4", + "UMask": "0x40", "Unit": "iMC" }, { - "BriefDescription": "All DRAM write CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.WR", + "BriefDescription": "Scoreboard Occupancy : Persistent Mem reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.PMM_RDS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Write CAS commands issued on this channel.", - "UMask": "0xf0", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.WR_NONPRE", + "BriefDescription": "Scoreboard Occupancy : Persistent Mem writes", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.PMM_WRS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre : DRAM RD_CAS and WR_CAS Commands", - "UMask": "0xd0", + "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", - "EventCode": "0x05", - "EventName": "UNC_M_CAS_COUNT.WR_PRE", + "BriefDescription": "Scoreboard Occupancy : Reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.RDS", "PerPkg": "1", - "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", - "UMask": "0xe0", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "IMC Clockticks at DCLK frequency", - "EventCode": "0x01", - "EventName": "UNC_M_CLOCKTICKS", + "BriefDescription": "Scoreboard Prefetch Inserts : All", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.ALL", "PerPkg": "1", - "PublicDescription": "Number of DRAM DCLK clock cycles while the event is enabled", "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "IMC Clockticks at HCLK frequency", - "EventCode": "0x01", - "EventName": "UNC_M_HCLOCKTICKS", + "BriefDescription": "Scoreboard Prefetch Inserts : DDR4", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.DDR", "PerPkg": "1", - "PublicDescription": "Number of DRAM HCLK clock cycles while the event is enabled", + "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue inserts", - "EventCode": "0xe3", - "EventName": "UNC_M_PMM_RPQ_INSERTS", + "BriefDescription": "Scoreboard Prefetch Inserts : PMM", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.PMM", "PerPkg": "1", - "PublicDescription": "Counts number of read requests allocated in the PMM Read Pending Queue.", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue occupancy", - "EventCode": "0xe0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH0", + "BriefDescription": "Scoreboard Prefetch Occupancy : All", + "EventCode": "0xdb", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.ALL", "PerPkg": "1", - "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue occupancy", - "EventCode": "0xe0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH1", + "BriefDescription": "Scoreboard Prefetch Occupancy : DDR4", + "EventCode": "0xdb", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.DDR", "PerPkg": "1", - "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue Occupancy", - "EventCode": "0xE0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH0", + "BriefDescription": "Scoreboard Prefetch Occupancy : Persistent Mem", + "EventCode": "0xDB", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.PMM", + "FCMask": "0x00000000", "PerPkg": "1", - "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", - "UMask": "0x10", + "PortMask": "0x00000000", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue Occupancy", - "EventCode": "0xE0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH1", + "BriefDescription": "Number of Scoreboard Requests Rejected", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.CANARY", "PerPkg": "1", - "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", - "UMask": "0x20", + "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue Occupancy", - "EventCode": "0xe0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH0", + "BriefDescription": "Number of Scoreboard Requests Rejected", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.DDR_EARLY_CMP", "PerPkg": "1", - "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", - "UMask": "0x4", + "UMask": "0x20", "Unit": "iMC" }, { - "BriefDescription": "PMM Read Pending Queue Occupancy", - "EventCode": "0xe0", - "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH1", + "BriefDescription": "Number of Scoreboard Requests Rejected : FM requests rejected due to full address conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.FM_ADDR_CNFLT", "PerPkg": "1", - "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", - "UMask": "0x8", + "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "PMM Write Pending Queue inserts", - "EventCode": "0xe7", - "EventName": "UNC_M_PMM_WPQ_INSERTS", + "BriefDescription": "Number of Scoreboard Requests Rejected : NM requests rejected due to set conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.NM_SET_CNFLT", "PerPkg": "1", - "PublicDescription": "Counts number of write requests allocated in the PMM Write Pending Queue.", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "PMM Write Pending Queue Occupancy", - "EventCode": "0xe4", - "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL", + "BriefDescription": "Number of Scoreboard Requests Rejected : Patrol requests rejected due to set conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.PATROL_SET_CNFLT", "PerPkg": "1", - "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the PMM DIMM.", - "UMask": "0x3", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "PMM Write Pending Queue Occupancy", - "EventCode": "0xE4", - "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH0", + "BriefDescription": ": Far Mem Read - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_RD", "PerPkg": "1", - "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", - "UMask": "0x1", + "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "PMM Write Pending Queue Occupancy", - "EventCode": "0xE4", - "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH1", + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_TGR", "PerPkg": "1", - "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", - "UMask": "0x2", + "UMask": "0x10", "Unit": "iMC" }, { - "BriefDescription": "Channel PPD Cycles", - "EventCode": "0x85", - "EventName": "UNC_M_POWER_CHANNEL_PPD", + "BriefDescription": ": Far Mem Write - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_WR", "PerPkg": "1", - "PublicDescription": "Channel PPD Cycles : Number of cycles when all the ranks in the channel are in PPD mode. If IBT=off is enabled, then this can be used to count those cycles. If it is not enabled, then this can count the number of cycles when that could have been taken advantage of.", + "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", - "EventCode": "0x47", - "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_0", + "BriefDescription": ": Near Mem Read - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.NM_RD", "PerPkg": "1", - "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", - "EventCode": "0x47", - "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_1", + "BriefDescription": ": Near Mem Write - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.NM_WR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_RD", "PerPkg": "1", - "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", - "EventCode": "0x47", - "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_2", + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_TGR", "PerPkg": "1", - "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", - "UMask": "0x4", + "UMask": "0x10", "Unit": "iMC" }, { - "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", - "EventCode": "0x47", - "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_3", + "BriefDescription": ": Far Mem Write - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_WR", "PerPkg": "1", - "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "Clock-Enabled Self-Refresh", - "EventCode": "0x43", - "EventName": "UNC_M_POWER_SELF_REFRESH", + "BriefDescription": ": Near Mem Read - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.NM_RD", "PerPkg": "1", - "PublicDescription": "Clock-Enabled Self-Refresh : Counts the number of cycles when the iMC is in self-refresh and the iMC still has a clock. This happens in some package C-states. For example, the PCU may ask the iMC to enter self-refresh even though some of the cores are still processing. One use of this is for Monroe technology. Self-refresh is required during package C3 and C6, but there is no clock in the iMC at this time, so it is not possible to count these cases.", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "Precharge due to read, write, underfill, or PGT.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.ALL", + "BriefDescription": ": Near Mem Write - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.NM_WR", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0xff", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands. : Precharge due to (?)", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.PGT", + "BriefDescription": ": Far Mem Read", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_RD", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to (?) : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x88", + "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands. : Prechages from Page Table", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.PGT_PCH0", + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_TGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_WR", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Prechages from Page Table : Counts the number of DRAM Precharge commands sent on this channel. : Equivalent to PAGE_EMPTY", "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.PGT_PCH1", + "BriefDescription": ": Near Mem Read", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.NM_RD", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x80", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "Precharge due to read on page miss", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.RD", + "BriefDescription": ": Near Mem Write", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.NM_WR", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x11", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands. : Precharge due to read", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.RD_PCH0", + "BriefDescription": "UNC_M_SB_TAGGED.DDR4_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.DDR4_CMP", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to read : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from read bank scheduler", - "UMask": "0x1", + "UMask": "0x8", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.RD_PCH1", + "BriefDescription": "UNC_M_SB_TAGGED.NEW", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.NEW", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x10", + "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.UFILL", + "BriefDescription": "UNC_M_SB_TAGGED.OCC", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.OCC", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x44", + "UMask": "0x80", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.UFILL_PCH0", + "BriefDescription": "UNC_M_SB_TAGGED.PMM0_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM0_CMP", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x4", + "UMask": "0x10", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.UFILL_PCH1", + "BriefDescription": "UNC_M_SB_TAGGED.PMM1_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM1_CMP", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x40", + "UMask": "0x20", "Unit": "iMC" }, { - "BriefDescription": "Precharge due to write on page miss", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.WR", + "BriefDescription": "UNC_M_SB_TAGGED.PMM2_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM2_CMP", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x22", + "UMask": "0x40", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands. : Precharge due to write", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.WR_PCH0", + "BriefDescription": "UNC_M_SB_TAGGED.RD_HIT", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.RD_HIT", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Precharge due to write : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from write bank scheduler", "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "DRAM Precharge commands.", - "EventCode": "0x03", - "EventName": "UNC_M_PRE_COUNT.WR_PCH1", + "BriefDescription": "UNC_M_SB_TAGGED.RD_MISS", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.RD_MISS", "PerPkg": "1", - "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", - "UMask": "0x20", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "Read Pending Queue Allocations", - "EventCode": "0x10", - "EventName": "UNC_M_RPQ_INSERTS.PCH0", + "BriefDescription": "2LM Tag check hit in near memory cache (DDR4)", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.HIT", "PerPkg": "1", - "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", "UMask": "0x1", "Unit": "iMC" }, { - "BriefDescription": "Read Pending Queue Allocations", - "EventCode": "0x10", - "EventName": "UNC_M_RPQ_INSERTS.PCH1", + "BriefDescription": "2LM Tag check miss, no data at this line", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.MISS_CLEAN", "PerPkg": "1", - "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", "UMask": "0x2", "Unit": "iMC" }, { - "BriefDescription": "Read Pending Queue Occupancy", - "EventCode": "0x80", - "EventName": "UNC_M_RPQ_OCCUPANCY_PCH0", + "BriefDescription": "2LM Tag check miss, existing data may be evicted to PMM", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.MISS_DIRTY", "PerPkg": "1", - "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "UMask": "0x4", "Unit": "iMC" }, { - "BriefDescription": "Read Pending Queue Occupancy", - "EventCode": "0x81", - "EventName": "UNC_M_RPQ_OCCUPANCY_PCH1", + "BriefDescription": "2LM Tag check hit due to memory read (bug?)", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.NM_RD_HIT", "PerPkg": "1", - "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check hit due to memory write (bug?)", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.NM_WR_HIT", + "PerPkg": "1", + "UMask": "0x10", "Unit": "iMC" }, { @@ -457,5 +3284,25 @@ "PerPkg": "1", "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_M_WPQ_READ_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_M_WPQ_WRITE_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" } ] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json deleted file mode 100644 index 11c037e8291d..000000000000 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-other.json +++ /dev/null @@ -1,4525 +0,0 @@ -[ - { - "BriefDescription": "CHA Clockticks", - "EventCode": "0x01", - "EventName": "UNC_CHA_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of CHA clock cycles while the event is enabled", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_CHA_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.HA", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.TOR", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x1bc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x1c19ff", - "Unit": "CHA" - }, - { - "BriefDescription": "All LLC lines in E state that are victimized on a fill", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "All LLC lines in M state that are victimized on a fill", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "All LLC lines in S state that are victimized on a fill", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Local InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Local Rd", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.LOCAL_READ", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Local Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests made into the CHA", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS", - "PerPkg": "1", - "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a remote socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Write requests made into the CHA", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "Write Requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Read and Write Requests; Writes Remote", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0xc001ffff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DDR Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DDR Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SF/LLC Evictions", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Hits", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from IA Cores", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts;CLFlush from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlush events that are initiated from the Core", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts;CLFlushOpt from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlushOpt events that are initiated from the Core", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read from local IA that misses in the snoop filter", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd Pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc817ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt Pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc897ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read from local IA that hits in the snoop filter", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd Pref hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read prefetch from local IA that hits in the snoop filter", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that hits in the snoop filter", - "UMask": "0xc817fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt from local IA that hits in the snoop filter", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt Pref hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that hits in the snoop filter", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Pref hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read prefetch from local IA that hits in the snoop filter", - "UMask": "0xc897fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefCode hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that hits in the snoop filter", - "UMask": "0xcccffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefData hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that hits in the snoop filter", - "UMask": "0xccd7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefRFO hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", - "UMask": "0xccc7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership from local IA that hits in the snoop filter", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO Pref hits from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that hits in the snoop filter", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts;ItoM from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; ItoM events that are initiated from the Core", - "UMask": "0xcc47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefCode from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA.", - "UMask": "0xcccfff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefData from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA.", - "UMask": "0xccd7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefRFO from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", - "UMask": "0xccc7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; misses from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for CRd misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode CRd", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd Pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", - "UMask": "0xc817fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRds issued by IA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", - "UMask": "0xc8178601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd misses from local IA targeting local memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", - "UMask": "0xc816fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", - "UMask": "0xc8178a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd Pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF", - "UMask": "0xc897fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting local memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target local memory", - "UMask": "0xc896fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting remote memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target remote memory", - "UMask": "0xc8977e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for DRd misses from local IA targeting remote memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and target remote memory", - "UMask": "0xc8177e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefCode misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that misses in the snoop filter", - "UMask": "0xcccffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefData misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that misses in the snoop filter", - "UMask": "0xccd7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; LLCPrefRFO misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", - "UMask": "0xccc7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts RFO misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc806fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc886fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8877e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc8077e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts;SpecItoM from Local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; SpecItoM events that are initiated from the Core", - "UMask": "0xcc57ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", - "PerPkg": "1", - "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc3fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; ItoM hits from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RdCur and FsRdCur hits from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO hits from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for ItoM from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IO with the opcode ItoM", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for ItoMCacheNears from IO devices.", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IO devices with the opcode ItoMCacheNears. This event indicates a partial write request.", - "UMask": "0xcd43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Misses from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; ItoM misses from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO misses from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts for RdCur from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Inserts into the TOR from local IO with the opcode RdCur", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO from local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IPQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IPQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - Non iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just ISOC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Local Targets", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA and IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Misses", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : MMCFG Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : MMIO Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MMIO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : MMIO Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NonCoherent", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PMM Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PM Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - Non IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Remote Targets", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Remote Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Remote", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All remote requests (e.g. snoops, writebacks) that came from remote sockets", - "UMask": "0xc001ffc8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All Snoops from Remote", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REM_SNPS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All Snoops from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All snoops to this LLC that came from remote sockets", - "UMask": "0xc001ff08", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RRQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All Snoops from Remote", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.SNPS_FROM_REM", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", - "UMask": "0xc001ff08", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WBQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0xc001ffff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DDR Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DDR Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SF/LLC Evictions", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Hits", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd Pref from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc817ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt Pref from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc897ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read from local IA that hits in the snoop filter", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd Pref hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that hits in the snoop filter", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that hits in the snoop filter", - "UMask": "0xc817fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt from local IA that hits in the snoop filter", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt Pref hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that hits in the snoop filter", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that hits in the snoop filter", - "UMask": "0xc897fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefCode hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that hits in the snoop filter", - "UMask": "0xcccffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefData hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that hits in the snoop filter", - "UMask": "0xccd7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefRFO hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", - "UMask": "0xccc7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership from local IA that hits in the snoop filter", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO Pref hits from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that hits in the snoop filter", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefCode from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA.", - "UMask": "0xcccfff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefData from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", - "UMask": "0xccd7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefRFO from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", - "UMask": "0xccc7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy for DRd misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "PerPkg": "1", - "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", - "UMask": "0xc817fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", - "PerPkg": "1", - "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", - "UMask": "0xc8178601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting local memory", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", - "UMask": "0xc816fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Opt Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", - "PerPkg": "1", - "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", - "UMask": "0xc8178a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc897fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc896fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8977e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting remote memory", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target remote memory", - "UMask": "0xc8177e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefCode misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that misses in the snoop filter", - "UMask": "0xcccffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefData misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", - "UMask": "0xccd7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; LLCPrefRFO misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", - "UMask": "0xccc7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc806fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc886fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8877e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc8077e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO prefetch from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ITOM hits from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RdCur and FsRdCur hits from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO hits from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ITOM from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ITOM misses from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RdCur and FsRdCur from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ItoM from local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IPQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IPQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - Non iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just ISOC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Local Targets", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA and IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Misses", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : MMCFG Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : MMIO Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MMIO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : MMIO Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NonCoherent", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PMM Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PMM Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Remote Targets", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Remote Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Remote", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All remote requests (e.g. snoops, writebacks) that came from remote sockets", - "UMask": "0xc001ffc8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All Snoops from Remote", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_SNPS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All Snoops from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All snoops to this LLC that came from remote sockets", - "UMask": "0xc001ff08", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RRQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.RRQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RRQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All Snoops from Remote", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.SNPS_FROM_REM", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", - "UMask": "0xc001ff08", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WBQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.WBQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WBQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IIO Clockticks", - "EventCode": "0x01", - "EventName": "UNC_IIO_CLOCKTICKS", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": "Number of IIO clock cycles while the event is enabled", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0100", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0200", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by IIO Part0-7 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x00ff", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by IIO Part0 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by IIO Part1 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by IIO Part2 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by IIO Part3 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made by IIO Part0-7 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x00ff", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made by IIO Part0 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made by IIO Part1 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made by IIO Part2 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made by IIO Part3 to Memory", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache hits", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache lookups", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB lookups first", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "IOTLB Fills (same as IOTLB miss)", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.MISSES", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": "IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOMMU memory access", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", - "PerPkg": "1", - "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", - "UMask": "0xc0", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 2M page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWT Hit to a 256T page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_256T_HITS", - "PerPkg": "1", - "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 4K page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 1G page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Global IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.PWT_OCCUPANCY_MSB", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PWT occupancy. Does not include 9th bit of occupancy (will undercount if PWT is greater than 255 per cycle).", - "EventCode": "0x42", - "EventName": "UNC_IIO_PWT_OCCUPANCY", - "PerPkg": "1", - "PortMask": "0x0000", - "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0001", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0002", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0004", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0008", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0010", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0020", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0040", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x0080", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "IRP Clockticks", - "EventCode": "0x01", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of IRP clock cycles while the event is enabled", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF - request insert from TC.", - "EventCode": "0x18", - "EventName": "UNC_I_FAF_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF occupancy", - "EventCode": "0x19", - "EventName": "UNC_I_FAF_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF allocation -- sent to ADQ", - "EventCode": "0x16", - "EventName": "UNC_I_FAF_TRANSACTIONS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Lost Forward", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound write (fast path) requests received by the IRP.", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "M2M Clockticks", - "EventCode": "0x01", - "EventName": "UNC_M2M_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Clockticks of the mesh to memory (M2M)", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", - "EventCode": "0x17", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to core (bypassing the CHA)", - "EventCode": "0x16", - "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to core transaction were overridden", - "EventCode": "0x18", - "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", - "EventCode": "0x1b", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to Intel UPI was disabled", - "EventCode": "0x1a", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to the Intel UPI", - "EventCode": "0x19", - "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", - "EventCode": "0x1c", - "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", - "EventCode": "0x20", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", - "EventCode": "0x20", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", - "EventCode": "0x20", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", - "EventCode": "0x20", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to I", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", - "PerPkg": "1", - "UMask": "0x320", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to S", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", - "PerPkg": "1", - "UMask": "0x340", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", - "PerPkg": "1", - "UMask": "0x301", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to A", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", - "PerPkg": "1", - "UMask": "0x304", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to S", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", - "PerPkg": "1", - "UMask": "0x302", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to A", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", - "PerPkg": "1", - "UMask": "0x310", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to I", - "EventCode": "0x21", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", - "PerPkg": "1", - "UMask": "0x308", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_IMC_READS.TO_PMM", - "EventCode": "0x24", - "EventName": "UNC_M2M_IMC_READS.TO_PMM", - "PerPkg": "1", - "UMask": "0x320", - "Unit": "M2M" - }, - { - "BriefDescription": "PMM - All Channels", - "EventCode": "0x25", - "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", - "PerPkg": "1", - "UMask": "0x1880", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped", - "EventCode": "0x58", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped", - "EventCode": "0x58", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped", - "EventCode": "0x58", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped", - "EventCode": "0x58", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped", - "EventCode": "0x58", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x5", - "Unit": "M2M" - }, - { - "BriefDescription": ": UPI - All Channels", - "EventCode": "0x5d", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.UPI_ALLCH", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "M2M" - }, - { - "BriefDescription": ": XPT - All Channels", - "EventCode": "0x5d", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x5", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", - "EventCode": "0x56", - "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", - "EventCode": "0x56", - "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", - "PerPkg": "1", - "PublicDescription": "Prefetch CAM Inserts : XPT -All Channels", - "UMask": "0x5", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", - "EventCode": "0x02", - "EventName": "UNC_M2M_RxC_AD_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy", - "EventCode": "0x03", - "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 0", - "EventCode": "0x32", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x104", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 1", - "EventCode": "0x32", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x204", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 0", - "EventCode": "0x33", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 1", - "EventCode": "0x33", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2P Clockticks", - "EventCode": "0x01", - "EventName": "UNC_M2P_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of M2P clock cycles while the event is enabled", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M2P_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M3UPI Clockticks", - "EventCode": "0x01", - "EventName": "UNC_M3UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of M2UPI clock cycles while the event is enabled", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M3UPI CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2C Sent", - "EventCode": "0x2b", - "EventName": "UNC_M3UPI_D2C_SENT", - "PerPkg": "1", - "PublicDescription": "D2C Sent : Count cases BL sends direct to core", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2U Sent", - "EventCode": "0x2a", - "EventName": "UNC_M3UPI_D2U_SENT", - "PerPkg": "1", - "PublicDescription": "D2U Sent : Cases where SMI3 sends D2U command", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FlowQ Generated Prefetch", - "EventCode": "0x29", - "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", - "PerPkg": "1", - "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", - "Unit": "M3UPI" - }, - { - "BriefDescription": "All CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_MCHBM_CAS_COUNT.ALL", - "PerPkg": "1", - "UMask": "0xff", - "Unit": "MCHBM" - }, - { - "BriefDescription": "Read CAS commands issued (regular and underfill)", - "EventCode": "0x05", - "EventName": "UNC_MCHBM_CAS_COUNT.RD", - "PerPkg": "1", - "UMask": "0xcf", - "Unit": "MCHBM" - }, - { - "BriefDescription": "Regular read CAS commands issued (does not include underfills)", - "EventCode": "0x05", - "EventName": "UNC_MCHBM_CAS_COUNT.RD_REG", - "PerPkg": "1", - "UMask": "0xc1", - "Unit": "MCHBM" - }, - { - "BriefDescription": "Underfill read CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_MCHBM_CAS_COUNT.RD_UNDERFILL", - "PerPkg": "1", - "UMask": "0xc4", - "Unit": "MCHBM" - }, - { - "BriefDescription": "Write CAS commands issued", - "EventCode": "0x05", - "EventName": "UNC_MCHBM_CAS_COUNT.WR", - "PerPkg": "1", - "UMask": "0xf0", - "Unit": "MCHBM" - }, - { - "BriefDescription": "UPI Clockticks", - "EventCode": "0x01", - "EventName": "UNC_UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of UPI LL clock cycles while the event is enabled", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Direct packet attempts : D2C", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", - "PerPkg": "1", - "PublicDescription": "Direct packet attempts : D2C : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L1", - "EventCode": "0x21", - "EventName": "UNC_UPI_L1_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L1 : Number of UPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a UPI link. Use edge detect to count the number of instances when the UPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 0 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 1 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 2 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : All Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : All Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Null FLITs received from any slot", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", - "PerPkg": "1", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Idle", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Idle : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : LLCRD Not Empty", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : LLCTRL", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : All Non Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Protocol Header", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 0", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 1", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 2", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 0 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 1 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 2 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 0 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 1 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 2 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0p", - "EventCode": "0x27", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Bypassed", - "EventCode": "0x41", - "EventName": "UNC_UPI_TxL_BYPASSED", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Bypassed : Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the UPI Link. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : All Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : All Data : Counts number of data flits across this UPI link.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "All Null Flits", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", - "PerPkg": "1", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Idle", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Idle : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : LLCTRL", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : All Non Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Protocol Header", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 0", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 1", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 2", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Allocations", - "EventCode": "0x40", - "EventName": "UNC_UPI_TxL_INSERTS", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x42", - "EventName": "UNC_UPI_TxL_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "UPI LL" - } -] diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json index b1d5a605e0a7..8948e85074f0 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-power.json @@ -7,6 +7,66 @@ "PublicDescription": "Number of PCU PCLK Clock cycles while the event is enabled", "Unit": "PCU" }, + { + "BriefDescription": "UNC_P_CORE_TRANSITION_CYCLES", + "EventCode": "0x60", + "EventName": "UNC_P_CORE_TRANSITION_CYCLES", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "UNC_P_DEMOTIONS", + "EventCode": "0x30", + "EventName": "UNC_P_DEMOTIONS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 0 Cycles", + "EventCode": "0x75", + "EventName": "UNC_P_FIVR_PS_PS0_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 0 Cycles : Cycles spent in phase-shedding power state 0", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 1 Cycles", + "EventCode": "0x76", + "EventName": "UNC_P_FIVR_PS_PS1_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 1 Cycles : Cycles spent in phase-shedding power state 1", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 2 Cycles", + "EventCode": "0x77", + "EventName": "UNC_P_FIVR_PS_PS2_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 2 Cycles : Cycles spent in phase-shedding power state 2", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 3 Cycles", + "EventCode": "0x78", + "EventName": "UNC_P_FIVR_PS_PS3_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 3 Cycles : Cycles spent in phase-shedding power state 3", + "Unit": "PCU" + }, + { + "BriefDescription": "AVX256 Frequency Clipping", + "EventCode": "0x49", + "EventName": "UNC_P_FREQ_CLIP_AVX256", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "AVX512 Frequency Clipping", + "EventCode": "0x4a", + "EventName": "UNC_P_FREQ_CLIP_AVX512", + "PerPkg": "1", + "Unit": "PCU" + }, { "BriefDescription": "Thermal Strongest Upper Limit Cycles", "EventCode": "0x04", @@ -23,6 +83,14 @@ "PublicDescription": "Power Strongest Upper Limit Cycles : Counts the number of cycles when power is the upper limit on frequency.", "Unit": "PCU" }, + { + "BriefDescription": "IO P Limit Strongest Lower Limit Cycles", + "EventCode": "0x73", + "EventName": "UNC_P_FREQ_MIN_IO_P_CYCLES", + "PerPkg": "1", + "PublicDescription": "IO P Limit Strongest Lower Limit Cycles : Counts the number of cycles when IO P Limit is preventing us from dropping the frequency lower. This algorithm monitors the needs to the IO subsystem on both local and remote sockets and will maintain a frequency high enough to maintain good IO BW. This is necessary for when all the IA cores on a socket are idle but a user still would like to maintain high IO Bandwidth.", + "Unit": "PCU" + }, { "BriefDescription": "Cycles spent changing Frequency", "EventCode": "0x74", @@ -31,6 +99,22 @@ "PublicDescription": "Cycles spent changing Frequency : Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.", "Unit": "PCU" }, + { + "BriefDescription": "Memory Phase Shedding Cycles", + "EventCode": "0x2f", + "EventName": "UNC_P_MEMORY_PHASE_SHEDDING_CYCLES", + "PerPkg": "1", + "PublicDescription": "Memory Phase Shedding Cycles : Counts the number of cycles that the PCU has triggered memory phase shedding. This is a mode that can be run in the iMC physicals that saves power at the expense of additional latency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C0", + "EventCode": "0x2a", + "EventName": "UNC_P_PKG_RESIDENCY_C0_CYCLES", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C0 : Counts the number of cycles when the package was in C0. This event can be used in conjunction with edge detect to count C0 entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, { "BriefDescription": "Package C State Residency - C2E", "EventCode": "0x2b", @@ -47,6 +131,13 @@ "PublicDescription": "Package C State Residency - C6 : Counts the number of cycles when the package was in C6. This event can be used in conjunction with edge detect to count C6 entrances (or exits using invert). Residency events do not include transition times.", "Unit": "PCU" }, + { + "BriefDescription": "UNC_P_PMAX_THROTTLED_CYCLES", + "EventCode": "0x06", + "EventName": "UNC_P_PMAX_THROTTLED_CYCLES", + "PerPkg": "1", + "Unit": "PCU" + }, { "BriefDescription": "Number of cores in C0", "EventCode": "0x35", @@ -86,5 +177,21 @@ "PerPkg": "1", "PublicDescription": "Internal Prochot : Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", "Unit": "PCU" + }, + { + "BriefDescription": "Total Core C State Transition Cycles", + "EventCode": "0x72", + "EventName": "UNC_P_TOTAL_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Total Core C State Transition Cycles : Number of cycles spent performing core C state transitions across all cores.", + "Unit": "PCU" + }, + { + "BriefDescription": "VR Hot", + "EventCode": "0x42", + "EventName": "UNC_P_VR_HOT_CYCLES", + "PerPkg": "1", + "PublicDescription": "VR Hot : Number of cycles that a CPU SVID VR is hot. Does not cover DRAM VRs", + "Unit": "PCU" } ] -- GitLab From dbe9d887d3015a95c8d10dd47ce3e241a5167772 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:30 -0700 Subject: [PATCH 2990/5631] perf vendor events intel: Add grandridge Add v1.00 from: https://github.com/intel/perfmon/pull/69 Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../pmu-events/arch/x86/grandridge/cache.json | 155 ++++++++++++++++++ .../arch/x86/grandridge/frontend.json | 16 ++ .../arch/x86/grandridge/memory.json | 20 +++ .../pmu-events/arch/x86/grandridge/other.json | 20 +++ .../arch/x86/grandridge/pipeline.json | 96 +++++++++++ .../arch/x86/grandridge/virtual-memory.json | 24 +++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + 7 files changed, 332 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/frontend.json create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/other.json create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/pipeline.json create mode 100644 tools/perf/pmu-events/arch/x86/grandridge/virtual-memory.json diff --git a/tools/perf/pmu-events/arch/x86/grandridge/cache.json b/tools/perf/pmu-events/arch/x86/grandridge/cache.json new file mode 100644 index 000000000000..7f0dc65a55d2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/cache.json @@ -0,0 +1,155 @@ +[ + { + "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Counts the number of load ops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Counts the number of store ops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x6" + } +] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/frontend.json b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json new file mode 100644 index 000000000000..be8f1c7e195c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/frontend.json @@ -0,0 +1,16 @@ +[ + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "200003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/memory.json b/tools/perf/pmu-events/arch/x86/grandridge/memory.json new file mode 100644 index 000000000000..79d8af45100c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/memory.json @@ -0,0 +1,20 @@ +[ + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/other.json b/tools/perf/pmu-events/arch/x86/grandridge/other.json new file mode 100644 index 000000000000..2414f6ff53b0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/other.json @@ -0,0 +1,20 @@ +[ + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json new file mode 100644 index 000000000000..41212957ef21 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json @@ -0,0 +1,96 @@ +[ + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "200003" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "200003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of instructions retired", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL", + "PEBS": "1", + "SampleAfterValue": "1000003" + } +] diff --git a/tools/perf/pmu-events/arch/x86/grandridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/grandridge/virtual-memory.json new file mode 100644 index 000000000000..bd5f2b634c98 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/grandridge/virtual-memory.json @@ -0,0 +1,24 @@ +[ + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 1G page.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 1G page.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0xe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 437eeecfaf64..c2b83cbae225 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -9,6 +9,7 @@ GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core GenuineIntel-6-9[6C],v1.03,elkhartlake,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core +GenuineIntel-6-B6,v1.00,grandridge,core GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v27,haswellx,core -- GitLab From 98806c08f995e850f4427e30852a7012f4f1c869 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:31 -0700 Subject: [PATCH 2991/5631] perf vendor events intel: Add sierraforest Add v1.00 from: https://github.com/intel/perfmon/pull/69 Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + .../arch/x86/sierraforest/cache.json | 155 ++++++++++++++++++ .../arch/x86/sierraforest/frontend.json | 16 ++ .../arch/x86/sierraforest/memory.json | 20 +++ .../arch/x86/sierraforest/other.json | 20 +++ .../arch/x86/sierraforest/pipeline.json | 96 +++++++++++ .../arch/x86/sierraforest/virtual-memory.json | 24 +++ 7 files changed, 332 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/frontend.json create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/other.json create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json create mode 100644 tools/perf/pmu-events/arch/x86/sierraforest/virtual-memory.json diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index c2b83cbae225..66c37a3cbf43 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -24,6 +24,7 @@ GenuineIntel-6-1[AEF],v3,nehalemep,core GenuineIntel-6-2E,v3,nehalemex,core GenuineIntel-6-2A,v19,sandybridge,core GenuineIntel-6-(8F|CF),v1.12,sapphirerapids,core +GenuineIntel-6-AF,v1.00,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v55,skylake,core GenuineIntel-6-55-[01234],v1.29,skylakex,core diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/cache.json b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json new file mode 100644 index 000000000000..7f0dc65a55d2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/cache.json @@ -0,0 +1,155 @@ +[ + { + "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x41" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Counts the number of load ops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x81" + }, + { + "BriefDescription": "Counts the number of store ops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x6" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json b/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json new file mode 100644 index 000000000000..be8f1c7e195c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/frontend.json @@ -0,0 +1,16 @@ +[ + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "200003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json new file mode 100644 index 000000000000..79d8af45100c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/memory.json @@ -0,0 +1,20 @@ +[ + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/other.json b/tools/perf/pmu-events/arch/x86/sierraforest/other.json new file mode 100644 index 000000000000..2414f6ff53b0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/other.json @@ -0,0 +1,20 @@ +[ + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json new file mode 100644 index 000000000000..41212957ef21 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json @@ -0,0 +1,96 @@ +[ + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "200003" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "200003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of instructions retired", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.ALL", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.ALL", + "SampleAfterValue": "1000003" + }, + { + "BriefDescription": "Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL", + "EventCode": "0x72", + "EventName": "TOPDOWN_RETIRING.ALL", + "PEBS": "1", + "SampleAfterValue": "1000003" + } +] diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sierraforest/virtual-memory.json new file mode 100644 index 000000000000..bd5f2b634c98 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/sierraforest/virtual-memory.json @@ -0,0 +1,24 @@ +[ + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to a 1G page.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to a 1G page.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "SampleAfterValue": "1000003", + "UMask": "0xe" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0xe" + } +] -- GitLab From 759e81507e82375475c6ff1cd328b2e4bb10aee6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:32 -0700 Subject: [PATCH 2992/5631] perf vendor events intel: Fix uncore topics for alderlake Move events from 'uncore-other' topic classification to interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../x86/alderlake/uncore-interconnect.json | 90 +++++++++++++++++++ .../arch/x86/alderlake/uncore-other.json | 88 ------------------ .../x86/alderlaken/uncore-interconnect.json | 26 ++++++ .../arch/x86/alderlaken/uncore-other.json | 24 ----- 4 files changed, 116 insertions(+), 112 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json new file mode 100644 index 000000000000..34fc052d00e4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json @@ -0,0 +1,90 @@ +[ + { + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", + "EventCode": "0x81", + "EventName": "UNC_ARB_DAT_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", + "EventCode": "0x85", + "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json index 5f3b4c6e2e39..2af92e43b28a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-other.json @@ -1,92 +1,4 @@ [ - { - "BriefDescription": "Number of requests allocated in Coherency Tracker.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", - "EventCode": "0x81", - "EventName": "UNC_ARB_DAT_REQUESTS.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", - "EventCode": "0x85", - "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", - "EventCode": "0x80", - "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", - "EventCode": "0x81", - "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "EventCode": "0xff", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json new file mode 100644 index 000000000000..4af695a5e755 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json @@ -0,0 +1,26 @@ +[ + { + "BriefDescription": "Number of requests allocated in Coherency Tracker.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-other.json b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-other.json index f9e7777cd2be..2af92e43b28a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-other.json @@ -1,28 +1,4 @@ [ - { - "BriefDescription": "Number of requests allocated in Coherency Tracker.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "EventCode": "0xff", -- GitLab From 141825578a2467294752d2952c166116e32af2ca Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:33 -0700 Subject: [PATCH 2993/5631] perf vendor events intel: Fix uncore topics for broadwell Reduce the number of 'uncore-other' topic classifications, move to cache and interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwell/uncore-cache.json | 30 ++++----- .../x86/broadwell/uncore-interconnect.json | 61 +++++++++++++++++++ .../arch/x86/broadwell/uncore-other.json | 59 ------------------ 3 files changed, 76 insertions(+), 74 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/broadwell/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore-cache.json index fcb15b880bad..c5cc43825cb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore-cache.json @@ -6,7 +6,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", "UMask": "0x86", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", @@ -15,7 +15,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", @@ -24,7 +24,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", @@ -33,7 +33,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", "UMask": "0x8f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", @@ -42,7 +42,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", "UMask": "0x16", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", @@ -51,7 +51,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", "UMask": "0x18", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in M-state", @@ -60,7 +60,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", @@ -69,7 +69,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", "UMask": "0x1f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", @@ -78,7 +78,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", "UMask": "0x26", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", @@ -87,7 +87,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", @@ -96,7 +96,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", "UMask": "0x2f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", @@ -104,7 +104,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", @@ -112,7 +112,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", @@ -120,7 +120,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", @@ -128,6 +128,6 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore-interconnect.json new file mode 100644 index 000000000000..64af685274a2 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore-interconnect.json @@ -0,0 +1,61 @@ +[ + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", + "CounterMask": "1", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT", + "PerPkg": "1", + "PublicDescription": "Each cycle count number of valid coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "PerPkg": "1", + "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json index 368a958a18a0..58be90d7cc93 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/uncore-other.json @@ -1,63 +1,4 @@ [ - { - "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;", - "CounterMask": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT", - "PerPkg": "1", - "PublicDescription": "Each cycle count number of valid coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", - "PerPkg": "1", - "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "ARB" - }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", "EventCode": "0xff", -- GitLab From 55b7bcef861c1345deb09c71d626e88174a20703 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:34 -0700 Subject: [PATCH 2994/5631] perf vendor events intel: Fix uncore topics for broadwellde Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-7-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwellde/uncore-cache.json | 324 ++++----- .../x86/broadwellde/uncore-interconnect.json | 614 ++++++++++++++++++ .../{uncore-other.json => uncore-io.json} | 612 ----------------- 3 files changed, 776 insertions(+), 774 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json rename tools/perf/pmu-events/arch/x86/broadwellde/{uncore-other.json => uncore-io.json} (53%) diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json index 2bf23ef7bfac..56bba6d4e0f6 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json @@ -4,13 +4,13 @@ "EventCode": "0xA", "EventName": "UNC_C_BOUNCE_CONTROL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Counter 0 Occupancy", @@ -18,7 +18,7 @@ "EventName": "UNC_C_COUNTER0_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "FaST wire asserted", @@ -26,7 +26,7 @@ "EventName": "UNC_C_FAST_ASSERTED", "PerPkg": "1", "PublicDescription": "Counts the number of cycles either the local distress or incoming distress signals are asserted. Incoming distress includes both up and dn.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Any Request", @@ -35,7 +35,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Data Read Request", @@ -44,7 +44,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Lookups that Match NID", @@ -53,7 +53,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Any Read Request", @@ -62,7 +62,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; External Snoop Request", @@ -71,7 +71,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", "UMask": "0x9", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Write Requests", @@ -80,7 +80,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in E state", @@ -89,7 +89,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -98,7 +98,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in S State", @@ -107,7 +107,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -116,7 +116,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in M state", @@ -125,7 +125,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", @@ -134,7 +134,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; DRd hitting non-M with raw CV=0", @@ -143,7 +143,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Clean Victim with raw CV=0", @@ -152,7 +152,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; RFO HitS", @@ -161,7 +161,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Number of times that an RFO hit in S state. This is useful for determining if it might be good for a workload to use RspIWB instead of RspSWB.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Silent Snoop Eviction", @@ -170,7 +170,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc", @@ -179,7 +179,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Write Combining Aliasing", @@ -188,7 +188,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 0", @@ -197,7 +197,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 0", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 1", @@ -206,7 +206,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 2", @@ -215,7 +215,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 2", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 3", @@ -224,7 +224,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 3", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Bits Decremented", @@ -233,7 +233,7 @@ "PerPkg": "1", "PublicDescription": "How often all LRU bits were decremented by 1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; Non-0 Aged Victim", @@ -242,7 +242,7 @@ "PerPkg": "1", "PublicDescription": "How often we picked a victim that had a non-zero age", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; All", @@ -251,7 +251,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down", @@ -260,7 +260,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up", @@ -269,7 +269,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even", @@ -278,7 +278,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd", @@ -287,7 +287,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even", @@ -296,7 +296,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd", @@ -305,7 +305,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; All", @@ -314,7 +314,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down", @@ -323,7 +323,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up", @@ -332,7 +332,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even", @@ -341,7 +341,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd", @@ -350,7 +350,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even", @@ -359,7 +359,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd", @@ -368,7 +368,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -377,7 +377,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -386,7 +386,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up", @@ -395,7 +395,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even", @@ -404,7 +404,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd", @@ -413,7 +413,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even", @@ -422,7 +422,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd", @@ -431,7 +431,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AD", @@ -439,7 +439,7 @@ "EventName": "UNC_C_RING_BOUNCES.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AK", @@ -447,7 +447,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; BL", @@ -455,7 +455,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", @@ -463,7 +463,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -472,7 +472,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -481,7 +481,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -490,7 +490,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters for Down polarity", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -499,7 +499,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD", @@ -507,7 +507,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK", @@ -515,7 +515,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL", @@ -523,7 +523,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IV", @@ -531,14 +531,14 @@ "EventName": "UNC_C_RING_SINK_STARVED.IV", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of cycles the Cbo is actively throttling traffic onto the Ring in order to limit bounce traffic.", "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", @@ -547,7 +547,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", @@ -556,7 +556,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IRQ is externally starved and therefore we are blocking the IPQ.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", @@ -565,7 +565,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; Number of times that the ISMQ Bid.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; PRQ", @@ -574,7 +574,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IPQ", @@ -583,7 +583,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ", @@ -592,7 +592,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ Rejected", @@ -601,7 +601,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -610,7 +610,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -619,7 +619,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", @@ -628,7 +628,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IPQ in Internal Starvation.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", @@ -637,7 +637,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IRQ in Internal Starvation.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", @@ -646,7 +646,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the ISMQ in Internal Starvation.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; PRQ", @@ -655,7 +655,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Address Conflict", @@ -664,7 +664,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from an address conflicts. Address conflicts out of the IPQ should be rare. They will generally only occur if two different sockets are sending requests to the same address at the same time. This is a true conflict case, unlike the IPQ Address Conflict which is commonly caused by prefetching characteristics.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Any Reject", @@ -673,7 +673,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject. TOR rejects from the IPQ can be caused by the Egress being full or Address Conflicts.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No Egress Credits", @@ -682,7 +682,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from the Egress being full. IPQ requests make use of the AD Egress for regular responses, the BL egress to forward data, and the AK egress to return credits.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No QPI Credits", @@ -691,7 +691,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No AD Sbo Credits", @@ -700,7 +700,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Target Node Filter", @@ -709,7 +709,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", @@ -718,7 +718,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because of an address match in the TOR. In order to maintain coherency, requests to the same address are not allowed to pass each other up in the Cbo. Therefore, if there is an outstanding request to a given address, one cannot issue another request to that address until it is complete. This comes up most commonly with prefetches. Outstanding prefetches occasionally will not complete their memory fetch and a demand request to the same address will then sit in the IRQ and get retried until the prefetch fills the data into the LLC. Therefore, it will not be uncommon to see this case in high bandwidth streaming workloads when the LLC Prefetcher in the core is enabled.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Any Reject", @@ -727,7 +727,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of IRQ retries that occur. Requests from the IRQ are retried if they are rejected from the TOR pipeline for a variety of reasons. Some of the most common reasons include if the Egress is full, there are no RTIDs, or there is a Physical Address match to another outstanding request.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", @@ -736,7 +736,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because it failed to acquire an entry in the Egress. The egress is the buffer that queues up for allocating onto the ring. IRQ requests can make use of all four rings and all four Egresses. If any of the queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No IIO Credits", @@ -745,7 +745,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects", @@ -754,7 +754,7 @@ "PerPkg": "1", "PublicDescription": "Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", @@ -763,7 +763,7 @@ "PerPkg": "1", "PublicDescription": "Number of requests rejects because of lack of QPI Ingress credits. These credits are required in order to send transactions to the QPI agent. Please see the QPI_IGR_CREDITS events for more information.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", @@ -772,7 +772,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that requests from the IRQ were retried because there were no RTIDs available. RTIDs are required after a request misses the LLC and needs to send snoops and/or requests to memory. If there are no RTIDs available, requests will queue up in the IRQ and retry until one becomes available. Note that there are multiple RTID pools for the different sockets. There may be cases where the local RTIDs are all used, but requests destined for remote memory can still acquire an RTID because there are remote RTIDs available. This event does not provide any filtering for this case.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No AD Sbo Credits", @@ -781,7 +781,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No BL Sbo Credits", @@ -790,7 +790,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Target Node Filter", @@ -799,7 +799,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; Any Reject", @@ -808,7 +808,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the total number of times that a request from the ISMQ retried because of a TOR reject. ISMQ requests generally will not need to retry (or at least ISMQ retries are less common than IRQ retries). ISMQ requests will retry if they are not able to acquire a needed Egress credit to get onto the ring, or for cache evictions that need to acquire an RTID. Most ISMQ requests already have an RTID, so eviction retries will be less common here.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No Egress Credits", @@ -817,7 +817,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by a lack of Egress credits. The egress is the buffer that queues up for allocating onto the ring. If any of the Egress queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No IIO Credits", @@ -826,7 +826,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -835,7 +835,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No QPI Credits", @@ -844,7 +844,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No RTIDs", @@ -853,7 +853,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by no RTIDs. M-state cache evictions are serviced through the ISMQ, and must acquire an RTID in order to write back to memory. If no RTIDs are available, they will be retried.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -862,7 +862,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No AD Sbo Credits", @@ -871,7 +871,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No BL Sbo Credits", @@ -880,7 +880,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; Target Node Filter", @@ -889,7 +889,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IPQ", @@ -898,7 +898,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ", @@ -907,7 +907,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ Rejected", @@ -916,7 +916,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; PRQ Rejects", @@ -925,7 +925,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For AD Ring", @@ -934,7 +934,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For BL Ring", @@ -943,7 +943,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For AD Ring", @@ -952,7 +952,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For BL Ring", @@ -961,7 +961,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; All", @@ -970,7 +970,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Evictions", @@ -979,7 +979,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory", @@ -988,7 +988,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory - Opcode Matched", @@ -997,7 +997,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory", @@ -1006,7 +1006,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory - Opcode Matched", @@ -1015,7 +1015,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss Opcode Match", @@ -1024,7 +1024,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory", @@ -1033,7 +1033,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory - Opcode Matched", @@ -1042,7 +1042,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched", @@ -1051,7 +1051,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Evictions", @@ -1060,7 +1060,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Miss All", @@ -1069,7 +1069,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", @@ -1078,7 +1078,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched", @@ -1087,7 +1087,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Writebacks", @@ -1096,7 +1096,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Opcode Match", @@ -1105,7 +1105,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory", @@ -1114,7 +1114,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory - Opcode Matched", @@ -1123,7 +1123,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Writebacks", @@ -1132,7 +1132,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Any", @@ -1141,7 +1141,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All valid TOR entries. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Evictions", @@ -1150,7 +1150,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding eviction transactions in the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1159,7 +1159,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Local Memory - Opcode Matched", @@ -1168,7 +1168,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss All", @@ -1177,7 +1177,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding miss requests in the TOR. 'Miss' means the allocation requires an RTID. This generally means that the request was sent to memory or MMIO.", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1186,7 +1186,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Local Memory - Opcode Matched", @@ -1195,7 +1195,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss Opcode Match", @@ -1204,7 +1204,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1213,7 +1213,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Remote Memory - Opcode Matched", @@ -1222,7 +1222,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1231,7 +1231,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of NID matched outstanding requests in the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid.In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Evictions", @@ -1240,7 +1240,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding NID matched eviction transactions in the TOR .", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1249,7 +1249,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", @@ -1258,7 +1258,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched", @@ -1267,7 +1267,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Writebacks", @@ -1276,7 +1276,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); NID matched write transactions int the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Opcode Match", @@ -1285,7 +1285,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc).", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1294,7 +1294,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Remote Memory - Opcode Matched", @@ -1303,7 +1303,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Writebacks", @@ -1312,7 +1312,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Write transactions in the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AD Ring", @@ -1320,7 +1320,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AK Ring", @@ -1328,7 +1328,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto BL Ring", @@ -1336,7 +1336,7 @@ "EventName": "UNC_C_TxR_ADS_USED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Cachebo", @@ -1345,7 +1345,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Corebo", @@ -1354,7 +1354,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AD ring. This is commonly used for outbound requests.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Cachebo", @@ -1363,7 +1363,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AK ring. This is commonly used for credit returns and GO responses.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Corebo", @@ -1372,7 +1372,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AK ring. This is commonly used for snoop responses coming from the core and destined for a Cachebo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Cacheno", @@ -1381,7 +1381,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the BL ring. This is commonly used to send data from the cache to various destinations.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Corebo", @@ -1390,7 +1390,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; IV - Cachebo", @@ -1399,7 +1399,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the IV ring. This is commonly used for snoops to the cores.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AD Ring (to core)", @@ -1408,7 +1408,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the core AD egress spent in starvation", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AK Ring", @@ -1417,7 +1417,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both AK egresses spent in starvation", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto BL Ring", @@ -1426,7 +1426,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both BL egresses spent in starvation", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto IV Ring", @@ -1435,7 +1435,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the cachebo IV egress spent in starvation", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BT Cycles Not Empty", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json new file mode 100644 index 000000000000..8a327e0f1441 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json @@ -0,0 +1,614 @@ +[ + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CLFlush", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CRd", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.CRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; DRd", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.DRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIDCAHin5t", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIRdCur", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIItoM", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; RFO", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.RFO", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; WbMtoI", + "EventCode": "0x13", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Requests", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_TIMEOUT", + "PerPkg": "1", + "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Data Throttled", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.DATA_THROTTLE", + "PerPkg": "1", + "PublicDescription": "IRP throttled switch data", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Invalid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Valid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_RxR_AK_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit E or S", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit E or S", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit I", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit I", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit M", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : Hit M", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Miss", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : Miss", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpCode", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpCode", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpData", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpData", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpInv", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "PublicDescription": "Snoop Responses : SnpInv", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Atomic", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Other", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.RD_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Write Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xF", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xD", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-io.json similarity index 53% rename from tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json rename to tools/perf/pmu-events/arch/x86/broadwellde/uncore-io.json index fea3dea67f38..01e04daf03da 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-io.json @@ -1,482 +1,4 @@ [ - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Select Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Clocks in the IRP", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of clocks in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CLFlush", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; DRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.DRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIDCAHin5t", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIRdCur", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIItoM", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; RFO", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; WbMtoI", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Requests", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_TIMEOUT", - "PerPkg": "1", - "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Data Throttled", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.DATA_THROTTLE", - "PerPkg": "1", - "PublicDescription": "IRP throttled switch data", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Invalid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Valid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Ingress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_RxR_AK_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "EventCode": "0x4", - "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - DRS", - "EventCode": "0x1", - "EventName": "UNC_I_RxR_BL_DRS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "EventCode": "0x7", - "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "EventCode": "0x5", - "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCB", - "EventCode": "0x2", - "EventName": "UNC_I_RxR_BL_NCB_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "EventCode": "0x8", - "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "EventCode": "0x6", - "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCS", - "EventCode": "0x3", - "EventName": "UNC_I_RxR_BL_NCS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "EventCode": "0x9", - "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit E or S", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit E or S", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit I", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit I", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit M", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit M", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Miss", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Miss", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpCode", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpCode", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpData", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpData", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpInv", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpInv", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Atomic", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Other", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.RD_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Write Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x18", - "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x19", - "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xF", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xD", - "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, { "BriefDescription": "Number of uclks in domain", "EventCode": "0x1", @@ -1029,139 +551,5 @@ "PublicDescription": "AD CounterClockwise Egress Queue", "UMask": "0x10", "Unit": "R2PCIe" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.CMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Livelock", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; LTError", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LTERROR", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T0", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T1", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Other", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.OTHER", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Trap", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.TRAP", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.UMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x20", - "Unit": "UBOX" } ] -- GitLab From c9f485c63d9332d4bc09e2d688613b231f0aa754 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:35 -0700 Subject: [PATCH 2995/5631] perf vendor events intel: Fix uncore topics for broadwellx Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/broadwellx/uncore-cache.json | 358 +- .../x86/broadwellx/uncore-interconnect.json | 4297 ++++++++++++++--- .../arch/x86/broadwellx/uncore-io.json | 555 +++ .../arch/x86/broadwellx/uncore-other.json | 3242 ------------- 4 files changed, 4226 insertions(+), 4226 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json index f794d2992323..400d784d1457 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json @@ -8,7 +8,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", @@ -19,7 +19,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", @@ -30,7 +30,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", @@ -41,7 +41,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", @@ -52,7 +52,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", @@ -63,7 +63,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", @@ -74,7 +74,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", @@ -85,7 +85,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", @@ -96,7 +96,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", @@ -107,7 +107,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", @@ -118,7 +118,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", @@ -128,7 +128,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", @@ -139,7 +139,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", @@ -150,7 +150,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", @@ -161,7 +161,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", @@ -172,20 +172,20 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Bounce Control", "EventCode": "0xA", "EventName": "UNC_C_BOUNCE_CONTROL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Counter 0 Occupancy", @@ -193,7 +193,7 @@ "EventName": "UNC_C_COUNTER0_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "FaST wire asserted", @@ -201,7 +201,7 @@ "EventName": "UNC_C_FAST_ASSERTED", "PerPkg": "1", "PublicDescription": "Counts the number of cycles either the local distress or incoming distress signals are asserted. Incoming distress includes both up and dn.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", @@ -212,7 +212,7 @@ "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", "ScaleUnit": "64Bytes", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Data Read Request", @@ -221,7 +221,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Lookups that Match NID", @@ -230,7 +230,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Any Read Request", @@ -239,7 +239,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; External Snoop Request", @@ -248,7 +248,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", "UMask": "0x9", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Write Requests", @@ -257,7 +257,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in E state", @@ -266,7 +266,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -275,7 +275,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in S State", @@ -284,7 +284,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -293,7 +293,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "M line evictions from LLC (writebacks to memory)", @@ -303,7 +303,7 @@ "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", @@ -312,7 +312,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; DRd hitting non-M with raw CV=0", @@ -321,7 +321,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Clean Victim with raw CV=0", @@ -330,7 +330,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; RFO HitS", @@ -339,7 +339,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Number of times that an RFO hit in S state. This is useful for determining if it might be good for a workload to use RspIWB instead of RspSWB.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Silent Snoop Eviction", @@ -348,7 +348,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc", @@ -357,7 +357,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Write Combining Aliasing", @@ -366,7 +366,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 0", @@ -375,7 +375,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 0", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 1", @@ -384,7 +384,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 2", @@ -393,7 +393,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 2", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 3", @@ -402,7 +402,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 3", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Bits Decremented", @@ -411,7 +411,7 @@ "PerPkg": "1", "PublicDescription": "How often all LRU bits were decremented by 1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; Non-0 Aged Victim", @@ -420,7 +420,7 @@ "PerPkg": "1", "PublicDescription": "How often we picked a victim that had a non-zero age", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; All", @@ -429,7 +429,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down", @@ -438,7 +438,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX-- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even", @@ -447,7 +447,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd", @@ -456,7 +456,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up", @@ -465,7 +465,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even", @@ -474,7 +474,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd", @@ -483,7 +483,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; All", @@ -492,7 +492,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down", @@ -501,7 +501,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even", @@ -510,7 +510,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd", @@ -519,7 +519,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up", @@ -528,7 +528,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even", @@ -537,7 +537,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd", @@ -546,7 +546,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -555,7 +555,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -564,7 +564,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even", @@ -573,7 +573,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd", @@ -582,7 +582,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up", @@ -591,7 +591,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even", @@ -600,7 +600,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd", @@ -609,7 +609,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AD", @@ -617,7 +617,7 @@ "EventName": "UNC_C_RING_BOUNCES.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AK", @@ -625,7 +625,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; BL", @@ -633,7 +633,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", @@ -641,7 +641,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -650,7 +650,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -659,7 +659,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -668,7 +668,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters for Down polarity", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -677,7 +677,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in BDX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD", @@ -685,7 +685,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK", @@ -693,7 +693,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL", @@ -701,7 +701,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IV", @@ -709,14 +709,14 @@ "EventName": "UNC_C_RING_SINK_STARVED.IV", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of cycles the Cbo is actively throttling traffic onto the Ring in order to limit bounce traffic.", "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", @@ -725,7 +725,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", @@ -734,7 +734,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IRQ is externally starved and therefore we are blocking the IPQ.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", @@ -743,7 +743,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; Number of times that the ISMQ Bid.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; PRQ", @@ -752,7 +752,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IPQ", @@ -761,7 +761,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ", @@ -770,7 +770,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ Rejected", @@ -779,7 +779,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -788,7 +788,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -797,7 +797,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", @@ -806,7 +806,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IPQ in Internal Starvation.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", @@ -815,7 +815,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IRQ in Internal Starvation.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", @@ -824,7 +824,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the ISMQ in Internal Starvation.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; PRQ", @@ -833,7 +833,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Address Conflict", @@ -842,7 +842,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from an address conflicts. Address conflicts out of the IPQ should be rare. They will generally only occur if two different sockets are sending requests to the same address at the same time. This is a true conflict case, unlike the IPQ Address Conflict which is commonly caused by prefetching characteristics.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Any Reject", @@ -851,7 +851,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject. TOR rejects from the IPQ can be caused by the Egress being full or Address Conflicts.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No Egress Credits", @@ -860,7 +860,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from the Egress being full. IPQ requests make use of the AD Egress for regular responses, the BL egress to forward data, and the AK egress to return credits.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No QPI Credits", @@ -869,7 +869,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No AD Sbo Credits", @@ -878,7 +878,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Target Node Filter", @@ -887,7 +887,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", @@ -896,7 +896,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because of an address match in the TOR. In order to maintain coherency, requests to the same address are not allowed to pass each other up in the Cbo. Therefore, if there is an outstanding request to a given address, one cannot issue another request to that address until it is complete. This comes up most commonly with prefetches. Outstanding prefetches occasionally will not complete their memory fetch and a demand request to the same address will then sit in the IRQ and get retried until the prefetch fills the data into the LLC. Therefore, it will not be uncommon to see this case in high bandwidth streaming workloads when the LLC Prefetcher in the core is enabled.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Any Reject", @@ -905,7 +905,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of IRQ retries that occur. Requests from the IRQ are retried if they are rejected from the TOR pipeline for a variety of reasons. Some of the most common reasons include if the Egress is full, there are no RTIDs, or there is a Physical Address match to another outstanding request.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", @@ -914,7 +914,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because it failed to acquire an entry in the Egress. The egress is the buffer that queues up for allocating onto the ring. IRQ requests can make use of all four rings and all four Egresses. If any of the queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No IIO Credits", @@ -923,7 +923,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects", @@ -932,7 +932,7 @@ "PerPkg": "1", "PublicDescription": "Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", @@ -941,7 +941,7 @@ "PerPkg": "1", "PublicDescription": "Number of requests rejects because of lack of QPI Ingress credits. These credits are required in order to send transactions to the QPI agent. Please see the QPI_IGR_CREDITS events for more information.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", @@ -950,7 +950,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that requests from the IRQ were retried because there were no RTIDs available. RTIDs are required after a request misses the LLC and needs to send snoops and/or requests to memory. If there are no RTIDs available, requests will queue up in the IRQ and retry until one becomes available. Note that there are multiple RTID pools for the different sockets. There may be cases where the local RTIDs are all used, but requests destined for remote memory can still acquire an RTID because there are remote RTIDs available. This event does not provide any filtering for this case.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No AD Sbo Credits", @@ -959,7 +959,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No BL Sbo Credits", @@ -968,7 +968,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Target Node Filter", @@ -977,7 +977,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; Any Reject", @@ -986,7 +986,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the total number of times that a request from the ISMQ retried because of a TOR reject. ISMQ requests generally will not need to retry (or at least ISMQ retries are less common than IRQ retries). ISMQ requests will retry if they are not able to acquire a needed Egress credit to get onto the ring, or for cache evictions that need to acquire an RTID. Most ISMQ requests already have an RTID, so eviction retries will be less common here.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No Egress Credits", @@ -995,7 +995,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by a lack of Egress credits. The egress is the buffer that queues up for allocating onto the ring. If any of the Egress queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No IIO Credits", @@ -1004,7 +1004,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -1013,7 +1013,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No QPI Credits", @@ -1022,7 +1022,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No RTIDs", @@ -1031,7 +1031,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by no RTIDs. M-state cache evictions are serviced through the ISMQ, and must acquire an RTID in order to write back to memory. If no RTIDs are available, they will be retried.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -1040,7 +1040,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No AD Sbo Credits", @@ -1049,7 +1049,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No BL Sbo Credits", @@ -1058,7 +1058,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; Target Node Filter", @@ -1067,7 +1067,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IPQ", @@ -1076,7 +1076,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ", @@ -1085,7 +1085,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ Rejected", @@ -1094,7 +1094,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; PRQ Rejects", @@ -1103,7 +1103,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For AD Ring", @@ -1112,7 +1112,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For BL Ring", @@ -1121,7 +1121,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For AD Ring", @@ -1130,7 +1130,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For BL Ring", @@ -1139,7 +1139,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; All", @@ -1148,7 +1148,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Evictions", @@ -1157,7 +1157,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory", @@ -1166,7 +1166,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory - Opcode Matched", @@ -1175,7 +1175,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory", @@ -1184,7 +1184,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory - Opcode Matched", @@ -1193,7 +1193,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss Opcode Match", @@ -1202,7 +1202,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory", @@ -1211,7 +1211,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory - Opcode Matched", @@ -1220,7 +1220,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched", @@ -1229,7 +1229,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Evictions", @@ -1238,7 +1238,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Miss All", @@ -1247,7 +1247,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", @@ -1256,7 +1256,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched", @@ -1265,7 +1265,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Writebacks", @@ -1274,7 +1274,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Opcode Match", @@ -1283,7 +1283,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory", @@ -1292,7 +1292,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory - Opcode Matched", @@ -1301,7 +1301,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Writebacks", @@ -1310,7 +1310,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Any", @@ -1319,7 +1319,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All valid TOR entries. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Evictions", @@ -1328,7 +1328,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding eviction transactions in the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", @@ -1338,7 +1338,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1347,7 +1347,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Local Memory - Opcode Matched", @@ -1356,7 +1356,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss All", @@ -1365,7 +1365,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding miss requests in the TOR. 'Miss' means the allocation requires an RTID. This generally means that the request was sent to memory or MMIO.", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1374,7 +1374,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Local Memory - Opcode Matched", @@ -1383,7 +1383,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss Opcode Match", @@ -1392,7 +1392,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1401,7 +1401,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Remote Memory - Opcode Matched", @@ -1410,7 +1410,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1419,7 +1419,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of NID matched outstanding requests in the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid.In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Evictions", @@ -1428,7 +1428,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding NID matched eviction transactions in the TOR .", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1437,7 +1437,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", @@ -1446,7 +1446,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched", @@ -1455,7 +1455,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Writebacks", @@ -1464,7 +1464,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); NID matched write transactions int the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Opcode Match", @@ -1473,7 +1473,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc).", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1482,7 +1482,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Remote Memory - Opcode Matched", @@ -1491,7 +1491,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Writebacks", @@ -1500,7 +1500,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Write transactions in the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AD Ring", @@ -1508,7 +1508,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AK Ring", @@ -1516,7 +1516,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto BL Ring", @@ -1524,7 +1524,7 @@ "EventName": "UNC_C_TxR_ADS_USED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Cachebo", @@ -1533,7 +1533,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Corebo", @@ -1542,7 +1542,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AD ring. This is commonly used for outbound requests.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Cachebo", @@ -1551,7 +1551,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AK ring. This is commonly used for credit returns and GO responses.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Corebo", @@ -1560,7 +1560,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AK ring. This is commonly used for snoop responses coming from the core and destined for a Cachebo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Cacheno", @@ -1569,7 +1569,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the BL ring. This is commonly used to send data from the cache to various destinations.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Corebo", @@ -1578,7 +1578,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; IV - Cachebo", @@ -1587,7 +1587,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the IV ring. This is commonly used for snoops to the cores.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AD Ring (to core)", @@ -1596,7 +1596,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the core AD egress spent in starvation", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AK Ring", @@ -1605,7 +1605,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both AK egresses spent in starvation", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto BL Ring", @@ -1614,7 +1614,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both BL egresses spent in starvation", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto IV Ring", @@ -1623,7 +1623,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the cachebo IV egress spent in starvation", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BT Cycles Not Empty", diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json index 2819c6621089..e61a23f68899 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -6,7 +6,7 @@ "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "ScaleUnit": "8Bytes", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", @@ -15,1317 +15,4004 @@ "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "ScaleUnit": "8Bytes", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { - "BriefDescription": "Number of qfclks", - "EventCode": "0x14", - "EventName": "UNC_Q_CLOCKTICKS", + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", "PerPkg": "1", - "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/4th the GT/s speed of the QPI link. For example, a 4GT/s link will have qfclk or 1GHz. BDX does not support dynamic link speeds, so this frequency is fixed.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" }, { - "BriefDescription": "Count of CTO Events", - "EventCode": "0x38", - "EventName": "UNC_Q_CTO_COUNT", + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", "PerPkg": "1", - "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CLFlush", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", + "BriefDescription": "Coherent Ops; CRd", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", + "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", + "BriefDescription": "Coherent Ops; DRd", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", + "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", + "BriefDescription": "Coherent Ops; PCIDCAHin5t", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", + "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", - "UMask": "0x80", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", + "BriefDescription": "Coherent Ops; PCIRdCur", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", + "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x1", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", + "BriefDescription": "Coherent Ops; PCIItoM", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", + "BriefDescription": "Coherent Ops; RFO", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", + "EventName": "UNC_I_COHERENT_OPS.RFO", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", - "UMask": "0x40", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Success", + "BriefDescription": "Coherent Ops; WbMtoI", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L1", - "EventCode": "0x12", - "EventName": "UNC_Q_L1_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L0p", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L0", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL0_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "Rx Flit Buffer Bypassed", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_BYPASSED", + "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REJ", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "CRC Errors Detected; LinkInit", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_CRC_ERRORS.LINK_INIT", + "BriefDescription": "Misc Events - Set 0; Fastpath Requests", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REQ", "PerPkg": "1", - "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_XFER", "PerPkg": "1", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; DRS", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.DRS", + "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; HOM", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.HOM", + "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_TIMEOUT", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NCB", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCB", + "BriefDescription": "Misc Events - Set 1; Data Throttled", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.DATA_THROTTLE", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "IRP throttled switch data", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NCS", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCS", + "BriefDescription": "Misc Events - Set 1", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.LOST_FWD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NDR", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NDR", + "BriefDescription": "Misc Events - Set 1; Received Invalid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; SNP", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.SNP", + "BriefDescription": "Misc Events - Set 1; Received Valid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; DRS", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.DRS", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_E", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; HOM", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.HOM", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_M", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NCB", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCB", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_S", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NCS", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCS", + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_RxR_AK_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NDR", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NDR", + "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; SNP", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.SNP", + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "VNA Credit Consumed", - "EventCode": "0x1D", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", + "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_CYCLES_NE", + "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN0", + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN1", + "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", - "EventCode": "0x12", - "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN0", + "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", - "EventCode": "0x12", - "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN1", + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN0", + "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN1", + "BriefDescription": "Snoop Responses; Hit E or S", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit E or S", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", - "EventCode": "0x11", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN0", + "BriefDescription": "Snoop Responses; Hit I", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit I", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", - "EventCode": "0x11", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN1", + "BriefDescription": "Snoop Responses; Hit M", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit M", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", - "EventCode": "0x14", - "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN0", + "BriefDescription": "Snoop Responses; Miss", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "PublicDescription": "Snoop Responses : Miss", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", - "EventCode": "0x14", - "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN1", + "BriefDescription": "Snoop Responses; SnpCode", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpCode", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", - "EventCode": "0x13", - "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN0", + "BriefDescription": "Snoop Responses; SnpData", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpData", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", - "EventCode": "0x13", - "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN1", + "BriefDescription": "Snoop Responses; SnpInv", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpInv", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", + "BriefDescription": "Inbound Transaction Count; Atomic", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Other", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.RD_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Write Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xF", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xD", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Number of qfclks", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/4th the GT/s speed of the QPI link. For example, a 4GT/s link will have qfclk or 1GHz. BDX does not support dynamic link speeds, so this frequency is fixed.", + "Unit": "QPI" + }, + { + "BriefDescription": "Count of CTO Events", + "EventCode": "0x38", + "EventName": "UNC_Q_CTO_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", + "UMask": "0x80", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", + "UMask": "0x40", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Success", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L1", + "EventCode": "0x12", + "EventName": "UNC_Q_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Bypassed", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "Unit": "QPI" + }, + { + "BriefDescription": "CRC Errors Detected; LinkInit", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.LINK_INIT", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; DRS", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; HOM", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCB", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCS", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NDR", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; SNP", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; DRS", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; HOM", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCB", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCS", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NDR", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; SNP", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x1D", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", + "UMask": "0x18", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Data Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Header Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Request Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; SNP Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xc", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations", + "EventCode": "0x8", + "EventName": "UNC_Q_RxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN0", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN1", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN0", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN1", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN0", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN1", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN0", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN1", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN0", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN1", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN0", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN1", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_DRS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_HOM", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCB", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NDR", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_SNP", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.EGRESS_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", + "UMask": "0x40", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.GV", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", + "UMask": "0x80", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_DRS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_HOM", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCB", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NDR", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_SNP", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0xD", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0xC", + "EventName": "UNC_Q_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "EventCode": "0x5", + "EventName": "UNC_Q_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.ALMOST_FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Cycles not Empty", + "EventCode": "0x6", + "EventName": "UNC_Q_TxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", + "UMask": "0x18", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; SNP Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xc", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x4", + "EventName": "UNC_Q_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x7", + "EventName": "UNC_Q_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "EventCode": "0x29", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "EventCode": "0x25", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN_SHR", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN_SHR", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", + "EventCode": "0x2B", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", + "EventCode": "0x2B", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", + "EventCode": "0x2C", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", + "EventCode": "0x2C", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credits Returned", + "EventCode": "0x1C", + "EventName": "UNC_Q_VNA_CREDIT_RETURNS", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits returned.", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x1B", + "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Number of uclks in domain", "EventCode": "0x1", - "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14_16", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO_15_17", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 15&17", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Backpressure", + "EventCode": "0xB", + "EventName": "UNC_R3_IOT_BACKPRESSURE.HUB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Backpressure", + "EventCode": "0xB", + "EventName": "UNC_R3_IOT_BACKPRESSURE.SAT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Hi", + "EventCode": "0xD", + "EventName": "UNC_R3_IOT_CTS_HI.CTS2", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Hi", + "EventCode": "0xD", + "EventName": "UNC_R3_IOT_CTS_HI.CTS3", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Lo", + "EventCode": "0xC", + "EventName": "UNC_R3_IOT_CTS_LO.CTS0", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Lo", + "EventCode": "0xC", + "EventName": "UNC_R3_IOT_CTS_LO.CTS1", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; All", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; All", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; All", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 IV Ring in Use; Clockwise", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ring Stop Starved; AK", + "EventCode": "0xE", + "EventName": "UNC_R3_RING_SINK_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles the ringstop is in starvation (per ring)", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; DRS", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; HOM", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NCB", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NCS", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NDR", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; SNP", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; DRS", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; HOM", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NCB", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NCS", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NDR", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; SNP", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For AD Ring", + "EventCode": "0x28", + "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For BL Ring", + "EventCode": "0x28", + "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", + "EventCode": "0x2A", + "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", + "EventCode": "0x2A", + "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo1 Credits Acquired; For AD Ring", + "EventCode": "0x29", + "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", + "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS", + "BriefDescription": "SBo1 Credits Acquired; For BL Ring", + "EventCode": "0x29", + "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", - "UMask": "0x18", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Data Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", + "BriefDescription": "SBo1 Credits Occupancy; For AD Ring", + "EventCode": "0x2B", + "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Header Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", + "BriefDescription": "SBo1 Credits Occupancy; For BL Ring", + "EventCode": "0x2B", + "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM", + "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", - "UMask": "0x6", - "Unit": "QPI LL" + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", + "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Request Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", + "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; SNP Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.SNP", + "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x8", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB", + "BriefDescription": "Egress CCW NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", - "UMask": "0xc", - "Unit": "QPI LL" + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "PublicDescription": "AK CounterClockwise Egress Queue", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCS", + "BriefDescription": "Egress CCW NACK; BL CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations", - "EventCode": "0x8", - "EventName": "UNC_Q_RxL_INSERTS", + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_INSERTS_DRS.VN0", + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_INSERTS_DRS.VN1", + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", - "EventCode": "0xC", - "EventName": "UNC_Q_RxL_INSERTS_HOM.VN0", + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", - "EventCode": "0xC", - "EventName": "UNC_Q_RxL_INSERTS_HOM.VN1", + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_INSERTS_NCB.VN0", + "BriefDescription": "VN1 Credit Used; DRS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; HOM Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_INSERTS_NCB.VN1", + "BriefDescription": "VN1 Credit Used; NCB Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NDR Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_INSERTS_NCS.VN0", + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_INSERTS_NCS.VN1", + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", - "EventCode": "0xE", - "EventName": "UNC_Q_RxL_INSERTS_NDR.VN0", + "BriefDescription": "Bounce Control", + "EventCode": "0xA", + "EventName": "UNC_S_BOUNCE_CONTROL", + "PerPkg": "1", + "Unit": "SBOX" + }, + { + "BriefDescription": "Uncore Clocks", + "EventName": "UNC_S_CLOCKTICKS", + "PerPkg": "1", + "Unit": "SBOX" + }, + { + "BriefDescription": "FaST wire asserted", + "EventCode": "0x9", + "EventName": "UNC_S_FAST_ASSERTED", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; All", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xf", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down and Event", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down and Odd", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Up", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Up and Even", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP_EVEN", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", - "EventCode": "0xE", - "EventName": "UNC_Q_RxL_INSERTS_NDR.VN1", + "BriefDescription": "AD Ring In Use; Up and Odd", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", - "EventCode": "0xD", - "EventName": "UNC_Q_RxL_INSERTS_SNP.VN0", + "BriefDescription": "AK Ring In Use; All", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.ALL", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xf", + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", - "EventCode": "0xD", - "EventName": "UNC_Q_RxL_INSERTS_SNP.VN1", + "BriefDescription": "AK Ring In Use; Down", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - All Packets", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_OCCUPANCY", + "BriefDescription": "AK Ring In Use; Down and Event", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - DRS; for VN0", - "EventCode": "0x15", - "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN0", + "BriefDescription": "AK Ring In Use; Down and Odd", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - DRS; for VN1", - "EventCode": "0x15", - "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN1", + "BriefDescription": "AK Ring In Use; Up", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - HOM; for VN0", - "EventCode": "0x18", - "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN0", + "BriefDescription": "AK Ring In Use; Up and Even", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - HOM; for VN1", - "EventCode": "0x18", - "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN1", + "BriefDescription": "AK Ring In Use; Up and Odd", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCB; for VN0", - "EventCode": "0x16", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN0", + "BriefDescription": "BL Ring in Use; All", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.ALL", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xf", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCB; for VN1", - "EventCode": "0x16", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN1", + "BriefDescription": "BL Ring in Use; Down", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCS; for VN0", - "EventCode": "0x17", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN0", + "BriefDescription": "BL Ring in Use; Down and Event", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCS; for VN1", - "EventCode": "0x17", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN1", + "BriefDescription": "BL Ring in Use; Down and Odd", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NDR; for VN0", - "EventCode": "0x1A", - "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN0", + "BriefDescription": "BL Ring in Use; Up", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" + }, + { + "BriefDescription": "BL Ring in Use; Up and Even", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NDR; for VN1", - "EventCode": "0x1A", - "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN1", + "BriefDescription": "BL Ring in Use; Up and Odd", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - SNP; for VN0", - "EventCode": "0x19", - "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN0", + "BriefDescription": "Number of LLC responses that bounced on the Ring.", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.AD_CACHE", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - SNP; for VN1", - "EventCode": "0x19", - "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN1", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.AK_CORE", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_DRS", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x1", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_HOM", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.IV_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCB", + "BriefDescription": "BL Ring in Use; Any", + "EventCode": "0x1E", + "EventName": "UNC_S_RING_IV_USED.DN", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCS", + "BriefDescription": "BL Ring in Use; Any", + "EventCode": "0x1E", + "EventName": "UNC_S_RING_IV_USED.UP", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", + "UMask": "0x3", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NDR", + "BriefDescription": "UNC_S_RING_SINK_STARVED.AD_CACHE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.AD_CACHE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x20", - "Unit": "QPI LL" + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_SNP", + "BriefDescription": "UNC_S_RING_SINK_STARVED.AK_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.AK_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x10", - "Unit": "QPI LL" + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.EGRESS_CREDITS", + "BriefDescription": "UNC_S_RING_SINK_STARVED.BL_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", - "UMask": "0x40", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.GV", + "BriefDescription": "UNC_S_RING_SINK_STARVED.IV_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.IV_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", - "UMask": "0x80", - "Unit": "QPI LL" + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_DRS", + "BriefDescription": "Injection Starvation; AD - Bounces", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", + "UMask": "0x2", + "Unit": "SBOX" + }, + { + "BriefDescription": "Injection Starvation; AD - Credits", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_HOM", + "BriefDescription": "Injection Starvation; BL - Bounces", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCB", + "BriefDescription": "Injection Starvation; BL - Credits", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCS", + "BriefDescription": "Bypass; AD - Bounces", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NDR", + "BriefDescription": "Bypass; AD - Credits", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_SNP", + "BriefDescription": "Bypass; AK", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AK", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Bypass the Sbo Ingress.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Cycles in L0p", - "EventCode": "0xD", - "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "BriefDescription": "Bypass; BL - Bounces", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Cycles in L0", - "EventCode": "0xC", - "EventName": "UNC_Q_TxL0_POWER_CYCLES", + "BriefDescription": "Bypass; BL - Credits", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Bypassed", - "EventCode": "0x5", - "EventName": "UNC_Q_TxL_BYPASSED", + "BriefDescription": "Bypass; IV", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", - "EventCode": "0x2", - "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.ALMOST_FULL", + "BriefDescription": "Injection Starvation; AD - Bounces", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", - "EventCode": "0x2", - "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.FULL", + "BriefDescription": "Injection Starvation; AD - Credits", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Cycles not Empty", - "EventCode": "0x6", - "EventName": "UNC_Q_TxL_CYCLES_NE", + "BriefDescription": "Injection Starvation; AK", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", - "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "BriefDescription": "Injection Starvation; BL - Bounces", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", - "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "BriefDescription": "Injection Starvation; BL - Credits", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS", + "BriefDescription": "Injection Starvation; IVF Credit", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.IFV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", - "UMask": "0x18", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x40", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", + "BriefDescription": "Injection Starvation; IV", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Allocations; AD - Bounces", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x2", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Allocations; AD - Credits", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", + "BriefDescription": "Ingress Allocations; AK", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM", + "BriefDescription": "Ingress Allocations; BL - Bounces", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", - "UMask": "0x6", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", + "BriefDescription": "Ingress Allocations; BL - Credits", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", + "BriefDescription": "Ingress Allocations; IV", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Occupancy; AD - Bounces", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; SNP Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.SNP", + "BriefDescription": "Ingress Occupancy; AD - Credits", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AD_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB", + "BriefDescription": "Ingress Occupancy; AK", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", - "UMask": "0xc", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", + "BriefDescription": "Ingress Occupancy; BL - Bounces", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", + "BriefDescription": "Ingress Occupancy; BL - Credits", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCS", + "BriefDescription": "Ingress Occupancy; IV", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", + "BriefDescription": "UNC_S_TxR_ADS_USED.AD", + "EventCode": "0x4", + "EventName": "UNC_S_TxR_ADS_USED.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", + "BriefDescription": "UNC_S_TxR_ADS_USED.AK", + "EventCode": "0x4", + "EventName": "UNC_S_TxR_ADS_USED.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Allocations", + "BriefDescription": "UNC_S_TxR_ADS_USED.BL", "EventCode": "0x4", - "EventName": "UNC_Q_TxL_INSERTS", + "EventName": "UNC_S_TxR_ADS_USED.BL", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x7", - "EventName": "UNC_Q_TxL_OCCUPANCY", + "BriefDescription": "Egress Allocations; AD - Bounces", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AD_BNC", "PerPkg": "1", - "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", - "EventCode": "0x26", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Allocations; AD - Credits", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", - "EventCode": "0x26", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Allocations; AK", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AK", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", - "EventCode": "0x22", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Allocations; BL - Bounces", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", - "EventCode": "0x22", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Egress Allocations; BL - Credits", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", - "EventCode": "0x28", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Allocations; IV", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.IV", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", - "EventCode": "0x28", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Occupancy; AD - Bounces", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", - "EventCode": "0x24", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Occupancy; AD - Credits", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AD_CRD", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", - "EventCode": "0x24", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Egress Occupancy; AK", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", - "EventCode": "0x27", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Occupancy; BL - Bounces", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", - "EventCode": "0x27", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Occupancy; BL - Credits", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", - "EventCode": "0x23", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Occupancy; IV", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.IV", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Injection Starvation; Onto AD Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.AD", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", - "EventCode": "0x23", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Injection Starvation; Onto AK Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.AK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", - "EventCode": "0x29", - "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", + "BriefDescription": "Injection Starvation; Onto BL Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.BL", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", - "EventCode": "0x25", - "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", + "BriefDescription": "Injection Starvation; Onto IV Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.IV", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN1", + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN_SHR", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN_SHR", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", - "EventCode": "0x2B", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", - "EventCode": "0x2B", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN1", + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number outstanding register requests within message channel tracker", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", - "EventCode": "0x20", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", - "EventCode": "0x20", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", - "EventCode": "0x2C", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", - "EventCode": "0x2C", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", - "EventCode": "0x21", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", - "EventCode": "0x21", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" }, { - "BriefDescription": "VNA Credits Returned", - "EventCode": "0x1C", - "EventName": "UNC_Q_VNA_CREDIT_RETURNS", + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", "PerPkg": "1", - "PublicDescription": "Number of VNA credits returned.", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" }, { - "BriefDescription": "VNA Credits Pending Return - Occupancy", - "EventCode": "0x1B", - "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", "PerPkg": "1", - "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-io.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-io.json new file mode 100644 index 000000000000..01e04daf03da --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-io.json @@ -0,0 +1,555 @@ +[ + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R2_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI0", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI1", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; DRS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCB", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; All", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Dn", + "EventCode": "0x12", + "EventName": "UNC_R2_RING_AK_BOUNCES.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Up", + "EventCode": "0x12", + "EventName": "UNC_R2_RING_AK_BOUNCES.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; All", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; All", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For AD Ring", + "EventCode": "0x28", + "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For BL Ring", + "EventCode": "0x28", + "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", + "EventCode": "0x2A", + "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", + "EventCode": "0x2A", + "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AD", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AK", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; BL", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AD", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AK", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; BL", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_AD", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_AK", + "PerPkg": "1", + "PublicDescription": "AK CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_BL", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_AK", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json deleted file mode 100644 index 43def2582617..000000000000 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-other.json +++ /dev/null @@ -1,3242 +0,0 @@ -[ - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Select Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Clocks in the IRP", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of clocks in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CLFlush", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; DRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.DRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIDCAHin5t", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIRdCur", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIItoM", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; RFO", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; WbMtoI", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Requests", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_TIMEOUT", - "PerPkg": "1", - "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Data Throttled", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.DATA_THROTTLE", - "PerPkg": "1", - "PublicDescription": "IRP throttled switch data", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Invalid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Valid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Ingress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_RxR_AK_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "EventCode": "0x4", - "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - DRS", - "EventCode": "0x1", - "EventName": "UNC_I_RxR_BL_DRS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "EventCode": "0x7", - "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "EventCode": "0x5", - "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCB", - "EventCode": "0x2", - "EventName": "UNC_I_RxR_BL_NCB_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "EventCode": "0x8", - "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "EventCode": "0x6", - "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCS", - "EventCode": "0x3", - "EventName": "UNC_I_RxR_BL_NCS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "EventCode": "0x9", - "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit E or S", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit E or S", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit I", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit I", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit M", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit M", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Miss", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Miss", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpCode", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpCode", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpData", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpData", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpInv", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpInv", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Atomic", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Other", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.RD_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Write Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x18", - "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x19", - "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xF", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xD", - "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R2_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI0", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI1", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; DRS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCB", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; All", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Dn", - "EventCode": "0x12", - "EventName": "UNC_R2_RING_AK_BOUNCES.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Up", - "EventCode": "0x12", - "EventName": "UNC_R2_RING_AK_BOUNCES.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; All", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; All", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Counterclockwise", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Clockwise", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCB", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCS", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For AD Ring", - "EventCode": "0x28", - "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For BL Ring", - "EventCode": "0x28", - "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", - "EventCode": "0x2A", - "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", - "EventCode": "0x2A", - "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AD", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AK", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; BL", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AD", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AK", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; BL", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AD CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_AD", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_AK", - "PerPkg": "1", - "PublicDescription": "AK CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_BL", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_AD", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_AK", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_BL", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R3_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14_16", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO_15_17", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 15&17", - "UMask": "0x80", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", - "UMask": "0x80", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Backpressure", - "EventCode": "0xB", - "EventName": "UNC_R3_IOT_BACKPRESSURE.HUB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Backpressure", - "EventCode": "0xB", - "EventName": "UNC_R3_IOT_BACKPRESSURE.SAT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Hi", - "EventCode": "0xD", - "EventName": "UNC_R3_IOT_CTS_HI.CTS2", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Hi", - "EventCode": "0xD", - "EventName": "UNC_R3_IOT_CTS_HI.CTS3", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Lo", - "EventCode": "0xC", - "EventName": "UNC_R3_IOT_CTS_LO.CTS0", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Lo", - "EventCode": "0xC", - "EventName": "UNC_R3_IOT_CTS_LO.CTS1", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; All", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; All", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; All", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R3_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 IV Ring in Use; Clockwise", - "EventCode": "0xA", - "EventName": "UNC_R3_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ring Stop Starved; AK", - "EventCode": "0xE", - "EventName": "UNC_R3_RING_SINK_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles the ringstop is in starvation (per ring)", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; HOM", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NDR", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; SNP", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; DRS", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; HOM", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NCB", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NCS", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NDR", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; SNP", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; DRS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; HOM", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NDR", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; SNP", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; DRS", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; HOM", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NCB", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NCS", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NDR", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; SNP", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; HOM", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCB", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NDR", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; SNP", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For AD Ring", - "EventCode": "0x28", - "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For BL Ring", - "EventCode": "0x28", - "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", - "EventCode": "0x2A", - "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", - "EventCode": "0x2A", - "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Acquired; For AD Ring", - "EventCode": "0x29", - "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Acquired; For BL Ring", - "EventCode": "0x29", - "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Occupancy; For AD Ring", - "EventCode": "0x2B", - "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Occupancy; For BL Ring", - "EventCode": "0x2B", - "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AD CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_AD", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_AK", - "PerPkg": "1", - "PublicDescription": "AK CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_BL", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_AD", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_AK", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_BL", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; DRS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; HOM Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NDR Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; DRS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; HOM Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCB Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NDR Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; SNP Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; DRS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; HOM Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCB Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NDR Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; SNP Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Bounce Control", - "EventCode": "0xA", - "EventName": "UNC_S_BOUNCE_CONTROL", - "PerPkg": "1", - "Unit": "SBO" - }, - { - "BriefDescription": "Uncore Clocks", - "EventName": "UNC_S_CLOCKTICKS", - "PerPkg": "1", - "Unit": "SBO" - }, - { - "BriefDescription": "FaST wire asserted", - "EventCode": "0x9", - "EventName": "UNC_S_FAST_ASSERTED", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; All", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xf", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down and Event", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down and Odd", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up and Even", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up and Odd", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; All", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xf", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down and Event", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down and Odd", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up and Even", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up and Odd", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; All", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xf", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down and Event", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down and Odd", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up and Even", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up and Odd", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in BDX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.AD_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.AK_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.BL_CORE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.IV_CORE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Any", - "EventCode": "0x1E", - "EventName": "UNC_S_RING_IV_USED.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Any", - "EventCode": "0x1E", - "EventName": "UNC_S_RING_IV_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.AD_CACHE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.AD_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.AK_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.AK_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.BL_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.BL_CORE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.IV_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.IV_CORE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Bounces", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Credits", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Bounces", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Credits", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AD - Bounces", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AD - Credits", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AK", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; BL - Bounces", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; BL - Credits", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; IV", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Bounces", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Credits", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AK", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Bounces", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Credits", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; IVF Credit", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x40", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; IV", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AD - Bounces", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AD - Credits", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AK", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; BL - Bounces", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; BL - Credits", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; IV", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AD - Bounces", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AD - Credits", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AK", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; BL - Bounces", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; BL - Credits", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; IV", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.AD", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.AK", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.BL", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AD - Bounces", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AD - Credits", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AK", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; BL - Bounces", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; BL - Credits", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; IV", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AD - Bounces", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AD - Credits", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AK", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; BL - Bounces", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; BL - Credits", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; IV", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto AD Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.AD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto AK Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto BL Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.BL", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto IV Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", - "EventCode": "0xff", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.CMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Livelock", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; LTError", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LTERROR", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T0", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T1", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Other", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.OTHER", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Trap", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.TRAP", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.UMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x20", - "Unit": "UBOX" - } -] -- GitLab From b3eb533ca5c663db8fdd9621b34b3e4c672b70f0 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:36 -0700 Subject: [PATCH 2996/5631] perf vendor events intel: Fix uncore topics for cascadelakex Remove 'uncore-other' topic classification, move to cache, interconnect, io and memory. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-9-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/cascadelakex/uncore-cache.json | 10764 +++++++ .../x86/cascadelakex/uncore-interconnect.json | 11334 +++++++ .../arch/x86/cascadelakex/uncore-io.json | 4250 +++ .../arch/x86/cascadelakex/uncore-memory.json | 2 +- .../arch/x86/cascadelakex/uncore-other.json | 26344 ---------------- 5 files changed, 26349 insertions(+), 26345 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json create mode 100644 tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/cascadelakex/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json new file mode 100644 index 000000000000..2c880535cc82 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-cache.json @@ -0,0 +1,10764 @@ +[ + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "ScaleUnit": "64Bytes", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Uncore cache clock ticks", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the clock controlling the uncore caching and home agent (CHA).", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C1 State", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C1_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C1 Transition", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C1_TRANSITION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C6 State", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C6_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C6 Transition", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C6_TRANSITION", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; GV", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.GV", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Snoop to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Core Request to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Eviction to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; External Snoop to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "Counter 0 Occupancy", + "EventCode": "0x1F", + "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; Shared hit and op is RdInvOwn, RdInv, Inv*", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoE", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; No SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a local request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "PublicDescription": "Received RspFwdI* for a local request, but converted HitME$ to SF entry", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache on RdInvOwn even if not RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a remote request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "PublicDescription": "Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache to SHARed", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued; ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Full Line MIG", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Full Line", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Partial Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Partial MIG", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Partial", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.INVITOM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations dropped due to IODC Full", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.IODCFULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IDOC allocation dropped due to OSB gate", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.OSBGATED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to any reason", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to conflicting transaction", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.SNPOUT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoE", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoI", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbPushMtoI", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", + "PerPkg": "1", + "PublicDescription": "Moved to Cbo section", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Read transactions", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Local", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Remote", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", + "UMask": "0x91", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; External Snoop Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", + "UMask": "0x9", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Write Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x5", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.F_STATE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB", + "PerPkg": "1", + "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in IODC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.IODC", + "PerPkg": "1", + "PublicDescription": "2LM related events; Counts the number of times CHA saw NM Set conflict in IODC", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", + "PerPkg": "1", + "PublicDescription": "NM evictions due to another read to the same near memory set in the LLC.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", + "PerPkg": "1", + "PublicDescription": "NM evictions due to another read to the same near memory set in the SF.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in TOR", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", + "PerPkg": "1", + "PublicDescription": "No Reject in the CHA due to a pending read to the same near memory set in the TOR.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory mode related events; Counts the number of times CHA saw NM Set conflict in TOR and the transaction was rejected", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR_REJECT", + "PerPkg": "1", + "PublicDescription": "Rejects in the CHA due to a pending read to the same near memory set in the TOR.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC0_SMI2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC1_SMI3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC2_SMI4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC3_SMI5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC0_SMI0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC1_SMI1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a remote socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Write requests", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Write Requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Read and Write Requests; Writes Remote", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_CHA_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IPQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; RRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; WBQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; AD REQ on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; AD RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Non UPI AK Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL NCB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL NCS on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL WB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Non UPI IV Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Allow Snoop", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; ANY0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; HA", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; LLC Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; PhyAddr Match", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; SF Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; AD REQ on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; AD RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; Non UPI AK Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL NCB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL NCS on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL WB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; Non UPI IV Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; ANY0", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; HA", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IPQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; RRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; WBQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; AD REQ on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; AD RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Non UPI AK Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL NCB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL NCS on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL WB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Non UPI IV Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Allow Snoop", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; ANY0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; HA", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; LLC Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; PhyAddr Match", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; SF Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; AD REQ on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; AD RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Non UPI AK Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL NCB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL NCS on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL WB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Non UPI IV Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Allow Snoop", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; ANY0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; HA", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; LLC Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; PhyAddr Match", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; SF Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; AD REQ on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; AD RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Non UPI AK Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL NCB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL NCS on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL WB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Non UPI IV Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Allow Snoop", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; ANY0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; HA", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; LLC Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; PhyAddr Match", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; SF Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; AD REQ on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; AD RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Non UPI AK Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL NCB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL NCS on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL WB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Non UPI IV Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Allow Snoop", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; ANY0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; HA", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; LLC Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; PhyAddr Match", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; SF Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast snoop for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Directed snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RspCnflct* Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received; RspFwd", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspS", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RspS : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*WB Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to its home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspCnflct", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspI", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspIFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspS", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspSFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*FWD*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0xff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x15", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_IO_IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests", + "UMask": "0x35", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from Local", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x25", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hit (Not a Miss)", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from iA Cores", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally generated IO traffic", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "Filter": "config1=0x49033", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", + "Filter": "config1=0x43C33", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; IPQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; IRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Miss", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; PRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ_HIT", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ_MISS", + "PerPkg": "1", + "UMask": "0x60", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ_HIT", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ_MISS", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All remotely generated requests", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x17", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x27", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hit (Not a Miss)", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally initiated requests from iA Cores", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally generated IO traffic", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM Misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "Filter": "config1=0x49033", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RDCUR misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", + "Filter": "config1=0x43C33", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; IPQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; IRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Miss", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; PRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; AD REQ Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; AD RSP VN0 Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL NCB Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL NCS Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL RSP Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL DRS Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; VN0 Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; VNA Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD REQ VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD RSP VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCB VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCS VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL RSP VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL DRS VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD VNA Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_AD", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL VNA Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_BL", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI; Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI; Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC0_SMI2", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC1_SMI3", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC2_SMI4", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC3_SMI5", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC0_SMI0", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC1_SMI1", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd F/E", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd M", + "UMask": "0xf0", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd F/E", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd M", + "UMask": "0xe8", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response any to Hit F/S/E", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd F/E", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd M", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd F/E", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd M", + "UMask": "0x48", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response any to Hit F/S/E", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd F/E", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd M", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd F/E", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd M", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response any to Hit F/S/E", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd F/E", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd M", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd F/E", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd M", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response any to Hit F/S/E", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CLOCKTICKS", + "Deprecated": "1", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_FAST_ASSERTED.HORZ", + "Deprecated": "1", + "EventCode": "0xA5", + "EventName": "UNC_C_FAST_ASSERTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.ANY", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.LOCAL", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.REMOTE", + "PerPkg": "1", + "UMask": "0x91", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.REMOTE_SNOOP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITE", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.F_STATE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.LOCAL", + "PerPkg": "1", + "UMask": "0x2f", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.REMOTE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SRC_THRTL", + "Deprecated": "1", + "EventCode": "0xA4", + "EventName": "UNC_C_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.EVICT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.EVICT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.HIT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IPQ", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ_HIT", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ_MISS", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.PRQ", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ_HIT", + "PerPkg": "1", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ_MISS", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.RRQ_HIT", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.RRQ_MISS", + "PerPkg": "1", + "UMask": "0x60", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.WBQ_HIT", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.WBQ_MISS", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.EVICT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IPQ", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_HIT", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_MISS", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.PRQ", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_HIT", + "PerPkg": "1", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_MISS", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CMS_CLOCKTICKS", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_H_CLOCK", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_STATE", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C1_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_TRANSITION", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C1_TRANSITION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_STATE", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C6_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_TRANSITION", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C6_TRANSITION", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.GV", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.GV", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_REMOTE", + "PerPkg": "1", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_REMOTE", + "PerPkg": "1", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_REMOTE", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_REMOTE", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_COUNTER0_OCCUPANCY", + "Deprecated": "1", + "EventCode": "0x1F", + "EventName": "UNC_H_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.NO_SNP", + "Deprecated": "1", + "EventCode": "0x53", + "EventName": "UNC_H_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.SNP", + "Deprecated": "1", + "EventCode": "0x53", + "EventName": "UNC_H_DIR_LOOKUP.SNP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.HA", + "Deprecated": "1", + "EventCode": "0x54", + "EventName": "UNC_H_DIR_UPDATE.HA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.TOR", + "Deprecated": "1", + "EventCode": "0x54", + "EventName": "UNC_H_DIR_UPDATE.TOR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "Deprecated": "1", + "EventCode": "0xAE", + "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "Deprecated": "1", + "EventCode": "0xAE", + "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.EX_RDS", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.EX_RDS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOE", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.READ", + "Deprecated": "1", + "EventCode": "0x5E", + "EventName": "UNC_H_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.WRITE", + "Deprecated": "1", + "EventCode": "0x5E", + "EventName": "UNC_H_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.READ_OR_INV", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RDINVOWN", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.SHARED", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "Deprecated": "1", + "EventCode": "0xAD", + "EventName": "UNC_H_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "Deprecated": "1", + "EventCode": "0xAD", + "EventName": "UNC_H_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.NORMAL", + "Deprecated": "1", + "EventCode": "0x59", + "EventName": "UNC_H_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.PRIORITY", + "Deprecated": "1", + "EventCode": "0x59", + "EventName": "UNC_H_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_MIG", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_MIG", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.INVITOM", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.INVITOM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.IODCFULL", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.IODCFULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.OSBGATED", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.OSBGATED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.ALL", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.SNPOUT", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.SNPOUT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOE", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBMTOE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOI", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBMTOI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBPUSHMTOI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_MISS", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_VIC", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RFO_HIT_S", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.RFO_HIT_S", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RSPI_WAS_FSE", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.WC_ALIASING", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.WC_ALIASING", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_OSB", + "Deprecated": "1", + "EventCode": "0x55", + "EventName": "UNC_H_OSB", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC0_SMI0", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC1_SMI1", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_LOCAL", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_REMOTE", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from local home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from remote home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from local home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from remote home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AD", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AK", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.BL", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.IV", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AD", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AK", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.BL", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.IV", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AD", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AK", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.BL", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.IV", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IPQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IPQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ_REJ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.PRQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ_REJ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.RRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.RRQ", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.WBQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.WBQ", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.ANY_IPQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.ANY_REJECT_IRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x25", + "EventName": "UNC_H_RxC_ISMQ1_REJECT.ANY_ISMQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x25", + "EventName": "UNC_H_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2D", + "EventName": "UNC_H_RxC_ISMQ1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2D", + "EventName": "UNC_H_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IPQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IRQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.RRQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.WBQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.ANY_PRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.ANY_RRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.ANY_WBQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IFV", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.E_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.M_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.S_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.ALL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.BCST_LOC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.BCST_REM", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.DIRECT_LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.DIRECT_REM", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPI", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPI", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPIFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPS", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPSFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_WBWB", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSP_WB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPFWD", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPI", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPIFWD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPSFWD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_FWD_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_WB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AK_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.IV_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.IV_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.IV", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.IV", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.IV", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.IV", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.IV", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.IV", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.IV", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.DN", + "Deprecated": "1", + "EventCode": "0xAC", + "EventName": "UNC_H_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.UP", + "Deprecated": "1", + "EventCode": "0xAC", + "EventName": "UNC_H_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.LLC", + "Deprecated": "1", + "EventCode": "0x56", + "EventName": "UNC_H_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.MEM", + "Deprecated": "1", + "EventCode": "0x56", + "EventName": "UNC_H_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0xf0", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0xe8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x48", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json new file mode 100644 index 000000000000..725780fb3990 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json @@ -0,0 +1,11334 @@ +[ + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Snoops", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests.", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "IRP Clocks", + "EventCode": "0x1", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CLFlush", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CRd", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; DRd", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.DRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIDCAHin5t", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIRdCur", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", + "PerPkg": "1", + "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.RFO", + "PerPkg": "1", + "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; WbMtoI", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Occupancy of the IRP FAF queue.", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x1E", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x1E", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Requests", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.UNKNOWN", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Lost Forward", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Invalid", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Valid", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Requests", + "EventCode": "0x14", + "EventName": "UNC_I_P2P_INSERTS", + "PerPkg": "1", + "PublicDescription": "P2P requests from the ITC", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Occupancy", + "EventCode": "0x15", + "EventName": "UNC_I_P2P_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "P2P B & S Queue Occupancy", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P completions", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if local only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if local and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P Message", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P reads", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; Match if remote only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if remote and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P Writes", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Atomic", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Other", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.RD_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0xB", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x5", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x2", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x8", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x6", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x3", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x9", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x7", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x4", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x1A", + "EventName": "UNC_I_TxR2_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1B", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xD", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xC", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Not Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles - at UCLK", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "EventCode": "0x23", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel(R) UPI", + "EventCode": "0x26", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to I (Invalid)", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to S (Shared)", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to A (SnoopAll)", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to S (Shared)", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to A (SnoopAll)", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to I (Invalid)", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_M2M_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_M2M_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC; All, regardless of priority.", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.FROM_TRANSGRESS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC; Critical Priority", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Read requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Reads Issued to iMC; All, regardless of priority.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Writes to iMC issued", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TRANSGRESS", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; Full Line Non-ISOCH", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; ISOCH Full Line", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-Isochronous writes to the iMC", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; ISOCH Partial", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches; MC Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches; Mesh Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MESH", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x4F", + "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x4F", + "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x4F", + "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x51", + "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x51", + "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x51", + "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full", + "EventCode": "0x53", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch requests that got turn into a demand request", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefetch queue is made of CAM (Content Addressable Memory)", + "Unit": "M2M" + }, + { + "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", + "EventCode": "0x57", + "EventName": "UNC_M2M_PREFCAM_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_M2M_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 0", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 2", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Full", + "EventCode": "0x4", + "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Not Empty", + "EventCode": "0x3", + "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Queue Inserts", + "EventCode": "0x1", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x2", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Full", + "EventCode": "0x8", + "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Not Empty", + "EventCode": "0x7", + "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "EventCode": "0x5", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x6", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Clean line read hits(Regular and RFO) to Near Memory(DRAM cache) in Memory Mode and regular reads to DRAM in 1LM", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit; Read Hit from NearMem, Clean Line", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Dirty line read hits(Regular and RFO) to Near Memory(DRAM cache) in Memory Mode", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit; Read Hit from NearMem, Dirty Line", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Clean line underfill read hits to Near Memory(DRAM cache) in Memory Mode", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit; Underfill Rd Hit from NearMem, Clean Line", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Dirty line underfill read hits to Near Memory(DRAM cache) in Memory Mode", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit; Underfill Rd Hit from NearMem, Dirty Line", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x41", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x42", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 0", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 1", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 2", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 0", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 1", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 2", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 0", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 1", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 2", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 2", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Pending Occupancy", + "EventCode": "0x48", + "EventName": "UNC_M2M_TRACKER_PENDING_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credit Acquired", + "EventCode": "0xD", + "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credits Occupancy", + "EventCode": "0xE", + "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Full", + "EventCode": "0xC", + "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Not Empty", + "EventCode": "0xB", + "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "EventCode": "0x9", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", + "EventCode": "0xF", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", + "EventCode": "0x10", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0xA", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK; CRD Transactions to Cbo", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.CRD_CBO", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK; NDR Transactions", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.NDR", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x1E", + "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x1E", + "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; All", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Near Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Far Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; All", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Read Credit Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Write Compare Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Write Credit Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; All", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Near Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Far Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Prefetch Read Cam Hit", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Read Credit Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Write Compare Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Write Credit Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; All", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Read Credit Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Write Compare Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Write Credit Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Sideband", + "EventCode": "0x6B", + "EventName": "UNC_M2M_TxC_AK_SIDEBAND.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Sideband", + "EventCode": "0x6B", + "EventName": "UNC_M2M_TxC_AK_SIDEBAND.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Cache", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Core", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to QPI", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x1A", + "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x1A", + "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; All", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Near Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Far Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; All", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; All", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Near Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Far Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; All", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 0", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 1", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 2", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 0", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 1", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 2", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 0", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 1", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 2", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 0", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 1", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 2", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 0", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 1", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 2", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Requests", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Snoops", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; VNA Messages", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Writebacks", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "EventCode": "0x2B", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "PublicDescription": "Count cases BL sends direct to core", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "EventCode": "0x2A", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "PublicDescription": "Cases where SMI3 sends D2U command", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO0_IIO1_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO2", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO3", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO4", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; All IIO targets for NCS are in single mask. ORs them together", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; Selected M2p BL NCS credits", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 1", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AK - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AK - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; BL - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; REQ on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; RSP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; SNP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; NCB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; NCS on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; RSP on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; WB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; REQ on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; RSP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; SNP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; NCB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; NCS on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; RSP on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; WB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; AD, BL Parallel Win", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN0", + "PerPkg": "1", + "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn0, delaying vn1 win, because vn0 offered parallel ad/bl", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN1", + "PerPkg": "1", + "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn1, delaying vn0 win, because vn1 offered parallel ad/bl", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; REQ on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; RSP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; SNP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; NCB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; NCS on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; RSP on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; WB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; REQ on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; RSP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; SNP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; NCB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; NCS on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; RSP on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; WB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; REQ on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; RSP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; SNP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; NCB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; NCS on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; RSP on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; WB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; REQ on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; RSP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; SNP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; NCB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; NCS on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; RSP on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; WB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on BL Arb", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on Idle", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 1", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 2", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; REQ on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; RSP on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; SNP on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; NCB on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; NCS on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; RSP on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; WB on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; REQ on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; RSP on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; SNP on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; NCB on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; NCS on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; RSP on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; WB on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; Any In BGF FIFO", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", + "PerPkg": "1", + "PublicDescription": "Indication that at least one packet (flit) is in the bgf (fifo only)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; Any in BGF Path", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", + "PerPkg": "1", + "PublicDescription": "Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; No D2K For Arb", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "VN0 or VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; D2K Credits", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", + "PerPkg": "1", + "PublicDescription": "D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Packets in BGF FIFO", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", + "PerPkg": "1", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Packets in BGF Path", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", + "PerPkg": "1", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", + "PerPkg": "1", + "PublicDescription": "count of bl messages in pump-1-pending state, in completion fifo only", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", + "PerPkg": "1", + "PublicDescription": "count of bl messages in pump-1-pending state, in marker table and in fifo", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Transmit Credits", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", + "PerPkg": "1", + "PublicDescription": "Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; VNA In Use", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", + "PerPkg": "1", + "PublicDescription": "Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; All", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; No BGF Credits", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_BGF", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; No TxQ Credits", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_TXQ", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 0", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "generating bl data flit sequence; waiting for data pump 0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is tracking at least one message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", + "PerPkg": "1", + "PublicDescription": "pump-1-pending completion fifo is full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", + "PerPkg": "1", + "PublicDescription": "a bl message finished but is in limbo and moved to pump-1-pending logic", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 1", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "generating bl data flit sequence; waiting for data pump 1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; One Message", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG", + "PerPkg": "1", + "PublicDescription": "One message in flit; VNA or non-VNA flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; One Message in non-VNA", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG_VNX", + "PerPkg": "1", + "PublicDescription": "One message in flit; non-VNA flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; Two Messages", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.2_MSGS", + "PerPkg": "1", + "PublicDescription": "Two messages in flit; VNA flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; Three Messages", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.3_MSGS", + "PerPkg": "1", + "PublicDescription": "Three messages in flit; VNA flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_2", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_3", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; All", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Needs Data Flit", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", + "PerPkg": "1", + "PublicDescription": "BL message requires data flit sequence", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 0", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Waiting for header pump 0", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Bubble", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit but flit transmission delayed", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Not Avail", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit and not available", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 1", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Waiting for header pump 1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate Ready", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate Wasted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Blocked", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Message", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting is in run-ahead to start new flit, and message is actually slotted into new flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Ok", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; New header flit construction may proceed in parallel with data flit sequence", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Flit Finished", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_FLIT", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit finished assembly in parallel with data flit sequence", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Message", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_MSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Message is slotted into header flit in parallel with data flit sequence", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate-matching stall injected", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall - No Message", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate matching stall injected, but no additional message slotted during stall cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; All", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No BGF Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_CRD", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No BGF Credits + No Extra Message Slotted", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_NO_MSG", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available; no additional message slotted into flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No TxQ Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_CRD", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No TxQ Credits + No Extra Message Slotted", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_NO_MSG", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available; no additional message slotted into flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - One Slot Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ONE_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only one slot taken (two slots free)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - Three Slots Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.THREE_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with three slots taken (no slots free)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - Two Slots Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.TWO_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only two slots taken (one slots free)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Can't Slot AD", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", + "PerPkg": "1", + "PublicDescription": "some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Can't Slot BL", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", + "PerPkg": "1", + "PublicDescription": "some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel AD Lost", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_AD_LOST", + "PerPkg": "1", + "PublicDescription": "some AD message lost contest for slot 0 (logical OR of all AD events under INGR_SLOT_LOST_MC_VN{0,1})", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel Attempt", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", + "PerPkg": "1", + "PublicDescription": "ad and bl messages attempted to slot into the same flit in parallel", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel BL Lost", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_BL_LOST", + "PerPkg": "1", + "PublicDescription": "some BL message lost contest for slot 0 (logical OR of all BL events under INGR_SLOT_LOST_MC_VN{0,1})", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel Success", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", + "PerPkg": "1", + "PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; VN0", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.VN0", + "PerPkg": "1", + "PublicDescription": "vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; VN1", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.VN1", + "PerPkg": "1", + "PublicDescription": "vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; REQ on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; SNP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCS on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; WB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; REQ on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; SNP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCS on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; WB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; REQ on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; SNP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCS on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; WB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; REQ on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; SNP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCS on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; WB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; REQ on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; RSP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; SNP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; NCB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; NCS on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; RSP on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; WB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; REQ on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; RSP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; SNP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; NCB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; NCS on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; RSP on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; WB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Lost Arbitration", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARB_LOST", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Arrived", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARRIVED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Dropped - Old", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_OLD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Dropped - Wrap", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_WRAP", + "PerPkg": "1", + "PublicDescription": "Dropped because it was overwritten by new message while prefetch queue was full", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Slotted", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.SLOTTED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Any In Use", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", + "PerPkg": "1", + "PublicDescription": "At least one remote vna credit is in use", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Corrected", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", + "PerPkg": "1", + "PublicDescription": "Number of remote vna credits corrected (local return) per cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 1", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 1 (i.e. no vna credits available)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 4", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 5", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Used", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.USED", + "PerPkg": "1", + "PublicDescription": "Number of remote vna credits consumed per cycle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 WB Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 WB Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; CHA on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_CHA", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to CHA", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_NON_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn0 Snpf", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI0", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI1", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; CHA on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_CHA", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to CHA", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_NON_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn1 Snpf", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI0", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI1", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_NONSNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_VN2SNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn0 SnpF issued when SnpF pending on Vn1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_NONSNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_VN0SNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn1 SnpF issued when SnpF pending on Vn0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 REQ Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 SNP Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 WB Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 REQ Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 SNP Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 WB Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 REQ Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 SNP Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 WB Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 REQ Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 SNP Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 WB Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 REQ Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 RSP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 SNP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 WB Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 REQ Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 RSP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 SNP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 WB Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Inserts", + "EventCode": "0x2F", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Occupancy", + "EventCode": "0x1E", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1_NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1_NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1_NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1_NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 NCS Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 NCB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 RSP Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCS Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 RSP Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 WB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCS Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 RSP Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 WB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VNA", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VNA", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; WB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; REQ on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; RSP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; RSP on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; WB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; NCB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; REQ on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; RSP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; SNP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; RSP on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; WB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; REQ on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; RSP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; RSP on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; WB on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; NCB on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; REQ on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; RSP on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; SNP on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; RSP on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_TxC_BL.DRS_UPI", + "Deprecated": "1", + "EventCode": "0x40", + "EventName": "UNC_NoUnit_TxC_BL.DRS_UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", + "EventCode": "0x1", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "Unit": "UPI" + }, + { + "BriefDescription": "Data Response packets that go direct to core", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_DIRECT_ATTEMPTS.D2U", + "Deprecated": "1", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "EventCode": "0x16", + "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", + "EventCode": "0x20", + "EventName": "UNC_UPI_PHY_INIT_CYCLES", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req Nack", + "EventCode": "0x23", + "EventName": "UNC_UPI_POWER_L1_NACK", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req (same as L1 Ack).", + "EventCode": "0x22", + "EventName": "UNC_UPI_POWER_L1_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0. Receive side.", + "EventCode": "0x24", + "EventName": "UNC_UPI_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Request", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "REQ Message Class", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Request Opcode", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Conflict", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Invalid", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Snoop", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "SNP Message Class", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Snoop Opcode", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "VN0 Credit Consumed", + "EventCode": "0x39", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN1 Credit Consumed", + "EventCode": "0x3A", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x38", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid data FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Data", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Idle", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; LLCRD Not Empty", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; LLCTRL", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Protocol header and credit FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.ALL_NULL", + "Deprecated": "1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Protocol Header", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.PROTHDR", + "Deprecated": "1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.PROT_HDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 0", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 2", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.RSP", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.SNP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.WB", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.WB", + "PerPkg": "1", + "UMask": "0xb", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 0", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 1", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 2", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 0", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 1", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 2", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0. Transmit side.", + "EventCode": "0x26", + "EventName": "UNC_UPI_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Request", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "REQ Message Class", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Request Opcode", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Conflict", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Invalid", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "SNP Message Class", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop Opcode", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs that bypassed the TxL Buffer", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid data FLITs transmitted via any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs transmitted from any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Data", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Idle FLITs transmitted", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; LLCRD Not Empty", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; LLCTRL", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.ALL_NULL", + "Deprecated": "1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Protocol Header", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.PROTHDR", + "Deprecated": "1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.PROT_HDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 0", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 2", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.DATA_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.DUAL_SLOT_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.LOC", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NON_DATA_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.REM", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.SGL_SLOT_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.SNP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.WB", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.WB", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "EventCode": "0x45", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x44", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0xf", + "Unit": "UPI" + } +] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-io.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-io.json new file mode 100644 index 000000000000..743c91f3d2f0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-io.json @@ -0,0 +1,4250 @@ +[ + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "ScaleUnit": "4Bytes", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "ScaleUnit": "4Bytes", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Clockticks of the IIO Traffic Controller", + "EventCode": "0x1", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the 1GHz traffic controller clock in the IIO unit.", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x0f", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x01", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x02", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x04", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x08", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 0", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x01", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 1", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x02", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 2", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x04", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x08", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 1", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 2", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 3", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num Link Correctable Errors", + "EventCode": "0xF", + "EventName": "UNC_IIO_LINK_NUM_CORR_ERR", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num Link Retries", + "EventCode": "0xE", + "EventName": "UNC_IIO_LINK_NUM_RETRIES", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number packets that passed the Mask/Match Filter", + "EventCode": "0x21", + "EventName": "UNC_IIO_MASK_MATCH", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Counting disabled", + "EventName": "UNC_IIO_NOTHING", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Symbol Times on Link", + "EventCode": "0x82", + "EventName": "UNC_IIO_SYMBOL_TIMES", + "PerPkg": "1", + "PublicDescription": "Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; context cache miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.CTXT_MISS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L1 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L1_MISS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L2 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L2_MISS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L3 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L3_MISS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; Vtd hit", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L4_PAGE_HIT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB1_MISS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB is full", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB_MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Occupancy", + "EventCode": "0x40", + "EventName": "UNC_IIO_VTD_OCCUPANCY", + "PerPkg": "1", + "Unit": "IIO" + } +] diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json index aafd2c9b813b..f761856d738e 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-memory.json @@ -2735,7 +2735,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts?", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json deleted file mode 100644 index 5f3ed5e843b9..000000000000 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-other.json +++ /dev/null @@ -1,26344 +0,0 @@ -[ - { - "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.MMIO_READ", - "Filter": "config1=0x40040e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.MMIO_WRITE", - "Filter": "config1=0x40041e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_READ", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "MetricName": "LLC_MISSES.PCIE_READ", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "ScaleUnit": "4Bytes", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_WRITE", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "MetricName": "LLC_MISSES.PCIE_WRITE", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "ScaleUnit": "4Bytes", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.UNCACHEABLE", - "Filter": "config1=0x40e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_REFERENCES.STREAMING_FULL", - "Filter": "config1=0x41833", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "ScaleUnit": "64Bytes", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", - "Filter": "config1=0x41a33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "ScaleUnit": "64Bytes", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Intermediate bypass Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the intermediate bypass.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Not Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the full bypass.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Uncore cache clock ticks", - "EventName": "UNC_CHA_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the clock controlling the uncore caching and home agent (CHA).", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_CHA_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C1 State", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C1_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C1 Transition", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C1_TRANSITION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C6 State", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C6_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C6 Transition", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C6_TRANSITION", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; GV", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.GV", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Cycle with Multiple Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Single Snoop", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Snoop to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Core Request to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Eviction to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; External Snoop to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "Counter 0 Occupancy", - "EventCode": "0x1F", - "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.HA", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.TOR", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_CHA_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.EX_RDS", - "PerPkg": "1", - "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; Shared hit and op is RdInvOwn, RdInv, Inv*", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoE", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.READ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; No SF/LLC HitS/F and op is RdInvOwn", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; SF/LLC HitS/F and op is RdInvOwn", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a local request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "PerPkg": "1", - "PublicDescription": "Received RspFwdI* for a local request, but converted HitME$ to SF entry", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache on RdInvOwn even if not RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a remote request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", - "PerPkg": "1", - "PublicDescription": "Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache to SHARed", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.SHARED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "HA to iMC Reads Issued; ISOCH", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "PublicDescription": "Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Full Line MIG", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Full Line", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Partial Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Partial MIG", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Partial", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.INVITOM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations dropped due to IODC Full", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.IODCFULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IDOC allocation dropped due to OSB gate", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.OSBGATED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to any reason", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to conflicting transaction", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.SNPOUT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoE", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoI", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbPushMtoI", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", - "PerPkg": "1", - "PublicDescription": "Moved to Cbo section", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Read transactions", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Local", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Remote", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", - "UMask": "0x91", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; External Snoop Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", - "UMask": "0x9", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Write Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", - "UMask": "0x5", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.F_STATE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in E state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in M state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; CV0 Prefetch Miss", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; CV0 Prefetch Victim", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Number of times that an RFO hit in S state.", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RFO_HIT_S", - "PerPkg": "1", - "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; Silent Snoop Eviction", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; Write Combining Aliasing", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.WC_ALIASING", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB", - "PerPkg": "1", - "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "Unit": "CHA" - }, - { - "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in IODC", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.IODC", - "PerPkg": "1", - "PublicDescription": "2LM related events; Counts the number of times CHA saw NM Set conflict in IODC", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in SF/LLC", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", - "PerPkg": "1", - "PublicDescription": "NM evictions due to another read to the same near memory set in the LLC.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in SF/LLC", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", - "PerPkg": "1", - "PublicDescription": "NM evictions due to another read to the same near memory set in the SF.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw NM Set conflict in TOR", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", - "PerPkg": "1", - "PublicDescription": "No Reject in the CHA due to a pending read to the same near memory set in the TOR.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Memory mode related events; Counts the number of times CHA saw NM Set conflict in TOR and the transaction was rejected", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR_REJECT", - "PerPkg": "1", - "PublicDescription": "Rejects in the CHA due to a pending read to the same near memory set in the TOR.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC0_SMI2", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC1_SMI3", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC2_SMI4", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC3_SMI5", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC0_SMI0", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC1_SMI1", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS", - "PerPkg": "1", - "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a remote socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Write requests", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "Write Requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Read and Write Requests; Writes Remote", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_CHA_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IPQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IRQ Rejected", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; RRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.RRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; WBQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.WBQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; AD REQ on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; AD RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Non UPI AK Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL NCB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL NCS on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL WB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Non UPI IV Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Allow Snoop", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; ANY0", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; HA", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; LLC Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; PhyAddr Match", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; SF Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; AD REQ on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; AD RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; Non UPI AK Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL NCB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL NCS on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL WB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; Non UPI IV Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; AD REQ on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; AD RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; Non UPI AK Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL NCB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL NCS on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL WB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; Non UPI IV Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; ANY0", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; HA", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; ANY0", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; HA", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; IPQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; RRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; WBQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; AD REQ on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; AD RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Non UPI AK Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL NCB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL NCS on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL WB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Non UPI IV Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Allow Snoop", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; ANY0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; HA", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; LLC Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; PhyAddr Match", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; SF Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC OR SF Way", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; AD REQ on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; AD RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Non UPI AK Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL NCB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL NCS on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL WB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Non UPI IV Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Allow Snoop", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; ANY0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; HA", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; LLC Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; PhyAddr Match", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; SF Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; AD REQ on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; AD RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Non UPI AK Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL NCB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL NCS on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL WB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Non UPI IV Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Allow Snoop", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; ANY0", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; HA", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; LLC Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; PhyAddr Match", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; SF Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; AD REQ on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; AD RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Non UPI AK Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL NCB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL NCS on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL WB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Non UPI IV Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Allow Snoop", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; ANY0", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; HA", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; LLC Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; PhyAddr Match", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; SF Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for E-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.E_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for M-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.M_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for S-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.S_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; All", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast snoop for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Directed snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Directed snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RspCnflct* Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received; RspFwd", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RspI Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPI", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RspIFwd Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspS", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : RspS : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RspSFwd Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Rsp*WB Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to its home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspCnflct", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspI", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspIFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspS", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspSFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; Rsp*FWD*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; Rsp*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0xff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x15", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local iA and IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_IO_IA", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests", - "UMask": "0x35", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Misses from Local", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x25", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; SF/LLC Evictions", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.EVICT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hit (Not a Miss)", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from iA Cores", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally generated IO traffic", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; ItoM misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", - "Filter": "config1=0x49033", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RdCur misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", - "Filter": "config1=0x43C33", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; IPQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; IRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Miss", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; PRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ_HIT", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ_MISS", - "PerPkg": "1", - "UMask": "0x60", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ_HIT", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ_MISS", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All remotely generated requests", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x17", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x27", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; SF/LLC Evictions", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hit (Not a Miss)", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally initiated requests from iA Cores", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally generated IO traffic", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ITOM Misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", - "Filter": "config1=0x49033", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RDCUR misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", - "Filter": "config1=0x43C33", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; IPQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; IRQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Miss", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; PRQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; AD REQ Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; AD RSP VN0 Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL NCB Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL NCS Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL RSP Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL DRS Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; VN0 Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VN0", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; VNA Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VNA", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD REQ VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD RSP VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCB VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCS VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL RSP VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL DRS VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD VNA Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_AD", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL VNA Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_BL", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI; Pushed to LLC", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was able to push WbPushMToI to LLC", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI; Pushed to Memory", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC0_SMI2", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC1_SMI3", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC2_SMI4", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC3_SMI5", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC0_SMI0", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC1_SMI1", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd F/E", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd M", - "UMask": "0xf0", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd F/E", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd M", - "UMask": "0xe8", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response any to Hit F/S/E", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd F/E", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd M", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd F/E", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd M", - "UMask": "0x48", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response any to Hit F/S/E", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd F/E", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd M", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd F/E", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd M", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response any to Hit F/S/E", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd F/E", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd M", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd F/E", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd M", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response any to Hit F/S/E", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CLOCKTICKS", - "Deprecated": "1", - "EventName": "UNC_C_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_FAST_ASSERTED.HORZ", - "Deprecated": "1", - "EventCode": "0xA5", - "EventName": "UNC_C_FAST_ASSERTED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.ANY", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.ANY", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.LOCAL", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.REMOTE", - "PerPkg": "1", - "UMask": "0x91", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.REMOTE_SNOOP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITE", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x5", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.F_STATE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.LOCAL", - "PerPkg": "1", - "UMask": "0x2f", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.REMOTE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SRC_THRTL", - "Deprecated": "1", - "EventCode": "0xA4", - "EventName": "UNC_C_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.EVICT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.EVICT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.HIT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IPQ", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ_HIT", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ_MISS", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_IA", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_IO", - "PerPkg": "1", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.PRQ", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ_HIT", - "PerPkg": "1", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ_MISS", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.REM_ALL", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.RRQ_HIT", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.RRQ_MISS", - "PerPkg": "1", - "UMask": "0x60", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.WBQ_HIT", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.WBQ_MISS", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.EVICT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IPQ", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_HIT", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_MISS", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IA", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IO", - "PerPkg": "1", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.PRQ", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_HIT", - "PerPkg": "1", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_MISS", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CMS_CLOCKTICKS", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_H_CLOCK", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_STATE", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C1_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_TRANSITION", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C1_TRANSITION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_STATE", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C6_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_TRANSITION", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C6_TRANSITION", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.GV", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.GV", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_REMOTE", - "PerPkg": "1", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_REMOTE", - "PerPkg": "1", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_REMOTE", - "PerPkg": "1", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_REMOTE", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_COUNTER0_OCCUPANCY", - "Deprecated": "1", - "EventCode": "0x1F", - "EventName": "UNC_H_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.NO_SNP", - "Deprecated": "1", - "EventCode": "0x53", - "EventName": "UNC_H_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.SNP", - "Deprecated": "1", - "EventCode": "0x53", - "EventName": "UNC_H_DIR_LOOKUP.SNP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.HA", - "Deprecated": "1", - "EventCode": "0x54", - "EventName": "UNC_H_DIR_UPDATE.HA", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.TOR", - "Deprecated": "1", - "EventCode": "0x54", - "EventName": "UNC_H_DIR_UPDATE.TOR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "Deprecated": "1", - "EventCode": "0xAE", - "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "Deprecated": "1", - "EventCode": "0xAE", - "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.EX_RDS", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.EX_RDS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.SHARED_OWNREQ", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.SHARED_OWNREQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOE", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.WBMTOE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOI_OR_S", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.WBMTOI_OR_S", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.READ", - "Deprecated": "1", - "EventCode": "0x5E", - "EventName": "UNC_H_HITME_LOOKUP.READ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.WRITE", - "Deprecated": "1", - "EventCode": "0x5E", - "EventName": "UNC_H_HITME_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.NOTSHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.READ_OR_INV", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.READ_OR_INV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.SHARED_RDINVOWN", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.SHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RDINVOWN", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.RDINVOWN", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RSPFWDI_REM", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.RSPFWDI_REM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.SHARED", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.SHARED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "Deprecated": "1", - "EventCode": "0xAD", - "EventName": "UNC_H_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "Deprecated": "1", - "EventCode": "0xAD", - "EventName": "UNC_H_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.NORMAL", - "Deprecated": "1", - "EventCode": "0x59", - "EventName": "UNC_H_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.PRIORITY", - "Deprecated": "1", - "EventCode": "0x59", - "EventName": "UNC_H_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_MIG", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_MIG", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.INVITOM", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.INVITOM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.IODCFULL", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.IODCFULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.OSBGATED", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.OSBGATED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.ALL", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.SNPOUT", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.SNPOUT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOE", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBMTOE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOI", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBMTOI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBPUSHMTOI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_MISS", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_VIC", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RFO_HIT_S", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.RFO_HIT_S", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RSPI_WAS_FSE", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.WC_ALIASING", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.WC_ALIASING", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_OSB", - "Deprecated": "1", - "EventCode": "0x55", - "EventName": "UNC_H_OSB", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC0_SMI0", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC1_SMI1", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_LOCAL", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_REMOTE", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.INVITOE_REMOTE", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from local home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from remote home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from local home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from remote home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AD", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AK", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.BL", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.IV", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AD", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AK", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.BL", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.IV", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AD", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AK", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.BL", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.IV", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IPQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IPQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ_REJ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.PRQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ_REJ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.RRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.RRQ", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.WBQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.WBQ", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.ANY_IPQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.ANY_REJECT_IRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x25", - "EventName": "UNC_H_RxC_ISMQ1_REJECT.ANY_ISMQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x25", - "EventName": "UNC_H_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2D", - "EventName": "UNC_H_RxC_ISMQ1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2D", - "EventName": "UNC_H_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IPQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.IPQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IRQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.RRQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.RRQ", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.WBQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.WBQ", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.ANY_PRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.ANY_RRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.ANY_WBQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IFV", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.E_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.M_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.S_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.ALL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.BCST_LOC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.BCST_REM", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.DIRECT_LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.DIRECT_REM", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.REMOTE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPCNFLCTS", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPFWD", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPI", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPI", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPIFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPS", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPSFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_FWD_WB", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_WBWB", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSP_WB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPFWD", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPI", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPIFWD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPSFWD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_FWD_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_WB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AK_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.IV_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.IV_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.IV", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.IV", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.IV", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.IV", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.IV", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.IV", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.IV", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.DN", - "Deprecated": "1", - "EventCode": "0xAC", - "EventName": "UNC_H_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.UP", - "Deprecated": "1", - "EventCode": "0xAC", - "EventName": "UNC_H_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.LLC", - "Deprecated": "1", - "EventCode": "0x56", - "EventName": "UNC_H_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.MEM", - "Deprecated": "1", - "EventCode": "0x56", - "EventName": "UNC_H_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0xf0", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0xe8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x48", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Clockticks of the IIO Traffic Controller", - "EventCode": "0x1", - "EventName": "UNC_IIO_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the 1GHz traffic controller clock in the IIO unit.", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x0f", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x01", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x02", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x04", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x08", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 0", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x01", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 1", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x02", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 2", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x04", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x08", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0xf", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 1", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 2", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 3", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Num Link Correctable Errors", - "EventCode": "0xF", - "EventName": "UNC_IIO_LINK_NUM_CORR_ERR", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num Link Retries", - "EventCode": "0xE", - "EventName": "UNC_IIO_LINK_NUM_RETRIES", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number packets that passed the Mask/Match Filter", - "EventCode": "0x21", - "EventName": "UNC_IIO_MASK_MATCH", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Counting disabled", - "EventName": "UNC_IIO_NOTHING", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Symbol Times on Link", - "EventCode": "0x82", - "EventName": "UNC_IIO_SYMBOL_TIMES", - "PerPkg": "1", - "PublicDescription": "Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; context cache miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.CTXT_MISS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L1 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L1_MISS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L2 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L2_MISS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L3 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L3_MISS", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; Vtd hit", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L4_PAGE_HIT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB1_MISS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB is full", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB_MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Occupancy", - "EventCode": "0x40", - "EventName": "UNC_IIO_VTD_OCCUPANCY", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Snoops", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total IRP occupancy of inbound read and write requests.", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", - "PerPkg": "1", - "PublicDescription": "Total IRP occupancy of inbound read and write requests. This is effectively the sum of read occupancy and write occupancy.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "IRP Clocks", - "EventCode": "0x1", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CLFlush", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CRd", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; DRd", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.DRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIDCAHin5t", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIRdCur", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; WbMtoI", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF RF full", - "EventCode": "0x17", - "EventName": "UNC_I_FAF_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", - "EventCode": "0x18", - "EventName": "UNC_I_FAF_INSERTS", - "PerPkg": "1", - "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Occupancy of the IRP FAF queue.", - "EventCode": "0x19", - "EventName": "UNC_I_FAF_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF allocation -- sent to ADQ", - "EventCode": "0x16", - "EventName": "UNC_I_FAF_TRANSACTIONS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "All Inserts Inbound (p2p + faf + cset)", - "EventCode": "0x1E", - "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x1E", - "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Requests", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.UNKNOWN", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Lost Forward", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Invalid", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Valid", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Requests", - "EventCode": "0x14", - "EventName": "UNC_I_P2P_INSERTS", - "PerPkg": "1", - "PublicDescription": "P2P requests from the ITC", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Occupancy", - "EventCode": "0x15", - "EventName": "UNC_I_P2P_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "P2P B & S Queue Occupancy", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P completions", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if local only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if local and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P Message", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P reads", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; Match if remote only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if remote and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P Writes", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", - "UMask": "0x7e", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", - "UMask": "0x74", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", - "UMask": "0x72", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", - "UMask": "0x78", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that miss the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", - "UMask": "0x71", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit E or S", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit I", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit M", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Miss", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpCode", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpData", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpInv", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Atomic", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Other", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.RD_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound write (fast path) requests received by the IRP.", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Egress Allocations", - "EventCode": "0xB", - "EventName": "UNC_I_TxC_AK_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Cycles Full", - "EventCode": "0x5", - "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Inserts", - "EventCode": "0x2", - "EventName": "UNC_I_TxC_BL_DRS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Occupancy", - "EventCode": "0x8", - "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Cycles Full", - "EventCode": "0x6", - "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Inserts", - "EventCode": "0x3", - "EventName": "UNC_I_TxC_BL_NCB_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Occupancy", - "EventCode": "0x9", - "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Cycles Full", - "EventCode": "0x7", - "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Inserts", - "EventCode": "0x4", - "EventName": "UNC_I_TxC_BL_NCS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x1A", - "EventName": "UNC_I_TxR2_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x1B", - "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xD", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xC", - "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_Egress.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Not Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles - at UCLK", - "EventName": "UNC_M2M_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_M2M_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", - "EventCode": "0x24", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to core (bypassing the CHA)", - "EventCode": "0x23", - "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to core transaction were overridden", - "EventCode": "0x25", - "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", - "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", - "EventCode": "0x28", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", - "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", - "EventCode": "0x27", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to the Intel(R) UPI", - "EventCode": "0x26", - "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", - "EventCode": "0x29", - "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", - "PerPkg": "1", - "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to I", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to I (Invalid)", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to S", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to S (Shared)", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to A", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to A (SnoopAll)", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to S", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to S (Shared)", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to A", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to A (SnoopAll)", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to I", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to I (Invalid)", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_M2M_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_M2M_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Reads to iMC issued", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ALL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC; All, regardless of priority.", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.FROM_TRANSGRESS", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC; Critical Priority", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ISOCH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Read requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Reads Issued to iMC; All, regardless of priority.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Writes to iMC issued", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.ALL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FROM_TRANSGRESS", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; Full Line Non-ISOCH", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; ISOCH Full Line", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.NI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Partial Non-Isochronous writes to the iMC", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; ISOCH Partial", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write requests to Intel(R) Optane(TM) DC persistent memory issued to the iMC from M2M", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Writes Issued to iMC; All, regardless of priority.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches; MC Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches; Mesh Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MESH", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x4F", - "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x4F", - "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x4F", - "EventName": "UNC_M2M_PMM_RPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x51", - "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x51", - "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x51", - "EventName": "UNC_M2M_PMM_WPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full", - "EventCode": "0x53", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty", - "EventCode": "0x54", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch requests that got turn into a demand request", - "EventCode": "0x56", - "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefetch queue is made of CAM (Content Addressable Memory)", - "Unit": "M2M" - }, - { - "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", - "EventCode": "0x57", - "EventName": "UNC_M2M_PREFCAM_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_M2M_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 0", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 2", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Full", - "EventCode": "0x4", - "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Not Empty", - "EventCode": "0x3", - "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Queue Inserts", - "EventCode": "0x1", - "EventName": "UNC_M2M_RxC_AD_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy", - "EventCode": "0x2", - "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Full", - "EventCode": "0x8", - "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Not Empty", - "EventCode": "0x7", - "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Allocations", - "EventCode": "0x5", - "EventName": "UNC_M2M_RxC_BL_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Occupancy", - "EventCode": "0x6", - "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Clean line read hits(Regular and RFO) to Near Memory(DRAM cache) in Memory Mode and regular reads to DRAM in 1LM", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", - "PerPkg": "1", - "PublicDescription": "Tag Hit; Read Hit from NearMem, Clean Line", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Dirty line read hits(Regular and RFO) to Near Memory(DRAM cache) in Memory Mode", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", - "PerPkg": "1", - "PublicDescription": "Tag Hit; Read Hit from NearMem, Dirty Line", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Clean line underfill read hits to Near Memory(DRAM cache) in Memory Mode", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", - "PerPkg": "1", - "PublicDescription": "Tag Hit; Underfill Rd Hit from NearMem, Clean Line", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Dirty line underfill read hits to Near Memory(DRAM cache) in Memory Mode", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", - "PerPkg": "1", - "PublicDescription": "Tag Hit; Underfill Rd Hit from NearMem, Dirty Line", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Number AD Ingress Credits", - "EventCode": "0x41", - "EventName": "UNC_M2M_TGR_AD_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number BL Ingress Credits", - "EventCode": "0x42", - "EventName": "UNC_M2M_TGR_BL_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 0", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 1", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 2", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 0", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 1", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 2", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 0", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 1", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 2", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 0", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 1", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 2", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Pending Occupancy", - "EventCode": "0x48", - "EventName": "UNC_M2M_TRACKER_PENDING_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credit Acquired", - "EventCode": "0xD", - "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credits Occupancy", - "EventCode": "0xE", - "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Full", - "EventCode": "0xC", - "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Not Empty", - "EventCode": "0xB", - "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Allocations", - "EventCode": "0x9", - "EventName": "UNC_M2M_TxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", - "EventCode": "0xF", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", - "EventCode": "0x10", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Occupancy", - "EventCode": "0xA", - "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK; CRD Transactions to Cbo", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.CRD_CBO", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK; NDR Transactions", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.NDR", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x1E", - "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x1E", - "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; All", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Near Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Far Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; All", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Read Credit Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Write Compare Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Write Credit Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; All", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Near Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Far Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Prefetch Read Cam Hit", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Read Credit Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Write Compare Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Write Credit Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; All", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Read Credit Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Write Compare Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Write Credit Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Sideband", - "EventCode": "0x6B", - "EventName": "UNC_M2M_TxC_AK_SIDEBAND.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Sideband", - "EventCode": "0x6B", - "EventName": "UNC_M2M_TxC_AK_SIDEBAND.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Cache", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Core", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to QPI", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_UPI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x1A", - "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x1A", - "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; All", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Near Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Far Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; All", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; All", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Near Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Far Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; All", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 0", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 1", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 2", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 0", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 1", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 2", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 0", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 1", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 2", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 0", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 1", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 2", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 0", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 1", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 2", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Requests", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Snoops", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; VNA Messages", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Writebacks", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_M3UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2C Sent", - "EventCode": "0x2B", - "EventName": "UNC_M3UPI_D2C_SENT", - "PerPkg": "1", - "PublicDescription": "Count cases BL sends direct to core", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2U Sent", - "EventCode": "0x2A", - "EventName": "UNC_M3UPI_D2U_SENT", - "PerPkg": "1", - "PublicDescription": "Cases where SMI3 sends D2U command", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO0_IIO1_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO2", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO3", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO4", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO5", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; All IIO targets for NCS are in single mask. ORs them together", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; Selected M2p BL NCS credits", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 1", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AK - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AK - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; BL - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; REQ on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; RSP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; SNP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; NCB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; NCS on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; RSP on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; WB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; REQ on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; RSP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; SNP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; NCB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; NCS on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; RSP on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; WB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; AD, BL Parallel Win", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN", - "PerPkg": "1", - "PublicDescription": "AD and BL messages won arbitration concurrently / in parallel", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN0", - "PerPkg": "1", - "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn0, delaying vn1 win, because vn0 offered parallel ad/bl", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN1", - "PerPkg": "1", - "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn1, delaying vn0 win, because vn1 offered parallel ad/bl", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; REQ on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; RSP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; SNP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; NCB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; NCS on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; RSP on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; WB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; REQ on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; RSP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; SNP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; NCB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; NCS on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; RSP on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; WB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; REQ on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; RSP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; SNP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; NCB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; NCS on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; RSP on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; WB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; REQ on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; RSP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; SNP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; NCB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; NCS on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; RSP on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; WB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on BL Arb", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on Idle", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 1", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 2", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; REQ on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; RSP on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; SNP on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; NCB on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; NCS on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; RSP on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; WB on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; REQ on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; RSP on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; SNP on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; NCB on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; NCS on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; RSP on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; WB on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; Any In BGF FIFO", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", - "PerPkg": "1", - "PublicDescription": "Indication that at least one packet (flit) is in the bgf (fifo only)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; Any in BGF Path", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", - "PerPkg": "1", - "PublicDescription": "Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; No D2K For Arb", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.NO_D2K_FOR_ARB", - "PerPkg": "1", - "PublicDescription": "VN0 or VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; D2K Credits", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", - "PerPkg": "1", - "PublicDescription": "D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Packets in BGF FIFO", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", - "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Packets in BGF Path", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", - "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", - "PerPkg": "1", - "PublicDescription": "count of bl messages in pump-1-pending state, in completion fifo only", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", - "PerPkg": "1", - "PublicDescription": "count of bl messages in pump-1-pending state, in marker table and in fifo", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Transmit Credits", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", - "PerPkg": "1", - "PublicDescription": "Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; VNA In Use", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", - "PerPkg": "1", - "PublicDescription": "Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; All", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; No BGF Credits", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_BGF", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; No TxQ Credits", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_TXQ", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 0", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "generating bl data flit sequence; waiting for data pump 0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is tracking at least one message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", - "PerPkg": "1", - "PublicDescription": "pump-1-pending completion fifo is full", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", - "PerPkg": "1", - "PublicDescription": "a bl message finished but is in limbo and moved to pump-1-pending logic", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 1", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "generating bl data flit sequence; waiting for data pump 1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; One Message", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG", - "PerPkg": "1", - "PublicDescription": "One message in flit; VNA or non-VNA flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; One Message in non-VNA", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG_VNX", - "PerPkg": "1", - "PublicDescription": "One message in flit; non-VNA flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; Two Messages", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.2_MSGS", - "PerPkg": "1", - "PublicDescription": "Two messages in flit; VNA flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; Three Messages", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.3_MSGS", - "PerPkg": "1", - "PublicDescription": "Three messages in flit; VNA flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_2", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_3", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; All", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Needs Data Flit", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", - "PerPkg": "1", - "PublicDescription": "BL message requires data flit sequence", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 0", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "Waiting for header pump 0", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Bubble", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit but flit transmission delayed", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Not Avail", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit and not available", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 1", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "Waiting for header pump 1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate Ready", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate Wasted", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Blocked", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Message", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting is in run-ahead to start new flit, and message is actually slotted into new flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Ok", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; New header flit construction may proceed in parallel with data flit sequence", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Flit Finished", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_FLIT", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit finished assembly in parallel with data flit sequence", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Message", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_MSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Message is slotted into header flit in parallel with data flit sequence", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate-matching stall injected", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall - No Message", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate matching stall injected, but no additional message slotted during stall cycle", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; All", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No BGF Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_CRD", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No BGF Credits + No Extra Message Slotted", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_NO_MSG", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available; no additional message slotted into flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No TxQ Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_CRD", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No TxQ Credits + No Extra Message Slotted", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_NO_MSG", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available; no additional message slotted into flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - One Slot Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ONE_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only one slot taken (two slots free)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - Three Slots Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.THREE_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with three slots taken (no slots free)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - Two Slots Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.TWO_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only two slots taken (one slots free)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Can't Slot AD", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", - "PerPkg": "1", - "PublicDescription": "some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Can't Slot BL", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", - "PerPkg": "1", - "PublicDescription": "some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel AD Lost", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_AD_LOST", - "PerPkg": "1", - "PublicDescription": "some AD message lost contest for slot 0 (logical OR of all AD events under INGR_SLOT_LOST_MC_VN{0,1})", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel Attempt", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", - "PerPkg": "1", - "PublicDescription": "ad and bl messages attempted to slot into the same flit in parallel", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel BL Lost", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_BL_LOST", - "PerPkg": "1", - "PublicDescription": "some BL message lost contest for slot 0 (logical OR of all BL events under INGR_SLOT_LOST_MC_VN{0,1})", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel Success", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", - "PerPkg": "1", - "PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; VN0", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.VN0", - "PerPkg": "1", - "PublicDescription": "vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; VN1", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.VN1", - "PerPkg": "1", - "PublicDescription": "vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; REQ on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; SNP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCS on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; WB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; REQ on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; SNP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCS on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; WB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; REQ on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; SNP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCS on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; WB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; REQ on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; SNP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCS on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; WB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; REQ on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; RSP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; SNP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; NCB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; NCS on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; RSP on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; WB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; REQ on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; RSP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; SNP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; NCB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; NCS on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; RSP on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; WB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Lost Arbitration", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARB_LOST", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Arrived", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARRIVED", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Dropped - Old", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_OLD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Dropped - Wrap", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_WRAP", - "PerPkg": "1", - "PublicDescription": "Dropped because it was overwritten by new message while prefetch queue was full", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Slotted", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.SLOTTED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Any In Use", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", - "PerPkg": "1", - "PublicDescription": "At least one remote vna credit is in use", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Corrected", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", - "PerPkg": "1", - "PublicDescription": "Number of remote vna credits corrected (local return) per cycle", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 1", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 1 (i.e. no vna credits available)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 4", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 5", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Used", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.USED", - "PerPkg": "1", - "PublicDescription": "Number of remote vna credits consumed per cycle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 WB Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 WB Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; CHA on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_CHA", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to CHA", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_NON_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn0 Snpf", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI0", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI1", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; CHA on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_CHA", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to CHA", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_NON_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn1 Snpf", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI0", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI0", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI1", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_NONSNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_VN2SNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn0 SnpF issued when SnpF pending on Vn1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_NONSNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_VN0SNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn1 SnpF issued when SnpF pending on Vn0", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 REQ Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 SNP Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 WB Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 REQ Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 SNP Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 WB Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 REQ Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 SNP Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 WB Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 REQ Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 SNP Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 WB Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 REQ Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 RSP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 SNP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 WB Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 REQ Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 RSP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 SNP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 WB Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Inserts", - "EventCode": "0x2F", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Occupancy", - "EventCode": "0x1E", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1_NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1_NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1_NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1_NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 NCS Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 NCB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 RSP Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCS Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 RSP Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 WB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCS Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 RSP Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 WB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VNA", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VNA", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", - "EventCode": "0x29", - "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", - "PerPkg": "1", - "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; WB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; REQ on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; RSP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; RSP on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; WB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; NCB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; REQ on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; RSP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; SNP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; RSP on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; WB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; REQ on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; RSP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; SNP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; RSP on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; WB on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; NCB on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; REQ on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; RSP on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; SNP on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; RSP on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_TxC_BL.DRS_UPI", - "Deprecated": "1", - "EventCode": "0x40", - "EventName": "UNC_NoUnit_TxC_BL.DRS_UPI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", - "EventCode": "0x1", - "EventName": "UNC_UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Data Response packets that go direct to core", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", - "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_DIRECT_ATTEMPTS.D2U", - "Deprecated": "1", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", - "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", - "EventCode": "0x21", - "EventName": "UNC_UPI_L1_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "EventCode": "0x16", - "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", - "EventCode": "0x20", - "EventName": "UNC_UPI_PHY_INIT_CYCLES", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req Nack", - "EventCode": "0x23", - "EventName": "UNC_UPI_POWER_L1_NACK", - "PerPkg": "1", - "PublicDescription": "Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req (same as L1 Ack).", - "EventCode": "0x22", - "EventName": "UNC_UPI_POWER_L1_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", - "EventCode": "0x25", - "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0. Receive side.", - "EventCode": "0x24", - "EventName": "UNC_UPI_RxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Request", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "REQ Message Class", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Request Opcode", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Conflict", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Invalid", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Snoop", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "SNP Message Class", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Snoop Opcode", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN0 Credit Consumed", - "EventCode": "0x39", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN1 Credit Consumed", - "EventCode": "0x3A", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credit Consumed", - "EventCode": "0x38", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid data FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Null FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Data", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Idle", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; LLCRD Not Empty", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; LLCTRL", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Protocol header and credit FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.ALL_NULL", - "Deprecated": "1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.NULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Protocol Header", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.PROTHDR", - "Deprecated": "1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.PROT_HDR", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 0", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 2", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.NCB", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.NCS", - "PerPkg": "1", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.REQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.RSP", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.SNP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.WB", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.WB", - "PerPkg": "1", - "UMask": "0xb", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 0", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 1", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 2", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 0", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 1", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 2", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", - "EventCode": "0x27", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "EventCode": "0x28", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "EventCode": "0x29", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0. Transmit side.", - "EventCode": "0x26", - "EventName": "UNC_UPI_TxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Request", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "REQ Message Class", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Request Opcode", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Conflict", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Invalid", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "SNP Message Class", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop Opcode", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs that bypassed the TxL Buffer", - "EventCode": "0x41", - "EventName": "UNC_UPI_TxL_BYPASSED", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid data FLITs transmitted via any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Null FLITs transmitted from any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Data", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Idle FLITs transmitted", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; LLCRD Not Empty", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; LLCTRL", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.ALL_NULL", - "Deprecated": "1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.NULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Protocol Header", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.PROTHDR", - "Deprecated": "1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.PROT_HDR", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 0", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 2", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.DATA_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.DUAL_SLOT_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.LOC", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NCB", - "PerPkg": "1", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NCS", - "PerPkg": "1", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NON_DATA_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.REM", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.REQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.SGL_SLOT_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.SNP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.WB", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.WB", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Allocations", - "EventCode": "0x40", - "EventName": "UNC_UPI_TxL_INSERTS", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x42", - "EventName": "UNC_UPI_TxL_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "EventCode": "0x45", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credits Pending Return - Occupancy", - "EventCode": "0x44", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", - "EventCode": "0xff", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; IPI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Inter Processor Interrupts", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; MSI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; VLW", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDRAND", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDSEED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - }, - { - "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", - "EventCode": "0x2", - "EventName": "UPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "ScaleUnit": "7.11E-06Bytes", - "UMask": "0xf", - "Unit": "UPI LL" - } -] -- GitLab From 6910f7bac205b28110f896b0b9881ecd35772426 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:37 -0700 Subject: [PATCH 2997/5631] perf vendor events intel: Fix uncore topics for haswell Move events from 'uncore-other' topic classification to cache and interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-10-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/haswell/uncore-cache.json | 50 +++++++++--------- .../arch/x86/haswell/uncore-interconnect.json | 52 +++++++++++++++++++ .../arch/x86/haswell/uncore-other.json | 50 ------------------ 3 files changed, 77 insertions(+), 75 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json index c538557ba4c0..be9a3ed1a940 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-cache.json @@ -5,7 +5,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", "PerPkg": "1", "UMask": "0x86", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", @@ -13,7 +13,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", @@ -21,7 +21,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", @@ -29,7 +29,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", "PerPkg": "1", "UMask": "0x8f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", @@ -37,7 +37,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", "PerPkg": "1", "UMask": "0x46", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", @@ -45,7 +45,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", @@ -53,7 +53,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", @@ -61,7 +61,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", "PerPkg": "1", "UMask": "0x4f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", @@ -69,7 +69,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", "PerPkg": "1", "UMask": "0x16", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", @@ -77,7 +77,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", "PerPkg": "1", "UMask": "0x18", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", @@ -85,7 +85,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", "PerPkg": "1", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", @@ -93,7 +93,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", "PerPkg": "1", "UMask": "0x1f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", @@ -101,7 +101,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", "PerPkg": "1", "UMask": "0x26", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", @@ -109,7 +109,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", @@ -117,7 +117,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", @@ -125,7 +125,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", "PerPkg": "1", "UMask": "0x2f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", @@ -133,7 +133,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a modified line in some processor core.", @@ -141,7 +141,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", @@ -149,7 +149,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", @@ -157,7 +157,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", "PerPkg": "1", "UMask": "0x84", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a non-modified line in some processor core.", @@ -165,7 +165,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", "PerPkg": "1", "UMask": "0x24", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", @@ -173,7 +173,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", @@ -181,7 +181,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop misses in some processor core.", @@ -189,7 +189,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", @@ -197,6 +197,6 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json new file mode 100644 index 000000000000..8da28239ebf9 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-interconnect.json @@ -0,0 +1,52 @@ +[ + { + "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)", + "EventCode": "0x83", + "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All", + "PerPkg": "1", + "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "CounterMask": "1", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json b/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json index 84cc2536de69..2af92e43b28a 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/haswell/uncore-other.json @@ -1,54 +1,4 @@ [ - { - "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)", - "EventCode": "0x83", - "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All", - "PerPkg": "1", - "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", - "CounterMask": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "ARB" - }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", "EventCode": "0xff", -- GitLab From 579c04721539f690c63a9fe095d76af235a95864 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:38 -0700 Subject: [PATCH 2998/5631] perf vendor events intel: Fix uncore topics for haswellx Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-11-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/haswellx/uncore-cache.json | 360 +- .../x86/haswellx/uncore-interconnect.json | 4242 +++++++++++++---- .../arch/x86/haswellx/uncore-io.json | 528 ++ .../arch/x86/haswellx/uncore-other.json | 3160 ------------ 4 files changed, 4145 insertions(+), 4145 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json index e969dc71bea1..9227cc226002 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json @@ -8,7 +8,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode", @@ -19,7 +19,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode", @@ -30,7 +30,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode", @@ -41,7 +41,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode", @@ -52,7 +52,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode", @@ -63,7 +63,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode", @@ -74,7 +74,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode", @@ -85,7 +85,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode", @@ -96,7 +96,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode", @@ -107,7 +107,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "ScaleUnit": "64Bytes", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode", @@ -118,7 +118,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode", @@ -128,7 +128,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode", @@ -139,7 +139,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode", @@ -150,7 +150,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode", @@ -161,7 +161,7 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode", @@ -172,20 +172,20 @@ "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Bounce Control", "EventCode": "0xA", "EventName": "UNC_C_BOUNCE_CONTROL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Counter 0 Occupancy", @@ -193,7 +193,7 @@ "EventName": "UNC_C_COUNTER0_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "FaST wire asserted", @@ -201,7 +201,7 @@ "EventName": "UNC_C_FAST_ASSERTED", "PerPkg": "1", "PublicDescription": "Counts the number of cycles either the local distress or incoming distress signals are asserted. Incoming distress includes both up and dn.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)", @@ -212,7 +212,7 @@ "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", "ScaleUnit": "64Bytes", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Data Read Request", @@ -221,7 +221,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Lookups that Match NID", @@ -230,7 +230,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Any Read Request", @@ -239,7 +239,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Read transactions", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; External Snoop Request", @@ -248,7 +248,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", "UMask": "0x9", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Write Requests", @@ -257,7 +257,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in E state", @@ -266,7 +266,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -275,7 +275,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in S State", @@ -284,7 +284,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -293,7 +293,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "M line evictions from LLC (writebacks to memory)", @@ -303,7 +303,7 @@ "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "ScaleUnit": "64Bytes", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", @@ -312,7 +312,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines in S State", @@ -321,7 +321,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; DRd hitting non-M with raw CV=0", @@ -330,7 +330,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Clean Victim with raw CV=0", @@ -339,7 +339,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; RFO HitS", @@ -348,7 +348,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Number of times that an RFO hit in S state. This is useful for determining if it might be good for a workload to use RspIWB instead of RspSWB.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Silent Snoop Eviction", @@ -357,7 +357,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc", @@ -366,7 +366,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Write Combining Aliasing", @@ -375,7 +375,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 0", @@ -384,7 +384,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 0", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 1", @@ -393,7 +393,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 2", @@ -402,7 +402,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 2", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 3", @@ -411,7 +411,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 3", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Bits Decremented", @@ -420,7 +420,7 @@ "PerPkg": "1", "PublicDescription": "How often all LRU bits were decremented by 1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; Non-0 Aged Victim", @@ -429,7 +429,7 @@ "PerPkg": "1", "PublicDescription": "How often we picked a victim that had a non-zero age", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; All", @@ -438,7 +438,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down", @@ -447,7 +447,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even", @@ -456,7 +456,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd", @@ -465,7 +465,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up", @@ -474,7 +474,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even", @@ -483,7 +483,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd", @@ -492,7 +492,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; All", @@ -501,7 +501,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down", @@ -510,7 +510,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even", @@ -519,7 +519,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd", @@ -528,7 +528,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up", @@ -537,7 +537,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even", @@ -546,7 +546,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd", @@ -555,7 +555,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -564,7 +564,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -573,7 +573,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even", @@ -582,7 +582,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd", @@ -591,7 +591,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up", @@ -600,7 +600,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even", @@ -609,7 +609,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd", @@ -618,7 +618,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AD", @@ -626,7 +626,7 @@ "EventName": "UNC_C_RING_BOUNCES.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; AK", @@ -634,7 +634,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; BL", @@ -642,7 +642,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", @@ -650,7 +650,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -659,7 +659,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in HSX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -668,7 +668,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in HSX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -677,7 +677,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in HSX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters for Down polarity", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -686,7 +686,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in HSX Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "UNC_C_RING_SINK_STARVED.AD", @@ -694,7 +694,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "UNC_C_RING_SINK_STARVED.AK", @@ -702,7 +702,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "UNC_C_RING_SINK_STARVED.BL", @@ -710,7 +710,7 @@ "EventName": "UNC_C_RING_SINK_STARVED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "UNC_C_RING_SINK_STARVED.IV", @@ -718,14 +718,14 @@ "EventName": "UNC_C_RING_SINK_STARVED.IV", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of cycles the Cbo is actively throttling traffic onto the Ring in order to limit bounce traffic.", "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", @@ -734,7 +734,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", @@ -743,7 +743,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IRQ is externally starved and therefore we are blocking the IPQ.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", @@ -752,7 +752,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; Number of times that the ISMQ Bid.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; PRQ", @@ -761,7 +761,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IPQ", @@ -770,7 +770,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ", @@ -779,7 +779,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ Rejected", @@ -788,7 +788,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -797,7 +797,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; PRQ", @@ -806,7 +806,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", @@ -815,7 +815,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IPQ in Internal Starvation.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", @@ -824,7 +824,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IRQ in Internal Starvation.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", @@ -833,7 +833,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the ISMQ in Internal Starvation.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; PRQ", @@ -842,7 +842,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Address Conflict", @@ -851,7 +851,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from an address conflicts. Address conflicts out of the IPQ should be rare. They will generally only occur if two different sockets are sending requests to the same address at the same time. This is a true conflict case, unlike the IPQ Address Conflict which is commonly caused by prefetching characteristics.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Any Reject", @@ -860,7 +860,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject. TOR rejects from the IPQ can be caused by the Egress being full or Address Conflicts.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No Egress Credits", @@ -869,7 +869,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from the Egress being full. IPQ requests make use of the AD Egress for regular responses, the BL egress to forward data, and the AK egress to return credits.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No QPI Credits", @@ -878,7 +878,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No AD Sbo Credits", @@ -887,7 +887,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Target Node Filter", @@ -896,7 +896,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", @@ -905,7 +905,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because of an address match in the TOR. In order to maintain coherency, requests to the same address are not allowed to pass each other up in the Cbo. Therefore, if there is an outstanding request to a given address, one cannot issue another request to that address until it is complete. This comes up most commonly with prefetches. Outstanding prefetches occasionally will not complete their memory fetch and a demand request to the same address will then sit in the IRQ and get retried until the prefetch fills the data into the LLC. Therefore, it will not be uncommon to see this case in high bandwidth streaming workloads when the LLC Prefetcher in the core is enabled.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Any Reject", @@ -914,7 +914,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of IRQ retries that occur. Requests from the IRQ are retried if they are rejected from the TOR pipeline for a variety of reasons. Some of the most common reasons include if the Egress is full, there are no RTIDs, or there is a Physical Address match to another outstanding request.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", @@ -923,7 +923,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because it failed to acquire an entry in the Egress. The egress is the buffer that queues up for allocating onto the ring. IRQ requests can make use of all four rings and all four Egresses. If any of the queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No IIO Credits", @@ -932,7 +932,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects", @@ -941,7 +941,7 @@ "PerPkg": "1", "PublicDescription": "Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", @@ -950,7 +950,7 @@ "PerPkg": "1", "PublicDescription": "Number of requests rejects because of lack of QPI Ingress credits. These credits are required in order to send transactions to the QPI agent. Please see the QPI_IGR_CREDITS events for more information.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", @@ -959,7 +959,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that requests from the IRQ were retried because there were no RTIDs available. RTIDs are required after a request misses the LLC and needs to send snoops and/or requests to memory. If there are no RTIDs available, requests will queue up in the IRQ and retry until one becomes available. Note that there are multiple RTID pools for the different sockets. There may be cases where the local RTIDs are all used, but requests destined for remote memory can still acquire an RTID because there are remote RTIDs available. This event does not provide any filtering for this case.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No AD Sbo Credits", @@ -968,7 +968,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No BL Sbo Credits", @@ -977,7 +977,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Target Node Filter", @@ -986,7 +986,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IPQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; Any Reject", @@ -995,7 +995,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the total number of times that a request from the ISMQ retried because of a TOR reject. ISMQ requests generally will not need to retry (or at least ISMQ retries are less common than IRQ retries). ISMQ requests will retry if they are not able to acquire a needed Egress credit to get onto the ring, or for cache evictions that need to acquire an RTID. Most ISMQ requests already have an RTID, so eviction retries will be less common here.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No Egress Credits", @@ -1004,7 +1004,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by a lack of Egress credits. The egress is the buffer that queues up for allocating onto the ring. If any of the Egress queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No IIO Credits", @@ -1013,7 +1013,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -1022,7 +1022,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No QPI Credits", @@ -1031,7 +1031,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No RTIDs", @@ -1040,7 +1040,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by no RTIDs. M-state cache evictions are serviced through the ISMQ, and must acquire an RTID in order to write back to memory. If no RTIDs are available, they will be retried.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries", @@ -1049,7 +1049,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Qualify one of the other subevents by a given RTID destination NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER1.nid.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No AD Sbo Credits", @@ -1058,7 +1058,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an AD packet to the Sbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; No BL Sbo Credits", @@ -1067,7 +1067,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried because of it lacked credits to send an BL packet to the Sbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Request Queue Rejects; Target Node Filter", @@ -1076,7 +1076,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the ISMQ was retried filtered by the Target NodeID as specified in the Cbox's Filter register.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IPQ", @@ -1085,7 +1085,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ", @@ -1094,7 +1094,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ Rejected", @@ -1103,7 +1103,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; PRQ Rejects", @@ -1112,7 +1112,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For AD Ring", @@ -1121,7 +1121,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Acquired; For BL Ring", @@ -1130,7 +1130,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits acquired in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For AD Ring", @@ -1139,7 +1139,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "SBo Credits Occupancy; For BL Ring", @@ -1148,7 +1148,7 @@ "PerPkg": "1", "PublicDescription": "Number of Sbo credits in use in a given cycle, per ring. Each Cbo is assigned an Sbo it can communicate with.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; All", @@ -1157,7 +1157,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Evictions", @@ -1166,7 +1166,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory", @@ -1175,7 +1175,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory - Opcode Matched", @@ -1184,7 +1184,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory", @@ -1193,7 +1193,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory - Opcode Matched", @@ -1202,7 +1202,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss Opcode Match", @@ -1211,7 +1211,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory", @@ -1220,7 +1220,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory - Opcode Matched", @@ -1229,7 +1229,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched", @@ -1238,7 +1238,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Evictions", @@ -1247,7 +1247,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Miss All", @@ -1256,7 +1256,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", @@ -1265,7 +1265,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched", @@ -1274,7 +1274,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Writebacks", @@ -1283,7 +1283,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Opcode Match", @@ -1292,7 +1292,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory", @@ -1301,7 +1301,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory - Opcode Matched", @@ -1310,7 +1310,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Writebacks", @@ -1319,7 +1319,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Any", @@ -1328,7 +1328,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All valid TOR entries. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Evictions", @@ -1337,7 +1337,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding eviction transactions in the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode", @@ -1347,7 +1347,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1356,7 +1356,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Local Memory - Opcode Matched", @@ -1365,7 +1365,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss All", @@ -1374,7 +1374,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding miss requests in the TOR. 'Miss' means the allocation requires an RTID. This generally means that the request was sent to memory or MMIO.", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1383,7 +1383,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Local Memory - Opcode Matched", @@ -1392,7 +1392,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss Opcode Match", @@ -1401,7 +1401,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1410,7 +1410,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Remote Memory - Opcode Matched", @@ -1419,7 +1419,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1428,7 +1428,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of NID matched outstanding requests in the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid.In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Evictions", @@ -1437,7 +1437,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding NID matched eviction transactions in the TOR .", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1446,7 +1446,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", @@ -1455,7 +1455,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched", @@ -1464,7 +1464,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Writebacks", @@ -1473,7 +1473,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); NID matched write transactions int the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Opcode Match", @@ -1482,7 +1482,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc).", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1491,7 +1491,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Remote Memory - Opcode Matched", @@ -1500,7 +1500,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Writebacks", @@ -1509,7 +1509,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Write transactions in the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AD Ring", @@ -1517,7 +1517,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AK Ring", @@ -1525,7 +1525,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto BL Ring", @@ -1533,7 +1533,7 @@ "EventName": "UNC_C_TxR_ADS_USED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Cachebo", @@ -1542,7 +1542,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Corebo", @@ -1551,7 +1551,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AD ring. This is commonly used for outbound requests.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Cachebo", @@ -1560,7 +1560,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AK ring. This is commonly used for credit returns and GO responses.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Corebo", @@ -1569,7 +1569,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AK ring. This is commonly used for snoop responses coming from the core and destined for a Cachebo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Cacheno", @@ -1578,7 +1578,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the BL ring. This is commonly used to send data from the cache to various destinations.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Corebo", @@ -1587,7 +1587,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; IV - Cachebo", @@ -1596,7 +1596,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the IV ring. This is commonly used for snoops to the cores.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AD Ring (to core)", @@ -1605,7 +1605,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the core AD egress spent in starvation", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AK Ring", @@ -1614,7 +1614,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both AK egresses spent in starvation", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto BL Ring", @@ -1623,7 +1623,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both BL egresses spent in starvation", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto IV Ring", @@ -1632,7 +1632,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the cachebo IV egress spent in starvation", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BT Cycles Not Empty", diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json index 15059b17cd19..954e8198c7a5 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -6,7 +6,7 @@ "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "ScaleUnit": "8Bytes", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data", @@ -15,1318 +15,3950 @@ "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "ScaleUnit": "8Bytes", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { - "BriefDescription": "Number of qfclks", - "EventCode": "0x14", - "EventName": "UNC_Q_CLOCKTICKS", + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", "PerPkg": "1", - "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/4th the GT/s speed of the QPI link. For example, a 4GT/s link will have qfclk or 1GHz. HSX does not support dynamic link speeds, so this frequency is fixed.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" }, { - "BriefDescription": "Count of CTO Events", - "EventCode": "0x38", - "EventName": "UNC_Q_CTO_COUNT", + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", "PerPkg": "1", - "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CLFlush", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", + "BriefDescription": "Coherent Ops; CRd", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", + "EventName": "UNC_I_COHERENT_OPS.CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", + "BriefDescription": "Coherent Ops; DRd", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", + "EventName": "UNC_I_COHERENT_OPS.DRD", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", + "BriefDescription": "Coherent Ops; PCIDCAHin5t", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", + "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", - "UMask": "0x80", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", + "BriefDescription": "Coherent Ops; PCIRdCur", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", + "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x1", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", + "BriefDescription": "Coherent Ops; PCIItoM", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", + "BriefDescription": "Coherent Ops; RFO", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", + "EventName": "UNC_I_COHERENT_OPS.RFO", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", - "UMask": "0x40", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "Direct 2 Core Spawning; Spawn Success", + "BriefDescription": "Coherent Ops; WbMtoI", "EventCode": "0x13", - "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", "PerPkg": "1", - "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L1", - "EventCode": "0x12", - "EventName": "UNC_Q_L1_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L0p", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "Cycles in L0", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL0_POWER_CYCLES", + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "Rx Flit Buffer Bypassed", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_BYPASSED", + "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REJ", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "CRC Errors Detected; LinkInit", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_CRC_ERRORS.LINK_INIT", + "BriefDescription": "Misc Events - Set 0; Fastpath Requests", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_REQ", "PerPkg": "1", - "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "CRC Errors Detected; Normal Operations", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.FAST_XFER", "PerPkg": "1", - "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during normal operation.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; DRS", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.DRS", + "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; HOM", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.HOM", + "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", + "EventCode": "0x14", + "EventName": "UNC_I_MISC0.PF_TIMEOUT", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NCB", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCB", + "BriefDescription": "Misc Events - Set 1; Data Throttled", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.DATA_THROTTLE", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "IRP throttled switch data", + "UMask": "0x80", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NCS", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCS", + "BriefDescription": "Misc Events - Set 1", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.LOST_FWD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; NDR", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NDR", + "BriefDescription": "Misc Events - Set 1; Received Invalid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN0 Credit Consumed; SNP", - "EventCode": "0x1E", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.SNP", + "BriefDescription": "Misc Events - Set 1; Received Valid", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; DRS", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.DRS", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_E", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; HOM", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.HOM", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_M", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NCB", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCB", + "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", + "EventCode": "0x15", + "EventName": "UNC_I_MISC1.SLOW_S", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NCS", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCS", + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_RxR_AK_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; NDR", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NDR", + "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "VN1 Credit Consumed; SNP", - "EventCode": "0x39", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.SNP", + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "VNA Credit Consumed", - "EventCode": "0x1D", - "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", + "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_CYCLES_NE", + "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN0", + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", - "EventCode": "0xF", - "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN1", + "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", - "EventCode": "0x12", - "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN0", + "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", - "EventCode": "0x12", - "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN1", + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN0", + "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", - "EventCode": "0x10", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN1", + "BriefDescription": "Snoop Responses; Hit E or S", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit E or S", + "UMask": "0x4", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", - "EventCode": "0x11", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN0", + "BriefDescription": "Snoop Responses; Hit I", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit I", + "UMask": "0x2", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", - "EventCode": "0x11", - "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN1", + "BriefDescription": "Snoop Responses; Hit M", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : Hit M", + "UMask": "0x8", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", - "EventCode": "0x14", - "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN0", + "BriefDescription": "Snoop Responses; Miss", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.MISS", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "PublicDescription": "Snoop Responses : Miss", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", - "EventCode": "0x14", - "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN1", + "BriefDescription": "Snoop Responses; SnpCode", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpCode", + "UMask": "0x10", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", - "EventCode": "0x13", - "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN0", + "BriefDescription": "Snoop Responses; SnpData", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpData", + "UMask": "0x20", + "Unit": "IRP" }, { - "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", - "EventCode": "0x13", - "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN1", + "BriefDescription": "Snoop Responses; SnpInv", + "EventCode": "0x17", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Snoop Responses : SnpInv", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Atomic", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Other", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.RD_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Write Prefetches", + "EventCode": "0x16", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xF", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xD", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Number of qfclks", + "EventCode": "0x14", + "EventName": "UNC_Q_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/4th the GT/s speed of the QPI link. For example, a 4GT/s link will have qfclk or 1GHz. HSX does not support dynamic link speeds, so this frequency is fixed.", + "Unit": "QPI" + }, + { + "BriefDescription": "Count of CTO Events", + "EventCode": "0x38", + "EventName": "UNC_Q_CTO_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_CREDITS_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", + "UMask": "0x80", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.FAILURE_RBT_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", + "UMask": "0x40", + "Unit": "QPI" + }, + { + "BriefDescription": "Direct 2 Core Spawning; Spawn Success", + "EventCode": "0x13", + "EventName": "UNC_Q_DIRECT2CORE.SUCCESS_RBT_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L1", + "EventCode": "0x12", + "EventName": "UNC_Q_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Bypassed", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "Unit": "QPI" + }, + { + "BriefDescription": "CRC Errors Detected; LinkInit", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.LINK_INIT", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "CRC Errors Detected; Normal Operations", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_CRC_ERRORS.NORMAL_OP", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during normal operation.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; DRS", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; HOM", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCB", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NCS", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; NDR", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "VN0 Credit Consumed; SNP", + "EventCode": "0x1E", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN0.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; DRS", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; HOM", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCB", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NCS", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; NDR", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "VN1 Credit Consumed; SNP", + "EventCode": "0x39", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x1D", + "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", + "EventCode": "0xF", + "EventName": "UNC_Q_RxL_CYCLES_NE_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", + "EventCode": "0x12", + "EventName": "UNC_Q_RxL_CYCLES_NE_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", + "EventCode": "0x10", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", + "EventCode": "0x11", + "EventName": "UNC_Q_RxL_CYCLES_NE_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", + "EventCode": "0x14", + "EventName": "UNC_Q_RxL_CYCLES_NE_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", + "EventCode": "0x13", + "EventName": "UNC_Q_RxL_CYCLES_NE_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", "EventCode": "0x1", - "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", + "EventName": "UNC_Q_RxL_FLITS_G0.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", + "UMask": "0x18", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Data Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; DRS Header Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; HOM Request Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 1; SNP Flits", + "EventCode": "0x2", + "EventName": "UNC_Q_RxL_FLITS_G1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xc", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", + "EventCode": "0x3", + "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations", + "EventCode": "0x8", + "EventName": "UNC_Q_RxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", + "EventCode": "0x9", + "EventName": "UNC_Q_RxL_INSERTS_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", + "EventCode": "0xC", + "EventName": "UNC_Q_RxL_INSERTS_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", + "EventCode": "0xA", + "EventName": "UNC_Q_RxL_INSERTS_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_INSERTS_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", + "EventCode": "0xE", + "EventName": "UNC_Q_RxL_INSERTS_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", + "EventCode": "0xD", + "EventName": "UNC_Q_RxL_INSERTS_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets", + "EventCode": "0xB", + "EventName": "UNC_Q_RxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN0", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - DRS; for VN1", + "EventCode": "0x15", + "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN0", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - HOM; for VN1", + "EventCode": "0x18", + "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN0", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCB; for VN1", + "EventCode": "0x16", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN0", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NCS; for VN1", + "EventCode": "0x17", + "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN0", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - NDR; for VN1", + "EventCode": "0x1A", + "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN0", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "RxQ Occupancy - SNP; for VN1", + "EventCode": "0x19", + "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_DRS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_HOM", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCB", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NDR", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_SNP", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.EGRESS_CREDITS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", + "UMask": "0x40", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", + "EventCode": "0x35", + "EventName": "UNC_Q_RxL_STALLS_VN0.GV", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", + "UMask": "0x80", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_DRS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_HOM", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCB", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCS", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NDR", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x20", + "Unit": "QPI" + }, + { + "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", + "EventCode": "0x3A", + "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_SNP", + "PerPkg": "1", + "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0xD", + "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0xC", + "EventName": "UNC_Q_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "EventCode": "0x5", + "EventName": "UNC_Q_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.ALMOST_FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", + "EventCode": "0x2", + "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.FULL", + "PerPkg": "1", + "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Cycles not Empty", + "EventCode": "0x6", + "EventName": "UNC_Q_TxL_CYCLES_NE", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", + "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", + "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", + "UMask": "0x18", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", + "UMask": "0x6", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 1; SNP Flits", + "EventName": "UNC_Q_TxL_FLITS_G1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", + "UMask": "0xc", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "UMask": "0x8", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", + "UMask": "0x10", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", + "EventCode": "0x1", + "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x4", + "EventName": "UNC_Q_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "QPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x7", + "EventName": "UNC_Q_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", + "EventCode": "0x26", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", + "EventCode": "0x22", + "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "EventCode": "0x28", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", + "EventCode": "0x24", + "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", + "EventCode": "0x27", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", + "EventCode": "0x23", + "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "EventCode": "0x29", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", + "EventCode": "0x25", + "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", + "EventCode": "0x2A", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN_SHR", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", + "EventCode": "0x1F", + "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN_SHR", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "UMask": "0x4", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", + "EventCode": "0x2B", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", + "EventCode": "0x2B", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", + "EventCode": "0x20", + "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", + "EventCode": "0x2C", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", + "EventCode": "0x2C", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN1", + "PerPkg": "1", + "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN0", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x1", + "Unit": "QPI" + }, + { + "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", + "EventCode": "0x21", + "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN1", + "PerPkg": "1", + "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", + "UMask": "0x2", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credits Returned", + "EventCode": "0x1C", + "EventName": "UNC_Q_VNA_CREDIT_RETURNS", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits returned.", + "Unit": "QPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x1B", + "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "QPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14_16", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x1F", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO_15_17", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 15&17", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x22", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2D", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Backpressure", + "EventCode": "0xB", + "EventName": "UNC_R3_IOT_BACKPRESSURE.HUB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Backpressure", + "EventCode": "0xB", + "EventName": "UNC_R3_IOT_BACKPRESSURE.SAT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Hi", + "EventCode": "0xD", + "EventName": "UNC_R3_IOT_CTS_HI.CTS2", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Hi", + "EventCode": "0xD", + "EventName": "UNC_R3_IOT_CTS_HI.CTS3", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Lo", + "EventCode": "0xC", + "EventName": "UNC_R3_IOT_CTS_LO.CTS0", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "IOT Common Trigger Sequencer - Lo", + "EventCode": "0xC", + "EventName": "UNC_R3_IOT_CTS_LO.CTS1", + "PerPkg": "1", + "PublicDescription": "Debug Mask/Match Tie-Ins", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x20", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x21", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2E", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2F", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 IV Ring in Use; Clockwise", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x3", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ring Stop Starved; AK", + "EventCode": "0xE", + "EventName": "UNC_R3_RING_SINK_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles the ringstop is in starvation (per ring)", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; DRS", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; HOM", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NCB", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NCS", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; NDR", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Cycles Not Empty; SNP", + "EventCode": "0x14", + "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; DRS", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; HOM", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NCB", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NCS", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; NDR", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Allocations; SNP", + "EventCode": "0x15", + "EventName": "UNC_R3_RxR_INSERTS_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For AD Ring", + "EventCode": "0x28", + "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For BL Ring", + "EventCode": "0x28", + "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", + "EventCode": "0x2A", + "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS", + "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", + "EventCode": "0x2A", + "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", - "UMask": "0x18", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Data Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS_DATA", + "BriefDescription": "SBo1 Credits Acquired; For AD Ring", + "EventCode": "0x29", + "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; DRS Header Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.DRS_NONDATA", + "BriefDescription": "SBo1 Credits Acquired; For BL Ring", + "EventCode": "0x29", + "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM", + "BriefDescription": "SBo1 Credits Occupancy; For AD Ring", + "EventCode": "0x2B", + "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", - "UMask": "0x6", - "Unit": "QPI LL" + "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM_NONREQ", + "BriefDescription": "SBo1 Credits Occupancy; For BL Ring", + "EventCode": "0x2B", + "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; HOM Request Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.HOM_REQ", + "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 1; SNP Flits", - "EventCode": "0x2", - "EventName": "UNC_Q_RxL_FLITS_G1.SNP", + "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x8", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB", + "BriefDescription": "Egress CCW NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", - "UMask": "0xc", - "Unit": "QPI LL" + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB_DATA", + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", + "PublicDescription": "AK CounterClockwise Egress Queue", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCB_NONDATA", + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.DN_BL", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NCS", + "BriefDescription": "Egress CCW NACK; BL CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK.UP_BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AD", + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", - "EventCode": "0x3", - "EventName": "UNC_Q_RxL_FLITS_G2.NDR_AK", + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", "PerPkg": "1", - "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations", - "EventCode": "0x8", - "EventName": "UNC_Q_RxL_INSERTS", + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_INSERTS_DRS.VN0", + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", - "EventCode": "0x9", - "EventName": "UNC_Q_RxL_INSERTS_DRS.VN1", + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", - "EventCode": "0xC", - "EventName": "UNC_Q_RxL_INSERTS_HOM.VN0", + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", - "EventCode": "0xC", - "EventName": "UNC_Q_RxL_INSERTS_HOM.VN1", + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_INSERTS_NCB.VN0", + "BriefDescription": "VN1 Credit Used; DRS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; HOM Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", - "EventCode": "0xA", - "EventName": "UNC_Q_RxL_INSERTS_NCB.VN1", + "BriefDescription": "VN1 Credit Used; NCB Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NDR Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_INSERTS_NCS.VN0", + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_INSERTS_NCS.VN1", + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "R3QPI" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", - "EventCode": "0xE", - "EventName": "UNC_Q_RxL_INSERTS_NDR.VN0", + "BriefDescription": "Bounce Control", + "EventCode": "0xA", + "EventName": "UNC_S_BOUNCE_CONTROL", + "PerPkg": "1", + "Unit": "SBOX" + }, + { + "BriefDescription": "Uncore Clocks", + "EventName": "UNC_S_CLOCKTICKS", + "PerPkg": "1", + "Unit": "SBOX" + }, + { + "BriefDescription": "FaST wire asserted", + "EventCode": "0x9", + "EventName": "UNC_S_FAST_ASSERTED", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down and Event", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" + }, + { + "BriefDescription": "AD Ring In Use; Down and Odd", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.DOWN_ODD", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", - "EventCode": "0xE", - "EventName": "UNC_Q_RxL_INSERTS_NDR.VN1", + "BriefDescription": "AD Ring In Use; Up", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", - "EventCode": "0xD", - "EventName": "UNC_Q_RxL_INSERTS_SNP.VN0", + "BriefDescription": "AD Ring In Use; Up and Even", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP_EVEN", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", - "EventCode": "0xD", - "EventName": "UNC_Q_RxL_INSERTS_SNP.VN1", + "BriefDescription": "AD Ring In Use; Up and Odd", + "EventCode": "0x1B", + "EventName": "UNC_S_RING_AD_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - All Packets", - "EventCode": "0xB", - "EventName": "UNC_Q_RxL_OCCUPANCY", + "BriefDescription": "AK Ring In Use; Down", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - DRS; for VN0", - "EventCode": "0x15", - "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN0", + "BriefDescription": "AK Ring In Use; Down and Event", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - DRS; for VN1", - "EventCode": "0x15", - "EventName": "UNC_Q_RxL_OCCUPANCY_DRS.VN1", + "BriefDescription": "AK Ring In Use; Down and Odd", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.DOWN_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - HOM; for VN0", - "EventCode": "0x18", - "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN0", + "BriefDescription": "AK Ring In Use; Up", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" + }, + { + "BriefDescription": "AK Ring In Use; Up and Even", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - HOM; for VN1", - "EventCode": "0x18", - "EventName": "UNC_Q_RxL_OCCUPANCY_HOM.VN1", + "BriefDescription": "AK Ring In Use; Up and Odd", + "EventCode": "0x1C", + "EventName": "UNC_S_RING_AK_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCB; for VN0", - "EventCode": "0x16", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN0", + "BriefDescription": "BL Ring in Use; Down", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCB; for VN1", - "EventCode": "0x16", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCB.VN1", + "BriefDescription": "BL Ring in Use; Down and Event", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCS; for VN0", - "EventCode": "0x17", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN0", + "BriefDescription": "BL Ring in Use; Down and Odd", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.DOWN_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NCS; for VN1", - "EventCode": "0x17", - "EventName": "UNC_Q_RxL_OCCUPANCY_NCS.VN1", + "BriefDescription": "BL Ring in Use; Up", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x3", + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NDR; for VN0", - "EventCode": "0x1A", - "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN0", + "BriefDescription": "BL Ring in Use; Up and Even", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP_EVEN", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - NDR; for VN1", - "EventCode": "0x1A", - "EventName": "UNC_Q_RxL_OCCUPANCY_NDR.VN1", + "BriefDescription": "BL Ring in Use; Up and Odd", + "EventCode": "0x1D", + "EventName": "UNC_S_RING_BL_USED.UP_ODD", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - SNP; for VN0", - "EventCode": "0x19", - "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN0", + "BriefDescription": "Number of LLC responses that bounced on the Ring.", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.AD_CACHE", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "RxQ Occupancy - SNP; for VN1", - "EventCode": "0x19", - "EventName": "UNC_Q_RxL_OCCUPANCY_SNP.VN1", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.AK_CORE", "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_DRS", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x1", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_HOM", + "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", + "EventCode": "0x5", + "EventName": "UNC_S_RING_BOUNCES.IV_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCB", + "BriefDescription": "BL Ring in Use; Any", + "EventCode": "0x1E", + "EventName": "UNC_S_RING_IV_USED.DN", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", + "UMask": "0xc", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NCS", + "BriefDescription": "BL Ring in Use; Any", + "EventCode": "0x1E", + "EventName": "UNC_S_RING_IV_USED.UP", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", + "UMask": "0x3", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_NDR", + "BriefDescription": "UNC_S_RING_SINK_STARVED.AD_CACHE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.AD_CACHE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x20", - "Unit": "QPI LL" + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.BGF_SNP", + "BriefDescription": "UNC_S_RING_SINK_STARVED.AK_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.AK_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x10", - "Unit": "QPI LL" + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.EGRESS_CREDITS", + "BriefDescription": "UNC_S_RING_SINK_STARVED.BL_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.BL_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", - "UMask": "0x40", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", - "EventCode": "0x35", - "EventName": "UNC_Q_RxL_STALLS_VN0.GV", + "BriefDescription": "UNC_S_RING_SINK_STARVED.IV_CORE", + "EventCode": "0x6", + "EventName": "UNC_S_RING_SINK_STARVED.IV_CORE", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", - "UMask": "0x80", - "Unit": "QPI LL" + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_DRS", + "BriefDescription": "Injection Starvation; AD - Bounces", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", + "UMask": "0x2", + "Unit": "SBOX" + }, + { + "BriefDescription": "Injection Starvation; AD - Credits", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_HOM", + "BriefDescription": "Injection Starvation; BL - Bounces", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCB", + "BriefDescription": "Injection Starvation; BL - Credits", + "EventCode": "0x15", + "EventName": "UNC_S_RxR_BUSY_STARVED.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NCS", + "BriefDescription": "Bypass; AD - Bounces", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_NDR", + "BriefDescription": "Bypass; AD - Credits", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", - "UMask": "0x20", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", - "EventCode": "0x3A", - "EventName": "UNC_Q_RxL_STALLS_VN1.BGF_SNP", + "BriefDescription": "Bypass; AK", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.AK", "PerPkg": "1", - "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", + "PublicDescription": "Bypass the Sbo Ingress.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Cycles in L0p", - "EventCode": "0xD", - "EventName": "UNC_Q_TxL0P_POWER_CYCLES", + "BriefDescription": "Bypass; BL - Bounces", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Cycles in L0", - "EventCode": "0xC", - "EventName": "UNC_Q_TxL0_POWER_CYCLES", + "BriefDescription": "Bypass; BL - Credits", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Bypassed", - "EventCode": "0x5", - "EventName": "UNC_Q_TxL_BYPASSED", + "BriefDescription": "Bypass; IV", + "EventCode": "0x12", + "EventName": "UNC_S_RxR_BYPASS.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "PublicDescription": "Bypass the Sbo Ingress.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", - "EventCode": "0x2", - "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.ALMOST_FULL", + "BriefDescription": "Injection Starvation; AD - Bounces", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", - "EventCode": "0x2", - "EventName": "UNC_Q_TxL_CRC_NO_CREDITS.FULL", + "BriefDescription": "Injection Starvation; AD - Credits", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Cycles not Empty", - "EventCode": "0x6", - "EventName": "UNC_Q_TxL_CYCLES_NE", + "BriefDescription": "Injection Starvation; AK", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", - "EventName": "UNC_Q_TxL_FLITS_G0.DATA", + "BriefDescription": "Injection Starvation; BL - Bounces", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", - "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA", + "BriefDescription": "Injection Starvation; BL - Credits", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS", + "BriefDescription": "Injection Starvation; IVF Credit", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.IFV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", - "UMask": "0x18", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x40", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS_DATA", + "BriefDescription": "Injection Starvation; IV", + "EventCode": "0x14", + "EventName": "UNC_S_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Allocations; AD - Bounces", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x2", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Allocations; AD - Credits", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x1", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.DRS_NONDATA", + "BriefDescription": "Ingress Allocations; AK", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM", + "BriefDescription": "Ingress Allocations; BL - Bounces", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", - "UMask": "0x6", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM_NONREQ", + "BriefDescription": "Ingress Allocations; BL - Credits", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.HOM_REQ", + "BriefDescription": "Ingress Allocations; IV", + "EventCode": "0x13", + "EventName": "UNC_S_RxR_INSERTS.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", + "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Ingress Occupancy; AD - Bounces", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 1; SNP Flits", - "EventName": "UNC_Q_TxL_FLITS_G1.SNP", + "BriefDescription": "Ingress Occupancy; AD - Credits", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AD_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB", + "BriefDescription": "Ingress Occupancy; AK", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", - "UMask": "0xc", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB_DATA", + "BriefDescription": "Ingress Occupancy; BL - Bounces", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.BL_BNC", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCB_NONDATA", + "BriefDescription": "Ingress Occupancy; BL - Credits", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.BL_CRD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", - "UMask": "0x8", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NCS", + "BriefDescription": "Ingress Occupancy; IV", + "EventCode": "0x11", + "EventName": "UNC_S_RxR_OCCUPANCY.IV", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", - "UMask": "0x10", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AD", + "BriefDescription": "UNC_S_TxR_ADS_USED.AD", + "EventCode": "0x4", + "EventName": "UNC_S_TxR_ADS_USED.AD", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", - "EventCode": "0x1", - "EventName": "UNC_Q_TxL_FLITS_G2.NDR_AK", + "BriefDescription": "UNC_S_TxR_ADS_USED.AK", + "EventCode": "0x4", + "EventName": "UNC_S_TxR_ADS_USED.AK", "PerPkg": "1", - "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Allocations", + "BriefDescription": "UNC_S_TxR_ADS_USED.BL", "EventCode": "0x4", - "EventName": "UNC_Q_TxL_INSERTS", + "EventName": "UNC_S_TxR_ADS_USED.BL", "PerPkg": "1", - "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x7", - "EventName": "UNC_Q_TxL_OCCUPANCY", + "BriefDescription": "Egress Allocations; AD - Bounces", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AD_BNC", "PerPkg": "1", - "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x2", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", - "EventCode": "0x26", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Allocations; AD - Credits", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AD_CRD", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", - "EventCode": "0x26", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Allocations; AK", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.AK", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", - "EventCode": "0x22", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Allocations; BL - Bounces", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.BL_BNC", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", - "EventCode": "0x22", - "EventName": "UNC_Q_TxR_AD_HOM_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Egress Allocations; BL - Credits", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.BL_CRD", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", - "EventCode": "0x28", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Allocations; IV", + "EventCode": "0x2", + "EventName": "UNC_S_TxR_INSERTS.IV", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", + "UMask": "0x20", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", - "EventCode": "0x28", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Occupancy; AD - Bounces", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AD_BNC", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", - "EventCode": "0x24", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Occupancy; AD - Credits", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AD_CRD", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", - "EventCode": "0x24", - "EventName": "UNC_Q_TxR_AD_NDR_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Egress Occupancy; AK", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.AK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x10", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", - "EventCode": "0x27", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Egress Occupancy; BL - Bounces", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.BL_BNC", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", - "EventCode": "0x27", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Egress Occupancy; BL - Credits", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.BL_CRD", "PerPkg": "1", - "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", - "EventCode": "0x23", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Egress Occupancy; IV", + "EventCode": "0x1", + "EventName": "UNC_S_TxR_OCCUPANCY.IV", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", + "UMask": "0x20", + "Unit": "SBOX" + }, + { + "BriefDescription": "Injection Starvation; Onto AD Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.AD", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", - "EventCode": "0x23", - "EventName": "UNC_Q_TxR_AD_SNP_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Injection Starvation; Onto AK Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.AK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", - "EventCode": "0x29", - "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", + "BriefDescription": "Injection Starvation; Onto BL Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.BL", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", + "UMask": "0x4", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", - "EventCode": "0x25", - "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", + "BriefDescription": "Injection Starvation; Onto IV Ring", + "EventCode": "0x3", + "EventName": "UNC_S_TxR_STARVED.IV", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", + "UMask": "0x8", + "Unit": "SBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN0", + "BriefDescription": "UNC_U_CLOCKTICKS", + "EventName": "UNC_U_CLOCKTICKS", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN1", + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", - "EventCode": "0x2A", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_ACQUIRED.VN_SHR", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", - "UMask": "0x4", - "Unit": "QPI LL" + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", - "EventCode": "0x1F", - "EventName": "UNC_Q_TxR_BL_DRS_CREDIT_OCCUPANCY.VN_SHR", + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", - "EventCode": "0x2B", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", - "EventCode": "0x2B", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_ACQUIRED.VN1", + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Number outstanding register requests within message channel tracker", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", - "EventCode": "0x20", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", - "EventCode": "0x20", - "EventName": "UNC_Q_TxR_BL_NCB_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", - "EventCode": "0x2C", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN0", + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", - "EventCode": "0x2C", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_ACQUIRED.VN1", + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", "PerPkg": "1", - "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", - "EventCode": "0x21", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN0", + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", - "UMask": "0x1", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" }, { - "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", - "EventCode": "0x21", - "EventName": "UNC_Q_TxR_BL_NCS_CREDIT_OCCUPANCY.VN1", + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", "PerPkg": "1", - "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", - "UMask": "0x2", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" }, { - "BriefDescription": "VNA Credits Returned", - "EventCode": "0x1C", - "EventName": "UNC_Q_VNA_CREDIT_RETURNS", + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", "PerPkg": "1", - "PublicDescription": "Number of VNA credits returned.", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" }, { - "BriefDescription": "VNA Credits Pending Return - Occupancy", - "EventCode": "0x1B", - "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", "PerPkg": "1", - "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "QPI LL" + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-io.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-io.json new file mode 100644 index 000000000000..bd64a8a1625f --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-io.json @@ -0,0 +1,528 @@ +[ + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R2_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI0", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI1", + "EventCode": "0x2D", + "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; DRS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCB", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Dn", + "EventCode": "0x12", + "EventName": "UNC_R2_RING_AK_BOUNCES.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Up", + "EventCode": "0x12", + "EventName": "UNC_R2_RING_AK_BOUNCES.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0xc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x3", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For AD Ring", + "EventCode": "0x28", + "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Acquired; For BL Ring", + "EventCode": "0x28", + "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", + "EventCode": "0x2A", + "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.AD", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", + "EventCode": "0x2A", + "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.BL", + "PerPkg": "1", + "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", + "EventCode": "0x2C", + "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AD", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AK", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; BL", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AD", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AK", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; BL", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_AD", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_AK", + "PerPkg": "1", + "PublicDescription": "AK CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.DN_BL", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_AK", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.UP_BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json deleted file mode 100644 index d30e3b16c1af..000000000000 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-other.json +++ /dev/null @@ -1,3160 +0,0 @@ -[ - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Select Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Clocks in the IRP", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of clocks in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CLFlush", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.CRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; DRd", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.DRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIDCAHin5t", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIRdCur", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIItoM", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; RFO", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; WbMtoI", - "EventCode": "0x13", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Requests", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Requests", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "PublicDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch TimeOut", - "EventCode": "0x14", - "EventName": "UNC_I_MISC0.PF_TIMEOUT", - "PerPkg": "1", - "PublicDescription": "Indicates the fetch for a previous prefetch wasn't accepted by the prefetch. This happens in the case of a prefetch TimeOut", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Data Throttled", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.DATA_THROTTLE", - "PerPkg": "1", - "PublicDescription": "IRP throttled switch data", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Invalid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Valid", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", - "EventCode": "0x15", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Ingress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_RxR_AK_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "EventCode": "0x4", - "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - DRS", - "EventCode": "0x1", - "EventName": "UNC_I_RxR_BL_DRS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "EventCode": "0x7", - "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "EventCode": "0x5", - "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCB", - "EventCode": "0x2", - "EventName": "UNC_I_RxR_BL_NCB_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "EventCode": "0x8", - "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "EventCode": "0x6", - "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCS", - "EventCode": "0x3", - "EventName": "UNC_I_RxR_BL_NCS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "EventCode": "0x9", - "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit E or S", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit E or S", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit I", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit I", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit M", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Hit M", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Miss", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : Miss", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpCode", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpCode", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpData", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpData", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpInv", - "EventCode": "0x17", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "PublicDescription": "Snoop Responses : SnpInv", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Atomic", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Other", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.RD_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Write Prefetches", - "EventCode": "0x16", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of write prefetches.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x18", - "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x19", - "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xF", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xD", - "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R2_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.ISOCH_QPI1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI0", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "UNC_R2_IIO_CREDIT.PRQ_QPI1", - "EventCode": "0x2D", - "EventName": "UNC_R2_IIO_CREDIT.PRQ_QPI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; DRS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCB", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Dn", - "EventCode": "0x12", - "EventName": "UNC_R2_RING_AK_BOUNCES.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Up", - "EventCode": "0x12", - "EventName": "UNC_R2_RING_AK_BOUNCES.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Counterclockwise", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Clockwise", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x3", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCB", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCS", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For AD Ring", - "EventCode": "0x28", - "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For BL Ring", - "EventCode": "0x28", - "EventName": "UNC_R2_SBO0_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", - "EventCode": "0x2A", - "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", - "EventCode": "0x2A", - "EventName": "UNC_R2_SBO0_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO0_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R2_STALL_NO_SBO_CREDIT.SBO1_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AD", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AK", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; BL", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AD", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AK", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; BL", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AD CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_AD", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_AK", - "PerPkg": "1", - "PublicDescription": "AK CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.DN_BL", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_AD", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_AK", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.UP_BL", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R3_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14_16", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x1F", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO_15_17", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 15&17", - "UMask": "0x80", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x22", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", - "UMask": "0x80", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2D", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Backpressure", - "EventCode": "0xB", - "EventName": "UNC_R3_IOT_BACKPRESSURE.HUB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Backpressure", - "EventCode": "0xB", - "EventName": "UNC_R3_IOT_BACKPRESSURE.SAT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Hi", - "EventCode": "0xD", - "EventName": "UNC_R3_IOT_CTS_HI.CTS2", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Hi", - "EventCode": "0xD", - "EventName": "UNC_R3_IOT_CTS_HI.CTS3", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Lo", - "EventCode": "0xC", - "EventName": "UNC_R3_IOT_CTS_LO.CTS0", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "IOT Common Trigger Sequencer - Lo", - "EventCode": "0xC", - "EventName": "UNC_R3_IOT_CTS_LO.CTS1", - "PerPkg": "1", - "PublicDescription": "Debug Mask/Match Tie-Ins", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x20", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x21", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2E", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2F", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R3_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 IV Ring in Use; Clockwise", - "EventCode": "0xA", - "EventName": "UNC_R3_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x3", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ring Stop Starved; AK", - "EventCode": "0xE", - "EventName": "UNC_R3_RING_SINK_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles the ringstop is in starvation (per ring)", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; HOM", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NDR", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; SNP", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; DRS", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; HOM", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NCB", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NCS", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; NDR", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Cycles Not Empty; SNP", - "EventCode": "0x14", - "EventName": "UNC_R3_RxR_CYCLES_NE_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI VN1 Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; DRS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; HOM", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NDR", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; SNP", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; DRS", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; HOM", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NCB", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NCS", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; NDR", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Allocations; SNP", - "EventCode": "0x15", - "EventName": "UNC_R3_RxR_INSERTS_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI VN1 Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; HOM", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.HOM", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCB", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NCS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; NDR", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.NDR", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Ingress Occupancy Accumulator; SNP", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY_VN1.SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI VN1 Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI VN1 Ingress Not Empty event to calculate average occupancy or the QPI VN1 Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For AD Ring", - "EventCode": "0x28", - "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Acquired; For BL Ring", - "EventCode": "0x28", - "EventName": "UNC_R3_SBO0_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For AD Ring", - "EventCode": "0x2A", - "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo0 Credits Occupancy; For BL Ring", - "EventCode": "0x2A", - "EventName": "UNC_R3_SBO0_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 0 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Acquired; For AD Ring", - "EventCode": "0x29", - "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Acquired; For BL Ring", - "EventCode": "0x29", - "EventName": "UNC_R3_SBO1_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits acquired in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Occupancy; For AD Ring", - "EventCode": "0x2B", - "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.AD", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "SBo1 Credits Occupancy; For BL Ring", - "EventCode": "0x2B", - "EventName": "UNC_R3_SBO1_CREDIT_OCCUPANCY.BL", - "PerPkg": "1", - "PublicDescription": "Number of Sbo 1 credits in use in a given cycle, per ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo0, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO0_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, AD Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Stall on No Sbo Credits; For SBo1, BL Ring", - "EventCode": "0x2C", - "EventName": "UNC_R3_STALL_NO_SBO_CREDIT.SBO1_BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles Egress is stalled waiting for an Sbo credit to become available. Per Sbo, per Ring.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AD CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_AD", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_AK", - "PerPkg": "1", - "PublicDescription": "AK CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.DN_BL", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_AD", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_AK", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK.UP_BL", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; DRS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; HOM Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NDR Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; DRS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; HOM Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCB Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NDR Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; SNP Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; DRS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; HOM Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCB Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NDR Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; SNP Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Bounce Control", - "EventCode": "0xA", - "EventName": "UNC_S_BOUNCE_CONTROL", - "PerPkg": "1", - "Unit": "SBO" - }, - { - "BriefDescription": "Uncore Clocks", - "EventName": "UNC_S_CLOCKTICKS", - "PerPkg": "1", - "Unit": "SBO" - }, - { - "BriefDescription": "FaST wire asserted", - "EventCode": "0x9", - "EventName": "UNC_S_FAST_ASSERTED", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down and Event", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Down and Odd", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up and Even", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "AD Ring In Use; Up and Odd", - "EventCode": "0x1B", - "EventName": "UNC_S_RING_AD_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down and Event", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Down and Odd", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up and Even", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "AK Ring In Use; Up and Odd", - "EventCode": "0x1C", - "EventName": "UNC_S_RING_AK_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down and Event", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Event ring polarity.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Down and Odd", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.DOWN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up and Even", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Up and Odd", - "EventCode": "0x1D", - "EventName": "UNC_S_RING_BL_USED.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. We really have two rings in HSX -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.AD_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.AK_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.BL_CORE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", - "EventCode": "0x5", - "EventName": "UNC_S_RING_BOUNCES.IV_CORE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Any", - "EventCode": "0x1E", - "EventName": "UNC_S_RING_IV_USED.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", - "UMask": "0xc", - "Unit": "SBO" - }, - { - "BriefDescription": "BL Ring in Use; Any", - "EventCode": "0x1E", - "EventName": "UNC_S_RING_IV_USED.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. There is only 1 IV ring in HSX. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.; Filters any polarity", - "UMask": "0x3", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.AD_CACHE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.AD_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.AK_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.AK_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.BL_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.BL_CORE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_RING_SINK_STARVED.IV_CORE", - "EventCode": "0x6", - "EventName": "UNC_S_RING_SINK_STARVED.IV_CORE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Bounces", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Credits", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Bounces", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Credits", - "EventCode": "0x15", - "EventName": "UNC_S_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress because a message (credited/bounceable) is being sent.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AD - Bounces", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AD - Credits", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; AK", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; BL - Bounces", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; BL - Credits", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Bypass; IV", - "EventCode": "0x12", - "EventName": "UNC_S_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Bypass the Sbo Ingress.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Bounces", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AD - Credits", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; AK", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Bounces", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; BL - Credits", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; IVF Credit", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x40", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; IV", - "EventCode": "0x14", - "EventName": "UNC_S_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Ingress cannot send a transaction onto the ring for a long period of time. In this case, the Ingress but unable to forward to Egress due to lack of credit.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AD - Bounces", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AD - Credits", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; AK", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; BL - Bounces", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; BL - Credits", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Allocations; IV", - "EventCode": "0x13", - "EventName": "UNC_S_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Ingress The Ingress is used to queue up requests received from the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AD - Bounces", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AD - Credits", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; AK", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; BL - Bounces", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; BL - Credits", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Ingress Occupancy; IV", - "EventCode": "0x11", - "EventName": "UNC_S_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the Sbo. The Ingress is used to queue up requests received from the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.AD", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.AK", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_S_TxR_ADS_USED.BL", - "EventCode": "0x4", - "EventName": "UNC_S_TxR_ADS_USED.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AD - Bounces", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AD - Credits", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; AK", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; BL - Bounces", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; BL - Credits", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Allocations; IV", - "EventCode": "0x2", - "EventName": "UNC_S_TxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Sbo Egress. The Egress is used to queue up requests destined for the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AD - Bounces", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AD - Credits", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; AK", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x10", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; BL - Bounces", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; BL - Credits", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Egress Occupancy; IV", - "EventCode": "0x1", - "EventName": "UNC_S_TxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Sbo. The egress is used to queue up requests destined for the ring.", - "UMask": "0x20", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto AD Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.AD", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x1", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto AK Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x2", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto BL Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.BL", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x4", - "Unit": "SBO" - }, - { - "BriefDescription": "Injection Starvation; Onto IV Ring", - "EventCode": "0x3", - "EventName": "UNC_S_TxR_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", - "UMask": "0x8", - "Unit": "SBO" - }, - { - "BriefDescription": "UNC_U_CLOCKTICKS", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.CMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Livelock", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; LTError", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LTERROR", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T0", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T1", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Other", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.OTHER", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Trap", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.TRAP", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.UMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x20", - "Unit": "UBOX" - } -] -- GitLab From bc4a245a80eef3ac1f0ee33f1ee3217218e38f3e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:39 -0700 Subject: [PATCH 2999/5631] perf vendor events intel: Fix uncore topics for icelake Move events from 'uncore-other' topic classification to interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-12-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/icelake/uncore-interconnect.json | 74 +++++++++++++++++++ .../arch/x86/icelake/uncore-other.json | 72 ------------------ 2 files changed, 74 insertions(+), 72 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json new file mode 100644 index 000000000000..8027590f1776 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-interconnect.json @@ -0,0 +1,74 @@ +[ + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json index b27d95b2c857..c6596ba09195 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json @@ -1,76 +1,4 @@ [ - { - "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x80", - "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches", - "EventCode": "0x81", - "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches. This event is not supported on ICL products but is supported on RKL products.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, { "BriefDescription": "UNC_CLOCK.SOCKET", "EventCode": "0xff", -- GitLab From f42a7d02b7a3ce2531fef0ae89e474f0e0bbf0f9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:40 -0700 Subject: [PATCH 3000/5631] perf vendor events intel: Fix uncore topics for icelakex Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-13-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/icelakex/uncore-cache.json | 9860 +++++ .../x86/icelakex/uncore-interconnect.json | 14571 +++++++ .../arch/x86/icelakex/uncore-io.json | 9270 +++++ .../arch/x86/icelakex/uncore-other.json | 33697 ---------------- 4 files changed, 33701 insertions(+), 33697 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json create mode 100644 tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json new file mode 100644 index 000000000000..b6ce14ebf844 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json @@ -0,0 +1,9860 @@ +[ + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "Deprecated": "1", + "EventCode": "0x65", + "EventName": "UNC_CHA_2LM_NM_INVITOX.LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "Deprecated": "1", + "EventCode": "0x65", + "EventName": "UNC_CHA_2LM_NM_INVITOX.REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "Deprecated": "1", + "EventCode": "0x65", + "EventName": "UNC_CHA_2LM_NM_INVITOX.SETCONFLICT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", + "Deprecated": "1", + "EventCode": "0x64", + "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.LLC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", + "Deprecated": "1", + "EventCode": "0x64", + "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.SF", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", + "Deprecated": "1", + "EventCode": "0x64", + "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.TOR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "Deprecated": "1", + "EventCode": "0x70", + "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS2.MEMWR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "Deprecated": "1", + "EventCode": "0x70", + "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS2.MEMWRNI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the uncore caching and home agent (CHA)", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x12", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Counter 0 Occupancy", + "EventCode": "0x1F", + "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counter 0 Occupancy : Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline directory state lookups : Snoop Not Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Multi-socket cacheline directory state lookups : Snoop Not Needed : Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to. : Filters for transactions that did not have to send any snoops because the directory was clean.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline directory state lookups : Snoop Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Multi-socket cacheline directory state lookups : Snoop Needed : Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to. : Filters for transactions that had to send one or more snoops because the directory was not clean.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline directory state updates; memory write due to directory update from the home agent (HA) pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline directory state updates memory writes issued from the home agent (HA) pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline directory state updates; memory write due to directory update from (table of requests) TOR pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline directory state updates due to memory writes issued from the table of requests (TOR) pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : PMM Local", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.PMM_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : PMM Remote", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.PMM_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xBA", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xBA", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket ownership read requests that hit in S state.", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "PublicDescription": "Counts Number of Hits in HitMe Cache : Remote socket ownership read requests that hit in S state. : Shared hit and op is RdInvOwn, RdInv, Inv*", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket WBMtoE requests", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket writeback to I or S requests", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "PublicDescription": "Counts Number of Hits in HitMe Cache : Remote socket writeback to I or S requests : op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : Remote socket read requests", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.READ", + "PerPkg": "1", + "PublicDescription": "Counts Number of times HitMe Cache is accessed : Remote socket read requests : op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : Remote socket write (i.e. writeback) requests", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "PublicDescription": "Counts Number of times HitMe Cache is accessed : Remote socket write (i.e. writeback) requests : op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests that are not to shared line", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests that are not to shared line : No SF/LLC HitS/F and op is RdInvOwn", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket read or invalidate requests", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket read or invalidate requests : op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests to shared line", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests to shared line : SF/LLC HitS/F and op is RdInvOwn", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HitME$ on Reads without RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request : Received RspFwdI* for a local request, but converted HitME$ to SF entry", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache on RdInvOwn even if not RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request : Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache to SHARed", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xB9", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xB9", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued : ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Full Line Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1fffff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All transactions from Remote Agents", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All transactions from Remote Agents : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1e20ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE", + "PerPkg": "1", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_LOCAL", + "PerPkg": "1", + "UMask": "0x19d0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Code Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Code Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_LOCAL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x19d0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Code Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Code Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1a10ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ_REMOTE", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_REMOTE", + "PerPkg": "1", + "UMask": "0x1a10ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, including prefetches from the Core", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", + "PerPkg": "1", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", + "PerPkg": "1", + "UMask": "0x1fc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Read transactions.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x19c1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bc101", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Requests that come from a Remote socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1a01ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL", + "PerPkg": "1", + "UMask": "0x841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Exclusive State", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : F State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Forward State", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a44ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV_LOCAL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1844ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a04ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush or Invalidate Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : I State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.I", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Miss", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Prefetch requests to the LLC that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x189dff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local LLC prefetch to the LLC", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LLC_PF_LOCAL", + "PerPkg": "1", + "UMask": "0x189dff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOC_HOM", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCALLY_HOMED_ADDRESS", + "PerPkg": "1", + "UMask": "0xbdfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "UMask": "0xbdfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : M State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.M", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Modified State", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fe001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Write Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Writeback transactions to the LLC This includes all write transactions -- both Cacheable and UC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote non-snoop request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.PREF_OR_DMND_REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote non-snoop request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Non-snoop transactions to the LLC from remote agent", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x9d9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x11d9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally HOMed Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0xbd901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely HOMed Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x13d901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_OR_SNOOP_REMOTE_MISS_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x161901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_REMOTE_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0xa19ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Reads that Hit the Snoop Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_SF_HIT", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Reads that Hit the Snoop Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd90e", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REM_HOM", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTELY_HOMED_ADDRESS", + "PerPkg": "1", + "UMask": "0x15dfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote snoop request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote snoop request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Snoop transactions to the LLC from remote agent", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1c19ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "UMask": "0x15dfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1bc8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x19c8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bc801", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x888ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1a08ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Shared State", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - H State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit HitMe State", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Shared State", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x1a42ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", + "PerPkg": "1", + "UMask": "0x842ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_REMOTE", + "PerPkg": "1", + "UMask": "0x17c2ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : All Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.ALL", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : All Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0xf", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x200f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x800f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xE6", + "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xE6", + "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Off", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.OFF_PWRHEURISTIC", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Off : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READINVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.RFO_HITS_SNP_BCAST", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ADEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.AKEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ALLRSFWAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.BLEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.FSF_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLOWSNP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLWAYRSV", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_PAMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_WAYMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.HACREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IDX_INPIPE", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IPQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IRQ_PMM", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IRQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ISMQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IVEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.LLC_WAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.NOTALLOWSNOOP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ONE_FSF_VIC", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ONE_RSP_CON", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.PMM_MEMMODE_TORMATCH_MULTI", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.PMM_MEMMODE_TOR_MATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.PRQ_PMM", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.PTL_INPIPE", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.RMW_SETMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.RRQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.SETMATCHENTRYWSCT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.SF_WAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.TOPA_MATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.TORID_MATCH_GO_P", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_REQ", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_RSP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCB", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCS", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_RSP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_WB", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.WAY_MATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", + "PerPkg": "1", + "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC : NM evictions due to another read to the same near memory set in the LLC.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", + "PerPkg": "1", + "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC : NM evictions due to another read to the same near memory set in the SF.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in TOR", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", + "PerPkg": "1", + "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in TOR : No Reject in the CHA due to a pending read to the same near memory set in the TOR.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.REJ_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.REJ_IRQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "PerPkg": "1", + "PublicDescription": ": count # of FAST TOR Request inserted to ha_tor_req_fifo", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", + "PerPkg": "1", + "PublicDescription": ": count # of SLOW TOR Request inserted to ha_pmm_tor_req_fifo", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC10", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC10", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC10 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 10 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC11", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC11", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC11 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 11 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC12", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC12", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC12 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 12 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC13", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC13", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC13 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 13 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC6", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC6", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC6 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 6 only.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC7", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC7", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC7 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 7 only.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC8", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC8", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC8 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 8 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC9", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC9", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC9 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 9 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and remote INVITOE requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and are sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Remote INVITOE requests (exclusive ownership of a cache line without receiving data) sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Local read requests that miss the SF/LLC and remote read requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Local read requests that miss the SF/LLC and are sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Remote read requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Local write requests that miss the SF/LLC and remote write requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Local write requests that miss the SF/LLC and are sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Remote write requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_CHA_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IPQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IPQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : RRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : RRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : WBQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : WBQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IPQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : ANY0", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : HA", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IPQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : IPQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : RRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : RRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : WBQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : WBQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Allow Snoop", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : ANY0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : HA", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : SF Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : ANY0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : HA", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : ANY0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Any condition listed in the RRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : HA", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : HA : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : SF Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : ANY0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : HA", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : HA : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : SF Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_CHA_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to local requests", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to remote requests", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to local requests", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to remote requests", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to local requests", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Snoops sent for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Snoops sent for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to remote requests", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RSPCNFLCT*", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RSPCNFLCT* : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspFwd", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RspFwd : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*Fwd*WB", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*Fwd*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspI", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspIFwd", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspS", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspS Snoop Response was received which indicates when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspSFwd", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*WB", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspCnflct", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspI", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspIFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspS", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspSFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DDR4 Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DDR4 Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR4", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Hits", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushes issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushOpts issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushOpts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRDs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRDs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCRD", + "PerPkg": "1", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDRD", + "PerPkg": "1", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores that hit in the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from remote IA that misses in the snoop filter", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_DRAM", + "PerPkg": "1", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_DRAM", + "PerPkg": "1", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_DRAM", + "PerPkg": "1", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_DRAM", + "PerPkg": "1", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DRAM", + "PerPkg": "1", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DRAM", + "PerPkg": "1", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remote memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc3fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoIs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc37ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBMtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", + "PerPkg": "1", + "PublicDescription": "WbMtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc2fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBStoIs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", + "PerPkg": "1", + "PublicDescription": "WbStoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc67ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushes issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to locally HOMed memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd42ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to remotely HOMed memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd437f04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to locally HOMed memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc42ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to remotely HOMed memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc437f04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WbMtoIs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IPQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IPQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - Non iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just ISOC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Local Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Misses", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMCFG Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NonCoherent", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NotNearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PMM Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PMM Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - Non IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Remote Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Remote Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RRQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WBQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DDR4 Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DDR4 Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Hits", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRDs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRDs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores that missed the LLC: For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IPQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IPQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - Non iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just ISOC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Local Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA and IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Misses", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMCFG Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NonCoherent", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NotNearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PMM Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PMM Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Remote Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Remote Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xB3", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xB3", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC10", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC10", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC10 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 10 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC11", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC11", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC11 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 11 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC12", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC12", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC12 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 12 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC13", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC13", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC13 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 13 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC6", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC6", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC6 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 6 only.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC7", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC7", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC7 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 7 only.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC8", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC8", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC8 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 8 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC9", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC9", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC9 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 9 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 0?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT0", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 1?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT1", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", + "UMask": "0x10", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json new file mode 100644 index 000000000000..8ac5907762e1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json @@ -0,0 +1,14571 @@ +[ + { + "BriefDescription": "Total Write Cache Occupancy : Any Source", + "EventCode": "0x0F", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Total Write Cache Occupancy : Any Source : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events. : Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy : Snoops", + "EventCode": "0x0F", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", + "PerPkg": "1", + "PublicDescription": "Total Write Cache Occupancy : Snoops : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", + "EventCode": "0x0f", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops : CLFlush", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", + "PerPkg": "1", + "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.RFO", + "PerPkg": "1", + "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops : WbMtoI", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", + "PerPkg": "1", + "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Occupancy of the IRP FAF queue.", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.EVICTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Lost Forward", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Invalid", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Valid", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Requests", + "EventCode": "0x14", + "EventName": "UNC_I_P2P_INSERTS", + "PerPkg": "1", + "PublicDescription": "P2P Requests : P2P requests from the ITC", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Occupancy", + "EventCode": "0x15", + "EventName": "UNC_I_P2P_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "P2P Occupancy : P2P B & S Queue Occupancy", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P completions", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if local only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if local and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P Message", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P reads", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : Match if remote only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if remote and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P Writes", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Atomic", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Atomic : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Other", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Other : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Writes", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0x0B", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x05", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x02", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x08", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x06", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x03", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x09", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x07", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x04", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0x0A", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "EventCode": "0x1C", + "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0&AD1 both. Stalls on both AD0 and AD1 will count as 2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD0 Egress Credits Stalls", + "EventCode": "0x1A", + "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD1 Egress Credits Stalls", + "EventCode": "0x1B", + "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1D", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0D", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0E", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0x0C", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Not Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Not Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Clockticks of the mesh to memory (M2M)", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "EventCode": "0x60", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to PCI (M2P)", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in any state", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in A state", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in I state", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in S state", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates : From/to any state. Note: event counts are incorrect in 2LM mode.", + "EventCode": "0x2e", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : PMM Local", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.PMM_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : PMM Remote", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.PMM_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_DISTRESS_PMM", + "EventCode": "0xF2", + "EventName": "UNC_M2M_DISTRESS_PMM", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_DISTRESS_PMM_MEMMODE", + "EventCode": "0xF1", + "EventName": "UNC_M2M_DISTRESS_PMM_MEMMODE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xBA", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xBA", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xB9", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xB9", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x704", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_ALL", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", + "PerPkg": "1", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : PMM - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Reads Issued to iMC : PMM - Ch0 : Counts all PMM dimm read requests(full line) sent from M2M to iMC", + "UMask": "0x120", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_ALL", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", + "PerPkg": "1", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : PMM - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Reads Issued to iMC : PMM - Ch1 : Counts all PMM dimm read requests(full line) sent from M2M to iMC", + "UMask": "0x220", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch2", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH2_FROM_TGR", + "PerPkg": "1", + "UMask": "0x440", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x740", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x702", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x701", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x710", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : DDR - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x708", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : PMM - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.TO_PMM", + "PerPkg": "1", + "UMask": "0x720", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1c10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", + "PerPkg": "1", + "UMask": "0x410", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", + "PerPkg": "1", + "UMask": "0x401", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x404", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "PerPkg": "1", + "UMask": "0x402", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x408", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x440", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x420", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : PMM - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Writes Issued to iMC : PMM - Ch0 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x480", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", + "PerPkg": "1", + "UMask": "0x810", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", + "PerPkg": "1", + "UMask": "0x801", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", + "PerPkg": "1", + "UMask": "0x802", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x840", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x820", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : PMM - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_PMM", + "PerPkg": "1", + "PublicDescription": "M2M Writes Issued to iMC : PMM - Ch1 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x880", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1c01", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1c04", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1c02", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1c08", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x1c40", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : DDR - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x1c20", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : PMM - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", + "PerPkg": "1", + "UMask": "0x1c80", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts", + "EventCode": "0x64", + "EventName": "UNC_M2M_MIRR_WRQ_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x65", + "EventName": "UNC_M2M_MIRR_WRQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xE6", + "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xE6", + "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches : MC Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches : Mesh Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MESH", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", + "EventCode": "0x73", + "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : All Channels", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : Channel 0", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : Channel 1", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : Channel 2", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : All Channels", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 0", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 1", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 2", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA0_INVAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA1_INVAL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_MISS_INVAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_RSP_PDRESET", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA0_INVAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA1_INVAL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_MISS_INVAL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_RSP_PDRESET", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_HITA0_INVAL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_HITA1_INVAL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_MISS_INVAL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_RSP_PDRESET", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - Ch 0", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - Ch 0", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - Ch 1", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - Ch 1", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - Ch 2", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH2_UPI", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - Ch 2", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH2_XPT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", + "EventCode": "0x6f", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0x2a", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - All Channels", + "EventCode": "0x6f", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 0", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 0", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 1", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 2", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH2_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 2", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- All Channels", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPTUPI_ALLCH", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - All Channels", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 0", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 0", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 1", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 2", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH2_XPTUPI", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - All Channels", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPTUPI_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.ERRORBLK_RxC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.NOT_PF_SAD_REGION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_HIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_SECURE_DROP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.RPQ_PROXY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.STOP_B2B", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.UPI_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.WPQ_PROXY", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.XPT_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.ERRORBLK_RxC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.NOT_PF_SAD_REGION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_HIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_SECURE_DROP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.RPQ_PROXY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.STOP_B2B", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.UPI_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.WPQ_PROXY", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.XPT_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.ERRORBLK_RxC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.NOT_PF_SAD_REGION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_CAM_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_CAM_HIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_SECURE_DROP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.RPQ_PROXY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.STOP_B2B", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.UPI_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.WPQ_PROXY", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", + "EventCode": "0x72", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.XPT_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 2", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH2_UPI", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 2", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH2_XPT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "EventCode": "0x6d", + "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0x2a", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 2", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": ": All Channels", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 2", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", + "EventCode": "0x79", + "EventName": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_INSERTS", + "EventCode": "0x78", + "EventName": "UNC_M2M_PREFCAM_RxC_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "EventCode": "0x77", + "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_M2M_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 2", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 0", + "EventCode": "0x4F", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 1", + "EventCode": "0x4F", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 2", + "EventCode": "0x4F", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 2", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Full", + "EventCode": "0x04", + "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Not Empty", + "EventCode": "0x03", + "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Allocations", + "EventCode": "0x01", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x02", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", + "EventCode": "0x77", + "EventName": "UNC_M2M_RxC_AD_PREF_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x5C", + "EventName": "UNC_M2M_RxC_AK_WR_CMP", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Full", + "EventCode": "0x08", + "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Not Empty", + "EventCode": "0x07", + "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "EventCode": "0x05", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x06", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_M2M_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_SCOREBOARD_AD_RETRY_ACCEPTS", + "EventCode": "0x33", + "EventName": "UNC_M2M_SCOREBOARD_AD_RETRY_ACCEPTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_SCOREBOARD_AD_RETRY_REJECTS", + "EventCode": "0x34", + "EventName": "UNC_M2M_SCOREBOARD_AD_RETRY_REJECTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Retry - Mem Mirroring Mode", + "EventCode": "0x35", + "EventName": "UNC_M2M_SCOREBOARD_BL_RETRY_ACCEPTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Retry - Mem Mirroring Mode", + "EventCode": "0x36", + "EventName": "UNC_M2M_SCOREBOARD_BL_RETRY_REJECTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Scoreboard Accepts", + "EventCode": "0x2F", + "EventName": "UNC_M2M_SCOREBOARD_RD_ACCEPTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Scoreboard Rejects", + "EventCode": "0x30", + "EventName": "UNC_M2M_SCOREBOARD_RD_REJECTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Scoreboard Accepts", + "EventCode": "0x31", + "EventName": "UNC_M2M_SCOREBOARD_WR_ACCEPTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Scoreboard Rejects", + "EventCode": "0x32", + "EventName": "UNC_M2M_SCOREBOARD_WR_REJECTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Clean NearMem Read Hit", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit : Clean NearMem Read Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean full line read hits (reads and RFOs).", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Dirty NearMem Read Hit", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit : Dirty NearMem Read Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty full line read hits (reads and RFOs).", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Clean NearMem Underfill Hit", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit : Clean NearMem Underfill Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean underfill hits due to a partial write", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Dirty NearMem Underfill Hit", + "EventCode": "0x2C", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit : Dirty NearMem Underfill Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty underfill read hits due to a partial write", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Miss", + "EventCode": "0x61", + "EventName": "UNC_M2M_TAG_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x41", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x42", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full : Channel 0", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full : Channel 1", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full : Channel 2", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 2", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty : Channel 2", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 2", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credit Acquired", + "EventCode": "0x0d", + "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credits Occupancy", + "EventCode": "0x0e", + "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Full", + "EventCode": "0x0c", + "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Not Empty", + "EventCode": "0x0b", + "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "EventCode": "0x09", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", + "EventCode": "0x0f", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", + "EventCode": "0x10", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0x0A", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK : CRD Transactions to Cbo", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.CRD_CBO", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK : NDR Transactions", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.NDR", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AKC Credits", + "EventCode": "0x5F", + "EventName": "UNC_M2M_TxC_AKC_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : All", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Near Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Far Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : All", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : All", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Near Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Far Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : All", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Cache", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Core", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to QPI", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : All", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Near Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Far Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : All", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : All", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Near Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Far Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xB3", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xB3", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x58", + "EventName": "UNC_M2M_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x58", + "EventName": "UNC_M2M_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 2", + "EventCode": "0x58", + "EventName": "UNC_M2M_WPQ_FLUSH.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 0", + "EventCode": "0x51", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 1", + "EventCode": "0x51", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 2", + "EventCode": "0x51", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Channel 0", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Channel 1", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Channel 2", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Mirror", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 2", + "EventCode": "0x56", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 2", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x63", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x63", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 2", + "EventCode": "0x63", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x62", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x62", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 2", + "EventCode": "0x62", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Channel 0", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Channel 1", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Channel 2", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Mirror", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x5E", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x5E", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 2", + "EventCode": "0x5E", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x5D", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x5D", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 2", + "EventCode": "0x5D", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8B", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8B", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8B", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8D", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8D", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8D", + "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8F", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8F", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8F", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Requests", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Requests : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Snoops", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Snoops : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : VNA Messages", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : VNA Messages : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Writebacks", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Writebacks : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Clockticks of the mesh to UPI (M3UPI)", + "EventCode": "0x01", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to UPI (M3UPI) : Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "EventCode": "0x2B", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "PublicDescription": "D2C Sent : Count cases BL sends direct to core", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "EventCode": "0x2A", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "PublicDescription": "D2U Sent : Cases where SMI3 sends D2U command", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : PMM Local", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.PMM_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : PMM Remote", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.PMM_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xAF", + "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xBA", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xBA", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xB6", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xB6", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xBB", + "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xBB", + "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xB7", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xB7", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xB8", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xB8", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xB9", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xB9", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO1_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only) : No vn0 and vna credits available to send to M2", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO2", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO2 : No vn0 and vna credits available to send to M2", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO3", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO3 : No vn0 and vna credits available to send to M2", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO4", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO4 : No vn0 and vna credits available to send to M2", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together : No vn0 and vna credits available to send to M2", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits : No vn0 and vna credits available to send to M2", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.UBOX_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xE6", + "EventName": "UNC_M3UPI_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xE6", + "EventName": "UNC_M3UPI_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 1", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 1 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : BL - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : BL - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_M3UPI_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : REQ on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : REQ on AD : VN0 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on AD : VN0 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : SNP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : SNP on AD : VN0 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCB on BL : VN0 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCS on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCS on BL : VN0 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on BL : VN0 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : WB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : WB on BL : VN0 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : REQ on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : REQ on AD : VN1 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on AD : VN1 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : SNP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : SNP on AD : VN1 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCB on BL : VN1 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCS on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCS on BL : VN1 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on BL : VN1 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : WB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : WB on BL : VN1 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : Max Parallel Win", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ALL_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : Max Parallel Win : VN0 and VN1 arbitration sub-pipelines both produced AD and BL winners (maximum possible parallel winners)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN0 : Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN1 : Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN0 : Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN1 : Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.VN01_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win : VN0 and VN1 arbitration sub-pipelines had parallel winners (at least one AD or BL on each side)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : REQ on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : REQ on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : SNP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : SNP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCS on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCS on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : WB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : WB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : REQ on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : REQ on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : SNP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : SNP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCS on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCS on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : WB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : WB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : REQ on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : REQ on AD : VN0 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : SNP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : SNP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCS on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCS on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on BL : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : WB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : WB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : REQ on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : REQ on AD : VN1 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : SNP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : SNP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCS on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCS on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on BL : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : WB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : WB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 1", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 1 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 2", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 2 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any In BGF FIFO", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any In BGF FIFO : Indication that at least one packet (flit) is in the bgf (fifo only)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any in BGF Path", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any in BGF Path : Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT1_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT2_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : No D2K For Arb", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN0_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : No D2K For Arb : VN0 BL RSP message was blocked from arbitration request due to lack of D2K CMP credit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN1_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Credits Consumed", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.CONSUMED", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Credits Consumed : number of remote vna credits consumed per cycle", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : D2K Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : D2K Credits : D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF FIFO", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF FIFO : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF Path", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF Path : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in completion fifo only", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in marker table and in fifo", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Transmit Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Transmit Credits : Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : VNA In Use", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : VNA In Use : Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : All", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : All : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but could not be sent for any reason, e.g. low credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No BGF Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_BGF", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No BGF Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No TxQ Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_TXQ", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No TxQ Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : TSV High", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : TSV High : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : Cycle valid for Flit", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : Cycle valid for Flit : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 0", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 0 : generating bl data flit sequence; waiting for data pump 0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is tracking at least one message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending completion fifo is full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : a bl message finished but is in limbo and moved to pump-1-pending logic", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 1", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 1 : generating bl data flit sequence; waiting for data pump 1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "PerPkg": "1", + "PublicDescription": ": slot 2 request naturally serviced during hold-off period", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "PerPkg": "1", + "PublicDescription": ": slot 2 request forcibly serviced during service window", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "PerPkg": "1", + "PublicDescription": ": slot 2 request received from link layer while idle (with no slot 2 request active immediately prior)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "PerPkg": "1", + "PublicDescription": ": slot 2 request withdrawn during hold-off period or service window", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : All", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Needs Data Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Needs Data Flit : BL message requires data flit sequence", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0 : Waiting for header pump 0", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 : Header pump 1 is not required for flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble : Header pump 1 is not required for flit but flit transmission delayed", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail : Header pump 1 is not required for flit and not available", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1 : Waiting for header pump 1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate : Events related to Header Flit Generation - Set 1 : Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Ready", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Ready : Events related to Header Flit Generation - Set 1 : header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Wasted", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Wasted : Events related to Header Flit Generation - Set 1 : Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked : Events related to Header Flit Generation - Set 1 : Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: message was slotted only after run-ahead was over; run-ahead mode definitely wasted", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Message", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_DURING", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Message : Events related to Header Flit Generation - Set 1 : run-ahead mode: one message slotted during run-ahead", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: second message slotted immediately after run-ahead; potential run-ahead success", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_SENT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: two (or three) message flit sent immediately after run-ahead; complete run-ahead success", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Ok", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Ok : Events related to Header Flit Generation - Set 2 : new header flit construction may proceed in parallel with data flit sequence", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Flit Finished", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_FLIT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Flit Finished : Events related to Header Flit Generation - Set 2 : header flit finished assembly in parallel with data flit sequence", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_MSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Message : Events related to Header Flit Generation - Set 2 : message is slotted into header flit in parallel with data flit sequence", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall : Events related to Header Flit Generation - Set 2 : Rate-matching stall injected", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message : Events related to Header Flit Generation - Set 2 : Rate matching stall injected, but no additional message slotted during stall cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message : One message in flit; VNA or non-VNA flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message in non-VNA", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG_VNX", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message in non-VNA : One message in flit; non-VNA flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.2_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Two Messages : Two messages in flit; VNA flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Three Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.3_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Three Messages : Three messages in flit; VNA flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Slot Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_2", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : All Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_3", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : All", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : All : header flit is ready for transmission but could not be sent : header flit is ready for transmission but could not be sent for any reason, e.g. no credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits : header flit is ready for transmission but could not be sent : No BGF credits available", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No BGF credits available; no additional message slotted into flit", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits : header flit is ready for transmission but could not be sent : No TxQ credits available", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No TxQ credits available; no additional message slotted into flit", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : TSV High", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : TSV High : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : Cycle valid for Flit", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : Cycle valid for Flit : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot AD : some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot BL : some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Attempt", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Attempt : ad and bl messages attempted to slot into the same flit in parallel", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Success", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN0", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN0", + "PerPkg": "1", + "PublicDescription": "Message Held : VN0 : vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN1", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN1", + "PerPkg": "1", + "PublicDescription": "Message Held : VN1 : vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : REQ on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : REQ on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : SNP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : SNP on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCB on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCS on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCS on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : WB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : WB on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : REQ on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : REQ on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : SNP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : SNP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCS on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCS on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : WB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : WB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : REQ on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : REQ on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : SNP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : SNP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCS on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCS on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : WB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : WB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : REQ on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : REQ on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : SNP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : SNP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCS on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCS on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : WB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : WB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : REQ on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : SNP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCS on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : WB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : REQ on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : SNP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCS on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : WB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Any In Use", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Any In Use : At least one remote vna credit is in use", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Corrected", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Corrected : Number of remote vna credits corrected (local return) per cycle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 1", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 1 : Remote vna credit level is less than 1 (i.e. no vna credits available)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 10", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT10", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 10 : remote vna credit level is less than 10; parallel vn0/vn1 arb not possible", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 4", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 4 : Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 5", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 5 : Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 5 and allocation to ad or bl messages was required", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 10 and allocation to vn0 or vn1 was required", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn0, not to vn1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn1, not to vn0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xE2", + "EventName": "UNC_M3UPI_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xE3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xE1", + "EventName": "UNC_M3UPI_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xE0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD1", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD1", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD1", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD3", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD3", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD3", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD5", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD5", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD5", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD7", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD7", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD7", + "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Inserts", + "EventCode": "0x2F", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Occupancy", + "EventCode": "0x1E", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_THROUGH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_WRPULL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_LOCAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_THROUGH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1F", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_WRPULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VNA", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VNA : No credits available to send to UPIs on the AD Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VNA", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VNA : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FlowQ Generated Prefetch", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xB5", + "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xB5", + "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : WB on BL", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : WB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : NCB on BL", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : NCB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : REQ on AD", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : REQ on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on AD", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : SNP on AD", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : SNP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on BL", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : WB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : WB on BL : Number of Cycles there were no VN0 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : NCB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : NCB on BL : Number of Cycles there were no VN0 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : REQ on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : REQ on AD : Number of Cycles there were no VN0 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on AD : Number of Cycles there were no VN0 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : SNP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : SNP on AD : Number of Cycles there were no VN0 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on BL : Number of Cycles there were no VN0 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : WB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : WB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : NCB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : NCB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : REQ on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : REQ on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : SNP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : SNP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : WB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : WB on BL : Number of Cycles there were no VN1 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : NCB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : NCB on BL : Number of Cycles there were no VN1 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : REQ on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : REQ on AD : Number of Cycles there were no VN1 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on AD : Number of Cycles there were no VN1 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : SNP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : SNP on AD : Number of Cycles there were no VN1 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on BL : Number of Cycles there were no VN1 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xc0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "EventCode": "0x7E", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "EventCode": "0x7D", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message is making arbitration request", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message arrived in ingress pipeline", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message took bypass path", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was slotted into flit (non bypass)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message lost arbitration", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it became too old", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it was overwritten by new message while prefetch queue was full", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of kfclks", + "EventCode": "0x01", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of kfclks : Counts the number of clocks in the UPI LL. This clock runs at 1/8th the GT/s speed of the UPI link. For example, a 8GT/s link will have qfclk or 1GHz. Current products do not support dynamic link speeds, so this frequency is fixed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2C", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2C : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2K", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2K : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L1", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L1 : Number of UPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a UPI link. Use edge detect to count the number of instances when the UPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "EventCode": "0x16", + "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", + "EventCode": "0x20", + "EventName": "UNC_UPI_PHY_INIT_CYCLES", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req Nack", + "EventCode": "0x23", + "EventName": "UNC_UPI_POWER_L1_NACK", + "PerPkg": "1", + "PublicDescription": "L1 Req Nack : Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req (same as L1 Ack).", + "EventCode": "0x22", + "EventName": "UNC_UPI_POWER_L1_REQ", + "PerPkg": "1", + "PublicDescription": "L1 Req (same as L1 Ack). : Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x24", + "EventName": "UNC_UPI_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Request", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Request : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - Conflict", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - Conflict : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - Invalid", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - Invalid : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - Data", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - No Data", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Snoop", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Snoop : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Writeback", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Writeback : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 0 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 1 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 2 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "CRC Errors Detected", + "EventCode": "0x0B", + "EventName": "UNC_UPI_RxL_CRC_ERRORS", + "PerPkg": "1", + "PublicDescription": "CRC Errors Detected : Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", + "Unit": "UPI" + }, + { + "BriefDescription": "LLR Requests Sent", + "EventCode": "0x08", + "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", + "PerPkg": "1", + "PublicDescription": "LLR Requests Sent : Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN0 Credit Consumed", + "EventCode": "0x39", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Consumed : Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN1 Credit Consumed", + "EventCode": "0x3A", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Consumed : Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x38", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", + "PerPkg": "1", + "PublicDescription": "VNA Credit Consumed : Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Null FLITs received from any slot", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Null FLITs received from any slot : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Null FLITs received from any slot", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Null FLITs received from any slot : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCRD Not Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCTRL", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Non Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Protocol Header", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 0", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 1", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 2", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 0 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 1 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 2 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 0 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 1 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 2 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x26", + "EventName": "UNC_UPI_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Request", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Request : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Conflict", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Conflict : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Invalid", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Invalid : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Data", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - No Data", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Snoop", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Writeback", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Bypassed : Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the UPI Link. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Null FLITs transmitted to any slot", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Null FLITs transmitted to any slot : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Idle", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Idle : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCTRL", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Non Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Protocol Header", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 0", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 1", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 2", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "EventCode": "0x45", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x44", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "VNA Credits Pending Return - Occupancy : Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Doorbell", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Interrupt", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Message Received : Interrupt : Interrupts", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "IDI Lock/SplitLock Cycles : Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "EventCode": "0x4F", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "EventCode": "0x4F", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json new file mode 100644 index 000000000000..9cef8862c428 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json @@ -0,0 +1,9270 @@ +[ + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", + "PerPkg": "1", + "UMask": "0x23", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", + "PerPkg": "1", + "UMask": "0x25", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", + "PerPkg": "1", + "UMask": "0x26", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the integrated IO (IIO) traffic controller : Increments counter once every Traffic Controller clock, the LSCLK (500MHz)", + "Unit": "IIO" + }, + { + "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", + "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", + "PerPkg": "1", + "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", + "UMask": "0x10", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 1", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 2", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 3", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 3 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 4", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 4 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 5", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 5 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 6", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 6 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 7 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Passing data to be written", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Request Ownership", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Writing line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Request Ownership", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Writing line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 1G Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.1G_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 2M Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.2M_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 4K Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.4K_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups all", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.ALL_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": IOTLB lookups all : Some transactions have to look up IOTLB multiple times. Counts every time a request looks up IOTLB.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache hits", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", + "PerPkg": "1", + "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache lookups", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups first", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Fills (same as IOTLB miss)", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.MISSES", + "PerPkg": "1", + "PublicDescription": ": IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Cycles PWT full", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.CYC_PWT_FULL", + "PerPkg": "1", + "PublicDescription": ": Cycles PWT full : Counts cycles the IOMMU has reached its maximum limit for outstanding page walks.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOMMU memory access", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", + "PerPkg": "1", + "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 4K page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_4K_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWT Hit to a 256T page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache fill", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache lookup", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Interrupt Entry cache hit", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.INT_CACHE_HITS", + "PerPkg": "1", + "PublicDescription": ": Interrupt Entry cache hit : Counts each time a transaction's first look up hits the IEC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Interrupt Entry cache lookup", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.INT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": Interrupt Entry cache lookup : Counts the number of transaction looks up that interrupt remapping cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": Device-selective Context cache invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DEVICE", + "PerPkg": "1", + "PublicDescription": ": Device-selective Context cache invalidation cycles : Counts number of Device selective context cache invalidation events", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Domain-selective Context cache invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DOMAIN", + "PerPkg": "1", + "PublicDescription": ": Domain-selective Context cache invalidation cycles : Counts number of Domain selective context cache invalidation events", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache global invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_GBL", + "PerPkg": "1", + "PublicDescription": ": Context cache global invalidation cycles : Counts number of Context Cache global invalidation events", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Domain-selective IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_DOMAIN", + "PerPkg": "1", + "PublicDescription": ": Domain-selective IOTLB invalidation cycles : Counts number of Domain selective invalidation events", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Global IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_GBL", + "PerPkg": "1", + "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Page-selective IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_PAGE", + "PerPkg": "1", + "PublicDescription": ": Page-selective IOTLB invalidation cycles : Counts number of Page-selective within Domain Invalidation events", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Counting disabled", + "EventCode": "0x80", + "EventName": "UNC_IIO_NOTHING", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Occupancy of outbound request queue : To device", + "EventCode": "0xC5", + "EventName": "UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Passing data to be written", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Passing data to be written : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Issuing final read or write of line", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Processing response from IOMMU", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Issuing to IOMMU", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Request Ownership", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Request Ownership : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": Writing line", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Writing line : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : From IRP", + "EventCode": "0xC2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : From ITC", + "EventCode": "0xC2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests sent to PCIe from main die : From ITC : Confined P2P", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : Completion allocations", + "EventCode": "0xc2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.PREALLOC", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : Drop request", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.ALL.DROP", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests PCIe makes of the main die : Drop request : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU. : Packet error detected, must be dropped", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : All", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Abort", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Memory", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : MsgB", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Ubox", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "ITC address map 1", + "EventCode": "0x8F", + "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", + "EventCode": "0xD0", + "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", + "EventCode": "0xD1", + "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PWT occupancy", + "EventCode": "0x42", + "EventName": "UNC_IIO_PWT_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Passing data to be written", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Issuing final read or write of line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Request Ownership", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Writing line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Passing data to be written", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Issuing final read or write of line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Processing response from IOMMU", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Processing response from IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Issuing to IOMMU", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Issuing to IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Request Ownership", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Writing line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Passing data to be written", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Request Ownership", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Writing line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Symbol Times on Link", + "EventCode": "0x82", + "EventName": "UNC_IIO_SYMBOL_TIMES", + "PerPkg": "1", + "PublicDescription": "Symbol Times on Link : Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Clockticks of the mesh to PCI (M2P)", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to PCI (M2P) : Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2P_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : PMM Local", + "EventCode": "0xAF", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.PMM_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : PMM Remote", + "EventCode": "0xAF", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.PMM_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xb9", + "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xb9", + "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent0", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent1", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent2", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xe6", + "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xe6", + "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : All", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : All", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : All", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - DRS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCB", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_M2P_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_M2P_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PMM", + "EventCode": "0x2D", + "EventName": "UNC_M2P_TxC_CREDITS.PMM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9e", + "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9e", + "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xb3", + "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xb3", + "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json deleted file mode 100644 index 134b54da0869..000000000000 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-other.json +++ /dev/null @@ -1,33697 +0,0 @@ -[ - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", - "Deprecated": "1", - "EventCode": "0x65", - "EventName": "UNC_CHA_2LM_NM_INVITOX.LOCAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", - "Deprecated": "1", - "EventCode": "0x65", - "EventName": "UNC_CHA_2LM_NM_INVITOX.REMOTE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", - "Deprecated": "1", - "EventCode": "0x65", - "EventName": "UNC_CHA_2LM_NM_INVITOX.SETCONFLICT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", - "Deprecated": "1", - "EventCode": "0x64", - "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.LLC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", - "Deprecated": "1", - "EventCode": "0x64", - "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.SF", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", - "Deprecated": "1", - "EventCode": "0x64", - "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS.TOR", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", - "Deprecated": "1", - "EventCode": "0x70", - "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS2.MEMWR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", - "Deprecated": "1", - "EventCode": "0x70", - "EventName": "UNC_CHA_2LM_NM_SETCONFLICTS2.MEMWRNI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Not Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Clockticks of the uncore caching and home agent (CHA)", - "EventName": "UNC_CHA_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_CHA_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xf2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xf1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.REMOTE_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x12", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.REMOTE_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Counter 0 Occupancy", - "EventCode": "0x1F", - "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Counter 0 Occupancy : Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline directory state lookups : Snoop Not Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "PublicDescription": "Multi-socket cacheline directory state lookups : Snoop Not Needed : Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to. : Filters for transactions that did not have to send any snoops because the directory was clean.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline directory state lookups : Snoop Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.SNP", - "PerPkg": "1", - "PublicDescription": "Multi-socket cacheline directory state lookups : Snoop Needed : Counts the number of transactions that looked up the directory. Can be filtered by requests that had to snoop and those that did not have to. : Filters for transactions that had to send one or more snoops because the directory was not clean.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline directory state updates; memory write due to directory update from the home agent (HA) pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.HA", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline directory state updates memory writes issued from the home agent (HA) pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline directory state updates; memory write due to directory update from (table of requests) TOR pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.TOR", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline directory state updates due to memory writes issued from the table of requests (TOR) pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : PMM Local", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.PMM_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : PMM Remote", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.PMM_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xBA", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xBA", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.EX_RDS", - "PerPkg": "1", - "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket ownership read requests that hit in S state.", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", - "PerPkg": "1", - "PublicDescription": "Counts Number of Hits in HitMe Cache : Remote socket ownership read requests that hit in S state. : Shared hit and op is RdInvOwn, RdInv, Inv*", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket WBMtoE requests", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache : Remote socket writeback to I or S requests", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", - "PerPkg": "1", - "PublicDescription": "Counts Number of Hits in HitMe Cache : Remote socket writeback to I or S requests : op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed : Remote socket read requests", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.READ", - "PerPkg": "1", - "PublicDescription": "Counts Number of times HitMe Cache is accessed : Remote socket read requests : op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed : Remote socket write (i.e. writeback) requests", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", - "PerPkg": "1", - "PublicDescription": "Counts Number of times HitMe Cache is accessed : Remote socket write (i.e. writeback) requests : op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests that are not to shared line", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", - "PerPkg": "1", - "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests that are not to shared line : No SF/LLC HitS/F and op is RdInvOwn", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket read or invalidate requests", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", - "PerPkg": "1", - "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket read or invalidate requests : op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests to shared line", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", - "PerPkg": "1", - "PublicDescription": "Counts Number of Misses in HitMe Cache : Remote socket RdInvOwn requests to shared line : SF/LLC HitS/F and op is RdInvOwn", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HitME$ on Reads without RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request : Received RspFwdI* for a local request, but converted HitME$ to SF entry", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache on RdInvOwn even if not RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", - "PerPkg": "1", - "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request : Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache to SHARed", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.SHARED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xB9", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xB9", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "HA to iMC Reads Issued : ISOCH", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : Full Line Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to any of the memory controller channels.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x1fffff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : All transactions from Remote Agents", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ALL_REMOTE", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : All transactions from Remote Agents : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1e20ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : All Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : All Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE", - "PerPkg": "1", - "UMask": "0x1bd0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_LOCAL", - "PerPkg": "1", - "UMask": "0x19d0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Code Reads", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Code Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : CRd Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : CRd Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : CRd Requests that come from the local socket (usually the core)", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_LOCAL", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", - "UMask": "0x19d0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Code Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Code Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd001", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : CRd Requests that come from a Remote socket.", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_REMOTE", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", - "UMask": "0x1a10ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ_REMOTE", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_REMOTE", - "PerPkg": "1", - "UMask": "0x1a10ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Local request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Local request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, including prefetches from the Core", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", - "PerPkg": "1", - "UMask": "0x1bc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x1bc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", - "PerPkg": "1", - "UMask": "0x1fc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Data Read Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Data Read Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Read transactions.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request that come from the local socket (usually the core)", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x19c1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Data Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bc101", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Requests that come from a Remote socket", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x1a01ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL", - "PerPkg": "1", - "UMask": "0x841ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : E State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.E", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Exclusive State", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : F State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Forward State", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", - "UMask": "0x1a44ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate Requests that come from the local socket (usually the core)", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV_LOCAL", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", - "UMask": "0x1844ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate requests that come from a Remote socket.", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV_REMOTE", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", - "UMask": "0x1a04ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush or Invalidate Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : I State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.I", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Miss", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Prefetch requests to the LLC that come from the local socket (usually the core)", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x189dff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local LLC prefetch to the LLC", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LLC_PF_LOCAL", - "PerPkg": "1", - "UMask": "0x189dff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOC_HOM", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOCALLY_HOMED_ADDRESS", - "PerPkg": "1", - "UMask": "0xbdfff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Transactions homed locally Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Transactions homed locally Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Transactions homed locally", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", - "UMask": "0xbdfff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : M State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.M", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Modified State", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : All Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : All Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1fe001", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Write Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Write Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Writeback transactions to the LLC This includes all write transactions -- both Cacheable and UC.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remote non-snoop request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.PREF_OR_DMND_REMOTE_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remote non-snoop request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Non-snoop transactions to the LLC from remote agent", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Reads", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x9d9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x11d9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally HOMed Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0xbd901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely HOMed Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x13d901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_OR_SNOOP_REMOTE_MISS_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x161901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_REMOTE_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0xa19ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Reads that Hit the Snoop Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_SF_HIT", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Reads that Hit the Snoop Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd90e", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REM_HOM", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTELY_HOMED_ADDRESS", - "PerPkg": "1", - "UMask": "0x15dfff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Transactions homed remotely Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Transactions homed remotely Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remote snoop request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remote snoop request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Snoop transactions to the LLC from remote agent", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x1c19ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Transactions homed remotely", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", - "UMask": "0x15dfff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "UMask": "0x1bc8ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Requests that come from the local socket (usually the core)", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_LOCAL", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "UMask": "0x19c8ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bc801", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL", - "PerPkg": "1", - "UMask": "0x888ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Requests that come from a Remote socket.", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_REMOTE", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "UMask": "0x1a08ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : S State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.S", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Shared State", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - E State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - H State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit HitMe State", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - S State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Shared State", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", - "UMask": "0x1a42ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", - "PerPkg": "1", - "UMask": "0x842ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_REMOTE", - "PerPkg": "1", - "UMask": "0x17c2ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : All Lines Victimized", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.ALL", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : All Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0xf", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in E state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x200f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2002", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2001", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local Only", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2004", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in M state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Remote - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Remote - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x800f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Remote - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Remote - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8002", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Remote - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Remote - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8001", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Remote Only", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ONLY", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Remote Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Remote - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Remote - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8004", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Number of times that an RFO hit in S state.", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RFO_HIT_S", - "PerPkg": "1", - "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : Silent Snoop Eviction", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : Write Combining Aliasing", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.WC_ALIASING", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xE6", - "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xE6", - "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Local InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Local Rd", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.LOCAL_READ", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Local Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Off", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.OFF_PWRHEURISTIC", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Off : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Remote Rd", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.REMOTE_READ", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Remote Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : Remote Rd InvItoE", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.REMOTE_READINVITOE", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : Remote Rd InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB.RFO_HITS_SNP_BCAST", - "PerPkg": "1", - "PublicDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ADEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.AKEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ALLRSFWAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.BLEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.FSF_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLOWSNP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLWAYRSV", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_PAMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_WAYMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.HACREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IDX_INPIPE", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IPQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IRQ_PMM", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IRQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ISMQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IVEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.LLC_WAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.NOTALLOWSNOOP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ONE_FSF_VIC", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ONE_RSP_CON", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.PMM_MEMMODE_TORMATCH_MULTI", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.PMM_MEMMODE_TOR_MATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.PRQ_PMM", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.PTL_INPIPE", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.RMW_SETMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.RRQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.SETMATCHENTRYWSCT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.SF_WAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.TOPA_MATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.TORID_MATCH_GO_P", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_REQ", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_RSP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCB", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCS", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_RSP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_WB", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.WAY_MATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", - "EventCode": "0x65", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", - "EventCode": "0x65", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", - "EventCode": "0x65", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", - "PerPkg": "1", - "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC : NM evictions due to another read to the same near memory set in the LLC.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", - "PerPkg": "1", - "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in SF/LLC : NM evictions due to another read to the same near memory set in the SF.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in TOR", - "EventCode": "0x64", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", - "PerPkg": "1", - "PublicDescription": "PMM Memory Mode related events : Counts the number of times CHA saw NM Set conflict in TOR : No Reject in the CHA due to a pending read to the same near memory set in the TOR.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", - "EventCode": "0x70", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", - "EventCode": "0x70", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", - "EventCode": "0x70", - "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.REJ_IRQ", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.REJ_IRQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.SLOW_INSERT", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.SLOW_INSERT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.THROTTLE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", - "EventCode": "0x66", - "EventName": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", - "EventCode": "0x67", - "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", - "PerPkg": "1", - "PublicDescription": ": count # of FAST TOR Request inserted to ha_tor_req_fifo", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", - "EventCode": "0x67", - "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", - "PerPkg": "1", - "PublicDescription": ": count # of SLOW TOR Request inserted to ha_pmm_tor_req_fifo", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC10", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC10", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC10 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 10 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC11", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC11", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC11 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 11 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC12", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC12", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC12 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 12 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC13", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC13", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC13 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 13 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC6", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC6", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC6 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 6 only.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC7", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC7", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC7 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 7 only.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC8", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC8", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC8 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 8 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC9", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC9", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC9 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 9 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and remote INVITOE requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and are sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Remote INVITOE requests (exclusive ownership of a cache line without receiving data) sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Local read requests that miss the SF/LLC and remote read requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS", - "PerPkg": "1", - "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Local read requests that miss the SF/LLC and are sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Remote read requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Local write requests that miss the SF/LLC and remote write requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "Local write requests that miss the SF/LLC and are sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Remote write requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_CHA_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : IPQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : IPQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : IRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : RRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.RRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : RRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : WBQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.WBQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : WBQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IPQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : HA", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 1 : HA", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 1 : ANY0", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 1 : HA", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy : IPQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Occupancy : IPQ : Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy : IRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy : RRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Occupancy : RRQ : Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy : WBQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Occupancy : WBQ : Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : Allow Snoop", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : ANY0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : HA", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : LLC Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : SF Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : ANY0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : HA", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : AD REQ on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : AD RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : Non UPI AK Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : BL NCB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : BL NCS on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : BL RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : BL WB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 0 : Non UPI IV Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : Allow Snoop", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : ANY0", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Any condition listed in the RRQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : HA", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : HA : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : LLC OR SF Way", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : LLC Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : PhyAddr Match", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : SF Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects - Set 1 : Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "RRQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : AD REQ on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : AD RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : Non UPI AK Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : BL NCB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : BL NCS on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : BL RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : BL WB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 0 : Non UPI IV Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : Allow Snoop", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : ANY0", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Any condition listed in the WBQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : HA", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : HA : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : LLC OR SF Way", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : LLC Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : PhyAddr Match", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : SF Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects - Set 1 : Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "WBQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_CHA_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for E-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.E_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for M-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.M_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for S-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.S_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : All", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Broadcast snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Broadcast snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to local requests", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Broadcast snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Broadcast snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to remote requests", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to local requests", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Directed snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Directed snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to remote requests", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Snoops sent for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to local requests", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Snoops sent for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Snoops sent for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to remote requests", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RSPCNFLCT*", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCT", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : RSPCNFLCT* : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspFwd", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : RspFwd : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : Rsp*Fwd*WB", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPFWDWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : Rsp*Fwd*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspI", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPI", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspIFwd", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspS", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPS", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type RspS Snoop Response was received which indicates when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspSFwd", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : Rsp*WB", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : Rsp*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspCnflct", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspI", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspIFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspS", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspSFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : Rsp*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ffff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DDR4 Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DDR4 Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.DDR4", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SF/LLC Evictions", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Hits", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushes issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushes issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushOpts issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushOpts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRDs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRDs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd Pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCRD", - "PerPkg": "1", - "UMask": "0xcccffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDRD", - "PerPkg": "1", - "UMask": "0xccd7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores that hit in the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccfff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8178601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc816fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8178a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc896fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; DRd Pref misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read prefetch from remote IA that misses in the snoop filter", - "UMask": "0xc8977e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8177e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_DRAM", - "PerPkg": "1", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_DRAM", - "PerPkg": "1", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_DRAM", - "PerPkg": "1", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefCode issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefData issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefData issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_DRAM", - "PerPkg": "1", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DRAM", - "PerPkg": "1", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DRAM", - "PerPkg": "1", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remote memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc806fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc886fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8877e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC - HOMed remotely : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8077e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SpecItoMs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SpecItoMs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", - "PerPkg": "1", - "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc3fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBEFtoIs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", - "PerPkg": "1", - "PublicDescription": "WbEFtoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc37ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBMtoEs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", - "PerPkg": "1", - "PublicDescription": "WbMtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc2fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBStoIs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", - "PerPkg": "1", - "PublicDescription": "WbStoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc67ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushes issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to locally HOMed memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd42ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices to remotely HOMed memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd437f04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to locally HOMed memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc42ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices to remotely HOMed memory", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc437f04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WbMtoIs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IPQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IPQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - Non iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just ISOC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Local Targets", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA and IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Misses", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : MMCFG Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NearMem", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NonCoherent", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NotNearMem", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PMM Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PMM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PMM Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - Non IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Remote Targets", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Remote Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RRQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WBQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DDR4 Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DDR4 Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SF/LLC Evictions", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Hits", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRDs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRDs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd Pref from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd47ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccfff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88efe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80f7e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc817fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8178601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc816fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8168a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8178a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc897fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc896fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8968a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8978a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc8977e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8970a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8177e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8170a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc47fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefCode issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcccffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefData issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccd7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xccc7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8668a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86e8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_LOCAL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86e8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR_REMOTE_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8670a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f0a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc806fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc886fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8877e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed remotely", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8077e01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores that missed the LLC: For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8678a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8601", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86f8a01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc57ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IPQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IPQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - Non iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just ISOC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Local Targets", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA and IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Misses", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : MMCFG Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NearMem", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NonCoherent", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NotNearMem", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PMM Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PMM Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Remote Targets", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Remote Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xB3", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xB3", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI : Pushed to LLC", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI : Pushed to Memory", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC10", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC10", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC10 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 10 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC11", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC11", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC11 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 11 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC12", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC12", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC12 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 12 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC13", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC13", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC13 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 13 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC6", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC6", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC6 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 6 only.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC7", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC7", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC7 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 7 only.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC8", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC8", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC8 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 8 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC9", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC9", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC9 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 9 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Sent (on 0?)", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.SENT0", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Sent (on 1?)", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.SENT1", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", - "PerPkg": "1", - "UMask": "0x22", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", - "PerPkg": "1", - "UMask": "0x23", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", - "PerPkg": "1", - "UMask": "0x25", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", - "PerPkg": "1", - "UMask": "0x26", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", - "PerPkg": "1", - "UMask": "0x27", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", - "EventCode": "0x01", - "EventName": "UNC_IIO_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Clockticks of the integrated IO (IIO) traffic controller : Increments counter once every Traffic Controller clock, the LSCLK (500MHz)", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for IIO clocktick", - "EventCode": "0xff", - "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", - "PerPkg": "1", - "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", - "UMask": "0x10", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0xff", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 1", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 2", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 3", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 3 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 4", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 4 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 5", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 5 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 6", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 6 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 7", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 7 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Passing data to be written", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Request Ownership", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Writing line", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Request Ownership", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Writing line", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 1G Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.1G_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 2M Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.2M_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 4K Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.4K_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB lookups all", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.ALL_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": IOTLB lookups all : Some transactions have to look up IOTLB multiple times. Counts every time a request looks up IOTLB.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache hits", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", - "PerPkg": "1", - "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache lookups", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB lookups first", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Fills (same as IOTLB miss)", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.MISSES", - "PerPkg": "1", - "PublicDescription": ": IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Cycles PWT full", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.CYC_PWT_FULL", - "PerPkg": "1", - "PublicDescription": ": Cycles PWT full : Counts cycles the IOMMU has reached its maximum limit for outstanding page walks.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOMMU memory access", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", - "PerPkg": "1", - "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 1G page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 2M page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 4K page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_4K_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWT Hit to a 256T page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": PageWalk cache fill", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", - "PerPkg": "1", - "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": PageWalk cache lookup", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Interrupt Entry cache hit", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.INT_CACHE_HITS", - "PerPkg": "1", - "PublicDescription": ": Interrupt Entry cache hit : Counts each time a transaction's first look up hits the IEC.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": Interrupt Entry cache lookup", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.INT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": Interrupt Entry cache lookup : Counts the number of transaction looks up that interrupt remapping cache.", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": Device-selective Context cache invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DEVICE", - "PerPkg": "1", - "PublicDescription": ": Device-selective Context cache invalidation cycles : Counts number of Device selective context cache invalidation events", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Domain-selective Context cache invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DOMAIN", - "PerPkg": "1", - "PublicDescription": ": Domain-selective Context cache invalidation cycles : Counts number of Domain selective context cache invalidation events", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache global invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_GBL", - "PerPkg": "1", - "PublicDescription": ": Context cache global invalidation cycles : Counts number of Context Cache global invalidation events", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Domain-selective IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_DOMAIN", - "PerPkg": "1", - "PublicDescription": ": Domain-selective IOTLB invalidation cycles : Counts number of Domain selective invalidation events", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Global IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_GBL", - "PerPkg": "1", - "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Page-selective IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_PAGE", - "PerPkg": "1", - "PublicDescription": ": Page-selective IOTLB invalidation cycles : Counts number of Page-selective within Domain Invalidation events", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Counting disabled", - "EventCode": "0x80", - "EventName": "UNC_IIO_NOTHING", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Occupancy of outbound request queue : To device", - "EventCode": "0xC5", - "EventName": "UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Passing data to be written", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Passing data to be written : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Issuing final read or write of line", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Processing response from IOMMU", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Issuing to IOMMU", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Request Ownership", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Request Ownership : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": Writing line", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Writing line : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From IRP", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From ITC", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From ITC : Confined P2P", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : Completion allocations", - "EventCode": "0xc2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.PREALLOC", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests PCIe makes of the main die : Drop request", - "EventCode": "0x85", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU.ALL.DROP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests PCIe makes of the main die : Drop request : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU. : Packet error detected, must be dropped", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests PCIe makes of the main die : All", - "EventCode": "0x85", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Abort", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Memory", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : MsgB", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Ubox", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "ITC address map 1", - "EventCode": "0x8F", - "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", - "EventCode": "0xD0", - "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", - "EventCode": "0xD1", - "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PWT occupancy", - "EventCode": "0x42", - "EventName": "UNC_IIO_PWT_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Passing data to be written", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Issuing final read or write of line", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Request Ownership", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Writing line", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Passing data to be written", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Issuing final read or write of line", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Processing response from IOMMU", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Processing response from IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Issuing to IOMMU", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Issuing to IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Request Ownership", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Writing line", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Passing data to be written", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Request Ownership", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Writing line", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Symbol Times on Link", - "EventCode": "0x82", - "EventName": "UNC_IIO_SYMBOL_TIMES", - "PerPkg": "1", - "PublicDescription": "Symbol Times on Link : Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Total Write Cache Occupancy : Any Source", - "EventCode": "0x0F", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Total Write Cache Occupancy : Any Source : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events. : Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy : Snoops", - "EventCode": "0x0F", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", - "PerPkg": "1", - "PublicDescription": "Total Write Cache Occupancy : Snoops : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", - "EventCode": "0x0f", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", - "PerPkg": "1", - "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", - "EventCode": "0x01", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops : CLFlush", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops : WbMtoI", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF RF full", - "EventCode": "0x17", - "EventName": "UNC_I_FAF_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", - "EventCode": "0x18", - "EventName": "UNC_I_FAF_INSERTS", - "PerPkg": "1", - "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Occupancy of the IRP FAF queue.", - "EventCode": "0x19", - "EventName": "UNC_I_FAF_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF allocation -- sent to ADQ", - "EventCode": "0x16", - "EventName": "UNC_I_FAF_TRANSACTIONS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.EVICTS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Lost Forward", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Received Invalid", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Received Valid", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Requests", - "EventCode": "0x14", - "EventName": "UNC_I_P2P_INSERTS", - "PerPkg": "1", - "PublicDescription": "P2P Requests : P2P requests from the ITC", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Occupancy", - "EventCode": "0x15", - "EventName": "UNC_I_P2P_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "P2P Occupancy : P2P B & S Queue Occupancy", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P completions", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if local only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if local and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P Message", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P reads", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : Match if remote only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if remote and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P Writes", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", - "UMask": "0x7e", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", - "UMask": "0x74", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", - "UMask": "0x72", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", - "UMask": "0x78", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that miss the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", - "UMask": "0x71", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit E or S", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit I", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit M", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Miss", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpCode", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpData", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpInv", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Atomic", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Atomic : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Other", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Other : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Writes", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound write (fast path) requests received by the IRP.", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Egress Allocations", - "EventCode": "0x0B", - "EventName": "UNC_I_TxC_AK_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Cycles Full", - "EventCode": "0x05", - "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Inserts", - "EventCode": "0x02", - "EventName": "UNC_I_TxC_BL_DRS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Occupancy", - "EventCode": "0x08", - "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Cycles Full", - "EventCode": "0x06", - "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Inserts", - "EventCode": "0x03", - "EventName": "UNC_I_TxC_BL_NCB_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Occupancy", - "EventCode": "0x09", - "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Cycles Full", - "EventCode": "0x07", - "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Inserts", - "EventCode": "0x04", - "EventName": "UNC_I_TxC_BL_NCS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Occupancy", - "EventCode": "0x0A", - "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", - "EventCode": "0x1C", - "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0&AD1 both. Stalls on both AD0 and AD1 will count as 2", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD0 Egress Credits Stalls", - "EventCode": "0x1A", - "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD1 Egress Credits Stalls", - "EventCode": "0x1B", - "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x1D", - "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0x0D", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0x0E", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0x0C", - "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Not Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Not Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Clockticks of the mesh to memory (M2M)", - "EventName": "UNC_M2M_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M2M_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled", - "EventCode": "0x24", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", - "EventCode": "0x60", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to core transaction was overridden", - "EventCode": "0x25", - "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", - "EventCode": "0x28", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when Direct2UPI was Disabled", - "EventCode": "0x27", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", - "EventCode": "0x29", - "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", - "PerPkg": "1", - "PublicDescription": "Clockticks of the mesh to PCI (M2P)", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On NonDirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On NonDirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On NonDirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On NonDirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On Dirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On Dirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On Dirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit : On Dirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in any state", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in A state", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in I state", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory Lookups : Found in S state", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On NonDirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On NonDirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On NonDirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On NonDirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On Dirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On Dirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On Dirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss : On Dirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory Updates : From/to any state. Note: event counts are incorrect in 2LM mode.", - "EventCode": "0x2e", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : PMM Local", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.PMM_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : PMM Remote", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.PMM_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_DISTRESS_PMM", - "EventCode": "0xF2", - "EventName": "UNC_M2M_DISTRESS_PMM", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_DISTRESS_PMM_MEMMODE", - "EventCode": "0xF1", - "EventName": "UNC_M2M_DISTRESS_PMM_MEMMODE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xBA", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xBA", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xB9", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xB9", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ALL", - "PerPkg": "1", - "UMask": "0x704", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_ALL", - "PerPkg": "1", - "UMask": "0x104", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", - "PerPkg": "1", - "UMask": "0x140", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", - "PerPkg": "1", - "UMask": "0x102", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", - "PerPkg": "1", - "UMask": "0x101", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x110", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x108", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : PMM - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Reads Issued to iMC : PMM - Ch0 : Counts all PMM dimm read requests(full line) sent from M2M to iMC", - "UMask": "0x120", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_ALL", - "PerPkg": "1", - "UMask": "0x204", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", - "PerPkg": "1", - "UMask": "0x240", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", - "PerPkg": "1", - "UMask": "0x202", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", - "PerPkg": "1", - "UMask": "0x201", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x210", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x208", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : PMM - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Reads Issued to iMC : PMM - Ch1 : Counts all PMM dimm read requests(full line) sent from M2M to iMC", - "UMask": "0x220", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch2", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH2_FROM_TGR", - "PerPkg": "1", - "UMask": "0x440", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.FROM_TGR", - "PerPkg": "1", - "UMask": "0x740", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ISOCH", - "PerPkg": "1", - "UMask": "0x702", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.NORMAL", - "PerPkg": "1", - "UMask": "0x701", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR, acting as Cache - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x710", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : DDR - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x708", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : PMM - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.TO_PMM", - "PerPkg": "1", - "UMask": "0x720", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.ALL", - "PerPkg": "1", - "UMask": "0x1c10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", - "PerPkg": "1", - "UMask": "0x410", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", - "PerPkg": "1", - "UMask": "0x401", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x404", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_NI", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", - "PerPkg": "1", - "UMask": "0x402", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x408", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x440", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x420", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : PMM - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Writes Issued to iMC : PMM - Ch0 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", - "UMask": "0x480", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", - "PerPkg": "1", - "UMask": "0x810", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", - "PerPkg": "1", - "UMask": "0x801", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x804", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_NI", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", - "PerPkg": "1", - "UMask": "0x802", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x808", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x840", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x820", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : PMM - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_PMM", - "PerPkg": "1", - "PublicDescription": "M2M Writes Issued to iMC : PMM - Ch1 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", - "UMask": "0x880", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL", - "PerPkg": "1", - "UMask": "0x1c01", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x1c04", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.NI", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", - "PerPkg": "1", - "UMask": "0x1c02", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x1c08", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR, acting as Cache - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_CACHE", - "PerPkg": "1", - "UMask": "0x1c40", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : DDR - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_MEM", - "PerPkg": "1", - "UMask": "0x1c20", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : PMM - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", - "PerPkg": "1", - "UMask": "0x1c80", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts", - "EventCode": "0x64", - "EventName": "UNC_M2M_MIRR_WRQ_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x65", - "EventName": "UNC_M2M_MIRR_WRQ_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xE6", - "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xE6", - "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches : MC Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches : Mesh Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MESH", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", - "EventCode": "0x73", - "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : All Channels", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : Channel 0", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : Channel 1", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : Channel 2", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : All Channels", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 0", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 1", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 2", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA0_INVAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA1_INVAL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_MISS_INVAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_RSP_PDRESET", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA0_INVAL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA1_INVAL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_MISS_INVAL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_RSP_PDRESET", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_HITA0_INVAL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_HITA1_INVAL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_MISS_INVAL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH2_RSP_PDRESET", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : UPI - Ch 0", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - Ch 0", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : UPI - Ch 1", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - Ch 1", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : UPI - Ch 2", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH2_UPI", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - Ch 2", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH2_XPT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", - "EventCode": "0x6f", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.UPI_ALLCH", - "PerPkg": "1", - "UMask": "0x2a", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - All Channels", - "EventCode": "0x6f", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 0", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 0", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 1", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 2", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH2_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 2", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- All Channels", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPTUPI_ALLCH", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - All Channels", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 0", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 0", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 1", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 2", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH2_XPTUPI", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - All Channels", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPTUPI_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.ERRORBLK_RxC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.NOT_PF_SAD_REGION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_HIT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_SECURE_DROP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.RPQ_PROXY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.STOP_B2B", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.UPI_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.WPQ_PROXY", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.XPT_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.ERRORBLK_RxC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.NOT_PF_SAD_REGION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_HIT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_SECURE_DROP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.RPQ_PROXY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.STOP_B2B", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.UPI_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.WPQ_PROXY", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.XPT_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.ERRORBLK_RxC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.NOT_PF_SAD_REGION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_CAM_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_CAM_HIT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.PF_SECURE_DROP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.RPQ_PROXY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.STOP_B2B", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.UPI_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.WPQ_PROXY", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch2 - Reasons", - "EventCode": "0x72", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH2.XPT_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_UPI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_UPI", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 2", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH2_UPI", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 2", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH2_XPT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", - "EventCode": "0x6d", - "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", - "PerPkg": "1", - "UMask": "0x2a", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : All Channels", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : Channel 0", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : Channel 1", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : Channel 2", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": ": All Channels", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": ": Channel 0", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": ": Channel 1", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": ": Channel 2", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", - "EventCode": "0x79", - "EventName": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_INSERTS", - "EventCode": "0x78", - "EventName": "UNC_M2M_PREFCAM_RxC_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", - "EventCode": "0x77", - "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_M2M_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 0", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 1", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 2", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 0", - "EventCode": "0x4F", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 1", - "EventCode": "0x4F", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC RPQ Cycles w/Credits - PMM : Channel 2", - "EventCode": "0x4F", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD_PMM.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 0", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 2", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Full", - "EventCode": "0x04", - "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Not Empty", - "EventCode": "0x03", - "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Allocations", - "EventCode": "0x01", - "EventName": "UNC_M2M_RxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy", - "EventCode": "0x02", - "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", - "EventCode": "0x77", - "EventName": "UNC_M2M_RxC_AD_PREF_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x5C", - "EventName": "UNC_M2M_RxC_AK_WR_CMP", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Full", - "EventCode": "0x08", - "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Not Empty", - "EventCode": "0x07", - "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Allocations", - "EventCode": "0x05", - "EventName": "UNC_M2M_RxC_BL_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Occupancy", - "EventCode": "0x06", - "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_M2M_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_SCOREBOARD_AD_RETRY_ACCEPTS", - "EventCode": "0x33", - "EventName": "UNC_M2M_SCOREBOARD_AD_RETRY_ACCEPTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_SCOREBOARD_AD_RETRY_REJECTS", - "EventCode": "0x34", - "EventName": "UNC_M2M_SCOREBOARD_AD_RETRY_REJECTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Retry - Mem Mirroring Mode", - "EventCode": "0x35", - "EventName": "UNC_M2M_SCOREBOARD_BL_RETRY_ACCEPTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Retry - Mem Mirroring Mode", - "EventCode": "0x36", - "EventName": "UNC_M2M_SCOREBOARD_BL_RETRY_REJECTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Scoreboard Accepts", - "EventCode": "0x2F", - "EventName": "UNC_M2M_SCOREBOARD_RD_ACCEPTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Scoreboard Rejects", - "EventCode": "0x30", - "EventName": "UNC_M2M_SCOREBOARD_RD_REJECTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Scoreboard Accepts", - "EventCode": "0x31", - "EventName": "UNC_M2M_SCOREBOARD_WR_ACCEPTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Scoreboard Rejects", - "EventCode": "0x32", - "EventName": "UNC_M2M_SCOREBOARD_WR_REJECTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tag Hit : Clean NearMem Read Hit", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", - "PerPkg": "1", - "PublicDescription": "Tag Hit : Clean NearMem Read Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean full line read hits (reads and RFOs).", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tag Hit : Dirty NearMem Read Hit", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", - "PerPkg": "1", - "PublicDescription": "Tag Hit : Dirty NearMem Read Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty full line read hits (reads and RFOs).", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tag Hit : Clean NearMem Underfill Hit", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", - "PerPkg": "1", - "PublicDescription": "Tag Hit : Clean NearMem Underfill Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean underfill hits due to a partial write", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tag Hit : Dirty NearMem Underfill Hit", - "EventCode": "0x2C", - "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", - "PerPkg": "1", - "PublicDescription": "Tag Hit : Dirty NearMem Underfill Hit : Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty underfill read hits due to a partial write", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Tag Miss", - "EventCode": "0x61", - "EventName": "UNC_M2M_TAG_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number AD Ingress Credits", - "EventCode": "0x41", - "EventName": "UNC_M2M_TGR_AD_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number BL Ingress Credits", - "EventCode": "0x42", - "EventName": "UNC_M2M_TGR_BL_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full : Channel 0", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full : Channel 1", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full : Channel 2", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 0", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 1", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 2", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty : Channel 0", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty : Channel 1", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty : Channel 2", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 0", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 1", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 2", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credit Acquired", - "EventCode": "0x0d", - "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credits Occupancy", - "EventCode": "0x0e", - "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Full", - "EventCode": "0x0c", - "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Not Empty", - "EventCode": "0x0b", - "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Allocations", - "EventCode": "0x09", - "EventName": "UNC_M2M_TxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", - "EventCode": "0x0f", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", - "EventCode": "0x10", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Occupancy", - "EventCode": "0x0A", - "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK : CRD Transactions to Cbo", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.CRD_CBO", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK : NDR Transactions", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.NDR", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AKC Credits", - "EventCode": "0x5F", - "EventName": "UNC_M2M_TxC_AKC_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : All", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Near Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Far Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : All", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : All", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Near Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Far Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : All", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Cache", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Core", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to QPI", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_UPI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : All", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Near Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Far Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : All", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : All", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Near Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Far Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xB3", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xB3", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "WPQ Flush : Channel 0", - "EventCode": "0x58", - "EventName": "UNC_M2M_WPQ_FLUSH.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "WPQ Flush : Channel 1", - "EventCode": "0x58", - "EventName": "UNC_M2M_WPQ_FLUSH.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "WPQ Flush : Channel 2", - "EventCode": "0x58", - "EventName": "UNC_M2M_WPQ_FLUSH.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 0", - "EventCode": "0x51", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 1", - "EventCode": "0x51", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - PMM : Channel 2", - "EventCode": "0x51", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD_PMM.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Channel 0", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Channel 1", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Channel 2", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Mirror", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts : Channel 0", - "EventCode": "0x56", - "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts : Channel 1", - "EventCode": "0x56", - "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts : Channel 2", - "EventCode": "0x56", - "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Channel 2", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", - "EventCode": "0x63", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", - "EventCode": "0x63", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 2", - "EventCode": "0x63", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", - "EventCode": "0x62", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", - "EventCode": "0x62", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 2", - "EventCode": "0x62", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Channel 0", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Channel 1", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Channel 2", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Mirror", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_NONTGR", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_PWR", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Inserts : Channel 0", - "EventCode": "0x5E", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Inserts : Channel 1", - "EventCode": "0x5E", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Inserts : Channel 2", - "EventCode": "0x5E", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", - "EventCode": "0x5D", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", - "EventCode": "0x5D", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Occupancy : Channel 2", - "EventCode": "0x5D", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Clockticks of the mesh to PCI (M2P)", - "EventCode": "0x01", - "EventName": "UNC_M2P_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Clockticks of the mesh to PCI (M2P) : Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M2P_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : PMM Local", - "EventCode": "0xAF", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.PMM_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : PMM Remote", - "EventCode": "0xAF", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.PMM_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xba", - "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xba", - "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xb9", - "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xb9", - "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent0", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent1", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent2", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xe6", - "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xe6", - "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : All", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Local NCB", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Local NCS", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Remote NCB", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Remote NCS", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : All", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Local NCB", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Local NCS", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Remote NCB", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Remote NCS", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : All", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Local NCB", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Local NCS", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Remote NCB", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Remote NCS", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - DRS", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCB", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCS", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - DRS", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_DRS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCB", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCS", - "EventCode": "0x48", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - DRS", - "EventCode": "0x49", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCB", - "EventCode": "0x49", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCS", - "EventCode": "0x49", - "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCB", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCS", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCB", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCS", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCB", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCS", - "EventCode": "0x1b", - "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - DRS", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCB", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCS", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - DRS", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_DRS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCB", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCS", - "EventCode": "0x42", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - DRS", - "EventCode": "0x43", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCB", - "EventCode": "0x43", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCS", - "EventCode": "0x43", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - DRS", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCB", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCS", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - DRS", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_DRS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCB", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCS", - "EventCode": "0x4c", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - DRS", - "EventCode": "0x4d", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_DRS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCB", - "EventCode": "0x4d", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCS", - "EventCode": "0x4d", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_M2P_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_M2P_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "UNC_M2P_TxC_CREDITS.PMM", - "EventCode": "0x2D", - "EventName": "UNC_M2P_TxC_CREDITS.PMM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", - "EventCode": "0x2d", - "EventName": "UNC_M2P_TxC_CREDITS.PRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9e", - "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9e", - "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xb3", - "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xb3", - "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8B", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8B", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8B", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8D", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8D", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8D", - "EventName": "UNC_M3UPI_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8F", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8F", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8F", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty : Requests", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", - "PerPkg": "1", - "PublicDescription": "CBox AD Credits Empty : Requests : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty : Snoops", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", - "PerPkg": "1", - "PublicDescription": "CBox AD Credits Empty : Snoops : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty : VNA Messages", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "CBox AD Credits Empty : VNA Messages : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty : Writebacks", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", - "PerPkg": "1", - "PublicDescription": "CBox AD Credits Empty : Writebacks : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Clockticks of the mesh to UPI (M3UPI)", - "EventCode": "0x01", - "EventName": "UNC_M3UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Clockticks of the mesh to UPI (M3UPI) : Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2C Sent", - "EventCode": "0x2B", - "EventName": "UNC_M3UPI_D2C_SENT", - "PerPkg": "1", - "PublicDescription": "D2C Sent : Count cases BL sends direct to core", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2U Sent", - "EventCode": "0x2A", - "EventName": "UNC_M3UPI_D2U_SENT", - "PerPkg": "1", - "PublicDescription": "D2U Sent : Cases where SMI3 sends D2U command", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : PMM Local", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.PMM_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Local : Counts the number of cycles either the local or incoming distress signals are asserted. : If the CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : PMM Remote", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.PMM_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : PMM Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : If another CHA TOR has too many PMM transactions, this signal will throttle outgoing MS2IDI traffic", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xAF", - "EventName": "UNC_M3UPI_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xBA", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xBA", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xB6", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xB6", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xBB", - "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xBB", - "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M3UPI_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xB7", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xB7", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xB8", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xB8", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xB9", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xB9", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO1_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only) : No vn0 and vna credits available to send to M2", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO2", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO2 : No vn0 and vna credits available to send to M2", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO3", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO3 : No vn0 and vna credits available to send to M2", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO4", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO4 : No vn0 and vna credits available to send to M2", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO5", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together : No vn0 and vna credits available to send to M2", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits : No vn0 and vna credits available to send to M2", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty : IIO5", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.UBOX_NCB", - "PerPkg": "1", - "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xE6", - "EventName": "UNC_M3UPI_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xE6", - "EventName": "UNC_M3UPI_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : AD - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : AD - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : AD - Slot 1", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : AD - Slot 1 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : AD - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : AD - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : AK - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : AK - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : AK - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : AK - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received : BL - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi Slot Flit Received : BL - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_M3UPI_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : REQ on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : REQ on AD : VN0 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : RSP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : RSP on AD : VN0 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : SNP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : SNP on AD : VN0 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : NCB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : NCB on BL : VN0 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : NCS on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : NCS on BL : VN0 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : RSP on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : RSP on BL : VN0 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0 : WB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN0 : WB on BL : VN0 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : REQ on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : REQ on AD : VN1 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : RSP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : RSP on AD : VN1 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : SNP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : SNP on AD : VN1 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : NCB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : NCB on BL : VN1 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : NCS on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : NCS on BL : VN1 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : RSP on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : RSP on BL : VN1 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1 : WB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Lost Arb for VN1 : WB on BL : VN1 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN0", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0 : AD and BL messages won arbitration concurrently / in parallel", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN1", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1 : AD and BL messages won arbitration concurrently / in parallel", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : Max Parallel Win", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.ALL_PARALLEL_WIN", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : Max Parallel Win : VN0 and VN1 arbitration sub-pipelines both produced AD and BL winners (maximum possible parallel winners)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN0 : Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN1 : Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN0 : Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN1 : Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.VN01_PARALLEL_WIN", - "PerPkg": "1", - "PublicDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win : VN0 and VN1 arbitration sub-pipelines had parallel winners (at least one AD or BL on each side)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : REQ on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : REQ on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : RSP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : RSP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : SNP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : SNP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : NCB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : NCB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : NCS on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : NCS on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : RSP on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : RSP on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0 : WB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN0 : WB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : REQ on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : REQ on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : RSP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : RSP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : SNP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : SNP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : NCB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : NCB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : NCS on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : NCS on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : RSP on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : RSP on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1 : WB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "No Credits to Arb for VN1 : WB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : REQ on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : REQ on AD : VN0 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : RSP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : RSP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : SNP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : SNP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : NCB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : NCB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : NCS on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : NCS on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : RSP on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : RSP on BL : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0 : WB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN0 : WB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : REQ on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : REQ on AD : VN1 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : RSP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : RSP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : SNP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : SNP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : NCB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : NCB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : NCS on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : NCS on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : RSP on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : RSP on BL : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1 : WB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Can't Arb for VN1 : WB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", - "PerPkg": "1", - "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", - "PerPkg": "1", - "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while pipeline is idle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 1", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 1 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 1 while merging with bl message in same flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 2", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 2 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 2 while merging with bl message in same flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events : Any In BGF FIFO", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : Any In BGF FIFO : Indication that at least one packet (flit) is in the bgf (fifo only)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events : Any in BGF Path", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : Any in BGF Path : Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT1_FOR_D2K", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT2_FOR_D2K", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 2", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events : No D2K For Arb", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN0_NO_D2K_FOR_ARB", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : No D2K For Arb : VN0 BL RSP message was blocked from arbitration request due to lack of D2K CMP credit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN1_NO_D2K_FOR_ARB", - "PerPkg": "1", - "PublicDescription": "Miscellaneous Credit Events : VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : Credits Consumed", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.CONSUMED", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : Credits Consumed : number of remote vna credits consumed per cycle", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : D2K Credits", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : D2K Credits : D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : Packets in BGF FIFO", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : Packets in BGF FIFO : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : Packets in BGF Path", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : Packets in BGF Path : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in completion fifo only", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in marker table and in fifo", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : Transmit Credits", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : Transmit Credits : Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy : VNA In Use", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", - "PerPkg": "1", - "PublicDescription": "Credit Occupancy : VNA In Use : Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent : All", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Data Flit Not Sent : All : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but could not be sent for any reason, e.g. low credits, low tsv, stall injection", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent : No BGF Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_BGF", - "PerPkg": "1", - "PublicDescription": "Data Flit Not Sent : No BGF Credits : Data flit is ready for transmission but could not be sent", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent : No TxQ Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_TXQ", - "PerPkg": "1", - "PublicDescription": "Data Flit Not Sent : No TxQ Credits : Data flit is ready for transmission but could not be sent", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent : TSV High", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.TSV_HI", - "PerPkg": "1", - "PublicDescription": "Data Flit Not Sent : TSV High : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while tsv high", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent : Cycle valid for Flit", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.VALID_FOR_FLIT", - "PerPkg": "1", - "PublicDescription": "Data Flit Not Sent : Cycle valid for Flit : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while cycle is valid for flit transmission", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 0", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 0 : generating bl data flit sequence; waiting for data pump 0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is tracking at least one message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending completion fifo is full", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : a bl message finished but is in limbo and moved to pump-1-pending logic", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 1", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 1 : generating bl data flit sequence; waiting for data pump 1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", - "PerPkg": "1", - "PublicDescription": ": slot 2 request naturally serviced during hold-off period", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", - "PerPkg": "1", - "PublicDescription": ": slot 2 request forcibly serviced during service window", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", - "PerPkg": "1", - "PublicDescription": ": slot 2 request received from link layer while idle (with no slot 2 request active immediately prior)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", - "PerPkg": "1", - "PublicDescription": ": slot 2 request withdrawn during hold-off period or service window", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : All", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Needs Data Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Needs Data Flit : BL message requires data flit sequence", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0 : Waiting for header pump 0", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 : Header pump 1 is not required for flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble : Header pump 1 is not required for flit but flit transmission delayed", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail : Header pump 1 is not required for flit and not available", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1 : Waiting for header pump 1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1 : Accumulate", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Accumulate : Events related to Header Flit Generation - Set 1 : Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1 : Accumulate Ready", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Accumulate Ready : Events related to Header Flit Generation - Set 1 : header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1 : Accumulate Wasted", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Accumulate Wasted : Events related to Header Flit Generation - Set 1 : Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked : Events related to Header Flit Generation - Set 1 : Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_AFTER", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: message was slotted only after run-ahead was over; run-ahead mode definitely wasted", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Message", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_DURING", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Message : Events related to Header Flit Generation - Set 1 : run-ahead mode: one message slotted during run-ahead", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_AFTER", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: second message slotted immediately after run-ahead; potential run-ahead success", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_SENT", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: two (or three) message flit sent immediately after run-ahead; complete run-ahead success", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2 : Parallel Ok", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 2 : Parallel Ok : Events related to Header Flit Generation - Set 2 : new header flit construction may proceed in parallel with data flit sequence", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2 : Parallel Flit Finished", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_FLIT", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 2 : Parallel Flit Finished : Events related to Header Flit Generation - Set 2 : header flit finished assembly in parallel with data flit sequence", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2 : Parallel Message", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_MSG", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 2 : Parallel Message : Events related to Header Flit Generation - Set 2 : message is slotted into header flit in parallel with data flit sequence", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall : Events related to Header Flit Generation - Set 2 : Rate-matching stall injected", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", - "PerPkg": "1", - "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message : Events related to Header Flit Generation - Set 2 : Rate matching stall injected, but no additional message slotted during stall cycle", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : One Message", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG", - "PerPkg": "1", - "PublicDescription": "Sent Header Flit : One Message : One message in flit; VNA or non-VNA flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : One Message in non-VNA", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG_VNX", - "PerPkg": "1", - "PublicDescription": "Sent Header Flit : One Message in non-VNA : One message in flit; non-VNA flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : Two Messages", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.2_MSGS", - "PerPkg": "1", - "PublicDescription": "Sent Header Flit : Two Messages : Two messages in flit; VNA flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : Three Messages", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.3_MSGS", - "PerPkg": "1", - "PublicDescription": "Sent Header Flit : Three Messages : Three messages in flit; VNA flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : One Slot Taken", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : Two Slots Taken", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_2", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit : All Slots Taken", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_3", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : All", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : All : header flit is ready for transmission but could not be sent : header flit is ready for transmission but could not be sent for any reason, e.g. no credits, low tsv, stall injection", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : No BGF Credits", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_CRD", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : No BGF Credits : header flit is ready for transmission but could not be sent : No BGF credits available", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_NO_MSG", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No BGF credits available; no additional message slotted into flit", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : No TxQ Credits", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_CRD", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : No TxQ Credits : header flit is ready for transmission but could not be sent : No TxQ credits available", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_NO_MSG", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No TxQ credits available; no additional message slotted into flit", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : TSV High", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.TSV_HI", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : TSV High : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while tsv high", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent : Cycle valid for Flit", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.VALID_FOR_FLIT", - "PerPkg": "1", - "PublicDescription": "Header Not Sent : Cycle valid for Flit : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while cycle is valid for flit transmission", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : Can't Slot AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", - "PerPkg": "1", - "PublicDescription": "Message Held : Can't Slot AD : some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : Can't Slot BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", - "PerPkg": "1", - "PublicDescription": "Message Held : Can't Slot BL : some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : Parallel Attempt", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", - "PerPkg": "1", - "PublicDescription": "Message Held : Parallel Attempt : ad and bl messages attempted to slot into the same flit in parallel", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : Parallel Success", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", - "PerPkg": "1", - "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : VN0", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.VN0", - "PerPkg": "1", - "PublicDescription": "Message Held : VN0 : vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held : VN1", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_HELD.VN1", - "PerPkg": "1", - "PublicDescription": "Message Held : VN1 : vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : REQ on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : REQ on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : SNP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : SNP on AD : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCB on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCS on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : NCS on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : RSP on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts : WB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Inserts : WB on BL : Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : REQ on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : REQ on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : SNP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : SNP on AD : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCS on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : NCS on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : RSP on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts : WB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Inserts : WB on BL : Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : REQ on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : REQ on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : SNP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : SNP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCS on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : NCS on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : RSP on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy : WB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 Ingress (from CMS) Queue - Occupancy : WB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : REQ on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : REQ on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : SNP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : SNP on AD : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCS on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : NCS on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : RSP on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy : WB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 Ingress (from CMS) Queue - Occupancy : WB on BL : Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : REQ on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : RSP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : SNP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : NCB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : NCS on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : RSP on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit : WB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : REQ on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : RSP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : SNP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : NCB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : NCS on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : RSP on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit : WB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Any In Use", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Any In Use : At least one remote vna credit is in use", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Corrected", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Corrected : Number of remote vna credits corrected (local return) per cycle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Level < 1", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Level < 1 : Remote vna credit level is less than 1 (i.e. no vna credits available)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Level < 10", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT10", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Level < 10 : remote vna credit level is less than 10; parallel vn0/vn1 arb not possible", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Level < 4", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Level < 4 : Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits : Level < 5", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", - "PerPkg": "1", - "PublicDescription": "Remote VNA Credits : Level < 5 : Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", - "PerPkg": "1", - "PublicDescription": ": remote vna credit count was less than 5 and allocation to ad or bl messages was required", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", - "PerPkg": "1", - "PublicDescription": ": remote vna credit count was less than 10 and allocation to vn0 or vn1 was required", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", - "PerPkg": "1", - "PublicDescription": ": on vn0, remote vna credits were allocated only to ad messages, not to bl", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", - "PerPkg": "1", - "PublicDescription": ": on vn0, remote vna credits were allocated only to bl messages, not to ad", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", - "PerPkg": "1", - "PublicDescription": ": remote vna credits were allocated only to vn0, not to vn1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", - "PerPkg": "1", - "PublicDescription": ": on vn1, remote vna credits were allocated only to ad messages, not to bl", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", - "PerPkg": "1", - "PublicDescription": ": on vn1, remote vna credits were allocated only to bl messages, not to ad", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", - "PerPkg": "1", - "PublicDescription": ": remote vna credits were allocated only to vn1, not to vn0", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xE2", - "EventName": "UNC_M3UPI_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xE3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xE1", - "EventName": "UNC_M3UPI_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xE0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD1", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD1", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD1", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD3", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD3", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD3", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD5", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD5", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD5", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD7", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD7", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD7", - "EventName": "UNC_M3UPI_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN0 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN0 REQ Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN0 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN0 RSP Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN0 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN0 SNP Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN0 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN0 WB Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN1 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN1 REQ Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN1 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN1 RSP Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN1 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN1 SNP Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD : VN1 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for AD : VN1 WB Messages : AD arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", - "PerPkg": "1", - "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN0 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN0 REQ Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN0 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN0 RSP Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN0 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN0 SNP Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN0 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN0 WB Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN1 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN1 REQ Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN1 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN1 RSP Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN1 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN1 SNP Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty : VN1 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Not Empty : VN1 WB Messages : Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN0 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN0 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN0 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN0 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN0 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN0 WB Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN1 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN1 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN1 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts : VN1 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD Flow Q Inserts : VN1 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN0 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN0 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN0 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN0 WB Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN1 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN1 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy : VN1 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Inserts", - "EventCode": "0x2F", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Occupancy", - "EventCode": "0x1E", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN0 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN0 NCB Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN0 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN0 NCS Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN0 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN0 RSP Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN0 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN0 WB Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN1 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN1 NCS Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN1 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN1 NCB Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN1 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN1 RSP Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL : VN1 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Failed ARB for BL : VN1 WB Messages : BL arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN0 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN0 REQ Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN0 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN0 RSP Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN0 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN0 SNP Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN0 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN0 WB Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN1 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN1 REQ Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN1 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN1 RSP Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN1 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN1 SNP Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty : VN1 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Not Empty : VN1 WB Messages : Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN0 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN0 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN0 NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN0 NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN0 NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN0 NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN1 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN1 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN1 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN1_NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN1_NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts : VN1_NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL Flow Q Inserts : VN1_NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1_NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_LOCAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_THROUGH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_WRPULL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_LOCAL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_THROUGH", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", - "EventCode": "0x1F", - "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_WRPULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN0 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN0 REQ Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN0 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN0 RSP Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN0 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN0 SNP Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN1 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN1 REQ Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN1 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN1 RSP Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VN1 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VN1 SNP Messages : No credits available to send to UPIs on the AD Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty : VNA", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "UPI0 AD Credits Empty : VNA : No credits available to send to UPIs on the AD Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN0 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN0 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN0 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN0 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN0 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN0 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN1 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN1 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN1 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN1 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VN1 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VN1 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty : VNA", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "UPI0 BL Credits Empty : VNA : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FlowQ Generated Prefetch", - "EventCode": "0x29", - "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", - "PerPkg": "1", - "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xB5", - "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xB5", - "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M3UPI_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : WB on BL", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : WB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : NCB on BL", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : NCB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : REQ on AD", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : REQ on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : RSP on AD", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : RSP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : SNP on AD", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : SNP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used : RSP on BL", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Used : RSP on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : WB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : WB on BL : Number of Cycles there were no VN0 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : NCB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : NCB on BL : Number of Cycles there were no VN0 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : REQ on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : REQ on AD : Number of Cycles there were no VN0 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : RSP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : RSP on AD : Number of Cycles there were no VN0 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : SNP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : SNP on AD : Number of Cycles there were no VN0 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits : RSP on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "VN0 No Credits : RSP on BL : Number of Cycles there were no VN0 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : WB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : WB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : NCB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : NCB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : REQ on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : REQ on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : RSP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : RSP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : SNP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : SNP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used : RSP on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Used : RSP on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : WB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : WB on BL : Number of Cycles there were no VN1 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : NCB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : NCB on BL : Number of Cycles there were no VN1 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : REQ on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : REQ on AD : Number of Cycles there were no VN1 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : RSP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : RSP on AD : Number of Cycles there were no VN1 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : SNP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : SNP on AD : Number of Cycles there were no VN1 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits : RSP on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "VN1 No Credits : RSP on BL : Number of Cycles there were no VN1 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x82", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x81", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x84", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0xc0", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", - "EventCode": "0x7E", - "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", - "EventCode": "0x7D", - "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARB", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.ARB", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message is making arbitration request", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARRIVED", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.ARRIVED", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message arrived in ingress pipeline", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.BYPASS", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.BYPASS", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message took bypass path", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.FLITTED", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.FLITTED", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message was slotted into flit (non bypass)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message lost arbitration", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message was dropped because it became too old", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", - "PerPkg": "1", - "PublicDescription": ": xpt prefetch message was dropped because it was overwritten by new message while prefetch queue was full", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of kfclks", - "EventCode": "0x01", - "EventName": "UNC_UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of kfclks : Counts the number of clocks in the UPI LL. This clock runs at 1/8th the GT/s speed of the UPI link. For example, a 8GT/s link will have qfclk or 1GHz. Current products do not support dynamic link speeds, so this frequency is fixed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Direct packet attempts : D2C", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", - "PerPkg": "1", - "PublicDescription": "Direct packet attempts : D2C : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Direct packet attempts : D2K", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", - "PerPkg": "1", - "PublicDescription": "Direct packet attempts : D2K : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L1", - "EventCode": "0x21", - "EventName": "UNC_UPI_L1_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L1 : Number of UPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a UPI link. Use edge detect to count the number of instances when the UPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "EventCode": "0x16", - "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", - "EventCode": "0x20", - "EventName": "UNC_UPI_PHY_INIT_CYCLES", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req Nack", - "EventCode": "0x23", - "EventName": "UNC_UPI_POWER_L1_NACK", - "PerPkg": "1", - "PublicDescription": "L1 Req Nack : Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req (same as L1 Ack).", - "EventCode": "0x22", - "EventName": "UNC_UPI_POWER_L1_REQ", - "PerPkg": "1", - "PublicDescription": "L1 Req (same as L1 Ack). : Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0p", - "EventCode": "0x25", - "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0", - "EventCode": "0x24", - "EventName": "UNC_UPI_RxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Request", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Request : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - Conflict", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - Conflict : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - Invalid", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - Invalid : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - Data", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - No Data", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Snoop", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Snoop : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Writeback", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Writeback : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode", - "EventCode": "0x05", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 0 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 1 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 2 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "CRC Errors Detected", - "EventCode": "0x0B", - "EventName": "UNC_UPI_RxL_CRC_ERRORS", - "PerPkg": "1", - "PublicDescription": "CRC Errors Detected : Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "LLR Requests Sent", - "EventCode": "0x08", - "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", - "PerPkg": "1", - "PublicDescription": "LLR Requests Sent : Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN0 Credit Consumed", - "EventCode": "0x39", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", - "PerPkg": "1", - "PublicDescription": "VN0 Credit Consumed : Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN1 Credit Consumed", - "EventCode": "0x3A", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", - "PerPkg": "1", - "PublicDescription": "VN1 Credit Consumed : Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credit Consumed", - "EventCode": "0x38", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", - "PerPkg": "1", - "PublicDescription": "VNA Credit Consumed : Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : All Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : All Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Null FLITs received from any slot", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Null FLITs received from any slot : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Null FLITs received from any slot", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Null FLITs received from any slot : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : LLCRD Not Empty", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : LLCTRL", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : All Non Data", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Protocol Header", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 0", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 1", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received : Slot 2", - "EventCode": "0x03", - "EventName": "UNC_UPI_RxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Valid Flits Received : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 0 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 1 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Flit Buffer Allocations : Slot 2 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 0 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 1 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", - "PerPkg": "1", - "PublicDescription": "RxQ Occupancy - All Packets : Slot 2 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0p", - "EventCode": "0x27", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "EventCode": "0x28", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "EventCode": "0x29", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0", - "EventCode": "0x26", - "EventName": "UNC_UPI_TxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Request", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Request : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Conflict", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Conflict : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Invalid", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Invalid : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Data", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - No Data", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Snoop", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Writeback", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode", - "EventCode": "0x04", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Bypassed", - "EventCode": "0x41", - "EventName": "UNC_UPI_TxL_BYPASSED", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Bypassed : Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the UPI Link. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : All Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : All Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Null FLITs transmitted to any slot", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Null FLITs transmitted to any slot : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Idle", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Idle : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : LLCTRL", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : All Non Data", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.NULL", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Protocol Header", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 0", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 1", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent : Slot 2", - "EventCode": "0x02", - "EventName": "UNC_UPI_TxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Valid Flits Sent : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Allocations", - "EventCode": "0x40", - "EventName": "UNC_UPI_TxL_INSERTS", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x42", - "EventName": "UNC_UPI_TxL_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "EventCode": "0x45", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credits Pending Return - Occupancy", - "EventCode": "0x44", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "VNA Credits Pending Return - Occupancy : Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", - "EventCode": "0xff", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : Doorbell", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : Interrupt", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Message Received : Interrupt : Interrupts", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : IPI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : MSI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : VLW", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "IDI Lock/SplitLock Cycles : Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", - "EventCode": "0x4F", - "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", - "EventCode": "0x4F", - "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDRAND", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDSEED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - } -] -- GitLab From c2f38d3b95e600d3a9a7195a2db57f7d47fb0664 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:41 -0700 Subject: [PATCH 3001/5631] perf vendor events intel: Fix uncore topics for ivybridge Remove 'uncore-other' topic classification, move to cache and interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-14-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/ivybridge/uncore-cache.json | 50 +++++++++---------- ...re-other.json => uncore-interconnect.json} | 0 2 files changed, 25 insertions(+), 25 deletions(-) rename tools/perf/pmu-events/arch/x86/ivybridge/{uncore-other.json => uncore-interconnect.json} (100%) diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore-cache.json index c538557ba4c0..be9a3ed1a940 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore-cache.json @@ -5,7 +5,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", "PerPkg": "1", "UMask": "0x86", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", @@ -13,7 +13,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", @@ -21,7 +21,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", @@ -29,7 +29,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", "PerPkg": "1", "UMask": "0x8f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", @@ -37,7 +37,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", "PerPkg": "1", "UMask": "0x46", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", @@ -45,7 +45,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", @@ -53,7 +53,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", @@ -61,7 +61,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", "PerPkg": "1", "UMask": "0x4f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", @@ -69,7 +69,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", "PerPkg": "1", "UMask": "0x16", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", @@ -77,7 +77,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", "PerPkg": "1", "UMask": "0x18", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", @@ -85,7 +85,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", "PerPkg": "1", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", @@ -93,7 +93,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", "PerPkg": "1", "UMask": "0x1f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", @@ -101,7 +101,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", "PerPkg": "1", "UMask": "0x26", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", @@ -109,7 +109,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", @@ -117,7 +117,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", @@ -125,7 +125,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", "PerPkg": "1", "UMask": "0x2f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", @@ -133,7 +133,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a modified line in some processor core.", @@ -141,7 +141,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", @@ -149,7 +149,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", @@ -157,7 +157,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", "PerPkg": "1", "UMask": "0x84", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a non-modified line in some processor core.", @@ -165,7 +165,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", "PerPkg": "1", "UMask": "0x24", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", @@ -173,7 +173,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", @@ -181,7 +181,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop misses in some processor core.", @@ -189,7 +189,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", @@ -197,6 +197,6 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore-interconnect.json similarity index 100% rename from tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json rename to tools/perf/pmu-events/arch/x86/ivybridge/uncore-interconnect.json -- GitLab From 14b4c54485bbab73e54c9170b8c9eae3f642edc2 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:42 -0700 Subject: [PATCH 3002/5631] perf vendor events intel: Fix uncore topics for ivytown Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/ivytown/uncore-cache.json | 314 +-- .../arch/x86/ivytown/uncore-interconnect.json | 2025 +++++++++++++-- .../arch/x86/ivytown/uncore-io.json | 549 +++++ .../arch/x86/ivytown/uncore-other.json | 2174 ----------------- 4 files changed, 2531 insertions(+), 2531 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json index 521175881173..8bf2706eb6d5 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json @@ -3,7 +3,7 @@ "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Counter 0 Occupancy", @@ -11,7 +11,7 @@ "EventName": "UNC_C_COUNTER0_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Any Request", @@ -20,7 +20,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Data Read Request", @@ -29,7 +29,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Read transactions", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Lookups that Match NID", @@ -38,7 +38,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; External Snoop Request", @@ -47,7 +47,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", "UMask": "0x9", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Write Requests", @@ -56,7 +56,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:17] bits correspond to [M'FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", "UMask": "0x5", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in E state", @@ -65,7 +65,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -74,7 +74,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in M state", @@ -83,7 +83,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", @@ -92,7 +92,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.; Qualify one of the other subevents by the Target NID. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in S State", @@ -101,7 +101,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; RFO HitS", @@ -110,7 +110,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Number of times that an RFO hit in S state. This is useful for determining if it might be good for a workload to use RspIWB instead of RspSWB.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Silent Snoop Eviction", @@ -119,7 +119,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc", @@ -128,7 +128,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Write Combining Aliasing", @@ -137,7 +137,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 0", @@ -146,7 +146,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 0", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 1", @@ -155,7 +155,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 2", @@ -164,7 +164,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 2", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Age 3", @@ -173,7 +173,7 @@ "PerPkg": "1", "PublicDescription": "How often age was set to 3", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; LRU Bits Decremented", @@ -182,7 +182,7 @@ "PerPkg": "1", "PublicDescription": "How often all LRU bits were decremented by 1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "LRU Queue; Non-0 Aged Victim", @@ -191,7 +191,7 @@ "PerPkg": "1", "PublicDescription": "How often we picked a victim that had a non-zero age", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Counterclockwise", @@ -200,7 +200,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Clockwise", @@ -209,7 +209,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down", @@ -218,7 +218,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even on Vring 0", @@ -227,7 +227,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd on Vring 0", @@ -236,7 +236,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even on VRing 1", @@ -245,7 +245,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd on VRing 1", @@ -254,7 +254,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up", @@ -263,7 +263,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x33", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even on Vring 0", @@ -272,7 +272,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd on Vring 0", @@ -281,7 +281,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even on VRing 1", @@ -290,7 +290,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd on VRing 1", @@ -299,7 +299,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Counterclockwise", @@ -308,7 +308,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Clockwise", @@ -317,7 +317,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down", @@ -326,7 +326,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even on Vring 0", @@ -335,7 +335,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd on Vring 0", @@ -344,7 +344,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even on VRing 1", @@ -353,7 +353,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd on VRing 1", @@ -362,7 +362,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up", @@ -371,7 +371,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x33", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even on Vring 0", @@ -380,7 +380,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd on Vring 0", @@ -389,7 +389,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even on VRing 1", @@ -398,7 +398,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd on VRing 1", @@ -407,7 +407,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Counterclockwise", @@ -416,7 +416,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Clockwise", @@ -425,7 +425,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down", @@ -434,7 +434,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even on Vring 0", @@ -443,7 +443,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 0.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd on Vring 0", @@ -452,7 +452,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 0.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even on VRing 1", @@ -461,7 +461,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Even ring polarity on Virtual Ring 1.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd on VRing 1", @@ -470,7 +470,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Down and Odd ring polarity on Virtual Ring 1.", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up", @@ -479,7 +479,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x33", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even on Vring 0", @@ -488,7 +488,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 0.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd on Vring 0", @@ -497,7 +497,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 0.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even on VRing 1", @@ -506,7 +506,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Even ring polarity on Virtual Ring 1.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd on VRing 1", @@ -515,7 +515,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.; Filters for the Up and Odd ring polarity on Virtual Ring 1.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.", @@ -523,7 +523,7 @@ "EventName": "UNC_C_RING_BOUNCES.AD_IRQ", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", @@ -531,7 +531,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.: Acknowledgements to core", @@ -539,7 +539,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK_CORE", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", @@ -547,7 +547,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.: Data Responses to core", @@ -555,7 +555,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL_CORE", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", @@ -563,7 +563,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.: Snoops of processor's cache.", @@ -571,7 +571,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV_CORE", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IV Ring in Use; Any", @@ -580,7 +580,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters any polarity", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IV Ring in Use; Down", @@ -589,7 +589,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for Down polarity", "UMask": "0xcc", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IV Ring in Use; Up", @@ -598,34 +598,34 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for Up polarity", "UMask": "0x33", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AD_IPQ", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AD_IRQ", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.IV", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", @@ -634,7 +634,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IPQ is externally startved and therefore we are blocking the IRQ.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", @@ -643,7 +643,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; IRQ is externally starved and therefore we are blocking the IPQ.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", @@ -652,7 +652,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.; Number of times that the ISMQ Bid.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles", @@ -661,7 +661,7 @@ "PerPkg": "1", "PublicDescription": "IRQ is blocking the ingress queue and causing the starvation.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IPQ", @@ -670,7 +670,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ", @@ -679,7 +679,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ Rejected", @@ -688,7 +688,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations: IRQ Rejected", @@ -697,7 +697,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; VFIFO", @@ -706,7 +706,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.; Counts the number of allocations into the IRQ Ordering FIFO. In JKT, it is necessary to keep IO requests in order. Therefore, they are allocated into an ordering FIFO that sits next to the IRQ, and must be satisfied from the FIFO in order (with respect to each other). This event, in conjunction with the Occupancy Accumulator event, can be used to calculate average lifetime in the FIFO. Transactions are allocated into the FIFO as soon as they enter the Cachebo (and the IRQ) and are deallocated from the FIFO as soon as they are deallocated from the IRQ.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", @@ -715,7 +715,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IPQ in Internal Starvation.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", @@ -724,7 +724,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the IRQ in Internal Starvation.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", @@ -733,7 +733,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.; Cycles with the ISMQ in Internal Starvation.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Address Conflict", @@ -742,7 +742,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from an address conflicts. Address conflicts out of the IPQ should be rare. They will generally only occur if two different sockets are sending requests to the same address at the same time. This is a true conflict case, unlike the IPQ Address Conflict which is commonly caused by prefetching characteristics.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Any Reject", @@ -751,7 +751,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject. TOR rejects from the IPQ can be caused by the Egress being full or Address Conflicts.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No Egress Credits", @@ -760,7 +760,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.; Counts the number of times that a request form the IPQ was retried because of a TOR reject from the Egress being full. IPQ requests make use of the AD Egress for regular responses, the BL egress to forward data, and the AK egress to return credits.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No QPI Credits", @@ -769,7 +769,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", @@ -778,7 +778,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because of an address match in the TOR. In order to maintain coherency, requests to the same address are not allowed to pass each other up in the Cbo. Therefore, if there is an outstanding request to a given address, one cannot issue another request to that address until it is complete. This comes up most commonly with prefetches. Outstanding prefetches occasionally will not complete their memory fetch and a demand request to the same address will then sit in the IRQ and get retried until the prefetch fills the data into the LLC. Therefore, it will not be uncommon to see this case in high bandwidth streaming workloads when the LLC Prefetcher in the core is enabled.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Any Reject", @@ -787,7 +787,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of IRQ retries that occur. Requests from the IRQ are retried if they are rejected from the TOR pipeline for a variety of reasons. Some of the most common reasons include if the Egress is full, there are no RTIDs, or there is a Physical Address match to another outstanding request.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", @@ -796,7 +796,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that a request from the IRQ was retried because it failed to acquire an entry in the Egress. The egress is the buffer that queues up for allocating onto the ring. IRQ requests can make use of all four rings and all four Egresses. If any of the queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No IIO Credits", @@ -805,7 +805,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", @@ -814,7 +814,7 @@ "PerPkg": "1", "PublicDescription": "Number of requests rejects because of lack of QPI Ingress credits. These credits are required in order to send transactions to the QPI agent. Please see the QPI_IGR_CREDITS events for more information.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", @@ -823,7 +823,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that requests from the IRQ were retried because there were no RTIDs available. RTIDs are required after a request misses the LLC and needs to send snoops and/or requests to memory. If there are no RTIDs available, requests will queue up in the IRQ and retry until one becomes available. Note that there are multiple RTID pools for the different sockets. There may be cases where the local RTIDs are all used, but requests destined for remote memory can still acquire an RTID because there are remote RTIDs available. This event does not provide any filtering for this case.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; Any Reject", @@ -832,7 +832,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the total number of times that a request from the ISMQ retried because of a TOR reject. ISMQ requests generally will not need to retry (or at least ISMQ retries are less common than IRQ retries). ISMQ requests will retry if they are not able to acquire a needed Egress credit to get onto the ring, or for cache evictions that need to acquire an RTID. Most ISMQ requests already have an RTID, so eviction retries will be less common here.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No Egress Credits", @@ -841,7 +841,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by a lack of Egress credits. The egress is the buffer that queues up for allocating onto the ring. If any of the Egress queues that a given request needs to make use of are full, the request will be retried.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No IIO Credits", @@ -850,7 +850,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Number of times a request attempted to acquire the NCS/NCB credit for sending messages on BL to the IIO. There is a single credit in each CBo that is shared between the NCS and NCB message classes for sending transactions on the BL ring (such as read data) to the IIO.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No QPI Credits", @@ -859,7 +859,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No RTIDs", @@ -868,7 +868,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Counts the number of times that a request from the ISMQ retried because of a TOR reject caused by no RTIDs. M-state cache evictions are serviced through the ISMQ, and must acquire an RTID in order to write back to memory. If no RTIDs are available, they will be retried.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No WB Credits", @@ -877,7 +877,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.; Retries of writes to local memory due to lack of HT WB credits", "UMask": "0x80", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IPQ", @@ -886,7 +886,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ", @@ -895,7 +895,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ Rejected", @@ -904,7 +904,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "IRQ Rejected", @@ -913,7 +913,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; VFIFO", @@ -922,7 +922,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.; Accumulates the number of used entries in the IRQ Ordering FIFO in each cycle. In JKT, it is necessary to keep IO requests in order. Therefore, they are allocated into an ordering FIFO that sits next to the IRQ, and must be satisfied from the FIFO in order (with respect to each other). This event, in conjunction with the Allocations event, can be used to calculate average lifetime in the FIFO. This event can be used in conjunction with the Not Empty event to calculate average queue occupancy. Transactions are allocated into the FIFO as soon as they enter the Cachebo (and the IRQ) and are deallocated from the FIFO as soon as they are deallocated from the IRQ.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; All", @@ -931,7 +931,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Evictions", @@ -940,7 +940,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Eviction transactions inserted into the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory", @@ -949,7 +949,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Local Memory - Opcode Matched", @@ -958,7 +958,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory", @@ -967,7 +967,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Local Memory - Opcode Matched", @@ -976,7 +976,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss Opcode Match", @@ -985,7 +985,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match an opcode.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory", @@ -994,7 +994,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Misses to Remote Memory - Opcode Matched", @@ -1003,7 +1003,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched", @@ -1012,7 +1012,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched (matches an RTID destination) transactions inserted into the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid. In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Evictions", @@ -1021,7 +1021,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched eviction transactions inserted into the TOR.", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Miss All", @@ -1030,7 +1030,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All NID matched miss requests that were inserted into the TOR.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", @@ -1039,7 +1039,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Miss transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched", @@ -1048,7 +1048,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Writebacks", @@ -1057,7 +1057,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; NID matched write transactions inserted into the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Opcode Match", @@ -1066,7 +1066,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Transactions inserted into the TOR that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory", @@ -1075,7 +1075,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Remote Memory - Opcode Matched", @@ -1084,7 +1084,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; All transactions, satisfied by an opcode, inserted into the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Writebacks", @@ -1093,7 +1093,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).; Write transactions inserted into the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Any", @@ -1102,7 +1102,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All valid TOR entries. This includes requests that reside in the TOR for a short time, such as LLC Hits that do not need to snoop cores or requests that get rejected and have to be retried through one of the ingress queues. The TOR is more commonly a bottleneck in skews with smaller core counts, where the ratio of RTIDs to TOR entries is larger. Note that there are reserved TOR entries for various request types, so it is possible that a given request type be blocked with an occupancy that is less than 20. Also note that generally requests will not be able to arbitrate into the TOR pipeline if there are no available TOR slots.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Evictions", @@ -1111,7 +1111,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding eviction transactions in the TOR. Evictions can be quick, such as when the line is in the F, S, or E states and no core valid bits are set. They can also be longer if either CV bits are set (so the cores need to be snooped) and/or if there is a HitM (in which case it is necessary to write the request out to memory).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1120,7 +1120,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Local Memory - Opcode Matched", @@ -1129,7 +1129,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss All", @@ -1138,7 +1138,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding miss requests in the TOR. 'Miss' means the allocation requires an RTID. This generally means that the request was sent to memory or MMIO.", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1147,7 +1147,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x2a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Local Memory - Opcode Matched", @@ -1156,7 +1156,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by locally HOMed memory.", "UMask": "0x23", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss Opcode Match", @@ -1165,7 +1165,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries for miss transactions that match an opcode. This generally means that the request was sent to memory or MMIO.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1174,7 +1174,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x8a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Misses to Remote Memory - Opcode Matched", @@ -1183,7 +1183,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x83", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1192,7 +1192,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of NID matched outstanding requests in the TOR. The NID is programmed in Cn_MSR_PMON_BOX_FILTER.nid.In conjunction with STATE = I, it is possible to monitor misses to specific NIDs in the system.", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Evictions", @@ -1201,7 +1201,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding NID matched eviction transactions in the TOR .", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -1210,7 +1210,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID.", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", @@ -1219,7 +1219,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding Miss requests in the TOR that match a NID and an opcode.", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched", @@ -1228,7 +1228,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match a NID and an opcode.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Writebacks", @@ -1237,7 +1237,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); NID matched write transactions int the TOR.", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Opcode Match", @@ -1246,7 +1246,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); TOR entries that match an opcode (matched by Cn_MSR_PMON_BOX_FILTER.opc).", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy", @@ -1255,7 +1255,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Remote Memory - Opcode Matched", @@ -1264,7 +1264,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Number of outstanding transactions, satisfied by an opcode, in the TOR that are satisfied by remote caches or remote memory.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Writebacks", @@ -1273,7 +1273,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); Write transactions in the TOR. This does not include RFO, but actual operations that contain data being sent from the core.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AD Ring", @@ -1281,7 +1281,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AD", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto AK Ring", @@ -1289,7 +1289,7 @@ "EventName": "UNC_C_TxR_ADS_USED.AK", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Onto BL Ring", @@ -1297,7 +1297,7 @@ "EventName": "UNC_C_TxR_ADS_USED.BL", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Cachebo", @@ -1306,7 +1306,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Corebo", @@ -1315,7 +1315,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AD ring. This is commonly used for outbound requests.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Cachebo", @@ -1324,7 +1324,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the AK ring. This is commonly used for credit returns and GO responses.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Corebo", @@ -1333,7 +1333,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the AK ring. This is commonly used for snoop responses coming from the core and destined for a Cachebo.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Cacheno", @@ -1342,7 +1342,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the BL ring. This is commonly used to send data from the cache to various destinations.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Corebo", @@ -1351,7 +1351,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Corebo destined for the BL ring. This is commonly used for transferring writeback data to the cache.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; IV - Cachebo", @@ -1360,7 +1360,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.; Ring transactions from the Cachebo destined for the IV ring. This is commonly used for snoops to the cores.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AD Ring (to core)", @@ -1369,7 +1369,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the core AD egress spent in starvation", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AK Ring", @@ -1378,7 +1378,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that both AK egresses spent in starvation", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto IV Ring", @@ -1387,7 +1387,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.; cycles that the cachebo IV egress spent in starvation", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BT Bypass", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json index e1b9799e3036..ccf451534d16 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -1,11 +1,316 @@ [ + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When two requests to the same address from the same source are received back to back, it is possible to merge the two of them together.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When it is not possible to merge two conflicting requests, a stall event occurs. This is bad for performance.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Any Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Select Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks all requests from any source port.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Any Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Select Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Any Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Select Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "EventCode": "0xb", + "EventName": "UNC_I_RxR_AK_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xa", + "EventName": "UNC_I_RxR_AK_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0xc", + "EventName": "UNC_I_RxR_AK_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Ownership Lost", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of requests that lost ownership as a result of a tickle. When a tickle comes in, if the request is not at the head of the queue in the switch, then that request as well as any requests behind it in the switch queue will lose ownership and have to re-acquire it later when they get to the head of the queue. This will therefore track the number of requests that lost ownership and not just the number of tickles.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Data Returned", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of cases when a tickle was received but the requests was at the head of the queue in the switch. In this case, data is returned rather than releasing ownership.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count: Read Prefetches", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.RD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xe", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xf", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xd", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ordering Stalls", + "EventCode": "0x1a", + "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", + "Unit": "IRP" + }, { "BriefDescription": "Number of qfclks", "EventCode": "0x14", "EventName": "UNC_Q_CLOCKTICKS", "PerPkg": "1", "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/8th the GT/s speed of the QPI link. For example, a 8GT/s link will have qfclk or 1GHz. JKT does not support dynamic link speeds, so this frequency is fixed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Count of CTO Events", @@ -13,7 +318,7 @@ "EventName": "UNC_Q_CTO_COUNT", "PerPkg": "1", "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", @@ -22,7 +327,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", @@ -31,7 +336,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", @@ -40,7 +345,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", @@ -49,7 +354,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", "UMask": "0x80", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", @@ -58,7 +363,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", @@ -67,7 +372,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", @@ -76,7 +381,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", "UMask": "0x40", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Success", @@ -85,7 +390,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L1", @@ -93,205 +398,205 @@ "EventName": "UNC_Q_L1_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MATCH_MASK", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyDataC", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp11flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp9flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E_Cmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E_FrcAckCnflt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F_Cmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F_FrcAckCnflt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_M", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbEData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbIData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbSData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.AnyReq", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.AnyResp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwd", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdI", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdIWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdS", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdSWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespIWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespSWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyInt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg11flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg9flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.AnyMsg1or2flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.AnyMsg3flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.NcRd", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NDR.AnyCmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.SNP.AnySnp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -299,7 +604,7 @@ "EventName": "UNC_Q_RxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -307,7 +612,7 @@ "EventName": "UNC_Q_RxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Bypassed", @@ -315,7 +620,7 @@ "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; LinkInit", @@ -324,7 +629,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; Normal Operations", @@ -333,7 +638,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during normal operation.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; DRS", @@ -342,7 +647,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; HOM", @@ -351,7 +656,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCB", @@ -360,7 +665,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCS", @@ -369,7 +674,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NDR", @@ -378,7 +683,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; SNP", @@ -387,7 +692,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; DRS", @@ -396,7 +701,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; HOM", @@ -405,7 +710,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NCB", @@ -414,7 +719,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NCS", @@ -423,7 +728,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NDR", @@ -432,7 +737,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; SNP", @@ -441,7 +746,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credit Consumed", @@ -449,7 +754,7 @@ "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty", @@ -457,7 +762,7 @@ "EventName": "UNC_Q_RxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", @@ -466,7 +771,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", @@ -475,7 +780,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", @@ -484,7 +789,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", @@ -493,7 +798,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", @@ -502,7 +807,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", @@ -511,7 +816,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", @@ -520,7 +825,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", @@ -529,7 +834,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", @@ -538,7 +843,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", @@ -547,7 +852,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", @@ -556,7 +861,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", @@ -565,7 +870,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Data Tx Flits", @@ -574,7 +879,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits received over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", @@ -583,7 +888,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Non-Data protocol Tx Flits", @@ -592,7 +897,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits received across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", @@ -601,7 +906,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Data Flits", @@ -610,7 +915,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Header Flits", @@ -619,7 +924,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Flits", @@ -628,7 +933,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", @@ -637,7 +942,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Request Flits", @@ -646,7 +951,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; SNP Flits", @@ -655,7 +960,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", @@ -664,7 +969,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", @@ -673,7 +978,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", @@ -682,7 +987,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", @@ -691,7 +996,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", @@ -700,7 +1005,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", @@ -709,7 +1014,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations", @@ -717,7 +1022,7 @@ "EventName": "UNC_Q_RxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS", @@ -725,7 +1030,7 @@ "EventName": "UNC_Q_RxL_INSERTS_DRS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", @@ -734,7 +1039,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", @@ -743,7 +1048,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM", @@ -751,7 +1056,7 @@ "EventName": "UNC_Q_RxL_INSERTS_HOM", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", @@ -760,7 +1065,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", @@ -769,7 +1074,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB", @@ -777,7 +1082,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCB", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", @@ -786,7 +1091,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", @@ -795,7 +1100,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS", @@ -803,7 +1108,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", @@ -812,7 +1117,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", @@ -821,7 +1126,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR", @@ -829,7 +1134,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NDR", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", @@ -838,7 +1143,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", @@ -847,7 +1152,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP", @@ -855,7 +1160,7 @@ "EventName": "UNC_Q_RxL_INSERTS_SNP", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", @@ -864,7 +1169,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", @@ -873,7 +1178,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - All Packets", @@ -881,7 +1186,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS", @@ -889,7 +1194,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_DRS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS; for VN0", @@ -898,7 +1203,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS; for VN1", @@ -907,7 +1212,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM", @@ -915,7 +1220,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_HOM", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM; for VN0", @@ -924,7 +1229,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM; for VN1", @@ -933,7 +1238,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB", @@ -941,7 +1246,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCB", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB; for VN0", @@ -950,7 +1255,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB; for VN1", @@ -959,7 +1264,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS", @@ -967,7 +1272,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS; for VN0", @@ -976,7 +1281,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS; for VN1", @@ -985,7 +1290,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR", @@ -993,7 +1298,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NDR", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR; for VN0", @@ -1002,7 +1307,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR; for VN1", @@ -1011,7 +1316,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP", @@ -1019,7 +1324,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_SNP", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP; for VN0", @@ -1028,7 +1333,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP; for VN1", @@ -1037,7 +1342,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", @@ -1046,7 +1351,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", @@ -1055,7 +1360,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", @@ -1064,7 +1369,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", @@ -1073,7 +1378,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", @@ -1082,7 +1387,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", @@ -1091,7 +1396,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", @@ -1100,7 +1405,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", "UMask": "0x40", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", @@ -1109,7 +1414,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", "UMask": "0x80", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", @@ -1118,7 +1423,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", @@ -1127,7 +1432,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", @@ -1136,7 +1441,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", @@ -1145,7 +1450,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", @@ -1154,7 +1459,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", @@ -1163,7 +1468,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -1171,7 +1476,7 @@ "EventName": "UNC_Q_TxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -1179,7 +1484,7 @@ "EventName": "UNC_Q_TxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Bypassed", @@ -1187,7 +1492,7 @@ "EventName": "UNC_Q_TxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", @@ -1196,7 +1501,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", @@ -1205,7 +1510,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Cycles not Empty", @@ -1213,7 +1518,7 @@ "EventName": "UNC_Q_TxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", @@ -1221,7 +1526,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", @@ -1229,7 +1534,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", @@ -1237,7 +1542,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", @@ -1245,7 +1550,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", @@ -1253,7 +1558,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Flits", @@ -1261,7 +1566,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", @@ -1269,7 +1574,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", @@ -1277,7 +1582,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; SNP Flits", @@ -1285,7 +1590,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", @@ -1294,7 +1599,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", @@ -1303,7 +1608,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", @@ -1312,7 +1617,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", @@ -1321,7 +1626,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", @@ -1330,7 +1635,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", @@ -1339,7 +1644,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Allocations", @@ -1347,7 +1652,7 @@ "EventName": "UNC_Q_TxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Occupancy", @@ -1355,7 +1660,7 @@ "EventName": "UNC_Q_TxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", @@ -1364,7 +1669,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", @@ -1373,7 +1678,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", @@ -1382,7 +1687,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", @@ -1391,7 +1696,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", @@ -1400,7 +1705,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", @@ -1409,7 +1714,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", @@ -1418,7 +1723,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", @@ -1427,7 +1732,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", @@ -1436,7 +1741,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", @@ -1445,7 +1750,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", @@ -1454,7 +1759,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", @@ -1463,7 +1768,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", @@ -1471,7 +1776,7 @@ "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", @@ -1480,7 +1785,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", @@ -1489,7 +1794,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", @@ -1497,7 +1802,7 @@ "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", @@ -1506,7 +1811,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", @@ -1515,7 +1820,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", @@ -1524,7 +1829,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", @@ -1533,7 +1838,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", @@ -1542,7 +1847,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", @@ -1551,7 +1856,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", @@ -1560,7 +1865,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", @@ -1569,7 +1874,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", @@ -1578,7 +1883,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", @@ -1587,7 +1892,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", @@ -1596,7 +1901,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", @@ -1605,7 +1910,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", @@ -1614,7 +1919,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", @@ -1623,7 +1928,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", @@ -1632,7 +1937,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", @@ -1641,7 +1946,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Returned", @@ -1649,7 +1954,7 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURNS", "PerPkg": "1", "PublicDescription": "Number of VNA credits returned.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Pending Return - Occupancy", @@ -1657,6 +1962,1326 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "QPI LL" + "Unit": "QPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", + "UMask": "0xff", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "AD Ingress Bypassed", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_AD_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the AD Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Bypassed", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_BYPASSED.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CCW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AK", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CCW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AD", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AK", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.BL", + "PerPkg": "1", + "PublicDescription": "BL Clockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; DRS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; HOM Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCB Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NDR Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with no VNA credits available", + "EventCode": "0x31", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with 1 or more VNA credits in use", + "EventCode": "0x32", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", + "Unit": "R3QPI" + }, + { + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-io.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-io.json new file mode 100644 index 000000000000..5887e6ebcfa8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-io.json @@ -0,0 +1,549 @@ +[ + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R2_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; DRS", + "EventCode": "0x34", + "EventName": "UNC_R2_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; DRS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCB", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 1", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 1", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 1", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 1", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 1", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 1", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 1", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 1", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 1", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x40", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 1", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x80", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 1", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR1_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 1", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_VR1_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R2_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", + "UMask": "0xff", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "EventCode": "0xa", + "EventName": "UNC_R2_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", + "UMask": "0xcc", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "EventCode": "0xa", + "EventName": "UNC_R2_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", + "UMask": "0x33", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Counterclockwise", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced; Clockwise", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R2_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AD", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AK", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; BL", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AD", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AK", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; BL", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AD CCW", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.AD", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; AK CCW", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.AK", + "PerPkg": "1", + "PublicDescription": "AK CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CCW NACK; BL CCW", + "EventCode": "0x28", + "EventName": "UNC_R2_TxR_NACK_CCW.BL", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; AD CW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.AD", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; AK CW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.AK", + "PerPkg": "1", + "PublicDescription": "AK Clockwise Egress Queue", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress CW NACK; BL CW", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACK_CW.BL", + "PerPkg": "1", + "PublicDescription": "BL Clockwise Egress Queue", + "UMask": "0x4", + "Unit": "R2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json deleted file mode 100644 index af9d14a6d145..000000000000 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-other.json +++ /dev/null @@ -1,2174 +0,0 @@ -[ - { - "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", - "EventCode": "0x17", - "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When two requests to the same address from the same source are received back to back, it is possible to merge the two of them together.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", - "EventCode": "0x17", - "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When it is not possible to merge two conflicting requests, a stall event occurs. This is bad for performance.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ack Pending Occupancy; Any Source", - "EventCode": "0x14", - "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ack Pending Occupancy; Select Source", - "EventCode": "0x14", - "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks all requests from any source port.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", - "EventCode": "0x13", - "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", - "EventCode": "0x13", - "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Read Occupancy; Any Source", - "EventCode": "0x10", - "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Read Occupancy; Select Source", - "EventCode": "0x10", - "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Select Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Occupancy; Any Source", - "EventCode": "0x11", - "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Occupancy; Select Source", - "EventCode": "0x11", - "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Clocks in the IRP", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of clocks in the IRP.", - "Unit": "IRP" - }, - { - "EventCode": "0xb", - "EventName": "UNC_I_RxR_AK_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Ingress Occupancy", - "EventCode": "0xa", - "EventName": "UNC_I_RxR_AK_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "EventCode": "0xc", - "EventName": "UNC_I_RxR_AK_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "EventCode": "0x4", - "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - DRS", - "EventCode": "0x1", - "EventName": "UNC_I_RxR_BL_DRS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x7", - "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x5", - "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCB", - "EventCode": "0x2", - "EventName": "UNC_I_RxR_BL_NCB_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x8", - "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x6", - "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCS", - "EventCode": "0x3", - "EventName": "UNC_I_RxR_BL_NCS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x9", - "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "Tickle Count; Ownership Lost", - "EventCode": "0x16", - "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", - "PerPkg": "1", - "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of requests that lost ownership as a result of a tickle. When a tickle comes in, if the request is not at the head of the queue in the switch, then that request as well as any requests behind it in the switch queue will lose ownership and have to re-acquire it later when they get to the head of the queue. This will therefore track the number of requests that lost ownership and not just the number of tickles.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Tickle Count; Data Returned", - "EventCode": "0x16", - "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", - "PerPkg": "1", - "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of cases when a tickle was received but the requests was at the head of the queue in the switch. In this case, data is returned rather than releasing ownership.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count: Read Prefetches", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.RD_PREFETCHES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x18", - "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x19", - "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xe", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xf", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xd", - "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ordering Stalls", - "EventCode": "0x1a", - "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", - "Unit": "IRP" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R2_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; DRS", - "EventCode": "0x34", - "EventName": "UNC_R2_IIO_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; DRS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCB", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).; Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even on VRing 1", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x40", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd on VRing 1", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x80", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Even on VRing 1", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd on VRing 1", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even on VRing 1", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x40", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd on VRing 1", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x80", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Even on VRing 1", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd on VRing 1", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even on VRing 1", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x40", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd on VRing 1", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x80", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Even on VRing 1", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_VR1_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 1.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd on VRing 1", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_VR1_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 1.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R2_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", - "UMask": "0xff", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Counterclockwise", - "EventCode": "0xa", - "EventName": "UNC_R2_RING_IV_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", - "UMask": "0xcc", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Clockwise", - "EventCode": "0xa", - "EventName": "UNC_R2_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", - "UMask": "0x33", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced", - "EventCode": "0x12", - "EventName": "UNC_R2_RxR_AK_BOUNCES", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Counterclockwise", - "EventCode": "0x12", - "EventName": "UNC_R2_RxR_AK_BOUNCES.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced; Clockwise", - "EventCode": "0x12", - "EventName": "UNC_R2_RxR_AK_BOUNCES.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCB", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCS", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R2_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the R2PCIe Ingress. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R2_RxR_OCCUPANCY.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given R2PCIe Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the R2PCIe Ingress Not Empty event to calculate average occupancy or the R2PCIe Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AD", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AK", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; BL", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AD", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AD Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AK", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; AK Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; BL", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.; BL Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AD CCW", - "EventCode": "0x28", - "EventName": "UNC_R2_TxR_NACK_CCW.AD", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; AK CCW", - "EventCode": "0x28", - "EventName": "UNC_R2_TxR_NACK_CCW.AK", - "PerPkg": "1", - "PublicDescription": "AK CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CCW NACK; BL CCW", - "EventCode": "0x28", - "EventName": "UNC_R2_TxR_NACK_CCW.BL", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CW NACK; AD CW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.AD", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CW NACK; AK CW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.AK", - "PerPkg": "1", - "PublicDescription": "AK Clockwise Egress Queue", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress CW NACK; BL CW", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACK_CW.BL", - "PerPkg": "1", - "PublicDescription": "BL Clockwise Egress Queue", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R3_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2c", - "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "CBox AD Credits Empty", - "EventCode": "0x2b", - "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", - "UMask": "0x80", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2f", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2f", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2f", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "HA/R2 AD Credits Empty", - "EventCode": "0x2f", - "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", - "PerPkg": "1", - "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 AD Credits Empty", - "EventCode": "0x29", - "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI0 BL Credits Empty", - "EventCode": "0x2d", - "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 AD Credits Empty", - "EventCode": "0x2a", - "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", - "UMask": "0x40", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "QPI1 BL Credits Empty", - "EventCode": "0x2e", - "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0xcc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x33", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Even on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_VR0_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd on VRing 0", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_VR0_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R2 IV Ring in Use; Any", - "EventCode": "0xA", - "EventName": "UNC_R3_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", - "UMask": "0xff", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R2 IV Ring in Use; Counterclockwise", - "EventCode": "0xa", - "EventName": "UNC_R3_RING_IV_USED.CCW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", - "UMask": "0xcc", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R2 IV Ring in Use; Clockwise", - "EventCode": "0xa", - "EventName": "UNC_R3_RING_IV_USED.CW", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", - "UMask": "0x33", - "Unit": "R3QPI" - }, - { - "BriefDescription": "AD Ingress Bypassed", - "EventCode": "0x12", - "EventName": "UNC_R3_RxR_AD_BYPASSED", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the AD Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Bypassed", - "EventCode": "0x12", - "EventName": "UNC_R3_RxR_BYPASSED.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; HOM", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NDR", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; SNP", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; DRS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; HOM", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NDR", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; SNP", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; HOM", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NCB", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NCS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NDR", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; SNP", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; AK CCW", - "EventCode": "0x28", - "EventName": "UNC_R3_TxR_NACK_CCW.AD", - "PerPkg": "1", - "PublicDescription": "BL CounterClockwise Egress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; BL CW", - "EventCode": "0x28", - "EventName": "UNC_R3_TxR_NACK_CCW.AK", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; BL CCW", - "EventCode": "0x28", - "EventName": "UNC_R3_TxR_NACK_CCW.BL", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; AD CW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK_CW.AD", - "PerPkg": "1", - "PublicDescription": "AD Clockwise Egress Queue", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; AD CCW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK_CW.AK", - "PerPkg": "1", - "PublicDescription": "AD CounterClockwise Egress Queue", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Egress NACK; AK CW", - "EventCode": "0x26", - "EventName": "UNC_R3_TxR_NACK_CW.BL", - "PerPkg": "1", - "PublicDescription": "BL Clockwise Egress Queue", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; DRS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; HOM Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NDR Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x39", - "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; DRS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; HOM Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCB Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCS Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; NDR Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN1 Credit Used; SNP Message Class", - "EventCode": "0x38", - "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions; HOM Message Class", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; DRS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; HOM Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCB Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NDR Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; SNP Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Cycles with no VNA credits available", - "EventCode": "0x31", - "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", - "PerPkg": "1", - "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Cycles with 1 or more VNA credits in use", - "EventCode": "0x32", - "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", - "PerPkg": "1", - "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", - "Unit": "R3QPI" - }, - { - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.CMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Livelock", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; LTError", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LTERROR", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T0", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T1", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Other", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.OTHER", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Trap", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.TRAP", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.UMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x20", - "Unit": "UBOX" - } -] -- GitLab From 05c74de4ecb66c75b63a348b0cb5a95bab92ce98 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:43 -0700 Subject: [PATCH 3003/5631] perf vendor events intel: Fix uncore topics for jaketown Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-16-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/jaketown/uncore-cache.json | 194 +-- .../x86/jaketown/uncore-interconnect.json | 1237 ++++++++++++++- .../arch/x86/jaketown/uncore-io.json | 324 ++++ .../arch/x86/jaketown/uncore-other.json | 1393 ----------------- 4 files changed, 1574 insertions(+), 1574 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json index 47830ca5c682..63395e7ee0ce 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json @@ -3,7 +3,7 @@ "BriefDescription": "Uncore Clocks", "EventName": "UNC_C_CLOCKTICKS", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Counter 0 Occupancy", @@ -11,13 +11,13 @@ "EventName": "UNC_C_COUNTER0_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x21", "EventName": "UNC_C_ISMQ_DRD_MISS_OCC", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Data Read Request", @@ -26,7 +26,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; RTID", @@ -35,7 +35,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; External Snoop Request", @@ -44,7 +44,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.", "UMask": "0x9", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cache Lookups; Write Requests", @@ -53,7 +53,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set filter mask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CBoGlCtrl[22:18] bits correspond to [FMESI] state.", "UMask": "0x5", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in E state", @@ -62,7 +62,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized", @@ -71,7 +71,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in M state", @@ -80,7 +80,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Victimized Lines that Match NID", @@ -89,7 +89,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Lines Victimized; Lines in S State", @@ -98,7 +98,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; RFO HitS", @@ -107,7 +107,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Silent Snoop Eviction", @@ -116,7 +116,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc", @@ -125,7 +125,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Cbo Misc; Write Combining Aliasing", @@ -134,7 +134,7 @@ "PerPkg": "1", "PublicDescription": "Miscellaneous events in the Cbo.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Even", @@ -143,7 +143,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Down and Odd", @@ -152,7 +152,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Even", @@ -161,7 +161,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AD Ring In Use; Up and Odd", @@ -170,7 +170,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Even", @@ -179,7 +179,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Down and Odd", @@ -188,7 +188,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Even", @@ -197,7 +197,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "AK Ring In Use; Up and Odd", @@ -206,7 +206,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Even", @@ -215,7 +215,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Down and Odd", @@ -224,7 +224,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Even", @@ -233,7 +233,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Up and Odd", @@ -242,7 +242,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the 'UP' direction is on the clockwise ring and 'DN' is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Acknowledgements to core", @@ -250,7 +250,7 @@ "EventName": "UNC_C_RING_BOUNCES.AK_CORE", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Data Responses to core", @@ -258,7 +258,7 @@ "EventName": "UNC_C_RING_BOUNCES.BL_CORE", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Number of LLC responses that bounced on the Ring.; Snoops of processor's cache.", @@ -266,7 +266,7 @@ "EventName": "UNC_C_RING_BOUNCES.IV_CORE", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "BL Ring in Use; Any", @@ -275,41 +275,41 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring in JKT. Therefore, if one wants to monitor the 'Even' ring, they should select both UP_EVEN and DN_EVEN. To monitor the 'Odd' ring, they should select both UP_ODD and DN_ODD.", "UMask": "0xf", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AD_CACHE", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.AK_CORE", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.BL_CORE", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x6", "EventName": "UNC_C_RING_SINK_STARVED.IV_CORE", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x7", "EventName": "UNC_C_RING_SRC_THRTL", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IRQ", @@ -318,7 +318,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; IPQ", @@ -327,7 +327,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ", @@ -336,7 +336,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Arbiter Blocking Cycles; ISMQ_BID", @@ -345,7 +345,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in external starvation. This occurs when one of the ingress queues is being starved by the other queues.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IPQ", @@ -354,7 +354,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ", @@ -363,7 +363,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; IRQ Rejected", @@ -372,7 +372,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Allocations; VFIFO", @@ -381,7 +381,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IPQ", @@ -390,7 +390,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; IRQ", @@ -399,7 +399,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Internal Starvation Cycles; ISMQ", @@ -408,7 +408,7 @@ "PerPkg": "1", "PublicDescription": "Counts cycles in internal starvation. This occurs when one (or more) of the entries in the ingress queue are being starved out by other entries in that queue.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Address Conflict", @@ -417,7 +417,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; Any Reject", @@ -426,7 +426,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No Egress Credits", @@ -435,7 +435,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Probe Queue Retries; No QPI Credits", @@ -444,7 +444,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a snoop (probe) request had to retry. Filters exist to cover some of the common cases retries.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Address Conflict", @@ -452,7 +452,7 @@ "EventName": "UNC_C_RxR_IRQ_RETRY.ADDR_CONFLICT", "PerPkg": "1", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; Any Reject", @@ -460,7 +460,7 @@ "EventName": "UNC_C_RxR_IRQ_RETRY.ANY", "PerPkg": "1", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No Egress Credits", @@ -468,7 +468,7 @@ "EventName": "UNC_C_RxR_IRQ_RETRY.FULL", "PerPkg": "1", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No QPI Credits", @@ -476,7 +476,7 @@ "EventName": "UNC_C_RxR_IRQ_RETRY.QPI_CREDITS", "PerPkg": "1", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Request Queue Rejects; No RTIDs", @@ -484,7 +484,7 @@ "EventName": "UNC_C_RxR_IRQ_RETRY.RTID", "PerPkg": "1", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; Any Reject", @@ -493,7 +493,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No Egress Credits", @@ -502,7 +502,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No IIO Credits", @@ -511,7 +511,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No QPI Credits", @@ -520,7 +520,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "ISMQ Retries; No RTIDs", @@ -529,7 +529,7 @@ "PerPkg": "1", "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IPQ", @@ -538,7 +538,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ", @@ -547,7 +547,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; IRQ Rejected", @@ -556,7 +556,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Ingress Occupancy; VFIFO", @@ -565,7 +565,7 @@ "PerPkg": "1", "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Evictions", @@ -574,7 +574,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss All", @@ -583,7 +583,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Miss Opcode Match", @@ -592,7 +592,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched", @@ -601,7 +601,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Evictions", @@ -610,7 +610,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Miss All", @@ -619,7 +619,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched Miss", @@ -628,7 +628,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID and Opcode Matched", @@ -637,7 +637,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; NID Matched Writebacks", @@ -646,7 +646,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x50", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Opcode Match", @@ -655,7 +655,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Inserts; Writebacks", @@ -664,7 +664,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182).", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Any", @@ -673,7 +673,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Evictions", @@ -682,7 +682,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss All", @@ -691,7 +691,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0xa", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Miss Opcode Match", @@ -700,7 +700,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x3", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -709,7 +709,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched Evictions", @@ -718,7 +718,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID Matched", @@ -727,7 +727,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x4a", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched Miss", @@ -736,7 +736,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x43", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; NID and Opcode Matched", @@ -745,7 +745,7 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "TOR Occupancy; Opcode Match", @@ -754,13 +754,13 @@ "PerPkg": "1", "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select 'MISS_OPC_MATCH' and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182)", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "EventCode": "0x4", "EventName": "UNC_C_TxR_ADS_USED", "PerPkg": "1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Cachebo", @@ -769,7 +769,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x1", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AD - Corebo", @@ -778,7 +778,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x10", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Cachebo", @@ -787,7 +787,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; AK - Corebo", @@ -796,7 +796,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x20", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Cacheno", @@ -805,7 +805,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; BL - Corebo", @@ -814,7 +814,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x40", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Egress Allocations; IV - Cachebo", @@ -823,7 +823,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the Cbo Egress. The Egress is used to queue up requests destined for the ring.", "UMask": "0x8", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto AK Ring", @@ -832,7 +832,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x2", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "Injection Starvation; Onto BL Ring", @@ -841,7 +841,7 @@ "PerPkg": "1", "PublicDescription": "Counts injection starvation. This starvation is triggered when the Egress cannot send a transaction onto the ring for a long period of time.", "UMask": "0x4", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "HA to iMC Bypass; Not Taken", diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json index b16bb649225d..874f15ea8228 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -1,11 +1,307 @@ [ + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Any Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Select Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Any Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Select Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Any Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Select Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "EventCode": "0xB", + "EventName": "UNC_I_RxR_AK_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_RxR_AK_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0xC", + "EventName": "UNC_I_RxR_AK_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Ownership Lost", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Data Returned", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xF", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xD", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ordering Stalls", + "EventCode": "0x1A", + "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", + "Unit": "IRP" + }, { "BriefDescription": "Number of qfclks", "EventCode": "0x14", "EventName": "UNC_Q_CLOCKTICKS", "PerPkg": "1", "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/8th the 'GT/s' speed of the QPI link. For example, a 8GT/s link will have qfclk or 1GHz. JKT does not support dynamic link speeds, so this frequency is fixed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Count of CTO Events", @@ -13,7 +309,7 @@ "EventName": "UNC_Q_CTO_COUNT", "PerPkg": "1", "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", @@ -22,7 +318,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT", @@ -31,7 +327,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Not Set", @@ -40,7 +336,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Success", @@ -49,7 +345,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L1", @@ -57,7 +353,7 @@ "EventName": "UNC_Q_L1_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -65,7 +361,7 @@ "EventName": "UNC_Q_RxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -73,7 +369,7 @@ "EventName": "UNC_Q_RxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Bypassed", @@ -81,7 +377,7 @@ "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; LinkInit", @@ -90,7 +386,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; Normal Operations", @@ -99,7 +395,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; DRS", @@ -108,7 +404,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; HOM", @@ -117,7 +413,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCB", @@ -126,7 +422,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCS", @@ -135,7 +431,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NDR", @@ -144,7 +440,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; SNP", @@ -153,7 +449,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credit Consumed", @@ -161,7 +457,7 @@ "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty", @@ -169,7 +465,7 @@ "EventName": "UNC_Q_RxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Data Tx Flits", @@ -178,7 +474,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", @@ -187,7 +483,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Non-Data protocol Tx Flits", @@ -196,7 +492,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", @@ -205,7 +501,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Data Flits", @@ -214,7 +510,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Header Flits", @@ -223,7 +519,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Flits", @@ -232,7 +528,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", @@ -241,7 +537,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Request Flits", @@ -250,7 +546,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; SNP Flits", @@ -259,7 +555,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", @@ -268,7 +564,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", @@ -277,7 +573,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", @@ -286,7 +582,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", @@ -295,7 +591,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", @@ -304,7 +600,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", @@ -313,7 +609,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations", @@ -321,7 +617,7 @@ "EventName": "UNC_Q_RxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS", @@ -329,7 +625,7 @@ "EventName": "UNC_Q_RxL_INSERTS_DRS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM", @@ -337,7 +633,7 @@ "EventName": "UNC_Q_RxL_INSERTS_HOM", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB", @@ -345,7 +641,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCB", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS", @@ -353,7 +649,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR", @@ -361,7 +657,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NDR", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP", @@ -369,7 +665,7 @@ "EventName": "UNC_Q_RxL_INSERTS_SNP", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - All Packets", @@ -377,7 +673,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS", @@ -385,7 +681,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_DRS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM", @@ -393,7 +689,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_HOM", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB", @@ -401,7 +697,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCB", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS", @@ -409,7 +705,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR", @@ -417,7 +713,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NDR", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP", @@ -425,7 +721,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_SNP", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - HOM", @@ -434,7 +730,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - DRS", @@ -443,7 +739,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - SNP", @@ -452,7 +748,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - NDR", @@ -461,7 +757,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - NCS", @@ -470,7 +766,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; BGF Stall - NCB", @@ -479,7 +775,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; Egress Credits", @@ -488,7 +784,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x40", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI; GV", @@ -497,7 +793,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI.", "UMask": "0x80", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -505,7 +801,7 @@ "EventName": "UNC_Q_TxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -513,7 +809,7 @@ "EventName": "UNC_Q_TxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Bypassed", @@ -521,7 +817,7 @@ "EventName": "UNC_Q_TxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", @@ -530,7 +826,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", @@ -539,7 +835,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Cycles not Empty", @@ -547,7 +843,7 @@ "EventName": "UNC_Q_TxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", @@ -555,7 +851,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Idle and Null Flits", @@ -563,7 +859,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", @@ -571,7 +867,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", @@ -579,7 +875,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", @@ -587,7 +883,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", @@ -595,7 +891,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Flits", @@ -603,7 +899,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", @@ -611,7 +907,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", @@ -619,7 +915,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; SNP Flits", @@ -627,7 +923,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", @@ -636,7 +932,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", @@ -645,7 +941,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", @@ -654,7 +950,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", @@ -663,7 +959,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", @@ -672,7 +968,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", @@ -681,7 +977,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three 'groups' that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each 'flit' is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four 'fits', each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI 'speed' (for example, 8.0 GT/s), the 'transfers' here refer to 'fits'. Therefore, in L0, the system will transfer 1 'flit' at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as 'data' bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual 'data' and an additional 16 bits of other information. To calculate 'data' bandwidth, one should therefore do: data flits * 8B / time.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Allocations", @@ -689,7 +985,7 @@ "EventName": "UNC_Q_TxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Occupancy", @@ -697,7 +993,7 @@ "EventName": "UNC_Q_TxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Returned", @@ -705,7 +1001,7 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURNS", "PerPkg": "1", "PublicDescription": "Number of VNA credits returned.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Pending Return - Occupancy", @@ -713,6 +1009,779 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "QPI LL" + "Unit": "QPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Acquired", + "EventCode": "0x20", + "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Acquired", + "EventCode": "0x20", + "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Acquired", + "EventCode": "0x20", + "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Rejected", + "EventCode": "0x21", + "EventName": "UNC_R3_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Rejected", + "EventCode": "0x21", + "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit Rejected", + "EventCode": "0x21", + "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit In Use", + "EventCode": "0x22", + "EventName": "UNC_R3_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit In Use", + "EventCode": "0x22", + "EventName": "UNC_R3_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "to IIO BL Credit In Use", + "EventCode": "0x22", + "EventName": "UNC_R3_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 IV Ring in Use; Any", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.", + "UMask": "0xf", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Bypassed", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_BYPASSED.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; DRS", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with no VNA credits available", + "EventCode": "0x31", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with 1 or more VNA credits in use", + "EventCode": "0x32", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", + "Unit": "R3QPI" + }, + { + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "MsgCh Requests by Size; 4B Requests", + "EventCode": "0x47", + "EventName": "UNC_U_MSG_CHNL_SIZE_COUNT.4B", + "PerPkg": "1", + "PublicDescription": "Number of transactions on the message channel filtered by request size. This includes both reads and writes.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "MsgCh Requests by Size; 8B Requests", + "EventCode": "0x47", + "EventName": "UNC_U_MSG_CHNL_SIZE_COUNT.8B", + "PerPkg": "1", + "PublicDescription": "Number of transactions on the message channel filtered by request size. This includes both reads and writes.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; ACK to Deassert", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ACK_TO_DEASSERT", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS.COUNT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-io.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-io.json new file mode 100644 index 000000000000..b1ce5f77675e --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-io.json @@ -0,0 +1,324 @@ +[ + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R2_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", + "EventCode": "0x33", + "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; DRS", + "EventCode": "0x34", + "EventName": "UNC_R2_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; NCB", + "EventCode": "0x34", + "EventName": "UNC_R2_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; NCS", + "EventCode": "0x34", + "EventName": "UNC_R2_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; DRS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCB", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2PCIe IIO Credits in Use; NCS", + "EventCode": "0x32", + "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", + "EventCode": "0x7", + "EventName": "UNC_R2_RING_AD_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", + "EventCode": "0x8", + "EventName": "UNC_R2_RING_AK_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", + "EventCode": "0x9", + "EventName": "UNC_R2_RING_BL_USED.CW_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xa", + "EventName": "UNC_R2_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.", + "UMask": "0xf", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "AK Ingress Bounced", + "EventCode": "0x12", + "EventName": "UNC_R2_RxR_AK_BOUNCES", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; DRS", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCB", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x10", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NCS", + "EventCode": "0x10", + "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x20", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AD", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; AK", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Full; BL", + "EventCode": "0x25", + "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AD", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; AK", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress Cycles Not Empty; BL", + "EventCode": "0x23", + "EventName": "UNC_R2_TxR_CYCLES_NE.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress NACK; AD", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACKS.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", + "UMask": "0x1", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress NACK; AK", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACKS.AK", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", + "UMask": "0x2", + "Unit": "R2PCIe" + }, + { + "BriefDescription": "Egress NACK; BL", + "EventCode": "0x26", + "EventName": "UNC_R2_TxR_NACKS.BL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", + "UMask": "0x4", + "Unit": "R2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json deleted file mode 100644 index ca727c0e1865..000000000000 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-other.json +++ /dev/null @@ -1,1393 +0,0 @@ -[ - { - "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", - "EventCode": "0x17", - "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", - "EventCode": "0x17", - "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ack Pending Occupancy; Any Source", - "EventCode": "0x14", - "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ack Pending Occupancy; Select Source", - "EventCode": "0x14", - "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", - "EventCode": "0x13", - "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", - "EventCode": "0x13", - "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Read Occupancy; Any Source", - "EventCode": "0x10", - "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Read Occupancy; Select Source", - "EventCode": "0x10", - "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Select Source", - "EventCode": "0x12", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Occupancy; Any Source", - "EventCode": "0x11", - "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Outstanding Write Occupancy; Select Source", - "EventCode": "0x11", - "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Clocks in the IRP", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Number of clocks in the IRP.", - "Unit": "IRP" - }, - { - "EventCode": "0xB", - "EventName": "UNC_I_RxR_AK_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Ingress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_RxR_AK_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "EventCode": "0xC", - "EventName": "UNC_I_RxR_AK_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", - "Unit": "IRP" - }, - { - "EventCode": "0x4", - "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - DRS", - "EventCode": "0x1", - "EventName": "UNC_I_RxR_BL_DRS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x7", - "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x5", - "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCB", - "EventCode": "0x2", - "EventName": "UNC_I_RxR_BL_NCB_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x8", - "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x6", - "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "BL Ingress Occupancy - NCS", - "EventCode": "0x3", - "EventName": "UNC_I_RxR_BL_NCS_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "EventCode": "0x9", - "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", - "Unit": "IRP" - }, - { - "BriefDescription": "Tickle Count; Ownership Lost", - "EventCode": "0x16", - "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", - "PerPkg": "1", - "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Tickle Count; Data Returned", - "EventCode": "0x16", - "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", - "PerPkg": "1", - "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", - "PerPkg": "1", - "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x15", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of 'Inbound' transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x18", - "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x19", - "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xF", - "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xD", - "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "Write Ordering Stalls", - "EventCode": "0x1A", - "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", - "Unit": "IRP" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R2_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the R2PCIe uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the R2PCIe is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; DRS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCB", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credit Acquired; NCS", - "EventCode": "0x33", - "EventName": "UNC_R2_IIO_CREDITS_ACQUIRED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of credits that are acquired in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; DRS", - "EventCode": "0x34", - "EventName": "UNC_R2_IIO_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; NCB", - "EventCode": "0x34", - "EventName": "UNC_R2_IIO_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Failed to Acquire a Credit; NCS", - "EventCode": "0x34", - "EventName": "UNC_R2_IIO_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; DRS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCB", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2PCIe IIO Credits in Use; NCS", - "EventCode": "0x32", - "EventName": "UNC_R2_IIO_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when one or more credits in the R2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly).", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R2_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R2_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R2_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "R2 IV Ring in Use; Any", - "EventCode": "0xa", - "EventName": "UNC_R2_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.", - "UMask": "0xf", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "AK Ingress Bounced", - "EventCode": "0x12", - "EventName": "UNC_R2_RxR_AK_BOUNCES", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when a request destined for the AK ingress bounced.", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; DRS", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x8", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCB", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x10", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCS", - "EventCode": "0x10", - "EventName": "UNC_R2_RxR_CYCLES_NE.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Ingress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x20", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AD", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; AK", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Full; BL", - "EventCode": "0x25", - "EventName": "UNC_R2_TxR_CYCLES_FULL.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress buffer is full.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AD", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; AK", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress Cycles Not Empty; BL", - "EventCode": "0x23", - "EventName": "UNC_R2_TxR_CYCLES_NE.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the R2PCIe Egress is not empty. This tracks one of the three rings that are used by the R2PCIe agent. This can be used in conjunction with the R2PCIe Egress Occupancy Accumulator event in order to calculate average queue occupancy. Only a single Egress queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress NACK; AD", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACKS.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", - "UMask": "0x1", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress NACK; AK", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACKS.AK", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", - "UMask": "0x2", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Egress NACK; BL", - "EventCode": "0x26", - "EventName": "UNC_R2_TxR_NACKS.BL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that the Egress received a NACK from the ring and could not issue a transaction.", - "UMask": "0x4", - "Unit": "R2PCIe" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_R3_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Acquired", - "EventCode": "0x20", - "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Acquired", - "EventCode": "0x20", - "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Acquired", - "EventCode": "0x20", - "EventName": "UNC_R3_IIO_CREDITS_ACQUIRED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the NCS/NCB/DRS credit is acquired in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Rejected", - "EventCode": "0x21", - "EventName": "UNC_R3_IIO_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Rejected", - "EventCode": "0x21", - "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit Rejected", - "EventCode": "0x21", - "EventName": "UNC_R3_IIO_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that a request attempted to acquire an NCS/NCB/DRS credit in the QPI for sending messages on BL to the IIO but was rejected because no credit was available. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit In Use", - "EventCode": "0x22", - "EventName": "UNC_R3_IIO_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit In Use", - "EventCode": "0x22", - "EventName": "UNC_R3_IIO_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "to IIO BL Credit In Use", - "EventCode": "0x22", - "EventName": "UNC_R3_IIO_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the NCS/NCB/DRS credit is in use in the QPI for sending messages on BL to the IIO. There is one credit for each of these three message classes (three credits total). NCS is used for reads to PCIe space, NCB is used for transferring data without coherency, and DRS is used for transferring data with coherency (cacheable PCI transactions). This event can only track one message class at a time.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Even", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd", - "EventCode": "0x7", - "EventName": "UNC_R3_RING_AD_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Even", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd", - "EventCode": "0x8", - "EventName": "UNC_R3_RING_AK_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CCW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Even", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd", - "EventCode": "0x9", - "EventName": "UNC_R3_RING_BL_USED.CW_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "R3 IV Ring in Use; Any", - "EventCode": "0xa", - "EventName": "UNC_R3_RING_IV_USED.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.", - "UMask": "0xf", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Bypassed", - "EventCode": "0x12", - "EventName": "UNC_R3_RxR_BYPASSED.AD", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; DRS", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; HOM", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCB", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NCS", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; NDR", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Cycles Not Empty; SNP", - "EventCode": "0x10", - "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; DRS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.DRS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; HOM", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.HOM", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCB", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NCS", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; NDR", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.NDR", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Allocations; SNP", - "EventCode": "0x11", - "EventName": "UNC_R3_RxR_INSERTS.SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; DRS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; HOM", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NCB", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NCS", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; NDR", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Ingress Occupancy Accumulator; SNP", - "EventCode": "0x13", - "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", - "EventCode": "0x37", - "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; DRS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; HOM Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCS Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; NDR Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP Message Class", - "EventCode": "0x36", - "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA credit Acquisitions", - "EventCode": "0x33", - "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", - "PerPkg": "1", - "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; DRS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x8", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; HOM Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x1", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCB Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x10", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NCS Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x20", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; NDR Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x4", - "Unit": "R3QPI" - }, - { - "BriefDescription": "VNA Credit Reject; SNP Message Class", - "EventCode": "0x34", - "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", - "PerPkg": "1", - "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.", - "UMask": "0x2", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Cycles with no VNA credits available", - "EventCode": "0x31", - "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", - "PerPkg": "1", - "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", - "Unit": "R3QPI" - }, - { - "BriefDescription": "Cycles with 1 or more VNA credits in use", - "EventCode": "0x32", - "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", - "PerPkg": "1", - "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", - "Unit": "R3QPI" - }, - { - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "VLW Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Filter Match", - "EventCode": "0x41", - "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", - "PerPkg": "1", - "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "MsgCh Requests by Size; 4B Requests", - "EventCode": "0x47", - "EventName": "UNC_U_MSG_CHNL_SIZE_COUNT.4B", - "PerPkg": "1", - "PublicDescription": "Number of transactions on the message channel filtered by request size. This includes both reads and writes.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "MsgCh Requests by Size; 8B Requests", - "EventCode": "0x47", - "EventName": "UNC_U_MSG_CHNL_SIZE_COUNT.8B", - "PerPkg": "1", - "PublicDescription": "Number of transactions on the message channel filtered by request size. This includes both reads and writes.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; ACK to Deassert", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ACK_TO_DEASSERT", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles. Filter from source CoreID.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS.COUNT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.CMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Livelock", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; LTError", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.LTERROR", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T0", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Monitor T1", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Other", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.OTHER", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Trap", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.TRAP", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", - "EventCode": "0x43", - "EventName": "UNC_U_U2C_EVENTS.UMC", - "PerPkg": "1", - "PublicDescription": "Events coming from Uncore can be sent to one or all cores", - "UMask": "0x20", - "Unit": "UBOX" - } -] -- GitLab From 6c3566c594505d1e3d1d49f2c0a8dac61441505c Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:44 -0700 Subject: [PATCH 3004/5631] perf vendor events intel: Fix uncore topics for knightslanding Remove 'uncore-other' topic classification, move to cache, io and memory. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-17-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../{uncore-other.json => uncore-cache.json} | 260 ------------------ .../arch/x86/knightslanding/uncore-io.json | 194 +++++++++++++ .../x86/knightslanding/uncore-memory.json | 68 +++++ 3 files changed, 262 insertions(+), 260 deletions(-) rename tools/perf/pmu-events/arch/x86/knightslanding/{uncore-other.json => uncore-cache.json} (91%) create mode 100644 tools/perf/pmu-events/arch/x86/knightslanding/uncore-io.json diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json similarity index 91% rename from tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json rename to tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json index fc85e0c95318..1b8dcfa5461c 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json @@ -55,74 +55,6 @@ "UMask": "0x24", "Unit": "CHA" }, - { - "BriefDescription": "Counts the number of read requests and streaming stores that hit in MCDRAM cache and the data in MCDRAM is clean with respect to DDR. This event is only valid in cache and hybrid memory mode.", - "EventCode": "0x02", - "EventName": "UNC_E_EDC_ACCESS.HIT_CLEAN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "Counts the number of read requests and streaming stores that hit in MCDRAM cache and the data in MCDRAM is dirty with respect to DDR. This event is only valid in cache and hybrid memory mode.", - "EventCode": "0x02", - "EventName": "UNC_E_EDC_ACCESS.HIT_DIRTY", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "Counts the number of read requests and streaming stores that miss in MCDRAM cache and the data evicted from the MCDRAM is clean with respect to DDR. This event is only valid in cache and hybrid memory mode.", - "EventCode": "0x02", - "EventName": "UNC_E_EDC_ACCESS.MISS_CLEAN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "Counts the number of read requests and streaming stores that miss in MCDRAM cache and the data evicted from the MCDRAM is dirty with respect to DDR. This event is only valid in cache and hybrid memory mode.", - "EventCode": "0x02", - "EventName": "UNC_E_EDC_ACCESS.MISS_DIRTY", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "Number of EDC Hits or Misses. Miss I", - "EventCode": "0x02", - "EventName": "UNC_E_EDC_ACCESS.MISS_INVALID", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "ECLK count", - "EventName": "UNC_E_E_CLOCKTICKS", - "PerPkg": "1", - "Unit": "EDC_ECLK" - }, - { - "BriefDescription": "Counts the number of read requests received by the MCDRAM controller. This event is valid in all three memory modes: flat, cache and hybrid. In cache and hybrid memory mode, this event counts all read requests as well as streaming stores that hit or miss in the MCDRAM cache.", - "EventCode": "0x01", - "EventName": "UNC_E_RPQ_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "EDC_ECLK" - }, - { - "BriefDescription": "UCLK count", - "EventName": "UNC_E_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "EDC_UCLK" - }, - { - "BriefDescription": "Counts the number of write requests received by the MCDRAM controller. This event is valid in all three memory modes: flat, cache and hybrid. In cache and hybrid memory mode, this event counts all streaming stores, writebacks and, read requests that miss in MCDRAM cache.", - "EventCode": "0x02", - "EventName": "UNC_E_WPQ_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "EDC_ECLK" - }, { "BriefDescription": "CMS Agent0 AD Credits Acquired For Transgress 0", "EventCode": "0x80", @@ -3429,197 +3361,5 @@ "PerPkg": "1", "UMask": "0x1", "Unit": "CHA" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AD_0", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AD_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AD_1", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AD_1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AK_0", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AK_0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AK_1", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AK_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. BL_0", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.BL_0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. BL_1", - "EventCode": "0x25", - "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.BL_1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AD_0", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AD_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AD_1", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AD_1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AK_0", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AK_0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AK_1", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AK_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. BL_0", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.BL_0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. BL_1", - "EventCode": "0x23", - "EventName": "UNC_M2P_EGRESS_CYCLES_NE.BL_1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AD_0", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AD_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AD_1", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AD_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_0", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AK_0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_1", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AK_1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_CRD_0", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AK_CRD_0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_CRD_1", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.AK_CRD_1", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. BL_0", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.BL_0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. BL_1", - "EventCode": "0x24", - "EventName": "UNC_M2P_EGRESS_INSERTS.BL_1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.ALL", - "EventCode": "0x10", - "EventName": "UNC_M2P_INGRESS_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_IDI", - "EventCode": "0x10", - "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_IDI", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_NCB", - "EventCode": "0x10", - "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_NCB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_NCS", - "EventCode": "0x10", - "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_NCS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" } ] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-io.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-io.json new file mode 100644 index 000000000000..898f7e425cd4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-io.json @@ -0,0 +1,194 @@ +[ + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AD_0", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AD_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AD_1", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AD_1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AK_0", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AK_0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. AK_1", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.AK_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. BL_0", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.BL_0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full. Counts the number of cycles when the M2PCIe Egress is full. BL_1", + "EventCode": "0x25", + "EventName": "UNC_M2P_EGRESS_CYCLES_FULL.BL_1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AD_0", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AD_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AD_1", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AD_1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AK_0", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AK_0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. AK_1", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.AK_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. BL_0", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.BL_0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty. Counts the number of cycles when the M2PCIe Egress is not empty. BL_1", + "EventCode": "0x23", + "EventName": "UNC_M2P_EGRESS_CYCLES_NE.BL_1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AD_0", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AD_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AD_1", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AD_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_0", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AK_0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_1", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AK_1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_CRD_0", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AK_CRD_0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. AK_CRD_1", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.AK_CRD_1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. BL_0", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.BL_0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress. Counts the number of number of messages inserted into the the M2PCIe Egress queue. BL_1", + "EventCode": "0x24", + "EventName": "UNC_M2P_EGRESS_INSERTS.BL_1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.ALL", + "EventCode": "0x10", + "EventName": "UNC_M2P_INGRESS_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_IDI", + "EventCode": "0x10", + "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_IDI", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_NCB", + "EventCode": "0x10", + "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress Queue Cycles Not Empty. Counts the number of cycles when the M2PCIe Ingress is not empty.CBO_NCS", + "EventCode": "0x10", + "EventName": "UNC_M2P_INGRESS_CYCLES_NE.CBO_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json index 47da947b1a6e..fb752974179b 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json @@ -1,4 +1,72 @@ [ + { + "BriefDescription": "Counts the number of read requests and streaming stores that hit in MCDRAM cache and the data in MCDRAM is clean with respect to DDR. This event is only valid in cache and hybrid memory mode.", + "EventCode": "0x02", + "EventName": "UNC_E_EDC_ACCESS.HIT_CLEAN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "Counts the number of read requests and streaming stores that hit in MCDRAM cache and the data in MCDRAM is dirty with respect to DDR. This event is only valid in cache and hybrid memory mode.", + "EventCode": "0x02", + "EventName": "UNC_E_EDC_ACCESS.HIT_DIRTY", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "Counts the number of read requests and streaming stores that miss in MCDRAM cache and the data evicted from the MCDRAM is clean with respect to DDR. This event is only valid in cache and hybrid memory mode.", + "EventCode": "0x02", + "EventName": "UNC_E_EDC_ACCESS.MISS_CLEAN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "Counts the number of read requests and streaming stores that miss in MCDRAM cache and the data evicted from the MCDRAM is dirty with respect to DDR. This event is only valid in cache and hybrid memory mode.", + "EventCode": "0x02", + "EventName": "UNC_E_EDC_ACCESS.MISS_DIRTY", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "Number of EDC Hits or Misses. Miss I", + "EventCode": "0x02", + "EventName": "UNC_E_EDC_ACCESS.MISS_INVALID", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "ECLK count", + "EventName": "UNC_E_E_CLOCKTICKS", + "PerPkg": "1", + "Unit": "EDC_ECLK" + }, + { + "BriefDescription": "Counts the number of read requests received by the MCDRAM controller. This event is valid in all three memory modes: flat, cache and hybrid. In cache and hybrid memory mode, this event counts all read requests as well as streaming stores that hit or miss in the MCDRAM cache.", + "EventCode": "0x01", + "EventName": "UNC_E_RPQ_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "EDC_ECLK" + }, + { + "BriefDescription": "UCLK count", + "EventName": "UNC_E_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "EDC_UCLK" + }, + { + "BriefDescription": "Counts the number of write requests received by the MCDRAM controller. This event is valid in all three memory modes: flat, cache and hybrid. In cache and hybrid memory mode, this event counts all streaming stores, writebacks and, read requests that miss in MCDRAM cache.", + "EventCode": "0x02", + "EventName": "UNC_E_WPQ_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "EDC_ECLK" + }, { "BriefDescription": "CAS All", "EventCode": "0x03", -- GitLab From f58468a815a3933710e871812ffe23b15421edc4 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:45 -0700 Subject: [PATCH 3005/5631] perf vendor events intel: Fix uncore topics for sandybridge Remove 'uncore-other' topic classification, move to cache and interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-18-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/sandybridge/uncore-cache.json | 50 +++++++++---------- ...re-other.json => uncore-interconnect.json} | 0 2 files changed, 25 insertions(+), 25 deletions(-) rename tools/perf/pmu-events/arch/x86/sandybridge/{uncore-other.json => uncore-interconnect.json} (100%) diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore-cache.json index c538557ba4c0..be9a3ed1a940 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore-cache.json @@ -5,7 +5,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES", "PerPkg": "1", "UMask": "0x86", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.", @@ -13,7 +13,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.", @@ -21,7 +21,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.", @@ -29,7 +29,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI", "PerPkg": "1", "UMask": "0x8f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.", @@ -37,7 +37,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES", "PerPkg": "1", "UMask": "0x46", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.", @@ -45,7 +45,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.", @@ -53,7 +53,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.", @@ -61,7 +61,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI", "PerPkg": "1", "UMask": "0x4f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.", @@ -69,7 +69,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES", "PerPkg": "1", "UMask": "0x16", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.", @@ -77,7 +77,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I", "PerPkg": "1", "UMask": "0x18", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.", @@ -85,7 +85,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M", "PerPkg": "1", "UMask": "0x11", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", @@ -93,7 +93,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI", "PerPkg": "1", "UMask": "0x1f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.", @@ -101,7 +101,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES", "PerPkg": "1", "UMask": "0x26", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.", @@ -109,7 +109,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.", @@ -117,7 +117,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.", @@ -125,7 +125,7 @@ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI", "PerPkg": "1", "UMask": "0x2f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.", @@ -133,7 +133,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION", "PerPkg": "1", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a modified line in some processor core.", @@ -141,7 +141,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL", "PerPkg": "1", "UMask": "0x28", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", @@ -149,7 +149,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.", @@ -157,7 +157,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION", "PerPkg": "1", "UMask": "0x84", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop hits a non-modified line in some processor core.", @@ -165,7 +165,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL", "PerPkg": "1", "UMask": "0x24", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", @@ -173,7 +173,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", @@ -181,7 +181,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "An external snoop misses in some processor core.", @@ -189,7 +189,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL", "PerPkg": "1", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", @@ -197,6 +197,6 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore-interconnect.json similarity index 100% rename from tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json rename to tools/perf/pmu-events/arch/x86/sandybridge/uncore-interconnect.json -- GitLab From 9a8b303688f80aa9480d6a196817c90b6a592356 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:46 -0700 Subject: [PATCH 3006/5631] perf vendor events intel: Fix uncore topics for skylake Move events from 'uncore-other' topic classification to cache and interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-19-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/skylake/uncore-cache.json | 28 ++++---- .../arch/x86/skylake/uncore-interconnect.json | 67 +++++++++++++++++++ .../arch/x86/skylake/uncore-other.json | 65 ------------------ 3 files changed, 81 insertions(+), 79 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/skylake/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore-cache.json b/tools/perf/pmu-events/arch/x86/skylake/uncore-cache.json index ec9463c94ffe..b4e061477c1a 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore-cache.json @@ -6,7 +6,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.", "UMask": "0x86", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in I-state", @@ -15,7 +15,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.", "UMask": "0x88", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in M-state", @@ -24,7 +24,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state", @@ -33,7 +33,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.", "UMask": "0x8f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state", @@ -42,7 +42,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.", "UMask": "0x16", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in I-state", @@ -51,7 +51,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.", "UMask": "0x18", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state", @@ -60,7 +60,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.", "UMask": "0x1f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state", @@ -69,7 +69,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.", "UMask": "0x26", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in M-state", @@ -78,7 +78,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.", "UMask": "0x21", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state", @@ -87,7 +87,7 @@ "PerPkg": "1", "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.", "UMask": "0x2f", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.", @@ -95,7 +95,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE", "PerPkg": "1", "UMask": "0x48", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.", @@ -103,7 +103,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE", "PerPkg": "1", "UMask": "0x44", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.", @@ -111,7 +111,7 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION", "PerPkg": "1", "UMask": "0x81", - "Unit": "CBO" + "Unit": "CBOX" }, { "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.", @@ -119,6 +119,6 @@ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE", "PerPkg": "1", "UMask": "0x41", - "Unit": "CBO" + "Unit": "CBOX" } ] diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/skylake/uncore-interconnect.json new file mode 100644 index 000000000000..fe7e19717371 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore-interconnect.json @@ -0,0 +1,67 @@ +[ + { + "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all Core entries outstanding for the memory controller. The outstanding interval starts after LLC miss till return of first data chunk. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", + "CounterMask": "1", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Core Data Read entries outstanding for the memory controller. The outstanding interval starts after LLC miss till return of first data chunk.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.DATA_READ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Core coherent Data Read requests sent to memory controller whose data is returned directly to requesting agent.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.DATA_READ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Core coherent Data Read requests sent to memory controller whose data is returned directly to requesting agent.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json index ef804df3f41e..58be90d7cc93 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/skylake/uncore-other.json @@ -1,69 +1,4 @@ [ - { - "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all Core entries outstanding for the memory controller. The outstanding interval starts after LLC miss till return of first data chunk. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.", - "CounterMask": "1", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Core Data Read entries outstanding for the memory controller. The outstanding interval starts after LLC miss till return of first data chunk.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.DATA_READ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Core coherent Data Read requests sent to memory controller whose data is returned directly to requesting agent.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.DATA_READ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Core coherent Data Read requests sent to memory controller whose data is returned directly to requesting agent.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.WRITES", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "ARB" - }, { "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles", "EventCode": "0xff", -- GitLab From 748d5cf71948d5ad2cac896777dd5ccc6ea494e9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:47 -0700 Subject: [PATCH 3007/5631] perf vendor events intel: Fix uncore topics for skylakex Remove 'uncore-other' topic classification, move to cache, interconnect, io and memory. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-20-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/skylakex/uncore-cache.json | 10649 +++++++ .../x86/skylakex/uncore-interconnect.json | 11248 +++++++ .../arch/x86/skylakex/uncore-io.json | 4250 +++ .../arch/x86/skylakex/uncore-memory.json | 2 +- .../arch/x86/skylakex/uncore-other.json | 26143 ---------------- 5 files changed, 26148 insertions(+), 26144 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json create mode 100644 tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json new file mode 100644 index 000000000000..543dfc1e5ad7 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-cache.json @@ -0,0 +1,10649 @@ +[ + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass; Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Clockticks of the uncore caching & home agent (CHA)", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the clock controlling the uncore caching and home agent (CHA).", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C1 State", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C1_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C1 Transition", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C1_TRANSITION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C6 State", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C6_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; C6 Transition", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.C6_TRANSITION", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Core PMA Events; GV", + "EventCode": "0x17", + "EventName": "UNC_CHA_CORE_PMA.GV", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Any Snoop to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Core Request to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Eviction to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued; External Snoop to Remote Node", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "Counter 0 Occupancy", + "EventCode": "0x1F", + "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_CHA_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; Shared hit and op is RdInvOwn, RdInv, Inv*", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoE", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5F", + "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5E", + "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; No SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache; SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a local request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "PublicDescription": "Received RspFwdI* for a local request, but converted HitME$ to SF entry", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache on RdInvOwn even if not RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a remote request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "PublicDescription": "Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache to SHARed", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued; ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Full Line MIG", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Full Line", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Partial Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; Partial MIG", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Partial", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.INVITOM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations dropped due to IODC Full", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.IODCFULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IDOC allocation dropped due to OSB gate", + "EventCode": "0x62", + "EventName": "UNC_CHA_IODC_ALLOC.OSBGATED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to any reason", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to conflicting transaction", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.SNPOUT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoE", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoI", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbPushMtoI", + "EventCode": "0x63", + "EventName": "UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", + "PerPkg": "1", + "PublicDescription": "Moved to Cbo section", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Read transactions", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Local", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Remote", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", + "UMask": "0x91", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; External Snoop Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", + "UMask": "0x9", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Write Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x5", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.F_STATE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in F State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc; Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB", + "PerPkg": "1", + "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC0_SMI2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC1_SMI3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC2_SMI4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC3_SMI5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC0_SMI0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC1_SMI1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a remote socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Write requests", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Write Requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Read and Write Requests; Writes Remote", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_CHA_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IPQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; RRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations; WBQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; AD REQ on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; AD RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Non UPI AK Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL NCB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL NCS on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; BL WB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Non UPI IV Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Allow Snoop", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; ANY0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; HA", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; LLC Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; PhyAddr Match", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; SF Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress Probe Queue Rejects; Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; AD REQ on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; AD RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; Non UPI AK Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL NCB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL NCS on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; BL WB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; Non UPI IV Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects; HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; ANY0", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries; HA", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IPQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; RRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy; WBQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; AD REQ on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; AD RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Non UPI AK Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL NCB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL NCS on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; BL WB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Non UPI IV Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Allow Snoop", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; ANY0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; HA", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; LLC Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; PhyAddr Match", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; SF Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries; Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; AD REQ on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; AD RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Non UPI AK Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL NCB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL NCS on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; BL WB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Non UPI IV Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Allow Snoop", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; ANY0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; HA", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; LLC Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; PhyAddr Match", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; SF Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries; Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; AD REQ on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; AD RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Non UPI AK Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL NCB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL NCS on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; BL WB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Non UPI IV Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Allow Snoop", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; ANY0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; HA", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; LLC Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; PhyAddr Match", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; SF Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects; Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; AD REQ on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; AD RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Non UPI AK Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL NCB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL NCS on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; BL WB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Non UPI IV Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Allow Snoop", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; ANY0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; HA", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Merging these two together to make room for ANY_REJECT_*0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; LLC Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; PhyAddr Match", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; SF Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects; Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_CHA_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_CHA_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast snoop for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Directed snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RspCnflct* Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received; RspFwd", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspS", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RspS : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Rsp*WB Snoop Responses Received", + "EventCode": "0x5C", + "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to its home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspCnflct", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspI", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspIFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspS", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; RspSFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*FWD*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local; Rsp*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", + "PerPkg": "1", + "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x15", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_IO_IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests", + "UMask": "0x35", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from Local", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x25", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hit (Not a Miss)", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from iA Cores", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally generated IO traffic", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "Filter": "config1=0x49033", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", + "Filter": "config1=0x43C33", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; IPQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; IRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Miss", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; PRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ_HIT", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ_MISS", + "PerPkg": "1", + "UMask": "0x60", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ_HIT", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ_MISS", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All remotely generated requests", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x17", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x27", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hit (Not a Miss)", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally initiated requests from iA Cores", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "Filter": "config1=0x40233", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "Filter": "config1=0x40433", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", + "Filter": "config1=0x4b233", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", + "Filter": "config1=0x4b433", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", + "Filter": "config1=0x4b033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally generated IO traffic", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM Misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "Filter": "config1=0x49033", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RDCUR misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", + "Filter": "config1=0x43C33", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "Filter": "config1=0x40033", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; IPQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; IRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Miss", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; PRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; AD REQ Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; AD RSP VN0 Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL NCB Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL NCS Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL RSP Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; BL DRS Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; VN0 Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credit Allocations; VNA Credits", + "EventCode": "0x38", + "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD REQ VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD RSP VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCB VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCS VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL RSP VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL DRS VN0 Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; AD VNA Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_AD", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UPI Ingress Credits In Use Cycles; BL VNA Credits", + "EventCode": "0x3B", + "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_BL", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI; Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI; Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC0_SMI2", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC1_SMI3", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC2_SMI4", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC3_SMI5", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC0_SMI0", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC1_SMI1", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd F/E", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd M", + "UMask": "0xf0", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd F/E", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd M", + "UMask": "0xe8", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Any RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response any to Hit F/S/E", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd F/E", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd M", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd F/E", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd M", + "UMask": "0x48", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Core RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response any to Hit F/S/E", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd F/E", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd M", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd F/E", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd M", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; Evict RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response any to Hit F/S/E", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspIFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd F/E", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspIFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd M", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspSFwdFE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd F/E", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspSFwdM", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd M", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoop Responses; External RspHitFSE", + "EventCode": "0x32", + "EventName": "UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", + "PerPkg": "1", + "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response any to Hit F/S/E", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CLOCKTICKS", + "Deprecated": "1", + "EventName": "UNC_C_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_FAST_ASSERTED.HORZ", + "Deprecated": "1", + "EventCode": "0xA5", + "EventName": "UNC_C_FAST_ASSERTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.ANY", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.ANY", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.LOCAL", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.REMOTE", + "PerPkg": "1", + "UMask": "0x91", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.REMOTE_SNOOP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITE", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_C_LLC_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.F_STATE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.LOCAL", + "PerPkg": "1", + "UMask": "0x2f", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.REMOTE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", + "Deprecated": "1", + "EventCode": "0x37", + "EventName": "UNC_C_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SRC_THRTL", + "Deprecated": "1", + "EventCode": "0xA4", + "EventName": "UNC_C_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.EVICT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.EVICT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.HIT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IPQ", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ_HIT", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.IRQ_MISS", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.PRQ", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_HIT", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ_HIT", + "PerPkg": "1", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_MISS", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.PRQ_MISS", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.RRQ_HIT", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.RRQ_MISS", + "PerPkg": "1", + "UMask": "0x60", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.WBQ_HIT", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_C_TOR_INSERTS.WBQ_MISS", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.EVICT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IPQ", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_HIT", + "PerPkg": "1", + "UMask": "0x18", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_MISS", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_HIT", + "PerPkg": "1", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_MISS", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "UMask": "0x37", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "UMask": "0x31", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "UMask": "0x34", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.PRQ", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_HIT", + "PerPkg": "1", + "UMask": "0x14", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "Deprecated": "1", + "EventCode": "0x36", + "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_MISS", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x80", + "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x82", + "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x88", + "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x8A", + "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x86", + "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", + "Deprecated": "1", + "EventCode": "0x8E", + "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", + "Deprecated": "1", + "EventCode": "0x8C", + "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "Deprecated": "1", + "EventCode": "0x57", + "EventName": "UNC_H_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CMS_CLOCKTICKS", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_H_CLOCK", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_STATE", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C1_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_TRANSITION", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C1_TRANSITION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_STATE", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C6_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_TRANSITION", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.C6_TRANSITION", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.GV", + "Deprecated": "1", + "EventCode": "0x17", + "EventName": "UNC_H_CORE_PMA.GV", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.ANY_REMOTE", + "PerPkg": "1", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.CORE_REMOTE", + "PerPkg": "1", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EVICT_REMOTE", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_GTONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_ONE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_REMOTE", + "Deprecated": "1", + "EventCode": "0x33", + "EventName": "UNC_H_CORE_SNP.EXT_REMOTE", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_COUNTER0_OCCUPANCY", + "Deprecated": "1", + "EventCode": "0x1F", + "EventName": "UNC_H_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.NO_SNP", + "Deprecated": "1", + "EventCode": "0x53", + "EventName": "UNC_H_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.SNP", + "Deprecated": "1", + "EventCode": "0x53", + "EventName": "UNC_H_DIR_LOOKUP.SNP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.HA", + "Deprecated": "1", + "EventCode": "0x54", + "EventName": "UNC_H_DIR_UPDATE.HA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.TOR", + "Deprecated": "1", + "EventCode": "0x54", + "EventName": "UNC_H_DIR_UPDATE.TOR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "Deprecated": "1", + "EventCode": "0xAE", + "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "Deprecated": "1", + "EventCode": "0xAE", + "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.EX_RDS", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.EX_RDS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOE", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "Deprecated": "1", + "EventCode": "0x5F", + "EventName": "UNC_H_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.READ", + "Deprecated": "1", + "EventCode": "0x5E", + "EventName": "UNC_H_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.WRITE", + "Deprecated": "1", + "EventCode": "0x5E", + "EventName": "UNC_H_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.READ_OR_INV", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "Deprecated": "1", + "EventCode": "0x60", + "EventName": "UNC_H_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RDINVOWN", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.SHARED", + "Deprecated": "1", + "EventCode": "0x61", + "EventName": "UNC_H_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xA7", + "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xA9", + "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "Deprecated": "1", + "EventCode": "0xAB", + "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "Deprecated": "1", + "EventCode": "0xAD", + "EventName": "UNC_H_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "Deprecated": "1", + "EventCode": "0xAD", + "EventName": "UNC_H_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.NORMAL", + "Deprecated": "1", + "EventCode": "0x59", + "EventName": "UNC_H_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.PRIORITY", + "Deprecated": "1", + "EventCode": "0x59", + "EventName": "UNC_H_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_MIG", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_MIG", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "Deprecated": "1", + "EventCode": "0x5B", + "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.INVITOM", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.INVITOM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.IODCFULL", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.IODCFULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.OSBGATED", + "Deprecated": "1", + "EventCode": "0x62", + "EventName": "UNC_H_IODC_ALLOC.OSBGATED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.ALL", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.SNPOUT", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.SNPOUT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOE", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBMTOE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOI", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBMTOI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", + "Deprecated": "1", + "EventCode": "0x63", + "EventName": "UNC_H_IODC_DEALLOC.WBPUSHMTOI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_MISS", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_VIC", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RFO_HIT_S", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.RFO_HIT_S", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RSPI_WAS_FSE", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.WC_ALIASING", + "Deprecated": "1", + "EventCode": "0x39", + "EventName": "UNC_H_MISC.WC_ALIASING", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_OSB", + "Deprecated": "1", + "EventCode": "0x55", + "EventName": "UNC_H_OSB", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC0_SMI0", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC1_SMI1", + "Deprecated": "1", + "EventCode": "0x58", + "EventName": "UNC_H_READ_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_LOCAL", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_REMOTE", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from local home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "read requests from remote home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from local home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "write requests from remote home agent", + "Deprecated": "1", + "EventCode": "0x50", + "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AD", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AK", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.BL", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.IV", + "Deprecated": "1", + "EventCode": "0xA1", + "EventName": "UNC_H_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AD", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AK", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.BL", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.IV", + "Deprecated": "1", + "EventCode": "0xA0", + "EventName": "UNC_H_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "Deprecated": "1", + "EventCode": "0xA3", + "EventName": "UNC_H_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AD", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AK", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.BL", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.IV", + "Deprecated": "1", + "EventCode": "0xA2", + "EventName": "UNC_H_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IPQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IPQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ_REJ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.PRQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ_REJ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.RRQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.RRQ", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.WBQ", + "Deprecated": "1", + "EventCode": "0x13", + "EventName": "UNC_H_RxC_INSERTS.WBQ", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x22", + "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.ANY_IPQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x23", + "EventName": "UNC_H_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x18", + "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.ANY_REJECT_IRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x19", + "EventName": "UNC_H_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x24", + "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2C", + "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x25", + "EventName": "UNC_H_RxC_ISMQ1_REJECT.ANY_ISMQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x25", + "EventName": "UNC_H_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2D", + "EventName": "UNC_H_RxC_ISMQ1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2D", + "EventName": "UNC_H_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IPQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IRQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.RRQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.WBQ", + "Deprecated": "1", + "EventCode": "0x11", + "EventName": "UNC_H_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2E", + "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "Deprecated": "1", + "EventCode": "0x2F", + "EventName": "UNC_H_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.ANY_PRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x21", + "EventName": "UNC_H_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x2A", + "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ANY", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "Deprecated": "1", + "EventCode": "0x2B", + "EventName": "UNC_H_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x26", + "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.ANY_RRQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x27", + "EventName": "UNC_H_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "Deprecated": "1", + "EventCode": "0x28", + "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.ANY_WBQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.HA", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "Deprecated": "1", + "EventCode": "0x29", + "EventName": "UNC_H_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB4", + "EventName": "UNC_H_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB2", + "EventName": "UNC_H_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IFV", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB3", + "EventName": "UNC_H_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB1", + "EventName": "UNC_H_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AK_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.IV_BNC", + "Deprecated": "1", + "EventCode": "0xB0", + "EventName": "UNC_H_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.E_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.E_STATE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.M_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.M_STATE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.S_STATE", + "Deprecated": "1", + "EventCode": "0x3D", + "EventName": "UNC_H_SF_EVICTION.S_STATE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.ALL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.BCST_LOC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.BCST_REM", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.DIRECT_LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.DIRECT_REM", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.LOCAL", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.REMOTE", + "Deprecated": "1", + "EventCode": "0x51", + "EventName": "UNC_H_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPCNFLCTS", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPI", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPI", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPIFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPS", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPSFWD", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_FWD_WB", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_WBWB", + "Deprecated": "1", + "EventCode": "0x5C", + "EventName": "UNC_H_SNOOP_RESP.RSP_WB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPFWD", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPI", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPIFWD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPSFWD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_FWD_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", + "Deprecated": "1", + "EventCode": "0x5D", + "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_WB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "Deprecated": "1", + "EventCode": "0xD0", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "Deprecated": "1", + "EventCode": "0xD2", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "Deprecated": "1", + "EventCode": "0xD4", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "Deprecated": "1", + "EventCode": "0xD6", + "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "Deprecated": "1", + "EventCode": "0x9D", + "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", + "Deprecated": "1", + "EventCode": "0x9F", + "EventName": "UNC_H_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", + "Deprecated": "1", + "EventCode": "0x96", + "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", + "Deprecated": "1", + "EventCode": "0x97", + "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", + "Deprecated": "1", + "EventCode": "0x95", + "EventName": "UNC_H_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AK_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.IV_BNC", + "Deprecated": "1", + "EventCode": "0x99", + "EventName": "UNC_H_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", + "Deprecated": "1", + "EventCode": "0x94", + "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AD_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AK_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.BL_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.IV_BNC", + "Deprecated": "1", + "EventCode": "0x9B", + "EventName": "UNC_H_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9C", + "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.IV", + "Deprecated": "1", + "EventCode": "0x9E", + "EventName": "UNC_H_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.IV", + "Deprecated": "1", + "EventCode": "0x92", + "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.IV", + "Deprecated": "1", + "EventCode": "0x93", + "EventName": "UNC_H_TxR_VERT_CYCLES_NE.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG0", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG1", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.IV", + "Deprecated": "1", + "EventCode": "0x91", + "EventName": "UNC_H_TxR_VERT_INSERTS.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG0", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG1", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.IV", + "Deprecated": "1", + "EventCode": "0x98", + "EventName": "UNC_H_TxR_VERT_NACK.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.IV", + "Deprecated": "1", + "EventCode": "0x90", + "EventName": "UNC_H_TxR_VERT_OCCUPANCY.IV_AG0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG0", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG1", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.IV", + "Deprecated": "1", + "EventCode": "0x9A", + "EventName": "UNC_H_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xA6", + "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xA8", + "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "Deprecated": "1", + "EventCode": "0xAA", + "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.DN", + "Deprecated": "1", + "EventCode": "0xAC", + "EventName": "UNC_H_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.UP", + "Deprecated": "1", + "EventCode": "0xAC", + "EventName": "UNC_H_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.LLC", + "Deprecated": "1", + "EventCode": "0x56", + "EventName": "UNC_H_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.MEM", + "Deprecated": "1", + "EventCode": "0x56", + "EventName": "UNC_H_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC0_SMI2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC1_SMI3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC2_SMI4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.EDC3_SMI5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.MC0_SMI0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", + "Deprecated": "1", + "EventCode": "0x5A", + "EventName": "UNC_H_WRITE_NO_CREDITS.MC1_SMI1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0xe4", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0xf0", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0xe2", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0xe8", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.ANY_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0xe1", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x50", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x48", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.CORE_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EVICT_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDFE", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDM", + "PerPkg": "1", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDFE", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDM", + "PerPkg": "1", + "UMask": "0x28", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", + "Deprecated": "1", + "EventCode": "0x32", + "EventName": "UNC_H_XSNP_RESP.EXT_RSP_HITFSE", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json new file mode 100644 index 000000000000..26a5a20bf37a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json @@ -0,0 +1,11248 @@ +[ + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Snoops", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests.", + "EventCode": "0xF", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "IRP Clocks", + "EventCode": "0x1", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CLFlush", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; CRd", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; DRd", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.DRD", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIDCAHin5t", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; PCIRdCur", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", + "PerPkg": "1", + "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.RFO", + "PerPkg": "1", + "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops; WbMtoI", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", + "PerPkg": "1", + "PublicDescription": "Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Occupancy of the IRP FAF queue.", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x1E", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x1E", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Requests", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 0", + "EventCode": "0x1C", + "EventName": "UNC_I_MISC0.UNKNOWN", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Lost Forward", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Invalid", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Received Valid", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", + "EventCode": "0x1D", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Requests", + "EventCode": "0x14", + "EventName": "UNC_I_P2P_INSERTS", + "PerPkg": "1", + "PublicDescription": "P2P requests from the ITC", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Occupancy", + "EventCode": "0x15", + "EventName": "UNC_I_P2P_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "P2P B & S Queue Occupancy", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P completions", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if local only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if local and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P Message", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P reads", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; Match if remote only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; match if remote and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions; P2P Writes", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses; SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Atomic", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Other", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.RD_PREF", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0xB", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x5", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x2", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x8", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x6", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x3", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x9", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x7", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x4", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0xA", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x1A", + "EventName": "UNC_I_TxR2_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1B", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xD", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xE", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xC", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_Egress.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Not Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass; Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles - at UCLK", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to core (bypassing the CHA)", + "EventCode": "0x23", + "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", + "EventCode": "0x28", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", + "EventCode": "0x27", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel(R) UPI", + "EventCode": "0x26", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", + "EventCode": "0x29", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On NonDirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in A State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in I State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in L State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit; On Dirty Line in S State", + "EventCode": "0x2A", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x2D", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On NonDirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in A State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in I State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in L State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss; On Dirty Line in S State", + "EventCode": "0x2B", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to I (Invalid)", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to S (Shared)", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to A (SnoopAll)", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to S (Shared)", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to A (SnoopAll)", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x2E", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to I (Invalid)", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_M2M_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_M2M_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC; All, regardless of priority.", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.FROM_TRANSGRESS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC; Critical Priority", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Writes to iMC issued", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TRANSGRESS", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; Full Line Non-ISOCH", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; ISOCH Full Line", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-Isochronous writes to the iMC", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC; ISOCH Partial", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches; MC Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches; Mesh Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MESH", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full", + "EventCode": "0x53", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch requests that got turn into a demand request", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefetch queue is made of CAM (Content Addressable Memory)", + "Unit": "M2M" + }, + { + "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", + "EventCode": "0x57", + "EventName": "UNC_M2M_PREFCAM_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_M2M_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", + "Deprecated": "1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 0", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 2", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Full", + "EventCode": "0x4", + "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Not Empty", + "EventCode": "0x3", + "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Queue Inserts", + "EventCode": "0x1", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x2", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Full", + "EventCode": "0x8", + "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Not Empty", + "EventCode": "0x7", + "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "EventCode": "0x5", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x6", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M2M_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M2M_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x41", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x42", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 0", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 1", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full; Channel 2", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 0", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 1", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty; Channel 2", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 0", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 1", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts; Channel 2", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy; Channel 2", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Pending Occupancy", + "EventCode": "0x48", + "EventName": "UNC_M2M_TRACKER_PENDING_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credit Acquired", + "EventCode": "0xD", + "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credits Occupancy", + "EventCode": "0xE", + "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Full", + "EventCode": "0xC", + "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Not Empty", + "EventCode": "0xB", + "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "EventCode": "0x9", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", + "EventCode": "0xF", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", + "EventCode": "0x10", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0xA", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK; CRD Transactions to Cbo", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.CRD_CBO", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK; NDR Transactions", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.NDR", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x1E", + "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x1E", + "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; All", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Near Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Far Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; All", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Read Credit Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Write Compare Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty; Write Credit Request", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; All", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Near Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Far Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Prefetch Read Cam Hit", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Read Credit Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Write Compare Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations; Write Credit Request", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; All", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Read Credit Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Write Compare Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy; Write Credit Request", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Sideband", + "EventCode": "0x6B", + "EventName": "UNC_M2M_TxC_AK_SIDEBAND.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Sideband", + "EventCode": "0x6B", + "EventName": "UNC_M2M_TxC_AK_SIDEBAND.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Cache", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Core", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to QPI", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x1A", + "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x1A", + "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; All", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Near Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Far Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; All", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; All", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Near Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Far Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; All", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", + "EventCode": "0x16", + "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", + "Deprecated": "1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 0", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 1", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 2", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 0", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 1", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full; Channel 2", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 0", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 1", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty; Channel 2", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 0", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 1", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts; Channel 2", + "EventCode": "0x61", + "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 0", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 1", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy; Channel 2", + "EventCode": "0x60", + "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Requests", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Snoops", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; VNA Messages", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty; Writebacks", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xC0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "EventCode": "0x2B", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "PublicDescription": "Count cases BL sends direct to core", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "EventCode": "0x2A", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "PublicDescription": "Cases where SMI3 sends D2U command", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Down", + "EventCode": "0xAE", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements; Up", + "EventCode": "0xAE", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FaST wire asserted; Horizontal", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_FAST_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FaST wire asserted; Vertical", + "EventCode": "0xA5", + "EventName": "UNC_M3UPI_FAST_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Even", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Even", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", + "EventCode": "0xA7", + "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Even", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Even", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", + "EventCode": "0xA9", + "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Even", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Even", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", + "EventCode": "0xAB", + "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Left", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Horizontal IV Ring in Use; Right", + "EventCode": "0xAD", + "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO0_IIO1_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO2", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO3", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO4", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; All IIO targets for NCS are in single mask. ORs them together", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty; Selected M2p BL NCS credits", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", + "PerPkg": "1", + "PublicDescription": "No vn0 and vna credits available to send to M2", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 1", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AD - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AK - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; AK - Slot 2", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received; BL - Slot 0", + "EventCode": "0x3E", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", + "EventCode": "0xA1", + "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", + "EventCode": "0xA0", + "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AD", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; AK", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; BL", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring; IV", + "EventCode": "0xA3", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; AD", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", + "EventCode": "0xA2", + "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xA4", + "EventName": "UNC_M3UPI_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; REQ on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; RSP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; SNP on AD", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; NCB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; NCS on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; RSP on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0; WB on BL", + "EventCode": "0x4B", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; REQ on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; RSP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; SNP on AD", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; NCB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; NCS on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; RSP on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1; WB on BL", + "EventCode": "0x4C", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; AD, BL Parallel Win", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", + "PerPkg": "1", + "PublicDescription": "Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN0", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN0", + "PerPkg": "1", + "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn0, delaying vn1 win, because vn0 offered parallel ad/bl", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN1", + "EventCode": "0x4D", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN1", + "PerPkg": "1", + "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn1, delaying vn0 win, because vn1 offered parallel ad/bl", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; REQ on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; RSP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; SNP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; NCB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; NCS on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; RSP on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0; WB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; REQ on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; RSP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; SNP on AD", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; NCB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; NCS on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; RSP on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1; WB on BL", + "EventCode": "0x4A", + "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; REQ on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; RSP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; SNP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; NCB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; NCS on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; RSP on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0; WB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; REQ on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; RSP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; SNP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; NCB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; NCS on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; RSP on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1; WB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on BL Arb", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on Idle", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 1", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 2", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; REQ on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; RSP on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; SNP on AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; NCB on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; NCS on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; RSP on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message lost contest for flit; WB on BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; REQ on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; RSP on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; SNP on AD", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; NCB on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; NCS on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; RSP on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message lost contest for flit; WB on BL", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; Any In BGF FIFO", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", + "PerPkg": "1", + "PublicDescription": "Indication that at least one packet (flit) is in the bgf (fifo only)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; Any in BGF Path", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", + "PerPkg": "1", + "PublicDescription": "Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events; No D2K For Arb", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "VN0 or VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; D2K Credits", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", + "PerPkg": "1", + "PublicDescription": "D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Packets in BGF FIFO", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", + "PerPkg": "1", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Packets in BGF Path", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", + "PerPkg": "1", + "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", + "PerPkg": "1", + "PublicDescription": "count of bl messages in pump-1-pending state, in completion fifo only", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", + "PerPkg": "1", + "PublicDescription": "count of bl messages in pump-1-pending state, in marker table and in fifo", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; Transmit Credits", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", + "PerPkg": "1", + "PublicDescription": "Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy; VNA In Use", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", + "PerPkg": "1", + "PublicDescription": "Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", + "EventCode": "0x44", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; All", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; No BGF Credits", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_BGF", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent; No TxQ Credits", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_TXQ", + "PerPkg": "1", + "PublicDescription": "Data flit is ready for transmission but could not be sent", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 0", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "generating bl data flit sequence; waiting for data pump 0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is tracking at least one message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", + "PerPkg": "1", + "PublicDescription": "pump-1-pending completion fifo is full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", + "PerPkg": "1", + "PublicDescription": "pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", + "PerPkg": "1", + "PublicDescription": "a bl message finished but is in limbo and moved to pump-1-pending logic", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 1", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "generating bl data flit sequence; waiting for data pump 1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC", + "EventCode": "0x5A", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; One Message", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG", + "PerPkg": "1", + "PublicDescription": "One message in flit; VNA or non-VNA flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; One Message in non-VNA", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG_VNX", + "PerPkg": "1", + "PublicDescription": "One message in flit; non-VNA flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; Two Messages", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.2_MSGS", + "PerPkg": "1", + "PublicDescription": "Two messages in flit; VNA flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit; Three Messages", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.3_MSGS", + "PerPkg": "1", + "PublicDescription": "Three messages in flit; VNA flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_2", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_3", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; All", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Needs Data Flit", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", + "PerPkg": "1", + "PublicDescription": "BL message requires data flit sequence", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 0", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Waiting for header pump 0", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Bubble", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit but flit transmission delayed", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Not Avail", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", + "PerPkg": "1", + "PublicDescription": "Header pump 1 is not required for flit and not available", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 1", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Waiting for header pump 1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate Ready", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Accumulate Wasted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Blocked", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Message", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting is in run-ahead to start new flit, and message is actually slotted into new flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Ok", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; New header flit construction may proceed in parallel with data flit sequence", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Flit Finished", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_FLIT", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit finished assembly in parallel with data flit sequence", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1; Parallel Message", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_MSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 1; Message is slotted into header flit in parallel with data flit sequence", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate-matching stall injected", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall - No Message", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", + "PerPkg": "1", + "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate matching stall injected, but no additional message slotted during stall cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; All", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No BGF Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_CRD", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No BGF Credits + No Extra Message Slotted", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_NO_MSG", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available; no additional message slotted into flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No TxQ Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_CRD", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; No TxQ Credits + No Extra Message Slotted", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_NO_MSG", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available; no additional message slotted into flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - One Slot Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ONE_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only one slot taken (two slots free)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - Three Slots Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.THREE_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with three slots taken (no slots free)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent; Sent - Two Slots Taken", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.TWO_TAKEN", + "PerPkg": "1", + "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only two slots taken (one slots free)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Can't Slot AD", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", + "PerPkg": "1", + "PublicDescription": "some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Can't Slot BL", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", + "PerPkg": "1", + "PublicDescription": "some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel AD Lost", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_AD_LOST", + "PerPkg": "1", + "PublicDescription": "some AD message lost contest for slot 0 (logical OR of all AD events under INGR_SLOT_LOST_MC_VN{0,1})", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel Attempt", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", + "PerPkg": "1", + "PublicDescription": "ad and bl messages attempted to slot into the same flit in parallel", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel BL Lost", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_BL_LOST", + "PerPkg": "1", + "PublicDescription": "some BL message lost contest for slot 0 (logical OR of all BL events under INGR_SLOT_LOST_MC_VN{0,1})", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; Parallel Success", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", + "PerPkg": "1", + "PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; VN0", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.VN0", + "PerPkg": "1", + "PublicDescription": "vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held; VN1", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_HELD.VN1", + "PerPkg": "1", + "PublicDescription": "vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; REQ on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; SNP on AD", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCS on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; WB on BL", + "EventCode": "0x41", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; REQ on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; SNP on AD", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCS on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; WB on BL", + "EventCode": "0x42", + "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; REQ on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; SNP on AD", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCS on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; WB on BL", + "EventCode": "0x45", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; REQ on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; SNP on AD", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCS on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; WB on BL", + "EventCode": "0x46", + "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; REQ on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; RSP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; SNP on AD", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; NCB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; NCS on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; RSP on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit; WB on BL", + "EventCode": "0x4E", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; REQ on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; RSP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; SNP on AD", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; NCB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; NCS on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; RSP on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit; WB on BL", + "EventCode": "0x4F", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Lost Arbitration", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARB_LOST", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Arrived", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARRIVED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Dropped - Old", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_OLD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Dropped - Wrap", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_WRAP", + "PerPkg": "1", + "PublicDescription": "Dropped because it was overwritten by new message while prefetch queue was full", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "SMI3 Prefetch Messages; Slotted", + "EventCode": "0x62", + "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.SLOTTED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Any In Use", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", + "PerPkg": "1", + "PublicDescription": "At least one remote vna credit is in use", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Corrected", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", + "PerPkg": "1", + "PublicDescription": "Number of remote vna credits corrected (local return) per cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 1", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 1 (i.e. no vna credits available)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 4", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Level < 5", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", + "PerPkg": "1", + "PublicDescription": "Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits; Used", + "EventCode": "0x5B", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.USED", + "PerPkg": "1", + "PublicDescription": "Number of remote vna credits consumed per cycle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB4", + "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AD - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; BL - Credit", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", + "EventCode": "0xB2", + "EventName": "UNC_M3UPI_RxR_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AD - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; AK - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; BL - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; IFV - Credit", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Injection Starvation; IV - Bounce", + "EventCode": "0xB3", + "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AD - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; BL - Credit", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", + "EventCode": "0xB1", + "EventName": "UNC_M3UPI_RxR_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", + "EventCode": "0xB0", + "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN0 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD; VN1 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", + "PerPkg": "1", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN0 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty; VN1 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN0 WB Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 REQ Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 RSP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts; VN1 SNP Messages", + "EventCode": "0x2D", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN0 WB Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 REQ Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 RSP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy; VN1 SNP Messages", + "EventCode": "0x1C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; CHA on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_CHA", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to CHA", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_NON_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn0 Snpf", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI0", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN0", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI1", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; CHA on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_CHA", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to CHA", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_NON_IDLE", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn1 Snpf", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI0", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN1", + "EventCode": "0x3C", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI1", + "PerPkg": "1", + "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_NONSNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_VN2SNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn0 SnpF issued when SnpF pending on Vn1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_NONSNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", + "EventCode": "0x3D", + "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_VN0SNP", + "PerPkg": "1", + "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn1 SnpF issued when SnpF pending on Vn0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 REQ Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 SNP Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 WB Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 REQ Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 SNP Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 WB Messages", + "EventCode": "0x34", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 REQ Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 SNP Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN0 WB Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 REQ Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 SNP Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - New Message; VN1 WB Messages", + "EventCode": "0x33", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 REQ Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 RSP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 SNP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN0 WB Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 REQ Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 RSP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 SNP Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD - No Credit; VN1 WB Messages", + "EventCode": "0x32", + "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Inserts", + "EventCode": "0x2F", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Occupancy", + "EventCode": "0x1E", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN0 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL; VN1 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN0 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty; VN1 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN0 NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1 RSP Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1 WB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1_NCB Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts; VN1_NCS Messages", + "EventCode": "0x2E", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN0 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1_NCS Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1_NCB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1 RSP Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy; VN1 WB Messages", + "EventCode": "0x1D", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 NCS Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 WB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 NCB Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for BL - New Message; VN1 RSP Messages", + "EventCode": "0x38", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCS Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 RSP Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 WB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCS Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 RSP Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 WB Messages", + "EventCode": "0x37", + "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", + "EventCode": "0x9D", + "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", + "EventCode": "0x9F", + "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", + "EventCode": "0x96", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", + "EventCode": "0x97", + "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", + "EventCode": "0x95", + "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", + "EventCode": "0x99", + "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", + "EventCode": "0x94", + "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", + "EventCode": "0x9B", + "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV_BNC", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical ADS Used; IV", + "EventCode": "0x9E", + "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", + "EventCode": "0x92", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", + "EventCode": "0x93", + "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Allocations; IV", + "EventCode": "0x91", + "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs; IV", + "EventCode": "0x98", + "EventName": "UNC_M3UPI_TxR_VERT_NACK.IV", + "PerPkg": "1", + "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy; IV", + "EventCode": "0x90", + "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", + "EventCode": "0x9A", + "EventName": "UNC_M3UPI_TxR_VERT_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN0 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VN1 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty; VNA", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPIs on the AD Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN0 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VN1 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty; VNA", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Even", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Down and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Even", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AD Ring In Use; Up and Odd", + "EventCode": "0xA6", + "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Even", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Down and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Even", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical AK Ring In Use; Up and Odd", + "EventCode": "0xA8", + "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Even", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Down and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Even", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical BL Ring in Use; Up and Odd", + "EventCode": "0xAA", + "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Down", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Vertical IV Ring in Use; Up", + "EventCode": "0xAC", + "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; WB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; REQ on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; RSP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP on AD", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used; RSP on BL", + "EventCode": "0x5C", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; WB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; NCB on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; REQ on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; RSP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; SNP on AD", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits; RSP on BL", + "EventCode": "0x5E", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; WB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCB on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; REQ on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; RSP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP on AD", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used; RSP on BL", + "EventCode": "0x5D", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; WB on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; NCB on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; REQ on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; RSP on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; SNP on AD", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits; RSP on BL", + "EventCode": "0x5F", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_TxC_BL.DRS_UPI", + "Deprecated": "1", + "EventCode": "0x40", + "EventName": "UNC_NoUnit_TxC_BL.DRS_UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", + "EventCode": "0x1", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", + "Unit": "UPI" + }, + { + "BriefDescription": "Data Response packets that go direct to core", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_DIRECT_ATTEMPTS.D2U", + "Deprecated": "1", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", + "PerPkg": "1", + "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "EventCode": "0x16", + "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", + "EventCode": "0x20", + "EventName": "UNC_UPI_PHY_INIT_CYCLES", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req Nack", + "EventCode": "0x23", + "EventName": "UNC_UPI_POWER_L1_NACK", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req (same as L1 Ack).", + "EventCode": "0x22", + "EventName": "UNC_UPI_POWER_L1_REQ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0. Receive side.", + "EventCode": "0x24", + "EventName": "UNC_UPI_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Request", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "REQ Message Class", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Request Opcode", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Conflict", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Invalid", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Snoop", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "SNP Message Class", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Snoop Opcode", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "CRC Errors Detected", + "EventCode": "0xB", + "EventName": "UNC_UPI_RxL_CRC_ERRORS", + "PerPkg": "1", + "PublicDescription": "Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", + "Unit": "UPI" + }, + { + "BriefDescription": "LLR Requests Sent", + "EventCode": "0x8", + "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", + "PerPkg": "1", + "PublicDescription": "Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN0 Credit Consumed", + "EventCode": "0x39", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN1 Credit Consumed", + "EventCode": "0x3A", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x38", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid data FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Data", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Idle", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; LLCRD Not Empty", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; LLCTRL", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Protocol header and credit FLITs received from any slot", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.ALL_NULL", + "Deprecated": "1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Protocol Header", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.PROTHDR", + "Deprecated": "1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.PROT_HDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 0", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 1", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received; Slot 2", + "EventCode": "0x3", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.RSP", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.SNP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.WB", + "Deprecated": "1", + "EventCode": "0x5", + "EventName": "UNC_UPI_RxL_HDR_MATCH.WB", + "PerPkg": "1", + "UMask": "0xb", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 0", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 1", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations; Slot 2", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 0", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 1", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets; Slot 2", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "EventCode": "0x2A", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0. Transmit side.", + "EventCode": "0x26", + "EventName": "UNC_UPI_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCB", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - NCS", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Request", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", + "PerPkg": "1", + "PublicDescription": "REQ Message Class", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Request Opcode", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", + "PerPkg": "1", + "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", + "UMask": "0x108", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Conflict", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", + "PerPkg": "1", + "UMask": "0x1aa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Invalid", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", + "PerPkg": "1", + "UMask": "0x12a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10c", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class - RSP", + "UMask": "0x10a", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", + "PerPkg": "1", + "PublicDescription": "SNP Message Class", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop Opcode", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", + "PerPkg": "1", + "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", + "UMask": "0x109", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0xd", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", + "PerPkg": "1", + "PublicDescription": "Match Message Class -WB", + "UMask": "0x10d", + "Unit": "UPI" + }, + { + "BriefDescription": "FLITs that bypassed the TxL Buffer", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid data FLITs transmitted via any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs transmitted from any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Data", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Idle FLITs transmitted", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; LLCRD Not Empty", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; LLCTRL", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.ALL_NULL", + "Deprecated": "1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Protocol Header", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.PROTHDR", + "Deprecated": "1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.PROT_HDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 0", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 1", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent; Slot 2", + "EventCode": "0x2", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.DATA_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.DUAL_SLOT_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.LOC", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NCB", + "PerPkg": "1", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NCS", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.NON_DATA_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.REM", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_DATA", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_NODATA", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.SGL_SLOT_HDR", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.SNP", + "PerPkg": "1", + "UMask": "0x9", + "Unit": "UPI" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.WB", + "Deprecated": "1", + "EventCode": "0x4", + "EventName": "UNC_UPI_TxL_HDR_MATCH.WB", + "PerPkg": "1", + "UMask": "0xc", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "EventCode": "0x45", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x44", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received; VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + }, + { + "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", + "EventCode": "0x2", + "EventName": "UPI_DATA_BANDWIDTH_TX", + "PerPkg": "1", + "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", + "ScaleUnit": "7.11E-06Bytes", + "UMask": "0xf", + "Unit": "UPI" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json new file mode 100644 index 000000000000..2a3a709018bb --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json @@ -0,0 +1,4250 @@ +[ + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "ScaleUnit": "4Bytes", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "ScaleUnit": "4Bytes", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Clockticks of the IIO Traffic Controller", + "EventCode": "0x1", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x0f", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x01", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x02", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x04", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x4", + "PerPkg": "1", + "PortMask": "0x08", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 0", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x01", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 1", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x02", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 2", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x04", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts; Port 3", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x08", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 1", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 2", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 3", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num Link Correctable Errors", + "EventCode": "0xF", + "EventName": "UNC_IIO_LINK_NUM_CORR_ERR", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num Link Retries", + "EventCode": "0xE", + "EventName": "UNC_IIO_LINK_NUM_RETRIES", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number packets that passed the Mask/Match Filter", + "EventCode": "0x21", + "EventName": "UNC_IIO_MASK_MATCH", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus", + "EventCode": "0x2", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x3", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Counting disabled", + "EventName": "UNC_IIO_NOTHING", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x83", + "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC0", + "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Symbol Times on Link", + "EventCode": "0x82", + "EventName": "UNC_IIO_SYMBOL_TIMES", + "PerPkg": "1", + "PublicDescription": "Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.MSG.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART2", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART3", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x8", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD0", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x10", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", + "Deprecated": "1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD1", + "FCMask": "0x7", + "PerPkg": "1", + "PortMask": "0x20", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; context cache miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.CTXT_MISS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L1 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L1_MISS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L2 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L2_MISS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; L3 miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L3_MISS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; Vtd hit", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.L4_PAGE_HIT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB1_MISS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB is full", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Access; TLB miss", + "EventCode": "0x41", + "EventName": "UNC_IIO_VTD_ACCESS.TLB_MISS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "VTd Occupancy", + "EventCode": "0x40", + "EventName": "UNC_IIO_VTD_OCCUPANCY", + "PerPkg": "1", + "Unit": "IIO" + } +] diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json index e0840c24e7aa..6f8ff2262ce7 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-memory.json @@ -1952,7 +1952,7 @@ "EventCode": "0x81", "EventName": "UNC_M_WPQ_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts???", + "PublicDescription": "Counts the number of entries in the Write Pending Queue (WPQ) at each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule writes out to the memory controller and to track the requests. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC (memory controller). They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have 'posted' to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the 'not posted' filter, we can track how long writes spent in the iMC before completions were sent to the HA. The 'posted' filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts. Is there a filter of sorts?", "Unit": "iMC" }, { diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json deleted file mode 100644 index 92a4bdcd4bd7..000000000000 --- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-other.json +++ /dev/null @@ -1,26143 +0,0 @@ -[ - { - "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_READ", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "MetricName": "LLC_MISSES.PCIE_READ", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "ScaleUnit": "4Bytes", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_WRITE", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "MetricName": "LLC_MISSES.PCIE_WRITE", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "ScaleUnit": "4Bytes", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Intermediate bypass Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the intermediate bypass.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Not Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass; Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not.; Filter for transactions that succeeded in taking the full bypass.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Clockticks of the uncore caching & home agent (CHA)", - "EventName": "UNC_CHA_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the clock controlling the uncore caching and home agent (CHA).", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_CHA_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C1 State", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C1_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C1 Transition", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C1_TRANSITION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C6 State", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C6_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; C6 Transition", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.C6_TRANSITION", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Core PMA Events; GV", - "EventCode": "0x17", - "EventName": "UNC_CHA_CORE_PMA.GV", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Cycle with Multiple Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Single Snoop", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Any Snoop to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Core Request to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Eviction to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Multiple External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; Single External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued; External Snoop to Remote Node", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "Counter 0 Occupancy", - "EventCode": "0x1F", - "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", - "EventCode": "0x53", - "EventName": "UNC_CHA_DIR_LOOKUP.SNP", - "PerPkg": "1", - "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.HA", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", - "EventCode": "0x54", - "EventName": "UNC_CHA_DIR_UPDATE.TOR", - "PerPkg": "1", - "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_CHA_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_CHA_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.EX_RDS", - "PerPkg": "1", - "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; Shared hit and op is RdInvOwn, RdInv, Inv*", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoE", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Hits in HitMe Cache; op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "EventCode": "0x5F", - "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.READ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times HitMe Cache is accessed; op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", - "EventCode": "0x5E", - "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; No SF/LLC HitS/F and op is RdInvOwn", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of Misses in HitMe Cache; SF/LLC HitS/F and op is RdInvOwn", - "EventCode": "0x60", - "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Deallocate HitME$ on Reads without RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a local request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "PerPkg": "1", - "PublicDescription": "Received RspFwdI* for a local request, but converted HitME$ to SF entry", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache on RdInvOwn even if not RspFwdI*", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; op is RspIFwd or RspIFwdWb for a remote request", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", - "PerPkg": "1", - "PublicDescription": "Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache; Update HitMe Cache to SHARed", - "EventCode": "0x61", - "EventName": "UNC_CHA_HITME_UPDATE.SHARED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "HA to iMC Reads Issued; ISOCH", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "PublicDescription": "Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Full Line MIG", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Full Line", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Partial Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; Partial MIG", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Writes Issued to the iMC by the HA; ISOCH Partial", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "Counts the total number of writes issued from the HA into the memory controller. This counts for all four channels. It can be filtered by full/partial and ISOCH/non-ISOCH.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.INVITOM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IODC allocations dropped due to IODC Full", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.IODCFULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts Number of times IODC entry allocation is attempted; Number of IDOC allocation dropped due to OSB gate", - "EventCode": "0x62", - "EventName": "UNC_CHA_IODC_ALLOC.OSBGATED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to any reason", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to conflicting transaction", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.SNPOUT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoE", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbMtoI", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBMTOI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Counts number of IODC deallocations; IODC deallocated due to WbPushMtoI", - "EventCode": "0x63", - "EventName": "UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", - "PerPkg": "1", - "PublicDescription": "Moved to Cbo section", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ANY", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Read transactions", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Local", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Remote", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.", - "UMask": "0x91", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; External Snoop Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for only snoop requests coming from the remote socket(s) through the IPQ.", - "UMask": "0x9", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Write Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITE", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", - "UMask": "0x5", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.F_STATE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Local - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Remote - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in E state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in F State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_F", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in M state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized; Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", - "PerPkg": "1", - "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; CV0 Prefetch Miss", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; CV0 Prefetch Victim", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Number of times that an RFO hit in S state.", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RFO_HIT_S", - "PerPkg": "1", - "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; Silent Snoop Eviction", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc; Write Combining Aliasing", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.WC_ALIASING", - "PerPkg": "1", - "PublicDescription": "Miscellaneous events in the Cbo.; Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "OSB Snoop Broadcast", - "EventCode": "0x55", - "EventName": "UNC_CHA_OSB", - "PerPkg": "1", - "PublicDescription": "Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC0_SMI2", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC1_SMI3", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC2_SMI4", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; EDC3_SMI5", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC0_SMI0", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty; MC1_SMI1", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue.; Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS", - "PerPkg": "1", - "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Read requests from a remote socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Write requests", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "Write Requests from a unit on this socket", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Read and Write Requests; Writes Remote", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_CHA_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IPQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; IRQ Rejected", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; RRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.RRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations; WBQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.WBQ", - "PerPkg": "1", - "PublicDescription": "Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; AD REQ on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; AD RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Non UPI AK Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL NCB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL NCS on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL RSP on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; BL WB on VN0", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Non UPI IV Request", - "EventCode": "0x22", - "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Allow Snoop", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; ANY0", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; HA", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; LLC Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; PhyAddr Match", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; SF Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress Probe Queue Rejects; Victim", - "EventCode": "0x23", - "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; AD REQ on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; AD RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; Non UPI AK Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL NCB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL NCS on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; BL WB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; Non UPI IV Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; AD REQ on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; AD RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; Non UPI AK Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL NCB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL NCS on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; BL WB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; Non UPI IV Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; ANY0", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects; HA", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; ANY0", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries; HA", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; IPQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; IRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; RRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy; WBQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", - "PerPkg": "1", - "PublicDescription": "Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; AD REQ on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; AD RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Non UPI AK Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL NCB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL NCS on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; BL WB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Non UPI IV Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Allow Snoop", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; ANY0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; HA", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; LLC Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; PhyAddr Match", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; SF Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries; Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD REQ on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; AD RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI AK Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL NCS on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; BL WB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Non UPI IV Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Allow Snoop", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; ANY0", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; HA", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC OR SF Way", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; LLC Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; SF Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; AD REQ on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; AD RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Non UPI AK Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL NCB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL NCS on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; BL WB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Non UPI IV Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Allow Snoop", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; ANY0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; HA", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; LLC Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; PhyAddr Match", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; SF Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries; Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; AD REQ on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; AD RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Non UPI AK Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL NCB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL NCS on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL RSP on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; BL WB on VN0", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Non UPI IV Request", - "EventCode": "0x26", - "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Allow Snoop", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; ANY0", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; HA", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; LLC Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; PhyAddr Match", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; SF Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RRQ Rejects; Victim", - "EventCode": "0x27", - "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; AD REQ on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; AD RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Non UPI AK Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL NCB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL NCS on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL RSP on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; BL WB on VN0", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Non UPI IV Request", - "EventCode": "0x28", - "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Allow Snoop", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; ANY0", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; HA", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Merging these two together to make room for ANY_REJECT_*0", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; LLC Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; PhyAddr Match", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; SF Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "WBQ Rejects; Victim", - "EventCode": "0x29", - "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", - "PerPkg": "1", - "PublicDescription": "Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_CHA_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_CHA_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for E-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.E_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for M-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.M_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for S-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.S_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores cache. Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry. Does not count clean evictions such as when a cores cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; All", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast snoop for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Directed snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Directed snoops for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent; Broadcast or directed Snoops sent for Remote Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", - "PerPkg": "1", - "PublicDescription": "Counts the number of snoops issued by the HA.; Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "RspCnflct* Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCTS", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspCnflct* Snoop Response was received. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent. This triggers conflict resolution hardware. This covers both the opcode RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received; RspFwd", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1.; Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "RspI Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPI", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "RspIFwd Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received : RspS", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received : RspS : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoop responses of RspS. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "RspSFwd Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Rsp*Fwd*WB Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSP_FWD_WB", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type Rsp*Fwd*WB Snoop Response was received which indicates the data was written back to its home socket, and the cacheline was forwarded to the requestor socket. This snoop response is only used in >= 4 socket systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to its home socket to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Rsp*WB Snoop Responses Received", - "EventCode": "0x5C", - "EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB", - "PerPkg": "1", - "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to its home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspCnflct", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspI", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspIFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspS", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; RspSFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; Rsp*FWD*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local; Rsp*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", - "PerPkg": "1", - "PublicDescription": "Number of snoop responses received for a Local request; Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x15", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local iA and IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_IO_IA", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests", - "UMask": "0x35", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Misses from Local", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x25", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; SF/LLC Evictions", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.EVICT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hit (Not a Miss)", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from iA Cores", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : LLCPrefRFO issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; All from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally generated IO traffic", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Hits from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; ItoM misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", - "Filter": "config1=0x49033", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM request is used by IIO to request a data write without first reading the data for ownership.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RdCur misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RDCUR", - "Filter": "config1=0x43C33", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RdCur requests and miss the LLC. A RdCur request is used by IIO to read data without changing state.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; RFO misses from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests a cache line to be cached in E state with the intent to modify.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; IPQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; IRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; Miss", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MISS", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; PRQ", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ_HIT", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.RRQ_MISS", - "PerPkg": "1", - "UMask": "0x60", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ_HIT", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.WBQ_MISS", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. There are a number of subevent 'filters' but only a subset of the subevent combinations are valid. Subevents that require an opcode or NID match require the Cn_MSR_PMON_BOX_FILTER.{opc, nid} field to be set. If, for example, one wanted to count DRD Local Misses, one should select MISS_OPC_MATCH and set Cn_MSR_PMON_BOX_FILTER.opc to DRD (0x182); All remotely generated requests", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x17", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x27", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; SF/LLC Evictions", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hit (Not a Miss)", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; HITs (hit is defined to be not a miss [see below], as a result for any request allocated into the TOR, one of either HIT or MISS must be true)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally initiated requests from iA Cores", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "Filter": "config1=0x40233", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", - "Filter": "config1=0x40433", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefCRD", - "Filter": "config1=0x4b233", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefDRD", - "Filter": "config1=0x4b433", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LlcPrefRFO", - "Filter": "config1=0x4b033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : LLCPrefRFO issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; All from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; All locally generated IO traffic", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Hits from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; ITOM Misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", - "Filter": "config1=0x49033", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO ItoM requests that miss the LLC. An ItoM is used by IIO to request a data write without first reading the data for ownership.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RDCUR misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RDCUR", - "Filter": "config1=0x43C33", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RdCur requests that miss the LLC. A RdCur request is used by IIO to read data without changing state.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; RFO misses from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", - "Filter": "config1=0x40033", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that are generated from local IO RFO requests that miss the LLC. A read for ownership (RFO) requests data to be cached in E state with the intent to modify.", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; IPQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; IRQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.ALL_FROM_LOC", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; Miss", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T; Misses. (a miss is defined to be any transaction from the IRQ, PRQ, RRQ, IPQ or (in the victim case) the ISMQ, that required the CHA to spawn a new UPI/SMI3 request on the UPI fabric (including UPI snoops and/or any RD/WR to a local memory controller, in the event that the CHA is the home node)). Basically, if the LLC/SF/MLC complex were not able to service the request without involving another agent...it is a miss. If only IDI snoops were required, it is not a miss (that means the SF/MLC com", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; PRQ", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; AD REQ Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; AD RSP VN0 Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL NCB Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL NCS Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL RSP Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; BL DRS Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; VN0 Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VN0", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credit Allocations; VNA Credits", - "EventCode": "0x38", - "EventName": "UNC_CHA_UPI_CREDITS_ACQUIRED.VNA", - "PerPkg": "1", - "PublicDescription": "Counts the number of UPI credits acquired for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This can be used with the Credit Occupancy event in order to calculate average credit lifetime. This event supports filtering to cover the VNA/VN0 credits and the different message classes. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD REQ VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD RSP VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCB VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL NCS VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL RSP VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL DRS VN0 Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VN0_BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; AD VNA Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_AD", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "UPI Ingress Credits In Use Cycles; BL VNA Credits", - "EventCode": "0x3B", - "EventName": "UNC_CHA_UPI_CREDIT_OCCUPANCY.VNA_BL", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of UPI credits available in each cycle for either the AD or BL ring. In order to send snoops, snoop responses, requests, data, etc to the UPI agent on the ring, it is necessary to first acquire a credit for the UPI ingress buffer. This stat increments by the number of credits that are available each cycle. This can be used in conjunction with the Credit Acquired event in order to calculate average credit lifetime. This event supports filtering for the different types of credits that are available. Note that you must select the link that you would like to monitor using the link select register, and you can only monitor 1 link at a time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI; Pushed to LLC", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was able to push WbPushMToI to LLC", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI; Pushed to Memory", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when the CHA was received WbPushMtoI; Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC0_SMI2", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC1_SMI3", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC2_SMI4", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; EDC3_SMI5", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC0_SMI0", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty; MC1_SMI1", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue.; Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd F/E", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response I to Fwd M", - "UMask": "0xf0", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd F/E", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response S to Fwd M", - "UMask": "0xe8", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Any RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Any Request - Response any to Hit F/S/E", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd F/E", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response I to Fwd M", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd F/E", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response S to Fwd M", - "UMask": "0x48", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Core RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Core Request - Response any to Hit F/S/E", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd F/E", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response I to Fwd M", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd F/E", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response S to Fwd M", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; Evict RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; Eviction Request - Response any to Hit F/S/E", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspIFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd F/E", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspIFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response I to Fwd M", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspSFwdFE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd F/E", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspSFwdM", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response S to Fwd M", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoop Responses; External RspHitFSE", - "EventCode": "0x32", - "EventName": "UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", - "PerPkg": "1", - "PublicDescription": "Counts the number of core cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type. This event can be filtered based on who triggered the initial snoop(s): from Evictions, Core or External (i.e. from a remote node) Requests. And the event can be filtered based on the responses: RspX_Fwd/HitY where Y is the state prior to the snoop response and X is the state following.; External Request - Response any to Hit F/S/E", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CLOCKTICKS", - "Deprecated": "1", - "EventName": "UNC_C_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_FAST_ASSERTED.HORZ", - "Deprecated": "1", - "EventCode": "0xA5", - "EventName": "UNC_C_FAST_ASSERTED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.ANY", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.ANY", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.LOCAL", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.REMOTE", - "PerPkg": "1", - "UMask": "0x91", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.REMOTE_SNOOP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.WRITE", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_C_LLC_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x5", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_E", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_F", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.F_STATE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.LOCAL", - "PerPkg": "1", - "UMask": "0x2f", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_M", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.REMOTE_ALL", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.REMOTE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_VICTIMS.TOTAL_S", - "Deprecated": "1", - "EventCode": "0x37", - "EventName": "UNC_C_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SRC_THRTL", - "Deprecated": "1", - "EventCode": "0xA4", - "EventName": "UNC_C_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.EVICT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.EVICT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.HIT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IPQ", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ_HIT", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA_MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.IRQ_MISS", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IA", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_IA", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.LOC_IO", - "PerPkg": "1", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.PRQ", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_HIT", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ_HIT", - "PerPkg": "1", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.IO_MISS", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.PRQ_MISS", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.REM_ALL", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.RRQ_HIT", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.RRQ_MISS", - "PerPkg": "1", - "UMask": "0x60", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.WBQ_HIT", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_C_TOR_INSERTS.WBQ_MISS", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.EVICT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IPQ", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_HIT", - "PerPkg": "1", - "UMask": "0x18", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IPQ_MISS", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_HIT", - "PerPkg": "1", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.IRQ_MISS", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "UMask": "0x37", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IA", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IA", - "PerPkg": "1", - "UMask": "0x31", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.LOC_IO", - "PerPkg": "1", - "UMask": "0x34", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.PRQ", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_HIT", - "PerPkg": "1", - "UMask": "0x14", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "Deprecated": "1", - "EventCode": "0x36", - "EventName": "UNC_C_TOR_OCCUPANCY.PRQ_MISS", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x80", - "EventName": "UNC_H_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_AD_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x82", - "EventName": "UNC_H_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x88", - "EventName": "UNC_H_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG0_BL_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x8A", - "EventName": "UNC_H_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_H_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_AD_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x86", - "EventName": "UNC_H_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR0", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR1", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR2", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR3", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR4", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CRD_OCCUPANCY.TGR5", - "Deprecated": "1", - "EventCode": "0x8E", - "EventName": "UNC_H_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR0", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR1", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR2", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR3", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR4", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_AG1_BL_CREDITS_ACQUIRED.TGR5", - "Deprecated": "1", - "EventCode": "0x8C", - "EventName": "UNC_H_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "Deprecated": "1", - "EventCode": "0x57", - "EventName": "UNC_H_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CMS_CLOCKTICKS", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_H_CLOCK", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_STATE", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C1_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C1_TRANSITION", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C1_TRANSITION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_STATE", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C6_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.C6_TRANSITION", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.C6_TRANSITION", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_PMA.GV", - "Deprecated": "1", - "EventCode": "0x17", - "EventName": "UNC_H_CORE_PMA.GV", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.ANY_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.ANY_REMOTE", - "PerPkg": "1", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.CORE_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.CORE_REMOTE", - "PerPkg": "1", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EVICT_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EVICT_REMOTE", - "PerPkg": "1", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_GTONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_ONE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_CORE_SNP.EXT_REMOTE", - "Deprecated": "1", - "EventCode": "0x33", - "EventName": "UNC_H_CORE_SNP.EXT_REMOTE", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_COUNTER0_OCCUPANCY", - "Deprecated": "1", - "EventCode": "0x1F", - "EventName": "UNC_H_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.NO_SNP", - "Deprecated": "1", - "EventCode": "0x53", - "EventName": "UNC_H_DIR_LOOKUP.NO_SNP", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_LOOKUP.SNP", - "Deprecated": "1", - "EventCode": "0x53", - "EventName": "UNC_H_DIR_LOOKUP.SNP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.HA", - "Deprecated": "1", - "EventCode": "0x54", - "EventName": "UNC_H_DIR_UPDATE.HA", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_DIR_UPDATE.TOR", - "Deprecated": "1", - "EventCode": "0x54", - "EventName": "UNC_H_DIR_UPDATE.TOR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "Deprecated": "1", - "EventCode": "0xAE", - "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "Deprecated": "1", - "EventCode": "0xAE", - "EventName": "UNC_H_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.EX_RDS", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.EX_RDS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.SHARED_OWNREQ", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.SHARED_OWNREQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOE", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.WBMTOE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_HIT.WBMTOI_OR_S", - "Deprecated": "1", - "EventCode": "0x5F", - "EventName": "UNC_H_HITME_HIT.WBMTOI_OR_S", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.READ", - "Deprecated": "1", - "EventCode": "0x5E", - "EventName": "UNC_H_HITME_LOOKUP.READ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_LOOKUP.WRITE", - "Deprecated": "1", - "EventCode": "0x5E", - "EventName": "UNC_H_HITME_LOOKUP.WRITE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.NOTSHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.READ_OR_INV", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.READ_OR_INV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_MISS.SHARED_RDINVOWN", - "Deprecated": "1", - "EventCode": "0x60", - "EventName": "UNC_H_HITME_MISS.SHARED_RDINVOWN", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RDINVOWN", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.RDINVOWN", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.RSPFWDI_REM", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.RSPFWDI_REM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HITME_UPDATE.SHARED", - "Deprecated": "1", - "EventCode": "0x61", - "EventName": "UNC_H_HITME_UPDATE.SHARED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xA7", - "EventName": "UNC_H_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xA9", - "EventName": "UNC_H_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "Deprecated": "1", - "EventCode": "0xAB", - "EventName": "UNC_H_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "Deprecated": "1", - "EventCode": "0xAD", - "EventName": "UNC_H_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "Deprecated": "1", - "EventCode": "0xAD", - "EventName": "UNC_H_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.NORMAL", - "Deprecated": "1", - "EventCode": "0x59", - "EventName": "UNC_H_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_READS_COUNT.PRIORITY", - "Deprecated": "1", - "EventCode": "0x59", - "EventName": "UNC_H_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_MIG", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_MIG", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_MIG", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_MIG", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "Deprecated": "1", - "EventCode": "0x5B", - "EventName": "UNC_H_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.INVITOM", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.INVITOM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.IODCFULL", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.IODCFULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_ALLOC.OSBGATED", - "Deprecated": "1", - "EventCode": "0x62", - "EventName": "UNC_H_IODC_ALLOC.OSBGATED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.ALL", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.SNPOUT", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.SNPOUT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOE", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBMTOE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBMTOI", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBMTOI", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_IODC_DEALLOC.WBPUSHMTOI", - "Deprecated": "1", - "EventCode": "0x63", - "EventName": "UNC_H_IODC_DEALLOC.WBPUSHMTOI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_MISS", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.CV0_PREF_VIC", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RFO_HIT_S", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.RFO_HIT_S", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.RSPI_WAS_FSE", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_MISC.WC_ALIASING", - "Deprecated": "1", - "EventCode": "0x39", - "EventName": "UNC_H_MISC.WC_ALIASING", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_OSB", - "Deprecated": "1", - "EventCode": "0x55", - "EventName": "UNC_H_OSB", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC0_SMI2", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC1_SMI3", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC2_SMI4", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.EDC3_SMI5", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC0_SMI0", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_READ_NO_CREDITS.MC1_SMI1", - "Deprecated": "1", - "EventCode": "0x58", - "EventName": "UNC_H_READ_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_LOCAL", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.INVITOE_LOCAL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_REQUESTS.INVITOE_REMOTE", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.INVITOE_REMOTE", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from local home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS_LOCAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "read requests from remote home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.READS_REMOTE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from local home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES_LOCAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "write requests from remote home agent", - "Deprecated": "1", - "EventCode": "0x50", - "EventName": "UNC_H_REQUESTS.WRITES_REMOTE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AD", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.AK", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.BL", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_HORZ.IV", - "Deprecated": "1", - "EventCode": "0xA1", - "EventName": "UNC_H_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AD", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.AK", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.BL", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_BOUNCES_VERT.IV", - "Deprecated": "1", - "EventCode": "0xA0", - "EventName": "UNC_H_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "Deprecated": "1", - "EventCode": "0xA3", - "EventName": "UNC_H_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AD", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.AK", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.BL", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RING_SINK_STARVED_VERT.IV", - "Deprecated": "1", - "EventCode": "0xA2", - "EventName": "UNC_H_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IPQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IPQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.IRQ_REJ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.PRQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.PRQ_REJ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.RRQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.RRQ", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_INSERTS.WBQ", - "Deprecated": "1", - "EventCode": "0x13", - "EventName": "UNC_H_RxC_INSERTS.WBQ", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x22", - "EventName": "UNC_H_RxC_IPQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.ANY_IPQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IPQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x23", - "EventName": "UNC_H_RxC_IPQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x18", - "EventName": "UNC_H_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.ANY_REJECT_IRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x19", - "EventName": "UNC_H_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x24", - "EventName": "UNC_H_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2C", - "EventName": "UNC_H_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x25", - "EventName": "UNC_H_RxC_ISMQ1_REJECT.ANY_ISMQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x25", - "EventName": "UNC_H_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2D", - "EventName": "UNC_H_RxC_ISMQ1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_ISMQ1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2D", - "EventName": "UNC_H_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IPQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.IPQ", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.IRQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.RRQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.RRQ", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OCCUPANCY.WBQ", - "Deprecated": "1", - "EventCode": "0x11", - "EventName": "UNC_H_RxC_OCCUPANCY.WBQ", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2E", - "EventName": "UNC_H_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "Deprecated": "1", - "EventCode": "0x2F", - "EventName": "UNC_H_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x20", - "EventName": "UNC_H_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.ANY_PRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x21", - "EventName": "UNC_H_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x2A", - "EventName": "UNC_H_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.ANY", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "Deprecated": "1", - "EventCode": "0x2B", - "EventName": "UNC_H_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x26", - "EventName": "UNC_H_RxC_RRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.ANY_RRQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_RRQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x27", - "EventName": "UNC_H_RxC_RRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", - "Deprecated": "1", - "EventCode": "0x28", - "EventName": "UNC_H_RxC_WBQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.ANY0", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.ANY_WBQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.HA", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxC_WBQ1_REJECT.VICTIM", - "Deprecated": "1", - "EventCode": "0x29", - "EventName": "UNC_H_RxC_WBQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB4", - "EventName": "UNC_H_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_BYPASS.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB2", - "EventName": "UNC_H_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IFV", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_CRD_STARVED.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB3", - "EventName": "UNC_H_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_INSERTS.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB1", - "EventName": "UNC_H_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.AK_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_RxR_OCCUPANCY.IV_BNC", - "Deprecated": "1", - "EventCode": "0xB0", - "EventName": "UNC_H_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.E_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.E_STATE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.M_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.M_STATE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SF_EVICTION.S_STATE", - "Deprecated": "1", - "EventCode": "0x3D", - "EventName": "UNC_H_SF_EVICTION.S_STATE", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.ALL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.BCST_LOC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.BCST_REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.BCST_REM", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.DIRECT_LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.DIRECT_REM", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.LOCAL", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOPS_SENT.REMOTE", - "Deprecated": "1", - "EventCode": "0x51", - "EventName": "UNC_H_SNOOPS_SENT.REMOTE", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPCNFLCTS", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPFWD", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPI", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPI", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPIFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPIFWD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPS", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSPSFWD", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSPSFWD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_FWD_WB", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP.RSP_WBWB", - "Deprecated": "1", - "EventCode": "0x5C", - "EventName": "UNC_H_SNOOP_RESP.RSP_WB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPFWD", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPI", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPIFWD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSPSFWD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_FWD_WB", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_FWD_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_SNOOP_RESP_LOCAL.RSP_WB", - "Deprecated": "1", - "EventCode": "0x5D", - "EventName": "UNC_H_SNP_RSP_RCV_LOCAL.RSP_WB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "Deprecated": "1", - "EventCode": "0xD0", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "Deprecated": "1", - "EventCode": "0xD2", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "Deprecated": "1", - "EventCode": "0xD4", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "Deprecated": "1", - "EventCode": "0xD6", - "EventName": "UNC_H_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "Deprecated": "1", - "EventCode": "0x9D", - "EventName": "UNC_H_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_BYPASS.IV_BNC", - "Deprecated": "1", - "EventCode": "0x9F", - "EventName": "UNC_H_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.AK_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_FULL.IV_BNC", - "Deprecated": "1", - "EventCode": "0x96", - "EventName": "UNC_H_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.AK_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_CYCLES_NE.IV_BNC", - "Deprecated": "1", - "EventCode": "0x97", - "EventName": "UNC_H_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.AK_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_INSERTS.IV_BNC", - "Deprecated": "1", - "EventCode": "0x95", - "EventName": "UNC_H_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.AK_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_NACK.IV_BNC", - "Deprecated": "1", - "EventCode": "0x99", - "EventName": "UNC_H_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.AK_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_OCCUPANCY.IV_BNC", - "Deprecated": "1", - "EventCode": "0x94", - "EventName": "UNC_H_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AD_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.AK_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.BL_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_HORZ_STARVED.IV_BNC", - "Deprecated": "1", - "EventCode": "0x9B", - "EventName": "UNC_H_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9C", - "EventName": "UNC_H_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_BYPASS.IV", - "Deprecated": "1", - "EventCode": "0x9E", - "EventName": "UNC_H_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AD_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.AK_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG0", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.BL_AG1", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_FULL.IV", - "Deprecated": "1", - "EventCode": "0x92", - "EventName": "UNC_H_TxR_VERT_CYCLES_FULL.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AD_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.AK_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG0", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.BL_AG1", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_CYCLES_NE.IV", - "Deprecated": "1", - "EventCode": "0x93", - "EventName": "UNC_H_TxR_VERT_CYCLES_NE.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AD_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.AK_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG0", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.BL_AG1", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_INSERTS.IV", - "Deprecated": "1", - "EventCode": "0x91", - "EventName": "UNC_H_TxR_VERT_INSERTS.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AD_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.AK_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG0", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.BL_AG1", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_NACK.IV", - "Deprecated": "1", - "EventCode": "0x98", - "EventName": "UNC_H_TxR_VERT_NACK.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AD_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.AK_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG0", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.BL_AG1", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_OCCUPANCY.IV", - "Deprecated": "1", - "EventCode": "0x90", - "EventName": "UNC_H_TxR_VERT_OCCUPANCY.IV_AG0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AD_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.AK_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG0", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.BL_AG1", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TxR_VERT_STARVED.IV", - "Deprecated": "1", - "EventCode": "0x9A", - "EventName": "UNC_H_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xA6", - "EventName": "UNC_H_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xA8", - "EventName": "UNC_H_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "Deprecated": "1", - "EventCode": "0xAA", - "EventName": "UNC_H_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.DN", - "Deprecated": "1", - "EventCode": "0xAC", - "EventName": "UNC_H_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_VERT_RING_IV_IN_USE.UP", - "Deprecated": "1", - "EventCode": "0xAC", - "EventName": "UNC_H_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.LLC", - "Deprecated": "1", - "EventCode": "0x56", - "EventName": "UNC_H_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WB_PUSH_MTOI.MEM", - "Deprecated": "1", - "EventCode": "0x56", - "EventName": "UNC_H_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC0_SMI2", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC0_SMI2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC1_SMI3", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC1_SMI3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC2_SMI4", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC2_SMI4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.EDC3_SMI5", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.EDC3_SMI5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC0_SMI0", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.MC0_SMI0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_WRITE_NO_CREDITS.MC1_SMI1", - "Deprecated": "1", - "EventCode": "0x5A", - "EventName": "UNC_H_WRITE_NO_CREDITS.MC1_SMI1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0xe4", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0xf0", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0xe2", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0xe8", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.ANY_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.ANY_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0xe1", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x50", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x48", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.CORE_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.CORE_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x84", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EVICT_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EVICT_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDFE", - "PerPkg": "1", - "UMask": "0x24", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPI_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPI_FWDM", - "PerPkg": "1", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDFE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDFE", - "PerPkg": "1", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSPS_FWDM", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSPS_FWDM", - "PerPkg": "1", - "UMask": "0x28", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_XSNP_RESP.EXT_RSP_HITFSE", - "Deprecated": "1", - "EventCode": "0x32", - "EventName": "UNC_H_XSNP_RESP.EXT_RSP_HITFSE", - "PerPkg": "1", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Clockticks of the IIO Traffic Controller", - "EventCode": "0x1", - "EventName": "UNC_IIO_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x0f", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x01", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x02", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x04", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", - "FCMask": "0x4", - "PerPkg": "1", - "PortMask": "0x08", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 0", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x01", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 1", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x02", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 2", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x04", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts; Port 3", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.PORT3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x08", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0-3", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0xf", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 0", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 1", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 2", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer occupancy of completions with data: Part 3", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for 4 bytes of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part2", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part3", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts ever peer to peer read request for 4 bytes of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part1 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part2 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part3 by a different IIO unit", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests initiated by the main die to the attached device.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of 4 bytes of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part1 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part2 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for 4 bytes made by IIO Part3 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request for 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of 4 bytes of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number of double word (4 bytes) requests the attached device made of the main die.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Num Link Correctable Errors", - "EventCode": "0xF", - "EventName": "UNC_IIO_LINK_NUM_CORR_ERR", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num Link Retries", - "EventCode": "0xE", - "EventName": "UNC_IIO_LINK_NUM_RETRIES", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number packets that passed the Mask/Match Filter", - "EventCode": "0x21", - "EventName": "UNC_IIO_MASK_MATCH", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus", - "EventCode": "0x2", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if all bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus; !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x3", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "Asserted if any bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Counting disabled", - "EventName": "UNC_IIO_NOTHING", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMIC.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.ATOMICCMP.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.ATOMICCMP.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.MSG.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.MSG.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x83", - "EventName": "UNC_IIO_PAYLOAD_BYTES_IN.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.CFG_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.IO_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC0", - "EventName": "UNC_IIO_PAYLOAD_BYTES_OUT.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Symbol Times on Link", - "EventCode": "0x82", - "EventName": "UNC_IIO_SYMBOL_TIMES", - "PerPkg": "1", - "PublicDescription": "Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMIC.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.ATOMICCMP.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.MSG.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_IN.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.CFG_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.IO_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.MEM_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_READ.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART2", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.PART3", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x8", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD0", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x10", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", - "Deprecated": "1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_OUT.PEER_WRITE.VTD1", - "FCMask": "0x7", - "PerPkg": "1", - "PortMask": "0x20", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part0. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part1. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part2. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by a unit on the main die (generally a core) or by another IIO unit to the MMIO space of a card on IIO Part3. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a unit on the main die (generally a core) or by another IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part0", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part0. Does not include requests made by the same IIO unit. In the general case, part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part1", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part1. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part2", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part2. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request for up to a 64 byte transaction is made by a different IIO unit to IIO Part3", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request for up to a 64 byte transaction of data made by a different IIO unit to the MMIO space of a card on IIO Part3. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part0 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part0 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part1 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part1 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part2 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part2 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made to IIO Part3 by a different IIO unit", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made to the MMIO space of a card on IIO Part3 by a different IIO unit. Does not include requests made by the same IIO unit. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU; Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Outbound. Number of requests, to the attached device, initiated by the main die.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Completion of atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMICCMP.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every read request for up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part0 to a unit on the main die (generally memory). In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part1 to a unit on the main die (generally memory). In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part2 to a unit on the main die (generally memory). In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every write request of up to a 64 byte transaction of data made by IIO Part3 to a unit on the main die (generally memory). In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part1 to the MMIO space of an IIO target. In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer read request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer read request of up to a 64 byte transaction made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part0 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part0 to the MMIO space of an IIO target. In the general case, Part0 refers to a standard PCIe card of any size (x16,x8,x4) that is plugged directly into one of the PCIe slots. Part0 could also refer to any device plugged into the first slot of a PCIe riser card or to a device attached to the IIO unit which starts its use of the bus using lane 0 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part1 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part1 to the MMIO space of an IIO target.In the general case, Part1 refers to a x4 PCIe card plugged into the second slot of a PCIe riser card, but it could refer to any x4 device attached to the IIO unit using lanes starting at lane 4 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part2 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part2 to the MMIO space of an IIO target. In the general case, Part2 refers to a x4 or x8 PCIe card plugged into the third slot of a PCIe riser card, but it could refer to any x4 or x8 device attached to the IIO unit and using lanes starting at lane 8 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Peer to peer write request of up to a 64 byte transaction is made by IIO Part3 to an IIO target", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Counts every peer to peer write request of up to a 64 byte transaction of data made by IIO Part3 to the MMIO space of an IIO target. In the general case, Part3 refers to a x4 PCIe card plugged into the fourth slot of a PCIe riser card, but it could brefer to any device attached to the IIO unit using the lanes starting at lane 12 of the 16 lanes supported by the bus.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU; Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.VTD1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Also known as Inbound. Number of 64 byte cache line requests initiated by the attached device.; VTd - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; context cache miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.CTXT_MISS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L1 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L1_MISS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L2 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L2_MISS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; L3 miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L3_MISS", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; Vtd hit", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.L4_PAGE_HIT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB1_MISS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB is full", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Access; TLB miss", - "EventCode": "0x41", - "EventName": "UNC_IIO_VTD_ACCESS.TLB_MISS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "VTd Occupancy", - "EventCode": "0x40", - "EventName": "UNC_IIO_VTD_OCCUPANCY", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Any Source", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy; Snoops", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total IRP occupancy of inbound read and write requests.", - "EventCode": "0xF", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", - "PerPkg": "1", - "PublicDescription": "Total IRP occupancy of inbound read and write requests. This is effectively the sum of read occupancy and write occupancy.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "IRP Clocks", - "EventCode": "0x1", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CLFlush", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; CRd", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; DRd", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.DRD", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIDCAHin5t", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; PCIRdCur", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops; WbMtoI", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF RF full", - "EventCode": "0x17", - "EventName": "UNC_I_FAF_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", - "EventCode": "0x18", - "EventName": "UNC_I_FAF_INSERTS", - "PerPkg": "1", - "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Occupancy of the IRP FAF queue.", - "EventCode": "0x19", - "EventName": "UNC_I_FAF_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF allocation -- sent to ADQ", - "EventCode": "0x16", - "EventName": "UNC_I_FAF_TRANSACTIONS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "All Inserts Inbound (p2p + faf + cset)", - "EventCode": "0x1E", - "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x1E", - "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Rejects", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Requests", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Fastpath Transfers From Primary to Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0; Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 0", - "EventCode": "0x1C", - "EventName": "UNC_I_MISC0.UNKNOWN", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Lost Forward", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Invalid", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Received Valid", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of E Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of I Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of M Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1; Slow Transfer of S Line", - "EventCode": "0x1D", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Requests", - "EventCode": "0x14", - "EventName": "UNC_I_P2P_INSERTS", - "PerPkg": "1", - "PublicDescription": "P2P requests from the ITC", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Occupancy", - "EventCode": "0x15", - "EventName": "UNC_I_P2P_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "P2P B & S Queue Occupancy", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P completions", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if local only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if local and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P Message", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P reads", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; Match if remote only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; match if remote and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions; P2P Writes", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", - "UMask": "0x7e", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", - "UMask": "0x74", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", - "UMask": "0x72", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", - "UMask": "0x78", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that miss the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", - "UMask": "0x71", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit E or S", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit I", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Hit M", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; Miss", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpCode", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpData", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses; SnpInv", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Atomic", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Other", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Read Prefetches", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.RD_PREF", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Reads", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.READS", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count; Writes", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound write (fast path) requests received by the IRP.", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Egress Allocations", - "EventCode": "0xB", - "EventName": "UNC_I_TxC_AK_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Cycles Full", - "EventCode": "0x5", - "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Inserts", - "EventCode": "0x2", - "EventName": "UNC_I_TxC_BL_DRS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Occupancy", - "EventCode": "0x8", - "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Cycles Full", - "EventCode": "0x6", - "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Inserts", - "EventCode": "0x3", - "EventName": "UNC_I_TxC_BL_NCB_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Occupancy", - "EventCode": "0x9", - "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Cycles Full", - "EventCode": "0x7", - "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Inserts", - "EventCode": "0x4", - "EventName": "UNC_I_TxC_BL_NCS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Occupancy", - "EventCode": "0xA", - "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD Egress Credit Stalls", - "EventCode": "0x1A", - "EventName": "UNC_I_TxR2_AD_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x1B", - "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xD", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0xE", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0xC", - "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Traffic in which the M2M to iMC Bypass was not taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_Egress.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts traffic in which the M2M (Mesh to Memory) to iMC (Memory Controller) bypass was not taken", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_Egress.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Not Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass; Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles - at UCLK", - "EventName": "UNC_M2M_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_M2M_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", - "EventCode": "0x24", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "PublicDescription": "Counts cycles when direct to core mode (which bypasses the CHA) was disabled", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to core (bypassing the CHA)", - "EventCode": "0x23", - "EventName": "UNC_M2M_DIRECT2CORE_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to core (bypassing the CHA)", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to core transaction were overridden", - "EventCode": "0x25", - "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", - "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to core transactions (which would have bypassed the CHA) were overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to Intel(R) UPI transactions were overridden", - "EventCode": "0x28", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", - "PerPkg": "1", - "PublicDescription": "Counts reads in which direct to Intel(R) Ultra Path Interconnect (UPI) transactions (which would have bypassed the CHA) were overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to Intel(R) UPI was disabled", - "EventCode": "0x27", - "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the ability to send messages direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was disabled", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages sent direct to the Intel(R) UPI", - "EventCode": "0x26", - "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", - "PerPkg": "1", - "PublicDescription": "Counts when messages were sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA)", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads that a message sent direct2 Intel(R) UPI was overridden", - "EventCode": "0x29", - "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", - "PerPkg": "1", - "PublicDescription": "Counts when a read message that was sent direct to the Intel(R) Ultra Path Interconnect (bypassing the CHA) was overridden", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On NonDirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in A State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in I State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in L State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Hit; On Dirty Line in S State", - "EventCode": "0x2A", - "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in Any State (A, I, S or unused)", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state, and found the cacheline marked in the A (SnoopAll) state, indicating the cacheline is stored in another socket in any state, and we must snoop the other sockets to make sure we get the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the I (Invalid) state indicating the cacheline is not stored in another socket, and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", - "EventCode": "0x2D", - "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) looks into the multi-socket cacheline Directory state , and found the cacheline marked in the S (Shared) state indicating the cacheline is either stored in another socket in the S(hared) state , and so there is no need to snoop the other sockets for the latest data. The data may be stored in any state in the local socket.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On NonDirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in A State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in I State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in L State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Directory Miss; On Dirty Line in S State", - "EventCode": "0x2B", - "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to I", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to I (Invalid)", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from A to S", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from A (SnoopAll) to S (Shared)", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory to a new state", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to A", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to A (SnoopAll)", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from I to S", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from I (Invalid) to S (Shared)", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to A", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to A (SnoopAll)", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Multi-socket cacheline Directory update from S to I", - "EventCode": "0x2E", - "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) updates the multi-socket cacheline Directory state from S (Shared) to I (Invalid)", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_M2M_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_M2M_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Reads to iMC issued", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ALL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller).", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC; All, regardless of priority.", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.FROM_TRANSGRESS", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC; Critical Priority", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ISOCH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Reads to iMC issued at Normal Priority (Non-Isochronous)", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues reads to the iMC (Memory Controller). It only counts normal priority non-isochronous reads.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Writes to iMC issued", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.ALL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues writes to the iMC (Memory Controller).", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FROM_TRANSGRESS", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; Full Line Non-ISOCH", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; ISOCH Full Line", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; All, regardless of priority.", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.NI", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Partial Non-Isochronous writes to the iMC", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) issues partial writes to the iMC (Memory Controller). It only counts normal priority non-isochronous writes.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC; ISOCH Partial", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches; MC Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches; Mesh Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MESH", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full", - "EventCode": "0x53", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty", - "EventCode": "0x54", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch requests that got turn into a demand request", - "EventCode": "0x56", - "EventName": "UNC_M2M_PREFCAM_DEMAND_PROMOTIONS", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) promotes a outstanding request in the prefetch queue due to a subsequent demand read request that entered the M2M with the same address. Explanatory Side Note: The Prefetch queue is made of CAM (Content Addressable Memory)", - "Unit": "M2M" - }, - { - "BriefDescription": "Inserts into the Memory Controller Prefetch Queue", - "EventCode": "0x57", - "EventName": "UNC_M2M_PREFCAM_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_M2M_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", - "Deprecated": "1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_NO_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 0", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special; Channel 2", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_CYCLES_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Full", - "EventCode": "0x4", - "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Not Empty", - "EventCode": "0x3", - "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Queue Inserts", - "EventCode": "0x1", - "EventName": "UNC_M2M_RxC_AD_INSERTS", - "PerPkg": "1", - "PublicDescription": "Counts when the a new entry is Received(RxC) and then added to the AD (Address Ring) Ingress Queue from the CMS (Common Mesh Stop). This is generally used for reads, and", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy", - "EventCode": "0x2", - "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Full", - "EventCode": "0x8", - "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Not Empty", - "EventCode": "0x7", - "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Allocations", - "EventCode": "0x5", - "EventName": "UNC_M2M_RxC_BL_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Occupancy", - "EventCode": "0x6", - "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M2M_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M2M_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Number AD Ingress Credits", - "EventCode": "0x41", - "EventName": "UNC_M2M_TGR_AD_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number BL Ingress Credits", - "EventCode": "0x42", - "EventName": "UNC_M2M_TGR_BL_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 0", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 1", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full; Channel 2", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_CYCLES_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 0", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 1", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty; Channel 2", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_CYCLES_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 0", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 1", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts; Channel 2", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 0", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 1", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy; Channel 2", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Pending Occupancy", - "EventCode": "0x48", - "EventName": "UNC_M2M_TRACKER_PENDING_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credit Acquired", - "EventCode": "0xD", - "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credits Occupancy", - "EventCode": "0xE", - "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Full", - "EventCode": "0xC", - "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Not Empty", - "EventCode": "0xB", - "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Allocations", - "EventCode": "0x9", - "EventName": "UNC_M2M_TxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", - "EventCode": "0xF", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", - "EventCode": "0x10", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Occupancy", - "EventCode": "0xA", - "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK; CRD Transactions to Cbo", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.CRD_CBO", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK; NDR Transactions", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.NDR", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x1E", - "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x1E", - "EventName": "UNC_M2M_TxC_AK_CREDIT_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; All", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Near Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Common Mesh Stop - Far Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Read Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Compare Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full; Write Credit Request", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; All", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Read Credit Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Write Compare Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty; Write Credit Request", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; All", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Near Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Common Mesh Stop - Far Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Prefetch Read Cam Hit", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Read Credit Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Write Compare Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations; Write Credit Request", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; All", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Read Credit Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Write Compare Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy; Write Credit Request", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Sideband", - "EventCode": "0x6B", - "EventName": "UNC_M2M_TxC_AK_SIDEBAND.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Sideband", - "EventCode": "0x6B", - "EventName": "UNC_M2M_TxC_AK_SIDEBAND.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Cache", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to Core", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache; Data to QPI", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_UPI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Near Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired; Common Mesh Stop - Far Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x1A", - "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credits Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x1A", - "EventName": "UNC_M2M_TxC_BL_CREDIT_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; All", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Near Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full; Common Mesh Stop - Far Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; All", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Near Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty; Common Mesh Stop - Far Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; All", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Near Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations; Common Mesh Stop - Far Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Near Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits; Common Mesh Stop - Far Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; All", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Near Side", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Occupancy; Common Mesh Stop - Far Side", - "EventCode": "0x16", - "EventName": "UNC_M2M_TxC_BL_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", - "Deprecated": "1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_NO_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 0", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular; Channel 2", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_CYCLES_REG_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 0", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 1", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special; Channel 2", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_CYCLES_SPEC_CREDITS.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 0", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 1", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full; Channel 2", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_FULL.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 0", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 1", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty; Channel 2", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WRITE_TRACKER_CYCLES_NE.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 0", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 1", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts; Channel 2", - "EventCode": "0x61", - "EventName": "UNC_M2M_WRITE_TRACKER_INSERTS.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 0", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 1", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy; Channel 2", - "EventCode": "0x60", - "EventName": "UNC_M2M_WRITE_TRACKER_OCCUPANCY.CH2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired; For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M3UPI_AG0_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M3UPI_AG0_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired; For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M3UPI_AG0_BL_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M3UPI_AG0_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired; For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M3UPI_AG1_AD_CRD_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy; For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M3UPI_AG1_AD_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy; For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M3UPI_AG1_BL_CRD_OCCUPANCY.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired; For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M3UPI_AG1_BL_CREDITS_ACQUIRED.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Requests", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Snoops", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; VNA Messages", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CBox AD Credits Empty; Writebacks", - "EventCode": "0x22", - "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of uclks in domain", - "EventCode": "0x1", - "EventName": "UNC_M3UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts the number of uclks in the M3 uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the M3 is close to the Ubox, they generally should not diverge by more than a handful of cycles.", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xC0", - "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2C Sent", - "EventCode": "0x2B", - "EventName": "UNC_M3UPI_D2C_SENT", - "PerPkg": "1", - "PublicDescription": "Count cases BL sends direct to core", - "Unit": "M3UPI" - }, - { - "BriefDescription": "D2U Sent", - "EventCode": "0x2A", - "EventName": "UNC_M3UPI_D2U_SENT", - "PerPkg": "1", - "PublicDescription": "Cases where SMI3 sends D2U command", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Down", - "EventCode": "0xAE", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements; Up", - "EventCode": "0xAE", - "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FaST wire asserted; Horizontal", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_FAST_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "FaST wire asserted; Vertical", - "EventCode": "0xA5", - "EventName": "UNC_M3UPI_FAST_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles either the local or incoming distress signals are asserted. Incoming distress includes up, dn and across.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Even", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Left and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Even", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AD Ring In Use; Right and Odd", - "EventCode": "0xA7", - "EventName": "UNC_M3UPI_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Even", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Left and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Even", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal AK Ring In Use; Right and Odd", - "EventCode": "0xA9", - "EventName": "UNC_M3UPI_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Even", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Left and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Even", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal BL Ring in Use; Right and Odd", - "EventCode": "0xAB", - "EventName": "UNC_M3UPI_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Left", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Horizontal IV Ring in Use; Right", - "EventCode": "0xAD", - "EventName": "UNC_M3UPI_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO0_IIO1_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO2", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO3", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO4", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; IIO5", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; All IIO targets for NCS are in single mask. ORs them together", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "M2 BL Credits Empty; Selected M2p BL NCS credits", - "EventCode": "0x23", - "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", - "PerPkg": "1", - "PublicDescription": "No vn0 and vna credits available to send to M2", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 1", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AD - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AK - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; AK - Slot 2", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Multi Slot Flit Received; BL - Slot 0", - "EventCode": "0x3E", - "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", - "PerPkg": "1", - "PublicDescription": "Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AD", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; AK", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; BL", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring.; IV", - "EventCode": "0xA1", - "EventName": "UNC_M3UPI_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; AD", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Acknowledgements to core", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Data Responses to core", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.; Snoops of processor's cache.", - "EventCode": "0xA0", - "EventName": "UNC_M3UPI_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AD", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; AK", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; Acknowledgements to Agent 1", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; BL", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring; IV", - "EventCode": "0xA3", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; AD", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Acknowledgements to core", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Data Responses to core", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring; Snoops of processor's cache.", - "EventCode": "0xA2", - "EventName": "UNC_M3UPI_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xA4", - "EventName": "UNC_M3UPI_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; REQ on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; RSP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; SNP on AD", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; NCB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; NCS on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; RSP on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN0; WB on BL", - "EventCode": "0x4B", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; REQ on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; RSP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; SNP on AD", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; NCB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; NCS on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; RSP on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Lost Arb for VN1; WB on BL", - "EventCode": "0x4C", - "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message requested but lost arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; AD, BL Parallel Win", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN", - "PerPkg": "1", - "PublicDescription": "AD and BL messages won arbitration concurrently / in parallel", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending AD VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; No Progress on Pending BL VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", - "PerPkg": "1", - "PublicDescription": "Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN0", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN0", - "PerPkg": "1", - "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn0, delaying vn1 win, because vn0 offered parallel ad/bl", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Arb Miscellaneous; Parallel Bias to VN1", - "EventCode": "0x4D", - "EventName": "UNC_M3UPI_RxC_ARB_MISC.PAR_BIAS_VN1", - "PerPkg": "1", - "PublicDescription": "VN0/VN1 arbiter gave second, consecutive win to vn1, delaying vn0 win, because vn1 offered parallel ad/bl", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; REQ on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; RSP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; SNP on AD", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; NCB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; NCS on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; RSP on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN0; WB on BL", - "EventCode": "0x49", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; REQ on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; RSP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; SNP on AD", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; NCB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; NCS on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; RSP on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Can't Arb for VN1; WB on BL", - "EventCode": "0x4A", - "EventName": "UNC_M3UPI_RxC_ARB_NOAD_REQ_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message was not able to request arbitration while some other message won arbitration; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; REQ on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; RSP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; SNP on AD", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; NCB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; NCS on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; RSP on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN0; WB on BL", - "EventCode": "0x47", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN0 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; REQ on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; RSP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; SNP on AD", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; NCB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; NCS on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; RSP on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "No Credits to Arb for VN1; WB on BL", - "EventCode": "0x48", - "EventName": "UNC_M3UPI_RxC_ARB_NOCRED_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "VN1 message is blocked from requesting arbitration due to lack of remote UPI credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on BL Arb", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD to Slot 0 on Idle", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to slot 0 of independent flit while pipeline is idle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 1", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 1 while merging with bl message in same flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Ingress Queue Bypasses; AD + BL to Slot 2", - "EventCode": "0x40", - "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", - "PerPkg": "1", - "PublicDescription": "Number of times message is bypassed around the Ingress Queue; AD is taking bypass to flit slot 2 while merging with bl message in same flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; REQ on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; RSP on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; SNP on AD", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; NCB on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; NCS on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; RSP on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message lost contest for flit; WB on BL", - "EventCode": "0x50", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN0 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; REQ on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; RSP on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; SNP on AD", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; NCB on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; NCS on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; RSP on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message lost contest for flit; WB on BL", - "EventCode": "0x51", - "EventName": "UNC_M3UPI_RxC_COLLISION_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress VN1 packets lost the contest for Flit Slot 0.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; Any In BGF FIFO", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", - "PerPkg": "1", - "PublicDescription": "Indication that at least one packet (flit) is in the bgf (fifo only)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; Any in BGF Path", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", - "PerPkg": "1", - "PublicDescription": "Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Miscellaneous Credit Events; No D2K For Arb", - "EventCode": "0x60", - "EventName": "UNC_M3UPI_RxC_CRD_MISC.NO_D2K_FOR_ARB", - "PerPkg": "1", - "PublicDescription": "VN0 or VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; D2K Credits", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", - "PerPkg": "1", - "PublicDescription": "D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Packets in BGF FIFO", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", - "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Packets in BGF Path", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", - "PerPkg": "1", - "PublicDescription": "Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", - "PerPkg": "1", - "PublicDescription": "count of bl messages in pump-1-pending state, in completion fifo only", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", - "PerPkg": "1", - "PublicDescription": "count of bl messages in pump-1-pending state, in marker table and in fifo", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; Transmit Credits", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", - "PerPkg": "1", - "PublicDescription": "Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Credit Occupancy; VNA In Use", - "EventCode": "0x61", - "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", - "PerPkg": "1", - "PublicDescription": "Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", - "EventCode": "0x43", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; REQ on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; SNP on AD", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; NCS on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; RSP on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Cycles Not Empty; WB on BL", - "EventCode": "0x44", - "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; All", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; No BGF Credits", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_BGF", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Data Flit Not Sent; No TxQ Credits", - "EventCode": "0x57", - "EventName": "UNC_M3UPI_RxC_FLITS_DATA_NOT_SENT.NO_TXQ", - "PerPkg": "1", - "PublicDescription": "Data flit is ready for transmission but could not be sent", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 0", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "generating bl data flit sequence; waiting for data pump 0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is tracking at least one message", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", - "PerPkg": "1", - "PublicDescription": "pump-1-pending completion fifo is full", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", - "PerPkg": "1", - "PublicDescription": "pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", - "PerPkg": "1", - "PublicDescription": "a bl message finished but is in limbo and moved to pump-1-pending logic", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Generating BL Data Flit Sequence; Wait on Pump 1", - "EventCode": "0x59", - "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "generating bl data flit sequence; waiting for data pump 1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC", - "EventCode": "0x5A", - "EventName": "UNC_M3UPI_RxC_FLITS_MISC", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; One Message", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG", - "PerPkg": "1", - "PublicDescription": "One message in flit; VNA or non-VNA flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; One Message in non-VNA", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.1_MSG_VNX", - "PerPkg": "1", - "PublicDescription": "One message in flit; non-VNA flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; Two Messages", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.2_MSGS", - "PerPkg": "1", - "PublicDescription": "Two messages in flit; VNA flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit; Three Messages", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.3_MSGS", - "PerPkg": "1", - "PublicDescription": "Three messages in flit; VNA flit", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_1", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_2", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Sent Header Flit", - "EventCode": "0x56", - "EventName": "UNC_M3UPI_RxC_FLITS_SENT.SLOTS_3", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; All", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Needs Data Flit", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", - "PerPkg": "1", - "PublicDescription": "BL message requires data flit sequence", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 0", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", - "PerPkg": "1", - "PublicDescription": "Waiting for header pump 0", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Bubble", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit but flit transmission delayed", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Don't Need Pump 1 - Not Avail", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", - "PerPkg": "1", - "PublicDescription": "Header pump 1 is not required for flit and not available", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Slotting BL Message Into Header Flit; Wait on Pump 1", - "EventCode": "0x58", - "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", - "PerPkg": "1", - "PublicDescription": "Waiting for header pump 1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate Ready", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Accumulate Wasted", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Blocked", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Run-Ahead - Message", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit slotting is in run-ahead to start new flit, and message is actually slotted into new flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Ok", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; New header flit construction may proceed in parallel with data flit sequence", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Flit Finished", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_FLIT", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Header flit finished assembly in parallel with data flit sequence", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 1; Parallel Message", - "EventCode": "0x53", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.PAR_MSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 1; Message is slotted into header flit in parallel with data flit sequence", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate-matching stall injected", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Flit Gen - Header 2; Rate-matching Stall - No Message", - "EventCode": "0x54", - "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", - "PerPkg": "1", - "PublicDescription": "Events related to Header Flit Generation - Set 2; Rate matching stall injected, but no additional message slotted during stall cycle", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; All", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No BGF Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_CRD", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No BGF Credits + No Extra Message Slotted", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_BGF_NO_MSG", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No BGF credits available; no additional message slotted into flit", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No TxQ Credits", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_CRD", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; No TxQ Credits + No Extra Message Slotted", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.NO_TXQ_NO_MSG", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; No TxQ credits available; no additional message slotted into flit", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - One Slot Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.ONE_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only one slot taken (two slots free)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - Three Slots Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.THREE_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with three slots taken (no slots free)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Header Not Sent; Sent - Two Slots Taken", - "EventCode": "0x55", - "EventName": "UNC_M3UPI_RxC_FLIT_NOT_SENT.TWO_TAKEN", - "PerPkg": "1", - "PublicDescription": "header flit is ready for transmission but could not be sent; sending header flit with only two slots taken (one slots free)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Can't Slot AD", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", - "PerPkg": "1", - "PublicDescription": "some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Can't Slot BL", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", - "PerPkg": "1", - "PublicDescription": "some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel AD Lost", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_AD_LOST", - "PerPkg": "1", - "PublicDescription": "some AD message lost contest for slot 0 (logical OR of all AD events under INGR_SLOT_LOST_MC_VN{0,1})", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel Attempt", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", - "PerPkg": "1", - "PublicDescription": "ad and bl messages attempted to slot into the same flit in parallel", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel BL Lost", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_BL_LOST", - "PerPkg": "1", - "PublicDescription": "some BL message lost contest for slot 0 (logical OR of all BL events under INGR_SLOT_LOST_MC_VN{0,1})", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; Parallel Success", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", - "PerPkg": "1", - "PublicDescription": "ad and bl messages were actually slotted into the same flit in paralle", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; VN0", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.VN0", - "PerPkg": "1", - "PublicDescription": "vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Message Held; VN1", - "EventCode": "0x52", - "EventName": "UNC_M3UPI_RxC_HELD.VN1", - "PerPkg": "1", - "PublicDescription": "vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; REQ on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; SNP on AD", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; NCS on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; RSP on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Inserts; WB on BL", - "EventCode": "0x41", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; REQ on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; SNP on AD", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; NCS on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; RSP on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Inserts; WB on BL", - "EventCode": "0x42", - "EventName": "UNC_M3UPI_RxC_INSERTS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the UPI VN1 Ingress. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI VN1 Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; REQ on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; SNP on AD", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; NCS on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; RSP on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Ingress (from CMS) Queue - Occupancy; WB on BL", - "EventCode": "0x45", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; REQ on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; SNP on AD", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; NCS on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; RSP on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Ingress (from CMS) Queue - Occupancy; WB on BL", - "EventCode": "0x46", - "EventName": "UNC_M3UPI_RxC_OCCUPANCY_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of a given UPI VN1 Ingress queue in each cycle. This tracks one of the three ring Ingress buffers. This can be used with the UPI VN1 Ingress Not Empty event to calculate average occupancy or the UPI VN1 Ingress Allocations event in order to calculate average queuing latency.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; REQ on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; RSP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; SNP on AD", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; NCB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; NCS on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; RSP on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 message can't slot into flit; WB on BL", - "EventCode": "0x4E", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; REQ on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; RSP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; SNP on AD", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; NCB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; NCS on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Non-Coherent Standard (NCS) messages on BL.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; RSP on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 message can't slot into flit; WB on BL", - "EventCode": "0x4F", - "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", - "PerPkg": "1", - "PublicDescription": "Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Lost Arbitration", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARB_LOST", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Arrived", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.ARRIVED", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Dropped - Old", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_OLD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Dropped - Wrap", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.DROP_WRAP", - "PerPkg": "1", - "PublicDescription": "Dropped because it was overwritten by new message while prefetch queue was full", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "SMI3 Prefetch Messages; Slotted", - "EventCode": "0x62", - "EventName": "UNC_M3UPI_RxC_SMI3_PFTCH.SLOTTED", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Any In Use", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", - "PerPkg": "1", - "PublicDescription": "At least one remote vna credit is in use", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Corrected", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", - "PerPkg": "1", - "PublicDescription": "Number of remote vna credits corrected (local return) per cycle", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 1", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 1 (i.e. no vna credits available)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 4", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Level < 5", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", - "PerPkg": "1", - "PublicDescription": "Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Remote VNA Credits; Used", - "EventCode": "0x5B", - "EventName": "UNC_M3UPI_RxC_VNA_CRD.USED", - "PerPkg": "1", - "PublicDescription": "Number of remote vna credits consumed per cycle", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB4", - "EventName": "UNC_M3UPI_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AD - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; AK - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; BL - Credit", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Bypass; IV - Bounce", - "EventCode": "0xB2", - "EventName": "UNC_M3UPI_RxR_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AD - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; AK - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; BL - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; IFV - Credit", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Injection Starvation; IV - Bounce", - "EventCode": "0xB3", - "EventName": "UNC_M3UPI_RxR_CRD_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AD - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; AK - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; BL - Credit", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Allocations; IV - Bounce", - "EventCode": "0xB1", - "EventName": "UNC_M3UPI_RxR_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AD - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; AK - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; BL - Credit", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Transgress Ingress Occupancy; IV - Bounce", - "EventCode": "0xB0", - "EventName": "UNC_M3UPI_RxR_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits; For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits; For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M3UPI_STALL_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN0 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 REQ Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 RSP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 SNP Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for AD; VN1 WB Messages", - "EventCode": "0x30", - "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD FlowQ Bypass", - "EventCode": "0x2C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", - "PerPkg": "1", - "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN0 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 REQ Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 RSP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 SNP Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Not Empty; VN1 WB Messages", - "EventCode": "0x27", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the AD Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN0 WB Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 REQ Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 RSP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Inserts; VN1 SNP Messages", - "EventCode": "0x2D", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN0 WB Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 REQ Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 RSP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AD Flow Q Occupancy; VN1 SNP Messages", - "EventCode": "0x1C", - "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; CHA on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_CHA", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to CHA", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_NON_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn0 Snpf", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI0", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN0", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN0_PEER_UPI1", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN0 Snpf to peer UPI1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; CHA on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_CHA", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to CHA", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Non Idle cycles on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_NON_IDLE", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of non-idle cycles in issuing Vn1 Snpf", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI0 on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI0", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI0", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Number of Snoop Targets; Peer UPI1 on VN1", - "EventCode": "0x3C", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP1_VN1.VN1_PEER_UPI1", - "PerPkg": "1", - "PublicDescription": "Number of snpfanout targets and non-idle cycles can be used to calculate average snpfanout latency; Number of VN1 Snpf to peer UPI1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_NONSNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn0", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN0_SNPFP_VN2SNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn0 SnpF issued when SnpF pending on Vn1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_NONSNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ txn issued when SnpF pending on Vn1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Snoop Arbitration; FlowQ SnpF Won", - "EventCode": "0x3D", - "EventName": "UNC_M3UPI_TxC_AD_SNPF_GRP2_VN1.VN1_SNPFP_VN0SNP", - "PerPkg": "1", - "PublicDescription": "Outcome of SnpF pending arbitration; FlowQ Vn1 SnpF issued when SnpF pending on Vn0", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 REQ Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 SNP Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN0 WB Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 REQ Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 SNP Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - Credit Available; VN1 WB Messages", - "EventCode": "0x34", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_CRD_AVAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request with prior cycle credit check complete and credit avail", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 REQ Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 SNP Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN0 WB Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 REQ Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 SNP Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - New Message; VN1 WB Messages", - "EventCode": "0x33", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NEW_MSG.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 REQ Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 RSP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 SNP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN0 WB Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN0_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 REQ Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 RSP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 SNP Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD - No Credit; VN1 WB Messages", - "EventCode": "0x32", - "EventName": "UNC_M3UPI_TxC_AD_SPEC_ARB_NO_OTHER_PEND.VN1_WB", - "PerPkg": "1", - "PublicDescription": "AD speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Inserts", - "EventCode": "0x2F", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "AK Flow Q Occupancy", - "EventCode": "0x1E", - "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", - "PerPkg": "1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN0 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 NCS Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 NCB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 RSP Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Failed ARB for BL; VN1 WB Messages", - "EventCode": "0x35", - "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL arb but no win; arb request asserted but not won", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN0 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 REQ Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 RSP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 SNP Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Not Empty; VN1 WB Messages", - "EventCode": "0x28", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Number of cycles the BL Egress queue is Not Empty", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN0 NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1 RSP Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1 WB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1_NCB Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Inserts; VN1_NCS Messages", - "EventCode": "0x2E", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", - "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN0 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1_NCS Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1_NCB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1 RSP Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "BL Flow Q Occupancy; VN1 WB Messages", - "EventCode": "0x1D", - "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 NCS Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN0 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 WB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 NCB Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for BL - New Message; VN1 RSP Messages", - "EventCode": "0x38", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NEW_MSG.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request due to new message arriving on a specific channel (MC/VN)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 NCS Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 RSP Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN0 WB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN0_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCS Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 NCB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_NCS", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x80", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 RSP Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Speculative ARB for AD Failed - No Credit; VN1 WB Messages", - "EventCode": "0x37", - "EventName": "UNC_M3UPI_TxC_BL_SPEC_ARB_NO_OTHER_PEND.VN1_WB", - "PerPkg": "1", - "PublicDescription": "BL speculative arb request asserted due to no other channel being active (have a valid entry but don't have credits to send)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AD - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; AK - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Bounce", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal ADS Used; BL - Credit", - "EventCode": "0x9D", - "EventName": "UNC_M3UPI_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AD - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; AK - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; BL - Credit", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used; IV - Bounce", - "EventCode": "0x9F", - "EventName": "UNC_M3UPI_TxR_HORZ_BYPASS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AD - Credit", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; AK - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; BL - Credit", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full; IV - Bounce", - "EventCode": "0x96", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_FULL.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AD - Credit", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; AK - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; BL - Credit", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty; IV - Bounce", - "EventCode": "0x97", - "EventName": "UNC_M3UPI_TxR_HORZ_CYCLES_NE.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AD - Credit", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; AK - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; BL - Credit", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts; IV - Bounce", - "EventCode": "0x95", - "EventName": "UNC_M3UPI_TxR_HORZ_INSERTS.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AD - Credit", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; AK - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; BL - Credit", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs; IV - Bounce", - "EventCode": "0x99", - "EventName": "UNC_M3UPI_TxR_HORZ_NACK.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AD - Credit", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; AK - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; BL - Credit", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy; IV - Bounce", - "EventCode": "0x94", - "EventName": "UNC_M3UPI_TxR_HORZ_OCCUPANCY.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AD - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AD_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; AK - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.AK_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; BL - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.BL_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation; IV - Bounce", - "EventCode": "0x9B", - "EventName": "UNC_M3UPI_TxR_HORZ_STARVED.IV_BNC", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M3UPI_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AD - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; AK - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; BL - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical ADS Used; IV", - "EventCode": "0x9E", - "EventName": "UNC_M3UPI_TxR_VERT_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full; IV", - "EventCode": "0x92", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AD - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; AK - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; BL - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty; IV", - "EventCode": "0x93", - "EventName": "UNC_M3UPI_TxR_VERT_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AD - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; AK - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; BL - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Allocations; IV", - "EventCode": "0x91", - "EventName": "UNC_M3UPI_TxR_VERT_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs; IV", - "EventCode": "0x98", - "EventName": "UNC_M3UPI_TxR_VERT_NACK.IV", - "PerPkg": "1", - "PublicDescription": "Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy; IV", - "EventCode": "0x90", - "EventName": "UNC_M3UPI_TxR_VERT_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh.; Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation; IV", - "EventCode": "0x9A", - "EventName": "UNC_M3UPI_TxR_VERT_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN0 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 REQ Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 RSP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VN1 SNP Messages", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 AD Credits Empty; VNA", - "EventCode": "0x20", - "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPIs on the AD Ring", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN0 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 RSP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 REQ Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VN1 SNP Messages", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x40", - "Unit": "M3UPI" - }, - { - "BriefDescription": "UPI0 BL Credits Empty; VNA", - "EventCode": "0x21", - "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", - "PerPkg": "1", - "PublicDescription": "No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Prefetches generated by the flow control queue of the M3UPI unit.", - "EventCode": "0x29", - "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", - "PerPkg": "1", - "PublicDescription": "Count cases where flow control queue that sits between the Intel(R) Ultra Path Interconnect (UPI) and the mesh spawns a prefetch to the iMC (Memory Controller)", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Even", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Down and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Even", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AD Ring In Use; Up and Odd", - "EventCode": "0xA6", - "EventName": "UNC_M3UPI_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Even", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Down and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Even", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical AK Ring In Use; Up and Odd", - "EventCode": "0xA8", - "EventName": "UNC_M3UPI_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Even", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Down and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Even", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical BL Ring in Use; Up and Odd", - "EventCode": "0xAA", - "EventName": "UNC_M3UPI_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Down", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "Vertical IV Ring in Use; Up", - "EventCode": "0xAC", - "EventName": "UNC_M3UPI_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; WB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; NCB on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; REQ on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; RSP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; SNP on AD", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 Credit Used; RSP on BL", - "EventCode": "0x5C", - "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; WB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; NCB on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; REQ on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; RSP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; SNP on AD", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN0 No Credits; RSP on BL", - "EventCode": "0x5E", - "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN0 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; WB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; NCB on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; REQ on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; RSP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; SNP on AD", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 Credit Used; RSP on BL", - "EventCode": "0x5D", - "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", - "PerPkg": "1", - "PublicDescription": "Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; WB on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", - "UMask": "0x10", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; NCB on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", - "UMask": "0x20", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; REQ on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", - "UMask": "0x1", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; RSP on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x4", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; SNP on AD", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", - "UMask": "0x2", - "Unit": "M3UPI" - }, - { - "BriefDescription": "VN1 No Credits; RSP on BL", - "EventCode": "0x5F", - "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", - "PerPkg": "1", - "PublicDescription": "Number of Cycles there were no VN1 Credits; Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", - "UMask": "0x8", - "Unit": "M3UPI" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_M2M_TxC_BL.DRS_UPI", - "Deprecated": "1", - "EventCode": "0x40", - "EventName": "UNC_NoUnit_TxC_BL.DRS_UPI", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Clocks of the Intel(R) Ultra Path Interconnect (UPI)", - "EventCode": "0x1", - "EventName": "UNC_UPI_CLOCKTICKS", - "PerPkg": "1", - "PublicDescription": "Counts clockticks of the fixed frequency clock controlling the Intel(R) Ultra Path Interconnect (UPI). This clock runs at1/8th the 'GT/s' speed of the UPI link. For example, a 9.6GT/s link will have a fixed Frequency of 1.2 Ghz.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Data Response packets that go direct to core", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", - "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to core bypassing the CHA.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_DIRECT_ATTEMPTS.D2U", - "Deprecated": "1", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Data Response packets that go direct to Intel(R) UPI", - "EventCode": "0x12", - "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2U", - "PerPkg": "1", - "PublicDescription": "Counts Data Response (DRS) packets that attempted to go direct to Intel(R) Ultra Path Interconnect (UPI) bypassing the CHA .", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "EventCode": "0x18", - "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles Intel(R) UPI is in L1 power mode (shutdown)", - "EventCode": "0x21", - "EventName": "UNC_UPI_L1_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the Intel(R) Ultra Path Interconnect (UPI) is in L1 power mode. L1 is a mode that totally shuts down the UPI link. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another, this event only coutns when both links are shutdown.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "EventCode": "0x14", - "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "EventCode": "0x16", - "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "EventCode": "0x15", - "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", - "EventCode": "0x20", - "EventName": "UNC_UPI_PHY_INIT_CYCLES", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req Nack", - "EventCode": "0x23", - "EventName": "UNC_UPI_POWER_L1_NACK", - "PerPkg": "1", - "PublicDescription": "Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "L1 Req (same as L1 Ack).", - "EventCode": "0x22", - "EventName": "UNC_UPI_POWER_L1_REQ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "EventCode": "0x46", - "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles the Rx of the Intel(R) UPI is in L0p power mode", - "EventCode": "0x25", - "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the receive side (Rx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0. Receive side.", - "EventCode": "0x24", - "EventName": "UNC_UPI_RxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Request", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "REQ Message Class", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Request Opcode", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Conflict", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Invalid", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Response - No Data", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Snoop", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "SNP Message Class", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Snoop Opcode", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Receive path of a UPI Port; Writeback", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer", - "EventCode": "0x31", - "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "CRC Errors Detected", - "EventCode": "0xB", - "EventName": "UNC_UPI_RxL_CRC_ERRORS", - "PerPkg": "1", - "PublicDescription": "Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", - "Unit": "UPI LL" - }, - { - "BriefDescription": "LLR Requests Sent", - "EventCode": "0x8", - "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", - "PerPkg": "1", - "PublicDescription": "Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN0 Credit Consumed", - "EventCode": "0x39", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VN1 Credit Consumed", - "EventCode": "0x3A", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credit Consumed", - "EventCode": "0x38", - "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", - "PerPkg": "1", - "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid data FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Null FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) received from any of the 3 Intel(R) Ultra Path Interconnect (UPI) Receive Queue slots on this UPI unit.", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Data", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Idle", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; LLCRD Not Empty", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; LLCTRL", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Protocol header and credit FLITs received from any slot", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) received from any of the 3 UPI slots on this UPI unit.", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.ALL_NULL", - "Deprecated": "1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.NULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Protocol Header", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_FLITS.PROTHDR", - "Deprecated": "1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.PROT_HDR", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 0", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 1", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Received; Slot 2", - "EventCode": "0x3", - "EventName": "UNC_UPI_RxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.NCB", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.NCS", - "PerPkg": "1", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.REQ", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.REQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.RSP", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.SNP", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.SNP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_RxL_BASIC_HDR_MATCH.WB", - "Deprecated": "1", - "EventCode": "0x5", - "EventName": "UNC_UPI_RxL_HDR_MATCH.WB", - "PerPkg": "1", - "UMask": "0xb", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 0", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 1", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Flit Buffer Allocations; Slot 2", - "EventCode": "0x30", - "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 0", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 1", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "RxQ Occupancy - All Packets; Slot 2", - "EventCode": "0x32", - "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "EventCode": "0x33", - "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "EventCode": "0x2A", - "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in which the Tx of the Intel(R) Ultra Path Interconnect (UPI) is in L0p power mode", - "EventCode": "0x27", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Counts cycles when the transmit side (Tx) of the Intel(R) Ultra Path Interconnect(UPI) is in L0p power mode. L0p is a mode where we disable 60% of the UPI lanes, decreasing our bandwidth in order to save power.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "EventCode": "0x28", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "EventCode": "0x29", - "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Cycles in L0. Transmit side.", - "EventCode": "0x26", - "EventName": "UNC_UPI_TxL0_POWER_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Bypass", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCB", - "UMask": "0x10e", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Non-Coherent Standard", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - NCS", - "UMask": "0x10f", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Request", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", - "PerPkg": "1", - "PublicDescription": "REQ Message Class", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Request Opcode", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC", - "PerPkg": "1", - "PublicDescription": "Match REQ Opcodes - Specified in Umask[7:4]", - "UMask": "0x108", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Conflict", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT", - "PerPkg": "1", - "UMask": "0x1aa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Invalid", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI", - "PerPkg": "1", - "UMask": "0x12a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10c", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Response - No Data", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class - RSP", - "UMask": "0x10a", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", - "PerPkg": "1", - "PublicDescription": "SNP Message Class", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Snoop Opcode", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC", - "PerPkg": "1", - "PublicDescription": "Match SNP Opcodes - Specified in Umask[7:4]", - "UMask": "0x109", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0xd", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Matches on Transmit path of a UPI Port; Writeback", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC", - "PerPkg": "1", - "PublicDescription": "Match Message Class -WB", - "UMask": "0x10d", - "Unit": "UPI LL" - }, - { - "BriefDescription": "FLITs that bypassed the TxL Buffer", - "EventCode": "0x41", - "EventName": "UNC_UPI_TxL_BYPASSED", - "PerPkg": "1", - "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the TxL(transmit) FLIT buffer and pass directly out the UPI Link. Generally, when data is transmitted across the Intel(R) Ultra Path Interconnect (UPI), it will bypass the TxQ and pass directly to the link. However, the TxQ will be used in L0p (Low Power) mode and (Link Layer Retry) LLR mode, increasing latency to transfer out to the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid data FLITs transmitted via any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Null FLITs transmitted from any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", - "PerPkg": "1", - "PublicDescription": "Counts null FLITs (80 bit FLow control unITs) transmitted via any of the 3 Intel(R) Ulra Path Interconnect (UPI) slots on this UPI unit.", - "UMask": "0x27", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Data", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.DATA", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Idle FLITs transmitted", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.IDLE", - "PerPkg": "1", - "PublicDescription": "Counts when the Intel Ultra Path Interconnect(UPI) transmits an idle FLIT(80 bit FLow control unITs). Every UPI cycle must be sending either data FLITs, protocol/credit FLITs or idle FLITs.", - "UMask": "0x47", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; LLCRD Not Empty", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.LLCRD", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", - "UMask": "0x10", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; LLCTRL", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", - "UMask": "0x40", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Protocol header and credit FLITs transmitted across any slot", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", - "PerPkg": "1", - "PublicDescription": "Counts protocol header and credit FLITs (80 bit FLow control unITs) transmitted across any of the 3 UPI (Ultra Path Interconnect) slots on this UPI unit.", - "UMask": "0x97", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.ALL_NULL", - "Deprecated": "1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.NULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Protocol Header", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_FLITS.PROTHDR", - "Deprecated": "1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.PROT_HDR", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 0", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT0", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 0 - Other mask bits determine types of headers to count.", - "UMask": "0x1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 1", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT1", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 1 - Other mask bits determine types of headers to count.", - "UMask": "0x2", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Valid Flits Sent; Slot 2", - "EventCode": "0x2", - "EventName": "UNC_UPI_TxL_FLITS.SLOT2", - "PerPkg": "1", - "PublicDescription": "Shows legal flit time (hides impact of L0p and L0c).; Count Slot 2 - Other mask bits determine types of headers to count.", - "UMask": "0x4", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.DATA_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.DUAL_SLOT_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.LOC", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NCB", - "PerPkg": "1", - "UMask": "0xe", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NCS", - "PerPkg": "1", - "UMask": "0xf", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.NON_DATA_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.REM", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.REQ", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.REQ", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_DATA", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.RSP_NODATA", - "PerPkg": "1", - "UMask": "0xa", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.SGL_SLOT_HDR", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.SNP", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.SNP", - "PerPkg": "1", - "UMask": "0x9", - "Unit": "UPI LL" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_UPI_TxL_BASIC_HDR_MATCH.WB", - "Deprecated": "1", - "EventCode": "0x4", - "EventName": "UNC_UPI_TxL_HDR_MATCH.WB", - "PerPkg": "1", - "UMask": "0xc", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Allocations", - "EventCode": "0x40", - "EventName": "UNC_UPI_TxL_INSERTS", - "PerPkg": "1", - "PublicDescription": "Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Tx Flit Buffer Occupancy", - "EventCode": "0x42", - "EventName": "UNC_UPI_TxL_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "EventCode": "0x45", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", - "PerPkg": "1", - "Unit": "UPI LL" - }, - { - "BriefDescription": "VNA Credits Pending Return - Occupancy", - "EventCode": "0x44", - "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "UPI LL" - }, - { - "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", - "EventCode": "0xff", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; IPI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Inter Processor Interrupts", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; MSI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.; Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received; VLW", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "PHOLD cycles.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDRAND", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDSEED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - }, - { - "BriefDescription": "UPI interconnect send bandwidth for payload. Derived from unc_upi_txl_flits.all_data", - "EventCode": "0x2", - "EventName": "UPI_DATA_BANDWIDTH_TX", - "PerPkg": "1", - "PublicDescription": "Counts valid data FLITs (80 bit FLow control unITs: 64bits of data) transmitted (TxL) via any of the 3 Intel(R) Ultra Path Interconnect (UPI) slots on this UPI unit.", - "ScaleUnit": "7.11E-06Bytes", - "UMask": "0xf", - "Unit": "UPI LL" - } -] -- GitLab From 2bb848f820a5df2f9684435886c44caee8f5a056 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:48 -0700 Subject: [PATCH 3008/5631] perf vendor events intel: Fix uncore topics for snowridgex Remove 'uncore-other' topic classification, move to cache, interconnect and io. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: http://lore.kernel.org/lkml/20230413132949.3487664-21-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/snowridgex/uncore-cache.json | 7100 +++++ .../x86/snowridgex/uncore-interconnect.json | 6016 +++++ .../arch/x86/snowridgex/uncore-io.json | 8944 +++++++ .../arch/x86/snowridgex/uncore-other.json | 22056 ---------------- 4 files changed, 22060 insertions(+), 22056 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json create mode 100644 tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json create mode 100644 tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json delete mode 100644 tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json new file mode 100644 index 000000000000..a68a5bb05c22 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json @@ -0,0 +1,7100 @@ +[ + { + "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_READ", + "Filter": "config1=0x40040e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.MMIO_WRITE", + "Filter": "config1=0x40041e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_MISSES.UNCACHEABLE", + "Filter": "config1=0x40e33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_FULL", + "Filter": "config1=0x41833", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "ScaleUnit": "64Bytes", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", + "EventCode": "0x35", + "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", + "Filter": "config1=0x41a33", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "ScaleUnit": "64Bytes", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8A", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8B", + "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8D", + "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8E", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8F", + "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Uncore cache clock ticks", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Counter 0 Occupancy", + "EventCode": "0x1F", + "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Counter 0 Occupancy : Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6E", + "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6D", + "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xAF", + "EventName": "UNC_CHA_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xBA", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xBA", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xB6", + "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xBB", + "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xB7", + "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xB8", + "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xB9", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xB9", + "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued : ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Full Line Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", + "EventCode": "0x5B", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1fffff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE", + "PerPkg": "1", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Code Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Code Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Code Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Code Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, including prefetches from the Core", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", + "PerPkg": "1", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", + "PerPkg": "1", + "UMask": "0x1fc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Read transactions.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bc101", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL", + "PerPkg": "1", + "UMask": "0x841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Exclusive State", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : F State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Forward State", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a44ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush or Invalidate Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : I State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.I", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Miss", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : M State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.M", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Modified State", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fe001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Write Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Writeback transactions to the LLC This includes all write transactions -- both Cacheable and UC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x9d9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x11d9ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally HOMed Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Locally HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0xbd901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely HOMed Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x13d901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_OR_SNOOP_REMOTE_MISS_REM_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x161901", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_REMOTE_LOC_HOM", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0xa19ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Reads that Hit the Snoop Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.READ_SF_HIT", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Reads that Hit the Snoop Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bd90e", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1bc8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1bc801", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL", + "PerPkg": "1", + "UMask": "0x888ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Shared State", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - H State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit HitMe State", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Shared State", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x1a42ff", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated.", + "Deprecated": "1", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", + "PerPkg": "1", + "UMask": "0x842ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : All Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.ALL", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : All Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0xf", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x200f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in E State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in M State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local - Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xE6", + "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xE6", + "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ADEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.AKEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ALLRSFWAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.BLEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.FSF_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLOWSNP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLWAYRSV", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_PAMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_WAYMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.HACREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IDX_INPIPE", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IPQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IRQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ISMQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.IVEGRCREDIT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.LLC_WAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.NOTALLOWSNOOP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ONE_FSF_VIC", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.ONE_RSP_CON", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.PTL_INPIPE", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.RMW_SETMATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.RRQ_SETMATCH_VICP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.SETMATCHENTRYWSCT", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.SF_WAYS_RES", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.TOPA_MATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.TORID_MATCH_GO_P", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_REQ", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_RSP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCB", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCS", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_RSP", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_WB", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "Pipe Rejects", + "EventCode": "0x42", + "EventName": "UNC_CHA_PIPE_REJECT.WAY_MATCH", + "PerPkg": "1", + "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC10", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC10", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC10 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 10 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC11", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC11", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC11 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 11 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC12", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC12", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC12 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 12 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC13", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC13", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC13 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 13 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC6", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC6", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC6 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 6 only.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC7", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC7", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC7 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 7 only.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC8", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC8", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC8 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 8 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC9", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC9", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC9 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 9 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and remote INVITOE requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Local read requests that miss the SF/LLC and remote read requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Local write requests that miss the SF/LLC and remote write requests sent to the CHA's home agent", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xAC", + "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xAA", + "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xAD", + "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xAB", + "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_CHA_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2C", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : ANY0", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : HA", + "EventCode": "0x2D", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2E", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Allow Snoop", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : ANY0", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : HA", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : SF Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Victim", + "EventCode": "0x2F", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2A", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : ANY0", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : HA", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Victim", + "EventCode": "0x2B", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xE2", + "EventName": "UNC_CHA_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xE3", + "EventName": "UNC_CHA_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_CHA_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xE1", + "EventName": "UNC_CHA_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xE0", + "EventName": "UNC_CHA_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for E-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.E_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for M-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.M_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop filter capacity evictions for S-state entries.", + "EventCode": "0x3D", + "EventName": "UNC_CHA_SF_EVICTION.S_STATE", + "PerPkg": "1", + "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to local requests", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to local requests", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to local requests", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspCnflct", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspI", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspIFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspS", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspSFwd", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*WB", + "EventCode": "0x5D", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", + "EventCode": "0x6B", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD0", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD2", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD4", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD6", + "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD1", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD3", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD5", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD7", + "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DDR4 Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DDR4 Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.DDR", + "Deprecated": "1", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR4", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Hits", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushes issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushOpts issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushOpts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRDs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRDs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiLF misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; WCiL misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc3fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoIs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc37ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBMtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", + "PerPkg": "1", + "PublicDescription": "WbMtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc2fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBStoIs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", + "PerPkg": "1", + "PublicDescription": "WbStoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc67ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : CLFlushes issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All requests from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RFOs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WbMtoIs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - Non iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just ISOC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Local Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Misses", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMCFG Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NonCoherent", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NotNearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - Non IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DDR4 Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DDR4 Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Hits", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRDs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRDs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; WCiL misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - Non iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just ISOC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Local Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA and IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Misses", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMCFG Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NonCoherent", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NotNearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xA7", + "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xA2", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xA3", + "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xA1", + "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xA4", + "EventName": "UNC_CHA_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xA0", + "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xA5", + "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_CHA_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_CHA_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9A", + "EventName": "UNC_CHA_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_CHA_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xB0", + "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xB4", + "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xB1", + "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xB2", + "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xB3", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xB3", + "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xB5", + "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC10", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC10", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC10 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 10 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC11", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC11", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC11 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 11 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC12", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC12", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC12 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 12 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC13", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC13", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC13 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 13 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC6", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC6", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC6 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 6 only.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC7", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC7", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC7 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 7 only.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC8", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC8", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC8 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 8 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC9", + "EventCode": "0x5A", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC9", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC9 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 9 only.", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 0?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT0", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 1?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT1", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", + "UMask": "0x10", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json new file mode 100644 index 000000000000..de3840078e21 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json @@ -0,0 +1,6016 @@ +[ + { + "BriefDescription": "Total Write Cache Occupancy : Any Source", + "EventCode": "0x0F", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Total Write Cache Occupancy : Any Source : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events. : Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy : Snoops", + "EventCode": "0x0F", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", + "PerPkg": "1", + "PublicDescription": "Total Write Cache Occupancy : Snoops : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", + "EventCode": "0x0f", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops : CLFlush", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.PCITOM", + "PerPkg": "1", + "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.RFO", + "PerPkg": "1", + "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Coherent Ops : WbMtoI", + "EventCode": "0x10", + "EventName": "UNC_I_COHERENT_OPS.WBMTOI", + "PerPkg": "1", + "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "Occupancy of the IRP FAF queue.", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.EVICTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", + "EventCode": "0x1E", + "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Lost Forward", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Invalid", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Valid", + "EventCode": "0x1F", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Requests", + "EventCode": "0x14", + "EventName": "UNC_I_P2P_INSERTS", + "PerPkg": "1", + "PublicDescription": "P2P Requests : P2P requests from the ITC", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Occupancy", + "EventCode": "0x15", + "EventName": "UNC_I_P2P_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "P2P Occupancy : P2P B & S Queue Occupancy", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P completions", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if local only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if local and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P Message", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P reads", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : Match if remote only", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : match if remote and target matches", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "P2P Transactions : P2P Writes", + "EventCode": "0x13", + "EventName": "UNC_I_P2P_TRANSACTIONS.WR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Atomic", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.ATOMIC", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Atomic : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of atomic transactions", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Other", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.OTHER", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Other : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of 'other' kinds of transactions.", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count : Writes", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0x0B", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x05", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x02", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x08", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x06", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x03", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x09", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x07", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x04", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0x0A", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "EventCode": "0x1C", + "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0&AD1 both. Stalls on both AD0 and AD1 will count as 2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD0 Egress Credits Stalls", + "EventCode": "0x1A", + "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD1 Egress Credits Stalls", + "EventCode": "0x1B", + "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1D", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0D", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0E", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0x0C", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Outbound Request Queue Occupancy : Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8A", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8B", + "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8C", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8D", + "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8E", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8F", + "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Not Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Taken", + "EventCode": "0x22", + "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Not Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC Bypass : Taken", + "EventCode": "0x21", + "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Clockticks of the mesh to memory (M2M)", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled", + "EventCode": "0x24", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "EventCode": "0x60", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden", + "EventCode": "0x25", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xAF", + "EventName": "UNC_M2M_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xBA", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xBA", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xB6", + "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xBB", + "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xB7", + "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xB8", + "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xB9", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xB9", + "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x704", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_ALL", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch0", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", + "PerPkg": "1", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_ALL", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch1", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", + "PerPkg": "1", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : From TGR - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x740", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x702", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - All Channels", + "EventCode": "0x37", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x701", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1c10", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", + "PerPkg": "1", + "UMask": "0x410", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", + "PerPkg": "1", + "UMask": "0x401", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x404", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "PerPkg": "1", + "UMask": "0x402", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch0", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x408", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", + "PerPkg": "1", + "UMask": "0x810", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", + "PerPkg": "1", + "UMask": "0x801", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", + "PerPkg": "1", + "UMask": "0x802", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch1", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : From TGR - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1c01", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1c04", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1c02", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - All Channels", + "EventCode": "0x38", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1c08", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts", + "EventCode": "0x64", + "EventName": "UNC_M2M_MIRR_WRQ_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x65", + "EventName": "UNC_M2M_MIRR_WRQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xE6", + "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xE6", + "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches : MC Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number Packet Header Matches : Mesh Match", + "EventCode": "0x4C", + "EventName": "UNC_M2M_PKT_MATCH.MESH", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", + "EventCode": "0x73", + "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : All Channels", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : Channel 0", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Full : Channel 1", + "EventCode": "0x6B", + "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : All Channels", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 0", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 1", + "EventCode": "0x6C", + "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA0_INVAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA1_INVAL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_MISS_INVAL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_RSP_PDRESET", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA0_INVAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA1_INVAL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_MISS_INVAL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Deallocs", + "EventCode": "0x6E", + "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_RSP_PDRESET", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - Ch 0", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - Ch 1", + "EventCode": "0x6F", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : XPT - All Channels", + "EventCode": "0x6f", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - Ch 0", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 0", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 0", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - Ch 1", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 1", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 2", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH2_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 2", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- All Channels", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPTUPI_ALLCH", + "PerPkg": "1", + "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - All Channels", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - All Channels", + "EventCode": "0x74", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - Ch 0", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 0", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 0", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - Ch 1", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 1", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPTUPI", + "PerPkg": "1", + "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 2", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH2_XPTUPI", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - All Channels", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPTUPI_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - All Channels", + "EventCode": "0x75", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.ERRORBLK_RxC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.NOT_PF_SAD_REGION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_HIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_SECURE_DROP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.RPQ_PROXY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.STOP_B2B", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.WPQ_PROXY", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", + "EventCode": "0x70", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.XPT_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.ERRORBLK_RxC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.NOT_PF_SAD_REGION", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_AD_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_FULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_HIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_SECURE_DROP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.RPQ_PROXY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.STOP_B2B", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.WPQ_PROXY", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", + "EventCode": "0x71", + "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.XPT_THRESH", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x6D", + "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x15", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x6A", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": ": All Channels", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x76", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", + "EventCode": "0x79", + "EventName": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x7A", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_INSERTS", + "EventCode": "0x78", + "EventName": "UNC_M2M_PREFCAM_RxC_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "EventCode": "0x77", + "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xAC", + "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xAA", + "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xAD", + "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xAB", + "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_M2M_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x43", + "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x44", + "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Full", + "EventCode": "0x04", + "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Not Empty", + "EventCode": "0x03", + "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Allocations", + "EventCode": "0x01", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x02", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", + "EventCode": "0x77", + "EventName": "UNC_M2M_RxC_AD_PREF_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x5C", + "EventName": "UNC_M2M_RxC_AK_WR_CMP", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Full", + "EventCode": "0x08", + "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Not Empty", + "EventCode": "0x07", + "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Allocations", + "EventCode": "0x05", + "EventName": "UNC_M2M_RxC_BL_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x06", + "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE5", + "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xE2", + "EventName": "UNC_M2M_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xE3", + "EventName": "UNC_M2M_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_M2M_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xE1", + "EventName": "UNC_M2M_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xE0", + "EventName": "UNC_M2M_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD0", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD2", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xD4", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xD6", + "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD1", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD3", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xD5", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xD7", + "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x41", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x42", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full : Channel 0", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Full : Channel 1", + "EventCode": "0x45", + "EventName": "UNC_M2M_TRACKER_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x49", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x46", + "EventName": "UNC_M2M_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credit Acquired", + "EventCode": "0x0d", + "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Credits Occupancy", + "EventCode": "0x0e", + "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Full", + "EventCode": "0x0c", + "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Not Empty", + "EventCode": "0x0b", + "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Allocations", + "EventCode": "0x09", + "EventName": "UNC_M2M_TxC_AD_INSERTS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", + "EventCode": "0x0f", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", + "EventCode": "0x10", + "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0x0A", + "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK : CRD Transactions to Cbo", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.CRD_CBO", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound Ring Transactions on AK : NDR Transactions", + "EventCode": "0x39", + "EventName": "UNC_M2M_TxC_AK.NDR", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AKC Credits", + "EventCode": "0x5F", + "EventName": "UNC_M2M_TxC_AKC_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", + "EventCode": "0x1D", + "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : All", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Near Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Far Side", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", + "PerPkg": "1", + "UMask": "0x88", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Full", + "EventCode": "0x14", + "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : All", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Not Empty", + "EventCode": "0x13", + "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : All", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Near Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Far Side", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Allocations", + "EventCode": "0x11", + "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x20", + "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : All", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "AK Egress (to CMS) Occupancy", + "EventCode": "0x12", + "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Cache", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Core", + "EventCode": "0x40", + "EventName": "UNC_M2M_TxC_BL.DRS_CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", + "EventCode": "0x19", + "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : All", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Near Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Far Side", + "EventCode": "0x18", + "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : All", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", + "EventCode": "0x17", + "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : All", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Near Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Far Side", + "EventCode": "0x15", + "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1B", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", + "EventCode": "0x1C", + "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xA6", + "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xA7", + "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xA2", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xA3", + "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xA1", + "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xA4", + "EventName": "UNC_M2M_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xA0", + "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xA5", + "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9C", + "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9D", + "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9E", + "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2M_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_M2M_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9A", + "EventName": "UNC_M2M_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9B", + "EventName": "UNC_M2M_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xB0", + "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xB4", + "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xB1", + "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xB2", + "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xB3", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xB3", + "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xB5", + "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x58", + "EventName": "UNC_M2M_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x58", + "EventName": "UNC_M2M_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", + "EventCode": "0x4D", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", + "EventCode": "0x4E", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Channel 0", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Channel 1", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Full : Mirror", + "EventCode": "0x4A", + "EventName": "UNC_M2M_WR_TRACKER_FULL.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x4B", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x63", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x63", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x62", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x62", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Channel 0", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Channel 1", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy : Mirror", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Occupancy", + "EventCode": "0x55", + "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x5E", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x5E", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x5D", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x5D", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", + "EventCode": "0xff", + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Doorbell", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Interrupt", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Message Received : Interrupt : Interrupts", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "IDI Lock/SplitLock Cycles : Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "EventCode": "0x4D", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "EventCode": "0x4E", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "EventCode": "0x4F", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "EventCode": "0x4F", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4C", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json new file mode 100644 index 000000000000..996028071ee4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json @@ -0,0 +1,8944 @@ +[ + { + "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_READ", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "MetricName": "LLC_MISSES.PCIE_READ", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "ScaleUnit": "4Bytes", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", + "EventCode": "0x83", + "EventName": "LLC_MISSES.PCIE_WRITE", + "FCMask": "0x07", + "Filter": "ch_mask=0x1f", + "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "MetricName": "LLC_MISSES.PCIE_WRITE", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "ScaleUnit": "4Bytes", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", + "UMask": "0x20", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", + "UMask": "0x21", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", + "UMask": "0x22", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", + "UMask": "0x23", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", + "UMask": "0x24", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", + "UMask": "0x25", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", + "UMask": "0x26", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", + "PerPkg": "1", + "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", + "UMask": "0x27", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", + "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", + "PerPkg": "1", + "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", + "UMask": "0x10", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", + "EventCode": "0xC2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", + "FCMask": "0x04", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x3", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", + "EventCode": "0xD5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 1", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 2", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 3", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 3 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 4", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 4 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 5", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 5 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 6", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 6 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", + "FCMask": "0x04", + "PerPkg": "1", + "PublicDescription": "PCIe Completion Buffer Occupancy : Part 7 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Messages", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Passing data to be written", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Request Ownership", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Writing line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Request Ownership", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Writing line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 1G Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.1G_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 2M Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.2M_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Hits to a 4K Page", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.4K_HITS", + "PerPkg": "1", + "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups all", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.ALL_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": IOTLB lookups all : Some transactions have to look up IOTLB multiple times. Counts every time a request looks up IOTLB.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache hits", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", + "PerPkg": "1", + "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache lookups", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups first", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB Fills (same as IOTLB miss)", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.MISSES", + "PerPkg": "1", + "PublicDescription": ": IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Cycles PWT full", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.CYC_PWT_FULL", + "PerPkg": "1", + "PublicDescription": ": Cycles PWT full : Counts cycles the IOMMU has reached its maximum limit for outstanding page walks.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOMMU memory access", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", + "PerPkg": "1", + "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 4K page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_4K_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWT Hit to a 256T page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache fill", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache lookup", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Interrupt Entry cache hit", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.INT_CACHE_HITS", + "PerPkg": "1", + "PublicDescription": ": Interrupt Entry cache hit : Counts each time a transaction's first look up hits the IEC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Interrupt Entry cache lookup", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.INT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": Interrupt Entry cache lookup : Counts the number of transaction looks up that interrupt remapping cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": Device-selective Context cache invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DEVICE", + "PerPkg": "1", + "PublicDescription": ": Device-selective Context cache invalidation cycles : Counts number of Device selective context cache invalidation events", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Domain-selective Context cache invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DOMAIN", + "PerPkg": "1", + "PublicDescription": ": Domain-selective Context cache invalidation cycles : Counts number of Domain selective context cache invalidation events", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache global invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_GBL", + "PerPkg": "1", + "PublicDescription": ": Context cache global invalidation cycles : Counts number of Context Cache global invalidation events", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Domain-selective IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_DOMAIN", + "PerPkg": "1", + "PublicDescription": ": Domain-selective IOTLB invalidation cycles : Counts number of Domain selective invalidation events", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Global IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_GBL", + "PerPkg": "1", + "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Page-selective IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_PAGE", + "PerPkg": "1", + "PublicDescription": ": Page-selective IOTLB invalidation cycles : Counts number of Page-selective within Domain Invalidation events", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Counting disabled", + "EventCode": "0x80", + "EventName": "UNC_IIO_NOTHING", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Occupancy of outbound request queue : To device", + "EventCode": "0xC5", + "EventName": "UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Passing data to be written", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Passing data to be written : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": Issuing final read or write of line", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Processing response from IOMMU", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": Issuing to IOMMU", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": Request Ownership", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Request Ownership : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": Writing line", + "EventCode": "0x88", + "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": ": Writing line : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : From IRP", + "EventCode": "0xC2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : From ITC", + "EventCode": "0xC2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests sent to PCIe from main die : From ITC : Confined P2P", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests sent to PCIe from main die : Completion allocations", + "EventCode": "0xc2", + "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.PREALLOC", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : Drop request", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.ALL.DROP", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests PCIe makes of the main die : Drop request : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU. : Packet error detected, must be dropped", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : All", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Abort", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Memory", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : MsgB", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Ubox", + "EventCode": "0x8E", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "ITC address map 1", + "EventCode": "0x8F", + "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "PerPkg": "1", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", + "EventCode": "0xD0", + "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", + "EventCode": "0xD1", + "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PWT occupancy", + "EventCode": "0x42", + "EventName": "UNC_IIO_PWT_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Passing data to be written", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Issuing final read or write of line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Request Ownership", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - cacheline complete : Writing line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - cacheline complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Passing data to be written", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Issuing final read or write of line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Processing response from IOMMU", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Processing response from IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Issuing to IOMMU", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Issuing to IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Request Ownership", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request complete : Writing line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Passing data to be written", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Request Ownership", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Writing line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xFF", + "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Symbol Times on Link", + "EventCode": "0x82", + "EventName": "UNC_IIO_SYMBOL_TIMES", + "PerPkg": "1", + "PublicDescription": "Symbol Times on Link : Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xC1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Messages", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x100", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x200", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x01", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x02", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x04", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x08", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x10", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x20", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x40", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x80", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", + "EventCode": "0x80", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", + "EventCode": "0x81", + "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x82", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x83", + "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", + "EventCode": "0x88", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", + "EventCode": "0x89", + "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8a", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8b", + "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", + "EventCode": "0x84", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", + "EventCode": "0x85", + "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", + "EventCode": "0x86", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", + "EventCode": "0x87", + "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", + "EventCode": "0x8c", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", + "EventCode": "0x8d", + "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR0", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR1", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR2", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR3", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR4", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR5", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR6", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", + "EventCode": "0x8e", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR7", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR10", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR8", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", + "EventCode": "0x8f", + "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR9", + "PerPkg": "1", + "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Clockticks of the mesh to PCI (M2P)", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2P_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Local", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Remote", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_NONLOCAL", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - IV", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_IV", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_NOCRD", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : Horizontal", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.HORZ", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Distress signal asserted : Vertical", + "EventCode": "0xaf", + "EventName": "UNC_M2P_DISTRESS_ASSERTED.VERT", + "PerPkg": "1", + "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Even", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Even", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", + "EventCode": "0xb6", + "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xbb", + "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Even", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Even", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", + "EventCode": "0xb7", + "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Even", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Even", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_EVEN", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", + "EventCode": "0xb8", + "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_ODD", + "PerPkg": "1", + "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Left", + "EventCode": "0xb9", + "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.LEFT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Horizontal IV Ring in Use : Right", + "EventCode": "0xb9", + "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.RIGHT", + "PerPkg": "1", + "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent0", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent1", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent2", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", + "EventCode": "0xe6", + "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", + "EventCode": "0xe6", + "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : All", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : All", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : All", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", + "EventCode": "0xac", + "EventName": "UNC_M2P_RING_BOUNCES_HORZ.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AD", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AK", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring.", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.AKC", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.BL", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", + "EventCode": "0xaa", + "EventName": "UNC_M2P_RING_BOUNCES_VERT.IV", + "PerPkg": "1", + "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AD", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : AK", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK_AG1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : BL", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Horizontal Ring : IV", + "EventCode": "0xad", + "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : AD", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AK", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AKC", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.BL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", + "EventCode": "0xab", + "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.IV", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Source Throttle", + "EventCode": "0xae", + "EventName": "UNC_M2P_RING_SRC_THRTL", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xe5", + "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - All", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Credited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AK", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - All", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Credited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Bypass : IV", + "EventCode": "0xe2", + "EventName": "UNC_M2P_RxR_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - All", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : AK", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - All", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : IFV - Credited", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.IFV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation : IV", + "EventCode": "0xe3", + "EventName": "UNC_M2P_RxR_CRD_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Injection Starvation", + "EventCode": "0xe4", + "EventName": "UNC_M2P_RxR_CRD_STARVED_1", + "PerPkg": "1", + "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - All", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Credited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AK", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - All", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Credited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Allocations : IV", + "EventCode": "0xe1", + "EventName": "UNC_M2P_RxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - All", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AK", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - All", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Transgress Ingress Occupancy : IV", + "EventCode": "0xe0", + "EventName": "UNC_M2P_RxR_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xd0", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xd2", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", + "EventCode": "0xd4", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", + "EventCode": "0xd6", + "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xd1", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xd3", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", + "EventCode": "0xd5", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", + "EventCode": "0xd7", + "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", + "PerPkg": "1", + "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.BL_0", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Ingress", + "EventCode": "0x24", + "EventName": "UNC_M2P_TxC_INSERTS.BL_1", + "PerPkg": "1", + "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - All", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - All", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", + "EventCode": "0xa6", + "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - All", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AK", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - All", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Bypass Used : IV", + "EventCode": "0xa7", + "EventName": "UNC_M2P_TxR_HORZ_BYPASS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", + "EventCode": "0xa2", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AK", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_ALL", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_CRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", + "EventCode": "0xa3", + "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.IV", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AK", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Inserts : IV", + "EventCode": "0xa1", + "EventName": "UNC_M2P_TxR_HORZ_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AK", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress NACKs : IV", + "EventCode": "0xa4", + "EventName": "UNC_M2P_TxR_HORZ_NACK.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x11", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AK", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", + "UMask": "0x44", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_CRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Occupancy : IV", + "EventCode": "0xa0", + "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AK", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.AKC_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_ALL", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_UNCRD", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", + "EventCode": "0xa5", + "EventName": "UNC_M2P_TxR_HORZ_STARVED.IV", + "PerPkg": "1", + "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9c", + "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", + "EventCode": "0x9d", + "EventName": "UNC_M2P_TxR_VERT_BYPASS.IV_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", + "EventCode": "0x9e", + "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", + "EventCode": "0x9e", + "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", + "EventCode": "0x94", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", + "EventCode": "0x95", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", + "EventCode": "0x95", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", + "EventCode": "0x96", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", + "EventCode": "0x97", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", + "EventCode": "0x97", + "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", + "EventCode": "0x92", + "EventName": "UNC_M2P_TxR_VERT_INSERTS0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", + "EventCode": "0x93", + "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", + "EventCode": "0x93", + "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : IV", + "EventCode": "0x98", + "EventName": "UNC_M2P_TxR_VERT_NACK0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", + "EventCode": "0x99", + "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", + "EventCode": "0x99", + "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", + "EventCode": "0x90", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", + "EventCode": "0x91", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", + "EventCode": "0x91", + "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", + "EventCode": "0x9a", + "EventName": "UNC_M2P_TxR_VERT_STARVED0.IV_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG0", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG1", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", + "EventCode": "0x9b", + "EventName": "UNC_M2P_TxR_VERT_STARVED1.TGC", + "PerPkg": "1", + "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Even", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Down and Odd", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Even", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AD Ring In Use : Up and Odd", + "EventCode": "0xb0", + "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Even", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Even", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", + "EventCode": "0xb4", + "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Even", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Down and Odd", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Even", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical AK Ring In Use : Up and Odd", + "EventCode": "0xb1", + "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Even", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Down and Odd", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Even", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical BL Ring in Use : Up and Odd", + "EventCode": "0xb2", + "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Down", + "EventCode": "0xb3", + "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.DN", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical IV Ring in Use : Up", + "EventCode": "0xb3", + "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.UP", + "PerPkg": "1", + "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Even", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Even", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_EVEN", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", + "EventCode": "0xb5", + "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_ODD", + "PerPkg": "1", + "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", + "UMask": "0x2", + "Unit": "M2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json deleted file mode 100644 index 8bd041bc0c57..000000000000 --- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-other.json +++ /dev/null @@ -1,22056 +0,0 @@ -[ - { - "BriefDescription": "MMIO reads. Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.MMIO_READ", - "Filter": "config1=0x40040e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "MMIO writes. Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.MMIO_WRITE", - "Filter": "config1=0x40041e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO. Derived from unc_iio_data_req_of_cpu.mem_read.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_READ", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "MetricName": "LLC_MISSES.PCIE_READ", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "ScaleUnit": "4Bytes", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO. Derived from unc_iio_data_req_of_cpu.mem_write.part0", - "EventCode": "0x83", - "EventName": "LLC_MISSES.PCIE_WRITE", - "FCMask": "0x07", - "Filter": "ch_mask=0x1f", - "MetricExpr": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2 + UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "MetricName": "LLC_MISSES.PCIE_WRITE", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "ScaleUnit": "4Bytes", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_MISSES.UNCACHEABLE", - "Filter": "config1=0x40e33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "Streaming stores (full cache line). Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_REFERENCES.STREAMING_FULL", - "Filter": "config1=0x41833", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "ScaleUnit": "64Bytes", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "Streaming stores (partial cache line). Derived from unc_cha_tor_inserts.ia_miss", - "EventCode": "0x35", - "EventName": "LLC_REFERENCES.STREAMING_PARTIAL", - "Filter": "config1=0x41a33", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "ScaleUnit": "64Bytes", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_CHA_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_CHA_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_CHA_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8A", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8B", - "EventName": "UNC_CHA_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_CHA_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_CHA_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8D", - "EventName": "UNC_CHA_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8E", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8F", - "EventName": "UNC_CHA_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Not Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Bypass : Taken", - "EventCode": "0x57", - "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Uncore cache clock ticks", - "EventName": "UNC_CHA_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_CHA_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xf2", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0xf1", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x42", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x41", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x82", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single Eviction", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x81", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x22", - "Unit": "CHA" - }, - { - "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", - "EventCode": "0x33", - "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", - "PerPkg": "1", - "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", - "UMask": "0x21", - "Unit": "CHA" - }, - { - "BriefDescription": "Counter 0 Occupancy", - "EventCode": "0x1F", - "EventName": "UNC_CHA_COUNTER0_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Counter 0 Occupancy : Since occupancy counts can only be captured in the Cbo's 0 counter, this event allows a user to capture occupancy related information by filtering the Cb0 occupancy count captured in Counter 0. The filtering available is found in the control register - threshold, invert and edge detect. E.g. setting threshold to 1 can effectively monitor how many cycles the monitored queue has an entry.", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6E", - "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Direct GO", - "EventCode": "0x6D", - "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xAF", - "EventName": "UNC_CHA_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xBA", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xBA", - "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xB6", - "EventName": "UNC_CHA_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xBB", - "EventName": "UNC_CHA_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xB7", - "EventName": "UNC_CHA_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xB8", - "EventName": "UNC_CHA_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xB9", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xB9", - "EventName": "UNC_CHA_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "HA to iMC Reads Issued : ISOCH", - "EventCode": "0x59", - "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", - "PerPkg": "1", - "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : Full Line Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", - "PerPkg": "1", - "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to any of the memory controller channels.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", - "EventCode": "0x5B", - "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", - "PerPkg": "1", - "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ALL", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", - "UMask": "0x1fffff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : All Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : All Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE", - "PerPkg": "1", - "UMask": "0x1bd0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Code Reads", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Code Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd0ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : CRd Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : CRd Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Code Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Code Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd001", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Local request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Local request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, including prefetches from the Core", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", - "PerPkg": "1", - "UMask": "0x1bc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ", - "PerPkg": "1", - "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", - "UMask": "0x1bc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", - "PerPkg": "1", - "UMask": "0x1fc1ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Data Read Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Data Read Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Read transactions.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Data Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bc101", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL", - "PerPkg": "1", - "UMask": "0x841ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : E State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.E", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Exclusive State", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : F State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Forward State", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", - "UMask": "0x1a44ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Flush or Invalidate Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Flush or Invalidate Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : I State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.I", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Miss", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Transactions homed locally Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Transactions homed locally Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : M State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.M", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Modified State", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : All Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : All Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1fe001", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Write Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Write Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Writeback transactions to the LLC This includes all write transactions -- both Cacheable and UC.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Reads", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x9d9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_LOCAL_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally Requested Reads that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x11d9ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Locally HOMed Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Locally HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0xbd901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely HOMed Read Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_MISS_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely HOMed Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x13d901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_OR_SNOOP_REMOTE_MISS_REM_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely requested Read or Snoop Misses that are Remotely HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x161901", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_REMOTE_LOC_HOM", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Remotely Requested Reads that are Locally HOMed : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0xa19ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Reads that Hit the Snoop Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.READ_SF_HIT", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Reads that Hit the Snoop Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bd90e", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Requests", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "UMask": "0x1bc8ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Request Filter", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Request Filter : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : RFO Misses", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_MISS", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : RFO Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", - "UMask": "0x1bc801", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL", - "PerPkg": "1", - "UMask": "0x888ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : S State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.S", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Hit Shared State", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - E State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - H State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit HitMe State", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : SnoopFilter - S State", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : SF Hit Shared State", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITES_AND_OTHER", - "PerPkg": "1", - "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", - "UMask": "0x1a42ff", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated.", - "Deprecated": "1", - "EventCode": "0x34", - "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", - "PerPkg": "1", - "UMask": "0x842ff", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : All Lines Victimized", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.ALL", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : All Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0xf", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in E state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - All Lines", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - All Lines : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x200f", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in E State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in E State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2002", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in M State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in M State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2001", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local Only", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Local - Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Local - Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x2004", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in M state", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Lines Victimized : Lines in S State", - "EventCode": "0x37", - "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", - "PerPkg": "1", - "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Number of times that an RFO hit in S state.", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RFO_HIT_S", - "PerPkg": "1", - "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : Silent Snoop Eviction", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cbo Misc : Write Combining Aliasing", - "EventCode": "0x39", - "EventName": "UNC_CHA_MISC.WC_ALIASING", - "PerPkg": "1", - "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xE6", - "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xE6", - "EventName": "UNC_CHA_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ADEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.AKEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ALLRSFWAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.BLEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.FSF_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLOWSNP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_ALLWAYRSV", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_PAMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.GOTRACK_WAYMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.HACREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IDX_INPIPE", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IPQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IRQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ISMQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.IVEGRCREDIT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.LLC_WAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.NOTALLOWSNOOP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ONE_FSF_VIC", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.ONE_RSP_CON", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.PTL_INPIPE", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.RMW_SETMATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.RRQ_SETMATCH_VICP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.SETMATCHENTRYWSCT", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.SF_WAYS_RES", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.TOPA_MATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.TORID_MATCH_GO_P", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_REQ", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_AD_RSP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCB", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_NCS", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_RSP", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.VN_BL_WB", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "Pipe Rejects", - "EventCode": "0x42", - "EventName": "UNC_CHA_PIPE_REJECT.WAY_MATCH", - "PerPkg": "1", - "PublicDescription": "Pipe Rejects : More Miscellaneous events in the Cbo.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC10", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC10", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC10 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 10 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC11", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC11", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC11 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 11 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC12", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC12", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC12 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 12 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC13", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC13", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC13 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 13 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC6", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC6", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC6 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 6 only.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC7", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC7", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC7 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 7 only.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC8", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC8", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC8 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 8 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC9", - "EventCode": "0x58", - "EventName": "UNC_CHA_READ_NO_CREDITS.MC9", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC9 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 9 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "Local INVITOE requests (exclusive ownership of a cache line without receiving data) that miss the SF/LLC and remote INVITOE requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.INVITOE", - "PerPkg": "1", - "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", - "UMask": "0x30", - "Unit": "CHA" - }, - { - "BriefDescription": "Local read requests that miss the SF/LLC and remote read requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.READS", - "PerPkg": "1", - "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", - "UMask": "0x3", - "Unit": "CHA" - }, - { - "BriefDescription": "Local write requests that miss the SF/LLC and remote write requests sent to the CHA's home agent", - "EventCode": "0x50", - "EventName": "UNC_CHA_REQUESTS.WRITES", - "PerPkg": "1", - "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", - "UMask": "0xc", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xAC", - "EventName": "UNC_CHA_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xAA", - "EventName": "UNC_CHA_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xAD", - "EventName": "UNC_CHA_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xAB", - "EventName": "UNC_CHA_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_CHA_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : IRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Allocations : PRQ", - "EventCode": "0x13", - "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", - "EventCode": "0x18", - "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", - "EventCode": "0x19", - "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", - "EventCode": "0x24", - "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2C", - "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Rejects - Set 1 : HA", - "EventCode": "0x25", - "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", - "PerPkg": "1", - "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 1 : ANY0", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "ISMQ Retries - Set 1 : HA", - "EventCode": "0x2D", - "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Ingress (from CMS) Occupancy : IRQ", - "EventCode": "0x11", - "EventName": "UNC_CHA_RxC_OCCUPANCY.IRQ", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Occupancy : IRQ : Counts number of entries in the specified Ingress queue in each cycle.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2E", - "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : Allow Snoop", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : ANY0", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : HA", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : LLC Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : SF Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Other Retries - Set 1 : Victim", - "EventCode": "0x2F", - "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", - "EventCode": "0x20", - "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", - "EventCode": "0x21", - "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", - "EventCode": "0x2A", - "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : ANY0", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : HA", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Request Queue Retries - Set 1 : Victim", - "EventCode": "0x2B", - "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", - "PerPkg": "1", - "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_CHA_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xE2", - "EventName": "UNC_CHA_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xE3", - "EventName": "UNC_CHA_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_CHA_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xE1", - "EventName": "UNC_CHA_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xE0", - "EventName": "UNC_CHA_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for E-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.E_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking exclusive lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for M-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.M_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking modified lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop filter capacity evictions for S-state entries.", - "EventCode": "0x3D", - "EventName": "UNC_CHA_SF_EVICTION.S_STATE", - "PerPkg": "1", - "PublicDescription": "Counts snoop filter capacity evictions for entries tracking shared lines in the cores? cache.? Snoop filter capacity evictions occur when the snoop filter is full and evicts an existing entry to track a new entry.? Does not count clean evictions such as when a core?s cache replaces a tracked cacheline with a new cacheline.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : All", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.ALL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Broadcast snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Broadcast snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA responding to local requests", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA responding to local requests", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoops Sent : Snoops sent for Local Requests", - "EventCode": "0x51", - "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", - "PerPkg": "1", - "PublicDescription": "Snoops Sent : Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA responding to local requests", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspCnflct", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspI", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspIFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspS", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : RspSFwd", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its currently copy. This is common for data and code reads that hit in a remote socket in E or F state.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Snoop Responses Received Local : Rsp*WB", - "EventCode": "0x5D", - "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", - "PerPkg": "1", - "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", - "EventCode": "0x6B", - "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD0", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD2", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD4", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD6", - "EventName": "UNC_CHA_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD1", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD3", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD5", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD7", - "EventName": "UNC_CHA_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ffff", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DDR4 Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DDR4 Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_TOR_INSERTS.DDR", - "Deprecated": "1", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.DDR4", - "PerPkg": "1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : SF/LLC Evictions", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Hits", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushes issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushes issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushOpts issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushOpts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRDs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRDs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; CRd Pref from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opts issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRds issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : DRd_Opt_Prefs issued by iA Cores that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiLF misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_FULL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts; WCiL misses from local IA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_PARTIAL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFO_Prefs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFO_Prefs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", - "PerPkg": "1", - "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc3fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBEFtoIs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", - "PerPkg": "1", - "PublicDescription": "WbEFtoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc37ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBMtoEs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", - "PerPkg": "1", - "PublicDescription": "WbMtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc2fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WBStoIs issued by an IA Core. Non Modified Write Backs", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", - "PerPkg": "1", - "PublicDescription": "WbStoIs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc67ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLs issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WCiLF issued by iA Cores : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : CLFlushes issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that Hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All requests from IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All requests from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PCIRdCurs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : RFOs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : WbMtoIs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : IRQ - Non iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just ISOC", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Local Targets", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA and IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local iA", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : All from Local IO", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just Misses", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : MMCFG Access", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NearMem", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NonCoherent", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Just NotNearMem", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Inserts : PRQ - Non IOSF", - "EventCode": "0x35", - "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DDR4 Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DDR4 Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : SF/LLC Evictions", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Hits", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8d7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRDs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRDs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; CRd Pref from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", - "UMask": "0xc88fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fd01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRds issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc80ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc88ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc837fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc827fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : DRd_Opt_Prefs issued by iA Cores that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8a7fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiLF misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_FULL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy; WCiL misses from local IA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_PARTIAL_STREAMING_WR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc877de01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86ffe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867fe01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc87fde01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc807ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFO_Prefs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc887ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc27ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc86fff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc867ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8c3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fd04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc001fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcd43fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803fe04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc8f3ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : RFOs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xc803ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0xcc23ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From an iA Core", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : IRQ - Non iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just ISOC", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Local Targets", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA and IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests", - "UMask": "0xc000ff05", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local iA", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally initiated requests from iA Cores", - "UMask": "0xc000ff01", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : All from Local IO", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : All locally generated IO traffic", - "UMask": "0xc000ff04", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just Misses", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : MMCFG Access", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NearMem", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NonCoherent", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Just NotNearMem", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts. : From a PCIe Device", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", - "EventCode": "0x36", - "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", - "PerPkg": "1", - "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_CHA_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xA7", - "EventName": "UNC_CHA_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xA2", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xA3", - "EventName": "UNC_CHA_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xA1", - "EventName": "UNC_CHA_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xA4", - "EventName": "UNC_CHA_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xA0", - "EventName": "UNC_CHA_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xA5", - "EventName": "UNC_CHA_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_CHA_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_CHA_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_CHA_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_CHA_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_CHA_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_CHA_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_CHA_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_CHA_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_CHA_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9A", - "EventName": "UNC_CHA_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_CHA_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xB0", - "EventName": "UNC_CHA_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xB4", - "EventName": "UNC_CHA_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xB1", - "EventName": "UNC_CHA_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xB2", - "EventName": "UNC_CHA_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xB3", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xB3", - "EventName": "UNC_CHA_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xB5", - "EventName": "UNC_CHA_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI : Pushed to LLC", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", - "PerPkg": "1", - "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "WbPushMtoI : Pushed to Memory", - "EventCode": "0x56", - "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", - "PerPkg": "1", - "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", - "UMask": "0x2", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC10", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC10", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC10 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 10 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC11", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC11", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC11 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 11 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC12", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC12", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC12 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 12 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC13", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC13", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC13 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 13 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", - "UMask": "0x20", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC6", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC6", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC6 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 6 only.", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC7", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC7", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC7 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 7 only.", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC8", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC8", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC8 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 8 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC9", - "EventCode": "0x5A", - "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC9", - "PerPkg": "1", - "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC9 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 9 only.", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", - "UMask": "0x8", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", - "UMask": "0x4", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", - "UMask": "0x80", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", - "UMask": "0x40", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Sent (on 0?)", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.SENT0", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", - "UMask": "0x1", - "Unit": "CHA" - }, - { - "BriefDescription": "XPT Prefetches : Sent (on 1?)", - "EventCode": "0x6f", - "EventName": "UNC_CHA_XPT_PREF.SENT1", - "PerPkg": "1", - "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", - "UMask": "0x10", - "Unit": "CHA" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", - "UMask": "0x20", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", - "UMask": "0x21", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", - "UMask": "0x22", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", - "UMask": "0x23", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", - "UMask": "0x24", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", - "UMask": "0x25", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", - "UMask": "0x26", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", - "EventCode": "0xff", - "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", - "PerPkg": "1", - "PublicDescription": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", - "UMask": "0x27", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "Clockticks of the integrated IO (IIO) traffic controller", - "EventCode": "0x01", - "EventName": "UNC_IIO_CLOCKTICKS", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Free running counter that increments for IIO clocktick", - "EventCode": "0xff", - "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", - "PerPkg": "1", - "PublicDescription": "Free running counter that increments for integrated IO (IIO) traffic controller clockticks", - "UMask": "0x10", - "Unit": "iio_free_running" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts : All Ports", - "EventCode": "0xC2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0xff", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", - "EventCode": "0xc2", - "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", - "FCMask": "0x04", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x3", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", - "EventCode": "0xD5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0-7", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0-7", - "UMask": "0xff", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 0", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 1", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 2", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 3", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 3 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 4", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 4 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 5", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 5 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 6", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 6 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Completion Buffer Occupancy of completions with data : Part 7", - "EventCode": "0xd5", - "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", - "FCMask": "0x04", - "PerPkg": "1", - "PublicDescription": "PCIe Completion Buffer Occupancy : Part 7 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reading from Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.CFG_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's PCICFG space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reading from Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.IO_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's IO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM", - "EventCode": "0xc0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core reporting completion of Card read from Core DRAM : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC0", - "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.ATOMIC.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Atomic requests targeting DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth reading at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card reading from DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 0", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 1", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 2", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCI Express bandwidth writing at IIO, part 3", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Four byte data request of the CPU : Card writing to DRAM", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Messages", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MSG.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Messages : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card reading from another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x83", - "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Passing data to be written", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Request Ownership", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests : Writing line", - "EventCode": "0x86", - "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Request Ownership", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Incoming arbitration requests granted : Writing line", - "EventCode": "0x87", - "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 1G Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.1G_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 1G Page : Counts if a transaction to a 1G page, on its first lookup, hits the IOTLB.", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 2M Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.2M_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 2M Page : Counts if a transaction to a 2M page, on its first lookup, hits the IOTLB.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Hits to a 4K Page", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.4K_HITS", - "PerPkg": "1", - "PublicDescription": ": IOTLB Hits to a 4K Page : Counts if a transaction to a 4K page, on its first lookup, hits the IOTLB.", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB lookups all", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.ALL_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": IOTLB lookups all : Some transactions have to look up IOTLB multiple times. Counts every time a request looks up IOTLB.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache hits", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", - "PerPkg": "1", - "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache lookups", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB lookups first", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOTLB Fills (same as IOTLB miss)", - "EventCode": "0x40", - "EventName": "UNC_IIO_IOMMU0.MISSES", - "PerPkg": "1", - "PublicDescription": ": IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Cycles PWT full", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.CYC_PWT_FULL", - "PerPkg": "1", - "PublicDescription": ": Cycles PWT full : Counts cycles the IOMMU has reached its maximum limit for outstanding page walks.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": IOMMU memory access", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", - "PerPkg": "1", - "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 1G page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 2M page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWC Hit to a 4K page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_4K_HITS", - "PerPkg": "1", - "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": PWT Hit to a 256T page", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", - "PerPkg": "1", - "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": PageWalk cache fill", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", - "PerPkg": "1", - "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": PageWalk cache lookup", - "EventCode": "0x41", - "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Interrupt Entry cache hit", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.INT_CACHE_HITS", - "PerPkg": "1", - "PublicDescription": ": Interrupt Entry cache hit : Counts each time a transaction's first look up hits the IEC.", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": ": Interrupt Entry cache lookup", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.INT_CACHE_LOOKUPS", - "PerPkg": "1", - "PublicDescription": ": Interrupt Entry cache lookup : Counts the number of transaction looks up that interrupt remapping cache.", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": ": Device-selective Context cache invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DEVICE", - "PerPkg": "1", - "PublicDescription": ": Device-selective Context cache invalidation cycles : Counts number of Device selective context cache invalidation events", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Domain-selective Context cache invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_DOMAIN", - "PerPkg": "1", - "PublicDescription": ": Domain-selective Context cache invalidation cycles : Counts number of Domain selective context cache invalidation events", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": ": Context cache global invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_CTXT_CACHE_INVAL_GBL", - "PerPkg": "1", - "PublicDescription": ": Context cache global invalidation cycles : Counts number of Context Cache global invalidation events", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Domain-selective IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_DOMAIN", - "PerPkg": "1", - "PublicDescription": ": Domain-selective IOTLB invalidation cycles : Counts number of Domain selective invalidation events", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Global IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_GBL", - "PerPkg": "1", - "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Page-selective IOTLB invalidation cycles", - "EventCode": "0x43", - "EventName": "UNC_IIO_IOMMU3.NUM_INVAL_PAGE", - "PerPkg": "1", - "PublicDescription": ": Page-selective IOTLB invalidation cycles : Counts number of Page-selective within Domain Invalidation events", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x02", - "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", - "EventCode": "0x03", - "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", - "PerPkg": "1", - "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Counting disabled", - "EventCode": "0x80", - "EventName": "UNC_IIO_NOTHING", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Occupancy of outbound request queue : To device", - "EventCode": "0xC5", - "EventName": "UNC_IIO_NUM_OUSTANDING_REQ_FROM_CPU.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Occupancy of outbound request queue : To device : Counts number of outbound requests/completions IIO is currently processing", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Passing data to be written", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Passing data to be written : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": ": Issuing final read or write of line", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": ": Processing response from IOMMU", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": ": Issuing to IOMMU", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": ": Request Ownership", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Request Ownership : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": ": Writing line", - "EventCode": "0x88", - "EventName": "UNC_IIO_NUM_OUTSTANDING_REQ_OF_CPU.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": ": Writing line : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From IRP", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : From ITC", - "EventCode": "0xC2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests sent to PCIe from main die : From ITC : Confined P2P", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests sent to PCIe from main die : Completion allocations", - "EventCode": "0xc2", - "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.PREALLOC", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests PCIe makes of the main die : Drop request", - "EventCode": "0x85", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU.ALL.DROP", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests PCIe makes of the main die : Drop request : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU. : Packet error detected, must be dropped", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number requests PCIe makes of the main die : All", - "EventCode": "0x85", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Abort", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Memory", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : MsgB", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Num requests sent by PCIe - by target : Ubox", - "EventCode": "0x8E", - "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "ITC address map 1", - "EventCode": "0x8F", - "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", - "PerPkg": "1", - "Unit": "IIO" - }, - { - "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", - "EventCode": "0xD0", - "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", - "EventCode": "0xD1", - "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PWT occupancy", - "EventCode": "0x42", - "EventName": "UNC_IIO_PWT_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Passing data to be written", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Issuing final read or write of line", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Request Ownership", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - cacheline complete : Writing line", - "EventCode": "0x91", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - cacheline complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes all its passes (e.g. finishes posting writes to all multi-cast targets) it advances line : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Passing data to be written", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Issuing final read or write of line", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Processing response from IOMMU", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Processing response from IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Issuing to IOMMU", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Issuing to IOMMU : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Request Ownership", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request complete : Writing line", - "EventCode": "0x92", - "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer. : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Passing data to be written", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Request Ownership", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "PCIe Request - pass complete : Writing line", - "EventCode": "0x90", - "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0xFF", - "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Symbol Times on Link", - "EventCode": "0x82", - "EventName": "UNC_IIO_SYMBOL_TIMES", - "PerPkg": "1", - "PublicDescription": "Symbol Times on Link : Gen1 - increment once every 4nS, Gen2 - increment once every 2nS, Gen3 - increment once every 1nS", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.CFG_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's PCICFG space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.IO_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's IO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x20", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space", - "EventCode": "0xc1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) reading from this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", - "EventCode": "0xC1", - "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.ATOMIC.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Atomic requests targeting DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x10", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x80", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x4", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x1", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Messages", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MSG.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Messages : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x40", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_READ.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card reading from another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x8", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x100", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.IOMMU1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x200", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : IOMMU - Type 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x01", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x02", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x04", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x08", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x10", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x20", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x40", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", - "EventCode": "0x84", - "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", - "FCMask": "0x07", - "PerPkg": "1", - "PortMask": "0x80", - "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", - "UMask": "0x2", - "Unit": "IIO" - }, - { - "BriefDescription": "Total Write Cache Occupancy : Any Source", - "EventCode": "0x0F", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", - "PerPkg": "1", - "PublicDescription": "Total Write Cache Occupancy : Any Source : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events. : Tracks all requests from any source port.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Total Write Cache Occupancy : Snoops", - "EventCode": "0x0F", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.IV_Q", - "PerPkg": "1", - "PublicDescription": "Total Write Cache Occupancy : Snoops : Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", - "EventCode": "0x0f", - "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", - "PerPkg": "1", - "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Clockticks of the IO coherency tracker (IRP)", - "EventCode": "0x01", - "EventName": "UNC_I_CLOCKTICKS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops : CLFlush", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.CLFLUSH", - "PerPkg": "1", - "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.PCITOM", - "PerPkg": "1", - "PublicDescription": "PCIITOM request issued by the IRP unit to the mesh with the intention of writing a full cacheline to coherent memory, without a RFO. PCIITOM is a speculative Invalidate to Modified command that requests ownership of the cacheline and does not move data from the mesh to IRP cache.", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline.", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.RFO", - "PerPkg": "1", - "PublicDescription": "RFO request issued by the IRP unit to the mesh with the intention of writing a partial cacheline to coherent memory. RFO is a Read For Ownership command that requests ownership of the cacheline and moves data from the mesh to IRP cache.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Coherent Ops : WbMtoI", - "EventCode": "0x10", - "EventName": "UNC_I_COHERENT_OPS.WBMTOI", - "PerPkg": "1", - "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF RF full", - "EventCode": "0x17", - "EventName": "UNC_I_FAF_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound read requests received by the IRP and inserted into the FAF queue.", - "EventCode": "0x18", - "EventName": "UNC_I_FAF_INSERTS", - "PerPkg": "1", - "PublicDescription": "Inbound read requests to coherent memory, received by the IRP and inserted into the Fire and Forget queue (FAF), a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "Occupancy of the IRP FAF queue.", - "EventCode": "0x19", - "EventName": "UNC_I_FAF_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Occupancy of the IRP Fire and Forget (FAF) queue, a queue used for processing inbound reads in the IRP.", - "Unit": "IRP" - }, - { - "BriefDescription": "FAF allocation -- sent to ADQ", - "EventCode": "0x16", - "EventName": "UNC_I_FAF_TRANSACTIONS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.EVICTS", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", - "EventCode": "0x20", - "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.2ND_RD_INSERT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.2ND_WR_INSERT", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.FAST_REJ", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", - "EventCode": "0x1e", - "EventName": "UNC_I_MISC0.FAST_REQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.FAST_XFER", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.PF_ACK_HINT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", - "EventCode": "0x1E", - "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Lost Forward", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.LOST_FWD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Received Invalid", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Received Valid", - "EventCode": "0x1F", - "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_E", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_I", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_M", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", - "EventCode": "0x1f", - "EventName": "UNC_I_MISC1.SLOW_S", - "PerPkg": "1", - "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Requests", - "EventCode": "0x14", - "EventName": "UNC_I_P2P_INSERTS", - "PerPkg": "1", - "PublicDescription": "P2P Requests : P2P requests from the ITC", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Occupancy", - "EventCode": "0x15", - "EventName": "UNC_I_P2P_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "P2P Occupancy : P2P B & S Queue Occupancy", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P completions", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.CMPL", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if local only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if local and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.LOC_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P Message", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.MSG", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P reads", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.RD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : Match if remote only", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : match if remote and target matches", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.REM_AND_TGT_MATCH", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "P2P Transactions : P2P Writes", - "EventCode": "0x13", - "EventName": "UNC_I_P2P_TRANSACTIONS.WR", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", - "UMask": "0x7e", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", - "UMask": "0x74", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", - "UMask": "0x72", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", - "UMask": "0x78", - "Unit": "IRP" - }, - { - "BriefDescription": "Responses to snoops of any type that miss the IIO cache", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", - "PerPkg": "1", - "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", - "UMask": "0x71", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit E or S", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_ES", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit I", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_I", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Hit M", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.HIT_M", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : Miss", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.MISS", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpCode", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPCODE", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpData", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPDATA", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Snoop Responses : SnpInv", - "EventCode": "0x12", - "EventName": "UNC_I_SNOOP_RESP.SNPINV", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Atomic", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.ATOMIC", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Atomic : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of atomic transactions", - "UMask": "0x10", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Other", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.OTHER", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Other : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks the number of 'other' kinds of transactions.", - "UMask": "0x20", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound Transaction Count : Writes", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WRITES", - "PerPkg": "1", - "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", - "UMask": "0x2", - "Unit": "IRP" - }, - { - "BriefDescription": "Inbound write (fast path) requests received by the IRP.", - "EventCode": "0x11", - "EventName": "UNC_I_TRANSACTIONS.WR_PREF", - "PerPkg": "1", - "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", - "UMask": "0x8", - "Unit": "IRP" - }, - { - "BriefDescription": "AK Egress Allocations", - "EventCode": "0x0B", - "EventName": "UNC_I_TxC_AK_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Cycles Full", - "EventCode": "0x05", - "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Inserts", - "EventCode": "0x02", - "EventName": "UNC_I_TxC_BL_DRS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL DRS Egress Occupancy", - "EventCode": "0x08", - "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Cycles Full", - "EventCode": "0x06", - "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Inserts", - "EventCode": "0x03", - "EventName": "UNC_I_TxC_BL_NCB_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCB Egress Occupancy", - "EventCode": "0x09", - "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Cycles Full", - "EventCode": "0x07", - "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Inserts", - "EventCode": "0x04", - "EventName": "UNC_I_TxC_BL_NCS_INSERTS", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "BL NCS Egress Occupancy", - "EventCode": "0x0A", - "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", - "PerPkg": "1", - "Unit": "IRP" - }, - { - "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", - "EventCode": "0x1C", - "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0&AD1 both. Stalls on both AD0 and AD1 will count as 2", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD0 Egress Credits Stalls", - "EventCode": "0x1A", - "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No AD1 Egress Credits Stalls", - "EventCode": "0x1B", - "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "No BL Egress Credit Stalls", - "EventCode": "0x1D", - "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", - "PerPkg": "1", - "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0x0D", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", - "PerPkg": "1", - "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Read Requests", - "EventCode": "0x0E", - "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", - "PerPkg": "1", - "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", - "Unit": "IRP" - }, - { - "BriefDescription": "Outbound Request Queue Occupancy", - "EventCode": "0x0C", - "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", - "PerPkg": "1", - "PublicDescription": "Outbound Request Queue Occupancy : Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", - "Unit": "IRP" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_M2M_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_M2M_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_M2M_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8A", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8B", - "EventName": "UNC_M2M_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_M2M_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_M2M_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8C", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8D", - "EventName": "UNC_M2M_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8E", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8F", - "EventName": "UNC_M2M_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Not Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Taken", - "EventCode": "0x22", - "EventName": "UNC_M2M_BYPASS_M2M_EGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Not Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.NOT_TAKEN", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC Bypass : Taken", - "EventCode": "0x21", - "EventName": "UNC_M2M_BYPASS_M2M_INGRESS.TAKEN", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Clockticks of the mesh to memory (M2M)", - "EventName": "UNC_M2M_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M2M_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled", - "EventCode": "0x24", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", - "EventCode": "0x60", - "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number of reads in which direct to core transaction was overridden", - "EventCode": "0x25", - "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xAF", - "EventName": "UNC_M2M_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xBA", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xBA", - "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xB6", - "EventName": "UNC_M2M_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xBB", - "EventName": "UNC_M2M_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xB7", - "EventName": "UNC_M2M_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xB8", - "EventName": "UNC_M2M_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xB9", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xB9", - "EventName": "UNC_M2M_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ALL", - "PerPkg": "1", - "UMask": "0x704", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_ALL", - "PerPkg": "1", - "UMask": "0x104", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", - "PerPkg": "1", - "UMask": "0x140", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", - "PerPkg": "1", - "UMask": "0x102", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch0", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", - "PerPkg": "1", - "UMask": "0x101", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : All, regardless of priority. - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_ALL", - "PerPkg": "1", - "UMask": "0x204", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", - "PerPkg": "1", - "UMask": "0x240", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", - "PerPkg": "1", - "UMask": "0x202", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - Ch1", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", - "PerPkg": "1", - "UMask": "0x201", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : From TGR - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.FROM_TGR", - "PerPkg": "1", - "UMask": "0x740", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Critical Priority - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.ISOCH", - "PerPkg": "1", - "UMask": "0x702", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Reads Issued to iMC : Normal Priority - All Channels", - "EventCode": "0x37", - "EventName": "UNC_M2M_IMC_READS.NORMAL", - "PerPkg": "1", - "UMask": "0x701", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.ALL", - "PerPkg": "1", - "UMask": "0x1c10", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", - "PerPkg": "1", - "UMask": "0x410", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", - "PerPkg": "1", - "UMask": "0x401", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x404", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", - "PerPkg": "1", - "UMask": "0x402", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch0", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x408", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : All Writes - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", - "PerPkg": "1", - "UMask": "0x810", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", - "PerPkg": "1", - "UMask": "0x801", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x804", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", - "PerPkg": "1", - "UMask": "0x802", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - Ch1", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x808", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : From TGR - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Full Line Non-ISOCH - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL", - "PerPkg": "1", - "UMask": "0x1c01", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Full Line - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", - "PerPkg": "1", - "UMask": "0x1c04", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Non-Inclusive Miss - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : Partial Non-ISOCH - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", - "PerPkg": "1", - "UMask": "0x1c02", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M Writes Issued to iMC : ISOCH Partial - All Channels", - "EventCode": "0x38", - "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", - "PerPkg": "1", - "UMask": "0x1c08", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts", - "EventCode": "0x64", - "EventName": "UNC_M2M_MIRR_WRQ_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x65", - "EventName": "UNC_M2M_MIRR_WRQ_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xE6", - "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xE6", - "EventName": "UNC_M2M_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches : MC Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number Packet Header Matches : Mesh Match", - "EventCode": "0x4C", - "EventName": "UNC_M2M_PKT_MATCH.MESH", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", - "EventCode": "0x73", - "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : All Channels", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : Channel 0", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Full : Channel 1", - "EventCode": "0x6B", - "EventName": "UNC_M2M_PREFCAM_CYCLES_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : All Channels", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 0", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Cycles Not Empty : Channel 1", - "EventCode": "0x6C", - "EventName": "UNC_M2M_PREFCAM_CYCLES_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA0_INVAL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_HITA1_INVAL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_MISS_INVAL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH0_RSP_PDRESET", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA0_INVAL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_HITA1_INVAL", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_MISS_INVAL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Deallocs", - "EventCode": "0x6E", - "EventName": "UNC_M2M_PREFCAM_DEALLOCS.CH1_RSP_PDRESET", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - Ch 0", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - Ch 1", - "EventCode": "0x6F", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped : XPT - All Channels", - "EventCode": "0x6f", - "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - Ch 0", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 0", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH0_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 0", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - Ch 1", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 1", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH1_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- Ch 2", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.CH2_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - Ch 2", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT & UPI- All Channels", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPTUPI_ALLCH", - "PerPkg": "1", - "PublicDescription": "Demands Merged with CAMed Prefetches : XPT & UPI - All Channels", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Merged with CAMed Prefetches : XPT - All Channels", - "EventCode": "0x74", - "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - Ch 0", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 0", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH0_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 0", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - Ch 1", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 1", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH1_XPTUPI", - "PerPkg": "1", - "PublicDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI- Ch 1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - Ch 2", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.CH2_XPTUPI", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT & UPI - All Channels", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPTUPI_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Demands Not Merged with CAMed Prefetches : XPT - All Channels", - "EventCode": "0x75", - "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.ERRORBLK_RxC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.NOT_PF_SAD_REGION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_CAM_HIT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.PF_SECURE_DROP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.RPQ_PROXY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.STOP_B2B", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.WPQ_PROXY", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch0 - Reasons", - "EventCode": "0x70", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH0.XPT_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.ERRORBLK_RxC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.NOT_PF_SAD_REGION", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_AD_CRD", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_FULL", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_CAM_HIT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.PF_SECURE_DROP", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.RPQ_PROXY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.STOP_B2B", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.WPQ_PROXY", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Data Prefetches Dropped Ch1 - Reasons", - "EventCode": "0x71", - "EventName": "UNC_M2M_PREFCAM_DROP_REASONS_CH1.XPT_THRESH", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", - "EventCode": "0x6D", - "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", - "PerPkg": "1", - "UMask": "0x15", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : All Channels", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : Channel 0", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Prefetch CAM Occupancy : Channel 1", - "EventCode": "0x6A", - "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": ": All Channels", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", - "PerPkg": "1", - "UMask": "0x7", - "Unit": "M2M" - }, - { - "BriefDescription": ": Channel 0", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": ": Channel 1", - "EventCode": "0x76", - "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", - "EventCode": "0x79", - "EventName": "UNC_M2M_PREFCAM_RxC_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", - "EventCode": "0x7A", - "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_INSERTS", - "EventCode": "0x78", - "EventName": "UNC_M2M_PREFCAM_RxC_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", - "EventCode": "0x77", - "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xAC", - "EventName": "UNC_M2M_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xAA", - "EventName": "UNC_M2M_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xAD", - "EventName": "UNC_M2M_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xAB", - "EventName": "UNC_M2M_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_M2M_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 0", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Regular : Channel 1", - "EventCode": "0x43", - "EventName": "UNC_M2M_RPQ_NO_REG_CRD.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 0", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M to iMC RPQ Cycles w/Credits - Special : Channel 1", - "EventCode": "0x44", - "EventName": "UNC_M2M_RPQ_NO_SPEC_CRD.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Full", - "EventCode": "0x04", - "EventName": "UNC_M2M_RxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Not Empty", - "EventCode": "0x03", - "EventName": "UNC_M2M_RxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Allocations", - "EventCode": "0x01", - "EventName": "UNC_M2M_RxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy", - "EventCode": "0x02", - "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", - "EventCode": "0x77", - "EventName": "UNC_M2M_RxC_AD_PREF_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x5C", - "EventName": "UNC_M2M_RxC_AK_WR_CMP", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Full", - "EventCode": "0x08", - "EventName": "UNC_M2M_RxC_BL_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Not Empty", - "EventCode": "0x07", - "EventName": "UNC_M2M_RxC_BL_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Allocations", - "EventCode": "0x05", - "EventName": "UNC_M2M_RxC_BL_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Ingress (from CMS) Occupancy", - "EventCode": "0x06", - "EventName": "UNC_M2M_RxC_BL_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE5", - "EventName": "UNC_M2M_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xE2", - "EventName": "UNC_M2M_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xE3", - "EventName": "UNC_M2M_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_M2M_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xE1", - "EventName": "UNC_M2M_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xE0", - "EventName": "UNC_M2M_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD0", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD2", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xD4", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xD6", - "EventName": "UNC_M2M_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD1", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD3", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xD5", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xD7", - "EventName": "UNC_M2M_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Number AD Ingress Credits", - "EventCode": "0x41", - "EventName": "UNC_M2M_TGR_AD_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Number BL Ingress Credits", - "EventCode": "0x42", - "EventName": "UNC_M2M_TGR_BL_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full : Channel 0", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Full : Channel 1", - "EventCode": "0x45", - "EventName": "UNC_M2M_TRACKER_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 0", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Inserts : Channel 1", - "EventCode": "0x49", - "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty : Channel 0", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Cycles Not Empty : Channel 1", - "EventCode": "0x46", - "EventName": "UNC_M2M_TRACKER_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 0", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Tracker Occupancy : Channel 1", - "EventCode": "0x47", - "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credit Acquired", - "EventCode": "0x0d", - "EventName": "UNC_M2M_TxC_AD_CREDITS_ACQUIRED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Credits Occupancy", - "EventCode": "0x0e", - "EventName": "UNC_M2M_TxC_AD_CREDIT_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Full", - "EventCode": "0x0c", - "EventName": "UNC_M2M_TxC_AD_CYCLES_FULL", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Not Empty", - "EventCode": "0x0b", - "EventName": "UNC_M2M_TxC_AD_CYCLES_NE", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Allocations", - "EventCode": "0x09", - "EventName": "UNC_M2M_TxC_AD_INSERTS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AD Egress (to CMS) Credits", - "EventCode": "0x0f", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_CYCLES", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AD Egress (to CMS) Credits", - "EventCode": "0x10", - "EventName": "UNC_M2M_TxC_AD_NO_CREDIT_STALLED", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AD Egress (to CMS) Occupancy", - "EventCode": "0x0A", - "EventName": "UNC_M2M_TxC_AD_OCCUPANCY", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK : CRD Transactions to Cbo", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.CRD_CBO", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound Ring Transactions on AK : NDR Transactions", - "EventCode": "0x39", - "EventName": "UNC_M2M_TxC_AK.NDR", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AKC Credits", - "EventCode": "0x5F", - "EventName": "UNC_M2M_TxC_AKC_CREDITS", - "PerPkg": "1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", - "EventCode": "0x1D", - "EventName": "UNC_M2M_TxC_AK_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : All", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Near Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full : Common Mesh Stop - Far Side", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD0", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.RDCRD1", - "PerPkg": "1", - "UMask": "0x88", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP0", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCMP1", - "PerPkg": "1", - "UMask": "0xa0", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD0", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Full", - "EventCode": "0x14", - "EventName": "UNC_M2M_TxC_AK_CYCLES_FULL.WRCRD1", - "PerPkg": "1", - "UMask": "0x90", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : All", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Not Empty", - "EventCode": "0x13", - "EventName": "UNC_M2M_TxC_AK_CYCLES_NE.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : All", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Near Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations : Common Mesh Stop - Far Side", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.PREF_RD_CAM_HIT", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Allocations", - "EventCode": "0x11", - "EventName": "UNC_M2M_TxC_AK_INSERTS.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1F", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No AK Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x20", - "EventName": "UNC_M2M_TxC_AK_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : All", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.RDCRD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCMP", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "AK Egress (to CMS) Occupancy", - "EventCode": "0x12", - "EventName": "UNC_M2M_TxC_AK_OCCUPANCY.WRCRD", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Cache", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CACHE", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Outbound DRS Ring Transactions to Cache : Data to Core", - "EventCode": "0x40", - "EventName": "UNC_M2M_TxC_BL.DRS_CORE", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Near Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Credit Acquired : Common Mesh Stop - Far Side", - "EventCode": "0x19", - "EventName": "UNC_M2M_TxC_BL_CREDITS_ACQUIRED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : All", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Near Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Full : Common Mesh Stop - Far Side", - "EventCode": "0x18", - "EventName": "UNC_M2M_TxC_BL_CYCLES_FULL.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : All", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Near Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Not Empty : Common Mesh Stop - Far Side", - "EventCode": "0x17", - "EventName": "UNC_M2M_TxC_BL_CYCLES_NE.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : All", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.ALL", - "PerPkg": "1", - "UMask": "0x3", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Near Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "BL Egress (to CMS) Allocations : Common Mesh Stop - Far Side", - "EventCode": "0x15", - "EventName": "UNC_M2M_TxC_BL_INSERTS.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1B", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_CYCLES.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Near Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles Stalled with No BL Egress (to CMS) Credits : Common Mesh Stop - Far Side", - "EventCode": "0x1C", - "EventName": "UNC_M2M_TxC_BL_NO_CREDIT_STALLED.CMS1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xA6", - "EventName": "UNC_M2M_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xA7", - "EventName": "UNC_M2M_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xA2", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xA3", - "EventName": "UNC_M2M_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xA1", - "EventName": "UNC_M2M_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xA4", - "EventName": "UNC_M2M_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xA0", - "EventName": "UNC_M2M_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xA5", - "EventName": "UNC_M2M_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9C", - "EventName": "UNC_M2M_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9D", - "EventName": "UNC_M2M_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9E", - "EventName": "UNC_M2M_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_M2M_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2M_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2M_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_M2M_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_M2M_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2M_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9A", - "EventName": "UNC_M2M_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9B", - "EventName": "UNC_M2M_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xB0", - "EventName": "UNC_M2M_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xB4", - "EventName": "UNC_M2M_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xB1", - "EventName": "UNC_M2M_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xB2", - "EventName": "UNC_M2M_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xB3", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xB3", - "EventName": "UNC_M2M_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xB5", - "EventName": "UNC_M2M_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "WPQ Flush : Channel 0", - "EventCode": "0x58", - "EventName": "UNC_M2M_WPQ_FLUSH.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "WPQ Flush : Channel 1", - "EventCode": "0x58", - "EventName": "UNC_M2M_WPQ_FLUSH.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 2", - "EventCode": "0x4D", - "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 2", - "EventCode": "0x4E", - "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Channel 0", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Channel 1", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Full : Mirror", - "EventCode": "0x4A", - "EventName": "UNC_M2M_WR_TRACKER_FULL.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts : Channel 0", - "EventCode": "0x56", - "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Inserts : Channel 1", - "EventCode": "0x56", - "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Cycles Not Empty", - "EventCode": "0x4B", - "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", - "EventCode": "0x63", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", - "EventCode": "0x63", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", - "EventCode": "0x62", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", - "EventCode": "0x62", - "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Channel 0", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Channel 1", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy : Mirror", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_NONTGR", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Occupancy", - "EventCode": "0x55", - "EventName": "UNC_M2M_WR_TRACKER_OCCUPANCY.MIRR_PWR", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Inserts : Channel 0", - "EventCode": "0x5E", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Inserts : Channel 1", - "EventCode": "0x5E", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", - "EventCode": "0x5D", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2M" - }, - { - "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", - "EventCode": "0x5D", - "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2M" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7", - "EventCode": "0x80", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9", - "EventCode": "0x81", - "EventName": "UNC_M2P_AG0_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 0 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x82", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x83", - "EventName": "UNC_M2P_AG0_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 6 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7", - "EventCode": "0x88", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 7 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9", - "EventCode": "0x89", - "EventName": "UNC_M2P_AG0_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 0 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8a", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8b", - "EventName": "UNC_M2P_AG0_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent0 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 0 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 0 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 1 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 2 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 3 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 4 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 5 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 6 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7", - "EventCode": "0x84", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 7 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 10 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 8 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9", - "EventCode": "0x85", - "EventName": "UNC_M2P_AG1_AD_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Acquired : For Transgress 9 : Number of CMS Agent 1 AD credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7", - "EventCode": "0x86", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9", - "EventCode": "0x87", - "EventName": "UNC_M2P_AG1_AD_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 AD Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 AD credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 0 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 1 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 2 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 3 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 4 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5", - "EventCode": "0x8c", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 5 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 10 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 8 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9", - "EventCode": "0x8d", - "EventName": "UNC_M2P_AG1_BL_CRD_ACQUIRED1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Acquired : For Transgress 9 : Number of CMS Agent 1 BL credits acquired in a given cycle, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR0", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 0 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR1", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 1 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR2", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 2 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR3", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 3 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR4", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 4 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR5", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 5 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR6", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 6 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7", - "EventCode": "0x8e", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY0.TGR7", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 7 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR10", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 10 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR8", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 8 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9", - "EventCode": "0x8f", - "EventName": "UNC_M2P_AG1_BL_CRD_OCCUPANCY1.TGR9", - "PerPkg": "1", - "PublicDescription": "CMS Agent1 BL Credits Occupancy : For Transgress 9 : Number of CMS Agent 1 BL credits in use in a given cycle, per transgress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Clockticks of the mesh to PCI (M2P)", - "EventCode": "0x01", - "EventName": "UNC_M2P_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Clockticks", - "EventCode": "0xc0", - "EventName": "UNC_M2P_CMS_CLOCKTICKS", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Local", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_LOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Local : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle triggered by this tile", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Remote", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_NONLOCAL", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Remote : Counts the number of cycles either the local or incoming distress signals are asserted. : Dynamic Prefetch Throttle received by this tile", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - IV", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_IV", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - IV : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while regular IVs were received, causing DPT to be stalled", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : DPT Stalled - No Credit", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.DPT_STALL_NOCRD", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : DPT Stalled - No Credit : Counts the number of cycles either the local or incoming distress signals are asserted. : DPT occurred while credit not available causing DPT to be stalled", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : Horizontal", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.HORZ", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Horizontal : Counts the number of cycles either the local or incoming distress signals are asserted. : If TGR egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Distress signal asserted : Vertical", - "EventCode": "0xaf", - "EventName": "UNC_M2P_DISTRESS_ASSERTED.VERT", - "PerPkg": "1", - "PublicDescription": "Distress signal asserted : Vertical : Counts the number of cycles either the local or incoming distress signals are asserted. : If IRQ egress is full, then agents will throttle outgoing AD IDI transactions", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Down", - "EventCode": "0xba", - "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress Blocking due to Ordering requirements : Up", - "EventCode": "0xba", - "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", - "PerPkg": "1", - "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Even", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Left and Odd", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Even", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AD Ring In Use : Right and Odd", - "EventCode": "0xb6", - "EventName": "UNC_M2P_HORZ_RING_AD_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AD Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xbb", - "EventName": "UNC_M2P_HORZ_RING_AKC_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Even", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Left and Odd", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Left and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Even", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Even : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal AK Ring In Use : Right and Odd", - "EventCode": "0xb7", - "EventName": "UNC_M2P_HORZ_RING_AK_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal AK Ring In Use : Right and Odd : Counts the number of cycles that the Horizontal AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Even", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Left and Odd", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.LEFT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Left and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Even", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_EVEN", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Even : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal BL Ring in Use : Right and Odd", - "EventCode": "0xb8", - "EventName": "UNC_M2P_HORZ_RING_BL_IN_USE.RIGHT_ODD", - "PerPkg": "1", - "PublicDescription": "Horizontal BL Ring in Use : Right and Odd : Counts the number of cycles that the Horizontal BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Left", - "EventCode": "0xb9", - "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.LEFT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Left : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Horizontal IV Ring in Use : Right", - "EventCode": "0xb9", - "EventName": "UNC_M2P_HORZ_RING_IV_IN_USE.RIGHT", - "PerPkg": "1", - "PublicDescription": "Horizontal IV Ring in Use : Right : Counts the number of cycles that the Horizontal IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", - "EventCode": "0x33", - "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", - "EventCode": "0x34", - "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", - "EventCode": "0x32", - "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", - "PerPkg": "1", - "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", - "EventCode": "0x46", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", - "EventCode": "0x47", - "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", - "EventCode": "0x19", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", - "EventCode": "0x1a", - "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent0", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent1", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local P2P Shared Credits Returned : Agent2", - "EventCode": "0x17", - "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", - "EventCode": "0x44", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", - "EventCode": "0x40", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", - "EventCode": "0x41", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", - "EventCode": "0x4a", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", - "EventCode": "0x4b", - "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI0", - "EventCode": "0xe6", - "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Miscellaneous Events (mostly from MS2IDI) : Number of cycles MBE is high for MS2IDI1", - "EventCode": "0xe6", - "EventName": "UNC_M2P_MISC_EXTERNAL.MBE_INST1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : All", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Local NCB", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Local NCS", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Remote NCB", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "P2P Credit Occupancy : Remote NCS", - "EventCode": "0x14", - "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : All", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Local NCB", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Local NCS", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Remote NCB", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Dedicated Credits Received : Remote NCS", - "EventCode": "0x16", - "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : All", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Local NCB", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Local NCS", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Remote NCB", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Shared Credits Received : Remote NCS", - "EventCode": "0x15", - "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", - "EventCode": "0x18", - "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", - "EventCode": "0x45", - "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AD", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AD : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : AK", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : AK : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : BL", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : BL : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Horizontal Ring. : IV", - "EventCode": "0xac", - "EventName": "UNC_M2P_RING_BOUNCES_HORZ.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Horizontal Ring. : IV : Number of cycles incoming messages from the Horizontal ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : AD", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AD", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : AD : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AK", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Acknowledgements to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring.", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.AKC", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.BL", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Data Responses to core : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache.", - "EventCode": "0xaa", - "EventName": "UNC_M2P_RING_BOUNCES_VERT.IV", - "PerPkg": "1", - "PublicDescription": "Messages that bounced on the Vertical Ring. : Snoops of processor's cache. : Number of cycles incoming messages from the Vertical ring that were bounced, by ring type.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AD", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : AK", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : Acknowledgements to Agent 1", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.AK_AG1", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : BL", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Horizontal Ring : IV", - "EventCode": "0xad", - "EventName": "UNC_M2P_RING_SINK_STARVED_HORZ.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : AD", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AD", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Acknowledgements to core", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AK", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.AKC", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Data Responses to core", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.BL", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Sink Starvation on Vertical Ring : Snoops of processor's cache.", - "EventCode": "0xab", - "EventName": "UNC_M2P_RING_SINK_STARVED_VERT.IV", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Source Throttle", - "EventCode": "0xae", - "EventName": "UNC_M2P_RING_SRC_THRTL", - "PerPkg": "1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", - "EventCode": "0x10", - "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.ALL", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Ingress (from CMS) Queue Inserts", - "EventCode": "0x11", - "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", - "PerPkg": "1", - "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xe5", - "EventName": "UNC_M2P_RxR_BUSY_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, because a message from the other queue has higher priority", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - All", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Credited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AD - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AD - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AK", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AK : Number of packets bypassing the CMS Ingress", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : AKC - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : AKC - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - All", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - All : Number of packets bypassing the CMS Ingress : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Credited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Credited : Number of packets bypassing the CMS Ingress", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : BL - Uncredited", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : BL - Uncredited : Number of packets bypassing the CMS Ingress", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Bypass : IV", - "EventCode": "0xe2", - "EventName": "UNC_M2P_RxR_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Bypass : IV : Number of packets bypassing the CMS Ingress", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - All", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AD - Uncredited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AD - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : AK", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : AK : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - All", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - All : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : BL - Uncredited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : BL - Uncredited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : IFV - Credited", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.IFV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IFV - Credited : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation : IV", - "EventCode": "0xe3", - "EventName": "UNC_M2P_RxR_CRD_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : IV : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Injection Starvation", - "EventCode": "0xe4", - "EventName": "UNC_M2P_RxR_CRD_STARVED_1", - "PerPkg": "1", - "PublicDescription": "Transgress Injection Starvation : Counts cycles under injection starvation mode. This starvation is triggered when the CMS Ingress cannot send a transaction onto the mesh for a long period of time. In this case, the Ingress is unable to forward to the Egress due to a lack of credit.", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - All", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Credited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AD - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AD - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AK", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AK : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : AKC - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : AKC - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - All", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - All : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Credited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Credited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : BL - Uncredited", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : BL - Uncredited : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Allocations : IV", - "EventCode": "0xe1", - "EventName": "UNC_M2P_RxR_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Allocations : IV : Number of allocations into the CMS Ingress The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - All", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Credited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AD - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AD - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AK", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AK : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : AKC - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : AKC - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - All", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - All : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Credited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Credited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : BL - Uncredited", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : BL - Uncredited : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Transgress Ingress Occupancy : IV", - "EventCode": "0xe0", - "EventName": "UNC_M2P_RxR_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "Transgress Ingress Occupancy : IV : Occupancy event for the Ingress buffers in the CMS The Ingress is used to queue up requests received from the mesh", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xd0", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 0 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 1 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 2 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 3 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 4 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 5 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 6 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xd2", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_AD_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 7 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7", - "EventCode": "0xd4", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG0.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR0", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 0 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR1", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 1 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR2", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 2 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR3", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 3 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR4", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 4 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR5", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 5 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR6", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 6 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7", - "EventCode": "0xd6", - "EventName": "UNC_M2P_STALL0_NO_TxR_HORZ_CRD_BL_AG1.TGR7", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 7 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xd1", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG0.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent0 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 10 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 8 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xd3", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_AD_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No AD Agent1 Transgress Credits : For Transgress 9 : Number of cycles the AD Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9", - "EventCode": "0xd5", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG0_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent0 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 0 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR10", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 10 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR8", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 8 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9", - "EventCode": "0xd7", - "EventName": "UNC_M2P_STALL1_NO_TxR_HORZ_CRD_BL_AG1_1.TGR9", - "PerPkg": "1", - "PublicDescription": "Stall on No BL Agent1 Transgress Credits : For Transgress 9 : Number of cycles the BL Agent 1 Egress Buffer is stalled waiting for a TGR credit to become available, per transgress.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", - "EventCode": "0x2d", - "EventName": "UNC_M2P_TxC_CREDITS.PRQ", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.AK_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Full", - "EventCode": "0x25", - "EventName": "UNC_M2P_TxC_CYCLES_FULL.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.AK_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Cycles Not Empty", - "EventCode": "0x23", - "EventName": "UNC_M2P_TxC_CYCLES_NE.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.AK_CRD_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.BL_0", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Egress (to CMS) Ingress", - "EventCode": "0x24", - "EventName": "UNC_M2P_TxC_INSERTS.BL_1", - "PerPkg": "1", - "PublicDescription": "Egress (to CMS) Ingress : Counts the number of number of messages inserted into the the M2PCIe Egress queue. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - All", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Credited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : AD - Uncredited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : AD - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - All", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - All : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Credited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Credited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal ADS Used : BL - Uncredited", - "EventCode": "0xa6", - "EventName": "UNC_M2P_TxR_HORZ_ADS_USED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal ADS Used : BL - Uncredited : Number of packets using the Horizontal Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - All", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Credited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AD - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AD - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AK", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AK : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : AKC - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : AKC - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - All", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - All : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Credited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Credited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : BL - Uncredited", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : BL - Uncredited : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Bypass Used : IV", - "EventCode": "0xa7", - "EventName": "UNC_M2P_TxR_HORZ_BYPASS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Bypass Used : IV : Number of packets bypassing the Horizontal Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AK", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AK : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Full : IV", - "EventCode": "0xa2", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_FULL.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Full : IV : Cycles the Transgress buffers in the Common Mesh Stop are Full. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AD - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AK", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AK : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : AKC - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_ALL", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - All : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_CRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Credited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : BL - Uncredited : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV", - "EventCode": "0xa3", - "EventName": "UNC_M2P_TxR_HORZ_CYCLES_NE.IV", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Horizontal Egress Queue is Not Empty : IV : Cycles the Transgress buffers in the Common Mesh Stop are Not-Empty. The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - All", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Credited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AD - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AD - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AK", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AK : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : AKC - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - All", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - All : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Credited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Credited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : BL - Uncredited", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : BL - Uncredited : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Inserts : IV", - "EventCode": "0xa1", - "EventName": "UNC_M2P_TxR_HORZ_INSERTS.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Inserts : IV : Number of allocations into the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - All", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Credited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AD - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AD - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AK", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AK : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : AKC - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - All", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - All : Counts number of Egress packets NACK'ed on to the Horizontal Ring : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Credited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Credited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : BL - Uncredited", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : BL - Uncredited : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress NACKs : IV", - "EventCode": "0xa4", - "EventName": "UNC_M2P_TxR_HORZ_NACK.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Horizontal Ring", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - All", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x11", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Credited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AD - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AK", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AK : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : AKC - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - All", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - All : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh. : All == Credited + Uncredited", - "UMask": "0x44", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Credited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_CRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Credited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : BL - Uncredited : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Occupancy : IV", - "EventCode": "0xa0", - "EventName": "UNC_M2P_TxR_HORZ_OCCUPANCY.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Occupancy : IV : Occupancy event for the Transgress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Horizontal Ring on the Mesh.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - All", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AD_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AD - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AK", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AK", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AK : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.AKC_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : AKC - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x80", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - All", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_ALL", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - All : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time. : All == Credited + Uncredited", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.BL_UNCRD", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : BL - Uncredited : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Horizontal Egress Injection Starvation : IV", - "EventCode": "0xa5", - "EventName": "UNC_M2P_TxR_HORZ_STARVED.IV", - "PerPkg": "1", - "PublicDescription": "CMS Horizontal Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Transgress buffer cannot send a transaction onto the Horizontal ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9c", - "EventName": "UNC_M2P_TxR_VERT_ADS_USED.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets using the Vertical Anti-Deadlock Slot, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AD - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AD - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AK - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AK - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 0", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : BL - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : BL - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : IV - Agent 1", - "EventCode": "0x9d", - "EventName": "UNC_M2P_TxR_VERT_BYPASS.IV_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : IV - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 0", - "EventCode": "0x9e", - "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 0 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical ADS Used : AKC - Agent 1", - "EventCode": "0x9e", - "EventName": "UNC_M2P_TxR_VERT_BYPASS_1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical ADS Used : AKC - Agent 1 : Number of packets bypassing the Vertical Egress, broken down by ring type and CMS Agent.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0", - "EventCode": "0x94", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0", - "EventCode": "0x95", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1", - "EventCode": "0x95", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_FULL1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Full : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Full. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AD - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AK - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : BL - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0", - "EventCode": "0x96", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : IV - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0", - "EventCode": "0x97", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 0 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1", - "EventCode": "0x97", - "EventName": "UNC_M2P_TxR_VERT_CYCLES_NE1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "Cycles CMS Vertical Egress Queue Is Not Empty : AKC - Agent 1 : Number of cycles the Common Mesh Stop Egress was Not Empty. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AD - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AD - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AK - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AK - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : BL - Agent 1", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : BL - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : IV - Agent 0", - "EventCode": "0x92", - "EventName": "UNC_M2P_TxR_VERT_INSERTS0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : IV - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 0", - "EventCode": "0x93", - "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 0 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Allocations : AKC - Agent 1", - "EventCode": "0x93", - "EventName": "UNC_M2P_TxR_VERT_INSERTS1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Allocations : AKC - Agent 1 : Number of allocations into the Common Mesh Stop Egress. The Egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AD - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AD - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AK - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AK - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 0", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : BL - Agent 1", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : BL - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : IV", - "EventCode": "0x98", - "EventName": "UNC_M2P_TxR_VERT_NACK0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : IV : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 0", - "EventCode": "0x99", - "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 0 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress NACKs : AKC - Agent 1", - "EventCode": "0x99", - "EventName": "UNC_M2P_TxR_VERT_NACK1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress NACKs : AKC - Agent 1 : Counts number of Egress packets NACK'ed on to the Vertical Ring", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AD - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AD - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AD ring. This is commonly used for outbound requests.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AK - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AK - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the AK ring.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the BL ring. This is commonly used to send data from the cache to various destinations.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : BL - Agent 1", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : BL - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 1 destined for the BL ring. This is commonly used for transferring writeback data to the cache.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : IV - Agent 0", - "EventCode": "0x90", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : IV - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the IV ring. This is commonly used for snoops to the cores.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 0", - "EventCode": "0x91", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 0 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AD ring. Some example include outbound requests, snoop requests, and snoop responses.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vert Egress Occupancy : AKC - Agent 1", - "EventCode": "0x91", - "EventName": "UNC_M2P_TxR_VERT_OCCUPANCY1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vert Egress Occupancy : AKC - Agent 1 : Occupancy event for the Egress buffers in the Common Mesh Stop The egress is used to queue up requests destined for the Vertical Ring on the Mesh. : Ring transactions from Agent 0 destined for the AK ring. This is commonly used for credit returns and GO responses.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AD_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AD - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x10", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.AK_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AK - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x20", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.BL_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : BL - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x40", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : IV", - "EventCode": "0x9a", - "EventName": "UNC_M2P_TxR_VERT_STARVED0.IV_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : IV : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG0", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.AKC_AG1", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 1 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0", - "EventCode": "0x9b", - "EventName": "UNC_M2P_TxR_VERT_STARVED1.TGC", - "PerPkg": "1", - "PublicDescription": "CMS Vertical Egress Injection Starvation : AKC - Agent 0 : Counts injection starvation. This starvation is triggered when the CMS Egress cannot send a transaction onto the Vertical ring for a long period of time.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Even", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Down and Odd", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Even", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Even : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AD Ring In Use : Up and Odd", - "EventCode": "0xb0", - "EventName": "UNC_M2P_VERT_RING_AD_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AD Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Even", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Down and Odd", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Even", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Even : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AKC Ring In Use : Up and Odd", - "EventCode": "0xb4", - "EventName": "UNC_M2P_VERT_RING_AKC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AKC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AKC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Even", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Down and Odd", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Down and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Even", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Even : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical AK Ring In Use : Up and Odd", - "EventCode": "0xb1", - "EventName": "UNC_M2P_VERT_RING_AK_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical AK Ring In Use : Up and Odd : Counts the number of cycles that the Vertical AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Even", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Down and Odd", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Down and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Even", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Even : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical BL Ring in Use : Up and Odd", - "EventCode": "0xb2", - "EventName": "UNC_M2P_VERT_RING_BL_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical BL Ring in Use : Up and Odd : Counts the number of cycles that the Vertical BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Down", - "EventCode": "0xb3", - "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.DN", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Down : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical IV Ring in Use : Up", - "EventCode": "0xb3", - "EventName": "UNC_M2P_VERT_RING_IV_IN_USE.UP", - "PerPkg": "1", - "PublicDescription": "Vertical IV Ring in Use : Up : Counts the number of cycles that the Vertical IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop. There is only 1 IV ring. Therefore, if one wants to monitor the Even ring, they should select both UP_EVEN and DN_EVEN. To monitor the Odd ring, they should select both UP_ODD and DN_ODD.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Even", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x4", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Down and Odd", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.DN_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Down and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x8", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Even", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_EVEN", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Even : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x1", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Vertical TGC Ring In Use : Up and Odd", - "EventCode": "0xb5", - "EventName": "UNC_M2P_VERT_RING_TGC_IN_USE.UP_ODD", - "PerPkg": "1", - "PublicDescription": "Vertical TGC Ring In Use : Up and Odd : Counts the number of cycles that the Vertical TGC ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.We really have two rings in JKT -- a clockwise ring and a counter-clockwise ring. On the left side of the ring, the UP direction is on the clockwise ring and DN is on the counter-clockwise ring. On the right side of the ring, this is reversed. The first half of the CBos are on the left side of the ring, and the 2nd half are on the right side of the ring. In other words (for example), in a 4c part, Cbo 0 UP AD is NOT the same ring as CBo 2 UP AD because they are on opposite sides of the ring.", - "UMask": "0x2", - "Unit": "M2PCIe" - }, - { - "BriefDescription": "Clockticks in the UBOX using a dedicated 48-bit Fixed Counter", - "EventCode": "0xff", - "EventName": "UNC_U_CLOCKTICKS", - "PerPkg": "1", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : Doorbell", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : Interrupt", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.INT_PRIO", - "PerPkg": "1", - "PublicDescription": "Message Received : Interrupt : Interrupts", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : IPI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : MSI", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Message Received : VLW", - "EventCode": "0x42", - "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", - "PerPkg": "1", - "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "IDI Lock/SplitLock Cycles", - "EventCode": "0x44", - "EventName": "UNC_U_LOCK_CYCLES", - "PerPkg": "1", - "PublicDescription": "IDI Lock/SplitLock Cycles : Number of times an IDI Lock/SplitLock sequence was started", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", - "EventCode": "0x4D", - "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", - "PerPkg": "1", - "UMask": "0x8", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", - "PerPkg": "1", - "UMask": "0x20", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", - "PerPkg": "1", - "UMask": "0x40", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", - "PerPkg": "1", - "UMask": "0x10", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", - "EventCode": "0x4E", - "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", - "PerPkg": "1", - "UMask": "0x80", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", - "EventCode": "0x4F", - "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", - "EventCode": "0x4F", - "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", - "EventCode": "0x45", - "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", - "PerPkg": "1", - "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", - "PerPkg": "1", - "UMask": "0x4", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDRAND", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "UBOX" - }, - { - "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", - "EventCode": "0x4C", - "EventName": "UNC_U_RACU_DRNG.RDSEED", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "UBOX" - }, - { - "BriefDescription": "RACU Request", - "EventCode": "0x46", - "EventName": "UNC_U_RACU_REQUESTS", - "PerPkg": "1", - "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", - "Unit": "UBOX" - } -] -- GitLab From ee31f6fea61c332100d2161081abbdfe65411fe9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 13 Apr 2023 06:29:49 -0700 Subject: [PATCH 3009/5631] perf vendor events intel: Fix uncore topics for tigerlake Move events from 'uncore-other' topic classification to interconnect. Signed-off-by: Ian Rogers Cc: Alexander Shishkin Cc: Caleb Biggers Cc: Edward Baker Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Xing Zhengjun Link: https://lore.kernel.org/r/20230413132949.3487664-22-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../x86/tigerlake/uncore-interconnect.json | 90 +++++++++++++++++++ .../arch/x86/tigerlake/uncore-other.json | 88 ------------------ 2 files changed, 90 insertions(+), 88 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json new file mode 100644 index 000000000000..eed1b90a2779 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-interconnect.json @@ -0,0 +1,90 @@ +[ + { + "BriefDescription": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "EventCode": "0x84", + "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", + "EventCode": "0x81", + "EventName": "UNC_ARB_DAT_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", + "EventCode": "0x85", + "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from it's allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + } +] diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json index 6e43aaf64e28..c6596ba09195 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/uncore-other.json @@ -1,92 +1,4 @@ [ - { - "BriefDescription": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "EventCode": "0x84", - "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", - "EventCode": "0x85", - "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", - "EventCode": "0x81", - "EventName": "UNC_ARB_DAT_REQUESTS.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", - "EventCode": "0x85", - "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", - "EventCode": "0x80", - "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", - "EventCode": "0x81", - "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from it's allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", - "EventCode": "0x80", - "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, - { - "BriefDescription": "UNC_ARB_TRK_REQUESTS.ALL", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.ALL", - "PerPkg": "1", - "UMask": "0x1", - "Unit": "ARB" - }, - { - "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", - "EventCode": "0x81", - "EventName": "UNC_ARB_TRK_REQUESTS.RD", - "PerPkg": "1", - "UMask": "0x2", - "Unit": "ARB" - }, { "BriefDescription": "UNC_CLOCK.SOCKET", "EventCode": "0xff", -- GitLab From c160118a90d4acf335993d8d59b02ae2147a524e Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Thu, 13 Apr 2023 14:46:39 +0200 Subject: [PATCH 3010/5631] perf map: Delete two variable initialisations before null pointer checks in sort__sym_from_cmp() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Addresses of two data structure members were determined before corresponding null pointer checks in the implementation of the function “sort__sym_from_cmp”. Thus avoid the risk for undefined behaviour by removing extra initialisations for the local variables “from_l” and “from_r” (also because they were already reassigned with the same value behind this pointer check). This issue was detected by using the Coccinelle software. Fixes: 1b9e97a2a95e4941 ("perf tools: Fix report -F symbol_from for data without branch info") Signed-off-by: Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: German Gomez Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Link: https://lore.kernel.org/cocci/54a21fea-64e3-de67-82ef-d61b90ffad05@web.de/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 80c9960c37e5..f2ffaf90648e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1020,8 +1020,7 @@ static int hist_entry__dso_to_filter(struct hist_entry *he, int type, static int64_t sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right) { - struct addr_map_symbol *from_l = &left->branch_info->from; - struct addr_map_symbol *from_r = &right->branch_info->from; + struct addr_map_symbol *from_l, *from_r; if (!left->branch_info || !right->branch_info) return cmp_null(left->branch_info, right->branch_info); -- GitLab From 7455b7007b9e93bcc2bc9c1c6c73a228e3152069 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 13 Apr 2023 23:20:45 +0100 Subject: [PATCH 3011/5631] clk: microchip: fix potential UAF in auxdev release callback Similar to commit 1c11289b34ab ("peci: cpu: Fix use-after-free in adev_release()"), the auxiliary device is not torn down in the correct order. If auxiliary_device_add() fails, the release callback will be called twice, resulting in a UAF. Due to timing, the auxdev code in this driver "took inspiration" from the aforementioned commit, and thus its bugs too! Moving auxiliary_device_uninit() to the unregister callback instead avoids the issue. CC: stable@vger.kernel.org Fixes: b56bae2dd6fd ("clk: microchip: mpfs: add reset controller") Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230413-critter-synopsis-dac070a86cb4@spud Signed-off-by: Stephen Boyd --- drivers/clk/microchip/clk-mpfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/clk/microchip/clk-mpfs.c b/drivers/clk/microchip/clk-mpfs.c index 4f0a19db7ed7..cc5d7dee59f0 100644 --- a/drivers/clk/microchip/clk-mpfs.c +++ b/drivers/clk/microchip/clk-mpfs.c @@ -374,14 +374,13 @@ static void mpfs_reset_unregister_adev(void *_adev) struct auxiliary_device *adev = _adev; auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); } static void mpfs_reset_adev_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); - auxiliary_device_uninit(adev); - kfree(adev); } -- GitLab From d1aae06630230daf747ef5bc291c19ea7f046129 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 13 Apr 2023 13:55:28 -0700 Subject: [PATCH 3012/5631] clk: starfive: Avoid casting iomem pointers Let's use a wrapper struct for the auxiliary_device made in jh7110_reset_controller_register() so that we can stop casting iomem pointers. The casts trip up tools like sparse, and make for some awkward casts that are largely unnecessary. While we're here, change the allocation from devm and actually free the auxiliary_device memory in the release function. This avoids any use after free problems where the parent device driver is unbound from the device but the auxiliuary_device is still in use accessing devm freed memory. Cc: Tommaso Merciai Cc: Emil Renner Berthing Cc: Hal Feng Cc: Conor Dooley Cc: Xingyu Wu Reviewed-by: Conor Dooley Fixes: edab7204afe5 ("clk: starfive: Add StarFive JH7110 system clock driver") Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413205528.4044216-1-sboyd@kernel.org --- drivers/clk/starfive/clk-starfive-jh7110-sys.c | 15 ++++++++++++--- drivers/reset/starfive/reset-starfive-jh7110.c | 9 ++++++--- include/soc/starfive/reset-starfive-jh71x0.h | 17 +++++++++++++++++ 3 files changed, 35 insertions(+), 6 deletions(-) create mode 100644 include/soc/starfive/reset-starfive-jh71x0.h diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c index 5ec210644e1d..851b93d0f371 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-sys.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c @@ -11,6 +11,9 @@ #include #include #include +#include + +#include #include @@ -335,26 +338,32 @@ static void jh7110_reset_unregister_adev(void *_adev) struct auxiliary_device *adev = _adev; auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); } static void jh7110_reset_adev_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); + struct jh71x0_reset_adev *rdev = to_jh71x0_reset_adev(adev); - auxiliary_device_uninit(adev); + kfree(rdev); } int jh7110_reset_controller_register(struct jh71x0_clk_priv *priv, const char *adev_name, u32 adev_id) { + struct jh71x0_reset_adev *rdev; struct auxiliary_device *adev; int ret; - adev = devm_kzalloc(priv->dev, sizeof(*adev), GFP_KERNEL); - if (!adev) + rdev = kzalloc(sizeof(*rdev), GFP_KERNEL); + if (!rdev) return -ENOMEM; + rdev->base = priv->base; + + adev = &rdev->adev; adev->name = adev_name; adev->dev.parent = priv->dev; adev->dev.release = jh7110_reset_adev_release; diff --git a/drivers/reset/starfive/reset-starfive-jh7110.c b/drivers/reset/starfive/reset-starfive-jh7110.c index c1b3a490d951..2d26ae95c8cc 100644 --- a/drivers/reset/starfive/reset-starfive-jh7110.c +++ b/drivers/reset/starfive/reset-starfive-jh7110.c @@ -7,6 +7,8 @@ #include +#include + #include "reset-starfive-jh71x0.h" #include @@ -33,14 +35,15 @@ static int jh7110_reset_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { struct jh7110_reset_info *info = (struct jh7110_reset_info *)(id->driver_data); - void __iomem **base = (void __iomem **)dev_get_drvdata(adev->dev.parent); + struct jh71x0_reset_adev *rdev = to_jh71x0_reset_adev(adev); + void __iomem *base = rdev->base; if (!info || !base) return -ENODEV; return reset_starfive_jh71x0_register(&adev->dev, adev->dev.parent->of_node, - *base + info->assert_offset, - *base + info->status_offset, + base + info->assert_offset, + base + info->status_offset, NULL, info->nr_resets, NULL); diff --git a/include/soc/starfive/reset-starfive-jh71x0.h b/include/soc/starfive/reset-starfive-jh71x0.h new file mode 100644 index 000000000000..47b486ececc5 --- /dev/null +++ b/include/soc/starfive/reset-starfive-jh71x0.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SOC_STARFIVE_RESET_JH71X0_H +#define __SOC_STARFIVE_RESET_JH71X0_H + +#include +#include +#include + +struct jh71x0_reset_adev { + void __iomem *base; + struct auxiliary_device adev; +}; + +#define to_jh71x0_reset_adev(_adev) \ + container_of((_adev), struct jh71x0_reset_adev, adev) + +#endif -- GitLab From 87e5b1e8f257023ac5c4d2b8f07716a7f3dcc8ea Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 31 Mar 2023 17:15:51 +0800 Subject: [PATCH 3013/5631] module: Sync code of is_arm_mapping_symbol() After commit 2e3a10a1551d ("ARM: avoid ARM binutils leaking ELF local symbols") and commit d6b732666a1b ("modpost: fix undefined behavior of is_arm_mapping_symbol()"), many differences of is_arm_mapping_symbol() exist in kernel/module/kallsyms.c and scripts/mod/modpost.c, just sync the code to keep consistent. Signed-off-by: Tiezhu Yang Signed-off-by: Luis Chamberlain --- kernel/module/kallsyms.c | 5 +++-- scripts/mod/modpost.c | 2 ++ 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 3320586584f1..a9045fe55bcd 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -251,8 +251,9 @@ static inline int is_arm_mapping_symbol(const char *str) { if (str[0] == '.' && str[1] == 'L') return true; - return str[0] == '$' && strchr("axtd", str[1]) && - (str[2] == '\0' || str[2] == '.'); + return str[0] == '$' && + (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') + && (str[2] == '\0' || str[2] == '.'); } static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index efff8078e395..79a27cc5f0b1 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1114,6 +1114,8 @@ static int secref_whitelist(const struct sectioncheck *mismatch, static inline int is_arm_mapping_symbol(const char *str) { + if (str[0] == '.' && str[1] == 'L') + return true; return str[0] == '$' && (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') && (str[2] == '\0' || str[2] == '.'); -- GitLab From 987d2e0aaa55de40938435be760aa96428470fd6 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 31 Mar 2023 17:15:52 +0800 Subject: [PATCH 3014/5631] module: Move is_arm_mapping_symbol() to module_symbol.h In order to avoid duplicated code, move is_arm_mapping_symbol() to include/linux/module_symbol.h, then remove is_arm_mapping_symbol() in the other places. Signed-off-by: Tiezhu Yang Signed-off-by: Luis Chamberlain --- include/linux/module_symbol.h | 15 +++++++++++++++ kernel/module/kallsyms.c | 14 +------------- scripts/mod/modpost.c | 10 +--------- 3 files changed, 17 insertions(+), 22 deletions(-) create mode 100644 include/linux/module_symbol.h diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h new file mode 100644 index 000000000000..9fa4173d0197 --- /dev/null +++ b/include/linux/module_symbol.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_MODULE_SYMBOL_H +#define _LINUX_MODULE_SYMBOL_H + +/* This ignores the intensely annoying "mapping symbols" found in ELF files. */ +static inline int is_arm_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + return str[0] == '$' && + (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') + && (str[2] == '\0' || str[2] == '.'); +} + +#endif /* _LINUX_MODULE_SYMBOL_H */ diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index a9045fe55bcd..5de3207f18af 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -243,19 +244,6 @@ void init_build_id(struct module *mod, const struct load_info *info) } #endif -/* - * This ignores the intensely annoying "mapping symbols" found - * in ARM ELF files: $a, $t and $d. - */ -static inline int is_arm_mapping_symbol(const char *str) -{ - if (str[0] == '.' && str[1] == 'L') - return true; - return str[0] == '$' && - (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') - && (str[2] == '\0' || str[2] == '.'); -} - static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) { return kallsyms->strtab + kallsyms->symtab[symnum].st_name; diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 79a27cc5f0b1..7241db81ffde 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -22,6 +22,7 @@ #include #include "modpost.h" #include "../../include/linux/license.h" +#include "../../include/linux/module_symbol.h" /* Are we using CONFIG_MODVERSIONS? */ static bool modversions; @@ -1112,15 +1113,6 @@ static int secref_whitelist(const struct sectioncheck *mismatch, return 1; } -static inline int is_arm_mapping_symbol(const char *str) -{ - if (str[0] == '.' && str[1] == 'L') - return true; - return str[0] == '$' && - (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') - && (str[2] == '\0' || str[2] == '.'); -} - /* * If there's no name there, ignore it; likewise, ignore it if it's * one of the magic symbols emitted used by current ARM tools. -- GitLab From 0a3bf86092c38f7b72c56c6901c78dd302411307 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 31 Mar 2023 17:15:53 +0800 Subject: [PATCH 3015/5631] module: Ignore L0 and rename is_arm_mapping_symbol() The L0 symbol is generated when build module on LoongArch, ignore it in modpost and when looking at module symbols, otherwise we can not see the expected call trace. Now is_arm_mapping_symbol() is not only for ARM, in order to reflect the reality, rename is_arm_mapping_symbol() to is_mapping_symbol(). This is related with commit c17a2538704f ("mksysmap: Fix the mismatch of 'L0' symbols in System.map"). (1) Simple test case [loongson@linux hello]$ cat hello.c #include #include #include static void test_func(void) { pr_info("This is a test\n"); dump_stack(); } static int __init hello_init(void) { pr_warn("Hello, world\n"); test_func(); return 0; } static void __exit hello_exit(void) { pr_warn("Goodbye\n"); } module_init(hello_init); module_exit(hello_exit); MODULE_LICENSE("GPL"); [loongson@linux hello]$ cat Makefile obj-m:=hello.o ccflags-y += -g -Og all: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) modules clean: make -C /lib/modules/$(shell uname -r)/build/ M=$(PWD) clean (2) Test environment system: LoongArch CLFS 5.5 https://github.com/sunhaiyong1978/CLFS-for-LoongArch/releases/tag/5.0 It needs to update grub to avoid booting error "invalid magic number". kernel: 6.3-rc1 with loongson3_defconfig + CONFIG_DYNAMIC_FTRACE=y (3) Test result Without this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [] L0\x01+0x20/0x2c [hello] [] L0\x01+0x20/0x30 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 With this patch: [root@linux hello]# insmod hello.ko [root@linux hello]# dmesg ... Hello, world This is a test ... Call Trace: [<9000000000223728>] show_stack+0x68/0x18c [<90000000013374cc>] dump_stack_lvl+0x60/0x88 [] test_func+0x28/0x34 [hello] [] hello_init+0x28/0x38 [hello] [<900000000022097c>] do_one_initcall+0x88/0x288 [<90000000002df890>] do_init_module+0x54/0x200 [<90000000002e1e18>] __do_sys_finit_module+0xc4/0x114 [<90000000013382e8>] do_syscall+0x7c/0x94 [<9000000000221e3c>] handle_syscall+0xbc/0x158 Signed-off-by: Tiezhu Yang Tested-by: Youling Tang # for LoongArch Signed-off-by: Luis Chamberlain --- include/linux/module_symbol.h | 4 +++- kernel/module/kallsyms.c | 2 +- scripts/mod/modpost.c | 4 ++-- 3 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h index 9fa4173d0197..7ace7ba30203 100644 --- a/include/linux/module_symbol.h +++ b/include/linux/module_symbol.h @@ -3,10 +3,12 @@ #define _LINUX_MODULE_SYMBOL_H /* This ignores the intensely annoying "mapping symbols" found in ELF files. */ -static inline int is_arm_mapping_symbol(const char *str) +static inline int is_mapping_symbol(const char *str) { if (str[0] == '.' && str[1] == 'L') return true; + if (str[0] == 'L' && str[1] == '0') + return true; return str[0] == '$' && (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') && (str[2] == '\0' || str[2] == '.'); diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 5de3207f18af..d8e426a9a0cd 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -289,7 +289,7 @@ static const char *find_kallsyms_symbol(struct module *mod, * and inserted at a whim. */ if (*kallsyms_symbol_name(kallsyms, i) == '\0' || - is_arm_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) + is_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) continue; if (thisval <= addr && thisval > bestval) { diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7241db81ffde..5cddf7623945 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1115,7 +1115,7 @@ static int secref_whitelist(const struct sectioncheck *mismatch, /* * If there's no name there, ignore it; likewise, ignore it if it's - * one of the magic symbols emitted used by current ARM tools. + * one of the magic symbols emitted used by current tools. * * Otherwise if find_symbols_between() returns those symbols, they'll * fail the whitelist tests and cause lots of false alarms ... fixable @@ -1128,7 +1128,7 @@ static inline int is_valid_name(struct elf_info *elf, Elf_Sym *sym) if (!name || !strlen(name)) return 0; - return !is_arm_mapping_symbol(name); + return !is_mapping_symbol(name); } /** -- GitLab From 5c3a7dcce10028c5839864ed475ae7930b03c1e8 Mon Sep 17 00:00:00 2001 From: Srinivasa Rao Mandadapu Date: Fri, 7 Apr 2023 14:52:53 +0530 Subject: [PATCH 3016/5631] dt-bindings: clock: qcom,sc7280-lpasscc: Add qcom,adsp-pil-mode property When this property is set, the remoteproc is used to boot the LPASS and therefore qdsp6ss clocks would be used to bring LPASS out of reset, hence they are directly controlled by the remoteproc. This is a cleanup done to handle overlap of regmap of lpasscc and adsp remoteproc blocks. Signed-off-by: Srinivasa Rao Mandadapu Signed-off-by: Mohammad Rafi Shaik Reviewed-by: Krzysztof Kozlowski Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230407092255.119690-2-quic_mohs@quicinc.com --- .../devicetree/bindings/clock/qcom,sc7280-lpasscc.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscc.yaml b/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscc.yaml index 6151fdebbff8..97c6bd96e0cb 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sc7280-lpasscc.yaml @@ -41,6 +41,12 @@ properties: - const: qdsp6ss - const: top_cc + qcom,adsp-pil-mode: + description: + Indicates if the LPASS would be brought out of reset using + remoteproc peripheral loader. + type: boolean + required: - compatible - reg @@ -60,6 +66,7 @@ examples: reg-names = "qdsp6ss", "top_cc"; clocks = <&gcc GCC_CFG_NOC_LPASS_CLK>; clock-names = "iface"; + qcom,adsp-pil-mode; #clock-cells = <1>; }; ... -- GitLab From 4fc1c2d9a2b7a394f3b873aae5e03bffd8b5cd31 Mon Sep 17 00:00:00 2001 From: Srinivasa Rao Mandadapu Date: Fri, 7 Apr 2023 14:52:54 +0530 Subject: [PATCH 3017/5631] clk: qcom: lpasscc-sc7280: Skip qdsp6ss clock registration The qdsp6ss memory region is being shared by ADSP remoteproc device and lpasscc clock device, hence causing memory conflict. To avoid this, when qdsp6ss clocks are being enabled in remoteproc driver, skip qdsp6ss clock registration if "qcom,adsp-pil-mode" is enabled and also assign max_register value. Fixes: 4ab43d171181 ("clk: qcom: Add lpass clock controller driver for SC7280") Signed-off-by: Srinivasa Rao Mandadapu Signed-off-by: Mohammad Rafi Shaik Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230407092255.119690-3-quic_mohs@quicinc.com --- drivers/clk/qcom/lpasscc-sc7280.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/drivers/clk/qcom/lpasscc-sc7280.c b/drivers/clk/qcom/lpasscc-sc7280.c index 48432010ce24..0df2b29e95e3 100644 --- a/drivers/clk/qcom/lpasscc-sc7280.c +++ b/drivers/clk/qcom/lpasscc-sc7280.c @@ -121,14 +121,18 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev) goto destroy_pm_clk; } - lpass_regmap_config.name = "qdsp6ss"; - desc = &lpass_qdsp6ss_sc7280_desc; - - ret = qcom_cc_probe_by_index(pdev, 0, desc); - if (ret) - goto destroy_pm_clk; + if (!of_property_read_bool(pdev->dev.of_node, "qcom,adsp-pil-mode")) { + lpass_regmap_config.name = "qdsp6ss"; + lpass_regmap_config.max_register = 0x3f; + desc = &lpass_qdsp6ss_sc7280_desc; + + ret = qcom_cc_probe_by_index(pdev, 0, desc); + if (ret) + goto destroy_pm_clk; + } lpass_regmap_config.name = "top_cc"; + lpass_regmap_config.max_register = 0x4; desc = &lpass_cc_top_sc7280_desc; ret = qcom_cc_probe_by_index(pdev, 1, desc); -- GitLab From aad09fc7c4a522892eb64a79627b17a3869936cb Mon Sep 17 00:00:00 2001 From: Mohammad Rafi Shaik Date: Fri, 7 Apr 2023 14:52:55 +0530 Subject: [PATCH 3018/5631] clk: qcom: lpassaudiocc-sc7280: Add required gdsc power domain clks in lpass_cc_sc7280_desc Add GDSCs in lpass_cc_sc7280_desc struct. When qcom,adsp-pil-mode is enabled, GDSCs required to solve dependencies in lpass_audiocc probe(). Fixes: 0cbcfbe50cbf ("clk: qcom: lpass: Handle the regmap overlap of lpasscc and lpass_aon") Signed-off-by: Mohammad Rafi Shaik Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230407092255.119690-4-quic_mohs@quicinc.com --- drivers/clk/qcom/lpassaudiocc-sc7280.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/clk/qcom/lpassaudiocc-sc7280.c b/drivers/clk/qcom/lpassaudiocc-sc7280.c index 1339f9211a14..134eb1529ede 100644 --- a/drivers/clk/qcom/lpassaudiocc-sc7280.c +++ b/drivers/clk/qcom/lpassaudiocc-sc7280.c @@ -696,6 +696,8 @@ static const struct qcom_cc_desc lpass_cc_sc7280_desc = { .config = &lpass_audio_cc_sc7280_regmap_config, .clks = lpass_cc_sc7280_clocks, .num_clks = ARRAY_SIZE(lpass_cc_sc7280_clocks), + .gdscs = lpass_aon_cc_sc7280_gdscs, + .num_gdscs = ARRAY_SIZE(lpass_aon_cc_sc7280_gdscs), }; static const struct qcom_cc_desc lpass_audio_cc_sc7280_desc = { -- GitLab From 1a500e0bc97b6cb3c0d9859e81973b8dd07d1b7b Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 12 Apr 2023 16:48:29 +0300 Subject: [PATCH 3019/5631] clk: qcom: gcc-sm8350: fix PCIe PIPE clocks handling On SM8350 platform the PCIe PIPE clocks require additional handling to function correctly. They are to be switched to the tcxo source before turning PCIe GDSCs off and should be switched to PHY PIPE source once they are working. Switch PCIe PHY clocks to use clk_regmap_phy_mux_ops, which provide support for this dance. Fixes: 44c20c9ed37f ("clk: qcom: gcc: Add clock driver for SM8350") Signed-off-by: Dmitry Baryshkov Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230412134829.3686467-1-dmitry.baryshkov@linaro.org --- drivers/clk/qcom/gcc-sm8350.c | 47 ++++++++++------------------------- 1 file changed, 13 insertions(+), 34 deletions(-) diff --git a/drivers/clk/qcom/gcc-sm8350.c b/drivers/clk/qcom/gcc-sm8350.c index af4a1ea28421..1385a98eb3bb 100644 --- a/drivers/clk/qcom/gcc-sm8350.c +++ b/drivers/clk/qcom/gcc-sm8350.c @@ -17,6 +17,7 @@ #include "clk-regmap.h" #include "clk-regmap-divider.h" #include "clk-regmap-mux.h" +#include "clk-regmap-phy-mux.h" #include "gdsc.h" #include "reset.h" @@ -158,26 +159,6 @@ static const struct clk_parent_data gcc_parent_data_3[] = { { .fw_name = "bi_tcxo" }, }; -static const struct parent_map gcc_parent_map_4[] = { - { P_PCIE_0_PIPE_CLK, 0 }, - { P_BI_TCXO, 2 }, -}; - -static const struct clk_parent_data gcc_parent_data_4[] = { - { .fw_name = "pcie_0_pipe_clk", }, - { .fw_name = "bi_tcxo" }, -}; - -static const struct parent_map gcc_parent_map_5[] = { - { P_PCIE_1_PIPE_CLK, 0 }, - { P_BI_TCXO, 2 }, -}; - -static const struct clk_parent_data gcc_parent_data_5[] = { - { .fw_name = "pcie_1_pipe_clk" }, - { .fw_name = "bi_tcxo" }, -}; - static const struct parent_map gcc_parent_map_6[] = { { P_BI_TCXO, 0 }, { P_GCC_GPLL0_OUT_MAIN, 1 }, @@ -274,32 +255,30 @@ static const struct clk_parent_data gcc_parent_data_14[] = { { .fw_name = "bi_tcxo" }, }; -static struct clk_regmap_mux gcc_pcie_0_pipe_clk_src = { +static struct clk_regmap_phy_mux gcc_pcie_0_pipe_clk_src = { .reg = 0x6b054, - .shift = 0, - .width = 2, - .parent_map = gcc_parent_map_4, .clkr = { .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_pipe_clk_src", - .parent_data = gcc_parent_data_4, - .num_parents = ARRAY_SIZE(gcc_parent_data_4), - .ops = &clk_regmap_mux_closest_ops, + .parent_data = &(const struct clk_parent_data){ + .fw_name = "pcie_0_pipe_clk", + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, }, }, }; -static struct clk_regmap_mux gcc_pcie_1_pipe_clk_src = { +static struct clk_regmap_phy_mux gcc_pcie_1_pipe_clk_src = { .reg = 0x8d054, - .shift = 0, - .width = 2, - .parent_map = gcc_parent_map_5, .clkr = { .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_pipe_clk_src", - .parent_data = gcc_parent_data_5, - .num_parents = ARRAY_SIZE(gcc_parent_data_5), - .ops = &clk_regmap_mux_closest_ops, + .parent_data = &(const struct clk_parent_data){ + .fw_name = "pcie_1_pipe_clk", + }, + .num_parents = 1, + .ops = &clk_regmap_phy_mux_ops, }, }, }; -- GitLab From daa9e76d17570cdd2dbec28244e60e2cb0eafb36 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 11 Apr 2023 14:59:04 +0200 Subject: [PATCH 3020/5631] dt-bindings: clock: qcom: describe the GPUCC clock for SA8775P Add the compatible for the Qualcomm Graphics Clock control module present on sa8775p platforms. It matches the generic QCom GPUCC description. Add device-specific DT bindings defines as well. Signed-off-by: Bartosz Golaszewski Reviewed-by: Krzysztof Kozlowski Acked-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230411125910.401075-2-brgl@bgdev.pl --- .../devicetree/bindings/clock/qcom,gpucc.yaml | 2 + .../dt-bindings/clock/qcom,sa8775p-gpucc.h | 50 +++++++++++++++++++ 2 files changed, 52 insertions(+) create mode 100644 include/dt-bindings/clock/qcom,sa8775p-gpucc.h diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml index db53eb288995..1e3dc9deded9 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml @@ -15,6 +15,7 @@ description: | See also:: include/dt-bindings/clock/qcom,gpucc-sdm845.h + include/dt-bindings/clock/qcom,gpucc-sa8775p.h include/dt-bindings/clock/qcom,gpucc-sc7180.h include/dt-bindings/clock/qcom,gpucc-sc7280.h include/dt-bindings/clock/qcom,gpucc-sc8280xp.h @@ -27,6 +28,7 @@ properties: compatible: enum: - qcom,sdm845-gpucc + - qcom,sa8775p-gpucc - qcom,sc7180-gpucc - qcom,sc7280-gpucc - qcom,sc8180x-gpucc diff --git a/include/dt-bindings/clock/qcom,sa8775p-gpucc.h b/include/dt-bindings/clock/qcom,sa8775p-gpucc.h new file mode 100644 index 000000000000..a5fd784b1ea2 --- /dev/null +++ b/include/dt-bindings/clock/qcom,sa8775p-gpucc.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2022, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023, Linaro Limited + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GPUCC_SA8775P_H +#define _DT_BINDINGS_CLK_QCOM_GPUCC_SA8775P_H + +/* GPU_CC clocks */ +#define GPU_CC_PLL0 0 +#define GPU_CC_PLL1 1 +#define GPU_CC_AHB_CLK 2 +#define GPU_CC_CB_CLK 3 +#define GPU_CC_CRC_AHB_CLK 4 +#define GPU_CC_CX_FF_CLK 5 +#define GPU_CC_CX_GMU_CLK 6 +#define GPU_CC_CX_SNOC_DVM_CLK 7 +#define GPU_CC_CXO_AON_CLK 8 +#define GPU_CC_CXO_CLK 9 +#define GPU_CC_DEMET_CLK 10 +#define GPU_CC_DEMET_DIV_CLK_SRC 11 +#define GPU_CC_FF_CLK_SRC 12 +#define GPU_CC_GMU_CLK_SRC 13 +#define GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK 14 +#define GPU_CC_HUB_AHB_DIV_CLK_SRC 15 +#define GPU_CC_HUB_AON_CLK 16 +#define GPU_CC_HUB_CLK_SRC 17 +#define GPU_CC_HUB_CX_INT_CLK 18 +#define GPU_CC_HUB_CX_INT_DIV_CLK_SRC 19 +#define GPU_CC_MEMNOC_GFX_CLK 20 +#define GPU_CC_SLEEP_CLK 21 +#define GPU_CC_XO_CLK_SRC 22 + +/* GPU_CC resets */ +#define GPUCC_GPU_CC_ACD_BCR 0 +#define GPUCC_GPU_CC_CB_BCR 1 +#define GPUCC_GPU_CC_CX_BCR 2 +#define GPUCC_GPU_CC_FAST_HUB_BCR 3 +#define GPUCC_GPU_CC_FF_BCR 4 +#define GPUCC_GPU_CC_GFX3D_AON_BCR 5 +#define GPUCC_GPU_CC_GMU_BCR 6 +#define GPUCC_GPU_CC_GX_BCR 7 +#define GPUCC_GPU_CC_XO_BCR 8 + +/* GPU_CC power domains */ +#define GPU_CC_CX_GDSC 0 +#define GPU_CC_GX_GDSC 1 + +#endif /* _DT_BINDINGS_CLK_QCOM_GPUCC_SA8775P_H */ -- GitLab From 0afa16afc36d0e462c7f815b0131d2e9013849ac Mon Sep 17 00:00:00 2001 From: Shazad Hussain Date: Tue, 11 Apr 2023 14:59:05 +0200 Subject: [PATCH 3021/5631] clk: qcom: add the GPUCC driver for sa8775p Add the clock driver for the Qualcomm Graphics Clock control module. Signed-off-by: Shazad Hussain [Bartosz: make ready for upstream] Co-developed-by: Bartosz Golaszewski Signed-off-by: Bartosz Golaszewski Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230411125910.401075-3-brgl@bgdev.pl --- drivers/clk/qcom/Kconfig | 9 + drivers/clk/qcom/Makefile | 1 + drivers/clk/qcom/gpucc-sa8775p.c | 625 +++++++++++++++++++++++++++++++ 3 files changed, 635 insertions(+) create mode 100644 drivers/clk/qcom/gpucc-sa8775p.c diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig index d71c9d6036bb..12be3e2371b3 100644 --- a/drivers/clk/qcom/Kconfig +++ b/drivers/clk/qcom/Kconfig @@ -445,6 +445,15 @@ config SA_GCC_8775P Say Y if you want to use peripheral devices such as UART, SPI, I2C, USB, UFS, SDCC, etc. +config SA_GPUCC_8775P + tristate "SA8775P Graphics clock controller" + select QCOM_GDSC + select SA_GCC_8775P + help + Support for the graphics clock controller on SA8775P devices. + Say Y if you want to support graphics controller devices and + functionality such as 3D graphics. + config SC_GCC_7180 tristate "SC7180 Global Clock Controller" select QCOM_GDSC diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile index b54085e579a0..9ff4c373ad95 100644 --- a/drivers/clk/qcom/Makefile +++ b/drivers/clk/qcom/Makefile @@ -72,6 +72,7 @@ obj-$(CONFIG_SC_DISPCC_7180) += dispcc-sc7180.o obj-$(CONFIG_SC_DISPCC_7280) += dispcc-sc7280.o obj-$(CONFIG_SC_DISPCC_8280XP) += dispcc-sc8280xp.o obj-$(CONFIG_SA_GCC_8775P) += gcc-sa8775p.o +obj-$(CONFIG_SA_GPUCC_8775P) += gpucc-sa8775p.o obj-$(CONFIG_SC_GCC_7180) += gcc-sc7180.o obj-$(CONFIG_SC_GCC_7280) += gcc-sc7280.o obj-$(CONFIG_SC_GCC_8180X) += gcc-sc8180x.o diff --git a/drivers/clk/qcom/gpucc-sa8775p.c b/drivers/clk/qcom/gpucc-sa8775p.c new file mode 100644 index 000000000000..18d23be8d435 --- /dev/null +++ b/drivers/clk/qcom/gpucc-sa8775p.c @@ -0,0 +1,625 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023, Linaro Limited + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "clk-alpha-pll.h" +#include "clk-branch.h" +#include "clk-rcg.h" +#include "clk-regmap.h" +#include "clk-regmap-divider.h" +#include "common.h" +#include "reset.h" +#include "gdsc.h" + +/* Need to match the order of clocks in DT binding */ +enum { + DT_BI_TCXO, + DT_GCC_GPU_GPLL0_CLK_SRC, + DT_GCC_GPU_GPLL0_DIV_CLK_SRC, +}; + +enum { + P_BI_TCXO, + P_GPLL0_OUT_MAIN, + P_GPLL0_OUT_MAIN_DIV, + P_GPU_CC_PLL0_OUT_MAIN, + P_GPU_CC_PLL1_OUT_MAIN, +}; + +static const struct clk_parent_data parent_data_tcxo = { .index = DT_BI_TCXO }; + +static const struct pll_vco lucid_evo_vco[] = { + { 249600000, 2020000000, 0 }, +}; + +/* 810MHz configuration */ +static struct alpha_pll_config gpu_cc_pll0_config = { + .l = 0x2a, + .alpha = 0x3000, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00182261, + .config_ctl_hi1_val = 0x32aa299c, + .user_ctl_val = 0x00000001, + .user_ctl_hi_val = 0x00400805, +}; + +static struct clk_alpha_pll gpu_cc_pll0 = { + .offset = 0x0, + .vco_table = lucid_evo_vco, + .num_vco = ARRAY_SIZE(lucid_evo_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID_EVO], + .clkr = { + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_pll0", + .parent_data = &parent_data_tcxo, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_evo_ops, + }, + }, +}; + +/* 1000MHz configuration */ +static struct alpha_pll_config gpu_cc_pll1_config = { + .l = 0x34, + .alpha = 0x1555, + .config_ctl_val = 0x20485699, + .config_ctl_hi_val = 0x00182261, + .config_ctl_hi1_val = 0x32aa299c, + .user_ctl_val = 0x00000001, + .user_ctl_hi_val = 0x00400805, +}; + +static struct clk_alpha_pll gpu_cc_pll1 = { + .offset = 0x1000, + .vco_table = lucid_evo_vco, + .num_vco = ARRAY_SIZE(lucid_evo_vco), + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_LUCID_EVO], + .clkr = { + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_pll1", + .parent_data = &parent_data_tcxo, + .num_parents = 1, + .ops = &clk_alpha_pll_lucid_evo_ops, + }, + }, +}; + +static const struct parent_map gpu_cc_parent_map_0[] = { + { P_BI_TCXO, 0 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_0[] = { + { .index = DT_BI_TCXO }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct parent_map gpu_cc_parent_map_1[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL0_OUT_MAIN, 1 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_1[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpu_cc_pll0.clkr.hw }, + { .hw = &gpu_cc_pll1.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct parent_map gpu_cc_parent_map_2[] = { + { P_BI_TCXO, 0 }, + { P_GPU_CC_PLL1_OUT_MAIN, 3 }, + { P_GPLL0_OUT_MAIN, 5 }, + { P_GPLL0_OUT_MAIN_DIV, 6 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_2[] = { + { .index = DT_BI_TCXO }, + { .hw = &gpu_cc_pll1.clkr.hw }, + { .index = DT_GCC_GPU_GPLL0_CLK_SRC }, + { .index = DT_GCC_GPU_GPLL0_DIV_CLK_SRC }, +}; + +static const struct parent_map gpu_cc_parent_map_3[] = { + { P_BI_TCXO, 0 }, +}; + +static const struct clk_parent_data gpu_cc_parent_data_3[] = { + { .index = DT_BI_TCXO }, +}; + +static const struct freq_tbl ftbl_gpu_cc_ff_clk_src[] = { + F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_ff_clk_src = { + .cmd_rcgr = 0x9474, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_0, + .freq_tbl = ftbl_gpu_cc_ff_clk_src, + .clkr.hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_ff_clk_src", + .parent_data = gpu_cc_parent_data_0, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = { + F(500000000, P_GPU_CC_PLL1_OUT_MAIN, 2, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_gmu_clk_src = { + .cmd_rcgr = 0x9318, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_1, + .freq_tbl = ftbl_gpu_cc_gmu_clk_src, + .clkr.hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_gmu_clk_src", + .parent_data = gpu_cc_parent_data_1, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_hub_clk_src[] = { + F(240000000, P_GPLL0_OUT_MAIN, 2.5, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_hub_clk_src = { + .cmd_rcgr = 0x93ec, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_2, + .freq_tbl = ftbl_gpu_cc_hub_clk_src, + .clkr.hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_hub_clk_src", + .parent_data = gpu_cc_parent_data_2, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_2), + .ops = &clk_rcg2_ops, + }, +}; + +static const struct freq_tbl ftbl_gpu_cc_xo_clk_src[] = { + F(19200000, P_BI_TCXO, 1, 0, 0), + { } +}; + +static struct clk_rcg2 gpu_cc_xo_clk_src = { + .cmd_rcgr = 0x9010, + .mnd_width = 0, + .hid_width = 5, + .parent_map = gpu_cc_parent_map_3, + .freq_tbl = ftbl_gpu_cc_xo_clk_src, + .clkr.hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_xo_clk_src", + .parent_data = gpu_cc_parent_data_3, + .num_parents = ARRAY_SIZE(gpu_cc_parent_data_3), + .ops = &clk_rcg2_ops, + }, +}; + +static struct clk_regmap_div gpu_cc_demet_div_clk_src = { + .reg = 0x9054, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_demet_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div gpu_cc_hub_ahb_div_clk_src = { + .reg = 0x9430, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_hub_ahb_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_regmap_div gpu_cc_hub_cx_int_div_clk_src = { + .reg = 0x942c, + .shift = 0, + .width = 4, + .clkr.hw.init = &(const struct clk_init_data) { + .name = "gpu_cc_hub_cx_int_div_clk_src", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, + .ops = &clk_regmap_div_ro_ops, + }, +}; + +static struct clk_branch gpu_cc_ahb_clk = { + .halt_reg = 0x911c, + .halt_check = BRANCH_HALT_DELAY, + .clkr = { + .enable_reg = 0x911c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_ahb_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cb_clk = { + .halt_reg = 0x93a4, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x93a4, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cb_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_crc_ahb_clk = { + .halt_reg = 0x9120, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9120, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_crc_ahb_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_ahb_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_ff_clk = { + .halt_reg = 0x914c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x914c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cx_ff_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_ff_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_gmu_clk = { + .halt_reg = 0x913c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x913c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cx_gmu_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_gmu_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cx_snoc_dvm_clk = { + .halt_reg = 0x9130, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9130, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cx_snoc_dvm_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_aon_clk = { + .halt_reg = 0x9004, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9004, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cxo_aon_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_cxo_clk = { + .halt_reg = 0x9144, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9144, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_cxo_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_xo_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_demet_clk = { + .halt_reg = 0x900c, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x900c, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_demet_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_demet_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = { + .halt_reg = 0x7000, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x7000, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_hlos1_vote_gpu_smmu_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hub_aon_clk = { + .halt_reg = 0x93e8, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x93e8, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_hub_aon_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_hub_cx_int_clk = { + .halt_reg = 0x9148, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9148, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_hub_cx_int_clk", + .parent_hws = (const struct clk_hw*[]){ + &gpu_cc_hub_cx_int_div_clk_src.clkr.hw, + }, + .num_parents = 1, + .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, + .ops = &clk_branch2_aon_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_memnoc_gfx_clk = { + .halt_reg = 0x9150, + .halt_check = BRANCH_HALT, + .clkr = { + .enable_reg = 0x9150, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_memnoc_gfx_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_branch gpu_cc_sleep_clk = { + .halt_reg = 0x9134, + .halt_check = BRANCH_HALT_VOTED, + .clkr = { + .enable_reg = 0x9134, + .enable_mask = BIT(0), + .hw.init = &(const struct clk_init_data){ + .name = "gpu_cc_sleep_clk", + .flags = CLK_IS_CRITICAL, + .ops = &clk_branch2_ops, + }, + }, +}; + +static struct clk_regmap *gpu_cc_sa8775p_clocks[] = { + [GPU_CC_AHB_CLK] = &gpu_cc_ahb_clk.clkr, + [GPU_CC_CB_CLK] = &gpu_cc_cb_clk.clkr, + [GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr, + [GPU_CC_CX_FF_CLK] = &gpu_cc_cx_ff_clk.clkr, + [GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr, + [GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr, + [GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr, + [GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr, + [GPU_CC_DEMET_CLK] = &gpu_cc_demet_clk.clkr, + [GPU_CC_DEMET_DIV_CLK_SRC] = &gpu_cc_demet_div_clk_src.clkr, + [GPU_CC_FF_CLK_SRC] = &gpu_cc_ff_clk_src.clkr, + [GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr, + [GPU_CC_HLOS1_VOTE_GPU_SMMU_CLK] = &gpu_cc_hlos1_vote_gpu_smmu_clk.clkr, + [GPU_CC_HUB_AHB_DIV_CLK_SRC] = &gpu_cc_hub_ahb_div_clk_src.clkr, + [GPU_CC_HUB_AON_CLK] = &gpu_cc_hub_aon_clk.clkr, + [GPU_CC_HUB_CLK_SRC] = &gpu_cc_hub_clk_src.clkr, + [GPU_CC_HUB_CX_INT_CLK] = &gpu_cc_hub_cx_int_clk.clkr, + [GPU_CC_HUB_CX_INT_DIV_CLK_SRC] = &gpu_cc_hub_cx_int_div_clk_src.clkr, + [GPU_CC_MEMNOC_GFX_CLK] = &gpu_cc_memnoc_gfx_clk.clkr, + [GPU_CC_PLL0] = &gpu_cc_pll0.clkr, + [GPU_CC_PLL1] = &gpu_cc_pll1.clkr, + [GPU_CC_SLEEP_CLK] = &gpu_cc_sleep_clk.clkr, + [GPU_CC_XO_CLK_SRC] = &gpu_cc_xo_clk_src.clkr, +}; + +static struct gdsc cx_gdsc = { + .gdscr = 0x9108, + .gds_hw_ctrl = 0x953c, + .pd = { + .name = "cx_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON, +}; + +static struct gdsc gx_gdsc = { + .gdscr = 0x905c, + .pd = { + .name = "gx_gdsc", + .power_on = gdsc_gx_do_nothing_enable, + }, + .pwrsts = PWRSTS_OFF_ON, + .flags = AON_RESET | RETAIN_FF_ENABLE, +}; + +static struct gdsc *gpu_cc_sa8775p_gdscs[] = { + [GPU_CC_CX_GDSC] = &cx_gdsc, + [GPU_CC_GX_GDSC] = &gx_gdsc, +}; + +static const struct qcom_reset_map gpu_cc_sa8775p_resets[] = { + [GPUCC_GPU_CC_ACD_BCR] = { 0x9358 }, + [GPUCC_GPU_CC_CB_BCR] = { 0x93a0 }, + [GPUCC_GPU_CC_CX_BCR] = { 0x9104 }, + [GPUCC_GPU_CC_FAST_HUB_BCR] = { 0x93e4 }, + [GPUCC_GPU_CC_FF_BCR] = { 0x9470 }, + [GPUCC_GPU_CC_GFX3D_AON_BCR] = { 0x9198 }, + [GPUCC_GPU_CC_GMU_BCR] = { 0x9314 }, + [GPUCC_GPU_CC_GX_BCR] = { 0x9058 }, + [GPUCC_GPU_CC_XO_BCR] = { 0x9000 }, +}; + +static const struct regmap_config gpu_cc_sa8775p_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x9988, + .fast_io = true, +}; + +static const struct qcom_cc_desc gpu_cc_sa8775p_desc = { + .config = &gpu_cc_sa8775p_regmap_config, + .clks = gpu_cc_sa8775p_clocks, + .num_clks = ARRAY_SIZE(gpu_cc_sa8775p_clocks), + .resets = gpu_cc_sa8775p_resets, + .num_resets = ARRAY_SIZE(gpu_cc_sa8775p_resets), + .gdscs = gpu_cc_sa8775p_gdscs, + .num_gdscs = ARRAY_SIZE(gpu_cc_sa8775p_gdscs), +}; + +static const struct of_device_id gpu_cc_sa8775p_match_table[] = { + { .compatible = "qcom,sa8775p-gpucc" }, + { } +}; +MODULE_DEVICE_TABLE(of, gpu_cc_sa8775p_match_table); + +static int gpu_cc_sa8775p_probe(struct platform_device *pdev) +{ + struct regmap *regmap; + + regmap = qcom_cc_map(pdev, &gpu_cc_sa8775p_desc); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + clk_lucid_evo_pll_configure(&gpu_cc_pll0, regmap, &gpu_cc_pll0_config); + clk_lucid_evo_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll1_config); + + return qcom_cc_really_probe(pdev, &gpu_cc_sa8775p_desc, regmap); +} + +static struct platform_driver gpu_cc_sa8775p_driver = { + .probe = gpu_cc_sa8775p_probe, + .driver = { + .name = "gpu_cc-sa8775p", + .of_match_table = gpu_cc_sa8775p_match_table, + }, +}; + +static int __init gpu_cc_sa8775p_init(void) +{ + return platform_driver_register(&gpu_cc_sa8775p_driver); +} +subsys_initcall(gpu_cc_sa8775p_init); + +static void __exit gpu_cc_sa8775p_exit(void) +{ + platform_driver_unregister(&gpu_cc_sa8775p_driver); +} +module_exit(gpu_cc_sa8775p_exit); + +MODULE_DESCRIPTION("SA8775P GPUCC driver"); +MODULE_LICENSE("GPL"); -- GitLab From 68d1151f03067533827fc50b770954ef33149533 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 12 Apr 2023 16:53:06 +0200 Subject: [PATCH 3022/5631] clk: qcom: dispcc-qcm2290: Remove inexistent DSI1PHY clk There's only one DSI PHY on this SoC. Remove the ghost entry for the clock produced by a secondary one. Fixes: cc517ea3333f ("clk: qcom: Add display clock controller driver for QCM2290") Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230412-topic-qcm_dispcc-v1-2-bf2989a75ae4@linaro.org --- drivers/clk/qcom/dispcc-qcm2290.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/clk/qcom/dispcc-qcm2290.c b/drivers/clk/qcom/dispcc-qcm2290.c index cbb5f1ec6a54..e9cfe41c0442 100644 --- a/drivers/clk/qcom/dispcc-qcm2290.c +++ b/drivers/clk/qcom/dispcc-qcm2290.c @@ -27,7 +27,6 @@ enum { P_DISP_CC_PLL0_OUT_MAIN, P_DSI0_PHY_PLL_OUT_BYTECLK, P_DSI0_PHY_PLL_OUT_DSICLK, - P_DSI1_PHY_PLL_OUT_DSICLK, P_GPLL0_OUT_MAIN, P_SLEEP_CLK, }; @@ -107,13 +106,11 @@ static const struct clk_parent_data disp_cc_parent_data_3[] = { static const struct parent_map disp_cc_parent_map_4[] = { { P_BI_TCXO, 0 }, { P_DSI0_PHY_PLL_OUT_DSICLK, 1 }, - { P_DSI1_PHY_PLL_OUT_DSICLK, 2 }, }; static const struct clk_parent_data disp_cc_parent_data_4[] = { { .fw_name = "bi_tcxo" }, { .fw_name = "dsi0_phy_pll_out_dsiclk" }, - { .fw_name = "dsi1_phy_pll_out_dsiclk" }, }; static const struct parent_map disp_cc_parent_map_5[] = { -- GitLab From 5bca3688bdbc3b58a2894b8671a8e2378efe28bd Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 13 Apr 2023 23:05:20 -0700 Subject: [PATCH 3023/5631] Input: raspberrypi-ts - fix refcount leak in rpi_ts_probe rpi_firmware_get() take reference, we need to release it in error paths as well. Use devm_rpi_firmware_get() helper to handling the resources. Also remove the existing rpi_firmware_put(). Fixes: 0b9f28fed3f7 ("Input: add official Raspberry Pi's touchscreen driver") Fixes: 3b8ddff780b7 ("input: raspberrypi-ts: Release firmware handle when not needed") Signed-off-by: Miaoqian Lin Reviewed-by: Mattijs Korpershoek Link: https://lore.kernel.org/r/20221223074657.810346-1-linmq006@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/input/touchscreen/raspberrypi-ts.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/input/touchscreen/raspberrypi-ts.c b/drivers/input/touchscreen/raspberrypi-ts.c index 5000f5fd9ec3..45c575df994e 100644 --- a/drivers/input/touchscreen/raspberrypi-ts.c +++ b/drivers/input/touchscreen/raspberrypi-ts.c @@ -134,7 +134,7 @@ static int rpi_ts_probe(struct platform_device *pdev) return -ENOENT; } - fw = rpi_firmware_get(fw_node); + fw = devm_rpi_firmware_get(&pdev->dev, fw_node); of_node_put(fw_node); if (!fw) return -EPROBE_DEFER; @@ -160,7 +160,6 @@ static int rpi_ts_probe(struct platform_device *pdev) touchbuf = (u32)ts->fw_regs_phys; error = rpi_firmware_property(fw, RPI_FIRMWARE_FRAMEBUFFER_SET_TOUCHBUF, &touchbuf, sizeof(touchbuf)); - rpi_firmware_put(fw); if (error || touchbuf != 0) { dev_warn(dev, "Failed to set touchbuf, %d\n", error); return error; -- GitLab From d6e680837ec568818eff275c15709231ce2e2b4f Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Thu, 13 Apr 2023 23:23:29 -0700 Subject: [PATCH 3024/5631] Input: synaptics-rmi4 - fix function name in kerneldoc No functional modification involved. drivers/input/rmi4/rmi_bus.c:300: warning: expecting prototype for rmi_register_function_handler(). Prototype was for __rmi_register_function_handler() instead. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Link: https://lore.kernel.org/r/20230209040710.111456-1-jiapeng.chong@linux.alibaba.com Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c index 50a0134b6901..f2e093b0b998 100644 --- a/drivers/input/rmi4/rmi_bus.c +++ b/drivers/input/rmi4/rmi_bus.c @@ -285,7 +285,7 @@ void rmi_unregister_function(struct rmi_function *fn) } /** - * rmi_register_function_handler - register a handler for an RMI function + * __rmi_register_function_handler - register a handler for an RMI function * @handler: RMI handler that should be registered. * @owner: pointer to module that implements the handler * @mod_name: name of the module implementing the handler -- GitLab From f9b2e603c6216824e34dc9a67205d98ccc9a41ca Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 13 Apr 2023 23:57:42 -0700 Subject: [PATCH 3025/5631] Input: xpad - add constants for GIP interface numbers Wired GIP devices present multiple interfaces with the same USB identification other than the interface number. This adds constants for differentiating two of them and uses them where appropriate Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230411031650.960322-2-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 260f91fef427..6ea9c10dfb8a 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -561,6 +561,9 @@ struct xboxone_init_packet { #define GIP_MOTOR_LT BIT(3) #define GIP_MOTOR_ALL (GIP_MOTOR_R | GIP_MOTOR_L | GIP_MOTOR_RT | GIP_MOTOR_LT) +#define GIP_WIRED_INTF_DATA 0 +#define GIP_WIRED_INTF_AUDIO 1 + /* * This packet is required for all Xbox One pads with 2015 * or later firmware installed (or present from the factory). @@ -2004,7 +2007,7 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id } if (xpad->xtype == XTYPE_XBOXONE && - intf->cur_altsetting->desc.bInterfaceNumber != 0) { + intf->cur_altsetting->desc.bInterfaceNumber != GIP_WIRED_INTF_DATA) { /* * The Xbox One controller lists three interfaces all with the * same interface class, subclass and protocol. Differentiate by -- GitLab From cf5950187319346d7cdc62522f90479dfefd9235 Mon Sep 17 00:00:00 2001 From: Vicki Pfau Date: Thu, 13 Apr 2023 23:58:12 -0700 Subject: [PATCH 3026/5631] Input: xpad - fix PowerA EnWired Controller guide button This commit explicitly disables the audio interface the same way the official driver does. This is needed for some controllers, such as the PowerA Enhanced Wired Controller for Series X|S (0x20d6:0x200e) to report the guide button. Signed-off-by: Vicki Pfau Link: https://lore.kernel.org/r/20230411031650.960322-3-vi@endrift.com Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 6ea9c10dfb8a..138e4a9f341f 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -1396,6 +1396,21 @@ static int xpad_start_xbox_one(struct usb_xpad *xpad) unsigned long flags; int retval; + if (usb_ifnum_to_if(xpad->udev, GIP_WIRED_INTF_AUDIO)) { + /* + * Explicitly disable the audio interface. This is needed + * for some controllers, such as the PowerA Enhanced Wired + * Controller for Series X|S (0x20d6:0x200e) to report the + * guide button. + */ + retval = usb_set_interface(xpad->udev, + GIP_WIRED_INTF_AUDIO, 0); + if (retval) + dev_warn(&xpad->dev->dev, + "unable to disable audio interface: %d\n", + retval); + } + spin_lock_irqsave(&xpad->odata_lock, flags); /* -- GitLab From c55d84fb2bd89fe2ad56768ead90eb1050581d29 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Thu, 13 Apr 2023 23:35:26 -0700 Subject: [PATCH 3027/5631] dt-bindings: input: pwm-beeper: convert to dt schema Convert the binding doc to dt schema, and also fixed the example from fixed-regulator to regulator-fixed. Signed-off-by: Peng Fan Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230407075259.1593739-1-peng.fan@oss.nxp.com Signed-off-by: Dmitry Torokhov --- .../devicetree/bindings/input/pwm-beeper.txt | 24 ----------- .../devicetree/bindings/input/pwm-beeper.yaml | 41 +++++++++++++++++++ 2 files changed, 41 insertions(+), 24 deletions(-) delete mode 100644 Documentation/devicetree/bindings/input/pwm-beeper.txt create mode 100644 Documentation/devicetree/bindings/input/pwm-beeper.yaml diff --git a/Documentation/devicetree/bindings/input/pwm-beeper.txt b/Documentation/devicetree/bindings/input/pwm-beeper.txt deleted file mode 100644 index 8fc0e48c20db..000000000000 --- a/Documentation/devicetree/bindings/input/pwm-beeper.txt +++ /dev/null @@ -1,24 +0,0 @@ -* PWM beeper device tree bindings - -Registers a PWM device as beeper. - -Required properties: -- compatible: should be "pwm-beeper" -- pwms: phandle to the physical PWM device - -Optional properties: -- amp-supply: phandle to a regulator that acts as an amplifier for the beeper -- beeper-hz: bell frequency in Hz - -Example: - -beeper_amp: amplifier { - compatible = "fixed-regulator"; - gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>; -}; - -beeper { - compatible = "pwm-beeper"; - pwms = <&pwm0>; - amp-supply = <&beeper_amp>; -}; diff --git a/Documentation/devicetree/bindings/input/pwm-beeper.yaml b/Documentation/devicetree/bindings/input/pwm-beeper.yaml new file mode 100644 index 000000000000..a7611c206989 --- /dev/null +++ b/Documentation/devicetree/bindings/input/pwm-beeper.yaml @@ -0,0 +1,41 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/input/pwm-beeper.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: PWM beeper + +maintainers: + - Sascha Hauer + +properties: + compatible: + const: pwm-beeper + + pwms: + maxItems: 1 + + amp-supply: + description: an amplifier for the beeper + + beeper-hz: + description: bell frequency in Hz + minimum: 10 + maximum: 10000 + +required: + - compatible + - pwms + +unevaluatedProperties: false + +examples: + - | + #include + beeper { + compatible = "pwm-beeper"; + pwms = <&pwm0>; + amp-supply = <&beeper_amp>; + beeper-hz = <1000>; + }; -- GitLab From 7e1b2329c205d0a08ebaf3f619318a8a18f36644 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 8 Apr 2023 17:04:24 +0100 Subject: [PATCH 3028/5631] KVM: arm64: nvhe: Synchronise with page table walker on TLBI A TLBI from EL2 impacting EL1 involves messing with the EL1&0 translation regime, and the page table walker may still be performing speculative walks. Piggyback on the existing DSBs to always have a DSB ISH that will synchronise all load/store operations that the PTW may still have. Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/nvhe/tlb.c | 38 ++++++++++++++++++++++++++--------- 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index d296d617f589..978179133f4b 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -15,8 +15,31 @@ struct tlb_inv_context { }; static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, - struct tlb_inv_context *cxt) + struct tlb_inv_context *cxt, + bool nsh) { + /* + * We have two requirements: + * + * - ensure that the page table updates are visible to all + * CPUs, for which a dsb(DOMAIN-st) is what we need, DOMAIN + * being either ish or nsh, depending on the invalidation + * type. + * + * - complete any speculative page table walk started before + * we trapped to EL2 so that we can mess with the MM + * registers out of context, for which dsb(nsh) is enough + * + * The composition of these two barriers is a dsb(DOMAIN), and + * the 'nsh' parameter tracks the distinction between + * Inner-Shareable and Non-Shareable, as specified by the + * callers. + */ + if (nsh) + dsb(nsh); + else + dsb(ish); + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { u64 val; @@ -60,10 +83,8 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, { struct tlb_inv_context cxt; - dsb(ishst); - /* Switch to requested VMID */ - __tlb_switch_to_guest(mmu, &cxt); + __tlb_switch_to_guest(mmu, &cxt, false); /* * We could do so much better if we had the VA as well. @@ -113,10 +134,8 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) { struct tlb_inv_context cxt; - dsb(ishst); - /* Switch to requested VMID */ - __tlb_switch_to_guest(mmu, &cxt); + __tlb_switch_to_guest(mmu, &cxt, false); __tlbi(vmalls12e1is); dsb(ish); @@ -130,7 +149,7 @@ void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) struct tlb_inv_context cxt; /* Switch to requested VMID */ - __tlb_switch_to_guest(mmu, &cxt); + __tlb_switch_to_guest(mmu, &cxt, false); __tlbi(vmalle1); asm volatile("ic iallu"); @@ -142,7 +161,8 @@ void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) void __kvm_flush_vm_context(void) { - dsb(ishst); + /* Same remark as in __tlb_switch_to_guest() */ + dsb(ish); __tlbi(alle1is); /* -- GitLab From 8442d65373c6316876208c1ad27729e9682fa3cf Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 8 Apr 2023 17:04:25 +0100 Subject: [PATCH 3029/5631] KVM: arm64: pkvm: Document the side effects of kvm_flush_dcache_to_poc() We rely on the presence of a DSB at the end of kvm_flush_dcache_to_poc() that, on top of ensuring completion of the cache clean, also covers the speculative page table walk started from EL1. Document this dependency. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 552653fa18be..2e9ec4a2a4a3 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -297,6 +297,13 @@ int __pkvm_prot_finalize(void) params->vttbr = kvm_get_vttbr(mmu); params->vtcr = host_mmu.arch.vtcr; params->hcr_el2 |= HCR_VM; + + /* + * The CMO below not only cleans the updated params to the + * PoC, but also provides the DSB that ensures ongoing + * page-table walks that have started before we trapped to EL2 + * have completed. + */ kvm_flush_dcache_to_poc(params, sizeof(*params)); write_sysreg(params->hcr_el2, hcr_el2); -- GitLab From 1ff2755d6800d60bee96fb303cbbf30f9bb483a2 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 8 Apr 2023 17:04:26 +0100 Subject: [PATCH 3030/5631] KVM: arm64: vhe: Synchronise with page table walker on MMU update Contrary to nVHE, VHE is a lot easier when it comes to dealing with speculative page table walks started at EL1. As we only change EL1&0 translation regime when context-switching, we already benefit from the effect of the DSB that sits in the context switch code. We only need to take care of it in the NV case, where we can flip between between two EL1 contexts (one of them being the virtual EL2) without a context switch. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton --- arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c index 7b44f6b3b547..b35a178e7e0d 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -13,6 +13,7 @@ #include #include #include +#include /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and @@ -69,6 +70,17 @@ void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu) host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; __sysreg_save_user_state(host_ctxt); + /* + * When running a normal EL1 guest, we only load a new vcpu + * after a context switch, which imvolves a DSB, so all + * speculative EL1&0 walks will have already completed. + * If running NV, the vcpu may transition between vEL1 and + * vEL2 without a context switch, so make sure we complete + * those walks before loading a new context. + */ + if (vcpu_has_nv(vcpu)) + dsb(nsh); + /* * Load guest EL1 and user state * -- GitLab From bcf3e7da3ad3bfea38ac6ba9f56b99b2877af51f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sat, 8 Apr 2023 17:04:27 +0100 Subject: [PATCH 3031/5631] KVM: arm64: vhe: Drop extra isb() on guest exit __kvm_vcpu_run_vhe() end on VHE with an isb(). However, this function is only reachable via kvm_call_hyp_ret(), which already contains an isb() in order to mimick the behaviour of nVHE and provide a context synchronisation event. We thus have two isb()s back to back, which is one too many. Drop the first one and solely rely on the one in the helper. Signed-off-by: Marc Zyngier Reviewed-by: Oliver Upton --- arch/arm64/kvm/hyp/vhe/switch.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index cd3f3117bf16..3d868e84c7a0 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -227,11 +227,10 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* * When we exit from the guest we change a number of CPU configuration - * parameters, such as traps. Make sure these changes take effect - * before running the host or additional guests. + * parameters, such as traps. We rely on the isb() in kvm_call_hyp*() + * to make sure these changes take effect before running the host or + * additional guests. */ - isb(); - return ret; } -- GitLab From 2cc4485e60a760fa50e0180e93308aa0975c73dd Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:03 +0200 Subject: [PATCH 3032/5631] pinctrl: iproc: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-1-503788a7f6e6@linaro.org --- drivers/pinctrl/bcm/pinctrl-iproc-gpio.c | 38 ++++++++++++++++-------- 1 file changed, 25 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c index 3df56a4ea510..cc3eb7409ab3 100644 --- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -108,7 +109,6 @@ struct iproc_gpio { raw_spinlock_t lock; - struct irq_chip irqchip; struct gpio_chip gc; unsigned num_banks; @@ -217,7 +217,7 @@ static void iproc_gpio_irq_set_mask(struct irq_data *d, bool unmask) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct iproc_gpio *chip = gpiochip_get_data(gc); - unsigned gpio = d->hwirq; + unsigned gpio = irqd_to_hwirq(d); iproc_set_bit(chip, IPROC_GPIO_INT_MSK_OFFSET, gpio, unmask); } @@ -231,6 +231,7 @@ static void iproc_gpio_irq_mask(struct irq_data *d) raw_spin_lock_irqsave(&chip->lock, flags); iproc_gpio_irq_set_mask(d, false); raw_spin_unlock_irqrestore(&chip->lock, flags); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void iproc_gpio_irq_unmask(struct irq_data *d) @@ -239,6 +240,7 @@ static void iproc_gpio_irq_unmask(struct irq_data *d) struct iproc_gpio *chip = gpiochip_get_data(gc); unsigned long flags; + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); raw_spin_lock_irqsave(&chip->lock, flags); iproc_gpio_irq_set_mask(d, true); raw_spin_unlock_irqrestore(&chip->lock, flags); @@ -302,6 +304,26 @@ static int iproc_gpio_irq_set_type(struct irq_data *d, unsigned int type) return 0; } +static void iproc_gpio_irq_print_chip(struct irq_data *d, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct iproc_gpio *chip = gpiochip_get_data(gc); + + seq_printf(p, dev_name(chip->dev)); +} + +static const struct irq_chip iproc_gpio_irq_chip = { + .irq_ack = iproc_gpio_irq_ack, + .irq_mask = iproc_gpio_irq_mask, + .irq_unmask = iproc_gpio_irq_unmask, + .irq_set_type = iproc_gpio_irq_set_type, + .irq_enable = iproc_gpio_irq_unmask, + .irq_disable = iproc_gpio_irq_mask, + .irq_print_chip = iproc_gpio_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + /* * Request the Iproc IOMUX pinmux controller to mux individual pins to GPIO */ @@ -852,20 +874,10 @@ static int iproc_gpio_probe(struct platform_device *pdev) /* optional GPIO interrupt support */ irq = platform_get_irq_optional(pdev, 0); if (irq > 0) { - struct irq_chip *irqc; struct gpio_irq_chip *girq; - irqc = &chip->irqchip; - irqc->name = dev_name(dev); - irqc->irq_ack = iproc_gpio_irq_ack; - irqc->irq_mask = iproc_gpio_irq_mask; - irqc->irq_unmask = iproc_gpio_irq_unmask; - irqc->irq_set_type = iproc_gpio_irq_set_type; - irqc->irq_enable = iproc_gpio_irq_unmask; - irqc->irq_disable = iproc_gpio_irq_mask; - girq = &gc->irq; - girq->chip = irqc; + gpio_irq_chip_set_chip(girq, &iproc_gpio_irq_chip); girq->parent_handler = iproc_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, -- GitLab From bb7e64e60e462c133a09e5674aa4c11ef888007d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:04 +0200 Subject: [PATCH 3033/5631] pinctrl: nsp: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-2-503788a7f6e6@linaro.org --- drivers/pinctrl/bcm/pinctrl-nsp-gpio.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c index 3c792bf03bda..5045a7e57f1d 100644 --- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c +++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c @@ -60,7 +60,6 @@ struct nsp_gpio { struct device *dev; void __iomem *base; void __iomem *io_ctrl; - struct irq_chip irqchip; struct gpio_chip gc; struct pinctrl_dev *pctl; struct pinctrl_desc pctldesc; @@ -193,6 +192,7 @@ static void nsp_gpio_irq_mask(struct irq_data *d) raw_spin_lock_irqsave(&chip->lock, flags); nsp_gpio_irq_set_mask(d, false); raw_spin_unlock_irqrestore(&chip->lock, flags); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void nsp_gpio_irq_unmask(struct irq_data *d) @@ -201,6 +201,7 @@ static void nsp_gpio_irq_unmask(struct irq_data *d) struct nsp_gpio *chip = gpiochip_get_data(gc); unsigned long flags; + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); raw_spin_lock_irqsave(&chip->lock, flags); nsp_gpio_irq_set_mask(d, true); raw_spin_unlock_irqrestore(&chip->lock, flags); @@ -258,6 +259,16 @@ static int nsp_gpio_irq_set_type(struct irq_data *d, unsigned int type) return 0; } +static const struct irq_chip nsp_gpio_irq_chip = { + .name = "gpio-a", + .irq_ack = nsp_gpio_irq_ack, + .irq_mask = nsp_gpio_irq_mask, + .irq_unmask = nsp_gpio_irq_unmask, + .irq_set_type = nsp_gpio_irq_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int nsp_gpio_direction_input(struct gpio_chip *gc, unsigned gpio) { struct nsp_gpio *chip = gpiochip_get_data(gc); @@ -650,14 +661,6 @@ static int nsp_gpio_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq > 0) { struct gpio_irq_chip *girq; - struct irq_chip *irqc; - - irqc = &chip->irqchip; - irqc->name = "gpio-a"; - irqc->irq_ack = nsp_gpio_irq_ack; - irqc->irq_mask = nsp_gpio_irq_mask; - irqc->irq_unmask = nsp_gpio_irq_unmask; - irqc->irq_set_type = nsp_gpio_irq_set_type; val = readl(chip->base + NSP_CHIP_A_INT_MASK); val = val | NSP_CHIP_A_GPIO_INT_BIT; @@ -673,7 +676,7 @@ static int nsp_gpio_probe(struct platform_device *pdev) } girq = &chip->gc.irq; - girq->chip = irqc; + gpio_irq_chip_set_chip(girq, &nsp_gpio_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; -- GitLab From dccdc09199b78cf3e24ec6becb70eb9a3c039d24 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:05 +0200 Subject: [PATCH 3034/5631] pinctrl: armada-37xx: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-3-503788a7f6e6@linaro.org --- drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 34 +++++++++++++++------ 1 file changed, 24 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c index 261b46841b9f..67c6751a6f06 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -101,7 +102,6 @@ struct armada_37xx_pinctrl { const struct armada_37xx_pin_data *data; struct device *dev; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; raw_spinlock_t irq_lock; struct pinctrl_desc pctl; struct pinctrl_dev *pctl_dev; @@ -548,6 +548,7 @@ static void armada_37xx_irq_mask(struct irq_data *d) val = readl(info->base + reg); writel(val & ~d->mask, info->base + reg); raw_spin_unlock_irqrestore(&info->irq_lock, flags); + gpiochip_disable_irq(chip, irqd_to_hwirq(d)); } static void armada_37xx_irq_unmask(struct irq_data *d) @@ -557,6 +558,7 @@ static void armada_37xx_irq_unmask(struct irq_data *d) u32 val, reg = IRQ_EN; unsigned long flags; + gpiochip_enable_irq(chip, irqd_to_hwirq(d)); armada_37xx_irq_update_reg(®, d); raw_spin_lock_irqsave(&info->irq_lock, flags); val = readl(info->base + reg); @@ -729,11 +731,30 @@ static unsigned int armada_37xx_irq_startup(struct irq_data *d) return 0; } +static void armada_37xx_irq_print_chip(struct irq_data *d, struct seq_file *p) +{ + struct gpio_chip *chip = irq_data_get_irq_chip_data(d); + struct armada_37xx_pinctrl *info = gpiochip_get_data(chip); + + seq_printf(p, info->data->name); +} + +static const struct irq_chip armada_37xx_irqchip = { + .irq_ack = armada_37xx_irq_ack, + .irq_mask = armada_37xx_irq_mask, + .irq_unmask = armada_37xx_irq_unmask, + .irq_set_wake = armada_37xx_irq_set_wake, + .irq_set_type = armada_37xx_irq_set_type, + .irq_startup = armada_37xx_irq_startup, + .irq_print_chip = armada_37xx_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int armada_37xx_irqchip_register(struct platform_device *pdev, struct armada_37xx_pinctrl *info) { struct gpio_chip *gc = &info->gpio_chip; - struct irq_chip *irqchip = &info->irq_chip; struct gpio_irq_chip *girq = &gc->irq; struct device_node *np = to_of_node(gc->fwnode); struct device *dev = &pdev->dev; @@ -751,14 +772,7 @@ static int armada_37xx_irqchip_register(struct platform_device *pdev, if (IS_ERR(info->base)) return PTR_ERR(info->base); - irqchip->irq_ack = armada_37xx_irq_ack; - irqchip->irq_mask = armada_37xx_irq_mask; - irqchip->irq_unmask = armada_37xx_irq_unmask; - irqchip->irq_set_wake = armada_37xx_irq_set_wake; - irqchip->irq_set_type = armada_37xx_irq_set_type; - irqchip->irq_startup = armada_37xx_irq_startup; - irqchip->name = info->data->name; - girq->chip = irqchip; + gpio_irq_chip_set_chip(girq, &armada_37xx_irqchip); girq->parent_handler = armada_37xx_irq_handler; /* * Many interrupts are connected to the parent interrupt -- GitLab From dcea54b7dad1b39757949d3e97a5eead161e8f0d Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:06 +0200 Subject: [PATCH 3035/5631] pinctrl: npcm7xx: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. I refactored the way the state container was accessed in the irq_chip callbacks to all look the same and switch to use irqd_to_hwirq() while we are at it. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-4-503788a7f6e6@linaro.org --- drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c | 34 ++++++++++++----------- 1 file changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c index ff5bcea172e8..05d39f9111c2 100644 --- a/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c +++ b/drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c @@ -82,7 +82,6 @@ struct npcm7xx_gpio { struct gpio_chip gc; int irqbase; int irq; - struct irq_chip irq_chip; u32 pinctrl_id; int (*direction_input)(struct gpio_chip *chip, unsigned int offset); int (*direction_output)(struct gpio_chip *chip, unsigned int offset, @@ -240,9 +239,9 @@ static void npcmgpio_irq_handler(struct irq_desc *desc) static int npcmgpio_set_irq_type(struct irq_data *d, unsigned int type) { - struct npcm7xx_gpio *bank = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int gpio = BIT(d->hwirq); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct npcm7xx_gpio *bank = gpiochip_get_data(gc); + unsigned int gpio = BIT(irqd_to_hwirq(d)); dev_dbg(bank->gc.parent, "setirqtype: %u.%u = %u\n", gpio, d->irq, type); @@ -288,9 +287,9 @@ static int npcmgpio_set_irq_type(struct irq_data *d, unsigned int type) static void npcmgpio_irq_ack(struct irq_data *d) { - struct npcm7xx_gpio *bank = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int gpio = d->hwirq; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct npcm7xx_gpio *bank = gpiochip_get_data(gc); + unsigned int gpio = irqd_to_hwirq(d); dev_dbg(bank->gc.parent, "irq_ack: %u.%u\n", gpio, d->irq); iowrite32(BIT(gpio), bank->base + NPCM7XX_GP_N_EVST); @@ -299,23 +298,25 @@ static void npcmgpio_irq_ack(struct irq_data *d) /* Disable GPIO interrupt */ static void npcmgpio_irq_mask(struct irq_data *d) { - struct npcm7xx_gpio *bank = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int gpio = d->hwirq; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct npcm7xx_gpio *bank = gpiochip_get_data(gc); + unsigned int gpio = irqd_to_hwirq(d); /* Clear events */ dev_dbg(bank->gc.parent, "irq_mask: %u.%u\n", gpio, d->irq); iowrite32(BIT(gpio), bank->base + NPCM7XX_GP_N_EVENC); + gpiochip_disable_irq(gc, gpio); } /* Enable GPIO interrupt */ static void npcmgpio_irq_unmask(struct irq_data *d) { - struct npcm7xx_gpio *bank = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int gpio = d->hwirq; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct npcm7xx_gpio *bank = gpiochip_get_data(gc); + unsigned int gpio = irqd_to_hwirq(d); /* Enable events */ + gpiochip_enable_irq(gc, gpio); dev_dbg(bank->gc.parent, "irq_unmask: %u.%u\n", gpio, d->irq); iowrite32(BIT(gpio), bank->base + NPCM7XX_GP_N_EVENS); } @@ -323,7 +324,7 @@ static void npcmgpio_irq_unmask(struct irq_data *d) static unsigned int npcmgpio_irq_startup(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - unsigned int gpio = d->hwirq; + unsigned int gpio = irqd_to_hwirq(d); /* active-high, input, clear interrupt, enable interrupt */ dev_dbg(gc->parent, "startup: %u.%u\n", gpio, d->irq); @@ -341,6 +342,8 @@ static const struct irq_chip npcmgpio_irqchip = { .irq_mask = npcmgpio_irq_mask, .irq_set_type = npcmgpio_set_irq_type, .irq_startup = npcmgpio_irq_startup, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; /* pinmux handing in the pinctrl driver*/ @@ -1906,7 +1909,6 @@ static int npcm7xx_gpio_of(struct npcm7xx_pinctrl *pctrl) return -EINVAL; } pctrl->gpio_bank[id].irq = ret; - pctrl->gpio_bank[id].irq_chip = npcmgpio_irqchip; pctrl->gpio_bank[id].irqbase = id * NPCM7XX_GPIO_PER_BANK; pctrl->gpio_bank[id].pinctrl_id = args.args[0]; pctrl->gpio_bank[id].gc.base = args.args[1]; @@ -1941,7 +1943,7 @@ static int npcm7xx_gpio_register(struct npcm7xx_pinctrl *pctrl) struct gpio_irq_chip *girq; girq = &pctrl->gpio_bank[id].gc.irq; - girq->chip = &pctrl->gpio_bank[id].irq_chip; + gpio_irq_chip_set_chip(girq, &npcmgpio_irqchip); girq->parent_handler = npcmgpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(pctrl->dev, 1, -- GitLab From 52066a53bd116a2f41d04d99b5095c02ad8cf953 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:07 +0200 Subject: [PATCH 3036/5631] pinctrl: equilibrium: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-5-503788a7f6e6@linaro.org --- drivers/pinctrl/pinctrl-equilibrium.c | 22 ++++++++++++++-------- drivers/pinctrl/pinctrl-equilibrium.h | 2 -- 2 files changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c index 99cf24eb67ae..5b5ddf7e5d0e 100644 --- a/drivers/pinctrl/pinctrl-equilibrium.c +++ b/drivers/pinctrl/pinctrl-equilibrium.c @@ -32,6 +32,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d) raw_spin_lock_irqsave(&gctrl->lock, flags); writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR); raw_spin_unlock_irqrestore(&gctrl->lock, flags); + gpiochip_disable_irq(gc, offset); } static void eqbr_gpio_enable_irq(struct irq_data *d) @@ -42,6 +43,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d) unsigned long flags; gc->direction_input(gc, offset); + gpiochip_enable_irq(gc, offset); raw_spin_lock_irqsave(&gctrl->lock, flags); writel(BIT(offset), gctrl->membase + GPIO_IRNRNSET); raw_spin_unlock_irqrestore(&gctrl->lock, flags); @@ -161,6 +163,17 @@ static void eqbr_irq_handler(struct irq_desc *desc) chained_irq_exit(ic, desc); } +static const struct irq_chip eqbr_irq_chip = { + .name = "gpio_irq", + .irq_mask = eqbr_gpio_disable_irq, + .irq_unmask = eqbr_gpio_enable_irq, + .irq_ack = eqbr_gpio_ack_irq, + .irq_mask_ack = eqbr_gpio_mask_ack_irq, + .irq_set_type = eqbr_gpio_set_irq_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int gpiochip_setup(struct device *dev, struct eqbr_gpio_ctrl *gctrl) { struct gpio_irq_chip *girq; @@ -176,15 +189,8 @@ static int gpiochip_setup(struct device *dev, struct eqbr_gpio_ctrl *gctrl) return 0; } - gctrl->ic.name = "gpio_irq"; - gctrl->ic.irq_mask = eqbr_gpio_disable_irq; - gctrl->ic.irq_unmask = eqbr_gpio_enable_irq; - gctrl->ic.irq_ack = eqbr_gpio_ack_irq; - gctrl->ic.irq_mask_ack = eqbr_gpio_mask_ack_irq; - gctrl->ic.irq_set_type = eqbr_gpio_set_irq_type; - girq = &gctrl->chip.irq; - girq->chip = &gctrl->ic; + gpio_irq_chip_set_chip(girq, &eqbr_irq_chip); girq->parent_handler = eqbr_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), GFP_KERNEL); diff --git a/drivers/pinctrl/pinctrl-equilibrium.h b/drivers/pinctrl/pinctrl-equilibrium.h index 0c635a5b79f0..83768cc8b3db 100644 --- a/drivers/pinctrl/pinctrl-equilibrium.h +++ b/drivers/pinctrl/pinctrl-equilibrium.h @@ -103,7 +103,6 @@ struct fwnode_handle; * @fwnode: firmware node of gpio controller. * @bank: pointer to corresponding pin bank. * @membase: base address of the gpio controller. - * @ic: irq chip. * @name: gpio chip name. * @virq: irq number of the gpio chip to parent's irq domain. * @lock: spin lock to protect gpio register write. @@ -113,7 +112,6 @@ struct eqbr_gpio_ctrl { struct fwnode_handle *fwnode; struct eqbr_pin_bank *bank; void __iomem *membase; - struct irq_chip ic; const char *name; unsigned int virq; raw_spinlock_t lock; /* protect gpio register */ -- GitLab From cca973a823f1c94313256ab214af0577dcc3a52b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:08 +0200 Subject: [PATCH 3037/5631] pinctrl: mcp23s08: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. I switched to using irqd_to_hwirq() consistently while we are at it. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-6-503788a7f6e6@linaro.org --- drivers/pinctrl/pinctrl-mcp23s08.c | 36 +++++++++++++++++++++--------- drivers/pinctrl/pinctrl-mcp23s08.h | 1 - 2 files changed, 26 insertions(+), 11 deletions(-) diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 8ec7f2a3d009..4551575e4e7d 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -467,17 +468,19 @@ static void mcp23s08_irq_mask(struct irq_data *data) { struct gpio_chip *gc = irq_data_get_irq_chip_data(data); struct mcp23s08 *mcp = gpiochip_get_data(gc); - unsigned int pos = data->hwirq; + unsigned int pos = irqd_to_hwirq(data); mcp_set_bit(mcp, MCP_GPINTEN, pos, false); + gpiochip_disable_irq(gc, pos); } static void mcp23s08_irq_unmask(struct irq_data *data) { struct gpio_chip *gc = irq_data_get_irq_chip_data(data); struct mcp23s08 *mcp = gpiochip_get_data(gc); - unsigned int pos = data->hwirq; + unsigned int pos = irqd_to_hwirq(data); + gpiochip_enable_irq(gc, pos); mcp_set_bit(mcp, MCP_GPINTEN, pos, true); } @@ -485,7 +488,7 @@ static int mcp23s08_irq_set_type(struct irq_data *data, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(data); struct mcp23s08 *mcp = gpiochip_get_data(gc); - unsigned int pos = data->hwirq; + unsigned int pos = irqd_to_hwirq(data); if ((type & IRQ_TYPE_EDGE_BOTH) == IRQ_TYPE_EDGE_BOTH) { mcp_set_bit(mcp, MCP_INTCON, pos, false); @@ -554,6 +557,25 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp) return 0; } +static void mcp23s08_irq_print_chip(struct irq_data *d, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct mcp23s08 *mcp = gpiochip_get_data(gc); + + seq_printf(p, dev_name(mcp->dev)); +} + +static const struct irq_chip mcp23s08_irq_chip = { + .irq_mask = mcp23s08_irq_mask, + .irq_unmask = mcp23s08_irq_unmask, + .irq_set_type = mcp23s08_irq_set_type, + .irq_bus_lock = mcp23s08_irq_bus_lock, + .irq_bus_sync_unlock = mcp23s08_irq_bus_unlock, + .irq_print_chip = mcp23s08_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + /*----------------------------------------------------------------------*/ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, @@ -569,12 +591,6 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, mcp->addr = addr; mcp->irq_active_high = false; - mcp->irq_chip.name = dev_name(dev); - mcp->irq_chip.irq_mask = mcp23s08_irq_mask; - mcp->irq_chip.irq_unmask = mcp23s08_irq_unmask; - mcp->irq_chip.irq_set_type = mcp23s08_irq_set_type; - mcp->irq_chip.irq_bus_lock = mcp23s08_irq_bus_lock; - mcp->irq_chip.irq_bus_sync_unlock = mcp23s08_irq_bus_unlock; mcp->chip.direction_input = mcp23s08_direction_input; mcp->chip.get = mcp23s08_get; @@ -636,7 +652,7 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, if (mcp->irq && mcp->irq_controller) { struct gpio_irq_chip *girq = &mcp->chip.irq; - girq->chip = &mcp->irq_chip; + gpio_irq_chip_set_chip(girq, &mcp23s08_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/pinctrl/pinctrl-mcp23s08.h b/drivers/pinctrl/pinctrl-mcp23s08.h index b8d15939e0c2..b15516af7783 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.h +++ b/drivers/pinctrl/pinctrl-mcp23s08.h @@ -36,7 +36,6 @@ struct mcp23s08 { struct mutex lock; struct gpio_chip chip; - struct irq_chip irq_chip; struct regmap *regmap; struct device *dev; -- GitLab From c36f8c06ebd0c4feda85b178d927e6e04dbe4c3f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:09 +0200 Subject: [PATCH 3038/5631] pinctrl: st: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. I switched to using irqd_to_hwirq() consistently while we are at it. This driver does not use the GPIOCHIP_IRQ_RESOURCE_HELPERS as it defines its own resource reservations, simply in order to turn IRQ lines into inputs on initialization. Also switched the open coded calls to gpiochip_lock_as_irq() to gpiochip_reqres_irq() so we also get the right module reference counting. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-7-503788a7f6e6@linaro.org --- drivers/pinctrl/pinctrl-st.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c index 1409339f0279..c1f36b164ea5 100644 --- a/drivers/pinctrl/pinctrl-st.c +++ b/drivers/pinctrl/pinctrl-st.c @@ -1313,7 +1313,8 @@ static void st_gpio_irq_mask(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct st_gpio_bank *bank = gpiochip_get_data(gc); - writel(BIT(d->hwirq), bank->base + REG_PIO_CLR_PMASK); + writel(BIT(irqd_to_hwirq(d)), bank->base + REG_PIO_CLR_PMASK); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void st_gpio_irq_unmask(struct irq_data *d) @@ -1321,7 +1322,8 @@ static void st_gpio_irq_unmask(struct irq_data *d) struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct st_gpio_bank *bank = gpiochip_get_data(gc); - writel(BIT(d->hwirq), bank->base + REG_PIO_SET_PMASK); + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); + writel(BIT(irqd_to_hwirq(d)), bank->base + REG_PIO_SET_PMASK); } static int st_gpio_irq_request_resources(struct irq_data *d) @@ -1330,14 +1332,14 @@ static int st_gpio_irq_request_resources(struct irq_data *d) st_gpio_direction_input(gc, d->hwirq); - return gpiochip_lock_as_irq(gc, d->hwirq); + return gpiochip_reqres_irq(gc, d->hwirq); } static void st_gpio_irq_release_resources(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - gpiochip_unlock_as_irq(gc, d->hwirq); + gpiochip_relres_irq(gc, d->hwirq); } static int st_gpio_irq_set_type(struct irq_data *d, unsigned type) @@ -1492,7 +1494,7 @@ static const struct gpio_chip st_gpio_template = { .ngpio = ST_GPIO_PINS_PER_BANK, }; -static struct irq_chip st_gpio_irqchip = { +static const struct irq_chip st_gpio_irqchip = { .name = "GPIO", .irq_request_resources = st_gpio_irq_request_resources, .irq_release_resources = st_gpio_irq_release_resources, @@ -1500,7 +1502,7 @@ static struct irq_chip st_gpio_irqchip = { .irq_mask = st_gpio_irq_mask, .irq_unmask = st_gpio_irq_unmask, .irq_set_type = st_gpio_irq_set_type, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE, }; static int st_gpiolib_register_bank(struct st_pinctrl *info, @@ -1570,7 +1572,7 @@ static int st_gpiolib_register_bank(struct st_pinctrl *info, } girq = &bank->gpio_chip.irq; - girq->chip = &st_gpio_irqchip; + gpio_irq_chip_set_chip(girq, &st_gpio_irqchip); girq->parent_handler = st_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(dev, 1, sizeof(*girq->parents), -- GitLab From 7341944c78d544d4f96cfee3c2d56ceec94d83a4 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:10 +0200 Subject: [PATCH 3039/5631] pinctrl: stmfx: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. This driver rolls it's own resource handling and does not use GPIOCHIP_IRQ_RESOURCE_HELPERS. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-8-503788a7f6e6@linaro.org --- drivers/pinctrl/pinctrl-stmfx.c | 36 ++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c index 3c031692e44d..ab23d7ac3107 100644 --- a/drivers/pinctrl/pinctrl-stmfx.c +++ b/drivers/pinctrl/pinctrl-stmfx.c @@ -85,7 +85,6 @@ struct stmfx_pinctrl { struct pinctrl_dev *pctl_dev; struct pinctrl_desc pctl_desc; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; struct mutex lock; /* IRQ bus lock */ unsigned long gpio_valid_mask; /* Cache of IRQ_GPI_* registers for bus_lock */ @@ -427,6 +426,7 @@ static void stmfx_pinctrl_irq_mask(struct irq_data *data) u32 mask = get_mask(data->hwirq); pctl->irq_gpi_src[reg] &= ~mask; + gpiochip_disable_irq(gpio_chip, irqd_to_hwirq(data)); } static void stmfx_pinctrl_irq_unmask(struct irq_data *data) @@ -436,6 +436,7 @@ static void stmfx_pinctrl_irq_unmask(struct irq_data *data) u32 reg = get_reg(data->hwirq); u32 mask = get_mask(data->hwirq); + gpiochip_enable_irq(gpio_chip, irqd_to_hwirq(data)); pctl->irq_gpi_src[reg] |= mask; } @@ -592,6 +593,26 @@ static irqreturn_t stmfx_pinctrl_irq_thread_fn(int irq, void *dev_id) return IRQ_HANDLED; } +static void stmfx_pinctrl_irq_print_chip(struct irq_data *d, struct seq_file *p) +{ + struct gpio_chip *gpio_chip = irq_data_get_irq_chip_data(d); + struct stmfx_pinctrl *pctl = gpiochip_get_data(gpio_chip); + + seq_printf(p, dev_name(pctl->dev)); +} + +static const struct irq_chip stmfx_pinctrl_irq_chip = { + .irq_mask = stmfx_pinctrl_irq_mask, + .irq_unmask = stmfx_pinctrl_irq_unmask, + .irq_set_type = stmfx_pinctrl_irq_set_type, + .irq_bus_lock = stmfx_pinctrl_irq_bus_lock, + .irq_bus_sync_unlock = stmfx_pinctrl_irq_bus_sync_unlock, + .irq_request_resources = stmfx_gpio_irq_request_resources, + .irq_release_resources = stmfx_gpio_irq_release_resources, + .irq_print_chip = stmfx_pinctrl_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, +}; + static int stmfx_pinctrl_gpio_function_enable(struct stmfx_pinctrl *pctl) { struct pinctrl_gpio_range *gpio_range; @@ -678,17 +699,8 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) pctl->gpio_chip.ngpio = pctl->pctl_desc.npins; pctl->gpio_chip.can_sleep = true; - pctl->irq_chip.name = dev_name(pctl->dev); - pctl->irq_chip.irq_mask = stmfx_pinctrl_irq_mask; - pctl->irq_chip.irq_unmask = stmfx_pinctrl_irq_unmask; - pctl->irq_chip.irq_set_type = stmfx_pinctrl_irq_set_type; - pctl->irq_chip.irq_bus_lock = stmfx_pinctrl_irq_bus_lock; - pctl->irq_chip.irq_bus_sync_unlock = stmfx_pinctrl_irq_bus_sync_unlock; - pctl->irq_chip.irq_request_resources = stmfx_gpio_irq_request_resources; - pctl->irq_chip.irq_release_resources = stmfx_gpio_irq_release_resources; - girq = &pctl->gpio_chip.irq; - girq->chip = &pctl->irq_chip; + gpio_irq_chip_set_chip(girq, &stmfx_pinctrl_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; @@ -710,7 +722,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev) ret = devm_request_threaded_irq(pctl->dev, irq, NULL, stmfx_pinctrl_irq_thread_fn, IRQF_ONESHOT, - pctl->irq_chip.name, pctl); + dev_name(pctl->dev), pctl); if (ret) { dev_err(pctl->dev, "cannot request irq%d\n", irq); return ret; -- GitLab From df60325839efcc0fa37f5ec64c0e29f5d84e56c8 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 4 Apr 2023 11:43:11 +0200 Subject: [PATCH 3040/5631] pinctrl: sx150x: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. I switched to consistently using irqd_to_hwirq() consistently while we are at it. As the driver now needs to get the gpio_chip in the .irq_mask and .irq_unmask callbacks, I switched to a pattern where we first fetch the gpio_chip and then the state container from that in two steps. The compiler will do the same thing anyway. Cc: Marc Zyngier Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230403-immutable-irqchips-v1-9-503788a7f6e6@linaro.org --- drivers/pinctrl/pinctrl-sx150x.c | 64 ++++++++++++++++++-------------- 1 file changed, 37 insertions(+), 27 deletions(-) diff --git a/drivers/pinctrl/pinctrl-sx150x.c b/drivers/pinctrl/pinctrl-sx150x.c index 87fcbfbf49b7..7632ffc3946f 100644 --- a/drivers/pinctrl/pinctrl-sx150x.c +++ b/drivers/pinctrl/pinctrl-sx150x.c @@ -99,7 +99,6 @@ struct sx150x_pinctrl { struct pinctrl_dev *pctldev; struct pinctrl_desc pinctrl_desc; struct gpio_chip gpio; - struct irq_chip irq_chip; struct regmap *regmap; struct { u32 sense; @@ -487,19 +486,21 @@ static int sx150x_gpio_direction_output(struct gpio_chip *chip, static void sx150x_irq_mask(struct irq_data *d) { - struct sx150x_pinctrl *pctl = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int n = d->hwirq; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); + unsigned int n = irqd_to_hwirq(d); pctl->irq.masked |= BIT(n); + gpiochip_disable_irq(gc, n); } static void sx150x_irq_unmask(struct irq_data *d) { - struct sx150x_pinctrl *pctl = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); - unsigned int n = d->hwirq; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); + unsigned int n = irqd_to_hwirq(d); + gpiochip_enable_irq(gc, n); pctl->irq.masked &= ~BIT(n); } @@ -520,14 +521,14 @@ static void sx150x_irq_set_sense(struct sx150x_pinctrl *pctl, static int sx150x_irq_set_type(struct irq_data *d, unsigned int flow_type) { - struct sx150x_pinctrl *pctl = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); unsigned int n, val = 0; if (flow_type & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW)) return -EINVAL; - n = d->hwirq; + n = irqd_to_hwirq(d); if (flow_type & IRQ_TYPE_EDGE_RISING) val |= SX150X_IRQ_TYPE_EDGE_RISING; @@ -562,22 +563,42 @@ static irqreturn_t sx150x_irq_thread_fn(int irq, void *dev_id) static void sx150x_irq_bus_lock(struct irq_data *d) { - struct sx150x_pinctrl *pctl = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); mutex_lock(&pctl->lock); } static void sx150x_irq_bus_sync_unlock(struct irq_data *d) { - struct sx150x_pinctrl *pctl = - gpiochip_get_data(irq_data_get_irq_chip_data(d)); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); regmap_write(pctl->regmap, pctl->data->reg_irq_mask, pctl->irq.masked); regmap_write(pctl->regmap, pctl->data->reg_sense, pctl->irq.sense); mutex_unlock(&pctl->lock); } + +static void sx150x_irq_print_chip(struct irq_data *d, struct seq_file *p) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct sx150x_pinctrl *pctl = gpiochip_get_data(gc); + + seq_printf(p, pctl->client->name); +} + +static const struct irq_chip sx150x_irq_chip = { + .irq_mask = sx150x_irq_mask, + .irq_unmask = sx150x_irq_unmask, + .irq_set_type = sx150x_irq_set_type, + .irq_bus_lock = sx150x_irq_bus_lock, + .irq_bus_sync_unlock = sx150x_irq_bus_sync_unlock, + .irq_print_chip = sx150x_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int sx150x_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, unsigned long *config) { @@ -1181,19 +1202,8 @@ static int sx150x_probe(struct i2c_client *client) if (client->irq > 0) { struct gpio_irq_chip *girq; - pctl->irq_chip.irq_mask = sx150x_irq_mask; - pctl->irq_chip.irq_unmask = sx150x_irq_unmask; - pctl->irq_chip.irq_set_type = sx150x_irq_set_type; - pctl->irq_chip.irq_bus_lock = sx150x_irq_bus_lock; - pctl->irq_chip.irq_bus_sync_unlock = sx150x_irq_bus_sync_unlock; - pctl->irq_chip.name = devm_kstrdup(dev, client->name, - GFP_KERNEL); - if (!pctl->irq_chip.name) - return -ENOMEM; - pctl->irq.masked = ~0; pctl->irq.sense = 0; - /* * Because sx150x_irq_threaded_fn invokes all of the * nested interrupt handlers via handle_nested_irq, @@ -1206,7 +1216,7 @@ static int sx150x_probe(struct i2c_client *client) * called (should not happen) */ girq = &pctl->gpio.irq; - girq->chip = &pctl->irq_chip; + gpio_irq_chip_set_chip(girq, &sx150x_irq_chip); /* This will let us handle the parent IRQ in the driver */ girq->parent_handler = NULL; girq->num_parents = 0; @@ -1219,7 +1229,7 @@ static int sx150x_probe(struct i2c_client *client) sx150x_irq_thread_fn, IRQF_ONESHOT | IRQF_SHARED | IRQF_TRIGGER_FALLING, - pctl->irq_chip.name, pctl); + client->name, pctl); if (ret < 0) return ret; } -- GitLab From 7a306e3eabf2b2fd8cffa69b87b32dbf814d79ce Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Fri, 14 Apr 2023 10:14:49 +0200 Subject: [PATCH 3041/5631] cacheinfo: Check sib_leaf in cache_leaves_are_shared() If there is no ACPI/DT information, it is assumed that L1 caches are private and L2 (and higher) caches are shared. A cache is 'shared' between two CPUs if it is accessible from these two CPUs. Each CPU owns a representation (i.e. has a dedicated cacheinfo struct) of the caches it has access to. cache_leaves_are_shared() tries to identify whether two representations are designating the same actual cache. In cache_leaves_are_shared(), if 'this_leaf' is a L2 cache (or higher) and 'sib_leaf' is a L1 cache, the caches are detected as shared as only this_leaf's cache level is checked. This is leads to setting sib_leaf as being shared with another CPU, which is incorrect as this is a L1 cache. Check 'sib_leaf->level'. Also update the comment as the function is called when populating 'shared_cpu_map'. Fixes: f16d1becf96f ("cacheinfo: Use cache identifiers to check if the caches are shared if available") Signed-off-by: Pierre Gondois Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230414081453.244787-2-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- drivers/base/cacheinfo.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index 6e0a44bad305..ba14c7872e4a 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -38,11 +38,10 @@ static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf, { /* * For non DT/ACPI systems, assume unique level 1 caches, - * system-wide shared caches for all other levels. This will be used - * only if arch specific code has not populated shared_cpu_map + * system-wide shared caches for all other levels. */ if (!(IS_ENABLED(CONFIG_OF) || IS_ENABLED(CONFIG_ACPI))) - return !(this_leaf->level == 1); + return (this_leaf->level != 1) && (sib_leaf->level != 1); if ((sib_leaf->attributes & CACHE_ID) && (this_leaf->attributes & CACHE_ID)) -- GitLab From cde0fbff07eff7e4e0e85fa053fe19a24c86b1e0 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Fri, 14 Apr 2023 10:14:50 +0200 Subject: [PATCH 3042/5631] cacheinfo: Check cache properties are present in DT If a Device Tree (DT) is used, the presence of cache properties is assumed. Not finding any is not considered. For arm64 platforms, cache information can be fetched from the clidr_el1 register. Checking whether cache information is available in the DT allows to switch to using clidr_el1. init_of_cache_level() \-of_count_cache_leaves() will assume there a 2 cache leaves (L1 data/instruction caches), which can be different from clidr_el1 information. cache_setup_of_node() tries to read cache properties in the DT. If there are none, this is considered a success. Knowing no information was available would allow to switch to using clidr_el1. Fixes: de0df442ee49 ("cacheinfo: Check 'cache-unified' property to count cache leaves") Reported-by: Alexandre Ghiti Link: https://lore.kernel.org/all/20230404-hatred-swimmer-6fecdf33b57a@spud/ Signed-off-by: Pierre Gondois Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230414081453.244787-3-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- drivers/base/cacheinfo.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index ba14c7872e4a..f16e5a82f0f3 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -78,6 +78,9 @@ bool last_level_cache_is_shared(unsigned int cpu_x, unsigned int cpu_y) } #ifdef CONFIG_OF + +static bool of_check_cache_nodes(struct device_node *np); + /* OF properties to query for a given cache type */ struct cache_type_info { const char *size_prop; @@ -205,6 +208,11 @@ static int cache_setup_of_node(unsigned int cpu) return -ENOENT; } + if (!of_check_cache_nodes(np)) { + of_node_put(np); + return -ENOENT; + } + prev = np; while (index < cache_leaves(cpu)) { @@ -229,6 +237,25 @@ static int cache_setup_of_node(unsigned int cpu) return 0; } +static bool of_check_cache_nodes(struct device_node *np) +{ + struct device_node *next; + + if (of_property_present(np, "cache-size") || + of_property_present(np, "i-cache-size") || + of_property_present(np, "d-cache-size") || + of_property_present(np, "cache-unified")) + return true; + + next = of_find_next_cache_node(np); + if (next) { + of_node_put(next); + return true; + } + + return false; +} + static int of_count_cache_leaves(struct device_node *np) { unsigned int leaves = 0; @@ -260,6 +287,11 @@ int init_of_cache_level(unsigned int cpu) struct device_node *prev = NULL; unsigned int levels = 0, leaves, level; + if (!of_check_cache_nodes(np)) { + of_node_put(np); + return -ENOENT; + } + leaves = of_count_cache_leaves(np); if (leaves > 0) levels = 1; -- GitLab From 3522340199cc060b70f0094e3039bdb43c3f6ee1 Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Fri, 14 Apr 2023 10:14:51 +0200 Subject: [PATCH 3043/5631] arch_topology: Remove early cacheinfo error message if -ENOENT fetch_cache_info() tries to get the number of cache leaves/levels for each CPU in order to pre-allocate memory for cacheinfo struct. Allocating this memory later triggers a: 'BUG: sleeping function called from invalid context' in PREEMPT_RT kernels. If there is no cache related information available in DT or ACPI, fetch_cache_info() fails and an error message is printed: 'Early cacheinfo failed, ret = ...' Not having cache information should be a valid configuration. Remove the error message if fetch_cache_info() fails with -ENOENT. Suggested-by: Conor Dooley Link: https://lore.kernel.org/all/20230404-hatred-swimmer-6fecdf33b57a@spud/ Signed-off-by: Pierre Gondois Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230414081453.244787-4-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- drivers/base/arch_topology.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 147fb7d4af96..b741b5ba82bd 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -843,10 +843,11 @@ void __init init_cpu_topology(void) for_each_possible_cpu(cpu) { ret = fetch_cache_info(cpu); - if (ret) { + if (!ret) + continue; + else if (ret != -ENOENT) pr_err("Early cacheinfo failed, ret = %d\n", ret); - break; - } + return; } } -- GitLab From ef9f643a9f8b62bcbcc51f0e0af8599adc2e17ed Mon Sep 17 00:00:00 2001 From: Pierre Gondois Date: Fri, 14 Apr 2023 10:14:52 +0200 Subject: [PATCH 3044/5631] cacheinfo: Add use_arch[|_cache]_info field/function The cache information can be extracted from either a Device Tree (DT), the PPTT ACPI table, or arch registers (clidr_el1 for arm64). The clidr_el1 register is used only if DT/ACPI information is not available. It does not states how caches are shared among CPUs. Add a use_arch_cache_info field/function to identify when the DT/ACPI doesn't provide cache information. Use this information to assume L1 caches are privates and L2 and higher are shared among all CPUs. Signed-off-by: Pierre Gondois Link: https://lore.kernel.org/r/20230414081453.244787-5-pierre.gondois@arm.com Signed-off-by: Sudeep Holla --- drivers/base/cacheinfo.c | 12 ++++++++++-- include/linux/cacheinfo.h | 6 ++++++ 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index f16e5a82f0f3..45e36721bc24 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -28,6 +28,9 @@ static DEFINE_PER_CPU(struct cpu_cacheinfo, ci_cpu_cacheinfo); #define per_cpu_cacheinfo_idx(cpu, idx) \ (per_cpu_cacheinfo(cpu) + (idx)) +/* Set if no cache information is found in DT/ACPI. */ +static bool use_arch_info; + struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu) { return ci_cacheinfo(cpu); @@ -40,7 +43,8 @@ static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf, * For non DT/ACPI systems, assume unique level 1 caches, * system-wide shared caches for all other levels. */ - if (!(IS_ENABLED(CONFIG_OF) || IS_ENABLED(CONFIG_ACPI))) + if (!(IS_ENABLED(CONFIG_OF) || IS_ENABLED(CONFIG_ACPI)) || + use_arch_info) return (this_leaf->level != 1) && (sib_leaf->level != 1); if ((sib_leaf->attributes & CACHE_ID) && @@ -343,6 +347,10 @@ static int cache_setup_properties(unsigned int cpu) else if (!acpi_disabled) ret = cache_setup_acpi(cpu); + // Assume there is no cache information available in DT/ACPI from now. + if (ret && use_arch_cache_info()) + use_arch_info = true; + return ret; } @@ -361,7 +369,7 @@ static int cache_shared_cpu_map_setup(unsigned int cpu) * to update the shared cpu_map if the cache attributes were * populated early before all the cpus are brought online */ - if (!last_level_cache_is_valid(cpu)) { + if (!last_level_cache_is_valid(cpu) && !use_arch_info) { ret = cache_setup_properties(cpu); if (ret) return ret; diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 6147b2672555..a5cfd44fab45 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -131,4 +131,10 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) return -1; } +#ifdef CONFIG_ARM64 +#define use_arch_cache_info() (true) +#else +#define use_arch_cache_info() (false) +#endif + #endif /* _LINUX_CACHEINFO_H */ -- GitLab From 247ee6c780406513c6031a7f4ea41f1648b03295 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 13 Apr 2023 14:25:48 +0200 Subject: [PATCH 3045/5631] pwm: Remove unused radix tree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The radix tree's only use was to map PWM channels to the global number space. With that number space gone, the radix tree is now unused, so it can simply be removed. Acked-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/core.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 9ce85c6157e4..3dacceaef4a9 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -28,12 +28,11 @@ static DEFINE_MUTEX(pwm_lookup_lock); static LIST_HEAD(pwm_lookup_list); -/* protects access to pwm_chips, allocated_pwms, and pwm_tree */ +/* protects access to pwm_chips and allocated_pwms */ static DEFINE_MUTEX(pwm_lock); static LIST_HEAD(pwm_chips); static DECLARE_BITMAP(allocated_pwms, MAX_PWMS); -static RADIX_TREE(pwm_tree, GFP_KERNEL); /* Called with pwm_lock held */ static int alloc_pwms(unsigned int count) @@ -54,14 +53,6 @@ static int alloc_pwms(unsigned int count) /* Called with pwm_lock held */ static void free_pwms(struct pwm_chip *chip) { - unsigned int i; - - for (i = 0; i < chip->npwm; i++) { - struct pwm_device *pwm = &chip->pwms[i]; - - radix_tree_delete(&pwm_tree, pwm->pwm); - } - bitmap_clear(allocated_pwms, chip->base, chip->npwm); kfree(chip->pwms); @@ -302,8 +293,6 @@ int pwmchip_add(struct pwm_chip *chip) pwm->chip = chip; pwm->pwm = chip->base + i; pwm->hwpwm = i; - - radix_tree_insert(&pwm_tree, pwm->pwm, pwm); } list_add(&chip->list, &pwm_chips); -- GitLab From dd8f7f463394f92c2f402e29cb39f5265ef97776 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 4 Apr 2023 12:11:17 +0100 Subject: [PATCH 3046/5631] MAINTAINERS: Remove Mathieu Poirier as coresight maintainer Mathieu Poirier is no longer involved in maintainig the CoreSight self-hosted tracing subsystem. Mathieu, Thank you very much creating and maintaing the subsystem all these years ! Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Acked-by: Mathieu Poirier Link: https://lore.kernel.org/r/20230404111117.569795-1-suzuki.poulose@arm.com --- CREDITS | 5 +++++ MAINTAINERS | 1 - 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/CREDITS b/CREDITS index 847059166a15..216e86f56dd9 100644 --- a/CREDITS +++ b/CREDITS @@ -3459,6 +3459,11 @@ D: several improvements to system programs S: Oldenburg S: Germany +N: Mathieu Poirier +E: mathieu.poirier@linaro.org +D: CoreSight kernel subsystem, Maintainer 2014-2022 +D: Perf tool support for CoreSight + N: Robert Schwebel E: robert@schwebel.de W: https://www.schwebel.de diff --git a/MAINTAINERS b/MAINTAINERS index 1dc8bd26b6cf..c16edd182e7b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2091,7 +2091,6 @@ F: arch/arm/boot/dts/cx92755* N: digicolor ARM/CORESIGHT FRAMEWORK AND DRIVERS -M: Mathieu Poirier M: Suzuki K Poulose R: Mike Leach R: Leo Yan -- GitLab From e223864f8257afde5e23eca4c006a0d69581a7a2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 12 Apr 2023 11:10:45 -0300 Subject: [PATCH 3047/5631] iommu: Make iommu_release_device() static This is not called outside the core code, and indeed cannot be called correctly outside the bus notifier. Make it static. Signed-off-by: Jason Gunthorpe Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/0-v1-c3da18124d2d+56-rm_iommu_release_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 3 ++- include/linux/iommu.h | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 7abee83610b6..435fc902df19 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -87,6 +87,7 @@ static const char * const iommu_group_resv_type_string[] = { static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data); +static void iommu_release_device(struct device *dev); static int iommu_alloc_default_domain(struct iommu_group *group, struct device *dev); static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, @@ -493,7 +494,7 @@ static void __iommu_group_release_device(struct iommu_group *group, kobject_put(group->devices_kobj); } -void iommu_release_device(struct device *dev) +static void iommu_release_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; struct group_device *device; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 54f535ff9868..c892e06f8357 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -699,7 +699,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) } int iommu_probe_device(struct device *dev); -void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); -- GitLab From f7f9c054a227ad4922070d748b1f4fc4b5657329 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 12 Apr 2023 11:11:58 -0300 Subject: [PATCH 3048/5631] iommu: Remove iommu_group_get_by_id() This is never called. Signed-off-by: Jason Gunthorpe Reviewed-by: Robin Murphy Link: https://lore.kernel.org/r/0-v1-60bbc66d7e92+24-rm_iommu_get_by_id_jgg@nvidia.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 29 ----------------------------- include/linux/iommu.h | 6 ------ 2 files changed, 35 deletions(-) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 435fc902df19..f35058f1d68e 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -882,35 +882,6 @@ struct iommu_group *iommu_group_alloc(void) } EXPORT_SYMBOL_GPL(iommu_group_alloc); -struct iommu_group *iommu_group_get_by_id(int id) -{ - struct kobject *group_kobj; - struct iommu_group *group; - const char *name; - - if (!iommu_group_kset) - return NULL; - - name = kasprintf(GFP_KERNEL, "%d", id); - if (!name) - return NULL; - - group_kobj = kset_find_obj(iommu_group_kset, name); - kfree(name); - - if (!group_kobj) - return NULL; - - group = container_of(group_kobj, struct iommu_group, kobj); - BUG_ON(group->id != id); - - kobject_get(group->devices_kobj); - kobject_put(&group->kobj); - - return group; -} -EXPORT_SYMBOL_GPL(iommu_group_get_by_id); - /** * iommu_group_get_iommudata - retrieve iommu_data registered for a group * @group: the group diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c892e06f8357..7dbdd13d7ce0 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -460,7 +460,6 @@ extern bool iommu_present(struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -extern struct iommu_group *iommu_group_get_by_id(int id); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -746,11 +745,6 @@ static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) return NULL; } -static inline struct iommu_group *iommu_group_get_by_id(int id) -{ - return NULL; -} - static inline void iommu_domain_free(struct iommu_domain *domain) { } -- GitLab From 18996a113f2567aef3057e300e3193ce2df1684c Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Wed, 5 Apr 2023 10:49:22 +0100 Subject: [PATCH 3049/5631] coresight: etm_pmu: Set the module field struct pmu::module must be set to the module owning the PMU driver. Set this for the coresight etm_pmu. Fixes: 8e264c52e1dab ("coresight: core: Allow the coresight core driver to be built as a module") Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230405094922.667834-1-suzuki.poulose@arm.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index a48c97da8165..711f451b6946 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -901,6 +901,7 @@ int __init etm_perf_init(void) etm_pmu.addr_filters_sync = etm_addr_filters_sync; etm_pmu.addr_filters_validate = etm_addr_filters_validate; etm_pmu.nr_addr_filters = ETM_ADDR_CMP_MAX; + etm_pmu.module = THIS_MODULE; ret = perf_pmu_register(&etm_pmu, CORESIGHT_ETM_PMU_NAME, -1); if (ret == 0) -- GitLab From 15def34e2635ab7e0e96f1bc32e1b69609f14942 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Mon, 27 Feb 2023 10:35:08 +0800 Subject: [PATCH 3050/5631] perf/core: Fix hardlockup failure caused by perf throttle commit e050e3f0a71bf ("perf: Fix broken interrupt rate throttling") introduces a change in throttling threshold judgment. Before this, compare hwc->interrupts and max_samples_per_tick, then increase hwc->interrupts by 1, but this commit reverses order of these two behaviors, causing the semantics of max_samples_per_tick to change. In literal sense of "max_samples_per_tick", if hwc->interrupts == max_samples_per_tick, it should not be throttled, therefore, the judgment condition should be changed to "hwc->interrupts > max_samples_per_tick". In fact, this may cause the hardlockup to fail, The minimum value of max_samples_per_tick may be 1, in this case, the return value of __perf_event_account_interrupt function is 1. As a result, nmi_watchdog gets throttled, which would stop PMU (Use x86 architecture as an example, see x86_pmu_handle_irq). Fixes: e050e3f0a71b ("perf: Fix broken interrupt rate throttling") Signed-off-by: Yang Jihong Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230227023508.102230-1-yangjihong1@huawei.com --- kernel/events/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index fb3e436bcd4a..82b95b8e0409 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9433,8 +9433,8 @@ __perf_event_account_interrupt(struct perf_event *event, int throttle) hwc->interrupts = 1; } else { hwc->interrupts++; - if (unlikely(throttle - && hwc->interrupts >= max_samples_per_tick)) { + if (unlikely(throttle && + hwc->interrupts > max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; -- GitLab From e0b081d17a9f4e5c0cbb0e5fbeb1abe3de0f7e4e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:07 -0700 Subject: [PATCH 3051/5631] sched: Fix KCSAN noinstr violation With KCSAN enabled, end_of_stack() can get out-of-lined. Force it inline. Fixes the following warnings: vmlinux.o: warning: objtool: check_stackleak_irqoff+0x2b: call to end_of_stack() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/cc1b4d73d3a428a00d206242a68fdf99a934ca7b.1681320026.git.jpoimboe@kernel.org --- include/linux/sched/task_stack.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 5e799a47431e..f158b025c175 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -23,7 +23,7 @@ static __always_inline void *task_stack_page(const struct task_struct *task) #define setup_thread_stack(new,old) do { } while(0) -static inline unsigned long *end_of_stack(const struct task_struct *task) +static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; -- GitLab From f571da059f86fd9d432aea32c9c7e5aaa53245d8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:08 -0700 Subject: [PATCH 3052/5631] lkdtm/stackleak: Fix noinstr violation Fixes the following warning: vmlinux.o: warning: objtool: check_stackleak_irqoff+0x2b6: call to _printk() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/ee5209f53aa0a62aea58be18f2b78b17606779a6.1681320026.git.jpoimboe@kernel.org --- drivers/misc/lkdtm/stackleak.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/misc/lkdtm/stackleak.c b/drivers/misc/lkdtm/stackleak.c index 025b133297a6..f1d022160913 100644 --- a/drivers/misc/lkdtm/stackleak.c +++ b/drivers/misc/lkdtm/stackleak.c @@ -43,12 +43,14 @@ static void noinstr check_stackleak_irqoff(void) * STACK_END_MAGIC, and in either casee something is seriously wrong. */ if (current_sp < task_stack_low || current_sp >= task_stack_high) { + instrumentation_begin(); pr_err("FAIL: current_stack_pointer (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n", current_sp, task_stack_low, task_stack_high - 1); test_failed = true; goto out; } if (lowest_sp < task_stack_low || lowest_sp >= task_stack_high) { + instrumentation_begin(); pr_err("FAIL: current->lowest_stack (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n", lowest_sp, task_stack_low, task_stack_high - 1); test_failed = true; @@ -86,11 +88,14 @@ static void noinstr check_stackleak_irqoff(void) if (*(unsigned long *)poison_low == STACKLEAK_POISON) continue; + instrumentation_begin(); pr_err("FAIL: non-poison value %lu bytes below poison boundary: 0x%lx\n", poison_high - poison_low, *(unsigned long *)poison_low); test_failed = true; + goto out; } + instrumentation_begin(); pr_info("stackleak stack usage:\n" " high offset: %lu bytes\n" " current: %lu bytes\n" @@ -113,6 +118,7 @@ static void noinstr check_stackleak_irqoff(void) } else { pr_info("OK: the rest of the thread stack is properly erased\n"); } + instrumentation_end(); } static void lkdtm_STACKLEAK_ERASING(void) -- GitLab From e18398e80c73e3cc7d9c3d2e0bc06a4af8f4f1cb Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:29:01 -0700 Subject: [PATCH 3053/5631] Revert "objtool: Support addition to set CFA base" Commit 468af56a7bba ("objtool: Support addition to set CFA base") was added as a preparatory patch for arm64 support, but that support never came. It triggers a false positive warning on x86, so just revert it for now. Fixes the following warning: vmlinux.o: warning: objtool: cdce925_regmap_i2c_write+0xdb: stack state mismatch: cfa1=4+120 cfa2=5+40 Fixes: 468af56a7bba ("objtool: Support addition to set CFA base") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/oe-kbuild-all/202304080538.j5G6h1AB-lkp@intel.com/ --- tools/objtool/check.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index cae6ac6ff246..9440b07cd3b6 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3002,17 +3002,6 @@ static int update_cfi_state(struct instruction *insn, break; } - if (!cfi->drap && op->src.reg == CFI_SP && - op->dest.reg == CFI_BP && cfa->base == CFI_SP && - check_reg_frame_pos(®s[CFI_BP], -cfa->offset + op->src.offset)) { - - /* lea disp(%rsp), %rbp */ - cfa->base = CFI_BP; - cfa->offset -= op->src.offset; - cfi->bp_scratch = false; - break; - } - if (op->src.reg == CFI_SP && cfa->base == CFI_SP) { /* drap: lea disp(%rsp), %drap */ -- GitLab From 7f530fba1123edcad00d59e1a73019814935f0c1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:29:35 -0700 Subject: [PATCH 3054/5631] objtool: Add stackleak instrumentation to uaccess safe list If a function has a large stack frame, the stackleak plugin adds a call to stackleak_track_stack() after the prologue. This function may be called in uaccess-enabled code. Add it to the uaccess safe list. Fixes the following warning: vmlinux.o: warning: objtool: kasan_report+0x12: call to stackleak_track_stack() with UACCESS enabled Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/42e9b487ef89e9b237fd5220ad1c7cf1a2ad7eb8.1681320562.git.jpoimboe@kernel.org --- tools/objtool/check.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9440b07cd3b6..4c8ef8173a79 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1279,6 +1279,8 @@ static const char *uaccess_safe_builtin[] = { "__ubsan_handle_type_mismatch_v1", "__ubsan_handle_shift_out_of_bounds", "__ubsan_handle_load_invalid_value", + /* STACKLEAK */ + "stackleak_track_stack", /* misc */ "csum_partial_copy_generic", "copy_mc_fragile", -- GitLab From e8deb00c0c4808654d1bf96a8f79cf1deb59b631 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 10:24:06 -0700 Subject: [PATCH 3055/5631] context_tracking: Fix KCSAN noinstr violation With KCSAN enabled, even empty inline stubs can be out-of-lined. Force the context_tracking_guest_exit() stub inline. Fixes the following warnings: vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x1be: call to context_tracking_guest_exit() leaves .noinstr.text section vmlinux.o: warning: objtool: svm_vcpu_enter_exit+0x85: call to context_tracking_guest_exit() leaves .noinstr.text section Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/dc93f45abdec90c171108b4b590b7fff5790963c.1681320026.git.jpoimboe@kernel.org --- include/linux/context_tracking.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d4afa8508a80..5ae3abd767b4 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -97,7 +97,7 @@ static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static inline void context_tracking_guest_exit(void) { } +static __always_inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ -- GitLab From 27d000d635ce48b579988e9b3240352a2a0306e0 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 12:03:16 -0700 Subject: [PATCH 3056/5631] scripts/objdump-func: Support multiple functions Allow specifying multiple functions on the cmdline. Note this removes the secret EXTRA_ARGS feature. While at it, spread out the awk to make it more readable. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/0bf5f4f5978660985037b24c6db49b114374eb4d.1681325924.git.jpoimboe@kernel.org --- scripts/objdump-func | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/scripts/objdump-func b/scripts/objdump-func index 4eb463dd9f52..7b15b873d0e2 100755 --- a/scripts/objdump-func +++ b/scripts/objdump-func @@ -3,7 +3,7 @@ # # Disassemble a single function. # -# usage: objdump-func +# usage: objdump-func [ ...] set -o errexit set -o nounset @@ -13,17 +13,33 @@ OBJDUMP="${CROSS_COMPILE:-}objdump" command -v gawk >/dev/null 2>&1 || die "gawk isn't installed" usage() { - echo "usage: objdump-func " >&2 + echo "usage: objdump-func [ ...]" >&2 exit 1 } [[ $# -lt 2 ]] && usage OBJ=$1; shift -FUNC=$1; shift - -# Secret feature to allow adding extra objdump args at the end -EXTRA_ARGS=$@ - -# Note this also matches compiler-added suffixes like ".cold", etc -${OBJDUMP} -wdr $EXTRA_ARGS $OBJ | gawk -M -v f=$FUNC '/^$/ { P=0; } $0 ~ "<" f "(\\..*)?>:" { P=1; O=strtonum("0x" $1); } { if (P) { o=strtonum("0x" $1); printf("%04x ", o-O); print $0; } }' +FUNCS=("$@") + +${OBJDUMP} -wdr $OBJ | gawk -M -v _funcs="${FUNCS[*]}" ' + BEGIN { split(_funcs, funcs); } + /^$/ { func_match=0; } + /<.*>:/ { + f = gensub(/.*<(.*)>:/, "\\1", 1); + for (i in funcs) { + # match compiler-added suffixes like ".cold", etc + if (f ~ "^" funcs[i] "(\\..*)?") { + func_match = 1; + base = strtonum("0x" $1); + break; + } + } + } + { + if (func_match) { + addr = strtonum("0x" $1); + printf("%04x ", addr - base); + print; + } + }' -- GitLab From 246b2c85487a7bc5f6a09098e18a96506b1b55df Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 12:03:17 -0700 Subject: [PATCH 3057/5631] objtool: Add WARN_INSN() It's easier to use and also gives easy access to the instruction's containing function, which is useful for printing that function's symbol. It will also be useful in the future for rate-limiting and disassembly of warned functions. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/2eaa3155c90fba683d8723599f279c46025b75f3.1681325924.git.jpoimboe@kernel.org --- tools/objtool/check.c | 171 ++++++++++----------------- tools/objtool/include/objtool/warn.h | 5 + tools/objtool/orc_gen.c | 9 +- 3 files changed, 70 insertions(+), 115 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4c8ef8173a79..7d1a42b31f60 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1446,7 +1446,7 @@ static void annotate_call_site(struct objtool_file *file, if (opts.mcount && sym->fentry) { if (sibling) - WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset); + WARN_INSN(insn, "tail call to __fentry__ !?!?"); if (opts.mnop) { if (reloc) { reloc->type = R_NONE; @@ -1648,9 +1648,8 @@ static int add_jump_destinations(struct objtool_file *file) continue; } - WARN_FUNC("can't find jump dest instruction at %s+0x%lx", - insn->sec, insn->offset, dest_sec->name, - dest_off); + WARN_INSN(insn, "can't find jump dest instruction at %s+0x%lx", + dest_sec->name, dest_off); return -1; } @@ -1733,13 +1732,12 @@ static int add_call_destinations(struct objtool_file *file) continue; if (!insn_call_dest(insn)) { - WARN_FUNC("unannotated intra-function call", insn->sec, insn->offset); + WARN_INSN(insn, "unannotated intra-function call"); return -1; } if (insn_func(insn) && insn_call_dest(insn)->type != STT_FUNC) { - WARN_FUNC("unsupported call to non-function", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported call to non-function"); return -1; } @@ -1747,10 +1745,8 @@ static int add_call_destinations(struct objtool_file *file) dest_off = arch_dest_reloc_offset(reloc->addend); dest = find_call_destination(reloc->sym->sec, dest_off); if (!dest) { - WARN_FUNC("can't find call dest symbol at %s+0x%lx", - insn->sec, insn->offset, - reloc->sym->sec->name, - dest_off); + WARN_INSN(insn, "can't find call dest symbol at %s+0x%lx", + reloc->sym->sec->name, dest_off); return -1; } @@ -1810,8 +1806,7 @@ static int handle_group_alt(struct objtool_file *file, } else { if (orig_alt_group->last_insn->offset + orig_alt_group->last_insn->len - orig_alt_group->first_insn->offset != special_alt->orig_len) { - WARN_FUNC("weirdly overlapping alternative! %ld != %d", - orig_insn->sec, orig_insn->offset, + WARN_INSN(orig_insn, "weirdly overlapping alternative! %ld != %d", orig_alt_group->last_insn->offset + orig_alt_group->last_insn->len - orig_alt_group->first_insn->offset, @@ -1880,8 +1875,7 @@ static int handle_group_alt(struct objtool_file *file, if (alt_reloc && arch_pc_relative_reloc(alt_reloc) && !arch_support_alt_relocation(special_alt, insn, alt_reloc)) { - WARN_FUNC("unsupported relocation in alternatives section", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported relocation in alternatives section"); return -1; } @@ -1895,8 +1889,7 @@ static int handle_group_alt(struct objtool_file *file, if (dest_off == special_alt->new_off + special_alt->new_len) { insn->jump_dest = next_insn_same_sec(file, orig_alt_group->last_insn); if (!insn->jump_dest) { - WARN_FUNC("can't find alternative jump destination", - insn->sec, insn->offset); + WARN_INSN(insn, "can't find alternative jump destination"); return -1; } } @@ -1930,8 +1923,7 @@ static int handle_jump_alt(struct objtool_file *file, if (orig_insn->type != INSN_JUMP_UNCONDITIONAL && orig_insn->type != INSN_NOP) { - WARN_FUNC("unsupported instruction at jump label", - orig_insn->sec, orig_insn->offset); + WARN_INSN(orig_insn, "unsupported instruction at jump label"); return -1; } @@ -2010,8 +2002,7 @@ static int add_special_section_alts(struct objtool_file *file) if (special_alt->group) { if (!special_alt->orig_len) { - WARN_FUNC("empty alternative entry", - orig_insn->sec, orig_insn->offset); + WARN_INSN(orig_insn, "empty alternative entry"); continue; } @@ -2102,8 +2093,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, } if (!prev_offset) { - WARN_FUNC("can't find switch jump table", - insn->sec, insn->offset); + WARN_INSN(insn, "can't find switch jump table"); return -1; } @@ -2307,8 +2297,7 @@ static int read_unwind_hints(struct objtool_file *file) if (sym && sym->bind == STB_GLOBAL) { if (opts.ibt && insn->type != INSN_ENDBR && !insn->noendbr) { - WARN_FUNC("UNWIND_HINT_IRET_REGS without ENDBR", - insn->sec, insn->offset); + WARN_INSN(insn, "UNWIND_HINT_IRET_REGS without ENDBR"); } } } @@ -2322,8 +2311,7 @@ static int read_unwind_hints(struct objtool_file *file) cfi = *(insn->cfi); if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { - WARN_FUNC("unsupported unwind_hint sp base reg %d", - insn->sec, insn->offset, hint->sp_reg); + WARN_INSN(insn, "unsupported unwind_hint sp base reg %d", hint->sp_reg); return -1; } @@ -2386,8 +2374,7 @@ static int read_retpoline_hints(struct objtool_file *file) insn->type != INSN_CALL_DYNAMIC && insn->type != INSN_RETURN && insn->type != INSN_NOP) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", - insn->sec, insn->offset); + WARN_INSN(insn, "retpoline_safe hint not an indirect jump/call/ret/nop"); return -1; } @@ -2498,8 +2485,7 @@ static int read_intra_function_calls(struct objtool_file *file) } if (insn->type != INSN_CALL) { - WARN_FUNC("intra_function_call not a direct call", - insn->sec, insn->offset); + WARN_INSN(insn, "intra_function_call not a direct call"); return -1; } @@ -2513,8 +2499,7 @@ static int read_intra_function_calls(struct objtool_file *file) dest_off = arch_jump_destination(insn); insn->jump_dest = find_insn(file, insn->sec, dest_off); if (!insn->jump_dest) { - WARN_FUNC("can't find call dest at %s+0x%lx", - insn->sec, insn->offset, + WARN_INSN(insn, "can't find call dest at %s+0x%lx", insn->sec->name, dest_off); return -1; } @@ -2855,7 +2840,7 @@ static int update_cfi_state(struct instruction *insn, /* stack operations don't make sense with an undefined CFA */ if (cfa->base == CFI_UNDEFINED) { if (insn_func(insn)) { - WARN_FUNC("undefined stack state", insn->sec, insn->offset); + WARN_INSN(insn, "undefined stack state"); return -1; } return 0; @@ -3038,8 +3023,7 @@ static int update_cfi_state(struct instruction *insn, } if (op->dest.reg == cfi->cfa.base && !(next_insn && next_insn->hint)) { - WARN_FUNC("unsupported stack register modification", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported stack register modification"); return -1; } @@ -3049,8 +3033,7 @@ static int update_cfi_state(struct instruction *insn, if (op->dest.reg != CFI_SP || (cfi->drap_reg != CFI_UNDEFINED && cfa->base != CFI_SP) || (cfi->drap_reg == CFI_UNDEFINED && cfa->base != CFI_BP)) { - WARN_FUNC("unsupported stack pointer realignment", - insn->sec, insn->offset); + WARN_INSN(insn, "unsupported stack pointer realignment"); return -1; } @@ -3145,8 +3128,7 @@ static int update_cfi_state(struct instruction *insn, break; default: - WARN_FUNC("unknown stack-related instruction", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related instruction"); return -1; } @@ -3235,8 +3217,7 @@ static int update_cfi_state(struct instruction *insn, case OP_DEST_MEM: if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) { - WARN_FUNC("unknown stack-related memory operation", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related memory operation"); return -1; } @@ -3248,8 +3229,7 @@ static int update_cfi_state(struct instruction *insn, break; default: - WARN_FUNC("unknown stack-related instruction", - insn->sec, insn->offset); + WARN_INSN(insn, "unknown stack-related instruction"); return -1; } @@ -3288,8 +3268,7 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn struct alt_group *orig_group = insn->alt_group->orig_group ?: insn->alt_group; struct instruction *orig = orig_group->first_insn; char *where = offstr(insn->sec, insn->offset); - WARN_FUNC("stack layout conflict in alternatives: %s", - orig->sec, orig->offset, where); + WARN_INSN(orig, "stack layout conflict in alternatives: %s", where); free(where); return -1; } @@ -3316,8 +3295,7 @@ static int handle_insn_ops(struct instruction *insn, if (!state->uaccess_stack) { state->uaccess_stack = 1; } else if (state->uaccess_stack >> 31) { - WARN_FUNC("PUSHF stack exhausted", - insn->sec, insn->offset); + WARN_INSN(insn, "PUSHF stack exhausted"); return 1; } state->uaccess_stack <<= 1; @@ -3349,8 +3327,7 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) { - WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: cfa1=%d%+d cfa2=%d%+d", cfi1->cfa.base, cfi1->cfa.offset, cfi2->cfa.base, cfi2->cfa.offset); @@ -3360,8 +3337,7 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) sizeof(struct cfi_reg))) continue; - WARN_FUNC("stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: reg1[%d]=%d%+d reg2[%d]=%d%+d", i, cfi1->regs[i].base, cfi1->regs[i].offset, i, cfi2->regs[i].base, cfi2->regs[i].offset); break; @@ -3369,15 +3345,14 @@ static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) } else if (cfi1->type != cfi2->type) { - WARN_FUNC("stack state mismatch: type1=%d type2=%d", - insn->sec, insn->offset, cfi1->type, cfi2->type); + WARN_INSN(insn, "stack state mismatch: type1=%d type2=%d", + cfi1->type, cfi2->type); } else if (cfi1->drap != cfi2->drap || (cfi1->drap && cfi1->drap_reg != cfi2->drap_reg) || (cfi1->drap && cfi1->drap_offset != cfi2->drap_offset)) { - WARN_FUNC("stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)", - insn->sec, insn->offset, + WARN_INSN(insn, "stack state mismatch: drap1=%d(%d,%d) drap2=%d(%d,%d)", cfi1->drap, cfi1->drap_reg, cfi1->drap_offset, cfi2->drap, cfi2->drap_reg, cfi2->drap_offset); @@ -3485,20 +3460,17 @@ static int validate_call(struct objtool_file *file, { if (state->noinstr && state->instr <= 0 && !noinstr_call_dest(file, insn, insn_call_dest(insn))) { - WARN_FUNC("call to %s() leaves .noinstr.text section", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() leaves .noinstr.text section", call_dest_name(insn)); return 1; } if (state->uaccess && !func_uaccess_safe(insn_call_dest(insn))) { - WARN_FUNC("call to %s() with UACCESS enabled", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() with UACCESS enabled", call_dest_name(insn)); return 1; } if (state->df) { - WARN_FUNC("call to %s() with DF set", - insn->sec, insn->offset, call_dest_name(insn)); + WARN_INSN(insn, "call to %s() with DF set", call_dest_name(insn)); return 1; } @@ -3510,8 +3482,7 @@ static int validate_sibling_call(struct objtool_file *file, struct insn_state *state) { if (insn_func(insn) && has_modified_stack_frame(insn, state)) { - WARN_FUNC("sibling call from callable instruction with modified stack frame", - insn->sec, insn->offset); + WARN_INSN(insn, "sibling call from callable instruction with modified stack frame"); return 1; } @@ -3521,38 +3492,32 @@ static int validate_sibling_call(struct objtool_file *file, static int validate_return(struct symbol *func, struct instruction *insn, struct insn_state *state) { if (state->noinstr && state->instr > 0) { - WARN_FUNC("return with instrumentation enabled", - insn->sec, insn->offset); + WARN_INSN(insn, "return with instrumentation enabled"); return 1; } if (state->uaccess && !func_uaccess_safe(func)) { - WARN_FUNC("return with UACCESS enabled", - insn->sec, insn->offset); + WARN_INSN(insn, "return with UACCESS enabled"); return 1; } if (!state->uaccess && func_uaccess_safe(func)) { - WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", - insn->sec, insn->offset); + WARN_INSN(insn, "return with UACCESS disabled from a UACCESS-safe function"); return 1; } if (state->df) { - WARN_FUNC("return with DF set", - insn->sec, insn->offset); + WARN_INSN(insn, "return with DF set"); return 1; } if (func && has_modified_stack_frame(insn, state)) { - WARN_FUNC("return with modified stack frame", - insn->sec, insn->offset); + WARN_INSN(insn, "return with modified stack frame"); return 1; } if (state->cfi.bp_scratch) { - WARN_FUNC("BP used as a scratch register", - insn->sec, insn->offset); + WARN_INSN(insn, "BP used as a scratch register"); return 1; } @@ -3624,8 +3589,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } if (func && insn->ignore) { - WARN_FUNC("BUG: why am I validating an ignored function?", - sec, insn->offset); + WARN_INSN(insn, "BUG: why am I validating an ignored function?"); return 1; } @@ -3658,14 +3622,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } if (!save_insn) { - WARN_FUNC("no corresponding CFI save for CFI restore", - sec, insn->offset); + WARN_INSN(insn, "no corresponding CFI save for CFI restore"); return 1; } if (!save_insn->visited) { - WARN_FUNC("objtool isn't smart enough to handle this CFI save/restore combo", - sec, insn->offset); + WARN_INSN(insn, "objtool isn't smart enough to handle this CFI save/restore combo"); return 1; } @@ -3725,8 +3687,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, if (opts.stackval && func && !is_fentry_call(insn) && !has_valid_stack_frame(&state)) { - WARN_FUNC("call without frame pointer save/setup", - sec, insn->offset); + WARN_INSN(insn, "call without frame pointer save/setup"); return 1; } @@ -3772,15 +3733,14 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CONTEXT_SWITCH: if (func && (!next_insn || !next_insn->hint)) { - WARN_FUNC("unsupported instruction in callable function", - sec, insn->offset); + WARN_INSN(insn, "unsupported instruction in callable function"); return 1; } return 0; case INSN_STAC: if (state.uaccess) { - WARN_FUNC("recursive UACCESS enable", sec, insn->offset); + WARN_INSN(insn, "recursive UACCESS enable"); return 1; } @@ -3789,12 +3749,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CLAC: if (!state.uaccess && func) { - WARN_FUNC("redundant UACCESS disable", sec, insn->offset); + WARN_INSN(insn, "redundant UACCESS disable"); return 1; } if (func_uaccess_safe(func) && !state.uaccess_stack) { - WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset); + WARN_INSN(insn, "UACCESS-safe disables UACCESS"); return 1; } @@ -3803,7 +3763,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_STD: if (state.df) { - WARN_FUNC("recursive STD", sec, insn->offset); + WARN_INSN(insn, "recursive STD"); return 1; } @@ -3812,7 +3772,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, case INSN_CLD: if (!state.df && func) { - WARN_FUNC("redundant CLD", sec, insn->offset); + WARN_INSN(insn, "redundant CLD"); return 1; } @@ -3920,15 +3880,14 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) case INSN_CALL_DYNAMIC: case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: - WARN_FUNC("early indirect call", insn->sec, insn->offset); + WARN_INSN(insn, "early indirect call"); return 1; case INSN_JUMP_UNCONDITIONAL: case INSN_JUMP_CONDITIONAL: if (!is_sibling_call(insn)) { if (!insn->jump_dest) { - WARN_FUNC("unresolved jump target after linking?!?", - insn->sec, insn->offset); + WARN_INSN(insn, "unresolved jump target after linking?!?"); return -1; } ret = validate_unret(file, insn->jump_dest); @@ -3969,7 +3928,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) return 0; case INSN_RETURN: - WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + WARN_INSN(insn, "RET before UNTRAIN"); return 1; case INSN_NOP: @@ -3982,7 +3941,7 @@ static int validate_unret(struct objtool_file *file, struct instruction *insn) } if (!next) { - WARN_FUNC("teh end!", insn->sec, insn->offset); + WARN_INSN(insn, "teh end!"); return -1; } insn = next; @@ -4006,7 +3965,7 @@ static int validate_unrets(struct objtool_file *file) ret = validate_unret(file, insn); if (ret < 0) { - WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + WARN_INSN(insn, "Failed UNRET validation"); return ret; } warnings += ret; @@ -4034,13 +3993,11 @@ static int validate_retpoline(struct objtool_file *file) if (insn->type == INSN_RETURN) { if (opts.rethunk) { - WARN_FUNC("'naked' return found in RETHUNK build", - insn->sec, insn->offset); + WARN_INSN(insn, "'naked' return found in RETHUNK build"); } else continue; } else { - WARN_FUNC("indirect %s found in RETPOLINE build", - insn->sec, insn->offset, + WARN_INSN(insn, "indirect %s found in RETPOLINE build", insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); } @@ -4419,9 +4376,7 @@ static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn if (noendbr_range(file, dest)) continue; - WARN_FUNC("relocation to !ENDBR: %s", - insn->sec, insn->offset, - offstr(dest->sec, dest->offset)); + WARN_INSN(insn, "relocation to !ENDBR: %s", offstr(dest->sec, dest->offset)); warnings++; } @@ -4523,16 +4478,14 @@ static int validate_sls(struct objtool_file *file) switch (insn->type) { case INSN_RETURN: if (!next_insn || next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after ret", - insn->sec, insn->offset); + WARN_INSN(insn, "missing int3 after ret"); warnings++; } break; case INSN_JUMP_DYNAMIC: if (!next_insn || next_insn->type != INSN_TRAP) { - WARN_FUNC("missing int3 after indirect jump", - insn->sec, insn->offset); + WARN_INSN(insn, "missing int3 after indirect jump"); warnings++; } break; @@ -4555,7 +4508,7 @@ static int validate_reachable_instructions(struct objtool_file *file) if (insn->visited || ignore_unreachable_insn(file, insn)) continue; - WARN_FUNC("unreachable instruction", insn->sec, insn->offset); + WARN_INSN(insn, "unreachable instruction"); return 1; } diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h index a3e79ae75f2e..b1c920dc9516 100644 --- a/tools/objtool/include/objtool/warn.h +++ b/tools/objtool/include/objtool/warn.h @@ -53,6 +53,11 @@ static inline char *offstr(struct section *sec, unsigned long offset) free(_str); \ }) +#define WARN_INSN(insn, format, ...) \ +({ \ + WARN_FUNC(format, insn->sec, insn->offset, ##__VA_ARGS__); \ +}) + #define BT_FUNC(format, insn, ...) \ ({ \ struct instruction *_insn = (insn); \ diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index b327f9ccfe73..48efd1e2f00d 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -47,8 +47,7 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->type = ORC_TYPE_REGS_PARTIAL; break; default: - WARN_FUNC("unknown unwind hint type %d", - insn->sec, insn->offset, cfi->type); + WARN_INSN(insn, "unknown unwind hint type %d", cfi->type); return -1; } @@ -80,8 +79,7 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->sp_reg = ORC_REG_DX; break; default: - WARN_FUNC("unknown CFA base reg %d", - insn->sec, insn->offset, cfi->cfa.base); + WARN_INSN(insn, "unknown CFA base reg %d", cfi->cfa.base); return -1; } @@ -96,8 +94,7 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, orc->bp_reg = ORC_REG_BP; break; default: - WARN_FUNC("unknown BP base reg %d", - insn->sec, insn->offset, bp->base); + WARN_INSN(insn, "unknown BP base reg %d", bp->base); return -1; } -- GitLab From 9290e772baccecec324ae9f2e0b470f870c097de Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 12:03:19 -0700 Subject: [PATCH 3058/5631] objtool: Add symbol iteration helpers Add [sec_]for_each_sym() and use them. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/59023e5886ab125aa30702e633be7732b1acaa7e.1681325924.git.jpoimboe@kernel.org --- tools/objtool/check.c | 98 ++++++++++++----------------- tools/objtool/elf.c | 2 +- tools/objtool/include/objtool/elf.h | 9 +++ 3 files changed, 51 insertions(+), 58 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 7d1a42b31f60..9de3972a9b1c 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -470,7 +470,7 @@ static int decode_instructions(struct objtool_file *file) // printf("%s: last chunk used: %d\n", sec->name, (int)idx); - list_for_each_entry(func, &sec->symbol_list, list) { + sec_for_each_sym(sec, func) { if (func->type != STT_NOTYPE && func->type != STT_FUNC) continue; @@ -924,7 +924,7 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file) static int create_cfi_sections(struct objtool_file *file) { - struct section *sec, *s; + struct section *sec; struct symbol *sym; unsigned int *loc; int idx; @@ -937,19 +937,14 @@ static int create_cfi_sections(struct objtool_file *file) } idx = 0; - for_each_sec(file, s) { - if (!s->text) + for_each_sym(file, sym) { + if (sym->type != STT_FUNC) continue; - list_for_each_entry(sym, &s->symbol_list, list) { - if (sym->type != STT_FUNC) - continue; - - if (strncmp(sym->name, "__cfi_", 6)) - continue; + if (strncmp(sym->name, "__cfi_", 6)) + continue; - idx++; - } + idx++; } sec = elf_create_section(file->elf, ".cfi_sites", 0, sizeof(unsigned int), idx); @@ -957,28 +952,23 @@ static int create_cfi_sections(struct objtool_file *file) return -1; idx = 0; - for_each_sec(file, s) { - if (!s->text) + for_each_sym(file, sym) { + if (sym->type != STT_FUNC) continue; - list_for_each_entry(sym, &s->symbol_list, list) { - if (sym->type != STT_FUNC) - continue; - - if (strncmp(sym->name, "__cfi_", 6)) - continue; + if (strncmp(sym->name, "__cfi_", 6)) + continue; - loc = (unsigned int *)sec->data->d_buf + idx; - memset(loc, 0, sizeof(unsigned int)); + loc = (unsigned int *)sec->data->d_buf + idx; + memset(loc, 0, sizeof(unsigned int)); - if (elf_add_reloc_to_insn(file->elf, sec, - idx * sizeof(unsigned int), - R_X86_64_PC32, - s, sym->offset)) - return -1; + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(unsigned int), + R_X86_64_PC32, + sym->sec, sym->offset)) + return -1; - idx++; - } + idx++; } return 0; @@ -2207,23 +2197,20 @@ static int add_func_jump_tables(struct objtool_file *file, */ static int add_jump_table_alts(struct objtool_file *file) { - struct section *sec; struct symbol *func; int ret; if (!file->rodata) return 0; - for_each_sec(file, sec) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->type != STT_FUNC) - continue; + for_each_sym(file, func) { + if (func->type != STT_FUNC) + continue; - mark_func_jump_tables(file, func); - ret = add_func_jump_tables(file, func); - if (ret) - return ret; - } + mark_func_jump_tables(file, func); + ret = add_func_jump_tables(file, func); + if (ret) + return ret; } return 0; @@ -2535,30 +2522,27 @@ static bool is_profiling_func(const char *name) static int classify_symbols(struct objtool_file *file) { - struct section *sec; struct symbol *func; - for_each_sec(file, sec) { - list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind != STB_GLOBAL) - continue; + for_each_sym(file, func) { + if (func->bind != STB_GLOBAL) + continue; - if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, - strlen(STATIC_CALL_TRAMP_PREFIX_STR))) - func->static_call_tramp = true; + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + strlen(STATIC_CALL_TRAMP_PREFIX_STR))) + func->static_call_tramp = true; - if (arch_is_retpoline(func)) - func->retpoline_thunk = true; + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; - if (arch_is_rethunk(func)) - func->return_thunk = true; + if (arch_is_rethunk(func)) + func->return_thunk = true; - if (arch_ftrace_match(func->name)) - func->fentry = true; + if (arch_ftrace_match(func->name)) + func->fentry = true; - if (is_profiling_func(func->name)) - func->profiling_func = true; - } + if (is_profiling_func(func->name)) + func->profiling_func = true; } return 0; @@ -4213,7 +4197,7 @@ static int validate_section(struct objtool_file *file, struct section *sec) struct symbol *func; int warnings = 0; - list_for_each_entry(func, &sec->symbol_list, list) { + sec_for_each_sym(sec, func) { if (func->type != STT_FUNC) continue; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 6806ce01d933..500e92979a31 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -474,7 +474,7 @@ static int read_symbols(struct elf *elf) /* Create parent/child links for any cold subfunctions */ list_for_each_entry(sec, &elf->sections, list) { - list_for_each_entry(sym, &sec->symbol_list, list) { + sec_for_each_sym(sec, sym) { char pname[MAX_NAME_LEN + 1]; size_t pnamelen; if (sym->type != STT_FUNC) diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h index ad0024da262b..e1ca588eb69d 100644 --- a/tools/objtool/include/objtool/elf.h +++ b/tools/objtool/include/objtool/elf.h @@ -188,4 +188,13 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset); #define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) +#define sec_for_each_sym(sec, sym) \ + list_for_each_entry(sym, &sec->symbol_list, list) + +#define for_each_sym(file, sym) \ + for (struct section *__sec, *__fake = (struct section *)1; \ + __fake; __fake = NULL) \ + for_each_sec(file, __sec) \ + sec_for_each_sym(__sec, sym) + #endif /* _OBJTOOL_ELF_H */ -- GitLab From 6126ed5dfbc656374e851bfdfb128f3aa9e1263a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 12:03:22 -0700 Subject: [PATCH 3059/5631] objtool: Remove superfluous dead_end_function() check annotate_call_site() already sets 'insn->dead_end' for calls to dead end functions. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/5d603a301e9a8b1036b61503385907e154867ace.1681325924.git.jpoimboe@kernel.org --- tools/objtool/check.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9de3972a9b1c..1cf2e2841c47 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4078,8 +4078,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio * It may also insert a UD2 after calling a __noreturn function. */ prev_insn = prev_insn_same_sec(file, insn); - if ((prev_insn->dead_end || - dead_end_function(file, insn_call_dest(prev_insn))) && + if (prev_insn->dead_end && (insn->type == INSN_BUG || (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest && insn->jump_dest->type == INSN_BUG))) -- GitLab From bd456a1bedd20cebd37493f8cb0291294a7356ea Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 13:26:13 -0700 Subject: [PATCH 3060/5631] objtool: Separate prefix code from stack validation code Simplify the prefix code by moving it after validate_reachable_instructions(). Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/d7f31ac2de462d0cd7b1db01b7ecb525c057c8f6.1681331135.git.jpoimboe@kernel.org --- tools/objtool/check.c | 88 ++++++++++++++++++++++++------------------- 1 file changed, 50 insertions(+), 38 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 1cf2e2841c47..8ee4d51de6fa 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4114,54 +4114,61 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio return false; } -static int add_prefix_symbol(struct objtool_file *file, struct symbol *func, - struct instruction *insn) +static int add_prefix_symbol(struct objtool_file *file, struct symbol *func) { - if (!opts.prefix) - return 0; + struct instruction *insn, *prev; - for (;;) { - struct instruction *prev = prev_insn_same_sec(file, insn); - u64 offset; + insn = find_insn(file, func->sec, func->offset); + if (!insn) + return -1; - if (!prev) - break; + for (prev = prev_insn_same_sec(file, insn); + prev; + prev = prev_insn_same_sec(file, prev)) { + u64 offset; if (prev->type != INSN_NOP) - break; + return -1; offset = func->offset - prev->offset; - if (offset >= opts.prefix) { - if (offset == opts.prefix) { - /* - * Since the sec->symbol_list is ordered by - * offset (see elf_add_symbol()) the added - * symbol will not be seen by the iteration in - * validate_section(). - * - * Hence the lack of list_for_each_entry_safe() - * there. - * - * The direct concequence is that prefix symbols - * don't get visited (because pointless), except - * for the logic in ignore_unreachable_insn() - * that needs the terminating insn to be visited - * otherwise it will report the hole. - * - * Hence mark the first instruction of the - * prefix symbol as visisted. - */ - prev->visited |= VISITED_BRANCH; - elf_create_prefix_symbol(file->elf, func, opts.prefix); - } - break; - } - insn = prev; + + if (offset > opts.prefix) + return -1; + + if (offset < opts.prefix) + continue; + + elf_create_prefix_symbol(file->elf, func, opts.prefix); + break; } + if (!prev) + return -1; + return 0; } +static int add_prefix_symbols(struct objtool_file *file) +{ + struct section *sec; + struct symbol *func; + int warnings = 0; + + for_each_sec(file, sec) { + if (!(sec->sh.sh_flags & SHF_EXECINSTR)) + continue; + + sec_for_each_sym(sec, func) { + if (func->type != STT_FUNC) + continue; + + add_prefix_symbol(file, func); + } + } + + return warnings; +} + static int validate_symbol(struct objtool_file *file, struct section *sec, struct symbol *sym, struct insn_state *state) { @@ -4180,8 +4187,6 @@ static int validate_symbol(struct objtool_file *file, struct section *sec, if (!insn || insn->ignore || insn->visited) return 0; - add_prefix_symbol(file, sym, insn); - state->uaccess = sym->uaccess_safe; ret = validate_branch(file, insn_func(insn), insn, *state); @@ -4621,6 +4626,13 @@ int check(struct objtool_file *file) warnings += ret; } + if (opts.prefix) { + ret = add_prefix_symbols(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (opts.ibt) { ret = create_ibt_endbr_seal_sections(file); if (ret < 0) -- GitLab From 4a2c3448ed3d362431c249ec0eb0f90281804ea8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 13:26:14 -0700 Subject: [PATCH 3061/5631] x86/linkage: Fix padding for typed functions CFI typed functions are failing to get padded properly for CONFIG_CALL_PADDING. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/721f0da48d2a49fe907225711b8b76a2b787f9a8.1681331135.git.jpoimboe@kernel.org --- arch/x86/include/asm/linkage.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index dd9b8118f784..0953aa32a324 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -99,7 +99,7 @@ /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ #define SYM_TYPED_FUNC_START(name) \ - SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \ ENDBR /* SYM_FUNC_START -- use for global functions */ -- GitLab From 5743654f5e2ebd56df99f56fca5ba4b23fe3c815 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 13:26:15 -0700 Subject: [PATCH 3062/5631] objtool: Generate ORC data for __pfx code Allow unwinding from prefix code by copying the CFI from the starting instruction of the corresponding function. Even when the NOPs are replaced, they're still stack-invariant instructions so the same ORC entry can be reused everywhere. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/bc3344e51f3e87102f1301a0be0f72a7689ea4a4.1681331135.git.jpoimboe@kernel.org --- tools/objtool/check.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8ee4d51de6fa..df634dafefc4 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -4117,6 +4117,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio static int add_prefix_symbol(struct objtool_file *file, struct symbol *func) { struct instruction *insn, *prev; + struct cfi_state *cfi; insn = find_insn(file, func->sec, func->offset); if (!insn) @@ -4145,6 +4146,19 @@ static int add_prefix_symbol(struct objtool_file *file, struct symbol *func) if (!prev) return -1; + if (!insn->cfi) { + /* + * This can happen if stack validation isn't enabled or the + * function is annotated with STACK_FRAME_NON_STANDARD. + */ + return 0; + } + + /* Propagate insn->cfi to the prefix code */ + cfi = cfi_hash_find_or_add(insn->cfi); + for (; prev != insn; prev = next_insn_same_sec(file, prev)) + prev->cfi = cfi; + return 0; } -- GitLab From 9ea7e6b62c2bd2f7bbfc3f10099df803002dd33b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:31 -0700 Subject: [PATCH 3063/5631] init: Mark [arch_call_]rest_init() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark start_kernel(), arch_call_rest_init(), and rest_init() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Nick Desaulniers Link: https://lore.kernel.org/r/7194ed8a989a85b98d92e62df660f4a90435a723.1681342859.git.jpoimboe@kernel.org --- arch/s390/kernel/setup.c | 2 +- include/linux/start_kernel.h | 4 ++-- init/main.c | 4 ++-- tools/objtool/check.c | 2 ++ 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 8ec5cdf9dadc..4259b6c50516 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -396,7 +396,7 @@ int __init arch_early_irq_init(void) return 0; } -void __init arch_call_rest_init(void) +void __init __noreturn arch_call_rest_init(void) { unsigned long stack; diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 8b369a41c03c..864921e54c92 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -9,7 +9,7 @@ up something else. */ extern asmlinkage void __init start_kernel(void); -extern void __init arch_call_rest_init(void); -extern void __ref rest_init(void); +extern void __init __noreturn arch_call_rest_init(void); +extern void __ref __noreturn rest_init(void); #endif /* _LINUX_START_KERNEL_H */ diff --git a/init/main.c b/init/main.c index 4425d1783d5c..161ed956d738 100644 --- a/init/main.c +++ b/init/main.c @@ -683,7 +683,7 @@ static void __init setup_command_line(char *command_line) static __initdata DECLARE_COMPLETION(kthreadd_done); -noinline void __ref rest_init(void) +noinline void __ref __noreturn rest_init(void) { struct task_struct *tsk; int pid; @@ -889,7 +889,7 @@ static int __init early_randomize_kstack_offset(char *buf) early_param("randomize_kstack_offset", early_randomize_kstack_offset); #endif -void __init __weak arch_call_rest_init(void) +void __init __weak __noreturn arch_call_rest_init(void) { rest_init(); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index df634dafefc4..3d7227f0ea2a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -202,6 +202,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__reiserfs_panic", "__stack_chk_fail", "__ubsan_handle_builtin_unreachable", + "arch_call_rest_init", "arch_cpu_idle_dead", "cpu_bringup_and_idle", "cpu_startup_entry", @@ -217,6 +218,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "machine_real_restart", "make_task_dead", "panic", + "rest_init", "rewind_stack_and_make_dead", "sev_es_terminate", "snp_abort", -- GitLab From 25a6917ca63ad4470bf88535c56f0dec72b570fe Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:32 -0700 Subject: [PATCH 3064/5631] init: Mark start_kernel() __noreturn Now that arch_call_rest_init() is __noreturn, mark its caller start_kernel() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/7069acf026a195f26a88061227fba5a3b0337b9a.1681342859.git.jpoimboe@kernel.org --- include/linux/start_kernel.h | 2 +- init/main.c | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 864921e54c92..a9806a44a605 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -8,7 +8,7 @@ /* Define the prototype for start_kernel here, rather than cluttering up something else. */ -extern asmlinkage void __init start_kernel(void); +extern asmlinkage void __init __noreturn start_kernel(void); extern void __init __noreturn arch_call_rest_init(void); extern void __ref __noreturn rest_init(void); diff --git a/init/main.c b/init/main.c index 161ed956d738..65aab4e9bb49 100644 --- a/init/main.c +++ b/init/main.c @@ -937,7 +937,7 @@ static void __init print_unknown_bootoptions(void) memblock_free(unknown_options, len); } -asmlinkage __visible void __init __no_sanitize_address start_kernel(void) +asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(void) { char *command_line; char *after_dashes; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 3d7227f0ea2a..9aaad9dc6c20 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -222,6 +222,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "rewind_stack_and_make_dead", "sev_es_terminate", "snp_abort", + "start_kernel", "stop_this_cpu", "usercopy_abort", "xen_cpu_bringup_again", -- GitLab From 4208d2d79837ef70f260d6170e3ac7fd6fde7788 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:33 -0700 Subject: [PATCH 3065/5631] x86/head: Mark *_start_kernel() __noreturn Now that start_kernel() is __noreturn, mark its chain of callers __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/c2525f96b88be98ee027ee0291d58003036d4120.1681342859.git.jpoimboe@kernel.org --- arch/x86/include/asm/setup.h | 6 +++--- arch/x86/kernel/head32.c | 2 +- arch/x86/kernel/head64.c | 4 ++-- tools/objtool/check.c | 2 ++ 4 files changed, 8 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index f37cbff7354c..f3495623ac99 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -125,11 +125,11 @@ void clear_bss(void); #ifdef __i386__ -asmlinkage void __init i386_start_kernel(void); +asmlinkage void __init __noreturn i386_start_kernel(void); #else -asmlinkage void __init x86_64_start_kernel(char *real_mode); -asmlinkage void __init x86_64_start_reservations(char *real_mode_data); +asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode); +asmlinkage void __init __noreturn x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index ec6fefbfd3c0..10c27b4261eb 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void) x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; } -asmlinkage __visible void __init i386_start_kernel(void) +asmlinkage __visible void __init __noreturn i386_start_kernel(void) { /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 387e4b12e823..49f7629b17f7 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -471,7 +471,7 @@ static void __init copy_bootdata(char *real_mode_data) sme_unmap_bootdata(real_mode_data); } -asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) +asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode_data) { /* * Build-time sanity checks on the kernel image and module @@ -537,7 +537,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) x86_64_start_reservations(real_mode_data); } -void __init x86_64_start_reservations(char *real_mode_data) +void __init __noreturn x86_64_start_reservations(char *real_mode_data) { /* version is always not zero if it is copied */ if (!boot_params.hdr.version) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9aaad9dc6c20..a436bc1e63d9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -225,6 +225,8 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "start_kernel", "stop_this_cpu", "usercopy_abort", + "x86_64_start_kernel", + "x86_64_start_reservations", "xen_cpu_bringup_again", "xen_start_kernel", }; -- GitLab From 5ab6876c7843db5fe8bef691c5fdb92518b12070 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:34 -0700 Subject: [PATCH 3066/5631] arm64/cpu: Mark cpu_park_loop() and friends __noreturn In preparation for marking panic_smp_self_stop() __noreturn across the kernel, first mark the arm64 implementation of cpu_park_loop() and related functions __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/55787d3193ea3e295ccbb097abfab0a10ae49d45.1681342859.git.jpoimboe@kernel.org --- arch/arm64/include/asm/exception.h | 4 ++-- arch/arm64/include/asm/smp.h | 6 +++--- arch/arm64/kernel/entry-common.c | 2 +- arch/arm64/kernel/smp.c | 8 +++++--- arch/arm64/kernel/traps.c | 3 +-- 5 files changed, 12 insertions(+), 11 deletions(-) diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 92963f98afec..e73af709cb7a 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -31,7 +31,7 @@ static inline unsigned long disr_to_esr(u64 disr) return esr; } -asmlinkage void handle_bad_stack(struct pt_regs *regs); +asmlinkage void __noreturn handle_bad_stack(struct pt_regs *regs); asmlinkage void el1t_64_sync_handler(struct pt_regs *regs); asmlinkage void el1t_64_irq_handler(struct pt_regs *regs); @@ -80,5 +80,5 @@ void do_el1_fpac(struct pt_regs *regs, unsigned long esr); void do_serror(struct pt_regs *regs, unsigned long esr); void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); -void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); +void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 5733a31bab08..07f4ea1490f4 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -101,9 +101,9 @@ extern int __cpu_disable(void); extern void __cpu_die(unsigned int cpu); extern void __noreturn cpu_die(void); -extern void cpu_die_early(void); +extern void __noreturn cpu_die_early(void); -static inline void cpu_park_loop(void) +static inline void __noreturn cpu_park_loop(void) { for (;;) { wfe(); @@ -123,7 +123,7 @@ static inline void update_cpu_boot_status(int val) * which calls for a kernel panic. Update the boot status and park the calling * CPU. */ -static inline void cpu_panic_kernel(void) +static inline void __noreturn cpu_panic_kernel(void) { update_cpu_boot_status(CPU_PANIC_KERNEL); cpu_park_loop(); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index cce1167199e3..3af3c01c93a6 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -840,7 +840,7 @@ UNHANDLED(el0t, 32, error) #endif /* CONFIG_COMPAT */ #ifdef CONFIG_VMAP_STACK -asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) +asmlinkage void noinstr __noreturn handle_bad_stack(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d5d09a18b4f8..07d156fddb5f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -398,7 +398,7 @@ static void __cpu_try_die(int cpu) * Kill the calling secondary CPU, early in bringup before it is turned * online. */ -void cpu_die_early(void) +void __noreturn cpu_die_early(void) { int cpu = smp_processor_id(); @@ -816,7 +816,7 @@ void arch_irq_work_raise(void) } #endif -static void local_cpu_stop(void) +static void __noreturn local_cpu_stop(void) { set_cpu_online(smp_processor_id(), false); @@ -839,7 +839,7 @@ void panic_smp_self_stop(void) static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); #endif -static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) { #ifdef CONFIG_KEXEC_CORE crash_save_cpu(regs, cpu); @@ -854,6 +854,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) /* just in case */ cpu_park_loop(); +#else + BUG(); #endif } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 4a79ba100799..4bb1b8f47298 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -863,7 +863,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) +void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -905,7 +905,6 @@ void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) nmi_panic(regs, "Asynchronous SError Interrupt"); cpu_park_loop(); - unreachable(); } bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr) -- GitLab From 7412a60decec2a6744cf773280ff17a0f89e8395 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:35 -0700 Subject: [PATCH 3067/5631] cpu: Mark panic_smp_self_stop() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark panic_smp_self_stop() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/92d76ab5c8bf660f04fdcd3da1084519212de248.1681342859.git.jpoimboe@kernel.org --- arch/arm/kernel/smp.c | 2 +- arch/arm64/include/asm/smp.h | 1 - arch/arm64/kernel/smp.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- include/linux/smp.h | 2 +- kernel/panic.c | 2 +- tools/objtool/check.c | 1 + 7 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index d6be4507d22d..f4a4ac028b6b 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -779,7 +779,7 @@ void smp_send_stop(void) * kdump fails. So split out the panic_smp_self_stop() and add * set_cpu_online(smp_processor_id(), false). */ -void panic_smp_self_stop(void) +void __noreturn panic_smp_self_stop(void) { pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n", smp_processor_id()); diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 07f4ea1490f4..f2d26235bfb4 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -143,7 +143,6 @@ bool cpus_are_stuck_in_kernel(void); extern void crash_smp_send_stop(void); extern bool smp_crash_stop_failed(void); -extern void panic_smp_self_stop(void); #endif /* ifndef __ASSEMBLY__ */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 07d156fddb5f..05fe797e4203 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -830,7 +830,7 @@ static void __noreturn local_cpu_stop(void) * that cpu_online_mask gets correctly updated and smp_send_stop() can skip * CPUs that have already stopped themselves. */ -void panic_smp_self_stop(void) +void __noreturn panic_smp_self_stop(void) { local_cpu_stop(); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b2e0d3ce4261..246201d0d879 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -480,7 +480,7 @@ void early_setup_secondary(void) #endif /* CONFIG_SMP */ -void panic_smp_self_stop(void) +void __noreturn panic_smp_self_stop(void) { hard_irq_disable(); spin_begin(); diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..2a737b39cf0a 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -59,7 +59,7 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ -void panic_smp_self_stop(void); +void __noreturn panic_smp_self_stop(void); void nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); diff --git a/kernel/panic.c b/kernel/panic.c index 5cfea8302d23..5e4982db8dc9 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -141,7 +141,7 @@ EXPORT_SYMBOL(panic_blink); /* * Stop ourself in panic -- architecture code may override this */ -void __weak panic_smp_self_stop(void) +void __weak __noreturn panic_smp_self_stop(void) { while (1) cpu_relax(); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a436bc1e63d9..4b52ed6bff66 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -218,6 +218,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "machine_real_restart", "make_task_dead", "panic", + "panic_smp_self_stop", "rest_init", "rewind_stack_and_make_dead", "sev_es_terminate", -- GitLab From 27dea14c7f05106f39850a9239874cd38703b405 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:36 -0700 Subject: [PATCH 3068/5631] cpu: Mark nmi_panic_self_stop() __noreturn In preparation for improving objtool's handling of weak noreturn functions, mark nmi_panic_self_stop() __noreturn. Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/316fc6dfab5a8c4e024c7185484a1ee5fb0afb79.1681342859.git.jpoimboe@kernel.org --- arch/x86/include/asm/reboot.h | 1 - arch/x86/kernel/reboot.c | 2 +- include/linux/smp.h | 2 +- kernel/panic.c | 2 +- tools/objtool/check.c | 1 + 5 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index bc5b4d788c08..9177b4354c3f 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -28,7 +28,6 @@ void __noreturn machine_real_restart(unsigned int type); void cpu_emergency_disable_virtualization(void); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); -void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); void run_crash_ipi_callback(struct pt_regs *regs); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index d03c551defcc..3adbe97015c1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -920,7 +920,7 @@ void run_crash_ipi_callback(struct pt_regs *regs) } /* Override the weak function in kernel/panic.c */ -void nmi_panic_self_stop(struct pt_regs *regs) +void __noreturn nmi_panic_self_stop(struct pt_regs *regs) { while (1) { /* If no CPU is preparing crash dump, we simply loop here. */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 2a737b39cf0a..7b93504eed26 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -60,7 +60,7 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Architecture-dependent code may override them. */ void __noreturn panic_smp_self_stop(void); -void nmi_panic_self_stop(struct pt_regs *regs); +void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); /* diff --git a/kernel/panic.c b/kernel/panic.c index 5e4982db8dc9..886d2ebd0a0d 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -151,7 +151,7 @@ void __weak __noreturn panic_smp_self_stop(void) * Stop ourselves in NMI context if another CPU has already panicked. Arch code * may override this to prepare for crash dumping, e.g. save regs info. */ -void __weak nmi_panic_self_stop(struct pt_regs *regs) +void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs) { panic_smp_self_stop(); } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4b52ed6bff66..8d073bfd7d7f 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -217,6 +217,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "lbug_with_loc", "machine_real_restart", "make_task_dead", + "nmi_panic_self_stop", "panic", "panic_smp_self_stop", "rest_init", -- GitLab From 1c47c8758a11345ac643fa68cb70b708a6668883 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:37 -0700 Subject: [PATCH 3069/5631] objtool: Include weak functions in global_noreturns check If a global function doesn't return, and its prototype has the __noreturn attribute, its weak counterpart must also not return so that it matches the prototype and meets call site expectations. To properly follow the compiled control flow at the call sites, change the global_noreturns check to include both global and weak functions. On the other hand, if a weak function isn't in global_noreturns, assume the prototype doesn't have __noreturn. Even if the weak function doesn't return, call sites treat it like a returnable function. Fixes the following warning: kernel/sched/build_policy.o: warning: objtool: do_idle() falls through to next function play_idle_precise() Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Miroslav Benes Link: https://lore.kernel.org/r/ede3460d63f4a65d282c86f1175bd2662c2286ba.1681342859.git.jpoimboe@kernel.org --- tools/objtool/check.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 8d073bfd7d7f..ae0c94285124 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -236,14 +236,14 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, if (!func) return false; - if (func->bind == STB_WEAK) - return false; - - if (func->bind == STB_GLOBAL) + if (func->bind == STB_GLOBAL || func->bind == STB_WEAK) for (i = 0; i < ARRAY_SIZE(global_noreturns); i++) if (!strcmp(func->name, global_noreturns[i])) return true; + if (func->bind == STB_WEAK) + return false; + if (!func->len) return false; -- GitLab From 09c5ae30d007514a1be870fa5873ad55c3319f3a Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:38 -0700 Subject: [PATCH 3070/5631] btrfs: Mark btrfs_assertfail() __noreturn Fixes a bunch of warnings including: vmlinux.o: warning: objtool: select_reloc_root+0x314: unreachable instruction vmlinux.o: warning: objtool: finish_inode_if_needed+0x15b1: unreachable instruction vmlinux.o: warning: objtool: get_bio_sector_nr+0x259: unreachable instruction vmlinux.o: warning: objtool: raid_wait_read_end_io+0xc26: unreachable instruction vmlinux.o: warning: objtool: raid56_parity_alloc_scrub_rbio+0x37b: unreachable instruction ... Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/960bd9c0c9e3cfc409ba9c35a17644b11b832956.1681342859.git.jpoimboe@kernel.org --- fs/btrfs/messages.c | 2 +- fs/btrfs/messages.h | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/messages.c b/fs/btrfs/messages.c index fde5aaa6e7c9..310a05cf95ef 100644 --- a/fs/btrfs/messages.c +++ b/fs/btrfs/messages.c @@ -253,7 +253,7 @@ void __cold _btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, #endif #ifdef CONFIG_BTRFS_ASSERT -void __cold btrfs_assertfail(const char *expr, const char *file, int line) +void __cold __noreturn btrfs_assertfail(const char *expr, const char *file, int line) { pr_err("assertion failed: %s, in %s:%d\n", expr, file, line); BUG(); diff --git a/fs/btrfs/messages.h b/fs/btrfs/messages.h index 8c516ee58ff9..ac2d1982ba3d 100644 --- a/fs/btrfs/messages.h +++ b/fs/btrfs/messages.h @@ -160,7 +160,7 @@ do { \ } while (0) #ifdef CONFIG_BTRFS_ASSERT -void __cold btrfs_assertfail(const char *expr, const char *file, int line); +void __cold __noreturn btrfs_assertfail(const char *expr, const char *file, int line); #define ASSERT(expr) \ (likely(expr) ? (void)0 : btrfs_assertfail(#expr, __FILE__, __LINE__)) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index ae0c94285124..ceb98489d718 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -204,6 +204,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "__ubsan_handle_builtin_unreachable", "arch_call_rest_init", "arch_cpu_idle_dead", + "btrfs_assertfail", "cpu_bringup_and_idle", "cpu_startup_entry", "do_exit", -- GitLab From 52668badd34b4b346f32c33a9bcba069a06c3caa Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:39 -0700 Subject: [PATCH 3071/5631] x86/cpu: Mark {hlt,resume}_play_dead() __noreturn Fixes the following warning: vmlinux.o: warning: objtool: resume_play_dead+0x21: unreachable instruction Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/ce1407c4bf88b1334fe40413126343792a77ca50.1681342859.git.jpoimboe@kernel.org --- arch/x86/include/asm/smp.h | 2 +- arch/x86/kernel/smpboot.c | 2 +- arch/x86/power/cpu.c | 2 +- tools/objtool/check.c | 2 ++ 4 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index e6d1d2810e38..47ce4c79a3b0 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -125,7 +125,7 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); -void hlt_play_dead(void); +void __noreturn hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9013bb28255a..a6da3f94b7b6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1816,7 +1816,7 @@ static inline void mwait_play_dead(void) } } -void hlt_play_dead(void) +void __noreturn hlt_play_dead(void) { if (__this_cpu_read(cpu_info.x86) >= 4) wbinvd(); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 236447ee9beb..7a4d5e911415 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -288,7 +288,7 @@ EXPORT_SYMBOL(restore_processor_state); #endif #if defined(CONFIG_HIBERNATION) && defined(CONFIG_HOTPLUG_CPU) -static void resume_play_dead(void) +static void __noreturn resume_play_dead(void) { play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index ceb98489d718..724a63bdc412 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -212,6 +212,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_task_dead", "ex_handler_msr_mce", "fortify_panic", + "hlt_play_dead", "kthread_complete_and_exit", "kthread_exit", "kunit_try_catch_throw", @@ -222,6 +223,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "panic_smp_self_stop", "rest_init", + "resume_play_dead", "rewind_stack_and_make_dead", "sev_es_terminate", "snp_abort", -- GitLab From 6e36a56a5f617262c0e8ae7e961487361c720b9e Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 12 Apr 2023 16:49:40 -0700 Subject: [PATCH 3072/5631] scsi: message: fusion: Mark mpt_halt_firmware() __noreturn mpt_halt_firmware() doesn't return. Mark it as such. Fixes the following warnings: vmlinux.o: warning: objtool: mptscsih_abort+0x7f4: unreachable instruction vmlinux.o: warning: objtool: mptctl_timeout_expired+0x310: unreachable instruction Reported-by: kernel test robot Reported-by: Mark Rutland Debugged-by: Peter Zijlstra Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/d8129817423422355bf30e90dadc6764261b53e0.1681342859.git.jpoimboe@kernel.org --- drivers/message/fusion/mptbase.c | 2 +- drivers/message/fusion/mptbase.h | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index 9b3ba2df71c7..4f0afce8428d 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6935,7 +6935,7 @@ EXPORT_SYMBOL(mpt_clear_taskmgmt_in_progress_flag); * @ioc: Pointer to MPT_ADAPTER structure * **/ -void +void __noreturn mpt_halt_firmware(MPT_ADAPTER *ioc) { u32 ioc_raw_state; diff --git a/drivers/message/fusion/mptbase.h b/drivers/message/fusion/mptbase.h index 4bd0682c65d3..0f226cdad64f 100644 --- a/drivers/message/fusion/mptbase.h +++ b/drivers/message/fusion/mptbase.h @@ -945,7 +945,7 @@ extern int mpt_raid_phys_disk_get_num_paths(MPT_ADAPTER *ioc, u8 phys_disk_num); extern int mpt_set_taskmgmt_in_progress_flag(MPT_ADAPTER *ioc); extern void mpt_clear_taskmgmt_in_progress_flag(MPT_ADAPTER *ioc); -extern void mpt_halt_firmware(MPT_ADAPTER *ioc); +extern void __noreturn mpt_halt_firmware(MPT_ADAPTER *ioc); /* diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 724a63bdc412..e1b01ea6ad1b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -219,6 +219,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "lbug_with_loc", "machine_real_restart", "make_task_dead", + "mpt_halt_firmware", "nmi_panic_self_stop", "panic", "panic_smp_self_stop", -- GitLab From 611d4c716db0141cfc436994dc5aff1d69c924ad Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Wed, 12 Apr 2023 16:49:41 -0700 Subject: [PATCH 3073/5631] x86/hyperv: Mark hv_ghcb_terminate() as noreturn Annotate the function prototype and definition as noreturn to prevent objtool warnings like: vmlinux.o: warning: objtool: hyperv_init+0x55c: unreachable instruction Also, as per Josh's suggestion, add it to the global_noreturns list. As a comparison, an objdump output without the annotation: [...] 1b63: mov $0x1,%esi 1b68: xor %edi,%edi 1b6a: callq ffffffff8102f680 1b6f: jmpq ffffffff82f217ec # unreachable 1b74: cmpq $0xffffffffffffffff,-0x702a24(%rip) [...] Now, after adding the __noreturn to the function prototype: [...] 17df: callq ffffffff8102f6d0 17e4: test %al,%al 17e6: je ffffffff82f21bb9 [...] 1bb9: mov $0x1,%esi 1bbe: xor %edi,%edi 1bc0: callq ffffffff8102f680 1bc5: nopw %cs:0x0(%rax,%rax,1) # end of function Reported-by: Arnd Bergmann Signed-off-by: Guilherme G. Piccoli Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/32453a703dfcf0d007b473c9acbf70718222b74b.1681342859.git.jpoimboe@kernel.org --- arch/x86/hyperv/ivm.c | 2 +- arch/x86/include/asm/mshyperv.h | 2 +- tools/objtool/check.c | 1 + 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 1dbcbd9da74d..4f79dc76042d 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -127,7 +127,7 @@ static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code, return ES_OK; } -void hv_ghcb_terminate(unsigned int set, unsigned int reason) +void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 4c4c0ec3b62e..09c26e658bcc 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -212,7 +212,7 @@ int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible); void hv_ghcb_msr_write(u64 msr, u64 value); void hv_ghcb_msr_read(u64 msr, u64 *value); bool hv_ghcb_negotiate_protocol(void); -void hv_ghcb_terminate(unsigned int set, unsigned int reason); +void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason); #else static inline void hv_ghcb_msr_write(u64 msr, u64 value) {} static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e1b01ea6ad1b..5b600bbf2389 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -213,6 +213,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "ex_handler_msr_mce", "fortify_panic", "hlt_play_dead", + "hv_ghcb_terminate", "kthread_complete_and_exit", "kthread_exit", "kunit_try_catch_throw", -- GitLab From 430bb0d1c3376c988982f14bcbe71f917c89e1ab Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 4 Apr 2023 18:52:47 -0700 Subject: [PATCH 3074/5631] module: fix kmemleak annotations for non init ELF sections Commit ac3b43283923 ("module: replace module_layout with module_memory") reworked the way to handle memory allocations to make it clearer. But it lost in translation how we handled kmemleak_ignore() or kmemleak_not_leak() for different ELF sections. Fix this and clarify the comments a bit more. Contrary to the old way of using kmemleak_ignore() for init.* ELF sections we stick now only to kmemleak_not_leak() as per suggestion by Catalin Marinas so to avoid any false positives and simplify the code. Fixes: ac3b43283923 ("module: replace module_layout with module_memory") Reported-by: Jim Cromie Acked-by: Song Liu Suggested-by: Catalin Marinas Reviewed-by: Catalin Marinas Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 5cc21083af04..32554d8a5791 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2231,13 +2231,18 @@ static int move_module(struct module *mod, struct load_info *info) } mod->mem[type].size = PAGE_ALIGN(mod->mem[type].size); ptr = module_memory_alloc(mod->mem[type].size, type); - /* - * The pointer to this block is stored in the module structure - * which is inside the block. Just mark it as not being a - * leak. + * The pointer to these blocks of memory are stored on the module + * structure and we keep that around so long as the module is + * around. We only free that memory when we unload the module. + * Just mark them as not being a leak then. The .init* ELF + * sections *do* get freed after boot so we *could* treat them + * slightly differently with kmemleak_ignore() and only grey + * them out as they work as typical memory allocations which + * *do* eventually get freed, but let's just keep things simple + * and avoid *any* false positives. */ - kmemleak_ignore(ptr); + kmemleak_not_leak(ptr); if (!ptr) { t = type; goto out_enomem; -- GitLab From 9403d9cb564b6a3af86cb18fe722097ed7620f6f Mon Sep 17 00:00:00 2001 From: Kamalesh Babulal Date: Fri, 14 Apr 2023 11:18:49 +0530 Subject: [PATCH 3075/5631] docs: cgroup-v1/cpusets: update libcgroup project link Update the libcgroup project link, in the cgroup v1/cpusets documentation. Signed-off-by: Kamalesh Babulal Signed-off-by: Tejun Heo --- Documentation/admin-guide/cgroup-v1/cpusets.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/cgroup-v1/cpusets.rst b/Documentation/admin-guide/cgroup-v1/cpusets.rst index 5d844ed4df69..ae646d621a8a 100644 --- a/Documentation/admin-guide/cgroup-v1/cpusets.rst +++ b/Documentation/admin-guide/cgroup-v1/cpusets.rst @@ -719,7 +719,7 @@ There are ways to query or modify cpusets: cat, rmdir commands from the shell, or their equivalent from C. - via the C library libcpuset. - via the C library libcgroup. - (http://sourceforge.net/projects/libcg/) + (https://github.com/libcgroup/libcgroup/) - via the python application cset. (http://code.google.com/p/cpuset/) -- GitLab From 20aef201dafba6a1ffe9daa145c7f2c525b74aae Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 14 Apr 2023 09:08:09 +0100 Subject: [PATCH 3076/5631] KVM: selftests: Fix spelling mistake "perrmited" -> "permitted" There is a spelling mistake in a test report message. Fix it. Signed-off-by: Colin Ian King Link: https://lore.kernel.org/r/20230414080809.1678603-1-colin.i.king@gmail.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/lib/x86_64/processor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 898b30096c80..d4a0b504b1e0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -731,7 +731,7 @@ void __vm_xsave_require_permission(uint64_t xfeature, const char *name) rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); TEST_ASSERT(bitmask & xfeature, - "'%s' (0x%lx) not permitted after prctl(ARCH_REQ_XCOMP_GUEST_PERM) perrmited=0x%lx", + "'%s' (0x%lx) not permitted after prctl(ARCH_REQ_XCOMP_GUEST_PERM) permitted=0x%lx", name, xfeature, bitmask); } -- GitLab From 6467d0740a2b2a1fc18b5d9dbc86a9705dbc2cf9 Mon Sep 17 00:00:00 2001 From: "K V P, Satyanarayana" Date: Fri, 17 Mar 2023 08:22:22 +0000 Subject: [PATCH 3077/5631] vfio/pci: Add DVSEC PCI Extended Config Capability to user visible list. The Designated Vendor-Specific Extended Capability (DVSEC Capability) is an optional Extended Capability that is permitted to be implemented by any PCI Express Function. This allows PCI Express component vendors to use the Extended Capability mechanism to expose vendor-specific registers that can be present in components by a variety of vendors. A DVSEC Capability structure can tell vendor-specific software which features a particular component supports. An example usage of DVSEC is Intel Platform Monitoring Technology (PMT) for enumerating and accessing hardware monitoring capabilities on a device. PMT encompasses three device monitoring features, Telemetry (device metrics), Watcher (sampling/tracing), and Crashlog. The DVSEC is used to discover these features and provide a BAR offset to their registers with the Intel vendor code. The current VFIO driver does not pass DVSEC capabilities to Virtual Machine (VM) which makes PMT not to work inside the virtual machine. This series adds DVSEC capability to user visible list to allow its use with VFIO. VFIO supports passing of Vendor Specific Extended Capability (VSEC) and raw write access to device. DVSEC also passed to VM in the same way as of VSEC. Signed-off-by: K V P Satyanarayana Link: https://lore.kernel.org/r/20230317082222.3355912-1-satyanarayana.k.v.p@intel.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 523e0144c86f..948cdd464f4e 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -96,6 +96,7 @@ static const u16 pci_ext_cap_length[PCI_EXT_CAP_ID_MAX + 1] = { [PCI_EXT_CAP_ID_SECPCI] = 0, /* not yet */ [PCI_EXT_CAP_ID_PMUX] = 0, /* not yet */ [PCI_EXT_CAP_ID_PASID] = 0, /* not yet */ + [PCI_EXT_CAP_ID_DVSEC] = 0xFF, }; /* @@ -1101,6 +1102,7 @@ int __init vfio_pci_init_perm_bits(void) ret |= init_pci_ext_cap_err_perm(&ecap_perms[PCI_EXT_CAP_ID_ERR]); ret |= init_pci_ext_cap_pwr_perm(&ecap_perms[PCI_EXT_CAP_ID_PWR]); ecap_perms[PCI_EXT_CAP_ID_VNDR].writefn = vfio_raw_config_write; + ecap_perms[PCI_EXT_CAP_ID_DVSEC].writefn = vfio_raw_config_write; if (ret) vfio_pci_uninit_perm_bits(); @@ -1440,6 +1442,11 @@ static int vfio_ext_cap_len(struct vfio_pci_core_device *vdev, u16 ecap, u16 epo return PCI_TPH_BASE_SIZEOF + (sts * 2) + 2; } return PCI_TPH_BASE_SIZEOF; + case PCI_EXT_CAP_ID_DVSEC: + ret = pci_read_config_dword(pdev, epos + PCI_DVSEC_HEADER1, &dword); + if (ret) + return pcibios_err_to_errno(ret); + return PCI_DVSEC_HEADER1_LEN(dword); default: pci_warn(pdev, "%s: unknown length for PCI ecap %#x@%#x\n", __func__, ecap, epos); -- GitLab From 38e4614c27210e63aafad1bb2e4a427515e46d71 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Wed, 29 Mar 2023 14:06:03 +0200 Subject: [PATCH 3078/5631] vfio: correct kdoc for ops structures Address minor omissions from kdoc for ops structures flagged by check-kdoc: ./scripts/kernel-doc -Werror -none include/linux/vfio.h include/linux/vfio.h:114: warning: Function parameter or member 'name' not described in 'vfio_device_ops' include/linux/vfio.h:143: warning: Cannot understand * @migration_set_state: Optional callback to change the migration state for on line 143 - I thought it was a doc line include/linux/vfio.h:168: warning: Cannot understand * @log_start: Optional callback to ask the device start DMA logging. on line 168 - I thought it was a doc line Signed-off-by: Simon Horman Link: https://lore.kernel.org/r/20230329120603.468031-1-horms@kernel.org Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 93134b023968..cb46050045c0 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -68,6 +68,7 @@ struct vfio_device { /** * struct vfio_device_ops - VFIO bus driver device callbacks * + * @name: Name of the device driver. * @init: initialize private fields in device structure * @release: Reclaim private fields in device structure * @bind_iommufd: Called when binding the device to an iommufd @@ -140,6 +141,8 @@ int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id); #endif /** + * struct vfio_migration_ops - VFIO bus device driver migration callbacks + * * @migration_set_state: Optional callback to change the migration state for * devices that support migration. It's mandatory for * VFIO_DEVICE_FEATURE_MIGRATION migration support. @@ -165,6 +168,8 @@ struct vfio_migration_ops { }; /** + * struct vfio_log_ops - VFIO bus device driver logging callbacks + * * @log_start: Optional callback to ask the device start DMA logging. * @log_stop: Optional callback to ask the device stop DMA logging. * @log_read_and_clear: Optional callback to ask the device read -- GitLab From 33ef1411a36b47ae7ecdb919463b0d78576b3832 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Fri, 7 Apr 2023 16:32:49 -0700 Subject: [PATCH 3079/5631] KVM: selftests: Add a common helper for the PMU event filter guest code Split out the common parts of the Intel and AMD guest code in the PMU event filter test into a helper function. This is in preparation for adding additional counters to the test. No functional changes intended. Signed-off-by: Aaron Lewis Link: https://lore.kernel.org/r/20230407233254.957013-2-seanjc@google.com Signed-off-by: Sean Christopherson --- .../kvm/x86_64/pmu_event_filter_test.c | 29 ++++++++++++------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2feef25ba691..13eca9357252 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -100,6 +100,15 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) GUEST_SYNC(0); } +static uint64_t run_and_measure_loop(uint32_t msr_base) +{ + uint64_t branches_retired = rdmsr(msr_base + 0); + + __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); + + return rdmsr(msr_base + 0) - branches_retired; +} + static void intel_guest_code(void) { check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1); @@ -108,16 +117,15 @@ static void intel_guest_code(void) GUEST_SYNC(1); for (;;) { - uint64_t br0, br1; + uint64_t count; wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1); - br0 = rdmsr(MSR_IA32_PMC0); - __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); - br1 = rdmsr(MSR_IA32_PMC0); - GUEST_SYNC(br1 - br0); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x1); + + count = run_and_measure_loop(MSR_IA32_PMC0); + GUEST_SYNC(count); } } @@ -133,15 +141,14 @@ static void amd_guest_code(void) GUEST_SYNC(1); for (;;) { - uint64_t br0, br1; + uint64_t count; wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); - br0 = rdmsr(MSR_K7_PERFCTR0); - __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); - br1 = rdmsr(MSR_K7_PERFCTR0); - GUEST_SYNC(br1 - br0); + + count = run_and_measure_loop(MSR_K7_PERFCTR0); + GUEST_SYNC(count); } } -- GitLab From fa32233d51b9d26369b8371e986c1030c4201fae Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Fri, 7 Apr 2023 16:32:50 -0700 Subject: [PATCH 3080/5631] KVM: selftests: Add helpers for PMC asserts in PMU event filter test Add helper macros to consolidate the asserts that a PMC is/isn't counting (branch) instructions retired. This will make it easier to add additional asserts related to counting instructions later on. No functional changes intended. Signed-off-by: Aaron Lewis [sean: add "INSTRUCTIONS", massage changelog] Link: https://lore.kernel.org/r/20230407233254.957013-3-seanjc@google.com Signed-off-by: Sean Christopherson --- .../kvm/x86_64/pmu_event_filter_test.c | 52 ++++++++++--------- 1 file changed, 27 insertions(+), 25 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 13eca9357252..20a1f4fc2f48 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -244,14 +244,27 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, return f; } +#define ASSERT_PMC_COUNTING_INSTRUCTIONS(count) \ +do { \ + if (count != NUM_BRANCHES) \ + pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ + __func__, count, NUM_BRANCHES); \ + TEST_ASSERT(count, "Allowed PMU event is not counting."); \ +} while (0) + +#define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count) \ +do { \ + if (count) \ + pr_info("%s: Branch instructions retired = %lu (expected 0)\n", \ + __func__, count); \ + TEST_ASSERT(!count, "Disallowed PMU Event is counting"); \ +} while (0) + static void test_without_filter(struct kvm_vcpu *vcpu) { uint64_t count = run_vcpu_to_sync(vcpu); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + ASSERT_PMC_COUNTING_INSTRUCTIONS(count); } static uint64_t test_with_filter(struct kvm_vcpu *vcpu, @@ -269,12 +282,9 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); count = test_with_filter(vcpu, f); - free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(count); } static void test_member_deny_list(struct kvm_vcpu *vcpu) @@ -283,10 +293,8 @@ static void test_member_deny_list(struct kvm_vcpu *vcpu) uint64_t count = test_with_filter(vcpu, f); free(f); - if (count) - pr_info("%s: Branch instructions retired = %lu (expected 0)\n", - __func__, count); - TEST_ASSERT(!count, "Disallowed PMU Event is counting"); + + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count); } static void test_member_allow_list(struct kvm_vcpu *vcpu) @@ -295,10 +303,8 @@ static void test_member_allow_list(struct kvm_vcpu *vcpu) uint64_t count = test_with_filter(vcpu, f); free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(count); } static void test_not_member_deny_list(struct kvm_vcpu *vcpu) @@ -310,10 +316,8 @@ static void test_not_member_deny_list(struct kvm_vcpu *vcpu) remove_event(f, AMD_ZEN_BR_RETIRED); count = test_with_filter(vcpu, f); free(f); - if (count != NUM_BRANCHES) - pr_info("%s: Branch instructions retired = %lu (expected %u)\n", - __func__, count, NUM_BRANCHES); - TEST_ASSERT(count, "Allowed PMU event is not counting"); + + ASSERT_PMC_COUNTING_INSTRUCTIONS(count); } static void test_not_member_allow_list(struct kvm_vcpu *vcpu) @@ -325,10 +329,8 @@ static void test_not_member_allow_list(struct kvm_vcpu *vcpu) remove_event(f, AMD_ZEN_BR_RETIRED); count = test_with_filter(vcpu, f); free(f); - if (count) - pr_info("%s: Branch instructions retired = %lu (expected 0)\n", - __func__, count); - TEST_ASSERT(!count, "Disallowed PMU Event is counting"); + + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count); } /* -- GitLab From c140e93a0c11ac5a56834ac11ddb0f777307b2c1 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Fri, 7 Apr 2023 16:32:51 -0700 Subject: [PATCH 3081/5631] KVM: selftests: Print detailed info in PMU event filter asserts Provide the actual vs. expected count in the PMU event filter test's asserts instead of relying on pr_info() to provide the context, e.g. so that all information needed to triage a failure is readily available even if the environment in which the test is run captures only the assert itself. Signed-off-by: Aaron Lewis [sean: rewrite changelog] Link: https://lore.kernel.org/r/20230407233254.957013-4-seanjc@google.com Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/pmu_event_filter_test.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 20a1f4fc2f48..79feec24ae73 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -246,18 +246,17 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, #define ASSERT_PMC_COUNTING_INSTRUCTIONS(count) \ do { \ - if (count != NUM_BRANCHES) \ + if (count && count != NUM_BRANCHES) \ pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ __func__, count, NUM_BRANCHES); \ - TEST_ASSERT(count, "Allowed PMU event is not counting."); \ + TEST_ASSERT(count, "%s: Branch instructions retired = %lu (expected > 0)", \ + __func__, count); \ } while (0) #define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count) \ do { \ - if (count) \ - pr_info("%s: Branch instructions retired = %lu (expected 0)\n", \ - __func__, count); \ - TEST_ASSERT(!count, "Disallowed PMU Event is counting"); \ + TEST_ASSERT(!count, "%s: Branch instructions retired = %lu (expected 0)", \ + __func__, count); \ } while (0) static void test_without_filter(struct kvm_vcpu *vcpu) -- GitLab From c02c74428288282c9bd5fd37fe4135f3ca419a86 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 7 Apr 2023 16:32:52 -0700 Subject: [PATCH 3082/5631] KVM: selftests: Use error codes to signal errors in PMU event filter test Use '0' to signal success and '-errno' to signal failure in the PMU event filter test so that the values are slightly less magical/arbitrary. Using '0' in the error paths is especially confusing as understanding it's an error value requires following the breadcrumbs to the host code that ultimately consumes the value. Arguably there should also be a #define for "success", but 0/-errno is a common enough pattern that defining another macro on top would likely do more harm than good. Link: https://lore.kernel.org/r/20230407233254.957013-5-seanjc@google.com Reviewed by: Aaron Lewis Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86_64/pmu_event_filter_test.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 79feec24ae73..0329c439b684 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -77,7 +77,7 @@ static const uint64_t event_list[] = { */ static void guest_gp_handler(struct ex_regs *regs) { - GUEST_SYNC(0); + GUEST_SYNC(-EFAULT); } /* @@ -92,12 +92,12 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) wrmsr(msr, v); if (rdmsr(msr) != v) - GUEST_SYNC(0); + GUEST_SYNC(-EIO); v ^= bits_to_flip; wrmsr(msr, v); if (rdmsr(msr) != v) - GUEST_SYNC(0); + GUEST_SYNC(-EIO); } static uint64_t run_and_measure_loop(uint32_t msr_base) @@ -114,7 +114,7 @@ static void intel_guest_code(void) check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1); check_msr(MSR_P6_EVNTSEL0, 0xffff); check_msr(MSR_IA32_PMC0, 0xffff); - GUEST_SYNC(1); + GUEST_SYNC(0); for (;;) { uint64_t count; @@ -138,7 +138,7 @@ static void amd_guest_code(void) { check_msr(MSR_K7_EVNTSEL0, 0xffff); check_msr(MSR_K7_PERFCTR0, 0xffff); - GUEST_SYNC(1); + GUEST_SYNC(0); for (;;) { uint64_t count; @@ -178,13 +178,13 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) */ static bool sanity_check_pmu(struct kvm_vcpu *vcpu) { - bool success; + uint64_t r; vm_install_exception_handler(vcpu->vm, GP_VECTOR, guest_gp_handler); - success = run_vcpu_to_sync(vcpu); + r = run_vcpu_to_sync(vcpu); vm_install_exception_handler(vcpu->vm, GP_VECTOR, NULL); - return success; + return !r; } static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) -- GitLab From e9f322bd23960026275014477e21f7a9445fd926 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 7 Apr 2023 16:32:53 -0700 Subject: [PATCH 3083/5631] KVM: selftests: Copy full counter values from guest in PMU event filter test Use a single struct to track all PMC event counts in the PMU filter test, and copy the full struct to/from the guest when running and measuring each guest workload. Using a common struct avoids naming conflicts, e.g. the loads/stores testcase has claimed "perf_counter", and eliminates the unnecessary truncation of the counter values when they are propagated from the guest MSRs to the host structs. Zero the struct before running the guest workload to ensure that the test doesn't get a false pass due to consuming data from a previous run. Link: https://lore.kernel.org/r/20230407233254.957013-6-seanjc@google.com Reviewed by: Aaron Lewis Signed-off-by: Sean Christopherson --- .../kvm/x86_64/pmu_event_filter_test.c | 170 +++++++++--------- 1 file changed, 80 insertions(+), 90 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 0329c439b684..58d2e17c7304 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -71,6 +71,13 @@ static const uint64_t event_list[] = { AMD_ZEN_BR_RETIRED, }; +struct { + uint64_t loads; + uint64_t stores; + uint64_t loads_stores; + uint64_t branches_retired; +} pmc_results; + /* * If we encounter a #GP during the guest PMU sanity check, then the guest * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0). @@ -100,13 +107,13 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) GUEST_SYNC(-EIO); } -static uint64_t run_and_measure_loop(uint32_t msr_base) +static void run_and_measure_loop(uint32_t msr_base) { - uint64_t branches_retired = rdmsr(msr_base + 0); + const uint64_t branches_retired = rdmsr(msr_base + 0); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); - return rdmsr(msr_base + 0) - branches_retired; + pmc_results.branches_retired = rdmsr(msr_base + 0) - branches_retired; } static void intel_guest_code(void) @@ -117,15 +124,13 @@ static void intel_guest_code(void) GUEST_SYNC(0); for (;;) { - uint64_t count; - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x1); - count = run_and_measure_loop(MSR_IA32_PMC0); - GUEST_SYNC(count); + run_and_measure_loop(MSR_IA32_PMC0); + GUEST_SYNC(0); } } @@ -141,14 +146,12 @@ static void amd_guest_code(void) GUEST_SYNC(0); for (;;) { - uint64_t count; - wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); - count = run_and_measure_loop(MSR_K7_PERFCTR0); - GUEST_SYNC(count); + run_and_measure_loop(MSR_K7_PERFCTR0); + GUEST_SYNC(0); } } @@ -168,6 +171,19 @@ static uint64_t run_vcpu_to_sync(struct kvm_vcpu *vcpu) return uc.args[1]; } +static void run_vcpu_and_sync_pmc_results(struct kvm_vcpu *vcpu) +{ + uint64_t r; + + memset(&pmc_results, 0, sizeof(pmc_results)); + sync_global_to_guest(vcpu->vm, pmc_results); + + r = run_vcpu_to_sync(vcpu); + TEST_ASSERT(!r, "Unexpected sync value: 0x%lx", r); + + sync_global_from_guest(vcpu->vm, pmc_results); +} + /* * In a nested environment or if the vPMU is disabled, the guest PMU * might not work as architected (accessing the PMU MSRs may raise @@ -244,92 +260,93 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, return f; } -#define ASSERT_PMC_COUNTING_INSTRUCTIONS(count) \ +#define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ do { \ - if (count && count != NUM_BRANCHES) \ + uint64_t br = pmc_results.branches_retired; \ + \ + if (br && br != NUM_BRANCHES) \ pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ - __func__, count, NUM_BRANCHES); \ - TEST_ASSERT(count, "%s: Branch instructions retired = %lu (expected > 0)", \ - __func__, count); \ + __func__, br, NUM_BRANCHES); \ + TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \ + __func__, br); \ } while (0) -#define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count) \ +#define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS() \ do { \ - TEST_ASSERT(!count, "%s: Branch instructions retired = %lu (expected 0)", \ - __func__, count); \ + uint64_t br = pmc_results.branches_retired; \ + \ + TEST_ASSERT(!br, "%s: Branch instructions retired = %lu (expected 0)", \ + __func__, br); \ } while (0) static void test_without_filter(struct kvm_vcpu *vcpu) { - uint64_t count = run_vcpu_to_sync(vcpu); + run_vcpu_and_sync_pmc_results(vcpu); - ASSERT_PMC_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } -static uint64_t test_with_filter(struct kvm_vcpu *vcpu, - struct kvm_pmu_event_filter *f) +static void test_with_filter(struct kvm_vcpu *vcpu, + struct kvm_pmu_event_filter *f) { vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); - return run_vcpu_to_sync(vcpu); + run_vcpu_and_sync_pmc_results(vcpu); } static void test_amd_deny_list(struct kvm_vcpu *vcpu) { uint64_t event = EVENT(0x1C2, 0); struct kvm_pmu_event_filter *f; - uint64_t count; f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); - count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - ASSERT_PMC_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); - uint64_t count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } static void test_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); - uint64_t count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - ASSERT_PMC_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); - uint64_t count; remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - ASSERT_PMC_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_COUNTING_INSTRUCTIONS(); } static void test_not_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); - uint64_t count; remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); - count = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(count); + ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS(); } /* @@ -458,51 +475,30 @@ static bool supports_event_mem_inst_retired(void) #define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) -struct perf_counter { - union { - uint64_t raw; - struct { - uint64_t loads:22; - uint64_t stores:22; - uint64_t loads_stores:20; - }; - }; -}; - -static uint64_t masked_events_guest_test(uint32_t msr_base) +static void masked_events_guest_test(uint32_t msr_base) { - uint64_t ld0, ld1, st0, st1, ls0, ls1; - struct perf_counter c; - int val; - /* - * The acutal value of the counters don't determine the outcome of + * The actual value of the counters don't determine the outcome of * the test. Only that they are zero or non-zero. */ - ld0 = rdmsr(msr_base + 0); - st0 = rdmsr(msr_base + 1); - ls0 = rdmsr(msr_base + 2); + const uint64_t loads = rdmsr(msr_base + 0); + const uint64_t stores = rdmsr(msr_base + 1); + const uint64_t loads_stores = rdmsr(msr_base + 2); + int val; + __asm__ __volatile__("movl $0, %[v];" "movl %[v], %%eax;" "incl %[v];" : [v]"+m"(val) :: "eax"); - ld1 = rdmsr(msr_base + 0); - st1 = rdmsr(msr_base + 1); - ls1 = rdmsr(msr_base + 2); - - c.loads = ld1 - ld0; - c.stores = st1 - st0; - c.loads_stores = ls1 - ls0; - - return c.raw; + pmc_results.loads = rdmsr(msr_base + 0) - loads; + pmc_results.stores = rdmsr(msr_base + 1) - stores; + pmc_results.loads_stores = rdmsr(msr_base + 2) - loads_stores; } static void intel_masked_events_guest_code(void) { - uint64_t r; - for (;;) { wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -515,16 +511,13 @@ static void intel_masked_events_guest_code(void) wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x7); - r = masked_events_guest_test(MSR_IA32_PMC0); - - GUEST_SYNC(r); + masked_events_guest_test(MSR_IA32_PMC0); + GUEST_SYNC(0); } } static void amd_masked_events_guest_code(void) { - uint64_t r; - for (;;) { wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL1, 0); @@ -537,26 +530,22 @@ static void amd_masked_events_guest_code(void) wrmsr(MSR_K7_EVNTSEL2, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD_STORE); - r = masked_events_guest_test(MSR_K7_PERFCTR0); - - GUEST_SYNC(r); + masked_events_guest_test(MSR_K7_PERFCTR0); + GUEST_SYNC(0); } } -static struct perf_counter run_masked_events_test(struct kvm_vcpu *vcpu, - const uint64_t masked_events[], - const int nmasked_events) +static void run_masked_events_test(struct kvm_vcpu *vcpu, + const uint64_t masked_events[], + const int nmasked_events) { struct kvm_pmu_event_filter *f; - struct perf_counter r; f = create_pmu_event_filter(masked_events, nmasked_events, KVM_PMU_EVENT_ALLOW, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); - r.raw = test_with_filter(vcpu, f); + test_with_filter(vcpu, f); free(f); - - return r; } /* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ @@ -681,7 +670,6 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, int nevents) { int ntests = ARRAY_SIZE(test_cases); - struct perf_counter c; int i, n; for (i = 0; i < ntests; i++) { @@ -693,13 +681,15 @@ static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, n = append_test_events(test, events, nevents); - c = run_masked_events_test(vcpu, events, n); - TEST_ASSERT(bool_eq(c.loads, test->flags & ALLOW_LOADS) && - bool_eq(c.stores, test->flags & ALLOW_STORES) && - bool_eq(c.loads_stores, + run_masked_events_test(vcpu, events, n); + + TEST_ASSERT(bool_eq(pmc_results.loads, test->flags & ALLOW_LOADS) && + bool_eq(pmc_results.stores, test->flags & ALLOW_STORES) && + bool_eq(pmc_results.loads_stores, test->flags & ALLOW_LOADS_STORES), - "%s loads: %u, stores: %u, loads + stores: %u", - test->msg, c.loads, c.stores, c.loads_stores); + "%s loads: %lu, stores: %lu, loads + stores: %lu", + test->msg, pmc_results.loads, pmc_results.stores, + pmc_results.loads_stores); } } -- GitLab From 457bd7af1a17182e7f1f97eeb5d9107f8699e99d Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Fri, 7 Apr 2023 16:32:54 -0700 Subject: [PATCH 3084/5631] KVM: selftests: Test the PMU event "Instructions retired" Add testing for the event "Instructions retired" (0xc0) in the PMU event filter on both Intel and AMD to ensure that the event doesn't count when it is disallowed. Unlike most of the other events, the event "Instructions retired" will be incremented by KVM when an instruction is emulated. Test that this case is being properly handled and that KVM doesn't increment the counter when that event is disallowed. Signed-off-by: Aaron Lewis Link: https://lore.kernel.org/r/20230307141400.1486314-6-aaronlewis@google.com Link: https://lore.kernel.org/r/20230407233254.957013-7-seanjc@google.com Signed-off-by: Sean Christopherson --- .../kvm/x86_64/pmu_event_filter_test.c | 34 +++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 58d2e17c7304..8cec5c8aca8a 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -54,6 +54,21 @@ #define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0) + +/* + * "Retired instructions", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + * --- and --- + * "Instructions retired", from the Intel SDM, volume 3, + * "Pre-defined Architectural Performance Events." + */ + +#define INST_RETIRED EVENT(0xc0, 0) + /* * This event list comprises Intel's eight architectural events plus * AMD's "retired branch instructions" for Zen[123] (and possibly @@ -61,7 +76,7 @@ */ static const uint64_t event_list[] = { EVENT(0x3c, 0), - EVENT(0xc0, 0), + INST_RETIRED, EVENT(0x3c, 1), EVENT(0x2e, 0x4f), EVENT(0x2e, 0x41), @@ -76,6 +91,7 @@ struct { uint64_t stores; uint64_t loads_stores; uint64_t branches_retired; + uint64_t instructions_retired; } pmc_results; /* @@ -110,10 +126,12 @@ static void check_msr(uint32_t msr, uint64_t bits_to_flip) static void run_and_measure_loop(uint32_t msr_base) { const uint64_t branches_retired = rdmsr(msr_base + 0); + const uint64_t insn_retired = rdmsr(msr_base + 1); __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES})); pmc_results.branches_retired = rdmsr(msr_base + 0) - branches_retired; + pmc_results.instructions_retired = rdmsr(msr_base + 1) - insn_retired; } static void intel_guest_code(void) @@ -127,7 +145,9 @@ static void intel_guest_code(void) wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED); - wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x1); + wrmsr(MSR_P6_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x3); run_and_measure_loop(MSR_IA32_PMC0); GUEST_SYNC(0); @@ -149,6 +169,8 @@ static void amd_guest_code(void) wrmsr(MSR_K7_EVNTSEL0, 0); wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED); + wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED); run_and_measure_loop(MSR_K7_PERFCTR0); GUEST_SYNC(0); @@ -263,20 +285,26 @@ static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f, #define ASSERT_PMC_COUNTING_INSTRUCTIONS() \ do { \ uint64_t br = pmc_results.branches_retired; \ + uint64_t ir = pmc_results.instructions_retired; \ \ if (br && br != NUM_BRANCHES) \ pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \ __func__, br, NUM_BRANCHES); \ TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \ __func__, br); \ + TEST_ASSERT(ir, "%s: Instructions retired = %lu (expected > 0)", \ + __func__, ir); \ } while (0) #define ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS() \ do { \ uint64_t br = pmc_results.branches_retired; \ + uint64_t ir = pmc_results.instructions_retired; \ \ TEST_ASSERT(!br, "%s: Branch instructions retired = %lu (expected 0)", \ __func__, br); \ + TEST_ASSERT(!ir, "%s: Instructions retired = %lu (expected 0)", \ + __func__, ir); \ } while (0) static void test_without_filter(struct kvm_vcpu *vcpu) @@ -329,6 +357,7 @@ static void test_not_member_deny_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY); + remove_event(f, INST_RETIRED); remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); test_with_filter(vcpu, f); @@ -341,6 +370,7 @@ static void test_not_member_allow_list(struct kvm_vcpu *vcpu) { struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW); + remove_event(f, INST_RETIRED); remove_event(f, INTEL_BR_RETIRED); remove_event(f, AMD_ZEN_BR_RETIRED); test_with_filter(vcpu, f); -- GitLab From 17354d1528f902b3a4f66023cd24012e7999c4dc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 14 Apr 2023 11:26:42 -0300 Subject: [PATCH 3085/5631] perf test: Simplify for_each_test() to avoid tripping on -Werror=array-bounds When cross building on debian to the mips 32-bit arch we get these warnings: In function '__cmd_test', inlined from 'cmd_test' at tests/builtin-test.c:561:9: tests/builtin-test.c:260:66: error: array subscript 1 is outside array bounds of 'struct test_suite *[1]' [-Werror=array-bounds] 260 | for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k]) | ^ tests/builtin-test.c:369:9: note: in expansion of macro 'for_each_test' 369 | for_each_test(j, k, t) { | ^~~~~~~~~~~~~ tests/builtin-test.c: In function 'cmd_test': tests/builtin-test.c:36:27: note: at offset 4 into object 'arch_tests' of size 4 36 | struct test_suite *__weak arch_tests[] = { | ^~~~~~~~~~ cc1: all warnings being treated as errors Switch to using a while(!sentinel) for the second level of the 'tests' array to avoid that compiler complaint. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/builtin-test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 35cc3807cc9e..b89d69afcef0 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -256,8 +256,8 @@ static int run_test(struct test_suite *test, int subtest) } #define for_each_test(j, k, t) \ - for (j = 0; j < ARRAY_SIZE(tests); j++) \ - for (k = 0, t = tests[j][k]; tests[j][k]; k++, t = tests[j][k]) + for (j = 0, k = 0; j < ARRAY_SIZE(tests); j++, k = 0) \ + while ((t = tests[j][k++]) != NULL) static int test_and_print(struct test_suite *t, int subtest) { -- GitLab From ffc5e1f3585e31c8f3572389a6418f5149db0fad Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 6 Apr 2023 10:18:16 +0200 Subject: [PATCH 3086/5631] staging: greybus: drop loopback test files The greybus loopback test tool does not belong burried down in a driver-specific directory. If it is needed, it should be somewhere else, like in the testing directory. But as the loopback driver is probably never going to be merged out of the staging directory, let's just delete the test alltogether for now. If it's needed in the future, it can be brought back with a revert. Also, having an Android.mk file in the kernel source tree breaks some Android build systems when trying to build from a read-only source tree, the report of which prompted this being a good reason to remove it as well. Cc: Johan Hovold Cc: Jack Schofield Cc: Vaibhav Nagare Cc: greybus-dev@lists.linaro.org Acked-by: Alex Elder Link: https://lore.kernel.org/r/2023040613-huntsman-goldsmith-4a41@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/staging/greybus/tools/.gitignore | 2 - drivers/staging/greybus/tools/Android.mk | 10 - drivers/staging/greybus/tools/Makefile | 33 - drivers/staging/greybus/tools/README.loopback | 198 ---- drivers/staging/greybus/tools/lbtest | 169 --- drivers/staging/greybus/tools/loopback_test.c | 979 ------------------ 6 files changed, 1391 deletions(-) delete mode 100644 drivers/staging/greybus/tools/.gitignore delete mode 100644 drivers/staging/greybus/tools/Android.mk delete mode 100644 drivers/staging/greybus/tools/Makefile delete mode 100644 drivers/staging/greybus/tools/README.loopback delete mode 100755 drivers/staging/greybus/tools/lbtest delete mode 100644 drivers/staging/greybus/tools/loopback_test.c diff --git a/drivers/staging/greybus/tools/.gitignore b/drivers/staging/greybus/tools/.gitignore deleted file mode 100644 index 1fd364aba774..000000000000 --- a/drivers/staging/greybus/tools/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -loopback_test diff --git a/drivers/staging/greybus/tools/Android.mk b/drivers/staging/greybus/tools/Android.mk deleted file mode 100644 index fdadbf611757..000000000000 --- a/drivers/staging/greybus/tools/Android.mk +++ /dev/null @@ -1,10 +0,0 @@ -LOCAL_PATH:= $(call my-dir) - -include $(CLEAR_VARS) - -LOCAL_SRC_FILES:= loopback_test.c -LOCAL_MODULE_TAGS := optional -LOCAL_MODULE := gb_loopback_test - -include $(BUILD_EXECUTABLE) - diff --git a/drivers/staging/greybus/tools/Makefile b/drivers/staging/greybus/tools/Makefile deleted file mode 100644 index a3bbd73171f2..000000000000 --- a/drivers/staging/greybus/tools/Makefile +++ /dev/null @@ -1,33 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -ifeq ($(strip $(V)), 1) - Q = -else - Q = @ -endif - -CFLAGS += -std=gnu99 -Wall -Wextra -g \ - -D_GNU_SOURCE \ - -Wno-unused-parameter \ - -Wmaybe-uninitialized \ - -Wredundant-decls \ - -Wcast-align \ - -Wsign-compare \ - -Wno-missing-field-initializers \ - -Wno-shift-negative-value - -CC := $(CROSS_COMPILE)gcc - -TOOLS = loopback_test - -all: $(TOOLS) - -%.o: %.c ../greybus_protocols.h - @echo ' TARGET_CC $@' - $(Q)$(CC) $(CFLAGS) -c $< -o $@ - -loopback_%: loopback_%.o - @echo ' TARGET_LD $@' - $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $^ -o $@ - -clean:: - rm -f *.o $(TOOLS) diff --git a/drivers/staging/greybus/tools/README.loopback b/drivers/staging/greybus/tools/README.loopback deleted file mode 100644 index 070a510cbe7c..000000000000 --- a/drivers/staging/greybus/tools/README.loopback +++ /dev/null @@ -1,198 +0,0 @@ - - - 1 - LOOPBACK DRIVER - -The driver implements the main logic of the loopback test and provides -sysfs files to configure the test and retrieve the results. -A user could run a test without the need of the test application given -that he understands the sysfs interface of the loopback driver. - -The loopback kernel driver needs to be loaded and at least one module -with the loopback feature enabled must be present for the sysfs files to be -created and for the loopback test application to be able to run. - -To load the module: -# modprobe gb-loopback - - -When the module is probed, New files are available on the sysfs -directory of the detected loopback device. -(typically under "/sys/bus/graybus/devices"). - -Here is a short summary of the sysfs interface files that should be visible: - -* Loopback Configuration Files: - async - Use asynchronous operations. - iteration_max - Number of tests iterations to perform. - size - payload size of the transfer. - timeout - The number of microseconds to give an individual - asynchronous request before timing out. - us_wait - Time to wait between 2 messages - type - By writing the test type to this file, the test starts. - Valid tests are: - 0 stop the test - 2 - ping - 3 - transfer - 4 - sink - -* Loopback feedback files: - error - number of errors that have occurred. - iteration_count - Number of iterations performed. - requests_completed - Number of requests successfully completed. - requests_timedout - Number of requests that have timed out. - timeout_max - Max allowed timeout - timeout_min - Min allowed timeout. - -* Loopback result files: - apbridge_unipro_latency_avg - apbridge_unipro_latency_max - apbridge_unipro_latency_min - gpbridge_firmware_latency_avg - gpbridge_firmware_latency_max - gpbridge_firmware_latency_min - requests_per_second_avg - requests_per_second_max - requests_per_second_min - latency_avg - latency_max - latency_min - throughput_avg - throughput_max - throughput_min - - - - 2 - LOOPBACK TEST APPLICATION - -The loopback test application manages and formats the results provided by -the loopback kernel module. The purpose of this application -is to: - - Start and manage multiple loopback device tests concurrently. - - Calculate the aggregate results for multiple devices. - - Gather and format test results (csv or human readable). - -The best way to get up to date usage information for the application is -usually to pass the "-h" parameter. -Here is the summary of the available options: - - Mandatory arguments - -t must be one of the test names - sink, transfer or ping - -i iteration count - the number of iterations to run the test over - Optional arguments - -S sysfs location - location for greybus 'endo' entries default /sys/bus/greybus/devices/ - -D debugfs location - location for loopback debugfs entries default /sys/kernel/debug/gb_loopback/ - -s size of data packet to send during test - defaults to zero - -m mask - a bit mask of connections to include example: -m 8 = 4th connection -m 9 = 1st and 4th connection etc - default is zero which means broadcast to all connections - -v verbose output - -d debug output - -r raw data output - when specified the full list of latency values are included in the output CSV - -p porcelain - when specified printout is in a user-friendly non-CSV format. This option suppresses writing to CSV file - -a aggregate - show aggregation of all enabled devies - -l list found loopback devices and exit. - -x Async - Enable async transfers. - -o Timeout - Timeout in microseconds for async operations. - - - - 3 - REAL WORLD EXAMPLE USAGES - - 3.1 - Using the driver sysfs files to run a test on a single device: - -* Run a 1000 transfers of a 100 byte packet. Each transfer is started only -after the previous one finished successfully: - echo 0 > /sys/bus/greybus/devices/1-2.17/type - echo 0 > /sys/bus/greybus/devices/1-2.17/async - echo 2000 > /sys/bus/greybus/devices/1-2.17/us_wait - echo 100 > /sys/bus/greybus/devices/1-2.17/size - echo 1000 > /sys/bus/greybus/devices/1-2.17/iteration_max - echo 0 > /sys/bus/greybus/devices/1-2.17/mask - echo 200000 > /sys/bus/greybus/devices/1-2.17/timeout - echo 3 > /sys/bus/greybus/devices/1-2.17/type - -* Run a 1000 transfers of a 100 byte packet. Transfers are started without -waiting for the previous one to finish: - echo 0 > /sys/bus/greybus/devices/1-2.17/type - echo 3 > /sys/bus/greybus/devices/1-2.17/async - echo 0 > /sys/bus/greybus/devices/1-2.17/us_wait - echo 100 > /sys/bus/greybus/devices/1-2.17/size - echo 1000 > /sys/bus/greybus/devices/1-2.17/iteration_max - echo 0 > /sys/bus/greybus/devices/1-2.17/mask - echo 200000 > /sys/bus/greybus/devices/1-2.17/timeout - echo 3 > /sys/bus/greybus/devices/1-2.17/type - -* Read the results from sysfs: - cat /sys/bus/greybus/devices/1-2.17/requests_per_second_min - cat /sys/bus/greybus/devices/1-2.17/requests_per_second_max - cat /sys/bus/greybus/devices/1-2.17/requests_per_second_avg - - cat /sys/bus/greybus/devices/1-2.17/latency_min - cat /sys/bus/greybus/devices/1-2.17/latency_max - cat /sys/bus/greybus/devices/1-2.17/latency_avg - - cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_min - cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_max - cat /sys/bus/greybus/devices/1-2.17/apbridge_unipro_latency_avg - - cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_min - cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_max - cat /sys/bus/greybus/devices/1-2.17/gpbridge_firmware_latency_avg - - cat /sys/bus/greybus/devices/1-2.17/error - cat /sys/bus/greybus/devices/1-2.17/requests_completed - cat /sys/bus/greybus/devices/1-2.17/requests_timedout - - -3.2 - using the test application: - -* Run a transfer test 10 iterations of size 100 bytes on all available devices - #/loopback_test -t transfer -i 10 -s 100 - 1970-1-1 0:10:7,transfer,1-4.17,100,10,0,443,509,471.700012,66,1963,2256,2124.600098,293,102776,118088,109318.898438,15312,1620,1998,1894.099976,378,56,57,56.799999,1 - 1970-1-1 0:10:7,transfer,1-5.17,100,10,0,399,542,463.399994,143,1845,2505,2175.800049,660,92568,125744,107393.296875,33176,1469,2305,1806.500000,836,56,57,56.799999,1 - - -* Show the aggregate results of both devices. ("-a") - #/loopback_test -t transfer -i 10 -s 100 -a - 1970-1-1 0:10:35,transfer,1-4.17,100,10,0,448,580,494.100006,132,1722,2230,2039.400024,508,103936,134560,114515.703125,30624,1513,1980,1806.900024,467,56,57,57.299999,1 - 1970-1-1 0:10:35,transfer,1-5.17,100,10,0,383,558,478.600006,175,1791,2606,2115.199951,815,88856,129456,110919.703125,40600,1457,2246,1773.599976,789,56,57,57.099998,1 - 1970-1-1 0:10:35,transfer,aggregate,100,10,0,383,580,486.000000,197,1722,2606,2077.000000,884,88856,134560,112717.000000,45704,1457,2246,1789.000000,789,56,57,57.000000,1 - -* Example usage of the mask option to select which devices will - run the test (1st, 2nd, or both devices): - # /loopback_test -t transfer -i 10 -s 100 -m 1 - 1970-1-1 0:11:56,transfer,1-4.17,100,10,0,514,558,544.900024,44,1791,1943,1836.599976,152,119248,129456,126301.296875,10208,1600,1001609,101613.601562,1000009,56,57,56.900002,1 - # /loopback_test -t transfer -i 10 -s 100 -m 2 - 1970-1-1 0:12:0,transfer,1-5.17,100,10,0,468,554,539.000000,86,1804,2134,1859.500000,330,108576,128528,124932.500000,19952,1606,1626,1619.300049,20,56,57,57.400002,1 - # /loopback_test -t transfer -i 10 -s 100 -m 3 - 1970-1-1 0:12:3,transfer,1-4.17,100,10,0,432,510,469.399994,78,1959,2313,2135.800049,354,100224,118320,108785.296875,18096,1610,2024,1893.500000,414,56,57,57.200001,1 - 1970-1-1 0:12:3,transfer,1-5.17,100,10,0,404,542,468.799988,138,1843,2472,2152.500000,629,93728,125744,108646.101562,32016,1504,2247,1853.099976,743,56,57,57.099998,1 - -* Show output in human readable format ("-p") - # /loopback_test -t transfer -i 10 -s 100 -m 3 -p - - 1970-1-1 0:12:37 - test: transfer - path: 1-4.17 - size: 100 - iterations: 10 - errors: 0 - async: Disabled - requests per-sec: min=390, max=547, average=469.299988, jitter=157 - ap-throughput B/s: min=90480 max=126904 average=108762.101562 jitter=36424 - ap-latency usec: min=1826 max=2560 average=2146.000000 jitter=734 - apbridge-latency usec: min=1620 max=1982 average=1882.099976 jitter=362 - gpbridge-latency usec: min=56 max=57 average=57.099998 jitter=1 - - - 1970-1-1 0:12:37 - test: transfer - path: 1-5.17 - size: 100 - iterations: 10 - errors: 0 - async: Disabled - requests per-sec: min=397, max=538, average=461.700012, jitter=141 - ap-throughput B/s: min=92104 max=124816 average=106998.898438 jitter=32712 - ap-latency usec: min=1856 max=2514 average=2185.699951 jitter=658 - apbridge-latency usec: min=1460 max=2296 average=1828.599976 jitter=836 - gpbridge-latency usec: min=56 max=57 average=57.099998 jitter=1 diff --git a/drivers/staging/greybus/tools/lbtest b/drivers/staging/greybus/tools/lbtest deleted file mode 100755 index 47c481239e98..000000000000 --- a/drivers/staging/greybus/tools/lbtest +++ /dev/null @@ -1,169 +0,0 @@ -#!/usr/bin/env python -# SPDX-License-Identifier: BSD-3-Clause - -# Copyright (c) 2015 Google, Inc. -# Copyright (c) 2015 Linaro, Ltd. -# All rights reserved. -# -# Redistribution and use in source and binary forms, with or without -# modification, are permitted provided that the following conditions are met: -# 1. Redistributions of source code must retain the above copyright notice, -# this list of conditions and the following disclaimer. -# 2. Redistributions in binary form must reproduce the above copyright notice, -# this list of conditions and the following disclaimer in the documentation -# and/or other materials provided with the distribution. -# 3. Neither the name of the copyright holder nor the names of its -# contributors may be used to endorse or promote products derived from this -# software without specific prior written permission. -# -# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, -# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR -# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR -# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, -# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, -# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; -# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, -# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR -# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF -# ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -from __future__ import print_function -import csv -import datetime -import sys -import time - -dict = {'ping': '2', 'transfer': '3', 'sink': '4'} -verbose = 1 - -def abort(): - sys.exit(1) - -def usage(): - print('Usage: looptest TEST SIZE ITERATIONS PATH\n\n' - ' Run TEST for a number of ITERATIONS with operation data SIZE bytes\n' - ' TEST may be \'ping\' \'transfer\' or \'sink\'\n' - ' SIZE indicates the size of transfer <= greybus max payload bytes\n' - ' ITERATIONS indicates the number of times to execute TEST at SIZE bytes\n' - ' Note if ITERATIONS is set to zero then this utility will\n' - ' initiate an infinite (non terminating) test and exit\n' - ' without logging any metrics data\n' - ' PATH indicates the sysfs path for the loopback greybus entries e.g.\n' - ' /sys/bus/greybus/devices/endo0:1:1:1:1/\n' - 'Examples:\n' - ' looptest transfer 128 10000\n' - ' looptest ping 0 128\n' - ' looptest sink 2030 32768\n' - .format(sys.argv[0]), file=sys.stderr) - - abort() - -def read_sysfs_int(path): - try: - f = open(path, "r"); - val = f.read(); - f.close() - return int(val) - except IOError as e: - print("I/O error({0}): {1}".format(e.errno, e.strerror)) - print("Invalid path %s" % path) - -def write_sysfs_val(path, val): - try: - f = open(path, "r+") - f.write(val) - f.close() - except IOError as e: - print("I/O error({0}): {1}".format(e.errno, e.strerror)) - print("Invalid path %s" % path) - -def log_csv(test_name, size, iteration_max, sys_pfx): - # file name will test_name_size_iteration_max.csv - # every time the same test with the same parameters is run we will then - # append to the same CSV with datestamp - representing each test dataset - fname = test_name + '_' + size + '_' + str(iteration_max) + '.csv' - - try: - # gather data set - date = str(datetime.datetime.now()) - error = read_sysfs_int(sys_pfx + 'error') - request_min = read_sysfs_int(sys_pfx + 'requests_per_second_min') - request_max = read_sysfs_int(sys_pfx + 'requests_per_second_max') - request_avg = read_sysfs_int(sys_pfx + 'requests_per_second_avg') - latency_min = read_sysfs_int(sys_pfx + 'latency_min') - latency_max = read_sysfs_int(sys_pfx + 'latency_max') - latency_avg = read_sysfs_int(sys_pfx + 'latency_avg') - throughput_min = read_sysfs_int(sys_pfx + 'throughput_min') - throughput_max = read_sysfs_int(sys_pfx + 'throughput_max') - throughput_avg = read_sysfs_int(sys_pfx + 'throughput_avg') - - # derive jitter - request_jitter = request_max - request_min - latency_jitter = latency_max - latency_min - throughput_jitter = throughput_max - throughput_min - - # append data set to file - with open(fname, 'a') as csvf: - row = csv.writer(csvf, delimiter=",", quotechar="'", - quoting=csv.QUOTE_MINIMAL) - row.writerow([date, test_name, size, iteration_max, error, - request_min, request_max, request_avg, request_jitter, - latency_min, latency_max, latency_avg, latency_jitter, - throughput_min, throughput_max, throughput_avg, throughput_jitter]) - except IOError as e: - print("I/O error({0}): {1}".format(e.errno, e.strerror)) - -def loopback_run(test_name, size, iteration_max, sys_pfx): - test_id = dict[test_name] - try: - # Terminate any currently running test - write_sysfs_val(sys_pfx + 'type', '0') - # Set parameter for no wait between messages - write_sysfs_val(sys_pfx + 'ms_wait', '0') - # Set operation size - write_sysfs_val(sys_pfx + 'size', size) - # Set iterations - write_sysfs_val(sys_pfx + 'iteration_max', str(iteration_max)) - # Initiate by setting loopback operation type - write_sysfs_val(sys_pfx + 'type', test_id) - time.sleep(1) - - if iteration_max == 0: - print ("Infinite test initiated CSV won't be logged\n") - return - - previous = 0 - err = 0 - while True: - # get current count bail out if it hasn't changed - iteration_count = read_sysfs_int(sys_pfx + 'iteration_count') - if previous == iteration_count: - err = 1 - break - elif iteration_count == iteration_max: - break - previous = iteration_count - if verbose: - print('%02d%% complete %d of %d ' % - (100 * iteration_count / iteration_max, - iteration_count, iteration_max)) - time.sleep(1) - if err: - print ('\nError executing test\n') - else: - log_csv(test_name, size, iteration_max, sys_pfx) - except ValueError as ve: - print("Error: %s " % format(e.strerror), file=sys.stderr) - abort() - -def main(): - if len(sys.argv) < 5: - usage() - - if sys.argv[1] in dict.keys(): - loopback_run(sys.argv[1], sys.argv[2], int(sys.argv[3]), sys.argv[4]) - else: - usage() -if __name__ == '__main__': - main() diff --git a/drivers/staging/greybus/tools/loopback_test.c b/drivers/staging/greybus/tools/loopback_test.c deleted file mode 100644 index d7ad51ff60c5..000000000000 --- a/drivers/staging/greybus/tools/loopback_test.c +++ /dev/null @@ -1,979 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause -/* - * Loopback test application - * - * Copyright 2015 Google Inc. - * Copyright 2015 Linaro Ltd. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define MAX_NUM_DEVICES 10 -#define MAX_SYSFS_PREFIX 0x80 -#define MAX_SYSFS_PATH 0x200 -#define CSV_MAX_LINE 0x1000 -#define SYSFS_MAX_INT 0x20 -#define MAX_STR_LEN 255 -#define DEFAULT_ASYNC_TIMEOUT 200000 - -struct dict { - char *name; - int type; -}; - -static struct dict dict[] = { - {"ping", 2}, - {"transfer", 3}, - {"sink", 4}, - {NULL,} /* list termination */ -}; - -struct loopback_results { - float latency_avg; - uint32_t latency_max; - uint32_t latency_min; - uint32_t latency_jitter; - - float request_avg; - uint32_t request_max; - uint32_t request_min; - uint32_t request_jitter; - - float throughput_avg; - uint32_t throughput_max; - uint32_t throughput_min; - uint32_t throughput_jitter; - - float apbridge_unipro_latency_avg; - uint32_t apbridge_unipro_latency_max; - uint32_t apbridge_unipro_latency_min; - uint32_t apbridge_unipro_latency_jitter; - - float gbphy_firmware_latency_avg; - uint32_t gbphy_firmware_latency_max; - uint32_t gbphy_firmware_latency_min; - uint32_t gbphy_firmware_latency_jitter; - - uint32_t error; -}; - -struct loopback_device { - char name[MAX_STR_LEN]; - char sysfs_entry[MAX_SYSFS_PATH]; - char debugfs_entry[MAX_SYSFS_PATH]; - struct loopback_results results; -}; - -struct loopback_test { - int verbose; - int debug; - int raw_data_dump; - int porcelain; - int mask; - int size; - int iteration_max; - int aggregate_output; - int test_id; - int device_count; - int list_devices; - int use_async; - int async_timeout; - int async_outstanding_operations; - int us_wait; - int file_output; - int stop_all; - int poll_count; - char test_name[MAX_STR_LEN]; - char sysfs_prefix[MAX_SYSFS_PREFIX]; - char debugfs_prefix[MAX_SYSFS_PREFIX]; - struct timespec poll_timeout; - struct loopback_device devices[MAX_NUM_DEVICES]; - struct loopback_results aggregate_results; - struct pollfd fds[MAX_NUM_DEVICES]; -}; - -struct loopback_test t; - -/* Helper macros to calculate the aggregate results for all devices */ -static inline int device_enabled(struct loopback_test *t, int dev_idx); - -#define GET_MAX(field) \ -static int get_##field##_aggregate(struct loopback_test *t) \ -{ \ - uint32_t max = 0; \ - int i; \ - for (i = 0; i < t->device_count; i++) { \ - if (!device_enabled(t, i)) \ - continue; \ - if (t->devices[i].results.field > max) \ - max = t->devices[i].results.field; \ - } \ - return max; \ -} \ - -#define GET_MIN(field) \ -static int get_##field##_aggregate(struct loopback_test *t) \ -{ \ - uint32_t min = ~0; \ - int i; \ - for (i = 0; i < t->device_count; i++) { \ - if (!device_enabled(t, i)) \ - continue; \ - if (t->devices[i].results.field < min) \ - min = t->devices[i].results.field; \ - } \ - return min; \ -} \ - -#define GET_AVG(field) \ -static int get_##field##_aggregate(struct loopback_test *t) \ -{ \ - uint32_t val = 0; \ - uint32_t count = 0; \ - int i; \ - for (i = 0; i < t->device_count; i++) { \ - if (!device_enabled(t, i)) \ - continue; \ - count++; \ - val += t->devices[i].results.field; \ - } \ - if (count) \ - val /= count; \ - return val; \ -} \ - -GET_MAX(throughput_max); -GET_MAX(request_max); -GET_MAX(latency_max); -GET_MAX(apbridge_unipro_latency_max); -GET_MAX(gbphy_firmware_latency_max); -GET_MIN(throughput_min); -GET_MIN(request_min); -GET_MIN(latency_min); -GET_MIN(apbridge_unipro_latency_min); -GET_MIN(gbphy_firmware_latency_min); -GET_AVG(throughput_avg); -GET_AVG(request_avg); -GET_AVG(latency_avg); -GET_AVG(apbridge_unipro_latency_avg); -GET_AVG(gbphy_firmware_latency_avg); - -void abort(void) -{ - _exit(1); -} - -void usage(void) -{ - fprintf(stderr, "Usage: loopback_test TEST [SIZE] ITERATIONS [SYSPATH] [DBGPATH]\n\n" - " Run TEST for a number of ITERATIONS with operation data SIZE bytes\n" - " TEST may be \'ping\' \'transfer\' or \'sink\'\n" - " SIZE indicates the size of transfer <= greybus max payload bytes\n" - " ITERATIONS indicates the number of times to execute TEST at SIZE bytes\n" - " Note if ITERATIONS is set to zero then this utility will\n" - " initiate an infinite (non terminating) test and exit\n" - " without logging any metrics data\n" - " SYSPATH indicates the sysfs path for the loopback greybus entries e.g.\n" - " /sys/bus/greybus/devices\n" - " DBGPATH indicates the debugfs path for the loopback greybus entries e.g.\n" - " /sys/kernel/debug/gb_loopback/\n" - " Mandatory arguments\n" - " -t must be one of the test names - sink, transfer or ping\n" - " -i iteration count - the number of iterations to run the test over\n" - " Optional arguments\n" - " -S sysfs location - location for greybus 'endo' entries default /sys/bus/greybus/devices/\n" - " -D debugfs location - location for loopback debugfs entries default /sys/kernel/debug/gb_loopback/\n" - " -s size of data packet to send during test - defaults to zero\n" - " -m mask - a bit mask of connections to include example: -m 8 = 4th connection -m 9 = 1st and 4th connection etc\n" - " default is zero which means broadcast to all connections\n" - " -v verbose output\n" - " -d debug output\n" - " -r raw data output - when specified the full list of latency values are included in the output CSV\n" - " -p porcelain - when specified printout is in a user-friendly non-CSV format. This option suppresses writing to CSV file\n" - " -a aggregate - show aggregation of all enabled devices\n" - " -l list found loopback devices and exit\n" - " -x Async - Enable async transfers\n" - " -o Async Timeout - Timeout in uSec for async operations\n" - " -O Poll loop time out in seconds(max time a test is expected to last, default: 30sec)\n" - " -c Max number of outstanding operations for async operations\n" - " -w Wait in uSec between operations\n" - " -z Enable output to a CSV file (incompatible with -p)\n" - " -f When starting new loopback test, stop currently running tests on all devices\n" - "Examples:\n" - " Send 10000 transfers with a packet size of 128 bytes to all active connections\n" - " loopback_test -t transfer -s 128 -i 10000 -S /sys/bus/greybus/devices/ -D /sys/kernel/debug/gb_loopback/\n" - " loopback_test -t transfer -s 128 -i 10000 -m 0\n" - " Send 10000 transfers with a packet size of 128 bytes to connection 1 and 4\n" - " loopback_test -t transfer -s 128 -i 10000 -m 9\n" - " loopback_test -t ping -s 0 128 -i -S /sys/bus/greybus/devices/ -D /sys/kernel/debug/gb_loopback/\n" - " loopback_test -t sink -s 2030 -i 32768 -S /sys/bus/greybus/devices/ -D /sys/kernel/debug/gb_loopback/\n"); - abort(); -} - -static inline int device_enabled(struct loopback_test *t, int dev_idx) -{ - if (!t->mask || (t->mask & (1 << dev_idx))) - return 1; - - return 0; -} - -static void show_loopback_devices(struct loopback_test *t) -{ - int i; - - if (t->device_count == 0) { - printf("No loopback devices.\n"); - return; - } - - for (i = 0; i < t->device_count; i++) - printf("device[%d] = %s\n", i, t->devices[i].name); -} - -int open_sysfs(const char *sys_pfx, const char *node, int flags) -{ - int fd; - char path[MAX_SYSFS_PATH]; - - snprintf(path, sizeof(path), "%s%s", sys_pfx, node); - fd = open(path, flags); - if (fd < 0) { - fprintf(stderr, "unable to open %s\n", path); - abort(); - } - return fd; -} - -int read_sysfs_int_fd(int fd, const char *sys_pfx, const char *node) -{ - char buf[SYSFS_MAX_INT]; - - if (read(fd, buf, sizeof(buf)) < 0) { - fprintf(stderr, "unable to read from %s%s %s\n", sys_pfx, node, - strerror(errno)); - close(fd); - abort(); - } - return atoi(buf); -} - -float read_sysfs_float_fd(int fd, const char *sys_pfx, const char *node) -{ - char buf[SYSFS_MAX_INT]; - - if (read(fd, buf, sizeof(buf)) < 0) { - fprintf(stderr, "unable to read from %s%s %s\n", sys_pfx, node, - strerror(errno)); - close(fd); - abort(); - } - return atof(buf); -} - -int read_sysfs_int(const char *sys_pfx, const char *node) -{ - int fd, val; - - fd = open_sysfs(sys_pfx, node, O_RDONLY); - val = read_sysfs_int_fd(fd, sys_pfx, node); - close(fd); - return val; -} - -float read_sysfs_float(const char *sys_pfx, const char *node) -{ - int fd; - float val; - - fd = open_sysfs(sys_pfx, node, O_RDONLY); - val = read_sysfs_float_fd(fd, sys_pfx, node); - close(fd); - return val; -} - -void write_sysfs_val(const char *sys_pfx, const char *node, int val) -{ - int fd, len; - char buf[SYSFS_MAX_INT]; - - fd = open_sysfs(sys_pfx, node, O_RDWR); - len = snprintf(buf, sizeof(buf), "%d", val); - if (write(fd, buf, len) < 0) { - fprintf(stderr, "unable to write to %s%s %s\n", sys_pfx, node, - strerror(errno)); - close(fd); - abort(); - } - close(fd); -} - -static int get_results(struct loopback_test *t) -{ - struct loopback_device *d; - struct loopback_results *r; - int i; - - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - - d = &t->devices[i]; - r = &d->results; - - r->error = read_sysfs_int(d->sysfs_entry, "error"); - r->request_min = read_sysfs_int(d->sysfs_entry, "requests_per_second_min"); - r->request_max = read_sysfs_int(d->sysfs_entry, "requests_per_second_max"); - r->request_avg = read_sysfs_float(d->sysfs_entry, "requests_per_second_avg"); - - r->latency_min = read_sysfs_int(d->sysfs_entry, "latency_min"); - r->latency_max = read_sysfs_int(d->sysfs_entry, "latency_max"); - r->latency_avg = read_sysfs_float(d->sysfs_entry, "latency_avg"); - - r->throughput_min = read_sysfs_int(d->sysfs_entry, "throughput_min"); - r->throughput_max = read_sysfs_int(d->sysfs_entry, "throughput_max"); - r->throughput_avg = read_sysfs_float(d->sysfs_entry, "throughput_avg"); - - r->apbridge_unipro_latency_min = - read_sysfs_int(d->sysfs_entry, "apbridge_unipro_latency_min"); - r->apbridge_unipro_latency_max = - read_sysfs_int(d->sysfs_entry, "apbridge_unipro_latency_max"); - r->apbridge_unipro_latency_avg = - read_sysfs_float(d->sysfs_entry, "apbridge_unipro_latency_avg"); - - r->gbphy_firmware_latency_min = - read_sysfs_int(d->sysfs_entry, "gbphy_firmware_latency_min"); - r->gbphy_firmware_latency_max = - read_sysfs_int(d->sysfs_entry, "gbphy_firmware_latency_max"); - r->gbphy_firmware_latency_avg = - read_sysfs_float(d->sysfs_entry, "gbphy_firmware_latency_avg"); - - r->request_jitter = r->request_max - r->request_min; - r->latency_jitter = r->latency_max - r->latency_min; - r->throughput_jitter = r->throughput_max - r->throughput_min; - r->apbridge_unipro_latency_jitter = - r->apbridge_unipro_latency_max - r->apbridge_unipro_latency_min; - r->gbphy_firmware_latency_jitter = - r->gbphy_firmware_latency_max - r->gbphy_firmware_latency_min; - } - - /*calculate the aggregate results of all enabled devices */ - if (t->aggregate_output) { - r = &t->aggregate_results; - - r->request_min = get_request_min_aggregate(t); - r->request_max = get_request_max_aggregate(t); - r->request_avg = get_request_avg_aggregate(t); - - r->latency_min = get_latency_min_aggregate(t); - r->latency_max = get_latency_max_aggregate(t); - r->latency_avg = get_latency_avg_aggregate(t); - - r->throughput_min = get_throughput_min_aggregate(t); - r->throughput_max = get_throughput_max_aggregate(t); - r->throughput_avg = get_throughput_avg_aggregate(t); - - r->apbridge_unipro_latency_min = - get_apbridge_unipro_latency_min_aggregate(t); - r->apbridge_unipro_latency_max = - get_apbridge_unipro_latency_max_aggregate(t); - r->apbridge_unipro_latency_avg = - get_apbridge_unipro_latency_avg_aggregate(t); - - r->gbphy_firmware_latency_min = - get_gbphy_firmware_latency_min_aggregate(t); - r->gbphy_firmware_latency_max = - get_gbphy_firmware_latency_max_aggregate(t); - r->gbphy_firmware_latency_avg = - get_gbphy_firmware_latency_avg_aggregate(t); - - r->request_jitter = r->request_max - r->request_min; - r->latency_jitter = r->latency_max - r->latency_min; - r->throughput_jitter = r->throughput_max - r->throughput_min; - r->apbridge_unipro_latency_jitter = - r->apbridge_unipro_latency_max - r->apbridge_unipro_latency_min; - r->gbphy_firmware_latency_jitter = - r->gbphy_firmware_latency_max - r->gbphy_firmware_latency_min; - } - - return 0; -} - -int format_output(struct loopback_test *t, - struct loopback_results *r, - const char *dev_name, - char *buf, int buf_len, - struct tm *tm) -{ - int len = 0; - - memset(buf, 0x00, buf_len); - len = snprintf(buf, buf_len, "%u-%u-%u %u:%u:%u", - tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday, - tm->tm_hour, tm->tm_min, tm->tm_sec); - - if (t->porcelain) { - len += snprintf(&buf[len], buf_len - len, - "\n test:\t\t\t%s\n path:\t\t\t%s\n size:\t\t\t%u\n iterations:\t\t%u\n errors:\t\t%u\n async:\t\t\t%s\n", - t->test_name, - dev_name, - t->size, - t->iteration_max, - r->error, - t->use_async ? "Enabled" : "Disabled"); - - len += snprintf(&buf[len], buf_len - len, - " requests per-sec:\tmin=%u, max=%u, average=%f, jitter=%u\n", - r->request_min, - r->request_max, - r->request_avg, - r->request_jitter); - - len += snprintf(&buf[len], buf_len - len, - " ap-throughput B/s:\tmin=%u max=%u average=%f jitter=%u\n", - r->throughput_min, - r->throughput_max, - r->throughput_avg, - r->throughput_jitter); - len += snprintf(&buf[len], buf_len - len, - " ap-latency usec:\tmin=%u max=%u average=%f jitter=%u\n", - r->latency_min, - r->latency_max, - r->latency_avg, - r->latency_jitter); - len += snprintf(&buf[len], buf_len - len, - " apbridge-latency usec:\tmin=%u max=%u average=%f jitter=%u\n", - r->apbridge_unipro_latency_min, - r->apbridge_unipro_latency_max, - r->apbridge_unipro_latency_avg, - r->apbridge_unipro_latency_jitter); - - len += snprintf(&buf[len], buf_len - len, - " gbphy-latency usec:\tmin=%u max=%u average=%f jitter=%u\n", - r->gbphy_firmware_latency_min, - r->gbphy_firmware_latency_max, - r->gbphy_firmware_latency_avg, - r->gbphy_firmware_latency_jitter); - - } else { - len += snprintf(&buf[len], buf_len - len, ",%s,%s,%u,%u,%u", - t->test_name, dev_name, t->size, t->iteration_max, - r->error); - - len += snprintf(&buf[len], buf_len - len, ",%u,%u,%f,%u", - r->request_min, - r->request_max, - r->request_avg, - r->request_jitter); - - len += snprintf(&buf[len], buf_len - len, ",%u,%u,%f,%u", - r->latency_min, - r->latency_max, - r->latency_avg, - r->latency_jitter); - - len += snprintf(&buf[len], buf_len - len, ",%u,%u,%f,%u", - r->throughput_min, - r->throughput_max, - r->throughput_avg, - r->throughput_jitter); - - len += snprintf(&buf[len], buf_len - len, ",%u,%u,%f,%u", - r->apbridge_unipro_latency_min, - r->apbridge_unipro_latency_max, - r->apbridge_unipro_latency_avg, - r->apbridge_unipro_latency_jitter); - - len += snprintf(&buf[len], buf_len - len, ",%u,%u,%f,%u", - r->gbphy_firmware_latency_min, - r->gbphy_firmware_latency_max, - r->gbphy_firmware_latency_avg, - r->gbphy_firmware_latency_jitter); - } - - printf("\n%s\n", buf); - - return len; -} - -static int log_results(struct loopback_test *t) -{ - int fd, i, len, ret; - struct tm tm; - time_t local_time; - char file_name[MAX_SYSFS_PATH]; - char data[CSV_MAX_LINE]; - - local_time = time(NULL); - tm = *localtime(&local_time); - - /* - * file name will test_name_size_iteration_max.csv - * every time the same test with the same parameters is run we will then - * append to the same CSV with datestamp - representing each test - * dataset. - */ - if (t->file_output && !t->porcelain) { - snprintf(file_name, sizeof(file_name), "%s_%d_%d.csv", - t->test_name, t->size, t->iteration_max); - - fd = open(file_name, O_WRONLY | O_CREAT | O_APPEND, 0644); - if (fd < 0) { - fprintf(stderr, "unable to open %s for appending\n", file_name); - abort(); - } - } - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - - len = format_output(t, &t->devices[i].results, - t->devices[i].name, - data, sizeof(data), &tm); - if (t->file_output && !t->porcelain) { - ret = write(fd, data, len); - if (ret == -1) - fprintf(stderr, "unable to write %d bytes to csv.\n", len); - } - } - - if (t->aggregate_output) { - len = format_output(t, &t->aggregate_results, "aggregate", - data, sizeof(data), &tm); - if (t->file_output && !t->porcelain) { - ret = write(fd, data, len); - if (ret == -1) - fprintf(stderr, "unable to write %d bytes to csv.\n", len); - } - } - - if (t->file_output && !t->porcelain) - close(fd); - - return 0; -} - -int is_loopback_device(const char *path, const char *node) -{ - char file[MAX_SYSFS_PATH]; - - snprintf(file, MAX_SYSFS_PATH, "%s%s/iteration_count", path, node); - if (access(file, F_OK) == 0) - return 1; - return 0; -} - -int find_loopback_devices(struct loopback_test *t) -{ - struct dirent **namelist; - int i, n, ret; - unsigned int dev_id; - struct loopback_device *d; - - n = scandir(t->sysfs_prefix, &namelist, NULL, alphasort); - if (n < 0) { - perror("scandir"); - ret = -ENODEV; - goto baddir; - } - - /* Don't include '.' and '..' */ - if (n <= 2) { - ret = -ENOMEM; - goto done; - } - - for (i = 0; i < n; i++) { - ret = sscanf(namelist[i]->d_name, "gb_loopback%u", &dev_id); - if (ret != 1) - continue; - - if (!is_loopback_device(t->sysfs_prefix, namelist[i]->d_name)) - continue; - - if (t->device_count == MAX_NUM_DEVICES) { - fprintf(stderr, "max number of devices reached!\n"); - break; - } - - d = &t->devices[t->device_count++]; - snprintf(d->name, MAX_STR_LEN, "gb_loopback%u", dev_id); - - snprintf(d->sysfs_entry, MAX_SYSFS_PATH, "%s%s/", - t->sysfs_prefix, d->name); - - snprintf(d->debugfs_entry, MAX_SYSFS_PATH, "%sraw_latency_%s", - t->debugfs_prefix, d->name); - - if (t->debug) - printf("add %s %s\n", d->sysfs_entry, d->debugfs_entry); - } - - ret = 0; -done: - for (i = 0; i < n; i++) - free(namelist[i]); - free(namelist); -baddir: - return ret; -} - -static int open_poll_files(struct loopback_test *t) -{ - struct loopback_device *dev; - char buf[MAX_SYSFS_PATH + MAX_STR_LEN]; - char dummy; - int fds_idx = 0; - int i; - - for (i = 0; i < t->device_count; i++) { - dev = &t->devices[i]; - - if (!device_enabled(t, i)) - continue; - - snprintf(buf, sizeof(buf), "%s%s", dev->sysfs_entry, "iteration_count"); - t->fds[fds_idx].fd = open(buf, O_RDONLY); - if (t->fds[fds_idx].fd < 0) { - fprintf(stderr, "Error opening poll file!\n"); - goto err; - } - read(t->fds[fds_idx].fd, &dummy, 1); - t->fds[fds_idx].events = POLLERR | POLLPRI; - t->fds[fds_idx].revents = 0; - fds_idx++; - } - - t->poll_count = fds_idx; - - return 0; - -err: - for (i = 0; i < fds_idx; i++) - close(t->fds[i].fd); - - return -1; -} - -static int close_poll_files(struct loopback_test *t) -{ - int i; - - for (i = 0; i < t->poll_count; i++) - close(t->fds[i].fd); - - return 0; -} -static int is_complete(struct loopback_test *t) -{ - int iteration_count; - int i; - - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - - iteration_count = read_sysfs_int(t->devices[i].sysfs_entry, - "iteration_count"); - - /* at least one device did not finish yet */ - if (iteration_count != t->iteration_max) - return 0; - } - - return 1; -} - -static void stop_tests(struct loopback_test *t) -{ - int i; - - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - write_sysfs_val(t->devices[i].sysfs_entry, "type", 0); - } -} - -static void handler(int sig) { /* do nothing */ } - -static int wait_for_complete(struct loopback_test *t) -{ - int number_of_events = 0; - char dummy; - int ret; - int i; - struct timespec *ts = NULL; - struct sigaction sa; - sigset_t mask_old, mask; - - sigemptyset(&mask); - sigemptyset(&mask_old); - sigaddset(&mask, SIGINT); - sigprocmask(SIG_BLOCK, &mask, &mask_old); - - sa.sa_handler = handler; - sa.sa_flags = 0; - sigemptyset(&sa.sa_mask); - if (sigaction(SIGINT, &sa, NULL) == -1) { - fprintf(stderr, "sigaction error\n"); - return -1; - } - - if (t->poll_timeout.tv_sec != 0) - ts = &t->poll_timeout; - - while (1) { - ret = ppoll(t->fds, t->poll_count, ts, &mask_old); - if (ret <= 0) { - stop_tests(t); - fprintf(stderr, "Poll exit with errno %d\n", errno); - return -1; - } - - for (i = 0; i < t->poll_count; i++) { - if (t->fds[i].revents & POLLPRI) { - /* Dummy read to clear the event */ - read(t->fds[i].fd, &dummy, 1); - number_of_events++; - } - } - - if (number_of_events == t->poll_count) - break; - } - - if (!is_complete(t)) { - fprintf(stderr, "Iteration count did not finish!\n"); - return -1; - } - - return 0; -} - -static void prepare_devices(struct loopback_test *t) -{ - int i; - - /* - * Cancel any running tests on enabled devices. If - * stop_all option is given, stop test on all devices. - */ - for (i = 0; i < t->device_count; i++) - if (t->stop_all || device_enabled(t, i)) - write_sysfs_val(t->devices[i].sysfs_entry, "type", 0); - - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - - write_sysfs_val(t->devices[i].sysfs_entry, "us_wait", - t->us_wait); - - /* Set operation size */ - write_sysfs_val(t->devices[i].sysfs_entry, "size", t->size); - - /* Set iterations */ - write_sysfs_val(t->devices[i].sysfs_entry, "iteration_max", - t->iteration_max); - - if (t->use_async) { - write_sysfs_val(t->devices[i].sysfs_entry, "async", 1); - write_sysfs_val(t->devices[i].sysfs_entry, - "timeout", t->async_timeout); - write_sysfs_val(t->devices[i].sysfs_entry, - "outstanding_operations_max", - t->async_outstanding_operations); - } else { - write_sysfs_val(t->devices[i].sysfs_entry, "async", 0); - } - } -} - -static int start(struct loopback_test *t) -{ - int i; - - /* the test starts by writing test_id to the type file. */ - for (i = 0; i < t->device_count; i++) { - if (!device_enabled(t, i)) - continue; - - write_sysfs_val(t->devices[i].sysfs_entry, "type", t->test_id); - } - - return 0; -} - -void loopback_run(struct loopback_test *t) -{ - int i; - int ret; - - for (i = 0; dict[i].name != NULL; i++) { - if (strstr(dict[i].name, t->test_name)) - t->test_id = dict[i].type; - } - if (!t->test_id) { - fprintf(stderr, "invalid test %s\n", t->test_name); - usage(); - return; - } - - prepare_devices(t); - - ret = open_poll_files(t); - if (ret) - goto err; - - start(t); - - ret = wait_for_complete(t); - close_poll_files(t); - if (ret) - goto err; - - get_results(t); - - log_results(t); - - return; - -err: - printf("Error running test\n"); -} - -static int sanity_check(struct loopback_test *t) -{ - int i; - - if (t->device_count == 0) { - fprintf(stderr, "No loopback devices found\n"); - return -1; - } - - for (i = 0; i < MAX_NUM_DEVICES; i++) { - if (!device_enabled(t, i)) - continue; - - if (t->mask && !strcmp(t->devices[i].name, "")) { - fprintf(stderr, "Bad device mask %x\n", (1 << i)); - return -1; - } - } - - return 0; -} - -int main(int argc, char *argv[]) -{ - int o, ret; - char *sysfs_prefix = "/sys/class/gb_loopback/"; - char *debugfs_prefix = "/sys/kernel/debug/gb_loopback/"; - - memset(&t, 0, sizeof(t)); - - while ((o = getopt(argc, argv, - "t:s:i:S:D:m:v::d::r::p::a::l::x::o:O:c:w:z::f::")) != -1) { - switch (o) { - case 't': - snprintf(t.test_name, MAX_STR_LEN, "%s", optarg); - break; - case 's': - t.size = atoi(optarg); - break; - case 'i': - t.iteration_max = atoi(optarg); - break; - case 'S': - snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg); - break; - case 'D': - snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", optarg); - break; - case 'm': - t.mask = atol(optarg); - break; - case 'v': - t.verbose = 1; - break; - case 'd': - t.debug = 1; - break; - case 'r': - t.raw_data_dump = 1; - break; - case 'p': - t.porcelain = 1; - break; - case 'a': - t.aggregate_output = 1; - break; - case 'l': - t.list_devices = 1; - break; - case 'x': - t.use_async = 1; - break; - case 'o': - t.async_timeout = atoi(optarg); - break; - case 'O': - t.poll_timeout.tv_sec = atoi(optarg); - break; - case 'c': - t.async_outstanding_operations = atoi(optarg); - break; - case 'w': - t.us_wait = atoi(optarg); - break; - case 'z': - t.file_output = 1; - break; - case 'f': - t.stop_all = 1; - break; - default: - usage(); - return -EINVAL; - } - } - - if (!strcmp(t.sysfs_prefix, "")) - snprintf(t.sysfs_prefix, MAX_SYSFS_PREFIX, "%s", sysfs_prefix); - - if (!strcmp(t.debugfs_prefix, "")) - snprintf(t.debugfs_prefix, MAX_SYSFS_PREFIX, "%s", debugfs_prefix); - - ret = find_loopback_devices(&t); - if (ret) - return ret; - ret = sanity_check(&t); - if (ret) - return ret; - - if (t.list_devices) { - show_loopback_devices(&t); - return 0; - } - - if (t.test_name[0] == '\0' || t.iteration_max == 0) - usage(); - - if (t.async_timeout == 0) - t.async_timeout = DEFAULT_ASYNC_TIMEOUT; - - loopback_run(&t); - - return 0; -} -- GitLab From 748b5db6a9991ba6549758a767ccecf6f3bf0096 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Fri, 7 Apr 2023 23:50:21 +0200 Subject: [PATCH 3087/5631] staging: rtl8192e: Remove macro IS_HARDWARE_TYPE_8192SE Remove unused macro IS_HARDWARE_TYPE_8192SE as it is used only in code areas that are not executed when 8192SE hardware is found. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/e9b19862ace002462e870e62c6f62bab3cc81c5a.1680902603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 3 --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 7 +------ 2 files changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 2b2d8af4cf6e..b0aa76574738 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -52,9 +52,6 @@ #define DRV_AUTHOR "" #define DRV_VERSION "0014.0401.2010" -#define IS_HARDWARE_TYPE_8192SE(_priv) \ - (((struct r8192_priv *)rtllib_priv(dev))->card_8192 == NIC_8192SE) - #define TOTAL_CAM_ENTRY 32 #define CAM_CONTENT_COUNT 8 diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index cde41111012a..50486f2a6f3a 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -214,8 +214,6 @@ void rtl92e_dm_init(struct net_device *dev) _rtl92e_dm_init_fsync(dev); _rtl92e_dm_init_rx_path_selection(dev); _rtl92e_dm_init_cts_to_self(dev); - if (IS_HARDWARE_TYPE_8192SE(dev)) - _rtl92e_dm_init_wa_broadcom_iot(dev); INIT_DELAYED_WORK(&priv->gpio_change_rf_wq, (void *)_rtl92e_dm_check_rf_ctrl_gpio); } @@ -816,10 +814,7 @@ static void _rtl92e_dm_check_tx_power_tracking_thermal(struct net_device *dev) static u8 TM_Trigger; u8 TxPowerCheckCnt = 0; - if (IS_HARDWARE_TYPE_8192SE(dev)) - TxPowerCheckCnt = 5; - else - TxPowerCheckCnt = 2; + TxPowerCheckCnt = 2; if (!priv->btxpower_tracking) return; -- GitLab From edc332a9f4deac969394c1ada1918f75564867aa Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Fri, 7 Apr 2023 23:50:28 +0200 Subject: [PATCH 3088/5631] staging: rtl8192e: Remove unused function _rtl92e_dm_init_wa_broadcom_iot Remove unused function _rtl92e_dm_init_wa_broadcom_iot and the variables that are not any longer used. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0e7a2a5b9edc85b7f8e3fc0f9e0e6ab7f2830d02.1680902603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 11 ----------- drivers/staging/rtl8192e/rtl819x_HT.h | 3 --- 2 files changed, 14 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 50486f2a6f3a..93504d5a8578 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -173,7 +173,6 @@ static void _rtl92e_dm_pd_th(struct net_device *dev); static void _rtl92e_dm_cs_ratio(struct net_device *dev); static void _rtl92e_dm_init_cts_to_self(struct net_device *dev); -static void _rtl92e_dm_init_wa_broadcom_iot(struct net_device *dev); static void _rtl92e_dm_check_edca_turbo(struct net_device *dev); static void _rtl92e_dm_check_rx_path_selection(struct net_device *dev); @@ -1531,16 +1530,6 @@ static void _rtl92e_dm_cts_to_self(struct net_device *dev) } } - -static void _rtl92e_dm_init_wa_broadcom_iot(struct net_device *dev) -{ - struct r8192_priv *priv = rtllib_priv((struct net_device *)dev); - struct rt_hi_throughput *ht_info = priv->rtllib->ht_info; - - ht_info->bWAIotBroadcom = false; - ht_info->WAIotTH = WA_IOT_TH_VAL; -} - static void _rtl92e_dm_check_rf_ctrl_gpio(void *data) { struct r8192_priv *priv = container_of_dwork_rsl(data, diff --git a/drivers/staging/rtl8192e/rtl819x_HT.h b/drivers/staging/rtl8192e/rtl819x_HT.h index 22e4f126ed56..f4e9fa849796 100644 --- a/drivers/staging/rtl8192e/rtl819x_HT.h +++ b/drivers/staging/rtl8192e/rtl819x_HT.h @@ -162,9 +162,6 @@ struct rt_hi_throughput { u8 IOTPeer; u32 iot_action; u8 iot_ra_func; - - u8 bWAIotBroadcom; - u8 WAIotTH; } __packed; struct bss_ht { -- GitLab From a273033cf466a8f078beb87ea0f4938382f90fb5 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Fri, 7 Apr 2023 23:50:34 +0200 Subject: [PATCH 3089/5631] staging: rtl8192e: Remove one of two checks for hardware RTL8192SE Check for hardware RTL8192SE is done in function _rtl92e_pci_probe() directly and also two lines later in function rtl92e_check_adapter(). Remove top level check to increase readability. This pci_read does not follow a pci_write to ensure data is written to the device. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/4126cca73739c75b1a0379af2ef8b0c63a705639.1680902603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 7506d7eb7b4c..45989a77a27c 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -2130,7 +2130,6 @@ static int _rtl92e_pci_probe(struct pci_dev *pdev, struct r8192_priv *priv = NULL; unsigned long pmem_start, pmem_len, pmem_flags; int err = -ENOMEM; - u8 revision_id; if (pci_enable_device(pdev)) { dev_err(&pdev->dev, "Failed to enable PCI device"); @@ -2189,11 +2188,6 @@ static int _rtl92e_pci_probe(struct pci_dev *pdev, dev->mem_start = ioaddr; dev->mem_end = ioaddr + pci_resource_len(pdev, 0); - pci_read_config_byte(pdev, 0x08, &revision_id); - /* If the revisionid is 0x10, the device uses rtl8192se. */ - if (pdev->device == 0x8192 && revision_id == 0x10) - goto err_unmap; - if (!rtl92e_check_adapter(pdev, dev)) goto err_unmap; -- GitLab From 1cadfcfe353dc36d3c37224047cd422264dab263 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Fri, 7 Apr 2023 23:50:41 +0200 Subject: [PATCH 3090/5631] staging: rtl8192e: Remove unused variable RF_Type Remove unused variable RF_Type. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/7710a87f627dcfd2d0c34f14f583625ffab10660.1680902603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 1a0177cd64af..b1729d65f67f 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -1393,7 +1393,6 @@ struct rtllib_device { size_t assocreq_ies_len, assocresp_ies_len; bool bForcedBgMode; - u8 RF_Type; u8 hwsec_active; bool is_silent_reset; -- GitLab From 86d3ad9684562cd3cee30f28d5976cd92e702473 Mon Sep 17 00:00:00 2001 From: Srihari S Date: Sat, 8 Apr 2023 20:46:23 +0530 Subject: [PATCH 3091/5631] staging: rtl8172: Add blank lines after declarations Add blank lines as reported by checkpatch.pl as below CHECK: Please use a blank line after function/struct/union/enum declarations Signed-off-by: Srihari S Link: https://lore.kernel.org/r/1680966983-11609-1-git-send-email-sriharisat@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8712/rtl8712_efuse.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/rtl8712/rtl8712_efuse.h b/drivers/staging/rtl8712/rtl8712_efuse.h index 2e1ea9d7a295..7a49740212eb 100644 --- a/drivers/staging/rtl8712/rtl8712_efuse.h +++ b/drivers/staging/rtl8712/rtl8712_efuse.h @@ -23,6 +23,7 @@ struct PGPKT_STRUCT { u8 word_en; u8 data[PGPKT_DATA_SIZE]; }; + /*--------------------------------------------------------------------------*/ u8 r8712_efuse_reg_init(struct _adapter *padapter); void r8712_efuse_reg_uninit(struct _adapter *padapter); -- GitLab From a90922fa25370902322e9de6640e58737d459a50 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Fri, 14 Apr 2023 14:29:25 -0700 Subject: [PATCH 3092/5631] swiotlb: relocate PageHighMem test away from rmem_swiotlb_setup The reservedmem_of_init_fn's are invoked very early at boot before the memory zones have even been defined. This makes it inappropriate to test whether the page corresponding to a PFN is in ZONE_HIGHMEM from within one. Removing the check allows an ARM 32-bit kernel with SPARSEMEM enabled to boot properly since otherwise we would be de-referencing an uninitialized sparsemem map to perform pfn_to_page() check. The arm64 architecture happens to work (and also has no high memory) but other 32-bit architectures could also be having similar issues. While it would be nice to provide early feedback about a reserved DMA pool residing in highmem, it is not possible to do that until the first time we try to use it, which is where the check is moved to. Fixes: 0b84e4f8b793 ("swiotlb: Add restricted DMA pool initialization") Signed-off-by: Doug Berger Signed-off-by: Florian Fainelli Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5b919ef832b6..1ec38701a7f5 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -998,6 +998,11 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem, /* Set Per-device io tlb area to one */ unsigned int nareas = 1; + if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { + dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping."); + return -EINVAL; + } + /* * Since multiple devices can share the same pool, the private data, * io_tlb_mem struct, will be initialized by the first device attached @@ -1059,11 +1064,6 @@ static int __init rmem_swiotlb_setup(struct reserved_mem *rmem) of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; - if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { - pr_err("Restricted DMA pool must be accessible within the linear mapping."); - return -EINVAL; - } - rmem->ops = &rmem_swiotlb_ops; pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n", &rmem->base, (unsigned long)rmem->size / SZ_1M); -- GitLab From 5499d01c029069044a3b3e50501c77b474c96178 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 13 Apr 2023 08:37:30 -0700 Subject: [PATCH 3093/5631] swiotlb: fix debugfs reporting of reserved memory pools For io_tlb_nslabs, the debugfs code reports the correct value for a specific reserved memory pool. But for io_tlb_used, the value reported is always for the default pool, not the specific reserved pool. Fix this. Fixes: 5c850d31880e ("swiotlb: fix passing local variable to debugfs_create_ulong()") Signed-off-by: Michael Kelley Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 1ec38701a7f5..938c959ab19e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -930,7 +930,9 @@ EXPORT_SYMBOL_GPL(is_swiotlb_active); static int io_tlb_used_get(void *data, u64 *val) { - *val = mem_used(&io_tlb_default_mem); + struct io_tlb_mem *mem = data; + + *val = mem_used(mem); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); @@ -943,7 +945,7 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, return; debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); - debugfs_create_file("io_tlb_used", 0400, mem->debugfs, NULL, + debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem, &fops_io_tlb_used); } -- GitLab From 8b0977ecc8b30a30966e76fcb64cef5041626b02 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Thu, 13 Apr 2023 10:57:37 -0700 Subject: [PATCH 3094/5631] swiotlb: track and report io_tlb_used high water marks in debugfs swiotlb currently reports the total number of slabs and the instantaneous in-use slabs in debugfs. But with increased usage of swiotlb for all I/O in Confidential Computing (coco) VMs, it has become difficult to know how much memory to allocate for swiotlb bounce buffers, either via the automatic algorithm in the kernel or by specifying a value on the kernel boot line. The current automatic algorithm generously allocates swiotlb bounce buffer memory, and may be wasting significant memory in many use cases. To support better understanding of swiotlb usage, add tracking of the the high water mark for usage of the default swiotlb bounce buffer memory pool and any reserved memory pools. Report these high water marks in debugfs along with the other swiotlb pool metrics. Allow the high water marks to be reset to zero at runtime by writing to them. Signed-off-by: Michael Kelley Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 7 +++++ kernel/dma/swiotlb.c | 66 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 73 insertions(+) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..6dc4598d2260 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -87,6 +87,11 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, * @for_alloc: %true if the pool is used for memory allocation * @nareas: The area number in the pool. * @area_nslabs: The slot number in the area. + * @total_used: The total number of slots in the pool that are currently used + * across all areas. Used only for calculating used_hiwater in + * debugfs. + * @used_hiwater: The high water mark for total_used. Used only for reporting + * in debugfs. */ struct io_tlb_mem { phys_addr_t start; @@ -102,6 +107,8 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; + atomic_long_t total_used; + atomic_long_t used_hiwater; }; extern struct io_tlb_mem io_tlb_default_mem; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 938c959ab19e..9bbc2802a444 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -608,6 +608,40 @@ static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index) return index; } +/* + * Track the total used slots with a global atomic value in order to have + * correct information to determine the high water mark. The mem_used() + * function gives imprecise results because there's no locking across + * multiple areas. + */ +#ifdef CONFIG_DEBUG_FS +static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) +{ + unsigned long old_hiwater, new_used; + + new_used = atomic_long_add_return(nslots, &mem->total_used); + old_hiwater = atomic_long_read(&mem->used_hiwater); + do { + if (new_used <= old_hiwater) + break; + } while (!atomic_long_try_cmpxchg(&mem->used_hiwater, + &old_hiwater, new_used)); +} + +static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) +{ + atomic_long_sub(nslots, &mem->total_used); +} + +#else /* !CONFIG_DEBUG_FS */ +static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +#endif /* CONFIG_DEBUG_FS */ + /* * Find a suitable number of IO TLB entries size that will fit this request and * allocate a buffer from that IO TLB pool. @@ -702,6 +736,8 @@ static int swiotlb_do_find_slots(struct device *dev, int area_index, area->index = wrap_area_index(mem, index + nslots); area->used += nslots; spin_unlock_irqrestore(&area->lock, flags); + + inc_used_and_hiwater(mem, nslots); return slot_index; } @@ -834,6 +870,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) mem->slots[i].list = ++count; area->used -= nslots; spin_unlock_irqrestore(&area->lock, flags); + + dec_used(mem, nslots); } /* @@ -935,11 +973,37 @@ static int io_tlb_used_get(void *data, u64 *val) *val = mem_used(mem); return 0; } + +static int io_tlb_hiwater_get(void *data, u64 *val) +{ + struct io_tlb_mem *mem = data; + + *val = atomic_long_read(&mem->used_hiwater); + return 0; +} + +static int io_tlb_hiwater_set(void *data, u64 val) +{ + struct io_tlb_mem *mem = data; + + /* Only allow setting to zero */ + if (val != 0) + return -EINVAL; + + atomic_long_set(&mem->used_hiwater, val); + return 0; +} + DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, + io_tlb_hiwater_set, "%llu\n"); static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { + atomic_long_set(&mem->total_used, 0); + atomic_long_set(&mem->used_hiwater, 0); + mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); if (!mem->nslabs) return; @@ -947,6 +1011,8 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem, &fops_io_tlb_used); + debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, + &fops_io_tlb_hiwater); } static int __init __maybe_unused swiotlb_create_default_debugfs(void) -- GitLab From b2b1ddc457458fecd1c6f385baa9fbda5f0c63ad Mon Sep 17 00:00:00 2001 From: Zhu Yanjun Date: Thu, 13 Apr 2023 18:11:15 +0800 Subject: [PATCH 3095/5631] RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task" In the function rxe_create_qp(), rxe_qp_from_init() is called to initialize qp, internally things like rxe_init_task are not setup until rxe_qp_init_req(). If an error occurred before this point then the unwind will call rxe_cleanup() and eventually to rxe_qp_do_cleanup()/rxe_cleanup_task() which will oops when trying to access the uninitialized spinlock. If rxe_init_task is not executed, rxe_cleanup_task will not be called. Reported-by: syzbot+cfcc1a3c85be15a40cba@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=fd85757b74b3eb59f904138486f755f71e090df8 Fixes: 8700e3e7c485 ("Soft RoCE driver") Fixes: 2d4b21e0a291 ("IB/rxe: Prevent from completer to operate on non valid QP") Signed-off-by: Zhu Yanjun Link: https://lore.kernel.org/r/20230413101115.1366068-1-yanjun.zhu@intel.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rxe/rxe_qp.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 49891f8ed4e6..d5de5ba6940f 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -761,9 +761,14 @@ static void rxe_qp_do_cleanup(struct work_struct *work) del_timer_sync(&qp->rnr_nak_timer); } - rxe_cleanup_task(&qp->resp.task); - rxe_cleanup_task(&qp->req.task); - rxe_cleanup_task(&qp->comp.task); + if (qp->resp.task.func) + rxe_cleanup_task(&qp->resp.task); + + if (qp->req.task.func) + rxe_cleanup_task(&qp->req.task); + + if (qp->comp.task.func) + rxe_cleanup_task(&qp->comp.task); /* flush out any receive wr's or pending requests */ rxe_requester(qp); -- GitLab From 8d7c7c0eeb74281c846ef9231ce20536c79a99b4 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 14 Apr 2023 10:58:29 -0300 Subject: [PATCH 3096/5631] RDMA: Add ib_virt_dma_to_page() Make it clearer what is going on by adding a function to go back from the "virtual" dma_addr to a kva and another to a struct page. This is used in the ib_uses_virt_dma() style drivers (siw, rxe, hfi, qib). Call them instead of a naked casting and virt_to_page() when working with dma_addr values encoded by the various ib_map functions. This also fixes the virt_to_page() casting problem Linus Walleij has been chasing. Cc: Linus Walleij Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v2-05ea785520ed+10-ib_virt_page_jgg@nvidia.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/sw/rxe/rxe_mr.c | 16 ++++++++-------- drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +- drivers/infiniband/sw/siw/siw_qp_rx.c | 6 +++--- drivers/infiniband/sw/siw/siw_qp_tx.c | 19 ++++++------------- drivers/infiniband/sw/siw/siw_verbs.c | 4 ++-- include/rdma/ib_verbs.h | 25 +++++++++++++++++++++++++ 6 files changed, 45 insertions(+), 27 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c index 1e17f8086d59..0e538fafcc20 100644 --- a/drivers/infiniband/sw/rxe/rxe_mr.c +++ b/drivers/infiniband/sw/rxe/rxe_mr.c @@ -210,10 +210,10 @@ int rxe_mr_init_fast(int max_pages, struct rxe_mr *mr) return err; } -static int rxe_set_page(struct ib_mr *ibmr, u64 iova) +static int rxe_set_page(struct ib_mr *ibmr, u64 dma_addr) { struct rxe_mr *mr = to_rmr(ibmr); - struct page *page = virt_to_page(iova & mr->page_mask); + struct page *page = ib_virt_dma_to_page(dma_addr); bool persistent = !!(mr->access & IB_ACCESS_FLUSH_PERSISTENT); int err; @@ -279,16 +279,16 @@ static int rxe_mr_copy_xarray(struct rxe_mr *mr, u64 iova, void *addr, return 0; } -static void rxe_mr_copy_dma(struct rxe_mr *mr, u64 iova, void *addr, +static void rxe_mr_copy_dma(struct rxe_mr *mr, u64 dma_addr, void *addr, unsigned int length, enum rxe_mr_copy_dir dir) { - unsigned int page_offset = iova & (PAGE_SIZE - 1); + unsigned int page_offset = dma_addr & (PAGE_SIZE - 1); unsigned int bytes; struct page *page; u8 *va; while (length) { - page = virt_to_page(iova & mr->page_mask); + page = ib_virt_dma_to_page(dma_addr); bytes = min_t(unsigned int, length, PAGE_SIZE - page_offset); va = kmap_local_page(page); @@ -300,7 +300,7 @@ static void rxe_mr_copy_dma(struct rxe_mr *mr, u64 iova, void *addr, kunmap_local(va); page_offset = 0; - iova += bytes; + dma_addr += bytes; addr += bytes; length -= bytes; } @@ -488,7 +488,7 @@ int rxe_mr_do_atomic_op(struct rxe_mr *mr, u64 iova, int opcode, if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); - page = virt_to_page(iova & PAGE_MASK); + page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; @@ -545,7 +545,7 @@ int rxe_mr_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value) if (mr->ibmr.type == IB_MR_TYPE_DMA) { page_offset = iova & (PAGE_SIZE - 1); - page = virt_to_page(iova & PAGE_MASK); + page = ib_virt_dma_to_page(iova); } else { unsigned long index; int err; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 4e2db7c2e4ed..12819153bda7 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -760,7 +760,7 @@ static void copy_inline_data_to_wqe(struct rxe_send_wqe *wqe, int i; for (i = 0; i < ibwr->num_sge; i++, sge++) { - memcpy(p, (void *)(uintptr_t)sge->addr, sge->length); + memcpy(p, ib_virt_dma_to_page(sge->addr), sge->length); p += sge->length; } } diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index fd721cc19682..58bbf738e4e5 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -139,7 +139,7 @@ static int siw_rx_pbl(struct siw_rx_stream *srx, int *pbl_idx, break; bytes = min(bytes, len); - if (siw_rx_kva(srx, (void *)(uintptr_t)buf_addr, bytes) == + if (siw_rx_kva(srx, ib_virt_dma_to_ptr(buf_addr), bytes) == bytes) { copied += bytes; offset += bytes; @@ -487,7 +487,7 @@ int siw_proc_send(struct siw_qp *qp) mem_p = *mem; if (mem_p->mem_obj == NULL) rv = siw_rx_kva(srx, - (void *)(uintptr_t)(sge->laddr + frx->sge_off), + ib_virt_dma_to_ptr(sge->laddr + frx->sge_off), sge_bytes); else if (!mem_p->is_pbl) rv = siw_rx_umem(srx, mem_p->umem, @@ -852,7 +852,7 @@ int siw_proc_rresp(struct siw_qp *qp) if (mem_p->mem_obj == NULL) rv = siw_rx_kva(srx, - (void *)(uintptr_t)(sge->laddr + wqe->processed), + ib_virt_dma_to_ptr(sge->laddr + wqe->processed), bytes); else if (!mem_p->is_pbl) rv = siw_rx_umem(srx, mem_p->umem, sge->laddr + wqe->processed, diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c index 6bb9e9e81ff4..4b292e0504f1 100644 --- a/drivers/infiniband/sw/siw/siw_qp_tx.c +++ b/drivers/infiniband/sw/siw/siw_qp_tx.c @@ -29,7 +29,7 @@ static struct page *siw_get_pblpage(struct siw_mem *mem, u64 addr, int *idx) dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx); if (paddr) - return virt_to_page((void *)(uintptr_t)paddr); + return ib_virt_dma_to_page(paddr); return NULL; } @@ -56,8 +56,7 @@ static int siw_try_1seg(struct siw_iwarp_tx *c_tx, void *paddr) if (!mem->mem_obj) { /* Kernel client using kva */ - memcpy(paddr, - (const void *)(uintptr_t)sge->laddr, bytes); + memcpy(paddr, ib_virt_dma_to_ptr(sge->laddr), bytes); } else if (c_tx->in_syscall) { if (copy_from_user(paddr, u64_to_user_ptr(sge->laddr), bytes)) @@ -477,7 +476,7 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) * or memory region with assigned kernel buffer */ iov[seg].iov_base = - (void *)(uintptr_t)(sge->laddr + sge_off); + ib_virt_dma_to_ptr(sge->laddr + sge_off); iov[seg].iov_len = sge_len; if (do_crc) @@ -537,19 +536,13 @@ static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s) * Cast to an uintptr_t to preserve all 64 bits * in sge->laddr. */ - uintptr_t va = (uintptr_t)(sge->laddr + sge_off); + u64 va = sge->laddr + sge_off; - /* - * virt_to_page() takes a (void *) pointer - * so cast to a (void *) meaning it will be 64 - * bits on a 64 bit platform and 32 bits on a - * 32 bit platform. - */ - page_array[seg] = virt_to_page((void *)(va & PAGE_MASK)); + page_array[seg] = ib_virt_dma_to_page(va); if (do_crc) crypto_shash_update( c_tx->mpa_crc_hd, - (void *)va, + ib_virt_dma_to_ptr(va), plen); } diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 906fde1a2a0d..398ec13db624 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -660,7 +660,7 @@ static int siw_copy_inline_sgl(const struct ib_send_wr *core_wr, bytes = -EINVAL; break; } - memcpy(kbuf, (void *)(uintptr_t)core_sge->addr, + memcpy(kbuf, ib_virt_dma_to_ptr(core_sge->addr), core_sge->length); kbuf += core_sge->length; @@ -1523,7 +1523,7 @@ int siw_map_mr_sg(struct ib_mr *base_mr, struct scatterlist *sl, int num_sle, } siw_dbg_mem(mem, "sge[%d], size %u, addr 0x%p, total %lu\n", - i, pble->size, (void *)(uintptr_t)pble->addr, + i, pble->size, ib_virt_dma_to_ptr(pble->addr), pbl_size); } rv = ib_sg_to_pages(base_mr, sl, num_sle, sg_off, siw_set_pbl_page); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 949cf4ffc536..1e7774ac808f 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -4035,6 +4035,31 @@ static inline bool ib_dma_pci_p2p_dma_supported(struct ib_device *dev) return dma_pci_p2pdma_supported(dev->dma_device); } +/** + * ib_virt_dma_to_ptr - Convert a dma_addr to a kernel pointer + * @dma_addr: The DMA address + * + * Used by ib_uses_virt_dma() devices to get back to the kernel pointer after + * going through the dma_addr marshalling. + */ +static inline void *ib_virt_dma_to_ptr(u64 dma_addr) +{ + /* virt_dma mode maps the kvs's directly into the dma addr */ + return (void *)(uintptr_t)dma_addr; +} + +/** + * ib_virt_dma_to_page - Convert a dma_addr to a struct page + * @dma_addr: The DMA address + * + * Used by ib_uses_virt_dma() device to get back to the struct page after going + * through the dma_addr marshalling. + */ +static inline struct page *ib_virt_dma_to_page(u64 dma_addr) +{ + return virt_to_page(ib_virt_dma_to_ptr(dma_addr)); +} + /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created -- GitLab From ed4b0661cce119870edb1994fd06c9cbc1dc05c3 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Mon, 10 Apr 2023 16:07:50 +0300 Subject: [PATCH 3097/5631] RDMA/mlx5: Remove pcie_relaxed_ordering_enabled() check for RO write pcie_relaxed_ordering_enabled() check was added to avoid a syndrome when creating a MKey with relaxed ordering (RO) enabled when the driver's relaxed_ordering_{read,write} HCA capabilities are out of sync with FW. While this can happen with relaxed_ordering_read, it can't happen with relaxed_ordering_write as it's set if the device supports RO write, regardless of RO in PCI config space, and thus can't change during runtime. Therefore, drop the pcie_relaxed_ordering_enabled() check for relaxed_ordering_write while keeping it for relaxed_ordering_read. Doing so will also allow the usage of RO write in VFs and VMs (where RO in PCI config space is not reported/emulated properly). Signed-off-by: Avihai Horon Reviewed-by: Shay Drory Link: https://lore.kernel.org/r/7e8f55e31572c1702d69cae015a395d3a824a38a.1681131553.git.leon@kernel.org Reviewed-by: Jacob Keller Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mr.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 3 +-- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 2 +- 3 files changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 67356f515261..bd0a818ba1cd 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -67,11 +67,11 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, MLX5_SET(mkc, mkc, lw, !!(acc & IB_ACCESS_LOCAL_WRITE)); MLX5_SET(mkc, mkc, lr, 1); - if ((acc & IB_ACCESS_RELAXED_ORDERING) && - pcie_relaxed_ordering_enabled(dev->mdev->pdev)) { + if (acc & IB_ACCESS_RELAXED_ORDERING) { if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) MLX5_SET(mkc, mkc, relaxed_ordering_write, 1); - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read)) + if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) && + pcie_relaxed_ordering_enabled(dev->mdev->pdev)) MLX5_SET(mkc, mkc, relaxed_ordering_read, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index a21bd1179477..d840a59aec88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -867,8 +867,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { bool lro_en = params->packet_merge.type == MLX5E_PACKET_MERGE_LRO; - bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) && - MLX5_CAP_GEN(mdev, relaxed_ordering_write); + bool ro = MLX5_CAP_GEN(mdev, relaxed_ordering_write); return ro && lro_en ? MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 4c9a3210600c..993af4c12d90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -44,7 +44,7 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read); MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_pci_enable && ro_read); - MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_pci_enable && ro_write); + MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_write); } int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey) -- GitLab From d43b020b0f82c088ef8ff3196ef00575a97d200e Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Mon, 10 Apr 2023 16:07:51 +0300 Subject: [PATCH 3098/5631] RDMA/mlx5: Check pcie_relaxed_ordering_enabled() in UMR relaxed_ordering_read HCA capability is set if both the device supports relaxed ordering (RO) read and RO is set in PCI config space. RO in PCI config space can change during runtime. This will change the value of relaxed_ordering_read HCA capability in FW, but the driver will not see it since it queries the capabilities only once. This can lead to the following scenario: 1. RO in PCI config space is enabled. 2. User creates MKey without RO. 3. RO in PCI config space is disabled. As a result, relaxed_ordering_read HCA capability is turned off in FW but remains on in driver copy of the capabilities. 4. User requests to reconfig the MKey with RO via UMR. 5. Driver will try to reconfig the MKey with RO read although it shouldn't (as relaxed_ordering_read HCA capability is really off). To fix this, check pcie_relaxed_ordering_enabled() before setting RO read in UMR. Fixes: 896ec9735336 ("RDMA/mlx5: Set mkey relaxed ordering by UMR with ConnectX-7") Signed-off-by: Avihai Horon Reviewed-by: Shay Drory Link: https://lore.kernel.org/r/8d39eb8317e7bed1a354311a20ae707788fd94ed.1681131553.git.leon@kernel.org Reviewed-by: Jacob Keller Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/umr.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index 55f4e048d947..c9e176e8ced4 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -380,6 +380,9 @@ static void mlx5r_umr_set_access_flags(struct mlx5_ib_dev *dev, struct mlx5_mkey_seg *seg, unsigned int access_flags) { + bool ro_read = (access_flags & IB_ACCESS_RELAXED_ORDERING) && + pcie_relaxed_ordering_enabled(dev->mdev->pdev); + MLX5_SET(mkc, seg, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC)); MLX5_SET(mkc, seg, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE)); MLX5_SET(mkc, seg, rr, !!(access_flags & IB_ACCESS_REMOTE_READ)); @@ -387,8 +390,7 @@ static void mlx5r_umr_set_access_flags(struct mlx5_ib_dev *dev, MLX5_SET(mkc, seg, lr, 1); MLX5_SET(mkc, seg, relaxed_ordering_write, !!(access_flags & IB_ACCESS_RELAXED_ORDERING)); - MLX5_SET(mkc, seg, relaxed_ordering_read, - !!(access_flags & IB_ACCESS_RELAXED_ORDERING)); + MLX5_SET(mkc, seg, relaxed_ordering_read, ro_read); } int mlx5r_umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd, -- GitLab From ccbbfe0682f2fff1e157413c30092dd27c50e20e Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Mon, 10 Apr 2023 16:07:52 +0300 Subject: [PATCH 3099/5631] net/mlx5: Update relaxed ordering read HCA capabilities Rename existing HCA capability relaxed_ordering_read to relaxed_ordering_read_pci_enabled. This is in accordance with recent PRM change to better describe the capability, as it's set only if both the device supports relaxed ordering (RO) read and RO is enabled in PCI config space. In addition, add new HCA capability relaxed_ordering_read which is set if the device supports RO read, regardless of RO in PCI config space. This will be used in the following patch to allow RO in VFs and VMs. Signed-off-by: Avihai Horon Reviewed-by: Shay Drory Link: https://lore.kernel.org/r/caa0002fd8135086357dfcc368e2f5cc73b08480.1681131553.git.leon@kernel.org Reviewed-by: Jacob Keller Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mr.c | 5 +++-- drivers/infiniband/hw/mlx5/umr.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 5 +++-- 4 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index bd0a818ba1cd..6a3a8e00bfaa 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -70,7 +70,8 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, if (acc & IB_ACCESS_RELAXED_ORDERING) { if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) MLX5_SET(mkc, mkc, relaxed_ordering_write, 1); - if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) && + if (MLX5_CAP_GEN(dev->mdev, + relaxed_ordering_read_pci_enabled) && pcie_relaxed_ordering_enabled(dev->mdev->pdev)) MLX5_SET(mkc, mkc, relaxed_ordering_read, 1); } @@ -791,7 +792,7 @@ static int get_unchangeable_access_flags(struct mlx5_ib_dev *dev, ret |= IB_ACCESS_RELAXED_ORDERING; if ((access_flags & IB_ACCESS_RELAXED_ORDERING) && - MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) && + MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled) && !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr)) ret |= IB_ACCESS_RELAXED_ORDERING; diff --git a/drivers/infiniband/hw/mlx5/umr.h b/drivers/infiniband/hw/mlx5/umr.h index c9d0021381a2..e12ecd7e079c 100644 --- a/drivers/infiniband/hw/mlx5/umr.h +++ b/drivers/infiniband/hw/mlx5/umr.h @@ -62,7 +62,7 @@ static inline bool mlx5r_umr_can_reconfig(struct mlx5_ib_dev *dev, return false; if ((diffs & IB_ACCESS_RELAXED_ORDERING) && - MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) && + MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled) && !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 993af4c12d90..3c765a1f91a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -41,7 +41,7 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) { bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev); bool ro_write = MLX5_CAP_GEN(mdev, relaxed_ordering_write); - bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read); + bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read_pci_enabled); MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_pci_enable && ro_read); MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_write); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e4306cd87cd7..b54339a1b1c6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1511,7 +1511,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 relaxed_ordering_write[0x1]; - u8 relaxed_ordering_read[0x1]; + u8 relaxed_ordering_read_pci_enabled[0x1]; u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x6]; u8 terminate_scatter_list_mkey[0x1]; @@ -1727,7 +1727,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_320[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_at_328[0x3]; + u8 reserved_at_328[0x2]; + u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; u8 reserved_at_330[0x9]; u8 q_counter_aggregation[0x1]; -- GitLab From bd4ba605c4a92b46ab414626a4f969a19103f97a Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Mon, 10 Apr 2023 16:07:53 +0300 Subject: [PATCH 3100/5631] RDMA/mlx5: Allow relaxed ordering read in VFs and VMs According to PCIe spec, Enable Relaxed Ordering value in the VF's PCI config space is wired to 0 and PF relaxed ordering (RO) setting should be applied to the VF. In QEMU (and maybe others), when assigning VFs, the RO bit in PCI config space is not emulated properly and is always set to 0. Therefore, pcie_relaxed_ordering_enabled() always returns 0 for VFs and VMs and thus MKeys can't be created with RO read even if the PF supports it. pcie_relaxed_ordering_enabled() check was added to avoid a syndrome when creating a MKey with relaxed ordering (RO) enabled when the driver's relaxed_ordering_read_pci_enabled HCA capability is out of sync with FW. With the new relaxed_ordering_read capability this can't happen, as it's set regardless of RO value in PCI config space and thus can't change during runtime. Hence, to allow RO read in VFs and VMs, use the new HCA capability relaxed_ordering_read without checking pcie_relaxed_ordering_enabled(). The old capability checks are kept for backward compatibility with older FWs. Allowing RO in VFs and VMs is valuable since it can greatly improve performance on some setups. For example, testing throughput of a VF on an AMD EPYC 7763 and ConnectX-6 Dx setup showed roughly 60% performance improvement. Signed-off-by: Avihai Horon Reviewed-by: Shay Drory Reviewed-by: Aya Levin Link: https://lore.kernel.org/r/e7048640d66c341a8fa0465e099926e7989184bc.1681131553.git.leon@kernel.org Reviewed-by: Jacob Keller Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mr.c | 11 +++++++---- drivers/infiniband/hw/mlx5/umr.c | 3 ++- drivers/infiniband/hw/mlx5/umr.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 ++++--- 4 files changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 6a3a8e00bfaa..2017ede100a6 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -70,9 +70,11 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, if (acc & IB_ACCESS_RELAXED_ORDERING) { if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write)) MLX5_SET(mkc, mkc, relaxed_ordering_write, 1); - if (MLX5_CAP_GEN(dev->mdev, - relaxed_ordering_read_pci_enabled) && - pcie_relaxed_ordering_enabled(dev->mdev->pdev)) + + if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) || + (MLX5_CAP_GEN(dev->mdev, + relaxed_ordering_read_pci_enabled) && + pcie_relaxed_ordering_enabled(dev->mdev->pdev))) MLX5_SET(mkc, mkc, relaxed_ordering_read, 1); } @@ -792,7 +794,8 @@ static int get_unchangeable_access_flags(struct mlx5_ib_dev *dev, ret |= IB_ACCESS_RELAXED_ORDERING; if ((access_flags & IB_ACCESS_RELAXED_ORDERING) && - MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled) && + (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) || + MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled)) && !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr)) ret |= IB_ACCESS_RELAXED_ORDERING; diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index c9e176e8ced4..234bf30db731 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -381,7 +381,8 @@ static void mlx5r_umr_set_access_flags(struct mlx5_ib_dev *dev, unsigned int access_flags) { bool ro_read = (access_flags & IB_ACCESS_RELAXED_ORDERING) && - pcie_relaxed_ordering_enabled(dev->mdev->pdev); + (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) || + pcie_relaxed_ordering_enabled(dev->mdev->pdev)); MLX5_SET(mkc, seg, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC)); MLX5_SET(mkc, seg, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE)); diff --git a/drivers/infiniband/hw/mlx5/umr.h b/drivers/infiniband/hw/mlx5/umr.h index e12ecd7e079c..3799bb758e49 100644 --- a/drivers/infiniband/hw/mlx5/umr.h +++ b/drivers/infiniband/hw/mlx5/umr.h @@ -62,7 +62,8 @@ static inline bool mlx5r_umr_can_reconfig(struct mlx5_ib_dev *dev, return false; if ((diffs & IB_ACCESS_RELAXED_ORDERING) && - MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled) && + (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read) || + MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_pci_enabled)) && !MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read_umr)) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 3c765a1f91a5..1f90594499c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -39,11 +39,12 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) { - bool ro_pci_enable = pcie_relaxed_ordering_enabled(mdev->pdev); bool ro_write = MLX5_CAP_GEN(mdev, relaxed_ordering_write); - bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read_pci_enabled); + bool ro_read = MLX5_CAP_GEN(mdev, relaxed_ordering_read) || + (pcie_relaxed_ordering_enabled(mdev->pdev) && + MLX5_CAP_GEN(mdev, relaxed_ordering_read_pci_enabled)); - MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_pci_enable && ro_read); + MLX5_SET(mkc, mkc, relaxed_ordering_read, ro_read); MLX5_SET(mkc, mkc, relaxed_ordering_write, ro_write); } -- GitLab From 2196087b306952204eb38199437358161de2ae6b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 28 Feb 2023 08:37:26 -0800 Subject: [PATCH 3101/5631] MAINTAINERS: drop uclinux.org uclinux.org is dead. Drop it from the MAINTAINERS file. Signed-off-by: Randy Dunlap Cc: Greg Ungerer Cc: linux-m68k@lists.linux-m68k.org Signed-off-by: Greg Ungerer --- MAINTAINERS | 2 -- 1 file changed, 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 0e64787aace8..eb16b704400b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -21365,10 +21365,8 @@ F: include/uapi/linux/ublk_cmd.h UCLINUX (M68KNOMMU AND COLDFIRE) M: Greg Ungerer L: linux-m68k@lists.linux-m68k.org -L: uclinux-dev@uclinux.org (subscribers-only) S: Maintained W: http://www.linux-m68k.org/ -W: http://www.uclinux.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu.git F: arch/m68k/*/*_no.* F: arch/m68k/68*/ -- GitLab From 8ab89e9563161921ffc86724eb3217d228eaad57 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 20 Mar 2023 14:54:18 +0100 Subject: [PATCH 3102/5631] m68k: Kconfig.machine: remove obsolete configs ROMBASE and ROMSIZE The configs ROMBASE and ROMSIZE were used in arch/m68k/68360/head-ram.S, which was removed with commit a3595962d824 ("m68knommu: remove obsolete 68360 support"). Remove the obsolete configs ROMBASE and ROMSIZE. Signed-off-by: Lukas Bulwahn Fixes: a3595962d82495f5 ("m68knommu: remove obsolete 68360 support") Reviewed-by: Geert Uytterhoeven Signed-off-by: Greg Ungerer --- arch/m68k/Kconfig.machine | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index e2f961208f18..255d50574065 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -439,15 +439,6 @@ config ROM that can be stored in flash, with possibly the text, and data regions being copied out to RAM at startup. -config ROMBASE - hex "Address of the base of ROM device" - default "0" - depends on ROM - help - Define the address that the ROM region starts at. Some platforms - use this to set their chip select region accordingly for the boot - device. - config ROMVEC hex "Address of the base of the ROM vectors" default "0" @@ -465,14 +456,6 @@ config ROMSTART Define the start address of the system image in ROM. Commonly this is strait after the ROM vectors. -config ROMSIZE - hex "Size of the ROM device" - default "0x100000" - depends on ROM - help - Size of the ROM device. On some platforms this is used to setup - the chip select that controls the boot ROM device. - choice prompt "Kernel executes from" help -- GitLab From bea5b74504742f1b51b815bcaf9a70bddbc49ce3 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 6 Mar 2023 11:14:51 +0100 Subject: [PATCH 3103/5631] kallsyms: expand symbol name into comment for debugging The assembler output of kallsyms.c is not meant for people to understand, and is generally not helpful when debugging "Inconsistent kallsyms data" warnings. I have previously struggled with these, but found it helpful to list which symbols changed between the first and second pass in the .tmp_vmlinux.kallsyms*.S files. As this file is preprocessed, it's possible to add a C-style multiline comment with the full type/name tuple. Signed-off-by: Arnd Bergmann Signed-off-by: Masahiro Yamada --- scripts/kallsyms.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index a239a87e7bec..ea1e3d3aaa6b 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -525,7 +525,8 @@ static void write_src(void) table[i]->addr); exit(EXIT_FAILURE); } - printf("\t.long\t%#x\n", (int)offset); + expand_symbol(table[i]->sym, table[i]->len, buf); + printf("\t.long\t%#x /* %s */\n", (int)offset, buf); } else if (!symbol_absolute(table[i])) { output_address(table[i]->addr); } else { -- GitLab From a7b00a1811c9e562b44f0b283de7f01443123390 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:36 +0900 Subject: [PATCH 3104/5631] scripts/kallsyms: remove redundant code for omitting U and N The symbol types 'U' and 'N' are already filtered out by the following line in scripts/mksysmap: -e ' [aNUw] ' Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers --- scripts/kallsyms.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index ea1e3d3aaa6b..8148e880f78e 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -178,10 +178,7 @@ static bool is_ignored_symbol(const char *name, char type) return true; } - if (type == 'U' || type == 'u') - return true; - /* exclude debugging symbols */ - if (type == 'N' || type == 'n') + if (type == 'u' || type == 'n') return true; if (toupper(type) == 'A') { -- GitLab From e9f76363d0aa2d7c01288d9aad79b7e44855a435 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:37 +0900 Subject: [PATCH 3105/5631] scripts/mksysmap: remove comments described in nm(1) I do not think we need to repeat what is written in 'man nm'. Signed-off-by: Masahiro Yamada --- scripts/mksysmap | 20 +------------------- 1 file changed, 1 insertion(+), 19 deletions(-) diff --git a/scripts/mksysmap b/scripts/mksysmap index 16a08b8ef2f8..fea65fc3b624 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -9,25 +9,7 @@ ##### # Generate System.map (actual filename passed as second argument) - -# $NM produces the following output: -# f0081e80 T alloc_vfsmnt - -# The second row specify the type of the symbol: -# A = Absolute -# B = Uninitialised data (.bss) -# C = Common symbol -# D = Initialised data -# G = Initialised data for small objects -# I = Indirect reference to another symbol -# N = Debugging symbol -# R = Read only -# S = Uninitialised data for small objects -# T = Text code symbol -# U = Undefined symbol -# V = Weak symbol -# W = Weak symbol -# Corresponding small letters are local symbols +# The following refers to the symbol type as per nm(1). # For System.map filter away: # a - local absolute symbols -- GitLab From c4802044a0a7d7dfa82af858c2fa3ae9d76249c4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:38 +0900 Subject: [PATCH 3106/5631] scripts/mksysmap: use sed with in-line comments It is not feasible to insert comments in a multi-line shell command. Use sed, and move comments close to the code. Signed-off-by: Masahiro Yamada --- scripts/mksysmap | 61 +++++++++++++++++++++++++++++------------------- 1 file changed, 37 insertions(+), 24 deletions(-) diff --git a/scripts/mksysmap b/scripts/mksysmap index fea65fc3b624..41ad4605aeef 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -11,32 +11,45 @@ # Generate System.map (actual filename passed as second argument) # The following refers to the symbol type as per nm(1). -# For System.map filter away: -# a - local absolute symbols -# U - undefined global symbols -# N - debugging symbols -# w - local weak symbols - # readprofile starts reading symbols when _stext is found, and # continue until it finds a symbol which is not either of 'T', 't', # 'W' or 'w'. # -# Ignored prefixes: -# $ - local symbols for ARM, MIPS, etc. -# .L - local labels, .LBB,.Ltmpxxx,.L__unnamed_xx,.LASANPC, etc. -# __crc_ - modversions -# __kstrtab_ - EXPORT_SYMBOL (symbol name) -# __kstrtabns_ - EXPORT_SYMBOL (namespace) + +${NM} -n ${1} | sed >${2} -e " +# --------------------------------------------------------------------------- +# Ignored symbol types # -# Ignored symbols: -# L0 - for LoongArch? - -$NM -n $1 | grep -v \ - -e ' [aNUw] ' \ - -e ' \$' \ - -e ' \.L' \ - -e ' __crc_' \ - -e ' __kstrtab_' \ - -e ' __kstrtabns_' \ - -e ' L0$' \ -> $2 + +# a: local absolute symbols +# N: debugging symbols +# U: undefined global symbols +# w: local weak symbols +/ [aNUw] /d + +# --------------------------------------------------------------------------- +# Ignored prefixes +# (do not forget a space before each pattern) + +# local symbols for ARM, MIPS, etc. +/ \$/d + +# local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. +/ \.L/d + +# CRC from modversions +/ __crc_/d + +# EXPORT_SYMBOL (symbol name) +/ __kstrtab_/d + +# EXPORT_SYMBOL (namespace) +/ __kstrtabns_/d + +# --------------------------------------------------------------------------- +# Ignored symbols (exact match) +# (do not forget a space before and '$' after each pattern) + +# for LoongArch? +/ L0$/d +" -- GitLab From ca09bf48f99bdc08e17da11aeae56b7ea132b7c8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:39 +0900 Subject: [PATCH 3107/5631] scripts/kallsyms: exclude symbols generated by itself dynamically Drop the symbols generated by scripts/kallsyms itself automatically instead of maintaining the symbol list manually. Pass the kallsyms object from the previous kallsyms step (if it exists) as the third parameter of scripts/mksysmap, which will weed out the generated symbols from the input to the next kallsyms step. Signed-off-by: Masahiro Yamada --- scripts/kallsyms.c | 16 ---------------- scripts/link-vmlinux.sh | 6 +++--- scripts/mksysmap | 11 ++++++++++- 3 files changed, 13 insertions(+), 20 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 8148e880f78e..0325d0d3ce97 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -104,22 +104,6 @@ static bool is_ignored_symbol(const char *name, char type) { /* Symbol names that exactly match to the following are ignored.*/ static const char * const ignored_symbols[] = { - /* - * Symbols which vary between passes. Passes 1 and 2 must have - * identical symbol lists. The kallsyms_* symbols below are - * only added after pass 1, they would be included in pass 2 - * when --all-symbols is specified so exclude them to get a - * stable symbol list. - */ - "kallsyms_addresses", - "kallsyms_offsets", - "kallsyms_relative_base", - "kallsyms_num_syms", - "kallsyms_names", - "kallsyms_markers", - "kallsyms_token_table", - "kallsyms_token_index", - "kallsyms_seqs_of_names", /* Exclude linker generated symbols which vary between passes */ "_SDA_BASE_", /* ppc */ "_SDA2_BASE_", /* ppc */ diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 32e573943cf0..679eb4653b16 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -174,7 +174,7 @@ kallsyms_step() kallsyms_S=${kallsyms_vmlinux}.S vmlinux_link ${kallsyms_vmlinux} "${kallsymso_prev}" ${btf_vmlinux_bin_o} - mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms + mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms ${kallsymso_prev} kallsyms ${kallsyms_vmlinux}.syms ${kallsyms_S} info AS ${kallsyms_S} @@ -188,7 +188,7 @@ kallsyms_step() mksysmap() { info NM ${2} - ${CONFIG_SHELL} "${srctree}/scripts/mksysmap" ${1} ${2} + ${CONFIG_SHELL} "${srctree}/scripts/mksysmap" ${1} ${2} ${3} } sorttable() @@ -277,7 +277,7 @@ if is_enabled CONFIG_DEBUG_INFO_BTF && is_enabled CONFIG_BPF; then ${RESOLVE_BTFIDS} vmlinux fi -mksysmap vmlinux System.map +mksysmap vmlinux System.map ${kallsymso} if is_enabled CONFIG_BUILDTIME_TABLE_SORT; then info SORTTAB vmlinux diff --git a/scripts/mksysmap b/scripts/mksysmap index 41ad4605aeef..ff91ec8ecca7 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -4,7 +4,7 @@ # tools to retrieve the actual addresses of symbols in the kernel. # # Usage -# mksysmap vmlinux System.map +# mksysmap vmlinux System.map [exclude] ##### @@ -52,4 +52,13 @@ ${NM} -n ${1} | sed >${2} -e " # for LoongArch? / L0$/d + +# --------------------------------------------------------------------------- +# Ignored kallsyms symbols +# +# If the 3rd parameter exists, symbols from it will be omitted from the output. +# This makes kallsyms have the identical symbol lists in the step 1 and 2. +# Without this, the step2 would get new symbols generated by scripts/kallsyms.c +# when CONFIG_KALLSYMS_ALL is enabled. That might require one more pass. +$(if [ $# -ge 3 ]; then ${NM} ${3} | sed -n '/ U /!s:.* \([^ ]*\)$:/ \1$/d:p'; fi) " -- GitLab From 320e7c9d4494f7a6f046871678f582a3392235f8 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:40 +0900 Subject: [PATCH 3108/5631] scripts/kallsyms: move compiler-generated symbol patterns to mksysmap scripts/kallsyms.c maintains compiler-generated symbols, but we end up with something similar in scripts/mksysmap to avoid the "Inconsistent kallsyms data" error. For example, commit c17a2538704f ("mksysmap: Fix the mismatch of 'L0' symbols in System.map"). They were separately maintained prior to commit 94ff2f63d6a3 ("kbuild: reuse mksysmap output for kallsyms"). Now that scripts/kallsyms.c parses the output of scripts/mksysmap, it makes more sense to collect all the ignored patterns to mksysmap. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers --- scripts/kallsyms.c | 60 ---------------------------------------------- scripts/mksysmap | 43 +++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 60 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 0325d0d3ce97..97d514c0fc8f 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -102,66 +102,6 @@ static char *sym_name(const struct sym_entry *s) static bool is_ignored_symbol(const char *name, char type) { - /* Symbol names that exactly match to the following are ignored.*/ - static const char * const ignored_symbols[] = { - /* Exclude linker generated symbols which vary between passes */ - "_SDA_BASE_", /* ppc */ - "_SDA2_BASE_", /* ppc */ - NULL - }; - - /* Symbol names that begin with the following are ignored.*/ - static const char * const ignored_prefixes[] = { - "__efistub_", /* arm64 EFI stub namespace */ - "__kvm_nvhe_$", /* arm64 local symbols in non-VHE KVM namespace */ - "__kvm_nvhe_.L", /* arm64 local symbols in non-VHE KVM namespace */ - "__AArch64ADRPThunk_", /* arm64 lld */ - "__ARMV5PILongThunk_", /* arm lld */ - "__ARMV7PILongThunk_", - "__ThumbV7PILongThunk_", - "__LA25Thunk_", /* mips lld */ - "__microLA25Thunk_", - "__kcfi_typeid_", /* CFI type identifiers */ - NULL - }; - - /* Symbol names that end with the following are ignored.*/ - static const char * const ignored_suffixes[] = { - "_from_arm", /* arm */ - "_from_thumb", /* arm */ - "_veneer", /* arm */ - NULL - }; - - /* Symbol names that contain the following are ignored.*/ - static const char * const ignored_matches[] = { - ".long_branch.", /* ppc stub */ - ".plt_branch.", /* ppc stub */ - NULL - }; - - const char * const *p; - - for (p = ignored_symbols; *p; p++) - if (!strcmp(name, *p)) - return true; - - for (p = ignored_prefixes; *p; p++) - if (!strncmp(name, *p, strlen(*p))) - return true; - - for (p = ignored_suffixes; *p; p++) { - int l = strlen(name) - strlen(*p); - - if (l >= 0 && !strcmp(name + l, *p)) - return true; - } - - for (p = ignored_matches; *p; p++) { - if (strstr(name, *p)) - return true; - } - if (type == 'u' || type == 'n') return true; diff --git a/scripts/mksysmap b/scripts/mksysmap index ff91ec8ecca7..cb3b1fff3eee 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -37,6 +37,28 @@ ${NM} -n ${1} | sed >${2} -e " # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d +# arm64 EFI stub namespace +/ __efistub_/d + +# arm64 local symbols in non-VHE KVM namespace +/ __kvm_nvhe_\$/d +/ __kvm_nvhe_\.L/d + +# arm64 lld +/ __AArch64ADRPThunk_/d + +# arm lld +/ __ARMV5PILongThunk_/d +/ __ARMV7PILongThunk_/d +/ __ThumbV7PILongThunk_/d + +# mips lld +/ __LA25Thunk_/d +/ __microLA25Thunk_/d + +# CFI type identifiers +/ __kcfi_typeid_/d + # CRC from modversions / __crc_/d @@ -46,6 +68,15 @@ ${NM} -n ${1} | sed >${2} -e " # EXPORT_SYMBOL (namespace) / __kstrtabns_/d +# --------------------------------------------------------------------------- +# Ignored suffixes +# (do not forget '$' after each pattern) + +# arm +/_from_arm$/d +/_from_thumb$/d +/_veneer$/d + # --------------------------------------------------------------------------- # Ignored symbols (exact match) # (do not forget a space before and '$' after each pattern) @@ -53,6 +84,18 @@ ${NM} -n ${1} | sed >${2} -e " # for LoongArch? / L0$/d +# ppc +/ _SDA_BASE_$/d +/ _SDA2_BASE_$/d + +# --------------------------------------------------------------------------- +# Ignored patterns +# (symbols that contain the pattern are ignored) + +# ppc stub +/\.long_branch\./d +/\.plt_branch\./d + # --------------------------------------------------------------------------- # Ignored kallsyms symbols # -- GitLab From 404bad70fcf7cb1a36198581e6904637f3c36846 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:41 +0900 Subject: [PATCH 3109/5631] scripts/kallsyms: change the output order Currently, this tool outputs symbol data in the following order. (1) kallsyms_addressed / kallsyms_offsets (2) kallsyms_relative_base (3) kallsyms_num_syms (4) kallsyms_names (5) kallsyms_markers (6) kallsyms_seq_of_names (7) kallsyms_token_table (8) kallsyms_token_index This commit changes the order as follows: (1) kallsyms_num_syms (2) kallsyms_names (3) kallsyms_markers (4) kallsyms_token_table (5) kallsyms_token_index (6) kallsyms_addressed / kallsyms_offsets (7) kallsyms_relative_base (8) kallsyms_seq_of_names The motivation is to decrease the number of function calls to expand_symbol() and cleanup_symbol_name(). The compressed names are only required for writing 'kallsyms_names'. If you do this first, we can restore the original symbol names. You do not need to repeat the same operation over again. The actual refactoring will happen in the next commit. Signed-off-by: Masahiro Yamada --- scripts/kallsyms.c | 118 ++++++++++++++++++++++----------------------- 1 file changed, 59 insertions(+), 59 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 97d514c0fc8f..5996f1e61bcf 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -412,56 +412,6 @@ static void write_src(void) printf("\t.section .rodata, \"a\"\n"); - if (!base_relative) - output_label("kallsyms_addresses"); - else - output_label("kallsyms_offsets"); - - for (i = 0; i < table_cnt; i++) { - if (base_relative) { - /* - * Use the offset relative to the lowest value - * encountered of all relative symbols, and emit - * non-relocatable fixed offsets that will be fixed - * up at runtime. - */ - - long long offset; - int overflow; - - if (!absolute_percpu) { - offset = table[i]->addr - relative_base; - overflow = (offset < 0 || offset > UINT_MAX); - } else if (symbol_absolute(table[i])) { - offset = table[i]->addr; - overflow = (offset < 0 || offset > INT_MAX); - } else { - offset = relative_base - table[i]->addr - 1; - overflow = (offset < INT_MIN || offset >= 0); - } - if (overflow) { - fprintf(stderr, "kallsyms failure: " - "%s symbol value %#llx out of range in relative mode\n", - symbol_absolute(table[i]) ? "absolute" : "relative", - table[i]->addr); - exit(EXIT_FAILURE); - } - expand_symbol(table[i]->sym, table[i]->len, buf); - printf("\t.long\t%#x /* %s */\n", (int)offset, buf); - } else if (!symbol_absolute(table[i])) { - output_address(table[i]->addr); - } else { - printf("\tPTR\t%#llx\n", table[i]->addr); - } - } - printf("\n"); - - if (base_relative) { - output_label("kallsyms_relative_base"); - output_address(relative_base); - printf("\n"); - } - output_label("kallsyms_num_syms"); printf("\t.long\t%u\n", table_cnt); printf("\n"); @@ -521,15 +471,6 @@ static void write_src(void) free(markers); - sort_symbols_by_name(); - output_label("kallsyms_seqs_of_names"); - for (i = 0; i < table_cnt; i++) - printf("\t.byte 0x%02x, 0x%02x, 0x%02x\n", - (unsigned char)(table[i]->seq >> 16), - (unsigned char)(table[i]->seq >> 8), - (unsigned char)(table[i]->seq >> 0)); - printf("\n"); - output_label("kallsyms_token_table"); off = 0; for (i = 0; i < 256; i++) { @@ -544,6 +485,65 @@ static void write_src(void) for (i = 0; i < 256; i++) printf("\t.short\t%d\n", best_idx[i]); printf("\n"); + + if (!base_relative) + output_label("kallsyms_addresses"); + else + output_label("kallsyms_offsets"); + + for (i = 0; i < table_cnt; i++) { + if (base_relative) { + /* + * Use the offset relative to the lowest value + * encountered of all relative symbols, and emit + * non-relocatable fixed offsets that will be fixed + * up at runtime. + */ + + long long offset; + int overflow; + + if (!absolute_percpu) { + offset = table[i]->addr - relative_base; + overflow = (offset < 0 || offset > UINT_MAX); + } else if (symbol_absolute(table[i])) { + offset = table[i]->addr; + overflow = (offset < 0 || offset > INT_MAX); + } else { + offset = relative_base - table[i]->addr - 1; + overflow = (offset < INT_MIN || offset >= 0); + } + if (overflow) { + fprintf(stderr, "kallsyms failure: " + "%s symbol value %#llx out of range in relative mode\n", + symbol_absolute(table[i]) ? "absolute" : "relative", + table[i]->addr); + exit(EXIT_FAILURE); + } + expand_symbol(table[i]->sym, table[i]->len, buf); + printf("\t.long\t%#x /* %s */\n", (int)offset, buf); + } else if (!symbol_absolute(table[i])) { + output_address(table[i]->addr); + } else { + printf("\tPTR\t%#llx\n", table[i]->addr); + } + } + printf("\n"); + + if (base_relative) { + output_label("kallsyms_relative_base"); + output_address(relative_base); + printf("\n"); + } + + sort_symbols_by_name(); + output_label("kallsyms_seqs_of_names"); + for (i = 0; i < table_cnt; i++) + printf("\t.byte 0x%02x, 0x%02x, 0x%02x\n", + (unsigned char)(table[i]->seq >> 16), + (unsigned char)(table[i]->seq >> 8), + (unsigned char)(table[i]->seq >> 0)); + printf("\n"); } -- GitLab From dd1553b8a5f2ef4e0aa2537c49ba0c37837b691e Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:42 +0900 Subject: [PATCH 3110/5631] scripts/kallsyms: decrease expand_symbol() / cleanup_symbol_name() calls Currently, expand_symbol() is called many times to get the uncompressed symbol names for sorting, and also for adding comments. With the output order shuffled in the previous commit, the symbol data are now written in the following order: (1) kallsyms_num_syms (2) kallsyms_names <-- need compressed names (3) kallsyms_markers (4) kallsyms_token_table (5) kallsyms_token_index (6) kallsyms_addressed / kallsyms_offsets <-- need uncompressed names (for commenting) (7) kallsyms_relative_base (8) kallsyms_seq_of_names <-- need uncompressed names (for sorting) The compressed names are only needed by (2). Call expand_symbol() between (2) and (3) to restore the original symbol names. This requires just one expand_symbol() call for each symbol. Call cleanup_symbol_name() between (7) and (8) instead of during sorting. It is allowed to overwrite the ->sym field because (8) just outputs the index instead of the name of each symbol. Again, this requires just one cleanup_symbol_name() call for each symbol. This refactoring makes it ~30% faster. [Before] $ time scripts/kallsyms --all-symbols --absolute-percpu --base-relative \ .tmp_vmlinux.kallsyms2.syms >/dev/null real 0m1.027s user 0m1.010s sys 0m0.016s [After] $ time scripts/kallsyms --all-symbols --absolute-percpu --base-relative \ .tmp_vmlinux.kallsyms2.syms >/dev/null real 0m0.717s user 0m0.717s sys 0m0.000s Signed-off-by: Masahiro Yamada --- scripts/kallsyms.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 5996f1e61bcf..937900823fa8 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -335,19 +335,10 @@ static int symbol_absolute(const struct sym_entry *s) return s->percpu_absolute; } -static char * s_name(char *buf) -{ - /* Skip the symbol type */ - return buf + 1; -} - static void cleanup_symbol_name(char *s) { char *p; - if (!lto_clang) - return; - /* * ASCII[.] = 2e * ASCII[0-9] = 30,39 @@ -366,16 +357,10 @@ static void cleanup_symbol_name(char *s) static int compare_names(const void *a, const void *b) { int ret; - char sa_namebuf[KSYM_NAME_LEN]; - char sb_namebuf[KSYM_NAME_LEN]; const struct sym_entry *sa = *(const struct sym_entry **)a; const struct sym_entry *sb = *(const struct sym_entry **)b; - expand_symbol(sa->sym, sa->len, sa_namebuf); - expand_symbol(sb->sym, sb->len, sb_namebuf); - cleanup_symbol_name(s_name(sa_namebuf)); - cleanup_symbol_name(s_name(sb_namebuf)); - ret = strcmp(s_name(sa_namebuf), s_name(sb_namebuf)); + ret = strcmp(sym_name(sa), sym_name(sb)); if (!ret) { if (sa->addr > sb->addr) return 1; @@ -464,6 +449,15 @@ static void write_src(void) } printf("\n"); + /* + * Now that we wrote out the compressed symbol names, restore the + * original names, which are needed in some of the later steps. + */ + for (i = 0; i < table_cnt; i++) { + expand_symbol(table[i]->sym, table[i]->len, buf); + strcpy((char *)table[i]->sym, buf); + } + output_label("kallsyms_markers"); for (i = 0; i < ((table_cnt + 255) >> 8); i++) printf("\t.long\t%u\n", markers[i]); @@ -520,8 +514,7 @@ static void write_src(void) table[i]->addr); exit(EXIT_FAILURE); } - expand_symbol(table[i]->sym, table[i]->len, buf); - printf("\t.long\t%#x /* %s */\n", (int)offset, buf); + printf("\t.long\t%#x /* %s */\n", (int)offset, table[i]->sym); } else if (!symbol_absolute(table[i])) { output_address(table[i]->addr); } else { @@ -536,6 +529,10 @@ static void write_src(void) printf("\n"); } + if (lto_clang) + for (i = 0; i < table_cnt; i++) + cleanup_symbol_name((char *)table[i]->sym); + sort_symbols_by_name(); output_label("kallsyms_seqs_of_names"); for (i = 0; i < table_cnt; i++) -- GitLab From 79549da691edd4874c19d99c578a134471817c47 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Wed, 8 Mar 2023 20:52:43 +0900 Subject: [PATCH 3111/5631] scripts/kallsyms: update the usage in the comment block Commit 010a0aad39fc ("kallsyms: Correctly sequence symbols when CONFIG_LTO_CLANG=y") added --lto-clang, and updated the usage() function, but not the comment. Update it in the same way. Signed-off-by: Masahiro Yamada Reviewed-by: Nick Desaulniers --- scripts/kallsyms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 937900823fa8..0d2db41177b2 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -6,7 +6,7 @@ * of the GNU General Public License, incorporated herein by reference. * * Usage: kallsyms [--all-symbols] [--absolute-percpu] - * [--base-relative] in.map > out.S + * [--base-relative] [--lto-clang] in.map > out.S * * Table compression uses all the unused char codes on the symbols and * maps these to the most used substrings (tokens). For instance, it might -- GitLab From 491b146d4c13908a23436bd44dc1f01d1a0a99e6 Mon Sep 17 00:00:00 2001 From: Bastian Germann Date: Tue, 14 Mar 2023 01:40:22 +0100 Subject: [PATCH 3112/5631] kbuild: builddeb: Eliminate debian/arch use In the builddeb context, the DEB_HOST_ARCH environment variable is set to the same value as debian/arch's content, so use the variable with dpkg-architecture. This is the last use of the debian/arch file during dpkg-buildpackage time. Signed-off-by: Bastian Germann Signed-off-by: Masahiro Yamada --- scripts/package/builddeb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 7b23f52c70c5..252faaa5561c 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -209,7 +209,7 @@ install_libc_headers () { # move asm headers to /usr/include//asm to match the structure # used by Debian-based distros (to support multi-arch) - host_arch=$(dpkg-architecture -a$(cat debian/arch) -qDEB_HOST_MULTIARCH) + host_arch=$(dpkg-architecture -a$DEB_HOST_ARCH -qDEB_HOST_MULTIARCH) mkdir $pdir/usr/include/$host_arch mv $pdir/usr/include/asm $pdir/usr/include/$host_arch/ } -- GitLab From 90fe4c506c855ee90116a96ec25fa39ea8e9f202 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Mar 2023 00:18:15 +0900 Subject: [PATCH 3113/5631] kconfig: menuconfig: remove OLD_NCURSES macro This code has been here for more than 20 years. The bug in the old days no longer matters. Signed-off-by: Masahiro Yamada --- scripts/kconfig/lxdialog/dialog.h | 16 ---------------- scripts/kconfig/lxdialog/menubox.c | 8 -------- scripts/kconfig/lxdialog/textbox.c | 9 --------- 3 files changed, 33 deletions(-) diff --git a/scripts/kconfig/lxdialog/dialog.h b/scripts/kconfig/lxdialog/dialog.h index 68b565e3c495..bd2da3a928a7 100644 --- a/scripts/kconfig/lxdialog/dialog.h +++ b/scripts/kconfig/lxdialog/dialog.h @@ -18,22 +18,6 @@ #endif #include -/* - * Colors in ncurses 1.9.9e do not work properly since foreground and - * background colors are OR'd rather than separately masked. This version - * of dialog was hacked to work with ncurses 1.9.9e, making it incompatible - * with standard curses. The simplest fix (to make this work with standard - * curses) uses the wbkgdset() function, not used in the original hack. - * Turn it off if we're building with 1.9.9e, since it just confuses things. - */ -#if defined(NCURSES_VERSION) && defined(_NEED_WRAP) && !defined(GCC_PRINTFLIKE) -#define OLD_NCURSES 1 -#undef wbkgdset -#define wbkgdset(w,p) /*nothing */ -#else -#define OLD_NCURSES 0 -#endif - #define TR(params) _tracef params #define KEY_ESC 27 diff --git a/scripts/kconfig/lxdialog/menubox.c b/scripts/kconfig/lxdialog/menubox.c index 58c2f8afe59b..0e333284e947 100644 --- a/scripts/kconfig/lxdialog/menubox.c +++ b/scripts/kconfig/lxdialog/menubox.c @@ -63,15 +63,7 @@ static void do_print_item(WINDOW * win, const char *item, int line_y, /* Clear 'residue' of last item */ wattrset(win, dlg.menubox.atr); wmove(win, line_y, 0); -#if OLD_NCURSES - { - int i; - for (i = 0; i < menu_width; i++) - waddch(win, ' '); - } -#else wclrtoeol(win); -#endif wattrset(win, selected ? dlg.item_selected.atr : dlg.item.atr); mvwaddstr(win, line_y, item_x, menu_item); if (hotkey) { diff --git a/scripts/kconfig/lxdialog/textbox.c b/scripts/kconfig/lxdialog/textbox.c index 4e339b12664e..4a6ff9de45b9 100644 --- a/scripts/kconfig/lxdialog/textbox.c +++ b/scripts/kconfig/lxdialog/textbox.c @@ -336,16 +336,7 @@ static void print_line(WINDOW * win, int row, int width) waddnstr(win, line, MIN(strlen(line), width - 2)); /* Clear 'residue' of previous line */ -#if OLD_NCURSES - { - int x = getcurx(win); - int i; - for (i = 0; i < width - x; i++) - waddch(win, ' '); - } -#else wclrtoeol(win); -#endif } /* -- GitLab From b84e3687da9436c5438021800ce2d7baa03c2eab Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Mar 2023 00:18:16 +0900 Subject: [PATCH 3114/5631] kconfig: menuconfig: remove unused M_EVENT macro This is not used anywhere. Signed-off-by: Masahiro Yamada --- scripts/kconfig/lxdialog/dialog.h | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/scripts/kconfig/lxdialog/dialog.h b/scripts/kconfig/lxdialog/dialog.h index bd2da3a928a7..347daf25fdc8 100644 --- a/scripts/kconfig/lxdialog/dialog.h +++ b/scripts/kconfig/lxdialog/dialog.h @@ -209,14 +209,3 @@ int dialog_checklist(const char *title, const char *prompt, int height, int width, int list_height); int dialog_inputbox(const char *title, const char *prompt, int height, int width, const char *init); - -/* - * This is the base for fictitious keys, which activate - * the buttons. - * - * Mouse-generated keys are the following: - * -- the first 32 are used as numbers, in addition to '0'-'9' - * -- the lowercase are used to signal mouse-enter events (M_EVENT + 'o') - * -- uppercase chars are used to invoke the button (M_EVENT + 'O') - */ -#define M_EVENT (KEY_MAX+1) -- GitLab From fb318e54fea6b8532833faef98c8b7720a30b29d Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Mar 2023 00:18:17 +0900 Subject: [PATCH 3115/5631] kconfig: menuconfig: reorder functions to remove forward declarations Define helper functions before the callers so that forward declarations can go away. Signed-off-by: Masahiro Yamada --- scripts/kconfig/lxdialog/textbox.c | 258 ++++++++++++------------ scripts/kconfig/mconf.c | 314 ++++++++++++++--------------- 2 files changed, 277 insertions(+), 295 deletions(-) diff --git a/scripts/kconfig/lxdialog/textbox.c b/scripts/kconfig/lxdialog/textbox.c index 4a6ff9de45b9..bc4d4fb1dc75 100644 --- a/scripts/kconfig/lxdialog/textbox.c +++ b/scripts/kconfig/lxdialog/textbox.c @@ -8,18 +8,136 @@ #include "dialog.h" -static void back_lines(int n); -static void print_page(WINDOW *win, int height, int width, update_text_fn - update_text, void *data); -static void print_line(WINDOW *win, int row, int width); -static char *get_line(void); -static void print_position(WINDOW * win); - static int hscroll; static int begin_reached, end_reached, page_length; static char *buf; static char *page; +/* + * Go back 'n' lines in text. Called by dialog_textbox(). + * 'page' will be updated to point to the desired line in 'buf'. + */ +static void back_lines(int n) +{ + int i; + + begin_reached = 0; + /* Go back 'n' lines */ + for (i = 0; i < n; i++) { + if (*page == '\0') { + if (end_reached) { + end_reached = 0; + continue; + } + } + if (page == buf) { + begin_reached = 1; + return; + } + page--; + do { + if (page == buf) { + begin_reached = 1; + return; + } + page--; + } while (*page != '\n'); + page++; + } +} + +/* + * Return current line of text. Called by dialog_textbox() and print_line(). + * 'page' should point to start of current line before calling, and will be + * updated to point to start of next line. + */ +static char *get_line(void) +{ + int i = 0; + static char line[MAX_LEN + 1]; + + end_reached = 0; + while (*page != '\n') { + if (*page == '\0') { + end_reached = 1; + break; + } else if (i < MAX_LEN) + line[i++] = *(page++); + else { + /* Truncate lines longer than MAX_LEN characters */ + if (i == MAX_LEN) + line[i++] = '\0'; + page++; + } + } + if (i <= MAX_LEN) + line[i] = '\0'; + if (!end_reached) + page++; /* move past '\n' */ + + return line; +} + +/* + * Print a new line of text. + */ +static void print_line(WINDOW *win, int row, int width) +{ + char *line; + + line = get_line(); + line += MIN(strlen(line), hscroll); /* Scroll horizontally */ + wmove(win, row, 0); /* move cursor to correct line */ + waddch(win, ' '); + waddnstr(win, line, MIN(strlen(line), width - 2)); + + /* Clear 'residue' of previous line */ + wclrtoeol(win); +} + +/* + * Print a new page of text. + */ +static void print_page(WINDOW *win, int height, int width, update_text_fn + update_text, void *data) +{ + int i, passed_end = 0; + + if (update_text) { + char *end; + + for (i = 0; i < height; i++) + get_line(); + end = page; + back_lines(height); + update_text(buf, page - buf, end - buf, data); + } + + page_length = 0; + for (i = 0; i < height; i++) { + print_line(win, i, width); + if (!passed_end) + page_length++; + if (end_reached && !passed_end) + passed_end = 1; + } + wnoutrefresh(win); +} + +/* + * Print current position + */ +static void print_position(WINDOW *win) +{ + int percent; + + wattrset(win, dlg.position_indicator.atr); + wbkgdset(win, dlg.position_indicator.atr & A_COLOR); + percent = (page - buf) * 100 / strlen(buf); + wmove(win, getmaxy(win) - 3, getmaxx(win) - 9); + wprintw(win, "(%3d%%)", percent); +} + /* * refresh window content */ @@ -33,7 +151,6 @@ static void refresh_text_box(WINDOW *dialog, WINDOW *box, int boxh, int boxw, wrefresh(dialog); } - /* * Display text from a file in a dialog box. * @@ -259,128 +376,3 @@ int dialog_textbox(const char *title, char *tbuf, int initial_height, *_hscroll = hscroll; return key; } - -/* - * Go back 'n' lines in text. Called by dialog_textbox(). - * 'page' will be updated to point to the desired line in 'buf'. - */ -static void back_lines(int n) -{ - int i; - - begin_reached = 0; - /* Go back 'n' lines */ - for (i = 0; i < n; i++) { - if (*page == '\0') { - if (end_reached) { - end_reached = 0; - continue; - } - } - if (page == buf) { - begin_reached = 1; - return; - } - page--; - do { - if (page == buf) { - begin_reached = 1; - return; - } - page--; - } while (*page != '\n'); - page++; - } -} - -/* - * Print a new page of text. - */ -static void print_page(WINDOW *win, int height, int width, update_text_fn - update_text, void *data) -{ - int i, passed_end = 0; - - if (update_text) { - char *end; - - for (i = 0; i < height; i++) - get_line(); - end = page; - back_lines(height); - update_text(buf, page - buf, end - buf, data); - } - - page_length = 0; - for (i = 0; i < height; i++) { - print_line(win, i, width); - if (!passed_end) - page_length++; - if (end_reached && !passed_end) - passed_end = 1; - } - wnoutrefresh(win); -} - -/* - * Print a new line of text. - */ -static void print_line(WINDOW * win, int row, int width) -{ - char *line; - - line = get_line(); - line += MIN(strlen(line), hscroll); /* Scroll horizontally */ - wmove(win, row, 0); /* move cursor to correct line */ - waddch(win, ' '); - waddnstr(win, line, MIN(strlen(line), width - 2)); - - /* Clear 'residue' of previous line */ - wclrtoeol(win); -} - -/* - * Return current line of text. Called by dialog_textbox() and print_line(). - * 'page' should point to start of current line before calling, and will be - * updated to point to start of next line. - */ -static char *get_line(void) -{ - int i = 0; - static char line[MAX_LEN + 1]; - - end_reached = 0; - while (*page != '\n') { - if (*page == '\0') { - end_reached = 1; - break; - } else if (i < MAX_LEN) - line[i++] = *(page++); - else { - /* Truncate lines longer than MAX_LEN characters */ - if (i == MAX_LEN) - line[i++] = '\0'; - page++; - } - } - if (i <= MAX_LEN) - line[i] = '\0'; - if (!end_reached) - page++; /* move past '\n' */ - - return line; -} - -/* - * Print current position - */ -static void print_position(WINDOW * win) -{ - int percent; - - wattrset(win, dlg.position_indicator.atr); - wbkgdset(win, dlg.position_indicator.atr & A_COLOR); - percent = (page - buf) * 100 / strlen(buf); - wmove(win, getmaxy(win) - 3, getmaxx(win) - 9); - wprintw(win, "(%3d%%)", percent); -} diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index e67e0db50b2e..53d8834d12fe 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -290,16 +290,6 @@ static int save_and_exit; static int silent; static void conf(struct menu *menu, struct menu *active_menu); -static void conf_choice(struct menu *menu); -static void conf_string(struct menu *menu); -static void conf_load(void); -static void conf_save(void); -static int show_textbox_ext(const char *title, char *text, int r, int c, - int *keys, int *vscroll, int *hscroll, - update_text_fn update_text, void *data); -static void show_textbox(const char *title, const char *text, int r, int c); -static void show_helptext(const char *title, const char *text); -static void show_help(struct menu *menu); static char filename[PATH_MAX+1]; static void set_config_filename(const char *config_filename) @@ -358,6 +348,37 @@ static void reset_subtitle(void) set_dialog_subtitles(subtitles); } +static int show_textbox_ext(const char *title, char *text, int r, int c, int + *keys, int *vscroll, int *hscroll, update_text_fn + update_text, void *data) +{ + dialog_clear(); + return dialog_textbox(title, text, r, c, keys, vscroll, hscroll, + update_text, data); +} + +static void show_textbox(const char *title, const char *text, int r, int c) +{ + show_textbox_ext(title, (char *) text, r, c, (int []) {0}, NULL, NULL, + NULL, NULL); +} + +static void show_helptext(const char *title, const char *text) +{ + show_textbox(title, text, 0, 0); +} + +static void show_help(struct menu *menu) +{ + struct gstr help = str_new(); + + help.max_width = getmaxx(stdscr) - 10; + menu_get_ext_help(menu, &help); + + show_helptext(menu_get_prompt(menu), str_get(&help)); + str_free(&help); +} + struct search_data { struct list_head *head; struct menu **targets; @@ -643,158 +664,6 @@ static void build_conf(struct menu *menu) indent -= doint; } -static void conf(struct menu *menu, struct menu *active_menu) -{ - struct menu *submenu; - const char *prompt = menu_get_prompt(menu); - struct subtitle_part stpart; - struct symbol *sym; - int res; - int s_scroll = 0; - - if (menu != &rootmenu) - stpart.text = menu_get_prompt(menu); - else - stpart.text = NULL; - list_add_tail(&stpart.entries, &trail); - - while (1) { - item_reset(); - current_menu = menu; - build_conf(menu); - if (!child_count) - break; - set_subtitle(); - dialog_clear(); - res = dialog_menu(prompt ? prompt : "Main Menu", - menu_instructions, - active_menu, &s_scroll); - if (res == 1 || res == KEY_ESC || res == -ERRDISPLAYTOOSMALL) - break; - if (item_count() != 0) { - if (!item_activate_selected()) - continue; - if (!item_tag()) - continue; - } - submenu = item_data(); - active_menu = item_data(); - if (submenu) - sym = submenu->sym; - else - sym = NULL; - - switch (res) { - case 0: - switch (item_tag()) { - case 'm': - if (single_menu_mode) - submenu->data = (void *) (long) !submenu->data; - else - conf(submenu, NULL); - break; - case 't': - if (sym_is_choice(sym) && sym_get_tristate_value(sym) == yes) - conf_choice(submenu); - else if (submenu->prompt->type == P_MENU) - conf(submenu, NULL); - break; - case 's': - conf_string(submenu); - break; - } - break; - case 2: - if (sym) - show_help(submenu); - else { - reset_subtitle(); - show_helptext("README", mconf_readme); - } - break; - case 3: - reset_subtitle(); - conf_save(); - break; - case 4: - reset_subtitle(); - conf_load(); - break; - case 5: - if (item_is_tag('t')) { - if (sym_set_tristate_value(sym, yes)) - break; - if (sym_set_tristate_value(sym, mod)) - show_textbox(NULL, setmod_text, 6, 74); - } - break; - case 6: - if (item_is_tag('t')) - sym_set_tristate_value(sym, no); - break; - case 7: - if (item_is_tag('t')) - sym_set_tristate_value(sym, mod); - break; - case 8: - if (item_is_tag('t')) - sym_toggle_tristate_value(sym); - else if (item_is_tag('m')) - conf(submenu, NULL); - break; - case 9: - search_conf(); - break; - case 10: - show_all_options = !show_all_options; - break; - } - } - - list_del(trail.prev); -} - -static int show_textbox_ext(const char *title, char *text, int r, int c, int - *keys, int *vscroll, int *hscroll, update_text_fn - update_text, void *data) -{ - dialog_clear(); - return dialog_textbox(title, text, r, c, keys, vscroll, hscroll, - update_text, data); -} - -static void show_textbox(const char *title, const char *text, int r, int c) -{ - show_textbox_ext(title, (char *) text, r, c, (int []) {0}, NULL, NULL, - NULL, NULL); -} - -static void show_helptext(const char *title, const char *text) -{ - show_textbox(title, text, 0, 0); -} - -static void conf_message_callback(const char *s) -{ - if (save_and_exit) { - if (!silent) - printf("%s", s); - } else { - show_textbox(NULL, s, 6, 60); - } -} - -static void show_help(struct menu *menu) -{ - struct gstr help = str_new(); - - help.max_width = getmaxx(stdscr) - 10; - menu_get_ext_help(menu, &help); - - show_helptext(menu_get_prompt(menu), str_get(&help)); - str_free(&help); -} - static void conf_choice(struct menu *menu) { const char *prompt = menu_get_prompt(menu); @@ -950,6 +819,127 @@ static void conf_save(void) } } +static void conf(struct menu *menu, struct menu *active_menu) +{ + struct menu *submenu; + const char *prompt = menu_get_prompt(menu); + struct subtitle_part stpart; + struct symbol *sym; + int res; + int s_scroll = 0; + + if (menu != &rootmenu) + stpart.text = menu_get_prompt(menu); + else + stpart.text = NULL; + list_add_tail(&stpart.entries, &trail); + + while (1) { + item_reset(); + current_menu = menu; + build_conf(menu); + if (!child_count) + break; + set_subtitle(); + dialog_clear(); + res = dialog_menu(prompt ? prompt : "Main Menu", + menu_instructions, + active_menu, &s_scroll); + if (res == 1 || res == KEY_ESC || res == -ERRDISPLAYTOOSMALL) + break; + if (item_count() != 0) { + if (!item_activate_selected()) + continue; + if (!item_tag()) + continue; + } + submenu = item_data(); + active_menu = item_data(); + if (submenu) + sym = submenu->sym; + else + sym = NULL; + + switch (res) { + case 0: + switch (item_tag()) { + case 'm': + if (single_menu_mode) + submenu->data = (void *) (long) !submenu->data; + else + conf(submenu, NULL); + break; + case 't': + if (sym_is_choice(sym) && sym_get_tristate_value(sym) == yes) + conf_choice(submenu); + else if (submenu->prompt->type == P_MENU) + conf(submenu, NULL); + break; + case 's': + conf_string(submenu); + break; + } + break; + case 2: + if (sym) + show_help(submenu); + else { + reset_subtitle(); + show_helptext("README", mconf_readme); + } + break; + case 3: + reset_subtitle(); + conf_save(); + break; + case 4: + reset_subtitle(); + conf_load(); + break; + case 5: + if (item_is_tag('t')) { + if (sym_set_tristate_value(sym, yes)) + break; + if (sym_set_tristate_value(sym, mod)) + show_textbox(NULL, setmod_text, 6, 74); + } + break; + case 6: + if (item_is_tag('t')) + sym_set_tristate_value(sym, no); + break; + case 7: + if (item_is_tag('t')) + sym_set_tristate_value(sym, mod); + break; + case 8: + if (item_is_tag('t')) + sym_toggle_tristate_value(sym); + else if (item_is_tag('m')) + conf(submenu, NULL); + break; + case 9: + search_conf(); + break; + case 10: + show_all_options = !show_all_options; + break; + } + } + + list_del(trail.prev); +} + +static void conf_message_callback(const char *s) +{ + if (save_and_exit) { + if (!silent) + printf("%s", s); + } else { + show_textbox(NULL, s, 6, 60); + } +} + static int handle_exit(void) { int res; -- GitLab From ddc72c9659b5a85a2d135503caf193da0723e813 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 2 Apr 2023 02:01:17 +0900 Subject: [PATCH 3116/5631] kbuild: clang: do not use CROSS_COMPILE for target triple The target triple is overridden by the user-supplied CROSS_COMPILE, but I do not see a good reason to support it. Users can use a new architecture without adding CLANG_TARGET_FLAGS_*, but that would be a rare case. Use the hard-coded and deterministic target triple all the time. Signed-off-by: Masahiro Yamada Acked-by: Nathan Chancellor Reviewed-by: Nick Desaulniers --- scripts/Makefile.clang | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/scripts/Makefile.clang b/scripts/Makefile.clang index 70b354fa1cb4..9076cc939e87 100644 --- a/scripts/Makefile.clang +++ b/scripts/Makefile.clang @@ -13,15 +13,11 @@ CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu CLANG_TARGET_FLAGS_um := $(CLANG_TARGET_FLAGS_$(SUBARCH)) CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(SRCARCH)) -ifeq ($(CROSS_COMPILE),) ifeq ($(CLANG_TARGET_FLAGS),) -$(error Specify CROSS_COMPILE or add '--target=' option to scripts/Makefile.clang) +$(error add '--target=' option to scripts/Makefile.clang) else CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS) -endif # CLANG_TARGET_FLAGS -else -CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) -endif # CROSS_COMPILE +endif ifeq ($(LLVM_IAS),0) CLANG_FLAGS += -fno-integrated-as -- GitLab From ccb2d173b983984bfa35398abed3f8a76c75f788 Mon Sep 17 00:00:00 2001 From: Fangrui Song Date: Tue, 11 Apr 2023 20:09:44 +0000 Subject: [PATCH 3117/5631] Makefile: use -z pack-relative-relocs Commit 27f2a4db76e8 ("Makefile: fix GDB warning with CONFIG_RELR") added --use-android-relr-tags to fix a GDB warning BFD: /android0/linux-next/vmlinux: unknown type [0x13] section `.relr.dyn' The GDB warning has been fixed in version 11.2. The DT_ANDROID_RELR tag was deprecated since DT_RELR was standardized. Thus, --use-android-relr-tags should be removed. While making the change, try -z pack-relative-relocs, which is supported since LLD 15. Keep supporting --pack-dyn-relocs=relr as well for older LLD versions. There is no indication of obsolescence for --pack-dyn-relocs=relr. As of today, GNU ld supports the latter option for x86 and powerpc64 ports and has no intention to support --pack-dyn-relocs=relr. In the absence of the glibc symbol version GLIBC_ABI_DT_RELR, --pack-dyn-relocs=relr and -z pack-relative-relocs are identical in ld.lld. GNU ld and newer versions of LLD report warnings (instead of errors) for unknown -z options. Only errors lead to non-zero exit codes. Therefore, we should test --pack-dyn-relocs=relr before testing -z pack-relative-relocs. Link: https://github.com/ClangBuiltLinux/linux/issues/1057 Link: https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=a619b58721f0a03fd91c27670d3e4c2fb0d88f1e Signed-off-by: Fangrui Song Reviewed-by: Nick Desaulniers Acked-by: Will Deacon Signed-off-by: Masahiro Yamada --- Makefile | 3 ++- scripts/tools-support-relr.sh | 8 ++++++-- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index b5c48e3c935a..3c0ec6dbcfd1 100644 --- a/Makefile +++ b/Makefile @@ -1113,7 +1113,8 @@ LDFLAGS_vmlinux += -X endif ifeq ($(CONFIG_RELR),y) -LDFLAGS_vmlinux += --pack-dyn-relocs=relr --use-android-relr-tags +# ld.lld before 15 did not support -z pack-relative-relocs. +LDFLAGS_vmlinux += $(call ld-option,--pack-dyn-relocs=relr,-z pack-relative-relocs) endif # We never want expected sections to be placed heuristically by the diff --git a/scripts/tools-support-relr.sh b/scripts/tools-support-relr.sh index cb55878bd5b8..4c121946e517 100755 --- a/scripts/tools-support-relr.sh +++ b/scripts/tools-support-relr.sh @@ -7,8 +7,12 @@ trap "rm -f $tmp_file.o $tmp_file $tmp_file.bin" EXIT cat << "END" | $CC -c -x c - -o $tmp_file.o >/dev/null 2>&1 void *p = &p; END -$LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr \ - --use-android-relr-tags -o $tmp_file + +# ld.lld before 15 did not support -z pack-relative-relocs. +if ! $LD $tmp_file.o -shared -Bsymbolic --pack-dyn-relocs=relr -o $tmp_file 2>/dev/null; then + $LD $tmp_file.o -shared -Bsymbolic -z pack-relative-relocs -o $tmp_file 2>&1 | + grep -q pack-relative-relocs && exit 1 +fi # Despite printing an error message, GNU nm still exits with exit code 0 if it # sees a relr section. So we need to check that nothing is printed to stderr. -- GitLab From 4121234a32887a49d5da06e4c219f67abb6e744f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 12:47:49 -0300 Subject: [PATCH 3118/5631] libperf: Add perf_cpu_map__refcnt() interanl accessor to use in the maps test To remove one more direct access to 'struct perf_cpu_map' so that we can intercept accesses to its instantiations and refcount check it to catch use after free, etc. Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/ZD1qdYjG+DL6KOfP@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/cpumap.c | 6 +++--- tools/lib/perf/include/internal/cpumap.h | 4 ++++ tools/perf/tests/cpumap.c | 4 ++-- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 6bbcbb83eb14..27c3e73c6db2 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -40,7 +40,7 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void) static void cpu_map__delete(struct perf_cpu_map *map) { if (map) { - WARN_ONCE(refcount_read(&map->refcnt) != 0, + WARN_ONCE(refcount_read(perf_cpu_map__refcnt(map)) != 0, "cpu_map refcnt unbalanced\n"); free(map); } @@ -49,13 +49,13 @@ static void cpu_map__delete(struct perf_cpu_map *map) struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map) { if (map) - refcount_inc(&map->refcnt); + refcount_inc(perf_cpu_map__refcnt(map)); return map; } void perf_cpu_map__put(struct perf_cpu_map *map) { - if (map && refcount_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(perf_cpu_map__refcnt(map))) cpu_map__delete(map); } diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index b82fd6607a00..1e840dd53a11 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -30,4 +30,8 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus); +static inline refcount_t *perf_cpu_map__refcnt(struct perf_cpu_map *map) +{ + return &map->refcnt; +} #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c index 3150fc1fed6f..b1a924314e09 100644 --- a/tools/perf/tests/cpumap.c +++ b/tools/perf/tests/cpumap.c @@ -68,7 +68,7 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", perf_cpu_map__nr(map) == 2); TEST_ASSERT_VAL("wrong cpu", perf_cpu_map__cpu(map, 0).cpu == 1); TEST_ASSERT_VAL("wrong cpu", perf_cpu_map__cpu(map, 1).cpu == 256); - TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); + TEST_ASSERT_VAL("wrong refcnt", refcount_read(perf_cpu_map__refcnt(map)) == 1); perf_cpu_map__put(map); return 0; } @@ -94,7 +94,7 @@ static int process_event_range_cpus(struct perf_tool *tool __maybe_unused, TEST_ASSERT_VAL("wrong nr", perf_cpu_map__nr(map) == 256); TEST_ASSERT_VAL("wrong cpu", perf_cpu_map__cpu(map, 0).cpu == 1); TEST_ASSERT_VAL("wrong cpu", perf_cpu_map__max(map).cpu == 256); - TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1); + TEST_ASSERT_VAL("wrong refcnt", refcount_read(perf_cpu_map__refcnt(map)) == 1); perf_cpu_map__put(map); return 0; } -- GitLab From a9b867f68e89a54fcac334b77e6d243e872573c9 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 7 Apr 2023 16:04:01 -0700 Subject: [PATCH 3119/5631] libperf: Add reference count checking macros The macros serve as a way to debug use of a reference counted struct. The macros add a memory allocated pointer that is interposed between the reference counted original struct at a get and freed by a put. The pointer replaces the original struct, so use of the struct name via APIs remains unchanged. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephane Eranian Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter Cc: Yury Norov Link: http://lore.kernel.org/lkml/20230407230405.2931830-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/include/internal/rc_check.h | 94 ++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 tools/lib/perf/include/internal/rc_check.h diff --git a/tools/lib/perf/include/internal/rc_check.h b/tools/lib/perf/include/internal/rc_check.h new file mode 100644 index 000000000000..c0626d8beb59 --- /dev/null +++ b/tools/lib/perf/include/internal/rc_check.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __LIBPERF_INTERNAL_RC_CHECK_H +#define __LIBPERF_INTERNAL_RC_CHECK_H + +#include +#include + +/* + * Shared reference count checking macros. + * + * Reference count checking is an approach to sanitizing the use of reference + * counted structs. It leverages address and leak sanitizers to make sure gets + * are paired with a put. Reference count checking adds a malloc-ed layer of + * indirection on a get, and frees it on a put. A missed put will be reported as + * a memory leak. A double put will be reported as a double free. Accessing + * after a put will cause a use-after-free and/or a segfault. + */ + +#ifndef REFCNT_CHECKING +/* Replaces "struct foo" so that the pointer may be interposed. */ +#define DECLARE_RC_STRUCT(struct_name) \ + struct struct_name + +/* Declare a reference counted struct variable. */ +#define RC_STRUCT(struct_name) struct struct_name + +/* + * Interpose the indirection. Result will hold the indirection and object is the + * reference counted struct. + */ +#define ADD_RC_CHK(result, object) (result = object, object) + +/* Strip the indirection layer. */ +#define RC_CHK_ACCESS(object) object + +/* Frees the object and the indirection layer. */ +#define RC_CHK_FREE(object) free(object) + +/* A get operation adding the indirection layer. */ +#define RC_CHK_GET(result, object) ADD_RC_CHK(result, object) + +/* A put operation removing the indirection layer. */ +#define RC_CHK_PUT(object) {} + +#else + +/* Replaces "struct foo" so that the pointer may be interposed. */ +#define DECLARE_RC_STRUCT(struct_name) \ + struct original_##struct_name; \ + struct struct_name { \ + struct original_##struct_name *orig; \ + }; \ + struct original_##struct_name + +/* Declare a reference counted struct variable. */ +#define RC_STRUCT(struct_name) struct original_##struct_name + +/* + * Interpose the indirection. Result will hold the indirection and object is the + * reference counted struct. + */ +#define ADD_RC_CHK(result, object) \ + ( \ + object ? (result = malloc(sizeof(*result)), \ + result ? (result->orig = object, result) \ + : (result = NULL, NULL)) \ + : (result = NULL, NULL) \ + ) + +/* Strip the indirection layer. */ +#define RC_CHK_ACCESS(object) object->orig + +/* Frees the object and the indirection layer. */ +#define RC_CHK_FREE(object) \ + do { \ + zfree(&object->orig); \ + free(object); \ + } while(0) + +/* A get operation adding the indirection layer. */ +#define RC_CHK_GET(result, object) ADD_RC_CHK(result, (object ? object->orig : NULL)) + +/* A put operation removing the indirection layer. */ +#define RC_CHK_PUT(object) \ + do { \ + if (object) { \ + object->orig = NULL; \ + free(object); \ + } \ + } while(0) + +#endif + +#endif /* __LIBPERF_INTERNAL_RC_CHECK_H */ -- GitLab From a588429a66e92960b195b8dceb3fc5477a2b2f80 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Tue, 4 Apr 2023 23:26:07 -0500 Subject: [PATCH 3120/5631] RDMA/rxe: Remove qp->resp.state The rxe driver has four different QP state variables, qp->attr.qp_state, qp->req.state, qp->comp.state, and qp->resp.state. All of these basically carry the same information. This patch replaces uses of qp->resp.state by qp->attr.qp_state. This is the first of three patches which will remove all but the qp->attr.qp_state variable. This will bring the driver closer to the IBA description. Link: https://lore.kernel.org/r/20230405042611.6467-1-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_net.c | 2 +- drivers/infiniband/sw/rxe/rxe_qp.c | 5 ----- drivers/infiniband/sw/rxe/rxe_recv.c | 2 +- drivers/infiniband/sw/rxe/rxe_resp.c | 10 +++++----- drivers/infiniband/sw/rxe/rxe_verbs.c | 2 +- drivers/infiniband/sw/rxe/rxe_verbs.h | 1 - 6 files changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index a2ace42e9536..2be2425083ce 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -414,7 +414,7 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, struct rxe_dev *rxe = to_rdev(qp->ibqp.device); if ((is_request && (qp->req.state != QP_STATE_READY)) || - (!is_request && (qp->resp.state != QP_STATE_READY))) { + (!is_request && (qp_state(qp) <= IB_QPS_RTR))) { rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index d5de5ba6940f..fcbcca39876b 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -287,7 +287,6 @@ static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, qp->resp.opcode = OPCODE_NONE; qp->resp.msn = 0; - qp->resp.state = QP_STATE_RESET; return 0; } @@ -479,7 +478,6 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move qp to the reset state */ qp->req.state = QP_STATE_RESET; qp->comp.state = QP_STATE_RESET; - qp->resp.state = QP_STATE_RESET; /* drain work and packet queuesc */ rxe_requester(qp); @@ -532,7 +530,6 @@ static void rxe_qp_drain(struct rxe_qp *qp) void rxe_qp_error(struct rxe_qp *qp) { qp->req.state = QP_STATE_ERROR; - qp->resp.state = QP_STATE_ERROR; qp->comp.state = QP_STATE_ERROR; qp->attr.qp_state = IB_QPS_ERR; @@ -663,13 +660,11 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, case IB_QPS_INIT: rxe_dbg_qp(qp, "state -> INIT\n"); qp->req.state = QP_STATE_INIT; - qp->resp.state = QP_STATE_INIT; qp->comp.state = QP_STATE_INIT; break; case IB_QPS_RTR: rxe_dbg_qp(qp, "state -> RTR\n"); - qp->resp.state = QP_STATE_READY; break; case IB_QPS_RTS: diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 434a693cd4a5..ac42ceccf71f 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -39,7 +39,7 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, } if (pkt->mask & RXE_REQ_MASK) { - if (unlikely(qp->resp.state != QP_STATE_READY)) + if (unlikely(qp_state(qp) <= IB_QPS_RTR)) return -EINVAL; } else if (unlikely(qp->req.state < QP_STATE_READY || qp->req.state > QP_STATE_DRAINED)) diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 01e3cbea8445..67eac616235c 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1137,7 +1137,7 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - if (unlikely(qp->resp.state == QP_STATE_ERROR)) + if (unlikely(qp_state(qp) == IB_QPS_ERR)) return RESPST_CHK_RESOURCE; if (unlikely(!pkt)) return RESPST_DONE; @@ -1464,10 +1464,10 @@ int rxe_responder(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; int ret; - if (!qp->valid || qp->resp.state == QP_STATE_ERROR || - qp->resp.state == QP_STATE_RESET) { - bool notify = qp->valid && - (qp->resp.state == QP_STATE_ERROR); + if (!qp->valid || qp_state(qp) == IB_QPS_ERR || + qp_state(qp) == IB_QPS_RESET) { + bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); + drain_req_pkts(qp); flush_recv_queue(qp, notify); goto exit; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 12819153bda7..36cad3665ee4 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -1012,7 +1012,7 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); - if (qp->resp.state == QP_STATE_ERROR) + if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); err_out: diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index d812093a3916..12594cb2a9cf 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -173,7 +173,6 @@ struct resp_res { }; struct rxe_resp_info { - enum rxe_qp_state state; u32 msn; u32 psn; u32 ack_psn; -- GitLab From f55efc2ed206eedfed08e1c8f8552f64fc3a11dd Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Tue, 4 Apr 2023 23:26:08 -0500 Subject: [PATCH 3121/5631] RDMA/rxe: Remove qp->comp.state The rxe driver has four different QP state variables, qp->attr.qp_state, qp->req.state, qp->comp.state, and qp->resp.state. All of these basically carry the same information. This patch replaces uses of qp->comp.state by qp->attr.qp_state. This is the second of three patches which will remove all but the qp->attr.qp_state variable. This will bring the driver closer to the IBA description. Link: https://lore.kernel.org/r/20230405042611.6467-2-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 8 ++++---- drivers/infiniband/sw/rxe/rxe_qp.c | 5 ----- drivers/infiniband/sw/rxe/rxe_verbs.h | 1 - 3 files changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 2c70cdcd55dc..173ebfe784e6 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -619,10 +619,10 @@ int rxe_completer(struct rxe_qp *qp) enum comp_state state; int ret; - if (!qp->valid || qp->comp.state == QP_STATE_ERROR || - qp->comp.state == QP_STATE_RESET) { - bool notify = qp->valid && - (qp->comp.state == QP_STATE_ERROR); + if (!qp->valid || qp_state(qp) == IB_QPS_ERR || + qp_state(qp) == IB_QPS_RESET) { + bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); + drain_resp_pkts(qp); flush_send_queue(qp, notify); goto exit; diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index fcbcca39876b..36e4a00e5d12 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -232,7 +232,6 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, QUEUE_TYPE_FROM_CLIENT); qp->req.state = QP_STATE_RESET; - qp->comp.state = QP_STATE_RESET; qp->req.opcode = -1; qp->comp.opcode = -1; @@ -477,7 +476,6 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move qp to the reset state */ qp->req.state = QP_STATE_RESET; - qp->comp.state = QP_STATE_RESET; /* drain work and packet queuesc */ rxe_requester(qp); @@ -530,7 +528,6 @@ static void rxe_qp_drain(struct rxe_qp *qp) void rxe_qp_error(struct rxe_qp *qp) { qp->req.state = QP_STATE_ERROR; - qp->comp.state = QP_STATE_ERROR; qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ @@ -660,7 +657,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, case IB_QPS_INIT: rxe_dbg_qp(qp, "state -> INIT\n"); qp->req.state = QP_STATE_INIT; - qp->comp.state = QP_STATE_INIT; break; case IB_QPS_RTR: @@ -670,7 +666,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, case IB_QPS_RTS: rxe_dbg_qp(qp, "state -> RTS\n"); qp->req.state = QP_STATE_READY; - qp->comp.state = QP_STATE_READY; break; case IB_QPS_SQD: diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 12594cb2a9cf..1ae8dfd0ce7b 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -127,7 +127,6 @@ struct rxe_req_info { }; struct rxe_comp_info { - enum rxe_qp_state state; u32 psn; int opcode; int timeout; -- GitLab From 98e891b5e4d94ceb0844de3355c9218027426e72 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Tue, 4 Apr 2023 23:26:09 -0500 Subject: [PATCH 3122/5631] RDMA/rxe: Remove qp->req.state The rxe driver has four different QP state variables, qp->attr.qp_state, qp->req.state, qp->comp.state, and qp->resp.state. All of these basically carry the same information. This patch replaces uses of qp->req.state by qp->attr.qp_state and enum rxe_qp_state. This is the third of three patches which will remove all but the qp->attr.qp_state variable. This will bring the driver closer to the IBA description. Link: https://lore.kernel.org/r/20230405042611.6467-3-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 9 +++-- drivers/infiniband/sw/rxe/rxe_net.c | 4 +-- drivers/infiniband/sw/rxe/rxe_qp.c | 49 ++++++++------------------- drivers/infiniband/sw/rxe/rxe_recv.c | 9 ++--- drivers/infiniband/sw/rxe/rxe_req.c | 15 ++++---- drivers/infiniband/sw/rxe/rxe_verbs.c | 4 +-- drivers/infiniband/sw/rxe/rxe_verbs.h | 10 ------ 7 files changed, 34 insertions(+), 66 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 173ebfe784e6..979990734e0c 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -491,12 +491,11 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp, } } - if (unlikely(qp->req.state == QP_STATE_DRAIN)) { + if (unlikely(qp_state(qp) == IB_QPS_SQD)) { /* state_lock used by requester & completer */ spin_lock_bh(&qp->state_lock); - if ((qp->req.state == QP_STATE_DRAIN) && - (qp->comp.psn == qp->req.psn)) { - qp->req.state = QP_STATE_DRAINED; + if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { + qp->attr.sq_draining = 0; spin_unlock_bh(&qp->state_lock); if (qp->ibqp.event_handler) { @@ -723,7 +722,7 @@ int rxe_completer(struct rxe_qp *qp) * (4) the timeout parameter is set */ if ((qp_type(qp) == IB_QPT_RC) && - (qp->req.state == QP_STATE_READY) && + (qp_state(qp) >= IB_QPS_RTS) && (psn_compare(qp->req.psn, qp->comp.psn) > 0) && qp->qp_timeout_jiffies) mod_timer(&qp->retrans_timer, diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 2be2425083ce..9ed81d0bd25c 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -413,8 +413,8 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); - if ((is_request && (qp->req.state != QP_STATE_READY)) || - (!is_request && (qp_state(qp) <= IB_QPS_RTR))) { + if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || + (!is_request && (qp_state(qp) < IB_QPS_RTR))) { rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 36e4a00e5d12..78c7c13e614b 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -231,7 +231,6 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, qp->req.wqe_index = queue_get_producer(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT); - qp->req.state = QP_STATE_RESET; qp->req.opcode = -1; qp->comp.opcode = -1; @@ -394,12 +393,9 @@ int rxe_qp_chk_attr(struct rxe_dev *rxe, struct rxe_qp *qp, goto err1; } - if (mask & IB_QP_STATE) { - if (cur_state == IB_QPS_SQD) { - if (qp->req.state == QP_STATE_DRAIN && - new_state != IB_QPS_ERR) - goto err1; - } + if (mask & IB_QP_STATE && cur_state == IB_QPS_SQD) { + if (qp->attr.sq_draining && new_state != IB_QPS_ERR) + goto err1; } if (mask & IB_QP_PORT) { @@ -474,9 +470,6 @@ static void rxe_qp_reset(struct rxe_qp *qp) rxe_disable_task(&qp->comp.task); rxe_disable_task(&qp->req.task); - /* move qp to the reset state */ - qp->req.state = QP_STATE_RESET; - /* drain work and packet queuesc */ rxe_requester(qp); rxe_completer(qp); @@ -512,22 +505,9 @@ static void rxe_qp_reset(struct rxe_qp *qp) rxe_enable_task(&qp->req.task); } -/* drain the send queue */ -static void rxe_qp_drain(struct rxe_qp *qp) -{ - if (qp->sq.queue) { - if (qp->req.state != QP_STATE_DRAINED) { - qp->req.state = QP_STATE_DRAIN; - rxe_sched_task(&qp->comp.task); - rxe_sched_task(&qp->req.task); - } - } -} - /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { - qp->req.state = QP_STATE_ERROR; qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ @@ -540,6 +520,8 @@ void rxe_qp_error(struct rxe_qp *qp) int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, struct ib_udata *udata) { + enum ib_qp_state cur_state = (mask & IB_QP_CUR_STATE) ? + attr->cur_qp_state : qp->attr.qp_state; int err; if (mask & IB_QP_MAX_QP_RD_ATOMIC) { @@ -656,7 +638,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, case IB_QPS_INIT: rxe_dbg_qp(qp, "state -> INIT\n"); - qp->req.state = QP_STATE_INIT; break; case IB_QPS_RTR: @@ -665,12 +646,15 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, case IB_QPS_RTS: rxe_dbg_qp(qp, "state -> RTS\n"); - qp->req.state = QP_STATE_READY; break; case IB_QPS_SQD: rxe_dbg_qp(qp, "state -> SQD\n"); - rxe_qp_drain(qp); + if (cur_state != IB_QPS_SQD) { + qp->attr.sq_draining = 1; + rxe_sched_task(&qp->comp.task); + rxe_sched_task(&qp->req.task); + } break; case IB_QPS_SQE: @@ -708,16 +692,11 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) rxe_av_to_attr(&qp->pri_av, &attr->ah_attr); rxe_av_to_attr(&qp->alt_av, &attr->alt_ah_attr); - if (qp->req.state == QP_STATE_DRAIN) { - attr->sq_draining = 1; - /* applications that get this state - * typically spin on it. yield the - * processor - */ + /* Applications that get this state typically spin on it. + * Yield the processor + */ + if (qp->attr.sq_draining) cond_resched(); - } else { - attr->sq_draining = 0; - } rxe_dbg_qp(qp, "attr->sq_draining = %d\n", attr->sq_draining); diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index ac42ceccf71f..ca17ac6c5878 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -39,11 +39,12 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, } if (pkt->mask & RXE_REQ_MASK) { - if (unlikely(qp_state(qp) <= IB_QPS_RTR)) + if (unlikely(qp_state(qp) < IB_QPS_RTR)) return -EINVAL; - } else if (unlikely(qp->req.state < QP_STATE_READY || - qp->req.state > QP_STATE_DRAINED)) - return -EINVAL; + } else { + if (unlikely(qp_state(qp) < IB_QPS_RTS)) + return -EINVAL; + } return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 745731140a54..8a8242512f2a 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -120,13 +120,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT); - if (unlikely(qp->req.state == QP_STATE_DRAIN)) { + if (unlikely(qp_state(qp) == IB_QPS_SQD)) { /* check to see if we are drained; * state_lock used by requester and completer */ spin_lock_bh(&qp->state_lock); do { - if (qp->req.state != QP_STATE_DRAIN) { + if (!qp->attr.sq_draining) { /* comp just finished */ spin_unlock_bh(&qp->state_lock); break; @@ -139,7 +139,7 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) break; } - qp->req.state = QP_STATE_DRAINED; + qp->attr.sq_draining = 0; spin_unlock_bh(&qp->state_lock); if (qp->ibqp.event_handler) { @@ -159,8 +159,7 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) wqe = queue_addr_from_index(q, index); - if (unlikely((qp->req.state == QP_STATE_DRAIN || - qp->req.state == QP_STATE_DRAINED) && + if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) return NULL; @@ -656,7 +655,7 @@ int rxe_requester(struct rxe_qp *qp) if (unlikely(!qp->valid)) goto exit; - if (unlikely(qp->req.state == QP_STATE_ERROR)) { + if (unlikely(qp_state(qp) == IB_QPS_ERR)) { wqe = req_next_wqe(qp); if (wqe) /* @@ -667,7 +666,7 @@ int rxe_requester(struct rxe_qp *qp) goto exit; } - if (unlikely(qp->req.state == QP_STATE_RESET)) { + if (unlikely(qp_state(qp) == IB_QPS_RESET)) { qp->req.wqe_index = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); qp->req.opcode = -1; @@ -836,7 +835,7 @@ int rxe_requester(struct rxe_qp *qp) /* update wqe_index for each wqe completion */ qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); wqe->state = wqe_state_error; - qp->req.state = QP_STATE_ERROR; + qp->attr.qp_state = IB_QPS_ERR; rxe_sched_task(&qp->comp.task); exit: ret = -EAGAIN; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 36cad3665ee4..6d97c7093ae6 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -881,7 +881,7 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, if (!err) rxe_sched_task(&qp->req.task); - if (unlikely(qp->req.state == QP_STATE_ERROR)) + if (unlikely(qp_state(qp) == IB_QPS_ERR)) rxe_sched_task(&qp->comp.task); return err; @@ -900,7 +900,7 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, goto err_out; } - if (unlikely(qp->req.state < QP_STATE_READY)) { + if (unlikely(qp_state(qp) < IB_QPS_RTS)) { *bad_wr = wr; err = -EINVAL; rxe_dbg_qp(qp, "qp not ready to send"); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 1ae8dfd0ce7b..26a20f088692 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -102,17 +102,7 @@ struct rxe_srq { int error; }; -enum rxe_qp_state { - QP_STATE_RESET, - QP_STATE_INIT, - QP_STATE_READY, - QP_STATE_DRAIN, /* req only */ - QP_STATE_DRAINED, /* req only */ - QP_STATE_ERROR -}; - struct rxe_req_info { - enum rxe_qp_state state; int wqe_index; u32 psn; int opcode; -- GitLab From 7b560b89a08d35c23dfc95dc44aee10651c8b9a0 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Tue, 4 Apr 2023 23:26:10 -0500 Subject: [PATCH 3123/5631] RDMA/rxe: Move code to check if drained to subroutine Move two blocks of code in rxe_comp.c and rxe_req.c to subroutines that check if draining is complete in the SQD state and, if so, generate a SQ_DRAINED event. Link: https://lore.kernel.org/r/20230405042611.6467-4-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 35 ++++++++++++++++------------ drivers/infiniband/sw/rxe/rxe_req.c | 32 ++++++++++++++----------- 2 files changed, 38 insertions(+), 29 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 979990734e0c..1ccae8cff359 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -477,20 +477,8 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) } } -static inline enum comp_state complete_ack(struct rxe_qp *qp, - struct rxe_pkt_info *pkt, - struct rxe_send_wqe *wqe) +static void comp_check_sq_drain_done(struct rxe_qp *qp) { - if (wqe->has_rd_atomic) { - wqe->has_rd_atomic = 0; - atomic_inc(&qp->req.rd_atomic); - if (qp->req.need_rd_atomic) { - qp->comp.timeout_retry = 0; - qp->req.need_rd_atomic = 0; - rxe_sched_task(&qp->req.task); - } - } - if (unlikely(qp_state(qp) == IB_QPS_SQD)) { /* state_lock used by requester & completer */ spin_lock_bh(&qp->state_lock); @@ -507,10 +495,27 @@ static inline enum comp_state complete_ack(struct rxe_qp *qp, qp->ibqp.event_handler(&ev, qp->ibqp.qp_context); } - } else { - spin_unlock_bh(&qp->state_lock); + return; } + spin_unlock_bh(&qp->state_lock); } +} + +static inline enum comp_state complete_ack(struct rxe_qp *qp, + struct rxe_pkt_info *pkt, + struct rxe_send_wqe *wqe) +{ + if (wqe->has_rd_atomic) { + wqe->has_rd_atomic = 0; + atomic_inc(&qp->req.rd_atomic); + if (qp->req.need_rd_atomic) { + qp->comp.timeout_retry = 0; + qp->req.need_rd_atomic = 0; + rxe_sched_task(&qp->req.task); + } + } + + comp_check_sq_drain_done(qp); do_complete(qp, wqe); diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 8a8242512f2a..f329038efbc8 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -108,17 +108,12 @@ void rnr_nak_timer(struct timer_list *t) rxe_sched_task(&qp->req.task); } -static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) +static void req_check_sq_drain_done(struct rxe_qp *qp) { - struct rxe_send_wqe *wqe; struct rxe_queue *q = qp->sq.queue; unsigned int index = qp->req.wqe_index; - unsigned int cons; - unsigned int prod; - - wqe = queue_head(q, QUEUE_TYPE_FROM_CLIENT); - cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); - prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT); + unsigned int cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); + struct rxe_send_wqe *wqe = queue_addr_from_index(q, cons); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { /* check to see if we are drained; @@ -126,18 +121,14 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) */ spin_lock_bh(&qp->state_lock); do { - if (!qp->attr.sq_draining) { + if (!qp->attr.sq_draining) /* comp just finished */ - spin_unlock_bh(&qp->state_lock); break; - } if (wqe && ((index != cons) || - (wqe->state != wqe_state_posted))) { + (wqe->state != wqe_state_posted))) /* comp not done yet */ - spin_unlock_bh(&qp->state_lock); break; - } qp->attr.sq_draining = 0; spin_unlock_bh(&qp->state_lock); @@ -151,9 +142,22 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) qp->ibqp.event_handler(&ev, qp->ibqp.qp_context); } + return; } while (0); + spin_unlock_bh(&qp->state_lock); } +} +static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) +{ + struct rxe_send_wqe *wqe; + struct rxe_queue *q = qp->sq.queue; + unsigned int index = qp->req.wqe_index; + unsigned int prod; + + req_check_sq_drain_done(qp); + + prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT); if (index == prod) return NULL; -- GitLab From a4fea9b78ebea6df9a61f34cfc2f7ed0bbc8a9fc Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:36 -0700 Subject: [PATCH 3124/5631] drivers/clocksource/hyper-v: non ACPI support in hyperv clock Add a placeholder function for the hv_setup_stimer0_irq API to accommodate systems without ACPI support. Since this function is not utilized on x86/x64 systems and non-ACPI support is only intended for x86/x64 systems, a placeholder function is sufficient for now and can be improved upon if necessary in the future. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1679298460-11855-2-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- drivers/clocksource/hyperv_timer.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index c0cef92b12b8..f32948c8a96f 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -49,7 +49,7 @@ static bool direct_mode_enabled; static int stimer0_irq = -1; static int stimer0_message_sint; -static DEFINE_PER_CPU(long, stimer0_evt); +static __maybe_unused DEFINE_PER_CPU(long, stimer0_evt); /* * Common code for stimer0 interrupts coming via Direct Mode or @@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(hv_stimer0_isr); * stimer0 interrupt handler for architectures that support * per-cpu interrupts, which also implies Direct Mode. */ -static irqreturn_t hv_stimer0_percpu_isr(int irq, void *dev_id) +static irqreturn_t __maybe_unused hv_stimer0_percpu_isr(int irq, void *dev_id) { hv_stimer0_isr(); return IRQ_HANDLED; @@ -196,6 +196,7 @@ void __weak hv_remove_stimer0_handler(void) { }; +#ifdef CONFIG_ACPI /* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */ static int hv_setup_stimer0_irq(void) { @@ -230,6 +231,16 @@ static void hv_remove_stimer0_irq(void) stimer0_irq = -1; } } +#else +static int hv_setup_stimer0_irq(void) +{ + return 0; +} + +static void hv_remove_stimer0_irq(void) +{ +} +#endif /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ int hv_stimer_alloc(bool have_percpu_irqs) -- GitLab From 1f6277bf716cc5ba0e3fa0c3e0af1adb4160fb5d Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:37 -0700 Subject: [PATCH 3125/5631] ACPI: bus: Add stub acpi_sleep_state_supported() in non-ACPI cases acpi_sleep_state_supported() is defined only when CONFIG_ACPI=y. The function is in acpi_bus.h, and acpi_bus.h can only be used in CONFIG_ACPI=y cases. Add the stub function to linux/acpi.h to make compilation successful for !CONFIG_ACPI cases. Signed-off-by: Saurabh Sengar Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/1679298460-11855-3-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- include/linux/acpi.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/acpi.h b/include/linux/acpi.h index efff750f326d..d331f76b0c19 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1075,6 +1075,11 @@ static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) return 0; } +static inline bool acpi_sleep_state_supported(u8 sleep_state) +{ + return false; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- GitLab From 9c8434238041e18d53fd6911826973b37656a8d1 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:38 -0700 Subject: [PATCH 3126/5631] Drivers: hv: vmbus: Convert acpi_device to more generic platform_device VMBus driver code currently has direct dependency on ACPI and struct acpi_device. As a staging step toward optionally configuring based on Devicetree instead of ACPI, use a more generic platform device to reduce the dependency on ACPI where possible, though the dependency on ACPI is not completely removed. Also rename the function vmbus_acpi_remove() to the more generic vmbus_mmio_remove(). Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1679298460-11855-4-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- drivers/hv/vmbus_drv.c | 58 +++++++++++++++++++++++++----------------- 1 file changed, 35 insertions(+), 23 deletions(-) diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index d24dd65b33d4..73497157a23a 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -44,7 +45,7 @@ struct vmbus_dynid { struct hv_vmbus_device_id id; }; -static struct acpi_device *hv_acpi_dev; +static struct device *hv_dev; static int hyperv_cpuhp_online; @@ -143,7 +144,7 @@ static DEFINE_MUTEX(hyperv_mmio_lock); static int vmbus_exists(void) { - if (hv_acpi_dev == NULL) + if (hv_dev == NULL) return -ENODEV; return 0; @@ -932,7 +933,7 @@ static int vmbus_dma_configure(struct device *child_device) * On x86/x64 coherence is assumed and these calls have no effect. */ hv_setup_dma_ops(child_device, - device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + device_get_dma_attr(hv_dev) == DEV_DMA_COHERENT); return 0; } @@ -2090,7 +2091,7 @@ int vmbus_device_register(struct hv_device *child_device_obj) &child_device_obj->channel->offermsg.offer.if_instance); child_device_obj->device.bus = &hv_bus; - child_device_obj->device.parent = &hv_acpi_dev->dev; + child_device_obj->device.parent = hv_dev; child_device_obj->device.release = vmbus_device_release; child_device_obj->device.dma_parms = &child_device_obj->dma_parms; @@ -2262,7 +2263,7 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) return AE_OK; } -static void vmbus_acpi_remove(struct acpi_device *device) +static void vmbus_mmio_remove(void) { struct resource *cur_res; struct resource *next_res; @@ -2441,13 +2442,14 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size) } EXPORT_SYMBOL_GPL(vmbus_free_mmio); -static int vmbus_acpi_add(struct acpi_device *device) +static int vmbus_acpi_add(struct platform_device *pdev) { acpi_status result; int ret_val = -ENODEV; struct acpi_device *ancestor; + struct acpi_device *device = ACPI_COMPANION(&pdev->dev); - hv_acpi_dev = device; + hv_dev = &device->dev; /* * Older versions of Hyper-V for ARM64 fail to include the _CCA @@ -2489,10 +2491,21 @@ static int vmbus_acpi_add(struct acpi_device *device) acpi_walk_err: if (ret_val) - vmbus_acpi_remove(device); + vmbus_mmio_remove(); return ret_val; } +static int vmbus_platform_driver_probe(struct platform_device *pdev) +{ + return vmbus_acpi_add(pdev); +} + +static int vmbus_platform_driver_remove(struct platform_device *pdev) +{ + vmbus_mmio_remove(); + return 0; +} + #ifdef CONFIG_PM_SLEEP static int vmbus_bus_suspend(struct device *dev) { @@ -2658,15 +2671,15 @@ static const struct dev_pm_ops vmbus_bus_pm = { .restore_noirq = vmbus_bus_resume }; -static struct acpi_driver vmbus_acpi_driver = { - .name = "vmbus", - .ids = vmbus_acpi_device_ids, - .ops = { - .add = vmbus_acpi_add, - .remove = vmbus_acpi_remove, - }, - .drv.pm = &vmbus_bus_pm, - .drv.probe_type = PROBE_FORCE_SYNCHRONOUS, +static struct platform_driver vmbus_platform_driver = { + .probe = vmbus_platform_driver_probe, + .remove = vmbus_platform_driver_remove, + .driver = { + .name = "vmbus", + .acpi_match_table = ACPI_PTR(vmbus_acpi_device_ids), + .pm = &vmbus_bus_pm, + .probe_type = PROBE_FORCE_SYNCHRONOUS, + } }; static void hv_kexec_handler(void) @@ -2750,12 +2763,11 @@ static int __init hv_acpi_init(void) /* * Get ACPI resources first. */ - ret = acpi_bus_register_driver(&vmbus_acpi_driver); - + ret = platform_driver_register(&vmbus_platform_driver); if (ret) return ret; - if (!hv_acpi_dev) { + if (!hv_dev) { ret = -ENODEV; goto cleanup; } @@ -2785,8 +2797,8 @@ static int __init hv_acpi_init(void) return 0; cleanup: - acpi_bus_unregister_driver(&vmbus_acpi_driver); - hv_acpi_dev = NULL; + platform_driver_unregister(&vmbus_platform_driver); + hv_dev = NULL; return ret; } @@ -2839,7 +2851,7 @@ static void __exit vmbus_exit(void) cpuhp_remove_state(hyperv_cpuhp_online); hv_synic_free(); - acpi_bus_unregister_driver(&vmbus_acpi_driver); + platform_driver_unregister(&vmbus_platform_driver); } -- GitLab From 61f7a325927e6f15de09aef96eea54801b227864 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:39 -0700 Subject: [PATCH 3127/5631] dt-bindings: bus: Add Hyper-V VMBus Add dt-bindings for Hyper-V VMBus. Signed-off-by: Saurabh Sengar Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/1679298460-11855-5-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- .../bindings/bus/microsoft,vmbus.yaml | 54 +++++++++++++++++++ MAINTAINERS | 1 + 2 files changed, 55 insertions(+) create mode 100644 Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml diff --git a/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml new file mode 100644 index 000000000000..a8d40c766dcd --- /dev/null +++ b/Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml @@ -0,0 +1,54 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/bus/microsoft,vmbus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microsoft Hyper-V VMBus + +maintainers: + - Saurabh Sengar + +description: + VMBus is a software bus that implement the protocols for communication + between the root or host OS and guest OSs (virtual machines). + +properties: + compatible: + const: microsoft,vmbus + + ranges: true + + '#address-cells': + const: 2 + + '#size-cells': + const: 1 + +required: + - compatible + - ranges + - '#address-cells' + - '#size-cells' + +additionalProperties: false + +examples: + - | + soc { + #address-cells = <2>; + #size-cells = <1>; + bus { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges; + + vmbus@ff0000000 { + compatible = "microsoft,vmbus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0x0f 0xf0000000 0x0f 0xf0000000 0x10000000>; + }; + }; + }; diff --git a/MAINTAINERS b/MAINTAINERS index 0e64787aace8..90ea0a7fb733 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9520,6 +9520,7 @@ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git F: Documentation/ABI/stable/sysfs-bus-vmbus F: Documentation/ABI/testing/debugfs-hyperv +F: Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml F: Documentation/virt/hyperv F: Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst F: arch/arm64/hyperv -- GitLab From f83705a51275ed29117d46e1d68e8b16dcb40507 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 20 Mar 2023 00:47:40 -0700 Subject: [PATCH 3128/5631] Driver: VMBus: Add Devicetree support Update the driver to support Devicetree boot as well along with ACPI. At present the Devicetree parsing only provides the mmio region info and is not the exact copy of ACPI parsing. This is sufficient to cater all the current Devicetree usecases for VMBus. Currently Devicetree is supported only for x86 systems. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1679298460-11855-6-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- drivers/hv/Kconfig | 5 ++-- drivers/hv/vmbus_drv.c | 66 +++++++++++++++++++++++++++++++++++++++--- 2 files changed, 65 insertions(+), 6 deletions(-) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 0747a8f1fcee..47132b30b7ee 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -4,11 +4,12 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on ACPI && ((X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \ - || (ARM64 && !CPU_BIG_ENDIAN)) + depends on (X86 && X86_LOCAL_APIC && HYPERVISOR_GUEST) \ + || (ACPI && ARM64 && !CPU_BIG_ENDIAN) select PARAVIRT select X86_HV_CALLBACK_VECTOR if X86 select VMAP_PFN + select OF_EARLY_FLATTREE if OF help Select this option to run Linux as a Hyper-V client operating system. diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 73497157a23a..20b4be426e0c 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -2152,7 +2153,7 @@ void vmbus_device_unregister(struct hv_device *device_obj) device_unregister(&device_obj->device); } - +#ifdef CONFIG_ACPI /* * VMBUS is an acpi enumerated device. Get the information we * need from DSDT. @@ -2262,6 +2263,7 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) return AE_OK; } +#endif static void vmbus_mmio_remove(void) { @@ -2282,7 +2284,7 @@ static void vmbus_mmio_remove(void) } } -static void vmbus_reserve_fb(void) +static void __maybe_unused vmbus_reserve_fb(void) { resource_size_t start = 0, size; struct pci_dev *pdev; @@ -2442,6 +2444,7 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size) } EXPORT_SYMBOL_GPL(vmbus_free_mmio); +#ifdef CONFIG_ACPI static int vmbus_acpi_add(struct platform_device *pdev) { acpi_status result; @@ -2494,10 +2497,54 @@ static int vmbus_acpi_add(struct platform_device *pdev) vmbus_mmio_remove(); return ret_val; } +#else +static int vmbus_acpi_add(struct platform_device *pdev) +{ + return 0; +} +#endif + +static int vmbus_device_add(struct platform_device *pdev) +{ + struct resource **cur_res = &hyperv_mmio; + struct of_range range; + struct of_range_parser parser; + struct device_node *np = pdev->dev.of_node; + int ret; + + hv_dev = &pdev->dev; + + ret = of_range_parser_init(&parser, np); + if (ret) + return ret; + + for_each_of_range(&parser, &range) { + struct resource *res; + + res = kzalloc(sizeof(*res), GFP_KERNEL); + if (!res) { + vmbus_mmio_remove(); + return -ENOMEM; + } + + res->name = "hyperv mmio"; + res->flags = range.flags; + res->start = range.cpu_addr; + res->end = range.cpu_addr + range.size; + + *cur_res = res; + cur_res = &res->sibling; + } + + return ret; +} static int vmbus_platform_driver_probe(struct platform_device *pdev) { - return vmbus_acpi_add(pdev); + if (acpi_disabled) + return vmbus_device_add(pdev); + else + return vmbus_acpi_add(pdev); } static int vmbus_platform_driver_remove(struct platform_device *pdev) @@ -2643,7 +2690,17 @@ static int vmbus_bus_resume(struct device *dev) #define vmbus_bus_resume NULL #endif /* CONFIG_PM_SLEEP */ -static const struct acpi_device_id vmbus_acpi_device_ids[] = { +static const __maybe_unused struct of_device_id vmbus_of_match[] = { + { + .compatible = "microsoft,vmbus", + }, + { + /* sentinel */ + }, +}; +MODULE_DEVICE_TABLE(of, vmbus_of_match); + +static const __maybe_unused struct acpi_device_id vmbus_acpi_device_ids[] = { {"VMBUS", 0}, {"VMBus", 0}, {"", 0}, @@ -2677,6 +2734,7 @@ static struct platform_driver vmbus_platform_driver = { .driver = { .name = "vmbus", .acpi_match_table = ACPI_PTR(vmbus_acpi_device_ids), + .of_match_table = of_match_ptr(vmbus_of_match), .pm = &vmbus_bus_pm, .probe_type = PROBE_FORCE_SYNCHRONOUS, } -- GitLab From 0459ff4873739986dccafbb417cfc69e71bdacf4 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:02 -0700 Subject: [PATCH 3129/5631] swiotlb: Remove bounce buffer remapping for Hyper-V With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), creating a second kernel virtual mapping for shared memory is no longer necessary. Everything needed for the transition to shared is handled by set_memory_decrypted(). As such, remove swiotlb_unencrypted_base and the associated code. Signed-off-by: Michael Kelley Acked-by: Christoph Hellwig Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/1679838727-87310-8-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/kernel/cpu/mshyperv.c | 7 +----- include/linux/swiotlb.h | 2 -- kernel/dma/swiotlb.c | 45 +--------------------------------- 3 files changed, 2 insertions(+), 52 deletions(-) diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 315fc358e584..ac630ecde795 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -408,12 +407,8 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n", ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b); - if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) { + if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP) static_branch_enable(&isolation_type_snp); -#ifdef CONFIG_SWIOTLB - swiotlb_unencrypted_base = ms_hyperv.shared_gpa_boundary; -#endif - } } if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) { diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..2ef25e6fa1b4 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -180,6 +180,4 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ -extern phys_addr_t swiotlb_unencrypted_base; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index dac42a2ad588..0fb16bdbbcae 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -73,8 +73,6 @@ static bool swiotlb_force_disable; struct io_tlb_mem io_tlb_default_mem; -phys_addr_t swiotlb_unencrypted_base; - static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; static unsigned long default_nareas; @@ -201,34 +199,6 @@ static inline unsigned long nr_slots(u64 val) return DIV_ROUND_UP(val, IO_TLB_SIZE); } -/* - * Remap swioltb memory in the unencrypted physical address space - * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP - * Isolation VMs). - */ -#ifdef CONFIG_HAS_IOMEM -static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) -{ - void *vaddr = NULL; - - if (swiotlb_unencrypted_base) { - phys_addr_t paddr = mem->start + swiotlb_unencrypted_base; - - vaddr = memremap(paddr, bytes, MEMREMAP_WB); - if (!vaddr) - pr_err("Failed to map the unencrypted memory %pa size %lx.\n", - &paddr, bytes); - } - - return vaddr; -} -#else -static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) -{ - return NULL; -} -#endif - /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to @@ -238,18 +208,12 @@ static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) void __init swiotlb_update_mem_attributes(void) { struct io_tlb_mem *mem = &io_tlb_default_mem; - void *vaddr; unsigned long bytes; if (!mem->nslabs || mem->late_alloc) return; - vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); - set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - - mem->vaddr = swiotlb_mem_remap(mem, bytes); - if (!mem->vaddr) - mem->vaddr = vaddr; + set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT); } static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, @@ -280,13 +244,6 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->slots[i].alloc_size = 0; } - /* - * If swiotlb_unencrypted_base is set, the bounce buffer memory will - * be remapped and cleared in swiotlb_update_mem_attributes. - */ - if (swiotlb_unencrypted_base) - return; - memset(vaddr, 0, bytes); mem->vaddr = vaddr; return; -- GitLab From a5ddb74588213c31ce993a8e9a09d1ffdc11a142 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:03 -0700 Subject: [PATCH 3130/5631] Drivers: hv: vmbus: Remove second mapping of VMBus monitor pages With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), creating a second kernel virtual mapping for shared memory is no longer necessary. Everything needed for the transition to shared is handled by set_memory_decrypted(). As such, remove the code to create and manage the second mapping for VMBus monitor pages. Because set_memory_decrypted() and set_memory_encrypted() are no-ops in normal VMs, it's not even necessary to test for being in a Confidential VM (a.k.a., "Isolation VM"). Signed-off-by: Michael Kelley Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1679838727-87310-9-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/connection.c | 113 ++++++++++---------------------------- drivers/hv/hyperv_vmbus.h | 2 - 2 files changed, 28 insertions(+), 87 deletions(-) diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index da51b50787df..5978e9dbc286 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -104,8 +104,14 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version) vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID; } - msg->monitor_page1 = vmbus_connection.monitor_pages_pa[0]; - msg->monitor_page2 = vmbus_connection.monitor_pages_pa[1]; + /* + * shared_gpa_boundary is zero in non-SNP VMs, so it's safe to always + * bitwise OR it + */ + msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]) | + ms_hyperv.shared_gpa_boundary; + msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]) | + ms_hyperv.shared_gpa_boundary; msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU); @@ -219,72 +225,27 @@ int vmbus_connect(void) * Setup the monitor notification facility. The 1st page for * parent->child and the 2nd page for child->parent */ - vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_zeroed_page(); - vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_zeroed_page(); + vmbus_connection.monitor_pages[0] = (void *)hv_alloc_hyperv_page(); + vmbus_connection.monitor_pages[1] = (void *)hv_alloc_hyperv_page(); if ((vmbus_connection.monitor_pages[0] == NULL) || (vmbus_connection.monitor_pages[1] == NULL)) { ret = -ENOMEM; goto cleanup; } - vmbus_connection.monitor_pages_original[0] - = vmbus_connection.monitor_pages[0]; - vmbus_connection.monitor_pages_original[1] - = vmbus_connection.monitor_pages[1]; - vmbus_connection.monitor_pages_pa[0] - = virt_to_phys(vmbus_connection.monitor_pages[0]); - vmbus_connection.monitor_pages_pa[1] - = virt_to_phys(vmbus_connection.monitor_pages[1]); - - if (hv_is_isolation_supported()) { - ret = set_memory_decrypted((unsigned long) - vmbus_connection.monitor_pages[0], - 1); - ret |= set_memory_decrypted((unsigned long) - vmbus_connection.monitor_pages[1], - 1); - if (ret) - goto cleanup; - - /* - * Isolation VM with AMD SNP needs to access monitor page via - * address space above shared gpa boundary. - */ - if (hv_isolation_type_snp()) { - vmbus_connection.monitor_pages_pa[0] += - ms_hyperv.shared_gpa_boundary; - vmbus_connection.monitor_pages_pa[1] += - ms_hyperv.shared_gpa_boundary; - - vmbus_connection.monitor_pages[0] - = memremap(vmbus_connection.monitor_pages_pa[0], - HV_HYP_PAGE_SIZE, - MEMREMAP_WB); - if (!vmbus_connection.monitor_pages[0]) { - ret = -ENOMEM; - goto cleanup; - } - - vmbus_connection.monitor_pages[1] - = memremap(vmbus_connection.monitor_pages_pa[1], - HV_HYP_PAGE_SIZE, - MEMREMAP_WB); - if (!vmbus_connection.monitor_pages[1]) { - ret = -ENOMEM; - goto cleanup; - } - } - - /* - * Set memory host visibility hvcall smears memory - * and so zero monitor pages here. - */ - memset(vmbus_connection.monitor_pages[0], 0x00, - HV_HYP_PAGE_SIZE); - memset(vmbus_connection.monitor_pages[1], 0x00, - HV_HYP_PAGE_SIZE); + ret = set_memory_decrypted((unsigned long) + vmbus_connection.monitor_pages[0], 1); + ret |= set_memory_decrypted((unsigned long) + vmbus_connection.monitor_pages[1], 1); + if (ret) + goto cleanup; - } + /* + * Set_memory_decrypted() will change the memory contents if + * decryption occurs, so zero monitor pages here. + */ + memset(vmbus_connection.monitor_pages[0], 0x00, HV_HYP_PAGE_SIZE); + memset(vmbus_connection.monitor_pages[1], 0x00, HV_HYP_PAGE_SIZE); msginfo = kzalloc(sizeof(*msginfo) + sizeof(struct vmbus_channel_initiate_contact), @@ -376,31 +337,13 @@ void vmbus_disconnect(void) vmbus_connection.int_page = NULL; } - if (hv_is_isolation_supported()) { - /* - * memunmap() checks input address is ioremap address or not - * inside. It doesn't unmap any thing in the non-SNP CVM and - * so not check CVM type here. - */ - memunmap(vmbus_connection.monitor_pages[0]); - memunmap(vmbus_connection.monitor_pages[1]); - - set_memory_encrypted((unsigned long) - vmbus_connection.monitor_pages_original[0], - 1); - set_memory_encrypted((unsigned long) - vmbus_connection.monitor_pages_original[1], - 1); - } + set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); + set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); - hv_free_hyperv_page((unsigned long) - vmbus_connection.monitor_pages_original[0]); - hv_free_hyperv_page((unsigned long) - vmbus_connection.monitor_pages_original[1]); - vmbus_connection.monitor_pages_original[0] = - vmbus_connection.monitor_pages[0] = NULL; - vmbus_connection.monitor_pages_original[1] = - vmbus_connection.monitor_pages[1] = NULL; + hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]); + hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]); + vmbus_connection.monitor_pages[0] = NULL; + vmbus_connection.monitor_pages[1] = NULL; } /* diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index dc673edf053c..167ac5115a78 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -241,8 +241,6 @@ struct vmbus_connection { * is child->parent notification */ struct hv_monitor_page *monitor_pages[2]; - void *monitor_pages_original[2]; - phys_addr_t monitor_pages_pa[2]; struct list_head chn_msg_list; spinlock_t channelmsg_lock; -- GitLab From bb862397f48fc79a1ea31b83a0bd8f1f913b4ab6 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:04 -0700 Subject: [PATCH 3131/5631] Drivers: hv: vmbus: Remove second way of mapping ring buffers With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), it's no longer necessary to have separate code paths for mapping VMBus ring buffers for for normal VMs and for Confidential VMs. As such, remove the code path that uses vmap_pfn(), and set the protection flags argument to vmap() to account for the difference between normal and Confidential VMs. Signed-off-by: Michael Kelley Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1679838727-87310-10-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/ring_buffer.c | 62 +++++++++++++--------------------------- 1 file changed, 20 insertions(+), 42 deletions(-) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 2111e97c3b63..3c9b02471760 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -186,8 +186,6 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt, u32 max_pkt_size) { struct page **pages_wraparound; - unsigned long *pfns_wraparound; - u64 pfn; int i; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); @@ -196,50 +194,30 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ - if (hv_isolation_type_snp()) { - pfn = page_to_pfn(pages) + - PFN_DOWN(ms_hyperv.shared_gpa_boundary); + pages_wraparound = kcalloc(page_cnt * 2 - 1, + sizeof(struct page *), + GFP_KERNEL); + if (!pages_wraparound) + return -ENOMEM; - pfns_wraparound = kcalloc(page_cnt * 2 - 1, - sizeof(unsigned long), GFP_KERNEL); - if (!pfns_wraparound) - return -ENOMEM; - - pfns_wraparound[0] = pfn; - for (i = 0; i < 2 * (page_cnt - 1); i++) - pfns_wraparound[i + 1] = pfn + i % (page_cnt - 1) + 1; - - ring_info->ring_buffer = (struct hv_ring_buffer *) - vmap_pfn(pfns_wraparound, page_cnt * 2 - 1, - pgprot_decrypted(PAGE_KERNEL)); - kfree(pfns_wraparound); - - if (!ring_info->ring_buffer) - return -ENOMEM; - - /* Zero ring buffer after setting memory host visibility. */ - memset(ring_info->ring_buffer, 0x00, PAGE_SIZE * page_cnt); - } else { - pages_wraparound = kcalloc(page_cnt * 2 - 1, - sizeof(struct page *), - GFP_KERNEL); - if (!pages_wraparound) - return -ENOMEM; - - pages_wraparound[0] = pages; - for (i = 0; i < 2 * (page_cnt - 1); i++) - pages_wraparound[i + 1] = - &pages[i % (page_cnt - 1) + 1]; + pages_wraparound[0] = pages; + for (i = 0; i < 2 * (page_cnt - 1); i++) + pages_wraparound[i + 1] = + &pages[i % (page_cnt - 1) + 1]; - ring_info->ring_buffer = (struct hv_ring_buffer *) - vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, - PAGE_KERNEL); + ring_info->ring_buffer = (struct hv_ring_buffer *) + vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, + pgprot_decrypted(PAGE_KERNEL)); - kfree(pages_wraparound); - if (!ring_info->ring_buffer) - return -ENOMEM; - } + kfree(pages_wraparound); + if (!ring_info->ring_buffer) + return -ENOMEM; + /* + * Ensure the header page is zero'ed since + * encryption status may have changed. + */ + memset(ring_info->ring_buffer, 0, HV_HYP_PAGE_SIZE); ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; -- GitLab From 25727aaed6514b88f98a18862c6f2d65a0b0ec3b Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:05 -0700 Subject: [PATCH 3132/5631] hv_netvsc: Remove second mapping of send and recv buffers With changes to how Hyper-V guest VMs flip memory between private (encrypted) and shared (decrypted), creating a second kernel virtual mapping for shared memory is no longer necessary. Everything needed for the transition to shared is handled by set_memory_decrypted(). As such, remove the code to create and manage the second mapping for the pre-allocated send and recv buffers. This mapping is the last user of hv_map_memory()/hv_unmap_memory(), so delete these functions as well. Finally, hv_map_memory() is the last user of vmap_pfn() in Hyper-V guest code, so remove the Kconfig selection of VMAP_PFN. Signed-off-by: Michael Kelley Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1679838727-87310-11-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/ivm.c | 28 ------------------- drivers/hv/Kconfig | 1 - drivers/hv/hv_common.c | 11 -------- drivers/net/hyperv/hyperv_net.h | 2 -- drivers/net/hyperv/netvsc.c | 48 ++------------------------------- include/asm-generic/mshyperv.h | 2 -- 6 files changed, 2 insertions(+), 90 deletions(-) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index f6a020cb1a24..127d5b7b63de 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -376,34 +376,6 @@ void __init hv_vtom_init(void) #endif /* CONFIG_AMD_MEM_ENCRYPT */ -/* - * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM. - */ -void *hv_map_memory(void *addr, unsigned long size) -{ - unsigned long *pfns = kcalloc(size / PAGE_SIZE, - sizeof(unsigned long), GFP_KERNEL); - void *vaddr; - int i; - - if (!pfns) - return NULL; - - for (i = 0; i < size / PAGE_SIZE; i++) - pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) + - (ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT); - - vaddr = vmap_pfn(pfns, size / PAGE_SIZE, pgprot_decrypted(PAGE_KERNEL)); - kfree(pfns); - - return vaddr; -} - -void hv_unmap_memory(void *addr) -{ - vunmap(addr); -} - enum hv_isolation_type hv_get_isolation_type(void) { if (!(ms_hyperv.priv_high & HV_ISOLATION)) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 47132b30b7ee..94982f08b661 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -8,7 +8,6 @@ config HYPERV || (ACPI && ARM64 && !CPU_BIG_ENDIAN) select PARAVIRT select X86_HV_CALLBACK_VECTOR if X86 - select VMAP_PFN select OF_EARLY_FLATTREE if OF help Select this option to run Linux as a Hyper-V client operating diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 52a6f89ccdbd..6d40b6c7b23b 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -311,14 +311,3 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_s return HV_STATUS_INVALID_PARAMETER; } EXPORT_SYMBOL_GPL(hv_ghcb_hypercall); - -void __weak *hv_map_memory(void *addr, unsigned long size) -{ - return NULL; -} -EXPORT_SYMBOL_GPL(hv_map_memory); - -void __weak hv_unmap_memory(void *addr) -{ -} -EXPORT_SYMBOL_GPL(hv_unmap_memory); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index dd5919ec408b..33d51e363913 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1139,7 +1139,6 @@ struct netvsc_device { /* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; - void *recv_original_buf; u32 recv_buf_size; /* allocated bytes */ struct vmbus_gpadl recv_buf_gpadl_handle; u32 recv_section_cnt; @@ -1148,7 +1147,6 @@ struct netvsc_device { /* Send buffer allocated by us */ void *send_buf; - void *send_original_buf; u32 send_buf_size; struct vmbus_gpadl send_buf_gpadl_handle; u32 send_section_cnt; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index da737d959e81..82e9796c8f5e 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -154,17 +154,8 @@ static void free_netvsc_device(struct rcu_head *head) int i; kfree(nvdev->extension); - - if (nvdev->recv_original_buf) - vfree(nvdev->recv_original_buf); - else - vfree(nvdev->recv_buf); - - if (nvdev->send_original_buf) - vfree(nvdev->send_original_buf); - else - vfree(nvdev->send_buf); - + vfree(nvdev->recv_buf); + vfree(nvdev->send_buf); bitmap_free(nvdev->send_section_map); for (i = 0; i < VRSS_CHANNEL_MAX; i++) { @@ -347,7 +338,6 @@ static int netvsc_init_buf(struct hv_device *device, struct nvsp_message *init_packet; unsigned int buf_size; int i, ret = 0; - void *vaddr; /* Get receive buffer area. */ buf_size = device_info->recv_sections * device_info->recv_section_size; @@ -383,17 +373,6 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } - if (hv_isolation_type_snp()) { - vaddr = hv_map_memory(net_device->recv_buf, buf_size); - if (!vaddr) { - ret = -ENOMEM; - goto cleanup; - } - - net_device->recv_original_buf = net_device->recv_buf; - net_device->recv_buf = vaddr; - } - /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -497,17 +476,6 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } - if (hv_isolation_type_snp()) { - vaddr = hv_map_memory(net_device->send_buf, buf_size); - if (!vaddr) { - ret = -ENOMEM; - goto cleanup; - } - - net_device->send_original_buf = net_device->send_buf; - net_device->send_buf = vaddr; - } - /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -762,12 +730,6 @@ void netvsc_device_remove(struct hv_device *device) netvsc_teardown_send_gpadl(device, net_device, ndev); } - if (net_device->recv_original_buf) - hv_unmap_memory(net_device->recv_buf); - - if (net_device->send_original_buf) - hv_unmap_memory(net_device->send_buf); - /* Release all resources */ free_netvsc_device_rcu(net_device); } @@ -1844,12 +1806,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, netif_napi_del(&net_device->chan_table[0].napi); cleanup2: - if (net_device->recv_original_buf) - hv_unmap_memory(net_device->recv_buf); - - if (net_device->send_original_buf) - hv_unmap_memory(net_device->send_buf); - free_netvsc_device(&net_device->rcu); return ERR_PTR(ret); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 90d7f68ed39d..afcd9ae9588c 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -271,8 +271,6 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); void hv_setup_dma_ops(struct device *dev, bool coherent); -void *hv_map_memory(void *addr, unsigned long size); -void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ static inline bool hv_is_hyperv_initialized(void) { return false; } static inline bool hv_is_hibernation_supported(void) { return false; } -- GitLab From 6afd9dc1a4b158456c072580f0851b4dbaaa02f1 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:06 -0700 Subject: [PATCH 3133/5631] Drivers: hv: Don't remap addresses that are above shared_gpa_boundary With the vTOM bit now treated as a protection flag and not part of the physical address, avoid remapping physical addresses with vTOM set since technically such addresses aren't valid. Use ioremap_cache() instead of memremap() to ensure that the mapping provides decrypted access, which will correctly set the vTOM bit as a protection flag. While this change is not required for correctness with the current implementation of memremap(), for general code hygiene it's better to not depend on the mapping functions doing something reasonable with a physical address that is out-of-range. While here, fix typos in two error messages. Signed-off-by: Michael Kelley Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1679838727-87310-12-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_init.c | 7 +++++-- drivers/hv/hv.c | 23 +++++++++++++---------- 2 files changed, 18 insertions(+), 12 deletions(-) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index edbc67ec1f3e..a5f9474f08e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -63,7 +63,10 @@ static int hyperv_init_ghcb(void) * memory boundary and map it here. */ rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa); - ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB); + + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary; + ghcb_va = (void *)ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE); if (!ghcb_va) return -ENOMEM; @@ -217,7 +220,7 @@ static int hv_cpu_die(unsigned int cpu) if (hv_ghcb_pg) { ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg); if (*ghcb_va) - memunmap(*ghcb_va); + iounmap(*ghcb_va); *ghcb_va = NULL; } diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 8b0dd8e5244d..008234894d28 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -217,11 +217,13 @@ void hv_synic_enable_regs(unsigned int cpu) simp.simp_enabled = 1; if (hv_isolation_type_snp() || hv_root_partition) { + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & + ~ms_hyperv.shared_gpa_boundary; hv_cpu->synic_message_page - = memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT, - HV_HYP_PAGE_SIZE, MEMREMAP_WB); + = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_message_page) - pr_err("Fail to map syinc message page.\n"); + pr_err("Fail to map synic message page.\n"); } else { simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page) >> HV_HYP_PAGE_SHIFT; @@ -234,12 +236,13 @@ void hv_synic_enable_regs(unsigned int cpu) siefp.siefp_enabled = 1; if (hv_isolation_type_snp() || hv_root_partition) { - hv_cpu->synic_event_page = - memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT, - HV_HYP_PAGE_SIZE, MEMREMAP_WB); - + /* Mask out vTOM bit. ioremap_cache() maps decrypted */ + u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & + ~ms_hyperv.shared_gpa_boundary; + hv_cpu->synic_event_page + = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_event_page) - pr_err("Fail to map syinc event page.\n"); + pr_err("Fail to map synic event page.\n"); } else { siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page) >> HV_HYP_PAGE_SHIFT; @@ -316,7 +319,7 @@ void hv_synic_disable_regs(unsigned int cpu) */ simp.simp_enabled = 0; if (hv_isolation_type_snp() || hv_root_partition) { - memunmap(hv_cpu->synic_message_page); + iounmap(hv_cpu->synic_message_page); hv_cpu->synic_message_page = NULL; } else { simp.base_simp_gpa = 0; @@ -328,7 +331,7 @@ void hv_synic_disable_regs(unsigned int cpu) siefp.siefp_enabled = 0; if (hv_isolation_type_snp() || hv_root_partition) { - memunmap(hv_cpu->synic_event_page); + iounmap(hv_cpu->synic_event_page); hv_cpu->synic_event_page = NULL; } else { siefp.base_siefp_gpa = 0; -- GitLab From 2c6ba4216844ca7918289b49ed5f3f7138ee2402 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 26 Mar 2023 06:52:07 -0700 Subject: [PATCH 3134/5631] PCI: hv: Enable PCI pass-thru devices in Confidential VMs For PCI pass-thru devices in a Confidential VM, Hyper-V requires that PCI config space be accessed via hypercalls. In normal VMs, config space accesses are trapped to the Hyper-V host and emulated. But in a confidential VM, the host can't access guest memory to decode the instruction for emulation, so an explicit hypercall must be used. Add functions to make the new MMIO read and MMIO write hypercalls. Update the PCI config space access functions to use the hypercalls when such use is indicated by Hyper-V flags. Also, set the flag to allow the Hyper-V PCI driver to be loaded and used in a Confidential VM (a.k.a., "Isolation VM"). The driver has previously been hardened against a malicious Hyper-V host[1]. [1] https://lore.kernel.org/all/20220511223207.3386-2-parri.andrea@gmail.com/ Co-developed-by: Dexuan Cui Signed-off-by: Dexuan Cui Signed-off-by: Michael Kelley Reviewed-by: Boqun Feng Reviewed-by: Haiyang Zhang Link: https://lore.kernel.org/r/1679838727-87310-13-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/include/asm/hyperv-tlfs.h | 3 + drivers/hv/channel_mgmt.c | 2 +- drivers/pci/controller/pci-hyperv.c | 232 ++++++++++++++++++++-------- include/asm-generic/hyperv-tlfs.h | 22 +++ 4 files changed, 194 insertions(+), 65 deletions(-) diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 0b73a809e9e1..b4fb75bd1013 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -122,6 +122,9 @@ /* Recommend using enlightened VMCS */ #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +/* Use hypercalls for MMIO config space access */ +#define HV_X64_USE_MMIO_HYPERCALLS BIT(21) + /* * CPU management features identification. * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits. diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index cc23b90cae02..007f26d5f1a4 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -67,7 +67,7 @@ const struct vmbus_device vmbus_devs[] = { { .dev_type = HV_PCIE, HV_PCIE_GUID, .perf_device = false, - .allowed_in_isolated = false, + .allowed_in_isolated = true, }, /* Synthetic Frame Buffer */ diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f33370b75628..337f3b4a04fc 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -514,6 +514,7 @@ struct hv_pcibus_device { /* Highest slot of child device with resources allocated */ int wslot_res_allocated; + bool use_calls; /* Use hypercalls to access mmio cfg space */ /* hypercall arg, must not cross page boundary */ struct hv_retarget_device_interrupt retarget_msi_interrupt_params; @@ -1041,6 +1042,70 @@ static int wslot_to_devfn(u32 wslot) return PCI_DEVFN(slot_no.bits.dev, slot_no.bits.func); } +static void hv_pci_read_mmio(struct device *dev, phys_addr_t gpa, int size, u32 *val) +{ + struct hv_mmio_read_input *in; + struct hv_mmio_read_output *out; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument page. Use it for + * both input and output. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + out = *this_cpu_ptr(hyperv_pcpu_input_arg) + sizeof(*in); + in->gpa = gpa; + in->size = size; + + ret = hv_do_hypercall(HVCALL_MMIO_READ, in, out); + if (hv_result_success(ret)) { + switch (size) { + case 1: + *val = *(u8 *)(out->data); + break; + case 2: + *val = *(u16 *)(out->data); + break; + default: + *val = *(u32 *)(out->data); + break; + } + } else + dev_err(dev, "MMIO read hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + +static void hv_pci_write_mmio(struct device *dev, phys_addr_t gpa, int size, u32 val) +{ + struct hv_mmio_write_input *in; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument memory. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + in->gpa = gpa; + in->size = size; + switch (size) { + case 1: + *(u8 *)(in->data) = val; + break; + case 2: + *(u16 *)(in->data) = val; + break; + default: + *(u32 *)(in->data) = val; + break; + } + + ret = hv_do_hypercall(HVCALL_MMIO_WRITE, in, NULL); + if (!hv_result_success(ret)) + dev_err(dev, "MMIO write hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + /* * PCI Configuration Space for these root PCI buses is implemented as a pair * of pages in memory-mapped I/O space. Writing to the first page chooses @@ -1059,8 +1124,10 @@ static int wslot_to_devfn(u32 wslot) static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, int size, u32 *val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; /* * If the attempt is to read the IDs or the ROM BAR, simulate that. @@ -1088,56 +1155,79 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, */ *val = 0; } else if (where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - switch (size) { - case 1: - *val = readb(addr); - break; - case 2: - *val = readw(addr); - break; - default: - *val = readl(addr); - break; + + spin_lock_irqsave(&hbus->config_lock, flags); + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before reading. */ + mb(); + /* Read from that function's config space. */ + switch (size) { + case 1: + *val = readb(addr); + break; + case 2: + *val = readw(addr); + break; + default: + *val = readl(addr); + break; + } + /* + * Make sure the read was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the read was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to read beyond a function's config space.\n"); + dev_err(dev, "Attempt to read beyond a function's config space.\n"); } } static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + u32 val; u16 ret; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + - PCI_VENDOR_ID; - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + spin_lock_irqsave(&hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - ret = readw(addr); - /* - * mb() is not required here, because the spin_unlock_irqrestore() - * is a barrier. - */ + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + + CFG_PAGE_OFFSET + PCI_VENDOR_ID; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, 2, &val); + ret = val; /* Truncates to 16 bits */ + } else { + void __iomem *addr = hbus->cfg_addr + CFG_PAGE_OFFSET + + PCI_VENDOR_ID; + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + ret = readw(addr); + /* + * mb() is not required here, because the + * spin_unlock_irqrestore() is a barrier. + */ + } - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); return ret; } @@ -1152,39 +1242,51 @@ static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where, int size, u32 val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <= PCI_CAPABILITY_LIST) { /* SSIDs and ROM BARs are read-only */ } else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be written. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start writing. */ - wmb(); - /* Write to that function's config space. */ - switch (size) { - case 1: - writeb(val, addr); - break; - case 2: - writew(val, addr); - break; - default: - writel(val, addr); - break; + spin_lock_irqsave(&hbus->config_lock, flags); + + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_write_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to write. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before writing. */ + wmb(); + /* Write to that function's config space. */ + switch (size) { + case 1: + writeb(val, addr); + break; + case 2: + writew(val, addr); + break; + default: + writel(val, addr); + break; + } + /* + * Make sure the write was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the write was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to write beyond a function's config space.\n"); + dev_err(dev, "Attempt to write beyond a function's config space.\n"); } } @@ -3563,6 +3665,7 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; + hbus->use_calls = !!(ms_hyperv.hints & HV_X64_USE_MMIO_HYPERCALLS); #elif defined(CONFIG_ARM64) /* * Set the PCI bus parent to be the corresponding VMbus @@ -3572,6 +3675,7 @@ static int hv_pci_probe(struct hv_device *hdev, * information to devices created on the bus. */ hbus->sysdata.parent = hdev->device.parent; + hbus->use_calls = false; #endif hbus->hdev = hdev; diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index b870983596b9..ea406e901469 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -168,6 +168,8 @@ union hv_reference_tsc_msr { #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db +#define HVCALL_MMIO_READ 0x0106 +#define HVCALL_MMIO_WRITE 0x0107 /* Extended hypercalls */ #define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 @@ -796,4 +798,24 @@ struct hv_memory_hint { union hv_gpa_page_range ranges[]; } __packed; +/* Data structures for HVCALL_MMIO_READ and HVCALL_MMIO_WRITE */ +#define HV_HYPERCALL_MMIO_MAX_DATA_LENGTH 64 + +struct hv_mmio_read_input { + u64 gpa; + u32 size; + u32 reserved; +} __packed; + +struct hv_mmio_read_output { + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + +struct hv_mmio_write_input { + u64 gpa; + u32 size; + u32 reserved; + u8 data[HV_HYPERCALL_MMIO_MAX_DATA_LENGTH]; +} __packed; + #endif -- GitLab From c0e96acf884a1ce91c9bdd692c6a425b83c90285 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 8 Apr 2023 14:03:39 -0700 Subject: [PATCH 3135/5631] clocksource: hyper-v: make sure Invariant-TSC is used if it is available If Hyper-V TSC page is unavailable and Invariant-TSC is available, currently hyperv_cs_msr (rather than Invariant-TSC) is used by default. Use Invariant-TSC by default by downgrading hyperv_cs_msr.rating in hv_init_tsc_clocksource(), if Invariant-TSC is available. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20230408210339.15085-1-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/clocksource/hyperv_timer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index f32948c8a96f..bcd9042a0c9f 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -517,9 +517,6 @@ static bool __init hv_init_tsc_clocksource(void) { union hv_reference_tsc_msr tsc_msr; - if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) - return false; - /* * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly * handles frequency and offset changes due to live migration, @@ -536,6 +533,9 @@ static bool __init hv_init_tsc_clocksource(void) hyperv_cs_msr.rating = 250; } + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return false; + hv_read_reference_counter = read_hv_clock_tsc; /* -- GitLab From 9a6b1a170ca8627d401fa76112e4920ba8c6314c Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Sat, 8 Apr 2023 14:34:41 -0700 Subject: [PATCH 3136/5631] Drivers: hv: vmbus: Remove the per-CPU post_msg_page The post_msg_page was introduced in 2014 in commit b29ef3546aec ("Drivers: hv: vmbus: Cleanup hv_post_message()") Commit 68bb7bfb7985 ("X86/Hyper-V: Enable IPI enlightenments") introduced the hyperv_pcpu_input_arg in 2018, which can be used in hv_post_message(). Remove post_msg_page to simplify the code a little bit. Signed-off-by: Dexuan Cui Reviewed-by: Jinank Jain Link: https://lore.kernel.org/r/20230408213441.15472-1-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/hv.c | 20 +++++--------------- drivers/hv/hyperv_vmbus.h | 4 ---- 2 files changed, 5 insertions(+), 19 deletions(-) diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 008234894d28..4e1407d59ba0 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -84,14 +84,15 @@ int hv_post_message(union hv_connection_id connection_id, void *payload, size_t payload_size) { struct hv_input_post_message *aligned_msg; - struct hv_per_cpu_context *hv_cpu; + unsigned long flags; u64 status; if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) return -EMSGSIZE; - hv_cpu = get_cpu_ptr(hv_context.cpu_context); - aligned_msg = hv_cpu->post_msg_page; + local_irq_save(flags); + + aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg); aligned_msg->connectionid = connection_id; aligned_msg->reserved = 0; aligned_msg->message_type = message_type; @@ -106,11 +107,7 @@ int hv_post_message(union hv_connection_id connection_id, status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL); - /* Preemption must remain disabled until after the hypercall - * so some other thread can't get scheduled onto this cpu and - * corrupt the per-cpu post_msg_page - */ - put_cpu_ptr(hv_cpu); + local_irq_restore(flags); return hv_result(status); } @@ -162,12 +159,6 @@ int hv_synic_alloc(void) goto err; } } - - hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->post_msg_page == NULL) { - pr_err("Unable to allocate post msg page\n"); - goto err; - } } return 0; @@ -190,7 +181,6 @@ void hv_synic_free(void) free_page((unsigned long)hv_cpu->synic_event_page); free_page((unsigned long)hv_cpu->synic_message_page); - free_page((unsigned long)hv_cpu->post_msg_page); } kfree(hv_context.hv_numa_map); diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 167ac5115a78..55f2086841ae 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -122,10 +122,6 @@ enum { struct hv_per_cpu_context { void *synic_message_page; void *synic_event_page; - /* - * buffer to post messages to the host. - */ - void *post_msg_page; /* * Starting with win8, we can take channel interrupts on any CPU; -- GitLab From d7b6ba9611aefc4bef207b16db8ff06b726efe35 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 27 Mar 2023 06:16:06 -0700 Subject: [PATCH 3137/5631] x86/hyperv: Add callback filter to cpumask_to_vpset() When copying CPUs from a Linux cpumask to a Hyper-V VPset, cpumask_to_vpset() currently has a "_noself" variant that doesn't copy the current CPU to the VPset. Generalize this variant by replacing it with a "_skip" variant having a callback function that is invoked for each CPU to decide if that CPU should be copied. Update the one caller of cpumask_to_vpset_noself() to use the new "_skip" variant instead. No functional change. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1679922967-26582-2-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/hv_apic.c | 12 ++++++++---- include/asm-generic/mshyperv.h | 22 ++++++++++++++-------- 2 files changed, 22 insertions(+), 12 deletions(-) diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index fb8b2c088681..1fbda2f94184 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -96,6 +96,11 @@ static void hv_apic_eoi_write(u32 reg, u32 val) wrmsr(HV_X64_MSR_EOI, val, 0); } +static bool cpu_is_self(int cpu) +{ + return cpu == smp_processor_id(); +} + /* * IPI implementation on Hyper-V. */ @@ -128,10 +133,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, */ if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - if (exclude_self) - nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask); - else - nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); + + nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask, + exclude_self ? cpu_is_self : NULL); /* * 'nr_bank <= 0' means some CPUs in cpumask can't be diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index afcd9ae9588c..402a8c1c202d 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -210,10 +210,9 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) static inline int __cpumask_to_vpset(struct hv_vpset *vpset, const struct cpumask *cpus, - bool exclude_self) + bool (*func)(int cpu)) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; - int this_cpu = smp_processor_id(); int max_vcpu_bank = hv_max_vp_index / HV_VCPUS_PER_SPARSE_BANK; /* vpset.valid_bank_mask can represent up to HV_MAX_SPARSE_VCPU_BANKS banks */ @@ -232,7 +231,7 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { - if (exclude_self && cpu == this_cpu) + if (func && func(cpu)) continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) @@ -248,17 +247,24 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +/* + * Convert a Linux cpumask into a Hyper-V VPset. In the _skip variant, + * 'func' is called for each CPU present in cpumask. If 'func' returns + * true, that CPU is skipped -- i.e., that CPU from cpumask is *not* + * added to the Hyper-V VPset. If 'func' is NULL, no CPUs are + * skipped. + */ static inline int cpumask_to_vpset(struct hv_vpset *vpset, const struct cpumask *cpus) { - return __cpumask_to_vpset(vpset, cpus, false); + return __cpumask_to_vpset(vpset, cpus, NULL); } -static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int cpumask_to_vpset_skip(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool (*func)(int cpu)) { - WARN_ON_ONCE(preemptible()); - return __cpumask_to_vpset(vpset, cpus, true); + return __cpumask_to_vpset(vpset, cpus, func); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); -- GitLab From 493cc07385cf1c6678a6159d410854b8e99aa945 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 27 Mar 2023 06:16:07 -0700 Subject: [PATCH 3138/5631] x86/hyperv: Exclude lazy TLB mode CPUs from enlightened TLB flushes In the case where page tables are not freed, native_flush_tlb_multi() does not do a remote TLB flush on CPUs in lazy TLB mode because the CPU will flush itself at the next context switch. By comparison, the Hyper-V enlightened TLB flush does not exclude CPUs in lazy TLB mode and so performs unnecessary flushes. If we're not freeing page tables, add logic to test for lazy TLB mode when adding CPUs to the input argument to the Hyper-V TLB flush hypercall. Exclude lazy TLB mode CPUs so the behavior matches native_flush_tlb_multi() and the unnecessary flushes are avoided. Handle both the <=64 vCPU case and the _ex case for >64 vCPUs. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1679922967-26582-3-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/mmu.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 0ad2378fe6ad..8460bd35e10c 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -52,6 +52,11 @@ static inline int fill_gva_list(u64 gva_list[], int offset, return gva_n - offset; } +static bool cpu_is_lazy(int cpu) +{ + return per_cpu(cpu_tlbstate_shared.is_lazy, cpu); +} + static void hyperv_flush_tlb_multi(const struct cpumask *cpus, const struct flush_tlb_info *info) { @@ -60,6 +65,7 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, struct hv_tlb_flush *flush; u64 status; unsigned long flags; + bool do_lazy = !info->freed_tables; trace_hyperv_mmu_flush_tlb_multi(cpus, info); @@ -112,6 +118,8 @@ static void hyperv_flush_tlb_multi(const struct cpumask *cpus, goto do_ex_hypercall; for_each_cpu(cpu, cpus) { + if (do_lazy && cpu_is_lazy(cpu)) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) { local_irq_restore(flags); @@ -198,7 +206,8 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); + nr_bank = cpumask_to_vpset_skip(&flush->hv_vp_set, cpus, + info->freed_tables ? NULL : cpu_is_lazy); if (nr_bank < 0) return HV_STATUS_INVALID_PARAMETER; -- GitLab From d57fd4926ab81ad5749c6950047ea40863a52e18 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 16:19:38 -0300 Subject: [PATCH 3139/5631] perf cpumap: Remove initializations done in perf_cpu_map__alloc() When extracting this patch from Ian's original patch I forgot to remove the setting of ->nr and ->refcnt, no need to do those initializations again as those are done in perf_cpu_map__alloc() already, duh. Cc: Ian Rogers Fixes: 1f94479edb4decdc ("libperf: Make perf_cpu_map__alloc() available as an internal function for tools/perf to use") Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 072831f0cad4..7008705d745c 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -163,13 +163,8 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr); if (cpus != NULL) { - int i; - - cpus->nr = nr; - for (i = 0; i < nr; i++) + for (int i = 0; i < nr; i++) cpus->map[i].cpu = -1; - - refcount_set(&cpus->refcnt, 1); } return cpus; -- GitLab From f605f26ea196a3b49bea249330cbd18dba61a33e Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Tue, 4 Apr 2023 23:26:11 -0500 Subject: [PATCH 3140/5631] RDMA/rxe: Protect QP state with qp->state_lock Currently the rxe driver makes little effort to make the changes to qp state (which includes qp->attr.qp_state, qp->attr.sq_draining and qp->valid) atomic between different client threads and IO threads. In particular a common template is for an RDMA application to call ib_modify_qp() to move a qp to ERR state and then wait until all the packet and work queues have drained before calling ib_destroy_qp(). None of these state changes are protected by locks to assure that the changes are executed atomically and that memory barriers are included. This has been observed to lead to incorrect behavior around qp cleanup. This patch continues the work of the previous patches in this series and adds locking code around qp state changes and lookups. Link: https://lore.kernel.org/r/20230405042611.6467-5-rpearsonhpe@gmail.com Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 48 ++++-- drivers/infiniband/sw/rxe/rxe_net.c | 3 + drivers/infiniband/sw/rxe/rxe_qp.c | 153 +++++++++-------- drivers/infiniband/sw/rxe/rxe_recv.c | 10 +- drivers/infiniband/sw/rxe/rxe_req.c | 71 +++++--- drivers/infiniband/sw/rxe/rxe_resp.c | 12 +- drivers/infiniband/sw/rxe/rxe_verbs.c | 238 +++++++++++++++----------- 7 files changed, 317 insertions(+), 218 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index 1ccae8cff359..db18ace74d2b 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -118,10 +118,12 @@ void retransmit_timer(struct timer_list *t) rxe_dbg_qp(qp, "retransmit timer fired\n"); + spin_lock_bh(&qp->state_lock); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->comp.task); } + spin_unlock_bh(&qp->state_lock); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) @@ -479,9 +481,8 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) static void comp_check_sq_drain_done(struct rxe_qp *qp) { + spin_lock_bh(&qp->state_lock); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { - /* state_lock used by requester & completer */ - spin_lock_bh(&qp->state_lock); if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { qp->attr.sq_draining = 0; spin_unlock_bh(&qp->state_lock); @@ -497,8 +498,8 @@ static void comp_check_sq_drain_done(struct rxe_qp *qp) } return; } - spin_unlock_bh(&qp->state_lock); } + spin_unlock_bh(&qp->state_lock); } static inline enum comp_state complete_ack(struct rxe_qp *qp, @@ -614,6 +615,26 @@ static void free_pkt(struct rxe_pkt_info *pkt) ib_device_put(dev); } +/* reset the retry timer if + * - QP is type RC + * - there is a packet sent by the requester that + * might be acked (we still might get spurious + * timeouts but try to keep them as few as possible) + * - the timeout parameter is set + * - the QP is alive + */ +static void reset_retry_timer(struct rxe_qp *qp) +{ + if (qp_type(qp) == IB_QPT_RC && qp->qp_timeout_jiffies) { + spin_lock_bh(&qp->state_lock); + if (qp_state(qp) >= IB_QPS_RTS && + psn_compare(qp->req.psn, qp->comp.psn) > 0) + mod_timer(&qp->retrans_timer, + jiffies + qp->qp_timeout_jiffies); + spin_unlock_bh(&qp->state_lock); + } +} + int rxe_completer(struct rxe_qp *qp) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); @@ -623,14 +644,17 @@ int rxe_completer(struct rxe_qp *qp) enum comp_state state; int ret; + spin_lock_bh(&qp->state_lock); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || - qp_state(qp) == IB_QPS_RESET) { + qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_resp_pkts(qp); flush_send_queue(qp, notify); + spin_unlock_bh(&qp->state_lock); goto exit; } + spin_unlock_bh(&qp->state_lock); if (qp->comp.timeout) { qp->comp.timeout_retry = 1; @@ -718,20 +742,7 @@ int rxe_completer(struct rxe_qp *qp) break; } - /* re reset the timeout counter if - * (1) QP is type RC - * (2) the QP is alive - * (3) there is a packet sent by the requester that - * might be acked (we still might get spurious - * timeouts but try to keep them as few as possible) - * (4) the timeout parameter is set - */ - if ((qp_type(qp) == IB_QPT_RC) && - (qp_state(qp) >= IB_QPS_RTS) && - (psn_compare(qp->req.psn, qp->comp.psn) > 0) && - qp->qp_timeout_jiffies) - mod_timer(&qp->retrans_timer, - jiffies + qp->qp_timeout_jiffies); + reset_retry_timer(qp); goto exit; case COMPST_ERROR_RETRY: @@ -793,6 +804,7 @@ int rxe_completer(struct rxe_qp *qp) */ qp->req.wait_for_rnr_timer = 1; rxe_dbg_qp(qp, "set rnr nak timer\n"); + // TODO who protects from destroy_qp?? mod_timer(&qp->rnr_nak_timer, jiffies + rnrnak_jiffies(aeth_syn(pkt) & ~AETH_TYPE_MASK)); diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 9ed81d0bd25c..2bc7361152ea 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -413,11 +413,14 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + spin_lock_bh(&qp->state_lock); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { + spin_unlock_bh(&qp->state_lock); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } + spin_unlock_bh(&qp->state_lock); rxe_icrc_generate(skb, pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 78c7c13e614b..c5451a4488ca 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -325,8 +325,10 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, if (err) goto err2; + spin_lock_bh(&qp->state_lock); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; + spin_unlock_bh(&qp->state_lock); return 0; @@ -377,27 +379,9 @@ int rxe_qp_to_init(struct rxe_qp *qp, struct ib_qp_init_attr *init) return 0; } -/* called by the modify qp verb, this routine checks all the parameters before - * making any changes - */ int rxe_qp_chk_attr(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { - enum ib_qp_state cur_state = (mask & IB_QP_CUR_STATE) ? - attr->cur_qp_state : qp->attr.qp_state; - enum ib_qp_state new_state = (mask & IB_QP_STATE) ? - attr->qp_state : cur_state; - - if (!ib_modify_qp_is_ok(cur_state, new_state, qp_type(qp), mask)) { - rxe_dbg_qp(qp, "invalid mask or state\n"); - goto err1; - } - - if (mask & IB_QP_STATE && cur_state == IB_QPS_SQD) { - if (qp->attr.sq_draining && new_state != IB_QPS_ERR) - goto err1; - } - if (mask & IB_QP_PORT) { if (!rdma_is_port_valid(&rxe->ib_dev, attr->port_num)) { rxe_dbg_qp(qp, "invalid port %d\n", attr->port_num); @@ -508,22 +492,96 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { + spin_lock_bh(&qp->state_lock); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); + spin_unlock_bh(&qp->state_lock); +} + +static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, + int mask) +{ + spin_lock_bh(&qp->state_lock); + qp->attr.sq_draining = 1; + rxe_sched_task(&qp->comp.task); + rxe_sched_task(&qp->req.task); + spin_unlock_bh(&qp->state_lock); +} + +/* caller should hold qp->state_lock */ +static int __qp_chk_state(struct rxe_qp *qp, struct ib_qp_attr *attr, + int mask) +{ + enum ib_qp_state cur_state; + enum ib_qp_state new_state; + + cur_state = (mask & IB_QP_CUR_STATE) ? + attr->cur_qp_state : qp->attr.qp_state; + new_state = (mask & IB_QP_STATE) ? + attr->qp_state : cur_state; + + if (!ib_modify_qp_is_ok(cur_state, new_state, qp_type(qp), mask)) + return -EINVAL; + + if (mask & IB_QP_STATE && cur_state == IB_QPS_SQD) { + if (qp->attr.sq_draining && new_state != IB_QPS_ERR) + return -EINVAL; + } + + return 0; } +static const char *const qps2str[] = { + [IB_QPS_RESET] = "RESET", + [IB_QPS_INIT] = "INIT", + [IB_QPS_RTR] = "RTR", + [IB_QPS_RTS] = "RTS", + [IB_QPS_SQD] = "SQD", + [IB_QPS_SQE] = "SQE", + [IB_QPS_ERR] = "ERR", +}; + /* called by the modify qp verb */ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, struct ib_udata *udata) { - enum ib_qp_state cur_state = (mask & IB_QP_CUR_STATE) ? - attr->cur_qp_state : qp->attr.qp_state; int err; + if (mask & IB_QP_CUR_STATE) + qp->attr.cur_qp_state = attr->qp_state; + + if (mask & IB_QP_STATE) { + spin_lock_bh(&qp->state_lock); + err = __qp_chk_state(qp, attr, mask); + if (!err) { + qp->attr.qp_state = attr->qp_state; + rxe_dbg_qp(qp, "state -> %s\n", + qps2str[attr->qp_state]); + } + spin_unlock_bh(&qp->state_lock); + + if (err) + return err; + + switch (attr->qp_state) { + case IB_QPS_RESET: + rxe_qp_reset(qp); + break; + case IB_QPS_SQD: + rxe_qp_sqd(qp, attr, mask); + break; + case IB_QPS_ERR: + rxe_qp_error(qp); + break; + default: + break; + } + } + if (mask & IB_QP_MAX_QP_RD_ATOMIC) { int max_rd_atomic = attr->max_rd_atomic ? roundup_pow_of_two(attr->max_rd_atomic) : 0; @@ -545,9 +603,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, return err; } - if (mask & IB_QP_CUR_STATE) - qp->attr.cur_qp_state = attr->qp_state; - if (mask & IB_QP_EN_SQD_ASYNC_NOTIFY) qp->attr.en_sqd_async_notify = attr->en_sqd_async_notify; @@ -627,48 +682,6 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, if (mask & IB_QP_DEST_QPN) qp->attr.dest_qp_num = attr->dest_qp_num; - if (mask & IB_QP_STATE) { - qp->attr.qp_state = attr->qp_state; - - switch (attr->qp_state) { - case IB_QPS_RESET: - rxe_dbg_qp(qp, "state -> RESET\n"); - rxe_qp_reset(qp); - break; - - case IB_QPS_INIT: - rxe_dbg_qp(qp, "state -> INIT\n"); - break; - - case IB_QPS_RTR: - rxe_dbg_qp(qp, "state -> RTR\n"); - break; - - case IB_QPS_RTS: - rxe_dbg_qp(qp, "state -> RTS\n"); - break; - - case IB_QPS_SQD: - rxe_dbg_qp(qp, "state -> SQD\n"); - if (cur_state != IB_QPS_SQD) { - qp->attr.sq_draining = 1; - rxe_sched_task(&qp->comp.task); - rxe_sched_task(&qp->req.task); - } - break; - - case IB_QPS_SQE: - rxe_dbg_qp(qp, "state -> SQE !!?\n"); - /* Not possible from modify_qp. */ - break; - - case IB_QPS_ERR: - rxe_dbg_qp(qp, "state -> ERR\n"); - rxe_qp_error(qp); - break; - } - } - return 0; } @@ -695,10 +708,12 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) /* Applications that get this state typically spin on it. * Yield the processor */ - if (qp->attr.sq_draining) + spin_lock_bh(&qp->state_lock); + if (qp->attr.sq_draining) { + spin_unlock_bh(&qp->state_lock); cond_resched(); - - rxe_dbg_qp(qp, "attr->sq_draining = %d\n", attr->sq_draining); + } + spin_unlock_bh(&qp->state_lock); return 0; } @@ -722,7 +737,9 @@ static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); + spin_lock_bh(&qp->state_lock); qp->valid = 0; + spin_unlock_bh(&qp->state_lock); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index ca17ac6c5878..2f953cc74256 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -38,13 +38,19 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EINVAL; } + spin_lock_bh(&qp->state_lock); if (pkt->mask & RXE_REQ_MASK) { - if (unlikely(qp_state(qp) < IB_QPS_RTR)) + if (unlikely(qp_state(qp) < IB_QPS_RTR)) { + spin_unlock_bh(&qp->state_lock); return -EINVAL; + } } else { - if (unlikely(qp_state(qp) < IB_QPS_RTS)) + if (unlikely(qp_state(qp) < IB_QPS_RTS)) { + spin_unlock_bh(&qp->state_lock); return -EINVAL; + } } + spin_unlock_bh(&qp->state_lock); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index f329038efbc8..8e50d116d273 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -102,24 +102,33 @@ void rnr_nak_timer(struct timer_list *t) rxe_dbg_qp(qp, "nak timer fired\n"); - /* request a send queue retry */ - qp->req.need_retry = 1; - qp->req.wait_for_rnr_timer = 0; - rxe_sched_task(&qp->req.task); + spin_lock_bh(&qp->state_lock); + if (qp->valid) { + /* request a send queue retry */ + qp->req.need_retry = 1; + qp->req.wait_for_rnr_timer = 0; + rxe_sched_task(&qp->req.task); + } + spin_unlock_bh(&qp->state_lock); } static void req_check_sq_drain_done(struct rxe_qp *qp) { - struct rxe_queue *q = qp->sq.queue; - unsigned int index = qp->req.wqe_index; - unsigned int cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); - struct rxe_send_wqe *wqe = queue_addr_from_index(q, cons); + struct rxe_queue *q; + unsigned int index; + unsigned int cons; + struct rxe_send_wqe *wqe; + + spin_lock_bh(&qp->state_lock); + if (qp_state(qp) == IB_QPS_SQD) { + q = qp->sq.queue; + index = qp->req.wqe_index; + cons = queue_get_consumer(q, QUEUE_TYPE_FROM_CLIENT); + wqe = queue_addr_from_index(q, cons); - if (unlikely(qp_state(qp) == IB_QPS_SQD)) { /* check to see if we are drained; * state_lock used by requester and completer */ - spin_lock_bh(&qp->state_lock); do { if (!qp->attr.sq_draining) /* comp just finished */ @@ -144,28 +153,40 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) } return; } while (0); - spin_unlock_bh(&qp->state_lock); } + spin_unlock_bh(&qp->state_lock); } -static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) +static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) { - struct rxe_send_wqe *wqe; struct rxe_queue *q = qp->sq.queue; unsigned int index = qp->req.wqe_index; unsigned int prod; - req_check_sq_drain_done(qp); - prod = queue_get_producer(q, QUEUE_TYPE_FROM_CLIENT); if (index == prod) return NULL; + else + return queue_addr_from_index(q, index); +} - wqe = queue_addr_from_index(q, index); +static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) +{ + struct rxe_send_wqe *wqe; + + req_check_sq_drain_done(qp); + + wqe = __req_next_wqe(qp); + if (wqe == NULL) + return NULL; + spin_lock(&qp->state_lock); if (unlikely((qp_state(qp) == IB_QPS_SQD) && - (wqe->state != wqe_state_processing))) + (wqe->state != wqe_state_processing))) { + spin_unlock(&qp->state_lock); return NULL; + } + spin_unlock(&qp->state_lock); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; @@ -656,15 +677,16 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_ah *ah; struct rxe_av *av; - if (unlikely(!qp->valid)) + spin_lock_bh(&qp->state_lock); + if (unlikely(!qp->valid)) { + spin_unlock_bh(&qp->state_lock); goto exit; + } if (unlikely(qp_state(qp) == IB_QPS_ERR)) { - wqe = req_next_wqe(qp); + wqe = __req_next_wqe(qp); + spin_unlock_bh(&qp->state_lock); if (wqe) - /* - * Generate an error completion for error qp state - */ goto err; else goto exit; @@ -678,8 +700,10 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; + spin_unlock_bh(&qp->state_lock); goto exit; } + spin_unlock_bh(&qp->state_lock); /* we come here if the retransmit timer has fired * or if the rnr timer has fired. If the retransmit @@ -839,8 +863,7 @@ int rxe_requester(struct rxe_qp *qp) /* update wqe_index for each wqe completion */ qp->req.wqe_index = queue_next_index(qp->sq.queue, qp->req.wqe_index); wqe->state = wqe_state_error; - qp->attr.qp_state = IB_QPS_ERR; - rxe_sched_task(&qp->comp.task); + rxe_qp_error(qp); exit: ret = -EAGAIN; out: diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 67eac616235c..68f6cd188d8e 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1137,8 +1137,13 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - if (unlikely(qp_state(qp) == IB_QPS_ERR)) + spin_lock_bh(&qp->state_lock); + if (unlikely(qp_state(qp) == IB_QPS_ERR)) { + spin_unlock_bh(&qp->state_lock); return RESPST_CHK_RESOURCE; + } + spin_unlock_bh(&qp->state_lock); + if (unlikely(!pkt)) return RESPST_DONE; if (qp_type(qp) == IB_QPT_RC) @@ -1464,14 +1469,17 @@ int rxe_responder(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; int ret; + spin_lock_bh(&qp->state_lock); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || - qp_state(qp) == IB_QPS_RESET) { + qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); + spin_unlock_bh(&qp->state_lock); goto exit; } + spin_unlock_bh(&qp->state_lock); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 6d97c7093ae6..dea605b7f683 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -660,42 +660,70 @@ static int rxe_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) } /* send wr */ + +/* sanity check incoming send work request */ static int validate_send_wr(struct rxe_qp *qp, const struct ib_send_wr *ibwr, - unsigned int mask, unsigned int length) + unsigned int *maskp, unsigned int *lengthp) { int num_sge = ibwr->num_sge; struct rxe_sq *sq = &qp->sq; + unsigned int mask = 0; + unsigned long length = 0; + int err = -EINVAL; + int i; - if (unlikely(num_sge > sq->max_sge)) { - rxe_dbg_qp(qp, "num_sge > max_sge"); - goto err_out; - } + do { + mask = wr_opcode_mask(ibwr->opcode, qp); + if (!mask) { + rxe_err_qp(qp, "bad wr opcode for qp type"); + break; + } - if (unlikely(mask & WR_ATOMIC_MASK)) { - if (length != 8) { - rxe_dbg_qp(qp, "atomic length != 8"); - goto err_out; + if (num_sge > sq->max_sge) { + rxe_err_qp(qp, "num_sge > max_sge"); + break; } - if (atomic_wr(ibwr)->remote_addr & 0x7) { - rxe_dbg_qp(qp, "misaligned atomic address"); - goto err_out; + length = 0; + for (i = 0; i < ibwr->num_sge; i++) + length += ibwr->sg_list[i].length; + + if (length > (1UL << 31)) { + rxe_err_qp(qp, "message length too long"); + break; } - } - if (unlikely((ibwr->send_flags & IB_SEND_INLINE) && - (length > sq->max_inline))) { - rxe_dbg_qp(qp, "inline length too big"); - goto err_out; - } + if (mask & WR_ATOMIC_MASK) { + if (length != 8) { + rxe_err_qp(qp, "atomic length != 8"); + break; + } + if (atomic_wr(ibwr)->remote_addr & 0x7) { + rxe_err_qp(qp, "misaligned atomic address"); + break; + } + } + if (ibwr->send_flags & IB_SEND_INLINE) { + if (!(mask & WR_INLINE_MASK)) { + rxe_err_qp(qp, "opcode doesn't support inline data"); + break; + } + if (length > sq->max_inline) { + rxe_err_qp(qp, "inline length too big"); + break; + } + } - return 0; + err = 0; + } while (0); -err_out: - return -EINVAL; + *maskp = mask; + *lengthp = (int)length; + + return err; } -static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, +static int init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, const struct ib_send_wr *ibwr) { wr->wr_id = ibwr->wr_id; @@ -711,8 +739,18 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, wr->wr.ud.ah_num = to_rah(ibah)->ah_num; if (qp_type(qp) == IB_QPT_GSI) wr->wr.ud.pkey_index = ud_wr(ibwr)->pkey_index; - if (wr->opcode == IB_WR_SEND_WITH_IMM) + + switch (wr->opcode) { + case IB_WR_SEND_WITH_IMM: wr->ex.imm_data = ibwr->ex.imm_data; + break; + case IB_WR_SEND: + break; + default: + rxe_err_qp(qp, "bad wr opcode %d for UD/GSI QP", + wr->opcode); + return -EINVAL; + } } else { switch (wr->opcode) { case IB_WR_RDMA_WRITE_WITH_IMM: @@ -729,6 +767,11 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, case IB_WR_SEND_WITH_INV: wr->ex.invalidate_rkey = ibwr->ex.invalidate_rkey; break; + case IB_WR_RDMA_READ_WITH_INV: + wr->ex.invalidate_rkey = ibwr->ex.invalidate_rkey; + wr->wr.rdma.remote_addr = rdma_wr(ibwr)->remote_addr; + wr->wr.rdma.rkey = rdma_wr(ibwr)->rkey; + break; case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: wr->wr.atomic.remote_addr = @@ -746,10 +789,20 @@ static void init_send_wr(struct rxe_qp *qp, struct rxe_send_wr *wr, wr->wr.reg.key = reg_wr(ibwr)->key; wr->wr.reg.access = reg_wr(ibwr)->access; break; + case IB_WR_SEND: + case IB_WR_BIND_MW: + case IB_WR_FLUSH: + case IB_WR_ATOMIC_WRITE: + break; default: + rxe_err_qp(qp, "unsupported wr opcode %d", + wr->opcode); + return -EINVAL; break; } } + + return 0; } static void copy_inline_data_to_wqe(struct rxe_send_wqe *wqe, @@ -765,19 +818,22 @@ static void copy_inline_data_to_wqe(struct rxe_send_wqe *wqe, } } -static void init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr, +static int init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr, unsigned int mask, unsigned int length, struct rxe_send_wqe *wqe) { int num_sge = ibwr->num_sge; + int err; - init_send_wr(qp, &wqe->wr, ibwr); + err = init_send_wr(qp, &wqe->wr, ibwr); + if (err) + return err; /* local operation */ if (unlikely(mask & WR_LOCAL_OP_MASK)) { wqe->mask = mask; wqe->state = wqe_state_posted; - return; + return 0; } if (unlikely(ibwr->send_flags & IB_SEND_INLINE)) @@ -796,93 +852,62 @@ static void init_send_wqe(struct rxe_qp *qp, const struct ib_send_wr *ibwr, wqe->dma.sge_offset = 0; wqe->state = wqe_state_posted; wqe->ssn = atomic_add_return(1, &qp->ssn); + + return 0; } -static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr, - unsigned int mask, u32 length) +static int post_one_send(struct rxe_qp *qp, const struct ib_send_wr *ibwr) { int err; struct rxe_sq *sq = &qp->sq; struct rxe_send_wqe *send_wqe; - unsigned long flags; + unsigned int mask; + unsigned int length; int full; - err = validate_send_wr(qp, ibwr, mask, length); + err = validate_send_wr(qp, ibwr, &mask, &length); if (err) return err; - spin_lock_irqsave(&qp->sq.sq_lock, flags); - full = queue_full(sq->queue, QUEUE_TYPE_FROM_ULP); if (unlikely(full)) { - spin_unlock_irqrestore(&qp->sq.sq_lock, flags); - rxe_dbg_qp(qp, "queue full"); + rxe_err_qp(qp, "send queue full"); return -ENOMEM; } send_wqe = queue_producer_addr(sq->queue, QUEUE_TYPE_FROM_ULP); - init_send_wqe(qp, ibwr, mask, length, send_wqe); - - queue_advance_producer(sq->queue, QUEUE_TYPE_FROM_ULP); - - spin_unlock_irqrestore(&qp->sq.sq_lock, flags); + err = init_send_wqe(qp, ibwr, mask, length, send_wqe); + if (!err) + queue_advance_producer(sq->queue, QUEUE_TYPE_FROM_ULP); - return 0; + return err; } -static int rxe_post_send_kernel(struct rxe_qp *qp, const struct ib_send_wr *wr, +static int rxe_post_send_kernel(struct rxe_qp *qp, + const struct ib_send_wr *ibwr, const struct ib_send_wr **bad_wr) { int err = 0; - unsigned int mask; - unsigned int length = 0; - int i; - struct ib_send_wr *next; - - while (wr) { - mask = wr_opcode_mask(wr->opcode, qp); - if (unlikely(!mask)) { - rxe_dbg_qp(qp, "bad wr opcode for qp"); - err = -EINVAL; - *bad_wr = wr; - break; - } - - if (unlikely((wr->send_flags & IB_SEND_INLINE) && - !(mask & WR_INLINE_MASK))) { - rxe_dbg_qp(qp, "opcode doesn't support inline data"); - err = -EINVAL; - *bad_wr = wr; - break; - } - - next = wr->next; - - length = 0; - for (i = 0; i < wr->num_sge; i++) - length += wr->sg_list[i].length; - if (length > 1<<31) { - err = -EINVAL; - rxe_dbg_qp(qp, "message length too long"); - *bad_wr = wr; - break; - } + unsigned long flags; - err = post_one_send(qp, wr, mask, length); + spin_lock_irqsave(&qp->sq.sq_lock, flags); + while (ibwr) { + err = post_one_send(qp, ibwr); if (err) { - *bad_wr = wr; + *bad_wr = ibwr; break; } - - wr = next; + ibwr = ibwr->next; } + spin_unlock_irqrestore(&qp->sq.sq_lock, flags); - /* if we didn't post anything there's nothing to do */ if (!err) rxe_sched_task(&qp->req.task); - if (unlikely(qp_state(qp) == IB_QPS_ERR)) + spin_lock_bh(&qp->state_lock); + if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->comp.task); + spin_unlock_bh(&qp->state_lock); return err; } @@ -893,19 +918,21 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, struct rxe_qp *qp = to_rqp(ibqp); int err; - if (unlikely(!qp->valid)) { - *bad_wr = wr; - err = -EINVAL; - rxe_dbg_qp(qp, "qp destroyed"); - goto err_out; + spin_lock_bh(&qp->state_lock); + /* caller has already called destroy_qp */ + if (WARN_ON_ONCE(!qp->valid)) { + spin_unlock_bh(&qp->state_lock); + rxe_err_qp(qp, "qp has been destroyed"); + return -EINVAL; } if (unlikely(qp_state(qp) < IB_QPS_RTS)) { + spin_unlock_bh(&qp->state_lock); *bad_wr = wr; - err = -EINVAL; - rxe_dbg_qp(qp, "qp not ready to send"); - goto err_out; + rxe_err_qp(qp, "qp not ready to send"); + return -EINVAL; } + spin_unlock_bh(&qp->state_lock); if (qp->is_user) { /* Utilize process context to do protocol processing */ @@ -913,14 +940,10 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, } else { err = rxe_post_send_kernel(qp, wr, bad_wr); if (err) - goto err_out; + return err; } return 0; - -err_out: - rxe_err_qp(qp, "returned err = %d", err); - return err; } /* recv wr */ @@ -985,18 +1008,27 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, struct rxe_rq *rq = &qp->rq; unsigned long flags; - if (unlikely((qp_state(qp) < IB_QPS_INIT) || !qp->valid)) { + spin_lock_bh(&qp->state_lock); + /* caller has already called destroy_qp */ + if (WARN_ON_ONCE(!qp->valid)) { + spin_unlock_bh(&qp->state_lock); + rxe_err_qp(qp, "qp has been destroyed"); + return -EINVAL; + } + + /* see C10-97.2.1 */ + if (unlikely((qp_state(qp) < IB_QPS_INIT))) { + spin_unlock_bh(&qp->state_lock); *bad_wr = wr; - err = -EINVAL; - rxe_dbg_qp(qp, "qp destroyed or not ready to post recv"); - goto err_out; + rxe_dbg_qp(qp, "qp not ready to post recv"); + return -EINVAL; } + spin_unlock_bh(&qp->state_lock); if (unlikely(qp->srq)) { *bad_wr = wr; - err = -EINVAL; - rxe_dbg_qp(qp, "use post_srq_recv instead"); - goto err_out; + rxe_dbg_qp(qp, "qp has srq, use post_srq_recv instead"); + return -EINVAL; } spin_lock_irqsave(&rq->producer_lock, flags); @@ -1012,12 +1044,10 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); + spin_lock_bh(&qp->state_lock); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); - -err_out: - if (err) - rxe_err_qp(qp, "returned err = %d", err); + spin_unlock_bh(&qp->state_lock); return err; } -- GitLab From 491b13c46d4165eacc294b880f388e00ed85e5aa Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 17 Apr 2023 16:28:28 -0300 Subject: [PATCH 3141/5631] perf cpumap: Use perf_cpu_map__cpu(map, cpu) instead of accessing map->map[cpu] directly So that we can validate the 'map' instance wrt refcount checking. Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-3-irogers@google.com [ Extracted from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 7008705d745c..240557de129e 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -582,26 +582,26 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size) bool last = i == perf_cpu_map__nr(map); if (!last) - cpu = map->map[i]; + cpu = perf_cpu_map__cpu(map, i); if (start == -1) { start = i; if (last) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[i].cpu); + perf_cpu_map__cpu(map, i).cpu); } - } else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) { + } else if (((i - start) != (cpu.cpu - perf_cpu_map__cpu(map, start).cpu)) || last) { int end = i - 1; if (start == end) { ret += snprintf(buf + ret, size - ret, "%s%d", COMMA, - map->map[start].cpu); + perf_cpu_map__cpu(map, start).cpu); } else { ret += snprintf(buf + ret, size - ret, "%s%d-%d", COMMA, - map->map[start].cpu, map->map[end].cpu); + perf_cpu_map__cpu(map, start).cpu, perf_cpu_map__cpu(map, end).cpu); } first = false; start = i; -- GitLab From da885a0e5e0610e011f14a70c2dc7c4ddf79c6d6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 17 Apr 2023 16:50:02 -0300 Subject: [PATCH 3142/5631] perf cpumap: Add reference count checking Enabled when REFCNT_CHECKING is defined. The change adds a memory allocated pointer that is interposed between the reference counted cpu map at a get and freed by a put. The pointer replaces the original perf_cpu_map struct, so use of the perf_cpu_map via APIs remains unchanged. Any use of the cpu map without the API requires two versions, handled via the RC_CHK_ACCESS macro. This change is intended to catch: - use after put: using a cpumap after you have put it will cause a segv. - unbalanced puts: two puts for a get will result in a double free that can be captured and reported by tools like address sanitizer, including with the associated stack traces of allocation and frees. - missing puts: if a put is missing then the get turns into a memory leak that can be reported by leak sanitizer, including the stack trace at the point the get occurs. Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Alexey Bayduraev Cc: Andi Kleen Cc: Andrew Morton Cc: Andy Shevchenko Cc: Darren Hart Cc: Davidlohr Bueso Cc: Dmitriy Vyukov Cc: Eric Dumazet Cc: German Gomez Cc: Hao Luo Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Leo Yan Cc: Madhavan Srinivasan Cc: Mark Rutland Cc: Masami Hiramatsu Cc: Miaoqian Lin Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Riccardo Mancini Cc: Shunsuke Nakamura Cc: Song Liu Cc: Stephen Brennan Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Thomas Richter , Cc: Yury Norov Link: https://lore.kernel.org/lkml/20230407230405.2931830-3-irogers@google.com [ Extracted from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/Makefile | 2 +- tools/lib/perf/cpumap.c | 85 +++++++++++++----------- tools/lib/perf/include/internal/cpumap.h | 5 +- tools/perf/util/cpumap.c | 12 ++-- tools/perf/util/pmu.c | 4 +- 5 files changed, 58 insertions(+), 50 deletions(-) diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile index d8cad124e4c5..3a9b2140aa04 100644 --- a/tools/lib/perf/Makefile +++ b/tools/lib/perf/Makefile @@ -188,7 +188,7 @@ install_lib: libs cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ) HDRS := bpf_perf.h core.h cpumap.h threadmap.h evlist.h evsel.h event.h mmap.h -INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h threadmap.h xyarray.h +INTERNAL_HDRS := cpumap.h evlist.h evsel.h lib.h mmap.h rc_check.h threadmap.h xyarray.h INSTALL_HDRS_PFX := $(DESTDIR)$(prefix)/include/perf INSTALL_HDRS := $(addprefix $(INSTALL_HDRS_PFX)/, $(HDRS)) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index 27c3e73c6db2..1229b18bcdb1 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -12,19 +12,19 @@ void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus) { - map->nr = nr_cpus; + RC_CHK_ACCESS(map)->nr = nr_cpus; } struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) { - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); + RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); + struct perf_cpu_map *result; - if (cpus != NULL) { + if (ADD_RC_CHK(result, cpus)) { cpus->nr = nr_cpus; refcount_set(&cpus->refcnt, 1); - } - return cpus; + return result; } struct perf_cpu_map *perf_cpu_map__dummy_new(void) @@ -32,7 +32,7 @@ struct perf_cpu_map *perf_cpu_map__dummy_new(void) struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); if (cpus) - cpus->map[0].cpu = -1; + RC_CHK_ACCESS(cpus)->map[0].cpu = -1; return cpus; } @@ -42,21 +42,28 @@ static void cpu_map__delete(struct perf_cpu_map *map) if (map) { WARN_ONCE(refcount_read(perf_cpu_map__refcnt(map)) != 0, "cpu_map refcnt unbalanced\n"); - free(map); + RC_CHK_FREE(map); } } struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map) { - if (map) + struct perf_cpu_map *result; + + if (RC_CHK_GET(result, map)) refcount_inc(perf_cpu_map__refcnt(map)); - return map; + + return result; } void perf_cpu_map__put(struct perf_cpu_map *map) { - if (map && refcount_dec_and_test(perf_cpu_map__refcnt(map))) - cpu_map__delete(map); + if (map) { + if (refcount_dec_and_test(perf_cpu_map__refcnt(map))) + cpu_map__delete(map); + else + RC_CHK_PUT(map); + } } static struct perf_cpu_map *cpu_map__default_new(void) @@ -73,7 +80,7 @@ static struct perf_cpu_map *cpu_map__default_new(void) int i; for (i = 0; i < nr_cpus; ++i) - cpus->map[i].cpu = i; + RC_CHK_ACCESS(cpus)->map[i].cpu = i; } return cpus; @@ -99,15 +106,15 @@ static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu int i, j; if (cpus != NULL) { - memcpy(cpus->map, tmp_cpus, payload_size); - qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); + memcpy(RC_CHK_ACCESS(cpus)->map, tmp_cpus, payload_size); + qsort(RC_CHK_ACCESS(cpus)->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); /* Remove dups */ j = 0; for (i = 0; i < nr_cpus; i++) { - if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu) - cpus->map[j++].cpu = cpus->map[i].cpu; + if (i == 0 || RC_CHK_ACCESS(cpus)->map[i].cpu != RC_CHK_ACCESS(cpus)->map[i - 1].cpu) + RC_CHK_ACCESS(cpus)->map[j++].cpu = RC_CHK_ACCESS(cpus)->map[i].cpu; } - cpus->nr = j; + perf_cpu_map__set_nr(cpus, j); assert(j <= nr_cpus); } return cpus; @@ -268,20 +275,20 @@ struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) .cpu = -1 }; - if (cpus && idx < cpus->nr) - return cpus->map[idx]; + if (cpus && idx < RC_CHK_ACCESS(cpus)->nr) + return RC_CHK_ACCESS(cpus)->map[idx]; return result; } int perf_cpu_map__nr(const struct perf_cpu_map *cpus) { - return cpus ? cpus->nr : 1; + return cpus ? RC_CHK_ACCESS(cpus)->nr : 1; } bool perf_cpu_map__empty(const struct perf_cpu_map *map) { - return map ? map->map[0].cpu == -1 : true; + return map ? RC_CHK_ACCESS(map)->map[0].cpu == -1 : true; } int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) @@ -292,10 +299,10 @@ int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) return -1; low = 0; - high = cpus->nr; + high = RC_CHK_ACCESS(cpus)->nr; while (low < high) { int idx = (low + high) / 2; - struct perf_cpu cpu_at_idx = cpus->map[idx]; + struct perf_cpu cpu_at_idx = RC_CHK_ACCESS(cpus)->map[idx]; if (cpu_at_idx.cpu == cpu.cpu) return idx; @@ -321,7 +328,7 @@ struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) }; // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return map->nr > 0 ? map->map[map->nr - 1] : result; + return RC_CHK_ACCESS(map)->nr > 0 ? RC_CHK_ACCESS(map)->map[RC_CHK_ACCESS(map)->nr - 1] : result; } /** Is 'b' a subset of 'a'. */ @@ -329,15 +336,15 @@ bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu { if (a == b || !b) return true; - if (!a || b->nr > a->nr) + if (!a || RC_CHK_ACCESS(b)->nr > RC_CHK_ACCESS(a)->nr) return false; - for (int i = 0, j = 0; i < a->nr; i++) { - if (a->map[i].cpu > b->map[j].cpu) + for (int i = 0, j = 0; i < RC_CHK_ACCESS(a)->nr; i++) { + if (RC_CHK_ACCESS(a)->map[i].cpu > RC_CHK_ACCESS(b)->map[j].cpu) return false; - if (a->map[i].cpu == b->map[j].cpu) { + if (RC_CHK_ACCESS(a)->map[i].cpu == RC_CHK_ACCESS(b)->map[j].cpu) { j++; - if (j == b->nr) + if (j == RC_CHK_ACCESS(b)->nr) return true; } } @@ -367,27 +374,27 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, return perf_cpu_map__get(other); } - tmp_len = orig->nr + other->nr; + tmp_len = RC_CHK_ACCESS(orig)->nr + RC_CHK_ACCESS(other)->nr; tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) return NULL; /* Standard merge algorithm from wikipedia */ i = j = k = 0; - while (i < orig->nr && j < other->nr) { - if (orig->map[i].cpu <= other->map[j].cpu) { - if (orig->map[i].cpu == other->map[j].cpu) + while (i < RC_CHK_ACCESS(orig)->nr && j < RC_CHK_ACCESS(other)->nr) { + if (RC_CHK_ACCESS(orig)->map[i].cpu <= RC_CHK_ACCESS(other)->map[j].cpu) { + if (RC_CHK_ACCESS(orig)->map[i].cpu == RC_CHK_ACCESS(other)->map[j].cpu) j++; - tmp_cpus[k++] = orig->map[i++]; + tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; } else - tmp_cpus[k++] = other->map[j++]; + tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; } - while (i < orig->nr) - tmp_cpus[k++] = orig->map[i++]; + while (i < RC_CHK_ACCESS(orig)->nr) + tmp_cpus[k++] = RC_CHK_ACCESS(orig)->map[i++]; - while (j < other->nr) - tmp_cpus[k++] = other->map[j++]; + while (j < RC_CHK_ACCESS(other)->nr) + tmp_cpus[k++] = RC_CHK_ACCESS(other)->map[j++]; assert(k <= tmp_len); merged = cpu_map__trim_new(k, tmp_cpus); diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 1e840dd53a11..49649eb51ce4 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -4,6 +4,7 @@ #include #include +#include /** * A sized, reference counted, sorted array of integers representing CPU @@ -12,7 +13,7 @@ * gaps if CPU numbers were used. For events associated with a pid, rather than * a CPU, a single dummy map with an entry of -1 is used. */ -struct perf_cpu_map { +DECLARE_RC_STRUCT(perf_cpu_map) { refcount_t refcnt; /** Length of the map array. */ int nr; @@ -32,6 +33,6 @@ void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus); static inline refcount_t *perf_cpu_map__refcnt(struct perf_cpu_map *map) { - return &map->refcnt; + return &RC_CHK_ACCESS(map)->refcnt; } #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 240557de129e..75d9c73e0184 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -77,9 +77,9 @@ static struct perf_cpu_map *cpu_map__from_entries(const struct perf_record_cpu_m * otherwise it would become 65535. */ if (data->cpus_data.cpu[i] == (u16) -1) - map->map[i].cpu = -1; + RC_CHK_ACCESS(map)->map[i].cpu = -1; else - map->map[i].cpu = (int) data->cpus_data.cpu[i]; + RC_CHK_ACCESS(map)->map[i].cpu = (int) data->cpus_data.cpu[i]; } } @@ -107,7 +107,7 @@ static struct perf_cpu_map *cpu_map__from_mask(const struct perf_record_cpu_map_ perf_record_cpu_map_data__read_one_mask(data, i, local_copy); for_each_set_bit(cpu, local_copy, 64) - map->map[j++].cpu = cpu + cpus_per_i; + RC_CHK_ACCESS(map)->map[j++].cpu = cpu + cpus_per_i; } return map; @@ -124,11 +124,11 @@ static struct perf_cpu_map *cpu_map__from_range(const struct perf_record_cpu_map return NULL; if (data->range_cpu_data.any_cpu) - map->map[i++].cpu = -1; + RC_CHK_ACCESS(map)->map[i++].cpu = -1; for (int cpu = data->range_cpu_data.start_cpu; cpu <= data->range_cpu_data.end_cpu; i++, cpu++) - map->map[i].cpu = cpu; + RC_CHK_ACCESS(map)->map[i].cpu = cpu; return map; } @@ -164,7 +164,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr) if (cpus != NULL) { for (int i = 0; i < nr; i++) - cpus->map[i].cpu = -1; + RC_CHK_ACCESS(cpus)->map[i].cpu = -1; } return cpus; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 760c848c9fa2..65d0eb9a740a 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -2015,9 +2015,9 @@ int perf_pmu__cpus_match(struct perf_pmu *pmu, struct perf_cpu_map *cpus, perf_cpu_map__for_each_cpu(cpu, i, cpus) { if (!perf_cpu_map__has(pmu_cpus, cpu)) - unmatched_cpus->map[unmatched_nr++] = cpu; + RC_CHK_ACCESS(unmatched_cpus)->map[unmatched_nr++] = cpu; else - matched_cpus->map[matched_nr++] = cpu; + RC_CHK_ACCESS(matched_cpus)->map[matched_nr++] = cpu; } perf_cpu_map__set_nr(unmatched_cpus, unmatched_nr); -- GitLab From 7031edac9dbc0f880c9fbaa40ca08b5de34239c6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 18:28:01 -0300 Subject: [PATCH 3143/5631] perf dso: Add dso__filename_with_chroot() to reduce number of accesses to dso->nsinfo members We'll need to reference count dso->nsinfo, so reduce the number of direct accesses by having a shorter form of obtaining a filename with a chroot (namespace one). Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/ZD26ZlqSbgSyH5lX@kernel.org [ Used nsinfo__pid(dso->nsinfo), as it was already present ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 4 +--- tools/perf/util/annotate.c | 3 +-- tools/perf/util/dso.c | 7 ++++++- tools/perf/util/dso.h | 2 ++ tools/perf/util/dsos.c | 3 +-- tools/perf/util/symbol.c | 3 +-- 6 files changed, 12 insertions(+), 10 deletions(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 76723ac314b6..61766eead4f4 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -630,10 +630,8 @@ static int dso__read_build_id(struct dso *dso) if (filename__read_build_id(dso->long_name, &dso->bid) > 0) dso->has_build_id = true; else if (dso->nsinfo) { - char *new_name; + char *new_name = dso__filename_with_chroot(dso, dso->long_name); - new_name = filename_with_chroot(dso->nsinfo->pid, - dso->long_name); if (new_name && filename__read_build_id(new_name, &dso->bid) > 0) dso->has_build_id = true; free(new_name); diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e2693a1c28d5..ca9f0add68f4 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -1692,8 +1692,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil mutex_lock(&dso->lock); if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) { - char *new_name = filename_with_chroot(dso->nsinfo->pid, - filename); + char *new_name = dso__filename_with_chroot(dso, filename); if (new_name) { strlcpy(filename, new_name, filename_size); free(new_name); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index e36b418df2c6..a86614599269 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -491,6 +491,11 @@ static int do_open(char *name) return -1; } +char *dso__filename_with_chroot(const struct dso *dso, const char *filename) +{ + return filename_with_chroot(nsinfo__pid(dso->nsinfo), filename); +} + static int __open_dso(struct dso *dso, struct machine *machine) { int fd = -EINVAL; @@ -515,7 +520,7 @@ static int __open_dso(struct dso *dso, struct machine *machine) if (errno != ENOENT || dso->nsinfo == NULL) goto out; - new_name = filename_with_chroot(dso->nsinfo->pid, name); + new_name = dso__filename_with_chroot(dso, name); if (!new_name) goto out; diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index 58d94175e714..0b7c7633b9f6 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -266,6 +266,8 @@ static inline bool dso__has_symbols(const struct dso *dso) return !RB_EMPTY_ROOT(&dso->symbols.rb_root); } +char *dso__filename_with_chroot(const struct dso *dso, const char *filename); + bool dso__sorted_by_name(const struct dso *dso); void dso__set_sorted_by_name(struct dso *dso); void dso__sort_by_name(struct dso *dso); diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c index 2bd23e4cf19e..cf80aa42dd07 100644 --- a/tools/perf/util/dsos.c +++ b/tools/perf/util/dsos.c @@ -91,8 +91,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits) have_build_id = true; pos->has_build_id = true; } else if (errno == ENOENT && pos->nsinfo) { - char *new_name = filename_with_chroot(pos->nsinfo->pid, - pos->long_name); + char *new_name = dso__filename_with_chroot(pos, pos->long_name); if (new_name && filename__read_build_id(new_name, &pos->bid) > 0) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 91ebf93e0c20..e7f63670688e 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1963,8 +1963,7 @@ int dso__load(struct dso *dso, struct map *map) is_reg = is_regular_file(name); if (!is_reg && errno == ENOENT && dso->nsinfo) { - char *new_name = filename_with_chroot(dso->nsinfo->pid, - name); + char *new_name = dso__filename_with_chroot(dso, name); if (new_name) { is_reg = is_regular_file(new_name); strlcpy(name, new_name, PATH_MAX); -- GitLab From c35ce1d918c12900375a60165c908de47856900d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 17 Apr 2023 18:51:57 -0300 Subject: [PATCH 3144/5631] perf namespaces: Add reference count checking Add reference count checking controlled by REFCNT_CHECKING ifdef. The reference count checking interposes an allocated pointer between the reference counted struct on a get and frees the pointer on a put. Accesses after a put cause faults and use after free, missed puts are caughts as leaks and double puts are double frees. This checking helped resolve a memory leak and use after free: https://lore.kernel.org/linux-perf-users/CAP-5=fWZH20L4kv-BwVtGLwR=Em3AOOT+Q4QGivvQuYn5AsPRg@mail.gmail.com/ Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-4-irogers@google.com [ Extracted from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/namespaces.c | 132 ++++++++++++++++++++--------------- tools/perf/util/namespaces.h | 3 +- 2 files changed, 78 insertions(+), 57 deletions(-) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index dd536220cdb9..8a3b7bd27b19 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -60,7 +60,7 @@ void namespaces__free(struct namespaces *namespaces) free(namespaces); } -static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path) +static int nsinfo__get_nspid(pid_t *tgid, pid_t *nstgid, bool *in_pidns, const char *path) { FILE *f = NULL; char *statln = NULL; @@ -74,19 +74,18 @@ static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path) while (getline(&statln, &linesz, f) != -1) { /* Use tgid if CONFIG_PID_NS is not defined. */ if (strstr(statln, "Tgid:") != NULL) { - nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'), - NULL, 10); - nsi->nstgid = nsinfo__tgid(nsi); + *tgid = (pid_t)strtol(strrchr(statln, '\t'), NULL, 10); + *nstgid = *tgid; } if (strstr(statln, "NStgid:") != NULL) { nspid = strrchr(statln, '\t'); - nsi->nstgid = (pid_t)strtol(nspid, NULL, 10); + *nstgid = (pid_t)strtol(nspid, NULL, 10); /* * If innermost tgid is not the first, process is in a different * PID namespace. */ - nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; + *in_pidns = (statln + sizeof("NStgid:") - 1) != nspid; break; } } @@ -121,8 +120,8 @@ int nsinfo__init(struct nsinfo *nsi) * want to switch as part of looking up dso/map data. */ if (old_stat.st_ino != new_stat.st_ino) { - nsi->need_setns = true; - nsi->mntns_path = newns; + RC_CHK_ACCESS(nsi)->need_setns = true; + RC_CHK_ACCESS(nsi)->mntns_path = newns; newns = NULL; } @@ -132,13 +131,26 @@ int nsinfo__init(struct nsinfo *nsi) if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsinfo__pid(nsi)) >= PATH_MAX) goto out; - rv = nsinfo__get_nspid(nsi, spath); + rv = nsinfo__get_nspid(&RC_CHK_ACCESS(nsi)->tgid, &RC_CHK_ACCESS(nsi)->nstgid, + &RC_CHK_ACCESS(nsi)->in_pidns, spath); out: free(newns); return rv; } +static struct nsinfo *nsinfo__alloc(void) +{ + struct nsinfo *res; + RC_STRUCT(nsinfo) *nsi; + + nsi = calloc(1, sizeof(*nsi)); + if (ADD_RC_CHK(res, nsi)) + refcount_set(&nsi->refcnt, 1); + + return res; +} + struct nsinfo *nsinfo__new(pid_t pid) { struct nsinfo *nsi; @@ -146,22 +158,21 @@ struct nsinfo *nsinfo__new(pid_t pid) if (pid == 0) return NULL; - nsi = calloc(1, sizeof(*nsi)); - if (nsi != NULL) { - nsi->pid = pid; - nsi->tgid = pid; - nsi->nstgid = pid; - nsi->need_setns = false; - nsi->in_pidns = false; - /* Init may fail if the process exits while we're trying to look - * at its proc information. In that case, save the pid but - * don't try to enter the namespace. - */ - if (nsinfo__init(nsi) == -1) - nsi->need_setns = false; + nsi = nsinfo__alloc(); + if (!nsi) + return NULL; - refcount_set(&nsi->refcnt, 1); - } + RC_CHK_ACCESS(nsi)->pid = pid; + RC_CHK_ACCESS(nsi)->tgid = pid; + RC_CHK_ACCESS(nsi)->nstgid = pid; + RC_CHK_ACCESS(nsi)->need_setns = false; + RC_CHK_ACCESS(nsi)->in_pidns = false; + /* Init may fail if the process exits while we're trying to look at its + * proc information. In that case, save the pid but don't try to enter + * the namespace. + */ + if (nsinfo__init(nsi) == -1) + RC_CHK_ACCESS(nsi)->need_setns = false; return nsi; } @@ -173,21 +184,21 @@ struct nsinfo *nsinfo__copy(const struct nsinfo *nsi) if (nsi == NULL) return NULL; - nnsi = calloc(1, sizeof(*nnsi)); - if (nnsi != NULL) { - nnsi->pid = nsinfo__pid(nsi); - nnsi->tgid = nsinfo__tgid(nsi); - nnsi->nstgid = nsinfo__nstgid(nsi); - nnsi->need_setns = nsinfo__need_setns(nsi); - nnsi->in_pidns = nsinfo__in_pidns(nsi); - if (nsi->mntns_path) { - nnsi->mntns_path = strdup(nsi->mntns_path); - if (!nnsi->mntns_path) { - free(nnsi); - return NULL; - } + nnsi = nsinfo__alloc(); + if (!nnsi) + return NULL; + + RC_CHK_ACCESS(nnsi)->pid = nsinfo__pid(nsi); + RC_CHK_ACCESS(nnsi)->tgid = nsinfo__tgid(nsi); + RC_CHK_ACCESS(nnsi)->nstgid = nsinfo__nstgid(nsi); + RC_CHK_ACCESS(nnsi)->need_setns = nsinfo__need_setns(nsi); + RC_CHK_ACCESS(nnsi)->in_pidns = nsinfo__in_pidns(nsi); + if (RC_CHK_ACCESS(nsi)->mntns_path) { + RC_CHK_ACCESS(nnsi)->mntns_path = strdup(RC_CHK_ACCESS(nsi)->mntns_path); + if (!RC_CHK_ACCESS(nnsi)->mntns_path) { + nsinfo__put(nnsi); + return NULL; } - refcount_set(&nnsi->refcnt, 1); } return nnsi; @@ -195,51 +206,60 @@ struct nsinfo *nsinfo__copy(const struct nsinfo *nsi) static void nsinfo__delete(struct nsinfo *nsi) { - zfree(&nsi->mntns_path); - free(nsi); + if (nsi) { + WARN_ONCE(refcount_read(&RC_CHK_ACCESS(nsi)->refcnt) != 0, + "nsinfo refcnt unbalanced\n"); + zfree(&RC_CHK_ACCESS(nsi)->mntns_path); + RC_CHK_FREE(nsi); + } } struct nsinfo *nsinfo__get(struct nsinfo *nsi) { - if (nsi) - refcount_inc(&nsi->refcnt); - return nsi; + struct nsinfo *result; + + if (RC_CHK_GET(result, nsi)) + refcount_inc(&RC_CHK_ACCESS(nsi)->refcnt); + + return result; } void nsinfo__put(struct nsinfo *nsi) { - if (nsi && refcount_dec_and_test(&nsi->refcnt)) + if (nsi && refcount_dec_and_test(&RC_CHK_ACCESS(nsi)->refcnt)) nsinfo__delete(nsi); + else + RC_CHK_PUT(nsi); } bool nsinfo__need_setns(const struct nsinfo *nsi) { - return nsi->need_setns; + return RC_CHK_ACCESS(nsi)->need_setns; } void nsinfo__clear_need_setns(struct nsinfo *nsi) { - nsi->need_setns = false; + RC_CHK_ACCESS(nsi)->need_setns = false; } pid_t nsinfo__tgid(const struct nsinfo *nsi) { - return nsi->tgid; + return RC_CHK_ACCESS(nsi)->tgid; } pid_t nsinfo__nstgid(const struct nsinfo *nsi) { - return nsi->nstgid; + return RC_CHK_ACCESS(nsi)->nstgid; } pid_t nsinfo__pid(const struct nsinfo *nsi) { - return nsi->pid; + return RC_CHK_ACCESS(nsi)->pid; } pid_t nsinfo__in_pidns(const struct nsinfo *nsi) { - return nsi->in_pidns; + return RC_CHK_ACCESS(nsi)->in_pidns; } void nsinfo__mountns_enter(struct nsinfo *nsi, @@ -256,7 +276,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, nc->oldns = -1; nc->newns = -1; - if (!nsi || !nsi->need_setns) + if (!nsi || !RC_CHK_ACCESS(nsi)->need_setns) return; if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) @@ -270,7 +290,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, if (oldns < 0) goto errout; - newns = open(nsi->mntns_path, O_RDONLY); + newns = open(RC_CHK_ACCESS(nsi)->mntns_path, O_RDONLY); if (newns < 0) goto errout; @@ -339,9 +359,9 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi) bool nsinfo__is_in_root_namespace(void) { - struct nsinfo nsi; + pid_t tgid = 0, nstgid = 0; + bool in_pidns = false; - memset(&nsi, 0x0, sizeof(nsi)); - nsinfo__get_nspid(&nsi, "/proc/self/status"); - return !nsi.in_pidns; + nsinfo__get_nspid(&tgid, &nstgid, &in_pidns, "/proc/self/status"); + return !in_pidns; } diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 567829262c42..8c0731c6cbb7 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -13,6 +13,7 @@ #include #include #include +#include #ifndef HAVE_SETNS_SUPPORT int setns(int fd, int nstype); @@ -29,7 +30,7 @@ struct namespaces { struct namespaces *namespaces__new(struct perf_record_namespaces *event); void namespaces__free(struct namespaces *namespaces); -struct nsinfo { +DECLARE_RC_STRUCT(nsinfo) { pid_t pid; pid_t tgid; pid_t nstgid; -- GitLab From 64042c28c3bb6729df8e2fda89bc7ebbe3790907 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Mon, 3 Apr 2023 21:32:49 +0200 Subject: [PATCH 3145/5631] clk: rockchip: rk3588: make gate linked clocks critical RK3588 has a couple of hardware blocks called Native Interface Unit (NIU) that gate the clocks to devices behind them. Effectively this means that some clocks require two parent clocks being enabled. Downstream implemented this by using a separate clock driver ("clk-link") for them, which enables the second clock using PM framework. In the upstream kernel we are currently missing support for the second parent. The information about it is in the GATE_LINK() macro as linkname, but that is not used. Thus the second parent clock is not properly enabled. So far this did not really matter, since these clocks are mostly required for the more advanced IP blocks, that are not yet supported upstream. As this is about to change we need a fix. There are three options available: 1. Properly implement support for having two parent clocks in the clock framework. 2. Mark the affected clocks CLK_IGNORE_UNUSED, so that they are not disabled. This wastes some power, but keeps the hack contained within the clock driver. Going from this to the first solution is easy once that has been implemented. 3. Enabling the extra clock in the consumer driver. This leaks some implementation details into DT. This patch implements the second option as an intermediate solution until the first one is available. I used an alias for CLK_IS_CRITICAL, so that it's easy to see which clocks are not really critical once the clock framework supports a better way to implement this. Tested-by: Vincent Legoll Signed-off-by: Sebastian Reichel Link: https://lore.kernel.org/r/20230403193250.108693-2-sebastian.reichel@collabora.com Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3588.c | 42 +++++++++++++++++++------------ 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3588.c b/drivers/clk/rockchip/clk-rk3588.c index b7ce3fbd6fa6..6994165e0395 100644 --- a/drivers/clk/rockchip/clk-rk3588.c +++ b/drivers/clk/rockchip/clk-rk3588.c @@ -13,15 +13,25 @@ #include "clk.h" /* - * GATE with additional linked clock. Downstream enables the linked clock - * (via runtime PM) whenever the gate is enabled. The downstream implementation - * does this via separate clock nodes for each of the linked gate clocks, - * which leaks parts of the clock tree into DT. It is unclear why this is - * actually needed and things work without it for simple use cases. Thus - * the linked clock is ignored for now. + * Recent Rockchip SoCs have a new hardware block called Native Interface + * Unit (NIU), which gates clocks to devices behind them. These effectively + * need two parent clocks. + * + * Downstream enables the linked clock via runtime PM whenever the gate is + * enabled. This implementation uses separate clock nodes for each of the + * linked gate clocks, which leaks parts of the clock tree into DT. + * + * The GATE_LINK macro instead takes the second parent via 'linkname', but + * ignores the information. Once the clock framework is ready to handle it, the + * information should be passed on here. But since these clocks are required to + * access multiple relevant IP blocks, such as PCIe or USB, we mark all linked + * clocks critical until a better solution is available. This will waste some + * power, but avoids leaking implementation details into DT or hanging the + * system. */ #define GATE_LINK(_id, cname, pname, linkname, f, o, b, gf) \ GATE(_id, cname, pname, f, o, b, gf) +#define RK3588_LINKED_CLK CLK_IS_CRITICAL #define RK3588_GRF_SOC_STATUS0 0x600 @@ -1446,7 +1456,7 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE_NODIV(HCLK_NVM_ROOT, "hclk_nvm_root", mux_200m_100m_50m_24m_p, 0, RK3588_CLKSEL_CON(77), 0, 2, MFLAGS, RK3588_CLKGATE_CON(31), 0, GFLAGS), - COMPOSITE(ACLK_NVM_ROOT, "aclk_nvm_root", gpll_cpll_p, 0, + COMPOSITE(ACLK_NVM_ROOT, "aclk_nvm_root", gpll_cpll_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(77), 7, 1, MFLAGS, 2, 5, DFLAGS, RK3588_CLKGATE_CON(31), 1, GFLAGS), GATE(ACLK_EMMC, "aclk_emmc", "aclk_nvm_root", 0, @@ -1675,13 +1685,13 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { RK3588_CLKGATE_CON(42), 9, GFLAGS), /* vdpu */ - COMPOSITE(ACLK_VDPU_ROOT, "aclk_vdpu_root", gpll_cpll_aupll_p, 0, + COMPOSITE(ACLK_VDPU_ROOT, "aclk_vdpu_root", gpll_cpll_aupll_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(98), 5, 2, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(44), 0, GFLAGS), COMPOSITE_NODIV(ACLK_VDPU_LOW_ROOT, "aclk_vdpu_low_root", mux_400m_200m_100m_24m_p, 0, RK3588_CLKSEL_CON(98), 7, 2, MFLAGS, RK3588_CLKGATE_CON(44), 1, GFLAGS), - COMPOSITE_NODIV(HCLK_VDPU_ROOT, "hclk_vdpu_root", mux_200m_100m_50m_24m_p, 0, + COMPOSITE_NODIV(HCLK_VDPU_ROOT, "hclk_vdpu_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(98), 9, 2, MFLAGS, RK3588_CLKGATE_CON(44), 2, GFLAGS), COMPOSITE(ACLK_JPEG_DECODER_ROOT, "aclk_jpeg_decoder_root", gpll_cpll_aupll_spll_p, 0, @@ -1732,9 +1742,9 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE(ACLK_RKVENC0_ROOT, "aclk_rkvenc0_root", gpll_cpll_npll_p, 0, RK3588_CLKSEL_CON(102), 7, 2, MFLAGS, 2, 5, DFLAGS, RK3588_CLKGATE_CON(47), 1, GFLAGS), - GATE(HCLK_RKVENC0, "hclk_rkvenc0", "hclk_rkvenc0_root", 0, + GATE(HCLK_RKVENC0, "hclk_rkvenc0", "hclk_rkvenc0_root", RK3588_LINKED_CLK, RK3588_CLKGATE_CON(47), 4, GFLAGS), - GATE(ACLK_RKVENC0, "aclk_rkvenc0", "aclk_rkvenc0_root", 0, + GATE(ACLK_RKVENC0, "aclk_rkvenc0", "aclk_rkvenc0_root", RK3588_LINKED_CLK, RK3588_CLKGATE_CON(47), 5, GFLAGS), COMPOSITE(CLK_RKVENC0_CORE, "clk_rkvenc0_core", gpll_cpll_aupll_npll_p, 0, RK3588_CLKSEL_CON(102), 14, 2, MFLAGS, 9, 5, DFLAGS, @@ -1744,10 +1754,10 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { RK3588_CLKGATE_CON(48), 6, GFLAGS), /* vi */ - COMPOSITE(ACLK_VI_ROOT, "aclk_vi_root", gpll_cpll_npll_aupll_spll_p, 0, + COMPOSITE(ACLK_VI_ROOT, "aclk_vi_root", gpll_cpll_npll_aupll_spll_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(106), 5, 3, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(49), 0, GFLAGS), - COMPOSITE_NODIV(HCLK_VI_ROOT, "hclk_vi_root", mux_200m_100m_50m_24m_p, 0, + COMPOSITE_NODIV(HCLK_VI_ROOT, "hclk_vi_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(106), 8, 2, MFLAGS, RK3588_CLKGATE_CON(49), 1, GFLAGS), COMPOSITE_NODIV(PCLK_VI_ROOT, "pclk_vi_root", mux_100m_50m_24m_p, 0, @@ -1919,10 +1929,10 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { COMPOSITE(ACLK_VOP_ROOT, "aclk_vop_root", gpll_cpll_dmyaupll_npll_spll_p, 0, RK3588_CLKSEL_CON(110), 5, 3, MFLAGS, 0, 5, DFLAGS, RK3588_CLKGATE_CON(52), 0, GFLAGS), - COMPOSITE_NODIV(ACLK_VOP_LOW_ROOT, "aclk_vop_low_root", mux_400m_200m_100m_24m_p, 0, + COMPOSITE_NODIV(ACLK_VOP_LOW_ROOT, "aclk_vop_low_root", mux_400m_200m_100m_24m_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(110), 8, 2, MFLAGS, RK3588_CLKGATE_CON(52), 1, GFLAGS), - COMPOSITE_NODIV(HCLK_VOP_ROOT, "hclk_vop_root", mux_200m_100m_50m_24m_p, 0, + COMPOSITE_NODIV(HCLK_VOP_ROOT, "hclk_vop_root", mux_200m_100m_50m_24m_p, RK3588_LINKED_CLK, RK3588_CLKSEL_CON(110), 10, 2, MFLAGS, RK3588_CLKGATE_CON(52), 2, GFLAGS), COMPOSITE_NODIV(PCLK_VOP_ROOT, "pclk_vop_root", mux_100m_50m_24m_p, 0, @@ -2425,7 +2435,7 @@ static struct rockchip_clk_branch rk3588_clk_branches[] __initdata = { GATE_LINK(ACLK_ISP1_PRE, "aclk_isp1_pre", "aclk_isp1_root", "aclk_vi_root", 0, RK3588_CLKGATE_CON(26), 6, GFLAGS), GATE_LINK(HCLK_ISP1_PRE, "hclk_isp1_pre", "hclk_isp1_root", "hclk_vi_root", 0, RK3588_CLKGATE_CON(26), 8, GFLAGS), - GATE_LINK(HCLK_NVM, "hclk_nvm", "hclk_nvm_root", "aclk_nvm_root", 0, RK3588_CLKGATE_CON(31), 2, GFLAGS), + GATE_LINK(HCLK_NVM, "hclk_nvm", "hclk_nvm_root", "aclk_nvm_root", RK3588_LINKED_CLK, RK3588_CLKGATE_CON(31), 2, GFLAGS), GATE_LINK(ACLK_USB, "aclk_usb", "aclk_usb_root", "aclk_vo1usb_top_root", 0, RK3588_CLKGATE_CON(42), 2, GFLAGS), GATE_LINK(HCLK_USB, "hclk_usb", "hclk_usb_root", "hclk_vo1usb_top_root", 0, RK3588_CLKGATE_CON(42), 3, GFLAGS), GATE_LINK(ACLK_JPEG_DECODER_PRE, "aclk_jpeg_decoder_pre", "aclk_jpeg_decoder_root", "aclk_vdpu_root", 0, RK3588_CLKGATE_CON(44), 7, GFLAGS), -- GitLab From c19d966e11c4521ef49c861a36aa29b5665fea76 Mon Sep 17 00:00:00 2001 From: Hal Feng Date: Mon, 17 Apr 2023 15:41:15 +0800 Subject: [PATCH 3146/5631] clk: starfive: Delete the redundant dev_set_drvdata() in JH7110 clock drivers The dev_set_drvdata() is no longer needed after we used a wrapper struct to get the data in auxiliary driver. Cc: Xingyu Wu Fixes: d1aae0663023 ("clk: starfive: Avoid casting iomem pointers") Signed-off-by: Hal Feng Link: https://lore.kernel.org/r/20230417074115.30786-3-hal.feng@starfivetech.com Signed-off-by: Stephen Boyd --- drivers/clk/starfive/clk-starfive-jh7110-aon.c | 2 -- drivers/clk/starfive/clk-starfive-jh7110-sys.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/drivers/clk/starfive/clk-starfive-jh7110-aon.c b/drivers/clk/starfive/clk-starfive-jh7110-aon.c index a2799fe8a234..62954eb7b50a 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-aon.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-aon.c @@ -83,8 +83,6 @@ static int jh7110_aoncrg_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - dev_set_drvdata(priv->dev, (void *)(&priv->base)); - for (idx = 0; idx < JH7110_AONCLK_END; idx++) { u32 max = jh7110_aonclk_data[idx].max; struct clk_parent_data parents[4] = {}; diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c index 851b93d0f371..e6031345ef05 100644 --- a/drivers/clk/starfive/clk-starfive-jh7110-sys.c +++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c @@ -402,8 +402,6 @@ static int __init jh7110_syscrg_probe(struct platform_device *pdev) if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - dev_set_drvdata(priv->dev, (void *)(&priv->base)); - /* * These PLL clocks are not actually fixed factor clocks and can be * controlled by the syscon registers of JH7110. They will be dropped -- GitLab From 4d623903f1ed63a06e469c4ce45231440d1be5b6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 22:11:58 -0300 Subject: [PATCH 3147/5631] perf namespaces: Use the need_setns() accessors instead of accessing ->need_setns directly This uses pre-existing accessors and reduces the use of RC_CHK_ACCESS(nsi). Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/namespaces.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 8a3b7bd27b19..214a8391e07c 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -165,14 +165,14 @@ struct nsinfo *nsinfo__new(pid_t pid) RC_CHK_ACCESS(nsi)->pid = pid; RC_CHK_ACCESS(nsi)->tgid = pid; RC_CHK_ACCESS(nsi)->nstgid = pid; - RC_CHK_ACCESS(nsi)->need_setns = false; + nsinfo__clear_need_setns(nsi); RC_CHK_ACCESS(nsi)->in_pidns = false; /* Init may fail if the process exits while we're trying to look at its * proc information. In that case, save the pid but don't try to enter * the namespace. */ if (nsinfo__init(nsi) == -1) - RC_CHK_ACCESS(nsi)->need_setns = false; + nsinfo__clear_need_setns(nsi); return nsi; } @@ -276,7 +276,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, nc->oldns = -1; nc->newns = -1; - if (!nsi || !RC_CHK_ACCESS(nsi)->need_setns) + if (!nsi || !nsinfo__need_setns(nsi)) return; if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) -- GitLab From f94c21dfd02e98aa0fcb9b453a1198e76ede60e7 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 22:11:58 -0300 Subject: [PATCH 3148/5631] perf namespaces: Introduce nsinfo__refcnt() accessor to avoid accessing ->refcnt directly To reduces the use of RC_CHK_ACCESS(nsi). Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/namespaces.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 214a8391e07c..2f9fb1e2769c 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -204,11 +204,15 @@ struct nsinfo *nsinfo__copy(const struct nsinfo *nsi) return nnsi; } +static refcount_t *nsinfo__refcnt(struct nsinfo *nsi) +{ + return &RC_CHK_ACCESS(nsi)->refcnt; +} + static void nsinfo__delete(struct nsinfo *nsi) { if (nsi) { - WARN_ONCE(refcount_read(&RC_CHK_ACCESS(nsi)->refcnt) != 0, - "nsinfo refcnt unbalanced\n"); + WARN_ONCE(refcount_read(nsinfo__refcnt(nsi)) != 0, "nsinfo refcnt unbalanced\n"); zfree(&RC_CHK_ACCESS(nsi)->mntns_path); RC_CHK_FREE(nsi); } @@ -219,14 +223,14 @@ struct nsinfo *nsinfo__get(struct nsinfo *nsi) struct nsinfo *result; if (RC_CHK_GET(result, nsi)) - refcount_inc(&RC_CHK_ACCESS(nsi)->refcnt); + refcount_inc(nsinfo__refcnt(nsi)); return result; } void nsinfo__put(struct nsinfo *nsi) { - if (nsi && refcount_dec_and_test(&RC_CHK_ACCESS(nsi)->refcnt)) + if (nsi && refcount_dec_and_test(nsinfo__refcnt(nsi))) nsinfo__delete(nsi); else RC_CHK_PUT(nsi); -- GitLab From 2d1acd3f10baed49329c1b201cafb060aeb377e0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 17 Apr 2023 22:11:58 -0300 Subject: [PATCH 3149/5631] perf namespaces: Introduce nsinfo__mntns_path() accessor to avoid accessing ->mntns_path directly To reduce the use of RC_CHK_ACCESS(nsi). Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/namespaces.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index 2f9fb1e2769c..cb185c5659d6 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -177,6 +177,11 @@ struct nsinfo *nsinfo__new(pid_t pid) return nsi; } +static const char *nsinfo__mntns_path(const struct nsinfo *nsi) +{ + return RC_CHK_ACCESS(nsi)->mntns_path; +} + struct nsinfo *nsinfo__copy(const struct nsinfo *nsi) { struct nsinfo *nnsi; @@ -193,8 +198,8 @@ struct nsinfo *nsinfo__copy(const struct nsinfo *nsi) RC_CHK_ACCESS(nnsi)->nstgid = nsinfo__nstgid(nsi); RC_CHK_ACCESS(nnsi)->need_setns = nsinfo__need_setns(nsi); RC_CHK_ACCESS(nnsi)->in_pidns = nsinfo__in_pidns(nsi); - if (RC_CHK_ACCESS(nsi)->mntns_path) { - RC_CHK_ACCESS(nnsi)->mntns_path = strdup(RC_CHK_ACCESS(nsi)->mntns_path); + if (nsinfo__mntns_path(nsi)) { + RC_CHK_ACCESS(nnsi)->mntns_path = strdup(nsinfo__mntns_path(nsi)); if (!RC_CHK_ACCESS(nnsi)->mntns_path) { nsinfo__put(nnsi); return NULL; @@ -294,7 +299,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, if (oldns < 0) goto errout; - newns = open(RC_CHK_ACCESS(nsi)->mntns_path, O_RDONLY); + newns = open(nsinfo__mntns_path(nsi), O_RDONLY); if (newns < 0) goto errout; -- GitLab From de047c1091854f0c0561f3d199c2ea2e344f10a5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 17 Apr 2023 18:48:26 +0100 Subject: [PATCH 3150/5631] perf script task-analyzer: Fix spelling mistake "miliseconds" -> "milliseconds" There is a spelling mistake in the help for the --ms option. Fix it. Signed-off-by: Colin Ian King Acked-by: Hagen Paul Pfeifer Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Petar Gligoric Cc: Peter Zijlstra Cc: kernel-janitors@vger.kernel.org Link: https://lore.kernel.org/r/20230417174826.52963-1-colin.i.king@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/task-analyzer.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/scripts/python/task-analyzer.py b/tools/perf/scripts/python/task-analyzer.py index 52e8dae9b1f0..3f1df9894246 100755 --- a/tools/perf/scripts/python/task-analyzer.py +++ b/tools/perf/scripts/python/task-analyzer.py @@ -114,7 +114,7 @@ def _parse_args(): "--ns", action="store_true", help="show timestamps in nanoseconds" ) parser.add_argument( - "--ms", action="store_true", help="show timestamps in miliseconds" + "--ms", action="store_true", help="show timestamps in milliseconds" ) parser.add_argument( "--extended-times", -- GitLab From 3e358ea8614ddfbc59ca7a3f5dff5dde2b350b2c Mon Sep 17 00:00:00 2001 From: Mark Bloch Date: Thu, 13 Apr 2023 12:23:09 +0300 Subject: [PATCH 3151/5631] RDMA/mlx5: Fix flow counter query via DEVX Commit cited in "fixes" tag added bulk support for flow counters but it didn't account that's also possible to query a counter using a non-base id if the counter was allocated as bulk. When a user performs a query, validate the flow counter id given in the mailbox is inside the valid range taking bulk value into account. Fixes: 208d70f562e5 ("IB/mlx5: Support flow counters offset for bulk counters") Signed-off-by: Mark Bloch Reviewed-by: Maor Gottlieb Link: https://lore.kernel.org/r/79d7fbe291690128e44672418934256254d93115.1681377114.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 31 ++++++++++++++++++++++++++----- include/linux/mlx5/mlx5_ifc.h | 3 ++- 2 files changed, 28 insertions(+), 6 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 07037b829c7e..db5fb196c728 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -666,7 +666,21 @@ static bool devx_is_valid_obj_id(struct uverbs_attr_bundle *attrs, obj_id; case MLX5_IB_OBJECT_DEVX_OBJ: - return ((struct devx_obj *)uobj->object)->obj_id == obj_id; + { + u16 opcode = MLX5_GET(general_obj_in_cmd_hdr, in, opcode); + struct devx_obj *devx_uobj = uobj->object; + + if (opcode == MLX5_CMD_OP_QUERY_FLOW_COUNTER && + devx_uobj->flow_counter_bulk_size) { + u64 end; + + end = devx_uobj->obj_id + + devx_uobj->flow_counter_bulk_size; + return devx_uobj->obj_id <= obj_id && end > obj_id; + } + + return devx_uobj->obj_id == obj_id; + } default: return false; @@ -1517,10 +1531,17 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)( goto obj_free; if (opcode == MLX5_CMD_OP_ALLOC_FLOW_COUNTER) { - u8 bulk = MLX5_GET(alloc_flow_counter_in, - cmd_in, - flow_counter_bulk); - obj->flow_counter_bulk_size = 128UL * bulk; + u32 bulk = MLX5_GET(alloc_flow_counter_in, + cmd_in, + flow_counter_bulk_log_size); + + if (bulk) + bulk = 1 << bulk; + else + bulk = 128UL * MLX5_GET(alloc_flow_counter_in, + cmd_in, + flow_counter_bulk); + obj->flow_counter_bulk_size = bulk; } uobj->object = obj; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b54339a1b1c6..3976e6266bcc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9283,7 +9283,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x38]; + u8 reserved_at_40[0x33]; + u8 flow_counter_bulk_log_size[0x5]; u8 flow_counter_bulk[0x8]; }; -- GitLab From a095edfc15f0832e046ae23964e249ef5c95af87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Mon, 17 Apr 2023 18:20:03 +0300 Subject: [PATCH 3152/5631] USB: serial: option: add UNISOC vendor and TOZED LT70C product MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add UNISOC vendor ID and TOZED LT70-C modem which is based from UNISOC SL8563. The modem supports the NCM mode. Interface 0 is used for running the AT commands. Interface 12 is the ADB interface. T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 6 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1782 ProdID=4055 Rev=04.04 S: Manufacturer=Unisoc Phone S: Product=Unisoc Phone S: SerialNumber= C: #Ifs=14 Cfg#= 1 Atr=c0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=82(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=10 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=11 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=12 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) E: Ad=09(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#=13 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=0a(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 2 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=84(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 3 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 4 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=86(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 5 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 6 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0d Prot=00 Driver=cdc_ncm E: Ad=88(I) Atr=03(Int.) MxPS= 16 Ivl=32ms I: If#= 7 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=01 Driver=cdc_ncm E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms Signed-off-by: Arınç ÜNAL Link: https://lore.kernel.org/r/20230417152003.243248-1-arinc.unal@arinc9.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e6d8d9b35ad0..d0d7c4b3f515 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -595,6 +595,11 @@ static void option_instat_callback(struct urb *urb); #define SIERRA_VENDOR_ID 0x1199 #define SIERRA_PRODUCT_EM9191 0x90d3 +/* UNISOC (Spreadtrum) products */ +#define UNISOC_VENDOR_ID 0x1782 +/* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */ +#define TOZED_PRODUCT_LT70C 0x4055 + /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -2215,6 +2220,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); -- GitLab From ca9d081b49cc225627aa73feb9284b7ffc190df5 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 18 Apr 2023 15:47:15 +0200 Subject: [PATCH 3153/5631] zram: fix up permission for the hot_add sysfs file Commit 75a2d4226b53 ("driver core: class: mark the struct class for sysfs callbacks as constant") changed the attribute to use CLASS_ATTR_RO() which changed the permission from 0400 to 0444. But this atribute is "special" in that reading it modifies the system state, so it MUST be set to 0400 so that only root processes can muck around with it. Fix this all up, AND document this so that I don't change it again in 3-4 years when I stumble across it and wonder why it's an open-coded _ATTR() macro. Reported-by: Denis Efremov Fixes: 75a2d4226b53 ("driver core: class: mark the struct class for sysfs callbacks as constant") Link: https://lore.kernel.org/r/2023041810-angelic-conical-52d8@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/block/zram/zram_drv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3feadfb96114..d8217529be6f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2438,7 +2438,9 @@ static ssize_t hot_add_show(const struct class *class, return ret; return scnprintf(buf, PAGE_SIZE, "%d\n", ret); } -static CLASS_ATTR_RO(hot_add); +/* This attribute must be set to 0400, so CLASS_ATTR_RO() can not be used */ +static struct class_attribute class_attr_hot_add = + __ATTR(hot_add, 0400, hot_add_show, NULL); static ssize_t hot_remove_store(const struct class *class, const struct class_attribute *attr, -- GitLab From b550bc90bb8218da8c944f28b99cb372ad969749 Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 18 Apr 2023 15:12:03 +0100 Subject: [PATCH 3154/5631] perf cs-etm: Fix segfault in dso lookup map__dso() is called before thread__find_map() which always results in a null pointer dereference. Fix it by finding first, then checking if it exists. Fixes: 63df0e4bc368adbd ("perf map: Add accessor for dso") Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230418141203.673465-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 103865968700..8dd81ddd9e4e 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -885,9 +885,11 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id, thread = etmq->etm->unknown_thread; } - dso = map__dso(al.map); + if (!thread__find_map(thread, cpumode, address, &al)) + return 0; - if (!thread__find_map(thread, cpumode, address, &al) || !dso) + dso = map__dso(al.map); + if (!dso) return 0; if (dso->data.status == DSO_DATA_STATUS_ERROR && -- GitLab From 85a953806557dbf25d16e8c132b5b9b100d16496 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Mon, 10 Apr 2023 09:16:52 -0700 Subject: [PATCH 3155/5631] mailbox: Allow direct registration to a channel Support virtual mailbox controllers and clients which are not platform devices or come from the devicetree by allowing them to match client to channel via some other mechanism. Tested-by: Sudeep Holla (pcc) Signed-off-by: Elliot Berman Signed-off-by: Jassi Brar --- drivers/mailbox/mailbox.c | 96 ++++++++++++++++++++++++---------- include/linux/mailbox_client.h | 1 + 2 files changed, 69 insertions(+), 28 deletions(-) diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 4229b9b5da98..adf36c05fa43 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -317,6 +317,71 @@ int mbox_flush(struct mbox_chan *chan, unsigned long timeout) } EXPORT_SYMBOL_GPL(mbox_flush); +static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) +{ + struct device *dev = cl->dev; + unsigned long flags; + int ret; + + if (chan->cl || !try_module_get(chan->mbox->dev->driver->owner)) { + dev_dbg(dev, "%s: mailbox not free\n", __func__); + return -EBUSY; + } + + spin_lock_irqsave(&chan->lock, flags); + chan->msg_free = 0; + chan->msg_count = 0; + chan->active_req = NULL; + chan->cl = cl; + init_completion(&chan->tx_complete); + + if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) + chan->txdone_method = TXDONE_BY_ACK; + + spin_unlock_irqrestore(&chan->lock, flags); + + if (chan->mbox->ops->startup) { + ret = chan->mbox->ops->startup(chan); + + if (ret) { + dev_err(dev, "Unable to startup the chan (%d)\n", ret); + mbox_free_channel(chan); + return ret; + } + } + + return 0; +} + +/** + * mbox_bind_client - Request a mailbox channel. + * @chan: The mailbox channel to bind the client to. + * @cl: Identity of the client requesting the channel. + * + * The Client specifies its requirements and capabilities while asking for + * a mailbox channel. It can't be called from atomic context. + * The channel is exclusively allocated and can't be used by another + * client before the owner calls mbox_free_channel. + * After assignment, any packet received on this channel will be + * handed over to the client via the 'rx_callback'. + * The framework holds reference to the client, so the mbox_client + * structure shouldn't be modified until the mbox_free_channel returns. + * + * Return: 0 if the channel was assigned to the client successfully. + * <0 for request failure. + */ +int mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) +{ + int ret; + + mutex_lock(&con_mutex); + ret = __mbox_bind_client(chan, cl); + mutex_unlock(&con_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(mbox_bind_client); + /** * mbox_request_channel - Request a mailbox channel. * @cl: Identity of the client requesting the channel. @@ -340,7 +405,6 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index) struct mbox_controller *mbox; struct of_phandle_args spec; struct mbox_chan *chan; - unsigned long flags; int ret; if (!dev || !dev->of_node) { @@ -372,33 +436,9 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index) return chan; } - if (chan->cl || !try_module_get(mbox->dev->driver->owner)) { - dev_dbg(dev, "%s: mailbox not free\n", __func__); - mutex_unlock(&con_mutex); - return ERR_PTR(-EBUSY); - } - - spin_lock_irqsave(&chan->lock, flags); - chan->msg_free = 0; - chan->msg_count = 0; - chan->active_req = NULL; - chan->cl = cl; - init_completion(&chan->tx_complete); - - if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) - chan->txdone_method = TXDONE_BY_ACK; - - spin_unlock_irqrestore(&chan->lock, flags); - - if (chan->mbox->ops->startup) { - ret = chan->mbox->ops->startup(chan); - - if (ret) { - dev_err(dev, "Unable to startup the chan (%d)\n", ret); - mbox_free_channel(chan); - chan = ERR_PTR(ret); - } - } + ret = __mbox_bind_client(chan, cl); + if (ret) + chan = ERR_PTR(ret); mutex_unlock(&con_mutex); return chan; diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index 65229a45590f..734694912ef7 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -37,6 +37,7 @@ struct mbox_client { void (*tx_done)(struct mbox_client *cl, void *mssg, int r); }; +int mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl); struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); -- GitLab From f11ff34d883a26f4f13c307aeb556f2b076a5066 Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Mon, 10 Apr 2023 09:16:53 -0700 Subject: [PATCH 3156/5631] mailbox: omap: Use mbox_bind_client Use generic mbox_bind_client() to bind omap mailbox channel to a client. mbox_bind_client is identical to the replaced lines, except that it: - Does the operation under con_mutex which prevents possible races in removal path - Sets TXDONE_BY_ACK if omap uses TXDONE_BY_POLL. omap uses TXDONE_BY_IRQ, so this check is not applicable. - Calls chan->mbox->ops->startup, if available. omap doesn't have, so this is not applicable. Signed-off-by: Elliot Berman Signed-off-by: Jassi Brar --- drivers/mailbox/omap-mailbox.c | 22 ++++------------------ 1 file changed, 4 insertions(+), 18 deletions(-) diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index 098c82d87137..dfe82a5ff403 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -417,8 +417,6 @@ struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl, struct device *dev = cl->dev; struct omap_mbox *mbox = NULL; struct omap_mbox_device *mdev; - struct mbox_chan *chan; - unsigned long flags; int ret; if (!dev) @@ -441,23 +439,11 @@ struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl, if (!mbox || !mbox->chan) return ERR_PTR(-ENOENT); - chan = mbox->chan; - spin_lock_irqsave(&chan->lock, flags); - chan->msg_free = 0; - chan->msg_count = 0; - chan->active_req = NULL; - chan->cl = cl; - init_completion(&chan->tx_complete); - spin_unlock_irqrestore(&chan->lock, flags); - - ret = chan->mbox->ops->startup(chan); - if (ret) { - pr_err("Unable to startup the chan (%d)\n", ret); - mbox_free_channel(chan); - chan = ERR_PTR(ret); - } + ret = mbox_bind_client(mbox->chan, cl); + if (ret) + return ERR_PTR(ret); - return chan; + return mbox->chan; } EXPORT_SYMBOL(omap_mbox_request_channel); -- GitLab From 76d4adacd52e78bea2e393081f2a5766261d1e3a Mon Sep 17 00:00:00 2001 From: Elliot Berman Date: Mon, 10 Apr 2023 09:16:54 -0700 Subject: [PATCH 3157/5631] mailbox: pcc: Use mbox_bind_client Use generic mbox_bind_client() to bind omap mailbox channel to a client. mbox_bind_client is identical to the replaced lines, except that it: - Does the operation under con_mutex which prevents possible races in removal path - Sets TXDONE_BY_ACK if pcc uses TXDONE_BY_POLL and the client knows when tx is done. TXDONE_BY_ACK is already set if there's no interrupt, so this is not applicable. - Calls chan->mbox->ops->startup. This is usecase for requesting irq: move the devm_request_irq into the startup callback and unregister it in the shutdown path. Tested-by: Sudeep Holla Signed-off-by: Elliot Berman Signed-off-by: Jassi Brar --- drivers/mailbox/pcc.c | 84 +++++++++++++++++++++++-------------------- 1 file changed, 45 insertions(+), 39 deletions(-) diff --git a/drivers/mailbox/pcc.c b/drivers/mailbox/pcc.c index 105d46c9801b..a44d4b3e5beb 100644 --- a/drivers/mailbox/pcc.c +++ b/drivers/mailbox/pcc.c @@ -282,8 +282,7 @@ pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id) { struct pcc_chan_info *pchan; struct mbox_chan *chan; - struct device *dev; - unsigned long flags; + int rc; if (subspace_id < 0 || subspace_id >= pcc_chan_count) return ERR_PTR(-ENOENT); @@ -294,32 +293,10 @@ pcc_mbox_request_channel(struct mbox_client *cl, int subspace_id) pr_err("Channel not found for idx: %d\n", subspace_id); return ERR_PTR(-EBUSY); } - dev = chan->mbox->dev; - spin_lock_irqsave(&chan->lock, flags); - chan->msg_free = 0; - chan->msg_count = 0; - chan->active_req = NULL; - chan->cl = cl; - init_completion(&chan->tx_complete); - - if (chan->txdone_method == TXDONE_BY_POLL && cl->knows_txdone) - chan->txdone_method = TXDONE_BY_ACK; - - spin_unlock_irqrestore(&chan->lock, flags); - - if (pchan->plat_irq > 0) { - int rc; - - rc = devm_request_irq(dev, pchan->plat_irq, pcc_mbox_irq, 0, - MBOX_IRQ_NAME, chan); - if (unlikely(rc)) { - dev_err(dev, "failed to register PCC interrupt %d\n", - pchan->plat_irq); - pcc_mbox_free_channel(&pchan->chan); - return ERR_PTR(rc); - } - } + rc = mbox_bind_client(chan, cl); + if (rc) + return ERR_PTR(rc); return &pchan->chan; } @@ -333,23 +310,12 @@ EXPORT_SYMBOL_GPL(pcc_mbox_request_channel); */ void pcc_mbox_free_channel(struct pcc_mbox_chan *pchan) { - struct pcc_chan_info *pchan_info = to_pcc_chan_info(pchan); struct mbox_chan *chan = pchan->mchan; - unsigned long flags; if (!chan || !chan->cl) return; - if (pchan_info->plat_irq > 0) - devm_free_irq(chan->mbox->dev, pchan_info->plat_irq, chan); - - spin_lock_irqsave(&chan->lock, flags); - chan->cl = NULL; - chan->active_req = NULL; - if (chan->txdone_method == TXDONE_BY_ACK) - chan->txdone_method = TXDONE_BY_POLL; - - spin_unlock_irqrestore(&chan->lock, flags); + mbox_free_channel(chan); } EXPORT_SYMBOL_GPL(pcc_mbox_free_channel); @@ -377,8 +343,48 @@ static int pcc_send_data(struct mbox_chan *chan, void *data) return pcc_chan_reg_read_modify_write(&pchan->db); } +/** + * pcc_startup - Called from Mailbox Controller code. Used here + * to request the interrupt. + * @chan: Pointer to Mailbox channel to startup. + * + * Return: Err if something failed else 0 for success. + */ +static int pcc_startup(struct mbox_chan *chan) +{ + struct pcc_chan_info *pchan = chan->con_priv; + int rc; + + if (pchan->plat_irq > 0) { + rc = devm_request_irq(chan->mbox->dev, pchan->plat_irq, pcc_mbox_irq, 0, + MBOX_IRQ_NAME, chan); + if (unlikely(rc)) { + dev_err(chan->mbox->dev, "failed to register PCC interrupt %d\n", + pchan->plat_irq); + return rc; + } + } + + return 0; +} + +/** + * pcc_shutdown - Called from Mailbox Controller code. Used here + * to free the interrupt. + * @chan: Pointer to Mailbox channel to shutdown. + */ +static void pcc_shutdown(struct mbox_chan *chan) +{ + struct pcc_chan_info *pchan = chan->con_priv; + + if (pchan->plat_irq > 0) + devm_free_irq(chan->mbox->dev, pchan->plat_irq, chan); +} + static const struct mbox_chan_ops pcc_chan_ops = { .send_data = pcc_send_data, + .startup = pcc_startup, + .shutdown = pcc_shutdown, }; /** -- GitLab From 2a61e7b7bd92f4745457c60c86d8bf045d185bda Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:10 -0600 Subject: [PATCH 3158/5631] mailbox: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Jassi Brar --- drivers/mailbox/hi6220-mailbox.c | 5 +---- drivers/mailbox/omap-mailbox.c | 3 +-- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c index fca61f5312d9..1c73c63598f5 100644 --- a/drivers/mailbox/hi6220-mailbox.c +++ b/drivers/mailbox/hi6220-mailbox.c @@ -325,10 +325,7 @@ static int hi6220_mbox_probe(struct platform_device *pdev) writel(~0x0, ACK_INT_CLR_REG(mbox->ipc)); /* use interrupt for tx's ack */ - if (of_find_property(node, "hi6220,mbox-tx-noirq", NULL)) - mbox->tx_irq_mode = false; - else - mbox->tx_irq_mode = true; + mbox->tx_irq_mode = !of_property_read_bool(node, "hi6220,mbox-tx-noirq"); if (mbox->tx_irq_mode) mbox->controller.txdone_irq = true; diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index dfe82a5ff403..fa2ce3246b70 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -749,8 +749,7 @@ static int omap_mbox_probe(struct platform_device *pdev) finfo->name = child->name; - if (of_find_property(child, "ti,mbox-send-noirq", NULL)) - finfo->send_no_irq = true; + finfo->send_no_irq = of_property_read_bool(child, "ti,mbox-send-noirq"); if (finfo->tx_id >= num_fifos || finfo->rx_id >= num_fifos || finfo->tx_usr >= num_users || finfo->rx_usr >= num_users) -- GitLab From d21a19e1c2f55504c4b3e9f9c82b4554bfa90d7b Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 10 Apr 2023 22:55:28 -0700 Subject: [PATCH 3159/5631] x86/init: Make get/set_rtc_noop() public Make get/set_rtc_noop() to be public so that they can be used in other modules as well. Co-developed-by: Tianyu Lan Signed-off-by: Tianyu Lan Signed-off-by: Saurabh Sengar Reviewed-by: Wei Liu Reviewed-by: Michael Kelley Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/1681192532-15460-2-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/include/asm/x86_init.h | 2 ++ arch/x86/kernel/x86_init.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index acc20ae4079d..88085f369ff6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -330,5 +330,7 @@ extern void x86_init_uint_noop(unsigned int unused); extern bool bool_x86_init_noop(void); extern void x86_op_int_noop(int cpu); extern bool x86_pnpbios_disabled(void); +extern int set_rtc_noop(const struct timespec64 *now); +extern void get_rtc_noop(struct timespec64 *now); #endif diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ecdeb0974a87..d82f4fa2f1bf 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -33,8 +33,8 @@ static int __init iommu_init_noop(void) { return 0; } static void iommu_shutdown_noop(void) { } bool __init bool_x86_init_noop(void) { return false; } void x86_op_int_noop(int cpu) { } -static int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } -static void get_rtc_noop(struct timespec64 *now) { } +int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; } +void get_rtc_noop(struct timespec64 *now) { } static __initconst const struct of_device_id of_cmos_match[] = { { .compatible = "motorola,mc146818" }, -- GitLab From c26e0527aaf84a34b4774d80c9a9baa65f4d77f2 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 10 Apr 2023 22:55:29 -0700 Subject: [PATCH 3160/5631] x86/hyperv: Add VTL specific structs and hypercalls Add structs and hypercalls required to enable VTL support on x86. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Reviewed-by: Stanislav Kinsburskii Link: https://lore.kernel.org/r/1681192532-15460-3-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/include/asm/hyperv-tlfs.h | 75 ++++++++++++++++++++++++++++++ include/asm-generic/hyperv-tlfs.h | 4 ++ 2 files changed, 79 insertions(+) diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index b4fb75bd1013..cea95dcd27c2 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -716,6 +716,81 @@ union hv_msi_entry { } __packed; }; +struct hv_x64_segment_register { + u64 base; + u32 limit; + u16 selector; + union { + struct { + u16 segment_type : 4; + u16 non_system_segment : 1; + u16 descriptor_privilege_level : 2; + u16 present : 1; + u16 reserved : 4; + u16 available : 1; + u16 _long : 1; + u16 _default : 1; + u16 granularity : 1; + } __packed; + u16 attributes; + }; +} __packed; + +struct hv_x64_table_register { + u16 pad[3]; + u16 limit; + u64 base; +} __packed; + +struct hv_init_vp_context { + u64 rip; + u64 rsp; + u64 rflags; + + struct hv_x64_segment_register cs; + struct hv_x64_segment_register ds; + struct hv_x64_segment_register es; + struct hv_x64_segment_register fs; + struct hv_x64_segment_register gs; + struct hv_x64_segment_register ss; + struct hv_x64_segment_register tr; + struct hv_x64_segment_register ldtr; + + struct hv_x64_table_register idtr; + struct hv_x64_table_register gdtr; + + u64 efer; + u64 cr0; + u64 cr3; + u64 cr4; + u64 msr_cr_pat; +} __packed; + +union hv_input_vtl { + u8 as_uint8; + struct { + u8 target_vtl: 4; + u8 use_target_vtl: 1; + u8 reserved_z: 3; + }; +} __packed; + +struct hv_enable_vp_vtl { + u64 partition_id; + u32 vp_index; + union hv_input_vtl target_vtl; + u8 mbz0; + u16 mbz1; + struct hv_init_vp_context vp_context; +} __packed; + +struct hv_get_vp_from_apic_id_in { + u64 partition_id; + union hv_input_vtl target_vtl; + u8 res[7]; + u32 apic_ids[]; +} __packed; + #include #endif diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index ea406e901469..f4e4cc4f965f 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -146,6 +146,7 @@ union hv_reference_tsc_msr { /* Declare the various hypercall operations. */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 +#define HVCALL_ENABLE_VP_VTL 0x000f #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 #define HVCALL_SEND_IPI 0x000b #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 @@ -165,6 +166,8 @@ union hv_reference_tsc_msr { #define HVCALL_MAP_DEVICE_INTERRUPT 0x007c #define HVCALL_UNMAP_DEVICE_INTERRUPT 0x007d #define HVCALL_RETARGET_INTERRUPT 0x007e +#define HVCALL_START_VP 0x0099 +#define HVCALL_GET_VP_ID_FROM_APIC_ID 0x009a #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db @@ -220,6 +223,7 @@ enum HV_GENERIC_SET_FORMAT { #define HV_STATUS_INVALID_PORT_ID 17 #define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 +#define HV_STATUS_VTL_ALREADY_ENABLED 134 /* * The Hyper-V TimeRefCount register and the TSC -- GitLab From 0a7a00580a4fad9a6cd28c2d825e0e5ae917e59e Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 10 Apr 2023 22:55:30 -0700 Subject: [PATCH 3161/5631] x86/hyperv: Make hv_get_nmi_reason public Move hv_get_nmi_reason to .h file so it can be used in other modules as well. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1681192532-15460-4-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/include/asm/mshyperv.h | 5 +++++ arch/x86/kernel/cpu/mshyperv.c | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index e3cef98a0142..67f8386c1775 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -29,6 +29,11 @@ typedef int (*hyperv_fill_flush_list_func)( void hyperv_vector_handler(struct pt_regs *regs); +static inline unsigned char hv_get_nmi_reason(void) +{ + return 0; +} + #if IS_ENABLED(CONFIG_HYPERV) extern int hyperv_init_cpuhp; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index ac630ecde795..c8a0e70cc484 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -248,11 +248,6 @@ static uint32_t __init ms_hyperv_platform(void) return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; } -static unsigned char hv_get_nmi_reason(void) -{ - return 0; -} - #ifdef CONFIG_X86_LOCAL_APIC /* * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes -- GitLab From d01b9a9f2d0131e1e249177a70e6b80d146d16d2 Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 10 Apr 2023 22:55:31 -0700 Subject: [PATCH 3162/5631] Drivers: hv: Kconfig: Add HYPERV_VTL_MODE Add HYPERV_VTL_MODE Kconfig flag for VTL mode. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1681192532-15460-5-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- drivers/hv/Kconfig | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 94982f08b661..00242107d62e 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -13,6 +13,30 @@ config HYPERV Select this option to run Linux as a Hyper-V client operating system. +config HYPERV_VTL_MODE + bool "Enable Linux to boot in VTL context" + depends on X86_64 && HYPERV + default n + help + Virtual Secure Mode (VSM) is a set of hypervisor capabilities and + enlightenments offered to host and guest partitions which enables + the creation and management of new security boundaries within + operating system software. + + VSM achieves and maintains isolation through Virtual Trust Levels + (VTLs). Virtual Trust Levels are hierarchical, with higher levels + being more privileged than lower levels. VTL0 is the least privileged + level, and currently only other level supported is VTL2. + + Select this option to build a Linux kernel to run at a VTL other than + the normal VTL0, which currently is only VTL2. This option + initializes the x86 platform for VTL2, and adds the ability to boot + secondary CPUs directly into 64-bit context as required for VTLs other + than 0. A kernel built with this option must run at VTL2, and will + not run as a normal guest. + + If unsure, say N + config HYPERV_TIMER def_bool HYPERV && X86 -- GitLab From 3be1bc2fe9d2e4fc1375efa2567d2f58cd2a2a7c Mon Sep 17 00:00:00 2001 From: Saurabh Sengar Date: Mon, 10 Apr 2023 22:55:32 -0700 Subject: [PATCH 3163/5631] x86/hyperv: VTL support for Hyper-V Virtual Trust Levels (VTL) helps enable Hyper-V Virtual Secure Mode (VSM) feature. VSM is a set of hypervisor capabilities and enlightenments offered to host and guest partitions which enable the creation and management of new security boundaries within operating system software. VSM achieves and maintains isolation through VTLs. Add early initialization for Virtual Trust Levels (VTL). This includes initializing the x86 platform for VTL and enabling boot support for secondary CPUs to start in targeted VTL context. For now, only enable the code for targeted VTL level as 2. When starting an AP at a VTL other than VTL0, the AP must start directly in 64-bit mode, bypassing the usual 16-bit -> 32-bit -> 64-bit mode transition sequence that occurs after waking up an AP with SIPI whose vector points to the 16-bit AP startup trampoline code. Signed-off-by: Saurabh Sengar Reviewed-by: Michael Kelley Reviewed-by: Stanislav Kinsburskii Link: https://lore.kernel.org/r/1681192532-15460-6-git-send-email-ssengar@linux.microsoft.com Signed-off-by: Wei Liu --- arch/x86/hyperv/Makefile | 1 + arch/x86/hyperv/hv_vtl.c | 227 ++++++++++++++++++++++++++++++++ arch/x86/include/asm/mshyperv.h | 10 ++ arch/x86/kernel/cpu/mshyperv.c | 1 + 4 files changed, 239 insertions(+) create mode 100644 arch/x86/hyperv/hv_vtl.c diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 5d2de10809ae..3a1548054b48 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y := hv_init.o mmu.o nested.o irqdomain.o ivm.o obj-$(CONFIG_X86_64) += hv_apic.o hv_proc.o +obj-$(CONFIG_HYPERV_VTL_MODE) += hv_vtl.o ifdef CONFIG_X86_64 obj-$(CONFIG_PARAVIRT_SPINLOCKS) += hv_spinlock.o diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c new file mode 100644 index 000000000000..1ba5d3b99b16 --- /dev/null +++ b/arch/x86/hyperv/hv_vtl.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023, Microsoft Corporation. + * + * Author: + * Saurabh Sengar + */ + +#include +#include +#include +#include +#include +#include + +extern struct boot_params boot_params; +static struct real_mode_header hv_vtl_real_mode_header; + +void __init hv_vtl_init_platform(void) +{ + pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); + + x86_init.irqs.pre_vector_init = x86_init_noop; + x86_init.timers.timer_init = x86_init_noop; + + x86_platform.get_wallclock = get_rtc_noop; + x86_platform.set_wallclock = set_rtc_noop; + x86_platform.get_nmi_reason = hv_get_nmi_reason; + + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; + x86_platform.legacy.rtc = 0; + x86_platform.legacy.warm_reset = 0; + x86_platform.legacy.reserve_bios_regions = 0; + x86_platform.legacy.devices.pnpbios = 0; +} + +static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) +{ + return ((u64)desc->base3 << 32) | ((u64)desc->base2 << 24) | + (desc->base1 << 16) | desc->base0; +} + +static inline u32 hv_vtl_system_desc_limit(struct ldttss_desc *desc) +{ + return ((u32)desc->limit1 << 16) | (u32)desc->limit0; +} + +typedef void (*secondary_startup_64_fn)(void*, void*); +static void hv_vtl_ap_entry(void) +{ + ((secondary_startup_64_fn)secondary_startup_64)(&boot_params, &boot_params); +} + +static int hv_vtl_bringup_vcpu(u32 target_vp_index, u64 eip_ignored) +{ + u64 status; + int ret = 0; + struct hv_enable_vp_vtl *input; + unsigned long irq_flags; + + struct desc_ptr gdt_ptr; + struct desc_ptr idt_ptr; + + struct ldttss_desc *tss; + struct ldttss_desc *ldt; + struct desc_struct *gdt; + + u64 rsp = current->thread.sp; + u64 rip = (u64)&hv_vtl_ap_entry; + + native_store_gdt(&gdt_ptr); + store_idt(&idt_ptr); + + gdt = (struct desc_struct *)((void *)(gdt_ptr.address)); + tss = (struct ldttss_desc *)(gdt + GDT_ENTRY_TSS); + ldt = (struct ldttss_desc *)(gdt + GDT_ENTRY_LDT); + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + + input->partition_id = HV_PARTITION_ID_SELF; + input->vp_index = target_vp_index; + input->target_vtl.target_vtl = HV_VTL_MGMT; + + /* + * The x86_64 Linux kernel follows the 16-bit -> 32-bit -> 64-bit + * mode transition sequence after waking up an AP with SIPI whose + * vector points to the 16-bit AP startup trampoline code. Here in + * VTL2, we can't perform that sequence as the AP has to start in + * the 64-bit mode. + * + * To make this happen, we tell the hypervisor to load a valid 64-bit + * context (most of which is just magic numbers from the CPU manual) + * so that AP jumps right to the 64-bit entry of the kernel, and the + * control registers are loaded with values that let the AP fetch the + * code and data and carry on with work it gets assigned. + */ + + input->vp_context.rip = rip; + input->vp_context.rsp = rsp; + input->vp_context.rflags = 0x0000000000000002; + input->vp_context.efer = __rdmsr(MSR_EFER); + input->vp_context.cr0 = native_read_cr0(); + input->vp_context.cr3 = __native_read_cr3(); + input->vp_context.cr4 = native_read_cr4(); + input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT); + input->vp_context.idtr.limit = idt_ptr.size; + input->vp_context.idtr.base = idt_ptr.address; + input->vp_context.gdtr.limit = gdt_ptr.size; + input->vp_context.gdtr.base = gdt_ptr.address; + + /* Non-system desc (64bit), long, code, present */ + input->vp_context.cs.selector = __KERNEL_CS; + input->vp_context.cs.base = 0; + input->vp_context.cs.limit = 0xffffffff; + input->vp_context.cs.attributes = 0xa09b; + /* Non-system desc (64bit), data, present, granularity, default */ + input->vp_context.ss.selector = __KERNEL_DS; + input->vp_context.ss.base = 0; + input->vp_context.ss.limit = 0xffffffff; + input->vp_context.ss.attributes = 0xc093; + + /* System desc (128bit), present, LDT */ + input->vp_context.ldtr.selector = GDT_ENTRY_LDT * 8; + input->vp_context.ldtr.base = hv_vtl_system_desc_base(ldt); + input->vp_context.ldtr.limit = hv_vtl_system_desc_limit(ldt); + input->vp_context.ldtr.attributes = 0x82; + + /* System desc (128bit), present, TSS, 0x8b - busy, 0x89 -- default */ + input->vp_context.tr.selector = GDT_ENTRY_TSS * 8; + input->vp_context.tr.base = hv_vtl_system_desc_base(tss); + input->vp_context.tr.limit = hv_vtl_system_desc_limit(tss); + input->vp_context.tr.attributes = 0x8b; + + status = hv_do_hypercall(HVCALL_ENABLE_VP_VTL, input, NULL); + + if (!hv_result_success(status) && + hv_result(status) != HV_STATUS_VTL_ALREADY_ENABLED) { + pr_err("HVCALL_ENABLE_VP_VTL failed for VP : %d ! [Err: %#llx\n]", + target_vp_index, status); + ret = -EINVAL; + goto free_lock; + } + + status = hv_do_hypercall(HVCALL_START_VP, input, NULL); + + if (!hv_result_success(status)) { + pr_err("HVCALL_START_VP failed for VP : %d ! [Err: %#llx]\n", + target_vp_index, status); + ret = -EINVAL; + } + +free_lock: + local_irq_restore(irq_flags); + + return ret; +} + +static int hv_vtl_apicid_to_vp_id(u32 apic_id) +{ + u64 control; + u64 status; + unsigned long irq_flags; + struct hv_get_vp_from_apic_id_in *input; + u32 *output, ret; + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + input->partition_id = HV_PARTITION_ID_SELF; + input->apic_ids[0] = apic_id; + + output = (u32 *)input; + + control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; + status = hv_do_hypercall(control, input, output); + ret = output[0]; + + local_irq_restore(irq_flags); + + if (!hv_result_success(status)) { + pr_err("failed to get vp id from apic id %d, status %#llx\n", + apic_id, status); + return -EINVAL; + } + + return ret; +} + +static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) +{ + int vp_id; + + pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); + vp_id = hv_vtl_apicid_to_vp_id(apicid); + + if (vp_id < 0) { + pr_err("Couldn't find CPU with APIC ID %d\n", apicid); + return -EINVAL; + } + if (vp_id > ms_hyperv.max_vp_index) { + pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid); + return -EINVAL; + } + + return hv_vtl_bringup_vcpu(vp_id, start_eip); +} + +static int __init hv_vtl_early_init(void) +{ + /* + * `boot_cpu_has` returns the runtime feature support, + * and here is the earliest it can be used. + */ + if (cpu_feature_enabled(X86_FEATURE_XSAVE)) + panic("XSAVE has to be disabled as it is not supported by this module.\n" + "Please add 'noxsave' to the kernel command line.\n"); + + real_mode_header = &hv_vtl_real_mode_header; + apic->wakeup_secondary_cpu_64 = hv_vtl_wakeup_secondary_cpu; + + return 0; +} +early_initcall(hv_vtl_early_init); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 67f8386c1775..b445e252aa83 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -19,6 +19,10 @@ */ #define HV_IOAPIC_BASE_ADDRESS 0xfec00000 +#define HV_VTL_NORMAL 0x0 +#define HV_VTL_SECURE 0x1 +#define HV_VTL_MGMT 0x2 + union hv_ghcb; DECLARE_STATIC_KEY_FALSE(isolation_type_snp); @@ -276,6 +280,12 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; } #endif /* CONFIG_HYPERV */ +#ifdef CONFIG_HYPERV_VTL_MODE +void __init hv_vtl_init_platform(void); +#else +static inline void __init hv_vtl_init_platform(void) {} +#endif + #include #endif diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index c8a0e70cc484..c7969e806c64 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -514,6 +514,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + hv_vtl_init_platform(); #endif /* * TSC should be marked as unstable only after Hyper-V -- GitLab From 7701c8bef4f14bd9f7940c6ed0e6a73584115a96 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Apr 2023 11:53:55 -0700 Subject: [PATCH 3164/5631] cxl/hdm: Fail upon detecting 0-sized decoders Decoders committed with 0-size lead to later crashes on shutdown as __cxl_dpa_release() assumes a 'struct resource' has been established in the in 'cxlds->dpa_res'. Just fail the driver load in this instance since there are deeper problems with the enumeration or the setup when this happens. Fixes: 9c57cde0dcbd ("cxl/hdm: Enumerate allocated DPA") Cc: Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/168149843516.792294.11872242648319572632.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/hdm.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 02cc2c38b44b..35b338b716fe 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -269,8 +269,11 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, lockdep_assert_held_write(&cxl_dpa_rwsem); - if (!len) - goto success; + if (!len) { + dev_warn(dev, "decoder%d.%d: empty reservation attempted\n", + port->id, cxled->cxld.id); + return -EINVAL; + } if (cxled->dpa_res) { dev_dbg(dev, "decoder%d.%d: existing allocation %pr assigned\n", @@ -323,7 +326,6 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled, cxled->mode = CXL_DECODER_MIXED; } -success: port->hdm_end++; get_device(&cxled->cxld.dev); return 0; @@ -833,6 +835,13 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, port->id, cxld->id); return -ENXIO; } + + if (size == 0) { + dev_warn(&port->dev, + "decoder%d.%d: Committed with zero size\n", + port->id, cxld->id); + return -ENXIO; + } port->commit_end = cxld->id; } else { /* unless / until type-2 drivers arrive, assume type-3 */ -- GitLab From 1423885c84a5b3a53b79bcf241b18124d0d7cba6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Apr 2023 11:54:00 -0700 Subject: [PATCH 3165/5631] cxl/hdm: Use 4-byte reads to retrieve HDM decoder base+limit The CXL specification mandates that 4-byte registers must be accessed with 4-byte access cycles. CXL 3.0 8.2.3 "Component Register Layout and Definition" states that the behavior is undefined if (2) 32-bit registers are accessed as an 8-byte quantity. It turns out that at least one hardware implementation is sensitive to this in practice. The @size variable results in zero with: size = readq(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which)); ...and the correct size with: lo = readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which)); hi = readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(which)); size = (hi << 32) + lo; Fixes: d17d0540a0db ("cxl/core/hdm: Add CXL standard decoder enumeration to the core") Cc: Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/168149844056.792294.8224490474529733736.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/hdm.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 35b338b716fe..6fdf7981ddc7 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2022 Intel Corporation. All rights reserved. */ -#include #include #include #include @@ -785,8 +784,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, int *target_map, void __iomem *hdm, int which, u64 *dpa_base, struct cxl_endpoint_dvsec_info *info) { + u64 size, base, skip, dpa_size, lo, hi; struct cxl_endpoint_decoder *cxled; - u64 size, base, skip, dpa_size; bool committed; u32 remainder; int i, rc; @@ -801,8 +800,12 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, which, info); ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which)); - base = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which)); - size = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which)); + lo = readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which)); + hi = readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(which)); + base = (hi << 32) + lo; + lo = readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which)); + hi = readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(which)); + size = (hi << 32) + lo; committed = !!(ctrl & CXL_HDM_DECODER0_CTRL_COMMITTED); cxld->commit = cxl_decoder_commit; cxld->reset = cxl_decoder_reset; @@ -865,8 +868,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, return rc; if (!info) { - target_list.value = - ioread64_hi_lo(hdm + CXL_HDM_DECODER0_TL_LOW(which)); + lo = readl(hdm + CXL_HDM_DECODER0_TL_LOW(which)); + hi = readl(hdm + CXL_HDM_DECODER0_TL_HIGH(which)); + target_list.value = (hi << 32) + lo; for (i = 0; i < cxld->interleave_ways; i++) target_map[i] = target_list.target_id[i]; @@ -883,7 +887,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, port->id, cxld->id, size, cxld->interleave_ways); return -ENXIO; } - skip = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SKIP_LOW(which)); + lo = readl(hdm + CXL_HDM_DECODER0_SKIP_LOW(which)); + hi = readl(hdm + CXL_HDM_DECODER0_SKIP_HIGH(which)); + skip = (hi << 32) + lo; cxled = to_cxl_endpoint_decoder(&cxld->dev); rc = devm_cxl_dpa_reserve(cxled, *dpa_base + skip, dpa_size, skip); if (rc) { -- GitLab From 104087a8aaf0f46d89376917eca977fad972cc93 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Apr 2023 11:54:06 -0700 Subject: [PATCH 3166/5631] cxl/core: Drop unused io-64-nonatomic-lo-hi.h After the discovery of a case where an implementation misbehaves with register reads larger than the definition of the register the other usages of readq() were audited and found to be correct, but some cases where the io-64-nonatomic-lo-hi.h include is not needed were discovered, delete them. Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/168149844596.792294.8273108394688012953.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 - drivers/cxl/core/port.c | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index f2addb457172..6198637cb0bb 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ -#include #include #include #include diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 4d1f9c5b5029..b060757c4000 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2020 Intel Corporation. All rights reserved. */ -#include #include #include #include -- GitLab From 7bba261e0aa6e8e5f28a3a3def8338b6512534ee Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Apr 2023 11:54:11 -0700 Subject: [PATCH 3167/5631] cxl/port: Scan single-target ports for decoders Do not assume that a single-target port falls back to a passthrough decoder configuration. Scan for decoders and only fallback after probing that the HDM decoder capability is not present. One user visible affect of this bug is the inability to enumerate present CXL regions as the decoder settings for the present decoders are skipped. Fixes: d17d0540a0db ("cxl/core/hdm: Add CXL standard decoder enumeration to the core") Reported-by: Jonathan Cameron Link: http://lore.kernel.org/r/20230227153128.8164-1-Jonathan.Cameron@huawei.com Cc: Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/168149845130.792294.3210421233937427962.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/hdm.c | 5 +++-- drivers/cxl/port.c | 18 +++++++++++++----- 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 6fdf7981ddc7..abe3877cfa63 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -92,8 +92,9 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb, cxl_probe_component_regs(&port->dev, crb, &map.component_map); if (!map.component_map.hdm_decoder.valid) { - dev_err(&port->dev, "HDM decoder registers invalid\n"); - return -ENXIO; + dev_dbg(&port->dev, "HDM decoder registers not implemented\n"); + /* unique error code to indicate no HDM decoder capability */ + return -ENODEV; } return cxl_map_component_regs(&port->dev, regs, &map, diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 22a7ab2bae7c..eb57324c4ad4 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -66,14 +66,22 @@ static int cxl_switch_port_probe(struct cxl_port *port) if (rc < 0) return rc; - if (rc == 1) - return devm_cxl_add_passthrough_decoder(port); - cxlhdm = devm_cxl_setup_hdm(port, NULL); - if (IS_ERR(cxlhdm)) + if (!IS_ERR(cxlhdm)) + return devm_cxl_enumerate_decoders(cxlhdm, NULL); + + if (PTR_ERR(cxlhdm) != -ENODEV) { + dev_err(&port->dev, "Failed to map HDM decoder capability\n"); return PTR_ERR(cxlhdm); + } + + if (rc == 1) { + dev_dbg(&port->dev, "Fallback to passthrough decoder\n"); + return devm_cxl_add_passthrough_decoder(port); + } - return devm_cxl_enumerate_decoders(cxlhdm, NULL); + dev_err(&port->dev, "HDM decoder capability not found\n"); + return -ENXIO; } static int cxl_endpoint_port_probe(struct cxl_port *port) -- GitLab From c841ecd8277154c9297dd9ac959494f6deb61e76 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 14 Apr 2023 11:54:16 -0700 Subject: [PATCH 3168/5631] cxl/hdm: Add more HDM decoder debug messages at startup A recent debug session yielded a couple debug messages that were useful for determining the reason why the driver was or was not falling back to CXL range register emulation, and for identifying decoder setting enumeration problems. Reviewed-by: Dave Jiang Reviewed-by: Alison Schofield Link: https://lore.kernel.org/r/168149845668.792294.11814353796371419167.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/hdm.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index abe3877cfa63..7889ff203a34 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -130,6 +130,14 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info) */ for (i = 0; i < cxlhdm->decoder_count; i++) { ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i)); + dev_dbg(&info->port->dev, + "decoder%d.%d: committed: %ld base: %#x_%.8x size: %#x_%.8x\n", + info->port->id, i, + FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl), + readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i)), + readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i)), + readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i)), + readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i))); if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl)) return false; } @@ -868,6 +876,10 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld, if (rc) return rc; + dev_dbg(&port->dev, "decoder%d.%d: range: %#llx-%#llx iw: %d ig: %d\n", + port->id, cxld->id, cxld->hpa_range.start, cxld->hpa_range.end, + cxld->interleave_ways, cxld->interleave_granularity); + if (!info) { lo = readl(hdm + CXL_HDM_DECODER0_TL_LOW(which)); hi = readl(hdm + CXL_HDM_DECODER0_TL_HIGH(which)); -- GitLab From 62e8b17ffc2ff0b0e29d5e05a18570c3e70b35ff Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:07 +0100 Subject: [PATCH 3169/5631] PCI/DOE: Provide synchronous API and use it internally The DOE API only allows asynchronous exchanges and forces callers to provide a completion callback. Yet all existing callers only perform synchronous exchanges. Upcoming commits for CMA (Component Measurement and Authentication, PCIe r6.0 sec 6.31) likewise require only synchronous DOE exchanges. Provide a synchronous pci_doe() API call which builds on the internal asynchronous machinery. Convert the internal pci_doe_discovery() to the new call. The new API allows submission of const-declared requests, necessitating the addition of a const qualifier in struct pci_doe_task. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Davidlohr Bueso Reviewed-by: Dan Williams Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/0f444206da9615c56301fbaff459c0f45d27f122.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 69 ++++++++++++++++++++++++++++++++--------- include/linux/pci-doe.h | 6 +++- 2 files changed, 59 insertions(+), 16 deletions(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index e5e9b287b976..adde8c66499c 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -321,26 +321,15 @@ static int pci_doe_discovery(struct pci_doe_mb *doe_mb, u8 *index, u16 *vid, __le32 request_pl_le = cpu_to_le32(request_pl); __le32 response_pl_le; u32 response_pl; - DECLARE_COMPLETION_ONSTACK(c); - struct pci_doe_task task = { - .prot.vid = PCI_VENDOR_ID_PCI_SIG, - .prot.type = PCI_DOE_PROTOCOL_DISCOVERY, - .request_pl = &request_pl_le, - .request_pl_sz = sizeof(request_pl), - .response_pl = &response_pl_le, - .response_pl_sz = sizeof(response_pl), - .complete = pci_doe_task_complete, - .private = &c, - }; int rc; - rc = pci_doe_submit_task(doe_mb, &task); + rc = pci_doe(doe_mb, PCI_VENDOR_ID_PCI_SIG, PCI_DOE_PROTOCOL_DISCOVERY, + &request_pl_le, sizeof(request_pl_le), + &response_pl_le, sizeof(response_pl_le)); if (rc < 0) return rc; - wait_for_completion(&c); - - if (task.rv != sizeof(response_pl)) + if (rc != sizeof(response_pl_le)) return -EIO; response_pl = le32_to_cpu(response_pl_le); @@ -552,3 +541,53 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) return 0; } EXPORT_SYMBOL_GPL(pci_doe_submit_task); + +/** + * pci_doe() - Perform Data Object Exchange + * + * @doe_mb: DOE Mailbox + * @vendor: Vendor ID + * @type: Data Object Type + * @request: Request payload + * @request_sz: Size of request payload (bytes) + * @response: Response payload + * @response_sz: Size of response payload (bytes) + * + * Submit @request to @doe_mb and store the @response. + * The DOE exchange is performed synchronously and may therefore sleep. + * + * Payloads are treated as opaque byte streams which are transmitted verbatim, + * without byte-swapping. If payloads contain little-endian register values, + * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). + * + * RETURNS: Length of received response or negative errno. + * Received data in excess of @response_sz is discarded. + * The length may be smaller than @response_sz and the caller + * is responsible for checking that. + */ +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz) +{ + DECLARE_COMPLETION_ONSTACK(c); + struct pci_doe_task task = { + .prot.vid = vendor, + .prot.type = type, + .request_pl = request, + .request_pl_sz = request_sz, + .response_pl = response, + .response_pl_sz = response_sz, + .complete = pci_doe_task_complete, + .private = &c, + }; + int rc; + + rc = pci_doe_submit_task(doe_mb, &task); + if (rc) + return rc; + + wait_for_completion(&c); + + return task.rv; +} +EXPORT_SYMBOL_GPL(pci_doe); diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 43765eaf2342..5dcd54f892e5 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -49,7 +49,7 @@ struct pci_doe_mb; */ struct pci_doe_task { struct pci_doe_protocol prot; - __le32 *request_pl; + const __le32 *request_pl; size_t request_pl_sz; __le32 *response_pl; size_t response_pl_sz; @@ -78,4 +78,8 @@ struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz); + #endif -- GitLab From 58709b924ea5911b7d500bba9ed36b71e1e76598 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:08 +0100 Subject: [PATCH 3170/5631] cxl/pci: Use synchronous API for DOE A synchronous API for DOE has just been introduced. Convert CXL CDAT retrieval over to it. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Cc: Dan Williams Link: https://lore.kernel.org/r/c329c0a21c11c3b524ce2336b0bbb3c80a28c415.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 66 ++++++++++++++---------------------------- 1 file changed, 22 insertions(+), 44 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 523d5b9fd7fc..8575eaadd522 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -469,51 +469,26 @@ static struct pci_doe_mb *find_cdat_doe(struct device *uport) CXL_DOE_TABLE_ACCESS_TABLE_TYPE_CDATA) | \ FIELD_PREP(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, (entry_handle))) -static void cxl_doe_task_complete(struct pci_doe_task *task) -{ - complete(task->private); -} - -struct cdat_doe_task { - __le32 request_pl; - __le32 response_pl[32]; - struct completion c; - struct pci_doe_task task; -}; - -#define DECLARE_CDAT_DOE_TASK(req, cdt) \ -struct cdat_doe_task cdt = { \ - .c = COMPLETION_INITIALIZER_ONSTACK(cdt.c), \ - .request_pl = req, \ - .task = { \ - .prot.vid = PCI_DVSEC_VENDOR_ID_CXL, \ - .prot.type = CXL_DOE_PROTOCOL_TABLE_ACCESS, \ - .request_pl = &cdt.request_pl, \ - .request_pl_sz = sizeof(cdt.request_pl), \ - .response_pl = cdt.response_pl, \ - .response_pl_sz = sizeof(cdt.response_pl), \ - .complete = cxl_doe_task_complete, \ - .private = &cdt.c, \ - } \ -} - static int cxl_cdat_get_length(struct device *dev, struct pci_doe_mb *cdat_doe, size_t *length) { - DECLARE_CDAT_DOE_TASK(CDAT_DOE_REQ(0), t); + __le32 request = CDAT_DOE_REQ(0); + __le32 response[32]; int rc; - rc = pci_doe_submit_task(cdat_doe, &t.task); + rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL, + CXL_DOE_PROTOCOL_TABLE_ACCESS, + &request, sizeof(request), + &response, sizeof(response)); if (rc < 0) { - dev_err(dev, "DOE submit failed: %d", rc); + dev_err(dev, "DOE failed: %d", rc); return rc; } - wait_for_completion(&t.c); - if (t.task.rv < 2 * sizeof(__le32)) + if (rc < 2 * sizeof(__le32)) return -EIO; - *length = le32_to_cpu(t.response_pl[1]); + *length = le32_to_cpu(response[1]); dev_dbg(dev, "CDAT length %zu\n", *length); return 0; @@ -528,31 +503,34 @@ static int cxl_cdat_read_table(struct device *dev, int entry_handle = 0; do { - DECLARE_CDAT_DOE_TASK(CDAT_DOE_REQ(entry_handle), t); + __le32 request = CDAT_DOE_REQ(entry_handle); struct cdat_entry_header *entry; + __le32 response[32]; size_t entry_dw; int rc; - rc = pci_doe_submit_task(cdat_doe, &t.task); + rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL, + CXL_DOE_PROTOCOL_TABLE_ACCESS, + &request, sizeof(request), + &response, sizeof(response)); if (rc < 0) { - dev_err(dev, "DOE submit failed: %d", rc); + dev_err(dev, "DOE failed: %d", rc); return rc; } - wait_for_completion(&t.c); /* 1 DW Table Access Response Header + CDAT entry */ - entry = (struct cdat_entry_header *)(t.response_pl + 1); + entry = (struct cdat_entry_header *)(response + 1); if ((entry_handle == 0 && - t.task.rv != sizeof(__le32) + sizeof(struct cdat_header)) || + rc != sizeof(__le32) + sizeof(struct cdat_header)) || (entry_handle > 0 && - (t.task.rv < sizeof(__le32) + sizeof(*entry) || - t.task.rv != sizeof(__le32) + le16_to_cpu(entry->length)))) + (rc < sizeof(__le32) + sizeof(*entry) || + rc != sizeof(__le32) + le16_to_cpu(entry->length)))) return -EIO; /* Get the CXL table access header entry handle */ entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, - le32_to_cpu(t.response_pl[0])); - entry_dw = t.task.rv / sizeof(__le32); + le32_to_cpu(response[0])); + entry_dw = rc / sizeof(__le32); /* Skip Header */ entry_dw -= 1; entry_dw = min(length / sizeof(__le32), entry_dw); -- GitLab From 0821ff8ed059d38dfc9bec2106c5cc53bcaa15b1 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:09 +0100 Subject: [PATCH 3171/5631] PCI/DOE: Make asynchronous API private A synchronous API for DOE has just been introduced. CXL (the only in-tree DOE user so far) was converted to use it instead of the asynchronous API. Consequently, pci_doe_submit_task() as well as the pci_doe_task struct are only used internally, so make them private. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/cc19544068483681e91dfe27545c2180cd09f931.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 45 ++++++++++++++++++++++++++++++++++++-- include/linux/pci-doe.h | 48 ----------------------------------------- 2 files changed, 43 insertions(+), 50 deletions(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index adde8c66499c..dfdec73f6abc 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -56,6 +56,47 @@ struct pci_doe_mb { unsigned long flags; }; +struct pci_doe_protocol { + u16 vid; + u8 type; +}; + +/** + * struct pci_doe_task - represents a single query/response + * + * @prot: DOE Protocol + * @request_pl: The request payload + * @request_pl_sz: Size of the request payload (bytes) + * @response_pl: The response payload + * @response_pl_sz: Size of the response payload (bytes) + * @rv: Return value. Length of received response or error (bytes) + * @complete: Called when task is complete + * @private: Private data for the consumer + * @work: Used internally by the mailbox + * @doe_mb: Used internally by the mailbox + * + * The payload sizes and rv are specified in bytes with the following + * restrictions concerning the protocol. + * + * 1) The request_pl_sz must be a multiple of double words (4 bytes) + * 2) The response_pl_sz must be >= a single double word (4 bytes) + * 3) rv is returned as bytes but it will be a multiple of double words + */ +struct pci_doe_task { + struct pci_doe_protocol prot; + const __le32 *request_pl; + size_t request_pl_sz; + __le32 *response_pl; + size_t response_pl_sz; + int rv; + void (*complete)(struct pci_doe_task *task); + void *private; + + /* initialized by pci_doe_submit_task() */ + struct work_struct work; + struct pci_doe_mb *doe_mb; +}; + static int pci_doe_wait(struct pci_doe_mb *doe_mb, unsigned long timeout) { if (wait_event_timeout(doe_mb->wq, @@ -519,7 +560,8 @@ EXPORT_SYMBOL_GPL(pci_doe_supports_prot); * * RETURNS: 0 when task has been successfully queued, -ERRNO on error */ -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) +static int pci_doe_submit_task(struct pci_doe_mb *doe_mb, + struct pci_doe_task *task) { if (!pci_doe_supports_prot(doe_mb, task->prot.vid, task->prot.type)) return -EINVAL; @@ -540,7 +582,6 @@ int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) queue_work(doe_mb->work_queue, &task->work); return 0; } -EXPORT_SYMBOL_GPL(pci_doe_submit_task); /** * pci_doe() - Perform Data Object Exchange diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 5dcd54f892e5..7f16749c6aa3 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -13,55 +13,8 @@ #ifndef LINUX_PCI_DOE_H #define LINUX_PCI_DOE_H -struct pci_doe_protocol { - u16 vid; - u8 type; -}; - struct pci_doe_mb; -/** - * struct pci_doe_task - represents a single query/response - * - * @prot: DOE Protocol - * @request_pl: The request payload - * @request_pl_sz: Size of the request payload (bytes) - * @response_pl: The response payload - * @response_pl_sz: Size of the response payload (bytes) - * @rv: Return value. Length of received response or error (bytes) - * @complete: Called when task is complete - * @private: Private data for the consumer - * @work: Used internally by the mailbox - * @doe_mb: Used internally by the mailbox - * - * Payloads are treated as opaque byte streams which are transmitted verbatim, - * without byte-swapping. If payloads contain little-endian register values, - * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). - * - * The payload sizes and rv are specified in bytes with the following - * restrictions concerning the protocol. - * - * 1) The request_pl_sz must be a multiple of double words (4 bytes) - * 2) The response_pl_sz must be >= a single double word (4 bytes) - * 3) rv is returned as bytes but it will be a multiple of double words - * - * NOTE there is no need for the caller to initialize work or doe_mb. - */ -struct pci_doe_task { - struct pci_doe_protocol prot; - const __le32 *request_pl; - size_t request_pl_sz; - __le32 *response_pl; - size_t response_pl_sz; - int rv; - void (*complete)(struct pci_doe_task *task); - void *private; - - /* No need for the user to initialize these fields */ - struct work_struct work; - struct pci_doe_mb *doe_mb; -}; - /** * pci_doe_for_each_off - Iterate each DOE capability * @pdev: struct pci_dev to iterate @@ -76,7 +29,6 @@ struct pci_doe_task { struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, const void *request, size_t request_sz, -- GitLab From c8fc07abeba5cd14e88a2d77f4c4fed670da9492 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:10 +0100 Subject: [PATCH 3172/5631] PCI/DOE: Deduplicate mailbox flushing When a DOE mailbox is torn down, its workqueue is flushed once in pci_doe_flush_mb() through a call to flush_workqueue() and subsequently flushed once more in pci_doe_destroy_workqueue() through a call to destroy_workqueue(). Deduplicate by dropping flush_workqueue() from pci_doe_flush_mb(). Rename pci_doe_flush_mb() to pci_doe_cancel_tasks() to more aptly describe what it now does. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/1f009f60b326d1c6d776641d4b20aff27de0c234.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index dfdec73f6abc..d9f3676bce29 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -429,7 +429,7 @@ static void pci_doe_destroy_workqueue(void *mb) destroy_workqueue(doe_mb->work_queue); } -static void pci_doe_flush_mb(void *mb) +static void pci_doe_cancel_tasks(void *mb) { struct pci_doe_mb *doe_mb = mb; @@ -439,9 +439,6 @@ static void pci_doe_flush_mb(void *mb) /* Cancel an in progress work item, if necessary */ set_bit(PCI_DOE_FLAG_CANCEL, &doe_mb->flags); wake_up(&doe_mb->wq); - - /* Flush all work items */ - flush_workqueue(doe_mb->work_queue); } /** @@ -498,9 +495,9 @@ struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) /* * The state machine and the mailbox should be in sync now; - * Set up mailbox flush prior to using the mailbox to query protocols. + * Set up cancel tasks prior to using the mailbox to query protocols. */ - rc = devm_add_action_or_reset(dev, pci_doe_flush_mb, doe_mb); + rc = devm_add_action_or_reset(dev, pci_doe_cancel_tasks, doe_mb); if (rc) return ERR_PTR(rc); -- GitLab From 022b66f38195f6760c193ceee18e0b676d9c9070 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:11 +0100 Subject: [PATCH 3173/5631] PCI/DOE: Allow mailbox creation without devres management DOE mailbox creation is currently only possible through a devres-managed API. The lifetime of mailboxes thus ends with driver unbinding. An upcoming commit will create DOE mailboxes upon device enumeration by the PCI core. Their lifetime shall not be limited by a driver. Therefore rework pcim_doe_create_mb() into the non-devres-managed pci_doe_create_mb(). Add pci_doe_destroy_mb() for mailbox destruction on device removal. Provide a devres-managed wrapper under the existing pcim_doe_create_mb() name. The error path of pcim_doe_create_mb() previously called xa_destroy() if alloc_ordered_workqueue() failed. That's unnecessary because the xarray is still empty at that point. It doesn't need to be destroyed until it's been populated by pci_doe_cache_protocols(). Arrange the error path of the new pci_doe_create_mb() accordingly. pci_doe_cancel_tasks() is no longer used as callback for devm_add_action(), so refactor it to accept a struct pci_doe_mb pointer instead of a generic void pointer. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/7c9a63867d70233c5e9d26cd8bf956742cd6d650.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 103 +++++++++++++++++++++++++++++----------------- 1 file changed, 66 insertions(+), 37 deletions(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index d9f3676bce29..7539e72db5cb 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -37,7 +37,7 @@ * * This state is used to manage a single DOE mailbox capability. All fields * should be considered opaque to the consumers and the structure passed into - * the helpers below after being created by devm_pci_doe_create() + * the helpers below after being created by pci_doe_create_mb(). * * @pdev: PCI device this mailbox belongs to * @cap_offset: Capability offset @@ -415,24 +415,8 @@ static int pci_doe_cache_protocols(struct pci_doe_mb *doe_mb) return 0; } -static void pci_doe_xa_destroy(void *mb) +static void pci_doe_cancel_tasks(struct pci_doe_mb *doe_mb) { - struct pci_doe_mb *doe_mb = mb; - - xa_destroy(&doe_mb->prots); -} - -static void pci_doe_destroy_workqueue(void *mb) -{ - struct pci_doe_mb *doe_mb = mb; - - destroy_workqueue(doe_mb->work_queue); -} - -static void pci_doe_cancel_tasks(void *mb) -{ - struct pci_doe_mb *doe_mb = mb; - /* Stop all pending work items from starting */ set_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags); @@ -442,7 +426,7 @@ static void pci_doe_cancel_tasks(void *mb) } /** - * pcim_doe_create_mb() - Create a DOE mailbox object + * pci_doe_create_mb() - Create a DOE mailbox object * * @pdev: PCI device to create the DOE mailbox for * @cap_offset: Offset of the DOE mailbox @@ -453,24 +437,20 @@ static void pci_doe_cancel_tasks(void *mb) * RETURNS: created mailbox object on success * ERR_PTR(-errno) on failure */ -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) +static struct pci_doe_mb *pci_doe_create_mb(struct pci_dev *pdev, + u16 cap_offset) { struct pci_doe_mb *doe_mb; - struct device *dev = &pdev->dev; int rc; - doe_mb = devm_kzalloc(dev, sizeof(*doe_mb), GFP_KERNEL); + doe_mb = kzalloc(sizeof(*doe_mb), GFP_KERNEL); if (!doe_mb) return ERR_PTR(-ENOMEM); doe_mb->pdev = pdev; doe_mb->cap_offset = cap_offset; init_waitqueue_head(&doe_mb->wq); - xa_init(&doe_mb->prots); - rc = devm_add_action(dev, pci_doe_xa_destroy, doe_mb); - if (rc) - return ERR_PTR(rc); doe_mb->work_queue = alloc_ordered_workqueue("%s %s DOE [%x]", 0, dev_driver_string(&pdev->dev), @@ -479,36 +459,85 @@ struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) if (!doe_mb->work_queue) { pci_err(pdev, "[%x] failed to allocate work queue\n", doe_mb->cap_offset); - return ERR_PTR(-ENOMEM); + rc = -ENOMEM; + goto err_free; } - rc = devm_add_action_or_reset(dev, pci_doe_destroy_workqueue, doe_mb); - if (rc) - return ERR_PTR(rc); /* Reset the mailbox by issuing an abort */ rc = pci_doe_abort(doe_mb); if (rc) { pci_err(pdev, "[%x] failed to reset mailbox with abort command : %d\n", doe_mb->cap_offset, rc); - return ERR_PTR(rc); + goto err_destroy_wq; } /* * The state machine and the mailbox should be in sync now; - * Set up cancel tasks prior to using the mailbox to query protocols. + * Use the mailbox to query protocols. */ - rc = devm_add_action_or_reset(dev, pci_doe_cancel_tasks, doe_mb); - if (rc) - return ERR_PTR(rc); - rc = pci_doe_cache_protocols(doe_mb); if (rc) { pci_err(pdev, "[%x] failed to cache protocols : %d\n", doe_mb->cap_offset, rc); - return ERR_PTR(rc); + goto err_cancel; } return doe_mb; + +err_cancel: + pci_doe_cancel_tasks(doe_mb); + xa_destroy(&doe_mb->prots); +err_destroy_wq: + destroy_workqueue(doe_mb->work_queue); +err_free: + kfree(doe_mb); + return ERR_PTR(rc); +} + +/** + * pci_doe_destroy_mb() - Destroy a DOE mailbox object + * + * @ptr: Pointer to DOE mailbox + * + * Destroy all internal data structures created for the DOE mailbox. + */ +static void pci_doe_destroy_mb(void *ptr) +{ + struct pci_doe_mb *doe_mb = ptr; + + pci_doe_cancel_tasks(doe_mb); + xa_destroy(&doe_mb->prots); + destroy_workqueue(doe_mb->work_queue); + kfree(doe_mb); +} + +/** + * pcim_doe_create_mb() - Create a DOE mailbox object + * + * @pdev: PCI device to create the DOE mailbox for + * @cap_offset: Offset of the DOE mailbox + * + * Create a single mailbox object to manage the mailbox protocol at the + * cap_offset specified. The mailbox will automatically be destroyed on + * driver unbinding from @pdev. + * + * RETURNS: created mailbox object on success + * ERR_PTR(-errno) on failure + */ +struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) +{ + struct pci_doe_mb *doe_mb; + int rc; + + doe_mb = pci_doe_create_mb(pdev, cap_offset); + if (IS_ERR(doe_mb)) + return doe_mb; + + rc = devm_add_action_or_reset(&pdev->dev, pci_doe_destroy_mb, doe_mb); + if (rc) + return ERR_PTR(rc); + + return doe_mb; } EXPORT_SYMBOL_GPL(pcim_doe_create_mb); -- GitLab From ac04840350e2c21a17d867b262a1586603b87a92 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:12 +0100 Subject: [PATCH 3174/5631] PCI/DOE: Create mailboxes on device enumeration Currently a DOE instance cannot be shared by multiple drivers because each driver creates its own pci_doe_mb struct for a given DOE instance. For the same reason a DOE instance cannot be shared between the PCI core and a driver. Moreover, finding out which protocols a DOE instance supports requires creating a pci_doe_mb for it. If a device has multiple DOE instances, a driver looking for a specific protocol may need to create a pci_doe_mb for each of the device's DOE instances and then destroy those which do not support the desired protocol. That's obviously an inefficient way to do things. Overcome these issues by creating mailboxes in the PCI core on device enumeration. Provide a pci_find_doe_mailbox() API call to allow drivers to get a pci_doe_mb for a given (pci_dev, vendor, protocol) triple. This API is modeled after pci_find_capability() and can later be amended with a pci_find_next_doe_mailbox() call to iterate over all mailboxes of a given pci_dev which support a specific protocol. On removal, destroy the mailboxes in pci_destroy_dev(), after the driver is unbound. This allows drivers to use DOE in their ->remove() hook. On surprise removal, cancel ongoing DOE exchanges and prevent new ones from being scheduled. Thereby ensure that a hot-removed device doesn't needlessly wait for a running exchange to time out. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/40a6f973f72ef283d79dd55e7e6fddc7481199af.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 73 +++++++++++++++++++++++++++++++++++++++++ drivers/pci/pci.h | 11 +++++++ drivers/pci/probe.c | 1 + drivers/pci/remove.c | 1 + include/linux/pci-doe.h | 2 ++ include/linux/pci.h | 3 ++ 6 files changed, 91 insertions(+) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index 7539e72db5cb..9c577f5b3878 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -20,6 +20,8 @@ #include #include +#include "pci.h" + #define PCI_DOE_PROTOCOL_DISCOVERY 0 /* Timeout of 1 second from 6.30.2 Operation, PCI Spec r6.0 */ @@ -658,3 +660,74 @@ int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, return task.rv; } EXPORT_SYMBOL_GPL(pci_doe); + +/** + * pci_find_doe_mailbox() - Find Data Object Exchange mailbox + * + * @pdev: PCI device + * @vendor: Vendor ID + * @type: Data Object Type + * + * Find first DOE mailbox of a PCI device which supports the given protocol. + * + * RETURNS: Pointer to the DOE mailbox or NULL if none was found. + */ +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + if (pci_doe_supports_prot(doe_mb, vendor, type)) + return doe_mb; + + return NULL; +} +EXPORT_SYMBOL_GPL(pci_find_doe_mailbox); + +void pci_doe_init(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + u16 offset = 0; + int rc; + + xa_init(&pdev->doe_mbs); + + while ((offset = pci_find_next_ext_capability(pdev, offset, + PCI_EXT_CAP_ID_DOE))) { + doe_mb = pci_doe_create_mb(pdev, offset); + if (IS_ERR(doe_mb)) { + pci_err(pdev, "[%x] failed to create mailbox: %ld\n", + offset, PTR_ERR(doe_mb)); + continue; + } + + rc = xa_insert(&pdev->doe_mbs, offset, doe_mb, GFP_KERNEL); + if (rc) { + pci_err(pdev, "[%x] failed to insert mailbox: %d\n", + offset, rc); + pci_doe_destroy_mb(doe_mb); + } + } +} + +void pci_doe_destroy(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + pci_doe_destroy_mb(doe_mb); + + xa_destroy(&pdev->doe_mbs); +} + +void pci_doe_disconnected(struct pci_dev *pdev) +{ + struct pci_doe_mb *doe_mb; + unsigned long index; + + xa_for_each(&pdev->doe_mbs, index, doe_mb) + pci_doe_cancel_tasks(doe_mb); +} diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index d2c08670a20e..815a4d2a41da 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -318,6 +318,16 @@ struct pci_sriov { bool drivers_autoprobe; /* Auto probing of VFs by driver */ }; +#ifdef CONFIG_PCI_DOE +void pci_doe_init(struct pci_dev *pdev); +void pci_doe_destroy(struct pci_dev *pdev); +void pci_doe_disconnected(struct pci_dev *pdev); +#else +static inline void pci_doe_init(struct pci_dev *pdev) { } +static inline void pci_doe_destroy(struct pci_dev *pdev) { } +static inline void pci_doe_disconnected(struct pci_dev *pdev) { } +#endif + /** * pci_dev_set_io_state - Set the new error state if possible. * @@ -354,6 +364,7 @@ static inline bool pci_dev_set_io_state(struct pci_dev *dev, static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { pci_dev_set_io_state(dev, pci_channel_io_perm_failure); + pci_doe_disconnected(dev); return 0; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index a3f68b6ba6ac..02d2bf80eedb 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2479,6 +2479,7 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_aer_init(dev); /* Advanced Error Reporting */ pci_dpc_init(dev); /* Downstream Port Containment */ pci_rcec_init(dev); /* Root Complex Event Collector */ + pci_doe_init(dev); /* Data Object Exchange */ pcie_report_downtraining(dev); pci_init_reset_methods(dev); diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 0145aef1b930..f25acf50879f 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -39,6 +39,7 @@ static void pci_destroy_dev(struct pci_dev *dev) list_del(&dev->bus_list); up_write(&pci_bus_sem); + pci_doe_destroy(dev); pcie_aspm_exit_link_state(dev); pci_bridge_d3_update(dev); pci_free_resources(dev); diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 7f16749c6aa3..d6192ee0ac07 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -29,6 +29,8 @@ struct pci_doe_mb; struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type); int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, const void *request, size_t request_sz, diff --git a/include/linux/pci.h b/include/linux/pci.h index b50e5c79f7e3..29d99530ec17 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -511,6 +511,9 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_P2PDMA struct pci_p2pdma __rcu *p2pdma; +#endif +#ifdef CONFIG_PCI_DOE + struct xarray doe_mbs; /* Data Object Exchange mailboxes */ #endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ -- GitLab From af0a6c3587dc39df348d23c46996b9dad46d07db Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:13 +0100 Subject: [PATCH 3175/5631] cxl/pci: Use CDAT DOE mailbox created by PCI core The PCI core has just been amended to create a pci_doe_mb struct for every DOE instance on device enumeration. Drop creation of a (duplicate) CDAT DOE mailbox on cxl probing in favor of the one already created by the PCI core. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/becaf70e8faf9681d474200117d62d7eaac46cca.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 27 +++++------------------ drivers/cxl/cxlmem.h | 3 --- drivers/cxl/pci.c | 49 ------------------------------------------ 3 files changed, 5 insertions(+), 74 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 8575eaadd522..c868f4a2f1de 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -441,27 +441,6 @@ EXPORT_SYMBOL_NS_GPL(cxl_hdm_decode_init, CXL); #define CXL_DOE_TABLE_ACCESS_LAST_ENTRY 0xffff #define CXL_DOE_PROTOCOL_TABLE_ACCESS 2 -static struct pci_doe_mb *find_cdat_doe(struct device *uport) -{ - struct cxl_memdev *cxlmd; - struct cxl_dev_state *cxlds; - unsigned long index; - void *entry; - - cxlmd = to_cxl_memdev(uport); - cxlds = cxlmd->cxlds; - - xa_for_each(&cxlds->doe_mbs, index, entry) { - struct pci_doe_mb *cur = entry; - - if (pci_doe_supports_prot(cur, PCI_DVSEC_VENDOR_ID_CXL, - CXL_DOE_PROTOCOL_TABLE_ACCESS)) - return cur; - } - - return NULL; -} - #define CDAT_DOE_REQ(entry_handle) cpu_to_le32 \ (FIELD_PREP(CXL_DOE_TABLE_ACCESS_REQ_CODE, \ CXL_DOE_TABLE_ACCESS_REQ_CODE_READ) | \ @@ -559,10 +538,14 @@ void read_cdat_data(struct cxl_port *port) struct pci_doe_mb *cdat_doe; struct device *dev = &port->dev; struct device *uport = port->uport; + struct cxl_memdev *cxlmd = to_cxl_memdev(uport); + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct pci_dev *pdev = to_pci_dev(cxlds->dev); size_t cdat_length; int rc; - cdat_doe = find_cdat_doe(uport); + cdat_doe = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL, + CXL_DOE_PROTOCOL_TABLE_ACCESS); if (!cdat_doe) { dev_dbg(dev, "No CDAT mailbox\n"); return; diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 090acebba4fa..001dabf0231b 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -249,7 +249,6 @@ struct cxl_event_state { * @component_reg_phys: register base of component registers * @info: Cached DVSEC information about the device. * @serial: PCIe Device Serial Number - * @doe_mbs: PCI DOE mailbox array * @event: event log driver state * @mbox_send: @dev specific transport for transmitting mailbox commands * @@ -287,8 +286,6 @@ struct cxl_dev_state { resource_size_t component_reg_phys; u64 serial; - struct xarray doe_mbs; - struct cxl_event_state event; int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 60b23624d167..ea38bd49b0cf 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include "cxlmem.h" @@ -357,52 +356,6 @@ static int cxl_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type, return rc; } -static void cxl_pci_destroy_doe(void *mbs) -{ - xa_destroy(mbs); -} - -static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds) -{ - struct device *dev = cxlds->dev; - struct pci_dev *pdev = to_pci_dev(dev); - u16 off = 0; - - xa_init(&cxlds->doe_mbs); - if (devm_add_action(&pdev->dev, cxl_pci_destroy_doe, &cxlds->doe_mbs)) { - dev_err(dev, "Failed to create XArray for DOE's\n"); - return; - } - - /* - * Mailbox creation is best effort. Higher layers must determine if - * the lack of a mailbox for their protocol is a device failure or not. - */ - pci_doe_for_each_off(pdev, off) { - struct pci_doe_mb *doe_mb; - - doe_mb = pcim_doe_create_mb(pdev, off); - if (IS_ERR(doe_mb)) { - dev_err(dev, "Failed to create MB object for MB @ %x\n", - off); - continue; - } - - if (!pci_request_config_region_exclusive(pdev, off, - PCI_DOE_CAP_SIZEOF, - dev_name(dev))) - pci_err(pdev, "Failed to exclude DOE registers\n"); - - if (xa_insert(&cxlds->doe_mbs, off, doe_mb, GFP_KERNEL)) { - dev_err(dev, "xa_insert failed to insert MB @ %x\n", - off); - continue; - } - - dev_dbg(dev, "Created DOE mailbox @%x\n", off); - } -} - /* * Assume that any RCIEP that emits the CXL memory expander class code * is an RCD @@ -750,8 +703,6 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) cxlds->component_reg_phys = map.resource; - devm_cxl_pci_create_doe(cxlds); - rc = cxl_map_component_regs(&pdev->dev, &cxlds->regs.component, &map, BIT(CXL_CM_CAP_CAP_ID_RAS)); if (rc) -- GitLab From 74e491e5d1bcc35a699291df720191760ff4130e Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:14 +0100 Subject: [PATCH 3176/5631] PCI/DOE: Make mailbox creation API private The PCI core has just been amended to create a pci_doe_mb struct for every DOE instance on device enumeration. CXL (the only in-tree DOE user so far) has been migrated to use those mailboxes instead of creating its own. That leaves pcim_doe_create_mb() and pci_doe_for_each_off() without any callers, so drop them. pci_doe_supports_prot() is now only used internally, so declare it static. pci_doe_destroy_mb() is no longer used as callback for devm_add_action(), so refactor it to accept a struct pci_doe_mb pointer instead of a generic void pointer. Because pci_doe_create_mb() is only called on device enumeration, i.e. before driver binding, the workqueue name never contains a driver name. So replace dev_driver_string() with dev_bus_name() when generating the workqueue name. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/64f614b6584982986c55d2c6229b4ee2b276dd59.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- .clang-format | 1 - drivers/pci/doe.c | 41 ++++------------------------------------- include/linux/pci-doe.h | 14 -------------- 3 files changed, 4 insertions(+), 52 deletions(-) diff --git a/.clang-format b/.clang-format index d988e9fa9b26..1c85f6ddc71a 100644 --- a/.clang-format +++ b/.clang-format @@ -520,7 +520,6 @@ ForEachMacros: - 'of_property_for_each_string' - 'of_property_for_each_u32' - 'pci_bus_for_each_resource' - - 'pci_doe_for_each_off' - 'pcl_for_each_chunk' - 'pcl_for_each_segment' - 'pcm_for_each_format' diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index 9c577f5b3878..db9a6b0c33c7 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -455,7 +455,7 @@ static struct pci_doe_mb *pci_doe_create_mb(struct pci_dev *pdev, xa_init(&doe_mb->prots); doe_mb->work_queue = alloc_ordered_workqueue("%s %s DOE [%x]", 0, - dev_driver_string(&pdev->dev), + dev_bus_name(&pdev->dev), pci_name(pdev), doe_mb->cap_offset); if (!doe_mb->work_queue) { @@ -499,50 +499,18 @@ static struct pci_doe_mb *pci_doe_create_mb(struct pci_dev *pdev, /** * pci_doe_destroy_mb() - Destroy a DOE mailbox object * - * @ptr: Pointer to DOE mailbox + * @doe_mb: DOE mailbox * * Destroy all internal data structures created for the DOE mailbox. */ -static void pci_doe_destroy_mb(void *ptr) +static void pci_doe_destroy_mb(struct pci_doe_mb *doe_mb) { - struct pci_doe_mb *doe_mb = ptr; - pci_doe_cancel_tasks(doe_mb); xa_destroy(&doe_mb->prots); destroy_workqueue(doe_mb->work_queue); kfree(doe_mb); } -/** - * pcim_doe_create_mb() - Create a DOE mailbox object - * - * @pdev: PCI device to create the DOE mailbox for - * @cap_offset: Offset of the DOE mailbox - * - * Create a single mailbox object to manage the mailbox protocol at the - * cap_offset specified. The mailbox will automatically be destroyed on - * driver unbinding from @pdev. - * - * RETURNS: created mailbox object on success - * ERR_PTR(-errno) on failure - */ -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset) -{ - struct pci_doe_mb *doe_mb; - int rc; - - doe_mb = pci_doe_create_mb(pdev, cap_offset); - if (IS_ERR(doe_mb)) - return doe_mb; - - rc = devm_add_action_or_reset(&pdev->dev, pci_doe_destroy_mb, doe_mb); - if (rc) - return ERR_PTR(rc); - - return doe_mb; -} -EXPORT_SYMBOL_GPL(pcim_doe_create_mb); - /** * pci_doe_supports_prot() - Return if the DOE instance supports the given * protocol @@ -552,7 +520,7 @@ EXPORT_SYMBOL_GPL(pcim_doe_create_mb); * * RETURNS: True if the DOE mailbox supports the protocol specified */ -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) +static bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) { unsigned long index; void *entry; @@ -567,7 +535,6 @@ bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type) return false; } -EXPORT_SYMBOL_GPL(pci_doe_supports_prot); /** * pci_doe_submit_task() - Submit a task to be processed by the state machine diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index d6192ee0ac07..1f14aed4354b 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -15,20 +15,6 @@ struct pci_doe_mb; -/** - * pci_doe_for_each_off - Iterate each DOE capability - * @pdev: struct pci_dev to iterate - * @off: u16 of config space offset of each mailbox capability found - */ -#define pci_doe_for_each_off(pdev, off) \ - for (off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE); \ - off > 0; \ - off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE)) - -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, u8 type); -- GitLab From cedf8d8a5013ce515df2edbc52575614f3409593 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:15 +0100 Subject: [PATCH 3177/5631] PCI/DOE: Relax restrictions on request and response size An upcoming user of DOE is CMA (Component Measurement and Authentication, PCIe r6.0 sec 6.31). It builds on SPDM (Security Protocol and Data Model): https://www.dmtf.org/dsp/DSP0274 SPDM message sizes are not always a multiple of dwords. To transport them over DOE without using bounce buffers, allow sending requests and receiving responses whose final dword is only partially populated. To be clear, PCIe r6.0 sec 6.30.1 specifies the Data Object Header 2 "Length" in dwords and pci_doe_send_req() and pci_doe_recv_resp() read/write dwords. So from a spec point of view, DOE is still specified in dwords and allowing non-dword request/response buffers is merely for the convenience of callers. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Ming Li Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/151b1a6a1794afb65d941287ecbc032c5b8004b9.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/pci/doe.c | 74 +++++++++++++++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 25 deletions(-) diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index db9a6b0c33c7..1b97a5ab71a9 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -76,13 +76,6 @@ struct pci_doe_protocol { * @private: Private data for the consumer * @work: Used internally by the mailbox * @doe_mb: Used internally by the mailbox - * - * The payload sizes and rv are specified in bytes with the following - * restrictions concerning the protocol. - * - * 1) The request_pl_sz must be a multiple of double words (4 bytes) - * 2) The response_pl_sz must be >= a single double word (4 bytes) - * 3) rv is returned as bytes but it will be a multiple of double words */ struct pci_doe_task { struct pci_doe_protocol prot; @@ -153,7 +146,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, { struct pci_dev *pdev = doe_mb->pdev; int offset = doe_mb->cap_offset; - size_t length; + size_t length, remainder; u32 val; int i; @@ -171,7 +164,7 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, return -EIO; /* Length is 2 DW of header + length of payload in DW */ - length = 2 + task->request_pl_sz / sizeof(__le32); + length = 2 + DIV_ROUND_UP(task->request_pl_sz, sizeof(__le32)); if (length > PCI_DOE_MAX_LENGTH) return -EIO; if (length == PCI_DOE_MAX_LENGTH) @@ -184,10 +177,21 @@ static int pci_doe_send_req(struct pci_doe_mb *doe_mb, pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, FIELD_PREP(PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH, length)); + + /* Write payload */ for (i = 0; i < task->request_pl_sz / sizeof(__le32); i++) pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, le32_to_cpu(task->request_pl[i])); + /* Write last payload dword */ + remainder = task->request_pl_sz % sizeof(__le32); + if (remainder) { + val = 0; + memcpy(&val, &task->request_pl[i], remainder); + le32_to_cpus(&val); + pci_write_config_dword(pdev, offset + PCI_DOE_WRITE, val); + } + pci_doe_write_ctrl(doe_mb, PCI_DOE_CTRL_GO); return 0; @@ -207,11 +211,11 @@ static bool pci_doe_data_obj_ready(struct pci_doe_mb *doe_mb) static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *task) { + size_t length, payload_length, remainder, received; struct pci_dev *pdev = doe_mb->pdev; int offset = doe_mb->cap_offset; - size_t length, payload_length; + int i = 0; u32 val; - int i; /* Read the first dword to get the protocol */ pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); @@ -238,15 +242,38 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas /* First 2 dwords have already been read */ length -= 2; - payload_length = min(length, task->response_pl_sz / sizeof(__le32)); - /* Read the rest of the response payload */ - for (i = 0; i < payload_length; i++) { + received = task->response_pl_sz; + payload_length = DIV_ROUND_UP(task->response_pl_sz, sizeof(__le32)); + remainder = task->response_pl_sz % sizeof(__le32); + + /* remainder signifies number of data bytes in last payload dword */ + if (!remainder) + remainder = sizeof(__le32); + + if (length < payload_length) { + received = length * sizeof(__le32); + payload_length = length; + remainder = sizeof(__le32); + } + + if (payload_length) { + /* Read all payload dwords except the last */ + for (; i < payload_length - 1; i++) { + pci_read_config_dword(pdev, offset + PCI_DOE_READ, + &val); + task->response_pl[i] = cpu_to_le32(val); + pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + } + + /* Read last payload dword */ pci_read_config_dword(pdev, offset + PCI_DOE_READ, &val); - task->response_pl[i] = cpu_to_le32(val); + cpu_to_le32s(&val); + memcpy(&task->response_pl[i], &val, remainder); /* Prior to the last ack, ensure Data Object Ready */ - if (i == (payload_length - 1) && !pci_doe_data_obj_ready(doe_mb)) + if (!pci_doe_data_obj_ready(doe_mb)) return -EIO; pci_write_config_dword(pdev, offset + PCI_DOE_READ, 0); + i++; } /* Flush excess length */ @@ -260,7 +287,7 @@ static int pci_doe_recv_resp(struct pci_doe_mb *doe_mb, struct pci_doe_task *tas if (FIELD_GET(PCI_DOE_STATUS_ERROR, val)) return -EIO; - return min(length, task->response_pl_sz / sizeof(__le32)) * sizeof(__le32); + return received; } static void signal_task_complete(struct pci_doe_task *task, int rv) @@ -561,14 +588,6 @@ static int pci_doe_submit_task(struct pci_doe_mb *doe_mb, if (!pci_doe_supports_prot(doe_mb, task->prot.vid, task->prot.type)) return -EINVAL; - /* - * DOE requests must be a whole number of DW and the response needs to - * be big enough for at least 1 DW - */ - if (task->request_pl_sz % sizeof(__le32) || - task->response_pl_sz < sizeof(__le32)) - return -EINVAL; - if (test_bit(PCI_DOE_FLAG_DEAD, &doe_mb->flags)) return -EIO; @@ -596,6 +615,11 @@ static int pci_doe_submit_task(struct pci_doe_mb *doe_mb, * without byte-swapping. If payloads contain little-endian register values, * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). * + * For convenience, arbitrary payload sizes are allowed even though PCIe r6.0 + * sec 6.30.1 specifies the Data Object Header 2 "Length" in dwords. The last + * (partial) dword is copied with byte granularity and padded with zeroes if + * necessary. Callers are thus relieved of using dword-sized bounce buffers. + * * RETURNS: Length of received response or negative errno. * Received data in excess of @response_sz is discarded. * The length may be smaller than @response_sz and the caller -- GitLab From 7a877c923995b8257069209b1d757735af4f4ce0 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Sat, 11 Mar 2023 15:40:16 +0100 Subject: [PATCH 3178/5631] cxl/pci: Simplify CDAT retrieval error path The cdat.table and cdat.length fields in struct cxl_port are set before CDAT retrieval and must therefore be unset on failure. Simplify by setting only on success. Suggested-by: Jonathan Cameron Link: https://lore.kernel.org/linux-cxl/20230209113422.00007017@Huawei.com/ Signed-off-by: Dave Jiang [lukas: rebase and rephrase commit message] Signed-off-by: Lukas Wunner Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/7a5c7104fb6a3016dbaec1c5d0ed34619ea11a0c.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index c868f4a2f1de..0609bd629073 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -475,10 +475,10 @@ static int cxl_cdat_get_length(struct device *dev, static int cxl_cdat_read_table(struct device *dev, struct pci_doe_mb *cdat_doe, - struct cxl_cdat *cdat) + void *cdat_table, size_t *cdat_length) { - size_t length = cdat->length; - __le32 *data = cdat->table; + size_t length = *cdat_length; + __le32 *data = cdat_table; int entry_handle = 0; do { @@ -522,7 +522,7 @@ static int cxl_cdat_read_table(struct device *dev, } while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY); /* Length in CDAT header may exceed concatenation of CDAT entries */ - cdat->length -= length; + *cdat_length -= length; return 0; } @@ -542,6 +542,7 @@ void read_cdat_data(struct cxl_port *port) struct cxl_dev_state *cxlds = cxlmd->cxlds; struct pci_dev *pdev = to_pci_dev(cxlds->dev); size_t cdat_length; + void *cdat_table; int rc; cdat_doe = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL, @@ -558,19 +559,19 @@ void read_cdat_data(struct cxl_port *port) return; } - port->cdat.table = devm_kzalloc(dev, cdat_length, GFP_KERNEL); - if (!port->cdat.table) + cdat_table = devm_kzalloc(dev, cdat_length, GFP_KERNEL); + if (!cdat_table) return; - port->cdat.length = cdat_length; - rc = cxl_cdat_read_table(dev, cdat_doe, &port->cdat); + rc = cxl_cdat_read_table(dev, cdat_doe, cdat_table, &cdat_length); if (rc) { /* Don't leave table data allocated on error */ - devm_kfree(dev, port->cdat.table); - port->cdat.table = NULL; - port->cdat.length = 0; + devm_kfree(dev, cdat_table); dev_err(dev, "CDAT data read error\n"); } + + port->cdat.table = cdat_table; + port->cdat.length = cdat_length; } EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL); -- GitLab From f960e57dca9fa3653d9e9c0a9e1386d2241e0aad Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Sat, 11 Mar 2023 15:40:17 +0100 Subject: [PATCH 3179/5631] cxl/pci: Rightsize CDAT response allocation Jonathan notes that cxl_cdat_get_length() and cxl_cdat_read_table() allocate 32 dwords for the DOE response even though it may be smaller. In the case of cxl_cdat_get_length(), only the second dword of the response is of interest (it contains the length). So reduce the allocation to 2 dwords and let DOE discard the remainder. In the case of cxl_cdat_read_table(), a correctly sized allocation for the full CDAT already exists. Let DOE write each table entry directly into that allocation. There's a snag in that the table entry is preceded by a Table Access Response Header (1 dword, CXL 3.0 table 8-14). Save the last dword of the previous table entry, let DOE overwrite it with the header of the next entry and restore it afterwards. The resulting CDAT is preceded by 4 unavoidable useless bytes. Increase the allocation size accordingly. The buffer overflow check in cxl_cdat_read_table() becomes unnecessary because the remaining bytes in the allocation are tracked in "length", which is passed to DOE and limits how many bytes it writes to the allocation. Additionally, cxl_cdat_read_table() bails out if the DOE response is truncated due to insufficient space. Tested-by: Ira Weiny Signed-off-by: Lukas Wunner Reviewed-by: Jonathan Cameron Cc: Dave Jiang Link: https://lore.kernel.org/r/7a4e1f86958a79a70f29b96a92199522f08f8322.1678543498.git.lukas@wunner.de Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 0609bd629073..25b7e8125d5d 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -453,7 +453,7 @@ static int cxl_cdat_get_length(struct device *dev, size_t *length) { __le32 request = CDAT_DOE_REQ(0); - __le32 response[32]; + __le32 response[2]; int rc; rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL, @@ -464,7 +464,7 @@ static int cxl_cdat_get_length(struct device *dev, dev_err(dev, "DOE failed: %d", rc); return rc; } - if (rc < 2 * sizeof(__le32)) + if (rc < sizeof(response)) return -EIO; *length = le32_to_cpu(response[1]); @@ -477,28 +477,28 @@ static int cxl_cdat_read_table(struct device *dev, struct pci_doe_mb *cdat_doe, void *cdat_table, size_t *cdat_length) { - size_t length = *cdat_length; + size_t length = *cdat_length + sizeof(__le32); __le32 *data = cdat_table; int entry_handle = 0; + __le32 saved_dw = 0; do { __le32 request = CDAT_DOE_REQ(entry_handle); struct cdat_entry_header *entry; - __le32 response[32]; size_t entry_dw; int rc; rc = pci_doe(cdat_doe, PCI_DVSEC_VENDOR_ID_CXL, CXL_DOE_PROTOCOL_TABLE_ACCESS, &request, sizeof(request), - &response, sizeof(response)); + data, length); if (rc < 0) { dev_err(dev, "DOE failed: %d", rc); return rc; } /* 1 DW Table Access Response Header + CDAT entry */ - entry = (struct cdat_entry_header *)(response + 1); + entry = (struct cdat_entry_header *)(data + 1); if ((entry_handle == 0 && rc != sizeof(__le32) + sizeof(struct cdat_header)) || (entry_handle > 0 && @@ -508,21 +508,22 @@ static int cxl_cdat_read_table(struct device *dev, /* Get the CXL table access header entry handle */ entry_handle = FIELD_GET(CXL_DOE_TABLE_ACCESS_ENTRY_HANDLE, - le32_to_cpu(response[0])); + le32_to_cpu(data[0])); entry_dw = rc / sizeof(__le32); /* Skip Header */ entry_dw -= 1; - entry_dw = min(length / sizeof(__le32), entry_dw); - /* Prevent length < 1 DW from causing a buffer overflow */ - if (entry_dw) { - memcpy(data, entry, entry_dw * sizeof(__le32)); - length -= entry_dw * sizeof(__le32); - data += entry_dw; - } + /* + * Table Access Response Header overwrote the last DW of + * previous entry, so restore that DW + */ + *data = saved_dw; + length -= entry_dw * sizeof(__le32); + data += entry_dw; + saved_dw = *data; } while (entry_handle != CXL_DOE_TABLE_ACCESS_LAST_ENTRY); /* Length in CDAT header may exceed concatenation of CDAT entries */ - *cdat_length -= length; + *cdat_length -= length - sizeof(__le32); return 0; } @@ -559,7 +560,8 @@ void read_cdat_data(struct cxl_port *port) return; } - cdat_table = devm_kzalloc(dev, cdat_length, GFP_KERNEL); + cdat_table = devm_kzalloc(dev, cdat_length + sizeof(__le32), + GFP_KERNEL); if (!cdat_table) return; @@ -570,7 +572,7 @@ void read_cdat_data(struct cxl_port *port) dev_err(dev, "CDAT data read error\n"); } - port->cdat.table = cdat_table; + port->cdat.table = cdat_table + sizeof(__le32); port->cdat.length = cdat_length; } EXPORT_SYMBOL_NS_GPL(read_cdat_data, CXL); -- GitLab From 48380368dec14859723b9e3fbd43e042638d9a76 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 29 Mar 2023 12:14:42 +0200 Subject: [PATCH 3180/5631] Change DEFINE_SEMAPHORE() to take a number argument Fundamentally semaphores are a counted primitive, but DEFINE_SEMAPHORE() does not expose this and explicitly creates a binary semaphore. Change DEFINE_SEMAPHORE() to take a number argument and use that in the few places that open-coded it using __SEMAPHORE_INITIALIZER(). Signed-off-by: Peter Zijlstra (Intel) [mcgrof: add some tribal knowledge about why some folks prefer binary sempahores over mutexes] Reviewed-by: Sergey Senozhatsky Reviewed-by: Davidlohr Bueso Signed-off-by: Luis Chamberlain --- arch/mips/cavium-octeon/setup.c | 2 +- arch/x86/kernel/cpu/intel.c | 2 +- drivers/firmware/efi/runtime-wrappers.c | 2 +- drivers/firmware/efi/vars.c | 2 +- drivers/macintosh/adb.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/platform/x86/intel/ifs/sysfs.c | 2 +- drivers/scsi/esas2r/esas2r_ioctl.c | 2 +- .../vc04_services/interface/vchiq_arm/vchiq_arm.c | 2 +- include/linux/semaphore.h | 10 ++++++++-- kernel/printk/printk.c | 2 +- net/rxrpc/call_object.c | 6 ++---- 12 files changed, 20 insertions(+), 16 deletions(-) diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index a71727f7a608..c5561016f577 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -72,7 +72,7 @@ extern void pci_console_init(const char *arg); static unsigned long long max_memory = ULLONG_MAX; static unsigned long long reserve_low_mem; -DEFINE_SEMAPHORE(octeon_bootbus_sem); +DEFINE_SEMAPHORE(octeon_bootbus_sem, 1); EXPORT_SYMBOL(octeon_bootbus_sem); static struct octeon_boot_descriptor *octeon_boot_desc_ptr; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 291d4167fab8..12bad63822f0 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1177,7 +1177,7 @@ static const struct { static struct ratelimit_state bld_ratelimit; static unsigned int sysctl_sld_mitigate = 1; -static DEFINE_SEMAPHORE(buslock_sem); +static DEFINE_SEMAPHORE(buslock_sem, 1); #ifdef CONFIG_PROC_SYSCTL static struct ctl_table sld_sysctls[] = { diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 1fba4e09cdcf..a400c4312c82 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -158,7 +158,7 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) * none of the remaining functions are actually ever called at runtime. * So let's just use a single lock to serialize all Runtime Services calls. */ -static DEFINE_SEMAPHORE(efi_runtime_lock); +static DEFINE_SEMAPHORE(efi_runtime_lock, 1); /* * Expose the EFI runtime lock to the UV platform diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index bd75b87f5fc1..bfc5fa6aa47b 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -21,7 +21,7 @@ /* Private pointer to registered efivars */ static struct efivars *__efivars; -static DEFINE_SEMAPHORE(efivars_lock); +static DEFINE_SEMAPHORE(efivars_lock, 1); static efi_status_t check_var_size(bool nonblocking, u32 attributes, unsigned long size) diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index 23bd0c77ac1a..56599515d51a 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -80,7 +80,7 @@ static struct adb_driver *adb_controller; BLOCKING_NOTIFIER_HEAD(adb_client_list); static int adb_got_sleep; static int adb_inited; -static DEFINE_SEMAPHORE(adb_probe_mutex); +static DEFINE_SEMAPHORE(adb_probe_mutex, 1); static int sleepy_trackpad; static int autopoll_devs; int __adb_probe_sync; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 5d1e4fe335aa..5a105bab4387 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -298,7 +298,7 @@ const u32 dmae_reg_go_c[] = { /* Global resources for unloading a previously loaded device */ #define BNX2X_PREV_WAIT_NEEDED 1 -static DEFINE_SEMAPHORE(bnx2x_prev_sem); +static DEFINE_SEMAPHORE(bnx2x_prev_sem, 1); static LIST_HEAD(bnx2x_prev_list); /* Forward declaration */ diff --git a/drivers/platform/x86/intel/ifs/sysfs.c b/drivers/platform/x86/intel/ifs/sysfs.c index ee636a76b083..4c3c642ee19a 100644 --- a/drivers/platform/x86/intel/ifs/sysfs.c +++ b/drivers/platform/x86/intel/ifs/sysfs.c @@ -13,7 +13,7 @@ * Protects against simultaneous tests on multiple cores, or * reloading can file while a test is in progress */ -static DEFINE_SEMAPHORE(ifs_sem); +static DEFINE_SEMAPHORE(ifs_sem, 1); /* * The sysfs interface to check additional details of last test diff --git a/drivers/scsi/esas2r/esas2r_ioctl.c b/drivers/scsi/esas2r/esas2r_ioctl.c index e003d923acbf..055d2e87a2c8 100644 --- a/drivers/scsi/esas2r/esas2r_ioctl.c +++ b/drivers/scsi/esas2r/esas2r_ioctl.c @@ -56,7 +56,7 @@ dma_addr_t esas2r_buffered_ioctl_addr; u32 esas2r_buffered_ioctl_size; struct pci_dev *esas2r_buffered_ioctl_pcid; -static DEFINE_SEMAPHORE(buffered_ioctl_semaphore); +static DEFINE_SEMAPHORE(buffered_ioctl_semaphore, 1); typedef int (*BUFFERED_IOCTL_CALLBACK)(struct esas2r_adapter *, struct esas2r_request *, struct esas2r_sg_context *, diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index cddcd3c596c9..1a656fdc9445 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -149,7 +149,7 @@ static char *g_fragments_base; static char *g_free_fragments; static struct semaphore g_free_fragments_sema; -static DEFINE_SEMAPHORE(g_free_fragments_mutex); +static DEFINE_SEMAPHORE(g_free_fragments_mutex, 1); static int vchiq_blocking_bulk_transfer(struct vchiq_instance *instance, unsigned int handle, void *data, diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 6694d0019a68..04655faadc2d 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -25,8 +25,14 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define DEFINE_SEMAPHORE(name) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) +/* + * Unlike mutexes, binary semaphores do not have an owner, so up() can + * be called in a different thread from the one which called down(). + * It is also safe to call down_trylock() and up() from interrupt + * context. + */ +#define DEFINE_SEMAPHORE(_name, _n) \ + struct semaphore _name = __SEMAPHORE_INITIALIZER(_name, _n) static inline void sema_init(struct semaphore *sem, int val) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fd0c9f913940..76987aaa5a45 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -89,7 +89,7 @@ static DEFINE_MUTEX(console_mutex); * console_sem protects updates to console->seq and console_suspended, * and also provides serialization for console printing. */ -static DEFINE_SEMAPHORE(console_sem); +static DEFINE_SEMAPHORE(console_sem, 1); HLIST_HEAD(console_list); EXPORT_SYMBOL_GPL(console_list); DEFINE_STATIC_SRCU(console_srcu); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index e9f1f49d18c2..3e5cc70884dd 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -40,10 +40,8 @@ const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = { struct kmem_cache *rxrpc_call_jar; -static struct semaphore rxrpc_call_limiter = - __SEMAPHORE_INITIALIZER(rxrpc_call_limiter, 1000); -static struct semaphore rxrpc_kernel_call_limiter = - __SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000); +static DEFINE_SEMAPHORE(rxrpc_call_limiter, 1000); +static DEFINE_SEMAPHORE(rxrpc_kernel_call_limiter, 1000); void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) { -- GitLab From 25a1b5b518f4336bff934ac8348da6c57158363a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 24 Mar 2023 18:38:00 -0700 Subject: [PATCH 3181/5631] modules/kmod: replace implementation with a semaphore Simplify the concurrency delimiter we use for kmod with the semaphore. I had used the kmod strategy to try to implement a similar concurrency delimiter for the kernel_read*() calls from the finit_module() path so to reduce vmalloc() memory pressure. That effort didn't provide yet conclusive results, but one thing that became clear is we can use the suggested alternative solution with semaphores which Linus hinted at instead of using the atomic / wait strategy. I've stress tested this with kmod test 0008: time /data/linux-next/tools/testing/selftests/kmod/kmod.sh -t 0008 And I get only a *slight* delay. That delay however is small, a few seconds for a full test loop run that runs 150 times, for about ~30-40 seconds. The small delay is worth the simplfication IMHO. Reviewed-by: Davidlohr Bueso Reviewed-by: Miroslav Benes Reviewed-by: David Hildenbrand Signed-off-by: Luis Chamberlain --- kernel/module/kmod.c | 26 +++++++------------------- 1 file changed, 7 insertions(+), 19 deletions(-) diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c index b717134ebe17..5899083436a3 100644 --- a/kernel/module/kmod.c +++ b/kernel/module/kmod.c @@ -40,8 +40,7 @@ * effect. Systems like these are very unlikely if modules are enabled. */ #define MAX_KMOD_CONCURRENT 50 -static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT); -static DECLARE_WAIT_QUEUE_HEAD(kmod_wq); +static DEFINE_SEMAPHORE(kmod_concurrent_max, MAX_KMOD_CONCURRENT); /* * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads @@ -148,29 +147,18 @@ int __request_module(bool wait, const char *fmt, ...) if (ret) return ret; - if (atomic_dec_if_positive(&kmod_concurrent_max) < 0) { - pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...", - atomic_read(&kmod_concurrent_max), - MAX_KMOD_CONCURRENT, module_name); - ret = wait_event_killable_timeout(kmod_wq, - atomic_dec_if_positive(&kmod_concurrent_max) >= 0, - MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); - if (!ret) { - pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", - module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); - return -ETIME; - } else if (ret == -ERESTARTSYS) { - pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name); - return ret; - } + ret = down_timeout(&kmod_concurrent_max, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); + if (ret) { + pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", + module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); + return ret; } trace_module_request(module_name, wait, _RET_IP_); ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); - atomic_inc(&kmod_concurrent_max); - wake_up(&kmod_wq); + up(&kmod_concurrent_max); return ret; } -- GitLab From f71afa6a420111da90657fe999a8e32c42d5c7d6 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 20:05:52 -0800 Subject: [PATCH 3182/5631] module: extract patient module check into helper The patient module check inside add_unformed_module() is large enough as we need it. It is a bit hard to read too, so just move it to a helper and do the inverse checks first to help shift the code and make it easier to read. The new helper then is module_patient_check_exists(). To make this work we need to mvoe the finished_loading() up, we do that without making any functional changes to that routine. Reviewed-by: David Hildenbrand Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 112 +++++++++++++++++++++++-------------------- 1 file changed, 60 insertions(+), 52 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 32554d8a5791..75b23257128d 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2447,27 +2447,6 @@ static int post_relocation(struct module *mod, const struct load_info *info) return module_finalize(info->hdr, info->sechdrs, mod); } -/* Is this module of this name done loading? No locks held. */ -static bool finished_loading(const char *name) -{ - struct module *mod; - bool ret; - - /* - * The module_mutex should not be a heavily contended lock; - * if we get the occasional sleep here, we'll go an extra iteration - * in the wait_event_interruptible(), which is harmless. - */ - sched_annotate_sleep(); - mutex_lock(&module_mutex); - mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE - || mod->state == MODULE_STATE_GOING; - mutex_unlock(&module_mutex); - - return ret; -} - /* Call module constructors. */ static void do_mod_ctors(struct module *mod) { @@ -2631,6 +2610,63 @@ static int may_init_module(void) return 0; } +/* Is this module of this name done loading? No locks held. */ +static bool finished_loading(const char *name) +{ + struct module *mod; + bool ret; + + /* + * The module_mutex should not be a heavily contended lock; + * if we get the occasional sleep here, we'll go an extra iteration + * in the wait_event_interruptible(), which is harmless. + */ + sched_annotate_sleep(); + mutex_lock(&module_mutex); + mod = find_module_all(name, strlen(name), true); + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; + mutex_unlock(&module_mutex); + + return ret; +} + +/* Must be called with module_mutex held */ +static int module_patient_check_exists(const char *name) +{ + struct module *old; + int err = 0; + + old = find_module_all(name, strlen(name), true); + if (old == NULL) + return 0; + + if (old->state == MODULE_STATE_COMING || + old->state == MODULE_STATE_UNFORMED) { + /* Wait in case it fails to load. */ + mutex_unlock(&module_mutex); + err = wait_event_interruptible(module_wq, + finished_loading(name)); + mutex_lock(&module_mutex); + if (err) + return err; + + /* The module might have gone in the meantime. */ + old = find_module_all(name, strlen(name), true); + } + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + return -EEXIST; + return -EBUSY; +} + /* * We try to place it in the list now to make sure it's unique before * we dedicate too many resources. In particular, temporary percpu @@ -2639,41 +2675,14 @@ static int may_init_module(void) static int add_unformed_module(struct module *mod) { int err; - struct module *old; mod->state = MODULE_STATE_UNFORMED; mutex_lock(&module_mutex); - old = find_module_all(mod->name, strlen(mod->name), true); - if (old != NULL) { - if (old->state == MODULE_STATE_COMING - || old->state == MODULE_STATE_UNFORMED) { - /* Wait in case it fails to load. */ - mutex_unlock(&module_mutex); - err = wait_event_interruptible(module_wq, - finished_loading(mod->name)); - if (err) - goto out_unlocked; - - /* The module might have gone in the meantime. */ - mutex_lock(&module_mutex); - old = find_module_all(mod->name, strlen(mod->name), - true); - } - - /* - * We are here only when the same module was being loaded. Do - * not try to load it again right now. It prevents long delays - * caused by serialized module load failures. It might happen - * when more devices of the same type trigger load of - * a particular module. - */ - if (old && old->state == MODULE_STATE_LIVE) - err = -EEXIST; - else - err = -EBUSY; + err = module_patient_check_exists(mod->name); + if (err) goto out; - } + mod_update_bounds(mod); list_add_rcu(&mod->list, &modules); mod_tree_insert(mod); @@ -2681,7 +2690,6 @@ static int add_unformed_module(struct module *mod) out: mutex_unlock(&module_mutex); -out_unlocked: return err; } -- GitLab From df3e764d8e5cd416efee29e0de3c93917dff5d33 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 28 Mar 2023 20:03:19 -0700 Subject: [PATCH 3183/5631] module: add debug stats to help identify memory pressure Loading modules with finit_module() can end up using vmalloc(), vmap() and vmalloc() again, for a total of up to 3 separate allocations in the worst case for a single module. We always kernel_read*() the module, that's a vmalloc(). Then vmap() is used for the module decompression, and if so the last read buffer is freed as we use the now decompressed module buffer to stuff data into our copy module. The last allocation is specific to each architectures but pretty much that's generally a series of vmalloc() calls or a variation of vmalloc to handle ELF sections with special permissions. Evaluation with new stress-ng module support [1] with just 100 ops is proving that you can end up using GiBs of data easily even with all care we have in the kernel and userspace today in trying to not load modules which are already loaded. 100 ops seems to resemble the sort of pressure a system with about 400 CPUs can create on module loading. Although issues relating to duplicate module requests due to each CPU inucurring a new module reuest is silly and some of these are being fixed, we currently lack proper tooling to help diagnose easily what happened, when it happened and who likely is to blame -- userspace or kernel module autoloading. Provide an initial set of stats which use debugfs to let us easily scrape post-boot information about failed loads. This sort of information can be used on production worklaods to try to optimize *avoiding* redundant memory pressure using finit_module(). There's a few examples that can be provided: A 255 vCPU system without the next patch in this series applied: Startup finished in 19.143s (kernel) + 7.078s (userspace) = 26.221s graphical.target reached after 6.988s in userspace And 13.58 GiB of virtual memory space lost due to failed module loading: root@big ~ # cat /sys/kernel/debug/modules/stats Mods ever loaded 67 Mods failed on kread 0 Mods failed on decompress 0 Mods failed on becoming 0 Mods failed on load 1411 Total module size 11464704 Total mod text size 4194304 Failed kread bytes 0 Failed decompress bytes 0 Failed becoming bytes 0 Failed kmod bytes 14588526272 Virtual mem wasted bytes 14588526272 Average mod size 171115 Average mod text size 62602 Average fail load bytes 10339140 Duplicate failed modules: module-name How-many-times Reason kvm_intel 249 Load kvm 249 Load irqbypass 8 Load crct10dif_pclmul 128 Load ghash_clmulni_intel 27 Load sha512_ssse3 50 Load sha512_generic 200 Load aesni_intel 249 Load crypto_simd 41 Load cryptd 131 Load evdev 2 Load serio_raw 1 Load virtio_pci 3 Load nvme 3 Load nvme_core 3 Load virtio_pci_legacy_dev 3 Load virtio_pci_modern_dev 3 Load t10_pi 3 Load virtio 3 Load crc32_pclmul 6 Load crc64_rocksoft 3 Load crc32c_intel 40 Load virtio_ring 3 Load crc64 3 Load The following screen shot, of a simple 8vcpu 8 GiB KVM guest with the next patch in this series applied, shows 226.53 MiB are wasted in virtual memory allocations which due to duplicate module requests during boot. It also shows an average module memory size of 167.10 KiB and an an average module .text + .init.text size of 61.13 KiB. The end shows all modules which were detected as duplicate requests and whether or not they failed early after just the first kernel_read*() call or late after we've already allocated the private space for the module in layout_and_allocate(). A system with module decompression would reveal more wasted virtual memory space. We should put effort now into identifying the source of these duplicate module requests and trimming these down as much possible. Larger systems will obviously show much more wasted virtual memory allocations. root@kmod ~ # cat /sys/kernel/debug/modules/stats Mods ever loaded 67 Mods failed on kread 0 Mods failed on decompress 0 Mods failed on becoming 83 Mods failed on load 16 Total module size 11464704 Total mod text size 4194304 Failed kread bytes 0 Failed decompress bytes 0 Failed becoming bytes 228959096 Failed kmod bytes 8578080 Virtual mem wasted bytes 237537176 Average mod size 171115 Average mod text size 62602 Avg fail becoming bytes 2758544 Average fail load bytes 536130 Duplicate failed modules: module-name How-many-times Reason kvm_intel 7 Becoming kvm 7 Becoming irqbypass 6 Becoming & Load crct10dif_pclmul 7 Becoming & Load ghash_clmulni_intel 7 Becoming & Load sha512_ssse3 6 Becoming & Load sha512_generic 7 Becoming & Load aesni_intel 7 Becoming crypto_simd 7 Becoming & Load cryptd 3 Becoming & Load evdev 1 Becoming serio_raw 1 Becoming nvme 3 Becoming nvme_core 3 Becoming t10_pi 3 Becoming virtio_pci 3 Becoming crc32_pclmul 6 Becoming & Load crc64_rocksoft 3 Becoming crc32c_intel 3 Becoming virtio_pci_modern_dev 2 Becoming virtio_pci_legacy_dev 1 Becoming crc64 2 Becoming virtio 2 Becoming virtio_ring 2 Becoming [0] https://github.com/ColinIanKing/stress-ng.git [1] echo 0 > /proc/sys/vm/oom_dump_tasks ./stress-ng --module 100 --module-name xfs Signed-off-by: Luis Chamberlain --- Documentation/core-api/kernel-api.rst | 22 +- kernel/module/Kconfig | 41 ++- kernel/module/Makefile | 1 + kernel/module/decompress.c | 4 + kernel/module/internal.h | 78 +++++ kernel/module/main.c | 65 +++- kernel/module/stats.c | 430 ++++++++++++++++++++++++++ kernel/module/tracking.c | 7 +- 8 files changed, 635 insertions(+), 13 deletions(-) create mode 100644 kernel/module/stats.c diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index e27728596008..9b3f3e5f5a95 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -220,12 +220,30 @@ relay interface Module Support ============== -Module Loading --------------- +Kernel module auto-loading +-------------------------- .. kernel-doc:: kernel/module/kmod.c :export: +Module debugging +---------------- + +.. kernel-doc:: kernel/module/stats.c + :doc: module debugging statistics overview + +dup_failed_modules - tracks duplicate failed modules +**************************************************** + +.. kernel-doc:: kernel/module/stats.c + :doc: dup_failed_modules - tracks duplicate failed modules + +module statistics debugfs counters +********************************** + +.. kernel-doc:: kernel/module/stats.c + :doc: module statistics debugfs counters + Inter Module support -------------------- diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 424b3bc58f3f..e6df183e2c80 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -22,6 +22,45 @@ menuconfig MODULES if MODULES +config MODULE_DEBUGFS + bool + +config MODULE_DEBUG + bool "Module debugging" + depends on DEBUG_FS + help + Allows you to enable / disable features which can help you debug + modules. You don't need these options on production systems. + +if MODULE_DEBUG + +config MODULE_STATS + bool "Module statistics" + depends on DEBUG_FS + select MODULE_DEBUGFS + help + This option allows you to maintain a record of module statistics. + For example, size of all modules, average size, text size, a list + of failed modules and the size for each of those. For failed + modules we keep track of modules which failed due to either the + existing module taking too long to load or that module was already + loaded. + + You should enable this if you are debugging production loads + and want to see if userspace or the kernel is doing stupid things + with loading modules when it shouldn't or if you want to help + optimize userspace / kernel space module autoloading schemes. + You might want to do this because failed modules tend to use + up significant amount of memory, and so you'd be doing everyone a + favor in avoiding these failures proactively. + + This functionality is also useful for those experimenting with + module .text ELF section optimization. + + If unsure, say N. + +endif # MODULE_DEBUG + config MODULE_FORCE_LOAD bool "Forced module loading" default n @@ -51,7 +90,7 @@ config MODULE_FORCE_UNLOAD config MODULE_UNLOAD_TAINT_TRACKING bool "Tainted module unload tracking" depends on MODULE_UNLOAD - default n + select MODULE_DEBUGFS help This option allows you to maintain a record of each unloaded module that tainted the kernel. In addition to displaying a diff --git a/kernel/module/Makefile b/kernel/module/Makefile index 5b1d26b53b8d..52340bce497e 100644 --- a/kernel/module/Makefile +++ b/kernel/module/Makefile @@ -21,3 +21,4 @@ obj-$(CONFIG_SYSFS) += sysfs.o obj-$(CONFIG_KGDB_KDB) += kdb.o obj-$(CONFIG_MODVERSIONS) += version.o obj-$(CONFIG_MODULE_UNLOAD_TAINT_TRACKING) += tracking.o +obj-$(CONFIG_MODULE_STATS) += stats.o diff --git a/kernel/module/decompress.c b/kernel/module/decompress.c index 7ddc87bee274..e97232b125eb 100644 --- a/kernel/module/decompress.c +++ b/kernel/module/decompress.c @@ -297,6 +297,10 @@ int module_decompress(struct load_info *info, const void *buf, size_t size) ssize_t data_size; int error; +#if defined(CONFIG_MODULE_STATS) + info->compressed_len = size; +#endif + /* * Start with number of pages twice as big as needed for * compressed data. diff --git a/kernel/module/internal.h b/kernel/module/internal.h index 6ae29bb8836f..1fd75dd346dc 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -59,6 +59,9 @@ struct load_info { unsigned long mod_kallsyms_init_off; #endif #ifdef CONFIG_MODULE_DECOMPRESS +#ifdef CONFIG_MODULE_STATS + unsigned long compressed_len; +#endif struct page **pages; unsigned int max_pages; unsigned int used_pages; @@ -143,6 +146,81 @@ static inline bool set_livepatch_module(struct module *mod) #endif } +/** + * enum fail_dup_mod_reason - state at which a duplicate module was detected + * + * @FAIL_DUP_MOD_BECOMING: the module is read properly, passes all checks but + * we've determined that another module with the same name is already loaded + * or being processed on our &modules list. This happens on early_mod_check() + * right before layout_and_allocate(). The kernel would have already + * vmalloc()'d space for the entire module through finit_module(). If + * decompression was used two vmap() spaces were used. These failures can + * happen when userspace has not seen the module present on the kernel and + * tries to load the module multiple times at same time. + * @FAIL_DUP_MOD_LOAD: the module has been read properly, passes all validation + * checks and the kernel determines that the module was unique and because + * of this allocated yet another private kernel copy of the module space in + * layout_and_allocate() but after this determined in add_unformed_module() + * that another module with the same name is already loaded or being processed. + * These failures should be mitigated as much as possible and are indicative + * of really fast races in loading modules. Without module decompression + * they waste twice as much vmap space. With module decompression three + * times the module's size vmap space is wasted. + */ +enum fail_dup_mod_reason { + FAIL_DUP_MOD_BECOMING = 0, + FAIL_DUP_MOD_LOAD, +}; + +#ifdef CONFIG_MODULE_DEBUGFS +extern struct dentry *mod_debugfs_root; +#endif + +#ifdef CONFIG_MODULE_STATS + +#define mod_stat_add_long(count, var) atomic_long_add(count, var) +#define mod_stat_inc(name) atomic_inc(name) + +extern atomic_long_t total_mod_size; +extern atomic_long_t total_text_size; +extern atomic_long_t invalid_kread_bytes; +extern atomic_long_t invalid_decompress_bytes; + +extern atomic_t modcount; +extern atomic_t failed_kreads; +extern atomic_t failed_decompress; +struct mod_fail_load { + struct list_head list; + char name[MODULE_NAME_LEN]; + atomic_long_t count; + unsigned long dup_fail_mask; +}; + +int try_add_failed_module(const char *name, enum fail_dup_mod_reason reason); +void mod_stat_bump_invalid(struct load_info *info, int flags); +void mod_stat_bump_becoming(struct load_info *info, int flags); + +#else + +#define mod_stat_add_long(name, var) +#define mod_stat_inc(name) + +static inline int try_add_failed_module(const char *name, + enum fail_dup_mod_reason reason) +{ + return 0; +} + +static inline void mod_stat_bump_invalid(struct load_info *info, int flags) +{ +} + +static inline void mod_stat_bump_becoming(struct load_info *info, int flags) +{ +} + +#endif /* CONFIG_MODULE_STATS */ + #ifdef CONFIG_MODULE_UNLOAD_TAINT_TRACKING struct mod_unload_taint { struct list_head list; diff --git a/kernel/module/main.c b/kernel/module/main.c index 75b23257128d..01fffa8afef2 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include "internal.h" @@ -2500,6 +2501,18 @@ static noinline int do_init_module(struct module *mod) { int ret = 0; struct mod_initfree *freeinit; +#if defined(CONFIG_MODULE_STATS) + unsigned int text_size = 0, total_size = 0; + + for_each_mod_mem_type(type) { + const struct module_memory *mod_mem = &mod->mem[type]; + if (mod_mem->size) { + total_size += mod_mem->size; + if (type == MOD_TEXT || type == MOD_INIT_TEXT) + text_size += mod_mem->size; + } + } +#endif freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL); if (!freeinit) { @@ -2561,6 +2574,7 @@ static noinline int do_init_module(struct module *mod) mod->mem[type].base = NULL; mod->mem[type].size = 0; } + #ifdef CONFIG_DEBUG_INFO_BTF_MODULES /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ mod->btf_data = NULL; @@ -2584,6 +2598,11 @@ static noinline int do_init_module(struct module *mod) mutex_unlock(&module_mutex); wake_up_all(&module_wq); + mod_stat_add_long(text_size, &total_text_size); + mod_stat_add_long(total_size, &total_mod_size); + + mod_stat_inc(&modcount); + return 0; fail_free_freeinit: @@ -2599,6 +2618,7 @@ static noinline int do_init_module(struct module *mod) ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); + return ret; } @@ -2632,7 +2652,8 @@ static bool finished_loading(const char *name) } /* Must be called with module_mutex held */ -static int module_patient_check_exists(const char *name) +static int module_patient_check_exists(const char *name, + enum fail_dup_mod_reason reason) { struct module *old; int err = 0; @@ -2655,6 +2676,9 @@ static int module_patient_check_exists(const char *name) old = find_module_all(name, strlen(name), true); } + if (try_add_failed_module(name, reason)) + pr_warn("Could not add fail-tracking for module: %s\n", name); + /* * We are here only when the same module was being loaded. Do * not try to load it again right now. It prevents long delays @@ -2679,7 +2703,7 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; mutex_lock(&module_mutex); - err = module_patient_check_exists(mod->name); + err = module_patient_check_exists(mod->name, FAIL_DUP_MOD_LOAD); if (err) goto out; @@ -2800,6 +2824,7 @@ static int load_module(struct load_info *info, const char __user *uargs, int flags) { struct module *mod; + bool module_allocated = false; long err = 0; char *after_dashes; @@ -2839,6 +2864,8 @@ static int load_module(struct load_info *info, const char __user *uargs, goto free_copy; } + module_allocated = true; + audit_log_kern_module(mod->name); /* Reserve our place in the list. */ @@ -2983,6 +3010,7 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_rcu(); mutex_unlock(&module_mutex); free_module: + mod_stat_bump_invalid(info, flags); /* Free lock-classes; relies on the preceding sync_rcu() */ for_class_mod_mem_type(type, core_data) { lockdep_free_key_range(mod->mem[type].base, @@ -2991,6 +3019,13 @@ static int load_module(struct load_info *info, const char __user *uargs, module_deallocate(mod, info); free_copy: + /* + * The info->len is always set. We distinguish between + * failures once the proper module was allocated and + * before that. + */ + if (!module_allocated) + mod_stat_bump_becoming(info, flags); free_copy(info, flags); return err; } @@ -3009,8 +3044,11 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, umod, len, uargs); err = copy_module_from_user(umod, len, &info); - if (err) + if (err) { + mod_stat_inc(&failed_kreads); + mod_stat_add_long(len, &invalid_kread_bytes); return err; + } return load_module(&info, uargs, 0); } @@ -3035,14 +3073,20 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); - if (len < 0) + if (len < 0) { + mod_stat_inc(&failed_kreads); + mod_stat_add_long(len, &invalid_kread_bytes); return len; + } if (flags & MODULE_INIT_COMPRESSED_FILE) { err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ - if (err) + if (err) { + mod_stat_inc(&failed_decompress); + mod_stat_add_long(len, &invalid_decompress_bytes); return err; + } } else { info.hdr = buf; info.len = len; @@ -3216,3 +3260,14 @@ void print_modules(void) last_unloaded_module.taints); pr_cont("\n"); } + +#ifdef CONFIG_MODULE_DEBUGFS +struct dentry *mod_debugfs_root; + +static int module_debugfs_init(void) +{ + mod_debugfs_root = debugfs_create_dir("modules", NULL); + return 0; +} +module_init(module_debugfs_init); +#endif diff --git a/kernel/module/stats.c b/kernel/module/stats.c new file mode 100644 index 000000000000..3d45744b3920 --- /dev/null +++ b/kernel/module/stats.c @@ -0,0 +1,430 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Debugging module statistics. + * + * Copyright (C) 2023 Luis Chamberlain + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "internal.h" + +/** + * DOC: module debugging statistics overview + * + * Enabling CONFIG_MODULE_STATS enables module debugging statistics which + * are useful to monitor and root cause memory pressure issues with module + * loading. These statistics are useful to allow us to improve production + * workloads. + * + * The current module debugging statistics supported help keep track of module + * loading failures to enable improvements either for kernel module auto-loading + * usage (request_module()) or interactions with userspace. Statistics are + * provided to track all possible failures in the finit_module() path and memory + * wasted in this process space. Each of the failure counters are associated + * to a type of module loading failure which is known to incur a certain amount + * of memory allocation loss. In the worst case loading a module will fail after + * a 3 step memory allocation process: + * + * a) memory allocated with kernel_read_file_from_fd() + * b) module decompression processes the file read from + * kernel_read_file_from_fd(), and vmap() is used to map + * the decompressed module to a new local buffer which represents + * a copy of the decompressed module passed from userspace. The buffer + * from kernel_read_file_from_fd() is freed right away. + * c) layout_and_allocate() allocates space for the final resting + * place where we would keep the module if it were to be processed + * successfully. + * + * If a failure occurs after these three different allocations only one + * counter will be incremented with the summation of the allocated bytes freed + * incurred during this failure. Likewise, if module loading failed only after + * step b) a separate counter is used and incremented for the bytes freed and + * not used during both of those allocations. + * + * Virtual memory space can be limited, for example on x86 virtual memory size + * defaults to 128 MiB. We should strive to limit and avoid wasting virtual + * memory allocations when possible. These module debugging statistics help + * to evaluate how much memory is being wasted on bootup due to module loading + * failures. + * + * All counters are designed to be incremental. Atomic counters are used so to + * remain simple and avoid delays and deadlocks. + */ + +/** + * DOC: dup_failed_modules - tracks duplicate failed modules + * + * Linked list of modules which failed to be loaded because an already existing + * module with the same name was already being processed or already loaded. + * The finit_module() system call incurs heavy virtual memory allocations. In + * the worst case an finit_module() system call can end up allocating virtual + * memory 3 times: + * + * 1) kernel_read_file_from_fd() call uses vmalloc() + * 2) optional module decompression uses vmap() + * 3) layout_and allocate() can use vzalloc() or an arch specific variation of + * vmalloc to deal with ELF sections requiring special permissions + * + * In practice on a typical boot today most finit_module() calls fail due to + * the module with the same name already being loaded or about to be processed. + * All virtual memory allocated to these failed modules will be freed with + * no functional use. + * + * To help with this the dup_failed_modules allows us to track modules which + * failed to load due to the fact that a module was already loaded or being + * processed. There are only two points at which we can fail such calls, + * we list them below along with the number of virtual memory allocation + * calls: + * + * a) FAIL_DUP_MOD_BECOMING: at the end of early_mod_check() before + * layout_and_allocate(). This does not yet happen. + * - with module decompression: 2 virtual memory allocation calls + * - without module decompression: 1 virtual memory allocation calls + * b) FAIL_DUP_MOD_LOAD: after layout_and_allocate() on add_unformed_module() + * - with module decompression 3 virtual memory allocation calls + * - without module decompression 2 virtual memory allocation calls + * + * We should strive to get this list to be as small as possible. If this list + * is not empty it is a reflection of possible work or optimizations possible + * either in-kernel or in userspace. + */ +static LIST_HEAD(dup_failed_modules); + +/** + * DOC: module statistics debugfs counters + * + * The total amount of wasted virtual memory allocation space during module + * loading can be computed by adding the total from the summation: + * + * * @invalid_kread_bytes + + * @invalid_decompress_bytes + + * @invalid_becoming_bytes + + * @invalid_mod_bytes + * + * The following debugfs counters are available to inspect module loading + * failures: + * + * * total_mod_size: total bytes ever used by all modules we've dealt with on + * this system + * * total_text_size: total bytes of the .text and .init.text ELF section + * sizes we've dealt with on this system + * * invalid_kread_bytes: bytes allocated and then freed on failures which + * happen due to the initial kernel_read_file_from_fd(). kernel_read_file_from_fd() + * uses vmalloc(). These should typically not happen unless your system is + * under memory pressure. + * * invalid_decompress_bytes: number of bytes allocated and freed due to + * memory allocations in the module decompression path that use vmap(). + * These typically should not happen unless your system is under memory + * pressure. + * * invalid_becoming_bytes: total number of bytes allocated and freed used + * used to read the kernel module userspace wants us to read before we + * promote it to be processed to be added to our @modules linked list. + * These failures could in theory happen if we had a check in + * between a successful kernel_read_file_from_fd() + * call and right before we allocate the our private memory for the module + * which would be kept if the module is successfully loaded. The most common + * reason for this failure is when userspace is racing to load a module + * which it does not yet see loaded. The first module to succeed in + * add_unformed_module() will add a module to our &modules list and + * subsequent loads of modules with the same name will error out at the + * end of early_mod_check(). A check for module_patient_check_exists() + * at the end of early_mod_check() could be added to prevent duplicate allocations + * on layout_and_allocate() for modules already being processed. These + * duplicate failed modules are non-fatal, however they typically are + * indicative of userspace not seeing a module in userspace loaded yet and + * unnecessarily trying to load a module before the kernel even has a chance + * to begin to process prior requests. Although duplicate failures can be + * non-fatal, we should try to reduce vmalloc() pressure proactively, so + * ideally after boot this will be close to as 0 as possible. If module + * decompression was used we also add to this counter the cost of the + * initial kernel_read_file_from_fd() of the compressed module. If module + * decompression was not used the value represents the total allocated and + * freed bytes in kernel_read_file_from_fd() calls for these type of + * failures. These failures can occur because: + * + * * module_sig_check() - module signature checks + * * elf_validity_cache_copy() - some ELF validation issue + * * early_mod_check(): + * + * * blacklisting + * * failed to rewrite section headers + * * version magic + * * live patch requirements didn't check out + * * the module was detected as being already present + * + * * invalid_mod_bytes: these are the total number of bytes allocated and + * freed due to failures after we did all the sanity checks of the module + * which userspace passed to us and after our first check that the module + * is unique. A module can still fail to load if we detect the module is + * loaded after we allocate space for it with layout_and_allocate(), we do + * this check right before processing the module as live and run its + * initialization routines. Note that you have a failure of this type it + * also means the respective kernel_read_file_from_fd() memory space was + * also freed and not used, and so we increment this counter with twice + * the size of the module. Additionally if you used module decompression + * the size of the compressed module is also added to this counter. + * + * * modcount: how many modules we've loaded in our kernel life time + * * failed_kreads: how many modules failed due to failed kernel_read_file_from_fd() + * * failed_decompress: how many failed module decompression attempts we've had. + * These really should not happen unless your compression / decompression + * might be broken. + * * failed_becoming: how many modules failed after we kernel_read_file_from_fd() + * it and before we allocate memory for it with layout_and_allocate(). This + * counter is never incremented if you manage to validate the module and + * call layout_and_allocate() for it. + * * failed_load_modules: how many modules failed once we've allocated our + * private space for our module using layout_and_allocate(). These failures + * should hopefully mostly be dealt with already. Races in theory could + * still exist here, but it would just mean the kernel had started processing + * two threads concurrently up to early_mod_check() and one thread won. + * These failures are good signs the kernel or userspace is doing something + * seriously stupid or that could be improved. We should strive to fix these, + * but it is perhaps not easy to fix them. A recent example are the modules + * requests incurred for frequency modules, a separate module request was + * being issued for each CPU on a system. + */ + +atomic_long_t total_mod_size; +atomic_long_t total_text_size; +atomic_long_t invalid_kread_bytes; +atomic_long_t invalid_decompress_bytes; +static atomic_long_t invalid_becoming_bytes; +static atomic_long_t invalid_mod_bytes; +atomic_t modcount; +atomic_t failed_kreads; +atomic_t failed_decompress; +static atomic_t failed_becoming; +static atomic_t failed_load_modules; + +static const char *mod_fail_to_str(struct mod_fail_load *mod_fail) +{ + if (test_bit(FAIL_DUP_MOD_BECOMING, &mod_fail->dup_fail_mask) && + test_bit(FAIL_DUP_MOD_LOAD, &mod_fail->dup_fail_mask)) + return "Becoming & Load"; + if (test_bit(FAIL_DUP_MOD_BECOMING, &mod_fail->dup_fail_mask)) + return "Becoming"; + if (test_bit(FAIL_DUP_MOD_LOAD, &mod_fail->dup_fail_mask)) + return "Load"; + return "Bug-on-stats"; +} + +void mod_stat_bump_invalid(struct load_info *info, int flags) +{ + atomic_long_add(info->len * 2, &invalid_mod_bytes); + atomic_inc(&failed_load_modules); +#if defined(CONFIG_MODULE_DECOMPRESS) + if (flags & MODULE_INIT_COMPRESSED_FILE) + atomic_long_add(info->compressed_len, &invalid_mod_byte); +#endif +} + +void mod_stat_bump_becoming(struct load_info *info, int flags) +{ + atomic_inc(&failed_becoming); + atomic_long_add(info->len, &invalid_becoming_bytes); +#if defined(CONFIG_MODULE_DECOMPRESS) + if (flags & MODULE_INIT_COMPRESSED_FILE) + atomic_long_add(info->compressed_len, &invalid_becoming_bytes); +#endif +} + +int try_add_failed_module(const char *name, enum fail_dup_mod_reason reason) +{ + struct mod_fail_load *mod_fail; + + list_for_each_entry_rcu(mod_fail, &dup_failed_modules, list, + lockdep_is_held(&module_mutex)) { + if (!strcmp(mod_fail->name, name)) { + atomic_long_inc(&mod_fail->count); + __set_bit(reason, &mod_fail->dup_fail_mask); + goto out; + } + } + + mod_fail = kzalloc(sizeof(*mod_fail), GFP_KERNEL); + if (!mod_fail) + return -ENOMEM; + memcpy(mod_fail->name, name, strlen(name)); + __set_bit(reason, &mod_fail->dup_fail_mask); + atomic_long_inc(&mod_fail->count); + list_add_rcu(&mod_fail->list, &dup_failed_modules); +out: + return 0; +} + +/* + * At 64 bytes per module and assuming a 1024 bytes preamble we can fit the + * 112 module prints within 8k. + * + * 1024 + (64*112) = 8k + */ +#define MAX_PREAMBLE 1024 +#define MAX_FAILED_MOD_PRINT 112 +#define MAX_BYTES_PER_MOD 64 +static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct mod_fail_load *mod_fail; + unsigned int len, size, count_failed = 0; + char *buf; + u32 live_mod_count, fkreads, fdecompress, fbecoming, floads; + u64 total_size, text_size, ikread_bytes, ibecoming_bytes, idecompress_bytes, imod_bytes, + total_virtual_lost; + + live_mod_count = atomic_read(&modcount); + fkreads = atomic_read(&failed_kreads); + fdecompress = atomic_read(&failed_decompress); + fbecoming = atomic_read(&failed_becoming); + floads = atomic_read(&failed_load_modules); + + total_size = atomic64_read(&total_mod_size); + text_size = atomic64_read(&total_text_size); + ikread_bytes = atomic64_read(&invalid_kread_bytes); + idecompress_bytes = atomic64_read(&invalid_decompress_bytes); + ibecoming_bytes = atomic64_read(&invalid_becoming_bytes); + imod_bytes = atomic64_read(&invalid_mod_bytes); + + total_virtual_lost = ikread_bytes + idecompress_bytes + ibecoming_bytes + imod_bytes; + + size = MAX_PREAMBLE + min((unsigned int)(floads + fbecoming), + (unsigned int)MAX_FAILED_MOD_PRINT) * MAX_BYTES_PER_MOD; + buf = kzalloc(size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + /* The beginning of our debug preamble */ + len = scnprintf(buf + 0, size - len, "%25s\t%u\n", "Mods ever loaded", live_mod_count); + + len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on kread", fkreads); + + len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on decompress", + fdecompress); + len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on becoming", fbecoming); + + len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on load", floads); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Total module size", total_size); + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Total mod text size", text_size); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed kread bytes", ikread_bytes); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed decompress bytes", + idecompress_bytes); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed becoming bytes", ibecoming_bytes); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed kmod bytes", imod_bytes); + + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Virtual mem wasted bytes", total_virtual_lost); + + if (live_mod_count && total_size) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average mod size", + DIV_ROUND_UP(total_size, live_mod_count)); + } + + if (live_mod_count && text_size) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average mod text size", + DIV_ROUND_UP(text_size, live_mod_count)); + } + + /* + * We use WARN_ON_ONCE() for the counters to ensure we always have parity + * for keeping tabs on a type of failure with one type of byte counter. + * The counters for imod_bytes does not increase for fkreads failures + * for example, and so on. + */ + + WARN_ON_ONCE(ikread_bytes && !fkreads); + if (fkreads && ikread_bytes) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail kread bytes", + DIV_ROUND_UP(ikread_bytes, fkreads)); + } + + WARN_ON_ONCE(ibecoming_bytes && !fbecoming); + if (fbecoming && ibecoming_bytes) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail becoming bytes", + DIV_ROUND_UP(ibecoming_bytes, fbecoming)); + } + + WARN_ON_ONCE(idecompress_bytes && !fdecompress); + if (fdecompress && idecompress_bytes) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail decomp bytes", + DIV_ROUND_UP(idecompress_bytes, fdecompress)); + } + + WARN_ON_ONCE(imod_bytes && !floads); + if (floads && imod_bytes) { + len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average fail load bytes", + DIV_ROUND_UP(imod_bytes, floads)); + } + + /* End of our debug preamble header. */ + + /* Catch when we've gone beyond our expected preamble */ + WARN_ON_ONCE(len >= MAX_PREAMBLE); + + if (list_empty(&dup_failed_modules)) + goto out; + + len += scnprintf(buf + len, size - len, "Duplicate failed modules:\n"); + len += scnprintf(buf + len, size - len, "%25s\t%15s\t%25s\n", + "Module-name", "How-many-times", "Reason"); + mutex_lock(&module_mutex); + + + list_for_each_entry_rcu(mod_fail, &dup_failed_modules, list) { + if (WARN_ON_ONCE(++count_failed >= MAX_FAILED_MOD_PRINT)) + goto out_unlock; + len += scnprintf(buf + len, size - len, "%25s\t%15llu\t%25s\n", mod_fail->name, + atomic64_read(&mod_fail->count), mod_fail_to_str(mod_fail)); + } +out_unlock: + mutex_unlock(&module_mutex); +out: + kfree(buf); + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} +#undef MAX_PREAMBLE +#undef MAX_FAILED_MOD_PRINT +#undef MAX_BYTES_PER_MOD + +static const struct file_operations fops_mod_stats = { + .read = read_file_mod_stats, + .open = simple_open, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + +#define mod_debug_add_ulong(name) debugfs_create_ulong(#name, 0400, mod_debugfs_root, (unsigned long *) &name.counter) +#define mod_debug_add_atomic(name) debugfs_create_atomic_t(#name, 0400, mod_debugfs_root, &name) +static int __init module_stats_init(void) +{ + mod_debug_add_ulong(total_mod_size); + mod_debug_add_ulong(total_text_size); + mod_debug_add_ulong(invalid_kread_bytes); + mod_debug_add_ulong(invalid_decompress_bytes); + mod_debug_add_ulong(invalid_becoming_bytes); + mod_debug_add_ulong(invalid_mod_bytes); + + mod_debug_add_atomic(modcount); + mod_debug_add_atomic(failed_kreads); + mod_debug_add_atomic(failed_decompress); + mod_debug_add_atomic(failed_becoming); + mod_debug_add_atomic(failed_load_modules); + + debugfs_create_file("stats", 0400, mod_debugfs_root, mod_debugfs_root, &fops_mod_stats); + + return 0; +} +#undef mod_debug_add_ulong +#undef mod_debug_add_atomic +module_init(module_stats_init); diff --git a/kernel/module/tracking.c b/kernel/module/tracking.c index 26d812e07615..16742d1c630c 100644 --- a/kernel/module/tracking.c +++ b/kernel/module/tracking.c @@ -15,6 +15,7 @@ #include "internal.h" static LIST_HEAD(unloaded_tainted_modules); +extern struct dentry *mod_debugfs_root; int try_add_tainted_module(struct module *mod) { @@ -120,12 +121,8 @@ static const struct file_operations unloaded_tainted_modules_fops = { static int __init unloaded_tainted_modules_init(void) { - struct dentry *dir; - - dir = debugfs_create_dir("modules", NULL); - debugfs_create_file("unloaded_tainted", 0444, dir, NULL, + debugfs_create_file("unloaded_tainted", 0444, mod_debugfs_root, NULL, &unloaded_tainted_modules_fops); - return 0; } module_init(unloaded_tainted_modules_init); -- GitLab From 064f4536d13939b6e8cdb71298ff5d657f4f8caa Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 10 Mar 2023 20:48:03 -0800 Subject: [PATCH 3184/5631] module: avoid allocation if module is already present and ready The finit_module() system call can create unnecessary virtual memory pressure for duplicate modules. This is because load_module() can in the worse case allocate more than twice the size of a module in virtual memory. This saves at least a full size of the module in wasted vmalloc space memory by trying to avoid duplicates as soon as we can validate the module name in the read module structure. This can only be an issue if a system is getting hammered with userspace loading modules. There are two ways to load modules typically on systems, one is the kernel moduile auto-loading (*request_module*() calls in-kernel) and the other is things like udev. The auto-loading is in-kernel, but that pings back to userspace to just call modprobe. We already have a way to restrict the amount of concurrent kernel auto-loads in a given time, however that still allows multiple requests for the same module to go through and force two threads in userspace racing to call modprobe for the same exact module. Even though libkmod which both modprobe and udev does check if a module is already loaded prior calling finit_module() races are still possible and this is clearly evident today when you have multiple CPUs. To avoid memory pressure for such stupid cases put a stop gap for them. The *earliest* we can detect duplicates from the modules side of things is once we have blessed the module name, sadly after the first vmalloc allocation. We can check for the module being present *before* a secondary vmalloc() allocation. There is a linear relationship between wasted virtual memory bytes and the number of CPU counts. The reason is that udev ends up racing to call tons of the same modules for each of the CPUs. We can see the different linear relationships between wasted virtual memory and CPU count during after boot in the following graph: +----------------------------------------------------------------------------+ 14GB |-+ + + + + *+ +-| | **** | | *** | | ** | 12GB |-+ ** +-| | ** | | ** | | ** | | ** | 10GB |-+ ** +-| | ** | | ** | | ** | 8GB |-+ ** +-| waste | ** ### | | ** #### | | ** ####### | 6GB |-+ **** #### +-| | * #### | | * #### | | ***** #### | 4GB |-+ ** #### +-| | ** #### | | ** #### | | ** #### | 2GB |-+ ** ##### +-| | * #### | | * #### Before ******* | | **## + + + + After ####### | +----------------------------------------------------------------------------+ 0 50 100 150 200 250 300 CPUs count On the y-axis we can see gigabytes of wasted virtual memory during boot due to duplicate module requests which just end up failing. Trying to infer the slope this ends up being about ~463 MiB per CPU lost prior to this patch. After this patch we only loose about ~230 MiB per CPU, for a total savings of about ~233 MiB per CPU. This is all *just on bootup*! On a 8vcpu 8 GiB RAM system using kdevops and testing against selftests kmod.sh -t 0008 I see a saving in the *highest* side of memory consumption of up to ~ 84 MiB with the Linux kernel selftests kmod test 0008. With the new stress-ng module test I see a 145 MiB difference in max memory consumption with 100 ops. The stress-ng module ops tests can be pretty pathalogical -- it is not realistic, however it was used to finally successfully reproduce issues which are only reported to happen on system with over 400 CPUs [0] by just usign 100 ops on a 8vcpu 8 GiB RAM system. Running out of virtual memory space is no surprise given the above graph, since at least on x86_64 we're capped at 128 MiB, eventually we'd hit a series of errors and once can use the above graph to guestimate when. This of course will vary depending on the features you have enabled. So for instance, enabling KASAN seems to make this much worse. The results with kmod and stress-ng can be observed and visualized below. The time it takes to run the test is also not affected. The kmod tests 0008: The gnuplot is set to a range from 400000 KiB (390 Mib) - 580000 (566 Mib) given the tests peak around that range. cat kmod.plot set term dumb set output fileout set yrange [400000:580000] plot filein with linespoints title "Memory usage (KiB)" Before: root@kmod ~ # /data/linux-next/tools/testing/selftests/kmod/kmod.sh -t 0008 root@kmod ~ # free -k -s 1 -c 40 | grep Mem | awk '{print $3}' > log-0008-before.txt ^C root@kmod ~ # sort -n -r log-0008-before.txt | head -1 528732 So ~516.33 MiB After: root@kmod ~ # /data/linux-next/tools/testing/selftests/kmod/kmod.sh -t 0008 root@kmod ~ # free -k -s 1 -c 40 | grep Mem | awk '{print $3}' > log-0008-after.txt ^C root@kmod ~ # sort -n -r log-0008-after.txt | head -1 442516 So ~432.14 MiB That's about 84 ~MiB in savings in the worst case. The graphs: root@kmod ~ # gnuplot -e "filein='log-0008-before.txt'; fileout='graph-0008-before.txt'" kmod.plot root@kmod ~ # gnuplot -e "filein='log-0008-after.txt'; fileout='graph-0008-after.txt'" kmod.plot root@kmod ~ # cat graph-0008-before.txt 580000 +-----------------------------------------------------------------+ | + + + + + + + | 560000 |-+ Memory usage (KiB) ***A***-| | | 540000 |-+ +-| | | | *A *AA*AA*A*AA *A*AA A*A*A *AA*A*AA*A A | 520000 |-+A*A*AA *AA*A *A*AA*A*AA *A*A A *A+-| |*A | 500000 |-+ +-| | | 480000 |-+ +-| | | 460000 |-+ +-| | | | | 440000 |-+ +-| | | 420000 |-+ +-| | + + + + + + + | 400000 +-----------------------------------------------------------------+ 0 5 10 15 20 25 30 35 40 root@kmod ~ # cat graph-0008-after.txt 580000 +-----------------------------------------------------------------+ | + + + + + + + | 560000 |-+ Memory usage (KiB) ***A***-| | | 540000 |-+ +-| | | | | 520000 |-+ +-| | | 500000 |-+ +-| | | 480000 |-+ +-| | | 460000 |-+ +-| | | | *A *A*A | 440000 |-+A*A*AA*A A A*A*AA A*A*AA*A*AA*A*AA*A*AA*AA*A*AA*A*AA-| |*A *A*AA*A | 420000 |-+ +-| | + + + + + + + | 400000 +-----------------------------------------------------------------+ 0 5 10 15 20 25 30 35 40 The stress-ng module tests: This is used to run the test to try to reproduce the vmap issues reported by David: echo 0 > /proc/sys/vm/oom_dump_tasks ./stress-ng --module 100 --module-name xfs Prior to this commit: root@kmod ~ # free -k -s 1 -c 40 | grep Mem | awk '{print $3}' > baseline-stress-ng.txt root@kmod ~ # sort -n -r baseline-stress-ng.txt | head -1 5046456 After this commit: root@kmod ~ # free -k -s 1 -c 40 | grep Mem | awk '{print $3}' > after-stress-ng.txt root@kmod ~ # sort -n -r after-stress-ng.txt | head -1 4896972 5046456 - 4896972 149484 149484/1024 145.98046875000000000000 So this commit using stress-ng reveals saving about 145 MiB in memory using 100 ops from stress-ng which reproduced the vmap issue reported. cat kmod.plot set term dumb set output fileout set yrange [4700000:5070000] plot filein with linespoints title "Memory usage (KiB)" root@kmod ~ # gnuplot -e "filein='baseline-stress-ng.txt'; fileout='graph-stress-ng-before.txt'" kmod-simple-stress-ng.plot root@kmod ~ # gnuplot -e "filein='after-stress-ng.txt'; fileout='graph-stress-ng-after.txt'" kmod-simple-stress-ng.plot root@kmod ~ # cat graph-stress-ng-before.txt +---------------------------------------------------------------+ 5.05e+06 |-+ + A + + + + + + +-| | * Memory usage (KiB) ***A*** | | * A | 5e+06 |-+ ** ** +-| | ** * * A | 4.95e+06 |-+ * * A * A* +-| | * * A A * * * * A | | * * * * * * *A * * * A * | 4.9e+06 |-+ * * * A*A * A*AA*A A *A **A **A*A *+-| | A A*A A * A * * A A * A * ** | | * ** ** * * * * * * * | 4.85e+06 |-+ A A A ** * * ** *-| | * * * * ** * | | * A * * * * | 4.8e+06 |-+ * * * A A-| | * * * | 4.75e+06 |-+ * * * +-| | * ** | | * + + + + + + ** + | 4.7e+06 +---------------------------------------------------------------+ 0 5 10 15 20 25 30 35 40 root@kmod ~ # cat graph-stress-ng-after.txt +---------------------------------------------------------------+ 5.05e+06 |-+ + + + + + + + +-| | Memory usage (KiB) ***A*** | | | 5e+06 |-+ +-| | | 4.95e+06 |-+ +-| | | | | 4.9e+06 |-+ *AA +-| | A*AA*A*A A A*AA*AA*A*AA*A A A A*A *AA*A*A A A*AA*AA | | * * ** * * * ** * *** * | 4.85e+06 |-+* *** * * * * *** A * * +-| | * A * * ** * * A * * | | * * * * ** * * | 4.8e+06 |-+* * * A * * * +-| | * * * A * * | 4.75e+06 |-* * * * * +-| | * * * * * | | * + * *+ + + + + * *+ | 4.7e+06 +---------------------------------------------------------------+ 0 5 10 15 20 25 30 35 40 [0] https://lkml.kernel.org/r/20221013180518.217405-1-david@redhat.com Reported-by: David Hildenbrand Signed-off-by: Luis Chamberlain --- kernel/module/main.c | 6 +++++- kernel/module/stats.c | 11 +++++------ 2 files changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/module/main.c b/kernel/module/main.c index 01fffa8afef2..044aa2c9e3cb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2813,7 +2813,11 @@ static int early_mod_check(struct load_info *info, int flags) if (err) return err; - return 0; + mutex_lock(&module_mutex); + err = module_patient_check_exists(info->mod->name, FAIL_DUP_MOD_BECOMING); + mutex_unlock(&module_mutex); + + return err; } /* diff --git a/kernel/module/stats.c b/kernel/module/stats.c index 3d45744b3920..1d31f96a5e28 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -85,7 +85,7 @@ * calls: * * a) FAIL_DUP_MOD_BECOMING: at the end of early_mod_check() before - * layout_and_allocate(). This does not yet happen. + * layout_and_allocate(). * - with module decompression: 2 virtual memory allocation calls * - without module decompression: 1 virtual memory allocation calls * b) FAIL_DUP_MOD_LOAD: after layout_and_allocate() on add_unformed_module() @@ -126,17 +126,16 @@ static LIST_HEAD(dup_failed_modules); * pressure. * * invalid_becoming_bytes: total number of bytes allocated and freed used * used to read the kernel module userspace wants us to read before we - * promote it to be processed to be added to our @modules linked list. - * These failures could in theory happen if we had a check in - * between a successful kernel_read_file_from_fd() + * promote it to be processed to be added to our @modules linked list. These + * failures can happen if we had a check in between a successful kernel_read_file_from_fd() * call and right before we allocate the our private memory for the module * which would be kept if the module is successfully loaded. The most common * reason for this failure is when userspace is racing to load a module * which it does not yet see loaded. The first module to succeed in * add_unformed_module() will add a module to our &modules list and * subsequent loads of modules with the same name will error out at the - * end of early_mod_check(). A check for module_patient_check_exists() - * at the end of early_mod_check() could be added to prevent duplicate allocations + * end of early_mod_check(). The check for module_patient_check_exists() + * at the end of early_mod_check() prevents duplicate allocations * on layout_and_allocate() for modules already being processed. These * duplicate failed modules are non-fatal, however they typically are * indicative of userspace not seeing a module in userspace loaded yet and -- GitLab From 635dc38314c75c5727711d896d4c71ec92f6f20b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 00:02:46 +0200 Subject: [PATCH 3185/5631] module: stats: include uapi/linux/module.h MODULE_INIT_COMPRESSED_FILE is defined in the uapi header, which is not included indirectly from the normal linux/module.h, but has to be pulled in explicitly: kernel/module/stats.c: In function 'mod_stat_bump_invalid': kernel/module/stats.c:227:14: error: 'MODULE_INIT_COMPRESSED_FILE' undeclared (first use in this function) 227 | if (flags & MODULE_INIT_COMPRESSED_FILE) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Arnd Bergmann Signed-off-by: Luis Chamberlain --- kernel/module/stats.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/module/stats.c b/kernel/module/stats.c index 1d31f96a5e28..c1cccd2c3595 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include -- GitLab From 719ccd803ed5bd1ad92b0b46fc095b8fe266827e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 00:48:04 +0200 Subject: [PATCH 3186/5631] module: fix building stats for 32-bit targets The new module statistics code mixes 64-bit types and wordsized 'long' variables, which leads to build failures on 32-bit architectures: kernel/module/stats.c: In function 'read_file_mod_stats': kernel/module/stats.c:291:29: error: passing argument 1 of 'atomic64_read' from incompatible pointer type [-Werror=incompatible-pointer-types] 291 | total_size = atomic64_read(&total_mod_size); x86_64-linux-ld: kernel/module/stats.o: in function `read_file_mod_stats': stats.c:(.text+0x2b2): undefined reference to `__udivdi3' To fix this, the code has to use one of the two types consistently. Change them all to word-size types here. Fixes: df3e764d8e5c ("module: add debug stats to help identify memory pressure") Signed-off-by: Arnd Bergmann Signed-off-by: Luis Chamberlain --- kernel/module/stats.c | 46 +++++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/kernel/module/stats.c b/kernel/module/stats.c index c1cccd2c3595..a1f545479174 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -277,8 +277,8 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, unsigned int len, size, count_failed = 0; char *buf; u32 live_mod_count, fkreads, fdecompress, fbecoming, floads; - u64 total_size, text_size, ikread_bytes, ibecoming_bytes, idecompress_bytes, imod_bytes, - total_virtual_lost; + unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes, + idecompress_bytes, imod_bytes, total_virtual_lost; live_mod_count = atomic_read(&modcount); fkreads = atomic_read(&failed_kreads); @@ -286,12 +286,12 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, fbecoming = atomic_read(&failed_becoming); floads = atomic_read(&failed_load_modules); - total_size = atomic64_read(&total_mod_size); - text_size = atomic64_read(&total_text_size); - ikread_bytes = atomic64_read(&invalid_kread_bytes); - idecompress_bytes = atomic64_read(&invalid_decompress_bytes); - ibecoming_bytes = atomic64_read(&invalid_becoming_bytes); - imod_bytes = atomic64_read(&invalid_mod_bytes); + total_size = atomic_long_read(&total_mod_size); + text_size = atomic_long_read(&total_text_size); + ikread_bytes = atomic_long_read(&invalid_kread_bytes); + idecompress_bytes = atomic_long_read(&invalid_decompress_bytes); + ibecoming_bytes = atomic_long_read(&invalid_becoming_bytes); + imod_bytes = atomic_long_read(&invalid_mod_bytes); total_virtual_lost = ikread_bytes + idecompress_bytes + ibecoming_bytes + imod_bytes; @@ -312,27 +312,27 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on load", floads); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Total module size", total_size); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Total mod text size", text_size); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Total module size", total_size); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Total mod text size", text_size); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed kread bytes", ikread_bytes); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed kread bytes", ikread_bytes); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed decompress bytes", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed decompress bytes", idecompress_bytes); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed becoming bytes", ibecoming_bytes); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed becoming bytes", ibecoming_bytes); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Failed kmod bytes", imod_bytes); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed kmod bytes", imod_bytes); - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Virtual mem wasted bytes", total_virtual_lost); + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Virtual mem wasted bytes", total_virtual_lost); if (live_mod_count && total_size) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average mod size", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average mod size", DIV_ROUND_UP(total_size, live_mod_count)); } if (live_mod_count && text_size) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average mod text size", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average mod text size", DIV_ROUND_UP(text_size, live_mod_count)); } @@ -345,25 +345,25 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, WARN_ON_ONCE(ikread_bytes && !fkreads); if (fkreads && ikread_bytes) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail kread bytes", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail kread bytes", DIV_ROUND_UP(ikread_bytes, fkreads)); } WARN_ON_ONCE(ibecoming_bytes && !fbecoming); if (fbecoming && ibecoming_bytes) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail becoming bytes", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail becoming bytes", DIV_ROUND_UP(ibecoming_bytes, fbecoming)); } WARN_ON_ONCE(idecompress_bytes && !fdecompress); if (fdecompress && idecompress_bytes) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Avg fail decomp bytes", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail decomp bytes", DIV_ROUND_UP(idecompress_bytes, fdecompress)); } WARN_ON_ONCE(imod_bytes && !floads); if (floads && imod_bytes) { - len += scnprintf(buf + len, size - len, "%25s\t%llu\n", "Average fail load bytes", + len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average fail load bytes", DIV_ROUND_UP(imod_bytes, floads)); } @@ -384,8 +384,8 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, list_for_each_entry_rcu(mod_fail, &dup_failed_modules, list) { if (WARN_ON_ONCE(++count_failed >= MAX_FAILED_MOD_PRINT)) goto out_unlock; - len += scnprintf(buf + len, size - len, "%25s\t%15llu\t%25s\n", mod_fail->name, - atomic64_read(&mod_fail->count), mod_fail_to_str(mod_fail)); + len += scnprintf(buf + len, size - len, "%25s\t%15lu\t%25s\n", mod_fail->name, + atomic_long_read(&mod_fail->count), mod_fail_to_str(mod_fail)); } out_unlock: mutex_unlock(&module_mutex); -- GitLab From 9f5cab173e19201eebeaca853ff664a9a269fed0 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 17 Apr 2023 19:09:57 -0400 Subject: [PATCH 3187/5631] module: remove use of uninitialized variable len clang build reports kernel/module/stats.c:307:34: error: variable 'len' is uninitialized when used here [-Werror,-Wuninitialized] len = scnprintf(buf + 0, size - len, ^~~ At the start of this sequence, neither the '+ 0', nor the '- len' are needed. So remove them and fix using 'len' uninitalized. Fixes: df3e764d8e5c ("module: add debug stats to help identify memory pressure") Signed-off-by: Tom Rix Signed-off-by: Luis Chamberlain --- kernel/module/stats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/module/stats.c b/kernel/module/stats.c index a1f545479174..6eeb35cc8d9f 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -302,7 +302,7 @@ static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf, return -ENOMEM; /* The beginning of our debug preamble */ - len = scnprintf(buf + 0, size - len, "%25s\t%u\n", "Mods ever loaded", live_mod_count); + len = scnprintf(buf, size, "%25s\t%u\n", "Mods ever loaded", live_mod_count); len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on kread", fkreads); -- GitLab From a81b1fc8ea639e03326c1d0dcde041986bc11500 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 09:17:51 +0200 Subject: [PATCH 3188/5631] module: stats: fix invalid_mod_bytes typo This was caught by randconfig builds but does not show up in build testing without CONFIG_MODULE_DECOMPRESS: kernel/module/stats.c: In function 'mod_stat_bump_invalid': kernel/module/stats.c:229:42: error: 'invalid_mod_byte' undeclared (first use in this function); did you mean 'invalid_mod_bytes'? 229 | atomic_long_add(info->compressed_len, &invalid_mod_byte); | ^~~~~~~~~~~~~~~~ | invalid_mod_bytes Fixes: df3e764d8e5c ("module: add debug stats to help identify memory pressure") Signed-off-by: Arnd Bergmann Acked-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Luis Chamberlain --- kernel/module/stats.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/module/stats.c b/kernel/module/stats.c index 6eeb35cc8d9f..ad7b6ada29f2 100644 --- a/kernel/module/stats.c +++ b/kernel/module/stats.c @@ -223,7 +223,7 @@ void mod_stat_bump_invalid(struct load_info *info, int flags) atomic_inc(&failed_load_modules); #if defined(CONFIG_MODULE_DECOMPRESS) if (flags & MODULE_INIT_COMPRESSED_FILE) - atomic_long_add(info->compressed_len, &invalid_mod_byte); + atomic_long_add(info->compressed_len, &invalid_mod_bytes); #endif } -- GitLab From 4de867fc237487ce2951a8231d7390237d3f3be8 Mon Sep 17 00:00:00 2001 From: Jane Jian Date: Thu, 13 Apr 2023 10:49:06 +0800 Subject: [PATCH 3189/5631] drm/amdgpu/vcn: fix mmsch ctx table size add jpeg table size to ctx table size rather than override it Signed-off-by: Jane Jian Reviewed-by: JingWen Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c index a6ad678fd507..77e1e64aa1d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c @@ -430,7 +430,7 @@ static int jpeg_v4_0_start_sriov(struct amdgpu_device *adev) MMSCH_COMMAND__END; header.version = MMSCH_VERSION; - header.total_size = sizeof(struct mmsch_v4_0_init_header) >> 2; + header.total_size = RREG32_SOC15(VCN, 0, regMMSCH_VF_CTX_SIZE); header.jpegdec.init_status = 0; header.jpegdec.table_offset = 0; -- GitLab From 8d9cdb4674f6e4e7fc789f8184a58c73eeadc16c Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 14 Apr 2023 08:03:44 -0400 Subject: [PATCH 3190/5631] drm/amd/pm: change pmfw_decoded_link_width, speed variables to globals MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 reports In file included from drivers/gpu/drm/amd/amdgpu/../pm/swsmu/smu13/smu_v13_0.c:36: ./drivers/gpu/drm/amd/amdgpu/../pm/swsmu/inc/smu_v13_0.h:66:18: error: ‘pmfw_decoded_link_width’ defined but not used [-Werror=unused-const-variable=] 66 | static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; | ^~~~~~~~~~~~~~~~~~~~~~~ ./drivers/gpu/drm/amd/amdgpu/../pm/swsmu/inc/smu_v13_0.h:65:18: error: ‘pmfw_decoded_link_speed’ defined but not used [-Werror=unused-const-variable=] 65 | static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; | ^~~~~~~~~~~~~~~~~~~~~~~ These variables are defined and used in smu_v13_0_7_ppt.c and smu_v13_0_0_ppt.c. There should be only one definition. So define the variables as globals in smu_v13_0.c Signed-off-by: Tom Rix Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h | 4 ++-- drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 7944ce80e5c3..df3baaab0037 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -62,8 +62,8 @@ #define CTF_OFFSET_HOTSPOT 5 #define CTF_OFFSET_MEM 5 -static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; -static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; +extern const int pmfw_decoded_link_speed[5]; +extern const int pmfw_decoded_link_width[7]; #define DECODE_GEN_SPEED(gen_speed_idx) (pmfw_decoded_link_speed[gen_speed_idx]) #define DECODE_LANE_WIDTH(lane_width_idx) (pmfw_decoded_link_width[lane_width_idx]) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 73175c993da9..393c6a7b9609 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -85,6 +85,9 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin"); static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; static const int link_speed[] = {25, 50, 80, 160}; +const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5}; +const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16}; + int smu_v13_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; -- GitLab From 38eecbe086a4e52f54b2bbda8feba65d44addbef Mon Sep 17 00:00:00 2001 From: Chong Li Date: Fri, 14 Apr 2023 13:51:19 +0800 Subject: [PATCH 3191/5631] drm/amdgpu: release gpu full access after "amdgpu_device_ip_late_init" [WHY] Function "amdgpu_irq_update()" called by "amdgpu_device_ip_late_init()" is an atomic context. We shouldn't access registers through KIQ since "msleep()" may be called in "amdgpu_kiq_rreg()". [HOW] Move function "amdgpu_virt_release_full_gpu()" after function "amdgpu_device_ip_late_init()", to ensure that registers be accessed through RLCG instead of KIQ. Call Trace: show_stack+0x52/0x69 dump_stack_lvl+0x49/0x6d dump_stack+0x10/0x18 __schedule_bug.cold+0x4f/0x6b __schedule+0x473/0x5d0 ? __wake_up_klogd.part.0+0x40/0x70 ? vprintk_emit+0xbe/0x1f0 schedule+0x68/0x110 schedule_timeout+0x87/0x160 ? timer_migration_handler+0xa0/0xa0 msleep+0x2d/0x50 amdgpu_kiq_rreg+0x18d/0x1f0 [amdgpu] amdgpu_device_rreg.part.0+0x59/0xd0 [amdgpu] amdgpu_device_rreg+0x3a/0x50 [amdgpu] amdgpu_sriov_rreg+0x3c/0xb0 [amdgpu] gfx_v10_0_set_gfx_eop_interrupt_state.constprop.0+0x16c/0x190 [amdgpu] gfx_v10_0_set_eop_interrupt_state+0xa5/0xb0 [amdgpu] amdgpu_irq_update+0x53/0x80 [amdgpu] amdgpu_irq_get+0x7c/0xb0 [amdgpu] amdgpu_fence_driver_hw_init+0x58/0x90 [amdgpu] amdgpu_device_init.cold+0x16b7/0x2022 [amdgpu] Signed-off-by: Chong Li Reviewed-by: JingWen.Chen2@amd.com Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 32 ++++++++++++---------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a2292acf06d0..9b1eaba85bbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2539,8 +2539,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev) amdgpu_fru_get_product_info(adev); init_failed: - if (amdgpu_sriov_vf(adev)) - amdgpu_virt_release_full_gpu(adev, true); return r; } @@ -3859,18 +3857,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_device_ip_init(adev); if (r) { - /* failed in exclusive mode due to timeout */ - if (amdgpu_sriov_vf(adev) && - !amdgpu_sriov_runtime(adev) && - amdgpu_virt_mmio_blocked(adev) && - !amdgpu_virt_wait_reset(adev)) { - dev_err(adev->dev, "VF exclusive mode timeout\n"); - /* Don't send request since VF is inactive. */ - adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME; - adev->virt.ops = NULL; - r = -EAGAIN; - goto release_ras_con; - } dev_err(adev->dev, "amdgpu_device_ip_init failed\n"); amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0); goto release_ras_con; @@ -3939,8 +3925,10 @@ int amdgpu_device_init(struct amdgpu_device *adev, msecs_to_jiffies(AMDGPU_RESUME_MS)); } - if (amdgpu_sriov_vf(adev)) + if (amdgpu_sriov_vf(adev)) { + amdgpu_virt_release_full_gpu(adev, true); flush_delayed_work(&adev->delayed_init_work); + } r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes); if (r) @@ -3980,6 +3968,20 @@ int amdgpu_device_init(struct amdgpu_device *adev, return 0; release_ras_con: + if (amdgpu_sriov_vf(adev)) + amdgpu_virt_release_full_gpu(adev, true); + + /* failed in exclusive mode due to timeout */ + if (amdgpu_sriov_vf(adev) && + !amdgpu_sriov_runtime(adev) && + amdgpu_virt_mmio_blocked(adev) && + !amdgpu_virt_wait_reset(adev)) { + dev_err(adev->dev, "VF exclusive mode timeout\n"); + /* Don't send request since VF is inactive. */ + adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME; + adev->virt.ops = NULL; + r = -EAGAIN; + } amdgpu_release_ras_context(adev); failed: -- GitLab From 764ba43d34ac5fd16e0e377643f89a7208f1f67b Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 14:06:16 -0600 Subject: [PATCH 3192/5631] drm/amd/display: Update bouding box values for DCN32 All clock values came from firmware, but bounding box values can be helpful in some debug situations. This commit updates some of the values associated with clock speed and memory channels. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 4548320217fc..f0037cb43dca 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -109,7 +109,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { { .state = 0, .dcfclk_mhz = 1564.0, - .fabricclk_mhz = 400.0, + .fabricclk_mhz = 2500.0, .dispclk_mhz = 2150.0, .dppclk_mhz = 2150.0, .phyclk_mhz = 810.0, @@ -117,7 +117,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { .phyclk_d32_mhz = 625.0, .socclk_mhz = 1200.0, .dscclk_mhz = 716.667, - .dram_speed_mts = 16000.0, + .dram_speed_mts = 18000.0, .dtbclk_mhz = 1564.0, }, }, @@ -148,7 +148,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = { .max_avg_fabric_bw_use_normal_percent = 60.0, .max_avg_dram_bw_use_normal_strobe_percent = 50.0, .max_avg_dram_bw_use_normal_percent = 15.0, - .num_chans = 8, + .num_chans = 24, .dram_channel_width_bytes = 2, .fabric_datapath_to_dcn_data_return_bytes = 64, .return_bus_width_bytes = 64, -- GitLab From ef3d74aa7e5d0ba4e9fc00f1409652e29f46fc59 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 14:10:27 -0600 Subject: [PATCH 3193/5631] drm/amd/display: Add missing mclk update When using FPO, there is some misconfiguration that happens for the lack of configuration of the MCLK switch in some circumstances. This commit adds the required field update when using the MCLK switch. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index f0037cb43dca..23a972f2885f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1331,6 +1331,11 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context, context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; + /* Pstate change might not be supported by hardware, but it might be + * possible with firmware driven vertical blank stretching. + */ + context->bw_ctx.bw.dcn.clk.p_state_change_support |= context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching; + context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); context->bw_ctx.bw.dcn.clk.ref_dtbclk_khz = context->bw_ctx.dml.vba.DTBCLKPerState[vlevel] * 1000; -- GitLab From 83aeb49c8c467e9fe77c4f01c80472a4329db49c Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 15:29:36 -0600 Subject: [PATCH 3194/5631] drm/amd/display: Adjust code identation and other minor details This commit replaces spaces with tabs in multiple functions and adjusts the indentation in some other parts of the code to improve readability. Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn32/dcn32_resource.c | 44 ++--- .../drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 170 +++++++++--------- 2 files changed, 109 insertions(+), 105 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index e30d1f60695d..0beb11d95eb7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -324,7 +324,6 @@ static const struct dcn10_link_enc_shift le_shift = { static const struct dcn10_link_enc_mask le_mask = { LINK_ENCODER_MASK_SH_LIST_DCN31(_MASK), \ - //DPCS_DCN31_MASK_SH_LIST(_MASK) }; @@ -2093,27 +2092,28 @@ static bool dcn32_resource_construct( uint32_t pipe_fuses = 0; uint32_t num_pipes = 4; - #undef REG_STRUCT - #define REG_STRUCT bios_regs - bios_regs_init(); - - #undef REG_STRUCT - #define REG_STRUCT clk_src_regs - clk_src_regs_init(0, A), - clk_src_regs_init(1, B), - clk_src_regs_init(2, C), - clk_src_regs_init(3, D), - clk_src_regs_init(4, E); - #undef REG_STRUCT - #define REG_STRUCT abm_regs - abm_regs_init(0), - abm_regs_init(1), - abm_regs_init(2), - abm_regs_init(3); - - #undef REG_STRUCT - #define REG_STRUCT dccg_regs - dccg_regs_init(); +#undef REG_STRUCT +#define REG_STRUCT bios_regs + bios_regs_init(); + +#undef REG_STRUCT +#define REG_STRUCT clk_src_regs + clk_src_regs_init(0, A), + clk_src_regs_init(1, B), + clk_src_regs_init(2, C), + clk_src_regs_init(3, D), + clk_src_regs_init(4, E); + +#undef REG_STRUCT +#define REG_STRUCT abm_regs + abm_regs_init(0), + abm_regs_init(1), + abm_regs_init(2), + abm_regs_init(3); + +#undef REG_STRUCT +#define REG_STRUCT dccg_regs + dccg_regs_init(); DC_FP_START(); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 38d1f2be8cf3..6e32dc68f7bc 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -917,19 +917,19 @@ void dcn20_populate_dml_writeback_from_context(struct dc *dc, } void dcn20_fpu_set_wb_arb_params(struct mcif_arb_params *wb_arb_params, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int pipe_cnt, int i) + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, int i) { - int k; + int k; - dc_assert_fp_enabled(); + dc_assert_fp_enabled(); - for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) { - wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; - } - wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */ + for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) { + wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; + } + wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */ } static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) @@ -1037,11 +1037,11 @@ static void dcn20_adjust_freesync_v_startup( *vstartup_start = ((newVstartup > *vstartup_start) ? newVstartup : *vstartup_start); } -void dcn20_calculate_dlg_params( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int pipe_cnt, - int vlevel) +void dcn20_calculate_dlg_params(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel) { int i, pipe_idx; @@ -1083,6 +1083,7 @@ void dcn20_calculate_dlg_params( pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); + if (context->res_ctx.pipe_ctx[i].stream->mall_stream_config.type == SUBVP_PHANTOM) { // Phantom pipe requires that DET_SIZE = 0 and no unbounded requests context->res_ctx.pipe_ctx[i].det_buffer_size_kb = 0; @@ -1091,6 +1092,7 @@ void dcn20_calculate_dlg_params( context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes; context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode; } + if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = @@ -1118,6 +1120,7 @@ void dcn20_calculate_dlg_params( if (!context->res_ctx.pipe_ctx[i].stream) continue; + /* cstate disabled on 201 */ if (dc->ctx->dce_version == DCN_VERSION_2_01) cstate_en = false; @@ -1201,11 +1204,10 @@ static void swizzle_to_dml_params( } } -int dcn20_populate_dml_pipes_from_context( - struct dc *dc, - struct dc_state *context, - display_e2e_pipe_params_st *pipes, - bool fast_validate) +int dcn20_populate_dml_pipes_from_context(struct dc *dc, + struct dc_state *context, + display_e2e_pipe_params_st *pipes, + bool fast_validate) { int pipe_cnt, i; bool synchronized_vblank = true; @@ -1507,6 +1509,7 @@ int dcn20_populate_dml_pipes_from_context( default: break; } + pipes[pipe_cnt].pipe.src.viewport_y_y = scl->viewport.y; pipes[pipe_cnt].pipe.src.viewport_y_c = scl->viewport_c.y; pipes[pipe_cnt].pipe.src.viewport_x_y = scl->viewport.x; @@ -1615,13 +1618,12 @@ int dcn20_populate_dml_pipes_from_context( return pipe_cnt; } -void dcn20_calculate_wm( - struct dc *dc, struct dc_state *context, - display_e2e_pipe_params_st *pipes, - int *out_pipe_cnt, - int *pipe_split_from, - int vlevel, - bool fast_validate) +void dcn20_calculate_wm(struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int *out_pipe_cnt, + int *pipe_split_from, + int vlevel, + bool fast_validate) { int pipe_cnt, i, pipe_idx; @@ -1733,8 +1735,11 @@ void dcn20_calculate_wm( context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000; } -void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states) +void dcn20_update_bounding_box(struct dc *dc, + struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table *max_clocks, + unsigned int *uclk_states, + unsigned int num_states) { int num_calculated_states = 0; int min_dcfclk = 0; @@ -1796,9 +1801,8 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s bb->clock_limits[num_calculated_states].state = bb->num_states; } -void dcn20_cap_soc_clocks( - struct _vcs_dpi_soc_bounding_box_st *bb, - struct pp_smu_nv_clock_table max_clocks) +void dcn20_cap_soc_clocks(struct _vcs_dpi_soc_bounding_box_st *bb, + struct pp_smu_nv_clock_table max_clocks) { int i; @@ -1954,80 +1958,80 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co } bool dcn20_validate_bandwidth_fp(struct dc *dc, - struct dc_state *context, - bool fast_validate) + struct dc_state *context, + bool fast_validate) { - bool voltage_supported = false; - bool full_pstate_supported = false; - bool dummy_pstate_supported = false; - double p_state_latency_us; + bool voltage_supported = false; + bool full_pstate_supported = false; + bool dummy_pstate_supported = false; + double p_state_latency_us; - dc_assert_fp_enabled(); + dc_assert_fp_enabled(); - p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; - context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = - dc->debug.disable_dram_clock_change_vactive_support; - context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive = - dc->debug.enable_dram_clock_change_one_display_vactive; + p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; + context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = + dc->debug.disable_dram_clock_change_vactive_support; + context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive = + dc->debug.enable_dram_clock_change_one_display_vactive; - /*Unsafe due to current pipe merge and split logic*/ - ASSERT(context != dc->current_state); + /*Unsafe due to current pipe merge and split logic*/ + ASSERT(context != dc->current_state); - if (fast_validate) { - return dcn20_validate_bandwidth_internal(dc, context, true); - } + if (fast_validate) { + return dcn20_validate_bandwidth_internal(dc, context, true); + } - // Best case, we support full UCLK switch latency - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); - full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; + // Best case, we support full UCLK switch latency + voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); + full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; - if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 || - (voltage_supported && full_pstate_supported)) { - context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported; - goto restore_dml_state; - } + if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 || + (voltage_supported && full_pstate_supported)) { + context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported; + goto restore_dml_state; + } - // Fallback: Try to only support G6 temperature read latency - context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; + // Fallback: Try to only support G6 temperature read latency + context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us; - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); - dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; + voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false); + dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support; - if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) { - context->bw_ctx.bw.dcn.clk.p_state_change_support = false; - goto restore_dml_state; - } + if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) { + context->bw_ctx.bw.dcn.clk.p_state_change_support = false; + goto restore_dml_state; + } - // ERROR: fallback is supposed to always work. - ASSERT(false); + // ERROR: fallback is supposed to always work. + ASSERT(false); restore_dml_state: - context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; - return voltage_supported; + context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; } void dcn20_fpu_set_wm_ranges(int i, - struct pp_smu_wm_range_sets *ranges, - struct _vcs_dpi_soc_bounding_box_st *loaded_bb) + struct pp_smu_wm_range_sets *ranges, + struct _vcs_dpi_soc_bounding_box_st *loaded_bb) { - dc_assert_fp_enabled(); + dc_assert_fp_enabled(); - ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; - ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; + ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0; + ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16; } void dcn20_fpu_adjust_dppclk(struct vba_vars_st *v, - int vlevel, - int max_mpc_comb, - int pipe_idx, - bool is_validating_bw) + int vlevel, + int max_mpc_comb, + int pipe_idx, + bool is_validating_bw) { - dc_assert_fp_enabled(); + dc_assert_fp_enabled(); - if (is_validating_bw) - v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2; - else - v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2; + if (is_validating_bw) + v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2; + else + v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2; } int dcn21_populate_dml_pipes_from_context(struct dc *dc, -- GitLab From 0fdf06e449b6d6d970c0709c71a8738cfe551ecc Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 15:37:46 -0600 Subject: [PATCH 3195/5631] drm/amd/display: Set maximum VStartup if is DCN201 Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 6e32dc68f7bc..b79014f04cef 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -1259,6 +1259,8 @@ int dcn20_populate_dml_pipes_from_context(struct dc *dc, pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0; + pipes[pipe_cnt].pipe.dest.use_maximum_vstartup = dc->ctx->dce_version == DCN_VERSION_2_01; + pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC; /* todo: rotation?*/ pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h; -- GitLab From ac7485cc363f2c603a3e1a7a609ef065ad56b19b Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 15:38:09 -0600 Subject: [PATCH 3196/5631] drm/amd/display: Set dp_rate to dm_dp_rate_na by default Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index b79014f04cef..9fadac1b4c64 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -1300,8 +1300,7 @@ int dcn20_populate_dml_pipes_from_context(struct dc *dc, pipes[pipe_cnt].pipe.dest.pixel_rate_mhz *= 2; pipes[pipe_cnt].pipe.dest.otg_inst = res_ctx->pipe_ctx[i].stream_res.tg->inst; pipes[pipe_cnt].dout.dp_lanes = 4; - if (res_ctx->pipe_ctx[i].stream->link) - pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na; + pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na; pipes[pipe_cnt].dout.is_virtual = 0; pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min; pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max; -- GitLab From b62f91569f9aa54b0a60d46a022482415cb968a9 Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 15:40:21 -0600 Subject: [PATCH 3197/5631] drm/amd/display: Remove wrong assignment of DP link rate Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 9fadac1b4c64..03718cc148e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -1360,7 +1360,6 @@ int dcn20_populate_dml_pipes_from_context(struct dc *dc, pipes[pipe_cnt].dout.is_virtual = 1; pipes[pipe_cnt].dout.output_type = dm_dp; pipes[pipe_cnt].dout.dp_lanes = 4; - pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_hbr2; } switch (res_ctx->pipe_ctx[i].stream->timing.display_color_depth) { -- GitLab From 64626c0ee13257e330bc09fa6a169385c0eaf9ca Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Mon, 3 Apr 2023 19:23:29 -0600 Subject: [PATCH 3198/5631] drm/amd/display: Use pointer in the memcpy Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 03718cc148e0..f1c1a4b5fcac 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -2333,7 +2333,7 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params k++; } - memcpy(dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits)); + memcpy(&dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits)); if (clk_table->num_entries) { dcn2_1_soc.num_states = clk_table->num_entries + 1; -- GitLab From 0c1f033159712b3d071cfe4a3ec0f36f1914453b Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sat, 15 Apr 2023 11:17:22 -0400 Subject: [PATCH 3199/5631] drm/amd/display: set variable dccg314_init storage-class-specifier to static smatch reports drivers/gpu/drm/amd/amdgpu/../display/dc/dcn314/dcn314_dccg.c:277:6: warning: symbol 'dccg314_init' was not declared. Should it be static? This variable is only used in one file so should be static. Signed-off-by: Tom Rix Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 6f879265ad9c..de7bfba2c179 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -274,7 +274,7 @@ static void dccg314_set_dpstreamclk( } } -void dccg314_init(struct dccg *dccg) +static void dccg314_init(struct dccg *dccg) { int otg_inst; -- GitLab From ff77cf5b2e033d0bb5e3b7f83ebf65c5adc20d12 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:10:58 -0700 Subject: [PATCH 3200/5631] RISC-V: Move struct riscv_cpuinfo to new header In preparation for tracking and exposing microarchitectural details to userspace (like whether or not unaligned accesses are fast), move the riscv_cpuinfo struct out to its own new cpufeatures.h header. It will need to be used by more than just cpu.c. Signed-off-by: Evan Green Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Tested-by: Heiko Stuebner Reviewed-by: Paul Walmsley Link: https://lore.kernel.org/r/20230407231103.2622178-2-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/cpufeature.h | 21 +++++++++++++++++++++ arch/riscv/kernel/cpu.c | 8 ++------ 2 files changed, 23 insertions(+), 6 deletions(-) create mode 100644 arch/riscv/include/asm/cpufeature.h diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h new file mode 100644 index 000000000000..66ebaae449c8 --- /dev/null +++ b/arch/riscv/include/asm/cpufeature.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022-2023 Rivos, Inc + */ + +#ifndef _ASM_CPUFEATURE_H +#define _ASM_CPUFEATURE_H + +/* + * These are probed via a device_initcall(), via either the SBI or directly + * from the corresponding CSRs. + */ +struct riscv_cpuinfo { + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; +}; + +DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +#endif diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 8400f0cc9704..dafd0caa4f1d 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -70,12 +71,7 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) return -1; } -struct riscv_cpuinfo { - unsigned long mvendorid; - unsigned long marchid; - unsigned long mimpid; -}; -static DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); +DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); unsigned long riscv_cached_mvendorid(unsigned int cpu_id) { -- GitLab From ea3de9ce8aa280c5175c835bd3e94a3a9b814b74 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:10:59 -0700 Subject: [PATCH 3201/5631] RISC-V: Add a syscall for HW probing We don't have enough space for these all in ELF_HWCAP{,2} and there's no system call that quite does this, so let's just provide an arch-specific one to probe for hardware capabilities. This currently just provides m{arch,imp,vendor}id, but with the key-value pairs we can pass more in the future. Co-developed-by: Palmer Dabbelt Signed-off-by: Evan Green Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Tested-by: Heiko Stuebner Reviewed-by: Paul Walmsley Link: https://lore.kernel.org/r/20230407231103.2622178-3-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/riscv/hwprobe.rst | 41 ++++++++ Documentation/riscv/index.rst | 1 + arch/riscv/include/asm/hwprobe.h | 13 +++ arch/riscv/include/asm/syscall.h | 4 + arch/riscv/include/uapi/asm/hwprobe.h | 25 +++++ arch/riscv/include/uapi/asm/unistd.h | 9 ++ arch/riscv/kernel/sys_riscv.c | 135 +++++++++++++++++++++++++- 7 files changed, 227 insertions(+), 1 deletion(-) create mode 100644 Documentation/riscv/hwprobe.rst create mode 100644 arch/riscv/include/asm/hwprobe.h create mode 100644 arch/riscv/include/uapi/asm/hwprobe.h diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst new file mode 100644 index 000000000000..211828f706e3 --- /dev/null +++ b/Documentation/riscv/hwprobe.rst @@ -0,0 +1,41 @@ +.. SPDX-License-Identifier: GPL-2.0 + +RISC-V Hardware Probing Interface +--------------------------------- + +The RISC-V hardware probing interface is based around a single syscall, which +is defined in :: + + struct riscv_hwprobe { + __s64 key; + __u64 value; + }; + + long sys_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, cpu_set_t *cpus, + unsigned int flags); + +The arguments are split into three groups: an array of key-value pairs, a CPU +set, and some flags. The key-value pairs are supplied with a count. Userspace +must prepopulate the key field for each element, and the kernel will fill in the +value if the key is recognized. If a key is unknown to the kernel, its key field +will be cleared to -1, and its value set to 0. The CPU set is defined by +CPU_SET(3). For value-like keys (eg. vendor/arch/impl), the returned value will +be only be valid if all CPUs in the given set have the same value. Otherwise -1 +will be returned. For boolean-like keys, the value returned will be a logical +AND of the values for the specified CPUs. Usermode can supply NULL for cpus and +0 for cpu_count as a shortcut for all online CPUs. There are currently no flags, +this value must be zero for future compatibility. + +On success 0 is returned, on failure a negative error code is returned. + +The following keys are defined: + +* :c:macro:`RISCV_HWPROBE_KEY_MVENDORID`: Contains the value of ``mvendorid``, + as defined by the RISC-V privileged architecture specification. + +* :c:macro:`RISCV_HWPROBE_KEY_MARCHID`: Contains the value of ``marchid``, as + defined by the RISC-V privileged architecture specification. + +* :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as + defined by the RISC-V privileged architecture specification. diff --git a/Documentation/riscv/index.rst b/Documentation/riscv/index.rst index 2e5b18fbb145..175a91db0200 100644 --- a/Documentation/riscv/index.rst +++ b/Documentation/riscv/index.rst @@ -7,6 +7,7 @@ RISC-V architecture boot-image-header vm-layout + hwprobe patch-acceptance uabi diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h new file mode 100644 index 000000000000..6184bbc77256 --- /dev/null +++ b/arch/riscv/include/asm/hwprobe.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2023 Rivos, Inc + */ + +#ifndef _ASM_HWPROBE_H +#define _ASM_HWPROBE_H + +#include + +#define RISCV_HWPROBE_MAX_KEY 2 + +#endif diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index 384a63b86420..3b5a667928bf 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -10,6 +10,7 @@ #ifndef _ASM_RISCV_SYSCALL_H #define _ASM_RISCV_SYSCALL_H +#include #include #include #include @@ -75,4 +76,7 @@ static inline int syscall_get_arch(struct task_struct *task) } asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); + +asmlinkage long sys_riscv_hwprobe(struct riscv_hwprobe *, size_t, size_t, + unsigned long *, unsigned int); #endif /* _ASM_RISCV_SYSCALL_H */ diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h new file mode 100644 index 000000000000..b79be00920db --- /dev/null +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2023 Rivos, Inc + */ + +#ifndef _UAPI_ASM_HWPROBE_H +#define _UAPI_ASM_HWPROBE_H + +#include + +/* + * Interface for probing hardware capabilities from userspace, see + * Documentation/riscv/hwprobe.rst for more information. + */ +struct riscv_hwprobe { + __s64 key; + __u64 value; +}; + +#define RISCV_HWPROBE_KEY_MVENDORID 0 +#define RISCV_HWPROBE_KEY_MARCHID 1 +#define RISCV_HWPROBE_KEY_MIMPID 2 +/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ + +#endif diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 73d7cdd2ec49..950ab3fd4409 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -43,3 +43,12 @@ #define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15) #endif __SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache) + +/* + * Allows userspace to query the kernel for CPU architecture and + * microarchitecture details across a given set of CPUs. + */ +#ifndef __NR_riscv_hwprobe +#define __NR_riscv_hwprobe (__NR_arch_specific_syscall + 14) +#endif +__SYSCALL(__NR_riscv_hwprobe, sys_riscv_hwprobe) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 5d3f2fbeb33c..fe8e833ecb2e 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -6,8 +6,11 @@ */ #include -#include #include +#include +#include +#include +#include #include static long riscv_sys_mmap(unsigned long addr, unsigned long len, @@ -69,3 +72,133 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, return 0; } + +/* + * The hwprobe interface, for allowing userspace to probe to see which features + * are supported by the hardware. See Documentation/riscv/hwprobe.rst for more + * details. + */ +static void hwprobe_arch_id(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + u64 id = -1ULL; + bool first = true; + int cpu; + + for_each_cpu(cpu, cpus) { + u64 cpu_id; + + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + cpu_id = riscv_cached_mvendorid(cpu); + break; + case RISCV_HWPROBE_KEY_MIMPID: + cpu_id = riscv_cached_mimpid(cpu); + break; + case RISCV_HWPROBE_KEY_MARCHID: + cpu_id = riscv_cached_marchid(cpu); + break; + } + + if (first) + id = cpu_id; + + /* + * If there's a mismatch for the given set, return -1 in the + * value. + */ + if (id != cpu_id) { + id = -1ULL; + break; + } + } + + pair->value = id; +} + +static void hwprobe_one_pair(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + case RISCV_HWPROBE_KEY_MARCHID: + case RISCV_HWPROBE_KEY_MIMPID: + hwprobe_arch_id(pair, cpus); + break; + + /* + * For forward compatibility, unknown keys don't fail the whole + * call, but get their element key set to -1 and value set to 0 + * indicating they're unrecognized. + */ + default: + pair->key = -1; + pair->value = 0; + break; + } +} + +static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpu_count, + unsigned long __user *cpus_user, + unsigned int flags) +{ + size_t out; + int ret; + cpumask_t cpus; + + /* Check the reserved flags. */ + if (flags != 0) + return -EINVAL; + + /* + * The interface supports taking in a CPU mask, and returns values that + * are consistent across that mask. Allow userspace to specify NULL and + * 0 as a shortcut to all online CPUs. + */ + cpumask_clear(&cpus); + if (!cpu_count && !cpus_user) { + cpumask_copy(&cpus, cpu_online_mask); + } else { + if (cpu_count > cpumask_size()) + cpu_count = cpumask_size(); + + ret = copy_from_user(&cpus, cpus_user, cpu_count); + if (ret) + return -EFAULT; + + /* + * Userspace must provide at least one online CPU, without that + * there's no way to define what is supported. + */ + cpumask_and(&cpus, &cpus, cpu_online_mask); + if (cpumask_empty(&cpus)) + return -EINVAL; + } + + for (out = 0; out < pair_count; out++, pairs++) { + struct riscv_hwprobe pair; + + if (get_user(pair.key, &pairs->key)) + return -EFAULT; + + pair.value = 0; + hwprobe_one_pair(&pair, &cpus); + ret = put_user(pair.key, &pairs->key); + if (ret == 0) + ret = put_user(pair.value, &pairs->value); + + if (ret) + return -EFAULT; + } + + return 0; +} + +SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, + size_t, pair_count, size_t, cpu_count, unsigned long __user *, + cpus, unsigned int, flags) +{ + return do_riscv_hwprobe(pairs, pair_count, cpu_count, + cpus, flags); +} -- GitLab From 00e76e2c6a2bd3976d44d4a1fdd0b7a3c2566607 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:11:00 -0700 Subject: [PATCH 3202/5631] RISC-V: hwprobe: Add support for RISCV_HWPROBE_BASE_BEHAVIOR_IMA We have an implicit set of base behaviors that userspace depends on, which are mostly defined in various ISA specifications. Co-developed-by: Palmer Dabbelt Signed-off-by: Evan Green Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Tested-by: Heiko Stuebner Reviewed-by: Paul Walmsley Link: https://lore.kernel.org/r/20230407231103.2622178-4-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/riscv/hwprobe.rst | 24 ++++++++++++++++++++++++ arch/riscv/include/asm/hwprobe.h | 2 +- arch/riscv/include/uapi/asm/hwprobe.h | 5 +++++ arch/riscv/kernel/sys_riscv.c | 20 ++++++++++++++++++++ 4 files changed, 50 insertions(+), 1 deletion(-) diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst index 211828f706e3..945d44683c40 100644 --- a/Documentation/riscv/hwprobe.rst +++ b/Documentation/riscv/hwprobe.rst @@ -39,3 +39,27 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_KEY_MIMPLID`: Contains the value of ``mimplid``, as defined by the RISC-V privileged architecture specification. + +* :c:macro:`RISCV_HWPROBE_KEY_BASE_BEHAVIOR`: A bitmask containing the base + user-visible behavior that this kernel supports. The following base user ABIs + are defined: + + * :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: Support for rv32ima or + rv64ima, as defined by version 2.2 of the user ISA and version 1.10 of the + privileged ISA, with the following known exceptions (more exceptions may be + added, but only if it can be demonstrated that the user ABI is not broken): + + * The :fence.i: instruction cannot be directly executed by userspace + programs (it may still be executed in userspace via a + kernel-controlled mechanism such as the vDSO). + +* :c:macro:`RISCV_HWPROBE_KEY_IMA_EXT_0`: A bitmask containing the extensions + that are compatible with the :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: + base system behavior. + + * :c:macro:`RISCV_HWPROBE_IMA_FD`: The F and D extensions are supported, as + defined by commit cd20cee ("FMIN/FMAX now implement + minimumNumber/maximumNumber, not minNum/maxNum") of the RISC-V ISA manual. + + * :c:macro:`RISCV_HWPROBE_IMA_C`: The C extension is supported, as defined + by version 2.2 of the RISC-V ISA manual. diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 6184bbc77256..d717c80a64ff 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -8,6 +8,6 @@ #include -#define RISCV_HWPROBE_MAX_KEY 2 +#define RISCV_HWPROBE_MAX_KEY 4 #endif diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index b79be00920db..398e08f7e083 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -20,6 +20,11 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_MVENDORID 0 #define RISCV_HWPROBE_KEY_MARCHID 1 #define RISCV_HWPROBE_KEY_MIMPID 2 +#define RISCV_HWPROBE_KEY_BASE_BEHAVIOR 3 +#define RISCV_HWPROBE_BASE_BEHAVIOR_IMA (1 << 0) +#define RISCV_HWPROBE_KEY_IMA_EXT_0 4 +#define RISCV_HWPROBE_IMA_FD (1 << 0) +#define RISCV_HWPROBE_IMA_C (1 << 1) /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ #endif diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index fe8e833ecb2e..5ca567cef142 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -125,6 +126,25 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, case RISCV_HWPROBE_KEY_MIMPID: hwprobe_arch_id(pair, cpus); break; + /* + * The kernel already assumes that the base single-letter ISA + * extensions are supported on all harts, and only supports the + * IMA base, so just cheat a bit here and tell that to + * userspace. + */ + case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: + pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA; + break; + + case RISCV_HWPROBE_KEY_IMA_EXT_0: + pair->value = 0; + if (has_fpu()) + pair->value |= RISCV_HWPROBE_IMA_FD; + + if (riscv_isa_extension_available(NULL, c)) + pair->value |= RISCV_HWPROBE_IMA_C; + + break; /* * For forward compatibility, unknown keys don't fail the whole -- GitLab From 62a31d6e38bd0faef7c956b358d651f7bdc4ae0c Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:11:01 -0700 Subject: [PATCH 3203/5631] RISC-V: hwprobe: Support probing of misaligned access performance This allows userspace to select various routines to use based on the performance of misaligned access on the target hardware. Rather than adding DT bindings, this change taps into the alternatives mechanism used to probe CPU errata. Add a new function pointer alongside the vendor-specific errata_patch_func() that probes for desirable errata (otherwise known as "features"). Unlike the errata_patch_func(), this function is called on each CPU as it comes up, so it can save feature information per-CPU. The T-head C906 has fast unaligned access, both as defined by GCC [1], and in performing a basic benchmark, which determined that byte copies are >50% slower than a misaligned word copy of the same data size (source for this test at [2]): bytecopy size f000 count 50000 offset 0 took 31664899 us wordcopy size f000 count 50000 offset 0 took 5180919 us wordcopy size f000 count 50000 offset 1 took 13416949 us [1] https://github.com/gcc-mirror/gcc/blob/master/gcc/config/riscv/riscv.cc#L353 [2] https://pastebin.com/EPXvDHSW Co-developed-by: Palmer Dabbelt Signed-off-by: Evan Green Reviewed-by: Heiko Stuebner Tested-by: Heiko Stuebner Reviewed-by: Conor Dooley Reviewed-by: Paul Walmsley Link: https://lore.kernel.org/r/20230407231103.2622178-5-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- Documentation/riscv/hwprobe.rst | 21 ++++++++++++++++++++ arch/riscv/errata/thead/errata.c | 10 ++++++++++ arch/riscv/include/asm/alternative.h | 5 +++++ arch/riscv/include/asm/cpufeature.h | 2 ++ arch/riscv/include/asm/hwprobe.h | 2 +- arch/riscv/include/uapi/asm/hwprobe.h | 7 +++++++ arch/riscv/kernel/alternative.c | 19 ++++++++++++++++++ arch/riscv/kernel/cpufeature.c | 3 +++ arch/riscv/kernel/smpboot.c | 1 + arch/riscv/kernel/sys_riscv.c | 28 +++++++++++++++++++++++++++ 10 files changed, 97 insertions(+), 1 deletion(-) diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst index 945d44683c40..9f0dd62dcb5d 100644 --- a/Documentation/riscv/hwprobe.rst +++ b/Documentation/riscv/hwprobe.rst @@ -63,3 +63,24 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_IMA_C`: The C extension is supported, as defined by version 2.2 of the RISC-V ISA manual. + +* :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: A bitmask that contains performance + information about the selected set of processors. + + * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNKNOWN`: The performance of misaligned + accesses is unknown. + + * :c:macro:`RISCV_HWPROBE_MISALIGNED_EMULATED`: Misaligned accesses are + emulated via software, either in or below the kernel. These accesses are + always extremely slow. + + * :c:macro:`RISCV_HWPROBE_MISALIGNED_SLOW`: Misaligned accesses are supported + in hardware, but are slower than the cooresponding aligned accesses + sequences. + + * :c:macro:`RISCV_HWPROBE_MISALIGNED_FAST`: Misaligned accesses are supported + in hardware and are faster than the cooresponding aligned accesses + sequences. + + * :c:macro:`RISCV_HWPROBE_MISALIGNED_UNSUPPORTED`: Misaligned accesses are + not supported at all and will generate a misaligned address fault. diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 3b96a06d3c54..5b6d62586a8b 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -11,7 +11,9 @@ #include #include #include +#include #include +#include #include #include @@ -115,3 +117,11 @@ void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct al if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) local_flush_icache_all(); } + +void __init_or_module thead_feature_probe_func(unsigned int cpu, + unsigned long archid, + unsigned long impid) +{ + if ((archid == 0) && (impid == 0)) + per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_FAST; +} diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index b8648d4f2ac1..b5774e24d4a3 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -28,6 +28,7 @@ #define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset) #define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset) +void __init probe_vendor_features(unsigned int cpu); void __init apply_boot_alternatives(void); void __init apply_early_boot_alternatives(void); void apply_module_alternatives(void *start, size_t length); @@ -55,11 +56,15 @@ void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); +void thead_feature_probe_func(unsigned int cpu, unsigned long archid, + unsigned long impid); + void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned int stage); #else /* CONFIG_RISCV_ALTERNATIVE */ +static inline void probe_vendor_features(unsigned int cpu) { } static inline void apply_boot_alternatives(void) { } static inline void apply_early_boot_alternatives(void) { } static inline void apply_module_alternatives(void *start, size_t length) { } diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 66ebaae449c8..808d5403f2ac 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -18,4 +18,6 @@ struct riscv_cpuinfo { DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); +DECLARE_PER_CPU(long, misaligned_access_speed); + #endif diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index d717c80a64ff..78936f4ff513 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -8,6 +8,6 @@ #include -#define RISCV_HWPROBE_MAX_KEY 4 +#define RISCV_HWPROBE_MAX_KEY 5 #endif diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 398e08f7e083..8d745a4ad8a2 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -25,6 +25,13 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_KEY_IMA_EXT_0 4 #define RISCV_HWPROBE_IMA_FD (1 << 0) #define RISCV_HWPROBE_IMA_C (1 << 1) +#define RISCV_HWPROBE_KEY_CPUPERF_0 5 +#define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) +#define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) +#define RISCV_HWPROBE_MISALIGNED_SLOW (2 << 0) +#define RISCV_HWPROBE_MISALIGNED_FAST (3 << 0) +#define RISCV_HWPROBE_MISALIGNED_UNSUPPORTED (4 << 0) +#define RISCV_HWPROBE_MISALIGNED_MASK (7 << 0) /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ #endif diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index 2354c69dc7d1..fc65c9293ac5 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -27,6 +27,8 @@ struct cpu_manufacturer_info_t { void (*patch_func)(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage); + void (*feature_probe_func)(unsigned int cpu, unsigned long archid, + unsigned long impid); }; static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) @@ -41,6 +43,7 @@ static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_inf cpu_mfr_info->imp_id = sbi_get_mimpid(); #endif + cpu_mfr_info->feature_probe_func = NULL; switch (cpu_mfr_info->vendor_id) { #ifdef CONFIG_ERRATA_SIFIVE case SIFIVE_VENDOR_ID: @@ -50,6 +53,7 @@ static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_inf #ifdef CONFIG_ERRATA_THEAD case THEAD_VENDOR_ID: cpu_mfr_info->patch_func = thead_errata_patch_func; + cpu_mfr_info->feature_probe_func = thead_feature_probe_func; break; #endif default: @@ -139,6 +143,20 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, } } +/* Called on each CPU as it starts */ +void __init_or_module probe_vendor_features(unsigned int cpu) +{ + struct cpu_manufacturer_info_t cpu_mfr_info; + + riscv_fill_cpu_mfr_info(&cpu_mfr_info); + if (!cpu_mfr_info.feature_probe_func) + return; + + cpu_mfr_info.feature_probe_func(cpu, + cpu_mfr_info.arch_id, + cpu_mfr_info.imp_id); +} + /* * This is called very early in the boot process (directly after we run * a feature detect on the boot CPU). No need to worry about other CPUs @@ -193,6 +211,7 @@ void __init apply_boot_alternatives(void) /* If called on non-boot cpu things could go wrong */ WARN_ON(smp_processor_id() != 0); + probe_vendor_features(0); _apply_alternatives((struct alt_entry *)__alt_start, (struct alt_entry *)__alt_end, RISCV_ALTERNATIVES_BOOT); diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 59d58ee0f68d..8bbc89351050 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -30,6 +30,9 @@ unsigned long elf_hwcap __read_mostly; /* Host ISA bitmap */ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; +/* Performance information */ +DEFINE_PER_CPU(long, misaligned_access_speed); + /** * riscv_isa_extension_base() - Get base extension word * diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index ddb2afba6d25..2867c12c3d16 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -168,6 +168,7 @@ asmlinkage __visible void smp_callin(void) notify_cpu_starting(curr_cpuid); numa_add_cpu(curr_cpuid); set_cpu_online(curr_cpuid, 1); + probe_vendor_features(curr_cpuid); /* * Remote TLB flushes are ignored while the CPU is offline, so emit diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 5ca567cef142..55389e7595f6 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -117,6 +118,29 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, pair->value = id; } +static u64 hwprobe_misaligned(const struct cpumask *cpus) +{ + int cpu; + u64 perf = -1ULL; + + for_each_cpu(cpu, cpus) { + int this_perf = per_cpu(misaligned_access_speed, cpu); + + if (perf == -1ULL) + perf = this_perf; + + if (perf != this_perf) { + perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN; + break; + } + } + + if (perf == -1ULL) + return RISCV_HWPROBE_MISALIGNED_UNKNOWN; + + return perf; +} + static void hwprobe_one_pair(struct riscv_hwprobe *pair, const struct cpumask *cpus) { @@ -146,6 +170,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, break; + case RISCV_HWPROBE_KEY_CPUPERF_0: + pair->value = hwprobe_misaligned(cpus); + break; + /* * For forward compatibility, unknown keys don't fail the whole * call, but get their element key set to -1 and value set to 0 -- GitLab From 287dcc2b0c831d3e3887421f68e3db6b8b8f4eb1 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:11:02 -0700 Subject: [PATCH 3204/5631] selftests: Test the new RISC-V hwprobe interface This adds a test for the recently added RISC-V interface for probing hardware capabilities. It happens to be the first selftest we have for RISC-V, so I've added some infrastructure for those as well. Co-developed-by: Palmer Dabbelt Signed-off-by: Evan Green Link: https://lore.kernel.org/r/20230407231103.2622178-6-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/riscv/Makefile | 58 ++++++++++++ .../testing/selftests/riscv/hwprobe/Makefile | 10 +++ .../testing/selftests/riscv/hwprobe/hwprobe.c | 90 +++++++++++++++++++ .../selftests/riscv/hwprobe/sys_hwprobe.S | 12 +++ 5 files changed, 171 insertions(+) create mode 100644 tools/testing/selftests/riscv/Makefile create mode 100644 tools/testing/selftests/riscv/hwprobe/Makefile create mode 100644 tools/testing/selftests/riscv/hwprobe/hwprobe.c create mode 100644 tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 13a6837a0c6b..4bea26109450 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -63,6 +63,7 @@ TARGETS += pstore TARGETS += ptrace TARGETS += openat2 TARGETS += resctrl +TARGETS += riscv TARGETS += rlimits TARGETS += rseq TARGETS += rtc diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile new file mode 100644 index 000000000000..32a72902d045 --- /dev/null +++ b/tools/testing/selftests/riscv/Makefile @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: GPL-2.0 +# Originally tools/testing/arm64/Makefile + +# When ARCH not overridden for crosscompiling, lookup machine +ARCH ?= $(shell uname -m 2>/dev/null || echo not) + +ifneq (,$(filter $(ARCH),riscv)) +RISCV_SUBTARGETS ?= hwprobe +else +RISCV_SUBTARGETS := +endif + +CFLAGS := -Wall -O2 -g + +# A proper top_srcdir is needed by KSFT(lib.mk) +top_srcdir = $(realpath ../../../../) + +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -I$(top_srcdir)/tools/testing/selftests/ + +CFLAGS += $(KHDR_INCLUDES) + +export CFLAGS +export top_srcdir + +all: + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + mkdir -p $$BUILD_TARGET; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +install: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +run_tests: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +# Avoid any output on non riscv on emit_tests +emit_tests: all + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +clean: + @for DIR in $(RISCV_SUBTARGETS); do \ + BUILD_TARGET=$(OUTPUT)/$$DIR; \ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ + done + +.PHONY: all clean install run_tests emit_tests diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile new file mode 100644 index 000000000000..ebdbb3c22e54 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +TEST_GEN_PROGS := hwprobe + +include ../../lib.mk + +$(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S + $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c new file mode 100644 index 000000000000..09f290a67420 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include + +/* + * Rather than relying on having a new enough libc to define this, just do it + * ourselves. This way we don't need to be coupled to a new-enough libc to + * contain the call. + */ +long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, unsigned int flags); + +int main(int argc, char **argv) +{ + struct riscv_hwprobe pairs[8]; + unsigned long cpus; + long out; + + /* Fake the CPU_SET ops. */ + cpus = -1; + + /* + * Just run a basic test: pass enough pairs to get up to the base + * behavior, and then check to make sure it's sane. + */ + for (long i = 0; i < 8; i++) + pairs[i].key = i; + out = riscv_hwprobe(pairs, 8, 1, &cpus, 0); + if (out != 0) + return -1; + for (long i = 0; i < 4; ++i) { + /* Fail if the kernel claims not to recognize a base key. */ + if ((i < 4) && (pairs[i].key != i)) + return -2; + + if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR) + continue; + + if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA) + continue; + + return -3; + } + + /* + * This should also work with a NULL CPU set, but should not work + * with an improperly supplied CPU set. + */ + out = riscv_hwprobe(pairs, 8, 0, 0, 0); + if (out != 0) + return -4; + + out = riscv_hwprobe(pairs, 8, 0, &cpus, 0); + if (out == 0) + return -5; + + out = riscv_hwprobe(pairs, 8, 1, 0, 0); + if (out == 0) + return -6; + + /* + * Check that keys work by providing one that we know exists, and + * checking to make sure the resultig pair is what we asked for. + */ + pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR; + out = riscv_hwprobe(pairs, 1, 1, &cpus, 0); + if (out != 0) + return -7; + if (pairs[0].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR) + return -8; + + /* + * Check that an unknown key gets overwritten with -1, + * but doesn't block elements after it. + */ + pairs[0].key = 0x5555; + pairs[1].key = 1; + pairs[1].value = 0xAAAA; + out = riscv_hwprobe(pairs, 2, 0, 0, 0); + if (out != 0) + return -9; + + if (pairs[0].key != -1) + return -10; + + if ((pairs[1].key != 1) || (pairs[1].value == 0xAAAA)) + return -11; + + return 0; +} diff --git a/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S b/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S new file mode 100644 index 000000000000..a4773c88d267 --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/sys_hwprobe.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos, Inc */ + +.text +.global riscv_hwprobe +riscv_hwprobe: + # Put __NR_riscv_hwprobe in the syscall number register, then just shim + # back the kernel's return. This doesn't do any sort of errno + # handling, the caller can deal with it. + li a7, 258 + ecall + ret -- GitLab From aa5af0aa90bad3f1cad5a90ee5eecd92ac9f3096 Mon Sep 17 00:00:00 2001 From: Evan Green Date: Fri, 7 Apr 2023 16:11:03 -0700 Subject: [PATCH 3205/5631] RISC-V: Add hwprobe vDSO function and data Add a vDSO function __vdso_riscv_hwprobe, which can sit in front of the riscv_hwprobe syscall and answer common queries. We stash a copy of static answers for the "all CPUs" case in the vDSO data page. This data is private to the vDSO, so we can decide later to change what's stored there or under what conditions we defer to the syscall. Currently all data can be discovered at boot, so the vDSO function answers all queries when the cpumask is set to the "all CPUs" hint. There's also a boolean in the data that lets the vDSO function know that all CPUs are the same. In that case, the vDSO will also answer queries for arbitrary CPU masks in addition to the "all CPUs" hint. Signed-off-by: Evan Green Link: https://lore.kernel.org/r/20230407231103.2622178-7-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + arch/riscv/include/asm/vdso/data.h | 17 +++++++ arch/riscv/include/asm/vdso/gettimeofday.h | 8 ++++ arch/riscv/kernel/compat_vdso/Makefile | 2 +- arch/riscv/kernel/sys_riscv.c | 45 +++++++++++++++++++ arch/riscv/kernel/vdso.c | 6 --- arch/riscv/kernel/vdso/Makefile | 4 ++ arch/riscv/kernel/vdso/hwprobe.c | 52 ++++++++++++++++++++++ arch/riscv/kernel/vdso/sys_hwprobe.S | 15 +++++++ arch/riscv/kernel/vdso/vdso.lds.S | 3 ++ 10 files changed, 146 insertions(+), 7 deletions(-) create mode 100644 arch/riscv/include/asm/vdso/data.h create mode 100644 arch/riscv/kernel/vdso/hwprobe.c create mode 100644 arch/riscv/kernel/vdso/sys_hwprobe.S diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..a20e105efa4e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -33,6 +33,7 @@ config RISCV select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_VDSO_DATA select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK diff --git a/arch/riscv/include/asm/vdso/data.h b/arch/riscv/include/asm/vdso/data.h new file mode 100644 index 000000000000..dc2f76f58b76 --- /dev/null +++ b/arch/riscv/include/asm/vdso/data.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __RISCV_ASM_VDSO_DATA_H +#define __RISCV_ASM_VDSO_DATA_H + +#include +#include +#include + +struct arch_vdso_data { + /* Stash static answers to the hwprobe queries when all CPUs are selected. */ + __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1]; + + /* Boolean indicating all CPUs have the same static hwprobe values. */ + __u8 homogeneous_cpus; +}; + +#endif /* __RISCV_ASM_VDSO_DATA_H */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index 77d9c2f721c4..ba3283cf7acc 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -9,6 +9,12 @@ #include #include +/* + * 32-bit land is lacking generic time vsyscalls as well as the legacy 32-bit + * time syscalls like gettimeofday. Skip these definitions since on 32-bit. + */ +#ifdef CONFIG_GENERIC_TIME_VSYSCALL + #define VDSO_HAS_CLOCK_GETRES 1 static __always_inline @@ -60,6 +66,8 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } +#endif /* CONFIG_GENERIC_TIME_VSYSCALL */ + static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, const struct vdso_data *vd) { diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index 260daf3236d3..91a3431ae1fe 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -22,7 +22,7 @@ targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso)) obj-y += compat_vdso.o -CPPFLAGS_compat_vdso.lds += -P -C -U$(ARCH) +CPPFLAGS_compat_vdso.lds += -P -C -DCOMPAT_VDSO -U$(ARCH) # Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 55389e7595f6..849b4170629d 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -14,6 +14,7 @@ #include #include #include +#include static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -243,6 +244,50 @@ static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, return 0; } +#ifdef CONFIG_MMU + +static int __init init_hwprobe_vdso_data(void) +{ + struct vdso_data *vd = __arch_get_k_vdso_data(); + struct arch_vdso_data *avd = &vd->arch_data; + u64 id_bitsmash = 0; + struct riscv_hwprobe pair; + int key; + + /* + * Initialize vDSO data with the answers for the "all CPUs" case, to + * save a syscall in the common case. + */ + for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) { + pair.key = key; + hwprobe_one_pair(&pair, cpu_online_mask); + + WARN_ON_ONCE(pair.key < 0); + + avd->all_cpu_hwprobe_values[key] = pair.value; + /* + * Smash together the vendor, arch, and impl IDs to see if + * they're all 0 or any negative. + */ + if (key <= RISCV_HWPROBE_KEY_MIMPID) + id_bitsmash |= pair.value; + } + + /* + * If the arch, vendor, and implementation ID are all the same across + * all harts, then assume all CPUs are the same, and allow the vDSO to + * answer queries for arbitrary masks. However if all values are 0 (not + * populated) or any value returns -1 (varies across CPUs), then the + * vDSO should defer to the kernel for exotic cpu masks. + */ + avd->homogeneous_cpus = (id_bitsmash > 0); + return 0; +} + +arch_initcall_sync(init_hwprobe_vdso_data); + +#endif /* CONFIG_MMU */ + SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, size_t, pair_count, size_t, cpu_count, unsigned long __user *, cpus, unsigned int, flags) diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index cc2d1e8c8736..9a68e7eaae4d 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -14,13 +14,7 @@ #include #include #include - -#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include -#else -struct vdso_data { -}; -#endif enum vvar_pages { VVAR_DATA_PAGE_OFFSET, diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 06e6b27f3bcc..022258426050 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -12,6 +12,8 @@ vdso-syms += vgettimeofday endif vdso-syms += getcpu vdso-syms += flush_icache +vdso-syms += hwprobe +vdso-syms += sys_hwprobe # Files to link into the vdso obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o @@ -23,6 +25,8 @@ ifneq ($(c-gettimeofday-y),) CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif +CFLAGS_hwprobe.o += -fPIC + # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c new file mode 100644 index 000000000000..d40bec6ac078 --- /dev/null +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2023 Rivos, Inc + */ + +#include +#include +#include + +extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, + unsigned int flags); + +/* Add a prototype to avoid -Wmissing-prototypes warning. */ +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, + unsigned int flags); + +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpu_count, unsigned long *cpus, + unsigned int flags) +{ + const struct vdso_data *vd = __arch_get_vdso_data(); + const struct arch_vdso_data *avd = &vd->arch_data; + bool all_cpus = !cpu_count && !cpus; + struct riscv_hwprobe *p = pairs; + struct riscv_hwprobe *end = pairs + pair_count; + + /* + * Defer to the syscall for exotic requests. The vdso has answers + * stashed away only for the "all cpus" case. If all CPUs are + * homogeneous, then this function can handle requests for arbitrary + * masks. + */ + if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus)) + return riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags); + + /* This is something we can handle, fill out the pairs. */ + while (p < end) { + if (p->key <= RISCV_HWPROBE_MAX_KEY) { + p->value = avd->all_cpu_hwprobe_values[p->key]; + + } else { + p->key = -1; + p->value = 0; + } + + p++; + } + + return 0; +} diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S new file mode 100644 index 000000000000..4e704146c77a --- /dev/null +++ b/arch/riscv/kernel/vdso/sys_hwprobe.S @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos, Inc */ + +#include +#include + +.text +ENTRY(riscv_hwprobe) + .cfi_startproc + li a7, __NR_riscv_hwprobe + ecall + ret + + .cfi_endproc +ENDPROC(riscv_hwprobe) diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index 4a0606633290..82ce64900f3d 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -82,6 +82,9 @@ VERSION #endif __vdso_getcpu; __vdso_flush_icache; +#ifndef COMPAT_VDSO + __vdso_riscv_hwprobe; +#endif local: *; }; } -- GitLab From 59f876fb9d68a4d8c20305d7a7a0daf4ee9478a8 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 6 Apr 2023 10:25:29 +0300 Subject: [PATCH 3206/5631] mm: avoid passing 0 to __ffs() 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely") results in various boot failures (hang) on arm targets Debug messages reveal the reason. ########### MAX_ORDER=10 start=0 __ffs(start)=-1 min()=10 min_t=-1 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ If start==0, __ffs(start) returns 0xfffffff or (as int) -1, which min_t() interprets as such, while min() apparently uses the returned unsigned long value. Obviously a negative order isn't received well by the rest of the code. [akpm@linux-foundation.org: fix comment, per Mike] Link: https://lkml.kernel.org/r/ZDBa7HWZK69dKKzH@kernel.org Link: https://lkml.kernel.org/r/20230406072529.vupqyrzqnhyozeyh@box.shutemov.name Fixes: 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely") Signed-off-by: "Kirill A. Shutemov" Reported-by: Guenter Roeck Link: https://lkml.kernel.org/r/9460377a-38aa-4f39-ad57-fb73725f92db@roeck-us.net Reviewed-by: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- mm/memblock.c | 11 ++++++++++- mm/memory_hotplug.c | 13 ++++++++++++- 2 files changed, 22 insertions(+), 2 deletions(-) diff --git a/mm/memblock.c b/mm/memblock.c index 7911224b1ed3..3feafea06ab2 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2043,7 +2043,16 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) int order; while (start < end) { - order = min_t(int, MAX_ORDER, __ffs(start)); + /* + * Free the pages in the largest chunks alignment allows. + * + * __ffs() behaviour is undefined for 0. start == 0 is + * MAX_ORDER-aligned, set order to MAX_ORDER for the case. + */ + if (start) + order = min_t(int, MAX_ORDER, __ffs(start)); + else + order = MAX_ORDER; while (start + (1UL << order) > end) order--; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c8f0a8c2d049..8e0fa209d533 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -605,7 +605,18 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * this and the first chunk to online will be pageblock_nr_pages. */ for (pfn = start_pfn; pfn < end_pfn;) { - int order = min_t(int, MAX_ORDER, __ffs(pfn)); + int order; + + /* + * Free to online pages in the largest chunks alignment allows. + * + * __ffs() behaviour is undefined for 0. start == 0 is + * MAX_ORDER-aligned, Set order to MAX_ORDER for the case. + */ + if (pfn) + order = min_t(int, MAX_ORDER, __ffs(pfn)); + else + order = MAX_ORDER; (*online_page_callback)(pfn_to_page(pfn), order); pfn += (1UL << order); -- GitLab From 5f300fd59a2ae90b8a7fb5ed3d5fd43768236c38 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Apr 2023 10:03:53 +0200 Subject: [PATCH 3207/5631] mm: make arch_has_descending_max_zone_pfns() static clang produces a build failure on x86 for some randconfig builds after a change that moves around code to mm/mm_init.c: Cannot find symbol for section 2: .text. mm/mm_init.o: failed I have not been able to figure out why this happens, but the __weak annotation on arch_has_descending_max_zone_pfns() is the trigger here. Removing the weak function in favor of an open-coded Kconfig option check avoids the problem and becomes clearer as well as better to optimize by the compiler. [arnd@arndb.de: fix logic bug] Link: https://lkml.kernel.org/r/20230415081904.969049-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20230414080418.110236-1-arnd@kernel.org Fixes: 9420f89db2dd ("mm: move most of core MM initialization to mm/mm_init.c") Signed-off-by: Arnd Bergmann Acked-by: Vlastimil Babka Tested-by: SeongJae Park Tested-by: Geert Uytterhoeven Acked-by: Mike Rapoport (IBM) Cc: kernel test robot Signed-off-by: Andrew Morton --- arch/arc/mm/init.c | 5 ----- include/linux/mm.h | 1 - mm/mm_init.c | 4 ++-- 3 files changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index ce4e939a7f07..2b89b6c53801 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -74,11 +74,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) base, TO_MB(size), !in_use ? "Not used":""); } -bool arch_has_descending_max_zone_pfns(void) -{ - return !IS_ENABLED(CONFIG_ARC_HAS_PAE40); -} - /* * First memory setup routine called from setup_arch() * 1. setup swapper's mm @init_mm diff --git a/include/linux/mm.h b/include/linux/mm.h index e249208f8fbe..5e5ef6ee4003 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3035,7 +3035,6 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; -extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; diff --git a/mm/mm_init.c b/mm/mm_init.c index dd3a6ed9663f..a0ec3b3acb5e 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1752,9 +1752,9 @@ static void __init free_area_init_memoryless_node(int nid) * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For * such cases we allow max_zone_pfn sorted in the descending order */ -bool __weak arch_has_descending_max_zone_pfns(void) +static bool arch_has_descending_max_zone_pfns(void) { - return false; + return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40); } /** -- GitLab From f7ddb612568361e04d53fcd984d43d1c32c1294a Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Mon, 17 Apr 2023 22:08:50 +0900 Subject: [PATCH 3208/5631] zsmalloc: reset compaction source zspage pointer after putback_zspage() The current implementation of the compaction loop fails to set the source zspage pointer to NULL in all cases, leading to a potential issue where __zs_compact() could use a stale zspage pointer. This pointer could even point to a previously freed zspage, causing unexpected behavior in the putback_zspage() and migrate_write_unlock() functions after returning from the compaction loop. Address the issue by ensuring that the source zspage pointer is always set to NULL when it should be. Link: https://lkml.kernel.org/r/20230417130850.1784777-1-senozhatsky@chromium.org Fixes: 5a845e9f2d66 ("zsmalloc: rework compaction algorithm") Signed-off-by: Sergey Senozhatsky Reported-by: Yu Zhao Tested-by: Yu Zhao Reviewed-by: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index aea50e2aa350..cc81dfba05a0 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -2239,8 +2239,8 @@ static unsigned long __zs_compact(struct zs_pool *pool, if (fg == ZS_INUSE_RATIO_0) { free_zspage(pool, class, src_zspage); pages_freed += class->pages_per_zspage; - src_zspage = NULL; } + src_zspage = NULL; if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100 || spin_is_contended(&pool->lock)) { -- GitLab From 90fd833609c82487a0eca1581becde7ab54d9429 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 14:23:35 +0200 Subject: [PATCH 3209/5631] kasan: remove hwasan-kernel-mem-intrinsic-prefix=1 for clang-14 Some unknown -mllvm options (i.e. those starting with the letter "h") don't cause an error to be returned by clang, so the cc-option helper adds the unknown hwasan-kernel-mem-intrinsic-prefix=1 flag to CFLAGS with compilers that are new enough for hwasan but too old for this option. This causes a rather unreadable build failure: fixdep: error opening file: scripts/mod/.empty.o.d: No such file or directory make[4]: *** [/home/arnd/arm-soc/scripts/Makefile.build:252: scripts/mod/empty.o] Error 2 fixdep: error opening file: scripts/mod/.devicetable-offsets.s.d: No such file or directory make[4]: *** [/home/arnd/arm-soc/scripts/Makefile.build:114: scripts/mod/devicetable-offsets.s] Error 2 Add a version check to only allow this option with clang-15, gcc-13 or later versions. Link: https://lkml.kernel.org/r/20230418122350.1646391-1-arnd@kernel.org Fixes: 51287dcb00cc ("kasan: emit different calls for instrumentable memintrinsics") Link: https://lore.kernel.org/all/CANpmjNMwYosrvqh4ogDO8rgn+SeDHM2b-shD21wTypm_6MMe=g@mail.gmail.com/ Signed-off-by: Arnd Bergmann Reviewed-by: Marco Elver Reviewed-by: Nathan Chancellor Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Masahiro Yamada Cc: Michael Ellerman Cc: Nick Desaulniers Cc: Nicolas Schier Cc: Peter Zijlstra Cc: Tom Rix Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- scripts/Makefile.kasan | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index c186110ffa20..390658a2d5b7 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -69,7 +69,9 @@ CFLAGS_KASAN := -fsanitize=kernel-hwaddress \ $(instrumentation_flags) # Instrument memcpy/memset/memmove calls by using instrumented __hwasan_mem*(). +ifeq ($(call clang-min-version, 150000)$(call gcc-min-version, 130000),y) CFLAGS_KASAN += $(call cc-param,hwasan-kernel-mem-intrinsic-prefix=1) +endif endif # CONFIG_KASAN_SW_TAGS -- GitLab From 2ce0bdfebc74f6cbd4e97a4e767d505a81c38cf2 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Wed, 29 Mar 2023 18:53:30 +0400 Subject: [PATCH 3210/5631] mm: khugepaged: fix kernel BUG in hpage_collapse_scan_file() Syzkaller reported the following issue: kernel BUG at mm/khugepaged.c:1823! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 5097 Comm: syz-executor220 Not tainted 6.2.0-syzkaller-13154-g857f1268a591 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/16/2023 RIP: 0010:collapse_file mm/khugepaged.c:1823 [inline] RIP: 0010:hpage_collapse_scan_file+0x67c8/0x7580 mm/khugepaged.c:2233 Code: 00 00 89 de e8 c9 66 a3 ff 31 ff 89 de e8 c0 66 a3 ff 45 84 f6 0f 85 28 0d 00 00 e8 22 64 a3 ff e9 dc f7 ff ff e8 18 64 a3 ff <0f> 0b f3 0f 1e fa e8 0d 64 a3 ff e9 93 f6 ff ff f3 0f 1e fa 4c 89 RSP: 0018:ffffc90003dff4e0 EFLAGS: 00010093 RAX: ffffffff81e95988 RBX: 00000000000001c1 RCX: ffff8880205b3a80 RDX: 0000000000000000 RSI: 00000000000001c0 RDI: 00000000000001c1 RBP: ffffc90003dff830 R08: ffffffff81e90e67 R09: fffffbfff1a433c3 R10: 0000000000000000 R11: dffffc0000000001 R12: 0000000000000000 R13: ffffc90003dff6c0 R14: 00000000000001c0 R15: 0000000000000000 FS: 00007fdbae5ee700(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fdbae6901e0 CR3: 000000007b2dd000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: madvise_collapse+0x721/0xf50 mm/khugepaged.c:2693 madvise_vma_behavior mm/madvise.c:1086 [inline] madvise_walk_vmas mm/madvise.c:1260 [inline] do_madvise+0x9e5/0x4680 mm/madvise.c:1439 __do_sys_madvise mm/madvise.c:1452 [inline] __se_sys_madvise mm/madvise.c:1450 [inline] __x64_sys_madvise+0xa5/0xb0 mm/madvise.c:1450 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd The xas_store() call during page cache scanning can potentially translate 'xas' into the error state (with the reproducer provided by the syzkaller the error code is -ENOMEM). However, there are no further checks after the 'xas_store', and the next call of 'xas_next' at the start of the scanning cycle doesn't increase the xa_index, and the issue occurs. This patch will add the xarray state error checking after the xas_store() and the corresponding result error code. Tested via syzbot. [akpm@linux-foundation.org: update include/trace/events/huge_memory.h's SCAN_STATUS] Link: https://lkml.kernel.org/r/20230329145330.23191-1-ivan.orlov0322@gmail.com Link: https://syzkaller.appspot.com/bug?id=7d6bb3760e026ece7524500fe44fb024a0e959fc Signed-off-by: Ivan Orlov Reported-by: syzbot+9578faa5475acb35fa50@syzkaller.appspotmail.com Tested-by: Zach O'Keefe Cc: Yang Shi Cc: Himadri Pandya Cc: Ivan Orlov Cc: Shuah Khan Cc: Song Liu Cc: Rik van Riel Cc: Kirill A. Shutemov Cc: Johannes Weiner Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 3 ++- mm/khugepaged.c | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+), 1 deletion(-) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 3e6fb05852f9..c84c7af70158 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -36,7 +36,8 @@ EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ EM( SCAN_TRUNCATED, "truncated") \ - EMe(SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ + EM( SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ + EMe(SCAN_STORE_FAILED, "store_failed") #undef EM #undef EMe diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 2c6548cd18a9..3b61cd188f7b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -55,6 +55,7 @@ enum scan_result { SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, + SCAN_STORE_FAILED, }; #define CREATE_TRACE_POINTS @@ -1857,6 +1858,15 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto xa_locked; } xas_store(&xas, hpage); + if (xas_error(&xas)) { + /* revert shmem_charge performed + * in the previous condition + */ + mapping->nrpages--; + shmem_uncharge(mapping->host, 1); + result = SCAN_STORE_FAILED; + goto xa_locked; + } nr_none++; continue; } @@ -2009,6 +2019,11 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, /* Finally, replace with the new page. */ xas_store(&xas, hpage); + /* We can't get an ENOMEM here (because the allocation happened before) + * but let's check for errors (XArray implementation can be + * changed in the future) + */ + WARN_ON_ONCE(xas_error(&xas)); continue; out_unlock: unlock_page(page); @@ -2046,6 +2061,11 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, /* Join all the small entries into a single multi-index entry */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, hpage); + /* Here we can't get an ENOMEM (because entries were + * previously allocated) But let's check for errors + * (XArray implementation can be changed in the future) + */ + WARN_ON_ONCE(xas_error(&xas)); xa_locked: xas_unlock_irq(&xas); xa_unlocked: -- GitLab From a85c2257a8ac353af16dbcbf32c50d3380860bc5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 17 Mar 2023 14:44:47 +0100 Subject: [PATCH 3211/5631] sched/isolation: add cpu_is_isolated() API Patch series "memcg, cpuisol: do not interfere pcp cache charges draining with cpuisol workloads". Leonardo has reported [1] that pcp memcg charge draining can interfere with cpu isolated workloads. The said draining is done from a WQ context with a pcp worker scheduled on each CPU which holds any cached charges for a specific memcg hierarchy. Operation is not really a common operation [2]. It can be triggered from the userspace though so some care is definitely due. Leonardo has tried to address the issue by allowing remote charge draining [3]. This approach requires an additional locking to synchronize pcp caches sync from a remote cpu from local pcp consumers. Even though the proposed lock was per-cpu there is still potential for contention and less predictable behavior. This patchset addresses the issue from a different angle. Rather than dealing with a potential synchronization, cpus which are isolated are simply never scheduled to be drained. This means that a small amount of charges could be laying around and waiting for a later use or they are flushed when a different memcg is charged from the same cpu. More details are in patch 2. The first patch from Frederic is implementing an abstraction to tell whether a specific cpu has been isolated and therefore require a special treatment. This patch (of 2): Provide this new API to check if a CPU has been isolated either through isolcpus= or nohz_full= kernel parameter. It aims at avoiding kernel load deemed to be safely spared on CPUs running sensitive workload that can't bear any disturbance, such as pcp cache draining. Link: https://lkml.kernel.org/r/20230317134448.11082-1-mhocko@kernel.org Link: https://lkml.kernel.org/r/20230317134448.11082-2-mhocko@kernel.org Signed-off-by: Frederic Weisbecker Signed-off-by: Michal Hocko Suggested-by: Michal Hocko Cc: Johannes Weiner Cc: Marcelo Tosatti Cc: Muchun Song Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Shakeel Butt Cc: Thomas Gleixner Cc: Leonardo Bras Cc: Ingo Molnar Signed-off-by: Andrew Morton --- include/linux/sched/isolation.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 8c15abd67aed..fe1a46f30d24 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -46,6 +46,12 @@ static inline bool housekeeping_enabled(enum hk_type type) static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } + +static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) +{ + return true; +} + static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ @@ -58,4 +64,10 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) return true; } +static inline bool cpu_is_isolated(int cpu) +{ + return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || + !housekeeping_test_cpu(cpu, HK_TYPE_TICK); +} + #endif /* _LINUX_SCHED_ISOLATION_H */ -- GitLab From 6a792697a53af5b3028aa2918b40677effbc349f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 17 Mar 2023 14:44:48 +0100 Subject: [PATCH 3212/5631] memcg: do not drain charge pcp caches on remote isolated cpus Leonardo Bras has noticed that pcp charge cache draining might be disruptive on workloads relying on 'isolated cpus', a feature commonly used on workloads that are sensitive to interruption and context switching such as vRAN and Industrial Control Systems. There are essentially two ways how to approach the issue. We can either allow the pcp cache to be drained on a different rather than a local cpu or avoid remote flushing on isolated cpus. The current pcp charge cache is really optimized for high performance and it always relies to stick with its cpu. That means it only requires local_lock (preempt_disable on !RT) and draining is handed over to pcp WQ to drain locally again. The former solution (remote draining) would require to add an additional locking to prevent local charges from racing with the draining. This adds an atomic operation to otherwise simple arithmetic fast path in the try_charge path. Another concern is that the remote draining can cause a lock contention for the isolated workloads and therefore interfere with it indirectly via user space interfaces. Another option is to avoid draining scheduling on isolated cpus altogether. That means that those remote cpus would keep their charges even after drain_all_stock returns. This is certainly not optimal either but it shouldn't really cause any major problems. In the worst case (many isolated cpus with charges - each of them with MEMCG_CHARGE_BATCH i.e 64 page) the memory consumption of a memcg would be artificially higher than can be immediately used from other cpus. Theoretically a memcg OOM killer could be triggered pre-maturely. Currently it is not really clear whether this is a practical problem though. Tight memcg limit would be really counter productive to cpu isolated workloads pretty much by definition because any memory reclaimed induced by memcg limit could break user space timing expectations as those usually expect execution in the userspace most of the time. Also charges could be left behind on memcg removal. Any future charge on those isolated cpus will drain that pcp cache so this won't be a permanent leak. Considering cons and pros of both approaches this patch is implementing the second option and simply do not schedule remote draining if the target cpu is isolated. This solution is much more simpler. It doesn't add any new locking and it is more more predictable from the user space POV. Should the pre-mature memcg OOM become a real life problem, we can revisit this decision. [akpm@linux-foundation.org: memcontrol.c needs sched/isolation.h] Link: https://lore.kernel.org/oe-kbuild-all/202303180617.7E3aIlHf-lkp@intel.com/ Link: https://lkml.kernel.org/r/20230317134448.11082-3-mhocko@kernel.org Signed-off-by: Michal Hocko Suggested-by: Roman Gushchin Acked-by: Roman Gushchin Reported-by: Leonardo Bras Acked-by: Shakeel Butt Cc: Marcelo Tosatti Cc: Muchun Song Cc: Johannes Weiner Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Signed-off-by: Andrew Morton --- mm/memcontrol.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0524add35cae..681e7528a714 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "internal.h" #include #include @@ -2366,7 +2367,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) !test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); - else + else if (!cpu_is_isolated(cpu)) schedule_work_on(cpu, &stock->work); } } -- GitLab From 8c907785b8cc6dff2b9dda52e499715b0c64f377 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:20 +0300 Subject: [PATCH 3213/5631] arm: reword ARCH_FORCE_MAX_ORDER prompt and help text Patch series "arch,mm: cleanup Kconfig entries for ARCH_FORCE_MAX_ORDER", v3. Several architectures have ARCH_FORCE_MAX_ORDER in their Kconfig and they all have wrong and misleading prompt and help text for this option. Besides, some define insane limits for possible values of ARCH_FORCE_MAX_ORDER, some carefully define ranges only for a subset of possible configurations, some make this option configurable by users for no good reason. This set updates the prompt and help text everywhere and does its best to update actual definitions of ranges where applicable. kbuild generated a bunch of false positives because it assigns -1 to ARCH_FORCE_MAX_ORDER, hopefully this will be fixed soon. This patch (of 14): The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230325060828.2662773-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20230324052233.2654090-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20230324052233.2654090-2-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/arm/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 929e646e84b9..0b15384c62e6 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1354,17 +1354,19 @@ config ARM_MODULE_PLTS configurations. If unsure, say y. config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" default "11" if SOC_AM33XX default "8" if SA1111 default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. + + Don't change if unsure. config ALIGNMENT_TRAP def_bool CPU_CP15_MMU -- GitLab From 34affcd7577a232803f729d1870ba475f294e4ea Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:21 +0300 Subject: [PATCH 3214/5631] arm64: drop ranges in definition of ARCH_FORCE_MAX_ORDER It is not a good idea to change fundamental parameters of core memory management. Having predefined ranges suggests that the values within those ranges are sensible, but one has to *really* understand implications of changing MAX_ORDER before actually amending it and ranges don't help here. Drop ranges in definition of ARCH_FORCE_MAX_ORDER and make its prompt visible only if EXPERT=y Link: https://lkml.kernel.org/r/20230324052233.2654090-3-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: Zi Yan Reviewed-by: Kefeng Wang Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Kirill A. Shutemov Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e60baf7859d1..7324032af859 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1487,11 +1487,9 @@ config XEN # 16K | 27 | 14 | 13 | 11 | # 64K | 29 | 16 | 13 | 13 | config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES + int "Maximum zone order" if EXPERT && (ARM64_4K_PAGES || ARM64_16K_PAGES) default "13" if ARM64_64K_PAGES - range 11 13 if ARM64_16K_PAGES default "11" if ARM64_16K_PAGES - range 10 15 if ARM64_4K_PAGES default "10" help The kernel memory allocator divides physically contiguous memory -- GitLab From 4632cb22ac26e9e6e4ad651fb53f25f0b78c2889 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:22 +0300 Subject: [PATCH 3215/5631] arm64: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. [rppt@kernel.org: change ARCH_FORCE_MAX_ORDER dependencies] Link: https://lkml.kernel.org/r/20230325060828.2662773-4-rppt@kernel.org Link: https://lkml.kernel.org/r/20230324052233.2654090-4-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Reviewed-by: Kefeng Wang Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/arm64/Kconfig | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7324032af859..cc11cdcf5a00 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1487,24 +1487,24 @@ config XEN # 16K | 27 | 14 | 13 | 11 | # 64K | 29 | 16 | 13 | 13 | config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" if EXPERT && (ARM64_4K_PAGES || ARM64_16K_PAGES) + int "Order of maximal physically contiguous allocations" if EXPERT && (ARM64_4K_PAGES || ARM64_16K_PAGES) default "13" if ARM64_64K_PAGES default "11" if ARM64_16K_PAGES default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. - We make sure that we can allocate up to a HugePage size for each configuration. - Hence we have : - MAX_ORDER = PMD_SHIFT - PAGE_SHIFT => PAGE_SHIFT - 3 + The maximal size of allocation cannot exceed the size of the + section, so the value of MAX_ORDER should satisfy - However for 4K, we choose a higher default value, 10 as opposed to 9, giving us - 4M allocations matching the default size used by generic code. + MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS + + Don't change if unsure. config UNMAP_KERNEL_AT_EL0 bool "Unmap kernel when running in userspace (aka \"KAISER\")" if EXPERT -- GitLab From 4e7c8655ab577e24ac2c6a26292be9d837679f69 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:23 +0300 Subject: [PATCH 3216/5631] csky: drop ARCH_FORCE_MAX_ORDER The default value of ARCH_FORCE_MAX_ORDER matches the generic default defined in the MM code, the architecture does not support huge pages, so there is no need to keep ARCH_FORCE_MAX_ORDER option available. Drop it. Link: https://lkml.kernel.org/r/20230324052233.2654090-5-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/csky/Kconfig | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index c694fac43bed..00379a843c37 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -332,10 +332,6 @@ config HIGHMEM select KMAP_LOCAL default y -config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" - default "10" - config DRAM_BASE hex "DRAM start addr (the same with memory-section in dts)" default 0x0 -- GitLab From 9d0f7a5780ef83e6e31581f90e73df9062d34470 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:24 +0300 Subject: [PATCH 3217/5631] ia64: don't allow users to override ARCH_FORCE_MAX_ORDER It is enough to keep default values for base and huge pages without letting users to override ARCH_FORCE_MAX_ORDER. Drop the prompt to make the option unvisible in *config. Link: https://lkml.kernel.org/r/20230324052233.2654090-6-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/ia64/Kconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 0d2f41fa56ee..b61437cae162 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -202,8 +202,7 @@ config IA64_CYCLONE If you're unsure, answer N. config ARCH_FORCE_MAX_ORDER - int "MAX_ORDER (10 - 16)" if !HUGETLB_PAGE - range 10 16 if !HUGETLB_PAGE + int default "16" if HUGETLB_PAGE default "10" -- GitLab From 7a5b272e0b17bcb431b5bc1d46d369871c391837 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:25 +0300 Subject: [PATCH 3218/5631] m68k: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230324052233.2654090-7-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Acked-by: Geert Uytterhoeven Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/m68k/Kconfig.cpu | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index c9df6572133f..e530bc8f240f 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -398,21 +398,23 @@ config SINGLE_MEMORY_CHUNK Say N if not sure. config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" if ADVANCED + int "Order of maximal physically contiguous allocations" if ADVANCED depends on !SINGLE_MEMORY_CHUNK default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. For systems that have holes in their physical address space this value also defines the minimal size of the hole that allows freeing unused memory map. + Don't change if unsure. + config 060_WRITETHROUGH bool "Use write-through caching for 68060 supervisor accesses" depends on ADVANCED && M68060 -- GitLab From 5646e83d6ae6f41d999b365d7d555fcdbcabc82b Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:26 +0300 Subject: [PATCH 3219/5631] nios2: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230324052233.2654090-8-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/nios2/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 89708b95978c..fcaa6bbda3fc 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -45,16 +45,18 @@ menu "Kernel features" source "kernel/Kconfig.hz" config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" range 8 19 default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. + + Don't change if unsure. endmenu -- GitLab From 482f7b7652b0aa2d39bd721f3bf3b664b4d75bb5 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:27 +0300 Subject: [PATCH 3220/5631] nios2: drop ranges for definition of ARCH_FORCE_MAX_ORDER nios2 defines range for ARCH_FORCE_MAX_ORDER allowing MAX_ORDER up to 19, which implies maximal contiguous allocation size of 2^19 pages or 2GiB. Drop bogus definition of ranges for ARCH_FORCE_MAX_ORDER and leave it a simple integer with sensible default. Users that *really* need to change the value of ARCH_FORCE_MAX_ORDER will be able to do so but they won't be mislead by the bogus ranges. Link: https://lkml.kernel.org/r/20230324052233.2654090-9-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/nios2/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index fcaa6bbda3fc..e5936417d3cd 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -46,7 +46,6 @@ source "kernel/Kconfig.hz" config ARCH_FORCE_MAX_ORDER int "Order of maximal physically contiguous allocations" - range 8 19 default "10" help The kernel page allocator limits the size of maximal physically -- GitLab From 6fc54303aa2597e30558cdbd310d45070c9a0325 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:28 +0300 Subject: [PATCH 3221/5631] powerpc: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230324052233.2654090-10-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/powerpc/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 24d56536b269..c0095bf795ca 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -896,7 +896,7 @@ config DATA_SHIFT 8M pages will be pinned. config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" range 7 8 if PPC64 && PPC_64K_PAGES default "8" if PPC64 && PPC_64K_PAGES range 12 12 if PPC64 && !PPC_64K_PAGES @@ -910,17 +910,19 @@ config ARCH_FORCE_MAX_ORDER range 10 63 default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. The page size is not necessarily 4KB. For example, on 64-bit systems, 64KB pages can be enabled via CONFIG_PPC_64K_PAGES. Keep this in mind when choosing a value for this option. + Don't change if unsure. + config PPC_SUBPAGE_PROT bool "Support setting protections for 4k subpages (subpage_prot syscall)" default n -- GitLab From 1e8fed873e7499bab8da05b2006f6a3960796c68 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:29 +0300 Subject: [PATCH 3222/5631] powerpc: drop ranges for definition of ARCH_FORCE_MAX_ORDER PowerPC defines ranges for ARCH_FORCE_MAX_ORDER some of which are insanely allowing MAX_ORDER up to 63, which implies maximal contiguous allocation size of 2^63 pages. Drop bogus definitions of ranges for ARCH_FORCE_MAX_ORDER and leave it a simple integer with sensible defaults. Users that *really* need to change the value of ARCH_FORCE_MAX_ORDER will be able to do so but they won't be mislead by the bogus ranges. Link: https://lkml.kernel.org/r/20230324052233.2654090-11-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/powerpc/Kconfig | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c0095bf795ca..419be4a71004 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -897,17 +897,11 @@ config DATA_SHIFT config ARCH_FORCE_MAX_ORDER int "Order of maximal physically contiguous allocations" - range 7 8 if PPC64 && PPC_64K_PAGES default "8" if PPC64 && PPC_64K_PAGES - range 12 12 if PPC64 && !PPC_64K_PAGES default "12" if PPC64 && !PPC_64K_PAGES - range 8 63 if PPC32 && PPC_16K_PAGES default "8" if PPC32 && PPC_16K_PAGES - range 6 63 if PPC32 && PPC_64K_PAGES default "6" if PPC32 && PPC_64K_PAGES - range 4 63 if PPC32 && PPC_256K_PAGES default "4" if PPC32 && PPC_256K_PAGES - range 10 63 default "10" help The kernel page allocator limits the size of maximal physically -- GitLab From b2a37fb2b54fd46bfa799268717f558d9e168376 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:30 +0300 Subject: [PATCH 3223/5631] sh: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. [rppt@kernel.org: tweak ARCH_FORCE_MAX_ORDER's `range'] Link: https://lkml.kernel.org/r/20230325060828.2662773-12-rppt@kernel.org Link: https://lkml.kernel.org/r/20230324052233.2654090-12-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/sh/mm/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 40271090bd7d..238b2772751e 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -19,7 +19,7 @@ config PAGE_OFFSET default "0x00000000" config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" range 8 63 if PAGE_SIZE_16KB default "8" if PAGE_SIZE_16KB range 6 63 if PAGE_SIZE_64KB @@ -28,16 +28,18 @@ config ARCH_FORCE_MAX_ORDER default "13" if !MMU default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. The page size is not necessarily 4KB. Keep this in mind when choosing a value for this option. + Don't change if unsure. + config MEMORY_START hex "Physical memory start address" default "0x08000000" -- GitLab From 0495408240c97429cb2d21c6aca717baacb9199f Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:31 +0300 Subject: [PATCH 3224/5631] sh: drop ranges for definition of ARCH_FORCE_MAX_ORDER sh defines insane ranges for ARCH_FORCE_MAX_ORDER allowing MAX_ORDER up to 63, which implies maximal contiguous allocation size of 2^63 pages. Drop bogus definitions of ranges for ARCH_FORCE_MAX_ORDER and leave it a simple integer with sensible defaults. Users that *really* need to change the value of ARCH_FORCE_MAX_ORDER will be able to do so but they won't be mislead by the bogus ranges. [rppt@kernel.org: untweak ARCH_FORCE_MAX_ORDER's `range'] Link: https://lkml.kernel.org/r/20230325060828.2662773-13-rppt@kernel.org Link: https://lkml.kernel.org/r/20230324052233.2654090-13-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/sh/mm/Kconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 238b2772751e..511c17aede4a 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -20,11 +20,8 @@ config PAGE_OFFSET config ARCH_FORCE_MAX_ORDER int "Order of maximal physically contiguous allocations" - range 8 63 if PAGE_SIZE_16KB default "8" if PAGE_SIZE_16KB - range 6 63 if PAGE_SIZE_64KB default "6" if PAGE_SIZE_64KB - range 10 63 default "13" if !MMU default "10" help -- GitLab From 8def4c058fe1a560b2e68e98a824b44e7e012024 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:32 +0300 Subject: [PATCH 3225/5631] sparc: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230324052233.2654090-14-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Max Filippov Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/sparc/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index e3242bf5a8df..959e43a1aaca 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -270,15 +270,17 @@ config ARCH_SPARSEMEM_DEFAULT def_bool y if SPARC64 config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" default "12" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. + + Don't change if unsure. if SPARC64 || COMPILE_TEST source "kernel/power/Kconfig" -- GitLab From 4519a254e0170c5d9d0b1054f045ec1f436c6336 Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Fri, 24 Mar 2023 08:22:33 +0300 Subject: [PATCH 3226/5631] xtensa: reword ARCH_FORCE_MAX_ORDER prompt and help text The prompt and help text of ARCH_FORCE_MAX_ORDER are not even close to describe this configuration option. Update both to actually describe what this option does. Link: https://lkml.kernel.org/r/20230324052233.2654090-15-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Reviewed-by: Max Filippov Acked-by: Kirill A. Shutemov Reviewed-by: Zi Yan Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Christophe Leroy Cc: David Miller Cc: Dinh Nguyen Cc: Geert Uytterhoeven Cc: Guo Ren Cc: John Paul Adrian Glaubitz Cc: Michael Ellerman Cc: Rich Felker Cc: "Russell King (Oracle)" Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton --- arch/xtensa/Kconfig | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 3eee334ba873..3c6e5471f025 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -772,15 +772,17 @@ config HIGHMEM If unsure, say Y. config ARCH_FORCE_MAX_ORDER - int "Maximum zone order" + int "Order of maximal physically contiguous allocations" default "10" help - The kernel memory allocator divides physically contiguous memory - blocks into "zones", where each zone is a power of two number of - pages. This option selects the largest power of two that the kernel - keeps in the memory allocator. If you need to allocate very large - blocks of physically contiguous memory, then you may need to - increase this value. + The kernel page allocator limits the size of maximal physically + contiguous allocations. The limit is called MAX_ORDER and it + defines the maximal power of two of number of pages that can be + allocated as a single contiguous block. This option allows + overriding the default setting when ability to allocate very + large blocks of physically contiguous memory is required. + + Don't change if unsure. endmenu -- GitLab From 957ebbdf434013ee01f29f6c9174eced995ebbe7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 27 Mar 2023 16:10:50 +0100 Subject: [PATCH 3227/5631] hugetlb: remove PageHeadHuge() Sidhartha Kumar removed the last caller of PageHeadHuge(), so we can now remove it and make folio_test_hugetlb() the real implementation. Add kernel-doc for folio_test_hugetlb(). Link: https://lkml.kernel.org/r/20230327151050.1787744-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 7 +------ mm/hugetlb.c | 18 +++++++++++------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index dcda20c47b8f..efc42fae3d96 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -815,14 +815,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); -int PageHeadHuge(struct page *page); -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return PageHeadHuge(&folio->page); -} +bool folio_test_hugetlb(struct folio *folio); #else TESTPAGEFLAG_FALSE(Huge, hugetlb) -TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a58b3739ed4b..7e4a80769c9e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2050,19 +2050,23 @@ int PageHuge(struct page *page) } EXPORT_SYMBOL_GPL(PageHuge); -/* - * PageHeadHuge() only returns true for hugetlbfs head page, but not for - * normal or transparent huge pages. +/** + * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs + * @folio: The folio to test. + * + * Context: Any context. Caller should have a reference on the folio to + * prevent it from being turned into a tail page. + * Return: True for hugetlbfs folios, false for anon folios or folios + * belonging to other filesystems. */ -int PageHeadHuge(struct page *page_head) +bool folio_test_hugetlb(struct folio *folio) { - struct folio *folio = (struct folio *)page_head; if (!folio_test_large(folio)) - return 0; + return false; return folio->_folio_dtor == HUGETLB_PAGE_DTOR; } -EXPORT_SYMBOL_GPL(PageHeadHuge); +EXPORT_SYMBOL_GPL(folio_test_hugetlb); /* * Find and lock address space (mapping) in write mode. -- GitLab From e961cc5652c68610d8acb65f20267b8c55444e5b Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Mon, 27 Mar 2023 11:41:49 +0800 Subject: [PATCH 3228/5631] kmsan: fix a stale comment in kmsan_save_stack_with_flags() After commit 446ec83805dd ("mm/page_alloc: use might_alloc()") and commit 84172f4bb752 ("mm/page_alloc: combine __alloc_pages and __alloc_pages_nodemask"), the comment is no longer accurate. Flag '__GFP_DIRECT_RECLAIM' is clear enough on its own, so remove the comment rather than update it. Link: https://lkml.kernel.org/r/20230327034149.942-1-thunder.leizhen@huawei.com Signed-off-by: Zhen Lei Reviewed-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: Marco Elver Signed-off-by: Andrew Morton --- mm/kmsan/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kmsan/core.c b/mm/kmsan/core.c index f710257d6867..7d1e4aa30bae 100644 --- a/mm/kmsan/core.c +++ b/mm/kmsan/core.c @@ -73,7 +73,7 @@ depot_stack_handle_t kmsan_save_stack_with_flags(gfp_t flags, nr_entries = stack_trace_save(entries, KMSAN_STACK_DEPTH, 0); - /* Don't sleep (see might_sleep_if() in __alloc_pages_nodemask()). */ + /* Don't sleep. */ flags &= ~__GFP_DIRECT_RECLAIM; handle = __stack_depot_save(entries, nr_entries, flags, true); -- GitLab From 62f31bd4dcedffe3c919deb76ed65bf62c3cf80b Mon Sep 17 00:00:00 2001 From: "Mike Rapoport (IBM)" Date: Sun, 26 Mar 2023 19:02:15 +0300 Subject: [PATCH 3229/5631] mm: move free_area_empty() to mm/internal.h The free_area_empty() helper is only used inside mm/ so move it there to reduce noise in include/linux/mmzone.h Link: https://lkml.kernel.org/r/20230326160215.2674531-1-rppt@kernel.org Signed-off-by: Mike Rapoport (IBM) Suggested-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 5 ----- mm/internal.h | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2d22e47dc1eb..337956748976 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -110,11 +110,6 @@ struct free_area { unsigned long nr_free; }; -static inline bool free_area_empty(struct free_area *area, int migratetype) -{ - return list_empty(&area->free_list[migratetype]); -} - struct pglist_data; #ifdef CONFIG_NUMA diff --git a/mm/internal.h b/mm/internal.h index 73b167b59cc5..92ddd3a05b74 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -517,6 +517,11 @@ void init_cma_reserved_pageblock(struct page *page); int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); +static inline bool free_area_empty(struct free_area *area, int migratetype) +{ + return list_empty(&area->free_list[migratetype]); +} + /* * These three helpers classifies VMAs for virtual memory accounting. */ -- GitLab From 062eacf57ad91b5c272f89dc964fd6dd9715ea7d Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Thu, 30 Mar 2023 21:06:38 +0200 Subject: [PATCH 3230/5631] mm: vmalloc: remove a global vmap_blocks xarray A global vmap_blocks-xarray array can be contented under heavy usage of the vm_map_ram()/vm_unmap_ram() APIs. The lock_stat shows that a "vmap_blocks.xa_lock" lock is a second in a top-list when it comes to contentions: ---------------------------------------- class name con-bounces contentions ... ---------------------------------------- vmap_area_lock: 2554079 2554276 ... -------------- vmap_area_lock 1297948 [<00000000dd41cbaa>] alloc_vmap_area+0x1c7/0x910 vmap_area_lock 1256330 [<000000009d927bf3>] free_vmap_block+0x4a/0xe0 vmap_area_lock 1 [<00000000c95c05a7>] find_vm_area+0x16/0x70 -------------- vmap_area_lock 1738590 [<00000000dd41cbaa>] alloc_vmap_area+0x1c7/0x910 vmap_area_lock 815688 [<000000009d927bf3>] free_vmap_block+0x4a/0xe0 vmap_area_lock 1 [<00000000c1d619d7>] __get_vm_area_node+0xd2/0x170 vmap_blocks.xa_lock: 862689 862698 ... ------------------- vmap_blocks.xa_lock 378418 [<00000000625a5626>] vm_map_ram+0x359/0x4a0 vmap_blocks.xa_lock 484280 [<00000000caa2ef03>] xa_erase+0xe/0x30 ------------------- vmap_blocks.xa_lock 576226 [<00000000caa2ef03>] xa_erase+0xe/0x30 vmap_blocks.xa_lock 286472 [<00000000625a5626>] vm_map_ram+0x359/0x4a0 ... that is a result of running vm_map_ram()/vm_unmap_ram() in a loop. The test creates 64(on 64 CPUs system) threads and each one maps/unmaps 1 page. After this change the "xa_lock" can be considered as a noise in the same test condition: ... &xa->xa_lock#1: 10333 10394 ... -------------- &xa->xa_lock#1 5349 [<00000000bbbc9751>] xa_erase+0xe/0x30 &xa->xa_lock#1 5045 [<0000000018def45d>] vm_map_ram+0x3a4/0x4f0 -------------- &xa->xa_lock#1 7326 [<0000000018def45d>] vm_map_ram+0x3a4/0x4f0 &xa->xa_lock#1 3068 [<00000000bbbc9751>] xa_erase+0xe/0x30 ... Running the test_vmalloc.sh run_test_mask=1024 nr_threads=64 nr_pages=5 shows around ~8 percent of throughput improvement of vm_map_ram() and vm_unmap_ram() APIs. This patch does not fix vmap_area_lock/free_vmap_area_lock and purge_vmap_area_lock bottle-necks, it is rather a separate rework. Link: https://lkml.kernel.org/r/20230330190639.431589-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Reviewed-by: Lorenzo Stoakes Reviewed-by: Baoquan He Cc: Christoph Hellwig Cc: Dave Chinner Cc: Matthew Wilcox (Oracle) Cc: Oleksiy Avramchenko Signed-off-by: Andrew Morton --- mm/vmalloc.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 63 insertions(+), 8 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 63a22557dc55..add33286a43b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1915,6 +1915,13 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) struct vmap_block_queue { spinlock_t lock; struct list_head free; + + /* + * An xarray requires an extra memory dynamically to + * be allocated. If it is an issue, we can use rb-tree + * instead. + */ + struct xarray vmap_blocks; }; struct vmap_block { @@ -1932,11 +1939,48 @@ struct vmap_block { static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* - * XArray of vmap blocks, indexed by address, to quickly find a vmap block - * in the free path. Could get rid of this if we change the API to return a - * "cookie" from alloc, to be passed to free. But no big deal yet. + * In order to fast access to any "vmap_block" associated with a + * specific address, we use a hash. + * + * A per-cpu vmap_block_queue is used in both ways, to serialize + * an access to free block chains among CPUs(alloc path) and it + * also acts as a vmap_block hash(alloc/free paths). It means we + * overload it, since we already have the per-cpu array which is + * used as a hash table. When used as a hash a 'cpu' passed to + * per_cpu() is not actually a CPU but rather a hash index. + * + * A hash function is addr_to_vb_xarray() which hashes any address + * to a specific index(in a hash) it belongs to. This then uses a + * per_cpu() macro to access an array with generated index. + * + * An example: + * + * CPU_1 CPU_2 CPU_0 + * | | | + * V V V + * 0 10 20 30 40 50 60 + * |------|------|------|------|------|------|... + * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 + * + * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus + * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; + * + * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus + * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; + * + * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus + * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. + * + * This technique almost always avoids lock contention on insert/remove, + * however xarray spinlocks protect against any contention that remains. */ -static DEFINE_XARRAY(vmap_blocks); +static struct xarray * +addr_to_vb_xarray(unsigned long addr) +{ + int index = (addr / VMAP_BLOCK_SIZE) % num_possible_cpus(); + + return &per_cpu(vmap_block_queue, index).vmap_blocks; +} /* * We should probably have a fallback mechanism to allocate virtual memory @@ -1974,6 +2018,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; + struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; @@ -2007,8 +2052,9 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); + xa = addr_to_vb_xarray(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); - err = xa_insert(&vmap_blocks, vb_idx, vb, gfp_mask); + err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { kfree(vb); free_vmap_area(va); @@ -2026,8 +2072,10 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) static void free_vmap_block(struct vmap_block *vb) { struct vmap_block *tmp; + struct xarray *xa; - tmp = xa_erase(&vmap_blocks, addr_to_vb_idx(vb->va->va_start)); + xa = addr_to_vb_xarray(vb->va->va_start); + tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); spin_lock(&vmap_area_lock); @@ -2139,6 +2187,7 @@ static void vb_free(unsigned long addr, unsigned long size) unsigned long offset; unsigned int order; struct vmap_block *vb; + struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -2147,7 +2196,10 @@ static void vb_free(unsigned long addr, unsigned long size) order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; - vb = xa_load(&vmap_blocks, addr_to_vb_idx(addr)); + + xa = addr_to_vb_xarray(addr); + vb = xa_load(xa, addr_to_vb_idx(addr)); + spin_lock(&vb->lock); bitmap_clear(vb->used_map, offset, (1UL << order)); spin_unlock(&vb->lock); @@ -3525,6 +3577,7 @@ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, { char *start; struct vmap_block *vb; + struct xarray *xa; unsigned long offset; unsigned int rs, re; size_t remains, n; @@ -3543,7 +3596,8 @@ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ - vb = xa_load(&vmap_blocks, addr_to_vb_idx((unsigned long)addr)); + xa = addr_to_vb_xarray((unsigned long) addr); + vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; @@ -4337,6 +4391,7 @@ void __init vmalloc_init(void) p = &per_cpu(vfree_deferred, i); init_llist_head(&p->list); INIT_WORK(&p->wq, delayed_vfree_work); + xa_init(&vbq->vmap_blocks); } /* Import existing vmlist entries. */ -- GitLab From 869cb29a61a14bbc52e7bc8b18e8810874caf320 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Thu, 30 Mar 2023 21:06:39 +0200 Subject: [PATCH 3231/5631] lib/test_vmalloc.c: add vm_map_ram()/vm_unmap_ram() test case Add vm_map_ram()/vm_unmap_ram() test case to our stress test-suite. [akpm@linux-foundation.org: fix whitespace, per Lorenzo] Link: https://lkml.kernel.org/r/20230330190639.431589-2-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Reviewed-by: Lorenzo Stoakes Reviewed-by: Baoquan He Cc: Christoph Hellwig Cc: Dave Chinner Cc: Matthew Wilcox (Oracle) Cc: Oleksiy Avramchenko Signed-off-by: Andrew Morton --- lib/test_vmalloc.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c index de4ee0d50906..84c124f097b7 100644 --- a/lib/test_vmalloc.c +++ b/lib/test_vmalloc.c @@ -53,6 +53,7 @@ __param(int, run_test_mask, INT_MAX, "\t\tid: 128, name: pcpu_alloc_test\n" "\t\tid: 256, name: kvfree_rcu_1_arg_vmalloc_test\n" "\t\tid: 512, name: kvfree_rcu_2_arg_vmalloc_test\n" + "\t\tid: 1024, name: vm_map_ram_test\n" /* Add a new test case description here. */ ); @@ -358,6 +359,41 @@ kvfree_rcu_2_arg_vmalloc_test(void) return 0; } +static int +vm_map_ram_test(void) +{ + unsigned long nr_allocated; + unsigned int map_nr_pages; + unsigned char *v_ptr; + struct page **pages; + int i; + + map_nr_pages = nr_pages > 0 ? nr_pages:1; + pages = kmalloc(map_nr_pages * sizeof(struct page), GFP_KERNEL); + if (!pages) + return -1; + + nr_allocated = alloc_pages_bulk_array(GFP_KERNEL, map_nr_pages, pages); + if (nr_allocated != map_nr_pages) + goto cleanup; + + /* Run the test loop. */ + for (i = 0; i < test_loop_count; i++) { + v_ptr = vm_map_ram(pages, map_nr_pages, NUMA_NO_NODE); + *v_ptr = 'a'; + vm_unmap_ram(v_ptr, map_nr_pages); + } + +cleanup: + for (i = 0; i < nr_allocated; i++) + __free_page(pages[i]); + + kfree(pages); + + /* 0 indicates success. */ + return nr_allocated != map_nr_pages; +} + struct test_case_desc { const char *test_name; int (*test_func)(void); @@ -374,6 +410,7 @@ static struct test_case_desc test_case_array[] = { { "pcpu_alloc_test", pcpu_alloc_test }, { "kvfree_rcu_1_arg_vmalloc_test", kvfree_rcu_1_arg_vmalloc_test }, { "kvfree_rcu_2_arg_vmalloc_test", kvfree_rcu_2_arg_vmalloc_test }, + { "vm_map_ram_test", vm_map_ram_test }, /* Add a new test case here. */ }; -- GitLab From 27d9a0fdb53f05c93ed9c674b870c8add451697e Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Thu, 30 Mar 2023 14:09:04 +0800 Subject: [PATCH 3232/5631] kmemleak-test: fix kmemleak_test.c build logic kmemleak-test.c was moved to the samples directory in 1abbef4f51724 ("mm,kmemleak-test.c: move kmemleak-test.c to samples dir"). If CONFIG_DEBUG_KMEMLEAK_TEST=m and CONFIG_SAMPLES is unset, kmemleak-test.c will be unnecessarily compiled. So move the entry for CONFIG_DEBUG_KMEMLEAK_TEST from mm/Kconfig and add a new CONFIG_SAMPLE_KMEMLEAK in samples/ to control whether kmemleak-test.c is built or not. Link: https://lkml.kernel.org/r/20230330060904.292975-1-gehao@kylinos.cn Fixes: 1abbef4f51724 ("mm,kmemleak-test.c: move kmemleak-test.c to samples dir") Signed-off-by: Hao Ge Cc: Catalin Marinas Cc: Alex Gaynor Cc: Alex Williamson Cc: Arnd Bergmann Cc: Finn Behrens Cc: Greg Kroah-Hartman Cc: Jason Gunthorpe Cc: Mark Rutland Cc: Miguel Ojeda Cc: Tony Krowiak Cc: Ye Xingchen Signed-off-by: Andrew Morton --- mm/Kconfig.debug | 8 -------- samples/Kconfig | 7 +++++++ samples/Makefile | 2 +- samples/kmemleak/Makefile | 2 +- 4 files changed, 9 insertions(+), 10 deletions(-) diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 4965a7333a3f..065ed0d687cb 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -249,14 +249,6 @@ config DEBUG_KMEMLEAK_MEM_POOL_SIZE fully initialised, this memory pool acts as an emergency one if slab allocations fail. -config DEBUG_KMEMLEAK_TEST - tristate "Simple test for the kernel memory leak detector" - depends on DEBUG_KMEMLEAK && m - help - This option enables a module that explicitly leaks memory. - - If unsure, say N. - config DEBUG_KMEMLEAK_DEFAULT_OFF bool "Default kmemleak to off" depends on DEBUG_KMEMLEAK diff --git a/samples/Kconfig b/samples/Kconfig index 30ef8bd48ba3..69076fbf3298 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -273,6 +273,13 @@ config SAMPLE_CORESIGHT_SYSCFG This demonstrates how a user may create their own CoreSight configurations and easily load them into the system at runtime. +config SAMPLE_KMEMLEAK + tristate "Simple test for the kernel memory leak detector" + depends on DEBUG_KMEMLEAK && m + help + Build a sample program which have explicitly leaks memory to test + kmemleak + source "samples/rust/Kconfig" endif # SAMPLES diff --git a/samples/Makefile b/samples/Makefile index 7cb632ef88ee..7727f1a0d6d1 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -33,7 +33,7 @@ subdir-$(CONFIG_SAMPLE_VFS) += vfs obj-$(CONFIG_SAMPLE_INTEL_MEI) += mei/ subdir-$(CONFIG_SAMPLE_WATCHDOG) += watchdog subdir-$(CONFIG_SAMPLE_WATCH_QUEUE) += watch_queue -obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak/ +obj-$(CONFIG_SAMPLE_KMEMLEAK) += kmemleak/ obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG) += coresight/ obj-$(CONFIG_SAMPLE_FPROBE) += fprobe/ obj-$(CONFIG_SAMPLES_RUST) += rust/ diff --git a/samples/kmemleak/Makefile b/samples/kmemleak/Makefile index 16b6132c540c..8a999ab43b6d 100644 --- a/samples/kmemleak/Makefile +++ b/samples/kmemleak/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o +obj-$(CONFIG_SAMPLE_KMEMLEAK) += kmemleak-test.o -- GitLab From fa1c77c13ca59101c4fbf0ff8bbadd3aaba375f8 Mon Sep 17 00:00:00 2001 From: "Uladzislau Rezki (Sony)" Date: Fri, 31 Mar 2023 09:37:27 +0200 Subject: [PATCH 3233/5631] mm: vmalloc: rename addr_to_vb_xarray() function Short the name of the addr_to_vb_xarray() function to the addr_to_vb_xa(). This aligns with other internal function abbreviations. Link: https://lkml.kernel.org/r/20230331073727.6968-1-urezki@gmail.com Signed-off-by: Uladzislau Rezki (Sony) Suggested-by: Baoquan He Reviewed-by: Baoquan He Reviewed-by: Lorenzo Stoakes Cc: Christoph Hellwig Cc: Dave Chinner Cc: Matthew Wilcox (Oracle) Cc: Oleksiy Avramchenko Signed-off-by: Andrew Morton --- mm/vmalloc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index add33286a43b..9683573f1225 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1949,7 +1949,7 @@ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * - * A hash function is addr_to_vb_xarray() which hashes any address + * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * @@ -1975,7 +1975,7 @@ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); * however xarray spinlocks protect against any contention that remains. */ static struct xarray * -addr_to_vb_xarray(unsigned long addr) +addr_to_vb_xa(unsigned long addr) { int index = (addr / VMAP_BLOCK_SIZE) % num_possible_cpus(); @@ -2052,7 +2052,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); - xa = addr_to_vb_xarray(va->va_start); + xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) { @@ -2074,7 +2074,7 @@ static void free_vmap_block(struct vmap_block *vb) struct vmap_block *tmp; struct xarray *xa; - xa = addr_to_vb_xarray(vb->va->va_start); + xa = addr_to_vb_xa(vb->va->va_start); tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); @@ -2197,7 +2197,7 @@ static void vb_free(unsigned long addr, unsigned long size) order = get_order(size); offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; - xa = addr_to_vb_xarray(addr); + xa = addr_to_vb_xa(addr); vb = xa_load(xa, addr_to_vb_idx(addr)); spin_lock(&vb->lock); @@ -3596,7 +3596,7 @@ static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions. */ - xa = addr_to_vb_xarray((unsigned long) addr); + xa = addr_to_vb_xa((unsigned long) addr); vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); if (!vb) goto finished_zero; -- GitLab From b791912252716168697a258bd8bbf579296ba438 Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 3 Apr 2023 20:13:16 +0800 Subject: [PATCH 3234/5631] mm/zswap: remove zswap_entry_cache_{create,destroy} helper function Patch series "Delay the initialization of zswap", v9. In the initialization of zswap, about 18MB memory will be allocated for zswap_pool. Since some users may not use zswap, the zswap_pool is wasted. Save memory by delaying the initialization of zswap until enabled. This patch (of 3): Remove zswap_entry_cache_create and zswap_entry_cache_destroy and use kmem_cache_* function directly. Link: https://lkml.kernel.org/r/20230411093632.822290-1-liushixin2@huawei.com Link: https://lkml.kernel.org/r/20230403121318.1876082-1-liushixin2@huawei.com Link: https://lkml.kernel.org/r/20230403121318.1876082-2-liushixin2@huawei.com Signed-off-by: Liu Shixin Reviewed-by: Christoph Hellwig Cc: Dan Streetman Cc: Nathan Chancellor Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton --- mm/zswap.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 2f0ebd8bc620..6d2b879f091e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -272,17 +272,6 @@ static void zswap_update_total_size(void) **********************************/ static struct kmem_cache *zswap_entry_cache; -static int __init zswap_entry_cache_create(void) -{ - zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); - return zswap_entry_cache == NULL; -} - -static void __init zswap_entry_cache_destroy(void) -{ - kmem_cache_destroy(zswap_entry_cache); -} - static struct zswap_entry *zswap_entry_cache_alloc(gfp_t gfp) { struct zswap_entry *entry; @@ -1489,7 +1478,8 @@ static int __init init_zswap(void) zswap_init_started = true; - if (zswap_entry_cache_create()) { + zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); + if (!zswap_entry_cache) { pr_err("entry cache creation failed\n"); goto cache_fail; } @@ -1538,7 +1528,7 @@ static int __init init_zswap(void) hp_fail: cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE); dstmem_fail: - zswap_entry_cache_destroy(); + kmem_cache_destroy(zswap_entry_cache); cache_fail: /* if built-in, we aren't unloaded on failure; don't allow use */ zswap_init_failed = true; -- GitLab From 9021ccec60f2d86b84080a7e262c91ea99495eaa Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 3 Apr 2023 20:13:17 +0800 Subject: [PATCH 3235/5631] mm/zswap: replace zswap_init_{started/failed} with zswap_init_state The zswap_init_started variable name has a bit confusing. Actually, there are three state: uninitialized, initial failed and initial succeed. Add a new variable zswap_init_state to replace zswap_init_{started/failed}. Link: https://lkml.kernel.org/r/20230403121318.1876082-3-liushixin2@huawei.com Signed-off-by: Liu Shixin Reviewed-by: Christoph Hellwig Cc: Dan Streetman Cc: Nathan Chancellor Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton --- mm/zswap.c | 55 +++++++++++++++++++++++++++++------------------------- 1 file changed, 30 insertions(+), 25 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 6d2b879f091e..9169c2baee87 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -214,11 +214,13 @@ static DEFINE_SPINLOCK(zswap_pools_lock); /* pool counter to provide unique names to zpool */ static atomic_t zswap_pools_count = ATOMIC_INIT(0); -/* used by param callback function */ -static bool zswap_init_started; +enum zswap_init_type { + ZSWAP_UNINIT, + ZSWAP_INIT_SUCCEED, + ZSWAP_INIT_FAILED +}; -/* fatal error during init */ -static bool zswap_init_failed; +static enum zswap_init_type zswap_init_state; /* init completed, but couldn't create the initial pool */ static bool zswap_has_pool; @@ -761,21 +763,22 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, char *s = strstrip((char *)val); int ret; - if (zswap_init_failed) { + switch (zswap_init_state) { + case ZSWAP_UNINIT: + /* if this is load-time (pre-init) param setting, + * don't create a pool; that's done during init. + */ + return param_set_charp(s, kp); + case ZSWAP_INIT_SUCCEED: + /* no change required */ + if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) + return 0; + break; + case ZSWAP_INIT_FAILED: pr_err("can't set param, initialization failed\n"); return -ENODEV; } - /* no change required */ - if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) - return 0; - - /* if this is load-time (pre-init) param setting, - * don't create a pool; that's done during init. - */ - if (!zswap_init_started) - return param_set_charp(s, kp); - if (!type) { if (!zpool_has_pool(s)) { pr_err("zpool %s not available\n", s); @@ -864,16 +867,19 @@ static int zswap_zpool_param_set(const char *val, static int zswap_enabled_param_set(const char *val, const struct kernel_param *kp) { - if (zswap_init_failed) { + switch (zswap_init_state) { + case ZSWAP_UNINIT: + return param_set_bool(val, kp); + case ZSWAP_INIT_SUCCEED: + if (!zswap_has_pool) { + pr_err("can't enable, no pool configured\n"); + return -ENODEV; + } else + return param_set_bool(val, kp); + case ZSWAP_INIT_FAILED: pr_err("can't enable, initialization failed\n"); return -ENODEV; } - if (!zswap_has_pool && zswap_init_started) { - pr_err("can't enable, no pool configured\n"); - return -ENODEV; - } - - return param_set_bool(val, kp); } /********************************* @@ -1476,8 +1482,6 @@ static int __init init_zswap(void) struct zswap_pool *pool; int ret; - zswap_init_started = true; - zswap_entry_cache = KMEM_CACHE(zswap_entry, 0); if (!zswap_entry_cache) { pr_err("entry cache creation failed\n"); @@ -1518,6 +1522,7 @@ static int __init init_zswap(void) goto destroy_wq; if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); + zswap_init_state = ZSWAP_INIT_SUCCEED; return 0; destroy_wq: @@ -1531,7 +1536,7 @@ static int __init init_zswap(void) kmem_cache_destroy(zswap_entry_cache); cache_fail: /* if built-in, we aren't unloaded on failure; don't allow use */ - zswap_init_failed = true; + zswap_init_state = ZSWAP_INIT_FAILED; zswap_enabled = false; return -ENOMEM; } -- GitLab From 141fdeececb3d7b782ea7361a22659775d53bc2a Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Mon, 3 Apr 2023 20:13:18 +0800 Subject: [PATCH 3236/5631] mm/zswap: delay the initialization of zswap Since some users may not use zswap, the zswap_pool is wasted. Save memory by delaying the initialization of zswap until enabled. [liushixin2@huawei.com: fix some pattern problem suggested by Christoph] Link: https://lkml.kernel.org/r/20230411093632.822290-4-liushixin2@huawei.com Link: https://lkml.kernel.org/r/20230403121318.1876082-4-liushixin2@huawei.com Signed-off-by: Liu Shixin Reviewed-by: Christoph Hellwig Cc: Dan Streetman Cc: Nathan Chancellor Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton --- mm/zswap.c | 71 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 54 insertions(+), 17 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 9169c2baee87..af97e8f9d678 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -81,6 +81,8 @@ static bool zswap_pool_reached_full; #define ZSWAP_PARAM_UNSET "" +static int zswap_setup(void); + /* Enable/disable zswap */ static bool zswap_enabled = IS_ENABLED(CONFIG_ZSWAP_DEFAULT_ON); static int zswap_enabled_param_set(const char *, @@ -222,6 +224,9 @@ enum zswap_init_type { static enum zswap_init_type zswap_init_state; +/* used to ensure the integrity of initialization */ +static DEFINE_MUTEX(zswap_init_lock); + /* init completed, but couldn't create the initial pool */ static bool zswap_has_pool; @@ -654,7 +659,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) return NULL; } -static __init struct zswap_pool *__zswap_pool_create_fallback(void) +static struct zswap_pool *__zswap_pool_create_fallback(void) { bool has_comp, has_zpool; @@ -755,29 +760,43 @@ static void zswap_pool_put(struct zswap_pool *pool) * param callbacks **********************************/ +static bool zswap_pool_changed(const char *s, const struct kernel_param *kp) +{ + /* no change required */ + if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) + return false; + return true; +} + /* val must be a null-terminated string */ static int __zswap_param_set(const char *val, const struct kernel_param *kp, char *type, char *compressor) { struct zswap_pool *pool, *put_pool = NULL; char *s = strstrip((char *)val); - int ret; + int ret = 0; + bool new_pool = false; + mutex_lock(&zswap_init_lock); switch (zswap_init_state) { case ZSWAP_UNINIT: /* if this is load-time (pre-init) param setting, * don't create a pool; that's done during init. */ - return param_set_charp(s, kp); + ret = param_set_charp(s, kp); + break; case ZSWAP_INIT_SUCCEED: - /* no change required */ - if (!strcmp(s, *(char **)kp->arg) && zswap_has_pool) - return 0; + new_pool = zswap_pool_changed(s, kp); break; case ZSWAP_INIT_FAILED: pr_err("can't set param, initialization failed\n"); - return -ENODEV; + ret = -ENODEV; } + mutex_unlock(&zswap_init_lock); + + /* no need to create a new pool, return directly */ + if (!new_pool) + return ret; if (!type) { if (!zpool_has_pool(s)) { @@ -867,19 +886,30 @@ static int zswap_zpool_param_set(const char *val, static int zswap_enabled_param_set(const char *val, const struct kernel_param *kp) { + int ret = -ENODEV; + + /* if this is load-time (pre-init) param setting, only set param. */ + if (system_state != SYSTEM_RUNNING) + return param_set_bool(val, kp); + + mutex_lock(&zswap_init_lock); switch (zswap_init_state) { case ZSWAP_UNINIT: - return param_set_bool(val, kp); + if (zswap_setup()) + break; + fallthrough; case ZSWAP_INIT_SUCCEED: - if (!zswap_has_pool) { + if (!zswap_has_pool) pr_err("can't enable, no pool configured\n"); - return -ENODEV; - } else - return param_set_bool(val, kp); + else + ret = param_set_bool(val, kp); + break; case ZSWAP_INIT_FAILED: pr_err("can't enable, initialization failed\n"); - return -ENODEV; } + mutex_unlock(&zswap_init_lock); + + return ret; } /********************************* @@ -1437,7 +1467,7 @@ static const struct frontswap_ops zswap_frontswap_ops = { static struct dentry *zswap_debugfs_root; -static int __init zswap_debugfs_init(void) +static int zswap_debugfs_init(void) { if (!debugfs_initialized()) return -ENODEV; @@ -1468,7 +1498,7 @@ static int __init zswap_debugfs_init(void) return 0; } #else -static int __init zswap_debugfs_init(void) +static int zswap_debugfs_init(void) { return 0; } @@ -1477,7 +1507,7 @@ static int __init zswap_debugfs_init(void) /********************************* * module init and exit **********************************/ -static int __init init_zswap(void) +static int zswap_setup(void) { struct zswap_pool *pool; int ret; @@ -1540,8 +1570,15 @@ static int __init init_zswap(void) zswap_enabled = false; return -ENOMEM; } + +static int __init zswap_init(void) +{ + if (!zswap_enabled) + return 0; + return zswap_setup(); +} /* must be late so crypto has time to come up */ -late_initcall(init_zswap); +late_initcall(zswap_init); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Seth Jennings "); -- GitLab From 1ba3cbf3ec3b21d866436fb46b4bb7bdc38608f9 Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Mon, 3 Apr 2023 20:27:38 +0800 Subject: [PATCH 3237/5631] mm: kfence: improve the performance of __kfence_alloc() and __kfence_free() In __kfence_alloc() and __kfence_free(), we will set and check canary. Assuming that the size of the object is close to 0, nearly 4k memory accesses are required because setting and checking canary is executed byte by byte. canary is now defined like this: KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) Observe that canary is only related to the lower three bits of the address, so every 8 bytes of canary are the same. We can access 8-byte canary each time instead of byte-by-byte, thereby optimizing nearly 4k memory accesses to 4k/8 times. Use the bcc tool funclatency to measure the latency of __kfence_alloc() and __kfence_free(), the numbers (deleted the distribution of latency) is posted below. Though different object sizes will have an impact on the measurement, we ignore it for now and assume the average object size is roughly equal. Before patching: __kfence_alloc: avg = 5055 nsecs, total: 5515252 nsecs, count: 1091 __kfence_free: avg = 5319 nsecs, total: 9735130 nsecs, count: 1830 After patching: __kfence_alloc: avg = 3597 nsecs, total: 6428491 nsecs, count: 1787 __kfence_free: avg = 3046 nsecs, total: 3415390 nsecs, count: 1121 The numbers indicate that there is ~30% - ~40% performance improvement. Link: https://lkml.kernel.org/r/20230403122738.6006-1-zhangpeng.00@bytedance.com Signed-off-by: Peng Zhang Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton --- mm/kfence/core.c | 70 ++++++++++++++++++++++++++++++++-------------- mm/kfence/kfence.h | 10 ++++++- mm/kfence/report.c | 2 +- 3 files changed, 59 insertions(+), 23 deletions(-) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 1065e0568d05..d085ac7c8ae0 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -297,20 +297,13 @@ metadata_update_state(struct kfence_metadata *meta, enum kfence_object_state nex WRITE_ONCE(meta->state, next); } -/* Write canary byte to @addr. */ -static inline bool set_canary_byte(u8 *addr) -{ - *addr = KFENCE_CANARY_PATTERN(addr); - return true; -} - /* Check canary byte at @addr. */ static inline bool check_canary_byte(u8 *addr) { struct kfence_metadata *meta; unsigned long flags; - if (likely(*addr == KFENCE_CANARY_PATTERN(addr))) + if (likely(*addr == KFENCE_CANARY_PATTERN_U8(addr))) return true; atomic_long_inc(&counters[KFENCE_COUNTER_BUGS]); @@ -323,15 +316,31 @@ static inline bool check_canary_byte(u8 *addr) return false; } -/* __always_inline this to ensure we won't do an indirect call to fn. */ -static __always_inline void for_each_canary(const struct kfence_metadata *meta, bool (*fn)(u8 *)) +static inline void set_canary(const struct kfence_metadata *meta) { const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); - unsigned long addr; + unsigned long addr = pageaddr; + + /* + * The canary may be written to part of the object memory, but it does + * not affect it. The user should initialize the object before using it. + */ + for (; addr < meta->addr; addr += sizeof(u64)) + *((u64 *)addr) = KFENCE_CANARY_PATTERN_U64; + + addr = ALIGN_DOWN(meta->addr + meta->size, sizeof(u64)); + for (; addr - pageaddr < PAGE_SIZE; addr += sizeof(u64)) + *((u64 *)addr) = KFENCE_CANARY_PATTERN_U64; +} + +static inline void check_canary(const struct kfence_metadata *meta) +{ + const unsigned long pageaddr = ALIGN_DOWN(meta->addr, PAGE_SIZE); + unsigned long addr = pageaddr; /* - * We'll iterate over each canary byte per-side until fn() returns - * false. However, we'll still iterate over the canary bytes to the + * We'll iterate over each canary byte per-side until a corrupted byte + * is found. However, we'll still iterate over the canary bytes to the * right of the object even if there was an error in the canary bytes to * the left of the object. Specifically, if check_canary_byte() * generates an error, showing both sides might give more clues as to @@ -339,16 +348,35 @@ static __always_inline void for_each_canary(const struct kfence_metadata *meta, */ /* Apply to left of object. */ - for (addr = pageaddr; addr < meta->addr; addr++) { - if (!fn((u8 *)addr)) + for (; meta->addr - addr >= sizeof(u64); addr += sizeof(u64)) { + if (unlikely(*((u64 *)addr) != KFENCE_CANARY_PATTERN_U64)) break; } - /* Apply to right of object. */ - for (addr = meta->addr + meta->size; addr < pageaddr + PAGE_SIZE; addr++) { - if (!fn((u8 *)addr)) + /* + * If the canary is corrupted in a certain 64 bytes, or the canary + * memory cannot be completely covered by multiple consecutive 64 bytes, + * it needs to be checked one by one. + */ + for (; addr < meta->addr; addr++) { + if (unlikely(!check_canary_byte((u8 *)addr))) break; } + + /* Apply to right of object. */ + for (addr = meta->addr + meta->size; addr % sizeof(u64) != 0; addr++) { + if (unlikely(!check_canary_byte((u8 *)addr))) + return; + } + for (; addr - pageaddr < PAGE_SIZE; addr += sizeof(u64)) { + if (unlikely(*((u64 *)addr) != KFENCE_CANARY_PATTERN_U64)) { + + for (; addr - pageaddr < PAGE_SIZE; addr++) { + if (!check_canary_byte((u8 *)addr)) + return; + } + } + } } static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t gfp, @@ -434,7 +462,7 @@ static void *kfence_guarded_alloc(struct kmem_cache *cache, size_t size, gfp_t g #endif /* Memory initialization. */ - for_each_canary(meta, set_canary_byte); + set_canary(meta); /* * We check slab_want_init_on_alloc() ourselves, rather than letting @@ -495,7 +523,7 @@ static void kfence_guarded_free(void *addr, struct kfence_metadata *meta, bool z alloc_covered_add(meta->alloc_stack_hash, -1); /* Check canary bytes for memory corruption. */ - for_each_canary(meta, check_canary_byte); + check_canary(meta); /* * Clear memory if init-on-free is set. While we protect the page, the @@ -751,7 +779,7 @@ static void kfence_check_all_canary(void) struct kfence_metadata *meta = &kfence_metadata[i]; if (meta->state == KFENCE_OBJECT_ALLOCATED) - for_each_canary(meta, check_canary_byte); + check_canary(meta); } } diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 600f2e2431d6..2aafc46a4aaf 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -21,7 +21,15 @@ * lower 3 bits of the address, to detect memory corruptions with higher * probability, where similar constants are used. */ -#define KFENCE_CANARY_PATTERN(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) +#define KFENCE_CANARY_PATTERN_U8(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) + +/* + * Define a continuous 8-byte canary starting from a multiple of 8. The canary + * of each byte is only related to the lowest three bits of its address, so the + * canary of every 8 bytes is the same. 64-bit memory can be filled and checked + * at a time instead of byte by byte to improve performance. + */ +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 60205f1257ef..197430a5be4a 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -168,7 +168,7 @@ static void print_diff_canary(unsigned long address, size_t bytes_to_show, pr_cont("["); for (cur = (const u8 *)address; cur < end; cur++) { - if (*cur == KFENCE_CANARY_PATTERN(cur)) + if (*cur == KFENCE_CANARY_PATTERN_U8(cur)) pr_cont(" ."); else if (no_hash_pointers) pr_cont(" 0x%02x", *cur); -- GitLab From 8bff9a04ca33476213ea6155850505787c540c25 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:54 +0000 Subject: [PATCH 3238/5631] cgroup: rename cgroup_rstat_flush_"irqsafe" to "atomic" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "memcg: avoid flushing stats atomically where possible", v3. rstat flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system. The purpose of this series is to minimize the contexts where we flush stats atomically. Patches 1 and 2 are cleanups requested during reviews of prior versions of this series. Patch 3 makes sure we never try to flush from within an irq context. Patches 4 to 7 introduce separate variants of mem_cgroup_flush_stats() for atomic and non-atomic flushing, and make sure we only flush the stats atomically when necessary. Patch 8 is a slightly tangential optimization that limits the work done by rstat flushing in some scenarios. This patch (of 8): cgroup_rstat_flush_irqsafe() can be a confusing name. It may read as "irqs are disabled throughout", which is what the current implementation does (currently under discussion [1]), but is not the intention. The intention is that this function is safe to call from atomic contexts. Name it as such. Link: https://lkml.kernel.org/r/20230330191801.1967435-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20230330191801.1967435-2-yosryahmed@google.com Signed-off-by: Yosry Ahmed Suggested-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Cc: Michal Hocko Signed-off-by: Andrew Morton --- include/linux/cgroup.h | 2 +- kernel/cgroup/rstat.c | 4 ++-- mm/memcontrol.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3410aecffdb4..885f5395fcd0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -692,7 +692,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); +void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 831f1f472bb8..d3252b0416b6 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -241,12 +241,12 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) } /** - * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() + * cgroup_rstat_flush_atomic- atomic version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) +void cgroup_rstat_flush_atomic(struct cgroup *cgrp) { unsigned long flags; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 681e7528a714..b7c3eab6b4fe 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -643,7 +643,7 @@ static void __mem_cgroup_flush_stats(void) return; flush_next_time = jiffies_64 + 2*FLUSH_TIME; - cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); + cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); spin_unlock_irqrestore(&stats_flush_lock, flag); } -- GitLab From 92fbbc7202ac4fb16250dc91c88211814ae2190b Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:55 +0000 Subject: [PATCH 3239/5631] memcg: rename mem_cgroup_flush_stats_"delayed" to "ratelimited" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mem_cgroup_flush_stats_delayed() suggests his is using a delayed_work, but this is actually sometimes flushing directly from the callsite. What it's doing is ratelimited calls. A better name would be mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-3-yosryahmed@google.com Signed-off-by: Yosry Ahmed Suggested-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 2 +- mm/workingset.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index aa69ea98e2d8..00a88cf947e1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1038,7 +1038,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_delayed(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1536,7 +1536,7 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_delayed(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b7c3eab6b4fe..a01f062e7007 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -654,7 +654,7 @@ void mem_cgroup_flush_stats(void) __mem_cgroup_flush_stats(); } -void mem_cgroup_flush_stats_delayed(void) +void mem_cgroup_flush_stats_ratelimited(void) { if (time_after64(jiffies_64, flush_next_time)) mem_cgroup_flush_stats(); diff --git a/mm/workingset.c b/mm/workingset.c index 00c6f4d9d9be..af862c6738c3 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -462,7 +462,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats_delayed(); + mem_cgroup_flush_stats_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if -- GitLab From a2174e95cce5e65ee49c60368434aaae944ff1af Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:56 +0000 Subject: [PATCH 3240/5631] memcg: do not flush stats in irq context MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, the only context in which we can invoke an rstat flush from irq context is through mem_cgroup_usage() on the root memcg when called from memcg_check_events(). An rstat flush is an expensive operation that should not be done in irq context, so do not flush stats and use the stale stats in this case. Arguably, usage threshold events are not reliable on the root memcg anyway since its usage is ill-defined. Link: https://lkml.kernel.org/r/20230330191801.1967435-4-yosryahmed@google.com Signed-off-by: Yosry Ahmed Suggested-by: Johannes Weiner Suggested-by: Shakeel Butt Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- mm/memcontrol.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a01f062e7007..5040db9a76a6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3670,7 +3670,21 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val; if (mem_cgroup_is_root(memcg)) { - mem_cgroup_flush_stats(); + /* + * We can reach here from irq context through: + * uncharge_batch() + * |--memcg_check_events() + * |--mem_cgroup_threshold() + * |--__mem_cgroup_threshold() + * |--mem_cgroup_usage + * + * rstat flushing is an expensive operation that should not be + * done from irq context; use stale stats in this case. + * Arguably, usage threshold events are not reliable on the root + * memcg anyway since its usage is ill-defined. + */ + if (in_task()) + mem_cgroup_flush_stats(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) -- GitLab From 3cd9992b93023cc5338423b3599eb987111e3ed5 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:57 +0000 Subject: [PATCH 3241/5631] memcg: replace stats_flush_lock with an atomic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As Johannes notes in [1], stats_flush_lock is currently used to: (a) Protect updated to stats_flush_threshold. (b) Protect updates to flush_next_time. (c) Serializes calls to cgroup_rstat_flush() based on those ratelimits. However: 1. stats_flush_threshold is already an atomic 2. flush_next_time is not atomic. The writer is locked, but the reader is lockless. If the reader races with a flush, you could see this: if (time_after(jiffies, flush_next_time)) spin_trylock() flush_next_time = now + delay flush() spin_unlock() spin_trylock() flush_next_time = now + delay flush() spin_unlock() which means we already can get flushes at a higher frequency than FLUSH_TIME during races. But it isn't really a problem. The reader could also see garbled partial updates if the compiler decides to split the write, so it needs at least READ_ONCE and WRITE_ONCE protection. 3. Serializing cgroup_rstat_flush() calls against the ratelimit factors is currently broken because of the race in 2. But the race is actually harmless, all we might get is the occasional earlier flush. If there is no delta, the flush won't do much. And if there is, the flush is justified. So the lock can be removed all together. However, the lock also served the purpose of preventing a thundering herd problem for concurrent flushers, see [2]. Use an atomic instead to serve the purpose of unifying concurrent flushers. [1]https://lore.kernel.org/lkml/20230323172732.GE739026@cmpxchg.org/ [2]https://lore.kernel.org/lkml/20210716212137.1391164-2-shakeelb@google.com/ Link: https://lkml.kernel.org/r/20230330191801.1967435-5-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Johannes Weiner Acked-by: Shakeel Butt Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- mm/memcontrol.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5040db9a76a6..a9f18456a16b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -586,8 +586,8 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) */ static void flush_memcg_stats_dwork(struct work_struct *w); static DECLARE_DEFERRABLE_WORK(stats_flush_dwork, flush_memcg_stats_dwork); -static DEFINE_SPINLOCK(stats_flush_lock); static DEFINE_PER_CPU(unsigned int, stats_updates); +static atomic_t stats_flush_ongoing = ATOMIC_INIT(0); static atomic_t stats_flush_threshold = ATOMIC_INIT(0); static u64 flush_next_time; @@ -637,15 +637,19 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) static void __mem_cgroup_flush_stats(void) { - unsigned long flag; - - if (!spin_trylock_irqsave(&stats_flush_lock, flag)) + /* + * We always flush the entire tree, so concurrent flushers can just + * skip. This avoids a thundering herd problem on the rstat global lock + * from memcg flushers (e.g. reclaim, refault, etc). + */ + if (atomic_read(&stats_flush_ongoing) || + atomic_xchg(&stats_flush_ongoing, 1)) return; - flush_next_time = jiffies_64 + 2*FLUSH_TIME; + WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME); cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); - spin_unlock_irqrestore(&stats_flush_lock, flag); + atomic_set(&stats_flush_ongoing, 0); } void mem_cgroup_flush_stats(void) @@ -656,7 +660,7 @@ void mem_cgroup_flush_stats(void) void mem_cgroup_flush_stats_ratelimited(void) { - if (time_after64(jiffies_64, flush_next_time)) + if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) mem_cgroup_flush_stats(); } -- GitLab From 9fad9aee1f267a8ad1f86b87ae70b2c4d6796164 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:58 +0000 Subject: [PATCH 3242/5631] memcg: sleep during flushing stats in safe contexts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, all contexts that flush memcg stats do so with sleeping not allowed. Some of these contexts are perfectly safe to sleep in, such as reading cgroup files from userspace or the background periodic flusher. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Refactor the code to make mem_cgroup_flush_stats() non-atomic (aka sleepable), and provide a separate atomic version. The atomic version is used in reclaim, refault, writeback, and in mem_cgroup_usage(). All other code paths are left to use the non-atomic version. This includes callbacks for userspace reads and the periodic flusher. Since refault is the only caller of mem_cgroup_flush_stats_ratelimited(), change it to mem_cgroup_flush_stats_atomic_ratelimited(). Reclaim and refault code paths are modified to do non-atomic flushing in separate later patches -- so it will eventually be changed back to mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-6-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 9 ++++++-- mm/memcontrol.c | 45 ++++++++++++++++++++++++++++++-------- mm/vmscan.c | 2 +- mm/workingset.c | 2 +- 4 files changed, 45 insertions(+), 13 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 00a88cf947e1..3db355e6677f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1038,7 +1038,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_ratelimited(void); +void mem_cgroup_flush_stats_atomic(void); +void mem_cgroup_flush_stats_atomic_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1536,7 +1537,11 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_ratelimited(void) +static inline void mem_cgroup_flush_stats_atomic(void) +{ +} + +static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a9f18456a16b..06786dea50b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -635,7 +635,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) } } -static void __mem_cgroup_flush_stats(void) +static void do_flush_stats(bool atomic) { /* * We always flush the entire tree, so concurrent flushers can just @@ -647,26 +647,46 @@ static void __mem_cgroup_flush_stats(void) return; WRITE_ONCE(flush_next_time, jiffies_64 + 2*FLUSH_TIME); - cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); + + if (atomic) + cgroup_rstat_flush_atomic(root_mem_cgroup->css.cgroup); + else + cgroup_rstat_flush(root_mem_cgroup->css.cgroup); + atomic_set(&stats_flush_threshold, 0); atomic_set(&stats_flush_ongoing, 0); } +static bool should_flush_stats(void) +{ + return atomic_read(&stats_flush_threshold) > num_online_cpus(); +} + void mem_cgroup_flush_stats(void) { - if (atomic_read(&stats_flush_threshold) > num_online_cpus()) - __mem_cgroup_flush_stats(); + if (should_flush_stats()) + do_flush_stats(false); } -void mem_cgroup_flush_stats_ratelimited(void) +void mem_cgroup_flush_stats_atomic(void) +{ + if (should_flush_stats()) + do_flush_stats(true); +} + +void mem_cgroup_flush_stats_atomic_ratelimited(void) { if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); } static void flush_memcg_stats_dwork(struct work_struct *w) { - __mem_cgroup_flush_stats(); + /* + * Always flush here so that flushing in latency-sensitive paths is + * as cheap as possible. + */ + do_flush_stats(false); queue_delayed_work(system_unbound_wq, &stats_flush_dwork, FLUSH_TIME); } @@ -3686,9 +3706,12 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) * done from irq context; use stale stats in this case. * Arguably, usage threshold events are not reliable on the root * memcg anyway since its usage is ill-defined. + * + * Additionally, other call paths through memcg_check_events() + * disable irqs, so make sure we are flushing stats atomically. */ if (in_task()) - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) @@ -4611,7 +4634,11 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - mem_cgroup_flush_stats(); + /* + * wb_writeback() takes a spinlock and calls + * wb_over_bg_thresh()->mem_cgroup_wb_stats(). Do not sleep. + */ + mem_cgroup_flush_stats_atomic(); *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); diff --git a/mm/vmscan.c b/mm/vmscan.c index 98719e72b5e2..c68db50ec109 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2861,7 +2861,7 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ - mem_cgroup_flush_stats(); + mem_cgroup_flush_stats_atomic(); /* * Determine the scan balance between anon and file LRUs. diff --git a/mm/workingset.c b/mm/workingset.c index af862c6738c3..dab0c362b9e3 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -462,7 +462,7 @@ void workingset_refault(struct folio *folio, void *shadow) mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - mem_cgroup_flush_stats_ratelimited(); + mem_cgroup_flush_stats_atomic_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if -- GitLab From 4009b2f1887036d30637bc06dd0ade7e18408bb3 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:17:59 +0000 Subject: [PATCH 3243/5631] workingset: memcg: sleep when flushing stats in workingset_refault() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In workingset_refault(), we call mem_cgroup_flush_stats_atomic_ratelimited() to read accurate stats within an RCU read section and with sleeping disallowed. Move the call above the RCU read section to make it non-atomic. Flushing is an expensive operation that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically where possible. Since workingset_refault() is the only caller of mem_cgroup_flush_stats_atomic_ratelimited(), just make it non-atomic, and rename it to mem_cgroup_flush_stats_ratelimited(). Link: https://lkml.kernel.org/r/20230330191801.1967435-7-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- mm/memcontrol.c | 4 ++-- mm/workingset.c | 5 +++-- 3 files changed, 7 insertions(+), 6 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3db355e6677f..222d7370134c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1039,7 +1039,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void mem_cgroup_flush_stats(void); void mem_cgroup_flush_stats_atomic(void); -void mem_cgroup_flush_stats_atomic_ratelimited(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1541,7 +1541,7 @@ static inline void mem_cgroup_flush_stats_atomic(void) { } -static inline void mem_cgroup_flush_stats_atomic_ratelimited(void) +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 06786dea50b8..e9e79ceb9a11 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -674,10 +674,10 @@ void mem_cgroup_flush_stats_atomic(void) do_flush_stats(true); } -void mem_cgroup_flush_stats_atomic_ratelimited(void) +void mem_cgroup_flush_stats_ratelimited(void) { if (time_after64(jiffies_64, READ_ONCE(flush_next_time))) - mem_cgroup_flush_stats_atomic(); + mem_cgroup_flush_stats(); } static void flush_memcg_stats_dwork(struct work_struct *w) diff --git a/mm/workingset.c b/mm/workingset.c index dab0c362b9e3..3025beee9b34 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -406,6 +406,9 @@ void workingset_refault(struct folio *folio, void *shadow) unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); eviction <<= bucket_order; + /* Flush stats (and potentially sleep) before holding RCU read lock */ + mem_cgroup_flush_stats_ratelimited(); + rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might @@ -461,8 +464,6 @@ void workingset_refault(struct folio *folio, void *shadow) lruvec = mem_cgroup_lruvec(memcg, pgdat); mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); - - mem_cgroup_flush_stats_atomic_ratelimited(); /* * Compare the distance to the existing workingset size. We * don't activate pages that couldn't stay resident even if -- GitLab From 0d856cfedd6bc0cb8e19c1e70d400e79b655cfdd Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:18:00 +0000 Subject: [PATCH 3244/5631] vmscan: memcg: sleep when flushing stats during reclaim MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Memory reclaim is a sleepable context. Flushing is an expensive operaiton that scales with the number of cpus and the number of cgroups in the system, so avoid doing it atomically unnecessarily. This can slow down reclaim code if flushing stats is taking too long, but there is already multiple cond_resched()'s in reclaim code. Link: https://lkml.kernel.org/r/20230330191801.1967435-8-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Michal Koutný Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index c68db50ec109..98719e72b5e2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2861,7 +2861,7 @@ static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc) * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ - mem_cgroup_flush_stats_atomic(); + mem_cgroup_flush_stats(); /* * Determine the scan balance between anon and file LRUs. -- GitLab From f9d911ca49d7fb30dde4858f8751cf2534e78b47 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 30 Mar 2023 19:18:01 +0000 Subject: [PATCH 3245/5631] memcg: do not modify rstat tree for zero updates MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In some situations, we may end up calling memcg_rstat_updated() with a value of 0, which means the stat was not actually updated. An example is if we fail to reclaim any pages in shrink_folio_list(). Do not add the cgroup to the rstat updated tree in this case, to avoid unnecessarily flushing it. Link: https://lkml.kernel.org/r/20230330191801.1967435-9-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Michal Koutný Cc: Jens Axboe Cc: Josef Bacik Cc: Michal Hocko Cc: Muchun Song Cc: Roman Gushchin Cc: Tejun Heo Cc: Vasily Averin Cc: Zefan Li Signed-off-by: Andrew Morton --- mm/memcontrol.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e9e79ceb9a11..3d040a5fa7a3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -619,6 +619,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { unsigned int x; + if (!val) + return; + cgroup_rstat_updated(memcg->css.cgroup, smp_processor_id()); x = __this_cpu_add_return(stats_updates, abs(val)); -- GitLab From 98c76c9f1ef7599b39bfd4bd99b8a760d4a8cd3b Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Wed, 29 Mar 2023 08:11:19 -0700 Subject: [PATCH 3246/5631] mm/khugepaged: recover from poisoned anonymous memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Problem ======= Memory DIMMs are subject to multi-bit flips, i.e. memory errors. As memory size and density increase, the chances of and number of memory errors increase. The increasing size and density of server RAM in the data center and cloud have shown increased uncorrectable memory errors. There are already mechanisms in the kernel to recover from uncorrectable memory errors. This series of patches provides the recovery mechanism for the particular kernel agent khugepaged when it collapses memory pages. Impact ====== The main reason we chose to make khugepaged collapsing tolerant of memory failures was its high possibility of accessing poisoned memory while performing functionally optional compaction actions. Standard applications typically don't have strict requirements on the size of its pages. So they are given 4K pages by the kernel. The kernel is able to improve application performance by either 1) giving applications 2M pages to begin with, or 2) collapsing 4K pages into 2M pages when possible. This collapsing operation is done by khugepaged, a kernel agent that is constantly scanning memory. When collapsing 4K pages into a 2M page, it must copy the data from the 4K pages into a physically contiguous 2M page. Therefore, as long as there exists one poisoned cache line in collapsible 4K pages, khugepaged will eventually access it. The current impact to users is a machine check exception triggered kernel panic. However, khugepaged’s compaction operations are not functionally required kernel actions. Therefore making khugepaged tolerant to poisoned memory will greatly improve user experience. This patch series is for cases where khugepaged is the first guy that detects the memory errors on the poisoned pages. IOW, the pages are not known to have memory errors when khugepaged collapsing gets to them. In our observation, this happens frequently when the huge page ratio of the system is relatively low, which is fairly common in virtual machines running on cloud. Solution ======== As stated before, it is less desirable to crash the system only because khugepaged accesses poisoned pages while it is collapsing 4K pages. The high level idea of this patch series is to skip the group of pages (usually 512 4K-size pages) once khugepaged finds one of them is poisoned, as these pages have become ineligible to be collapsed. We are also careful to unwind operations khuagepaged has performed before it detects memory failures. For example, before copying and collapsing a group of anonymous pages into a huge page, the source pages will be isolated and their page table is unlinked from their PMD. These operations need to be undone in order to ensure these pages are not changed/lost from the perspective of other threads (both user and kernel space). As for file backed memory pages, there already exists a rollback case. This patch just extends it so that khugepaged also correctly rolls back when it fails to copy poisoned 4K pages. This patch (of 3): Make __collapse_huge_page_copy return whether copying anonymous pages succeeded, and make collapse_huge_page handle the return status. Break existing PTE scan loop into two for-loops. The first loop copies source pages into target huge page, and can fail gracefully when running into memory errors in source pages. If copying all pages succeeds, the second loop releases and clears up these normal pages. Otherwise, the second loop rolls back the page table and page states by: - re-establishing the original PTEs-to-PMD connection. - releasing source pages back to their LRU list. Tested manually: 0. Enable khugepaged on system under test. 1. Start a two-thread application. Each thread allocates a chunk of non-huge anonymous memory buffer. 2. Pick 4 random buffer locations (2 in each thread) and inject uncorrectable memory errors at corresponding physical addresses. 3. Signal both threads to make their memory buffer collapsible, i.e. calling madvise(MADV_HUGEPAGE). 4. Wait and check kernel log: khugepaged is able to recover from poisoned pages and skips collapsing them. 5. Signal both threads to inspect their buffer contents and make sure no data corruption. Link: https://lkml.kernel.org/r/20230329151121.949896-1-jiaqiyan@google.com Link: https://lkml.kernel.org/r/20230329151121.949896-2-jiaqiyan@google.com Signed-off-by: Jiaqi Yan Cc: David Stevens Cc: Hugh Dickins Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Tong Tiangen Cc: Tony Luck Cc: Yang Shi Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 3 +- mm/khugepaged.c | 112 +++++++++++++++++++++++++---- 2 files changed, 101 insertions(+), 14 deletions(-) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index c84c7af70158..eca4c6f3625e 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -37,7 +37,8 @@ EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ EM( SCAN_TRUNCATED, "truncated") \ EM( SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ - EMe(SCAN_STORE_FAILED, "store_failed") + EM( SCAN_STORE_FAILED, "store_failed") \ + EMe(SCAN_COPY_MC, "copy_poisoned_page") #undef EM #undef EMe diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 3b61cd188f7b..c66933d8a8b8 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -56,6 +56,7 @@ enum scan_result { SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, + SCAN_COPY_MC, }; #define CREATE_TRACE_POINTS @@ -686,20 +687,21 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, return result; } -static void __collapse_huge_page_copy(pte_t *pte, struct page *page, - struct vm_area_struct *vma, - unsigned long address, - spinlock_t *ptl, - struct list_head *compound_pagelist) +static void __collapse_huge_page_copy_succeeded(pte_t *pte, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl, + struct list_head *compound_pagelist) { - struct page *src_page, *tmp; + struct page *src_page; + struct page *tmp; pte_t *_pte; - for (_pte = pte; _pte < pte + HPAGE_PMD_NR; - _pte++, page++, address += PAGE_SIZE) { - pte_t pteval = *_pte; + pte_t pteval; + for (_pte = pte; _pte < pte + HPAGE_PMD_NR; + _pte++, address += PAGE_SIZE) { + pteval = *_pte; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { - clear_user_highpage(page, address); add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* @@ -711,7 +713,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, } } else { src_page = pte_page(pteval); - copy_user_highpage(page, src_page, address, vma); if (!PageCompound(src_page)) release_pte_page(src_page); /* @@ -738,6 +739,87 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, } } +static void __collapse_huge_page_copy_failed(pte_t *pte, + pmd_t *pmd, + pmd_t orig_pmd, + struct vm_area_struct *vma, + struct list_head *compound_pagelist) +{ + spinlock_t *pmd_ptl; + + /* + * Re-establish the PMD to point to the original page table + * entry. Restoring PMD needs to be done prior to releasing + * pages. Since pages are still isolated and locked here, + * acquiring anon_vma_lock_write is unnecessary. + */ + pmd_ptl = pmd_lock(vma->vm_mm, pmd); + pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); + spin_unlock(pmd_ptl); + /* + * Release both raw and compound pages isolated + * in __collapse_huge_page_isolate. + */ + release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); +} + +/* + * __collapse_huge_page_copy - attempts to copy memory contents from raw + * pages to a hugepage. Cleans up the raw pages if copying succeeds; + * otherwise restores the original page table and releases isolated raw pages. + * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. + * + * @pte: starting of the PTEs to copy from + * @page: the new hugepage to copy contents to + * @pmd: pointer to the new hugepage's PMD + * @orig_pmd: the original raw pages' PMD + * @vma: the original raw pages' virtual memory area + * @address: starting address to copy + * @ptl: lock on raw pages' PTEs + * @compound_pagelist: list that stores compound pages + */ +static int __collapse_huge_page_copy(pte_t *pte, + struct page *page, + pmd_t *pmd, + pmd_t orig_pmd, + struct vm_area_struct *vma, + unsigned long address, + spinlock_t *ptl, + struct list_head *compound_pagelist) +{ + struct page *src_page; + pte_t *_pte; + pte_t pteval; + unsigned long _address; + int result = SCAN_SUCCEED; + + /* + * Copying pages' contents is subject to memory poison at any iteration. + */ + for (_pte = pte, _address = address; _pte < pte + HPAGE_PMD_NR; + _pte++, page++, _address += PAGE_SIZE) { + pteval = *_pte; + if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { + clear_user_highpage(page, _address); + continue; + } + src_page = pte_page(pteval); + if (copy_mc_user_highpage(page, src_page, _address, vma) > 0) { + result = SCAN_COPY_MC; + break; + } + } + + if (likely(result == SCAN_SUCCEED)) + __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, + compound_pagelist); + else + __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, + compound_pagelist); + + return result; +} + static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); @@ -1111,9 +1193,13 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, */ anon_vma_unlock_write(vma->anon_vma); - __collapse_huge_page_copy(pte, hpage, vma, address, pte_ptl, - &compound_pagelist); + result = __collapse_huge_page_copy(pte, hpage, pmd, _pmd, + vma, address, pte_ptl, + &compound_pagelist); pte_unmap(pte); + if (unlikely(result != SCAN_SUCCEED)) + goto out_up_write; + /* * spin_lock() below is not the equivalent of smp_wmb(), but * the smp_wmb() inside __SetPageUptodate() can be reused to -- GitLab From 6efc7afb5cc98488410d44695685d003d832534d Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Wed, 29 Mar 2023 08:11:20 -0700 Subject: [PATCH 3247/5631] mm/hwpoison: introduce copy_mc_highpage Similar to how copy_mc_user_highpage is implemented for copy_user_highpage on #MC supported architecture, introduce the #MC handled version of copy_highpage. This helper has immediate usage when khugepaged wants to copy file-backed memory pages and tolerate #MC. Link: https://lkml.kernel.org/r/20230329151121.949896-3-jiaqiyan@google.com Signed-off-by: Jiaqi Yan Reviewed-by: Yang Shi Cc: David Stevens Cc: Hugh Dickins Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Tong Tiangen Cc: Tony Luck Signed-off-by: Andrew Morton --- include/linux/highmem.h | 54 +++++++++++++++++++++++++++++++---------- 1 file changed, 41 insertions(+), 13 deletions(-) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 9c7cdaa3de8c..4de1dbcd3ef6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -315,7 +315,29 @@ static inline void copy_user_highpage(struct page *to, struct page *from, #endif +#ifndef __HAVE_ARCH_COPY_HIGHPAGE + +static inline void copy_highpage(struct page *to, struct page *from) +{ + char *vfrom, *vto; + + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); + copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); + kunmap_local(vto); + kunmap_local(vfrom); +} + +#endif + #ifdef copy_mc_to_kernel +/* + * If architecture supports machine check exception handling, define the + * #MC versions of copy_user_highpage and copy_highpage. They copy a memory + * page with #MC in source page (@from) handled, and return the number + * of bytes not copied if there was a #MC, otherwise 0 for success. + */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { @@ -332,29 +354,35 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, return ret; } -#else -static inline int copy_mc_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - copy_user_highpage(to, from, vaddr, vma); - return 0; -} -#endif -#ifndef __HAVE_ARCH_COPY_HIGHPAGE - -static inline void copy_highpage(struct page *to, struct page *from) +static inline int copy_mc_highpage(struct page *to, struct page *from) { + unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); - copy_page(vto, vfrom); - kmsan_copy_page_meta(to, from); + ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); + if (!ret) + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); + + return ret; +} +#else +static inline int copy_mc_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + copy_user_highpage(to, from, vaddr, vma); + return 0; } +static inline int copy_mc_highpage(struct page *to, struct page *from) +{ + copy_highpage(to, from); + return 0; +} #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, -- GitLab From 12904d953364e3bd21789a45137bf90df7cc78ee Mon Sep 17 00:00:00 2001 From: Jiaqi Yan Date: Wed, 29 Mar 2023 08:11:21 -0700 Subject: [PATCH 3248/5631] mm/khugepaged: recover from poisoned file-backed memory Make collapse_file roll back when copying pages failed. More concretely: - extract copying operations into a separate loop - postpone the updates for nr_none until both scanning and copying succeeded - postpone joining small xarray entries until both scanning and copying succeeded - postpone the update operations to NR_XXX_THPS until both scanning and copying succeeded - for non-SHMEM file, roll back filemap_nr_thps_inc if scan succeeded but copying failed Tested manually: 0. Enable khugepaged on system under test. Mount tmpfs at /mnt/ramdisk. 1. Start a two-thread application. Each thread allocates a chunk of non-huge memory buffer from /mnt/ramdisk. 2. Pick 4 random buffer address (2 in each thread) and inject uncorrectable memory errors at physical addresses. 3. Signal both threads to make their memory buffer collapsible, i.e. calling madvise(MADV_HUGEPAGE). 4. Wait and then check kernel log: khugepaged is able to recover from poisoned pages by skipping them. 5. Signal both threads to inspect their buffer contents and make sure no data corruption. Link: https://lkml.kernel.org/r/20230329151121.949896-4-jiaqiyan@google.com Signed-off-by: Jiaqi Yan Reviewed-by: Yang Shi Acked-by: Hugh Dickins Cc: David Stevens Cc: Kefeng Wang Cc: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Oscar Salvador Cc: Tong Tiangen Cc: Tony Luck Signed-off-by: Andrew Morton --- mm/khugepaged.c | 87 +++++++++++++++++++++++++++++++------------------ 1 file changed, 56 insertions(+), 31 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c66933d8a8b8..deea5c5cd9e8 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1877,6 +1877,9 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, { struct address_space *mapping = file->f_mapping; struct page *hpage; + struct page *page; + struct page *tmp; + struct folio *folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); @@ -1921,8 +1924,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_set(&xas, start); for (index = start; index < end; index++) { - struct page *page = xas_next(&xas); - struct folio *folio; + page = xas_next(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { @@ -2116,12 +2118,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, put_page(page); goto xa_unlocked; } - nr = thp_nr_pages(hpage); - if (is_shmem) - __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); - else { - __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr); + if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with smp_mb() in do_dentry_open() to ensure @@ -2132,21 +2130,10 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; - __mod_lruvec_page_state(hpage, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); - goto xa_locked; } } - if (nr_none) { - __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none); - /* nr_none is always 0 for non-shmem. */ - __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); - } - - /* Join all the small entries into a single multi-index entry */ - xas_set_order(&xas, start, HPAGE_PMD_ORDER); - xas_store(&xas, hpage); /* Here we can't get an ENOMEM (because entries were * previously allocated) But let's check for errors * (XArray implementation can be changed in the future) @@ -2164,21 +2151,36 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, try_to_unmap_flush(); if (result == SCAN_SUCCEED) { - struct page *page, *tmp; - struct folio *folio; - /* * Replacing old pages with new one has succeeded, now we - * need to copy the content and free the old pages. + * attempt to copy the contents. */ index = start; - list_for_each_entry_safe(page, tmp, &pagelist, lru) { + list_for_each_entry(page, &pagelist, lru) { while (index < page->index) { clear_highpage(hpage + (index % HPAGE_PMD_NR)); index++; } - copy_highpage(hpage + (page->index % HPAGE_PMD_NR), - page); + if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), + page) > 0) { + result = SCAN_COPY_MC; + break; + } + index++; + } + while (result == SCAN_SUCCEED && index < end) { + clear_highpage(hpage + (index % HPAGE_PMD_NR)); + index++; + } + } + + nr = thp_nr_pages(hpage); + if (result == SCAN_SUCCEED) { + /* + * Copying old pages to huge one has succeeded, now we + * need to free the old pages. + */ + list_for_each_entry_safe(page, tmp, &pagelist, lru) { list_del(&page->lru); page->mapping = NULL; page_ref_unfreeze(page, 1); @@ -2186,12 +2188,23 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, ClearPageUnevictable(page); unlock_page(page); put_page(page); - index++; } - while (index < end) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); - index++; + + xas_lock_irq(&xas); + if (is_shmem) + __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); + else + __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr); + + if (nr_none) { + __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none); + /* nr_none is always 0 for non-shmem. */ + __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); } + /* Join all the small entries into a single multi-index entry. */ + xas_set_order(&xas, start, HPAGE_PMD_ORDER); + xas_store(&xas, hpage); + xas_unlock_irq(&xas); folio = page_folio(hpage); folio_mark_uptodate(folio); @@ -2209,8 +2222,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, unlock_page(hpage); hpage = NULL; } else { - struct page *page; - /* Something went wrong: roll back page cache changes */ xas_lock_irq(&xas); if (nr_none) { @@ -2244,6 +2255,20 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_lock_irq(&xas); } VM_BUG_ON(nr_none); + /* + * Undo the updates of filemap_nr_thps_inc for non-SHMEM + * file only. This undo is not needed unless failure is + * due to SCAN_COPY_MC. + */ + if (!is_shmem && result == SCAN_COPY_MC) { + filemap_nr_thps_dec(mapping); + /* + * Paired with smp_mb() in do_dentry_open() to + * ensure the update to nr_thps is visible. + */ + smp_mb(); + } + xas_unlock_irq(&xas); hpage->mapping = NULL; -- GitLab From efa3d814fad151ed5209539ecc1fc2880f7680b2 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 4 Apr 2023 21:01:14 +0900 Subject: [PATCH 3249/5631] mm/khugepaged: drain lru after swapping in shmem Patch series "mm/khugepaged: fixes for khugepaged+shmem", v6. This series reworks collapse_file so that the intermediate state of the collapse does not leak out of collapse_file. Although this makes collapse_file a bit more complicated, it means that the rest of the kernel doesn't have to deal with the unusual state. This directly fixes races with both lseek and mincore. This series also fixes the fact that khugepaged completely breaks userfaultfd+shmem. The rework of collapse_file provides a convenient place to check for registered userfaultfds without making the shmem userfaultfd implementation care about khugepaged. Finally, this series adds a lru_add_drain after swapping in shmem pages, which makes the subsequent folio_isolate_lru significantly more likely to succeed. This patch (of 4): Call lru_add_drain after swapping in shmem pages so that isolate_lru_page is more likely to succeed. Link: https://lkml.kernel.org/r/20230404120117.2562166-1-stevensd@google.com Link: https://lkml.kernel.org/r/20230404120117.2562166-2-stevensd@google.com Signed-off-by: David Stevens Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jiaqi Yan Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/khugepaged.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index deea5c5cd9e8..d92b61423c6b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1967,6 +1967,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, result = SCAN_FAIL; goto xa_unlocked; } + /* drain pagevecs to help isolate_lru_page() */ + lru_add_drain(); page = folio_file_page(folio, index); } else if (trylock_page(page)) { get_page(page); -- GitLab From cae106dd67b99a65d117a9f6c977a86b120dad61 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 4 Apr 2023 21:01:15 +0900 Subject: [PATCH 3250/5631] mm/khugepaged: refactor collapse_file control flow Add a rollback label to deal with failure, instead of continuously checking for RESULT_SUCCESS, to make it easier to add more failure cases. The refactoring also allows the collapse_file tracepoint to include hpage on success (instead of NULL). Link: https://lkml.kernel.org/r/20230404120117.2562166-3-stevensd@google.com Signed-off-by: David Stevens Acked-by: Peter Xu Reviewed-by: Yang Shi Acked-by: Hugh Dickins Cc: David Hildenbrand Cc: Jiaqi Yan Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/khugepaged.c | 230 ++++++++++++++++++++++++------------------------ 1 file changed, 113 insertions(+), 117 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index d92b61423c6b..762877539634 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1894,6 +1894,12 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, if (result != SCAN_SUCCEED) goto out; + __SetPageLocked(hpage); + if (is_shmem) + __SetPageSwapBacked(hpage); + hpage->index = start; + hpage->mapping = mapping; + /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present @@ -1906,16 +1912,10 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; - goto out; + goto rollback; } } while (1); - __SetPageLocked(hpage); - if (is_shmem) - __SetPageSwapBacked(hpage); - hpage->index = start; - hpage->mapping = mapping; - /* * At this point the hpage is locked and not up-to-date. * It's safe to insert it into the page cache, because nobody would @@ -2152,137 +2152,133 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, */ try_to_unmap_flush(); - if (result == SCAN_SUCCEED) { - /* - * Replacing old pages with new one has succeeded, now we - * attempt to copy the contents. - */ - index = start; - list_for_each_entry(page, &pagelist, lru) { - while (index < page->index) { - clear_highpage(hpage + (index % HPAGE_PMD_NR)); - index++; - } - if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), - page) > 0) { - result = SCAN_COPY_MC; - break; - } - index++; - } - while (result == SCAN_SUCCEED && index < end) { + if (result != SCAN_SUCCEED) + goto rollback; + + /* + * Replacing old pages with new one has succeeded, now we + * attempt to copy the contents. + */ + index = start; + list_for_each_entry(page, &pagelist, lru) { + while (index < page->index) { clear_highpage(hpage + (index % HPAGE_PMD_NR)); index++; } + if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR), page) > 0) { + result = SCAN_COPY_MC; + goto rollback; + } + index++; + } + while (index < end) { + clear_highpage(hpage + (index % HPAGE_PMD_NR)); + index++; + } + + /* + * Copying old pages to huge one has succeeded, now we + * need to free the old pages. + */ + list_for_each_entry_safe(page, tmp, &pagelist, lru) { + list_del(&page->lru); + page->mapping = NULL; + page_ref_unfreeze(page, 1); + ClearPageActive(page); + ClearPageUnevictable(page); + unlock_page(page); + put_page(page); } nr = thp_nr_pages(hpage); - if (result == SCAN_SUCCEED) { - /* - * Copying old pages to huge one has succeeded, now we - * need to free the old pages. - */ - list_for_each_entry_safe(page, tmp, &pagelist, lru) { - list_del(&page->lru); - page->mapping = NULL; - page_ref_unfreeze(page, 1); - ClearPageActive(page); - ClearPageUnevictable(page); - unlock_page(page); - put_page(page); - } + xas_lock_irq(&xas); + if (is_shmem) + __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); + else + __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr); - xas_lock_irq(&xas); - if (is_shmem) - __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); - else - __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr); + if (nr_none) { + __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none); + /* nr_none is always 0 for non-shmem. */ + __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); + } + /* Join all the small entries into a single multi-index entry. */ + xas_set_order(&xas, start, HPAGE_PMD_ORDER); + xas_store(&xas, hpage); + xas_unlock_irq(&xas); - if (nr_none) { - __mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none); - /* nr_none is always 0 for non-shmem. */ - __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); - } - /* Join all the small entries into a single multi-index entry. */ - xas_set_order(&xas, start, HPAGE_PMD_ORDER); - xas_store(&xas, hpage); - xas_unlock_irq(&xas); + folio = page_folio(hpage); + folio_mark_uptodate(folio); + folio_ref_add(folio, HPAGE_PMD_NR - 1); - folio = page_folio(hpage); - folio_mark_uptodate(folio); - folio_ref_add(folio, HPAGE_PMD_NR - 1); + if (is_shmem) + folio_mark_dirty(folio); + folio_add_lru(folio); - if (is_shmem) - folio_mark_dirty(folio); - folio_add_lru(folio); + /* + * Remove pte page tables, so we can re-fault the page as huge. + */ + result = retract_page_tables(mapping, start, mm, addr, hpage, + cc); + unlock_page(hpage); + goto out; + +rollback: + /* Something went wrong: roll back page cache changes */ + xas_lock_irq(&xas); + if (nr_none) { + mapping->nrpages -= nr_none; + shmem_uncharge(mapping->host, nr_none); + } - /* - * Remove pte page tables, so we can re-fault the page as huge. - */ - result = retract_page_tables(mapping, start, mm, addr, hpage, - cc); - unlock_page(hpage); - hpage = NULL; - } else { - /* Something went wrong: roll back page cache changes */ - xas_lock_irq(&xas); - if (nr_none) { - mapping->nrpages -= nr_none; - shmem_uncharge(mapping->host, nr_none); + xas_set(&xas, start); + xas_for_each(&xas, page, end - 1) { + page = list_first_entry_or_null(&pagelist, + struct page, lru); + if (!page || xas.xa_index < page->index) { + if (!nr_none) + break; + nr_none--; + /* Put holes back where they were */ + xas_store(&xas, NULL); + continue; } - xas_set(&xas, start); - xas_for_each(&xas, page, end - 1) { - page = list_first_entry_or_null(&pagelist, - struct page, lru); - if (!page || xas.xa_index < page->index) { - if (!nr_none) - break; - nr_none--; - /* Put holes back where they were */ - xas_store(&xas, NULL); - continue; - } + VM_BUG_ON_PAGE(page->index != xas.xa_index, page); - VM_BUG_ON_PAGE(page->index != xas.xa_index, page); - - /* Unfreeze the page. */ - list_del(&page->lru); - page_ref_unfreeze(page, 2); - xas_store(&xas, page); - xas_pause(&xas); - xas_unlock_irq(&xas); - unlock_page(page); - putback_lru_page(page); - xas_lock_irq(&xas); - } - VM_BUG_ON(nr_none); + /* Unfreeze the page. */ + list_del(&page->lru); + page_ref_unfreeze(page, 2); + xas_store(&xas, page); + xas_pause(&xas); + xas_unlock_irq(&xas); + unlock_page(page); + putback_lru_page(page); + xas_lock_irq(&xas); + } + VM_BUG_ON(nr_none); + /* + * Undo the updates of filemap_nr_thps_inc for non-SHMEM + * file only. This undo is not needed unless failure is + * due to SCAN_COPY_MC. + */ + if (!is_shmem && result == SCAN_COPY_MC) { + filemap_nr_thps_dec(mapping); /* - * Undo the updates of filemap_nr_thps_inc for non-SHMEM - * file only. This undo is not needed unless failure is - * due to SCAN_COPY_MC. + * Paired with smp_mb() in do_dentry_open() to + * ensure the update to nr_thps is visible. */ - if (!is_shmem && result == SCAN_COPY_MC) { - filemap_nr_thps_dec(mapping); - /* - * Paired with smp_mb() in do_dentry_open() to - * ensure the update to nr_thps is visible. - */ - smp_mb(); - } + smp_mb(); + } - xas_unlock_irq(&xas); + xas_unlock_irq(&xas); - hpage->mapping = NULL; - } + hpage->mapping = NULL; - if (hpage) - unlock_page(hpage); + unlock_page(hpage); + put_page(hpage); out: VM_BUG_ON(!list_empty(&pagelist)); - if (hpage) - put_page(hpage); - trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result); return result; } -- GitLab From ac492b9c70cac4d887e9dce4410b1d521851e142 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 4 Apr 2023 21:01:16 +0900 Subject: [PATCH 3251/5631] mm/khugepaged: skip shmem with userfaultfd Make sure that collapse_file respects any userfaultfds registered with MODE_MISSING. If userspace has any such userfaultfds registered, then for any page which it knows to be missing, it may expect a UFFD_EVENT_PAGEFAULT. This means collapse_file needs to be careful when collapsing a shmem range would result in replacing an empty page with a THP, to avoid breaking userfaultfd. Synchronization when checking for userfaultfds in collapse_file is tricky because the mmap locks can't be used to prevent races with the registration of new userfaultfds. Instead, we provide synchronization by ensuring that userspace cannot observe the fact that pages are missing before we check for userfaultfds. Although this allows registration of a userfaultfd to race with collapse_file, it ensures that userspace cannot observe any pages transition from missing to present after such a race occurs. This makes such a race indistinguishable to the collapse occurring immediately before the userfaultfd registration. The first step to provide this synchronization is to stop filling gaps during the loop iterating over the target range, since the page cache lock can be dropped during that loop. The second step is to fill the gaps with XA_RETRY_ENTRY after the page cache lock is acquired the final time, to avoid races with accesses to the page cache that only take the RCU read lock. The fact that we don't fill holes during the initial iteration means that collapse_file now has to handle faults occurring during the collapse. This is done by re-validating the number of missing pages after acquiring the page cache lock for the final time. This fix is targeted at khugepaged, but the change also applies to MADV_COLLAPSE. MADV_COLLAPSE on a range with a userfaultfd will now return EBUSY if there are any missing pages (instead of succeeding on shmem and returning EINVAL on anonymous memory). There is also now a window during MADV_COLLAPSE where a fault on a missing page will cause the syscall to fail with EAGAIN. The fact that intermediate page cache state can no longer be observed before the rollback of a failed collapse is also technically a userspace-visible change (via at least SEEK_DATA and SEEK_END), but it is exceedingly unlikely that anything relies on being able to observe that transient state. Link: https://lkml.kernel.org/r/20230404120117.2562166-4-stevensd@google.com Signed-off-by: David Stevens Acked-by: Peter Xu Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jiaqi Yan Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Cc: Yang Shi Signed-off-by: Andrew Morton --- include/trace/events/huge_memory.h | 3 +- mm/khugepaged.c | 99 ++++++++++++++++++++++++------ 2 files changed, 81 insertions(+), 21 deletions(-) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index eca4c6f3625e..6e2ef1d4b002 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -38,7 +38,8 @@ EM( SCAN_TRUNCATED, "truncated") \ EM( SCAN_PAGE_HAS_PRIVATE, "page_has_private") \ EM( SCAN_STORE_FAILED, "store_failed") \ - EMe(SCAN_COPY_MC, "copy_poisoned_page") + EM( SCAN_COPY_MC, "copy_poisoned_page") \ + EMe(SCAN_PAGE_FILLED, "page_filled") #undef EM #undef EMe diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 762877539634..434674ca0c8a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -57,6 +57,7 @@ enum scan_result { SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, + SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS @@ -1860,8 +1861,8 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * - allocate and lock a new huge page; * - scan page cache replacing old pages with the new one * + swap/gup in pages if necessary; - * + fill in gaps; * + keep old pages around in case rollback is required; + * - finalize updates to the page cache; * - if replacing succeeds: * + copy data over; * + free old pages; @@ -1939,7 +1940,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, result = SCAN_TRUNCATED; goto xa_locked; } - xas_set(&xas, index); + xas_set(&xas, index + 1); } if (!shmem_charge(mapping->host, 1)) { result = SCAN_FAIL; @@ -2176,22 +2177,66 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, index++; } - /* - * Copying old pages to huge one has succeeded, now we - * need to free the old pages. - */ - list_for_each_entry_safe(page, tmp, &pagelist, lru) { - list_del(&page->lru); - page->mapping = NULL; - page_ref_unfreeze(page, 1); - ClearPageActive(page); - ClearPageUnevictable(page); - unlock_page(page); - put_page(page); + if (nr_none) { + struct vm_area_struct *vma; + int nr_none_check = 0; + + i_mmap_lock_read(mapping); + xas_lock_irq(&xas); + + xas_set(&xas, start); + for (index = start; index < end; index++) { + if (!xas_next(&xas)) { + xas_store(&xas, XA_RETRY_ENTRY); + if (xas_error(&xas)) { + result = SCAN_STORE_FAILED; + goto immap_locked; + } + nr_none_check++; + } + } + + if (nr_none != nr_none_check) { + result = SCAN_PAGE_FILLED; + goto immap_locked; + } + + /* + * If userspace observed a missing page in a VMA with a MODE_MISSING + * userfaultfd, then it might expect a UFFD_EVENT_PAGEFAULT for that + * page. If so, we need to roll back to avoid suppressing such an + * event. Since wp/minor userfaultfds don't give userspace any + * guarantees that the kernel doesn't fill a missing page with a zero + * page, so they don't matter here. + * + * Any userfaultfds registered after this point will not be able to + * observe any missing pages due to the previously inserted retry + * entries. + */ + vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { + if (userfaultfd_missing(vma)) { + result = SCAN_EXCEED_NONE_PTE; + goto immap_locked; + } + } + +immap_locked: + i_mmap_unlock_read(mapping); + if (result != SCAN_SUCCEED) { + xas_set(&xas, start); + for (index = start; index < end; index++) { + if (xas_next(&xas) == XA_RETRY_ENTRY) + xas_store(&xas, NULL); + } + + xas_unlock_irq(&xas); + goto rollback; + } + } else { + xas_lock_irq(&xas); } nr = thp_nr_pages(hpage); - xas_lock_irq(&xas); if (is_shmem) __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr); else @@ -2221,6 +2266,20 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, result = retract_page_tables(mapping, start, mm, addr, hpage, cc); unlock_page(hpage); + + /* + * The collapse has succeeded, so free the old pages. + */ + list_for_each_entry_safe(page, tmp, &pagelist, lru) { + list_del(&page->lru); + page->mapping = NULL; + page_ref_unfreeze(page, 1); + ClearPageActive(page); + ClearPageUnevictable(page); + unlock_page(page); + put_page(page); + } + goto out; rollback: @@ -2232,15 +2291,13 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } xas_set(&xas, start); - xas_for_each(&xas, page, end - 1) { + end = index; + for (index = start; index < end; index++) { + xas_next(&xas); page = list_first_entry_or_null(&pagelist, struct page, lru); if (!page || xas.xa_index < page->index) { - if (!nr_none) - break; nr_none--; - /* Put holes back where they were */ - xas_store(&xas, NULL); continue; } @@ -2764,12 +2821,14 @@ static int madvise_collapse_errno(enum scan_result r) case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: + case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: + case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to -- GitLab From a2e17cc2efc72792c0d13d669d824fe9ab7155a1 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Tue, 4 Apr 2023 21:01:17 +0900 Subject: [PATCH 3252/5631] mm/khugepaged: maintain page cache uptodate flag Make sure that collapse_file doesn't interfere with checking the uptodate flag in the page cache by only inserting hpage into the page cache after it has been updated and marked uptodate. This is achieved by simply not replacing present pages with hpage when iterating over the target range. The present pages are already locked, so replacing them with the locked hpage before the collapse is finalized is unnecessary. However, it is necessary to stop freezing the present pages after validating them, since leaving long-term frozen pages in the page cache can lead to deadlocks. Simply checking the reference count is sufficient to ensure that there are no long-term references hanging around that would the collapse would break. Similar to hpage, there is no reason that the present pages actually need to be frozen in addition to being locked. This fixes a race where folio_seek_hole_data would mistake hpage for an fallocated but unwritten page. This race is visible to userspace via data temporarily disappearing from SEEK_DATA/SEEK_HOLE. This also fixes a similar race where pages could temporarily disappear from mincore. Link: https://lkml.kernel.org/r/20230404120117.2562166-5-stevensd@google.com Fixes: f3f0e1d2150b ("khugepaged: add support of collapse for tmpfs/shmem pages") Signed-off-by: David Stevens Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jiaqi Yan Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Yang Shi Signed-off-by: Andrew Morton --- mm/khugepaged.c | 85 +++++++++++++++++++------------------------------ 1 file changed, 33 insertions(+), 52 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 434674ca0c8a..d72e74e007fc 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1859,17 +1859,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; - * - scan page cache replacing old pages with the new one + * - scan page cache, locking old pages * + swap/gup in pages if necessary; - * + keep old pages around in case rollback is required; + * - copy data to new page + * - handle shmem holes + * + re-validate that holes weren't filled by someone else + * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: - * + copy data over; - * + free old pages; * + unlock huge page; + * + free old pages; * - if replacing failed; - * + put all pages back and unfreeze them; - * + restore gaps in the page cache; + * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, @@ -1917,12 +1918,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } } while (1); - /* - * At this point the hpage is locked and not up-to-date. - * It's safe to insert it into the page cache, because nobody would - * be able to map it or use it in another way until we unlock it. - */ - xas_set(&xas, start); for (index = start; index < end; index++) { page = xas_next(&xas); @@ -2090,12 +2085,16 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, VM_BUG_ON_PAGE(page != xas_load(&xas), page); /* - * The page is expected to have page_count() == 3: + * We control three references to the page: * - we hold a pin on it; * - one reference from page cache; * - one from isolate_lru_page; + * If those are the only references, then any new usage of the + * page will have to fetch it from the page cache. That requires + * locking the page to handle truncate, so any new usage will be + * blocked until we unlock page after collapse/during rollback. */ - if (!page_ref_freeze(page, 3)) { + if (page_count(page) != 3) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); putback_lru_page(page); @@ -2103,16 +2102,14 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } /* - * Add the page to the list to be able to undo the collapse if - * something go wrong. + * Accumulate the pages that are being collapsed. */ list_add_tail(&page->lru, &pagelist); - /* Finally, replace with the new page. */ - xas_store(&xas, hpage); - /* We can't get an ENOMEM here (because the allocation happened before) - * but let's check for errors (XArray implementation can be - * changed in the future) + /* + * We can't get an ENOMEM here (because the allocation happened + * before) but let's check for errors (XArray implementation + * can be changed in the future) */ WARN_ON_ONCE(xas_error(&xas)); continue; @@ -2157,8 +2154,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto rollback; /* - * Replacing old pages with new one has succeeded, now we - * attempt to copy the contents. + * The old pages are locked, so they won't change anymore. */ index = start; list_for_each_entry(page, &pagelist, lru) { @@ -2247,11 +2243,11 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, /* nr_none is always 0 for non-shmem. */ __mod_lruvec_page_state(hpage, NR_SHMEM, nr_none); } - /* Join all the small entries into a single multi-index entry. */ - xas_set_order(&xas, start, HPAGE_PMD_ORDER); - xas_store(&xas, hpage); - xas_unlock_irq(&xas); + /* + * Mark hpage as uptodate before inserting it into the page cache so + * that it isn't mistaken for an fallocated but unwritten page. + */ folio = page_folio(hpage); folio_mark_uptodate(folio); folio_ref_add(folio, HPAGE_PMD_NR - 1); @@ -2260,6 +2256,11 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, folio_mark_dirty(folio); folio_add_lru(folio); + /* Join all the small entries into a single multi-index entry. */ + xas_set_order(&xas, start, HPAGE_PMD_ORDER); + xas_store(&xas, hpage); + xas_unlock_irq(&xas); + /* * Remove pte page tables, so we can re-fault the page as huge. */ @@ -2273,47 +2274,29 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, list_for_each_entry_safe(page, tmp, &pagelist, lru) { list_del(&page->lru); page->mapping = NULL; - page_ref_unfreeze(page, 1); ClearPageActive(page); ClearPageUnevictable(page); unlock_page(page); - put_page(page); + folio_put_refs(page_folio(page), 3); } goto out; rollback: /* Something went wrong: roll back page cache changes */ - xas_lock_irq(&xas); if (nr_none) { + xas_lock_irq(&xas); mapping->nrpages -= nr_none; shmem_uncharge(mapping->host, nr_none); + xas_unlock_irq(&xas); } - xas_set(&xas, start); - end = index; - for (index = start; index < end; index++) { - xas_next(&xas); - page = list_first_entry_or_null(&pagelist, - struct page, lru); - if (!page || xas.xa_index < page->index) { - nr_none--; - continue; - } - - VM_BUG_ON_PAGE(page->index != xas.xa_index, page); - - /* Unfreeze the page. */ + list_for_each_entry_safe(page, tmp, &pagelist, lru) { list_del(&page->lru); - page_ref_unfreeze(page, 2); - xas_store(&xas, page); - xas_pause(&xas); - xas_unlock_irq(&xas); unlock_page(page); putback_lru_page(page); - xas_lock_irq(&xas); + put_page(page); } - VM_BUG_ON(nr_none); /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is @@ -2328,8 +2311,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, smp_mb(); } - xas_unlock_irq(&xas); - hpage->mapping = NULL; unlock_page(hpage); -- GitLab From 6b0ba2abbeede5e1756d54277e811cf2783eb0a8 Mon Sep 17 00:00:00 2001 From: Florian Schmidt Date: Tue, 4 Apr 2023 10:58:59 +0000 Subject: [PATCH 3253/5631] memcg v1: provide read access to memory.pressure_level cgroups v1 has a unique way of setting up memory pressure notifications: the user opens "memory.pressure_level" of the cgroup they want to monitor for pressure, then open "cgroup.event_control" and write the fd (among other things) to that file. memory.pressure_level has no other use, specifically it does not support any read or write operations. Consequently, no handlers are provided, and cgroup_file_mode() sets the permissions to 000. However, to actually use the mechanism, the subscribing user must have read access to the file and open the fd for reading, see memcg_write_event_control(). This is all fine as long as the subscribing process runs as root and is otherwise unconfined by further restrictions. However, if you add strict access controls such as selinux, the permission bits will be enforced, and opening memory.pressure_level for reading will fail, preventing the process from subscribing, even as root. To work around this issue, introduce a dummy read handler. When memory.pressure_level is created, cgroup_file_mode() will notice the existence of a handler, and therefore add read permissions to the file. Link: https://lkml.kernel.org/r/20230404105900.2005-1-flosch@nutanix.com Signed-off-by: Florian Schmidt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Muchun Song Cc: Roman Gushchin Cc: Shakeel Butt Signed-off-by: Andrew Morton --- mm/memcontrol.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3d040a5fa7a3..cb17f3abdfe0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3779,6 +3779,16 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } +/* + * This function doesn't do anything useful. Its only job is to provide a read + * handler for a file so that cgroup_file_mode() will add read permissions. + */ +static int mem_cgroup_dummy_seq_show(__always_unused struct seq_file *m, + __always_unused void *v) +{ + return -EINVAL; +} + #ifdef CONFIG_MEMCG_KMEM static int memcg_online_kmem(struct mem_cgroup *memcg) { @@ -5113,6 +5123,7 @@ static struct cftype mem_cgroup_legacy_files[] = { }, { .name = "pressure_level", + .seq_show = mem_cgroup_dummy_seq_show, }, #ifdef CONFIG_NUMA { -- GitLab From 92d5df38ca91f138d4964d71a6835add95f99e59 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Tue, 4 Apr 2023 17:45:15 +0800 Subject: [PATCH 3254/5631] mm/madvise: use vma_lookup() instead of find_vma() Using vma_lookup() verifies the address is contained in the found vma. This results in easier to read the code. Link: https://lkml.kernel.org/r/20230404094515.1883552-1-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- mm/madvise.c | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/mm/madvise.c b/mm/madvise.c index 340125d08c03..405a2c4a0a18 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -852,21 +852,9 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, *prev = NULL; /* mmap_lock has been dropped, prev is stale */ mmap_read_lock(mm); - vma = find_vma(mm, start); + vma = vma_lookup(mm, start); if (!vma) return -ENOMEM; - if (start < vma->vm_start) { - /* - * This "vma" under revalidation is the one - * with the lowest vma->vm_start where start - * is also < vma->vm_end. If start < - * vma->vm_start it means an hole materialized - * in the user address space within the - * virtual range passed to MADV_DONTNEED - * or MADV_FREE. - */ - return -ENOMEM; - } /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. -- GitLab From 9bc47f11525fb666a370063888904160188b024e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 4 Apr 2023 10:56:36 +0200 Subject: [PATCH 3255/5631] m68k/mm: use correct bit number in _PAGE_SWP_EXCLUSIVE comment As noticed by Geert, commit b5c88f21531c ("microblaze/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE") modified m68k code by accident. While replacing 0x080 by CF_PAGE_NOCACHE is correct, although it should have been part of commit ed4154067a08 ("m68k/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE"), replacing "bit 7" by "bit 24" in the comment was wrong. Let's revert to the previous, correct, comment. Link: https://lkml.kernel.org/r/20230404085636.121409-1-david@redhat.com Signed-off-by: David Hildenbrand Reported-by: Geert Uytterhoeven Signed-off-by: Andrew Morton --- arch/m68k/include/asm/mcf_pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h index 13741c1245e1..d97fbb812f63 100644 --- a/arch/m68k/include/asm/mcf_pgtable.h +++ b/arch/m68k/include/asm/mcf_pgtable.h @@ -46,7 +46,7 @@ #define _CACHEMASK040 (~0x060) #define _PAGE_GLOBAL040 0x400 /* 68040 global bit, used for kva descs */ -/* We borrow bit 24 to store the exclusive marker in swap PTEs. */ +/* We borrow bit 7 to store the exclusive marker in swap PTEs. */ #define _PAGE_SWP_EXCLUSIVE CF_PAGE_NOCACHE /* -- GitLab From 97f7e09481f312b143db53cadbdfe81abac97e73 Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Tue, 14 Mar 2023 20:42:02 +0800 Subject: [PATCH 3256/5631] maple_tree: simplify mas_wr_node_walk() Simplify code of mas_wr_node_walk() without changing functionality, and improve readability. Remove some special judgments. Instead of dynamically recording the min and max in the loop, get the final min and max directly at the end. Link: https://lkml.kernel.org/r/20230314124203.91572-3-zhangpeng.00@bytedance.com Signed-off-by: Peng Zhang Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- lib/maple_tree.c | 34 +++++----------------------------- 1 file changed, 5 insertions(+), 29 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 4a6ecdb12a92..f475bac9d914 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -2312,9 +2312,7 @@ static inline struct maple_enode *mte_node_or_none(struct maple_enode *enode) static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; - unsigned char count; - unsigned char offset; - unsigned long index, min, max; + unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; @@ -2327,34 +2325,12 @@ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) count = wr_mas->node_end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; - min = mas_safe_min(mas, wr_mas->pivots, offset); - if (unlikely(offset == count)) - goto max; - - max = wr_mas->pivots[offset]; - index = mas->index; - if (unlikely(index <= max)) - goto done; - - if (unlikely(!max && offset)) - goto max; - min = max + 1; - while (++offset < count) { - max = wr_mas->pivots[offset]; - if (index <= max) - goto done; - else if (unlikely(!max)) - break; - - min = max + 1; - } + while (offset < count && mas->index > wr_mas->pivots[offset]) + offset++; -max: - max = mas->max; -done: - wr_mas->r_max = max; - wr_mas->r_min = min; + wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; + wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } -- GitLab From ddc65971bb677aa9f6a4c21f76d3133e106f88eb Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Tue, 4 Apr 2023 21:31:48 +0900 Subject: [PATCH 3257/5631] prctl: add PR_GET_AUXV to copy auxv to userspace If a library wants to get information from auxv (for instance, AT_HWCAP/AT_HWCAP2), it has a few options, none of them perfectly reliable or ideal: - Be main or the pre-main startup code, and grub through the stack above main. Doesn't work for a library. - Call libc getauxval. Not ideal for libraries that are trying to be libc-independent and/or don't otherwise require anything from other libraries. - Open and read /proc/self/auxv. Doesn't work for libraries that may run in arbitrarily constrained environments that may not have /proc mounted (e.g. libraries that might be used by an init program or a container setup tool). - Assume you're on the main thread and still on the original stack, and try to walk the stack upwards, hoping to find auxv. Extremely bad idea. - Ask the caller to pass auxv in for you. Not ideal for a user-friendly library, and then your caller may have the same problem. Add a prctl that copies current->mm->saved_auxv to a userspace buffer. Link: https://lkml.kernel.org/r/d81864a7f7f43bca6afa2a09fc2e850e4050ab42.1680611394.git.josh@joshtriplett.org Signed-off-by: Josh Triplett Signed-off-by: Andrew Morton --- include/uapi/linux/prctl.h | 2 ++ kernel/sys.c | 15 +++++++++++++++ 2 files changed, 17 insertions(+) diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 1312a137f7fb..b99c0be72577 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -290,4 +290,6 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 351de7916302..26c1399e0654 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2388,6 +2388,16 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, PR_MDWE_REFUSE_EXEC_GAIN : 0; } +static int prctl_get_auxv(void __user *addr, unsigned long len) +{ + struct mm_struct *mm = current->mm; + unsigned long size = min_t(unsigned long, sizeof(mm->saved_auxv), len); + + if (size && copy_to_user(addr, mm->saved_auxv, size)) + return -EFAULT; + return sizeof(mm->saved_auxv); +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2518,6 +2528,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, else return -EINVAL; break; + case PR_GET_AUXV: + if (arg4 || arg5) + return -EINVAL; + error = prctl_get_auxv((void __user *)arg2, arg3); + break; default: return -EINVAL; } -- GitLab From 2bd7f621130b47cab8bed82234cac1f9f105efb7 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Thu, 6 Apr 2023 00:18:54 +0800 Subject: [PATCH 3258/5631] mm: mlock: use folios_put() in mlock_folio_batch() Since we have updated mlock to use folios, it's better to call folios_put() instead of calling release_pages() directly. Link: https://lkml.kernel.org/r/20230405161854.6931-2-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Acked-by: Mel Gorman Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/mlock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mlock.c b/mm/mlock.c index 617469fce96d..40b43f8740df 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -206,7 +206,7 @@ static void mlock_folio_batch(struct folio_batch *fbatch) if (lruvec) unlock_page_lruvec_irq(lruvec); - release_pages(fbatch->folios, fbatch->nr); + folios_put(fbatch->folios, folio_batch_count(fbatch)); folio_batch_reinit(fbatch); } -- GitLab From 27da93d8e6d5633ac065c9316afc0f0240303c0a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 5 Apr 2023 18:02:36 +0200 Subject: [PATCH 3259/5631] mm/userfaultfd: don't consider uffd-wp bit of writable migration entries If we end up with a writable migration entry that has the uffd-wp bit set, we already messed up: the source PTE/PMD was writable, which means we could have modified the page without notifying uffd first. Setting the uffd-wp bit always implies converting migration entries to !writable migration entries. Commit 8f34f1eac382 ("mm/userfaultfd: fix uffd-wp special cases for fork()") documents that "3. Forget to carry over uffd-wp bit for a write migration huge pmd entry", but it doesn't really say why that should be relevant. So let's remove that code to avoid hiding an eventual underlying issue (in the future, we might want to warn when creating writable migration entries that have the uffd-wp bit set -- or even better when turning a PTE writable that still has the uffd-wp bit set). This now matches the handling for hugetlb migration entries in hugetlb_change_protection(). In copy_huge_pmd()/copy_nonpresent_pte()/copy_hugetlb_page_range(), we still transfer the uffd-bit also for writable migration entries, but simply because we have unified handling for "writable" and "readable-exclusive" migration entries, and we care about transferring the uffd-wp bit for the latter. Link: https://lkml.kernel.org/r/20230405160236.587705-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Peter Xu Cc: Muhammad Usama Anjum Signed-off-by: Andrew Morton --- mm/huge_memory.c | 2 -- mm/mprotect.c | 2 -- 2 files changed, 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 03d78901a7a7..0dbce09916c4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1845,8 +1845,6 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); - if (pmd_swp_uffd_wp(*pmd)) - newpmd = pmd_swp_mkuffd_wp(newpmd); } else { newpmd = *pmd; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 204194155863..92d3d3ca390a 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -223,8 +223,6 @@ static long change_pte_range(struct mmu_gather *tlb, newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); - if (pte_swp_uffd_wp(oldpte)) - newpte = pte_swp_mkuffd_wp(newpte); } else if (is_writable_device_private_entry(entry)) { /* * We do not preserve soft-dirtiness. See -- GitLab From 8666925c498674426de44ecba79fd8bf42d3cda3 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 5 Apr 2023 16:28:40 +0200 Subject: [PATCH 3260/5631] mm, page_alloc: use check_pages_enabled static key to check tail pages Commit 700d2e9a36b9 ("mm, page_alloc: reduce page alloc/free sanity checks") has introduced a new static key check_pages_enabled to control when struct pages are sanity checked during allocation and freeing. Mel Gorman suggested that free_tail_pages_check() could use this static key as well, instead of relying on CONFIG_DEBUG_VM. That makes sense, so do that. Also rename the function to free_tail_page_prepare() because it works on a single tail page and has a struct page preparation component as well as the optional checking component. Also remove some unnecessary unlikely() within static_branch_unlikely() statements that Mel pointed out for commit 700d2e9a36b9. Link: https://lkml.kernel.org/r/20230405142840.11068-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Suggested-by: Mel Gorman Acked-by: Mel Gorman Cc: Alexander Halbuer Cc: Kees Cook Signed-off-by: Andrew Morton --- mm/hugetlb_vmemmap.c | 2 +- mm/page_alloc.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 1198064f80eb..27f001e0f0a2 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -264,7 +264,7 @@ static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, * How many struct page structs need to be reset. When we reuse the head * struct page, the special metadata (e.g. page->flags or page->mapping) * cannot copy to the tail struct page structs. The invalid value will be - * checked in the free_tail_pages_check(). In order to avoid the message + * checked in the free_tail_page_prepare(). In order to avoid the message * of "corrupted mapping in tail page". We need to reset at least 3 (one * head struct page struct and two tail struct page structs) struct page * structs. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9c325e5e6b15..6da423ec356f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1131,7 +1131,7 @@ static inline bool free_page_is_bad(struct page *page) return true; } -static int free_tail_pages_check(struct page *head_page, struct page *page) +static int free_tail_page_prepare(struct page *head_page, struct page *page) { struct folio *folio = (struct folio *)head_page; int ret = 1; @@ -1142,7 +1142,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) */ BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); - if (!IS_ENABLED(CONFIG_DEBUG_VM)) { + if (!static_branch_unlikely(&check_pages_enabled)) { ret = 0; goto out; } @@ -1276,9 +1276,9 @@ static __always_inline bool free_pages_prepare(struct page *page, ClearPageHasHWPoisoned(page); for (i = 1; i < (1 << order); i++) { if (compound) - bad += free_tail_pages_check(page, page + i); + bad += free_tail_page_prepare(page, page + i); if (is_check_pages_enabled()) { - if (unlikely(free_page_is_bad(page + i))) { + if (free_page_is_bad(page + i)) { bad++; continue; } @@ -1627,7 +1627,7 @@ static inline bool check_new_pages(struct page *page, unsigned int order) for (int i = 0; i < (1 << order); i++) { struct page *p = page + i; - if (unlikely(check_new_page(p))) + if (check_new_page(p)) return true; } } -- GitLab From b4aca54792e76556bb9f8661bab07b4bf2eb4e5f Mon Sep 17 00:00:00 2001 From: Steven Price Date: Wed, 5 Apr 2023 11:38:19 +0100 Subject: [PATCH 3261/5631] smaps: fix defined but not used smaps_shmem_walk_ops MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When !CONFIG_SHMEM smaps_shmem_walk_ops is defined but not used, triggering a compiler warning. To avoid the warning remove the #ifdef around the usage. This has no effect because shmem_mapping() is a stub returning false when !CONFIG_SHMEM so the code will be compiled out, however we now need to also provide a stub for shmem_swap_usage(). Link: https://lkml.kernel.org/r/20230405103819.151246-1-steven.price@arm.com Fixes: 7b86ac3371b7 ("pagewalk: separate function pointers from iterator data") Signed-off-by: Steven Price Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304031749.UiyJpxzF-lkp@intel.com/ Reviewed-by: Jason Gunthorpe Cc: Christoph Hellwig Cc: Alexey Dobriyan Cc: Thomas Hellström Signed-off-by: Andrew Morton --- fs/proc/task_mmu.c | 3 +-- include/linux/shmem_fs.h | 7 +++++++ 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6a96e1713fd5..cb49479acd2e 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -782,7 +782,6 @@ static void smap_gather_stats(struct vm_area_struct *vma, if (start >= vma->vm_end) return; -#ifdef CONFIG_SHMEM if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { /* * For shared or readonly shmem mappings we know that all @@ -803,7 +802,7 @@ static void smap_gather_stats(struct vm_area_struct *vma, ops = &smaps_shmem_walk_ops; } } -#endif + /* mmap_lock is held in m_start */ if (!start) walk_page_vma(vma, ops, mss); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3bb8d21edbb3..b9516a9802bf 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -96,7 +96,14 @@ int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +#else +static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + return 0; +} +#endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); -- GitLab From 07e6d4095c75bcf0bf511b36eecaceb3fbb91ad9 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:27 +0800 Subject: [PATCH 3262/5631] userfaultfd: convert mfill_atomic_pte_copy() to use a folio Patch series "userfaultfd: convert userfaultfd functions to use folios", v6. This patch series converts several userfaultfd functions to use folios. This patch (of 6): Call vma_alloc_folio() directly instead of alloc_page_vma() and convert page_kaddr to kaddr in mfill_atomic_pte_copy(). Removes several calls to compound_head(). Link: https://lkml.kernel.org/r/20230410133932.32288-1-zhangpeng362@huawei.com Link: https://lkml.kernel.org/r/20230410133932.32288-2-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 7f1b5f8b712c..313bc683c2b6 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -135,17 +135,18 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, uffd_flags_t flags, struct page **pagep) { - void *page_kaddr; + void *kaddr; int ret; - struct page *page; + struct folio *folio; if (!*pagep) { ret = -ENOMEM; - page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr); - if (!page) + folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, dst_vma, + dst_addr, false); + if (!folio) goto out; - page_kaddr = kmap_local_page(page); + kaddr = kmap_local_folio(folio, 0); /* * The read mmap_lock is held here. Despite the * mmap_lock being read recursive a deadlock is still @@ -162,45 +163,44 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, * and retry the copy outside the mmap_lock. */ pagefault_disable(); - ret = copy_from_user(page_kaddr, - (const void __user *) src_addr, + ret = copy_from_user(kaddr, (const void __user *) src_addr, PAGE_SIZE); pagefault_enable(); - kunmap_local(page_kaddr); + kunmap_local(kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; - *pagep = page; + *pagep = &folio->page; /* don't free the page */ goto out; } - flush_dcache_page(page); + flush_dcache_folio(folio); } else { - page = *pagep; + folio = page_folio(*pagep); *pagep = NULL; } /* - * The memory barrier inside __SetPageUptodate makes sure that + * The memory barrier inside __folio_mark_uptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ - __SetPageUptodate(page); + __folio_mark_uptodate(folio); ret = -ENOMEM; - if (mem_cgroup_charge(page_folio(page), dst_vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, - page, true, flags); + &folio->page, true, flags); if (ret) goto out_release; out: return ret; out_release: - put_page(page); + folio_put(folio); goto out; } -- GitLab From 0d508c1f0e2c7cec76c141e9d2ebc3020d9e4be4 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:28 +0800 Subject: [PATCH 3263/5631] userfaultfd: use kmap_local_page() in copy_huge_page_from_user() kmap() and kmap_atomic() are being deprecated in favor of kmap_local_page() which is appropriate for any thread local context.[1] Let's replace the kmap() and kmap_atomic() with kmap_local_page() in copy_huge_page_from_user(). When allow_pagefault is false, disable page faults to prevent potential deadlock.[2] [1] https://lore.kernel.org/all/20220813220034.806698-1-ira.weiny@intel.com/ [2] https://lkml.kernel.org/r/20221025220136.2366143-1-ira.weiny@intel.com Link: https://lkml.kernel.org/r/20230410133932.32288-3-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Sidhartha Kumar Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- mm/memory.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 387226d6094d..808f354bce65 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5880,16 +5880,14 @@ long copy_huge_page_from_user(struct page *dst_page, for (i = 0; i < pages_per_huge_page; i++) { subpage = nth_page(dst_page, i); - if (allow_pagefault) - page_kaddr = kmap(subpage); - else - page_kaddr = kmap_atomic(subpage); + page_kaddr = kmap_local_page(subpage); + if (!allow_pagefault) + pagefault_disable(); rc = copy_from_user(page_kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); - if (allow_pagefault) - kunmap(subpage); - else - kunmap_atomic(page_kaddr); + if (!allow_pagefault) + pagefault_enable(); + kunmap_local(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) -- GitLab From e87340ca5c9cecc8a11daf1a2dcabf23f06a4e10 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:29 +0800 Subject: [PATCH 3264/5631] userfaultfd: convert copy_huge_page_from_user() to copy_folio_from_user() Replace copy_huge_page_from_user() with copy_folio_from_user(). copy_folio_from_user() does the same as copy_huge_page_from_user(), but takes in a folio instead of a page. Convert page_kaddr to kaddr in copy_folio_from_user() to do indenting cleanup. Link: https://lkml.kernel.org/r/20230410133932.32288-4-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++---- mm/hugetlb.c | 5 ++--- mm/memory.c | 23 +++++++++++------------ mm/userfaultfd.c | 6 ++---- 4 files changed, 18 insertions(+), 23 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 5e5ef6ee4003..01a009efc2cb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3681,10 +3681,9 @@ extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page); -extern long copy_huge_page_from_user(struct page *dst_page, - const void __user *usr_src, - unsigned int pages_per_huge_page, - bool allow_pagefault); +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7e4a80769c9e..aade1b513474 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6217,9 +6217,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, goto out; } - ret = copy_huge_page_from_user(&folio->page, - (const void __user *) src_addr, - pages_per_huge_page(h), false); + ret = copy_folio_from_user(folio, (const void __user *) src_addr, + false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { diff --git a/mm/memory.c b/mm/memory.c index 808f354bce65..021cab989703 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5868,26 +5868,25 @@ void copy_user_huge_page(struct page *dst, struct page *src, process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } -long copy_huge_page_from_user(struct page *dst_page, - const void __user *usr_src, - unsigned int pages_per_huge_page, - bool allow_pagefault) +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault) { - void *page_kaddr; + void *kaddr; unsigned long i, rc = 0; - unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; + unsigned int nr_pages = folio_nr_pages(dst_folio); + unsigned long ret_val = nr_pages * PAGE_SIZE; struct page *subpage; - for (i = 0; i < pages_per_huge_page; i++) { - subpage = nth_page(dst_page, i); - page_kaddr = kmap_local_page(subpage); + for (i = 0; i < nr_pages; i++) { + subpage = folio_page(dst_folio, i); + kaddr = kmap_local_page(subpage); if (!allow_pagefault) pagefault_disable(); - rc = copy_from_user(page_kaddr, - usr_src + i * PAGE_SIZE, PAGE_SIZE); + rc = copy_from_user(kaddr, usr_src + i * PAGE_SIZE, PAGE_SIZE); if (!allow_pagefault) pagefault_enable(); - kunmap_local(page_kaddr); + kunmap_local(kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 313bc683c2b6..1e7dba6c4c5f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -421,10 +421,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb( mmap_read_unlock(dst_mm); BUG_ON(!page); - err = copy_huge_page_from_user(page, - (const void __user *)src_addr, - vma_hpagesize / PAGE_SIZE, - true); + err = copy_folio_from_user(page_folio(page), + (const void __user *)src_addr, true); if (unlikely(err)) { err = -EFAULT; goto out; -- GitLab From 0169fd518a8934d8d723659752b07589ecc9f692 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:30 +0800 Subject: [PATCH 3265/5631] userfaultfd: convert mfill_atomic_hugetlb() to use a folio Convert hugetlb_mfill_atomic_pte() to take in a folio pointer instead of a page pointer. Convert mfill_atomic_hugetlb() to use a folio. Link: https://lkml.kernel.org/r/20230410133932.32288-5-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Sidhartha Kumar Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 4 ++-- mm/hugetlb.c | 26 +++++++++++++------------- mm/userfaultfd.c | 16 ++++++++-------- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2a758bcd6719..28703fe22386 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -163,7 +163,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep); + struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -397,7 +397,7 @@ static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { BUG(); return 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index aade1b513474..c88f856ec2e2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6178,7 +6178,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); @@ -6201,8 +6201,8 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, if (IS_ERR(folio)) goto out; folio_in_pagecache = true; - } else if (!*pagep) { - /* If a page already exists, then it's UFFDIO_COPY for + } else if (!*foliop) { + /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && @@ -6237,33 +6237,33 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, ret = -ENOMEM; goto out; } - *pagep = &folio->page; - /* Set the outparam pagep and return to the caller to + *foliop = folio; + /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the - * page. + * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { - put_page(*pagep); + folio_put(*foliop); ret = -EEXIST; - *pagep = NULL; + *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { - put_page(*pagep); + folio_put(*foliop); ret = -ENOMEM; - *pagep = NULL; + *foliop = NULL; goto out; } - copy_user_huge_page(&folio->page, *pagep, dst_addr, dst_vma, + copy_user_huge_page(&folio->page, &(*foliop)->page, dst_addr, dst_vma, pages_per_huge_page(h)); - put_page(*pagep); - *pagep = NULL; + folio_put(*foliop); + *foliop = NULL; } /* diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 1e7dba6c4c5f..2f263afb823d 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -321,7 +321,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( pte_t *dst_pte; unsigned long src_addr, dst_addr; long copied; - struct page *page; + struct folio *folio; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; @@ -341,7 +341,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( src_addr = src_start; dst_addr = dst_start; copied = 0; - page = NULL; + folio = NULL; vma_hpagesize = vma_kernel_pagesize(dst_vma); /* @@ -410,7 +410,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( } err = hugetlb_mfill_atomic_pte(dst_pte, dst_vma, dst_addr, - src_addr, flags, &page); + src_addr, flags, &folio); hugetlb_vma_unlock_read(dst_vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); @@ -419,9 +419,9 @@ static __always_inline ssize_t mfill_atomic_hugetlb( if (unlikely(err == -ENOENT)) { mmap_read_unlock(dst_mm); - BUG_ON(!page); + BUG_ON(!folio); - err = copy_folio_from_user(page_folio(page), + err = copy_folio_from_user(folio, (const void __user *)src_addr, true); if (unlikely(err)) { err = -EFAULT; @@ -432,7 +432,7 @@ static __always_inline ssize_t mfill_atomic_hugetlb( dst_vma = NULL; goto retry; } else - BUG_ON(page); + BUG_ON(folio); if (!err) { dst_addr += vma_hpagesize; @@ -449,8 +449,8 @@ static __always_inline ssize_t mfill_atomic_hugetlb( out_unlock: mmap_read_unlock(dst_mm); out: - if (page) - put_page(page); + if (folio) + folio_put(folio); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); -- GitLab From c0e8150e144b62ae467520d0b51c4707c09e897b Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:31 +0800 Subject: [PATCH 3266/5631] mm: convert copy_user_huge_page() to copy_user_large_folio() Replace copy_user_huge_page() with copy_user_large_folio(). copy_user_large_folio() does the same as copy_user_huge_page(), but takes in folios instead of pages. Remove pages_per_huge_page from copy_user_large_folio(), because we can get that from folio_nr_pages(dst). Convert copy_user_gigantic_page() to take in folios. Link: https://lkml.kernel.org/r/20230410133932.32288-6-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Mike Kravetz Cc: Muchun Song Cc: Nanyong Sun Cc: Sidhartha Kumar Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/mm.h | 7 +++---- mm/hugetlb.c | 11 +++++------ mm/memory.c | 28 ++++++++++++++-------------- 3 files changed, 22 insertions(+), 24 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 01a009efc2cb..5a3eaa9a1f8c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3677,10 +3677,9 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -extern void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr_hint, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page); +void copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c88f856ec2e2..f16b25b1a6b9 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5097,8 +5097,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, ret = PTR_ERR(new_folio); break; } - copy_user_huge_page(&new_folio->page, ptepage, addr, dst_vma, - npages); + copy_user_large_folio(new_folio, + page_folio(ptepage), + addr, dst_vma); put_page(ptepage); /* Install the new hugetlb folio if src pte stable */ @@ -5616,8 +5617,7 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, goto out_release_all; } - copy_user_huge_page(&new_folio->page, old_page, address, vma, - pages_per_huge_page(h)); + copy_user_large_folio(new_folio, page_folio(old_page), address, vma); __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, @@ -6260,8 +6260,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, *foliop = NULL; goto out; } - copy_user_huge_page(&folio->page, &(*foliop)->page, dst_addr, dst_vma, - pages_per_huge_page(h)); + copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; } diff --git a/mm/memory.c b/mm/memory.c index 021cab989703..f315c2198098 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5815,21 +5815,21 @@ void clear_huge_page(struct page *page, process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } -static void copy_user_gigantic_page(struct page *dst, struct page *src, - unsigned long addr, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page) +static void copy_user_gigantic_page(struct folio *dst, struct folio *src, + unsigned long addr, + struct vm_area_struct *vma, + unsigned int pages_per_huge_page) { int i; - struct page *dst_base = dst; - struct page *src_base = src; + struct page *dst_page; + struct page *src_page; for (i = 0; i < pages_per_huge_page; i++) { - dst = nth_page(dst_base, i); - src = nth_page(src_base, i); + dst_page = folio_page(dst, i); + src_page = folio_page(src, i); cond_resched(); - copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + copy_user_highpage(dst_page, src_page, addr + i*PAGE_SIZE, vma); } } @@ -5847,15 +5847,15 @@ static void copy_subpage(unsigned long addr, int idx, void *arg) addr, copy_arg->vma); } -void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr_hint, struct vm_area_struct *vma, - unsigned int pages_per_huge_page) +void copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, struct vm_area_struct *vma) { + unsigned int pages_per_huge_page = folio_nr_pages(dst); unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { - .dst = dst, - .src = src, + .dst = &dst->page, + .src = &src->page, .vma = vma, }; -- GitLab From d7be6d7eee1bbf98671d7a2c95654322241e2ae4 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 10 Apr 2023 21:39:32 +0800 Subject: [PATCH 3267/5631] userfaultfd: convert mfill_atomic() to use a folio Convert mfill_atomic_pte_copy(), shmem_mfill_atomic_pte() and mfill_atomic_pte() to take in a folio pointer. Convert mfill_atomic() to use a folio. Convert page_kaddr to kaddr in mfill_atomic(). Link: https://lkml.kernel.org/r/20230410133932.32288-7-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: Mike Kravetz Cc: Kefeng Wang Cc: Matthew Wilcox Cc: Muchun Song Cc: Nanyong Sun Cc: Sidhartha Kumar Cc: Vishal Moola (Oracle) Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 4 ++-- mm/shmem.c | 16 ++++++++-------- mm/userfaultfd.c | 40 ++++++++++++++++++++-------------------- 3 files changed, 30 insertions(+), 30 deletions(-) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index b9516a9802bf..9029abd29b1c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -165,10 +165,10 @@ extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep); + struct folio **foliop); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ - src_addr, flags, pagep) ({ BUG(); 0; }) + src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/mm/shmem.c b/mm/shmem.c index b185c1db3009..3531ebb3494e 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2433,7 +2433,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); @@ -2451,14 +2451,14 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, * and now we find ourselves with -ENOMEM. Release the page, to * avoid a BUG_ON in our caller. */ - if (unlikely(*pagep)) { - put_page(*pagep); - *pagep = NULL; + if (unlikely(*foliop)) { + folio_put(*foliop); + *foliop = NULL; } return -ENOMEM; } - if (!*pagep) { + if (!*foliop) { ret = -ENOMEM; folio = shmem_alloc_folio(gfp, info, pgoff); if (!folio) @@ -2490,7 +2490,7 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { - *pagep = &folio->page; + *foliop = folio; ret = -ENOENT; /* don't free the page */ goto out_unacct_blocks; @@ -2501,9 +2501,9 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd, clear_user_highpage(&folio->page, dst_addr); } } else { - folio = page_folio(*pagep); + folio = *foliop; VM_BUG_ON_FOLIO(folio_test_large(folio), folio); - *pagep = NULL; + *foliop = NULL; } VM_BUG_ON(folio_test_locked(folio)); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 2f263afb823d..11cfd82c6726 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -133,13 +133,13 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { void *kaddr; int ret; struct folio *folio; - if (!*pagep) { + if (!*foliop) { ret = -ENOMEM; folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, dst_vma, dst_addr, false); @@ -171,15 +171,15 @@ static int mfill_atomic_pte_copy(pmd_t *dst_pmd, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; - *pagep = &folio->page; + *foliop = folio; /* don't free the page */ goto out; } flush_dcache_folio(folio); } else { - folio = page_folio(*pagep); - *pagep = NULL; + folio = *foliop; + *foliop = NULL; } /* @@ -470,7 +470,7 @@ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, - struct page **pagep) + struct folio **foliop) { ssize_t err; @@ -493,14 +493,14 @@ static __always_inline ssize_t mfill_atomic_pte(pmd_t *dst_pmd, if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) err = mfill_atomic_pte_copy(dst_pmd, dst_vma, dst_addr, src_addr, - flags, pagep); + flags, foliop); else err = mfill_atomic_pte_zeropage(dst_pmd, dst_vma, dst_addr); } else { err = shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, src_addr, - flags, pagep); + flags, foliop); } return err; @@ -518,7 +518,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, pmd_t *dst_pmd; unsigned long src_addr, dst_addr; long copied; - struct page *page; + struct folio *folio; /* * Sanitize the command parameters: @@ -533,7 +533,7 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, src_addr = src_start; dst_addr = dst_start; copied = 0; - page = NULL; + folio = NULL; retry: mmap_read_lock(dst_mm); @@ -629,28 +629,28 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, - src_addr, flags, &page); + src_addr, flags, &folio); cond_resched(); if (unlikely(err == -ENOENT)) { - void *page_kaddr; + void *kaddr; mmap_read_unlock(dst_mm); - BUG_ON(!page); + BUG_ON(!folio); - page_kaddr = kmap_local_page(page); - err = copy_from_user(page_kaddr, + kaddr = kmap_local_folio(folio, 0); + err = copy_from_user(kaddr, (const void __user *) src_addr, PAGE_SIZE); - kunmap_local(page_kaddr); + kunmap_local(kaddr); if (unlikely(err)) { err = -EFAULT; goto out; } - flush_dcache_page(page); + flush_dcache_folio(folio); goto retry; } else - BUG_ON(page); + BUG_ON(folio); if (!err) { dst_addr += PAGE_SIZE; @@ -667,8 +667,8 @@ static __always_inline ssize_t mfill_atomic(struct mm_struct *dst_mm, out_unlock: mmap_read_unlock(dst_mm); out: - if (page) - put_page(page); + if (folio) + folio_put(folio); BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); -- GitLab From fb20e99a74f8f08c53061e0186d0c26d546dc843 Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Tue, 11 Apr 2023 10:35:13 +0800 Subject: [PATCH 3268/5631] maple_tree: use correct variable type in sizeof The type of variable pointed to by pivs is unsigned long, but the type used in sizeof is a pointer type. Change it to unsigned long. This change has no runtime effect, as sizeof(ul) == sizeof(ul *). Link: https://lkml.kernel.org/r/20230411023513.15227-1-zhangpeng.00@bytedance.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Peng Zhang Reported-by: David Binderman Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- lib/maple_tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index f475bac9d914..9172bcee94b4 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -3258,7 +3258,7 @@ static inline void mas_destroy_rebalance(struct ma_state *mas, unsigned char end if (tmp < max_p) memset(pivs + tmp, 0, - sizeof(unsigned long *) * (max_p - tmp)); + sizeof(unsigned long) * (max_p - tmp)); if (tmp < mt_slots[mt]) memset(slots + tmp, 0, sizeof(void *) * (max_s - tmp)); -- GitLab From f6365881bf797c734bf4cf1353bfa59ffd444f8f Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sat, 8 Apr 2023 10:16:09 -0400 Subject: [PATCH 3269/5631] mm: backing-dev: set variables dev_attr_min,max_bytes storage-class-specifier to static smatch reports mm/backing-dev.c:266:1: warning: symbol 'dev_attr_min_bytes' was not declared. Should it be static? mm/backing-dev.c:294:1: warning: symbol 'dev_attr_max_bytes' was not declared. Should it be static? These variables are only used in one file so should be static. Link: https://lkml.kernel.org/r/20230408141609.2703647-1-trix@redhat.com Signed-off-by: Tom Rix Reviewed-by: Christoph Hellwig Signed-off-by: Andrew Morton --- mm/backing-dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 30d2d0386fdb..aee6e5a8ff3a 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -263,7 +263,7 @@ static ssize_t min_bytes_store(struct device *dev, return ret; } -DEVICE_ATTR_RW(min_bytes); +static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, @@ -291,7 +291,7 @@ static ssize_t max_bytes_store(struct device *dev, return ret; } -DEVICE_ATTR_RW(max_bytes); +static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, -- GitLab From 3b7939c8e5345fb84309f2605a4b6f7ac8dd7fce Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Tue, 11 Apr 2023 12:10:05 +0800 Subject: [PATCH 3270/5631] maple_tree: add a test case to check maple_alloc Add a test case to check whether the number of maple_alloc structures is actually equal to mas->alloc->total. Link: https://lkml.kernel.org/r/20230411041005.26205-2-zhangpeng.00@bytedance.com Signed-off-by: Peng Zhang Cc: Liam R. Howlett Signed-off-by: Andrew Morton --- tools/testing/radix-tree/maple.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 4c89ff333f6f..9286d3baa12d 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -55,6 +55,28 @@ struct rcu_reader_struct { struct rcu_test_struct2 *test; }; +static int get_alloc_node_count(struct ma_state *mas) +{ + int count = 1; + struct maple_alloc *node = mas->alloc; + + if (!node || ((unsigned long)node & 0x1)) + return 0; + while (node->node_count) { + count += node->node_count; + node = node->slot[0]; + } + return count; +} + +static void check_mas_alloc_node_count(struct ma_state *mas) +{ + mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 1, GFP_KERNEL); + mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 3, GFP_KERNEL); + MT_BUG_ON(mas->tree, get_alloc_node_count(mas) != mas->alloc->total); + mas_destroy(mas); +} + /* * check_new_node() - Check the creation of new nodes and error path * verification. @@ -69,6 +91,8 @@ static noinline void check_new_node(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); + check_mas_alloc_node_count(&mas); + /* Try allocating 3 nodes */ mtree_lock(mt); mt_set_non_kernel(0); -- GitLab From a70aae12502b130b0c30dda44dff09e575c1aaeb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:43 +0200 Subject: [PATCH 3271/5631] zram: always compile read_from_bdev_sync Patch series "zram I/O path cleanups and fixups", v3. This series cleans up the zram I/O path, and fixes the handling of synchronous I/O to the underlying device in the writeback_store function or for > 4K PAGE_SIZE systems. The fixes are at the end, as I could not fully reason about them being safe before untangling the callchain. This patch (of 17): read_from_bdev_sync is currently only compiled for non-4k PAGE_SIZE, which means it won't be built with the most common configurations. Replace the ifdef with a check for the PAGE_SIZE in an if instead. The check uses an extra symbol and IS_ENABLED to allow the compiler to eliminate the dead code, leading to the same generated code size: text data bss dec hex filename 16709 1428 12 18149 46e5 drivers/block/zram/zram_drv.o.old 16709 1428 12 18149 46e5 drivers/block/zram/zram_drv.o.new Link: https://lkml.kernel.org/r/20230411171459.567614-1-hch@lst.de Link: https://lkml.kernel.org/r/20230411171459.567614-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Cc: Jens Axboe Cc: Minchan Kim Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index aa490da3cef2..57787cbdf1f7 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -148,6 +148,7 @@ static inline bool is_partial_io(struct bio_vec *bvec) { return bvec->bv_len != PAGE_SIZE; } +#define ZRAM_PARTIAL_IO 1 #else static inline bool is_partial_io(struct bio_vec *bvec) { @@ -833,7 +834,6 @@ struct zram_work { struct bio_vec bvec; }; -#if PAGE_SIZE != 4096 static void zram_sync_read(struct work_struct *work) { struct zram_work *zw = container_of(work, struct zram_work, work); @@ -866,23 +866,17 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, return 1; } -#else -static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, - unsigned long entry, struct bio *bio) -{ - WARN_ON(1); - return -EIO; -} -#endif static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, unsigned long entry, struct bio *parent, bool sync) { atomic64_inc(&zram->stats.bd_reads); - if (sync) + if (sync) { + if (WARN_ON_ONCE(!IS_ENABLED(ZRAM_PARTIAL_IO))) + return -EIO; return read_from_bdev_sync(zram, bvec, entry, parent); - else - return read_from_bdev_async(zram, bvec, entry, parent); + } + return read_from_bdev_async(zram, bvec, entry, parent); } #else static inline void reset_bdev(struct zram *zram) {}; -- GitLab From 9fe95babc7420722d39a1ded379027a1e1825d3a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:44 +0200 Subject: [PATCH 3272/5631] zram: remove valid_io_request All bios hande to drivers from the block layer are checked against the device size and for logical block alignment already (and have been since long before zram was merged), so don't duplicate those checks. Link: https://lkml.kernel.org/r/20230411171459.567614-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 34 +--------------------------------- drivers/block/zram/zram_drv.h | 1 - 2 files changed, 1 insertion(+), 34 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 57787cbdf1f7..f4466ad1fd4a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -175,30 +175,6 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index) return prio & ZRAM_COMP_PRIORITY_MASK; } -/* - * Check if request is within bounds and aligned on zram logical blocks. - */ -static inline bool valid_io_request(struct zram *zram, - sector_t start, unsigned int size) -{ - u64 end, bound; - - /* unaligned request */ - if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1))) - return false; - if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1))) - return false; - - end = start + (size >> SECTOR_SHIFT); - bound = zram->disksize >> SECTOR_SHIFT; - /* out of range */ - if (unlikely(start >= bound || end > bound || start > end)) - return false; - - /* I/O request is valid */ - return true; -} - static void update_position(u32 *index, int *offset, struct bio_vec *bvec) { *index += (*offset + bvec->bv_len) / PAGE_SIZE; @@ -1184,10 +1160,9 @@ static ssize_t io_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "%8llu %8llu %8llu %8llu\n", + "%8llu %8llu 0 %8llu\n", (u64)atomic64_read(&zram->stats.failed_reads), (u64)atomic64_read(&zram->stats.failed_writes), - (u64)atomic64_read(&zram->stats.invalid_io), (u64)atomic64_read(&zram->stats.notify_free)); up_read(&zram->init_lock); @@ -2037,13 +2012,6 @@ static void zram_submit_bio(struct bio *bio) { struct zram *zram = bio->bi_bdev->bd_disk->private_data; - if (!valid_io_request(zram, bio->bi_iter.bi_sector, - bio->bi_iter.bi_size)) { - atomic64_inc(&zram->stats.invalid_io); - bio_io_error(bio); - return; - } - __zram_make_request(zram, bio); } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index c5254626f051..ca7a15bd4845 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -78,7 +78,6 @@ struct zram_stats { atomic64_t compr_data_size; /* compressed size of pages stored */ atomic64_t failed_reads; /* can happen when memory is too low */ atomic64_t failed_writes; /* can happen when memory is too low */ - atomic64_t invalid_io; /* non-page-aligned I/O requests */ atomic64_t notify_free; /* no. of swap slot free notifications */ atomic64_t same_pages; /* no. of same element filled pages */ atomic64_t huge_pages; /* no. of huge pages */ -- GitLab From 0120dd6e4e202e19a0e011e486fb2da40a5ea279 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:45 +0200 Subject: [PATCH 3273/5631] zram: make zram_bio_discard more self-contained Derive the index and offset variables inside the function, and complete the bio directly in preparation for cleaning up the I/O path. Link: https://lkml.kernel.org/r/20230411171459.567614-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f4466ad1fd4a..e9b31c199027 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1890,15 +1890,12 @@ static ssize_t recompress_store(struct device *dev, } #endif -/* - * zram_bio_discard - handler on discard request - * @index: physical block index in PAGE_SIZE units - * @offset: byte offset within physical block - */ -static void zram_bio_discard(struct zram *zram, u32 index, - int offset, struct bio *bio) +static void zram_bio_discard(struct zram *zram, struct bio *bio) { size_t n = bio->bi_iter.bi_size; + u32 index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; + u32 offset = (bio->bi_iter.bi_sector & (SECTORS_PER_PAGE - 1)) << + SECTOR_SHIFT; /* * zram manages data in physical block size units. Because logical block @@ -1926,6 +1923,8 @@ static void zram_bio_discard(struct zram *zram, u32 index, index++; n -= PAGE_SIZE; } + + bio_endio(bio); } /* @@ -1974,8 +1973,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - zram_bio_discard(zram, index, offset, bio); - bio_endio(bio); + zram_bio_discard(zram, bio); return; default: break; -- GitLab From af8b04c63708fa730c0257084fab91fb2a9cecc4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:46 +0200 Subject: [PATCH 3274/5631] zram: simplify bvec iteration in __zram_make_request bio_for_each_segment synthetize bvecs that never cross page boundaries, so don't duplicate that work in an inner loop. Link: https://lkml.kernel.org/r/20230411171459.567614-5-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 42 +++++++++-------------------------- 1 file changed, 11 insertions(+), 31 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e9b31c199027..e13c7d8e283b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -175,12 +175,6 @@ static inline u32 zram_get_priority(struct zram *zram, u32 index) return prio & ZRAM_COMP_PRIORITY_MASK; } -static void update_position(u32 *index, int *offset, struct bio_vec *bvec) -{ - *index += (*offset + bvec->bv_len) / PAGE_SIZE; - *offset = (*offset + bvec->bv_len) % PAGE_SIZE; -} - static inline void update_used_max(struct zram *zram, const unsigned long pages) { @@ -1960,16 +1954,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, static void __zram_make_request(struct zram *zram, struct bio *bio) { - int offset; - u32 index; - struct bio_vec bvec; struct bvec_iter iter; + struct bio_vec bv; unsigned long start_time; - index = bio->bi_iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; - offset = (bio->bi_iter.bi_sector & - (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; - switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: @@ -1980,24 +1968,16 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) } start_time = bio_start_io_acct(bio); - bio_for_each_segment(bvec, bio, iter) { - struct bio_vec bv = bvec; - unsigned int unwritten = bvec.bv_len; - - do { - bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset, - unwritten); - if (zram_bvec_rw(zram, &bv, index, offset, - bio_op(bio), bio) < 0) { - bio->bi_status = BLK_STS_IOERR; - break; - } - - bv.bv_offset += bv.bv_len; - unwritten -= bv.bv_len; - - update_position(&index, &offset, &bv); - } while (unwritten); + bio_for_each_segment(bv, bio, iter) { + u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; + u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) << + SECTOR_SHIFT; + + if (zram_bvec_rw(zram, &bv, index, offset, bio_op(bio), + bio) < 0) { + bio->bi_status = BLK_STS_IOERR; + break; + } } bio_end_io_acct(bio, start_time); bio_endio(bio); -- GitLab From d6eea0097e26769fb58c2773214c3bda85d1678a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:47 +0200 Subject: [PATCH 3275/5631] zram: move discard handling to zram_submit_bio Switch on the bio operation in zram_submit_bio and only call into __zram_make_request for read and write operations. Link: https://lkml.kernel.org/r/20230411171459.567614-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e13c7d8e283b..00f13eb1c800 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1958,15 +1958,6 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) struct bio_vec bv; unsigned long start_time; - switch (bio_op(bio)) { - case REQ_OP_DISCARD: - case REQ_OP_WRITE_ZEROES: - zram_bio_discard(zram, bio); - return; - default: - break; - } - start_time = bio_start_io_acct(bio); bio_for_each_segment(bv, bio, iter) { u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; @@ -1990,7 +1981,19 @@ static void zram_submit_bio(struct bio *bio) { struct zram *zram = bio->bi_bdev->bd_disk->private_data; - __zram_make_request(zram, bio); + switch (bio_op(bio)) { + case REQ_OP_READ: + case REQ_OP_WRITE: + __zram_make_request(zram, bio); + break; + case REQ_OP_DISCARD: + case REQ_OP_WRITE_ZEROES: + zram_bio_discard(zram, bio); + break; + default: + WARN_ON_ONCE(1); + bio_endio(bio); + } } static void zram_slot_free_notify(struct block_device *bdev, -- GitLab From 57de7bd830dae90301329748d60e196fab4c4125 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:48 +0200 Subject: [PATCH 3276/5631] zram: return early on error in zram_bvec_rw When the low-level access fails, don't clear the idle flag or clear the caches, and just return. Link: https://lkml.kernel.org/r/20230411171459.567614-7-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 00f13eb1c800..46dc7a274867 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1933,23 +1933,23 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, if (!op_is_write(op)) { ret = zram_bvec_read(zram, bvec, index, offset, bio); + if (unlikely(ret < 0)) { + atomic64_inc(&zram->stats.failed_reads); + return ret; + } flush_dcache_page(bvec->bv_page); } else { ret = zram_bvec_write(zram, bvec, index, offset, bio); + if (unlikely(ret < 0)) { + atomic64_inc(&zram->stats.failed_writes); + return ret; + } } zram_slot_lock(zram, index); zram_accessed(zram, index); zram_slot_unlock(zram, index); - - if (unlikely(ret < 0)) { - if (!op_is_write(op)) - atomic64_inc(&zram->stats.failed_reads); - else - atomic64_inc(&zram->stats.failed_writes); - } - - return ret; + return 0; } static void __zram_make_request(struct zram *zram, struct bio *bio) -- GitLab From 82ca875d2549f6843d0d16e897c9e1e0a13c8a74 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:49 +0200 Subject: [PATCH 3277/5631] zram: refactor highlevel read and write handling Instead of having an outer loop in __zram_make_request and then branch out for reads vs writes for each loop iteration in zram_bvec_rw, split the main handler into separat zram_bio_read and zram_bio_write handlers that also include the functionality formerly in zram_bvec_rw. Link: https://lkml.kernel.org/r/20230411171459.567614-8-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 58 ++++++++++++++++++----------------- 1 file changed, 30 insertions(+), 28 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 46dc7a274867..2d0154489f03 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1921,38 +1921,34 @@ static void zram_bio_discard(struct zram *zram, struct bio *bio) bio_endio(bio); } -/* - * Returns errno if it has some problem. Otherwise return 0 or 1. - * Returns 0 if IO request was done synchronously - * Returns 1 if IO request was successfully submitted. - */ -static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, enum req_op op, struct bio *bio) +static void zram_bio_read(struct zram *zram, struct bio *bio) { - int ret; + struct bvec_iter iter; + struct bio_vec bv; + unsigned long start_time; - if (!op_is_write(op)) { - ret = zram_bvec_read(zram, bvec, index, offset, bio); - if (unlikely(ret < 0)) { + start_time = bio_start_io_acct(bio); + bio_for_each_segment(bv, bio, iter) { + u32 index = iter.bi_sector >> SECTORS_PER_PAGE_SHIFT; + u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) << + SECTOR_SHIFT; + + if (zram_bvec_read(zram, &bv, index, offset, bio) < 0) { atomic64_inc(&zram->stats.failed_reads); - return ret; - } - flush_dcache_page(bvec->bv_page); - } else { - ret = zram_bvec_write(zram, bvec, index, offset, bio); - if (unlikely(ret < 0)) { - atomic64_inc(&zram->stats.failed_writes); - return ret; + bio->bi_status = BLK_STS_IOERR; + break; } - } + flush_dcache_page(bv.bv_page); - zram_slot_lock(zram, index); - zram_accessed(zram, index); - zram_slot_unlock(zram, index); - return 0; + zram_slot_lock(zram, index); + zram_accessed(zram, index); + zram_slot_unlock(zram, index); + } + bio_end_io_acct(bio, start_time); + bio_endio(bio); } -static void __zram_make_request(struct zram *zram, struct bio *bio) +static void zram_bio_write(struct zram *zram, struct bio *bio) { struct bvec_iter iter; struct bio_vec bv; @@ -1964,11 +1960,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) u32 offset = (iter.bi_sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT; - if (zram_bvec_rw(zram, &bv, index, offset, bio_op(bio), - bio) < 0) { + if (zram_bvec_write(zram, &bv, index, offset, bio) < 0) { + atomic64_inc(&zram->stats.failed_writes); bio->bi_status = BLK_STS_IOERR; break; } + + zram_slot_lock(zram, index); + zram_accessed(zram, index); + zram_slot_unlock(zram, index); } bio_end_io_acct(bio, start_time); bio_endio(bio); @@ -1983,8 +1983,10 @@ static void zram_submit_bio(struct bio *bio) switch (bio_op(bio)) { case REQ_OP_READ: + zram_bio_read(zram, bio); + break; case REQ_OP_WRITE: - __zram_make_request(zram, bio); + zram_bio_write(zram, bio); break; case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: -- GitLab From f575a5add8a9a3ca593e58e218f2113e5bd3e50e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:50 +0200 Subject: [PATCH 3278/5631] zram: don't use highmem for the bounce buffer in zram_bvec_{read,write} There is no point in allocation a highmem page when we instantly need to copy from it. Link: https://lkml.kernel.org/r/20230411171459.567614-9-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2d0154489f03..0182316b2a90 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1431,7 +1431,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, page = bvec->bv_page; if (is_partial_io(bvec)) { /* Use a temporary buffer to decompress the page */ - page = alloc_page(GFP_NOIO|__GFP_HIGHMEM); + page = alloc_page(GFP_NOIO); if (!page) return -ENOMEM; } @@ -1440,12 +1440,8 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, if (unlikely(ret)) goto out; - if (is_partial_io(bvec)) { - void *src = kmap_atomic(page); - - memcpy_to_bvec(bvec, src + offset); - kunmap_atomic(src); - } + if (is_partial_io(bvec)) + memcpy_to_bvec(bvec, page_address(page) + offset); out: if (is_partial_io(bvec)) __free_page(page); @@ -1589,12 +1585,11 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, vec = *bvec; if (is_partial_io(bvec)) { - void *dst; /* * This is a partial IO. We need to read the full page * before to write the changes. */ - page = alloc_page(GFP_NOIO|__GFP_HIGHMEM); + page = alloc_page(GFP_NOIO); if (!page) return -ENOMEM; @@ -1602,9 +1597,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (ret) goto out; - dst = kmap_atomic(page); - memcpy_from_bvec(dst + offset, bvec); - kunmap_atomic(dst); + memcpy_from_bvec(page_address(page) + offset, bvec); bvec_set_page(&vec, page, PAGE_SIZE, 0); } -- GitLab From ffb0a9e66562083cc0fb0a93d2de85cecd23a0e8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:51 +0200 Subject: [PATCH 3279/5631] zram: rename __zram_bvec_read to zram_read_page __zram_bvec_read doesn't get passed a bvec, but always read a whole page. Rename it to make the usage more clear. Link: https://lkml.kernel.org/r/20230411171459.567614-10-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 0182316b2a90..414343b46ade 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1397,8 +1397,8 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page, return ret; } -static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, - struct bio *bio, bool partial_io) +static int zram_read_page(struct zram *zram, struct page *page, u32 index, + struct bio *bio, bool partial_io) { int ret; @@ -1436,7 +1436,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return -ENOMEM; } - ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec)); + ret = zram_read_page(zram, page, index, bio, is_partial_io(bvec)); if (unlikely(ret)) goto out; @@ -1593,7 +1593,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (!page) return -ENOMEM; - ret = __zram_bvec_read(zram, page, index, bio, true); + ret = zram_read_page(zram, page, index, bio, true); if (ret) goto out; -- GitLab From 79c744eeaa8eaa2d8fbb4f2c1edf292df7163c8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:52 +0200 Subject: [PATCH 3280/5631] zram: directly call zram_read_page in writeback_store writeback_store always reads a full page, so just call zram_read_page directly and bypass the boune buffer handling. Link: https://lkml.kernel.org/r/20230411171459.567614-11-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 414343b46ade..40ef0a7ce348 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -54,9 +54,8 @@ static size_t huge_class_size; static const struct block_device_operations zram_devops; static void zram_free_page(struct zram *zram, size_t index); -static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset, struct bio *bio); - +static int zram_read_page(struct zram *zram, struct page *page, u32 index, + struct bio *bio, bool partial_io); static int zram_slot_trylock(struct zram *zram, u32 index) { @@ -672,10 +671,6 @@ static ssize_t writeback_store(struct device *dev, } for (; nr_pages != 0; index++, nr_pages--) { - struct bio_vec bvec; - - bvec_set_page(&bvec, page, PAGE_SIZE, 0); - spin_lock(&zram->wb_limit_lock); if (zram->wb_limit_enable && !zram->bd_wb_limit) { spin_unlock(&zram->wb_limit_lock); @@ -719,7 +714,7 @@ static ssize_t writeback_store(struct device *dev, /* Need for hugepage writeback racing */ zram_set_flag(zram, index, ZRAM_IDLE); zram_slot_unlock(zram, index); - if (zram_bvec_read(zram, &bvec, index, 0, NULL)) { + if (zram_read_page(zram, page, index, NULL, false)) { zram_slot_lock(zram, index); zram_clear_flag(zram, index, ZRAM_UNDER_WB); zram_clear_flag(zram, index, ZRAM_IDLE); @@ -730,9 +725,8 @@ static ssize_t writeback_store(struct device *dev, bio_init(&bio, zram->bdev, &bio_vec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); + bio_add_page(&bio, page, PAGE_SIZE, 0); - bio_add_page(&bio, bvec.bv_page, bvec.bv_len, - bvec.bv_offset); /* * XXX: A single page IO would be inefficient for write * but it would be not bad as starter. -- GitLab From 889ae9169b45f0fc3fc05f93c3c6fa8a851eab67 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:53 +0200 Subject: [PATCH 3281/5631] zram: refactor zram_bdev_read Split the partial read into a separate helper. Link: https://lkml.kernel.org/r/20230411171459.567614-12-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 40 +++++++++++++++++------------------ 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 40ef0a7ce348..2e985531d8cb 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1416,33 +1416,33 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, return ret; } -static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset, struct bio *bio) +/* + * Use a temporary buffer to decompress the page, as the decompressor + * always expects a full page for the output. + */ +static int zram_bvec_read_partial(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio) { + struct page *page = alloc_page(GFP_NOIO); int ret; - struct page *page; - - page = bvec->bv_page; - if (is_partial_io(bvec)) { - /* Use a temporary buffer to decompress the page */ - page = alloc_page(GFP_NOIO); - if (!page) - return -ENOMEM; - } - - ret = zram_read_page(zram, page, index, bio, is_partial_io(bvec)); - if (unlikely(ret)) - goto out; - if (is_partial_io(bvec)) + if (!page) + return -ENOMEM; + ret = zram_read_page(zram, page, index, bio, true); + if (likely(!ret)) memcpy_to_bvec(bvec, page_address(page) + offset); -out: - if (is_partial_io(bvec)) - __free_page(page); - + __free_page(page); return ret; } +static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio) +{ + if (is_partial_io(bvec)) + return zram_bvec_read_partial(zram, bvec, index, offset, bio); + return zram_read_page(zram, bvec->bv_page, index, bio, false); +} + static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, struct bio *bio) { -- GitLab From 6aa4b839e7a481cc20b243168dc3333fc3d87eb0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:54 +0200 Subject: [PATCH 3282/5631] zram: don't pass a bvec to __zram_bvec_write __zram_bvec_write only extracts the page from __zram_bvec_write and always expects a full page of input. Pass the page directly instead of the bvec and rename the function to zram_write_page. Link: https://lkml.kernel.org/r/20230411171459.567614-13-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2e985531d8cb..cbcfb5cb2fed 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1443,8 +1443,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return zram_read_page(zram, bvec->bv_page, index, bio, false); } -static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, - u32 index, struct bio *bio) +static int zram_write_page(struct zram *zram, struct page *page, u32 index) { int ret = 0; unsigned long alloced_pages; @@ -1452,7 +1451,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, unsigned int comp_len = 0; void *src, *dst, *mem; struct zcomp_strm *zstrm; - struct page *page = bvec->bv_page; unsigned long element = 0; enum zram_pageflags flags = 0; @@ -1573,11 +1571,9 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, int offset, struct bio *bio) { + struct page *page = bvec->bv_page; int ret; - struct page *page = NULL; - struct bio_vec vec; - vec = *bvec; if (is_partial_io(bvec)) { /* * This is a partial IO. We need to read the full page @@ -1592,11 +1588,9 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, goto out; memcpy_from_bvec(page_address(page) + offset, bvec); - - bvec_set_page(&vec, page, PAGE_SIZE, 0); } - ret = __zram_bvec_write(zram, &vec, index, bio); + ret = zram_write_page(zram, page, index); out: if (is_partial_io(bvec)) __free_page(page); @@ -1711,7 +1705,7 @@ static int zram_recompress(struct zram *zram, u32 index, struct page *page, /* * No direct reclaim (slow path) for handle allocation and no - * re-compression attempt (unlike in __zram_bvec_write()) since + * re-compression attempt (unlike in zram_write_bvec()) since * we already have stored that object in zsmalloc. If we cannot * alloc memory for recompressed object then we bail out and * simply keep the old (existing) object in zsmalloc. -- GitLab From a0b81ae7a4ff8a779e9f16152563d614cb91f13c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:55 +0200 Subject: [PATCH 3283/5631] zram: refactor zram_bdev_write Split the read/modify/write case into a separate helper. Link: https://lkml.kernel.org/r/20230411171459.567614-14-hch@lst.de Signed-off-by: Christoph Hellwig Acked-by: Minchan Kim Reviewed-by: Sergey Senozhatsky Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 38 +++++++++++++++++------------------ 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cbcfb5cb2fed..1a7fe75285e6 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1568,33 +1568,33 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index) return ret; } -static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset, struct bio *bio) +/* + * This is a partial IO. Read the full page before writing the changes. + */ +static int zram_bvec_write_partial(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio) { - struct page *page = bvec->bv_page; + struct page *page = alloc_page(GFP_NOIO); int ret; - if (is_partial_io(bvec)) { - /* - * This is a partial IO. We need to read the full page - * before to write the changes. - */ - page = alloc_page(GFP_NOIO); - if (!page) - return -ENOMEM; - - ret = zram_read_page(zram, page, index, bio, true); - if (ret) - goto out; + if (!page) + return -ENOMEM; + ret = zram_read_page(zram, page, index, bio, true); + if (!ret) { memcpy_from_bvec(page_address(page) + offset, bvec); + ret = zram_write_page(zram, page, index); } + __free_page(page); + return ret; +} - ret = zram_write_page(zram, page, index); -out: +static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio) +{ if (is_partial_io(bvec)) - __free_page(page); - return ret; + return zram_bvec_write_partial(zram, bvec, index, offset, bio); + return zram_write_page(zram, bvec->bv_page, index); } #ifdef CONFIG_ZRAM_MULTI_COMP -- GitLab From fd45af53e220b2fe13a5e8db88c5e92bc3296754 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:56 +0200 Subject: [PATCH 3284/5631] zram: pass a page to read_from_bdev read_from_bdev always reads a whole page, so pass a page to it instead of the bvec and remove the now pointless zram_bvec_read_from_bdev wrapper. Link: https://lkml.kernel.org/r/20230411171459.567614-15-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 43 +++++++++++++---------------------- 1 file changed, 16 insertions(+), 27 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 1a7fe75285e6..9a35bb0f1a03 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -588,7 +588,7 @@ static void zram_page_end_io(struct bio *bio) /* * Returns 1 if the submission is successful. */ -static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, +static int read_from_bdev_async(struct zram *zram, struct page *page, unsigned long entry, struct bio *parent) { struct bio *bio; @@ -599,7 +599,7 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, return -ENOMEM; bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); - if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) { + if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { bio_put(bio); return -EIO; } @@ -795,7 +795,7 @@ struct zram_work { struct zram *zram; unsigned long entry; struct bio *bio; - struct bio_vec bvec; + struct page *page; }; static void zram_sync_read(struct work_struct *work) @@ -805,7 +805,7 @@ static void zram_sync_read(struct work_struct *work) unsigned long entry = zw->entry; struct bio *bio = zw->bio; - read_from_bdev_async(zram, &zw->bvec, entry, bio); + read_from_bdev_async(zram, zw->page, entry, bio); } /* @@ -813,12 +813,12 @@ static void zram_sync_read(struct work_struct *work) * chained IO with parent IO in same context, it's a deadlock. To avoid that, * use a worker thread context. */ -static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, +static int read_from_bdev_sync(struct zram *zram, struct page *page, unsigned long entry, struct bio *bio) { struct zram_work work; - work.bvec = *bvec; + work.page = page; work.zram = zram; work.entry = entry; work.bio = bio; @@ -831,20 +831,20 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, return 1; } -static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, +static int read_from_bdev(struct zram *zram, struct page *page, unsigned long entry, struct bio *parent, bool sync) { atomic64_inc(&zram->stats.bd_reads); if (sync) { if (WARN_ON_ONCE(!IS_ENABLED(ZRAM_PARTIAL_IO))) return -EIO; - return read_from_bdev_sync(zram, bvec, entry, parent); + return read_from_bdev_sync(zram, page, entry, parent); } - return read_from_bdev_async(zram, bvec, entry, parent); + return read_from_bdev_async(zram, page, entry, parent); } #else static inline void reset_bdev(struct zram *zram) {}; -static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, +static int read_from_bdev(struct zram *zram, struct page *page, unsigned long entry, struct bio *parent, bool sync) { return -EIO; @@ -1328,20 +1328,6 @@ static void zram_free_page(struct zram *zram, size_t index) ~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB)); } -/* - * Reads a page from the writeback devices. Corresponding ZRAM slot - * should be unlocked. - */ -static int zram_bvec_read_from_bdev(struct zram *zram, struct page *page, - u32 index, struct bio *bio, bool partial_io) -{ - struct bio_vec bvec; - - bvec_set_page(&bvec, page, PAGE_SIZE, 0); - return read_from_bdev(zram, &bvec, zram_get_element(zram, index), bio, - partial_io); -} - /* * Reads (decompresses if needed) a page from zspool (zsmalloc). * Corresponding ZRAM slot should be locked. @@ -1402,11 +1388,14 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, ret = zram_read_from_zspool(zram, page, index); zram_slot_unlock(zram, index); } else { - /* Slot should be unlocked before the function call */ + /* + * The slot should be unlocked before reading from the backing + * device. + */ zram_slot_unlock(zram, index); - ret = zram_bvec_read_from_bdev(zram, page, index, bio, - partial_io); + ret = read_from_bdev(zram, page, zram_get_element(zram, index), + bio, partial_io); } /* Should NEVER happen. Return bio error if it does. */ -- GitLab From 0cd97a0372f21a66d1591114d0a12391e8d977d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:57 +0200 Subject: [PATCH 3285/5631] zram: don't return errors from read_from_bdev_async bio_alloc will never return a NULL bio when it is allowed to sleep, and adding a single page to bio with a single vector also can't fail, so switch to the asserting __bio_add_page variant and drop the error returns. Link: https://lkml.kernel.org/r/20230411171459.567614-16-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 9a35bb0f1a03..24b31957d9e8 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -585,24 +585,16 @@ static void zram_page_end_io(struct bio *bio) bio_put(bio); } -/* - * Returns 1 if the submission is successful. - */ -static int read_from_bdev_async(struct zram *zram, struct page *page, +static void read_from_bdev_async(struct zram *zram, struct page *page, unsigned long entry, struct bio *parent) { struct bio *bio; bio = bio_alloc(zram->bdev, 1, parent ? parent->bi_opf : REQ_OP_READ, GFP_NOIO); - if (!bio) - return -ENOMEM; bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); - if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { - bio_put(bio); - return -EIO; - } + __bio_add_page(bio, page, PAGE_SIZE, 0); if (!parent) bio->bi_end_io = zram_page_end_io; @@ -610,7 +602,6 @@ static int read_from_bdev_async(struct zram *zram, struct page *page, bio_chain(bio, parent); submit_bio(bio); - return 1; } #define PAGE_WB_SIG "page_index=" @@ -840,7 +831,8 @@ static int read_from_bdev(struct zram *zram, struct page *page, return -EIO; return read_from_bdev_sync(zram, page, entry, parent); } - return read_from_bdev_async(zram, page, entry, parent); + read_from_bdev_async(zram, page, entry, parent); + return 1; } #else static inline void reset_bdev(struct zram *zram) {}; -- GitLab From 4e3c87b9421df497d849ae61aab9762de7f66afb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:58 +0200 Subject: [PATCH 3286/5631] zram: fix synchronous reads Currently nothing waits for the synchronous reads before accessing the data. Switch them to an on-stack bio and submit_bio_wait to make sure the I/O has actually completed when the work item has been flushed. This also removes the call to page_endio that would unlock a page that has never been locked. Drop the partial_io/sync flag, as chaining only makes sense for the asynchronous reads of the entire page. Link: https://lkml.kernel.org/r/20230411171459.567614-17-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 60 +++++++++++++---------------------- 1 file changed, 22 insertions(+), 38 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 24b31957d9e8..a2b98100cbda 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -55,7 +55,7 @@ static const struct block_device_operations zram_devops; static void zram_free_page(struct zram *zram, size_t index); static int zram_read_page(struct zram *zram, struct page *page, u32 index, - struct bio *bio, bool partial_io); + struct bio *parent); static int zram_slot_trylock(struct zram *zram, u32 index) { @@ -576,31 +576,15 @@ static void free_block_bdev(struct zram *zram, unsigned long blk_idx) atomic64_dec(&zram->stats.bd_count); } -static void zram_page_end_io(struct bio *bio) -{ - struct page *page = bio_first_page_all(bio); - - page_endio(page, op_is_write(bio_op(bio)), - blk_status_to_errno(bio->bi_status)); - bio_put(bio); -} - static void read_from_bdev_async(struct zram *zram, struct page *page, unsigned long entry, struct bio *parent) { struct bio *bio; - bio = bio_alloc(zram->bdev, 1, parent ? parent->bi_opf : REQ_OP_READ, - GFP_NOIO); - + bio = bio_alloc(zram->bdev, 1, parent->bi_opf, GFP_NOIO); bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); __bio_add_page(bio, page, PAGE_SIZE, 0); - - if (!parent) - bio->bi_end_io = zram_page_end_io; - else - bio_chain(bio, parent); - + bio_chain(bio, parent); submit_bio(bio); } @@ -705,7 +689,7 @@ static ssize_t writeback_store(struct device *dev, /* Need for hugepage writeback racing */ zram_set_flag(zram, index, ZRAM_IDLE); zram_slot_unlock(zram, index); - if (zram_read_page(zram, page, index, NULL, false)) { + if (zram_read_page(zram, page, index, NULL)) { zram_slot_lock(zram, index); zram_clear_flag(zram, index, ZRAM_UNDER_WB); zram_clear_flag(zram, index, ZRAM_IDLE); @@ -785,18 +769,19 @@ struct zram_work { struct work_struct work; struct zram *zram; unsigned long entry; - struct bio *bio; struct page *page; }; static void zram_sync_read(struct work_struct *work) { struct zram_work *zw = container_of(work, struct zram_work, work); - struct zram *zram = zw->zram; - unsigned long entry = zw->entry; - struct bio *bio = zw->bio; + struct bio_vec bv; + struct bio bio; - read_from_bdev_async(zram, zw->page, entry, bio); + bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ); + bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9); + __bio_add_page(&bio, zw->page, PAGE_SIZE, 0); + submit_bio_wait(&bio); } /* @@ -805,14 +790,13 @@ static void zram_sync_read(struct work_struct *work) * use a worker thread context. */ static int read_from_bdev_sync(struct zram *zram, struct page *page, - unsigned long entry, struct bio *bio) + unsigned long entry) { struct zram_work work; work.page = page; work.zram = zram; work.entry = entry; - work.bio = bio; INIT_WORK_ONSTACK(&work.work, zram_sync_read); queue_work(system_unbound_wq, &work.work); @@ -823,13 +807,13 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page, } static int read_from_bdev(struct zram *zram, struct page *page, - unsigned long entry, struct bio *parent, bool sync) + unsigned long entry, struct bio *parent) { atomic64_inc(&zram->stats.bd_reads); - if (sync) { + if (!parent) { if (WARN_ON_ONCE(!IS_ENABLED(ZRAM_PARTIAL_IO))) return -EIO; - return read_from_bdev_sync(zram, page, entry, parent); + return read_from_bdev_sync(zram, page, entry); } read_from_bdev_async(zram, page, entry, parent); return 1; @@ -837,7 +821,7 @@ static int read_from_bdev(struct zram *zram, struct page *page, #else static inline void reset_bdev(struct zram *zram) {}; static int read_from_bdev(struct zram *zram, struct page *page, - unsigned long entry, struct bio *parent, bool sync) + unsigned long entry, struct bio *parent) { return -EIO; } @@ -1370,7 +1354,7 @@ static int zram_read_from_zspool(struct zram *zram, struct page *page, } static int zram_read_page(struct zram *zram, struct page *page, u32 index, - struct bio *bio, bool partial_io) + struct bio *parent) { int ret; @@ -1387,7 +1371,7 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, zram_slot_unlock(zram, index); ret = read_from_bdev(zram, page, zram_get_element(zram, index), - bio, partial_io); + parent); } /* Should NEVER happen. Return bio error if it does. */ @@ -1402,14 +1386,14 @@ static int zram_read_page(struct zram *zram, struct page *page, u32 index, * always expects a full page for the output. */ static int zram_bvec_read_partial(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset, struct bio *bio) + u32 index, int offset) { struct page *page = alloc_page(GFP_NOIO); int ret; if (!page) return -ENOMEM; - ret = zram_read_page(zram, page, index, bio, true); + ret = zram_read_page(zram, page, index, NULL); if (likely(!ret)) memcpy_to_bvec(bvec, page_address(page) + offset); __free_page(page); @@ -1420,8 +1404,8 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, u32 index, int offset, struct bio *bio) { if (is_partial_io(bvec)) - return zram_bvec_read_partial(zram, bvec, index, offset, bio); - return zram_read_page(zram, bvec->bv_page, index, bio, false); + return zram_bvec_read_partial(zram, bvec, index, offset); + return zram_read_page(zram, bvec->bv_page, index, bio); } static int zram_write_page(struct zram *zram, struct page *page, u32 index) @@ -1561,7 +1545,7 @@ static int zram_bvec_write_partial(struct zram *zram, struct bio_vec *bvec, if (!page) return -ENOMEM; - ret = zram_read_page(zram, page, index, bio, true); + ret = zram_read_page(zram, page, index, bio); if (!ret) { memcpy_from_bvec(page_address(page) + offset, bvec); ret = zram_write_page(zram, page, index); -- GitLab From 1e9460d132cc728941621f0f7a7b03a7d1c469af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 11 Apr 2023 19:14:59 +0200 Subject: [PATCH 3287/5631] zram: return errors from read_from_bdev_sync Propagate read errors to the caller instead of dropping them on the floor, and stop returning the somewhat dangerous 1 on success from read_from_bdev*. Link: https://lkml.kernel.org/r/20230411171459.567614-18-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Jens Axboe Signed-off-by: Andrew Morton --- drivers/block/zram/zram_drv.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index a2b98100cbda..38a5d3a2836b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -770,6 +770,7 @@ struct zram_work { struct zram *zram; unsigned long entry; struct page *page; + int error; }; static void zram_sync_read(struct work_struct *work) @@ -781,7 +782,7 @@ static void zram_sync_read(struct work_struct *work) bio_init(&bio, zw->zram->bdev, &bv, 1, REQ_OP_READ); bio.bi_iter.bi_sector = zw->entry * (PAGE_SIZE >> 9); __bio_add_page(&bio, zw->page, PAGE_SIZE, 0); - submit_bio_wait(&bio); + zw->error = submit_bio_wait(&bio); } /* @@ -803,7 +804,7 @@ static int read_from_bdev_sync(struct zram *zram, struct page *page, flush_work(&work.work); destroy_work_on_stack(&work.work); - return 1; + return work.error; } static int read_from_bdev(struct zram *zram, struct page *page, @@ -816,7 +817,7 @@ static int read_from_bdev(struct zram *zram, struct page *page, return read_from_bdev_sync(zram, page, entry); } read_from_bdev_async(zram, page, entry, parent); - return 1; + return 0; } #else static inline void reset_bdev(struct zram *zram) {}; -- GitLab From d6e61afb40e2208d90470f4b2012c4c8092863b9 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:07 +0200 Subject: [PATCH 3288/5631] selftests/mm: reuse read_pmd_pagesize() in COW selftest Patch series "mm: (pte|pmd)_mkdirty() should not unconditionally allow for write access". This is the follow-up on [1], adding selftests (testing for known issues we added workarounds for and other issues that haven't been fixed yet), fixing sparc64, reverting the workarounds, and perform one cleanup. The patch from [1] was modified slightly (updated/extended patch description, dropped one unnecessary NOP instruction from the ASM in __pte_mkhwwrite()). Retested on x86_64 and sparc64 (sun4u in QEMU). I scanned most architectures to make sure their (pte|pmd)_mkdirty() handling is correct. To be sure, we can run the selftests and find out if other architectures are still affectes (loongarch was fixed recently as well). Based on master for now. I don't expect surprises regarding mm-tress, but I can rebase if there are any problems. This patch (of 6): The COW selftest can deal with THP not being configured. So move error handling of read_pmd_pagesize() into the callers such that we can reuse it in the COW selftest. Link: https://lkml.kernel.org/r/20230411142512.438404-1-david@redhat.com Link: https://lkml.kernel.org/r/20221212130213.136267-1-david@redhat.com [1] Link: https://lkml.kernel.org/r/20230411142512.438404-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/cow.c | 33 +++---------------- tools/testing/selftests/mm/khugepaged.c | 4 +++ tools/testing/selftests/mm/soft-dirty.c | 3 ++ .../selftests/mm/split_huge_page_test.c | 4 +++ tools/testing/selftests/mm/vm_util.c | 4 +-- 5 files changed, 17 insertions(+), 31 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 0eb2e8180aa5..dc9d6fe86028 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -45,34 +45,6 @@ static size_t hugetlbsizes[10]; static int gup_fd; static bool has_huge_zeropage; -static void detect_thpsize(void) -{ - int fd = open("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", - O_RDONLY); - size_t size = 0; - char buf[15]; - int ret; - - if (fd < 0) - return; - - ret = pread(fd, buf, sizeof(buf), 0); - if (ret > 0 && ret < sizeof(buf)) { - buf[ret] = 0; - - size = strtoul(buf, NULL, 10); - if (size < pagesize) - size = 0; - if (size > 0) { - thpsize = size; - ksft_print_msg("[INFO] detected THP size: %zu KiB\n", - thpsize / 1024); - } - } - - close(fd); -} - static void detect_huge_zeropage(void) { int fd = open("/sys/kernel/mm/transparent_hugepage/use_zero_page", @@ -1741,7 +1713,10 @@ int main(int argc, char **argv) int err; pagesize = getpagesize(); - detect_thpsize(); + thpsize = read_pmd_pagesize(); + if (thpsize) + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", + thpsize / 1024); detect_hugetlbsizes(); detect_huge_zeropage(); diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 64126c8cd561..97adc0f34f9c 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1476,6 +1476,10 @@ int main(int argc, const char **argv) page_size = getpagesize(); hpage_pmd_size = read_pmd_pagesize(); + if (!hpage_pmd_size) { + printf("Reading PMD pagesize failed"); + exit(EXIT_FAILURE); + } hpage_pmd_nr = hpage_pmd_size / page_size; default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 21d8830c5f24..cc5f144430d4 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -80,6 +80,9 @@ static void test_hugepage(int pagemap_fd, int pagesize) int i, ret; size_t hpage_len = read_pmd_pagesize(); + if (!hpage_len) + ksft_exit_fail_msg("Reading PMD pagesize failed"); + map = memalign(hpage_len, hpage_len); if (!map) ksft_exit_fail_msg("memalign failed\n"); diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index b8558c7f1a39..0e74635c8c3d 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -300,6 +300,10 @@ int main(int argc, char **argv) pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); + if (!pmd_pagesize) { + printf("Reading PMD pagesize failed\n"); + exit(EXIT_FAILURE); + } split_pmd_thp(); split_pte_mapped_thp(); diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 40e795624ff3..8dc74dd022c2 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -84,12 +84,12 @@ uint64_t read_pmd_pagesize(void) fd = open(PMD_SIZE_FILE_PATH, O_RDONLY); if (fd == -1) - ksft_exit_fail_msg("Open hpage_pmd_size failed\n"); + return 0; num_read = read(fd, buf, 19); if (num_read < 1) { close(fd); - ksft_exit_fail_msg("Read hpage_pmd_size failed\n"); + return 0; } buf[num_read] = '\0'; close(fd); -- GitLab From 9eac40fc0cc7b5bbc405af3b94cbe8aeb680ab26 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:08 +0200 Subject: [PATCH 3289/5631] selftests/mm: mkdirty: test behavior of (pte|pmd)_mkdirty on VMAs without write permissions Let's add some tests that trigger (pte|pmd)_mkdirty on VMAs without write permissions. If an architecture implementation is wrong, we might accidentally set the PTE/PMD writable and allow for write access in a VMA without write permissions. The tests include reproducers for the two issues recently discovered and worked-around in core-MM for now: (1) commit 624a2c94f5b7 ("Partly revert "mm/thp: carry over dirty bit when thp splits on pmd"") (2) commit 96a9c287e25d ("mm/migrate: fix wrongly apply write bit after mkdirty on sparc64") In addition, some other tests that reveal further issues. All tests pass under x86_64: ./mkdirty # [INFO] detected THP size: 2048 KiB TAP version 13 1..6 # [INFO] PTRACE write access ok 1 SIGSEGV generated, page not modified # [INFO] PTRACE write access to THP ok 2 SIGSEGV generated, page not modified # [INFO] Page migration ok 3 SIGSEGV generated, page not modified # [INFO] Page migration of THP ok 4 SIGSEGV generated, page not modified # [INFO] PTE-mapping a THP ok 5 SIGSEGV generated, page not modified # [INFO] UFFDIO_COPY ok 6 SIGSEGV generated, page not modified # Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0 But some fail on sparc64: ./mkdirty # [INFO] detected THP size: 8192 KiB TAP version 13 1..6 # [INFO] PTRACE write access not ok 1 SIGSEGV generated, page not modified # [INFO] PTRACE write access to THP not ok 2 SIGSEGV generated, page not modified # [INFO] Page migration ok 3 SIGSEGV generated, page not modified # [INFO] Page migration of THP ok 4 SIGSEGV generated, page not modified # [INFO] PTE-mapping a THP ok 5 SIGSEGV generated, page not modified # [INFO] UFFDIO_COPY not ok 6 SIGSEGV generated, page not modified Bail out! 3 out of 6 tests failed # Totals: pass:3 fail:3 xfail:0 xpass:0 skip:0 error:0 Reverting both above commits makes all tests fail on sparc64: ./mkdirty # [INFO] detected THP size: 8192 KiB TAP version 13 1..6 # [INFO] PTRACE write access not ok 1 SIGSEGV generated, page not modified # [INFO] PTRACE write access to THP not ok 2 SIGSEGV generated, page not modified # [INFO] Page migration not ok 3 SIGSEGV generated, page not modified # [INFO] Page migration of THP not ok 4 SIGSEGV generated, page not modified # [INFO] PTE-mapping a THP not ok 5 SIGSEGV generated, page not modified # [INFO] UFFDIO_COPY not ok 6 SIGSEGV generated, page not modified Bail out! 6 out of 6 tests failed # Totals: pass:0 fail:6 xfail:0 xpass:0 skip:0 error:0 The tests are useful to detect other problematic archs, to verify new arch fixes, and to stop such issues from reappearing in the future. For now, we don't add any hugetlb tests. Link: https://lkml.kernel.org/r/20230411142512.438404-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 2 + tools/testing/selftests/mm/mkdirty.c | 379 +++++++++++++++++++++++++++ 2 files changed, 381 insertions(+) create mode 100644 tools/testing/selftests/mm/mkdirty.c diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index c31d952cff68..8235dddbbbc6 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -47,6 +47,7 @@ TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate TEST_GEN_FILES += memfd_secret TEST_GEN_FILES += migration +TEST_GEN_PROGS += mkdirty TEST_GEN_FILES += mlock-random-test TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mrelease_test @@ -108,6 +109,7 @@ $(OUTPUT)/cow: vm_util.c $(OUTPUT)/khugepaged: vm_util.c $(OUTPUT)/ksm_functional_tests: vm_util.c $(OUTPUT)/madv_populate: vm_util.c +$(OUTPUT)/mkdirty: vm_util.c $(OUTPUT)/soft-dirty: vm_util.c $(OUTPUT)/split_huge_page_test: vm_util.c $(OUTPUT)/userfaultfd: vm_util.c diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c new file mode 100644 index 000000000000..6d71d972997b --- /dev/null +++ b/tools/testing/selftests/mm/mkdirty.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test handling of code that might set PTE/PMD dirty in read-only VMAs. + * Setting a PTE/PMD dirty must not accidentally set the PTE/PMD writable. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static size_t thpsize; +static int mem_fd; +static int pagemap_fd; +static sigjmp_buf env; + +static void signal_handler(int sig) +{ + if (sig == SIGSEGV) + siglongjmp(env, 1); + siglongjmp(env, 2); +} + +static void do_test_write_sigsegv(char *mem) +{ + char orig = *mem; + int ret; + + if (signal(SIGSEGV, signal_handler) == SIG_ERR) { + ksft_test_result_fail("signal() failed\n"); + return; + } + + ret = sigsetjmp(env, 1); + if (!ret) + *mem = orig + 1; + + if (signal(SIGSEGV, SIG_DFL) == SIG_ERR) + ksft_test_result_fail("signal() failed\n"); + + ksft_test_result(ret == 1 && *mem == orig, + "SIGSEGV generated, page not modified\n"); +} + +static char *mmap_thp_range(int prot, char **_mmap_mem, size_t *_mmap_size) +{ + const size_t mmap_size = 2 * thpsize; + char *mem, *mmap_mem; + + mmap_mem = mmap(NULL, mmap_size, prot, MAP_PRIVATE|MAP_ANON, + -1, 0); + if (mmap_mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return MAP_FAILED; + } + mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1)); + + if (madvise(mem, thpsize, MADV_HUGEPAGE)) { + ksft_test_result_skip("MADV_HUGEPAGE failed\n"); + munmap(mmap_mem, mmap_size); + return MAP_FAILED; + } + + *_mmap_mem = mmap_mem; + *_mmap_size = mmap_size; + return mem; +} + +static void test_ptrace_write(void) +{ + char data = 1; + char *mem; + int ret; + + ksft_print_msg("[INFO] PTRACE write access\n"); + + mem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); + if (mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + /* Fault in the shared zeropage. */ + if (*mem != 0) { + ksft_test_result_fail("Memory not zero\n"); + goto munmap; + } + + /* + * Unshare the page (populating a fresh anon page that might be set + * dirty in the PTE) in the read-only VMA using ptrace (FOLL_FORCE). + */ + lseek(mem_fd, (uintptr_t) mem, SEEK_SET); + ret = write(mem_fd, &data, 1); + if (ret != 1 || *mem != data) { + ksft_test_result_fail("write() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mem, pagesize); +} + +static void test_ptrace_write_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + char data = 1; + int ret; + + ksft_print_msg("[INFO] PTRACE write access to THP\n"); + + mem = mmap_thp_range(PROT_READ, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first subpage in the read-only VMA using + * ptrace(FOLL_FORCE), eventually placing a fresh THP that is marked + * dirty in the PMD. + */ + lseek(mem_fd, (uintptr_t) mem, SEEK_SET); + ret = write(mem_fd, &data, 1); + if (ret != 1 || *mem != data) { + ksft_test_result_fail("write() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +static void test_page_migration(void) +{ + char *mem; + + ksft_print_msg("[INFO] Page migration\n"); + + mem = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, + -1, 0); + if (mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + /* Populate a fresh page and dirty it. */ + memset(mem, 1, pagesize); + if (mprotect(mem, pagesize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* Trigger page migration. Might not be available or fail. */ + if (syscall(__NR_mbind, mem, pagesize, MPOL_LOCAL, NULL, 0x7fful, + MPOL_MF_MOVE)) { + ksft_test_result_skip("mbind() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mem, pagesize); +} + +static void test_page_migration_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + + ksft_print_msg("[INFO] Page migration of THP\n"); + + mem = mmap_thp_range(PROT_READ|PROT_WRITE, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first page, which might populate a fresh anon THP + * and dirty it. + */ + memset(mem, 1, pagesize); + if (mprotect(mem, thpsize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + /* Trigger page migration. Might not be available or fail. */ + if (syscall(__NR_mbind, mem, thpsize, MPOL_LOCAL, NULL, 0x7fful, + MPOL_MF_MOVE)) { + ksft_test_result_skip("mbind() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +static void test_pte_mapped_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + + ksft_print_msg("[INFO] PTE-mapping a THP\n"); + + mem = mmap_thp_range(PROT_READ|PROT_WRITE, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first page, which might populate a fresh anon THP + * and dirty it. + */ + memset(mem, 1, pagesize); + if (mprotect(mem, thpsize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + /* Trigger PTE-mapping the THP by mprotect'ing the last subpage. */ + if (mprotect(mem + thpsize - pagesize, pagesize, + PROT_READ|PROT_WRITE)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +#ifdef __NR_userfaultfd +static void test_uffdio_copy(void) +{ + struct uffdio_register uffdio_register; + struct uffdio_copy uffdio_copy; + struct uffdio_api uffdio_api; + char *dst, *src; + int uffd; + + ksft_print_msg("[INFO] UFFDIO_COPY\n"); + + src = malloc(pagesize); + memset(src, 1, pagesize); + dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); + if (dst == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + ksft_test_result_skip("__NR_userfaultfd failed\n"); + goto munmap; + } + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { + ksft_test_result_fail("UFFDIO_API failed\n"); + goto close_uffd; + } + + uffdio_register.range.start = (unsigned long) dst; + uffdio_register.range.len = pagesize; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + ksft_test_result_fail("UFFDIO_REGISTER failed\n"); + goto close_uffd; + } + + /* Place a page in a read-only VMA, which might set the PTE dirty. */ + uffdio_copy.dst = (unsigned long) dst; + uffdio_copy.src = (unsigned long) src; + uffdio_copy.len = pagesize; + uffdio_copy.mode = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) { + ksft_test_result_fail("UFFDIO_COPY failed\n"); + goto close_uffd; + } + + do_test_write_sigsegv(dst); +close_uffd: + close(uffd); +munmap: + munmap(dst, pagesize); + free(src); +#endif /* __NR_userfaultfd */ +} + +int main(void) +{ + int err, tests = 2; + + pagesize = getpagesize(); + thpsize = read_pmd_pagesize(); + if (thpsize) { + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", + thpsize / 1024); + tests += 3; + } +#ifdef __NR_userfaultfd + tests += 1; +#endif /* __NR_userfaultfd */ + + ksft_print_header(); + ksft_set_plan(tests); + + mem_fd = open("/proc/self/mem", O_RDWR); + if (mem_fd < 0) + ksft_exit_fail_msg("opening /proc/self/mem failed\n"); + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("opening /proc/self/pagemap failed\n"); + + /* + * On some ptrace(FOLL_FORCE) write access via /proc/self/mem in + * read-only VMAs, the kernel may set the PTE/PMD dirty. + */ + test_ptrace_write(); + if (thpsize) + test_ptrace_write_thp(); + /* + * On page migration, the kernel may set the PTE/PMD dirty when + * remapping the page. + */ + test_page_migration(); + if (thpsize) + test_page_migration_thp(); + /* PTE-mapping a THP might propagate the dirty PMD bit to the PTEs. */ + if (thpsize) + test_pte_mapped_thp(); + /* Placing a fresh page via userfaultfd may set the PTE dirty. */ +#ifdef __NR_userfaultfd + test_uffdio_copy(); +#endif /* __NR_userfaultfd */ + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} -- GitLab From fa2e71a6fcee495e16176bd606e7121332627a16 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:09 +0200 Subject: [PATCH 3290/5631] sparc/mm: don't unconditionally set HW writable bit when setting PTE dirty on 64bit On sparc64, there is no HW modified bit, therefore, SW tracks via a SW bit if the PTE is dirty via pte_mkdirty(). However, pte_mkdirty() currently also unconditionally sets the HW writable bit, which is wrong. pte_mkdirty() is not supposed to make a PTE actually writable, unless the SW writable bit -- pte_write() -- indicates that the PTE is not write-protected. Fortunately, sparc64 also defines a SW writable bit. For example, this already turned into a problem in the context of THP splitting as documented in commit 624a2c94f5b7 ("Partly revert "mm/thp: carry over dirty bit when thp splits on pmd""), and for page migration, as documented in commit 96a9c287e25d ("mm/migrate: fix wrongly apply write bit after mkdirty on sparc64"). Also, we might want to use the dirty PTE bit in the context of KSM with shared zeropage [1], whereby setting the page writable would be problematic. But more general, any code that might end up setting a PTE/PMD dirty inside a VM without write permissions is possibly broken, Before this commit (sun4u in QEMU): root@debian:~/linux/tools/testing/selftests/mm# ./mkdirty # [INFO] detected THP size: 8192 KiB TAP version 13 1..6 # [INFO] PTRACE write access not ok 1 SIGSEGV generated, page not modified # [INFO] PTRACE write access to THP not ok 2 SIGSEGV generated, page not modified # [INFO] Page migration ok 3 SIGSEGV generated, page not modified # [INFO] Page migration of THP ok 4 SIGSEGV generated, page not modified # [INFO] PTE-mapping a THP ok 5 SIGSEGV generated, page not modified # [INFO] UFFDIO_COPY not ok 6 SIGSEGV generated, page not modified Bail out! 3 out of 6 tests failed # Totals: pass:3 fail:3 xfail:0 xpass:0 skip:0 error:0 Test #3,#4,#5 pass ever since we added some MM workarounds, the underlying issue remains. Let's fix the remaining issues and prepare for reverting the workarounds by setting the HW writable bit only if both, the SW dirty bit and the SW writable bit are set. We have to move pte_dirty() and pte_write() up. The code patching mechanism and handling constants > 22bit is a bit special on sparc64. The ASM logic in pte_mkdirty() and pte_mkwrite() match the logic in pte_mkold() to create the mask depending on the machine type. The ASM logic in __pte_mkhwwrite() matches the logic in pte_present(), just using an "or" instead of an "and" instruction. With this commit (sun4u in QEMU): root@debian:~/linux/tools/testing/selftests/mm# ./mkdirty # [INFO] detected THP size: 8192 KiB TAP version 13 1..6 # [INFO] PTRACE write access ok 1 SIGSEGV generated, page not modified # [INFO] PTRACE write access to THP ok 2 SIGSEGV generated, page not modified # [INFO] Page migration ok 3 SIGSEGV generated, page not modified # [INFO] Page migration of THP ok 4 SIGSEGV generated, page not modified # [INFO] PTE-mapping a THP ok 5 SIGSEGV generated, page not modified # [INFO] UFFDIO_COPY ok 6 SIGSEGV generated, page not modified # Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0 This handling seems to have been in place forever. [1] https://lkml.kernel.org/r/533a7c3d-3a48-b16b-b421-6e8386e0b142@redhat.com Link: https://lkml.kernel.org/r/20230411142512.438404-4-david@redhat.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- arch/sparc/include/asm/pgtable_64.h | 116 ++++++++++++++++------------ 1 file changed, 66 insertions(+), 50 deletions(-) diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 2dc8d4641734..5563efa1a19f 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -357,6 +357,42 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) */ #define pgprot_noncached pgprot_noncached +static inline unsigned long pte_dirty(pte_t pte) +{ + unsigned long mask; + + __asm__ __volatile__( + "\n661: mov %1, %0\n" + " nop\n" + " .section .sun4v_2insn_patch, \"ax\"\n" + " .word 661b\n" + " sethi %%uhi(%2), %0\n" + " sllx %0, 32, %0\n" + " .previous\n" + : "=r" (mask) + : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V)); + + return (pte_val(pte) & mask); +} + +static inline unsigned long pte_write(pte_t pte) +{ + unsigned long mask; + + __asm__ __volatile__( + "\n661: mov %1, %0\n" + " nop\n" + " .section .sun4v_2insn_patch, \"ax\"\n" + " .word 661b\n" + " sethi %%uhi(%2), %0\n" + " sllx %0, 32, %0\n" + " .previous\n" + : "=r" (mask) + : "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V)); + + return (pte_val(pte) & mask); +} + #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte @@ -418,28 +454,43 @@ static inline bool is_hugetlb_pte(pte_t pte) } #endif +static inline pte_t __pte_mkhwwrite(pte_t pte) +{ + unsigned long val = pte_val(pte); + + /* + * Note: we only want to set the HW writable bit if the SW writable bit + * and the SW dirty bit are set. + */ + __asm__ __volatile__( + "\n661: or %0, %2, %0\n" + " .section .sun4v_1insn_patch, \"ax\"\n" + " .word 661b\n" + " or %0, %3, %0\n" + " .previous\n" + : "=r" (val) + : "0" (val), "i" (_PAGE_W_4U), "i" (_PAGE_W_4V)); + + return __pte(val); +} + static inline pte_t pte_mkdirty(pte_t pte) { - unsigned long val = pte_val(pte), tmp; + unsigned long val = pte_val(pte), mask; __asm__ __volatile__( - "\n661: or %0, %3, %0\n" - " nop\n" - "\n662: nop\n" + "\n661: mov %1, %0\n" " nop\n" " .section .sun4v_2insn_patch, \"ax\"\n" " .word 661b\n" - " sethi %%uhi(%4), %1\n" - " sllx %1, 32, %1\n" - " .word 662b\n" - " or %1, %%lo(%4), %1\n" - " or %0, %1, %0\n" + " sethi %%uhi(%2), %0\n" + " sllx %0, 32, %0\n" " .previous\n" - : "=r" (val), "=r" (tmp) - : "0" (val), "i" (_PAGE_MODIFIED_4U | _PAGE_W_4U), - "i" (_PAGE_MODIFIED_4V | _PAGE_W_4V)); + : "=r" (mask) + : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V)); - return __pte(val); + pte = __pte(val | mask); + return pte_write(pte) ? __pte_mkhwwrite(pte) : pte; } static inline pte_t pte_mkclean(pte_t pte) @@ -481,7 +532,8 @@ static inline pte_t pte_mkwrite(pte_t pte) : "=r" (mask) : "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V)); - return __pte(val | mask); + pte = __pte(val | mask); + return pte_dirty(pte) ? __pte_mkhwwrite(pte) : pte; } static inline pte_t pte_wrprotect(pte_t pte) @@ -584,42 +636,6 @@ static inline unsigned long pte_young(pte_t pte) return (pte_val(pte) & mask); } -static inline unsigned long pte_dirty(pte_t pte) -{ - unsigned long mask; - - __asm__ __volatile__( - "\n661: mov %1, %0\n" - " nop\n" - " .section .sun4v_2insn_patch, \"ax\"\n" - " .word 661b\n" - " sethi %%uhi(%2), %0\n" - " sllx %0, 32, %0\n" - " .previous\n" - : "=r" (mask) - : "i" (_PAGE_MODIFIED_4U), "i" (_PAGE_MODIFIED_4V)); - - return (pte_val(pte) & mask); -} - -static inline unsigned long pte_write(pte_t pte) -{ - unsigned long mask; - - __asm__ __volatile__( - "\n661: mov %1, %0\n" - " nop\n" - " .section .sun4v_2insn_patch, \"ax\"\n" - " .word 661b\n" - " sethi %%uhi(%2), %0\n" - " sllx %0, 32, %0\n" - " .previous\n" - : "=r" (mask) - : "i" (_PAGE_WRITE_4U), "i" (_PAGE_WRITE_4V)); - - return (pte_val(pte) & mask); -} - static inline unsigned long pte_exec(pte_t pte) { unsigned long mask; -- GitLab From 3c811f7883c4ee5a34ba4354381bde062888dd31 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:10 +0200 Subject: [PATCH 3291/5631] mm/migrate: revert "mm/migrate: fix wrongly apply write bit after mkdirty on sparc64" This reverts commit 96a9c287e25d ("mm/migrate: fix wrongly apply write bit after mkdirty on sparc64"). Now that sparc64 mkdirty handling is fixed and no longer sets a PTE/PMD writable that shouldn't be writable, let's revert the temporary fix. The mkdirty mm selftest still passes with this change on sparc64. Note that loongarch handling was fixed in commit bf2f34a506e6 ("LoongArch: Set _PAGE_DIRTY only if _PAGE_WRITE is set in {pmd,pte}_mkdirty()"). Link: https://lkml.kernel.org/r/20230411142512.438404-5-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/huge_memory.c | 6 ++---- mm/migrate.c | 2 -- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0dbce09916c4..00a7a98f2ba2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3276,6 +3276,8 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); + if (is_writable_migration_entry(entry)) + pmde = maybe_pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_mkuffd_wp(pmde); if (!is_migration_entry_young(entry)) @@ -3283,10 +3285,6 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) /* NOTE: this may contain setting soft-dirty on some archs */ if (PageDirty(new) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); - if (is_writable_migration_entry(entry)) - pmde = maybe_pmd_mkwrite(pmde, vma); - else - pmde = pmd_wrprotect(pmde); if (PageAnon(new)) { rmap_t rmap_flags = RMAP_COMPOUND; diff --git a/mm/migrate.c b/mm/migrate.c index afe21c48dc6e..41f2154d66ad 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -225,8 +225,6 @@ static bool remove_migration_pte(struct folio *folio, pte = maybe_mkwrite(pte, vma); else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); - else - pte = pte_wrprotect(pte); if (folio_test_anon(folio) && !is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; -- GitLab From 5436d6556937de6236ffa1829550d13702569dab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:11 +0200 Subject: [PATCH 3292/5631] mm/huge_memory: revert "Partly revert "mm/thp: carry over dirty bit when thp splits on pmd"" This reverts commit 624a2c94f5b7 ("Partly revert "mm/thp: carry over dirty bit when thp splits on pmd"") and the fixup in commit e833bc503405 ("mm/thp: re-apply mkdirty for small pages after split"). Now that sparc64 mkdirty handling is fixed and no longer sets a PTE/PMD writable that shouldn't be writable, let's revert the temporary fix and remove the stale comment. The mkdirty mm selftest still passes with this change on sparc64. Note that loongarch handling was fixed in commit bf2f34a506e6 ("LoongArch: Set _PAGE_DIRTY only if _PAGE_WRITE is set in {pmd,pte}_mkdirty()") Link: https://lkml.kernel.org/r/20230411142512.438404-6-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/huge_memory.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 00a7a98f2ba2..5700b1c727b6 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2236,18 +2236,13 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = maybe_mkwrite(entry, vma); if (anon_exclusive) SetPageAnonExclusive(page + i); + if (!write) + entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); /* NOTE: this may set soft-dirty too on some archs */ if (dirty) entry = pte_mkdirty(entry); - /* - * NOTE: this needs to happen after pte_mkdirty, - * because some archs (sparc64, loongarch) could - * set hw write bit when mkdirty. - */ - if (!write) - entry = pte_wrprotect(entry); if (soft_dirty) entry = pte_mksoft_dirty(entry); if (uffd_wp) -- GitLab From 1462c52e9f2b99e72022ed8979bfc969894bb3da Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 11 Apr 2023 16:25:12 +0200 Subject: [PATCH 3293/5631] mm/huge_memory: conditionally call maybe_mkwrite() and drop pte_wrprotect() in __split_huge_pmd_locked() No need to call maybe_mkwrite() to then wrprotect if the source PMD was not writable. It's worth nothing that this now allows for PTEs to be writable even if the source PMD was not writable: if vma->vm_page_prot includes write permissions. As documented in commit 931298e103c2 ("mm/userfaultfd: rely on vma->vm_page_prot in uffd_wp_range()"), any mechanism that intends to have pages wrprotected (COW, writenotify, mprotect, uffd-wp, softdirty, ...) has to properly adjust vma->vm_page_prot upfront, to not include write permissions. If vma->vm_page_prot includes write permissions, the PTE/PMD can be writable as default. This now mimics the handling in mm/migrate.c:remove_migration_pte() and in mm/huge_memory.c:remove_migration_pmd(), which has been in place for a long time (except that 96a9c287e25d ("mm/migrate: fix wrongly apply write bit after mkdirty on sparc64") temporarily changed it). Link: https://lkml.kernel.org/r/20230411142512.438404-7-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: David S. Miller Cc: Hugh Dickins Cc: Peter Xu Cc: Sam Ravnborg Cc: Shuah Khan Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/huge_memory.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5700b1c727b6..c23fa39dec92 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2233,11 +2233,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_swp_mkuffd_wp(entry); } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); - entry = maybe_mkwrite(entry, vma); + if (write) + entry = maybe_mkwrite(entry, vma); if (anon_exclusive) SetPageAnonExclusive(page + i); - if (!write) - entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); /* NOTE: this may set soft-dirty too on some archs */ -- GitLab From cd01049d9ca3788a9d1537b64aec26edc96ad0bd Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 11 Apr 2023 14:29:18 +0200 Subject: [PATCH 3294/5631] orangefs: use folios in orangefs_readahead Patch series "remove page_endio()", v3. It was decided to remove the page_endio() as per the previous RFC discussion[1] of this series and move that functionality into the caller itself. One of the side benefit of doing that is the callers have been modified to directly work on folios as page_endio() already worked on folios. As Christoph is doing ZRAM cleanups[4] which will get rid of page_endio() function usage, I removed the final patch that removes page_endio()[5]. I will send it separately after rc-1 once the zram cleanups are merged. mpage changes were tested with a simple boot testing and running a fio workload on ext2 filesystem. orangefs was tested by Mike Marshall (No code changes since he tested). This patch (of 3): Convert orangefs_readahead() from using struct page to struct folio. This conversion removes the call to page_endio() which is soon to be removed, and simplifies the final page handling. The page error flags is not required to be set in the error case as orangefs doesn't depend on them. Link: https://lkml.kernel.org/r/20230411122920.30134-1-p.raghav@samsung.com Link: https://lkml.kernel.org/r/20230411122920.30134-2-p.raghav@samsung.com Link: https://lore.kernel.org/linux-mm/ZBHcl8Pz2ULb4RGD@infradead.org/ [1] Link: https://lore.kernel.org/linux-mm/20230322135013.197076-1-p.raghav@samsung.com/ [2] Link: https://lore.kernel.org/linux-mm/8adb0770-6124-e11f-2551-6582db27ed32@samsung.com/ [3] Link: https://lore.kernel.org/linux-block/20230404150536.2142108-1-hch@lst.de/T/#t [4] Link: https://lore.kernel.org/lkml/20230403132221.94921-6-p.raghav@samsung.com/ [5] Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Tested-by: Mike Marshall Cc: Alexander Viro Cc: Christian Brauner Cc: Jens Axboe Cc: Luis Chamberlain Cc: Martin Brandenburg Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- fs/orangefs/inode.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index aefdf1d3be7c..9014bbcc8031 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -244,7 +244,7 @@ static void orangefs_readahead(struct readahead_control *rac) struct iov_iter iter; struct inode *inode = rac->mapping->host; struct xarray *i_pages; - struct page *page; + struct folio *folio; loff_t new_start = readahead_pos(rac); int ret; size_t new_len = 0; @@ -275,9 +275,10 @@ static void orangefs_readahead(struct readahead_control *rac) ret = 0; /* clean up. */ - while ((page = readahead_page(rac))) { - page_endio(page, false, ret); - put_page(page); + while ((folio = readahead_folio(rac))) { + if (!ret) + folio_mark_uptodate(folio); + folio_unlock(folio); } } -- GitLab From f0d6ca46d68670d04a43116fe07309643bac596e Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 11 Apr 2023 14:29:19 +0200 Subject: [PATCH 3295/5631] mpage: split submit_bio and bio end_io handler for reads and writes Split the submit_bio() and bio end_io handler for reads and writes similar to other aops. This is a prep patch before we convert end_io handlers to use folios. Link: https://lkml.kernel.org/r/20230411122920.30134-3-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Cc: Alexander Viro Cc: Christian Brauner Cc: Jens Axboe Cc: Luis Chamberlain Cc: Martin Brandenburg Cc: Matthew Wilcox (Oracle) Cc: Mike Marshall Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- fs/mpage.c | 54 ++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 18 deletions(-) diff --git a/fs/mpage.c b/fs/mpage.c index 22b9de5ddd68..d9540c1b7427 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -43,23 +43,41 @@ * status of that page is hard. See end_buffer_async_read() for the details. * There is no point in duplicating all that complexity. */ -static void mpage_end_io(struct bio *bio) +static void mpage_read_end_io(struct bio *bio) { struct bio_vec *bv; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, bio, iter_all) { - struct page *page = bv->bv_page; - page_endio(page, bio_op(bio), + bio_for_each_segment_all(bv, bio, iter_all) + page_endio(bv->bv_page, REQ_OP_READ, blk_status_to_errno(bio->bi_status)); - } bio_put(bio); } -static struct bio *mpage_bio_submit(struct bio *bio) +static void mpage_write_end_io(struct bio *bio) +{ + struct bio_vec *bv; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bv, bio, iter_all) + page_endio(bv->bv_page, REQ_OP_WRITE, + blk_status_to_errno(bio->bi_status)); + + bio_put(bio); +} + +static struct bio *mpage_bio_submit_read(struct bio *bio) +{ + bio->bi_end_io = mpage_read_end_io; + guard_bio_eod(bio); + submit_bio(bio); + return NULL; +} + +static struct bio *mpage_bio_submit_write(struct bio *bio) { - bio->bi_end_io = mpage_end_io; + bio->bi_end_io = mpage_write_end_io; guard_bio_eod(bio); submit_bio(bio); return NULL; @@ -265,7 +283,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) * This folio will go to BIO. Do we need to send this BIO off first? */ if (args->bio && (args->last_block_in_bio != blocks[0] - 1)) - args->bio = mpage_bio_submit(args->bio); + args->bio = mpage_bio_submit_read(args->bio); alloc_new: if (args->bio == NULL) { @@ -278,7 +296,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) length = first_hole << blkbits; if (!bio_add_folio(args->bio, folio, length, 0)) { - args->bio = mpage_bio_submit(args->bio); + args->bio = mpage_bio_submit_read(args->bio); goto alloc_new; } @@ -286,7 +304,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) nblocks = map_bh->b_size >> blkbits; if ((buffer_boundary(map_bh) && relative_block == nblocks) || (first_hole != blocks_per_page)) - args->bio = mpage_bio_submit(args->bio); + args->bio = mpage_bio_submit_read(args->bio); else args->last_block_in_bio = blocks[blocks_per_page - 1]; out: @@ -294,7 +312,7 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) confused: if (args->bio) - args->bio = mpage_bio_submit(args->bio); + args->bio = mpage_bio_submit_read(args->bio); if (!folio_test_uptodate(folio)) block_read_full_folio(folio, args->get_block); else @@ -356,7 +374,7 @@ void mpage_readahead(struct readahead_control *rac, get_block_t get_block) args.bio = do_mpage_readpage(&args); } if (args.bio) - mpage_bio_submit(args.bio); + mpage_bio_submit_read(args.bio); } EXPORT_SYMBOL(mpage_readahead); @@ -373,7 +391,7 @@ int mpage_read_folio(struct folio *folio, get_block_t get_block) args.bio = do_mpage_readpage(&args); if (args.bio) - mpage_bio_submit(args.bio); + mpage_bio_submit_read(args.bio); return 0; } EXPORT_SYMBOL(mpage_read_folio); @@ -577,7 +595,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, * This page will go to BIO. Do we need to send this BIO off first? */ if (bio && mpd->last_block_in_bio != blocks[0] - 1) - bio = mpage_bio_submit(bio); + bio = mpage_bio_submit_write(bio); alloc_new: if (bio == NULL) { @@ -596,7 +614,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, wbc_account_cgroup_owner(wbc, &folio->page, folio_size(folio)); length = first_unmapped << blkbits; if (!bio_add_folio(bio, folio, length, 0)) { - bio = mpage_bio_submit(bio); + bio = mpage_bio_submit_write(bio); goto alloc_new; } @@ -606,7 +624,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, folio_start_writeback(folio); folio_unlock(folio); if (boundary || (first_unmapped != blocks_per_page)) { - bio = mpage_bio_submit(bio); + bio = mpage_bio_submit_write(bio); if (boundary_block) { write_boundary_block(boundary_bdev, boundary_block, 1 << blkbits); @@ -618,7 +636,7 @@ static int __mpage_writepage(struct folio *folio, struct writeback_control *wbc, confused: if (bio) - bio = mpage_bio_submit(bio); + bio = mpage_bio_submit_write(bio); /* * The caller has a ref on the inode, so *mapping is stable @@ -652,7 +670,7 @@ mpage_writepages(struct address_space *mapping, blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd); if (mpd.bio) - mpage_bio_submit(mpd.bio); + mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); return ret; } -- GitLab From 09a607c9cd23d9521e7be3ab5eb94f217d7a37f5 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Tue, 11 Apr 2023 14:29:20 +0200 Subject: [PATCH 3296/5631] mpage: use folios in bio end_io handler Use folios in the bio end_io handler. This conversion does the appropriate handling on the folios in the respective end_io callback and removes the call to page_endio(), which is soon to be removed. Link: https://lkml.kernel.org/r/20230411122920.30134-4-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Christoph Hellwig Cc: Alexander Viro Cc: Christian Brauner Cc: Jens Axboe Cc: Luis Chamberlain Cc: Martin Brandenburg Cc: Matthew Wilcox (Oracle) Cc: Mike Marshall Cc: Minchan Kim Cc: Sergey Senozhatsky Signed-off-by: Andrew Morton --- fs/mpage.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) diff --git a/fs/mpage.c b/fs/mpage.c index d9540c1b7427..242e213ee064 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -45,24 +45,32 @@ */ static void mpage_read_end_io(struct bio *bio) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bv, bio, iter_all) - page_endio(bv->bv_page, REQ_OP_READ, - blk_status_to_errno(bio->bi_status)); + struct folio_iter fi; + int err = blk_status_to_errno(bio->bi_status); + + bio_for_each_folio_all(fi, bio) { + if (err) + folio_set_error(fi.folio); + else + folio_mark_uptodate(fi.folio); + folio_unlock(fi.folio); + } bio_put(bio); } static void mpage_write_end_io(struct bio *bio) { - struct bio_vec *bv; - struct bvec_iter_all iter_all; + struct folio_iter fi; + int err = blk_status_to_errno(bio->bi_status); - bio_for_each_segment_all(bv, bio, iter_all) - page_endio(bv->bv_page, REQ_OP_WRITE, - blk_status_to_errno(bio->bi_status)); + bio_for_each_folio_all(fi, bio) { + if (err) { + folio_set_error(fi.folio); + mapping_set_error(fi.folio->mapping, err); + } + folio_end_writeback(fi.folio); + } bio_put(bio); } -- GitLab From 54c4fe08f65e4c39c3d62f5d181f958e9c6c97f7 Mon Sep 17 00:00:00 2001 From: Haifeng Xu Date: Tue, 11 Apr 2023 06:17:57 +0000 Subject: [PATCH 3297/5631] mm/vmscan: simplify shrink_node() The difference between sc->nr_reclaimed and nr_reclaimed is computed three times. Introduce a new variable to record the value, so it only needs to be computed once. Link: https://lkml.kernel.org/r/20230411061757.12041-1-haifeng.xu@shopee.com Signed-off-by: Haifeng Xu Reviewed-by: David Hildenbrand Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/vmscan.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 98719e72b5e2..7f2441d6dfb2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -6463,7 +6463,7 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; - unsigned long nr_reclaimed, nr_scanned; + unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; @@ -6489,13 +6489,14 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) reclaim_state->reclaimed_slab = 0; } + nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; + /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, - sc->nr_scanned - nr_scanned, - sc->nr_reclaimed - nr_reclaimed); + sc->nr_scanned - nr_scanned, nr_node_reclaimed); - if (sc->nr_reclaimed - nr_reclaimed) + if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { @@ -6557,8 +6558,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); - if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, - sc)) + if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* -- GitLab From c14ef37871fcee9dbcaebb1bc73ac4da21547c13 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:41:14 -0400 Subject: [PATCH 3298/5631] selftests/mm: update .gitignore with two missing tests Patch series "selftests/mm: Split / Refactor userfault test", v2. This patchset splits userfaultfd.c into two tests: - uffd-stress: the "vanilla", old and powerful stress test - uffd-unit-tests: all the unit tests will be moved here This is on my todo list for a long time but I never did it for real. The uffd test is growing into a small and cute monster. I start to notice it's going harder to maintain such a test and make it useful. A few issues I found when looking at userfaultfd test: - We have a bunch of unit tests in userfaultfd.c, but they always need to be run only after a stress type. No way to not do it. - We can only run an unit test for one memory type only, if we want to do a quick smoke test to check regressions, there's no good way. The best to come currently is "bash ./run_vmtests.sh -t userfaultfd" thanks to the most recent changes to run_vmtests.sh on tagging. Still, that needs to run the stress tests always and hard to see what's wrong. - It's hard to add a new unit test to userfaultfd.c, we don't really know what's happening, not until we mostly read the whole file. - We did a bunch of useless tests, e.g. we run twice the whole suite of stress test just to verify both syscall and /dev/userfaultfd. They're all using userfaultfd_new() to create the handle, everything should really be the same underneath. One simple unit test should cover that! - We have tens of global variables in one file but shared with all the tests. Some of them are not suitable to be a global var from maintainance pov. It enforces every unit test to consider how these vars affects the stress test and vice versa, but that's logically not necessary. - Userfaultfd test is not friendly to old kernels. Mostly it only works on the latest kernel tree. It's preferrable to be run on all kernels and properly report what's missing. I'll stop here, I feel like I can still list some.. This patchset should resolve all issues above, and actually we can do even more on top. I stopped doing that until I found I already got 29 patches and 2000+ LOC changes. That's already a patchset terrible enough so we should move in small steps. After the whole set applied, "./run_vmtests.sh -t userfaultfd" looks like this: ===8<=== vm.nr_hugepages = 1024 ------------------------- running ./uffd-unit-tests ------------------------- Testing UFFDIO_API (with syscall)... done Testing UFFDIO_API (with /dev/userfaultfd)... done Testing register-ioctls on anon... done Testing register-ioctls on shmem... done Testing register-ioctls on shmem-private... done Testing register-ioctls on hugetlb... done Testing register-ioctls on hugetlb-private... done Testing zeropage on anon... done Testing zeropage on shmem... done Testing zeropage on shmem-private... done Testing zeropage on hugetlb... done Testing zeropage on hugetlb-private... done Testing pagemap on anon... done Testing wp-unpopulated on anon... done Testing minor on shmem... done Testing minor on hugetlb... done Testing minor-wp on shmem... done Testing minor-wp on hugetlb... done Testing minor-collapse on shmem... done Testing sigbus on anon... done Testing sigbus on shmem... done Testing sigbus on shmem-private... done Testing sigbus on hugetlb... done Testing sigbus on hugetlb-private... done Testing sigbus-wp on anon... done Testing sigbus-wp on shmem... done Testing sigbus-wp on shmem-private... done Testing sigbus-wp on hugetlb... done Testing sigbus-wp on hugetlb-private... done Testing events on anon... done Testing events on shmem... done Testing events on shmem-private... done Testing events on hugetlb... done Testing events on hugetlb-private... done Testing events-wp on anon... done Testing events-wp on shmem... done Testing events-wp on shmem-private... done Testing events-wp on hugetlb... done Testing events-wp on hugetlb-private... done Userfaults unit tests: pass=39, skip=0, fail=0 (total=39) [PASS] -------------------------------- running ./uffd-stress anon 20 16 -------------------------------- nr_pages: 5120, nr_pages_per_cpu: 640 bounces: 15, mode: rnd racing ver poll, userfaults: 345 missing (26+48+61+102+30+12+59+7) 1596 wp (120+139+317+346+215+67+306+86) [...] [PASS] ------------------------------------ running ./uffd-stress hugetlb 128 32 ------------------------------------ nr_pages: 64, nr_pages_per_cpu: 8 bounces: 31, mode: rnd racing ver poll, userfaults: 29 missing (6+6+6+5+4+2+0+0) 104 wp (20+19+22+18+7+12+5+1) [...] [PASS] -------------------------------------------- running ./uffd-stress hugetlb-private 128 32 -------------------------------------------- nr_pages: 64, nr_pages_per_cpu: 8 bounces: 31, mode: rnd racing ver poll, userfaults: 33 missing (12+9+7+0+5+0+0+0) 111 wp (24+25+14+14+11+17+5+1) [...] [PASS] --------------------------------- running ./uffd-stress shmem 20 16 --------------------------------- nr_pages: 5120, nr_pages_per_cpu: 640 bounces: 15, mode: rnd racing ver poll, userfaults: 247 missing (15+17+34+60+81+37+3+0) 2038 wp (180+114+276+400+381+318+165+204) [...] [PASS] ----------------------------------------- running ./uffd-stress shmem-private 20 16 ----------------------------------------- nr_pages: 5120, nr_pages_per_cpu: 640 bounces: 15, mode: rnd racing ver poll, userfaults: 235 missing (52+29+55+56+13+9+16+5) 2849 wp (218+406+461+531+328+284+430+191) [...] [PASS] SUMMARY: PASS=6 SKIP=0 FAIL=0 ===8<=== The output may be different if we miss some features (e.g., hugetlb not allocated, old kernel, less privilege of uffd handle), but they should show up with good reasons. E.g., I tried to run the unit test on my Fedora kernel and it gives me: ===8<=== UFFDIO_API (with syscall)... failed [reason: UFFDIO_API should fail with wrong api but didn't] UFFDIO_API (with /dev/userfaultfd)... skipped [reason: cannot open userfaultfd handle] zeropage on anon... done zeropage on shmem... done zeropage on shmem-private... done zeropage-hugetlb on hugetlb... done zeropage-hugetlb on hugetlb-private... done pagemap on anon... pagemap on anon... pagemap on anon... done wp-unpopulated on anon... skipped [reason: feature missing] minor on shmem... done minor on hugetlb... done minor-wp on shmem... skipped [reason: feature missing] minor-wp on hugetlb... skipped [reason: feature missing] minor-collapse on shmem... done sigbus on anon... skipped [reason: possible lack of priviledge] sigbus on shmem... skipped [reason: possible lack of priviledge] sigbus on shmem-private... skipped [reason: possible lack of priviledge] sigbus on hugetlb... skipped [reason: possible lack of priviledge] sigbus on hugetlb-private... skipped [reason: possible lack of priviledge] sigbus-wp on anon... skipped [reason: possible lack of priviledge] sigbus-wp on shmem... skipped [reason: possible lack of priviledge] sigbus-wp on shmem-private... skipped [reason: possible lack of priviledge] sigbus-wp on hugetlb... skipped [reason: possible lack of priviledge] sigbus-wp on hugetlb-private... skipped [reason: possible lack of priviledge] events on anon... skipped [reason: possible lack of priviledge] events on shmem... skipped [reason: possible lack of priviledge] events on shmem-private... skipped [reason: possible lack of priviledge] events on hugetlb... skipped [reason: possible lack of priviledge] events on hugetlb-private... skipped [reason: possible lack of priviledge] events-wp on anon... skipped [reason: possible lack of priviledge] events-wp on shmem... skipped [reason: possible lack of priviledge] events-wp on shmem-private... skipped [reason: possible lack of priviledge] events-wp on hugetlb... skipped [reason: possible lack of priviledge] events-wp on hugetlb-private... skipped [reason: possible lack of priviledge] Userfaults unit tests: pass=9, skip=24, fail=1 (total=34) ===8<=== Patch layout: - Revert "userfaultfd: don't fail on unrecognized features" Something I found when I got the UFFDIO_API test below. Axel, I still propose to revert it as a whole, but feel free to continue the discussion from the original patch thread. - selftests/mm: Update .gitignore with two missing tests - selftests/mm: Dump a summary in run_vmtests.sh - selftests/mm: Merge util.h into vm_util.h - selftests/mm: Use TEST_GEN_PROGS where proper - selftests/mm: Link vm_util.c always - selftests/mm: Merge default_huge_page_size() into one - selftests/mm: Use PM_* macros in vm_utils.h - selftests/mm: Reuse pagemap_get_entry() in vm_util.h - selftests/mm: Test UFFDIO_ZEROPAGE only when !hugetlb - selftests/mm: Drop test_uffdio_zeropage_eexist Until here, all cleanups here and there. I wanted to keep going, but I found that maybe it'll take a few more days to split the test. Hence I did a split starting from the next one, so we have a working thing first. - selftests/mm: Create uffd-common.[ch] - selftests/mm: Split uffd tests into uffd-stress and uffd-unit-tests This did the major brute force split of common codes into uffd-common.[ch]. That'll be the so far common base for stress and unit tests. Then a new unit test is created. - selftests/mm: uffd_[un]register() - selftests/mm: uffd_open_{dev|sys}() - selftests/mm: UFFDIO_API test This patch hides here to start writting the 1st unit test with UFFDIO_API, also detection of userfaultfd privileges. - selftests/mm: Drop global mem_fd in uffd tests - selftests/mm: Drop global hpage_size in uffd tests - selftests/mm: Rename uffd_stats to uffd_args - selftests/mm: Let uffd_handle_page_fault() takes wp parameter - selftests/mm: Allow allocate_area() to fail properly Some further cleanup that I noticed otherwise hard to move the tests. - selftests/mm: Add framework for uffd-unit-test The major patch provides the framework for most of the rest unit tests. - selftests/mm: Move uffd pagemap test to unit test - selftests/mm: Move uffd minor test to unit test - selftests/mm: Move uffd sig/events tests into uffd unit tests - selftests/mm: Move zeropage test into uffd unit tests Move unit tests and suite them into the new file. - selftests/mm: Workaround no way to detect uffd-minor + wp - selftests/mm: Allow uffd test to skip properly with no privilege - selftests/mm: Drop sys/dev test in uffd-stress test - selftests/mm: Add shmem-private test to uffd-stress A bunch of changes to do better on error reportings, and add shmem-private to the stress test which was long missing. - selftests/mm: Add uffdio register ioctls test One more patch to test uffdio_register.ioctls. This patch (of 30): Update .gitignore with two missing tests. Link: https://lkml.kernel.org/r/20230412163922.327282-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20230412164114.327709-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/.gitignore | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 1f8c36a9fa10..347277f2adc3 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -36,3 +36,5 @@ split_huge_page_test ksm_tests local_config.h local_config.mk +ksm_functional_tests +mdwe_test -- GitLab From c7c55fc4e39aed6a5a4d47f2201e53b1efb24ca6 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:41:17 -0400 Subject: [PATCH 3299/5631] selftests/mm: dump a summary in run_vmtests.sh Dump a summary after running whatever test specified. Useful for human runners to identify any kind of failures (besides exit code). Link: https://lkml.kernel.org/r/20230412164117.327720-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c0f93b668c0c..ddf40f883747 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -5,6 +5,9 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +count_pass=0 +count_fail=0 +count_skip=0 exitcode=0 usage() { @@ -149,11 +152,14 @@ run_test() { "$@" local ret=$? if [ $ret -eq 0 ]; then + count_pass=$(( count_pass + 1 )) echo "[PASS]" elif [ $ret -eq $ksft_skip ]; then + count_skip=$(( count_skip + 1 )) echo "[SKIP]" exitcode=$ksft_skip else + count_fail=$(( count_fail + 1 )) echo "[FAIL]" exitcode=1 fi @@ -279,4 +285,6 @@ CATEGORY="soft_dirty" run_test ./soft-dirty # COW tests CATEGORY="cow" run_test ./cow +echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" + exit $exitcode -- GitLab From af605d26a8f26e9e46fa82246dc1241efd3834a5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:41:20 -0400 Subject: [PATCH 3300/5631] selftests/mm: merge util.h into vm_util.h There're two util headers under mm/ kselftest. Merge one with another. It turns out util.h is the easy one to move. When merging, drop PAGE_SIZE / PAGE_SHIFT because they're unnecessary wrappers to page_size() / page_shift(), meanwhile rename them to psize() and pshift() so as to not conflict with some existing definitions in some test files that includes vm_util.h. Link: https://lkml.kernel.org/r/20230412164120.327731-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 4 ++ tools/testing/selftests/mm/gup_test.c | 5 +- tools/testing/selftests/mm/ksm_tests.c | 2 +- tools/testing/selftests/mm/mrelease_test.c | 11 ++- tools/testing/selftests/mm/transhuge-stress.c | 12 ++-- tools/testing/selftests/mm/util.h | 69 ------------------- tools/testing/selftests/mm/vm_util.c | 31 +++++++++ tools/testing/selftests/mm/vm_util.h | 31 +++++++++ 8 files changed, 80 insertions(+), 85 deletions(-) delete mode 100644 tools/testing/selftests/mm/util.h diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 8235dddbbbc6..9d9822b4bf24 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -113,6 +113,10 @@ $(OUTPUT)/mkdirty: vm_util.c $(OUTPUT)/soft-dirty: vm_util.c $(OUTPUT)/split_huge_page_test: vm_util.c $(OUTPUT)/userfaultfd: vm_util.c +$(OUTPUT)/gup_test: vm_util.c +$(OUTPUT)/mrelease_test: vm_util.c +$(OUTPUT)/transhuge-stress: vm_util.c +$(OUTPUT)/ksm_tests: vm_util.c ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index e43879291dac..ec2229136384 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -12,8 +12,7 @@ #include #include #include "../kselftest.h" - -#include "util.h" +#include "vm_util.h" #define MB (1UL << 20) @@ -251,7 +250,7 @@ int main(int argc, char **argv) if (touch) { gup.gup_flags |= FOLL_TOUCH; } else { - for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE) + for (; (unsigned long)p < gup.addr + size; p += psize()) p[0] = 0; } diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index f9eb4d67e0dd..74281593a124 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -12,7 +12,7 @@ #include "../kselftest.h" #include -#include "util.h" +#include "vm_util.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 6c62966ab5db..37b6d33b9e84 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -9,8 +9,7 @@ #include #include #include - -#include "util.h" +#include "vm_util.h" #include "../kselftest.h" @@ -32,7 +31,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) unsigned long i; char *buf; - buf = (char *)mmap(NULL, nr_pages * PAGE_SIZE, PROT_READ | PROT_WRITE, + buf = (char *)mmap(NULL, nr_pages * psize(), PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, 0, 0); if (buf == MAP_FAILED) { perror("mmap failed, halting the test"); @@ -40,7 +39,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) } for (i = 0; i < nr_pages; i++) - *((unsigned long *)(buf + (i * PAGE_SIZE))) = i; + *((unsigned long *)(buf + (i * psize()))) = i; /* Signal the parent that the child is ready */ if (write(pipefd, "", 1) < 0) { @@ -54,7 +53,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) timeout--; } - munmap(buf, nr_pages * PAGE_SIZE); + munmap(buf, nr_pages * psize()); return (timeout > 0) ? KSFT_PASS : KSFT_FAIL; } @@ -87,7 +86,7 @@ static int child_main(int pipefd[], size_t size) /* Allocate and fault-in memory and wait to be killed */ close(pipefd[0]); - res = alloc_noexit(MB(size) / PAGE_SIZE, pipefd[1]); + res = alloc_noexit(MB(size) / psize(), pipefd[1]); close(pipefd[1]); return res; } diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index e3f00adb1b82..ba9d37ad3a89 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -15,7 +15,7 @@ #include #include #include -#include "util.h" +#include "vm_util.h" int backing_fd = -1; int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; @@ -34,10 +34,10 @@ int main(int argc, char **argv) int pagemap_fd; ram = sysconf(_SC_PHYS_PAGES); - if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) + if (ram > SIZE_MAX / psize() / 4) ram = SIZE_MAX / 4; else - ram *= sysconf(_SC_PAGESIZE); + ram *= psize(); len = ram; while (++i < argc) { @@ -58,7 +58,7 @@ int main(int argc, char **argv) warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, - ram >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); + ram >> (20 + HPAGE_SHIFT - pshift() - 1)); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) @@ -92,7 +92,7 @@ int main(int argc, char **argv) if (pfn < 0) { nr_failed++; } else { - size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT); + size_t idx = pfn >> (HPAGE_SHIFT - pshift()); nr_succeed++; if (idx >= map_len) { @@ -108,7 +108,7 @@ int main(int argc, char **argv) } /* split transhuge page, keep last page */ - if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED)) + if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED)) err(2, "MADV_DONTNEED"); } clock_gettime(CLOCK_MONOTONIC, &b); diff --git a/tools/testing/selftests/mm/util.h b/tools/testing/selftests/mm/util.h deleted file mode 100644 index b27d26199334..000000000000 --- a/tools/testing/selftests/mm/util.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __KSELFTEST_VM_UTIL_H -#define __KSELFTEST_VM_UTIL_H - -#include -#include -#include -#include /* ffsl() */ -#include /* _SC_PAGESIZE */ - -static unsigned int __page_size; -static unsigned int __page_shift; - -static inline unsigned int page_size(void) -{ - if (!__page_size) - __page_size = sysconf(_SC_PAGESIZE); - return __page_size; -} - -static inline unsigned int page_shift(void) -{ - if (!__page_shift) - __page_shift = (ffsl(page_size()) - 1); - return __page_shift; -} - -#define PAGE_SHIFT (page_shift()) -#define PAGE_SIZE (page_size()) -/* - * On ppc64 this will only work with radix 2M hugepage size - */ -#define HPAGE_SHIFT 21 -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - - -static inline int64_t allocate_transhuge(void *ptr, int pagemap_fd) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} - -#endif diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 8dc74dd022c2..85411ee7ff8b 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -8,6 +8,9 @@ #define SMAP_FILE_PATH "/proc/self/smaps" #define MAX_LINE_LENGTH 500 +unsigned int __page_size; +unsigned int __page_shift; + uint64_t pagemap_get_entry(int fd, char *start) { const unsigned long pfn = (unsigned long)start / getpagesize(); @@ -149,3 +152,31 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size) { return __check_huge(addr, "ShmemPmdMapped:", nr_hpages, hpage_size); } + +int64_t allocate_transhuge(void *ptr, int pagemap_fd) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (pshift() - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - pshift())) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 1995ee911ef2..6edeb531afc6 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -1,6 +1,27 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include #include +#include +#include +#include /* ffsl() */ +#include /* _SC_PAGESIZE */ + +extern unsigned int __page_size; +extern unsigned int __page_shift; + +static inline unsigned int psize(void) +{ + if (!__page_size) + __page_size = sysconf(_SC_PAGESIZE); + return __page_size; +} + +static inline unsigned int pshift(void) +{ + if (!__page_shift) + __page_shift = (ffsl(psize()) - 1); + return __page_shift; +} uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); @@ -13,3 +34,13 @@ uint64_t read_pmd_pagesize(void); bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); +int64_t allocate_transhuge(void *ptr, int pagemap_fd); + +/* + * On ppc64 this will only work with radix 2M hugepage size + */ +#define HPAGE_SHIFT 21 +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) -- GitLab From aef6fde75d8c6c1cad4a0e017a8d4cbee2143723 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:18 -0400 Subject: [PATCH 3301/5631] selftests/mm: use TEST_GEN_PROGS where proper TEST_GEN_PROGS and TEST_GEN_FILES are used randomly in the mm/Makefile to specify programs that need to build. Logically all these binaries should all fall into TEST_GEN_PROGS. Replace those TEST_GEN_FILES with TEST_GEN_PROGS, so that we can reference all the tests easily later. [peterx@redhat.com: tools/testing/selftests/mm/Makefile: don't wipe out TEST_GEN_PROGS] Link: https://lkml.kernel.org/r/ZDxrvZh/cw357D8P@x1n Link: https://lkml.kernel.org/r/20230412164218.328104-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 65 +++++++++++++++-------------- 1 file changed, 33 insertions(+), 32 deletions(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 9d9822b4bf24..fa3ad6ca5859 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -31,35 +31,36 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread -TEST_GEN_FILES = cow -TEST_GEN_FILES += compaction_test -TEST_GEN_FILES += gup_test -TEST_GEN_FILES += hmm-tests -TEST_GEN_FILES += hugetlb-madvise -TEST_GEN_FILES += hugepage-mmap -TEST_GEN_FILES += hugepage-mremap -TEST_GEN_FILES += hugepage-shm -TEST_GEN_FILES += hugepage-vmemmap -TEST_GEN_FILES += khugepaged -TEST_GEN_PROGS = madv_populate -TEST_GEN_FILES += map_fixed_noreplace -TEST_GEN_FILES += map_hugetlb -TEST_GEN_FILES += map_populate -TEST_GEN_FILES += memfd_secret -TEST_GEN_FILES += migration + +TEST_GEN_PROGS = cow +TEST_GEN_PROGS += compaction_test +TEST_GEN_PROGS += gup_test +TEST_GEN_PROGS += hmm-tests +TEST_GEN_PROGS += hugetlb-madvise +TEST_GEN_PROGS += hugepage-mmap +TEST_GEN_PROGS += hugepage-mremap +TEST_GEN_PROGS += hugepage-shm +TEST_GEN_PROGS += hugepage-vmemmap +TEST_GEN_PROGS += khugepaged +TEST_GEN_PROGS += madv_populate +TEST_GEN_PROGS += map_fixed_noreplace +TEST_GEN_PROGS += map_hugetlb +TEST_GEN_PROGS += map_populate +TEST_GEN_PROGS += memfd_secret +TEST_GEN_PROGS += migration TEST_GEN_PROGS += mkdirty -TEST_GEN_FILES += mlock-random-test -TEST_GEN_FILES += mlock2-tests -TEST_GEN_FILES += mrelease_test -TEST_GEN_FILES += mremap_dontunmap -TEST_GEN_FILES += mremap_test -TEST_GEN_FILES += on-fault-limit -TEST_GEN_FILES += thuge-gen -TEST_GEN_FILES += transhuge-stress -TEST_GEN_FILES += userfaultfd +TEST_GEN_PROGS += mlock-random-test +TEST_GEN_PROGS += mlock2-tests +TEST_GEN_PROGS += mrelease_test +TEST_GEN_PROGS += mremap_dontunmap +TEST_GEN_PROGS += mremap_test +TEST_GEN_PROGS += on-fault-limit +TEST_GEN_PROGS += thuge-gen +TEST_GEN_PROGS += transhuge-stress +TEST_GEN_PROGS += userfaultfd TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test -TEST_GEN_FILES += ksm_tests +TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test @@ -77,24 +78,24 @@ CFLAGS += -no-pie endif ifeq ($(CAN_BUILD_I386),1) -TEST_GEN_FILES += $(BINARIES_32) +TEST_GEN_PROGS += $(BINARIES_32) endif ifeq ($(CAN_BUILD_X86_64),1) -TEST_GEN_FILES += $(BINARIES_64) +TEST_GEN_PROGS += $(BINARIES_64) endif else ifneq (,$(findstring $(MACHINE),ppc64)) -TEST_GEN_FILES += protection_keys +TEST_GEN_PROGS += protection_keys endif endif ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) -TEST_GEN_FILES += va_128TBswitch -TEST_GEN_FILES += virtual_address_range -TEST_GEN_FILES += write_to_hugetlbfs +TEST_GEN_PROGS += va_128TBswitch +TEST_GEN_PROGS += virtual_address_range +TEST_GEN_PROGS += write_to_hugetlbfs endif TEST_PROGS := run_vmtests.sh -- GitLab From 4b54f5a758b7ac521d4658cb0d18b132b87597c0 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:20 -0400 Subject: [PATCH 3302/5631] selftests/mm: link vm_util.c always We do have plenty of files that want to link against vm_util.c. Just make it simple by linking it always. Link: https://lkml.kernel.org/r/20230412164220.328123-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index fa3ad6ca5859..b2a8cac79899 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -106,18 +106,7 @@ TEST_FILES += va_128TBswitch.sh include ../lib.mk -$(OUTPUT)/cow: vm_util.c -$(OUTPUT)/khugepaged: vm_util.c -$(OUTPUT)/ksm_functional_tests: vm_util.c -$(OUTPUT)/madv_populate: vm_util.c -$(OUTPUT)/mkdirty: vm_util.c -$(OUTPUT)/soft-dirty: vm_util.c -$(OUTPUT)/split_huge_page_test: vm_util.c -$(OUTPUT)/userfaultfd: vm_util.c -$(OUTPUT)/gup_test: vm_util.c -$(OUTPUT)/mrelease_test: vm_util.c -$(OUTPUT)/transhuge-stress: vm_util.c -$(OUTPUT)/ksm_tests: vm_util.c +$(TEST_GEN_PROGS): vm_util.c ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) -- GitLab From bd4d67e76f699688d15e6194f1505b8bdfee0dd7 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:23 -0400 Subject: [PATCH 3303/5631] selftests/mm: merge default_huge_page_size() into one There're already 3 same definitions of the three functions. Move it into vm_util.[ch]. Link: https://lkml.kernel.org/r/20230412164223.328134-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/hugetlb-madvise.c | 25 +------------------- tools/testing/selftests/mm/thuge-gen.c | 19 +-------------- tools/testing/selftests/mm/userfaultfd.c | 24 ------------------- tools/testing/selftests/mm/vm_util.c | 21 ++++++++++++++++ tools/testing/selftests/mm/vm_util.h | 1 + 5 files changed, 24 insertions(+), 66 deletions(-) diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 9a127a8fe176..28426e30d9bc 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include "vm_util.h" #define MIN_FREE_PAGES 20 #define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ @@ -35,30 +36,6 @@ unsigned long huge_page_size; unsigned long base_page_size; -/* - * default_huge_page_size copied from mlock2-tests.c - */ -unsigned long default_huge_page_size(void) -{ - unsigned long hps = 0; - char *line = NULL; - size_t linelen = 0; - FILE *f = fopen("/proc/meminfo", "r"); - - if (!f) - return 0; - while (getline(&line, &linelen, f) > 0) { - if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { - hps <<= 10; - break; - } - } - - free(line); - fclose(f); - return hps; -} - unsigned long get_free_hugepages(void) { unsigned long fhp = 0; diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 361ef7192cc6..380ab5f0a534 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -24,6 +24,7 @@ #include #include #include +#include "vm_util.h" #define err(x) perror(x), exit(1) @@ -74,24 +75,6 @@ void find_pagesizes(void) globfree(&g); } -unsigned long default_huge_page_size(void) -{ - unsigned long hps = 0; - char *line = NULL; - size_t linelen = 0; - FILE *f = fopen("/proc/meminfo", "r"); - if (!f) - return 0; - while (getline(&line, &linelen, f) > 0) { - if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { - hps <<= 10; - break; - } - } - free(line); - return hps; -} - void show(unsigned long ps) { char buf[100]; diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index a96d126cb40e..4cc80a0e8955 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -1703,30 +1703,6 @@ static int userfaultfd_stress(void) || userfaultfd_events_test() || userfaultfd_minor_test(); } -/* - * Copied from mlock2-tests.c - */ -unsigned long default_huge_page_size(void) -{ - unsigned long hps = 0; - char *line = NULL; - size_t linelen = 0; - FILE *f = fopen("/proc/meminfo", "r"); - - if (!f) - return 0; - while (getline(&line, &linelen, f) > 0) { - if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { - hps <<= 10; - break; - } - } - - free(line); - fclose(f); - return hps; -} - static void set_test_type(const char *type) { if (!strcmp(type, "anon")) { diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 85411ee7ff8b..7ffad87aa7e8 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -180,3 +180,24 @@ int64_t allocate_transhuge(void *ptr, int pagemap_fd) return -1; } + +unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 6edeb531afc6..d7163fff8fb7 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -35,6 +35,7 @@ bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); +unsigned long default_huge_page_size(void); /* * On ppc64 this will only work with radix 2M hugepage size -- GitLab From 9f74696bd23da71ab19b1825f813421904cd4169 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:27 -0400 Subject: [PATCH 3304/5631] selftests/mm: use PM_* macros in vm_utils.h We've got the macros in uffd-stress.c, move it over and use it in vm_util.h. Link: https://lkml.kernel.org/r/20230412164227.328145-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/userfaultfd.c | 8 -------- tools/testing/selftests/mm/vm_util.c | 16 ++++------------ tools/testing/selftests/mm/vm_util.h | 8 ++++++++ 3 files changed, 12 insertions(+), 20 deletions(-) diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 4cc80a0e8955..7e841f7e2884 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -1389,14 +1389,6 @@ static int userfaultfd_minor_test(void) return stats.missing_faults != 0 || stats.minor_faults != nr_pages; } -#define BIT_ULL(nr) (1ULL << (nr)) -#define PM_SOFT_DIRTY BIT_ULL(55) -#define PM_MMAP_EXCLUSIVE BIT_ULL(56) -#define PM_UFFD_WP BIT_ULL(57) -#define PM_FILE BIT_ULL(61) -#define PM_SWAP BIT_ULL(62) -#define PM_PRESENT BIT_ULL(63) - static int pagemap_open(void) { int fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 7ffad87aa7e8..54d227d6f70a 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -25,25 +25,17 @@ uint64_t pagemap_get_entry(int fd, char *start) bool pagemap_is_softdirty(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - // Check if dirty bit (55th bit) is set - return entry & 0x0080000000000000ull; + return pagemap_get_entry(fd, start) & PM_SOFT_DIRTY; } bool pagemap_is_swapped(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - return entry & 0x4000000000000000ull; + return pagemap_get_entry(fd, start) & PM_SWAP; } bool pagemap_is_populated(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - /* Present or swapped. */ - return entry & 0xc000000000000000ull; + return pagemap_get_entry(fd, start) & (PM_PRESENT | PM_SWAP); } unsigned long pagemap_get_pfn(int fd, char *start) @@ -51,7 +43,7 @@ unsigned long pagemap_get_pfn(int fd, char *start) uint64_t entry = pagemap_get_entry(fd, start); /* If present (63th bit), PFN is at bit 0 -- 54. */ - if (entry & 0x8000000000000000ull) + if (entry & PM_PRESENT) return entry & 0x007fffffffffffffull; return -1ul; } diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index d7163fff8fb7..d9fadddb5c69 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -6,6 +6,14 @@ #include /* ffsl() */ #include /* _SC_PAGESIZE */ +#define BIT_ULL(nr) (1ULL << (nr)) +#define PM_SOFT_DIRTY BIT_ULL(55) +#define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_UFFD_WP BIT_ULL(57) +#define PM_FILE BIT_ULL(61) +#define PM_SWAP BIT_ULL(62) +#define PM_PRESENT BIT_ULL(63) + extern unsigned int __page_size; extern unsigned int __page_shift; -- GitLab From 366e93c46576e77f1ccfdeab31127f40537e7484 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:31 -0400 Subject: [PATCH 3305/5631] selftests/mm: reuse pagemap_get_entry() in vm_util.h Meanwhile drop pagemap_read_vaddr(). Link: https://lkml.kernel.org/r/20230412164231.328157-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/userfaultfd.c | 31 +++++++----------------- 1 file changed, 9 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 7e841f7e2884..795fbc4d84f8 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -1399,19 +1399,6 @@ static int pagemap_open(void) return fd; } -static uint64_t pagemap_read_vaddr(int fd, void *vaddr) -{ - uint64_t value; - int ret; - - ret = pread(fd, &value, sizeof(uint64_t), - ((uint64_t)vaddr >> 12) * sizeof(uint64_t)); - if (ret != sizeof(uint64_t)) - err("pread() on pagemap failed"); - - return value; -} - /* This macro let __LINE__ works in err() */ #define pagemap_check_wp(value, wp) do { \ if (!!(value & PM_UFFD_WP) != wp) \ @@ -1427,7 +1414,7 @@ static int pagemap_test_fork(bool present) if (!child) { /* Open the pagemap fd of the child itself */ fd = pagemap_open(); - value = pagemap_read_vaddr(fd, area_dst); + value = pagemap_get_entry(fd, area_dst); /* * After fork() uffd-wp bit should be gone as long as we're * without UFFD_FEATURE_EVENT_FORK @@ -1446,24 +1433,24 @@ static void userfaultfd_wp_unpopulated_test(int pagemap_fd) /* Test applying pte marker to anon unpopulated */ wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); /* Test unprotect on anon pte marker */ wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); /* Test zap on anon marker */ wp_range(uffd, (uint64_t)area_dst, page_size, true); if (madvise(area_dst, page_size, MADV_DONTNEED)) err("madvise(MADV_DONTNEED) failed"); - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); /* Test fault in after marker removed */ *area_dst = 1; - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); /* Drop it to make pte none again */ if (madvise(area_dst, page_size, MADV_DONTNEED)) @@ -1522,7 +1509,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) /* Touch the page */ *area_dst = 1; wp_range(uffd, (uint64_t)area_dst, test_pgsize, true); - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); /* Make sure uffd-wp bit dropped when fork */ if (pagemap_test_fork(true)) @@ -1536,7 +1523,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) err("madvise(MADV_PAGEOUT) failed"); /* Uffd-wp should persist even swapped out */ - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); /* Make sure uffd-wp bit dropped when fork */ if (pagemap_test_fork(false)) @@ -1544,12 +1531,12 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) /* Unprotect; this tests swap pte modifications */ wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); /* Fault in the page from disk */ *area_dst = 2; - value = pagemap_read_vaddr(pagemap_fd, area_dst); + value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); close(pagemap_fd); -- GitLab From 4af9ff29816ac011af143c9d5cd16ab75429a600 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:34 -0400 Subject: [PATCH 3306/5631] selftests/mm: test UFFDIO_ZEROPAGE only when !hugetlb Make the check as simple as "test_type == TEST_HUGETLB" because that's the only mem that doesn't support ZEROPAGE. Link: https://lkml.kernel.org/r/20230412164234.328168-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/userfaultfd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 795fbc4d84f8..d724f1c78847 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -1118,7 +1118,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) { struct uffdio_zeropage uffdio_zeropage; int ret; - bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE); + bool has_zeropage = !(test_type == TEST_HUGETLB); __s64 res; if (offset >= nr_pages * page_size) -- GitLab From 618aeb5d6255a7c2db2ac9cb850e5e044dd916c5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:38 -0400 Subject: [PATCH 3307/5631] selftests/mm: drop test_uffdio_zeropage_eexist The idea was trying to flip this var in the alarm handler from time to time to test -EEXIST of UFFDIO_ZEROPAGE, but firstly it's only used in the zeropage test so probably only used once, meanwhile we passed "retry==false" so it'll never got tested anyway. Drop both sides so we always test UFFDIO_ZEROPAGE retries if has_zeropage is set (!hugetlb). One more thing to do is doing UFFDIO_REGISTER for the alias buffer too, because otherwise the test won't even pass! We were just lucky that this test never really got ran at all. Link: https://lkml.kernel.org/r/20230412164238.328238-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/userfaultfd.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index d724f1c78847..3487ec0bfcc8 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -88,7 +88,6 @@ static bool test_dev_userfaultfd; /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 static volatile bool test_uffdio_copy_eexist = true; -static volatile bool test_uffdio_zeropage_eexist = true; /* Whether to test uffd write-protection */ static bool test_uffdio_wp = true; /* Whether to test uffd minor faults */ @@ -1114,7 +1113,7 @@ static void retry_uffdio_zeropage(int ufd, } } -static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) +static int __uffdio_zeropage(int ufd, unsigned long offset) { struct uffdio_zeropage uffdio_zeropage; int ret; @@ -1138,11 +1137,8 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) if (res != page_size) { err("UFFDIO_ZEROPAGE unexpected size"); } else { - if (test_uffdio_zeropage_eexist && retry) { - test_uffdio_zeropage_eexist = false; - retry_uffdio_zeropage(ufd, &uffdio_zeropage, - offset); - } + retry_uffdio_zeropage(ufd, &uffdio_zeropage, + offset); return 1; } } else @@ -1153,7 +1149,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) static int uffdio_zeropage(int ufd, unsigned long offset) { - return __uffdio_zeropage(ufd, offset, false); + return __uffdio_zeropage(ufd, offset); } /* exercise UFFDIO_ZEROPAGE */ @@ -1177,6 +1173,13 @@ static int userfaultfd_zeropage_test(void) assert_expected_ioctls_present( uffdio_register.mode, uffdio_register.ioctls); + if (area_dst_alias) { + /* Needed this to test zeropage-retry on shared memory */ + uffdio_register.range.start = (unsigned long) area_dst_alias; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); + } + if (uffdio_zeropage(uffd, 0)) if (my_bcmp(area_dst, zeropage, page_size)) err("zeropage is not zero"); @@ -1763,7 +1766,6 @@ static void sigalrm(int sig) if (sig != SIGALRM) abort(); test_uffdio_copy_eexist = true; - test_uffdio_zeropage_eexist = true; alarm(ALARM_INTERVAL_SECS); } -- GitLab From 33be4e892877eec7c8eb32988b95f5c42c87f0f0 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:41 -0400 Subject: [PATCH 3308/5631] selftests/mm: create uffd-common.[ch] Move common utility functions into uffd-common.[ch] files from the original userfaultfd.c. This prepares for a split of userfaultfd.c into two tests: one to only cover the old but powerful stress test, the other one covers all the functional tests. This movement is kind of a brute-force effort for now, with light touch-ups but nothing should really change. There's chances to optimize more, but let's leave that for later. Link: https://lkml.kernel.org/r/20230412164241.328259-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Rapoport (IBM) Reviewed-by: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 2 + tools/testing/selftests/mm/uffd-common.c | 611 ++++++++++++++++++++ tools/testing/selftests/mm/uffd-common.h | 117 ++++ tools/testing/selftests/mm/userfaultfd.c | 694 +---------------------- 4 files changed, 731 insertions(+), 693 deletions(-) create mode 100644 tools/testing/selftests/mm/uffd-common.c create mode 100644 tools/testing/selftests/mm/uffd-common.h diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index b2a8cac79899..210da78ec495 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -108,6 +108,8 @@ include ../lib.mk $(TEST_GEN_PROGS): vm_util.c +$(OUTPUT)/userfaultfd: uffd-common.c + ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c new file mode 100644 index 000000000000..c57757c2a36f --- /dev/null +++ b/tools/testing/selftests/mm/uffd-common.c @@ -0,0 +1,611 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd tests util functions + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ + +#include "uffd-common.h" + +#define BASE_PMD_ADDR ((void *)(1UL << 30)) + +volatile bool test_uffdio_copy_eexist = true; +unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; +char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; +int mem_fd, uffd = -1, uffd_flags, finished, *pipefd, test_type; +bool map_shared, test_collapse, test_dev_userfaultfd; +bool test_uffdio_wp = true, test_uffdio_minor = false; +unsigned long long *count_verify; +uffd_test_ops_t *uffd_test_ops; + +static void anon_release_pages(char *rel_area) +{ + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); +} + +static void anon_allocate_area(void **alloc_area, bool is_src) +{ + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); +} + +static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ +} + +static void hugetlb_release_pages(char *rel_area) +{ + if (!map_shared) { + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + } else { + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); + } +} + +static void hugetlb_allocate_area(void **alloc_area, bool is_src) +{ + off_t size = nr_pages * page_size; + off_t offset = is_src ? 0 : size; + void *area_alias = NULL; + char **alloc_area_alias; + + *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, + (map_shared ? MAP_SHARED : MAP_PRIVATE) | + (is_src ? 0 : MAP_NORESERVE), + mem_fd, offset); + if (*alloc_area == MAP_FAILED) + err("mmap of hugetlbfs file failed"); + + if (map_shared) { + area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_SHARED, mem_fd, offset); + if (area_alias == MAP_FAILED) + err("mmap of hugetlb file alias failed"); + } + + if (is_src) { + alloc_area_alias = &area_src_alias; + } else { + alloc_area_alias = &area_dst_alias; + } + if (area_alias) + *alloc_area_alias = area_alias; +} + +static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + if (!map_shared) + return; + + *start = (unsigned long) area_dst_alias + offset; +} + +static void shmem_release_pages(char *rel_area) +{ + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); +} + +static void shmem_allocate_area(void **alloc_area, bool is_src) +{ + void *area_alias = NULL; + size_t bytes = nr_pages * page_size; + unsigned long offset = is_src ? 0 : bytes; + char *p = NULL, *p_alias = NULL; + + if (test_collapse) { + p = BASE_PMD_ADDR; + if (!is_src) + /* src map + alias + interleaved hpages */ + p += 2 * (bytes + hpage_size); + p_alias = p; + p_alias += bytes; + p_alias += hpage_size; /* Prevent src/dst VMA merge */ + } + + *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + mem_fd, offset); + if (*alloc_area == MAP_FAILED) + err("mmap of memfd failed"); + if (test_collapse && *alloc_area != p) + err("mmap of memfd failed at %p", p); + + area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + mem_fd, offset); + if (area_alias == MAP_FAILED) + err("mmap of memfd alias failed"); + if (test_collapse && area_alias != p_alias) + err("mmap of anonymous memory failed at %p", p_alias); + + if (is_src) + area_src_alias = area_alias; + else + area_dst_alias = area_alias; +} + +static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + *start = (unsigned long)area_dst_alias + offset; +} + +static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) +{ + if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, hpage_size)) + err("Did not find expected %d number of hugepages", + expect_nr_hpages); +} + +struct uffd_test_ops anon_uffd_test_ops = { + .allocate_area = anon_allocate_area, + .release_pages = anon_release_pages, + .alias_mapping = noop_alias_mapping, + .check_pmd_mapping = NULL, +}; + +struct uffd_test_ops shmem_uffd_test_ops = { + .allocate_area = shmem_allocate_area, + .release_pages = shmem_release_pages, + .alias_mapping = shmem_alias_mapping, + .check_pmd_mapping = shmem_check_pmd_mapping, +}; + +struct uffd_test_ops hugetlb_uffd_test_ops = { + .allocate_area = hugetlb_allocate_area, + .release_pages = hugetlb_release_pages, + .alias_mapping = hugetlb_alias_mapping, + .check_pmd_mapping = NULL, +}; + +void uffd_stats_report(struct uffd_stats *stats, int n_cpus) +{ + int i; + unsigned long long miss_total = 0, wp_total = 0, minor_total = 0; + + for (i = 0; i < n_cpus; i++) { + miss_total += stats[i].missing_faults; + wp_total += stats[i].wp_faults; + minor_total += stats[i].minor_faults; + } + + printf("userfaults: "); + if (miss_total) { + printf("%llu missing (", miss_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].missing_faults); + printf("\b) "); + } + if (wp_total) { + printf("%llu wp (", wp_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].wp_faults); + printf("\b) "); + } + if (minor_total) { + printf("%llu minor (", minor_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].minor_faults); + printf("\b)"); + } + printf("\n"); +} + +static int __userfaultfd_open_dev(void) +{ + int fd, _uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + errexit(KSFT_SKIP, "opening /dev/userfaultfd failed"); + + _uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS); + if (_uffd < 0) + errexit(errno == ENOTTY ? KSFT_SKIP : 1, + "creating userfaultfd failed"); + close(fd); + return _uffd; +} + +void userfaultfd_open(uint64_t *features) +{ + struct uffdio_api uffdio_api; + + if (test_dev_userfaultfd) + uffd = __userfaultfd_open_dev(); + else { + uffd = syscall(__NR_userfaultfd, UFFD_FLAGS); + if (uffd < 0) + errexit(errno == ENOSYS ? KSFT_SKIP : 1, + "creating userfaultfd failed"); + } + uffd_flags = fcntl(uffd, F_GETFD, NULL); + + uffdio_api.api = UFFD_API; + uffdio_api.features = *features; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + err("UFFDIO_API failed.\nPlease make sure to " + "run with either root or ptrace capability."); + if (uffdio_api.api != UFFD_API) + err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); + + *features = uffdio_api.features; +} + +static inline void munmap_area(void **area) +{ + if (*area) + if (munmap(*area, nr_pages * page_size)) + err("munmap"); + + *area = NULL; +} + +static void uffd_test_ctx_clear(void) +{ + size_t i; + + if (pipefd) { + for (i = 0; i < nr_cpus * 2; ++i) { + if (close(pipefd[i])) + err("close pipefd"); + } + free(pipefd); + pipefd = NULL; + } + + if (count_verify) { + free(count_verify); + count_verify = NULL; + } + + if (uffd != -1) { + if (close(uffd)) + err("close uffd"); + uffd = -1; + } + + munmap_area((void **)&area_src); + munmap_area((void **)&area_src_alias); + munmap_area((void **)&area_dst); + munmap_area((void **)&area_dst_alias); + munmap_area((void **)&area_remap); +} + +void uffd_test_ctx_init(uint64_t features) +{ + unsigned long nr, cpu; + + uffd_test_ctx_clear(); + + uffd_test_ops->allocate_area((void **)&area_src, true); + uffd_test_ops->allocate_area((void **)&area_dst, false); + + userfaultfd_open(&features); + + count_verify = malloc(nr_pages * sizeof(unsigned long long)); + if (!count_verify) + err("count_verify"); + + for (nr = 0; nr < nr_pages; nr++) { + *area_mutex(area_src, nr) = + (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; + count_verify[nr] = *area_count(area_src, nr) = 1; + /* + * In the transition between 255 to 256, powerpc will + * read out of order in my_bcmp and see both bytes as + * zero, so leave a placeholder below always non-zero + * after the count, to avoid my_bcmp to trigger false + * positives. + */ + *(area_count(area_src, nr) + 1) = 1; + } + + /* + * After initialization of area_src, we must explicitly release pages + * for area_dst to make sure it's fully empty. Otherwise we could have + * some area_dst pages be errornously initialized with zero pages, + * hence we could hit memory corruption later in the test. + * + * One example is when THP is globally enabled, above allocate_area() + * calls could have the two areas merged into a single VMA (as they + * will have the same VMA flags so they're mergeable). When we + * initialize the area_src above, it's possible that some part of + * area_dst could have been faulted in via one huge THP that will be + * shared between area_src and area_dst. It could cause some of the + * area_dst won't be trapped by missing userfaults. + * + * This release_pages() will guarantee even if that happened, we'll + * proactively split the thp and drop any accidentally initialized + * pages within area_dst. + */ + uffd_test_ops->release_pages(area_dst); + + pipefd = malloc(sizeof(int) * nr_cpus * 2); + if (!pipefd) + err("pipefd"); + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + err("pipe"); +} + +uint64_t get_expected_ioctls(uint64_t mode) +{ + uint64_t ioctls = UFFD_API_RANGE_IOCTLS; + + if (test_type == TEST_HUGETLB) + ioctls &= ~(1 << _UFFDIO_ZEROPAGE); + + if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp)) + ioctls &= ~(1 << _UFFDIO_WRITEPROTECT); + + if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor)) + ioctls &= ~(1 << _UFFDIO_CONTINUE); + + return ioctls; +} + +void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) +{ + uint64_t expected = get_expected_ioctls(mode); + uint64_t actual = ioctls & expected; + + if (actual != expected) { + err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64, + expected, actual); + } +} + +void wp_range(int ufd, __u64 start, __u64 len, bool wp) +{ + struct uffdio_writeprotect prms; + + /* Write protection page faults */ + prms.range.start = start; + prms.range.len = len; + /* Undo write-protect, do wakeup after that */ + prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; + + if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) + err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); +} + +static void continue_range(int ufd, __u64 start, __u64 len) +{ + struct uffdio_continue req; + int ret; + + req.range.start = start; + req.range.len = len; + req.mode = 0; + if (test_uffdio_wp) + req.mode |= UFFDIO_CONTINUE_MODE_WP; + + if (ioctl(ufd, UFFDIO_CONTINUE, &req)) + err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, + (uint64_t)start); + + /* + * Error handling within the kernel for continue is subtly different + * from copy or zeropage, so it may be a source of bugs. Trigger an + * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG. + */ + req.mapped = 0; + ret = ioctl(ufd, UFFDIO_CONTINUE, &req); + if (ret >= 0 || req.mapped != -EEXIST) + err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64, + ret, (int64_t) req.mapped); +} + +int uffd_read_msg(int ufd, struct uffd_msg *msg) +{ + int ret = read(uffd, msg, sizeof(*msg)); + + if (ret != sizeof(*msg)) { + if (ret < 0) { + if (errno == EAGAIN || errno == EINTR) + return 1; + err("blocking read error"); + } else { + err("short read"); + } + } + + return 0; +} + +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); + + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { + /* Write protect page faults */ + wp_range(uffd, msg->arg.pagefault.address, page_size, false); + stats->wp_faults++; + } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { + uint8_t *area; + int b; + + /* + * Minor page faults + * + * To prove we can modify the original range for testing + * purposes, we're going to bit flip this range before + * continuing. + * + * Note that this requires all minor page fault tests operate on + * area_dst (non-UFFD-registered) and area_dst_alias + * (UFFD-registered). + */ + + area = (uint8_t *)(area_dst + + ((char *)msg->arg.pagefault.address - + area_dst_alias)); + for (b = 0; b < page_size; ++b) + area[b] = ~area[b]; + continue_range(uffd, msg->arg.pagefault.address, page_size); + stats->minor_faults++; + } else { + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + err("unexpected write fault"); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + + if (copy_page(uffd, offset)) + stats->missing_faults++; + } +} + +void *uffd_poll_thread(void *arg) +{ + struct uffd_stats *stats = (struct uffd_stats *)arg; + unsigned long cpu = stats->cpu; + struct pollfd pollfd[2]; + struct uffd_msg msg; + struct uffdio_register uffd_reg; + int ret; + char tmp_chr; + + pollfd[0].fd = uffd; + pollfd[0].events = POLLIN; + pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].events = POLLIN; + + for (;;) { + ret = poll(pollfd, 2, -1); + if (ret <= 0) { + if (errno == EINTR || errno == EAGAIN) + continue; + err("poll error: %d", ret); + } + if (pollfd[1].revents) { + if (!(pollfd[1].revents & POLLIN)) + err("pollfd[1].revents %d", pollfd[1].revents); + if (read(pollfd[1].fd, &tmp_chr, 1) != 1) + err("read pipefd error"); + break; + } + if (!(pollfd[0].revents & POLLIN)) + err("pollfd[0].revents %d", pollfd[0].revents); + if (uffd_read_msg(uffd, &msg)) + continue; + switch (msg.event) { + default: + err("unexpected msg event %u\n", msg.event); + break; + case UFFD_EVENT_PAGEFAULT: + uffd_handle_page_fault(&msg, stats); + break; + case UFFD_EVENT_FORK: + close(uffd); + uffd = msg.arg.fork.ufd; + pollfd[0].fd = uffd; + break; + case UFFD_EVENT_REMOVE: + uffd_reg.range.start = msg.arg.remove.start; + uffd_reg.range.len = msg.arg.remove.end - + msg.arg.remove.start; + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + err("remove failure"); + break; + case UFFD_EVENT_REMAP: + area_remap = area_dst; /* save for later unmap */ + area_dst = (char *)(unsigned long)msg.arg.remap.to; + break; + } + } + + return NULL; +} + +static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, + unsigned long offset) +{ + uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffdio_copy->len, + offset); + if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy->copy != -EEXIST) + err("UFFDIO_COPY retry error: %"PRId64, + (int64_t)uffdio_copy->copy); + } else { + err("UFFDIO_COPY retry unexpected: %"PRId64, + (int64_t)uffdio_copy->copy); + } +} + +static void wake_range(int ufd, unsigned long addr, unsigned long len) +{ + struct uffdio_range uffdio_wake; + + uffdio_wake.start = addr; + uffdio_wake.len = len; + + if (ioctl(ufd, UFFDIO_WAKE, &uffdio_wake)) + fprintf(stderr, "error waking %lu\n", + addr), exit(1); +} + +int __copy_page(int ufd, unsigned long offset, bool retry) +{ + struct uffdio_copy uffdio_copy; + + if (offset >= nr_pages * page_size) + err("unexpected offset %lu\n", offset); + uffdio_copy.dst = (unsigned long) area_dst + offset; + uffdio_copy.src = (unsigned long) area_src + offset; + uffdio_copy.len = page_size; + if (test_uffdio_wp) + uffdio_copy.mode = UFFDIO_COPY_MODE_WP; + else + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy.copy != -EEXIST) + err("UFFDIO_COPY error: %"PRId64, + (int64_t)uffdio_copy.copy); + wake_range(ufd, uffdio_copy.dst, page_size); + } else if (uffdio_copy.copy != page_size) { + err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); + } else { + if (test_uffdio_copy_eexist && retry) { + test_uffdio_copy_eexist = false; + retry_copy_page(ufd, &uffdio_copy, offset); + } + return 1; + } + return 0; +} + +int copy_page(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, false); +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h new file mode 100644 index 000000000000..d9430cfdcb19 --- /dev/null +++ b/tools/testing/selftests/mm/uffd-common.h @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd tests common header + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ +#ifndef __UFFD_COMMON_H__ +#define __UFFD_COMMON_H__ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" +#include "vm_util.h" + +#define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) + +#define _err(fmt, ...) \ + do { \ + int ret = errno; \ + fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__); \ + fprintf(stderr, " (errno=%d, @%s:%d)\n", \ + ret, __FILE__, __LINE__); \ + } while (0) + +#define errexit(exitcode, fmt, ...) \ + do { \ + _err(fmt, ##__VA_ARGS__); \ + exit(exitcode); \ + } while (0) + +#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) + +/* pthread_mutex_t starts at page offset 0 */ +#define area_mutex(___area, ___nr) \ + ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +#define area_count(___area, ___nr) \ + ((volatile unsigned long long *) ((unsigned long) \ + ((___area) + (___nr)*page_size + \ + sizeof(pthread_mutex_t) + \ + sizeof(unsigned long long) - 1) & \ + ~(unsigned long)(sizeof(unsigned long long) \ + - 1))) + +/* Userfaultfd test statistics */ +struct uffd_stats { + int cpu; + unsigned long missing_faults; + unsigned long wp_faults; + unsigned long minor_faults; +}; + +struct uffd_test_ops { + void (*allocate_area)(void **alloc_area, bool is_src); + void (*release_pages)(char *rel_area); + void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); + void (*check_pmd_mapping)(void *p, int expect_nr_hpages); +}; +typedef struct uffd_test_ops uffd_test_ops_t; + +extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; +extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; +extern int mem_fd, uffd, uffd_flags, finished, *pipefd, test_type; +extern bool map_shared, test_collapse, test_dev_userfaultfd; +extern bool test_uffdio_wp, test_uffdio_minor; +extern unsigned long long *count_verify; +extern volatile bool test_uffdio_copy_eexist; + +extern uffd_test_ops_t anon_uffd_test_ops; +extern uffd_test_ops_t shmem_uffd_test_ops; +extern uffd_test_ops_t hugetlb_uffd_test_ops; +extern uffd_test_ops_t *uffd_test_ops; + +void uffd_stats_report(struct uffd_stats *stats, int n_cpus); +void uffd_test_ctx_init(uint64_t features); +void userfaultfd_open(uint64_t *features); +uint64_t get_expected_ioctls(uint64_t mode); +void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls); +int uffd_read_msg(int ufd, struct uffd_msg *msg); +void wp_range(int ufd, __u64 start, __u64 len, bool wp); +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats); +int __copy_page(int ufd, unsigned long offset, bool retry); +int copy_page(int ufd, unsigned long offset); +void *uffd_poll_thread(void *arg); + +#define TEST_ANON 1 +#define TEST_HUGETLB 2 +#define TEST_SHMEM 3 + +#endif diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c index 3487ec0bfcc8..c68a9aeefc41 100644 --- a/tools/testing/selftests/mm/userfaultfd.c +++ b/tools/testing/selftests/mm/userfaultfd.c @@ -34,96 +34,20 @@ * transfer (UFFDIO_COPY). */ -#define _GNU_SOURCE -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "../kselftest.h" -#include "vm_util.h" +#include "uffd-common.h" #ifdef __NR_userfaultfd -static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; - #define BOUNCE_RANDOM (1<<0) #define BOUNCE_RACINGFAULTS (1<<1) #define BOUNCE_VERIFY (1<<2) #define BOUNCE_POLL (1<<3) static int bounces; -#define TEST_ANON 1 -#define TEST_HUGETLB 2 -#define TEST_SHMEM 3 -static int test_type; - -#define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) - -#define BASE_PMD_ADDR ((void *)(1UL << 30)) - -/* test using /dev/userfaultfd, instead of userfaultfd(2) */ -static bool test_dev_userfaultfd; - /* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ #define ALARM_INTERVAL_SECS 10 -static volatile bool test_uffdio_copy_eexist = true; -/* Whether to test uffd write-protection */ -static bool test_uffdio_wp = true; -/* Whether to test uffd minor faults */ -static bool test_uffdio_minor = false; -static bool map_shared; -static int mem_fd; -static unsigned long long *count_verify; -static int uffd = -1; -static int uffd_flags, finished, *pipefd; -static char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; static char *zeropage; pthread_attr_t attr; -static bool test_collapse; - -/* Userfaultfd test statistics */ -struct uffd_stats { - int cpu; - unsigned long missing_faults; - unsigned long wp_faults; - unsigned long minor_faults; -}; - -/* pthread_mutex_t starts at page offset 0 */ -#define area_mutex(___area, ___nr) \ - ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) -/* - * count is placed in the page after pthread_mutex_t naturally aligned - * to avoid non alignment faults on non-x86 archs. - */ -#define area_count(___area, ___nr) \ - ((volatile unsigned long long *) ((unsigned long) \ - ((___area) + (___nr)*page_size + \ - sizeof(pthread_mutex_t) + \ - sizeof(unsigned long long) - 1) & \ - ~(unsigned long)(sizeof(unsigned long long) \ - - 1))) #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) @@ -166,22 +90,6 @@ static void usage(void) exit(1); } -#define _err(fmt, ...) \ - do { \ - int ret = errno; \ - fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__); \ - fprintf(stderr, " (errno=%d, line=%d)\n", \ - ret, __LINE__); \ - } while (0) - -#define errexit(exitcode, fmt, ...) \ - do { \ - _err(fmt, ##__VA_ARGS__); \ - exit(exitcode); \ - } while (0) - -#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) - static void uffd_stats_reset(struct uffd_stats *uffd_stats, unsigned long n_cpus) { @@ -195,189 +103,6 @@ static void uffd_stats_reset(struct uffd_stats *uffd_stats, } } -static void uffd_stats_report(struct uffd_stats *stats, int n_cpus) -{ - int i; - unsigned long long miss_total = 0, wp_total = 0, minor_total = 0; - - for (i = 0; i < n_cpus; i++) { - miss_total += stats[i].missing_faults; - wp_total += stats[i].wp_faults; - minor_total += stats[i].minor_faults; - } - - printf("userfaults: "); - if (miss_total) { - printf("%llu missing (", miss_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].missing_faults); - printf("\b) "); - } - if (wp_total) { - printf("%llu wp (", wp_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].wp_faults); - printf("\b) "); - } - if (minor_total) { - printf("%llu minor (", minor_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].minor_faults); - printf("\b)"); - } - printf("\n"); -} - -static void anon_release_pages(char *rel_area) -{ - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); -} - -static void anon_allocate_area(void **alloc_area, bool is_src) -{ - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); -} - -static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) -{ -} - -static void hugetlb_release_pages(char *rel_area) -{ - if (!map_shared) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); - } else { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) - err("madvise(MADV_REMOVE) failed"); - } -} - -static void hugetlb_allocate_area(void **alloc_area, bool is_src) -{ - off_t size = nr_pages * page_size; - off_t offset = is_src ? 0 : size; - void *area_alias = NULL; - char **alloc_area_alias; - - *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | - (is_src ? 0 : MAP_NORESERVE), - mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of hugetlbfs file failed"); - - if (map_shared) { - area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, - MAP_SHARED, mem_fd, offset); - if (area_alias == MAP_FAILED) - err("mmap of hugetlb file alias failed"); - } - - if (is_src) { - alloc_area_alias = &area_src_alias; - } else { - alloc_area_alias = &area_dst_alias; - } - if (area_alias) - *alloc_area_alias = area_alias; -} - -static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) -{ - if (!map_shared) - return; - - *start = (unsigned long) area_dst_alias + offset; -} - -static void shmem_release_pages(char *rel_area) -{ - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) - err("madvise(MADV_REMOVE) failed"); -} - -static void shmem_allocate_area(void **alloc_area, bool is_src) -{ - void *area_alias = NULL; - size_t bytes = nr_pages * page_size; - unsigned long offset = is_src ? 0 : bytes; - char *p = NULL, *p_alias = NULL; - - if (test_collapse) { - p = BASE_PMD_ADDR; - if (!is_src) - /* src map + alias + interleaved hpages */ - p += 2 * (bytes + hpage_size); - p_alias = p; - p_alias += bytes; - p_alias += hpage_size; /* Prevent src/dst VMA merge */ - } - - *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, - mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of memfd failed"); - if (test_collapse && *alloc_area != p) - err("mmap of memfd failed at %p", p); - - area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, - mem_fd, offset); - if (area_alias == MAP_FAILED) - err("mmap of memfd alias failed"); - if (test_collapse && area_alias != p_alias) - err("mmap of anonymous memory failed at %p", p_alias); - - if (is_src) - area_src_alias = area_alias; - else - area_dst_alias = area_alias; -} - -static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) -{ - *start = (unsigned long)area_dst_alias + offset; -} - -static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) -{ - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, hpage_size)) - err("Did not find expected %d number of hugepages", - expect_nr_hpages); -} - -struct uffd_test_ops { - void (*allocate_area)(void **alloc_area, bool is_src); - void (*release_pages)(char *rel_area); - void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); - void (*check_pmd_mapping)(void *p, int expect_nr_hpages); -}; - -static struct uffd_test_ops anon_uffd_test_ops = { - .allocate_area = anon_allocate_area, - .release_pages = anon_release_pages, - .alias_mapping = noop_alias_mapping, - .check_pmd_mapping = NULL, -}; - -static struct uffd_test_ops shmem_uffd_test_ops = { - .allocate_area = shmem_allocate_area, - .release_pages = shmem_release_pages, - .alias_mapping = shmem_alias_mapping, - .check_pmd_mapping = shmem_check_pmd_mapping, -}; - -static struct uffd_test_ops hugetlb_uffd_test_ops = { - .allocate_area = hugetlb_allocate_area, - .release_pages = hugetlb_release_pages, - .alias_mapping = hugetlb_alias_mapping, - .check_pmd_mapping = NULL, -}; - -static struct uffd_test_ops *uffd_test_ops; - static inline uint64_t uffd_minor_feature(void) { if (test_type == TEST_HUGETLB && map_shared) @@ -388,171 +113,6 @@ static inline uint64_t uffd_minor_feature(void) return 0; } -static uint64_t get_expected_ioctls(uint64_t mode) -{ - uint64_t ioctls = UFFD_API_RANGE_IOCTLS; - - if (test_type == TEST_HUGETLB) - ioctls &= ~(1 << _UFFDIO_ZEROPAGE); - - if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp)) - ioctls &= ~(1 << _UFFDIO_WRITEPROTECT); - - if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor)) - ioctls &= ~(1 << _UFFDIO_CONTINUE); - - return ioctls; -} - -static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) -{ - uint64_t expected = get_expected_ioctls(mode); - uint64_t actual = ioctls & expected; - - if (actual != expected) { - err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64, - expected, actual); - } -} - -static int __userfaultfd_open_dev(void) -{ - int fd, _uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - errexit(KSFT_SKIP, "opening /dev/userfaultfd failed"); - - _uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS); - if (_uffd < 0) - errexit(errno == ENOTTY ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - close(fd); - return _uffd; -} - -static void userfaultfd_open(uint64_t *features) -{ - struct uffdio_api uffdio_api; - - if (test_dev_userfaultfd) - uffd = __userfaultfd_open_dev(); - else { - uffd = syscall(__NR_userfaultfd, UFFD_FLAGS); - if (uffd < 0) - errexit(errno == ENOSYS ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - } - uffd_flags = fcntl(uffd, F_GETFD, NULL); - - uffdio_api.api = UFFD_API; - uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) - err("UFFDIO_API failed.\nPlease make sure to " - "run with either root or ptrace capability."); - if (uffdio_api.api != UFFD_API) - err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); - - *features = uffdio_api.features; -} - -static inline void munmap_area(void **area) -{ - if (*area) - if (munmap(*area, nr_pages * page_size)) - err("munmap"); - - *area = NULL; -} - -static void uffd_test_ctx_clear(void) -{ - size_t i; - - if (pipefd) { - for (i = 0; i < nr_cpus * 2; ++i) { - if (close(pipefd[i])) - err("close pipefd"); - } - free(pipefd); - pipefd = NULL; - } - - if (count_verify) { - free(count_verify); - count_verify = NULL; - } - - if (uffd != -1) { - if (close(uffd)) - err("close uffd"); - uffd = -1; - } - - munmap_area((void **)&area_src); - munmap_area((void **)&area_src_alias); - munmap_area((void **)&area_dst); - munmap_area((void **)&area_dst_alias); - munmap_area((void **)&area_remap); -} - -static void uffd_test_ctx_init(uint64_t features) -{ - unsigned long nr, cpu; - - uffd_test_ctx_clear(); - - uffd_test_ops->allocate_area((void **)&area_src, true); - uffd_test_ops->allocate_area((void **)&area_dst, false); - - userfaultfd_open(&features); - - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) - err("count_verify"); - - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = - (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; - /* - * In the transition between 255 to 256, powerpc will - * read out of order in my_bcmp and see both bytes as - * zero, so leave a placeholder below always non-zero - * after the count, to avoid my_bcmp to trigger false - * positives. - */ - *(area_count(area_src, nr) + 1) = 1; - } - - /* - * After initialization of area_src, we must explicitly release pages - * for area_dst to make sure it's fully empty. Otherwise we could have - * some area_dst pages be errornously initialized with zero pages, - * hence we could hit memory corruption later in the test. - * - * One example is when THP is globally enabled, above allocate_area() - * calls could have the two areas merged into a single VMA (as they - * will have the same VMA flags so they're mergeable). When we - * initialize the area_src above, it's possible that some part of - * area_dst could have been faulted in via one huge THP that will be - * shared between area_src and area_dst. It could cause some of the - * area_dst won't be trapped by missing userfaults. - * - * This release_pages() will guarantee even if that happened, we'll - * proactively split the thp and drop any accidentally initialized - * pages within area_dst. - */ - uffd_test_ops->release_pages(area_dst); - - pipefd = malloc(sizeof(int) * nr_cpus * 2); - if (!pipefd) - err("pipefd"); - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) - err("pipe"); -} - static int my_bcmp(char *str1, char *str2, size_t n) { unsigned long i; @@ -562,47 +122,6 @@ static int my_bcmp(char *str1, char *str2, size_t n) return 0; } -static void wp_range(int ufd, __u64 start, __u64 len, bool wp) -{ - struct uffdio_writeprotect prms; - - /* Write protection page faults */ - prms.range.start = start; - prms.range.len = len; - /* Undo write-protect, do wakeup after that */ - prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; - - if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) - err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); -} - -static void continue_range(int ufd, __u64 start, __u64 len) -{ - struct uffdio_continue req; - int ret; - - req.range.start = start; - req.range.len = len; - req.mode = 0; - if (test_uffdio_wp) - req.mode |= UFFDIO_CONTINUE_MODE_WP; - - if (ioctl(ufd, UFFDIO_CONTINUE, &req)) - err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, - (uint64_t)start); - - /* - * Error handling within the kernel for continue is subtly different - * from copy or zeropage, so it may be a source of bugs. Trigger an - * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG. - */ - req.mapped = 0; - ret = ioctl(ufd, UFFDIO_CONTINUE, &req); - if (ret >= 0 || req.mapped != -EEXIST) - err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64, - ret, (int64_t) req.mapped); -} - static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -635,222 +154,11 @@ static void *locking_thread(void *arg) return NULL; } -static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, - unsigned long offset) -{ - uffd_test_ops->alias_mapping(&uffdio_copy->dst, - uffdio_copy->len, - offset); - if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { - /* real retval in ufdio_copy.copy */ - if (uffdio_copy->copy != -EEXIST) - err("UFFDIO_COPY retry error: %"PRId64, - (int64_t)uffdio_copy->copy); - } else { - err("UFFDIO_COPY retry unexpected: %"PRId64, - (int64_t)uffdio_copy->copy); - } -} - -static void wake_range(int ufd, unsigned long addr, unsigned long len) -{ - struct uffdio_range uffdio_wake; - - uffdio_wake.start = addr; - uffdio_wake.len = len; - - if (ioctl(ufd, UFFDIO_WAKE, &uffdio_wake)) - fprintf(stderr, "error waking %lu\n", - addr), exit(1); -} - -static int __copy_page(int ufd, unsigned long offset, bool retry) -{ - struct uffdio_copy uffdio_copy; - - if (offset >= nr_pages * page_size) - err("unexpected offset %lu\n", offset); - uffdio_copy.dst = (unsigned long) area_dst + offset; - uffdio_copy.src = (unsigned long) area_src + offset; - uffdio_copy.len = page_size; - if (test_uffdio_wp) - uffdio_copy.mode = UFFDIO_COPY_MODE_WP; - else - uffdio_copy.mode = 0; - uffdio_copy.copy = 0; - if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { - /* real retval in ufdio_copy.copy */ - if (uffdio_copy.copy != -EEXIST) - err("UFFDIO_COPY error: %"PRId64, - (int64_t)uffdio_copy.copy); - wake_range(ufd, uffdio_copy.dst, page_size); - } else if (uffdio_copy.copy != page_size) { - err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); - } else { - if (test_uffdio_copy_eexist && retry) { - test_uffdio_copy_eexist = false; - retry_copy_page(ufd, &uffdio_copy, offset); - } - return 1; - } - return 0; -} - static int copy_page_retry(int ufd, unsigned long offset) { return __copy_page(ufd, offset, true); } -static int copy_page(int ufd, unsigned long offset) -{ - return __copy_page(ufd, offset, false); -} - -static int uffd_read_msg(int ufd, struct uffd_msg *msg) -{ - int ret = read(uffd, msg, sizeof(*msg)); - - if (ret != sizeof(*msg)) { - if (ret < 0) { - if (errno == EAGAIN || errno == EINTR) - return 1; - err("blocking read error"); - } else { - err("short read"); - } - } - - return 0; -} - -static void uffd_handle_page_fault(struct uffd_msg *msg, - struct uffd_stats *stats) -{ - unsigned long offset; - - if (msg->event != UFFD_EVENT_PAGEFAULT) - err("unexpected msg event %u", msg->event); - - if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { - /* Write protect page faults */ - wp_range(uffd, msg->arg.pagefault.address, page_size, false); - stats->wp_faults++; - } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { - uint8_t *area; - int b; - - /* - * Minor page faults - * - * To prove we can modify the original range for testing - * purposes, we're going to bit flip this range before - * continuing. - * - * Note that this requires all minor page fault tests operate on - * area_dst (non-UFFD-registered) and area_dst_alias - * (UFFD-registered). - */ - - area = (uint8_t *)(area_dst + - ((char *)msg->arg.pagefault.address - - area_dst_alias)); - for (b = 0; b < page_size; ++b) - area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size); - stats->minor_faults++; - } else { - /* - * Missing page faults. - * - * Here we force a write check for each of the missing mode - * faults. It's guaranteed because the only threads that - * will trigger uffd faults are the locking threads, and - * their first instruction to touch the missing page will - * always be pthread_mutex_lock(). - * - * Note that here we relied on an NPTL glibc impl detail to - * always read the lock type at the entry of the lock op - * (pthread_mutex_t.__data.__type, offset 0x10) before - * doing any locking operations to guarantee that. It's - * actually not good to rely on this impl detail because - * logically a pthread-compatible lib can implement the - * locks without types and we can fail when linking with - * them. However since we used to find bugs with this - * strict check we still keep it around. Hopefully this - * could be a good hint when it fails again. If one day - * it'll break on some other impl of glibc we'll revisit. - */ - if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - err("unexpected write fault"); - - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); - - if (copy_page(uffd, offset)) - stats->missing_faults++; - } -} - -static void *uffd_poll_thread(void *arg) -{ - struct uffd_stats *stats = (struct uffd_stats *)arg; - unsigned long cpu = stats->cpu; - struct pollfd pollfd[2]; - struct uffd_msg msg; - struct uffdio_register uffd_reg; - int ret; - char tmp_chr; - - pollfd[0].fd = uffd; - pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd[cpu*2]; - pollfd[1].events = POLLIN; - - for (;;) { - ret = poll(pollfd, 2, -1); - if (ret <= 0) { - if (errno == EINTR || errno == EAGAIN) - continue; - err("poll error: %d", ret); - } - if (pollfd[1].revents & POLLIN) { - if (read(pollfd[1].fd, &tmp_chr, 1) != 1) - err("read pipefd error"); - break; - } - if (!(pollfd[0].revents & POLLIN)) - err("pollfd[0].revents %d", pollfd[0].revents); - if (uffd_read_msg(uffd, &msg)) - continue; - switch (msg.event) { - default: - err("unexpected msg event %u\n", msg.event); - break; - case UFFD_EVENT_PAGEFAULT: - uffd_handle_page_fault(&msg, stats); - break; - case UFFD_EVENT_FORK: - close(uffd); - uffd = msg.arg.fork.ufd; - pollfd[0].fd = uffd; - break; - case UFFD_EVENT_REMOVE: - uffd_reg.range.start = msg.arg.remove.start; - uffd_reg.range.len = msg.arg.remove.end - - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) - err("remove failure"); - break; - case UFFD_EVENT_REMAP: - area_remap = area_dst; /* save for later unmap */ - area_dst = (char *)(unsigned long)msg.arg.remap.to; - break; - } - } - - return NULL; -} - pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) -- GitLab From 686a8bb723497197022c73807cdd29eb5a1aeec8 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:44 -0400 Subject: [PATCH 3309/5631] selftests/mm: split uffd tests into uffd-stress and uffd-unit-tests In many ways it's weird and unwanted to keep all the tests in the same userfaultfd.c at least when still in the current way. For example, it doesn't make much sense to run the stress test for each method we can create an userfaultfd handle (either via syscall or /dev/ node). It's a waste of time running this twice for the whole stress as the stress paths are the same, only the open path is different. It's also just weird to need to manually specify different types of memory to run all unit tests for the userfaultfd interface. We should be able to just run a single program and that should go through all functional uffd tests without running the stress test at all. The stress test was more for torturing and finding race conditions. We don't want to wait for stress to finish just to regress test a functional test. When we start to pile up more things on top of the same file and same functions, things start to go a bit chaos and the code is just harder to maintain too with tons of global variables. This patch creates a new test uffd-unit-tests to keep userfaultfd unit tests in the future, currently empty. Meanwhile rename the old userfaultfd.c test to uffd-stress.c. Link: https://lkml.kernel.org/r/20230412164244.328270-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Rapoport (IBM) Reviewed-by: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/.gitignore | 3 ++- tools/testing/selftests/mm/Makefile | 8 +++--- tools/testing/selftests/mm/run_vmtests.sh | 10 ++++--- .../mm/{userfaultfd.c => uffd-stress.c} | 0 tools/testing/selftests/mm/uffd-unit-tests.c | 27 +++++++++++++++++++ 5 files changed, 40 insertions(+), 8 deletions(-) rename tools/testing/selftests/mm/{userfaultfd.c => uffd-stress.c} (100%) create mode 100644 tools/testing/selftests/mm/uffd-unit-tests.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 347277f2adc3..8917455f4f51 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -21,7 +21,8 @@ protection_keys protection_keys_32 protection_keys_64 madv_populate -userfaultfd +uffd-stress +uffd-unit-tests mlock-intersect-test mlock-random-test virtual_address_range diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 210da78ec495..63c03a6414fc 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -20,7 +20,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # Avoid accidental wrong builds, due to built-in rules working just a little # bit too well--but not quite as well as required for our situation here. # -# In other words, "make userfaultfd" is supposed to fail to build at all, +# In other words, "make $SOME_TEST" is supposed to fail to build at all, # because this Makefile only supports either "make" (all), or "make /full/path". # However, the built-in rules, if not suppressed, will pick up CFLAGS and the # initial LDLIBS (but not the target-specific LDLIBS, because those are only @@ -57,7 +57,8 @@ TEST_GEN_PROGS += mremap_test TEST_GEN_PROGS += on-fault-limit TEST_GEN_PROGS += thuge-gen TEST_GEN_PROGS += transhuge-stress -TEST_GEN_PROGS += userfaultfd +TEST_GEN_PROGS += uffd-stress +TEST_GEN_PROGS += uffd-unit-tests TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test TEST_GEN_PROGS += ksm_tests @@ -108,7 +109,8 @@ include ../lib.mk $(TEST_GEN_PROGS): vm_util.c -$(OUTPUT)/userfaultfd: uffd-common.c +$(OUTPUT)/uffd-stress: uffd-common.c +$(OUTPUT)/uffd-unit-tests: uffd-common.c ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index ddf40f883747..efe22dc569f0 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -196,14 +196,16 @@ CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 +CATEGORY="userfaultfd" run_test ./uffd-unit-tests uffd_mods=("" ":dev") +uffd_stress_bin=./uffd-stress for mod in "${uffd_mods[@]}"; do - CATEGORY="userfaultfd" run_test ./userfaultfd anon${mod} 20 16 + CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon${mod} 20 16 # Hugetlb tests require source and destination huge pages. Pass in half # the size ($half_ufd_size_MB), which is used for *each*. - CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb_shared${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ./userfaultfd shmem${mod} 20 16 + CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb${mod} "$half_ufd_size_MB" 32 + CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb_shared${mod} "$half_ufd_size_MB" 32 + CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem${mod} 20 16 done #cleanup diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/uffd-stress.c similarity index 100% rename from tools/testing/selftests/mm/userfaultfd.c rename to tools/testing/selftests/mm/uffd-stress.c diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c new file mode 100644 index 000000000000..6857388783be --- /dev/null +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd unit tests. + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ + +#include "uffd-common.h" + +#ifdef __NR_userfaultfd + +int main(int argc, char *argv[]) +{ + return KSFT_PASS; +} + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("Skipping %s (missing __NR_userfaultfd)\n", __file__); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ -- GitLab From c4277cb6c8e5dc60d425f3a148b3e2bf40d8d778 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:47 -0400 Subject: [PATCH 3310/5631] selftests/mm: uffd_[un]register() Add two helpers to register/unregister to an uffd. Use them to drop duplicate codes. This patch also drops assert_expected_ioctls_present() and get_expected_ioctls(). Reasons: - It'll need a lot of effort to pass test_type==HUGETLB into it from the upper, so it's the simplest way to get rid of another global var - The ioctls returned in UFFDIO_REGISTER is hardly useful at all, because any app can already detect kernel support on any ioctl via its corresponding UFFD_FEATURE_*. The check here is for sanity mostly but it's probably destined no user app will even use it. - It's not friendly to one future goal of uffd to run on old kernels, the problem is get_expected_ioctls() compiles against UFFD_API_RANGE_IOCTLS, which is a value that can change depending on where the test is compiled, rather than reflecting what the kernel underneath has. It means it'll report false negatives on old kernels so it's against our will. So let's make our lives easier. [peterx@redhat.com; tools/testing/selftests/mm/hugepage-mremap.c: add headers] Link: https://lkml.kernel.org/r/ZDxrvZh/cw357D8P@x1n Link: https://lkml.kernel.org/r/20230412164247.328293-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/hugepage-mremap.c | 9 +- .../selftests/mm/ksm_functional_tests.c | 6 +- tools/testing/selftests/mm/uffd-common.c | 27 ------ tools/testing/selftests/mm/uffd-common.h | 2 - tools/testing/selftests/mm/uffd-stress.c | 83 +++++-------------- tools/testing/selftests/mm/vm_util.c | 37 +++++++++ tools/testing/selftests/mm/vm_util.h | 4 + 7 files changed, 64 insertions(+), 104 deletions(-) diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index e53b5eaa8fce..cabd0084f57b 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -23,6 +23,8 @@ #include #include #include +#include +#include "vm_util.h" #define DEFAULT_LENGTH_MB 10UL #define MB_TO_BYTES(x) (x * 1024 * 1024) @@ -60,7 +62,6 @@ static void register_region_with_uffd(char *addr, size_t len) { long uffd; /* userfaultfd file descriptor */ struct uffdio_api uffdio_api; - struct uffdio_register uffdio_register; /* Create and enable userfaultfd object. */ @@ -96,11 +97,7 @@ static void register_region_with_uffd(char *addr, size_t len) * handling by the userfaultfd object. In mode, we request to track * missing pages (i.e., pages that have not yet been faulted in). */ - - uffdio_register.range.start = (unsigned long)addr; - uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { + if (uffd_register(uffd, addr, len, true, false, false)) { perror("ioctl-UFFDIO_REGISTER"); exit(1); } diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index d8b5b4930412..d3f26050dfd7 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -178,7 +178,6 @@ static void test_unmerge_discarded(void) static void test_unmerge_uffd_wp(void) { struct uffdio_writeprotect uffd_writeprotect; - struct uffdio_register uffdio_register; const unsigned int size = 2 * MiB; struct uffdio_api uffdio_api; char *map; @@ -210,10 +209,7 @@ static void test_unmerge_uffd_wp(void) } /* Register UFFD-WP, no need for an actual handler. */ - uffdio_register.range.start = (unsigned long) map; - uffdio_register.range.len = size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) { + if (uffd_register(uffd, map, size, false, true, false)) { ksft_test_result_fail("UFFDIO_REGISTER_MODE_WP failed\n"); goto close_uffd; } diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index c57757c2a36f..daa5b5781e7a 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -330,33 +330,6 @@ void uffd_test_ctx_init(uint64_t features) err("pipe"); } -uint64_t get_expected_ioctls(uint64_t mode) -{ - uint64_t ioctls = UFFD_API_RANGE_IOCTLS; - - if (test_type == TEST_HUGETLB) - ioctls &= ~(1 << _UFFDIO_ZEROPAGE); - - if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp)) - ioctls &= ~(1 << _UFFDIO_WRITEPROTECT); - - if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor)) - ioctls &= ~(1 << _UFFDIO_CONTINUE); - - return ioctls; -} - -void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) -{ - uint64_t expected = get_expected_ioctls(mode); - uint64_t actual = ioctls & expected; - - if (actual != expected) { - err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64, - expected, actual); - } -} - void wp_range(int ufd, __u64 start, __u64 len, bool wp) { struct uffdio_writeprotect prms; diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index d9430cfdcb19..11f770391bd9 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -101,8 +101,6 @@ extern uffd_test_ops_t *uffd_test_ops; void uffd_stats_report(struct uffd_stats *stats, int n_cpus); void uffd_test_ctx_init(uint64_t features); void userfaultfd_open(uint64_t *features); -uint64_t get_expected_ioctls(uint64_t mode); -void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls); int uffd_read_msg(int ufd, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index c68a9aeefc41..e6d39a755082 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -463,28 +463,19 @@ static int uffdio_zeropage(int ufd, unsigned long offset) /* exercise UFFDIO_ZEROPAGE */ static int userfaultfd_zeropage_test(void) { - struct uffdio_register uffdio_register; - printf("testing UFFDIO_ZEROPAGE: "); fflush(stdout); uffd_test_ctx_init(0); - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, test_uffdio_wp, false)) err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - if (area_dst_alias) { /* Needed this to test zeropage-retry on shared memory */ - uffdio_register.range.start = (unsigned long) area_dst_alias; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + true, test_uffdio_wp, false)) err("register failure"); } @@ -498,7 +489,6 @@ static int userfaultfd_zeropage_test(void) static int userfaultfd_events_test(void) { - struct uffdio_register uffdio_register; pthread_t uffd_mon; int err, features; pid_t pid; @@ -514,17 +504,10 @@ static int userfaultfd_events_test(void) fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, test_uffdio_wp, false)) err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) err("uffd_poll_thread create"); @@ -550,7 +533,6 @@ static int userfaultfd_events_test(void) static int userfaultfd_sig_test(void) { - struct uffdio_register uffdio_register; unsigned long userfaults; pthread_t uffd_mon; int err, features; @@ -566,17 +548,10 @@ static int userfaultfd_sig_test(void) fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, test_uffdio_wp, false)) err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - if (faulting_process(1)) err("faulting process failed"); @@ -629,7 +604,6 @@ void check_memory_contents(char *p) static int userfaultfd_minor_test(void) { unsigned long p; - struct uffdio_register uffdio_register; pthread_t uffd_mon; char c; struct uffd_stats stats = { 0 }; @@ -642,17 +616,10 @@ static int userfaultfd_minor_test(void) uffd_test_ctx_init(uffd_minor_feature()); - uffdio_register.range.start = (unsigned long)area_dst_alias; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + false, test_uffdio_wp, true)) err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - /* * After registering with UFFD, populate the non-UFFD-registered side of * the shared mapping. This should *not* trigger any UFFD minor faults. @@ -777,7 +744,6 @@ static void userfaultfd_wp_unpopulated_test(int pagemap_fd) static void userfaultfd_pagemap_test(unsigned int test_pgsize) { - struct uffdio_register uffdio_register; int pagemap_fd; uint64_t value; @@ -805,10 +771,8 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) err("madvise(MADV_NOHUGEPAGE) failed"); } - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst, nr_pages * page_size, + false, true, false)) err("register failed"); pagemap_fd = pagemap_open(); @@ -858,8 +822,8 @@ static int userfaultfd_stress(void) { void *area; unsigned long nr; - struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; + uint64_t mem_size = nr_pages * page_size; uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); @@ -894,20 +858,13 @@ static int userfaultfd_stress(void) fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); /* register */ - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst, mem_size, + true, test_uffdio_wp, false)) err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); if (area_dst_alias) { - uffdio_register.range.start = (unsigned long) - area_dst_alias; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + if (uffd_register(uffd, area_dst_alias, mem_size, + true, test_uffdio_wp, false)) err("register failure alias"); } @@ -949,12 +906,10 @@ static int userfaultfd_stress(void) nr_pages * page_size, false); /* unregister */ - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) + if (uffd_unregister(uffd, area_dst, mem_size)) err("unregister failure"); if (area_dst_alias) { - uffdio_register.range.start = (unsigned long) area_dst; - if (ioctl(uffd, UFFDIO_UNREGISTER, - &uffdio_register.range)) + if (uffd_unregister(uffd, area_dst_alias, mem_size)) err("unregister failure alias"); } diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 54d227d6f70a..bb633d050d71 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include +#include #include "../kselftest.h" #include "vm_util.h" @@ -193,3 +195,38 @@ unsigned long default_huge_page_size(void) fclose(f); return hps; } + +int uffd_register(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor) +{ + struct uffdio_register uffdio_register = { 0 }; + uint64_t mode = 0; + int ret = 0; + + if (miss) + mode |= UFFDIO_REGISTER_MODE_MISSING; + if (wp) + mode |= UFFDIO_REGISTER_MODE_WP; + if (minor) + mode |= UFFDIO_REGISTER_MODE_MINOR; + + uffdio_register.range.start = (unsigned long)addr; + uffdio_register.range.len = len; + uffdio_register.mode = mode; + + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) + ret = -errno; + + return ret; +} + +int uffd_unregister(int uffd, void *addr, uint64_t len) +{ + struct uffdio_range range = { .start = (uintptr_t)addr, .len = len }; + int ret = 0; + + if (ioctl(uffd, UFFDIO_UNREGISTER, &range) == -1) + ret = -errno; + + return ret; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index d9fadddb5c69..3a9762022efd 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -45,6 +45,10 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); int64_t allocate_transhuge(void *ptr, int pagemap_fd); unsigned long default_huge_page_size(void); +int uffd_register(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor); +int uffd_unregister(int uffd, void *addr, uint64_t len); + /* * On ppc64 this will only work with radix 2M hugepage size */ -- GitLab From 78391f6460ee2cb43f64bbdd7a7cf840e5a118a6 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:54 -0400 Subject: [PATCH 3311/5631] selftests/mm: uffd_open_{dev|sys}() Provide two helpers to open an uffd handle. Drop the error checks around SKIPs because it's inside an errexit() anyway, which IMHO doesn't really help much if the test will not continue. Link: https://lkml.kernel.org/r/20230412164254.328335-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Reviewed-by: Mike Rapoport (IBM) Reviewed-by: Axel Rasmussen Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 28 +++++------------------- tools/testing/selftests/mm/vm_util.c | 24 ++++++++++++++++++++ tools/testing/selftests/mm/vm_util.h | 2 ++ 3 files changed, 31 insertions(+), 23 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index daa5b5781e7a..09ea24c5f02c 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -192,34 +192,16 @@ void uffd_stats_report(struct uffd_stats *stats, int n_cpus) printf("\n"); } -static int __userfaultfd_open_dev(void) -{ - int fd, _uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - errexit(KSFT_SKIP, "opening /dev/userfaultfd failed"); - - _uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS); - if (_uffd < 0) - errexit(errno == ENOTTY ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - close(fd); - return _uffd; -} - void userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; if (test_dev_userfaultfd) - uffd = __userfaultfd_open_dev(); - else { - uffd = syscall(__NR_userfaultfd, UFFD_FLAGS); - if (uffd < 0) - errexit(errno == ENOSYS ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - } + uffd = uffd_open_dev(UFFD_FLAGS); + else + uffd = uffd_open_sys(UFFD_FLAGS); + if (uffd < 0) + err("uffd open failed (dev=%d)", test_dev_userfaultfd); uffd_flags = fcntl(uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index bb633d050d71..5ee6c4688a7c 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -3,6 +3,8 @@ #include #include #include +#include +#include #include "../kselftest.h" #include "vm_util.h" @@ -230,3 +232,25 @@ int uffd_unregister(int uffd, void *addr, uint64_t len) return ret; } + +int uffd_open_dev(unsigned int flags) +{ + int fd, uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); + close(fd); + + return uffd; +} + +int uffd_open_sys(unsigned int flags) +{ +#ifdef __NR_userfaultfd + return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 3a9762022efd..481354141533 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -48,6 +48,8 @@ unsigned long default_huge_page_size(void); int uffd_register(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor); int uffd_unregister(int uffd, void *addr, uint64_t len); +int uffd_open_dev(unsigned int flags); +int uffd_open_sys(unsigned int flags); /* * On ppc64 this will only work with radix 2M hugepage size -- GitLab From d5433ce84d2572d43a3c58e5cab21db200669bfd Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:42:57 -0400 Subject: [PATCH 3312/5631] selftests/mm: UFFDIO_API test Add one simple test for UFFDIO_API. With that, I also added a bunch of small but handy helpers along the way. Link: https://lkml.kernel.org/r/20230412164257.328375-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 109 ++++++++++++++++++- 1 file changed, 108 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 6857388783be..bb492c258486 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -9,9 +9,116 @@ #ifdef __NR_userfaultfd +static void uffd_test_report(void) +{ + printf("Userfaults unit tests: pass=%u, skip=%u, fail=%u (total=%u)\n", + ksft_get_pass_cnt(), + ksft_get_xskip_cnt(), + ksft_get_fail_cnt(), + ksft_test_num()); +} + +static void uffd_test_pass(void) +{ + printf("done\n"); + ksft_inc_pass_cnt(); +} + +#define uffd_test_start(...) do { \ + printf("Testing "); \ + printf(__VA_ARGS__); \ + printf("... "); \ + fflush(stdout); \ + } while (0) + +#define uffd_test_fail(...) do { \ + printf("failed [reason: "); \ + printf(__VA_ARGS__); \ + printf("]\n"); \ + ksft_inc_fail_cnt(); \ + } while (0) + +#define uffd_test_skip(...) do { \ + printf("skipped [reason: "); \ + printf(__VA_ARGS__); \ + printf("]\n"); \ + ksft_inc_xskip_cnt(); \ + } while (0) + +/* + * Returns 1 if specific userfaultfd supported, 0 otherwise. Note, we'll + * return 1 even if some test failed as long as uffd supported, because in + * that case we still want to proceed with the rest uffd unit tests. + */ +static int test_uffd_api(bool use_dev) +{ + struct uffdio_api uffdio_api; + int uffd; + + uffd_test_start("UFFDIO_API (with %s)", + use_dev ? "/dev/userfaultfd" : "syscall"); + + if (use_dev) + uffd = uffd_open_dev(UFFD_FLAGS); + else + uffd = uffd_open_sys(UFFD_FLAGS); + if (uffd < 0) { + uffd_test_skip("cannot open userfaultfd handle"); + return 0; + } + + /* Test wrong UFFD_API */ + uffdio_api.api = 0xab; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should fail with wrong api but didn't"); + goto out; + } + + /* Test wrong feature bit */ + uffdio_api.api = UFFD_API; + uffdio_api.features = BIT_ULL(63); + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should fail with wrong feature but didn't"); + goto out; + } + + /* Test normal UFFDIO_API */ + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { + uffd_test_fail("UFFDIO_API should succeed but failed"); + goto out; + } + + /* Test double requests of UFFDIO_API with a random feature set */ + uffdio_api.features = BIT_ULL(0); + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should reject initialized uffd"); + goto out; + } + + uffd_test_pass(); +out: + close(uffd); + /* We have a valid uffd handle */ + return 1; +} + int main(int argc, char *argv[]) { - return KSFT_PASS; + int has_uffd; + + has_uffd = test_uffd_api(false); + has_uffd |= test_uffd_api(true); + + if (!has_uffd) { + printf("Userfaultfd not supported or unprivileged, skip all tests\n"); + exit(KSFT_SKIP); + } + uffd_test_report(); + + return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS; } #else /* __NR_userfaultfd */ -- GitLab From c5cb903646f4df0ab3760dcb2e5571b528b6db59 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:31 -0400 Subject: [PATCH 3313/5631] selftests/mm: drop global mem_fd in uffd tests Drop it by creating the memfd dynamically in the tests. Link: https://lkml.kernel.org/r/20230412164331.328584-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 28 +++++++++++++++++++++++- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-stress.c | 15 ------------- 3 files changed, 28 insertions(+), 17 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 09ea24c5f02c..b1617f5d4517 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -12,12 +12,32 @@ volatile bool test_uffdio_copy_eexist = true; unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -int mem_fd, uffd = -1, uffd_flags, finished, *pipefd, test_type; +int uffd = -1, uffd_flags, finished, *pipefd, test_type; bool map_shared, test_collapse, test_dev_userfaultfd; bool test_uffdio_wp = true, test_uffdio_minor = false; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; +static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) +{ + unsigned int memfd_flags = 0; + int mem_fd; + + if (hugetlb) + memfd_flags = MFD_HUGETLB; + mem_fd = memfd_create("uffd-test", memfd_flags); + if (mem_fd < 0) + err("memfd_create"); + if (ftruncate(mem_fd, mem_size)) + err("ftruncate"); + if (fallocate(mem_fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + mem_size)) + err("fallocate"); + + return mem_fd; +} + static void anon_release_pages(char *rel_area) { if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) @@ -51,6 +71,7 @@ static void hugetlb_allocate_area(void **alloc_area, bool is_src) off_t offset = is_src ? 0 : size; void *area_alias = NULL; char **alloc_area_alias; + int mem_fd = uffd_mem_fd_create(size * 2, true); *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, (map_shared ? MAP_SHARED : MAP_PRIVATE) | @@ -73,6 +94,8 @@ static void hugetlb_allocate_area(void **alloc_area, bool is_src) } if (area_alias) *alloc_area_alias = area_alias; + + close(mem_fd); } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -95,6 +118,7 @@ static void shmem_allocate_area(void **alloc_area, bool is_src) size_t bytes = nr_pages * page_size; unsigned long offset = is_src ? 0 : bytes; char *p = NULL, *p_alias = NULL; + int mem_fd = uffd_mem_fd_create(bytes * 2, false); if (test_collapse) { p = BASE_PMD_ADDR; @@ -124,6 +148,8 @@ static void shmem_allocate_area(void **alloc_area, bool is_src) area_src_alias = area_alias; else area_dst_alias = area_alias; + + close(mem_fd); } static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 11f770391bd9..0dfab7057295 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -87,7 +87,7 @@ typedef struct uffd_test_ops uffd_test_ops_t; extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -extern int mem_fd, uffd, uffd_flags, finished, *pipefd, test_type; +extern int uffd, uffd_flags, finished, *pipefd, test_type; extern bool map_shared, test_collapse, test_dev_userfaultfd; extern bool test_uffdio_wp, test_uffdio_minor; extern unsigned long long *count_verify; diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index e6d39a755082..4eca1a0276c2 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -1090,21 +1090,6 @@ int main(int argc, char **argv) } nr_pages = nr_pages_per_cpu * nr_cpus; - if (test_type == TEST_SHMEM || test_type == TEST_HUGETLB) { - unsigned int memfd_flags = 0; - - if (test_type == TEST_HUGETLB) - memfd_flags = MFD_HUGETLB; - mem_fd = memfd_create(argv[0], memfd_flags); - if (mem_fd < 0) - err("memfd_create"); - if (ftruncate(mem_fd, nr_pages * page_size * 2)) - err("ftruncate"); - if (fallocate(mem_fd, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - nr_pages * page_size * 2)) - err("fallocate"); - } printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", nr_pages, nr_pages_per_cpu); return userfaultfd_stress(); -- GitLab From 265818ef988b3a4cd12fc8885966413b78f06d96 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:33 -0400 Subject: [PATCH 3314/5631] selftests/mm: drop global hpage_size in uffd tests hpage_size was wrongly used. Sometimes it means hugetlb default size, sometimes it was used as thp size. Remove the global variable and use the right one at each place. Link: https://lkml.kernel.org/r/20230412164333.328596-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 7 ++++--- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-stress.c | 6 +++--- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index b1617f5d4517..f02dfcf10714 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -10,7 +10,7 @@ #define BASE_PMD_ADDR ((void *)(1UL << 30)) volatile bool test_uffdio_copy_eexist = true; -unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; +unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; int uffd = -1, uffd_flags, finished, *pipefd, test_type; bool map_shared, test_collapse, test_dev_userfaultfd; @@ -115,7 +115,7 @@ static void shmem_release_pages(char *rel_area) static void shmem_allocate_area(void **alloc_area, bool is_src) { void *area_alias = NULL; - size_t bytes = nr_pages * page_size; + size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); unsigned long offset = is_src ? 0 : bytes; char *p = NULL, *p_alias = NULL; int mem_fd = uffd_mem_fd_create(bytes * 2, false); @@ -159,7 +159,8 @@ static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) { - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, hpage_size)) + if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, + read_pmd_pagesize())) err("Did not find expected %d number of hugepages", expect_nr_hpages); } diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 0dfab7057295..47565b2f2dee 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -85,7 +85,7 @@ struct uffd_test_ops { }; typedef struct uffd_test_ops uffd_test_ops_t; -extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; +extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; extern int uffd, uffd_flags, finished, *pipefd, test_type; extern bool map_shared, test_collapse, test_dev_userfaultfd; diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 4eca1a0276c2..54fc9b4ffa3c 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -655,7 +655,7 @@ static int userfaultfd_minor_test(void) uffd_test_ops->check_pmd_mapping(area_dst, nr_pages * page_size / - hpage_size); + read_pmd_pagesize()); /* * This won't cause uffd-fault - it purely just makes sure there * was no corruption. @@ -997,7 +997,7 @@ static void parse_test_type_arg(const char *raw_type) err("Unsupported test: %s", raw_type); if (test_type == TEST_HUGETLB) - page_size = hpage_size; + page_size = default_huge_page_size(); else page_size = sysconf(_SC_PAGE_SIZE); @@ -1035,6 +1035,7 @@ static void sigalrm(int sig) int main(int argc, char **argv) { size_t bytes; + size_t hpage_size = read_pmd_pagesize(); if (argc < 4) usage(); @@ -1043,7 +1044,6 @@ int main(int argc, char **argv) err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); - hpage_size = default_huge_page_size(); parse_test_type_arg(argv[1]); bytes = atol(argv[2]) * 1024 * 1024; -- GitLab From 508340845dd1423b6c81fccf082039dff202fb9f Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:37 -0400 Subject: [PATCH 3315/5631] selftests/mm: rename uffd_stats to uffd_args Prepare for adding more fields into the struct. Link: https://lkml.kernel.org/r/20230412164337.328607-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 28 ++++++------- tools/testing/selftests/mm/uffd-common.h | 6 +-- tools/testing/selftests/mm/uffd-stress.c | 51 ++++++++++++------------ 3 files changed, 42 insertions(+), 43 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index f02dfcf10714..e746405aa8f3 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -186,34 +186,34 @@ struct uffd_test_ops hugetlb_uffd_test_ops = { .check_pmd_mapping = NULL, }; -void uffd_stats_report(struct uffd_stats *stats, int n_cpus) +void uffd_stats_report(struct uffd_args *args, int n_cpus) { int i; unsigned long long miss_total = 0, wp_total = 0, minor_total = 0; for (i = 0; i < n_cpus; i++) { - miss_total += stats[i].missing_faults; - wp_total += stats[i].wp_faults; - minor_total += stats[i].minor_faults; + miss_total += args[i].missing_faults; + wp_total += args[i].wp_faults; + minor_total += args[i].minor_faults; } printf("userfaults: "); if (miss_total) { printf("%llu missing (", miss_total); for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].missing_faults); + printf("%lu+", args[i].missing_faults); printf("\b) "); } if (wp_total) { printf("%llu wp (", wp_total); for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].wp_faults); + printf("%lu+", args[i].wp_faults); printf("\b) "); } if (minor_total) { printf("%llu minor (", minor_total); for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].minor_faults); + printf("%lu+", args[i].minor_faults); printf("\b)"); } printf("\n"); @@ -397,7 +397,7 @@ int uffd_read_msg(int ufd, struct uffd_msg *msg) return 0; } -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats) +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) { unsigned long offset; @@ -407,7 +407,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats) if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { /* Write protect page faults */ wp_range(uffd, msg->arg.pagefault.address, page_size, false); - stats->wp_faults++; + args->wp_faults++; } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { uint8_t *area; int b; @@ -430,7 +430,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats) for (b = 0; b < page_size; ++b) area[b] = ~area[b]; continue_range(uffd, msg->arg.pagefault.address, page_size); - stats->minor_faults++; + args->minor_faults++; } else { /* * Missing page faults. @@ -460,14 +460,14 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats) offset &= ~(page_size-1); if (copy_page(uffd, offset)) - stats->missing_faults++; + args->missing_faults++; } } void *uffd_poll_thread(void *arg) { - struct uffd_stats *stats = (struct uffd_stats *)arg; - unsigned long cpu = stats->cpu; + struct uffd_args *args = (struct uffd_args *)arg; + unsigned long cpu = args->cpu; struct pollfd pollfd[2]; struct uffd_msg msg; struct uffdio_register uffd_reg; @@ -502,7 +502,7 @@ void *uffd_poll_thread(void *arg) err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: - uffd_handle_page_fault(&msg, stats); + uffd_handle_page_fault(&msg, args); break; case UFFD_EVENT_FORK: close(uffd); diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 47565b2f2dee..f8d2ad178827 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -70,7 +70,7 @@ - 1))) /* Userfaultfd test statistics */ -struct uffd_stats { +struct uffd_args { int cpu; unsigned long missing_faults; unsigned long wp_faults; @@ -98,12 +98,12 @@ extern uffd_test_ops_t shmem_uffd_test_ops; extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; -void uffd_stats_report(struct uffd_stats *stats, int n_cpus); +void uffd_stats_report(struct uffd_args *args, int n_cpus); void uffd_test_ctx_init(uint64_t features); void userfaultfd_open(uint64_t *features); int uffd_read_msg(int ufd, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); -void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_stats *stats); +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); int __copy_page(int ufd, unsigned long offset, bool retry); int copy_page(int ufd, unsigned long offset); void *uffd_poll_thread(void *arg); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 54fc9b4ffa3c..ce7251ab93ef 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -90,16 +90,15 @@ static void usage(void) exit(1); } -static void uffd_stats_reset(struct uffd_stats *uffd_stats, - unsigned long n_cpus) +static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) { int i; for (i = 0; i < n_cpus; i++) { - uffd_stats[i].cpu = i; - uffd_stats[i].missing_faults = 0; - uffd_stats[i].wp_faults = 0; - uffd_stats[i].minor_faults = 0; + args[i].cpu = i; + args[i].missing_faults = 0; + args[i].wp_faults = 0; + args[i].minor_faults = 0; } } @@ -163,7 +162,7 @@ pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; static void *uffd_read_thread(void *arg) { - struct uffd_stats *stats = (struct uffd_stats *)arg; + struct uffd_args *args = (struct uffd_args *)arg; struct uffd_msg msg; pthread_mutex_unlock(&uffd_read_mutex); @@ -172,7 +171,7 @@ static void *uffd_read_thread(void *arg) for (;;) { if (uffd_read_msg(uffd, &msg)) continue; - uffd_handle_page_fault(&msg, stats); + uffd_handle_page_fault(&msg, args); } return NULL; @@ -210,7 +209,7 @@ static void *background_thread(void *arg) return NULL; } -static int stress(struct uffd_stats *uffd_stats) +static int stress(struct uffd_args *args) { unsigned long cpu; pthread_t locking_threads[nr_cpus]; @@ -225,12 +224,12 @@ static int stress(struct uffd_stats *uffd_stats) if (bounces & BOUNCE_POLL) { if (pthread_create(&uffd_threads[cpu], &attr, uffd_poll_thread, - (void *)&uffd_stats[cpu])) + (void *)&args[cpu])) return 1; } else { if (pthread_create(&uffd_threads[cpu], &attr, uffd_read_thread, - (void *)&uffd_stats[cpu])) + (void *)&args[cpu])) return 1; pthread_mutex_lock(&uffd_read_mutex); } @@ -264,7 +263,7 @@ static int stress(struct uffd_stats *uffd_stats) if (write(pipefd[cpu*2+1], &c, 1) != 1) err("pipefd write error"); if (pthread_join(uffd_threads[cpu], - (void *)&uffd_stats[cpu])) + (void *)&args[cpu])) return 1; } else { if (pthread_cancel(uffd_threads[cpu])) @@ -493,7 +492,7 @@ static int userfaultfd_events_test(void) int err, features; pid_t pid; char c; - struct uffd_stats stats = { 0 }; + struct uffd_args args = { 0 }; printf("testing events (fork, remap, remove): "); fflush(stdout); @@ -508,7 +507,7 @@ static int userfaultfd_events_test(void) true, test_uffdio_wp, false)) err("register failure"); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); pid = fork(); @@ -526,9 +525,9 @@ static int userfaultfd_events_test(void) if (pthread_join(uffd_mon, NULL)) return 1; - uffd_stats_report(&stats, 1); + uffd_stats_report(&args, 1); - return stats.missing_faults != nr_pages; + return args.missing_faults != nr_pages; } static int userfaultfd_sig_test(void) @@ -538,7 +537,7 @@ static int userfaultfd_sig_test(void) int err, features; pid_t pid; char c; - struct uffd_stats stats = { 0 }; + struct uffd_args args = { 0 }; printf("testing signal delivery: "); fflush(stdout); @@ -557,7 +556,7 @@ static int userfaultfd_sig_test(void) uffd_test_ops->release_pages(area_dst); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); pid = fork(); @@ -606,7 +605,7 @@ static int userfaultfd_minor_test(void) unsigned long p; pthread_t uffd_mon; char c; - struct uffd_stats stats = { 0 }; + struct uffd_args args = { 0 }; if (!test_uffdio_minor) return 0; @@ -629,7 +628,7 @@ static int userfaultfd_minor_test(void) page_size); } - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); /* @@ -645,7 +644,7 @@ static int userfaultfd_minor_test(void) if (pthread_join(uffd_mon, NULL)) return 1; - uffd_stats_report(&stats, 1); + uffd_stats_report(&args, 1); if (test_collapse) { printf("testing collapse of uffd memory into PMD-mapped THPs:"); @@ -664,7 +663,7 @@ static int userfaultfd_minor_test(void) printf(" done.\n"); } - return stats.missing_faults != 0 || stats.minor_faults != nr_pages; + return args.missing_faults != 0 || args.minor_faults != nr_pages; } static int pagemap_open(void) @@ -822,7 +821,7 @@ static int userfaultfd_stress(void) { void *area; unsigned long nr; - struct uffd_stats uffd_stats[nr_cpus]; + struct uffd_args args[nr_cpus]; uint64_t mem_size = nr_pages * page_size; uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); @@ -894,10 +893,10 @@ static int userfaultfd_stress(void) */ uffd_test_ops->release_pages(area_dst); - uffd_stats_reset(uffd_stats, nr_cpus); + uffd_stats_reset(args, nr_cpus); /* bounce pass */ - if (stress(uffd_stats)) + if (stress(args)) return 1; /* Clear all the write protections if there is any */ @@ -926,7 +925,7 @@ static int userfaultfd_stress(void) swap(area_src_alias, area_dst_alias); - uffd_stats_report(uffd_stats, nr_cpus); + uffd_stats_report(args, nr_cpus); } if (test_type == TEST_ANON) { -- GitLab From 0210c43ef623a3c35cafd7dbe25b1b3c1699e7e9 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:41 -0400 Subject: [PATCH 3316/5631] selftests/mm: let uffd_handle_page_fault() take wp parameter Make the handler optionally apply WP bit when resolving page faults for either missing or minor page faults. This moves towards removing global test_uffdio_wp outside of the common code. Link: https://lkml.kernel.org/r/20230412164341.328618-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 17 +++++++++-------- tools/testing/selftests/mm/uffd-common.h | 6 ++++-- tools/testing/selftests/mm/uffd-stress.c | 16 ++++++++++------ 3 files changed, 23 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index e746405aa8f3..daa2a95408e6 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -353,7 +353,7 @@ void wp_range(int ufd, __u64 start, __u64 len, bool wp) err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); } -static void continue_range(int ufd, __u64 start, __u64 len) +static void continue_range(int ufd, __u64 start, __u64 len, bool wp) { struct uffdio_continue req; int ret; @@ -361,7 +361,7 @@ static void continue_range(int ufd, __u64 start, __u64 len) req.range.start = start; req.range.len = len; req.mode = 0; - if (test_uffdio_wp) + if (wp) req.mode |= UFFDIO_CONTINUE_MODE_WP; if (ioctl(ufd, UFFDIO_CONTINUE, &req)) @@ -429,7 +429,8 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) area_dst_alias)); for (b = 0; b < page_size; ++b) area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size); + continue_range(uffd, msg->arg.pagefault.address, page_size, + args->apply_wp); args->minor_faults++; } else { /* @@ -459,7 +460,7 @@ void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; offset &= ~(page_size-1); - if (copy_page(uffd, offset)) + if (copy_page(uffd, offset, args->apply_wp)) args->missing_faults++; } } @@ -555,7 +556,7 @@ static void wake_range(int ufd, unsigned long addr, unsigned long len) addr), exit(1); } -int __copy_page(int ufd, unsigned long offset, bool retry) +int __copy_page(int ufd, unsigned long offset, bool retry, bool wp) { struct uffdio_copy uffdio_copy; @@ -564,7 +565,7 @@ int __copy_page(int ufd, unsigned long offset, bool retry) uffdio_copy.dst = (unsigned long) area_dst + offset; uffdio_copy.src = (unsigned long) area_src + offset; uffdio_copy.len = page_size; - if (test_uffdio_wp) + if (wp) uffdio_copy.mode = UFFDIO_COPY_MODE_WP; else uffdio_copy.mode = 0; @@ -587,7 +588,7 @@ int __copy_page(int ufd, unsigned long offset, bool retry) return 0; } -int copy_page(int ufd, unsigned long offset) +int copy_page(int ufd, unsigned long offset, bool wp) { - return __copy_page(ufd, offset, false); + return __copy_page(ufd, offset, false, wp); } diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index f8d2ad178827..0ec07d025cfe 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -72,6 +72,8 @@ /* Userfaultfd test statistics */ struct uffd_args { int cpu; + /* Whether apply wr-protects when installing pages */ + bool apply_wp; unsigned long missing_faults; unsigned long wp_faults; unsigned long minor_faults; @@ -104,8 +106,8 @@ void userfaultfd_open(uint64_t *features); int uffd_read_msg(int ufd, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); -int __copy_page(int ufd, unsigned long offset, bool retry); -int copy_page(int ufd, unsigned long offset); +int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); +int copy_page(int ufd, unsigned long offset, bool wp); void *uffd_poll_thread(void *arg); #define TEST_ANON 1 diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index ce7251ab93ef..747d588c0d69 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -96,6 +96,7 @@ static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) for (i = 0; i < n_cpus; i++) { args[i].cpu = i; + args[i].apply_wp = test_uffdio_wp; args[i].missing_faults = 0; args[i].wp_faults = 0; args[i].minor_faults = 0; @@ -155,7 +156,7 @@ static void *locking_thread(void *arg) static int copy_page_retry(int ufd, unsigned long offset) { - return __copy_page(ufd, offset, true); + return __copy_page(ufd, offset, true, test_uffdio_wp); } pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -308,7 +309,7 @@ static void sighndl(int sig, siginfo_t *siginfo, void *ptr) * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(int signal_test) +static int faulting_process(int signal_test, bool wp) { unsigned long nr; unsigned long long count; @@ -343,7 +344,7 @@ static int faulting_process(int signal_test) if (steps == 1) { /* This is a MISSING request */ steps++; - if (copy_page(uffd, offset)) + if (copy_page(uffd, offset, wp)) signalled++; } else { /* This is a WP request */ @@ -507,6 +508,7 @@ static int userfaultfd_events_test(void) true, test_uffdio_wp, false)) err("register failure"); + args.apply_wp = test_uffdio_wp; if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); @@ -515,7 +517,7 @@ static int userfaultfd_events_test(void) err("fork"); if (!pid) - exit(faulting_process(0)); + exit(faulting_process(0, test_uffdio_wp)); waitpid(pid, &err, 0); if (err) @@ -551,11 +553,12 @@ static int userfaultfd_sig_test(void) true, test_uffdio_wp, false)) err("register failure"); - if (faulting_process(1)) + if (faulting_process(1, test_uffdio_wp)) err("faulting process failed"); uffd_test_ops->release_pages(area_dst); + args.apply_wp = test_uffdio_wp; if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); @@ -564,7 +567,7 @@ static int userfaultfd_sig_test(void) err("fork"); if (!pid) - exit(faulting_process(2)); + exit(faulting_process(2, test_uffdio_wp)); waitpid(pid, &err, 0); if (err) @@ -628,6 +631,7 @@ static int userfaultfd_minor_test(void) page_size); } + args.apply_wp = test_uffdio_wp; if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) err("uffd_poll_thread create"); -- GitLab From be39fec4f97f01329ef48a5a3836f592f6a82766 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:45 -0400 Subject: [PATCH 3317/5631] selftests/mm: allow allocate_area() to fail properly Mostly to detect hugetlb allocation errors and skip hugetlb tests when pages are not allocated. Link: https://lkml.kernel.org/r/20230412164345.328659-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 47 +++++++++++++++++------- tools/testing/selftests/mm/uffd-common.h | 4 +- 2 files changed, 36 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index daa2a95408e6..bc6c5c38d6dd 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -44,10 +44,15 @@ static void anon_release_pages(char *rel_area) err("madvise(MADV_DONTNEED) failed"); } -static void anon_allocate_area(void **alloc_area, bool is_src) +static int anon_allocate_area(void **alloc_area, bool is_src) { *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } + return 0; } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -65,7 +70,7 @@ static void hugetlb_release_pages(char *rel_area) } } -static void hugetlb_allocate_area(void **alloc_area, bool is_src) +static int hugetlb_allocate_area(void **alloc_area, bool is_src) { off_t size = nr_pages * page_size; off_t offset = is_src ? 0 : size; @@ -77,14 +82,16 @@ static void hugetlb_allocate_area(void **alloc_area, bool is_src) (map_shared ? MAP_SHARED : MAP_PRIVATE) | (is_src ? 0 : MAP_NORESERVE), mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of hugetlbfs file failed"); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } if (map_shared) { area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); if (area_alias == MAP_FAILED) - err("mmap of hugetlb file alias failed"); + return -errno; } if (is_src) { @@ -96,6 +103,7 @@ static void hugetlb_allocate_area(void **alloc_area, bool is_src) *alloc_area_alias = area_alias; close(mem_fd); + return 0; } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -112,7 +120,7 @@ static void shmem_release_pages(char *rel_area) err("madvise(MADV_REMOVE) failed"); } -static void shmem_allocate_area(void **alloc_area, bool is_src) +static int shmem_allocate_area(void **alloc_area, bool is_src) { void *area_alias = NULL; size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); @@ -132,15 +140,20 @@ static void shmem_allocate_area(void **alloc_area, bool is_src) *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of memfd failed"); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } if (test_collapse && *alloc_area != p) err("mmap of memfd failed at %p", p); area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); - if (area_alias == MAP_FAILED) - err("mmap of memfd alias failed"); + if (area_alias == MAP_FAILED) { + munmap(*alloc_area, bytes); + *alloc_area = NULL; + return -errno; + } if (test_collapse && area_alias != p_alias) err("mmap of anonymous memory failed at %p", p_alias); @@ -150,6 +163,7 @@ static void shmem_allocate_area(void **alloc_area, bool is_src) area_dst_alias = area_alias; close(mem_fd); + return 0; } static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -282,14 +296,19 @@ static void uffd_test_ctx_clear(void) munmap_area((void **)&area_remap); } -void uffd_test_ctx_init(uint64_t features) +int uffd_test_ctx_init(uint64_t features) { unsigned long nr, cpu; + int ret; uffd_test_ctx_clear(); - uffd_test_ops->allocate_area((void **)&area_src, true); - uffd_test_ops->allocate_area((void **)&area_dst, false); + ret = uffd_test_ops->allocate_area((void **)&area_src, true); + if (ret) + return ret; + ret = uffd_test_ops->allocate_area((void **)&area_dst, false); + if (ret) + return ret; userfaultfd_open(&features); @@ -337,6 +356,8 @@ void uffd_test_ctx_init(uint64_t features) for (cpu = 0; cpu < nr_cpus; cpu++) if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) err("pipe"); + + return 0; } void wp_range(int ufd, __u64 start, __u64 len, bool wp) diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 0ec07d025cfe..9479a0649d7f 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -80,7 +80,7 @@ struct uffd_args { }; struct uffd_test_ops { - void (*allocate_area)(void **alloc_area, bool is_src); + int (*allocate_area)(void **alloc_area, bool is_src); void (*release_pages)(char *rel_area); void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); void (*check_pmd_mapping)(void *p, int expect_nr_hpages); @@ -101,7 +101,7 @@ extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; void uffd_stats_report(struct uffd_args *args, int n_cpus); -void uffd_test_ctx_init(uint64_t features); +int uffd_test_ctx_init(uint64_t features); void userfaultfd_open(uint64_t *features); int uffd_read_msg(int ufd, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); -- GitLab From 16a45b57cbf2312215fbac79df4b58a0d70e1f2b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:48 -0400 Subject: [PATCH 3318/5631] selftests/mm: add framework for uffd-unit-test Add a framework to be prepared to move unit tests from uffd-stress.c into uffd-unit-tests.c. The goal is to allow detection of uffd features for each test, and also loop over specified types of memory that a test support. Link: https://lkml.kernel.org/r/20230412164348.328710-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 124 +++++++++++++++++++ tools/testing/selftests/mm/vm_util.c | 37 ++++++ tools/testing/selftests/mm/vm_util.h | 2 + 3 files changed, 163 insertions(+) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index bb492c258486..936b24a6f468 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -9,6 +9,66 @@ #ifdef __NR_userfaultfd +/* The unit test doesn't need a large or random size, make it 32MB for now */ +#define UFFD_TEST_MEM_SIZE (32UL << 20) + +#define MEM_ANON BIT_ULL(0) +#define MEM_SHMEM BIT_ULL(1) +#define MEM_SHMEM_PRIVATE BIT_ULL(2) +#define MEM_HUGETLB BIT_ULL(3) +#define MEM_HUGETLB_PRIVATE BIT_ULL(4) + +struct mem_type { + const char *name; + unsigned int mem_flag; + uffd_test_ops_t *mem_ops; + bool shared; +}; +typedef struct mem_type mem_type_t; + +mem_type_t mem_types[] = { + { + .name = "anon", + .mem_flag = MEM_ANON, + .mem_ops = &anon_uffd_test_ops, + .shared = false, + }, + { + .name = "shmem", + .mem_flag = MEM_SHMEM, + .mem_ops = &shmem_uffd_test_ops, + .shared = true, + }, + { + .name = "shmem-private", + .mem_flag = MEM_SHMEM_PRIVATE, + .mem_ops = &shmem_uffd_test_ops, + .shared = false, + }, + { + .name = "hugetlb", + .mem_flag = MEM_HUGETLB, + .mem_ops = &hugetlb_uffd_test_ops, + .shared = true, + }, + { + .name = "hugetlb-private", + .mem_flag = MEM_HUGETLB_PRIVATE, + .mem_ops = &hugetlb_uffd_test_ops, + .shared = false, + }, +}; + +/* Returns: UFFD_TEST_* */ +typedef void (*uffd_test_fn)(void); + +typedef struct { + const char *name; + uffd_test_fn uffd_fn; + unsigned int mem_targets; + uint64_t uffd_feature_required; +} uffd_test_case_t; + static void uffd_test_report(void) { printf("Userfaults unit tests: pass=%u, skip=%u, fail=%u (total=%u)\n", @@ -105,9 +165,50 @@ static int test_uffd_api(bool use_dev) return 1; } +/* + * This function initializes the global variables. TODO: remove global + * vars and then remove this. + */ +static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type) +{ + map_shared = mem_type->shared; + uffd_test_ops = mem_type->mem_ops; + + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) + page_size = default_huge_page_size(); + else + page_size = psize(); + + nr_pages = UFFD_TEST_MEM_SIZE / page_size; + /* TODO: remove this global var.. it's so ugly */ + nr_cpus = 1; + + return uffd_test_ctx_init(test->uffd_feature_required); +} + +static bool uffd_feature_supported(uffd_test_case_t *test) +{ + uint64_t features; + + if (uffd_get_features(&features)) + return false; + + return (features & test->uffd_feature_required) == + test->uffd_feature_required; +} + +uffd_test_case_t uffd_tests[] = { +}; + int main(int argc, char *argv[]) { + int n_tests = sizeof(uffd_tests) / sizeof(uffd_test_case_t); + int n_mems = sizeof(mem_types) / sizeof(mem_type_t); + uffd_test_case_t *test; + mem_type_t *mem_type; + char test_name[128]; int has_uffd; + int i, j; has_uffd = test_uffd_api(false); has_uffd |= test_uffd_api(true); @@ -116,6 +217,29 @@ int main(int argc, char *argv[]) printf("Userfaultfd not supported or unprivileged, skip all tests\n"); exit(KSFT_SKIP); } + + for (i = 0; i < n_tests; i++) { + test = &uffd_tests[i]; + for (j = 0; j < n_mems; j++) { + mem_type = &mem_types[j]; + if (!(test->mem_targets & mem_type->mem_flag)) + continue; + snprintf(test_name, sizeof(test_name), + "%s on %s", test->name, mem_type->name); + + uffd_test_start(test_name); + if (!uffd_feature_supported(test)) { + uffd_test_skip("feature missing"); + continue; + } + if (uffd_setup_environment(test, mem_type)) { + uffd_test_skip("environment setup failed"); + continue; + } + test->uffd_fn(); + } + } + uffd_test_report(); return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 5ee6c4688a7c..1bc0ceb01adb 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -254,3 +254,40 @@ int uffd_open_sys(unsigned int flags) return -1; #endif } + +int uffd_open(unsigned int flags) +{ + int uffd = uffd_open_sys(flags); + + if (uffd < 0) + uffd = uffd_open_dev(flags); + + return uffd; +} + +int uffd_get_features(uint64_t *features) +{ + struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; + /* + * This should by default work in most kernels; the feature list + * will be the same no matter what we pass in here. + */ + int fd = uffd_open(UFFD_USER_MODE_ONLY); + + if (fd < 0) + /* Maybe the kernel is older than user-only mode? */ + fd = uffd_open(0); + + if (fd < 0) + return fd; + + if (ioctl(fd, UFFDIO_API, &uffdio_api)) { + close(fd); + return -errno; + } + + *features = uffdio_api.features; + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 481354141533..634eb2f41145 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -50,6 +50,8 @@ int uffd_register(int uffd, void *addr, uint64_t len, int uffd_unregister(int uffd, void *addr, uint64_t len); int uffd_open_dev(unsigned int flags); int uffd_open_sys(unsigned int flags); +int uffd_open(unsigned int flags); +int uffd_get_features(uint64_t *features); /* * On ppc64 this will only work with radix 2M hugepage size -- GitLab From 8bda424fca0a0cc056c49a2500df03590648d029 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:52 -0400 Subject: [PATCH 3319/5631] selftests/mm: move uffd pagemap test to unit test Move it over and make it split into two tests, one for pagemap and one for the new WP_UNPOPULATED (to be a separate one). The thp pagemap test wasn't really working (with MADV_HUGEPAGE). Let's just drop it (since it never really worked anyway..) and leave that for later. Link: https://lkml.kernel.org/r/20230412164352.328733-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Mike Rapoport (IBM) Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-stress.c | 166 ------------------- tools/testing/selftests/mm/uffd-unit-tests.c | 145 ++++++++++++++++ 2 files changed, 145 insertions(+), 166 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 747d588c0d69..61d025d87bf2 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -670,157 +670,6 @@ static int userfaultfd_minor_test(void) return args.missing_faults != 0 || args.minor_faults != nr_pages; } -static int pagemap_open(void) -{ - int fd = open("/proc/self/pagemap", O_RDONLY); - - if (fd < 0) - err("open pagemap"); - - return fd; -} - -/* This macro let __LINE__ works in err() */ -#define pagemap_check_wp(value, wp) do { \ - if (!!(value & PM_UFFD_WP) != wp) \ - err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ - } while (0) - -static int pagemap_test_fork(bool present) -{ - pid_t child = fork(); - uint64_t value; - int fd, result; - - if (!child) { - /* Open the pagemap fd of the child itself */ - fd = pagemap_open(); - value = pagemap_get_entry(fd, area_dst); - /* - * After fork() uffd-wp bit should be gone as long as we're - * without UFFD_FEATURE_EVENT_FORK - */ - pagemap_check_wp(value, false); - /* Succeed */ - exit(0); - } - waitpid(child, &result, 0); - return result; -} - -static void userfaultfd_wp_unpopulated_test(int pagemap_fd) -{ - uint64_t value; - - /* Test applying pte marker to anon unpopulated */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, true); - - /* Test unprotect on anon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - /* Test zap on anon marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - if (madvise(area_dst, page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - /* Test fault in after marker removed */ - *area_dst = 1; - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); - - /* Test read-zero-page upon pte marker */ - wp_range(uffd, (uint64_t)area_dst, page_size, true); - *(volatile char *)area_dst; - /* Drop it to make pte none again */ - if (madvise(area_dst, page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); -} - -static void userfaultfd_pagemap_test(unsigned int test_pgsize) -{ - int pagemap_fd; - uint64_t value; - - /* Pagemap tests uffd-wp only */ - if (!test_uffdio_wp) - return; - - /* Not enough memory to test this page size */ - if (test_pgsize > nr_pages * page_size) - return; - - printf("testing uffd-wp with pagemap (pgsize=%u): ", test_pgsize); - /* Flush so it doesn't flush twice in parent/child later */ - fflush(stdout); - - uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); - - if (test_pgsize > page_size) { - /* This is a thp test */ - if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE)) - err("madvise(MADV_HUGEPAGE) failed"); - } else if (test_pgsize == page_size) { - /* This is normal page test; force no thp */ - if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE)) - err("madvise(MADV_NOHUGEPAGE) failed"); - } - - if (uffd_register(uffd, area_dst, nr_pages * page_size, - false, true, false)) - err("register failed"); - - pagemap_fd = pagemap_open(); - - /* Smoke test WP_UNPOPULATED first when it's still empty */ - if (test_pgsize == page_size) - userfaultfd_wp_unpopulated_test(pagemap_fd); - - /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, test_pgsize, true); - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(true)) - err("Detected stall uffd-wp bit in child"); - - /* Exclusive required or PAGEOUT won't work */ - if (!(value & PM_MMAP_EXCLUSIVE)) - err("multiple mapping detected: 0x%"PRIx64, value); - - if (madvise(area_dst, test_pgsize, MADV_PAGEOUT)) - err("madvise(MADV_PAGEOUT) failed"); - - /* Uffd-wp should persist even swapped out */ - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(false)) - err("Detected stall uffd-wp bit in child"); - - /* Unprotect; this tests swap pte modifications */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - /* Fault in the page from disk */ - *area_dst = 2; - value = pagemap_get_entry(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - close(pagemap_fd); - printf("done\n"); -} - static int userfaultfd_stress(void) { void *area; @@ -932,21 +781,6 @@ static int userfaultfd_stress(void) uffd_stats_report(args, nr_cpus); } - if (test_type == TEST_ANON) { - /* - * shmem/hugetlb won't be able to run since they have different - * behavior on fork() (file-backed memory normally drops ptes - * directly when fork), meanwhile the pagemap test will verify - * pgtable entry of fork()ed child. - */ - userfaultfd_pagemap_test(page_size); - /* - * Hard-code for x86_64 for now for 2M THP, as x86_64 is - * currently the only one that supports uffd-wp - */ - userfaultfd_pagemap_test(page_size * 512); - } - return userfaultfd_zeropage_test() || userfaultfd_sig_test() || userfaultfd_events_test() || userfaultfd_minor_test(); } diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 936b24a6f468..4690c95a9420 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -197,7 +197,152 @@ static bool uffd_feature_supported(uffd_test_case_t *test) test->uffd_feature_required; } +static int pagemap_open(void) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + + if (fd < 0) + err("open pagemap"); + + return fd; +} + +/* This macro let __LINE__ works in err() */ +#define pagemap_check_wp(value, wp) do { \ + if (!!(value & PM_UFFD_WP) != wp) \ + err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ + } while (0) + +static int pagemap_test_fork(bool present) +{ + pid_t child = fork(); + uint64_t value; + int fd, result; + + if (!child) { + /* Open the pagemap fd of the child itself */ + fd = pagemap_open(); + value = pagemap_get_entry(fd, area_dst); + /* + * After fork() uffd-wp bit should be gone as long as we're + * without UFFD_FEATURE_EVENT_FORK + */ + pagemap_check_wp(value, false); + /* Succeed */ + exit(0); + } + waitpid(child, &result, 0); + return result; +} + +static void uffd_wp_unpopulated_test(void) +{ + uint64_t value; + int pagemap_fd; + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Test applying pte marker to anon unpopulated */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + + /* Test unprotect on anon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test zap on anon marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test fault in after marker removed */ + *area_dst = 1; + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + + /* Test read-zero-page upon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + *(volatile char *)area_dst; + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + + uffd_test_pass(); +} + +static void uffd_pagemap_test(void) +{ + int pagemap_fd; + uint64_t value; + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Touch the page */ + *area_dst = 1; + wp_range(uffd, (uint64_t)area_dst, page_size, true); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + /* Make sure uffd-wp bit dropped when fork */ + if (pagemap_test_fork(true)) + err("Detected stall uffd-wp bit in child"); + + /* Exclusive required or PAGEOUT won't work */ + if (!(value & PM_MMAP_EXCLUSIVE)) + err("multiple mapping detected: 0x%"PRIx64, value); + + if (madvise(area_dst, page_size, MADV_PAGEOUT)) + err("madvise(MADV_PAGEOUT) failed"); + + /* Uffd-wp should persist even swapped out */ + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + /* Make sure uffd-wp bit dropped when fork */ + if (pagemap_test_fork(false)) + err("Detected stall uffd-wp bit in child"); + + /* Unprotect; this tests swap pte modifications */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Fault in the page from disk */ + *area_dst = 2; + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + close(pagemap_fd); + uffd_test_pass(); +} + uffd_test_case_t uffd_tests[] = { + { + .name = "pagemap", + .uffd_fn = uffd_pagemap_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP, + }, + { + .name = "wp-unpopulated", + .uffd_fn = uffd_wp_unpopulated_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = + UFFD_FEATURE_PAGEFAULT_FLAG_WP | UFFD_FEATURE_WP_UNPOPULATED, + }, }; int main(int argc, char *argv[]) -- GitLab From 62515b5f9fdabf740efd28d5746c219f1b2e75cc Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:43:57 -0400 Subject: [PATCH 3320/5631] selftests/mm: move uffd minor test to unit test This moves the minor test to the new unit test. Rewrite the content check with char* opeartions to avoid fiddling with my_bcmp(). Drop global vars test_uffdio_minor and test_collapse, just assume test them always in common code for now. OTOH make this single test into five tests: - minor test on [shmem, hugetlb] with wp=false - minor test on [shmem, hugetlb] with wp=true - minor test + collapse on shmem only One thing to mention that we used to test COLLAPSE+WP but that doesn't sound right at all. It's possible it's silently broken but unnoticed because COLLAPSE is not part of the default test suite. Make the MADV_COLLAPSE test fail-able (by skip it when failing), because it's not guaranteed to success anyway. Drop a bunch of useless code after the move, because the unit test always use aligned num of pages and has nothing to do with n_cpus. Link: https://lkml.kernel.org/r/20230412164357.328779-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Zach O'Keefe Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 25 ++-- tools/testing/selftests/mm/uffd-common.h | 4 +- tools/testing/selftests/mm/uffd-stress.c | 131 +------------------ tools/testing/selftests/mm/uffd-unit-tests.c | 120 +++++++++++++++++ 4 files changed, 135 insertions(+), 145 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index bc6c5c38d6dd..12ac84712a38 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -13,8 +13,8 @@ volatile bool test_uffdio_copy_eexist = true; unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; int uffd = -1, uffd_flags, finished, *pipefd, test_type; -bool map_shared, test_collapse, test_dev_userfaultfd; -bool test_uffdio_wp = true, test_uffdio_minor = false; +bool map_shared, test_dev_userfaultfd; +bool test_uffdio_wp = true; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; @@ -128,15 +128,14 @@ static int shmem_allocate_area(void **alloc_area, bool is_src) char *p = NULL, *p_alias = NULL; int mem_fd = uffd_mem_fd_create(bytes * 2, false); - if (test_collapse) { - p = BASE_PMD_ADDR; - if (!is_src) - /* src map + alias + interleaved hpages */ - p += 2 * (bytes + hpage_size); - p_alias = p; - p_alias += bytes; - p_alias += hpage_size; /* Prevent src/dst VMA merge */ - } + /* TODO: clean this up. Use a static addr is ugly */ + p = BASE_PMD_ADDR; + if (!is_src) + /* src map + alias + interleaved hpages */ + p += 2 * (bytes + hpage_size); + p_alias = p; + p_alias += bytes; + p_alias += hpage_size; /* Prevent src/dst VMA merge */ *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, mem_fd, offset); @@ -144,7 +143,7 @@ static int shmem_allocate_area(void **alloc_area, bool is_src) *alloc_area = NULL; return -errno; } - if (test_collapse && *alloc_area != p) + if (*alloc_area != p) err("mmap of memfd failed at %p", p); area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, @@ -154,7 +153,7 @@ static int shmem_allocate_area(void **alloc_area, bool is_src) *alloc_area = NULL; return -errno; } - if (test_collapse && area_alias != p_alias) + if (area_alias != p_alias) err("mmap of anonymous memory failed at %p", p_alias); if (is_src) diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 9479a0649d7f..4bd5915cf5b4 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -90,8 +90,8 @@ typedef struct uffd_test_ops uffd_test_ops_t; extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; extern int uffd, uffd_flags, finished, *pipefd, test_type; -extern bool map_shared, test_collapse, test_dev_userfaultfd; -extern bool test_uffdio_wp, test_uffdio_minor; +extern bool map_shared, test_dev_userfaultfd; +extern bool test_uffdio_wp; extern unsigned long long *count_verify; extern volatile bool test_uffdio_copy_eexist; diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 61d025d87bf2..f9322bbaf825 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -52,8 +52,6 @@ pthread_attr_t attr; #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) -#define factor_of_2(x) ((x) ^ ((x) & ((x) - 1))) - const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" "./userfaultfd anon 100 99999\n\n" @@ -79,8 +77,6 @@ static void usage(void) "Supported mods:\n"); fprintf(stderr, "\tsyscall - Use userfaultfd(2) (default)\n"); fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n"); - fprintf(stderr, "\tcollapse - Test MADV_COLLAPSE of UFFDIO_REGISTER_MODE_MINOR\n" - "memory\n"); fprintf(stderr, "\nExample test mod usage:\n"); fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n"); fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n"); @@ -584,92 +580,6 @@ static int userfaultfd_sig_test(void) return userfaults != 0; } -void check_memory_contents(char *p) -{ - unsigned long i; - uint8_t expected_byte; - void *expected_page; - - if (posix_memalign(&expected_page, page_size, page_size)) - err("out of memory"); - - for (i = 0; i < nr_pages; ++i) { - expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); - memset(expected_page, expected_byte, page_size); - if (my_bcmp(expected_page, p + (i * page_size), page_size)) - err("unexpected page contents after minor fault"); - } - - free(expected_page); -} - -static int userfaultfd_minor_test(void) -{ - unsigned long p; - pthread_t uffd_mon; - char c; - struct uffd_args args = { 0 }; - - if (!test_uffdio_minor) - return 0; - - printf("testing minor faults: "); - fflush(stdout); - - uffd_test_ctx_init(uffd_minor_feature()); - - if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, - false, test_uffdio_wp, true)) - err("register failure"); - - /* - * After registering with UFFD, populate the non-UFFD-registered side of - * the shared mapping. This should *not* trigger any UFFD minor faults. - */ - for (p = 0; p < nr_pages; ++p) { - memset(area_dst + (p * page_size), p % ((uint8_t)-1), - page_size); - } - - args.apply_wp = test_uffdio_wp; - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) - err("uffd_poll_thread create"); - - /* - * Read each of the pages back using the UFFD-registered mapping. We - * expect that the first time we touch a page, it will result in a minor - * fault. uffd_poll_thread will resolve the fault by bit-flipping the - * page's contents, and then issuing a CONTINUE ioctl. - */ - check_memory_contents(area_dst_alias); - - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, NULL)) - return 1; - - uffd_stats_report(&args, 1); - - if (test_collapse) { - printf("testing collapse of uffd memory into PMD-mapped THPs:"); - if (madvise(area_dst_alias, nr_pages * page_size, - MADV_COLLAPSE)) - err("madvise(MADV_COLLAPSE)"); - - uffd_test_ops->check_pmd_mapping(area_dst, - nr_pages * page_size / - read_pmd_pagesize()); - /* - * This won't cause uffd-fault - it purely just makes sure there - * was no corruption. - */ - check_memory_contents(area_dst_alias); - printf(" done.\n"); - } - - return args.missing_faults != 0 || args.minor_faults != nr_pages; -} - static int userfaultfd_stress(void) { void *area; @@ -782,7 +692,7 @@ static int userfaultfd_stress(void) } return userfaultfd_zeropage_test() || userfaultfd_sig_test() - || userfaultfd_events_test() || userfaultfd_minor_test(); + || userfaultfd_events_test(); } static void set_test_type(const char *type) @@ -797,13 +707,10 @@ static void set_test_type(const char *type) map_shared = true; test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; - /* Minor faults require shared hugetlb; only enable here. */ - test_uffdio_minor = true; } else if (!strcmp(type, "shmem")) { map_shared = true; test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; - test_uffdio_minor = true; } } @@ -821,8 +728,6 @@ static void parse_test_type_arg(const char *raw_type) test_dev_userfaultfd = true; else if (!strcmp(token, "syscall")) test_dev_userfaultfd = false; - else if (!strcmp(token, "collapse")) - test_collapse = true; else err("unrecognized test mod '%s'", token); } @@ -830,9 +735,6 @@ static void parse_test_type_arg(const char *raw_type) if (!test_type) err("failed to parse test type argument: '%s'", raw_type); - if (test_collapse && test_type != TEST_SHMEM) - err("Unsupported test: %s", raw_type); - if (test_type == TEST_HUGETLB) page_size = default_huge_page_size(); else @@ -854,8 +756,6 @@ static void parse_test_type_arg(const char *raw_type) test_uffdio_wp = test_uffdio_wp && (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); - test_uffdio_minor = test_uffdio_minor && - (features & uffd_minor_feature()); close(uffd); uffd = -1; @@ -872,7 +772,6 @@ static void sigalrm(int sig) int main(int argc, char **argv) { size_t bytes; - size_t hpage_size = read_pmd_pagesize(); if (argc < 4) usage(); @@ -884,36 +783,8 @@ int main(int argc, char **argv) parse_test_type_arg(argv[1]); bytes = atol(argv[2]) * 1024 * 1024; - if (test_collapse && bytes & (hpage_size - 1)) - err("MiB must be multiple of %lu if :collapse mod set", - hpage_size >> 20); - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - if (test_collapse) { - /* nr_cpus must divide (bytes / page_size), otherwise, - * area allocations of (nr_pages * paze_size) won't be a - * multiple of hpage_size, even if bytes is a multiple of - * hpage_size. - * - * This means that nr_cpus must divide (N * (2 << (H-P)) - * where: - * bytes = hpage_size * N - * hpage_size = 2 << H - * page_size = 2 << P - * - * And we want to chose nr_cpus to be the largest value - * satisfying this constraint, not larger than the number - * of online CPUs. Unfortunately, prime factorization of - * N and nr_cpus may be arbitrary, so have to search for it. - * Instead, just use the highest power of 2 dividing both - * nr_cpus and (bytes / page_size). - */ - int x = factor_of_2(nr_cpus); - int y = factor_of_2(bytes / page_size); - - nr_cpus = x < y ? x : y; - } nr_pages_per_cpu = bytes / page_size / nr_cpus; if (!nr_pages_per_cpu) { _err("invalid MiB"); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 4690c95a9420..cba04608bdb0 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -329,6 +329,103 @@ static void uffd_pagemap_test(void) uffd_test_pass(); } +static void check_memory_contents(char *p) +{ + unsigned long i, j; + uint8_t expected_byte; + + for (i = 0; i < nr_pages; ++i) { + expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); + for (j = 0; j < page_size; j++) { + uint8_t v = *(uint8_t *)(p + (i * page_size) + j); + if (v != expected_byte) + err("unexpected page contents"); + } + } +} + +static void uffd_minor_test_common(bool test_collapse, bool test_wp) +{ + unsigned long p; + pthread_t uffd_mon; + char c; + struct uffd_args args = { 0 }; + + /* + * NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing + * both do not make much sense. + */ + assert(!(test_collapse && test_wp)); + + if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + /* NOTE! MADV_COLLAPSE may not work with uffd-wp */ + false, test_wp, true)) + err("register failure"); + + /* + * After registering with UFFD, populate the non-UFFD-registered side of + * the shared mapping. This should *not* trigger any UFFD minor faults. + */ + for (p = 0; p < nr_pages; ++p) + memset(area_dst + (p * page_size), p % ((uint8_t)-1), + page_size); + + args.apply_wp = test_wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + /* + * Read each of the pages back using the UFFD-registered mapping. We + * expect that the first time we touch a page, it will result in a minor + * fault. uffd_poll_thread will resolve the fault by bit-flipping the + * page's contents, and then issuing a CONTINUE ioctl. + */ + check_memory_contents(area_dst_alias); + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("join() failed"); + + if (test_collapse) { + if (madvise(area_dst_alias, nr_pages * page_size, + MADV_COLLAPSE)) { + /* It's fine to fail for this one... */ + uffd_test_skip("MADV_COLLAPSE failed"); + return; + } + + uffd_test_ops->check_pmd_mapping(area_dst, + nr_pages * page_size / + read_pmd_pagesize()); + /* + * This won't cause uffd-fault - it purely just makes sure there + * was no corruption. + */ + check_memory_contents(area_dst_alias); + } + + if (args.missing_faults != 0 || args.minor_faults != nr_pages) + uffd_test_fail("stats check error"); + else + uffd_test_pass(); +} + +void uffd_minor_test(void) +{ + uffd_minor_test_common(false, false); +} + +void uffd_minor_wp_test(void) +{ + uffd_minor_test_common(false, true); +} + +void uffd_minor_collapse_test(void) +{ + uffd_minor_test_common(true, false); +} + uffd_test_case_t uffd_tests[] = { { .name = "pagemap", @@ -343,6 +440,29 @@ uffd_test_case_t uffd_tests[] = { .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | UFFD_FEATURE_WP_UNPOPULATED, }, + { + .name = "minor", + .uffd_fn = uffd_minor_test, + .mem_targets = MEM_SHMEM | MEM_HUGETLB, + .uffd_feature_required = + UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM, + }, + { + .name = "minor-wp", + .uffd_fn = uffd_minor_wp_test, + .mem_targets = MEM_SHMEM | MEM_HUGETLB, + .uffd_feature_required = + UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM | + UFFD_FEATURE_PAGEFAULT_FLAG_WP, + }, + { + .name = "minor-collapse", + .uffd_fn = uffd_minor_collapse_test, + /* MADV_COLLAPSE only works with shmem */ + .mem_targets = MEM_SHMEM, + /* We can't test MADV_COLLAPSE, so try our luck */ + .uffd_feature_required = UFFD_FEATURE_MINOR_SHMEM, + }, }; int main(int argc, char *argv[]) -- GitLab From 73c1ea939b658962345e81e8bcff1439ede25eff Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:44:00 -0400 Subject: [PATCH 3321/5631] selftests/mm: move uffd sig/events tests into uffd unit tests Move the two tests into the unit test, and convert it into 20 standalone tests: - events test on all 5 mem types, with wp on/off - signal test on all 5 mem types, with wp on/off Testing sigbus on anon... done Testing sigbus on shmem... done Testing sigbus on shmem-private... done Testing sigbus on hugetlb... done Testing sigbus on hugetlb-private... done Testing sigbus-wp on anon... done Testing sigbus-wp on shmem... done Testing sigbus-wp on shmem-private... done Testing sigbus-wp on hugetlb... done Testing sigbus-wp on hugetlb-private... done Testing events on anon... done Testing events on shmem... done Testing events on shmem-private... done Testing events on hugetlb... done Testing events on hugetlb-private... done Testing events-wp on anon... done Testing events-wp on shmem... done Testing events-wp on shmem-private... done Testing events-wp on hugetlb... done Testing events-wp on hugetlb-private... done It'll also remove a lot of global references along the way, e.g. test_uffdio_wp will be replaced with the wp value passed over. Link: https://lkml.kernel.org/r/20230412164400.328798-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-stress.c | 227 +--------------- tools/testing/selftests/mm/uffd-unit-tests.c | 264 +++++++++++++++++++ 2 files changed, 265 insertions(+), 226 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index f9322bbaf825..ce51180238d8 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -273,133 +273,6 @@ static int stress(struct uffd_args *args) return 0; } -sigjmp_buf jbuf, *sigbuf; - -static void sighndl(int sig, siginfo_t *siginfo, void *ptr) -{ - if (sig == SIGBUS) { - if (sigbuf) - siglongjmp(*sigbuf, 1); - abort(); - } -} - -/* - * For non-cooperative userfaultfd test we fork() a process that will - * generate pagefaults, will mremap the area monitored by the - * userfaultfd and at last this process will release the monitored - * area. - * For the anonymous and shared memory the area is divided into two - * parts, the first part is accessed before mremap, and the second - * part is accessed after mremap. Since hugetlbfs does not support - * mremap, the entire monitored area is accessed in a single pass for - * HUGETLB_TEST. - * The release of the pages currently generates event for shmem and - * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked - * for hugetlb. - * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register - * monitored area, generate pagefaults and test that signal is delivered. - * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2 - * test robustness use case - we release monitored area, fork a process - * that will generate pagefaults and verify signal is generated. - * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal - * feature. Using monitor thread, verify no userfault events are generated. - */ -static int faulting_process(int signal_test, bool wp) -{ - unsigned long nr; - unsigned long long count; - unsigned long split_nr_pages; - unsigned long lastnr; - struct sigaction act; - volatile unsigned long signalled = 0; - - split_nr_pages = (nr_pages + 1) / 2; - - if (signal_test) { - sigbuf = &jbuf; - memset(&act, 0, sizeof(act)); - act.sa_sigaction = sighndl; - act.sa_flags = SA_SIGINFO; - if (sigaction(SIGBUS, &act, 0)) - err("sigaction"); - lastnr = (unsigned long)-1; - } - - for (nr = 0; nr < split_nr_pages; nr++) { - volatile int steps = 1; - unsigned long offset = nr * page_size; - - if (signal_test) { - if (sigsetjmp(*sigbuf, 1) != 0) { - if (steps == 1 && nr == lastnr) - err("Signal repeated"); - - lastnr = nr; - if (signal_test == 1) { - if (steps == 1) { - /* This is a MISSING request */ - steps++; - if (copy_page(uffd, offset, wp)) - signalled++; - } else { - /* This is a WP request */ - assert(steps == 2); - wp_range(uffd, - (__u64)area_dst + - offset, - page_size, false); - } - } else { - signalled++; - continue; - } - } - } - - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) - err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); - /* - * Trigger write protection if there is by writing - * the same value back. - */ - *area_count(area_dst, nr) = count; - } - - if (signal_test) - return signalled != split_nr_pages; - - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, - MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) - err("mremap"); - /* Reset area_src since we just clobbered it */ - area_src = NULL; - - for (; nr < nr_pages; nr++) { - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { - err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); - } - /* - * Trigger write protection if there is by writing - * the same value back. - */ - *area_count(area_dst, nr) = count; - } - - uffd_test_ops->release_pages(area_dst); - - for (nr = 0; nr < nr_pages; nr++) - if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) - err("nr %lu is not zero", nr); - - return 0; -} - static void retry_uffdio_zeropage(int ufd, struct uffdio_zeropage *uffdio_zeropage, unsigned long offset) @@ -483,103 +356,6 @@ static int userfaultfd_zeropage_test(void) return 0; } -static int userfaultfd_events_test(void) -{ - pthread_t uffd_mon; - int err, features; - pid_t pid; - char c; - struct uffd_args args = { 0 }; - - printf("testing events (fork, remap, remove): "); - fflush(stdout); - - features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP | - UFFD_FEATURE_EVENT_REMOVE; - uffd_test_ctx_init(features); - - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - - if (uffd_register(uffd, area_dst, nr_pages * page_size, - true, test_uffdio_wp, false)) - err("register failure"); - - args.apply_wp = test_uffdio_wp; - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) - err("uffd_poll_thread create"); - - pid = fork(); - if (pid < 0) - err("fork"); - - if (!pid) - exit(faulting_process(0, test_uffdio_wp)); - - waitpid(pid, &err, 0); - if (err) - err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, NULL)) - return 1; - - uffd_stats_report(&args, 1); - - return args.missing_faults != nr_pages; -} - -static int userfaultfd_sig_test(void) -{ - unsigned long userfaults; - pthread_t uffd_mon; - int err, features; - pid_t pid; - char c; - struct uffd_args args = { 0 }; - - printf("testing signal delivery: "); - fflush(stdout); - - features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; - uffd_test_ctx_init(features); - - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - - if (uffd_register(uffd, area_dst, nr_pages * page_size, - true, test_uffdio_wp, false)) - err("register failure"); - - if (faulting_process(1, test_uffdio_wp)) - err("faulting process failed"); - - uffd_test_ops->release_pages(area_dst); - - args.apply_wp = test_uffdio_wp; - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &args)) - err("uffd_poll_thread create"); - - pid = fork(); - if (pid < 0) - err("fork"); - - if (!pid) - exit(faulting_process(2, test_uffdio_wp)); - - waitpid(pid, &err, 0); - if (err) - err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, (void **)&userfaults)) - return 1; - - printf("done.\n"); - if (userfaults) - err("Signal test failed, userfaults: %ld", userfaults); - - return userfaults != 0; -} - static int userfaultfd_stress(void) { void *area; @@ -691,8 +467,7 @@ static int userfaultfd_stress(void) uffd_stats_report(args, nr_cpus); } - return userfaultfd_zeropage_test() || userfaultfd_sig_test() - || userfaultfd_events_test(); + return userfaultfd_zeropage_test(); } static void set_test_type(const char *type) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index cba04608bdb0..94549696f4b2 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -18,6 +18,9 @@ #define MEM_HUGETLB BIT_ULL(3) #define MEM_HUGETLB_PRIVATE BIT_ULL(4) +#define MEM_ALL (MEM_ANON | MEM_SHMEM | MEM_SHMEM_PRIVATE | \ + MEM_HUGETLB | MEM_HUGETLB_PRIVATE) + struct mem_type { const char *name; unsigned int mem_flag; @@ -426,6 +429,237 @@ void uffd_minor_collapse_test(void) uffd_minor_test_common(true, false); } +static sigjmp_buf jbuf, *sigbuf; + +static void sighndl(int sig, siginfo_t *siginfo, void *ptr) +{ + if (sig == SIGBUS) { + if (sigbuf) + siglongjmp(*sigbuf, 1); + abort(); + } +} + +/* + * For non-cooperative userfaultfd test we fork() a process that will + * generate pagefaults, will mremap the area monitored by the + * userfaultfd and at last this process will release the monitored + * area. + * For the anonymous and shared memory the area is divided into two + * parts, the first part is accessed before mremap, and the second + * part is accessed after mremap. Since hugetlbfs does not support + * mremap, the entire monitored area is accessed in a single pass for + * HUGETLB_TEST. + * The release of the pages currently generates event for shmem and + * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked + * for hugetlb. + * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register + * monitored area, generate pagefaults and test that signal is delivered. + * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2 + * test robustness use case - we release monitored area, fork a process + * that will generate pagefaults and verify signal is generated. + * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal + * feature. Using monitor thread, verify no userfault events are generated. + */ +static int faulting_process(int signal_test, bool wp) +{ + unsigned long nr, i; + unsigned long long count; + unsigned long split_nr_pages; + unsigned long lastnr; + struct sigaction act; + volatile unsigned long signalled = 0; + + split_nr_pages = (nr_pages + 1) / 2; + + if (signal_test) { + sigbuf = &jbuf; + memset(&act, 0, sizeof(act)); + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) + err("sigaction"); + lastnr = (unsigned long)-1; + } + + for (nr = 0; nr < split_nr_pages; nr++) { + volatile int steps = 1; + unsigned long offset = nr * page_size; + + if (signal_test) { + if (sigsetjmp(*sigbuf, 1) != 0) { + if (steps == 1 && nr == lastnr) + err("Signal repeated"); + + lastnr = nr; + if (signal_test == 1) { + if (steps == 1) { + /* This is a MISSING request */ + steps++; + if (copy_page(uffd, offset, wp)) + signalled++; + } else { + /* This is a WP request */ + assert(steps == 2); + wp_range(uffd, + (__u64)area_dst + + offset, + page_size, false); + } + } else { + signalled++; + continue; + } + } + } + + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); + /* + * Trigger write protection if there is by writing + * the same value back. + */ + *area_count(area_dst, nr) = count; + } + + if (signal_test) + return signalled != split_nr_pages; + + area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, area_src); + if (area_dst == MAP_FAILED) + err("mremap"); + /* Reset area_src since we just clobbered it */ + area_src = NULL; + + for (; nr < nr_pages; nr++) { + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) { + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); + } + /* + * Trigger write protection if there is by writing + * the same value back. + */ + *area_count(area_dst, nr) = count; + } + + uffd_test_ops->release_pages(area_dst); + + for (nr = 0; nr < nr_pages; nr++) + for (i = 0; i < page_size; i++) + if (*(area_dst + nr * page_size + i) != 0) + err("page %lu offset %lu is not zero", nr, i); + + return 0; +} + +static void uffd_sigbus_test_common(bool wp) +{ + unsigned long userfaults; + pthread_t uffd_mon; + pid_t pid; + int err; + char c; + struct uffd_args args = { 0 }; + + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, wp, false)) + err("register failure"); + + if (faulting_process(1, wp)) + err("faulting process failed"); + + uffd_test_ops->release_pages(area_dst); + + args.apply_wp = wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + pid = fork(); + if (pid < 0) + err("fork"); + + if (!pid) + exit(faulting_process(2, wp)); + + waitpid(pid, &err, 0); + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, (void **)&userfaults)) + err("pthread_join()"); + + if (userfaults) + uffd_test_fail("Signal test failed, userfaults: %ld", userfaults); + else + uffd_test_pass(); +} + +static void uffd_sigbus_test(void) +{ + uffd_sigbus_test_common(false); +} + +static void uffd_sigbus_wp_test(void) +{ + uffd_sigbus_test_common(true); +} + +static void uffd_events_test_common(bool wp) +{ + pthread_t uffd_mon; + pid_t pid; + int err; + char c; + struct uffd_args args = { 0 }; + + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, wp, false)) + err("register failure"); + + args.apply_wp = wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + pid = fork(); + if (pid < 0) + err("fork"); + + if (!pid) + exit(faulting_process(0, wp)); + + waitpid(pid, &err, 0); + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("pthread_join()"); + + if (args.missing_faults != nr_pages) + uffd_test_fail("Fault counts wrong"); + else + uffd_test_pass(); +} + +static void uffd_events_test(void) +{ + uffd_events_test_common(false); +} + +static void uffd_events_wp_test(void) +{ + uffd_events_test_common(true); +} + uffd_test_case_t uffd_tests[] = { { .name = "pagemap", @@ -463,6 +697,36 @@ uffd_test_case_t uffd_tests[] = { /* We can't test MADV_COLLAPSE, so try our luck */ .uffd_feature_required = UFFD_FEATURE_MINOR_SHMEM, }, + { + .name = "sigbus", + .uffd_fn = uffd_sigbus_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_SIGBUS | + UFFD_FEATURE_EVENT_FORK, + }, + { + .name = "sigbus-wp", + .uffd_fn = uffd_sigbus_wp_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_SIGBUS | + UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP, + }, + { + .name = "events", + .uffd_fn = uffd_events_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_EVENT_FORK | + UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE, + }, + { + .name = "events-wp", + .uffd_fn = uffd_events_wp_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_EVENT_FORK | + UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE | + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, }; int main(int argc, char *argv[]) -- GitLab From c3315502c92406ec5bf36ba687f9651b43f838f6 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:44:04 -0400 Subject: [PATCH 3322/5631] selftests/mm: move zeropage test into uffd unit tests Simplifies it a bit along the way, e.g., drop the never used offset field (which was always the 1st page so offset=0). Introduce uffd_register_with_ioctls() out of uffd_register() to detect uffdio_register.ioctls got returned. Check that automatically when testing UFFDIO_ZEROPAGE on different types of memory (and kernel). Link: https://lkml.kernel.org/r/20230412164404.328815-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-stress.c | 94 +------------------- tools/testing/selftests/mm/uffd-unit-tests.c | 93 +++++++++++++++++++ tools/testing/selftests/mm/vm_util.c | 14 ++- tools/testing/selftests/mm/vm_util.h | 2 + 4 files changed, 108 insertions(+), 95 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index ce51180238d8..d78f88850011 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -109,15 +109,6 @@ static inline uint64_t uffd_minor_feature(void) return 0; } -static int my_bcmp(char *str1, char *str2, size_t n) -{ - unsigned long i; - for (i = 0; i < n; i++) - if (str1[i] != str2[i]) - return 1; - return 0; -} - static void *locking_thread(void *arg) { unsigned long cpu = (unsigned long) arg; @@ -273,89 +264,6 @@ static int stress(struct uffd_args *args) return 0; } -static void retry_uffdio_zeropage(int ufd, - struct uffdio_zeropage *uffdio_zeropage, - unsigned long offset) -{ - uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, - uffdio_zeropage->range.len, - offset); - if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { - if (uffdio_zeropage->zeropage != -EEXIST) - err("UFFDIO_ZEROPAGE error: %"PRId64, - (int64_t)uffdio_zeropage->zeropage); - } else { - err("UFFDIO_ZEROPAGE error: %"PRId64, - (int64_t)uffdio_zeropage->zeropage); - } -} - -static int __uffdio_zeropage(int ufd, unsigned long offset) -{ - struct uffdio_zeropage uffdio_zeropage; - int ret; - bool has_zeropage = !(test_type == TEST_HUGETLB); - __s64 res; - - if (offset >= nr_pages * page_size) - err("unexpected offset %lu", offset); - uffdio_zeropage.range.start = (unsigned long) area_dst + offset; - uffdio_zeropage.range.len = page_size; - uffdio_zeropage.mode = 0; - ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); - res = uffdio_zeropage.zeropage; - if (ret) { - /* real retval in ufdio_zeropage.zeropage */ - if (has_zeropage) - err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res); - else if (res != -EINVAL) - err("UFFDIO_ZEROPAGE not -EINVAL"); - } else if (has_zeropage) { - if (res != page_size) { - err("UFFDIO_ZEROPAGE unexpected size"); - } else { - retry_uffdio_zeropage(ufd, &uffdio_zeropage, - offset); - return 1; - } - } else - err("UFFDIO_ZEROPAGE succeeded"); - - return 0; -} - -static int uffdio_zeropage(int ufd, unsigned long offset) -{ - return __uffdio_zeropage(ufd, offset); -} - -/* exercise UFFDIO_ZEROPAGE */ -static int userfaultfd_zeropage_test(void) -{ - printf("testing UFFDIO_ZEROPAGE: "); - fflush(stdout); - - uffd_test_ctx_init(0); - - if (uffd_register(uffd, area_dst, nr_pages * page_size, - true, test_uffdio_wp, false)) - err("register failure"); - - if (area_dst_alias) { - /* Needed this to test zeropage-retry on shared memory */ - if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, - true, test_uffdio_wp, false)) - err("register failure"); - } - - if (uffdio_zeropage(uffd, 0)) - if (my_bcmp(area_dst, zeropage, page_size)) - err("zeropage is not zero"); - - printf("done.\n"); - return 0; -} - static int userfaultfd_stress(void) { void *area; @@ -467,7 +375,7 @@ static int userfaultfd_stress(void) uffd_stats_report(args, nr_cpus); } - return userfaultfd_zeropage_test(); + return 0; } static void set_test_type(const char *type) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 94549696f4b2..160bd8ccda55 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -660,7 +660,100 @@ static void uffd_events_wp_test(void) uffd_events_test_common(true); } +static void retry_uffdio_zeropage(int ufd, + struct uffdio_zeropage *uffdio_zeropage) +{ + uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffdio_zeropage->range.len, + 0); + if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (uffdio_zeropage->zeropage != -EEXIST) + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); + } else { + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); + } +} + +static bool do_uffdio_zeropage(int ufd, bool has_zeropage) +{ + struct uffdio_zeropage uffdio_zeropage = { 0 }; + int ret; + __s64 res; + + uffdio_zeropage.range.start = (unsigned long) area_dst; + uffdio_zeropage.range.len = page_size; + uffdio_zeropage.mode = 0; + ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + res = uffdio_zeropage.zeropage; + if (ret) { + /* real retval in ufdio_zeropage.zeropage */ + if (has_zeropage) + err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res); + else if (res != -EINVAL) + err("UFFDIO_ZEROPAGE not -EINVAL"); + } else if (has_zeropage) { + if (res != page_size) + err("UFFDIO_ZEROPAGE unexpected size"); + else + retry_uffdio_zeropage(ufd, &uffdio_zeropage); + return true; + } else + err("UFFDIO_ZEROPAGE succeeded"); + + return false; +} + +/* + * Registers a range with MISSING mode only for zeropage test. Return true + * if UFFDIO_ZEROPAGE supported, false otherwise. Can't use uffd_register() + * because we want to detect .ioctls along the way. + */ +static bool +uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) +{ + uint64_t ioctls = 0; + + if (uffd_register_with_ioctls(uffd, addr, len, true, + false, false, &ioctls)) + err("zeropage register fail"); + + return ioctls & (1 << _UFFDIO_ZEROPAGE); +} + +/* exercise UFFDIO_ZEROPAGE */ +static void uffd_zeropage_test(void) +{ + bool has_zeropage; + int i; + + has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size); + if (area_dst_alias) + /* Ignore the retval; we already have it */ + uffd_register_detect_zeropage(uffd, area_dst_alias, page_size); + + if (do_uffdio_zeropage(uffd, has_zeropage)) + for (i = 0; i < page_size; i++) + if (area_dst[i] != 0) + err("data non-zero at offset %d\n", i); + + if (uffd_unregister(uffd, area_dst, page_size)) + err("unregister"); + + if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size)) + err("unregister"); + + uffd_test_pass(); +} + uffd_test_case_t uffd_tests[] = { + { + .name = "zeropage", + .uffd_fn = uffd_zeropage_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = 0, + }, { .name = "pagemap", .uffd_fn = uffd_pagemap_test, diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 1bc0ceb01adb..9b06a5034808 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -198,8 +198,9 @@ unsigned long default_huge_page_size(void) return hps; } -int uffd_register(int uffd, void *addr, uint64_t len, - bool miss, bool wp, bool minor) +/* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ +int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor, uint64_t *ioctls) { struct uffdio_register uffdio_register = { 0 }; uint64_t mode = 0; @@ -218,10 +219,19 @@ int uffd_register(int uffd, void *addr, uint64_t len, if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) ret = -errno; + else if (ioctls) + *ioctls = uffdio_register.ioctls; return ret; } +int uffd_register(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor) +{ + return uffd_register_with_ioctls(uffd, addr, len, + miss, wp, minor, NULL); +} + int uffd_unregister(int uffd, void *addr, uint64_t len) { struct uffdio_range range = { .start = (uintptr_t)addr, .len = len }; diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 634eb2f41145..b950bd16083a 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -52,6 +52,8 @@ int uffd_open_dev(unsigned int flags); int uffd_open_sys(unsigned int flags); int uffd_open(unsigned int flags); int uffd_get_features(uint64_t *features); +int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor, uint64_t *ioctls); /* * On ppc64 this will only work with radix 2M hugepage size -- GitLab From 4df9cefa9419718c32259c105ac8fbbc680410f7 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:45:17 -0400 Subject: [PATCH 3323/5631] selftests/mm: workaround no way to detect uffd-minor + wp Userfaultfd minor+wp mode was very recently added. The test will fail on the old kernels at ioctl(UFFDIO_CONTINUE) which is misterious. Unfortunately there's no feature bit to detect for this support. Add a hack to leverage WP_UNPOPULATED to detect whether that feature existed, since WP_UNPOPULATED was merged right after minor+wp. Link: https://lkml.kernel.org/r/20230412164517.329152-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 160bd8ccda55..a33d6c928eeb 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -780,7 +780,13 @@ uffd_test_case_t uffd_tests[] = { .mem_targets = MEM_SHMEM | MEM_HUGETLB, .uffd_feature_required = UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM | - UFFD_FEATURE_PAGEFAULT_FLAG_WP, + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + /* + * HACK: here we leveraged WP_UNPOPULATED to detect whether + * minor mode supports wr-protect. There's no feature flag + * for it so this is the best we can test against. + */ + UFFD_FEATURE_WP_UNPOPULATED, }, { .name = "minor-collapse", -- GitLab From f9da24263db43da12f1e105cb8ac5e02c66f12d0 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:45:20 -0400 Subject: [PATCH 3324/5631] selftests/mm: allow uffd test to skip properly with no privilege Allow skip a unit test properly due to no privilege (e.g. sigbus and events tests). [colin.i.king@gmail.com: fix spelling mistake "priviledge" -> "privilege"] Link: https://lkml.kernel.org/r/20230414081506.1678998-1-colin.i.king@gmail.com Link: https://lkml.kernel.org/r/20230412164520.329163-1-peterx@redhat.com Signed-off-by: Peter Xu Signed-off-by: Colin Ian King Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-common.c | 27 ++++++++++++-------- tools/testing/selftests/mm/uffd-common.h | 4 +-- tools/testing/selftests/mm/uffd-stress.c | 6 +++-- tools/testing/selftests/mm/uffd-unit-tests.c | 10 +++++--- 4 files changed, 29 insertions(+), 18 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 12ac84712a38..3e98e129f8bd 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -232,7 +232,7 @@ void uffd_stats_report(struct uffd_args *args, int n_cpus) printf("\n"); } -void userfaultfd_open(uint64_t *features) +int userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; @@ -241,18 +241,19 @@ void userfaultfd_open(uint64_t *features) else uffd = uffd_open_sys(UFFD_FLAGS); if (uffd < 0) - err("uffd open failed (dev=%d)", test_dev_userfaultfd); + return -1; uffd_flags = fcntl(uffd, F_GETFD, NULL); uffdio_api.api = UFFD_API; uffdio_api.features = *features; if (ioctl(uffd, UFFDIO_API, &uffdio_api)) - err("UFFDIO_API failed.\nPlease make sure to " - "run with either root or ptrace capability."); + /* Probably lack of CAP_PTRACE? */ + return -1; if (uffdio_api.api != UFFD_API) err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); *features = uffdio_api.features; + return 0; } static inline void munmap_area(void **area) @@ -295,7 +296,7 @@ static void uffd_test_ctx_clear(void) munmap_area((void **)&area_remap); } -int uffd_test_ctx_init(uint64_t features) +int uffd_test_ctx_init(uint64_t features, const char **errmsg) { unsigned long nr, cpu; int ret; @@ -303,13 +304,19 @@ int uffd_test_ctx_init(uint64_t features) uffd_test_ctx_clear(); ret = uffd_test_ops->allocate_area((void **)&area_src, true); - if (ret) - return ret; - ret = uffd_test_ops->allocate_area((void **)&area_dst, false); - if (ret) + ret |= uffd_test_ops->allocate_area((void **)&area_dst, false); + if (ret) { + if (errmsg) + *errmsg = "memory allocation failed"; return ret; + } - userfaultfd_open(&features); + ret = userfaultfd_open(&features); + if (ret) { + if (errmsg) + *errmsg = "possible lack of priviledge"; + return ret; + } count_verify = malloc(nr_pages * sizeof(unsigned long long)); if (!count_verify) diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 4bd5915cf5b4..32e590ce9442 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -101,8 +101,8 @@ extern uffd_test_ops_t hugetlb_uffd_test_ops; extern uffd_test_ops_t *uffd_test_ops; void uffd_stats_report(struct uffd_args *args, int n_cpus); -int uffd_test_ctx_init(uint64_t features); -void userfaultfd_open(uint64_t *features); +int uffd_test_ctx_init(uint64_t features, const char **errmsg); +int userfaultfd_open(uint64_t *features); int uffd_read_msg(int ufd, struct uffd_msg *msg); void wp_range(int ufd, __u64 start, __u64 len, bool wp); void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index d78f88850011..c0e804f05002 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -271,7 +271,8 @@ static int userfaultfd_stress(void) struct uffd_args args[nr_cpus]; uint64_t mem_size = nr_pages * page_size; - uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED); + if (uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED, NULL)) + err("context init failed"); if (posix_memalign(&area, page_size, page_size)) err("out of memory"); @@ -435,7 +436,8 @@ static void parse_test_type_arg(const char *raw_type) * feature. */ - userfaultfd_open(&features); + if (userfaultfd_open(&features)) + err("Userfaultfd open failed"); test_uffdio_wp = test_uffdio_wp && (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index a33d6c928eeb..b0acf558e8cb 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -172,7 +172,8 @@ static int test_uffd_api(bool use_dev) * This function initializes the global variables. TODO: remove global * vars and then remove this. */ -static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type) +static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type, + const char **errmsg) { map_shared = mem_type->shared; uffd_test_ops = mem_type->mem_ops; @@ -186,7 +187,7 @@ static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type) /* TODO: remove this global var.. it's so ugly */ nr_cpus = 1; - return uffd_test_ctx_init(test->uffd_feature_required); + return uffd_test_ctx_init(test->uffd_feature_required, errmsg); } static bool uffd_feature_supported(uffd_test_case_t *test) @@ -835,6 +836,7 @@ int main(int argc, char *argv[]) uffd_test_case_t *test; mem_type_t *mem_type; char test_name[128]; + const char *errmsg; int has_uffd; int i, j; @@ -860,8 +862,8 @@ int main(int argc, char *argv[]) uffd_test_skip("feature missing"); continue; } - if (uffd_setup_environment(test, mem_type)) { - uffd_test_skip("environment setup failed"); + if (uffd_setup_environment(test, mem_type, &errmsg)) { + uffd_test_skip(errmsg); continue; } test->uffd_fn(); -- GitLab From 111fd29b2aed34f1841015df2196a9b489da06b0 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:45:25 -0400 Subject: [PATCH 3325/5631] selftests/mm: drop sys/dev test in uffd-stress test With the new uffd unit test covering the /dev/userfaultfd path and syscall path of uffd initializations, we can safely drop the devnode test in the old stress test. One thing is to avoid duplication of running the stress test twice which is an overkill to only test the /dev/ interface in run_vmtests.sh. The other benefit is now all uffd tests (that uses userfaultfd_open) can run automatically as long as any type of interface is enabled (either syscall or dev), so it's more likely to succeed rather than fail due to unprivilege. With this patch lands, we can drop all the "mem_type:XXX" handlings too. Link: https://lkml.kernel.org/r/20230412164525.329176-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 15 +++++-------- tools/testing/selftests/mm/uffd-common.c | 7 ++---- tools/testing/selftests/mm/uffd-common.h | 2 +- tools/testing/selftests/mm/uffd-stress.c | 27 ++--------------------- 4 files changed, 11 insertions(+), 40 deletions(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index efe22dc569f0..ecc16ea6fc40 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -197,16 +197,13 @@ CATEGORY="gup_test" run_test ./gup_test -a CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 CATEGORY="userfaultfd" run_test ./uffd-unit-tests -uffd_mods=("" ":dev") uffd_stress_bin=./uffd-stress -for mod in "${uffd_mods[@]}"; do - CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon${mod} 20 16 - # Hugetlb tests require source and destination huge pages. Pass in half - # the size ($half_ufd_size_MB), which is used for *each*. - CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb_shared${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem${mod} 20 16 -done +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 +# Hugetlb tests require source and destination huge pages. Pass in half +# the size ($half_ufd_size_MB), which is used for *each*. +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb_shared "$half_ufd_size_MB" 32 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c index 3e98e129f8bd..61c6250adf93 100644 --- a/tools/testing/selftests/mm/uffd-common.c +++ b/tools/testing/selftests/mm/uffd-common.c @@ -13,7 +13,7 @@ volatile bool test_uffdio_copy_eexist = true; unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; int uffd = -1, uffd_flags, finished, *pipefd, test_type; -bool map_shared, test_dev_userfaultfd; +bool map_shared; bool test_uffdio_wp = true; unsigned long long *count_verify; uffd_test_ops_t *uffd_test_ops; @@ -236,10 +236,7 @@ int userfaultfd_open(uint64_t *features) { struct uffdio_api uffdio_api; - if (test_dev_userfaultfd) - uffd = uffd_open_dev(UFFD_FLAGS); - else - uffd = uffd_open_sys(UFFD_FLAGS); + uffd = uffd_open(UFFD_FLAGS); if (uffd < 0) return -1; uffd_flags = fcntl(uffd, F_GETFD, NULL); diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 32e590ce9442..6068f2346b86 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -90,7 +90,7 @@ typedef struct uffd_test_ops uffd_test_ops_t; extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; extern int uffd, uffd_flags, finished, *pipefd, test_type; -extern bool map_shared, test_dev_userfaultfd; +extern bool map_shared; extern bool test_uffdio_wp; extern unsigned long long *count_verify; extern volatile bool test_uffdio_copy_eexist; diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index c0e804f05002..4e071a7d0ff5 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -55,8 +55,6 @@ pthread_attr_t attr; const char *examples = "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" "./userfaultfd anon 100 99999\n\n" - "# Run the same anonymous memory test, but using /dev/userfaultfd:\n" - "./userfaultfd anon:dev 100 99999\n\n" "# Run share memory test on 1GiB region with 99 bounces:\n" "./userfaultfd shmem 1000 99\n\n" "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" @@ -69,18 +67,9 @@ const char *examples = static void usage(void) { - fprintf(stderr, "\nUsage: ./userfaultfd " - "[hugetlbfs_file]\n\n"); + fprintf(stderr, "\nUsage: ./userfaultfd \n\n"); fprintf(stderr, "Supported : anon, hugetlb, " "hugetlb_shared, shmem\n\n"); - fprintf(stderr, "'Test mods' can be joined to the test type string with a ':'. " - "Supported mods:\n"); - fprintf(stderr, "\tsyscall - Use userfaultfd(2) (default)\n"); - fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n"); - fprintf(stderr, "\nExample test mod usage:\n"); - fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n"); - fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n"); - fprintf(stderr, "Examples:\n\n"); fprintf(stderr, "%s", examples); exit(1); @@ -400,21 +389,9 @@ static void set_test_type(const char *type) static void parse_test_type_arg(const char *raw_type) { - char *buf = strdup(raw_type); uint64_t features = UFFD_API_FEATURES; - while (buf) { - const char *token = strsep(&buf, ":"); - - if (!test_type) - set_test_type(token); - else if (!strcmp(token, "dev")) - test_dev_userfaultfd = true; - else if (!strcmp(token, "syscall")) - test_dev_userfaultfd = false; - else - err("unrecognized test mod '%s'", token); - } + set_test_type(raw_type); if (!test_type) err("failed to parse test type argument: '%s'", raw_type); -- GitLab From 5aec236fdd69d39f9fa5e579d10f7a45ed11b005 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:45:46 -0400 Subject: [PATCH 3326/5631] selftests/mm: add shmem-private test to uffd-stress The userfaultfd stress test never tested private shmem, which I think was overlooked long due. Add it so it matches with uffd unit test and it'll cover all memory supported with the three memory types. Meanwhile, rename the memory types a bit. Considering shared mem is the major use case for both shmem / hugetlbfs, changing from: anon, hugetlb, hugetlb_shared, shmem To (with shmem-private added): anon, hugetlb, hugetlb-private, shmem, shmem-private Add the shmem-private to run_vmtests.sh too. Link: https://lkml.kernel.org/r/20230412164546.329355-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 3 ++- tools/testing/selftests/mm/uffd-stress.c | 11 +++++++---- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index ecc16ea6fc40..438eb49567b6 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -202,8 +202,9 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 # Hugetlb tests require source and destination huge pages. Pass in half # the size ($half_ufd_size_MB), which is used for *each*. CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 -CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb_shared "$half_ufd_size_MB" 32 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16 #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c index 4e071a7d0ff5..f1ad9eef1c3a 100644 --- a/tools/testing/selftests/mm/uffd-stress.c +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -59,8 +59,8 @@ const char *examples = "./userfaultfd shmem 1000 99\n\n" "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" "./userfaultfd hugetlb 256 50\n\n" - "# Run the same hugetlb test but using shared file:\n" - "./userfaultfd hugetlb_shared 256 50\n\n" + "# Run the same hugetlb test but using private file:\n" + "./userfaultfd hugetlb-private 256 50\n\n" "# 10MiB-~6GiB 999 bounces anonymous test, " "continue forever unless an error triggers\n" "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; @@ -69,7 +69,7 @@ static void usage(void) { fprintf(stderr, "\nUsage: ./userfaultfd \n\n"); fprintf(stderr, "Supported : anon, hugetlb, " - "hugetlb_shared, shmem\n\n"); + "hugetlb-private, shmem, shmem-private\n\n"); fprintf(stderr, "Examples:\n\n"); fprintf(stderr, "%s", examples); exit(1); @@ -376,14 +376,17 @@ static void set_test_type(const char *type) } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; - } else if (!strcmp(type, "hugetlb_shared")) { map_shared = true; + } else if (!strcmp(type, "hugetlb-private")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { map_shared = true; test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; + } else if (!strcmp(type, "shmem-private")) { + test_type = TEST_SHMEM; + uffd_test_ops = &shmem_uffd_test_ops; } } -- GitLab From 43759d44dc346273efd79e99ba5d195ed6c2bfa2 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 12 Apr 2023 12:45:48 -0400 Subject: [PATCH 3327/5631] selftests/mm: add uffdio register ioctls test This new test tests against the returned ioctls from UFFDIO_REGISTER, where put into uffdio_register.ioctls. This also tests the expected failure cases of UFFDIO_REGISTER, aka: - Register with empty mode should fail with -EINVAL - Register minor without page cache (anon) should fail with -EINVAL Link: https://lkml.kernel.org/r/20230412164548.329376-1-peterx@redhat.com Signed-off-by: Peter Xu Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Mike Kravetz Cc: Mike Rapoport (IBM) Cc: Zach O'Keefe Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 112 ++++++++++++++++--- 1 file changed, 97 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index b0acf558e8cb..d871bf732e62 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -62,8 +62,14 @@ mem_type_t mem_types[] = { }, }; +/* Arguments to be passed over to each uffd unit test */ +struct uffd_test_args { + mem_type_t *mem_type; +}; +typedef struct uffd_test_args uffd_test_args_t; + /* Returns: UFFD_TEST_* */ -typedef void (*uffd_test_fn)(void); +typedef void (*uffd_test_fn)(uffd_test_args_t *); typedef struct { const char *name; @@ -172,8 +178,9 @@ static int test_uffd_api(bool use_dev) * This function initializes the global variables. TODO: remove global * vars and then remove this. */ -static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type, - const char **errmsg) +static int +uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test, + mem_type_t *mem_type, const char **errmsg) { map_shared = mem_type->shared; uffd_test_ops = mem_type->mem_ops; @@ -187,6 +194,9 @@ static int uffd_setup_environment(uffd_test_case_t *test, mem_type_t *mem_type, /* TODO: remove this global var.. it's so ugly */ nr_cpus = 1; + /* Initialize test arguments */ + args->mem_type = mem_type; + return uffd_test_ctx_init(test->uffd_feature_required, errmsg); } @@ -239,7 +249,7 @@ static int pagemap_test_fork(bool present) return result; } -static void uffd_wp_unpopulated_test(void) +static void uffd_wp_unpopulated_test(uffd_test_args_t *args) { uint64_t value; int pagemap_fd; @@ -285,7 +295,7 @@ static void uffd_wp_unpopulated_test(void) uffd_test_pass(); } -static void uffd_pagemap_test(void) +static void uffd_pagemap_test(uffd_test_args_t *args) { int pagemap_fd; uint64_t value; @@ -415,17 +425,17 @@ static void uffd_minor_test_common(bool test_collapse, bool test_wp) uffd_test_pass(); } -void uffd_minor_test(void) +void uffd_minor_test(uffd_test_args_t *args) { uffd_minor_test_common(false, false); } -void uffd_minor_wp_test(void) +void uffd_minor_wp_test(uffd_test_args_t *args) { uffd_minor_test_common(false, true); } -void uffd_minor_collapse_test(void) +void uffd_minor_collapse_test(uffd_test_args_t *args) { uffd_minor_test_common(true, false); } @@ -603,12 +613,12 @@ static void uffd_sigbus_test_common(bool wp) uffd_test_pass(); } -static void uffd_sigbus_test(void) +static void uffd_sigbus_test(uffd_test_args_t *args) { uffd_sigbus_test_common(false); } -static void uffd_sigbus_wp_test(void) +static void uffd_sigbus_wp_test(uffd_test_args_t *args) { uffd_sigbus_test_common(true); } @@ -651,12 +661,12 @@ static void uffd_events_test_common(bool wp) uffd_test_pass(); } -static void uffd_events_test(void) +static void uffd_events_test(uffd_test_args_t *args) { uffd_events_test_common(false); } -static void uffd_events_wp_test(void) +static void uffd_events_wp_test(uffd_test_args_t *args) { uffd_events_test_common(true); } @@ -724,7 +734,7 @@ uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) } /* exercise UFFDIO_ZEROPAGE */ -static void uffd_zeropage_test(void) +static void uffd_zeropage_test(uffd_test_args_t *args) { bool has_zeropage; int i; @@ -748,7 +758,77 @@ static void uffd_zeropage_test(void) uffd_test_pass(); } +/* + * Test the returned uffdio_register.ioctls with different register modes. + * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. + */ +static void +do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) +{ + uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE); + mem_type_t *mem_type = args->mem_type; + int ret; + + ret = uffd_register_with_ioctls(uffd, area_dst, page_size, + miss, wp, minor, &ioctls); + + /* + * Handle special cases of UFFDIO_REGISTER here where it should + * just fail with -EINVAL first.. + * + * Case 1: register MINOR on anon + * Case 2: register with no mode selected + */ + if ((minor && (mem_type->mem_flag == MEM_ANON)) || + (!miss && !wp && !minor)) { + if (ret != -EINVAL) + err("register (miss=%d, wp=%d, minor=%d) failed " + "with wrong errno=%d", miss, wp, minor, ret); + return; + } + + /* UFFDIO_REGISTER should succeed, then check ioctls returned */ + if (miss) + expected |= BIT_ULL(_UFFDIO_COPY); + if (wp) + expected |= BIT_ULL(_UFFDIO_WRITEPROTECT); + if (minor) + expected |= BIT_ULL(_UFFDIO_CONTINUE); + + if ((ioctls & expected) != expected) + err("unexpected uffdio_register.ioctls " + "(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", " + "returned=0x%"PRIx64, miss, wp, minor, expected, ioctls); + + if (uffd_unregister(uffd, area_dst, page_size)) + err("unregister"); +} + +static void uffd_register_ioctls_test(uffd_test_args_t *args) +{ + int miss, wp, minor; + + for (miss = 0; miss <= 1; miss++) + for (wp = 0; wp <= 1; wp++) + for (minor = 0; minor <= 1; minor++) + do_register_ioctls_test(args, miss, wp, minor); + + uffd_test_pass(); +} + uffd_test_case_t uffd_tests[] = { + { + /* Test returned uffdio_register.ioctls. */ + .name = "register-ioctls", + .uffd_fn = uffd_register_ioctls_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_MISSING_HUGETLBFS | + UFFD_FEATURE_MISSING_SHMEM | + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + UFFD_FEATURE_MINOR_HUGETLBFS | + UFFD_FEATURE_MINOR_SHMEM, + }, { .name = "zeropage", .uffd_fn = uffd_zeropage_test, @@ -835,6 +915,7 @@ int main(int argc, char *argv[]) int n_mems = sizeof(mem_types) / sizeof(mem_type_t); uffd_test_case_t *test; mem_type_t *mem_type; + uffd_test_args_t args; char test_name[128]; const char *errmsg; int has_uffd; @@ -862,11 +943,12 @@ int main(int argc, char *argv[]) uffd_test_skip("feature missing"); continue; } - if (uffd_setup_environment(test, mem_type, &errmsg)) { + if (uffd_setup_environment(&args, test, mem_type, + &errmsg)) { uffd_test_skip(errmsg); continue; } - test->uffd_fn(); + test->uffd_fn(&args); } } -- GitLab From 87a7ae75d7383afa998f57656d1d14e2a730cc47 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 11 Apr 2023 19:52:13 +0530 Subject: [PATCH 3328/5631] mm/vmemmap/devdax: fix kernel crash when probing devdax devices commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") added support for using optimized vmmemap for devdax devices. But how vmemmap mappings are created are architecture specific. For example, powerpc with hash translation doesn't have vmemmap mappings in init_mm page table instead they are bolted table entries in the hardware page table vmemmap_populate_compound_pages() used by vmemmap optimization code is not aware of these architecture-specific mapping. Hence allow architecture to opt for this feature. I selected architectures supporting HUGETLB_PAGE_OPTIMIZE_VMEMMAP option as also supporting this feature. This patch fixes the below crash on ppc64. BUG: Unable to handle kernel data access on write at 0xc00c000100400038 Faulting instruction address: 0xc000000001269d90 Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries Modules linked in: CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries NIP: c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000 REGS: c000000003632c30 TRAP: 0300 Not tainted (6.3.0-rc5-150500.34-default+) MSR: 8000000000009033 CR: 24842228 XER: 00000000 CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0 .... NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0 Call Trace: [c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable) [c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250 [c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0 [c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0 [c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0 [c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140 [c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520 [c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120 [c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0 [c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130 [c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250 [c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110 [c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10 [c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530 [c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270 [c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70 [c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0 [c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520 [c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230 [c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120 [c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240 [c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130 [c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50 [c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300 [c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0 [c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100 [c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48 [c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320 [c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400 [c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0 [c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64 Link: https://lkml.kernel.org/r/20230411142214.64464-1-aneesh.kumar@linux.ibm.com Fixes: 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory savings for compound devmaps") Signed-off-by: Aneesh Kumar K.V Reported-by: Tarun Sahu Reviewed-by: Joao Martins Cc: Muchun Song Cc: Dan Williams Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 16 ++++++++++++++++ mm/mm_init.c | 10 ++++++---- mm/sparse-vmemmap.c | 3 +-- 3 files changed, 23 insertions(+), 6 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a3eaa9a1f8c..21a7e2460084 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3560,6 +3560,22 @@ void vmemmap_populate_print_last(void); void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif + +#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return is_power_of_2(sizeof(struct page)) && + pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; +} +#else +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return false; +} +#endif + void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); diff --git a/mm/mm_init.c b/mm/mm_init.c index a0ec3b3acb5e..7f7f9c677854 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1015,10 +1015,12 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, * of an altmap. See vmemmap_populate_compound_pages(). */ static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap, - unsigned long nr_pages) + struct dev_pagemap *pgmap) { - return is_power_of_2(sizeof(struct page)) && - !altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages; + if (!vmemmap_can_optimize(altmap, pgmap)) + return pgmap_vmemmap_nr(pgmap); + + return 2 * (PAGE_SIZE / sizeof(struct page)); } static void __ref memmap_init_compound(struct page *head, @@ -1083,7 +1085,7 @@ void __ref memmap_init_zone_device(struct zone *zone, continue; memmap_init_compound(page, pfn, zone_idx, nid, pgmap, - compound_nr_pages(altmap, pfns_per_compound)); + compound_nr_pages(altmap, pgmap)); } pr_debug("%s initialised %lu pages in %ums\n", __func__, diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index c5398a5960d0..10d73a0dfcec 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -458,8 +458,7 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn, !IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION))) return NULL; - if (is_power_of_2(sizeof(struct page)) && - pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap) + if (vmemmap_can_optimize(altmap, pgmap)) r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap); else r = vmemmap_populate(start, end, nid, altmap); -- GitLab From 0b376f1e0ff555435597fa16823ae0f30b2883e3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Apr 2023 10:30:25 +0530 Subject: [PATCH 3329/5631] mm/hugetlb_vmemmap: rename ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP Now we use ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP config option to indicate devdax and hugetlb vmemmap optimization support. Hence rename that to a generic ARCH_WANT_OPTIMIZE_VMEMMAP Link: https://lkml.kernel.org/r/20230412050025.84346-2-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: Muchun Song Cc: Joao Martins Cc: Dan Williams Cc: Mike Kravetz Cc: Tarun Sahu Signed-off-by: Andrew Morton --- arch/loongarch/Kconfig | 2 +- arch/s390/Kconfig | 2 +- arch/x86/Kconfig | 2 +- fs/Kconfig | 9 +-------- include/linux/mm.h | 2 +- mm/Kconfig | 6 ++++++ 6 files changed, 11 insertions(+), 12 deletions(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index e1e3a3828962..5abd13093c1a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -53,8 +53,8 @@ config LOONGARCH select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT - select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_OPTIMIZE_VMEMMAP select ARCH_WANTS_NO_INSTR select BUILDTIME_TABLE_SORT select COMMON_CLK diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 548b5b587003..61d778397720 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -126,8 +126,8 @@ config S390 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT - select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_OPTIMIZE_VMEMMAP select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 select DMA_OPS if PCI diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index df21fba77db1..4c123315c440 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -126,8 +126,8 @@ config X86 select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE - select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP if X86_64 select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_OPTIMIZE_VMEMMAP if X86_64 select ARCH_WANTS_THP_SWAP if X86_64 select ARCH_HAS_PARANOID_L1D_FLUSH select BUILDTIME_TABLE_SORT diff --git a/fs/Kconfig b/fs/Kconfig index e99830c65033..cc07a0cd3172 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -250,16 +250,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS -# -# Select this config option from the architecture Kconfig, if it is preferred -# to enable the feature of HugeTLB Vmemmap Optimization (HVO). -# -config ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP - bool - config HUGETLB_PAGE_OPTIMIZE_VMEMMAP def_bool HUGETLB_PAGE - depends on ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP + depends on ARCH_WANT_OPTIMIZE_VMEMMAP depends on SPARSEMEM_VMEMMAP config HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON diff --git a/include/linux/mm.h b/include/linux/mm.h index 21a7e2460084..0b514de43143 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3561,7 +3561,7 @@ void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif -#ifdef CONFIG_ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap) { diff --git a/mm/Kconfig b/mm/Kconfig index 6ee3b48ed298..5ca8fcfae243 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -479,6 +479,12 @@ config SPARSEMEM_VMEMMAP SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. +# +# Select this config option from the architecture Kconfig, if it is preferred +# to enable the feature of HugeTLB/dev_dax vmemmap optimization. +# +config ARCH_WANT_OPTIMIZE_VMEMMAP + bool config HAVE_MEMBLOCK_PHYS_MAP bool -- GitLab From ec342603e6d7404c17936a6b53670c28355d3bc3 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Wed, 12 Apr 2023 00:34:51 +0000 Subject: [PATCH 3330/5631] memcg: page_cgroup_ino() get memcg from the page's folio In a kernel with added WARN_ON_ONCE(PageTail) in page_memcg_check(), we observed a warning from page_cgroup_ino() when reading /proc/kpagecgroup. This warning was added to catch fragile reads of a page memcg. Make page_cgroup_ino() get memcg from the page's folio using folio_memcg_check(): that gives it the correct memcg for each page of a folio, so is the right fix. Note that page_folio() is racy, the page's folio can change from under us, but the entire function is racy and documented as such. I dithered between the right fix and the safer "fix": it's unlikely but conceivable that some userspace has learnt that /proc/kpagecgroup gives no memcg on tail pages, and compensates for that in some (racy) way: so continuing to give no memcg on tails, without warning, might be safer. But hwpoison_filter_task(), the only other user of page_cgroup_ino(), persuaded me. It looks as if it currently leaves out tail pages of the selected memcg, by mistake: whereas hwpoison_inject() uses compound_head() and expects the tails to be included. So hwpoison testing coverage has probably been restricted by the wrong output from page_cgroup_ino() (if that memcg filter is used at all): in the short term, it might be safer not to enable wider coverage there, but long term we would regret that. This is based on a patch originally written by Hugh Dickins and retains most of the original commit log [1] The patch was changed to use folio_memcg_check(page_folio(page)) instead of page_memcg_check(compound_head(page)) based on discussions with Matthew Wilcox; where he stated that callers of page_memcg_check() should stop using it due to the ambiguity around tail pages -- instead they should use folio_memcg_check() and handle tail pages themselves. Link: https://lkml.kernel.org/r/20230412003451.4018887-1-yosryahmed@google.com Link: https://lore.kernel.org/linux-mm/20230313083452.1319968-1-yosryahmed@google.com/ [1] Signed-off-by: Yosry Ahmed Cc: Hugh Dickins Cc: Johannes Weiner Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Roman Gushchin Cc: Shakeel Butt Cc: Vladimir Davydov Signed-off-by: Andrew Morton --- mm/memcontrol.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cb17f3abdfe0..4b27e245a055 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -396,7 +396,8 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - memcg = page_memcg_check(page); + /* page_folio() is racy here, but the entire function is racy anyway */ + memcg = folio_memcg_check(page_folio(page)); while (memcg && !(memcg->css.flags & CSS_ONLINE)) memcg = parent_mem_cgroup(memcg); -- GitLab From 1cb9dc4b475c7418f925ab0c97b6750007d9f52e Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Thu, 13 Apr 2023 21:13:49 +0800 Subject: [PATCH 3331/5631] mm: hwpoison: support recovery from HugePage copy-on-write faults copy-on-write of hugetlb user pages with uncorrectable errors will result in a kernel crash. This is because the copy is performed in kernel mode and in general we can not handle accessing memory with such errors while in kernel mode. Commit a873dfe1032a ("mm, hwpoison: try to recover from copy-on write faults") introduced the routine copy_user_highpage_mc() to gracefully handle copying of user pages with uncorrectable errors. However, the separate hugetlb copy-on-write code paths were not modified as part of commit a873dfe1032a. Modify hugetlb copy-on-write code paths to use copy_mc_user_highpage() so that they can also gracefully handle uncorrectable errors in user pages. This involves changing the hugetlb specific routine copy_user_large_folio() from type void to int so that it can return an error. Modify the hugetlb userfaultfd code in the same way so that it can return -EHWPOISON if it encounters an uncorrectable error. Link: https://lkml.kernel.org/r/20230413131349.2524210-1-liushixin2@huawei.com Signed-off-by: Liu Shixin Acked-by: Mike Kravetz Reviewed-by: Naoya Horiguchi Cc: Miaohe Lin Cc: Muchun Song Cc: Tony Luck Signed-off-by: Andrew Morton --- include/linux/mm.h | 6 ++--- mm/hugetlb.c | 17 ++++++++++--- mm/memory.c | 59 +++++++++++++++++++++++++++++----------------- 3 files changed, 55 insertions(+), 27 deletions(-) diff --git a/include/linux/mm.h b/include/linux/mm.h index 0b514de43143..2772a1800cf3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3693,9 +3693,9 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -void copy_user_large_folio(struct folio *dst, struct folio *src, - unsigned long addr_hint, - struct vm_area_struct *vma); +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); long copy_folio_from_user(struct folio *dst_folio, const void __user *usr_src, bool allow_pagefault); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f16b25b1a6b9..a08fb47fb200 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5097,10 +5097,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, ret = PTR_ERR(new_folio); break; } - copy_user_large_folio(new_folio, + ret = copy_user_large_folio(new_folio, page_folio(ptepage), addr, dst_vma); put_page(ptepage); + if (ret) { + folio_put(new_folio); + break; + } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); @@ -5617,7 +5621,10 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, goto out_release_all; } - copy_user_large_folio(new_folio, page_folio(old_page), address, vma); + if (copy_user_large_folio(new_folio, page_folio(old_page), address, vma)) { + ret = VM_FAULT_HWPOISON_LARGE; + goto out_release_all; + } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, @@ -6260,9 +6267,13 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, *foliop = NULL; goto out; } - copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); + ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; + if (ret) { + folio_put(folio); + goto out; + } } /* diff --git a/mm/memory.c b/mm/memory.c index f315c2198098..f7510a06a2d0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5733,12 +5733,12 @@ EXPORT_SYMBOL(__might_fault); * operation. The target subpage will be processed last to keep its * cache lines hot. */ -static inline void process_huge_page( +static inline int process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, - void (*process_subpage)(unsigned long addr, int idx, void *arg), + int (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { - int i, n, base, l; + int i, n, base, l, ret; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); @@ -5752,7 +5752,9 @@ static inline void process_huge_page( /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); - process_subpage(addr + i * PAGE_SIZE, i, arg); + ret = process_subpage(addr + i * PAGE_SIZE, i, arg); + if (ret) + return ret; } } else { /* If target subpage in second half of huge page */ @@ -5761,7 +5763,9 @@ static inline void process_huge_page( /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); - process_subpage(addr + i * PAGE_SIZE, i, arg); + ret = process_subpage(addr + i * PAGE_SIZE, i, arg); + if (ret) + return ret; } } /* @@ -5773,10 +5777,15 @@ static inline void process_huge_page( int right_idx = base + 2 * l - 1 - i; cond_resched(); - process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); + ret = process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); + if (ret) + return ret; cond_resched(); - process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); + ret = process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); + if (ret) + return ret; } + return 0; } static void clear_gigantic_page(struct page *page, @@ -5794,11 +5803,12 @@ static void clear_gigantic_page(struct page *page, } } -static void clear_subpage(unsigned long addr, int idx, void *arg) +static int clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); + return 0; } void clear_huge_page(struct page *page, @@ -5815,7 +5825,7 @@ void clear_huge_page(struct page *page, process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } -static void copy_user_gigantic_page(struct folio *dst, struct folio *src, +static int copy_user_gigantic_page(struct folio *dst, struct folio *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) @@ -5829,8 +5839,13 @@ static void copy_user_gigantic_page(struct folio *dst, struct folio *src, src_page = folio_page(src, i); cond_resched(); - copy_user_highpage(dst_page, src_page, addr + i*PAGE_SIZE, vma); + if (copy_mc_user_highpage(dst_page, src_page, + addr + i*PAGE_SIZE, vma)) { + memory_failure_queue(page_to_pfn(src_page), 0); + return -EHWPOISON; + } } + return 0; } struct copy_subpage_arg { @@ -5839,16 +5854,20 @@ struct copy_subpage_arg { struct vm_area_struct *vma; }; -static void copy_subpage(unsigned long addr, int idx, void *arg) +static int copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; - copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, - addr, copy_arg->vma); + if (copy_mc_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, + addr, copy_arg->vma)) { + memory_failure_queue(page_to_pfn(copy_arg->src + idx), 0); + return -EHWPOISON; + } + return 0; } -void copy_user_large_folio(struct folio *dst, struct folio *src, - unsigned long addr_hint, struct vm_area_struct *vma) +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, struct vm_area_struct *vma) { unsigned int pages_per_huge_page = folio_nr_pages(dst); unsigned long addr = addr_hint & @@ -5859,13 +5878,11 @@ void copy_user_large_folio(struct folio *dst, struct folio *src, .vma = vma, }; - if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { - copy_user_gigantic_page(dst, src, addr, vma, - pages_per_huge_page); - return; - } + if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) + return copy_user_gigantic_page(dst, src, addr, vma, + pages_per_huge_page); - process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); + return process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_folio_from_user(struct folio *dst_folio, -- GitLab From bb1508c24c9c361e6344308c8de2cb81d7f228ba Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:22 +0200 Subject: [PATCH 3332/5631] mm: kmsan: apply __must_check to non-void functions Non-void KMSAN hooks may return error codes that indicate that KMSAN failed to reflect the changed memory state in the metadata (e.g. it could not create the necessary memory mappings). In such cases the callers should handle the errors to prevent the tool from using the inconsistent metadata in the future. We mark non-void hooks with __must_check so that error handling is not skipped. Link: https://lkml.kernel.org/r/20230413131223.4135168-3-glider@google.com Signed-off-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dipanjan Das Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- include/linux/kmsan.h | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index 30b17647ce3c..e0c23a32cdf0 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -54,7 +54,8 @@ void __init kmsan_init_runtime(void); * Freed pages are either returned to buddy allocator or held back to be used * as metadata pages. */ -bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); +bool __init __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order); /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. @@ -137,9 +138,11 @@ void kmsan_kfree_large(const void *ptr); * vmalloc metadata address range. Returns 0 on success, callers must check * for non-zero return value. */ -int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int __must_check kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -163,9 +166,9 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * virtual memory. Returns 0 on success, callers must check for non-zero return * value. */ -int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int __must_check kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -237,8 +240,8 @@ static inline void kmsan_init_runtime(void) { } -static inline bool kmsan_memblock_free_pages(struct page *page, - unsigned int order) +static inline bool __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order) { return true; } @@ -251,10 +254,9 @@ static inline void kmsan_task_exit(struct task_struct *task) { } -static inline int kmsan_alloc_page(struct page *page, unsigned int order, - gfp_t flags) +static inline void kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) { - return 0; } static inline void kmsan_free_page(struct page *page, unsigned int order) @@ -283,11 +285,9 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline int kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int __must_check kmsan_vmap_pages_range_noflush( + unsigned long start, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift) { return 0; } @@ -297,10 +297,11 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline int kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift) +static inline int __must_check kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) { return 0; } -- GitLab From d905ae2b0f7eaf8fb37febfe4833ccf3f8c1c27a Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Thu, 13 Apr 2023 15:12:23 +0200 Subject: [PATCH 3333/5631] mm: apply __must_check to vmap_pages_range_noflush() To prevent errors when vmap_pages_range_noflush() or __vmap_pages_range_noflush() silently fail (see the link below for an example), annotate them with __must_check so that the callers do not unconditionally assume the mapping succeeded. Link: https://lkml.kernel.org/r/20230413131223.4135168-4-glider@google.com Signed-off-by: Alexander Potapenko Reported-by: Dipanjan Das Link: https://lore.kernel.org/linux-mm/CANX2M5ZRrRA64k0hOif02TjmY9kbbO2aCBPyq79es34RXZ=cAw@mail.gmail.com/ Reviewed-by: Marco Elver Cc: Christoph Hellwig Cc: Dmitry Vyukov Cc: Uladzislau Rezki (Sony) Signed-off-by: Andrew Morton --- mm/internal.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 92ddd3a05b74..6483db57a31f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -885,7 +885,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, */ #ifdef CONFIG_MMU void __init vmalloc_init(void); -int vmap_pages_range_noflush(unsigned long addr, unsigned long end, +int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); #else static inline void vmalloc_init(void) @@ -893,16 +893,16 @@ static inline void vmalloc_init(void) } static inline -int vmap_pages_range_noflush(unsigned long addr, unsigned long end, +int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif -int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int __must_check __vmap_pages_range_noflush(unsigned long addr, + unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); -- GitLab From 583c27a167c2bc6088ec80be0d16ef44dd9fc6b0 Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 13 Apr 2023 10:40:32 +0000 Subject: [PATCH 3334/5631] mm: vmscan: ignore non-LRU-based reclaim in memcg reclaim Patch series "Ignore non-LRU-based reclaim in memcg reclaim", v6. Upon running some proactive reclaim tests using memory.reclaim, we noticed some tests flaking where writing to memory.reclaim would be successful even though we did not reclaim the requested amount fully Looking further into it, I discovered that *sometimes* we overestimate the number of reclaimed pages in memcg reclaim. Reclaimed pages through other means than LRU-based reclaim are tracked through reclaim_state in struct scan_control, which is stashed in current task_struct. These pages are added to the number of reclaimed pages through LRUs. For memcg reclaim, these pages generally cannot be linked to the memcg under reclaim and can cause an overestimated count of reclaimed pages. This short series tries to address that. Patch 1 ignores pages reclaimed outside of LRU reclaim in memcg reclaim. The pages are uncharged anyway, so even if we end up under-reporting reclaimed pages we will still succeed in making progress during charging. Patches 2-3 are just refactoring. Patch 2 moves set_reclaim_state() helper next to flush_reclaim_state(). Patch 3 adds a helper that wraps updating current->reclaim_state, and renames reclaim_state->reclaimed_slab to reclaim_state->reclaimed. This patch (of 3): We keep track of different types of reclaimed pages through reclaim_state->reclaimed_slab, and we add them to the reported number of reclaimed pages. For non-memcg reclaim, this makes sense. For memcg reclaim, we have no clue if those pages are charged to the memcg under reclaim. Slab pages are shared by different memcgs, so a freed slab page may have only been partially charged to the memcg under reclaim. The same goes for clean file pages from pruned inodes (on highmem systems) or xfs buffer pages, there is no simple way to currently link them to the memcg under reclaim. Stop reporting those freed pages as reclaimed pages during memcg reclaim. This should make the return value of writing to memory.reclaim, and may help reduce unnecessary reclaim retries during memcg charging. Writing to memory.reclaim on the root memcg is considered as cgroup_reclaim(), but for this case we want to include any freed pages, so use the global_reclaim() check instead of !cgroup_reclaim(). Generally, this should make the return value of try_to_free_mem_cgroup_pages() more accurate. In some limited cases (e.g. freed a slab page that was mostly charged to the memcg under reclaim), the return value of try_to_free_mem_cgroup_pages() can be underestimated, but this should be fine. The freed pages will be uncharged anyway, and we can charge the memcg the next time around as we usually do memcg reclaim in a retry loop. Link: https://lkml.kernel.org/r/20230413104034.1086717-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20230413104034.1086717-2-yosryahmed@google.com Fixes: f2fe7b09a52b ("mm: memcg/slab: charge individual slab objects instead of pages") Signed-off-by: Yosry Ahmed Acked-by: David Hildenbrand Acked-by: Michal Hocko Cc: Alexander Viro Cc: Christoph Lameter Cc: Darrick J. Wong Cc: Dave Chinner Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Miaohe Lin Cc: NeilBrown Cc: Peter Xu Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Chen Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/vmscan.c | 49 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 7 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index 7f2441d6dfb2..f2fa565276cb 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -528,6 +528,46 @@ static bool writeback_throttling_sane(struct scan_control *sc) } #endif +/* + * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to + * scan_control->nr_reclaimed. + */ +static void flush_reclaim_state(struct scan_control *sc) +{ + /* + * Currently, reclaim_state->reclaimed includes three types of pages + * freed outside of vmscan: + * (1) Slab pages. + * (2) Clean file pages from pruned inodes (on highmem systems). + * (3) XFS freed buffer pages. + * + * For all of these cases, we cannot universally link the pages to a + * single memcg. For example, a memcg-aware shrinker can free one object + * charged to the target memcg, causing an entire page to be freed. + * If we count the entire page as reclaimed from the memcg, we end up + * overestimating the reclaimed amount (potentially under-reclaiming). + * + * Only count such pages for global reclaim to prevent under-reclaiming + * from the target memcg; preventing unnecessary retries during memcg + * charging and false positives from proactive reclaim. + * + * For uncommon cases where the freed pages were actually mostly + * charged to the target memcg, we end up underestimating the reclaimed + * amount. This should be fine. The freed pages will be uncharged + * anyway, even if they are not counted here properly, and we will be + * able to make forward progress in charging (which is usually in a + * retry loop). + * + * We can go one step further, and report the uncharged objcg pages in + * memcg reclaim, to make reporting more accurate and reduce + * underestimation, but it's probably not worth the complexity for now. + */ + if (current->reclaim_state && global_reclaim(sc)) { + sc->nr_reclaimed += current->reclaim_state->reclaimed; + current->reclaim_state->reclaimed = 0; + } +} + static long xchg_nr_deferred(struct shrinker *shrinker, struct shrink_control *sc) { @@ -5362,8 +5402,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); - sc->nr_reclaimed += current->reclaim_state->reclaimed_slab; - current->reclaim_state->reclaimed_slab = 0; + flush_reclaim_state(sc); return success ? MEMCG_LRU_YOUNG : 0; } @@ -6462,7 +6501,6 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { - struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; @@ -6484,10 +6522,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) shrink_node_memcgs(pgdat, sc); - if (reclaim_state) { - sc->nr_reclaimed += reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } + flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; -- GitLab From ef05e68936ff06e64919b3428ac92c4de002366c Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 13 Apr 2023 10:40:33 +0000 Subject: [PATCH 3335/5631] mm: vmscan: move set_task_reclaim_state() near flush_reclaim_state() Move set_task_reclaim_state() near flush_reclaim_state() so that all helpers manipulating reclaim_state are in close proximity. Link: https://lkml.kernel.org/r/20230413104034.1086717-3-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Michal Hocko Cc: Alexander Viro Cc: Christoph Lameter Cc: Darrick J. Wong Cc: Dave Chinner Cc: David Hildenbrand Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Miaohe Lin Cc: NeilBrown Cc: Peter Xu Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Chen Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton --- mm/vmscan.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/mm/vmscan.c b/mm/vmscan.c index f2fa565276cb..2eb5862e99ec 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -189,18 +189,6 @@ struct scan_control { */ int vm_swappiness = 60; -static void set_task_reclaim_state(struct task_struct *task, - struct reclaim_state *rs) -{ - /* Check for an overwrite */ - WARN_ON_ONCE(rs && task->reclaim_state); - - /* Check for the nulling of an already-nulled member */ - WARN_ON_ONCE(!rs && !task->reclaim_state); - - task->reclaim_state = rs; -} - LIST_HEAD(shrinker_list); DEFINE_MUTEX(shrinker_mutex); DEFINE_SRCU(shrinker_srcu); @@ -528,6 +516,18 @@ static bool writeback_throttling_sane(struct scan_control *sc) } #endif +static void set_task_reclaim_state(struct task_struct *task, + struct reclaim_state *rs) +{ + /* Check for an overwrite */ + WARN_ON_ONCE(rs && task->reclaim_state); + + /* Check for the nulling of an already-nulled member */ + WARN_ON_ONCE(!rs && !task->reclaim_state); + + task->reclaim_state = rs; +} + /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. -- GitLab From c7b23b68e2aa93f86a206222d23ccd9a21f5982a Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Thu, 13 Apr 2023 10:40:34 +0000 Subject: [PATCH 3336/5631] mm: vmscan: refactor updating current->reclaim_state During reclaim, we keep track of pages reclaimed from other means than LRU-based reclaim through scan_control->reclaim_state->reclaimed_slab, which we stash a pointer to in current task_struct. However, we keep track of more than just reclaimed slab pages through this. We also use it for clean file pages dropped through pruned inodes, and xfs buffer pages freed. Rename reclaimed_slab to reclaimed, and add a helper function that wraps updating it through current, so that future changes to this logic are contained within include/linux/swap.h. Link: https://lkml.kernel.org/r/20230413104034.1086717-4-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Michal Hocko Cc: Alexander Viro Cc: Christoph Lameter Cc: Darrick J. Wong Cc: Dave Chinner Cc: David Hildenbrand Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Miaohe Lin Cc: NeilBrown Cc: Peter Xu Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Chen Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton --- fs/inode.c | 3 +-- fs/xfs/xfs_buf.c | 3 +-- include/linux/swap.h | 17 ++++++++++++++++- mm/slab.c | 3 +-- mm/slob.c | 6 ++---- mm/slub.c | 5 ++--- 6 files changed, 23 insertions(+), 14 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 4558dc2f1355..e60fcc41faf1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -864,8 +864,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += reap; + mm_account_reclaimed_pages(reap); } iput(inode); spin_lock(lru_lock); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 54c774af6e1c..15d1e5a7c2d3 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -286,8 +286,7 @@ xfs_buf_free_pages( if (bp->b_pages[i]) __free_page(bp->b_pages[i]); } - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += bp->b_page_count; + mm_account_reclaimed_pages(bp->b_page_count); if (bp->b_pages != bp->b_page_array) kmem_free(bp->b_pages); diff --git a/include/linux/swap.h b/include/linux/swap.h index bfc3b06b5f8f..7f7d5b9ddf7e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -153,13 +153,28 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +static inline void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} + #ifdef __KERNEL__ struct address_space; diff --git a/mm/slab.c b/mm/slab.c index 6b7c172158e5..bb57f7fdbae1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1392,8 +1392,7 @@ static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab) smp_wmb(); __folio_clear_slab(folio); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += 1 << order; + mm_account_reclaimed_pages(1 << order); unaccount_slab(slab, order, cachep); __free_pages(&folio->page, order); } diff --git a/mm/slob.c b/mm/slob.c index fe567fcfa3a3..79cc8680c973 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -61,7 +61,7 @@ #include #include -#include /* struct reclaim_state */ +#include /* mm_account_reclaimed_pages() */ #include #include #include @@ -211,9 +211,7 @@ static void slob_free_pages(void *b, int order) { struct page *sp = virt_to_page(b); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += 1 << order; - + mm_account_reclaimed_pages(1 << order); mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(sp, order); diff --git a/mm/slub.c b/mm/slub.c index f49d669ff604..2728d5ae4dc0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -11,7 +11,7 @@ */ #include -#include /* struct reclaim_state */ +#include /* mm_account_reclaimed_pages() */ #include #include #include @@ -2063,8 +2063,7 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) /* Make the mapping reset visible before clearing the flag */ smp_wmb(); __folio_clear_slab(folio); - if (current->reclaim_state) - current->reclaim_state->reclaimed_slab += pages; + mm_account_reclaimed_pages(pages); unaccount_slab(slab, order, s); __free_pages(&folio->page, order); } -- GitLab From 1f6ab566cb3be9e8292e34b89e8be83d75aa232e Mon Sep 17 00:00:00 2001 From: Pavankumar Kondeti Date: Thu, 13 Apr 2023 15:38:59 +0530 Subject: [PATCH 3337/5631] printk: export console trace point for kcsan/kasan/kfence/kmsan The console tracepoint is used by kcsan/kasan/kfence/kmsan test modules. Since this tracepoint is not exported, these modules iterate over all available tracepoints to find the console trace point. Export the trace point so that it can be directly used. Link: https://lkml.kernel.org/r/20230413100859.1492323-1-quic_pkondeti@quicinc.com Signed-off-by: Pavankumar Kondeti Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: John Ogness Cc: Marco Elver Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Steven Rostedt Cc: Vincenzo Frascino Signed-off-by: Andrew Morton --- kernel/kcsan/kcsan_test.c | 20 ++++++-------------- kernel/printk/printk.c | 2 ++ mm/kasan/kasan_test.c | 22 ++-------------------- mm/kfence/kfence_test.c | 22 ++-------------------- mm/kmsan/kmsan_test.c | 22 ++-------------------- 5 files changed, 14 insertions(+), 74 deletions(-) diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index a60c561724be..0ddbdab5903d 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -1572,34 +1572,26 @@ static void test_exit(struct kunit *test) } __no_kcsan -static void register_tracepoints(struct tracepoint *tp, void *ignore) +static void register_tracepoints(void) { - check_trace_callback_type_console(probe_console); - if (!strcmp(tp->name, "console")) - WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); + register_trace_console(probe_console, NULL); } __no_kcsan -static void unregister_tracepoints(struct tracepoint *tp, void *ignore) +static void unregister_tracepoints(void) { - if (!strcmp(tp->name, "console")) - tracepoint_probe_unregister(tp, probe_console, NULL); + unregister_trace_console(probe_console, NULL); } static int kcsan_suite_init(struct kunit_suite *suite) { - /* - * Because we want to be able to build the test as a module, we need to - * iterate through all known tracepoints, since the static registration - * won't work here. - */ - for_each_kernel_tracepoint(register_tracepoints, NULL); + register_tracepoints(); return 0; } static void kcsan_suite_exit(struct kunit_suite *suite) { - for_each_kernel_tracepoint(unregister_tracepoints, NULL); + unregister_tracepoints(); tracepoint_synchronize_unregister(); } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fd0c9f913940..1c71bb170e85 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -71,6 +71,8 @@ EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); +EXPORT_TRACEPOINT_SYMBOL_GPL(console); + /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index a375776f9896..b61cc6a42541 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -56,19 +56,6 @@ static void probe_console(void *ignore, const char *buf, size_t len) WRITE_ONCE(test_status.async_fault, true); } -static void register_tracepoints(struct tracepoint *tp, void *ignore) -{ - check_trace_callback_type_console(probe_console); - if (!strcmp(tp->name, "console")) - WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); -} - -static void unregister_tracepoints(struct tracepoint *tp, void *ignore) -{ - if (!strcmp(tp->name, "console")) - tracepoint_probe_unregister(tp, probe_console, NULL); -} - static int kasan_suite_init(struct kunit_suite *suite) { if (!kasan_enabled()) { @@ -86,12 +73,7 @@ static int kasan_suite_init(struct kunit_suite *suite) */ multishot = kasan_save_enable_multi_shot(); - /* - * Because we want to be able to build the test as a module, we need to - * iterate through all known tracepoints, since the static registration - * won't work here. - */ - for_each_kernel_tracepoint(register_tracepoints, NULL); + register_trace_console(probe_console, NULL); return 0; } @@ -99,7 +81,7 @@ static void kasan_suite_exit(struct kunit_suite *suite) { kasan_kunit_test_suite_end(); kasan_restore_multi_shot(multishot); - for_each_kernel_tracepoint(unregister_tracepoints, NULL); + unregister_trace_console(probe_console, NULL); tracepoint_synchronize_unregister(); } diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index b5d66a69200d..6aee19a79236 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -825,33 +825,15 @@ static void test_exit(struct kunit *test) test_cache_destroy(); } -static void register_tracepoints(struct tracepoint *tp, void *ignore) -{ - check_trace_callback_type_console(probe_console); - if (!strcmp(tp->name, "console")) - WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); -} - -static void unregister_tracepoints(struct tracepoint *tp, void *ignore) -{ - if (!strcmp(tp->name, "console")) - tracepoint_probe_unregister(tp, probe_console, NULL); -} - static int kfence_suite_init(struct kunit_suite *suite) { - /* - * Because we want to be able to build the test as a module, we need to - * iterate through all known tracepoints, since the static registration - * won't work here. - */ - for_each_kernel_tracepoint(register_tracepoints, NULL); + register_trace_console(probe_console, NULL); return 0; } static void kfence_suite_exit(struct kunit_suite *suite) { - for_each_kernel_tracepoint(unregister_tracepoints, NULL); + unregister_trace_console(probe_console, NULL); tracepoint_synchronize_unregister(); } diff --git a/mm/kmsan/kmsan_test.c b/mm/kmsan/kmsan_test.c index d9eb141c27aa..312989aa2865 100644 --- a/mm/kmsan/kmsan_test.c +++ b/mm/kmsan/kmsan_test.c @@ -626,33 +626,15 @@ static void test_exit(struct kunit *test) { } -static void register_tracepoints(struct tracepoint *tp, void *ignore) -{ - check_trace_callback_type_console(probe_console); - if (!strcmp(tp->name, "console")) - WARN_ON(tracepoint_probe_register(tp, probe_console, NULL)); -} - -static void unregister_tracepoints(struct tracepoint *tp, void *ignore) -{ - if (!strcmp(tp->name, "console")) - tracepoint_probe_unregister(tp, probe_console, NULL); -} - static int kmsan_suite_init(struct kunit_suite *suite) { - /* - * Because we want to be able to build the test as a module, we need to - * iterate through all known tracepoints, since the static registration - * won't work here. - */ - for_each_kernel_tracepoint(register_tracepoints, NULL); + register_trace_console(probe_console, NULL); return 0; } static void kmsan_suite_exit(struct kunit_suite *suite) { - for_each_kernel_tracepoint(unregister_tracepoints, NULL); + unregister_trace_console(probe_console, NULL); tracepoint_synchronize_unregister(); } -- GitLab From ed8f3f999e9270ccc542ac44e237e389a2687a9e Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Thu, 13 Apr 2023 16:34:49 +0800 Subject: [PATCH 3338/5631] mm: workingset: update description of the source file The calculation of workingset size is the core logic of handling refault, it had been updated several times[1][2] after workingset.c was created[3]. But the description hadn't been updated accordingly, this mismatch may confuse the readers. So we update the description to make it consistent to the code. [1] commit 34e58cac6d8f ("mm: workingset: let cache workingset challenge anon") [2] commit aae466b0052e ("mm/swap: implement workingset detection for anonymous LRU") [3] commit a528910e12ec ("mm: thrash detection-based file cache sizing") Link: https://lkml.kernel.org/r/202304131634494948454@zte.com.cn Signed-off-by: Yang Yang Cc: Johannes Weiner Cc: Joonsoo Kim Signed-off-by: Andrew Morton --- mm/workingset.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/mm/workingset.c b/mm/workingset.c index 3025beee9b34..817758951886 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -111,9 +111,20 @@ * * NR_inactive + (R - E) <= NR_inactive + NR_active * - * which can be further simplified to + * If we have swap we should consider about NR_inactive_anon and + * NR_active_anon, so for page cache and anonymous respectively: * - * (R - E) <= NR_active + * NR_inactive_file + (R - E) <= NR_inactive_file + NR_active_file + * + NR_inactive_anon + NR_active_anon + * + * NR_inactive_anon + (R - E) <= NR_inactive_anon + NR_active_anon + * + NR_inactive_file + NR_active_file + * + * Which can be further simplified to: + * + * (R - E) <= NR_active_file + NR_inactive_anon + NR_active_anon + * + * (R - E) <= NR_active_anon + NR_inactive_file + NR_active_file * * Put into words, the refault distance (out-of-cache) can be seen as * a deficit in inactive list space (in-cache). If the inactive list @@ -130,14 +141,14 @@ * are no longer in active use. * * So when a refault distance of (R - E) is observed and there are at - * least (R - E) active pages, the refaulting page is activated - * optimistically in the hope that (R - E) active pages are actually + * least (R - E) pages in the userspace workingset, the refaulting page + * is activated optimistically in the hope that (R - E) pages are actually * used less frequently than the refaulting page - or even not used at * all anymore. * * That means if inactive cache is refaulting with a suitable refault * distance, we assume the cache workingset is transitioning and put - * pressure on the current active list. + * pressure on the current workingset. * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently @@ -469,7 +480,7 @@ void workingset_refault(struct folio *folio, void *shadow) * don't activate pages that couldn't stay resident even if * all the memory was available to the workingset. Whether * workingset competition needs to consider anon or not depends - * on having swap. + * on having free swap space. */ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE); if (!file) { -- GitLab From 7f63cf2d9b9bbe7b90f808927558a66ff737d399 Mon Sep 17 00:00:00 2001 From: Kalesh Singh Date: Thu, 13 Apr 2023 14:43:26 -0700 Subject: [PATCH 3339/5631] mm: Multi-gen LRU: remove wait_event_killable() Android 14 and later default to MGLRU [1] and field telemetry showed occasional long tail latency (>100ms) in the reclaim path. Tracing revealed priority inversion in the reclaim path. In try_to_inc_max_seq(), when high priority tasks were blocked on wait_event_killable(), the preemption of the low priority task to call wake_up_all() caused those high priority tasks to wait longer than necessary. In general, this problem is not different from others of its kind, e.g., one caused by mutex_lock(). However, it is specific to MGLRU because it introduced the new wait queue lruvec->mm_state.wait. The purpose of this new wait queue is to avoid the thundering herd problem. If many direct reclaimers rush into try_to_inc_max_seq(), only one can succeed, i.e., the one to wake up the rest, and the rest who failed might cause premature OOM kills if they do not wait. So far there is no evidence supporting this scenario, based on how often the wait has been hit. And this begs the question how useful the wait queue is in practice. Based on Minchan's recommendation, which is in line with his commit 6d4675e60135 ("mm: don't be stuck to rmap lock on reclaim path") and the rest of the MGLRU code which also uses trylock when possible, remove the wait queue. [1] https://android-review.googlesource.com/q/I7ed7fbfd6ef9ce10053347528125dd98c39e50bf Link: https://lkml.kernel.org/r/20230413214326.2147568-1-kaleshsingh@google.com Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks") Signed-off-by: Kalesh Singh Suggested-by: Minchan Kim Reported-by: Wei Wang Acked-by: Yu Zhao Cc: Minchan Kim Cc: Jan Alexander Steffens (heftig) Cc: Oleksandr Natalenko Cc: Suleiman Souhlal Cc: Suren Baghdasaryan Signed-off-by: Andrew Morton --- include/linux/mmzone.h | 8 +-- mm/vmscan.c | 112 +++++++++++++++-------------------------- 2 files changed, 42 insertions(+), 78 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 337956748976..a4889c9d4055 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -443,18 +443,14 @@ enum { struct lru_gen_mm_state { /* set to max_seq after each iteration */ unsigned long seq; - /* where the current iteration continues (inclusive) */ + /* where the current iteration continues after */ struct list_head *head; - /* where the last iteration ended (exclusive) */ + /* where the last iteration ended before */ struct list_head *tail; - /* to wait for the last page table walker to finish */ - struct wait_queue_head wait; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; - /* the number of concurrent page table walkers */ - int nr_walkers; }; struct lru_gen_mm_walk { diff --git a/mm/vmscan.c b/mm/vmscan.c index 2eb5862e99ec..8c05f4c288ce 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3450,18 +3450,13 @@ void lru_gen_del_mm(struct mm_struct *mm) for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); - /* where the last iteration ended (exclusive) */ + /* where the current iteration continues after */ + if (lruvec->mm_state.head == &mm->lru_gen.list) + lruvec->mm_state.head = lruvec->mm_state.head->prev; + + /* where the last iteration ended before */ if (lruvec->mm_state.tail == &mm->lru_gen.list) lruvec->mm_state.tail = lruvec->mm_state.tail->next; - - /* where the current iteration continues (inclusive) */ - if (lruvec->mm_state.head != &mm->lru_gen.list) - continue; - - lruvec->mm_state.head = lruvec->mm_state.head->next; - /* the deletion ends the current iteration */ - if (lruvec->mm_state.head == &mm_list->fifo) - WRITE_ONCE(lruvec->mm_state.seq, lruvec->mm_state.seq + 1); } list_del_init(&mm->lru_gen.list); @@ -3557,68 +3552,54 @@ static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; - bool last = true; + bool last = false; struct mm_struct *mm = NULL; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = &lruvec->mm_state; /* - * There are four interesting cases for this page table walker: - * 1. It tries to start a new iteration of mm_list with a stale max_seq; - * there is nothing left to do. - * 2. It's the first of the current generation, and it needs to reset - * the Bloom filter for the next generation. - * 3. It reaches the end of mm_list, and it needs to increment - * mm_state->seq; the iteration is done. - * 4. It's the last of the current generation, and it needs to reset the - * mm stats counters for the next generation. + * mm_state->seq is incremented after each iteration of mm_list. There + * are three interesting cases for this page table walker: + * 1. It tries to start a new iteration with a stale max_seq: there is + * nothing left to do. + * 2. It started the next iteration: it needs to reset the Bloom filter + * so that a fresh set of PTE tables can be recorded. + * 3. It ended the current iteration: it needs to reset the mm stats + * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq); - VM_WARN_ON_ONCE(*iter && mm_state->seq > walk->max_seq); - VM_WARN_ON_ONCE(*iter && !mm_state->nr_walkers); - if (walk->max_seq <= mm_state->seq) { - if (!*iter) - last = false; + if (walk->max_seq <= mm_state->seq) goto done; - } - if (!mm_state->nr_walkers) { - VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); + if (!mm_state->head) + mm_state->head = &mm_list->fifo; - mm_state->head = mm_list->fifo.next; + if (mm_state->head == &mm_list->fifo) first = true; - } - - while (!mm && mm_state->head != &mm_list->fifo) { - mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); + do { mm_state->head = mm_state->head->next; + if (mm_state->head == &mm_list->fifo) { + WRITE_ONCE(mm_state->seq, mm_state->seq + 1); + last = true; + break; + } /* force scan for those added after the last iteration */ - if (!mm_state->tail || mm_state->tail == &mm->lru_gen.list) { - mm_state->tail = mm_state->head; + if (!mm_state->tail || mm_state->tail == mm_state->head) { + mm_state->tail = mm_state->head->next; walk->force_scan = true; } + mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); if (should_skip_mm(mm, walk)) mm = NULL; - } - - if (mm_state->head == &mm_list->fifo) - WRITE_ONCE(mm_state->seq, mm_state->seq + 1); + } while (!mm); done: - if (*iter && !mm) - mm_state->nr_walkers--; - if (!*iter && mm) - mm_state->nr_walkers++; - - if (mm_state->nr_walkers) - last = false; - if (*iter || last) reset_mm_stats(lruvec, walk, last); @@ -3646,9 +3627,9 @@ static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq) VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq); - if (max_seq > mm_state->seq && !mm_state->nr_walkers) { - VM_WARN_ON_ONCE(mm_state->head && mm_state->head != &mm_list->fifo); - + if (max_seq > mm_state->seq) { + mm_state->head = NULL; + mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); reset_mm_stats(lruvec, NULL, true); success = true; @@ -4248,10 +4229,6 @@ static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, walk_pmd_range(&val, addr, next, args); - /* a racy check to curtail the waiting time */ - if (wq_has_sleeper(&walk->lruvec->mm_state.wait)) - return 1; - if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; @@ -4284,8 +4261,14 @@ static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_ walk->next_addr = FIRST_USER_ADDRESS; do { + DEFINE_MAX_SEQ(lruvec); + err = -EBUSY; + /* another thread might have called inc_max_seq() */ + if (walk->max_seq != max_seq) + break; + /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) break; @@ -4518,25 +4501,12 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, success = iterate_mm_list(lruvec, walk, &mm); if (mm) walk_mm(lruvec, mm, walk); - - cond_resched(); } while (mm); done: - if (!success) { - if (sc->priority <= DEF_PRIORITY - 2) - wait_event_killable(lruvec->mm_state.wait, - max_seq < READ_ONCE(lrugen->max_seq)); - return false; - } + if (success) + inc_max_seq(lruvec, can_swap, force_scan); - VM_WARN_ON_ONCE(max_seq != READ_ONCE(lrugen->max_seq)); - - inc_max_seq(lruvec, can_swap, force_scan); - /* either this sees any waiters or they will see updated max_seq */ - if (wq_has_sleeper(&lruvec->mm_state.wait)) - wake_up_all(&lruvec->mm_state.wait); - - return true; + return success; } /****************************************************************************** @@ -6173,7 +6143,6 @@ void lru_gen_init_lruvec(struct lruvec *lruvec) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); lruvec->mm_state.seq = MIN_NR_GENS; - init_waitqueue_head(&lruvec->mm_state.wait); } #ifdef CONFIG_MEMCG @@ -6206,7 +6175,6 @@ void lru_gen_exit_memcg(struct mem_cgroup *memcg) for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); - VM_WARN_ON_ONCE(lruvec->mm_state.nr_walkers); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); -- GitLab From f7b8f70ba44fb63df47b6fc3204d49ac2885de64 Mon Sep 17 00:00:00 2001 From: Luca Vizzarro Date: Fri, 14 Apr 2023 16:24:58 +0100 Subject: [PATCH 3340/5631] memfd: pass argument of memfd_fcntl as int The interface for fcntl expects the argument passed for the command F_ADD_SEALS to be of type int. The current code wrongly treats it as a long. In order to avoid access to undefined bits, we should explicitly cast the argument to int. This commit changes the signature of all the related and helper functions so that they treat the argument as int instead of long. Link: https://lkml.kernel.org/r/20230414152459.816046-5-Luca.Vizzarro@arm.com Signed-off-by: Luca Vizzarro Cc: Alexander Viro Cc: Christian Brauner Cc: Jeff Layton Cc: Chuck Lever Cc: Kevin Brodsky Cc: Vincenzo Frascino Cc: Szabolcs Nagy Cc: "Theodore Ts'o" Cc: David Laight Cc: Mark Rutland Signed-off-by: Andrew Morton --- include/linux/memfd.h | 4 ++-- mm/memfd.c | 6 +----- 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 4f1600413f91..e7abf6fa4c52 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -5,9 +5,9 @@ #include #ifdef CONFIG_MEMFD_CREATE -extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); #else -static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) +static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } diff --git a/mm/memfd.c b/mm/memfd.c index a0a7a37e8177..69b90c31d38c 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -243,16 +243,12 @@ static int memfd_get_seals(struct file *file) return seals ? *seals : -EINVAL; } -long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) +long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { long error; switch (cmd) { case F_ADD_SEALS: - /* disallow upper 32bit */ - if (arg > UINT_MAX) - return -EINVAL; - error = memfd_add_seals(file, arg); break; case F_GET_SEALS: -- GitLab From 747cd84f677cedb27db10d4ada777d7ec20431ee Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Tue, 21 Mar 2023 14:18:43 +0800 Subject: [PATCH 3341/5631] scripts/gdb: fix lx-timerlist for struct timequeue_head change commit 511885d7061e ("lib/timerqueue: Rely on rbtree semantics for next timer") changed struct timerqueue_head, and so print_active_timers() should be changed accordingly with its way to interpret the structure. Link: https://lkml.kernel.org/r/TYCP286MB21463BD277330B26DDC18903C6819@TYCP286MB2146.JPNP286.PROD.OUTLOOK.COM Signed-off-by: Peng Liu Reviewed-by: Jan Kiszka Cc: Kieran Bingham Cc: Florian Fainelli Signed-off-by: Andrew Morton --- scripts/gdb/linux/timerlist.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index 071d0dd5a634..44e39dc3eb64 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -43,8 +43,7 @@ def print_timer(rb_node, idx): def print_active_timers(base): - curr = base['active']['next']['node'] - curr = curr.address.cast(rbtree.rb_node_type.get_type().pointer()) + curr = base['active']['rb_root']['rb_leftmost'] idx = 0 while curr: yield print_timer(curr, idx) -- GitLab From 7362042f3556528e9e9b1eb5ce8d7a3a6331476b Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Tue, 21 Mar 2023 14:19:29 +0800 Subject: [PATCH 3342/5631] scripts/gdb: fix lx-timerlist for Python3 Below incompatibilities between Python2 and Python3 made lx-timerlist fail to run under Python3. o xrange() is replaced by range() in Python3 o bytes and str are different types in Python3 o the return value of Inferior.read_memory() is memoryview object in Python3 akpm: cc stable so that older kernels are properly debuggable under newer Python. Link: https://lkml.kernel.org/r/TYCP286MB2146EE1180A4D5176CBA8AB2C6819@TYCP286MB2146.JPNP286.PROD.OUTLOOK.COM Signed-off-by: Peng Liu Reviewed-by: Jan Kiszka Cc: Florian Fainelli Cc: Kieran Bingham Cc: Signed-off-by: Andrew Morton --- scripts/gdb/linux/timerlist.py | 4 +++- scripts/gdb/linux/utils.py | 5 ++++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index 44e39dc3eb64..8281da068c5b 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -72,7 +72,7 @@ def print_cpu(hrtimer_bases, cpu, max_clock_bases): ts = cpus.per_cpu(tick_sched_ptr, cpu) text = "cpu: {}\n".format(cpu) - for i in xrange(max_clock_bases): + for i in range(max_clock_bases): text += " clock {}:\n".format(i) text += print_base(cpu_base['clock_base'][i]) @@ -157,6 +157,8 @@ def pr_cpumask(mask): num_bytes = (nr_cpu_ids + 7) / 8 buf = utils.read_memoryview(inf, bits, num_bytes).tobytes() buf = binascii.b2a_hex(buf) + if type(buf) is not str: + buf=buf.decode() chunks = [] i = num_bytes diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 1553f68716cc..7f36aee32ac6 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -88,7 +88,10 @@ def get_target_endianness(): def read_memoryview(inf, start, length): - return memoryview(inf.read_memory(start, length)) + m = inf.read_memory(start, length) + if type(m) is memoryview: + return m + return memoryview(m) def read_u16(buffer, offset): -- GitLab From 8fc2a304f57cb304231a4b0564d5995b2dd04f63 Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Tue, 21 Mar 2023 14:20:04 +0800 Subject: [PATCH 3343/5631] scripts/gdb: fix lx-timerlist for HRTIMER_MAX_CLOCK_BASES printing HRTIMER_MAX_CLOCK_BASES is of enum type hrtimer_base_type. To print it as an integer, HRTIMER_MAX_CLOCK_BASES should be converted first. Link: https://lkml.kernel.org/r/TYCP286MB214640FF0E7F04AC3926A39EC6819@TYCP286MB2146.JPNP286.PROD.OUTLOOK.COM Signed-off-by: Peng Liu Reviewed-by: Jan Kiszka Cc: Florian Fainelli Cc: Kieran Bingham Signed-off-by: Andrew Morton --- scripts/gdb/linux/timerlist.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index 8281da068c5b..249f0e804b24 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -188,7 +188,8 @@ class LxTimerList(gdb.Command): max_clock_bases = gdb.parse_and_eval("HRTIMER_MAX_CLOCK_BASES") text = "Timer List Version: gdb scripts\n" - text += "HRTIMER_MAX_CLOCK_BASES: {}\n".format(max_clock_bases) + text += "HRTIMER_MAX_CLOCK_BASES: {}\n".format( + max_clock_bases.type.fields()[max_clock_bases].enumval) text += "now at {} nsecs\n".format(ktime_get()) for cpu in cpus.each_online_cpu(): -- GitLab From 0d828200ad56505a827610af876ca0b138b943a6 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 3 Apr 2023 18:23:46 +0200 Subject: [PATCH 3344/5631] docs: process: allow Closes tags with links MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since v6.3, checkpatch.pl now complains about the use of "Closes:" tags followed by a link [1]. It also complains if a "Reported-by:" tag is followed by a "Closes:" one [2]. As detailed in the first patch, this "Closes:" tag is used for a bit of time, mainly by DRM and MPTCP subsystems. It is used by some bug trackers to automate the closure of issues when a patch is accepted. It is even planned to use this tag with bugzilla.kernel.org [3]. The first patch updates the documentation to explain what is this "Closes:" tag and how/when to use it. The second patch modifies checkpatch.pl to stop complaining about it. The DRM maintainers and their mailing list have been added in Cc as they are probably interested by these two patches as well. [1] https://lore.kernel.org/all/3b036087d80b8c0e07a46a1dbaaf4ad0d018f8d5.1674217480.git.linux@leemhuis.info/ [2] https://lore.kernel.org/all/bb5dfd55ea2026303ab2296f4a6df3da7dd64006.1674217480.git.linux@leemhuis.info/ [3] https://lore.kernel.org/linux-doc/20230315181205.f3av7h6owqzzw64p@meerkat.local/ This patch (of 5): Making sure a bug tracker is up to date is not an easy task. For example, a first version of a patch fixing a tracked issue can be sent a long time after having created the issue. But also, it can take some time to have this patch accepted upstream in its final form. When it is done, someone -- probably not the person who accepted the patch -- has to remember about closing the corresponding issue. This task of closing and tracking the patch can be done automatically by bug trackers like GitLab [1], GitHub [2] and hopefully soon [3] bugzilla.kernel.org when the appropriated tag is used. The two first ones accept multiple tags but it is probably better to pick one. According to commit 76f381bb77a0 ("checkpatch: warn when unknown tags are used for links"), the "Closes" tag seems to have been used in the past by a few people and it is supported by popular bug trackers. Here is how it has been used in the past: $ git log --no-merges --format=email -P --grep='^Closes: http' | \ grep '^Closes: http' | cut -d/ -f3-5 | sort | uniq -c | sort -rn 391 gitlab.freedesktop.org/drm/intel 79 github.com/multipath-tcp/mptcp_net-next 8 gitlab.freedesktop.org/drm/msm 3 gitlab.freedesktop.org/drm/amd 2 gitlab.freedesktop.org/mesa/mesa 1 patchwork.freedesktop.org/series/73320 1 gitlab.freedesktop.org/lima/linux 1 gitlab.freedesktop.org/drm/nouveau 1 github.com/ClangBuiltLinux/linux 1 bugzilla.netfilter.org/show_bug.cgi?id=1579 1 bugzilla.netfilter.org/show_bug.cgi?id=1543 1 bugzilla.netfilter.org/show_bug.cgi?id=1436 1 bugzilla.netfilter.org/show_bug.cgi?id=1427 1 bugs.debian.org/625804 Likely here, the "Closes" tag was only properly used with GitLab and GitHub. We can also see that it has been used quite a few times (and still used recently) and this is then not a "random tag that makes no sense" like it was the case with "BugLink" recently [4]. It has also been misused but that was a long time ago, when it was common to use many different random tags. checkpatch.pl script should then stop complaining about this "Closes" tag. As suggested by Thorsten [5], if this tag is accepted, it should first be described in the documentation. This is what is done here in this patch. To avoid confusion, the "Closes" should be used with any public bug report. No need to check if the underlying bug tracker supports automations. Having this tag with any kind of public bug reports allows bots like regzbot to clearly identify patches fixing a specific bug and avoid false-positives, e.g. patches mentioning it is related to an issue but not fixing it. As suggested by Thorsten [6] again, if we follow the same logic, the "Closes" tag should then be used after a "Reported-by" one. Note that thanks to this "Closes" tag, the mentioned bug trackers can also locate where a patch has been applied in different branches and repositories. If only the "Link" tag is used, the tracking can also be done but the ticket will not be closed and a manual operation will be needed. Also, these bug trackers have some safeguards: the closure is only done if a commit having the "Closes:" tag is applied in a specific branch. It will then not be closed if a random commit having the same tag is published elsewhere. Also in case of closure, a notification is sent to the owners. Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-0-d26d1fa66f9f@tessares.net Link: https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#default-closing-pattern [1] Link: https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/using-keywords-in-issues-and-pull-requests [2] Link: https://lore.kernel.org/linux-doc/20230315181205.f3av7h6owqzzw64p@meerkat.local/ [3] Link: https://lore.kernel.org/all/CAHk-=wgs38ZrfPvy=nOwVkVzjpM3VFU1zobP37Fwd_h9iAD5JQ@mail.gmail.com/ [4] Link: https://lore.kernel.org/all/688cd6cb-90ab-6834-a6f5-97080e39ca8e@leemhuis.info/ [5] Link: https://lore.kernel.org/linux-doc/2194d19d-f195-1a1e-41fc-7827ae569351@leemhuis.info/ [6] Link: https://github.com/multipath-tcp/mptcp_net-next/issues/373 Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-1-d26d1fa66f9f@tessares.net Signed-off-by: Matthieu Baerts Suggested-by: Thorsten Leemhuis Acked-by: Konstantin Ryabitsev Acked-by: Joe Perches Cc: Andy Whitcroft Cc: Bagas Sanjaya Cc: Daniel Vetter Cc: David Airlie Cc: Dwaipayan Ray Cc: Jonathan Corbet Cc: Kai Wasserbäch Cc: Linus Torvalds Cc: Lukas Bulwahn Signed-off-by: Andrew Morton --- Documentation/process/5.Posting.rst | 22 +++++++++++++---- Documentation/process/submitting-patches.rst | 26 ++++++++++++++------ 2 files changed, 35 insertions(+), 13 deletions(-) diff --git a/Documentation/process/5.Posting.rst b/Documentation/process/5.Posting.rst index 7a670a075ab6..de4edd42d5c0 100644 --- a/Documentation/process/5.Posting.rst +++ b/Documentation/process/5.Posting.rst @@ -207,8 +207,8 @@ the patch:: Fixes: 1f2e3d4c5b6a ("The first line of the commit specified by the first 12 characters of its SHA-1 ID") Another tag is used for linking web pages with additional backgrounds or -details, for example a report about a bug fixed by the patch or a document -with a specification implemented by the patch:: +details, for example an earlier discussion which leads to the patch or a +document with a specification implemented by the patch:: Link: https://example.com/somewhere.html optional-other-stuff @@ -217,7 +217,17 @@ latest public review posting of the patch; often this is automatically done by tools like b4 or a git hook like the one described in 'Documentation/maintainer/configure-git.rst'. -A third kind of tag is used to document who was involved in the development of +If the URL points to a public bug report being fixed by the patch, use the +"Closes:" tag instead:: + + Closes: https://example.com/issues/1234 optional-other-stuff + +Some bug trackers have the ability to close issues automatically when a +commit with such a tag is applied. Some bots monitoring mailing lists can +also track such tags and take certain actions. Private bug trackers and +invalid URLs are forbidden. + +Another kind of tag is used to document who was involved in the development of the patch. Each of these uses this format:: tag: Full Name optional-other-stuff @@ -251,8 +261,10 @@ The tags in common use are: - Reported-by: names a user who reported a problem which is fixed by this patch; this tag is used to give credit to the (often underappreciated) people who test our code and let us know when things do not work - correctly. Note, this tag should be followed by a Link: tag pointing to the - report, unless the report is not available on the web. + correctly. Note, this tag should be followed by a Closes: tag pointing to + the report, unless the report is not available on the web. The Link: tag + can be used instead of Closes: if the patch fixes a part of the issue(s) + being reported. - Cc: the named person received a copy of the patch and had the opportunity to comment on it. diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index 828997bc9ff9..12d58ddc2b8a 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -113,11 +113,9 @@ there is no collision with your six-character ID now, that condition may change five years from now. If related discussions or any other background information behind the change -can be found on the web, add 'Link:' tags pointing to it. In case your patch -fixes a bug, for example, add a tag with a URL referencing the report in the -mailing list archives or a bug tracker; if the patch is a result of some -earlier mailing list discussion or something documented on the web, point to -it. +can be found on the web, add 'Link:' tags pointing to it. If the patch is a +result of some earlier mailing list discussions or something documented on the +web, point to it. When linking to mailing list archives, preferably use the lore.kernel.org message archiver service. To create the link URL, use the contents of the @@ -134,6 +132,16 @@ resources. In addition to giving a URL to a mailing list archive or bug, summarize the relevant points of the discussion that led to the patch as submitted. +In case your patch fixes a bug, use the 'Closes:' tag with a URL referencing +the report in the mailing list archives or a public bug tracker. For example:: + + Closes: https://example.com/issues/1234 + +Some bug trackers have the ability to close issues automatically when a +commit with such a tag is applied. Some bots monitoring mailing lists can +also track such tags and take certain actions. Private bug trackers and +invalid URLs are forbidden. + If your patch fixes a bug in a specific commit, e.g. you found an issue using ``git bisect``, please use the 'Fixes:' tag with the first 12 characters of the SHA-1 ID, and the one line summary. Do not split the tag across multiple @@ -498,9 +506,11 @@ Using Reported-by:, Tested-by:, Reviewed-by:, Suggested-by: and Fixes: The Reported-by tag gives credit to people who find bugs and report them and it hopefully inspires them to help us again in the future. The tag is intended for bugs; please do not use it to credit feature requests. The tag should be -followed by a Link: tag pointing to the report, unless the report is not -available on the web. Please note that if the bug was reported in private, then -ask for permission first before using the Reported-by tag. +followed by a Closes: tag pointing to the report, unless the report is not +available on the web. The Link: tag can be used instead of Closes: if the patch +fixes a part of the issue(s) being reported. Please note that if the bug was +reported in private, then ask for permission first before using the Reported-by +tag. A Tested-by: tag indicates that the patch has been successfully tested (in some environment) by the person named. This tag informs maintainers that -- GitLab From c917a872cee480d1fc8461da9be93e27e7977877 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 3 Apr 2023 18:23:47 +0200 Subject: [PATCH 3345/5631] checkpatch: don't print the next line if not defined MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When checking if "Reported-by" tag is followed by "Link:", there is no need to print the next line if there is no next line. While at it, also mention in this case that the "Link:" tag should be followed by a URL, similar to the next warning. By doing that, the code is now similar to what is done above when checking if the Co-developed-by tag is properly used. Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-2-d26d1fa66f9f@tessares.net Fixes: d7f1d71e5ef6 ("checkpatch: warn when Reported-by: is not followed by Link:") Signed-off-by: Matthieu Baerts Acked-by: Joe Perches Cc: Andy Whitcroft Cc: Bagas Sanjaya Cc: Daniel Vetter Cc: David Airlie Cc: Dwaipayan Ray Cc: Jonathan Corbet Cc: Kai Wasserbäch Cc: Konstantin Ryabitsev Cc: Linus Torvalds Cc: Lukas Bulwahn Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index c7cd0750b41e..8e22eb45ab2d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3162,7 +3162,7 @@ sub process { if ($sign_off =~ /^reported(?:|-and-tested)-by:$/i) { if (!defined $lines[$linenr]) { WARN("BAD_REPORTED_BY_LINK", - "Reported-by: should be immediately followed by Link: to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); + "Reported-by: should be immediately followed by Link: with a URL to the report\n" . $herecurr . "\n"); } elsif ($rawlines[$linenr] !~ m{^link:\s*https?://}i) { WARN("BAD_REPORTED_BY_LINK", "Reported-by: should be immediately followed by Link: with a URL to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); -- GitLab From f94e40ea272b9847833de1114677eb5ad8b12a0a Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 3 Apr 2023 18:23:48 +0200 Subject: [PATCH 3346/5631] checkpatch: use a list of "link" tags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The following commit will allow the use of a similar "link" tag. Because there is a possibility that other similar tags will be added in the future and to reduce the number of places where the code will be modified to allow this new tag, a list with all these "link" tags is now used. Two variables are created from it: one to search for such tags and one to print all tags in a warning message. Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-3-d26d1fa66f9f@tessares.net Signed-off-by: Matthieu Baerts Suggested-by: Joe Perches Acked-by: Joe Perches Cc: Andy Whitcroft Cc: Bagas Sanjaya Cc: Daniel Vetter Cc: David Airlie Cc: Dwaipayan Ray Cc: Jonathan Corbet Cc: Kai Wasserbäch Cc: Konstantin Ryabitsev Cc: Linus Torvalds Cc: Lukas Bulwahn Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8e22eb45ab2d..209898b8f0b6 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -620,6 +620,22 @@ our $signature_tags = qr{(?xi: Cc: )}; +our @link_tags = qw(Link); + +#Create a search and print patterns for all these strings to be used directly below +our $link_tags_search = ""; +our $link_tags_print = ""; +foreach my $entry (@link_tags) { + if ($link_tags_search ne "") { + $link_tags_search .= '|'; + $link_tags_print .= ' or '; + } + $entry .= ':'; + $link_tags_search .= $entry; + $link_tags_print .= "'$entry'"; +} +$link_tags_search = "(?:${link_tags_search})"; + our $tracing_logging_tags = qr{(?xi: [=-]*> | <[=-]* | @@ -3250,8 +3266,8 @@ sub process { # file delta changes $line =~ /^\s*(?:[\w\.\-\+]*\/)++[\w\.\-\+]+:/ || # filename then : - $line =~ /^\s*(?:Fixes:|Link:|$signature_tags)/i || - # A Fixes: or Link: line or signature tag line + $line =~ /^\s*(?:Fixes:|$link_tags_search|$signature_tags)/i || + # A Fixes:, link or signature tag line $commit_log_possible_stack_dump)) { WARN("COMMIT_LOG_LONG_LINE", "Possible unwrapped commit description (prefer a maximum 75 chars per line)\n" . $herecurr); @@ -3266,13 +3282,13 @@ sub process { # Check for odd tags before a URI/URL if ($in_commit_log && - $line =~ /^\s*(\w+):\s*http/ && $1 ne 'Link') { + $line =~ /^\s*(\w+:)\s*http/ && $1 !~ /^$link_tags_search$/) { if ($1 =~ /^v(?:ersion)?\d+/i) { WARN("COMMIT_LOG_VERSIONING", "Patch version information should be after the --- line\n" . $herecurr); } else { WARN("COMMIT_LOG_USE_LINK", - "Unknown link reference '$1:', use 'Link:' instead\n" . $herecurr); + "Unknown link reference '$1', use $link_tags_print instead\n" . $herecurr); } } -- GitLab From 44c31888098a590b8ec5ba37009e5a983f7c4b46 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 3 Apr 2023 18:23:49 +0200 Subject: [PATCH 3347/5631] checkpatch: allow Closes tags with links MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As a follow-up of a previous patch modifying the documentation to allow using the "Closes:" tag, checkpatch.pl is updated accordingly. checkpatch.pl now no longer complain when the "Closes:" tag is used by itself: commit 76f381bb77a0 ("checkpatch: warn when unknown tags are used for links") ... or after the "Reported-by:" tag: commit d7f1d71e5ef6 ("checkpatch: warn when Reported-by: is not followed by Link:") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/373 Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-4-d26d1fa66f9f@tessares.net Signed-off-by: Matthieu Baerts Acked-by: Joe Perches Cc: Andy Whitcroft Cc: Bagas Sanjaya Cc: Daniel Vetter Cc: David Airlie Cc: Dwaipayan Ray Cc: Jonathan Corbet Cc: Kai Wasserbäch Cc: Konstantin Ryabitsev Cc: Linus Torvalds Cc: Lukas Bulwahn Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 209898b8f0b6..922428ee3be5 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -620,7 +620,7 @@ our $signature_tags = qr{(?xi: Cc: )}; -our @link_tags = qw(Link); +our @link_tags = qw(Link Closes); #Create a search and print patterns for all these strings to be used directly below our $link_tags_search = ""; @@ -3174,14 +3174,14 @@ sub process { } } -# check if Reported-by: is followed by a Link: +# check if Reported-by: is followed by a Closes: tag if ($sign_off =~ /^reported(?:|-and-tested)-by:$/i) { if (!defined $lines[$linenr]) { WARN("BAD_REPORTED_BY_LINK", - "Reported-by: should be immediately followed by Link: with a URL to the report\n" . $herecurr . "\n"); - } elsif ($rawlines[$linenr] !~ m{^link:\s*https?://}i) { + "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . "\n"); + } elsif ($rawlines[$linenr] !~ m{^closes:\s*https?://}i) { WARN("BAD_REPORTED_BY_LINK", - "Reported-by: should be immediately followed by Link: with a URL to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); + "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); } } } -- GitLab From d6ccdd678e459fdcfe675a45c76b3f1a75b9a8e8 Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Mon, 3 Apr 2023 18:23:50 +0200 Subject: [PATCH 3348/5631] checkpatch: check for misuse of the link tags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "Link:" and "Closes:" tags have to be used with public URLs. It is difficult to make sure the link is public but at least we can verify the tag is followed by 'http(s)://'. With that, we avoid such a tag that is not allowed [1]: Closes: Now that we check the "link" tags are followed by a URL, we can relax the check linked to "Reported-by being followed by a link tag" to only verify if a "link" tag is present after the "Reported-by" one. Link: https://lore.kernel.org/linux-doc/CAHk-=wh0v1EeDV3v8TzK81nDC40=XuTdY2MCr0xy3m3FiBV3+Q@mail.gmail.com/ [1] Link: https://lkml.kernel.org/r/20230314-doc-checkpatch-closes-tag-v4-5-d26d1fa66f9f@tessares.net Signed-off-by: Matthieu Baerts Acked-by: Joe Perches Cc: Andy Whitcroft Cc: Bagas Sanjaya Cc: Daniel Vetter Cc: David Airlie Cc: Dwaipayan Ray Cc: Jonathan Corbet Cc: Kai Wasserbäch Cc: Konstantin Ryabitsev Cc: Linus Torvalds Cc: Lukas Bulwahn Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 922428ee3be5..3e6f5a8614d3 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3179,7 +3179,7 @@ sub process { if (!defined $lines[$linenr]) { WARN("BAD_REPORTED_BY_LINK", "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . "\n"); - } elsif ($rawlines[$linenr] !~ m{^closes:\s*https?://}i) { + } elsif ($rawlines[$linenr] !~ /^closes:\s*/i) { WARN("BAD_REPORTED_BY_LINK", "Reported-by: should be immediately followed by Closes: with a URL to the report\n" . $herecurr . $rawlines[$linenr] . "\n"); } @@ -3292,6 +3292,17 @@ sub process { } } +# Check for misuse of the link tags + if ($in_commit_log && + $line =~ /^\s*(\w+:)\s*(\S+)/) { + my $tag = $1; + my $value = $2; + if ($tag =~ /^$link_tags_search$/ && $value !~ m{^https?://}) { + WARN("COMMIT_LOG_WRONG_LINK", + "'$tag' should be followed by a public http(s) link\n" . $herecurr); + } + } + # Check for lines starting with a # if ($in_commit_log && $line =~ /^#/) { if (WARN("COMMIT_COMMENT_SYMBOL", -- GitLab From 1be2edb25c72c3fe1bf955694c5521b035fcb276 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 5 Apr 2023 16:34:52 +0200 Subject: [PATCH 3349/5631] proc/stat: remove arch_idle_time() The last (only) architecture specific arch_idle_time() implementation was removed with commit be76ea614460 ("s390/idle: remove arch_cpu_idle_time() and corresponding code"). Therefore remove the now dead code in fs/proc/stat.c as well. Link: https://lkml.kernel.org/r/20230405143452.2677172-1-hca@linux.ibm.com Signed-off-by: Heiko Carstens Cc: Alexey Dobriyan Signed-off-by: Andrew Morton --- fs/proc/stat.c | 26 -------------------------- 1 file changed, 26 deletions(-) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 4fb8729a68d4..da60956b2915 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -22,30 +22,6 @@ #define arch_irq_stat() 0 #endif -#ifdef arch_idle_time - -u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) -{ - u64 idle; - - idle = kcs->cpustat[CPUTIME_IDLE]; - if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) - idle += arch_idle_time(cpu); - return idle; -} - -static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) -{ - u64 iowait; - - iowait = kcs->cpustat[CPUTIME_IOWAIT]; - if (cpu_online(cpu) && nr_iowait_cpu(cpu)) - iowait += arch_idle_time(cpu); - return iowait; -} - -#else - u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -78,8 +54,6 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) return iowait; } -#endif - static void show_irq_gap(struct seq_file *p, unsigned int gap) { static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0"; -- GitLab From b0687c1119b4e8c88a651b6e876b7eae28d076e3 Mon Sep 17 00:00:00 2001 From: Noah Goldstein Date: Tue, 4 Apr 2023 17:13:51 -0500 Subject: [PATCH 3350/5631] lib/rbtree: use '+' instead of '|' for setting color. This has a slight benefit for x86 and has no effect on other targets. The benefit to x86 is it change the codegen for setting a node to block from `mov %r0, %r1; or $RB_BLACK, %r1` to `lea RB_BLACK(%r0), %r1` which saves an instructions. In all other cases it just replace ALU with ALU (or -> and) which perform the same on all machines I am aware of. Total instructions in rbtree.o: Before - 802 After - 782 so it saves about 20 `mov` instructions. Link: https://lkml.kernel.org/r/20230404221350.3806566-1-goldstein.w.n@gmail.com Signed-off-by: Noah Goldstein Cc: Michel Lespinasse Signed-off-by: Andrew Morton --- include/linux/rbtree_augmented.h | 4 ++-- lib/rbtree.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d1c53e9d8c75..7ee7ed5de722 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -156,13 +156,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { - rb->__rb_parent_color = rb_color(rb) | (unsigned long)p; + rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { - rb->__rb_parent_color = (unsigned long)p | color; + rb->__rb_parent_color = (unsigned long)p + color; } static inline void diff --git a/lib/rbtree.c b/lib/rbtree.c index c4ac5c2421f2..5114eda6309c 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -58,7 +58,7 @@ static inline void rb_set_black(struct rb_node *rb) { - rb->__rb_parent_color |= RB_BLACK; + rb->__rb_parent_color += RB_BLACK; } static inline struct rb_node *rb_red_parent(struct rb_node *red) -- GitLab From b7235d6bb516fed6d62d2c9e30e7123b6ce5124c Mon Sep 17 00:00:00 2001 From: Kieran Bingham Date: Tue, 4 Apr 2023 14:40:49 -0700 Subject: [PATCH 3351/5631] scripts/gdb: add a Radix Tree Parser Linux makes use of the Radix Tree data structure to store pointers indexed by integer values. This structure is utilised across many structures in the kernel including the IRQ descriptor tables, and several filesystems. This module provides a method to lookup values from a structure given its head node. Usage: The function lx_radix_tree_lookup, must be given a symbol of type struct radix_tree_root, and an index into that tree. The object returned is a generic integer value, and must be cast correctly to the type based on the storage in the data structure. For example, to print the irq descriptor in the sparse irq_desc_tree at index 18, try the following: (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18) This script previously existed under commit e127a73d41ac471d7e3ba950cf128f42d6ee3448 ("scripts/gdb: add a Radix Tree Parser") and was later reverted with b447e02548a3304c47b78b5e2d75a4312a8f17e1i (Revert "scripts/gdb: add a Radix Tree Parser"). This version expects the XArray based radix tree implementation and has been verified using QEMU/x86 on Linux 6.3-rc5. [f.fainelli@gmail.com: revive and update for xarray implementation] [f.fainelli@gmail.com: guard against a NULL node in the while loop] Link: https://lkml.kernel.org/r/20230405222743.1191674-1-f.fainelli@gmail.com Link: https://lkml.kernel.org/r/20230404214049.1016811-1-f.fainelli@gmail.com Signed-off-by: Kieran Bingham Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Signed-off-by: Andrew Morton --- scripts/gdb/linux/constants.py.in | 8 +++ scripts/gdb/linux/radixtree.py | 90 +++++++++++++++++++++++++++++++ scripts/gdb/vmlinux-gdb.py | 1 + 3 files changed, 99 insertions(+) create mode 100644 scripts/gdb/linux/radixtree.py diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 2efbec6b6b8d..6c886deb0b18 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -17,6 +17,7 @@ #include #include #include +#include #include /* We need to stringify expanded macros so that they can be parsed */ @@ -68,6 +69,13 @@ LX_VALUE(NR_CPUS) /* linux/of_fdt.h> */ LX_VALUE(OF_DT_HEADER) +/* linux/radix-tree.h */ +LX_GDBPARSED(RADIX_TREE_ENTRY_MASK) +LX_GDBPARSED(RADIX_TREE_INTERNAL_NODE) +LX_GDBPARSED(RADIX_TREE_MAP_SIZE) +LX_GDBPARSED(RADIX_TREE_MAP_SHIFT) +LX_GDBPARSED(RADIX_TREE_MAP_MASK) + /* Kernel Configs */ LX_CONFIG(CONFIG_GENERIC_CLOCKEVENTS) LX_CONFIG(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) diff --git a/scripts/gdb/linux/radixtree.py b/scripts/gdb/linux/radixtree.py new file mode 100644 index 000000000000..074543ac763d --- /dev/null +++ b/scripts/gdb/linux/radixtree.py @@ -0,0 +1,90 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Radix Tree Parser +# +# Copyright (c) 2016 Linaro Ltd +# Copyright (c) 2023 Broadcom +# +# Authors: +# Kieran Bingham +# Florian Fainelli + +import gdb + +from linux import utils +from linux import constants + +radix_tree_root_type = utils.CachedType("struct xarray") +radix_tree_node_type = utils.CachedType("struct xa_node") + +def is_internal_node(node): + long_type = utils.get_long_type() + return ((node.cast(long_type) & constants.LX_RADIX_TREE_ENTRY_MASK) == constants.LX_RADIX_TREE_INTERNAL_NODE) + +def entry_to_node(node): + long_type = utils.get_long_type() + node_type = node.type + indirect_ptr = node.cast(long_type) & ~constants.LX_RADIX_TREE_INTERNAL_NODE + return indirect_ptr.cast(radix_tree_node_type.get_type().pointer()) + +def node_maxindex(node): + return (constants.LX_RADIX_TREE_MAP_SIZE << node['shift']) - 1 + +def lookup(root, index): + if root.type == radix_tree_root_type.get_type().pointer(): + node = root.dereference() + elif root.type != radix_tree_root_type.get_type(): + raise gdb.GdbError("must be {} not {}" + .format(radix_tree_root_type.get_type(), root.type)) + + node = root['xa_head'] + if node == 0: + return None + + if not (is_internal_node(node)): + if (index > 0): + return None + return node + + node = entry_to_node(node) + maxindex = node_maxindex(node) + + if (index > maxindex): + return None + + shift = node['shift'] + constants.LX_RADIX_TREE_MAP_SHIFT + + while True: + offset = (index >> node['shift']) & constants.LX_RADIX_TREE_MAP_MASK + slot = node['slots'][offset] + + if slot == 0: + return None + + node = slot.cast(node.type.pointer()).dereference() + if node == 0: + return None + + shift -= constants.LX_RADIX_TREE_MAP_SHIFT + if (shift <= 0): + break + + return node + +class LxRadixTree(gdb.Function): + """ Lookup and return a node from a RadixTree. + +$lx_radix_tree_lookup(root_node [, index]): Return the node at the given index. +If index is omitted, the root node is dereference and returned.""" + + def __init__(self): + super(LxRadixTree, self).__init__("lx_radix_tree_lookup") + + def invoke(self, root, index=0): + result = lookup(root, index) + if result is None: + raise gdb.GdbError("No entry in tree at index {}".format(index)) + + return result + +LxRadixTree() diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 3a5b44cd6bfe..4a5056f2c247 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -38,3 +38,4 @@ else: import linux.genpd import linux.device import linux.mm + import linux.radixtree -- GitLab From 8af055ae25bff48f57227f5e3d48a4306f3dd1c4 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 6 Apr 2023 14:52:51 -0700 Subject: [PATCH 3352/5631] scripts/gdb: raise error with reduced debugging information If CONFIG_DEBUG_INFO_REDUCED is enabled in the kernel configuration, we will typically not be able to load vmlinux-gdb.py and will fail with: Traceback (most recent call last): File "/home/fainelli/work/buildroot/output/arm64/build/linux-custom/vmlinux-gdb.py", line 25, in import linux.utils File "/home/fainelli/work/buildroot/output/arm64/build/linux-custom/scripts/gdb/linux/utils.py", line 131, in atomic_long_counter_offset = atomic_long_type.get_type()['counter'].bitpos KeyError: 'counter' Rather be left wondering what is happening only to find out that reduced debug information is the cause, raise an eror. This was not typically a problem until e3c8d33e0d62 ("scripts/gdb: fix 'lx-dmesg' on 32 bits arch") but it has since then. Link: https://lkml.kernel.org/r/20230406215252.1580538-1-f.fainelli@gmail.com Fixes: e3c8d33e0d62 ("scripts/gdb: fix 'lx-dmesg' on 32 bits arch") Signed-off-by: Florian Fainelli Cc: Antonio Borneo Cc: Jan Kiszka Cc: John Ogness Cc: Kieran Bingham Cc: Petr Mladek Signed-off-by: Andrew Morton --- scripts/gdb/linux/constants.py.in | 2 ++ scripts/gdb/vmlinux-gdb.py | 5 ++++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 6c886deb0b18..e484e2e7e4d5 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -40,6 +40,8 @@ import gdb +LX_CONFIG(CONFIG_DEBUG_INFO_REDUCED) + /* linux/clk-provider.h */ if IS_BUILTIN(CONFIG_COMMON_CLK): LX_GDBPARSED(CLK_GET_RATE_NOCACHE) diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 4a5056f2c247..2f57adcf3dff 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -22,6 +22,10 @@ except: gdb.write("NOTE: gdb 7.2 or later required for Linux helper scripts to " "work.\n") else: + import linux.constants + if linux.constants.LX_CONFIG_DEBUG_INFO_REDUCED: + raise gdb.GdbError("Reduced debug information will prevent GDB " + "from having complete types.\n") import linux.utils import linux.symbols import linux.modules @@ -32,7 +36,6 @@ else: import linux.lists import linux.rbtree import linux.proc - import linux.constants import linux.timerlist import linux.clk import linux.genpd -- GitLab From b0969d7687a7aaa82dcf2d1f245ef699387886da Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 6 Apr 2023 15:04:51 -0700 Subject: [PATCH 3353/5631] scripts/gdb: print interrupts This GDB script prints the interrupts in the system in the same way that /proc/interrupts does. This does include the architecture specific part done by arch_show_interrupts() for x86, ARM, ARM64 and MIPS. Example output from an ARM64 system: (gdb) lx-interruptlist CPU0 CPU1 CPU2 CPU3 10: 3167 1225 1276 2629 GICv2 30 Level arch_timer 13: 0 0 0 0 GICv2 36 Level arm-pmu 14: 0 0 0 0 GICv2 37 Level arm-pmu 15: 0 0 0 0 GICv2 38 Level arm-pmu 16: 0 0 0 0 GICv2 39 Level arm-pmu 28: 0 0 0 0 interrupt-controller@8410640 5 Edge brcmstb-gpio-wake 30: 125 0 0 0 GICv2 128 Level ttyS0 31: 0 0 0 0 interrupt-controller@8416000 0 Level mspi_done 32: 0 0 0 0 interrupt-controller@8410640 3 Edge brcmstb-waketimer 33: 0 0 0 0 interrupt-controller@8418580 8 Edge brcmstb-waketimer-rtc 34: 872 0 0 0 GICv2 230 Level brcm_scmi@0 35: 0 0 0 0 interrupt-controller@8410640 10 Edge 8d0f200.usb-phy 37: 0 0 0 0 GICv2 97 Level PCIe PME 42: 0 0 0 0 GICv2 145 Level xhci-hcd:usb1 43: 94 0 0 0 GICv2 71 Level mmc1 44: 0 0 0 0 GICv2 70 Level mmc0 IPI0: 23 666 154 98 Rescheduling interrupts IPI1: 247 1053 1701 634 Function call interrupts IPI2: 0 0 0 0 CPU stop interrupts IPI3: 0 0 0 0 CPU stop (for crash dump) interrupts IPI4: 0 0 0 0 Timer broadcast interrupts IPI5: 7 9 5 0 IRQ work interrupts IPI6: 0 0 0 0 CPU wake-up interrupts ERR: 0 Link: https://lkml.kernel.org/r/20230406220451.1583239-1-f.fainelli@gmail.com Signed-off-by: Florian Fainelli Cc: Jan Kiszka Cc: Kieran Bingham Signed-off-by: Andrew Morton --- scripts/gdb/linux/constants.py.in | 14 ++ scripts/gdb/linux/interrupts.py | 232 ++++++++++++++++++++++++++++++ scripts/gdb/vmlinux-gdb.py | 1 + 3 files changed, 247 insertions(+) create mode 100644 scripts/gdb/linux/interrupts.py diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index e484e2e7e4d5..36fd2b145853 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -57,6 +58,10 @@ LX_VALUE(SB_NODIRATIME) /* linux/htimer.h */ LX_GDBPARSED(hrtimer_resolution) +/* linux/irq.h */ +LX_GDBPARSED(IRQD_LEVEL) +LX_GDBPARSED(IRQ_HIDDEN) + /* linux/mount.h */ LX_VALUE(MNT_NOSUID) LX_VALUE(MNT_NODEV) @@ -85,3 +90,12 @@ LX_CONFIG(CONFIG_HIGH_RES_TIMERS) LX_CONFIG(CONFIG_NR_CPUS) LX_CONFIG(CONFIG_OF) LX_CONFIG(CONFIG_TICK_ONESHOT) +LX_CONFIG(CONFIG_GENERIC_IRQ_SHOW_LEVEL) +LX_CONFIG(CONFIG_X86_LOCAL_APIC) +LX_CONFIG(CONFIG_SMP) +LX_CONFIG(CONFIG_X86_THERMAL_VECTOR) +LX_CONFIG(CONFIG_X86_MCE_THRESHOLD) +LX_CONFIG(CONFIG_X86_MCE_AMD) +LX_CONFIG(CONFIG_X86_MCE) +LX_CONFIG(CONFIG_X86_IO_APIC) +LX_CONFIG(CONFIG_HAVE_KVM) diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py new file mode 100644 index 000000000000..ef478e273791 --- /dev/null +++ b/scripts/gdb/linux/interrupts.py @@ -0,0 +1,232 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright 2023 Broadcom + +import gdb + +from linux import constants +from linux import cpus +from linux import utils +from linux import radixtree + +irq_desc_type = utils.CachedType("struct irq_desc") + +def irq_settings_is_hidden(desc): + return desc['status_use_accessors'] & constants.LX_IRQ_HIDDEN + +def irq_desc_is_chained(desc): + return desc['action'] and desc['action'] == gdb.parse_and_eval("&chained_action") + +def irqd_is_level(desc): + return desc['irq_data']['common']['state_use_accessors'] & constants.LX_IRQD_LEVEL + +def show_irq_desc(prec, irq): + text = "" + + desc = radixtree.lookup(gdb.parse_and_eval("&irq_desc_tree"), irq) + if desc is None: + return text + + desc = desc.cast(irq_desc_type.get_type()) + if desc is None: + return text + + if irq_settings_is_hidden(desc): + return text + + any_count = 0 + if desc['kstat_irqs']: + for cpu in cpus.each_online_cpu(): + any_count += cpus.per_cpu(desc['kstat_irqs'], cpu) + + if (desc['action'] == 0 or irq_desc_is_chained(desc)) and any_count == 0: + return text; + + text += "%*d: " % (prec, irq) + for cpu in cpus.each_online_cpu(): + if desc['kstat_irqs']: + count = cpus.per_cpu(desc['kstat_irqs'], cpu) + else: + count = 0 + text += "%10u" % (count) + + name = "None" + if desc['irq_data']['chip']: + chip = desc['irq_data']['chip'] + if chip['name']: + name = chip['name'].string() + else: + name = "-" + + text += " %8s" % (name) + + if desc['irq_data']['domain']: + text += " %*lu" % (prec, desc['irq_data']['hwirq']) + else: + text += " %*s" % (prec, "") + + if constants.LX_CONFIG_GENERIC_IRQ_SHOW_LEVEL: + text += " %-8s" % ("Level" if irqd_is_level(desc) else "Edge") + + if desc['name']: + text += "-%-8s" % (desc['name'].string()) + + """ Some toolchains may not be able to provide information about irqaction """ + try: + gdb.lookup_type("struct irqaction") + action = desc['action'] + if action is not None: + text += " %s" % (action['name'].string()) + while True: + action = action['next'] + if action is not None: + break + if action['name']: + text += ", %s" % (action['name'].string()) + except: + pass + + text += "\n" + + return text + +def show_irq_err_count(prec): + cnt = utils.gdb_eval_or_none("irq_err_count") + text = "" + if cnt is not None: + text += "%*s: %10u\n" % (prec, "ERR", cnt['counter']) + return text + +def x86_show_irqstat(prec, pfx, field, desc): + irq_stat = gdb.parse_and_eval("&irq_stat") + text = "%*s: " % (prec, pfx) + for cpu in cpus.each_online_cpu(): + stat = cpus.per_cpu(irq_stat, cpu) + text += "%10u " % (stat[field]) + text += " %s\n" % (desc) + return text + +def x86_show_mce(prec, var, pfx, desc): + pvar = gdb.parse_and_eval(var) + text = "%*s: " % (prec, pfx) + for cpu in cpus.each_online_cpu(): + text += "%10u " % (cpus.per_cpu(pvar, cpu)) + text += " %s\n" % (desc) + return text + +def x86_show_interupts(prec): + text = x86_show_irqstat(prec, "NMI", '__nmi_count', 'Non-maskable interrupts') + + if constants.LX_CONFIG_X86_LOCAL_APIC: + text += x86_show_irqstat(prec, "LOC", 'apic_timer_irqs', "Local timer interrupts") + text += x86_show_irqstat(prec, "SPU", 'irq_spurious_count', "Spurious interrupts") + text += x86_show_irqstat(prec, "PMI", 'apic_perf_irqs', "Performance monitoring interrupts") + text += x86_show_irqstat(prec, "IWI", 'apic_irq_work_irqs', "IRQ work interrupts") + text += x86_show_irqstat(prec, "RTR", 'icr_read_retry_count', "APIC ICR read retries") + if utils.gdb_eval_or_none("x86_platform_ipi_callback") is not None: + text += x86_show_irqstat(prec, "PLT", 'x86_platform_ipis', "Platform interrupts") + + if constants.LX_CONFIG_SMP: + text += x86_show_irqstat(prec, "RES", 'irq_resched_count', "Rescheduling interrupts") + text += x86_show_irqstat(prec, "CAL", 'irq_call_count', "Function call interrupts") + text += x86_show_irqstat(prec, "TLB", 'irq_tlb_count', "TLB shootdowns") + + if constants.LX_CONFIG_X86_THERMAL_VECTOR: + text += x86_show_irqstat(prec, "TRM", 'irq_thermal_count', "Thermal events interrupts") + + if constants.LX_CONFIG_X86_MCE_THRESHOLD: + text += x86_show_irqstat(prec, "THR", 'irq_threshold_count', "Threshold APIC interrupts") + + if constants.LX_CONFIG_X86_MCE_AMD: + text += x86_show_irqstat(prec, "DFR", 'irq_deferred_error_count', "Deferred Error APIC interrupts") + + if constants.LX_CONFIG_X86_MCE: + text += x86_show_mce(prec, "&mce_exception_count", "MCE", "Machine check exceptions") + text == x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls") + + text += show_irq_err_count(prec) + + if constants.LX_CONFIG_X86_IO_APIC: + cnt = utils.gdb_eval_or_none("irq_mis_count") + if cnt is not None: + text += "%*s: %10u\n" % (prec, "MIS", cnt['counter']) + + if constants.LX_CONFIG_HAVE_KVM: + text += x86_show_irqstat(prec, "PIN", 'kvm_posted_intr_ipis', 'Posted-interrupt notification event') + text += x86_show_irqstat(prec, "NPI", 'kvm_posted_intr_nested_ipis', 'Nested posted-interrupt event') + text += x86_show_irqstat(prec, "PIW", 'kvm_posted_intr_wakeup_ipis', 'Posted-interrupt wakeup event') + + return text + +def arm_common_show_interrupts(prec): + text = "" + nr_ipi = utils.gdb_eval_or_none("nr_ipi") + ipi_desc = utils.gdb_eval_or_none("ipi_desc") + ipi_types = utils.gdb_eval_or_none("ipi_types") + if nr_ipi is None or ipi_desc is None or ipi_types is None: + return text + + if prec >= 4: + sep = " " + else: + sep = "" + + for ipi in range(nr_ipi): + text += "%*s%u:%s" % (prec - 1, "IPI", ipi, sep) + desc = ipi_desc[ipi].cast(irq_desc_type.get_type().pointer()) + if desc == 0: + continue + for cpu in cpus.each_online_cpu(): + text += "%10u" % (cpus.per_cpu(desc['kstat_irqs'], cpu)) + text += " %s" % (ipi_types[ipi].string()) + text += "\n" + return text + +def aarch64_show_interrupts(prec): + text = arm_common_show_interrupts(prec) + text += "%*s: %10lu\n" % (prec, "ERR", gdb.parse_and_eval("irq_err_count")) + return text + +def arch_show_interrupts(prec): + text = "" + if utils.is_target_arch("x86"): + text += x86_show_interupts(prec) + elif utils.is_target_arch("aarch64"): + text += aarch64_show_interrupts(prec) + elif utils.is_target_arch("arm"): + text += arm_common_show_interrupts(prec) + elif utils.is_target_arch("mips"): + text += show_irq_err_count(prec) + else: + raise gdb.GdbError("Unsupported architecture: {}".format(target_arch)) + + return text + +class LxInterruptList(gdb.Command): + """Print /proc/interrupts""" + + def __init__(self): + super(LxInterruptList, self).__init__("lx-interruptlist", gdb.COMMAND_DATA) + + def invoke(self, arg, from_tty): + nr_irqs = gdb.parse_and_eval("nr_irqs") + prec = 3 + j = 1000 + while prec < 10 and j <= nr_irqs: + prec += 1 + j *= 10 + + gdb.write("%*s" % (prec + 8, "")) + for cpu in cpus.each_online_cpu(): + gdb.write("CPU%-8d" % cpu) + gdb.write("\n") + + if utils.gdb_eval_or_none("&irq_desc_tree") is None: + return + + for irq in range(nr_irqs): + gdb.write(show_irq_desc(prec, irq)) + gdb.write(arch_show_interrupts(prec)) + + +LxInterruptList() diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 2f57adcf3dff..2a72f91059b5 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -42,3 +42,4 @@ else: import linux.device import linux.mm import linux.radixtree + import linux.interrupts -- GitLab From 29692fc92c5b6a2c7cfe6f588ef68272e3343647 Mon Sep 17 00:00:00 2001 From: Amjad Ouled-Ameur Date: Thu, 6 Apr 2023 15:12:17 -0700 Subject: [PATCH 3354/5631] scripts/gdb: timerlist: convert int chunks to str join() expects strings but integers are given. Convert chunks list to strings before passing it to join() Link: https://lkml.kernel.org/r/20230406221217.1585486-4-f.fainelli@gmail.com Signed-off-by: Amjad Ouled-Ameur Signed-by: Florian Fainelli Tested-by: Florian Fainelli Cc: Jan Kiszka Signed-off-by: Andrew Morton --- scripts/gdb/linux/timerlist.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/gdb/linux/timerlist.py b/scripts/gdb/linux/timerlist.py index 249f0e804b24..64bc87191003 100644 --- a/scripts/gdb/linux/timerlist.py +++ b/scripts/gdb/linux/timerlist.py @@ -174,7 +174,7 @@ def pr_cpumask(mask): if 0 < extra <= 4: chunks[0] = chunks[0][0] # Cut off the first 0 - return "".join(chunks) + return "".join(str(chunks)) class LxTimerList(gdb.Command): -- GitLab From a3b2aeac9d154e5e15ddbf19de934c0c606b6acd Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Sat, 8 Apr 2023 17:28:35 +0800 Subject: [PATCH 3355/5631] delayacct: track delays from IRQ/SOFTIRQ Delay accounting does not track the delay of IRQ/SOFTIRQ. While IRQ/SOFTIRQ could have obvious impact on some workloads productivity, such as when workloads are running on system which is busy handling network IRQ/SOFTIRQ. Get the delay of IRQ/SOFTIRQ could help users to reduce such delay. Such as setting interrupt affinity or task affinity, using kernel thread for NAPI etc. This is inspired by "sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure"[1]. Also fix some code indent problems of older code. And update tools/accounting/getdelays.c: / # ./getdelays -p 156 -di print delayacct stats ON printing IO accounting PID 156 CPU count real total virtual total delay total delay average 15 15836008 16218149 275700790 18.380ms IO count delay total delay average 0 0 0.000ms SWAP count delay total delay average 0 0 0.000ms RECLAIM count delay total delay average 0 0 0.000ms THRASHING count delay total delay average 0 0 0.000ms COMPACT count delay total delay average 0 0 0.000ms WPCOPY count delay total delay average 36 7586118 0.211ms IRQ count delay total delay average 42 929161 0.022ms [1] commit 52b1364ba0b1("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure") Link: https://lkml.kernel.org/r/202304081728353557233@zte.com.cn Signed-off-by: Yang Yang Cc: Jiang Xuexin Cc: wangyong Cc: junhua huang Cc: Balbir Singh Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Juri Lelli Cc: Peter Zijlstra Signed-off-by: Andrew Morton --- Documentation/accounting/delay-accounting.rst | 7 +++-- include/linux/delayacct.h | 15 ++++++++++ include/uapi/linux/taskstats.h | 6 +++- kernel/delayacct.c | 14 +++++++++ kernel/sched/core.c | 1 + tools/accounting/getdelays.c | 30 +++++++++++-------- 6 files changed, 58 insertions(+), 15 deletions(-) diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index 79f537c9f160..f61c01fc376e 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -16,6 +16,7 @@ d) memory reclaim e) thrashing f) direct compact g) write-protect copy +h) IRQ/SOFTIRQ and makes these statistics available to userspace through the taskstats interface. @@ -49,7 +50,7 @@ this structure. See for a description of the fields pertaining to delay accounting. It will generally be in the form of counters returning the cumulative delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page -cache, direct compact, write-protect copy etc. +cache, direct compact, write-protect copy, IRQ/SOFTIRQ etc. Taking the difference of two successive readings of a given counter (say cpu_delay_total) for a task will give the delay @@ -118,7 +119,9 @@ Get sum of delays, since system boot, for all pids with tgid 5:: 0 0 0.000ms COMPACT count delay total delay average 0 0 0.000ms - WPCOPY count delay total delay average + WPCOPY count delay total delay average + 0 0 0.000ms + IRQ count delay total delay average 0 0 0.000ms Get IO accounting for pid 1, it works only with -p:: diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 0da97dba9ef8..6639f48dac36 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -48,10 +48,13 @@ struct task_delay_info { u64 wpcopy_start; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay; /* wait for IRQ/SOFTIRQ */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ u32 wpcopy_count; /* total count of write-protect copy */ + u32 irq_count; /* total count of IRQ/SOFTIRQ */ }; #endif @@ -81,6 +84,7 @@ extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); extern void __delayacct_wpcopy_start(void); extern void __delayacct_wpcopy_end(void); +extern void __delayacct_irq(struct task_struct *task, u32 delta); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -215,6 +219,15 @@ static inline void delayacct_wpcopy_end(void) __delayacct_wpcopy_end(); } +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (task->delays) + __delayacct_irq(task, delta); +} + #else static inline void delayacct_init(void) {} @@ -253,6 +266,8 @@ static inline void delayacct_wpcopy_start(void) {} static inline void delayacct_wpcopy_end(void) {} +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index a7f5b11a8f1b..b50b2eb257a0 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 13 +#define TASKSTATS_VERSION 14 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -198,6 +198,10 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; + + /* v14: Delay waiting for IRQ/SOFTIRQ */ + __u64 irq_count; + __u64 irq_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index e39cb696cfbd..6f0c358e73d8 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -179,12 +179,15 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay; d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp; + tmp = d->irq_delay_total + tsk->delays->irq_delay; + d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; d->compact_count += tsk->delays->compact_count; d->wpcopy_count += tsk->delays->wpcopy_count; + d->irq_count += tsk->delays->irq_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -274,3 +277,14 @@ void __delayacct_wpcopy_end(void) ¤t->delays->wpcopy_delay, ¤t->delays->wpcopy_count); } + +void __delayacct_irq(struct task_struct *task, u32 delta) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&task->delays->lock, flags); + task->delays->irq_delay += delta; + task->delays->irq_count++; + raw_spin_unlock_irqrestore(&task->delays->lock, flags); +} + diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0d18c3969f90..5473e831daf3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -704,6 +704,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; psi_account_irqtime(rq->curr, irq_delta); + delayacct_irq(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 23a15d8f2bf4..1334214546d7 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -198,17 +198,19 @@ static void print_delayacct(struct taskstats *t) printf("\n\nCPU %15s%15s%15s%15s%15s\n" " %15llu%15llu%15llu%15llu%15.3fms\n" "IO %15s%15s%15s\n" - " %15llu%15llu%15.3fms\n" + " %15llu%15llu%15.3fms\n" "SWAP %15s%15s%15s\n" - " %15llu%15llu%15.3fms\n" + " %15llu%15llu%15.3fms\n" "RECLAIM %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" + " %15llu%15llu%15.3fms\n" "THRASHING%12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" + " %15llu%15llu%15.3fms\n" "COMPACT %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n" + " %15llu%15llu%15.3fms\n" "WPCOPY %12s%15s%15s\n" - " %15llu%15llu%15.3fms\n", + " %15llu%15llu%15.3fms\n" + "IRQ %15s%15s%15s\n" + " %15llu%15llu%15.3fms\n", "count", "real total", "virtual total", "delay total", "delay average", (unsigned long long)t->cpu_count, @@ -219,27 +221,31 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->blkio_count, (unsigned long long)t->blkio_delay_total, - average_ms((double)t->blkio_delay_total, t->blkio_count), + average_ms((double)t->blkio_delay_total, t->blkio_count), "count", "delay total", "delay average", (unsigned long long)t->swapin_count, (unsigned long long)t->swapin_delay_total, - average_ms((double)t->swapin_delay_total, t->swapin_count), + average_ms((double)t->swapin_delay_total, t->swapin_count), "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms((double)t->freepages_delay_total, t->freepages_count), + average_ms((double)t->freepages_delay_total, t->freepages_count), "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms((double)t->thrashing_delay_total, t->thrashing_count), + average_ms((double)t->thrashing_delay_total, t->thrashing_count), "count", "delay total", "delay average", (unsigned long long)t->compact_count, (unsigned long long)t->compact_delay_total, - average_ms((double)t->compact_delay_total, t->compact_count), + average_ms((double)t->compact_delay_total, t->compact_count), "count", "delay total", "delay average", (unsigned long long)t->wpcopy_count, (unsigned long long)t->wpcopy_delay_total, - average_ms((double)t->wpcopy_delay_total, t->wpcopy_count)); + average_ms((double)t->wpcopy_delay_total, t->wpcopy_count), + "count", "delay total", "delay average", + (unsigned long long)t->irq_count, + (unsigned long long)t->irq_delay_total, + average_ms((double)t->irq_delay_total, t->irq_count)); } static void task_context_switch_counts(struct taskstats *t) -- GitLab From 31088f6f7906253ef4577f6a9b84e2d42447dba0 Mon Sep 17 00:00:00 2001 From: Kevin Brodsky Date: Tue, 11 Apr 2023 10:27:47 +0100 Subject: [PATCH 3356/5631] uapi/linux/const.h: prefer ISO-friendly __typeof__ typeof is (still) a GNU extension, which means that it cannot be used when building ISO C (e.g. -std=c99). It should therefore be avoided in uapi headers in favour of the ISO-friendly __typeof__. Unfortunately this issue could not be detected by CONFIG_UAPI_HEADER_TEST=y as the __ALIGN_KERNEL() macro is not expanded in any uapi header. This matters from a userspace perspective, not a kernel one. uapi headers and their contents are expected to be usable in a variety of situations, and in particular when building ISO C applications (with -std=c99 or similar). This particular problem can be reproduced by trying to use the __ALIGN_KERNEL macro directly in application code, say: #include int align(int x, int a) { return __KERNEL_ALIGN(x, a); } and trying to build that with -std=c99. Link: https://lkml.kernel.org/r/20230411092747.3759032-1-kevin.brodsky@arm.com Fixes: a79ff731a1b2 ("netfilter: xtables: make XT_ALIGN() usable in exported headers by exporting __ALIGN_KERNEL()") Signed-off-by: Kevin Brodsky Reported-by: Ruben Ayrapetyan Tested-by: Ruben Ayrapetyan Reviewed-by: Petr Vorel Tested-by: Petr Vorel Reviewed-by: Masahiro Yamada Cc: Sam Ravnborg Signed-off-by: Andrew Morton --- include/uapi/linux/const.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) -- GitLab From f4efbdaf59e959507a1a931ec4afecdfb09db76e Mon Sep 17 00:00:00 2001 From: Glenn Washburn Date: Tue, 28 Feb 2023 18:53:34 -0600 Subject: [PATCH 3357/5631] scripts/gdb: create linux/vfs.py for VFS related GDB helpers Patch series "GDB VFS utils". I've created a couple GDB convenience functions that I found useful when debugging some VFS issues and figure others might find them useful. For instance, they are useful in setting conditional breakpoints on VFS functions where you only care if the dentry path is a certain value. I took the opportunity to create a new "vfs" python module to give VFS related utilities a home. This patch (of 2): This will allow for more VFS specific GDB helpers to be collected in one place. Move utils.dentry_name into the vfs modules. Also a local variable in proc.py was changed from vfs to mnt to prevent a naming collision with the new vfs module. [akpm@linux-foundation.org: add SPDX-License-Identifier] Link: https://lkml.kernel.org/r/cover.1677631565.git.development@efficientek.com Link: https://lkml.kernel.org/r/7bba4c065a8c2c47f1fc5b03a7278005b04db251.1677631565.git.development@efficientek.com Signed-off-by: Glenn Washburn Cc: Alexander Viro Cc: Antonio Borneo Cc: Jan Kiszka Cc: John Ogness Cc: Kieran Bingham Cc: Petr Mladek Signed-off-by: Andrew Morton --- scripts/gdb/linux/proc.py | 16 +++++++++------- scripts/gdb/linux/utils.py | 8 -------- scripts/gdb/linux/vfs.py | 22 ++++++++++++++++++++++ scripts/gdb/vmlinux-gdb.py | 1 + 4 files changed, 32 insertions(+), 15 deletions(-) create mode 100644 scripts/gdb/linux/vfs.py diff --git a/scripts/gdb/linux/proc.py b/scripts/gdb/linux/proc.py index 09cd871925a5..43c687e7a69d 100644 --- a/scripts/gdb/linux/proc.py +++ b/scripts/gdb/linux/proc.py @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # gdb helper commands and functions for Linux kernel debugging # @@ -16,6 +17,7 @@ from linux import constants from linux import utils from linux import tasks from linux import lists +from linux import vfs from struct import * @@ -170,16 +172,16 @@ values of that process namespace""" gdb.write("{:^18} {:^15} {:>9} {} {} options\n".format( "mount", "super_block", "devname", "pathname", "fstype")) - for vfs in lists.list_for_each_entry(namespace['list'], + for mnt in lists.list_for_each_entry(namespace['list'], mount_ptr_type, "mnt_list"): - devname = vfs['mnt_devname'].string() + devname = mnt['mnt_devname'].string() devname = devname if devname else "none" pathname = "" - parent = vfs + parent = mnt while True: mntpoint = parent['mnt_mountpoint'] - pathname = utils.dentry_name(mntpoint) + pathname + pathname = vfs.dentry_name(mntpoint) + pathname if (parent == parent['mnt_parent']): break parent = parent['mnt_parent'] @@ -187,14 +189,14 @@ values of that process namespace""" if (pathname == ""): pathname = "/" - superblock = vfs['mnt']['mnt_sb'] + superblock = mnt['mnt']['mnt_sb'] fstype = superblock['s_type']['name'].string() s_flags = int(superblock['s_flags']) - m_flags = int(vfs['mnt']['mnt_flags']) + m_flags = int(mnt['mnt']['mnt_flags']) rd = "ro" if (s_flags & constants.LX_SB_RDONLY) else "rw" gdb.write("{} {} {} {} {} {}{}{} 0 0\n".format( - vfs.format_string(), superblock.format_string(), devname, + mnt.format_string(), superblock.format_string(), devname, pathname, fstype, rd, info_opts(FS_INFO, s_flags), info_opts(MNT_INFO, m_flags))) diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index 7f36aee32ac6..9f44df13761e 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -196,11 +196,3 @@ def gdb_eval_or_none(expresssion): return gdb.parse_and_eval(expresssion) except gdb.error: return None - - -def dentry_name(d): - parent = d['d_parent'] - if parent == d or parent == 0: - return "" - p = dentry_name(d['d_parent']) + "/" - return p + d['d_iname'].string() diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py new file mode 100644 index 000000000000..62d4f9ad7d79 --- /dev/null +++ b/scripts/gdb/linux/vfs.py @@ -0,0 +1,22 @@ +# +# gdb helper commands and functions for Linux kernel debugging +# +# VFS tools +# +# Copyright (c) 2023 Glenn Washburn +# Copyright (c) 2016 Linaro Ltd +# +# Authors: +# Glenn Washburn +# Kieran Bingham +# +# This work is licensed under the terms of the GNU GPL version 2. +# + + +def dentry_name(d): + parent = d['d_parent'] + if parent == d or parent == 0: + return "" + p = dentry_name(d['d_parent']) + "/" + return p + d['d_iname'].string() diff --git a/scripts/gdb/vmlinux-gdb.py b/scripts/gdb/vmlinux-gdb.py index 2a72f91059b5..2d32308c3f7a 100644 --- a/scripts/gdb/vmlinux-gdb.py +++ b/scripts/gdb/vmlinux-gdb.py @@ -40,6 +40,7 @@ else: import linux.clk import linux.genpd import linux.device + import linux.vfs import linux.mm import linux.radixtree import linux.interrupts -- GitLab From 5a10562bdeb58006de4b1cd5f671b7da26b20bb3 Mon Sep 17 00:00:00 2001 From: Glenn Washburn Date: Tue, 28 Feb 2023 18:53:35 -0600 Subject: [PATCH 3358/5631] scripts/gdb: add GDB convenience functions $lx_dentry_name() and $lx_i_dentry() $lx_dentry_name() generates a full VFS path from a given dentry pointer, and $lx_i_dentry() returns the dentry pointer associated with the given inode pointer, if there is one. Link: https://lkml.kernel.org/r/c9a5ad8efbfbd2cc6559e082734eed7628f43a16.1677631565.git.development@efficientek.com Signed-off-by: Glenn Washburn Cc: Alexander Viro Cc: Antonio Borneo Cc: Jan Kiszka Cc: John Ogness Cc: Kieran Bingham Cc: Petr Mladek Signed-off-by: Andrew Morton --- scripts/gdb/linux/vfs.py | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py index 62d4f9ad7d79..c77b9ce75f6d 100644 --- a/scripts/gdb/linux/vfs.py +++ b/scripts/gdb/linux/vfs.py @@ -13,6 +13,9 @@ # This work is licensed under the terms of the GNU GPL version 2. # +import gdb +from linux import utils + def dentry_name(d): parent = d['d_parent'] @@ -20,3 +23,37 @@ def dentry_name(d): return "" p = dentry_name(d['d_parent']) + "/" return p + d['d_iname'].string() + +class DentryName(gdb.Function): + """Return string of the full path of a dentry. + +$lx_dentry_name(PTR): Given PTR to a dentry struct, return a string +of the full path of the dentry.""" + + def __init__(self): + super(DentryName, self).__init__("lx_dentry_name") + + def invoke(self, dentry_ptr): + return dentry_name(dentry_ptr) + +DentryName() + + +dentry_type = utils.CachedType("struct dentry") + +class InodeDentry(gdb.Function): + """Return dentry pointer for inode. + +$lx_i_dentry(PTR): Given PTR to an inode struct, return a pointer to +the associated dentry struct, if there is one.""" + + def __init__(self): + super(InodeDentry, self).__init__("lx_i_dentry") + + def invoke(self, inode_ptr): + d_u = inode_ptr["i_dentry"]["first"] + if d_u == 0: + return "" + return utils.container_of(d_u, dentry_type.get_type().pointer(), "d_u") + +InodeDentry() -- GitLab From d4cb626d6f3e86121e08ce1492836f37f91858dd Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 11 Apr 2023 16:41:59 -0700 Subject: [PATCH 3359/5631] epoll: rename global epmutex As of 4f04cbaf128 ("epoll: use refcount to reduce ep_mutex contention"), this lock is now specific to nesting cases - inserting an epoll fd onto another epoll fd. Rename the lock to be less generic. Link: https://lkml.kernel.org/r/20230411234159.20421-1-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Cc: Paolo Abeni Cc: Eric Dumazet Signed-off-by: Andrew Morton --- fs/eventpoll.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 0ecdfd3043a3..98134f0af6a8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -43,7 +43,7 @@ * LOCKING: * There are three level of locking required by epoll : * - * 1) epmutex (mutex) + * 1) epnested_mutex (mutex) * 2) ep->mtx (mutex) * 3) ep->lock (rwlock) * @@ -57,8 +57,8 @@ * we need a lock that will allow us to sleep. This lock is a * mutex (ep->mtx). It is acquired during the event transfer loop, * during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file(). - * The epmutex is acquired when inserting an epoll fd onto another epoll - * fd. We do this so that we walk the epoll tree and ensure that this + * The epnested_mutex is acquired when inserting an epoll fd onto another + * epoll fd. We do this so that we walk the epoll tree and ensure that this * insertion does not create a cycle of epoll file descriptors, which * could lead to deadlock. We need a global mutex to prevent two * simultaneous inserts (A into B and B into A) from racing and @@ -74,9 +74,9 @@ * of epoll file descriptors, we use the current recursion depth as * the lockdep subkey. * It is possible to drop the "ep->mtx" and to use the global - * mutex "epmutex" (together with "ep->lock") to have it working, + * mutex "epnested_mutex" (together with "ep->lock") to have it working, * but having "ep->mtx" will make the interface more scalable. - * Events that require holding "epmutex" are very rare, while for + * Events that require holding "epnested_mutex" are very rare, while for * normal operations the epoll private "ep->mtx" will guarantee * a better scalability. */ @@ -248,7 +248,7 @@ struct ep_pqueue { static long max_user_watches __read_mostly; /* Used for cycles detection */ -static DEFINE_MUTEX(epmutex); +static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; @@ -263,7 +263,7 @@ static struct kmem_cache *pwq_cache __read_mostly; /* * List of files with newly added links, where we may need to limit the number - * of emanating paths. Protected by the epmutex. + * of emanating paths. Protected by the epnested_mutex. */ struct epitems_head { struct hlist_head epitems; @@ -1337,7 +1337,7 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) * is connected to n file sources. In this case each file source has 1 path * of length 1. Thus, the numbers below should be more than sufficient. These * path limits are enforced during an EPOLL_CTL_ADD operation, since a modify - * and delete can't add additional paths. Protected by the epmutex. + * and delete can't add additional paths. Protected by the epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count[PATH_ARR_SIZE]; @@ -2167,7 +2167,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when * the epoll file descriptor is attaching directly to a wakeup source, * unless the epoll file descriptor is nested. The purpose of taking the - * 'epmutex' on add is to prevent complex toplogies such as loops and + * 'epnested_mutex' on add is to prevent complex toplogies such as loops and * deep wakeup paths from forming in parallel through multiple * EPOLL_CTL_ADD operations. */ @@ -2178,7 +2178,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, if (READ_ONCE(f.file->f_ep) || ep->gen == loop_check_gen || is_file_epoll(tf.file)) { mutex_unlock(&ep->mtx); - error = epoll_mutex_lock(&epmutex, 0, nonblock); + error = epoll_mutex_lock(&epnested_mutex, 0, nonblock); if (error) goto error_tgt_fput; loop_check_gen++; @@ -2239,7 +2239,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, if (full_check) { clear_tfile_check_list(); loop_check_gen++; - mutex_unlock(&epmutex); + mutex_unlock(&epnested_mutex); } fdput(tf); -- GitLab From a04bb4c24a4846232a81047784d5eff2848e45bd Mon Sep 17 00:00:00 2001 From: Dmitry Rokosov Date: Tue, 4 Apr 2023 22:17:15 +0300 Subject: [PATCH 3360/5631] checkpatch: introduce proper bindings license check All headers from 'include/dt-bindings/' must be verified by checkpatch together with Documentation bindings, because all of them are part of the whole DT bindings system. The requirement is dual licensed and matching patterns: * Schemas: /GPL-2\.0(?:-only)? OR BSD-2-Clause/ * Headers: /GPL-2\.0(?:-only)? OR \S+/ Above patterns suggested by Rob at: https://lore.kernel.org/all/CAL_Jsq+-YJsBO+LuPJ=ZQ=eb-monrwzuCppvReH+af7hYZzNaQ@mail.gmail.com The issue was found during patch review: https://lore.kernel.org/all/20230313201259.19998-4-ddrokosov@sberdevices.ru/ Link: https://lkml.kernel.org/r/20230404191715.7319-1-ddrokosov@sberdevices.ru Signed-off-by: Dmitry Rokosov Reviewed-by: Rob Herring Cc: Andy Whitcroft Cc: Dwaipayan Ray Cc: Joe Perches Cc: Krzysztof Kozlowski Cc: Lukas Bulwahn Signed-off-by: Andrew Morton --- scripts/checkpatch.pl | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 3e6f5a8614d3..23bb211de4ce 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3763,7 +3763,7 @@ sub process { "'$spdx_license' is not supported in LICENSES/...\n" . $herecurr); } if ($realfile =~ m@^Documentation/devicetree/bindings/@ && - not $spdx_license =~ /GPL-2\.0.*BSD-2-Clause/) { + $spdx_license !~ /GPL-2\.0(?:-only)? OR BSD-2-Clause/) { my $msg_level = \&WARN; $msg_level = \&CHK if ($file); if (&{$msg_level}("SPDX_LICENSE_TAG", @@ -3773,6 +3773,11 @@ sub process { $fixed[$fixlinenr] =~ s/SPDX-License-Identifier: .*/SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)/; } } + if ($realfile =~ m@^include/dt-bindings/@ && + $spdx_license !~ /GPL-2\.0(?:-only)? OR \S+/) { + WARN("SPDX_LICENSE_TAG", + "DT binding headers should be licensed (GPL-2.0-only OR .*)\n" . $herecurr); + } } } } -- GitLab From cd834afa8ee3751644534be20d63cff445641f0f Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 16:22:39 +0530 Subject: [PATCH 3361/5631] selftests/mm: add support for arm64 platform on va switch Patch series "selftests/mm: Implement support for arm64 on va". The va_128TBswitch selftest is designed and implemented for PowerPC and x86 architectures which support a 128TB switch, up to 256TB of virtual address space and hugepage sizes of 16MB and 2MB respectively. Arm64 platforms on the other hand support a 256Tb switch, up to 4PB of virtual address space and a default hugepage size of 512MB when 64k pagesize is enabled. These architectural differences require introducing support for arm64 platforms, after which a more generic naming convention is suggested. The in code comments are amended to provide a more platform independent explanation of the working of the code and nr_hugepages are configured as required. Finally, the file running the testcase is modified in order to prevent skipping of hugetlb testcases of va_high_addr_switch. This patch (of 5): Arm64 platforms have the ability to support 64kb pagesize, 512MB default hugepage size and up to 4PB of virtual address space. The address switch occurs at 256TB as opposed to 128TB. Hence, the necessary support has been added. Link: https://lkml.kernel.org/r/20230323105243.2807166-1-chaitanyas.prakash@arm.com Link: https://lkml.kernel.org/r/20230323105243.2807166-2-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Shuah Khan Cc: Mark Rutland Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/va_128TBswitch.c | 26 +++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/va_128TBswitch.c b/tools/testing/selftests/mm/va_128TBswitch.c index 1d2068989883..6679213effed 100644 --- a/tools/testing/selftests/mm/va_128TBswitch.c +++ b/tools/testing/selftests/mm/va_128TBswitch.c @@ -17,6 +17,13 @@ * This will work with 16M and 2M hugepage size */ #define HUGETLB_SIZE (16 << 20) +#elif __aarch64__ +/* + * The default hugepage size for 64k base pagesize + * is 512MB. + */ +#define PAGE_SIZE (64 << 10) +#define HUGETLB_SIZE (512 << 20) #else #define PAGE_SIZE (4 << 10) #define HUGETLB_SIZE (2 << 20) @@ -26,9 +33,22 @@ * >= 128TB is the hint addr value we used to select * large address space. */ -#define ADDR_SWITCH_HINT (1UL << 47) + +#define ADDR_MARK_128TB (1UL << 47) +#define ADDR_MARK_256TB (1UL << 48) + +#define HIGH_ADDR_128TB ((void *) (1UL << 48)) +#define HIGH_ADDR_256TB ((void *) (1UL << 49)) + #define LOW_ADDR ((void *) (1UL << 30)) -#define HIGH_ADDR ((void *) (1UL << 48)) + +#ifdef __aarch64__ +#define ADDR_SWITCH_HINT ADDR_MARK_256TB +#define HIGH_ADDR HIGH_ADDR_256TB +#else +#define ADDR_SWITCH_HINT ADDR_MARK_128TB +#define HIGH_ADDR HIGH_ADDR_128TB +#endif struct testcase { void *addr; @@ -270,6 +290,8 @@ static int supported_arch(void) return 1; #elif defined(__x86_64__) return 1; +#elif defined(__aarch64__) + return 1; #else return 0; #endif -- GitLab From bbe168729d4ef8305f4e35c3bbe4711389ab8354 Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 16:22:40 +0530 Subject: [PATCH 3362/5631] selftests/mm: rename va_128TBswitch to va_high_addr_switch As the initial selftest only took into consideration PowperPC and x86 architectures, on adding support for arm64, a platform independent naming convention is chosen. Link: https://lkml.kernel.org/r/20230323105243.2807166-3-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Shuah Khan Cc: Mark Rutland Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 4 ++-- tools/testing/selftests/mm/run_vmtests.sh | 2 +- .../selftests/mm/{va_128TBswitch.c => va_high_addr_switch.c} | 0 .../mm/{va_128TBswitch.sh => va_high_addr_switch.sh} | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) rename tools/testing/selftests/mm/{va_128TBswitch.c => va_high_addr_switch.c} (100%) rename tools/testing/selftests/mm/{va_128TBswitch.sh => va_high_addr_switch.sh} (98%) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 63c03a6414fc..de32f7dafa5d 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -94,7 +94,7 @@ endif endif ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sh64 sparc64 x86_64)) -TEST_GEN_PROGS += va_128TBswitch +TEST_GEN_PROGS += va_high_addr_switch TEST_GEN_PROGS += virtual_address_range TEST_GEN_PROGS += write_to_hugetlbfs endif @@ -103,7 +103,7 @@ TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh -TEST_FILES += va_128TBswitch.sh +TEST_FILES += va_high_addr_switch.sh include ../lib.mk diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 438eb49567b6..83b59ae2d6f0 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -237,7 +237,7 @@ if [ $VADDR64 -ne 0 ]; then echo $prev_policy > /proc/sys/vm/overcommit_memory # virtual address 128TB switch test - CATEGORY="hugevm" run_test ./va_128TBswitch.sh + CATEGORY="hugevm" run_test ./va_high_addr_switch.sh fi # VADDR64 # vmalloc stability smoke test diff --git a/tools/testing/selftests/mm/va_128TBswitch.c b/tools/testing/selftests/mm/va_high_addr_switch.c similarity index 100% rename from tools/testing/selftests/mm/va_128TBswitch.c rename to tools/testing/selftests/mm/va_high_addr_switch.c diff --git a/tools/testing/selftests/mm/va_128TBswitch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh similarity index 98% rename from tools/testing/selftests/mm/va_128TBswitch.sh rename to tools/testing/selftests/mm/va_high_addr_switch.sh index 41580751dc51..3056788a27ac 100644 --- a/tools/testing/selftests/mm/va_128TBswitch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -51,4 +51,4 @@ check_test_requirements() } check_test_requirements -./va_128TBswitch +./va_high_addr_switch -- GitLab From c2af2a41905efcf662b53f280f8538e5c6bd05f4 Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 16:22:41 +0530 Subject: [PATCH 3363/5631] selftests/mm: add platform independent in code comments The in code comments for the selftest were made on the basis of 128TB switch, an architecture feature specific to PowerPc and x86 platforms. Keeping in mind the support added for arm64 platforms which implements a 256TB switch, a more generic explanation has been provided. Link: https://lkml.kernel.org/r/20230323105243.2807166-4-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Shuah Khan Cc: Mark Rutland Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/va_high_addr_switch.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index 6679213effed..7cfaf4a74c57 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -30,8 +30,8 @@ #endif /* - * >= 128TB is the hint addr value we used to select - * large address space. + * The hint addr value is used to allocate addresses + * beyond the high address switch boundary. */ #define ADDR_MARK_128TB (1UL << 47) @@ -73,9 +73,10 @@ static struct testcase testcases[] = { }, { /* - * We should never allocate at the requested address or above it - * The len cross the 128TB boundary. Without MAP_FIXED - * we will always search in the lower address space. + * Unless MAP_FIXED is specified, allocation based on hint + * addr is never at requested address or above it, which is + * beyond high address switch boundary in this case. Instead, + * a suitable allocation is found in lower address space. */ .addr = ((void *)(ADDR_SWITCH_HINT - PAGE_SIZE)), .size = 2 * PAGE_SIZE, @@ -85,8 +86,8 @@ static struct testcase testcases[] = { }, { /* - * Exact mapping at 128TB, the area is free we should get that - * even without MAP_FIXED. + * Exact mapping at high address switch boundary, should + * be obtained even without MAP_FIXED as area is free. */ .addr = ((void *)(ADDR_SWITCH_HINT)), .size = PAGE_SIZE, -- GitLab From 2f489e2e69463729eefc77da22c163ae63b48b74 Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 16:22:42 +0530 Subject: [PATCH 3364/5631] selftests/mm: configure nr_hugepages for arm64 Arm64 has a default hugepage size of 512MB when CONFIG_ARM64_64K_PAGES=y is enabled. While testing on arm64 platforms having up to 4PB of virtual address space, a minimum of 6 hugepages were required for all test cases to pass. Support for this requirement has been added. Link: https://lkml.kernel.org/r/20230323105243.2807166-5-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Shuah Khan Cc: Mark Rutland Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/run_vmtests.sh | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 83b59ae2d6f0..83c438a18aa7 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -236,8 +236,16 @@ if [ $VADDR64 -ne 0 ]; then CATEGORY="hugevm" run_test ./virtual_address_range echo $prev_policy > /proc/sys/vm/overcommit_memory - # virtual address 128TB switch test + # va high address boundary switch test + ARCH_ARM64="arm64" + prev_nr_hugepages=$(cat /proc/sys/vm/nr_hugepages) + if [ "$ARCH" == "$ARCH_ARM64" ]; then + echo 6 > /proc/sys/vm/nr_hugepages + fi CATEGORY="hugevm" run_test ./va_high_addr_switch.sh + if [ "$ARCH" == "$ARCH_ARM64" ]; then + echo $prev_nr_hugepages > /proc/sys/vm/nr_hugepages + fi fi # VADDR64 # vmalloc stability smoke test -- GitLab From c025da0f14e80028de93f72976a0d81dafc17d03 Mon Sep 17 00:00:00 2001 From: Chaitanya S Prakash Date: Thu, 23 Mar 2023 16:22:43 +0530 Subject: [PATCH 3365/5631] selftests/mm: run hugetlb testcases of va switch The va_high_addr_switch selftest is used to test mmap across 128TB boundary. It divides the selftest cases into two main categories on the basis of size. One set is used to create mappings that are multiples of PAGE_SIZE while the other creates mappings that are multiples of HUGETLB_SIZE. In order to run the hugetlb testcases the binary must be appended with "--run-hugetlb" but the file that used to run the test only invokes the binary, thereby completely skipping the hugetlb testcases. Hence, the required statement has been added. Link: https://lkml.kernel.org/r/20230323105243.2807166-6-chaitanyas.prakash@arm.com Signed-off-by: Chaitanya S Prakash Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Shuah Khan Cc: Mark Rutland Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/va_high_addr_switch.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 3056788a27ac..45cae7cab27e 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -52,3 +52,7 @@ check_test_requirements() check_test_requirements ./va_high_addr_switch + +# In order to run hugetlb testcases, "--run-hugetlb" must be appended +# to the binary. +./va_high_addr_switch --run-hugetlb -- GitLab From 3cc0c3738cde66a1eadf977fa7b2fdecbbcf5d4f Mon Sep 17 00:00:00 2001 From: Jeff Xu Date: Fri, 14 Apr 2023 02:28:01 +0000 Subject: [PATCH 3366/5631] selftests/memfd: fix test_sysctl sysctl memfd_noexec is pid-namespaced, non-reservable, and inherent to the child process. Move the inherence test from init ns to child ns, so init ns can keep the default value. Link: https://lkml.kernel.org/r/20230414022801.2545257-1-jeffxu@google.com Signed-off-by: Jeff Xu Reported-by: kernel test robot Link: https://lore.kernel.org/oe-lkp/202303312259.441e35db-yujie.liu@intel.com Tested-by: Yujie Liu Cc: Daniel Verkamp Cc: Dmitry Torokhov Cc: Hugh Dickins Cc: Jann Horn Cc: Jorge Lucangeli Obes Cc: Kees Cook Cc: Shuah Khan Signed-off-by: Andrew Morton --- tools/testing/selftests/memfd/memfd_test.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index ae71f15f790d..dba0e8ba002f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -43,6 +43,9 @@ */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; +static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)); +static int newpid_thread_fn2(void *arg); +static void join_newpid_thread(pid_t pid); static ssize_t fd2name(int fd, char *buf, size_t bufsize) { @@ -1111,6 +1114,7 @@ static void test_noexec_seal(void) static void test_sysctl_child(void) { int fd; + int pid; printf("%s sysctl 0\n", memfd_str); sysctl_assert_write("0"); @@ -1129,6 +1133,10 @@ static void test_sysctl_child(void) mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); + printf("%s child ns\n", memfd_str); + pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); + join_newpid_thread(pid); + mfd_assert_mode(fd, 0666); mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); @@ -1206,12 +1214,6 @@ static void test_sysctl(void) int pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn); join_newpid_thread(pid); - - printf("%s child ns\n", memfd_str); - sysctl_assert_write("1"); - - pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); - join_newpid_thread(pid); } /* -- GitLab From 4f775086a6eee07c6ae4be4734d736e13b537351 Mon Sep 17 00:00:00 2001 From: Longlong Xia Date: Fri, 14 Apr 2023 10:17:40 +0800 Subject: [PATCH 3367/5631] mm: memory-failure: refactor add_to_kill() Patch series "mm: ksm: support hwpoison for ksm page", v2. Currently, ksm does not support hwpoison. As ksm is being used more widely for deduplication at the system level, container level, and process level, supporting hwpoison for ksm has become increasingly important. However, ksm pages were not processed by hwpoison in 2009 [1]. The main method of implementation: 1. Refactor add_to_kill() and add new add_to_kill_*() to better accommodate the handling of different types of pages. 2. Add collect_procs_ksm() to collect processes when the error hit an ksm page. 3. Add task_in_to_kill_list() to avoid duplicate addition of tsk to the to_kill list. 4. Try_to_unmap ksm page (already supported). 5. Handle related processes such as sending SIGBUS. Tested with poisoning to ksm page from 1) different process 2) one process and with/without memory_failure_early_kill set, the processes are killed as expected with the patchset. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/ commit/?h=01e00f880ca700376e1845cf7a2524ebe68e47d6 This patch (of 2): The page_address_in_vma() is used to find the user virtual address of page in add_to_kill(), but it doesn't support ksm due to the ksm page->index unusable, add an ksm_addr as parameter to add_to_kill(), let's the caller to pass it, also rename the function to __add_to_kill(), and adding add_to_kill_anon_file() for handling anonymous pages and file pages, adding add_to_kill_fsdax() for handling fsdax pages. Link: https://lkml.kernel.org/r/20230414021741.2597273-1-xialonglong1@huawei.com Link: https://lkml.kernel.org/r/20230414021741.2597273-2-xialonglong1@huawei.com Signed-off-by: Longlong Xia Tested-by: Naoya Horiguchi Reviewed-by: Kefeng Wang Cc: Kefeng Wang Cc: Miaohe Lin Cc: Nanyong Sun Signed-off-by: Andrew Morton --- mm/memory-failure.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f761704d27d7..bb09999108ef 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -405,9 +405,9 @@ static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, * page->mapping are sufficient for mapping the page back to its * corresponding user virtual address. */ -static void add_to_kill(struct task_struct *tsk, struct page *p, - pgoff_t fsdax_pgoff, struct vm_area_struct *vma, - struct list_head *to_kill) +static void __add_to_kill(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr, pgoff_t fsdax_pgoff) { struct to_kill *tk; @@ -417,7 +417,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, return; } - tk->addr = page_address_in_vma(p, vma); + tk->addr = ksm_addr ? ksm_addr : page_address_in_vma(p, vma); if (is_zone_device_page(p)) { if (fsdax_pgoff != FSDAX_INVALID_PGOFF) tk->addr = vma_pgoff_address(fsdax_pgoff, 1, vma); @@ -448,6 +448,13 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, list_add_tail(&tk->nd, to_kill); } +static void add_to_kill_anon_file(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, + struct list_head *to_kill) +{ + __add_to_kill(tsk, p, vma, to_kill, 0, FSDAX_INVALID_PGOFF); +} + /* * Kill the processes that have been collected earlier. * @@ -573,7 +580,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, continue; if (!page_mapped_in_vma(page, vma)) continue; - add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, to_kill); + add_to_kill_anon_file(t, page, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -609,8 +616,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) - add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, - to_kill); + add_to_kill_anon_file(t, page, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -618,6 +624,13 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, } #ifdef CONFIG_FS_DAX +static void add_to_kill_fsdax(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, + struct list_head *to_kill, pgoff_t pgoff) +{ + __add_to_kill(tsk, p, vma, to_kill, 0, pgoff); +} + /* * Collect processes when the error hit a fsdax page. */ @@ -637,7 +650,7 @@ static void collect_procs_fsdax(struct page *page, continue; vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (vma->vm_mm == t->mm) - add_to_kill(t, page, pgoff, vma, to_kill); + add_to_kill_fsdax(t, page, vma, to_kill, pgoff); } } read_unlock(&tasklist_lock); -- GitLab From 4248d0083ec5817eebfb916c54950d100b3468ee Mon Sep 17 00:00:00 2001 From: Longlong Xia Date: Fri, 14 Apr 2023 10:17:41 +0800 Subject: [PATCH 3368/5631] mm: ksm: support hwpoison for ksm page hwpoison_user_mappings() is updated to support ksm pages, and add collect_procs_ksm() to collect processes when the error hit an ksm page. The difference from collect_procs_anon() is that it also needs to traverse the rmap-item list on the stable node of the ksm page. At the same time, add_to_kill_ksm() is added to handle ksm pages. And task_in_to_kill_list() is added to avoid duplicate addition of tsk to the to_kill list. This is because when scanning the list, if the pages that make up the ksm page all come from the same process, they may be added repeatedly. Link: https://lkml.kernel.org/r/20230414021741.2597273-3-xialonglong1@huawei.com Signed-off-by: Longlong Xia Tested-by: Naoya Horiguchi Reviewed-by: Kefeng Wang Cc: Miaohe Lin Cc: Nanyong Sun Signed-off-by: Andrew Morton --- include/linux/ksm.h | 11 +++++++++++ include/linux/mm.h | 7 +++++++ mm/ksm.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ mm/memory-failure.c | 34 +++++++++++++++++++++++++--------- 4 files changed, 88 insertions(+), 9 deletions(-) diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7e232ba59b86..d9e701326a88 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,6 +51,10 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); +#ifdef CONFIG_MEMORY_FAILURE +void collect_procs_ksm(struct page *page, struct list_head *to_kill, + int force_early); +#endif #else /* !CONFIG_KSM */ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) @@ -62,6 +66,13 @@ static inline void ksm_exit(struct mm_struct *mm) { } +#ifdef CONFIG_MEMORY_FAILURE +static inline void collect_procs_ksm(struct page *page, + struct list_head *to_kill, int force_early) +{ +} +#endif + #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) diff --git a/include/linux/mm.h b/include/linux/mm.h index 2772a1800cf3..37554b08bb28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3604,6 +3604,7 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -3624,6 +3625,12 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) +void add_to_kill_ksm(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr); +#endif + #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); diff --git a/mm/ksm.c b/mm/ksm.c index 290a3eb6d8de..37c63310bc4e 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2738,6 +2738,51 @@ void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) goto again; } +#ifdef CONFIG_MEMORY_FAILURE +/* + * Collect processes when the error hit an ksm page. + */ +void collect_procs_ksm(struct page *page, struct list_head *to_kill, + int force_early) +{ + struct ksm_stable_node *stable_node; + struct ksm_rmap_item *rmap_item; + struct folio *folio = page_folio(page); + struct vm_area_struct *vma; + struct task_struct *tsk; + + stable_node = folio_stable_node(folio); + if (!stable_node) + return; + hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) { + struct anon_vma *av = rmap_item->anon_vma; + + anon_vma_lock_read(av); + read_lock(&tasklist_lock); + for_each_process(tsk) { + struct anon_vma_chain *vmac; + unsigned long addr; + struct task_struct *t = + task_early_kill(tsk, force_early); + if (!t) + continue; + anon_vma_interval_tree_foreach(vmac, &av->rb_root, 0, + ULONG_MAX) + { + vma = vmac->vma; + if (vma->vm_mm == t->mm) { + addr = rmap_item->address & PAGE_MASK; + add_to_kill_ksm(t, page, vma, to_kill, + addr); + } + } + } + read_unlock(&tasklist_lock); + anon_vma_unlock_read(av); + } +} +#endif + #ifdef CONFIG_MIGRATION void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bb09999108ef..f69c410fb9f9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -455,6 +455,27 @@ static void add_to_kill_anon_file(struct task_struct *tsk, struct page *p, __add_to_kill(tsk, p, vma, to_kill, 0, FSDAX_INVALID_PGOFF); } +#ifdef CONFIG_KSM +static bool task_in_to_kill_list(struct list_head *to_kill, + struct task_struct *tsk) +{ + struct to_kill *tk, *next; + + list_for_each_entry_safe(tk, next, to_kill, nd) { + if (tk->tsk == tsk) + return true; + } + + return false; +} +void add_to_kill_ksm(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr) +{ + if (!task_in_to_kill_list(to_kill, tsk)) + __add_to_kill(tsk, p, vma, to_kill, ksm_addr, FSDAX_INVALID_PGOFF); +} +#endif /* * Kill the processes that have been collected earlier. * @@ -534,8 +555,7 @@ static struct task_struct *find_early_kill_thread(struct task_struct *tsk) * processes sharing the same error page,if the process is "early kill", the * task_struct of the dedicated thread will also be returned. */ -static struct task_struct *task_early_kill(struct task_struct *tsk, - int force_early) +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early) { if (!tsk->mm) return NULL; @@ -666,8 +686,9 @@ static void collect_procs(struct page *page, struct list_head *tokill, { if (!page->mapping) return; - - if (PageAnon(page)) + if (unlikely(PageKsm(page))) + collect_procs_ksm(page, tokill, force_early); + else if (PageAnon(page)) collect_procs_anon(page, tokill, force_early); else collect_procs_file(page, tokill, force_early); @@ -1522,11 +1543,6 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!page_mapped(hpage)) return true; - if (PageKsm(p)) { - pr_err("%#lx: can't handle KSM pages.\n", pfn); - return false; - } - if (PageSwapCache(p)) { pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); ttu &= ~TTU_HWPOISON; -- GitLab From 0c028b6a115e7f18480ec3f98ba7bccf011646ea Mon Sep 17 00:00:00 2001 From: John Garry Date: Sun, 16 Apr 2023 17:56:54 +0000 Subject: [PATCH 3369/5631] scsi: scsi_debug: Abort commands from scsi_debug_device_reset() Currently scsi_debug_device_reset() does not do much apart from setting the SDEBUG_UA_POR ("Power on, reset, or bus device reset") flag, which is eventually passed back to the SCSI midlayer later for a "unit attention" command. There is a report that blktest scsi/007 test fails due to commit 1107c7b24ee3 ("scsi: scsi_debug: Dynamically allocate sdebug_queued_cmd"). The problem there is that there are dangling scsi_debug queued commands when we attempt to remove the driver. scsi/007 test triggers SCSI EH and attempts to abort a timed-out command. Function scsi_debug_device_reset() is called as part of the EH, but does not deal with outstanding erroneous command. Prior to the named commit, removing the driver caused all dangling queued commands to be stopped - this should have not been necessary. Fix by aborting outstanding commands on a scsi_device basis from scsi_debug_device_reset(). Fixes: 1107c7b24ee3 ("scsi: scsi_debug: Dynamically allocate sdebug_queued_cmd") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-lkp/202304071111.e762fcbd-yujie.liu@intel.com Signed-off-by: John Garry Link: https://lore.kernel.org/r/20230416175654.159163-1-john.g.garry@oracle.com Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_debug.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index f4fa1035a191..8c58128ad32a 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5291,6 +5291,26 @@ static int scsi_debug_abort(struct scsi_cmnd *SCpnt) return SUCCESS; } +static bool scsi_debug_stop_all_queued_iter(struct request *rq, void *data) +{ + struct scsi_device *sdp = data; + struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); + + if (scmd->device == sdp) + scsi_debug_abort_cmnd(scmd); + + return true; +} + +/* Deletes (stops) timers or work queues of all queued commands per sdev */ +static void scsi_debug_stop_all_queued(struct scsi_device *sdp) +{ + struct Scsi_Host *shost = sdp->host; + + blk_mq_tagset_busy_iter(&shost->tag_set, + scsi_debug_stop_all_queued_iter, sdp); +} + static int scsi_debug_device_reset(struct scsi_cmnd *SCpnt) { struct scsi_device *sdp = SCpnt->device; @@ -5300,6 +5320,8 @@ static int scsi_debug_device_reset(struct scsi_cmnd *SCpnt) if (SDEBUG_OPT_ALL_NOISE & sdebug_opts) sdev_printk(KERN_INFO, sdp, "%s\n", __func__); + + scsi_debug_stop_all_queued(sdp); if (devip) set_bit(SDEBUG_UA_POR, devip->uas_bm); -- GitLab From 65a15d6560dff065339f6cac91de4beded60fe3f Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 12 Apr 2023 12:40:15 -0500 Subject: [PATCH 3370/5631] scsi: ipr: Remove SATA support Linux SATA support in ipr has always been limited to SATA DVDs. The last systems that had the option of including a SATA DVD was Power 8, which have been withdrawn for some time now, so this support can be removed. Signed-off-by: Brian King Link: https://lore.kernel.org/r/20230412174015.114764-1-brking@linux.vnet.ibm.com Reviewed-by: Damien Le Moal Reviewed-by: John Garry Signed-off-by: Martin K. Petersen --- drivers/scsi/Kconfig | 3 +- drivers/scsi/ipr.c | 774 +------------------------------------------ drivers/scsi/ipr.h | 64 ---- 3 files changed, 11 insertions(+), 830 deletions(-) diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 03e71e3d5e5b..0704809d9d99 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -971,8 +971,7 @@ config SCSI_SYM53C8XX_MMIO config SCSI_IPR tristate "IBM Power Linux RAID adapter support" - depends on PCI && SCSI && ATA - select SATA_HOST + depends on PCI && SCSI select FW_LOADER select IRQ_POLL select SGL_ALLOC diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 4d3c280a7360..d81189ba8773 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -58,7 +58,6 @@ #include #include #include -#include #include #include #include @@ -595,10 +594,6 @@ static void ipr_trc_hook(struct ipr_cmnd *ipr_cmd, trace_entry->time = jiffies; trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0]; trace_entry->type = type; - if (ipr_cmd->ioa_cfg->sis64) - trace_entry->ata_op_code = ipr_cmd->i.ata_ioadl.regs.command; - else - trace_entry->ata_op_code = ipr_cmd->ioarcb.u.add_data.u.regs.command; trace_entry->cmd_index = ipr_cmd->cmd_index & 0xff; trace_entry->res_handle = ipr_cmd->ioarcb.res_handle; trace_entry->u.add_data = add_data; @@ -636,7 +631,6 @@ static void ipr_reinit_ipr_cmnd(struct ipr_cmnd *ipr_cmd) { struct ipr_ioarcb *ioarcb = &ipr_cmd->ioarcb; struct ipr_ioasa *ioasa = &ipr_cmd->s.ioasa; - struct ipr_ioasa64 *ioasa64 = &ipr_cmd->s.ioasa64; dma_addr_t dma_addr = ipr_cmd->dma_addr; int hrrq_id; @@ -651,18 +645,15 @@ static void ipr_reinit_ipr_cmnd(struct ipr_cmnd *ipr_cmd) if (ipr_cmd->ioa_cfg->sis64) { ioarcb->u.sis64_addr_data.data_ioadl_addr = cpu_to_be64(dma_addr + offsetof(struct ipr_cmnd, i.ioadl64)); - ioasa64->u.gata.status = 0; } else { ioarcb->write_ioadl_addr = cpu_to_be32(dma_addr + offsetof(struct ipr_cmnd, i.ioadl)); ioarcb->read_ioadl_addr = ioarcb->write_ioadl_addr; - ioasa->u.gata.status = 0; } ioasa->hdr.ioasc = 0; ioasa->hdr.residual_data_len = 0; ipr_cmd->scsi_cmd = NULL; - ipr_cmd->qc = NULL; ipr_cmd->sense_buffer[0] = 0; ipr_cmd->dma_use_sg = 0; } @@ -806,48 +797,6 @@ static int ipr_set_pcix_cmd_reg(struct ipr_ioa_cfg *ioa_cfg) return 0; } -/** - * __ipr_sata_eh_done - done function for aborted SATA commands - * @ipr_cmd: ipr command struct - * - * This function is invoked for ops generated to SATA - * devices which are being aborted. - * - * Return value: - * none - **/ -static void __ipr_sata_eh_done(struct ipr_cmnd *ipr_cmd) -{ - struct ata_queued_cmd *qc = ipr_cmd->qc; - struct ipr_sata_port *sata_port = qc->ap->private_data; - - qc->err_mask |= AC_ERR_OTHER; - sata_port->ioasa.status |= ATA_BUSY; - ata_qc_complete(qc); - if (ipr_cmd->eh_comp) - complete(ipr_cmd->eh_comp); - list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); -} - -/** - * ipr_sata_eh_done - done function for aborted SATA commands - * @ipr_cmd: ipr command struct - * - * This function is invoked for ops generated to SATA - * devices which are being aborted. - * - * Return value: - * none - **/ -static void ipr_sata_eh_done(struct ipr_cmnd *ipr_cmd) -{ - struct ipr_hrr_queue *hrrq = ipr_cmd->hrrq; - unsigned long hrrq_flags; - - spin_lock_irqsave(&hrrq->_lock, hrrq_flags); - __ipr_sata_eh_done(ipr_cmd); - spin_unlock_irqrestore(&hrrq->_lock, hrrq_flags); -} /** * __ipr_scsi_eh_done - mid-layer done function for aborted ops @@ -920,8 +869,6 @@ static void ipr_fail_all_ops(struct ipr_ioa_cfg *ioa_cfg) if (ipr_cmd->scsi_cmd) ipr_cmd->done = __ipr_scsi_eh_done; - else if (ipr_cmd->qc) - ipr_cmd->done = __ipr_sata_eh_done; ipr_trc_hook(ipr_cmd, IPR_TRACE_FINISH, IPR_IOASC_IOA_WAS_RESET); @@ -1142,31 +1089,6 @@ static void ipr_send_hcam(struct ipr_ioa_cfg *ioa_cfg, u8 type, } } -/** - * ipr_update_ata_class - Update the ata class in the resource entry - * @res: resource entry struct - * @proto: cfgte device bus protocol value - * - * Return value: - * none - **/ -static void ipr_update_ata_class(struct ipr_resource_entry *res, unsigned int proto) -{ - switch (proto) { - case IPR_PROTO_SATA: - case IPR_PROTO_SAS_STP: - res->ata_class = ATA_DEV_ATA; - break; - case IPR_PROTO_SATA_ATAPI: - case IPR_PROTO_SAS_STP_ATAPI: - res->ata_class = ATA_DEV_ATAPI; - break; - default: - res->ata_class = ATA_DEV_UNKNOWN; - break; - } -} - /** * ipr_init_res_entry - Initialize a resource entry struct. * @res: resource entry struct @@ -1190,7 +1112,6 @@ static void ipr_init_res_entry(struct ipr_resource_entry *res, res->resetting_device = 0; res->reset_occurred = 0; res->sdev = NULL; - res->sata_port = NULL; if (ioa_cfg->sis64) { proto = cfgtew->u.cfgte64->proto; @@ -1252,8 +1173,6 @@ static void ipr_init_res_entry(struct ipr_resource_entry *res, res->lun = cfgtew->u.cfgte->res_addr.lun; res->lun_wwn = get_unaligned_be64(cfgtew->u.cfgte->lun_wwn); } - - ipr_update_ata_class(res, proto); } /** @@ -1383,8 +1302,6 @@ static void ipr_update_res_entry(struct ipr_resource_entry *res, proto = cfgtew->u.cfgte->proto; res->res_handle = cfgtew->u.cfgte->res_handle; } - - ipr_update_ata_class(res, proto); } /** @@ -4502,9 +4419,6 @@ static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth) spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); res = (struct ipr_resource_entry *)sdev->hostdata; - - if (res && ipr_is_gata(res) && qdepth > IPR_MAX_CMD_PER_ATA_LUN) - qdepth = IPR_MAX_CMD_PER_ATA_LUN; spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); scsi_change_queue_depth(sdev, qdepth); @@ -4799,68 +4713,13 @@ static struct ipr_resource_entry *ipr_find_starget(struct scsi_target *starget) return NULL; } -static struct ata_port_info sata_port_info; - -/** - * ipr_target_alloc - Prepare for commands to a SCSI target - * @starget: scsi target struct - * - * If the device is a SATA device, this function allocates an - * ATA port with libata, else it does nothing. - * - * Return value: - * 0 on success / non-0 on failure - **/ -static int ipr_target_alloc(struct scsi_target *starget) -{ - struct Scsi_Host *shost = dev_to_shost(&starget->dev); - struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) shost->hostdata; - struct ipr_sata_port *sata_port; - struct ata_port *ap; - struct ipr_resource_entry *res; - unsigned long lock_flags; - - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - res = ipr_find_starget(starget); - starget->hostdata = NULL; - - if (res && ipr_is_gata(res)) { - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - sata_port = kzalloc(sizeof(*sata_port), GFP_KERNEL); - if (!sata_port) - return -ENOMEM; - - ap = ata_sas_port_alloc(&ioa_cfg->ata_host, &sata_port_info, shost); - if (ap) { - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - sata_port->ioa_cfg = ioa_cfg; - sata_port->ap = ap; - sata_port->res = res; - - res->sata_port = sata_port; - ap->private_data = sata_port; - starget->hostdata = sata_port; - } else { - kfree(sata_port); - return -ENOMEM; - } - } - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - - return 0; -} - /** * ipr_target_destroy - Destroy a SCSI target * @starget: scsi target struct * - * If the device was a SATA device, this function frees the libata - * ATA port, else it does nothing. - * **/ static void ipr_target_destroy(struct scsi_target *starget) { - struct ipr_sata_port *sata_port = starget->hostdata; struct Scsi_Host *shost = dev_to_shost(&starget->dev); struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) shost->hostdata; @@ -4874,12 +4733,6 @@ static void ipr_target_destroy(struct scsi_target *starget) clear_bit(starget->id, ioa_cfg->target_ids); } } - - if (sata_port) { - starget->hostdata = NULL; - ata_sas_port_destroy(sata_port->ap); - kfree(sata_port); - } } /** @@ -4922,11 +4775,8 @@ static void ipr_slave_destroy(struct scsi_device *sdev) spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); res = (struct ipr_resource_entry *) sdev->hostdata; if (res) { - if (res->sata_port) - res->sata_port->ap->link.device[0].class = ATA_DEV_NONE; sdev->hostdata = NULL; res->sdev = NULL; - res->sata_port = NULL; } spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); } @@ -4944,7 +4794,6 @@ static int ipr_slave_configure(struct scsi_device *sdev) { struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *) sdev->host->hostdata; struct ipr_resource_entry *res; - struct ata_port *ap = NULL; unsigned long lock_flags = 0; char buffer[IPR_MAX_RES_PATH_LENGTH]; @@ -4964,15 +4813,8 @@ static int ipr_slave_configure(struct scsi_device *sdev) IPR_VSET_RW_TIMEOUT); blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS); } - if (ipr_is_gata(res) && res->sata_port) - ap = res->sata_port->ap; spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - if (ap) { - scsi_change_queue_depth(sdev, IPR_MAX_CMD_PER_ATA_LUN); - ata_sas_slave_configure(sdev, ap); - } - if (ioa_cfg->sis64) sdev_printk(KERN_INFO, sdev, "Resource path: %s\n", ipr_format_res_path(ioa_cfg, @@ -4983,37 +4825,6 @@ static int ipr_slave_configure(struct scsi_device *sdev) return 0; } -/** - * ipr_ata_slave_alloc - Prepare for commands to a SATA device - * @sdev: scsi device struct - * - * This function initializes an ATA port so that future commands - * sent through queuecommand will work. - * - * Return value: - * 0 on success - **/ -static int ipr_ata_slave_alloc(struct scsi_device *sdev) -{ - struct ipr_sata_port *sata_port = NULL; - int rc = -ENXIO; - - ENTER; - if (sdev->sdev_target) - sata_port = sdev->sdev_target->hostdata; - if (sata_port) { - rc = ata_sas_port_init(sata_port->ap); - if (rc == 0) - rc = ata_sas_sync_probe(sata_port->ap); - } - - if (rc) - ipr_slave_destroy(sdev); - - LEAVE; - return rc; -} - /** * ipr_slave_alloc - Prepare for commands to a device. * @sdev: scsi device struct @@ -5047,8 +4858,10 @@ static int ipr_slave_alloc(struct scsi_device *sdev) res->needs_sync_complete = 1; rc = 0; if (ipr_is_gata(res)) { + sdev_printk(KERN_ERR, sdev, "SATA devices are no longer " + "supported by this driver. Skipping device.\n"); spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - return ipr_ata_slave_alloc(sdev); + return -ENXIO; } } @@ -5091,23 +4904,6 @@ static bool ipr_cmnd_is_free(struct ipr_cmnd *ipr_cmd) return false; } -/** - * ipr_match_res - Match function for specified resource entry - * @ipr_cmd: ipr command struct - * @resource: resource entry to match - * - * Returns: - * 1 if command matches sdev / 0 if command does not match sdev - **/ -static int ipr_match_res(struct ipr_cmnd *ipr_cmd, void *resource) -{ - struct ipr_resource_entry *res = resource; - - if (res && ipr_cmd->ioarcb.res_handle == res->res_handle) - return 1; - return 0; -} - /** * ipr_wait_for_ops - Wait for matching commands to complete * @ioa_cfg: ioa config struct @@ -5220,8 +5016,7 @@ static int ipr_eh_host_reset(struct scsi_cmnd *cmd) * This function issues a device reset to the affected device. * If the device is a SCSI device, a LUN reset will be sent * to the device first. If that does not work, a target reset - * will be sent. If the device is a SATA device, a PHY reset will - * be sent. + * will be sent. * * Return value: * 0 on success / non-zero on failure @@ -5232,7 +5027,6 @@ static int ipr_device_reset(struct ipr_ioa_cfg *ioa_cfg, struct ipr_cmnd *ipr_cmd; struct ipr_ioarcb *ioarcb; struct ipr_cmd_pkt *cmd_pkt; - struct ipr_ioarcb_ata_regs *regs; u32 ioasc; ENTER; @@ -5240,86 +5034,21 @@ static int ipr_device_reset(struct ipr_ioa_cfg *ioa_cfg, ioarcb = &ipr_cmd->ioarcb; cmd_pkt = &ioarcb->cmd_pkt; - if (ipr_cmd->ioa_cfg->sis64) { - regs = &ipr_cmd->i.ata_ioadl.regs; + if (ipr_cmd->ioa_cfg->sis64) ioarcb->add_cmd_parms_offset = cpu_to_be16(sizeof(*ioarcb)); - } else - regs = &ioarcb->u.add_data.u.regs; ioarcb->res_handle = res->res_handle; cmd_pkt->request_type = IPR_RQTYPE_IOACMD; cmd_pkt->cdb[0] = IPR_RESET_DEVICE; - if (ipr_is_gata(res)) { - cmd_pkt->cdb[2] = IPR_ATA_PHY_RESET; - ioarcb->add_cmd_parms_len = cpu_to_be16(sizeof(regs->flags)); - regs->flags |= IPR_ATA_FLAG_STATUS_ON_GOOD_COMPLETION; - } ipr_send_blocking_cmd(ipr_cmd, ipr_timeout, IPR_DEVICE_RESET_TIMEOUT); ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc); list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); - if (ipr_is_gata(res) && res->sata_port && ioasc != IPR_IOASC_IOA_WAS_RESET) { - if (ipr_cmd->ioa_cfg->sis64) - memcpy(&res->sata_port->ioasa, &ipr_cmd->s.ioasa64.u.gata, - sizeof(struct ipr_ioasa_gata)); - else - memcpy(&res->sata_port->ioasa, &ipr_cmd->s.ioasa.u.gata, - sizeof(struct ipr_ioasa_gata)); - } LEAVE; return IPR_IOASC_SENSE_KEY(ioasc) ? -EIO : 0; } -/** - * ipr_sata_reset - Reset the SATA port - * @link: SATA link to reset - * @classes: class of the attached device - * @deadline: unused - * - * This function issues a SATA phy reset to the affected ATA link. - * - * Return value: - * 0 on success / non-zero on failure - **/ -static int ipr_sata_reset(struct ata_link *link, unsigned int *classes, - unsigned long deadline) -{ - struct ipr_sata_port *sata_port = link->ap->private_data; - struct ipr_ioa_cfg *ioa_cfg = sata_port->ioa_cfg; - struct ipr_resource_entry *res; - unsigned long lock_flags = 0; - int rc = -ENXIO, ret; - - ENTER; - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - while (ioa_cfg->in_reset_reload) { - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - } - - res = sata_port->res; - if (res) { - rc = ipr_device_reset(ioa_cfg, res); - *classes = res->ata_class; - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - - ret = ipr_wait_for_ops(ioa_cfg, res, ipr_match_res); - if (ret != SUCCESS) { - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - ipr_initiate_ioa_reset(ioa_cfg, IPR_SHUTDOWN_ABBREV); - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - - wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); - } - } else - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - - LEAVE; - return rc; -} - /** * __ipr_eh_dev_reset - Reset the device * @scsi_cmd: scsi command struct @@ -5333,12 +5062,9 @@ static int ipr_sata_reset(struct ata_link *link, unsigned int *classes, **/ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd) { - struct ipr_cmnd *ipr_cmd; struct ipr_ioa_cfg *ioa_cfg; struct ipr_resource_entry *res; - struct ata_port *ap; - int rc = 0, i; - struct ipr_hrr_queue *hrrq; + int rc = 0; ENTER; ioa_cfg = (struct ipr_ioa_cfg *) scsi_cmd->device->host->hostdata; @@ -5354,36 +5080,10 @@ static int __ipr_eh_dev_reset(struct scsi_cmnd *scsi_cmd) if (ioa_cfg->hrrq[IPR_INIT_HRRQ].ioa_is_dead) return FAILED; - for_each_hrrq(hrrq, ioa_cfg) { - spin_lock(&hrrq->_lock); - for (i = hrrq->min_cmd_id; i <= hrrq->max_cmd_id; i++) { - ipr_cmd = ioa_cfg->ipr_cmnd_list[i]; - - if (ipr_cmd->ioarcb.res_handle == res->res_handle) { - if (!ipr_cmd->qc) - continue; - if (ipr_cmnd_is_free(ipr_cmd)) - continue; - - ipr_cmd->done = ipr_sata_eh_done; - if (!(ipr_cmd->qc->flags & ATA_QCFLAG_EH)) { - ipr_cmd->qc->err_mask |= AC_ERR_TIMEOUT; - ipr_cmd->qc->flags |= ATA_QCFLAG_EH; - } - } - } - spin_unlock(&hrrq->_lock); - } res->resetting_device = 1; scmd_printk(KERN_ERR, scsi_cmd, "Resetting device\n"); - if (ipr_is_gata(res) && res->sata_port) { - ap = res->sata_port->ap; - spin_unlock_irq(scsi_cmd->device->host->host_lock); - ata_std_error_handler(ap); - spin_lock_irq(scsi_cmd->device->host->host_lock); - } else - rc = ipr_device_reset(ioa_cfg, res); + rc = ipr_device_reset(ioa_cfg, res); res->resetting_device = 0; res->reset_occurred = 1; @@ -5407,12 +5107,8 @@ static int ipr_eh_dev_reset(struct scsi_cmnd *cmd) rc = __ipr_eh_dev_reset(cmd); spin_unlock_irq(cmd->device->host->host_lock); - if (rc == SUCCESS) { - if (ipr_is_gata(res) && res->sata_port) - rc = ipr_wait_for_ops(ioa_cfg, res, ipr_match_res); - else - rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun); - } + if (rc == SUCCESS) + rc = ipr_wait_for_ops(ioa_cfg, cmd->device, ipr_match_lun); return rc; } @@ -6564,7 +6260,7 @@ static int ipr_queuecommand(struct Scsi_Host *shost, struct ipr_resource_entry *res; struct ipr_ioarcb *ioarcb; struct ipr_cmnd *ipr_cmd; - unsigned long hrrq_flags, lock_flags; + unsigned long hrrq_flags; int rc; struct ipr_hrr_queue *hrrq; int hrrq_id; @@ -6574,13 +6270,6 @@ static int ipr_queuecommand(struct Scsi_Host *shost, scsi_cmd->result = (DID_OK << 16); res = scsi_cmd->device->hostdata; - if (ipr_is_gata(res) && res->sata_port) { - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - rc = ata_sas_queuecmd(scsi_cmd, res->sata_port->ap); - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - return rc; - } - hrrq_id = ipr_get_hrrq_index(ioa_cfg); hrrq = &ioa_cfg->hrrq[hrrq_id]; @@ -6690,30 +6379,6 @@ static int ipr_queuecommand(struct Scsi_Host *shost, return 0; } -/** - * ipr_ioctl - IOCTL handler - * @sdev: scsi device struct - * @cmd: IOCTL cmd - * @arg: IOCTL arg - * - * Return value: - * 0 on success / other on failure - **/ -static int ipr_ioctl(struct scsi_device *sdev, unsigned int cmd, - void __user *arg) -{ - struct ipr_resource_entry *res; - - res = (struct ipr_resource_entry *)sdev->hostdata; - if (res && ipr_is_gata(res)) { - if (cmd == HDIO_GET_IDENTITY) - return -ENOTTY; - return ata_sas_scsi_ioctl(res->sata_port->ap, sdev, cmd, arg); - } - - return -EINVAL; -} - /** * ipr_ioa_info - Get information about the card/driver * @host: scsi host struct @@ -6740,12 +6405,7 @@ static const struct scsi_host_template driver_template = { .module = THIS_MODULE, .name = "IPR", .info = ipr_ioa_info, - .ioctl = ipr_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = ipr_ioctl, -#endif .queuecommand = ipr_queuecommand, - .dma_need_drain = ata_scsi_dma_need_drain, .eh_abort_handler = ipr_eh_abort, .eh_device_reset_handler = ipr_eh_dev_reset, .eh_host_reset_handler = ipr_eh_host_reset, @@ -6753,7 +6413,6 @@ static const struct scsi_host_template driver_template = { .slave_configure = ipr_slave_configure, .slave_destroy = ipr_slave_destroy, .scan_finished = ipr_scan_finished, - .target_alloc = ipr_target_alloc, .target_destroy = ipr_target_destroy, .change_queue_depth = ipr_change_queue_depth, .bios_param = ipr_biosparam, @@ -6767,418 +6426,6 @@ static const struct scsi_host_template driver_template = { .proc_name = IPR_NAME, }; -/** - * ipr_ata_phy_reset - libata phy_reset handler - * @ap: ata port to reset - * - **/ -static void ipr_ata_phy_reset(struct ata_port *ap) -{ - unsigned long flags; - struct ipr_sata_port *sata_port = ap->private_data; - struct ipr_resource_entry *res = sata_port->res; - struct ipr_ioa_cfg *ioa_cfg = sata_port->ioa_cfg; - int rc; - - ENTER; - spin_lock_irqsave(ioa_cfg->host->host_lock, flags); - while (ioa_cfg->in_reset_reload) { - spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); - wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); - spin_lock_irqsave(ioa_cfg->host->host_lock, flags); - } - - if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) - goto out_unlock; - - rc = ipr_device_reset(ioa_cfg, res); - - if (rc) { - ap->link.device[0].class = ATA_DEV_NONE; - goto out_unlock; - } - - ap->link.device[0].class = res->ata_class; - if (ap->link.device[0].class == ATA_DEV_UNKNOWN) - ap->link.device[0].class = ATA_DEV_NONE; - -out_unlock: - spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); - LEAVE; -} - -/** - * ipr_ata_post_internal - Cleanup after an internal command - * @qc: ATA queued command - * - * Return value: - * none - **/ -static void ipr_ata_post_internal(struct ata_queued_cmd *qc) -{ - struct ipr_sata_port *sata_port = qc->ap->private_data; - struct ipr_ioa_cfg *ioa_cfg = sata_port->ioa_cfg; - struct ipr_cmnd *ipr_cmd; - struct ipr_hrr_queue *hrrq; - unsigned long flags; - - spin_lock_irqsave(ioa_cfg->host->host_lock, flags); - while (ioa_cfg->in_reset_reload) { - spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); - wait_event(ioa_cfg->reset_wait_q, !ioa_cfg->in_reset_reload); - spin_lock_irqsave(ioa_cfg->host->host_lock, flags); - } - - for_each_hrrq(hrrq, ioa_cfg) { - spin_lock(&hrrq->_lock); - list_for_each_entry(ipr_cmd, &hrrq->hrrq_pending_q, queue) { - if (ipr_cmd->qc == qc) { - ipr_device_reset(ioa_cfg, sata_port->res); - break; - } - } - spin_unlock(&hrrq->_lock); - } - spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); -} - -/** - * ipr_copy_sata_tf - Copy a SATA taskfile to an IOA data structure - * @regs: destination - * @tf: source ATA taskfile - * - * Return value: - * none - **/ -static void ipr_copy_sata_tf(struct ipr_ioarcb_ata_regs *regs, - struct ata_taskfile *tf) -{ - regs->feature = tf->feature; - regs->nsect = tf->nsect; - regs->lbal = tf->lbal; - regs->lbam = tf->lbam; - regs->lbah = tf->lbah; - regs->device = tf->device; - regs->command = tf->command; - regs->hob_feature = tf->hob_feature; - regs->hob_nsect = tf->hob_nsect; - regs->hob_lbal = tf->hob_lbal; - regs->hob_lbam = tf->hob_lbam; - regs->hob_lbah = tf->hob_lbah; - regs->ctl = tf->ctl; -} - -/** - * ipr_sata_done - done function for SATA commands - * @ipr_cmd: ipr command struct - * - * This function is invoked by the interrupt handler for - * ops generated by the SCSI mid-layer to SATA devices - * - * Return value: - * none - **/ -static void ipr_sata_done(struct ipr_cmnd *ipr_cmd) -{ - struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg; - struct ata_queued_cmd *qc = ipr_cmd->qc; - struct ipr_sata_port *sata_port = qc->ap->private_data; - struct ipr_resource_entry *res = sata_port->res; - u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc); - - spin_lock(&ipr_cmd->hrrq->_lock); - if (ipr_cmd->ioa_cfg->sis64) - memcpy(&sata_port->ioasa, &ipr_cmd->s.ioasa64.u.gata, - sizeof(struct ipr_ioasa_gata)); - else - memcpy(&sata_port->ioasa, &ipr_cmd->s.ioasa.u.gata, - sizeof(struct ipr_ioasa_gata)); - ipr_dump_ioasa(ioa_cfg, ipr_cmd, res); - - if (be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc_specific) & IPR_ATA_DEVICE_WAS_RESET) - scsi_report_device_reset(ioa_cfg->host, res->bus, res->target); - - if (IPR_IOASC_SENSE_KEY(ioasc) > RECOVERED_ERROR) - qc->err_mask |= __ac_err_mask(sata_port->ioasa.status); - else - qc->err_mask |= ac_err_mask(sata_port->ioasa.status); - list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); - spin_unlock(&ipr_cmd->hrrq->_lock); - ata_qc_complete(qc); -} - -/** - * ipr_build_ata_ioadl64 - Build an ATA scatter/gather list - * @ipr_cmd: ipr command struct - * @qc: ATA queued command - * - **/ -static void ipr_build_ata_ioadl64(struct ipr_cmnd *ipr_cmd, - struct ata_queued_cmd *qc) -{ - u32 ioadl_flags = 0; - struct ipr_ioarcb *ioarcb = &ipr_cmd->ioarcb; - struct ipr_ioadl64_desc *ioadl64 = ipr_cmd->i.ata_ioadl.ioadl64; - struct ipr_ioadl64_desc *last_ioadl64 = NULL; - int len = qc->nbytes; - struct scatterlist *sg; - unsigned int si; - dma_addr_t dma_addr = ipr_cmd->dma_addr; - - if (len == 0) - return; - - if (qc->dma_dir == DMA_TO_DEVICE) { - ioadl_flags = IPR_IOADL_FLAGS_WRITE; - ioarcb->cmd_pkt.flags_hi |= IPR_FLAGS_HI_WRITE_NOT_READ; - } else if (qc->dma_dir == DMA_FROM_DEVICE) - ioadl_flags = IPR_IOADL_FLAGS_READ; - - ioarcb->data_transfer_length = cpu_to_be32(len); - ioarcb->ioadl_len = - cpu_to_be32(sizeof(struct ipr_ioadl64_desc) * ipr_cmd->dma_use_sg); - ioarcb->u.sis64_addr_data.data_ioadl_addr = - cpu_to_be64(dma_addr + offsetof(struct ipr_cmnd, i.ata_ioadl.ioadl64)); - - for_each_sg(qc->sg, sg, qc->n_elem, si) { - ioadl64->flags = cpu_to_be32(ioadl_flags); - ioadl64->data_len = cpu_to_be32(sg_dma_len(sg)); - ioadl64->address = cpu_to_be64(sg_dma_address(sg)); - - last_ioadl64 = ioadl64; - ioadl64++; - } - - if (likely(last_ioadl64)) - last_ioadl64->flags |= cpu_to_be32(IPR_IOADL_FLAGS_LAST); -} - -/** - * ipr_build_ata_ioadl - Build an ATA scatter/gather list - * @ipr_cmd: ipr command struct - * @qc: ATA queued command - * - **/ -static void ipr_build_ata_ioadl(struct ipr_cmnd *ipr_cmd, - struct ata_queued_cmd *qc) -{ - u32 ioadl_flags = 0; - struct ipr_ioarcb *ioarcb = &ipr_cmd->ioarcb; - struct ipr_ioadl_desc *ioadl = ipr_cmd->i.ioadl; - struct ipr_ioadl_desc *last_ioadl = NULL; - int len = qc->nbytes; - struct scatterlist *sg; - unsigned int si; - - if (len == 0) - return; - - if (qc->dma_dir == DMA_TO_DEVICE) { - ioadl_flags = IPR_IOADL_FLAGS_WRITE; - ioarcb->cmd_pkt.flags_hi |= IPR_FLAGS_HI_WRITE_NOT_READ; - ioarcb->data_transfer_length = cpu_to_be32(len); - ioarcb->ioadl_len = - cpu_to_be32(sizeof(struct ipr_ioadl_desc) * ipr_cmd->dma_use_sg); - } else if (qc->dma_dir == DMA_FROM_DEVICE) { - ioadl_flags = IPR_IOADL_FLAGS_READ; - ioarcb->read_data_transfer_length = cpu_to_be32(len); - ioarcb->read_ioadl_len = - cpu_to_be32(sizeof(struct ipr_ioadl_desc) * ipr_cmd->dma_use_sg); - } - - for_each_sg(qc->sg, sg, qc->n_elem, si) { - ioadl->flags_and_data_len = cpu_to_be32(ioadl_flags | sg_dma_len(sg)); - ioadl->address = cpu_to_be32(sg_dma_address(sg)); - - last_ioadl = ioadl; - ioadl++; - } - - if (likely(last_ioadl)) - last_ioadl->flags_and_data_len |= cpu_to_be32(IPR_IOADL_FLAGS_LAST); -} - -/** - * ipr_qc_defer - Get a free ipr_cmd - * @qc: queued command - * - * Return value: - * 0 if success - **/ -static int ipr_qc_defer(struct ata_queued_cmd *qc) -{ - struct ata_port *ap = qc->ap; - struct ipr_sata_port *sata_port = ap->private_data; - struct ipr_ioa_cfg *ioa_cfg = sata_port->ioa_cfg; - struct ipr_cmnd *ipr_cmd; - struct ipr_hrr_queue *hrrq; - int hrrq_id; - - hrrq_id = ipr_get_hrrq_index(ioa_cfg); - hrrq = &ioa_cfg->hrrq[hrrq_id]; - - qc->lldd_task = NULL; - spin_lock(&hrrq->_lock); - if (unlikely(hrrq->ioa_is_dead)) { - spin_unlock(&hrrq->_lock); - return 0; - } - - if (unlikely(!hrrq->allow_cmds)) { - spin_unlock(&hrrq->_lock); - return ATA_DEFER_LINK; - } - - ipr_cmd = __ipr_get_free_ipr_cmnd(hrrq); - if (ipr_cmd == NULL) { - spin_unlock(&hrrq->_lock); - return ATA_DEFER_LINK; - } - - qc->lldd_task = ipr_cmd; - spin_unlock(&hrrq->_lock); - return 0; -} - -/** - * ipr_qc_issue - Issue a SATA qc to a device - * @qc: queued command - * - * Return value: - * 0 if success - **/ -static unsigned int ipr_qc_issue(struct ata_queued_cmd *qc) -{ - struct ata_port *ap = qc->ap; - struct ipr_sata_port *sata_port = ap->private_data; - struct ipr_resource_entry *res = sata_port->res; - struct ipr_ioa_cfg *ioa_cfg = sata_port->ioa_cfg; - struct ipr_cmnd *ipr_cmd; - struct ipr_ioarcb *ioarcb; - struct ipr_ioarcb_ata_regs *regs; - - if (qc->lldd_task == NULL) - ipr_qc_defer(qc); - - ipr_cmd = qc->lldd_task; - if (ipr_cmd == NULL) - return AC_ERR_SYSTEM; - - qc->lldd_task = NULL; - spin_lock(&ipr_cmd->hrrq->_lock); - if (unlikely(!ipr_cmd->hrrq->allow_cmds || - ipr_cmd->hrrq->ioa_is_dead)) { - list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); - spin_unlock(&ipr_cmd->hrrq->_lock); - return AC_ERR_SYSTEM; - } - - ipr_init_ipr_cmnd(ipr_cmd, ipr_lock_and_done); - ioarcb = &ipr_cmd->ioarcb; - - if (ioa_cfg->sis64) { - regs = &ipr_cmd->i.ata_ioadl.regs; - ioarcb->add_cmd_parms_offset = cpu_to_be16(sizeof(*ioarcb)); - } else - regs = &ioarcb->u.add_data.u.regs; - - memset(regs, 0, sizeof(*regs)); - ioarcb->add_cmd_parms_len = cpu_to_be16(sizeof(*regs)); - - list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_pending_q); - ipr_cmd->qc = qc; - ipr_cmd->done = ipr_sata_done; - ipr_cmd->ioarcb.res_handle = res->res_handle; - ioarcb->cmd_pkt.request_type = IPR_RQTYPE_ATA_PASSTHRU; - ioarcb->cmd_pkt.flags_hi |= IPR_FLAGS_HI_NO_LINK_DESC; - ioarcb->cmd_pkt.flags_hi |= IPR_FLAGS_HI_NO_ULEN_CHK; - ipr_cmd->dma_use_sg = qc->n_elem; - - if (ioa_cfg->sis64) - ipr_build_ata_ioadl64(ipr_cmd, qc); - else - ipr_build_ata_ioadl(ipr_cmd, qc); - - regs->flags |= IPR_ATA_FLAG_STATUS_ON_GOOD_COMPLETION; - ipr_copy_sata_tf(regs, &qc->tf); - memcpy(ioarcb->cmd_pkt.cdb, qc->cdb, IPR_MAX_CDB_LEN); - ipr_trc_hook(ipr_cmd, IPR_TRACE_START, IPR_GET_RES_PHYS_LOC(res)); - - switch (qc->tf.protocol) { - case ATA_PROT_NODATA: - case ATA_PROT_PIO: - break; - - case ATA_PROT_DMA: - regs->flags |= IPR_ATA_FLAG_XFER_TYPE_DMA; - break; - - case ATAPI_PROT_PIO: - case ATAPI_PROT_NODATA: - regs->flags |= IPR_ATA_FLAG_PACKET_CMD; - break; - - case ATAPI_PROT_DMA: - regs->flags |= IPR_ATA_FLAG_PACKET_CMD; - regs->flags |= IPR_ATA_FLAG_XFER_TYPE_DMA; - break; - - default: - WARN_ON(1); - spin_unlock(&ipr_cmd->hrrq->_lock); - return AC_ERR_INVALID; - } - - ipr_send_command(ipr_cmd); - spin_unlock(&ipr_cmd->hrrq->_lock); - - return 0; -} - -/** - * ipr_qc_fill_rtf - Read result TF - * @qc: ATA queued command - **/ -static void ipr_qc_fill_rtf(struct ata_queued_cmd *qc) -{ - struct ipr_sata_port *sata_port = qc->ap->private_data; - struct ipr_ioasa_gata *g = &sata_port->ioasa; - struct ata_taskfile *tf = &qc->result_tf; - - tf->feature = g->error; - tf->nsect = g->nsect; - tf->lbal = g->lbal; - tf->lbam = g->lbam; - tf->lbah = g->lbah; - tf->device = g->device; - tf->command = g->status; - tf->hob_nsect = g->hob_nsect; - tf->hob_lbal = g->hob_lbal; - tf->hob_lbam = g->hob_lbam; - tf->hob_lbah = g->hob_lbah; -} - -static struct ata_port_operations ipr_sata_ops = { - .phy_reset = ipr_ata_phy_reset, - .hardreset = ipr_sata_reset, - .post_internal_cmd = ipr_ata_post_internal, - .qc_prep = ata_noop_qc_prep, - .qc_defer = ipr_qc_defer, - .qc_issue = ipr_qc_issue, - .qc_fill_rtf = ipr_qc_fill_rtf, - .port_start = ata_sas_port_start, - .port_stop = ata_sas_port_stop -}; - -static struct ata_port_info sata_port_info = { - .flags = ATA_FLAG_SATA | ATA_FLAG_PIO_DMA | - ATA_FLAG_SAS_HOST, - .pio_mask = ATA_PIO4_ONLY, - .mwdma_mask = ATA_MWDMA2, - .udma_mask = ATA_UDMA6, - .port_ops = &ipr_sata_ops -}; - #ifdef CONFIG_PPC_PSERIES static const u16 ipr_blocked_processors[] = { PVR_NORTHSTAR, @@ -10181,7 +9428,6 @@ static int ipr_probe_ioa(struct pci_dev *pdev, ioa_cfg = (struct ipr_ioa_cfg *)host->hostdata; memset(ioa_cfg, 0, sizeof(struct ipr_ioa_cfg)); - ata_host_init(&ioa_cfg->ata_host, &pdev->dev, &ipr_sata_ops); ioa_cfg->ipr_chip = ipr_get_chip_info(dev_id); diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index 69444d21fca1..c77d6ca1a210 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -35,7 +34,6 @@ * This can be adjusted at runtime through sysfs device attributes. */ #define IPR_MAX_CMD_PER_LUN 6 -#define IPR_MAX_CMD_PER_ATA_LUN 1 /* * IPR_NUM_BASE_CMD_BLKS: This defines the maximum number of @@ -197,7 +195,6 @@ #define IPR_LUN_RESET 0x40 #define IPR_TARGET_RESET 0x20 #define IPR_BUS_RESET 0x10 -#define IPR_ATA_PHY_RESET 0x80 #define IPR_ID_HOST_RR_Q 0xC4 #define IPR_QUERY_IOA_CONFIG 0xC5 #define IPR_CANCEL_ALL_REQUESTS 0xCE @@ -521,7 +518,6 @@ struct ipr_cmd_pkt { #define IPR_RQTYPE_SCSICDB 0x00 #define IPR_RQTYPE_IOACMD 0x01 #define IPR_RQTYPE_HCAM 0x02 -#define IPR_RQTYPE_ATA_PASSTHRU 0x04 #define IPR_RQTYPE_PIPE 0x05 u8 reserved2; @@ -546,30 +542,6 @@ struct ipr_cmd_pkt { __be16 timeout; }__attribute__ ((packed, aligned(4))); -struct ipr_ioarcb_ata_regs { /* 22 bytes */ - u8 flags; -#define IPR_ATA_FLAG_PACKET_CMD 0x80 -#define IPR_ATA_FLAG_XFER_TYPE_DMA 0x40 -#define IPR_ATA_FLAG_STATUS_ON_GOOD_COMPLETION 0x20 - u8 reserved[3]; - - __be16 data; - u8 feature; - u8 nsect; - u8 lbal; - u8 lbam; - u8 lbah; - u8 device; - u8 command; - u8 reserved2[3]; - u8 hob_feature; - u8 hob_nsect; - u8 hob_lbal; - u8 hob_lbam; - u8 hob_lbah; - u8 ctl; -}__attribute__ ((packed, aligned(2))); - struct ipr_ioadl_desc { __be32 flags_and_data_len; #define IPR_IOADL_FLAGS_MASK 0xff000000 @@ -591,15 +563,8 @@ struct ipr_ioadl64_desc { __be64 address; }__attribute__((packed, aligned (16))); -struct ipr_ata64_ioadl { - struct ipr_ioarcb_ata_regs regs; - u16 reserved[5]; - struct ipr_ioadl64_desc ioadl64[IPR_NUM_IOADL_ENTRIES]; -}__attribute__((packed, aligned (16))); - struct ipr_ioarcb_add_data { union { - struct ipr_ioarcb_ata_regs regs; struct ipr_ioadl_desc ioadl[5]; __be32 add_cmd_parms[10]; } u; @@ -665,21 +630,6 @@ struct ipr_ioasa_gpdd { __be32 ioa_data[2]; }__attribute__((packed, aligned (4))); -struct ipr_ioasa_gata { - u8 error; - u8 nsect; /* Interrupt reason */ - u8 lbal; - u8 lbam; - u8 lbah; - u8 device; - u8 status; - u8 alt_status; /* ATA CTL */ - u8 hob_nsect; - u8 hob_lbal; - u8 hob_lbam; - u8 hob_lbah; -}__attribute__((packed, aligned (4))); - struct ipr_auto_sense { __be16 auto_sense_len; __be16 ioa_data_len; @@ -713,7 +663,6 @@ struct ipr_ioasa_hdr { __be32 ioasc_specific; /* status code specific field */ #define IPR_ADDITIONAL_STATUS_FMT 0x80000000 #define IPR_AUTOSENSE_VALID 0x40000000 -#define IPR_ATA_DEVICE_WAS_RESET 0x20000000 #define IPR_IOASC_SPECIFIC_MASK 0x00ffffff #define IPR_FIELD_POINTER_VALID (0x80000000 >> 8) #define IPR_FIELD_POINTER_MASK 0x0000ffff @@ -727,7 +676,6 @@ struct ipr_ioasa { struct ipr_ioasa_vset vset; struct ipr_ioasa_af_dasd dasd; struct ipr_ioasa_gpdd gpdd; - struct ipr_ioasa_gata gata; } u; struct ipr_auto_sense auto_sense; @@ -741,7 +689,6 @@ struct ipr_ioasa64 { struct ipr_ioasa_vset vset; struct ipr_ioasa_af_dasd dasd; struct ipr_ioasa_gpdd gpdd; - struct ipr_ioasa_gata gata; } u; struct ipr_auto_sense auto_sense; @@ -1279,13 +1226,6 @@ struct ipr_bus_attributes { u32 max_xfer_rate; }; -struct ipr_sata_port { - struct ipr_ioa_cfg *ioa_cfg; - struct ata_port *ap; - struct ipr_resource_entry *res; - struct ipr_ioasa_gata ioasa; -}; - struct ipr_resource_entry { u8 needs_sync_complete:1; u8 in_erp:1; @@ -1323,7 +1263,6 @@ struct ipr_resource_entry { struct ipr_ioa_cfg *ioa_cfg; struct scsi_device *sdev; - struct ipr_sata_port *sata_port; struct list_head queue; }; /* struct ipr_resource_entry */ @@ -1582,7 +1521,6 @@ struct ipr_ioa_cfg { struct ipr_cmnd *reset_cmd; int (*reset) (struct ipr_cmnd *); - struct ata_host ata_host; char ipr_cmd_label[8]; #define IPR_CMD_LABEL "ipr_cmd" u32 max_cmds; @@ -1604,7 +1542,6 @@ struct ipr_cmnd { union { struct ipr_ioadl_desc ioadl[IPR_NUM_IOADL_ENTRIES]; struct ipr_ioadl64_desc ioadl64[IPR_NUM_IOADL_ENTRIES]; - struct ipr_ata64_ioadl ata_ioadl; } i; union { struct ipr_ioasa ioasa; @@ -1612,7 +1549,6 @@ struct ipr_cmnd { } s; struct list_head queue; struct scsi_cmnd *scsi_cmd; - struct ata_queued_cmd *qc; struct completion completion; struct timer_list timer; struct work_struct work; -- GitLab From c4b52d8b6c1de1e6359bef2d1394d5917940b3dc Mon Sep 17 00:00:00 2001 From: Song Shuai Date: Thu, 23 Mar 2023 20:39:24 +0800 Subject: [PATCH 3371/5631] riscv: export cpu/freq invariant to scheduler RISC-V now manages CPU topology using arch_topology which provides CPU capacity and frequency related interfaces to access the cpu/freq invariant in possible heterogeneous or DVFS-enabled platforms. Here adds topology.h file to export the arch_topology interfaces for replacing the scheduler's constant-based cpu/freq invariant accounting. Signed-off-by: Song Shuai Reviewed-by: Andrew Jones Reviewed-by: Ley Foon Tan Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230323123924.3032174-1-suagrfillet@gmail.com [Palmer: Fix the whitespace issues.] Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/topology.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 arch/riscv/include/asm/topology.h diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h new file mode 100644 index 000000000000..727e8d163a3b --- /dev/null +++ b/arch/riscv/include/asm/topology.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_TOPOLOGY_H +#define _ASM_RISCV_TOPOLOGY_H + +#include + +/* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_tick topology_scale_freq_tick +#define arch_set_freq_scale topology_set_freq_scale +#define arch_scale_freq_capacity topology_get_freq_scale +#define arch_scale_freq_invariant topology_scale_freq_invariant + +/* Replace task scheduler's default cpu-invariant accounting */ +#define arch_scale_cpu_capacity topology_get_cpu_scale + +/* Enable topology flag updates */ +#define arch_update_cpu_topology topology_update_cpu_topology + +#include +#endif /* _ASM_RISCV_TOPOLOGY_H */ -- GitLab From 8bf7b3b6676270c0ed3e4968608e1e052ecc8606 Mon Sep 17 00:00:00 2001 From: Song Shuai Date: Fri, 10 Mar 2023 19:03:36 +0800 Subject: [PATCH 3372/5631] riscv: Kconfig: enable SCHED_MC kconfig RISC-V now builds the sched domain based on the simple possible map. Enable SCHED_MC to make the building based on cpu_coregroup_mask() which also takes care of the NUMA and cores with LLC. Signed-off-by: Song Shuai Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20230310110336.970985-1-suagrfillet@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index aaa11fb48b86..2db7b1b1b85c 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -322,6 +322,14 @@ config SMP If you don't know what to do here, say N. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + config NR_CPUS int "Maximum number of CPUs (2-512)" depends on SMP -- GitLab From 5464912cfae706aff47f6253c495bf81284bc5d5 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 5 Apr 2023 11:21:10 +0100 Subject: [PATCH 3373/5631] RISC-V: align ISA extension Kconfig help text with each other Other extensions only capitalise the first letter in the text visible in Kconfig menus, and provide a short comment about the extension's meaning. Do the same for Svnapot & Svpbmt. The precedent for capitalisation in the Kconfig text was set by Zicbom & sorta followed for Zicboz. The RVI styling used for multi-letter extensions only capitalises the first letter, so do the same here. If nothing else, my OCD likes it when the extensions follow a consistent pattern. While editing one of the lines, reformat the "spelling" of 64-bit. Signed-off-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230405-pucker-cogwheel-3a999a94a2f2@wendy Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 2db7b1b1b85c..ba94d08a7d0e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -409,31 +409,31 @@ config RISCV_ISA_C If you don't know what to do here, say Y. config RISCV_ISA_SVNAPOT - bool "SVNAPOT extension support" + bool "Svnapot extension support for supervisor mode NAPOT pages" depends on 64BIT && MMU depends on RISCV_ALTERNATIVE default y help - Allow kernel to detect the SVNAPOT ISA-extension dynamically at boot + Allow kernel to detect the Svnapot ISA-extension dynamically at boot time and enable its usage. - The SVNAPOT extension is used to mark contiguous PTEs as a range + The Svnapot extension is used to mark contiguous PTEs as a range of contiguous virtual-to-physical translations for a naturally aligned power-of-2 (NAPOT) granularity larger than the base 4KB page size. When HUGETLBFS is also selected this option unconditionally allocates some memory for each NAPOT page size supported by the kernel. When optimizing for low memory consumption and for platforms without - the SVNAPOT extension, it may be better to say N here. + the Svnapot extension, it may be better to say N here. If you don't know what to do here, say Y. config RISCV_ISA_SVPBMT - bool "SVPBMT extension support" + bool "Svpbmt extension support for supervisor mode page-based memory types" depends on 64BIT && MMU depends on RISCV_ALTERNATIVE default y help - Adds support to dynamically detect the presence of the SVPBMT + Adds support to dynamically detect the presence of the Svpbmt ISA-extension (Supervisor-mode: page-based memory types) and enable its usage. @@ -441,7 +441,7 @@ config RISCV_ISA_SVPBMT that indicate the cacheability, idempotency, and ordering properties for access to that page. - The SVPBMT extension is only available on 64Bit cpus. + The Svpbmt extension is only available on 64-bit cpus. If you don't know what to do here, say Y. @@ -491,7 +491,7 @@ config RISCV_ISA_ZICBOZ depends on RISCV_ALTERNATIVE default y help - Enable the use of the ZICBOZ extension (cbo.zero instruction) + Enable the use of the Zicboz extension (cbo.zero instruction) when available. The Zicboz extension is used for faster zeroing of memory. -- GitLab From a7407a1318a9d7b5a7de7ab19935de5fc4c47a57 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 24 Mar 2023 16:54:19 +0100 Subject: [PATCH 3374/5631] riscv: Get rid of riscv_pfn_base variable Use directly phys_ram_base instead, riscv_pfn_base is just the pfn of the address contained in phys_ram_base. Even if there is no functional change intended in this patch, actually setting phys_ram_base that early changes the behaviour of kernel_mapping_pa_to_va during the early boot: phys_ram_base used to be zero before this patch and now it is set to the physical start address of the kernel. But it does not break the conversion of a kernel physical address into a virtual address since kernel_mapping_pa_to_va should only be used on kernel physical addresses, i.e. addresses greater than the physical start address of the kernel. Signed-off-by: Alexandre Ghiti Reviewed-by: Andrew Jones Reviewed-by: Anup Patel Tested-by: Anup Patel Link: https://lore.kernel.org/r/20230324155421.271544-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/page.h | 3 +-- arch/riscv/mm/init.c | 6 +----- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 7fed7c431928..8dc686f549b6 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -91,8 +91,7 @@ typedef struct page *pgtable_t; #endif #ifdef CONFIG_MMU -extern unsigned long riscv_pfn_base; -#define ARCH_PFN_OFFSET (riscv_pfn_base) +#define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base)) #else #define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 478d6763a01a..225a7d2b65cc 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -271,9 +271,6 @@ static void __init setup_bootmem(void) #ifdef CONFIG_MMU struct pt_alloc_ops pt_ops __initdata; -unsigned long riscv_pfn_base __ro_after_init; -EXPORT_SYMBOL(riscv_pfn_base); - pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; @@ -285,7 +282,6 @@ static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAG #ifdef CONFIG_XIP_KERNEL #define pt_ops (*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops)) -#define riscv_pfn_base (*(unsigned long *)XIP_FIXUP(&riscv_pfn_base)) #define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir)) #define fixmap_pte ((pte_t *)XIP_FIXUP(fixmap_pte)) #define early_pg_dir ((pgd_t *)XIP_FIXUP(early_pg_dir)) @@ -985,7 +981,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr; kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; - riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr); + phys_ram_base = kernel_map.phys_addr; /* * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit -- GitLab From 8589e346bbb679cf7a4b564f75295d94250058f0 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 24 Mar 2023 16:54:20 +0100 Subject: [PATCH 3375/5631] riscv: Move the linear mapping creation in its own function No change intended, it just splits the linear mapping creation from setup_vm_final: this prepares for upcoming additions to the linear mapping creation. Signed-off-by: Alexandre Ghiti Reviewed-by: Andrew Jones Reviewed-by: Anup Patel Tested-by: Anup Patel Link: https://lore.kernel.org/r/20230324155421.271544-3-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 225a7d2b65cc..ed07ae111f3a 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1086,16 +1086,25 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) pt_ops_set_fixmap(); } -static void __init setup_vm_final(void) +static void __init create_linear_mapping_range(phys_addr_t start, + phys_addr_t end) { + phys_addr_t pa; uintptr_t va, map_size; - phys_addr_t pa, start, end; - u64 i; - /* Setup swapper PGD for fixmap */ - create_pgd_mapping(swapper_pg_dir, FIXADDR_START, - __pa_symbol(fixmap_pgd_next), - PGDIR_SIZE, PAGE_TABLE); + for (pa = start; pa < end; pa += map_size) { + va = (uintptr_t)__va(pa); + map_size = best_map_size(pa, end - pa); + + create_pgd_mapping(swapper_pg_dir, va, pa, map_size, + pgprot_from_va(va)); + } +} + +static void __init create_linear_mapping_page_table(void) +{ + phys_addr_t start, end; + u64 i; /* Map all memory banks in the linear mapping */ for_each_mem_range(i, &start, &end) { @@ -1107,14 +1116,19 @@ static void __init setup_vm_final(void) if (end >= __pa(PAGE_OFFSET) + memory_limit) end = __pa(PAGE_OFFSET) + memory_limit; - for (pa = start; pa < end; pa += map_size) { - va = (uintptr_t)__va(pa); - map_size = best_map_size(pa, end - pa); - - create_pgd_mapping(swapper_pg_dir, va, pa, map_size, - pgprot_from_va(va)); - } + create_linear_mapping_range(start, end); } +} + +static void __init setup_vm_final(void) +{ + /* Setup swapper PGD for fixmap */ + create_pgd_mapping(swapper_pg_dir, FIXADDR_START, + __pa_symbol(fixmap_pgd_next), + PGDIR_SIZE, PAGE_TABLE); + + /* Map the linear mapping */ + create_linear_mapping_page_table(); /* Map the kernel */ if (IS_ENABLED(CONFIG_64BIT)) -- GitLab From 3335068f87217ea59d08f462187dc856652eea15 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 24 Mar 2023 16:54:21 +0100 Subject: [PATCH 3376/5631] riscv: Use PUD/P4D/PGD pages for the linear mapping During the early page table creation, we used to set the mapping for PAGE_OFFSET to the kernel load address: but the kernel load address is always offseted by PMD_SIZE which makes it impossible to use PUD/P4D/PGD pages as this physical address is not aligned on PUD/P4D/PGD size (whereas PAGE_OFFSET is). But actually we don't have to establish this mapping (ie set va_pa_offset) that early in the boot process because: - first, setup_vm installs a temporary kernel mapping and among other things, discovers the system memory, - then, setup_vm_final creates the final kernel mapping and takes advantage of the discovered system memory to create the linear mapping. During the first phase, we don't know the start of the system memory and then until the second phase is finished, we can't use the linear mapping at all and phys_to_virt/virt_to_phys translations must not be used because it would result in a different translation from the 'real' one once the final mapping is installed. So here we simply delay the initialization of va_pa_offset to after the system memory discovery. But to make sure noone uses the linear mapping before, we add some guard in the DEBUG_VIRTUAL config. Finally we can use PUD/P4D/PGD hugepages when possible, which will result in a better TLB utilization. Note that: - this does not apply to rv32 as the kernel mapping lies in the linear mapping. - we rely on the firmware to protect itself using PMP. Signed-off-by: Alexandre Ghiti Acked-by: Rob Herring # DT bits Reviewed-by: Andrew Jones Reviewed-by: Anup Patel Tested-by: Anup Patel Link: https://lore.kernel.org/r/20230324155421.271544-4-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/page.h | 16 ++++++++++ arch/riscv/mm/init.c | 58 +++++++++++++++++++++++++++++++---- arch/riscv/mm/physaddr.c | 16 ++++++++++ drivers/of/fdt.c | 11 ++++--- 4 files changed, 90 insertions(+), 11 deletions(-) diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 8dc686f549b6..ea1a0e237211 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -90,6 +90,14 @@ typedef struct page *pgtable_t; #define PTE_FMT "%08lx" #endif +#ifdef CONFIG_64BIT +/* + * We override this value as its generic definition uses __pa too early in + * the boot process (before kernel_map.va_pa_offset is set). + */ +#define MIN_MEMBLOCK_ADDR 0 +#endif + #ifdef CONFIG_MMU #define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base)) #else @@ -121,7 +129,11 @@ extern phys_addr_t phys_ram_base; #define is_linear_mapping(x) \ ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE)) +#ifndef CONFIG_DEBUG_VIRTUAL #define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) +#else +void *linear_mapping_pa_to_va(unsigned long x); +#endif #define kernel_mapping_pa_to_va(y) ({ \ unsigned long _y = (unsigned long)(y); \ (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \ @@ -130,7 +142,11 @@ extern phys_addr_t phys_ram_base; }) #define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x) +#ifndef CONFIG_DEBUG_VIRTUAL #define linear_mapping_va_to_pa(x) ((unsigned long)(x) - kernel_map.va_pa_offset) +#else +phys_addr_t linear_mapping_va_to_pa(unsigned long x); +#endif #define kernel_mapping_va_to_pa(y) ({ \ unsigned long _y = (unsigned long)(y); \ (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \ diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ed07ae111f3a..7bd66795165d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -213,6 +213,14 @@ static void __init setup_bootmem(void) phys_ram_end = memblock_end_of_DRAM(); if (!IS_ENABLED(CONFIG_XIP_KERNEL)) phys_ram_base = memblock_start_of_DRAM(); + + /* + * In 64-bit, any use of __va/__pa before this point is wrong as we + * did not know the start of DRAM before. + */ + if (IS_ENABLED(CONFIG_64BIT)) + kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; + /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE @@ -667,9 +675,16 @@ void __init create_pgd_mapping(pgd_t *pgdp, static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size) { - /* Upgrade to PMD_SIZE mappings whenever possible */ - base &= PMD_SIZE - 1; - if (!base && size >= PMD_SIZE) + if (!(base & (PGDIR_SIZE - 1)) && size >= PGDIR_SIZE) + return PGDIR_SIZE; + + if (!(base & (P4D_SIZE - 1)) && size >= P4D_SIZE) + return P4D_SIZE; + + if (!(base & (PUD_SIZE - 1)) && size >= PUD_SIZE) + return PUD_SIZE; + + if (!(base & (PMD_SIZE - 1)) && size >= PMD_SIZE) return PMD_SIZE; return PAGE_SIZE; @@ -978,11 +993,22 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) set_satp_mode(); #endif - kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr; + /* + * In 64-bit, we defer the setup of va_pa_offset to setup_bootmem, + * where we have the system memory layout: this allows us to align + * the physical and virtual mappings and then make use of PUD/P4D/PGD + * for the linear mapping. This is only possible because the kernel + * mapping lies outside the linear mapping. + * In 32-bit however, as the kernel resides in the linear mapping, + * setup_vm_final can not change the mapping established here, + * otherwise the same kernel addresses would get mapped to different + * physical addresses (if the start of dram is different from the + * kernel physical address start). + */ + kernel_map.va_pa_offset = IS_ENABLED(CONFIG_64BIT) ? + 0UL : PAGE_OFFSET - kernel_map.phys_addr; kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; - phys_ram_base = kernel_map.phys_addr; - /* * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit * kernel, whereas for 64-bit kernel, the end of the virtual address @@ -1106,6 +1132,17 @@ static void __init create_linear_mapping_page_table(void) phys_addr_t start, end; u64 i; +#ifdef CONFIG_STRICT_KERNEL_RWX + phys_addr_t ktext_start = __pa_symbol(_start); + phys_addr_t ktext_size = __init_data_begin - _start; + phys_addr_t krodata_start = __pa_symbol(__start_rodata); + phys_addr_t krodata_size = _data - __start_rodata; + + /* Isolate kernel text and rodata so they don't get mapped with a PUD */ + memblock_mark_nomap(ktext_start, ktext_size); + memblock_mark_nomap(krodata_start, krodata_size); +#endif + /* Map all memory banks in the linear mapping */ for_each_mem_range(i, &start, &end) { if (start >= end) @@ -1118,6 +1155,15 @@ static void __init create_linear_mapping_page_table(void) create_linear_mapping_range(start, end); } + +#ifdef CONFIG_STRICT_KERNEL_RWX + create_linear_mapping_range(ktext_start, ktext_start + ktext_size); + create_linear_mapping_range(krodata_start, + krodata_start + krodata_size); + + memblock_clear_nomap(ktext_start, ktext_size); + memblock_clear_nomap(krodata_start, krodata_size); +#endif } static void __init setup_vm_final(void) diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c index 9b18bda74154..18706f457da7 100644 --- a/arch/riscv/mm/physaddr.c +++ b/arch/riscv/mm/physaddr.c @@ -33,3 +33,19 @@ phys_addr_t __phys_addr_symbol(unsigned long x) return __va_to_pa_nodebug(x); } EXPORT_SYMBOL(__phys_addr_symbol); + +phys_addr_t linear_mapping_va_to_pa(unsigned long x) +{ + BUG_ON(!kernel_map.va_pa_offset); + + return ((unsigned long)(x) - kernel_map.va_pa_offset); +} +EXPORT_SYMBOL(linear_mapping_va_to_pa); + +void *linear_mapping_pa_to_va(unsigned long x) +{ + BUG_ON(!kernel_map.va_pa_offset); + + return ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)); +} +EXPORT_SYMBOL(linear_mapping_pa_to_va); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index d1a68b6d03b3..d14735a81301 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -887,12 +887,13 @@ const void * __init of_flat_dt_match_machine(const void *default_match, static void __early_init_dt_declare_initrd(unsigned long start, unsigned long end) { - /* ARM64 would cause a BUG to occur here when CONFIG_DEBUG_VM is - * enabled since __va() is called too early. ARM64 does make use - * of phys_initrd_start/phys_initrd_size so we can skip this - * conversion. + /* + * __va() is not yet available this early on some platforms. In that + * case, the platform uses phys_initrd_start/phys_initrd_size instead + * and does the VA conversion itself. */ - if (!IS_ENABLED(CONFIG_ARM64)) { + if (!IS_ENABLED(CONFIG_ARM64) && + !(IS_ENABLED(CONFIG_RISCV) && IS_ENABLED(CONFIG_64BIT))) { initrd_start = (unsigned long)__va(start); initrd_end = (unsigned long)__va(end); initrd_below_start_ok = 1; -- GitLab From 63f148c44f3919047301a023b10b0e3ce65a7389 Mon Sep 17 00:00:00 2001 From: John Paul Adrian Glaubitz Date: Wed, 19 Apr 2023 09:09:33 +0200 Subject: [PATCH 3377/5631] sh: pci: Remove unused variable in SH-7786 PCI Express code Addresses the following warning when building sdk7786_defconfig: arch/sh/drivers/pci/pcie-sh7786.c:34:22: warning: 'dma_pfn_offset' defined but not used [-Wunused-variable] 34 | static unsigned long dma_pfn_offset; | ^~~~~~~~~~~~~~ Fixes: e0d072782c73 ("dma-mapping: introduce DMA range map, supplanting dma_pfn_offset") Reviewed-by: Geert Uytterhoeven Signed-off-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230419070934.422997-1-glaubitz@physik.fu-berlin.de --- arch/sh/drivers/pci/pcie-sh7786.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/sh/drivers/pci/pcie-sh7786.c b/arch/sh/drivers/pci/pcie-sh7786.c index b0c2a5238d04..39bb5038e1c6 100644 --- a/arch/sh/drivers/pci/pcie-sh7786.c +++ b/arch/sh/drivers/pci/pcie-sh7786.c @@ -31,7 +31,6 @@ struct sh7786_pcie_port { static struct sh7786_pcie_port *sh7786_pcie_ports; static unsigned int nr_ports; -static unsigned long dma_pfn_offset; size_t memsize; u64 memstart; -- GitLab From 3ad1be6faef9a482c3098928220fcafaa51a1283 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 18 Apr 2023 12:46:02 -0300 Subject: [PATCH 3378/5631] perf dso: Fix use before NULL check introduced by map__dso() introduction James Clark noticed that the recent 63df0e4bc368adbd ("perf map: Add accessor for dso") patch accessed map->dso before the 'map' variable was NULL checked, which is a change in logic that leads to segmentation faults, so comb thru that patch to fix similar cases. Fixes: 63df0e4bc368adbd ("perf map: Add accessor for dso") Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Link: https://lore.kernel.org/lkml/ZD68RYCVT8hqPuxr@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 +++---- tools/perf/ui/browsers/hists.c | 4 ++-- tools/perf/util/sort.c | 2 +- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8fba247b798c..006f522d0e7f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1075,8 +1075,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, return 0; } - dso = map__dso(al.map); - if (!thread__find_map(thread, *cpumode, start, &al) || !dso) { + if (!thread__find_map(thread, *cpumode, start, &al) || (dso = map__dso(al.map)) == NULL) { pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end); return 0; } @@ -1106,9 +1105,9 @@ static int map__fprintf_srccode(struct map *map, u64 addr, FILE *fp, struct srcc unsigned line; int len; char *srccode; - struct dso *dso = map__dso(map); + struct dso *dso; - if (!map || !dso) + if (!map || (dso = map__dso(map)) == NULL) return 0; srcfile = get_srcline_split(dso, map__rip_2objdump(map, addr), diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index ab70e5f5fad2..69c81759a64f 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2499,9 +2499,9 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused, struct map_symbol *ms, u64 addr) { - struct dso *dso = map__dso(ms->map); + struct dso *dso; - if (!ms->map || !dso || dso->annotate_warned) + if (!ms->map || (dso = map__dso(ms->map)) == NULL || dso->annotate_warned) return 0; if (!ms->sym) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index f2ffaf90648e..31b1cd0935e2 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1568,7 +1568,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf, if (he->mem_info) { struct map *map = he->mem_info->daddr.ms.map; - struct dso *dso = map__dso(map); + struct dso *dso = map ? map__dso(map) : NULL; addr = cl_address(he->mem_info->daddr.al_addr, chk_double_cl); ms = &he->mem_info->daddr.ms; -- GitLab From fe693d951e3c303b4fb6c712f8affecbe9e8b001 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 18 Apr 2023 17:33:48 -0300 Subject: [PATCH 3379/5631] perf maps: Add maps__refcnt() accessor to allow checking maps pointer To remove one more direct access to 'struct maps' so that we can intercept accesses to its instantiations and refcount check it to catch use after free, etc. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/thread-maps-share.c | 12 ++++++------ tools/perf/util/maps.c | 6 +++--- tools/perf/util/maps.h | 5 +++++ 3 files changed, 14 insertions(+), 9 deletions(-) diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index 84edd82c519e..caf8fbe7c440 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -43,7 +43,7 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s leader && t1 && t2 && t3 && other); maps = leader->maps; - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 4); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 4); /* test the maps pointer is shared */ TEST_ASSERT_VAL("maps don't match", maps == t1->maps); @@ -71,25 +71,25 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s machine__remove_thread(machine, other_leader); other_maps = other->maps; - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_maps->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(other_maps)), 2); TEST_ASSERT_VAL("maps don't match", other_maps == other_leader->maps); /* release thread group */ thread__put(leader); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 3); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 3); thread__put(t1); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 2); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 2); thread__put(t2); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&maps->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 1); thread__put(t3); /* release other group */ thread__put(other_leader); - TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_maps->refcnt), 1); + TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(other_maps)), 1); thread__put(other); diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 5afed53ea0b4..953dc20d55d7 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -12,13 +12,13 @@ static void maps__init(struct maps *maps, struct machine *machine) { + refcount_set(maps__refcnt(maps), 1); maps->entries = RB_ROOT; init_rwsem(maps__lock(maps)); maps->machine = machine; maps->last_search_by_name = NULL; maps->nr_maps = 0; maps->maps_by_name = NULL; - refcount_set(&maps->refcnt, 1); } static void __maps__free_maps_by_name(struct maps *maps) @@ -180,14 +180,14 @@ void maps__delete(struct maps *maps) struct maps *maps__get(struct maps *maps) { if (maps) - refcount_inc(&maps->refcnt); + refcount_inc(maps__refcnt(maps)); return maps; } void maps__put(struct maps *maps) { - if (maps && refcount_dec_and_test(&maps->refcnt)) + if (maps && refcount_dec_and_test(maps__refcnt(maps))) maps__delete(maps); } diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index bde3390c7096..cfb1b79d1671 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -88,6 +88,11 @@ static inline unsigned int maps__nr_maps(const struct maps *maps) return maps->nr_maps; } +static inline refcount_t *maps__refcnt(struct maps *maps) +{ + return &maps->refcnt; +} + #ifdef HAVE_LIBUNWIND_SUPPORT static inline void *maps__addr_space(struct maps *maps) { -- GitLab From a07dacad8ac40d1beadb640fe341b5198c1cf097 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 18 Apr 2023 17:45:34 -0300 Subject: [PATCH 3380/5631] perf maps: Use maps__nr_maps() instead of open coded maps->nr_maps To use the existing accessor and be consistent. Signef-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 25738775834e..85787672d335 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -435,7 +435,7 @@ static struct thread *findnew_guest_code(struct machine *machine, return NULL; /* Assume maps are set up if there are any */ - if (thread->maps->nr_maps) + if (maps__nr_maps(thread->maps)) return thread; host_thread = machine__find_thread(host_machine, -1, pid); -- GitLab From 8f12692b7e61e5fb5d3e4f6692d6675f62eeebdc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 19 Apr 2023 10:48:37 -0300 Subject: [PATCH 3381/5631] perf maps: Add reference count checking Add reference count checking to make sure of good use of get and put. Add and use accessors to reduce RC_CHK clutter. The only significant issue was in tests/thread-maps-share.c where reference counts were released in the reverse order to acquisition, leading to a use after put. This was fixed by reversing the put order. Committer notes: Extracted from a larger patch removing bits that were covered by the use of pre-existing maps__ accessors (e.g. maps__nr_maps()) and new ones added (maps__refcnt()) to reduce RC_CHK_ACCESS(maps)-> source code pollution. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/thread-maps-share.c | 8 ++-- tools/perf/util/maps.c | 47 +++++++++++++----------- tools/perf/util/maps.h | 19 +++++----- tools/perf/util/symbol.c | 13 ++++--- tools/perf/util/unwind-libdw.c | 2 +- tools/perf/util/unwind-libunwind-local.c | 2 +- tools/perf/util/unwind-libunwind.c | 2 +- 7 files changed, 50 insertions(+), 43 deletions(-) diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index caf8fbe7c440..75ce8aedfc78 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -46,9 +46,9 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 4); /* test the maps pointer is shared */ - TEST_ASSERT_VAL("maps don't match", maps == t1->maps); - TEST_ASSERT_VAL("maps don't match", maps == t2->maps); - TEST_ASSERT_VAL("maps don't match", maps == t3->maps); + TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(t1->maps)); + TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(t2->maps)); + TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(t3->maps)); /* * Verify the other leader was created by previous call. @@ -73,7 +73,7 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s other_maps = other->maps; TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(other_maps)), 2); - TEST_ASSERT_VAL("maps don't match", other_maps == other_leader->maps); + TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(other_maps) == RC_CHK_ACCESS(other_leader->maps)); /* release thread group */ thread__put(leader); diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 953dc20d55d7..8a13396acd1a 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -13,12 +13,12 @@ static void maps__init(struct maps *maps, struct machine *machine) { refcount_set(maps__refcnt(maps), 1); - maps->entries = RB_ROOT; init_rwsem(maps__lock(maps)); - maps->machine = machine; - maps->last_search_by_name = NULL; - maps->nr_maps = 0; - maps->maps_by_name = NULL; + RC_CHK_ACCESS(maps)->entries = RB_ROOT; + RC_CHK_ACCESS(maps)->machine = machine; + RC_CHK_ACCESS(maps)->last_search_by_name = NULL; + RC_CHK_ACCESS(maps)->nr_maps = 0; + RC_CHK_ACCESS(maps)->maps_by_name = NULL; } static void __maps__free_maps_by_name(struct maps *maps) @@ -29,8 +29,8 @@ static void __maps__free_maps_by_name(struct maps *maps) for (unsigned int i = 0; i < maps__nr_maps(maps); i++) map__put(maps__maps_by_name(maps)[i]); - zfree(&maps->maps_by_name); - maps->nr_maps_allocated = 0; + zfree(&RC_CHK_ACCESS(maps)->maps_by_name); + RC_CHK_ACCESS(maps)->nr_maps_allocated = 0; } static int __maps__insert(struct maps *maps, struct map *map) @@ -71,7 +71,7 @@ int maps__insert(struct maps *maps, struct map *map) if (err) goto out; - ++maps->nr_maps; + ++RC_CHK_ACCESS(maps)->nr_maps; if (dso && dso->kernel) { struct kmap *kmap = map__kmap(map); @@ -88,7 +88,7 @@ int maps__insert(struct maps *maps, struct map *map) * inserted map and resort. */ if (maps__maps_by_name(maps)) { - if (maps__nr_maps(maps) > maps->nr_maps_allocated) { + if (maps__nr_maps(maps) > RC_CHK_ACCESS(maps)->nr_maps_allocated) { int nr_allocate = maps__nr_maps(maps) * 2; struct map **maps_by_name = realloc(maps__maps_by_name(maps), nr_allocate * sizeof(map)); @@ -99,8 +99,8 @@ int maps__insert(struct maps *maps, struct map *map) goto out; } - maps->maps_by_name = maps_by_name; - maps->nr_maps_allocated = nr_allocate; + RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name; + RC_CHK_ACCESS(maps)->nr_maps_allocated = nr_allocate; } maps__maps_by_name(maps)[maps__nr_maps(maps) - 1] = map__get(map); __maps__sort_by_name(maps); @@ -122,15 +122,15 @@ void maps__remove(struct maps *maps, struct map *map) struct map_rb_node *rb_node; down_write(maps__lock(maps)); - if (maps->last_search_by_name == map) - maps->last_search_by_name = NULL; + if (RC_CHK_ACCESS(maps)->last_search_by_name == map) + RC_CHK_ACCESS(maps)->last_search_by_name = NULL; rb_node = maps__find_node(maps, map); assert(rb_node->map == map); __maps__remove(maps, rb_node); if (maps__maps_by_name(maps)) __maps__free_maps_by_name(maps); - --maps->nr_maps; + --RC_CHK_ACCESS(maps)->nr_maps; up_write(maps__lock(maps)); } @@ -162,33 +162,38 @@ bool maps__empty(struct maps *maps) struct maps *maps__new(struct machine *machine) { - struct maps *maps = zalloc(sizeof(*maps)); + struct maps *result; + RC_STRUCT(maps) *maps = zalloc(sizeof(*maps)); - if (maps != NULL) - maps__init(maps, machine); + if (ADD_RC_CHK(result, maps)) + maps__init(result, machine); - return maps; + return result; } void maps__delete(struct maps *maps) { maps__exit(maps); unwind__finish_access(maps); - free(maps); + RC_CHK_FREE(maps); } struct maps *maps__get(struct maps *maps) { - if (maps) + struct maps *result; + + if (RC_CHK_GET(result, maps)) refcount_inc(maps__refcnt(maps)); - return maps; + return result; } void maps__put(struct maps *maps) { if (maps && refcount_dec_and_test(maps__refcnt(maps))) maps__delete(maps); + else + RC_CHK_PUT(maps); } struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp) diff --git a/tools/perf/util/maps.h b/tools/perf/util/maps.h index cfb1b79d1671..d2963456cfbe 100644 --- a/tools/perf/util/maps.h +++ b/tools/perf/util/maps.h @@ -8,6 +8,7 @@ #include #include #include "rwsem.h" +#include struct ref_reloc_sym; struct machine; @@ -32,7 +33,7 @@ struct map *maps__find(struct maps *maps, u64 addr); for (map = maps__first(maps), next = map_rb_node__next(map); map; \ map = next, next = map_rb_node__next(map)) -struct maps { +DECLARE_RC_STRUCT(maps) { struct rb_root entries; struct rw_semaphore lock; struct machine *machine; @@ -65,43 +66,43 @@ void maps__put(struct maps *maps); static inline struct rb_root *maps__entries(struct maps *maps) { - return &maps->entries; + return &RC_CHK_ACCESS(maps)->entries; } static inline struct machine *maps__machine(struct maps *maps) { - return maps->machine; + return RC_CHK_ACCESS(maps)->machine; } static inline struct rw_semaphore *maps__lock(struct maps *maps) { - return &maps->lock; + return &RC_CHK_ACCESS(maps)->lock; } static inline struct map **maps__maps_by_name(struct maps *maps) { - return maps->maps_by_name; + return RC_CHK_ACCESS(maps)->maps_by_name; } static inline unsigned int maps__nr_maps(const struct maps *maps) { - return maps->nr_maps; + return RC_CHK_ACCESS(maps)->nr_maps; } static inline refcount_t *maps__refcnt(struct maps *maps) { - return &maps->refcnt; + return &RC_CHK_ACCESS(maps)->refcnt; } #ifdef HAVE_LIBUNWIND_SUPPORT static inline void *maps__addr_space(struct maps *maps) { - return maps->addr_space; + return RC_CHK_ACCESS(maps)->addr_space; } static inline const struct unwind_libunwind_ops *maps__unwind_libunwind_ops(const struct maps *maps) { - return maps->unwind_libunwind_ops; + return RC_CHK_ACCESS(maps)->unwind_libunwind_ops; } #endif diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index e7f63670688e..01fa5560a0bb 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -2096,8 +2096,8 @@ static int map__groups__sort_by_name_from_rbtree(struct maps *maps) up_read(maps__lock(maps)); down_write(maps__lock(maps)); - maps->maps_by_name = maps_by_name; - maps->nr_maps_allocated = maps__nr_maps(maps); + RC_CHK_ACCESS(maps)->maps_by_name = maps_by_name; + RC_CHK_ACCESS(maps)->nr_maps_allocated = maps__nr_maps(maps); maps__for_each_entry(maps, rb_node) maps_by_name[i++] = map__get(rb_node->map); @@ -2132,11 +2132,12 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) down_read(maps__lock(maps)); - if (maps->last_search_by_name) { - const struct dso *dso = map__dso(maps->last_search_by_name); + + if (RC_CHK_ACCESS(maps)->last_search_by_name) { + const struct dso *dso = map__dso(RC_CHK_ACCESS(maps)->last_search_by_name); if (strcmp(dso->short_name, name) == 0) { - map = maps->last_search_by_name; + map = RC_CHK_ACCESS(maps)->last_search_by_name; goto out_unlock; } } @@ -2156,7 +2157,7 @@ struct map *maps__find_by_name(struct maps *maps, const char *name) map = rb_node->map; dso = map__dso(map); if (strcmp(dso->short_name, name) == 0) { - maps->last_search_by_name = map; + RC_CHK_ACCESS(maps)->last_search_by_name = map; goto out_unlock; } } diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 9565f9906e5d..bdccfc511b7e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -230,7 +230,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct unwind_info *ui, ui_buf = { .sample = data, .thread = thread, - .machine = thread->maps->machine, + .machine = RC_CHK_ACCESS(thread->maps)->machine, .cb = cb, .arg = arg, .max_stack = max_stack, diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index f9a52af48de4..83dd79dcd597 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -677,7 +677,7 @@ static int _unwind__prepare_access(struct maps *maps) { void *addr_space = unw_create_addr_space(&accessors, 0); - maps->addr_space = addr_space; + RC_CHK_ACCESS(maps)->addr_space = addr_space; if (!addr_space) { pr_err("unwind: Can't create unwind address space.\n"); return -ENOMEM; diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 4378daaafcd3..b54968e6a4e4 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -14,7 +14,7 @@ struct unwind_libunwind_ops __weak *arm64_unwind_libunwind_ops; static void unwind__register_ops(struct maps *maps, struct unwind_libunwind_ops *ops) { - maps->unwind_libunwind_ops = ops; + RC_CHK_ACCESS(maps)->unwind_libunwind_ops = ops; } int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized) -- GitLab From 80f746e2bd0e1da3fdb49a53570e54a1a225faac Mon Sep 17 00:00:00 2001 From: John Paul Adrian Glaubitz Date: Wed, 19 Apr 2023 13:48:52 +0200 Subject: [PATCH 3382/5631] sh: sq: Fix incorrect element size for allocating bitmap buffer The Store Queue code allocates a bitmap buffer with the size of multiple of sizeof(long) in sq_api_init(). While the buffer size is calculated correctly, the code uses the wrong element size to allocate the buffer which results in the allocated bitmap buffer being too small. Fix this by allocating the buffer with kcalloc() with element size sizeof(long) instead of kzalloc() whose elements size defaults to sizeof(char). Fixes: d7c30c682a27 ("sh: Store Queue API rework.") Reviewed-by: Geert Uytterhoeven Signed-off-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/20230419114854.528677-1-glaubitz@physik.fu-berlin.de --- arch/sh/kernel/cpu/sh4/sq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index 27f2e3da5aa2..6e0bb3f47fa5 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -382,7 +382,7 @@ static int __init sq_api_init(void) if (unlikely(!sq_cache)) return ret; - sq_bitmap = kzalloc(size, GFP_KERNEL); + sq_bitmap = kcalloc(size, sizeof(long), GFP_KERNEL); if (unlikely(!sq_bitmap)) goto out; -- GitLab From cd0334e1c091fc0263ccf76e81d333a2ece4f3ab Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:27 +0100 Subject: [PATCH 3383/5631] riscv: Split early and final KASAN population functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a preliminary work that allows to make the code more understandable. Signed-off-by: Alexandre Ghiti Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230203075232.274282-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/kasan_init.c | 185 +++++++++++++++++++++++-------------- 1 file changed, 116 insertions(+), 69 deletions(-) diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index e1226709490f..2a48eba6bd08 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -95,23 +95,13 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned } static void __init kasan_populate_pud(pgd_t *pgd, - unsigned long vaddr, unsigned long end, - bool early) + unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; pud_t *pudp, *base_pud; unsigned long next; - if (early) { - /* - * We can't use pgd_page_vaddr here as it would return a linear - * mapping address but it is not mapped yet, but when populating - * early_pg_dir, we need the physical address and when populating - * swapper_pg_dir, we need the kernel virtual address so use - * pt_ops facility. - */ - base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd))); - } else if (pgd_none(*pgd)) { + if (pgd_none(*pgd)) { base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); memcpy(base_pud, (void *)kasan_early_shadow_pud, sizeof(pud_t) * PTRS_PER_PUD); @@ -130,16 +120,10 @@ static void __init kasan_populate_pud(pgd_t *pgd, next = pud_addr_end(vaddr, end); if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { - if (early) { - phys_addr = __pa(((uintptr_t)kasan_early_shadow_pmd)); - set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE)); + phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); + if (phys_addr) { + set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); continue; - } else { - phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); - if (phys_addr) { - set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); - continue; - } } } @@ -152,34 +136,21 @@ static void __init kasan_populate_pud(pgd_t *pgd, * it entirely, memblock could allocate a page at a physical address * where KASAN is not populated yet and then we'd get a page fault. */ - if (!early) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE)); + set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE)); } static void __init kasan_populate_p4d(pgd_t *pgd, - unsigned long vaddr, unsigned long end, - bool early) + unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; p4d_t *p4dp, *base_p4d; unsigned long next; - if (early) { - /* - * We can't use pgd_page_vaddr here as it would return a linear - * mapping address but it is not mapped yet, but when populating - * early_pg_dir, we need the physical address and when populating - * swapper_pg_dir, we need the kernel virtual address so use - * pt_ops facility. - */ - base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd))); - } else { - base_p4d = (p4d_t *)pgd_page_vaddr(*pgd); - if (base_p4d == lm_alias(kasan_early_shadow_p4d)) { - base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE); - memcpy(base_p4d, (void *)kasan_early_shadow_p4d, - sizeof(p4d_t) * PTRS_PER_P4D); - } + base_p4d = (p4d_t *)pgd_page_vaddr(*pgd); + if (base_p4d == lm_alias(kasan_early_shadow_p4d)) { + base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE); + memcpy(base_p4d, (void *)kasan_early_shadow_p4d, + sizeof(p4d_t) * PTRS_PER_P4D); } p4dp = base_p4d + p4d_index(vaddr); @@ -188,20 +159,14 @@ static void __init kasan_populate_p4d(pgd_t *pgd, next = p4d_addr_end(vaddr, end); if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) { - if (early) { - phys_addr = __pa(((uintptr_t)kasan_early_shadow_pud)); - set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE)); + phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); + if (phys_addr) { + set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); continue; - } else { - phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); - if (phys_addr) { - set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); - continue; - } } } - kasan_populate_pud((pgd_t *)p4dp, vaddr, next, early); + kasan_populate_pud((pgd_t *)p4dp, vaddr, next); } while (p4dp++, vaddr = next, vaddr != end); /* @@ -210,8 +175,7 @@ static void __init kasan_populate_p4d(pgd_t *pgd, * it entirely, memblock could allocate a page at a physical address * where KASAN is not populated yet and then we'd get a page fault. */ - if (!early) - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE)); + set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE)); } #define kasan_early_shadow_pgd_next (pgtable_l5_enabled ? \ @@ -219,16 +183,15 @@ static void __init kasan_populate_p4d(pgd_t *pgd, (pgtable_l4_enabled ? \ (uintptr_t)kasan_early_shadow_pud : \ (uintptr_t)kasan_early_shadow_pmd)) -#define kasan_populate_pgd_next(pgdp, vaddr, next, early) \ +#define kasan_populate_pgd_next(pgdp, vaddr, next) \ (pgtable_l5_enabled ? \ - kasan_populate_p4d(pgdp, vaddr, next, early) : \ + kasan_populate_p4d(pgdp, vaddr, next) : \ (pgtable_l4_enabled ? \ - kasan_populate_pud(pgdp, vaddr, next, early) : \ + kasan_populate_pud(pgdp, vaddr, next) : \ kasan_populate_pmd((pud_t *)pgdp, vaddr, next))) static void __init kasan_populate_pgd(pgd_t *pgdp, - unsigned long vaddr, unsigned long end, - bool early) + unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; unsigned long next; @@ -237,11 +200,7 @@ static void __init kasan_populate_pgd(pgd_t *pgdp, next = pgd_addr_end(vaddr, end); if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { - if (early) { - phys_addr = __pa((uintptr_t)kasan_early_shadow_pgd_next); - set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE)); - continue; - } else if (pgd_page_vaddr(*pgdp) == + if (pgd_page_vaddr(*pgdp) == (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) { /* * pgdp can't be none since kasan_early_init @@ -258,7 +217,95 @@ static void __init kasan_populate_pgd(pgd_t *pgdp, } } - kasan_populate_pgd_next(pgdp, vaddr, next, early); + kasan_populate_pgd_next(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_pud(p4d_t *p4dp, + unsigned long vaddr, + unsigned long end) +{ + pud_t *pudp, *base_pud; + phys_addr_t phys_addr; + unsigned long next; + + if (!pgtable_l4_enabled) { + pudp = (pud_t *)p4dp; + } else { + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + pudp = base_pud + pud_index(vaddr); + } + + do { + next = pud_addr_end(vaddr, end); + + if (pud_none(*pudp) && IS_ALIGNED(vaddr, PUD_SIZE) && + (next - vaddr) >= PUD_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd); + set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + BUG(); + } while (pudp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_p4d(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + p4d_t *p4dp, *base_p4d; + phys_addr_t phys_addr; + unsigned long next; + + /* + * We can't use pgd_page_vaddr here as it would return a linear + * mapping address but it is not mapped yet, but when populating + * early_pg_dir, we need the physical address and when populating + * swapper_pg_dir, we need the kernel virtual address so use + * pt_ops facility. + * Note that this test is then completely equivalent to + * p4dp = p4d_offset(pgdp, vaddr) + */ + if (!pgtable_l5_enabled) { + p4dp = (p4d_t *)pgdp; + } else { + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + p4dp = base_p4d + p4d_index(vaddr); + } + + do { + next = p4d_addr_end(vaddr, end); + + if (p4d_none(*p4dp) && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_pud); + set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + kasan_early_populate_pud(p4dp, vaddr, next); + } while (p4dp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_pgd(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + phys_addr_t phys_addr; + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d); + set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + kasan_early_populate_p4d(pgdp, vaddr, next); } while (pgdp++, vaddr = next, vaddr != end); } @@ -295,16 +342,16 @@ asmlinkage void __init kasan_early_init(void) PAGE_TABLE)); } - kasan_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START), - KASAN_SHADOW_START, KASAN_SHADOW_END, true); + kasan_early_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); local_flush_tlb_all(); } void __init kasan_swapper_init(void) { - kasan_populate_pgd(pgd_offset_k(KASAN_SHADOW_START), - KASAN_SHADOW_START, KASAN_SHADOW_END, true); + kasan_early_populate_pgd(pgd_offset_k(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); local_flush_tlb_all(); } @@ -314,7 +361,7 @@ static void __init kasan_populate(void *start, void *end) unsigned long vaddr = (unsigned long)start & PAGE_MASK; unsigned long vend = PAGE_ALIGN((unsigned long)end); - kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend, false); + kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend); local_flush_tlb_all(); memset(start, KASAN_SHADOW_INIT, end - start); -- GitLab From 96f9d4daf745205fe869e9e5ac23199ef11c5448 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:28 +0100 Subject: [PATCH 3384/5631] riscv: Rework kasan population functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Our previous kasan population implementation used to have the final kasan shadow region mapped with kasan_early_shadow_page, because we did not clean the early mapping and then we had to populate the kasan region "in-place" which made the code cumbersome. So now we clear the early mapping, establish a temporary mapping while we populate the kasan shadow region with just the kernel regions that will be used. This new version uses the "generic" way of going through a page table that may be folded at runtime (avoid the XXX_next macros). It was tested with outline instrumentation on an Ubuntu kernel configuration successfully. Signed-off-by: Alexandre Ghiti Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230203075232.274282-3-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/kasan_init.c | 361 +++++++++++++++++++------------------ 1 file changed, 183 insertions(+), 178 deletions(-) diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 2a48eba6bd08..8fc0efcf905c 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -18,58 +18,48 @@ * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate * the page global directory with kasan_early_shadow_pmd. * - * For sv48 and sv57, the region is not aligned on PGDIR_SIZE so the mapping - * must be divided as follows: - * - the first PGD entry, although incomplete, is populated with - * kasan_early_shadow_pud/p4d - * - the PGD entries in the middle are populated with kasan_early_shadow_pud/p4d - * - the last PGD entry is shared with the kernel mapping so populated at the - * lower levels pud/p4d - * - * In addition, when shallow populating a kasan region (for example vmalloc), - * this region may also not be aligned on PGDIR size, so we must go down to the - * pud level too. + * For sv48 and sv57, the region start is aligned on PGDIR_SIZE whereas the end + * region is not and then we have to go down to the PUD level. */ extern pgd_t early_pg_dir[PTRS_PER_PGD]; +pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; +p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; +pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; - pte_t *ptep, *base_pte; + pte_t *ptep, *p; - if (pmd_none(*pmd)) - base_pte = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); - else - base_pte = (pte_t *)pmd_page_vaddr(*pmd); + if (pmd_none(*pmd)) { + p = memblock_alloc(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); + } - ptep = base_pte + pte_index(vaddr); + ptep = pte_offset_kernel(pmd, vaddr); do { if (pte_none(*ptep)) { phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE); } } while (ptep++, vaddr += PAGE_SIZE, vaddr != end); - - set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(base_pte)), PAGE_TABLE)); } static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; - pmd_t *pmdp, *base_pmd; + pmd_t *pmdp, *p; unsigned long next; if (pud_none(*pud)) { - base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); - } else { - base_pmd = (pmd_t *)pud_pgtable(*pud); - if (base_pmd == lm_alias(kasan_early_shadow_pmd)) - base_pmd = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + p = memblock_alloc(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); } - pmdp = base_pmd + pmd_index(vaddr); + pmdp = pmd_offset(pud, vaddr); do { next = pmd_addr_end(vaddr, end); @@ -78,43 +68,28 @@ static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE); if (phys_addr) { set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PMD_SIZE); continue; } } kasan_populate_pte(pmdp, vaddr, next); } while (pmdp++, vaddr = next, vaddr != end); - - /* - * Wait for the whole PGD to be populated before setting the PGD in - * the page table, otherwise, if we did set the PGD before populating - * it entirely, memblock could allocate a page at a physical address - * where KASAN is not populated yet and then we'd get a page fault. - */ - set_pud(pud, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE)); } -static void __init kasan_populate_pud(pgd_t *pgd, +static void __init kasan_populate_pud(p4d_t *p4d, unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; - pud_t *pudp, *base_pud; + pud_t *pudp, *p; unsigned long next; - if (pgd_none(*pgd)) { - base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); - memcpy(base_pud, (void *)kasan_early_shadow_pud, - sizeof(pud_t) * PTRS_PER_PUD); - } else { - base_pud = (pud_t *)pgd_page_vaddr(*pgd); - if (base_pud == lm_alias(kasan_early_shadow_pud)) { - base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); - memcpy(base_pud, (void *)kasan_early_shadow_pud, - sizeof(pud_t) * PTRS_PER_PUD); - } + if (p4d_none(*p4d)) { + p = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); } - pudp = base_pud + pud_index(vaddr); + pudp = pud_offset(p4d, vaddr); do { next = pud_addr_end(vaddr, end); @@ -123,37 +98,28 @@ static void __init kasan_populate_pud(pgd_t *pgd, phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); if (phys_addr) { set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PUD_SIZE); continue; } } kasan_populate_pmd(pudp, vaddr, next); } while (pudp++, vaddr = next, vaddr != end); - - /* - * Wait for the whole PGD to be populated before setting the PGD in - * the page table, otherwise, if we did set the PGD before populating - * it entirely, memblock could allocate a page at a physical address - * where KASAN is not populated yet and then we'd get a page fault. - */ - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_pud)), PAGE_TABLE)); } static void __init kasan_populate_p4d(pgd_t *pgd, unsigned long vaddr, unsigned long end) { phys_addr_t phys_addr; - p4d_t *p4dp, *base_p4d; + p4d_t *p4dp, *p; unsigned long next; - base_p4d = (p4d_t *)pgd_page_vaddr(*pgd); - if (base_p4d == lm_alias(kasan_early_shadow_p4d)) { - base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE); - memcpy(base_p4d, (void *)kasan_early_shadow_p4d, - sizeof(p4d_t) * PTRS_PER_P4D); + if (pgd_none(*pgd)) { + p = memblock_alloc(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); + set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); } - p4dp = base_p4d + p4d_index(vaddr); + p4dp = p4d_offset(pgd, vaddr); do { next = p4d_addr_end(vaddr, end); @@ -162,34 +128,15 @@ static void __init kasan_populate_p4d(pgd_t *pgd, phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); if (phys_addr) { set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, P4D_SIZE); continue; } } - kasan_populate_pud((pgd_t *)p4dp, vaddr, next); + kasan_populate_pud(p4dp, vaddr, next); } while (p4dp++, vaddr = next, vaddr != end); - - /* - * Wait for the whole P4D to be populated before setting the P4D in - * the page table, otherwise, if we did set the P4D before populating - * it entirely, memblock could allocate a page at a physical address - * where KASAN is not populated yet and then we'd get a page fault. - */ - set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(base_p4d)), PAGE_TABLE)); } -#define kasan_early_shadow_pgd_next (pgtable_l5_enabled ? \ - (uintptr_t)kasan_early_shadow_p4d : \ - (pgtable_l4_enabled ? \ - (uintptr_t)kasan_early_shadow_pud : \ - (uintptr_t)kasan_early_shadow_pmd)) -#define kasan_populate_pgd_next(pgdp, vaddr, next) \ - (pgtable_l5_enabled ? \ - kasan_populate_p4d(pgdp, vaddr, next) : \ - (pgtable_l4_enabled ? \ - kasan_populate_pud(pgdp, vaddr, next) : \ - kasan_populate_pmd((pud_t *)pgdp, vaddr, next))) - static void __init kasan_populate_pgd(pgd_t *pgdp, unsigned long vaddr, unsigned long end) { @@ -199,25 +146,86 @@ static void __init kasan_populate_pgd(pgd_t *pgdp, do { next = pgd_addr_end(vaddr, end); - if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) { - if (pgd_page_vaddr(*pgdp) == - (unsigned long)lm_alias(kasan_early_shadow_pgd_next)) { - /* - * pgdp can't be none since kasan_early_init - * initialized all KASAN shadow region with - * kasan_early_shadow_pud: if this is still the - * case, that means we can try to allocate a - * hugepage as a replacement. - */ - phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); - if (phys_addr) { - set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL)); - continue; - } + if (pgd_none(*pgdp) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); + if (phys_addr) { + set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PGDIR_SIZE); + continue; } } - kasan_populate_pgd_next(pgdp, vaddr, next); + kasan_populate_p4d(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_pud(p4d_t *p4dp, + unsigned long vaddr, unsigned long end) +{ + pud_t *pudp, *base_pud; + unsigned long next; + + if (!pgtable_l4_enabled) { + pudp = (pud_t *)p4dp; + } else { + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(*p4dp))); + pudp = base_pud + pud_index(vaddr); + } + + do { + next = pud_addr_end(vaddr, end); + + if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { + pud_clear(pudp); + continue; + } + + BUG(); + } while (pudp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_p4d(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + p4d_t *p4dp, *base_p4d; + unsigned long next; + + if (!pgtable_l5_enabled) { + p4dp = (p4d_t *)pgdp; + } else { + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgdp))); + p4dp = base_p4d + p4d_index(vaddr); + } + + do { + next = p4d_addr_end(vaddr, end); + + if (pgtable_l4_enabled && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { + p4d_clear(p4dp); + continue; + } + + kasan_early_clear_pud(p4dp, vaddr, next); + } while (p4dp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_pgd(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + if (pgtable_l5_enabled && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + pgd_clear(pgdp); + continue; + } + + kasan_early_clear_p4d(pgdp, vaddr, next); } while (pgdp++, vaddr = next, vaddr != end); } @@ -362,117 +370,64 @@ static void __init kasan_populate(void *start, void *end) unsigned long vend = PAGE_ALIGN((unsigned long)end); kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend); - - local_flush_tlb_all(); - memset(start, KASAN_SHADOW_INIT, end - start); -} - -static void __init kasan_shallow_populate_pmd(pgd_t *pgdp, - unsigned long vaddr, unsigned long end) -{ - unsigned long next; - pmd_t *pmdp, *base_pmd; - bool is_kasan_pte; - - base_pmd = (pmd_t *)pgd_page_vaddr(*pgdp); - pmdp = base_pmd + pmd_index(vaddr); - - do { - next = pmd_addr_end(vaddr, end); - is_kasan_pte = (pmd_pgtable(*pmdp) == lm_alias(kasan_early_shadow_pte)); - - if (is_kasan_pte) - pmd_clear(pmdp); - } while (pmdp++, vaddr = next, vaddr != end); } -static void __init kasan_shallow_populate_pud(pgd_t *pgdp, +static void __init kasan_shallow_populate_pud(p4d_t *p4d, unsigned long vaddr, unsigned long end) { unsigned long next; - pud_t *pudp, *base_pud; - pmd_t *base_pmd; - bool is_kasan_pmd; - - base_pud = (pud_t *)pgd_page_vaddr(*pgdp); - pudp = base_pud + pud_index(vaddr); + void *p; + pud_t *pud_k = pud_offset(p4d, vaddr); do { next = pud_addr_end(vaddr, end); - is_kasan_pmd = (pud_pgtable(*pudp) == lm_alias(kasan_early_shadow_pmd)); - if (!is_kasan_pmd) - continue; - - base_pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - set_pud(pudp, pfn_pud(PFN_DOWN(__pa(base_pmd)), PAGE_TABLE)); - - if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) + if (pud_none(*pud_k)) { + p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; + } - memcpy(base_pmd, (void *)kasan_early_shadow_pmd, PAGE_SIZE); - kasan_shallow_populate_pmd((pgd_t *)pudp, vaddr, next); - } while (pudp++, vaddr = next, vaddr != end); + BUG(); + } while (pud_k++, vaddr = next, vaddr != end); } -static void __init kasan_shallow_populate_p4d(pgd_t *pgdp, +static void __init kasan_shallow_populate_p4d(pgd_t *pgd, unsigned long vaddr, unsigned long end) { unsigned long next; - p4d_t *p4dp, *base_p4d; - pud_t *base_pud; - bool is_kasan_pud; - - base_p4d = (p4d_t *)pgd_page_vaddr(*pgdp); - p4dp = base_p4d + p4d_index(vaddr); + void *p; + p4d_t *p4d_k = p4d_offset(pgd, vaddr); do { next = p4d_addr_end(vaddr, end); - is_kasan_pud = (p4d_pgtable(*p4dp) == lm_alias(kasan_early_shadow_pud)); - - if (!is_kasan_pud) - continue; - - base_pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - set_p4d(p4dp, pfn_p4d(PFN_DOWN(__pa(base_pud)), PAGE_TABLE)); - if (IS_ALIGNED(vaddr, P4D_SIZE) && (next - vaddr) >= P4D_SIZE) + if (p4d_none(*p4d_k)) { + p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); continue; + } - memcpy(base_pud, (void *)kasan_early_shadow_pud, PAGE_SIZE); - kasan_shallow_populate_pud((pgd_t *)p4dp, vaddr, next); - } while (p4dp++, vaddr = next, vaddr != end); + kasan_shallow_populate_pud(p4d_k, vaddr, end); + } while (p4d_k++, vaddr = next, vaddr != end); } -#define kasan_shallow_populate_pgd_next(pgdp, vaddr, next) \ - (pgtable_l5_enabled ? \ - kasan_shallow_populate_p4d(pgdp, vaddr, next) : \ - (pgtable_l4_enabled ? \ - kasan_shallow_populate_pud(pgdp, vaddr, next) : \ - kasan_shallow_populate_pmd(pgdp, vaddr, next))) - static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end) { unsigned long next; void *p; pgd_t *pgd_k = pgd_offset_k(vaddr); - bool is_kasan_pgd_next; do { next = pgd_addr_end(vaddr, end); - is_kasan_pgd_next = (pgd_page_vaddr(*pgd_k) == - (unsigned long)lm_alias(kasan_early_shadow_pgd_next)); - if (is_kasan_pgd_next) { + if (pgd_none(*pgd_k)) { p = memblock_alloc(PAGE_SIZE, PAGE_SIZE); set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); - } - - if (IS_ALIGNED(vaddr, PGDIR_SIZE) && (next - vaddr) >= PGDIR_SIZE) continue; + } - memcpy(p, (void *)kasan_early_shadow_pgd_next, PAGE_SIZE); - kasan_shallow_populate_pgd_next(pgd_k, vaddr, next); + kasan_shallow_populate_p4d(pgd_k, vaddr, next); } while (pgd_k++, vaddr = next, vaddr != end); } @@ -482,7 +437,37 @@ static void __init kasan_shallow_populate(void *start, void *end) unsigned long vend = PAGE_ALIGN((unsigned long)end); kasan_shallow_populate_pgd(vaddr, vend); - local_flush_tlb_all(); +} + +static void create_tmp_mapping(void) +{ + void *ptr; + p4d_t *base_p4d; + + /* + * We need to clean the early mapping: this is hard to achieve "in-place", + * so install a temporary mapping like arm64 and x86 do. + */ + memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(pgd_t) * PTRS_PER_PGD); + + /* Copy the last p4d since it is shared with the kernel mapping. */ + if (pgtable_l5_enabled) { + ptr = (p4d_t *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END)); + memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D); + set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)], + pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE)); + base_p4d = tmp_p4d; + } else { + base_p4d = (p4d_t *)tmp_pg_dir; + } + + /* Copy the last pud since it is shared with the kernel mapping. */ + if (pgtable_l4_enabled) { + ptr = (pud_t *)p4d_page_vaddr(*(base_p4d + p4d_index(KASAN_SHADOW_END))); + memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD); + set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)], + pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE)); + } } void __init kasan_init(void) @@ -490,10 +475,27 @@ void __init kasan_init(void) phys_addr_t p_start, p_end; u64 i; - if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + create_tmp_mapping(); + csr_write(CSR_SATP, PFN_DOWN(__pa(tmp_pg_dir)) | satp_mode); + + kasan_early_clear_pgd(pgd_offset_k(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); + + kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)FIXADDR_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_START)); + + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { kasan_shallow_populate( (void *)kasan_mem_to_shadow((void *)VMALLOC_START), (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + /* Shallow populate modules and BPF which are vmalloc-allocated */ + kasan_shallow_populate( + (void *)kasan_mem_to_shadow((void *)MODULES_VADDR), + (void *)kasan_mem_to_shadow((void *)MODULES_END)); + } else { + kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)VMALLOC_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + } /* Populate the linear mapping */ for_each_mem_range(i, &p_start, &p_end) { @@ -506,8 +508,8 @@ void __init kasan_init(void) kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); } - /* Populate kernel, BPF, modules mapping */ - kasan_populate(kasan_mem_to_shadow((const void *)MODULES_VADDR), + /* Populate kernel */ + kasan_populate(kasan_mem_to_shadow((const void *)MODULES_END), kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G)); for (i = 0; i < PTRS_PER_PTE; i++) @@ -518,4 +520,7 @@ void __init kasan_init(void) memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); init_task.kasan_depth = 0; + + csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | satp_mode); + local_flush_tlb_all(); } -- GitLab From 401e84488800d05e8ed6db2a687eaa94415f4ec8 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:29 +0100 Subject: [PATCH 3385/5631] riscv: Move DTB_EARLY_BASE_VA to the kernel address space MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The early virtual address should lie in the kernel address space for inline kasan instrumentation to succeed, otherwise kasan tries to dereference an address that does not exist in the address space (since kasan only maps *kernel* address space, not the userspace). Simply use the very first address of the kernel address space for the early fdt mapping. It allowed an Ubuntu kernel to boot successfully with inline instrumentation. Signed-off-by: Alexandre Ghiti Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230203075232.274282-4-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 478d6763a01a..87f6a5d475a6 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -57,7 +57,7 @@ unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] EXPORT_SYMBOL(empty_zero_page); extern char _start[]; -#define DTB_EARLY_BASE_VA PGDIR_SIZE +#define DTB_EARLY_BASE_VA (ADDRESS_SPACE_END - (PTRS_PER_PGD / 2 * PGDIR_SIZE) + 1) void *_dtb_early_va __initdata; uintptr_t _dtb_early_pa __initdata; -- GitLab From 617955ca6e275c4dd0dcf5316fca7fc04a8f2fe6 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:30 +0100 Subject: [PATCH 3386/5631] riscv: Fix EFI stub usage of KASAN instrumented strcmp function The EFI stub must not use any KASAN instrumented code as the kernel proper did not initialize the thread pointer and the mapping for the KASAN shadow region. Avoid using the generic strcmp function, instead use the one in drivers/firmware/efi/libstub/string.c. Signed-off-by: Alexandre Ghiti Acked-by: Ard Biesheuvel Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20230203075232.274282-5-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/image-vars.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h index 7e2962ef73f9..15616155008c 100644 --- a/arch/riscv/kernel/image-vars.h +++ b/arch/riscv/kernel/image-vars.h @@ -23,8 +23,6 @@ * linked at. The routines below are all implemented in assembler in a * position independent manner */ -__efistub_strcmp = strcmp; - __efistub__start = _start; __efistub__start_kernel = _start_kernel; __efistub__end = _end; -- GitLab From ecd7ebaf0b5a094a6180b299a5635c0eea42be4b Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:31 +0100 Subject: [PATCH 3387/5631] riscv: Fix ptdump when KASAN is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The KASAN shadow region was moved next to the kernel mapping but the ptdump code was not updated and it appears to break the dump of the kernel page table, so fix this by moving the KASAN shadow region in ptdump. Fixes: f7ae02333d13 ("riscv: Move KASAN mapping next to the kernel mapping") Signed-off-by: Alexandre Ghiti Tested-by: Björn Töpel Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230203075232.274282-6-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/ptdump.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 830e7de65e3a..20a9f991a6d7 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -59,10 +59,6 @@ struct ptd_mm_info { }; enum address_markers_idx { -#ifdef CONFIG_KASAN - KASAN_SHADOW_START_NR, - KASAN_SHADOW_END_NR, -#endif FIXMAP_START_NR, FIXMAP_END_NR, PCI_IO_START_NR, @@ -74,6 +70,10 @@ enum address_markers_idx { VMALLOC_START_NR, VMALLOC_END_NR, PAGE_OFFSET_NR, +#ifdef CONFIG_KASAN + KASAN_SHADOW_START_NR, + KASAN_SHADOW_END_NR, +#endif #ifdef CONFIG_64BIT MODULES_MAPPING_NR, KERNEL_MAPPING_NR, @@ -82,10 +82,6 @@ enum address_markers_idx { }; static struct addr_marker address_markers[] = { -#ifdef CONFIG_KASAN - {0, "Kasan shadow start"}, - {0, "Kasan shadow end"}, -#endif {0, "Fixmap start"}, {0, "Fixmap end"}, {0, "PCI I/O start"}, @@ -97,6 +93,10 @@ static struct addr_marker address_markers[] = { {0, "vmalloc() area"}, {0, "vmalloc() end"}, {0, "Linear mapping"}, +#ifdef CONFIG_KASAN + {0, "Kasan shadow start"}, + {0, "Kasan shadow end"}, +#endif #ifdef CONFIG_64BIT {0, "Modules/BPF mapping"}, {0, "Kernel mapping"}, @@ -362,10 +362,6 @@ static int __init ptdump_init(void) { unsigned int i, j; -#ifdef CONFIG_KASAN - address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START; - address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END; -#endif address_markers[FIXMAP_START_NR].start_address = FIXADDR_START; address_markers[FIXMAP_END_NR].start_address = FIXADDR_TOP; address_markers[PCI_IO_START_NR].start_address = PCI_IO_START; @@ -377,6 +373,10 @@ static int __init ptdump_init(void) address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET; +#ifdef CONFIG_KASAN + address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START; + address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END; +#endif #ifdef CONFIG_64BIT address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR; address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr; -- GitLab From 864046c512c2cd8418dc928b91981fb12a80396c Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 3 Feb 2023 08:52:32 +0100 Subject: [PATCH 3388/5631] riscv: Unconditionnally select KASAN_VMALLOC if KASAN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If KASAN is enabled, VMAP_STACK depends on KASAN_VMALLOC so enable KASAN_VMALLOC with KASAN so that we can enable VMAP_STACK by default. Signed-off-by: Alexandre Ghiti Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230203075232.274282-7-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index e2b656043abf..0f226d3261ca 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -117,6 +117,7 @@ config RISCV select HAVE_RSEQ select IRQ_DOMAIN select IRQ_FORCED_THREADING + select KASAN_VMALLOC if KASAN select MODULES_USE_ELF_RELA if MODULES select MODULE_SECTIONS if MODULES select OF -- GitLab From 55de1e4ad43b375566162ae0cc2b56dfa44aae4e Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 29 Mar 2023 06:53:24 +0200 Subject: [PATCH 3389/5631] riscv: Prepare EFI header for relocatable kernels ld does not handle relocations correctly as explained here [1], a fix for that was proposed by Nelson there but we have to support older toolchains and then provide this fix. Note that llvm does not need this fix and is then excluded. [1] https://sourceware.org/pipermail/binutils/2023-March/126690.html Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230329045329.64565-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/set_memory.h | 3 +++ arch/riscv/kernel/efi-header.S | 19 ++++++++++++++++--- arch/riscv/kernel/vmlinux.lds.S | 5 ++--- 3 files changed, 21 insertions(+), 6 deletions(-) diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index a2c14d4b3993..ec11001c3fe0 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -56,4 +56,7 @@ bool kernel_page_present(struct page *page); #define SECTION_ALIGN L1_CACHE_BYTES #endif /* CONFIG_STRICT_KERNEL_RWX */ +#define PECOFF_SECTION_ALIGNMENT 0x1000 +#define PECOFF_FILE_ALIGNMENT 0x200 + #endif /* _ASM_RISCV_SET_MEMORY_H */ diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S index 8e733aa48ba6..515b2dfbca75 100644 --- a/arch/riscv/kernel/efi-header.S +++ b/arch/riscv/kernel/efi-header.S @@ -6,6 +6,7 @@ #include #include +#include .macro __EFI_PE_HEADER .long PE_MAGIC @@ -33,7 +34,11 @@ optional_header: .byte 0x02 // MajorLinkerVersion .byte 0x14 // MinorLinkerVersion .long __pecoff_text_end - efi_header_end // SizeOfCode - .long __pecoff_data_virt_size // SizeOfInitializedData +#ifdef __clang__ + .long __pecoff_data_virt_size // SizeOfInitializedData +#else + .long __pecoff_data_virt_end - __pecoff_text_end // SizeOfInitializedData +#endif .long 0 // SizeOfUninitializedData .long __efistub_efi_pe_entry - _start // AddressOfEntryPoint .long efi_header_end - _start // BaseOfCode @@ -91,9 +96,17 @@ section_table: IMAGE_SCN_MEM_EXECUTE // Characteristics .ascii ".data\0\0\0" - .long __pecoff_data_virt_size // VirtualSize +#ifdef __clang__ + .long __pecoff_data_virt_size // VirtualSize +#else + .long __pecoff_data_virt_end - __pecoff_text_end // VirtualSize +#endif .long __pecoff_text_end - _start // VirtualAddress - .long __pecoff_data_raw_size // SizeOfRawData +#ifdef __clang__ + .long __pecoff_data_raw_size // SizeOfRawData +#else + .long __pecoff_data_raw_end - __pecoff_text_end // SizeOfRawData +#endif .long __pecoff_text_end - _start // PointerToRawData .long 0 // PointerToRelocations diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 53a8ad65b255..1c38294580c0 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -27,9 +27,6 @@ ENTRY(_start) jiffies = jiffies_64; -PECOFF_SECTION_ALIGNMENT = 0x1000; -PECOFF_FILE_ALIGNMENT = 0x200; - SECTIONS { /* Beginning of code and text segment */ @@ -132,6 +129,7 @@ SECTIONS #ifdef CONFIG_EFI .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_raw_end = ABSOLUTE(.); #endif /* End of data section */ @@ -142,6 +140,7 @@ SECTIONS #ifdef CONFIG_EFI . = ALIGN(PECOFF_SECTION_ALIGNMENT); __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_virt_end = ABSOLUTE(.); #endif _end = .; -- GitLab From 69a90d2fe107c8bf6a424af0f30d2b223cdeaf7c Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 29 Mar 2023 06:53:25 +0200 Subject: [PATCH 3390/5631] riscv: Move .rela.dyn outside of init to avoid empty relocations This is a preparatory patch for relocatable kernels: .rela.dyn should be in .init but doing so actually produces empty relocations, so this should be a temporary commit until we find a solution. This issue was reported here [1]. [1] https://lore.kernel.org/all/4a6fc7a3-9697-a49b-0941-97f32194b0d7@ghiti.fr/. Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230329045329.64565-3-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/vmlinux.lds.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 1c38294580c0..e05e6df44225 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -96,10 +96,6 @@ SECTIONS *(.rel.dyn*) } - .rela.dyn : { - *(.rela*) - } - __init_data_end = .; . = ALIGN(8); @@ -126,6 +122,10 @@ SECTIONS *(.sdata*) } + .rela.dyn : { + *(.rela*) + } + #ifdef CONFIG_EFI .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); -- GitLab From 39b33072941f8bab82aa2c802044062385a046bf Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 29 Mar 2023 06:53:26 +0200 Subject: [PATCH 3391/5631] riscv: Introduce CONFIG_RELOCATABLE This config allows to compile 64b kernel as PIE and to relocate it at any virtual address at runtime: this paves the way to KASLR. Runtime relocation is possible since relocation metadata are embedded into the kernel. Note that relocating at runtime introduces an overhead even if the kernel is loaded at the same address it was linked at and that the compiler options are those used in arm64 which uses the same RELA relocation format. Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230329045329.64565-4-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 14 +++++++++ arch/riscv/Makefile | 7 +++-- arch/riscv/kernel/vmlinux.lds.S | 17 +++++++++-- arch/riscv/mm/Makefile | 4 +++ arch/riscv/mm/init.c | 54 ++++++++++++++++++++++++++++++++- 5 files changed, 91 insertions(+), 5 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..ccbb05118ca0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -561,6 +561,20 @@ config COMPAT If you want to execute 32-bit userspace applications, say Y. +config RELOCATABLE + bool "Build a relocatable kernel" + depends on MMU && 64BIT && !XIP_KERNEL + help + This builds a kernel as a Position Independent Executable (PIE), + which retains all relocation metadata required to relocate the + kernel binary at runtime to a different virtual address than the + address it was linked at. + Since RISCV uses the RELA relocation format, this requires a + relocation pass at runtime even if the kernel is loaded at the + same address it was linked at. + + If unsure, say N. + endmenu # "Kernel features" menu "Boot options" diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 6203c3378922..860b09e409c7 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -7,9 +7,12 @@ # OBJCOPYFLAGS := -O binary -LDFLAGS_vmlinux := +ifeq ($(CONFIG_RELOCATABLE),y) + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro + KBUILD_CFLAGS += -fPIE +endif ifeq ($(CONFIG_DYNAMIC_FTRACE),y) - LDFLAGS_vmlinux := --no-relax + LDFLAGS_vmlinux += --no-relax KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY ifeq ($(CONFIG_RISCV_ISA_C),y) CC_FLAGS_FTRACE := -fpatchable-function-entry=4 diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index e05e6df44225..615ff5842690 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -122,10 +122,23 @@ SECTIONS *(.sdata*) } - .rela.dyn : { - *(.rela*) + .rela.dyn : ALIGN(8) { + __rela_dyn_start = .; + *(.rela .rela*) + __rela_dyn_end = .; } +#ifdef CONFIG_RELOCATABLE + .data.rel : { *(.data.rel*) } + .got : { *(.got*) } + .plt : { *(.plt) } + .dynamic : { *(.dynamic) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .hash : { *(.hash) } + .gnu.hash : { *(.gnu.hash) } +#endif + #ifdef CONFIG_EFI .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 2ac177c05352..b85e9e82f082 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS_init.o := -mcmodel=medany +ifdef CONFIG_RELOCATABLE +CFLAGS_init.o += -fno-pie +endif + ifdef CONFIG_FTRACE CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 478d6763a01a..029a844d4ad8 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -20,6 +20,9 @@ #include #include #include +#ifdef CONFIG_RELOCATABLE +#include +#endif #include #include @@ -146,7 +149,7 @@ static void __init print_vm_layout(void) print_ml("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END); #endif - print_ml("kernel", (unsigned long)KERNEL_LINK_ADDR, + print_ml("kernel", (unsigned long)kernel_map.virt_addr, (unsigned long)ADDRESS_SPACE_END); } } @@ -820,6 +823,44 @@ static __init void set_satp_mode(void) #error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." #endif +#ifdef CONFIG_RELOCATABLE +extern unsigned long __rela_dyn_start, __rela_dyn_end; + +static void __init relocate_kernel(void) +{ + Elf64_Rela *rela = (Elf64_Rela *)&__rela_dyn_start; + /* + * This holds the offset between the linked virtual address and the + * relocated virtual address. + */ + uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR; + /* + * This holds the offset between kernel linked virtual address and + * physical address. + */ + uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr; + + for ( ; rela < (Elf64_Rela *)&__rela_dyn_end; rela++) { + Elf64_Addr addr = (rela->r_offset - va_kernel_link_pa_offset); + Elf64_Addr relocated_addr = rela->r_addend; + + if (rela->r_info != R_RISCV_RELATIVE) + continue; + + /* + * Make sure to not relocate vdso symbols like rt_sigreturn + * which are linked from the address 0 in vmlinux since + * vdso symbol addresses are actually used as an offset from + * mm->context.vdso in VDSO_OFFSET macro. + */ + if (relocated_addr >= KERNEL_LINK_ADDR) + relocated_addr += reloc_offset; + + *(Elf64_Addr *)addr = relocated_addr; + } +} +#endif /* CONFIG_RELOCATABLE */ + #ifdef CONFIG_XIP_KERNEL static void __init create_kernel_page_table(pgd_t *pgdir, __always_unused bool early) @@ -1007,6 +1048,17 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K); #endif +#ifdef CONFIG_RELOCATABLE + /* + * Early page table uses only one PUD, which makes it possible + * to map PUD_SIZE aligned on PUD_SIZE: if the relocation offset + * makes the kernel cross over a PUD_SIZE boundary, raise a bug + * since a part of the kernel would not get mapped. + */ + BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size); + relocate_kernel(); +#endif + apply_early_boot_alternatives(); pt_ops_set_early(); -- GitLab From 47981b5cc6871d78aee67b6c9ae70aff90ddb97d Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 29 Mar 2023 06:53:27 +0200 Subject: [PATCH 3392/5631] powerpc: Move script to check relocations at compile time in scripts/ Relocating kernel at runtime is done very early in the boot process, so it is not convenient to check for relocations there and react in case a relocation was not expected. Powerpc architecture has a script that allows to check at compile time for such unexpected relocations: extract the common logic to scripts/ so that other architectures can take advantage of it. Signed-off-by: Alexandre Ghiti Reviewed-by: Anup Patel Acked-by: Michael Ellerman (powerpc) Link: https://lore.kernel.org/r/20230329045329.64565-5-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/powerpc/tools/relocs_check.sh | 18 ++---------------- scripts/relocs_check.sh | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+), 16 deletions(-) create mode 100755 scripts/relocs_check.sh diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh index 63792af00417..6b350e75014c 100755 --- a/arch/powerpc/tools/relocs_check.sh +++ b/arch/powerpc/tools/relocs_check.sh @@ -15,21 +15,8 @@ if [ $# -lt 3 ]; then exit 1 fi -# Have Kbuild supply the path to objdump and nm so we handle cross compilation. -objdump="$1" -nm="$2" -vmlinux="$3" - -# Remove from the bad relocations those that match an undefined weak symbol -# which will result in an absolute relocation to 0. -# Weak unresolved symbols are of that form in nm output: -# " w _binary__btf_vmlinux_bin_end" -undef_weak_symbols=$($nm "$vmlinux" | awk '$1 ~ /w/ { print $2 }') - bad_relocs=$( -$objdump -R "$vmlinux" | - # Only look at relocation lines. - grep -E '\ Date: Wed, 29 Mar 2023 06:53:28 +0200 Subject: [PATCH 3393/5631] riscv: Check relocations at compile time Relocating kernel at runtime is done very early in the boot process, so it is not convenient to check for relocations there and react in case a relocation was not expected. There exists a script in scripts/ that extracts the relocations from vmlinux that is then used at postlink to check the relocations. Signed-off-by: Alexandre Ghiti Reviewed-by: Anup Patel Link: https://lore.kernel.org/r/20230329045329.64565-6-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Makefile.postlink | 36 ++++++++++++++++++++++++++++++++ arch/riscv/tools/relocs_check.sh | 26 +++++++++++++++++++++++ 2 files changed, 62 insertions(+) create mode 100644 arch/riscv/Makefile.postlink create mode 100755 arch/riscv/tools/relocs_check.sh diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink new file mode 100644 index 000000000000..d5de8d520d3e --- /dev/null +++ b/arch/riscv/Makefile.postlink @@ -0,0 +1,36 @@ +# SPDX-License-Identifier: GPL-2.0 +# =========================================================================== +# Post-link riscv pass +# =========================================================================== +# +# Check that vmlinux relocations look sane + +PHONY := __archpost +__archpost: + +-include include/config/auto.conf +include $(srctree)/scripts/Kbuild.include + +quiet_cmd_relocs_check = CHKREL $@ +cmd_relocs_check = \ + $(CONFIG_SHELL) $(srctree)/arch/riscv/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" + +# `@true` prevents complaint when there is nothing to be done + +vmlinux: FORCE + @true +ifdef CONFIG_RELOCATABLE + $(call if_changed,relocs_check) +endif + +%.ko: FORCE + @true + +clean: + @true + +PHONY += FORCE clean + +FORCE: + +.PHONY: $(PHONY) diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh new file mode 100755 index 000000000000..baeb2e7b2290 --- /dev/null +++ b/arch/riscv/tools/relocs_check.sh @@ -0,0 +1,26 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Based on powerpc relocs_check.sh + +# This script checks the relocations of a vmlinux for "suspicious" +# relocations. + +if [ $# -lt 3 ]; then + echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2 + exit 1 +fi + +bad_relocs=$( +${srctree}/scripts/relocs_check.sh "$@" | + # These relocations are okay + # R_RISCV_RELATIVE + grep -F -w -v 'R_RISCV_RELATIVE' +) + +if [ -z "$bad_relocs" ]; then + exit 0 +fi + +num_bad=$(echo "$bad_relocs" | wc -l) +echo "WARNING: $num_bad bad relocations" +echo "$bad_relocs" -- GitLab From 559d1e45a16dcf1542e430ea3dce9ab625be98d0 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Wed, 29 Mar 2023 06:53:29 +0200 Subject: [PATCH 3394/5631] riscv: Use --emit-relocs in order to move .rela.dyn in init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To circumvent an issue where placing the relocations inside the init sections produces empty relocations, use --emit-relocs. But to avoid carrying those relocations in vmlinux, use an intermediate vmlinux.relocs file which is a copy of vmlinux *before* stripping its relocations. Suggested-by: Björn Töpel Suggested-by: Nick Desaulniers Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230329045329.64565-7-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Makefile | 2 +- arch/riscv/Makefile.postlink | 13 +++++++++++++ arch/riscv/boot/Makefile | 7 +++++++ 3 files changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 860b09e409c7..7dc6904a6836 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -8,7 +8,7 @@ OBJCOPYFLAGS := -O binary ifeq ($(CONFIG_RELOCATABLE),y) - LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro --emit-relocs KBUILD_CFLAGS += -fPIE endif ifeq ($(CONFIG_DYNAMIC_FTRACE),y) diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index d5de8d520d3e..a46fc578b30b 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -15,12 +15,25 @@ quiet_cmd_relocs_check = CHKREL $@ cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/riscv/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" +ifdef CONFIG_RELOCATABLE +quiet_cmd_cp_vmlinux_relocs = CPREL vmlinux.relocs +cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs + +quiet_cmd_relocs_strip = STRIPREL $@ +cmd_relocs_strip = $(OBJCOPY) --remove-section='.rel.*' \ + --remove-section='.rel__*' \ + --remove-section='.rela.*' \ + --remove-section='.rela__*' $@ +endif + # `@true` prevents complaint when there is nothing to be done vmlinux: FORCE @true ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) + $(call if_changed,cp_vmlinux_relocs) + $(call if_changed,relocs_strip) endif %.ko: FORCE diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile index c72de7232abb..22b13947bd13 100644 --- a/arch/riscv/boot/Makefile +++ b/arch/riscv/boot/Makefile @@ -33,7 +33,14 @@ $(obj)/xipImage: vmlinux FORCE endif +ifdef CONFIG_RELOCATABLE +vmlinux.relocs: vmlinux + @ (! [ -f vmlinux.relocs ] && echo "vmlinux.relocs can't be found, please remove vmlinux and try again") || true + +$(obj)/Image: vmlinux.relocs FORCE +else $(obj)/Image: vmlinux FORCE +endif $(call if_changed,objcopy) $(obj)/Image.gz: $(obj)/Image FORCE -- GitLab From 3b42877cd53ad4a1b1e3875a0fe537c9c517e635 Mon Sep 17 00:00:00 2001 From: Harald Freudenberger Date: Fri, 14 Apr 2023 17:33:19 +0200 Subject: [PATCH 3395/5631] s390/zcrypt: rework arrays with length zero occurrences Review and rework all the zero length array occurrences within structs to flexible array fields or comment if not used at all. However, some struct fields are there for documentation purpose or to have correct sizeof() evaluation of a struct and thus should not get deleted. Signed-off-by: Harald Freudenberger Acked-by: Heiko Carstens Reviewed-by: Holger Dengler Signed-off-by: Vasily Gorbik --- drivers/s390/crypto/zcrypt_cca_key.h | 2 +- drivers/s390/crypto/zcrypt_ccamisc.c | 74 +++++++++++++-------------- drivers/s390/crypto/zcrypt_ep11misc.c | 2 +- drivers/s390/crypto/zcrypt_msgtype6.c | 4 +- 4 files changed, 40 insertions(+), 42 deletions(-) diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h index 5d68b61c9fe1..f5907b67db29 100644 --- a/drivers/s390/crypto/zcrypt_cca_key.h +++ b/drivers/s390/crypto/zcrypt_cca_key.h @@ -168,7 +168,7 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p) struct t6_keyblock_hdr t6_hdr; struct cca_token_hdr token; struct cca_pvt_ext_crt_sec pvt; - char key_parts[0]; + char key_parts[]; } __packed *key = p; struct cca_public_sec *pub; int short_len, long_len, pad_len, key_len, size; diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 60ba20a133be..8c8808cc68a4 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -450,18 +450,18 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, char rule_array[8]; struct lv1 { u16 len; - u8 clrkey[0]; + u8 clrkey[]; } lv1; - struct lv2 { - u16 len; - struct keyid { - u16 len; - u16 attr; - u8 data[SECKEYBLOBSIZE]; - } keyid; - } lv2; + /* followed by struct lv2 */ } __packed * preqparm; - struct lv2 *plv2; + struct lv2 { + u16 len; + struct keyid { + u16 len; + u16 attr; + u8 data[SECKEYBLOBSIZE]; + } keyid; + } __packed * plv2; struct cmrepparm { u8 subfunc_code[2]; u16 rule_array_len; @@ -512,11 +512,11 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, } preqparm->lv1.len = sizeof(struct lv1) + keysize; memcpy(preqparm->lv1.clrkey, clrkey, keysize); - plv2 = (struct lv2 *)(((u8 *)&preqparm->lv2) + keysize); + plv2 = (struct lv2 *)(((u8 *)preqparm) + sizeof(*preqparm) + keysize); plv2->len = sizeof(struct lv2); plv2->keyid.len = sizeof(struct keyid); plv2->keyid.attr = 0x30; - preqcblk->req_parml = sizeof(struct cmreqparm) + keysize; + preqcblk->req_parml = sizeof(*preqparm) + keysize + sizeof(*plv2); /* fill xcrb struct */ prep_xcrb(&xcrb, cardnr, preqcblk, prepcblk); @@ -761,22 +761,22 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, u16 key_name_2_len; u16 user_data_1_len; u16 user_data_2_len; - u8 key_name_1[0]; - u8 key_name_2[0]; - u8 user_data_1[0]; - u8 user_data_2[0]; + /* u8 key_name_1[]; */ + /* u8 key_name_2[]; */ + /* u8 user_data_1[]; */ + /* u8 user_data_2[]; */ } vud; struct { u16 len; struct { u16 len; u16 flag; - u8 kek_id_1[0]; + /* u8 kek_id_1[]; */ } tlv1; struct { u16 len; u16 flag; - u8 kek_id_2[0]; + /* u8 kek_id_2[]; */ } tlv2; struct { u16 len; @@ -786,17 +786,17 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, struct { u16 len; u16 flag; - u8 gen_key_id_1_label[0]; + /* u8 gen_key_id_1_label[]; */ } tlv4; struct { u16 len; u16 flag; - u8 gen_key_id_2[0]; + /* u8 gen_key_id_2[]; */ } tlv5; struct { u16 len; u16 flag; - u8 gen_key_id_2_label[0]; + /* u8 gen_key_id_2_label[]; */ } tlv6; } kb; } __packed * preqparm; @@ -811,7 +811,7 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, struct { u16 len; u16 flag; - u8 gen_key[0]; /* 120-136 bytes */ + u8 gen_key[]; /* 120-136 bytes */ } tlv1; } kb; } __packed * prepparm; @@ -955,7 +955,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, struct rule_array_block { u8 subfunc_code[2]; u16 rule_array_len; - char rule_array[0]; + char rule_array[]; } __packed * preq_ra_block; struct vud_block { u16 len; @@ -967,7 +967,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, struct { u16 len; u16 flag; /* 0x0063 */ - u8 clr_key[0]; /* clear key value bytes */ + u8 clr_key[]; /* clear key value bytes */ } tlv2; } __packed * preq_vud_block; struct key_block { @@ -975,7 +975,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, struct { u16 len; u16 flag; /* 0x0030 */ - u8 key_token[0]; /* key skeleton */ + u8 key_token[]; /* key skeleton */ } tlv1; } __packed * preq_key_block; struct iprepparm { @@ -989,7 +989,7 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, struct { u16 len; u16 flag; /* 0x0030 */ - u8 key_token[0]; /* key token */ + u8 key_token[]; /* key token */ } tlv1; } kb; } __packed * prepparm; @@ -1201,7 +1201,7 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, u16 len; u16 cca_key_token_len; u16 cca_key_token_flags; - u8 cca_key_token[0]; // 64 or more + u8 cca_key_token[]; /* 64 or more */ } kb; } __packed * preqparm; struct aurepparm { @@ -1370,7 +1370,7 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, u16 len; u16 cca_key_token_len; u16 cca_key_token_flags; - u8 cca_key_token[0]; + u8 cca_key_token[]; } kb; } __packed * preqparm; struct aurepparm { @@ -1387,17 +1387,15 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, u8 form; u8 pad1[3]; u16 keylen; - u8 key[0]; /* the key (keylen bytes) */ - u16 keyattrlen; - u8 keyattr[32]; - u8 pad2[1]; - u8 vptype; - u8 vp[32]; /* verification pattern */ + u8 key[]; /* the key (keylen bytes) */ + /* u16 keyattrlen; */ + /* u8 keyattr[32]; */ + /* u8 pad2[1]; */ + /* u8 vptype; */ + /* u8 vp[32]; verification pattern */ } ckb; } vud; - struct { - u16 len; - } kb; + /* followed by a key block */ } __packed * prepparm; int keylen = ((struct eccprivkeytoken *)key)->len; @@ -1525,7 +1523,7 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, size_t parmbsize = sizeof(struct fqreqparm); struct fqrepparm { u8 subfunc_code[2]; - u8 lvdata[0]; + u8 lvdata[]; } __packed * prepparm; /* get already prepared memory for 2 cprbs with param block each */ diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index b1c29017be5b..f67d19d08571 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -1275,7 +1275,7 @@ int ep11_kblob2protkey(u16 card, u16 dom, const u8 *keyblob, size_t keybloblen, u32 pkeybitsize; u64 pkeysize; u8 res2[8]; - u8 pkey[0]; + u8 pkey[]; } __packed * wki; const u8 *key; struct ep11kblob_header *hdr; diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 7c7ff6560858..2f9bf23fbb44 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -208,7 +208,7 @@ static int icamex_msg_to_type6mex_msgx(struct zcrypt_queue *zq, struct CPRBX cprbx; struct function_and_rules_block fr; unsigned short length; - char text[0]; + char text[]; } __packed * msg = ap_msg->msg; int size; @@ -278,7 +278,7 @@ static int icacrt_msg_to_type6crt_msgx(struct zcrypt_queue *zq, struct CPRBX cprbx; struct function_and_rules_block fr; unsigned short length; - char text[0]; + char text[]; } __packed * msg = ap_msg->msg; int size; -- GitLab From 46c4d945ea1f9beebf49148b0d4aafb44e41ceb6 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 4 Apr 2023 14:47:55 +0200 Subject: [PATCH 3396/5631] s390/cpum_cf: introduce static CPU counter facility information The CPU measurement facility counter information instruction qctri() retrieves information about the available counter sets. The information varies between machine generations, but is constant when running on a particular machine. For example the CPU measurement facility counter first and second version numbers determine the amount of counters in a counter set. This information never changes. The counter sets are identical for all CPUs in the system. It does not matter which CPU performs the instruction. Authorization control of the CPU Measurement facility can only be changed in the activation profile while the LPAR is not running. Retrieve the CPU measurement counter information at device driver initialization time and use its constant values. Function validate_ctr_version() verifies if a user provided CPU Measurement counter facility counter is valid and defined. It now uses the newly introduced static CPU counter facility information. To avoid repeated recalculation of the counter set sizes (numbers of counters per set), which never changes on a running machine, calculate the counter set size once at device driver initialization and store the result in an array. Functions cpum_cf_make_setsize() and cpum_cf_read_setsize() are introduced. Finally remove cpu_cf_events::info member and use the static CPU counter facility information instead. Signed-off-by: Thomas Richter Acked-by: Heiko Carstens Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 132 ++++++++++++++++---------------- 1 file changed, 65 insertions(+), 67 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 96b581967334..e235b5b83d3c 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -76,7 +76,6 @@ static inline int ctr_stcctm(enum cpumf_ctr_set set, u64 range, u64 *dest) } struct cpu_cf_events { - struct cpumf_ctr_info info; atomic_t ctr_set[CPUMF_CTR_SET_MAX]; u64 state; /* For perf_event_open SVC */ u64 dev_state; /* For /dev/hwctr */ @@ -95,6 +94,15 @@ static DEFINE_PER_CPU(struct cpu_cf_events, cpu_cf_events); static unsigned int cfdiag_cpu_speed; /* CPU speed for CF_DIAG trailer */ static debug_info_t *cf_dbg; +/* + * The CPU Measurement query counter information instruction contains + * information which varies per machine generation, but is constant and + * does not change when running on a particular machine, such as counter + * first and second version number. This is needed to determine the size + * of counter sets. Extract this information at device driver initialization. + */ +static struct cpumf_ctr_info cpumf_ctr_info; + #define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */ /* interval in seconds */ @@ -167,11 +175,10 @@ struct cf_trailer_entry { /* CPU-M CF_DIAG trailer (64 byte) */ /* Create the trailer data at the end of a page. */ static void cfdiag_trailer(struct cf_trailer_entry *te) { - struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); struct cpuid cpuid; - te->cfvn = cpuhw->info.cfvn; /* Counter version numbers */ - te->csvn = cpuhw->info.csvn; + te->cfvn = cpumf_ctr_info.cfvn; /* Counter version numbers */ + te->csvn = cpumf_ctr_info.csvn; get_cpu_id(&cpuid); /* Machine type */ te->mach_type = cpuid.machine; @@ -184,50 +191,60 @@ static void cfdiag_trailer(struct cf_trailer_entry *te) } /* - * Return the maximum possible counter set size (in number of 8 byte counters) - * depending on type and model number. + * The number of counters per counter set varies between machine generations, + * but is constant when running on a particular machine generation. + * Determine each counter set size at device driver initialization and + * retrieve it later. */ -static size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset, - struct cpumf_ctr_info *info) +static size_t cpumf_ctr_setsizes[CPUMF_CTR_SET_MAX]; +static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset) { size_t ctrset_size = 0; switch (ctrset) { case CPUMF_CTR_SET_BASIC: - if (info->cfvn >= 1) + if (cpumf_ctr_info.cfvn >= 1) ctrset_size = 6; break; case CPUMF_CTR_SET_USER: - if (info->cfvn == 1) + if (cpumf_ctr_info.cfvn == 1) ctrset_size = 6; - else if (info->cfvn >= 3) + else if (cpumf_ctr_info.cfvn >= 3) ctrset_size = 2; break; case CPUMF_CTR_SET_CRYPTO: - if (info->csvn >= 1 && info->csvn <= 5) + if (cpumf_ctr_info.csvn >= 1 && cpumf_ctr_info.csvn <= 5) ctrset_size = 16; - else if (info->csvn == 6 || info->csvn == 7) + else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7) ctrset_size = 20; break; case CPUMF_CTR_SET_EXT: - if (info->csvn == 1) + if (cpumf_ctr_info.csvn == 1) ctrset_size = 32; - else if (info->csvn == 2) + else if (cpumf_ctr_info.csvn == 2) ctrset_size = 48; - else if (info->csvn >= 3 && info->csvn <= 5) + else if (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5) ctrset_size = 128; - else if (info->csvn == 6 || info->csvn == 7) + else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7) ctrset_size = 160; break; case CPUMF_CTR_SET_MT_DIAG: - if (info->csvn > 3) + if (cpumf_ctr_info.csvn > 3) ctrset_size = 48; break; case CPUMF_CTR_SET_MAX: break; } + cpumf_ctr_setsizes[ctrset] = ctrset_size; +} - return ctrset_size; +/* + * Return the maximum possible counter set size (in number of 8 byte counters) + * depending on type and model number. + */ +static size_t cpum_cf_read_setsize(enum cpumf_ctr_set ctrset) +{ + return cpumf_ctr_setsizes[ctrset]; } /* Read a counter set. The counter set number determines the counter set and @@ -248,14 +265,13 @@ static size_t cpum_cf_ctrset_size(enum cpumf_ctr_set ctrset, static size_t cfdiag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, size_t room, bool error_ok) { - struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events); size_t ctrset_size, need = 0; int rc = 3; /* Assume write failure */ ctrdata->def = CF_DIAG_CTRSET_DEF; ctrdata->set = ctrset; ctrdata->res1 = 0; - ctrset_size = cpum_cf_ctrset_size(ctrset, &cpuhw->info); + ctrset_size = cpum_cf_read_setsize(ctrset); if (ctrset_size) { /* Save data */ need = ctrset_size * sizeof(u64) + sizeof(*ctrdata); @@ -269,10 +285,6 @@ static size_t cfdiag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset, need = 0; } - debug_sprintf_event(cf_dbg, 3, - "%s ctrset %d ctrset_size %zu cfvn %d csvn %d" - " need %zd rc %d\n", __func__, ctrset, ctrset_size, - cpuhw->info.cfvn, cpuhw->info.csvn, need, rc); return need; } @@ -380,37 +392,34 @@ static enum cpumf_ctr_set get_counter_set(u64 event) static int validate_ctr_version(const struct hw_perf_event *hwc, enum cpumf_ctr_set set) { - struct cpu_cf_events *cpuhw; - int err = 0; u16 mtdiag_ctl; - - cpuhw = &get_cpu_var(cpu_cf_events); + int err = 0; /* check required version for counter sets */ switch (set) { case CPUMF_CTR_SET_BASIC: case CPUMF_CTR_SET_USER: - if (cpuhw->info.cfvn < 1) + if (cpumf_ctr_info.cfvn < 1) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_CRYPTO: - if ((cpuhw->info.csvn >= 1 && cpuhw->info.csvn <= 5 && + if ((cpumf_ctr_info.csvn >= 1 && cpumf_ctr_info.csvn <= 5 && hwc->config > 79) || - (cpuhw->info.csvn >= 6 && hwc->config > 83)) + (cpumf_ctr_info.csvn >= 6 && hwc->config > 83)) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_EXT: - if (cpuhw->info.csvn < 1) + if (cpumf_ctr_info.csvn < 1) err = -EOPNOTSUPP; - if ((cpuhw->info.csvn == 1 && hwc->config > 159) || - (cpuhw->info.csvn == 2 && hwc->config > 175) || - (cpuhw->info.csvn >= 3 && cpuhw->info.csvn <= 5 + if ((cpumf_ctr_info.csvn == 1 && hwc->config > 159) || + (cpumf_ctr_info.csvn == 2 && hwc->config > 175) || + (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5 && hwc->config > 255) || - (cpuhw->info.csvn >= 6 && hwc->config > 287)) + (cpumf_ctr_info.csvn >= 6 && hwc->config > 287)) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_MT_DIAG: - if (cpuhw->info.csvn <= 3) + if (cpumf_ctr_info.csvn <= 3) err = -EOPNOTSUPP; /* * MT-diagnostic counters are read-only. The counter set @@ -425,35 +434,30 @@ static int validate_ctr_version(const struct hw_perf_event *hwc, * counter set is enabled and active. */ mtdiag_ctl = cpumf_ctr_ctl[CPUMF_CTR_SET_MT_DIAG]; - if (!((cpuhw->info.auth_ctl & mtdiag_ctl) && - (cpuhw->info.enable_ctl & mtdiag_ctl) && - (cpuhw->info.act_ctl & mtdiag_ctl))) + if (!((cpumf_ctr_info.auth_ctl & mtdiag_ctl) && + (cpumf_ctr_info.enable_ctl & mtdiag_ctl) && + (cpumf_ctr_info.act_ctl & mtdiag_ctl))) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_MAX: err = -EOPNOTSUPP; } - put_cpu_var(cpu_cf_events); return err; } static int validate_ctr_auth(const struct hw_perf_event *hwc) { - struct cpu_cf_events *cpuhw; - int err = 0; - - cpuhw = &get_cpu_var(cpu_cf_events); + int err = -ENOENT; /* Check authorization for cpu counter sets. * If the particular CPU counter set is not authorized, * return with -ENOENT in order to fall back to other * PMUs that might suffice the event request. */ - if (!(hwc->config_base & cpuhw->info.auth_ctl)) - err = -ENOENT; + if ((hwc->config_base & cpumf_ctr_info.auth_ctl)) + err = 0; - put_cpu_var(cpu_cf_events); return err; } @@ -509,8 +513,6 @@ static void cpum_cf_setup_cpu(void *flags) switch ((unsigned long)flags) { case PMC_INIT: - memset(&cpuhw->info, 0, sizeof(cpuhw->info)); - qctri(&cpuhw->info); cpuhw->flags |= PMU_F_RESERVED; break; @@ -977,7 +979,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code, /* counter authorization change alert */ if (alert & CPU_MF_INT_CF_CACA) - qctri(&cpuhw->info); + qctri(&cpumf_ctr_info); /* loss of counter data alert */ if (alert & CPU_MF_INT_CF_LCDA) @@ -994,9 +996,14 @@ static int __init cpumf_pmu_init(void) { int rc; - if (!cpum_cf_avail()) + /* Extract counter measurement facility information */ + if (!cpum_cf_avail() || qctri(&cpumf_ctr_info)) return -ENODEV; + /* Determine and store counter set sizes for later reference */ + for (rc = CPUMF_CTR_SET_BASIC; rc < CPUMF_CTR_SET_MAX; ++rc) + cpum_cf_make_setsize(rc); + /* * Clear bit 15 of cr0 to unauthorize problem-state to * extract measurement counters @@ -1263,21 +1270,19 @@ static int cfset_all_start(struct cfset_request *req) */ static size_t cfset_needspace(unsigned int sets) { - struct cpu_cf_events *cpuhw = get_cpu_ptr(&cpu_cf_events); size_t bytes = 0; int i; for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { if (!(sets & cpumf_ctr_ctl[i])) continue; - bytes += cpum_cf_ctrset_size(i, &cpuhw->info) * sizeof(u64) + + bytes += cpum_cf_read_setsize(i) * sizeof(u64) + sizeof(((struct s390_ctrset_setdata *)0)->set) + sizeof(((struct s390_ctrset_setdata *)0)->no_cnts); } bytes = sizeof(((struct s390_ctrset_read *)0)->no_cpus) + nr_cpu_ids * (bytes + sizeof(((struct s390_ctrset_cpudata *)0)->cpu_nr) + sizeof(((struct s390_ctrset_cpudata *)0)->no_sets)); - put_cpu_ptr(&cpu_cf_events); return bytes; } @@ -1351,7 +1356,7 @@ static void cfset_cpu_read(void *parm) if (!(p->sets & cpumf_ctr_ctl[set])) continue; /* Counter set not in list */ - set_size = cpum_cf_ctrset_size(set, &cpuhw->info); + set_size = cpum_cf_read_setsize(set); space = sizeof(cpuhw->data) - cpuhw->used; space = cfset_cpuset_read(sp, set, set_size, space); if (space) { @@ -1562,16 +1567,13 @@ static void cfdiag_read(struct perf_event *event) static int get_authctrsets(void) { - struct cpu_cf_events *cpuhw; unsigned long auth = 0; enum cpumf_ctr_set i; - cpuhw = &get_cpu_var(cpu_cf_events); for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { - if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i]) + if (cpumf_ctr_info.auth_ctl & cpumf_ctr_ctl[i]) auth |= cpumf_ctr_ctl[i]; } - put_cpu_var(cpu_cf_events); return auth; } @@ -1709,7 +1711,7 @@ static size_t cfdiag_maxsize(struct cpumf_ctr_info *info) enum cpumf_ctr_set i; for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) { - size_t size = cpum_cf_ctrset_size(i, info); + size_t size = cpum_cf_read_setsize(i); if (size) max_size += size * sizeof(u64) + @@ -1743,16 +1745,12 @@ static void cfdiag_get_cpu_speed(void) static int cfset_init(void) { - struct cpumf_ctr_info info; size_t need; int rc; - if (qctri(&info)) - return -ENODEV; - cfdiag_get_cpu_speed(); /* Make sure the counter set data fits into predefined buffer. */ - need = cfdiag_maxsize(&info); + need = cfdiag_maxsize(&cpumf_ctr_info); if (need > sizeof(((struct cpu_cf_events *)0)->start)) { pr_err("Insufficient memory for PMU(cpum_cf_diag) need=%zu\n", need); -- GitLab From 9ae9b868aeaad377f6315d7196a43e8827e24cb3 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 6 Apr 2023 11:32:18 +0200 Subject: [PATCH 3397/5631] s390/cpum_cf: provide counter number to validate_ctr_version() Function validate_ctr_version() first parameter is a pointer to a large structure, but only member hw_perf_event::config is used. Supply this structure member value in the function invocation. No functional change. Signed-off-by: Thomas Richter Acked-by: Heiko Carstens Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index e235b5b83d3c..ecbb89b76906 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -389,8 +389,7 @@ static enum cpumf_ctr_set get_counter_set(u64 event) return set; } -static int validate_ctr_version(const struct hw_perf_event *hwc, - enum cpumf_ctr_set set) +static int validate_ctr_version(const u64 config, enum cpumf_ctr_set set) { u16 mtdiag_ctl; int err = 0; @@ -404,18 +403,17 @@ static int validate_ctr_version(const struct hw_perf_event *hwc, break; case CPUMF_CTR_SET_CRYPTO: if ((cpumf_ctr_info.csvn >= 1 && cpumf_ctr_info.csvn <= 5 && - hwc->config > 79) || - (cpumf_ctr_info.csvn >= 6 && hwc->config > 83)) + config > 79) || (cpumf_ctr_info.csvn >= 6 && config > 83)) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_EXT: if (cpumf_ctr_info.csvn < 1) err = -EOPNOTSUPP; - if ((cpumf_ctr_info.csvn == 1 && hwc->config > 159) || - (cpumf_ctr_info.csvn == 2 && hwc->config > 175) || - (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5 - && hwc->config > 255) || - (cpumf_ctr_info.csvn >= 6 && hwc->config > 287)) + if ((cpumf_ctr_info.csvn == 1 && config > 159) || + (cpumf_ctr_info.csvn == 2 && config > 175) || + (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5 && + config > 255) || + (cpumf_ctr_info.csvn >= 6 && config > 287)) err = -EOPNOTSUPP; break; case CPUMF_CTR_SET_MT_DIAG: @@ -677,7 +675,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) /* Finally, validate version and authorization of the counter set */ err = validate_ctr_auth(hwc); if (!err) - err = validate_ctr_version(hwc, set); + err = validate_ctr_version(hwc->config, set); return err; } -- GitLab From 1a33aee1dc2476c5937a0890f2dfc228a165f364 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Thu, 6 Apr 2023 11:40:42 +0200 Subject: [PATCH 3398/5631] s390/cpum_cf: remove function validate_ctr_auth() by inline code Remove function validate_ctr_auth() and replace this very small function by its body. No functional change. Signed-off-by: Thomas Richter Acked-by: Heiko Carstens Acked-by: Sumanth Korikkar Signed-off-by: Vasily Gorbik --- arch/s390/kernel/perf_cpum_cf.c | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index ecbb89b76906..cf1b6e8a708d 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -444,21 +444,6 @@ static int validate_ctr_version(const u64 config, enum cpumf_ctr_set set) return err; } -static int validate_ctr_auth(const struct hw_perf_event *hwc) -{ - int err = -ENOENT; - - /* Check authorization for cpu counter sets. - * If the particular CPU counter set is not authorized, - * return with -ENOENT in order to fall back to other - * PMUs that might suffice the event request. - */ - if ((hwc->config_base & cpumf_ctr_info.auth_ctl)) - err = 0; - - return err; -} - /* * Change the CPUMF state to active. * Enable and activate the CPU-counter sets according @@ -596,7 +581,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) struct perf_event_attr *attr = &event->attr; struct hw_perf_event *hwc = &event->hw; enum cpumf_ctr_set set; - int err = 0; u64 ev; switch (type) { @@ -672,12 +656,15 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) cpumf_hw_inuse(); event->destroy = hw_perf_event_destroy; - /* Finally, validate version and authorization of the counter set */ - err = validate_ctr_auth(hwc); - if (!err) - err = validate_ctr_version(hwc->config, set); - - return err; + /* + * Finally, validate version and authorization of the counter set. + * If the particular CPU counter set is not authorized, + * return with -ENOENT in order to fall back to other + * PMUs that might suffice the event request. + */ + if (!(hwc->config_base & cpumf_ctr_info.auth_ctl)) + return -ENOENT; + return validate_ctr_version(hwc->config, set); } /* Events CPU_CYLCES and INSTRUCTIONS can be submitted with two different -- GitLab From 7a04d491edf4766e7724671355b1ab27cae81a4a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 3 Apr 2023 08:44:36 +0200 Subject: [PATCH 3399/5631] s390/kexec: turn DAT mode off immediately before purgatory The kernel code is not guaranteed DAT-off mode safe. Turn the DAT mode off immediately before entering the purgatory. Further, to avoid subtle side effects reset the system immediately before turning DAT mode off while making all necessary preparations in advance. Signed-off-by: Alexander Gordeev Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/machine_kexec.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 2a8e73266428..eb473fc835b2 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -254,14 +254,13 @@ static void __do_machine_kexec(void *data) relocate_kernel_t data_mover; struct kimage *image = data; - s390_reset_system(); data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); - - __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ - /* Call the moving routine */ diag308_subcode = DIAG308_CLEAR_RESET; if (sclp.has_iplcc) diag308_subcode |= DIAG308_FLAG_EI; + s390_reset_system(); + + __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ (*data_mover)(&image->head, image->start, diag308_subcode); /* Die if kexec returns */ -- GitLab From 86295cb4530dfbc2315ca5997502dad03748e5dd Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 3 Apr 2023 08:44:37 +0200 Subject: [PATCH 3400/5631] s390/kdump: cleanup do_start_kdump() prototype and usage Avoid unnecessary run-time and compile-time type conversions of do_start_kdump() function return value and parameter. Signed-off-by: Alexander Gordeev Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/machine_kexec.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index eb473fc835b2..3e0fd01a192a 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -111,9 +111,8 @@ static noinline void __machine_kdump(void *image) store_status(__do_machine_kdump, image); } -static unsigned long do_start_kdump(unsigned long addr) +static int do_start_kdump(struct kimage *image) { - struct kimage *image = (struct kimage *) addr; int (*start_kdump)(int) = (void *)image->start; int rc; @@ -134,8 +133,8 @@ static bool kdump_csum_valid(struct kimage *image) int rc; preempt_disable(); - rc = call_on_stack(1, S390_lowcore.nodat_stack, unsigned long, do_start_kdump, - unsigned long, (unsigned long)image); + rc = call_on_stack(1, S390_lowcore.nodat_stack, int, do_start_kdump, + struct kimage *, image); preempt_enable(); return rc == 0; #else -- GitLab From 39218bcf941ab1a5eabbf350c0f7a1f1325434b0 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 3 Apr 2023 08:44:38 +0200 Subject: [PATCH 3401/5631] s390/kdump: fix virtual vs physical address confusion Fix virtual vs physical address confusion (which currently are the same). Signed-off-by: Alexander Gordeev Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/machine_kexec.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 3e0fd01a192a..fb887674e159 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -29,8 +29,7 @@ #include #include -typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long, - unsigned long); +typedef void (*relocate_kernel_t)(unsigned long, unsigned long, unsigned long); extern const unsigned char relocate_kernel[]; extern const unsigned long long relocate_kernel_len; @@ -58,7 +57,7 @@ static void __do_machine_kdump(void *image) * prefix register of this CPU to zero */ memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), - (void *)(prefix + __LC_FPREGS_SAVE_AREA), 512); + phys_to_virt(prefix + __LC_FPREGS_SAVE_AREA), 512); __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); start_kdump = (void *)((struct kimage *) image)->start; @@ -209,7 +208,7 @@ int machine_kexec_prepare(struct kimage *image) return -EINVAL; /* Get the destination where the assembler code should be copied to.*/ - reboot_code_buffer = (void *) page_to_phys(image->control_code_page); + reboot_code_buffer = page_to_virt(image->control_code_page); /* Then copy it */ memcpy(reboot_code_buffer, relocate_kernel, relocate_kernel_len); @@ -249,18 +248,18 @@ void machine_crash_shutdown(struct pt_regs *regs) */ static void __do_machine_kexec(void *data) { - unsigned long diag308_subcode; - relocate_kernel_t data_mover; + unsigned long data_mover, entry, diag308_subcode; struct kimage *image = data; - data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page); + data_mover = page_to_phys(image->control_code_page); + entry = virt_to_phys(&image->head); diag308_subcode = DIAG308_CLEAR_RESET; if (sclp.has_iplcc) diag308_subcode |= DIAG308_FLAG_EI; s390_reset_system(); __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ - (*data_mover)(&image->head, image->start, diag308_subcode); + (*(relocate_kernel_t)data_mover)(entry, image->start, diag308_subcode); /* Die if kexec returns */ disabled_wait(); -- GitLab From 82caf7aba107dbc0e70c330786bed9961a098ab0 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 3 Apr 2023 08:44:39 +0200 Subject: [PATCH 3402/5631] s390/kdump: rework invocation of DAT-off code Calling kdump kernel is a two-step process that involves invocation of the purgatory code: first time - to verify the new kernel checksum and second time - to call the new kernel itself. The purgatory code operates on real addresses and does not expect any memory protection. Therefore, before the purgatory code is entered the DAT mode is always turned off. However, it is only restored upon return from the new kernel checksum verification. In case the purgatory was called to start the new kernel and failed the control is returned to the old kernel, but the DAT mode continues staying off. The new kernel start failure is unlikely and leads to the disabled wait state anyway. Still that poses a risk, since the kernel code in general is not DAT-off safe and even calling the disabled_wait() function might crash. Introduce call_nodat() macro that allows entering DAT-off mode, calling an arbitrary function and restoring DAT mode back on. Switch all invocations of DAT-off code to that macro and avoid the above described scenario altogether. Name the call_nodat() macro in small letters after the already existing call_on_stack() and put it to the same header file. Signed-off-by: Alexander Gordeev Reviewed-by: Heiko Carstens [hca@linux.ibm.com: some small modifications to call_nodat() macro] Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/stacktrace.h | 47 ++++++++++++++++++++++++++++++ arch/s390/kernel/machine_kexec.c | 28 +++++++++--------- 2 files changed, 61 insertions(+), 14 deletions(-) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 25e833cd883c..1966422cf030 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -189,4 +189,51 @@ static __always_inline unsigned long get_stack_pointer(struct task_struct *task, (rettype)r2; \ }) +/* + * Use call_nodat() to call a function with DAT disabled. + * Proper sign and zero extension of function arguments is done. + * Usage: + * + * rc = call_nodat(nr, rettype, fn, t1, a1, t2, a2, ...) + * + * - nr specifies the number of function arguments of fn. + * - fn is the function to be called, where fn is a physical address. + * - rettype is the return type of fn. + * - t1, a1, ... are pairs, where t1 must match the type of the first + * argument of fn, t2 the second, etc. a1 is the corresponding + * first function argument (not name), etc. + * + * fn() is called with standard C function call ABI, with the exception + * that no useful stackframe or stackpointer is passed via register 15. + * Therefore the called function must not use r15 to access the stack. + */ +#define call_nodat(nr, rettype, fn, ...) \ +({ \ + rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = (fn); \ + psw_t psw_enter, psw_leave; \ + CALL_LARGS_##nr(__VA_ARGS__); \ + CALL_REGS_##nr; \ + \ + CALL_TYPECHECK_##nr(__VA_ARGS__); \ + psw_enter.mask = PSW_KERNEL_BITS & ~PSW_MASK_DAT; \ + psw_enter.addr = (unsigned long)__fn; \ + asm volatile( \ + " epsw 0,1\n" \ + " risbg 1,0,0,31,32\n" \ + " larl 7,1f\n" \ + " stg 1,%[psw_leave]\n" \ + " stg 7,8+%[psw_leave]\n" \ + " la 7,%[psw_leave]\n" \ + " lra 7,0(7)\n" \ + " larl 1,0f\n" \ + " lra 14,0(1)\n" \ + " lpswe %[psw_enter]\n" \ + "0: lpswe 0(7)\n" \ + "1:\n" \ + : CALL_FMT_##nr, [psw_leave] "=Q" (psw_leave) \ + : [psw_enter] "Q" (psw_enter) \ + : "7", CALL_CLOBBER_##nr); \ + (rettype)r2; \ +}) + #endif /* _ASM_S390_STACKTRACE_H */ diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index fb887674e159..f5d8abf3b4fb 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -30,6 +30,7 @@ #include typedef void (*relocate_kernel_t)(unsigned long, unsigned long, unsigned long); +typedef int (*purgatory_t)(int); extern const unsigned char relocate_kernel[]; extern const unsigned long long relocate_kernel_len; @@ -40,11 +41,14 @@ extern const unsigned long long relocate_kernel_len; * Reset the system, copy boot CPU registers to absolute zero, * and jump to the kdump image */ -static void __do_machine_kdump(void *image) +static void __do_machine_kdump(void *data) { - int (*start_kdump)(int); + struct kimage *image = data; + purgatory_t purgatory; unsigned long prefix; + purgatory = (purgatory_t)image->start; + /* store_status() saved the prefix register to lowcore */ prefix = (unsigned long) S390_lowcore.prefixreg_save_area; @@ -59,11 +63,9 @@ static void __do_machine_kdump(void *image) memcpy(absolute_pointer(__LC_FPREGS_SAVE_AREA), phys_to_virt(prefix + __LC_FPREGS_SAVE_AREA), 512); - __load_psw_mask(PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA); - start_kdump = (void *)((struct kimage *) image)->start; - start_kdump(1); + call_nodat(1, int, purgatory, int, 1); - /* Die if start_kdump returns */ + /* Die if kdump returns */ disabled_wait(); } @@ -112,13 +114,9 @@ static noinline void __machine_kdump(void *image) static int do_start_kdump(struct kimage *image) { - int (*start_kdump)(int) = (void *)image->start; - int rc; + purgatory_t purgatory = (purgatory_t)image->start; - __arch_local_irq_stnsm(0xfb); /* disable DAT */ - rc = start_kdump(0); - __arch_local_irq_stosm(0x04); /* enable DAT */ - return rc; + return call_nodat(1, int, purgatory, int, 0); } #endif /* CONFIG_CRASH_DUMP */ @@ -258,8 +256,10 @@ static void __do_machine_kexec(void *data) diag308_subcode |= DIAG308_FLAG_EI; s390_reset_system(); - __arch_local_irq_stnsm(0xfb); /* disable DAT - avoid no-execute */ - (*(relocate_kernel_t)data_mover)(entry, image->start, diag308_subcode); + call_nodat(3, void, (relocate_kernel_t)data_mover, + unsigned long, entry, + unsigned long, image->start, + unsigned long, diag308_subcode); /* Die if kexec returns */ disabled_wait(); -- GitLab From 2d1b21eceaf0765d60b543b2b8e26c2f55517259 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 3 Apr 2023 08:44:40 +0200 Subject: [PATCH 3403/5631] s390/kdump: remove nodat stack restriction for calling nodat functions To allow calling of DAT-off code from kernel the stack needs to be switched to nodat_stack (or other stack mapped as 1:1). Before call_nodat() macro was introduced that was necessary to provide the very same memory address for STNSM and STOSM instructions. If the kernel would stay on a random stack (e.g. a virtually mapped one) then a virtual address provided for STNSM instruction could differ from the physical address needed for the corresponding STOSM instruction. After call_nodat() macro is introduced the kernel stack does not need to be mapped 1:1 anymore, since the macro stores the physical memory address of return PSW in a register before entering DAT-off mode. This way the return LPSWE instruction is able to pick the correct memory location and restore the DAT-on mode. That however might fail in case the 16-byte return PSW happened to cross page boundary: PSW mask and PSW address could end up in two separate non-contiguous physical pages. Align the return PSW on 16-byte boundary so it always fits into a single physical page. As result any stack (including the virtually mapped one) could be used for calling DAT-off code and prior switching to nodat_stack becomes unnecessary. Signed-off-by: Alexander Gordeev Reviewed-by: Heiko Carstens Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/stacktrace.h | 4 +++- arch/s390/kernel/machine_kexec.c | 13 ++----------- 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 1966422cf030..78f7b729b65f 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -210,7 +210,9 @@ static __always_inline unsigned long get_stack_pointer(struct task_struct *task, #define call_nodat(nr, rettype, fn, ...) \ ({ \ rettype (*__fn)(CALL_PARM_##nr(__VA_ARGS__)) = (fn); \ - psw_t psw_enter, psw_leave; \ + /* aligned since psw_leave must not cross page boundary */ \ + psw_t __aligned(16) psw_leave; \ + psw_t psw_enter; \ CALL_LARGS_##nr(__VA_ARGS__); \ CALL_REGS_##nr; \ \ diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index f5d8abf3b4fb..6d9276c096a6 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -112,13 +112,6 @@ static noinline void __machine_kdump(void *image) store_status(__do_machine_kdump, image); } -static int do_start_kdump(struct kimage *image) -{ - purgatory_t purgatory = (purgatory_t)image->start; - - return call_nodat(1, int, purgatory, int, 0); -} - #endif /* CONFIG_CRASH_DUMP */ /* @@ -127,12 +120,10 @@ static int do_start_kdump(struct kimage *image) static bool kdump_csum_valid(struct kimage *image) { #ifdef CONFIG_CRASH_DUMP + purgatory_t purgatory = (purgatory_t)image->start; int rc; - preempt_disable(); - rc = call_on_stack(1, S390_lowcore.nodat_stack, int, do_start_kdump, - struct kimage *, image); - preempt_enable(); + rc = call_nodat(1, int, purgatory, int, 0); return rc == 0; #else return false; -- GitLab From e48b6853d81b6b48dc238d328700536b425c8e70 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 16 Apr 2023 20:15:17 +0200 Subject: [PATCH 3404/5631] s390/kasan: remove override of mem*() functions The kasan mem*() functions are not used anymore since s390 has switched to GENERIC_ENTRY and commit 69d4c0d32186 ("entry, kasan, x86: Disallow overriding mem*() functions"). Therefore remove the now dead code, similar to x86. While at it also use the SYM* macros in mem.S. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/string.h | 15 +++------------ arch/s390/lib/mem.S | 24 +++++++++++++++--------- 2 files changed, 18 insertions(+), 21 deletions(-) diff --git a/arch/s390/include/asm/string.h b/arch/s390/include/asm/string.h index 3fae93ddb322..351685de53d2 100644 --- a/arch/s390/include/asm/string.h +++ b/arch/s390/include/asm/string.h @@ -55,18 +55,6 @@ char *strstr(const char *s1, const char *s2); #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) -extern void *__memcpy(void *dest, const void *src, size_t n); -extern void *__memset(void *s, int c, size_t n); -extern void *__memmove(void *dest, const void *src, size_t n); - -/* - * For files that are not instrumented (e.g. mm/slub.c) we - * should use not instrumented version of mem* functions. - */ - -#define memcpy(dst, src, len) __memcpy(dst, src, len) -#define memmove(dst, src, len) __memmove(dst, src, len) -#define memset(s, c, n) __memset(s, c, n) #define strlen(s) __strlen(s) #define __no_sanitize_prefix_strfunc(x) __##x @@ -79,6 +67,9 @@ extern void *__memmove(void *dest, const void *src, size_t n); #define __no_sanitize_prefix_strfunc(x) x #endif /* defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) */ +void *__memcpy(void *dest, const void *src, size_t n); +void *__memset(void *s, int c, size_t n); +void *__memmove(void *dest, const void *src, size_t n); void *__memset16(uint16_t *s, uint16_t v, size_t count); void *__memset32(uint32_t *s, uint32_t v, size_t count); void *__memset64(uint64_t *s, uint64_t v, size_t count); diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index dc0874f2e203..2e0480424f40 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -14,8 +14,7 @@ /* * void *memmove(void *dest, const void *src, size_t n) */ -WEAK(memmove) -ENTRY(__memmove) +SYM_FUNC_START(__memmove) ltgr %r4,%r4 lgr %r1,%r2 jz .Lmemmove_exit @@ -48,7 +47,10 @@ ENTRY(__memmove) BR_EX %r14 .Lmemmove_mvc: mvc 0(1,%r1),0(%r3) -ENDPROC(__memmove) +SYM_FUNC_END(__memmove) +EXPORT_SYMBOL(__memmove) + +SYM_FUNC_ALIAS(memmove, __memmove) EXPORT_SYMBOL(memmove) /* @@ -66,8 +68,7 @@ EXPORT_SYMBOL(memmove) * return __builtin_memset(s, c, n); * } */ -WEAK(memset) -ENTRY(__memset) +SYM_FUNC_START(__memset) ltgr %r4,%r4 jz .Lmemset_exit ltgr %r3,%r3 @@ -111,7 +112,10 @@ ENTRY(__memset) xc 0(1,%r1),0(%r1) .Lmemset_mvc: mvc 1(1,%r1),0(%r1) -ENDPROC(__memset) +SYM_FUNC_END(__memset) +EXPORT_SYMBOL(__memset) + +SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) /* @@ -119,8 +123,7 @@ EXPORT_SYMBOL(memset) * * void *memcpy(void *dest, const void *src, size_t n) */ -WEAK(memcpy) -ENTRY(__memcpy) +SYM_FUNC_START(__memcpy) ltgr %r4,%r4 jz .Lmemcpy_exit aghi %r4,-1 @@ -141,7 +144,10 @@ ENTRY(__memcpy) j .Lmemcpy_remainder .Lmemcpy_mvc: mvc 0(1,%r1),0(%r3) -ENDPROC(__memcpy) +SYM_FUNC_END(__memcpy) +EXPORT_SYMBOL(__memcpy) + +SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) /* -- GitLab From 45769052ae77c0fb0f846c151bb0a845cf5d4237 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:04 +0200 Subject: [PATCH 3405/5631] s390/lib: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/lib/mem.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 2e0480424f40..5a9a55de2e10 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -158,7 +158,7 @@ EXPORT_SYMBOL(memcpy) * void *__memset64(uint64_t *s, uint64_t v, size_t count) */ .macro __MEMSET bits,bytes,insn -ENTRY(__memset\bits) +SYM_FUNC_START(__memset\bits) ltgr %r4,%r4 jz .L__memset_exit\bits cghi %r4,\bytes @@ -184,7 +184,7 @@ ENTRY(__memset\bits) BR_EX %r14 .L__memset_mvc\bits: mvc \bytes(1,%r1),0(%r1) -ENDPROC(__memset\bits) +SYM_FUNC_END(__memset\bits) .endm __MEMSET 16,2,sth -- GitLab From ac0c06a1dc8702209e651975ce6f54715f7321c8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:05 +0200 Subject: [PATCH 3406/5631] s390/amode31: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/text_amode31.S | 75 ++++++++++++++------------------- 1 file changed, 31 insertions(+), 44 deletions(-) diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S index e0f01ce251f5..14c6d25c035f 100644 --- a/arch/s390/kernel/text_amode31.S +++ b/arch/s390/kernel/text_amode31.S @@ -27,7 +27,7 @@ /* * int _diag14_amode31(unsigned long rx, unsigned long ry1, unsigned long subcode) */ -ENTRY(_diag14_amode31) +SYM_FUNC_START(_diag14_amode31) lgr %r1,%r2 lgr %r2,%r3 lgr %r3,%r4 @@ -42,12 +42,12 @@ ENTRY(_diag14_amode31) lgfr %r2,%r5 BR_EX_AMODE31_r14 EX_TABLE_AMODE31(.Ldiag14_ex, .Ldiag14_fault) -ENDPROC(_diag14_amode31) +SYM_FUNC_END(_diag14_amode31) /* * int _diag210_amode31(struct diag210 *addr) */ -ENTRY(_diag210_amode31) +SYM_FUNC_START(_diag210_amode31) lgr %r1,%r2 lhi %r2,-1 sam31 @@ -60,12 +60,12 @@ ENTRY(_diag210_amode31) lgfr %r2,%r2 BR_EX_AMODE31_r14 EX_TABLE_AMODE31(.Ldiag210_ex, .Ldiag210_fault) -ENDPROC(_diag210_amode31) +SYM_FUNC_END(_diag210_amode31) /* * int diag8c(struct diag8c *addr, struct ccw_dev_id *devno, size_t len) */ -ENTRY(_diag8c_amode31) +SYM_FUNC_START(_diag8c_amode31) llgf %r3,0(%r3) sam31 diag %r2,%r4,0x8c @@ -74,11 +74,11 @@ ENTRY(_diag8c_amode31) lgfr %r2,%r3 BR_EX_AMODE31_r14 EX_TABLE_AMODE31(.Ldiag8c_ex, .Ldiag8c_ex) -ENDPROC(_diag8c_amode31) +SYM_FUNC_END(_diag8c_amode31) /* * int _diag26c_amode31(void *req, void *resp, enum diag26c_sc subcode) */ -ENTRY(_diag26c_amode31) +SYM_FUNC_START(_diag26c_amode31) lghi %r5,-EOPNOTSUPP sam31 diag %r2,%r4,0x26c @@ -87,42 +87,42 @@ ENTRY(_diag26c_amode31) lgfr %r2,%r5 BR_EX_AMODE31_r14 EX_TABLE_AMODE31(.Ldiag26c_ex, .Ldiag26c_ex) -ENDPROC(_diag26c_amode31) +SYM_FUNC_END(_diag26c_amode31) /* * void _diag0c_amode31(struct hypfs_diag0c_entry *entry) */ -ENTRY(_diag0c_amode31) +SYM_FUNC_START(_diag0c_amode31) sam31 diag %r2,%r2,0x0c sam64 BR_EX_AMODE31_r14 -ENDPROC(_diag0c_amode31) +SYM_FUNC_END(_diag0c_amode31) /* * void _diag308_reset_amode31(void) * * Calls diag 308 subcode 1 and continues execution */ -ENTRY(_diag308_reset_amode31) - larl %r4,.Lctlregs # Save control registers +SYM_FUNC_START(_diag308_reset_amode31) + larl %r4,ctlregs # Save control registers stctg %c0,%c15,0(%r4) lg %r2,0(%r4) # Disable lowcore protection nilh %r2,0xefff - larl %r4,.Lctlreg0 + larl %r4,ctlreg0 stg %r2,0(%r4) lctlg %c0,%c0,0(%r4) - larl %r4,.Lfpctl # Floating point control register + larl %r4,fpctl # Floating point control register stfpc 0(%r4) - larl %r4,.Lprefix # Save prefix register + larl %r4,prefix # Save prefix register stpx 0(%r4) - larl %r4,.Lprefix_zero # Set prefix register to 0 + larl %r4,prefix_zero # Set prefix register to 0 spx 0(%r4) - larl %r4,.Lcontinue_psw # Save PSW flags + larl %r4,continue_psw # Save PSW flags epsw %r2,%r3 stm %r2,%r3,0(%r4) larl %r4,.Lrestart_part2 # Setup restart PSW at absolute 0 - larl %r3,.Lrestart_diag308_psw + larl %r3,restart_diag308_psw og %r4,0(%r3) # Save PSW lghi %r3,0 sturg %r4,%r3 # Use sturg, because of large pages @@ -134,39 +134,26 @@ ENTRY(_diag308_reset_amode31) lhi %r1,2 # Use mode 2 = ESAME (dump) sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to ESAME mode sam64 # Switch to 64 bit addressing mode - larl %r4,.Lctlregs # Restore control registers + larl %r4,ctlregs # Restore control registers lctlg %c0,%c15,0(%r4) - larl %r4,.Lfpctl # Restore floating point ctl register + larl %r4,fpctl # Restore floating point ctl register lfpc 0(%r4) - larl %r4,.Lprefix # Restore prefix register + larl %r4,prefix # Restore prefix register spx 0(%r4) - larl %r4,.Lcontinue_psw # Restore PSW flags + larl %r4,continue_psw # Restore PSW flags larl %r2,.Lcontinue stg %r2,8(%r4) lpswe 0(%r4) .Lcontinue: BR_EX_AMODE31_r14 -ENDPROC(_diag308_reset_amode31) +SYM_FUNC_END(_diag308_reset_amode31) .section .amode31.data,"aw",@progbits -.align 8 -.Lrestart_diag308_psw: - .long 0x00080000,0x80000000 - -.align 8 -.Lcontinue_psw: - .quad 0,0 - -.align 8 -.Lctlreg0: - .quad 0 -.Lctlregs: - .rept 16 - .quad 0 - .endr -.Lfpctl: - .long 0 -.Lprefix: - .long 0 -.Lprefix_zero: - .long 0 + .balign 8 +SYM_DATA_LOCAL(restart_diag308_psw, .long 0x00080000,0x80000000) +SYM_DATA_LOCAL(continue_psw, .quad 0,0) +SYM_DATA_LOCAL(ctlreg0, .quad 0) +SYM_DATA_LOCAL(ctlregs, .fill 16,8,0) +SYM_DATA_LOCAL(fpctl, .long 0) +SYM_DATA_LOCAL(prefix, .long 0) +SYM_DATA_LOCAL(prefix_zero, .long 0) -- GitLab From 3e5e5107b7c6efe319069272a68a4d0ec8bce7fb Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:06 +0200 Subject: [PATCH 3407/5631] s390/crypto,chacha: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Acked-by: Harald Freudenberger Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/chacha-s390.S | 47 +++++++++++++++++----------------- 1 file changed, 24 insertions(+), 23 deletions(-) diff --git a/arch/s390/crypto/chacha-s390.S b/arch/s390/crypto/chacha-s390.S index 9b033622191c..37cb63f25b17 100644 --- a/arch/s390/crypto/chacha-s390.S +++ b/arch/s390/crypto/chacha-s390.S @@ -13,27 +13,28 @@ #define SP %r15 #define FRAME (16 * 8 + 4 * 8) -.data -.align 32 - -.Lsigma: -.long 0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral -.long 1,0,0,0 -.long 2,0,0,0 -.long 3,0,0,0 -.long 0x03020100,0x07060504,0x0b0a0908,0x0f0e0d0c # byte swap - -.long 0,1,2,3 -.long 0x61707865,0x61707865,0x61707865,0x61707865 # smashed sigma -.long 0x3320646e,0x3320646e,0x3320646e,0x3320646e -.long 0x79622d32,0x79622d32,0x79622d32,0x79622d32 -.long 0x6b206574,0x6b206574,0x6b206574,0x6b206574 + .data + .balign 32 -.previous +SYM_DATA_START_LOCAL(sigma) + .long 0x61707865,0x3320646e,0x79622d32,0x6b206574 # endian-neutral + .long 1,0,0,0 + .long 2,0,0,0 + .long 3,0,0,0 + .long 0x03020100,0x07060504,0x0b0a0908,0x0f0e0d0c # byte swap + + .long 0,1,2,3 + .long 0x61707865,0x61707865,0x61707865,0x61707865 # smashed sigma + .long 0x3320646e,0x3320646e,0x3320646e,0x3320646e + .long 0x79622d32,0x79622d32,0x79622d32,0x79622d32 + .long 0x6b206574,0x6b206574,0x6b206574,0x6b206574 +SYM_DATA_END(sigma) + + .previous GEN_BR_THUNK %r14 -.text + .text ############################################################################# # void chacha20_vx_4x(u8 *out, counst u8 *inp, size_t len, @@ -78,10 +79,10 @@ #define XT2 %v29 #define XT3 %v30 -ENTRY(chacha20_vx_4x) +SYM_FUNC_START(chacha20_vx_4x) stmg %r6,%r7,6*8(SP) - larl %r7,.Lsigma + larl %r7,sigma lhi %r0,10 lhi %r1,0 @@ -403,7 +404,7 @@ ENTRY(chacha20_vx_4x) lmg %r6,%r7,6*8(SP) BR_EX %r14 -ENDPROC(chacha20_vx_4x) +SYM_FUNC_END(chacha20_vx_4x) #undef OUT #undef INP @@ -471,7 +472,7 @@ ENDPROC(chacha20_vx_4x) #define T2 %v29 #define T3 %v30 -ENTRY(chacha20_vx) +SYM_FUNC_START(chacha20_vx) clgfi LEN,256 jle chacha20_vx_4x stmg %r6,%r7,6*8(SP) @@ -481,7 +482,7 @@ ENTRY(chacha20_vx) la SP,0(%r1,SP) stg %r0,0(SP) # back-chain - larl %r7,.Lsigma + larl %r7,sigma lhi %r0,10 VLM K1,K2,0,KEY,0 # load key @@ -902,6 +903,6 @@ ENTRY(chacha20_vx) lmg %r6,%r7,FRAME+6*8(SP) la SP,FRAME(SP) BR_EX %r14 -ENDPROC(chacha20_vx) +SYM_FUNC_END(chacha20_vx) .previous -- GitLab From 4b788ac8ed39686f7810733c16521a7b91e005c1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:07 +0200 Subject: [PATCH 3408/5631] s390/crc32be: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/crc32be-vx.S | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S index 6b3d1009c392..6ea17628ea10 100644 --- a/arch/s390/crypto/crc32be-vx.S +++ b/arch/s390/crypto/crc32be-vx.S @@ -24,8 +24,8 @@ #define CONST_RU_POLY %v13 #define CONST_CRC_POLY %v14 -.data -.align 8 + .data + .balign 8 /* * The CRC-32 constant block contains reduction constants to fold and @@ -58,19 +58,20 @@ * P'(x) = 0xEDB88320 */ -.Lconstants_CRC_32_BE: +SYM_DATA_START_LOCAL(constants_CRC_32_BE) .quad 0x08833794c, 0x0e6228b11 # R1, R2 .quad 0x0c5b9cd4c, 0x0e8a45605 # R3, R4 .quad 0x0f200aa66, 1 << 32 # R5, x32 .quad 0x0490d678d, 1 # R6, 1 .quad 0x104d101df, 0 # u .quad 0x104C11DB7, 0 # P(x) +SYM_DATA_END(constants_CRC_32_BE) -.previous + .previous GEN_BR_THUNK %r14 -.text + .text /* * The CRC-32 function(s) use these calling conventions: * @@ -90,9 +91,9 @@ * * V9..V14: CRC-32 constants. */ -ENTRY(crc32_be_vgfm_16) +SYM_FUNC_START(crc32_be_vgfm_16) /* Load CRC-32 constants */ - larl %r5,.Lconstants_CRC_32_BE + larl %r5,constants_CRC_32_BE VLM CONST_R1R2,CONST_CRC_POLY,0,%r5 /* Load the initial CRC value into the leftmost word of V0. */ @@ -207,6 +208,6 @@ ENTRY(crc32_be_vgfm_16) .Ldone: VLGVF %r2,%v2,3 BR_EX %r14 -ENDPROC(crc32_be_vgfm_16) +SYM_FUNC_END(crc32_be_vgfm_16) .previous -- GitLab From b5f3c99d15725d78a2e720ca48ab47a43bd1b5cb Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:08 +0200 Subject: [PATCH 3409/5631] s390/crc32le: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/crypto/crc32le-vx.S | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S index 71caf0f4ec08..5a819ae09a0b 100644 --- a/arch/s390/crypto/crc32le-vx.S +++ b/arch/s390/crypto/crc32le-vx.S @@ -25,8 +25,8 @@ #define CONST_RU_POLY %v13 #define CONST_CRC_POLY %v14 -.data -.align 8 + .data + .balign 8 /* * The CRC-32 constant block contains reduction constants to fold and @@ -59,27 +59,29 @@ * P'(x) = 0x82F63B78 */ -.Lconstants_CRC_32_LE: +SYM_DATA_START_LOCAL(constants_CRC_32_LE) .octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask .quad 0x1c6e41596, 0x154442bd4 # R2, R1 .quad 0x0ccaa009e, 0x1751997d0 # R4, R3 .octa 0x163cd6124 # R5 .octa 0x1F7011641 # u' .octa 0x1DB710641 # P'(x) << 1 +SYM_DATA_END(constants_CRC_32_LE) -.Lconstants_CRC_32C_LE: +SYM_DATA_START_LOCAL(constants_CRC_32C_LE) .octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask .quad 0x09e4addf8, 0x740eef02 # R2, R1 .quad 0x14cd00bd6, 0xf20c0dfe # R4, R3 .octa 0x0dd45aab8 # R5 .octa 0x0dea713f1 # u' .octa 0x105ec76f0 # P'(x) << 1 +SYM_DATA_END(constants_CRC_32C_LE) -.previous + .previous GEN_BR_THUNK %r14 -.text + .text /* * The CRC-32 functions use these calling conventions: @@ -102,17 +104,17 @@ * V10..V14: CRC-32 constants. */ -ENTRY(crc32_le_vgfm_16) - larl %r5,.Lconstants_CRC_32_LE +SYM_FUNC_START(crc32_le_vgfm_16) + larl %r5,constants_CRC_32_LE j crc32_le_vgfm_generic -ENDPROC(crc32_le_vgfm_16) +SYM_FUNC_END(crc32_le_vgfm_16) -ENTRY(crc32c_le_vgfm_16) - larl %r5,.Lconstants_CRC_32C_LE +SYM_FUNC_START(crc32c_le_vgfm_16) + larl %r5,constants_CRC_32C_LE j crc32_le_vgfm_generic -ENDPROC(crc32c_le_vgfm_16) +SYM_FUNC_END(crc32c_le_vgfm_16) -ENTRY(crc32_le_vgfm_generic) +SYM_FUNC_START(crc32_le_vgfm_generic) /* Load CRC-32 constants */ VLM CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5 @@ -268,6 +270,6 @@ ENTRY(crc32_le_vgfm_generic) .Ldone: VLGVF %r2,%v2,2 BR_EX %r14 -ENDPROC(crc32_le_vgfm_generic) +SYM_FUNC_END(crc32_le_vgfm_generic) .previous -- GitLab From aaaac068f0d2d137b7fcad47d4cebbd24bf060ae Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:09 +0200 Subject: [PATCH 3410/5631] s390/mcount: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/mcount.S | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 4c4ee762f515..a7902fdb7ba2 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -28,9 +28,9 @@ .section .kprobes.text, "ax" -ENTRY(ftrace_stub) +SYM_FUNC_START(ftrace_stub) BR_EX %r14 -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) .macro ftrace_regs_entry, allregs=0 stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller @@ -153,8 +153,7 @@ SYM_CODE_END(ftrace_shared_hotpatch_trampoline_exrl) #ifdef CONFIG_RETHOOK -SYM_FUNC_START(arch_rethook_trampoline) - +SYM_CODE_START(arch_rethook_trampoline) stg %r14,(__SF_GPRS+8*8)(%r15) lay %r15,-STACK_FRAME_SIZE(%r15) stmg %r0,%r14,STACK_PTREGS_GPRS(%r15) @@ -177,7 +176,6 @@ SYM_FUNC_START(arch_rethook_trampoline) mvc __SF_EMPTY(16,%r7),STACK_PTREGS_PSW(%r15) lmg %r0,%r15,STACK_PTREGS_GPRS(%r15) lpswe __SF_EMPTY(%r15) - -SYM_FUNC_END(arch_rethook_trampoline) +SYM_CODE_END(arch_rethook_trampoline) #endif /* CONFIG_RETHOOK */ -- GitLab From a89d60fc7a9ad544a30251d238a5f35d023754d1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:10 +0200 Subject: [PATCH 3411/5631] s390/earlypgm: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/earlypgm.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/earlypgm.S b/arch/s390/kernel/earlypgm.S index f521c6da37b8..c634871f0d90 100644 --- a/arch/s390/kernel/earlypgm.S +++ b/arch/s390/kernel/earlypgm.S @@ -7,7 +7,7 @@ #include #include -ENTRY(early_pgm_check_handler) +SYM_CODE_START(early_pgm_check_handler) stmg %r8,%r15,__LC_SAVE_AREA_SYNC aghi %r15,-(STACK_FRAME_OVERHEAD+__PT_SIZE) la %r11,STACK_FRAME_OVERHEAD(%r15) @@ -20,4 +20,4 @@ ENTRY(early_pgm_check_handler) mvc __LC_RETURN_PSW(16),STACK_FRAME_OVERHEAD+__PT_PSW(%r15) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) lpswe __LC_RETURN_PSW -ENDPROC(early_pgm_check_handler) +SYM_CODE_END(early_pgm_check_handler) -- GitLab From 05d0935d12966686eb1d780e3f929727e9fa500d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:11 +0200 Subject: [PATCH 3412/5631] s390/head64: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/head64.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index f67982f562db..df77ba102096 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ #include __HEAD -ENTRY(startup_continue) +SYM_CODE_START(startup_continue) larl %r1,tod_clock_base mvc 0(16,%r1),__LC_BOOT_CLOCK # @@ -33,8 +33,8 @@ ENTRY(startup_continue) # We returned from start_kernel ?!? PANIK # basr %r13,0 - lpswe .Ldw-.(%r13) # load disabled wait psw + lpswe dw_psw-.(%r13) # load disabled wait psw +SYM_CODE_END(startup_continue) .align 16 -.LPG1: -.Ldw: .quad 0x0002000180000000,0x0000000000000000 +SYM_DATA_LOCAL(dw_psw, .quad 0x0002000180000000,0x0000000000000000) -- GitLab From 26d14299220ab8e1d4fb166d8e66dd4a43097ec1 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:12 +0200 Subject: [PATCH 3413/5631] s390/reipl: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/reipl.S | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index 4a22163962eb..88087a32ebc6 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -19,7 +19,7 @@ # r2 = Function to be called after store status # r3 = Parameter for function # -ENTRY(store_status) +SYM_CODE_START(store_status) /* Save register one and load save area base */ stg %r1,__LC_SAVE_AREA_RESTART /* General purpose registers */ @@ -61,7 +61,7 @@ ENTRY(store_status) stpx 0(%r1) /* Clock comparator - seven bytes */ lghi %r1,__LC_CLOCK_COMP_SAVE_AREA - larl %r4,.Lclkcmp + larl %r4,clkcmp stckc 0(%r4) mvc 1(7,%r1),1(%r4) /* Program status word */ @@ -73,9 +73,9 @@ ENTRY(store_status) lgr %r9,%r2 lgr %r2,%r3 BR_EX %r9 -ENDPROC(store_status) +SYM_CODE_END(store_status) .section .bss - .align 8 -.Lclkcmp: .quad 0x0000000000000000 + .balign 8 +SYM_DATA_LOCAL(clkcmp, .quad 0x0000000000000000) .previous -- GitLab From 6cea5f0bc93dffc74f0fa8cad7680b5ad21d1961 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:13 +0200 Subject: [PATCH 3414/5631] s390/kprobes: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/kprobes_insn_page.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/kprobes_insn_page.S b/arch/s390/kernel/kprobes_insn_page.S index f6cb022ef8c8..b6335296dcd8 100644 --- a/arch/s390/kernel/kprobes_insn_page.S +++ b/arch/s390/kernel/kprobes_insn_page.S @@ -14,9 +14,9 @@ */ .section .kprobes.text, "ax" .align 4096 -ENTRY(kprobes_insn_page) +SYM_CODE_START(kprobes_insn_page) .rept 2048 .word 0x07fe .endr -ENDPROC(kprobes_insn_page) +SYM_CODE_END(kprobes_insn_page) .previous -- GitLab From 04b6d02dbecdda5d15aa55edbae2f0e1eb81749e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:14 +0200 Subject: [PATCH 3415/5631] s390/purgatory: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/purgatory/head.S | 62 ++++++++------------------- arch/s390/purgatory/kexec-purgatory.S | 14 +++--- 2 files changed, 25 insertions(+), 51 deletions(-) diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S index 6f835124ee82..e5bd1a503528 100644 --- a/arch/s390/purgatory/head.S +++ b/arch/s390/purgatory/head.S @@ -76,9 +76,9 @@ diag %r0,%r1,0x308 .endm -.text -.align PAGE_SIZE -ENTRY(purgatory_start) + .text + .balign PAGE_SIZE +SYM_CODE_START(purgatory_start) /* The purgatory might be called after a diag308 so better set * architecture and addressing mode. */ @@ -245,45 +245,21 @@ ENTRY(purgatory_start) /* start crash kernel */ START_NEXT_KERNEL .base_dst 1 - - -load_psw_mask: - .long 0x00080000,0x80000000 - - .align 8 -disabled_wait_psw: - .quad 0x0002000180000000 - .quad 0x0000000000000000 + .do_checksum_verification - -gprregs: - .rept 10 - .quad 0 - .endr - -/* Macro to define a global variable with name and size (in bytes) to be - * shared with C code. - * - * Add the .size and .type attribute to satisfy checks on the Elf_Sym during - * purgatory load. - */ -.macro GLOBAL_VARIABLE name,size -\name: - .global \name - .size \name,\size - .type \name,object - .skip \size,0 -.endm - -GLOBAL_VARIABLE purgatory_sha256_digest,32 -GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE -GLOBAL_VARIABLE kernel_entry,8 -GLOBAL_VARIABLE kernel_type,8 -GLOBAL_VARIABLE crash_start,8 -GLOBAL_VARIABLE crash_size,8 - - .align PAGE_SIZE -stack: +SYM_CODE_END(purgatory_start) + +SYM_DATA_LOCAL(load_psw_mask, .long 0x00080000,0x80000000) + .balign 8 +SYM_DATA_LOCAL(disabled_wait_psw, .quad 0x0002000180000000,.do_checksum_verification) +SYM_DATA_LOCAL(gprregs, .fill 10,8,0) +SYM_DATA(purgatory_sha256_digest, .skip 32) +SYM_DATA(purgatory_sha_regions, .skip 16*__KEXEC_SHA_REGION_SIZE) +SYM_DATA(kernel_entry, .skip 8) +SYM_DATA(kernel_type, .skip 8) +SYM_DATA(crash_start, .skip 8) +SYM_DATA(crash_size, .skip 8) + .balign PAGE_SIZE +SYM_DATA_START_LOCAL(stack) /* The buffer to move this code must be as big as the code. */ .skip stack-purgatory_start - .align PAGE_SIZE -purgatory_end: + .balign PAGE_SIZE +SYM_DATA_END_LABEL(stack, SYM_L_LOCAL, purgatory_end) diff --git a/arch/s390/purgatory/kexec-purgatory.S b/arch/s390/purgatory/kexec-purgatory.S index 8293753100ae..25f512b1de12 100644 --- a/arch/s390/purgatory/kexec-purgatory.S +++ b/arch/s390/purgatory/kexec-purgatory.S @@ -1,14 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include .section .rodata, "a" - .align 8 -kexec_purgatory: - .globl kexec_purgatory + .balign 8 +SYM_DATA_START(kexec_purgatory) .incbin "arch/s390/purgatory/purgatory.ro" -.Lkexec_purgatroy_end: +SYM_DATA_END_LABEL(kexec_purgatory, SYM_L_LOCAL, kexec_purgatory_end) - .align 8 -kexec_purgatory_size: - .globl kexec_purgatory_size - .quad .Lkexec_purgatroy_end - kexec_purgatory + .balign 8 +SYM_DATA(kexec_purgatory_size, .quad kexec_purgatory_end-kexec_purgatory) -- GitLab From fda1dffa44b0ea657e413f1e548022e3f0269592 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:15 +0200 Subject: [PATCH 3416/5631] s390/entry: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/entry.S | 69 ++++++++++++++++++++-------------------- 1 file changed, 34 insertions(+), 35 deletions(-) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index d5f8cd4319a4..e5b6c1369e8e 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -177,7 +177,7 @@ _LPP_OFFSET = __LC_LPP * Returns: * gpr2 = prev */ -ENTRY(__switch_to) +SYM_FUNC_START(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread @@ -193,7 +193,7 @@ ENTRY(__switch_to) lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40 BR_EX %r14 -ENDPROC(__switch_to) +SYM_FUNC_END(__switch_to) #if IS_ENABLED(CONFIG_KVM) /* @@ -202,7 +202,7 @@ ENDPROC(__switch_to) * %r3 pointer to sie control block virt * %r4 guest register save area */ -ENTRY(__sie64a) +SYM_FUNC_START(__sie64a) stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers lg %r12,__LC_CURRENT stg %r2,__SF_SIE_CONTROL_PHYS(%r15) # save sie block physical.. @@ -248,8 +248,7 @@ ENTRY(__sie64a) nopr 7 .Lrewind_pad2: nopr 7 - .globl sie_exit -sie_exit: +SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL) lg %r14,__SF_SIE_SAVEAREA(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 xgr %r0,%r0 # clear guest registers to @@ -269,7 +268,7 @@ sie_exit: EX_TABLE(.Lrewind_pad4,.Lsie_fault) EX_TABLE(.Lrewind_pad2,.Lsie_fault) EX_TABLE(sie_exit,.Lsie_fault) -ENDPROC(__sie64a) +SYM_FUNC_END(__sie64a) EXPORT_SYMBOL(__sie64a) EXPORT_SYMBOL(sie_exit) #endif @@ -279,7 +278,7 @@ EXPORT_SYMBOL(sie_exit) * are entered with interrupts disabled. */ -ENTRY(system_call) +SYM_CODE_START(system_call) stpt __LC_SYS_ENTER_TIMER stmg %r8,%r15,__LC_SAVE_AREA_SYNC BPOFF @@ -314,12 +313,12 @@ ENTRY(system_call) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE -ENDPROC(system_call) +SYM_CODE_END(system_call) # # a new process exits the kernel with ret_from_fork # -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) lgr %r3,%r11 brasl %r14,__ret_from_fork STACKLEAK_ERASE @@ -330,13 +329,13 @@ ENTRY(ret_from_fork) lmg %r0,%r15,STACK_FRAME_OVERHEAD+__PT_R0(%r15) stpt __LC_EXIT_TIMER LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE -ENDPROC(ret_from_fork) +SYM_CODE_END(ret_from_fork) /* * Program check handler routine */ -ENTRY(pgm_check_handler) +SYM_CODE_START(pgm_check_handler) stpt __LC_SYS_ENTER_TIMER BPOFF stmg %r8,%r15,__LC_SAVE_AREA_SYNC @@ -403,13 +402,13 @@ ENTRY(pgm_check_handler) lghi %r14,1 LBEAR __LC_PGM_LAST_BREAK LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE # branch to .Lsysc_per -ENDPROC(pgm_check_handler) +SYM_CODE_END(pgm_check_handler) /* * Interrupt handler macro used for external and IO interrupts. */ .macro INT_HANDLER name,lc_old_psw,handler -ENTRY(\name) +SYM_CODE_START(\name) stckf __LC_INT_CLOCK stpt __LC_SYS_ENTER_TIMER STBEAR __LC_LAST_BREAK @@ -456,7 +455,7 @@ ENTRY(\name) 2: LBEAR __PT_LAST_BREAK(%r11) lmg %r0,%r15,__PT_R0(%r11) LPSWEY __LC_RETURN_PSW,__LC_RETURN_LPSWE -ENDPROC(\name) +SYM_CODE_END(\name) .endm INT_HANDLER ext_int_handler,__LC_EXT_OLD_PSW,do_ext_irq @@ -465,7 +464,7 @@ INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq /* * Load idle PSW. */ -ENTRY(psw_idle) +SYM_FUNC_START(psw_idle) stg %r14,(__SF_GPRS+8*8)(%r15) stg %r3,__SF_EMPTY(%r15) larl %r1,psw_idle_exit @@ -481,15 +480,14 @@ ENTRY(psw_idle) stckf __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) lpswe __SF_EMPTY(%r15) -.globl psw_idle_exit -psw_idle_exit: +SYM_INNER_LABEL(psw_idle_exit, SYM_L_GLOBAL) BR_EX %r14 -ENDPROC(psw_idle) +SYM_FUNC_END(psw_idle) /* * Machine check handler routines */ -ENTRY(mcck_int_handler) +SYM_CODE_START(mcck_int_handler) stckf __LC_MCCK_CLOCK BPOFF la %r1,4095 # validate r1 @@ -573,10 +571,10 @@ ENTRY(mcck_int_handler) */ lhi %r5,0 lhi %r6,1 - larl %r7,.Lstop_lock + larl %r7,stop_lock cs %r5,%r6,0(%r7) # single CPU-stopper only jnz 4f - larl %r7,.Lthis_cpu + larl %r7,this_cpu stap 0(%r7) # this CPU address lh %r4,0(%r7) nilh %r4,0 @@ -592,15 +590,15 @@ ENTRY(mcck_int_handler) 3: sigp %r1,%r4,SIGP_STOP # stop this CPU brc SIGP_CC_BUSY,3b 4: j 4b -ENDPROC(mcck_int_handler) +SYM_CODE_END(mcck_int_handler) -ENTRY(restart_int_handler) +SYM_CODE_START(restart_int_handler) ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40 stg %r15,__LC_SAVE_AREA_RESTART TSTMSK __LC_RESTART_FLAGS,RESTART_FLAG_CTLREGS,4 jz 0f lctlg %c0,%c15,__LC_CREGS_SAVE_AREA -0: larl %r15,.Lstosm_tmp +0: larl %r15,stosm_tmp stosm 0(%r15),0x04 # turn dat on, keep irqs off lg %r15,__LC_RESTART_STACK xc STACK_FRAME_OVERHEAD(__PT_SIZE,%r15),STACK_FRAME_OVERHEAD(%r15) @@ -621,7 +619,7 @@ ENTRY(restart_int_handler) 2: sigp %r4,%r3,SIGP_STOP # sigp stop to current cpu brc 2,2b 3: j 3b -ENDPROC(restart_int_handler) +SYM_CODE_END(restart_int_handler) .section .kprobes.text, "ax" @@ -631,7 +629,7 @@ ENDPROC(restart_int_handler) * No need to properly save the registers, we are going to panic anyway. * Setup a pt_regs so that show_trace can provide a good call trace. */ -ENTRY(stack_overflow) +SYM_CODE_START(stack_overflow) lg %r15,__LC_NODAT_STACK # change to panic stack la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) @@ -641,26 +639,27 @@ ENTRY(stack_overflow) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow -ENDPROC(stack_overflow) +SYM_CODE_END(stack_overflow) #endif .section .data, "aw" - .align 4 -.Lstop_lock: .long 0 -.Lthis_cpu: .short 0 -.Lstosm_tmp: .byte 0 + .balign 4 +SYM_DATA_LOCAL(stop_lock, .long 0) +SYM_DATA_LOCAL(this_cpu, .short 0) +SYM_DATA_LOCAL(stosm_tmp, .byte 0) + .section .rodata, "a" #define SYSCALL(esame,emu) .quad __s390x_ ## esame - .globl sys_call_table -sys_call_table: +SYM_DATA_START(sys_call_table) #include "asm/syscall_table.h" +SYM_DATA_END(sys_call_table) #undef SYSCALL #ifdef CONFIG_COMPAT #define SYSCALL(esame,emu) .quad __s390_ ## emu - .globl sys_call_table_emu -sys_call_table_emu: +SYM_DATA_START(sys_call_table_emu) #include "asm/syscall_table.h" +SYM_DATA_END(sys_call_table_emu) #undef SYSCALL #endif -- GitLab From 680957b3b8b0b2e8697592fcb77369d4f643908a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:16 +0200 Subject: [PATCH 3417/5631] s390/relocate_kernel: use SYM* macros instead of ENTRY(), etc. Consistently use the SYM* family of macros instead of the deprecated ENTRY(), ENDPROC(), etc. family of macros. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/relocate_kernel.S | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index a9a1a6f45375..89a3efce0500 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -26,7 +26,7 @@ */ .text -ENTRY(relocate_kernel) +SYM_CODE_START(relocate_kernel) basr %r13,0 # base address .base: lghi %r7,PAGE_SIZE # load PAGE_SIZE in r7 @@ -66,13 +66,11 @@ ENTRY(relocate_kernel) mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0 .diag: diag %r0,%r0,0x308 -ENDPROC(relocate_kernel) +SYM_CODE_END(relocate_kernel) - .align 8 - load_psw: + .balign 8 +SYM_DATA_START_LOCAL(load_psw) .long 0x00080000,0x80000000 - relocate_kernel_end: - .align 8 - .globl relocate_kernel_len - relocate_kernel_len: - .quad relocate_kernel_end - relocate_kernel +SYM_DATA_END_LABEL(load_psw, SYM_L_LOCAL, relocate_kernel_end) + .balign 8 +SYM_DATA(relocate_kernel_len, .quad relocate_kernel_end - relocate_kernel) -- GitLab From 0ae241f4d7d0003f091df6f8d1f45767c3d96d62 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 17 Apr 2023 14:45:17 +0200 Subject: [PATCH 3418/5631] s390/relocate_kernel: adjust indentation relocate_kernel.S seems to be the only assembler file which doesn't follow the standard way of indentation. Adjust this for the sake of consistency. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/relocate_kernel.S | 84 +++++++++++++++--------------- 1 file changed, 42 insertions(+), 42 deletions(-) diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S index 89a3efce0500..0ae297c82afd 100644 --- a/arch/s390/kernel/relocate_kernel.S +++ b/arch/s390/kernel/relocate_kernel.S @@ -27,50 +27,50 @@ .text SYM_CODE_START(relocate_kernel) - basr %r13,0 # base address - .base: - lghi %r7,PAGE_SIZE # load PAGE_SIZE in r7 - lghi %r9,PAGE_SIZE # load PAGE_SIZE in r9 - lg %r5,0(%r2) # read another word for indirection page - aghi %r2,8 # increment pointer - tml %r5,0x1 # is it a destination page? - je .indir_check # NO, goto "indir_check" - lgr %r6,%r5 # r6 = r5 - nill %r6,0xf000 # mask it out and... - j .base # ...next iteration - .indir_check: - tml %r5,0x2 # is it a indirection page? - je .done_test # NO, goto "done_test" - nill %r5,0xf000 # YES, mask out, - lgr %r2,%r5 # move it into the right register, - j .base # and read next... - .done_test: - tml %r5,0x4 # is it the done indicator? - je .source_test # NO! Well, then it should be the source indicator... - j .done # ok, lets finish it here... - .source_test: - tml %r5,0x8 # it should be a source indicator... - je .base # NO, ignore it... - lgr %r8,%r5 # r8 = r5 - nill %r8,0xf000 # masking - 0: mvcle %r6,%r8,0x0 # copy PAGE_SIZE bytes from r8 to r6 - pad with 0 - jo 0b - j .base - .done: - lgr %r0,%r4 # subcode - cghi %r3,0 - je .diag - la %r4,load_psw-.base(%r13) # load psw-address into the register - o %r3,4(%r4) # or load address into psw - st %r3,4(%r4) - mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0 - .diag: - diag %r0,%r0,0x308 + basr %r13,0 # base address +.base: + lghi %r7,PAGE_SIZE # load PAGE_SIZE in r7 + lghi %r9,PAGE_SIZE # load PAGE_SIZE in r9 + lg %r5,0(%r2) # read another word for indirection page + aghi %r2,8 # increment pointer + tml %r5,0x1 # is it a destination page? + je .indir_check # NO, goto "indir_check" + lgr %r6,%r5 # r6 = r5 + nill %r6,0xf000 # mask it out and... + j .base # ...next iteration +.indir_check: + tml %r5,0x2 # is it a indirection page? + je .done_test # NO, goto "done_test" + nill %r5,0xf000 # YES, mask out, + lgr %r2,%r5 # move it into the right register, + j .base # and read next... +.done_test: + tml %r5,0x4 # is it the done indicator? + je .source_test # NO! Well, then it should be the source indicator... + j .done # ok, lets finish it here... +.source_test: + tml %r5,0x8 # it should be a source indicator... + je .base # NO, ignore it... + lgr %r8,%r5 # r8 = r5 + nill %r8,0xf000 # masking +0: mvcle %r6,%r8,0x0 # copy PAGE_SIZE bytes from r8 to r6 - pad with 0 + jo 0b + j .base +.done: + lgr %r0,%r4 # subcode + cghi %r3,0 + je .diag + la %r4,load_psw-.base(%r13) # load psw-address into the register + o %r3,4(%r4) # or load address into psw + st %r3,4(%r4) + mvc 0(8,%r0),0(%r4) # copy psw to absolute address 0 +.diag: + diag %r0,%r0,0x308 SYM_CODE_END(relocate_kernel) - .balign 8 + .balign 8 SYM_DATA_START_LOCAL(load_psw) - .long 0x00080000,0x80000000 + .long 0x00080000,0x80000000 SYM_DATA_END_LABEL(load_psw, SYM_L_LOCAL, relocate_kernel_end) - .balign 8 + .balign 8 SYM_DATA(relocate_kernel_len, .quad relocate_kernel_end - relocate_kernel) -- GitLab From e1805aae1e0f648351913e7f5a8a7530a90c8634 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 Apr 2023 10:57:57 -0300 Subject: [PATCH 3419/5631] perf map: Add missing conversions to map__refcnt() Some conversions weren't performed in 4e8db2d7520f780f ("perf map: Add map__refcnt() accessor to use in the maps test"), fix it. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/map.c | 6 +++--- tools/perf/util/map.h | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index d81b6ca18ee9..b6a8935026eb 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -112,7 +112,7 @@ void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) map->map_ip = map__dso_map_ip; map->unmap_ip = map__dso_unmap_ip; map->erange_warned = false; - refcount_set(&map->refcnt, 1); + refcount_set(map__refcnt(map), 1); } struct map *map__new(struct machine *machine, u64 start, u64 len, @@ -292,7 +292,7 @@ bool map__has_symbols(const struct map *map) static void map__exit(struct map *map) { - BUG_ON(refcount_read(&map->refcnt) != 0); + BUG_ON(refcount_read(map__refcnt(map)) != 0); dso__zput(map->dso); } @@ -304,7 +304,7 @@ void map__delete(struct map *map) void map__put(struct map *map) { - if (map && refcount_dec_and_test(&map->refcnt)) + if (map && refcount_dec_and_test(map__refcnt(map))) map__delete(map); } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index f89ab7c2d327..4f7d9505f7ff 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -159,7 +159,7 @@ struct map *map__clone(struct map *map); static inline struct map *map__get(struct map *map) { if (map) - refcount_inc(&map->refcnt); + refcount_inc(map__refcnt(map)); return map; } -- GitLab From e6a9efcee55f084a5450e4853ecbbaa0b086dcd0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 Apr 2023 12:24:12 -0300 Subject: [PATCH 3420/5631] perf map: Add set_ methods for map->{start,end,pgoff,pgoff,reloc,erange_warned,dso,map_ip,unmap_ip,priv} To have a way to intercept usage of the reference counted struct map. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 4 +- tools/perf/tests/maps.c | 16 +++---- tools/perf/tests/vmlinux-kallsyms.c | 4 +- tools/perf/util/machine.c | 23 +++++----- tools/perf/util/map.c | 20 ++++----- tools/perf/util/map.h | 65 +++++++++++++++++++++++++++++ tools/perf/util/maps.c | 6 +-- tools/perf/util/symbol-elf.c | 26 ++++++------ tools/perf/util/symbol.c | 33 ++++++++------- 9 files changed, 132 insertions(+), 65 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 5d448c36ed22..eb5740154bc0 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -191,7 +191,7 @@ static void ui__warn_map_erange(struct map *map, struct symbol *sym, u64 ip) if (use_browser <= 0) sleep(5); - map->erange_warned = true; + map__set_erange_warned(map, true); } static void perf_top__record_precise_ip(struct perf_top *top, @@ -225,7 +225,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, */ mutex_unlock(&he->hists->lock); - if (err == -ERANGE && !he->ms.map->erange_warned) + if (err == -ERANGE && !map__erange_warned(he->ms.map)) ui__warn_map_erange(he->ms.map, sym, ip); else if (err == -ENOMEM) { pr_err("Not enough memory for annotating '%s' symbol!\n", diff --git a/tools/perf/tests/maps.c b/tools/perf/tests/maps.c index a6278f9c8b71..8c0eb5cf8bb5 100644 --- a/tools/perf/tests/maps.c +++ b/tools/perf/tests/maps.c @@ -95,8 +95,8 @@ static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest map = dso__new_map(bpf_progs[i].name); TEST_ASSERT_VAL("failed to create map", map); - map->start = bpf_progs[i].start; - map->end = bpf_progs[i].end; + map__set_start(map, bpf_progs[i].start); + map__set_end(map, bpf_progs[i].end); TEST_ASSERT_VAL("failed to insert map", maps__insert(maps, map) == 0); map__put(map); } @@ -111,16 +111,16 @@ static int test__maps__merge_in(struct test_suite *t __maybe_unused, int subtest TEST_ASSERT_VAL("failed to create map", map_kcore3); /* kcore1 map overlaps over all bpf maps */ - map_kcore1->start = 100; - map_kcore1->end = 1000; + map__set_start(map_kcore1, 100); + map__set_end(map_kcore1, 1000); /* kcore2 map hides behind bpf_prog_2 */ - map_kcore2->start = 550; - map_kcore2->end = 570; + map__set_start(map_kcore2, 550); + map__set_end(map_kcore2, 570); /* kcore3 map hides behind bpf_prog_3, kcore1 and adds new map */ - map_kcore3->start = 880; - map_kcore3->end = 1100; + map__set_start(map_kcore3, 880); + map__set_end(map_kcore3, 1100); ret = maps__merge_in(maps, map_kcore1); TEST_ASSERT_VAL("failed to merge map", !ret); diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index af511233c764..1078a93b01aa 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -304,7 +304,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused dso->short_name : dso->name)); if (pair) { - pair->priv = 1; + map__set_priv(pair, 1); } else { if (!header_printed) { pr_info("WARN: Maps only in vmlinux:\n"); @@ -340,7 +340,7 @@ static int test__vmlinux_matches_kallsyms(struct test_suite *test __maybe_unused pr_info(":\nWARN: *%" PRIx64 "-%" PRIx64 " %" PRIx64, map__start(pair), map__end(pair), map__pgoff(pair)); pr_info(" %s\n", dso->name); - pair->priv = 1; + map__set_priv(pair, 1); } } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 85787672d335..8ccbe48e23bd 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -910,8 +910,8 @@ static int machine__process_ksymbol_register(struct machine *machine, dso__set_loaded(dso); } - map->start = event->ksymbol.addr; - map->end = map__start(map) + event->ksymbol.len; + map__set_start(map, event->ksymbol.addr); + map__set_end(map, map__start(map) + event->ksymbol.len); err = maps__insert(machine__kernel_maps(machine), map); if (err) { err = -ENOMEM; @@ -1218,8 +1218,8 @@ int machine__create_extra_kernel_map(struct machine *machine, if (!map) return -ENOMEM; - map->end = xm->end; - map->pgoff = xm->pgoff; + map__set_end(map, xm->end); + map__set_pgoff(map, xm->pgoff); kmap = map__kmap(map); @@ -1291,7 +1291,7 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine, dest_map = maps__find(kmaps, map__pgoff(map)); if (dest_map != map) - map->pgoff = map__map_ip(dest_map, map__pgoff(map)); + map__set_pgoff(map, map__map_ip(dest_map, map__pgoff(map))); found = true; } if (found || machine->trampolines_mapped) @@ -1342,7 +1342,8 @@ __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) if (machine->vmlinux_map == NULL) return -ENOMEM; - machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip; + map__set_map_ip(machine->vmlinux_map, identity__map_ip); + map__set_unmap_ip(machine->vmlinux_map, identity__map_ip); return maps__insert(machine__kernel_maps(machine), machine->vmlinux_map); } @@ -1623,7 +1624,7 @@ static int machine__create_module(void *arg, const char *name, u64 start, map = machine__addnew_module_map(machine, start, name); if (map == NULL) return -1; - map->end = start + size; + map__set_end(map, start + size); dso__kernel_module_get_build_id(map__dso(map), machine->root_dir); map__put(map); @@ -1659,14 +1660,14 @@ static int machine__create_modules(struct machine *machine) static void machine__set_kernel_mmap(struct machine *machine, u64 start, u64 end) { - machine->vmlinux_map->start = start; - machine->vmlinux_map->end = end; + map__set_start(machine->vmlinux_map, start); + map__set_end(machine->vmlinux_map, end); /* * Be a bit paranoid here, some perf.data file came with * a zero sized synthesized MMAP event for the kernel. */ if (start == 0 && end == 0) - machine->vmlinux_map->end = ~0ULL; + map__set_end(machine->vmlinux_map, ~0ULL); } static int machine__update_kernel_mmap(struct machine *machine, @@ -1810,7 +1811,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine, if (map == NULL) goto out_problem; - map->end = map__start(map) + xm->end - xm->start; + map__set_end(map, map__start(map) + xm->end - xm->start); if (build_id__is_defined(bid)) dso__set_build_id(map__dso(map), bid); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index b6a8935026eb..bdd2742fa35b 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -104,14 +104,14 @@ static inline bool replace_android_lib(const char *filename, char *newfilename) void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso) { - map->start = start; - map->end = end; - map->pgoff = pgoff; - map->reloc = 0; - map->dso = dso__get(dso); - map->map_ip = map__dso_map_ip; - map->unmap_ip = map__dso_unmap_ip; - map->erange_warned = false; + map__set_start(map, start); + map__set_end(map, end); + map__set_pgoff(map, pgoff); + map__set_reloc(map, 0); + map__set_dso(map, dso__get(dso)); + map__set_map_ip(map, map__dso_map_ip); + map__set_unmap_ip(map, map__dso_unmap_ip); + map__set_erange_warned(map, false); refcount_set(map__refcnt(map), 1); } @@ -317,7 +317,7 @@ void map__fixup_start(struct map *map) if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - map->start = sym->start; + map__set_start(map, sym->start); } } @@ -329,7 +329,7 @@ void map__fixup_end(struct map *map) if (nd != NULL) { struct symbol *sym = rb_entry(nd, struct symbol, rb_node); - map->end = sym->end; + map__set_end(map, sym->end); } } diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 4f7d9505f7ff..0760c671314d 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -62,6 +62,16 @@ static inline u64 map__unmap_ip(const struct map *map, u64 ip) return map->unmap_ip(map, ip); } +static inline void *map__map_ip_ptr(struct map *map) +{ + return map->map_ip; +} + +static inline void* map__unmap_ip_ptr(struct map *map) +{ + return map->unmap_ip; +} + static inline u64 map__start(const struct map *map) { return map->start; @@ -102,6 +112,11 @@ static inline refcount_t *map__refcnt(struct map *map) return &map->refcnt; } +static inline bool map__erange_warned(struct map *map) +{ + return map->erange_warned; +} + static inline size_t map__size(const struct map *map) { return map__end(map) - map__start(map); @@ -231,4 +246,54 @@ static inline int is_no_dso_memory(const char *filename) !strncmp(filename, "/SYSV", 5) || !strcmp(filename, "[heap]"); } + +static inline void map__set_start(struct map *map, u64 start) +{ + map->start = start; +} + +static inline void map__set_end(struct map *map, u64 end) +{ + map->end = end; +} + +static inline void map__set_pgoff(struct map *map, u64 pgoff) +{ + map->pgoff = pgoff; +} + +static inline void map__add_pgoff(struct map *map, u64 inc) +{ + map->pgoff += inc; +} + +static inline void map__set_reloc(struct map *map, u64 reloc) +{ + map->reloc = reloc; +} + +static inline void map__set_priv(struct map *map, int priv) +{ + map->priv = priv; +} + +static inline void map__set_erange_warned(struct map *map, bool erange_warned) +{ + map->erange_warned = erange_warned; +} + +static inline void map__set_dso(struct map *map, struct dso *dso) +{ + map->dso = dso; +} + +static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip)) +{ + map->map_ip = map_ip; +} + +static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip)) +{ + map->unmap_ip = unmap_ip; +} #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 8a13396acd1a..df2fc8221f3c 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -339,7 +339,7 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) goto put_map; } - before->end = map__start(map); + map__set_end(before, map__start(map)); err = __maps__insert(maps, before); if (err) { map__put(before); @@ -359,8 +359,8 @@ int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp) goto put_map; } - after->start = map__end(map); - after->pgoff += map__end(map) - map__start(pos->map); + map__set_start(after, map__end(map)); + map__add_pgoff(after, map__end(map) - map__start(pos->map)); assert(map__map_ip(pos->map, map__end(map)) == map__map_ip(after, map__end(map))); err = __maps__insert(maps, after); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 35724f6a84fa..2a165d83aac4 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1354,11 +1354,11 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, */ if (*remap_kernel && dso->kernel && !kmodule) { *remap_kernel = false; - map->start = shdr->sh_addr + ref_reloc(kmap); - map->end = map__start(map) + shdr->sh_size; - map->pgoff = shdr->sh_offset; - map->map_ip = map__dso_map_ip; - map->unmap_ip = map__dso_unmap_ip; + map__set_start(map, shdr->sh_addr + ref_reloc(kmap)); + map__set_end(map, map__start(map) + shdr->sh_size); + map__set_pgoff(map, shdr->sh_offset); + map__set_map_ip(map, map__dso_map_ip); + map__set_unmap_ip(map, map__dso_unmap_ip); /* Ensure maps are correctly ordered */ if (kmaps) { int err; @@ -1379,7 +1379,7 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, */ if (*remap_kernel && kmodule) { *remap_kernel = false; - map->pgoff = shdr->sh_offset; + map__set_pgoff(map, shdr->sh_offset); } *curr_mapp = map; @@ -1414,11 +1414,12 @@ static int dso__process_kernel_symbol(struct dso *dso, struct map *map, map__kmap(curr_map)->kmaps = kmaps; if (adjust_kernel_syms) { - curr_map->start = shdr->sh_addr + ref_reloc(kmap); - curr_map->end = map__start(curr_map) + shdr->sh_size; - curr_map->pgoff = shdr->sh_offset; + map__set_start(curr_map, shdr->sh_addr + ref_reloc(kmap)); + map__set_end(curr_map, map__start(curr_map) + shdr->sh_size); + map__set_pgoff(curr_map, shdr->sh_offset); } else { - curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; + map__set_map_ip(curr_map, identity__map_ip); + map__set_unmap_ip(curr_map, identity__map_ip); } curr_dso->symtab_type = dso->symtab_type; if (maps__insert(kmaps, curr_map)) @@ -1525,8 +1526,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, if (strcmp(elf_name, kmap->ref_reloc_sym->name)) continue; kmap->ref_reloc_sym->unrelocated_addr = sym.st_value; - map->reloc = kmap->ref_reloc_sym->addr - - kmap->ref_reloc_sym->unrelocated_addr; + map__set_reloc(map, kmap->ref_reloc_sym->addr - kmap->ref_reloc_sym->unrelocated_addr); break; } } @@ -1536,7 +1536,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * attempted to prelink vdso to its virtual address. */ if (dso__is_vdso(dso)) - map->reloc = map__start(map) - dso->text_offset; + map__set_reloc(map, map__start(map) - dso->text_offset); dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap); /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 01fa5560a0bb..35d860f95b18 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -279,7 +279,7 @@ void maps__fixup_end(struct maps *maps) maps__for_each_entry(maps, curr) { if (prev != NULL && !map__end(prev->map)) - prev->map->end = map__start(curr->map); + map__set_end(prev->map, map__start(curr->map)); prev = curr; } @@ -289,7 +289,7 @@ void maps__fixup_end(struct maps *maps) * last map final address. */ if (curr && !map__end(curr->map)) - curr->map->end = ~0ULL; + map__set_end(curr->map, ~0ULL); up_write(maps__lock(maps)); } @@ -944,7 +944,8 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, return -1; } - curr_map->map_ip = curr_map->unmap_ip = identity__map_ip; + map__set_map_ip(curr_map, identity__map_ip); + map__set_unmap_ip(curr_map, identity__map_ip); if (maps__insert(kmaps, curr_map)) { dso__put(ndso); return -1; @@ -1250,8 +1251,8 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data) return -ENOMEM; } - list_node->map->end = map__start(list_node->map) + len; - list_node->map->pgoff = pgoff; + map__set_end(list_node->map, map__start(list_node->map) + len); + map__set_pgoff(list_node->map, pgoff); list_add(&list_node->node, &md->maps); @@ -1286,7 +1287,7 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) * |new......| -> |new..| * |old....| -> |old....| */ - new_map->end = map__start(old_map); + map__set_end(new_map, map__start(old_map)); } else { /* * |new.............| -> |new..| |new..| @@ -1306,10 +1307,10 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) goto out; } - m->map->end = map__start(old_map); + map__set_end(m->map, map__start(old_map)); list_add_tail(&m->node, &merged); - new_map->pgoff += map__end(old_map) - map__start(new_map); - new_map->start = map__end(old_map); + map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); + map__set_start(new_map, map__end(old_map)); } } else { /* @@ -1329,8 +1330,8 @@ int maps__merge_in(struct maps *kmaps, struct map *new_map) * |new......| -> |new...| * |old....| -> |old....| */ - new_map->pgoff += map__end(old_map) - map__start(new_map); - new_map->start = map__end(old_map); + map__add_pgoff(new_map, map__end(old_map) - map__start(new_map)); + map__set_start(new_map, map__end(old_map)); } } } @@ -1457,11 +1458,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_del_init(&new_node->node); if (new_map == replacement_map) { - map->start = map__start(new_map); - map->end = map__end(new_map); - map->pgoff = map__pgoff(new_map); - map->map_ip = new_map->map_ip; - map->unmap_ip = new_map->unmap_ip; + map__set_start(map, map__start(new_map)); + map__set_end(map, map__end(new_map)); + map__set_pgoff(map, map__pgoff(new_map)); + map__set_map_ip(map, map__map_ip_ptr(new_map)); + map__set_unmap_ip(map, map__unmap_ip_ptr(new_map)); /* Ensure maps are correctly ordered */ map__get(map); maps__remove(kmaps, map); -- GitLab From 2832ef81d4c75d4f0e3945bd2cb0b7012313cbb3 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 19 Apr 2023 12:57:53 -0300 Subject: [PATCH 3421/5631] perf map: Add reference count checking There's no strict get/put policy with map that leads to leaks or use after free. Reference count checking identifies correct pairing of gets and puts. Committer notes: Extracted from a larger patch removing bits that were covered by the use of pre-existing map__ accessors (e.g. maps__nr_maps()) and new ones added (map__refcnt() and the maps__set_ ones) to reduce RC_CHK_ACCESS(maps)-> source code pollution. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexey Bayduraev Cc: Dmitriy Vyukov Cc: Jiri Olsa Cc: Namhyung Kim Cc: Riccardo Mancini Cc: Stephane Eranian Cc: Stephen Brennan Link: https://lore.kernel.org/lkml/20230407230405.2931830-6-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/hists_link.c | 2 +- tools/perf/util/machine.c | 2 +- tools/perf/util/map.c | 43 +++++++++++++++----------- tools/perf/util/map.h | 58 +++++++++++++++++++---------------- tools/perf/util/maps.c | 4 +-- tools/perf/util/symbol.c | 4 +-- 6 files changed, 62 insertions(+), 51 deletions(-) diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 64ce8097889c..141e2972e34f 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -145,7 +145,7 @@ static int find_sample(struct sample *samples, size_t nr_samples, { while (nr_samples--) { if (samples->thread == t && - samples->map == m && + RC_CHK_ACCESS(samples->map) == RC_CHK_ACCESS(m) && samples->sym == s) return 1; samples++; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8ccbe48e23bd..9e02e19c1b7a 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -953,7 +953,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine, if (!map) return 0; - if (map != machine->vmlinux_map) + if (RC_CHK_ACCESS(map) != RC_CHK_ACCESS(machine->vmlinux_map)) maps__remove(machine__kernel_maps(machine), map); else { struct dso *dso = map__dso(map); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index bdd2742fa35b..b7f890950909 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -120,11 +120,13 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, u32 prot, u32 flags, struct build_id *bid, char *filename, struct thread *thread) { - struct map *map = malloc(sizeof(*map)); + struct map *result; + RC_STRUCT(map) *map; struct nsinfo *nsi = NULL; struct nsinfo *nnsi; - if (map != NULL) { + map = malloc(sizeof(*map)); + if (ADD_RC_CHK(result, map)) { char newfilename[PATH_MAX]; struct dso *dso, *header_bid_dso; int anon, no_dso, vdso, android; @@ -167,7 +169,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (dso == NULL) goto out_delete; - map__init(map, start, start + len, pgoff, dso); + map__init(result, start, start + len, pgoff, dso); if (anon || no_dso) { map->map_ip = map->unmap_ip = identity__map_ip; @@ -204,10 +206,10 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, } dso__put(dso); } - return map; + return result; out_delete: nsinfo__put(nsi); - free(map); + RC_CHK_FREE(result); return NULL; } @@ -218,16 +220,18 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, */ struct map *map__new2(u64 start, struct dso *dso) { - struct map *map = calloc(1, (sizeof(*map) + - (dso->kernel ? sizeof(struct kmap) : 0))); - if (map != NULL) { + struct map *result; + RC_STRUCT(map) *map; + + map = calloc(1, sizeof(*map) + (dso->kernel ? sizeof(struct kmap) : 0)); + if (ADD_RC_CHK(result, map)) { /* * ->end will be filled after we load all the symbols */ - map__init(map, start, 0, 0, dso); + map__init(result, start, 0, 0, dso); } - return map; + return result; } bool __map__is_kernel(const struct map *map) @@ -293,19 +297,21 @@ bool map__has_symbols(const struct map *map) static void map__exit(struct map *map) { BUG_ON(refcount_read(map__refcnt(map)) != 0); - dso__zput(map->dso); + dso__zput(RC_CHK_ACCESS(map)->dso); } void map__delete(struct map *map) { map__exit(map); - free(map); + RC_CHK_FREE(map); } void map__put(struct map *map) { if (map && refcount_dec_and_test(map__refcnt(map))) map__delete(map); + else + RC_CHK_PUT(map); } void map__fixup_start(struct map *map) @@ -400,20 +406,21 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name) struct map *map__clone(struct map *from) { - size_t size = sizeof(struct map); - struct map *map; + struct map *result; + RC_STRUCT(map) *map; + size_t size = sizeof(RC_STRUCT(map)); struct dso *dso = map__dso(from); if (dso && dso->kernel) size += sizeof(struct kmap); - map = memdup(from, size); - if (map != NULL) { + map = memdup(RC_CHK_ACCESS(from), size); + if (ADD_RC_CHK(result, map)) { refcount_set(&map->refcnt, 1); map->dso = dso__get(dso); } - return map; + return result; } size_t map__fprintf(struct map *map, FILE *fp) @@ -567,7 +574,7 @@ struct kmap *__map__kmap(struct map *map) if (!dso || !dso->kernel) return NULL; - return (struct kmap *)(map + 1); + return (struct kmap *)(&RC_CHK_ACCESS(map)[1]); } struct kmap *map__kmap(struct map *map) diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h index 0760c671314d..823ab7fc0acf 100644 --- a/tools/perf/util/map.h +++ b/tools/perf/util/map.h @@ -10,12 +10,13 @@ #include #include #include +#include struct dso; struct maps; struct machine; -struct map { +DECLARE_RC_STRUCT(map) { u64 start; u64 end; bool erange_warned:1; @@ -49,72 +50,72 @@ u64 identity__map_ip(const struct map *map __maybe_unused, u64 ip); static inline struct dso *map__dso(const struct map *map) { - return map->dso; + return RC_CHK_ACCESS(map)->dso; } static inline u64 map__map_ip(const struct map *map, u64 ip) { - return map->map_ip(map, ip); + return RC_CHK_ACCESS(map)->map_ip(map, ip); } static inline u64 map__unmap_ip(const struct map *map, u64 ip) { - return map->unmap_ip(map, ip); + return RC_CHK_ACCESS(map)->unmap_ip(map, ip); } static inline void *map__map_ip_ptr(struct map *map) { - return map->map_ip; + return RC_CHK_ACCESS(map)->map_ip; } static inline void* map__unmap_ip_ptr(struct map *map) { - return map->unmap_ip; + return RC_CHK_ACCESS(map)->unmap_ip; } static inline u64 map__start(const struct map *map) { - return map->start; + return RC_CHK_ACCESS(map)->start; } static inline u64 map__end(const struct map *map) { - return map->end; + return RC_CHK_ACCESS(map)->end; } static inline u64 map__pgoff(const struct map *map) { - return map->pgoff; + return RC_CHK_ACCESS(map)->pgoff; } static inline u64 map__reloc(const struct map *map) { - return map->reloc; + return RC_CHK_ACCESS(map)->reloc; } static inline u32 map__flags(const struct map *map) { - return map->flags; + return RC_CHK_ACCESS(map)->flags; } static inline u32 map__prot(const struct map *map) { - return map->prot; + return RC_CHK_ACCESS(map)->prot; } static inline bool map__priv(const struct map *map) { - return map->priv; + return RC_CHK_ACCESS(map)->priv; } static inline refcount_t *map__refcnt(struct map *map) { - return &map->refcnt; + return &RC_CHK_ACCESS(map)->refcnt; } static inline bool map__erange_warned(struct map *map) { - return map->erange_warned; + return RC_CHK_ACCESS(map)->erange_warned; } static inline size_t map__size(const struct map *map) @@ -173,9 +174,12 @@ struct map *map__clone(struct map *map); static inline struct map *map__get(struct map *map) { - if (map) + struct map *result; + + if (RC_CHK_GET(result, map)) refcount_inc(map__refcnt(map)); - return map; + + return result; } void map__put(struct map *map); @@ -249,51 +253,51 @@ static inline int is_no_dso_memory(const char *filename) static inline void map__set_start(struct map *map, u64 start) { - map->start = start; + RC_CHK_ACCESS(map)->start = start; } static inline void map__set_end(struct map *map, u64 end) { - map->end = end; + RC_CHK_ACCESS(map)->end = end; } static inline void map__set_pgoff(struct map *map, u64 pgoff) { - map->pgoff = pgoff; + RC_CHK_ACCESS(map)->pgoff = pgoff; } static inline void map__add_pgoff(struct map *map, u64 inc) { - map->pgoff += inc; + RC_CHK_ACCESS(map)->pgoff += inc; } static inline void map__set_reloc(struct map *map, u64 reloc) { - map->reloc = reloc; + RC_CHK_ACCESS(map)->reloc = reloc; } static inline void map__set_priv(struct map *map, int priv) { - map->priv = priv; + RC_CHK_ACCESS(map)->priv = priv; } static inline void map__set_erange_warned(struct map *map, bool erange_warned) { - map->erange_warned = erange_warned; + RC_CHK_ACCESS(map)->erange_warned = erange_warned; } static inline void map__set_dso(struct map *map, struct dso *dso) { - map->dso = dso; + RC_CHK_ACCESS(map)->dso = dso; } static inline void map__set_map_ip(struct map *map, u64 (*map_ip)(const struct map *map, u64 ip)) { - map->map_ip = map_ip; + RC_CHK_ACCESS(map)->map_ip = map_ip; } static inline void map__set_unmap_ip(struct map *map, u64 (*unmap_ip)(const struct map *map, u64 rip)) { - map->unmap_ip = unmap_ip; + RC_CHK_ACCESS(map)->unmap_ip = unmap_ip; } #endif /* __PERF_MAP_H */ diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index df2fc8221f3c..1aeb1db58fe5 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -126,7 +126,7 @@ void maps__remove(struct maps *maps, struct map *map) RC_CHK_ACCESS(maps)->last_search_by_name = NULL; rb_node = maps__find_node(maps, map); - assert(rb_node->map == map); + assert(rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map)); __maps__remove(maps, rb_node); if (maps__maps_by_name(maps)) __maps__free_maps_by_name(maps); @@ -420,7 +420,7 @@ struct map_rb_node *maps__find_node(struct maps *maps, struct map *map) struct map_rb_node *rb_node; maps__for_each_entry(maps, rb_node) { - if (rb_node->map == map) + if (rb_node->RC_CHK_ACCESS(map) == RC_CHK_ACCESS(map)) return rb_node; } return NULL; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 35d860f95b18..6b9c55784b56 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -865,7 +865,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, *module++ = '\0'; curr_map_dso = map__dso(curr_map); if (strcmp(curr_map_dso->short_name, module)) { - if (curr_map != initial_map && + if (RC_CHK_ACCESS(curr_map) != RC_CHK_ACCESS(initial_map) && dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(machine)) { /* @@ -1457,7 +1457,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_del_init(&new_node->node); - if (new_map == replacement_map) { + if (RC_CHK_ACCESS(new_map) == RC_CHK_ACCESS(replacement_map)) { map__set_start(map, map__start(new_map)); map__set_end(map, map__end(new_map)); map__set_pgoff(map, map__pgoff(new_map)); -- GitLab From 686c511866b4634734be9d6e827e4e55b877d35e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 Apr 2023 13:47:03 -0300 Subject: [PATCH 3422/5631] perf build: Test the refcnt check build Make sure we test build the currently added REFCNT_CHECKING infrastructure. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/make | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 96896d498641..d75876126631 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -95,6 +95,7 @@ make_no_syscall_tbl := NO_SYSCALL_TABLE=1 make_with_clangllvm := LIBCLANGLLVM=1 make_no_libpfm4 := NO_LIBPFM4=1 make_with_gtk2 := GTK2=1 +make_refcnt_check := EXTRA_CFLAGS="-DREFCNT_CHECKING=1" make_tags := tags make_cscope := cscope make_help := help @@ -159,6 +160,7 @@ run += make_with_babeltrace run += make_with_coresight run += make_with_clangllvm run += make_no_libpfm4 +run += make_refcnt_check run += make_help run += make_doc run += make_perf_o -- GitLab From 265b0de2f0f293f98173abb336edb63921b9c282 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 19 Apr 2023 16:30:05 -0300 Subject: [PATCH 3423/5631] perf probe: Add missing 0x prefix for addresses printed in hexadecimal To fix this confusing warning: # perf probe -l Failed to find debug information for address 798240 probe_main:prometheus_new_counter__return (on github.com/prometheus/client_golang/prometheus.NewCounter%return in /home/acme/git/prometheus-uprobes/main with counter) # As that 798240 is printed with PRIx64 but has no letters, better print the 0x prefix to disambiguate. Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZEBCyFu2GjTw6qOi@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/probe-finder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 54b49ce85c9f..f171360b0ef4 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -1729,7 +1729,7 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr, addr += baseaddr; /* Find cu die */ if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) { - pr_warning("Failed to find debug information for address %" PRIx64 "\n", + pr_warning("Failed to find debug information for address %#" PRIx64 "\n", addr); ret = -EINVAL; goto end; -- GitLab From 691d0b782066a6eeeecbfceb7910a8f6184e6105 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Tue, 18 Apr 2023 13:19:02 -0700 Subject: [PATCH 3424/5631] SUNRPC: remove the maximum number of retries in call_bind_status Currently call_bind_status places a hard limit of 3 to the number of retries on EACCES error. This limit was done to prevent NLM unlock requests from being hang forever when the server keeps returning garbage. However this change causes problem for cases when NLM service takes longer than 9 seconds to register with the port mapper after a restart. This patch removes this hard coded limit and let the RPC handles the retry based on the standard hard/soft task semantics. Fixes: 0b760113a3a1 ("NLM: Don't hang forever on NLM unlock requests") Reported-by: Helen Chao Tested-by: Helen Chao Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Anna Schumaker --- include/linux/sunrpc/sched.h | 3 +-- net/sunrpc/clnt.c | 3 --- net/sunrpc/sched.c | 1 - 3 files changed, 1 insertion(+), 6 deletions(-) diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index b8ca3ecaf8d7..8ada7dc802d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index fd7e1c630493..d2ee56634308 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2050,9 +2050,6 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } - if (task->tk_rebind_retry == 0) - break; - task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ENOBUFS: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index be587a308e05..c8321de341ee 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -817,7 +817,6 @@ rpc_init_task_statistics(struct rpc_task *task) /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; /* starting timestamp */ task->tk_start = ktime_get(); -- GitLab From 422d56536fd2ebac254e469e196c64cf53cd8a07 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 20 Apr 2023 08:18:34 +1000 Subject: [PATCH 3425/5631] xfs: fix duplicate includes Header files were already included, just not in the normal order. Remove the duplicates, preserving normal order. Also move xfs_ag.h include to before the scrub internal includes which are normally last in the include list. Fixes: d5c88131dbf0 ("xfs: allow queued AG intents to drain before scrubbing") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/scrub/refcount.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index ed5eb367ce49..304ea1e1bfb0 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -9,6 +9,7 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" +#include "xfs_ag.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_refcount.h" @@ -16,9 +17,6 @@ #include "scrub/common.h" #include "scrub/btree.h" #include "scrub/trace.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_ag.h" /* * Set us up to scrub reference count btrees. -- GitLab From 71deb8a5658c592ccad5ededb2ceffef6fcbba5f Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Thu, 20 Apr 2023 08:18:36 +1000 Subject: [PATCH 3426/5631] xfs: Extend table marker on deprecated mount options table Sphinx reports htmldocs warning on deprecated mount options table: /home/bagas/repo/linux-kernel/Documentation/admin-guide/xfs.rst:243: WARNING: Malformed table. Text in column margin in table line 5. =========================== ================ Name Removal Schedule =========================== ================ Mounting with V4 filesystem September 2030 Mounting ascii-ci filesystem September 2030 ikeep/noikeep September 2025 attr2/noattr2 September 2025 =========================== ================ Extend the table markers to take account of the second name entry ("Mounting ascii-ci filesystem"), which is now the widest and to fix the above warning. Fixes: 7ba83850ca2691 ("xfs: deprecate the ascii-ci feature") Signed-off-by: Bagas Sanjaya Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- Documentation/admin-guide/xfs.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst index e85a9404d5c0..3a9c041d7f6c 100644 --- a/Documentation/admin-guide/xfs.rst +++ b/Documentation/admin-guide/xfs.rst @@ -236,14 +236,14 @@ the dates listed above. Deprecated Mount Options ======================== -=========================== ================ +============================ ================ Name Removal Schedule -=========================== ================ +============================ ================ Mounting with V4 filesystem September 2030 Mounting ascii-ci filesystem September 2030 ikeep/noikeep September 2025 attr2/noattr2 September 2025 -=========================== ================ +============================ ================ Removed Mount Options -- GitLab From 648a1783fe2551f5a091c9a5f8f463cb2cbf8745 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Fri, 7 Apr 2023 14:09:09 +1000 Subject: [PATCH 3427/5631] powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU -mcpu=power10 will generate prefixed and pcrel code by default, which we do not support. The general kernel disables these with cflags, but those were missed for the boot wrapper. Fixes: 4b2a9315f20d ("powerpc/64s: POWER10 CPU Kconfig build option") Cc: stable@vger.kernel.org # v6.1+ Reported-by: Danny Tsen Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230407040909.230998-1-npiggin@gmail.com --- arch/powerpc/boot/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 08071bac056d..129a1e190f25 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,6 +34,8 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ + $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) -- GitLab From 821b3a471f686910b97228010861c4a99d07fd86 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sun, 9 Apr 2023 02:08:05 +0200 Subject: [PATCH 3428/5631] powerpc/fsl_uli1575: Misc cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use a single line for uli_exclude_device(). Add uli_exclude_device() prototype in ppc-pci.h and guard it. Remove that prototype from mpc85xx_ds.c and mpc86xx_hpcn.c files. Make uli_pirq_to_irq[] static as it is used only in that file. Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-2-pali@kernel.org --- arch/powerpc/include/asm/ppc-pci.h | 9 +++++++++ arch/powerpc/platforms/85xx/mpc85xx_ds.c | 4 +--- arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 4 +--- arch/powerpc/platforms/fsl_uli1575.c | 6 +++--- 4 files changed, 14 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index f6cf0159024e..a8db969dd595 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -57,11 +57,20 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev); #endif /* CONFIG_EEH */ +#ifdef CONFIG_FSL_ULI1575 +int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn); +#endif /* CONFIG_FSL_ULI1575 */ + #define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) #else /* CONFIG_PCI */ static inline void init_pci_config_tokens(void) { } #endif /* !CONFIG_PCI */ +#if !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) +#include +static inline int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { return PCIBIOS_SUCCESSFUL; } +#endif /* !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) */ + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_PPC_PCI_H */ diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 70167b8f00a3..ed7b71d55b10 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include @@ -107,9 +108,6 @@ void __init mpc85xx_ds_pic_init(void) } #ifdef CONFIG_PCI -extern int uli_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn); - static struct device_node *pci_with_uli; static int mpc85xx_exclude_device(struct pci_controller *hose, diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 7b00ebd2d7f8..3dbd396a0df5 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -39,9 +40,6 @@ #endif #ifdef CONFIG_PCI -extern int uli_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn); - static int mpc86xx_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c index 84afae7a2561..a32f9cef7845 100644 --- a/arch/powerpc/platforms/fsl_uli1575.c +++ b/arch/powerpc/platforms/fsl_uli1575.c @@ -13,6 +13,7 @@ #include #include +#include #define ULI_PIRQA 0x08 #define ULI_PIRQB 0x09 @@ -36,7 +37,7 @@ #define ULI_8259_IRQ14 0x0d #define ULI_8259_IRQ15 0x0f -u8 uli_pirq_to_irq[8] = { +static u8 uli_pirq_to_irq[8] = { ULI_8259_IRQ9, /* PIRQA */ ULI_8259_IRQ10, /* PIRQB */ ULI_8259_IRQ11, /* PIRQC */ @@ -341,8 +342,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5288, hpcd_quirk_uli5288); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5229, hpcd_quirk_uli5229); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 0x5288, hpcd_final_uli5288); -int uli_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) +int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { if (bus == (hose->first_busno + 2)) { /* exclude Modem controller */ -- GitLab From 485536b9f289c8c3c86ecaad0f05a1a7b633cb8a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:06 +0200 Subject: [PATCH 3429/5631] powerpc/85xx: mpc85xx_ds: Simplify mpc85xx_exclude_device() function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function mpc85xx_exclude_device() is installed and used only when pci_with_uli is fsl_pci_primary. So replace check for pci_with_uli by fsl_pci_primary in mpc85xx_exclude_device() and move pci_with_uli variable declaration into function mpc85xx_ds_uli_init() where it is used. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-3-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index ed7b71d55b10..0c905a838942 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -108,12 +108,10 @@ void __init mpc85xx_ds_pic_init(void) } #ifdef CONFIG_PCI -static struct device_node *pci_with_uli; - static int mpc85xx_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { - if (hose->dn == pci_with_uli) + if (hose->dn == fsl_pci_primary) return uli_exclude_device(hose, bus, devfn); return PCIBIOS_SUCCESSFUL; @@ -124,6 +122,7 @@ static void __init mpc85xx_ds_uli_init(void) { #ifdef CONFIG_PCI struct device_node *node; + struct device_node *pci_with_uli; /* See if we have a ULI under the primary */ -- GitLab From aa9f3d2d619b878a66dc918d8b3bf984300f975f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:07 +0200 Subject: [PATCH 3430/5631] powerpc/fsl_uli1575: Simplify uli_exclude_device() usage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function uli_exclude_device() is called only from mpc86xx_exclude_device() and mpc85xx_exclude_device() functions. Both those functions are same, so merge its logic directly into the uli_exclude_device() function. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-4-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 13 +------------ arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 13 +------------ arch/powerpc/platforms/fsl_uli1575.c | 4 +++- 3 files changed, 5 insertions(+), 25 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 0c905a838942..581b5f0ef3be 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -107,17 +107,6 @@ void __init mpc85xx_ds_pic_init(void) #endif /* CONFIG_PPC_I8259 */ } -#ifdef CONFIG_PCI -static int mpc85xx_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) -{ - if (hose->dn == fsl_pci_primary) - return uli_exclude_device(hose, bus, devfn); - - return PCIBIOS_SUCCESSFUL; -} -#endif /* CONFIG_PCI */ - static void __init mpc85xx_ds_uli_init(void) { #ifdef CONFIG_PCI @@ -132,7 +121,7 @@ static void __init mpc85xx_ds_uli_init(void) node = pci_with_uli; if (pci_with_uli == fsl_pci_primary) { - ppc_md.pci_exclude_device = mpc85xx_exclude_device; + ppc_md.pci_exclude_device = uli_exclude_device; break; } } diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 3dbd396a0df5..645125cc8420 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -39,17 +39,6 @@ #define DBG(fmt...) do { } while(0) #endif -#ifdef CONFIG_PCI -static int mpc86xx_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) -{ - if (hose->dn == fsl_pci_primary) - return uli_exclude_device(hose, bus, devfn); - - return PCIBIOS_SUCCESSFUL; -} -#endif /* CONFIG_PCI */ - static void __init mpc86xx_hpcn_setup_arch(void) @@ -58,7 +47,7 @@ mpc86xx_hpcn_setup_arch(void) ppc_md.progress("mpc86xx_hpcn_setup_arch()", 0); #ifdef CONFIG_PCI - ppc_md.pci_exclude_device = mpc86xx_exclude_device; + ppc_md.pci_exclude_device = uli_exclude_device; #endif printk("MPC86xx HPCN board from Freescale Semiconductor\n"); diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c index a32f9cef7845..1350db0b935d 100644 --- a/arch/powerpc/platforms/fsl_uli1575.c +++ b/arch/powerpc/platforms/fsl_uli1575.c @@ -15,6 +15,8 @@ #include #include +#include + #define ULI_PIRQA 0x08 #define ULI_PIRQB 0x09 #define ULI_PIRQC 0x0a @@ -344,7 +346,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 0x5288, hpcd_final_uli5288); int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { - if (bus == (hose->first_busno + 2)) { + if (hose->dn == fsl_pci_primary && bus == (hose->first_busno + 2)) { /* exclude Modem controller */ if ((PCI_SLOT(devfn) == 29) && (PCI_FUNC(devfn) == 1)) return PCIBIOS_DEVICE_NOT_FOUND; -- GitLab From c4f6d8665cff0abacd164b3cd10afe0385290db2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:08 +0200 Subject: [PATCH 3431/5631] powerpc/85xx: mpc85xx_ds: Move uli_init() code into its own driver file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move uli_init() function into existing driver fsl_uli1575.c file in order to share its code between more platforms and board files. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-5-pali@kernel.org --- arch/powerpc/include/asm/ppc-pci.h | 2 ++ arch/powerpc/platforms/85xx/mpc85xx_ds.c | 23 +---------------------- arch/powerpc/platforms/fsl_uli1575.c | 19 +++++++++++++++++++ 3 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index a8db969dd595..0e393aeed912 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -59,6 +59,7 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev); #ifdef CONFIG_FSL_ULI1575 int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn); +void __init uli_init(void); #endif /* CONFIG_FSL_ULI1575 */ #define PCI_BUSNO(bdfn) ((bdfn >> 8) & 0xff) @@ -70,6 +71,7 @@ static inline void init_pci_config_tokens(void) { } #if !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) #include static inline int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { return PCIBIOS_SUCCESSFUL; } +static inline void __init uli_init(void) {} #endif /* !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 581b5f0ef3be..c474da3eeea8 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -107,27 +107,6 @@ void __init mpc85xx_ds_pic_init(void) #endif /* CONFIG_PPC_I8259 */ } -static void __init mpc85xx_ds_uli_init(void) -{ -#ifdef CONFIG_PCI - struct device_node *node; - struct device_node *pci_with_uli; - - /* See if we have a ULI under the primary */ - - node = of_find_node_by_name(NULL, "uli1575"); - while ((pci_with_uli = of_get_parent(node))) { - of_node_put(node); - node = pci_with_uli; - - if (pci_with_uli == fsl_pci_primary) { - ppc_md.pci_exclude_device = uli_exclude_device; - break; - } - } -#endif -} - /* * Setup the architecture */ @@ -138,7 +117,7 @@ static void __init mpc85xx_ds_setup_arch(void) swiotlb_detect_4g(); fsl_pci_assign_primary(); - mpc85xx_ds_uli_init(); + uli_init(); mpc85xx_smp_init(); printk("MPC85xx DS board from Freescale Semiconductor\n"); diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c index 1350db0b935d..b073db9d7c79 100644 --- a/arch/powerpc/platforms/fsl_uli1575.c +++ b/arch/powerpc/platforms/fsl_uli1575.c @@ -358,3 +358,22 @@ int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) return PCIBIOS_SUCCESSFUL; } + +void __init uli_init(void) +{ + struct device_node *node; + struct device_node *pci_with_uli; + + /* See if we have a ULI under the primary */ + + node = of_find_node_by_name(NULL, "uli1575"); + while ((pci_with_uli = of_get_parent(node))) { + of_node_put(node); + node = pci_with_uli; + + if (pci_with_uli == fsl_pci_primary) { + ppc_md.pci_exclude_device = uli_exclude_device; + break; + } + } +} -- GitLab From 304e364d1f89f590b72af6bec42b5199971b531b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:09 +0200 Subject: [PATCH 3432/5631] powerpc/85xx: mpc85xx_rdb: Do not automatically select FSL_ULI1575 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Boards provided by CONFIG_MPC85xx_RDB option do not initialize fsl_uli1575.c driver. So remove explicit select dependency on it. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-6-pali@kernel.org --- arch/powerpc/platforms/85xx/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index b92cb2b4d54d..a8ce6616fd0a 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -90,7 +90,6 @@ config MPC85xx_RDB bool "Freescale P102x MBG/UTM/RDB and P2020 RDB" select PPC_I8259 select DEFAULT_UIMAGE - select FSL_ULI1575 if PCI select SWIOTLB help This option enables support for the P1020 MBG PC, P1020 UTM PC, -- GitLab From 22fdf79171e8509db54599fd2c05ef0022ee83f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:10 +0200 Subject: [PATCH 3433/5631] powerpc/fsl_uli1575: Allow to disable FSL_ULI1575 support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ULI1575 PCIe south bridge exists only on some Freescale boards. Allow to disable CONFIG_FSL_ULI1575 symbol when it is not explicitly selected and only implied. This is achieved by marking symbol as visible by providing short description. Also adds dependency for this symbol to prevent enabling it on platforms on which driver does not compile. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-7-pali@kernel.org --- arch/powerpc/platforms/Kconfig | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d41dad227de8..608ac0290e3a 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -261,7 +261,9 @@ config CPM2 on it (826x, 827x, 8560). config FSL_ULI1575 - bool + bool "ULI1575 PCIe south bridge support" + depends on FSL_SOC_BOOKE || PPC_86xx + select FSL_PCI select GENERIC_ISA_DMA help Supports for the ULI1575 PCIe south bridge that exists on some -- GitLab From 40b221daf17bf8e0f27c7f1ffc8d5179d58e8597 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:11 +0200 Subject: [PATCH 3434/5631] powerpc/86xx: mpc86xx_hpcn: Call uli_init() instead of explicit ppc_md assignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After calling fsl_pci_assign_primary(), it is possible to use uli_init() to conditionally initialize ppc_md.pci_exclude_device callback based on the uli1575 detection. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-8-pali@kernel.org --- arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index 645125cc8420..812110673d88 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -46,10 +46,6 @@ mpc86xx_hpcn_setup_arch(void) if (ppc_md.progress) ppc_md.progress("mpc86xx_hpcn_setup_arch()", 0); -#ifdef CONFIG_PCI - ppc_md.pci_exclude_device = uli_exclude_device; -#endif - printk("MPC86xx HPCN board from Freescale Semiconductor\n"); #ifdef CONFIG_SMP @@ -57,6 +53,7 @@ mpc86xx_hpcn_setup_arch(void) #endif fsl_pci_assign_primary(); + uli_init(); swiotlb_detect_4g(); } -- GitLab From 3ce271435b717e1dbc4fc8191a69e88deb4f8990 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sun, 9 Apr 2023 02:08:12 +0200 Subject: [PATCH 3435/5631] powerpc/fsl_uli1575: Mark uli_exclude_device() as static MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function uli_exclude_device() is not used outside of the fsl_uli1575.c source file anymore. So mark it as static and remove public prototype. Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230409000812.18904-9-pali@kernel.org --- arch/powerpc/include/asm/ppc-pci.h | 3 --- arch/powerpc/platforms/fsl_uli1575.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index 0e393aeed912..d9fcff575027 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -58,7 +58,6 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev); #endif /* CONFIG_EEH */ #ifdef CONFIG_FSL_ULI1575 -int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn); void __init uli_init(void); #endif /* CONFIG_FSL_ULI1575 */ @@ -69,8 +68,6 @@ static inline void init_pci_config_tokens(void) { } #endif /* !CONFIG_PCI */ #if !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) -#include -static inline int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { return PCIBIOS_SUCCESSFUL; } static inline void __init uli_init(void) {} #endif /* !defined(CONFIG_PCI) || !defined(CONFIG_FSL_ULI1575) */ diff --git a/arch/powerpc/platforms/fsl_uli1575.c b/arch/powerpc/platforms/fsl_uli1575.c index b073db9d7c79..b8d37a9932f1 100644 --- a/arch/powerpc/platforms/fsl_uli1575.c +++ b/arch/powerpc/platforms/fsl_uli1575.c @@ -344,7 +344,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5288, hpcd_quirk_uli5288); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AL, 0x5229, hpcd_quirk_uli5229); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL, 0x5288, hpcd_final_uli5288); -int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) +static int uli_exclude_device(struct pci_controller *hose, u_char bus, u_char devfn) { if (hose->dn == fsl_pci_primary && bus == (hose->first_busno + 2)) { /* exclude Modem controller */ -- GitLab From 6faab5d7ac49d40bedf348a879042681755c14b0 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:10 +0200 Subject: [PATCH 3436/5631] powerpc/85xx: Remove DBG() macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DBG() macro is defined at three places while used only one time at one place. Replace its only use by a pr_debug() and remove the macro. Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-2-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 10 +--------- arch/powerpc/platforms/85xx/mpc85xx_mds.c | 7 ------- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 9 --------- 3 files changed, 1 insertion(+), 25 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index c474da3eeea8..25edfe1b8ae1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -34,14 +34,6 @@ #include "mpc85xx.h" -#undef DEBUG - -#ifdef DEBUG -#define DBG(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define DBG(fmt, args...) -#endif - #ifdef CONFIG_PPC_I8259 static void mpc85xx_8259_cascade(struct irq_desc *desc) { @@ -98,7 +90,7 @@ void __init mpc85xx_ds_pic_init(void) return; } - DBG("mpc85xxds: cascade mapped to irq %d\n", cascade_irq); + pr_debug("mpc85xxds: cascade mapped to irq %d\n", cascade_irq); i8259_init(cascade_node, 0); of_node_put(cascade_node); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index 28a04928250f..0546f19416c2 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -49,13 +49,6 @@ #include "mpc85xx.h" -#undef DEBUG -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - #if IS_BUILTIN(CONFIG_PHYLIB) #define MV88E1111_SCR 0x10 diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index aa24793ad25c..acc4145adcf7 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -29,15 +29,6 @@ #include "mpc85xx.h" -#undef DEBUG - -#ifdef DEBUG -#define DBG(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define DBG(fmt, args...) -#endif - - void __init mpc85xx_rdb_pic_init(void) { struct mpic *mpic; -- GitLab From 0abc1eadd605d461b9a953e6a27d810ed169ed7b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:11 +0200 Subject: [PATCH 3437/5631] powerpc/85xx: mpc85xx_{ds/rdb} compact the call to mpic_alloc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reduce number of lines in the call to mpic_alloc(). Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-3-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 18 ++++++------------ arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 16 +++++----------- 2 files changed, 11 insertions(+), 23 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 25edfe1b8ae1..c6016915264c 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -50,23 +50,17 @@ static void mpc85xx_8259_cascade(struct irq_desc *desc) void __init mpc85xx_ds_pic_init(void) { struct mpic *mpic; + int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; #ifdef CONFIG_PPC_I8259 struct device_node *np; struct device_node *cascade_node = NULL; int cascade_irq; #endif - if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) { - mpic = mpic_alloc(NULL, 0, - MPIC_NO_RESET | - MPIC_BIG_ENDIAN | - MPIC_SINGLE_DEST_CPU, - 0, 256, " OpenPIC "); - } else { - mpic = mpic_alloc(NULL, 0, - MPIC_BIG_ENDIAN | - MPIC_SINGLE_DEST_CPU, - 0, 256, " OpenPIC "); - } + + if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) + flags |= MPIC_NO_RESET; + + mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); BUG_ON(mpic == NULL); mpic_init(mpic); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index acc4145adcf7..c7ce8a79992d 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -32,18 +32,12 @@ void __init mpc85xx_rdb_pic_init(void) { struct mpic *mpic; + int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; - if (of_machine_is_compatible("fsl,MPC85XXRDB-CAMP")) { - mpic = mpic_alloc(NULL, 0, MPIC_NO_RESET | - MPIC_BIG_ENDIAN | - MPIC_SINGLE_DEST_CPU, - 0, 256, " OpenPIC "); - } else { - mpic = mpic_alloc(NULL, 0, - MPIC_BIG_ENDIAN | - MPIC_SINGLE_DEST_CPU, - 0, 256, " OpenPIC "); - } + if (of_machine_is_compatible("fsl,MPC85XXRDB-CAMP")) + flags |= MPIC_NO_RESET; + + mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); BUG_ON(mpic == NULL); mpic_init(mpic); -- GitLab From 1bca2f8219da51a1119d1f4054b44880cbf0494e Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:12 +0200 Subject: [PATCH 3438/5631] powerpc/85xx: mpc85xx_{ds/rdb} replace BUG_ON() by WARN_ON() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit No need to BUG() in case mpic_alloc() fails. Use WARN_ON(). Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-4-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 4 +++- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index c6016915264c..98cca1102e0b 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -62,7 +62,9 @@ void __init mpc85xx_ds_pic_init(void) mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); - BUG_ON(mpic == NULL); + if (WARN_ON(!mpic)) + return; + mpic_init(mpic); #ifdef CONFIG_PPC_I8259 diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index c7ce8a79992d..a802053b37b3 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -39,7 +39,9 @@ void __init mpc85xx_rdb_pic_init(void) mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); - BUG_ON(mpic == NULL); + if (WARN_ON(!mpic)) + return; + mpic_init(mpic); } -- GitLab From 15c6ba7992993fecdac52a424ce35b6e4a272c75 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:13 +0200 Subject: [PATCH 3439/5631] powerpc/85xx: mpc85xx_{ds/rdb} replace prink by pr_xxx macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use pr_debug() instead of printk(KERN_DEBUG Use pr_err() instead of printk(KERN_ERR Use pr_info() instead of printk(KERN_INFO or printk(" Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-5-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 6 +++--- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 98cca1102e0b..d8d13438e18f 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -76,13 +76,13 @@ void __init mpc85xx_ds_pic_init(void) } if (cascade_node == NULL) { - printk(KERN_DEBUG "Could not find i8259 PIC\n"); + pr_debug("Could not find i8259 PIC\n"); return; } cascade_irq = irq_of_parse_and_map(cascade_node, 0); if (!cascade_irq) { - printk(KERN_ERR "Failed to map cascade interrupt\n"); + pr_err("Failed to map cascade interrupt\n"); return; } @@ -108,7 +108,7 @@ static void __init mpc85xx_ds_setup_arch(void) uli_init(); mpc85xx_smp_init(); - printk("MPC85xx DS board from Freescale Semiconductor\n"); + pr_info("MPC85xx DS board from Freescale Semiconductor\n"); } machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index a802053b37b3..64badacf126d 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -92,7 +92,7 @@ static void __init mpc85xx_rdb_setup_arch(void) #endif #endif /* CONFIG_QUICC_ENGINE */ - printk(KERN_INFO "MPC85xx RDB board from Freescale Semiconductor\n"); + pr_info("MPC85xx RDB board from Freescale Semiconductor\n"); } machine_arch_initcall(p2020_rdb, mpc85xx_common_publish_devices); -- GitLab From f435f67024cbee223083aa843f9b69888c8de8a8 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:14 +0200 Subject: [PATCH 3440/5631] powerpc/85xx: Remove #ifdefs CONFIG_PPC_I8259 in mpc85xx_ds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All necessary items are declared all the time, no need to use a #ifdef CONFIG_PPC_I8259. Refactor CONFIG_PPC_I8259 actions into a dedicated init function. Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-6-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 37 +++++++++++++----------- 1 file changed, 20 insertions(+), 17 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index d8d13438e18f..4ae300e76c2d 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -34,7 +34,6 @@ #include "mpc85xx.h" -#ifdef CONFIG_PPC_I8259 static void mpc85xx_8259_cascade(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); @@ -45,29 +44,16 @@ static void mpc85xx_8259_cascade(struct irq_desc *desc) } chip->irq_eoi(&desc->irq_data); } -#endif /* CONFIG_PPC_I8259 */ -void __init mpc85xx_ds_pic_init(void) +static void __init mpc85xx_8259_init(void) { - struct mpic *mpic; - int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; -#ifdef CONFIG_PPC_I8259 struct device_node *np; struct device_node *cascade_node = NULL; int cascade_irq; -#endif - if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) - flags |= MPIC_NO_RESET; - - mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); - - if (WARN_ON(!mpic)) + if (!IS_ENABLED(CONFIG_PPC_I8259)) return; - mpic_init(mpic); - -#ifdef CONFIG_PPC_I8259 /* Initialize the i8259 controller */ for_each_node_by_type(np, "interrupt-controller") if (of_device_is_compatible(np, "chrp,iic")) { @@ -92,7 +78,24 @@ void __init mpc85xx_ds_pic_init(void) of_node_put(cascade_node); irq_set_chained_handler(cascade_irq, mpc85xx_8259_cascade); -#endif /* CONFIG_PPC_I8259 */ +} + +void __init mpc85xx_ds_pic_init(void) +{ + struct mpic *mpic; + int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; + + if (of_machine_is_compatible("fsl,MPC8572DS-CAMP")) + flags |= MPIC_NO_RESET; + + mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); + + if (WARN_ON(!mpic)) + return; + + mpic_init(mpic); + + mpc85xx_8259_init(); } /* -- GitLab From b1a54cb693724b6212efa64d877126769ece4d4c Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Sat, 8 Apr 2023 16:01:15 +0200 Subject: [PATCH 3441/5631] powerpc/85xx: Remove #ifdef CONFIG_QUICC_ENGINE in mpc85xx_rdb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mpc85xx_qe_par_io_init() is a stub when CONFIG_QUICC_ENGINE is not set. CONFIG_UCC_GETH and CONFIG_SERIAL_QE depend on CONFIG_QUICC_ENGINE. Remove #ifdef CONFIG_QUICC_ENGINE Signed-off-by: Christophe Leroy Signed-off-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-7-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index 64badacf126d..cdafecaecf56 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -57,7 +57,6 @@ static void __init mpc85xx_rdb_setup_arch(void) fsl_pci_assign_primary(); -#ifdef CONFIG_QUICC_ENGINE mpc85xx_qe_par_io_init(); #if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE) if (machine_is(p1025_rdb)) { @@ -90,7 +89,6 @@ static void __init mpc85xx_rdb_setup_arch(void) } #endif -#endif /* CONFIG_QUICC_ENGINE */ pr_info("MPC85xx RDB board from Freescale Semiconductor\n"); } -- GitLab From ba5a7ca277afc0e9083a7a2021725425a493cfb2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:16 +0200 Subject: [PATCH 3442/5631] powerpc/85xx: p2020: Move all P2020 DS machine descriptions to p2020.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This moves P2020 DS machine descriptions into new p2020.c source file. This is preparation for code de-duplication and providing one unified machine description for all P2020 boards. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-8-pali@kernel.org --- arch/powerpc/platforms/85xx/Makefile | 2 +- arch/powerpc/platforms/85xx/mpc85xx.h | 3 ++ arch/powerpc/platforms/85xx/mpc85xx_ds.c | 16 +-------- arch/powerpc/platforms/85xx/p2020.c | 41 ++++++++++++++++++++++++ 4 files changed, 46 insertions(+), 16 deletions(-) create mode 100644 arch/powerpc/platforms/85xx/p2020.c diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 260fbad7967b..1f54623db9b7 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -16,7 +16,7 @@ obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o obj-$(CONFIG_MPC8536_DS) += mpc8536_ds.o -obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o +obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o p2020.o obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index cb84c5c56c36..ca8b39e6b05a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -15,4 +15,7 @@ extern void mpc85xx_qe_par_io_init(void); static inline void __init mpc85xx_qe_par_io_init(void) {} #endif +void __init mpc85xx_ds_pic_init(void); +void __init mpc85xx_ds_setup_arch(void); + #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index 4ae300e76c2d..af2cafec4f0a 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -101,7 +101,7 @@ void __init mpc85xx_ds_pic_init(void) /* * Setup the architecture */ -static void __init mpc85xx_ds_setup_arch(void) +void __init mpc85xx_ds_setup_arch(void) { if (ppc_md.progress) ppc_md.progress("mpc85xx_ds_setup_arch()", 0); @@ -116,7 +116,6 @@ static void __init mpc85xx_ds_setup_arch(void) machine_arch_initcall(mpc8544_ds, mpc85xx_common_publish_devices); machine_arch_initcall(mpc8572_ds, mpc85xx_common_publish_devices); -machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); define_machine(mpc8544_ds) { .name = "MPC8544 DS", @@ -143,16 +142,3 @@ define_machine(mpc8572_ds) { .get_irq = mpic_get_irq, .progress = udbg_progress, }; - -define_machine(p2020_ds) { - .name = "P2020 DS", - .compatible = "fsl,P2020DS", - .setup_arch = mpc85xx_ds_setup_arch, - .init_IRQ = mpc85xx_ds_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif - .get_irq = mpic_get_irq, - .progress = udbg_progress, -}; diff --git a/arch/powerpc/platforms/85xx/p2020.c b/arch/powerpc/platforms/85xx/p2020.c new file mode 100644 index 000000000000..356335122153 --- /dev/null +++ b/arch/powerpc/platforms/85xx/p2020.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Freescale P2020 board Setup + * + * Copyright 2007,2009,2012-2013 Freescale Semiconductor Inc. + * Copyright 2022-2023 Pali Rohár + */ + +#include +#include +#include + +#include +#include +#include +#include +#include + +#include + +#include "smp.h" +#include "mpc85xx.h" + +#ifdef CONFIG_MPC85xx_DS +machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); +#endif /* CONFIG_MPC85xx_DS */ + +#ifdef CONFIG_MPC85xx_DS +define_machine(p2020_ds) { + .name = "P2020 DS", + .compatible = "fsl,P2020DS", + .setup_arch = mpc85xx_ds_setup_arch, + .init_IRQ = mpc85xx_ds_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_irq, + .progress = udbg_progress, +}; +#endif /* CONFIG_MPC85xx_DS */ -- GitLab From c30aa8fd6cabd12917277facbd2bd81dc3a226d6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:17 +0200 Subject: [PATCH 3443/5631] powerpc/85xx: p2020: Move all P2020 RDB machine descriptions to p2020.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This moves P2020 RDB machine descriptions into new p2020.c source file. This is preparation for code de-duplication and providing one unified machine description for all P2020 boards. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-9-pali@kernel.org --- arch/powerpc/platforms/85xx/Makefile | 2 +- arch/powerpc/platforms/85xx/mpc85xx.h | 2 ++ arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 30 +-------------------- arch/powerpc/platforms/85xx/p2020.c | 33 +++++++++++++++++++++++ 4 files changed, 37 insertions(+), 30 deletions(-) diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 1f54623db9b7..93451850ed83 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -18,7 +18,7 @@ obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o obj-$(CONFIG_MPC8536_DS) += mpc8536_ds.o obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o p2020.o obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o -obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o +obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o p2020.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o obj-$(CONFIG_P1022_DS) += p1022_ds.o obj-$(CONFIG_P1022_RDK) += p1022_rdk.o diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index ca8b39e6b05a..8f7b37c1de87 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -17,5 +17,7 @@ static inline void __init mpc85xx_qe_par_io_init(void) {} void __init mpc85xx_ds_pic_init(void); void __init mpc85xx_ds_setup_arch(void); +void __init mpc85xx_rdb_setup_arch(void); +void __init mpc85xx_rdb_pic_init(void); #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index cdafecaecf56..dbedffc57ce8 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -48,7 +48,7 @@ void __init mpc85xx_rdb_pic_init(void) /* * Setup the architecture */ -static void __init mpc85xx_rdb_setup_arch(void) +void __init mpc85xx_rdb_setup_arch(void) { if (ppc_md.progress) ppc_md.progress("mpc85xx_rdb_setup_arch()", 0); @@ -93,8 +93,6 @@ static void __init mpc85xx_rdb_setup_arch(void) pr_info("MPC85xx RDB board from Freescale Semiconductor\n"); } -machine_arch_initcall(p2020_rdb, mpc85xx_common_publish_devices); -machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_rdb, mpc85xx_common_publish_devices); machine_arch_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices); @@ -104,19 +102,6 @@ machine_arch_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices); machine_arch_initcall(p1025_rdb, mpc85xx_common_publish_devices); machine_arch_initcall(p1024_rdb, mpc85xx_common_publish_devices); -define_machine(p2020_rdb) { - .name = "P2020 RDB", - .compatible = "fsl,P2020RDB", - .setup_arch = mpc85xx_rdb_setup_arch, - .init_IRQ = mpc85xx_rdb_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif - .get_irq = mpic_get_irq, - .progress = udbg_progress, -}; - define_machine(p1020_rdb) { .name = "P1020 RDB", .compatible = "fsl,P1020RDB", @@ -143,19 +128,6 @@ define_machine(p1021_rdb_pc) { .progress = udbg_progress, }; -define_machine(p2020_rdb_pc) { - .name = "P2020RDB-PC", - .compatible = "fsl,P2020RDB-PC", - .setup_arch = mpc85xx_rdb_setup_arch, - .init_IRQ = mpc85xx_rdb_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif - .get_irq = mpic_get_irq, - .progress = udbg_progress, -}; - define_machine(p1025_rdb) { .name = "P1025 RDB", .compatible = "fsl,P1025RDB", diff --git a/arch/powerpc/platforms/85xx/p2020.c b/arch/powerpc/platforms/85xx/p2020.c index 356335122153..41bba8c0e335 100644 --- a/arch/powerpc/platforms/85xx/p2020.c +++ b/arch/powerpc/platforms/85xx/p2020.c @@ -25,6 +25,11 @@ machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); #endif /* CONFIG_MPC85xx_DS */ +#ifdef CONFIG_MPC85xx_RDB +machine_arch_initcall(p2020_rdb, mpc85xx_common_publish_devices); +machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices); +#endif /* CONFIG_MPC85xx_RDB */ + #ifdef CONFIG_MPC85xx_DS define_machine(p2020_ds) { .name = "P2020 DS", @@ -39,3 +44,31 @@ define_machine(p2020_ds) { .progress = udbg_progress, }; #endif /* CONFIG_MPC85xx_DS */ + +#ifdef CONFIG_MPC85xx_RDB +define_machine(p2020_rdb) { + .name = "P2020 RDB", + .compatible = "fsl,P2020RDB", + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_irq, + .progress = udbg_progress, +}; + +define_machine(p2020_rdb_pc) { + .name = "P2020RDB-PC", + .compatible = "fsl,P2020RDB-PC", + .setup_arch = mpc85xx_rdb_setup_arch, + .init_IRQ = mpc85xx_rdb_pic_init, +#ifdef CONFIG_PCI + .pcibios_fixup_bus = fsl_pcibios_fixup_bus, + .pcibios_fixup_phb = fsl_pcibios_fixup_phb, +#endif + .get_irq = mpic_get_irq, + .progress = udbg_progress, +}; +#endif /* CONFIG_MPC85xx_RDB */ -- GitLab From 8660484ed1cf3261e89e0bad94c6395597e87599 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 13 Apr 2023 22:28:39 -0700 Subject: [PATCH 3444/5631] module: add debugging auto-load duplicate module support The finit_module() system call can in the worst case use up to more than twice of a module's size in virtual memory. Duplicate finit_module() system calls are non fatal, however they unnecessarily strain virtual memory during bootup and in the worst case can cause a system to fail to boot. This is only known to currently be an issue on systems with larger number of CPUs. To help debug this situation we need to consider the different sources for finit_module(). Requests from the kernel that rely on module auto-loading, ie, the kernel's *request_module() API, are one source of calls. Although modprobe checks to see if a module is already loaded prior to calling finit_module() there is a small race possible allowing userspace to trigger multiple modprobe calls racing against modprobe and this not seeing the module yet loaded. This adds debugging support to the kernel module auto-loader (*request_module() calls) to easily detect duplicate module requests. To aid with possible bootup failure issues incurred by this, it will converge duplicates requests to a single request. This avoids any possible strain on virtual memory during bootup which could be incurred by duplicate module autoloading requests. Folks debugging virtual memory abuse on bootup can and should enable this to see what pr_warn()s come on, to see if module auto-loading is to blame for their wores. If they see duplicates they can further debug this by enabling the module.enable_dups_trace kernel parameter or by enabling CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS_TRACE. Current evidence seems to point to only a few duplicates for module auto-loading. And so the source for other duplicates creating heavy virtual memory pressure due to larger number of CPUs should becoming from another place (likely udev). Signed-off-by: Luis Chamberlain --- .../admin-guide/kernel-parameters.txt | 6 + kernel/module/Kconfig | 59 +++++ kernel/module/Makefile | 1 + kernel/module/dups.c | 246 ++++++++++++++++++ kernel/module/internal.h | 15 ++ kernel/module/kmod.c | 23 +- 6 files changed, 346 insertions(+), 4 deletions(-) create mode 100644 kernel/module/dups.c diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..5915a23207da 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3332,6 +3332,12 @@ specified, .async_probe takes precedence for the specific module. + module.enable_dups_trace + [KNL] When CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS is set, + this means that duplicate request_module() calls will + trigger a WARN_ON() instead of a pr_warn(). Note that + if MODULE_DEBUG_AUTOLOAD_DUPS_TRACE is set, WARN_ON()s + will always be issued and this option does nothing. module.sig_enforce [KNL] When CONFIG_MODULE_SIG is set, this means that modules without (valid) signatures will fail to load. diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index e6df183e2c80..33a2e991f608 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -59,6 +59,65 @@ config MODULE_STATS If unsure, say N. +config MODULE_DEBUG_AUTOLOAD_DUPS + bool "Debug duplicate modules with auto-loading" + help + Module autoloading allows in-kernel code to request modules through + the *request_module*() API calls. This in turn just calls userspace + modprobe. Although modprobe checks to see if a module is already + loaded before trying to load a module there is a small time window in + which multiple duplicate requests can end up in userspace and multiple + modprobe calls race calling finit_module() around the same time for + duplicate modules. The finit_module() system call can consume in the + worst case more than twice the respective module size in virtual + memory for each duplicate module requests. Although duplicate module + requests are non-fatal virtual memory is a limited resource and each + duplicate module request ends up just unnecessarily straining virtual + memory. + + This debugging facility will create pr_warn() splats for duplicate + module requests to help identify if module auto-loading may be the + culprit to your early boot virtual memory pressure. Since virtual + memory abuse caused by duplicate module requests could render a + system unusable this functionality will also converge races in + requests for the same module to a single request. You can boot with + the module.enable_dups_trace=1 kernel parameter to use WARN_ON() + instead of the pr_warn(). + + If the first module request used request_module_nowait() we cannot + use that as the anchor to wait for duplicate module requests, since + users of request_module() do want a proper return value. If a call + for the same module happened earlier with request_module() though, + then a duplicate request_module_nowait() would be detected. The + non-wait request_module() call is synchronous and waits until modprobe + completes. Subsequent auto-loading requests for the same module do + not trigger a new finit_module() calls and do not strain virtual + memory, and so as soon as modprobe successfully completes we remove + tracking for duplicates for that module. + + Enable this functionality to try to debug virtual memory abuse during + boot on systems which are failing to boot or if you suspect you may be + straining virtual memory during boot, and you want to identify if the + abuse was due to module auto-loading. These issues are currently only + known to occur on systems with many CPUs (over 400) and is likely the + result of udev issuing duplicate module requests for each CPU, and so + module auto-loading is not the culprit. There may very well still be + many duplicate module auto-loading requests which could be optimized + for and this debugging facility can be used to help identify them. + + Only enable this for debugging system functionality, never have it + enabled on real systems. + +config MODULE_DEBUG_AUTOLOAD_DUPS_TRACE + bool "Force full stack trace when duplicates are found" + depends on MODULE_DEBUG_AUTOLOAD_DUPS + help + Enabling this will force a full stack trace for duplicate module + auto-loading requests using WARN_ON() instead of pr_warn(). You + should keep this disabled at all times unless you are a developer + and are doing a manual inspection and want to debug exactly why + these duplicates occur. + endif # MODULE_DEBUG config MODULE_FORCE_LOAD diff --git a/kernel/module/Makefile b/kernel/module/Makefile index 52340bce497e..a10b2b9a6fdf 100644 --- a/kernel/module/Makefile +++ b/kernel/module/Makefile @@ -10,6 +10,7 @@ KCOV_INSTRUMENT_module.o := n obj-y += main.o obj-y += strict_rwx.o obj-y += kmod.o +obj-$(CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS) += dups.o obj-$(CONFIG_MODULE_DECOMPRESS) += decompress.o obj-$(CONFIG_MODULE_SIG) += signing.o obj-$(CONFIG_LIVEPATCH) += livepatch.o diff --git a/kernel/module/dups.c b/kernel/module/dups.c new file mode 100644 index 000000000000..aa8e1361fdb5 --- /dev/null +++ b/kernel/module/dups.c @@ -0,0 +1,246 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * kmod dups - the kernel module autoloader duplicate suppressor + * + * Copyright (C) 2023 Luis Chamberlain + */ + +#define pr_fmt(fmt) "module: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "module." +static bool enable_dups_trace = IS_ENABLED(CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS_TRACE); +module_param(enable_dups_trace, bool_enable_only, 0644); + +/* + * Protects dup_kmod_reqs list, adds / removals with RCU. + */ +static DEFINE_MUTEX(kmod_dup_mutex); +static LIST_HEAD(dup_kmod_reqs); + +struct kmod_dup_req { + struct list_head list; + char name[MODULE_NAME_LEN]; + struct completion first_req_done; + struct work_struct complete_work; + struct delayed_work delete_work; + int dup_ret; +}; + +static struct kmod_dup_req *kmod_dup_request_lookup(char *module_name) +{ + struct kmod_dup_req *kmod_req; + + list_for_each_entry_rcu(kmod_req, &dup_kmod_reqs, list, + lockdep_is_held(&kmod_dup_mutex)) { + if (strlen(kmod_req->name) == strlen(module_name) && + !memcmp(kmod_req->name, module_name, strlen(module_name))) { + return kmod_req; + } + } + + return NULL; +} + +static void kmod_dup_request_delete(struct work_struct *work) +{ + struct kmod_dup_req *kmod_req; + kmod_req = container_of(to_delayed_work(work), struct kmod_dup_req, delete_work); + + /* + * The typical situation is a module successully loaded. In that + * situation the module will be present already in userspace. If + * new requests come in after that, userspace will already know the + * module is loaded so will just return 0 right away. There is still + * a small chance right after we delete this entry new request_module() + * calls may happen after that, they can happen. These heuristics + * are to protect finit_module() abuse for auto-loading, if modules + * are still tryign to auto-load even if a module is already loaded, + * that's on them, and those inneficiencies should not be fixed by + * kmod. The inneficies there are a call to modprobe and modprobe + * just returning 0. + */ + mutex_lock(&kmod_dup_mutex); + list_del_rcu(&kmod_req->list); + synchronize_rcu(); + mutex_unlock(&kmod_dup_mutex); + kfree(kmod_req); +} + +static void kmod_dup_request_complete(struct work_struct *work) +{ + struct kmod_dup_req *kmod_req; + + kmod_req = container_of(work, struct kmod_dup_req, complete_work); + + /* + * This will ensure that the kernel will let all the waiters get + * informed its time to check the return value. It's time to + * go home. + */ + complete_all(&kmod_req->first_req_done); + + /* + * Now that we have allowed prior request_module() calls to go on + * with life, let's schedule deleting this entry. We don't have + * to do it right away, but we *eventually* want to do it so to not + * let this linger forever as this is just a boot optimization for + * possible abuses of vmalloc() incurred by finit_module() thrashing. + */ + queue_delayed_work(system_wq, &kmod_req->delete_work, 60 * HZ); +} + +bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret) +{ + struct kmod_dup_req *kmod_req, *new_kmod_req; + int ret; + + /* + * Pre-allocate the entry in case we have to use it later + * to avoid contention with the mutex. + */ + new_kmod_req = kzalloc(sizeof(*new_kmod_req), GFP_KERNEL); + if (!new_kmod_req) + return false; + + memcpy(new_kmod_req->name, module_name, strlen(module_name)); + INIT_WORK(&new_kmod_req->complete_work, kmod_dup_request_complete); + INIT_DELAYED_WORK(&new_kmod_req->delete_work, kmod_dup_request_delete); + init_completion(&new_kmod_req->first_req_done); + + mutex_lock(&kmod_dup_mutex); + + kmod_req = kmod_dup_request_lookup(module_name); + if (!kmod_req) { + /* + * If the first request that came through for a module + * was with request_module_nowait() we cannot wait for it + * and share its return value with other users which may + * have used request_module() and need a proper return value + * so just skip using them as an anchor. + * + * If a prior request to this one came through with + * request_module() though, then a request_module_nowait() + * would benefit from duplicate detection. + */ + if (!wait) { + kfree(new_kmod_req); + pr_debug("New request_module_nowait() for %s -- cannot track duplicates for this request\n", module_name); + mutex_unlock(&kmod_dup_mutex); + return false; + } + + /* + * There was no duplicate, just add the request so we can + * keep tab on duplicates later. + */ + pr_debug("New request_module() for %s\n", module_name); + list_add_rcu(&new_kmod_req->list, &dup_kmod_reqs); + mutex_unlock(&kmod_dup_mutex); + return false; + } + mutex_unlock(&kmod_dup_mutex); + + /* We are dealing with a duplicate request now */ + kfree(new_kmod_req); + + /* + * To fix these try to use try_then_request_module() instead as that + * will check if the component you are looking for is present or not. + * You could also just queue a single request to load the module once, + * instead of having each and everything you need try to request for + * the module. + * + * Duplicate request_module() calls can cause quite a bit of wasted + * vmalloc() space when racing with userspace. + */ + if (enable_dups_trace) + WARN(1, "module-autoload: duplicate request for module %s\n", module_name); + else + pr_warn("module-autoload: duplicate request for module %s\n", module_name); + + if (!wait) { + /* + * If request_module_nowait() was used then the user just + * wanted to issue the request and if another module request + * was already its way with the same name we don't care for + * the return value either. Let duplicate request_module_nowait() + * calls bail out right away. + */ + *dup_ret = 0; + return true; + } + + /* + * If a duplicate request_module() was used they *may* care for + * the return value, so we have no other option but to wait for + * the first caller to complete. If the first caller used + * the request_module_nowait() call, subsquent callers will + * deal with the comprmise of getting a successful call with this + * optimization enabled ... + */ + ret = wait_for_completion_state(&kmod_req->first_req_done, + TASK_UNINTERRUPTIBLE | TASK_KILLABLE); + if (ret) { + *dup_ret = ret; + return true; + } + + /* Now the duplicate request has the same exact return value as the first request */ + *dup_ret = kmod_req->dup_ret; + + return true; +} + +void kmod_dup_request_announce(char *module_name, int ret) +{ + struct kmod_dup_req *kmod_req; + + mutex_lock(&kmod_dup_mutex); + + kmod_req = kmod_dup_request_lookup(module_name); + if (!kmod_req) + goto out; + + kmod_req->dup_ret = ret; + + /* + * If we complete() here we may allow duplicate threads + * to continue before the first one that submitted the + * request. We're in no rush also, given that each and + * every bounce back to userspace is slow we avoid that + * with a slight delay here. So queueue up the completion + * and let duplicates suffer, just wait a tad bit longer. + * There is no rush. But we also don't want to hold the + * caller up forever or introduce any boot delays. + */ + queue_work(system_wq, &kmod_req->complete_work); + +out: + mutex_unlock(&kmod_dup_mutex); +} diff --git a/kernel/module/internal.h b/kernel/module/internal.h index 1fd75dd346dc..d67682489d14 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -3,6 +3,7 @@ * * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) + * Copyright (C) 2023 Luis Chamberlain */ #include @@ -221,6 +222,20 @@ static inline void mod_stat_bump_becoming(struct load_info *info, int flags) #endif /* CONFIG_MODULE_STATS */ +#ifdef CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS +bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret); +void kmod_dup_request_announce(char *module_name, int ret); +#else +static inline bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret) +{ + return false; +} + +static inline void kmod_dup_request_announce(char *module_name, int ret) +{ +} +#endif + #ifdef CONFIG_MODULE_UNLOAD_TAINT_TRACKING struct mod_unload_taint { struct list_head list; diff --git a/kernel/module/kmod.c b/kernel/module/kmod.c index 5899083436a3..0800d9891692 100644 --- a/kernel/module/kmod.c +++ b/kernel/module/kmod.c @@ -1,6 +1,9 @@ /* * kmod - the kernel module loader + * + * Copyright (C) 2023 Luis Chamberlain */ + #include #include #include @@ -27,6 +30,7 @@ #include #include +#include "internal.h" /* * Assuming: @@ -65,7 +69,7 @@ static void free_modprobe_argv(struct subprocess_info *info) kfree(info->argv); } -static int call_modprobe(char *module_name, int wait) +static int call_modprobe(char *orig_module_name, int wait) { struct subprocess_info *info; static char *envp[] = { @@ -74,12 +78,14 @@ static int call_modprobe(char *module_name, int wait) "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; + char *module_name; + int ret; char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); if (!argv) goto out; - module_name = kstrdup(module_name, GFP_KERNEL); + module_name = kstrdup(orig_module_name, GFP_KERNEL); if (!module_name) goto free_argv; @@ -94,13 +100,16 @@ static int call_modprobe(char *module_name, int wait) if (!info) goto free_module_name; - return call_usermodehelper_exec(info, wait | UMH_KILLABLE); + ret = call_usermodehelper_exec(info, wait | UMH_KILLABLE); + kmod_dup_request_announce(orig_module_name, ret); + return ret; free_module_name: kfree(module_name); free_argv: kfree(argv); out: + kmod_dup_request_announce(orig_module_name, -ENOMEM); return -ENOMEM; } @@ -124,7 +133,7 @@ int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; - int ret; + int ret, dup_ret; /* * We don't allow synchronous module loading from async. Module @@ -156,8 +165,14 @@ int __request_module(bool wait, const char *fmt, ...) trace_module_request(module_name, wait, _RET_IP_); + if (kmod_dup_request_exists_wait(module_name, wait, &dup_ret)) { + ret = dup_ret; + goto out; + } + ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); +out: up(&kmod_concurrent_max); return ret; -- GitLab From 92189c902c2e2f8c0d4238310686e93da99156b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:18 +0200 Subject: [PATCH 3445/5631] powerpc/85xx: mpc85xx_ds: Move i8259 code into own file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to share mpc85xx i8259 code between DS and P2020. Prefix i8259 debug and error messages by i8259 word. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy [mpe: Fix some coding style warnings in the moved code] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-10-pali@kernel.org --- arch/powerpc/platforms/85xx/Makefile | 3 +- arch/powerpc/platforms/85xx/mpc85xx.h | 6 ++ arch/powerpc/platforms/85xx/mpc85xx_8259.c | 64 ++++++++++++++++++++++ arch/powerpc/platforms/85xx/mpc85xx_ds.c | 46 ---------------- 4 files changed, 72 insertions(+), 47 deletions(-) create mode 100644 arch/powerpc/platforms/85xx/mpc85xx_8259.c diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 93451850ed83..0a0011e8c63c 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -16,7 +16,8 @@ obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o obj-$(CONFIG_MPC8536_DS) += mpc8536_ds.o -obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o p2020.o +obj8259-$(CONFIG_PPC_I8259) += mpc85xx_8259.o +obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o p2020.o $(obj8259-y) obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o p2020.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index 8f7b37c1de87..e792907ee3d5 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -15,6 +15,12 @@ extern void mpc85xx_qe_par_io_init(void); static inline void __init mpc85xx_qe_par_io_init(void) {} #endif +#ifdef CONFIG_PPC_I8259 +void __init mpc85xx_8259_init(void); +#else +static inline void __init mpc85xx_8259_init(void) {} +#endif + void __init mpc85xx_ds_pic_init(void); void __init mpc85xx_ds_setup_arch(void); void __init mpc85xx_rdb_setup_arch(void); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_8259.c b/arch/powerpc/platforms/85xx/mpc85xx_8259.c new file mode 100644 index 000000000000..cb00d596ad80 --- /dev/null +++ b/arch/powerpc/platforms/85xx/mpc85xx_8259.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * MPC85xx 8259 functions for DS Board Setup + * + * Author Xianghua Xiao (x.xiao@freescale.com) + * Roy Zang + * - Add PCI/PCI Express support + * Copyright 2007 Freescale Semiconductor Inc. + */ + +#include +#include +#include +#include +#include + +#include +#include + +#include "mpc85xx.h" + +static void mpc85xx_8259_cascade(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int cascade_irq = i8259_irq(); + + if (cascade_irq) + generic_handle_irq(cascade_irq); + + chip->irq_eoi(&desc->irq_data); +} + +void __init mpc85xx_8259_init(void) +{ + struct device_node *np; + struct device_node *cascade_node = NULL; + int cascade_irq; + + /* Initialize the i8259 controller */ + for_each_node_by_type(np, "interrupt-controller") { + if (of_device_is_compatible(np, "chrp,iic")) { + cascade_node = np; + break; + } + } + + if (cascade_node == NULL) { + pr_debug("i8259: Could not find i8259 PIC\n"); + return; + } + + cascade_irq = irq_of_parse_and_map(cascade_node, 0); + if (!cascade_irq) { + pr_err("i8259: Failed to map cascade interrupt\n"); + return; + } + + pr_debug("i8259: cascade mapped to irq %d\n", cascade_irq); + + i8259_init(cascade_node, 0); + of_node_put(cascade_node); + + irq_set_chained_handler(cascade_irq, mpc85xx_8259_cascade); +} diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index af2cafec4f0a..db4cf76c0fd1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -34,52 +34,6 @@ #include "mpc85xx.h" -static void mpc85xx_8259_cascade(struct irq_desc *desc) -{ - struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int cascade_irq = i8259_irq(); - - if (cascade_irq) { - generic_handle_irq(cascade_irq); - } - chip->irq_eoi(&desc->irq_data); -} - -static void __init mpc85xx_8259_init(void) -{ - struct device_node *np; - struct device_node *cascade_node = NULL; - int cascade_irq; - - if (!IS_ENABLED(CONFIG_PPC_I8259)) - return; - - /* Initialize the i8259 controller */ - for_each_node_by_type(np, "interrupt-controller") - if (of_device_is_compatible(np, "chrp,iic")) { - cascade_node = np; - break; - } - - if (cascade_node == NULL) { - pr_debug("Could not find i8259 PIC\n"); - return; - } - - cascade_irq = irq_of_parse_and_map(cascade_node, 0); - if (!cascade_irq) { - pr_err("Failed to map cascade interrupt\n"); - return; - } - - pr_debug("mpc85xxds: cascade mapped to irq %d\n", cascade_irq); - - i8259_init(cascade_node, 0); - of_node_put(cascade_node); - - irq_set_chained_handler(cascade_irq, mpc85xx_8259_cascade); -} - void __init mpc85xx_ds_pic_init(void) { struct mpic *mpic; -- GitLab From 7d8ae6e081428699999c9d128c4e9d3927c1da03 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:19 +0200 Subject: [PATCH 3446/5631] powerpc/85xx: p2020: Unify .setup_arch and .init_IRQ callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make just one .setup_arch and one .init_IRQ callback implementation for all P2020 board code. This deduplicate repeated and same code. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-11-pali@kernel.org --- arch/powerpc/platforms/85xx/mpc85xx.h | 5 --- arch/powerpc/platforms/85xx/mpc85xx_ds.c | 4 +-- arch/powerpc/platforms/85xx/mpc85xx_rdb.c | 4 +-- arch/powerpc/platforms/85xx/p2020.c | 38 +++++++++++++++++++---- 4 files changed, 36 insertions(+), 15 deletions(-) diff --git a/arch/powerpc/platforms/85xx/mpc85xx.h b/arch/powerpc/platforms/85xx/mpc85xx.h index e792907ee3d5..c764d7551ef1 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx.h +++ b/arch/powerpc/platforms/85xx/mpc85xx.h @@ -21,9 +21,4 @@ void __init mpc85xx_8259_init(void); static inline void __init mpc85xx_8259_init(void) {} #endif -void __init mpc85xx_ds_pic_init(void); -void __init mpc85xx_ds_setup_arch(void); -void __init mpc85xx_rdb_setup_arch(void); -void __init mpc85xx_rdb_pic_init(void); - #endif diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index db4cf76c0fd1..4347d629b567 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -34,7 +34,7 @@ #include "mpc85xx.h" -void __init mpc85xx_ds_pic_init(void) +static void __init mpc85xx_ds_pic_init(void) { struct mpic *mpic; int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; @@ -55,7 +55,7 @@ void __init mpc85xx_ds_pic_init(void) /* * Setup the architecture */ -void __init mpc85xx_ds_setup_arch(void) +static void __init mpc85xx_ds_setup_arch(void) { if (ppc_md.progress) ppc_md.progress("mpc85xx_ds_setup_arch()", 0); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c index dbedffc57ce8..c42a68da6dfd 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c @@ -29,7 +29,7 @@ #include "mpc85xx.h" -void __init mpc85xx_rdb_pic_init(void) +static void __init mpc85xx_rdb_pic_init(void) { struct mpic *mpic; int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; @@ -48,7 +48,7 @@ void __init mpc85xx_rdb_pic_init(void) /* * Setup the architecture */ -void __init mpc85xx_rdb_setup_arch(void) +static void __init mpc85xx_rdb_setup_arch(void) { if (ppc_md.progress) ppc_md.progress("mpc85xx_rdb_setup_arch()", 0); diff --git a/arch/powerpc/platforms/85xx/p2020.c b/arch/powerpc/platforms/85xx/p2020.c index 41bba8c0e335..0e7be454b2de 100644 --- a/arch/powerpc/platforms/85xx/p2020.c +++ b/arch/powerpc/platforms/85xx/p2020.c @@ -21,6 +21,32 @@ #include "smp.h" #include "mpc85xx.h" +static void __init p2020_pic_init(void) +{ + struct mpic *mpic; + int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU; + + mpic = mpic_alloc(NULL, 0, flags, 0, 256, " OpenPIC "); + + if (WARN_ON(!mpic)) + return; + + mpic_init(mpic); + mpc85xx_8259_init(); +} + +/* + * Setup the architecture + */ +static void __init p2020_setup_arch(void) +{ + swiotlb_detect_4g(); + fsl_pci_assign_primary(); + uli_init(); + mpc85xx_smp_init(); + mpc85xx_qe_par_io_init(); +} + #ifdef CONFIG_MPC85xx_DS machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); #endif /* CONFIG_MPC85xx_DS */ @@ -34,8 +60,8 @@ machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices); define_machine(p2020_ds) { .name = "P2020 DS", .compatible = "fsl,P2020DS", - .setup_arch = mpc85xx_ds_setup_arch, - .init_IRQ = mpc85xx_ds_pic_init, + .setup_arch = p2020_setup_arch, + .init_IRQ = p2020_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, .pcibios_fixup_phb = fsl_pcibios_fixup_phb, @@ -49,8 +75,8 @@ define_machine(p2020_ds) { define_machine(p2020_rdb) { .name = "P2020 RDB", .compatible = "fsl,P2020RDB", - .setup_arch = mpc85xx_rdb_setup_arch, - .init_IRQ = mpc85xx_rdb_pic_init, + .setup_arch = p2020_setup_arch, + .init_IRQ = p2020_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, .pcibios_fixup_phb = fsl_pcibios_fixup_phb, @@ -62,8 +88,8 @@ define_machine(p2020_rdb) { define_machine(p2020_rdb_pc) { .name = "P2020RDB-PC", .compatible = "fsl,P2020RDB-PC", - .setup_arch = mpc85xx_rdb_setup_arch, - .init_IRQ = mpc85xx_rdb_pic_init, + .setup_arch = p2020_setup_arch, + .init_IRQ = p2020_pic_init, #ifdef CONFIG_PCI .pcibios_fixup_bus = fsl_pcibios_fixup_bus, .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -- GitLab From 1a170efec56ba4707cd33e711dbafb60b7f94626 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:20 +0200 Subject: [PATCH 3447/5631] powerpc/85xx: p2020: Define just one machine description MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Combine machine descriptions and code of all P2020 boards into just one generic unified P2020 machine description. This allows kernel to boot on any P2020-based board with P2020 DTS file without need to patch kernel and define a new machine description in 85xx powerpc platform directory. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-12-pali@kernel.org --- arch/powerpc/platforms/85xx/p2020.c | 57 ++++++++++------------------- 1 file changed, 19 insertions(+), 38 deletions(-) diff --git a/arch/powerpc/platforms/85xx/p2020.c b/arch/powerpc/platforms/85xx/p2020.c index 0e7be454b2de..0e4d715145af 100644 --- a/arch/powerpc/platforms/85xx/p2020.c +++ b/arch/powerpc/platforms/85xx/p2020.c @@ -47,47 +47,29 @@ static void __init p2020_setup_arch(void) mpc85xx_qe_par_io_init(); } -#ifdef CONFIG_MPC85xx_DS -machine_arch_initcall(p2020_ds, mpc85xx_common_publish_devices); -#endif /* CONFIG_MPC85xx_DS */ +/* + * Called very early, device-tree isn't unflattened + */ +static int __init p2020_probe(void) +{ + struct device_node *p2020_cpu; -#ifdef CONFIG_MPC85xx_RDB -machine_arch_initcall(p2020_rdb, mpc85xx_common_publish_devices); -machine_arch_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices); -#endif /* CONFIG_MPC85xx_RDB */ + /* + * There is no common compatible string for all P2020 boards. + * The only common thing is "PowerPC,P2020@0" cpu node. + * So check for P2020 board via this cpu node. + */ + p2020_cpu = of_find_node_by_path("/cpus/PowerPC,P2020@0"); + of_node_put(p2020_cpu); -#ifdef CONFIG_MPC85xx_DS -define_machine(p2020_ds) { - .name = "P2020 DS", - .compatible = "fsl,P2020DS", - .setup_arch = p2020_setup_arch, - .init_IRQ = p2020_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif - .get_irq = mpic_get_irq, - .progress = udbg_progress, -}; -#endif /* CONFIG_MPC85xx_DS */ + return !!p2020_cpu; +} -#ifdef CONFIG_MPC85xx_RDB -define_machine(p2020_rdb) { - .name = "P2020 RDB", - .compatible = "fsl,P2020RDB", - .setup_arch = p2020_setup_arch, - .init_IRQ = p2020_pic_init, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, - .pcibios_fixup_phb = fsl_pcibios_fixup_phb, -#endif - .get_irq = mpic_get_irq, - .progress = udbg_progress, -}; +machine_arch_initcall(p2020, mpc85xx_common_publish_devices); -define_machine(p2020_rdb_pc) { - .name = "P2020RDB-PC", - .compatible = "fsl,P2020RDB-PC", +define_machine(p2020) { + .name = "Freescale P2020", + .probe = p2020_probe, .setup_arch = p2020_setup_arch, .init_IRQ = p2020_pic_init, #ifdef CONFIG_PCI @@ -97,4 +79,3 @@ define_machine(p2020_rdb_pc) { .get_irq = mpic_get_irq, .progress = udbg_progress, }; -#endif /* CONFIG_MPC85xx_RDB */ -- GitLab From b5340a094b5c753ee3490716bcd86546dfd3e078 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:21 +0200 Subject: [PATCH 3448/5631] powerpc/85xx: p2020: Enable boards by new config option CONFIG_PPC_P2020 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Generic unified P2020 machine description which supports all P2020-based boards is now in separate file p2020.c. So create a separate config option CONFIG_PPC_P2020 for it. Previously machine descriptions for P2020 boards were enabled by CONFIG_MPC85xx_DS or CONFIG_MPC85xx_RDB option. So set CONFIG_PPC_P2020 to be enabled by default when one of those option is enabled. This allows to compile support for P2020 boards without need to have enabled support for older mpc85xx boards. And to compile kernel for old mpc85xx boards without having enabled support for new P2020 boards. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-13-pali@kernel.org --- arch/powerpc/platforms/85xx/Kconfig | 22 ++++++++++++++++++---- arch/powerpc/platforms/85xx/Makefile | 5 +++-- 2 files changed, 21 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index a8ce6616fd0a..9315a3b69d6d 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -78,23 +78,37 @@ config MPC8536_DS This option enables support for the MPC8536 DS board config MPC85xx_DS - bool "Freescale MPC8544 DS / MPC8572 DS / P2020 DS" + bool "Freescale MPC8544 DS / MPC8572 DS" select PPC_I8259 select DEFAULT_UIMAGE select FSL_ULI1575 if PCI select SWIOTLB help - This option enables support for the MPC8544 DS, MPC8572 DS and P2020 DS boards + This option enables support for the MPC8544 DS and MPC8572 DS boards config MPC85xx_RDB - bool "Freescale P102x MBG/UTM/RDB and P2020 RDB" + bool "Freescale P102x MBG/UTM/RDB" select PPC_I8259 select DEFAULT_UIMAGE select SWIOTLB help This option enables support for the P1020 MBG PC, P1020 UTM PC, P1020 RDB PC, P1020 RDB PD, P1020 RDB, P1021 RDB PC, P1024 RDB, - P1025 RDB, P2020 RDB and P2020 RDB PC boards + and P1025 RDB boards + +config PPC_P2020 + bool "Freescale P2020" + default y if MPC85xx_DS || MPC85xx_RDB + select DEFAULT_UIMAGE + select SWIOTLB + imply PPC_I8259 + imply FSL_ULI1575 if PCI + help + This option enables generic unified support for any board with the + Freescale P2020 processor. + + For example: P2020 DS board, P2020 RDB board, P2020 RDB PC board or + CZ.NIC Turris 1.x boards. config P1010_RDB bool "Freescale P1010 RDB" diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile index 0a0011e8c63c..e3d977624e33 100644 --- a/arch/powerpc/platforms/85xx/Makefile +++ b/arch/powerpc/platforms/85xx/Makefile @@ -17,13 +17,14 @@ obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o obj-$(CONFIG_MPC8536_DS) += mpc8536_ds.o obj8259-$(CONFIG_PPC_I8259) += mpc85xx_8259.o -obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o p2020.o $(obj8259-y) +obj-$(CONFIG_MPC85xx_DS) += mpc85xx_ds.o $(obj8259-y) obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o -obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o p2020.o +obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o obj-$(CONFIG_P1010_RDB) += p1010rdb.o obj-$(CONFIG_P1022_DS) += p1022_ds.o obj-$(CONFIG_P1022_RDK) += p1022_rdk.o obj-$(CONFIG_P1023_RDB) += p1023_rdb.o +obj-$(CONFIG_PPC_P2020) += p2020.o $(obj8259-y) obj-$(CONFIG_TWR_P102x) += twr_p102x.o obj-$(CONFIG_CORENET_GENERIC) += corenet_generic.o obj-$(CONFIG_FB_FSL_DIU) += t1042rdb_diu.o -- GitLab From 40f7b523e31fd68163d9dfe639f2f34b6a726ecd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pali=20Roh=C3=A1r?= Date: Sat, 8 Apr 2023 16:01:22 +0200 Subject: [PATCH 3449/5631] powerpc: dts: turris1x.dts: Remove "fsl,P2020RDB-PC" compatible string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "fsl,P2020RDB-PC" compatible string was present in Turris 1.x DTS file just because Linux kernel required it for proper detection of P2020 processor during boot. This was quite a hack as CZ.NIC Turris 1.x is not compatible with Freescale P2020-RDB-PC board. Now when kernel has generic unified support for boards with P2020 processors, there is no need to have this "hack" in turris1x.dts file. So remove incorrect "fsl,P2020RDB-PC" compatible string from turris1x.dts. Signed-off-by: Pali Rohár Signed-off-by: Christophe Leroy Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408140122.25293-14-pali@kernel.org --- arch/powerpc/boot/dts/turris1x.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/boot/dts/turris1x.dts b/arch/powerpc/boot/dts/turris1x.dts index c9b619f6ed5c..6612160c19d5 100644 --- a/arch/powerpc/boot/dts/turris1x.dts +++ b/arch/powerpc/boot/dts/turris1x.dts @@ -15,7 +15,7 @@ / { model = "Turris 1.x"; - compatible = "cznic,turris1x", "fsl,P2020RDB-PC"; /* fsl,P2020RDB-PC is required for booting Linux */ + compatible = "cznic,turris1x"; aliases { ethernet0 = &enet0; -- GitLab From 4f18b9e6ca58440394e86a53bf1be0d8a1920bcd Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:47 +1000 Subject: [PATCH 3450/5631] powerpc/64: Move initial base and TOC pointer calculation A later change moves the non-prom case to run at the virtual address earlier, which calls for virtual TOC and kernel base. Split these two calculations for prom and non-prom to make that change simpler. Signed-off-by: Nicholas Piggin [mpe: Retain relative_toc call for start_initialization_book3e] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-2-npiggin@gmail.com --- arch/powerpc/kernel/head_64.S | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 1febb56ebaeb..00ac5920e84b 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -515,15 +515,6 @@ __start_initialization_multiplatform: /* Zero r13 (paca) so early program check / mce don't use it */ li r13,0 - /* Get TOC pointer (current runtime address) */ - bl relative_toc - - /* find out where we are now */ - bcl 20,31,$+4 -0: mflr r26 /* r26 = runtime addr here */ - addis r26,r26,(_stext - 0b)@ha - addi r26,r26,(_stext - 0b)@l /* current runtime base addr */ - /* * Are we booted from a PROM Of-type client-interface ? */ @@ -540,16 +531,38 @@ __start_initialization_multiplatform: mr r29,r9 #endif + /* Get TOC pointer (current runtime address) */ + bl relative_toc + #ifdef CONFIG_PPC_BOOK3E_64 bl start_initialization_book3e #else bl start_initialization_book3s #endif /* CONFIG_PPC_BOOK3E_64 */ + + /* Get TOC pointer */ + bl relative_toc + + /* find out where we are now */ + bcl 20,31,$+4 +0: mflr r26 /* r26 = runtime addr here */ + addis r26,r26,(_stext - 0b)@ha + addi r26,r26,(_stext - 0b)@l /* current runtime base addr */ + b __after_prom_start __REF __boot_from_prom: #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE + /* Get TOC pointer */ + bl relative_toc + + /* find out where we are now */ + bcl 20,31,$+4 +0: mflr r26 /* r26 = runtime addr here */ + addis r26,r26,(_stext - 0b)@ha + addi r26,r26,(_stext - 0b)@l /* current runtime base addr */ + /* Save parameters */ mr r31,r3 mr r30,r4 -- GitLab From b270bebd34e36fb69363d65e24b00a9d148903e8 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:48 +1000 Subject: [PATCH 3451/5631] powerpc/64s: Run at the kernel virtual address earlier in boot This mostly consolidates the Book3E and Book3S behaviour in boot WRT executing from the physical or virtual address. Book3E sets up kernel virtual linear map in start_initialization_book3e and runs from the virtual linear alias after that. This change makes Book3S begin to execute from the virtual alias at the same point. Book3S can not use its MMU for that at this point, but when the MMU is disabled, the virtual linear address correctly aliases to physical memory because the top bits of the address are ignored with MMU disabled. Secondaries execute from the virtual address similarly early. This reduces the differences between subarchs, but the main motivation was to enable the PC-relative addressing ABI for Book3S, where pointer calculations must execute from the virtual address or the top bits of the pointer will be lost. This is similar to the requirement the TOC relative addressing already has that the TOC pointer use its virtual address. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-3-npiggin@gmail.com --- arch/powerpc/kernel/head_64.S | 82 +++++++++++++++++++---------------- 1 file changed, 44 insertions(+), 38 deletions(-) diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 00ac5920e84b..bac1dfe52ae5 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -76,6 +76,13 @@ * 2. The kernel is entered at __start */ +/* + * boot_from_prom and prom_init run at the physical address. Everything + * after prom and kexec entry run at the virtual address (PAGE_OFFSET). + * Secondaries run at the virtual address from generic_secondary_common_init + * onward. + */ + OPEN_FIXED_SECTION(first_256B, 0x0, 0x100) USE_FIXED_SECTION(first_256B) /* @@ -303,13 +310,11 @@ _GLOBAL(fsl_secondary_thread_init) /* turn on 64-bit mode */ bl enable_64b_mode - /* get a valid TOC pointer, wherever we're mapped at */ - bl relative_toc - tovirt(r2,r2) - /* Book3E initialization */ mr r3,r24 bl book3e_secondary_thread_init + bl relative_toc + b generic_secondary_common_init #endif /* CONFIG_PPC_BOOK3E_64 */ @@ -331,16 +336,12 @@ _GLOBAL(generic_secondary_smp_init) /* turn on 64-bit mode */ bl enable_64b_mode - /* get a valid TOC pointer, wherever we're mapped at */ - bl relative_toc - tovirt(r2,r2) - #ifdef CONFIG_PPC_BOOK3E_64 /* Book3E initialization */ mr r3,r24 mr r4,r25 bl book3e_secondary_core_init - + /* Now NIA and r2 are relocated to PAGE_OFFSET if not already */ /* * After common core init has finished, check if the current thread is the * one we wanted to boot. If not, start the specified thread and stop the @@ -378,6 +379,16 @@ _GLOBAL(generic_secondary_smp_init) 10: b 10b 20: +#else + /* Now the MMU is off, can branch to our PAGE_OFFSET address */ + bcl 20,31,$+4 +1: mflr r11 + addi r11,r11,(2f - 1b) + tovirt(r11, r11) + mtctr r11 + bctr +2: + bl relative_toc #endif generic_secondary_common_init: @@ -492,6 +503,8 @@ SYM_FUNC_START_LOCAL(start_initialization_book3s) /* Switch off MMU if not already off */ bl __mmu_off + /* Now the MMU is off, can return to our PAGE_OFFSET address */ + tovirt(r25,r25) mtlr r25 blr SYM_FUNC_END(start_initialization_book3s) @@ -534,16 +547,19 @@ __start_initialization_multiplatform: /* Get TOC pointer (current runtime address) */ bl relative_toc + /* These functions return to the virtual (PAGE_OFFSET) address */ #ifdef CONFIG_PPC_BOOK3E_64 bl start_initialization_book3e #else bl start_initialization_book3s #endif /* CONFIG_PPC_BOOK3E_64 */ - /* Get TOC pointer */ + /* Get TOC pointer, virtual */ bl relative_toc /* find out where we are now */ + + /* OPAL doesn't pass base address in r4, have to derive it. */ bcl 20,31,$+4 0: mflr r26 /* r26 = runtime addr here */ addis r26,r26,(_stext - 0b)@ha @@ -554,7 +570,7 @@ __start_initialization_multiplatform: __REF __boot_from_prom: #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE - /* Get TOC pointer */ + /* Get TOC pointer, non-virtual */ bl relative_toc /* find out where we are now */ @@ -603,18 +619,11 @@ __boot_from_prom: __after_prom_start: #ifdef CONFIG_RELOCATABLE /* process relocations for the final address of the kernel */ - lis r25,PAGE_OFFSET@highest /* compute virtual base of kernel */ - sldi r25,r25,32 -#if defined(CONFIG_PPC_BOOK3E_64) - tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ -#endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) -#if defined(CONFIG_PPC_BOOK3E_64) - tophys(r26,r26) -#endif cmplwi cr0,r7,1 /* flagged to stay where we are ? */ - bne 1f - add r25,r25,r26 + mr r25,r26 /* then use current kernel base */ + beq 1f + LOAD_REG_IMMEDIATE(r25, PAGE_OFFSET) /* else use static kernel base */ 1: mr r3,r25 bl relocate #if defined(CONFIG_PPC_BOOK3E_64) @@ -630,14 +639,8 @@ __after_prom_start: * * Note: This process overwrites the OF exception vectors. */ - li r3,0 /* target addr */ -#ifdef CONFIG_PPC_BOOK3E_64 - tovirt(r3,r3) /* on booke, we already run at PAGE_OFFSET */ -#endif + LOAD_REG_IMMEDIATE(r3, PAGE_OFFSET) mr. r4,r26 /* In some cases the loader may */ -#if defined(CONFIG_PPC_BOOK3E_64) - tovirt(r4,r4) -#endif beq 9f /* have already put us at zero */ li r6,0x100 /* Start offset, the first 0x100 */ /* bytes were copied earlier. */ @@ -648,9 +651,6 @@ __after_prom_start: * variable __run_at_load, if it is set the kernel is treated as relocatable * kernel, otherwise it will be moved to PHYSICAL_START */ -#if defined(CONFIG_PPC_BOOK3E_64) - tovirt(r26,r26) /* on booke, we already run at PAGE_OFFSET */ -#endif lwz r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26) cmplwi cr0,r7,1 bne 3f @@ -769,9 +769,15 @@ _GLOBAL(pmac_secondary_start) sync slbia - /* get TOC pointer (real address) */ + /* Branch to our PAGE_OFFSET address */ + bcl 20,31,$+4 +1: mflr r11 + addi r11,r11,(2f - 1b) + tovirt(r11, r11) + mtctr r11 + bctr +2: bl relative_toc - tovirt(r2,r2) /* Copy some CPU settings from CPU 0 */ bl __restore_cpu_ppc970 @@ -910,8 +916,9 @@ SYM_FUNC_END(enable_64b_mode) * TOC in -mcmodel=medium mode. After we relocate to 0 but before * the MMU is on we need our TOC to be a virtual address otherwise * these pointers will be real addresses which may get stored and - * accessed later with the MMU on. We use tovirt() at the call - * sites to handle this. + * accessed later with the MMU on. We branch to the virtual address + * while still in real mode then call relative_toc again to handle + * this. */ _GLOBAL(relative_toc) mflr r0 @@ -930,9 +937,8 @@ p_toc: .8byte .TOC. - 0b */ __REF start_here_multiplatform: - /* set up the TOC */ - bl relative_toc - tovirt(r2,r2) + /* Adjust TOC for moved kernel. Could adjust when moving it instead. */ + bl relative_toc /* Clear out the BSS. It may have been done in prom_init, * already but that's irrelevant since prom_init will soon -- GitLab From dc5dac748af9087e9240bd2ae6ae7db48d5360ae Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:49 +1000 Subject: [PATCH 3452/5631] powerpc/64: Add support to build with prefixed instructions Add an option to build kernel and module with prefixed instructions if the CPU and toolchain support it. This is not related to kernel support for userspace execution of prefixed instructions. Building with prefixed instructions breaks some extended inline asm memory addressing, for example it will provide immediates that exceed the range of simple load/store displacement. Whether this is a toolchain or a kernel asm problem remains to be seen. For now, these are replaced with simpler and less efficient direct register addressing when compiling with prefixed. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-4-npiggin@gmail.com --- arch/powerpc/Kconfig | 3 +++ arch/powerpc/Makefile | 4 +++ arch/powerpc/include/asm/atomic.h | 24 ++++++++++++++--- arch/powerpc/include/asm/io.h | 37 ++++++++++++++++++++++++++ arch/powerpc/include/asm/uaccess.h | 28 +++++++++++++++++-- arch/powerpc/kernel/trace/ftrace.c | 2 ++ arch/powerpc/platforms/Kconfig.cputype | 20 ++++++++++++++ 7 files changed, 112 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3fb2c2766139..109c00bd91db 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -4,6 +4,9 @@ source "arch/powerpc/platforms/Kconfig.cputype" config CC_HAS_ELFV2 def_bool PPC64 && $(cc-option, -mabi=elfv2) +config CC_HAS_PREFIXED + def_bool PPC64 && $(cc-option, -mcpu=power10 -mprefixed) + config 32BIT bool default y if PPC32 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 4343cca57cb3..9fb770d3b409 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -180,7 +180,11 @@ ifdef CONFIG_476FPE_ERR46 endif # No prefix or pcrel +ifdef CONFIG_PPC_KERNEL_PREFIXED +KBUILD_CFLAGS += $(call cc-option,-mprefixed) +else KBUILD_CFLAGS += $(call cc-option,-mno-prefixed) +endif KBUILD_CFLAGS += $(call cc-option,-mno-pcrel) # No AltiVec or VSX or MMA instructions when building kernel diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index b3a53830446b..47228b177478 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -27,14 +27,22 @@ static __inline__ int arch_atomic_read(const atomic_t *v) { int t; - __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("lwz %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } static __inline__ void arch_atomic_set(atomic_t *v, int i) { - __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("stw %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC_OP(op, asm_op, suffix, sign, ...) \ @@ -197,14 +205,22 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v) { s64 t; - __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) { - __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC64_OP(op, asm_op) \ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index fc112a91d0c2..f1e657c9bbe8 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -97,6 +97,42 @@ extern bool isa_io_special; * */ +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define DEF_MMIO_IN_X(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync" \ + : "=r" (ret) : "r" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_X(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0,%0" \ + : : "r" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} + +#define DEF_MMIO_IN_D(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0(%1);twi 0,%0,0;isync"\ + : "=r" (ret) : "b" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_D(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0(%0)" \ + : : "b" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} +#else #define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ @@ -130,6 +166,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ : "=m<>" (*addr) : "r" (val) : "memory"); \ mmiowb_set_pending(); \ } +#endif DEF_MMIO_IN_D(in_8, 8, lbz); DEF_MMIO_OUT_D(out_8, 8, stb); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 52378e641d38..a2d255aa9627 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -71,14 +71,26 @@ __pu_failed: \ * because we do not write to any memory gcc knows about, so there * are no aliasing issues. */ +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __put_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: " op " %0,0(%1) # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), "b" (addr) \ + : \ + : label) +#else #define __put_user_asm_goto(x, addr, label, op) \ asm_volatile_goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ - : "r" (x), "m<>" (*addr) \ + : "r" (x), "m<>" (*addr) \ : \ : label) +#endif #ifdef __powerpc64__ #define __put_user_asm2_goto(x, ptr, label) \ @@ -131,14 +143,26 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __get_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: "op" %0,0(%1) # get_user\n" \ + EX_TABLE(1b, %l2) \ + : "=r" (x) \ + : "b" (addr) \ + : \ + : label) +#else #define __get_user_asm_goto(x, addr, label, op) \ asm_volatile_goto( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ - : "m<>" (*addr) \ + : "m<>" (*addr) \ : \ : label) +#endif #ifdef __powerpc64__ #define __get_user_asm2_goto(x, addr, label) \ diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 7b85c3b460a3..72864fb7a6cc 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -194,6 +194,8 @@ __ftrace_make_nop(struct module *mod, * get corrupted. * * Use a b +8 to jump over the load. + * XXX: could make PCREL depend on MPROFILE_KERNEL + * XXX: check PCREL && MPROFILE_KERNEL calling sequence */ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32)) pop = ppc_inst(PPC_RAW_NOP()); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 046b571496b1..1ff0d2818da6 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -180,6 +180,7 @@ config POWER10_CPU bool "POWER10" depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER + select PPC_HAVE_PREFIXED_SUPPORT config E5500_CPU bool "Freescale e5500" @@ -454,6 +455,22 @@ config PPC_RADIX_MMU_DEFAULT If you're unsure, say Y. +config PPC_KERNEL_PREFIXED + depends on PPC_HAVE_PREFIXED_SUPPORT + depends on CC_HAS_PREFIXED + default n + bool "Build Kernel with Prefixed Instructions" + help + POWER10 and later CPUs support prefixed instructions, 8 byte + instructions that include large immediate, pc relative addressing, + and various floating point, vector, MMA. + + This option builds the kernel with prefixed instructions, and + allows a pc relative addressing option to be selected. + + Kernel support for prefixed instructions in applications and guests + is not affected by this option. + config PPC_KUEP bool "Kernel Userspace Execution Prevention" if !40x default y if !40x @@ -490,6 +507,9 @@ config PPC_MMU_NOHASH config PPC_HAVE_PMU_SUPPORT bool +config PPC_HAVE_PREFIXED_SUPPORT + bool + config PMU_SYSFS bool "Create PMU SPRs sysfs file" default n -- GitLab From 4e991e3c16a350d1eeffc100ce3fb25292596d03 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:50 +1000 Subject: [PATCH 3453/5631] powerpc: add CFUNC assembly label annotation This macro is to be used in assembly where C functions are called. pcrel addressing mode requires branches to functions with a localentry value of 1 to have either a trailing nop or @notoc. This macro permits the latter without changing callers. Signed-off-by: Nicholas Piggin [mpe: Add dummy definitions to fix selftests build] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-5-npiggin@gmail.com --- arch/powerpc/include/asm/ppc_asm.h | 5 + arch/powerpc/kernel/exceptions-64s.S | 112 +++++++++--------- arch/powerpc/kernel/head_64.S | 12 +- arch/powerpc/kernel/interrupt_64.S | 28 ++--- arch/powerpc/kernel/misc_64.S | 2 +- arch/powerpc/kernel/vdso/gettimeofday.S | 6 +- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 16 +-- arch/powerpc/lib/copypage_power7.S | 4 +- arch/powerpc/lib/copyuser_power7.S | 8 +- arch/powerpc/lib/hweight_64.S | 8 +- arch/powerpc/lib/memcmp_64.S | 4 +- arch/powerpc/lib/memcpy_power7.S | 6 +- arch/powerpc/platforms/pseries/hvCall.S | 4 +- .../selftests/powerpc/copyloops/asm/ppc_asm.h | 1 + .../powerpc/stringloops/asm/ppc_asm.h | 1 + 15 files changed, 114 insertions(+), 103 deletions(-) diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 1f1a64b780e3..f08b7990a69d 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -180,6 +180,11 @@ #ifdef __KERNEL__ +/* + * Used to name C functions called from asm + */ +#define CFUNC(name) name + /* * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit * version below in the else case of the ifdef. diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 6441a1ba57ac..c33c8ebf8641 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1075,7 +1075,7 @@ EXC_COMMON_BEGIN(system_reset_common) __GEN_COMMON_BODY system_reset addi r3,r1,STACK_INT_FRAME_REGS - bl system_reset_exception + bl CFUNC(system_reset_exception) /* Clear MSR_RI before setting SRR0 and SRR1. */ li r9,0 @@ -1223,9 +1223,9 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) addi r3,r1,STACK_INT_FRAME_REGS BEGIN_FTR_SECTION - bl machine_check_early_boot + bl CFUNC(machine_check_early_boot) END_FTR_SECTION(0, 1) // nop out after boot - bl machine_check_early + bl CFUNC(machine_check_early) std r3,RESULT(r1) /* Save result */ ld r12,_MSR(r1) @@ -1286,7 +1286,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) * Queue up the MCE event so that we can log it later, while * returning from kernel or opal call. */ - bl machine_check_queue_event + bl CFUNC(machine_check_queue_event) MACHINE_CHECK_HANDLER_WINDUP RFI_TO_KERNEL @@ -1312,7 +1312,7 @@ EXC_COMMON_BEGIN(machine_check_common) */ GEN_COMMON machine_check addi r3,r1,STACK_INT_FRAME_REGS - bl machine_check_exception_async + bl CFUNC(machine_check_exception_async) b interrupt_return_srr @@ -1322,7 +1322,7 @@ EXC_COMMON_BEGIN(machine_check_common) * done. Queue the event then call the idle code to do the wake up. */ EXC_COMMON_BEGIN(machine_check_idle_common) - bl machine_check_queue_event + bl CFUNC(machine_check_queue_event) /* * GPR-loss wakeups are relatively straightforward, because the @@ -1361,7 +1361,7 @@ EXC_COMMON_BEGIN(unrecoverable_mce) BEGIN_FTR_SECTION li r10,0 /* clear MSR_RI */ mtmsrd r10,1 - bl disable_machine_check + bl CFUNC(disable_machine_check) END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) ld r10,PACAKMSR(r13) li r3,MSR_ME @@ -1378,14 +1378,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) * the early handler which is a true NMI. */ addi r3,r1,STACK_INT_FRAME_REGS - bl machine_check_exception + bl CFUNC(machine_check_exception) /* * We will not reach here. Even if we did, there is no way out. * Call unrecoverable_exception and die. */ addi r3,r1,STACK_INT_FRAME_REGS - bl unrecoverable_exception + bl CFUNC(unrecoverable_exception) b . @@ -1440,16 +1440,16 @@ EXC_COMMON_BEGIN(data_access_common) bne- 1f #ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION - bl do_hash_fault + bl CFUNC(do_hash_fault) MMU_FTR_SECTION_ELSE - bl do_page_fault + bl CFUNC(do_page_fault) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) #else - bl do_page_fault + bl CFUNC(do_page_fault) #endif b interrupt_return_srr -1: bl do_break +1: bl CFUNC(do_break) /* * do_break() may have changed the NV GPRS while handling a breakpoint. * If so, we need to restore them with their updated values. @@ -1493,7 +1493,7 @@ EXC_COMMON_BEGIN(data_access_slb_common) BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_INT_FRAME_REGS - bl do_slb_fault + bl CFUNC(do_slb_fault) cmpdi r3,0 bne- 1f b fast_interrupt_return_srr @@ -1507,7 +1507,7 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) #endif std r3,RESULT(r1) addi r3,r1,STACK_INT_FRAME_REGS - bl do_bad_segment_interrupt + bl CFUNC(do_bad_segment_interrupt) b interrupt_return_srr @@ -1541,12 +1541,12 @@ EXC_COMMON_BEGIN(instruction_access_common) addi r3,r1,STACK_INT_FRAME_REGS #ifdef CONFIG_PPC_64S_HASH_MMU BEGIN_MMU_FTR_SECTION - bl do_hash_fault + bl CFUNC(do_hash_fault) MMU_FTR_SECTION_ELSE - bl do_page_fault + bl CFUNC(do_page_fault) ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) #else - bl do_page_fault + bl CFUNC(do_page_fault) #endif b interrupt_return_srr @@ -1581,7 +1581,7 @@ EXC_COMMON_BEGIN(instruction_access_slb_common) BEGIN_MMU_FTR_SECTION /* HPT case, do SLB fault */ addi r3,r1,STACK_INT_FRAME_REGS - bl do_slb_fault + bl CFUNC(do_slb_fault) cmpdi r3,0 bne- 1f b fast_interrupt_return_srr @@ -1595,7 +1595,7 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX) #endif std r3,RESULT(r1) addi r3,r1,STACK_INT_FRAME_REGS - bl do_bad_segment_interrupt + bl CFUNC(do_bad_segment_interrupt) b interrupt_return_srr @@ -1649,7 +1649,7 @@ EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100) EXC_COMMON_BEGIN(hardware_interrupt_common) GEN_COMMON hardware_interrupt addi r3,r1,STACK_INT_FRAME_REGS - bl do_IRQ + bl CFUNC(do_IRQ) BEGIN_FTR_SECTION b interrupt_return_hsrr FTR_SECTION_ELSE @@ -1679,7 +1679,7 @@ EXC_VIRT_END(alignment, 0x4600, 0x100) EXC_COMMON_BEGIN(alignment_common) GEN_COMMON alignment addi r3,r1,STACK_INT_FRAME_REGS - bl alignment_exception + bl CFUNC(alignment_exception) HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */ b interrupt_return_srr @@ -1745,7 +1745,7 @@ EXC_COMMON_BEGIN(program_check_common) .Ldo_program_check: addi r3,r1,STACK_INT_FRAME_REGS - bl program_check_exception + bl CFUNC(program_check_exception) HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */ b interrupt_return_srr @@ -1777,7 +1777,7 @@ EXC_COMMON_BEGIN(fp_unavailable_common) GEN_COMMON fp_unavailable bne 1f /* if from user, just load it up */ addi r3,r1,STACK_INT_FRAME_REGS - bl kernel_fp_unavailable_exception + bl CFUNC(kernel_fp_unavailable_exception) 0: trap EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0 1: @@ -1790,12 +1790,12 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - bl load_up_fpu + bl CFUNC(load_up_fpu) b fast_interrupt_return_srr #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ addi r3,r1,STACK_INT_FRAME_REGS - bl fp_unavailable_tm + bl CFUNC(fp_unavailable_tm) b interrupt_return_srr #endif @@ -1839,7 +1839,7 @@ EXC_VIRT_END(decrementer, 0x4900, 0x80) EXC_COMMON_BEGIN(decrementer_common) GEN_COMMON decrementer addi r3,r1,STACK_INT_FRAME_REGS - bl timer_interrupt + bl CFUNC(timer_interrupt) b interrupt_return_srr @@ -1925,9 +1925,9 @@ EXC_COMMON_BEGIN(doorbell_super_common) GEN_COMMON doorbell_super addi r3,r1,STACK_INT_FRAME_REGS #ifdef CONFIG_PPC_DOORBELL - bl doorbell_exception + bl CFUNC(doorbell_exception) #else - bl unknown_async_exception + bl CFUNC(unknown_async_exception) #endif b interrupt_return_srr @@ -2091,7 +2091,7 @@ EXC_VIRT_END(single_step, 0x4d00, 0x100) EXC_COMMON_BEGIN(single_step_common) GEN_COMMON single_step addi r3,r1,STACK_INT_FRAME_REGS - bl single_step_exception + bl CFUNC(single_step_exception) b interrupt_return_srr @@ -2126,9 +2126,9 @@ EXC_COMMON_BEGIN(h_data_storage_common) GEN_COMMON h_data_storage addi r3,r1,STACK_INT_FRAME_REGS BEGIN_MMU_FTR_SECTION - bl do_bad_page_fault_segv + bl CFUNC(do_bad_page_fault_segv) MMU_FTR_SECTION_ELSE - bl unknown_exception + bl CFUNC(unknown_exception) ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX) b interrupt_return_hsrr @@ -2154,7 +2154,7 @@ EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20) EXC_COMMON_BEGIN(h_instr_storage_common) GEN_COMMON h_instr_storage addi r3,r1,STACK_INT_FRAME_REGS - bl unknown_exception + bl CFUNC(unknown_exception) b interrupt_return_hsrr @@ -2177,7 +2177,7 @@ EXC_VIRT_END(emulation_assist, 0x4e40, 0x20) EXC_COMMON_BEGIN(emulation_assist_common) GEN_COMMON emulation_assist addi r3,r1,STACK_INT_FRAME_REGS - bl emulation_assist_interrupt + bl CFUNC(emulation_assist_interrupt) HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */ b interrupt_return_hsrr @@ -2237,7 +2237,7 @@ EXC_COMMON_BEGIN(hmi_exception_early_common) __GEN_COMMON_BODY hmi_exception_early addi r3,r1,STACK_INT_FRAME_REGS - bl hmi_exception_realmode + bl CFUNC(hmi_exception_realmode) cmpdi cr0,r3,0 bne 1f @@ -2255,7 +2255,7 @@ EXC_COMMON_BEGIN(hmi_exception_early_common) EXC_COMMON_BEGIN(hmi_exception_common) GEN_COMMON hmi_exception addi r3,r1,STACK_INT_FRAME_REGS - bl handle_hmi_exception + bl CFUNC(handle_hmi_exception) b interrupt_return_hsrr @@ -2290,9 +2290,9 @@ EXC_COMMON_BEGIN(h_doorbell_common) GEN_COMMON h_doorbell addi r3,r1,STACK_INT_FRAME_REGS #ifdef CONFIG_PPC_DOORBELL - bl doorbell_exception + bl CFUNC(doorbell_exception) #else - bl unknown_async_exception + bl CFUNC(unknown_async_exception) #endif b interrupt_return_hsrr @@ -2325,7 +2325,7 @@ EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20) EXC_COMMON_BEGIN(h_virt_irq_common) GEN_COMMON h_virt_irq addi r3,r1,STACK_INT_FRAME_REGS - bl do_IRQ + bl CFUNC(do_IRQ) b interrupt_return_hsrr @@ -2374,10 +2374,10 @@ EXC_COMMON_BEGIN(performance_monitor_common) lbz r4,PACAIRQSOFTMASK(r13) cmpdi r4,IRQS_ENABLED bne 1f - bl performance_monitor_exception_async + bl CFUNC(performance_monitor_exception_async) b interrupt_return_srr 1: - bl performance_monitor_exception_nmi + bl CFUNC(performance_monitor_exception_nmi) /* Clear MSR_RI before setting SRR0 and SRR1. */ li r9,0 mtmsrd r9,1 @@ -2421,19 +2421,19 @@ BEGIN_FTR_SECTION bne- 2f END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69) #endif - bl load_up_altivec + bl CFUNC(load_up_altivec) b fast_interrupt_return_srr #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ addi r3,r1,STACK_INT_FRAME_REGS - bl altivec_unavailable_tm + bl CFUNC(altivec_unavailable_tm) b interrupt_return_srr #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif addi r3,r1,STACK_INT_FRAME_REGS - bl altivec_unavailable_exception + bl CFUNC(altivec_unavailable_exception) b interrupt_return_srr @@ -2475,14 +2475,14 @@ BEGIN_FTR_SECTION #ifdef CONFIG_PPC_TRANSACTIONAL_MEM 2: /* User process was in a transaction */ addi r3,r1,STACK_INT_FRAME_REGS - bl vsx_unavailable_tm + bl CFUNC(vsx_unavailable_tm) b interrupt_return_srr #endif 1: END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif addi r3,r1,STACK_INT_FRAME_REGS - bl vsx_unavailable_exception + bl CFUNC(vsx_unavailable_exception) b interrupt_return_srr @@ -2509,7 +2509,7 @@ EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20) EXC_COMMON_BEGIN(facility_unavailable_common) GEN_COMMON facility_unavailable addi r3,r1,STACK_INT_FRAME_REGS - bl facility_unavailable_exception + bl CFUNC(facility_unavailable_exception) HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */ b interrupt_return_srr @@ -2537,7 +2537,7 @@ EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20) EXC_COMMON_BEGIN(h_facility_unavailable_common) GEN_COMMON h_facility_unavailable addi r3,r1,STACK_INT_FRAME_REGS - bl facility_unavailable_exception + bl CFUNC(facility_unavailable_exception) /* XXX Shouldn't be necessary in practice */ HANDLER_RESTORE_NVGPRS() b interrupt_return_hsrr @@ -2568,7 +2568,7 @@ EXC_VIRT_NONE(0x5200, 0x100) EXC_COMMON_BEGIN(cbe_system_error_common) GEN_COMMON cbe_system_error addi r3,r1,STACK_INT_FRAME_REGS - bl cbe_system_error_exception + bl CFUNC(cbe_system_error_exception) b interrupt_return_hsrr #else /* CONFIG_CBE_RAS */ @@ -2599,7 +2599,7 @@ EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100) EXC_COMMON_BEGIN(instruction_breakpoint_common) GEN_COMMON instruction_breakpoint addi r3,r1,STACK_INT_FRAME_REGS - bl instruction_breakpoint_exception + bl CFUNC(instruction_breakpoint_exception) b interrupt_return_srr @@ -2721,7 +2721,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) EXC_COMMON_BEGIN(denorm_exception_common) GEN_COMMON denorm_exception addi r3,r1,STACK_INT_FRAME_REGS - bl unknown_exception + bl CFUNC(unknown_exception) b interrupt_return_hsrr @@ -2738,7 +2738,7 @@ EXC_VIRT_NONE(0x5600, 0x100) EXC_COMMON_BEGIN(cbe_maintenance_common) GEN_COMMON cbe_maintenance addi r3,r1,STACK_INT_FRAME_REGS - bl cbe_maintenance_exception + bl CFUNC(cbe_maintenance_exception) b interrupt_return_hsrr #else /* CONFIG_CBE_RAS */ @@ -2764,10 +2764,10 @@ EXC_COMMON_BEGIN(altivec_assist_common) GEN_COMMON altivec_assist addi r3,r1,STACK_INT_FRAME_REGS #ifdef CONFIG_ALTIVEC - bl altivec_assist_exception + bl CFUNC(altivec_assist_exception) HANDLER_RESTORE_NVGPRS() /* instruction emulation may change GPRs */ #else - bl unknown_exception + bl CFUNC(unknown_exception) #endif b interrupt_return_srr @@ -2785,7 +2785,7 @@ EXC_VIRT_NONE(0x5800, 0x100) EXC_COMMON_BEGIN(cbe_thermal_common) GEN_COMMON cbe_thermal addi r3,r1,STACK_INT_FRAME_REGS - bl cbe_thermal_exception + bl CFUNC(cbe_thermal_exception) b interrupt_return_hsrr #else /* CONFIG_CBE_RAS */ @@ -2818,7 +2818,7 @@ EXC_COMMON_BEGIN(soft_nmi_common) __GEN_COMMON_BODY soft_nmi addi r3,r1,STACK_INT_FRAME_REGS - bl soft_nmi_interrupt + bl CFUNC(soft_nmi_interrupt) /* Clear MSR_RI before setting SRR0 and SRR1. */ li r9,0 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index bac1dfe52ae5..6e04e30ae44c 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -608,7 +608,7 @@ __boot_from_prom: /* Do all of the interaction with OF client interface */ mr r8,r26 - bl prom_init + bl CFUNC(prom_init) #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */ /* We never return. We also hit that trap if trying to boot @@ -836,7 +836,7 @@ __secondary_start: * can turn it on below. This is a call to C, which is OK, we're still * running on the emergency stack. */ - bl early_setup_secondary + bl CFUNC(early_setup_secondary) /* * The primary has initialized our kernel stack for us in the paca, grab @@ -875,7 +875,7 @@ start_secondary_prolog: LOAD_PACA_TOC() li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl start_secondary + bl CFUNC(start_secondary) b . /* * Reset stack pointer and call start_secondary @@ -886,7 +886,7 @@ _GLOBAL(start_secondary_resume) ld r1,PACAKSAVE(r13) /* Reload kernel stack pointer */ li r3,0 std r3,0(r1) /* Zero the stack frame pointer */ - bl start_secondary + bl CFUNC(start_secondary) b . #endif @@ -991,7 +991,7 @@ start_here_multiplatform: */ #ifdef CONFIG_KASAN - bl kasan_early_init + bl CFUNC(kasan_early_init) #endif /* Restore parameters passed from prom_init/kexec */ mr r3,r31 @@ -1024,7 +1024,7 @@ start_here_common: stb r0,PACAIRQHAPPENED(r13) /* Generic kernel entry */ - bl start_kernel + bl CFUNC(start_kernel) /* Not reached */ 0: trap diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 2a059214c1a9..6730d676284c 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -101,12 +101,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) * state of kernel code. */ SANITIZE_SYSCALL_GPRS() - bl system_call_exception + bl CFUNC(system_call_exception) .Lsyscall_vectored_\name\()_exit: addi r4,r1,STACK_INT_FRAME_REGS li r5,1 /* scv */ - bl syscall_exit_prepare + bl CFUNC(syscall_exit_prepare) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ .Lsyscall_vectored_\name\()_rst_start: lbz r11,PACAIRQHAPPENED(r13) @@ -185,7 +185,7 @@ _ASM_NOKPROBE_SYMBOL(syscall_vectored_\name\()_restart) addi r4,r1,STACK_INT_FRAME_REGS li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) - bl syscall_exit_restart + bl CFUNC(syscall_exit_restart) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ b .Lsyscall_vectored_\name\()_rst_start 1: @@ -286,12 +286,12 @@ END_BTB_FLUSH_SECTION * state of kernel code. */ SANITIZE_SYSCALL_GPRS() - bl system_call_exception + bl CFUNC(system_call_exception) .Lsyscall_exit: addi r4,r1,STACK_INT_FRAME_REGS li r5,0 /* !scv */ - bl syscall_exit_prepare + bl CFUNC(syscall_exit_prepare) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ #ifdef CONFIG_PPC_BOOK3S .Lsyscall_rst_start: @@ -372,7 +372,7 @@ _ASM_NOKPROBE_SYMBOL(syscall_restart) addi r4,r1,STACK_INT_FRAME_REGS li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) - bl syscall_exit_restart + bl CFUNC(syscall_exit_restart) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ b .Lsyscall_rst_start 1: @@ -401,7 +401,7 @@ _ASM_NOKPROBE_SYMBOL(fast_interrupt_return_srr) li r3,0 /* 0 return value, no EMULATE_STACK_STORE */ bne+ .Lfast_kernel_interrupt_return_srr addi r3,r1,STACK_INT_FRAME_REGS - bl unrecoverable_exception + bl CFUNC(unrecoverable_exception) b . /* should not get here */ #else bne .Lfast_user_interrupt_return_srr @@ -419,7 +419,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()) interrupt_return_\srr\()_user: /* make backtraces match the _kernel variant */ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user) addi r3,r1,STACK_INT_FRAME_REGS - bl interrupt_exit_user_prepare + bl CFUNC(interrupt_exit_user_prepare) #ifndef CONFIG_INTERRUPT_SANITIZE_REGISTERS cmpdi r3,0 bne- .Lrestore_nvgprs_\srr @@ -523,7 +523,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_user_restart) addi r3,r1,STACK_INT_FRAME_REGS li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) - bl interrupt_exit_user_restart + bl CFUNC(interrupt_exit_user_restart) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ b .Linterrupt_return_\srr\()_user_rst_start 1: @@ -536,7 +536,7 @@ RESTART_TABLE(.Linterrupt_return_\srr\()_user_rst_start, .Linterrupt_return_\srr interrupt_return_\srr\()_kernel: _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel) addi r3,r1,STACK_INT_FRAME_REGS - bl interrupt_exit_kernel_prepare + bl CFUNC(interrupt_exit_kernel_prepare) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ .Linterrupt_return_\srr\()_kernel_rst_start: @@ -705,7 +705,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel_restart) addi r3,r1,STACK_INT_FRAME_REGS li r11,IRQS_ALL_DISABLED stb r11,PACAIRQSOFTMASK(r13) - bl interrupt_exit_kernel_restart + bl CFUNC(interrupt_exit_kernel_restart) std r1,PACA_EXIT_SAVE_R1(r13) /* save r1 for restart */ b .Linterrupt_return_\srr\()_kernel_rst_start 1: @@ -727,20 +727,20 @@ DEFINE_FIXED_SYMBOL(__end_soft_masked, text) #ifdef CONFIG_PPC_BOOK3S _GLOBAL(ret_from_fork_scv) - bl schedule_tail + bl CFUNC(schedule_tail) HANDLER_RESTORE_NVGPRS() li r3,0 /* fork() return value */ b .Lsyscall_vectored_common_exit #endif _GLOBAL(ret_from_fork) - bl schedule_tail + bl CFUNC(schedule_tail) HANDLER_RESTORE_NVGPRS() li r3,0 /* fork() return value */ b .Lsyscall_exit _GLOBAL(ret_from_kernel_user_thread) - bl schedule_tail + bl CFUNC(schedule_tail) mtctr r14 mr r3,r15 #ifdef CONFIG_PPC64_ELF_ABI_V2 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index c39c07a4c06e..2c9ac70aaf0c 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -432,7 +432,7 @@ _GLOBAL(kexec_sequence) 1: /* copy dest pages, flush whole dest image */ mr r3,r29 - bl kexec_copy_flush /* (image) */ + bl CFUNC(kexec_copy_flush) /* (image) */ /* turn off mmu now if not done earlier */ cmpdi r26,0 diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index 0c4ecc8fec5a..48fc6658053a 100644 --- a/arch/powerpc/kernel/vdso/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -38,7 +38,11 @@ .else addi r4, r5, VDSO_DATA_OFFSET .endif - bl DOTSYM(\funct) +#ifdef __powerpc64__ + bl CFUNC(DOTSYM(\funct)) +#else + bl \funct +#endif PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) #ifdef __powerpc64__ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 800892dab48e..870110e3d9b1 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -381,7 +381,7 @@ kvm_secondary_got_guest: bne kvm_no_guest li r3,0 /* NULL argument */ - bl hmi_exception_realmode + bl CFUNC(hmi_exception_realmode) /* * At this point we have finished executing in the guest. * We need to wait for hwthread_req to become zero, since @@ -458,7 +458,7 @@ kvm_unsplit_nap: cmpwi r12, BOOK3S_INTERRUPT_HMI bne 55f li r3, 0 /* NULL argument */ - bl hmi_exception_realmode + bl CFUNC(hmi_exception_realmode) 55: /* * Ensure that secondary doesn't nap when it has @@ -858,7 +858,7 @@ deliver_guest_interrupt: /* r4 = vcpu, r13 = paca */ cmpdi r0, 0 beq 71f mr r3, r4 - bl kvmppc_guest_entry_inject_int + bl CFUNC(kvmppc_guest_entry_inject_int) ld r4, HSTATE_KVM_VCPU(r13) 71: ld r6, VCPU_SRR0(r4) @@ -1544,7 +1544,7 @@ kvmppc_guest_external: /* External interrupt, first check for host_ipi. If this is * set, we know the host wants us out so let's do it now */ - bl kvmppc_read_intr + bl CFUNC(kvmppc_read_intr) /* * Restore the active volatile registers after returning from @@ -1626,7 +1626,7 @@ kvmppc_hdsi: /* Search the hash table. */ mr r3, r9 /* vcpu pointer */ li r7, 1 /* data fault */ - bl kvmppc_hpte_hv_fault + bl CFUNC(kvmppc_hpte_hv_fault) ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -1702,7 +1702,7 @@ kvmppc_hisi: mr r4, r10 mr r6, r11 li r7, 0 /* instruction fault */ - bl kvmppc_hpte_hv_fault + bl CFUNC(kvmppc_hpte_hv_fault) ld r9, HSTATE_KVM_VCPU(r13) ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) @@ -2342,7 +2342,7 @@ hmi_realmode: lbz r0, HSTATE_PTID(r13) cmpwi r0, 0 bne guest_exit_cont - bl kvmppc_realmode_hmi_handler + bl CFUNC(kvmppc_realmode_hmi_handler) ld r9, HSTATE_KVM_VCPU(r13) li r12, BOOK3S_INTERRUPT_HMI b guest_exit_cont @@ -2413,7 +2413,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) 7: mflr r0 std r0, PPC_LR_STKOFF(r1) stdu r1, -PPC_MIN_STKFRM(r1) - bl kvmppc_read_intr + bl CFUNC(kvmppc_read_intr) nop li r12, BOOK3S_INTERRUPT_EXTERNAL cmpdi r3, 1 diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index a9844c6353cf..a783973f1215 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -45,7 +45,7 @@ _GLOBAL(copypage_power7) std r4,-STACKFRAMESIZE+STK_REG(R30)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl enter_vmx_ops + bl CFUNC(enter_vmx_ops) cmpwi r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STK_REG(R31)(r1) @@ -88,7 +88,7 @@ _GLOBAL(copypage_power7) addi r3,r3,128 bdnz 1b - b exit_vmx_ops /* tail call optimise */ + b CFUNC(exit_vmx_ops) /* tail call optimise */ #else li r0,(PAGE_SIZE/128) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 28f0be523c06..ac41053c3a5a 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -47,7 +47,7 @@ ld r15,STK_REG(R15)(r1) ld r14,STK_REG(R14)(r1) .Ldo_err3: - bl exit_vmx_usercopy + bl CFUNC(exit_vmx_usercopy) ld r0,STACKFRAMESIZE+16(r1) mtlr r0 b .Lexit @@ -272,7 +272,7 @@ err1; stb r0,0(r3) mflr r0 std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl enter_vmx_usercopy + bl CFUNC(enter_vmx_usercopy) cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STK_REG(R31)(r1) @@ -488,7 +488,7 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b exit_vmx_usercopy /* tail call optimise */ + b CFUNC(exit_vmx_usercopy) /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -691,5 +691,5 @@ err3; lbz r0,0(r4) err3; stb r0,0(r3) 15: addi r1,r1,STACKFRAMESIZE - b exit_vmx_usercopy /* tail call optimise */ + b CFUNC(exit_vmx_usercopy) /* tail call optimise */ #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S index 6effad901ef7..09af29561314 100644 --- a/arch/powerpc/lib/hweight_64.S +++ b/arch/powerpc/lib/hweight_64.S @@ -14,7 +14,7 @@ _GLOBAL(__arch_hweight8) BEGIN_FTR_SECTION - b __sw_hweight8 + b CFUNC(__sw_hweight8) nop nop FTR_SECTION_ELSE @@ -26,7 +26,7 @@ EXPORT_SYMBOL(__arch_hweight8) _GLOBAL(__arch_hweight16) BEGIN_FTR_SECTION - b __sw_hweight16 + b CFUNC(__sw_hweight16) nop nop nop @@ -49,7 +49,7 @@ EXPORT_SYMBOL(__arch_hweight16) _GLOBAL(__arch_hweight32) BEGIN_FTR_SECTION - b __sw_hweight32 + b CFUNC(__sw_hweight32) nop nop nop @@ -75,7 +75,7 @@ EXPORT_SYMBOL(__arch_hweight32) _GLOBAL(__arch_hweight64) BEGIN_FTR_SECTION - b __sw_hweight64 + b CFUNC(__sw_hweight64) nop nop nop diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S index 384218df71ba..0b9b1685a33d 100644 --- a/arch/powerpc/lib/memcmp_64.S +++ b/arch/powerpc/lib/memcmp_64.S @@ -44,7 +44,7 @@ std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \ std r0,16(r1); \ stdu r1,-STACKFRAMESIZE(r1); \ - bl enter_vmx_ops; \ + bl CFUNC(enter_vmx_ops); \ cmpwi cr1,r3,0; \ ld r0,STACKFRAMESIZE+16(r1); \ ld r3,STK_REG(R31)(r1); \ @@ -60,7 +60,7 @@ std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \ std r0,16(r1); \ stdu r1,-STACKFRAMESIZE(r1); \ - bl exit_vmx_ops; \ + bl CFUNC(exit_vmx_ops); \ ld r0,STACKFRAMESIZE+16(r1); \ ld r3,STK_REG(R31)(r1); \ ld r4,STK_REG(R30)(r1); \ diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 54f226333c94..9398b2b746c4 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -218,7 +218,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) std r5,-STACKFRAMESIZE+STK_REG(R29)(r1) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) - bl enter_vmx_ops + bl CFUNC(enter_vmx_ops) cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STK_REG(R31)(r1) @@ -433,7 +433,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) 15: addi r1,r1,STACKFRAMESIZE ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - b exit_vmx_ops /* tail call optimise */ + b CFUNC(exit_vmx_ops) /* tail call optimise */ .Lvmx_unaligned_copy: /* Get the destination 16B aligned */ @@ -637,5 +637,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) 15: addi r1,r1,STACKFRAMESIZE ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1) - b exit_vmx_ops /* tail call optimise */ + b CFUNC(exit_vmx_ops) /* tail call optimise */ #endif /* CONFIG_ALTIVEC */ diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 783c16ad648b..35254ac7af5e 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -44,7 +44,7 @@ hcall_tracepoint_refcount: std r0,16(r1); \ addi r4,r1,STK_PARAM(FIRST_REG); \ stdu r1,-STACK_FRAME_MIN_SIZE(r1); \ - bl __trace_hcall_entry; \ + bl CFUNC(__trace_hcall_entry); \ ld r3,STACK_FRAME_MIN_SIZE+STK_PARAM(R3)(r1); \ ld r4,STACK_FRAME_MIN_SIZE+STK_PARAM(R4)(r1); \ ld r5,STACK_FRAME_MIN_SIZE+STK_PARAM(R5)(r1); \ @@ -63,7 +63,7 @@ hcall_tracepoint_refcount: std r3,STACK_FRAME_MIN_SIZE+STK_PARAM(R3)(r1); \ mr r4,r3; \ mr r3,r0; \ - bl __trace_hcall_exit; \ + bl CFUNC(__trace_hcall_exit); \ ld r0,STACK_FRAME_MIN_SIZE+16(r1); \ addi r1,r1,STACK_FRAME_MIN_SIZE; \ ld r3,STK_PARAM(R3)(r1); \ diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h index 003e1b3d9300..a89f1fbf86ec 100644 --- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h @@ -27,6 +27,7 @@ #define _GLOBAL_TOC(A) _GLOBAL(A) #define _GLOBAL_TOC_KASAN(A) _GLOBAL(A) #define _GLOBAL_KASAN(A) _GLOBAL(A) +#define CFUNC(name) name #define PPC_MTOCRF(A, B) mtocrf A, B diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h index 2b488b78c4f2..e713b69d694a 100644 --- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h +++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h @@ -9,6 +9,7 @@ #define _GLOBAL(A) FUNC_START(test_ ## A) #define _GLOBAL_TOC(A) FUNC_START(test_ ## A) +#define CFUNC(name) name #define CONFIG_ALTIVEC -- GitLab From 7e3a68be42e10f5fa5890e97afc0afd992355bc3 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:51 +1000 Subject: [PATCH 3454/5631] powerpc/64: vmlinux support building with PCREL addresing PC-Relative or PCREL addressing is an extension to the ELF ABI which uses Power ISA v3.1 PC-relative instructions to calculate addresses, rather than the traditional TOC scheme. Add an option to build vmlinux using pcrel addressing. Modules continue to use TOC addressing. - TOC address helpers and r2 are poisoned with -1 when running vmlinux. r2 could be used for something useful once things are ironed out. - Assembly must call C functions with @notoc annotation, or the linker complains aobut a missing nop after the call. This is done with the CFUNC macro introduced earlier. - Boot: with the exception of prom_init, the execution branches to the kernel virtual address early in boot, before any addresses are generated, which ensures 34-bit pcrel addressing does not miss the high PAGE_OFFSET bits. TOC relative addressing has a similar requirement. prom_init does not go to the virtual address and its addresses should not carry over to the post-prom kernel. - Ftrace trampolines are converted from TOC addressing to pcrel addressing, including module ftrace trampolines that currently use the kernel TOC to find ftrace target functions. - BPF function prologue and function calling generation are converted from TOC to pcrel. - copypage_64.S has an interesting problem, prefixed instructions have alignment restrictions so the linker can add padding, which makes the assembler treat the difference between two local labels as non-constant even if alignment is arranged so padding is not required. This may need toolchain help to solve nicely, for now move the prefix instruction out of the alternate patch section to work around it. This reduces kernel text size by about 6%. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-6-npiggin@gmail.com --- arch/powerpc/Kconfig | 3 ++ arch/powerpc/Makefile | 7 +++ arch/powerpc/include/asm/paca.h | 2 + arch/powerpc/include/asm/ppc-opcode.h | 8 ++++ arch/powerpc/include/asm/ppc_asm.h | 19 ++++++++ arch/powerpc/include/asm/sections.h | 5 +++ arch/powerpc/kernel/asm-offsets.c | 2 + arch/powerpc/kernel/head_64.S | 14 ++++++ arch/powerpc/kernel/irq.c | 8 ++++ arch/powerpc/kernel/module_64.c | 60 +++++++++++++++++++------- arch/powerpc/kernel/paca.c | 2 + arch/powerpc/kernel/trace/ftrace.c | 48 ++++++++++++++++----- arch/powerpc/kernel/vector.S | 6 +++ arch/powerpc/kernel/vmlinux.lds.S | 6 +++ arch/powerpc/lib/copypage_64.S | 10 +++++ arch/powerpc/net/bpf_jit.h | 10 +++-- arch/powerpc/net/bpf_jit_comp64.c | 36 ++++++++++++---- arch/powerpc/platforms/Kconfig.cputype | 18 ++++++++ arch/powerpc/xmon/xmon.c | 2 + 19 files changed, 228 insertions(+), 38 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 109c00bd91db..873eaa888a70 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -7,6 +7,9 @@ config CC_HAS_ELFV2 config CC_HAS_PREFIXED def_bool PPC64 && $(cc-option, -mcpu=power10 -mprefixed) +config CC_HAS_PCREL + def_bool PPC64 && $(cc-option, -mcpu=power10 -mpcrel) + config 32BIT bool default y if PPC32 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 9fb770d3b409..0297ad9a4ffb 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -107,6 +107,9 @@ LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) += -z notext LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) ifdef CONFIG_PPC64 +ifdef CONFIG_PPC_KERNEL_PCREL + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-pcrel) +endif ifeq ($(call cc-option-yn,-mcmodel=medium),y) # -mcmodel=medium breaks modules because it uses 32bit offsets from # the TOC pointer to create pointers where possible. Pointers into the @@ -185,7 +188,11 @@ KBUILD_CFLAGS += $(call cc-option,-mprefixed) else KBUILD_CFLAGS += $(call cc-option,-mno-prefixed) endif +ifdef CONFIG_PPC_KERNEL_PCREL +KBUILD_CFLAGS += $(call cc-option,-mpcrel) +else KBUILD_CFLAGS += $(call cc-option,-mno-pcrel) +endif # No AltiVec or VSX or MMA instructions when building kernel KBUILD_CFLAGS += $(call cc-option,-mno-altivec) diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 0ab3511a47d7..da0377f46597 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -88,7 +88,9 @@ struct paca_struct { u16 lock_token; /* Constant 0x8000, used in locks */ #endif +#ifndef CONFIG_PPC_KERNEL_PCREL u64 kernel_toc; /* Kernel TOC address */ +#endif u64 kernelbase; /* Base address of kernel */ u64 kernel_msr; /* MSR while running in kernel */ void *emergency_sp; /* pointer to emergency stack */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 21e33e46f4b8..ca5a0da7df4e 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -120,11 +120,18 @@ * 16-bit immediate helper macros: HA() is for use with sign-extending instrs * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + * + * XXX: should these mask out possible sign bits? */ #define IMM_H(i) ((uintptr_t)(i)>>16) #define IMM_HA(i) (((uintptr_t)(i)>>16) + \ (((uintptr_t)(i) & 0x8000) >> 15)) +/* + * 18-bit immediate helper for prefix 18-bit upper immediate si0 field. + */ +#define IMM_H18(i) (((uintptr_t)(i)>>16) & 0x3ffff) + /* opcode and xopcode for instructions */ #define OP_PREFIX 1 @@ -306,6 +313,7 @@ #define PPC_PREFIX_8LS 0x04000000 /* Prefixed instructions */ +#define PPC_INST_PADDI 0x38000000 #define PPC_INST_PLD 0xe4000000 #define PPC_INST_PSTD 0xf4000000 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index f08b7990a69d..4dfabf4ef966 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -183,7 +183,11 @@ /* * Used to name C functions called from asm */ +#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#define CFUNC(name) name@notoc +#else #define CFUNC(name) name +#endif /* * We use __powerpc64__ here because we want the compat VDSO to use the 32-bit @@ -212,6 +216,9 @@ .globl name; \ name: +#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#define _GLOBAL_TOC _GLOBAL +#else #define _GLOBAL_TOC(name) \ .align 2 ; \ .type name,@function; \ @@ -220,6 +227,7 @@ name: \ 0: addis r2,r12,(.TOC.-0b)@ha; \ addi r2,r2,(.TOC.-0b)@l; \ .localentry name,.-name +#endif #define DOTSYM(a) a @@ -351,8 +359,13 @@ GLUE(.,name): #ifdef __powerpc64__ +#ifdef CONFIG_PPC_KERNEL_PCREL +#define __LOAD_PACA_TOC(reg) \ + li reg,-1 +#else #define __LOAD_PACA_TOC(reg) \ ld reg,PACATOC(r13) +#endif #define LOAD_PACA_TOC() \ __LOAD_PACA_TOC(r2) @@ -366,9 +379,15 @@ GLUE(.,name): ori reg, reg, (expr)@l; \ rldimi reg, tmp, 32, 0 +#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#define LOAD_REG_ADDR(reg,name) \ + pla reg,name@pcrel + +#else #define LOAD_REG_ADDR(reg,name) \ addis reg,r2,name@toc@ha; \ addi reg,reg,name@toc@l +#endif #ifdef CONFIG_PPC_BOOK3E_64 /* diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 9c00c9c0ca8f..4e1f548c8d37 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -46,10 +46,15 @@ extern char end_virt_trampolines[]; */ static inline unsigned long kernel_toc_addr(void) { +#ifdef CONFIG_PPC_KERNEL_PCREL + BUILD_BUG(); + return -1UL; +#else unsigned long toc_ptr; asm volatile("mr %0, 2" : "=r" (toc_ptr)); return toc_ptr; +#endif } static inline int overlaps_interrupt_vector_text(unsigned long start, diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index d24a59a98c0c..9f14d95b8b32 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -185,7 +185,9 @@ int main(void) offsetof(struct task_struct, thread_info)); OFFSET(PACASAVEDMSR, paca_struct, saved_msr); OFFSET(PACAR1, paca_struct, saved_r1); +#ifndef CONFIG_PPC_KERNEL_PCREL OFFSET(PACATOC, paca_struct, kernel_toc); +#endif OFFSET(PACAKBASE, paca_struct, kernelbase); OFFSET(PACAKMSR, paca_struct, kernel_msr); #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 6e04e30ae44c..f132d8704263 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -330,6 +330,12 @@ _GLOBAL(fsl_secondary_thread_init) */ _GLOBAL(generic_secondary_smp_init) FIXUP_ENDIAN + + li r13,0 + + /* Poison TOC */ + li r2,-1 + mr r24,r3 mr r25,r4 @@ -528,6 +534,9 @@ __start_initialization_multiplatform: /* Zero r13 (paca) so early program check / mce don't use it */ li r13,0 + /* Poison TOC */ + li r2,-1 + /* * Are we booted from a PROM Of-type client-interface ? */ @@ -921,6 +930,10 @@ SYM_FUNC_END(enable_64b_mode) * this. */ _GLOBAL(relative_toc) +#ifdef CONFIG_PPC_KERNEL_PCREL + tdnei r2,-1 + blr +#else mflr r0 bcl 20,31,$+4 0: mflr r11 @@ -931,6 +944,7 @@ _GLOBAL(relative_toc) .balign 8 p_toc: .8byte .TOC. - 0b +#endif /* * This is where the main kernel code starts. diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c9535f2760b5..6f7d4edaa0bc 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -206,7 +206,11 @@ static __always_inline void call_do_softirq(const void *sp) asm volatile ( PPC_STLU " %%r1, %[offset](%[sp]) ;" "mr %%r1, %[sp] ;" +#ifdef CONFIG_PPC_KERNEL_PCREL + "bl %[callee]@notoc ;" +#else "bl %[callee] ;" +#endif PPC_LL " %%r1, 0(%%r1) ;" : // Outputs : // Inputs @@ -259,7 +263,11 @@ static __always_inline void call_do_irq(struct pt_regs *regs, void *sp) PPC_STLU " %%r1, %[offset](%[sp]) ;" "mr %%r4, %%r1 ;" "mr %%r1, %[sp] ;" +#ifdef CONFIG_PPC_KERNEL_PCREL + "bl %[callee]@notoc ;" +#else "bl %[callee] ;" +#endif PPC_LL " %%r1, 0(%%r1) ;" : // Outputs "+r" (r3) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 2ac78d207f77..0fc04abac3bd 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -101,17 +101,18 @@ static unsigned long stub_func_addr(func_desc_t func) /* Like PPC32, we need little trampolines to do > 24-bit jumps (into the kernel itself). But on PPC64, these need to be used for every jump, actually, to reset r2 (TOC+0x8000). */ -struct ppc64_stub_entry -{ - /* 28 byte jump instruction sequence (7 instructions). We only - * need 6 instructions on ABIv2 but we always allocate 7 so - * so we don't have to modify the trampoline load instruction. */ +struct ppc64_stub_entry { + /* + * 28 byte jump instruction sequence (7 instructions) that can + * hold ppc64_stub_insns or stub_insns. Must be 8-byte aligned + * with PCREL kernels that use prefix instructions in the stub. + */ u32 jump[7]; /* Used by ftrace to identify stubs */ u32 magic; /* Data for the above code */ func_desc_t funcdata; -}; +} __aligned(8); /* * PPC64 uses 24 bit jumps, but we need to jump into other modules or @@ -333,11 +334,21 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, #ifdef CONFIG_MPROFILE_KERNEL static u32 stub_insns[] = { +#ifdef CONFIG_PPC_KERNEL_PCREL + PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase)), + PPC_RAW_NOP(), /* align the prefix insn */ + /* paddi r12,r12,addr */ + PPC_PREFIX_MLS | __PPC_PRFX_R(0), + PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12), + PPC_RAW_MTCTR(_R12), + PPC_RAW_BCTR(), +#else PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernel_toc)), PPC_RAW_ADDIS(_R12, _R12, 0), PPC_RAW_ADDI(_R12, _R12, 0), PPC_RAW_MTCTR(_R12), PPC_RAW_BCTR(), +#endif }; /* @@ -358,18 +369,37 @@ static inline int create_ftrace_stub(struct ppc64_stub_entry *entry, { long reladdr; - memcpy(entry->jump, stub_insns, sizeof(stub_insns)); - - /* Stub uses address relative to kernel toc (from the paca) */ - reladdr = addr - kernel_toc_addr(); - if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { - pr_err("%s: Address of %ps out of range of kernel_toc.\n", - me->name, (void *)addr); + if ((unsigned long)entry->jump % 8 != 0) { + pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name); return 0; } - entry->jump[1] |= PPC_HA(reladdr); - entry->jump[2] |= PPC_LO(reladdr); + BUILD_BUG_ON(sizeof(stub_insns) > sizeof(entry->jump)); + memcpy(entry->jump, stub_insns, sizeof(stub_insns)); + + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { + /* Stub uses address relative to kernel base (from the paca) */ + reladdr = addr - local_paca->kernelbase; + if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) { + pr_err("%s: Address of %ps out of range of 34-bit relative address.\n", + me->name, (void *)addr); + return 0; + } + + entry->jump[2] |= IMM_H18(reladdr); + entry->jump[3] |= IMM_L(reladdr); + } else { + /* Stub uses address relative to kernel toc (from the paca) */ + reladdr = addr - kernel_toc_addr(); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("%s: Address of %ps out of range of kernel_toc.\n", + me->name, (void *)addr); + return 0; + } + + entry->jump[1] |= PPC_HA(reladdr); + entry->jump[2] |= PPC_LO(reladdr); + } /* Even though we don't use funcdata in the stub, it's needed elsewhere. */ entry->funcdata = func_desc(addr); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index be8db402e963..cda4e00b67c1 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -191,7 +191,9 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu) #endif new_paca->lock_token = 0x8000; new_paca->paca_index = cpu; +#ifndef CONFIG_PPC_KERNEL_PCREL new_paca->kernel_toc = kernel_toc_addr(); +#endif new_paca->kernelbase = (unsigned long) _stext; /* Only set MSR:IR/DR when MMU is initialized */ new_paca->kernel_msr = MSR_KERNEL & ~(MSR_IR | MSR_DR); diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 72864fb7a6cc..a47f30373423 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -727,6 +727,15 @@ int __init ftrace_dyn_arch_init(void) { int i; unsigned int *tramp[] = { ftrace_tramp_text, ftrace_tramp_init }; +#ifdef CONFIG_PPC_KERNEL_PCREL + u32 stub_insns[] = { + /* pla r12,addr */ + PPC_PREFIX_MLS | __PPC_PRFX_R(1), + PPC_INST_PADDI | ___PPC_RT(_R12), + PPC_RAW_MTCTR(_R12), + PPC_RAW_BCTR() + }; +#else u32 stub_insns[] = { PPC_RAW_LD(_R12, _R13, PACATOC), PPC_RAW_ADDIS(_R12, _R12, 0), @@ -734,6 +743,8 @@ int __init ftrace_dyn_arch_init(void) PPC_RAW_MTCTR(_R12), PPC_RAW_BCTR() }; +#endif + unsigned long addr; long reladdr; @@ -742,19 +753,36 @@ int __init ftrace_dyn_arch_init(void) else addr = ppc_global_function_entry((void *)ftrace_caller); - reladdr = addr - kernel_toc_addr(); + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { + for (i = 0; i < 2; i++) { + reladdr = addr - (unsigned long)tramp[i]; - if (reladdr >= SZ_2G || reladdr < -(long)SZ_2G) { - pr_err("Address of %ps out of range of kernel_toc.\n", + if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) { + pr_err("Address of %ps out of range of pcrel address.\n", + (void *)addr); + return -1; + } + + memcpy(tramp[i], stub_insns, sizeof(stub_insns)); + tramp[i][0] |= IMM_H18(reladdr); + tramp[i][1] |= IMM_L(reladdr); + add_ftrace_tramp((unsigned long)tramp[i]); + } + } else { + reladdr = addr - kernel_toc_addr(); + + if (reladdr >= (long)SZ_2G || reladdr < -(long)SZ_2G) { + pr_err("Address of %ps out of range of kernel_toc.\n", (void *)addr); - return -1; - } + return -1; + } - for (i = 0; i < 2; i++) { - memcpy(tramp[i], stub_insns, sizeof(stub_insns)); - tramp[i][1] |= PPC_HA(reladdr); - tramp[i][2] |= PPC_LO(reladdr); - add_ftrace_tramp((unsigned long)tramp[i]); + for (i = 0; i < 2; i++) { + memcpy(tramp[i], stub_insns, sizeof(stub_insns)); + tramp[i][1] |= PPC_HA(reladdr); + tramp[i][2] |= PPC_LO(reladdr); + add_ftrace_tramp((unsigned long)tramp[i]); + } } return 0; diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index ffe5d90abe17..fcc0ad6d9c7b 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -177,9 +177,15 @@ fpone: fphalf: .quad 0x3fe0000000000000 /* 0.5 */ +#ifdef CONFIG_PPC_KERNEL_PCREL +#define LDCONST(fr, name) \ + pla r11,name@pcrel; \ + lfd fr,0(r11) +#else #define LDCONST(fr, name) \ addis r11,r2,name@toc@ha; \ lfd fr,name@toc@l(r11) +#endif #endif .text /* diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index ee86753e444e..13614f0b269c 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -169,12 +169,18 @@ SECTIONS } #else /* CONFIG_PPC32 */ +#ifndef CONFIG_PPC_KERNEL_PCREL .toc1 : AT(ADDR(.toc1) - LOAD_OFFSET) { *(.toc1) } +#endif .got : AT(ADDR(.got) - LOAD_OFFSET) ALIGN(256) { +#ifdef CONFIG_PPC_KERNEL_PCREL + *(.got) +#else *(.got .toc) +#endif } SOFT_MASK_TABLE(8) diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S index 6812cb19d04a..5d09a029b556 100644 --- a/arch/powerpc/lib/copypage_64.S +++ b/arch/powerpc/lib/copypage_64.S @@ -18,8 +18,18 @@ FTR_SECTION_ELSE #endif ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY) ori r5,r5,PAGE_SIZE@l +#ifdef CONFIG_PPC_KERNEL_PCREL + /* + * Hack for toolchain - prefixed instructions cause label difference to + * be non-constant even if 8 byte alignment is known, so they can not + * be put in FTR sections. + */ + LOAD_REG_ADDR(r10, ppc64_caches) +BEGIN_FTR_SECTION +#else BEGIN_FTR_SECTION LOAD_REG_ADDR(r10, ppc64_caches) +#endif lwz r11,DCACHEL1LOGBLOCKSIZE(r10) /* log2 of cache block size */ lwz r12,DCACHEL1BLOCKSIZE(r10) /* get cache block size */ li r9,0 diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index d767e39d5645..72b7bb34fade 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -19,6 +19,8 @@ #define FUNCTION_DESCR_SIZE 0 #endif +#define CTX_NIA(ctx) ((unsigned long)ctx->idx * 4) + #define PLANT_INSTR(d, idx, instr) \ do { if (d) { (d)[idx] = instr; } idx++; } while (0) #define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) @@ -26,7 +28,7 @@ /* Long jump; (unconditional 'branch') */ #define PPC_JMP(dest) \ do { \ - long offset = (long)(dest) - (ctx->idx * 4); \ + long offset = (long)(dest) - CTX_NIA(ctx); \ if ((dest) != 0 && !is_offset_in_branch_range(offset)) { \ pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ return -ERANGE; \ @@ -40,7 +42,7 @@ /* "cond" here covers BO:BI fields. */ #define PPC_BCC_SHORT(cond, dest) \ do { \ - long offset = (long)(dest) - (ctx->idx * 4); \ + long offset = (long)(dest) - CTX_NIA(ctx); \ if ((dest) != 0 && !is_offset_in_cond_branch_range(offset)) { \ pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ return -ERANGE; \ @@ -92,12 +94,12 @@ * state. */ #define PPC_BCC(cond, dest) do { \ - if (is_offset_in_cond_branch_range((long)(dest) - (ctx->idx * 4))) { \ + if (is_offset_in_cond_branch_range((long)(dest) - CTX_NIA(ctx))) { \ PPC_BCC_SHORT(cond, dest); \ EMIT(PPC_RAW_NOP()); \ } else { \ /* Flip the 'T or F' bit to invert comparison */ \ - PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \ + PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, CTX_NIA(ctx) + 2*4); \ PPC_JMP(dest); \ } } while(0) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 8dd3cabaa83a..0f8048f6dad6 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -126,8 +126,10 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) { int i; +#ifndef CONFIG_PPC_KERNEL_PCREL if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc))); +#endif /* * Initialize tail_call_cnt if we do tail calls. @@ -208,16 +210,32 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u if (WARN_ON_ONCE(!core_kernel_text(func_addr))) return -EINVAL; - reladdr = func_addr - kernel_toc_addr(); - if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { - pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func); - return -ERANGE; - } + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { + reladdr = func_addr - CTX_NIA(ctx); - EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr))); - EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr))); - EMIT(PPC_RAW_MTCTR(_R12)); - EMIT(PPC_RAW_BCTRL()); + if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) { + pr_err("eBPF: address of %ps out of range of pcrel address.\n", + (void *)func); + return -ERANGE; + } + /* pla r12,addr */ + EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr)); + EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr)); + EMIT(PPC_RAW_MTCTR(_R12)); + EMIT(PPC_RAW_BCTR()); + + } else { + reladdr = func_addr - kernel_toc_addr(); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func); + return -ERANGE; + } + + EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr))); + EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr))); + EMIT(PPC_RAW_MTCTR(_R12)); + EMIT(PPC_RAW_BCTRL()); + } return 0; } diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 1ff0d2818da6..45fd975ef521 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -181,6 +181,7 @@ config POWER10_CPU depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER select PPC_HAVE_PREFIXED_SUPPORT + select PPC_HAVE_PCREL_SUPPORT config E5500_CPU bool "Freescale e5500" @@ -471,6 +472,20 @@ config PPC_KERNEL_PREFIXED Kernel support for prefixed instructions in applications and guests is not affected by this option. +config PPC_KERNEL_PCREL + depends on PPC_HAVE_PCREL_SUPPORT + depends on PPC_HAVE_PREFIXED_SUPPORT + depends on CC_HAS_PCREL + default n + select PPC_KERNEL_PREFIXED + bool "Build Kernel with PC-Relative addressing model" + help + POWER10 and later CPUs support pc relative addressing. Recent + compilers have support for an ELF ABI extension for a pc relative + ABI. + + This option builds the kernel with the pc relative ABI model. + config PPC_KUEP bool "Kernel Userspace Execution Prevention" if !40x default y if !40x @@ -510,6 +525,9 @@ config PPC_HAVE_PMU_SUPPORT config PPC_HAVE_PREFIXED_SUPPORT bool +config PPC_HAVE_PCREL_SUPPORT + bool + config PMU_SYSFS bool "Create PMU SPRs sysfs file" default n diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index e753a6bd4888..728d3c257e4a 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2634,7 +2634,9 @@ static void dump_one_paca(int cpu) DUMP(p, lock_token, "%#-*x"); DUMP(p, paca_index, "%#-*x"); +#ifndef CONFIG_PPC_KERNEL_PCREL DUMP(p, kernel_toc, "%#-*llx"); +#endif DUMP(p, kernelbase, "%#-*llx"); DUMP(p, kernel_msr, "%#-*llx"); DUMP(p, emergency_sp, "%-*px"); -- GitLab From 77e69ee7ce0715c39b9a0cde68ff44fe467435ef Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sat, 8 Apr 2023 12:17:52 +1000 Subject: [PATCH 3455/5631] powerpc/64: modules support building with PCREL addresing Build modules using PCREL addressing when CONFIG_PPC_KERNEL_PCREL=y. - The module loader must handle several new relocation types: * R_PPC64_REL24_NOTOC is a function call handled like R_PPC_REL24, but does not restore r2 upon return. The external function call stub is changed to use pcrel addressing to load the function pointer rather than based on the module TOC. * R_PPC64_GOT_PCREL34 is a reference to external data. A GOT table must be built by hand, because the linker adds this during the final link (which is not done for kernel modules). The GOT table is built similarly to the way the external function call stub table is. This section is called .mygot because .got has a special meaning for the linker and can become upset. * R_PPC64_PCREL34 is used for local data addressing, but there is a special case where the percpu section is moved at load-time to the percpu area which is out of range of this relocation. This requires the PCREL34 relocations are converted to use GOT_PCREL34 addressing. Signed-off-by: Nicholas Piggin [mpe: Some coding style & formatting fixups] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230408021752.862660-7-npiggin@gmail.com --- arch/powerpc/Makefile | 5 +- arch/powerpc/include/asm/module.h | 10 +- arch/powerpc/include/asm/ppc_asm.h | 6 +- arch/powerpc/include/uapi/asm/elf.h | 4 + arch/powerpc/kernel/module_64.c | 319 +++++++++++++++++++++++++--- 5 files changed, 309 insertions(+), 35 deletions(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 0297ad9a4ffb..5f47f2ce7cc3 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -107,9 +107,7 @@ LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) += -z notext LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) ifdef CONFIG_PPC64 -ifdef CONFIG_PPC_KERNEL_PCREL - KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-pcrel) -endif +ifndef CONFIG_PPC_KERNEL_PCREL ifeq ($(call cc-option-yn,-mcmodel=medium),y) # -mcmodel=medium breaks modules because it uses 32bit offsets from # the TOC pointer to create pointers where possible. Pointers into the @@ -124,6 +122,7 @@ else export NO_MINIMAL_TOC := -mno-minimal-toc endif endif +endif CFLAGS-$(CONFIG_PPC64) := $(call cc-option,-mtraceback=no) ifdef CONFIG_PPC64_ELF_ABI_V2 diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index 09e2ffd360bb..ac53606c2594 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -27,8 +27,13 @@ struct ppc_plt_entry { struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ +#ifdef CONFIG_PPC_KERNEL_PCREL + unsigned int got_section; /* What section is the GOT? */ + unsigned int pcpu_section; /* .data..percpu section */ +#else unsigned int toc_section; /* What section is the TOC? */ bool toc_fixed; /* Have we fixed up .TOC.? */ +#endif /* For module function descriptor dereference */ unsigned long start_opd; @@ -52,12 +57,15 @@ struct mod_arch_specific { /* * Select ELF headers. - * Make empty section for module_frob_arch_sections to expand. + * Make empty sections for module_frob_arch_sections to expand. */ #ifdef __powerpc64__ # ifdef MODULE asm(".section .stubs,\"ax\",@nobits; .align 3; .previous"); +# ifdef CONFIG_PPC_KERNEL_PCREL + asm(".section .mygot,\"a\",@nobits; .align 3; .previous"); +# endif # endif #else # ifdef MODULE diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 4dfabf4ef966..5f05a984b103 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -183,7 +183,7 @@ /* * Used to name C functions called from asm */ -#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#ifdef CONFIG_PPC_KERNEL_PCREL #define CFUNC(name) name@notoc #else #define CFUNC(name) name @@ -216,7 +216,7 @@ .globl name; \ name: -#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#ifdef CONFIG_PPC_KERNEL_PCREL #define _GLOBAL_TOC _GLOBAL #else #define _GLOBAL_TOC(name) \ @@ -379,7 +379,7 @@ GLUE(.,name): ori reg, reg, (expr)@l; \ rldimi reg, tmp, 32, 0 -#if defined(CONFIG_PPC_KERNEL_PCREL) && !defined(MODULE) +#ifdef CONFIG_PPC_KERNEL_PCREL #define LOAD_REG_ADDR(reg,name) \ pla reg,name@pcrel diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 308857123a08..dbc4a5b8d02d 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -279,8 +279,12 @@ typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG]; #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_REL24_NOTOC 116 #define R_PPC64_ENTRY 118 +#define R_PPC64_PCREL34 132 +#define R_PPC64_GOT_PCREL34 133 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 0fc04abac3bd..92570289ce08 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -114,20 +114,32 @@ struct ppc64_stub_entry { func_desc_t funcdata; } __aligned(8); +struct ppc64_got_entry { + u64 addr; +}; + /* * PPC64 uses 24 bit jumps, but we need to jump into other modules or * the kernel which may be further. So we jump to a stub. * - * For ELFv1 we need to use this to set up the new r2 value (aka TOC - * pointer). For ELFv2 it's the callee's responsibility to set up the - * new r2, but for both we need to save the old r2. + * Target address and TOC are loaded from function descriptor in the + * ppc64_stub_entry. + * + * r12 is used to generate the target address, which is required for the + * ELFv2 global entry point calling convention. * - * We could simply patch the new r2 value and function pointer into - * the stub, but it's significantly shorter to put these values at the - * end of the stub code, and patch the stub address (32-bits relative - * to the TOC ptr, r2) into the stub. + * TOC handling: + * - PCREL does not have a TOC. + * - ELFv2 non-PCREL just has to save r2, the callee is responsible for + * setting its own TOC pointer at the global entry address. + * - ELFv1 must load the new TOC pointer from the function descriptor. */ static u32 ppc64_stub_insns[] = { +#ifdef CONFIG_PPC_KERNEL_PCREL + /* pld r12,addr */ + PPC_PREFIX_8LS | __PPC_PRFX_R(1), + PPC_INST_PLD | ___PPC_RT(_R12), +#else PPC_RAW_ADDIS(_R11, _R2, 0), PPC_RAW_ADDI(_R11, _R11, 0), /* Save current r2 value in magic place on the stack. */ @@ -136,14 +148,18 @@ static u32 ppc64_stub_insns[] = { #ifdef CONFIG_PPC64_ELF_ABI_V1 /* Set up new r2 from function descriptor */ PPC_RAW_LD(_R2, _R11, 40), +#endif #endif PPC_RAW_MTCTR(_R12), PPC_RAW_BCTR(), }; -/* Count how many different 24-bit relocations (different symbol, - different addend) */ -static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num) +/* + * Count how many different r_type relocations (different symbol, + * different addend). + */ +static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num, + unsigned long r_type) { unsigned int i, r_info, r_addend, _count_relocs; @@ -152,8 +168,8 @@ static unsigned int count_relocs(const Elf64_Rela *rela, unsigned int num) r_info = 0; r_addend = 0; for (i = 0; i < num; i++) - /* Only count 24-bit relocs, others don't need stubs */ - if (ELF64_R_TYPE(rela[i].r_info) == R_PPC_REL24 && + /* Only count r_type relocs, others don't need stubs */ + if (ELF64_R_TYPE(rela[i].r_info) == r_type && (r_info != ELF64_R_SYM(rela[i].r_info) || r_addend != rela[i].r_addend)) { _count_relocs++; @@ -214,7 +230,14 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, relocs += count_relocs((void *)sechdrs[i].sh_addr, sechdrs[i].sh_size - / sizeof(Elf64_Rela)); + / sizeof(Elf64_Rela), + R_PPC_REL24); +#ifdef CONFIG_PPC_KERNEL_PCREL + relocs += count_relocs((void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size + / sizeof(Elf64_Rela), + R_PPC64_REL24_NOTOC); +#endif } } @@ -231,6 +254,95 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, return relocs * sizeof(struct ppc64_stub_entry); } +#ifdef CONFIG_PPC_KERNEL_PCREL +static int count_pcpu_relocs(const Elf64_Shdr *sechdrs, + const Elf64_Rela *rela, unsigned int num, + unsigned int symindex, unsigned int pcpu) +{ + unsigned int i, r_info, r_addend, _count_relocs; + + _count_relocs = 0; + r_info = 0; + r_addend = 0; + + for (i = 0; i < num; i++) { + Elf64_Sym *sym; + + /* This is the symbol it is referring to */ + sym = (Elf64_Sym *)sechdrs[symindex].sh_addr + + ELF64_R_SYM(rela[i].r_info); + + if (sym->st_shndx == pcpu && + (r_info != ELF64_R_SYM(rela[i].r_info) || + r_addend != rela[i].r_addend)) { + _count_relocs++; + r_info = ELF64_R_SYM(rela[i].r_info); + r_addend = rela[i].r_addend; + } + } + + return _count_relocs; +} + +/* Get size of potential GOT required. */ +static unsigned long get_got_size(const Elf64_Ehdr *hdr, + const Elf64_Shdr *sechdrs, + struct module *me) +{ + /* One extra reloc so it's always 0-addr terminated */ + unsigned long relocs = 1; + unsigned int i, symindex = 0; + + for (i = 1; i < hdr->e_shnum; i++) { + if (sechdrs[i].sh_type == SHT_SYMTAB) { + symindex = i; + break; + } + } + WARN_ON_ONCE(!symindex); + + /* Every relocated section... */ + for (i = 1; i < hdr->e_shnum; i++) { + if (sechdrs[i].sh_type == SHT_RELA) { + pr_debug("Found relocations in section %u\n", i); + pr_debug("Ptr: %p. Number: %llu\n", (void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size / sizeof(Elf64_Rela)); + + /* + * Sort the relocation information based on a symbol and + * addend key. This is a stable O(n*log n) complexity + * algorithm but it will reduce the complexity of + * count_relocs() to linear complexity O(n) + */ + sort((void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size / sizeof(Elf64_Rela), + sizeof(Elf64_Rela), relacmp, NULL); + + relocs += count_relocs((void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size + / sizeof(Elf64_Rela), + R_PPC64_GOT_PCREL34); + + /* + * Percpu data access typically gets linked with + * REL34 relocations, but the percpu section gets + * moved at load time and requires that to be + * converted to GOT linkage. + */ + if (IS_ENABLED(CONFIG_SMP) && symindex) + relocs += count_pcpu_relocs(sechdrs, + (void *)sechdrs[i].sh_addr, + sechdrs[i].sh_size + / sizeof(Elf64_Rela), + symindex, me->arch.pcpu_section); + } + } + + pr_debug("Looks like a total of %lu GOT entries, max\n", relocs); + return relocs * sizeof(struct ppc64_got_entry); +} +#else /* CONFIG_PPC_KERNEL_PCREL */ + /* Still needed for ELFv2, for .TOC. */ static void dedotify_versions(struct modversion_info *vers, unsigned long size) @@ -280,6 +392,7 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, } return NULL; } +#endif /* CONFIG_PPC_KERNEL_PCREL */ bool module_init_section(const char *name) { @@ -298,6 +411,15 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, for (i = 1; i < hdr->e_shnum; i++) { if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) me->arch.stubs_section = i; +#ifdef CONFIG_PPC_KERNEL_PCREL + else if (strcmp(secstrings + sechdrs[i].sh_name, ".data..percpu") == 0) + me->arch.pcpu_section = i; + else if (strcmp(secstrings + sechdrs[i].sh_name, ".mygot") == 0) { + me->arch.got_section = i; + if (sechdrs[i].sh_addralign < 8) + sechdrs[i].sh_addralign = 8; + } +#else else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) { me->arch.toc_section = i; if (sechdrs[i].sh_addralign < 8) @@ -312,6 +434,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, sechdrs[i].sh_size / sizeof(Elf64_Sym), (void *)hdr + sechdrs[sechdrs[i].sh_link].sh_offset); +#endif } if (!me->arch.stubs_section) { @@ -319,15 +442,26 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, return -ENOEXEC; } +#ifdef CONFIG_PPC_KERNEL_PCREL + if (!me->arch.got_section) { + pr_err("%s: doesn't contain .mygot.\n", me->name); + return -ENOEXEC; + } + + /* Override the got size */ + sechdrs[me->arch.got_section].sh_size = get_got_size(hdr, sechdrs, me); +#else /* If we don't have a .toc, just use .stubs. We need to set r2 to some reasonable value in case the module calls out to other functions via a stub, or if a function pointer escapes the module by some means. */ if (!me->arch.toc_section) me->arch.toc_section = me->arch.stubs_section; +#endif /* Override the stubs size */ sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs); + return 0; } @@ -445,7 +579,11 @@ static bool is_mprofile_ftrace_call(const char *name) */ static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me) { +#ifndef CONFIG_PPC_KERNEL_PCREL return (sechdrs[me->arch.toc_section].sh_addr & ~0xfful) + 0x8000; +#else + return -1; +#endif } /* Patch stub to reference function and correct r2 value. */ @@ -462,28 +600,53 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, if (is_mprofile_ftrace_call(name)) return create_ftrace_stub(entry, addr, me); + if ((unsigned long)entry->jump % 8 != 0) { + pr_err("%s: Address of stub entry is not 8-byte aligned\n", me->name); + return 0; + } + + BUILD_BUG_ON(sizeof(ppc64_stub_insns) > sizeof(entry->jump)); for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { if (patch_instruction(&entry->jump[i], ppc_inst(ppc64_stub_insns[i]))) return 0; } - /* Stub uses address relative to r2. */ - reladdr = (unsigned long)entry - my_r2(sechdrs, me); - if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { - pr_err("%s: Address %p of stub out of range of %p.\n", - me->name, (void *)reladdr, (void *)my_r2); - return 0; - } - pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr); + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { + /* Stub uses address relative to itself! */ + reladdr = 0 + offsetof(struct ppc64_stub_entry, funcdata); + BUILD_BUG_ON(reladdr != 32); + if (reladdr > 0x1FFFFFFFFL || reladdr < -0x200000000L) { + pr_err("%s: Address of %p out of range of 34-bit relative address.\n", + me->name, (void *)reladdr); + return 0; + } + pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr); - if (patch_instruction(&entry->jump[0], - ppc_inst(entry->jump[0] | PPC_HA(reladdr)))) - return 0; + /* May not even need this if we're relative to 0 */ + if (patch_instruction(&entry->jump[0], + ppc_inst_prefix(entry->jump[0] | IMM_H18(reladdr), + entry->jump[1] | IMM_L(reladdr)))) + return 0; - if (patch_instruction(&entry->jump[1], - ppc_inst(entry->jump[1] | PPC_LO(reladdr)))) - return 0; + } else { + /* Stub uses address relative to r2. */ + reladdr = (unsigned long)entry - my_r2(sechdrs, me); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("%s: Address %p of stub out of range of %p.\n", + me->name, (void *)reladdr, (void *)my_r2); + return 0; + } + pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr); + + if (patch_instruction(&entry->jump[0], + ppc_inst(entry->jump[0] | PPC_HA(reladdr)))) + return 0; + + if (patch_instruction(&entry->jump[1], + ppc_inst(entry->jump[1] | PPC_LO(reladdr)))) + return 0; + } // func_desc_t is 8 bytes if ABIv2, else 16 bytes desc = func_desc(addr); @@ -527,6 +690,37 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs, return (unsigned long)&stubs[i]; } +#ifdef CONFIG_PPC_KERNEL_PCREL +/* Create GOT to load the location described in this ptr */ +static unsigned long got_for_addr(const Elf64_Shdr *sechdrs, + unsigned long addr, + struct module *me, + const char *name) +{ + struct ppc64_got_entry *got; + unsigned int i, num_got; + + if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) + return addr; + + num_got = sechdrs[me->arch.got_section].sh_size / sizeof(*got); + + /* Find this stub, or if that fails, the next avail. entry */ + got = (void *)sechdrs[me->arch.got_section].sh_addr; + for (i = 0; got[i].addr; i++) { + if (WARN_ON(i >= num_got)) + return 0; + + if (got[i].addr == addr) + return (unsigned long)&got[i]; + } + + got[i].addr = addr; + + return (unsigned long)&got[i]; +} +#endif + /* We expect a noop next: if it is, replace it with instruction to restore r2. */ static int restore_r2(const char *name, u32 *instruction, struct module *me) @@ -534,6 +728,9 @@ static int restore_r2(const char *name, u32 *instruction, struct module *me) u32 *prev_insn = instruction - 1; u32 insn_val = *instruction; + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) + return 0; + if (is_mprofile_ftrace_call(name)) return 0; @@ -579,6 +776,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, pr_debug("Applying ADD relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); +#ifndef CONFIG_PPC_KERNEL_PCREL /* First time we're called, we can fix up .TOC. */ if (!me->arch.toc_fixed) { sym = find_dot_toc(sechdrs, strtab, symindex); @@ -588,7 +786,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, sym->st_value = my_r2(sechdrs, me); me->arch.toc_fixed = true; } - +#endif for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr @@ -616,6 +814,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *(unsigned long *)location = value; break; +#ifndef CONFIG_PPC_KERNEL_PCREL case R_PPC64_TOC: *(unsigned long *)location = my_r2(sechdrs, me); break; @@ -675,8 +874,13 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, = (*((uint16_t *) location) & ~0xffff) | (value & 0xffff); break; +#endif case R_PPC_REL24: +#ifdef CONFIG_PPC_KERNEL_PCREL + /* PCREL still generates REL24 for mcount */ + case R_PPC64_REL24_NOTOC: +#endif /* FIXME: Handle weak symbols here --RR */ if (sym->st_shndx == SHN_UNDEF || sym->st_shndx == SHN_LIVEPATCH) { @@ -724,6 +928,47 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, *(u32 *)location = value; break; +#ifdef CONFIG_PPC_KERNEL_PCREL + case R_PPC64_PCREL34: { + unsigned long absvalue = value; + + /* Convert value to relative */ + value -= (unsigned long)location; + + if (value + 0x200000000 > 0x3ffffffff) { + if (sym->st_shndx != me->arch.pcpu_section) { + pr_err("%s: REL34 %li out of range!\n", + me->name, (long)value); + return -ENOEXEC; + } + + /* + * per-cpu section is special cased because + * it is moved during loading, so has to be + * converted to use GOT. + */ + value = got_for_addr(sechdrs, absvalue, me, + strtab + sym->st_name); + if (!value) + return -ENOENT; + value -= (unsigned long)location; + + /* Turn pla into pld */ + if (patch_instruction((u32 *)location, + ppc_inst_prefix((*(u32 *)location & ~0x02000000), + (*((u32 *)location + 1) & ~0xf8000000) | 0xe4000000))) + return -EFAULT; + } + + if (patch_instruction((u32 *)location, + ppc_inst_prefix((*(u32 *)location & ~0x3ffff) | IMM_H18(value), + (*((u32 *)location + 1) & ~0xffff) | IMM_L(value)))) + return -EFAULT; + + break; + } + +#else case R_PPC64_TOCSAVE: /* * Marker reloc indicates we don't have to save r2. @@ -731,8 +976,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, * it. */ break; +#endif case R_PPC64_ENTRY: + if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) + break; + /* * Optimize ELFv2 large code model entry point if * the TOC is within 2GB range of current location. @@ -775,6 +1024,20 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, | (value & 0xffff); break; +#ifdef CONFIG_PPC_KERNEL_PCREL + case R_PPC64_GOT_PCREL34: + value = got_for_addr(sechdrs, value, me, + strtab + sym->st_name); + if (!value) + return -ENOENT; + value -= (unsigned long)location; + ((uint32_t *)location)[0] = (((uint32_t *)location)[0] & ~0x3ffff) | + ((value >> 16) & 0x3ffff); + ((uint32_t *)location)[1] = (((uint32_t *)location)[1] & ~0xffff) | + (value & 0xffff); + break; +#endif + default: pr_err("%s: Unknown ADD relocation: %lu\n", me->name, -- GitLab From 92cb1eff88a67e95daaf39eccf777272e85398c6 Mon Sep 17 00:00:00 2001 From: Joel Stanley Date: Wed, 5 Apr 2023 14:23:16 +0930 Subject: [PATCH 3456/5631] powerpc: Remove duplicate SPRN_HSRR definitions There are two copies of these defines. Keep the older ones as they have associated bit definitions. Signed-off-by: Joel Stanley Signed-off-by: Michael Ellerman Link: https://msgid.link/20230405045316.95003-1-joel@jms.id.au --- arch/powerpc/include/asm/reg.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 077439421892..6372e5f55ef0 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -382,8 +382,6 @@ #define SPRN_HIOR 0x137 /* 970 Hypervisor interrupt offset */ #define SPRN_RMOR 0x138 /* Real mode offset register */ #define SPRN_HRMOR 0x139 /* Real mode offset register */ -#define SPRN_HSRR0 0x13A /* Hypervisor Save/Restore 0 */ -#define SPRN_HSRR1 0x13B /* Hypervisor Save/Restore 1 */ #define SPRN_ASDR 0x330 /* Access segment descriptor register */ #define SPRN_IC 0x350 /* Virtual Instruction Count */ #define SPRN_VTB 0x351 /* Virtual Time Base */ -- GitLab From 15f0c2601e141e3c01c8dc3368b81181bc1c9228 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:14 +1000 Subject: [PATCH 3457/5631] selftests/powerpc/dscr: Correct typos Correct a couple of typos while working on other improvements to the DSCR tests. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-2-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c | 4 ++-- tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c | 4 ++-- tools/testing/selftests/powerpc/dscr/dscr_user_test.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c index 32fcf2b324b1..5659d98cf340 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c @@ -7,8 +7,8 @@ * privilege state SPR and the problem state SPR for this purpose. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * diff --git a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c index f9dfd3d3c2d5..68ce328e813e 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_inherit_test.c @@ -7,8 +7,8 @@ * value using mfspr. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * diff --git a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c index e09072446dd3..67bb872a246a 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_user_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_user_test.c @@ -8,8 +8,8 @@ * numbers. * * When using the privilege state SPR, the instructions such as - * mfspr or mtspr are priviledged and the kernel emulates them - * for us. Instructions using problem state SPR can be exuecuted + * mfspr or mtspr are privileged and the kernel emulates them + * for us. Instructions using problem state SPR can be executed * directly without any emulation if the HW supports them. Else * they also get emulated by the kernel. * -- GitLab From c97b2fc6627e1c26a3a84633e135322918a1e592 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:15 +1000 Subject: [PATCH 3458/5631] selftests/powerpc: Move bind_to_cpu() to utils.h This function will be useful in the DSCR test patches later in this series, so promote it to be shared by all powerpc selftests. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-3-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/include/utils.h | 1 + tools/testing/selftests/powerpc/pmu/lib.c | 13 ------------- tools/testing/selftests/powerpc/pmu/lib.h | 1 - tools/testing/selftests/powerpc/utils.c | 12 ++++++++++++ 4 files changed, 13 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index eed7dd7582b2..d3589e16a20f 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -32,6 +32,7 @@ void *find_auxv_entry(int type, char *auxv); void *get_auxv_entry(int type); int pick_online_cpu(void); +int bind_to_cpu(int cpu); int parse_intmax(const char *buffer, size_t count, intmax_t *result, int base); int parse_uintmax(const char *buffer, size_t count, uintmax_t *result, int base); diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 719f94f10d41..144f90a78d69 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -14,19 +14,6 @@ #include "utils.h" #include "lib.h" - -int bind_to_cpu(int cpu) -{ - cpu_set_t mask; - - printf("Binding to cpu %d\n", cpu); - - CPU_ZERO(&mask); - CPU_SET(cpu, &mask); - - return sched_setaffinity(0, sizeof(mask), &mask); -} - #define PARENT_TOKEN 0xAA #define CHILD_TOKEN 0x55 diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h index bf1bec013bbb..1d62403ae6ea 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.h +++ b/tools/testing/selftests/powerpc/pmu/lib.h @@ -20,7 +20,6 @@ union pipe { int fds[2]; }; -extern int bind_to_cpu(int cpu); extern int kill_child_and_wait(pid_t child_pid); extern int wait_for_child(pid_t child_pid); extern int sync_with_child(union pipe read_pipe, union pipe write_pipe); diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 7c8cfedb012a..cdb996dba703 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -452,6 +452,18 @@ int pick_online_cpu(void) return cpu; } +int bind_to_cpu(int cpu) +{ + cpu_set_t mask; + + printf("Binding to cpu %d\n", cpu); + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + + return sched_setaffinity(0, sizeof(mask), &mask); +} + bool is_ppc64le(void) { struct utsname uts; -- GitLab From 6ff4dc25483f3f49d1db48af28d4c485fc77bd21 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:16 +1000 Subject: [PATCH 3459/5631] selftests/powerpc: Allow bind_to_cpu() to automatically pick CPU All current users of bind_to_cpu() don't care _which_ CPU they get, just that they are bound to a single free one. So alter the interface to 1. Accept a BIND_CPU_ANY value that tells it to automatically pick a CPU 2. Return the picked CPU And convert all these users to bind_to_cpu(BIND_CPU_ANY). Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-4-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/include/utils.h | 2 ++ .../powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c | 3 +-- .../powerpc/pmu/ebb/cpu_event_vs_ebb_test.c | 3 +-- .../powerpc/pmu/ebb/ebb_vs_cpu_event_test.c | 3 +-- .../powerpc/pmu/ebb/multi_ebb_procs_test.c | 6 ++---- tools/testing/selftests/powerpc/pmu/lib.c | 6 ++---- tools/testing/selftests/powerpc/utils.c | 13 ++++++++++++- 7 files changed, 21 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index d3589e16a20f..44bfd48b93d6 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -31,6 +31,8 @@ int read_auxv(char *buf, ssize_t buf_size); void *find_auxv_entry(int type, char *auxv); void *get_auxv_entry(int type); +#define BIND_CPU_ANY (-1) + int pick_online_cpu(void); int bind_to_cpu(int cpu); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c index 3cd33eb51e5e..fab7f34d7ce1 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c @@ -45,9 +45,8 @@ int cpu_event_pinned_vs_ebb(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c index 8466ef9d7de8..7c54c262036e 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c @@ -43,9 +43,8 @@ int cpu_event_vs_ebb(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c index 4d822cb3589c..d7064b54c64f 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c @@ -43,9 +43,8 @@ int ebb_vs_cpu_event(void) SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); + cpu = bind_to_cpu(BIND_CPU_ANY); FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); FAIL_IF(pipe(read_pipe.fds) == -1); FAIL_IF(pipe(write_pipe.fds) == -1); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c index 9b0f70d59702..4ac22b2e774f 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c @@ -75,13 +75,11 @@ static int cycles_child(void) int multi_ebb_procs(void) { pid_t pids[NR_CHILDREN]; - int cpu, rc, i; + int rc, i; SKIP_IF(!ebb_is_supported()); - cpu = pick_online_cpu(); - FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); for (i = 0; i < NR_CHILDREN; i++) { pids[i] = fork(); diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 144f90a78d69..321357987408 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -103,12 +103,10 @@ static int eat_cpu_child(union pipe read_pipe, union pipe write_pipe) pid_t eat_cpu(int (test_function)(void)) { union pipe read_pipe, write_pipe; - int cpu, rc; + int rc; pid_t pid; - cpu = pick_online_cpu(); - FAIL_IF(cpu < 0); - FAIL_IF(bind_to_cpu(cpu)); + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); if (pipe(read_pipe.fds) == -1) return -1; diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index cdb996dba703..252fb4a95e90 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -455,13 +455,24 @@ int pick_online_cpu(void) int bind_to_cpu(int cpu) { cpu_set_t mask; + int err; + + if (cpu == BIND_CPU_ANY) { + cpu = pick_online_cpu(); + if (cpu < 0) + return cpu; + } printf("Binding to cpu %d\n", cpu); CPU_ZERO(&mask); CPU_SET(cpu, &mask); - return sched_setaffinity(0, sizeof(mask), &mask); + err = sched_setaffinity(0, sizeof(mask), &mask); + if (err) + return err; + + return cpu; } bool is_ppc64le(void) -- GitLab From fda8158870063b99b88a0904bbb95188973b4297 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:17 +1000 Subject: [PATCH 3460/5631] selftests/powerpc/dscr: Add lockstep test cases to DSCR explicit tests Add new cases to the relevant tests that use explicitly synchronized threads to test the behaviour across context switches with less randomness. By locking the participants to the same CPU we guarantee a context switch occurs each time they make progress, which is a likely failure point if the kernel is not tracking the thread local DSCR correctly. The random case is left in to keep exercising potential edge cases. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-5-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/dscr/Makefile | 1 + .../powerpc/dscr/dscr_default_test.c | 87 ++++++++++++++++--- .../powerpc/dscr/dscr_explicit_test.c | 85 +++++++++++++++++- 3 files changed, 159 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index 845db6273a1b..b29a8863a734 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -9,5 +9,6 @@ top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/dscr_default_test: LDLIBS += -lpthread +$(OUTPUT)/dscr_explicit_test: LDLIBS += -lpthread $(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c index e76611e608af..18e533d46c9a 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c @@ -9,8 +9,66 @@ * Copyright 2012, Anton Blanchard, IBM Corporation. * Copyright 2015, Anshuman Khandual, IBM Corporation. */ + +#define _GNU_SOURCE + #include "dscr.h" +#include +#include +#include + +static void *dscr_default_lockstep_writer(void *arg) +{ + sem_t *reader_sem = (sem_t *)arg; + sem_t *writer_sem = (sem_t *)arg + 1; + unsigned long expected_dscr = 0; + + for (int i = 0; i < COUNT; i++) { + FAIL_IF_EXIT(sem_wait(writer_sem)); + + set_default_dscr(expected_dscr); + expected_dscr = (expected_dscr + 1) % DSCR_MAX; + + FAIL_IF_EXIT(sem_post(reader_sem)); + } + + return NULL; +} + +int dscr_default_lockstep_test(void) +{ + pthread_t writer; + sem_t rw_semaphores[2]; + sem_t *reader_sem = &rw_semaphores[0]; + sem_t *writer_sem = &rw_semaphores[1]; + unsigned long expected_dscr = 0; + + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + + FAIL_IF(sem_init(reader_sem, 0, 0)); + FAIL_IF(sem_init(writer_sem, 0, 1)); /* writer starts first */ + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); + FAIL_IF(pthread_create(&writer, NULL, dscr_default_lockstep_writer, (void *)rw_semaphores)); + + for (int i = 0; i < COUNT ; i++) { + FAIL_IF(sem_wait(reader_sem)); + + FAIL_IF(get_dscr() != expected_dscr); + FAIL_IF(get_dscr_usr() != expected_dscr); + + expected_dscr = (expected_dscr + 1) % DSCR_MAX; + + FAIL_IF(sem_post(writer_sem)); + } + + FAIL_IF(pthread_join(writer, NULL)); + FAIL_IF(sem_destroy(reader_sem)); + FAIL_IF(sem_destroy(writer_sem)); + + return 0; +} + static unsigned long dscr; /* System DSCR default */ static unsigned long sequence; static unsigned long result[THREADS]; @@ -57,16 +115,13 @@ static void *do_test(void *in) pthread_exit(&result[thread]); } -int dscr_default(void) +int dscr_default_random_test(void) { pthread_t threads[THREADS]; unsigned long i, *status[THREADS]; - unsigned long orig_dscr_default; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); - orig_dscr_default = get_default_dscr(); - /* Initial DSCR default */ dscr = 1; set_default_dscr(dscr); @@ -75,7 +130,7 @@ int dscr_default(void) for (i = 0; i < THREADS; i++) { if (pthread_create(&threads[i], NULL, do_test, (void *)i)) { perror("pthread_create() failed"); - goto fail; + return 1; } } @@ -104,23 +159,31 @@ int dscr_default(void) for (i = 0; i < THREADS; i++) { if (pthread_join(threads[i], (void **)&(status[i]))) { perror("pthread_join() failed"); - goto fail; + return 1; } if (*status[i]) { printf("%ldth thread failed to join with %ld status\n", i, *status[i]); - goto fail; + return 1; } } - set_default_dscr(orig_dscr_default); return 0; -fail: - set_default_dscr(orig_dscr_default); - return 1; } int main(int argc, char *argv[]) { - return test_harness(dscr_default, "dscr_default_test"); + unsigned long orig_dscr_default = 0; + int err = 0; + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + orig_dscr_default = get_default_dscr(); + + err |= test_harness(dscr_default_lockstep_test, "dscr_default_lockstep_test"); + err |= test_harness(dscr_default_random_test, "dscr_default_random_test"); + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + set_default_dscr(orig_dscr_default); + + return err; } diff --git a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c index 5659d98cf340..3b98b9a88207 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c @@ -15,9 +15,78 @@ * Copyright 2012, Anton Blanchard, IBM Corporation. * Copyright 2015, Anshuman Khandual, IBM Corporation. */ + +#define _GNU_SOURCE + #include "dscr.h" +#include "utils.h" + +#include +#include +#include + +void *dscr_explicit_lockstep_thread(void *args) +{ + sem_t *prev = (sem_t *)args; + sem_t *next = (sem_t *)args + 1; + unsigned long expected_dscr = 0; + + set_dscr(expected_dscr); + srand(gettid()); + + for (int i = 0; i < COUNT; i++) { + FAIL_IF_EXIT(sem_wait(prev)); + + FAIL_IF_EXIT(expected_dscr != get_dscr()); + FAIL_IF_EXIT(expected_dscr != get_dscr_usr()); + + expected_dscr = (expected_dscr + 1) % DSCR_MAX; + set_dscr(expected_dscr); + + FAIL_IF_EXIT(sem_post(next)); + } + + return NULL; +} + +int dscr_explicit_lockstep_test(void) +{ + pthread_t thread; + sem_t semaphores[2]; + sem_t *prev = &semaphores[1]; /* reversed prev/next than for the other thread */ + sem_t *next = &semaphores[0]; + unsigned long expected_dscr = 0; + + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + + srand(gettid()); + set_dscr(expected_dscr); + + FAIL_IF(sem_init(prev, 0, 0)); + FAIL_IF(sem_init(next, 0, 1)); /* other thread starts first */ + FAIL_IF(bind_to_cpu(BIND_CPU_ANY) < 0); + FAIL_IF(pthread_create(&thread, NULL, dscr_explicit_lockstep_thread, (void *)semaphores)); + + for (int i = 0; i < COUNT; i++) { + FAIL_IF(sem_wait(prev)); + + FAIL_IF(expected_dscr != get_dscr()); + FAIL_IF(expected_dscr != get_dscr_usr()); + + expected_dscr = (expected_dscr - 1) % DSCR_MAX; + set_dscr(expected_dscr); + + FAIL_IF(sem_post(next)); + } -int dscr_explicit(void) + FAIL_IF(pthread_join(thread, NULL)); + FAIL_IF(sem_destroy(prev)); + FAIL_IF(sem_destroy(next)); + + return 0; +} + +int dscr_explicit_random_test(void) { unsigned long i, dscr = 0; @@ -66,5 +135,17 @@ int dscr_explicit(void) int main(int argc, char *argv[]) { - return test_harness(dscr_explicit, "dscr_explicit_test"); + unsigned long orig_dscr_default = 0; + int err = 0; + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + orig_dscr_default = get_default_dscr(); + + err |= test_harness(dscr_explicit_lockstep_test, "dscr_explicit_lockstep_test"); + err |= test_harness(dscr_explicit_random_test, "dscr_explicit_random_test"); + + if (have_hwcap2(PPC_FEATURE2_DSCR)) + set_default_dscr(orig_dscr_default); + + return err; } -- GitLab From 3067b89ab62305c54ec15b00a2c4dbaf64809c59 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:18 +1000 Subject: [PATCH 3461/5631] selftests/powerpc/dscr: Improve DSCR explicit random test case The tests currently have a single writer thread updating the system DSCR with a 1/1000 chance looped only 100 times. So only around one in 10 runs actually do anything. * Add multiple threads to the dscr_explicit_random_test case. * Use a barrier to make all the threads start work as simultaneously as possible. * Use a rwlock and make all threads have a reasonable chance to write to the DSCR on each iteration. PTHREAD_RWLOCK_PREFER_WRITER_NONRECURSIVE_NP is used to prevent writers from starving while all the other threads keep reading. Logging the reads/writes shows a decent mix across the whole test. * Allow all threads a chance to write. * Make the chance of writing more likely. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-6-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/dscr/dscr.h | 4 - .../powerpc/dscr/dscr_default_test.c | 140 ++++++++---------- .../powerpc/dscr/dscr_explicit_test.c | 84 +++++++---- 3 files changed, 113 insertions(+), 115 deletions(-) diff --git a/tools/testing/selftests/powerpc/dscr/dscr.h b/tools/testing/selftests/powerpc/dscr/dscr.h index 2c54998d4715..b281659071e8 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr.h +++ b/tools/testing/selftests/powerpc/dscr/dscr.h @@ -86,8 +86,4 @@ void set_default_dscr(unsigned long val) } } -double uniform_deviate(int seed) -{ - return seed * (1.0 / (RAND_MAX + 1.0)); -} #endif /* _SELFTESTS_POWERPC_DSCR_DSCR_H */ diff --git a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c index 18e533d46c9a..60ab02525b79 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_default_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_default_test.c @@ -69,105 +69,85 @@ int dscr_default_lockstep_test(void) return 0; } -static unsigned long dscr; /* System DSCR default */ -static unsigned long sequence; -static unsigned long result[THREADS]; - -static void *do_test(void *in) +struct random_thread_args { + pthread_t thread_id; + unsigned long *expected_system_dscr; + pthread_rwlock_t *rw_lock; + pthread_barrier_t *barrier; +}; + +static void *dscr_default_random_thread(void *in) { - unsigned long thread = (unsigned long)in; - unsigned long i; - - for (i = 0; i < COUNT; i++) { - unsigned long d, cur_dscr, cur_dscr_usr; - unsigned long s1, s2; - - s1 = READ_ONCE(sequence); - if (s1 & 1) - continue; - rmb(); - - d = dscr; - cur_dscr = get_dscr(); - cur_dscr_usr = get_dscr_usr(); - - rmb(); - s2 = sequence; + struct random_thread_args *args = (struct random_thread_args *)in; + unsigned long *expected_dscr_p = args->expected_system_dscr; + pthread_rwlock_t *rw_lock = args->rw_lock; + int err; - if (s1 != s2) - continue; + srand(gettid()); - if (cur_dscr != d) { - fprintf(stderr, "thread %ld kernel DSCR should be %ld " - "but is %ld\n", thread, d, cur_dscr); - result[thread] = 1; - pthread_exit(&result[thread]); - } + err = pthread_barrier_wait(args->barrier); + FAIL_IF_EXIT(err != 0 && err != PTHREAD_BARRIER_SERIAL_THREAD); - if (cur_dscr_usr != d) { - fprintf(stderr, "thread %ld user DSCR should be %ld " - "but is %ld\n", thread, d, cur_dscr_usr); - result[thread] = 1; - pthread_exit(&result[thread]); + for (int i = 0; i < COUNT; i++) { + unsigned long expected_dscr; + unsigned long current_dscr; + unsigned long current_dscr_usr; + + FAIL_IF_EXIT(pthread_rwlock_rdlock(rw_lock)); + expected_dscr = *expected_dscr_p; + current_dscr = get_dscr(); + current_dscr_usr = get_dscr_usr(); + FAIL_IF_EXIT(pthread_rwlock_unlock(rw_lock)); + + FAIL_IF_EXIT(current_dscr != expected_dscr); + FAIL_IF_EXIT(current_dscr_usr != expected_dscr); + + if (rand() % 10 == 0) { + unsigned long next_dscr; + + FAIL_IF_EXIT(pthread_rwlock_wrlock(rw_lock)); + next_dscr = (*expected_dscr_p + 1) % DSCR_MAX; + set_default_dscr(next_dscr); + *expected_dscr_p = next_dscr; + FAIL_IF_EXIT(pthread_rwlock_unlock(rw_lock)); } } - result[thread] = 0; - pthread_exit(&result[thread]); + + pthread_exit((void *)0); } int dscr_default_random_test(void) { - pthread_t threads[THREADS]; - unsigned long i, *status[THREADS]; + struct random_thread_args threads[THREADS]; + unsigned long expected_system_dscr = 0; + pthread_rwlockattr_t rwlock_attr; + pthread_rwlock_t rw_lock; + pthread_barrier_t barrier; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); - /* Initial DSCR default */ - dscr = 1; - set_default_dscr(dscr); + FAIL_IF(pthread_rwlockattr_setkind_np(&rwlock_attr, + PTHREAD_RWLOCK_PREFER_WRITER_NONRECURSIVE_NP)); + FAIL_IF(pthread_rwlock_init(&rw_lock, &rwlock_attr)); + FAIL_IF(pthread_barrier_init(&barrier, NULL, THREADS)); - /* Spawn all testing threads */ - for (i = 0; i < THREADS; i++) { - if (pthread_create(&threads[i], NULL, do_test, (void *)i)) { - perror("pthread_create() failed"); - return 1; - } - } + set_default_dscr(expected_system_dscr); - srand(getpid()); + for (int i = 0; i < THREADS; i++) { + threads[i].expected_system_dscr = &expected_system_dscr; + threads[i].rw_lock = &rw_lock; + threads[i].barrier = &barrier; - /* Keep changing the DSCR default */ - for (i = 0; i < COUNT; i++) { - double ret = uniform_deviate(rand()); - - if (ret < 0.0001) { - sequence++; - wmb(); - - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; - - set_default_dscr(dscr); - - wmb(); - sequence++; - } + FAIL_IF(pthread_create(&threads[i].thread_id, NULL, + dscr_default_random_thread, (void *)&threads[i])); } - /* Individual testing thread exit status */ - for (i = 0; i < THREADS; i++) { - if (pthread_join(threads[i], (void **)&(status[i]))) { - perror("pthread_join() failed"); - return 1; - } + for (int i = 0; i < THREADS; i++) + FAIL_IF(pthread_join(threads[i].thread_id, NULL)); + + FAIL_IF(pthread_barrier_destroy(&barrier)); + FAIL_IF(pthread_rwlock_destroy(&rw_lock)); - if (*status[i]) { - printf("%ldth thread failed to join with %ld status\n", - i, *status[i]); - return 1; - } - } return 0; } diff --git a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c index 3b98b9a88207..e2268e9183a8 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_explicit_test.c @@ -86,50 +86,72 @@ int dscr_explicit_lockstep_test(void) return 0; } -int dscr_explicit_random_test(void) +struct random_thread_args { + pthread_t thread_id; + bool do_yields; + pthread_barrier_t *barrier; +}; + +void *dscr_explicit_random_thread(void *in) { - unsigned long i, dscr = 0; + struct random_thread_args *args = (struct random_thread_args *)in; + unsigned long expected_dscr = 0; + int err; - SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + srand(gettid()); - srand(getpid()); - set_dscr(dscr); + err = pthread_barrier_wait(args->barrier); + FAIL_IF_EXIT(err != 0 && err != PTHREAD_BARRIER_SERIAL_THREAD); - for (i = 0; i < COUNT; i++) { - unsigned long cur_dscr, cur_dscr_usr; - double ret = uniform_deviate(rand()); + for (int i = 0; i < COUNT; i++) { + expected_dscr = rand() % DSCR_MAX; + set_dscr(expected_dscr); - if (ret < 0.001) { - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; + for (int j = rand() % 5; j > 0; --j) { + FAIL_IF_EXIT(get_dscr() != expected_dscr); + FAIL_IF_EXIT(get_dscr_usr() != expected_dscr); - set_dscr(dscr); + if (args->do_yields && rand() % 2) + sched_yield(); } - cur_dscr = get_dscr(); - if (cur_dscr != dscr) { - fprintf(stderr, "Kernel DSCR should be %ld but " - "is %ld\n", dscr, cur_dscr); - return 1; - } + expected_dscr = rand() % DSCR_MAX; + set_dscr_usr(expected_dscr); - ret = uniform_deviate(rand()); - if (ret < 0.001) { - dscr++; - if (dscr > DSCR_MAX) - dscr = 0; + for (int j = rand() % 5; j > 0; --j) { + FAIL_IF_EXIT(get_dscr() != expected_dscr); + FAIL_IF_EXIT(get_dscr_usr() != expected_dscr); - set_dscr_usr(dscr); + if (args->do_yields && rand() % 2) + sched_yield(); } + } - cur_dscr_usr = get_dscr_usr(); - if (cur_dscr_usr != dscr) { - fprintf(stderr, "User DSCR should be %ld but " - "is %ld\n", dscr, cur_dscr_usr); - return 1; - } + return NULL; +} + +int dscr_explicit_random_test(void) +{ + struct random_thread_args threads[THREADS]; + pthread_barrier_t barrier; + + SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); + + FAIL_IF(pthread_barrier_init(&barrier, NULL, THREADS)); + + for (int i = 0; i < THREADS; i++) { + threads[i].do_yields = i % 2 == 0; + threads[i].barrier = &barrier; + + FAIL_IF(pthread_create(&threads[i].thread_id, NULL, + dscr_explicit_random_thread, (void *)&threads[i])); } + + for (int i = 0; i < THREADS; i++) + FAIL_IF(pthread_join(threads[i].thread_id, NULL)); + + FAIL_IF(pthread_barrier_destroy(&barrier)); + return 0; } -- GitLab From c14a9d0a79d4fb83c4e9e8cadc5cb094f41d01d0 Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:19 +1000 Subject: [PATCH 3462/5631] selftests/powerpc/dscr: Speed up DSCR sysfs tests This test case is extremely slow, taking around a minute compared to most of the other DSCR tests taking a second at most. Perf shows most time is spent by the kernel switching to each CPU it reads in /sys/devices/system/cpu. This switching is an unavoidable consequnce of reading all the .../cpuN/dscr values. Remove the outer iteration loop from this test case, reducing the reads from 1600 to 16. This still updates the DSCR 16 times and verifies on every CPU each time, so I do not expect the lower coverage to be meaningful. The speedup is significant: back down to ~1 second like the other tests. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-7-bgray@linux.ibm.com --- .../testing/selftests/powerpc/dscr/dscr_sysfs_test.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c index 4f1fef6198fc..e7cd0d6b1fad 100644 --- a/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c +++ b/tools/testing/selftests/powerpc/dscr/dscr_sysfs_test.c @@ -67,17 +67,14 @@ static int check_all_cpu_dscr_defaults(unsigned long val) int dscr_sysfs(void) { unsigned long orig_dscr_default; - int i, j; SKIP_IF(!have_hwcap2(PPC_FEATURE2_DSCR)); orig_dscr_default = get_default_dscr(); - for (i = 0; i < COUNT; i++) { - for (j = 0; j < DSCR_MAX; j++) { - set_default_dscr(j); - if (check_all_cpu_dscr_defaults(j)) - goto fail; - } + for (int i = 0; i < DSCR_MAX; i++) { + set_default_dscr(i); + if (check_all_cpu_dscr_defaults(i)) + goto fail; } set_default_dscr(orig_dscr_default); return 0; -- GitLab From ae7312c09014fceb782a92cfb934e973f08b338f Mon Sep 17 00:00:00 2001 From: Benjamin Gray Date: Thu, 6 Apr 2023 14:33:20 +1000 Subject: [PATCH 3463/5631] selftests/powerpc/dscr: Restore timeout to DSCR selftests Reducing the time taken by dscr_sysfs_test.c allows restoring the default timeout, which was removed in commit 850507f30c38 ("selftests/powerpc: Turn off timeout setting for benchmarks, dscr, signal, tm") because that test took too long. Signed-off-by: Benjamin Gray Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406043320.125138-8-bgray@linux.ibm.com --- tools/testing/selftests/powerpc/dscr/Makefile | 2 -- tools/testing/selftests/powerpc/dscr/settings | 1 - 2 files changed, 3 deletions(-) delete mode 100644 tools/testing/selftests/powerpc/dscr/settings diff --git a/tools/testing/selftests/powerpc/dscr/Makefile b/tools/testing/selftests/powerpc/dscr/Makefile index b29a8863a734..9289d5febe1e 100644 --- a/tools/testing/selftests/powerpc/dscr/Makefile +++ b/tools/testing/selftests/powerpc/dscr/Makefile @@ -3,8 +3,6 @@ TEST_GEN_PROGS := dscr_default_test dscr_explicit_test dscr_user_test \ dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test \ dscr_sysfs_thread_test -TEST_FILES := settings - top_srcdir = ../../../../.. include ../../lib.mk diff --git a/tools/testing/selftests/powerpc/dscr/settings b/tools/testing/selftests/powerpc/dscr/settings deleted file mode 100644 index e7b9417537fb..000000000000 --- a/tools/testing/selftests/powerpc/dscr/settings +++ /dev/null @@ -1 +0,0 @@ -timeout=0 -- GitLab From df9cad09493808dca7d16a2fbcac1a78e8d412af Mon Sep 17 00:00:00 2001 From: Andrew Donnellan Date: Fri, 24 Feb 2023 15:10:12 +1100 Subject: [PATCH 3464/5631] powerpc/pseries: Add FW_FEATURE_PLPKS feature flag Add a firmware feature flag, FW_FEATURE_PLPKS, to indicate availability of Platform KeyStore related hcalls. Check this flag in plpks_is_available() and pseries_plpks_init() before trying to make an hcall. Suggested-by: Michael Ellerman Signed-off-by: Andrew Donnellan Signed-off-by: Michael Ellerman Link: https://msgid.link/20230224041012.772648-1-ajd@linux.ibm.com --- arch/powerpc/include/asm/firmware.h | 4 +++- arch/powerpc/platforms/pseries/firmware.c | 1 + arch/powerpc/platforms/pseries/plpks.c | 5 ++++- 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index ed6db13a1d7c..69ae9cf57d50 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -56,6 +56,7 @@ #define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000) #define FW_FEATURE_ENERGY_SCALE_INFO ASM_CONST(0x0000040000000000) #define FW_FEATURE_WATCHDOG ASM_CONST(0x0000080000000000) +#define FW_FEATURE_PLPKS ASM_CONST(0x0000100000000000) #ifndef __ASSEMBLY__ @@ -77,7 +78,8 @@ enum { FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY | - FW_FEATURE_ENERGY_SCALE_INFO | FW_FEATURE_WATCHDOG, + FW_FEATURE_ENERGY_SCALE_INFO | FW_FEATURE_WATCHDOG | + FW_FEATURE_PLPKS, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 080108d129ed..18447e5fa17d 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -68,6 +68,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_RPT_INVALIDATE, "hcall-rpt-invalidate"}, {FW_FEATURE_ENERGY_SCALE_INFO, "hcall-energy-scale-info"}, {FW_FEATURE_WATCHDOG, "hcall-watchdog"}, + {FW_FEATURE_PLPKS, "hcall-pks"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 6f7bf3fc3aea..b0658ea3eccb 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -378,7 +378,7 @@ bool plpks_is_available(void) { int rc; - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_PLPKS)) return false; rc = _plpks_get_config(); @@ -690,6 +690,9 @@ static __init int pseries_plpks_init(void) { int rc; + if (!firmware_has_feature(FW_FEATURE_PLPKS)) + return -ENODEV; + rc = _plpks_get_config(); if (rc) { -- GitLab From da03101799579f6477feb47a3aefcdb2e2379da1 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Apr 2023 11:08:53 +1000 Subject: [PATCH 3465/5631] powerpc: drop MPC834x_MDS platform support This 2006 era Modular Development System (MDS) has, at its core component, a full length card with a PCI-64 edge. No case. Serial and network connectors were on card, so it could optionally be fitted with plastic stand-offs and run stand-alone off a power brick. Like all the MDS systems, it was meant as a vehicle to get the CPU out early to hardware OEMs so software and board development could take place in parallel. To that end, the BGA CPU was held in place with a mechanical spring loaded pressure assembly (vs. solder) so that early rev silicon could be replaced in the field. Not for COTS deployment! These were made in limited numbers and availability preference was given to partners who were planning to make their own boards, like our WR SBC8349 [since retired in v4.18 (2017, commit 3bc6cf5a86e5)] Given that the whole reason for existence was to assist in enabling new board designs [not happening for 10+ years], and that they weren't generally available, and that the hardware wasn't really hobbyist friendly even for retro computing, it makes sense to retire the support for this platform. Signed-off-by: Paul Gortmaker Acked-by: Li Yang Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220115913.25811-2-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 1 - arch/powerpc/boot/dts/mpc834x_mds.dts | 403 ------------------ .../configs/83xx/mpc834x_mds_defconfig | 58 --- arch/powerpc/configs/mpc83xx_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/83xx/Kconfig | 12 - arch/powerpc/platforms/83xx/Makefile | 1 - arch/powerpc/platforms/83xx/mpc834x_mds.c | 92 ---- 8 files changed, 569 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc834x_mds.dts delete mode 100644 arch/powerpc/configs/83xx/mpc834x_mds_defconfig delete mode 100644 arch/powerpc/platforms/83xx/mpc834x_mds.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 129a1e190f25..f701dff92cfd 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -338,7 +338,6 @@ image-$(CONFIG_MPC832x_MDS) += cuImage.mpc832x_mds image-$(CONFIG_MPC832x_RDB) += cuImage.mpc832x_rdb image-$(CONFIG_MPC834x_ITX) += cuImage.mpc8349emitx \ cuImage.mpc8349emitxgp -image-$(CONFIG_MPC834x_MDS) += cuImage.mpc834x_mds image-$(CONFIG_MPC836x_MDS) += cuImage.mpc836x_mds image-$(CONFIG_ASP834x) += dtbImage.asp834x-redboot diff --git a/arch/powerpc/boot/dts/mpc834x_mds.dts b/arch/powerpc/boot/dts/mpc834x_mds.dts deleted file mode 100644 index 6c8cb859c55f..000000000000 --- a/arch/powerpc/boot/dts/mpc834x_mds.dts +++ /dev/null @@ -1,403 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8349E MDS Device Tree Source - * - * Copyright 2005, 2006 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "MPC8349EMDS"; - compatible = "MPC8349EMDS", "MPC834xMDS", "MPC83xxMDS"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - pci1 = &pci1; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8349@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; - i-cache-size = <32768>; - timebase-frequency = <0>; // from bootloader - bus-frequency = <0>; // from bootloader - clock-frequency = <0>; // from bootloader - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x10000000>; // 256MB at 0 - }; - - bcsr@e2400000 { - compatible = "fsl,mpc8349mds-bcsr"; - reg = <0xe2400000 0x8000>; - }; - - soc8349@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <0>; - - wdt@200 { - device_type = "watchdog"; - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - spi@7000 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x7000 0x1000>; - interrupts = <16 0x8>; - interrupt-parent = <&ipic>; - mode = "cpu"; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8349-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - /* phy type (ULPI or SERIAL) are only types supported for MPH */ - /* port = 0 or 1 */ - usb@22000 { - compatible = "fsl-usb2-mph"; - reg = <0x22000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <39 0x8>; - phy_type = "ulpi"; - port0; - }; - /* phy type (ULPI, UTMI, UTMI_WIDE, SERIAL) */ - usb@23000 { - compatible = "fsl-usb2-dr"; - reg = <0x23000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <38 0x8>; - dr_mode = "otg"; - phy_type = "ulpi"; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy0>; - linux,network-index = <0>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - - phy0: ethernet-phy@0 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x0>; - }; - - phy1: ethernet-phy@1 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x1>; - }; - - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "TSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy1>; - linux,network-index = <1>; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - crypto@30000 { - compatible = "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x7e>; - fsl,descriptor-types-mask = <0x01010ebf>; - }; - - /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - ipic: pic@700 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - device_type = "ipic"; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 */ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0 0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>; - clock-frequency = <66666666>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; - - pci1: pci@e0008600 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 */ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <67 0x8>; - bus-range = <0 0>; - ranges = <0x02000000 0x0 0xb0000000 0xb0000000 0x0 0x10000000 - 0x42000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe2100000 0x0 0x00100000>; - clock-frequency = <66666666>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008600 0x100 /* internal registers */ - 0xe0008380 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; -}; diff --git a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig deleted file mode 100644 index e2ff684d8792..000000000000 --- a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig +++ /dev/null @@ -1,58 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_KALLSYMS is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y -# CONFIG_MSDOS_PARTITION is not set -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_83xx=y -CONFIG_MPC834x_MDS=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_NETDEVICES=y -CONFIG_GIANFAR=y -CONFIG_E100=y -CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_MPC=y -CONFIG_WATCHDOG=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_DS1374=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 95d43f8a3869..03f6a478d0cf 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -13,7 +13,6 @@ CONFIG_PPC_83xx=y CONFIG_MPC831x_RDB=y CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y -CONFIG_MPC834x_MDS=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index f73c98be56c8..025d2cfd06d7 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -46,7 +46,6 @@ CONFIG_PPC_83xx=y CONFIG_MPC831x_RDB=y CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y -CONFIG_MPC834x_MDS=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index bee119725f61..1ca0ba3b0f1c 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -39,18 +39,6 @@ config MPC832x_RDB help This option enables support for the MPC8323 RDB board. -config MPC834x_MDS - bool "Freescale MPC834x MDS" - select DEFAULT_UIMAGE - select PPC_MPC834x - help - This option enables support for the MPC 834x MDS evaluation board. - - Be aware that PCI buses can only function when MDS board is plugged - into the PIB (Platform IO Board) board from Freescale which provide - 3 PCI slots. The PIBs PCI initialization is the bootloader's - responsibility. - config MPC834x_ITX bool "Freescale MPC834x ITX" select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index 41cb5f842eff..5697b70492b8 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_MCU_MPC8349EMITX) += mcu_mpc8349emitx.o obj-$(CONFIG_MPC830x_RDB) += mpc830x_rdb.o obj-$(CONFIG_MPC831x_RDB) += mpc831x_rdb.o obj-$(CONFIG_MPC832x_RDB) += mpc832x_rdb.o -obj-$(CONFIG_MPC834x_MDS) += mpc834x_mds.o obj-$(CONFIG_MPC834x_ITX) += mpc834x_itx.o obj-$(CONFIG_MPC836x_MDS) += mpc836x_mds.o obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o diff --git a/arch/powerpc/platforms/83xx/mpc834x_mds.c b/arch/powerpc/platforms/83xx/mpc834x_mds.c deleted file mode 100644 index d08974a60848..000000000000 --- a/arch/powerpc/platforms/83xx/mpc834x_mds.c +++ /dev/null @@ -1,92 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/powerpc/platforms/83xx/mpc834x_mds.c - * - * MPC834x MDS board specific routines - * - * Maintainer: Kumar Gala - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "mpc83xx.h" - -#define BCSR5_INT_USB 0x02 -static int __init mpc834xemds_usb_cfg(void) -{ - struct device_node *np; - void __iomem *bcsr_regs = NULL; - u8 bcsr5; - - mpc834x_usb_cfg(); - /* Map BCSR area */ - np = of_find_node_by_name(NULL, "bcsr"); - if (np) { - struct resource res; - - of_address_to_resource(np, 0, &res); - bcsr_regs = ioremap(res.start, resource_size(&res)); - of_node_put(np); - } - if (!bcsr_regs) - return -1; - - /* - * if Processor Board is plugged into PIB board, - * force to use the PHY on Processor Board - */ - bcsr5 = in_8(bcsr_regs + 5); - if (!(bcsr5 & BCSR5_INT_USB)) - out_8(bcsr_regs + 5, (bcsr5 | BCSR5_INT_USB)); - iounmap(bcsr_regs); - return 0; -} - -/* ************************************************************************ - * - * Setup the architecture - * - */ -static void __init mpc834x_mds_setup_arch(void) -{ - mpc83xx_setup_arch(); - - mpc834xemds_usb_cfg(); -} - -machine_device_initcall(mpc834x_mds, mpc83xx_declare_of_platform_devices); - -define_machine(mpc834x_mds) { - .name = "MPC834x MDS", - .compatible = "MPC834xMDS", - .setup_arch = mpc834x_mds_setup_arch, - .discover_phbs = mpc83xx_setup_pci, - .init_IRQ = mpc83xx_ipic_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc83xx_restart, - .time_init = mpc83xx_time_init, - .progress = udbg_progress, -}; -- GitLab From 7840b08aeccbd4d46261a6d5c27699d6939f712e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Apr 2023 11:08:55 +1000 Subject: [PATCH 3466/5631] powerpc: drop MPC836x_MDS platform support This 2006 era Modular Development System (MDS) has, at its core component, a full length card with a PCI edge. No case. Serial and network connectors were on card, so it could optionally be fitted with plastic stand-offs and run stand-alone off a power brick. This is very similar to the MPC834x_MDS removed in the prior commit, but with this board variant as an evolutionary step. DDR2 was now an option, and the card edge was revised down to PCI-32 as PCI-64 never got traction. But overall the form factor and design goals were unchanged. Like all the MDS systems, it was meant as a vehicle to get the CPU out early to hardware OEMs so software and board development could take place in parallel. To that end, the BGA CPU was held in place with a mechanical spring loaded pressure assembly (vs. solder) so that early rev silicon could be replaced in the field. Not for COTS deployment! These were made in limited numbers and availability preference was given to partners who were planning to make their own boards. Given that the whole reason for existence was to assist in enabling new board designs [not happening for 10+ years], and that they weren't generally available, and that the hardware wasn't really hobbyist friendly even for retro computing, it makes sense to retire the support for this particular platform. Signed-off-by: Paul Gortmaker Acked-by: Li Yang [mpe: Drop stale reference to MPC836x_MDS in arch/powerpc/boot/Makefile] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220115913.25811-3-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 1 - arch/powerpc/boot/dts/mpc836x_mds.dts | 481 ------------------ .../configs/83xx/mpc836x_mds_defconfig | 64 --- arch/powerpc/configs/mpc83xx_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/83xx/Kconfig | 6 - arch/powerpc/platforms/83xx/Makefile | 1 - arch/powerpc/platforms/83xx/mpc836x_mds.c | 201 -------- 8 files changed, 756 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc836x_mds.dts delete mode 100644 arch/powerpc/configs/83xx/mpc836x_mds_defconfig delete mode 100644 arch/powerpc/platforms/83xx/mpc836x_mds.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index f701dff92cfd..c9b03feb8d67 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -338,7 +338,6 @@ image-$(CONFIG_MPC832x_MDS) += cuImage.mpc832x_mds image-$(CONFIG_MPC832x_RDB) += cuImage.mpc832x_rdb image-$(CONFIG_MPC834x_ITX) += cuImage.mpc8349emitx \ cuImage.mpc8349emitxgp -image-$(CONFIG_MPC836x_MDS) += cuImage.mpc836x_mds image-$(CONFIG_ASP834x) += dtbImage.asp834x-redboot # Board ports in arch/powerpc/platform/85xx/Kconfig diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts deleted file mode 100644 index f4ca12ec57f1..000000000000 --- a/arch/powerpc/boot/dts/mpc836x_mds.dts +++ /dev/null @@ -1,481 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8360E EMDS Device Tree Source - * - * Copyright 2006 Freescale Semiconductor Inc. - */ - - -/* -/memreserve/ 00000000 1000000; -*/ - -/dts-v1/; - -/ { - model = "MPC8360MDS"; - compatible = "MPC8360EMDS", "MPC836xMDS", "MPC83xxMDS"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8360@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; // 32 bytes - i-cache-line-size = <32>; // 32 bytes - d-cache-size = <32768>; // L1, 32K - i-cache-size = <32768>; // L1, 32K - timebase-frequency = <66000000>; - bus-frequency = <264000000>; - clock-frequency = <528000000>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x10000000>; - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8360-localbus", "fsl,pq2pro-localbus", - "simple-bus"; - reg = <0xe0005000 0xd8>; - ranges = <0 0 0xfe000000 0x02000000 - 1 0 0xf8000000 0x00008000>; - - flash@0,0 { - compatible = "cfi-flash"; - reg = <0 0 0x2000000>; - bank-width = <2>; - device-width = <1>; - }; - - bcsr@1,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8360mds-bcsr"; - reg = <1 0 0x8000>; - ranges = <0 1 0 0x8000>; - - bcsr13: gpio-controller@d { - #gpio-cells = <2>; - compatible = "fsl,mpc8360mds-bcsr-gpio"; - reg = <0xd 1>; - gpio-controller; - }; - }; - }; - - soc8360@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <264000000>; - - wdt@200 { - device_type = "watchdog"; - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - pmc: power@b00 { - compatible = "fsl,mpc8360-pmc", "fsl,mpc8349-pmc"; - reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 0x8>; - interrupt-parent = <&ipic>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <264000000>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <264000000>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8360-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8360-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8360-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8360-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8360-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - crypto@30000 { - compatible = "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x7e>; - fsl,descriptor-types-mask = <0x01010ebf>; - sleep = <&pmc 0x03000000>; - }; - - ipic: pic@700 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - device_type = "ipic"; - }; - - par_io@1400 { - #address-cells = <1>; - #size-cells = <1>; - reg = <0x1400 0x100>; - ranges = <0 0x1400 0x100>; - device_type = "par_io"; - num-ports = <7>; - - qe_pio_b: gpio-controller@18 { - #gpio-cells = <2>; - compatible = "fsl,mpc8360-qe-pario-bank", - "fsl,mpc8323-qe-pario-bank"; - reg = <0x18 0x18>; - gpio-controller; - }; - - pio1: ucc_pin@1 { - pio-map = < - /* port pin dir open_drain assignment has_irq */ - 0 3 1 0 1 0 /* TxD0 */ - 0 4 1 0 1 0 /* TxD1 */ - 0 5 1 0 1 0 /* TxD2 */ - 0 6 1 0 1 0 /* TxD3 */ - 1 6 1 0 3 0 /* TxD4 */ - 1 7 1 0 1 0 /* TxD5 */ - 1 9 1 0 2 0 /* TxD6 */ - 1 10 1 0 2 0 /* TxD7 */ - 0 9 2 0 1 0 /* RxD0 */ - 0 10 2 0 1 0 /* RxD1 */ - 0 11 2 0 1 0 /* RxD2 */ - 0 12 2 0 1 0 /* RxD3 */ - 0 13 2 0 1 0 /* RxD4 */ - 1 1 2 0 2 0 /* RxD5 */ - 1 0 2 0 2 0 /* RxD6 */ - 1 4 2 0 2 0 /* RxD7 */ - 0 7 1 0 1 0 /* TX_EN */ - 0 8 1 0 1 0 /* TX_ER */ - 0 15 2 0 1 0 /* RX_DV */ - 0 16 2 0 1 0 /* RX_ER */ - 0 0 2 0 1 0 /* RX_CLK */ - 2 9 1 0 3 0 /* GTX_CLK - CLK10 */ - 2 8 2 0 1 0>; /* GTX125 - CLK9 */ - }; - pio2: ucc_pin@2 { - pio-map = < - /* port pin dir open_drain assignment has_irq */ - 0 17 1 0 1 0 /* TxD0 */ - 0 18 1 0 1 0 /* TxD1 */ - 0 19 1 0 1 0 /* TxD2 */ - 0 20 1 0 1 0 /* TxD3 */ - 1 2 1 0 1 0 /* TxD4 */ - 1 3 1 0 2 0 /* TxD5 */ - 1 5 1 0 3 0 /* TxD6 */ - 1 8 1 0 3 0 /* TxD7 */ - 0 23 2 0 1 0 /* RxD0 */ - 0 24 2 0 1 0 /* RxD1 */ - 0 25 2 0 1 0 /* RxD2 */ - 0 26 2 0 1 0 /* RxD3 */ - 0 27 2 0 1 0 /* RxD4 */ - 1 12 2 0 2 0 /* RxD5 */ - 1 13 2 0 3 0 /* RxD6 */ - 1 11 2 0 2 0 /* RxD7 */ - 0 21 1 0 1 0 /* TX_EN */ - 0 22 1 0 1 0 /* TX_ER */ - 0 29 2 0 1 0 /* RX_DV */ - 0 30 2 0 1 0 /* RX_ER */ - 0 31 2 0 1 0 /* RX_CLK */ - 2 2 1 0 2 0 /* GTX_CLK - CLK10 */ - 2 3 2 0 1 0 /* GTX125 - CLK4 */ - 0 1 3 0 2 0 /* MDIO */ - 0 2 1 0 1 0>; /* MDC */ - }; - - }; - }; - - qe@e0100000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "qe"; - compatible = "fsl,qe"; - ranges = <0x0 0xe0100000 0x00100000>; - reg = <0xe0100000 0x480>; - brg-frequency = <0>; - bus-frequency = <396000000>; - fsl,qe-num-riscs = <2>; - fsl,qe-num-snums = <28>; - - muram@10000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,qe-muram", "fsl,cpm-muram"; - ranges = <0x0 0x00010000 0x0000c000>; - - data-only@0 { - compatible = "fsl,qe-muram-data", - "fsl,cpm-muram-data"; - reg = <0x0 0xc000>; - }; - }; - - timer@440 { - compatible = "fsl,mpc8360-qe-gtm", - "fsl,qe-gtm", "fsl,gtm"; - reg = <0x440 0x40>; - clock-frequency = <132000000>; - interrupts = <12 13 14 15>; - interrupt-parent = <&qeic>; - }; - - spi@4c0 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x4c0 0x40>; - interrupts = <2>; - interrupt-parent = <&qeic>; - mode = "cpu"; - }; - - spi@500 { - cell-index = <1>; - compatible = "fsl,spi"; - reg = <0x500 0x40>; - interrupts = <1>; - interrupt-parent = <&qeic>; - mode = "cpu"; - }; - - usb@6c0 { - compatible = "fsl,mpc8360-qe-usb", - "fsl,mpc8323-qe-usb"; - reg = <0x6c0 0x40 0x8b00 0x100>; - interrupts = <11>; - interrupt-parent = <&qeic>; - fsl,fullspeed-clock = "clk21"; - fsl,lowspeed-clock = "brg9"; - gpios = <&qe_pio_b 2 0 /* USBOE */ - &qe_pio_b 3 0 /* USBTP */ - &qe_pio_b 8 0 /* USBTN */ - &qe_pio_b 9 0 /* USBRP */ - &qe_pio_b 11 0 /* USBRN */ - &bcsr13 5 0 /* SPEED */ - &bcsr13 4 1>; /* POWER */ - }; - - enet0: ucc@2000 { - device_type = "network"; - compatible = "ucc_geth"; - cell-index = <1>; - reg = <0x2000 0x200>; - interrupts = <32>; - interrupt-parent = <&qeic>; - local-mac-address = [ 00 00 00 00 00 00 ]; - rx-clock-name = "none"; - tx-clock-name = "clk9"; - phy-handle = <&phy0>; - phy-connection-type = "rgmii-id"; - pio-handle = <&pio1>; - }; - - enet1: ucc@3000 { - device_type = "network"; - compatible = "ucc_geth"; - cell-index = <2>; - reg = <0x3000 0x200>; - interrupts = <33>; - interrupt-parent = <&qeic>; - local-mac-address = [ 00 00 00 00 00 00 ]; - rx-clock-name = "none"; - tx-clock-name = "clk4"; - phy-handle = <&phy1>; - phy-connection-type = "rgmii-id"; - pio-handle = <&pio2>; - }; - - mdio@2120 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0x2120 0x18>; - compatible = "fsl,ucc-mdio"; - - phy0: ethernet-phy@0 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x0>; - }; - phy1: ethernet-phy@1 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x1>; - }; - tbi-phy@2 { - device_type = "tbi-phy"; - reg = <0x2>; - }; - }; - - qeic: interrupt-controller@80 { - interrupt-controller; - compatible = "fsl,qe-ic"; - #address-cells = <0>; - #interrupt-cells = <1>; - reg = <0x80 0x80>; - big-endian; - interrupts = <32 0x8 33 0x8>; // high:32 low:33 - interrupt-parent = <&ipic>; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 AD17 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 AD18 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 AD19 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 AD21*/ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 AD22*/ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 AD23*/ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 AD24*/ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0 0>; - ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>; - clock-frequency = <66666666>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - sleep = <&pmc 0x00010000>; - }; -}; diff --git a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig deleted file mode 100644 index 3eceb6db2982..000000000000 --- a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig +++ /dev/null @@ -1,64 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_KALLSYMS is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y -# CONFIG_MSDOS_PARTITION is not set -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_83xx=y -CONFIG_MPC836x_MDS=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y -CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_PHYSMAP_OF=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_SCSI=y -CONFIG_NETDEVICES=y -CONFIG_UCC_GETH=y -CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_HW_RANDOM=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_MPC=y -CONFIG_WATCHDOG=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_DS1374=y -CONFIG_QUICC_ENGINE=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 03f6a478d0cf..0fa29520808f 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -14,7 +14,6 @@ CONFIG_MPC831x_RDB=y CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y -CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 025d2cfd06d7..26147b206363 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -47,7 +47,6 @@ CONFIG_MPC831x_RDB=y CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y -CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 1ca0ba3b0f1c..90d0041fb8a7 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -49,12 +49,6 @@ config MPC834x_ITX Be aware that PCI initialization is the bootloader's responsibility. -config MPC836x_MDS - bool "Freescale MPC836x MDS" - select DEFAULT_UIMAGE - help - This option enables support for the MPC836x MDS Processor Board. - config MPC836x_RDK bool "Freescale/Logic MPC836x RDK" select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index 5697b70492b8..4f979f2fc64e 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -9,7 +9,6 @@ obj-$(CONFIG_MPC830x_RDB) += mpc830x_rdb.o obj-$(CONFIG_MPC831x_RDB) += mpc831x_rdb.o obj-$(CONFIG_MPC832x_RDB) += mpc832x_rdb.o obj-$(CONFIG_MPC834x_ITX) += mpc834x_itx.o -obj-$(CONFIG_MPC836x_MDS) += mpc836x_mds.o obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o obj-$(CONFIG_MPC832x_MDS) += mpc832x_mds.o obj-$(CONFIG_MPC837x_MDS) += mpc837x_mds.o diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c deleted file mode 100644 index 84c08fdf503c..000000000000 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ /dev/null @@ -1,201 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright 2006 Freescale Semiconductor, Inc. All rights reserved. - * - * Author: Li Yang - * Yin Olivia - * - * Description: - * MPC8360E MDS board specific routines. - * - * Changelog: - * Jun 21, 2006 Initial version - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "mpc83xx.h" - -#undef DEBUG -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -/* ************************************************************************ - * - * Setup the architecture - * - */ -static void __init mpc836x_mds_setup_arch(void) -{ - struct device_node *np; - u8 __iomem *bcsr_regs = NULL; - - mpc83xx_setup_arch(); - - /* Map BCSR area */ - np = of_find_node_by_name(NULL, "bcsr"); - if (np) { - struct resource res; - - of_address_to_resource(np, 0, &res); - bcsr_regs = ioremap(res.start, resource_size(&res)); - of_node_put(np); - } - -#ifdef CONFIG_QUICC_ENGINE - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { - par_io_init(np); - of_node_put(np); - - for_each_node_by_name(np, "ucc") - par_io_of_config(np); -#ifdef CONFIG_QE_USB - /* Must fixup Par IO before QE GPIO chips are registered. */ - par_io_config_pin(1, 2, 1, 0, 3, 0); /* USBOE */ - par_io_config_pin(1, 3, 1, 0, 3, 0); /* USBTP */ - par_io_config_pin(1, 8, 1, 0, 1, 0); /* USBTN */ - par_io_config_pin(1, 10, 2, 0, 3, 0); /* USBRXD */ - par_io_config_pin(1, 9, 2, 1, 3, 0); /* USBRP */ - par_io_config_pin(1, 11, 2, 1, 3, 0); /* USBRN */ - par_io_config_pin(2, 20, 2, 0, 1, 0); /* CLK21 */ -#endif /* CONFIG_QE_USB */ - } - - if ((np = of_find_compatible_node(NULL, "network", "ucc_geth")) - != NULL){ - uint svid; - - /* Reset the Ethernet PHY */ -#define BCSR9_GETHRST 0x20 - clrbits8(&bcsr_regs[9], BCSR9_GETHRST); - udelay(1000); - setbits8(&bcsr_regs[9], BCSR9_GETHRST); - - /* handle mpc8360ea rev.2.1 erratum 2: RGMII Timing */ - svid = mfspr(SPRN_SVR); - if (svid == 0x80480021) { - void __iomem *immap; - - immap = ioremap(get_immrbase() + 0x14a8, 8); - - /* - * IMMR + 0x14A8[4:5] = 11 (clk delay for UCC 2) - * IMMR + 0x14A8[18:19] = 11 (clk delay for UCC 1) - */ - setbits32(immap, 0x0c003000); - - /* - * IMMR + 0x14AC[20:27] = 10101010 - * (data delay for both UCC's) - */ - clrsetbits_be32(immap + 4, 0xff0, 0xaa0); - - iounmap(immap); - } - - iounmap(bcsr_regs); - of_node_put(np); - } -#endif /* CONFIG_QUICC_ENGINE */ -} - -machine_device_initcall(mpc836x_mds, mpc83xx_declare_of_platform_devices); - -#ifdef CONFIG_QE_USB -static int __init mpc836x_usb_cfg(void) -{ - u8 __iomem *bcsr; - struct device_node *np; - const char *mode; - int ret = 0; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc8360mds-bcsr"); - if (!np) - return -ENODEV; - - bcsr = of_iomap(np, 0); - of_node_put(np); - if (!bcsr) - return -ENOMEM; - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc8323-qe-usb"); - if (!np) { - ret = -ENODEV; - goto err; - } - -#define BCSR8_TSEC1M_MASK (0x3 << 6) -#define BCSR8_TSEC1M_RGMII (0x0 << 6) -#define BCSR8_TSEC2M_MASK (0x3 << 4) -#define BCSR8_TSEC2M_RGMII (0x0 << 4) - /* - * Default is GMII (2), but we should set it to RGMII (0) if we use - * USB (Eth PHY is in RGMII mode anyway). - */ - clrsetbits_8(&bcsr[8], BCSR8_TSEC1M_MASK | BCSR8_TSEC2M_MASK, - BCSR8_TSEC1M_RGMII | BCSR8_TSEC2M_RGMII); - -#define BCSR13_USBMASK 0x0f -#define BCSR13_nUSBEN 0x08 /* 1 - Disable, 0 - Enable */ -#define BCSR13_USBSPEED 0x04 /* 1 - Full, 0 - Low */ -#define BCSR13_USBMODE 0x02 /* 1 - Host, 0 - Function */ -#define BCSR13_nUSBVCC 0x01 /* 1 - gets VBUS, 0 - supplies VBUS */ - - clrsetbits_8(&bcsr[13], BCSR13_USBMASK, BCSR13_USBSPEED); - - mode = of_get_property(np, "mode", NULL); - if (mode && !strcmp(mode, "peripheral")) { - setbits8(&bcsr[13], BCSR13_nUSBVCC); - qe_usb_clock_set(QE_CLK21, 48000000); - } else { - setbits8(&bcsr[13], BCSR13_USBMODE); - } - - of_node_put(np); -err: - iounmap(bcsr); - return ret; -} -machine_arch_initcall(mpc836x_mds, mpc836x_usb_cfg); -#endif /* CONFIG_QE_USB */ - -define_machine(mpc836x_mds) { - .name = "MPC836x MDS", - .compatible = "MPC836xMDS", - .setup_arch = mpc836x_mds_setup_arch, - .discover_phbs = mpc83xx_setup_pci, - .init_IRQ = mpc83xx_ipic_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc83xx_restart, - .time_init = mpc83xx_time_init, - .progress = udbg_progress, -}; -- GitLab From aa572079633c293882d8fa3973bf6d8c27eb430f Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Apr 2023 11:08:57 +1000 Subject: [PATCH 3467/5631] powerpc: drop MPC837x_MDS platform support This next evolutionary step in the e300 family of Modular Development System (MDS) still has, at its core component, a full length card with a PCI edge. No case. Serial and network connectors were on card, so it could optionally be fitted with plastic stand-offs and run stand-alone off a power brick. This is very similar to the MPC834x_MDS and MPC836x_MDS removed in the prior commits, but with this board variant as yet another evolutionary step. SATA and PCI-e were now available. But overall the form factor and design goals were unchanged. Like all the MDS systems, it was meant as a vehicle to get the CPU out early to hardware OEMs so software and board development could take place in parallel. These were made in limited numbers and availability preference was given to partners who were planning to make their own boards. Given that the whole reason for existence was to assist in enabling new board designs [not happening for 10+ years], and that they weren't generally available, and that the hardware wasn't really hobbyist friendly even for retro computing, it makes sense to retire the support for this particular platform. Signed-off-by: Paul Gortmaker Acked-by: Li Yang Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220115913.25811-4-paul.gortmaker@windriver.com --- arch/powerpc/boot/dts/mpc8377_mds.dts | 505 ------------------ arch/powerpc/boot/dts/mpc8378_mds.dts | 489 ----------------- arch/powerpc/boot/dts/mpc8379_mds.dts | 455 ---------------- .../configs/83xx/mpc837x_mds_defconfig | 58 -- arch/powerpc/configs/mpc83xx_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/83xx/Kconfig | 7 - arch/powerpc/platforms/83xx/Makefile | 1 - arch/powerpc/platforms/83xx/mpc837x_mds.c | 94 ---- 9 files changed, 1611 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc8377_mds.dts delete mode 100644 arch/powerpc/boot/dts/mpc8378_mds.dts delete mode 100644 arch/powerpc/boot/dts/mpc8379_mds.dts delete mode 100644 arch/powerpc/configs/83xx/mpc837x_mds_defconfig delete mode 100644 arch/powerpc/platforms/83xx/mpc837x_mds.c diff --git a/arch/powerpc/boot/dts/mpc8377_mds.dts b/arch/powerpc/boot/dts/mpc8377_mds.dts deleted file mode 100644 index 9227bce0e2f5..000000000000 --- a/arch/powerpc/boot/dts/mpc8377_mds.dts +++ /dev/null @@ -1,505 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8377E MDS Device Tree Source - * - * Copyright 2007 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "fsl,mpc8377emds"; - compatible = "fsl,mpc8377emds","fsl,mpc837xmds"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - pci1 = &pci1; - pci2 = &pci2; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8377@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; - i-cache-size = <32768>; - timebase-frequency = <0>; - bus-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x20000000>; // 512MB at 0 - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8377-elbc", "fsl,elbc", "simple-bus"; - reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; - interrupt-parent = <&ipic>; - - // booting from NOR flash - ranges = <0 0x0 0xfe000000 0x02000000 - 1 0x0 0xf8000000 0x00008000 - 3 0x0 0xe0600000 0x00008000>; - - flash@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "cfi-flash"; - reg = <0 0x0 0x2000000>; - bank-width = <2>; - device-width = <1>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - fs@100000 { - reg = <0x100000 0x800000>; - }; - - kernel@1d00000 { - reg = <0x1d00000 0x200000>; - }; - - dtb@1f00000 { - reg = <0x1f00000 0x100000>; - }; - }; - - bcsr@1,0 { - reg = <1 0x0 0x8000>; - compatible = "fsl,mpc837xmds-bcsr"; - }; - - nand@3,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8377-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <3 0x0 0x8000>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - kernel@100000 { - reg = <0x100000 0x300000>; - }; - - fs@400000 { - reg = <0x400000 0x1c00000>; - }; - }; - }; - - soc@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <0>; - - wdt@200 { - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - sleep-nexus { - #address-cells = <1>; - #size-cells = <1>; - compatible = "simple-bus"; - sleep = <&pmc 0x0c000000>; - ranges; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - interrupts = <19 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - sdhci@2e000 { - compatible = "fsl,mpc8377-esdhc", "fsl,esdhc"; - reg = <0x2e000 0x1000>; - interrupts = <42 0x8>; - interrupt-parent = <&ipic>; - sdhci,wp-inverted; - /* Filled in by U-Boot */ - clock-frequency = <0>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - spi@7000 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x7000 0x1000>; - interrupts = <16 0x8>; - interrupt-parent = <&ipic>; - mode = "cpu"; - }; - - usb@23000 { - compatible = "fsl-usb2-dr"; - reg = <0x23000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <38 0x8>; - dr_mode = "host"; - phy_type = "ulpi"; - sleep = <&pmc 0x00c00000>; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy2>; - sleep = <&pmc 0xc0000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - - phy2: ethernet-phy@2 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x2>; - }; - - phy3: ethernet-phy@3 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x3>; - }; - - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy3>; - sleep = <&pmc 0x30000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8377-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <0x47 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8377-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <0x47 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8377-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <0x47 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8377-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <0x47 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8377-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <0x47 8>; - }; - }; - - crypto@30000 { - compatible = "fsl,sec3.0", "fsl,sec2.4", "fsl,sec2.2", - "fsl,sec2.1", "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x9fe>; - fsl,descriptor-types-mask = <0x3ab0ebf>; - sleep = <&pmc 0x03000000>; - }; - - sata@18000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x18000 0x1000>; - interrupts = <44 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x000000c0>; - }; - - sata@19000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x19000 0x1000>; - interrupts = <45 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x00000030>; - }; - - /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - ipic: pic@700 { - compatible = "fsl,ipic"; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - }; - - pmc: power@b00 { - compatible = "fsl,mpc8377-pmc", "fsl,mpc8349-pmc"; - reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 */ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0x0 0x0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe0300000 0x0 0x00100000>; - sleep = <&pmc 0x00010000>; - clock-frequency = <0>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; - - pci1: pcie@e0009000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "fsl,mpc8377-pcie", "fsl,mpc8314-pcie"; - reg = <0xe0009000 0x00001000>; - ranges = <0x02000000 0 0xa8000000 0xa8000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb8000000 0 0x00800000>; - bus-range = <0 255>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 1 8 - 0 0 0 2 &ipic 1 8 - 0 0 0 3 &ipic 1 8 - 0 0 0 4 &ipic 1 8>; - sleep = <&pmc 0x00300000>; - clock-frequency = <0>; - - pcie@0 { - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - reg = <0 0 0 0 0>; - ranges = <0x02000000 0 0xa8000000 - 0x02000000 0 0xa8000000 - 0 0x10000000 - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00800000>; - }; - }; - - pci2: pcie@e000a000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "fsl,mpc8377-pcie", "fsl,mpc8314-pcie"; - reg = <0xe000a000 0x00001000>; - ranges = <0x02000000 0 0xc8000000 0xc8000000 0 0x10000000 - 0x01000000 0 0x00000000 0xd8000000 0 0x00800000>; - bus-range = <0 255>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 2 8 - 0 0 0 2 &ipic 2 8 - 0 0 0 3 &ipic 2 8 - 0 0 0 4 &ipic 2 8>; - sleep = <&pmc 0x000c0000>; - clock-frequency = <0>; - - pcie@0 { - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - reg = <0 0 0 0 0>; - ranges = <0x02000000 0 0xc8000000 - 0x02000000 0 0xc8000000 - 0 0x10000000 - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00800000>; - }; - }; -}; diff --git a/arch/powerpc/boot/dts/mpc8378_mds.dts b/arch/powerpc/boot/dts/mpc8378_mds.dts deleted file mode 100644 index e45b25554e8c..000000000000 --- a/arch/powerpc/boot/dts/mpc8378_mds.dts +++ /dev/null @@ -1,489 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8378E MDS Device Tree Source - * - * Copyright 2007 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "fsl,mpc8378emds"; - compatible = "fsl,mpc8378emds","fsl,mpc837xmds"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - pci1 = &pci1; - pci2 = &pci2; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8378@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; - i-cache-size = <32768>; - timebase-frequency = <0>; - bus-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x20000000>; // 512MB at 0 - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8378-elbc", "fsl,elbc", "simple-bus"; - reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; - interrupt-parent = <&ipic>; - - // booting from NOR flash - ranges = <0 0x0 0xfe000000 0x02000000 - 1 0x0 0xf8000000 0x00008000 - 3 0x0 0xe0600000 0x00008000>; - - flash@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "cfi-flash"; - reg = <0 0x0 0x2000000>; - bank-width = <2>; - device-width = <1>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - fs@100000 { - reg = <0x100000 0x800000>; - }; - - kernel@1d00000 { - reg = <0x1d00000 0x200000>; - }; - - dtb@1f00000 { - reg = <0x1f00000 0x100000>; - }; - }; - - bcsr@1,0 { - reg = <1 0x0 0x8000>; - compatible = "fsl,mpc837xmds-bcsr"; - }; - - nand@3,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8378-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <3 0x0 0x8000>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - kernel@100000 { - reg = <0x100000 0x300000>; - }; - - fs@400000 { - reg = <0x400000 0x1c00000>; - }; - }; - }; - - soc@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <0>; - - wdt@200 { - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - sleep-nexus { - #address-cells = <1>; - #size-cells = <1>; - compatible = "simple-bus"; - sleep = <&pmc 0x0c000000>; - ranges; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - interrupts = <19 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - sdhci@2e000 { - compatible = "fsl,mpc8378-esdhc", "fsl,esdhc"; - reg = <0x2e000 0x1000>; - interrupts = <42 0x8>; - interrupt-parent = <&ipic>; - sdhci,wp-inverted; - /* Filled in by U-Boot */ - clock-frequency = <0>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - spi@7000 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x7000 0x1000>; - interrupts = <16 0x8>; - interrupt-parent = <&ipic>; - mode = "cpu"; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8378-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8378-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8378-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8378-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8378-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - usb@23000 { - compatible = "fsl-usb2-dr"; - reg = <0x23000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <38 0x8>; - dr_mode = "host"; - phy_type = "ulpi"; - sleep = <&pmc 0x00c00000>; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy2>; - sleep = <&pmc 0xc0000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - - phy2: ethernet-phy@2 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x2>; - }; - - phy3: ethernet-phy@3 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x3>; - }; - - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy3>; - sleep = <&pmc 0x30000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - crypto@30000 { - compatible = "fsl,sec3.0", "fsl,sec2.4", "fsl,sec2.2", - "fsl,sec2.1", "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x9fe>; - fsl,descriptor-types-mask = <0x3ab0ebf>; - sleep = <&pmc 0x03000000>; - }; - - /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - ipic: pic@700 { - compatible = "fsl,ipic"; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - }; - - pmc: power@b00 { - compatible = "fsl,mpc8378-pmc", "fsl,mpc8349-pmc"; - reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 */ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0x0 0x0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe0300000 0x0 0x00100000>; - clock-frequency = <0>; - sleep = <&pmc 0x00010000>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; - - pci1: pcie@e0009000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "fsl,mpc8378-pcie", "fsl,mpc8314-pcie"; - reg = <0xe0009000 0x00001000>; - ranges = <0x02000000 0 0xa8000000 0xa8000000 0 0x10000000 - 0x01000000 0 0x00000000 0xb8000000 0 0x00800000>; - bus-range = <0 255>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 1 8 - 0 0 0 2 &ipic 1 8 - 0 0 0 3 &ipic 1 8 - 0 0 0 4 &ipic 1 8>; - sleep = <&pmc 0x00300000>; - clock-frequency = <0>; - - pcie@0 { - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - reg = <0 0 0 0 0>; - ranges = <0x02000000 0 0xa8000000 - 0x02000000 0 0xa8000000 - 0 0x10000000 - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00800000>; - }; - }; - - pci2: pcie@e000a000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "fsl,mpc8378-pcie", "fsl,mpc8314-pcie"; - reg = <0xe000a000 0x00001000>; - ranges = <0x02000000 0 0xc8000000 0xc8000000 0 0x10000000 - 0x01000000 0 0x00000000 0xd8000000 0 0x00800000>; - bus-range = <0 255>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0 0 0 1 &ipic 2 8 - 0 0 0 2 &ipic 2 8 - 0 0 0 3 &ipic 2 8 - 0 0 0 4 &ipic 2 8>; - sleep = <&pmc 0x000c0000>; - clock-frequency = <0>; - - pcie@0 { - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - reg = <0 0 0 0 0>; - ranges = <0x02000000 0 0xc8000000 - 0x02000000 0 0xc8000000 - 0 0x10000000 - 0x01000000 0 0x00000000 - 0x01000000 0 0x00000000 - 0 0x00800000>; - }; - }; -}; diff --git a/arch/powerpc/boot/dts/mpc8379_mds.dts b/arch/powerpc/boot/dts/mpc8379_mds.dts deleted file mode 100644 index f7379a1cbb6c..000000000000 --- a/arch/powerpc/boot/dts/mpc8379_mds.dts +++ /dev/null @@ -1,455 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8379E MDS Device Tree Source - * - * Copyright 2007 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "fsl,mpc8379emds"; - compatible = "fsl,mpc8379emds","fsl,mpc837xmds"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8379@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; - i-cache-size = <32768>; - timebase-frequency = <0>; - bus-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x20000000>; // 512MB at 0 - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8379-elbc", "fsl,elbc", "simple-bus"; - reg = <0xe0005000 0x1000>; - interrupts = <77 0x8>; - interrupt-parent = <&ipic>; - - // booting from NOR flash - ranges = <0 0x0 0xfe000000 0x02000000 - 1 0x0 0xf8000000 0x00008000 - 3 0x0 0xe0600000 0x00008000>; - - flash@0,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "cfi-flash"; - reg = <0 0x0 0x2000000>; - bank-width = <2>; - device-width = <1>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - fs@100000 { - reg = <0x100000 0x800000>; - }; - - kernel@1d00000 { - reg = <0x1d00000 0x200000>; - }; - - dtb@1f00000 { - reg = <0x1f00000 0x100000>; - }; - }; - - bcsr@1,0 { - reg = <1 0x0 0x8000>; - compatible = "fsl,mpc837xmds-bcsr"; - }; - - nand@3,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8379-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <3 0x0 0x8000>; - - u-boot@0 { - reg = <0x0 0x100000>; - read-only; - }; - - kernel@100000 { - reg = <0x100000 0x300000>; - }; - - fs@400000 { - reg = <0x400000 0x1c00000>; - }; - }; - }; - - soc@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <0>; - - wdt@200 { - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - sleep-nexus { - #address-cells = <1>; - #size-cells = <1>; - compatible = "simple-bus"; - sleep = <&pmc 0x0c000000>; - ranges; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - interrupts = <19 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - sdhci@2e000 { - compatible = "fsl,mpc8379-esdhc", "fsl,esdhc"; - reg = <0x2e000 0x1000>; - interrupts = <42 0x8>; - interrupt-parent = <&ipic>; - sdhci,wp-inverted; - /* Filled in by U-Boot */ - clock-frequency = <0>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <15 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - }; - - spi@7000 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x7000 0x1000>; - interrupts = <16 0x8>; - interrupt-parent = <&ipic>; - mode = "cpu"; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8379-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8379-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8379-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8379-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8379-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - usb@23000 { - compatible = "fsl-usb2-dr"; - reg = <0x23000 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupt-parent = <&ipic>; - interrupts = <38 0x8>; - dr_mode = "host"; - phy_type = "ulpi"; - sleep = <&pmc 0x00c00000>; - }; - - enet0: ethernet@24000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <0>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x24000 0x1000>; - ranges = <0x0 0x24000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 0x8 33 0x8 34 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi0>; - phy-handle = <&phy2>; - sleep = <&pmc 0xc0000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-mdio"; - reg = <0x520 0x20>; - - phy2: ethernet-phy@2 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x2>; - }; - - phy3: ethernet-phy@3 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x3>; - }; - - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - enet1: ethernet@25000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - device_type = "network"; - model = "eTSEC"; - compatible = "gianfar"; - reg = <0x25000 0x1000>; - ranges = <0x0 0x25000 0x1000>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <35 0x8 36 0x8 37 0x8>; - phy-connection-type = "mii"; - interrupt-parent = <&ipic>; - tbi-handle = <&tbi1>; - phy-handle = <&phy3>; - sleep = <&pmc 0x30000000>; - fsl,magic-packet; - - mdio@520 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,gianfar-tbi"; - reg = <0x520 0x20>; - - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - crypto@30000 { - compatible = "fsl,sec3.0", "fsl,sec2.4", "fsl,sec2.2", - "fsl,sec2.1", "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x9fe>; - fsl,descriptor-types-mask = <0x3ab0ebf>; - sleep = <&pmc 0x03000000>; - }; - - sata@18000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x18000 0x1000>; - interrupts = <44 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x000000c0>; - }; - - sata@19000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x19000 0x1000>; - interrupts = <45 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x00000030>; - }; - - sata@1a000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x1a000 0x1000>; - interrupts = <46 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x0000000c>; - }; - - sata@1b000 { - compatible = "fsl,mpc8379-sata", "fsl,pq-sata"; - reg = <0x1b000 0x1000>; - interrupts = <47 0x8>; - interrupt-parent = <&ipic>; - sleep = <&pmc 0x00000003>; - }; - - /* IPIC - * interrupts cell = - * sense values match linux IORESOURCE_IRQ_* defines: - * sense == 8: Level, low assertion - * sense == 2: Edge, high-to-low change - */ - ipic: pic@700 { - compatible = "fsl,ipic"; - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - }; - - pmc: power@b00 { - compatible = "fsl,mpc8379-pmc", "fsl,mpc8349-pmc"; - reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 0x8>; - interrupt-parent = <&ipic>; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 */ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0x0 0x0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe0300000 0x0 0x00100000>; - sleep = <&pmc 0x00010000>; - clock-frequency = <0>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - }; -}; diff --git a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig deleted file mode 100644 index 3f5e5d10789f..000000000000 --- a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig +++ /dev/null @@ -1,58 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_83xx=y -CONFIG_MPC837x_MDS=y -CONFIG_GEN_RTC=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_SG=y -CONFIG_ATA=y -CONFIG_SATA_FSL=y -CONFIG_NETDEVICES=y -CONFIG_GIANFAR=y -CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_MPC=y -CONFIG_WATCHDOG=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_CRC_T10DIF=y -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 0fa29520808f..943c2d51bb60 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -15,7 +15,6 @@ CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_RDK=y -CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y CONFIG_ASP834x=y CONFIG_QE_GPIO=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 26147b206363..8afd8045004f 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -48,7 +48,6 @@ CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_RDK=y -CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y CONFIG_ASP834x=y CONFIG_PPC_86xx=y diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 90d0041fb8a7..978d2b12e97c 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -58,13 +58,6 @@ config MPC836x_RDK This option enables support for the MPC836x RDK Processor Board, also known as ZOOM PowerQUICC Kit. -config MPC837x_MDS - bool "Freescale MPC837x MDS" - select DEFAULT_UIMAGE - select PPC_MPC837x - help - This option enables support for the MPC837x MDS Processor Board. - config MPC837x_RDB bool "Freescale MPC837x RDB/WLAN" select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index 4f979f2fc64e..0c3a5067bd77 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -11,7 +11,6 @@ obj-$(CONFIG_MPC832x_RDB) += mpc832x_rdb.o obj-$(CONFIG_MPC834x_ITX) += mpc834x_itx.o obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o obj-$(CONFIG_MPC832x_MDS) += mpc832x_mds.o -obj-$(CONFIG_MPC837x_MDS) += mpc837x_mds.o obj-$(CONFIG_MPC837x_RDB) += mpc837x_rdb.o obj-$(CONFIG_ASP834x) += asp834x.o obj-$(CONFIG_KMETER1) += km83xx.o diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c deleted file mode 100644 index c2055ef35b63..000000000000 --- a/arch/powerpc/platforms/83xx/mpc837x_mds.c +++ /dev/null @@ -1,94 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * arch/powerpc/platforms/83xx/mpc837x_mds.c - * - * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved. - * - * MPC837x MDS board specific routines - */ - -#include -#include -#include -#include - -#include -#include -#include -#include - -#include "mpc83xx.h" - -#define BCSR12_USB_SER_MASK 0x8a -#define BCSR12_USB_SER_PIN 0x80 -#define BCSR12_USB_SER_DEVICE 0x02 - -static int __init mpc837xmds_usb_cfg(void) -{ - struct device_node *np; - const void *phy_type, *mode; - void __iomem *bcsr_regs = NULL; - u8 bcsr12; - int ret; - - ret = mpc837x_usb_cfg(); - if (ret) - return ret; - /* Map BCSR area */ - np = of_find_compatible_node(NULL, NULL, "fsl,mpc837xmds-bcsr"); - if (np) { - bcsr_regs = of_iomap(np, 0); - of_node_put(np); - } - if (!bcsr_regs) - return -1; - - np = of_find_node_by_name(NULL, "usb"); - if (!np) { - ret = -ENODEV; - goto out; - } - phy_type = of_get_property(np, "phy_type", NULL); - if (phy_type && !strcmp(phy_type, "ulpi")) { - clrbits8(bcsr_regs + 12, BCSR12_USB_SER_PIN); - } else if (phy_type && !strcmp(phy_type, "serial")) { - mode = of_get_property(np, "dr_mode", NULL); - bcsr12 = in_8(bcsr_regs + 12) & ~BCSR12_USB_SER_MASK; - bcsr12 |= BCSR12_USB_SER_PIN; - if (mode && !strcmp(mode, "peripheral")) - bcsr12 |= BCSR12_USB_SER_DEVICE; - out_8(bcsr_regs + 12, bcsr12); - } else { - printk(KERN_ERR "USB DR: unsupported PHY\n"); - } - - of_node_put(np); -out: - iounmap(bcsr_regs); - return ret; -} - -/* ************************************************************************ - * - * Setup the architecture - * - */ -static void __init mpc837x_mds_setup_arch(void) -{ - mpc83xx_setup_arch(); - mpc837xmds_usb_cfg(); -} - -machine_device_initcall(mpc837x_mds, mpc83xx_declare_of_platform_devices); - -define_machine(mpc837x_mds) { - .name = "MPC837x MDS", - .compatible = "fsl,mpc837xmds", - .setup_arch = mpc837x_mds_setup_arch, - .discover_phbs = mpc83xx_setup_pci, - .init_IRQ = mpc83xx_ipic_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc83xx_restart, - .time_init = mpc83xx_time_init, - .progress = udbg_progress, -}; -- GitLab From b8fa3af2dbcb0c84270d4d2ecf54a088f7c90701 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Thu, 13 Apr 2023 11:08:58 +1000 Subject: [PATCH 3468/5631] powerpc: drop MPC832x_MDS platform support This final variant in the e300 family of Modular Development System (MDS) in this series was actually aimed at feature reduction - things like floating point and ethernet were removed in order to make for a lower power and lower cost system. Like all the MDS systems, it was meant as a vehicle to get the CPU out early to hardware OEMs so software and board development could take place in parallel. These were made in limited numbers and availability preference was given to partners who were planning to make their own boards. Given that the whole reason for existence was to assist in enabling new board designs [not happening for 10+ years], and that they weren't generally available, and that the hardware wasn't really hobbyist friendly even for retro computing, it makes sense to retire the support for this particular platform. Signed-off-by: Paul Gortmaker Acked-by: Li Yang [mpe: Drop stale reference to MPC832x_MDS in arch/powerpc/boot/Makefile] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230220115913.25811-5-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 1 - arch/powerpc/boot/dts/mpc832x_mds.dts | 436 ------------------ .../configs/83xx/mpc832x_mds_defconfig | 59 --- arch/powerpc/configs/mpc83xx_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/83xx/Kconfig | 7 - arch/powerpc/platforms/83xx/Makefile | 1 - arch/powerpc/platforms/83xx/mpc832x_mds.c | 101 ---- 8 files changed, 607 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc832x_mds.dts delete mode 100644 arch/powerpc/configs/83xx/mpc832x_mds_defconfig delete mode 100644 arch/powerpc/platforms/83xx/mpc832x_mds.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index c9b03feb8d67..911fe07d24cf 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -334,7 +334,6 @@ image-$(CONFIG_PQ2FADS) += cuImage.pq2fads image-$(CONFIG_EP8248E) += dtbImage.ep8248e # Board ports in arch/powerpc/platform/83xx/Kconfig -image-$(CONFIG_MPC832x_MDS) += cuImage.mpc832x_mds image-$(CONFIG_MPC832x_RDB) += cuImage.mpc832x_rdb image-$(CONFIG_MPC834x_ITX) += cuImage.mpc8349emitx \ cuImage.mpc8349emitxgp diff --git a/arch/powerpc/boot/dts/mpc832x_mds.dts b/arch/powerpc/boot/dts/mpc832x_mds.dts deleted file mode 100644 index 3af073f01e71..000000000000 --- a/arch/powerpc/boot/dts/mpc832x_mds.dts +++ /dev/null @@ -1,436 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8323E EMDS Device Tree Source - * - * Copyright 2006 Freescale Semiconductor Inc. - * - - * To enable external serial I/O on a Freescale MPC 8323 SYS/MDS board, do - * this: - * - * 1) On chip U61, lift (disconnect) pins 21 (TXD) and 22 (RXD) from the board. - * 2) Solder a wire from U61-21 to P19A-23. P19 is a grid of pins on the board - * next to the serial ports. - * 3) Solder a wire from U61-22 to P19K-22. - * - * Note that there's a typo in the schematic. The board labels the last column - * of pins "P19K", but in the schematic, that column is called "P19J". So if - * you're going by the schematic, the pin is called "P19J-K22". - */ - -/dts-v1/; - -/ { - model = "MPC8323EMDS"; - compatible = "MPC8323EMDS", "MPC832xMDS", "MPC83xxMDS"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8323@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; // 32 bytes - i-cache-line-size = <32>; // 32 bytes - d-cache-size = <16384>; // L1, 16K - i-cache-size = <16384>; // L1, 16K - timebase-frequency = <0>; - bus-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x08000000>; - }; - - bcsr@f8000000 { - compatible = "fsl,mpc8323mds-bcsr"; - reg = <0xf8000000 0x8000>; - }; - - soc8323@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - reg = <0xe0000000 0x00000200>; - bus-frequency = <132000000>; - - wdt@200 { - device_type = "watchdog"; - compatible = "mpc83xx_wdt"; - reg = <0x200 0x100>; - }; - - pmc: power@b00 { - compatible = "fsl,mpc8323-pmc", "fsl,mpc8349-pmc"; - reg = <0xb00 0x100 0xa00 0x100>; - interrupts = <80 0x8>; - interrupt-parent = <&ipic>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <14 0x8>; - interrupt-parent = <&ipic>; - dfsrr; - - rtc@68 { - compatible = "dallas,ds1374"; - reg = <0x68>; - }; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <9 0x8>; - interrupt-parent = <&ipic>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <10 0x8>; - interrupt-parent = <&ipic>; - }; - - dma@82a8 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8323-dma", "fsl,elo-dma"; - reg = <0x82a8 4>; - ranges = <0 0x8100 0x1a8>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - cell-index = <0>; - dma-channel@0 { - compatible = "fsl,mpc8323-dma-channel", "fsl,elo-dma-channel"; - reg = <0 0x80>; - cell-index = <0>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@80 { - compatible = "fsl,mpc8323-dma-channel", "fsl,elo-dma-channel"; - reg = <0x80 0x80>; - cell-index = <1>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@100 { - compatible = "fsl,mpc8323-dma-channel", "fsl,elo-dma-channel"; - reg = <0x100 0x80>; - cell-index = <2>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - dma-channel@180 { - compatible = "fsl,mpc8323-dma-channel", "fsl,elo-dma-channel"; - reg = <0x180 0x28>; - cell-index = <3>; - interrupt-parent = <&ipic>; - interrupts = <71 8>; - }; - }; - - crypto@30000 { - compatible = "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0"; - reg = <0x30000 0x10000>; - interrupts = <11 0x8>; - interrupt-parent = <&ipic>; - fsl,num-channels = <1>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x4c>; - fsl,descriptor-types-mask = <0x0122003f>; - sleep = <&pmc 0x03000000>; - }; - - ipic: pic@700 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x700 0x100>; - device_type = "ipic"; - }; - - par_io@1400 { - reg = <0x1400 0x100>; - device_type = "par_io"; - num-ports = <7>; - - pio3: ucc_pin@3 { - pio-map = < - /* port pin dir open_drain assignment has_irq */ - 3 4 3 0 2 0 /* MDIO */ - 3 5 1 0 2 0 /* MDC */ - 0 13 2 0 1 0 /* RX_CLK (CLK9) */ - 3 24 2 0 1 0 /* TX_CLK (CLK10) */ - 1 0 1 0 1 0 /* TxD0 */ - 1 1 1 0 1 0 /* TxD1 */ - 1 2 1 0 1 0 /* TxD2 */ - 1 3 1 0 1 0 /* TxD3 */ - 1 4 2 0 1 0 /* RxD0 */ - 1 5 2 0 1 0 /* RxD1 */ - 1 6 2 0 1 0 /* RxD2 */ - 1 7 2 0 1 0 /* RxD3 */ - 1 8 2 0 1 0 /* RX_ER */ - 1 9 1 0 1 0 /* TX_ER */ - 1 10 2 0 1 0 /* RX_DV */ - 1 11 2 0 1 0 /* COL */ - 1 12 1 0 1 0 /* TX_EN */ - 1 13 2 0 1 0>; /* CRS */ - }; - pio4: ucc_pin@4 { - pio-map = < - /* port pin dir open_drain assignment has_irq */ - 3 31 2 0 1 0 /* RX_CLK (CLK7) */ - 3 6 2 0 1 0 /* TX_CLK (CLK8) */ - 1 18 1 0 1 0 /* TxD0 */ - 1 19 1 0 1 0 /* TxD1 */ - 1 20 1 0 1 0 /* TxD2 */ - 1 21 1 0 1 0 /* TxD3 */ - 1 22 2 0 1 0 /* RxD0 */ - 1 23 2 0 1 0 /* RxD1 */ - 1 24 2 0 1 0 /* RxD2 */ - 1 25 2 0 1 0 /* RxD3 */ - 1 26 2 0 1 0 /* RX_ER */ - 1 27 1 0 1 0 /* TX_ER */ - 1 28 2 0 1 0 /* RX_DV */ - 1 29 2 0 1 0 /* COL */ - 1 30 1 0 1 0 /* TX_EN */ - 1 31 2 0 1 0>; /* CRS */ - }; - pio5: ucc_pin@5 { - pio-map = < - /* - * open has - * port pin dir drain sel irq - */ - 2 0 1 0 2 0 /* TxD5 */ - 2 8 2 0 2 0 /* RxD5 */ - - 2 29 2 0 0 0 /* CTS5 */ - 2 31 1 0 2 0 /* RTS5 */ - - 2 24 2 0 0 0 /* CD */ - - >; - }; - - }; - }; - - qe@e0100000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "qe"; - compatible = "fsl,qe"; - ranges = <0x0 0xe0100000 0x00100000>; - reg = <0xe0100000 0x480>; - brg-frequency = <0>; - bus-frequency = <198000000>; - fsl,qe-num-riscs = <1>; - fsl,qe-num-snums = <28>; - - muram@10000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,qe-muram", "fsl,cpm-muram"; - ranges = <0x0 0x00010000 0x00004000>; - - data-only@0 { - compatible = "fsl,qe-muram-data", - "fsl,cpm-muram-data"; - reg = <0x0 0x4000>; - }; - }; - - spi@4c0 { - cell-index = <0>; - compatible = "fsl,spi"; - reg = <0x4c0 0x40>; - interrupts = <2>; - interrupt-parent = <&qeic>; - mode = "cpu"; - }; - - spi@500 { - cell-index = <1>; - compatible = "fsl,spi"; - reg = <0x500 0x40>; - interrupts = <1>; - interrupt-parent = <&qeic>; - mode = "cpu"; - }; - - usb@6c0 { - compatible = "qe_udc"; - reg = <0x6c0 0x40 0x8b00 0x100>; - interrupts = <11>; - interrupt-parent = <&qeic>; - mode = "slave"; - }; - - enet0: ucc@2200 { - device_type = "network"; - compatible = "ucc_geth"; - cell-index = <3>; - reg = <0x2200 0x200>; - interrupts = <34>; - interrupt-parent = <&qeic>; - local-mac-address = [ 00 00 00 00 00 00 ]; - rx-clock-name = "clk9"; - tx-clock-name = "clk10"; - phy-handle = <&phy3>; - pio-handle = <&pio3>; - }; - - enet1: ucc@3200 { - device_type = "network"; - compatible = "ucc_geth"; - cell-index = <4>; - reg = <0x3200 0x200>; - interrupts = <35>; - interrupt-parent = <&qeic>; - local-mac-address = [ 00 00 00 00 00 00 ]; - rx-clock-name = "clk7"; - tx-clock-name = "clk8"; - phy-handle = <&phy4>; - pio-handle = <&pio4>; - }; - - ucc@2400 { - device_type = "serial"; - compatible = "ucc_uart"; - cell-index = <5>; /* The UCC number, 1-7*/ - port-number = <0>; /* Which ttyQEx device */ - soft-uart; /* We need Soft-UART */ - reg = <0x2400 0x200>; - interrupts = <40>; /* From Table 18-12 */ - interrupt-parent = < &qeic >; - /* - * For Soft-UART, we need to set TX to 1X, which - * means specifying separate clock sources. - */ - rx-clock-name = "brg5"; - tx-clock-name = "brg6"; - pio-handle = < &pio5 >; - }; - - - mdio@2320 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0x2320 0x18>; - compatible = "fsl,ucc-mdio"; - - phy3: ethernet-phy@3 { - interrupt-parent = <&ipic>; - interrupts = <17 0x8>; - reg = <0x3>; - }; - phy4: ethernet-phy@4 { - interrupt-parent = <&ipic>; - interrupts = <18 0x8>; - reg = <0x4>; - }; - }; - - qeic: interrupt-controller@80 { - interrupt-controller; - compatible = "fsl,qe-ic"; - #address-cells = <0>; - #interrupt-cells = <1>; - reg = <0x80 0x80>; - big-endian; - interrupts = <32 0x8 33 0x8>; //high:32 low:33 - interrupt-parent = <&ipic>; - }; - }; - - pci0: pci@e0008500 { - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - /* IDSEL 0x11 AD17 */ - 0x8800 0x0 0x0 0x1 &ipic 20 0x8 - 0x8800 0x0 0x0 0x2 &ipic 21 0x8 - 0x8800 0x0 0x0 0x3 &ipic 22 0x8 - 0x8800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x12 AD18 */ - 0x9000 0x0 0x0 0x1 &ipic 22 0x8 - 0x9000 0x0 0x0 0x2 &ipic 23 0x8 - 0x9000 0x0 0x0 0x3 &ipic 20 0x8 - 0x9000 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x13 AD19 */ - 0x9800 0x0 0x0 0x1 &ipic 23 0x8 - 0x9800 0x0 0x0 0x2 &ipic 20 0x8 - 0x9800 0x0 0x0 0x3 &ipic 21 0x8 - 0x9800 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x15 AD21*/ - 0xa800 0x0 0x0 0x1 &ipic 20 0x8 - 0xa800 0x0 0x0 0x2 &ipic 21 0x8 - 0xa800 0x0 0x0 0x3 &ipic 22 0x8 - 0xa800 0x0 0x0 0x4 &ipic 23 0x8 - - /* IDSEL 0x16 AD22*/ - 0xb000 0x0 0x0 0x1 &ipic 23 0x8 - 0xb000 0x0 0x0 0x2 &ipic 20 0x8 - 0xb000 0x0 0x0 0x3 &ipic 21 0x8 - 0xb000 0x0 0x0 0x4 &ipic 22 0x8 - - /* IDSEL 0x17 AD23*/ - 0xb800 0x0 0x0 0x1 &ipic 22 0x8 - 0xb800 0x0 0x0 0x2 &ipic 23 0x8 - 0xb800 0x0 0x0 0x3 &ipic 20 0x8 - 0xb800 0x0 0x0 0x4 &ipic 21 0x8 - - /* IDSEL 0x18 AD24*/ - 0xc000 0x0 0x0 0x1 &ipic 21 0x8 - 0xc000 0x0 0x0 0x2 &ipic 22 0x8 - 0xc000 0x0 0x0 0x3 &ipic 23 0x8 - 0xc000 0x0 0x0 0x4 &ipic 20 0x8>; - interrupt-parent = <&ipic>; - interrupts = <66 0x8>; - bus-range = <0x0 0x0>; - ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000 - 0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xd0000000 0x0 0x00100000>; - clock-frequency = <0>; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008500 0x100 /* internal registers */ - 0xe0008300 0x8>; /* config space access registers */ - compatible = "fsl,mpc8349-pci"; - device_type = "pci"; - sleep = <&pmc 0x00010000>; - }; -}; diff --git a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig deleted file mode 100644 index e94555452fb2..000000000000 --- a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig +++ /dev/null @@ -1,59 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_KALLSYMS is not set -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y -# CONFIG_MSDOS_PARTITION is not set -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_83xx=y -CONFIG_MPC832x_MDS=y -CONFIG_MATH_EMULATION=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_SCSI=y -CONFIG_NETDEVICES=y -CONFIG_UCC_GETH=y -CONFIG_DAVICOM_PHY=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_HW_RANDOM=y -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y -CONFIG_I2C_MPC=y -CONFIG_WATCHDOG=y -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_DS1374=y -CONFIG_QUICC_ENGINE=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V4=y -CONFIG_ROOT_NFS=y -CONFIG_CRYPTO_ECB=m -CONFIG_CRYPTO_PCBC=m diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 943c2d51bb60..8779f03bced1 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -11,7 +11,6 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC831x_RDB=y -CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_RDK=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 8afd8045004f..fde956f11ce3 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -44,7 +44,6 @@ CONFIG_EP8248E=y CONFIG_MGCOGE=y CONFIG_PPC_83xx=y CONFIG_MPC831x_RDB=y -CONFIG_MPC832x_MDS=y CONFIG_MPC832x_RDB=y CONFIG_MPC834x_ITX=y CONFIG_MPC836x_RDK=y diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 978d2b12e97c..d355ad40995f 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -25,13 +25,6 @@ config MPC831x_RDB help This option enables support for the MPC8313 RDB and MPC8315 RDB boards. -config MPC832x_MDS - bool "Freescale MPC832x MDS" - select DEFAULT_UIMAGE - select PPC_MPC832x - help - This option enables support for the MPC832x MDS evaluation board. - config MPC832x_RDB bool "Freescale MPC832x RDB" select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/83xx/Makefile b/arch/powerpc/platforms/83xx/Makefile index 0c3a5067bd77..6b4013e01b3b 100644 --- a/arch/powerpc/platforms/83xx/Makefile +++ b/arch/powerpc/platforms/83xx/Makefile @@ -10,7 +10,6 @@ obj-$(CONFIG_MPC831x_RDB) += mpc831x_rdb.o obj-$(CONFIG_MPC832x_RDB) += mpc832x_rdb.o obj-$(CONFIG_MPC834x_ITX) += mpc834x_itx.o obj-$(CONFIG_MPC836x_RDK) += mpc836x_rdk.o -obj-$(CONFIG_MPC832x_MDS) += mpc832x_mds.o obj-$(CONFIG_MPC837x_RDB) += mpc837x_rdb.o obj-$(CONFIG_ASP834x) += asp834x.o obj-$(CONFIG_KMETER1) += km83xx.o diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c deleted file mode 100644 index c08f043e3963..000000000000 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright 2006 Freescale Semiconductor, Inc. All rights reserved. - * - * Description: - * MPC832xE MDS board specific routines. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "mpc83xx.h" - -#undef DEBUG -#ifdef DEBUG -#define DBG(fmt...) udbg_printf(fmt) -#else -#define DBG(fmt...) -#endif - -/* ************************************************************************ - * - * Setup the architecture - * - */ -static void __init mpc832x_sys_setup_arch(void) -{ - struct device_node *np; - u8 __iomem *bcsr_regs = NULL; - - mpc83xx_setup_arch(); - - /* Map BCSR area */ - np = of_find_node_by_name(NULL, "bcsr"); - if (np) { - struct resource res; - - of_address_to_resource(np, 0, &res); - bcsr_regs = ioremap(res.start, resource_size(&res)); - of_node_put(np); - } - -#ifdef CONFIG_QUICC_ENGINE - if ((np = of_find_node_by_name(NULL, "par_io")) != NULL) { - par_io_init(np); - of_node_put(np); - - for_each_node_by_name(np, "ucc") - par_io_of_config(np); - } - - if ((np = of_find_compatible_node(NULL, "network", "ucc_geth")) - != NULL){ - /* Reset the Ethernet PHYs */ -#define BCSR8_FETH_RST 0x50 - clrbits8(&bcsr_regs[8], BCSR8_FETH_RST); - udelay(1000); - setbits8(&bcsr_regs[8], BCSR8_FETH_RST); - iounmap(bcsr_regs); - of_node_put(np); - } -#endif /* CONFIG_QUICC_ENGINE */ -} - -machine_device_initcall(mpc832x_mds, mpc83xx_declare_of_platform_devices); - -define_machine(mpc832x_mds) { - .name = "MPC832x MDS", - .compatible = "MPC832xMDS", - .setup_arch = mpc832x_sys_setup_arch, - .discover_phbs = mpc83xx_setup_pci, - .init_IRQ = mpc83xx_ipic_init_IRQ, - .get_irq = ipic_get_irq, - .restart = mpc83xx_restart, - .time_init = mpc83xx_time_init, - .progress = udbg_progress, -}; -- GitLab From f03425a5fd838a841138e3be586c1245fa9c78d6 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 25 Feb 2023 15:13:16 -0500 Subject: [PATCH 3469/5631] powerpc: drop HPC II (MPC7448) evaluation platform support. This was an interesting platform - it was the 1st instance of a respin of earlier 130nm 74xx CPUs on 90nm and systems using MPC7448 were positioned as a rack server platform solution. Given that, the evaluation platform (at least the one I had) was shipped in a horizontal 1/2 height Antec desktop case with retro styling and colours, despite the fact the docs explicitly stated that the HPC II is not a desktop machine (noting it had no gfx or legacy PC I/O support). Historic trivia aside, this was the 1st introduction of the e600 procfam as an evolution from the earlier G4. However even with the claim to being "1st e600" it seems the 2005+ era was turning its attention to multicore support and from my memory this poor guy was quickly overshadowed by the dual core MPC8641D. All that aside, we are once again looking at 15+ year old evaluation platforms that were not widely distributed, so 2023 removal makes sense. Signed-off-by: Paul Gortmaker Signed-off-by: Michael Ellerman Link: https://msgid.link/20230225201318.3682-2-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 3 +- arch/powerpc/boot/cuboot-mpc7448hpc2.c | 43 ---- arch/powerpc/boot/dts/mpc7448hpc2.dts | 192 ------------------ arch/powerpc/configs/mpc7448_hpc2_defconfig | 54 ----- arch/powerpc/platforms/embedded6xx/Kconfig | 10 - arch/powerpc/platforms/embedded6xx/Makefile | 1 - .../platforms/embedded6xx/mpc7448_hpc2.c | 187 ----------------- 7 files changed, 1 insertion(+), 489 deletions(-) delete mode 100644 arch/powerpc/boot/cuboot-mpc7448hpc2.c delete mode 100644 arch/powerpc/boot/dts/mpc7448hpc2.dts delete mode 100644 arch/powerpc/configs/mpc7448_hpc2_defconfig delete mode 100644 arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 911fe07d24cf..73496c5997d7 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -166,7 +166,7 @@ src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c src-plat-$(CONFIG_PPC_82xx) += cuboot-pq2.c fixed-head.S ep8248e.c cuboot-824x.c src-plat-$(CONFIG_PPC_83xx) += cuboot-83xx.c fixed-head.S redboot-83xx.c src-plat-$(CONFIG_FSL_SOC_BOOKE) += cuboot-85xx.c cuboot-85xx-cpm2.c -src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \ +src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c \ gamecube-head.S gamecube.c \ wii-head.S wii.c holly.c \ fixed-head.S mvme5100.c @@ -360,7 +360,6 @@ image-$(CONFIG_MVME7100) += dtbImage.mvme7100 # Board ports in arch/powerpc/platform/embedded6xx/Kconfig image-$(CONFIG_STORCENTER) += cuImage.storcenter -image-$(CONFIG_MPC7448HPC2) += cuImage.mpc7448hpc2 image-$(CONFIG_GAMECUBE) += dtbImage.gamecube image-$(CONFIG_WII) += dtbImage.wii image-$(CONFIG_MVME5100) += dtbImage.mvme5100 diff --git a/arch/powerpc/boot/cuboot-mpc7448hpc2.c b/arch/powerpc/boot/cuboot-mpc7448hpc2.c deleted file mode 100644 index 335fb65212e7..000000000000 --- a/arch/powerpc/boot/cuboot-mpc7448hpc2.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved. - * - * Author: Roy Zang - * - * Description: - * Old U-boot compatibility for mpc7448hpc2 board - * Based on the code of Scott Wood - * for 83xx and 85xx. - */ - -#include "ops.h" -#include "stdio.h" -#include "cuboot.h" - -#define TARGET_HAS_ETH1 -#include "ppcboot.h" - -static bd_t bd; -extern char _dtb_start[], _dtb_end[]; - -static void platform_fixups(void) -{ - void *tsi; - - dt_fixup_memory(bd.bi_memstart, bd.bi_memsize); - dt_fixup_mac_addresses(bd.bi_enetaddr, bd.bi_enet1addr); - dt_fixup_cpu_clocks(bd.bi_intfreq, bd.bi_busfreq / 4, bd.bi_busfreq); - tsi = find_node_by_devtype(NULL, "tsi-bridge"); - if (tsi) - setprop(tsi, "bus-frequency", &bd.bi_busfreq, - sizeof(bd.bi_busfreq)); -} - -void platform_init(unsigned long r3, unsigned long r4, unsigned long r5, - unsigned long r6, unsigned long r7) -{ - CUBOOT_INIT(); - fdt_init(_dtb_start); - serial_console_init(); - platform_ops.fixups = platform_fixups; -} diff --git a/arch/powerpc/boot/dts/mpc7448hpc2.dts b/arch/powerpc/boot/dts/mpc7448hpc2.dts deleted file mode 100644 index 9494af160e95..000000000000 --- a/arch/powerpc/boot/dts/mpc7448hpc2.dts +++ /dev/null @@ -1,192 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC7448HPC2 (Taiga) board Device Tree Source - * - * Copyright 2006, 2008 Freescale Semiconductor Inc. - * 2006 Roy Zang . - */ - -/dts-v1/; - -/ { - model = "mpc7448hpc2"; - compatible = "mpc74xx"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - - serial0 = &serial0; - serial1 = &serial1; - - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells =<0>; - - PowerPC,7448@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; // 32 bytes - i-cache-line-size = <32>; // 32 bytes - d-cache-size = <0x8000>; // L1, 32K bytes - i-cache-size = <0x8000>; // L1, 32K bytes - timebase-frequency = <0>; // 33 MHz, from uboot - clock-frequency = <0>; // From U-Boot - bus-frequency = <0>; // From U-Boot - }; - }; - - memory { - device_type = "memory"; - reg = <0x0 0x20000000 // DDR2 512M at 0 - >; - }; - - tsi108@c0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "tsi-bridge"; - ranges = <0x0 0xc0000000 0x10000>; - reg = <0xc0000000 0x10000>; - bus-frequency = <0>; - - i2c@7000 { - interrupt-parent = <&mpic>; - interrupts = <14 0>; - reg = <0x7000 0x400>; - device_type = "i2c"; - compatible = "tsi108-i2c"; - }; - - MDIO: mdio@6000 { - compatible = "tsi108-mdio"; - reg = <0x6000 0x50>; - #address-cells = <1>; - #size-cells = <0>; - - phy8: ethernet-phy@8 { - interrupt-parent = <&mpic>; - interrupts = <2 1>; - reg = <0x8>; - }; - - phy9: ethernet-phy@9 { - interrupt-parent = <&mpic>; - interrupts = <2 1>; - reg = <0x9>; - }; - - }; - - enet0: ethernet@6200 { - linux,network-index = <0>; - #size-cells = <0>; - device_type = "network"; - compatible = "tsi108-ethernet"; - reg = <0x6000 0x200>; - address = [ 00 06 D2 00 00 01 ]; - interrupts = <16 2>; - interrupt-parent = <&mpic>; - mdio-handle = <&MDIO>; - phy-handle = <&phy8>; - }; - - enet1: ethernet@6600 { - linux,network-index = <1>; - #address-cells = <1>; - #size-cells = <0>; - device_type = "network"; - compatible = "tsi108-ethernet"; - reg = <0x6400 0x200>; - address = [ 00 06 D2 00 00 02 ]; - interrupts = <17 2>; - interrupt-parent = <&mpic>; - mdio-handle = <&MDIO>; - phy-handle = <&phy9>; - }; - - serial0: serial@7808 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0x7808 0x200>; - clock-frequency = <1064000000>; - interrupts = <12 0>; - interrupt-parent = <&mpic>; - }; - - serial1: serial@7c08 { - device_type = "serial"; - compatible = "ns16550"; - reg = <0x7c08 0x200>; - clock-frequency = <1064000000>; - interrupts = <13 0>; - interrupt-parent = <&mpic>; - }; - - mpic: pic@7400 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x7400 0x400>; - compatible = "chrp,open-pic"; - device_type = "open-pic"; - }; - pci0: pci@1000 { - compatible = "tsi108-pci"; - device_type = "pci"; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0x1000 0x1000>; - bus-range = <0 0>; - ranges = <0x2000000 0x0 0xe0000000 0xe0000000 0x0 0x1a000000 - 0x1000000 0x0 0x0 0xfa000000 0x0 0x10000>; - clock-frequency = <133333332>; - interrupt-parent = <&mpic>; - interrupts = <23 2>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - - /* IDSEL 0x11 */ - 0x800 0x0 0x0 0x1 &RT0 0x24 0x0 - 0x800 0x0 0x0 0x2 &RT0 0x25 0x0 - 0x800 0x0 0x0 0x3 &RT0 0x26 0x0 - 0x800 0x0 0x0 0x4 &RT0 0x27 0x0 - - /* IDSEL 0x12 */ - 0x1000 0x0 0x0 0x1 &RT0 0x25 0x0 - 0x1000 0x0 0x0 0x2 &RT0 0x26 0x0 - 0x1000 0x0 0x0 0x3 &RT0 0x27 0x0 - 0x1000 0x0 0x0 0x4 &RT0 0x24 0x0 - - /* IDSEL 0x13 */ - 0x1800 0x0 0x0 0x1 &RT0 0x26 0x0 - 0x1800 0x0 0x0 0x2 &RT0 0x27 0x0 - 0x1800 0x0 0x0 0x3 &RT0 0x24 0x0 - 0x1800 0x0 0x0 0x4 &RT0 0x25 0x0 - - /* IDSEL 0x14 */ - 0x2000 0x0 0x0 0x1 &RT0 0x27 0x0 - 0x2000 0x0 0x0 0x2 &RT0 0x24 0x0 - 0x2000 0x0 0x0 0x3 &RT0 0x25 0x0 - 0x2000 0x0 0x0 0x4 &RT0 0x26 0x0 - >; - - RT0: router@1180 { - clock-frequency = <0>; - interrupt-controller; - device_type = "pic-router"; - #address-cells = <0>; - #interrupt-cells = <2>; - big-endian; - interrupts = <23 2>; - interrupt-parent = <&mpic>; - }; - }; - }; -}; diff --git a/arch/powerpc/configs/mpc7448_hpc2_defconfig b/arch/powerpc/configs/mpc7448_hpc2_defconfig deleted file mode 100644 index 19406a6c2648..000000000000 --- a/arch/powerpc/configs/mpc7448_hpc2_defconfig +++ /dev/null @@ -1,54 +0,0 @@ -CONFIG_ALTIVEC=y -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_PARTITION_ADVANCED=y -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_EMBEDDED6xx=y -CONFIG_MPC7448HPC2=y -CONFIG_GEN_RTC=y -CONFIG_BINFMT_MISC=y -# CONFIG_SECCOMP is not set -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_BLK_DEV_SD=y -CONFIG_ATA=y -CONFIG_SATA_MV=y -CONFIG_NETDEVICES=y -CONFIG_E100=y -CONFIG_8139TOO=y -# CONFIG_8139TOO_PIO is not set -CONFIG_TSI108_ETH=y -CONFIG_PHYLIB=y -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -# CONFIG_VT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_HW_RANDOM is not set -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_NFS_FS=y -CONFIG_ROOT_NFS=y -CONFIG_CRC_T10DIF=y diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index c54786f8461e..a57424d6ef20 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -29,16 +29,6 @@ config STORCENTER Select STORCENTER if configuring for the iomega StorCenter with an 8241 CPU in it. -config MPC7448HPC2 - bool "Freescale MPC7448HPC2(Taiga)" - depends on EMBEDDED6xx - select TSI108_BRIDGE - select DEFAULT_UIMAGE - select PPC_UDBG_16550 - help - Select MPC7448HPC2 if configuring for Freescale MPC7448HPC2 (Taiga) - platform - config PPC_HOLLY bool "PPC750GX/CL with TSI10x bridge (Hickory/Holly)" depends on EMBEDDED6xx diff --git a/arch/powerpc/platforms/embedded6xx/Makefile b/arch/powerpc/platforms/embedded6xx/Makefile index e656ae9f23c6..7f2a8154e5a0 100644 --- a/arch/powerpc/platforms/embedded6xx/Makefile +++ b/arch/powerpc/platforms/embedded6xx/Makefile @@ -2,7 +2,6 @@ # # Makefile for the 6xx/7xx/7xxxx linux kernel. # -obj-$(CONFIG_MPC7448HPC2) += mpc7448_hpc2.o obj-$(CONFIG_LINKSTATION) += linkstation.o ls_uart.o obj-$(CONFIG_STORCENTER) += storcenter.o obj-$(CONFIG_PPC_HOLLY) += holly.o diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c deleted file mode 100644 index ec93d69dc0ee..000000000000 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ /dev/null @@ -1,187 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * mpc7448_hpc2.c - * - * Board setup routines for the Freescale mpc7448hpc2(taiga) platform - * - * Author: Jacob Pan - * jacob.pan@freescale.com - * Author: Xianghua Xiao - * x.xiao@freescale.com - * Maintainer: Roy Zang - * Add Flat Device Tree support fot mpc7448hpc2 board - * - * Copyright 2004-2006 Freescale Semiconductor, Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#undef DEBUG -#ifdef DEBUG -#define DBG(fmt...) do { printk(fmt); } while(0) -#else -#define DBG(fmt...) do { } while(0) -#endif - -#define MPC7448HPC2_PCI_CFG_PHYS 0xfb000000 - -int mpc7448_hpc2_exclude_device(struct pci_controller *hose, - u_char bus, u_char devfn) -{ - if (bus == 0 && PCI_SLOT(devfn) == 0) - return PCIBIOS_DEVICE_NOT_FOUND; - else - return PCIBIOS_SUCCESSFUL; -} - -static void __init mpc7448_hpc2_setup_pci(void) -{ -#ifdef CONFIG_PCI - struct device_node *np; - if (ppc_md.progress) - ppc_md.progress("mpc7448_hpc2_setup_pci():set_bridge", 0); - - /* setup PCI host bridge */ - for_each_compatible_node(np, "pci", "tsi108-pci") - tsi108_setup_pci(np, MPC7448HPC2_PCI_CFG_PHYS, 0); - - ppc_md.pci_exclude_device = mpc7448_hpc2_exclude_device; - if (ppc_md.progress) - ppc_md.progress("tsi108: resources set", 0x100); -#endif -} - -static void __init mpc7448_hpc2_setup_arch(void) -{ - tsi108_csr_vir_base = get_vir_csrbase(); - - printk(KERN_INFO "MPC7448HPC2 (TAIGA) Platform\n"); - printk(KERN_INFO - "Jointly ported by Freescale and Tundra Semiconductor\n"); - printk(KERN_INFO - "Enabling L2 cache then enabling the HID0 prefetch engine.\n"); -} - -/* - * Interrupt setup and service. Interrupts on the mpc7448_hpc2 come - * from the four external INT pins, PCI interrupts are routed via - * PCI interrupt control registers, it generates internal IRQ23 - * - * Interrupt routing on the Taiga Board: - * TSI108:PB_INT[0] -> CPU0:INT# - * TSI108:PB_INT[1] -> CPU0:MCP# - * TSI108:PB_INT[2] -> N/C - * TSI108:PB_INT[3] -> N/C - */ -static void __init mpc7448_hpc2_init_IRQ(void) -{ - struct mpic *mpic; -#ifdef CONFIG_PCI - unsigned int cascade_pci_irq; - struct device_node *tsi_pci; - struct device_node *cascade_node = NULL; -#endif - - mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | - MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108, - 24, 0, - "Tsi108_PIC"); - - BUG_ON(mpic == NULL); - - mpic_assign_isu(mpic, 0, mpic->paddr + 0x100); - - mpic_init(mpic); - -#ifdef CONFIG_PCI - tsi_pci = of_find_node_by_type(NULL, "pci"); - if (tsi_pci == NULL) { - printk("%s: No tsi108 pci node found !\n", __func__); - return; - } - cascade_node = of_find_node_by_type(NULL, "pic-router"); - if (cascade_node == NULL) { - printk("%s: No tsi108 pci cascade node found !\n", __func__); - return; - } - - cascade_pci_irq = irq_of_parse_and_map(tsi_pci, 0); - DBG("%s: tsi108 cascade_pci_irq = 0x%x\n", __func__, - (u32) cascade_pci_irq); - tsi108_pci_int_init(cascade_node); - irq_set_handler_data(cascade_pci_irq, mpic); - irq_set_chained_handler(cascade_pci_irq, tsi108_irq_cascade); - - of_node_put(tsi_pci); - of_node_put(cascade_node); -#endif - /* Configure MPIC outputs to CPU0 */ - tsi108_write_reg(TSI108_MPIC_OFFSET + 0x30c, 0); -} - -void mpc7448_hpc2_show_cpuinfo(struct seq_file *m) -{ - seq_printf(m, "vendor\t\t: Freescale Semiconductor\n"); -} - -static void __noreturn mpc7448_hpc2_restart(char *cmd) -{ - local_irq_disable(); - - /* Set exception prefix high - to the firmware */ - mtmsr(mfmsr() | MSR_IP); - isync(); - - for (;;) ; /* Spin until reset happens */ -} - -static int mpc7448_machine_check_exception(struct pt_regs *regs) -{ - const struct exception_table_entry *entry; - - /* Are we prepared to handle this fault */ - if ((entry = search_exception_tables(regs->nip)) != NULL) { - tsi108_clear_pci_cfg_error(); - regs_set_recoverable(regs); - regs_set_return_ip(regs, extable_fixup(entry)); - return 1; - } - return 0; -} - -define_machine(mpc7448_hpc2){ - .name = "MPC7448 HPC2", - .compatible = "mpc74xx", - .setup_arch = mpc7448_hpc2_setup_arch, - .discover_phbs = mpc7448_hpc2_setup_pci, - .init_IRQ = mpc7448_hpc2_init_IRQ, - .show_cpuinfo = mpc7448_hpc2_show_cpuinfo, - .get_irq = mpic_get_irq, - .restart = mpc7448_hpc2_restart, - .machine_check_exception= mpc7448_machine_check_exception, - .progress = udbg_progress, -}; -- GitLab From c1d85f3f75e3c8391134b67aefc8d029b26fa38e Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 25 Feb 2023 15:13:17 -0500 Subject: [PATCH 3470/5631] powerpc: drop HPC-NET/MPC8641D evaluation platform support There is no denying that this was an interesting platform in its day. Access to a SMP powerpc platform became a bit more obtainable for folks in the BSP industry in the 2007 era, thanks to this platform. Add to that the move to the black Antec case vs. the generic white 2005 era case of the MPC8548CDS or the retro 1950s 1/2 height horizontal case of the HPC II, and it was pretty interesting to people like myself then. However, like all the other evaluation platforms, the overall system was complex out of necessity, as it tried to showcase all possible features and use-cases. That included an AMP option, where you could run two bootloaders and two kernels over two serial consoles. Peripheral sharing got a bit more tricky when you got to the hard disk and similar. In any case we still have the same circumstance. A relatively rare and expensive evaluation platform that is now 15+ years old and not out there in large numbers in the general public. Removal in 2023 just makes sense. Signed-off-by: Paul Gortmaker Signed-off-by: Michael Ellerman Link: https://msgid.link/20230225201318.3682-3-paul.gortmaker@windriver.com --- arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts | 394 ------------------ .../powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts | 337 --------------- arch/powerpc/configs/mpc86xx_base.config | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/86xx/Kconfig | 12 +- arch/powerpc/platforms/86xx/Makefile | 1 - arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 98 ----- 7 files changed, 1 insertion(+), 843 deletions(-) delete mode 100644 arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts delete mode 100644 arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts delete mode 100644 arch/powerpc/platforms/86xx/mpc86xx_hpcn.c diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts deleted file mode 100644 index f7a2430d6629..000000000000 --- a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn.dts +++ /dev/null @@ -1,394 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8641 HPCN Device Tree Source - * - * Copyright 2006 Freescale Semiconductor Inc. - */ - -/include/ "mpc8641si-pre.dtsi" - -/ { - model = "MPC8641HPCN"; - compatible = "fsl,mpc8641hpcn"; - - memory { - device_type = "memory"; - reg = <0x00000000 0x40000000>; // 1G at 0x0 - }; - - lbc: localbus@ffe05000 { - reg = <0xffe05000 0x1000>; - - ranges = <0 0 0xef800000 0x00800000 - 2 0 0xffdf8000 0x00008000 - 3 0 0xffdf0000 0x00008000>; - - flash@0,0 { - compatible = "cfi-flash"; - reg = <0 0 0x00800000>; - bank-width = <2>; - device-width = <2>; - #address-cells = <1>; - #size-cells = <1>; - partition@0 { - label = "kernel"; - reg = <0x00000000 0x00300000>; - }; - partition@300000 { - label = "firmware b"; - reg = <0x00300000 0x00100000>; - read-only; - }; - partition@400000 { - label = "fs"; - reg = <0x00400000 0x00300000>; - }; - partition@700000 { - label = "firmware a"; - reg = <0x00700000 0x00100000>; - read-only; - }; - }; - }; - - soc: soc8641@ffe00000 { - ranges = <0x00000000 0xffe00000 0x00100000>; - - enet0: ethernet@24000 { - tbi-handle = <&tbi0>; - phy-handle = <&phy0>; - phy-connection-type = "rgmii-id"; - }; - - mdio@24520 { - phy0: ethernet-phy@0 { - interrupts = <10 1 0 0>; - reg = <0>; - }; - phy1: ethernet-phy@1 { - interrupts = <10 1 0 0>; - reg = <1>; - }; - phy2: ethernet-phy@2 { - interrupts = <10 1 0 0>; - reg = <2>; - }; - phy3: ethernet-phy@3 { - interrupts = <10 1 0 0>; - reg = <3>; - }; - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet1: ethernet@25000 { - tbi-handle = <&tbi1>; - phy-handle = <&phy1>; - phy-connection-type = "rgmii-id"; - }; - - mdio@25520 { - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet2: ethernet@26000 { - tbi-handle = <&tbi2>; - phy-handle = <&phy2>; - phy-connection-type = "rgmii-id"; - }; - - mdio@26520 { - tbi2: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet3: ethernet@27000 { - tbi-handle = <&tbi3>; - phy-handle = <&phy3>; - phy-connection-type = "rgmii-id"; - }; - - mdio@27520 { - tbi3: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - rmu: rmu@d3000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,srio-rmu"; - reg = <0xd3000 0x500>; - ranges = <0x0 0xd3000 0x500>; - - message-unit@0 { - compatible = "fsl,srio-msg-unit"; - reg = <0x0 0x100>; - interrupts = < - 53 2 0 0 /* msg1_tx_irq */ - 54 2 0 0>;/* msg1_rx_irq */ - }; - message-unit@100 { - compatible = "fsl,srio-msg-unit"; - reg = <0x100 0x100>; - interrupts = < - 55 2 0 0 /* msg2_tx_irq */ - 56 2 0 0>;/* msg2_rx_irq */ - }; - doorbell-unit@400 { - compatible = "fsl,srio-dbell-unit"; - reg = <0x400 0x80>; - interrupts = < - 49 2 0 0 /* bell_outb_irq */ - 50 2 0 0>;/* bell_inb_irq */ - }; - port-write-unit@4e0 { - compatible = "fsl,srio-port-write-unit"; - reg = <0x4e0 0x20>; - interrupts = <48 2 0 0>; - }; - }; - }; - - pci0: pcie@ffe08000 { - reg = <0xffe08000 0x1000>; - ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xffc00000 0x0 0x00010000>; - interrupt-map-mask = <0xff00 0 0 7>; - interrupt-map = < - /* IDSEL 0x11 func 0 - PCI slot 1 */ - 0x8800 0 0 1 &mpic 2 1 0 0 - 0x8800 0 0 2 &mpic 3 1 0 0 - 0x8800 0 0 3 &mpic 4 1 0 0 - 0x8800 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 1 - PCI slot 1 */ - 0x8900 0 0 1 &mpic 2 1 0 0 - 0x8900 0 0 2 &mpic 3 1 0 0 - 0x8900 0 0 3 &mpic 4 1 0 0 - 0x8900 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 2 - PCI slot 1 */ - 0x8a00 0 0 1 &mpic 2 1 0 0 - 0x8a00 0 0 2 &mpic 3 1 0 0 - 0x8a00 0 0 3 &mpic 4 1 0 0 - 0x8a00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 3 - PCI slot 1 */ - 0x8b00 0 0 1 &mpic 2 1 0 0 - 0x8b00 0 0 2 &mpic 3 1 0 0 - 0x8b00 0 0 3 &mpic 4 1 0 0 - 0x8b00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 4 - PCI slot 1 */ - 0x8c00 0 0 1 &mpic 2 1 0 0 - 0x8c00 0 0 2 &mpic 3 1 0 0 - 0x8c00 0 0 3 &mpic 4 1 0 0 - 0x8c00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 5 - PCI slot 1 */ - 0x8d00 0 0 1 &mpic 2 1 0 0 - 0x8d00 0 0 2 &mpic 3 1 0 0 - 0x8d00 0 0 3 &mpic 4 1 0 0 - 0x8d00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 6 - PCI slot 1 */ - 0x8e00 0 0 1 &mpic 2 1 0 0 - 0x8e00 0 0 2 &mpic 3 1 0 0 - 0x8e00 0 0 3 &mpic 4 1 0 0 - 0x8e00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 7 - PCI slot 1 */ - 0x8f00 0 0 1 &mpic 2 1 0 0 - 0x8f00 0 0 2 &mpic 3 1 0 0 - 0x8f00 0 0 3 &mpic 4 1 0 0 - 0x8f00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x12 func 0 - PCI slot 2 */ - 0x9000 0 0 1 &mpic 3 1 0 0 - 0x9000 0 0 2 &mpic 4 1 0 0 - 0x9000 0 0 3 &mpic 1 1 0 0 - 0x9000 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 1 - PCI slot 2 */ - 0x9100 0 0 1 &mpic 3 1 0 0 - 0x9100 0 0 2 &mpic 4 1 0 0 - 0x9100 0 0 3 &mpic 1 1 0 0 - 0x9100 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 2 - PCI slot 2 */ - 0x9200 0 0 1 &mpic 3 1 0 0 - 0x9200 0 0 2 &mpic 4 1 0 0 - 0x9200 0 0 3 &mpic 1 1 0 0 - 0x9200 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 3 - PCI slot 2 */ - 0x9300 0 0 1 &mpic 3 1 0 0 - 0x9300 0 0 2 &mpic 4 1 0 0 - 0x9300 0 0 3 &mpic 1 1 0 0 - 0x9300 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 4 - PCI slot 2 */ - 0x9400 0 0 1 &mpic 3 1 0 0 - 0x9400 0 0 2 &mpic 4 1 0 0 - 0x9400 0 0 3 &mpic 1 1 0 0 - 0x9400 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 5 - PCI slot 2 */ - 0x9500 0 0 1 &mpic 3 1 0 0 - 0x9500 0 0 2 &mpic 4 1 0 0 - 0x9500 0 0 3 &mpic 1 1 0 0 - 0x9500 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 6 - PCI slot 2 */ - 0x9600 0 0 1 &mpic 3 1 0 0 - 0x9600 0 0 2 &mpic 4 1 0 0 - 0x9600 0 0 3 &mpic 1 1 0 0 - 0x9600 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 7 - PCI slot 2 */ - 0x9700 0 0 1 &mpic 3 1 0 0 - 0x9700 0 0 2 &mpic 4 1 0 0 - 0x9700 0 0 3 &mpic 1 1 0 0 - 0x9700 0 0 4 &mpic 2 1 0 0 - - // IDSEL 0x1c USB - 0xe000 0 0 1 &i8259 12 2 - 0xe100 0 0 2 &i8259 9 2 - 0xe200 0 0 3 &i8259 10 2 - 0xe300 0 0 4 &i8259 11 2 - - // IDSEL 0x1d Audio - 0xe800 0 0 1 &i8259 6 2 - - // IDSEL 0x1e Legacy - 0xf000 0 0 1 &i8259 7 2 - 0xf100 0 0 1 &i8259 7 2 - - // IDSEL 0x1f IDE/SATA - 0xf800 0 0 1 &i8259 14 2 - 0xf900 0 0 1 &i8259 5 2 - >; - - pcie@0 { - ranges = <0x02000000 0x0 0x80000000 - 0x02000000 0x0 0x80000000 - 0x0 0x20000000 - - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - uli1575@0 { - reg = <0 0 0 0 0>; - #size-cells = <2>; - #address-cells = <3>; - ranges = <0x02000000 0x0 0x80000000 - 0x02000000 0x0 0x80000000 - 0x0 0x20000000 - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - isa@1e { - device_type = "isa"; - #size-cells = <1>; - #address-cells = <2>; - reg = <0xf000 0 0 0 0>; - ranges = <1 0 0x01000000 0 0 - 0x00001000>; - interrupt-parent = <&i8259>; - - i8259: interrupt-controller@20 { - reg = <1 0x20 2 - 1 0xa0 2 - 1 0x4d0 2>; - interrupt-controller; - device_type = "interrupt-controller"; - #address-cells = <0>; - #interrupt-cells = <2>; - compatible = "chrp,iic"; - interrupts = <9 2 0 0>; - }; - - i8042@60 { - #size-cells = <0>; - #address-cells = <1>; - reg = <1 0x60 1 1 0x64 1>; - interrupts = <1 3 12 3>; - interrupt-parent = <&i8259>; - - keyboard@0 { - reg = <0>; - compatible = "pnpPNP,303"; - }; - - mouse@1 { - reg = <1>; - compatible = "pnpPNP,f03"; - }; - }; - - rtc@70 { - compatible = - "pnpPNP,b00"; - reg = <1 0x70 2>; - }; - - gpio@400 { - reg = <1 0x400 0x80>; - }; - }; - }; - }; - - }; - - pci1: pcie@ffe09000 { - reg = <0xffe09000 0x1000>; - ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xffc10000 0x0 0x00010000>; - - pcie@0 { - ranges = <0x02000000 0x0 0xa0000000 - 0x02000000 0x0 0xa0000000 - 0x0 0x20000000 - - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - }; - }; -/* - * Only one of Rapid IO or PCI can be present due to HW limitations and - * due to the fact that the 2 now share address space in the new memory - * map. The most likely case is that we have PCI, so comment out the - * rapidio node. Leave it here for reference. - - rapidio@ffec0000 { - reg = <0xffec0000 0x11000>; - compatible = "fsl,srio"; - interrupts = <48 2 0 0>; - #address-cells = <2>; - #size-cells = <2>; - fsl,srio-rmu-handle = <&rmu>; - ranges; - - port1 { - #address-cells = <2>; - #size-cells = <2>; - cell-index = <1>; - ranges = <0 0 0x80000000 0 0x20000000>; - }; - }; -*/ - -}; - -/include/ "mpc8641si-post.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts b/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts deleted file mode 100644 index 3f5f7a99b9ea..000000000000 --- a/arch/powerpc/boot/dts/fsl/mpc8641_hpcn_36b.dts +++ /dev/null @@ -1,337 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8641 HPCN Device Tree Source - * - * Copyright 2008-2009 Freescale Semiconductor Inc. - */ - -/include/ "mpc8641si-pre.dtsi" - -/ { - model = "MPC8641HPCN"; - compatible = "fsl,mpc8641hpcn"; - #address-cells = <2>; - #size-cells = <2>; - - memory { - device_type = "memory"; - reg = <0x0 0x00000000 0x0 0x40000000>; // 1G at 0x0 - }; - - lbc: localbus@fffe05000 { - reg = <0x0f 0xffe05000 0x0 0x1000>; - - ranges = <0 0 0xf 0xef800000 0x00800000 - 2 0 0xf 0xffdf8000 0x00008000 - 3 0 0xf 0xffdf0000 0x00008000>; - - flash@0,0 { - compatible = "cfi-flash"; - reg = <0 0 0x00800000>; - bank-width = <2>; - device-width = <2>; - #address-cells = <1>; - #size-cells = <1>; - partition@0 { - label = "kernel"; - reg = <0x00000000 0x00300000>; - }; - partition@300000 { - label = "firmware b"; - reg = <0x00300000 0x00100000>; - read-only; - }; - partition@400000 { - label = "fs"; - reg = <0x00400000 0x00300000>; - }; - partition@700000 { - label = "firmware a"; - reg = <0x00700000 0x00100000>; - read-only; - }; - }; - }; - - soc: soc8641@fffe00000 { - ranges = <0x00000000 0x0f 0xffe00000 0x00100000>; - - enet0: ethernet@24000 { - tbi-handle = <&tbi0>; - phy-handle = <&phy0>; - phy-connection-type = "rgmii-id"; - }; - - mdio@24520 { - phy0: ethernet-phy@0 { - interrupts = <10 1 0 0>; - reg = <0>; - }; - phy1: ethernet-phy@1 { - interrupts = <10 1 0 0>; - reg = <1>; - }; - phy2: ethernet-phy@2 { - interrupts = <10 1 0 0>; - reg = <2>; - }; - phy3: ethernet-phy@3 { - interrupts = <10 1 0 0>; - reg = <3>; - }; - tbi0: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet1: ethernet@25000 { - tbi-handle = <&tbi1>; - phy-handle = <&phy1>; - phy-connection-type = "rgmii-id"; - }; - - mdio@25520 { - tbi1: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet2: ethernet@26000 { - tbi-handle = <&tbi2>; - phy-handle = <&phy2>; - phy-connection-type = "rgmii-id"; - }; - - mdio@26520 { - tbi2: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - - enet3: ethernet@27000 { - tbi-handle = <&tbi3>; - phy-handle = <&phy3>; - phy-connection-type = "rgmii-id"; - }; - - mdio@27520 { - tbi3: tbi-phy@11 { - reg = <0x11>; - device_type = "tbi-phy"; - }; - }; - }; - - pci0: pcie@fffe08000 { - reg = <0x0f 0xffe08000 0x0 0x1000>; - ranges = <0x02000000 0x0 0xe0000000 0x0c 0x00000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0x0f 0xffc00000 0x0 0x00010000>; - interrupt-map-mask = <0xff00 0 0 7>; - interrupt-map = < - /* IDSEL 0x11 func 0 - PCI slot 1 */ - 0x8800 0 0 1 &mpic 2 1 0 0 - 0x8800 0 0 2 &mpic 3 1 0 0 - 0x8800 0 0 3 &mpic 4 1 0 0 - 0x8800 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 1 - PCI slot 1 */ - 0x8900 0 0 1 &mpic 2 1 0 0 - 0x8900 0 0 2 &mpic 3 1 0 0 - 0x8900 0 0 3 &mpic 4 1 0 0 - 0x8900 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 2 - PCI slot 1 */ - 0x8a00 0 0 1 &mpic 2 1 0 0 - 0x8a00 0 0 2 &mpic 3 1 0 0 - 0x8a00 0 0 3 &mpic 4 1 0 0 - 0x8a00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 3 - PCI slot 1 */ - 0x8b00 0 0 1 &mpic 2 1 0 0 - 0x8b00 0 0 2 &mpic 3 1 0 0 - 0x8b00 0 0 3 &mpic 4 1 0 0 - 0x8b00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 4 - PCI slot 1 */ - 0x8c00 0 0 1 &mpic 2 1 0 0 - 0x8c00 0 0 2 &mpic 3 1 0 0 - 0x8c00 0 0 3 &mpic 4 1 0 0 - 0x8c00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 5 - PCI slot 1 */ - 0x8d00 0 0 1 &mpic 2 1 0 0 - 0x8d00 0 0 2 &mpic 3 1 0 0 - 0x8d00 0 0 3 &mpic 4 1 0 0 - 0x8d00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 6 - PCI slot 1 */ - 0x8e00 0 0 1 &mpic 2 1 0 0 - 0x8e00 0 0 2 &mpic 3 1 0 0 - 0x8e00 0 0 3 &mpic 4 1 0 0 - 0x8e00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x11 func 7 - PCI slot 1 */ - 0x8f00 0 0 1 &mpic 2 1 0 0 - 0x8f00 0 0 2 &mpic 3 1 0 0 - 0x8f00 0 0 3 &mpic 4 1 0 0 - 0x8f00 0 0 4 &mpic 1 1 0 0 - - /* IDSEL 0x12 func 0 - PCI slot 2 */ - 0x9000 0 0 1 &mpic 3 1 0 0 - 0x9000 0 0 2 &mpic 4 1 0 0 - 0x9000 0 0 3 &mpic 1 1 0 0 - 0x9000 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 1 - PCI slot 2 */ - 0x9100 0 0 1 &mpic 3 1 0 0 - 0x9100 0 0 2 &mpic 4 1 0 0 - 0x9100 0 0 3 &mpic 1 1 0 0 - 0x9100 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 2 - PCI slot 2 */ - 0x9200 0 0 1 &mpic 3 1 0 0 - 0x9200 0 0 2 &mpic 4 1 0 0 - 0x9200 0 0 3 &mpic 1 1 0 0 - 0x9200 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 3 - PCI slot 2 */ - 0x9300 0 0 1 &mpic 3 1 0 0 - 0x9300 0 0 2 &mpic 4 1 0 0 - 0x9300 0 0 3 &mpic 1 1 0 0 - 0x9300 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 4 - PCI slot 2 */ - 0x9400 0 0 1 &mpic 3 1 0 0 - 0x9400 0 0 2 &mpic 4 1 0 0 - 0x9400 0 0 3 &mpic 1 1 0 0 - 0x9400 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 5 - PCI slot 2 */ - 0x9500 0 0 1 &mpic 3 1 0 0 - 0x9500 0 0 2 &mpic 4 1 0 0 - 0x9500 0 0 3 &mpic 1 1 0 0 - 0x9500 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 6 - PCI slot 2 */ - 0x9600 0 0 1 &mpic 3 1 0 0 - 0x9600 0 0 2 &mpic 4 1 0 0 - 0x9600 0 0 3 &mpic 1 1 0 0 - 0x9600 0 0 4 &mpic 2 1 0 0 - - /* IDSEL 0x12 func 7 - PCI slot 2 */ - 0x9700 0 0 1 &mpic 3 1 0 0 - 0x9700 0 0 2 &mpic 4 1 0 0 - 0x9700 0 0 3 &mpic 1 1 0 0 - 0x9700 0 0 4 &mpic 2 1 0 0 - - // IDSEL 0x1c USB - 0xe000 0 0 1 &i8259 12 2 - 0xe100 0 0 2 &i8259 9 2 - 0xe200 0 0 3 &i8259 10 2 - 0xe300 0 0 4 &i8259 11 2 - - // IDSEL 0x1d Audio - 0xe800 0 0 1 &i8259 6 2 - - // IDSEL 0x1e Legacy - 0xf000 0 0 1 &i8259 7 2 - 0xf100 0 0 1 &i8259 7 2 - - // IDSEL 0x1f IDE/SATA - 0xf800 0 0 1 &i8259 14 2 - 0xf900 0 0 1 &i8259 5 2 - >; - - pcie@0 { - ranges = <0x02000000 0x0 0xe0000000 - 0x02000000 0x0 0xe0000000 - 0x0 0x20000000 - - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - uli1575@0 { - reg = <0 0 0 0 0>; - #size-cells = <2>; - #address-cells = <3>; - ranges = <0x02000000 0x0 0xe0000000 - 0x02000000 0x0 0xe0000000 - 0x0 0x20000000 - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - isa@1e { - device_type = "isa"; - #size-cells = <1>; - #address-cells = <2>; - reg = <0xf000 0 0 0 0>; - ranges = <1 0 0x01000000 0 0 - 0x00001000>; - interrupt-parent = <&i8259>; - - i8259: interrupt-controller@20 { - reg = <1 0x20 2 - 1 0xa0 2 - 1 0x4d0 2>; - interrupt-controller; - device_type = "interrupt-controller"; - #address-cells = <0>; - #interrupt-cells = <2>; - compatible = "chrp,iic"; - interrupts = <9 2 0 0>; - }; - - i8042@60 { - #size-cells = <0>; - #address-cells = <1>; - reg = <1 0x60 1 1 0x64 1>; - interrupts = <1 3 12 3>; - interrupt-parent = <&i8259>; - - keyboard@0 { - reg = <0>; - compatible = "pnpPNP,303"; - }; - - mouse@1 { - reg = <1>; - compatible = "pnpPNP,f03"; - }; - }; - - rtc@70 { - compatible = - "pnpPNP,b00"; - reg = <1 0x70 2>; - }; - - gpio@400 { - reg = <1 0x400 0x80>; - }; - }; - }; - }; - - }; - - pci1: pcie@fffe09000 { - reg = <0x0f 0xffe09000 0x0 0x1000>; - ranges = <0x02000000 0x0 0xe0000000 0x0c 0x20000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0x0f 0xffc10000 0x0 0x00010000>; - - pcie@0 { - ranges = <0x02000000 0x0 0xe0000000 - 0x02000000 0x0 0xe0000000 - 0x0 0x20000000 - - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00010000>; - }; - }; -}; - -/include/ "mpc8641si-post.dtsi" diff --git a/arch/powerpc/configs/mpc86xx_base.config b/arch/powerpc/configs/mpc86xx_base.config index 588870e6af3b..9f7a232c9357 100644 --- a/arch/powerpc/configs/mpc86xx_base.config +++ b/arch/powerpc/configs/mpc86xx_base.config @@ -1,5 +1,4 @@ CONFIG_PPC_86xx=y -CONFIG_MPC8641_HPCN=y CONFIG_MPC8610_HPCD=y CONFIG_GEF_PPC9A=y CONFIG_GEF_SBC310=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index fde956f11ce3..670f4ca3fb3c 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -50,7 +50,6 @@ CONFIG_MPC836x_RDK=y CONFIG_MPC837x_RDB=y CONFIG_ASP834x=y CONFIG_PPC_86xx=y -CONFIG_MPC8641_HPCN=y CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index be867abebc83..4fe385f37f3b 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -10,16 +10,6 @@ menuconfig PPC_86xx if PPC_86xx -config MPC8641_HPCN - bool "Freescale MPC8641 HPCN" - select PPC_I8259 - select DEFAULT_UIMAGE - select FSL_ULI1575 if PCI - select HAVE_RAPIDIO - select SWIOTLB - help - This option enables support for the MPC8641 HPCN board. - config MPC8610_HPCD bool "Freescale MPC8610 HPCD" select DEFAULT_UIMAGE @@ -68,7 +58,7 @@ config MPC8641 select FSL_PCI if PCI select PPC_UDBG_16550 select MPIC - default y if MPC8641_HPCN || GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \ + default y if GEF_SBC610 || GEF_SBC310 || GEF_PPC9A \ || MVME7100 config MPC8610 diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile index 5bbe1475bf26..ab2c15114228 100644 --- a/arch/powerpc/platforms/86xx/Makefile +++ b/arch/powerpc/platforms/86xx/Makefile @@ -5,7 +5,6 @@ obj-y := pic.o common.o obj-$(CONFIG_SMP) += mpc86xx_smp.o -obj-$(CONFIG_MPC8641_HPCN) += mpc86xx_hpcn.o obj-$(CONFIG_MPC8610_HPCD) += mpc8610_hpcd.o obj-$(CONFIG_GEF_SBC610) += gef_sbc610.o obj-$(CONFIG_GEF_SBC310) += gef_sbc310.o diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c deleted file mode 100644 index 812110673d88..000000000000 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ /dev/null @@ -1,98 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC86xx HPCN board specific routines - * - * Recode: ZHANG WEI - * Initial author: Xianghua Xiao - * - * Copyright 2006 Freescale Semiconductor Inc. - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -#include - -#include -#include - -#include "mpc86xx.h" - -#undef DEBUG - -#ifdef DEBUG -#define DBG(fmt...) do { printk(KERN_ERR fmt); } while(0) -#else -#define DBG(fmt...) do { } while(0) -#endif - - -static void __init -mpc86xx_hpcn_setup_arch(void) -{ - if (ppc_md.progress) - ppc_md.progress("mpc86xx_hpcn_setup_arch()", 0); - - printk("MPC86xx HPCN board from Freescale Semiconductor\n"); - -#ifdef CONFIG_SMP - mpc86xx_smp_init(); -#endif - - fsl_pci_assign_primary(); - uli_init(); - - swiotlb_detect_4g(); -} - - -static void -mpc86xx_hpcn_show_cpuinfo(struct seq_file *m) -{ - uint svid = mfspr(SPRN_SVR); - - seq_printf(m, "Vendor\t\t: Freescale Semiconductor\n"); - - seq_printf(m, "SVR\t\t: 0x%x\n", svid); -} - -static const struct of_device_id of_bus_ids[] __initconst = { - { .compatible = "fsl,srio", }, - {}, -}; - -static int __init declare_of_platform_devices(void) -{ - mpc86xx_common_publish_devices(); - of_platform_bus_probe(NULL, of_bus_ids, NULL); - - return 0; -} -machine_arch_initcall(mpc86xx_hpcn, declare_of_platform_devices); - -define_machine(mpc86xx_hpcn) { - .name = "MPC86xx HPCN", - .compatible = "fsl,MPC8610HPCD", - .setup_arch = mpc86xx_hpcn_setup_arch, - .init_IRQ = mpc86xx_init_irq, - .show_cpuinfo = mpc86xx_hpcn_show_cpuinfo, - .get_irq = mpic_get_irq, - .time_init = mpc86xx_time_init, - .progress = udbg_progress, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif -}; -- GitLab From 248667f8bbded6c00a300dbcabe0d15b3d0de9ab Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 25 Feb 2023 15:13:18 -0500 Subject: [PATCH 3471/5631] powerpc: drop HPCD/MPC8610 evaluation platform support This evaluation platform was essentially a single core 8641 with integrated graphics/display support - in an effort to reduce chip count on kiosk and similar applications. Compared to other evaluation platforms considered for removal in other recent commits, this platform was relatively rare. Unlike all the other 10+ platforms, I couldn't find any documentation on it - just a link to downloading the 2007 era BSP in "LTIB" format as was done back then. With all that in mind, it seems prudent to remove it here in 2023. Signed-off-by: Paul Gortmaker [mpe: Drop stale reference to MPC8610_HPCD in 86xx/Kconfig] Signed-off-by: Michael Ellerman Link: https://msgid.link/20230225201318.3682-4-paul.gortmaker@windriver.com --- arch/powerpc/boot/dts/mpc8610_hpcd.dts | 503 --------------------- arch/powerpc/configs/mpc86xx_base.config | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/86xx/Kconfig | 8 - arch/powerpc/platforms/86xx/Makefile | 1 - arch/powerpc/platforms/86xx/mpc8610_hpcd.c | 321 ------------- 6 files changed, 835 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc8610_hpcd.dts delete mode 100644 arch/powerpc/platforms/86xx/mpc8610_hpcd.c diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts deleted file mode 100644 index 33bbe58c1ad0..000000000000 --- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts +++ /dev/null @@ -1,503 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * MPC8610 HPCD Device Tree Source - * - * Copyright 2007-2008 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "MPC8610HPCD"; - compatible = "fsl,MPC8610HPCD"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - pci1 = &pci1; - pci2 = &pci2; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8610@0 { - device_type = "cpu"; - reg = <0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <32768>; // L1 - i-cache-size = <32768>; // L1 - sleep = <&pmc 0x00008000 0 // core - &pmc 0x00004000 0>; // timebase - timebase-frequency = <0>; // From uboot - bus-frequency = <0>; // From uboot - clock-frequency = <0>; // From uboot - }; - }; - - memory { - device_type = "memory"; - reg = <0x00000000 0x20000000>; // 512M at 0x0 - }; - - localbus@e0005000 { - #address-cells = <2>; - #size-cells = <1>; - compatible = "fsl,mpc8610-elbc", "fsl,elbc", "simple-bus"; - reg = <0xe0005000 0x1000>; - interrupts = <19 2>; - interrupt-parent = <&mpic>; - ranges = <0 0 0xf8000000 0x08000000 - 1 0 0xf0000000 0x08000000 - 2 0 0xe8400000 0x00008000 - 4 0 0xe8440000 0x00008000 - 5 0 0xe8480000 0x00008000 - 6 0 0xe84c0000 0x00008000 - 3 0 0xe8000000 0x00000020>; - sleep = <&pmc 0x08000000 0>; - - flash@0,0 { - compatible = "cfi-flash"; - reg = <0 0 0x8000000>; - bank-width = <2>; - device-width = <1>; - }; - - flash@1,0 { - compatible = "cfi-flash"; - reg = <1 0 0x8000000>; - bank-width = <2>; - device-width = <1>; - }; - - flash@2,0 { - compatible = "fsl,mpc8610-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <2 0 0x8000>; - }; - - flash@4,0 { - compatible = "fsl,mpc8610-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <4 0 0x8000>; - }; - - flash@5,0 { - compatible = "fsl,mpc8610-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <5 0 0x8000>; - }; - - flash@6,0 { - compatible = "fsl,mpc8610-fcm-nand", - "fsl,elbc-fcm-nand"; - reg = <6 0 0x8000>; - }; - - board-control@3,0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,fpga-pixis"; - reg = <3 0 0x20>; - ranges = <0 3 0 0x20>; - interrupt-parent = <&mpic>; - interrupts = <8 8>; - - sdcsr_pio: gpio-controller@a { - #gpio-cells = <2>; - compatible = "fsl,fpga-pixis-gpio-bank"; - reg = <0xa 1>; - gpio-controller; - }; - }; - }; - - soc@e0000000 { - #address-cells = <1>; - #size-cells = <1>; - #interrupt-cells = <2>; - device_type = "soc"; - compatible = "fsl,mpc8610-immr", "simple-bus"; - ranges = <0x0 0xe0000000 0x00100000>; - bus-frequency = <0>; - - mcm-law@0 { - compatible = "fsl,mcm-law"; - reg = <0x0 0x1000>; - fsl,num-laws = <10>; - }; - - mcm@1000 { - compatible = "fsl,mpc8610-mcm", "fsl,mcm"; - reg = <0x1000 0x1000>; - interrupts = <17 2>; - interrupt-parent = <&mpic>; - }; - - i2c@3000 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <0>; - compatible = "fsl-i2c"; - reg = <0x3000 0x100>; - interrupts = <43 2>; - interrupt-parent = <&mpic>; - dfsrr; - - cs4270:codec@4f { - compatible = "cirrus,cs4270"; - reg = <0x4f>; - /* MCLK source is a stand-alone oscillator */ - clock-frequency = <12288000>; - }; - }; - - i2c@3100 { - #address-cells = <1>; - #size-cells = <0>; - cell-index = <1>; - compatible = "fsl-i2c"; - reg = <0x3100 0x100>; - interrupts = <43 2>; - interrupt-parent = <&mpic>; - sleep = <&pmc 0x00000004 0>; - dfsrr; - }; - - serial0: serial@4500 { - cell-index = <0>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4500 0x100>; - clock-frequency = <0>; - interrupts = <42 2>; - interrupt-parent = <&mpic>; - sleep = <&pmc 0x00000002 0>; - }; - - serial1: serial@4600 { - cell-index = <1>; - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550"; - reg = <0x4600 0x100>; - clock-frequency = <0>; - interrupts = <42 2>; - interrupt-parent = <&mpic>; - sleep = <&pmc 0x00000008 0>; - }; - - spi@7000 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,mpc8610-spi", "fsl,spi"; - reg = <0x7000 0x40>; - cell-index = <0>; - interrupts = <59 2>; - interrupt-parent = <&mpic>; - mode = "cpu"; - cs-gpios = <&sdcsr_pio 7 0>; - sleep = <&pmc 0x00000800 0>; - - mmc-slot@0 { - compatible = "fsl,mpc8610hpcd-mmc-slot", - "mmc-spi-slot"; - reg = <0>; - gpios = <&sdcsr_pio 0 1 /* nCD */ - &sdcsr_pio 1 0>; /* WP */ - voltage-ranges = <3300 3300>; - spi-max-frequency = <50000000>; - }; - }; - - display@2c000 { - compatible = "fsl,diu"; - reg = <0x2c000 100>; - interrupts = <72 2>; - interrupt-parent = <&mpic>; - sleep = <&pmc 0x04000000 0>; - }; - - mpic: interrupt-controller@40000 { - interrupt-controller; - #address-cells = <0>; - #interrupt-cells = <2>; - reg = <0x40000 0x40000>; - compatible = "chrp,open-pic"; - device_type = "open-pic"; - }; - - msi@41600 { - compatible = "fsl,mpc8610-msi", "fsl,mpic-msi"; - reg = <0x41600 0x80>; - msi-available-ranges = <0 0x100>; - interrupts = < - 0xe0 0 - 0xe1 0 - 0xe2 0 - 0xe3 0 - 0xe4 0 - 0xe5 0 - 0xe6 0 - 0xe7 0>; - interrupt-parent = <&mpic>; - }; - - global-utilities@e0000 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8610-guts"; - reg = <0xe0000 0x1000>; - ranges = <0 0xe0000 0x1000>; - fsl,has-rstcr; - - pmc: power@70 { - compatible = "fsl,mpc8610-pmc", - "fsl,mpc8641d-pmc"; - reg = <0x70 0x20>; - }; - }; - - wdt@e4000 { - compatible = "fsl,mpc8610-wdt"; - reg = <0xe4000 0x100>; - }; - - ssi@16000 { - compatible = "fsl,mpc8610-ssi"; - cell-index = <0>; - reg = <0x16000 0x100>; - interrupt-parent = <&mpic>; - interrupts = <62 2>; - fsl,mode = "i2s-slave"; - codec-handle = <&cs4270>; - fsl,playback-dma = <&dma00>; - fsl,capture-dma = <&dma01>; - fsl,fifo-depth = <8>; - sleep = <&pmc 0 0x08000000>; - }; - - ssi@16100 { - compatible = "fsl,mpc8610-ssi"; - status = "disabled"; - cell-index = <1>; - reg = <0x16100 0x100>; - interrupt-parent = <&mpic>; - interrupts = <63 2>; - fsl,fifo-depth = <8>; - sleep = <&pmc 0 0x04000000>; - }; - - dma@21300 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8610-dma", "fsl,eloplus-dma"; - cell-index = <0>; - reg = <0x21300 0x4>; /* DMA general status register */ - ranges = <0x0 0x21100 0x200>; - sleep = <&pmc 0x00000400 0>; - - dma00: dma-channel@0 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,ssi-dma-channel"; - cell-index = <0>; - reg = <0x0 0x80>; - interrupt-parent = <&mpic>; - interrupts = <20 2>; - }; - dma01: dma-channel@1 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,ssi-dma-channel"; - cell-index = <1>; - reg = <0x80 0x80>; - interrupt-parent = <&mpic>; - interrupts = <21 2>; - }; - dma-channel@2 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <2>; - reg = <0x100 0x80>; - interrupt-parent = <&mpic>; - interrupts = <22 2>; - }; - dma-channel@3 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <3>; - reg = <0x180 0x80>; - interrupt-parent = <&mpic>; - interrupts = <23 2>; - }; - }; - - dma@c300 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8610-dma", "fsl,eloplus-dma"; - cell-index = <1>; - reg = <0xc300 0x4>; /* DMA general status register */ - ranges = <0x0 0xc100 0x200>; - sleep = <&pmc 0x00000200 0>; - - dma-channel@0 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <0>; - reg = <0x0 0x80>; - interrupt-parent = <&mpic>; - interrupts = <76 2>; - }; - dma-channel@1 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <1>; - reg = <0x80 0x80>; - interrupt-parent = <&mpic>; - interrupts = <77 2>; - }; - dma-channel@2 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <2>; - reg = <0x100 0x80>; - interrupt-parent = <&mpic>; - interrupts = <78 2>; - }; - dma-channel@3 { - compatible = "fsl,mpc8610-dma-channel", - "fsl,eloplus-dma-channel"; - cell-index = <3>; - reg = <0x180 0x80>; - interrupt-parent = <&mpic>; - interrupts = <79 2>; - }; - }; - - }; - - pci0: pci@e0008000 { - compatible = "fsl,mpc8610-pci"; - device_type = "pci"; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe0008000 0x1000>; - bus-range = <0 0>; - ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe1000000 0x0 0x00100000>; - sleep = <&pmc 0x80000000 0>; - clock-frequency = <33333333>; - interrupt-parent = <&mpic>; - interrupts = <24 2>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = < - /* IDSEL 0x11 */ - 0x8800 0 0 1 &mpic 4 1 - 0x8800 0 0 2 &mpic 5 1 - 0x8800 0 0 3 &mpic 6 1 - 0x8800 0 0 4 &mpic 7 1 - - /* IDSEL 0x12 */ - 0x9000 0 0 1 &mpic 5 1 - 0x9000 0 0 2 &mpic 6 1 - 0x9000 0 0 3 &mpic 7 1 - 0x9000 0 0 4 &mpic 4 1 - >; - }; - - pci1: pcie@e000a000 { - compatible = "fsl,mpc8641-pcie"; - device_type = "pci"; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - reg = <0xe000a000 0x1000>; - bus-range = <1 3>; - ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000 - 0x01000000 0x0 0x00000000 0xe3000000 0x0 0x00100000>; - sleep = <&pmc 0x40000000 0>; - clock-frequency = <33333333>; - interrupt-parent = <&mpic>; - interrupts = <26 2>; - interrupt-map-mask = <0xf800 0 0 7>; - - interrupt-map = < - /* IDSEL 0x1b */ - 0xd800 0 0 1 &mpic 2 1 - - /* IDSEL 0x1c*/ - 0xe000 0 0 1 &mpic 1 1 - 0xe000 0 0 2 &mpic 1 1 - 0xe000 0 0 3 &mpic 1 1 - 0xe000 0 0 4 &mpic 1 1 - - /* IDSEL 0x1f */ - 0xf800 0 0 1 &mpic 3 2 - 0xf800 0 0 2 &mpic 0 1 - >; - - pcie@0 { - reg = <0 0 0 0 0>; - #size-cells = <2>; - #address-cells = <3>; - device_type = "pci"; - ranges = <0x02000000 0x0 0xa0000000 - 0x02000000 0x0 0xa0000000 - 0x0 0x10000000 - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00100000>; - uli1575@0 { - reg = <0 0 0 0 0>; - #size-cells = <2>; - #address-cells = <3>; - ranges = <0x02000000 0x0 0xa0000000 - 0x02000000 0x0 0xa0000000 - 0x0 0x10000000 - 0x01000000 0x0 0x00000000 - 0x01000000 0x0 0x00000000 - 0x0 0x00100000>; - - isa@1e { - device_type = "isa"; - #size-cells = <1>; - #address-cells = <2>; - reg = <0xf000 0 0 0 0>; - ranges = <1 0 0x01000000 0 0 - 0x00001000>; - - rtc@70 { - compatible = "pnpPNP,b00"; - reg = <1 0x70 2>; - }; - }; - }; - }; - }; - - pci2: pcie@e0009000 { - #address-cells = <3>; - #size-cells = <2>; - #interrupt-cells = <1>; - device_type = "pci"; - compatible = "fsl,mpc8641-pcie"; - reg = <0xe0009000 0x00001000>; - ranges = <0x02000000 0 0x90000000 0x90000000 0 0x10000000 - 0x01000000 0 0x00000000 0xe2000000 0 0x00100000>; - bus-range = <0 255>; - interrupt-map-mask = <0xf800 0 0 7>; - interrupt-map = <0x0000 0 0 1 &mpic 4 1 - 0x0000 0 0 2 &mpic 5 1 - 0x0000 0 0 3 &mpic 6 1 - 0x0000 0 0 4 &mpic 7 1>; - interrupt-parent = <&mpic>; - interrupts = <25 2>; - sleep = <&pmc 0x20000000 0>; - clock-frequency = <33333333>; - }; -}; diff --git a/arch/powerpc/configs/mpc86xx_base.config b/arch/powerpc/configs/mpc86xx_base.config index 9f7a232c9357..632c014b122d 100644 --- a/arch/powerpc/configs/mpc86xx_base.config +++ b/arch/powerpc/configs/mpc86xx_base.config @@ -1,5 +1,4 @@ CONFIG_PPC_86xx=y -CONFIG_MPC8610_HPCD=y CONFIG_GEF_PPC9A=y CONFIG_GEF_SBC310=y CONFIG_GEF_SBC610=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 670f4ca3fb3c..fcdb3a25e895 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -50,7 +50,6 @@ CONFIG_MPC836x_RDK=y CONFIG_MPC837x_RDB=y CONFIG_ASP834x=y CONFIG_PPC_86xx=y -CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_STAT=y diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index 4fe385f37f3b..8bfafc9d2bf7 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -10,13 +10,6 @@ menuconfig PPC_86xx if PPC_86xx -config MPC8610_HPCD - bool "Freescale MPC8610 HPCD" - select DEFAULT_UIMAGE - select FSL_ULI1575 if PCI - help - This option enables support for the MPC8610 HPCD board. - config GEF_PPC9A bool "GE PPC9A" select DEFAULT_UIMAGE @@ -67,4 +60,3 @@ config MPC8610 select FSL_PCI if PCI select PPC_UDBG_16550 select MPIC - default y if MPC8610_HPCD diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile index ab2c15114228..dafbc037ff42 100644 --- a/arch/powerpc/platforms/86xx/Makefile +++ b/arch/powerpc/platforms/86xx/Makefile @@ -5,7 +5,6 @@ obj-y := pic.o common.o obj-$(CONFIG_SMP) += mpc86xx_smp.o -obj-$(CONFIG_MPC8610_HPCD) += mpc8610_hpcd.o obj-$(CONFIG_GEF_SBC610) += gef_sbc610.o obj-$(CONFIG_GEF_SBC310) += gef_sbc310.o obj-$(CONFIG_GEF_PPC9A) += gef_ppc9a.o diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c deleted file mode 100644 index 6a403705ae44..000000000000 --- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c +++ /dev/null @@ -1,321 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8610 HPCD board specific routines - * - * Initial author: Xianghua Xiao - * Recode: Jason Jin - * York Sun - * - * Rewrite the interrupt routing. remove the 8259PIC support, - * All the integrated device in ULI use sideband interrupt. - * - * Copyright 2008 Freescale Semiconductor Inc. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include - -#include -#include -#include - -#include "mpc86xx.h" - -static struct device_node *pixis_node; -static unsigned char *pixis_bdcfg0, *pixis_arch; - -/* DIU Pixel Clock bits of the CLKDVDR Global Utilities register */ -#define CLKDVDR_PXCKEN 0x80000000 -#define CLKDVDR_PXCKINV 0x10000000 -#define CLKDVDR_PXCKDLY 0x06000000 -#define CLKDVDR_PXCLK_MASK 0x001F0000 - -#ifdef CONFIG_SUSPEND -static irqreturn_t mpc8610_sw9_irq(int irq, void *data) -{ - pr_debug("%s: PIXIS' event (sw9/wakeup) IRQ handled\n", __func__); - return IRQ_HANDLED; -} - -static void __init mpc8610_suspend_init(void) -{ - int irq; - int ret; - - if (!pixis_node) - return; - - irq = irq_of_parse_and_map(pixis_node, 0); - if (!irq) { - pr_err("%s: can't map pixis event IRQ.\n", __func__); - return; - } - - ret = request_irq(irq, mpc8610_sw9_irq, 0, "sw9:wakeup", NULL); - if (ret) { - pr_err("%s: can't request pixis event IRQ: %d\n", - __func__, ret); - irq_dispose_mapping(irq); - } - - enable_irq_wake(irq); -} -#else -static inline void mpc8610_suspend_init(void) { } -#endif /* CONFIG_SUSPEND */ - -static const struct of_device_id mpc8610_ids[] __initconst = { - { .compatible = "fsl,mpc8610-immr", }, - { .compatible = "fsl,mpc8610-guts", }, - /* So that the DMA channel nodes can be probed individually: */ - { .compatible = "fsl,eloplus-dma", }, - /* PCI controllers */ - { .compatible = "fsl,mpc8610-pci", }, - {} -}; - -static int __init mpc8610_declare_of_platform_devices(void) -{ - /* Enable wakeup on PIXIS' event IRQ. */ - mpc8610_suspend_init(); - - mpc86xx_common_publish_devices(); - - /* Without this call, the SSI device driver won't get probed. */ - of_platform_bus_probe(NULL, mpc8610_ids, NULL); - - return 0; -} -machine_arch_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices); - -#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - -/* - * DIU Area Descriptor - * - * The MPC8610 reference manual shows the bits of the AD register in - * little-endian order, which causes the BLUE_C field to be split into two - * parts. To simplify the definition of the MAKE_AD() macro, we define the - * fields in big-endian order and byte-swap the result. - * - * So even though the registers don't look like they're in the - * same bit positions as they are on the P1022, the same value is written to - * the AD register on the MPC8610 and on the P1022. - */ -#define AD_BYTE_F 0x10000000 -#define AD_ALPHA_C_MASK 0x0E000000 -#define AD_ALPHA_C_SHIFT 25 -#define AD_BLUE_C_MASK 0x01800000 -#define AD_BLUE_C_SHIFT 23 -#define AD_GREEN_C_MASK 0x00600000 -#define AD_GREEN_C_SHIFT 21 -#define AD_RED_C_MASK 0x00180000 -#define AD_RED_C_SHIFT 19 -#define AD_PALETTE 0x00040000 -#define AD_PIXEL_S_MASK 0x00030000 -#define AD_PIXEL_S_SHIFT 16 -#define AD_COMP_3_MASK 0x0000F000 -#define AD_COMP_3_SHIFT 12 -#define AD_COMP_2_MASK 0x00000F00 -#define AD_COMP_2_SHIFT 8 -#define AD_COMP_1_MASK 0x000000F0 -#define AD_COMP_1_SHIFT 4 -#define AD_COMP_0_MASK 0x0000000F -#define AD_COMP_0_SHIFT 0 - -#define MAKE_AD(alpha, red, blue, green, size, c0, c1, c2, c3) \ - cpu_to_le32(AD_BYTE_F | (alpha << AD_ALPHA_C_SHIFT) | \ - (blue << AD_BLUE_C_SHIFT) | (green << AD_GREEN_C_SHIFT) | \ - (red << AD_RED_C_SHIFT) | (c3 << AD_COMP_3_SHIFT) | \ - (c2 << AD_COMP_2_SHIFT) | (c1 << AD_COMP_1_SHIFT) | \ - (c0 << AD_COMP_0_SHIFT) | (size << AD_PIXEL_S_SHIFT)) - -u32 mpc8610hpcd_get_pixel_format(enum fsl_diu_monitor_port port, - unsigned int bits_per_pixel) -{ - static const u32 pixelformat[][3] = { - { - MAKE_AD(3, 0, 2, 1, 3, 8, 8, 8, 8), - MAKE_AD(4, 2, 0, 1, 2, 8, 8, 8, 0), - MAKE_AD(4, 0, 2, 1, 1, 5, 6, 5, 0) - }, - { - MAKE_AD(3, 2, 0, 1, 3, 8, 8, 8, 8), - MAKE_AD(4, 0, 2, 1, 2, 8, 8, 8, 0), - MAKE_AD(4, 2, 0, 1, 1, 5, 6, 5, 0) - }, - }; - unsigned int arch_monitor; - - /* The DVI port is mis-wired on revision 1 of this board. */ - arch_monitor = - ((*pixis_arch == 0x01) && (port == FSL_DIU_PORT_DVI)) ? 0 : 1; - - switch (bits_per_pixel) { - case 32: - return pixelformat[arch_monitor][0]; - case 24: - return pixelformat[arch_monitor][1]; - case 16: - return pixelformat[arch_monitor][2]; - default: - pr_err("fsl-diu: unsupported pixel depth %u\n", bits_per_pixel); - return 0; - } -} - -void mpc8610hpcd_set_gamma_table(enum fsl_diu_monitor_port port, - char *gamma_table_base) -{ - int i; - if (port == FSL_DIU_PORT_DLVDS) { - for (i = 0; i < 256*3; i++) - gamma_table_base[i] = (gamma_table_base[i] << 2) | - ((gamma_table_base[i] >> 6) & 0x03); - } -} - -#define PX_BRDCFG0_DVISEL (1 << 3) -#define PX_BRDCFG0_DLINK (1 << 4) -#define PX_BRDCFG0_DIU_MASK (PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK) - -void mpc8610hpcd_set_monitor_port(enum fsl_diu_monitor_port port) -{ - switch (port) { - case FSL_DIU_PORT_DVI: - clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK, - PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK); - break; - case FSL_DIU_PORT_LVDS: - clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK, - PX_BRDCFG0_DLINK); - break; - case FSL_DIU_PORT_DLVDS: - clrbits8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK); - break; - } -} - -/** - * mpc8610hpcd_set_pixel_clock: program the DIU's clock - * - * @pixclock: the wavelength, in picoseconds, of the clock - */ -void mpc8610hpcd_set_pixel_clock(unsigned int pixclock) -{ - struct device_node *guts_np = NULL; - struct ccsr_guts __iomem *guts; - unsigned long freq; - u64 temp; - u32 pxclk; - - /* Map the global utilities registers. */ - guts_np = of_find_compatible_node(NULL, NULL, "fsl,mpc8610-guts"); - if (!guts_np) { - pr_err("mpc8610hpcd: missing global utilities device node\n"); - return; - } - - guts = of_iomap(guts_np, 0); - of_node_put(guts_np); - if (!guts) { - pr_err("mpc8610hpcd: could not map global utilities device\n"); - return; - } - - /* Convert pixclock from a wavelength to a frequency */ - temp = 1000000000000ULL; - do_div(temp, pixclock); - freq = temp; - - /* - * 'pxclk' is the ratio of the platform clock to the pixel clock. - * On the MPC8610, the value programmed into CLKDVDR is the ratio - * minus one. The valid range of values is 2-31. - */ - pxclk = DIV_ROUND_CLOSEST(fsl_get_sys_freq(), freq) - 1; - pxclk = clamp_t(u32, pxclk, 2, 31); - - /* Disable the pixel clock, and set it to non-inverted and no delay */ - clrbits32(&guts->clkdvdr, - CLKDVDR_PXCKEN | CLKDVDR_PXCKDLY | CLKDVDR_PXCLK_MASK); - - /* Enable the clock and set the pxclk */ - setbits32(&guts->clkdvdr, CLKDVDR_PXCKEN | (pxclk << 16)); - - iounmap(guts); -} - -enum fsl_diu_monitor_port -mpc8610hpcd_valid_monitor_port(enum fsl_diu_monitor_port port) -{ - return port; -} - -#endif - -static void __init mpc86xx_hpcd_setup_arch(void) -{ - struct resource r; - unsigned char *pixis; - - if (ppc_md.progress) - ppc_md.progress("mpc86xx_hpcd_setup_arch()", 0); - - fsl_pci_assign_primary(); - -#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE) - diu_ops.get_pixel_format = mpc8610hpcd_get_pixel_format; - diu_ops.set_gamma_table = mpc8610hpcd_set_gamma_table; - diu_ops.set_monitor_port = mpc8610hpcd_set_monitor_port; - diu_ops.set_pixel_clock = mpc8610hpcd_set_pixel_clock; - diu_ops.valid_monitor_port = mpc8610hpcd_valid_monitor_port; -#endif - - pixis_node = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis"); - if (pixis_node) { - of_address_to_resource(pixis_node, 0, &r); - of_node_put(pixis_node); - pixis = ioremap(r.start, 32); - if (!pixis) { - printk(KERN_ERR "Err: can't map FPGA cfg register!\n"); - return; - } - pixis_bdcfg0 = pixis + 8; - pixis_arch = pixis + 1; - } else - printk(KERN_ERR "Err: " - "can't find device node 'fsl,fpga-pixis'\n"); - - printk("MPC86xx HPCD board from Freescale Semiconductor\n"); -} - -define_machine(mpc86xx_hpcd) { - .name = "MPC86xx HPCD", - .compatible = "fsl,MPC8610HPCD", - .setup_arch = mpc86xx_hpcd_setup_arch, - .init_IRQ = mpc86xx_init_irq, - .get_irq = mpic_get_irq, - .time_init = mpc86xx_time_init, - .progress = udbg_progress, -#ifdef CONFIG_PCI - .pcibios_fixup_bus = fsl_pcibios_fixup_bus, -#endif -}; -- GitLab From 33777a4e9bb93f66ac2511d99ec66ab50f1a04bc Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 24 Feb 2023 15:49:57 -0500 Subject: [PATCH 3472/5631] powerpc: drop MPC8272_ADS platform support The MPC8272-ADS also supported other 82xx CPU variants, had 64MB RAM, 8MB flash, and like the 85xx ADS platforms, was on a fairly large PCB in order to have space for breakout connectors for all the features. These 82xx platforms are two decades old, and originally made for a small group of industry related people in order to assist in new OEM board designs. Given that, it makes sense to remove support today. Signed-off-by: Paul Gortmaker Signed-off-by: Michael Ellerman Link: https://msgid.link/20230224204959.17425-2-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 1 - arch/powerpc/boot/dts/mpc8272ads.dts | 263 --------------------- arch/powerpc/configs/mpc8272_ads_defconfig | 79 ------- arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/platforms/82xx/Kconfig | 11 - arch/powerpc/platforms/82xx/Makefile | 1 - arch/powerpc/platforms/82xx/mpc8272_ads.c | 204 ---------------- 7 files changed, 560 deletions(-) delete mode 100644 arch/powerpc/boot/dts/mpc8272ads.dts delete mode 100644 arch/powerpc/configs/mpc8272_ads_defconfig delete mode 100644 arch/powerpc/platforms/82xx/mpc8272_ads.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 73496c5997d7..34d0f61f64c8 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -329,7 +329,6 @@ image-$(CONFIG_PPC_LITE5200) += cuImage.lite5200b image-$(CONFIG_PPC_MEDIA5200) += cuImage.media5200 # Board ports in arch/powerpc/platform/82xx/Kconfig -image-$(CONFIG_MPC8272_ADS) += cuImage.mpc8272ads image-$(CONFIG_PQ2FADS) += cuImage.pq2fads image-$(CONFIG_EP8248E) += dtbImage.ep8248e diff --git a/arch/powerpc/boot/dts/mpc8272ads.dts b/arch/powerpc/boot/dts/mpc8272ads.dts deleted file mode 100644 index 13ec786f6adf..000000000000 --- a/arch/powerpc/boot/dts/mpc8272ads.dts +++ /dev/null @@ -1,263 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8272 ADS Device Tree Source - * - * Copyright 2005,2008 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "MPC8272ADS"; - compatible = "fsl,mpc8272ads"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = ð0; - ethernet1 = ð1; - serial0 = &scc1; - serial1 = &scc4; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - PowerPC,8272@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <16384>; - i-cache-size = <16384>; - timebase-frequency = <0>; - bus-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x0 0x0>; - }; - - localbus@f0010100 { - compatible = "fsl,mpc8272-localbus", - "fsl,pq2-localbus"; - #address-cells = <2>; - #size-cells = <1>; - reg = <0xf0010100 0x40>; - - ranges = <0x0 0x0 0xff800000 0x00800000 - 0x1 0x0 0xf4500000 0x8000 - 0x3 0x0 0xf8200000 0x8000>; - - flash@0,0 { - compatible = "jedec-flash"; - reg = <0x0 0x0 0x00800000>; - bank-width = <4>; - device-width = <1>; - }; - - board-control@1,0 { - reg = <0x1 0x0 0x20>; - compatible = "fsl,mpc8272ads-bcsr"; - }; - - PCI_PIC: interrupt-controller@3,0 { - compatible = "fsl,mpc8272ads-pci-pic", - "fsl,pq2ads-pci-pic"; - #interrupt-cells = <1>; - interrupt-controller; - reg = <0x3 0x0 0x8>; - interrupt-parent = <&PIC>; - interrupts = <20 8>; - }; - }; - - - pci@f0010800 { - device_type = "pci"; - reg = <0xf0010800 0x10c 0xf00101ac 0x8 0xf00101c4 0x8>; - compatible = "fsl,mpc8272-pci", "fsl,pq2-pci"; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - clock-frequency = <66666666>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &PCI_PIC 0 - 0xb000 0x0 0x0 0x2 &PCI_PIC 1 - 0xb000 0x0 0x0 0x3 &PCI_PIC 2 - 0xb000 0x0 0x0 0x4 &PCI_PIC 3 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &PCI_PIC 4 - 0xb800 0x0 0x0 0x2 &PCI_PIC 5 - 0xb800 0x0 0x0 0x3 &PCI_PIC 6 - 0xb800 0x0 0x0 0x4 &PCI_PIC 7 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &PCI_PIC 8 - 0xc000 0x0 0x0 0x2 &PCI_PIC 9 - 0xc000 0x0 0x0 0x3 &PCI_PIC 10 - 0xc000 0x0 0x0 0x4 &PCI_PIC 11>; - - interrupt-parent = <&PIC>; - interrupts = <18 8>; - ranges = <0x42000000 0x0 0x80000000 0x80000000 0x0 0x20000000 - 0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000 - 0x1000000 0x0 0x0 0xf6000000 0x0 0x2000000>; - }; - - soc@f0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "fsl,mpc8272", "fsl,pq2-soc"; - ranges = <0x0 0xf0000000 0x53000>; - - // Temporary -- will go away once kernel uses ranges for get_immrbase(). - reg = <0xf0000000 0x53000>; - - cpm@119c0 { - #address-cells = <1>; - #size-cells = <1>; - compatible = "fsl,mpc8272-cpm", "fsl,cpm2"; - reg = <0x119c0 0x30>; - ranges; - - muram@0 { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x10000>; - - data@0 { - compatible = "fsl,cpm-muram-data"; - reg = <0x0 0x2000 0x9800 0x800>; - }; - }; - - brg@119f0 { - compatible = "fsl,mpc8272-brg", - "fsl,cpm2-brg", - "fsl,cpm-brg"; - reg = <0x119f0 0x10 0x115f0 0x10>; - }; - - scc1: serial@11a00 { - device_type = "serial"; - compatible = "fsl,mpc8272-scc-uart", - "fsl,cpm2-scc-uart"; - reg = <0x11a00 0x20 0x8000 0x100>; - interrupts = <40 8>; - interrupt-parent = <&PIC>; - fsl,cpm-brg = <1>; - fsl,cpm-command = <0x800000>; - }; - - scc4: serial@11a60 { - device_type = "serial"; - compatible = "fsl,mpc8272-scc-uart", - "fsl,cpm2-scc-uart"; - reg = <0x11a60 0x20 0x8300 0x100>; - interrupts = <43 8>; - interrupt-parent = <&PIC>; - fsl,cpm-brg = <4>; - fsl,cpm-command = <0xce00000>; - }; - - usb@11b60 { - compatible = "fsl,mpc8272-cpm-usb"; - reg = <0x11b60 0x40 0x8b00 0x100>; - interrupts = <11 8>; - interrupt-parent = <&PIC>; - mode = "peripheral"; - }; - - mdio@10d40 { - compatible = "fsl,mpc8272ads-mdio-bitbang", - "fsl,mpc8272-mdio-bitbang", - "fsl,cpm2-mdio-bitbang"; - reg = <0x10d40 0x14>; - #address-cells = <1>; - #size-cells = <0>; - fsl,mdio-pin = <18>; - fsl,mdc-pin = <19>; - - PHY0: ethernet-phy@0 { - interrupt-parent = <&PIC>; - interrupts = <23 8>; - reg = <0x0>; - }; - - PHY1: ethernet-phy@1 { - interrupt-parent = <&PIC>; - interrupts = <23 8>; - reg = <0x3>; - }; - }; - - eth0: ethernet@11300 { - device_type = "network"; - compatible = "fsl,mpc8272-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x11300 0x20 0x8400 0x100 0x11390 0x1>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <32 8>; - interrupt-parent = <&PIC>; - phy-handle = <&PHY0>; - linux,network-index = <0>; - fsl,cpm-command = <0x12000300>; - }; - - eth1: ethernet@11320 { - device_type = "network"; - compatible = "fsl,mpc8272-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x11320 0x20 0x8500 0x100 0x113b0 0x1>; - local-mac-address = [ 00 00 00 00 00 00 ]; - interrupts = <33 8>; - interrupt-parent = <&PIC>; - phy-handle = <&PHY1>; - linux,network-index = <1>; - fsl,cpm-command = <0x16200300>; - }; - - i2c@11860 { - compatible = "fsl,mpc8272-i2c", - "fsl,cpm2-i2c"; - reg = <0x11860 0x20 0x8afc 0x2>; - interrupts = <1 8>; - interrupt-parent = <&PIC>; - fsl,cpm-command = <0x29600000>; - #address-cells = <1>; - #size-cells = <0>; - }; - }; - - PIC: interrupt-controller@10c00 { - #interrupt-cells = <2>; - interrupt-controller; - reg = <0x10c00 0x80>; - compatible = "fsl,mpc8272-pic", "fsl,cpm2-pic"; - }; - - crypto@30000 { - compatible = "fsl,sec1.0"; - reg = <0x40000 0x13000>; - interrupts = <47 0x8>; - interrupt-parent = <&PIC>; - fsl,num-channels = <4>; - fsl,channel-fifo-len = <24>; - fsl,exec-units-mask = <0x7e>; - fsl,descriptor-types-mask = <0x1010415>; - }; - }; - - chosen { - stdout-path = "/soc/cpm/serial@11a00"; - }; -}; diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig deleted file mode 100644 index 4145ef5689ca..000000000000 --- a/arch/powerpc/configs/mpc8272_ads_defconfig +++ /dev/null @@ -1,79 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_EXPERT=y -CONFIG_KALLSYMS_ALL=y -CONFIG_PARTITION_ADVANCED=y -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_82xx=y -CONFIG_MPC8272_ADS=y -CONFIG_BINFMT_MISC=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -CONFIG_NETFILTER=y -# CONFIG_FW_LOADER is not set -CONFIG_MTD=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_2 is not set -# CONFIG_MTD_CFI_I1 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_CFI_I4=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP_OF=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_NETDEVICES=y -CONFIG_TUN=y -CONFIG_FS_ENET=y -# CONFIG_FS_ENET_HAS_SCC is not set -CONFIG_FS_ENET_MDIO_FCC=y -CONFIG_DAVICOM_PHY=y -CONFIG_PPP=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_ASYNC=y -CONFIG_PPP_SYNC_TTY=y -CONFIG_INPUT_EVDEV=y -# CONFIG_VT is not set -CONFIG_SERIAL_CPM=y -CONFIG_SERIAL_CPM_CONSOLE=y -# CONFIG_HWMON is not set -# CONFIG_USB_SUPPORT is not set -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3_ACL=y -CONFIG_ROOT_NFS=y -CONFIG_NLS=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_BDI_SWITCH=y -CONFIG_CRYPTO_CBC=y -CONFIG_CRYPTO_ECB=y -CONFIG_CRYPTO_PCBC=y -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index fcdb3a25e895..97227c39c567 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -38,7 +38,6 @@ CONFIG_PPC_MPC52xx=y CONFIG_PPC_EFIKA=y CONFIG_PPC_MPC5200_BUGFIX=y CONFIG_PPC_82xx=y -CONFIG_MPC8272_ADS=y CONFIG_PQ2FADS=y CONFIG_EP8248E=y CONFIG_MGCOGE=y diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 1af81de1c4e6..6de033c82960 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -5,17 +5,6 @@ menuconfig PPC_82xx if PPC_82xx -config MPC8272_ADS - bool "Freescale MPC8272 ADS" - select DEFAULT_UIMAGE - select PQ2ADS - select 8272 - select 8260 - select FSL_SOC - select PQ2_ADS_PCI_PIC if PCI - help - This option enables support for the MPC8272 ADS board - config PQ2FADS bool "Freescale PQ2FADS" select DEFAULT_UIMAGE diff --git a/arch/powerpc/platforms/82xx/Makefile b/arch/powerpc/platforms/82xx/Makefile index 8d713c601bf2..5426a1479006 100644 --- a/arch/powerpc/platforms/82xx/Makefile +++ b/arch/powerpc/platforms/82xx/Makefile @@ -2,7 +2,6 @@ # # Makefile for the PowerPC 82xx linux kernel. # -obj-$(CONFIG_MPC8272_ADS) += mpc8272_ads.o obj-$(CONFIG_CPM2) += pq2.o obj-$(CONFIG_PQ2_ADS_PCI_PIC) += pq2ads-pci-pic.o obj-$(CONFIG_PQ2FADS) += pq2fads.o diff --git a/arch/powerpc/platforms/82xx/mpc8272_ads.c b/arch/powerpc/platforms/82xx/mpc8272_ads.c deleted file mode 100644 index f9b2b1617eeb..000000000000 --- a/arch/powerpc/platforms/82xx/mpc8272_ads.c +++ /dev/null @@ -1,204 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * MPC8272 ADS board support - * - * Copyright 2007 Freescale Semiconductor, Inc. - * Author: Scott Wood - * - * Based on code by Vitaly Bordug - * Copyright (c) 2006 MontaVista Software, Inc. - */ - -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include - -#include -#include - -#include "pq2.h" - -static void __init mpc8272_ads_pic_init(void) -{ - struct device_node *np = of_find_compatible_node(NULL, NULL, - "fsl,cpm2-pic"); - if (!np) { - printk(KERN_ERR "PIC init: can not find fsl,cpm2-pic node\n"); - return; - } - - cpm2_pic_init(np); - of_node_put(np); - - /* Initialize stuff for the 82xx CPLD IC and install demux */ - pq2ads_pci_init_irq(); -} - -struct cpm_pin { - int port, pin, flags; -}; - -static struct cpm_pin mpc8272_ads_pins[] = { - /* SCC1 */ - {3, 30, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {3, 31, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* SCC4 */ - {3, 21, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 22, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* FCC1 */ - {0, 14, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {0, 15, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {0, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {0, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {0, 18, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {0, 19, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {0, 20, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {0, 21, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {0, 26, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, - {0, 27, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, - {0, 28, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {0, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {0, 30, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, - {0, 31, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, - {2, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 22, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* FCC2 */ - {1, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 20, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 22, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 25, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 26, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 27, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {1, 30, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 31, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {2, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* I2C */ - {3, 14, CPM_PIN_INPUT | CPM_PIN_SECONDARY | CPM_PIN_OPENDRAIN}, - {3, 15, CPM_PIN_INPUT | CPM_PIN_SECONDARY | CPM_PIN_OPENDRAIN}, - - /* USB */ - {2, 10, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 11, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 20, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {2, 24, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {3, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 25, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, -}; - -static void __init init_ioports(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mpc8272_ads_pins); i++) { - struct cpm_pin *pin = &mpc8272_ads_pins[i]; - cpm2_set_pin(pin->port, pin->pin, pin->flags); - } - - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_SCC3, CPM_CLK8, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC3, CPM_CLK8, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_SCC4, CPM_BRG4, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC4, CPM_BRG4, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC1, CPM_CLK11, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC1, CPM_CLK10, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK15, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK16, CPM_CLK_TX); -} - -static void __init mpc8272_ads_setup_arch(void) -{ - struct device_node *np; - __be32 __iomem *bcsr; - - if (ppc_md.progress) - ppc_md.progress("mpc8272_ads_setup_arch()", 0); - - cpm2_reset(); - - np = of_find_compatible_node(NULL, NULL, "fsl,mpc8272ads-bcsr"); - if (!np) { - printk(KERN_ERR "No bcsr in device tree\n"); - return; - } - - bcsr = of_iomap(np, 0); - of_node_put(np); - if (!bcsr) { - printk(KERN_ERR "Cannot map BCSR registers\n"); - return; - } - -#define BCSR1_FETHIEN 0x08000000 -#define BCSR1_FETH_RST 0x04000000 -#define BCSR1_RS232_EN1 0x02000000 -#define BCSR1_RS232_EN2 0x01000000 -#define BCSR3_USB_nEN 0x80000000 -#define BCSR3_FETHIEN2 0x10000000 -#define BCSR3_FETH2_RST 0x08000000 - - clrbits32(&bcsr[1], BCSR1_RS232_EN1 | BCSR1_RS232_EN2 | BCSR1_FETHIEN); - setbits32(&bcsr[1], BCSR1_FETH_RST); - - clrbits32(&bcsr[3], BCSR3_FETHIEN2); - setbits32(&bcsr[3], BCSR3_FETH2_RST); - - clrbits32(&bcsr[3], BCSR3_USB_nEN); - - iounmap(bcsr); - - init_ioports(); - - if (ppc_md.progress) - ppc_md.progress("mpc8272_ads_setup_arch(), finish", 0); -} - -static const struct of_device_id of_bus_ids[] __initconst = { - { .name = "soc", }, - { .name = "cpm", }, - { .name = "localbus", }, - {}, -}; - -static int __init declare_of_platform_devices(void) -{ - /* Publish the QE devices */ - of_platform_bus_probe(NULL, of_bus_ids, NULL); - return 0; -} -machine_device_initcall(mpc8272_ads, declare_of_platform_devices); - -define_machine(mpc8272_ads) -{ - .name = "Freescale MPC8272 ADS", - .compatible = "fsl,mpc8272ads", - .setup_arch = mpc8272_ads_setup_arch, - .discover_phbs = pq2_init_pci, - .init_IRQ = mpc8272_ads_pic_init, - .get_irq = cpm2_get_irq, - .restart = pq2_restart, - .progress = udbg_progress, -}; -- GitLab From 859b21a008ebcc7fd876f50738f63750d46b5296 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 24 Feb 2023 15:49:58 -0500 Subject: [PATCH 3473/5631] powerpc: drop PowerQUICC II Family ADS platform support Based on documentation revision dates, this MPC82xx pq2fads system predates the MPC8272-ADS variant by about a year and only has 1/2 the amount of RAM (32MB) -- largely making it useless with a modern v6.x kernel from today. Similar to the MPC8272-ADS the pq2fads also supported other 82xx CPU variants, had 8MB flash, and like the 8272 ADS platform, was on a fairly large PCB in order to have space for breakout connectors for all features. These 82xx platforms are two decades old, and originally made for a small group of industry related people in order to assist in new OEM board designs. Given that, it makes sense to remove support today. Signed-off-by: Paul Gortmaker Signed-off-by: Michael Ellerman Link: https://msgid.link/20230224204959.17425-3-paul.gortmaker@windriver.com --- arch/powerpc/boot/Makefile | 1 - arch/powerpc/boot/dts/pq2fads.dts | 243 ------------------------- arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/powerpc/configs/pq2fads_defconfig | 80 -------- arch/powerpc/platforms/82xx/Kconfig | 10 - arch/powerpc/platforms/82xx/Makefile | 1 - arch/powerpc/platforms/82xx/pq2fads.c | 182 ------------------ 7 files changed, 518 deletions(-) delete mode 100644 arch/powerpc/boot/dts/pq2fads.dts delete mode 100644 arch/powerpc/configs/pq2fads_defconfig delete mode 100644 arch/powerpc/platforms/82xx/pq2fads.c diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 34d0f61f64c8..85cde5bf04b7 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -329,7 +329,6 @@ image-$(CONFIG_PPC_LITE5200) += cuImage.lite5200b image-$(CONFIG_PPC_MEDIA5200) += cuImage.media5200 # Board ports in arch/powerpc/platform/82xx/Kconfig -image-$(CONFIG_PQ2FADS) += cuImage.pq2fads image-$(CONFIG_EP8248E) += dtbImage.ep8248e # Board ports in arch/powerpc/platform/83xx/Kconfig diff --git a/arch/powerpc/boot/dts/pq2fads.dts b/arch/powerpc/boot/dts/pq2fads.dts deleted file mode 100644 index b6666215ed63..000000000000 --- a/arch/powerpc/boot/dts/pq2fads.dts +++ /dev/null @@ -1,243 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Device Tree for the PQ2FADS-ZU board with an MPC8280 chip. - * - * Copyright 2007,2008 Freescale Semiconductor Inc. - */ - -/dts-v1/; - -/ { - model = "pq2fads"; - compatible = "fsl,pq2fads"; - #address-cells = <1>; - #size-cells = <1>; - - aliases { - ethernet0 = &enet0; - ethernet1 = &enet1; - serial0 = &serial0; - serial1 = &serial1; - pci0 = &pci0; - }; - - cpus { - #address-cells = <1>; - #size-cells = <0>; - - cpu@0 { - device_type = "cpu"; - reg = <0x0>; - d-cache-line-size = <32>; - i-cache-line-size = <32>; - d-cache-size = <16384>; - i-cache-size = <16384>; - timebase-frequency = <0>; - clock-frequency = <0>; - }; - }; - - memory { - device_type = "memory"; - reg = <0x0 0x0>; - }; - - localbus@f0010100 { - compatible = "fsl,mpc8280-localbus", - "fsl,pq2-localbus"; - #address-cells = <2>; - #size-cells = <1>; - reg = <0xf0010100 0x60>; - - ranges = <0x0 0x0 0xff800000 0x800000 - 0x1 0x0 0xf4500000 0x8000 - 0x8 0x0 0xf8200000 0x8000>; - - flash@0,0 { - compatible = "jedec-flash"; - reg = <0x0 0x0 0x800000>; - bank-width = <4>; - device-width = <1>; - }; - - bcsr@1,0 { - reg = <0x1 0x0 0x20>; - compatible = "fsl,pq2fads-bcsr"; - }; - - PCI_PIC: pic@8,0 { - #interrupt-cells = <1>; - interrupt-controller; - reg = <0x8 0x0 0x8>; - compatible = "fsl,pq2ads-pci-pic"; - interrupt-parent = <&PIC>; - interrupts = <24 8>; - }; - }; - - pci0: pci@f0010800 { - device_type = "pci"; - reg = <0xf0010800 0x10c 0xf00101ac 0x8 0xf00101c4 0x8>; - compatible = "fsl,mpc8280-pci", "fsl,pq2-pci"; - #interrupt-cells = <1>; - #size-cells = <2>; - #address-cells = <3>; - clock-frequency = <66000000>; - interrupt-map-mask = <0xf800 0x0 0x0 0x7>; - interrupt-map = < - /* IDSEL 0x16 */ - 0xb000 0x0 0x0 0x1 &PCI_PIC 0 - 0xb000 0x0 0x0 0x2 &PCI_PIC 1 - 0xb000 0x0 0x0 0x3 &PCI_PIC 2 - 0xb000 0x0 0x0 0x4 &PCI_PIC 3 - - /* IDSEL 0x17 */ - 0xb800 0x0 0x0 0x1 &PCI_PIC 4 - 0xb800 0x0 0x0 0x2 &PCI_PIC 5 - 0xb800 0x0 0x0 0x3 &PCI_PIC 6 - 0xb800 0x0 0x0 0x4 &PCI_PIC 7 - - /* IDSEL 0x18 */ - 0xc000 0x0 0x0 0x1 &PCI_PIC 8 - 0xc000 0x0 0x0 0x2 &PCI_PIC 9 - 0xc000 0x0 0x0 0x3 &PCI_PIC 10 - 0xc000 0x0 0x0 0x4 &PCI_PIC 11>; - - interrupt-parent = <&PIC>; - interrupts = <18 8>; - ranges = <0x42000000 0x0 0x80000000 0x80000000 0x0 0x20000000 - 0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000 - 0x1000000 0x0 0x0 0xf6000000 0x0 0x2000000>; - }; - - soc@f0000000 { - #address-cells = <1>; - #size-cells = <1>; - device_type = "soc"; - compatible = "fsl,mpc8280", "fsl,pq2-soc"; - ranges = <0x0 0xf0000000 0x53000>; - - // Temporary -- will go away once kernel uses ranges for get_immrbase(). - reg = <0xf0000000 0x53000>; - - cpm@119c0 { - #address-cells = <1>; - #size-cells = <1>; - #interrupt-cells = <2>; - compatible = "fsl,mpc8280-cpm", "fsl,cpm2"; - reg = <0x119c0 0x30>; - ranges; - - muram@0 { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x0 0x0 0x10000>; - - data@0 { - compatible = "fsl,cpm-muram-data"; - reg = <0x0 0x2000 0x9800 0x800>; - }; - }; - - brg@119f0 { - compatible = "fsl,mpc8280-brg", - "fsl,cpm2-brg", - "fsl,cpm-brg"; - reg = <0x119f0 0x10 0x115f0 0x10>; - }; - - serial0: serial@11a00 { - device_type = "serial"; - compatible = "fsl,mpc8280-scc-uart", - "fsl,cpm2-scc-uart"; - reg = <0x11a00 0x20 0x8000 0x100>; - interrupts = <40 8>; - interrupt-parent = <&PIC>; - fsl,cpm-brg = <1>; - fsl,cpm-command = <0x800000>; - }; - - serial1: serial@11a20 { - device_type = "serial"; - compatible = "fsl,mpc8280-scc-uart", - "fsl,cpm2-scc-uart"; - reg = <0x11a20 0x20 0x8100 0x100>; - interrupts = <41 8>; - interrupt-parent = <&PIC>; - fsl,cpm-brg = <2>; - fsl,cpm-command = <0x4a00000>; - }; - - enet0: ethernet@11320 { - device_type = "network"; - compatible = "fsl,mpc8280-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x11320 0x20 0x8500 0x100 0x113b0 0x1>; - interrupts = <33 8>; - interrupt-parent = <&PIC>; - phy-handle = <&PHY0>; - linux,network-index = <0>; - fsl,cpm-command = <0x16200300>; - }; - - enet1: ethernet@11340 { - device_type = "network"; - compatible = "fsl,mpc8280-fcc-enet", - "fsl,cpm2-fcc-enet"; - reg = <0x11340 0x20 0x8600 0x100 0x113d0 0x1>; - interrupts = <34 8>; - interrupt-parent = <&PIC>; - phy-handle = <&PHY1>; - linux,network-index = <1>; - fsl,cpm-command = <0x1a400300>; - local-mac-address = [00 e0 0c 00 79 01]; - }; - - mdio@10d40 { - compatible = "fsl,pq2fads-mdio-bitbang", - "fsl,mpc8280-mdio-bitbang", - "fsl,cpm2-mdio-bitbang"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x10d40 0x14>; - fsl,mdio-pin = <9>; - fsl,mdc-pin = <10>; - - PHY0: ethernet-phy@0 { - interrupt-parent = <&PIC>; - interrupts = <25 2>; - reg = <0x0>; - }; - - PHY1: ethernet-phy@1 { - interrupt-parent = <&PIC>; - interrupts = <25 2>; - reg = <0x3>; - }; - }; - - usb@11b60 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "fsl,mpc8280-usb", - "fsl,cpm2-usb"; - reg = <0x11b60 0x18 0x8b00 0x100>; - interrupt-parent = <&PIC>; - interrupts = <11 8>; - fsl,cpm-command = <0x2e600000>; - }; - }; - - PIC: interrupt-controller@10c00 { - #interrupt-cells = <2>; - interrupt-controller; - reg = <0x10c00 0x80>; - compatible = "fsl,mpc8280-pic", "fsl,cpm2-pic"; - }; - - }; - - chosen { - stdout-path = "/soc/cpm/serial@11a00"; - }; -}; diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 97227c39c567..bf5a07b274de 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -38,7 +38,6 @@ CONFIG_PPC_MPC52xx=y CONFIG_PPC_EFIKA=y CONFIG_PPC_MPC5200_BUGFIX=y CONFIG_PPC_82xx=y -CONFIG_PQ2FADS=y CONFIG_EP8248E=y CONFIG_MGCOGE=y CONFIG_PPC_83xx=y diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig deleted file mode 100644 index 9d63e2e65211..000000000000 --- a/arch/powerpc/configs/pq2fads_defconfig +++ /dev/null @@ -1,80 +0,0 @@ -CONFIG_SYSVIPC=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=14 -CONFIG_BLK_DEV_INITRD=y -CONFIG_EXPERT=y -CONFIG_KALLSYMS_ALL=y -CONFIG_PARTITION_ADVANCED=y -# CONFIG_PPC_CHRP is not set -# CONFIG_PPC_PMAC is not set -CONFIG_PPC_82xx=y -CONFIG_PQ2FADS=y -CONFIG_BINFMT_MISC=y -CONFIG_PCI=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_SYN_COOKIES=y -CONFIG_NETFILTER=y -# CONFIG_FW_LOADER is not set -CONFIG_MTD=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_JEDECPROBE=y -CONFIG_MTD_CFI_ADV_OPTIONS=y -CONFIG_MTD_CFI_GEOMETRY=y -# CONFIG_MTD_MAP_BANK_WIDTH_1 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_2 is not set -# CONFIG_MTD_CFI_I1 is not set -# CONFIG_MTD_CFI_I2 is not set -CONFIG_MTD_CFI_I4=y -CONFIG_MTD_CFI_INTELEXT=y -CONFIG_MTD_PHYSMAP_OF=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_NETDEVICES=y -CONFIG_TUN=y -CONFIG_FS_ENET=y -# CONFIG_FS_ENET_HAS_SCC is not set -CONFIG_FS_ENET_MDIO_FCC=y -CONFIG_DAVICOM_PHY=y -CONFIG_PPP=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_ASYNC=y -CONFIG_PPP_SYNC_TTY=y -CONFIG_INPUT_EVDEV=y -# CONFIG_VT is not set -CONFIG_SERIAL_CPM=y -CONFIG_SERIAL_CPM_CONSOLE=y -# CONFIG_HWMON is not set -CONFIG_USB_GADGET=y -CONFIG_USB_ETH=y -CONFIG_EXT2_FS=y -CONFIG_EXT4_FS=y -CONFIG_AUTOFS4_FS=y -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_CRAMFS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3_ACL=y -CONFIG_ROOT_NFS=y -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_UTF8=y -CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DETECT_HUNG_TASK=y -# CONFIG_SCHED_DEBUG is not set -CONFIG_BDI_SWITCH=y -CONFIG_CRYPTO_CBC=y -CONFIG_CRYPTO_ECB=y -CONFIG_CRYPTO_PCBC=y -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_DES=y diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 6de033c82960..62a057c6a356 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -5,16 +5,6 @@ menuconfig PPC_82xx if PPC_82xx -config PQ2FADS - bool "Freescale PQ2FADS" - select DEFAULT_UIMAGE - select PQ2ADS - select 8260 - select FSL_SOC - select PQ2_ADS_PCI_PIC if PCI - help - This option enables support for the PQ2FADS board - config EP8248E bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)" select 8272 diff --git a/arch/powerpc/platforms/82xx/Makefile b/arch/powerpc/platforms/82xx/Makefile index 5426a1479006..a4257f057401 100644 --- a/arch/powerpc/platforms/82xx/Makefile +++ b/arch/powerpc/platforms/82xx/Makefile @@ -4,6 +4,5 @@ # obj-$(CONFIG_CPM2) += pq2.o obj-$(CONFIG_PQ2_ADS_PCI_PIC) += pq2ads-pci-pic.o -obj-$(CONFIG_PQ2FADS) += pq2fads.o obj-$(CONFIG_EP8248E) += ep8248e.o obj-$(CONFIG_MGCOGE) += km82xx.o diff --git a/arch/powerpc/platforms/82xx/pq2fads.c b/arch/powerpc/platforms/82xx/pq2fads.c deleted file mode 100644 index 4080cb4253d3..000000000000 --- a/arch/powerpc/platforms/82xx/pq2fads.c +++ /dev/null @@ -1,182 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * PQ2FADS board support - * - * Copyright 2007 Freescale Semiconductor, Inc. - * Author: Scott Wood - * - * Loosely based on mp82xx ADS support by Vitaly Bordug - * Copyright (c) 2006 MontaVista Software, Inc. - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -#include -#include - -#include "pq2ads.h" -#include "pq2.h" - -static void __init pq2fads_pic_init(void) -{ - struct device_node *np = of_find_compatible_node(NULL, NULL, "fsl,cpm2-pic"); - if (!np) { - printk(KERN_ERR "PIC init: can not find fsl,cpm2-pic node\n"); - return; - } - - cpm2_pic_init(np); - of_node_put(np); - - /* Initialize stuff for the 82xx CPLD IC and install demux */ - pq2ads_pci_init_irq(); -} - -struct cpm_pin { - int port, pin, flags; -}; - -static struct cpm_pin pq2fads_pins[] = { - /* SCC1 */ - {3, 30, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {3, 31, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* SCC2 */ - {3, 27, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {3, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* FCC2 */ - {1, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 20, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 22, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 25, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 26, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 27, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY}, - {1, 30, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 31, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {2, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - - /* FCC3 */ - {1, 4, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 6, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 7, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 9, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 10, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 11, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 12, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 13, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 14, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 15, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, - {1, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {1, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, - {2, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, -}; - -static void __init init_ioports(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(pq2fads_pins); i++) { - struct cpm_pin *pin = &pq2fads_pins[i]; - cpm2_set_pin(pin->port, pin->pin, pin->flags); - } - - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK13, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK14, CPM_CLK_TX); - cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK15, CPM_CLK_RX); - cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK16, CPM_CLK_TX); -} - -static void __init pq2fads_setup_arch(void) -{ - struct device_node *np; - __be32 __iomem *bcsr; - - if (ppc_md.progress) - ppc_md.progress("pq2fads_setup_arch()", 0); - - cpm2_reset(); - - np = of_find_compatible_node(NULL, NULL, "fsl,pq2fads-bcsr"); - if (!np) { - printk(KERN_ERR "No fsl,pq2fads-bcsr in device tree\n"); - return; - } - - bcsr = of_iomap(np, 0); - of_node_put(np); - if (!bcsr) { - printk(KERN_ERR "Cannot map BCSR registers\n"); - return; - } - - /* Enable the serial and ethernet ports */ - - clrbits32(&bcsr[1], BCSR1_RS232_EN1 | BCSR1_RS232_EN2 | BCSR1_FETHIEN); - setbits32(&bcsr[1], BCSR1_FETH_RST); - - clrbits32(&bcsr[3], BCSR3_FETHIEN2); - setbits32(&bcsr[3], BCSR3_FETH2_RST); - - iounmap(bcsr); - - init_ioports(); - - /* Enable external IRQs */ - clrbits32(&cpm2_immr->im_siu_conf.siu_82xx.sc_siumcr, 0x0c000000); - - if (ppc_md.progress) - ppc_md.progress("pq2fads_setup_arch(), finish", 0); -} - -static const struct of_device_id of_bus_ids[] __initconst = { - { .name = "soc", }, - { .name = "cpm", }, - { .name = "localbus", }, - {}, -}; - -static int __init declare_of_platform_devices(void) -{ - /* Publish the QE devices */ - of_platform_bus_probe(NULL, of_bus_ids, NULL); - return 0; -} -machine_device_initcall(pq2fads, declare_of_platform_devices); - -define_machine(pq2fads) -{ - .name = "Freescale PQ2FADS", - .compatible = "fsl,pq2fads", - .setup_arch = pq2fads_setup_arch, - .discover_phbs = pq2_init_pci, - .init_IRQ = pq2fads_pic_init, - .get_irq = cpm2_get_irq, - .restart = pq2_restart, - .progress = udbg_progress, -}; -- GitLab From ad46ad2d853daf082f742c9654da84e3d2a46765 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Fri, 24 Feb 2023 15:49:59 -0500 Subject: [PATCH 3474/5631] powerpc: drop MPC8272-ADS and PowerQUICC II FADS shared code. With the two platforms depending on this shared code, and no others, we can remove the orphaned code and Kconfigs Signed-off-by: Paul Gortmaker Signed-off-by: Michael Ellerman Link: https://msgid.link/20230224204959.17425-4-paul.gortmaker@windriver.com --- arch/powerpc/include/asm/mpc8260.h | 4 - arch/powerpc/platforms/82xx/Kconfig | 6 - arch/powerpc/platforms/82xx/Makefile | 1 - arch/powerpc/platforms/82xx/pq2ads-pci-pic.c | 172 ------------------- arch/powerpc/platforms/82xx/pq2ads.h | 40 ----- 5 files changed, 223 deletions(-) delete mode 100644 arch/powerpc/platforms/82xx/pq2ads-pci-pic.c delete mode 100644 arch/powerpc/platforms/82xx/pq2ads.h diff --git a/arch/powerpc/include/asm/mpc8260.h b/arch/powerpc/include/asm/mpc8260.h index fd8c5707425b..155114bbd1a2 100644 --- a/arch/powerpc/include/asm/mpc8260.h +++ b/arch/powerpc/include/asm/mpc8260.h @@ -13,10 +13,6 @@ #ifdef CONFIG_8260 -#if defined(CONFIG_PQ2ADS) || defined (CONFIG_PQ2FADS) -#include -#endif - #ifdef CONFIG_PCI_8260 #include #endif diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 62a057c6a356..4eb372bdab70 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -28,9 +28,6 @@ config MGCOGE endif -config PQ2ADS - bool - config 8260 bool depends on PPC_BOOK3S_32 @@ -46,6 +43,3 @@ config 8272 help The MPC8272 CPM has a different internal dpram setup than other CPM2 devices - -config PQ2_ADS_PCI_PIC - bool diff --git a/arch/powerpc/platforms/82xx/Makefile b/arch/powerpc/platforms/82xx/Makefile index a4257f057401..4fa43a5cd582 100644 --- a/arch/powerpc/platforms/82xx/Makefile +++ b/arch/powerpc/platforms/82xx/Makefile @@ -3,6 +3,5 @@ # Makefile for the PowerPC 82xx linux kernel. # obj-$(CONFIG_CPM2) += pq2.o -obj-$(CONFIG_PQ2_ADS_PCI_PIC) += pq2ads-pci-pic.o obj-$(CONFIG_EP8248E) += ep8248e.o obj-$(CONFIG_MGCOGE) += km82xx.o diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c deleted file mode 100644 index cf3210042a2e..000000000000 --- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c +++ /dev/null @@ -1,172 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * PQ2 ADS-style PCI interrupt controller - * - * Copyright 2007 Freescale Semiconductor, Inc. - * Author: Scott Wood - * - * Loosely based on mpc82xx ADS support by Vitaly Bordug - * Copyright (c) 2006 MontaVista Software, Inc. - */ - -#include -#include -#include -#include -#include -#include - -#include -#include - -#include "pq2.h" - -static DEFINE_RAW_SPINLOCK(pci_pic_lock); - -struct pq2ads_pci_pic { - struct device_node *node; - struct irq_domain *host; - - struct { - u32 stat; - u32 mask; - } __iomem *regs; -}; - -#define NUM_IRQS 32 - -static void pq2ads_pci_mask_irq(struct irq_data *d) -{ - struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d); - int irq = NUM_IRQS - irqd_to_hwirq(d) - 1; - - if (irq != -1) { - unsigned long flags; - raw_spin_lock_irqsave(&pci_pic_lock, flags); - - setbits32(&priv->regs->mask, 1 << irq); - mb(); - - raw_spin_unlock_irqrestore(&pci_pic_lock, flags); - } -} - -static void pq2ads_pci_unmask_irq(struct irq_data *d) -{ - struct pq2ads_pci_pic *priv = irq_data_get_irq_chip_data(d); - int irq = NUM_IRQS - irqd_to_hwirq(d) - 1; - - if (irq != -1) { - unsigned long flags; - - raw_spin_lock_irqsave(&pci_pic_lock, flags); - clrbits32(&priv->regs->mask, 1 << irq); - raw_spin_unlock_irqrestore(&pci_pic_lock, flags); - } -} - -static struct irq_chip pq2ads_pci_ic = { - .name = "PQ2 ADS PCI", - .irq_mask = pq2ads_pci_mask_irq, - .irq_mask_ack = pq2ads_pci_mask_irq, - .irq_ack = pq2ads_pci_mask_irq, - .irq_unmask = pq2ads_pci_unmask_irq, - .irq_enable = pq2ads_pci_unmask_irq, - .irq_disable = pq2ads_pci_mask_irq -}; - -static void pq2ads_pci_irq_demux(struct irq_desc *desc) -{ - struct pq2ads_pci_pic *priv = irq_desc_get_handler_data(desc); - u32 stat, mask, pend; - int bit; - - for (;;) { - stat = in_be32(&priv->regs->stat); - mask = in_be32(&priv->regs->mask); - - pend = stat & ~mask; - - if (!pend) - break; - - for (bit = 0; pend != 0; ++bit, pend <<= 1) { - if (pend & 0x80000000) - generic_handle_domain_irq(priv->host, bit); - } - } -} - -static int pci_pic_host_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw) -{ - irq_set_status_flags(virq, IRQ_LEVEL); - irq_set_chip_data(virq, h->host_data); - irq_set_chip_and_handler(virq, &pq2ads_pci_ic, handle_level_irq); - return 0; -} - -static const struct irq_domain_ops pci_pic_host_ops = { - .map = pci_pic_host_map, -}; - -int __init pq2ads_pci_init_irq(void) -{ - struct pq2ads_pci_pic *priv; - struct irq_domain *host; - struct device_node *np; - int ret = -ENODEV; - int irq; - - np = of_find_compatible_node(NULL, NULL, "fsl,pq2ads-pci-pic"); - if (!np) { - printk(KERN_ERR "No pci pic node in device tree.\n"); - goto out; - } - - irq = irq_of_parse_and_map(np, 0); - if (!irq) { - printk(KERN_ERR "No interrupt in pci pic node.\n"); - goto out_put_node; - } - - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) { - ret = -ENOMEM; - goto out_unmap_irq; - } - - /* PCI interrupt controller registers: status and mask */ - priv->regs = of_iomap(np, 0); - if (!priv->regs) { - printk(KERN_ERR "Cannot map PCI PIC registers.\n"); - goto out_free_kmalloc; - } - - /* mask all PCI interrupts */ - out_be32(&priv->regs->mask, ~0); - mb(); - - host = irq_domain_add_linear(np, NUM_IRQS, &pci_pic_host_ops, priv); - if (!host) { - ret = -ENOMEM; - goto out_unmap_regs; - } - - priv->host = host; - irq_set_handler_data(irq, priv); - irq_set_chained_handler(irq, pq2ads_pci_irq_demux); - ret = 0; - goto out_put_node; - -out_unmap_regs: - iounmap(priv->regs); -out_free_kmalloc: - kfree(priv); -out_unmap_irq: - irq_dispose_mapping(irq); -out_put_node: - of_node_put(np); -out: - return ret; -} diff --git a/arch/powerpc/platforms/82xx/pq2ads.h b/arch/powerpc/platforms/82xx/pq2ads.h deleted file mode 100644 index 9d0bf744945c..000000000000 --- a/arch/powerpc/platforms/82xx/pq2ads.h +++ /dev/null @@ -1,40 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * PQ2/mpc8260 board-specific stuff - * - * A collection of structures, addresses, and values associated with - * the Freescale MPC8260ADS/MPC8266ADS-PCI boards. - * Copied from the RPX-Classic and SBS8260 stuff. - * - * Author: Vitaly Bordug - * - * Originally written by Dan Malek for Motorola MPC8260 family - * - * Copyright (c) 2001 Dan Malek - * Copyright (c) 2006 MontaVista Software, Inc. - */ - -#ifdef __KERNEL__ -#ifndef __MACH_ADS8260_DEFS -#define __MACH_ADS8260_DEFS - -#include - -/* The ADS8260 has 16, 32-bit wide control/status registers, accessed - * only on word boundaries. - * Not all are used (yet), or are interesting to us (yet). - */ - -/* Things of interest in the CSR. - */ -#define BCSR0_LED0 ((uint)0x02000000) /* 0 == on */ -#define BCSR0_LED1 ((uint)0x01000000) /* 0 == on */ -#define BCSR1_FETHIEN ((uint)0x08000000) /* 0 == enable*/ -#define BCSR1_FETH_RST ((uint)0x04000000) /* 0 == reset */ -#define BCSR1_RS232_EN1 ((uint)0x02000000) /* 0 ==enable */ -#define BCSR1_RS232_EN2 ((uint)0x01000000) /* 0 ==enable */ -#define BCSR3_FETHIEN2 ((uint)0x10000000) /* 0 == enable*/ -#define BCSR3_FETH2_RST ((uint)0x80000000) /* 0 == reset */ - -#endif /* __MACH_ADS8260_DEFS */ -#endif /* __KERNEL__ */ -- GitLab From 9ab9de2f3aa99ab6245203236d66a057d73b7e9f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 11 Apr 2023 20:28:38 +1000 Subject: [PATCH 3475/5631] powerpc/corenet: Add PPC_QEMU_E500 to corenet configs Add PPC_QEMU_E500 to corenet_base.config, which is then used to generate corenet64_smp_defconfig and corenet32_smp_defconfig. That then allows both those configs to build kernels that boot in qemu using the ppce500 machine type and respectively -cpu e5500 or -cpu e500mc. The code that is added by PPC_QEMU_E500 just defines another machine with a probe function that recognises qemu, so there should be no change when booting on actual hardware supported by CORENET_GENERIC. The increase in vmlinux size is less than 1KB. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230411102838.512859-1-mpe@ellerman.id.au --- arch/powerpc/configs/corenet_base.config | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/corenet_base.config b/arch/powerpc/configs/corenet_base.config index b568d465e59e..1c40de1e764b 100644 --- a/arch/powerpc/configs/corenet_base.config +++ b/arch/powerpc/configs/corenet_base.config @@ -1 +1,2 @@ CONFIG_CORENET_GENERIC=y +CONFIG_PPC_QEMU_E500=y -- GitLab From e5b6634aa1bcbd43120b2fd6f15780f00e9e7f66 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 6 Apr 2023 22:21:18 +1000 Subject: [PATCH 3476/5631] powerpc/irq: Mark check_return_regs_valid() notrace check_return_regs_valid() is called from the middle of the irq exit handling, which is all notrace, so mark it notrace also. Reported-by: Sachin Sant Link: https://lore.kernel.org/all/4C073F6A-C812-4C4A-BB7A-ECD10B75FB88@linux.ibm.com/ Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406122118.3760344-1-mpe@ellerman.id.au --- arch/powerpc/kernel/interrupt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 0ec1581619db..e34c72285b4e 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -95,7 +95,7 @@ static notrace void booke_load_dbcr0(void) #endif } -static void check_return_regs_valid(struct pt_regs *regs) +static notrace void check_return_regs_valid(struct pt_regs *regs) { #ifdef CONFIG_PPC_BOOK3S_64 unsigned long trap, srr0, srr1; -- GitLab From 7640854d966449e5befeff02c45c799cfc3d4fcf Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 7 Apr 2023 00:45:32 +1000 Subject: [PATCH 3477/5631] powerpc/64: Mark prep_irq_for_idle() __cpuidle Code in the idle path is not allowed to be instrumented because RCU is disabled, see commit 0e985e9d2286 ("cpuidle: Add comments about noinstr/__cpuidle usage"). Mark prep_irq_for_idle() __cpuidle, which is equivalent to noinstr, to enforce that. Suggested-by: Peter Zijlstra Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406144535.3786008-1-mpe@ellerman.id.au --- arch/powerpc/kernel/irq_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index c788c55512ed..2ab0e8d84c1d 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -354,7 +354,7 @@ EXPORT_SYMBOL(arch_local_irq_restore); * disabled and marked as such, so the local_irq_enable() call * in arch_cpu_idle() will properly re-enable everything. */ -bool prep_irq_for_idle(void) +__cpuidle bool prep_irq_for_idle(void) { /* * First we need to hard disable to ensure no interrupt -- GitLab From 6fee130204650515af80c2786176da0fe7e94482 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 7 Apr 2023 00:45:33 +1000 Subject: [PATCH 3478/5631] powerpc/64: Don't call trace_hardirqs_on() in prep_irq_for_idle() Since commit a01353cf1896 ("cpuidle: Fix ct_idle_*() usage"), the cpuidle entry code calls trace_hardirqs_on() (actually trace_hardirqs_on_prepare()) in ct_cpuidle_enter() before calling into the cpuidle driver. Suggested-by: Peter Zijlstra Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406144535.3786008-2-mpe@ellerman.id.au --- arch/powerpc/kernel/irq_64.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/kernel/irq_64.c b/arch/powerpc/kernel/irq_64.c index 2ab0e8d84c1d..938e66829eae 100644 --- a/arch/powerpc/kernel/irq_64.c +++ b/arch/powerpc/kernel/irq_64.c @@ -348,9 +348,8 @@ EXPORT_SYMBOL(arch_local_irq_restore); * already the case when ppc_md.power_save is called). The function * will return whether to enter power save or just return. * - * In the former case, it will have notified lockdep of interrupts - * being re-enabled and generally sanitized the lazy irq state, - * and in the latter case it will leave with interrupts hard + * In the former case, it will have generally sanitized the lazy irq + * state, and in the latter case it will leave with interrupts hard * disabled and marked as such, so the local_irq_enable() call * in arch_cpu_idle() will properly re-enable everything. */ @@ -370,9 +369,6 @@ __cpuidle bool prep_irq_for_idle(void) if (lazy_irq_pending()) return false; - /* Tell lockdep we are about to re-enable */ - trace_hardirqs_on(); - /* * Mark interrupts as soft-enabled and clear the * PACA_IRQ_HARD_DIS from the pending mask since we -- GitLab From 88990745c934b14359e526033c5bc1daaf15267c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 7 Apr 2023 00:45:34 +1000 Subject: [PATCH 3479/5631] cpuidle: pseries: Mark ->enter() functions as __cpuidle Code in the idle path is not allowed to be instrumented because RCU is disabled, see commit 0e985e9d2286 ("cpuidle: Add comments about noinstr/__cpuidle usage"). Mark the cpuidle ->enter() callbacks as __cpuidle and use the raw_local_irq_*() routines to ensure that is the case. Reported-by: Sachin Sant Link: https://lore.kernel.org/all/4C073F6A-C812-4C4A-BB7A-ECD10B75FB88@linux.ibm.com/ Suggested-by: Peter Zijlstra Tested-by: Sachin Sant Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406144535.3786008-3-mpe@ellerman.id.au --- drivers/cpuidle/cpuidle-pseries.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index 1bad4d2b7be3..a7d33f3ee01e 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -33,16 +33,16 @@ static struct cpuidle_state *cpuidle_state_table __read_mostly; static u64 snooze_timeout __read_mostly; static bool snooze_timeout_en __read_mostly; -static int snooze_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) +static __cpuidle +int snooze_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) { u64 snooze_exit_time; set_thread_flag(TIF_POLLING_NRFLAG); pseries_idle_prolog(); - local_irq_enable(); + raw_local_irq_enable(); snooze_exit_time = get_tb() + snooze_timeout; dev->poll_time_limit = false; @@ -65,14 +65,14 @@ static int snooze_loop(struct cpuidle_device *dev, HMT_medium(); clear_thread_flag(TIF_POLLING_NRFLAG); - local_irq_disable(); + raw_local_irq_disable(); pseries_idle_epilog(); return index; } -static void check_and_cede_processor(void) +static __cpuidle void check_and_cede_processor(void) { /* * Ensure our interrupt state is properly tracked, @@ -216,9 +216,9 @@ static int __init parse_cede_parameters(void) #define NR_DEDICATED_STATES 2 /* snooze, CEDE */ static u8 cede_latency_hint[NR_DEDICATED_STATES]; -static int dedicated_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) +static __cpuidle +int dedicated_cede_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) { u8 old_latency_hint; @@ -230,7 +230,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev, HMT_medium(); check_and_cede_processor(); - local_irq_disable(); + raw_local_irq_disable(); get_lppaca()->donate_dedicated_cpu = 0; get_lppaca()->cede_latency_hint = old_latency_hint; @@ -239,9 +239,9 @@ static int dedicated_cede_loop(struct cpuidle_device *dev, return index; } -static int shared_cede_loop(struct cpuidle_device *dev, - struct cpuidle_driver *drv, - int index) +static __cpuidle +int shared_cede_loop(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) { pseries_idle_prolog(); @@ -255,7 +255,7 @@ static int shared_cede_loop(struct cpuidle_device *dev, */ check_and_cede_processor(); - local_irq_disable(); + raw_local_irq_disable(); pseries_idle_epilog(); return index; -- GitLab From 18b5e7170a33a985dc842ab24a690fa6ff0f50e4 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 7 Apr 2023 00:45:35 +1000 Subject: [PATCH 3480/5631] powerpc/pseries: Always inline functions called from cpuidle Code in the idle path is not allowed to be instrumented because RCU is disabled, see commit 0e985e9d2286 ("cpuidle: Add comments about noinstr/__cpuidle usage"). Force inlining of the inline functions called from cpuidle, to ensure they are not emitted out-of-line and then available for tracing. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230406144535.3786008-4-mpe@ellerman.id.au --- arch/powerpc/include/asm/idle.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/include/asm/idle.h b/arch/powerpc/include/asm/idle.h index accd1f50085a..00f360667391 100644 --- a/arch/powerpc/include/asm/idle.h +++ b/arch/powerpc/include/asm/idle.h @@ -9,17 +9,17 @@ DECLARE_PER_CPU(u64, idle_spurr_cycles); DECLARE_PER_CPU(u64, idle_entry_purr_snap); DECLARE_PER_CPU(u64, idle_entry_spurr_snap); -static inline void snapshot_purr_idle_entry(void) +static __always_inline void snapshot_purr_idle_entry(void) { *this_cpu_ptr(&idle_entry_purr_snap) = mfspr(SPRN_PURR); } -static inline void snapshot_spurr_idle_entry(void) +static __always_inline void snapshot_spurr_idle_entry(void) { *this_cpu_ptr(&idle_entry_spurr_snap) = mfspr(SPRN_SPURR); } -static inline void update_idle_purr_accounting(void) +static __always_inline void update_idle_purr_accounting(void) { u64 wait_cycles; u64 in_purr = *this_cpu_ptr(&idle_entry_purr_snap); @@ -29,7 +29,7 @@ static inline void update_idle_purr_accounting(void) get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); } -static inline void update_idle_spurr_accounting(void) +static __always_inline void update_idle_spurr_accounting(void) { u64 *idle_spurr_cycles_ptr = this_cpu_ptr(&idle_spurr_cycles); u64 in_spurr = *this_cpu_ptr(&idle_entry_spurr_snap); @@ -37,7 +37,7 @@ static inline void update_idle_spurr_accounting(void) *idle_spurr_cycles_ptr += mfspr(SPRN_SPURR) - in_spurr; } -static inline void pseries_idle_prolog(void) +static __always_inline void pseries_idle_prolog(void) { ppc64_runlatch_off(); snapshot_purr_idle_entry(); @@ -49,7 +49,7 @@ static inline void pseries_idle_prolog(void) get_lppaca()->idle = 1; } -static inline void pseries_idle_epilog(void) +static __always_inline void pseries_idle_epilog(void) { update_idle_purr_accounting(); update_idle_spurr_accounting(); -- GitLab From 228c7a95534b438859d6cc068691164bd705a9c8 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 29 Mar 2023 18:23:33 +1100 Subject: [PATCH 3481/5631] powerpc/Makefile: Don't prefix archhelp commands with "@" It's not necessary to prefix every command in archhelp with "@" (to suppress echoing the command), because that is done by the top level Makefile when it evaluates archhelp. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230329072334.2023357-1-mpe@ellerman.id.au --- arch/powerpc/Makefile | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 5f47f2ce7cc3..15c5f4c06614 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -332,25 +332,25 @@ ppc64_randconfig: -f $(srctree)/Makefile randconfig define archhelp - @echo '* zImage - Build default images selected by kernel config' - @echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)' - @echo ' uImage - U-Boot native image format' - @echo ' cuImage.

- Backwards compatible U-Boot image for older' - @echo ' versions which do not support device trees' - @echo ' dtbImage.
- zImage with an embedded device tree blob' - @echo ' simpleImage.
- Firmware independent image.' - @echo ' treeImage.
- Support for older IBM 4xx firmware (not U-Boot)' - @echo ' install - Install kernel using' - @echo ' (your) ~/bin/$(INSTALLKERNEL) or' - @echo ' (distribution) /sbin/$(INSTALLKERNEL) or' - @echo ' install to $$(INSTALL_PATH) and run lilo' - @echo ' *_defconfig - Select default config from arch/$(ARCH)/configs' - @echo '' - @echo ' Targets with
embed a device tree blob inside the image' - @echo ' These targets support board with firmware that does not' - @echo ' support passing a device tree directly. Replace
with the' - @echo ' name of a dts file from the arch/$(ARCH)/boot/dts/ directory' - @echo ' (minus the .dts extension).' + echo '* zImage - Build default images selected by kernel config' + echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)' + echo ' uImage - U-Boot native image format' + echo ' cuImage.
- Backwards compatible U-Boot image for older' + echo ' versions which do not support device trees' + echo ' dtbImage.
- zImage with an embedded device tree blob' + echo ' simpleImage.
- Firmware independent image.' + echo ' treeImage.
- Support for older IBM 4xx firmware (not U-Boot)' + echo ' install - Install kernel using' + echo ' (your) ~/bin/$(INSTALLKERNEL) or' + echo ' (distribution) /sbin/$(INSTALLKERNEL) or' + echo ' install to $$(INSTALL_PATH) and run lilo' + echo ' *_defconfig - Select default config from arch/$(ARCH)/configs' + echo '' + echo ' Targets with
embed a device tree blob inside the image' + echo ' These targets support board with firmware that does not' + echo ' support passing a device tree directly. Replace
with the' + echo ' name of a dts file from the arch/$(ARCH)/boot/dts/ directory' + echo ' (minus the .dts extension).' endef PHONY += install -- GitLab From 5629d31955297ca47b9283c64fff70f2f34aa528 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 5 Apr 2023 19:18:53 +0100 Subject: [PATCH 3482/5631] usb: gadget: tegra-xudc: Fix crash in vbus_draw Commit ac82b56bda5f ("usb: gadget: tegra-xudc: Add vbus_draw support") populated the vbus_draw callback for the Tegra XUDC driver. The function tegra_xudc_gadget_vbus_draw(), that was added by this commit, assumes that the pointer 'curr_usbphy' has been initialised, which is not always the case because this is only initialised when the USB role is updated. Fix this crash, by checking that the 'curr_usbphy' is valid before dereferencing. Fixes: ac82b56bda5f ("usb: gadget: tegra-xudc: Add vbus_draw support") Reviewed-by: Thierry Reding Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20230405181854.42355-1-jonathanh@nvidia.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/tegra-xudc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 2b71b33725f1..5bccd64847ff 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -2167,7 +2167,7 @@ static int tegra_xudc_gadget_vbus_draw(struct usb_gadget *gadget, dev_dbg(xudc->dev, "%s: %u mA\n", __func__, m_a); - if (xudc->curr_usbphy->chg_type == SDP_TYPE) + if (xudc->curr_usbphy && xudc->curr_usbphy->chg_type == SDP_TYPE) ret = usb_phy_set_power(xudc->curr_usbphy, m_a); return ret; -- GitLab From 9d9a7614a75989a2356c8d2db736ce1a69d92fe4 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Wed, 5 Apr 2023 19:18:54 +0100 Subject: [PATCH 3483/5631] usb: gadget: tegra-xudc: Remove unneeded return variable The 'ret' variable in the function tegra_xudc_gadget_vbus_draw() is not needed and so remove this variable. Reviewed-by: Thierry Reding Signed-off-by: Jon Hunter Link: https://lore.kernel.org/r/20230405181854.42355-2-jonathanh@nvidia.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/tegra-xudc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 5bccd64847ff..34e9c1df54c7 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -2162,15 +2162,14 @@ static int tegra_xudc_gadget_stop(struct usb_gadget *gadget) static int tegra_xudc_gadget_vbus_draw(struct usb_gadget *gadget, unsigned int m_a) { - int ret = 0; struct tegra_xudc *xudc = to_xudc(gadget); dev_dbg(xudc->dev, "%s: %u mA\n", __func__, m_a); if (xudc->curr_usbphy && xudc->curr_usbphy->chg_type == SDP_TYPE) - ret = usb_phy_set_power(xudc->curr_usbphy, m_a); + return usb_phy_set_power(xudc->curr_usbphy, m_a); - return ret; + return 0; } static int tegra_xudc_set_selfpowered(struct usb_gadget *gadget, int is_on) -- GitLab From 4ff910be01c0ca28c2ea8b354dd47a3a17524489 Mon Sep 17 00:00:00 2001 From: Reiji Watanabe Date: Tue, 18 Apr 2023 19:18:51 -0700 Subject: [PATCH 3484/5631] KVM: arm64: Acquire mp_state_lock in kvm_arch_vcpu_ioctl_vcpu_init() kvm_arch_vcpu_ioctl_vcpu_init() doesn't acquire mp_state_lock when setting the mp_state to KVM_MP_STATE_RUNNABLE. Fix the code to acquire the lock. Signed-off-by: Reiji Watanabe [maz: minor refactor] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230419021852.2981107-2-reijiw@google.com --- arch/arm64/kvm/arm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fd8d355aca15..ad3655a7d122 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1241,11 +1241,15 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, /* * Handle the "start in power-off" case. */ + spin_lock(&vcpu->arch.mp_state_lock); + if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features)) - kvm_arm_vcpu_power_off(vcpu); + __kvm_arm_vcpu_power_off(vcpu); else WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); + spin_unlock(&vcpu->arch.mp_state_lock); + return 0; } -- GitLab From a189884bdc9238aeba941c50f02e25eb584fafed Mon Sep 17 00:00:00 2001 From: Reiji Watanabe Date: Tue, 18 Apr 2023 19:18:52 -0700 Subject: [PATCH 3485/5631] KVM: arm64: Have kvm_psci_vcpu_on() use WRITE_ONCE() to update mp_state All accessors of kvm_vcpu_arch::mp_state should be {READ,WRITE}_ONCE(), since readers of the mp_state don't acquire the mp_state_lock. Nonetheless, kvm_psci_vcpu_on() updates the mp_state without using WRITE_ONCE(). So, fix the code to update the mp_state using WRITE_ONCE. Signed-off-by: Reiji Watanabe Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230419021852.2981107-3-reijiw@google.com --- arch/arm64/kvm/psci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 5767e6baa61a..d046e82e3723 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -110,7 +110,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) */ smp_wmb(); - vcpu->arch.mp_state.mp_state = KVM_MP_STATE_RUNNABLE; + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); kvm_vcpu_wake_up(vcpu); out_unlock: -- GitLab From 4be8ddb48b1b6c6067fb59c846b9c6e19d6efe14 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:37 +0200 Subject: [PATCH 3486/5631] KVM: arm64: Slightly optimize flush_context() bitmap_zero() is faster than bitmap_clear(), so use it to save a few cycles. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/97bf2743f3a302b3066aced02218b9da60690dd3.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..bbf0677cfefa 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); -- GitLab From a00e9e4319c2a8a8b166da028292de83190e39a4 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:38 +0200 Subject: [PATCH 3487/5631] KVM: arm64: Use the bitmap API to allocate bitmaps Use bitmap_zalloc()/bitmap_free() instead of hand-writing them. It is less verbose and it improves the semantic. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/3c5043731db4d3635383e9326bc7e98e25de3288.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index bbf0677cfefa..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } -- GitLab From 091b813d3d1078afba6ed74fa8df2a5bbc9bf124 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Mon, 10 Apr 2023 18:26:38 -0500 Subject: [PATCH 3488/5631] usb: Add explicit of.h of_platform.h include Several USB drivers use of_platform_* functions which are declared in of_platform.h. of_platform.h gets implicitly included by of_device.h, but that is going to be removed soon. Nothing else depends on of_device.h so it can be dropped. Acked-by: Thinh Nguyen Acked-by: Chunfeng Yun Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20230410232639.1561152-1-robh@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/dwc3-am62.c | 2 +- drivers/usb/gadget/udc/rzv2m_usb3drd.c | 2 +- drivers/usb/mtu3/mtu3_host.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index b22fb78bc8e7..cda9458c809b 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/usb/gadget/udc/rzv2m_usb3drd.c b/drivers/usb/gadget/udc/rzv2m_usb3drd.c index 8855d8e8d793..589c7252e014 100644 --- a/drivers/usb/gadget/udc/rzv2m_usb3drd.c +++ b/drivers/usb/gadget/udc/rzv2m_usb3drd.c @@ -6,7 +6,7 @@ */ #include -#include +#include #include #include #include diff --git a/drivers/usb/mtu3/mtu3_host.c b/drivers/usb/mtu3/mtu3_host.c index f3903367a6a0..177d2caf887c 100644 --- a/drivers/usb/mtu3/mtu3_host.c +++ b/drivers/usb/mtu3/mtu3_host.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include "mtu3.h" -- GitLab From 735baf1b23458f71a8b15cb924af22c9ff9cd125 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 5 Apr 2023 11:03:42 +0200 Subject: [PATCH 3489/5631] xhci: fix debugfs register accesses while suspended Wire up the debugfs regset device pointer so that the controller is resumed before accessing registers to avoid crashing or locking up if it happens to be runtime suspended. Fixes: 02b6fdc2a153 ("usb: xhci: Add debugfs interface for xHCI driver") Cc: stable@vger.kernel.org # 4.15: 30332eeefec8: debugfs: regset32: Add Runtime PM support Cc: stable@vger.kernel.org # 4.15 Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230405090342.7363-1-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-debugfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 0bc7fe11f749..99baa60ef50f 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -133,6 +133,7 @@ static void xhci_debugfs_regset(struct xhci_hcd *xhci, u32 base, regset->regs = regs; regset->nregs = nregs; regset->base = hcd->regs + base; + regset->dev = hcd->self.controller; debugfs_create_regset32((const char *)rgs->name, 0444, parent, regset); } -- GitLab From f3588ea40aa17273c3303789b1828b3aa6b80748 Mon Sep 17 00:00:00 2001 From: Nobuhiro Iwamatsu Date: Thu, 6 Apr 2023 08:46:05 +0900 Subject: [PATCH 3490/5631] usb: host: xhci-plat: Use dev_is_pci() helper Use common dev_is_pci() helper for checking PCI devices. And if CONFIG_PCI is not defined, dev_is_pci returns false. Therefore, CONFIG_PCI is also unnecessary, so remove it. Signed-off-by: Nobuhiro Iwamatsu Link: https://lore.kernel.org/r/20230405234605.2310155-1-nobuhiro1.iwamatsu@toshiba.co.jp Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-plat.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index b9f9625467d6..76c5a84616ea 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -362,10 +362,8 @@ static int xhci_generic_plat_probe(struct platform_device *pdev) if (is_of_node(sysdev->fwnode) || is_acpi_device_node(sysdev->fwnode)) break; -#ifdef CONFIG_PCI - else if (sysdev->bus == &pci_bus_type) + else if (dev_is_pci(sysdev)) break; -#endif } if (!sysdev) -- GitLab From 9134c1fd05034dd29a1a2f010abd178af409171e Mon Sep 17 00:00:00 2001 From: Stanley Chang Date: Fri, 7 Apr 2023 14:07:31 +0800 Subject: [PATCH 3491/5631] usb: xhci: plat: Add USB 3.0 phy support For Realtek SoC, the usb xhci uses different driver for u2phy and u3phy. Therefore, add a hook to retrieve the USB 3.0 PHY to XHCI plat. Signed-off-by: Stanley Chang Link: https://lore.kernel.org/r/20230407060731.20537-1-stanley_chang@realtek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-plat.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 76c5a84616ea..b0c8e8efc43b 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -291,6 +291,21 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s goto dealloc_usb2_hcd; } + xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, + "usb-phy", 1); + if (IS_ERR(xhci->shared_hcd->usb_phy)) { + if (PTR_ERR(xhci->shared_hcd->usb_phy) != -ENODEV) + dev_err(sysdev, "%s get usb3phy fail (ret=%d)\n", + __func__, + (int)PTR_ERR(xhci->shared_hcd->usb_phy)); + xhci->shared_hcd->usb_phy = NULL; + } else { + ret = usb_phy_init(xhci->shared_hcd->usb_phy); + if (ret) + dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n", + __func__, ret); + } + xhci->shared_hcd->tpl_support = hcd->tpl_support; } -- GitLab From 4076c4f37bd9ef8415a7ab6acb6e2b5d6fddaf05 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Fri, 7 Apr 2023 14:24:05 +0800 Subject: [PATCH 3492/5631] dt-bindings: usb: mtk-xhci: add an optional frame count clock Add optional clock 'frmcnt_ck' used on 4nm or advanced process SoC Reviewed-by: AngeloGioacchino Del Regno Acked-by: Krzysztof Kozlowski Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230407062406.12575-1-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml index 72639c6b4e1c..e9644e333d78 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.yaml @@ -77,6 +77,7 @@ properties: - description: Mcu bus clock for register access - description: DMA bus clock for data transfer - description: controller clock + - description: frame count clock clock-names: minItems: 1 @@ -86,6 +87,7 @@ properties: - const: mcu_ck - const: dma_ck - const: xhci_ck + - const: frmcnt_ck phys: description: -- GitLab From 6a14ffc05c60fb4d5b7beb95460ac5642293e03f Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Fri, 7 Apr 2023 14:24:06 +0800 Subject: [PATCH 3493/5631] usb: xhci-mtk: add optional frame count clock Add optional clock frmcnt_ck used on 4nm or advanced process SoC Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230407062406.12575-2-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-mtk.c | 1 + drivers/usb/host/xhci-mtk.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index f7cbb08fc506..90cf40d6d0c3 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -398,6 +398,7 @@ static int xhci_mtk_clks_get(struct xhci_hcd_mtk *mtk) clks[2].id = "ref_ck"; clks[3].id = "mcu_ck"; clks[4].id = "dma_ck"; + clks[5].id = "frmcnt_ck"; return devm_clk_bulk_get_optional(mtk->dev, BULK_CLKS_NUM, clks); } diff --git a/drivers/usb/host/xhci-mtk.h b/drivers/usb/host/xhci-mtk.h index 1174a510dd38..faaaf05e36ce 100644 --- a/drivers/usb/host/xhci-mtk.h +++ b/drivers/usb/host/xhci-mtk.h @@ -15,7 +15,7 @@ #include "xhci.h" -#define BULK_CLKS_NUM 5 +#define BULK_CLKS_NUM 6 #define BULK_VREGS_NUM 2 /* support at most 64 ep, use 32 size hash table */ -- GitLab From 236d835302bd4e11697dfe65eb24a219ea5c70eb Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 14 Apr 2023 10:41:34 +0200 Subject: [PATCH 3494/5631] usb: dwc2: improve error handling in __dwc2_lowlevel_hw_enable Add error handling in __dwc2_lowlevel_hw_enable() that may leave the clocks and regulators enabled upon error. Acked-by: Minas Harutyunyan Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230414084137.1050487-2-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/platform.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index d1589ba7d322..c431ce6c119f 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -104,7 +104,7 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) if (hsotg->clk) { ret = clk_prepare_enable(hsotg->clk); if (ret) - return ret; + goto err_dis_reg; } if (hsotg->uphy) { @@ -113,10 +113,25 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) ret = hsotg->plat->phy_init(pdev, hsotg->plat->phy_type); } else { ret = phy_init(hsotg->phy); - if (ret == 0) + if (ret == 0) { ret = phy_power_on(hsotg->phy); + if (ret) + phy_exit(hsotg->phy); + } } + if (ret) + goto err_dis_clk; + + return 0; + +err_dis_clk: + if (hsotg->clk) + clk_disable_unprepare(hsotg->clk); + +err_dis_reg: + regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); + return ret; } -- GitLab From 28f75a39d8a878d9e8e57fd2aa0a1ad262d257bd Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 14 Apr 2023 10:41:35 +0200 Subject: [PATCH 3495/5631] dt-bindings: usb: dwc2: add utmi optional clock utmi clock is typically provided by PHY output. Add this optional clock, as the core could use other clocks depending on the SoC where it's used. This is needed on stm32mp15, when using the integrated full-speed PHY. Acked-by: Krzysztof Kozlowski Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230414084137.1050487-3-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/dwc2.yaml | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/usb/dwc2.yaml b/Documentation/devicetree/bindings/usb/dwc2.yaml index 371ba93f3ce5..d3506090f8b1 100644 --- a/Documentation/devicetree/bindings/usb/dwc2.yaml +++ b/Documentation/devicetree/bindings/usb/dwc2.yaml @@ -75,11 +75,14 @@ properties: maxItems: 1 clocks: - maxItems: 1 + minItems: 1 + maxItems: 2 clock-names: items: - const: otg + - const: utmi + minItems: 1 disable-over-current: type: boolean -- GitLab From 02329adeae1f92b0133cfc1a2b06645f4c496c1b Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 14 Apr 2023 10:41:36 +0200 Subject: [PATCH 3496/5631] usb: dwc2: platform: add support for utmi optional clock Add support for the utmi clock. It's needed on STM32MP15, when using the integrated full-speed PHY. This clock is an output of USBPHYC, but HS USBPHYC is not attached as PHY in this case: Full-Speed PHY is directly managed in dwc2 glue, through GGPIO register. Typical DT when using FS PHY &usbotg_hs { compatible = "st,stm32mp15-fsotg", "snps,dwc2"; pinctrl-names = "default"; pinctrl-0 = <&usbotg_hs_pins_a &usbotg_fs_dp_dm_pins_a>; vbus-supply = <&vbus_otg>; status = "okay"; }; In this configuration, USBPHYC clock output must be defined, so it can be properly enabled as a clock provider: clocks = <&rcc USBO_K>, <&usbphyc>; clock-names = "otg", "utmi"; Acked-by: Minas Harutyunyan Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230414084137.1050487-4-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc2/core.h | 2 ++ drivers/usb/dwc2/platform.c | 20 +++++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 40cf2880d7e5..0bb4c0c845bf 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -1003,6 +1003,7 @@ struct dwc2_hregs_backup { * @ctrl_out_desc: EP0 OUT data phase desc chain pointer * @irq: Interrupt request line number * @clk: Pointer to otg clock + * @utmi_clk: Pointer to utmi_clk clock * @reset: Pointer to dwc2 reset controller * @reset_ecc: Pointer to dwc2 optional reset controller in Stratix10. * @regset: A pointer to a struct debugfs_regset32, which contains @@ -1065,6 +1066,7 @@ struct dwc2_hsotg { void *priv; int irq; struct clk *clk; + struct clk *utmi_clk; struct reset_control *reset; struct reset_control *reset_ecc; diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index c431ce6c119f..5aee284018c0 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -101,10 +101,16 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) if (ret) return ret; + if (hsotg->utmi_clk) { + ret = clk_prepare_enable(hsotg->utmi_clk); + if (ret) + goto err_dis_reg; + } + if (hsotg->clk) { ret = clk_prepare_enable(hsotg->clk); if (ret) - goto err_dis_reg; + goto err_dis_utmi_clk; } if (hsotg->uphy) { @@ -129,6 +135,10 @@ static int __dwc2_lowlevel_hw_enable(struct dwc2_hsotg *hsotg) if (hsotg->clk) clk_disable_unprepare(hsotg->clk); +err_dis_utmi_clk: + if (hsotg->utmi_clk) + clk_disable_unprepare(hsotg->utmi_clk); + err_dis_reg: regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); @@ -171,6 +181,9 @@ static int __dwc2_lowlevel_hw_disable(struct dwc2_hsotg *hsotg) if (hsotg->clk) clk_disable_unprepare(hsotg->clk); + if (hsotg->utmi_clk) + clk_disable_unprepare(hsotg->utmi_clk); + return regulator_bulk_disable(ARRAY_SIZE(hsotg->supplies), hsotg->supplies); } @@ -247,6 +260,11 @@ static int dwc2_lowlevel_hw_init(struct dwc2_hsotg *hsotg) if (IS_ERR(hsotg->clk)) return dev_err_probe(hsotg->dev, PTR_ERR(hsotg->clk), "cannot get otg clock\n"); + hsotg->utmi_clk = devm_clk_get_optional(hsotg->dev, "utmi"); + if (IS_ERR(hsotg->utmi_clk)) + return dev_err_probe(hsotg->dev, PTR_ERR(hsotg->utmi_clk), + "cannot get utmi clock\n"); + /* Regulators */ for (i = 0; i < ARRAY_SIZE(hsotg->supplies); i++) hsotg->supplies[i].supply = dwc2_hsotg_supply_names[i]; -- GitLab From 21d018b75f4f1c183be565d302fde7a01ae79fb0 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Fri, 14 Apr 2023 10:41:37 +0200 Subject: [PATCH 3497/5631] ARM: dts: stm32: add USB OTG UTMI clock on stm32mp151 It's needed on STM32MP15, when using the integrated full-speed PHY. This clock is an output of USBPHYC, and the HS USBPHYC is not attached as PHY in this case (managed directly by dwc2 ggpio glue): &usbotg_hs { compatible = "st,stm32mp15-fsotg", "snps,dwc2"; pinctrl-names = "default"; pinctrl-0 = <&usbotg_hs_pins_a &usbotg_fs_dp_dm_pins_a>; vbus-supply = <&vbus_otg>; status = "okay"; }; USBPHYC clock output must be used, so it can be properly enabled as a clock provider. Without this, currently, when the dualport High-Speed USBPHYC isn't requested by either USBH or OTG, it remains uninitialized when probing OTG: OTG configured with full-speed PHY isn't properly clocked, resulting in error log like: [ 2.383138] dwc2 49000000.usb-otg: dwc2_core_reset: HANG! Soft Reset timeout GRSTCTL_CSFTRST. Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230414084137.1050487-5-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/boot/dts/stm32mp151.dtsi | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/boot/dts/stm32mp151.dtsi b/arch/arm/boot/dts/stm32mp151.dtsi index 4e437d3f2ed6..63f4c78fcc1d 100644 --- a/arch/arm/boot/dts/stm32mp151.dtsi +++ b/arch/arm/boot/dts/stm32mp151.dtsi @@ -1130,8 +1130,8 @@ usbotg_hs: usb-otg@49000000 { compatible = "st,stm32mp15-hsotg", "snps,dwc2"; reg = <0x49000000 0x10000>; - clocks = <&rcc USBO_K>; - clock-names = "otg"; + clocks = <&rcc USBO_K>, <&usbphyc>; + clock-names = "otg", "utmi"; resets = <&rcc USBO_R>; reset-names = "dwc2"; interrupts = ; -- GitLab From 9a8ad10c9f2e0925ff26308ec6756b93fc2f4977 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:14 +0200 Subject: [PATCH 3498/5631] USB: dwc3: fix runtime pm imbalance on probe errors Make sure not to suspend the device when probe fails to avoid disabling clocks and phys multiple times. Fixes: 328082376aea ("usb: dwc3: fix runtime PM in error path") Cc: stable@vger.kernel.org # 4.8 Cc: Roger Quadros Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-2-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index ed0ab90d3fac..d2350a87450e 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1895,13 +1895,11 @@ static int dwc3_probe(struct platform_device *pdev) spin_lock_init(&dwc->lock); mutex_init(&dwc->mutex); + pm_runtime_get_noresume(dev); pm_runtime_set_active(dev); pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, DWC3_DEFAULT_AUTOSUSPEND_DELAY); pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) - goto err1; pm_runtime_forbid(dev); @@ -1966,12 +1964,10 @@ static int dwc3_probe(struct platform_device *pdev) dwc3_free_event_buffers(dwc); err2: - pm_runtime_allow(&pdev->dev); - -err1: - pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); - + pm_runtime_allow(dev); + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_put_noidle(dev); disable_clks: dwc3_clk_disable(dwc); assert_reset: -- GitLab From 44d257e9012ee8040e41d224d0e5bfb5ef5427ea Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:15 +0200 Subject: [PATCH 3499/5631] USB: dwc3: fix runtime pm imbalance on unbind Make sure to balance the runtime PM usage count on driver unbind by adding back the pm_runtime_allow() call that had been erroneously removed. Fixes: 266d0493900a ("usb: dwc3: core: don't trigger runtime pm when remove driver") Cc: stable@vger.kernel.org # 5.9 Cc: Li Jun Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-3-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index d2350a87450e..ad48b7ebd880 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1991,6 +1991,7 @@ static int dwc3_remove(struct platform_device *pdev) dwc3_core_exit(dwc); dwc3_ulpi_exit(dwc); + pm_runtime_allow(&pdev->dev); pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); -- GitLab From 6b3b2402ca5be6a19f92968a5654bc64d3996d16 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:16 +0200 Subject: [PATCH 3500/5631] USB: dwc3: disable autosuspend on unbind Add the missing calls to disable autosuspend on probe errors and on driver unbind. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-4-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index ad48b7ebd880..bb737c3bd58a 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1966,6 +1966,7 @@ static int dwc3_probe(struct platform_device *pdev) err2: pm_runtime_allow(dev); pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); disable_clks: @@ -1993,6 +1994,7 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_allow(&pdev->dev); pm_runtime_disable(&pdev->dev); + pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); -- GitLab From bdb19d01026a5cccfa437be8adcf2df472c5889e Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:17 +0200 Subject: [PATCH 3501/5631] USB: dwc3: gadget: drop dead hibernation code The hibernation code is broken and has never been enabled in mainline and should thus be dropped. Remove the hibernation bits from the gadget code, which effectively reverts commits e1dadd3b0f27 ("usb: dwc3: workaround: bogus hibernation events") and 7b2a0368bbc9 ("usb: dwc3: gadget: set KEEP_CONNECT in case of hibernation") except for the spurious interrupt warning. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-5-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 46 +++++---------------------------------- 1 file changed, 6 insertions(+), 40 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 287ea6ee2463..087efbad94f7 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2569,7 +2569,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCFG, reg); } -static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on, int suspend) +static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) { u32 reg; u32 timeout = 2000; @@ -2588,17 +2588,11 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on, int suspend) reg &= ~DWC3_DCTL_KEEP_CONNECT; reg |= DWC3_DCTL_RUN_STOP; - if (dwc->has_hibernation) - reg |= DWC3_DCTL_KEEP_CONNECT; - __dwc3_gadget_set_speed(dwc); dwc->pullups_connected = true; } else { reg &= ~DWC3_DCTL_RUN_STOP; - if (dwc->has_hibernation && !suspend) - reg &= ~DWC3_DCTL_KEEP_CONNECT; - dwc->pullups_connected = false; } @@ -2665,7 +2659,7 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) * remaining event generated by the controller while polling for * DSTS.DEVCTLHLT. */ - return dwc3_gadget_run_stop(dwc, false, false); + return dwc3_gadget_run_stop(dwc, false); } static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) @@ -2719,7 +2713,7 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) dwc3_event_buffers_setup(dwc); __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true, false); + ret = dwc3_gadget_run_stop(dwc, true); } pm_runtime_put(dwc->dev); @@ -4300,30 +4294,6 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, dwc->link_state = next; } -static void dwc3_gadget_hibernation_interrupt(struct dwc3 *dwc, - unsigned int evtinfo) -{ - unsigned int is_ss = evtinfo & BIT(4); - - /* - * WORKAROUND: DWC3 revision 2.20a with hibernation support - * have a known issue which can cause USB CV TD.9.23 to fail - * randomly. - * - * Because of this issue, core could generate bogus hibernation - * events which SW needs to ignore. - * - * Refers to: - * - * STAR#9000546576: Device Mode Hibernation: Issue in USB 2.0 - * Device Fallback from SuperSpeed - */ - if (is_ss ^ (dwc->speed == USB_SPEED_SUPER)) - return; - - /* enter hibernation here */ -} - static void dwc3_gadget_interrupt(struct dwc3 *dwc, const struct dwc3_event_devt *event) { @@ -4341,11 +4311,7 @@ static void dwc3_gadget_interrupt(struct dwc3 *dwc, dwc3_gadget_wakeup_interrupt(dwc, event->event_info); break; case DWC3_DEVICE_EVENT_HIBER_REQ: - if (dev_WARN_ONCE(dwc->dev, !dwc->has_hibernation, - "unexpected hibernation event\n")) - break; - - dwc3_gadget_hibernation_interrupt(dwc, event->event_info); + dev_WARN_ONCE(dwc->dev, true, "unexpected hibernation event\n"); break; case DWC3_DEVICE_EVENT_LINK_STATUS_CHANGE: dwc3_gadget_linksts_change_interrupt(dwc, event->event_info); @@ -4678,7 +4644,7 @@ int dwc3_gadget_suspend(struct dwc3 *dwc) if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false, false); + dwc3_gadget_run_stop(dwc, false); spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); @@ -4699,7 +4665,7 @@ int dwc3_gadget_resume(struct dwc3 *dwc) if (ret < 0) goto err0; - ret = dwc3_gadget_run_stop(dwc, true, false); + ret = dwc3_gadget_run_stop(dwc, true); if (ret < 0) goto err1; -- GitLab From f56d0d29b018b6c19b4d5c60e768b5f90bb20c8d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:18 +0200 Subject: [PATCH 3502/5631] USB: dwc3: drop dead hibernation code The hibernation code is broken and has never been enabled in mainline and should thus be dropped. Specifically, the scratch buffer DMA mapping would have been leaked on every suspend cycle since commit 51f5d49ad6f0 ("usb: dwc3: core: simplify suspend/resume operations") if this feature was ever enabled. The related error handling was also broken and could have resulted in attempts to unmap never mapped buffers, etc. This effectively revert commit 0ffcaf3798bf ("usb: dwc3: core: allocate scratch buffers"). Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-6-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 103 +--------------------------------------- drivers/usb/dwc3/core.h | 8 ---- 2 files changed, 1 insertion(+), 110 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index bb737c3bd58a..4ed98855bf64 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -534,90 +534,6 @@ void dwc3_event_buffers_cleanup(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), 0); } -static int dwc3_alloc_scratch_buffers(struct dwc3 *dwc) -{ - if (!dwc->has_hibernation) - return 0; - - if (!dwc->nr_scratch) - return 0; - - dwc->scratchbuf = kmalloc_array(dwc->nr_scratch, - DWC3_SCRATCHBUF_SIZE, GFP_KERNEL); - if (!dwc->scratchbuf) - return -ENOMEM; - - return 0; -} - -static int dwc3_setup_scratch_buffers(struct dwc3 *dwc) -{ - dma_addr_t scratch_addr; - u32 param; - int ret; - - if (!dwc->has_hibernation) - return 0; - - if (!dwc->nr_scratch) - return 0; - - /* should never fall here */ - if (!WARN_ON(dwc->scratchbuf)) - return 0; - - scratch_addr = dma_map_single(dwc->sysdev, dwc->scratchbuf, - dwc->nr_scratch * DWC3_SCRATCHBUF_SIZE, - DMA_BIDIRECTIONAL); - if (dma_mapping_error(dwc->sysdev, scratch_addr)) { - dev_err(dwc->sysdev, "failed to map scratch buffer\n"); - ret = -EFAULT; - goto err0; - } - - dwc->scratch_addr = scratch_addr; - - param = lower_32_bits(scratch_addr); - - ret = dwc3_send_gadget_generic_command(dwc, - DWC3_DGCMD_SET_SCRATCHPAD_ADDR_LO, param); - if (ret < 0) - goto err1; - - param = upper_32_bits(scratch_addr); - - ret = dwc3_send_gadget_generic_command(dwc, - DWC3_DGCMD_SET_SCRATCHPAD_ADDR_HI, param); - if (ret < 0) - goto err1; - - return 0; - -err1: - dma_unmap_single(dwc->sysdev, dwc->scratch_addr, dwc->nr_scratch * - DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL); - -err0: - return ret; -} - -static void dwc3_free_scratch_buffers(struct dwc3 *dwc) -{ - if (!dwc->has_hibernation) - return; - - if (!dwc->nr_scratch) - return; - - /* should never fall here */ - if (!WARN_ON(dwc->scratchbuf)) - return; - - dma_unmap_single(dwc->sysdev, dwc->scratch_addr, dwc->nr_scratch * - DWC3_SCRATCHBUF_SIZE, DMA_BIDIRECTIONAL); - kfree(dwc->scratchbuf); -} - static void dwc3_core_num_eps(struct dwc3 *dwc) { struct dwc3_hwparams *parms = &dwc->hwparams; @@ -887,7 +803,6 @@ static bool dwc3_core_is_valid(struct dwc3 *dwc) static void dwc3_core_setup_global_control(struct dwc3 *dwc) { - u32 hwparams4 = dwc->hwparams.hwparams4; u32 reg; reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -915,9 +830,6 @@ static void dwc3_core_setup_global_control(struct dwc3 *dwc) reg &= ~DWC3_GCTL_DSBLCLKGTNG; break; case DWC3_GHWPARAMS1_EN_PWROPT_HIB: - /* enable hibernation here */ - dwc->nr_scratch = DWC3_GHWPARAMS4_HIBER_SCRATCHBUFS(hwparams4); - /* * REVISIT Enabling this bit so that host-mode hibernation * will work. Device-mode hibernation is not yet implemented. @@ -1161,10 +1073,6 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); - ret = dwc3_setup_scratch_buffers(dwc); - if (ret) - goto err1; - /* Set power down scale of suspend_clk */ dwc3_set_power_down_clk_scale(dwc); @@ -1920,14 +1828,10 @@ static int dwc3_probe(struct platform_device *pdev) if (ret) goto err3; - ret = dwc3_alloc_scratch_buffers(dwc); - if (ret) - goto err3; - ret = dwc3_core_init(dwc); if (ret) { dev_err_probe(dev, ret, "failed to initialize core\n"); - goto err4; + goto err3; } dwc3_check_params(dwc); @@ -1956,10 +1860,6 @@ static int dwc3_probe(struct platform_device *pdev) phy_exit(dwc->usb3_generic_phy); dwc3_ulpi_exit(dwc); - -err4: - dwc3_free_scratch_buffers(dwc); - err3: dwc3_free_event_buffers(dwc); @@ -1999,7 +1899,6 @@ static int dwc3_remove(struct platform_device *pdev) pm_runtime_set_suspended(&pdev->dev); dwc3_free_event_buffers(dwc); - dwc3_free_scratch_buffers(dwc); if (dwc->usb_psy) power_supply_put(dwc->usb_psy); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 26c8efefbff9..19490dca7937 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -973,12 +973,10 @@ struct dwc3_scratchpad_array { * @drd_work: workqueue used for role swapping * @ep0_trb: trb which is used for the ctrl_req * @bounce: address of bounce buffer - * @scratchbuf: address of scratch buffer * @setup_buf: used while precessing STD USB requests * @ep0_trb_addr: dma address of @ep0_trb * @bounce_addr: dma address of @bounce * @ep0_usb_req: dummy req used while handling STD USB requests - * @scratch_addr: dma address of scratchbuf * @ep0_in_setup: one control transfer is completed and enter setup phase * @lock: for synchronizing * @mutex: for mode switching @@ -1003,7 +1001,6 @@ struct dwc3_scratchpad_array { * @current_otg_role: current role of operation while using the OTG block * @desired_otg_role: desired role of operation while using the OTG block * @otg_restart_host: flag that OTG controller needs to restart host - * @nr_scratch: number of scratch buffers * @u1u2: only used on revisions <1.83a for workaround * @maximum_speed: maximum speed requested (mainly for testing purposes) * @max_ssp_rate: SuperSpeed Plus maximum signaling rate and lane count @@ -1060,7 +1057,6 @@ struct dwc3_scratchpad_array { * @delayed_status: true when gadget driver asks for delayed status * @ep0_bounced: true when we used bounce buffer * @ep0_expect_in: true when we expect a DATA IN transfer - * @has_hibernation: true when dwc3 was configured with Hibernation * @sysdev_is_parent: true when dwc3 device has a parent driver * @has_lpm_erratum: true when core was configured with LPM Erratum. Note that * there's now way for software to detect this in runtime. @@ -1130,11 +1126,9 @@ struct dwc3 { struct work_struct drd_work; struct dwc3_trb *ep0_trb; void *bounce; - void *scratchbuf; u8 *setup_buf; dma_addr_t ep0_trb_addr; dma_addr_t bounce_addr; - dma_addr_t scratch_addr; struct dwc3_request ep0_usb_req; struct completion ep0_in_setup; @@ -1194,7 +1188,6 @@ struct dwc3 { u32 current_otg_role; u32 desired_otg_role; bool otg_restart_host; - u32 nr_scratch; u32 u1u2; u32 maximum_speed; u32 gadget_max_speed; @@ -1291,7 +1284,6 @@ struct dwc3 { unsigned delayed_status:1; unsigned ep0_bounced:1; unsigned ep0_expect_in:1; - unsigned has_hibernation:1; unsigned sysdev_is_parent:1; unsigned has_lpm_erratum:1; unsigned is_utmi_l1_suspend:1; -- GitLab From fe296046c7219c3b156cddc90a0efaa52a5eb996 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:19 +0200 Subject: [PATCH 3503/5631] USB: dwc3: clean up probe error labels Use descriptive names consistently for the probe error labels. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-7-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 45 ++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 23 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 4ed98855bf64..e9cba095394c 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1717,7 +1717,7 @@ static int dwc3_probe(struct platform_device *pdev) dwc->reset = devm_reset_control_array_get_optional_shared(dev); if (IS_ERR(dwc->reset)) { ret = PTR_ERR(dwc->reset); - goto put_usb_psy; + goto err_put_psy; } if (dev->of_node) { @@ -1731,7 +1731,7 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->bus_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->bus_clk), "could not get bus clock\n"); - goto put_usb_psy; + goto err_put_psy; } if (dwc->bus_clk == NULL) { @@ -1739,7 +1739,7 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->bus_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->bus_clk), "could not get bus clock\n"); - goto put_usb_psy; + goto err_put_psy; } } @@ -1747,7 +1747,7 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->ref_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->ref_clk), "could not get ref clock\n"); - goto put_usb_psy; + goto err_put_psy; } if (dwc->ref_clk == NULL) { @@ -1755,7 +1755,7 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->ref_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->ref_clk), "could not get ref clock\n"); - goto put_usb_psy; + goto err_put_psy; } } @@ -1763,7 +1763,7 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->susp_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->susp_clk), "could not get suspend clock\n"); - goto put_usb_psy; + goto err_put_psy; } if (dwc->susp_clk == NULL) { @@ -1771,23 +1771,23 @@ static int dwc3_probe(struct platform_device *pdev) if (IS_ERR(dwc->susp_clk)) { ret = dev_err_probe(dev, PTR_ERR(dwc->susp_clk), "could not get suspend clock\n"); - goto put_usb_psy; + goto err_put_psy; } } } ret = reset_control_deassert(dwc->reset); if (ret) - goto put_usb_psy; + goto err_put_psy; ret = dwc3_clk_enable(dwc); if (ret) - goto assert_reset; + goto err_assert_reset; if (!dwc3_core_is_valid(dwc)) { dev_err(dwc->dev, "this is not a DesignWare USB3 DRD Core\n"); ret = -ENODEV; - goto disable_clks; + goto err_disable_clks; } platform_set_drvdata(pdev, dwc); @@ -1797,7 +1797,7 @@ static int dwc3_probe(struct platform_device *pdev) DWC3_GHWPARAMS0_AWIDTH(dwc->hwparams.hwparams0) == 64) { ret = dma_set_mask_and_coherent(dwc->sysdev, DMA_BIT_MASK(64)); if (ret) - goto disable_clks; + goto err_disable_clks; } spin_lock_init(&dwc->lock); @@ -1815,23 +1815,23 @@ static int dwc3_probe(struct platform_device *pdev) if (ret) { dev_err(dwc->dev, "failed to allocate event buffers\n"); ret = -ENOMEM; - goto err2; + goto err_allow_rpm; } dwc->edev = dwc3_get_extcon(dwc); if (IS_ERR(dwc->edev)) { ret = dev_err_probe(dwc->dev, PTR_ERR(dwc->edev), "failed to get extcon\n"); - goto err3; + goto err_free_event_buffers; } ret = dwc3_get_dr_mode(dwc); if (ret) - goto err3; + goto err_free_event_buffers; ret = dwc3_core_init(dwc); if (ret) { dev_err_probe(dev, ret, "failed to initialize core\n"); - goto err3; + goto err_free_event_buffers; } dwc3_check_params(dwc); @@ -1839,13 +1839,13 @@ static int dwc3_probe(struct platform_device *pdev) ret = dwc3_core_init_mode(dwc); if (ret) - goto err5; + goto err_exit_debugfs; pm_runtime_put(dev); return 0; -err5: +err_exit_debugfs: dwc3_debugfs_exit(dwc); dwc3_event_buffers_cleanup(dwc); @@ -1860,20 +1860,19 @@ static int dwc3_probe(struct platform_device *pdev) phy_exit(dwc->usb3_generic_phy); dwc3_ulpi_exit(dwc); -err3: +err_free_event_buffers: dwc3_free_event_buffers(dwc); - -err2: +err_allow_rpm: pm_runtime_allow(dev); pm_runtime_disable(dev); pm_runtime_dont_use_autosuspend(dev); pm_runtime_set_suspended(dev); pm_runtime_put_noidle(dev); -disable_clks: +err_disable_clks: dwc3_clk_disable(dwc); -assert_reset: +err_assert_reset: reset_control_assert(dwc->reset); -put_usb_psy: +err_put_psy: if (dwc->usb_psy) power_supply_put(dwc->usb_psy); -- GitLab From c8e9eccf6ed29f6c20fa489286eee1059566d035 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:20 +0200 Subject: [PATCH 3504/5631] USB: dwc3: clean up phy init error handling While there likely are no platforms out there that mix generic and legacy PHYs the driver should still be able to handle that, if only for consistency reasons. Add the missing calls to shutdown any legacy PHYs if generic PHY initialisation fails. Note that we continue to happily ignore potential errors from the legacy PHY callbacks... Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-8-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index e9cba095394c..c2326a37cd74 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1041,15 +1041,14 @@ static int dwc3_core_init(struct dwc3 *dwc) usb_phy_init(dwc->usb2_phy); usb_phy_init(dwc->usb3_phy); + ret = phy_init(dwc->usb2_generic_phy); if (ret < 0) - goto err0a; + goto err_shutdown_usb3_phy; ret = phy_init(dwc->usb3_generic_phy); - if (ret < 0) { - phy_exit(dwc->usb2_generic_phy); - goto err0a; - } + if (ret < 0) + goto err_exit_usb2_phy; ret = dwc3_core_soft_reset(dwc); if (ret) @@ -1225,11 +1224,12 @@ static int dwc3_core_init(struct dwc3 *dwc) usb_phy_set_suspend(dwc->usb3_phy, 1); err1: - usb_phy_shutdown(dwc->usb2_phy); - usb_phy_shutdown(dwc->usb3_phy); - phy_exit(dwc->usb2_generic_phy); phy_exit(dwc->usb3_generic_phy); - +err_exit_usb2_phy: + phy_exit(dwc->usb2_generic_phy); +err_shutdown_usb3_phy: + usb_phy_shutdown(dwc->usb3_phy); + usb_phy_shutdown(dwc->usb2_phy); err0a: dwc3_ulpi_exit(dwc); -- GitLab From d2f197822d5807d48bf27e713e2fd569e7017610 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:21 +0200 Subject: [PATCH 3505/5631] USB: dwc3: clean up core init error handling Clean up the core init error handling by using descriptive names for the error labels and releasing resourcing in reverse order consistently. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-9-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index c2326a37cd74..a83e9fc4668e 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1018,7 +1018,7 @@ static int dwc3_core_init(struct dwc3 *dwc) ret = dwc3_phy_setup(dwc); if (ret) - goto err0; + return ret; if (!dwc->ulpi_ready) { ret = dwc3_core_ulpi_init(dwc); @@ -1027,7 +1027,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_core_soft_reset(dwc); ret = -EPROBE_DEFER; } - goto err0; + return ret; } dwc->ulpi_ready = true; } @@ -1035,7 +1035,7 @@ static int dwc3_core_init(struct dwc3 *dwc) if (!dwc->phys_ready) { ret = dwc3_core_get_phy(dwc); if (ret) - goto err0a; + goto err_exit_ulpi; dwc->phys_ready = true; } @@ -1052,7 +1052,7 @@ static int dwc3_core_init(struct dwc3 *dwc) ret = dwc3_core_soft_reset(dwc); if (ret) - goto err1; + goto err_exit_usb3_phy; if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { @@ -1087,16 +1087,16 @@ static int dwc3_core_init(struct dwc3 *dwc) usb_phy_set_suspend(dwc->usb3_phy, 0); ret = phy_power_on(dwc->usb2_generic_phy); if (ret < 0) - goto err2; + goto err_suspend_usb3_phy; ret = phy_power_on(dwc->usb3_generic_phy); if (ret < 0) - goto err3; + goto err_power_off_usb2_phy; ret = dwc3_event_buffers_setup(dwc); if (ret) { dev_err(dwc->dev, "failed to setup event buffers\n"); - goto err4; + goto err_power_off_usb3_phy; } /* @@ -1213,27 +1213,23 @@ static int dwc3_core_init(struct dwc3 *dwc) return 0; -err4: +err_power_off_usb3_phy: phy_power_off(dwc->usb3_generic_phy); - -err3: +err_power_off_usb2_phy: phy_power_off(dwc->usb2_generic_phy); - -err2: - usb_phy_set_suspend(dwc->usb2_phy, 1); +err_suspend_usb3_phy: usb_phy_set_suspend(dwc->usb3_phy, 1); - -err1: + usb_phy_set_suspend(dwc->usb2_phy, 1); +err_exit_usb3_phy: phy_exit(dwc->usb3_generic_phy); err_exit_usb2_phy: phy_exit(dwc->usb2_generic_phy); err_shutdown_usb3_phy: usb_phy_shutdown(dwc->usb3_phy); usb_phy_shutdown(dwc->usb2_phy); -err0a: +err_exit_ulpi: dwc3_ulpi_exit(dwc); -err0: return ret; } -- GitLab From 1d72fab476567a0e4f51ee0a93882208ba28dc54 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:22 +0200 Subject: [PATCH 3506/5631] USB: dwc3: refactor phy handling Refactor the PHY handling using four new helpers to initialise, deinitialise, power on and power off all the PHYs. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-10-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 143 ++++++++++++++++++++++++---------------- 1 file changed, 86 insertions(+), 57 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index a83e9fc4668e..16f6270eb9ff 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -731,6 +731,76 @@ static int dwc3_phy_setup(struct dwc3 *dwc) return 0; } +static int dwc3_phy_init(struct dwc3 *dwc) +{ + int ret; + + usb_phy_init(dwc->usb2_phy); + usb_phy_init(dwc->usb3_phy); + + ret = phy_init(dwc->usb2_generic_phy); + if (ret < 0) + goto err_shutdown_usb3_phy; + + ret = phy_init(dwc->usb3_generic_phy); + if (ret < 0) + goto err_exit_usb2_phy; + + return 0; + +err_exit_usb2_phy: + phy_exit(dwc->usb2_generic_phy); +err_shutdown_usb3_phy: + usb_phy_shutdown(dwc->usb3_phy); + usb_phy_shutdown(dwc->usb2_phy); + + return ret; +} + +static void dwc3_phy_exit(struct dwc3 *dwc) +{ + phy_exit(dwc->usb3_generic_phy); + phy_exit(dwc->usb2_generic_phy); + + usb_phy_shutdown(dwc->usb3_phy); + usb_phy_shutdown(dwc->usb2_phy); +} + +static int dwc3_phy_power_on(struct dwc3 *dwc) +{ + int ret; + + usb_phy_set_suspend(dwc->usb2_phy, 0); + usb_phy_set_suspend(dwc->usb3_phy, 0); + + ret = phy_power_on(dwc->usb2_generic_phy); + if (ret < 0) + goto err_suspend_usb3_phy; + + ret = phy_power_on(dwc->usb3_generic_phy); + if (ret < 0) + goto err_power_off_usb2_phy; + + return 0; + +err_power_off_usb2_phy: + phy_power_off(dwc->usb2_generic_phy); +err_suspend_usb3_phy: + usb_phy_set_suspend(dwc->usb3_phy, 1); + usb_phy_set_suspend(dwc->usb2_phy, 1); + + return ret; +} + +static void dwc3_phy_power_off(struct dwc3 *dwc) +{ + phy_power_off(dwc->usb3_generic_phy); + phy_power_off(dwc->usb2_generic_phy); + + usb_phy_set_suspend(dwc->usb3_phy, 1); + usb_phy_set_suspend(dwc->usb2_phy, 1); +} + static int dwc3_clk_enable(struct dwc3 *dwc) { int ret; @@ -766,17 +836,8 @@ static void dwc3_clk_disable(struct dwc3 *dwc) static void dwc3_core_exit(struct dwc3 *dwc) { dwc3_event_buffers_cleanup(dwc); - - usb_phy_set_suspend(dwc->usb2_phy, 1); - usb_phy_set_suspend(dwc->usb3_phy, 1); - phy_power_off(dwc->usb2_generic_phy); - phy_power_off(dwc->usb3_generic_phy); - - usb_phy_shutdown(dwc->usb2_phy); - usb_phy_shutdown(dwc->usb3_phy); - phy_exit(dwc->usb2_generic_phy); - phy_exit(dwc->usb3_generic_phy); - + dwc3_phy_power_off(dwc); + dwc3_phy_exit(dwc); dwc3_clk_disable(dwc); reset_control_assert(dwc->reset); } @@ -1039,20 +1100,13 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc->phys_ready = true; } - usb_phy_init(dwc->usb2_phy); - usb_phy_init(dwc->usb3_phy); - - ret = phy_init(dwc->usb2_generic_phy); - if (ret < 0) - goto err_shutdown_usb3_phy; - - ret = phy_init(dwc->usb3_generic_phy); - if (ret < 0) - goto err_exit_usb2_phy; + ret = dwc3_phy_init(dwc); + if (ret) + goto err_exit_ulpi; ret = dwc3_core_soft_reset(dwc); if (ret) - goto err_exit_usb3_phy; + goto err_exit_phy; if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !DWC3_VER_IS_WITHIN(DWC3, ANY, 194A)) { @@ -1083,20 +1137,14 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - usb_phy_set_suspend(dwc->usb2_phy, 0); - usb_phy_set_suspend(dwc->usb3_phy, 0); - ret = phy_power_on(dwc->usb2_generic_phy); - if (ret < 0) - goto err_suspend_usb3_phy; - - ret = phy_power_on(dwc->usb3_generic_phy); - if (ret < 0) - goto err_power_off_usb2_phy; + dwc3_phy_power_on(dwc); + if (ret) + goto err_exit_phy; ret = dwc3_event_buffers_setup(dwc); if (ret) { dev_err(dwc->dev, "failed to setup event buffers\n"); - goto err_power_off_usb3_phy; + goto err_power_off_phy; } /* @@ -1213,20 +1261,10 @@ static int dwc3_core_init(struct dwc3 *dwc) return 0; -err_power_off_usb3_phy: - phy_power_off(dwc->usb3_generic_phy); -err_power_off_usb2_phy: - phy_power_off(dwc->usb2_generic_phy); -err_suspend_usb3_phy: - usb_phy_set_suspend(dwc->usb3_phy, 1); - usb_phy_set_suspend(dwc->usb2_phy, 1); -err_exit_usb3_phy: - phy_exit(dwc->usb3_generic_phy); -err_exit_usb2_phy: - phy_exit(dwc->usb2_generic_phy); -err_shutdown_usb3_phy: - usb_phy_shutdown(dwc->usb3_phy); - usb_phy_shutdown(dwc->usb2_phy); +err_power_off_phy: + dwc3_phy_power_off(dwc); +err_exit_phy: + dwc3_phy_exit(dwc); err_exit_ulpi: dwc3_ulpi_exit(dwc); @@ -1844,17 +1882,8 @@ static int dwc3_probe(struct platform_device *pdev) err_exit_debugfs: dwc3_debugfs_exit(dwc); dwc3_event_buffers_cleanup(dwc); - - usb_phy_set_suspend(dwc->usb2_phy, 1); - usb_phy_set_suspend(dwc->usb3_phy, 1); - phy_power_off(dwc->usb2_generic_phy); - phy_power_off(dwc->usb3_generic_phy); - - usb_phy_shutdown(dwc->usb2_phy); - usb_phy_shutdown(dwc->usb3_phy); - phy_exit(dwc->usb2_generic_phy); - phy_exit(dwc->usb3_generic_phy); - + dwc3_phy_power_off(dwc); + dwc3_phy_exit(dwc); dwc3_ulpi_exit(dwc); err_free_event_buffers: dwc3_free_event_buffers(dwc); -- GitLab From bd82857424d37897ad994381f7c580dacf2e2988 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:23 +0200 Subject: [PATCH 3507/5631] USB: dwc3: refactor clock lookups The probe callback has become unwieldy so break out the clock lookups into a new helper function to improve readability. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-11-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 116 +++++++++++++++++++++------------------- 1 file changed, 61 insertions(+), 55 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 16f6270eb9ff..31dd9f21820e 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1704,6 +1704,64 @@ static struct extcon_dev *dwc3_get_extcon(struct dwc3 *dwc) return edev; } +static int dwc3_get_clocks(struct dwc3 *dwc) +{ + struct device *dev = dwc->dev; + + if (!dev->of_node) + return 0; + + /* + * Clocks are optional, but new DT platforms should support all clocks + * as required by the DT-binding. + * Some devices have different clock names in legacy device trees, + * check for them to retain backwards compatibility. + */ + dwc->bus_clk = devm_clk_get_optional(dev, "bus_early"); + if (IS_ERR(dwc->bus_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), + "could not get bus clock\n"); + } + + if (dwc->bus_clk == NULL) { + dwc->bus_clk = devm_clk_get_optional(dev, "bus_clk"); + if (IS_ERR(dwc->bus_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->bus_clk), + "could not get bus clock\n"); + } + } + + dwc->ref_clk = devm_clk_get_optional(dev, "ref"); + if (IS_ERR(dwc->ref_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), + "could not get ref clock\n"); + } + + if (dwc->ref_clk == NULL) { + dwc->ref_clk = devm_clk_get_optional(dev, "ref_clk"); + if (IS_ERR(dwc->ref_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->ref_clk), + "could not get ref clock\n"); + } + } + + dwc->susp_clk = devm_clk_get_optional(dev, "suspend"); + if (IS_ERR(dwc->susp_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), + "could not get suspend clock\n"); + } + + if (dwc->susp_clk == NULL) { + dwc->susp_clk = devm_clk_get_optional(dev, "suspend_clk"); + if (IS_ERR(dwc->susp_clk)) { + return dev_err_probe(dev, PTR_ERR(dwc->susp_clk), + "could not get suspend clock\n"); + } + } + + return 0; +} + static int dwc3_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1754,61 +1812,9 @@ static int dwc3_probe(struct platform_device *pdev) goto err_put_psy; } - if (dev->of_node) { - /* - * Clocks are optional, but new DT platforms should support all - * clocks as required by the DT-binding. - * Some devices have different clock names in legacy device trees, - * check for them to retain backwards compatibility. - */ - dwc->bus_clk = devm_clk_get_optional(dev, "bus_early"); - if (IS_ERR(dwc->bus_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->bus_clk), - "could not get bus clock\n"); - goto err_put_psy; - } - - if (dwc->bus_clk == NULL) { - dwc->bus_clk = devm_clk_get_optional(dev, "bus_clk"); - if (IS_ERR(dwc->bus_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->bus_clk), - "could not get bus clock\n"); - goto err_put_psy; - } - } - - dwc->ref_clk = devm_clk_get_optional(dev, "ref"); - if (IS_ERR(dwc->ref_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->ref_clk), - "could not get ref clock\n"); - goto err_put_psy; - } - - if (dwc->ref_clk == NULL) { - dwc->ref_clk = devm_clk_get_optional(dev, "ref_clk"); - if (IS_ERR(dwc->ref_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->ref_clk), - "could not get ref clock\n"); - goto err_put_psy; - } - } - - dwc->susp_clk = devm_clk_get_optional(dev, "suspend"); - if (IS_ERR(dwc->susp_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->susp_clk), - "could not get suspend clock\n"); - goto err_put_psy; - } - - if (dwc->susp_clk == NULL) { - dwc->susp_clk = devm_clk_get_optional(dev, "suspend_clk"); - if (IS_ERR(dwc->susp_clk)) { - ret = dev_err_probe(dev, PTR_ERR(dwc->susp_clk), - "could not get suspend clock\n"); - goto err_put_psy; - } - } - } + ret = dwc3_get_clocks(dwc); + if (ret) + goto err_put_psy; ret = reset_control_deassert(dwc->reset); if (ret) -- GitLab From 9a4d7dd1990383df8ffa09d6879cecb0534405e1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Apr 2023 09:25:24 +0200 Subject: [PATCH 3508/5631] USB: dwc3: clean up probe declarations Clean up the probe variable declarations by removing the stray newlines. Acked-by: Thinh Nguyen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230404072524.19014-12-johan+linaro@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 31dd9f21820e..435a4ad780d8 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1766,12 +1766,10 @@ static int dwc3_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *res, dwc_res; + void __iomem *regs; struct dwc3 *dwc; - int ret; - void __iomem *regs; - dwc = devm_kzalloc(dev, sizeof(*dwc), GFP_KERNEL); if (!dwc) return -ENOMEM; -- GitLab From dac3b192107b978198e89ec0f77375738352e0c8 Mon Sep 17 00:00:00 2001 From: Frank Wang Date: Thu, 16 Mar 2023 16:11:49 +0800 Subject: [PATCH 3509/5631] usb: typec: tcpm: fix multiple times discover svids error PD3.0 Spec 6.4.4.3.2 say that only Responder supports 12 or more SVIDs, the Discover SVIDs Command Shall be executed multiple times until a Discover SVIDs VDO is returned ending either with a SVID value of 0x0000 in the last part of the last VDO or with a VDO containing two SVIDs with values of 0x0000. In the current implementation, if the last VDO does not find that the Discover SVIDs Command would be executed multiple times even if the Responder SVIDs are less than 12, and we found some odd dockers just meet this case. So fix it. Acked-by: Heikki Krogerus Signed-off-by: Frank Wang Link: https://lore.kernel.org/r/20230316081149.24519-1-frank.wang@rock-chips.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tcpm/tcpm.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4e276d2f15d1..3c6b0c8e2d3a 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1523,7 +1523,21 @@ static bool svdm_consume_svids(struct tcpm_port *port, const u32 *p, int cnt) pmdata->svids[pmdata->nsvids++] = svid; tcpm_log(port, "SVID %d: 0x%x", pmdata->nsvids, svid); } - return true; + + /* + * PD3.0 Spec 6.4.4.3.2: The SVIDs are returned 2 per VDO (see Table + * 6-43), and can be returned maximum 6 VDOs per response (see Figure + * 6-19). If the Respondersupports 12 or more SVID then the Discover + * SVIDs Command Shall be executed multiple times until a Discover + * SVIDs VDO is returned ending either with a SVID value of 0x0000 in + * the last part of the last VDO or with a VDO containing two SVIDs + * with values of 0x0000. + * + * However, some odd dockers support SVIDs less than 12 but without + * 0x0000 in the last VDO, so we need to break the Discover SVIDs + * request and return false here. + */ + return cnt == 7; abort: tcpm_log(port, "SVID_DISCOVERY_MAX(%d) too low!", SVID_DISCOVERY_MAX); return false; -- GitLab From 511b74e7c0b8ecd78b8175f5ee84dc0b6e014c19 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Wed, 12 Apr 2023 18:17:34 +0200 Subject: [PATCH 3510/5631] usb: typec: ucsi: don't print PPM init deferred errors ucsi_init() may be deferred as usb_role_sw may be deferred in ucsi_register_port(). This results in several PPM init failed (-517) messages maybe printed several times upon boot, like on stm32mp135f-dk board, until the role_switch driver gets probed. [ 19.880945] dwc2 49000000.usb: supply vusb_d not found, using dummy regulator [ 19.887136] dwc2 49000000.usb: supply vusb_a not found, using dummy regulator [ 19.975432] ucsi-stm32g0-i2c 0-0053: PPM init failed (-517) [ 20.155746] dwc2 49000000.usb: EPs: 9, dedicated fifos, 952 entries in SPRAM [ 20.175429] ucsi-stm32g0-i2c 0-0053: PPM init failed (-517) [ 20.184242] dwc2 49000000.usb: DWC OTG Controller Adopt dev_err_probe() instead of dev_err(), to only print other errors. Also print an error in case the wait count has expired. Reviewed-by: Heikki Krogerus Signed-off-by: Fabrice Gasnier Link: https://lore.kernel.org/r/20230412161734.3425090-1-fabrice.gasnier@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/ucsi/ucsi.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 8d1baf28df55..2b472ec01dc4 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1444,11 +1444,13 @@ static void ucsi_init_work(struct work_struct *work) ret = ucsi_init(ucsi); if (ret) - dev_err(ucsi->dev, "PPM init failed (%d)\n", ret); + dev_err_probe(ucsi->dev, ret, "PPM init failed\n"); if (ret == -EPROBE_DEFER) { - if (ucsi->work_count++ > UCSI_ROLE_SWITCH_WAIT_COUNT) + if (ucsi->work_count++ > UCSI_ROLE_SWITCH_WAIT_COUNT) { + dev_err(ucsi->dev, "PPM init failed, stop trying\n"); return; + } queue_delayed_work(system_long_wq, &ucsi->work, UCSI_ROLE_SWITCH_INTERVAL); -- GitLab From 0db213ea8eed5534a5169e807f28103cbc9d23df Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Fri, 7 Apr 2023 03:07:40 +0000 Subject: [PATCH 3511/5631] usb: gadget: udc: core: Invoke usb_gadget_connect only when started usb_udc_connect_control does not check to see if the udc has already been started. This causes gadget->ops->pullup to be called through usb_gadget_connect when invoked from usb_udc_vbus_handler even before usb_gadget_udc_start is called. Guard this by checking for udc->started in usb_udc_connect_control before invoking usb_gadget_connect. Guarding udc->vbus, udc->started, gadget->connect, gadget->deactivate related functions with connect_lock. usb_gadget_connect_locked, usb_gadget_disconnect_locked, usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are called with this lock held as they can be simulataneously invoked from different code paths. Adding an additional check to make sure udc is started(udc->started) before pullup callback is invoked. Fixes: 628ef0d273a6 ("usb: udc: add usb_udc_vbus_handler") Cc: stable@vger.kernel.org Signed-off-by: Badhri Jagan Sridharan Link: https://lore.kernel.org/r/20230407030741.3163220-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 148 ++++++++++++++++++++++++---------- 1 file changed, 104 insertions(+), 44 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 3dcbba739db6..af92c2e8e10c 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,6 +37,10 @@ static struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. + * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related + * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, + * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are + * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -48,6 +52,7 @@ struct usb_udc { struct list_head list; bool vbus; bool started; + struct mutex connect_lock; }; static struct class *udc_class; @@ -687,17 +692,9 @@ int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected - * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_connect(struct usb_gadget *gadget) +/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ +static int usb_gadget_connect_locked(struct usb_gadget *gadget) + __must_hold(&gadget->udc->connect_lock) { int ret = 0; @@ -706,10 +703,12 @@ int usb_gadget_connect(struct usb_gadget *gadget) goto out; } - if (gadget->deactivated) { + if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. + * + * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -724,22 +723,32 @@ int usb_gadget_connect(struct usb_gadget *gadget) return ret; } -EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). * * Returns zero on success, else negative errno. */ -int usb_gadget_disconnect(struct usb_gadget *gadget) +int usb_gadget_connect(struct usb_gadget *gadget) +{ + int ret; + + mutex_lock(&gadget->udc->connect_lock); + ret = usb_gadget_connect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_gadget_connect); + +/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ +static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) + __must_hold(&gadget->udc->connect_lock) { int ret = 0; @@ -751,10 +760,12 @@ int usb_gadget_disconnect(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated) { + if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. + * + * udc should have been started before gadget being pulled down. */ gadget->connected = false; goto out; @@ -774,6 +785,30 @@ int usb_gadget_disconnect(struct usb_gadget *gadget) return ret; } + +/** + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected + * + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_disconnect(struct usb_gadget *gadget) +{ + int ret; + + mutex_lock(&gadget->udc->connect_lock); + ret = usb_gadget_disconnect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); + + return ret; +} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -794,10 +829,11 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; + mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect(gadget); + ret = usb_gadget_disconnect_locked(gadget); if (ret) - goto out; + goto unlock; /* * If gadget was being connected before deactivation, we want @@ -807,6 +843,8 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; +unlock: + mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -830,6 +868,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; + mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -837,7 +876,8 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect(gadget); + ret = usb_gadget_connect_locked(gadget); + mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_activate(gadget, ret); @@ -1078,12 +1118,13 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -static void usb_udc_connect_control(struct usb_udc *udc) +/* Acquire connect_lock before calling this function. */ +static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) { - if (udc->vbus) - usb_gadget_connect(udc->gadget); + if (udc->vbus && udc->started) + usb_gadget_connect_locked(udc->gadget); else - usb_gadget_disconnect(udc->gadget); + usb_gadget_disconnect_locked(udc->gadget); } /** @@ -1099,10 +1140,12 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; + mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control(udc); + usb_udc_connect_control_locked(udc); } + mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1124,7 +1167,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start - tells usb device controller to start up + * usb_gadget_udc_start_locked - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1135,8 +1178,11 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. + * + * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start(struct usb_udc *udc) +static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) + __must_hold(&udc->connect_lock) { int ret; @@ -1153,7 +1199,7 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc) } /** - * usb_gadget_udc_stop - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1162,8 +1208,11 @@ static inline int usb_gadget_udc_start(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. + * + * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop(struct usb_udc *udc) +static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) + __must_hold(&udc->connect_lock) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1322,6 +1371,7 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; + mutex_init(&udc->connect_lock); udc->started = false; @@ -1523,11 +1573,15 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - ret = usb_gadget_udc_start(udc); - if (ret) + mutex_lock(&udc->connect_lock); + ret = usb_gadget_udc_start_locked(udc); + if (ret) { + mutex_unlock(&udc->connect_lock); goto err_start; + } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control(udc); + usb_udc_connect_control_locked(udc); + mutex_unlock(&udc->connect_lock); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1558,12 +1612,14 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - usb_gadget_disconnect(gadget); + mutex_lock(&udc->connect_lock); + usb_gadget_disconnect_locked(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop(udc); + usb_gadget_udc_stop_locked(udc); + mutex_unlock(&udc->connect_lock); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1649,11 +1705,15 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - usb_gadget_udc_start(udc); - usb_gadget_connect(udc->gadget); + mutex_lock(&udc->connect_lock); + usb_gadget_udc_start_locked(udc); + usb_gadget_connect_locked(udc->gadget); + mutex_unlock(&udc->connect_lock); } else if (sysfs_streq(buf, "disconnect")) { - usb_gadget_disconnect(udc->gadget); - usb_gadget_udc_stop(udc); + mutex_lock(&udc->connect_lock); + usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_udc_stop_locked(udc); + mutex_unlock(&udc->connect_lock); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; -- GitLab From a3afbf5cc887fc3401f012fe629810998ed61859 Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Fri, 7 Apr 2023 03:07:41 +0000 Subject: [PATCH 3512/5631] usb: gadget: udc: core: Prevent redundant calls to pullup usb_gadget_connect calls gadget->ops->pullup without checking whether gadget->connected was previously set. Make this symmetric to usb_gadget_disconnect by returning early if gadget->connected is already set. Fixes: 5a1da544e572 ("usb: gadget: core: do not try to disconnect gadget if it is not connected") Cc: stable@vger.kernel.org Signed-off-by: Badhri Jagan Sridharan Link: https://lore.kernel.org/r/20230407030741.3163220-2-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index af92c2e8e10c..1c5403ce9e7c 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -703,6 +703,9 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } + if (gadget->connected) + goto out; + if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. -- GitLab From d6f712f53b79f5017cdcefafb7a5aea9ec52da5d Mon Sep 17 00:00:00 2001 From: Yinhao Hu Date: Wed, 12 Apr 2023 13:58:52 +0800 Subject: [PATCH 3513/5631] usb: chipidea: fix missing goto in `ci_hdrc_probe` From the comment of ci_usb_phy_init, it returns an error code if usb_phy_init has failed, and it should do some clean up, not just return directly. Fix this by goto the error handling. Fixes: 74475ede784d ("usb: chipidea: move PHY operation to core") Reviewed-by: Dongliang Mu Acked-by: Peter Chen Signed-off-by: Yinhao Hu Link: https://lore.kernel.org/r/20230412055852.971991-1-dddddd@hust.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/usb/chipidea/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index d1d252c87e4f..798cb077867a 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1108,7 +1108,7 @@ static int ci_hdrc_probe(struct platform_device *pdev) ret = ci_usb_phy_init(ci); if (ret) { dev_err(dev, "unable to init phy: %d\n", ret); - return ret; + goto ulpi_exit; } ci->hw_bank.phys = res->start; -- GitLab From c507565aac2e8c4ca8dd36afcd40e15e4b459d93 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:51:57 +0800 Subject: [PATCH 3514/5631] usb: mtu3: give back request when rx error happens When the Rx enconnter errors, currently, only print error logs, that may cause class driver's RX halt, shall give back the request with error status meanwhile. Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-1-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3_qmu.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/usb/mtu3/mtu3_qmu.c b/drivers/usb/mtu3/mtu3_qmu.c index a2fdab8b63b2..a4da1af0b2c0 100644 --- a/drivers/usb/mtu3/mtu3_qmu.c +++ b/drivers/usb/mtu3/mtu3_qmu.c @@ -466,6 +466,37 @@ static void qmu_tx_zlp_error_handler(struct mtu3 *mtu, u8 epnum) mtu3_qmu_resume(mep); } +/* + * when rx error happens (except zlperr), QMU will stop, and RQCPR saves + * the GPD encountered error, Done irq will arise after resuming QMU again. + */ +static void qmu_error_rx(struct mtu3 *mtu, u8 epnum) +{ + struct mtu3_ep *mep = mtu->out_eps + epnum; + struct mtu3_gpd_ring *ring = &mep->gpd_ring; + struct qmu_gpd *gpd_current = NULL; + struct mtu3_request *mreq; + dma_addr_t cur_gpd_dma; + + cur_gpd_dma = read_rxq_cur_addr(mtu->mac_base, epnum); + gpd_current = gpd_dma_to_virt(ring, cur_gpd_dma); + + mreq = next_request(mep); + if (!mreq || mreq->gpd != gpd_current) { + dev_err(mtu->dev, "no correct RX req is found\n"); + return; + } + + mreq->request.status = -EAGAIN; + + /* by pass the current GDP */ + gpd_current->dw0_info |= cpu_to_le32(GPD_FLAGS_BPS | GPD_FLAGS_HWO); + mtu3_qmu_resume(mep); + + dev_dbg(mtu->dev, "%s EP%d, current=%p, req=%p\n", + __func__, epnum, gpd_current, mreq); +} + /* * NOTE: request list maybe is already empty as following case: * queue_tx --> qmu_interrupt(clear interrupt pending, schedule tasklet)--> @@ -571,14 +602,18 @@ static void qmu_exception_isr(struct mtu3 *mtu, u32 qmu_status) if ((qmu_status & RXQ_CSERR_INT) || (qmu_status & RXQ_LENERR_INT)) { errval = mtu3_readl(mbase, U3D_RQERRIR0); + mtu3_writel(mbase, U3D_RQERRIR0, errval); + for (i = 1; i < mtu->num_eps; i++) { if (errval & QMU_RX_CS_ERR(i)) dev_err(mtu->dev, "Rx %d CS error!\n", i); if (errval & QMU_RX_LEN_ERR(i)) dev_err(mtu->dev, "RX %d Length error\n", i); + + if (errval & (QMU_RX_CS_ERR(i) | QMU_RX_LEN_ERR(i))) + qmu_error_rx(mtu, i); } - mtu3_writel(mbase, U3D_RQERRIR0, errval); } if (qmu_status & RXQ_ZLPERR_INT) { -- GitLab From 3481769cd05b2ff3fa00d0aab526eb64de994fad Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:51:58 +0800 Subject: [PATCH 3515/5631] usb: mtu3: use boolean return value Prefer to use boolean value due to gpd_ring_empty() return true or false. See "16) Function return values and names" in coding-style.rst Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-2-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3_qmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/mtu3/mtu3_qmu.c b/drivers/usb/mtu3/mtu3_qmu.c index a4da1af0b2c0..6be4977a5db5 100644 --- a/drivers/usb/mtu3/mtu3_qmu.c +++ b/drivers/usb/mtu3/mtu3_qmu.c @@ -221,7 +221,7 @@ static struct qmu_gpd *advance_deq_gpd(struct mtu3_gpd_ring *ring) } /* check if a ring is emtpy */ -static int gpd_ring_empty(struct mtu3_gpd_ring *ring) +static bool gpd_ring_empty(struct mtu3_gpd_ring *ring) { struct qmu_gpd *enq = ring->enqueue; struct qmu_gpd *next; -- GitLab From d28f4091ea7ec3510fd6a3c6d433234e7a2bef14 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:51:59 +0800 Subject: [PATCH 3516/5631] usb: mtu3: fix kernel panic at qmu transfer done irq handler When handle qmu transfer irq, it will unlock @mtu->lock before give back request, if another thread handle disconnect event at the same time, and try to disable ep, it may lock @mtu->lock and free qmu ring, then qmu irq hanlder may get a NULL gpd, avoid the KE by checking gpd's value before handling it. e.g. qmu done irq on cpu0 thread running on cpu1 qmu_done_tx() handle gpd [0] mtu3_requ_complete() mtu3_gadget_ep_disable() unlock @mtu->lock give back request lock @mtu->lock mtu3_ep_disable() mtu3_gpd_ring_free() unlock @mtu->lock lock @mtu->lock get next gpd [1] [1]: goto [0] to handle next gpd, and next gpd may be NULL. Fixes: 48e0d3735aa5 ("usb: mtu3: supports new QMU format") Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-3-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3_qmu.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/usb/mtu3/mtu3_qmu.c b/drivers/usb/mtu3/mtu3_qmu.c index 6be4977a5db5..3d77408e3133 100644 --- a/drivers/usb/mtu3/mtu3_qmu.c +++ b/drivers/usb/mtu3/mtu3_qmu.c @@ -210,6 +210,7 @@ static struct qmu_gpd *advance_enq_gpd(struct mtu3_gpd_ring *ring) return ring->enqueue; } +/* @dequeue may be NULL if ring is unallocated or freed */ static struct qmu_gpd *advance_deq_gpd(struct mtu3_gpd_ring *ring) { if (ring->dequeue < ring->end) @@ -522,7 +523,7 @@ static void qmu_done_tx(struct mtu3 *mtu, u8 epnum) dev_dbg(mtu->dev, "%s EP%d, last=%p, current=%p, enq=%p\n", __func__, epnum, gpd, gpd_current, ring->enqueue); - while (gpd != gpd_current && !GET_GPD_HWO(gpd)) { + while (gpd && gpd != gpd_current && !GET_GPD_HWO(gpd)) { mreq = next_request(mep); @@ -561,7 +562,7 @@ static void qmu_done_rx(struct mtu3 *mtu, u8 epnum) dev_dbg(mtu->dev, "%s EP%d, last=%p, current=%p, enq=%p\n", __func__, epnum, gpd, gpd_current, ring->enqueue); - while (gpd != gpd_current && !GET_GPD_HWO(gpd)) { + while (gpd && gpd != gpd_current && !GET_GPD_HWO(gpd)) { mreq = next_request(mep); -- GitLab From ed50be81d536cdb25d00befe6ca21cd02f1c509d Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:52:00 +0800 Subject: [PATCH 3517/5631] usb: mtu3: unlock @mtu->lock just before giving back request No need unlock @mtu->lock when unmap request, unlock it just before giving back request, due to we do not lock this spinlock when map the request. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-4-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3_gadget.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/mtu3/mtu3_gadget.c b/drivers/usb/mtu3/mtu3_gadget.c index c0264d5426bf..ad0eeac4332d 100644 --- a/drivers/usb/mtu3/mtu3_gadget.c +++ b/drivers/usb/mtu3/mtu3_gadget.c @@ -23,7 +23,6 @@ __acquires(mep->mtu->lock) req->status = status; trace_mtu3_req_complete(mreq); - spin_unlock(&mtu->lock); /* ep0 makes use of PIO, needn't unmap it */ if (mep->epnum) @@ -32,6 +31,7 @@ __acquires(mep->mtu->lock) dev_dbg(mtu->dev, "%s complete req: %p, sts %d, %d/%d\n", mep->name, req, req->status, req->actual, req->length); + spin_unlock(&mtu->lock); usb_gadget_giveback_request(&mep->ep, req); spin_lock(&mtu->lock); } -- GitLab From 976a5c256e34085207c0abf0941b5c967d8d1c18 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:52:01 +0800 Subject: [PATCH 3518/5631] usb: mtu3: expose role-switch control to userspace The allow_userspace_control flag enables manual role switch from userspace, turn this feature on like several other USB DRD controller drivers. Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-5-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3_dr.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/mtu3/mtu3_dr.c b/drivers/usb/mtu3/mtu3_dr.c index 9b8aded3d95e..8191b7ed3852 100644 --- a/drivers/usb/mtu3/mtu3_dr.c +++ b/drivers/usb/mtu3/mtu3_dr.c @@ -294,6 +294,7 @@ static int ssusb_role_sw_register(struct otg_switch_mtk *otg_sx) role_sx_desc.get = ssusb_role_sw_get; role_sx_desc.fwnode = dev_fwnode(dev); role_sx_desc.driver_data = ssusb; + role_sx_desc.allow_userspace_control = true; otg_sx->role_sw = usb_role_switch_register(dev, &role_sx_desc); if (IS_ERR(otg_sx->role_sw)) return PTR_ERR(otg_sx->role_sw); -- GitLab From d10cb206acb45b9a0aa83318f0101bb56c33b7de Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:52:02 +0800 Subject: [PATCH 3519/5631] dt-bindings: usb: mtu3: add two optional clocks Add optional clock 'xhci_ck' and 'frmcnt_ck'; Reviewed-by: Rob Herring Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-6-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml index 5b908c457e3d..478214ab045e 100644 --- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml +++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.yaml @@ -66,6 +66,8 @@ properties: - description: Reference clock used by low power mode etc - description: Mcu bus clock for register access - description: DMA bus clock for data transfer + - description: DRD controller clock + - description: Frame count clock clock-names: minItems: 1 @@ -74,6 +76,8 @@ properties: - const: ref_ck - const: mcu_ck - const: dma_ck + - const: xhci_ck + - const: frmcnt_ck phys: description: -- GitLab From 41792870dc1cb8305ca04d563cabd63833e94762 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 17 Apr 2023 10:52:03 +0800 Subject: [PATCH 3520/5631] usb: mtu3: add optional clock xhci_ck and frmcnt_ck Add optional clock 'xhci_ck' which is usually the same as sys_ck, but some SoC use two separated clocks when the controller supports dual role mode; Add optional clock 'frmcnt_ck' used on 4nm or advanced process SoC. Signed-off-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230417025203.18097-7-chunfeng.yun@mediatek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/mtu3/mtu3.h | 2 +- drivers/usb/mtu3/mtu3_plat.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/mtu3/mtu3.h b/drivers/usb/mtu3/mtu3.h index 2d7b57e07eee..b4a7662dded5 100644 --- a/drivers/usb/mtu3/mtu3.h +++ b/drivers/usb/mtu3/mtu3.h @@ -90,7 +90,7 @@ struct mtu3_request; */ #define EP0_RESPONSE_BUF 6 -#define BULK_CLKS_CNT 4 +#define BULK_CLKS_CNT 6 /* device operated link and speed got from DEVICE_CONF register */ enum mtu3_speed { diff --git a/drivers/usb/mtu3/mtu3_plat.c b/drivers/usb/mtu3/mtu3_plat.c index d78ae52b4e26..6f264b129243 100644 --- a/drivers/usb/mtu3/mtu3_plat.c +++ b/drivers/usb/mtu3/mtu3_plat.c @@ -234,6 +234,8 @@ static int get_ssusb_rscs(struct platform_device *pdev, struct ssusb_mtk *ssusb) clks[1].id = "ref_ck"; clks[2].id = "mcu_ck"; clks[3].id = "dma_ck"; + clks[4].id = "xhci_ck"; + clks[5].id = "frmcnt_ck"; ret = devm_clk_bulk_get_optional(dev, BULK_CLKS_CNT, clks); if (ret) return ret; -- GitLab From a804a47658ced9e9cc6b6000846ddf208362f1b3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Apr 2023 08:50:51 +0200 Subject: [PATCH 3521/5631] dt-bindings: usb: ci-hdrc-usb2: allow multiple PHYs Qualcomm MSM8974 comes with USB HS phy in two variants, although final DTS chooses only one. Allow such combination in the ChipIdea USB2 bindings and also disallow any other properties in the ulpi node. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230420065051.22994-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml index e5e4dbc5a7a0..b26d26c2b023 100644 --- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml +++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.yaml @@ -322,8 +322,9 @@ properties: ulpi: type: object - properties: - phy: + additionalProperties: false + patternProperties: + "^phy(-[0-9])?$": description: The phy child node for Qcom chips. type: object $ref: /schemas/phy/qcom,usb-hs-phy.yaml -- GitLab From d21a797a3eeb2b001e07ff943e5611eab67a71a3 Mon Sep 17 00:00:00 2001 From: Stanley Chang Date: Wed, 19 Apr 2023 10:00:42 +0800 Subject: [PATCH 3522/5631] usb: dwc3: core: add support for disabling High-speed park mode Setting the PARKMODE_DISABLE_HS bit in the DWC3_USB3_GUCTL1. When this bit is set to '1' all HS bus instances in park mode are disabled For some USB wifi devices, if enable this feature it will reduce the performance. Therefore, add an option for disabling HS park mode by device-tree. In Synopsys's dwc3 data book: In a few high speed devices when an IN request is sent within 900ns of the ACK of the previous packet, these devices send a NAK. When connected to these devices, if required, the software can disable the park mode if you see performance drop in your system. When park mode is disabled, pipelining of multiple packet is disabled and instead one packet at a time is requested by the scheduler. This allows up to 12 NAKs in a micro-frame and improves performance of these slow devices. Acked-by: Thinh Nguyen Signed-off-by: Stanley Chang Link: https://lore.kernel.org/r/20230419020044.15475-1-stanley_chang@realtek.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 5 +++++ drivers/usb/dwc3/core.h | 4 ++++ 2 files changed, 9 insertions(+) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 435a4ad780d8..0beaab932e7d 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1198,6 +1198,9 @@ static int dwc3_core_init(struct dwc3 *dwc) if (dwc->parkmode_disable_ss_quirk) reg |= DWC3_GUCTL1_PARKMODE_DISABLE_SS; + if (dwc->parkmode_disable_hs_quirk) + reg |= DWC3_GUCTL1_PARKMODE_DISABLE_HS; + if (DWC3_VER_IS_WITHIN(DWC3, 290A, ANY) && (dwc->maximum_speed == USB_SPEED_HIGH || dwc->maximum_speed == USB_SPEED_FULL)) @@ -1509,6 +1512,8 @@ static void dwc3_get_properties(struct dwc3 *dwc) "snps,ulpi-ext-vbus-drv"); dwc->parkmode_disable_ss_quirk = device_property_read_bool(dev, "snps,parkmode-disable-ss-quirk"); + dwc->parkmode_disable_hs_quirk = device_property_read_bool(dev, + "snps,parkmode-disable-hs-quirk"); dwc->gfladj_refclk_lpm_sel = device_property_read_bool(dev, "snps,gfladj-refclk-lpm-sel-quirk"); diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 19490dca7937..d56457c02996 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -263,6 +263,7 @@ #define DWC3_GUCTL1_DEV_FORCE_20_CLK_FOR_30_CLK BIT(26) #define DWC3_GUCTL1_DEV_L1_EXIT_BY_HW BIT(24) #define DWC3_GUCTL1_PARKMODE_DISABLE_SS BIT(17) +#define DWC3_GUCTL1_PARKMODE_DISABLE_HS BIT(16) #define DWC3_GUCTL1_RESUME_OPMODE_HS_HOST BIT(10) /* Global Status Register */ @@ -1104,6 +1105,8 @@ struct dwc3_scratchpad_array { * VBUS with an external supply. * @parkmode_disable_ss_quirk: set if we need to disable all SuperSpeed * instances in park mode. + * @parkmode_disable_hs_quirk: set if we need to disable all HishSpeed + * instances in park mode. * @tx_de_emphasis_quirk: set if we enable Tx de-emphasis quirk * @tx_de_emphasis: Tx de-emphasis value * 0 - -6dB de-emphasis @@ -1318,6 +1321,7 @@ struct dwc3 { unsigned resume_hs_terminations:1; unsigned ulpi_ext_vbus_drv:1; unsigned parkmode_disable_ss_quirk:1; + unsigned parkmode_disable_hs_quirk:1; unsigned gfladj_refclk_lpm_sel:1; unsigned tx_de_emphasis_quirk:1; -- GitLab From 4a2f152af1c478d42bd4f535788d4dbec015704f Mon Sep 17 00:00:00 2001 From: Stanley Chang Date: Wed, 19 Apr 2023 10:00:43 +0800 Subject: [PATCH 3523/5631] dt-bindings: usb: snps,dwc3: Add 'snps,parkmode-disable-hs-quirk' quirk Add a new 'snps,parkmode-disable-hs-quirk' DT quirk to dwc3 core for disable the high-speed parkmode. For some USB wifi devices, if enable this feature it will reduce the performance. Therefore, add an option for disabling HS park mode by device-tree. In Synopsys's dwc3 data book: In a few high speed devices when an IN request is sent within 900ns of the ACK of the previous packet, these devices send a NAK. When connected to these devices, if required, the software can disable the park mode if you see performance drop in your system. When park mode is disabled, pipelining of multiple packet is disabled and instead one packet at a time is requested by the scheduler. This allows up to 12 NAKs in a micro-frame and improves performance of these slow devices. Acked-by: Rob Herring Signed-off-by: Stanley Chang Link: https://lore.kernel.org/r/20230419020044.15475-2-stanley_chang@realtek.com Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/usb/snps,dwc3.yaml | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml index eb58ba96b850..50edc4da780e 100644 --- a/Documentation/devicetree/bindings/usb/snps,dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/snps,dwc3.yaml @@ -236,6 +236,11 @@ properties: When set, all SuperSpeed bus instances in park mode are disabled. type: boolean + snps,parkmode-disable-hs-quirk: + description: + When set, all HighSpeed bus instances in park mode are disabled. + type: boolean + snps,dis_metastability_quirk: description: When set, disable metastability workaround. CAUTION! Use only if you are -- GitLab From 02435a739b81ae24aff5d6e930efef9458e2af3c Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Thu, 13 Apr 2023 12:57:40 -0700 Subject: [PATCH 3524/5631] usb: dwc3: gadget: Stall and restart EP0 if host is unresponsive It was observed that there are hosts that may complete pending SETUP transactions before the stop active transfers and controller halt occurs, leading to lingering endxfer commands on DEPs on subsequent pullup/gadget start iterations. dwc3_gadget_ep_disable name=ep8in flags=0x3009 direction=1 dwc3_gadget_ep_disable name=ep4in flags=1 direction=1 dwc3_gadget_ep_disable name=ep3out flags=1 direction=0 usb_gadget_disconnect deactivated=0 connected=0 ret=0 The sequence shows that the USB gadget disconnect (dwc3_gadget_pullup(0)) routine completed successfully, allowing for the USB gadget to proceed with a USB gadget connect. However, if this occurs the system runs into an issue where: BUG: spinlock already unlocked on CPU spin_bug+0x0 dwc3_remove_requests+0x278 dwc3_ep0_out_start+0xb0 __dwc3_gadget_start+0x25c This is due to the pending endxfers, leading to gadget start (w/o lock held) to execute the remove requests, which will unlock the dwc3 spinlock as part of giveback. To mitigate this, resolve the pending endxfers on the pullup disable path by re-locating the SETUP phase check after stop active transfers, since that is where the DWC3_EP_DELAY_STOP is potentially set. This also allows for handling of a host that may be unresponsive by using the completion timeout to trigger the stall and restart for EP0. Fixes: c96683798e27 ("usb: dwc3: ep0: Don't prepare beyond Setup stage") Cc: stable@vger.kernel.org Acked-by: Thinh Nguyen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20230413195742.11821-2-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 49 +++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 17 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 087efbad94f7..9f492c8a7d0b 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2617,29 +2617,17 @@ static int __dwc3_gadget_start(struct dwc3 *dwc); static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) { unsigned long flags; + int ret; spin_lock_irqsave(&dwc->lock, flags); dwc->connected = false; /* - * Per databook, when we want to stop the gadget, if a control transfer - * is still in process, complete it and get the core into setup phase. + * Attempt to end pending SETUP status phase, and not wait for the + * function to do so. */ - if (dwc->ep0state != EP0_SETUP_PHASE) { - int ret; - - if (dwc->delayed_status) - dwc3_ep0_send_delayed_status(dwc); - - reinit_completion(&dwc->ep0_in_setup); - - spin_unlock_irqrestore(&dwc->lock, flags); - ret = wait_for_completion_timeout(&dwc->ep0_in_setup, - msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); - spin_lock_irqsave(&dwc->lock, flags); - if (ret == 0) - dev_warn(dwc->dev, "timed out waiting for SETUP phase\n"); - } + if (dwc->delayed_status) + dwc3_ep0_send_delayed_status(dwc); /* * In the Synopsys DesignWare Cores USB3 Databook Rev. 3.30a @@ -2652,6 +2640,33 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); + /* + * Per databook, when we want to stop the gadget, if a control transfer + * is still in process, complete it and get the core into setup phase. + * In case the host is unresponsive to a SETUP transaction, forcefully + * stall the transfer, and move back to the SETUP phase, so that any + * pending endxfers can be executed. + */ + if (dwc->ep0state != EP0_SETUP_PHASE) { + reinit_completion(&dwc->ep0_in_setup); + + ret = wait_for_completion_timeout(&dwc->ep0_in_setup, + msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); + if (ret == 0) { + unsigned int dir; + + dev_warn(dwc->dev, "wait for SETUP phase timed out\n"); + spin_lock_irqsave(&dwc->lock, flags); + dir = !!dwc->ep0_expect_in; + if (dwc->ep0state == EP0_DATA_PHASE) + dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); + else + dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); + dwc3_ep0_stall_and_restart(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + } + } + /* * Note: if the GEVNTCOUNT indicates events in the event buffer, the * driver needs to acknowledge them before the controller can halt. -- GitLab From 17c51b1ba9c2d4b497349ac1622aafe67be16103 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 14 Apr 2023 14:30:43 +0200 Subject: [PATCH 3525/5631] s390/mm: use BIT macro to generate SET_MEMORY bit masks Use BIT macro to generate SET_MEMORY bit masks, which is easier to maintain if bits get added, or removed. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/set_memory.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index 25f2464dbb7e..ec3f44c602eb 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -6,11 +6,19 @@ extern struct mutex cpa_mutex; -#define SET_MEMORY_RO 1UL -#define SET_MEMORY_RW 2UL -#define SET_MEMORY_NX 4UL -#define SET_MEMORY_X 8UL -#define SET_MEMORY_4K 16UL +enum { + _SET_MEMORY_RO_BIT, + _SET_MEMORY_RW_BIT, + _SET_MEMORY_NX_BIT, + _SET_MEMORY_X_BIT, + _SET_MEMORY_4K_BIT, +}; + +#define SET_MEMORY_RO BIT(_SET_MEMORY_RO_BIT) +#define SET_MEMORY_RW BIT(_SET_MEMORY_RW_BIT) +#define SET_MEMORY_NX BIT(_SET_MEMORY_NX_BIT) +#define SET_MEMORY_X BIT(_SET_MEMORY_X_BIT) +#define SET_MEMORY_4K BIT(_SET_MEMORY_4K_BIT) int __set_memory(unsigned long addr, int numpages, unsigned long flags); -- GitLab From 0490d6d7ba0a479fdd805da54ae25220ce5b514d Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 14 Apr 2023 14:30:44 +0200 Subject: [PATCH 3526/5631] s390/mm: enable ARCH_HAS_SET_DIRECT_MAP Implement the set_direct_map_*() API, which allows to invalidate and set default permissions to pages within the direct mapping. Note that kernel_page_present(), which is also supposed to be part of this API, is intentionally not implemented. The reason for this is that kernel_page_present() is only used (and currently only makes sense) for suspend/resume, which isn't supported on s390. Reviewed-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + arch/s390/include/asm/set_memory.h | 7 ++++++ arch/s390/mm/pageattr.c | 35 ++++++++++++++++++++++++++++++ 3 files changed, 43 insertions(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a7568449ca59..37986abfe007 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -77,6 +77,7 @@ config S390 select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME + select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX diff --git a/arch/s390/include/asm/set_memory.h b/arch/s390/include/asm/set_memory.h index ec3f44c602eb..7a3eefd7a242 100644 --- a/arch/s390/include/asm/set_memory.h +++ b/arch/s390/include/asm/set_memory.h @@ -12,6 +12,8 @@ enum { _SET_MEMORY_NX_BIT, _SET_MEMORY_X_BIT, _SET_MEMORY_4K_BIT, + _SET_MEMORY_INV_BIT, + _SET_MEMORY_DEF_BIT, }; #define SET_MEMORY_RO BIT(_SET_MEMORY_RO_BIT) @@ -19,6 +21,8 @@ enum { #define SET_MEMORY_NX BIT(_SET_MEMORY_NX_BIT) #define SET_MEMORY_X BIT(_SET_MEMORY_X_BIT) #define SET_MEMORY_4K BIT(_SET_MEMORY_4K_BIT) +#define SET_MEMORY_INV BIT(_SET_MEMORY_INV_BIT) +#define SET_MEMORY_DEF BIT(_SET_MEMORY_DEF_BIT) int __set_memory(unsigned long addr, int numpages, unsigned long flags); @@ -58,4 +62,7 @@ static inline int set_memory_4k(unsigned long addr, int numpages) return __set_memory(addr, numpages, SET_MEMORY_4K); } +int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_default_noflush(struct page *page); + #endif diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 77f31791044d..0b196dea2d92 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -4,6 +4,7 @@ * Author(s): Jan Glauber */ #include +#include #include #include #include @@ -101,6 +102,14 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end, new = set_pte_bit(new, __pgprot(_PAGE_NOEXEC)); else if (flags & SET_MEMORY_X) new = clear_pte_bit(new, __pgprot(_PAGE_NOEXEC)); + if (flags & SET_MEMORY_INV) { + new = set_pte_bit(new, __pgprot(_PAGE_INVALID)); + } else if (flags & SET_MEMORY_DEF) { + new = __pte(pte_val(new) & PAGE_MASK); + new = set_pte_bit(new, PAGE_KERNEL); + if (!MACHINE_HAS_NX) + new = clear_pte_bit(new, __pgprot(_PAGE_NOEXEC)); + } pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE); ptep++; addr += PAGE_SIZE; @@ -151,6 +160,14 @@ static void modify_pmd_page(pmd_t *pmdp, unsigned long addr, new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC)); else if (flags & SET_MEMORY_X) new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC)); + if (flags & SET_MEMORY_INV) { + new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_INVALID)); + } else if (flags & SET_MEMORY_DEF) { + new = __pmd(pmd_val(new) & PMD_MASK); + new = set_pmd_bit(new, SEGMENT_KERNEL); + if (!MACHINE_HAS_NX) + new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC)); + } pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT); } @@ -232,6 +249,14 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr, new = set_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC)); else if (flags & SET_MEMORY_X) new = clear_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC)); + if (flags & SET_MEMORY_INV) { + new = set_pud_bit(new, __pgprot(_REGION_ENTRY_INVALID)); + } else if (flags & SET_MEMORY_DEF) { + new = __pud(pud_val(new) & PUD_MASK); + new = set_pud_bit(new, REGION3_KERNEL); + if (!MACHINE_HAS_NX) + new = clear_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC)); + } pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3); } @@ -325,6 +350,16 @@ int __set_memory(unsigned long addr, int numpages, unsigned long flags) return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags); } +int set_direct_map_invalid_noflush(struct page *page) +{ + return __set_memory((unsigned long)page_to_virt(page), 1, SET_MEMORY_INV); +} + +int set_direct_map_default_noflush(struct page *page) +{ + return __set_memory((unsigned long)page_to_virt(page), 1, SET_MEMORY_DEF); +} + #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE) static void ipte_range(pte_t *pte, unsigned long address, int nr) -- GitLab From 7608f70adcb1ea6957d7b9e1d5bd53584178fbbc Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 14 Apr 2023 14:30:45 +0200 Subject: [PATCH 3527/5631] s390: wire up memfd_secret system call s390 supports ARCH_HAS_SET_DIRECT_MAP, therefore wire up the memfd_secret system call, which depends on it. Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/syscalls/syscall.tbl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node -- GitLab From 34e4c79f3ba9e3d7de56be8ef1a514950915e0ee Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 14 Apr 2023 14:30:46 +0200 Subject: [PATCH 3528/5631] s390/mm: use VM_FLUSH_RESET_PERMS in module_alloc() Make use of the set_direct_map() calls for module allocations. In particular: - All changes to read-only permissions in kernel VA mappings are also applied to the direct mapping. Note that execute permissions are intentionally not applied to the direct mapping in order to make sure that all allocated pages within the direct mapping stay non-executable - module_alloc() passes the VM_FLUSH_RESET_PERMS to __vmalloc_node_range() to make sure that all implicit permission changes made to the direct mapping are reset when the allocated vm area is freed again Side effects: the direct mapping will be fragmented depending on how many vm areas with VM_FLUSH_RESET_PERMS and/or explicit page permission changes are allocated and freed again. For example, just after boot of a system the direct mapping statistics look like: $cat /proc/meminfo ... DirectMap4k: 111628 kB DirectMap1M: 16665600 kB DirectMap2G: 0 kB Acked-by: Alexander Gordeev Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/kernel/module.c | 7 ++--- arch/s390/mm/pageattr.c | 55 +++++++++++++++++++++++++++++++++++---- 2 files changed, 54 insertions(+), 8 deletions(-) diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 07a13546980d..adf3796f4dab 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -62,9 +62,10 @@ void *module_alloc(unsigned long size) if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, - MODULES_VADDR + get_module_load_offset(), MODULES_END, - gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, - __builtin_return_address(0)); + MODULES_VADDR + get_module_load_offset(), + MODULES_END, gfp_mask, PAGE_KERNEL, + VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK, + NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 0b196dea2d92..5ba3bd8a7b12 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -323,9 +323,6 @@ static int change_page_attr(unsigned long addr, unsigned long end, int rc = -EINVAL; pgd_t *pgdp; - if (addr == end) - return 0; - mutex_lock(&cpa_mutex); pgdp = pgd_offset_k(addr); do { if (pgd_none(*pgdp)) @@ -336,18 +333,66 @@ static int change_page_attr(unsigned long addr, unsigned long end, break; cond_resched(); } while (pgdp++, addr = next, addr < end && !rc); - mutex_unlock(&cpa_mutex); + return rc; +} + +static int change_page_attr_alias(unsigned long addr, unsigned long end, + unsigned long flags) +{ + unsigned long alias, offset, va_start, va_end; + struct vm_struct *area; + int rc = 0; + + /* + * Changes to read-only permissions on kernel VA mappings are also + * applied to the kernel direct mapping. Execute permissions are + * intentionally not transferred to keep all allocated pages within + * the direct mapping non-executable. + */ + flags &= SET_MEMORY_RO | SET_MEMORY_RW; + if (!flags) + return 0; + area = NULL; + while (addr < end) { + if (!area) + area = find_vm_area((void *)addr); + if (!area || !(area->flags & VM_ALLOC)) + return 0; + va_start = (unsigned long)area->addr; + va_end = va_start + area->nr_pages * PAGE_SIZE; + offset = (addr - va_start) >> PAGE_SHIFT; + alias = (unsigned long)page_address(area->pages[offset]); + rc = change_page_attr(alias, alias + PAGE_SIZE, flags); + if (rc) + break; + addr += PAGE_SIZE; + if (addr >= va_end) + area = NULL; + } return rc; } int __set_memory(unsigned long addr, int numpages, unsigned long flags) { + unsigned long end; + int rc; + if (!MACHINE_HAS_NX) flags &= ~(SET_MEMORY_NX | SET_MEMORY_X); if (!flags) return 0; + if (!numpages) + return 0; addr &= PAGE_MASK; - return change_page_attr(addr, addr + numpages * PAGE_SIZE, flags); + end = addr + numpages * PAGE_SIZE; + mutex_lock(&cpa_mutex); + rc = change_page_attr(addr, end, flags); + if (rc) + goto out; + rc = change_page_attr_alias(addr, end, flags); +out: + mutex_unlock(&cpa_mutex); + return rc; } int set_direct_map_invalid_noflush(struct page *page) -- GitLab From ccf7c3fb61ed7f3019b5be9fe70ccc0ab782cf2e Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 19 Apr 2023 15:17:02 +0200 Subject: [PATCH 3529/5631] s390: select ARCH_USE_SYM_ANNOTATIONS All old style assembly annotations have been converted for s390. Select ARCH_USE_SYM_ANNOTATIONS to make sure the old macros like ENTRY() aren't available anymore. This prevents that new code which uses the old macros will be added again. This follows what has been done for x86 with commit 2ce0d7f9766f ("x86/asm: Provide a Kconfig symbol for disabling old assembly annotations") and for arm64 with commit 50479d58eaa3 ("arm64: Disable old style assembly annotations"). Signed-off-by: Heiko Carstens Signed-off-by: Vasily Gorbik --- arch/s390/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 37986abfe007..574bd48199f2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -120,6 +120,7 @@ config S390 select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_SYM_ANNOTATIONS select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT -- GitLab From 491a78663e039fabc58c892ca8f2c2e08caaf4f8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 5 Apr 2023 15:08:40 +0200 Subject: [PATCH 3530/5631] stackleak: allow to specify arch specific stackleak poison function Factor out the code that fills the stack with the stackleak poison value in order to allow architectures to provide a faster implementation. Acked-by: Vasily Gorbik Signed-off-by: Heiko Carstens Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230405130841.1350565-2-hca@linux.ibm.com Signed-off-by: Vasily Gorbik --- kernel/stackleak.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/kernel/stackleak.c b/kernel/stackleak.c index c2c33d2202e9..34c9d81eea94 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -70,6 +70,18 @@ late_initcall(stackleak_sysctls_init); #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ +#ifndef __stackleak_poison +static __always_inline void __stackleak_poison(unsigned long erase_low, + unsigned long erase_high, + unsigned long poison) +{ + while (erase_low < erase_high) { + *(unsigned long *)erase_low = poison; + erase_low += sizeof(unsigned long); + } +} +#endif + static __always_inline void __stackleak_erase(bool on_task_stack) { const unsigned long task_stack_low = stackleak_task_low_bound(current); @@ -101,10 +113,7 @@ static __always_inline void __stackleak_erase(bool on_task_stack) else erase_high = task_stack_high; - while (erase_low < erase_high) { - *(unsigned long *)erase_low = STACKLEAK_POISON; - erase_low += sizeof(unsigned long); - } + __stackleak_poison(erase_low, erase_high, STACKLEAK_POISON); /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = task_stack_high; -- GitLab From 2a405f6bb3a5b2baaa74dfc5aaa0e1b99145bd1b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 5 Apr 2023 15:08:41 +0200 Subject: [PATCH 3531/5631] s390/stackleak: provide fast __stackleak_poison() implementation Provide an s390 specific __stackleak_poison() implementation which is faster than the generic variant. For the original implementation with an enforced 4kb stackframe for the getpid() system call the system call overhead increases by a factor of 3 if the stackleak feature is enabled. Using the s390 mvc based variant this is reduced to an increase of 25% instead. This is within the expected area, since the mvc based implementation is more or less a memset64() variant which comes with similar results. See commit 0b77d6701cf8 ("s390: implement memset16, memset32 & memset64"). Reviewed-by: Vasily Gorbik Signed-off-by: Heiko Carstens Link: https://lore.kernel.org/r/20230405130841.1350565-3-hca@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/include/asm/processor.h | 35 +++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index efffc28cbad8..dc17896a001a 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -118,6 +118,41 @@ unsigned long vdso_size(void); #define HAVE_ARCH_PICK_MMAP_LAYOUT +#define __stackleak_poison __stackleak_poison +static __always_inline void __stackleak_poison(unsigned long erase_low, + unsigned long erase_high, + unsigned long poison) +{ + unsigned long tmp, count; + + count = erase_high - erase_low; + if (!count) + return; + asm volatile( + " cghi %[count],8\n" + " je 2f\n" + " aghi %[count],-(8+1)\n" + " srlg %[tmp],%[count],8\n" + " ltgr %[tmp],%[tmp]\n" + " jz 1f\n" + "0: stg %[poison],0(%[addr])\n" + " mvc 8(256-8,%[addr]),0(%[addr])\n" + " la %[addr],256(%[addr])\n" + " brctg %[tmp],0b\n" + "1: stg %[poison],0(%[addr])\n" + " larl %[tmp],3f\n" + " ex %[count],0(%[tmp])\n" + " j 4f\n" + "2: stg %[poison],0(%[addr])\n" + " j 4f\n" + "3: mvc 8(1,%[addr]),0(%[addr])\n" + "4:\n" + : [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp) + : [poison] "d" (poison) + : "memory", "cc" + ); +} + /* * Thread structure */ -- GitLab From 495ff36388e8b71eb49e9242c8e04e06c5609e74 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 13 Apr 2023 12:17:57 -0700 Subject: [PATCH 3532/5631] firmware_loader: Strip off \n from customized path Having helped an user recently figure out why the customized path being specified was not taken into account landed on a subtle difference between using: echo "/xyz/firmware" > /sys/module/firmware_class/parameters/path which inserts an additional newline which is passed as is down to fw_get_filesystem_firmware() and ultimately kernel_read_file_from_path() and fails. Strip off \n from the customized firmware path such that users do not run into these hard to debug situations. Link: https://lore.kernel.org/all/20230402135423.3235-1-f.fainelli@gmail.com/ Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20230413191757.1949088-1-f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/main.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index b2c292ca95e8..9d79d5ad9102 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -493,9 +493,9 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv, const void *in_buffer)) { size_t size; - int i, len; + int i, len, maxlen = 0; int rc = -ENOENT; - char *path; + char *path, *nt = NULL; size_t msize = INT_MAX; void *buffer = NULL; @@ -518,8 +518,17 @@ fw_get_filesystem_firmware(struct device *device, struct fw_priv *fw_priv, if (!fw_path[i][0]) continue; - len = snprintf(path, PATH_MAX, "%s/%s%s", - fw_path[i], fw_priv->fw_name, suffix); + /* strip off \n from customized path */ + maxlen = strlen(fw_path[i]); + if (i == 0) { + nt = strchr(fw_path[i], '\n'); + if (nt) + maxlen = nt - fw_path[i]; + } + + len = snprintf(path, PATH_MAX, "%.*s/%s%s", + maxlen, fw_path[i], + fw_priv->fw_name, suffix); if (len >= PATH_MAX) { rc = -ENAMETOOLONG; break; -- GitLab From bedee105bf4a072294af068d89ec2d2bb5f457ae Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Apr 2023 10:03:07 +0200 Subject: [PATCH 3533/5631] firmware_loader: rework crypto dependencies MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The crypto dependencies for the firmwware loader are incomplete, in particular a built-in FW_LOADER fails to link against a modular crypto hash driver: ld.lld: error: undefined symbol: crypto_alloc_shash ld.lld: error: undefined symbol: crypto_shash_digest ld.lld: error: undefined symbol: crypto_destroy_tfm >>> referenced by main.c >>> drivers/base/firmware_loader/main.o:(fw_log_firmware_info) in archive vmlinux.a Rework this to use the usual 'select' from the driver module, to respect the built-in vs module dependencies, and add a more verbose crypto dependency to the debug option to prevent configurations that lead to a link failure. Fixes: 02fe26f25325 ("firmware_loader: Add debug message with checksum for FW file") Reviewed-by: Amadeusz Sławiński Acked-by: Herbert Xu Acked-by: Luis Chamberlain Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230414080329.76176-1-arnd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/Kconfig | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/base/firmware_loader/Kconfig b/drivers/base/firmware_loader/Kconfig index 0cabc783d67a..5ca00e02fe82 100644 --- a/drivers/base/firmware_loader/Kconfig +++ b/drivers/base/firmware_loader/Kconfig @@ -3,6 +3,8 @@ menu "Firmware loader" config FW_LOADER tristate "Firmware loading facility" if EXPERT + select CRYPTO_HASH if FW_LOADER_DEBUG + select CRYPTO_SHA256 if FW_LOADER_DEBUG default y help This enables the firmware loading facility in the kernel. The kernel @@ -26,10 +28,9 @@ config FW_LOADER config FW_LOADER_DEBUG bool "Log filenames and checksums for loaded firmware" + depends on CRYPTO = FW_LOADER || CRYPTO=y depends on DYNAMIC_DEBUG depends on FW_LOADER - depends on CRYPTO - depends on CRYPTO_SHA256 default FW_LOADER help Select this option to use dynamic debug to log firmware filenames and -- GitLab From 13890626501ffda22b18213ddaf7930473da5792 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 10 Apr 2023 15:37:07 -0400 Subject: [PATCH 3534/5631] USB: core: Add routines for endpoint checks in old drivers Many of the older USB drivers in the Linux USB stack were written based simply on a vendor's device specification. They use the endpoint information in the spec and assume these endpoints will always be present, with the properties listed, in any device matching the given vendor and product IDs. While that may have been true back then, with spoofing and fuzzing it is not true any more. More and more we are finding that those old drivers need to perform at least a minimum of checking before they try to use any endpoint other than ep0. To make this checking as simple as possible, we now add a couple of utility routines to the USB core. usb_check_bulk_endpoints() and usb_check_int_endpoints() take an interface pointer together with a list of endpoint addresses (numbers and directions). They check that the interface's current alternate setting includes endpoints with those addresses and that each of these endpoints has the right type: bulk or interrupt, respectively. Although we already have usb_find_common_endpoints() and related routines meant for a similar purpose, they are not well suited for this kind of checking. Those routines find endpoints of various kinds, but only one (either the first or the last) of each kind, and they don't verify that the endpoints' addresses agree with what the caller expects. In theory the new routines could be more general: They could take a particular altsetting as their argument instead of always using the interface's current altsetting. In practice I think this won't matter too much; multiple altsettings tend to be used for transferring media (audio or visual) over isochronous endpoints, not bulk or interrupt. Drivers for such devices will generally require more sophisticated checking than these simplistic routines provide. Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/dd2c8e8c-2c87-44ea-ba17-c64b97e201c9@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/usb.c | 76 ++++++++++++++++++++++++++++++++++++++++++ include/linux/usb.h | 5 +++ 2 files changed, 81 insertions(+) diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 34742fbbd84d..901ec732321c 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -206,6 +206,82 @@ int usb_find_common_endpoints_reverse(struct usb_host_interface *alt, } EXPORT_SYMBOL_GPL(usb_find_common_endpoints_reverse); +/** + * usb_find_endpoint() - Given an endpoint address, search for the endpoint's + * usb_host_endpoint structure in an interface's current altsetting. + * @intf: the interface whose current altsetting should be searched + * @ep_addr: the endpoint address (number and direction) to find + * + * Search the altsetting's list of endpoints for one with the specified address. + * + * Return: Pointer to the usb_host_endpoint if found, %NULL otherwise. + */ +static const struct usb_host_endpoint *usb_find_endpoint( + const struct usb_interface *intf, unsigned int ep_addr) +{ + int n; + const struct usb_host_endpoint *ep; + + n = intf->cur_altsetting->desc.bNumEndpoints; + ep = intf->cur_altsetting->endpoint; + for (; n > 0; (--n, ++ep)) { + if (ep->desc.bEndpointAddress == ep_addr) + return ep; + } + return NULL; +} + +/** + * usb_check_bulk_endpoints - Check whether an interface's current altsetting + * contains a set of bulk endpoints with the given addresses. + * @intf: the interface whose current altsetting should be searched + * @ep_addrs: 0-terminated array of the endpoint addresses (number and + * direction) to look for + * + * Search for endpoints with the specified addresses and check their types. + * + * Return: %true if all the endpoints are found and are bulk, %false otherwise. + */ +bool usb_check_bulk_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs) +{ + const struct usb_host_endpoint *ep; + + for (; *ep_addrs; ++ep_addrs) { + ep = usb_find_endpoint(intf, *ep_addrs); + if (!ep || !usb_endpoint_xfer_bulk(&ep->desc)) + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(usb_check_bulk_endpoints); + +/** + * usb_check_int_endpoints - Check whether an interface's current altsetting + * contains a set of interrupt endpoints with the given addresses. + * @intf: the interface whose current altsetting should be searched + * @ep_addrs: 0-terminated array of the endpoint addresses (number and + * direction) to look for + * + * Search for endpoints with the specified addresses and check their types. + * + * Return: %true if all the endpoints are found and are interrupt, + * %false otherwise. + */ +bool usb_check_int_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs) +{ + const struct usb_host_endpoint *ep; + + for (; *ep_addrs; ++ep_addrs) { + ep = usb_find_endpoint(intf, *ep_addrs); + if (!ep || !usb_endpoint_xfer_int(&ep->desc)) + return false; + } + return true; +} +EXPORT_SYMBOL_GPL(usb_check_int_endpoints); + /** * usb_find_alt_setting() - Given a configuration, find the alternate setting * for the given interface. diff --git a/include/linux/usb.h b/include/linux/usb.h index d510fabcafa2..4ae0466c846c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -291,6 +291,11 @@ void usb_put_intf(struct usb_interface *intf); #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) +bool usb_check_bulk_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); +bool usb_check_int_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); + /* * USB Resume Timer: Every Host controller driver should drive the resume * signalling on the bus for the amount of time defined by this macro. -- GitLab From df05a9b05e466a46725564528b277d0c570d0104 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 10 Apr 2023 15:38:22 -0400 Subject: [PATCH 3535/5631] USB: sisusbvga: Add endpoint checks The syzbot fuzzer was able to provoke a WARNING from the sisusbvga driver: ------------[ cut here ]------------ usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 1 PID: 26 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 1 PID: 26 Comm: kworker/1:1 Not tainted 6.2.0-rc5-syzkaller-00199-g5af6ce704936 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Workqueue: usb_hub_wq hub_event RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Code: 7c 24 18 e8 6c 50 80 fb 48 8b 7c 24 18 e8 62 1a 01 ff 41 89 d8 44 89 e1 4c 89 ea 48 89 c6 48 c7 c7 60 b1 fa 8a e8 84 b0 be 03 <0f> 0b e9 58 f8 ff ff e8 3e 50 80 fb 48 81 c5 c0 05 00 00 e9 84 f7 RSP: 0018:ffffc90000a1ed18 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff888012783a80 RSI: ffffffff816680ec RDI: fffff52000143d95 RBP: ffff888079020000 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000080000000 R11: 0000000000000000 R12: 0000000000000003 R13: ffff888017d33370 R14: 0000000000000003 R15: ffff888021213600 FS: 0000000000000000(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005592753a60b0 CR3: 0000000022899000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: sisusb_bulkout_msg drivers/usb/misc/sisusbvga/sisusbvga.c:224 [inline] sisusb_send_bulk_msg.constprop.0+0x904/0x1230 drivers/usb/misc/sisusbvga/sisusbvga.c:379 sisusb_send_bridge_packet drivers/usb/misc/sisusbvga/sisusbvga.c:567 [inline] sisusb_do_init_gfxdevice drivers/usb/misc/sisusbvga/sisusbvga.c:2077 [inline] sisusb_init_gfxdevice+0x87b/0x4000 drivers/usb/misc/sisusbvga/sisusbvga.c:2177 sisusb_probe+0x9cd/0xbe2 drivers/usb/misc/sisusbvga/sisusbvga.c:2869 ... The problem was caused by the fact that the driver does not check whether the endpoints it uses are actually present and have the appropriate types. This can be fixed by adding a simple check of the endpoints. Link: https://syzkaller.appspot.com/bug?extid=23be03b56c5259385d79 Reported-and-tested-by: syzbot+23be03b56c5259385d79@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/48ef98f7-51ae-4f63-b8d3-0ef2004bb60a@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/misc/sisusbvga/sisusbvga.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/usb/misc/sisusbvga/sisusbvga.c b/drivers/usb/misc/sisusbvga/sisusbvga.c index 654a79fd3231..febf34f9f049 100644 --- a/drivers/usb/misc/sisusbvga/sisusbvga.c +++ b/drivers/usb/misc/sisusbvga/sisusbvga.c @@ -2778,6 +2778,20 @@ static int sisusb_probe(struct usb_interface *intf, struct usb_device *dev = interface_to_usbdev(intf); struct sisusb_usb_data *sisusb; int retval = 0, i; + static const u8 ep_addresses[] = { + SISUSB_EP_GFX_IN | USB_DIR_IN, + SISUSB_EP_GFX_OUT | USB_DIR_OUT, + SISUSB_EP_GFX_BULK_OUT | USB_DIR_OUT, + SISUSB_EP_GFX_LBULK_OUT | USB_DIR_OUT, + SISUSB_EP_BRIDGE_IN | USB_DIR_IN, + SISUSB_EP_BRIDGE_OUT | USB_DIR_OUT, + 0}; + + /* Are the expected endpoints present? */ + if (!usb_check_bulk_endpoints(intf, ep_addresses)) { + dev_err(&intf->dev, "Invalid USB2VGA device\n"); + return -EINVAL; + } dev_info(&dev->dev, "USB2VGA dongle found at address %d\n", dev->devnum); -- GitLab From 76e31045ba030e94e72105c01b2e98f543d175ac Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 10 Apr 2023 15:40:05 -0400 Subject: [PATCH 3536/5631] media: radio-shark: Add endpoint checks The syzbot fuzzer was able to provoke a WARNING from the radio-shark2 driver: ------------[ cut here ]------------ usb 1-1: BOGUS urb xfer, pipe 1 != type 3 WARNING: CPU: 0 PID: 3271 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed2/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 0 PID: 3271 Comm: kworker/0:3 Not tainted 6.1.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Workqueue: usb_hub_wq hub_event RIP: 0010:usb_submit_urb+0xed2/0x1880 drivers/usb/core/urb.c:504 Code: 7c 24 18 e8 00 36 ea fb 48 8b 7c 24 18 e8 36 1c 02 ff 41 89 d8 44 89 e1 4c 89 ea 48 89 c6 48 c7 c7 a0 b6 90 8a e8 9a 29 b8 03 <0f> 0b e9 58 f8 ff ff e8 d2 35 ea fb 48 81 c5 c0 05 00 00 e9 84 f7 RSP: 0018:ffffc90003876dd0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000000 RDX: ffff8880750b0040 RSI: ffffffff816152b8 RDI: fffff5200070edac RBP: ffff8880172d81e0 R08: 0000000000000005 R09: 0000000000000000 R10: 0000000080000000 R11: 0000000000000000 R12: 0000000000000001 R13: ffff8880285c5040 R14: 0000000000000002 R15: ffff888017158200 FS: 0000000000000000(0000) GS:ffff8880b9a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffe03235b90 CR3: 000000000bc8e000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_bulk_msg+0x226/0x550 drivers/usb/core/message.c:387 shark_write_reg+0x1ff/0x2e0 drivers/media/radio/radio-shark2.c:88 ... The problem was caused by the fact that the driver does not check whether the endpoints it uses are actually present and have the appropriate types. This can be fixed by adding a simple check of these endpoints (and similarly for the radio-shark driver). Link: https://syzkaller.appspot.com/bug?extid=4b3f8190f6e13b3efd74 Reported-and-tested-by: syzbot+4b3f8190f6e13b3efd74@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/r/e2858ab4-4adf-46e5-bbf6-c56742034547@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/media/radio/radio-shark.c | 10 ++++++++++ drivers/media/radio/radio-shark2.c | 10 ++++++++++ 2 files changed, 20 insertions(+) diff --git a/drivers/media/radio/radio-shark.c b/drivers/media/radio/radio-shark.c index 8230da828d0e..127a3be0e0f0 100644 --- a/drivers/media/radio/radio-shark.c +++ b/drivers/media/radio/radio-shark.c @@ -316,6 +316,16 @@ static int usb_shark_probe(struct usb_interface *intf, { struct shark_device *shark; int retval = -ENOMEM; + static const u8 ep_addresses[] = { + SHARK_IN_EP | USB_DIR_IN, + SHARK_OUT_EP | USB_DIR_OUT, + 0}; + + /* Are the expected endpoints present? */ + if (!usb_check_int_endpoints(intf, ep_addresses)) { + dev_err(&intf->dev, "Invalid radioSHARK device\n"); + return -EINVAL; + } shark = kzalloc(sizeof(struct shark_device), GFP_KERNEL); if (!shark) diff --git a/drivers/media/radio/radio-shark2.c b/drivers/media/radio/radio-shark2.c index d150f12382c6..f1c5c0a6a335 100644 --- a/drivers/media/radio/radio-shark2.c +++ b/drivers/media/radio/radio-shark2.c @@ -282,6 +282,16 @@ static int usb_shark_probe(struct usb_interface *intf, { struct shark_device *shark; int retval = -ENOMEM; + static const u8 ep_addresses[] = { + SHARK_IN_EP | USB_DIR_IN, + SHARK_OUT_EP | USB_DIR_OUT, + 0}; + + /* Are the expected endpoints present? */ + if (!usb_check_int_endpoints(intf, ep_addresses)) { + dev_err(&intf->dev, "Invalid radioSHARK2 device\n"); + return -EINVAL; + } shark = kzalloc(sizeof(struct shark_device), GFP_KERNEL); if (!shark) -- GitLab From e1d6ca042e62c2a69513235f8629eb6e62ca79c5 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Apr 2023 17:27:03 +0300 Subject: [PATCH 3537/5631] firmware: stratix10-svc: Fix an NULL vs IS_ERR() bug in probe The svc_create_memory_pool() function returns error pointers. It never returns NULL. Fix the check. Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/5f9a8cb4-5a4f-460b-9cdc-2fae6c5b7922@kili.mountain Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/stratix10-svc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/stratix10-svc.c b/drivers/firmware/stratix10-svc.c index bde1f543f529..80f4e2d14e04 100644 --- a/drivers/firmware/stratix10-svc.c +++ b/drivers/firmware/stratix10-svc.c @@ -1133,8 +1133,8 @@ static int stratix10_svc_drv_probe(struct platform_device *pdev) return ret; genpool = svc_create_memory_pool(pdev, sh_memory); - if (!genpool) - return -ENOMEM; + if (IS_ERR(genpool)) + return PTR_ERR(genpool); /* allocate service controller and supporting channel */ controller = devm_kzalloc(dev, sizeof(*controller), GFP_KERNEL); -- GitLab From 03a85ab3ac910bc29e23db744091c40c8ed3d3af Mon Sep 17 00:00:00 2001 From: Anjelique Melendez Date: Fri, 7 Apr 2023 15:38:47 -0700 Subject: [PATCH 3538/5631] dt-bindings: leds-qcom-lpg: Add qcom,pmk8550-pwm compatible string Add qcom,pmk8550-pwm compatible string for the Qualcomm Technologies, Inc. PMK8550 PMIC which has two high resolution PWM channels. Signed-off-by: Anjelique Melendez Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230407223849.17623-2-quic_amelende@quicinc.com --- Documentation/devicetree/bindings/leds/leds-qcom-lpg.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/leds/leds-qcom-lpg.yaml b/Documentation/devicetree/bindings/leds/leds-qcom-lpg.yaml index 1df837798249..6295c91f43e8 100644 --- a/Documentation/devicetree/bindings/leds/leds-qcom-lpg.yaml +++ b/Documentation/devicetree/bindings/leds/leds-qcom-lpg.yaml @@ -27,6 +27,7 @@ properties: - qcom,pmc8180c-lpg - qcom,pmi8994-lpg - qcom,pmi8998-lpg + - qcom,pmk8550-pwm "#pwm-cells": const: 2 -- GitLab From b00d2ed37617b5f2f091c98acf542fbedefcbf9b Mon Sep 17 00:00:00 2001 From: Anjelique Melendez Date: Fri, 7 Apr 2023 15:38:48 -0700 Subject: [PATCH 3539/5631] leds: rgb: leds-qcom-lpg: Add support for high resolution PWM Certain PMICs like PMK8550 have a high resolution PWM module which can support from 8-bit to 15-bit PWM. Add support for it. Signed-off-by: Anjelique Melendez Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230407223849.17623-3-quic_amelende@quicinc.com --- drivers/leds/rgb/leds-qcom-lpg.c | 151 ++++++++++++++++++++++--------- 1 file changed, 106 insertions(+), 45 deletions(-) diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index 67f48f222109..373bcf8ebb52 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2017-2022 Linaro Ltd * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved. + * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved. */ #include #include @@ -17,10 +18,13 @@ #define LPG_SUBTYPE_REG 0x05 #define LPG_SUBTYPE_LPG 0x2 #define LPG_SUBTYPE_PWM 0xb +#define LPG_SUBTYPE_HI_RES_PWM 0xc #define LPG_SUBTYPE_LPG_LITE 0x11 #define LPG_PATTERN_CONFIG_REG 0x40 #define LPG_SIZE_CLK_REG 0x41 #define PWM_CLK_SELECT_MASK GENMASK(1, 0) +#define PWM_CLK_SELECT_HI_RES_MASK GENMASK(2, 0) +#define PWM_SIZE_HI_RES_MASK GENMASK(6, 4) #define LPG_PREDIV_CLK_REG 0x42 #define PWM_FREQ_PRE_DIV_MASK GENMASK(6, 5) #define PWM_FREQ_EXP_MASK GENMASK(2, 0) @@ -43,8 +47,10 @@ #define LPG_LUT_REG(x) (0x40 + (x) * 2) #define RAMP_CONTROL_REG 0xc8 -#define LPG_RESOLUTION 512 +#define LPG_RESOLUTION_9BIT BIT(9) +#define LPG_RESOLUTION_15BIT BIT(15) #define LPG_MAX_M 7 +#define LPG_MAX_PREDIV 6 struct lpg_channel; struct lpg_data; @@ -106,6 +112,7 @@ struct lpg { * @clk_sel: reference clock frequency selector * @pre_div_sel: divider selector of the reference clock * @pre_div_exp: exponential divider of the reference clock + * @pwm_resolution_sel: pwm resolution selector * @ramp_enabled: duty cycle is driven by iterating over lookup table * @ramp_ping_pong: reverse through pattern, rather than wrapping to start * @ramp_oneshot: perform only a single pass over the pattern @@ -138,6 +145,7 @@ struct lpg_channel { unsigned int clk_sel; unsigned int pre_div_sel; unsigned int pre_div_exp; + unsigned int pwm_resolution_sel; bool ramp_enabled; bool ramp_ping_pong; @@ -253,17 +261,24 @@ static int lpg_lut_sync(struct lpg *lpg, unsigned int mask) } static const unsigned int lpg_clk_rates[] = {0, 1024, 32768, 19200000}; +static const unsigned int lpg_clk_rates_hi_res[] = {0, 1024, 32768, 19200000, 76800000}; static const unsigned int lpg_pre_divs[] = {1, 3, 5, 6}; +static const unsigned int lpg_pwm_resolution[] = {9}; +static const unsigned int lpg_pwm_resolution_hi_res[] = {8, 9, 10, 11, 12, 13, 14, 15}; static int lpg_calc_freq(struct lpg_channel *chan, uint64_t period) { - unsigned int clk_sel, best_clk = 0; + unsigned int i, pwm_resolution_count, best_pwm_resolution_sel = 0; + const unsigned int *clk_rate_arr, *pwm_resolution_arr; + unsigned int clk_sel, clk_len, best_clk = 0; unsigned int div, best_div = 0; unsigned int m, best_m = 0; + unsigned int resolution; unsigned int error; unsigned int best_err = UINT_MAX; + u64 max_period, min_period; u64 best_period = 0; - u64 max_period; + u64 max_res; /* * The PWM period is determined by: @@ -272,73 +287,107 @@ static int lpg_calc_freq(struct lpg_channel *chan, uint64_t period) * period = -------------------------- * refclk * - * With resolution fixed at 2^9 bits, pre_div = {1, 3, 5, 6} and + * Resolution = 2^9 bits for PWM or + * 2^{8, 9, 10, 11, 12, 13, 14, 15} bits for high resolution PWM + * pre_div = {1, 3, 5, 6} and * M = [0..7]. * - * This allows for periods between 27uS and 384s, as the PWM framework - * wants a period of equal or lower length than requested, reject - * anything below 27uS. + * This allows for periods between 27uS and 384s for PWM channels and periods between + * 3uS and 24576s for high resolution PWMs. + * The PWM framework wants a period of equal or lower length than requested, + * reject anything below minimum period. */ - if (period <= (u64)NSEC_PER_SEC * LPG_RESOLUTION / 19200000) + + if (chan->subtype == LPG_SUBTYPE_HI_RES_PWM) { + clk_rate_arr = lpg_clk_rates_hi_res; + clk_len = ARRAY_SIZE(lpg_clk_rates_hi_res); + pwm_resolution_arr = lpg_pwm_resolution_hi_res; + pwm_resolution_count = ARRAY_SIZE(lpg_pwm_resolution_hi_res); + max_res = LPG_RESOLUTION_15BIT; + } else { + clk_rate_arr = lpg_clk_rates; + clk_len = ARRAY_SIZE(lpg_clk_rates); + pwm_resolution_arr = lpg_pwm_resolution; + pwm_resolution_count = ARRAY_SIZE(lpg_pwm_resolution); + max_res = LPG_RESOLUTION_9BIT; + } + + min_period = (u64)NSEC_PER_SEC * + div64_u64((1 << pwm_resolution_arr[0]), clk_rate_arr[clk_len - 1]); + if (period <= min_period) return -EINVAL; /* Limit period to largest possible value, to avoid overflows */ - max_period = (u64)NSEC_PER_SEC * LPG_RESOLUTION * 6 * (1 << LPG_MAX_M) / 1024; + max_period = (u64)NSEC_PER_SEC * max_res * LPG_MAX_PREDIV * + div64_u64((1 << LPG_MAX_M), 1024); if (period > max_period) period = max_period; /* - * Search for the pre_div, refclk and M by solving the rewritten formula - * for each refclk and pre_div value: + * Search for the pre_div, refclk, resolution and M by solving the rewritten formula + * for each refclk, resolution and pre_div value: * * period * refclk * M = log2 ------------------------------------- * NSEC_PER_SEC * pre_div * resolution */ - for (clk_sel = 1; clk_sel < ARRAY_SIZE(lpg_clk_rates); clk_sel++) { - u64 numerator = period * lpg_clk_rates[clk_sel]; - - for (div = 0; div < ARRAY_SIZE(lpg_pre_divs); div++) { - u64 denominator = (u64)NSEC_PER_SEC * lpg_pre_divs[div] * LPG_RESOLUTION; - u64 actual; - u64 ratio; - - if (numerator < denominator) - continue; - - ratio = div64_u64(numerator, denominator); - m = ilog2(ratio); - if (m > LPG_MAX_M) - m = LPG_MAX_M; - - actual = DIV_ROUND_UP_ULL(denominator * (1 << m), lpg_clk_rates[clk_sel]); - - error = period - actual; - if (error < best_err) { - best_err = error; - best_div = div; - best_m = m; - best_clk = clk_sel; - best_period = actual; + for (i = 0; i < pwm_resolution_count; i++) { + resolution = 1 << pwm_resolution_arr[i]; + for (clk_sel = 1; clk_sel < clk_len; clk_sel++) { + u64 numerator = period * clk_rate_arr[clk_sel]; + + for (div = 0; div < ARRAY_SIZE(lpg_pre_divs); div++) { + u64 denominator = (u64)NSEC_PER_SEC * lpg_pre_divs[div] * + resolution; + u64 actual; + u64 ratio; + + if (numerator < denominator) + continue; + + ratio = div64_u64(numerator, denominator); + m = ilog2(ratio); + if (m > LPG_MAX_M) + m = LPG_MAX_M; + + actual = DIV_ROUND_UP_ULL(denominator * (1 << m), + clk_rate_arr[clk_sel]); + error = period - actual; + if (error < best_err) { + best_err = error; + best_div = div; + best_m = m; + best_clk = clk_sel; + best_period = actual; + best_pwm_resolution_sel = i; + } } } } - chan->clk_sel = best_clk; chan->pre_div_sel = best_div; chan->pre_div_exp = best_m; chan->period = best_period; - + chan->pwm_resolution_sel = best_pwm_resolution_sel; return 0; } static void lpg_calc_duty(struct lpg_channel *chan, uint64_t duty) { - unsigned int max = LPG_RESOLUTION - 1; + unsigned int max; unsigned int val; + unsigned int clk_rate; + + if (chan->subtype == LPG_SUBTYPE_HI_RES_PWM) { + max = LPG_RESOLUTION_15BIT - 1; + clk_rate = lpg_clk_rates_hi_res[chan->clk_sel]; + } else { + max = LPG_RESOLUTION_9BIT - 1; + clk_rate = lpg_clk_rates[chan->clk_sel]; + } - val = div64_u64(duty * lpg_clk_rates[chan->clk_sel], + val = div64_u64(duty * clk_rate, (u64)NSEC_PER_SEC * lpg_pre_divs[chan->pre_div_sel] * (1 << chan->pre_div_exp)); chan->pwm_value = min(val, max); @@ -354,7 +403,7 @@ static void lpg_apply_freq(struct lpg_channel *chan) val = chan->clk_sel; - /* Specify 9bit resolution, based on the subtype of the channel */ + /* Specify resolution, based on the subtype of the channel */ switch (chan->subtype) { case LPG_SUBTYPE_LPG: val |= GENMASK(5, 4); @@ -362,6 +411,9 @@ static void lpg_apply_freq(struct lpg_channel *chan) case LPG_SUBTYPE_PWM: val |= BIT(2); break; + case LPG_SUBTYPE_HI_RES_PWM: + val |= FIELD_PREP(PWM_SIZE_HI_RES_MASK, chan->pwm_resolution_sel); + break; case LPG_SUBTYPE_LPG_LITE: default: val |= BIT(4); @@ -670,7 +722,7 @@ static int lpg_blink_set(struct lpg_led *led, triled_set(lpg, triled_mask, triled_mask); chan = led->channels[0]; - duty = div_u64(chan->pwm_value * chan->period, LPG_RESOLUTION); + duty = div_u64(chan->pwm_value * chan->period, LPG_RESOLUTION_9BIT); *delay_on = div_u64(duty, NSEC_PER_MSEC); *delay_off = div_u64(chan->period - duty, NSEC_PER_MSEC); @@ -977,6 +1029,7 @@ static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, { struct lpg *lpg = container_of(chip, struct lpg, pwm); struct lpg_channel *chan = &lpg->channels[pwm->hwpwm]; + unsigned int resolution; unsigned int pre_div; unsigned int refclk; unsigned int val; @@ -988,7 +1041,14 @@ static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, if (ret) return ret; - refclk = lpg_clk_rates[val & PWM_CLK_SELECT_MASK]; + if (chan->subtype == LPG_SUBTYPE_HI_RES_PWM) { + refclk = lpg_clk_rates_hi_res[FIELD_GET(PWM_CLK_SELECT_HI_RES_MASK, val)]; + resolution = lpg_pwm_resolution_hi_res[FIELD_GET(PWM_SIZE_HI_RES_MASK, val)]; + } else { + refclk = lpg_clk_rates[FIELD_GET(PWM_CLK_SELECT_MASK, val)]; + resolution = 9; + } + if (refclk) { ret = regmap_read(lpg->map, chan->base + LPG_PREDIV_CLK_REG, &val); if (ret) @@ -1001,7 +1061,8 @@ static int lpg_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm, if (ret) return ret; - state->period = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * LPG_RESOLUTION * pre_div * (1 << m), refclk); + state->period = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * (1 << resolution) * + pre_div * (1 << m), refclk); state->duty_cycle = DIV_ROUND_UP_ULL((u64)NSEC_PER_SEC * pwm_value * pre_div * (1 << m), refclk); } else { state->period = 0; @@ -1149,7 +1210,7 @@ static int lpg_add_led(struct lpg *lpg, struct device_node *np) } cdev->default_trigger = of_get_property(np, "linux,default-trigger", NULL); - cdev->max_brightness = LPG_RESOLUTION - 1; + cdev->max_brightness = LPG_RESOLUTION_9BIT - 1; if (!of_property_read_string(np, "default-state", &state) && !strcmp(state, "on")) -- GitLab From 7fec65155494fb9817adbd584f813a3faec33797 Mon Sep 17 00:00:00 2001 From: Anjelique Melendez Date: Fri, 7 Apr 2023 15:38:49 -0700 Subject: [PATCH 3540/5631] leds: rgb: leds-qcom-lpg: Add support for PMK8550 PWM Add support for pmk8550 compatible and lpg_data. Signed-off-by: Anjelique Melendez Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230407223849.17623-4-quic_amelende@quicinc.com --- drivers/leds/rgb/leds-qcom-lpg.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c index 373bcf8ebb52..55a037234df1 100644 --- a/drivers/leds/rgb/leds-qcom-lpg.c +++ b/drivers/leds/rgb/leds-qcom-lpg.c @@ -1490,6 +1490,14 @@ static const struct lpg_data pm8350c_pwm_data = { }, }; +static const struct lpg_data pmk8550_pwm_data = { + .num_channels = 2, + .channels = (const struct lpg_channel_data[]) { + { .base = 0xe800 }, + { .base = 0xe900 }, + }, +}; + static const struct of_device_id lpg_of_table[] = { { .compatible = "qcom,pm8150b-lpg", .data = &pm8150b_lpg_data }, { .compatible = "qcom,pm8150l-lpg", .data = &pm8150l_lpg_data }, @@ -1500,6 +1508,7 @@ static const struct of_device_id lpg_of_table[] = { { .compatible = "qcom,pmi8994-lpg", .data = &pmi8994_lpg_data }, { .compatible = "qcom,pmi8998-lpg", .data = &pmi8998_lpg_data }, { .compatible = "qcom,pmc8180c-lpg", .data = &pm8150l_lpg_data }, + { .compatible = "qcom,pmk8550-pwm", .data = &pmk8550_pwm_data }, {} }; MODULE_DEVICE_TABLE(of, lpg_of_table); -- GitLab From edd4cab2d492daa5e45bd45e44084a2b9880f224 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 19 Apr 2023 20:04:30 -0700 Subject: [PATCH 3541/5631] perf test: Fix maps use after put Fix a use after put reference count issue. maps is copied from leader, but the leader is put on line 79 and then maps is used to read the reference count below - so a use after put, with the put of maps happening within thread__put. Fix by reversing the order of puts so that the leader is put last. To explain the reference count checker, I wrote this up as a little example here: https://perf.wiki.kernel.org/index.php/Reference_Count_Checking Note, the bug was introduced by the committer and wasn't present in the original reference count patch set. Committer notes: Yes, the bug predated your patch and is detected by the reference count checking you contributed. This was just part of splitting up your series into smaller chunks, in this case either we fix the problem detected while developing this reference counting infrastructure before the patch introducing REFCNT_CHECKING or fix it later after the merged infrastructure, when built with EXTRA_CFLAGS="-DREFCNT_CHECKING=1" detects it when running 'perf test', which is what this patch does. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lore.kernel.org/lkml/20230420030430.489243-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/thread-maps-share.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index 75ce8aedfc78..858e725318a9 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -76,16 +76,16 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(other_maps) == RC_CHK_ACCESS(other_leader->maps)); /* release thread group */ - thread__put(leader); + thread__put(t3); TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 3); - thread__put(t1); + thread__put(t2); TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 2); - thread__put(t2); + thread__put(t1); TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 1); - thread__put(t3); + thread__put(leader); /* release other group */ thread__put(other_leader); -- GitLab From 254d5a59464eea1324353d84c0f614c413e8e54f Mon Sep 17 00:00:00 2001 From: Daniel Starke Date: Thu, 20 Apr 2023 10:50:09 +0200 Subject: [PATCH 3542/5631] tty: n_gsm: fix redundant assignment of gsm->encoding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The function gsmld_open() contains a redundant assignment of gsm->encoding. The same value of GSM_ADV_OPT is already assigned to it during the initialization of the struct in gsm_alloc_mux() a few lines earlier. Fix this by removing the redundant second assignment of gsm->encoding in gsmld_open(). Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Reviewed-by: Ilpo Järvinen Signed-off-by: Daniel Starke Link: https://lore.kernel.org/r/20230420085017.7314-1-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index b7e1369a035c..c42c8b89fd46 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3585,7 +3585,6 @@ static int gsmld_open(struct tty_struct *tty) tty->receive_room = 65536; /* Attach the initial passive connection */ - gsm->encoding = GSM_ADV_OPT; gsmld_attach_gsm(tty, gsm); /* The mux will not be activated yet, we wait for correct -- GitLab From 9f6ffd0da650f6ed264e124a3d6bb4e11a49f9f1 Mon Sep 17 00:00:00 2001 From: Wadim Egorov Date: Wed, 12 Apr 2023 16:05:51 +0200 Subject: [PATCH 3543/5631] dt-bindings: leds: Convert PCA9532 to dtschema Convert the PCA9532 LED Dimmer to dtschema. While at it, update the example to match recommended node names and the link to the product datasheet. Also add GPIO properties since the driver allows to use unused pins as GPIOs. Signed-off-by: Wadim Egorov Acked-by: Pavel Machek Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230412140552.451527-1-w.egorov@phytec.de --- .../devicetree/bindings/leds/leds-pca9532.txt | 49 ---------- .../devicetree/bindings/leds/nxp,pca953x.yaml | 90 +++++++++++++++++++ 2 files changed, 90 insertions(+), 49 deletions(-) delete mode 100644 Documentation/devicetree/bindings/leds/leds-pca9532.txt create mode 100644 Documentation/devicetree/bindings/leds/nxp,pca953x.yaml diff --git a/Documentation/devicetree/bindings/leds/leds-pca9532.txt b/Documentation/devicetree/bindings/leds/leds-pca9532.txt deleted file mode 100644 index f769c52e3643..000000000000 --- a/Documentation/devicetree/bindings/leds/leds-pca9532.txt +++ /dev/null @@ -1,49 +0,0 @@ -*NXP - pca9532 PWM LED Driver - -The PCA9532 family is SMBus I/O expander optimized for dimming LEDs. -The PWM support 256 steps. - -Required properties: - - compatible: - "nxp,pca9530" - "nxp,pca9531" - "nxp,pca9532" - "nxp,pca9533" - - reg - I2C slave address - -Each led is represented as a sub-node of the nxp,pca9530. - -Optional sub-node properties: - - label: see Documentation/devicetree/bindings/leds/common.txt - - type: Output configuration, see dt-bindings/leds/leds-pca9532.h (default NONE) - - linux,default-trigger: see Documentation/devicetree/bindings/leds/common.txt - - default-state: see Documentation/devicetree/bindings/leds/common.txt - This property is only valid for sub-nodes of type . - -Example: - #include - - leds: pca9530@60 { - compatible = "nxp,pca9530"; - reg = <0x60>; - - red-power { - label = "pca:red:power"; - type = ; - }; - green-power { - label = "pca:green:power"; - type = ; - }; - kernel-booting { - type = ; - default-state = "on"; - }; - sys-stat { - type = ; - default-state = "keep"; // don't touch, was set by U-Boot - }; - }; - -For more product information please see the link below: -http://nxp.com/documents/data_sheet/PCA9532.pdf diff --git a/Documentation/devicetree/bindings/leds/nxp,pca953x.yaml b/Documentation/devicetree/bindings/leds/nxp,pca953x.yaml new file mode 100644 index 000000000000..edf6f55df685 --- /dev/null +++ b/Documentation/devicetree/bindings/leds/nxp,pca953x.yaml @@ -0,0 +1,90 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/nxp,pca953x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP PCA9532 LED Dimmer + +maintainers: + - Riku Voipio + +description: | + The PCA9532 family is SMBus I/O expander optimized for dimming LEDs. + The PWM support 256 steps. + + For more product information please see the link below: + https://www.nxp.com/docs/en/data-sheet/PCA9532.pdf + +properties: + compatible: + enum: + - nxp,pca9530 + - nxp,pca9531 + - nxp,pca9532 + - nxp,pca9533 + + reg: + maxItems: 1 + + gpio-controller: true + + '#gpio-cells': + const: 2 + +patternProperties: + "^led-[0-9a-z]+$": + type: object + $ref: common.yaml# + unevaluatedProperties: false + + properties: + type: + description: | + Output configuration, see include/dt-bindings/leds/leds-pca9532.h + $ref: /schemas/types.yaml#/definitions/uint32 + default: 0 + minimum: 0 + maximum: 4 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + led-controller@62 { + compatible = "nxp,pca9533"; + reg = <0x62>; + + led-1 { + label = "pca:red:power"; + type = ; + }; + + led-2 { + label = "pca:green:power"; + type = ; + }; + + led-3 { + type = ; + default-state = "on"; + }; + + led-4 { + type = ; + default-state = "keep"; + }; + }; + }; + +... -- GitLab From f3ef9d668b8b1b0e3e91dd9ea532f9d60eb61704 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 15 Apr 2023 18:27:11 +0200 Subject: [PATCH 3544/5631] leds: pwm-multicolor: Simplify an error message dev_err_probe() already display the error code. There is no need to duplicate it explicitly in the error message. While at it, add a missing \n at the end of the message. Signed-off-by: Christophe JAILLET Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/07d35e221faaa380fd11cd4597e42354c8eb350c.1681576017.git.christophe.jaillet@wanadoo.fr --- drivers/leds/rgb/leds-pwm-multicolor.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/leds/rgb/leds-pwm-multicolor.c b/drivers/leds/rgb/leds-pwm-multicolor.c index da9d2218ae18..46cd062b8b24 100644 --- a/drivers/leds/rgb/leds-pwm-multicolor.c +++ b/drivers/leds/rgb/leds-pwm-multicolor.c @@ -158,8 +158,8 @@ static int led_pwm_mc_probe(struct platform_device *pdev) ret = led_pwm_mc_set(cdev, cdev->brightness); if (ret) return dev_err_probe(&pdev->dev, ret, - "failed to set led PWM value for %s: %d", - cdev->name, ret); + "failed to set led PWM value for %s\n", + cdev->name); platform_set_drvdata(pdev, priv); return 0; -- GitLab From 5c7e105cd156fc9adf5294a83623d7a40c15f9b9 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:14 +0200 Subject: [PATCH 3545/5631] tty: serial: simplify qcom_geni_serial_send_chunk_fifo() * use memcpy() instead of the loop (removes c variable) * use remaining parameter directly (removes chunk variable) The code is simpler and easier to follow. Cc: Andy Gross Cc: Bjorn Andersson Cc: Konrad Dybcio Cc: linux-arm-msm@vger.kernel.org Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093514.13055-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 1881dd5b3c4d..08dc3e2a729c 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -854,21 +854,19 @@ static void qcom_geni_serial_stop_tx(struct uart_port *uport) } static void qcom_geni_serial_send_chunk_fifo(struct uart_port *uport, - unsigned int chunk) + unsigned int remaining) { struct qcom_geni_serial_port *port = to_dev_port(uport); struct circ_buf *xmit = &uport->state->xmit; - unsigned int tx_bytes, c, remaining = chunk; + unsigned int tx_bytes; u8 buf[BYTES_PER_FIFO_WORD]; while (remaining) { memset(buf, 0, sizeof(buf)); tx_bytes = min(remaining, BYTES_PER_FIFO_WORD); - for (c = 0; c < tx_bytes ; c++) { - buf[c] = xmit->buf[xmit->tail]; - uart_xmit_advance(uport, 1); - } + memcpy(buf, &xmit->buf[xmit->tail], tx_bytes); + uart_xmit_advance(uport, tx_bytes); iowrite32_rep(uport->membase + SE_GENI_TX_FIFOn, buf, 1); -- GitLab From ee13ea33e066507a374a0d091034f1150e9d0c07 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:30 +0200 Subject: [PATCH 3546/5631] tty: synclink_gt: don't allocate and pass dummy flags In synclinc_gt, the flag_buf is allocated, zeroed and passed to ldisc's receive_buf(). It is never written to, so it serves as a dummy buffer. That's unneeded because all ldiscs accept NULL as flags. That NULL resolves to the TTY_NORMAL flag. So drop all this nonsense. Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093530.13133-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/synclink_gt.c | 18 +++++------------- 1 file changed, 5 insertions(+), 13 deletions(-) diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c index 543b3224dce9..16e469e581ec 100644 --- a/drivers/tty/synclink_gt.c +++ b/drivers/tty/synclink_gt.c @@ -287,7 +287,6 @@ struct slgt_info { unsigned char *tx_buf; int tx_count; - char *flag_buf; bool drop_rts_on_tx_done; struct _input_signal_events input_signal_events; @@ -3244,13 +3243,7 @@ static int alloc_tmp_rbuf(struct slgt_info *info) info->tmp_rbuf = kmalloc(info->max_frame_size + 5, GFP_KERNEL); if (info->tmp_rbuf == NULL) return -ENOMEM; - /* unused flag buffer to satisfy receive_buf calling interface */ - info->flag_buf = kzalloc(info->max_frame_size + 5, GFP_KERNEL); - if (!info->flag_buf) { - kfree(info->tmp_rbuf); - info->tmp_rbuf = NULL; - return -ENOMEM; - } + return 0; } @@ -3258,8 +3251,6 @@ static void free_tmp_rbuf(struct slgt_info *info) { kfree(info->tmp_rbuf); info->tmp_rbuf = NULL; - kfree(info->flag_buf); - info->flag_buf = NULL; } /* @@ -4657,7 +4648,8 @@ static bool rx_get_frame(struct slgt_info *info) hdlcdev_rx(info,info->tmp_rbuf, framesize); else #endif - ldisc_receive_buf(tty, info->tmp_rbuf, info->flag_buf, framesize); + ldisc_receive_buf(tty, info->tmp_rbuf, NULL, + framesize); } } free_rbufs(info, start, end); @@ -4691,8 +4683,8 @@ static bool rx_get_buf(struct slgt_info *info) DBGDATA(info, info->rbufs[i].buf, count, "rx"); DBGINFO(("rx_get_buf size=%d\n", count)); if (count) - ldisc_receive_buf(info->port.tty, info->rbufs[i].buf, - info->flag_buf, count); + ldisc_receive_buf(info->port.tty, info->rbufs[i].buf, NULL, + count); free_rbufs(info, i, i); return true; } -- GitLab From c6c01763f24c40ec1a5faeb260632fdf0824bb72 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 6 Apr 2023 21:57:50 +0100 Subject: [PATCH 3547/5631] serial: make SiFive serial drivers depend on ARCH_ symbols As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the use of such symbols on other architectures, convert the SiFive serial driver Kconfig entries from the SOC_ symbols to ARCH_ instead. Signed-off-by: Conor Dooley Link: https://lore.kernel.org/r/20230406-carnival-aspirate-fcf69a30078c@spud Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 39a0078f54f6..398e5aac2e77 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -951,7 +951,7 @@ config SERIAL_OMAP_CONSOLE config SERIAL_SIFIVE tristate "SiFive UART support" depends on OF - default SOC_SIFIVE || SOC_CANAAN + default ARCH_SIFIVE || ARCH_CANAAN select SERIAL_CORE help Select this option if you are building a kernel for a device that @@ -961,7 +961,7 @@ config SERIAL_SIFIVE config SERIAL_SIFIVE_CONSOLE bool "Console on SiFive UART" depends on SERIAL_SIFIVE=y - default SOC_SIFIVE || SOC_CANAAN + default ARCH_SIFIVE || ARCH_CANAAN select SERIAL_CORE_CONSOLE select SERIAL_EARLYCON help -- GitLab From 9e4f2a8004213339e9d837d891a59cc80e082966 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 12 Apr 2023 14:48:11 +0200 Subject: [PATCH 3548/5631] serial: fix TIOCSRS485 locking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The RS485 multipoint addressing support for some reason added a new ADDRB termios cflag which is (only!) updated from one of the RS485 ioctls. Make sure to take the termios rw semaphore for the right ioctl (i.e. set, not get). Fixes: ae50bb275283 ("serial: take termios_rwsem for ->rs485_config() & pass termios as param") Cc: stable@vger.kernel.org # 6.0 Cc: Ilpo Järvinen Reviewed-by: Ilpo Järvinen Signed-off-by: Johan Hovold Link: https://lore.kernel.org/r/20230412124811.11217-1-johan@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index afafbb7edb4a..59b62fa2e287 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1549,7 +1549,7 @@ uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) goto out; /* rs485_config requires more locking than others */ - if (cmd == TIOCGRS485) + if (cmd == TIOCSRS485) down_write(&tty->termios_rwsem); mutex_lock(&port->mutex); @@ -1592,7 +1592,7 @@ uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) } out_up: mutex_unlock(&port->mutex); - if (cmd == TIOCGRS485) + if (cmd == TIOCSRS485) up_write(&tty->termios_rwsem); out: return ret; -- GitLab From f73fd750552524b06b5d77ebfdd106ccc8fcac61 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Mon, 10 Apr 2023 14:55:55 -0500 Subject: [PATCH 3549/5631] tty: serial: fsl_lpuart: adjust buffer length to the intended size Based on the fls function definition provided below, we should not subtract 1 to obtain the correct buffer length: fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. Fixes: 5887ad43ee02 ("tty: serial: fsl_lpuart: Use cyclic DMA for Rx") Signed-off-by: Shenwei Wang Link: https://lore.kernel.org/r/20230410195555.1003900-1-shenwei.wang@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index 074bfed57fc9..aef9be3e73c1 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1296,7 +1296,7 @@ static inline int lpuart_start_rx_dma(struct lpuart_port *sport) * 10ms at any baud rate. */ sport->rx_dma_rng_buf_len = (DMA_RX_TIMEOUT * baud / bits / 1000) * 2; - sport->rx_dma_rng_buf_len = (1 << (fls(sport->rx_dma_rng_buf_len) - 1)); + sport->rx_dma_rng_buf_len = (1 << fls(sport->rx_dma_rng_buf_len)); if (sport->rx_dma_rng_buf_len < 16) sport->rx_dma_rng_buf_len = 16; -- GitLab From d57d56e4dddfb5c92cd81abf8922055bf0fb85a4 Mon Sep 17 00:00:00 2001 From: Sherry Sun Date: Fri, 14 Apr 2023 10:21:11 +0800 Subject: [PATCH 3550/5631] tty: serial: fsl_lpuart: use UARTMODIR register bits for lpuart32 platform MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For lpuart32 platforms, UARTMODIR register is used instead of UARTMODEM. So here should configure the corresponding UARTMODIR register bits to avoid confusion. Reviewed-by: Ilpo Järvinen Signed-off-by: Sherry Sun Link: https://lore.kernel.org/r/20230414022111.20896-1-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/fsl_lpuart.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index aef9be3e73c1..c91916e13648 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -1406,12 +1406,12 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio struct lpuart_port, port); unsigned long modem = lpuart32_read(&sport->port, UARTMODIR) - & ~(UARTMODEM_TXRTSPOL | UARTMODEM_TXRTSE); + & ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE); lpuart32_write(&sport->port, modem, UARTMODIR); if (rs485->flags & SER_RS485_ENABLED) { /* Enable auto RS-485 RTS mode */ - modem |= UARTMODEM_TXRTSE; + modem |= UARTMODIR_TXRTSE; /* * The hardware defaults to RTS logic HIGH while transfer. @@ -1420,9 +1420,9 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio * Note: UART is assumed to be active high. */ if (rs485->flags & SER_RS485_RTS_ON_SEND) - modem |= UARTMODEM_TXRTSPOL; + modem |= UARTMODIR_TXRTSPOL; else if (rs485->flags & SER_RS485_RTS_AFTER_SEND) - modem &= ~UARTMODEM_TXRTSPOL; + modem &= ~UARTMODIR_TXRTSPOL; } lpuart32_write(&sport->port, modem, UARTMODIR); -- GitLab From 0ba9e3a13c6adfa99e32b2576d20820ab10ad48a Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 14 Apr 2023 10:02:39 -0700 Subject: [PATCH 3551/5631] serial: 8250: Add missing wakeup event reporting An 8250 UART configured as a wake-up source would not have reported itself through sysfs as being the source of wake-up, correct that. Fixes: b3b708fa2780 ("wake up from a serial port") Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20230414170241.2016255-1-f.fainelli@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index dfbc501cf9d1..fe8d79c4ae95 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1932,6 +1933,7 @@ static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) int serial8250_handle_irq(struct uart_port *port, unsigned int iir) { struct uart_8250_port *up = up_to_u8250p(port); + struct tty_port *tport = &port->state->port; bool skip_rx = false; unsigned long flags; u16 status; @@ -1957,6 +1959,8 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { + if (irqd_is_wakeup_set(irq_get_irq_data(port->irq))) + pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } -- GitLab From 04e82793f068d2f0ffe62fcea03d007a8cdc16a7 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 18 Apr 2023 13:14:06 +0300 Subject: [PATCH 3552/5631] serial: 8250: Reinit port->pm on port specific driver unbind When we unbind a serial port hardware specific 8250 driver, the generic serial8250 driver takes over the port. After that we see an oops about 10 seconds later. This can produce the following at least on some TI SoCs: Unhandled fault: imprecise external abort (0x1406) Internal error: : 1406 [#1] SMP ARM Turns out that we may still have the serial port hardware specific driver port->pm in use, and serial8250_pm() tries to call it after the port specific driver is gone: serial8250_pm [8250_base] from uart_change_pm+0x54/0x8c [serial_base] uart_change_pm [serial_base] from uart_hangup+0x154/0x198 [serial_base] uart_hangup [serial_base] from __tty_hangup.part.0+0x328/0x37c __tty_hangup.part.0 from disassociate_ctty+0x154/0x20c disassociate_ctty from do_exit+0x744/0xaac do_exit from do_group_exit+0x40/0x8c do_group_exit from __wake_up_parent+0x0/0x1c Let's fix the issue by calling serial8250_set_defaults() in serial8250_unregister_port(). This will set the port back to using the serial8250 default functions, and sets the port->pm to point to serial8250_pm. Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20230418101407.12403-1-tony@atomide.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index ab63c308be0a..13bf535eedcd 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -1158,6 +1158,7 @@ void serial8250_unregister_port(int line) uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->capabilities = 0; + serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { -- GitLab From 63f4c34561718a349d321105adab028cbf212d57 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 19 Apr 2023 14:54:22 +0300 Subject: [PATCH 3553/5631] serial: core: Disable uart_start() on uart_remove_one_port() While rebinding a uart device in a loop I noticed we may see a tx related race on uart_remove_one_port(): uart_write from n_tty_write n_tty_write from file_tty_write.constprop.0 file_tty_write.constprop.0 from vfs_write vfs_write from ksys_write ksys_write from ret_fast_syscall Let's disallow tx on port->UPF_DEAD. This flag gets set before we start tearing down the port in uart_remove_one_port(). Signed-off-by: Tony Lindgren Link: https://lore.kernel.org/r/20230419115423.59957-1-tony@atomide.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 59b62fa2e287..54e82f476a2c 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -135,7 +135,7 @@ static void __uart_start(struct tty_struct *tty) struct uart_state *state = tty->driver_data; struct uart_port *port = state->uart_port; - if (port && !uart_tx_stopped(port)) + if (port && !(port->flags & UPF_DEAD) && !uart_tx_stopped(port)) port->ops->start_tx(port); } -- GitLab From 3f42b142ea1171967e40e10e4b0241c0d6d28d41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jan=20Kundr=C3=A1t?= Date: Wed, 5 Apr 2023 22:14:23 +0200 Subject: [PATCH 3554/5631] serial: max310x: fix IO data corruption in batched operations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After upgrading from 5.16 to 6.1, our board with a MAX14830 started producing lots of garbage data over UART. Bisection pointed out commit 285e76fc049c as the culprit. That patch tried to replace hand-written code which I added in 2b4bac48c1084 ("serial: max310x: Use batched reads when reasonably safe") with the generic regmap infrastructure for batched operations. Unfortunately, the `regmap_raw_read` and `regmap_raw_write` which were used are actually functions which perform IO over *multiple* registers. That's not what is needed for accessing these Tx/Rx FIFOs; the appropriate functions are the `_noinc_` versions, not the `_raw_` ones. Fix this regression by using `regmap_noinc_read()` and `regmap_noinc_write()` along with the necessary `regmap_config` setup; with this patch in place, our board communicates happily again. Since our board uses SPI for talking to this chip, the I2C part is completely untested. Fixes: 285e76fc049c ("serial: max310x: use regmap methods for SPI batch operations") Cc: stable@vger.kernel.org Reviewed-by: Andy Shevchenko Signed-off-by: Jan Kundrát Link: https://lore.kernel.org/r/79db8e82aadb0e174bc82b9996423c3503c8fb37.1680732084.git.jan.kundrat@cesnet.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/max310x.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c index e9cacfe7e032..9fee722058f4 100644 --- a/drivers/tty/serial/max310x.c +++ b/drivers/tty/serial/max310x.c @@ -525,6 +525,11 @@ static bool max310x_reg_precious(struct device *dev, unsigned int reg) return false; } +static bool max310x_reg_noinc(struct device *dev, unsigned int reg) +{ + return reg == MAX310X_RHR_REG; +} + static int max310x_set_baud(struct uart_port *port, int baud) { unsigned int mode = 0, div = 0, frac = 0, c = 0, F = 0; @@ -651,14 +656,14 @@ static void max310x_batch_write(struct uart_port *port, u8 *txbuf, unsigned int { struct max310x_one *one = to_max310x_port(port); - regmap_raw_write(one->regmap, MAX310X_THR_REG, txbuf, len); + regmap_noinc_write(one->regmap, MAX310X_THR_REG, txbuf, len); } static void max310x_batch_read(struct uart_port *port, u8 *rxbuf, unsigned int len) { struct max310x_one *one = to_max310x_port(port); - regmap_raw_read(one->regmap, MAX310X_RHR_REG, rxbuf, len); + regmap_noinc_read(one->regmap, MAX310X_RHR_REG, rxbuf, len); } static void max310x_handle_rx(struct uart_port *port, unsigned int rxlen) @@ -1468,6 +1473,10 @@ static struct regmap_config regcfg = { .writeable_reg = max310x_reg_writeable, .volatile_reg = max310x_reg_volatile, .precious_reg = max310x_reg_precious, + .writeable_noinc_reg = max310x_reg_noinc, + .readable_noinc_reg = max310x_reg_noinc, + .max_raw_read = MAX310X_FIFO_SIZE, + .max_raw_write = MAX310X_FIFO_SIZE, }; #ifdef CONFIG_SPI_MASTER @@ -1553,6 +1562,10 @@ static struct regmap_config regcfg_i2c = { .volatile_reg = max310x_reg_volatile, .precious_reg = max310x_reg_precious, .max_register = MAX310X_I2C_REVID_EXTREG, + .writeable_noinc_reg = max310x_reg_noinc, + .readable_noinc_reg = max310x_reg_noinc, + .max_raw_read = MAX310X_FIFO_SIZE, + .max_raw_write = MAX310X_FIFO_SIZE, }; static const struct max310x_if_cfg max310x_i2c_if_cfg = { -- GitLab From 8749061be196b41a874d71c073c03171bf2741b2 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 12 Apr 2023 15:50:49 +0100 Subject: [PATCH 3555/5631] tty: serial: sh-sci: Add RZ/G2L SCIFA DMA tx support SCIFA IP on RZ/G2L SoC has the same signal for both interrupt and DMA transfer request. Setting DMARS register for DMA transfer makes the signal to work as a DMA transfer request signal and subsequent interrupt requests to the interrupt controller are masked. Similarly clearing DMARS register makes signal to work as interrupt signal and subsequent interrupt requests to the interrupt controller are unmasked. Add SCIFA DMA tx support for RZ/G2L alike SoCs by disabling TXI line interrupt and setting DMARS registers by DMA api for DMA transfer request. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230412145053.114847-2-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ca31e34afd83..f70d06a03864 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -588,12 +588,17 @@ static void sci_start_tx(struct uart_port *port) if (s->chan_tx && !uart_circ_empty(&s->port.state->xmit) && dma_submit_error(s->cookie_tx)) { + if (s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) + /* Switch irq from SCIF to DMA */ + disable_irq(s->irqs[SCIx_TXI_IRQ]); + s->cookie_tx = 0; schedule_work(&s->work_tx); } #endif - if (!s->chan_tx || port->type == PORT_SCIFA || port->type == PORT_SCIFB) { + if (!s->chan_tx || s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE || + port->type == PORT_SCIFA || port->type == PORT_SCIFB) { /* Set TIE (Transmit Interrupt Enable) bit in SCSCR */ ctrl = serial_port_in(port, SCSCR); serial_port_out(port, SCSCR, ctrl | SCSCR_TIE); @@ -1192,9 +1197,15 @@ static void sci_dma_tx_complete(void *arg) schedule_work(&s->work_tx); } else { s->cookie_tx = -EINVAL; - if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) { + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB || + s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) { u16 ctrl = serial_port_in(port, SCSCR); serial_port_out(port, SCSCR, ctrl & ~SCSCR_TIE); + if (s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) { + /* Switch irq from DMA to SCIF */ + dmaengine_pause(s->chan_tx_saved); + enable_irq(s->irqs[SCIx_TXI_IRQ]); + } } } -- GitLab From cf383d123869574d1de4304ed73771d3eb5a3d40 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 12 Apr 2023 15:50:50 +0100 Subject: [PATCH 3556/5631] tty: serial: sh-sci: Add RZ/G2L SCIFA DMA rx support SCIFA IP on RZ/G2L SoC has the same signal for both interrupt and DMA transfer request. Setting DMARS register for DMA transfer makes the signal to work as a DMA transfer request signal and subsequent interrupt requests to the interrupt controller are masked. Similarly clearing DMARS register makes signal to work as interrupt signal and subsequent interrupt requests to the interrupt controller are unmasked. Add SCIFA DMA rx support for RZ/G2L alike SoCs by disabling RXI line interrupt and setting DMARS registers by DMA api for DMA transfer request. Apart from this, we must set FIFO trigger to 1 for the expected behavior of the receive transmission. While at it replace the parameter irq to s->irqs[SCIx_RXI_IRQ] in disable_irq_nosync() to match enable_irq() in sci_dma_rx_reenable_irq(). Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230412145053.114847-3-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index f70d06a03864..15743c2f3d3d 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1277,9 +1277,13 @@ static void sci_dma_rx_reenable_irq(struct sci_port *s) /* Direct new serial port interrupts back to CPU */ scr = serial_port_in(port, SCSCR); - if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) { - scr &= ~SCSCR_RDRQE; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB || + s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) { enable_irq(s->irqs[SCIx_RXI_IRQ]); + if (s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) + scif_set_rtrg(port, s->rx_trigger); + else + scr &= ~SCSCR_RDRQE; } serial_port_out(port, SCSCR, scr | SCSCR_RIE); } @@ -1516,7 +1520,8 @@ static enum hrtimer_restart sci_dma_rx_timer_fn(struct hrtimer *t) tty_flip_buffer_push(&port->state->port); } - if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB || + s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) sci_dma_rx_submit(s, true); sci_dma_rx_reenable_irq(s); @@ -1640,7 +1645,8 @@ static void sci_request_dma(struct uart_port *port) s->chan_rx_saved = s->chan_rx = chan; - if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB || + s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) sci_dma_rx_submit(s, false); } } @@ -1693,9 +1699,15 @@ static irqreturn_t sci_rx_interrupt(int irq, void *ptr) u16 ssr = serial_port_in(port, SCxSR); /* Disable future Rx interrupts */ - if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) { - disable_irq_nosync(irq); - scr |= SCSCR_RDRQE; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB || + s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) { + disable_irq_nosync(s->irqs[SCIx_RXI_IRQ]); + if (s->cfg->regtype == SCIx_RZ_SCIFA_REGTYPE) { + scif_set_rtrg(port, 1); + scr |= SCSCR_RIE; + } else { + scr |= SCSCR_RDRQE; + } } else { if (sci_dma_rx_submit(s, false) < 0) goto handle_pio; -- GitLab From 1707ce2d1e4d701db28ba2250d9d72dcf762babc Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 12 Apr 2023 15:50:51 +0100 Subject: [PATCH 3557/5631] tty: serial: sh-sci: Fix TE setting on SCI IP As per the RZ/G2L users hardware manual (Rev.1.20 Sep, 2022), section 23.3.7 Serial Data Transmission (Asynchronous Mode) it is mentioned that the TE (transmit enable) must be set after setting TIE (transmit interrupt enable) or these 2 bits are set to 1 simultaneously by a single instruction. So set these 2 bits in single instruction. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230412145053.114847-4-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 15743c2f3d3d..32f5c1f7d697 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -601,6 +601,15 @@ static void sci_start_tx(struct uart_port *port) port->type == PORT_SCIFA || port->type == PORT_SCIFB) { /* Set TIE (Transmit Interrupt Enable) bit in SCSCR */ ctrl = serial_port_in(port, SCSCR); + + /* + * For SCI, TE (transmit enable) must be set after setting TIE + * (transmit interrupt enable) or in the same instruction to start + * the transmit process. + */ + if (port->type == PORT_SCI) + ctrl |= SCSCR_TE; + serial_port_out(port, SCSCR, ctrl | SCSCR_TIE); } } @@ -2600,8 +2609,14 @@ static void sci_set_termios(struct uart_port *port, struct ktermios *termios, sci_set_mctrl(port, port->mctrl); } - scr_val |= SCSCR_RE | SCSCR_TE | - (s->cfg->scscr & ~(SCSCR_CKE1 | SCSCR_CKE0)); + /* + * For SCI, TE (transmit enable) must be set after setting TIE + * (transmit interrupt enable) or in the same instruction to + * start the transmitting process. So skip setting TE here for SCI. + */ + if (port->type != PORT_SCI) + scr_val |= SCSCR_TE; + scr_val |= SCSCR_RE | (s->cfg->scscr & ~(SCSCR_CKE1 | SCSCR_CKE0)); serial_port_out(port, SCSCR, scr_val | s->hscif_tot); if ((srr + 1 == 5) && (port->type == PORT_SCIFA || port->type == PORT_SCIFB)) { -- GitLab From d61ae331d6f35183b38e0c992bc01bf15d8591c3 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 12 Apr 2023 15:50:52 +0100 Subject: [PATCH 3558/5631] tty: serial: sh-sci: Add support for tx end interrupt handling As per the RZ/G2L users hardware manual (Rev.1.20 Sep, 2022), section 23.3.7 Serial Data Transmission (Asynchronous Mode), it is mentioned that, set the SCR.TIE bit to 0 and SCR.TEIE bit to 1, after the last data to be transmitted are written to the TDR. This will generate tx end interrupt and in the handler set SCR.TE and SCR.TEIE to 0. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230412145053.114847-5-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 31 ++++++++++++++++++++++++++++--- drivers/tty/serial/sh-sci.h | 3 +++ 2 files changed, 31 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 32f5c1f7d697..5c9ae69c0555 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -860,9 +860,16 @@ static void sci_transmit_chars(struct uart_port *port) if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); - if (uart_circ_empty(xmit)) - sci_stop_tx(port); + if (uart_circ_empty(xmit)) { + if (port->type == PORT_SCI) { + ctrl = serial_port_in(port, SCSCR); + ctrl &= ~SCSCR_TIE; + ctrl |= SCSCR_TEIE; + serial_port_out(port, SCSCR, ctrl); + } + sci_stop_tx(port); + } } static void sci_receive_chars(struct uart_port *port) @@ -1766,6 +1773,24 @@ static irqreturn_t sci_tx_interrupt(int irq, void *ptr) return IRQ_HANDLED; } +static irqreturn_t sci_tx_end_interrupt(int irq, void *ptr) +{ + struct uart_port *port = ptr; + unsigned long flags; + unsigned short ctrl; + + if (port->type != PORT_SCI) + return sci_tx_interrupt(irq, ptr); + + spin_lock_irqsave(&port->lock, flags); + ctrl = serial_port_in(port, SCSCR); + ctrl &= ~(SCSCR_TE | SCSCR_TEIE); + serial_port_out(port, SCSCR, ctrl); + spin_unlock_irqrestore(&port->lock, flags); + + return IRQ_HANDLED; +} + static irqreturn_t sci_br_interrupt(int irq, void *ptr) { struct uart_port *port = ptr; @@ -1902,7 +1927,7 @@ static const struct sci_irq_desc { [SCIx_TEI_IRQ] = { .desc = "tx end", - .handler = sci_tx_interrupt, + .handler = sci_tx_end_interrupt, }, /* diff --git a/drivers/tty/serial/sh-sci.h b/drivers/tty/serial/sh-sci.h index c0ae78632dda..0b65563c4e9e 100644 --- a/drivers/tty/serial/sh-sci.h +++ b/drivers/tty/serial/sh-sci.h @@ -59,6 +59,9 @@ enum { #define SCSMR_SRC_19 0x0600 /* Sampling rate 1/19 */ #define SCSMR_SRC_27 0x0700 /* Sampling rate 1/27 */ +/* Serial Control Register, SCI only bits */ +#define SCSCR_TEIE BIT(2) /* Transmit End Interrupt Enable */ + /* Serial Control Register, SCIFA/SCIFB only bits */ #define SCSCR_TDRQE BIT(15) /* Tx Data Transfer Request Enable */ #define SCSCR_RDRQE BIT(14) /* Rx Data Transfer Request Enable */ -- GitLab From f06c2a9000ebecbb461196e59ce063f742272902 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Wed, 12 Apr 2023 15:50:53 +0100 Subject: [PATCH 3559/5631] tty: serial: sh-sci: Fix end of transmission on SCI We need to set TE to "0" (i.e., disable serial transmission) to get the expected behavior of the end of serial transmission. Signed-off-by: Biju Das Link: https://lore.kernel.org/r/20230412145053.114847-6-biju.das.jz@bp.renesas.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 5c9ae69c0555..7c9457962a3d 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -847,6 +847,11 @@ static void sci_transmit_chars(struct uart_port *port) } else if (!uart_circ_empty(xmit) && !stopped) { c = xmit->buf[xmit->tail]; xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); + } else if (port->type == PORT_SCI && uart_circ_empty(xmit)) { + ctrl = serial_port_in(port, SCSCR); + ctrl &= ~SCSCR_TE; + serial_port_out(port, SCSCR, ctrl); + return; } else { break; } -- GitLab From 6b97370b2cc6ef75acb72d651ef57041c8f1ece9 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:56 +0200 Subject: [PATCH 3560/5631] tty: vt: reformat tioclinux() Reformat tioclinux() to what we are used to. That is: * format switch-case (one less indent level), * format comments (the same indent level), and * add a newline before return. Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093559.13200-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 167 ++++++++++++++++++++++---------------------- 1 file changed, 84 insertions(+), 83 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 3c2ea9c098f7..84a3f705c8bf 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3143,93 +3143,94 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) return -EFAULT; ret = 0; - switch (type) - { - case TIOCL_SETSEL: - ret = set_selection_user((struct tiocl_selection - __user *)(p+1), tty); - break; - case TIOCL_PASTESEL: - ret = paste_selection(tty); - break; - case TIOCL_UNBLANKSCREEN: - console_lock(); - unblank_screen(); - console_unlock(); - break; - case TIOCL_SELLOADLUT: - console_lock(); - ret = sel_loadlut(p); - console_unlock(); - break; - case TIOCL_GETSHIFTSTATE: - - /* - * Make it possible to react to Shift+Mousebutton. - * Note that 'shift_state' is an undocumented - * kernel-internal variable; programs not closely - * related to the kernel should not use this. - */ - data = vt_get_shift_state(); - ret = put_user(data, p); - break; - case TIOCL_GETMOUSEREPORTING: - console_lock(); /* May be overkill */ - data = mouse_reporting(); - console_unlock(); - ret = put_user(data, p); - break; - case TIOCL_SETVESABLANK: - console_lock(); - ret = set_vesa_blanking(p); - console_unlock(); - break; - case TIOCL_GETKMSGREDIRECT: - data = vt_get_kmsg_redirect(); - ret = put_user(data, p); - break; - case TIOCL_SETKMSGREDIRECT: - if (!capable(CAP_SYS_ADMIN)) { - ret = -EPERM; - } else { - if (get_user(data, p+1)) - ret = -EFAULT; - else - vt_kmsg_redirect(data); - } - break; - case TIOCL_GETFGCONSOLE: - /* No locking needed as this is a transiently - correct return anyway if the caller hasn't - disabled switching */ - ret = fg_console; - break; - case TIOCL_SCROLLCONSOLE: - if (get_user(lines, (s32 __user *)(p+4))) { + switch (type) { + case TIOCL_SETSEL: + ret = set_selection_user((struct tiocl_selection + __user *)(p+1), tty); + break; + case TIOCL_PASTESEL: + ret = paste_selection(tty); + break; + case TIOCL_UNBLANKSCREEN: + console_lock(); + unblank_screen(); + console_unlock(); + break; + case TIOCL_SELLOADLUT: + console_lock(); + ret = sel_loadlut(p); + console_unlock(); + break; + case TIOCL_GETSHIFTSTATE: + /* + * Make it possible to react to Shift+Mousebutton. Note that + * 'shift_state' is an undocumented kernel-internal variable; + * programs not closely related to the kernel should not use + * this. + */ + data = vt_get_shift_state(); + ret = put_user(data, p); + break; + case TIOCL_GETMOUSEREPORTING: + console_lock(); /* May be overkill */ + data = mouse_reporting(); + console_unlock(); + ret = put_user(data, p); + break; + case TIOCL_SETVESABLANK: + console_lock(); + ret = set_vesa_blanking(p); + console_unlock(); + break; + case TIOCL_GETKMSGREDIRECT: + data = vt_get_kmsg_redirect(); + ret = put_user(data, p); + break; + case TIOCL_SETKMSGREDIRECT: + if (!capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + } else { + if (get_user(data, p+1)) ret = -EFAULT; - } else { - /* Need the console lock here. Note that lots - of other calls need fixing before the lock - is actually useful ! */ - console_lock(); - scrollfront(vc_cons[fg_console].d, lines); - console_unlock(); - ret = 0; - } - break; - case TIOCL_BLANKSCREEN: /* until explicitly unblanked, not only poked */ + else + vt_kmsg_redirect(data); + } + break; + case TIOCL_GETFGCONSOLE: + /* + * No locking needed as this is a transiently correct return + * anyway if the caller hasn't disabled switching. + */ + ret = fg_console; + break; + case TIOCL_SCROLLCONSOLE: + if (get_user(lines, (s32 __user *)(p+4))) { + ret = -EFAULT; + } else { + /* + * Needs the console lock here. Note that lots of other + * calls need fixing before the lock is actually useful! + */ console_lock(); - ignore_poke = 1; - do_blank_screen(0); + scrollfront(vc_cons[fg_console].d, lines); console_unlock(); - break; - case TIOCL_BLANKEDSCREEN: - ret = console_blanked; - break; - default: - ret = -EINVAL; - break; + ret = 0; + } + break; + case TIOCL_BLANKSCREEN: /* until explicitly unblanked, not only poked */ + console_lock(); + ignore_poke = 1; + do_blank_screen(0); + console_unlock(); + break; + case TIOCL_BLANKEDSCREEN: + ret = console_blanked; + break; + default: + ret = -EINVAL; + break; } + return ret; } -- GitLab From 71ca6e4bf44f9a737f11e3f169430f81e9febd7b Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:57 +0200 Subject: [PATCH 3561/5631] tty: vt: simplify some cases in tioclinux() There is no need to set "ret" variable and break. We can simply return from the cases. This makes the code much easier to follow, as many else branches are redundant. Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093559.13200-2-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 62 +++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 36 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 84a3f705c8bf..a1564678b659 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3145,12 +3145,10 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) switch (type) { case TIOCL_SETSEL: - ret = set_selection_user((struct tiocl_selection + return set_selection_user((struct tiocl_selection __user *)(p+1), tty); - break; case TIOCL_PASTESEL: - ret = paste_selection(tty); - break; + return paste_selection(tty); case TIOCL_UNBLANKSCREEN: console_lock(); unblank_screen(); @@ -3169,14 +3167,12 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) * this. */ data = vt_get_shift_state(); - ret = put_user(data, p); - break; + return put_user(data, p); case TIOCL_GETMOUSEREPORTING: console_lock(); /* May be overkill */ data = mouse_reporting(); console_unlock(); - ret = put_user(data, p); - break; + return put_user(data, p); case TIOCL_SETVESABLANK: console_lock(); ret = set_vesa_blanking(p); @@ -3184,38 +3180,34 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) break; case TIOCL_GETKMSGREDIRECT: data = vt_get_kmsg_redirect(); - ret = put_user(data, p); - break; + return put_user(data, p); case TIOCL_SETKMSGREDIRECT: - if (!capable(CAP_SYS_ADMIN)) { - ret = -EPERM; - } else { - if (get_user(data, p+1)) - ret = -EFAULT; - else - vt_kmsg_redirect(data); - } + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(data, p+1)) + return -EFAULT; + + vt_kmsg_redirect(data); + break; case TIOCL_GETFGCONSOLE: /* * No locking needed as this is a transiently correct return * anyway if the caller hasn't disabled switching. */ - ret = fg_console; - break; + return fg_console; case TIOCL_SCROLLCONSOLE: - if (get_user(lines, (s32 __user *)(p+4))) { - ret = -EFAULT; - } else { - /* - * Needs the console lock here. Note that lots of other - * calls need fixing before the lock is actually useful! - */ - console_lock(); - scrollfront(vc_cons[fg_console].d, lines); - console_unlock(); - ret = 0; - } + if (get_user(lines, (s32 __user *)(p+4))) + return -EFAULT; + + /* + * Needs the console lock here. Note that lots of other calls + * need fixing before the lock is actually useful! + */ + console_lock(); + scrollfront(vc_cons[fg_console].d, lines); + console_unlock(); break; case TIOCL_BLANKSCREEN: /* until explicitly unblanked, not only poked */ console_lock(); @@ -3224,11 +3216,9 @@ int tioclinux(struct tty_struct *tty, unsigned long arg) console_unlock(); break; case TIOCL_BLANKEDSCREEN: - ret = console_blanked; - break; + return console_blanked; default: - ret = -EINVAL; - break; + return -EINVAL; } return ret; -- GitLab From 921234d78339b9ee67c2da4dc78aa6ecd47d76e1 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:58 +0200 Subject: [PATCH 3562/5631] tty: vt: distribute EXPORT_SYMBOL() There is a list of EXPORT_SYMBOL()s at the end of the file. Put them all by their definition. This is how we usually do that. give_up_console() lost its VT_SINGLE_DRIVER local ifndef protection as that whole code is under this check. Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093559.13200-3-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index a1564678b659..8582ec0b1499 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -135,6 +135,7 @@ const struct consw *conswitchp; #define DEFAULT_CURSOR_BLINK_MS 200 struct vc vc_cons [MAX_NR_CONSOLES]; +EXPORT_SYMBOL(vc_cons); #ifndef VT_SINGLE_DRIVER static const struct consw *con_driver_map[MAX_NR_CONSOLES]; @@ -162,6 +163,7 @@ int default_utf8 = true; module_param(default_utf8, int, S_IRUGO | S_IWUSR); int global_cursor_default = -1; module_param(global_cursor_default, int, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL(global_cursor_default); static int cur_default = CUR_UNDERLINE; module_param(cur_default, int, S_IRUGO | S_IWUSR); @@ -174,6 +176,7 @@ static int ignore_poke; int do_poke_blanked_console; int console_blanked; +EXPORT_SYMBOL(console_blanked); static int vesa_blank_mode; /* 0:none 1:suspendV 2:suspendH 3:powerdown */ static int vesa_off_interval; @@ -190,8 +193,10 @@ static DECLARE_WORK(con_driver_unregister_work, con_driver_unregister_callback); * saved_* variants are for save/restore around kernel debugger enter/leave */ int fg_console; +EXPORT_SYMBOL(fg_console); int last_console; int want_console = -1; + static int saved_fg_console; static int saved_last_console; static int saved_want_console; @@ -223,6 +228,7 @@ static int scrollback_delta; * the console on our behalf. */ int (*console_blank_hook)(int); +EXPORT_SYMBOL(console_blank_hook); static DEFINE_TIMER(console_timer, blank_screen_t); static int blank_state; @@ -639,6 +645,7 @@ void update_region(struct vc_data *vc, unsigned long start, int count) set_cursor(vc); } } +EXPORT_SYMBOL(update_region); /* Structure of attributes is hardware-dependent */ @@ -984,6 +991,7 @@ void redraw_screen(struct vc_data *vc, int is_switch) notify_update(vc); } } +EXPORT_SYMBOL(redraw_screen); /* * Allocation, freeing and resizing of VTs. @@ -1305,6 +1313,7 @@ int vc_resize(struct vc_data *vc, unsigned int cols, unsigned int rows) { return vc_do_resize(vc->port.tty, vc, cols, rows); } +EXPORT_SYMBOL(vc_resize); /** * vt_resize - resize a VT @@ -1368,6 +1377,7 @@ enum { EPecma = 0, EPdec, EPeq, EPgt, EPlt}; const unsigned char color_table[] = { 0, 4, 2, 6, 1, 5, 3, 7, 8,12,10,14, 9,13,11,15 }; +EXPORT_SYMBOL(color_table); /* the default colour table, for VGA+ colour systems */ unsigned char default_red[] = { @@ -1375,18 +1385,21 @@ unsigned char default_red[] = { 0x55, 0xff, 0x55, 0xff, 0x55, 0xff, 0x55, 0xff }; module_param_array(default_red, byte, NULL, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL(default_red); unsigned char default_grn[] = { 0x00, 0x00, 0xaa, 0x55, 0x00, 0x00, 0xaa, 0xaa, 0x55, 0x55, 0xff, 0xff, 0x55, 0x55, 0xff, 0xff }; module_param_array(default_grn, byte, NULL, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL(default_grn); unsigned char default_blu[] = { 0x00, 0x00, 0x00, 0x00, 0xaa, 0xaa, 0xaa, 0xaa, 0x55, 0x55, 0x55, 0x55, 0xff, 0xff, 0xff, 0xff }; module_param_array(default_blu, byte, NULL, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL(default_blu); /* * gotoxy() must verify all boundaries, because the arguments @@ -4227,6 +4240,7 @@ void give_up_console(const struct consw *csw) do_unregister_con_driver(csw); console_unlock(); } +EXPORT_SYMBOL(give_up_console); static int __init vtconsole_class_init(void) { @@ -4783,23 +4797,3 @@ void vc_scrolldelta_helper(struct vc_data *c, int lines, c->vc_visible_origin = ubase + (from + from_off) % wrap; } EXPORT_SYMBOL_GPL(vc_scrolldelta_helper); - -/* - * Visible symbols for modules - */ - -EXPORT_SYMBOL(color_table); -EXPORT_SYMBOL(default_red); -EXPORT_SYMBOL(default_grn); -EXPORT_SYMBOL(default_blu); -EXPORT_SYMBOL(update_region); -EXPORT_SYMBOL(redraw_screen); -EXPORT_SYMBOL(vc_resize); -EXPORT_SYMBOL(fg_console); -EXPORT_SYMBOL(console_blank_hook); -EXPORT_SYMBOL(console_blanked); -EXPORT_SYMBOL(vc_cons); -EXPORT_SYMBOL(global_cursor_default); -#ifndef VT_SINGLE_DRIVER -EXPORT_SYMBOL(give_up_console); -#endif -- GitLab From f91cf1a30255d81cf1d8992974ec0a9c0fd4a771 Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Thu, 20 Apr 2023 11:35:59 +0200 Subject: [PATCH 3563/5631] tty: vt: drop checks for undefined VT_SINGLE_DRIVER VT_SINGLE_DRIVER is defined nowhere. Remove its checks. These were added long time ago and never used. Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20230420093559.13200-4-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vt.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 8582ec0b1499..5c5ca74c03af 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -137,9 +137,7 @@ const struct consw *conswitchp; struct vc vc_cons [MAX_NR_CONSOLES]; EXPORT_SYMBOL(vc_cons); -#ifndef VT_SINGLE_DRIVER static const struct consw *con_driver_map[MAX_NR_CONSOLES]; -#endif static int con_open(struct tty_struct *, struct file *); static void vc_init(struct vc_data *vc, unsigned int rows, @@ -1008,10 +1006,10 @@ static void visual_init(struct vc_data *vc, int num, int init) if (vc->vc_sw) module_put(vc->vc_sw->owner); vc->vc_sw = conswitchp; -#ifndef VT_SINGLE_DRIVER + if (con_driver_map[num]) vc->vc_sw = con_driver_map[num]; -#endif + __module_get(vc->vc_sw->owner); vc->vc_num = num; vc->vc_display_fg = &master_display_fg; @@ -3575,8 +3573,6 @@ int __init vty_init(const struct file_operations *console_fops) return 0; } -#ifndef VT_SINGLE_DRIVER - static struct class *vtconsole_class; static int do_bind_con_driver(const struct consw *csw, int first, int last, @@ -4278,8 +4274,6 @@ static int __init vtconsole_class_init(void) } postcore_initcall(vtconsole_class_init); -#endif - /* * Screen blanking */ -- GitLab From 8020247877ebdf40416cb24bdfc47cba6c499412 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:19:37 +0200 Subject: [PATCH 3564/5631] staging: rtl8192e: Remove unchanged variable RegRfPsLevel Remove unchanged variable RegRfPsLevel and equations that have always the same result to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/49162b0041db33c6c43c4126839baed69c76cb89.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c | 9 +-------- drivers/staging/rtl8192e/rtllib.h | 1 - 2 files changed, 1 insertion(+), 9 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c index dd666701138e..4b0ebe96302e 100644 --- a/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c +++ b/drivers/staging/rtl8192e/rtl8192e/r8192E_phy.c @@ -1089,14 +1089,7 @@ static bool _rtl92e_set_rf_power_state(struct net_device *dev, if (i >= MAX_DOZE_WAITING_TIMES_9x) break; } - if (psc->RegRfPsLevel & RT_RF_OFF_LEVL_HALT_NIC && - !RT_IN_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC)) { - rtl92e_disable_nic(dev); - RT_SET_PS_LEVEL(psc, RT_RF_OFF_LEVL_HALT_NIC); - } else if (!(psc->RegRfPsLevel & - RT_RF_OFF_LEVL_HALT_NIC)) { - rtl92e_set_rf_off(dev); - } + rtl92e_set_rf_off(dev); break; default: bResult = false; diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index b1729d65f67f..1a0e7ae70ca6 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -1237,7 +1237,6 @@ struct rt_pwr_save_ctrl { u8 LPSAwakeIntvl; u32 CurPsLevel; - u32 RegRfPsLevel; }; #define RT_RF_CHANGE_SOURCE u32 -- GitLab From 88b81bddf1f3c2b4b23c687e27a5b6e0a6a63795 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:19:45 +0200 Subject: [PATCH 3565/5631] staging: rtl8192e: Remove unused function rtl92e_disable_nic Remove unused function rtl92e_disable_nic to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/5ce2ef58f66e25d7db7432c56c7b7c37a2b15fc1.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 16 ---------------- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 1 - 2 files changed, 17 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 45989a77a27c..ff650bd5441c 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -2301,22 +2301,6 @@ bool rtl92e_enable_nic(struct net_device *dev) return init_status; } -bool rtl92e_disable_nic(struct net_device *dev) -{ - struct r8192_priv *priv = rtllib_priv(dev); - u8 tmp_state = 0; - - priv->bdisable_nic = true; - tmp_state = priv->rtllib->state; - rtllib_softmac_stop_protocol(priv->rtllib, 0, false); - priv->rtllib->state = tmp_state; - _rtl92e_cancel_deferred_work(priv); - rtl92e_irq_disable(dev); - - rtl92e_stop_adapter(dev, false); - return true; -} - module_pci_driver(rtl8192_pci_driver); void rtl92e_check_rfctrl_gpio_timer(struct timer_list *t) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index b0aa76574738..51240cbde0d3 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -433,7 +433,6 @@ u8 rtl92e_rx_db_to_percent(s8 antpower); void rtl92e_copy_mpdu_stats(struct rtllib_rx_stats *psrc_stats, struct rtllib_rx_stats *ptarget_stats); bool rtl92e_enable_nic(struct net_device *dev); -bool rtl92e_disable_nic(struct net_device *dev); bool rtl92e_set_rf_state(struct net_device *dev, enum rt_rf_power_state state_to_set, -- GitLab From b0e60e96afa0719afddd483d9492a11851c2d9cf Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:19:52 +0200 Subject: [PATCH 3566/5631] staging: rtl8192e: Remove unused macro RT_SET_PS_LEVEL Remove unused macro RT_SET_PS_LEVEL to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0d397210830f77ad3231c3b4a0465ae89aacb962.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtllib.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index 1a0e7ae70ca6..6e665e866f1f 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -100,7 +100,6 @@ static inline void *netdev_priv_rsl(struct net_device *dev) ((psc->CurPsLevel & _PS_FLAG) ? true : false) #define RT_CLEAR_PS_LEVEL(psc, _PS_FLAG) \ (psc->CurPsLevel &= (~(_PS_FLAG))) -#define RT_SET_PS_LEVEL(psc, _PS_FLAG) (psc->CurPsLevel |= _PS_FLAG) /* defined for skb cb field */ /* At most 28 byte */ -- GitLab From bfc1bb7866f8c91ae829eadbc1bc7c81b5f6f623 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:19:58 +0200 Subject: [PATCH 3567/5631] staging: rtl8192e: Remove second initialization of bActuallySet Remove second initialization of bActuallySet to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/ebf51fbd56bad4f8fd7fb51fe031f376c3ab6d2c.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 93504d5a8578..7342ef591169 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -1539,8 +1539,6 @@ static void _rtl92e_dm_check_rf_ctrl_gpio(void *data) enum rt_rf_power_state rf_power_state_to_set; bool bActuallySet = false; - bActuallySet = false; - if ((priv->up_first_time == 1) || (priv->being_init_adapter)) return; -- GitLab From 93bf41cc8afbcc2988be881c4bb569fe9a8c36e1 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:20:06 +0200 Subject: [PATCH 3568/5631] staging: rtl8192e: Remove set to true while true of bfirst_after_down Remove set to true while true of bfirst_after_down to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/053ab341e80909e81867e42ec4c077e76b762051.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 7342ef591169..ed8b39d3c856 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -1542,10 +1542,8 @@ static void _rtl92e_dm_check_rf_ctrl_gpio(void *data) if ((priv->up_first_time == 1) || (priv->being_init_adapter)) return; - if (priv->bfirst_after_down) { - priv->bfirst_after_down = true; + if (priv->bfirst_after_down) return; - } tmp1byte = rtl92e_readb(dev, GPI); -- GitLab From dc8aaa4f327b17603165c0b6f8d40f297f5f94c0 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:20:12 +0200 Subject: [PATCH 3569/5631] staging: rtl8192e: Remove unchanged variable chan_forced Remove unchanged variable chan_forced and equations that have always the same result to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/3f218531a9d31c399d1351d3da7f9ca13d20df0c.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 3 --- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 2 -- 2 files changed, 5 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index ff650bd5441c..60fc358cfadf 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -249,9 +249,6 @@ static void _rtl92e_set_chan(struct net_device *dev, short ch) { struct r8192_priv *priv = rtllib_priv(dev); - if (priv->chan_forced) - return; - priv->chan = ch; if (priv->rf_set_chan) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 51240cbde0d3..0eca73e4540f 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -392,8 +392,6 @@ struct r8192_priv { bool reset_in_progress; bool force_reset; bool force_lps; - - bool chan_forced; }; extern const struct ethtool_ops rtl819x_ethtool_ops; -- GitLab From 548534d95b1dd7f9a51ac0ce06f1435be1e8ca33 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:20:19 +0200 Subject: [PATCH 3570/5631] staging: rtl8192e: Remove unchanged variable frame_sync_monitor Remove unchanged variable frame_sync_monitor and equations that have always the same result to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/0c4bdca5f5dbb93bb05c6b7f32136d4dfb3b0e4b.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 2 - drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 73 ++++++++------------ 2 files changed, 30 insertions(+), 45 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index 0eca73e4540f..c97e315a9091 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -382,8 +382,6 @@ struct r8192_priv { u32 continue_diff_count; bool bswitch_fsync; u8 framesync; - u8 frame_sync_monitor; - u32 reset_count; enum reset_type rst_progress; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index ed8b39d3c856..43e335ab0733 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -1826,7 +1826,6 @@ static void _rtl92e_dm_init_fsync(struct net_device *dev) priv->rtllib->fsync_firstdiff_ratethreshold = 100; priv->rtllib->fsync_seconddiff_ratethreshold = 200; priv->rtllib->fsync_state = Default_Fsync; - priv->frame_sync_monitor = 1; timer_setup(&priv->fsync_timer, _rtl92e_dm_fsync_timer_callback, 0); } @@ -2053,12 +2052,10 @@ static void _rtl92e_dm_check_fsync(struct net_device *dev) } } - if (priv->frame_sync_monitor) { - if (reg_c38_State != RegC38_Fsync_AP_BCM) { - rtl92e_writeb(dev, rOFDM0_RxDetector3, 0x95); + if (reg_c38_State != RegC38_Fsync_AP_BCM) { + rtl92e_writeb(dev, rOFDM0_RxDetector3, 0x95); - reg_c38_State = RegC38_Fsync_AP_BCM; - } + reg_c38_State = RegC38_Fsync_AP_BCM; } } else { switch (priv->rtllib->fsync_state) { @@ -2075,50 +2072,40 @@ static void _rtl92e_dm_check_fsync(struct net_device *dev) break; } - if (priv->frame_sync_monitor) { - if (priv->rtllib->state == RTLLIB_LINKED) { - if (priv->undecorated_smoothed_pwdb <= - RegC38_TH) { - if (reg_c38_State != - RegC38_NonFsync_Other_AP) { - rtl92e_writeb(dev, - rOFDM0_RxDetector3, - 0x90); - - reg_c38_State = - RegC38_NonFsync_Other_AP; - } - } else if (priv->undecorated_smoothed_pwdb >= - (RegC38_TH+5)) { - if (reg_c38_State) { - rtl92e_writeb(dev, - rOFDM0_RxDetector3, - priv->framesync); - reg_c38_State = RegC38_Default; - } + if (priv->rtllib->state == RTLLIB_LINKED) { + if (priv->undecorated_smoothed_pwdb <= + RegC38_TH) { + if (reg_c38_State != + RegC38_NonFsync_Other_AP) { + rtl92e_writeb(dev, + rOFDM0_RxDetector3, + 0x90); + + reg_c38_State = + RegC38_NonFsync_Other_AP; } - } else { + } else if (priv->undecorated_smoothed_pwdb >= + (RegC38_TH+5)) { if (reg_c38_State) { - rtl92e_writeb(dev, rOFDM0_RxDetector3, - priv->framesync); + rtl92e_writeb(dev, + rOFDM0_RxDetector3, + priv->framesync); reg_c38_State = RegC38_Default; } } + } else { + if (reg_c38_State) { + rtl92e_writeb(dev, rOFDM0_RxDetector3, + priv->framesync); + reg_c38_State = RegC38_Default; + } } } - if (priv->frame_sync_monitor) { - if (priv->reset_count != reset_cnt) { - rtl92e_writeb(dev, rOFDM0_RxDetector3, - priv->framesync); - reg_c38_State = RegC38_Default; - reset_cnt = priv->reset_count; - } - } else { - if (reg_c38_State) { - rtl92e_writeb(dev, rOFDM0_RxDetector3, - priv->framesync); - reg_c38_State = RegC38_Default; - } + if (priv->reset_count != reset_cnt) { + rtl92e_writeb(dev, rOFDM0_RxDetector3, + priv->framesync); + reg_c38_State = RegC38_Default; + reset_cnt = priv->reset_count; } } -- GitLab From 4de65f2b975fc0eb17629242db09e5895003edbe Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Sun, 16 Apr 2023 09:20:25 +0200 Subject: [PATCH 3571/5631] staging: rtl8192e: Remove unchanged variables bfsync_processing and more Remove unchanged variable bfsync_processing and rfc_txpowertrackingindex_real to shorten code. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/cb609f904d988febaa579526514586877b1dabf7.1681627603.git.philipp.g.hortmann@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 - drivers/staging/rtl8192e/rtl8192e/rtl_core.h | 2 -- drivers/staging/rtl8192e/rtl8192e/rtl_dm.c | 1 - 3 files changed, 4 deletions(-) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 60fc358cfadf..4cf84b5666a7 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -785,7 +785,6 @@ static void _rtl92e_init_priv_variable(struct net_device *dev) priv->rtllib->short_slot = 1; priv->promisc = (dev->flags & IFF_PROMISC) ? 1 : 0; priv->bcck_in_ch14 = false; - priv->bfsync_processing = false; priv->cck_present_attn = 0; priv->rfa_txpowertrackingindex = 0; priv->rfc_txpowertrackingindex = 0; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h index c97e315a9091..285dac32c074 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.h +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.h @@ -357,7 +357,6 @@ struct r8192_priv { u8 rfa_txpowertrackingindex_real; u8 rfa_txpowertracking_default; u8 rfc_txpowertrackingindex; - u8 rfc_txpowertrackingindex_real; bool btxpower_tracking; bool bcck_in_ch14; @@ -376,7 +375,6 @@ struct r8192_priv { bool bcurrent_turbo_EDCA; bool bis_cur_rdlstate; - bool bfsync_processing; u32 rate_record; u32 rate_count_diff_rec; u32 continue_diff_count; diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c index 43e335ab0733..56a8ec517c06 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_dm.c @@ -998,7 +998,6 @@ void rtl92e_dm_backup_state(struct net_device *dev) u32 bit_mask = bMaskByte0; priv->bswitch_fsync = false; - priv->bfsync_processing = false; if (dm_digtable.dig_algorithm == DIG_ALGO_BY_RSSI) return; -- GitLab From 3fac2397f562eb669ddc2f45867a253f3fc26184 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Tue, 18 Apr 2023 22:02:01 +0200 Subject: [PATCH 3572/5631] staging: rtl8192e: Fix W_DISABLE# does not work after stop/start When loading the driver for rtl8192e, the W_DISABLE# switch is working as intended. But when the WLAN is turned off in software and then turned on again the W_DISABLE# does not work anymore. Reason for this is that in the function _rtl92e_dm_check_rf_ctrl_gpio() the bfirst_after_down is checked and returned when true. bfirst_after_down is set true when switching the WLAN off in software. But it is not set to false again when WLAN is turned on again. Add bfirst_after_down = false in _rtl92e_sta_up to reset bit and fix above described bug. Fixes: 94a799425eee ("From: wlanfae [PATCH 1/8] rtl8192e: Import new version of driver from realtek") Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/20230418200201.GA17398@matrix-ESPRIMO-P710 Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rtl8192e/rtl8192e/rtl_core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index 4cf84b5666a7..27040d1e3230 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -645,6 +645,7 @@ static int _rtl92e_sta_up(struct net_device *dev, bool is_silent_reset) else netif_wake_queue(dev); + priv->bfirst_after_down = false; return 0; } -- GitLab From 2b3174c96696cde676393474f0e01d0d108462f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Tue, 11 Apr 2023 19:45:32 +0300 Subject: [PATCH 3573/5631] n_gsm: Use array_index_nospec() with index that comes from userspace MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dc.channel used for indexing comes directly from copy_from_user(). Use array_index_nospec() to mitigate speculative side-channel. Link: https://lore.kernel.org/linux-serial/64306d13.ONswMlyWlVKLGkKR%25lkp@intel.com/ Cc: stable Fixes: afe3154ba87e ("tty: n_gsm: add ioctl for DLC config via ldisc handle") Reported-by: kernel test robot Reviewed-by: Daniel Starke Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230411164532.64175-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_gsm.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index c42c8b89fd46..b411a26cc092 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include @@ -3717,8 +3718,8 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, struct gsm_config_ext ce; struct gsm_dlci_config dc; struct gsm_mux *gsm = tty->disc_data; + unsigned int base, addr; struct gsm_dlci *dlci; - unsigned int base; switch (cmd) { case GSMIOC_GETCONF: @@ -3747,9 +3748,10 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, return -EFAULT; if (dc.channel == 0 || dc.channel >= NUM_DLCI) return -EINVAL; - dlci = gsm->dlci[dc.channel]; + addr = array_index_nospec(dc.channel, NUM_DLCI); + dlci = gsm->dlci[addr]; if (!dlci) { - dlci = gsm_dlci_alloc(gsm, dc.channel); + dlci = gsm_dlci_alloc(gsm, addr); if (!dlci) return -ENOMEM; } @@ -3762,9 +3764,10 @@ static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, return -EFAULT; if (dc.channel == 0 || dc.channel >= NUM_DLCI) return -EINVAL; - dlci = gsm->dlci[dc.channel]; + addr = array_index_nospec(dc.channel, NUM_DLCI); + dlci = gsm->dlci[addr]; if (!dlci) { - dlci = gsm_dlci_alloc(gsm, dc.channel); + dlci = gsm_dlci_alloc(gsm, addr); if (!dlci) return -ENOMEM; } -- GitLab From 6f36ff32809aeaa7276d5f663d7adf9298a8bf5c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:38:56 +0200 Subject: [PATCH 3574/5631] MAINTAINERS: w1: add Krzysztof Kozlowski as maintainer Evgeniy wrote that he no longer takes patches for 1-Wire/W1 subsystem, so add Krzysztof Kozlowski to help reviewing and handling these. Link: https://lore.kernel.org/all/bdcf41d5-cd61-1e95-0b21-b8fe401644bd@ioremap.net/ Cc: Evgeniy Polyakov Cc: Arnd Bergmann Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415093856.41948-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index e314ae0614b7..78944f72b6fe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22436,7 +22436,7 @@ S: Orphan F: drivers/mmc/host/vub300.c W1 DALLAS'S 1-WIRE BUS -M: Evgeniy Polyakov +M: Krzysztof Kozlowski S: Maintained F: Documentation/devicetree/bindings/w1/ F: Documentation/w1/ -- GitLab From 22ab6c515d9602e5ddf41998ce5352e8887f4543 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Thu, 6 Apr 2023 12:31:36 +0200 Subject: [PATCH 3575/5631] dt-bindings: w1: Add DS2482/DS2484 I2C to 1-W bridges This adds a dedicated devicetree binding for the Maxim DS2482/DS2484 I2C to 1-W bridges, which can be extended later for further features (e.g. sleep mode control GPIO). Since one wire is a bus, child nodes needs to be allowed here. Reviewed-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/20230406103137.6092-2-stefan.wahren@chargebyte.com Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/w1/maxim,ds2482.yaml | 44 +++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 Documentation/devicetree/bindings/w1/maxim,ds2482.yaml diff --git a/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml new file mode 100644 index 000000000000..422becc6e1fa --- /dev/null +++ b/Documentation/devicetree/bindings/w1/maxim,ds2482.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/w1/maxim,ds2482.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Maxim One wire bus master controller + +maintainers: + - Stefan Wahren + +description: | + I2C to 1-wire bridges + + https://www.analog.com/media/en/technical-documentation/data-sheets/ds2482-100.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/DS2482-800.pdf + https://www.analog.com/media/en/technical-documentation/data-sheets/DS2484.pdf + +properties: + compatible: + enum: + - maxim,ds2482 + - maxim,ds2484 + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: + type: object + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + onewire@18 { + compatible = "maxim,ds2484"; + reg = <0x18>; + }; + }; -- GitLab From 58ecb03fc74a5ec4b8c8222c5b4bac572a264c47 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Thu, 6 Apr 2023 12:31:37 +0200 Subject: [PATCH 3576/5631] w1: ds2482: add i2c id for DS2484 The DS2484 is compatible to the DS2482-100, but also supports a pin-controlled power-saving sleep mode. Link: https://www.analog.com/media/en/technical-documentation/data-sheets/DS2484.pdf Signed-off-by: Stefan Wahren Link: https://lore.kernel.org/r/20230406103137.6092-3-stefan.wahren@chargebyte.com Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index 3d8b51316bef..1665fd28b964 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -544,6 +544,7 @@ static void ds2482_remove(struct i2c_client *client) */ static const struct i2c_device_id ds2482_id[] = { { "ds2482", 0 }, + { "ds2484", 0 }, { } }; MODULE_DEVICE_TABLE(i2c, ds2482_id); -- GitLab From 45c85d974f60aa519769c1933859e84aa96fa3f1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:49 +0200 Subject: [PATCH 3577/5631] w1: ds2408: drop kerneldoc annotation Drop kerneldoc annotation from comment which is not a kerneldoc to fix: w1_ds2408.c:210: warning: This comment starts with '/**', but isn't a kernel-doc comment Reviewed-by: Randy Dunlap Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/slaves/w1_ds2408.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c index ad102c577122..7fa911989193 100644 --- a/drivers/w1/slaves/w1_ds2408.c +++ b/drivers/w1/slaves/w1_ds2408.c @@ -206,7 +206,7 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj, } -/** +/* * Writing to the activity file resets the activity latches. */ static ssize_t activity_write(struct file *filp, struct kobject *kobj, -- GitLab From a866ce3b4fde3d0fb399cb5a81fd12cc3ff6e5c1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:50 +0200 Subject: [PATCH 3578/5631] w1: ds2433: correct kerneldoc annotation Correct kerneldoc comments (or drop annotation) to fix: w1_ds2433.c:46: warning: This comment starts with '/**', but isn't a kernel-doc comment. w1_ds2433.c:141: warning: This comment starts with '/**', but isn't a kernel-doc comment. Reviewed-by: Randy Dunlap Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-2-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/slaves/w1_ds2433.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index 0f72df15a024..6134ca2f37fe 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -42,7 +42,7 @@ struct w1_f23_data { u32 validcrc; }; -/** +/* * Check the file size bounds and adjusts count as needed. * This would not be needed if the file size didn't reset to 0 after a write. */ @@ -138,16 +138,17 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, } /** - * Writes to the scratchpad and reads it back for verification. + * w1_f23_write() - Writes to the scratchpad and reads it back for verification. + * @sl: The slave structure + * @addr: Address for the write + * @len: length must be <= (W1_PAGE_SIZE - (addr & W1_PAGE_MASK)) + * @data: The data to write + * * Then copies the scratchpad to EEPROM. * The data must be on one page. * The master must be locked. * - * @param sl The slave structure - * @param addr Address for the write - * @param len length must be <= (W1_PAGE_SIZE - (addr & W1_PAGE_MASK)) - * @param data The data to write - * @return 0=Success -1=failure + * Return: 0=Success, -1=failure */ static int w1_f23_write(struct w1_slave *sl, int addr, int len, const u8 *data) { -- GitLab From a2809664ca296ca89c6c8cc52ce728c1088d5af1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:51 +0200 Subject: [PATCH 3579/5631] w1: ds28e04: correct kerneldoc annotation Correct kerneldoc comments (or drop annotation) to fix: w1_ds28e04.c:57: warning: This comment starts with '/**', but isn't a kernel-doc comment. w1_ds28e04.c:149: warning: This comment starts with '/**', but isn't a kernel-doc comment. Reviewed-by: Randy Dunlap Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-3-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/slaves/w1_ds28e04.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/w1/slaves/w1_ds28e04.c b/drivers/w1/slaves/w1_ds28e04.c index 6cef6e2edb89..f54d6afd79c3 100644 --- a/drivers/w1/slaves/w1_ds28e04.c +++ b/drivers/w1/slaves/w1_ds28e04.c @@ -53,7 +53,7 @@ struct w1_f1C_data { u32 validcrc; }; -/** +/* * Check the file size bounds and adjusts count as needed. * This would not be needed if the file size didn't reset to 0 after a write. */ @@ -146,16 +146,17 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, } /** - * Writes to the scratchpad and reads it back for verification. + * w1_f1C_write() - Writes to the scratchpad and reads it back for verification. + * @sl: The slave structure + * @addr: Address for the write + * @len: length must be <= (W1_PAGE_SIZE - (addr & W1_PAGE_MASK)) + * @data: The data to write + * * Then copies the scratchpad to EEPROM. * The data must be on one page. * The master must be locked. * - * @param sl The slave structure - * @param addr Address for the write - * @param len length must be <= (W1_PAGE_SIZE - (addr & W1_PAGE_MASK)) - * @param data The data to write - * @return 0=Success -1=failure + * Return: 0=Success, -1=failure */ static int w1_f1C_write(struct w1_slave *sl, int addr, int len, const u8 *data) { -- GitLab From ad9c36be1f78f2990310cdcf902eba64cd2b2cf3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:52 +0200 Subject: [PATCH 3580/5631] w1: minor white-space and code style fixes Correct several coding convention violations around white-spaces: ERROR: spaces required around that '=' (ctx:VxV) WARNING: Missing a blank line after declarations ERROR: "foo* bar" should be "foo *bar" ERROR: "(foo*)" should be "(foo *)" WARNING: Block comments use * on subsequent lines WARNING: Block comments use a trailing */ on a separate line WARNING: please, no space before tabs WARNING: Missing a blank line after declarations ERROR: open brace '{' following struct go on the same line ERROR: that open brace { should be on the previous line Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-4-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 6 ++---- drivers/w1/masters/ds2490.c | 13 +++++++++---- drivers/w1/masters/matrox_w1.c | 3 +-- drivers/w1/slaves/w1_ds2406.c | 31 ++++++++++++++++--------------- drivers/w1/slaves/w1_ds2408.c | 10 +++++----- drivers/w1/slaves/w1_ds2413.c | 6 ++++-- drivers/w1/slaves/w1_ds2433.c | 2 +- drivers/w1/slaves/w1_ds2780.c | 1 + drivers/w1/slaves/w1_ds2781.c | 1 + drivers/w1/slaves/w1_ds28e04.c | 6 ++++-- drivers/w1/slaves/w1_ds28e17.c | 2 +- 11 files changed, 45 insertions(+), 36 deletions(-) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index 1665fd28b964..104bdf5c8064 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -78,10 +78,8 @@ MODULE_PARM_DESC(extra_config, "Extra Configuration settings 1=APU,2=PPM,3=SPU,8 * To set the channel, write the value at the index of the channel. * Read and compare against the corresponding value to verify the change. */ -static const u8 ds2482_chan_wr[8] = - { 0xF0, 0xE1, 0xD2, 0xC3, 0xB4, 0xA5, 0x96, 0x87 }; -static const u8 ds2482_chan_rd[8] = - { 0xB8, 0xB1, 0xAA, 0xA3, 0x9C, 0x95, 0x8E, 0x87 }; +static const u8 ds2482_chan_wr[8] = { 0xF0, 0xE1, 0xD2, 0xC3, 0xB4, 0xA5, 0x96, 0x87 }; +static const u8 ds2482_chan_rd[8] = { 0xB8, 0xB1, 0xAA, 0xA3, 0x9C, 0x95, 0x8E, 0x87 }; /* diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c index 0eb560fc0153..5f5b97e24700 100644 --- a/drivers/w1/masters/ds2490.c +++ b/drivers/w1/masters/ds2490.c @@ -304,6 +304,7 @@ static void ds_reset_device(struct ds_device *dev) if (dev->spu_sleep) { /* lower 4 bits are 0, see ds_set_pullup */ u8 del = dev->spu_sleep>>4; + if (ds_send_control(dev, COMM_SET_DURATION | COMM_IM, del)) dev_err(&dev->udev->dev, "%s: Error setting duration\n", __func__); @@ -731,7 +732,8 @@ static void ds9490r_search(void *data, struct w1_master *master, break; if (st.data_in_buffer_status) { - /* Bulk in can receive partial ids, but when it does + /* + * Bulk in can receive partial ids, but when it does * they fail crc and will be discarded anyway. * That has only been seen when status in buffer * is 0 and bulk is read anyway, so don't read @@ -743,8 +745,10 @@ static void ds9490r_search(void *data, struct w1_master *master, break; for (i = 0; i < err/8; ++i) { found_ids[found++] = buf[i]; - /* can't know if there will be a discrepancy - * value after until the next id */ + /* + * can't know if there will be a discrepancy + * value after until the next id + */ if (found == search_limit) { master->search_id = buf[i]; break; @@ -760,7 +764,8 @@ static void ds9490r_search(void *data, struct w1_master *master, if (found <= search_limit) { master->search_id = 0; } else if (!test_bit(W1_WARN_MAX_COUNT, &master->flags)) { - /* Only max_slave_count will be scanned in a search, + /* + * Only max_slave_count will be scanned in a search, * but it will start where it left off next search * until all ids are identified and then it will start * over. A continued search will report the previous diff --git a/drivers/w1/masters/matrox_w1.c b/drivers/w1/masters/matrox_w1.c index ee716c715710..94a1f3fa2dc3 100644 --- a/drivers/w1/masters/matrox_w1.c +++ b/drivers/w1/masters/matrox_w1.c @@ -39,8 +39,7 @@ #define MATROX_GET_DATA 0x2B #define MATROX_CURSOR_CTL 0x06 -struct matrox_device -{ +struct matrox_device { void __iomem *base_addr; void __iomem *port_index; void __iomem *port_data; diff --git a/drivers/w1/slaves/w1_ds2406.c b/drivers/w1/slaves/w1_ds2406.c index 6c269af73c80..3bb88b51fe2b 100644 --- a/drivers/w1/slaves/w1_ds2406.c +++ b/drivers/w1/slaves/w1_ds2406.c @@ -27,11 +27,11 @@ static ssize_t w1_f12_read_state( struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { - u8 w1_buf[6]={W1_F12_FUNC_READ_STATUS, 7, 0, 0, 0, 0}; + u8 w1_buf[6] = {W1_F12_FUNC_READ_STATUS, 7, 0, 0, 0, 0}; struct w1_slave *sl = kobj_to_w1_slave(kobj); - u16 crc=0; + u16 crc = 0; int i; - ssize_t rtnval=1; + ssize_t rtnval = 1; if (off != 0) return 0; @@ -47,12 +47,12 @@ static ssize_t w1_f12_read_state( w1_write_block(sl->master, w1_buf, 3); w1_read_block(sl->master, w1_buf+3, 3); - for (i=0; i<6; i++) - crc=crc16_byte(crc, w1_buf[i]); - if (crc==0xb001) /* good read? */ - *buf=((w1_buf[3]>>5)&3)|0x30; + for (i = 0; i < 6; i++) + crc = crc16_byte(crc, w1_buf[i]); + if (crc == 0xb001) /* good read? */ + *buf = ((w1_buf[3]>>5)&3)|0x30; else - rtnval=-EIO; + rtnval = -EIO; mutex_unlock(&sl->master->bus_mutex); @@ -65,10 +65,10 @@ static ssize_t w1_f12_write_output( char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); - u8 w1_buf[6]={W1_F12_FUNC_WRITE_STATUS, 7, 0, 0, 0, 0}; - u16 crc=0; + u8 w1_buf[6] = {W1_F12_FUNC_WRITE_STATUS, 7, 0, 0, 0, 0}; + u16 crc = 0; int i; - ssize_t rtnval=1; + ssize_t rtnval = 1; if (count != 1 || off != 0) return -EFAULT; @@ -83,12 +83,12 @@ static ssize_t w1_f12_write_output( w1_buf[3] = (((*buf)&3)<<5)|0x1F; w1_write_block(sl->master, w1_buf, 4); w1_read_block(sl->master, w1_buf+4, 2); - for (i=0; i<6; i++) - crc=crc16_byte(crc, w1_buf[i]); - if (crc==0xb001) /* good read? */ + for (i = 0; i < 6; i++) + crc = crc16_byte(crc, w1_buf[i]); + if (crc == 0xb001) /* good read? */ w1_write_8(sl->master, 0xFF); else - rtnval=-EIO; + rtnval = -EIO; mutex_unlock(&sl->master->bus_mutex); return rtnval; @@ -133,6 +133,7 @@ static int w1_f12_add_slave(struct w1_slave *sl) static void w1_f12_remove_slave(struct w1_slave *sl) { int i; + for (i = NB_SYSFS_BIN_FILES - 1; i >= 0; --i) sysfs_remove_bin_file(&sl->dev.kobj, &(w1_f12_sysfs_bin_files[i])); diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c index 7fa911989193..56f822a1dfdb 100644 --- a/drivers/w1/slaves/w1_ds2408.c +++ b/drivers/w1/slaves/w1_ds2408.c @@ -35,12 +35,12 @@ #define W1_F29_SUCCESS_CONFIRM_BYTE 0xAA -static int _read_reg(struct w1_slave *sl, u8 address, unsigned char* buf) +static int _read_reg(struct w1_slave *sl, u8 address, unsigned char *buf) { u8 wrbuf[3]; - dev_dbg(&sl->dev, - "Reading with slave: %p, reg addr: %0#4x, buff addr: %p", - sl, (unsigned int)address, buf); + + dev_dbg(&sl->dev, "Reading with slave: %p, reg addr: %0#4x, buff addr: %p", + sl, (unsigned int)address, buf); if (!buf) return -EINVAL; @@ -292,7 +292,7 @@ static int w1_f29_disable_test_mode(struct w1_slave *sl) { int res; u8 magic[10] = {0x96, }; - u64 rn = le64_to_cpu(*((u64*)&sl->reg_num)); + u64 rn = le64_to_cpu(*((u64 *)&sl->reg_num)); memcpy(&magic[1], &rn, 8); magic[9] = 0x3C; diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c index c8cfac555b48..bf4a72aae28a 100644 --- a/drivers/w1/slaves/w1_ds2413.c +++ b/drivers/w1/slaves/w1_ds2413.c @@ -99,8 +99,10 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj, if (w1_reset_select_slave(sl)) goto out; - /* according to the DS2413 datasheet the most significant 6 bits - should be set to "1"s, so do it now */ + /* + * according to the DS2413 datasheet the most significant 6 bits + * should be set to "1"s, so do it now + */ *buf = *buf | 0xFC; while (retries--) { diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index 6134ca2f37fe..23cd099d032b 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -115,7 +115,7 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, } memcpy(buf, &data->memory[off], count); -#else /* CONFIG_W1_SLAVE_DS2433_CRC */ +#else /* CONFIG_W1_SLAVE_DS2433_CRC */ /* read directly from the EEPROM */ if (w1_reset_select_slave(sl)) { diff --git a/drivers/w1/slaves/w1_ds2780.c b/drivers/w1/slaves/w1_ds2780.c index 9dcb5a54f7fc..3cde1bb1886b 100644 --- a/drivers/w1/slaves/w1_ds2780.c +++ b/drivers/w1/slaves/w1_ds2780.c @@ -91,6 +91,7 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); + return w1_ds2780_io(dev, buf, off, count, 0); } diff --git a/drivers/w1/slaves/w1_ds2781.c b/drivers/w1/slaves/w1_ds2781.c index 2cb7c020b607..e418484b4a49 100644 --- a/drivers/w1/slaves/w1_ds2781.c +++ b/drivers/w1/slaves/w1_ds2781.c @@ -88,6 +88,7 @@ static ssize_t w1_slave_read(struct file *filp, struct kobject *kobj, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); + return w1_ds2781_io(dev, buf, off, count, 0); } diff --git a/drivers/w1/slaves/w1_ds28e04.c b/drivers/w1/slaves/w1_ds28e04.c index f54d6afd79c3..2854b8b9e93f 100644 --- a/drivers/w1/slaves/w1_ds28e04.c +++ b/drivers/w1/slaves/w1_ds28e04.c @@ -198,8 +198,10 @@ static int w1_f1C_write(struct w1_slave *sl, int addr, int len, const u8 *data) wrbuf[3] = es; for (i = 0; i < sizeof(wrbuf); ++i) { - /* issue 10ms strong pullup (or delay) on the last byte - for writing the data from the scratchpad to EEPROM */ + /* + * issue 10ms strong pullup (or delay) on the last byte + * for writing the data from the scratchpad to EEPROM + */ if (w1_strong_pullup && i == sizeof(wrbuf)-1) w1_next_pullup(sl->master, tm); diff --git a/drivers/w1/slaves/w1_ds28e17.c b/drivers/w1/slaves/w1_ds28e17.c index aed10b72fc99..fdbaf77620ac 100644 --- a/drivers/w1/slaves/w1_ds28e17.c +++ b/drivers/w1/slaves/w1_ds28e17.c @@ -59,7 +59,7 @@ MODULE_PARM_DESC(stretch, "Default I2C stretch value to be set when a DS28E17 is /* * Maximum number of I2C bytes to transfer within one CRC16 protected onewire * command. - * */ + */ #define W1_F19_WRITE_DATA_LIMIT 255 /* Maximum number of I2C bytes to read with one onewire command. */ -- GitLab From 921e0f2fb09d8decfa8f19eae01f0b68e322363e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:54 +0200 Subject: [PATCH 3581/5631] w1: use octal for file permissions Improve code readability and checkpatch warnings: WARNING: Symbolic permissions 'S_IRUGO' are not preferred. Consider using octal permissions '0444'. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-6-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 2 +- drivers/w1/masters/omap_hdq.c | 2 +- drivers/w1/slaves/w1_ds2406.c | 4 ++-- drivers/w1/slaves/w1_ds2413.c | 2 +- drivers/w1/slaves/w1_ds2805.c | 2 +- drivers/w1/slaves/w1_ds28e17.c | 4 ++-- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index 104bdf5c8064..b1c76a96cc8d 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -36,7 +36,7 @@ MODULE_PARM_DESC(active_pullup, "Active pullup (apply to all buses): " \ /* extra configurations - e.g. 1WS */ static int extra_config; -module_param(extra_config, int, S_IRUGO | S_IWUSR); +module_param(extra_config, int, 0644); MODULE_PARM_DESC(extra_config, "Extra Configuration settings 1=APU,2=PPM,3=SPU,8=1WS"); /* diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index bf2ec59c1f9d..ae3e504cd543 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -48,7 +48,7 @@ static DECLARE_WAIT_QUEUE_HEAD(hdq_wait_queue); static int w1_id; -module_param(w1_id, int, S_IRUSR); +module_param(w1_id, int, 0400); MODULE_PARM_DESC(w1_id, "1-wire id for the slave detection in HDQ mode"); struct hdq_data { diff --git a/drivers/w1/slaves/w1_ds2406.c b/drivers/w1/slaves/w1_ds2406.c index 3bb88b51fe2b..2f5926859b8b 100644 --- a/drivers/w1/slaves/w1_ds2406.c +++ b/drivers/w1/slaves/w1_ds2406.c @@ -99,7 +99,7 @@ static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { { .attr = { .name = "state", - .mode = S_IRUGO, + .mode = 0444, }, .size = 1, .read = w1_f12_read_state, @@ -107,7 +107,7 @@ static struct bin_attribute w1_f12_sysfs_bin_files[NB_SYSFS_BIN_FILES] = { { .attr = { .name = "output", - .mode = S_IRUGO | S_IWUSR | S_IWGRP, + .mode = 0664, }, .size = 1, .write = w1_f12_write_output, diff --git a/drivers/w1/slaves/w1_ds2413.c b/drivers/w1/slaves/w1_ds2413.c index bf4a72aae28a..739009806467 100644 --- a/drivers/w1/slaves/w1_ds2413.c +++ b/drivers/w1/slaves/w1_ds2413.c @@ -128,7 +128,7 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj, return bytes_written; } -static BIN_ATTR(output, S_IRUGO | S_IWUSR | S_IWGRP, NULL, output_write, 1); +static BIN_ATTR(output, 0664, NULL, output_write, 1); static struct bin_attribute *w1_f3a_bin_attrs[] = { &bin_attr_state, diff --git a/drivers/w1/slaves/w1_ds2805.c b/drivers/w1/slaves/w1_ds2805.c index 6b5d12ba1b65..4c1a2c515317 100644 --- a/drivers/w1/slaves/w1_ds2805.c +++ b/drivers/w1/slaves/w1_ds2805.c @@ -264,7 +264,7 @@ static ssize_t w1_f0d_write_bin(struct file *filp, struct kobject *kobj, static struct bin_attribute w1_f0d_bin_attr = { .attr = { .name = "eeprom", - .mode = S_IRUGO | S_IWUSR, + .mode = 0644, }, .size = W1_F0D_EEPROM_SIZE, .read = w1_f0d_read_bin, diff --git a/drivers/w1/slaves/w1_ds28e17.c b/drivers/w1/slaves/w1_ds28e17.c index fdbaf77620ac..52261b54d842 100644 --- a/drivers/w1/slaves/w1_ds28e17.c +++ b/drivers/w1/slaves/w1_ds28e17.c @@ -31,12 +31,12 @@ MODULE_ALIAS("w1-family-" __stringify(W1_FAMILY_DS28E17)); /* Default I2C speed to be set when a DS28E17 is detected. */ static int i2c_speed = 100; -module_param_named(speed, i2c_speed, int, (S_IRUSR | S_IWUSR)); +module_param_named(speed, i2c_speed, int, 0600); MODULE_PARM_DESC(speed, "Default I2C speed to be set when a DS28E17 is detected"); /* Default I2C stretch value to be set when a DS28E17 is detected. */ static char i2c_stretch = 1; -module_param_named(stretch, i2c_stretch, byte, (S_IRUSR | S_IWUSR)); +module_param_named(stretch, i2c_stretch, byte, 0600); MODULE_PARM_DESC(stretch, "Default I2C stretch value to be set when a DS28E17 is detected"); /* DS28E17 device command codes. */ -- GitLab From 39bbfdacaebbe2576fb0f591e218e76a117886cf Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:55 +0200 Subject: [PATCH 3582/5631] w1: ds2433: do not use assignment in if condition Assignments in if condition are less readable and error-prone. Fixes also checkpatch warning: ERROR: do not use assignment in if condition Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-7-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/slaves/w1_ds2433.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/w1/slaves/w1_ds2433.c b/drivers/w1/slaves/w1_ds2433.c index 23cd099d032b..9f21fd98f799 100644 --- a/drivers/w1/slaves/w1_ds2433.c +++ b/drivers/w1/slaves/w1_ds2433.c @@ -98,7 +98,8 @@ static ssize_t eeprom_read(struct file *filp, struct kobject *kobj, u8 wrbuf[3]; #endif - if ((count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE)) == 0) + count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE); + if (!count) return 0; mutex_lock(&sl->master->bus_mutex); @@ -208,7 +209,8 @@ static ssize_t eeprom_write(struct file *filp, struct kobject *kobj, struct w1_slave *sl = kobj_to_w1_slave(kobj); int addr, len, idx; - if ((count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE)) == 0) + count = w1_f23_fix_count(off, count, W1_EEPROM_SIZE); + if (!count) return 0; #ifdef CONFIG_W1_SLAVE_DS2433_CRC -- GitLab From 076909c24ffa747a56d9c0167c74ee167dd81cd1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:56 +0200 Subject: [PATCH 3583/5631] w1: ds2482: drop unnecessary header linux/delay.h is already included, so drop asm header to also fix checkpatch: WARNING: Use #include instead of Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-8-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index b1c76a96cc8d..cc5938fb6239 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -15,7 +15,6 @@ #include #include #include -#include #include -- GitLab From 787e19ae1fa96cfbbb943e647253e966b4d53407 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:57 +0200 Subject: [PATCH 3584/5631] w1: ds2482: do not use assignment in if condition Assignments in if condition are less readable and error-prone. Fixes also checkpatch warning: ERROR: do not use assignment in if condition Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-9-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index cc5938fb6239..c1de8a92e144 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -451,7 +451,8 @@ static int ds2482_probe(struct i2c_client *client) I2C_FUNC_SMBUS_BYTE)) return -ENODEV; - if (!(data = kzalloc(sizeof(struct ds2482_data), GFP_KERNEL))) { + data = kzalloc(sizeof(struct ds2482_data), GFP_KERNEL); + if (!data) { err = -ENOMEM; goto exit; } -- GitLab From 01bc199b42594e31e5c4fe335f4feb40f976db1f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:58 +0200 Subject: [PATCH 3585/5631] w1: matrox: switch from asm to linux header linux/io.h is preferred over asm/io.h: WARNING: Use #include instead of Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-10-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/matrox_w1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/w1/masters/matrox_w1.c b/drivers/w1/masters/matrox_w1.c index 94a1f3fa2dc3..662108b1d806 100644 --- a/drivers/w1/masters/matrox_w1.c +++ b/drivers/w1/masters/matrox_w1.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include -- GitLab From 115ddc758bfbd24e077e2e96b307d174622e1584 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:42:59 +0200 Subject: [PATCH 3586/5631] w1: matrox: use inline over __inline__ Switch to inline as preferred by coding style: WARNING: plain inline is preferred over __inline__ Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-11-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/matrox_w1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/w1/masters/matrox_w1.c b/drivers/w1/masters/matrox_w1.c index 662108b1d806..fb38d92b2f43 100644 --- a/drivers/w1/masters/matrox_w1.c +++ b/drivers/w1/masters/matrox_w1.c @@ -63,7 +63,7 @@ struct matrox_device { * * Port mapping. */ -static __inline__ u8 matrox_w1_read_reg(struct matrox_device *dev, u8 reg) +static inline u8 matrox_w1_read_reg(struct matrox_device *dev, u8 reg) { u8 ret; @@ -74,7 +74,7 @@ static __inline__ u8 matrox_w1_read_reg(struct matrox_device *dev, u8 reg) return ret; } -static __inline__ void matrox_w1_write_reg(struct matrox_device *dev, u8 reg, u8 val) +static inline void matrox_w1_write_reg(struct matrox_device *dev, u8 reg, u8 val) { writeb(reg, dev->port_index); writeb(val, dev->port_data); -- GitLab From 4f4129e4e28fb5f5e84a2d9719666968049d95e3 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:43:00 +0200 Subject: [PATCH 3587/5631] w1: matrox: remove unnecessary ENOMEM messages Core already prints detailed reports on out of memory: WARNING: Possible unnecessary 'out of memory' message Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-12-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/matrox_w1.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/w1/masters/matrox_w1.c b/drivers/w1/masters/matrox_w1.c index fb38d92b2f43..2852cd2dc67c 100644 --- a/drivers/w1/masters/matrox_w1.c +++ b/drivers/w1/masters/matrox_w1.c @@ -122,13 +122,8 @@ static int matrox_w1_probe(struct pci_dev *pdev, const struct pci_device_id *ent dev = kzalloc(sizeof(struct matrox_device) + sizeof(struct w1_bus_master), GFP_KERNEL); - if (!dev) { - dev_err(&pdev->dev, - "%s: Failed to create new matrox_device object.\n", - __func__); + if (!dev) return -ENOMEM; - } - dev->bus_master = (struct w1_bus_master *)(dev + 1); -- GitLab From 0cb90771913922e4b34c296e96d80d451766d942 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:43:01 +0200 Subject: [PATCH 3588/5631] w1: omap-hdq: allow compile testing omap-hdq does not depend on anything from ARCH_OMAP for building. Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-13-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig index 692cac3ff0ee..ad316573288a 100644 --- a/drivers/w1/masters/Kconfig +++ b/drivers/w1/masters/Kconfig @@ -53,7 +53,7 @@ config W1_MASTER_GPIO config HDQ_MASTER_OMAP tristate "OMAP HDQ driver" - depends on ARCH_OMAP + depends on ARCH_OMAP || COMPILE_TEST help Say Y here if you want support for the 1-wire or HDQ Interface on an OMAP processor. -- GitLab From 752144d8939a5b303b753da8528e14d14c2a235c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:43:02 +0200 Subject: [PATCH 3589/5631] w1: omap-hdq: add SPDX tag Replace GPLv2 license text with SPDX and drop unnecessary file name in comment to fix checkpatch warnings: WARNING: Missing or malformed SPDX-License-Identifier tag in line 1 WARNING: It's generally not useful to have the filename in the file Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-14-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/omap_hdq.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index ae3e504cd543..826207c24bd0 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -1,12 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* - * drivers/w1/masters/omap_hdq.c - * * Copyright (C) 2007,2012 Texas Instruments, Inc. - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - * */ #include #include -- GitLab From 1e5d6652154aca23da856ac7926f23217239ea60 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:43:03 +0200 Subject: [PATCH 3590/5631] w1: omap-hdq: remove unnecessary ENOMEM messages Core already prints detailed reports on out of memory: WARNING: Possible unnecessary 'out of memory' message Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-15-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/omap_hdq.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index 826207c24bd0..6a39b71eb718 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -573,10 +573,8 @@ static int omap_hdq_probe(struct platform_device *pdev) const char *mode; hdq_data = devm_kzalloc(dev, sizeof(*hdq_data), GFP_KERNEL); - if (!hdq_data) { - dev_dbg(&pdev->dev, "unable to allocate memory\n"); + if (!hdq_data) return -ENOMEM; - } hdq_data->dev = dev; platform_set_drvdata(pdev, hdq_data); -- GitLab From 4ccb0fc2a212d11e5491a4a1e705d6d84463c3a5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 12:43:04 +0200 Subject: [PATCH 3591/5631] w1: gpio: remove unnecessary ENOMEM messages Core already prints detailed reports on out of memory: WARNING: Possible unnecessary 'out of memory' message Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230415104304.104134-16-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/w1-gpio.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/w1/masters/w1-gpio.c b/drivers/w1/masters/w1-gpio.c index d4632aace402..ac7ad63f8f8d 100644 --- a/drivers/w1/masters/w1-gpio.c +++ b/drivers/w1/masters/w1-gpio.c @@ -101,10 +101,8 @@ static int w1_gpio_probe(struct platform_device *pdev) master = devm_kzalloc(dev, sizeof(struct w1_bus_master), GFP_KERNEL); - if (!master) { - dev_err(dev, "Out of memory\n"); + if (!master) return -ENOMEM; - } pdata->gpiod = devm_gpiod_get_index(dev, NULL, 0, gflags); if (IS_ERR(pdata->gpiod)) { -- GitLab From 15f44da0ab041e6f4d2218468eec792ebfa25665 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 13 Apr 2023 15:38:29 -0700 Subject: [PATCH 3592/5631] spmi: hisi-spmi-controller: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Link: https://lore.kernel.org/r/20230306073446.2194048-2-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-2-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/hisi-spmi-controller.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/spmi/hisi-spmi-controller.c b/drivers/spmi/hisi-spmi-controller.c index 5bd23262abd6..9cbd473487cb 100644 --- a/drivers/spmi/hisi-spmi-controller.c +++ b/drivers/spmi/hisi-spmi-controller.c @@ -324,13 +324,12 @@ static int spmi_controller_probe(struct platform_device *pdev) return ret; } -static int spmi_del_controller(struct platform_device *pdev) +static void spmi_del_controller(struct platform_device *pdev) { struct spmi_controller *ctrl = platform_get_drvdata(pdev); spmi_controller_remove(ctrl); spmi_controller_put(ctrl); - return 0; } static const struct of_device_id spmi_controller_match_table[] = { @@ -343,7 +342,7 @@ MODULE_DEVICE_TABLE(of, spmi_controller_match_table); static struct platform_driver spmi_controller_driver = { .probe = spmi_controller_probe, - .remove = spmi_del_controller, + .remove_new = spmi_del_controller, .driver = { .name = "hisi_spmi_controller", .of_match_table = spmi_controller_match_table, -- GitLab From 75fbbd8b53b46fa1c36d055854d7c0c849abf9ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 13 Apr 2023 15:38:30 -0700 Subject: [PATCH 3593/5631] spmi: mtk-pmif: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Link: https://lore.kernel.org/r/20230306073446.2194048-3-u.kleine-koenig@pengutronix.de Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Uwe Kleine-König Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-3-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/spmi-mtk-pmif.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c index ad511f2c3324..fbcb3921e70c 100644 --- a/drivers/spmi/spmi-mtk-pmif.c +++ b/drivers/spmi/spmi-mtk-pmif.c @@ -503,7 +503,7 @@ static int mtk_spmi_probe(struct platform_device *pdev) return err; } -static int mtk_spmi_remove(struct platform_device *pdev) +static void mtk_spmi_remove(struct platform_device *pdev) { struct spmi_controller *ctrl = platform_get_drvdata(pdev); struct pmif *arb = spmi_controller_get_drvdata(ctrl); @@ -511,7 +511,6 @@ static int mtk_spmi_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(arb->nclks, arb->clks); spmi_controller_remove(ctrl); spmi_controller_put(ctrl); - return 0; } static const struct of_device_id mtk_spmi_match_table[] = { @@ -533,7 +532,7 @@ static struct platform_driver mtk_spmi_driver = { .of_match_table = of_match_ptr(mtk_spmi_match_table), }, .probe = mtk_spmi_probe, - .remove = mtk_spmi_remove, + .remove_new = mtk_spmi_remove, }; module_platform_driver(mtk_spmi_driver); -- GitLab From 019fe19bd4079bc9775fb034e49da68b1b8db06a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 13 Apr 2023 15:38:31 -0700 Subject: [PATCH 3594/5631] spmi: pmic-arb: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Link: https://lore.kernel.org/r/20230306073446.2194048-4-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-4-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/spmi-pmic-arb.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index 8b6a42ab816f..42a593418aad 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -1674,7 +1674,7 @@ static int spmi_pmic_arb_probe(struct platform_device *pdev) return err; } -static int spmi_pmic_arb_remove(struct platform_device *pdev) +static void spmi_pmic_arb_remove(struct platform_device *pdev) { struct spmi_controller *ctrl = platform_get_drvdata(pdev); struct spmi_pmic_arb *pmic_arb = spmi_controller_get_drvdata(ctrl); @@ -1682,7 +1682,6 @@ static int spmi_pmic_arb_remove(struct platform_device *pdev) irq_set_chained_handler_and_data(pmic_arb->irq, NULL, NULL); irq_domain_remove(pmic_arb->domain); spmi_controller_put(ctrl); - return 0; } static const struct of_device_id spmi_pmic_arb_match_table[] = { @@ -1693,7 +1692,7 @@ MODULE_DEVICE_TABLE(of, spmi_pmic_arb_match_table); static struct platform_driver spmi_pmic_arb_driver = { .probe = spmi_pmic_arb_probe, - .remove = spmi_pmic_arb_remove, + .remove_new = spmi_pmic_arb_remove, .driver = { .name = "spmi_pmic_arb", .of_match_table = spmi_pmic_arb_match_table, -- GitLab From 77982a7f4970dcabf4bbcbcae9d1dc85a731ce6b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 13 Apr 2023 15:38:32 -0700 Subject: [PATCH 3595/5631] spmi: mtk-pmif: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it is not relevant here). drivers/spmi/spmi-mtk-pmif.c:517:34: error: ‘mtk_spmi_match_table’ defined but not used [-Werror=unused-const-variable=] Link: https://lore.kernel.org/r/20230310222857.315629-2-krzysztof.kozlowski@linaro.org Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Krzysztof Kozlowski Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-5-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/spmi-mtk-pmif.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/spmi/spmi-mtk-pmif.c b/drivers/spmi/spmi-mtk-pmif.c index fbcb3921e70c..b3c991e1ea40 100644 --- a/drivers/spmi/spmi-mtk-pmif.c +++ b/drivers/spmi/spmi-mtk-pmif.c @@ -529,7 +529,7 @@ MODULE_DEVICE_TABLE(of, mtk_spmi_match_table); static struct platform_driver mtk_spmi_driver = { .driver = { .name = "spmi-mtk", - .of_match_table = of_match_ptr(mtk_spmi_match_table), + .of_match_table = mtk_spmi_match_table, }, .probe = mtk_spmi_probe, .remove_new = mtk_spmi_remove, -- GitLab From 80c606a842e6b6b6f4a2b53a734a9d3be2cdddff Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 13 Apr 2023 15:38:33 -0700 Subject: [PATCH 3596/5631] spmi: fix W=1 kernel-doc warnings Fix all W=1 kernel-doc warnings in drivers/spmi/: drivers/spmi/spmi.c:414: warning: expecting prototype for spmi_controller_alloc(). Prototype was for spmi_device_alloc() instead drivers/spmi/spmi.c:592: warning: expecting prototype for spmi_driver_register(). Prototype was for __spmi_driver_register() instead drivers/spmi/spmi.c:592: warning: Function parameter or member 'owner' not described in '__spmi_driver_register' drivers/spmi/spmi-pmic-arb.c:155: warning: cannot understand function prototype: 'struct spmi_pmic_arb ' drivers/spmi/spmi-pmic-arb.c:203: warning: cannot understand function prototype: 'struct pmic_arb_ver_ops ' drivers/spmi/spmi-pmic-arb.c:219: warning: expecting prototype for struct pmic_arb_ver. Prototype was for struct pmic_arb_ver_ops instead Link: https://lore.kernel.org/r/20230113064040.26801-1-rdunlap@infradead.org Cc: Stephen Boyd Signed-off-by: Randy Dunlap Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-6-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/spmi-pmic-arb.c | 4 ++-- drivers/spmi/spmi.c | 5 +++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index 42a593418aad..dcb675d980d4 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -126,7 +126,7 @@ struct apid_data { }; /** - * spmi_pmic_arb - SPMI PMIC Arbiter object + * struct spmi_pmic_arb - SPMI PMIC Arbiter object * * @rd_base: on v1 "core", on v2 "observer" register base off DT. * @wr_base: on v1 "core", on v2 "chnls" register base off DT. @@ -180,7 +180,7 @@ struct spmi_pmic_arb { }; /** - * pmic_arb_ver: version dependent functionality. + * struct pmic_arb_ver_ops - version dependent functionality. * * @ver_str: version string. * @ppid_to_apid: finds the apid for a given ppid. diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 73551531ed43..5705151013b3 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -404,7 +404,7 @@ struct spmi_device *spmi_device_from_of(struct device_node *np) EXPORT_SYMBOL_GPL(spmi_device_from_of); /** - * spmi_controller_alloc() - Allocate a new SPMI device + * spmi_device_alloc() - Allocate a new SPMI device * @ctrl: associated controller * * Caller is responsible for either calling spmi_device_add() to add the @@ -582,8 +582,9 @@ void spmi_controller_remove(struct spmi_controller *ctrl) EXPORT_SYMBOL_GPL(spmi_controller_remove); /** - * spmi_driver_register() - Register client driver with SPMI core + * __spmi_driver_register() - Register client driver with SPMI core * @sdrv: client driver to be associated with client-device. + * @owner: module owner * * This API will register the client driver with the SPMI framework. * It is typically called from the driver's module-init function. -- GitLab From b56eef3e16d888883fefab47425036de80dd38fc Mon Sep 17 00:00:00 2001 From: Jishnu Prakash Date: Thu, 13 Apr 2023 15:38:34 -0700 Subject: [PATCH 3597/5631] spmi: Add a check for remove callback when removing a SPMI driver When removing a SPMI driver, there can be a crash due to NULL pointer dereference if it does not have a remove callback defined. This is one such call trace observed when removing the QCOM SPMI PMIC driver: dump_backtrace.cfi_jt+0x0/0x8 dump_stack_lvl+0xd8/0x16c panic+0x188/0x498 __cfi_slowpath+0x0/0x214 __cfi_slowpath+0x1dc/0x214 spmi_drv_remove+0x16c/0x1e0 device_release_driver_internal+0x468/0x79c driver_detach+0x11c/0x1a0 bus_remove_driver+0xc4/0x124 driver_unregister+0x58/0x84 cleanup_module+0x1c/0xc24 [qcom_spmi_pmic] __do_sys_delete_module+0x3ec/0x53c __arm64_sys_delete_module+0x18/0x28 el0_svc_common+0xdc/0x294 el0_svc+0x38/0x9c el0_sync_handler+0x8c/0xf0 el0_sync+0x1b4/0x1c0 If a driver has all its resources allocated through devm_() APIs and does not need any other explicit cleanup, it would not require a remove callback to be defined. Hence, add a check for remove callback presence before calling it when removing a SPMI driver. Link: https://lore.kernel.org/r/1671601032-18397-2-git-send-email-quic_jprakash@quicinc.com Fixes: 6f00f8c8635f ("mfd: qcom-spmi-pmic: Use devm_of_platform_populate()") Fixes: 5a86bf343976 ("spmi: Linux driver framework for SPMI") Signed-off-by: Jishnu Prakash Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230413223834.4084793-7-sboyd@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/spmi/spmi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c index 5705151013b3..7313d4c18a04 100644 --- a/drivers/spmi/spmi.c +++ b/drivers/spmi/spmi.c @@ -350,7 +350,8 @@ static void spmi_drv_remove(struct device *dev) const struct spmi_driver *sdrv = to_spmi_driver(dev->driver); pm_runtime_get_sync(dev); - sdrv->remove(to_spmi_device(dev)); + if (sdrv->remove) + sdrv->remove(to_spmi_device(dev)); pm_runtime_put_noidle(dev); pm_runtime_disable(dev); -- GitLab From e2f06aa885081e1391916367f53bad984714b4db Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Wed, 12 Apr 2023 15:58:42 -0700 Subject: [PATCH 3598/5631] driver core: Don't require dynamic_debug for initcall_debug probe timing Don't require the use of dynamic debug (or modification of the kernel to add a #define DEBUG to the top of this file) to get the printk message about driver probe timing. This printk is only emitted when initcall_debug is enabled on the kernel commandline, and it isn't immediately obvious that you have to do something else to debug boot timing issues related to driver probe. Add a comment too so it doesn't get converted back to pr_debug(). Fixes: eb7fbc9fb118 ("driver core: Add missing '\n' in log messages") Cc: stable Cc: Christophe JAILLET Cc: Brian Norris Reviewed-by: Brian Norris Acked-by: Randy Dunlap Signed-off-by: Stephen Boyd Link: https://lore.kernel.org/r/20230412225842.3196599-1-swboyd@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/dd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 7b9ab2050b84..9c09ca5c4ab6 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -735,7 +735,12 @@ static int really_probe_debug(struct device *dev, struct device_driver *drv) calltime = ktime_get(); ret = really_probe(dev, drv); rettime = ktime_get(); - pr_debug("probe of %s returned %d after %lld usecs\n", + /* + * Don't change this to pr_debug() because that requires + * CONFIG_DYNAMIC_DEBUG and we want a simple 'initcall_debug' on the + * kernel commandline to print this all the time at the debug level. + */ + printk(KERN_DEBUG "probe of %s returned %d after %lld usecs\n", dev_name(dev), ret, ktime_us_delta(rettime, calltime)); return ret; } -- GitLab From 11a96703943fc4293f50f554b9e33c79ef4f5d8d Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Thu, 6 Apr 2023 01:54:35 -0300 Subject: [PATCH 3599/5631] driver core: update comments in device_rename() Document that some subsystems are still going to use device_rename for the time being, so it is not a good idea to assume it's not used. Also remove mentions of a plan to stop renaming net devices. Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230406045435.19452-1-wedsonaf@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 7a42d1b6b721..3dff5037943e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4416,9 +4416,12 @@ EXPORT_SYMBOL_GPL(device_destroy); * on the same device to ensure that new_name is valid and * won't conflict with other devices. * - * Note: Don't call this function. Currently, the networking layer calls this - * function, but that will change. The following text from Kay Sievers offers - * some insight: + * Note: given that some subsystems (networking and infiniband) use this + * function, with no immediate plans for this to change, we cannot assume or + * require that this function not be called at all. + * + * However, if you're writing new code, do not call this function. The following + * text from Kay Sievers offers some insight: * * Renaming devices is racy at many levels, symlinks and other stuff are not * replaced atomically, and you get a "move" uevent, but it's not easy to @@ -4432,13 +4435,6 @@ EXPORT_SYMBOL_GPL(device_destroy); * kernel device renaming. Besides that, it's not even implemented now for * other things than (driver-core wise very simple) network devices. * - * We are currently about to change network renaming in udev to completely - * disallow renaming of devices in the same namespace as the kernel uses, - * because we can't solve the problems properly, that arise with swapping names - * of multiple interfaces without races. Means, renaming of eth[0-9]* will only - * be allowed to some other name than eth[0-9]*, for the aforementioned - * reasons. - * * Make up a "real" name in the driver before you register anything, or add * some other attributes for userspace to find the device, or use udev to add * symlinks -- but never rename kernel devices later, it's a complete mess. We -- GitLab From 32118bdc9471f6d28dbf3d55b2bf0f912be0c62b Mon Sep 17 00:00:00 2001 From: Deming Wang Date: Wed, 12 Apr 2023 03:30:41 -0400 Subject: [PATCH 3600/5631] virt: acrn: Replace obsolete memalign() with posix_memalign() memalign() is obsolete according to its manpage. Replace memalign() with posix_memalign() and remove malloc.h include that was there for memalign(). As a pointer is passed into posix_memalign(), initialize *p to NULL to silence a warning about the function's return value being used as uninitialized (which is not valid anyway because the error is properly checked before p is returned). Signed-off-by: Deming Wang Link: https://lore.kernel.org/r/20230412073041.2168-1-wangdeming@inspur.com Signed-off-by: Greg Kroah-Hartman --- samples/acrn/vm-sample.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/samples/acrn/vm-sample.c b/samples/acrn/vm-sample.c index 7abd68b20153..704402c64ea3 100644 --- a/samples/acrn/vm-sample.c +++ b/samples/acrn/vm-sample.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include @@ -54,8 +53,8 @@ int main(int argc, char **argv) argc = argc; argv = argv; - guest_memory = memalign(4096, GUEST_MEMORY_SIZE); - if (!guest_memory) { + ret = posix_memalign(&guest_memory, 4096, GUEST_MEMORY_SIZE); + if (ret < 0) { printf("No enough memory!\n"); return -1; } -- GitLab From 4daa669efcfa5147e4bd5ecb3f1e10c0c96eef27 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 11 Apr 2023 18:04:09 +0000 Subject: [PATCH 3601/5631] kernel/configs: Drop Android config fragments In the old days where each device had a custom kernel, the android config fragments were useful to provide the required and reccomended options expected by userland. However, these days devices are expected to use the GKI kernel, so these config fragments no longer needed, and out of date, so they seem to only cause confusion. So lets drop them. If folks are curious what configs are expected by the Android environment, check out the gki_defconfig file in the latest android common kernel tree. Cc: Rob Herring Cc: Amit Pundir Cc: Signed-off-by: John Stultz Link: https://lore.kernel.org/r/20230411180409.1706067-1-jstultz@google.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 5 - kernel/configs/android-base.config | 159 ---------------------- kernel/configs/android-recommended.config | 127 ----------------- 3 files changed, 291 deletions(-) delete mode 100644 kernel/configs/android-base.config delete mode 100644 kernel/configs/android-recommended.config diff --git a/MAINTAINERS b/MAINTAINERS index 78944f72b6fe..5408ca5771a2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1436,11 +1436,6 @@ S: Supported F: drivers/clk/analogbits/* F: include/linux/clk/analogbits* -ANDROID CONFIG FRAGMENTS -M: Rob Herring -S: Supported -F: kernel/configs/android* - ANDROID DRIVERS M: Greg Kroah-Hartman M: Arve Hjønnevåg diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config deleted file mode 100644 index 44b0f0146a3f..000000000000 --- a/kernel/configs/android-base.config +++ /dev/null @@ -1,159 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_DEVMEM is not set -# CONFIG_FHANDLE is not set -# CONFIG_INET_LRO is not set -# CONFIG_NFSD is not set -# CONFIG_NFS_FS is not set -# CONFIG_OABI_COMPAT is not set -# CONFIG_SYSVIPC is not set -# CONFIG_USELIB is not set -CONFIG_ANDROID_BINDER_IPC=y -CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder -CONFIG_ANDROID_LOW_MEMORY_KILLER=y -CONFIG_ARMV8_DEPRECATED=y -CONFIG_ASHMEM=y -CONFIG_AUDIT=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_CGROUPS=y -CONFIG_CGROUP_BPF=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_DEBUG=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_SCHED=y -CONFIG_CP15_BARRIER_EMULATION=y -CONFIG_DEFAULT_SECURITY_SELINUX=y -CONFIG_EMBEDDED=y -CONFIG_FB=y -CONFIG_HARDENED_USERCOPY=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_INET6_AH=y -CONFIG_INET6_ESP=y -CONFIG_INET6_IPCOMP=y -CONFIG_INET=y -CONFIG_INET_DIAG_DESTROY=y -CONFIG_INET_ESP=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_IP6_NF_FILTER=y -CONFIG_IP6_NF_IPTABLES=y -CONFIG_IP6_NF_MANGLE=y -CONFIG_IP6_NF_RAW=y -CONFIG_IP6_NF_TARGET_REJECT=y -CONFIG_IPV6=y -CONFIG_IPV6_MIP6=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_ARPFILTER=y -CONFIG_IP_NF_ARPTABLES=y -CONFIG_IP_NF_ARP_MANGLE=y -CONFIG_IP_NF_FILTER=y -CONFIG_IP_NF_IPTABLES=y -CONFIG_IP_NF_MANGLE=y -CONFIG_IP_NF_MATCH_AH=y -CONFIG_IP_NF_MATCH_ECN=y -CONFIG_IP_NF_MATCH_TTL=y -CONFIG_IP_NF_NAT=y -CONFIG_IP_NF_RAW=y -CONFIG_IP_NF_SECURITY=y -CONFIG_IP_NF_TARGET_MASQUERADE=y -CONFIG_IP_NF_TARGET_NETMAP=y -CONFIG_IP_NF_TARGET_REDIRECT=y -CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_NET=y -CONFIG_NETDEVICES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_TPROXY=y -CONFIG_NETFILTER_XT_MATCH_COMMENT=y -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y -CONFIG_NETFILTER_XT_MATCH_CONNMARK=y -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y -CONFIG_NETFILTER_XT_MATCH_HELPER=y -CONFIG_NETFILTER_XT_MATCH_IPRANGE=y -CONFIG_NETFILTER_XT_MATCH_LENGTH=y -CONFIG_NETFILTER_XT_MATCH_LIMIT=y -CONFIG_NETFILTER_XT_MATCH_MAC=y -CONFIG_NETFILTER_XT_MATCH_MARK=y -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y -CONFIG_NETFILTER_XT_MATCH_POLICY=y -CONFIG_NETFILTER_XT_MATCH_QUOTA=y -CONFIG_NETFILTER_XT_MATCH_SOCKET=y -CONFIG_NETFILTER_XT_MATCH_STATE=y -CONFIG_NETFILTER_XT_MATCH_STATISTIC=y -CONFIG_NETFILTER_XT_MATCH_STRING=y -CONFIG_NETFILTER_XT_MATCH_TIME=y -CONFIG_NETFILTER_XT_MATCH_U32=y -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y -CONFIG_NETFILTER_XT_TARGET_CONNMARK=y -CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y -CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y -CONFIG_NETFILTER_XT_TARGET_MARK=y -CONFIG_NETFILTER_XT_TARGET_NFLOG=y -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y -CONFIG_NETFILTER_XT_TARGET_SECMARK=y -CONFIG_NETFILTER_XT_TARGET_TCPMSS=y -CONFIG_NETFILTER_XT_TARGET_TPROXY=y -CONFIG_NETFILTER_XT_TARGET_TRACE=y -CONFIG_NET_CLS_ACT=y -CONFIG_NET_CLS_U32=y -CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_U32=y -CONFIG_NET_KEY=y -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_HTB=y -CONFIG_NF_CONNTRACK=y -CONFIG_NF_CONNTRACK_AMANDA=y -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CONNTRACK_FTP=y -CONFIG_NF_CONNTRACK_H323=y -CONFIG_NF_CONNTRACK_IPV4=y -CONFIG_NF_CONNTRACK_IPV6=y -CONFIG_NF_CONNTRACK_IRC=y -CONFIG_NF_CONNTRACK_NETBIOS_NS=y -CONFIG_NF_CONNTRACK_PPTP=y -CONFIG_NF_CONNTRACK_SANE=y -CONFIG_NF_CONNTRACK_SECMARK=y -CONFIG_NF_CONNTRACK_TFTP=y -CONFIG_NF_CT_NETLINK=y -CONFIG_NF_CT_PROTO_DCCP=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_NAT=y -CONFIG_NO_HZ=y -CONFIG_PACKET=y -CONFIG_PM_AUTOSLEEP=y -CONFIG_PM_WAKELOCKS=y -CONFIG_PPP=y -CONFIG_PPP_BSDCOMP=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_MPPE=y -CONFIG_PREEMPT=y -CONFIG_QUOTA=y -CONFIG_RANDOMIZE_BASE=y -CONFIG_RTC_CLASS=y -CONFIG_RT_GROUP_SCHED=y -CONFIG_SECCOMP=y -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SETEND_EMULATION=y -CONFIG_STAGING=y -CONFIG_SWP_EMULATION=y -CONFIG_SYNC=y -CONFIG_TUN=y -CONFIG_UNIX=y -CONFIG_USB_GADGET=y -CONFIG_USB_CONFIGFS=y -CONFIG_USB_CONFIGFS_F_FS=y -CONFIG_USB_CONFIGFS_F_MIDI=y -CONFIG_USB_OTG_WAKELOCK=y -CONFIG_XFRM_USER=y diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config deleted file mode 100644 index e400fbbc8aba..000000000000 --- a/kernel/configs/android-recommended.config +++ /dev/null @@ -1,127 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_BPF_UNPRIV_DEFAULT_OFF is not set -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_LEGACY_PTYS is not set -# CONFIG_NF_CONNTRACK_SIP is not set -# CONFIG_PM_WAKELOCKS_GC is not set -# CONFIG_VT is not set -CONFIG_ARM64_SW_TTBR0_PAN=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -CONFIG_BLK_DEV_DM=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_STACKPROTECTOR_STRONG=y -CONFIG_COMPACTION=y -CONFIG_CPU_SW_DOMAIN_PAN=y -CONFIG_DM_CRYPT=y -CONFIG_DM_UEVENT=y -CONFIG_DM_VERITY=y -CONFIG_DM_VERITY_FEC=y -CONFIG_DRAGONRISE_FF=y -CONFIG_ENABLE_DEFAULT_TRACERS=y -CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_SECURITY=y -CONFIG_FUSE_FS=y -CONFIG_GREENASIA_FF=y -CONFIG_HIDRAW=y -CONFIG_HID_A4TECH=y -CONFIG_HID_ACRUX=y -CONFIG_HID_ACRUX_FF=y -CONFIG_HID_APPLE=y -CONFIG_HID_BELKIN=y -CONFIG_HID_CHERRY=y -CONFIG_HID_CHICONY=y -CONFIG_HID_CYPRESS=y -CONFIG_HID_DRAGONRISE=y -CONFIG_HID_ELECOM=y -CONFIG_HID_EMS_FF=y -CONFIG_HID_EZKEY=y -CONFIG_HID_GREENASIA=y -CONFIG_HID_GYRATION=y -CONFIG_HID_HOLTEK=y -CONFIG_HID_KENSINGTON=y -CONFIG_HID_KEYTOUCH=y -CONFIG_HID_KYE=y -CONFIG_HID_LCPOWER=y -CONFIG_HID_LOGITECH=y -CONFIG_HID_LOGITECH_DJ=y -CONFIG_HID_MAGICMOUSE=y -CONFIG_HID_MICROSOFT=y -CONFIG_HID_MONTEREY=y -CONFIG_HID_MULTITOUCH=y -CONFIG_HID_NTRIG=y -CONFIG_HID_ORTEK=y -CONFIG_HID_PANTHERLORD=y -CONFIG_HID_PETALYNX=y -CONFIG_HID_PICOLCD=y -CONFIG_HID_PRIMAX=y -CONFIG_HID_PRODIKEYS=y -CONFIG_HID_ROCCAT=y -CONFIG_HID_SAITEK=y -CONFIG_HID_SAMSUNG=y -CONFIG_HID_SMARTJOYPLUS=y -CONFIG_HID_SONY=y -CONFIG_HID_SPEEDLINK=y -CONFIG_HID_SUNPLUS=y -CONFIG_HID_THRUSTMASTER=y -CONFIG_HID_TIVO=y -CONFIG_HID_TOPSEED=y -CONFIG_HID_TWINHAN=y -CONFIG_HID_UCLOGIC=y -CONFIG_HID_WACOM=y -CONFIG_HID_WALTOP=y -CONFIG_HID_WIIMOTE=y -CONFIG_HID_ZEROPLUS=y -CONFIG_HID_ZYDACRON=y -CONFIG_INPUT_EVDEV=y -CONFIG_INPUT_GPIO=y -CONFIG_INPUT_JOYSTICK=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_TABLET=y -CONFIG_INPUT_UINPUT=y -CONFIG_JOYSTICK_XPAD=y -CONFIG_JOYSTICK_XPAD_FF=y -CONFIG_JOYSTICK_XPAD_LEDS=y -CONFIG_KALLSYMS_ALL=y -CONFIG_KSM=y -CONFIG_LOGIG940_FF=y -CONFIG_LOGIRUMBLEPAD2_FF=y -CONFIG_LOGITECH_FF=y -CONFIG_MD=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_MSDOS_FS=y -CONFIG_PANIC_TIMEOUT=5 -CONFIG_PANTHERLORD_FF=y -CONFIG_PERF_EVENTS=y -CONFIG_PM_DEBUG=y -CONFIG_PM_RUNTIME=y -CONFIG_PM_WAKELOCKS_LIMIT=0 -CONFIG_POWER_SUPPLY=y -CONFIG_PSTORE=y -CONFIG_PSTORE_CONSOLE=y -CONFIG_PSTORE_RAM=y -CONFIG_SCHEDSTATS=y -CONFIG_SMARTJOYPLUS_FF=y -CONFIG_SND=y -CONFIG_SOUND=y -CONFIG_STRICT_KERNEL_RWX=y -CONFIG_SUSPEND_TIME=y -CONFIG_TABLET_USB_ACECAD=y -CONFIG_TABLET_USB_AIPTEK=y -CONFIG_TABLET_USB_HANWANG=y -CONFIG_TABLET_USB_KBTAB=y -CONFIG_TASKSTATS=y -CONFIG_TASK_DELAY_ACCT=y -CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_TASK_XACCT=y -CONFIG_TIMER_STATS=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_UHID=y -CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_EHCI_HCD=y -CONFIG_USB_HIDDEV=y -CONFIG_USB_USBNET=y -CONFIG_VFAT_FS=y -- GitLab From a889c276d33d333ae96697510f33533f6e9d9591 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rodr=C3=ADguez=20Barbarin=2C=20Jos=C3=A9=20Javier?= Date: Tue, 11 Apr 2023 10:33:27 +0200 Subject: [PATCH 3602/5631] mcb: Return actual parsed size when reading chameleon table The function chameleon_parse_cells() returns the number of cells parsed which has an undetermined size. This return value is only used for error checking but the number of cells is never used. Change return value to be number of bytes parsed to allow for memory management improvements. Co-developed-by: Jorge Sanjuan Garcia Signed-off-by: Jorge Sanjuan Garcia Signed-off-by: Javier Rodriguez Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230411083329.4506-2-jth@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/mcb/mcb-parse.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c index aa6938da0db8..2aef990f379f 100644 --- a/drivers/mcb/mcb-parse.c +++ b/drivers/mcb/mcb-parse.c @@ -130,7 +130,7 @@ static void chameleon_parse_bar(void __iomem *base, } } -static int chameleon_get_bar(char __iomem **base, phys_addr_t mapbase, +static int chameleon_get_bar(void __iomem **base, phys_addr_t mapbase, struct chameleon_bar **cb) { struct chameleon_bar *c; @@ -179,12 +179,13 @@ int chameleon_parse_cells(struct mcb_bus *bus, phys_addr_t mapbase, { struct chameleon_fpga_header *header; struct chameleon_bar *cb; - char __iomem *p = base; + void __iomem *p = base; int num_cells = 0; uint32_t dtype; int bar_count; int ret; u32 hsize; + u32 table_size; hsize = sizeof(struct chameleon_fpga_header); @@ -239,12 +240,16 @@ int chameleon_parse_cells(struct mcb_bus *bus, phys_addr_t mapbase, num_cells++; } - if (num_cells == 0) - num_cells = -EINVAL; + if (num_cells == 0) { + ret = -EINVAL; + goto free_bar; + } + table_size = p - base; + pr_debug("%d cell(s) found. Chameleon table size: 0x%04x bytes\n", num_cells, table_size); kfree(cb); kfree(header); - return num_cells; + return table_size; free_bar: kfree(cb); -- GitLab From 9be24faadd085c284890c3afcec7a0184642315a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rodr=C3=ADguez=20Barbarin=2C=20Jos=C3=A9=20Javier?= Date: Tue, 11 Apr 2023 10:33:28 +0200 Subject: [PATCH 3603/5631] mcb-pci: Reallocate memory region to avoid memory overlapping mcb-pci requests a fixed-size memory region to parse the chameleon table, however, if the chameleon table is smaller that the allocated region, it could overlap with the IP Cores' memory regions. After parsing the chameleon table, drop/reallocate the memory region with the actual chameleon table size. Co-developed-by: Jorge Sanjuan Garcia Signed-off-by: Jorge Sanjuan Garcia Signed-off-by: Javier Rodriguez Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230411083329.4506-3-jth@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/mcb/mcb-pci.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/drivers/mcb/mcb-pci.c b/drivers/mcb/mcb-pci.c index dc88232d9af8..53d9202ff9a7 100644 --- a/drivers/mcb/mcb-pci.c +++ b/drivers/mcb/mcb-pci.c @@ -31,7 +31,7 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct resource *res; struct priv *priv; - int ret; + int ret, table_size; unsigned long flags; priv = devm_kzalloc(&pdev->dev, sizeof(struct priv), GFP_KERNEL); @@ -90,7 +90,30 @@ static int mcb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret < 0) goto out_mcb_bus; - dev_dbg(&pdev->dev, "Found %d cells\n", ret); + table_size = ret; + + if (table_size < CHAM_HEADER_SIZE) { + /* Release the previous resources */ + devm_iounmap(&pdev->dev, priv->base); + devm_release_mem_region(&pdev->dev, priv->mapbase, CHAM_HEADER_SIZE); + + /* Then, allocate it again with the actual chameleon table size */ + res = devm_request_mem_region(&pdev->dev, priv->mapbase, + table_size, + KBUILD_MODNAME); + if (!res) { + dev_err(&pdev->dev, "Failed to request PCI memory\n"); + ret = -EBUSY; + goto out_mcb_bus; + } + + priv->base = devm_ioremap(&pdev->dev, priv->mapbase, table_size); + if (!priv->base) { + dev_err(&pdev->dev, "Cannot ioremap\n"); + ret = -ENOMEM; + goto out_mcb_bus; + } + } mcb_bus_add_devices(priv->bus); -- GitLab From 2025b2ca8004c04861903d076c67a73a0ec6dfca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rodr=C3=ADguez=20Barbarin=2C=20Jos=C3=A9=20Javier?= Date: Tue, 11 Apr 2023 10:33:29 +0200 Subject: [PATCH 3604/5631] mcb-lpc: Reallocate memory region to avoid memory overlapping mcb-lpc requests a fixed-size memory region to parse the chameleon table, however, if the chameleon table is smaller that the allocated region, it could overlap with the IP Cores' memory regions. After parsing the chameleon table, drop/reallocate the memory region with the actual chameleon table size. Co-developed-by: Jorge Sanjuan Garcia Signed-off-by: Jorge Sanjuan Garcia Signed-off-by: Javier Rodriguez Signed-off-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20230411083329.4506-4-jth@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/mcb/mcb-lpc.c | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-) diff --git a/drivers/mcb/mcb-lpc.c b/drivers/mcb/mcb-lpc.c index 53decd89876e..a851e0236464 100644 --- a/drivers/mcb/mcb-lpc.c +++ b/drivers/mcb/mcb-lpc.c @@ -23,7 +23,7 @@ static int mcb_lpc_probe(struct platform_device *pdev) { struct resource *res; struct priv *priv; - int ret = 0; + int ret = 0, table_size; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -58,16 +58,43 @@ static int mcb_lpc_probe(struct platform_device *pdev) ret = chameleon_parse_cells(priv->bus, priv->mem->start, priv->base); if (ret < 0) { - mcb_release_bus(priv->bus); - return ret; + goto out_mcb_bus; } - dev_dbg(&pdev->dev, "Found %d cells\n", ret); + table_size = ret; + + if (table_size < CHAM_HEADER_SIZE) { + /* Release the previous resources */ + devm_iounmap(&pdev->dev, priv->base); + devm_release_mem_region(&pdev->dev, priv->mem->start, resource_size(priv->mem)); + + /* Then, allocate it again with the actual chameleon table size */ + res = devm_request_mem_region(&pdev->dev, priv->mem->start, + table_size, + KBUILD_MODNAME); + if (!res) { + dev_err(&pdev->dev, "Failed to request PCI memory\n"); + ret = -EBUSY; + goto out_mcb_bus; + } + + priv->base = devm_ioremap(&pdev->dev, priv->mem->start, table_size); + if (!priv->base) { + dev_err(&pdev->dev, "Cannot ioremap\n"); + ret = -ENOMEM; + goto out_mcb_bus; + } + + platform_set_drvdata(pdev, priv); + } mcb_bus_add_devices(priv->bus); return 0; +out_mcb_bus: + mcb_release_bus(priv->bus); + return ret; } static int mcb_lpc_remove(struct platform_device *pdev) -- GitLab From 046b6a171009e1ed9ede02194025e9ccd709beb2 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Wed, 19 Apr 2023 09:41:27 -0700 Subject: [PATCH 3605/5631] device property: make device_property functions take const device * device_property functions do not modify the device pointer passed to them. The underlying of_device and fwnode_ functions actually already take const * arguments. Mark the parameter constant to simplify conversion from of_property to device_property functions, and to let the calling code use const device pointers where possible. Cc: Chris Packham Reviewed-by: Chris Packham Reviewed-by: Sakari Ailus Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20230419164127.3773278-1-linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman --- drivers/base/property.c | 16 ++++++++-------- include/linux/property.h | 36 ++++++++++++++++++------------------ 2 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/base/property.c b/drivers/base/property.c index 6a908e9c30f8..f6117ec9805c 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(__dev_fwnode_const); * * Return: true if property @propname is present. Otherwise, returns false. */ -bool device_property_present(struct device *dev, const char *propname) +bool device_property_present(const struct device *dev, const char *propname) { return fwnode_property_present(dev_fwnode(dev), propname); } @@ -90,7 +90,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_present); * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_u8_array(struct device *dev, const char *propname, +int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval) { return fwnode_property_read_u8_array(dev_fwnode(dev), propname, val, nval); @@ -118,7 +118,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u8_array); * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_u16_array(struct device *dev, const char *propname, +int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval) { return fwnode_property_read_u16_array(dev_fwnode(dev), propname, val, nval); @@ -146,7 +146,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u16_array); * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_u32_array(struct device *dev, const char *propname, +int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval) { return fwnode_property_read_u32_array(dev_fwnode(dev), propname, val, nval); @@ -174,7 +174,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u32_array); * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_u64_array(struct device *dev, const char *propname, +int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval) { return fwnode_property_read_u64_array(dev_fwnode(dev), propname, val, nval); @@ -202,7 +202,7 @@ EXPORT_SYMBOL_GPL(device_property_read_u64_array); * %-EOVERFLOW if the size of the property is not as expected. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_string_array(struct device *dev, const char *propname, +int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval) { return fwnode_property_read_string_array(dev_fwnode(dev), propname, val, nval); @@ -224,7 +224,7 @@ EXPORT_SYMBOL_GPL(device_property_read_string_array); * %-EPROTO or %-EILSEQ if the property type is not a string. * %-ENXIO if no suitable firmware interface is present. */ -int device_property_read_string(struct device *dev, const char *propname, +int device_property_read_string(const struct device *dev, const char *propname, const char **val) { return fwnode_property_read_string(dev_fwnode(dev), propname, val); @@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(device_property_read_string); * %-EPROTO if the property is not an array of strings, * %-ENXIO if no suitable firmware interface is present. */ -int device_property_match_string(struct device *dev, const char *propname, +int device_property_match_string(const struct device *dev, const char *propname, const char *string) { return fwnode_property_match_string(dev_fwnode(dev), propname, string); diff --git a/include/linux/property.h b/include/linux/property.h index 59f452198c64..66df1a15d518 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -39,20 +39,20 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); const struct device *: __dev_fwnode_const, \ struct device *: __dev_fwnode)(dev) -bool device_property_present(struct device *dev, const char *propname); -int device_property_read_u8_array(struct device *dev, const char *propname, +bool device_property_present(const struct device *dev, const char *propname); +int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); -int device_property_read_u16_array(struct device *dev, const char *propname, +int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval); -int device_property_read_u32_array(struct device *dev, const char *propname, +int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval); -int device_property_read_u64_array(struct device *dev, const char *propname, +int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval); -int device_property_read_string_array(struct device *dev, const char *propname, +int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval); -int device_property_read_string(struct device *dev, const char *propname, +int device_property_read_string(const struct device *dev, const char *propname, const char **val); -int device_property_match_string(struct device *dev, +int device_property_match_string(const struct device *dev, const char *propname, const char *string); bool fwnode_property_present(const struct fwnode_handle *fwnode, @@ -142,57 +142,57 @@ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(struct device *dev, +static inline bool device_property_read_bool(const struct device *dev, const char *propname) { return device_property_present(dev, propname); } -static inline int device_property_read_u8(struct device *dev, +static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { return device_property_read_u8_array(dev, propname, val, 1); } -static inline int device_property_read_u16(struct device *dev, +static inline int device_property_read_u16(const struct device *dev, const char *propname, u16 *val) { return device_property_read_u16_array(dev, propname, val, 1); } -static inline int device_property_read_u32(struct device *dev, +static inline int device_property_read_u32(const struct device *dev, const char *propname, u32 *val) { return device_property_read_u32_array(dev, propname, val, 1); } -static inline int device_property_read_u64(struct device *dev, +static inline int device_property_read_u64(const struct device *dev, const char *propname, u64 *val) { return device_property_read_u64_array(dev, propname, val, 1); } -static inline int device_property_count_u8(struct device *dev, const char *propname) +static inline int device_property_count_u8(const struct device *dev, const char *propname) { return device_property_read_u8_array(dev, propname, NULL, 0); } -static inline int device_property_count_u16(struct device *dev, const char *propname) +static inline int device_property_count_u16(const struct device *dev, const char *propname) { return device_property_read_u16_array(dev, propname, NULL, 0); } -static inline int device_property_count_u32(struct device *dev, const char *propname) +static inline int device_property_count_u32(const struct device *dev, const char *propname) { return device_property_read_u32_array(dev, propname, NULL, 0); } -static inline int device_property_count_u64(struct device *dev, const char *propname) +static inline int device_property_count_u64(const struct device *dev, const char *propname) { return device_property_read_u64_array(dev, propname, NULL, 0); } -static inline int device_property_string_array_count(struct device *dev, +static inline int device_property_string_array_count(const struct device *dev, const char *propname) { return device_property_read_string_array(dev, propname, NULL, 0); -- GitLab From ec274aff21b6a94c7973384ca80a503c1bc3b173 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Thu, 20 Apr 2023 11:58:58 +0200 Subject: [PATCH 3606/5631] swiotlb: Omit total_used and used_hiwater if !CONFIG_DEBUG_FS The tracking of used_hiwater adds an atomic operation to the hot path. This is acceptable only when debugging the kernel. To make sure that the fields can never be used by mistake, do not even include them in struct io_tlb_mem if CONFIG_DEBUG_FS is not set. The build fails after doing that. To fix it, it is necessary to remove all code specific to debugfs and instead provide a stub implementation of swiotlb_create_debugfs_files(). As a bonus, this change allows to remove one __maybe_unused attribute. Signed-off-by: Petr Tesarik Signed-off-by: Christoph Hellwig --- include/linux/swiotlb.h | 2 ++ kernel/dma/swiotlb.c | 15 ++++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 6dc4598d2260..44767844e12b 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -107,8 +107,10 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; +#ifdef CONFIG_DEBUG_FS atomic_long_t total_used; atomic_long_t used_hiwater; +#endif }; extern struct io_tlb_mem io_tlb_default_mem; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9bbc2802a444..e67dafc255f2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -966,6 +966,8 @@ bool is_swiotlb_active(struct device *dev) } EXPORT_SYMBOL_GPL(is_swiotlb_active); +#ifdef CONFIG_DEBUG_FS + static int io_tlb_used_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; @@ -1015,15 +1017,22 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, &fops_io_tlb_hiwater); } -static int __init __maybe_unused swiotlb_create_default_debugfs(void) +static int __init swiotlb_create_default_debugfs(void) { swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb"); return 0; } -#ifdef CONFIG_DEBUG_FS late_initcall(swiotlb_create_default_debugfs); -#endif + +#else /* !CONFIG_DEBUG_FS */ + +static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, + const char *dirname) +{ +} + +#endif /* CONFIG_DEBUG_FS */ #ifdef CONFIG_DMA_RESTRICTED_POOL -- GitLab From 654d0310007146fae87b0c1a68f81e53ad519b14 Mon Sep 17 00:00:00 2001 From: Etienne Carriere Date: Thu, 20 Apr 2023 09:49:23 +0200 Subject: [PATCH 3607/5631] optee: fix uninited async notif value Fixes an uninitialized variable in irq_handler() that could lead to unpredictable behavior in case OP-TEE fails to handle SMC function ID OPTEE_SMC_GET_ASYNC_NOTIF_VALUE. This change ensures that in that case get_async_notif_value() properly reports there are no notification event. Reported-by: kernel test robot Link: https://lore.kernel.org/r/202304200755.OoiuclDZ-lkp@intel.com/ Reported-by: Dan Carpenter Link: https://lore.kernel.org/all/d9b7f69b-c737-4cb3-8e74-79fe00c934f9@kili.mountain/ Fixes: 6749e69c4dad ("optee: add asynchronous notifications") Signed-off-by: Etienne Carriere Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/optee/smc_abi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index a1c1fa1a9c28..e6e0428f8e7b 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -984,8 +984,10 @@ static u32 get_async_notif_value(optee_invoke_fn *invoke_fn, bool *value_valid, invoke_fn(OPTEE_SMC_GET_ASYNC_NOTIF_VALUE, 0, 0, 0, 0, 0, 0, 0, &res); - if (res.a0) + if (res.a0) { + *value_valid = false; return 0; + } *value_valid = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_VALID); *value_pending = (res.a2 & OPTEE_SMC_ASYNC_NOTIF_VALUE_PENDING); return res.a1; -- GitLab From 038585573d0544bc717cdc5b3be4e95206d3ee3d Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:47 +0200 Subject: [PATCH 3608/5631] efi/pe: Import new BTI/IBT header flags from the spec The latest version of your favorite fork of the PE/COFF spec includes a new type of header flag that is intended to be used in the context of EFI firmware to indicate to the image loader that the executable regions of an image can be mapped with BTI/IBT enforcement enabled. So let's import these definitions so we can use them in subsequent patches. Signed-off-by: Ard Biesheuvel --- include/linux/pe.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/include/linux/pe.h b/include/linux/pe.h index 6ffabf1e6d03..5e1e11540870 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -118,6 +118,9 @@ #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +#define IMAGE_DLLCHARACTERISTICS_EX_CET_COMPAT 0x0001 +#define IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT 0x0040 + /* they actually defined 0x00000000 as well, but I think we'll skip that one. */ #define IMAGE_SCN_RESERVED_0 0x00000001 #define IMAGE_SCN_RESERVED_1 0x00000002 @@ -165,6 +168,7 @@ #define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ #define IMAGE_DEBUG_TYPE_CODEVIEW 2 +#define IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS 20 #ifndef __ASSEMBLY__ -- GitLab From 8358098b9787caab8bbc93fd78d046afaed43c16 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:48 +0200 Subject: [PATCH 3609/5631] arm64: efi: Enable BTI codegen and add PE/COFF annotation UEFI heavily relies on so-called protocols, which are essentially tables populated with pointers to executable code, and these are invoked indirectly using BR or BLR instructions. This makes the EFI execution context vulnerable to attacks on forward edge control flow, and so it would help if we could enable hardware enforcement (BTI) on CPUs that implement it. So let's no longer disable BTI codegen for the EFI stub, and set the newly introduced PE/COFF header flag when the kernel is built with BTI landing pads. Signed-off-by: Ard Biesheuvel Reviewed-by: Mark Brown --- arch/arm64/kernel/efi-header.S | 71 ++++++++++++++++----------- drivers/firmware/efi/libstub/Makefile | 3 +- 2 files changed, 44 insertions(+), 30 deletions(-) diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S index d731b4655df8..11d7f7de202d 100644 --- a/arch/arm64/kernel/efi-header.S +++ b/arch/arm64/kernel/efi-header.S @@ -81,9 +81,47 @@ .quad 0 // CertificationTable .quad 0 // BaseRelocationTable -#ifdef CONFIG_DEBUG_EFI +#if defined(CONFIG_DEBUG_EFI) || defined(CONFIG_ARM64_BTI_KERNEL) .long .Lefi_debug_table - .L_head // DebugTable .long .Lefi_debug_table_size + + /* + * The debug table is referenced via its Relative Virtual Address (RVA), + * which is only defined for those parts of the image that are covered + * by a section declaration. Since this header is not covered by any + * section, the debug table must be emitted elsewhere. So stick it in + * the .init.rodata section instead. + * + * Note that the payloads themselves are permitted to have zero RVAs, + * which means we can simply put those right after the section headers. + */ + __INITRODATA + + .align 2 +.Lefi_debug_table: +#ifdef CONFIG_DEBUG_EFI + // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_CODEVIEW // Type + .long .Lefi_debug_entry_size // SizeOfData + .long 0 // RVA + .long .Lefi_debug_entry - .L_head // FileOffset +#endif +#ifdef CONFIG_ARM64_BTI_KERNEL + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS // Type + .long 4 // SizeOfData + .long 0 // RVA + .long .Lefi_dll_characteristics_ex - .L_head // FileOffset +#endif + .set .Lefi_debug_table_size, . - .Lefi_debug_table + .previous #endif // Section table @@ -119,33 +157,6 @@ .set .Lsection_count, (. - .Lsection_table) / 40 #ifdef CONFIG_DEBUG_EFI - /* - * The debug table is referenced via its Relative Virtual Address (RVA), - * which is only defined for those parts of the image that are covered - * by a section declaration. Since this header is not covered by any - * section, the debug table must be emitted elsewhere. So stick it in - * the .init.rodata section instead. - * - * Note that the EFI debug entry itself may legally have a zero RVA, - * which means we can simply put it right after the section headers. - */ - __INITRODATA - - .align 2 -.Lefi_debug_table: - // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY - .long 0 // Characteristics - .long 0 // TimeDateStamp - .short 0 // MajorVersion - .short 0 // MinorVersion - .long IMAGE_DEBUG_TYPE_CODEVIEW // Type - .long .Lefi_debug_entry_size // SizeOfData - .long 0 // RVA - .long .Lefi_debug_entry - .L_head // FileOffset - - .set .Lefi_debug_table_size, . - .Lefi_debug_table - .previous - .Lefi_debug_entry: // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY .ascii "NB10" // Signature @@ -157,6 +168,10 @@ .set .Lefi_debug_entry_size, . - .Lefi_debug_entry #endif +#ifdef CONFIG_ARM64_BTI_KERNEL +.Lefi_dll_characteristics_ex: + .long IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT +#endif .balign SEGMENT_ALIGN .Lefi_header_end: diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 80d85a5169fb..3abb2b357482 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -23,8 +23,7 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly # disable the stackleak plugin cflags-$(CONFIG_ARM64) += -fpie $(DISABLE_STACKLEAK_PLUGIN) \ - -fno-unwind-tables -fno-asynchronous-unwind-tables \ - $(call cc-option,-mbranch-protection=none) + -fno-unwind-tables -fno-asynchronous-unwind-tables cflags-$(CONFIG_ARM) += -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \ -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \ -DEFI_HAVE_STRCMP -fno-builtin -fpic \ -- GitLab From bca2f3a9406b89961fbc6c92c52c6fc1fd91d35f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:50 +0200 Subject: [PATCH 3610/5631] efi/zboot: Add BSS padding before compression We don't really care about the size of the decompressed image - what matters is how much space needs to be allocated for the image to execute, and this includes space for BSS that is not part of the loadable image and so it is not accounted for in the decompressed size. So let's add some zero padding to the end of the image: this compresses well, and it ensures that BSS is accounted for, and as a bonus, it will be zeroed before launching the image. Since all architectures that implement support for EFI zboot carry this value in the header in the same location, we can just grab it from the binary that is being compressed. Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/libstub/Makefile.zboot | 36 +++++++++++++++------ drivers/firmware/efi/libstub/zboot-header.S | 2 +- drivers/firmware/efi/libstub/zboot.c | 6 ++-- 3 files changed, 31 insertions(+), 13 deletions(-) diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index ccdd6a130d98..2d7877023604 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -3,6 +3,14 @@ # to be include'd by arch/$(ARCH)/boot/Makefile after setting # EFI_ZBOOT_PAYLOAD, EFI_ZBOOT_BFD_TARGET and EFI_ZBOOT_MACH_TYPE +quiet_cmd_copy_and_pad = PAD $@ + cmd_copy_and_pad = cp $< $@ && \ + truncate -s $(shell hexdump -s16 -n4 -e '"%u"' $<) $@ + +# Pad the file to the size of the uncompressed image in memory, including BSS +$(obj)/vmlinux.bin: $(obj)/$(EFI_ZBOOT_PAYLOAD) FORCE + $(call if_changed,copy_and_pad) + comp-type-$(CONFIG_KERNEL_GZIP) := gzip comp-type-$(CONFIG_KERNEL_LZ4) := lz4 comp-type-$(CONFIG_KERNEL_LZMA) := lzma @@ -10,16 +18,25 @@ comp-type-$(CONFIG_KERNEL_LZO) := lzo comp-type-$(CONFIG_KERNEL_XZ) := xzkern comp-type-$(CONFIG_KERNEL_ZSTD) := zstd22 -# Copy the SizeOfHeaders, SizeOfCode and SizeOfImage fields from the payload to -# the end of the compressed image. Note that this presupposes a PE header -# offset of 64 bytes, which is what arm64, RISC-V and LoongArch use. -quiet_cmd_compwithsize = $(quiet_cmd_$(comp-type-y)) - cmd_compwithsize = $(cmd_$(comp-type-y)) && ( \ +# in GZIP, the appended le32 carrying the uncompressed size is part of the +# format, but in other cases, we just append it at the end for convenience, +# causing the original tools to complain when checking image integrity. +# So disregard it when calculating the payload size in the zimage header. +zboot-method-y := $(comp-type-y)_with_size +zboot-size-len-y := 12 + +zboot-method-$(CONFIG_KERNEL_GZIP) := gzip +zboot-size-len-$(CONFIG_KERNEL_GZIP) := 8 + +# Copy the SizeOfHeaders and SizeOfCode fields from the payload to the end of +# the compressed image. Note that this presupposes a PE header offset of 64 +# bytes, which is what arm64, RISC-V and LoongArch use. +quiet_cmd_compwithsize = $(quiet_cmd_$(zboot-method-y)) + cmd_compwithsize = $(cmd_$(zboot-method-y)) && ( \ dd status=none if=$< bs=4 count=1 skip=37 ; \ - dd status=none if=$< bs=4 count=1 skip=23 ; \ - dd status=none if=$< bs=4 count=1 skip=36 ) >> $@ + dd status=none if=$< bs=4 count=1 skip=23 ) >> $@ -$(obj)/vmlinuz: $(obj)/$(EFI_ZBOOT_PAYLOAD) FORCE +$(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE $(call if_changed,compwithsize) OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) \ @@ -29,6 +46,7 @@ $(obj)/vmlinuz.o: $(obj)/vmlinuz FORCE AFLAGS_zboot-header.o += -DMACHINE_TYPE=IMAGE_FILE_MACHINE_$(EFI_ZBOOT_MACH_TYPE) \ -DZBOOT_EFI_PATH="\"$(realpath $(obj)/vmlinuz.efi.elf)\"" \ + -DZBOOT_SIZE_LEN=$(zboot-size-len-y) \ -DCOMP_TYPE="\"$(comp-type-y)\"" $(obj)/zboot-header.o: $(srctree)/drivers/firmware/efi/libstub/zboot-header.S FORCE @@ -44,4 +62,4 @@ OBJCOPYFLAGS_vmlinuz.efi := -O binary $(obj)/vmlinuz.efi: $(obj)/vmlinuz.efi.elf FORCE $(call if_changed,objcopy) -targets += zboot-header.o vmlinuz vmlinuz.o vmlinuz.efi.elf vmlinuz.efi +targets += zboot-header.o vmlinux.bin vmlinuz vmlinuz.o vmlinuz.efi.elf vmlinuz.efi diff --git a/drivers/firmware/efi/libstub/zboot-header.S b/drivers/firmware/efi/libstub/zboot-header.S index 445cb646eaaa..053aba073594 100644 --- a/drivers/firmware/efi/libstub/zboot-header.S +++ b/drivers/firmware/efi/libstub/zboot-header.S @@ -17,7 +17,7 @@ __efistub_efi_zboot_header: .long MZ_MAGIC .ascii "zimg" // image type .long __efistub__gzdata_start - .Ldoshdr // payload offset - .long __efistub__gzdata_size - 12 // payload size + .long __efistub__gzdata_size - ZBOOT_SIZE_LEN // payload size .long 0, 0 // reserved .asciz COMP_TYPE // compression type .org .Ldoshdr + 0x38 diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index 6105e5e2eda4..63ece4800900 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -91,12 +91,12 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) efi_info("Decompressing Linux Kernel...\n"); // SizeOfImage from the compressee's PE/COFF header - alloc_size = round_up(get_unaligned_le32(_gzdata_end - 4), + alloc_size = round_up(get_unaligned_le32(_gzdata_end - 12), EFI_ALLOC_ALIGN); // SizeOfHeaders and SizeOfCode from the compressee's PE/COFF header - code_size = get_unaligned_le32(_gzdata_end - 8) + - get_unaligned_le32(_gzdata_end - 12); + code_size = get_unaligned_le32(_gzdata_end - 4) + + get_unaligned_le32(_gzdata_end - 8); // If the architecture has a preferred address for the image, // try that first. -- GitLab From 538bc0f40b364f2c7b81f11aa163f723b138b40f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:51 +0200 Subject: [PATCH 3611/5631] efi/zboot: Set forward edge CFI compat header flag if supported Add some plumbing to the zboot EFI header generation to set the newly introduced DllCharacteristicsEx flag associated with forward edge CFI enforcement instructions (BTI on arm64, IBT on x86) x86 does not currently uses the zboot infrastructure, so let's wire it up only for arm64. Signed-off-by: Ard Biesheuvel --- arch/arm64/boot/Makefile | 1 + drivers/firmware/efi/libstub/Makefile.zboot | 9 +++- drivers/firmware/efi/libstub/zboot-header.S | 49 ++++++++++++++------- 3 files changed, 40 insertions(+), 19 deletions(-) diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index c65aee088410..ae645fda90bc 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -42,5 +42,6 @@ $(obj)/Image.zst: $(obj)/Image FORCE EFI_ZBOOT_PAYLOAD := Image EFI_ZBOOT_BFD_TARGET := elf64-littleaarch64 EFI_ZBOOT_MACH_TYPE := ARM64 +EFI_ZBOOT_FORWARD_CFI := $(CONFIG_ARM64_BTI_KERNEL) include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 2d7877023604..0a9dcc2b1373 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # to be include'd by arch/$(ARCH)/boot/Makefile after setting -# EFI_ZBOOT_PAYLOAD, EFI_ZBOOT_BFD_TARGET and EFI_ZBOOT_MACH_TYPE +# EFI_ZBOOT_PAYLOAD, EFI_ZBOOT_BFD_TARGET, EFI_ZBOOT_MACH_TYPE and +# EFI_ZBOOT_FORWARD_CFI quiet_cmd_copy_and_pad = PAD $@ cmd_copy_and_pad = cp $< $@ && \ @@ -44,10 +45,14 @@ OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) \ $(obj)/vmlinuz.o: $(obj)/vmlinuz FORCE $(call if_changed,objcopy) +aflags-zboot-header-$(EFI_ZBOOT_FORWARD_CFI) := \ + -DPE_DLL_CHAR_EX=IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT + AFLAGS_zboot-header.o += -DMACHINE_TYPE=IMAGE_FILE_MACHINE_$(EFI_ZBOOT_MACH_TYPE) \ -DZBOOT_EFI_PATH="\"$(realpath $(obj)/vmlinuz.efi.elf)\"" \ -DZBOOT_SIZE_LEN=$(zboot-size-len-y) \ - -DCOMP_TYPE="\"$(comp-type-y)\"" + -DCOMP_TYPE="\"$(comp-type-y)\"" \ + $(aflags-zboot-header-y) $(obj)/zboot-header.o: $(srctree)/drivers/firmware/efi/libstub/zboot-header.S FORCE $(call if_changed_rule,as_o_S) diff --git a/drivers/firmware/efi/libstub/zboot-header.S b/drivers/firmware/efi/libstub/zboot-header.S index 053aba073594..fb676ded47fa 100644 --- a/drivers/firmware/efi/libstub/zboot-header.S +++ b/drivers/firmware/efi/libstub/zboot-header.S @@ -78,9 +78,36 @@ __efistub_efi_zboot_header: .quad 0 // ExceptionTable .quad 0 // CertificationTable .quad 0 // BaseRelocationTable -#ifdef CONFIG_DEBUG_EFI +#if defined(PE_DLL_CHAR_EX) || defined(CONFIG_DEBUG_EFI) .long .Lefi_debug_table - .Ldoshdr // DebugTable .long .Lefi_debug_table_size + + .section ".rodata", "a" + .p2align 2 +.Lefi_debug_table: + // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY[] +#ifdef PE_DLL_CHAR_EX + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS // Type + .long 4 // SizeOfData + .long 0 // RVA + .long .Lefi_dll_characteristics_ex - .Ldoshdr // FileOffset +#endif +#ifdef CONFIG_DEBUG_EFI + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_CODEVIEW // Type + .long .Lefi_debug_entry_size // SizeOfData + .long 0 // RVA + .long .Lefi_debug_entry - .Ldoshdr // FileOffset +#endif + .set .Lefi_debug_table_size, . - .Lefi_debug_table + .previous #endif .Lsection_table: @@ -110,23 +137,11 @@ __efistub_efi_zboot_header: .set .Lsection_count, (. - .Lsection_table) / 40 +#ifdef PE_DLL_CHAR_EX +.Lefi_dll_characteristics_ex: + .long PE_DLL_CHAR_EX +#endif #ifdef CONFIG_DEBUG_EFI - .section ".rodata", "a" - .align 2 -.Lefi_debug_table: - // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY - .long 0 // Characteristics - .long 0 // TimeDateStamp - .short 0 // MajorVersion - .short 0 // MinorVersion - .long IMAGE_DEBUG_TYPE_CODEVIEW // Type - .long .Lefi_debug_entry_size // SizeOfData - .long 0 // RVA - .long .Lefi_debug_entry - .Ldoshdr // FileOffset - - .set .Lefi_debug_table_size, . - .Lefi_debug_table - .previous - .Lefi_debug_entry: // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY .ascii "NB10" // Signature -- GitLab From 57fbfb3b0b6526c9fd9c32383720ff550ace4919 Mon Sep 17 00:00:00 2001 From: Alexander Dahl Date: Tue, 18 Apr 2023 13:34:02 +0200 Subject: [PATCH 3612/5631] docs: leds: ledtrig-oneshot: Fix spelling mistake It's no comparison, but a "first this, then that" situation. Signed-off-by: Alexander Dahl Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230418113402.188391-1-ada@thorsis.com --- Documentation/leds/ledtrig-oneshot.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/leds/ledtrig-oneshot.rst b/Documentation/leds/ledtrig-oneshot.rst index 69fa3ea1d554..e044d69e9c0f 100644 --- a/Documentation/leds/ledtrig-oneshot.rst +++ b/Documentation/leds/ledtrig-oneshot.rst @@ -5,7 +5,7 @@ One-shot LED Trigger This is a LED trigger useful for signaling the user of an event where there are no clear trap points to put standard led-on and led-off settings. Using this trigger, the application needs only to signal the trigger when an event has -happened, than the trigger turns the LED on and than keeps it off for a +happened, then the trigger turns the LED on and then keeps it off for a specified amount of time. This trigger is meant to be usable both for sporadic and dense events. In the -- GitLab From a0a53f1bf1f712b6a52eae21a2f82cf44a7cfe5c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:17 +0200 Subject: [PATCH 3613/5631] pinctrl: pic32: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Switch some call to use irqd_to_hwirq() in the process. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-1-6b59a5186b00@linaro.org --- drivers/pinctrl/pinctrl-pic32.c | 36 +++++++++++++++++++++++---------- 1 file changed, 25 insertions(+), 11 deletions(-) diff --git a/drivers/pinctrl/pinctrl-pic32.c b/drivers/pinctrl/pinctrl-pic32.c index 37acfdfc2cae..dad05294fa72 100644 --- a/drivers/pinctrl/pinctrl-pic32.c +++ b/drivers/pinctrl/pinctrl-pic32.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -60,8 +61,8 @@ struct pic32_desc_function { struct pic32_gpio_bank { void __iomem *reg_base; + int instance; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; struct clk *clk; }; @@ -2008,12 +2009,14 @@ static void pic32_gpio_irq_mask(struct irq_data *data) struct pic32_gpio_bank *bank = irqd_to_bank(data); writel(BIT(PIC32_CNCON_ON), bank->reg_base + PIC32_CLR(CNCON_REG)); + gpiochip_disable_irq(&bank->gpio_chip, irqd_to_hwirq(data)); } static void pic32_gpio_irq_unmask(struct irq_data *data) { struct pic32_gpio_bank *bank = irqd_to_bank(data); + gpiochip_enable_irq(&bank->gpio_chip, irqd_to_hwirq(data)); writel(BIT(PIC32_CNCON_ON), bank->reg_base + PIC32_SET(CNCON_REG)); } @@ -2030,7 +2033,7 @@ static unsigned int pic32_gpio_irq_startup(struct irq_data *data) static int pic32_gpio_irq_set_type(struct irq_data *data, unsigned int type) { struct pic32_gpio_bank *bank = irqd_to_bank(data); - u32 mask = BIT(data->hwirq); + u32 mask = irqd_to_hwirq(data); switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_RISING: @@ -2122,14 +2125,7 @@ static void pic32_gpio_irq_handler(struct irq_desc *desc) .owner = THIS_MODULE, \ .can_sleep = 0, \ }, \ - .irq_chip = { \ - .name = "GPIO" #_bank, \ - .irq_startup = pic32_gpio_irq_startup, \ - .irq_ack = pic32_gpio_irq_ack, \ - .irq_mask = pic32_gpio_irq_mask, \ - .irq_unmask = pic32_gpio_irq_unmask, \ - .irq_set_type = pic32_gpio_irq_set_type, \ - }, \ + .instance = (_bank), \ } static struct pic32_gpio_bank pic32_gpio_banks[] = { @@ -2145,6 +2141,24 @@ static struct pic32_gpio_bank pic32_gpio_banks[] = { GPIO_BANK(9, PINS_PER_BANK), }; +static void pic32_gpio_irq_print_chip(struct irq_data *data, struct seq_file *p) +{ + struct pic32_gpio_bank *bank = irqd_to_bank(data); + + seq_printf(p, "GPIO%d", bank->instance); +} + +static const struct irq_chip pic32_gpio_irq_chip = { + .irq_startup = pic32_gpio_irq_startup, + .irq_ack = pic32_gpio_irq_ack, + .irq_mask = pic32_gpio_irq_mask, + .irq_unmask = pic32_gpio_irq_unmask, + .irq_set_type = pic32_gpio_irq_set_type, + .irq_print_chip = pic32_gpio_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int pic32_pinctrl_probe(struct platform_device *pdev) { struct pic32_pinctrl *pctl; @@ -2243,7 +2257,7 @@ static int pic32_gpio_probe(struct platform_device *pdev) bank->gpio_chip.parent = &pdev->dev; girq = &bank->gpio_chip.irq; - girq->chip = &bank->irq_chip; + gpio_irq_chip_set_chip(girq, &pic32_gpio_irq_chip); girq->parent_handler = pic32_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, 1, sizeof(*girq->parents), -- GitLab From 33c56e5ca01b85d235f464572a640ef657d53fca Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:18 +0200 Subject: [PATCH 3614/5631] pinctrl: pistachio: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-2-6b59a5186b00@linaro.org --- drivers/pinctrl/pinctrl-pistachio.c | 35 ++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index 7ca4ecb6eb8d..53408344927a 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -93,10 +94,10 @@ struct pistachio_pin_group { struct pistachio_gpio_bank { struct pistachio_pinctrl *pctl; void __iomem *base; + int instance; unsigned int pin_base; unsigned int npins; struct gpio_chip gpio_chip; - struct irq_chip irq_chip; }; struct pistachio_pinctrl { @@ -1228,12 +1229,14 @@ static void pistachio_gpio_irq_mask(struct irq_data *data) struct pistachio_gpio_bank *bank = irqd_to_bank(data); gpio_mask_writel(bank, GPIO_INTERRUPT_EN, data->hwirq, 0); + gpiochip_disable_irq(&bank->gpio_chip, irqd_to_hwirq(data)); } static void pistachio_gpio_irq_unmask(struct irq_data *data) { struct pistachio_gpio_bank *bank = irqd_to_bank(data); + gpiochip_enable_irq(&bank->gpio_chip, irqd_to_hwirq(data)); gpio_mask_writel(bank, GPIO_INTERRUPT_EN, data->hwirq, 1); } @@ -1312,6 +1315,7 @@ static void pistachio_gpio_irq_handler(struct irq_desc *desc) #define GPIO_BANK(_bank, _pin_base, _npins) \ { \ + .instance = (_bank), \ .pin_base = _pin_base, \ .npins = _npins, \ .gpio_chip = { \ @@ -1326,14 +1330,6 @@ static void pistachio_gpio_irq_handler(struct irq_desc *desc) .base = _pin_base, \ .ngpio = _npins, \ }, \ - .irq_chip = { \ - .name = "GPIO" #_bank, \ - .irq_startup = pistachio_gpio_irq_startup, \ - .irq_ack = pistachio_gpio_irq_ack, \ - .irq_mask = pistachio_gpio_irq_mask, \ - .irq_unmask = pistachio_gpio_irq_unmask, \ - .irq_set_type = pistachio_gpio_irq_set_type, \ - }, \ } static struct pistachio_gpio_bank pistachio_gpio_banks[] = { @@ -1345,6 +1341,25 @@ static struct pistachio_gpio_bank pistachio_gpio_banks[] = { GPIO_BANK(5, PISTACHIO_PIN_MFIO(80), 10), }; +static void pistachio_gpio_irq_print_chip(struct irq_data *data, + struct seq_file *p) +{ + struct pistachio_gpio_bank *bank = irqd_to_bank(data); + + seq_printf(p, "GPIO%d", bank->instance); +} + +static const struct irq_chip pistachio_gpio_irq_chip = { + .irq_startup = pistachio_gpio_irq_startup, + .irq_ack = pistachio_gpio_irq_ack, + .irq_mask = pistachio_gpio_irq_mask, + .irq_unmask = pistachio_gpio_irq_unmask, + .irq_set_type = pistachio_gpio_irq_set_type, + .irq_print_chip = pistachio_gpio_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int pistachio_gpio_register(struct pistachio_pinctrl *pctl) { struct pistachio_gpio_bank *bank; @@ -1394,7 +1409,7 @@ static int pistachio_gpio_register(struct pistachio_pinctrl *pctl) bank->gpio_chip.fwnode = child; girq = &bank->gpio_chip.irq; - girq->chip = &bank->irq_chip; + gpio_irq_chip_set_chip(girq, &pistachio_gpio_irq_chip); girq->parent_handler = pistachio_gpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(pctl->dev, 1, -- GitLab From 35d008679a5af05dcca4fac5c0e8491196a6ffdf Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:19 +0200 Subject: [PATCH 3615/5631] pinctrl: plgpio: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-3-6b59a5186b00@linaro.org --- drivers/pinctrl/spear/pinctrl-plgpio.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/spear/pinctrl-plgpio.c b/drivers/pinctrl/spear/pinctrl-plgpio.c index ada401ef4342..722681e0b89b 100644 --- a/drivers/pinctrl/spear/pinctrl-plgpio.c +++ b/drivers/pinctrl/spear/pinctrl-plgpio.c @@ -301,6 +301,7 @@ static void plgpio_irq_disable(struct irq_data *d) spin_lock_irqsave(&plgpio->lock, flags); plgpio_reg_set(plgpio->regmap, offset, plgpio->regs.ie); spin_unlock_irqrestore(&plgpio->lock, flags); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void plgpio_irq_enable(struct irq_data *d) @@ -317,6 +318,7 @@ static void plgpio_irq_enable(struct irq_data *d) return; } + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); spin_lock_irqsave(&plgpio->lock, flags); plgpio_reg_reset(plgpio->regmap, offset, plgpio->regs.ie); spin_unlock_irqrestore(&plgpio->lock, flags); @@ -356,11 +358,13 @@ static int plgpio_irq_set_type(struct irq_data *d, unsigned trigger) return 0; } -static struct irq_chip plgpio_irqchip = { +static const struct irq_chip plgpio_irqchip = { .name = "PLGPIO", .irq_enable = plgpio_irq_enable, .irq_disable = plgpio_irq_disable, .irq_set_type = plgpio_irq_set_type, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; static void plgpio_irq_handler(struct irq_desc *desc) @@ -595,7 +599,7 @@ static int plgpio_probe(struct platform_device *pdev) struct gpio_irq_chip *girq; girq = &plgpio->chip.irq; - girq->chip = &plgpio_irqchip; + gpio_irq_chip_set_chip(girq, &plgpio_irqchip); girq->parent_handler = plgpio_irq_handler; girq->num_parents = 1; girq->parents = devm_kcalloc(&pdev->dev, 1, -- GitLab From 9890a043b3d755f796f6ae14aa66cc9cecd15a68 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:20 +0200 Subject: [PATCH 3616/5631] pinctrl: qcom spmi-mpp: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-4-6b59a5186b00@linaro.org --- drivers/pinctrl/qcom/pinctrl-spmi-mpp.c | 38 ++++++++++++++++++------- 1 file changed, 28 insertions(+), 10 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c index 644fb4a0e72a..fe0393829c20 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c @@ -143,7 +143,6 @@ struct pmic_mpp_state { struct regmap *map; struct pinctrl_dev *ctrl; struct gpio_chip chip; - struct irq_chip irq; }; static const struct pinconf_generic_params pmic_mpp_bindings[] = { @@ -823,6 +822,33 @@ static int pmic_mpp_child_to_parent_hwirq(struct gpio_chip *chip, return 0; } +static void pmic_mpp_irq_mask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + irq_chip_mask_parent(d); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); +} + +static void pmic_mpp_irq_unmask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); + irq_chip_unmask_parent(d); +} + +static const struct irq_chip pmic_mpp_irq_chip = { + .name = "spmi-mpp", + .irq_ack = irq_chip_ack_parent, + .irq_mask = pmic_mpp_irq_mask, + .irq_unmask = pmic_mpp_irq_unmask, + .irq_set_type = irq_chip_set_type_parent, + .irq_set_wake = irq_chip_set_wake_parent, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int pmic_mpp_probe(struct platform_device *pdev) { struct irq_domain *parent_domain; @@ -915,16 +941,8 @@ static int pmic_mpp_probe(struct platform_device *pdev) if (!parent_domain) return -ENXIO; - state->irq.name = "spmi-mpp", - state->irq.irq_ack = irq_chip_ack_parent, - state->irq.irq_mask = irq_chip_mask_parent, - state->irq.irq_unmask = irq_chip_unmask_parent, - state->irq.irq_set_type = irq_chip_set_type_parent, - state->irq.irq_set_wake = irq_chip_set_wake_parent, - state->irq.flags = IRQCHIP_MASK_ON_SUSPEND, - girq = &state->chip.irq; - girq->chip = &state->irq; + gpio_irq_chip_set_chip(girq, &pmic_mpp_irq_chip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_level_irq; girq->fwnode = dev_fwnode(state->dev); -- GitLab From 5e75e24eb111245b1a1fd08496fc012d5e1f9e7f Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:21 +0200 Subject: [PATCH 3617/5631] pinctrl: qcom ssbi-mpp: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-5-6b59a5186b00@linaro.org --- drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c | 35 +++++++++++++++++++------ 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c index 86f66cb8bf30..b5aed540f07e 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c @@ -126,7 +126,6 @@ struct pm8xxx_mpp { struct regmap *regmap; struct pinctrl_dev *pctrl; struct gpio_chip chip; - struct irq_chip irq; struct pinctrl_desc desc; unsigned npins; @@ -778,6 +777,32 @@ static int pm8xxx_mpp_child_to_parent_hwirq(struct gpio_chip *chip, return 0; } +static void pm8xxx_mpp_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); +} + +static void pm8xxx_mpp_irq_enable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); +} + +static const struct irq_chip pm8xxx_mpp_irq_chip = { + .name = "ssbi-mpp", + .irq_mask_ack = irq_chip_mask_ack_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_disable = pm8xxx_mpp_irq_disable, + .irq_enable = pm8xxx_mpp_irq_enable, + .irq_set_type = irq_chip_set_type_parent, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static const struct of_device_id pm8xxx_mpp_of_match[] = { { .compatible = "qcom,pm8018-mpp", .data = (void *) 6 }, { .compatible = "qcom,pm8038-mpp", .data = (void *) 6 }, @@ -871,14 +896,8 @@ static int pm8xxx_mpp_probe(struct platform_device *pdev) if (!parent_domain) return -ENXIO; - pctrl->irq.name = "ssbi-mpp"; - pctrl->irq.irq_mask_ack = irq_chip_mask_ack_parent; - pctrl->irq.irq_unmask = irq_chip_unmask_parent; - pctrl->irq.irq_set_type = irq_chip_set_type_parent; - pctrl->irq.flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE; - girq = &pctrl->chip.irq; - girq->chip = &pctrl->irq; + gpio_irq_chip_set_chip(girq, &pm8xxx_mpp_irq_chip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_level_irq; girq->fwnode = dev_fwnode(pctrl->dev); -- GitLab From 19bcff7e2777c7337caeef5532ad6f93f3d24d64 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Apr 2023 16:06:22 +0200 Subject: [PATCH 3618/5631] pinctrl: qcom ssbi-gpio: Convert to immutable irq_chip Convert the driver to immutable irq-chip with a bit of intuition. Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20230414-immutable-irqchips-2-v1-6-6b59a5186b00@linaro.org --- drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c index e973001e5c88..dec1ffc49ffd 100644 --- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c @@ -652,12 +652,30 @@ static int pm8xxx_pin_populate(struct pm8xxx_gpio *pctrl, return 0; } -static struct irq_chip pm8xxx_irq_chip = { +static void pm8xxx_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); +} + +static void pm8xxx_irq_enable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); +} + +static const struct irq_chip pm8xxx_irq_chip = { .name = "ssbi-gpio", .irq_mask_ack = irq_chip_mask_ack_parent, .irq_unmask = irq_chip_unmask_parent, + .irq_disable = pm8xxx_irq_disable, + .irq_enable = pm8xxx_irq_enable, .irq_set_type = irq_chip_set_type_parent, - .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, }; static int pm8xxx_domain_translate(struct irq_domain *domain, @@ -788,7 +806,7 @@ static int pm8xxx_gpio_probe(struct platform_device *pdev) return -ENXIO; girq = &pctrl->chip.irq; - girq->chip = &pm8xxx_irq_chip; + gpio_irq_chip_set_chip(girq, &pm8xxx_irq_chip); girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_level_irq; girq->fwnode = dev_fwnode(pctrl->dev); -- GitLab From 2f2c0911b950794dbf394ee2d784138fbf714dbd Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Thu, 23 Feb 2023 17:22:36 +0100 Subject: [PATCH 3619/5631] KVM: s390: interrupt: fix virtual-physical confusion for next alert GISA We sometimes put a virtual address in next_alert, which should always be a physical address, since it is shared with hardware. This currently works, because virtual and physical addresses are the same. Add phys_to_virt() to resolve the virtual-physical confusion. Signed-off-by: Nico Boehr Reviewed-by: Janosch Frank Reviewed-by: Michael Mueller Signed-off-by: Janosch Frank Link: https://lore.kernel.org/r/20230223162236.51569-1-nrb@linux.ibm.com Message-Id: <20230223162236.51569-1-nrb@linux.ibm.com> --- arch/s390/kvm/interrupt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 9250fde1f97d..da6dac36e959 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -305,7 +305,7 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi) static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa) { - return READ_ONCE(gisa->next_alert) != (u32)(u64)gisa; + return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa); } static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) @@ -3168,7 +3168,7 @@ void kvm_s390_gisa_init(struct kvm *kvm) hrtimer_init(&gi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); gi->timer.function = gisa_vcpu_kicker; memset(gi->origin, 0, sizeof(struct kvm_s390_gisa)); - gi->origin->next_alert = (u32)(u64)gi->origin; + gi->origin->next_alert = (u32)virt_to_phys(gi->origin); VM_EVENT(kvm, 3, "gisa 0x%pK initialized", gi->origin); } -- GitLab From 7be3e3392335131b2234fa3e6feda3e989cb837c Mon Sep 17 00:00:00 2001 From: Pierre Morel Date: Tue, 14 Feb 2023 13:28:41 +0100 Subject: [PATCH 3620/5631] KVM: s390: vsie: clarifications on setting the APCB The APCB is part of the CRYCB. The calculation of the APCB origin can be done by adding the APCB offset to the CRYCB origin. Current code makes confusing transformations, converting the CRYCB origin to a pointer to calculate the APCB origin. Let's make things simpler and keep the CRYCB origin to make these calculations. Signed-off-by: Pierre Morel Reviewed-by: Claudio Imbrenda Acked-by: David Hildenbrand Acked-by: Janosch Frank Signed-off-by: Janosch Frank Link: https://lore.kernel.org/r/20230214122841.13066-2-pmorel@linux.ibm.com Message-Id: <20230214122841.13066-2-pmorel@linux.ibm.com> --- arch/s390/kvm/vsie.c | 50 +++++++++++++++++++++++++------------------- 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index b6a0219e470a..8d6b765abf29 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -138,11 +138,15 @@ static int prepare_cpuflags(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) } /* Copy to APCB FORMAT1 from APCB FORMAT0 */ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s, - unsigned long apcb_o, struct kvm_s390_apcb1 *apcb_h) + unsigned long crycb_gpa, struct kvm_s390_apcb1 *apcb_h) { struct kvm_s390_apcb0 tmp; + unsigned long apcb_gpa; - if (read_guest_real(vcpu, apcb_o, &tmp, sizeof(struct kvm_s390_apcb0))) + apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0); + + if (read_guest_real(vcpu, apcb_gpa, &tmp, + sizeof(struct kvm_s390_apcb0))) return -EFAULT; apcb_s->apm[0] = apcb_h->apm[0] & tmp.apm[0]; @@ -157,15 +161,19 @@ static int setup_apcb10(struct kvm_vcpu *vcpu, struct kvm_s390_apcb1 *apcb_s, * setup_apcb00 - Copy to APCB FORMAT0 from APCB FORMAT0 * @vcpu: pointer to the virtual CPU * @apcb_s: pointer to start of apcb in the shadow crycb - * @apcb_o: pointer to start of original apcb in the guest2 + * @crycb_gpa: guest physical address to start of original guest crycb * @apcb_h: pointer to start of apcb in the guest1 * * Returns 0 and -EFAULT on error reading guest apcb */ static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s, - unsigned long apcb_o, unsigned long *apcb_h) + unsigned long crycb_gpa, unsigned long *apcb_h) { - if (read_guest_real(vcpu, apcb_o, apcb_s, + unsigned long apcb_gpa; + + apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb0); + + if (read_guest_real(vcpu, apcb_gpa, apcb_s, sizeof(struct kvm_s390_apcb0))) return -EFAULT; @@ -178,16 +186,20 @@ static int setup_apcb00(struct kvm_vcpu *vcpu, unsigned long *apcb_s, * setup_apcb11 - Copy the FORMAT1 APCB from the guest to the shadow CRYCB * @vcpu: pointer to the virtual CPU * @apcb_s: pointer to start of apcb in the shadow crycb - * @apcb_o: pointer to start of original guest apcb + * @crycb_gpa: guest physical address to start of original guest crycb * @apcb_h: pointer to start of apcb in the host * * Returns 0 and -EFAULT on error reading guest apcb */ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s, - unsigned long apcb_o, + unsigned long crycb_gpa, unsigned long *apcb_h) { - if (read_guest_real(vcpu, apcb_o, apcb_s, + unsigned long apcb_gpa; + + apcb_gpa = crycb_gpa + offsetof(struct kvm_s390_crypto_cb, apcb1); + + if (read_guest_real(vcpu, apcb_gpa, apcb_s, sizeof(struct kvm_s390_apcb1))) return -EFAULT; @@ -200,7 +212,7 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s, * setup_apcb - Create a shadow copy of the apcb. * @vcpu: pointer to the virtual CPU * @crycb_s: pointer to shadow crycb - * @crycb_o: pointer to original guest crycb + * @crycb_gpa: guest physical address of original guest crycb * @crycb_h: pointer to the host crycb * @fmt_o: format of the original guest crycb. * @fmt_h: format of the host crycb. @@ -211,50 +223,46 @@ static int setup_apcb11(struct kvm_vcpu *vcpu, unsigned long *apcb_s, * Return 0 or an error number if the guest and host crycb are incompatible. */ static int setup_apcb(struct kvm_vcpu *vcpu, struct kvm_s390_crypto_cb *crycb_s, - const u32 crycb_o, + const u32 crycb_gpa, struct kvm_s390_crypto_cb *crycb_h, int fmt_o, int fmt_h) { - struct kvm_s390_crypto_cb *crycb; - - crycb = (struct kvm_s390_crypto_cb *) (unsigned long)crycb_o; - switch (fmt_o) { case CRYCB_FORMAT2: - if ((crycb_o & PAGE_MASK) != ((crycb_o + 256) & PAGE_MASK)) + if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 256) & PAGE_MASK)) return -EACCES; if (fmt_h != CRYCB_FORMAT2) return -EINVAL; return setup_apcb11(vcpu, (unsigned long *)&crycb_s->apcb1, - (unsigned long) &crycb->apcb1, + crycb_gpa, (unsigned long *)&crycb_h->apcb1); case CRYCB_FORMAT1: switch (fmt_h) { case CRYCB_FORMAT2: return setup_apcb10(vcpu, &crycb_s->apcb1, - (unsigned long) &crycb->apcb0, + crycb_gpa, &crycb_h->apcb1); case CRYCB_FORMAT1: return setup_apcb00(vcpu, (unsigned long *) &crycb_s->apcb0, - (unsigned long) &crycb->apcb0, + crycb_gpa, (unsigned long *) &crycb_h->apcb0); } break; case CRYCB_FORMAT0: - if ((crycb_o & PAGE_MASK) != ((crycb_o + 32) & PAGE_MASK)) + if ((crycb_gpa & PAGE_MASK) != ((crycb_gpa + 32) & PAGE_MASK)) return -EACCES; switch (fmt_h) { case CRYCB_FORMAT2: return setup_apcb10(vcpu, &crycb_s->apcb1, - (unsigned long) &crycb->apcb0, + crycb_gpa, &crycb_h->apcb1); case CRYCB_FORMAT1: case CRYCB_FORMAT0: return setup_apcb00(vcpu, (unsigned long *) &crycb_s->apcb0, - (unsigned long) &crycb->apcb0, + crycb_gpa, (unsigned long *) &crycb_h->apcb0); } } -- GitLab From 8a46df7cd135fe576c18efa418cd1549e51f2732 Mon Sep 17 00:00:00 2001 From: Nico Boehr Date: Wed, 22 Feb 2023 16:55:02 +0100 Subject: [PATCH 3621/5631] KVM: s390: pci: fix virtual-physical confusion on module unload/load When the kvm module is unloaded, zpci_setup_aipb() perists some data in the zpci_aipb structure in s390 pci code. Note that this struct is also passed to firmware in the zpci_set_irq_ctrl() call and thus the GAIT must be a physical address. On module re-insertion, the GAIT is restored from this structure in zpci_reset_aipb(). But it is a physical address, hence this may cause issues when the kvm module is unloaded and loaded again. Fix virtual vs physical address confusion (which currently are the same) by adding the necessary physical-to-virtual-conversion in zpci_reset_aipb(). Signed-off-by: Nico Boehr Reviewed-by: Matthew Rosato Signed-off-by: Janosch Frank Link: https://lore.kernel.org/r/20230222155503.43399-1-nrb@linux.ibm.com Message-Id: <20230222155503.43399-1-nrb@linux.ibm.com> --- arch/s390/kvm/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index b124d586db55..7dab00f1e833 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -112,7 +112,7 @@ static int zpci_reset_aipb(u8 nisc) return -EINVAL; aift->sbv = zpci_aif_sbv; - aift->gait = (struct zpci_gaite *)zpci_aipb->aipb.gait; + aift->gait = phys_to_virt(zpci_aipb->aipb.gait); return 0; } -- GitLab From 9be6ab181b7b8d6114e225ae3c7c01bb6380cf8a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Thu, 20 Apr 2023 10:18:12 -0700 Subject: [PATCH 3622/5631] libperf rc_check: Enable implicitly with sanitizers If using leak sanitizer then implicitly enable reference count checking. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230420171812.561603-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/perf/include/internal/rc_check.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/lib/perf/include/internal/rc_check.h b/tools/lib/perf/include/internal/rc_check.h index c0626d8beb59..d5d771ccdc7b 100644 --- a/tools/lib/perf/include/internal/rc_check.h +++ b/tools/lib/perf/include/internal/rc_check.h @@ -5,6 +5,14 @@ #include #include +/* + * Enable reference count checking implicitly with leak checking, which is + * integrated into address sanitizer. + */ +#if defined(LEAK_SANITIZER) || defined(ADDRESS_SANITIZER) +#define REFCNT_CHECKING 1 +#endif + /* * Shared reference count checking macros. * -- GitLab From ce1831fe2febf7a3a03fda43b41d7589caa022cd Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 12 Feb 2023 20:32:04 +0100 Subject: [PATCH 3623/5631] um: add __weak for exported functions If the exported glibc functions don't exist, we get link failures. Avoid that by adding __weak so they're allowed to not exist. Reported-by: Randy Dunlap Signed-off-by: Johannes Berg Acked-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Richard Weinberger --- arch/um/os-Linux/user_syms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index fd575ecbcaec..54722c7f884f 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -39,7 +39,7 @@ EXPORT_SYMBOL(printf); * good; so the versions of these symbols will always match */ #define EXPORT_SYMBOL_PROTO(sym) \ - int sym(void); \ + int sym(void) __weak; \ EXPORT_SYMBOL(sym); extern void readdir64(void) __attribute__((weak)); -- GitLab From 8c6174503c7b7134c22072b45f92724c8a959f06 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 Feb 2023 22:05:08 +0100 Subject: [PATCH 3624/5631] um: hostfs: define our own API boundary Instead of exporting the set of functions provided by glibc that are needed for hostfs_user.c, just build that into the kernel image whenever hostfs is built, and then export _those_ functions cleanly, to be independent of the libc implementation. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/os-Linux/user_syms.c | 70 ------------------------------------ fs/Makefile | 2 +- fs/hostfs/Makefile | 6 ++-- fs/hostfs/hostfs_user_exp.c | 28 +++++++++++++++ 4 files changed, 33 insertions(+), 73 deletions(-) create mode 100644 fs/hostfs/hostfs_user_exp.c diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 54722c7f884f..22ed13a9b3e7 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -34,81 +34,11 @@ EXPORT_SYMBOL(memset); EXPORT_SYMBOL(printf); -/* Here, instead, I can provide a fake prototype. Yes, someone cares: genksyms. - * However, the modules will use the CRC defined *here*, no matter if it is - * good; so the versions of these symbols will always match - */ -#define EXPORT_SYMBOL_PROTO(sym) \ - int sym(void) __weak; \ - EXPORT_SYMBOL(sym); - -extern void readdir64(void) __attribute__((weak)); -EXPORT_SYMBOL(readdir64); -extern void truncate64(void) __attribute__((weak)); -EXPORT_SYMBOL(truncate64); - #ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA EXPORT_SYMBOL(vsyscall_ehdr); EXPORT_SYMBOL(vsyscall_end); #endif -EXPORT_SYMBOL_PROTO(__errno_location); - -EXPORT_SYMBOL_PROTO(access); -EXPORT_SYMBOL_PROTO(open); -EXPORT_SYMBOL_PROTO(open64); -EXPORT_SYMBOL_PROTO(close); -EXPORT_SYMBOL_PROTO(read); -EXPORT_SYMBOL_PROTO(write); -EXPORT_SYMBOL_PROTO(dup2); -EXPORT_SYMBOL_PROTO(__xstat); -EXPORT_SYMBOL_PROTO(__lxstat); -EXPORT_SYMBOL_PROTO(__lxstat64); -EXPORT_SYMBOL_PROTO(__fxstat64); -EXPORT_SYMBOL_PROTO(lseek); -EXPORT_SYMBOL_PROTO(lseek64); -EXPORT_SYMBOL_PROTO(chown); -EXPORT_SYMBOL_PROTO(fchown); -EXPORT_SYMBOL_PROTO(truncate); -EXPORT_SYMBOL_PROTO(ftruncate64); -EXPORT_SYMBOL_PROTO(utime); -EXPORT_SYMBOL_PROTO(utimes); -EXPORT_SYMBOL_PROTO(futimes); -EXPORT_SYMBOL_PROTO(chmod); -EXPORT_SYMBOL_PROTO(fchmod); -EXPORT_SYMBOL_PROTO(rename); -EXPORT_SYMBOL_PROTO(__xmknod); - -EXPORT_SYMBOL_PROTO(symlink); -EXPORT_SYMBOL_PROTO(link); -EXPORT_SYMBOL_PROTO(unlink); -EXPORT_SYMBOL_PROTO(readlink); - -EXPORT_SYMBOL_PROTO(mkdir); -EXPORT_SYMBOL_PROTO(rmdir); -EXPORT_SYMBOL_PROTO(opendir); -EXPORT_SYMBOL_PROTO(readdir); -EXPORT_SYMBOL_PROTO(closedir); -EXPORT_SYMBOL_PROTO(seekdir); -EXPORT_SYMBOL_PROTO(telldir); - -EXPORT_SYMBOL_PROTO(ioctl); - -EXPORT_SYMBOL_PROTO(pread64); -EXPORT_SYMBOL_PROTO(pwrite64); - -EXPORT_SYMBOL_PROTO(statfs); -EXPORT_SYMBOL_PROTO(statfs64); - -EXPORT_SYMBOL_PROTO(getuid); - -EXPORT_SYMBOL_PROTO(fsync); -EXPORT_SYMBOL_PROTO(fdatasync); - -EXPORT_SYMBOL_PROTO(lstat64); -EXPORT_SYMBOL_PROTO(fstat64); -EXPORT_SYMBOL_PROTO(mknod); - /* Export symbols used by GCC for the stack protector. */ extern void __stack_smash_handler(void *) __attribute__((weak)); EXPORT_SYMBOL(__stack_smash_handler); diff --git a/fs/Makefile b/fs/Makefile index 05f89b5c962f..a07631f932bb 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -124,7 +124,7 @@ obj-$(CONFIG_9P_FS) += 9p/ obj-$(CONFIG_AFS_FS) += afs/ obj-$(CONFIG_NILFS2_FS) += nilfs2/ obj-$(CONFIG_BEFS_FS) += befs/ -obj-$(CONFIG_HOSTFS) += hostfs/ +obj-y += hostfs/ obj-$(CONFIG_CACHEFILES) += cachefiles/ obj-$(CONFIG_DEBUG_FS) += debugfs/ obj-$(CONFIG_TRACING) += tracefs/ diff --git a/fs/hostfs/Makefile b/fs/hostfs/Makefile index 587bcd6e50a3..16be592e8085 100644 --- a/fs/hostfs/Makefile +++ b/fs/hostfs/Makefile @@ -3,9 +3,11 @@ # Licensed under the GPL # -hostfs-objs := hostfs_kern.o hostfs_user.o +hostfs-objs := hostfs_kern.o -obj-y := +hostfs-builtin-$(CONFIG_HOSTFS) += hostfs_user.o hostfs_user_exp.o + +obj-y := $(hostfs-builtin-y) $(hostfs-builtin-m) obj-$(CONFIG_HOSTFS) += hostfs.o include $(srctree)/arch/um/scripts/Makefile.rules diff --git a/fs/hostfs/hostfs_user_exp.c b/fs/hostfs/hostfs_user_exp.c new file mode 100644 index 000000000000..250c91c55c46 --- /dev/null +++ b/fs/hostfs/hostfs_user_exp.c @@ -0,0 +1,28 @@ +#include +#include "hostfs.h" + +EXPORT_SYMBOL_GPL(stat_file); +EXPORT_SYMBOL_GPL(access_file); +EXPORT_SYMBOL_GPL(open_file); +EXPORT_SYMBOL_GPL(open_dir); +EXPORT_SYMBOL_GPL(seek_dir); +EXPORT_SYMBOL_GPL(read_dir); +EXPORT_SYMBOL_GPL(read_file); +EXPORT_SYMBOL_GPL(write_file); +EXPORT_SYMBOL_GPL(lseek_file); +EXPORT_SYMBOL_GPL(fsync_file); +EXPORT_SYMBOL_GPL(replace_file); +EXPORT_SYMBOL_GPL(close_file); +EXPORT_SYMBOL_GPL(close_dir); +EXPORT_SYMBOL_GPL(file_create); +EXPORT_SYMBOL_GPL(set_attr); +EXPORT_SYMBOL_GPL(make_symlink); +EXPORT_SYMBOL_GPL(unlink_file); +EXPORT_SYMBOL_GPL(do_mkdir); +EXPORT_SYMBOL_GPL(hostfs_do_rmdir); +EXPORT_SYMBOL_GPL(do_mknod); +EXPORT_SYMBOL_GPL(link_file); +EXPORT_SYMBOL_GPL(hostfs_do_readlink); +EXPORT_SYMBOL_GPL(rename_file); +EXPORT_SYMBOL_GPL(rename2_file); +EXPORT_SYMBOL_GPL(do_statfs); -- GitLab From 6d708d1a0d81fe85a114766ff6beb3037fa77429 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 Feb 2023 22:05:09 +0100 Subject: [PATCH 3625/5631] um: don't export printf() Since printf() cannot be used in kernel threads (it uses too much stack space) don't export it for modules either. This should leave us exporting only things that are absolutely critical (such as memset and friends) and things that are injected by the compiler (stack guard and similar.) Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/os-Linux/user_syms.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 22ed13a9b3e7..1e9e92740b32 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -18,7 +18,6 @@ extern size_t strlen(const char *); extern void *memmove(void *, const void *, size_t); extern void *memset(void *, int, size_t); -extern int printf(const char *, ...); /* If it's not defined, the export is included in lib/string.c.*/ #ifdef __HAVE_ARCH_STRSTR @@ -32,8 +31,6 @@ EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memset); #endif -EXPORT_SYMBOL(printf); - #ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA EXPORT_SYMBOL(vsyscall_ehdr); EXPORT_SYMBOL(vsyscall_end); -- GitLab From 5d90cf6dcc6a4cb85a51ffe007a8e34375799164 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 Feb 2023 22:05:10 +0100 Subject: [PATCH 3626/5631] um: further clean up user_syms Make some cleanups, add and fix some comments and document here that we shouldn't export (libc) symbols for "_user.c" code, rather such should work like hostfs does now. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/os-Linux/user_syms.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/arch/um/os-Linux/user_syms.c b/arch/um/os-Linux/user_syms.c index 1e9e92740b32..9b62a9d352b3 100644 --- a/arch/um/os-Linux/user_syms.c +++ b/arch/um/os-Linux/user_syms.c @@ -3,35 +3,36 @@ #include #include -/* Some of this are builtin function (some are not but could in the future), - * so I *must* declare good prototypes for them and then EXPORT them. - * The kernel code uses the macro defined by include/linux/string.h, - * so I undef macros; the userspace code does not include that and I - * add an EXPORT for the glibc one. +/* + * This file exports some critical string functions and compiler + * built-in functions (where calls are emitted by the compiler + * itself that we cannot avoid even in kernel code) to modules. + * + * "_user.c" code that previously used exports here such as hostfs + * really should be considered part of the 'hypervisor' and define + * its own API boundary like hostfs does now; don't add exports to + * this file for such cases. */ -#undef strlen -#undef strstr -#undef memcpy -#undef memset - -extern size_t strlen(const char *); -extern void *memmove(void *, const void *, size_t); -extern void *memset(void *, int, size_t); - /* If it's not defined, the export is included in lib/string.c.*/ #ifdef __HAVE_ARCH_STRSTR +#undef strstr EXPORT_SYMBOL(strstr); #endif #ifndef __x86_64__ +#undef memcpy extern void *memcpy(void *, const void *, size_t); EXPORT_SYMBOL(memcpy); +extern void *memmove(void *, const void *, size_t); EXPORT_SYMBOL(memmove); +#undef memset +extern void *memset(void *, int, size_t); EXPORT_SYMBOL(memset); #endif #ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA +/* needed for __access_ok() */ EXPORT_SYMBOL(vsyscall_ehdr); EXPORT_SYMBOL(vsyscall_end); #endif @@ -44,6 +45,6 @@ extern long __guard __attribute__((weak)); EXPORT_SYMBOL(__guard); #ifdef _FORTIFY_SOURCE -extern int __sprintf_chk(char *str, int flag, size_t strlen, const char *format); +extern int __sprintf_chk(char *str, int flag, size_t len, const char *format); EXPORT_SYMBOL(__sprintf_chk); #endif -- GitLab From fc54a4f15988e228cf88f888483e985c5f35031e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 Feb 2023 22:05:11 +0100 Subject: [PATCH 3627/5631] um: prevent user code in modules By not doing the user code cflags mangling we can simply break the build for any user code sneaking into modules. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/scripts/Makefile.rules | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/um/scripts/Makefile.rules b/arch/um/scripts/Makefile.rules index a4dfa7d7636e..a8b7d9dab0a6 100644 --- a/arch/um/scripts/Makefile.rules +++ b/arch/um/scripts/Makefile.rules @@ -4,8 +4,8 @@ # =========================================================================== USER_SINGLE_OBJS := \ - $(foreach f,$(patsubst %.o,%,$(obj-y) $(obj-m)),$($(f)-objs)) -USER_OBJS += $(filter %_user.o,$(obj-y) $(obj-m) $(USER_SINGLE_OBJS)) + $(foreach f,$(patsubst %.o,%,$(obj-y)),$($(f)-objs)) +USER_OBJS += $(filter %_user.o,$(obj-y) $(USER_SINGLE_OBJS)) USER_OBJS := $(foreach file,$(USER_OBJS),$(obj)/$(file)) $(USER_OBJS:.o=.%): \ -- GitLab From 6032aca0deb9c138df122192f8ef02de1fdccf25 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 14 Apr 2023 15:46:39 +0200 Subject: [PATCH 3628/5631] um: make stub data pages size tweakable There's a lot of code here that hard-codes that the data is a single page, and right now that seems to be sufficient, but to make it easier to change this in the future, add a new STUB_DATA_PAGES constant and use it throughout the code. Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/include/shared/as-layout.h | 3 ++- arch/um/kernel/skas/clone.c | 5 +++-- arch/um/kernel/skas/mmu.c | 6 +++--- arch/um/kernel/um_arch.c | 10 +++++++--- arch/um/os-Linux/skas/process.c | 6 +++--- arch/x86/um/shared/sysdep/stub_32.h | 8 ++++---- arch/x86/um/shared/sysdep/stub_64.h | 8 ++++---- arch/x86/um/stub_segv.c | 2 +- 8 files changed, 27 insertions(+), 21 deletions(-) diff --git a/arch/um/include/shared/as-layout.h b/arch/um/include/shared/as-layout.h index 9a0bd648d872..9ec3015bc5e2 100644 --- a/arch/um/include/shared/as-layout.h +++ b/arch/um/include/shared/as-layout.h @@ -23,7 +23,8 @@ #define STUB_START stub_start #define STUB_CODE STUB_START #define STUB_DATA (STUB_CODE + UM_KERN_PAGE_SIZE) -#define STUB_END (STUB_DATA + UM_KERN_PAGE_SIZE) +#define STUB_DATA_PAGES 1 /* must be a power of two */ +#define STUB_END (STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE) #ifndef __ASSEMBLY__ diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c index ff5061f29167..62435187dda4 100644 --- a/arch/um/kernel/skas/clone.c +++ b/arch/um/kernel/skas/clone.c @@ -24,11 +24,12 @@ void __attribute__ ((__section__ (".__syscall_stub"))) stub_clone_handler(void) { - struct stub_data *data = get_stub_page(); + struct stub_data *data = get_stub_data(); long err; err = stub_syscall2(__NR_clone, CLONE_PARENT | CLONE_FILES | SIGCHLD, - (unsigned long)data + UM_KERN_PAGE_SIZE / 2); + (unsigned long)data + + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE / 2); if (err) { data->parent_err = err; goto done; diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c index 125df465e8ea..656fe16c9b63 100644 --- a/arch/um/kernel/skas/mmu.c +++ b/arch/um/kernel/skas/mmu.c @@ -21,7 +21,7 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) unsigned long stack = 0; int ret = -ENOMEM; - stack = get_zeroed_page(GFP_KERNEL); + stack = __get_free_pages(GFP_KERNEL | __GFP_ZERO, ilog2(STUB_DATA_PAGES)); if (stack == 0) goto out; @@ -52,7 +52,7 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm) out_free: if (to_mm->id.stack != 0) - free_page(to_mm->id.stack); + free_pages(to_mm->id.stack, ilog2(STUB_DATA_PAGES)); out: return ret; } @@ -74,6 +74,6 @@ void destroy_context(struct mm_struct *mm) } os_kill_ptraced_process(mmu->id.u.pid, 1); - free_page(mmu->id.stack); + free_pages(mmu->id.stack, ilog2(STUB_DATA_PAGES)); free_ldt(mmu); } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8dcda617b8bf..0a23a98d4ca0 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -326,9 +326,13 @@ int __init linux_main(int argc, char **argv) add_arg(DEFAULT_COMMAND_LINE_CONSOLE); host_task_size = os_get_top_address(); - /* reserve two pages for the stubs */ - host_task_size -= 2 * PAGE_SIZE; - stub_start = host_task_size; + /* reserve a few pages for the stubs (taking care of data alignment) */ + /* align the data portion */ + BUILD_BUG_ON(!is_power_of_2(STUB_DATA_PAGES)); + stub_start = (host_task_size - 1) & ~(STUB_DATA_PAGES * PAGE_SIZE - 1); + /* another page for the code portion */ + stub_start -= PAGE_SIZE; + host_task_size = stub_start; /* * TASK_SIZE needs to be PGDIR_SIZE aligned or else exit_mmap craps diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index b1ea53285af1..9464833e741a 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -262,7 +262,7 @@ static int userspace_tramp(void *stack) if (stack != NULL) { fd = phys_mapping(uml_to_phys(stack), &offset); addr = mmap((void *) STUB_DATA, - UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE, + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE, MAP_FIXED | MAP_SHARED, fd, offset); if (addr == MAP_FAILED) { printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n", @@ -277,7 +277,7 @@ static int userspace_tramp(void *stack) (unsigned long) stub_segv_handler - (unsigned long) __syscall_stub_start; - set_sigstack((void *) STUB_DATA, UM_KERN_PAGE_SIZE); + set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE); sigemptyset(&sa.sa_mask); sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO; sa.sa_sigaction = (void *) v; @@ -515,7 +515,7 @@ static int __init init_thread_regs(void) thread_regs[REGS_IP_INDEX] = STUB_CODE + (unsigned long) stub_clone_handler - (unsigned long) __syscall_stub_start; - thread_regs[REGS_SP_INDEX] = STUB_DATA + UM_KERN_PAGE_SIZE - + thread_regs[REGS_SP_INDEX] = STUB_DATA + STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - sizeof(void *); #ifdef __SIGNAL_FRAMESIZE thread_regs[REGS_SP_INDEX] -= __SIGNAL_FRAMESIZE; diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 4c6c2be0c899..38fa894b65d0 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -89,19 +89,19 @@ static inline void remap_stack_and_trap(void) "addl %4,%%ebx ; movl %%eax, (%%ebx) ;" "int $3" : : - "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), "g" (STUB_MMAP_NR), "g" (UML_STUB_FIELD_FD), "g" (UML_STUB_FIELD_OFFSET), "g" (UML_STUB_FIELD_CHILD_ERR), - "c" (UM_KERN_PAGE_SIZE), + "c" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), "d" (PROT_READ | PROT_WRITE), "S" (MAP_FIXED | MAP_SHARED) : "memory"); } -static __always_inline void *get_stub_page(void) +static __always_inline void *get_stub_data(void) { unsigned long ret; @@ -109,7 +109,7 @@ static __always_inline void *get_stub_page(void) "movl %%esp,%0 ;" "andl %1,%0" : "=a" (ret) - : "g" (~(UM_KERN_PAGE_SIZE - 1))); + : "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1))); return (void *)ret; } diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 92ea1670cf1c..2de1c8f88173 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -98,18 +98,18 @@ static inline void remap_stack_and_trap(void) "int3" : : "g" (STUB_MMAP_NR), - "g" (~(UM_KERN_PAGE_SIZE - 1)), + "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)), "g" (MAP_FIXED | MAP_SHARED), "g" (UML_STUB_FIELD_FD), "g" (UML_STUB_FIELD_OFFSET), "g" (UML_STUB_FIELD_CHILD_ERR), - "S" (UM_KERN_PAGE_SIZE), + "S" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE), "d" (PROT_READ | PROT_WRITE) : __syscall_clobber, "r10", "r8", "r9"); } -static __always_inline void *get_stub_page(void) +static __always_inline void *get_stub_data(void) { unsigned long ret; @@ -117,7 +117,7 @@ static __always_inline void *get_stub_page(void) "movq %%rsp,%0 ;" "andq %1,%0" : "=a" (ret) - : "g" (~(UM_KERN_PAGE_SIZE - 1))); + : "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1))); return (void *)ret; } diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c index f7eefba034f9..040668b989b5 100644 --- a/arch/x86/um/stub_segv.c +++ b/arch/x86/um/stub_segv.c @@ -11,7 +11,7 @@ void __attribute__ ((__section__ (".__syscall_stub"))) stub_segv_handler(int sig, siginfo_t *info, void *p) { - struct faultinfo *f = get_stub_page(); + struct faultinfo *f = get_stub_data(); ucontext_t *uc = p; GET_FAULTINFO_FROM_MC(*f, &uc->uc_mcontext); -- GitLab From 52a7f2deb4be8706bcbd16bba1d70eb2b5735d19 Mon Sep 17 00:00:00 2001 From: Benno Lossin Date: Thu, 13 Apr 2023 10:02:17 +0000 Subject: [PATCH 3629/5631] rust: init: broaden the blanket impl of `Init` This makes it possible to use `T` as a `impl Init` for every error type `E` instead of just `Infallible`. Signed-off-by: Benno Lossin Reviewed-by: Gary Guo Reviewed-by: Martin Rodriguez Reboredo Link: https://lore.kernel.org/r/20230413100157.740697-1-benno.lossin@proton.me Signed-off-by: Miguel Ojeda --- rust/kernel/init.rs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index a1298c8bbda0..4ebfb08dab11 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -1190,8 +1190,8 @@ pub fn uninit() -> impl Init, E> { } // SAFETY: Every type can be initialized by-value. -unsafe impl Init for T { - unsafe fn __init(self, slot: *mut T) -> Result<(), Infallible> { +unsafe impl Init for T { + unsafe fn __init(self, slot: *mut T) -> Result<(), E> { unsafe { slot.write(self) }; Ok(()) } -- GitLab From b0cf5d50210df982878df53ab465e4377ea07065 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 13 Apr 2023 00:18:22 +0200 Subject: [PATCH 3630/5631] MAINTAINERS: add Benno Lossin as Rust reviewer Benno has been involved with the Rust for Linux project for the better part of a year now. He has been working on solving the safe pinned initialization problem [1], which resulted in the pin-init API patch series [2] that allows to reduce the need for `unsafe` code in the kernel. He is also working on the field projection RFC for Rust [3] to bring pin-init as a language feature. His expertise with the language will be very useful to have around in the future if Rust grows within the kernel, thus add him to the `RUST` entry as reviewer. Link: https://rust-for-linux.com/the-safe-pinned-initialization-problem [1] Link: https://lore.kernel.org/rust-for-linux/20230408122429.1103522-1-y86-dev@protonmail.com/ [2] Link: https://github.com/rust-lang/rfcs/pull/3318 [3] Cc: Benno Lossin Reviewed-by: Alex Gaynor Link: https://lore.kernel.org/r/20230412221823.830135-1-ojeda@kernel.org Signed-off-by: Miguel Ojeda --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 90abe83c02f3..bf9deaa4aa5a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18225,6 +18225,7 @@ M: Wedson Almeida Filho R: Boqun Feng R: Gary Guo R: Björn Roy Baron +R: Benno Lossin L: rust-for-linux@vger.kernel.org S: Supported W: https://github.com/Rust-for-Linux/linux -- GitLab From 6ea5aa08857a81be7114b3c21d6aa6db0bc95f99 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:31 -0300 Subject: [PATCH 3631/5631] rust: sync: introduce `LockClassKey` It is a wrapper around C's `lock_class_key`, which is used by the synchronisation primitives that are checked with lockdep. This is in preparation for introducing Rust abstractions for these primitives. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Reviewed-by: Martin Rodriguez Reboredo Co-developed-by: Boqun Feng Signed-off-by: Boqun Feng Signed-off-by: Wedson Almeida Filho Reviewed-by: Gary Guo Reviewed-by: Benno Lossin Link: https://lore.kernel.org/r/20230411054543.21278-1-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/sync.rs | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 33da23e3076d..541d235ffbeb 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -5,6 +5,51 @@ //! This module contains the kernel APIs related to synchronisation that have been ported or //! wrapped for usage by Rust code in the kernel. +use crate::types::Opaque; + mod arc; pub use arc::{Arc, ArcBorrow, UniqueArc}; + +/// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. +#[repr(transparent)] +pub struct LockClassKey(Opaque); + +// SAFETY: `bindings::lock_class_key` is designed to be used concurrently from multiple threads and +// provides its own synchronization. +unsafe impl Sync for LockClassKey {} + +impl LockClassKey { + /// Creates a new lock class key. + pub const fn new() -> Self { + Self(Opaque::uninit()) + } + + #[allow(dead_code)] + pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key { + self.0.get() + } +} + +/// Defines a new static lock class and returns a pointer to it. +#[doc(hidden)] +#[macro_export] +macro_rules! static_lock_class { + () => {{ + static CLASS: $crate::sync::LockClassKey = $crate::sync::LockClassKey::new(); + &CLASS + }}; +} + +/// Returns the given string, if one is provided, otherwise generates one based on the source code +/// location. +#[doc(hidden)] +#[macro_export] +macro_rules! optional_name { + () => { + $crate::c_str!(::core::concat!(::core::file!(), ":", ::core::line!())) + }; + ($name:literal) => { + $crate::c_str!($name) + }; +} -- GitLab From 9c318a1d9b5000c77527011f158a75c5483510f5 Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 20 Apr 2023 15:49:06 -0700 Subject: [PATCH 3632/5631] Drivers: hv: move panic report code from vmbus to hv early init code The panic reporting code was added in commit 81b18bce48af ("Drivers: HV: Send one page worth of kmsg dump over Hyper-V during panic") It was added to the vmbus driver. The panic reporting has no dependence on vmbus, and can be enabled at an earlier boot time when Hyper-V is initialized. This patch moves the panic reporting code out of vmbus. There is no functionality changes. During moving, also refactored some cleanup functions into hv_kmsg_dump_unregister(). Signed-off-by: Long Li Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1682030946-6372-1-git-send-email-longli@linuxonhyperv.com Signed-off-by: Wei Liu --- drivers/hv/hv.c | 36 ------- drivers/hv/hv_common.c | 231 +++++++++++++++++++++++++++++++++++++++++ drivers/hv/vmbus_drv.c | 199 ----------------------------------- 3 files changed, 231 insertions(+), 235 deletions(-) diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 4e1407d59ba0..de6708dbe0df 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -38,42 +38,6 @@ int hv_init(void) return 0; } -/* - * Functions for allocating and freeing memory with size and - * alignment HV_HYP_PAGE_SIZE. These functions are needed because - * the guest page size may not be the same as the Hyper-V page - * size. We depend upon kmalloc() aligning power-of-two size - * allocations to the allocation size boundary, so that the - * allocated memory appears to Hyper-V as a page of the size - * it expects. - */ - -void *hv_alloc_hyperv_page(void) -{ - BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); - - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL); - else - return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); -} - -void *hv_alloc_hyperv_zeroed_page(void) -{ - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - else - return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); -} - -void hv_free_hyperv_page(unsigned long addr) -{ - if (PAGE_SIZE == HV_HYP_PAGE_SIZE) - free_page(addr); - else - kfree((void *)addr); -} - /* * hv_post_message - Post a message using the hypervisor message IPC. * diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 6d40b6c7b23b..64f9ceca887b 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -17,8 +17,11 @@ #include #include #include +#include #include #include +#include +#include #include #include #include @@ -54,6 +57,10 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); void * __percpu *hyperv_pcpu_output_arg; EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg); +static void hv_kmsg_dump_unregister(void); + +static struct ctl_table_header *hv_ctl_table_hdr; + /* * Hyper-V specific initialization and shutdown code that is * common across all architectures. Called from architecture @@ -62,6 +69,12 @@ EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg); void __init hv_common_free(void) { + unregister_sysctl_table(hv_ctl_table_hdr); + hv_ctl_table_hdr = NULL; + + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) + hv_kmsg_dump_unregister(); + kfree(hv_vp_index); hv_vp_index = NULL; @@ -72,10 +85,203 @@ void __init hv_common_free(void) hyperv_pcpu_input_arg = NULL; } +/* + * Functions for allocating and freeing memory with size and + * alignment HV_HYP_PAGE_SIZE. These functions are needed because + * the guest page size may not be the same as the Hyper-V page + * size. We depend upon kmalloc() aligning power-of-two size + * allocations to the allocation size boundary, so that the + * allocated memory appears to Hyper-V as a page of the size + * it expects. + */ + +void *hv_alloc_hyperv_page(void) +{ + BUILD_BUG_ON(PAGE_SIZE < HV_HYP_PAGE_SIZE); + + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + return (void *)__get_free_page(GFP_KERNEL); + else + return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_page); + +void *hv_alloc_hyperv_zeroed_page(void) +{ + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + else + return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(hv_alloc_hyperv_zeroed_page); + +void hv_free_hyperv_page(unsigned long addr) +{ + if (PAGE_SIZE == HV_HYP_PAGE_SIZE) + free_page(addr); + else + kfree((void *)addr); +} +EXPORT_SYMBOL_GPL(hv_free_hyperv_page); + +static void *hv_panic_page; + +/* + * Boolean to control whether to report panic messages over Hyper-V. + * + * It can be set via /proc/sys/kernel/hyperv_record_panic_msg + */ +static int sysctl_record_panic_msg = 1; + +/* + * sysctl option to allow the user to control whether kmsg data should be + * reported to Hyper-V on panic. + */ +static struct ctl_table hv_ctl_table[] = { + { + .procname = "hyperv_record_panic_msg", + .data = &sysctl_record_panic_msg, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + {} +}; + +static int hv_die_panic_notify_crash(struct notifier_block *self, + unsigned long val, void *args); + +static struct notifier_block hyperv_die_report_block = { + .notifier_call = hv_die_panic_notify_crash, +}; + +static struct notifier_block hyperv_panic_report_block = { + .notifier_call = hv_die_panic_notify_crash, +}; + +/* + * The following callback works both as die and panic notifier; its + * goal is to provide panic information to the hypervisor unless the + * kmsg dumper is used [see hv_kmsg_dump()], which provides more + * information but isn't always available. + * + * Notice that both the panic/die report notifiers are registered only + * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set. + */ +static int hv_die_panic_notify_crash(struct notifier_block *self, + unsigned long val, void *args) +{ + struct pt_regs *regs; + bool is_die; + + /* Don't notify Hyper-V unless we have a die oops event or panic. */ + if (self == &hyperv_panic_report_block) { + is_die = false; + regs = current_pt_regs(); + } else { /* die event */ + if (val != DIE_OOPS) + return NOTIFY_DONE; + + is_die = true; + regs = ((struct die_args *)args)->regs; + } + + /* + * Hyper-V should be notified only once about a panic/die. If we will + * be calling hv_kmsg_dump() later with kmsg data, don't do the + * notification here. + */ + if (!sysctl_record_panic_msg || !hv_panic_page) + hyperv_report_panic(regs, val, is_die); + + return NOTIFY_DONE; +} + +/* + * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg + * buffer and call into Hyper-V to transfer the data. + */ +static void hv_kmsg_dump(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + struct kmsg_dump_iter iter; + size_t bytes_written; + + /* We are only interested in panics. */ + if (reason != KMSG_DUMP_PANIC || !sysctl_record_panic_msg) + return; + + /* + * Write dump contents to the page. No need to synchronize; panic should + * be single-threaded. + */ + kmsg_dump_rewind(&iter); + kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, + &bytes_written); + if (!bytes_written) + return; + /* + * P3 to contain the physical address of the panic page & P4 to + * contain the size of the panic data in that page. Rest of the + * registers are no-op when the NOTIFY_MSG flag is set. + */ + hv_set_register(HV_REGISTER_CRASH_P0, 0); + hv_set_register(HV_REGISTER_CRASH_P1, 0); + hv_set_register(HV_REGISTER_CRASH_P2, 0); + hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); + + /* + * Let Hyper-V know there is crash data available along with + * the panic message. + */ + hv_set_register(HV_REGISTER_CRASH_CTL, + (HV_CRASH_CTL_CRASH_NOTIFY | + HV_CRASH_CTL_CRASH_NOTIFY_MSG)); +} + +static struct kmsg_dumper hv_kmsg_dumper = { + .dump = hv_kmsg_dump, +}; + +static void hv_kmsg_dump_unregister(void) +{ + kmsg_dump_unregister(&hv_kmsg_dumper); + unregister_die_notifier(&hyperv_die_report_block); + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_report_block); + + hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_panic_page = NULL; +} + +static void hv_kmsg_dump_register(void) +{ + int ret; + + hv_panic_page = hv_alloc_hyperv_zeroed_page(); + if (!hv_panic_page) { + pr_err("Hyper-V: panic message page memory allocation failed\n"); + return; + } + + ret = kmsg_dump_register(&hv_kmsg_dumper); + if (ret) { + pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); + hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_panic_page = NULL; + } +} + int __init hv_common_init(void) { int i; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Hyper-V expects to get crash register data or kmsg when * crash enlightment is available and system crashes. Set @@ -84,8 +290,33 @@ int __init hv_common_init(void) * kernel. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { + u64 hyperv_crash_ctl; + crash_kexec_post_notifiers = true; pr_info("Hyper-V: enabling crash_kexec_post_notifiers\n"); + + /* + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. + */ + hv_ctl_table_hdr = register_sysctl("kernel", hv_ctl_table); + if (!hv_ctl_table_hdr) + pr_err("Hyper-V: sysctl table register error"); + + /* + * Register for panic kmsg callback only if the right + * capability is supported by the hypervisor. + */ + hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); + if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) + hv_kmsg_dump_register(); + + register_die_notifier(&hyperv_die_report_block); + atomic_notifier_chain_register(&panic_notifier_list, + &hyperv_panic_report_block); } /* diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 19a0069dc4a9..309c78ce1d30 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include @@ -50,26 +49,12 @@ static struct device *hv_dev; static int hyperv_cpuhp_online; -static void *hv_panic_page; - static long __percpu *vmbus_evt; /* Values parsed from ACPI DSDT */ int vmbus_irq; int vmbus_interrupt; -/* - * Boolean to control whether to report panic messages over Hyper-V. - * - * It can be set via /proc/sys/kernel/hyperv_record_panic_msg - */ -static int sysctl_record_panic_msg = 1; - -static int hyperv_report_reg(void) -{ - return !sysctl_record_panic_msg || !hv_panic_page; -} - /* * The panic notifier below is responsible solely for unloading the * vmbus connection, which is necessary in a panic event. @@ -90,54 +75,6 @@ static struct notifier_block hyperv_panic_vmbus_unload_block = { .priority = INT_MIN + 1, /* almost the latest one to execute */ }; -static int hv_die_panic_notify_crash(struct notifier_block *self, - unsigned long val, void *args); - -static struct notifier_block hyperv_die_report_block = { - .notifier_call = hv_die_panic_notify_crash, -}; -static struct notifier_block hyperv_panic_report_block = { - .notifier_call = hv_die_panic_notify_crash, -}; - -/* - * The following callback works both as die and panic notifier; its - * goal is to provide panic information to the hypervisor unless the - * kmsg dumper is used [see hv_kmsg_dump()], which provides more - * information but isn't always available. - * - * Notice that both the panic/die report notifiers are registered only - * if we have the capability HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE set. - */ -static int hv_die_panic_notify_crash(struct notifier_block *self, - unsigned long val, void *args) -{ - struct pt_regs *regs; - bool is_die; - - /* Don't notify Hyper-V unless we have a die oops event or panic. */ - if (self == &hyperv_panic_report_block) { - is_die = false; - regs = current_pt_regs(); - } else { /* die event */ - if (val != DIE_OOPS) - return NOTIFY_DONE; - - is_die = true; - regs = ((struct die_args *)args)->regs; - } - - /* - * Hyper-V should be notified only once about a panic/die. If we will - * be calling hv_kmsg_dump() later with kmsg data, don't do the - * notification here. - */ - if (hyperv_report_reg()) - hyperv_report_panic(regs, val, is_die); - - return NOTIFY_DONE; -} - static const char *fb_mmio_name = "fb_range"; static struct resource *fb_mmio; static struct resource *hyperv_mmio; @@ -1379,98 +1316,6 @@ static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id) return IRQ_HANDLED; } -/* - * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg - * buffer and call into Hyper-V to transfer the data. - */ -static void hv_kmsg_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason) -{ - struct kmsg_dump_iter iter; - size_t bytes_written; - - /* We are only interested in panics. */ - if ((reason != KMSG_DUMP_PANIC) || (!sysctl_record_panic_msg)) - return; - - /* - * Write dump contents to the page. No need to synchronize; panic should - * be single-threaded. - */ - kmsg_dump_rewind(&iter); - kmsg_dump_get_buffer(&iter, false, hv_panic_page, HV_HYP_PAGE_SIZE, - &bytes_written); - if (!bytes_written) - return; - /* - * P3 to contain the physical address of the panic page & P4 to - * contain the size of the panic data in that page. Rest of the - * registers are no-op when the NOTIFY_MSG flag is set. - */ - hv_set_register(HV_REGISTER_CRASH_P0, 0); - hv_set_register(HV_REGISTER_CRASH_P1, 0); - hv_set_register(HV_REGISTER_CRASH_P2, 0); - hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); - hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); - - /* - * Let Hyper-V know there is crash data available along with - * the panic message. - */ - hv_set_register(HV_REGISTER_CRASH_CTL, - (HV_CRASH_CTL_CRASH_NOTIFY | HV_CRASH_CTL_CRASH_NOTIFY_MSG)); -} - -static struct kmsg_dumper hv_kmsg_dumper = { - .dump = hv_kmsg_dump, -}; - -static void hv_kmsg_dump_register(void) -{ - int ret; - - hv_panic_page = hv_alloc_hyperv_zeroed_page(); - if (!hv_panic_page) { - pr_err("Hyper-V: panic message page memory allocation failed\n"); - return; - } - - ret = kmsg_dump_register(&hv_kmsg_dumper); - if (ret) { - pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); - hv_free_hyperv_page((unsigned long)hv_panic_page); - hv_panic_page = NULL; - } -} - -static struct ctl_table_header *hv_ctl_table_hdr; - -/* - * sysctl option to allow the user to control whether kmsg data should be - * reported to Hyper-V on panic. - */ -static struct ctl_table hv_ctl_table[] = { - { - .procname = "hyperv_record_panic_msg", - .data = &sysctl_record_panic_msg, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE - }, - {} -}; - -static struct ctl_table hv_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = hv_ctl_table - }, - {} -}; - /* * vmbus_bus_init -Main vmbus driver initialization routine. * @@ -1534,38 +1379,6 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; - if (hv_is_isolation_supported()) - sysctl_record_panic_msg = 0; - - /* - * Only register if the crash MSRs are available - */ - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { - u64 hyperv_crash_ctl; - /* - * Panic message recording (sysctl_record_panic_msg) - * is enabled by default in non-isolated guests and - * disabled by default in isolated guests; the panic - * message recording won't be available in isolated - * guests should the following registration fail. - */ - hv_ctl_table_hdr = register_sysctl_table(hv_root_table); - if (!hv_ctl_table_hdr) - pr_err("Hyper-V: sysctl table register error"); - - /* - * Register for panic kmsg callback only if the right - * capability is supported by the hypervisor. - */ - hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); - if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) - hv_kmsg_dump_register(); - - register_die_notifier(&hyperv_die_report_block); - atomic_notifier_chain_register(&panic_notifier_list, - &hyperv_panic_report_block); - } - /* * Always register the vmbus unload panic notifier because we * need to shut the VMbus channel connection on panic. @@ -1590,8 +1403,6 @@ static int vmbus_bus_init(void) } err_setup: bus_unregister(&hv_bus); - unregister_sysctl_table(hv_ctl_table_hdr); - hv_ctl_table_hdr = NULL; return ret; } @@ -2887,13 +2698,6 @@ static void __exit vmbus_exit(void) vmbus_free_channels(); kfree(vmbus_connection.channels); - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { - kmsg_dump_unregister(&hv_kmsg_dumper); - unregister_die_notifier(&hyperv_die_report_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_report_block); - } - /* * The vmbus panic notifier is always registered, hence we should * also unconditionally unregister it here as well. @@ -2901,9 +2705,6 @@ static void __exit vmbus_exit(void) atomic_notifier_chain_unregister(&panic_notifier_list, &hyperv_panic_vmbus_unload_block); - free_page((unsigned long)hv_panic_page); - unregister_sysctl_table(hv_ctl_table_hdr); - hv_ctl_table_hdr = NULL; bus_unregister(&hv_bus); cpuhp_remove_state(hyperv_cpuhp_online); -- GitLab From 211db0ac9e3dc6c46f2dd53395b34d76af929faf Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 16 Mar 2023 07:34:33 +0900 Subject: [PATCH 3633/5631] ksmbd: remove internal.h include Since vfs_path_lookup is exported, It should not be internal. Move vfs_path_lookup prototype in internal.h to linux/namei.h. Suggested-by: Al Viro Reviewed-by: Christian Brauner Signed-off-by: Namjae Jeon Signed-off-by: Al Viro --- fs/internal.h | 2 -- fs/ksmbd/vfs.c | 2 -- include/linux/namei.h | 2 ++ 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/internal.h b/fs/internal.h index dc4eb91a577a..071a7517f1a7 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -59,8 +59,6 @@ extern int finish_clean_context(struct fs_context *fc); */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root); -extern int vfs_path_lookup(struct dentry *, struct vfsmount *, - const char *, unsigned int, struct path *); int do_rmdir(int dfd, struct filename *name); int do_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 5ea9229dad2c..cef07d7fb7dc 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -19,8 +19,6 @@ #include #include -#include "../internal.h" /* for vfs_path_lookup */ - #include "glob.h" #include "oplock.h" #include "connection.h" diff --git a/include/linux/namei.h b/include/linux/namei.h index 0d797f3367ca..ba9b32b4d1b0 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -63,6 +63,8 @@ extern struct dentry *kern_path_create(int, const char *, struct path *, unsigne extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, + unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); -- GitLab From 9bc37e04823b5280dd0f22b6680fc23fe81ca325 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 16 Mar 2023 07:34:34 +0900 Subject: [PATCH 3634/5631] fs: introduce lock_rename_child() helper Pass the dentry of a source file and the dentry of a destination directory to lock parent inodes for rename. As soon as this function returns, ->d_parent of the source file dentry is stable and inodes are properly locked for calling vfs-rename. This helper is needed for ksmbd server. rename request of SMB protocol has to rename an opened file, no matter which directory it's in. Signed-off-by: Al Viro Signed-off-by: Namjae Jeon Signed-off-by: Al Viro --- fs/namei.c | 68 ++++++++++++++++++++++++++++++++++++------- include/linux/namei.h | 1 + 2 files changed, 58 insertions(+), 11 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index edfedfbccaef..6bc1964e2214 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2980,20 +2980,10 @@ static inline int may_create(struct mnt_idmap *idmap, return inode_permission(idmap, dir, MAY_WRITE | MAY_EXEC); } -/* - * p1 and p2 should be directories on the same fs. - */ -struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) +static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) { struct dentry *p; - if (p1 == p2) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - return NULL; - } - - mutex_lock(&p1->d_sb->s_vfs_rename_mutex); - p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); @@ -3012,8 +3002,64 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return NULL; } + +/* + * p1 and p2 should be directories on the same fs. + */ +struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) +{ + if (p1 == p2) { + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + return NULL; + } + + mutex_lock(&p1->d_sb->s_vfs_rename_mutex); + return lock_two_directories(p1, p2); +} EXPORT_SYMBOL(lock_rename); +/* + * c1 and p2 should be on the same fs. + */ +struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) +{ + if (READ_ONCE(c1->d_parent) == p2) { + /* + * hopefully won't need to touch ->s_vfs_rename_mutex at all. + */ + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + /* + * now that p2 is locked, nobody can move in or out of it, + * so the test below is safe. + */ + if (likely(c1->d_parent == p2)) + return NULL; + + /* + * c1 got moved out of p2 while we'd been taking locks; + * unlock and fall back to slow case. + */ + inode_unlock(p2->d_inode); + } + + mutex_lock(&c1->d_sb->s_vfs_rename_mutex); + /* + * nobody can move out of any directories on this fs. + */ + if (likely(c1->d_parent != p2)) + return lock_two_directories(c1->d_parent, p2); + + /* + * c1 got moved into p2 while we were taking locks; + * we need p2 locked and ->s_vfs_rename_mutex unlocked, + * for consistency with lock_rename(). + */ + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); + mutex_unlock(&c1->d_sb->s_vfs_rename_mutex); + return NULL; +} +EXPORT_SYMBOL(lock_rename_child); + void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); diff --git a/include/linux/namei.h b/include/linux/namei.h index ba9b32b4d1b0..5864e4d82e56 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -83,6 +83,7 @@ extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); +extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); extern int __must_check nd_jump_link(const struct path *path); -- GitLab From 39674be56fba1cd3a03bf4617f523a35f85fd2c1 Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Thu, 20 Apr 2023 14:27:58 -0700 Subject: [PATCH 3635/5631] usb: dwc3: gadget: Execute gadget stop after halting the controller Do not call gadget stop until the poll for controller halt is completed. DEVTEN is cleared as part of gadget stop, so the intention to allow ep0 events to continue while waiting for controller halt is not happening. Fixes: c96683798e27 ("usb: dwc3: ep0: Don't prepare beyond Setup stage") Cc: stable@vger.kernel.org Acked-by: Thinh Nguyen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20230420212759.29429-2-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 9f492c8a7d0b..dd6057bad37e 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2637,7 +2637,6 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) * bit. */ dwc3_stop_active_transfers(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); /* @@ -2674,7 +2673,19 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) * remaining event generated by the controller while polling for * DSTS.DEVCTLHLT. */ - return dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_run_stop(dwc, false); + + /* + * Stop the gadget after controller is halted, so that if needed, the + * events to update EP0 state can still occur while the run/stop + * routine polls for the halted state. DEVTEN is cleared as part of + * gadget stop. + */ + spin_lock_irqsave(&dwc->lock, flags); + __dwc3_gadget_stop(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + + return ret; } static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) -- GitLab From 8f40fc0808137c157dd408d2632e63bfca2aecdb Mon Sep 17 00:00:00 2001 From: Wesley Cheng Date: Thu, 20 Apr 2023 14:27:59 -0700 Subject: [PATCH 3636/5631] usb: dwc3: gadget: Refactor EP0 forced stall/restart into a separate API Several sequences utilize the same routine for forcing the control endpoint back into the SETUP phase. This is required, because those operations need to ensure that EP0 is back in the default state. Acked-by: Thinh Nguyen Signed-off-by: Wesley Cheng Link: https://lore.kernel.org/r/20230420212759.29429-3-quic_wcheng@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 53 ++++++++++++++++----------------------- 1 file changed, 21 insertions(+), 32 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index dd6057bad37e..c0ca4d12f95d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -139,6 +139,24 @@ int dwc3_gadget_set_link_state(struct dwc3 *dwc, enum dwc3_link_state state) return -ETIMEDOUT; } +static void dwc3_ep0_reset_state(struct dwc3 *dwc) +{ + unsigned int dir; + + if (dwc->ep0state != EP0_SETUP_PHASE) { + dir = !!dwc->ep0_expect_in; + if (dwc->ep0state == EP0_DATA_PHASE) + dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); + else + dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); + + dwc->eps[0]->trb_enqueue = 0; + dwc->eps[1]->trb_enqueue = 0; + + dwc3_ep0_stall_and_restart(dwc); + } +} + /** * dwc3_ep_inc_trb - increment a trb index. * @index: Pointer to the TRB index to increment. @@ -2652,16 +2670,9 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) ret = wait_for_completion_timeout(&dwc->ep0_in_setup, msecs_to_jiffies(DWC3_PULL_UP_TIMEOUT)); if (ret == 0) { - unsigned int dir; - dev_warn(dwc->dev, "wait for SETUP phase timed out\n"); spin_lock_irqsave(&dwc->lock, flags); - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - dwc3_ep0_stall_and_restart(dwc); + dwc3_ep0_reset_state(dwc); spin_unlock_irqrestore(&dwc->lock, flags); } } @@ -3944,16 +3955,7 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_gadget_enable_linksts_evts(dwc, false); usb_gadget_set_state(dwc->gadget, USB_STATE_NOTATTACHED); - if (dwc->ep0state != EP0_SETUP_PHASE) { - unsigned int dir; - - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - dwc3_ep0_stall_and_restart(dwc); - } + dwc3_ep0_reset_state(dwc); } static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) @@ -4007,20 +4009,7 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) * phase. So ensure that EP0 is in setup phase by issuing a stall * and restart if EP0 is not in setup phase. */ - if (dwc->ep0state != EP0_SETUP_PHASE) { - unsigned int dir; - - dir = !!dwc->ep0_expect_in; - if (dwc->ep0state == EP0_DATA_PHASE) - dwc3_ep0_end_control_data(dwc, dwc->eps[dir]); - else - dwc3_ep0_end_control_data(dwc, dwc->eps[!dir]); - - dwc->eps[0]->trb_enqueue = 0; - dwc->eps[1]->trb_enqueue = 0; - - dwc3_ep0_stall_and_restart(dwc); - } + dwc3_ep0_reset_state(dwc); /* * In the Synopsis DesignWare Cores USB3 Databook Rev. 3.30a -- GitLab From 22db99d673641d37c4e184ca8cff95d8441986af Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Wed, 29 Mar 2023 18:23:34 +1100 Subject: [PATCH 3637/5631] powerpc/Makefile: Add generated defconfigs to help output Currently none of the generated defconfigs appear in the help output, because the help text discovers defconfigs by looking for actual files named "*_defconfig". Collect the generated defconfig names into a variable and then print those out in archhelp. Output looks like eg: pseries_le_defconfig - Build for pseries_le ppc64le_defconfig - Build for ppc64le ppc64le_guest_defconfig - Build for ppc64le_guest ... ppc64_randconfig - Build for ppc64_randconfig adder875_defconfig - Build for adder875 amigaone_defconfig - Build for amigaone Signed-off-by: Michael Ellerman [mpe: Fix PHONY bug which broke in-tree build, thanks rmclure] Link: https://msgid.link/20230329072334.2023357-2-mpe@ellerman.id.au --- arch/powerpc/Makefile | 42 ++++++++++++++++++++++++------------------ 1 file changed, 24 insertions(+), 18 deletions(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 15c5f4c06614..85eb8e31b503 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -247,90 +247,93 @@ bootwrapper_install: $(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@) include $(srctree)/scripts/Makefile.defconf -PHONY += pseries_le_defconfig + +generated_configs += pseries_le_defconfig pseries_le_defconfig: $(call merge_into_defconfig,pseries_defconfig,le) -PHONY += ppc64le_defconfig +generated_configs += ppc64le_defconfig ppc64le_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le) -PHONY += ppc64le_guest_defconfig +generated_configs += ppc64le_guest_defconfig ppc64le_guest_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le guest) -PHONY += ppc64_guest_defconfig +generated_configs += ppc64_guest_defconfig ppc64_guest_defconfig: $(call merge_into_defconfig,ppc64_defconfig,be guest) -PHONY += powernv_be_defconfig +generated_configs += powernv_be_defconfig powernv_be_defconfig: $(call merge_into_defconfig,powernv_defconfig,be) -PHONY += mpc85xx_defconfig +generated_configs += mpc85xx_defconfig mpc85xx_defconfig: $(call merge_into_defconfig,mpc85xx_base.config,\ 85xx-32bit 85xx-hw fsl-emb-nonhw) -PHONY += mpc85xx_smp_defconfig +generated_configs += mpc85xx_smp_defconfig mpc85xx_smp_defconfig: $(call merge_into_defconfig,mpc85xx_base.config,\ 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw) -PHONY += corenet32_smp_defconfig +generated_configs += corenet32_smp_defconfig corenet32_smp_defconfig: $(call merge_into_defconfig,corenet_base.config,\ 85xx-32bit 85xx-smp 85xx-hw fsl-emb-nonhw dpaa) -PHONY += corenet64_smp_defconfig +generated_configs += corenet64_smp_defconfig corenet64_smp_defconfig: $(call merge_into_defconfig,corenet_base.config,\ 85xx-64bit 85xx-smp altivec 85xx-hw fsl-emb-nonhw dpaa) -PHONY += mpc86xx_defconfig +generated_configs += mpc86xx_defconfig mpc86xx_defconfig: $(call merge_into_defconfig,mpc86xx_base.config,\ 86xx-hw fsl-emb-nonhw) -PHONY += mpc86xx_smp_defconfig +generated_configs += mpc86xx_smp_defconfig mpc86xx_smp_defconfig: $(call merge_into_defconfig,mpc86xx_base.config,\ 86xx-smp 86xx-hw fsl-emb-nonhw) -PHONY += ppc32_allmodconfig +generated_configs += ppc32_allmodconfig ppc32_allmodconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/book3s_32.config \ -f $(srctree)/Makefile allmodconfig -PHONY += ppc_defconfig +generated_configs += ppc_defconfig ppc_defconfig: $(call merge_into_defconfig,book3s_32.config,) -PHONY += ppc64le_allmodconfig +generated_configs += ppc64le_allmodconfig ppc64le_allmodconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/le.config \ -f $(srctree)/Makefile allmodconfig -PHONY += ppc64le_allnoconfig +generated_configs += ppc64le_allnoconfig ppc64le_allnoconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/ppc64le.config \ -f $(srctree)/Makefile allnoconfig -PHONY += ppc64_book3e_allmodconfig +generated_configs += ppc64_book3e_allmodconfig ppc64_book3e_allmodconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/85xx-64bit.config \ -f $(srctree)/Makefile allmodconfig -PHONY += ppc32_randconfig +generated_configs += ppc32_randconfig ppc32_randconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/32-bit.config \ -f $(srctree)/Makefile randconfig -PHONY += ppc64_randconfig +generated_configs += ppc64_randconfig ppc64_randconfig: $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/powerpc/configs/64-bit.config \ -f $(srctree)/Makefile randconfig +PHONY += $(generated_configs) + define archhelp echo '* zImage - Build default images selected by kernel config' echo ' zImage.* - Compressed kernel image (arch/$(ARCH)/boot/zImage.*)' @@ -351,6 +354,9 @@ define archhelp echo ' support passing a device tree directly. Replace
with the' echo ' name of a dts file from the arch/$(ARCH)/boot/dts/ directory' echo ' (minus the .dts extension).' + echo + $(foreach cfg,$(generated_configs), + printf " %-27s - Build for %s\\n" $(cfg) $(subst _defconfig,,$(cfg));) endef PHONY += install -- GitLab From cc876c7a245979e3e860da66a693fc5d94543010 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:44 +1000 Subject: [PATCH 3638/5631] powerpc/configs/64s: Update defconfig for symbol movement Update ppc64_defconfig to account for symbols moving around, no actual changes. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-1-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 42 ++++++++++++++-------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index d6949a6c5b2b..1028b90ce121 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -3,6 +3,8 @@ CONFIG_POSIX_MQUEUE=y # CONFIG_CONTEXT_TRACKING_USER_FORCE is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y CONFIG_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y @@ -21,8 +23,6 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y CONFIG_BLK_DEV_INITRD=y -CONFIG_BPF_SYSCALL=y -# CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_PPC64=y CONFIG_NR_CPUS=2048 @@ -54,15 +54,9 @@ CONFIG_CRASH_DUMP=y CONFIG_FA_DUMP=y CONFIG_IRQ_ALL_CPUS=y CONFIG_SCHED_SMT=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_RPA=m -CONFIG_HOTPLUG_PCI_RPA_DLPAR=m -CONFIG_PCCARD=y -CONFIG_ELECTRA_CF=y CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_VHOST_NET=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_MODULES=y @@ -71,6 +65,7 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=m +# CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -98,7 +93,11 @@ CONFIG_NET_SCHED=y CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y CONFIG_NET_ACT_BPF=m -CONFIG_BPF_JIT=y +CONFIG_HOTPLUG_PCI=y +CONFIG_HOTPLUG_PCI_RPA=m +CONFIG_HOTPLUG_PCI_RPA_DLPAR=m +CONFIG_PCCARD=y +CONFIG_ELECTRA_CF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_FD=y @@ -267,9 +266,9 @@ CONFIG_LEDS_POWERNV=m CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m -CONFIG_INFINIBAND_MTHCA=m CONFIG_INFINIBAND_CXGB4=m CONFIG_MLX4_INFINIBAND=m +CONFIG_INFINIBAND_MTHCA=m CONFIG_INFINIBAND_IPOIB=m CONFIG_INFINIBAND_IPOIB_CM=y CONFIG_INFINIBAND_SRP=m @@ -280,8 +279,9 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=y CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m -CONFIG_LIBNVDIMM=y +CONFIG_VHOST_NET=m CONFIG_RAS=y +CONFIG_LIBNVDIMM=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -336,38 +336,38 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_CRC32C_VPMSUM=m -CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m +CONFIG_CRYPTO_CRC32C_VPMSUM=m +CONFIG_CRYPTO_MD5_PPC=m +CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y CONFIG_PRINTK_TIME=y CONFIG_PRINTK_CALLER=y -CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y CONFIG_FUNCTION_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_SCHED_TRACER=y CONFIG_STACK_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y -- GitLab From 91c4ef9539c439af454674b0a617f1b855056066 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:45 +1000 Subject: [PATCH 3639/5631] powerpc/configs/64s: Drop SPLPAR which is default y SPLPAR is default y since commit 20c0e8269e9d ("powerpc/pseries: Implement paravirt qspinlocks for SPLPAR"), so doesn't need to be in the defconfig. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-2-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 1028b90ce121..0a3a2fefb652 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -26,7 +26,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y CONFIG_PPC64=y CONFIG_NR_CPUS=2048 -CONFIG_PPC_SPLPAR=y CONFIG_DTL=y CONFIG_PPC_SMLPAR=y CONFIG_IBMEBUS=y -- GitLab From 1ce7fda142af48f5c603cc72061e4e8bd32edab6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:46 +1000 Subject: [PATCH 3640/5631] powerpc/configs/64s: Drop IPV6 which is default y Since commit de551f2eb22a ("net: Build IPv6 into kernel by default"), IPV6 is default y. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-3-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 0a3a2fefb652..c4f3ce96d924 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -84,7 +84,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=m CONFIG_INET_ESP=m CONFIG_INET_IPCOMP=m -CONFIG_IPV6=y CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set CONFIG_BRIDGE=m -- GitLab From 94d0b37feedc3701d5da4f69448d12352f437837 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:47 +1000 Subject: [PATCH 3641/5631] powerpc/configs/6s: Drop obsolete crypto ALGs These algorithms were marked obsolete in commit 1674aea5f080 ("crypto: Kconfig - mark unused ciphers as obsolete"). Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-4-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index c4f3ce96d924..74477f89c108 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -343,9 +343,6 @@ CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_CRC32C_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m -- GitLab From 64fcdb2930290c84a65147410551857e60a7db2c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:48 +1000 Subject: [PATCH 3642/5631] powerpc/configs/64s: Enable PAPR_SCM This is a powerpc specific driver so add the symbols required to enable it so it gets some build/boot test coverage. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-5-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 74477f89c108..d98fe52a5892 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -29,6 +29,7 @@ CONFIG_NR_CPUS=2048 CONFIG_DTL=y CONFIG_PPC_SMLPAR=y CONFIG_IBMEBUS=y +CONFIG_PAPR_SCM=m CONFIG_PPC_SVM=y CONFIG_PPC_MAPLE=y CONFIG_PPC_PASEMI=y @@ -69,6 +70,7 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_ZONE_DEVICE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y -- GitLab From d892ed0420e20a6423a165fdebb228590ece5f95 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:49 +1000 Subject: [PATCH 3643/5631] powerpc/configs/64s: Add secure boot options to defconfig Add the numerous options required to get secure boot enabled. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-6-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index d98fe52a5892..f185adc128db 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -54,6 +54,7 @@ CONFIG_CRASH_DUMP=y CONFIG_FA_DUMP=y CONFIG_IRQ_ALL_CPUS=y CONFIG_SCHED_SMT=y +CONFIG_PPC_SECURE_BOOT=y CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m @@ -335,13 +336,25 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y +CONFIG_SECURITY=y +CONFIG_SECURITY_LOCKDOWN_LSM=y +CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y +CONFIG_INTEGRITY_SIGNATURE=y +CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y +CONFIG_IMA=y +CONFIG_IMA_KEXEC=y +CONFIG_IMA_DEFAULT_HASH_SHA256=y +CONFIG_IMA_WRITE_POLICY=y +CONFIG_IMA_APPRAISE=y +CONFIG_IMA_ARCH_POLICY=y +CONFIG_IMA_APPRAISE_MODSIG=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_WP512=m @@ -352,6 +365,8 @@ CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y +CONFIG_SYSTEM_TRUSTED_KEYRING=y +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_PRINTK_TIME=y CONFIG_PRINTK_CALLER=y CONFIG_DEBUG_KERNEL=y -- GitLab From e0fe568ebbc0705fe2fe4ea62be752fad9d801d0 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:50 +1000 Subject: [PATCH 3644/5631] powerpc/configs/64s: Select ARCH_WANT_DEFAULT_BPF_JIT Tell the generic BPF code that the JIT should be enabled by default, rather than the interpreter. Most distros use CONFIG_BPF_JIT_ALWAYS_ON=y anyway, so this just updates upstream to more closely match that. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-7-mpe@ellerman.id.au --- arch/powerpc/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 873eaa888a70..7a0f25a09759 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,6 +164,7 @@ config PPC select ARCH_USE_CMPXCHG_LOCKREF if PPC64 select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS + select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_IRQS_OFF_ACTIVATE_MM -- GitLab From 3a4b71786e9828a0b85600013da7fbe8cb3d0138 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:51 +1000 Subject: [PATCH 3645/5631] powerpc/configs/64s: Enable PREEMPT_VOLUNTARY Traditionally on powerpc servers PREEMPT_NONE was used, but these days multiple distros are building with PREEMPT_VOLUNTARY - Ubuntu, Fedora & CentOS all enable it. So update the upstream config to reflect that, and get test coverage before code hits the distros. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-8-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index f185adc128db..b332b05a668f 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -5,6 +5,7 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y +CONFIG_PREEMPT_VOLUNTARY=y CONFIG_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y -- GitLab From 1b813ac21b5d2c142bcbe0dbd58a23dcc8594d59 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:52 +1000 Subject: [PATCH 3646/5631] powerpc/configs/64s: Enable AUDIT Essentially all distros enable it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-9-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index b332b05a668f..0e3b420aaa6e 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -1,6 +1,7 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CONTEXT_TRACKING_USER_FORCE is not set +CONFIG_AUDIT=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BPF_SYSCALL=y -- GitLab From 88e284b64b0b3193fc3c451d12e912f58375904c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:53 +1000 Subject: [PATCH 3647/5631] powerpc/configs/64s: Enable common accounting options These options are enabled by most distros. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-10-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 0e3b420aaa6e..ecad254eee6c 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -8,8 +8,13 @@ CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_VIRT_CPU_ACCOUNTING_GEN=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 -- GitLab From ea87ec60e96e55ed034fbf1f91300b9bf12e412a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:54 +1000 Subject: [PATCH 3648/5631] powerpc/configs/64s: Enable NO_HZ_FULL At least Fedora & SUSE enable it. VIRT_CPU_ACCOUNTING_GEN is selected so no longer needs to be in the defconfig. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-11-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index ecad254eee6c..7e265cbbeaef 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -1,13 +1,12 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -# CONFIG_CONTEXT_TRACKING_USER_FORCE is not set CONFIG_AUDIT=y +CONFIG_NO_HZ_FULL=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_PREEMPT_VOLUNTARY=y -CONFIG_VIRT_CPU_ACCOUNTING_GEN=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y -- GitLab From 6c95035e06e8c38ce8d9a74f53ac49ede86e584f Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:55 +1000 Subject: [PATCH 3649/5631] powerpc/configs/64s: Enable common CGROUP & related options Distros enable these options. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-12-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 7e265cbbeaef..e853905c4e7e 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -19,15 +19,20 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 CONFIG_NUMA_BALANCING=y -CONFIG_CGROUPS=y CONFIG_MEMCG=y -CONFIG_CGROUP_SCHED=y +CONFIG_BLK_CGROUP=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y +CONFIG_CGROUP_MISC=y +CONFIG_USER_NS=y +CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y CONFIG_PPC64=y -- GitLab From b92c4675f0b20ccf493449c02357f0ff1241f6db Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:56 +1000 Subject: [PATCH 3650/5631] powerpc/configs/64s: Enable CHECKPOINT_RESTORE Most distros enable this. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-13-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index e853905c4e7e..07a92f02e1f8 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -32,6 +32,7 @@ CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y CONFIG_CGROUP_MISC=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_PROFILING=y -- GitLab From 90ae13b654ee58d5d0d0152d196d0419021273e6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:57 +1000 Subject: [PATCH 3651/5631] powerpc/configs/64s: Enable ZSWAP & ZRAM Most distros enable these. In particular Fedore uses zram in the default install. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-14-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 07a92f02e1f8..59b9d8eb1c7b 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -78,6 +78,9 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=m +CONFIG_ZSWAP=y +CONFIG_Z3FOLD=y +CONFIG_ZSMALLOC=y # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y @@ -114,6 +117,7 @@ CONFIG_ELECTRA_CF=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_FD=y +CONFIG_ZRAM=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y -- GitLab From 40605274cf9b26f921df6d1875e3cf6fcc22dec0 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:58 +1000 Subject: [PATCH 3652/5631] powerpc/configs/64s: Enable SLAB hardening options Fedora & CentOS enable these. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-15-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 59b9d8eb1c7b..0aafe64cd1d7 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -81,6 +81,10 @@ CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y CONFIG_Z3FOLD=y CONFIG_ZSMALLOC=y +# CONFIG_SLAB_MERGE_DEFAULT is not set +CONFIG_SLAB_FREELIST_RANDOM=y +CONFIG_SLAB_FREELIST_HARDENED=y +CONFIG_SHUFFLE_PAGE_ALLOCATOR=y # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y -- GitLab From 2e46fbe0881b18e4e338035958e1f49263629ca1 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:23:59 +1000 Subject: [PATCH 3653/5631] powerpc/configs/64s: Enable YAMA, LANDLOCK & BPF LSMs Multiple distros enable these. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-16-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 0aafe64cd1d7..8673277f9b20 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -6,6 +6,7 @@ CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y +CONFIG_BPF_LSM=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -357,8 +358,10 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_SECURITY=y +CONFIG_SECURITY_YAMA=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y +CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y CONFIG_INTEGRITY_PLATFORM_KEYRING=y -- GitLab From 69c483660ef9735a71ca280f48584068c903c278 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:00 +1000 Subject: [PATCH 3654/5631] powerpc/configs/64s: Enable SELINUX Fedora, CentOS, RHEL & SUSE all enable it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-17-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 8673277f9b20..946307c54afa 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -358,6 +358,9 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_YAMA=y CONFIG_SECURITY_LOCKDOWN_LSM=y CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y -- GitLab From 5029aa2a47bd18c654a20a6b1a84b9e418189ad9 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:01 +1000 Subject: [PATCH 3655/5631] powerpc/configs/64s: Enable KUNIT and most tests All built as modules, so the tests only happen when the modules are loaded, not affecting normal boot time. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-18-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 43 ++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 946307c54afa..8d4231fd878a 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -397,12 +397,14 @@ CONFIG_PRINTK_TIME=y CONFIG_PRINTK_CALLER=y CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_RODATA_TEST=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y CONFIG_FUNCTION_TRACER=y +CONFIG_LOCK_TORTURE_TEST=m CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y @@ -412,3 +414,44 @@ CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y CONFIG_XMON=y CONFIG_BOOTX_TEXT=y +CONFIG_KUNIT=m +CONFIG_KUNIT_ALL_TESTS=m +CONFIG_LKDTM=m +CONFIG_TEST_MIN_HEAP=m +CONFIG_TEST_DIV64=m +CONFIG_BACKTRACE_SELF_TEST=m +CONFIG_TEST_REF_TRACKER=m +CONFIG_RBTREE_TEST=m +CONFIG_REED_SOLOMON_TEST=m +CONFIG_INTERVAL_TREE_TEST=m +CONFIG_PERCPU_TEST=m +CONFIG_ATOMIC64_SELFTEST=m +CONFIG_ASYNC_RAID6_TEST=m +CONFIG_TEST_HEXDUMP=m +CONFIG_STRING_SELFTEST=m +CONFIG_TEST_STRING_HELPERS=m +CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m +CONFIG_TEST_SCANF=m +CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m +CONFIG_TEST_MAPLE_TREE=m +CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_IDA=m +CONFIG_TEST_BITOPS=m +CONFIG_TEST_VMALLOC=m +CONFIG_TEST_USER_COPY=m +CONFIG_TEST_BPF=m +CONFIG_TEST_BLACKHOLE_DEV=m +CONFIG_FIND_BIT_BENCHMARK=m +CONFIG_TEST_FIRMWARE=m +CONFIG_TEST_SYSCTL=m +CONFIG_LINEAR_RANGES_TEST=m +CONFIG_TEST_UDELAY=m +CONFIG_TEST_STATIC_KEYS=m +CONFIG_TEST_KMOD=m +CONFIG_TEST_MEMCAT_P=m +CONFIG_TEST_MEMINIT=m +CONFIG_TEST_FREE_PAGES=m +CONFIG_MEMTEST=y -- GitLab From 7ccad8eee0d92f7566e4f9e12f2f26d74885f1a5 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:02 +1000 Subject: [PATCH 3656/5631] powerpc/configs/64s: Enable EMULATED_STATS This is enabled in some of the other powerpc configs, and can be useful for debugging, so enable it in ppc64[le]_defconfig. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-19-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 8d4231fd878a..c8b49e33fd81 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -409,6 +409,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_PPC_EMULATED_STATS=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y -- GitLab From 3c18a2094ffe06626f09c923067ab284b294d5c6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:03 +1000 Subject: [PATCH 3657/5631] powerpc/configs/64s: Enable DEBUG_VM & other options Fedora enables DEBUG_VM, which has led to occasions where a VM_BUG_ON() is not caught by upstream testing, but rather is first found in Fedora, which is not how it's meant to be. PAGE_OWNER & PAGE_POISONING both need to be enabled on the kernel command line, so should not add much overhead in normal operation. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-20-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index c8b49e33fd81..3154f307bba6 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -397,14 +397,20 @@ CONFIG_PRINTK_TIME=y CONFIG_PRINTK_CALLER=y CONFIG_DEBUG_KERNEL=y CONFIG_MAGIC_SYSRQ=y +CONFIG_PAGE_OWNER=y +CONFIG_PAGE_POISONING=y CONFIG_DEBUG_RODATA_TEST=y +CONFIG_DEBUG_WX=y CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_VM=y +# CONFIG_DEBUG_VM_PGTABLE is not set CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y CONFIG_FUNCTION_TRACER=y CONFIG_LOCK_TORTURE_TEST=m +CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y -- GitLab From d3a85f29c30d9876440c03933b3793607f616ed6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:04 +1000 Subject: [PATCH 3658/5631] powerpc/configs/64s: Enable SCHEDSTATS Distros enable it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-21-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 3154f307bba6..2cee399d3abc 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -407,6 +407,7 @@ CONFIG_DEBUG_VM=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_SCHEDSTATS=y CONFIG_DEBUG_MUTEXES=y CONFIG_FUNCTION_TRACER=y CONFIG_LOCK_TORTURE_TEST=m -- GitLab From 6880db8fe1d042b164473fd865ee2ec6f5ee3df6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:05 +1000 Subject: [PATCH 3659/5631] powerpc/configs/64s: Enable IO_STRICT_DEVMEM Distros enable it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-22-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 2cee399d3abc..4c347f6be401 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -416,6 +416,7 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_IO_STRICT_DEVMEM=y CONFIG_PPC_EMULATED_STATS=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y -- GitLab From 649181aea2be6deaa1c9aef66e765a7ba0d077c5 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:06 +1000 Subject: [PATCH 3660/5631] powerpc/configs/64s: Use SHA512 for module signatures Modern distros use SHA512 for module signing. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-23-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 4c347f6be401..b7c6cd72a0ce 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -77,6 +77,7 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA512=y CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=m CONFIG_ZSWAP=y -- GitLab From a4f64f73b6a368c067beae20e0fac6625e8768cb Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:07 +1000 Subject: [PATCH 3661/5631] powerpc/configs/64s: Drop REISERFS No reason to use this anymore. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-24-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index b7c6cd72a0ce..12d49f3e56b7 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -312,10 +312,6 @@ CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_REISERFS_FS=m -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y -- GitLab From 22f615cb87af5a26c0ac91d02020575edb5aeb89 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:08 +1000 Subject: [PATCH 3662/5631] powerpc/configs/64s: Enable BLK_DEV_NVME Copy powernv_defconfig and enable BLK_DEV_NVME. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-25-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 12d49f3e56b7..b88155ddab65 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -129,6 +129,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_VIRTIO_BLK=m +CONFIG_BLK_DEV_NVME=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -- GitLab From 48b2e99def2d92dbf2f7cb4b7f42ee8d98c56768 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:09 +1000 Subject: [PATCH 3663/5631] powerpc/configs/64s: Enable VLAN support Most other configs, and distros enable it. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-26-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index b88155ddab65..833847b775ec 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -111,6 +111,7 @@ CONFIG_INET_IPCOMP=m CONFIG_NETFILTER=y # CONFIG_NETFILTER_ADVANCED is not set CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m CONFIG_NET_SCHED=y CONFIG_NET_CLS_BPF=m CONFIG_NET_CLS_ACT=y -- GitLab From 262a3589df8cd28c152c46c166be9e552da90ed3 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:10 +1000 Subject: [PATCH 3664/5631] powerpc/configs/64s: Enable PSTORE Like pseries & powernv_defconfig, enable PSTORE. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-27-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 833847b775ec..037219dda19f 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -341,6 +341,7 @@ CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZO=y CONFIG_SQUASHFS_XZ=y +CONFIG_PSTORE=y CONFIG_NFS_FS=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y -- GitLab From 4f6cfb53646794a2dc14210fbfedd5c6db38ba2c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:11 +1000 Subject: [PATCH 3665/5631] powerpc/configs/64s: Enable Device Mapper options Add device mapper options for test coverage and in case folks are booting systems that require them. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-28-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 037219dda19f..a17cb31105e3 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -167,18 +167,30 @@ CONFIG_BLK_DEV_MD=y CONFIG_MD_LINEAR=y CONFIG_MD_RAID0=y CONFIG_MD_RAID1=y -CONFIG_MD_RAID10=m -CONFIG_MD_RAID456=m CONFIG_MD_MULTIPATH=m CONFIG_MD_FAULTY=m CONFIG_BLK_DEV_DM=y +CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m +CONFIG_DM_THIN_PROVISIONING=m +CONFIG_DM_CACHE=m +CONFIG_DM_WRITECACHE=m +CONFIG_DM_EBS=m +CONFIG_DM_ERA=m +CONFIG_DM_CLONE=m CONFIG_DM_MIRROR=m +CONFIG_DM_LOG_USERSPACE=m +CONFIG_DM_RAID=m CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m +CONFIG_DM_MULTIPATH_IOA=m +CONFIG_DM_DELAY=m +CONFIG_DM_DUST=m +CONFIG_DM_INIT=y CONFIG_DM_UEVENT=y CONFIG_ADB_PMU=y CONFIG_PMAC_SMU=y -- GitLab From 9ee937539e9bd0bef2ad845b3dfa34fa997775c5 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:12 +1000 Subject: [PATCH 3666/5631] powerpc/configs: Add IBMVETH=y and IBMVNIC=y to guest configs These drivers are sometimes required to have functional networking in a guest, so build them in when building ppc64[le]_guest_defconfig. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-29-mpe@ellerman.id.au --- arch/powerpc/configs/guest.config | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/configs/guest.config b/arch/powerpc/configs/guest.config index 209f58515d88..fece83487215 100644 --- a/arch/powerpc/configs/guest.config +++ b/arch/powerpc/configs/guest.config @@ -10,3 +10,5 @@ CONFIG_EPAPR_PARAVIRT=y CONFIG_VIRTIO_BALLOON=y CONFIG_VHOST_NET=y CONFIG_VHOST=y +CONFIG_IBMVETH=y +CONFIG_IBMVNIC=y -- GitLab From bac949621c40ec09357c6a8beaacac235ae39239 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:13 +1000 Subject: [PATCH 3667/5631] powerpc/configs: Incorporate generic kvm_guest.config into guest configs Incorporate the generic kvm_guest.config into the powerpc guest configs, ppc64[le]_guest_defconfig. This brings in some useful options, in particular 9P support, and also means future additions to the generic file will be automatically picked up by the powerpc configs. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-30-mpe@ellerman.id.au --- arch/powerpc/Makefile | 4 ++-- arch/powerpc/configs/kvm_guest.config | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) create mode 120000 arch/powerpc/configs/kvm_guest.config diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 85eb8e31b503..030e41af2eaf 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -258,11 +258,11 @@ ppc64le_defconfig: generated_configs += ppc64le_guest_defconfig ppc64le_guest_defconfig: - $(call merge_into_defconfig,ppc64_defconfig,le guest) + $(call merge_into_defconfig,ppc64_defconfig,le guest kvm_guest) generated_configs += ppc64_guest_defconfig ppc64_guest_defconfig: - $(call merge_into_defconfig,ppc64_defconfig,be guest) + $(call merge_into_defconfig,ppc64_defconfig,be guest kvm_guest) generated_configs += powernv_be_defconfig powernv_be_defconfig: diff --git a/arch/powerpc/configs/kvm_guest.config b/arch/powerpc/configs/kvm_guest.config new file mode 120000 index 000000000000..a5f7a2fa74ef --- /dev/null +++ b/arch/powerpc/configs/kvm_guest.config @@ -0,0 +1 @@ +../../../kernel/configs/kvm_guest.config \ No newline at end of file -- GitLab From 596ddea8be17b5f4e2f72a0c9af313444d51d177 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:14 +1000 Subject: [PATCH 3668/5631] powerpc/configs: Make pseries_le an alias for ppc64le_guest Rather than trying to keep multiple configs up to date, make pseries_le_defconfig an alias for ppc64le_guest_defconfig. ppc64le_guest_defconfig should work in all cases that pseries_le_defconfig currently does, but if not we can update it. Move pseries_le_defconfig down in the Makefile, so it appears after ppc64le_guest_defconfig in the help output. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-31-mpe@ellerman.id.au --- arch/powerpc/Makefile | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 030e41af2eaf..6b677e257378 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -248,10 +248,6 @@ bootwrapper_install: include $(srctree)/scripts/Makefile.defconf -generated_configs += pseries_le_defconfig -pseries_le_defconfig: - $(call merge_into_defconfig,pseries_defconfig,le) - generated_configs += ppc64le_defconfig ppc64le_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le) @@ -264,6 +260,9 @@ generated_configs += ppc64_guest_defconfig ppc64_guest_defconfig: $(call merge_into_defconfig,ppc64_defconfig,be guest kvm_guest) +generated_configs += pseries_le_defconfig +pseries_le_defconfig: ppc64le_guest_defconfig + generated_configs += powernv_be_defconfig powernv_be_defconfig: $(call merge_into_defconfig,powernv_defconfig,be) -- GitLab From 9ecda934f43b1502c420653b02d54d4ffd7ae4cb Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 14 Apr 2023 23:24:15 +1000 Subject: [PATCH 3669/5631] powerpc/configs: Make pseries_defconfig an alias for ppc64le_guest Rather than trying to keep multiple configs up to date, make pseries_defconfig an alias for ppc64le_guest_defconfig. NOTE, pseries_defconfig was a big endian config, but this commit switches it to little endian. Almost all distros are ppc64le these days, so little endian is much more likely to be what a user wants when they build for "pseries". For an actual big endian guest, use ppc64_guest_defconfig. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230414132415.821564-32-mpe@ellerman.id.au --- arch/powerpc/Makefile | 3 + arch/powerpc/configs/pseries_defconfig | 323 ------------------------- 2 files changed, 3 insertions(+), 323 deletions(-) delete mode 100644 arch/powerpc/configs/pseries_defconfig diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 6b677e257378..dca73f673d70 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -263,6 +263,9 @@ ppc64_guest_defconfig: generated_configs += pseries_le_defconfig pseries_le_defconfig: ppc64le_guest_defconfig +generated_configs += pseries_defconfig +pseries_defconfig: ppc64le_guest_defconfig + generated_configs += powernv_be_defconfig powernv_be_defconfig: $(call merge_into_defconfig,powernv_defconfig,be) diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig deleted file mode 100644 index 7497e17ea657..000000000000 --- a/arch/powerpc/configs/pseries_defconfig +++ /dev/null @@ -1,323 +0,0 @@ -CONFIG_PPC64=y -CONFIG_NR_CPUS=2048 -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_AUDIT=y -# CONFIG_CONTEXT_TRACKING_USER_FORCE is not set -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_VIRT_CPU_ACCOUNTING_GEN=y -CONFIG_TASKSTATS=y -CONFIG_TASK_DELAY_ACCT=y -CONFIG_TASK_XACCT=y -CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_LOG_BUF_SHIFT=18 -CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 -CONFIG_NUMA_BALANCING=y -CONFIG_CGROUPS=y -CONFIG_MEMCG=y -CONFIG_CGROUP_SCHED=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CPUSETS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_PERF=y -CONFIG_CGROUP_BPF=y -CONFIG_USER_NS=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_BPF_SYSCALL=y -# CONFIG_COMPAT_BRK is not set -CONFIG_PROFILING=y -CONFIG_KPROBES=y -CONFIG_JUMP_LABEL=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_PPC_SPLPAR=y -CONFIG_DTL=y -CONFIG_PPC_SMLPAR=y -CONFIG_IBMEBUS=y -CONFIG_LIBNVDIMM=m -CONFIG_PAPR_SCM=m -CONFIG_PPC_SVM=y -# CONFIG_PPC_PMAC is not set -CONFIG_RTAS_FLASH=m -CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y -CONFIG_HZ_100=y -CONFIG_BINFMT_MISC=m -CONFIG_PPC_TRANSACTIONAL_MEM=y -CONFIG_KEXEC=y -CONFIG_KEXEC_FILE=y -CONFIG_IRQ_ALL_CPUS=y -CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTREMOVE=y -CONFIG_KSM=y -CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_SCHED_SMT=y -CONFIG_HOTPLUG_PCI=y -CONFIG_HOTPLUG_PCI_RPA=m -CONFIG_HOTPLUG_PCI_RPA_DLPAR=m -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_XFRM_USER=m -CONFIG_NET_KEY=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_NET_IPIP=y -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_ADVANCED is not set -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_NET_SCHED=y -CONFIG_NET_CLS_BPF=m -CONFIG_NET_CLS_ACT=y -CONFIG_NET_ACT_BPF=m -CONFIG_BPF_JIT=y -CONFIG_DEVTMPFS=y -CONFIG_DEVTMPFS_MOUNT=y -CONFIG_PARPORT=m -CONFIG_PARPORT_PC=m -CONFIG_BLK_DEV_FD=m -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=65536 -CONFIG_VIRTIO_BLK=m -CONFIG_BLK_DEV_NVME=y -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=m -CONFIG_BLK_DEV_SR=y -CONFIG_CHR_DEV_SG=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_FC_ATTRS=y -CONFIG_SCSI_CXGB3_ISCSI=m -CONFIG_SCSI_CXGB4_ISCSI=m -CONFIG_SCSI_BNX2_ISCSI=m -CONFIG_BE2ISCSI=m -CONFIG_SCSI_MPT2SAS=m -CONFIG_SCSI_IBMVSCSI=y -CONFIG_SCSI_IBMVFC=m -CONFIG_SCSI_SYM53C8XX_2=m -CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0 -CONFIG_SCSI_IPR=y -CONFIG_SCSI_QLA_FC=m -CONFIG_SCSI_QLA_ISCSI=m -CONFIG_SCSI_LPFC=m -CONFIG_SCSI_VIRTIO=m -CONFIG_SCSI_DH=y -CONFIG_SCSI_DH_RDAC=m -CONFIG_SCSI_DH_ALUA=m -CONFIG_ATA=y -CONFIG_SATA_AHCI=y -CONFIG_PATA_AMD=y -CONFIG_ATA_GENERIC=y -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=y -CONFIG_MD_RAID0=y -CONFIG_MD_RAID1=y -CONFIG_MD_RAID10=m -CONFIG_MD_RAID456=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m -CONFIG_BLK_DEV_DM=y -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_THIN_PROVISIONING=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m -CONFIG_DM_MULTIPATH_QL=m -CONFIG_DM_MULTIPATH_ST=m -CONFIG_DM_UEVENT=y -CONFIG_BONDING=m -CONFIG_DUMMY=m -CONFIG_MACVLAN=m -CONFIG_MACVTAP=m -CONFIG_VXLAN=m -CONFIG_NETCONSOLE=y -CONFIG_TUN=m -CONFIG_VETH=m -CONFIG_VIRTIO_NET=m -CONFIG_VORTEX=m -CONFIG_ACENIC=m -CONFIG_ACENIC_OMIT_TIGON_I=y -CONFIG_PCNET32=m -CONFIG_TIGON3=y -CONFIG_BNX2X=m -CONFIG_CHELSIO_T1=m -CONFIG_BE2NET=m -CONFIG_S2IO=m -CONFIG_IBMVETH=y -CONFIG_EHEA=y -CONFIG_IBMVNIC=y -CONFIG_E100=y -CONFIG_E1000=y -CONFIG_E1000E=y -CONFIG_IXGB=m -CONFIG_IXGBE=m -CONFIG_I40E=m -CONFIG_MLX4_EN=m -CONFIG_MYRI10GE=m -CONFIG_NETXEN_NIC=m -CONFIG_PPP=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPPOE=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_INPUT_EVDEV=m -CONFIG_INPUT_MISC=y -CONFIG_INPUT_PCSPKR=m -# CONFIG_SERIO_SERPORT is not set -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_ICOM=m -CONFIG_SERIAL_JSM=m -CONFIG_HVC_CONSOLE=y -CONFIG_HVC_RTAS=y -CONFIG_HVCS=m -CONFIG_VIRTIO_CONSOLE=m -CONFIG_IBM_BSR=m -CONFIG_I2C_CHARDEV=y -CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y -CONFIG_FB_OF=y -CONFIG_FB_MATROX=y -CONFIG_FB_MATROX_MILLENIUM=y -CONFIG_FB_MATROX_MYSTIQUE=y -CONFIG_FB_MATROX_G=y -CONFIG_FB_RADEON=y -CONFIG_FB_IBM_GXT4500=y -CONFIG_LCD_PLATFORM=m -# CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_LOGO=y -CONFIG_HID_GYRATION=y -CONFIG_HID_PANTHERLORD=y -CONFIG_HID_PETALYNX=y -CONFIG_HID_SAMSUNG=y -CONFIG_HID_SUNPLUS=y -CONFIG_USB_HIDDEV=y -CONFIG_USB=y -CONFIG_USB_MON=m -CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_HCD_PPC_OF is not set -CONFIG_USB_OHCI_HCD=y -CONFIG_USB_XHCI_HCD=y -CONFIG_USB_STORAGE=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=m -CONFIG_LEDS_POWERNV=m -CONFIG_INFINIBAND=m -CONFIG_INFINIBAND_USER_MAD=m -CONFIG_INFINIBAND_USER_ACCESS=m -CONFIG_INFINIBAND_MTHCA=m -CONFIG_INFINIBAND_CXGB4=m -CONFIG_MLX4_INFINIBAND=m -CONFIG_INFINIBAND_IPOIB=m -CONFIG_INFINIBAND_IPOIB_CM=y -CONFIG_INFINIBAND_SRP=m -CONFIG_INFINIBAND_ISER=m -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_GENERIC=y -CONFIG_VIRTIO_PCI=m -CONFIG_VIRTIO_BALLOON=m -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_POSIX_ACL=y -CONFIG_EXT4_FS_SECURITY=y -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -CONFIG_JFS_SECURITY=y -CONFIG_XFS_FS=m -CONFIG_XFS_POSIX_ACL=y -CONFIG_BTRFS_FS=m -CONFIG_BTRFS_FS_POSIX_ACL=y -CONFIG_NILFS2_FS=m -CONFIG_FS_DAX=y -CONFIG_AUTOFS4_FS=m -CONFIG_FUSE_FS=m -CONFIG_OVERLAY_FS=m -CONFIG_ISO9660_FS=y -CONFIG_UDF_FS=m -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=m -CONFIG_PROC_KCORE=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_HUGETLBFS=y -CONFIG_CRAMFS=m -CONFIG_SQUASHFS=m -CONFIG_SQUASHFS_XATTR=y -CONFIG_SQUASHFS_LZO=y -CONFIG_SQUASHFS_XZ=y -CONFIG_PSTORE=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3_ACL=y -CONFIG_NFS_V4=y -CONFIG_NFSD=m -CONFIG_NFSD_V3_ACL=y -CONFIG_NFSD_V4=y -CONFIG_CIFS=m -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -CONFIG_NLS_DEFAULT="utf8" -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_UTF8=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_STACK_USAGE=y -CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_HARDLOCKUP_DETECTOR=y -CONFIG_FUNCTION_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_SCHED_TRACER=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_CODE_PATCHING_SELFTEST=y -CONFIG_FTR_FIXUP_SELFTEST=y -CONFIG_MSI_BITMAP_SELFTEST=y -CONFIG_XMON=y -CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_CRC32C_VPMSUM=m -CONFIG_CRYPTO_MD5_PPC=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_SHA1_PPC=m -CONFIG_CRYPTO_SHA256=y -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_LZO=m -CONFIG_CRYPTO_DEV_NX=y -CONFIG_CRYPTO_DEV_NX_ENCRYPT=m -CONFIG_CRYPTO_DEV_VMX=y -CONFIG_VIRTUALIZATION=y -CONFIG_KVM_BOOK3S_64=m -CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_VHOST_NET=m -CONFIG_PRINTK_TIME=y -CONFIG_PRINTK_CALLER=y -- GitLab From e4c02c3e6c39c3866d517388f6bb431c47743bde Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 20 Apr 2023 15:16:08 +1000 Subject: [PATCH 3670/5631] powerpc/configs/64s: Use EXT4 to mount EXT2 filesystems The ext4 code will mount ext2 filesystems, no need to build in both. Suggested-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230420051609.1324201-1-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index a17cb31105e3..2836190448d5 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -319,10 +319,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VHOST_NET=m CONFIG_RAS=y CONFIG_LIBNVDIMM=y -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -- GitLab From da66ed3198162882755d5c9a147e36f02dc9be93 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 20 Apr 2023 15:16:09 +1000 Subject: [PATCH 3671/5631] powerpc/configs/64s: Drop JFS Filesystem Unlikely that anyone is still regularly using JFS, drop it from the defconfig. Suggested-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230420051609.1324201-2-mpe@ellerman.id.au --- arch/powerpc/configs/ppc64_defconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 2836190448d5..7e8bc53f4e64 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -322,9 +322,6 @@ CONFIG_LIBNVDIMM=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -CONFIG_JFS_SECURITY=y CONFIG_XFS_FS=y CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m -- GitLab From 836a3de6b2bfe0b7c96a7104d3d567883d8a57b3 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 20 Apr 2023 15:21:49 +1000 Subject: [PATCH 3672/5631] powerpc/configs/powernv: Add IGB=y Some powernv machines use IGB for networking, so build the driver in to enable net booting such machines. Suggested-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230420052149.1328094-1-mpe@ellerman.id.au --- arch/powerpc/configs/powernv_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index c92652575064..92e3a8fea04a 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -170,6 +170,7 @@ CONFIG_S2IO=m CONFIG_E100=y CONFIG_E1000=y CONFIG_E1000E=y +CONFIG_IGB=y CONFIG_IXGB=m CONFIG_IXGBE=m CONFIG_I40E=m -- GitLab From 94b95dfaa814f565d92f5a65f0ff12a483095522 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 19 Apr 2023 15:19:07 +0300 Subject: [PATCH 3673/5631] xfrm: release all offloaded policy memory Failure to add offloaded policy will cause to the following error once user will try to reload driver. Unregister_netdevice: waiting for eth3 to become free. Usage count = 2 This was caused by xfrm_dev_policy_add() which increments reference to net_device. That reference was supposed to be decremented in xfrm_dev_policy_free(). However the latter wasn't called. unregister_netdevice: waiting for eth3 to become free. Usage count = 2 leaked reference. xfrm_dev_policy_add+0xff/0x3d0 xfrm_policy_construct+0x352/0x420 xfrm_add_policy+0x179/0x320 xfrm_user_rcv_msg+0x1d2/0x3d0 netlink_rcv_skb+0xe0/0x210 xfrm_netlink_rcv+0x45/0x50 netlink_unicast+0x346/0x490 netlink_sendmsg+0x3b0/0x6c0 sock_sendmsg+0x73/0xc0 sock_write_iter+0x13b/0x1f0 vfs_write+0x528/0x5d0 ksys_write+0x120/0x150 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Fixes: 919e43fad516 ("xfrm: add an interface to offload policy") Signed-off-by: Leon Romanovsky Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 103af2b3e986..af8fbcbfbe69 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1978,6 +1978,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) { xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); security_xfrm_policy_free(xp->security); kfree(xp); return err; -- GitLab From ec8f32ad9a65a8cbb465b69e154aaec9d2fe45c4 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Wed, 19 Apr 2023 15:19:08 +0300 Subject: [PATCH 3674/5631] xfrm: Fix leak of dev tracker At the stage of direction checks, the netdev reference tracker is already initialized, but released with wrong *_put() call. Fixes: 919e43fad516 ("xfrm: add an interface to offload policy") Signed-off-by: Leon Romanovsky Reviewed-by: Simon Horman Reviewed-by: Eric Dumazet Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 95f1436bf6a2..e2ca50bfca24 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -378,7 +378,7 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, break; default: xdo->dev = NULL; - dev_put(dev); + netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } -- GitLab From c384c2401eed99a2e1f84191e573f15b898babe6 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Mon, 17 Apr 2023 14:03:43 +0300 Subject: [PATCH 3675/5631] vdpa/mlx5: Avoid losing link state updates Current code ignores link state updates if VIRTIO_NET_F_STATUS was not negotiated. However, link state updates could be received before feature negotiation was completed , therefore causing link state events to be lost, possibly leaving the link state down. Modify the code so link state notifier is registered after DRIVER_OK was negotiated and carry the registration only if VIRTIO_NET_F_STATUS was negotiated. Unregister the notifier when the device is reset. Fixes: 033779a708f0 ("vdpa/mlx5: make MTU/STATUS presence conditional on feature bits") Acked-by: Jason Wang Signed-off-by: Eli Cohen Message-Id: <20230417110343.138319-1-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 203 +++++++++++++++++------------- 1 file changed, 114 insertions(+), 89 deletions(-) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 195963b82b63..97a16f7eb894 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2298,6 +2298,113 @@ static void update_cvq_info(struct mlx5_vdpa_dev *mvdev) } } +static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) +{ + u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {}; + int err; + + MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE); + MLX5_SET(query_vport_state_in, in, op_mod, opmod); + MLX5_SET(query_vport_state_in, in, vport_number, vport); + if (vport) + MLX5_SET(query_vport_state_in, in, other_vport, 1); + + err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out); + if (err) + return 0; + + return MLX5_GET(query_vport_state_out, out, state); +} + +static bool get_link_state(struct mlx5_vdpa_dev *mvdev) +{ + if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) == + VPORT_STATE_UP) + return true; + + return false; +} + +static void update_carrier(struct work_struct *work) +{ + struct mlx5_vdpa_wq_ent *wqent; + struct mlx5_vdpa_dev *mvdev; + struct mlx5_vdpa_net *ndev; + + wqent = container_of(work, struct mlx5_vdpa_wq_ent, work); + mvdev = wqent->mvdev; + ndev = to_mlx5_vdpa_ndev(mvdev); + if (get_link_state(mvdev)) + ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP); + else + ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP); + + if (ndev->config_cb.callback) + ndev->config_cb.callback(ndev->config_cb.private); + + kfree(wqent); +} + +static int queue_link_work(struct mlx5_vdpa_net *ndev) +{ + struct mlx5_vdpa_wq_ent *wqent; + + wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); + if (!wqent) + return -ENOMEM; + + wqent->mvdev = &ndev->mvdev; + INIT_WORK(&wqent->work, update_carrier); + queue_work(ndev->mvdev.wq, &wqent->work); + return 0; +} + +static int event_handler(struct notifier_block *nb, unsigned long event, void *param) +{ + struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb); + struct mlx5_eqe *eqe = param; + int ret = NOTIFY_DONE; + + if (event == MLX5_EVENT_TYPE_PORT_CHANGE) { + switch (eqe->sub_type) { + case MLX5_PORT_CHANGE_SUBTYPE_DOWN: + case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: + if (queue_link_work(ndev)) + return NOTIFY_DONE; + + ret = NOTIFY_OK; + break; + default: + return NOTIFY_DONE; + } + return ret; + } + return ret; +} + +static void register_link_notifier(struct mlx5_vdpa_net *ndev) +{ + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_STATUS))) + return; + + ndev->nb.notifier_call = event_handler; + mlx5_notifier_register(ndev->mvdev.mdev, &ndev->nb); + ndev->nb_registered = true; + queue_link_work(ndev); +} + +static void unregister_link_notifier(struct mlx5_vdpa_net *ndev) +{ + if (!ndev->nb_registered) + return; + + ndev->nb_registered = false; + mlx5_notifier_unregister(ndev->mvdev.mdev, &ndev->nb); + if (ndev->mvdev.wq) + flush_workqueue(ndev->mvdev.wq); +} + static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); @@ -2567,10 +2674,11 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) mlx5_vdpa_warn(mvdev, "failed to setup control VQ vring\n"); goto err_setup; } + register_link_notifier(ndev); err = setup_driver(mvdev); if (err) { mlx5_vdpa_warn(mvdev, "failed to setup driver\n"); - goto err_setup; + goto err_driver; } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); @@ -2582,6 +2690,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) up_write(&ndev->reslock); return; +err_driver: + unregister_link_notifier(ndev); err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; @@ -2607,6 +2717,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) mlx5_vdpa_info(mvdev, "performing device reset\n"); down_write(&ndev->reslock); + unregister_link_notifier(ndev); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2861,9 +2972,7 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) mlx5_vdpa_info(mvdev, "suspending device\n"); down_write(&ndev->reslock); - ndev->nb_registered = false; - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); - flush_workqueue(ndev->mvdev.wq); + unregister_link_notifier(ndev); for (i = 0; i < ndev->cur_num_vqs; i++) { mvq = &ndev->vqs[i]; suspend_vq(ndev, mvq); @@ -3000,84 +3109,6 @@ struct mlx5_vdpa_mgmtdev { struct mlx5_vdpa_net *ndev; }; -static u8 query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) -{ - u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {}; - u32 in[MLX5_ST_SZ_DW(query_vport_state_in)] = {}; - int err; - - MLX5_SET(query_vport_state_in, in, opcode, MLX5_CMD_OP_QUERY_VPORT_STATE); - MLX5_SET(query_vport_state_in, in, op_mod, opmod); - MLX5_SET(query_vport_state_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vport_state_in, in, other_vport, 1); - - err = mlx5_cmd_exec_inout(mdev, query_vport_state, in, out); - if (err) - return 0; - - return MLX5_GET(query_vport_state_out, out, state); -} - -static bool get_link_state(struct mlx5_vdpa_dev *mvdev) -{ - if (query_vport_state(mvdev->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0) == - VPORT_STATE_UP) - return true; - - return false; -} - -static void update_carrier(struct work_struct *work) -{ - struct mlx5_vdpa_wq_ent *wqent; - struct mlx5_vdpa_dev *mvdev; - struct mlx5_vdpa_net *ndev; - - wqent = container_of(work, struct mlx5_vdpa_wq_ent, work); - mvdev = wqent->mvdev; - ndev = to_mlx5_vdpa_ndev(mvdev); - if (get_link_state(mvdev)) - ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP); - else - ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP); - - if (ndev->nb_registered && ndev->config_cb.callback) - ndev->config_cb.callback(ndev->config_cb.private); - - kfree(wqent); -} - -static int event_handler(struct notifier_block *nb, unsigned long event, void *param) -{ - struct mlx5_vdpa_net *ndev = container_of(nb, struct mlx5_vdpa_net, nb); - struct mlx5_eqe *eqe = param; - int ret = NOTIFY_DONE; - struct mlx5_vdpa_wq_ent *wqent; - - if (event == MLX5_EVENT_TYPE_PORT_CHANGE) { - if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_STATUS))) - return NOTIFY_DONE; - switch (eqe->sub_type) { - case MLX5_PORT_CHANGE_SUBTYPE_DOWN: - case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE: - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return NOTIFY_DONE; - - wqent->mvdev = &ndev->mvdev; - INIT_WORK(&wqent->work, update_carrier); - queue_work(ndev->mvdev.wq, &wqent->work); - ret = NOTIFY_OK; - break; - default: - return NOTIFY_DONE; - } - return ret; - } - return ret; -} - static int config_func_mtu(struct mlx5_core_dev *mdev, u16 mtu) { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); @@ -3258,9 +3289,6 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, goto err_res2; } - ndev->nb.notifier_call = event_handler; - mlx5_notifier_register(mdev, &ndev->nb); - ndev->nb_registered = true; mvdev->vdev.mdev = &mgtdev->mgtdev; err = _vdpa_register_device(&mvdev->vdev, max_vqs + 1); if (err) @@ -3294,10 +3322,7 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device * mlx5_vdpa_remove_debugfs(ndev->debugfs); ndev->debugfs = NULL; - if (ndev->nb_registered) { - ndev->nb_registered = false; - mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); - } + unregister_link_notifier(ndev); wq = mvdev->wq; mvdev->wq = NULL; destroy_workqueue(wq); -- GitLab From e4be66e5f36b8cd2a052ba9e2ba063e6c37f5453 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 27 Feb 2023 13:41:27 -0800 Subject: [PATCH 3676/5631] vhost: use struct_size and size_add to compute flex array sizes The vhost_get_avail_size and vhost_get_used_size functions compute the size of structures with flexible array members with an additional 2 bytes if the VIRTIO_RING_F_EVENT_IDX feature flag is set. Convert these functions to use struct_size() and size_add() instead of coding the calculation by hand. This ensures that the calculations will saturate at SIZE_MAX rather than overflowing. Signed-off-by: Jacob Keller Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: virtualization@lists.linux-foundation.org Cc: kvm@vger.kernel.org Message-Id: <20230227214127.3678392-1-jacob.e.keller@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vhost.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f11bdbe4c2c5..43fa626d4e44 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -436,8 +436,7 @@ static size_t vhost_get_avail_size(struct vhost_virtqueue *vq, size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - return sizeof(*vq->avail) + - sizeof(*vq->avail->ring) * num + event; + return size_add(struct_size(vq->avail, ring, num), event); } static size_t vhost_get_used_size(struct vhost_virtqueue *vq, @@ -446,8 +445,7 @@ static size_t vhost_get_used_size(struct vhost_virtqueue *vq, size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; - return sizeof(*vq->used) + - sizeof(*vq->used->ring) * num + event; + return size_add(struct_size(vq->used, ring, num), event); } static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, -- GitLab From 48cd6bc5b22d68b8bbc8601f3c7ddeed99541a0b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 18 Feb 2023 09:10:31 +0100 Subject: [PATCH 3677/5631] virtio: Reorder fields in 'struct virtqueue' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct virtqueue' from 72 to 68 bytes. It saves a few bytes of memory. Signed-off-by: Christophe JAILLET Message-Id: <8f3d2e49270a2158717e15008e7ed7228196ba02.1676707807.git.christophe.jaillet@wanadoo.fr> Signed-off-by: Michael S. Tsirkin Acked-by: Peter Lafreniere Reviewed-by: Stefano Garzarella --- include/linux/virtio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 2b472514c49b..d6e161aa532e 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,8 +34,8 @@ struct virtqueue { unsigned int index; unsigned int num_free; unsigned int num_max; - void *priv; bool reset; + void *priv; }; int virtqueue_add_outbuf(struct virtqueue *vq, -- GitLab From 9b2b3de63c07123c0ec9b912d7b8e77b150e520b Mon Sep 17 00:00:00 2001 From: Rong Tao Date: Thu, 9 Mar 2023 14:13:20 +0800 Subject: [PATCH 3678/5631] tools/virtio: virtio_test: Fix indentation Replace eight spaces with Tab. Signed-off-by: Rong Tao Message-Id: Signed-off-by: Michael S. Tsirkin --- tools/virtio/virtio_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 120062f94590..280c6f8ee297 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -134,7 +134,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); - dev->control = open("/dev/vhost-test", O_RDWR); + dev->control = open("/dev/vhost-test", O_RDWR); assert(dev->control >= 0); r = ioctl(dev->control, VHOST_SET_OWNER, NULL); assert(r >= 0); -- GitLab From 6b27cd84a7917b995f66c052fd3453fdbd6e3d70 Mon Sep 17 00:00:00 2001 From: Rong Tao Date: Thu, 9 Mar 2023 16:42:50 +0800 Subject: [PATCH 3679/5631] tools/virtio: virtio_test -h,--help should return directly When we get help information, we should return directly, and we should not execute test cases. Move the exit() directly into the help() function and remove it from case '?'. Signed-off-by: Rong Tao Message-Id: Signed-off-by: Michael S. Tsirkin --- tools/virtio/virtio_test.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index 280c6f8ee297..028f54e6854a 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -327,7 +327,7 @@ const struct option longopts[] = { } }; -static void help(void) +static void help(int status) { fprintf(stderr, "Usage: virtio_test [--help]" " [--no-indirect]" @@ -337,6 +337,8 @@ static void help(void) " [--batch=random/N]" " [--reset=N]" "\n"); + + exit(status); } int main(int argc, char **argv) @@ -354,14 +356,12 @@ int main(int argc, char **argv) case -1: goto done; case '?': - help(); - exit(2); + help(2); case 'e': features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX); break; case 'h': - help(); - goto done; + help(0); case 'i': features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC); break; -- GitLab From 1adbd6b2fc0c09645c4c30c5eb47beaa3e6ea4b4 Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 10 Mar 2023 07:34:27 +0200 Subject: [PATCH 3680/5631] virtio_ring: Avoid using inline for small functions According to kernel coding style [1], defining inline functions is not necessary and beneficial for simple functions. Hence clean up the code by removing the inline keyword. It is verified with GCC 12.2.0, the generated code with/without inline is same. Additionally tested with pktgen and iperf, and verified the result, the pps test results are the same in the cases of with/without inline. Iperf and pps of pktgen for virtio-net didn't change before and after the change. [1] https://www.kernel.org/doc/html/v6.2-rc3/process/coding-style.html#the-inline-disease Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: Parav Pandit Reviewed-by: Gavin Li Reviewed-by: Bodong Wang Reviewed-by: David Edmondson Message-Id: <20230310053428.3376-3-feliu@nvidia.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 41144b5246a8..a26fab91c59f 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -233,8 +233,8 @@ static void vring_free(struct virtqueue *_vq); #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) -static inline bool virtqueue_use_indirect(struct vring_virtqueue *vq, - unsigned int total_sg) +static bool virtqueue_use_indirect(struct vring_virtqueue *vq, + unsigned int total_sg) { /* * If the host supports indirect descriptor tables, and we have multiple @@ -349,7 +349,7 @@ static void vring_free_queue(struct virtio_device *vdev, size_t size, * making all of the arch DMA ops work on the vring device itself * is a mess. */ -static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq) +static struct device *vring_dma_dev(const struct vring_virtqueue *vq) { return vq->dma_dev; } @@ -784,7 +784,7 @@ static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head, } } -static inline bool more_used_split(const struct vring_virtqueue *vq) +static bool more_used_split(const struct vring_virtqueue *vq) { return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->split.vring.used->idx); @@ -1172,12 +1172,12 @@ static int virtqueue_resize_split(struct virtqueue *_vq, u32 num) /* * Packed ring specific functions - *_packed(). */ -static inline bool packed_used_wrap_counter(u16 last_used_idx) +static bool packed_used_wrap_counter(u16 last_used_idx) { return !!(last_used_idx & (1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } -static inline u16 packed_last_used(u16 last_used_idx) +static u16 packed_last_used(u16 last_used_idx) { return last_used_idx & ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR)); } @@ -1612,7 +1612,7 @@ static inline bool is_used_desc_packed(const struct vring_virtqueue *vq, return avail == used && used == used_wrap_counter; } -static inline bool more_used_packed(const struct vring_virtqueue *vq) +static bool more_used_packed(const struct vring_virtqueue *vq) { u16 last_used; u16 last_used_idx; -- GitLab From 4b6ec919b84830949313c805c586fb34f141ce0c Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 10 Mar 2023 07:34:28 +0200 Subject: [PATCH 3681/5631] virtio_ring: Use const to annotate read-only pointer params Add const to make the read-only pointer parameters clear, similar to many existing functions. To implement this change, the commit also introduces the use of `container_of_const` to implement `to_vvq`, which ensures the const-ness of read-only parameters and avoids accidental modification of their members. Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: Parav Pandit Reviewed-by: Gavin Li Reviewed-by: Bodong Wang Message-Id: <20230310053428.3376-4-feliu@nvidia.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 36 ++++++++++++++++++------------------ include/linux/virtio.h | 14 +++++++------- 2 files changed, 25 insertions(+), 25 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index a26fab91c59f..4c3bb0ddeb9b 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -231,9 +231,9 @@ static void vring_free(struct virtqueue *_vq); * Helpers. */ -#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) +#define to_vvq(_vq) container_of_const(_vq, struct vring_virtqueue, vq) -static bool virtqueue_use_indirect(struct vring_virtqueue *vq, +static bool virtqueue_use_indirect(const struct vring_virtqueue *vq, unsigned int total_sg) { /* @@ -269,7 +269,7 @@ static bool virtqueue_use_indirect(struct vring_virtqueue *vq, * unconditionally on data path. */ -static bool vring_use_dma_api(struct virtio_device *vdev) +static bool vring_use_dma_api(const struct virtio_device *vdev) { if (!virtio_has_dma_quirk(vdev)) return true; @@ -289,7 +289,7 @@ static bool vring_use_dma_api(struct virtio_device *vdev) return false; } -size_t virtio_max_dma_size(struct virtio_device *vdev) +size_t virtio_max_dma_size(const struct virtio_device *vdev) { size_t max_segment_size = SIZE_MAX; @@ -423,7 +423,7 @@ static void virtqueue_init(struct vring_virtqueue *vq, u32 num) */ static void vring_unmap_one_split_indirect(const struct vring_virtqueue *vq, - struct vring_desc *desc) + const struct vring_desc *desc) { u16 flags; @@ -1183,7 +1183,7 @@ static u16 packed_last_used(u16 last_used_idx) } static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, - struct vring_desc_extra *extra) + const struct vring_desc_extra *extra) { u16 flags; @@ -1206,7 +1206,7 @@ static void vring_unmap_extra_packed(const struct vring_virtqueue *vq, } static void vring_unmap_desc_packed(const struct vring_virtqueue *vq, - struct vring_packed_desc *desc) + const struct vring_packed_desc *desc) { u16 flags; @@ -2786,10 +2786,10 @@ EXPORT_SYMBOL_GPL(vring_transport_features); * Returns the size of the vring. This is mainly used for boasting to * userspace. Unlike other operations, this need not be serialized. */ -unsigned int virtqueue_get_vring_size(struct virtqueue *_vq) +unsigned int virtqueue_get_vring_size(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num; } @@ -2819,9 +2819,9 @@ void __virtqueue_unbreak(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(__virtqueue_unbreak); -bool virtqueue_is_broken(struct virtqueue *_vq) +bool virtqueue_is_broken(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); return READ_ONCE(vq->broken); } @@ -2868,9 +2868,9 @@ void __virtio_unbreak_device(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(__virtio_unbreak_device); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2881,9 +2881,9 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2895,9 +2895,9 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq) +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *_vq) { - struct vring_virtqueue *vq = to_vvq(_vq); + const struct vring_virtqueue *vq = to_vvq(_vq); BUG_ON(!vq->we_own_ring); @@ -2910,7 +2910,7 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq) EXPORT_SYMBOL_GPL(virtqueue_get_used_addr); /* Only available for split ring */ -const struct vring *virtqueue_get_vring(struct virtqueue *vq) +const struct vring *virtqueue_get_vring(const struct virtqueue *vq) { return &to_vvq(vq)->split.vring; } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index d6e161aa532e..b93238db94e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -84,14 +84,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *vq); void *virtqueue_detach_unused_buf(struct virtqueue *vq); -unsigned int virtqueue_get_vring_size(struct virtqueue *vq); +unsigned int virtqueue_get_vring_size(const struct virtqueue *vq); -bool virtqueue_is_broken(struct virtqueue *vq); +bool virtqueue_is_broken(const struct virtqueue *vq); -const struct vring *virtqueue_get_vring(struct virtqueue *vq); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(const struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); @@ -147,7 +147,7 @@ int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); -size_t virtio_max_dma_size(struct virtio_device *vdev); +size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ list_for_each_entry(vq, &vdev->vqs, list) -- GitLab From 9a10cb4de33f4c914bd2e33ac05cff3ddb6a67b0 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Mar 2023 21:06:20 -0500 Subject: [PATCH 3682/5631] vhost-scsi: Delay releasing our refcount on the tpg We currently hold the vhost_scsi_mutex the entire time we are running vhost_scsi_clear_endpoint. One of the reasons for this is that it prevents userspace from being able to free the se_tpg from under us after we have called target_undepend_item. However, it forces management operations for for other devices to have to wait on a flakey device's: vhost_scsi_clear_endpoint -> vhost_scsi_flush() call which can which can take a long time. This moves the target_undepend_item call and the tpg unsetup code to after we have stopped new IO from starting up and after we have waited on running IO. We can then release our refcount on the tpg and session knowing our device is no longer accessing them. We can then drop the vhost_scsi_mutex use during thee flush call in later patches in this set, when we have removed other reasons for holding it. Signed-off-by: Mike Christie Message-Id: <20230321020624.13323-4-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 61 +++++++++++++++++++++++++++----------------- 1 file changed, 37 insertions(+), 24 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 32d0be968103..502d6803df0b 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1691,11 +1691,10 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, if (!tpg) continue; - mutex_lock(&tpg->tv_tpg_mutex); tv_tport = tpg->tport; if (!tv_tport) { ret = -ENODEV; - goto err_tpg; + goto err_dev; } if (strcmp(tv_tport->tport_name, t->vhost_wwpn)) { @@ -1704,35 +1703,51 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, tv_tport->tport_name, tpg->tport_tpgt, t->vhost_wwpn, t->vhost_tpgt); ret = -EINVAL; - goto err_tpg; + goto err_dev; } + match = true; + } + if (!match) + goto free_vs_tpg; + + /* Prevent new cmds from starting and accessing the tpgs/sessions */ + for (i = 0; i < vs->dev.nvqs; i++) { + vq = &vs->vqs[i].vq; + mutex_lock(&vq->mutex); + vhost_vq_set_backend(vq, NULL); + mutex_unlock(&vq->mutex); + } + /* Make sure cmds are not running before tearing them down. */ + vhost_scsi_flush(vs); + + for (i = 0; i < vs->dev.nvqs; i++) { + vq = &vs->vqs[i].vq; + vhost_scsi_destroy_vq_cmds(vq); + } + + /* + * We can now release our hold on the tpg and sessions and userspace + * can free them after this point. + */ + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + target = i; + tpg = vs->vs_tpg[target]; + if (!tpg) + continue; + + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_vhost_count--; tpg->vhost_scsi = NULL; vs->vs_tpg[target] = NULL; - match = true; + mutex_unlock(&tpg->tv_tpg_mutex); - /* - * Release se_tpg->tpg_group.cg_item configfs dependency now - * to allow vhost-scsi WWPN se_tpg->tpg_group shutdown to occur. - */ + se_tpg = &tpg->se_tpg; target_undepend_item(&se_tpg->tpg_group.cg_item); } - if (match) { - for (i = 0; i < vs->dev.nvqs; i++) { - vq = &vs->vqs[i].vq; - mutex_lock(&vq->mutex); - vhost_vq_set_backend(vq, NULL); - mutex_unlock(&vq->mutex); - } - /* Make sure cmds are not running before tearing them down. */ - vhost_scsi_flush(vs); - for (i = 0; i < vs->dev.nvqs; i++) { - vq = &vs->vqs[i].vq; - vhost_scsi_destroy_vq_cmds(vq); - } - } +free_vs_tpg: /* * Act as synchronize_rcu to make sure access to * old vs->vs_tpg is finished. @@ -1745,8 +1760,6 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, mutex_unlock(&vhost_scsi_mutex); return 0; -err_tpg: - mutex_unlock(&tpg->tv_tpg_mutex); err_dev: mutex_unlock(&vs->dev.mutex); mutex_unlock(&vhost_scsi_mutex); -- GitLab From eb1b291466376ad4d2f0a42392a2cd9f0e4983e5 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Mar 2023 21:06:21 -0500 Subject: [PATCH 3683/5631] vhost-scsi: Drop device mutex use in vhost_scsi_do_plug We don't need the device mutex in vhost_scsi_do_plug because: 1. we have the vhost_scsi_mutex so the tpg->vhost_scsi pointer will not change on us and the vhost_scsi can't be freed from under us if it was set. 2. vhost_scsi_clear_endpoint will stop the virtqueues and flush them while holding the vhost_scsi_mutex so we know once vhost_scsi_clear_endpoint has completed that vhost_scsi_do_plug can't send new events and any queued ones have completed. So this patch drops the device mutex use in vhost_scsi_do_plug. Signed-off-by: Mike Christie Message-Id: <20230321020624.13323-5-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 502d6803df0b..c945136ecf18 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -2003,8 +2003,6 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg, if (!vs) return; - mutex_lock(&vs->dev.mutex); - if (plug) reason = VIRTIO_SCSI_EVT_RESET_RESCAN; else @@ -2016,7 +2014,6 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg, vhost_scsi_send_evt(vs, tpg, lun, VIRTIO_SCSI_T_TRANSPORT_RESET, reason); mutex_unlock(&vq->mutex); - mutex_unlock(&vs->dev.mutex); } static void vhost_scsi_hotplug(struct vhost_scsi_tpg *tpg, struct se_lun *lun) -- GitLab From ced9eb376ab716ec5b06bef8c3e05608b8eb6700 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Mar 2023 21:06:22 -0500 Subject: [PATCH 3684/5631] vhost-scsi: Check for a cleared backend before queueing an event We currenly hold the vhost_scsi_mutex while clearing the endpoint and while performing vhost_scsi_do_plug, so tpg->vhost_scsi can't be freed from uder us, and to make sure anything queued is handled by the full call in vhost_scsi_clear_endpoint. This patch removes the need for the vhost_scsi_mutex for the latter case. In the next patches, we won't hold the vhost_scsi_mutex while flushing so this patch adds a check for the clearing of the virtqueue from vhost_scsi_clear_endpoint. We then know that once vhost_scsi_clear_endpoint has cleared the backend that no new events will be queued, and the flush after the vhost_vq_set_backend(vq, NULL) call will see everything that's been queued to that point. So the flush will then handle all events without the need for the vhost_scsi_mutex. Signed-off-by: Mike Christie Message-Id: <20230321020624.13323-6-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index c945136ecf18..ba8097fcea43 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -2010,9 +2010,17 @@ vhost_scsi_do_plug(struct vhost_scsi_tpg *tpg, vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq; mutex_lock(&vq->mutex); + /* + * We can't queue events if the backend has been cleared, because + * we could end up queueing an event after the flush. + */ + if (!vhost_vq_get_backend(vq)) + goto unlock; + if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG)) vhost_scsi_send_evt(vs, tpg, lun, VIRTIO_SCSI_T_TRANSPORT_RESET, reason); +unlock: mutex_unlock(&vq->mutex); } -- GitLab From f5ed6f9e82ee62bf805551522dfa2d6c8030bb47 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Mar 2023 21:06:23 -0500 Subject: [PATCH 3685/5631] vhost-scsi: Drop vhost_scsi_mutex use in port callouts We are using the vhost_scsi_mutex to make sure vhost_scsi_port_link and vhost_scsi_port_unlink see if vhost_scsi_clear_endpoint has cleared tpg->vhost_scsi and it can't be freed while they are using. However, we currently set the tpg->vhost_scsi pointer while holding tv_tpg_mutex. So, we can just hold that while calling vhost_scsi_hotplug/hotunplug. We then don't need to hold the vhost_scsi_mutex while vhost_scsi_clear_endpoint is holding it and doing a flush which could cause the LUN map/unmap to have to wait on another device's flush. Signed-off-by: Mike Christie Message-Id: <20230321020624.13323-7-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index ba8097fcea43..d4372a4aff49 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -2040,15 +2040,10 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - mutex_lock(&vhost_scsi_mutex); - mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; - mutex_unlock(&tpg->tv_tpg_mutex); - vhost_scsi_hotplug(tpg, lun); - - mutex_unlock(&vhost_scsi_mutex); + mutex_unlock(&tpg->tv_tpg_mutex); return 0; } @@ -2059,15 +2054,10 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); - mutex_lock(&vhost_scsi_mutex); - mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - vhost_scsi_hotunplug(tpg, lun); - - mutex_unlock(&vhost_scsi_mutex); + mutex_unlock(&tpg->tv_tpg_mutex); } static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( -- GitLab From bea273c7a8712a055cd504a2bb7d76d8d713ba6e Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 20 Mar 2023 21:06:24 -0500 Subject: [PATCH 3686/5631] vhost-scsi: Reduce vhost_scsi_mutex use We on longer need to hold the vhost_scsi_mutex the entire time we set/clear the endpoint. The tv_tpg_mutex handles tpg accesses not related to the tpg list, the port link/unlink functions use the tv_tpg_mutex while accessing the tpg->vhost_scsi pointer, vhost_scsi_do_plug will no longer queue events after the virtqueue's backend has been cleared and flushed, and we don't drop our refcount to the tpg until after we have stopped cmds and wait for outstanding cmds to complete. This moves the vhost_scsi_mutex use to it's documented use of being used to access the tpg list. We then don't need to hold it while a flush is being performed causing other device's vhost_scsi_set_endpoint and vhost_scsi_make_tpg/vhost_scsi_drop_tpg calls to have to wait on a flakey device. Signed-off-by: Mike Christie Message-Id: <20230321020624.13323-8-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/scsi.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index d4372a4aff49..3b0b556c57ef 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -229,7 +229,10 @@ struct vhost_scsi_ctx { struct iov_iter out_iter; }; -/* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ +/* + * Global mutex to protect vhost_scsi TPG list for vhost IOCTLs and LIO + * configfs management operations. + */ static DEFINE_MUTEX(vhost_scsi_mutex); static LIST_HEAD(vhost_scsi_list); @@ -1526,7 +1529,7 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) * vhost_scsi_tpg with an active struct vhost_scsi_nexus * * The lock nesting rule is: - * vhost_scsi_mutex -> vs->dev.mutex -> tpg->tv_tpg_mutex -> vq->mutex + * vs->dev.mutex -> vhost_scsi_mutex -> tpg->tv_tpg_mutex -> vq->mutex */ static int vhost_scsi_set_endpoint(struct vhost_scsi *vs, @@ -1540,7 +1543,6 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, int index, ret, i, len; bool match = false; - mutex_lock(&vhost_scsi_mutex); mutex_lock(&vs->dev.mutex); /* Verify that ring has been setup correctly. */ @@ -1561,6 +1563,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (vs->vs_tpg) memcpy(vs_tpg, vs->vs_tpg, len); + mutex_lock(&vhost_scsi_mutex); list_for_each_entry(tpg, &vhost_scsi_list, tv_tpg_list) { mutex_lock(&tpg->tv_tpg_mutex); if (!tpg->tpg_nexus) { @@ -1576,6 +1579,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { mutex_unlock(&tpg->tv_tpg_mutex); + mutex_unlock(&vhost_scsi_mutex); ret = -EEXIST; goto undepend; } @@ -1590,6 +1594,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); mutex_unlock(&tpg->tv_tpg_mutex); + mutex_unlock(&vhost_scsi_mutex); goto undepend; } tpg->tv_tpg_vhost_count++; @@ -1599,6 +1604,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, } mutex_unlock(&tpg->tv_tpg_mutex); } + mutex_unlock(&vhost_scsi_mutex); if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, @@ -1654,7 +1660,6 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return ret; } @@ -1670,7 +1675,6 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, int index, ret, i; u8 target; - mutex_lock(&vhost_scsi_mutex); mutex_lock(&vs->dev.mutex); /* Verify that ring has been setup correctly. */ for (index = 0; index < vs->dev.nvqs; ++index) { @@ -1757,12 +1761,10 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, vs->vs_tpg = NULL; WARN_ON(vs->vs_events_nr); mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return 0; err_dev: mutex_unlock(&vs->dev.mutex); - mutex_unlock(&vhost_scsi_mutex); return ret; } -- GitLab From a084983dcd4e75616fe4102c690d2fc922ac32b5 Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Wed, 15 Mar 2023 20:54:56 +0200 Subject: [PATCH 3687/5631] virtio_ring: Allow non power of 2 sizes for packed virtqueue According to the Virtio Specification, the Queue Size parameter of a virtqueue corresponds to the maximum number of descriptors in that queue, and it does not have to be a power of 2 for packed virtqueues. However, the virtio_pci_modern driver enforced a power of 2 check for virtqueue sizes, which is unnecessary and restrictive for packed virtuqueue. Split virtqueue still needs to check the virtqueue size is power_of_2 which has been done in vring_alloc_queue_split of the virtio_ring layer. To validate this change, we tested various virtqueue sizes for packed rings, including 128, 256, 512, 100, 200, 500, and 1000, with CONFIG_PAGE_POISONING enabled, and all tests passed successfully. Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Message-Id: <20230315185458.11638-2-feliu@nvidia.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_pci_modern.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 9e496e288cfa..6e713904d8e8 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -310,11 +310,6 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, if (!num || vp_modern_get_queue_enable(mdev, index)) return ERR_PTR(-ENOENT); - if (!is_power_of_2(num)) { - dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num); - return ERR_PTR(-EINVAL); - } - info->msix_vector = msix_vec; /* create the vring */ -- GitLab From 791a1cb7b8591ece6a5075dfed803da379e7ecd3 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 21 Mar 2023 13:28:08 +0200 Subject: [PATCH 3688/5631] vdpa/mlx5: Make VIRTIO_NET_F_MRG_RXBUF off by default Following patch adds driver support for VIRTIO_NET_F_MRG_RXBUF. Current firmware versions show degradation in packet rate when using MRG_RXBUF. Users who favor memory saving over packet rate could enable this feature but we want to keep it off by default. One can still enable it when creating the vdpa device using vdpa tool by providing features that include it. For example: $ vdpa dev add name vdpa0 mgmtdev pci/0000:86:00.2 device_features 0x300cb982b Acked-by: Jason Wang Signed-off-by: Eli Cohen Message-Id: <20230321112809.221432-2-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 97a16f7eb894..b5245956665b 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -3158,6 +3158,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, return -EINVAL; } device_features &= add_config->device_features; + } else { + device_features &= ~BIT_ULL(VIRTIO_NET_F_MRG_RXBUF); } if (!(device_features & BIT_ULL(VIRTIO_F_VERSION_1) && device_features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) { -- GitLab From e9d67e59f151eae964f749af74dbe4bd3b01b0d2 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 21 Mar 2023 13:28:09 +0200 Subject: [PATCH 3689/5631] vdpa/mlx5: Extend driver support for new features MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend the possible list for features that can be supported by firmware. Note that different versions of firmware may or may not support these features. The driver is made aware of them by querying the firmware. While doing this, improve the code so we use enum names instead of hard coded numerical values. The new features supported by the driver are the following: VIRTIO_NET_F_MRG_RXBUF VIRTIO_NET_F_HOST_ECN VIRTIO_NET_F_GUEST_ECN VIRTIO_NET_F_GUEST_TSO6 VIRTIO_NET_F_GUEST_TSO4 Reviewed-by: Si-Wei Liu Acked-by: Jason Wang Signed-off-by: Eli Cohen Message-Id: <20230321112809.221432-3-elic@nvidia.com> Signed-off-by: Michael S. Tsirkin Acked-by: Eugenio Pérez Martin --- drivers/vdpa/mlx5/net/mlx5_vnet.c | 56 ++++++++++++++++++++++--------- 1 file changed, 40 insertions(+), 16 deletions(-) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index b5245956665b..e29e32b306ad 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -778,12 +778,28 @@ static bool vq_is_tx(u16 idx) return idx % 2; } -static u16 get_features_12_3(u64 features) +enum { + MLX5_VIRTIO_NET_F_MRG_RXBUF = 2, + MLX5_VIRTIO_NET_F_HOST_ECN = 4, + MLX5_VIRTIO_NET_F_GUEST_ECN = 6, + MLX5_VIRTIO_NET_F_GUEST_TSO6 = 7, + MLX5_VIRTIO_NET_F_GUEST_TSO4 = 8, + MLX5_VIRTIO_NET_F_GUEST_CSUM = 9, + MLX5_VIRTIO_NET_F_CSUM = 10, + MLX5_VIRTIO_NET_F_HOST_TSO6 = 11, + MLX5_VIRTIO_NET_F_HOST_TSO4 = 12, +}; + +static u16 get_features(u64 features) { - return (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << 9) | - (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << 8) | - (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << 7) | - (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_CSUM)) << 6); + return (!!(features & BIT_ULL(VIRTIO_NET_F_MRG_RXBUF)) << MLX5_VIRTIO_NET_F_MRG_RXBUF) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_ECN)) << MLX5_VIRTIO_NET_F_HOST_ECN) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_ECN)) << MLX5_VIRTIO_NET_F_GUEST_ECN) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_TSO6)) << MLX5_VIRTIO_NET_F_GUEST_TSO6) | + (!!(features & BIT_ULL(VIRTIO_NET_F_GUEST_TSO4)) << MLX5_VIRTIO_NET_F_GUEST_TSO4) | + (!!(features & BIT_ULL(VIRTIO_NET_F_CSUM)) << MLX5_VIRTIO_NET_F_CSUM) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO6)) << MLX5_VIRTIO_NET_F_HOST_TSO6) | + (!!(features & BIT_ULL(VIRTIO_NET_F_HOST_TSO4)) << MLX5_VIRTIO_NET_F_HOST_TSO4); } static bool counters_supported(const struct mlx5_vdpa_dev *mvdev) @@ -797,6 +813,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque int inlen = MLX5_ST_SZ_BYTES(create_virtio_net_q_in); u32 out[MLX5_ST_SZ_DW(create_virtio_net_q_out)] = {}; void *obj_context; + u16 mlx_features; void *cmd_hdr; void *vq_ctx; void *in; @@ -812,6 +829,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque goto err_alloc; } + mlx_features = get_features(ndev->mvdev.actual_features); cmd_hdr = MLX5_ADDR_OF(create_virtio_net_q_in, in, general_obj_in_cmd_hdr); MLX5_SET(general_obj_in_cmd_hdr, cmd_hdr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT); @@ -822,7 +840,9 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(virtio_net_q_object, obj_context, hw_available_index, mvq->avail_idx); MLX5_SET(virtio_net_q_object, obj_context, hw_used_index, mvq->used_idx); MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_12_3, - get_features_12_3(ndev->mvdev.actual_features)); + mlx_features >> 3); + MLX5_SET(virtio_net_q_object, obj_context, queue_feature_bit_mask_2_0, + mlx_features & 7); vq_ctx = MLX5_ADDR_OF(virtio_net_q_object, obj_context, virtio_q_context); MLX5_SET(virtio_q, vq_ctx, virtio_q_type, get_queue_type(ndev)); @@ -2171,23 +2191,27 @@ static u32 mlx5_vdpa_get_vq_group(struct vdpa_device *vdev, u16 idx) return MLX5_VDPA_DATAVQ_GROUP; } -enum { MLX5_VIRTIO_NET_F_GUEST_CSUM = 1 << 9, - MLX5_VIRTIO_NET_F_CSUM = 1 << 10, - MLX5_VIRTIO_NET_F_HOST_TSO6 = 1 << 11, - MLX5_VIRTIO_NET_F_HOST_TSO4 = 1 << 12, -}; - static u64 mlx_to_vritio_features(u16 dev_features) { u64 result = 0; - if (dev_features & MLX5_VIRTIO_NET_F_GUEST_CSUM) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_MRG_RXBUF)) + result |= BIT_ULL(VIRTIO_NET_F_MRG_RXBUF); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_ECN)) + result |= BIT_ULL(VIRTIO_NET_F_HOST_ECN); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_ECN)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_ECN); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_TSO6)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_TSO6); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_TSO4)) + result |= BIT_ULL(VIRTIO_NET_F_GUEST_TSO4); + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_GUEST_CSUM)) result |= BIT_ULL(VIRTIO_NET_F_GUEST_CSUM); - if (dev_features & MLX5_VIRTIO_NET_F_CSUM) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_CSUM)) result |= BIT_ULL(VIRTIO_NET_F_CSUM); - if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO6) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_TSO6)) result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO6); - if (dev_features & MLX5_VIRTIO_NET_F_HOST_TSO4) + if (dev_features & BIT_ULL(MLX5_VIRTIO_NET_F_HOST_TSO4)) result |= BIT_ULL(VIRTIO_NET_F_HOST_TSO4); return result; -- GitLab From aaf0594829c3a6f16bdf5d30904a7db4548dae15 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:33 +0800 Subject: [PATCH 3690/5631] lib/group_cpus: Export group_cpus_evenly() Export group_cpus_evenly() so that some modules can make use of it to group CPUs evenly according to NUMA and CPU locality. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-2-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- lib/group_cpus.c | 1 + 1 file changed, 1 insertion(+) diff --git a/lib/group_cpus.c b/lib/group_cpus.c index 9c837a35fef7..aa3f6815bb12 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -426,3 +426,4 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) return masks; } #endif /* CONFIG_SMP */ +EXPORT_SYMBOL_GPL(group_cpus_evenly); -- GitLab From 1d24692732fb299c94b0dcc032b48ac8fa85c854 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:34 +0800 Subject: [PATCH 3691/5631] vdpa: Add set/get_vq_affinity callbacks in vdpa_config_ops This introduces set/get_vq_affinity callbacks in vdpa_config_ops to support virtqueue affinity management for vdpa device drivers. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-3-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_vdpa.c | 28 ++++++++++++++++++++++++++++ include/linux/vdpa.h | 13 +++++++++++++ 2 files changed, 41 insertions(+) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index d7f5af62ddaa..f72696b4c1c2 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -337,6 +337,32 @@ static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) return dev_name(&vdpa->dev); } +static int virtio_vdpa_set_vq_affinity(struct virtqueue *vq, + const struct cpumask *cpu_mask) +{ + struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev); + struct vdpa_device *vdpa = vd_dev->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + unsigned int index = vq->index; + + if (ops->set_vq_affinity) + return ops->set_vq_affinity(vdpa, index, cpu_mask); + + return 0; +} + +static const struct cpumask * +virtio_vdpa_get_vq_affinity(struct virtio_device *vdev, int index) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vdev); + const struct vdpa_config_ops *ops = vdpa->config; + + if (ops->get_vq_affinity) + return ops->get_vq_affinity(vdpa, index); + + return NULL; +} + static const struct virtio_config_ops virtio_vdpa_config_ops = { .get = virtio_vdpa_get, .set = virtio_vdpa_set, @@ -349,6 +375,8 @@ static const struct virtio_config_ops virtio_vdpa_config_ops = { .get_features = virtio_vdpa_get_features, .finalize_features = virtio_vdpa_finalize_features, .bus_name = virtio_vdpa_bus_name, + .set_vq_affinity = virtio_vdpa_set_vq_affinity, + .get_vq_affinity = virtio_vdpa_get_vq_affinity, }; static void virtio_vdpa_release_dev(struct device *_d) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 43f59ef10cc9..2313db735773 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -250,6 +250,15 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_vq_affinity: Set the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * @cpu_mask: the affinity mask + * Returns integer: success (0) or error (< 0) + * @get_vq_affinity: Get the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the affinity mask * @set_group_asid: Set address space identifier for a * virtqueue group (optional) * @vdev: vdpa device @@ -340,6 +349,10 @@ struct vdpa_config_ops { const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); + int (*set_vq_affinity)(struct vdpa_device *vdev, u16 idx, + const struct cpumask *cpu_mask); + const struct cpumask *(*get_vq_affinity)(struct vdpa_device *vdev, + u16 idx); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, unsigned int asid, -- GitLab From 3dad56823b5332ffdbe1867b2d7b50fbacea124a Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:35 +0800 Subject: [PATCH 3692/5631] virtio-vdpa: Support interrupt affinity spreading mechanism To support interrupt affinity spreading mechanism, this makes use of group_cpus_evenly() to create an irq callback affinity mask for each virtqueue of vdpa device. Then we will unify set_vq_affinity callback to pass the affinity to the vdpa device driver. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-4-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_vdpa.c | 68 ++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index f72696b4c1c2..f3826f42b704 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -272,6 +273,66 @@ static void virtio_vdpa_del_vqs(struct virtio_device *vdev) virtio_vdpa_del_vq(vq); } +static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) +{ + affd->nr_sets = 1; + affd->set_size[0] = affvecs; +} + +static struct cpumask * +create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd) +{ + unsigned int affvecs = 0, curvec, usedvecs, i; + struct cpumask *masks = NULL; + + if (nvecs > affd->pre_vectors + affd->post_vectors) + affvecs = nvecs - affd->pre_vectors - affd->post_vectors; + + if (!affd->calc_sets) + affd->calc_sets = default_calc_sets; + + affd->calc_sets(affd, affvecs); + + if (!affvecs) + return NULL; + + masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL); + if (!masks) + return NULL; + + /* Fill out vectors at the beginning that don't need affinity */ + for (curvec = 0; curvec < affd->pre_vectors; curvec++) + cpumask_setall(&masks[curvec]); + + for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) { + unsigned int this_vecs = affd->set_size[i]; + int j; + struct cpumask *result = group_cpus_evenly(this_vecs); + + if (!result) { + kfree(masks); + return NULL; + } + + for (j = 0; j < this_vecs; j++) + cpumask_copy(&masks[curvec + j], &result[j]); + kfree(result); + + curvec += this_vecs; + usedvecs += this_vecs; + } + + /* Fill out vectors at the end that don't need affinity */ + if (usedvecs >= affvecs) + curvec = affd->pre_vectors + affvecs; + else + curvec = affd->pre_vectors + usedvecs; + for (; curvec < nvecs; curvec++) + cpumask_setall(&masks[curvec]); + + return masks; +} + static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtqueue *vqs[], vq_callback_t *callbacks[], @@ -282,9 +343,15 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev); struct vdpa_device *vdpa = vd_get_vdpa(vdev); const struct vdpa_config_ops *ops = vdpa->config; + struct irq_affinity default_affd = { 0 }; + struct cpumask *masks; struct vdpa_callback cb; int i, err, queue_idx = 0; + masks = create_affinity_masks(nvqs, desc ? desc : &default_affd); + if (!masks) + return -ENOMEM; + for (i = 0; i < nvqs; ++i) { if (!names[i]) { vqs[i] = NULL; @@ -298,6 +365,7 @@ static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned int nvqs, err = PTR_ERR(vqs[i]); goto err_setup_vq; } + ops->set_vq_affinity(vdpa, i, &masks[i]); } cb.callback = virtio_vdpa_config_cb; -- GitLab From 78885597b9ccf68d4ce554aec98db01ee3c2d3fc Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:36 +0800 Subject: [PATCH 3693/5631] vduse: Refactor allocation for vduse virtqueues Allocate memory for vduse virtqueues one by one instead of doing one allocation for all of them. This is a preparation for adding sysfs interface for virtqueues. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-5-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_user/vduse_dev.c | 98 ++++++++++++++++++++---------- 1 file changed, 66 insertions(+), 32 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 0c3b48616a9f..98359d87a06f 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -76,7 +76,7 @@ struct vduse_umem { struct vduse_dev { struct vduse_vdpa *vdev; struct device *dev; - struct vduse_virtqueue *vqs; + struct vduse_virtqueue **vqs; struct vduse_iova_domain *domain; char *name; struct mutex lock; @@ -434,7 +434,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) flush_work(&dev->inject); for (i = 0; i < dev->vq_num; i++) { - struct vduse_virtqueue *vq = &dev->vqs[i]; + struct vduse_virtqueue *vq = dev->vqs[i]; vq->ready = false; vq->desc_addr = 0; @@ -466,7 +466,7 @@ static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx, u64 device_area) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->desc_addr = desc_area; vq->driver_addr = driver_area; @@ -500,7 +500,7 @@ static void vduse_vq_kick_work(struct work_struct *work) static void vduse_vdpa_kick_vq(struct vdpa_device *vdpa, u16 idx) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (!eventfd_signal_allowed()) { schedule_work(&vq->kick); @@ -513,7 +513,7 @@ static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx, struct vdpa_callback *cb) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; spin_lock(&vq->irq_lock); vq->cb.callback = cb->callback; @@ -524,7 +524,7 @@ static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx, static void vduse_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->num = num; } @@ -533,7 +533,7 @@ static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; vq->ready = ready; } @@ -541,7 +541,7 @@ static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa, static bool vduse_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 idx) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; return vq->ready; } @@ -550,7 +550,7 @@ static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx, const struct vdpa_vq_state *state) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) { vq->state.packed.last_avail_counter = @@ -569,7 +569,7 @@ static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx, struct vdpa_vq_state *state) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - struct vduse_virtqueue *vq = &dev->vqs[idx]; + struct vduse_virtqueue *vq = dev->vqs[idx]; if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) return vduse_dev_get_vq_state_packed(dev, vq, &state->packed); @@ -624,8 +624,8 @@ static u16 vduse_vdpa_get_vq_num_max(struct vdpa_device *vdpa) int i; for (i = 0; i < dev->vq_num; i++) - if (num_max < dev->vqs[i].num_max) - num_max = dev->vqs[i].num_max; + if (num_max < dev->vqs[i]->num_max) + num_max = dev->vqs[i]->num_max; return num_max; } @@ -863,7 +863,7 @@ static int vduse_kickfd_setup(struct vduse_dev *dev, return -EINVAL; index = array_index_nospec(eventfd->index, dev->vq_num); - vq = &dev->vqs[index]; + vq = dev->vqs[index]; if (eventfd->fd >= 0) { ctx = eventfd_ctx_fdget(eventfd->fd); if (IS_ERR(ctx)) @@ -889,7 +889,7 @@ static bool vduse_dev_is_ready(struct vduse_dev *dev) int i; for (i = 0; i < dev->vq_num; i++) - if (!dev->vqs[i].num_max) + if (!dev->vqs[i]->num_max) return false; return true; @@ -1130,7 +1130,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(config.index, dev->vq_num); - dev->vqs[index].num_max = config.max_size; + dev->vqs[index]->num_max = config.max_size; ret = 0; break; } @@ -1148,7 +1148,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(vq_info.index, dev->vq_num); - vq = &dev->vqs[index]; + vq = dev->vqs[index]; vq_info.desc_addr = vq->desc_addr; vq_info.driver_addr = vq->driver_addr; vq_info.device_addr = vq->device_addr; @@ -1198,7 +1198,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(index, dev->vq_num); - ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject); + ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index]->inject); break; } case VDUSE_IOTLB_REG_UMEM: { @@ -1339,6 +1339,49 @@ static const struct file_operations vduse_dev_fops = { .llseek = noop_llseek, }; +static void vduse_dev_deinit_vqs(struct vduse_dev *dev) +{ + int i; + + if (!dev->vqs) + return; + + for (i = 0; i < dev->vq_num; i++) + kfree(dev->vqs[i]); + kfree(dev->vqs); +} + +static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) +{ + int i; + + dev->vq_align = vq_align; + dev->vq_num = vq_num; + dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL); + if (!dev->vqs) + return -ENOMEM; + + for (i = 0; i < vq_num; i++) { + dev->vqs[i] = kzalloc(sizeof(*dev->vqs[i]), GFP_KERNEL); + if (!dev->vqs[i]) + goto err; + + dev->vqs[i]->index = i; + INIT_WORK(&dev->vqs[i]->inject, vduse_vq_irq_inject); + INIT_WORK(&dev->vqs[i]->kick, vduse_vq_kick_work); + spin_lock_init(&dev->vqs[i]->kick_lock); + spin_lock_init(&dev->vqs[i]->irq_lock); + } + + return 0; +err: + while (i--) + kfree(dev->vqs[i]); + kfree(dev->vqs); + dev->vqs = NULL; + return -ENOMEM; +} + static struct vduse_dev *vduse_dev_create(void) { struct vduse_dev *dev = kzalloc(sizeof(*dev), GFP_KERNEL); @@ -1396,7 +1439,7 @@ static int vduse_destroy_dev(char *name) device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor)); idr_remove(&vduse_idr, dev->minor); kvfree(dev->config); - kfree(dev->vqs); + vduse_dev_deinit_vqs(dev); vduse_domain_destroy(dev->domain); kfree(dev->name); vduse_dev_destroy(dev); @@ -1486,7 +1529,7 @@ ATTRIBUTE_GROUPS(vduse_dev); static int vduse_create_dev(struct vduse_dev_config *config, void *config_buf, u64 api_version) { - int i, ret; + int ret; struct vduse_dev *dev; ret = -EEXIST; @@ -1513,19 +1556,10 @@ static int vduse_create_dev(struct vduse_dev_config *config, dev->config = config_buf; dev->config_size = config->config_size; - dev->vq_align = config->vq_align; - dev->vq_num = config->vq_num; - dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL); - if (!dev->vqs) - goto err_vqs; - for (i = 0; i < dev->vq_num; i++) { - dev->vqs[i].index = i; - INIT_WORK(&dev->vqs[i].inject, vduse_vq_irq_inject); - INIT_WORK(&dev->vqs[i].kick, vduse_vq_kick_work); - spin_lock_init(&dev->vqs[i].kick_lock); - spin_lock_init(&dev->vqs[i].irq_lock); - } + ret = vduse_dev_init_vqs(dev, config->vq_align, config->vq_num); + if (ret) + goto err_vqs; ret = idr_alloc(&vduse_idr, dev, 1, VDUSE_DEV_MAX, GFP_KERNEL); if (ret < 0) @@ -1546,7 +1580,7 @@ static int vduse_create_dev(struct vduse_dev_config *config, err_dev: idr_remove(&vduse_idr, dev->minor); err_idr: - kfree(dev->vqs); + vduse_dev_deinit_vqs(dev); err_vqs: vduse_domain_destroy(dev->domain); err_domain: -- GitLab From 28f6288eb63d5979fa6758e64f52e4d55cf184a8 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:37 +0800 Subject: [PATCH 3694/5631] vduse: Support set_vq_affinity callback Since virtio-vdpa bus driver already support interrupt affinity spreading mechanism, let's implement the set_vq_affinity callback to bring it to vduse device. After we get the virtqueue's affinity, we can spread IRQs between CPUs in the affinity mask, in a round-robin manner, to run the irq callback. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-6-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 61 ++++++++++++++++++++++++++---- 1 file changed, 54 insertions(+), 7 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 98359d87a06f..45aa8703c4b5 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -41,6 +41,8 @@ #define VDUSE_IOVA_SIZE (128 * 1024 * 1024) #define VDUSE_MSG_DEFAULT_TIMEOUT 30 +#define IRQ_UNBOUND -1 + struct vduse_virtqueue { u16 index; u16 num_max; @@ -57,6 +59,8 @@ struct vduse_virtqueue { struct vdpa_callback cb; struct work_struct inject; struct work_struct kick; + int irq_effective_cpu; + struct cpumask irq_affinity; }; struct vduse_dev; @@ -128,6 +132,7 @@ static struct class *vduse_class; static struct cdev vduse_ctrl_cdev; static struct cdev vduse_cdev; static struct workqueue_struct *vduse_irq_wq; +static struct workqueue_struct *vduse_irq_bound_wq; static u32 allowed_device_id[] = { VIRTIO_ID_BLOCK, @@ -708,6 +713,15 @@ static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa) return dev->generation; } +static int vduse_vdpa_set_vq_affinity(struct vdpa_device *vdpa, u16 idx, + const struct cpumask *cpu_mask) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + cpumask_copy(&dev->vqs[idx]->irq_affinity, cpu_mask); + return 0; +} + static int vduse_vdpa_set_map(struct vdpa_device *vdpa, unsigned int asid, struct vhost_iotlb *iotlb) @@ -758,6 +772,7 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = { .get_config = vduse_vdpa_get_config, .set_config = vduse_vdpa_set_config, .get_generation = vduse_vdpa_get_generation, + .set_vq_affinity = vduse_vdpa_set_vq_affinity, .reset = vduse_vdpa_reset, .set_map = vduse_vdpa_set_map, .free = vduse_vdpa_free, @@ -917,7 +932,8 @@ static void vduse_vq_irq_inject(struct work_struct *work) } static int vduse_dev_queue_irq_work(struct vduse_dev *dev, - struct work_struct *irq_work) + struct work_struct *irq_work, + int irq_effective_cpu) { int ret = -EINVAL; @@ -926,7 +942,11 @@ static int vduse_dev_queue_irq_work(struct vduse_dev *dev, goto unlock; ret = 0; - queue_work(vduse_irq_wq, irq_work); + if (irq_effective_cpu == IRQ_UNBOUND) + queue_work(vduse_irq_wq, irq_work); + else + queue_work_on(irq_effective_cpu, + vduse_irq_bound_wq, irq_work); unlock: up_read(&dev->rwsem); @@ -1029,6 +1049,22 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev, return ret; } +static void vduse_vq_update_effective_cpu(struct vduse_virtqueue *vq) +{ + int curr_cpu = vq->irq_effective_cpu; + + while (true) { + curr_cpu = cpumask_next(curr_cpu, &vq->irq_affinity); + if (cpu_online(curr_cpu)) + break; + + if (curr_cpu >= nr_cpu_ids) + curr_cpu = IRQ_UNBOUND; + } + + vq->irq_effective_cpu = curr_cpu; +} + static long vduse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -1111,7 +1147,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; } case VDUSE_DEV_INJECT_CONFIG_IRQ: - ret = vduse_dev_queue_irq_work(dev, &dev->inject); + ret = vduse_dev_queue_irq_work(dev, &dev->inject, IRQ_UNBOUND); break; case VDUSE_VQ_SETUP: { struct vduse_vq_config config; @@ -1198,7 +1234,10 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; index = array_index_nospec(index, dev->vq_num); - ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index]->inject); + + vduse_vq_update_effective_cpu(dev->vqs[index]); + ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index]->inject, + dev->vqs[index]->irq_effective_cpu); break; } case VDUSE_IOTLB_REG_UMEM: { @@ -1367,10 +1406,12 @@ static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) goto err; dev->vqs[i]->index = i; + dev->vqs[i]->irq_effective_cpu = IRQ_UNBOUND; INIT_WORK(&dev->vqs[i]->inject, vduse_vq_irq_inject); INIT_WORK(&dev->vqs[i]->kick, vduse_vq_kick_work); spin_lock_init(&dev->vqs[i]->kick_lock); spin_lock_init(&dev->vqs[i]->irq_lock); + cpumask_setall(&dev->vqs[i]->irq_affinity); } return 0; @@ -1858,12 +1899,15 @@ static int vduse_init(void) if (ret) goto err_cdev; + ret = -ENOMEM; vduse_irq_wq = alloc_workqueue("vduse-irq", WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0); - if (!vduse_irq_wq) { - ret = -ENOMEM; + if (!vduse_irq_wq) goto err_wq; - } + + vduse_irq_bound_wq = alloc_workqueue("vduse-irq-bound", WQ_HIGHPRI, 0); + if (!vduse_irq_bound_wq) + goto err_bound_wq; ret = vduse_domain_init(); if (ret) @@ -1877,6 +1921,8 @@ static int vduse_init(void) err_mgmtdev: vduse_domain_exit(); err_domain: + destroy_workqueue(vduse_irq_bound_wq); +err_bound_wq: destroy_workqueue(vduse_irq_wq); err_wq: cdev_del(&vduse_cdev); @@ -1896,6 +1942,7 @@ static void vduse_exit(void) { vduse_mgmtdev_exit(); vduse_domain_exit(); + destroy_workqueue(vduse_irq_bound_wq); destroy_workqueue(vduse_irq_wq); cdev_del(&vduse_cdev); device_destroy(vduse_class, vduse_major); -- GitLab From bfae1648ec2159da0a14d71a7d75b810f728a1e6 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:38 +0800 Subject: [PATCH 3695/5631] vduse: Support get_vq_affinity callback This implements get_vq_affinity callback so that the virtio-blk driver can build the blk-mq queues based on the irq callback affinity. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-7-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 45aa8703c4b5..cefabd0dab9c 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -722,6 +722,14 @@ static int vduse_vdpa_set_vq_affinity(struct vdpa_device *vdpa, u16 idx, return 0; } +static const struct cpumask * +vduse_vdpa_get_vq_affinity(struct vdpa_device *vdpa, u16 idx) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return &dev->vqs[idx]->irq_affinity; +} + static int vduse_vdpa_set_map(struct vdpa_device *vdpa, unsigned int asid, struct vhost_iotlb *iotlb) @@ -773,6 +781,7 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = { .set_config = vduse_vdpa_set_config, .get_generation = vduse_vdpa_get_generation, .set_vq_affinity = vduse_vdpa_set_vq_affinity, + .get_vq_affinity = vduse_vdpa_get_vq_affinity, .reset = vduse_vdpa_reset, .set_map = vduse_vdpa_set_map, .free = vduse_vdpa_free, -- GitLab From 66640f4a6fcc1861d1b1f9b36b65a218064f263f Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:39 +0800 Subject: [PATCH 3696/5631] vduse: Add sysfs interface for irq callback affinity Add sysfs interface for each vduse virtqueue to get/set the affinity for irq callback. This might be useful for performance tuning when the irq callback affinity mask contains more than one CPU. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-8-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/vdpa_user/vduse_dev.c | 124 ++++++++++++++++++++++++++--- 1 file changed, 113 insertions(+), 11 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index cefabd0dab9c..77da3685568a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -61,6 +61,7 @@ struct vduse_virtqueue { struct work_struct kick; int irq_effective_cpu; struct cpumask irq_affinity; + struct kobject kobj; }; struct vduse_dev; @@ -1387,6 +1388,96 @@ static const struct file_operations vduse_dev_fops = { .llseek = noop_llseek, }; +static ssize_t irq_cb_affinity_show(struct vduse_virtqueue *vq, char *buf) +{ + return sprintf(buf, "%*pb\n", cpumask_pr_args(&vq->irq_affinity)); +} + +static ssize_t irq_cb_affinity_store(struct vduse_virtqueue *vq, + const char *buf, size_t count) +{ + cpumask_var_t new_value; + int ret; + + if (!zalloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + + ret = cpumask_parse(buf, new_value); + if (ret) + goto free_mask; + + ret = -EINVAL; + if (!cpumask_intersects(new_value, cpu_online_mask)) + goto free_mask; + + cpumask_copy(&vq->irq_affinity, new_value); + ret = count; +free_mask: + free_cpumask_var(new_value); + return ret; +} + +struct vq_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct vduse_virtqueue *vq, char *buf); + ssize_t (*store)(struct vduse_virtqueue *vq, const char *buf, + size_t count); +}; + +static struct vq_sysfs_entry irq_cb_affinity_attr = __ATTR_RW(irq_cb_affinity); + +static struct attribute *vq_attrs[] = { + &irq_cb_affinity_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(vq); + +static ssize_t vq_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + struct vq_sysfs_entry *entry = container_of(attr, + struct vq_sysfs_entry, attr); + + if (!entry->show) + return -EIO; + + return entry->show(vq, buf); +} + +static ssize_t vq_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + struct vq_sysfs_entry *entry = container_of(attr, + struct vq_sysfs_entry, attr); + + if (!entry->store) + return -EIO; + + return entry->store(vq, buf, count); +} + +static const struct sysfs_ops vq_sysfs_ops = { + .show = vq_attr_show, + .store = vq_attr_store, +}; + +static void vq_release(struct kobject *kobj) +{ + struct vduse_virtqueue *vq = container_of(kobj, + struct vduse_virtqueue, kobj); + kfree(vq); +} + +static const struct kobj_type vq_type = { + .release = vq_release, + .sysfs_ops = &vq_sysfs_ops, + .default_groups = vq_groups, +}; + static void vduse_dev_deinit_vqs(struct vduse_dev *dev) { int i; @@ -1395,13 +1486,13 @@ static void vduse_dev_deinit_vqs(struct vduse_dev *dev) return; for (i = 0; i < dev->vq_num; i++) - kfree(dev->vqs[i]); + kobject_put(&dev->vqs[i]->kobj); kfree(dev->vqs); } static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) { - int i; + int ret, i; dev->vq_align = vq_align; dev->vq_num = vq_num; @@ -1411,8 +1502,10 @@ static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) for (i = 0; i < vq_num; i++) { dev->vqs[i] = kzalloc(sizeof(*dev->vqs[i]), GFP_KERNEL); - if (!dev->vqs[i]) + if (!dev->vqs[i]) { + ret = -ENOMEM; goto err; + } dev->vqs[i]->index = i; dev->vqs[i]->irq_effective_cpu = IRQ_UNBOUND; @@ -1421,15 +1514,23 @@ static int vduse_dev_init_vqs(struct vduse_dev *dev, u32 vq_align, u32 vq_num) spin_lock_init(&dev->vqs[i]->kick_lock); spin_lock_init(&dev->vqs[i]->irq_lock); cpumask_setall(&dev->vqs[i]->irq_affinity); + + kobject_init(&dev->vqs[i]->kobj, &vq_type); + ret = kobject_add(&dev->vqs[i]->kobj, + &dev->dev->kobj, "vq%d", i); + if (ret) { + kfree(dev->vqs[i]); + goto err; + } } return 0; err: while (i--) - kfree(dev->vqs[i]); + kobject_put(&dev->vqs[i]->kobj); kfree(dev->vqs); dev->vqs = NULL; - return -ENOMEM; + return ret; } static struct vduse_dev *vduse_dev_create(void) @@ -1607,10 +1708,6 @@ static int vduse_create_dev(struct vduse_dev_config *config, dev->config = config_buf; dev->config_size = config->config_size; - ret = vduse_dev_init_vqs(dev, config->vq_align, config->vq_num); - if (ret) - goto err_vqs; - ret = idr_alloc(&vduse_idr, dev, 1, VDUSE_DEV_MAX, GFP_KERNEL); if (ret < 0) goto err_idr; @@ -1624,14 +1721,19 @@ static int vduse_create_dev(struct vduse_dev_config *config, ret = PTR_ERR(dev->dev); goto err_dev; } + + ret = vduse_dev_init_vqs(dev, config->vq_align, config->vq_num); + if (ret) + goto err_vqs; + __module_get(THIS_MODULE); return 0; +err_vqs: + device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor)); err_dev: idr_remove(&vduse_idr, dev->minor); err_idr: - vduse_dev_deinit_vqs(dev); -err_vqs: vduse_domain_destroy(dev->domain); err_domain: kfree(dev->name); -- GitLab From 5e68470f4e80a4120e9ecec408f6ab4ad386bd4a Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:40 +0800 Subject: [PATCH 3697/5631] vdpa: Add eventfd for the vdpa callback Add eventfd for the vdpa callback so that user can signal it directly instead of triggering the callback. It will be used for vhost-vdpa case. Signed-off-by: Xie Yongji Message-Id: <20230323053043.35-9-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vhost/vdpa.c | 2 ++ drivers/virtio/virtio_vdpa.c | 1 + include/linux/vdpa.h | 6 ++++++ 3 files changed, 9 insertions(+) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 7be9d9d8f01c..9cd878e25cff 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -599,9 +599,11 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, if (vq->call_ctx.ctx) { cb.callback = vhost_vdpa_virtqueue_cb; cb.private = vq; + cb.trigger = vq->call_ctx.ctx; } else { cb.callback = NULL; cb.private = NULL; + cb.trigger = NULL; } ops->set_vq_cb(vdpa, idx, &cb); vhost_vdpa_setup_vq_irq(v, idx); diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index f3826f42b704..2a095f37f26b 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -196,6 +196,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, /* Setup virtqueue callback */ cb.callback = callback ? virtio_vdpa_virtqueue_cb : NULL; cb.private = info; + cb.trigger = NULL; ops->set_vq_cb(vdpa, index, &cb); ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq)); diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2313db735773..f2064fa2d2da 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -13,10 +13,16 @@ * struct vdpa_calllback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function + * @trigger: the eventfd for the callback (Optional). + * When it is set, the vDPA driver must guarantee that + * signaling it is functional equivalent to triggering + * the callback. Then vDPA parent can signal it directly + * instead of triggering the callback. */ struct vdpa_callback { irqreturn_t (*callback)(void *data); void *private; + struct eventfd_ctx *trigger; }; /** -- GitLab From e38632dd71818d99bcebeb55f27dc764a9f7d547 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:41 +0800 Subject: [PATCH 3698/5631] vduse: Signal vq trigger eventfd directly if possible Now the vdpa callback will associate an trigger eventfd in some cases. For performance reasons, VDUSE can signal it directly during irq injection. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-10-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_user/vduse_dev.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 77da3685568a..8c06f6ab960b 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -459,6 +459,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) spin_lock(&vq->irq_lock); vq->cb.callback = NULL; vq->cb.private = NULL; + vq->cb.trigger = NULL; spin_unlock(&vq->irq_lock); flush_work(&vq->inject); flush_work(&vq->kick); @@ -524,6 +525,7 @@ static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx, spin_lock(&vq->irq_lock); vq->cb.callback = cb->callback; vq->cb.private = cb->private; + vq->cb.trigger = cb->trigger; spin_unlock(&vq->irq_lock); } @@ -941,6 +943,23 @@ static void vduse_vq_irq_inject(struct work_struct *work) spin_unlock_irq(&vq->irq_lock); } +static bool vduse_vq_signal_irqfd(struct vduse_virtqueue *vq) +{ + bool signal = false; + + if (!vq->cb.trigger) + return false; + + spin_lock_irq(&vq->irq_lock); + if (vq->ready && vq->cb.trigger) { + eventfd_signal(vq->cb.trigger, 1); + signal = true; + } + spin_unlock_irq(&vq->irq_lock); + + return signal; +} + static int vduse_dev_queue_irq_work(struct vduse_dev *dev, struct work_struct *irq_work, int irq_effective_cpu) @@ -1243,11 +1262,14 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (index >= dev->vq_num) break; + ret = 0; index = array_index_nospec(index, dev->vq_num); - - vduse_vq_update_effective_cpu(dev->vqs[index]); - ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index]->inject, - dev->vqs[index]->irq_effective_cpu); + if (!vduse_vq_signal_irqfd(dev->vqs[index])) { + vduse_vq_update_effective_cpu(dev->vqs[index]); + ret = vduse_dev_queue_irq_work(dev, + &dev->vqs[index]->inject, + dev->vqs[index]->irq_effective_cpu); + } break; } case VDUSE_IOTLB_REG_UMEM: { -- GitLab From d4438d23eeeef8bb1b3a8abe418abffd60bb544a Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:42 +0800 Subject: [PATCH 3699/5631] vduse: Delay iova domain creation Delay creating iova domain until the vduse device is registered to vdpa bus. This is a preparation for adding sysfs interface to support specifying bounce buffer size for the iova domain. Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-11-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_user/vduse_dev.c | 75 +++++++++++++++++++++--------- 1 file changed, 53 insertions(+), 22 deletions(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 8c06f6ab960b..ccca84d51a28 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -111,6 +111,8 @@ struct vduse_dev { u32 vq_align; struct vduse_umem *umem; struct mutex mem_lock; + unsigned int bounce_size; + struct mutex domain_lock; }; struct vduse_dev_msg { @@ -425,7 +427,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) struct vduse_iova_domain *domain = dev->domain; /* The coherent mappings are handled in vduse_dev_free_coherent() */ - if (domain->bounce_map) + if (domain && domain->bounce_map) vduse_domain_reset_bounce_map(domain); down_write(&dev->rwsem); @@ -993,6 +995,9 @@ static int vduse_dev_dereg_umem(struct vduse_dev *dev, goto unlock; ret = -EINVAL; + if (!dev->domain) + goto unlock; + if (dev->umem->iova != iova || size != dev->domain->bounce_size) goto unlock; @@ -1019,7 +1024,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev, unsigned long npages, lock_limit; int ret; - if (!dev->domain->bounce_map || + if (!dev->domain || !dev->domain->bounce_map || size != dev->domain->bounce_size || iova != 0 || uaddr & ~PAGE_MASK) return -EINVAL; @@ -1109,7 +1114,6 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, struct vduse_iotlb_entry entry; struct vhost_iotlb_map *map; struct vdpa_map_file *map_file; - struct vduse_iova_domain *domain = dev->domain; struct file *f = NULL; ret = -EFAULT; @@ -1120,8 +1124,13 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (entry.start > entry.last) break; - spin_lock(&domain->iotlb_lock); - map = vhost_iotlb_itree_first(domain->iotlb, + mutex_lock(&dev->domain_lock); + if (!dev->domain) { + mutex_unlock(&dev->domain_lock); + break; + } + spin_lock(&dev->domain->iotlb_lock); + map = vhost_iotlb_itree_first(dev->domain->iotlb, entry.start, entry.last); if (map) { map_file = (struct vdpa_map_file *)map->opaque; @@ -1131,7 +1140,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, entry.last = map->last; entry.perm = map->perm; } - spin_unlock(&domain->iotlb_lock); + spin_unlock(&dev->domain->iotlb_lock); + mutex_unlock(&dev->domain_lock); ret = -EINVAL; if (!f) break; @@ -1284,8 +1294,10 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, sizeof(umem.reserved))) break; + mutex_lock(&dev->domain_lock); ret = vduse_dev_reg_umem(dev, umem.iova, umem.uaddr, umem.size); + mutex_unlock(&dev->domain_lock); break; } case VDUSE_IOTLB_DEREG_UMEM: { @@ -1299,15 +1311,15 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, if (!is_mem_zero((const char *)umem.reserved, sizeof(umem.reserved))) break; - + mutex_lock(&dev->domain_lock); ret = vduse_dev_dereg_umem(dev, umem.iova, umem.size); + mutex_unlock(&dev->domain_lock); break; } case VDUSE_IOTLB_GET_INFO: { struct vduse_iova_info info; struct vhost_iotlb_map *map; - struct vduse_iova_domain *domain = dev->domain; ret = -EFAULT; if (copy_from_user(&info, argp, sizeof(info))) @@ -1321,18 +1333,24 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, sizeof(info.reserved))) break; - spin_lock(&domain->iotlb_lock); - map = vhost_iotlb_itree_first(domain->iotlb, + mutex_lock(&dev->domain_lock); + if (!dev->domain) { + mutex_unlock(&dev->domain_lock); + break; + } + spin_lock(&dev->domain->iotlb_lock); + map = vhost_iotlb_itree_first(dev->domain->iotlb, info.start, info.last); if (map) { info.start = map->start; info.last = map->last; info.capability = 0; - if (domain->bounce_map && map->start == 0 && - map->last == domain->bounce_size - 1) + if (dev->domain->bounce_map && map->start == 0 && + map->last == dev->domain->bounce_size - 1) info.capability |= VDUSE_IOVA_CAP_UMEM; } - spin_unlock(&domain->iotlb_lock); + spin_unlock(&dev->domain->iotlb_lock); + mutex_unlock(&dev->domain_lock); if (!map) break; @@ -1355,7 +1373,10 @@ static int vduse_dev_release(struct inode *inode, struct file *file) { struct vduse_dev *dev = file->private_data; - vduse_dev_dereg_umem(dev, 0, dev->domain->bounce_size); + mutex_lock(&dev->domain_lock); + if (dev->domain) + vduse_dev_dereg_umem(dev, 0, dev->domain->bounce_size); + mutex_unlock(&dev->domain_lock); spin_lock(&dev->msg_lock); /* Make sure the inflight messages can processed after reconncection */ list_splice_init(&dev->recv_list, &dev->send_list); @@ -1564,6 +1585,7 @@ static struct vduse_dev *vduse_dev_create(void) mutex_init(&dev->lock); mutex_init(&dev->mem_lock); + mutex_init(&dev->domain_lock); spin_lock_init(&dev->msg_lock); INIT_LIST_HEAD(&dev->send_list); INIT_LIST_HEAD(&dev->recv_list); @@ -1613,7 +1635,8 @@ static int vduse_destroy_dev(char *name) idr_remove(&vduse_idr, dev->minor); kvfree(dev->config); vduse_dev_deinit_vqs(dev); - vduse_domain_destroy(dev->domain); + if (dev->domain) + vduse_domain_destroy(dev->domain); kfree(dev->name); vduse_dev_destroy(dev); module_put(THIS_MODULE); @@ -1722,11 +1745,7 @@ static int vduse_create_dev(struct vduse_dev_config *config, if (!dev->name) goto err_str; - dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1, - VDUSE_BOUNCE_SIZE); - if (!dev->domain) - goto err_domain; - + dev->bounce_size = VDUSE_BOUNCE_SIZE; dev->config = config_buf; dev->config_size = config->config_size; @@ -1756,8 +1775,6 @@ static int vduse_create_dev(struct vduse_dev_config *config, err_dev: idr_remove(&vduse_idr, dev->minor); err_idr: - vduse_domain_destroy(dev->domain); -err_domain: kfree(dev->name); err_str: vduse_dev_destroy(dev); @@ -1924,9 +1941,23 @@ static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, if (ret) return ret; + mutex_lock(&dev->domain_lock); + if (!dev->domain) + dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1, + dev->bounce_size); + mutex_unlock(&dev->domain_lock); + if (!dev->domain) { + put_device(&dev->vdev->vdpa.dev); + return -ENOMEM; + } + ret = _vdpa_register_device(&dev->vdev->vdpa, dev->vq_num); if (ret) { put_device(&dev->vdev->vdpa.dev); + mutex_lock(&dev->domain_lock); + vduse_domain_destroy(dev->domain); + dev->domain = NULL; + mutex_unlock(&dev->domain_lock); return ret; } -- GitLab From b774f93d87e198481680873b22c2a443e10c3f93 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Thu, 23 Mar 2023 13:30:43 +0800 Subject: [PATCH 3700/5631] vduse: Support specifying bounce buffer size via sysfs As discussed in [1], this adds sysfs interface to support specifying bounce buffer size in virtio-vdpa case. It would be a performance tuning parameter for high throughput workloads. [1] https://lore.kernel.org/netdev/e8f25a35-9d45-69f9-795d-bdbbb90337a3@redhat.com/ Signed-off-by: Xie Yongji Acked-by: Jason Wang Message-Id: <20230323053043.35-12-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_user/vduse_dev.c | 45 +++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index ccca84d51a28..34eebdf030af 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -37,8 +37,11 @@ #define DRV_LICENSE "GPL v2" #define VDUSE_DEV_MAX (1U << MINORBITS) +#define VDUSE_MAX_BOUNCE_SIZE (1024 * 1024 * 1024) +#define VDUSE_MIN_BOUNCE_SIZE (1024 * 1024) #define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024) -#define VDUSE_IOVA_SIZE (128 * 1024 * 1024) +/* 128 MB reserved for virtqueue creation */ +#define VDUSE_IOVA_SIZE (VDUSE_MAX_BOUNCE_SIZE + 128 * 1024 * 1024) #define VDUSE_MSG_DEFAULT_TIMEOUT 30 #define IRQ_UNBOUND -1 @@ -1715,8 +1718,48 @@ static ssize_t msg_timeout_store(struct device *device, static DEVICE_ATTR_RW(msg_timeout); +static ssize_t bounce_size_show(struct device *device, + struct device_attribute *attr, char *buf) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + + return sysfs_emit(buf, "%u\n", dev->bounce_size); +} + +static ssize_t bounce_size_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct vduse_dev *dev = dev_get_drvdata(device); + unsigned int bounce_size; + int ret; + + ret = -EPERM; + mutex_lock(&dev->domain_lock); + if (dev->domain) + goto unlock; + + ret = kstrtouint(buf, 10, &bounce_size); + if (ret < 0) + goto unlock; + + ret = -EINVAL; + if (bounce_size > VDUSE_MAX_BOUNCE_SIZE || + bounce_size < VDUSE_MIN_BOUNCE_SIZE) + goto unlock; + + dev->bounce_size = bounce_size & PAGE_MASK; + ret = count; +unlock: + mutex_unlock(&dev->domain_lock); + return ret; +} + +static DEVICE_ATTR_RW(bounce_size); + static struct attribute *vduse_dev_attrs[] = { &dev_attr_msg_timeout.attr, + &dev_attr_bounce_size.attr, NULL }; -- GitLab From 905233af513c0c6971cae0f25280f23be1f6cbe4 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 31 Mar 2023 10:02:08 +0200 Subject: [PATCH 3701/5631] vringh: fix typos in the vringh_init_* documentation Replace `userpace` with `userspace`. Cc: Simon Horman Signed-off-by: Stefano Garzarella Message-Id: <20230331080208.17002-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin Reviewed-by: Xuan Zhuo Acked-by: Jason Wang --- drivers/vhost/vringh.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index a1e27da54481..694462ba3242 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -636,9 +636,9 @@ static inline int xfer_to_user(const struct vringh *vrh, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid: you should check pointers * yourself! @@ -911,9 +911,9 @@ static inline int kern_xfer(const struct vringh *vrh, void *dst, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid. */ @@ -1306,9 +1306,9 @@ static inline int putused_iotlb(const struct vringh *vrh, * @features: the feature bits for this ring. * @num: the number of elements. * @weak_barriers: true if we only need memory barriers, not I/O. - * @desc: the userpace descriptor pointer. - * @avail: the userpace avail pointer. - * @used: the userpace used pointer. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. * * Returns an error if num is invalid. */ -- GitLab From c618c84d4ccc6268c3da7609c7388b6cb305c639 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:13:18 +0200 Subject: [PATCH 3702/5631] vdpa: add bind_mm/unbind_mm callbacks These new optional callbacks is used to bind/unbind the device to a specific address space so the vDPA framework can use VA when these callbacks are implemented. Suggested-by: Jason Wang Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131326.44403-2-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index f2064fa2d2da..2f1af73b3a1a 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -305,6 +305,14 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * Returns pointer to structure device or error (NULL) + * @bind_mm: Bind the device to a specific address space + * so the vDPA framework can use VA when this + * callback is implemented. (optional) + * @vdev: vdpa device + * @mm: address space to bind + * @unbind_mm: Unbind the device from the address space + * bound using the bind_mm callback. (optional) + * @vdev: vdpa device * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -370,6 +378,8 @@ struct vdpa_config_ops { int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); + int (*bind_mm)(struct vdpa_device *vdev, struct mm_struct *mm); + void (*unbind_mm)(struct vdpa_device *vdev); /* Free device resources */ void (*free)(struct vdpa_device *vdev); -- GitLab From 9067de4725a299bc1baf11de9f5040fdd0bd05c3 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:13:19 +0200 Subject: [PATCH 3703/5631] vhost-vdpa: use bind_mm/unbind_mm device callbacks When the user call VHOST_SET_OWNER ioctl and the vDPA device has `use_va` set to true, let's call the bind_mm callback. In this way we can bind the device to the user address space and directly use the user VA. The unbind_mm callback is called during the release after stopping the device. Signed-off-by: Stefano Garzarella Message-Id: <20230404131326.44403-3-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 9cd878e25cff..cd266fa80c4e 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -219,6 +219,28 @@ static int vhost_vdpa_reset(struct vhost_vdpa *v) return vdpa_reset(vdpa); } +static long vhost_vdpa_bind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->bind_mm) + return 0; + + return ops->bind_mm(vdpa, v->vdev.mm); +} + +static void vhost_vdpa_unbind_mm(struct vhost_vdpa *v) +{ + struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; + + if (!vdpa->use_va || !ops->unbind_mm) + return; + + ops->unbind_mm(vdpa); +} + static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) { struct vdpa_device *vdpa = v->vdpa; @@ -718,6 +740,17 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, break; } + if (r) + goto out; + + switch (cmd) { + case VHOST_SET_OWNER: + r = vhost_vdpa_bind_mm(v); + if (r) + vhost_dev_reset_owner(d, NULL); + break; + } +out: mutex_unlock(&d->mutex); return r; } @@ -1289,6 +1322,7 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); + vhost_vdpa_unbind_mm(v); vhost_vdpa_config_put(v); vhost_vdpa_cleanup(v); mutex_unlock(&d->mutex); -- GitLab From c0371782500c5314741da9ccbfbf0375a0d379fc Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:13:20 +0200 Subject: [PATCH 3704/5631] vringh: replace kmap_atomic() with kmap_local_page() kmap_atomic() is deprecated in favor of kmap_local_page() since commit f3ba3c710ac5 ("mm/highmem: Provide kmap_local*"). With kmap_local_page() the mappings are per thread, CPU local, can take page-faults, and can be called from any context (including interrupts). Furthermore, the tasks can be preempted and, when they are scheduled to run again, the kernel virtual addresses are restored and still valid. kmap_atomic() is implemented like a kmap_local_page() which also disables page-faults and preemption (the latter only for !PREEMPT_RT kernels, otherwise it only disables migration). The code within the mappings/un-mappings in getu16_iotlb() and putu16_iotlb() don't depend on the above-mentioned side effects of kmap_atomic(), so that mere replacements of the old API with the new one is all that is required (i.e., there is no need to explicitly add calls to pagefault_disable() and/or preempt_disable()). This commit reuses a "boiler plate" commit message from Fabio, who has already did this change in several places. Cc: "Fabio M. De Francesco" Reviewed-by: Fabio M. De Francesco Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131326.44403-4-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vringh.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 694462ba3242..a98adc469f19 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1220,10 +1220,10 @@ static inline int getu16_iotlb(const struct vringh *vrh, if (ret < 0) return ret; - kaddr = kmap_atomic(iov.bv_page); + kaddr = kmap_local_page(iov.bv_page); from = kaddr + iov.bv_offset; *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); - kunmap_atomic(kaddr); + kunmap_local(kaddr); return 0; } @@ -1241,10 +1241,10 @@ static inline int putu16_iotlb(const struct vringh *vrh, if (ret < 0) return ret; - kaddr = kmap_atomic(iov.bv_page); + kaddr = kmap_local_page(iov.bv_page); to = kaddr + iov.bv_offset; WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); - kunmap_atomic(kaddr); + kunmap_local(kaddr); return 0; } -- GitLab From f609d6cbb36ab1c9c7434f67d555c57a2f7d3dde Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:13:21 +0200 Subject: [PATCH 3705/5631] vringh: define the stride used for translation Define a macro to be reused in the different parts of the code. Useful for the next patches where we add more arrays to manage also translations with user VA. Suggested-by: Eugenio Perez Martin Signed-off-by: Stefano Garzarella Message-Id: <20230404131326.44403-5-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vringh.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index a98adc469f19..3d5f6bb4ac31 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1141,13 +1141,15 @@ static int iotlb_translate(const struct vringh *vrh, return ret; } +#define IOTLB_IOV_STRIDE 16 + static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { u64 total_translated = 0; while (total_translated < len) { - struct bio_vec iov[16]; + struct bio_vec iov[IOTLB_IOV_STRIDE]; struct iov_iter iter; u64 translated; int ret; @@ -1180,7 +1182,7 @@ static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, u64 total_translated = 0; while (total_translated < len) { - struct bio_vec iov[16]; + struct bio_vec iov[IOTLB_IOV_STRIDE]; struct iov_iter iter; u64 translated; int ret; -- GitLab From 42823a871fd4e17b34034f43b36ae57bd2ed8a67 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:16 +0200 Subject: [PATCH 3706/5631] vringh: support VA with iotlb MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vDPA supports the possibility to use user VA in the iotlb messages. So, let's add support for user VA in vringh to use it in the vDPA simulators. Acked-by: Eugenio Pérez Signed-off-by: Stefano Garzarella Message-Id: <20230404131716.45855-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vringh.c | 171 +++++++++++++++++++++++++++++++++-------- include/linux/vringh.h | 9 +++ 2 files changed, 148 insertions(+), 32 deletions(-) diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 3d5f6bb4ac31..955d938eb663 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -1094,10 +1094,17 @@ EXPORT_SYMBOL(vringh_need_notify_kern); #if IS_REACHABLE(CONFIG_VHOST_IOTLB) +struct iotlb_vec { + union { + struct iovec *iovec; + struct bio_vec *bvec; + } iov; + size_t count; +}; + static int iotlb_translate(const struct vringh *vrh, u64 addr, u64 len, u64 *translated, - struct bio_vec iov[], - int iov_size, u32 perm) + struct iotlb_vec *ivec, u32 perm) { struct vhost_iotlb_map *map; struct vhost_iotlb *iotlb = vrh->iotlb; @@ -1107,9 +1114,11 @@ static int iotlb_translate(const struct vringh *vrh, spin_lock(vrh->iotlb_lock); while (len > s) { - u64 size, pa, pfn; + uintptr_t io_addr; + size_t io_len; + u64 size; - if (unlikely(ret >= iov_size)) { + if (unlikely(ret >= ivec->count)) { ret = -ENOBUFS; break; } @@ -1124,10 +1133,22 @@ static int iotlb_translate(const struct vringh *vrh, } size = map->size - addr + map->start; - pa = map->addr + addr - map->start; - pfn = pa >> PAGE_SHIFT; - bvec_set_page(&iov[ret], pfn_to_page(pfn), min(len - s, size), - pa & (PAGE_SIZE - 1)); + io_len = min(len - s, size); + io_addr = map->addr - map->start + addr; + + if (vrh->use_va) { + struct iovec *iovec = ivec->iov.iovec; + + iovec[ret].iov_len = io_len; + iovec[ret].iov_base = (void __user *)io_addr; + } else { + u64 pfn = io_addr >> PAGE_SHIFT; + struct bio_vec *bvec = ivec->iov.bvec; + + bvec_set_page(&bvec[ret], pfn_to_page(pfn), io_len, + io_addr & (PAGE_SIZE - 1)); + } + s += size; addr += size; ++ret; @@ -1146,23 +1167,36 @@ static int iotlb_translate(const struct vringh *vrh, static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; u64 total_translated = 0; + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + while (total_translated < len) { - struct bio_vec iov[IOTLB_IOV_STRIDE]; struct iov_iter iter; u64 translated; int ret; ret = iotlb_translate(vrh, (u64)(uintptr_t)src, len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_RO); + &ivec, VHOST_MAP_RO); if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); + ret = IOTLB_IOV_STRIDE; else if (ret < 0) return ret; - iov_iter_bvec(&iter, ITER_SOURCE, iov, ret, translated); + if (vrh->use_va) { + iov_iter_init(&iter, ITER_SOURCE, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_SOURCE, ivec.iov.bvec, ret, + translated); + } ret = copy_from_iter(dst, translated, &iter); if (ret < 0) @@ -1179,23 +1213,36 @@ static inline int copy_from_iotlb(const struct vringh *vrh, void *dst, static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, void *src, size_t len) { + struct iotlb_vec ivec; + union { + struct iovec iovec[IOTLB_IOV_STRIDE]; + struct bio_vec bvec[IOTLB_IOV_STRIDE]; + } iov; u64 total_translated = 0; + ivec.iov.iovec = iov.iovec; + ivec.count = IOTLB_IOV_STRIDE; + while (total_translated < len) { - struct bio_vec iov[IOTLB_IOV_STRIDE]; struct iov_iter iter; u64 translated; int ret; ret = iotlb_translate(vrh, (u64)(uintptr_t)dst, len - total_translated, &translated, - iov, ARRAY_SIZE(iov), VHOST_MAP_WO); + &ivec, VHOST_MAP_WO); if (ret == -ENOBUFS) - ret = ARRAY_SIZE(iov); + ret = IOTLB_IOV_STRIDE; else if (ret < 0) return ret; - iov_iter_bvec(&iter, ITER_DEST, iov, ret, translated); + if (vrh->use_va) { + iov_iter_init(&iter, ITER_DEST, ivec.iov.iovec, ret, + translated); + } else { + iov_iter_bvec(&iter, ITER_DEST, ivec.iov.bvec, ret, + translated); + } ret = copy_to_iter(src, translated, &iter); if (ret < 0) @@ -1212,20 +1259,36 @@ static inline int copy_to_iotlb(const struct vringh *vrh, void *dst, static inline int getu16_iotlb(const struct vringh *vrh, u16 *val, const __virtio16 *p) { - struct bio_vec iov; - void *kaddr, *from; + struct iotlb_vec ivec; + union { + struct iovec iovec[1]; + struct bio_vec bvec[1]; + } iov; + __virtio16 tmp; int ret; + ivec.iov.iovec = iov.iovec; + ivec.count = 1; + /* Atomic read is needed for getu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_RO); + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); if (ret < 0) return ret; - kaddr = kmap_local_page(iov.bv_page); - from = kaddr + iov.bv_offset; - *val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from)); - kunmap_local(kaddr); + if (vrh->use_va) { + ret = __get_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + void *kaddr = kmap_local_page(ivec.iov.bvec[0].bv_page); + void *from = kaddr + ivec.iov.bvec[0].bv_offset; + + tmp = READ_ONCE(*(__virtio16 *)from); + kunmap_local(kaddr); + } + + *val = vringh16_to_cpu(vrh, tmp); return 0; } @@ -1233,20 +1296,36 @@ static inline int getu16_iotlb(const struct vringh *vrh, static inline int putu16_iotlb(const struct vringh *vrh, __virtio16 *p, u16 val) { - struct bio_vec iov; - void *kaddr, *to; + struct iotlb_vec ivec; + union { + struct iovec iovec; + struct bio_vec bvec; + } iov; + __virtio16 tmp; int ret; + ivec.iov.iovec = &iov.iovec; + ivec.count = 1; + /* Atomic write is needed for putu16 */ - ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL, - &iov, 1, VHOST_MAP_WO); + ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), + NULL, &ivec, VHOST_MAP_RO); if (ret < 0) return ret; - kaddr = kmap_local_page(iov.bv_page); - to = kaddr + iov.bv_offset; - WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val)); - kunmap_local(kaddr); + tmp = cpu_to_vringh16(vrh, val); + + if (vrh->use_va) { + ret = __put_user(tmp, (__virtio16 __user *)ivec.iov.iovec[0].iov_base); + if (ret) + return ret; + } else { + void *kaddr = kmap_local_page(ivec.iov.bvec[0].bv_page); + void *to = kaddr + ivec.iov.bvec[0].bv_offset; + + WRITE_ONCE(*(__virtio16 *)to, tmp); + kunmap_local(kaddr); + } return 0; } @@ -1320,11 +1399,39 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used) { + vrh->use_va = false; + return vringh_init_kern(vrh, features, num, weak_barriers, desc, avail, used); } EXPORT_SYMBOL(vringh_init_iotlb); +/** + * vringh_init_iotlb_va - initialize a vringh for a ring with IOTLB containing + * user VA. + * @vrh: the vringh to initialize. + * @features: the feature bits for this ring. + * @num: the number of elements. + * @weak_barriers: true if we only need memory barriers, not I/O. + * @desc: the userspace descriptor pointer. + * @avail: the userspace avail pointer. + * @used: the userspace used pointer. + * + * Returns an error if num is invalid. + */ +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used) +{ + vrh->use_va = true; + + return vringh_init_kern(vrh, features, num, weak_barriers, + desc, avail, used); +} +EXPORT_SYMBOL(vringh_init_iotlb_va); + /** * vringh_set_iotlb - initialize a vringh for a ring with IOTLB. * @vrh: the vring diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 1991a02c6431..b4edfadf5479 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -284,6 +287,12 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used); +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, -- GitLab From e2a4f808a78646badefcd13a6e995d369898f443 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:21 +0200 Subject: [PATCH 3707/5631] vdpa_sim: make devices agnostic for work management MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Let's move work management inside the vdpa_sim core. This way we can easily change how we manage the works, without having to change the devices each time. Acked-by: Eugenio Pérez Martin Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131721.45886-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 17 +++++++++++++++-- drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 ++- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 6 ++---- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 6 ++---- 4 files changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index eea23c630f7c..2df5227e0b62 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -127,6 +127,13 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) static const struct vdpa_config_ops vdpasim_config_ops; static const struct vdpa_config_ops vdpasim_batch_config_ops; +static void vdpasim_work_fn(struct work_struct *work) +{ + struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); + + vdpasim->dev_attr.work_fn(vdpasim); +} + struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, const struct vdpa_dev_set_config *config) { @@ -163,7 +170,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, vdpasim = vdpa_to_sim(vdpa); vdpasim->dev_attr = *dev_attr; - INIT_WORK(&vdpasim->work, dev_attr->work_fn); + INIT_WORK(&vdpasim->work, vdpasim_work_fn); spin_lock_init(&vdpasim->lock); spin_lock_init(&vdpasim->iommu_lock); @@ -214,6 +221,12 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, } EXPORT_SYMBOL_GPL(vdpasim_create); +void vdpasim_schedule_work(struct vdpasim *vdpasim) +{ + schedule_work(&vdpasim->work); +} +EXPORT_SYMBOL_GPL(vdpasim_schedule_work); + static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx, u64 desc_area, u64 driver_area, u64 device_area) @@ -248,7 +261,7 @@ static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx) } if (vq->ready) - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); } static void vdpasim_set_vq_cb(struct vdpa_device *vdpa, u16 idx, diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index 144858636c10..acee20faaf6a 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -45,7 +45,7 @@ struct vdpasim_dev_attr { u32 ngroups; u32 nas; - work_func_t work_fn; + void (*work_fn)(struct vdpasim *vdpasim); void (*get_config)(struct vdpasim *vdpasim, void *config); void (*set_config)(struct vdpasim *vdpasim, const void *config); int (*get_stats)(struct vdpasim *vdpasim, u16 idx, @@ -78,6 +78,7 @@ struct vdpasim { struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr, const struct vdpa_dev_set_config *config); +void vdpasim_schedule_work(struct vdpasim *vdpasim); /* TODO: cross-endian support */ static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index 5117959bed8a..eb4897c8541e 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -286,9 +285,8 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, return handled; } -static void vdpasim_blk_work(struct work_struct *work) +static void vdpasim_blk_work(struct vdpasim *vdpasim) { - struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); bool reschedule = false; int i; @@ -326,7 +324,7 @@ static void vdpasim_blk_work(struct work_struct *work) spin_unlock(&vdpasim->lock); if (reschedule) - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); } static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index dfe2ce341803..30ac41c5827e 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include @@ -192,9 +191,8 @@ static void vdpasim_handle_cvq(struct vdpasim *vdpasim) u64_stats_update_end(&net->cq_stats.syncp); } -static void vdpasim_net_work(struct work_struct *work) +static void vdpasim_net_work(struct vdpasim *vdpasim) { - struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); struct vdpasim_virtqueue *txq = &vdpasim->vqs[1]; struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0]; struct vdpasim_net *net = sim_to_net(vdpasim); @@ -260,7 +258,7 @@ static void vdpasim_net_work(struct work_struct *work) vdpasim_net_complete(rxq, write); if (tx_pkts > 4) { - schedule_work(&vdpasim->work); + vdpasim_schedule_work(vdpasim); goto out; } } -- GitLab From 76acfa7bc54f1e3b9dde396e0a3534493419fd6f Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:25 +0200 Subject: [PATCH 3708/5631] vdpa_sim: use kthread worker Let's use our own kthread to run device jobs. This allows us more flexibility, especially we can attach the kthread to the user address space when vDPA uses user's VA. Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131725.45908-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 19 +++++++++++++------ drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 ++- 2 files changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 2df5227e0b62..bd9f9054de94 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -11,8 +11,8 @@ #include #include #include +#include #include -#include #include #include #include @@ -127,7 +127,7 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim) static const struct vdpa_config_ops vdpasim_config_ops; static const struct vdpa_config_ops vdpasim_batch_config_ops; -static void vdpasim_work_fn(struct work_struct *work) +static void vdpasim_work_fn(struct kthread_work *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); @@ -170,11 +170,17 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, vdpasim = vdpa_to_sim(vdpa); vdpasim->dev_attr = *dev_attr; - INIT_WORK(&vdpasim->work, vdpasim_work_fn); + dev = &vdpasim->vdpa.dev; + + kthread_init_work(&vdpasim->work, vdpasim_work_fn); + vdpasim->worker = kthread_create_worker(0, "vDPA sim worker: %s", + dev_attr->name); + if (IS_ERR(vdpasim->worker)) + goto err_iommu; + spin_lock_init(&vdpasim->lock); spin_lock_init(&vdpasim->iommu_lock); - dev = &vdpasim->vdpa.dev; dev->dma_mask = &dev->coherent_dma_mask; if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) goto err_iommu; @@ -223,7 +229,7 @@ EXPORT_SYMBOL_GPL(vdpasim_create); void vdpasim_schedule_work(struct vdpasim *vdpasim) { - schedule_work(&vdpasim->work); + kthread_queue_work(vdpasim->worker, &vdpasim->work); } EXPORT_SYMBOL_GPL(vdpasim_schedule_work); @@ -623,7 +629,8 @@ static void vdpasim_free(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int i; - cancel_work_sync(&vdpasim->work); + kthread_cancel_work_sync(&vdpasim->work); + kthread_destroy_worker(vdpasim->worker); for (i = 0; i < vdpasim->dev_attr.nvqs; i++) { vringh_kiov_cleanup(&vdpasim->vqs[i].out_iov); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index acee20faaf6a..ce83f9130a5d 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -57,7 +57,8 @@ struct vdpasim_dev_attr { struct vdpasim { struct vdpa_device vdpa; struct vdpasim_virtqueue *vqs; - struct work_struct work; + struct kthread_worker *worker; + struct kthread_work work; struct vdpasim_dev_attr dev_attr; /* spinlock to synchronize virtqueue state */ spinlock_t lock; -- GitLab From d7621c28fca1c16f9e94245479792024a5676c50 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:29 +0200 Subject: [PATCH 3709/5631] vdpa_sim: replace the spinlock with a mutex to protect the state The spinlock we use to protect the state of the simulator is sometimes held for a long time (for example, when devices handle requests). This also prevents us from calling functions that might sleep (such as kthread_flush_work() in the next patch), and thus having to release and retake the lock. For these reasons, let's replace the spinlock with a mutex that gives us more flexibility. Suggested-by: Jason Wang Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131730.45920-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 34 ++++++++++++++-------------- drivers/vdpa/vdpa_sim/vdpa_sim.h | 4 ++-- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 4 ++-- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 4 ++-- 4 files changed, 23 insertions(+), 23 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index bd9f9054de94..2b2e439a66f7 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -178,7 +178,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, if (IS_ERR(vdpasim->worker)) goto err_iommu; - spin_lock_init(&vdpasim->lock); + mutex_init(&vdpasim->mutex); spin_lock_init(&vdpasim->iommu_lock); dev->dma_mask = &dev->coherent_dma_mask; @@ -286,13 +286,13 @@ static void vdpasim_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready) struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; bool old_ready; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); old_ready = vq->ready; vq->ready = ready; if (vq->ready && !old_ready) { vdpasim_queue_ready(vdpasim, idx); } - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); } static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx) @@ -310,9 +310,9 @@ static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; struct vringh *vrh = &vq->vring; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vrh->last_avail_idx = state->split.avail_index; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -409,9 +409,9 @@ static u8 vdpasim_get_status(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); u8 status; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); status = vdpasim->status; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return status; } @@ -420,19 +420,19 @@ static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->status = status; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); } static int vdpasim_reset(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->status = 0; vdpasim_do_reset(vdpasim); - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -441,9 +441,9 @@ static int vdpasim_suspend(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->running = false; - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -453,7 +453,7 @@ static int vdpasim_resume(struct vdpa_device *vdpa) struct vdpasim *vdpasim = vdpa_to_sim(vdpa); int i; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); vdpasim->running = true; if (vdpasim->pending_kick) { @@ -464,7 +464,7 @@ static int vdpasim_resume(struct vdpa_device *vdpa) vdpasim->pending_kick = false; } - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } @@ -536,14 +536,14 @@ static int vdpasim_set_group_asid(struct vdpa_device *vdpa, unsigned int group, iommu = &vdpasim->iommu[asid]; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); for (i = 0; i < vdpasim->dev_attr.nvqs; i++) if (vdpasim_get_vq_group(vdpa, i) == group) vringh_set_iotlb(&vdpasim->vqs[i].vring, iommu, &vdpasim->iommu_lock); - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); return 0; } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index ce83f9130a5d..4774292fba8c 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -60,8 +60,8 @@ struct vdpasim { struct kthread_worker *worker; struct kthread_work work; struct vdpasim_dev_attr dev_attr; - /* spinlock to synchronize virtqueue state */ - spinlock_t lock; + /* mutex to synchronize virtqueue state */ + struct mutex mutex; /* virtio config according to device type */ void *config; struct vhost_iotlb *iommu; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index eb4897c8541e..568119e1553f 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -290,7 +290,7 @@ static void vdpasim_blk_work(struct vdpasim *vdpasim) bool reschedule = false; int i; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK)) goto out; @@ -321,7 +321,7 @@ static void vdpasim_blk_work(struct vdpasim *vdpasim) } } out: - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); if (reschedule) vdpasim_schedule_work(vdpasim); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 30ac41c5827e..55920502f76b 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -201,7 +201,7 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) u64 rx_drops = 0, rx_overruns = 0, rx_errors = 0, tx_errors = 0; int err; - spin_lock(&vdpasim->lock); + mutex_lock(&vdpasim->mutex); if (!vdpasim->running) goto out; @@ -264,7 +264,7 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) } out: - spin_unlock(&vdpasim->lock); + mutex_unlock(&vdpasim->mutex); u64_stats_update_begin(&net->tx_stats.syncp); net->tx_stats.pkts += tx_pkts; -- GitLab From 4bb94d2de2fa90aa8d4e1ce940b1b2f7708cf141 Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Tue, 4 Apr 2023 15:17:34 +0200 Subject: [PATCH 3710/5631] vdpa_sim: add support for user VA The new "use_va" module parameter (default: true) is used in vdpa_alloc_device() to inform the vDPA framework that the device supports VA. vringh is initialized to use VA only when "use_va" is true and the user's mm has been bound. So, only when the bus supports user VA (e.g. vhost-vdpa). vdpasim_mm_work_fn work is used to serialize the binding to a new address space when the .bind_mm callback is invoked, and unbinding when the .unbind_mm callback is invoked. Call mmget_not_zero()/kthread_use_mm() inside the worker function to pin the address space only as long as needed, following the documentation of mmget() in include/linux/sched/mm.h: * Never use this function to pin this address space for an * unbounded/indefinite amount of time. Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Message-Id: <20230404131734.45943-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 97 +++++++++++++++++++++++++++++--- drivers/vdpa/vdpa_sim/vdpa_sim.h | 1 + 2 files changed, 90 insertions(+), 8 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 2b2e439a66f7..2c706bb18897 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -35,10 +35,44 @@ module_param(max_iotlb_entries, int, 0444); MODULE_PARM_DESC(max_iotlb_entries, "Maximum number of iotlb entries for each address space. 0 means unlimited. (default: 2048)"); +static bool use_va = true; +module_param(use_va, bool, 0444); +MODULE_PARM_DESC(use_va, "Enable/disable the device's ability to use VA"); + #define VDPASIM_QUEUE_ALIGN PAGE_SIZE #define VDPASIM_QUEUE_MAX 256 #define VDPASIM_VENDOR_ID 0 +struct vdpasim_mm_work { + struct kthread_work work; + struct vdpasim *vdpasim; + struct mm_struct *mm_to_bind; + int ret; +}; + +static void vdpasim_mm_work_fn(struct kthread_work *work) +{ + struct vdpasim_mm_work *mm_work = + container_of(work, struct vdpasim_mm_work, work); + struct vdpasim *vdpasim = mm_work->vdpasim; + + mm_work->ret = 0; + + //TODO: should we attach the cgroup of the mm owner? + vdpasim->mm_bound = mm_work->mm_to_bind; +} + +static void vdpasim_worker_change_mm_sync(struct vdpasim *vdpasim, + struct vdpasim_mm_work *mm_work) +{ + struct kthread_work *work = &mm_work->work; + + kthread_init_work(work, vdpasim_mm_work_fn); + kthread_queue_work(vdpasim->worker, work); + + kthread_flush_work(work); +} + static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa) { return container_of(vdpa, struct vdpasim, vdpa); @@ -59,13 +93,20 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) { struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx]; uint16_t last_avail_idx = vq->vring.last_avail_idx; - - vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, true, - (struct vring_desc *)(uintptr_t)vq->desc_addr, - (struct vring_avail *) - (uintptr_t)vq->driver_addr, - (struct vring_used *) - (uintptr_t)vq->device_addr); + struct vring_desc *desc = (struct vring_desc *) + (uintptr_t)vq->desc_addr; + struct vring_avail *avail = (struct vring_avail *) + (uintptr_t)vq->driver_addr; + struct vring_used *used = (struct vring_used *) + (uintptr_t)vq->device_addr; + + if (use_va && vdpasim->mm_bound) { + vringh_init_iotlb_va(&vq->vring, vdpasim->features, vq->num, + true, desc, avail, used); + } else { + vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, + true, desc, avail, used); + } vq->vring.last_avail_idx = last_avail_idx; @@ -130,8 +171,20 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops; static void vdpasim_work_fn(struct kthread_work *work) { struct vdpasim *vdpasim = container_of(work, struct vdpasim, work); + struct mm_struct *mm = vdpasim->mm_bound; + + if (use_va && mm) { + if (!mmget_not_zero(mm)) + return; + kthread_use_mm(mm); + } vdpasim->dev_attr.work_fn(vdpasim); + + if (use_va && mm) { + kthread_unuse_mm(mm); + mmput(mm); + } } struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, @@ -162,7 +215,7 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, vdpa = __vdpa_alloc_device(NULL, ops, dev_attr->ngroups, dev_attr->nas, dev_attr->alloc_size, - dev_attr->name, false); + dev_attr->name, use_va); if (IS_ERR(vdpa)) { ret = PTR_ERR(vdpa); goto err_alloc; @@ -582,6 +635,30 @@ static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid, return ret; } +static int vdpasim_bind_mm(struct vdpa_device *vdpa, struct mm_struct *mm) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_mm_work mm_work; + + mm_work.vdpasim = vdpasim; + mm_work.mm_to_bind = mm; + + vdpasim_worker_change_mm_sync(vdpasim, &mm_work); + + return mm_work.ret; +} + +static void vdpasim_unbind_mm(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + struct vdpasim_mm_work mm_work; + + mm_work.vdpasim = vdpasim; + mm_work.mm_to_bind = NULL; + + vdpasim_worker_change_mm_sync(vdpasim, &mm_work); +} + static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid, u64 iova, u64 size, u64 pa, u32 perm, void *opaque) @@ -678,6 +755,8 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_group_asid = vdpasim_set_group_asid, .dma_map = vdpasim_dma_map, .dma_unmap = vdpasim_dma_unmap, + .bind_mm = vdpasim_bind_mm, + .unbind_mm = vdpasim_unbind_mm, .free = vdpasim_free, }; @@ -712,6 +791,8 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .get_iova_range = vdpasim_get_iova_range, .set_group_asid = vdpasim_set_group_asid, .set_map = vdpasim_set_map, + .bind_mm = vdpasim_bind_mm, + .unbind_mm = vdpasim_unbind_mm, .free = vdpasim_free, }; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index 4774292fba8c..3a42887d05d9 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -59,6 +59,7 @@ struct vdpasim { struct vdpasim_virtqueue *vqs; struct kthread_worker *worker; struct kthread_work work; + struct mm_struct *mm_bound; struct vdpasim_dev_attr dev_attr; /* mutex to synchronize virtqueue state */ struct mutex mutex; -- GitLab From 6c0b057cec5eade4c3afec3908821176931a9997 Mon Sep 17 00:00:00 2001 From: Albert Huang Date: Wed, 29 Mar 2023 18:23:00 +0800 Subject: [PATCH 3711/5631] virtio_ring: don't update event idx on get_buf In virtio_net, if we disable napi_tx, when we trigger a tx interrupt, the vq->event_triggered will be set to true. It is then never reset until we explicitly call virtqueue_enable_cb_delayed or virtqueue_enable_cb_prepare. If we disable the napi_tx, virtqueue_enable_cb* will only be called when the tx ring is getting relatively empty. Since event_triggered is true, VRING_AVAIL_F_NO_INTERRUPT or VRING_PACKED_EVENT_FLAG_DISABLE will not be set. As a result we update vring_used_event(&vq->split.vring) or vq->packed.vring.driver->off_wrap every time we call virtqueue_get_buf_ctx. This causes more interrupts. To summarize: 1) event_triggered was set to true in vring_interrupt() 2) after this nothing will happen in virtqueue_disable_cb() so VRING_AVAIL_F_NO_INTERRUPT is not set in avail_flags_shadow 3) virtqueue_get_buf_ctx_split() will still think the cb is enabled and then it will publish a new event index To fix: update VRING_AVAIL_F_NO_INTERRUPT or VRING_PACKED_EVENT_FLAG_DISABLE in the vq when we call virtqueue_disable_cb even when event_triggered is true. Tested with iperf: iperf3 tcp stream: vm1 -----------------> vm2 vm2 just receives tcp data stream from vm1, and sends acks to vm1, there are many tx interrupts in vm2. with the patch applied there are just a few tx interrupts. v2->v3: -update the interrupt disable flag even with the event_triggered is set, -instead of checking whether event_triggered is set in -virtqueue_get_buf_ctx_{packed/split}, will cause the drivers which have -not called virtqueue_{enable/disable}_cb to miss notifications. v3->v4: -remove change for -"if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE)" -in virtqueue_disable_cb_packed Fixes: 8d622d21d248 ("virtio: fix up virtio_disable_cb") Signed-off-by: Albert Huang Signed-off-by: Michael S. Tsirkin Signed-off-by: Jason Wang Message-Id: <20230329102300.61000-1-huangjie.albert@bytedance.com> Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 4c3bb0ddeb9b..34e3849629da 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -854,6 +854,14 @@ static void virtqueue_disable_cb_split(struct virtqueue *_vq) if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) { vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT; + + /* + * If device triggered an event already it won't trigger one again: + * no need to disable. + */ + if (vq->event_triggered) + return; + if (vq->event) /* TODO: this is a hack. Figure out a cleaner value to write. */ vring_used_event(&vq->split.vring) = 0x0; @@ -1699,6 +1707,14 @@ static void virtqueue_disable_cb_packed(struct virtqueue *_vq) if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; + + /* + * If device triggered an event already it won't trigger one again: + * no need to disable. + */ + if (vq->event_triggered) + return; + vq->packed.vring.driver->flags = cpu_to_le16(vq->packed.event_flags_shadow); } @@ -2330,12 +2346,6 @@ void virtqueue_disable_cb(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - /* If device triggered an event already it won't trigger one again: - * no need to disable. - */ - if (vq->event_triggered) - return; - if (vq->packed_ring) virtqueue_disable_cb_packed(_vq); else -- GitLab From 9be5d2d424a19a0c6d643a1baecba3d58e725012 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 31 Mar 2023 10:56:55 +0200 Subject: [PATCH 3712/5631] vdpa: address kdoc warnings This patch addresses the following minor kdoc problems. * Incorrect spelling of 'callback' and 'notification' * Unrecognised kdoc format for 'struct vdpa_map_file' * Missing documentation of 'get_vendor_vq_stats' member of 'struct vdpa_config_ops' * Missing documentation of 'max_supported_vqs' and 'supported_features' members of 'struct vdpa_mgmt_dev' Most of these problems were flagged by: $ ./scripts/kernel-doc -Werror -none include/linux/vdpa.h include/linux/vdpa.h:20: warning: expecting prototype for struct vdpa_calllback. Prototype was for struct vdpa_callback instead include/linux/vdpa.h:117: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Corresponding file area for device memory mapping include/linux/vdpa.h:357: warning: Function parameter or member 'get_vendor_vq_stats' not described in 'vdpa_config_ops' include/linux/vdpa.h:518: warning: Function parameter or member 'supported_features' not described in 'vdpa_mgmt_dev' include/linux/vdpa.h:518: warning: Function parameter or member 'max_supported_vqs' not described in 'vdpa_mgmt_dev' The misspelling of 'notification' was flagged by: $ ./scripts/checkpatch.pl --codespell --showfile --strict -f include/linux/vdpa.h include/linux/vdpa.h:171: CHECK: 'notifcation' may be misspelled - perhaps 'notification'? ... Signed-off-by: Simon Horman Message-Id: <20230331-vhost-fixes-v1-1-1f046e735b9e@kernel.org> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- include/linux/vdpa.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2f1af73b3a1a..c0d3f5433af7 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -10,7 +10,7 @@ #include /** - * struct vdpa_calllback - vDPA callback definition. + * struct vdpa_callback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function * @trigger: the eventfd for the callback (Optional). @@ -120,7 +120,7 @@ struct vdpa_dev_set_config { }; /** - * Corresponding file area for device memory mapping + * struct vdpa_map_file - file area for device memory mapping * @file: vma->vm_file for the mapping * @offset: mapping offset in the vm_file */ @@ -171,10 +171,16 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) + * @get_vendor_vq_stats: Get the vendor statistics of a device. + * @vdev: vdpa device + * @idx: virtqueue index + * @msg: socket buffer holding stats message + * @extack: extack for reporting error messages + * Returns integer: success (0) or error (< 0) * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index - * Returns the notifcation area + * Returns the notification area * @get_vq_irq: Get the irq number of a virtqueue (optional, * but must implemented if require vq irq offloading) * @vdev: vdpa device @@ -535,6 +541,8 @@ struct vdpa_mgmtdev_ops { * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that * management device support during dev_add callback * @list: list entry + * @supported_features: features supported by device + * @max_supported_vqs: maximum number of virtqueues supported by device */ struct vdpa_mgmt_dev { struct device *device; -- GitLab From b2ffaa672edaf1a681537a9f47bc14ab6c9e8845 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 31 Mar 2023 10:56:56 +0200 Subject: [PATCH 3713/5631] vringh: address kdoc warnings Address some minor kdoc warnings in vring.h. * Place kdoc for 'struct vringh_config_ops' immediately before the structure * Add missing documentation of members of 'vringh_iov' and 'vringh_kiov' Warnings flagged by: $ ./scripts/kernel-doc -none include/linux/vringh.h include/linux/vringh.h:68: error: Cannot parse struct or union! include/linux/vringh.h:92: warning: Function parameter or member 'iov' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'consumed' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'i' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'used' not described in 'vringh_iov' include/linux/vringh.h:92: warning: Function parameter or member 'max_num' not described in 'vringh_iov' include/linux/vringh.h:104: warning: Function parameter or member 'iov' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'consumed' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'i' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'used' not described in 'vringh_kiov' include/linux/vringh.h:104: warning: Function parameter or member 'max_num' not described in 'vringh_kiov' Signed-off-by: Simon Horman Message-Id: <20230331-vhost-fixes-v1-2-1f046e735b9e@kernel.org> Signed-off-by: Michael S. Tsirkin --- include/linux/vringh.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/include/linux/vringh.h b/include/linux/vringh.h index b4edfadf5479..c3a8117dabe8 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -57,6 +57,9 @@ struct vringh { void (*notify)(struct vringh *); }; +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); + /** * struct vringh_config_ops - ops for creating a host vring from a virtio driver * @find_vrhs: find the host vrings and instantiate them @@ -68,8 +71,6 @@ struct vringh { * Returns 0 on success or error status * @del_vrhs: free the host vrings found by find_vrhs(). */ -struct virtio_device; -typedef void vrh_callback_t(struct virtio_device *, struct vringh *); struct vringh_config_ops { int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, struct vringh *vrhs[], vrh_callback_t *callbacks[]); @@ -84,6 +85,12 @@ struct vringh_range { /** * struct vringh_iov - iovec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles iovec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -96,6 +103,12 @@ struct vringh_iov { /** * struct vringh_kiov - kvec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. -- GitLab From 4a536d881a661c7ff7d241c537ee511106d88163 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Fri, 31 Mar 2023 10:56:57 +0200 Subject: [PATCH 3714/5631] MAINTAINERS: add vringh.h to Virtio Core and Net Drivers vringh.h doesn't seem to belong to any section in MAINTAINERS. Add it to Virtio Core and Net Drivers, which seems to be the most appropriate section to me. Signed-off-by: Simon Horman Message-Id: <20230331-vhost-fixes-v1-3-1f046e735b9e@kernel.org> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 0e64787aace8..a8df70387877 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22077,6 +22077,7 @@ F: drivers/vdpa/ F: drivers/virtio/ F: include/linux/vdpa.h F: include/linux/virtio*.h +F: include/linux/vringh.h F: include/uapi/linux/virtio_*.h F: tools/virtio/ -- GitLab From 3f3a1675b731e532d479e65570f2904878fbd9f0 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Thu, 13 Apr 2023 10:33:36 +0300 Subject: [PATCH 3715/5631] vdpa/snet: support getting and setting VQ state This patch adds the get_vq_state and set_vq_state vDPA callbacks. In order to get the VQ state, the state needs to be read from the DPU. In order to allow that, the old messaging mechanism is replaced with a new, flexible control mechanism. This mechanism allows to read data from the DPU. The mechanism can be used if the negotiated config version is 2 or higher. If the new mechanism is used when the config version is 1, it will call snet_send_ctrl_msg_old, which is config 1 compatible. Signed-off-by: Alvaro Karsz Message-Id: <20230413073337.31367-2-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/solidrun/Makefile | 1 + drivers/vdpa/solidrun/snet_ctrl.c | 324 +++++++++++++++++++++++++++++ drivers/vdpa/solidrun/snet_hwmon.c | 2 +- drivers/vdpa/solidrun/snet_main.c | 112 ++++------ drivers/vdpa/solidrun/snet_vdpa.h | 19 +- 5 files changed, 387 insertions(+), 71 deletions(-) create mode 100644 drivers/vdpa/solidrun/snet_ctrl.c diff --git a/drivers/vdpa/solidrun/Makefile b/drivers/vdpa/solidrun/Makefile index c0aa3415bf7b..9116252cd5fa 100644 --- a/drivers/vdpa/solidrun/Makefile +++ b/drivers/vdpa/solidrun/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SNET_VDPA) += snet_vdpa.o snet_vdpa-$(CONFIG_SNET_VDPA) += snet_main.o +snet_vdpa-$(CONFIG_SNET_VDPA) += snet_ctrl.o ifdef CONFIG_HWMON snet_vdpa-$(CONFIG_SNET_VDPA) += snet_hwmon.o endif diff --git a/drivers/vdpa/solidrun/snet_ctrl.c b/drivers/vdpa/solidrun/snet_ctrl.c new file mode 100644 index 000000000000..10cde502f1a9 --- /dev/null +++ b/drivers/vdpa/solidrun/snet_ctrl.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SolidRun DPU driver for control plane + * + * Copyright (C) 2022-2023 SolidRun + * + * Author: Alvaro Karsz + * + */ + +#include + +#include "snet_vdpa.h" + +enum snet_ctrl_opcodes { + SNET_CTRL_OP_DESTROY = 1, + SNET_CTRL_OP_READ_VQ_STATE, +}; + +#define SNET_CTRL_TIMEOUT 2000000 + +#define SNET_CTRL_DATA_SIZE_MASK 0x0000FFFF +#define SNET_CTRL_IN_PROCESS_MASK 0x00010000 +#define SNET_CTRL_CHUNK_RDY_MASK 0x00020000 +#define SNET_CTRL_ERROR_MASK 0x0FFC0000 + +#define SNET_VAL_TO_ERR(val) (-(((val) & SNET_CTRL_ERROR_MASK) >> 18)) +#define SNET_EMPTY_CTRL(val) (((val) & SNET_CTRL_ERROR_MASK) || \ + !((val) & SNET_CTRL_IN_PROCESS_MASK)) +#define SNET_DATA_READY(val) ((val) & (SNET_CTRL_ERROR_MASK | SNET_CTRL_CHUNK_RDY_MASK)) + +/* Control register used to read data from the DPU */ +struct snet_ctrl_reg_ctrl { + /* Chunk size in 4B words */ + u16 data_size; + /* We are in the middle of a command */ + u16 in_process:1; + /* A data chunk is ready and can be consumed */ + u16 chunk_ready:1; + /* Error code */ + u16 error:10; + /* Saved for future usage */ + u16 rsvd:4; +}; + +/* Opcode register */ +struct snet_ctrl_reg_op { + u16 opcode; + /* Only if VQ index is relevant for the command */ + u16 vq_idx; +}; + +struct snet_ctrl_regs { + struct snet_ctrl_reg_op op; + struct snet_ctrl_reg_ctrl ctrl; + u32 rsvd; + u32 data[]; +}; + +static struct snet_ctrl_regs __iomem *snet_get_ctrl(struct snet *snet) +{ + return snet->bar + snet->psnet->cfg.ctrl_off; +} + +static int snet_wait_for_empty_ctrl(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->ctrl, val, SNET_EMPTY_CTRL(val), 10, + SNET_CTRL_TIMEOUT); +} + +static int snet_wait_for_empty_op(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->op, val, !val, 10, SNET_CTRL_TIMEOUT); +} + +static int snet_wait_for_data(struct snet_ctrl_regs __iomem *regs) +{ + u32 val; + + return readx_poll_timeout(ioread32, ®s->ctrl, val, SNET_DATA_READY(val), 10, + SNET_CTRL_TIMEOUT); +} + +static u32 snet_read32_word(struct snet_ctrl_regs __iomem *ctrl_regs, u16 word_idx) +{ + return ioread32(&ctrl_regs->data[word_idx]); +} + +static u32 snet_read_ctrl(struct snet_ctrl_regs __iomem *ctrl_regs) +{ + return ioread32(&ctrl_regs->ctrl); +} + +static void snet_write_ctrl(struct snet_ctrl_regs __iomem *ctrl_regs, u32 val) +{ + iowrite32(val, &ctrl_regs->ctrl); +} + +static void snet_write_op(struct snet_ctrl_regs __iomem *ctrl_regs, u32 val) +{ + iowrite32(val, &ctrl_regs->op); +} + +static int snet_wait_for_dpu_completion(struct snet_ctrl_regs __iomem *ctrl_regs) +{ + /* Wait until the DPU finishes completely. + * It will clear the opcode register. + */ + return snet_wait_for_empty_op(ctrl_regs); +} + +/* Reading ctrl from the DPU: + * buf_size must be 4B aligned + * + * Steps: + * + * (1) Verify that the DPU is not in the middle of another operation by + * reading the in_process and error bits in the control register. + * (2) Write the request opcode and the VQ idx in the opcode register + * and write the buffer size in the control register. + * (3) Start readind chunks of data, chunk_ready bit indicates that a + * data chunk is available, we signal that we read the data by clearing the bit. + * (4) Detect that the transfer is completed when the in_process bit + * in the control register is cleared or when the an error appears. + */ +static int snet_ctrl_read_from_dpu(struct snet *snet, u16 opcode, u16 vq_idx, void *buffer, + u32 buf_size) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + u32 *bfr_ptr = (u32 *)buffer; + u32 val; + u16 buf_words; + int ret; + u16 words, i, tot_words = 0; + + /* Supported for config 2+ */ + if (!SNET_CFG_VER(snet, 2)) + return -EOPNOTSUPP; + + if (!IS_ALIGNED(buf_size, 4)) + return -EINVAL; + + mutex_lock(&snet->ctrl_lock); + + buf_words = buf_size / 4; + + /* Make sure control register is empty */ + ret = snet_wait_for_empty_ctrl(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control data to be consumed\n"); + goto exit; + } + + /* We need to write the buffer size in the control register, and the opcode + vq index in + * the opcode register. + * We use a spinlock to serialize the writes. + */ + spin_lock(&snet->ctrl_spinlock); + + snet_write_ctrl(regs, buf_words); + snet_write_op(regs, opcode | (vq_idx << 16)); + + spin_unlock(&snet->ctrl_spinlock); + + while (buf_words != tot_words) { + ret = snet_wait_for_data(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for control data\n"); + goto exit; + } + + val = snet_read_ctrl(regs); + + /* Error? */ + if (val & SNET_CTRL_ERROR_MASK) { + ret = SNET_VAL_TO_ERR(val); + SNET_WARN(pdev, "Error while reading control data from DPU, err %d\n", ret); + goto exit; + } + + words = min_t(u16, val & SNET_CTRL_DATA_SIZE_MASK, buf_words - tot_words); + + for (i = 0; i < words; i++) { + *bfr_ptr = snet_read32_word(regs, i); + bfr_ptr++; + } + + tot_words += words; + + /* Is the job completed? */ + if (!(val & SNET_CTRL_IN_PROCESS_MASK)) + break; + + /* Clear the chunk ready bit and continue */ + val &= ~SNET_CTRL_CHUNK_RDY_MASK; + snet_write_ctrl(regs, val); + } + + ret = snet_wait_for_dpu_completion(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for the DPU to complete a control command\n"); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +/* Send a control message to the DPU using the old mechanism + * used with config version 1. + */ +static int snet_send_ctrl_msg_old(struct snet *snet, u32 opcode) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + int ret; + + mutex_lock(&snet->ctrl_lock); + + /* Old mechanism uses just 1 register, the opcode register. + * Make sure that the opcode register is empty, and that the DPU isn't + * processing an old message. + */ + ret = snet_wait_for_empty_op(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control message to be ACKed\n"); + goto exit; + } + + /* Write the message */ + snet_write_op(regs, opcode); + + /* DPU ACKs the message by clearing the opcode register */ + ret = snet_wait_for_empty_op(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for a control message to be ACKed\n"); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +/* Send a control message to the DPU. + * A control message is a message without payload. + */ +static int snet_send_ctrl_msg(struct snet *snet, u16 opcode, u16 vq_idx) +{ + struct pci_dev *pdev = snet->pdev; + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + u32 val; + int ret; + + /* If config version is not 2+, use the old mechanism */ + if (!SNET_CFG_VER(snet, 2)) + return snet_send_ctrl_msg_old(snet, opcode); + + mutex_lock(&snet->ctrl_lock); + + /* Make sure control register is empty */ + ret = snet_wait_for_empty_ctrl(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for previous control data to be consumed\n"); + goto exit; + } + + /* We need to clear the control register and write the opcode + vq index in the opcode + * register. + * We use a spinlock to serialize the writes. + */ + spin_lock(&snet->ctrl_spinlock); + + snet_write_ctrl(regs, 0); + snet_write_op(regs, opcode | (vq_idx << 16)); + + spin_unlock(&snet->ctrl_spinlock); + + /* The DPU ACKs control messages by setting the chunk ready bit + * without data. + */ + ret = snet_wait_for_data(regs); + if (ret) { + SNET_WARN(pdev, "Timeout waiting for control message to be ACKed\n"); + goto exit; + } + + /* Check for errors */ + val = snet_read_ctrl(regs); + ret = SNET_VAL_TO_ERR(val); + + /* Clear the chunk ready bit */ + val &= ~SNET_CTRL_CHUNK_RDY_MASK; + snet_write_ctrl(regs, val); + + ret = snet_wait_for_dpu_completion(regs); + if (ret) + SNET_WARN(pdev, "Timeout waiting for DPU to complete a control command, err %d\n", + ret); + +exit: + mutex_unlock(&snet->ctrl_lock); + return ret; +} + +void snet_ctrl_clear(struct snet *snet) +{ + struct snet_ctrl_regs __iomem *regs = snet_get_ctrl(snet); + + snet_write_op(regs, 0); +} + +int snet_destroy_dev(struct snet *snet) +{ + return snet_send_ctrl_msg(snet, SNET_CTRL_OP_DESTROY, 0); +} + +int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state) +{ + return snet_ctrl_read_from_dpu(snet, SNET_CTRL_OP_READ_VQ_STATE, idx, state, + sizeof(*state)); +} diff --git a/drivers/vdpa/solidrun/snet_hwmon.c b/drivers/vdpa/solidrun/snet_hwmon.c index e695e36ff753..42c87387a0f1 100644 --- a/drivers/vdpa/solidrun/snet_hwmon.c +++ b/drivers/vdpa/solidrun/snet_hwmon.c @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 68de727398ed..86769f436b4d 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * @@ -16,14 +16,12 @@ /* SNET signature */ #define SNET_SIGNATURE 0xD0D06363 /* Max. config version that we can work with */ -#define SNET_CFG_VERSION 0x1 +#define SNET_CFG_VERSION 0x2 /* Queue align */ #define SNET_QUEUE_ALIGNMENT PAGE_SIZE /* Kick value to notify that new data is available */ #define SNET_KICK_VAL 0x1 #define SNET_CONFIG_OFF 0x0 -/* ACK timeout for a message */ -#define SNET_ACK_TIMEOUT 2000000 /* How long we are willing to wait for a SNET device */ #define SNET_DETECT_TIMEOUT 5000000 /* How long should we wait for the DPU to read our config */ @@ -32,56 +30,11 @@ #define SNET_GENERAL_CFG_LEN 36 #define SNET_GENERAL_CFG_VQ_LEN 40 -enum snet_msg { - SNET_MSG_DESTROY = 1, -}; - static struct snet *vdpa_to_snet(struct vdpa_device *vdpa) { return container_of(vdpa, struct snet, vdpa); } -static int snet_wait_for_msg_ack(struct snet *snet) -{ - struct pci_dev *pdev = snet->pdev; - int ret; - u32 val; - - /* The DPU will clear the messages offset once messages - * are processed. - */ - ret = readx_poll_timeout(ioread32, snet->bar + snet->psnet->cfg.msg_off, - val, !val, 10, SNET_ACK_TIMEOUT); - if (ret) - SNET_WARN(pdev, "Timeout waiting for message ACK\n"); - - return ret; -} - -/* Sends a message to the DPU. - * If blocking is set, the function will return once the - * message was processed by the DPU (or timeout). - */ -static int snet_send_msg(struct snet *snet, u32 msg, bool blocking) -{ - int ret = 0; - - /* Make sure the DPU acked last message before issuing a new one */ - ret = snet_wait_for_msg_ack(snet); - if (ret) - return ret; - - /* Write the message */ - snet_write32(snet, snet->psnet->cfg.msg_off, msg); - - if (blocking) - ret = snet_wait_for_msg_ack(snet); - else /* If non-blocking, flush the write by issuing a read */ - snet_read32(snet, snet->psnet->cfg.msg_off); - - return ret; -} - static irqreturn_t snet_cfg_irq_hndlr(int irq, void *data) { struct snet *snet = data; @@ -181,33 +134,48 @@ static bool snet_get_vq_ready(struct vdpa_device *vdev, u16 idx) return snet->vqs[idx]->ready; } -static int snet_set_vq_state(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state) +static bool snet_vq_state_is_initial(struct snet *snet, const struct vdpa_vq_state *state) { - struct snet *snet = vdpa_to_snet(vdev); - /* Setting the VQ state is not supported. - * If the asked state is the same as the initial one - * we can ignore it. - */ if (SNET_HAS_FEATURE(snet, VIRTIO_F_RING_PACKED)) { const struct vdpa_vq_state_packed *p = &state->packed; if (p->last_avail_counter == 1 && p->last_used_counter == 1 && p->last_avail_idx == 0 && p->last_used_idx == 0) - return 0; + return true; } else { const struct vdpa_vq_state_split *s = &state->split; if (s->avail_index == 0) - return 0; + return true; + } + + return false; +} + +static int snet_set_vq_state(struct vdpa_device *vdev, u16 idx, const struct vdpa_vq_state *state) +{ + struct snet *snet = vdpa_to_snet(vdev); + + /* We can set any state for config version 2+ */ + if (SNET_CFG_VER(snet, 2)) { + memcpy(&snet->vqs[idx]->vq_state, state, sizeof(*state)); + return 0; } + /* Older config - we can't set the VQ state. + * Return 0 only if this is the initial state we use in the DPU. + */ + if (snet_vq_state_is_initial(snet, state)) + return 0; + return -EOPNOTSUPP; } static int snet_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa_vq_state *state) { - /* Not supported */ - return -EOPNOTSUPP; + struct snet *snet = vdpa_to_snet(vdev); + + return snet_read_vq_state(snet, idx, state); } static int snet_get_vq_irq(struct vdpa_device *vdev, u16 idx) @@ -232,9 +200,9 @@ static int snet_reset_dev(struct snet *snet) if (!snet->status) return 0; - /* If DPU started, send a destroy message */ + /* If DPU started, destroy it */ if (snet->status & VIRTIO_CONFIG_S_DRIVER_OK) - ret = snet_send_msg(snet, SNET_MSG_DESTROY, true); + ret = snet_destroy_dev(snet); /* Clear VQs */ for (i = 0; i < snet->cfg->vq_num; i++) { @@ -258,7 +226,7 @@ static int snet_reset_dev(struct snet *snet) snet->dpu_ready = false; if (ret) - SNET_WARN(pdev, "Incomplete reset to SNET[%u] device\n", snet->sid); + SNET_WARN(pdev, "Incomplete reset to SNET[%u] device, err: %d\n", snet->sid, ret); else SNET_DBG(pdev, "Reset SNET[%u] device\n", snet->sid); @@ -356,7 +324,7 @@ static int snet_write_conf(struct snet *snet) * | DESC AREA | * | DEVICE AREA | * | DRIVER AREA | - * | RESERVED | + * | VQ STATE (CFG 2+) | RSVD | * * Magic number should be written last, this is the DPU indication that the data is ready */ @@ -391,12 +359,15 @@ static int snet_write_conf(struct snet *snet) off += 8; snet_write64(snet, off, snet->vqs[i]->driver_area); off += 8; + /* Write VQ state if config version is 2+ */ + if (SNET_CFG_VER(snet, 2)) + snet_write32(snet, off, *(u32 *)&snet->vqs[i]->vq_state); + off += 4; + /* Ignore reserved */ - off += 8; + off += 4; } - /* Clear snet messages address for this device */ - snet_write32(snet, snet->psnet->cfg.msg_off, 0); /* Write magic number - data is ready */ snet_write32(snet, snet->psnet->cfg.host_cfg_off, SNET_SIGNATURE); @@ -697,7 +668,7 @@ static int psnet_read_cfg(struct pci_dev *pdev, struct psnet *psnet) off += 4; cfg->hwmon_off = psnet_read32(psnet, off); off += 4; - cfg->msg_off = psnet_read32(psnet, off); + cfg->ctrl_off = psnet_read32(psnet, off); off += 4; cfg->flags = psnet_read32(psnet, off); off += 4; @@ -997,6 +968,10 @@ static int snet_vdpa_probe_vf(struct pci_dev *pdev) goto free_irqs; } + /* Init control mutex and spinlock */ + mutex_init(&snet->ctrl_lock); + spin_lock_init(&snet->ctrl_spinlock); + /* Save pci device pointer */ snet->pdev = pdev; snet->psnet = psnet; @@ -1013,6 +988,9 @@ static int snet_vdpa_probe_vf(struct pci_dev *pdev) /* Create a VirtIO config pointer */ snet->cfg->virtio_cfg = snet->bar + snet->psnet->cfg.virtio_cfg_off; + /* Clear control registers */ + snet_ctrl_clear(snet); + pci_set_master(pdev); pci_set_drvdata(pdev, snet); diff --git a/drivers/vdpa/solidrun/snet_vdpa.h b/drivers/vdpa/solidrun/snet_vdpa.h index b7f34169053f..09ff676e7a2d 100644 --- a/drivers/vdpa/solidrun/snet_vdpa.h +++ b/drivers/vdpa/solidrun/snet_vdpa.h @@ -2,7 +2,7 @@ /* * SolidRun DPU driver for control plane * - * Copyright (C) 2022 SolidRun + * Copyright (C) 2022-2023 SolidRun * * Author: Alvaro Karsz * @@ -20,10 +20,15 @@ #define SNET_INFO(pdev, fmt, ...) dev_info(&(pdev)->dev, "%s"fmt, "snet_vdpa: ", ##__VA_ARGS__) #define SNET_DBG(pdev, fmt, ...) dev_dbg(&(pdev)->dev, "%s"fmt, "snet_vdpa: ", ##__VA_ARGS__) #define SNET_HAS_FEATURE(s, f) ((s)->negotiated_features & BIT_ULL(f)) +/* Check if negotiated config version is at least @ver */ +#define SNET_CFG_VER(snet, ver) ((snet)->psnet->negotiated_cfg_ver >= (ver)) + /* VQ struct */ struct snet_vq { /* VQ callback */ struct vdpa_callback cb; + /* VQ state received from bus */ + struct vdpa_vq_state vq_state; /* desc base address */ u64 desc_area; /* device base address */ @@ -51,6 +56,10 @@ struct snet { struct vdpa_device vdpa; /* Config callback */ struct vdpa_callback cb; + /* To lock the control mechanism */ + struct mutex ctrl_lock; + /* Spinlock to protect critical parts in the control mechanism */ + spinlock_t ctrl_spinlock; /* array of virqueues */ struct snet_vq **vqs; /* Used features */ @@ -117,8 +126,8 @@ struct snet_cfg { u32 kick_off; /* Offset in PCI BAR for HW monitoring */ u32 hwmon_off; - /* Offset in PCI BAR for SNET messages */ - u32 msg_off; + /* Offset in PCI BAR for Control mechanism */ + u32 ctrl_off; /* Config general flags - enum snet_cfg_flags */ u32 flags; /* Reserved for future usage */ @@ -191,4 +200,8 @@ static inline void snet_write64(struct snet *snet, u32 off, u64 val) void psnet_create_hwmon(struct pci_dev *pdev); #endif +void snet_ctrl_clear(struct snet *snet); +int snet_destroy_dev(struct snet *snet); +int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state); + #endif //_SNET_VDPA_H_ -- GitLab From 3616bf377a5a8ef4f124dfde5f3522c4da335561 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Thu, 13 Apr 2023 10:33:37 +0300 Subject: [PATCH 3716/5631] vdpa/snet: support the suspend vDPA callback When suspend is called, the driver sends a suspend command to the DPU through the control mechanism. Signed-off-by: Alvaro Karsz Message-Id: <20230413073337.31367-3-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/vdpa/solidrun/snet_ctrl.c | 6 ++++++ drivers/vdpa/solidrun/snet_main.c | 15 +++++++++++++++ drivers/vdpa/solidrun/snet_vdpa.h | 1 + 3 files changed, 22 insertions(+) diff --git a/drivers/vdpa/solidrun/snet_ctrl.c b/drivers/vdpa/solidrun/snet_ctrl.c index 10cde502f1a9..3858738643b4 100644 --- a/drivers/vdpa/solidrun/snet_ctrl.c +++ b/drivers/vdpa/solidrun/snet_ctrl.c @@ -15,6 +15,7 @@ enum snet_ctrl_opcodes { SNET_CTRL_OP_DESTROY = 1, SNET_CTRL_OP_READ_VQ_STATE, + SNET_CTRL_OP_SUSPEND, }; #define SNET_CTRL_TIMEOUT 2000000 @@ -322,3 +323,8 @@ int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state) return snet_ctrl_read_from_dpu(snet, SNET_CTRL_OP_READ_VQ_STATE, idx, state, sizeof(*state)); } + +int snet_suspend_dev(struct snet *snet) +{ + return snet_send_ctrl_msg(snet, SNET_CTRL_OP_SUSPEND, 0); +} diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 86769f436b4d..7359599e09e4 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -483,6 +483,20 @@ static void snet_set_config(struct vdpa_device *vdev, unsigned int offset, iowrite8(*buf_ptr++, cfg_ptr + i); } +static int snet_suspend(struct vdpa_device *vdev) +{ + struct snet *snet = vdpa_to_snet(vdev); + int ret; + + ret = snet_suspend_dev(snet); + if (ret) + SNET_ERR(snet->pdev, "SNET[%u] suspend failed, err: %d\n", snet->sid, ret); + else + SNET_DBG(snet->pdev, "Suspend SNET[%u] device\n", snet->sid); + + return ret; +} + static const struct vdpa_config_ops snet_config_ops = { .set_vq_address = snet_set_vq_address, .set_vq_num = snet_set_vq_num, @@ -508,6 +522,7 @@ static const struct vdpa_config_ops snet_config_ops = { .set_status = snet_set_status, .get_config = snet_get_config, .set_config = snet_set_config, + .suspend = snet_suspend, }; static int psnet_open_pf_bar(struct pci_dev *pdev, struct psnet *psnet) diff --git a/drivers/vdpa/solidrun/snet_vdpa.h b/drivers/vdpa/solidrun/snet_vdpa.h index 09ff676e7a2d..3c78d4e7d485 100644 --- a/drivers/vdpa/solidrun/snet_vdpa.h +++ b/drivers/vdpa/solidrun/snet_vdpa.h @@ -203,5 +203,6 @@ void psnet_create_hwmon(struct pci_dev *pdev); void snet_ctrl_clear(struct snet *snet); int snet_destroy_dev(struct snet *snet); int snet_read_vq_state(struct snet *snet, u16 idx, struct vdpa_vq_state *state); +int snet_suspend_dev(struct snet *snet); #endif //_SNET_VDPA_H_ -- GitLab From af8ececda185078c096852edb4e1d7a2349e6856 Mon Sep 17 00:00:00 2001 From: Viktor Prutyanov Date: Thu, 13 Apr 2023 11:18:54 +0300 Subject: [PATCH 3717/5631] virtio: add VIRTIO_F_NOTIFICATION_DATA feature support According to VirtIO spec v1.2, VIRTIO_F_NOTIFICATION_DATA feature indicates that the driver passes extra data along with the queue notifications. In a split queue case, the extra data is 16-bit available index. In a packed queue case, the extra data is 1-bit wrap counter and 15-bit available index. Add support for this feature for MMIO, channel I/O and modern PCI transports. Signed-off-by: Viktor Prutyanov Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Message-Id: <20230413081855.36643-2-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin --- drivers/s390/virtio/virtio_ccw.c | 22 +++++++++++++++++++--- drivers/virtio/virtio_mmio.c | 18 +++++++++++++++++- drivers/virtio/virtio_pci_modern.c | 17 ++++++++++++++++- drivers/virtio/virtio_ring.c | 19 +++++++++++++++++++ include/linux/virtio_ring.h | 2 ++ include/uapi/linux/virtio_config.h | 6 ++++++ 6 files changed, 79 insertions(+), 5 deletions(-) diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 954fc31b4bc7..02922768b129 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -391,7 +391,7 @@ static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev, ccw_device_dma_free(vcdev->cdev, thinint_area, sizeof(*thinint_area)); } -static bool virtio_ccw_kvm_notify(struct virtqueue *vq) +static inline bool virtio_ccw_do_kvm_notify(struct virtqueue *vq, u32 data) { struct virtio_ccw_vq_info *info = vq->priv; struct virtio_ccw_device *vcdev; @@ -402,12 +402,22 @@ static bool virtio_ccw_kvm_notify(struct virtqueue *vq) BUILD_BUG_ON(sizeof(struct subchannel_id) != sizeof(unsigned int)); info->cookie = kvm_hypercall3(KVM_S390_VIRTIO_CCW_NOTIFY, *((unsigned int *)&schid), - vq->index, info->cookie); + data, info->cookie); if (info->cookie < 0) return false; return true; } +static bool virtio_ccw_kvm_notify(struct virtqueue *vq) +{ + return virtio_ccw_do_kvm_notify(vq, vq->index); +} + +static bool virtio_ccw_kvm_notify_with_data(struct virtqueue *vq) +{ + return virtio_ccw_do_kvm_notify(vq, vring_notification_data(vq)); +} + static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev, struct ccw1 *ccw, int index) { @@ -495,6 +505,7 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, struct ccw1 *ccw) { struct virtio_ccw_device *vcdev = to_vc_device(vdev); + bool (*notify)(struct virtqueue *vq); int err; struct virtqueue *vq = NULL; struct virtio_ccw_vq_info *info; @@ -502,6 +513,11 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, unsigned long flags; bool may_reduce; + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = virtio_ccw_kvm_notify_with_data; + else + notify = virtio_ccw_kvm_notify; + /* Allocate queue. */ info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL); if (!info) { @@ -524,7 +540,7 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev, may_reduce = vcdev->revision > 0; vq = vring_create_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev, true, may_reduce, ctx, - virtio_ccw_kvm_notify, callback, name); + notify, callback, name); if (!vq) { /* For now, we fail if we can't get the requested size. */ diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 3ff746e3f24a..dd4424c14233 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -285,6 +285,16 @@ static bool vm_notify(struct virtqueue *vq) return true; } +static bool vm_notify_with_data(struct virtqueue *vq) +{ + struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev); + u32 data = vring_notification_data(vq); + + writel(data, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY); + + return true; +} + /* Notify all virtqueues on an interrupt. */ static irqreturn_t vm_interrupt(int irq, void *opaque) { @@ -363,12 +373,18 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in const char *name, bool ctx) { struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev); + bool (*notify)(struct virtqueue *vq); struct virtio_mmio_vq_info *info; struct virtqueue *vq; unsigned long flags; unsigned int num; int err; + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = vm_notify_with_data; + else + notify = vm_notify; + if (!name) return NULL; @@ -397,7 +413,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in /* Create the vring */ vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev, - true, true, ctx, vm_notify, callback, name); + true, true, ctx, notify, callback, name); if (!vq) { err = -ENOMEM; goto error_new_virtqueue; diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index 6e713904d8e8..d6bb68ba84e5 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -288,6 +288,15 @@ static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) return vp_modern_config_vector(&vp_dev->mdev, vector); } +static bool vp_notify_with_data(struct virtqueue *vq) +{ + u32 data = vring_notification_data(vq); + + iowrite32(data, (void __iomem *)vq->priv); + + return true; +} + static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, struct virtio_pci_vq_info *info, unsigned int index, @@ -298,10 +307,16 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, { struct virtio_pci_modern_device *mdev = &vp_dev->mdev; + bool (*notify)(struct virtqueue *vq); struct virtqueue *vq; u16 num; int err; + if (__virtio_test_bit(&vp_dev->vdev, VIRTIO_F_NOTIFICATION_DATA)) + notify = vp_notify_with_data; + else + notify = vp_notify; + if (index >= vp_modern_get_num_queues(mdev)) return ERR_PTR(-EINVAL); @@ -316,7 +331,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, vq = vring_create_virtqueue(index, num, SMP_CACHE_BYTES, &vp_dev->vdev, true, true, ctx, - vp_notify, callback, name); + notify, callback, name); if (!vq) return ERR_PTR(-ENOMEM); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 34e3849629da..c5310eaf8b46 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2762,6 +2762,23 @@ void vring_del_virtqueue(struct virtqueue *_vq) } EXPORT_SYMBOL_GPL(vring_del_virtqueue); +u32 vring_notification_data(struct virtqueue *_vq) +{ + struct vring_virtqueue *vq = to_vvq(_vq); + u16 next; + + if (vq->packed_ring) + next = (vq->packed.next_avail_idx & + ~(-(1 << VRING_PACKED_EVENT_F_WRAP_CTR))) | + vq->packed.avail_wrap_counter << + VRING_PACKED_EVENT_F_WRAP_CTR; + else + next = vq->split.avail_idx_shadow; + + return next << 16 | _vq->index; +} +EXPORT_SYMBOL_GPL(vring_notification_data); + /* Manipulates transport-specific feature bits. */ void vring_transport_features(struct virtio_device *vdev) { @@ -2781,6 +2798,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_ORDER_PLATFORM: break; + case VIRTIO_F_NOTIFICATION_DATA: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b95b69ef694..2550c9170f4f 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -117,4 +117,6 @@ void vring_del_virtqueue(struct virtqueue *vq); void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); + +u32 vring_notification_data(struct virtqueue *_vq); #endif /* _LINUX_VIRTIO_RING_H */ diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 3c05162bc988..2c712c654165 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -99,6 +99,12 @@ */ #define VIRTIO_F_SR_IOV 37 +/* + * This feature indicates that the driver passes extra data (besides + * identifying the virtqueue) in its device notifications. + */ +#define VIRTIO_F_NOTIFICATION_DATA 38 + /* * This feature indicates that the driver can reset a queue individually. */ -- GitLab From 2c4e4a22a3b090e06191f8544d21e0e1d72ce518 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Thu, 13 Apr 2023 11:18:55 +0300 Subject: [PATCH 3718/5631] virtio-vdpa: add VIRTIO_F_NOTIFICATION_DATA feature support Add VIRTIO_F_NOTIFICATION_DATA support for vDPA transport. If this feature is negotiated, the driver passes extra data when kicking a virtqueue. A device that offers this feature needs to implement the kick_vq_with_data callback. kick_vq_with_data receives the vDPA device and data. data includes: 16 bits vqn and 16 bits next available index for split virtqueues. 16 bits vqs, 15 least significant bits of next available index and 1 bit next_wrap for packed virtqueues. This patch follows a patch [1] by Viktor Prutyanov which adds support for the MMIO, channel I/O and modern PCI transports. Signed-off-by: Alvaro Karsz Message-Id: <20230413081855.36643-3-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang --- drivers/virtio/virtio_vdpa.c | 23 +++++++++++++++++++++-- include/linux/vdpa.h | 9 +++++++++ 2 files changed, 30 insertions(+), 2 deletions(-) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 2a095f37f26b..eb6aee8c06b2 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -113,6 +113,17 @@ static bool virtio_vdpa_notify(struct virtqueue *vq) return true; } +static bool virtio_vdpa_notify_with_data(struct virtqueue *vq) +{ + struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev); + const struct vdpa_config_ops *ops = vdpa->config; + u32 data = vring_notification_data(vq); + + ops->kick_vq_with_data(vdpa, data); + + return true; +} + static irqreturn_t virtio_vdpa_config_cb(void *private) { struct virtio_vdpa_device *vd_dev = private; @@ -139,6 +150,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, struct device *dma_dev; const struct vdpa_config_ops *ops = vdpa->config; struct virtio_vdpa_vq_info *info; + bool (*notify)(struct virtqueue *vq) = virtio_vdpa_notify; struct vdpa_callback cb; struct virtqueue *vq; u64 desc_addr, driver_addr, device_addr; @@ -155,6 +167,14 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, if (index >= vdpa->nvqs) return ERR_PTR(-ENOENT); + /* We cannot accept VIRTIO_F_NOTIFICATION_DATA without kick_vq_with_data */ + if (__virtio_test_bit(vdev, VIRTIO_F_NOTIFICATION_DATA)) { + if (ops->kick_vq_with_data) + notify = virtio_vdpa_notify_with_data; + else + __virtio_clear_bit(vdev, VIRTIO_F_NOTIFICATION_DATA); + } + /* Queue shouldn't already be set up. */ if (ops->get_vq_ready(vdpa, index)) return ERR_PTR(-ENOENT); @@ -184,8 +204,7 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, dma_dev = vdpa_get_dma_dev(vdpa); vq = vring_create_virtqueue_dma(index, max_num, align, vdev, true, may_reduce_num, ctx, - virtio_vdpa_notify, callback, - name, dma_dev); + notify, callback, name, dma_dev); if (!vq) { err = -ENOMEM; goto error_new_virtqueue; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c0d3f5433af7..db1b0eaef4eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -149,6 +149,14 @@ struct vdpa_map_file { * @kick_vq: Kick the virtqueue * @vdev: vdpa device * @idx: virtqueue index + * @kick_vq_with_data: Kick the virtqueue and supply extra data + * (only if VIRTIO_F_NOTIFICATION_DATA is negotiated) + * @vdev: vdpa device + * @data for split virtqueue: + * 16 bits vqn and 16 bits next available index. + * @data for packed virtqueue: + * 16 bits vqn, 15 least significant bits of + * next available index and 1 bit next_wrap. * @set_vq_cb: Set the interrupt callback function for * a virtqueue * @vdev: vdpa device @@ -329,6 +337,7 @@ struct vdpa_config_ops { u64 device_area); void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num); void (*kick_vq)(struct vdpa_device *vdev, u16 idx); + void (*kick_vq_with_data)(struct vdpa_device *vdev, u32 data); void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); -- GitLab From 51b6e6c1c8e382c50fe88a04e25d326ceff74f89 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Mon, 17 Apr 2023 11:38:53 +0300 Subject: [PATCH 3719/5631] vdpa/snet: implement kick_vq_with_data callback Implement the kick_vq_with_data vDPA callback. On kick, we pass the next available data to the DPU by writing it in the kick offset. Signed-off-by: Alvaro Karsz Message-Id: <20230417083853.375076-1-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/solidrun/snet_main.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index 7359599e09e4..da14d437af33 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -112,6 +112,18 @@ static void snet_kick_vq(struct vdpa_device *vdev, u16 idx) iowrite32(SNET_KICK_VAL, snet->vqs[idx]->kick_ptr); } +static void snet_kick_vq_with_data(struct vdpa_device *vdev, u32 data) +{ + struct snet *snet = vdpa_to_snet(vdev); + u16 idx = data & 0xFFFF; + + /* not ready - ignore */ + if (unlikely(!snet->vqs[idx]->ready)) + return; + + iowrite32((data & 0xFFFF0000) | SNET_KICK_VAL, snet->vqs[idx]->kick_ptr); +} + static void snet_set_vq_cb(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb) { struct snet *snet = vdpa_to_snet(vdev); @@ -501,6 +513,7 @@ static const struct vdpa_config_ops snet_config_ops = { .set_vq_address = snet_set_vq_address, .set_vq_num = snet_set_vq_num, .kick_vq = snet_kick_vq, + .kick_vq_with_data = snet_kick_vq_with_data, .set_vq_cb = snet_set_vq_cb, .set_vq_ready = snet_set_vq_ready, .get_vq_ready = snet_get_vq_ready, -- GitLab From 5b250fac7c76b670dd1b28b67f1a91a1907bc117 Mon Sep 17 00:00:00 2001 From: Alvaro Karsz Date: Sun, 9 Apr 2023 15:02:42 +0300 Subject: [PATCH 3720/5631] vdpa/snet: use likely/unlikely macros in hot functions - kick callback: most likely that the VQ is ready. - interrupt handlers: most likely that the callback is not NULL. Signed-off-by: Alvaro Karsz Message-Id: <20230409120242.3460074-1-alvaro.karsz@solid-run.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/solidrun/snet_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/vdpa/solidrun/snet_main.c b/drivers/vdpa/solidrun/snet_main.c index da14d437af33..cdcd84ce4f5a 100644 --- a/drivers/vdpa/solidrun/snet_main.c +++ b/drivers/vdpa/solidrun/snet_main.c @@ -39,7 +39,7 @@ static irqreturn_t snet_cfg_irq_hndlr(int irq, void *data) { struct snet *snet = data; /* Call callback if any */ - if (snet->cb.callback) + if (likely(snet->cb.callback)) return snet->cb.callback(snet->cb.private); return IRQ_HANDLED; @@ -49,7 +49,7 @@ static irqreturn_t snet_vq_irq_hndlr(int irq, void *data) { struct snet_vq *vq = data; /* Call callback if any */ - if (vq->cb.callback) + if (likely(vq->cb.callback)) return vq->cb.callback(vq->cb.private); return IRQ_HANDLED; @@ -106,7 +106,7 @@ static void snet_kick_vq(struct vdpa_device *vdev, u16 idx) { struct snet *snet = vdpa_to_snet(vdev); /* not ready - ignore */ - if (!snet->vqs[idx]->ready) + if (unlikely(!snet->vqs[idx]->ready)) return; iowrite32(SNET_KICK_VAL, snet->vqs[idx]->kick_ptr); -- GitLab From 112f23cd72a2975e11986d73575e2c3651ea4c7e Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 7 Apr 2023 15:36:57 +0200 Subject: [PATCH 3721/5631] vdpa_sim: move buffer allocation in the devices Currently, the vdpa_sim core does not use the buffer, but only allocates it. The buffer is used by devices differently, and some future devices may not use it. So let's move all its management inside the devices. Add a new `free` device callback called to clean up the resources allocated by the device. Signed-off-by: Stefano Garzarella Message-Id: <20230407133658.66339-2-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim.c | 7 ++--- drivers/vdpa/vdpa_sim/vdpa_sim.h | 3 +-- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 40 +++++++++++++++++++++++----- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 28 ++++++++++++++----- 4 files changed, 57 insertions(+), 21 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 2c706bb18897..d343af4fa60e 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -261,10 +261,6 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr, for (i = 0; i < vdpasim->dev_attr.nas; i++) vhost_iotlb_init(&vdpasim->iommu[i], max_iotlb_entries, 0); - vdpasim->buffer = kvmalloc(dev_attr->buffer_size, GFP_KERNEL); - if (!vdpasim->buffer) - goto err_iommu; - for (i = 0; i < dev_attr->nvqs; i++) vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0], &vdpasim->iommu_lock); @@ -714,7 +710,8 @@ static void vdpasim_free(struct vdpa_device *vdpa) vringh_kiov_cleanup(&vdpasim->vqs[i].in_iov); } - kvfree(vdpasim->buffer); + vdpasim->dev_attr.free(vdpasim); + for (i = 0; i < vdpasim->dev_attr.nas; i++) vhost_iotlb_reset(&vdpasim->iommu[i]); kfree(vdpasim->iommu); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h index 3a42887d05d9..bb137e479763 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.h +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h @@ -39,7 +39,6 @@ struct vdpasim_dev_attr { u64 supported_features; size_t alloc_size; size_t config_size; - size_t buffer_size; int nvqs; u32 id; u32 ngroups; @@ -51,6 +50,7 @@ struct vdpasim_dev_attr { int (*get_stats)(struct vdpasim *vdpasim, u16 idx, struct sk_buff *msg, struct netlink_ext_ack *extack); + void (*free)(struct vdpasim *vdpasim); }; /* State of each vdpasim device */ @@ -67,7 +67,6 @@ struct vdpasim { void *config; struct vhost_iotlb *iommu; bool *iommu_pt; - void *buffer; u32 status; u32 generation; u64 features; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index 568119e1553f..c996e750dc02 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -43,6 +43,16 @@ #define VDPASIM_BLK_AS_NUM 1 #define VDPASIM_BLK_GROUP_NUM 1 +struct vdpasim_blk { + struct vdpasim vdpasim; + void *buffer; +}; + +static struct vdpasim_blk *sim_to_blk(struct vdpasim *vdpasim) +{ + return container_of(vdpasim, struct vdpasim_blk, vdpasim); +} + static char vdpasim_blk_id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim"; static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, @@ -78,6 +88,7 @@ static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, struct vdpasim_virtqueue *vq) { + struct vdpasim_blk *blk = sim_to_blk(vdpasim); size_t pushed = 0, to_pull, to_push; struct virtio_blk_outhdr hdr; bool handled = false; @@ -144,8 +155,7 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, } bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, - vdpasim->buffer + offset, - to_push); + blk->buffer + offset, to_push); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_push_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -166,8 +176,7 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, } bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, - vdpasim->buffer + offset, - to_pull); + blk->buffer + offset, to_pull); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -247,7 +256,7 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, } if (type == VIRTIO_BLK_T_WRITE_ZEROES) { - memset(vdpasim->buffer + offset, 0, + memset(blk->buffer + offset, 0, num_sectors << SECTOR_SHIFT); } @@ -353,6 +362,13 @@ static void vdpasim_blk_get_config(struct vdpasim *vdpasim, void *config) } +static void vdpasim_blk_free(struct vdpasim *vdpasim) +{ + struct vdpasim_blk *blk = sim_to_blk(vdpasim); + + kvfree(blk->buffer); +} + static void vdpasim_blk_mgmtdev_release(struct device *dev) { } @@ -366,6 +382,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; + struct vdpasim_blk *blk; struct vdpasim *simdev; int ret; @@ -376,16 +393,25 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.nvqs = VDPASIM_BLK_VQ_NUM; dev_attr.ngroups = VDPASIM_BLK_GROUP_NUM; dev_attr.nas = VDPASIM_BLK_AS_NUM; - dev_attr.alloc_size = sizeof(struct vdpasim); + dev_attr.alloc_size = sizeof(struct vdpasim_blk); dev_attr.config_size = sizeof(struct virtio_blk_config); dev_attr.get_config = vdpasim_blk_get_config; dev_attr.work_fn = vdpasim_blk_work; - dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT; + dev_attr.free = vdpasim_blk_free; simdev = vdpasim_create(&dev_attr, config); if (IS_ERR(simdev)) return PTR_ERR(simdev); + blk = sim_to_blk(simdev); + + blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + GFP_KERNEL); + if (!blk->buffer) { + ret = -ENOMEM; + goto put_dev; + } + ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_BLK_VQ_NUM); if (ret) goto put_dev; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index 55920502f76b..cfe962911804 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -58,6 +58,7 @@ struct vdpasim_net{ struct vdpasim_dataq_stats tx_stats; struct vdpasim_dataq_stats rx_stats; struct vdpasim_cq_stats cq_stats; + void *buffer; }; static struct vdpasim_net *sim_to_net(struct vdpasim *vdpasim) @@ -87,14 +88,15 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len) size_t hdr_len = modern ? sizeof(struct virtio_net_hdr_v1) : sizeof(struct virtio_net_hdr); struct virtio_net_config *vio_config = vdpasim->config; + struct vdpasim_net *net = sim_to_net(vdpasim); if (len < ETH_ALEN + hdr_len) return false; - if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) || - is_multicast_ether_addr(vdpasim->buffer + hdr_len)) + if (is_broadcast_ether_addr(net->buffer + hdr_len) || + is_multicast_ether_addr(net->buffer + hdr_len)) return true; - if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN)) + if (!strncmp(net->buffer + hdr_len, vio_config->mac, ETH_ALEN)) return true; return false; @@ -225,8 +227,7 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) ++tx_pkts; read = vringh_iov_pull_iotlb(&txq->vring, &txq->out_iov, - vdpasim->buffer, - PAGE_SIZE); + net->buffer, PAGE_SIZE); tx_bytes += read; @@ -245,7 +246,7 @@ static void vdpasim_net_work(struct vdpasim *vdpasim) } write = vringh_iov_push_iotlb(&rxq->vring, &rxq->in_iov, - vdpasim->buffer, read); + net->buffer, read); if (write <= 0) { ++rx_errors; break; @@ -427,6 +428,13 @@ static void vdpasim_net_setup_config(struct vdpasim *vdpasim, vio_config->mtu = cpu_to_vdpasim16(vdpasim, 1500); } +static void vdpasim_net_free(struct vdpasim *vdpasim) +{ + struct vdpasim_net *net = sim_to_net(vdpasim); + + kvfree(net->buffer); +} + static void vdpasim_net_mgmtdev_release(struct device *dev) { } @@ -456,7 +464,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, dev_attr.get_config = vdpasim_net_get_config; dev_attr.work_fn = vdpasim_net_work; dev_attr.get_stats = vdpasim_net_get_stats; - dev_attr.buffer_size = PAGE_SIZE; + dev_attr.free = vdpasim_net_free; simdev = vdpasim_create(&dev_attr, config); if (IS_ERR(simdev)) @@ -470,6 +478,12 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, u64_stats_init(&net->rx_stats.syncp); u64_stats_init(&net->cq_stats.syncp); + net->buffer = kvmalloc(PAGE_SIZE, GFP_KERNEL); + if (!net->buffer) { + ret = -ENOMEM; + goto reg_err; + } + /* * Initialization must be completed before this call, since it can * connect the device to the vDPA bus, so requests can arrive after -- GitLab From abebb16254b362664452e14d9711ddb54855ddcf Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 7 Apr 2023 15:36:58 +0200 Subject: [PATCH 3722/5631] vdpa_sim_blk: support shared backend The vdpa_sim_blk simulator uses a ramdisk as the backend. To test live migration, we need two devices that share the backend to have the data synchronized with each other. Add a new module parameter to make the buffer shared between all devices. The shared_buffer_mutex is used just to ensure that each operation is atomic, but it is up to the user to use the devices knowing that the underlying ramdisk is shared. For example, when we do a migration, the VMM (e.g., QEMU) will guarantee to write to the destination device, only after completing operations with the source device. Signed-off-by: Stefano Garzarella Message-Id: <20230407133658.66339-3-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 57 ++++++++++++++++++++++++---- 1 file changed, 50 insertions(+), 7 deletions(-) diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index c996e750dc02..00d7d72713be 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -46,6 +46,7 @@ struct vdpasim_blk { struct vdpasim vdpasim; void *buffer; + bool shared_backend; }; static struct vdpasim_blk *sim_to_blk(struct vdpasim *vdpasim) @@ -55,6 +56,26 @@ static struct vdpasim_blk *sim_to_blk(struct vdpasim *vdpasim) static char vdpasim_blk_id[VIRTIO_BLK_ID_BYTES] = "vdpa_blk_sim"; +static bool shared_backend; +module_param(shared_backend, bool, 0444); +MODULE_PARM_DESC(shared_backend, "Enable the shared backend between virtio-blk devices"); + +static void *shared_buffer; +/* mutex to synchronize shared_buffer access */ +static DEFINE_MUTEX(shared_buffer_mutex); + +static void vdpasim_blk_buffer_lock(struct vdpasim_blk *blk) +{ + if (blk->shared_backend) + mutex_lock(&shared_buffer_mutex); +} + +static void vdpasim_blk_buffer_unlock(struct vdpasim_blk *blk) +{ + if (blk->shared_backend) + mutex_unlock(&shared_buffer_mutex); +} + static bool vdpasim_blk_check_range(struct vdpasim *vdpasim, u64 start_sector, u64 num_sectors, u64 max_sectors) { @@ -154,8 +175,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, break; } + vdpasim_blk_buffer_lock(blk); bytes = vringh_iov_push_iotlb(&vq->vring, &vq->in_iov, blk->buffer + offset, to_push); + vdpasim_blk_buffer_unlock(blk); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_push_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -175,8 +198,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, break; } + vdpasim_blk_buffer_lock(blk); bytes = vringh_iov_pull_iotlb(&vq->vring, &vq->out_iov, blk->buffer + offset, to_pull); + vdpasim_blk_buffer_unlock(blk); if (bytes < 0) { dev_dbg(&vdpasim->vdpa.dev, "vringh_iov_pull_iotlb() error: %zd offset: 0x%llx len: 0x%zx\n", @@ -256,8 +281,10 @@ static bool vdpasim_blk_handle_req(struct vdpasim *vdpasim, } if (type == VIRTIO_BLK_T_WRITE_ZEROES) { + vdpasim_blk_buffer_lock(blk); memset(blk->buffer + offset, 0, num_sectors << SECTOR_SHIFT); + vdpasim_blk_buffer_unlock(blk); } break; @@ -366,7 +393,8 @@ static void vdpasim_blk_free(struct vdpasim *vdpasim) { struct vdpasim_blk *blk = sim_to_blk(vdpasim); - kvfree(blk->buffer); + if (!blk->shared_backend) + kvfree(blk->buffer); } static void vdpasim_blk_mgmtdev_release(struct device *dev) @@ -404,12 +432,17 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, return PTR_ERR(simdev); blk = sim_to_blk(simdev); - - blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, - GFP_KERNEL); - if (!blk->buffer) { - ret = -ENOMEM; - goto put_dev; + blk->shared_backend = shared_backend; + + if (blk->shared_backend) { + blk->buffer = shared_buffer; + } else { + blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + GFP_KERNEL); + if (!blk->buffer) { + ret = -ENOMEM; + goto put_dev; + } } ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_BLK_VQ_NUM); @@ -461,6 +494,15 @@ static int __init vdpasim_blk_init(void) if (ret) goto parent_err; + if (shared_backend) { + shared_buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + GFP_KERNEL); + if (!shared_buffer) { + ret = -ENOMEM; + goto parent_err; + } + } + return 0; parent_err: @@ -470,6 +512,7 @@ static int __init vdpasim_blk_init(void) static void __exit vdpasim_blk_exit(void) { + kvfree(shared_buffer); vdpa_mgmtdev_unregister(&mgmt_dev); device_unregister(&vdpasim_blk_mgmtdev); } -- GitLab From 38fc29ea754711e9a8c4e9ca2678ab41353a4662 Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Mon, 17 Apr 2023 11:20:36 +0900 Subject: [PATCH 3723/5631] virtio_ring: add a struct device forward declaration The virtio_ring header file uses the struct device without a forward declaration. Signed-off-by: Shunsuke Mie Message-Id: <20230417022037.917668-1-mie@igel.co.jp> Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_ring.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 2550c9170f4f..9b33df741b63 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -58,6 +58,7 @@ do { \ struct virtio_device; struct virtqueue; +struct device; /* * Creates a virtqueue and allocates the descriptor ring. If -- GitLab From e9c4962c5d69b8a238bb8bd51e8fdce39be13e5b Mon Sep 17 00:00:00 2001 From: Shunsuke Mie Date: Mon, 17 Apr 2023 11:20:37 +0900 Subject: [PATCH 3724/5631] tools/virtio: fix build caused by virtio_ring changes Fix the build dependency for virtio_test. The virtio_ring that is used from the test requires container_of_const(). Change to use container_of.h kernel header directly and adapt related codes. Signed-off-by: Shunsuke Mie Message-Id: <20230417022037.917668-2-mie@igel.co.jp> Signed-off-by: Michael S. Tsirkin --- tools/include/linux/types.h | 5 +++++ tools/virtio/linux/compiler.h | 2 ++ tools/virtio/linux/kernel.h | 5 +---- tools/virtio/linux/uaccess.h | 11 ++--------- 4 files changed, 10 insertions(+), 13 deletions(-) diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h index 051fdeaf2670..8519386acd23 100644 --- a/tools/include/linux/types.h +++ b/tools/include/linux/types.h @@ -49,7 +49,12 @@ typedef __s8 s8; #endif #define __force +/* This is defined in linux/compiler_types.h and is left for backward + * compatibility. + */ +#ifndef __user #define __user +#endif #define __must_check #define __cold diff --git a/tools/virtio/linux/compiler.h b/tools/virtio/linux/compiler.h index 2c51bccb97bb..1f3a15b954b9 100644 --- a/tools/virtio/linux/compiler.h +++ b/tools/virtio/linux/compiler.h @@ -2,6 +2,8 @@ #ifndef LINUX_COMPILER_H #define LINUX_COMPILER_H +#include "../../../include/linux/compiler_types.h" + #define WRITE_ONCE(var, val) \ (*((volatile typeof(val) *)(&(var))) = (val)) diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 8b877167933d..6702008f7f5c 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include #include +#include "../../../include/linux/container_of.h" #include #include #include @@ -107,10 +108,6 @@ static inline void free_page(unsigned long addr) free((void *)addr); } -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) - # ifndef likely # define likely(x) (__builtin_expect(!!(x), 1)) # endif diff --git a/tools/virtio/linux/uaccess.h b/tools/virtio/linux/uaccess.h index 991dfb263998..f13828e0c409 100644 --- a/tools/virtio/linux/uaccess.h +++ b/tools/virtio/linux/uaccess.h @@ -6,15 +6,10 @@ extern void *__user_addr_min, *__user_addr_max; -static inline void __chk_user_ptr(const volatile void *p, size_t size) -{ - assert(p >= __user_addr_min && p + size <= __user_addr_max); -} - #define put_user(x, ptr) \ ({ \ typeof(ptr) __pu_ptr = (ptr); \ - __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \ + __chk_user_ptr(__pu_ptr); \ WRITE_ONCE(*(__pu_ptr), x); \ 0; \ }) @@ -22,7 +17,7 @@ static inline void __chk_user_ptr(const volatile void *p, size_t size) #define get_user(x, ptr) \ ({ \ typeof(ptr) __pu_ptr = (ptr); \ - __chk_user_ptr(__pu_ptr, sizeof(*__pu_ptr)); \ + __chk_user_ptr(__pu_ptr); \ x = READ_ONCE(*(__pu_ptr)); \ 0; \ }) @@ -37,7 +32,6 @@ static void volatile_memcpy(volatile char *to, const volatile char *from, static inline int copy_from_user(void *to, const void __user volatile *from, unsigned long n) { - __chk_user_ptr(from, n); volatile_memcpy(to, from, n); return 0; } @@ -45,7 +39,6 @@ static inline int copy_from_user(void *to, const void __user volatile *from, static inline int copy_to_user(void __user volatile *to, const void *from, unsigned long n) { - __chk_user_ptr(to, n); volatile_memcpy(to, from, n); return 0; } -- GitLab From 11841c52fa525c9be17c0731cc897d93c3c0f4fe Mon Sep 17 00:00:00 2001 From: Xuan Zhuo Date: Thu, 13 Apr 2023 15:16:10 +0800 Subject: [PATCH 3725/5631] MAINTAINERS: make me a reviewer of VIRTIO CORE AND NET DRIVERS First of all, I personally love open source, linux and virtio. I have also participated in community work such as virtio for a long time. I think I am familiar enough with virtio/virtio-net and is adequate as a reviewer. Every time there is some patch/bug, I wish I can get pinged and I will feedback on that. For me personally, being a reviewer is an honor and a responsibility, and it also makes it easier for me to participate in virtio-related work. And I will spend more time reviewing virtio patch. Better advance virtio development I had some contributions to virtio/virtio-net and some support for it. * per-queue reset * virtio-net xdp * some bug fix * ...... I make a humble request to grant the reviewer role for the virtio core and net drivers. Signed-off-by: Xuan Zhuo Message-Id: <20230413071610.43659-1-xuanzhuo@linux.alibaba.com> Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index a8df70387877..4bdf08b2ab55 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22064,6 +22064,7 @@ F: include/uapi/linux/virtio_console.h VIRTIO CORE AND NET DRIVERS M: "Michael S. Tsirkin" M: Jason Wang +R: Xuan Zhuo L: virtualization@lists.linux-foundation.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-vdpa -- GitLab From c82729e06644f4e087f5ff0f91b8fb15e03b8890 Mon Sep 17 00:00:00 2001 From: Cindy Lu Date: Thu, 20 Apr 2023 23:17:34 +0800 Subject: [PATCH 3726/5631] vhost_vdpa: fix unmap process in no-batch mode While using the vdpa device with vIOMMU enabled in the guest VM, when the vdpa device bind to vfio-pci and run testpmd then system will fail to unmap. The test process is Load guest VM --> attach to virtio driver--> bind to vfio-pci driver So the mapping process is 1)batched mode map to normal MR 2)batched mode unmapped the normal MR 3)unmapped all the memory 4)mapped to iommu MR This error happened in step 3). The iotlb was freed in step 2) and the function vhost_vdpa_process_iotlb_msg will return fail Which causes failure. To fix this, we will not remove the AS while the iotlb->nmaps is 0. This will free in the vhost_vdpa_clean Cc: stable@vger.kernel.org Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API") Signed-off-by: Cindy Lu Message-Id: <20230420151734.860168-1-lulu@redhat.com> Signed-off-by: Michael S. Tsirkin --- drivers/vhost/vdpa.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index cd266fa80c4e..5133004452a1 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -886,11 +886,7 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v, if (!v->in_batch) ops->set_map(vdpa, asid, iotlb); } - /* If we are in the middle of batch processing, delay the free - * of AS until BATCH_END. - */ - if (!v->in_batch && !iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); + } static int vhost_vdpa_va_map(struct vhost_vdpa *v, @@ -1147,8 +1143,6 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid, if (v->in_batch && ops->set_map) ops->set_map(vdpa, asid, iotlb); v->in_batch = false; - if (!iotlb->nmaps) - vhost_vdpa_remove_as(v, asid); break; default: r = -EINVAL; -- GitLab From 4327a6137ed43a091d900b1ac833345d60f32228 Mon Sep 17 00:00:00 2001 From: Jammy Huang Date: Fri, 21 Apr 2023 08:33:54 +0800 Subject: [PATCH 3727/5631] drm/ast: Fix ARM compatibility ARM architecture only has 'memory', so all devices are accessed by MMIO if possible. Signed-off-by: Jammy Huang Reviewed-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230421003354.27767-1-jammy_huang@aspeedtech.com --- drivers/gpu/drm/ast/ast_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index f83ce77127cb..a6d0ee4da2b8 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -425,11 +425,12 @@ struct ast_private *ast_device_create(const struct drm_driver *drv, return ERR_PTR(-EIO); /* - * If we don't have IO space at all, use MMIO now and - * assume the chip has MMIO enabled by default (rev 0x20 - * and higher). + * After AST2500, MMIO is enabled by default, and it should be adopted + * to be compatible with Arm. */ - if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) { + if (pdev->revision >= 0x40) { + ast->ioregs = ast->regs + AST_IO_MM_OFFSET; + } else if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) { drm_info(dev, "platform has no IO space, trying MMIO\n"); ast->ioregs = ast->regs + AST_IO_MM_OFFSET; } -- GitLab From c8687694bb1f5c48134f152f8c5c2e53483eb99d Mon Sep 17 00:00:00 2001 From: Sui Jingfeng Date: Thu, 20 Apr 2023 11:05:00 +0800 Subject: [PATCH 3728/5631] drm/fbdev-generic: prohibit potential out-of-bounds access The fbdev test of IGT may write after EOF, which lead to out-of-bound access for drm drivers with fbdev-generic. For example, run fbdev test on a x86+ast2400 platform, with 1680x1050 resolution, will cause the linux kernel hang with the following call trace: Oops: 0000 [#1] PREEMPT SMP PTI [IGT] fbdev: starting subtest eof Workqueue: events drm_fb_helper_damage_work [drm_kms_helper] [IGT] fbdev: starting subtest nullptr RIP: 0010:memcpy_erms+0xa/0x20 RSP: 0018:ffffa17d40167d98 EFLAGS: 00010246 RAX: ffffa17d4eb7fa80 RBX: ffffa17d40e0aa80 RCX: 00000000000014c0 RDX: 0000000000001a40 RSI: ffffa17d40e0b000 RDI: ffffa17d4eb80000 RBP: ffffa17d40167e20 R08: 0000000000000000 R09: ffff89522ecff8c0 R10: ffffa17d4e4c5000 R11: 0000000000000000 R12: ffffa17d4eb7fa80 R13: 0000000000001a40 R14: 000000000000041a R15: ffffa17d40167e30 FS: 0000000000000000(0000) GS:ffff895257380000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffa17d40e0b000 CR3: 00000001eaeca006 CR4: 00000000001706e0 Call Trace: ? drm_fbdev_generic_helper_fb_dirty+0x207/0x330 [drm_kms_helper] drm_fb_helper_damage_work+0x8f/0x170 [drm_kms_helper] process_one_work+0x21f/0x430 worker_thread+0x4e/0x3c0 ? __pfx_worker_thread+0x10/0x10 kthread+0xf4/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 CR2: ffffa17d40e0b000 ---[ end trace 0000000000000000 ]--- The is because damage rectangles computed by drm_fb_helper_memory_range_to_clip() function is not guaranteed to be bound in the screen's active display area. Possible reasons are: 1) Buffers are allocated in the granularity of page size, for mmap system call support. The shadow screen buffer consumed by fbdev emulation may also choosed be page size aligned. 2) The DIV_ROUND_UP() used in drm_fb_helper_memory_range_to_clip() will introduce off-by-one error. For example, on a 16KB page size system, in order to store a 1920x1080 XRGB framebuffer, we need allocate 507 pages. Unfortunately, the size 1920*1080*4 can not be divided exactly by 16KB. 1920 * 1080 * 4 = 8294400 bytes 506 * 16 * 1024 = 8290304 bytes 507 * 16 * 1024 = 8306688 bytes line_length = 1920*4 = 7680 bytes 507 * 16 * 1024 / 7680 = 1081.6 off / line_length = 507 * 16 * 1024 / 7680 = 1081 DIV_ROUND_UP(507 * 16 * 1024, 7680) will yeild 1082 memcpy_toio() typically issue the copy line by line, when copy the last line, out-of-bound access will be happen. Because: 1082 * line_length = 1082 * 7680 = 8309760, and 8309760 > 8306688 Note that userspace may still write to the invisiable area if a larger buffer than width x stride is exposed. But it is not a big issue as long as there still have memory resolve the access if not drafting so far. - Also limit the y1 (Daniel) - keep fix patch it to minimal (Daniel) - screen_size is page size aligned because of it need mmap (Thomas) - Adding fixes tag (Thomas) Signed-off-by: Sui Jingfeng Fixes: aa15c677cc34 ("drm/fb-helper: Fix vertical damage clipping") Reviewed-by: Thomas Zimmermann Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/dri-devel/ad44df29-3241-0d9e-e708-b0338bf3c623@189.cn/ Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230420030500.1578756-1-suijingfeng@loongson.cn --- drivers/gpu/drm/drm_fb_helper.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index a39998047f8a..883f31db1143 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -625,19 +625,27 @@ static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, size_t len, struct drm_rect *clip) { + u32 line_length = info->fix.line_length; + u32 fb_height = info->var.yres; off_t end = off + len; u32 x1 = 0; - u32 y1 = off / info->fix.line_length; + u32 y1 = off / line_length; u32 x2 = info->var.xres; - u32 y2 = DIV_ROUND_UP(end, info->fix.line_length); + u32 y2 = DIV_ROUND_UP(end, line_length); + + /* Don't allow any of them beyond the bottom bound of display area */ + if (y1 > fb_height) + y1 = fb_height; + if (y2 > fb_height) + y2 = fb_height; if ((y2 - y1) == 1) { /* * We've only written to a single scanline. Try to reduce * the number of horizontal pixels that need an update. */ - off_t bit_off = (off % info->fix.line_length) * 8; - off_t bit_end = (end % info->fix.line_length) * 8; + off_t bit_off = (off % line_length) * 8; + off_t bit_end = (end % line_length) * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); -- GitLab From f9a5502f8ee3d2bc4403f561f0037c920ca35e6d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Wed, 12 Apr 2023 20:50:49 +0200 Subject: [PATCH 3729/5631] pinctrl: wpcm450: select MFD_SYSCON MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pinctrl-wpcm450 driver relies on MFD_SYSCON functionality in order to find some of its MMIO registers. Select MFD_SYSCON from PINCTRL_WPCM450 to ensure that it's enabled. Signed-off-by: Jonathan Neuschäfer Link: https://lore.kernel.org/r/20230412185049.3782842-1-j.neuschaefer@gmx.net Signed-off-by: Linus Walleij --- drivers/pinctrl/nuvoton/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/nuvoton/Kconfig b/drivers/pinctrl/nuvoton/Kconfig index 852b0d0eb08e..8fe61b348181 100644 --- a/drivers/pinctrl/nuvoton/Kconfig +++ b/drivers/pinctrl/nuvoton/Kconfig @@ -11,6 +11,7 @@ config PINCTRL_WPCM450 select GPIOLIB select GPIO_GENERIC select GPIOLIB_IRQCHIP + select MFD_SYSCON help Say Y or M here to enable pin controller and GPIO support for the Nuvoton WPCM450 SoC. This is strongly recommended when -- GitLab From 4b648d94946618c7efee21227a5d646cec3335c3 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Tue, 18 Apr 2023 18:43:17 +0200 Subject: [PATCH 3730/5631] dt-bindings: pinctrl: qcom,pmic-gpio: add PMI632 Document the 8 GPIOs found on PMI632. Signed-off-by: Luca Weiss Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230414-pmi632-v2-1-98bafa909c36@z3ntu.xyz Signed-off-by: Linus Walleij --- Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml index 36c6435cfd0a..eaadd5a9a445 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml @@ -52,6 +52,7 @@ properties: - qcom,pm8994-gpio - qcom,pm8998-gpio - qcom,pma8084-gpio + - qcom,pmi632-gpio - qcom,pmi8950-gpio - qcom,pmi8994-gpio - qcom,pmi8998-gpio @@ -174,6 +175,7 @@ allOf: - qcom,pm8350b-gpio - qcom,pm8550ve-gpio - qcom,pm8950-gpio + - qcom,pmi632-gpio then: properties: gpio-line-names: @@ -435,6 +437,7 @@ $defs: - gpio1-gpio22 for pm8994 - gpio1-gpio26 for pm8998 - gpio1-gpio22 for pma8084 + - gpio1-gpio8 for pmi632 - gpio1-gpio2 for pmi8950 - gpio1-gpio10 for pmi8994 - gpio1-gpio4 for pmk8350 -- GitLab From 7abf7f88df456a373ce34c05a54068574f6fbfef Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Tue, 18 Apr 2023 18:43:18 +0200 Subject: [PATCH 3731/5631] pinctrl: qcom: spmi-gpio: Add PMI632 support Add support for the 8 GPIOs found on PMI632. Signed-off-by: Luca Weiss Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230414-pmi632-v2-2-98bafa909c36@z3ntu.xyz Signed-off-by: Linus Walleij --- drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c index 0d94175b34f8..43c7857c06a5 100644 --- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c +++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c @@ -1232,6 +1232,7 @@ static const struct of_device_id pmic_gpio_of_match[] = { { .compatible = "qcom,pm8994-gpio", .data = (void *) 22 }, { .compatible = "qcom,pm8998-gpio", .data = (void *) 26 }, { .compatible = "qcom,pma8084-gpio", .data = (void *) 22 }, + { .compatible = "qcom,pmi632-gpio", .data = (void *) 8 }, { .compatible = "qcom,pmi8950-gpio", .data = (void *) 2 }, { .compatible = "qcom,pmi8994-gpio", .data = (void *) 10 }, { .compatible = "qcom,pmi8998-gpio", .data = (void *) 14 }, -- GitLab From d59655d3c014fd08896b01a4602bbd8ee67db944 Mon Sep 17 00:00:00 2001 From: Devi Priya Date: Mon, 17 Apr 2023 11:43:37 +0530 Subject: [PATCH 3732/5631] dt-bindings: pinctrl: qcom: Add few missing functions Added the missing functions cri_trng2, gpio and removed the duplicate entry qdss_tracedata_b Fixes: 5b63ccb69ee8 ("dt-bindings: pinctrl: qcom: Add support for IPQ9574") Acked-by: Krzysztof Kozlowski Signed-off-by: Devi Priya Link: https://lore.kernel.org/r/20230417061337.6552-1-quic_devipriy@quicinc.com Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml index f32239d08c32..673713debac2 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq9574-tlmm.yaml @@ -74,15 +74,15 @@ $defs: blsp1_i2c, blsp1_spi, blsp1_uart, blsp2_i2c, blsp2_spi, blsp2_uart, blsp3_i2c, blsp3_spi, blsp3_uart, blsp4_i2c, blsp4_spi, blsp4_uart, blsp5_i2c, blsp5_uart, cri_trng0, - cri_trng1, cri_trng3, cxc0, cxc1, dbg_out, dwc_ddrphy, - gcc_plltest, gcc_tlmm, mac, mdc, mdio, pcie0_clk, pcie0_wake, + cri_trng1, cri_trng2, cri_trng3, cxc0, cxc1, dbg_out, dwc_ddrphy, + gcc_plltest, gcc_tlmm, gpio, mac, mdc, mdio, pcie0_clk, pcie0_wake, pcie1_clk, pcie1_wake, pcie2_clk, pcie2_wake, pcie3_clk, pcie3_wake, prng_rosc0, prng_rosc1, prng_rosc2, prng_rosc3, pta, pwm, qdss_cti_trig_in_a0, qdss_cti_trig_in_a1, qdss_cti_trig_in_b0, qdss_cti_trig_in_b1, qdss_cti_trig_out_a0, qdss_cti_trig_out_a1, qdss_cti_trig_out_b0, qdss_cti_trig_out_b1, qdss_traceclk_a, qdss_traceclk_b, qdss_tracectl_a, qdss_tracectl_b, qdss_tracedata_a, - qdss_tracedata_b, qdss_tracedata_b, qspi_clk, qspi_cs, qspi_data, + qdss_tracedata_b, qspi_clk, qspi_cs, qspi_data, rx0, rx1, sdc_clk, sdc_cmd, sdc_data, sdc_rclk, tsens_max, wci20, wci21, wsa_swrm ] -- GitLab From b19a1d8f1dbd2410eaa2f4a5f7680197e2647c94 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 18 Apr 2023 10:06:13 -0500 Subject: [PATCH 3733/5631] dt-bindings: pinctrl: qcom,sm8150: Drop duplicate function value "atest_usb2" The enum value "atest_usb2" appears twice. Remove the duplicate. The meta-schema normally catches these, but schemas under "$defs" was not getting checked. A fix for that is pending. Signed-off-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230418150613.1528233-1-robh@kernel.org Signed-off-by: Linus Walleij --- .../devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml index c5ffbea95957..c6439626464e 100644 --- a/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/qcom,sm8150-pinctrl.yaml @@ -82,7 +82,7 @@ $defs: enum: [ adsp_ext, agera_pll, aoss_cti, ddr_pxi2, atest_char, atest_char0, atest_char1, atest_char2, atest_char3, audio_ref, atest_usb1, atest_usb2, atest_usb10, atest_usb11, atest_usb12, - atest_usb13, atest_usb20, atest_usb21, atest_usb22, atest_usb2, + atest_usb13, atest_usb20, atest_usb21, atest_usb22, atest_usb23, btfm_slimbus, cam_mclk, cci_async, cci_i2c, cci_timer0, cci_timer1, cci_timer2, cci_timer3, cci_timer4, cri_trng, cri_trng0, cri_trng1, dbg_out, ddr_bist, ddr_pxi0, -- GitLab From b7badd752de05312fdb1aeb388480f706d0c087f Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 20 Apr 2023 14:47:05 +0200 Subject: [PATCH 3734/5631] pinctrl-bcm2835.c: fix race condition when setting gpio dir In the past setting the pin direction called pinctrl_gpio_direction() which uses a mutex to serialize this. That was changed to set the direction directly in the pin controller driver, but that lost the serialization mechanism. Since the direction of multiple pins are in the same register you can have a race condition, something that was in fact observed with the cec-gpio driver. Add a new spinlock to serialize writing to the FSEL registers. Signed-off-by: Hans Verkuil Fixes: 1a4541b68e25 ("pinctrl-bcm2835: don't call pinctrl_gpio_direction()") Link: https://lore.kernel.org/r/4302b66b-ca20-0f19-d2aa-ee8661118863@xs4all.nl Signed-off-by: Linus Walleij --- drivers/pinctrl/bcm/pinctrl-bcm2835.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index 8e2551a08c37..7435173e10f4 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -90,6 +90,8 @@ struct bcm2835_pinctrl { struct pinctrl_gpio_range gpio_range; raw_spinlock_t irq_lock[BCM2835_NUM_BANKS]; + /* Protect FSEL registers */ + spinlock_t fsel_lock; }; /* pins are just named GPIO0..GPIO53 */ @@ -284,14 +286,19 @@ static inline void bcm2835_pinctrl_fsel_set( struct bcm2835_pinctrl *pc, unsigned pin, enum bcm2835_fsel fsel) { - u32 val = bcm2835_gpio_rd(pc, FSEL_REG(pin)); - enum bcm2835_fsel cur = (val >> FSEL_SHIFT(pin)) & BCM2835_FSEL_MASK; + u32 val; + enum bcm2835_fsel cur; + unsigned long flags; + + spin_lock_irqsave(&pc->fsel_lock, flags); + val = bcm2835_gpio_rd(pc, FSEL_REG(pin)); + cur = (val >> FSEL_SHIFT(pin)) & BCM2835_FSEL_MASK; dev_dbg(pc->dev, "read %08x (%u => %s)\n", val, pin, - bcm2835_functions[cur]); + bcm2835_functions[cur]); if (cur == fsel) - return; + goto unlock; if (cur != BCM2835_FSEL_GPIO_IN && fsel != BCM2835_FSEL_GPIO_IN) { /* always transition through GPIO_IN */ @@ -309,6 +316,9 @@ static inline void bcm2835_pinctrl_fsel_set( dev_dbg(pc->dev, "write %08x (%u <= %s)\n", val, pin, bcm2835_functions[fsel]); bcm2835_gpio_wr(pc, FSEL_REG(pin), val); + +unlock: + spin_unlock_irqrestore(&pc->fsel_lock, flags); } static int bcm2835_gpio_direction_input(struct gpio_chip *chip, unsigned offset) @@ -1248,6 +1258,7 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) pc->gpio_chip = *pdata->gpio_chip; pc->gpio_chip.parent = dev; + spin_lock_init(&pc->fsel_lock); for (i = 0; i < BCM2835_NUM_BANKS; i++) { unsigned long events; unsigned offset; -- GitLab From 1f0f4a2ef7a5693b135ce174e71f116db4bd684d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 21 Apr 2023 07:16:05 +0000 Subject: [PATCH 3735/5631] KVM: arm64: Infer the PA offset from IPA in stage-2 map walker Until now, the page table walker counted increments to the PA and IPA of a walk in two separate places. While the PA is incremented as soon as a leaf PTE is installed in stage2_map_walker_try_leaf(), the IPA is actually bumped in the generic table walker context. Critically, __kvm_pgtable_visit() rereads the PTE after the LEAF callback returns to work out if a table or leaf was installed, and only bumps the IPA for a leaf PTE. This arrangement worked fine when we handled faults behind the write lock, as the walker had exclusive access to the stage-2 page tables. However, commit 1577cb5823ce ("KVM: arm64: Handle stage-2 faults in parallel") started handling all stage-2 faults behind the read lock, opening up a race where a walker could increment the PA but not the IPA of a walk. Nothing good ensues, as the walker starts mapping with the incorrect IPA -> PA relationship. For example, assume that two vCPUs took a data abort on the same IPA. One observes that dirty logging is disabled, and the other observed that it is enabled: vCPU attempting PMD mapping vCPU attempting PTE mapping ====================================== ===================================== /* install PMD */ stage2_make_pte(ctx, leaf); data->phys += granule; /* replace PMD with a table */ stage2_try_break_pte(ctx, data->mmu); stage2_make_pte(ctx, table); /* table is observed */ ctx.old = READ_ONCE(*ptep); table = kvm_pte_table(ctx.old, level); /* * map walk continues w/o incrementing * IPA. */ __kvm_pgtable_walk(..., level + 1); Bring an end to the whole mess by using the IPA as the single source of truth for how far along a walk has gotten. Work out the correct PA to map by calculating the IPA offset from the beginning of the walk and add that to the starting physical address. Cc: stable@vger.kernel.org Fixes: 1577cb5823ce ("KVM: arm64: Handle stage-2 faults in parallel") Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230421071606.1603916-2-oliver.upton@linux.dev --- arch/arm64/include/asm/kvm_pgtable.h | 1 + arch/arm64/kvm/hyp/pgtable.c | 32 ++++++++++++++++++++++++---- 2 files changed, 29 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h index 4cd6762bda80..dc3c072e862f 100644 --- a/arch/arm64/include/asm/kvm_pgtable.h +++ b/arch/arm64/include/asm/kvm_pgtable.h @@ -209,6 +209,7 @@ struct kvm_pgtable_visit_ctx { kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; + u64 start; u64 addr; u64 end; u32 level; diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 3d61bd3e591d..140f82300db5 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,6 +58,7 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; + u64 start; u64 addr; u64 end; }; @@ -201,6 +202,7 @@ static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, .old = READ_ONCE(*ptep), .arg = data->walker->arg, .mm_ops = mm_ops, + .start = data->start, .addr = data->addr, .end = data->end, .level = level, @@ -293,6 +295,7 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker) { struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), .addr = ALIGN_DOWN(addr, PAGE_SIZE), .end = PAGE_ALIGN(walk_data.addr + size), .walker = walker, @@ -794,20 +797,43 @@ static bool stage2_pte_executable(kvm_pte_t pte) return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN); } +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* + * Stage-2 walks to update ownership data are communicated to the map + * walker using an invalid PA. Avoid offsetting an already invalid PA, + * which could overflow and make the address valid again. + */ + if (!kvm_phys_is_valid(phys)) + return phys; + + /* + * Otherwise, work out the correct PA based on how far the walk has + * gotten. + */ + return phys + (ctx->addr - ctx->start); +} + static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { + u64 phys = stage2_map_walker_phys_addr(ctx, data); + if (data->force_pte && (ctx->level < (KVM_PGTABLE_MAX_LEVELS - 1))) return false; - return kvm_block_mapping_supported(ctx, data->phys); + return kvm_block_mapping_supported(ctx, phys); } static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct stage2_map_data *data) { kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); struct kvm_pgtable *pgt = data->mmu->pgt; struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; @@ -841,8 +867,6 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, stage2_make_pte(ctx, new); - if (kvm_phys_is_valid(phys)) - data->phys += granule; return 0; } -- GitLab From 39bc95be3782ba88e55cd72e830f37e74395831b Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 21 Apr 2023 07:16:06 +0000 Subject: [PATCH 3736/5631] KVM: arm64: Infer PA offset from VA in hyp map walker Similar to the recently fixed stage-2 walker, the hyp map walker increments the PA and VA of a walk separately. Unlike stage-2, there is no bug here as the map walker has exclusive access to the stage-1 page tables. Nonetheless, in the interest of continuity throughout the page table code, tweak the hyp map walker to avoid incrementing the PA and instead use the VA as the authoritative source of how far along a table walk has gotten. Calculate the PA to use for a leaf PTE by adding the offset of the VA from the start of the walk to the starting PA. Signed-off-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230421071606.1603916-3-oliver.upton@linux.dev --- arch/arm64/kvm/hyp/pgtable.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 140f82300db5..356a3fd5220c 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -410,13 +410,12 @@ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, struct hyp_map_data *data) { + u64 phys = data->phys + (ctx->addr - ctx->start); kvm_pte_t new; - u64 granule = kvm_granule_size(ctx->level), phys = data->phys; if (!kvm_block_mapping_supported(ctx, phys)) return false; - data->phys += granule; new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); if (ctx->old == new) return true; -- GitLab From 1ea244158a4a20ac686f4d1d46285f3d38d4571f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 21 Apr 2023 10:18:34 +0100 Subject: [PATCH 3737/5631] KVM: arm64: Constify start/end/phys fields of the pgtable walker data As we are revamping the way the pgtable walker evaluates some of the data, make it clear that we rely on somew of the fields to be constant across the lifetime of a walk. For this, flag the start, end and phys fields of the walk data as 'const', which will generate an error if we were to accidentally update these fields again. Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/pgtable.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 356a3fd5220c..5282cb9ca4cf 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -58,9 +58,9 @@ struct kvm_pgtable_walk_data { struct kvm_pgtable_walker *walker; - u64 start; + const u64 start; u64 addr; - u64 end; + const u64 end; }; static bool kvm_phys_is_valid(u64 phys) @@ -352,7 +352,7 @@ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, } struct hyp_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; }; @@ -578,7 +578,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) } struct stage2_map_data { - u64 phys; + const u64 phys; kvm_pte_t attr; u8 owner_id; -- GitLab From 2d60eca501bc70fc73d30a1b151a137c3b990183 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 20 Apr 2023 21:19:03 +0200 Subject: [PATCH 3738/5631] sh: sq: Use the bitmap API when applicable Using the bitmap API is less verbose than hand writing it. It also improves the semantic. Signed-off-by: Christophe JAILLET Reviewed-by: Geert Uytterhoeven Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/a51e9f32c19a007f4922943282cb12c89064440d.1681671848.git.christophe.jaillet@wanadoo.fr Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/kernel/cpu/sh4/sq.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index 6e0bb3f47fa5..d289e99dc118 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -372,7 +372,6 @@ static struct subsys_interface sq_interface = { static int __init sq_api_init(void) { unsigned int nr_pages = 0x04000000 >> PAGE_SHIFT; - unsigned int size = (nr_pages + (BITS_PER_LONG - 1)) / BITS_PER_LONG; int ret = -ENOMEM; printk(KERN_NOTICE "sq: Registering store queue API.\n"); @@ -382,7 +381,7 @@ static int __init sq_api_init(void) if (unlikely(!sq_cache)) return ret; - sq_bitmap = kcalloc(size, sizeof(long), GFP_KERNEL); + sq_bitmap = bitmap_zalloc(nr_pages, GFP_KERNEL); if (unlikely(!sq_bitmap)) goto out; @@ -393,7 +392,7 @@ static int __init sq_api_init(void) return 0; out: - kfree(sq_bitmap); + bitmap_free(sq_bitmap); kmem_cache_destroy(sq_cache); return ret; @@ -402,7 +401,7 @@ static int __init sq_api_init(void) static void __exit sq_api_exit(void) { subsys_interface_unregister(&sq_interface); - kfree(sq_bitmap); + bitmap_free(sq_bitmap); kmem_cache_destroy(sq_cache); } -- GitLab From 223baf9d17f25e2608dbdff7232c095c1e612268 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Thu, 20 Apr 2023 10:55:48 -0400 Subject: [PATCH 3739/5631] sched: Fix performance regression introduced by mm_cid Introduce per-mm/cpu current concurrency id (mm_cid) to fix a PostgreSQL sysbench regression reported by Aaron Lu. Keep track of the currently allocated mm_cid for each mm/cpu rather than freeing them immediately on context switch. This eliminates most atomic operations when context switching back and forth between threads belonging to different memory spaces in multi-threaded scenarios (many processes, each with many threads). The per-mm/per-cpu mm_cid values are serialized by their respective runqueue locks. Thread migration is handled by introducing invocation to sched_mm_cid_migrate_to() (with destination runqueue lock held) in activate_task() for migrating tasks. If the destination cpu's mm_cid is unset, and if the source runqueue is not actively using its mm_cid, then the source cpu's mm_cid is moved to the destination cpu on migration. Introduce a task-work executed periodically, similarly to NUMA work, which delays reclaim of cid values when they are unused for a period of time. Keep track of the allocation time for each per-cpu cid, and let the task work clear them when they are observed to be older than SCHED_MM_CID_PERIOD_NS and unused. This task work also clears all mm_cids which are greater or equal to the Hamming weight of the mm cidmask to keep concurrency ids compact. Because we want to ensure the mm_cid converges towards the smaller values as migrations happen, the prior optimization that was done when context switching between threads belonging to the same mm is removed, because it could delay the lazy release of the destination runqueue mm_cid after it has been replaced by a migration. Removing this prior optimization is not an issue performance-wise because the introduced per-mm/per-cpu mm_cid tracking also covers this more specific case. Fixes: af7f588d8f73 ("sched: Introduce per-memory-map concurrency ID") Reported-by: Aaron Lu Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Tested-by: Aaron Lu Link: https://lore.kernel.org/lkml/20230327080502.GA570847@ziqianlu-desk2/ --- include/linux/mm_types.h | 82 +++++- include/linux/sched.h | 3 + include/linux/sched/mm.h | 5 + kernel/fork.c | 9 +- kernel/sched/core.c | 523 +++++++++++++++++++++++++++++++++++++-- kernel/sched/sched.h | 239 +++++++++++++++--- 6 files changed, 804 insertions(+), 57 deletions(-) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a57e6ae78e65..5eab61156f0e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -550,6 +550,13 @@ struct vm_area_struct { struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; +#ifdef CONFIG_SCHED_MM_CID +struct mm_cid { + u64 time; + int cid; +}; +#endif + struct kioctx_table; struct mm_struct { struct { @@ -600,15 +607,19 @@ struct mm_struct { atomic_t mm_count; #ifdef CONFIG_SCHED_MM_CID /** - * @cid_lock: Protect cid bitmap updates vs lookups. + * @pcpu_cid: Per-cpu current cid. * - * Prevent situations where updates to the cid bitmap happen - * concurrently with lookups. Those can lead to situations - * where a lookup cannot find a free bit simply because it was - * unlucky enough to load, non-atomically, bitmap words as they - * were being concurrently updated by the updaters. + * Keep track of the currently allocated mm_cid for each cpu. + * The per-cpu mm_cid values are serialized by their respective + * runqueue locks. */ - raw_spinlock_t cid_lock; + struct mm_cid __percpu *pcpu_cid; + /* + * @mm_cid_next_scan: Next mm_cid scan (in jiffies). + * + * When the next mm_cid scan is due (in jiffies). + */ + unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -873,6 +884,37 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID + +enum mm_cid_state { + MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ + MM_CID_LAZY_PUT = (1U << 31), +}; + +static inline bool mm_cid_is_unset(int cid) +{ + return cid == MM_CID_UNSET; +} + +static inline bool mm_cid_is_lazy_put(int cid) +{ + return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); +} + +static inline bool mm_cid_is_valid(int cid) +{ + return !(cid & MM_CID_LAZY_PUT); +} + +static inline int mm_cid_set_lazy_put(int cid) +{ + return cid | MM_CID_LAZY_PUT; +} + +static inline int mm_cid_clear_lazy_put(int cid) +{ + return cid & ~MM_CID_LAZY_PUT; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { @@ -886,16 +928,40 @@ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) static inline void mm_init_cid(struct mm_struct *mm) { - raw_spin_lock_init(&mm->cid_lock); + int i; + + for_each_possible_cpu(i) { + struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); + + pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->time = 0; + } cpumask_clear(mm_cidmask(mm)); } +static inline int mm_alloc_cid(struct mm_struct *mm) +{ + mm->pcpu_cid = alloc_percpu(struct mm_cid); + if (!mm->pcpu_cid) + return -ENOMEM; + mm_init_cid(mm); + return 0; +} + +static inline void mm_destroy_cid(struct mm_struct *mm) +{ + free_percpu(mm->pcpu_cid); + mm->pcpu_cid = NULL; +} + static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } +static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; diff --git a/include/linux/sched.h b/include/linux/sched.h index 6d654eb4cabd..675298d6eb36 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1314,7 +1314,10 @@ struct task_struct { #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ + int last_mm_cid; /* Most recent cid in mm */ + int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ + struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..f20fc0600fcc 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -37,6 +37,11 @@ static inline void mmgrab(struct mm_struct *mm) atomic_inc(&mm->mm_count); } +static inline void smp_mb__after_mmgrab(void) +{ + smp_mb__after_atomic(); +} + extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) diff --git a/kernel/fork.c b/kernel/fork.c index 0c92f224c68c..ad2ee22272a3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -793,6 +793,7 @@ void __mmdrop(struct mm_struct *mm) check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); + mm_destroy_cid(mm); for (i = 0; i < NR_MM_COUNTERS; i++) percpu_counter_destroy(&mm->rss_stat[i]); @@ -1057,7 +1058,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; + tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; + tsk->migrate_from_cpu = -1; #endif return tsk; @@ -1162,18 +1165,22 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, if (init_new_context(p, mm)) goto fail_nocontext; + if (mm_alloc_cid(mm)) + goto fail_cid; + for (i = 0; i < NR_MM_COUNTERS; i++) if (percpu_counter_init(&mm->rss_stat[i], 0, GFP_KERNEL_ACCOUNT)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); - mm_init_cid(mm); return mm; fail_pcpu: while (i > 0) percpu_counter_destroy(&mm->rss_stat[--i]); + mm_destroy_cid(mm); +fail_cid: fail_nocontext: mm_free_pgd(mm); fail_nopgd: diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5a97ceb37c13..898fa3bc2765 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2101,6 +2101,8 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags) { if (task_on_rq_migrating(p)) flags |= ENQUEUE_MIGRATED; + if (flags & ENQUEUE_MIGRATED) + sched_mm_cid_migrate_to(rq, p); enqueue_task(rq, p, flags); @@ -3210,6 +3212,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; rseq_migrate(p); + sched_mm_cid_migrate_from(p); perf_event_task_migrate(p); } @@ -4483,6 +4486,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->wake_entry.u_flags = CSD_TYPE_TTWU; p->migration_pending = NULL; #endif + init_sched_mm_cid(p); } DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); @@ -5129,7 +5133,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, sched_info_switch(rq, prev, next); perf_event_task_sched_out(prev, next); rseq_preempt(prev); - switch_mm_cid(prev, next); fire_sched_out_preempt_notifiers(prev, next); kmap_local_sched_out(); prepare_task(next); @@ -5285,6 +5288,9 @@ context_switch(struct rq *rq, struct task_struct *prev, * * kernel -> user switch + mmdrop() active * user -> user switch + * + * switch_mm_cid() needs to be updated if the barriers provided + * by context_switch() are modified. */ if (!next->mm) { // to kernel enter_lazy_tlb(prev->active_mm, next); @@ -5314,6 +5320,9 @@ context_switch(struct rq *rq, struct task_struct *prev, } } + /* switch_mm_cid() requires the memory barriers above. */ + switch_mm_cid(rq, prev, next); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); prepare_lock_switch(rq, next, rf); @@ -5602,6 +5611,7 @@ void scheduler_tick(void) resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); sched_core_tick(rq); + task_tick_mm_cid(rq, curr); rq_unlock(rq, &rf); @@ -11469,45 +11479,524 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) } #ifdef CONFIG_SCHED_MM_CID -void sched_mm_cid_exit_signals(struct task_struct *t) + +/** + * @cid_lock: Guarantee forward-progress of cid allocation. + * + * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock + * is only used when contention is detected by the lock-free allocation so + * forward progress can be guaranteed. + */ +DEFINE_RAW_SPINLOCK(cid_lock); + +/** + * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock. + * + * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is + * detected, it is set to 1 to ensure that all newly coming allocations are + * serialized by @cid_lock until the allocation which detected contention + * completes and sets @use_cid_lock back to 0. This guarantees forward progress + * of a cid allocation. + */ +int use_cid_lock; + +/* + * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid + * concurrently with respect to the execution of the source runqueue context + * switch. + * + * There is one basic properties we want to guarantee here: + * + * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively + * used by a task. That would lead to concurrent allocation of the cid and + * userspace corruption. + * + * Provide this guarantee by introducing a Dekker memory ordering to guarantee + * that a pair of loads observe at least one of a pair of stores, which can be + * shown as: + * + * X = Y = 0 + * + * w[X]=1 w[Y]=1 + * MB MB + * r[Y]=y r[X]=x + * + * Which guarantees that x==0 && y==0 is impossible. But rather than using + * values 0 and 1, this algorithm cares about specific state transitions of the + * runqueue current task (as updated by the scheduler context switch), and the + * per-mm/cpu cid value. + * + * Let's introduce task (Y) which has task->mm == mm and task (N) which has + * task->mm != mm for the rest of the discussion. There are two scheduler state + * transitions on context switch we care about: + * + * (TSA) Store to rq->curr with transition from (N) to (Y) + * + * (TSB) Store to rq->curr with transition from (Y) to (N) + * + * On the remote-clear side, there is one transition we care about: + * + * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag + * + * There is also a transition to UNSET state which can be performed from all + * sides (scheduler, remote-clear). It is always performed with a cmpxchg which + * guarantees that only a single thread will succeed: + * + * (TMB) cmpxchg to *pcpu_cid to mark UNSET + * + * Just to be clear, what we do _not_ want to happen is a transition to UNSET + * when a thread is actively using the cid (property (1)). + * + * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions. + * + * Scenario A) (TSA)+(TMA) (from next task perspective) + * + * CPU0 CPU1 + * + * Context switch CS-1 Remote-clear + * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA) + * (implied barrier after cmpxchg) + * - switch_mm_cid() + * - memory barrier (see switch_mm_cid() + * comment explaining how this barrier + * is combined with other scheduler + * barriers) + * - mm_cid_get (next) + * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr) + * + * This Dekker ensures that either task (Y) is observed by the + * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are + * observed. + * + * If task (Y) store is observed by rcu_dereference(), it means that there is + * still an active task on the cpu. Remote-clear will therefore not transition + * to UNSET, which fulfills property (1). + * + * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(), + * it will move its state to UNSET, which clears the percpu cid perhaps + * uselessly (which is not an issue for correctness). Because task (Y) is not + * observed, CPU1 can move ahead to set the state to UNSET. Because moving + * state to UNSET is done with a cmpxchg expecting that the old state has the + * LAZY flag set, only one thread will successfully UNSET. + * + * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0 + * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and + * CPU1 will observe task (Y) and do nothing more, which is fine. + * + * What we are effectively preventing with this Dekker is a scenario where + * neither LAZY flag nor store (Y) are observed, which would fail property (1) + * because this would UNSET a cid which is actively used. + */ + +void sched_mm_cid_migrate_from(struct task_struct *t) +{ + t->migrate_from_cpu = task_cpu(t); +} + +static +int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq, + struct task_struct *t, + struct mm_cid *src_pcpu_cid) { struct mm_struct *mm = t->mm; - unsigned long flags; + struct task_struct *src_task; + int src_cid, last_mm_cid; if (!mm) + return -1; + + last_mm_cid = t->last_mm_cid; + /* + * If the migrated task has no last cid, or if the current + * task on src rq uses the cid, it means the source cid does not need + * to be moved to the destination cpu. + */ + if (last_mm_cid == -1) + return -1; + src_cid = READ_ONCE(src_pcpu_cid->cid); + if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid) + return -1; + + /* + * If we observe an active task using the mm on this rq, it means we + * are not the last task to be migrated from this cpu for this mm, so + * there is no need to move src_cid to the destination cpu. + */ + rcu_read_lock(); + src_task = rcu_dereference(src_rq->curr); + if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) { + rcu_read_unlock(); + t->last_mm_cid = -1; + return -1; + } + rcu_read_unlock(); + + return src_cid; +} + +static +int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq, + struct task_struct *t, + struct mm_cid *src_pcpu_cid, + int src_cid) +{ + struct task_struct *src_task; + struct mm_struct *mm = t->mm; + int lazy_cid; + + if (src_cid == -1) + return -1; + + /* + * Attempt to clear the source cpu cid to move it to the destination + * cpu. + */ + lazy_cid = mm_cid_set_lazy_put(src_cid); + if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid)) + return -1; + + /* + * The implicit barrier after cmpxchg per-mm/cpu cid before loading + * rq->curr->mm matches the scheduler barrier in context_switch() + * between store to rq->curr and load of prev and next task's + * per-mm/cpu cid. + * + * The implicit barrier after cmpxchg per-mm/cpu cid before loading + * rq->curr->mm_cid_active matches the barrier in + * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and + * sched_mm_cid_after_execve() between store to t->mm_cid_active and + * load of per-mm/cpu cid. + */ + + /* + * If we observe an active task using the mm on this rq after setting + * the lazy-put flag, this task will be responsible for transitioning + * from lazy-put flag set to MM_CID_UNSET. + */ + rcu_read_lock(); + src_task = rcu_dereference(src_rq->curr); + if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) { + rcu_read_unlock(); + /* + * We observed an active task for this mm, there is therefore + * no point in moving this cid to the destination cpu. + */ + t->last_mm_cid = -1; + return -1; + } + rcu_read_unlock(); + + /* + * The src_cid is unused, so it can be unset. + */ + if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET)) + return -1; + return src_cid; +} + +/* + * Migration to dst cpu. Called with dst_rq lock held. + * Interrupts are disabled, which keeps the window of cid ownership without the + * source rq lock held small. + */ +void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t) +{ + struct mm_cid *src_pcpu_cid, *dst_pcpu_cid; + struct mm_struct *mm = t->mm; + int src_cid, dst_cid, src_cpu; + struct rq *src_rq; + + lockdep_assert_rq_held(dst_rq); + + if (!mm) + return; + src_cpu = t->migrate_from_cpu; + if (src_cpu == -1) { + t->last_mm_cid = -1; + return; + } + /* + * Move the src cid if the dst cid is unset. This keeps id + * allocation closest to 0 in cases where few threads migrate around + * many cpus. + * + * If destination cid is already set, we may have to just clear + * the src cid to ensure compactness in frequent migrations + * scenarios. + * + * It is not useful to clear the src cid when the number of threads is + * greater or equal to the number of allowed cpus, because user-space + * can expect that the number of allowed cids can reach the number of + * allowed cpus. + */ + dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq)); + dst_cid = READ_ONCE(dst_pcpu_cid->cid); + if (!mm_cid_is_unset(dst_cid) && + atomic_read(&mm->mm_users) >= t->nr_cpus_allowed) + return; + src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu); + src_rq = cpu_rq(src_cpu); + src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid); + if (src_cid == -1) + return; + src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid, + src_cid); + if (src_cid == -1) + return; + if (!mm_cid_is_unset(dst_cid)) { + __mm_cid_put(mm, src_cid); + return; + } + /* Move src_cid to dst cpu. */ + mm_cid_snapshot_time(dst_rq, mm); + WRITE_ONCE(dst_pcpu_cid->cid, src_cid); +} + +static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid, + int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct task_struct *t; + unsigned long flags; + int cid, lazy_cid; + + cid = READ_ONCE(pcpu_cid->cid); + if (!mm_cid_is_valid(cid)) return; + + /* + * Clear the cpu cid if it is set to keep cid allocation compact. If + * there happens to be other tasks left on the source cpu using this + * mm, the next task using this mm will reallocate its cid on context + * switch. + */ + lazy_cid = mm_cid_set_lazy_put(cid); + if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid)) + return; + + /* + * The implicit barrier after cmpxchg per-mm/cpu cid before loading + * rq->curr->mm matches the scheduler barrier in context_switch() + * between store to rq->curr and load of prev and next task's + * per-mm/cpu cid. + * + * The implicit barrier after cmpxchg per-mm/cpu cid before loading + * rq->curr->mm_cid_active matches the barrier in + * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and + * sched_mm_cid_after_execve() between store to t->mm_cid_active and + * load of per-mm/cpu cid. + */ + + /* + * If we observe an active task using the mm on this rq after setting + * the lazy-put flag, that task will be responsible for transitioning + * from lazy-put flag set to MM_CID_UNSET. + */ + rcu_read_lock(); + t = rcu_dereference(rq->curr); + if (READ_ONCE(t->mm_cid_active) && t->mm == mm) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + /* + * The cid is unused, so it can be unset. + * Disable interrupts to keep the window of cid ownership without rq + * lock small. + */ local_irq_save(flags); - mm_cid_put(mm, t->mm_cid); - t->mm_cid = -1; - t->mm_cid_active = 0; + if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET)) + __mm_cid_put(mm, cid); local_irq_restore(flags); } +static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct mm_cid *pcpu_cid; + struct task_struct *curr; + u64 rq_clock; + + /* + * rq->clock load is racy on 32-bit but one spurious clear once in a + * while is irrelevant. + */ + rq_clock = READ_ONCE(rq->clock); + pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu); + + /* + * In order to take care of infrequently scheduled tasks, bump the time + * snapshot associated with this cid if an active task using the mm is + * observed on this rq. + */ + rcu_read_lock(); + curr = rcu_dereference(rq->curr); + if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) { + WRITE_ONCE(pcpu_cid->time, rq_clock); + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS) + return; + sched_mm_cid_remote_clear(mm, pcpu_cid, cpu); +} + +static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu, + int weight) +{ + struct mm_cid *pcpu_cid; + int cid; + + pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu); + cid = READ_ONCE(pcpu_cid->cid); + if (!mm_cid_is_valid(cid) || cid < weight) + return; + sched_mm_cid_remote_clear(mm, pcpu_cid, cpu); +} + +static void task_mm_cid_work(struct callback_head *work) +{ + unsigned long now = jiffies, old_scan, next_scan; + struct task_struct *t = current; + struct cpumask *cidmask; + struct mm_struct *mm; + int weight, cpu; + + SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work)); + + work->next = work; /* Prevent double-add */ + if (t->flags & PF_EXITING) + return; + mm = t->mm; + if (!mm) + return; + old_scan = READ_ONCE(mm->mm_cid_next_scan); + next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY); + if (!old_scan) { + unsigned long res; + + res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan); + if (res != old_scan) + old_scan = res; + else + old_scan = next_scan; + } + if (time_before(now, old_scan)) + return; + if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan)) + return; + cidmask = mm_cidmask(mm); + /* Clear cids that were not recently used. */ + for_each_possible_cpu(cpu) + sched_mm_cid_remote_clear_old(mm, cpu); + weight = cpumask_weight(cidmask); + /* + * Clear cids that are greater or equal to the cidmask weight to + * recompact it. + */ + for_each_possible_cpu(cpu) + sched_mm_cid_remote_clear_weight(mm, cpu, weight); +} + +void init_sched_mm_cid(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + int mm_users = 0; + + if (mm) { + mm_users = atomic_read(&mm->mm_users); + if (mm_users == 1) + mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY); + } + t->cid_work.next = &t->cid_work; /* Protect against double add */ + init_task_work(&t->cid_work, task_mm_cid_work); +} + +void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->cid_work; + unsigned long now = jiffies; + + if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) || + work->next != work) + return; + if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan))) + return; + task_work_add(curr, work, TWA_RESUME); +} + +void sched_mm_cid_exit_signals(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + struct rq_flags rf; + struct rq *rq; + + if (!mm) + return; + + preempt_disable(); + rq = this_rq(); + rq_lock_irqsave(rq, &rf); + preempt_enable_no_resched(); /* holding spinlock */ + WRITE_ONCE(t->mm_cid_active, 0); + /* + * Store t->mm_cid_active before loading per-mm/cpu cid. + * Matches barrier in sched_mm_cid_remote_clear_old(). + */ + smp_mb(); + mm_cid_put(mm); + t->last_mm_cid = t->mm_cid = -1; + rq_unlock_irqrestore(rq, &rf); +} + void sched_mm_cid_before_execve(struct task_struct *t) { struct mm_struct *mm = t->mm; - unsigned long flags; + struct rq_flags rf; + struct rq *rq; if (!mm) return; - local_irq_save(flags); - mm_cid_put(mm, t->mm_cid); - t->mm_cid = -1; - t->mm_cid_active = 0; - local_irq_restore(flags); + + preempt_disable(); + rq = this_rq(); + rq_lock_irqsave(rq, &rf); + preempt_enable_no_resched(); /* holding spinlock */ + WRITE_ONCE(t->mm_cid_active, 0); + /* + * Store t->mm_cid_active before loading per-mm/cpu cid. + * Matches barrier in sched_mm_cid_remote_clear_old(). + */ + smp_mb(); + mm_cid_put(mm); + t->last_mm_cid = t->mm_cid = -1; + rq_unlock_irqrestore(rq, &rf); } void sched_mm_cid_after_execve(struct task_struct *t) { struct mm_struct *mm = t->mm; - unsigned long flags; + struct rq_flags rf; + struct rq *rq; if (!mm) return; - local_irq_save(flags); - t->mm_cid = mm_cid_get(mm); - t->mm_cid_active = 1; - local_irq_restore(flags); + + preempt_disable(); + rq = this_rq(); + rq_lock_irqsave(rq, &rf); + preempt_enable_no_resched(); /* holding spinlock */ + WRITE_ONCE(t->mm_cid_active, 1); + /* + * Store t->mm_cid_active before loading per-mm/cpu cid. + * Matches barrier in sched_mm_cid_remote_clear_old(). + */ + smp_mb(); + t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm); + rq_unlock_irqrestore(rq, &rf); rseq_set_notify_resume(t); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 060616944d7a..ec7b3e0a2b20 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3253,61 +3253,238 @@ static inline void update_current_exec_runtime(struct task_struct *curr, } #ifdef CONFIG_SCHED_MM_CID -static inline int __mm_cid_get(struct mm_struct *mm) + +#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */ +#define MM_CID_SCAN_DELAY 100 /* 100ms */ + +extern raw_spinlock_t cid_lock; +extern int use_cid_lock; + +extern void sched_mm_cid_migrate_from(struct task_struct *t); +extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t); +extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr); +extern void init_sched_mm_cid(struct task_struct *t); + +static inline void __mm_cid_put(struct mm_struct *mm, int cid) +{ + if (cid < 0) + return; + cpumask_clear_cpu(cid, mm_cidmask(mm)); +} + +/* + * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to + * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to + * be held to transition to other states. + * + * State transitions synchronized with cmpxchg or try_cmpxchg need to be + * consistent across cpus, which prevents use of this_cpu_cmpxchg. + */ +static inline void mm_cid_put_lazy(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; + int cid; + + lockdep_assert_irqs_disabled(); + cid = __this_cpu_read(pcpu_cid->cid); + if (!mm_cid_is_lazy_put(cid) || + !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET)) + return; + __mm_cid_put(mm, mm_cid_clear_lazy_put(cid)); +} + +static inline int mm_cid_pcpu_unset(struct mm_struct *mm) +{ + struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; + int cid, res; + + lockdep_assert_irqs_disabled(); + cid = __this_cpu_read(pcpu_cid->cid); + for (;;) { + if (mm_cid_is_unset(cid)) + return MM_CID_UNSET; + /* + * Attempt transition from valid or lazy-put to unset. + */ + res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET); + if (res == cid) + break; + cid = res; + } + return cid; +} + +static inline void mm_cid_put(struct mm_struct *mm) +{ + int cid; + + lockdep_assert_irqs_disabled(); + cid = mm_cid_pcpu_unset(mm); + if (cid == MM_CID_UNSET) + return; + __mm_cid_put(mm, mm_cid_clear_lazy_put(cid)); +} + +static inline int __mm_cid_try_get(struct mm_struct *mm) { struct cpumask *cpumask; int cid; cpumask = mm_cidmask(mm); - cid = cpumask_first_zero(cpumask); - if (cid >= nr_cpu_ids) + /* + * Retry finding first zero bit if the mask is temporarily + * filled. This only happens during concurrent remote-clear + * which owns a cid without holding a rq lock. + */ + for (;;) { + cid = cpumask_first_zero(cpumask); + if (cid < nr_cpu_ids) + break; + cpu_relax(); + } + if (cpumask_test_and_set_cpu(cid, cpumask)) return -1; - __cpumask_set_cpu(cid, cpumask); return cid; } -static inline void mm_cid_put(struct mm_struct *mm, int cid) +/* + * Save a snapshot of the current runqueue time of this cpu + * with the per-cpu cid value, allowing to estimate how recently it was used. + */ +static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm) { - lockdep_assert_irqs_disabled(); - if (cid < 0) - return; - raw_spin_lock(&mm->cid_lock); - __cpumask_clear_cpu(cid, mm_cidmask(mm)); - raw_spin_unlock(&mm->cid_lock); + struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq)); + + lockdep_assert_rq_held(rq); + WRITE_ONCE(pcpu_cid->time, rq->clock); } -static inline int mm_cid_get(struct mm_struct *mm) +static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm) { - int ret; + int cid; - lockdep_assert_irqs_disabled(); - raw_spin_lock(&mm->cid_lock); - ret = __mm_cid_get(mm); - raw_spin_unlock(&mm->cid_lock); - return ret; + /* + * All allocations (even those using the cid_lock) are lock-free. If + * use_cid_lock is set, hold the cid_lock to perform cid allocation to + * guarantee forward progress. + */ + if (!READ_ONCE(use_cid_lock)) { + cid = __mm_cid_try_get(mm); + if (cid >= 0) + goto end; + raw_spin_lock(&cid_lock); + } else { + raw_spin_lock(&cid_lock); + cid = __mm_cid_try_get(mm); + if (cid >= 0) + goto unlock; + } + + /* + * cid concurrently allocated. Retry while forcing following + * allocations to use the cid_lock to ensure forward progress. + */ + WRITE_ONCE(use_cid_lock, 1); + /* + * Set use_cid_lock before allocation. Only care about program order + * because this is only required for forward progress. + */ + barrier(); + /* + * Retry until it succeeds. It is guaranteed to eventually succeed once + * all newcoming allocations observe the use_cid_lock flag set. + */ + do { + cid = __mm_cid_try_get(mm); + cpu_relax(); + } while (cid < 0); + /* + * Allocate before clearing use_cid_lock. Only care about + * program order because this is for forward progress. + */ + barrier(); + WRITE_ONCE(use_cid_lock, 0); +unlock: + raw_spin_unlock(&cid_lock); +end: + mm_cid_snapshot_time(rq, mm); + return cid; } -static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) +static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm) { + struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; + struct cpumask *cpumask; + int cid; + + lockdep_assert_rq_held(rq); + cpumask = mm_cidmask(mm); + cid = __this_cpu_read(pcpu_cid->cid); + if (mm_cid_is_valid(cid)) { + mm_cid_snapshot_time(rq, mm); + return cid; + } + if (mm_cid_is_lazy_put(cid)) { + if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET)) + __mm_cid_put(mm, mm_cid_clear_lazy_put(cid)); + } + cid = __mm_cid_get(rq, mm); + __this_cpu_write(pcpu_cid->cid, cid); + return cid; +} + +static inline void switch_mm_cid(struct rq *rq, + struct task_struct *prev, + struct task_struct *next) +{ + /* + * Provide a memory barrier between rq->curr store and load of + * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition. + * + * Should be adapted if context_switch() is modified. + */ + if (!next->mm) { // to kernel + /* + * user -> kernel transition does not guarantee a barrier, but + * we can use the fact that it performs an atomic operation in + * mmgrab(). + */ + if (prev->mm) // from user + smp_mb__after_mmgrab(); + /* + * kernel -> kernel transition does not change rq->curr->mm + * state. It stays NULL. + */ + } else { // to user + /* + * kernel -> user transition does not provide a barrier + * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu]. + * Provide it here. + */ + if (!prev->mm) // from kernel + smp_mb(); + /* + * user -> user transition guarantees a memory barrier through + * switch_mm() when current->mm changes. If current->mm is + * unchanged, no barrier is needed. + */ + } if (prev->mm_cid_active) { - if (next->mm_cid_active && next->mm == prev->mm) { - /* - * Context switch between threads in same mm, hand over - * the mm_cid from prev to next. - */ - next->mm_cid = prev->mm_cid; - prev->mm_cid = -1; - return; - } - mm_cid_put(prev->mm, prev->mm_cid); + mm_cid_snapshot_time(rq, prev->mm); + mm_cid_put_lazy(prev); prev->mm_cid = -1; } if (next->mm_cid_active) - next->mm_cid = mm_cid_get(next->mm); + next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm); } #else -static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) { } +static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { } +static inline void sched_mm_cid_migrate_from(struct task_struct *t) { } +static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t) { } +static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { } +static inline void init_sched_mm_cid(struct task_struct *t) { } #endif #endif /* _KERNEL_SCHED_SCHED_H */ -- GitLab From feffe5bb274dd3442080ef0e4053746091878799 Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Mon, 29 Aug 2022 01:03:02 +0800 Subject: [PATCH 3740/5631] sched/rt: Fix bad task migration for rt tasks Commit 95158a89dd50 ("sched,rt: Use the full cpumask for balancing") allows find_lock_lowest_rq() to pick a task with migration disabled. The purpose of the commit is to push the current running task on the CPU that has the migrate_disable() task away. However, there is a race which allows a migrate_disable() task to be migrated. Consider: CPU0 CPU1 push_rt_task check is_migration_disabled(next_task) task not running and migration_disabled == 0 find_lock_lowest_rq(next_task, rq); _double_lock_balance(this_rq, busiest); raw_spin_rq_unlock(this_rq); double_rq_lock(this_rq, busiest); <> task become running migrate_disable(); deactivate_task(rq, next_task, 0); set_task_cpu(next_task, lowest_rq->cpu); WARN_ON_ONCE(is_migration_disabled(p)); Fixes: 95158a89dd50 ("sched,rt: Use the full cpumask for balancing") Signed-off-by: Schspa Shi Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Reviewed-by: Dietmar Eggemann Reviewed-by: Valentin Schneider Tested-by: Dwaine Gonyier --- kernel/sched/deadline.c | 1 + kernel/sched/rt.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 4cc7e1ca066d..5a9a4b81c972 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2246,6 +2246,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) || task_on_cpu(rq, task) || !dl_task(task) || + is_migration_disabled(task) || !task_on_rq_queued(task))) { double_unlock_balance(rq, later_rq); later_rq = NULL; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 9d67dfbf1000..00e0e5074115 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2000,11 +2000,15 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * the mean time, task could have * migrated already or had its affinity changed. * Also make sure that it wasn't scheduled on its rq. + * It is possible the task was scheduled, set + * "migrate_disabled" and then got preempted, so we must + * check the task migration disable flag here too. */ if (unlikely(task_rq(task) != rq || !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) || task_on_cpu(rq, task) || !rt_task(task) || + is_migration_disabled(task) || !task_on_rq_queued(task))) { double_unlock_balance(rq, lowest_rq); -- GitLab From f31dcb152a3d0816e2f1deab4e64572336da197d Mon Sep 17 00:00:00 2001 From: Aaron Thompson Date: Thu, 13 Apr 2023 17:50:12 +0000 Subject: [PATCH 3741/5631] sched/clock: Fix local_clock() before sched_clock_init() Have local_clock() return sched_clock() if sched_clock_init() has not yet run. sched_clock_cpu() has this check but it was not included in the new noinstr implementation of local_clock(). The effect can be seen on x86 with CONFIG_PRINTK_TIME enabled, for instance. scd->clock quickly reaches the value of TICK_NSEC and that value is returned until sched_clock_init() runs. dmesg without this patch: [ 0.000000] kvm-clock: ... [ 0.000002] kvm-clock: ... [ 0.000672] clocksource: ... [ 0.001000] tsc: ... [ 0.001000] e820: ... [ 0.001000] e820: ... ... [ 0.001000] ..TIMER: ... [ 0.001000] clocksource: ... [ 0.378956] Calibrating delay loop ... [ 0.379955] pid_max: ... dmesg with this patch: [ 0.000000] kvm-clock: ... [ 0.000001] kvm-clock: ... [ 0.000675] clocksource: ... [ 0.002685] tsc: ... [ 0.003331] e820: ... [ 0.004190] e820: ... ... [ 0.421939] ..TIMER: ... [ 0.422842] clocksource: ... [ 0.424582] Calibrating delay loop ... [ 0.425580] pid_max: ... Fixes: 776f22913b8e ("sched/clock: Make local_clock() noinstr") Signed-off-by: Aaron Thompson Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230413175012.2201-1-dev@aaront.org --- kernel/sched/clock.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 5732fa75ebab..b5cc2b53464d 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -300,6 +300,9 @@ noinstr u64 local_clock(void) if (static_branch_likely(&__sched_clock_stable)) return sched_clock() + __sched_clock_offset; + if (!static_branch_likely(&sched_clock_running)) + return sched_clock(); + preempt_disable_notrace(); clock = sched_clock_local(this_scd()); preempt_enable_notrace(); -- GitLab From 743767d6f6b8f28228be181fe369657f7ecd1eb2 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 19 Apr 2023 14:42:41 -0700 Subject: [PATCH 3742/5631] perf/x86/intel/uncore: Add events for Intel SPR IMC PMU Add missing clockticks and cas_count_* events for Intel SapphireRapids IMC PMU. These events are useful to measure memory bandwidth. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Kan Liang Link: https://lore.kernel.org/r/20230419214241.2310385-1-eranian@google.com --- arch/x86/events/intel/uncore_snbep.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 7d1199554fe3..fa9b209a11fa 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6068,6 +6068,17 @@ static struct intel_uncore_ops spr_uncore_mmio_ops = { .read_counter = uncore_mmio_read_counter, }; +static struct uncore_event_desc spr_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x01,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x05,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x05,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"), + { /* end: all zeroes */ }, +}; + static struct intel_uncore_type spr_uncore_imc = { SPR_UNCORE_COMMON_FORMAT(), .name = "imc", @@ -6075,6 +6086,7 @@ static struct intel_uncore_type spr_uncore_imc = { .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, .ops = &spr_uncore_mmio_ops, + .event_descs = spr_uncore_imc_events, }; static void spr_uncore_pci_enable_event(struct intel_uncore_box *box, -- GitLab From 2ed90cb0938a45b12eb947af062d12c7af0067b3 Mon Sep 17 00:00:00 2001 From: David Matlack Date: Fri, 17 Mar 2023 14:11:06 -0700 Subject: [PATCH 3743/5631] KVM: RISC-V: Retry fault if vma_lookup() results become invalid Read mmu_invalidate_seq before dropping the mmap_lock so that KVM can detect if the results of vma_lookup() (e.g. vma_shift) become stale before it acquires kvm->mmu_lock. This fixes a theoretical bug where a VMA could be changed by userspace after vma_lookup() and before KVM reads the mmu_invalidate_seq, causing KVM to install page table entries based on a (possibly) no-longer-valid vma_shift. Re-order the MMU cache top-up to earlier in user_mem_abort() so that it is not done after KVM has read mmu_invalidate_seq (i.e. so as to avoid inducing spurious fault retries). It's unlikely that any sane userspace currently modifies VMAs in such a way as to trigger this race. And even with directed testing I was unable to reproduce it. But a sufficiently motivated host userspace might be able to exploit this race. Note KVM/ARM had the same bug and was fixed in a separate, near identical patch (see Link). Link: https://lore.kernel.org/kvm/20230313235454.2964067-1-dmatlack@google.com/ Fixes: 9955371cc014 ("RISC-V: KVM: Implement MMU notifiers") Cc: stable@vger.kernel.org Signed-off-by: David Matlack Tested-by: Anup Patel Signed-off-by: Anup Patel --- arch/riscv/kvm/mmu.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 78211aed36fa..46d692995830 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -628,6 +628,13 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, !(memslot->flags & KVM_MEM_READONLY)) ? true : false; unsigned long vma_pagesize, mmu_seq; + /* We need minimum second+third level pages */ + ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels); + if (ret) { + kvm_err("Failed to topup G-stage cache\n"); + return ret; + } + mmap_read_lock(current->mm); vma = vma_lookup(current->mm, hva); @@ -648,6 +655,15 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; + /* + * Read mmu_invalidate_seq so that KVM can detect if the results of + * vma_lookup() or gfn_to_pfn_prot() become stale priort to acquiring + * kvm->mmu_lock. + * + * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs + * with the smp_wmb() in kvm_mmu_invalidate_end(). + */ + mmu_seq = kvm->mmu_invalidate_seq; mmap_read_unlock(current->mm); if (vma_pagesize != PUD_SIZE && @@ -657,15 +673,6 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, return -EFAULT; } - /* We need minimum second+third level pages */ - ret = kvm_mmu_topup_memory_cache(pcache, gstage_pgd_levels); - if (ret) { - kvm_err("Failed to topup G-stage cache\n"); - return ret; - } - - mmu_seq = kvm->mmu_invalidate_seq; - hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable); if (hfn == KVM_PFN_ERR_HWPOISON) { send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, -- GitLab From c69daf8bf88c09271a55c65140c8af8fcd565c09 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 22 Mar 2023 20:28:57 +0100 Subject: [PATCH 3744/5631] RISC-V: KVM: Alphabetize selects While alphabetized lists tend to become unalphabetized almost as quickly as they get fixed up, it is preferred to keep select lists in Kconfigs in order. Let's fix KVM's up. Signed-off-by: Andrew Jones Reviewed-by: Anup Patel Signed-off-by: Anup Patel --- arch/riscv/kvm/Kconfig | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index d5a658a047a7..5bcb2d519b95 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -20,14 +20,14 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" depends on RISCV_SBI && MMU + select HAVE_KVM_EVENTFD + select HAVE_KVM_VCPU_ASYNC_IOCTL + select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_GENERIC_HARDWARE_ENABLING - select MMU_NOTIFIER - select PREEMPT_NOTIFIERS select KVM_MMIO - select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_XFER_TO_GUEST_WORK - select HAVE_KVM_VCPU_ASYNC_IOCTL - select HAVE_KVM_EVENTFD + select MMU_NOTIFIER + select PREEMPT_NOTIFIERS select SRCU help Support hosting virtualized guest machines. -- GitLab From 96b3d4bd93f913440b4cb06233a1ecbc4dd41dad Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 28 Nov 2022 11:43:16 +0530 Subject: [PATCH 3745/5631] RISC-V: KVM: Add ONE_REG interface to enable/disable SBI extensions We add ONE_REG interface to enable/disable SBI extensions (just like the ONE_REG interface for ISA extensions). This allows KVM user-space to decide the set of SBI extension enabled for a Guest and by default all SBI extensions are enabled. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_vcpu_sbi.h | 8 +- arch/riscv/include/uapi/asm/kvm.h | 32 ++++ arch/riscv/kvm/vcpu.c | 4 + arch/riscv/kvm/vcpu_sbi.c | 247 ++++++++++++++++++++++++-- arch/riscv/kvm/vcpu_sbi_base.c | 2 +- 5 files changed, 274 insertions(+), 19 deletions(-) diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index 8425556af7d1..4278125a38a5 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -16,6 +16,7 @@ struct kvm_vcpu_sbi_context { int return_handled; + bool extension_disabled[KVM_RISCV_SBI_EXT_MAX]; }; struct kvm_vcpu_sbi_return { @@ -45,7 +46,12 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type, u64 flags); int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); -const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid); +int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext( + struct kvm_vcpu *vcpu, unsigned long extid); int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); #ifdef CONFIG_RISCV_SBI_V01 diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 92af6f3f057c..d8ead5952ed9 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -12,6 +12,7 @@ #ifndef __ASSEMBLY__ #include +#include #include #define __KVM_HAVE_READONLY_MEM @@ -108,6 +109,23 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_MAX, }; +/* + * SBI extension IDs specific to KVM. This is not the same as the SBI + * extension IDs defined by the RISC-V SBI specification. + */ +enum KVM_RISCV_SBI_EXT_ID { + KVM_RISCV_SBI_EXT_V01 = 0, + KVM_RISCV_SBI_EXT_TIME, + KVM_RISCV_SBI_EXT_IPI, + KVM_RISCV_SBI_EXT_RFENCE, + KVM_RISCV_SBI_EXT_SRST, + KVM_RISCV_SBI_EXT_HSM, + KVM_RISCV_SBI_EXT_PMU, + KVM_RISCV_SBI_EXT_EXPERIMENTAL, + KVM_RISCV_SBI_EXT_VENDOR, + KVM_RISCV_SBI_EXT_MAX, +}; + /* Possible states for kvm_riscv_timer */ #define KVM_RISCV_TIMER_STATE_OFF 0 #define KVM_RISCV_TIMER_STATE_ON 1 @@ -118,6 +136,8 @@ enum KVM_RISCV_ISA_EXT_ID { /* If you need to interpret the index values, here is the key: */ #define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000 #define KVM_REG_RISCV_TYPE_SHIFT 24 +#define KVM_REG_RISCV_SUBTYPE_MASK 0x0000000000FF0000 +#define KVM_REG_RISCV_SUBTYPE_SHIFT 16 /* Config registers are mapped as type 1 */ #define KVM_REG_RISCV_CONFIG (0x01 << KVM_REG_RISCV_TYPE_SHIFT) @@ -152,6 +172,18 @@ enum KVM_RISCV_ISA_EXT_ID { /* ISA Extension registers are mapped as type 7 */ #define KVM_REG_RISCV_ISA_EXT (0x07 << KVM_REG_RISCV_TYPE_SHIFT) +/* SBI extension registers are mapped as type 8 */ +#define KVM_REG_RISCV_SBI_EXT (0x08 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_SBI_SINGLE (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_EN (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_DIS (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_REG(__ext_id) \ + ((__ext_id) / __BITS_PER_LONG) +#define KVM_REG_RISCV_SBI_MULTI_MASK(__ext_id) \ + (1UL << ((__ext_id) % __BITS_PER_LONG)) +#define KVM_REG_RISCV_SBI_MULTI_REG_LAST \ + KVM_REG_RISCV_SBI_MULTI_REG(KVM_RISCV_SBI_EXT_MAX - 1) + #endif #endif /* __LINUX_KVM_RISCV_H */ diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7d010b0be54e..3112697cb12d 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -601,6 +601,8 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, KVM_REG_RISCV_FP_D); case KVM_REG_RISCV_ISA_EXT: return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_EXT: + return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg); default: break; } @@ -628,6 +630,8 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu, KVM_REG_RISCV_FP_D); case KVM_REG_RISCV_ISA_EXT: return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_EXT: + return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg); default: break; } diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 15fde15f9fb8..e52fde504433 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -30,17 +30,52 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { }; #endif -static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { - &vcpu_sbi_ext_v01, - &vcpu_sbi_ext_base, - &vcpu_sbi_ext_time, - &vcpu_sbi_ext_ipi, - &vcpu_sbi_ext_rfence, - &vcpu_sbi_ext_srst, - &vcpu_sbi_ext_hsm, - &vcpu_sbi_ext_pmu, - &vcpu_sbi_ext_experimental, - &vcpu_sbi_ext_vendor, +struct kvm_riscv_sbi_extension_entry { + enum KVM_RISCV_SBI_EXT_ID dis_idx; + const struct kvm_vcpu_sbi_extension *ext_ptr; +}; + +static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = { + { + .dis_idx = KVM_RISCV_SBI_EXT_V01, + .ext_ptr = &vcpu_sbi_ext_v01, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_MAX, /* Can't be disabled */ + .ext_ptr = &vcpu_sbi_ext_base, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_TIME, + .ext_ptr = &vcpu_sbi_ext_time, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_IPI, + .ext_ptr = &vcpu_sbi_ext_ipi, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_RFENCE, + .ext_ptr = &vcpu_sbi_ext_rfence, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_SRST, + .ext_ptr = &vcpu_sbi_ext_srst, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_HSM, + .ext_ptr = &vcpu_sbi_ext_hsm, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_PMU, + .ext_ptr = &vcpu_sbi_ext_pmu, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_EXPERIMENTAL, + .ext_ptr = &vcpu_sbi_ext_experimental, + }, + { + .dis_idx = KVM_RISCV_SBI_EXT_VENDOR, + .ext_ptr = &vcpu_sbi_ext_vendor, + }, }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) @@ -99,14 +134,192 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext(unsigned long extid) +static int riscv_vcpu_set_sbi_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + unsigned long i; + const struct kvm_riscv_sbi_extension_entry *sext = NULL; + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + + if (reg_num >= KVM_RISCV_SBI_EXT_MAX || + (reg_val != 1 && reg_val != 0)) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + if (sbi_ext[i].dis_idx == reg_num) { + sext = &sbi_ext[i]; + break; + } + } + if (!sext) + return -ENOENT; + + scontext->extension_disabled[sext->dis_idx] = !reg_val; + + return 0; +} + +static int riscv_vcpu_get_sbi_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + unsigned long i; + const struct kvm_riscv_sbi_extension_entry *sext = NULL; + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + + if (reg_num >= KVM_RISCV_SBI_EXT_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + if (sbi_ext[i].dis_idx == reg_num) { + sext = &sbi_ext[i]; + break; + } + } + if (!sext) + return -ENOENT; + + *reg_val = !scontext->extension_disabled[sext->dis_idx]; + + return 0; +} + +static int riscv_vcpu_set_sbi_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val, bool enable) +{ + unsigned long i, ext_id; + + if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST) + return -EINVAL; + + for_each_set_bit(i, ®_val, BITS_PER_LONG) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_SBI_EXT_MAX) + break; + + riscv_vcpu_set_sbi_ext_single(vcpu, ext_id, enable); + } + + return 0; +} + +static int riscv_vcpu_get_sbi_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + unsigned long i, ext_id, ext_val; + + if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST) + return -EINVAL; + + for (i = 0; i < BITS_PER_LONG; i++) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_SBI_EXT_MAX) + break; + + ext_val = 0; + riscv_vcpu_get_sbi_ext_single(vcpu, ext_id, &ext_val); + if (ext_val) + *reg_val |= KVM_REG_RISCV_SBI_MULTI_MASK(ext_id); + } + + return 0; +} + +int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (vcpu->arch.ran_atleast_once) + return -EBUSY; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_SINGLE: + return riscv_vcpu_set_sbi_ext_single(vcpu, reg_num, reg_val); + case KVM_REG_RISCV_SBI_MULTI_EN: + return riscv_vcpu_set_sbi_ext_multi(vcpu, reg_num, reg_val, true); + case KVM_REG_RISCV_SBI_MULTI_DIS: + return riscv_vcpu_set_sbi_ext_multi(vcpu, reg_num, reg_val, false); + default: + return -EINVAL; + } + + return 0; +} + +int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + int rc; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + reg_val = 0; + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_SINGLE: + rc = riscv_vcpu_get_sbi_ext_single(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_SBI_MULTI_EN: + case KVM_REG_RISCV_SBI_MULTI_DIS: + rc = riscv_vcpu_get_sbi_ext_multi(vcpu, reg_num, ®_val); + if (!rc && reg_subtype == KVM_REG_RISCV_SBI_MULTI_DIS) + reg_val = ~reg_val; + break; + default: + rc = -EINVAL; + } + if (rc) + return rc; + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext( + struct kvm_vcpu *vcpu, unsigned long extid) { - int i = 0; + int i; + const struct kvm_riscv_sbi_extension_entry *sext; + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { - if (sbi_ext[i]->extid_start <= extid && - sbi_ext[i]->extid_end >= extid) - return sbi_ext[i]; + sext = &sbi_ext[i]; + if (sext->ext_ptr->extid_start <= extid && + sext->ext_ptr->extid_end >= extid) { + if (sext->dis_idx < KVM_RISCV_SBI_EXT_MAX && + scontext->extension_disabled[sext->dis_idx]) + return NULL; + return sbi_ext[i].ext_ptr; + } } return NULL; @@ -126,7 +339,7 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) }; bool ext_is_v01 = false; - sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); + sbi_ext = kvm_vcpu_sbi_find_ext(vcpu, cp->a7); if (sbi_ext && sbi_ext->handler) { #ifdef CONFIG_RISCV_SBI_V01 if (cp->a7 >= SBI_EXT_0_1_SET_TIMER && diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 9945aff34c14..5bc570b984f4 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -44,7 +44,7 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, kvm_riscv_vcpu_sbi_forward(vcpu, run); retdata->uexit = true; } else { - sbi_ext = kvm_vcpu_sbi_find_ext(cp->a0); + sbi_ext = kvm_vcpu_sbi_find_ext(vcpu, cp->a0); *out_val = sbi_ext && sbi_ext->probe ? sbi_ext->probe(vcpu) : !!sbi_ext; } -- GitLab From 90deec51d726b4d829ca7a684595154bebdf8353 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Sat, 1 Apr 2023 15:21:34 +0530 Subject: [PATCH 3746/5631] RISC-V: KVM: Allow Zbb extension for Guest/VM We extend the KVM ISA extension ONE_REG interface to allow KVM user space to detect and enable Zbb extension for Guest/VM. Signed-off-by: Anup Patel Reviewed-by: Atish Patra Reviewed-by: Andrew Jones Signed-off-by: Anup Patel --- arch/riscv/include/uapi/asm/kvm.h | 1 + arch/riscv/kvm/vcpu.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index d8ead5952ed9..47a7c3958229 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_SVINVAL, KVM_RISCV_ISA_EXT_ZIHINTPAUSE, KVM_RISCV_ISA_EXT_ZICBOM, + KVM_RISCV_ISA_EXT_ZBB, KVM_RISCV_ISA_EXT_MAX, }; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 3112697cb12d..02b49cb94561 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -61,6 +61,7 @@ static const unsigned long kvm_isa_ext_arr[] = { KVM_ISA_EXT_ARR(SSTC), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(ZBB), KVM_ISA_EXT_ARR(ZIHINTPAUSE), KVM_ISA_EXT_ARR(ZICBOM), }; @@ -99,6 +100,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_SSTC: case KVM_RISCV_ISA_EXT_SVINVAL: case KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_RISCV_ISA_EXT_ZBB: return false; default: break; -- GitLab From d6f5f6e904be628941eeab7d6ae7d1fb9190c486 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 18 Jan 2022 11:12:40 +0530 Subject: [PATCH 3747/5631] RISC-V: Add AIA related CSR defines The RISC-V AIA specification improves handling per-HART local interrupts in a backward compatible manner. This patch adds defines for new RISC-V AIA CSRs. Signed-off-by: Anup Patel Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Reviewed-by: Atish Patra Signed-off-by: Anup Patel Acked-by: Palmer Dabbelt --- arch/riscv/include/asm/csr.h | 95 +++++++++++++++++++++++++++++++++++- 1 file changed, 94 insertions(+), 1 deletion(-) diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 0e571f6483d9..3c8d68152bce 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -7,7 +7,7 @@ #define _ASM_RISCV_CSR_H #include -#include +#include /* Status register flags */ #define SR_SIE _AC(0x00000002, UL) /* Supervisor Interrupt Enable */ @@ -73,7 +73,10 @@ #define IRQ_S_EXT 9 #define IRQ_VS_EXT 10 #define IRQ_M_EXT 11 +#define IRQ_S_GEXT 12 #define IRQ_PMU_OVF 13 +#define IRQ_LOCAL_MAX (IRQ_PMU_OVF + 1) +#define IRQ_LOCAL_MASK GENMASK((IRQ_LOCAL_MAX - 1), 0) /* Exception causes */ #define EXC_INST_MISALIGNED 0 @@ -156,6 +159,27 @@ (_AC(1, UL) << IRQ_S_TIMER) | \ (_AC(1, UL) << IRQ_S_EXT)) +/* AIA CSR bits */ +#define TOPI_IID_SHIFT 16 +#define TOPI_IID_MASK GENMASK(11, 0) +#define TOPI_IPRIO_MASK GENMASK(7, 0) +#define TOPI_IPRIO_BITS 8 + +#define TOPEI_ID_SHIFT 16 +#define TOPEI_ID_MASK GENMASK(10, 0) +#define TOPEI_PRIO_MASK GENMASK(10, 0) + +#define ISELECT_IPRIO0 0x30 +#define ISELECT_IPRIO15 0x3f +#define ISELECT_MASK GENMASK(8, 0) + +#define HVICTL_VTI BIT(30) +#define HVICTL_IID GENMASK(27, 16) +#define HVICTL_IID_SHIFT 16 +#define HVICTL_DPR BIT(9) +#define HVICTL_IPRIOM BIT(8) +#define HVICTL_IPRIO GENMASK(7, 0) + /* xENVCFG flags */ #define ENVCFG_STCE (_AC(1, ULL) << 63) #define ENVCFG_PBMTE (_AC(1, ULL) << 62) @@ -250,6 +274,18 @@ #define CSR_STIMECMP 0x14D #define CSR_STIMECMPH 0x15D +/* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ +#define CSR_SISELECT 0x150 +#define CSR_SIREG 0x151 + +/* Supervisor-Level Interrupts (AIA) */ +#define CSR_STOPEI 0x15c +#define CSR_STOPI 0xdb0 + +/* Supervisor-Level High-Half CSRs (AIA) */ +#define CSR_SIEH 0x114 +#define CSR_SIPH 0x154 + #define CSR_VSSTATUS 0x200 #define CSR_VSIE 0x204 #define CSR_VSTVEC 0x205 @@ -279,8 +315,32 @@ #define CSR_HGATP 0x680 #define CSR_HGEIP 0xe12 +/* Virtual Interrupts and Interrupt Priorities (H-extension with AIA) */ +#define CSR_HVIEN 0x608 +#define CSR_HVICTL 0x609 +#define CSR_HVIPRIO1 0x646 +#define CSR_HVIPRIO2 0x647 + +/* VS-Level Window to Indirectly Accessed Registers (H-extension with AIA) */ +#define CSR_VSISELECT 0x250 +#define CSR_VSIREG 0x251 + +/* VS-Level Interrupts (H-extension with AIA) */ +#define CSR_VSTOPEI 0x25c +#define CSR_VSTOPI 0xeb0 + +/* Hypervisor and VS-Level High-Half CSRs (H-extension with AIA) */ +#define CSR_HIDELEGH 0x613 +#define CSR_HVIENH 0x618 +#define CSR_HVIPH 0x655 +#define CSR_HVIPRIO1H 0x656 +#define CSR_HVIPRIO2H 0x657 +#define CSR_VSIEH 0x214 +#define CSR_VSIPH 0x254 + #define CSR_MSTATUS 0x300 #define CSR_MISA 0x301 +#define CSR_MIDELEG 0x303 #define CSR_MIE 0x304 #define CSR_MTVEC 0x305 #define CSR_MENVCFG 0x30a @@ -297,6 +357,25 @@ #define CSR_MIMPID 0xf13 #define CSR_MHARTID 0xf14 +/* Machine-Level Window to Indirectly Accessed Registers (AIA) */ +#define CSR_MISELECT 0x350 +#define CSR_MIREG 0x351 + +/* Machine-Level Interrupts (AIA) */ +#define CSR_MTOPEI 0x35c +#define CSR_MTOPI 0xfb0 + +/* Virtual Interrupts for Supervisor Level (AIA) */ +#define CSR_MVIEN 0x308 +#define CSR_MVIP 0x309 + +/* Machine-Level High-Half CSRs (AIA) */ +#define CSR_MIDELEGH 0x313 +#define CSR_MIEH 0x314 +#define CSR_MVIENH 0x318 +#define CSR_MVIPH 0x319 +#define CSR_MIPH 0x354 + #ifdef CONFIG_RISCV_M_MODE # define CSR_STATUS CSR_MSTATUS # define CSR_IE CSR_MIE @@ -307,6 +386,13 @@ # define CSR_TVAL CSR_MTVAL # define CSR_IP CSR_MIP +# define CSR_IEH CSR_MIEH +# define CSR_ISELECT CSR_MISELECT +# define CSR_IREG CSR_MIREG +# define CSR_IPH CSR_MIPH +# define CSR_TOPEI CSR_MTOPEI +# define CSR_TOPI CSR_MTOPI + # define SR_IE SR_MIE # define SR_PIE SR_MPIE # define SR_PP SR_MPP @@ -324,6 +410,13 @@ # define CSR_TVAL CSR_STVAL # define CSR_IP CSR_SIP +# define CSR_IEH CSR_SIEH +# define CSR_ISELECT CSR_SISELECT +# define CSR_IREG CSR_SIREG +# define CSR_IPH CSR_SIPH +# define CSR_TOPEI CSR_STOPEI +# define CSR_TOPI CSR_STOPI + # define SR_IE SR_SIE # define SR_PIE SR_SPIE # define SR_PP SR_SPP -- GitLab From 8fe6f7e14c7eeb01c3a1994eba2356400981cb1e Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 6 Mar 2023 12:10:15 +0530 Subject: [PATCH 3748/5631] RISC-V: Detect AIA CSRs from ISA string We have two extension names for AIA ISA support: Smaia (M-mode AIA CSRs) and Ssaia (S-mode AIA CSRs). We extend the ISA string parsing to detect Smaia and Ssaia extensions. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Reviewed-by: Atish Patra Reviewed-by: Conor Dooley Signed-off-by: Anup Patel Acked-by: Palmer Dabbelt --- arch/riscv/include/asm/hwcap.h | 2 ++ arch/riscv/kernel/cpu.c | 2 ++ arch/riscv/kernel/cpufeature.c | 2 ++ 3 files changed, 6 insertions(+) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 6263a0de1c6a..74f5dab2148f 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -42,6 +42,8 @@ #define RISCV_ISA_EXT_ZBB 30 #define RISCV_ISA_EXT_ZICBOM 31 #define RISCV_ISA_EXT_ZIHINTPAUSE 32 +#define RISCV_ISA_EXT_SMAIA 33 +#define RISCV_ISA_EXT_SSAIA 34 #define RISCV_ISA_EXT_MAX 64 #define RISCV_ISA_EXT_NAME_LEN_MAX 32 diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 8400f0cc9704..ae1e7bbf9344 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -188,6 +188,8 @@ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 59d58ee0f68d..9e92e23f6f82 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -221,6 +221,8 @@ void __init riscv_fill_hwcap(void) } } else { /* sorted alphabetically */ + SET_ISA_EXT_MAP("smaia", RISCV_ISA_EXT_SMAIA); + SET_ISA_EXT_MAP("ssaia", RISCV_ISA_EXT_SSAIA); SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); SET_ISA_EXT_MAP("sstc", RISCV_ISA_EXT_SSTC); SET_ISA_EXT_MAP("svinval", RISCV_ISA_EXT_SVINVAL); -- GitLab From e290dbb7f73670e06df7f8ec44c3f502c20707d7 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 9 Jan 2023 11:55:55 +0530 Subject: [PATCH 3749/5631] RISC-V: KVM: Drop the _MASK suffix from hgatp.VMID mask defines The hgatp.VMID mask defines are used before shifting when extracting VMID value from hgatp CSR value so based on the convention followed in the other parts of asm/csr.h, the hgatp.VMID mask defines should not have a _MASK suffix. While we are here, let's use GENMASK() for hgatp.VMID and hgatp.PPN. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Reviewed-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/asm/csr.h | 12 ++++++------ arch/riscv/kvm/mmu.c | 3 +-- arch/riscv/kvm/vmid.c | 4 ++-- 3 files changed, 9 insertions(+), 10 deletions(-) diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 3c8d68152bce..3176355cf4e9 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -131,25 +131,25 @@ #define HGATP32_MODE_SHIFT 31 #define HGATP32_VMID_SHIFT 22 -#define HGATP32_VMID_MASK _AC(0x1FC00000, UL) -#define HGATP32_PPN _AC(0x003FFFFF, UL) +#define HGATP32_VMID GENMASK(28, 22) +#define HGATP32_PPN GENMASK(21, 0) #define HGATP64_MODE_SHIFT 60 #define HGATP64_VMID_SHIFT 44 -#define HGATP64_VMID_MASK _AC(0x03FFF00000000000, UL) -#define HGATP64_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define HGATP64_VMID GENMASK(57, 44) +#define HGATP64_PPN GENMASK(43, 0) #define HGATP_PAGE_SHIFT 12 #ifdef CONFIG_64BIT #define HGATP_PPN HGATP64_PPN #define HGATP_VMID_SHIFT HGATP64_VMID_SHIFT -#define HGATP_VMID_MASK HGATP64_VMID_MASK +#define HGATP_VMID HGATP64_VMID #define HGATP_MODE_SHIFT HGATP64_MODE_SHIFT #else #define HGATP_PPN HGATP32_PPN #define HGATP_VMID_SHIFT HGATP32_VMID_SHIFT -#define HGATP_VMID_MASK HGATP32_VMID_MASK +#define HGATP_VMID HGATP32_VMID #define HGATP_MODE_SHIFT HGATP32_MODE_SHIFT #endif diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 46d692995830..f2eb47925806 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -755,8 +755,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) unsigned long hgatp = gstage_mode; struct kvm_arch *k = &vcpu->kvm->arch; - hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & - HGATP_VMID_MASK; + hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID; hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN; csr_write(CSR_HGATP, hgatp); diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 5246da1c9167..ddc98714ce8e 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -26,9 +26,9 @@ void __init kvm_riscv_gstage_vmid_detect(void) /* Figure-out number of VMID bits in HW */ old = csr_read(CSR_HGATP); - csr_write(CSR_HGATP, old | HGATP_VMID_MASK); + csr_write(CSR_HGATP, old | HGATP_VMID); vmid_bits = csr_read(CSR_HGATP); - vmid_bits = (vmid_bits & HGATP_VMID_MASK) >> HGATP_VMID_SHIFT; + vmid_bits = (vmid_bits & HGATP_VMID) >> HGATP_VMID_SHIFT; vmid_bits = fls_long(vmid_bits); csr_write(CSR_HGATP, old); -- GitLab From 54e43320c2ba0c70258a3aea690da38c6ea3293c Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 10 Jan 2023 16:44:25 +0530 Subject: [PATCH 3750/5631] RISC-V: KVM: Initial skeletal support for AIA To incrementally implement AIA support, we first add minimal skeletal support which only compiles and detects AIA hardware support at the boot-time but does not provide any functionality. Signed-off-by: Anup Patel Reviewed-by: Atish Patra Reviewed-by: Andrew Jones Signed-off-by: Anup Patel --- arch/riscv/include/asm/hwcap.h | 6 ++ arch/riscv/include/asm/kvm_aia.h | 109 ++++++++++++++++++++++++++++++ arch/riscv/include/asm/kvm_host.h | 7 ++ arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/aia.c | 66 ++++++++++++++++++ arch/riscv/kvm/main.c | 22 +++++- arch/riscv/kvm/vcpu.c | 45 ++++++++++-- arch/riscv/kvm/vcpu_insn.c | 1 + arch/riscv/kvm/vm.c | 4 ++ 9 files changed, 255 insertions(+), 6 deletions(-) create mode 100644 arch/riscv/include/asm/kvm_aia.h create mode 100644 arch/riscv/kvm/aia.c diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 74f5dab2148f..ab2abf561520 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -48,6 +48,12 @@ #define RISCV_ISA_EXT_MAX 64 #define RISCV_ISA_EXT_NAME_LEN_MAX 32 +#ifdef CONFIG_RISCV_M_MODE +#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA +#else +#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SSAIA +#endif + #ifndef __ASSEMBLY__ #include diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h new file mode 100644 index 000000000000..258a835d4c32 --- /dev/null +++ b/arch/riscv/include/asm/kvm_aia.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#ifndef __KVM_RISCV_AIA_H +#define __KVM_RISCV_AIA_H + +#include +#include + +struct kvm_aia { + /* In-kernel irqchip created */ + bool in_kernel; + + /* In-kernel irqchip initialized */ + bool initialized; +}; + +struct kvm_vcpu_aia { +}; + +#define kvm_riscv_aia_initialized(k) ((k)->arch.aia.initialized) + +#define irqchip_in_kernel(k) ((k)->arch.aia.in_kernel) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); +#define kvm_riscv_aia_available() \ + static_branch_unlikely(&kvm_riscv_aia_available) + +static inline void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) +{ +} + +static inline bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, + u64 mask) +{ + return false; +} + +static inline void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) +{ +} + +static inline void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) +{ +} + +static inline int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + *out_val = 0; + return 0; +} + +static inline int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long val) +{ + return 0; +} + +#define KVM_RISCV_VCPU_AIA_CSR_FUNCS + +static inline int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static inline void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu) +{ +} + +static inline int kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_aia_init_vm(struct kvm *kvm) +{ +} + +static inline void kvm_riscv_aia_destroy_vm(struct kvm *kvm) +{ +} + +void kvm_riscv_aia_enable(void); +void kvm_riscv_aia_disable(void); +int kvm_riscv_aia_init(void); +void kvm_riscv_aia_exit(void); + +#endif diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index cc7da66ee0c0..3157cf748df1 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -94,6 +95,9 @@ struct kvm_arch { /* Guest Timer */ struct kvm_guest_timer timer; + + /* AIA Guest/VM context */ + struct kvm_aia aia; }; struct kvm_cpu_trap { @@ -221,6 +225,9 @@ struct kvm_vcpu_arch { /* SBI context */ struct kvm_vcpu_sbi_context sbi_context; + /* AIA VCPU context */ + struct kvm_vcpu_aia aia_context; + /* Cache pages needed to program page tables with spinlock held */ struct kvm_mmu_memory_cache mmu_page_cache; diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 278e97c06e0a..8031b8912a0d 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -26,3 +26,4 @@ kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o +kvm-y += aia.o diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c new file mode 100644 index 000000000000..7a633331cd3e --- /dev/null +++ b/arch/riscv/kvm/aia.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include + +DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available); + +static void aia_set_hvictl(bool ext_irq_pending) +{ + unsigned long hvictl; + + /* + * HVICTL.IID == 9 and HVICTL.IPRIO == 0 represents + * no interrupt in HVICTL. + */ + + hvictl = (IRQ_S_EXT << HVICTL_IID_SHIFT) & HVICTL_IID; + hvictl |= ext_irq_pending; + csr_write(CSR_HVICTL, hvictl); +} + +void kvm_riscv_aia_enable(void) +{ + if (!kvm_riscv_aia_available()) + return; + + aia_set_hvictl(false); + csr_write(CSR_HVIPRIO1, 0x0); + csr_write(CSR_HVIPRIO2, 0x0); +#ifdef CONFIG_32BIT + csr_write(CSR_HVIPH, 0x0); + csr_write(CSR_HIDELEGH, 0x0); + csr_write(CSR_HVIPRIO1H, 0x0); + csr_write(CSR_HVIPRIO2H, 0x0); +#endif +} + +void kvm_riscv_aia_disable(void) +{ + if (!kvm_riscv_aia_available()) + return; + + aia_set_hvictl(false); +} + +int kvm_riscv_aia_init(void) +{ + if (!riscv_isa_extension_available(NULL, SxAIA)) + return -ENODEV; + + /* Enable KVM AIA support */ + static_branch_enable(&kvm_riscv_aia_available); + + return 0; +} + +void kvm_riscv_aia_exit(void) +{ +} diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 41ad7639a17b..6396352b4e4d 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -44,11 +44,15 @@ int kvm_arch_hardware_enable(void) csr_write(CSR_HVIP, 0); + kvm_riscv_aia_enable(); + return 0; } void kvm_arch_hardware_disable(void) { + kvm_riscv_aia_disable(); + /* * After clearing the hideleg CSR, the host kernel will receive * spurious interrupts if hvip CSR has pending interrupts and the @@ -63,6 +67,7 @@ void kvm_arch_hardware_disable(void) static int __init riscv_kvm_init(void) { + int rc; const char *str; if (!riscv_isa_extension_available(NULL, h)) { @@ -84,6 +89,10 @@ static int __init riscv_kvm_init(void) kvm_riscv_gstage_vmid_detect(); + rc = kvm_riscv_aia_init(); + if (rc && rc != -ENODEV) + return rc; + kvm_info("hypervisor extension available\n"); switch (kvm_riscv_gstage_mode()) { @@ -106,12 +115,23 @@ static int __init riscv_kvm_init(void) kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); - return kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (kvm_riscv_aia_available()) + kvm_info("AIA available\n"); + + rc = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (rc) { + kvm_riscv_aia_exit(); + return rc; + } + + return 0; } module_init(riscv_kvm_init); static void __exit riscv_kvm_exit(void) { + kvm_riscv_aia_exit(); + kvm_exit(); } module_exit(riscv_kvm_exit); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 02b49cb94561..b46e9cc92938 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -137,6 +137,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_timer_reset(vcpu); + kvm_riscv_vcpu_aia_reset(vcpu); + WRITE_ONCE(vcpu->arch.irqs_pending, 0); WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); @@ -159,6 +161,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { + int rc; struct kvm_cpu_context *cntx; struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; unsigned long host_isa, i; @@ -201,6 +204,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* setup performance monitoring */ kvm_riscv_vcpu_pmu_init(vcpu); + /* Setup VCPU AIA */ + rc = kvm_riscv_vcpu_aia_init(vcpu); + if (rc) + return rc; + /* Reset VCPU */ kvm_riscv_reset_vcpu(vcpu); @@ -220,6 +228,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { + /* Cleanup VCPU AIA context */ + kvm_riscv_vcpu_aia_deinit(vcpu); + /* Cleanup VCPU timer */ kvm_riscv_vcpu_timer_deinit(vcpu); @@ -741,6 +752,9 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) csr->hvip &= ~mask; csr->hvip |= val; } + + /* Flush AIA high interrupts */ + kvm_riscv_vcpu_aia_flush_interrupts(vcpu); } void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) @@ -766,6 +780,9 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) } } + /* Sync-up AIA high interrupts */ + kvm_riscv_vcpu_aia_sync_interrupts(vcpu); + /* Sync-up timer CSRs */ kvm_riscv_vcpu_timer_sync(vcpu); } @@ -802,10 +819,15 @@ int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask) { - unsigned long ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK) - << VSIP_TO_HVIP_SHIFT) & mask; + unsigned long ie; + + ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK) + << VSIP_TO_HVIP_SHIFT) & mask; + if (READ_ONCE(vcpu->arch.irqs_pending) & ie) + return true; - return (READ_ONCE(vcpu->arch.irqs_pending) & ie) ? true : false; + /* Check AIA high interrupts */ + return kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); } void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) @@ -901,6 +923,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context, vcpu->arch.isa); + kvm_riscv_vcpu_aia_load(vcpu, cpu); + vcpu->cpu = cpu; } @@ -910,6 +934,8 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->cpu = -1; + kvm_riscv_vcpu_aia_put(vcpu); + kvm_riscv_vcpu_guest_fp_save(&vcpu->arch.guest_context, vcpu->arch.isa); kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); @@ -977,6 +1003,7 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; csr_write(CSR_HVIP, csr->hvip); + kvm_riscv_vcpu_aia_update_hvip(vcpu); } /* @@ -1049,6 +1076,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_riscv_check_vcpu_requests(vcpu); + preempt_disable(); + + /* Update AIA HW state before entering guest */ + ret = kvm_riscv_vcpu_aia_update(vcpu); + if (ret <= 0) { + preempt_enable(); + continue; + } + local_irq_disable(); /* @@ -1077,6 +1113,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) xfer_to_guest_mode_work_pending()) { vcpu->mode = OUTSIDE_GUEST_MODE; local_irq_enable(); + preempt_enable(); kvm_vcpu_srcu_read_lock(vcpu); continue; } @@ -1110,8 +1147,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) /* Syncup interrupts state with HW */ kvm_riscv_vcpu_sync_interrupts(vcpu); - preempt_disable(); - /* * We must ensure that any pending interrupts are taken before * we exit guest timing so that timer ticks are accounted as diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index f689337b78ff..7a6abed41bc1 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -214,6 +214,7 @@ struct csr_func { }; static const struct csr_func csr_funcs[] = { + KVM_RISCV_VCPU_AIA_CSR_FUNCS KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS }; diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 65a964d7e70d..bc03d2ddcb51 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -41,6 +41,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return r; } + kvm_riscv_aia_init_vm(kvm); + kvm_riscv_guest_timer_init(kvm); return 0; @@ -49,6 +51,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_destroy_vcpus(kvm); + + kvm_riscv_aia_destroy_vm(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) -- GitLab From 7d50dd5012013f7c8e3c3e5d0bed78ba85800934 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 31 Mar 2023 19:56:56 +0530 Subject: [PATCH 3751/5631] RISC-V: KVM: Implement subtype for CSR ONE_REG interface To make the CSR ONE_REG interface extensible, we implement subtype for the CSR ONE_REG IDs. The existing CSR ONE_REG IDs are treated as subtype = 0 (aka General CSRs). Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Reviewed-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/uapi/asm/kvm.h | 3 +- arch/riscv/kvm/vcpu.c | 88 +++++++++++++++++++++++-------- 2 files changed, 69 insertions(+), 22 deletions(-) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 47a7c3958229..182023dc9a51 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -65,7 +65,7 @@ struct kvm_riscv_core { #define KVM_RISCV_MODE_S 1 #define KVM_RISCV_MODE_U 0 -/* CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +/* General CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ struct kvm_riscv_csr { unsigned long sstatus; unsigned long sie; @@ -152,6 +152,7 @@ enum KVM_RISCV_SBI_EXT_ID { /* Control and status registers are mapped as type 3 */ #define KVM_REG_RISCV_CSR (0x03 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_CSR_GENERAL (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) #define KVM_REG_RISCV_CSR_REG(name) \ (offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long)) diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index b46e9cc92938..3394859c5f85 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -460,27 +460,72 @@ static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu, return 0; } +static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + return -EINVAL; + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + kvm_riscv_vcpu_flush_interrupts(vcpu); + *out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; + } else + *out_val = ((unsigned long *)csr)[reg_num]; + + return 0; +} + +static inline int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) + return -EINVAL; + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + reg_val &= VSIP_VALID_MASK; + reg_val <<= VSIP_TO_HVIP_SHIFT; + } + + ((unsigned long *)csr)[reg_num] = reg_val; + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) + WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + + return 0; +} + static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { - struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + int rc; unsigned long __user *uaddr = (unsigned long __user *)(unsigned long)reg->addr; unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CSR); - unsigned long reg_val; + unsigned long reg_val, reg_subtype; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) - return -EINVAL; - if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { - kvm_riscv_vcpu_flush_interrupts(vcpu); - reg_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; - } else - reg_val = ((unsigned long *)csr)[reg_num]; + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + switch (reg_subtype) { + case KVM_REG_RISCV_CSR_GENERAL: + rc = kvm_riscv_vcpu_general_get_csr(vcpu, reg_num, ®_val); + break; + default: + rc = -EINVAL; + break; + } + if (rc) + return rc; if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) return -EFAULT; @@ -491,31 +536,32 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { - struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + int rc; unsigned long __user *uaddr = (unsigned long __user *)(unsigned long)reg->addr; unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_RISCV_CSR); - unsigned long reg_val; + unsigned long reg_val, reg_subtype; if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) return -EINVAL; - if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long)) - return -EINVAL; if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; - if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { - reg_val &= VSIP_VALID_MASK; - reg_val <<= VSIP_TO_HVIP_SHIFT; + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + switch (reg_subtype) { + case KVM_REG_RISCV_CSR_GENERAL: + rc = kvm_riscv_vcpu_general_set_csr(vcpu, reg_num, reg_val); + break; + default: + rc = -EINVAL; + break; } - - ((unsigned long *)csr)[reg_num] = reg_val; - - if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + if (rc) + return rc; return 0; } -- GitLab From 78f94c082a2f74b78c8b9c779756d8b25317a55a Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Fri, 31 Mar 2023 20:06:18 +0530 Subject: [PATCH 3752/5631] RISC-V: KVM: Add ONE_REG interface for AIA CSRs We implement ONE_REG interface for AIA CSRs as a separate subtype under the CSR ONE_REG interface. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Reviewed-by: Atish Patra Signed-off-by: Anup Patel --- arch/riscv/include/uapi/asm/kvm.h | 8 ++++++++ arch/riscv/kvm/vcpu.c | 8 ++++++++ 2 files changed, 16 insertions(+) diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index 182023dc9a51..cbc3e74fa670 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -79,6 +79,10 @@ struct kvm_riscv_csr { unsigned long scounteren; }; +/* AIA CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_aia_csr { +}; + /* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ struct kvm_riscv_timer { __u64 frequency; @@ -107,6 +111,7 @@ enum KVM_RISCV_ISA_EXT_ID { KVM_RISCV_ISA_EXT_ZIHINTPAUSE, KVM_RISCV_ISA_EXT_ZICBOM, KVM_RISCV_ISA_EXT_ZBB, + KVM_RISCV_ISA_EXT_SSAIA, KVM_RISCV_ISA_EXT_MAX, }; @@ -153,8 +158,11 @@ enum KVM_RISCV_SBI_EXT_ID { /* Control and status registers are mapped as type 3 */ #define KVM_REG_RISCV_CSR (0x03 << KVM_REG_RISCV_TYPE_SHIFT) #define KVM_REG_RISCV_CSR_GENERAL (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_CSR_AIA (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) #define KVM_REG_RISCV_CSR_REG(name) \ (offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_CSR_AIA_REG(name) \ + (offsetof(struct kvm_riscv_aia_csr, name) / sizeof(unsigned long)) /* Timer registers are mapped as type 4 */ #define KVM_REG_RISCV_TIMER (0x04 << KVM_REG_RISCV_TYPE_SHIFT) diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 3394859c5f85..57bdbfc17d48 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -58,6 +58,7 @@ static const unsigned long kvm_isa_ext_arr[] = { [KVM_RISCV_ISA_EXT_I] = RISCV_ISA_EXT_i, [KVM_RISCV_ISA_EXT_M] = RISCV_ISA_EXT_m, + KVM_ISA_EXT_ARR(SSAIA), KVM_ISA_EXT_ARR(SSTC), KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVPBMT), @@ -97,6 +98,7 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext) case KVM_RISCV_ISA_EXT_C: case KVM_RISCV_ISA_EXT_I: case KVM_RISCV_ISA_EXT_M: + case KVM_RISCV_ISA_EXT_SSAIA: case KVM_RISCV_ISA_EXT_SSTC: case KVM_RISCV_ISA_EXT_SVINVAL: case KVM_RISCV_ISA_EXT_ZIHINTPAUSE: @@ -520,6 +522,9 @@ static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, case KVM_REG_RISCV_CSR_GENERAL: rc = kvm_riscv_vcpu_general_get_csr(vcpu, reg_num, ®_val); break; + case KVM_REG_RISCV_CSR_AIA: + rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, ®_val); + break; default: rc = -EINVAL; break; @@ -556,6 +561,9 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, case KVM_REG_RISCV_CSR_GENERAL: rc = kvm_riscv_vcpu_general_set_csr(vcpu, reg_num, reg_val); break; + case KVM_REG_RISCV_CSR_AIA: + rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val); + break; default: rc = -EINVAL; break; -- GitLab From 6b1e8ba4bac49d99232026cae7eb8db3d338f9c2 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Tue, 4 Apr 2023 11:55:55 +0530 Subject: [PATCH 3753/5631] RISC-V: KVM: Use bitmap for irqs_pending and irqs_pending_mask To support 64 VCPU local interrupts on RV32 host, we should use bitmap for irqs_pending and irqs_pending_mask in struct kvm_vcpu_arch. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_host.h | 7 ++-- arch/riscv/kvm/vcpu.c | 53 ++++++++++++++++++++----------- 2 files changed, 38 insertions(+), 22 deletions(-) diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 3157cf748df1..ee0acccb1d3b 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -204,8 +204,9 @@ struct kvm_vcpu_arch { * in irqs_pending. Our approach is modeled around multiple producer * and single consumer problem where the consumer is the VCPU itself. */ - unsigned long irqs_pending; - unsigned long irqs_pending_mask; +#define KVM_RISCV_VCPU_NR_IRQS 64 + DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS); + DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); /* VCPU Timer */ struct kvm_vcpu_timer timer; @@ -334,7 +335,7 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq); int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq); void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu); -bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask); +bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask); void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 57bdbfc17d48..811c7e9a308c 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -141,8 +141,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_aia_reset(vcpu); - WRITE_ONCE(vcpu->arch.irqs_pending, 0); - WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + bitmap_zero(vcpu->arch.irqs_pending, KVM_RISCV_VCPU_NR_IRQS); + bitmap_zero(vcpu->arch.irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); kvm_riscv_vcpu_pmu_reset(vcpu); @@ -474,6 +474,7 @@ static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { kvm_riscv_vcpu_flush_interrupts(vcpu); *out_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK; + *out_val |= csr->hvip & ~IRQ_LOCAL_MASK; } else *out_val = ((unsigned long *)csr)[reg_num]; @@ -497,7 +498,7 @@ static inline int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, ((unsigned long *)csr)[reg_num] = reg_val; if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) - WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + WRITE_ONCE(vcpu->arch.irqs_pending_mask[0], 0); return 0; } @@ -799,9 +800,9 @@ void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; unsigned long mask, val; - if (READ_ONCE(vcpu->arch.irqs_pending_mask)) { - mask = xchg_acquire(&vcpu->arch.irqs_pending_mask, 0); - val = READ_ONCE(vcpu->arch.irqs_pending) & mask; + if (READ_ONCE(vcpu->arch.irqs_pending_mask[0])) { + mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[0], 0); + val = READ_ONCE(vcpu->arch.irqs_pending[0]) & mask; csr->hvip &= ~mask; csr->hvip |= val; @@ -825,12 +826,12 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) { if (hvip & (1UL << IRQ_VS_SOFT)) { if (!test_and_set_bit(IRQ_VS_SOFT, - &v->irqs_pending_mask)) - set_bit(IRQ_VS_SOFT, &v->irqs_pending); + v->irqs_pending_mask)) + set_bit(IRQ_VS_SOFT, v->irqs_pending); } else { if (!test_and_set_bit(IRQ_VS_SOFT, - &v->irqs_pending_mask)) - clear_bit(IRQ_VS_SOFT, &v->irqs_pending); + v->irqs_pending_mask)) + clear_bit(IRQ_VS_SOFT, v->irqs_pending); } } @@ -843,14 +844,20 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { - if (irq != IRQ_VS_SOFT && + /* + * We only allow VS-mode software, timer, and external + * interrupts when irq is one of the local interrupts + * defined by RISC-V privilege specification. + */ + if (irq < IRQ_LOCAL_MAX && + irq != IRQ_VS_SOFT && irq != IRQ_VS_TIMER && irq != IRQ_VS_EXT) return -EINVAL; - set_bit(irq, &vcpu->arch.irqs_pending); + set_bit(irq, vcpu->arch.irqs_pending); smp_mb__before_atomic(); - set_bit(irq, &vcpu->arch.irqs_pending_mask); + set_bit(irq, vcpu->arch.irqs_pending_mask); kvm_vcpu_kick(vcpu); @@ -859,25 +866,33 @@ int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) { - if (irq != IRQ_VS_SOFT && + /* + * We only allow VS-mode software, timer, and external + * interrupts when irq is one of the local interrupts + * defined by RISC-V privilege specification. + */ + if (irq < IRQ_LOCAL_MAX && + irq != IRQ_VS_SOFT && irq != IRQ_VS_TIMER && irq != IRQ_VS_EXT) return -EINVAL; - clear_bit(irq, &vcpu->arch.irqs_pending); + clear_bit(irq, vcpu->arch.irqs_pending); smp_mb__before_atomic(); - set_bit(irq, &vcpu->arch.irqs_pending_mask); + set_bit(irq, vcpu->arch.irqs_pending_mask); return 0; } -bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask) +bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { unsigned long ie; ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK) - << VSIP_TO_HVIP_SHIFT) & mask; - if (READ_ONCE(vcpu->arch.irqs_pending) & ie) + << VSIP_TO_HVIP_SHIFT) & (unsigned long)mask; + ie |= vcpu->arch.guest_csr.vsie & ~IRQ_LOCAL_MASK & + (unsigned long)mask; + if (READ_ONCE(vcpu->arch.irqs_pending[0]) & ie) return true; /* Check AIA high interrupts */ -- GitLab From 1b617bc93178912fa36f87a957c15d1f1708c299 Mon Sep 17 00:00:00 2001 From: Pierre Asselin Date: Wed, 19 Apr 2023 00:48:34 -0400 Subject: [PATCH 3754/5631] firmware/sysfb: Fix VESA format selection Some legacy BIOSes report no reserved bits in their 32-bit rgb mode, breaking the calculation of bits_per_pixel in commit f35cd3fa7729 ("firmware/sysfb: Fix EFI/VESA format selection"). However they report lfb_depth correctly for those modes. Keep the computation but set bits_per_pixel to lfb_depth if the latter is larger. v2 fixes the warnings from a max3() macro with arguments of different types; split the bits_per_pixel assignment to avoid uglyfing the code with too many typecasts. v3 fixes space and formatting blips pointed out by Javier, and change the bit_per_pixel assignment back to a single statement using two casts. v4 go back to v2 and use max_t() Signed-off-by: Pierre Asselin Fixes: f35cd3fa7729 ("firmware/sysfb: Fix EFI/VESA format selection") Link: https://lore.kernel.org/r/4Psm6B6Lqkz1QXM@panix3.panix.com Link: https://lore.kernel.org/r/20230412150225.3757223-1-javierm@redhat.com Tested-by: Thomas Zimmermann Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230419044834.10816-1-pa@panix.com --- drivers/firmware/sysfb_simplefb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c index 82c64cb9f531..74363ed7501f 100644 --- a/drivers/firmware/sysfb_simplefb.c +++ b/drivers/firmware/sysfb_simplefb.c @@ -51,7 +51,8 @@ __init bool sysfb_parse_mode(const struct screen_info *si, * * It's not easily possible to fix this in struct screen_info, * as this could break UAPI. The best solution is to compute - * bits_per_pixel here and ignore lfb_depth. In the loop below, + * bits_per_pixel from the color bits, reserved bits and + * reported lfb_depth, whichever is highest. In the loop below, * ignore simplefb formats with alpha bits, as EFI and VESA * don't specify alpha channels. */ @@ -60,6 +61,7 @@ __init bool sysfb_parse_mode(const struct screen_info *si, si->green_size + si->green_pos, si->blue_size + si->blue_pos), si->rsvd_size + si->rsvd_pos); + bits_per_pixel = max_t(u32, bits_per_pixel, si->lfb_depth); } else { bits_per_pixel = si->lfb_depth; } -- GitLab From 2f4d58f7635aec014428e73ef6120c4d0377c430 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Wed, 11 Jan 2023 11:26:10 +0530 Subject: [PATCH 3755/5631] RISC-V: KVM: Virtualize per-HART AIA CSRs The AIA specification introduce per-HART AIA CSRs which primarily support: * 64 local interrupts on both RV64 and RV32 * priority for each of the 64 local interrupts * interrupt filtering for local interrupts This patch virtualize above mentioned AIA CSRs and also extend ONE_REG interface to allow user-space save/restore Guest/VM view of these CSRs. Signed-off-by: Anup Patel Reviewed-by: Andrew Jones Signed-off-by: Anup Patel --- arch/riscv/include/asm/kvm_aia.h | 88 ++++---- arch/riscv/include/uapi/asm/kvm.h | 7 + arch/riscv/kvm/aia.c | 322 ++++++++++++++++++++++++++++++ 3 files changed, 382 insertions(+), 35 deletions(-) diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 258a835d4c32..1de0717112e5 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -12,6 +12,7 @@ #include #include +#include struct kvm_aia { /* In-kernel irqchip created */ @@ -21,7 +22,22 @@ struct kvm_aia { bool initialized; }; +struct kvm_vcpu_aia_csr { + unsigned long vsiselect; + unsigned long hviprio1; + unsigned long hviprio2; + unsigned long vsieh; + unsigned long hviph; + unsigned long hviprio1h; + unsigned long hviprio2h; +}; + struct kvm_vcpu_aia { + /* CPU AIA CSR context of Guest VCPU */ + struct kvm_vcpu_aia_csr guest_csr; + + /* CPU AIA CSR context upon Guest VCPU reset */ + struct kvm_vcpu_aia_csr guest_reset_csr; }; #define kvm_riscv_aia_initialized(k) ((k)->arch.aia.initialized) @@ -32,48 +48,50 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); #define kvm_riscv_aia_available() \ static_branch_unlikely(&kvm_riscv_aia_available) -static inline void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) -{ -} - -static inline void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) -{ -} - -static inline bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, - u64 mask) -{ - return false; -} - -static inline void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) -{ -} - -static inline void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) -{ -} - -static inline void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) +#define KVM_RISCV_AIA_IMSIC_TOPEI (ISELECT_MASK + 1) +static inline int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, + unsigned long isel, + unsigned long *val, + unsigned long new_val, + unsigned long wr_mask) { + return 0; } -static inline int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, - unsigned long reg_num, - unsigned long *out_val) +#ifdef CONFIG_32BIT +void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu); +#else +static inline void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) { - *out_val = 0; - return 0; } - -static inline int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, - unsigned long reg_num, - unsigned long val) +static inline void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) { - return 0; } - -#define KVM_RISCV_VCPU_AIA_CSR_FUNCS +#endif +bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask); + +void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val); +int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long val); + +int kvm_riscv_vcpu_aia_rmw_topei(struct kvm_vcpu *vcpu, + unsigned int csr_num, + unsigned long *val, + unsigned long new_val, + unsigned long wr_mask); +int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +#define KVM_RISCV_VCPU_AIA_CSR_FUNCS \ +{ .base = CSR_SIREG, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_ireg }, \ +{ .base = CSR_STOPEI, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_topei }, static inline int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu) { diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h index cbc3e74fa670..59707b80b315 100644 --- a/arch/riscv/include/uapi/asm/kvm.h +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -81,6 +81,13 @@ struct kvm_riscv_csr { /* AIA CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ struct kvm_riscv_aia_csr { + unsigned long siselect; + unsigned long iprio1; + unsigned long iprio2; + unsigned long sieh; + unsigned long siph; + unsigned long iprio1h; + unsigned long iprio2h; }; /* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 7a633331cd3e..4f1286fc7f17 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -7,6 +7,7 @@ * Anup Patel */ +#include #include #include @@ -26,6 +27,327 @@ static void aia_set_hvictl(bool ext_irq_pending) csr_write(CSR_HVICTL, hvictl); } +#ifdef CONFIG_32BIT +void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long mask, val; + + if (!kvm_riscv_aia_available()) + return; + + if (READ_ONCE(vcpu->arch.irqs_pending_mask[1])) { + mask = xchg_acquire(&vcpu->arch.irqs_pending_mask[1], 0); + val = READ_ONCE(vcpu->arch.irqs_pending[1]) & mask; + + csr->hviph &= ~mask; + csr->hviph |= val; + } +} + +void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (kvm_riscv_aia_available()) + csr->vsieh = csr_read(CSR_VSIEH); +} +#endif + +bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) +{ + unsigned long seip; + + if (!kvm_riscv_aia_available()) + return false; + +#ifdef CONFIG_32BIT + if (READ_ONCE(vcpu->arch.irqs_pending[1]) & + (vcpu->arch.aia_context.guest_csr.vsieh & upper_32_bits(mask))) + return true; +#endif + + seip = vcpu->arch.guest_csr.vsie; + seip &= (unsigned long)mask; + seip &= BIT(IRQ_S_EXT); + + if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip) + return false; + + return false; +} + +void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + if (!kvm_riscv_aia_available()) + return; + +#ifdef CONFIG_32BIT + csr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph); +#endif + aia_set_hvictl(!!(csr->hvip & BIT(IRQ_VS_EXT))); +} + +void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (!kvm_riscv_aia_available()) + return; + + csr_write(CSR_VSISELECT, csr->vsiselect); + csr_write(CSR_HVIPRIO1, csr->hviprio1); + csr_write(CSR_HVIPRIO2, csr->hviprio2); +#ifdef CONFIG_32BIT + csr_write(CSR_VSIEH, csr->vsieh); + csr_write(CSR_HVIPH, csr->hviph); + csr_write(CSR_HVIPRIO1H, csr->hviprio1h); + csr_write(CSR_HVIPRIO2H, csr->hviprio2h); +#endif +} + +void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (!kvm_riscv_aia_available()) + return; + + csr->vsiselect = csr_read(CSR_VSISELECT); + csr->hviprio1 = csr_read(CSR_HVIPRIO1); + csr->hviprio2 = csr_read(CSR_HVIPRIO2); +#ifdef CONFIG_32BIT + csr->vsieh = csr_read(CSR_VSIEH); + csr->hviph = csr_read(CSR_HVIPH); + csr->hviprio1h = csr_read(CSR_HVIPRIO1H); + csr->hviprio2h = csr_read(CSR_HVIPRIO2H); +#endif +} + +int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + return -EINVAL; + + *out_val = 0; + if (kvm_riscv_aia_available()) + *out_val = ((unsigned long *)csr)[reg_num]; + + return 0; +} + +int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long val) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (reg_num >= sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long)) + return -EINVAL; + + if (kvm_riscv_aia_available()) { + ((unsigned long *)csr)[reg_num] = val; + +#ifdef CONFIG_32BIT + if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) + WRITE_ONCE(vcpu->arch.irqs_pending_mask[1], 0); +#endif + } + + return 0; +} + +int kvm_riscv_vcpu_aia_rmw_topei(struct kvm_vcpu *vcpu, + unsigned int csr_num, + unsigned long *val, + unsigned long new_val, + unsigned long wr_mask) +{ + /* If AIA not available then redirect trap */ + if (!kvm_riscv_aia_available()) + return KVM_INSN_ILLEGAL_TRAP; + + /* If AIA not initialized then forward to user space */ + if (!kvm_riscv_aia_initialized(vcpu->kvm)) + return KVM_INSN_EXIT_TO_USER_SPACE; + + return kvm_riscv_vcpu_aia_imsic_rmw(vcpu, KVM_RISCV_AIA_IMSIC_TOPEI, + val, new_val, wr_mask); +} + +/* + * External IRQ priority always read-only zero. This means default + * priority order is always preferred for external IRQs unless + * HVICTL.IID == 9 and HVICTL.IPRIO != 0 + */ +static int aia_irq2bitpos[] = { +0, 8, -1, -1, 16, 24, -1, -1, /* 0 - 7 */ +32, -1, -1, -1, -1, 40, 48, 56, /* 8 - 15 */ +64, 72, 80, 88, 96, 104, 112, 120, /* 16 - 23 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 24 - 31 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 32 - 39 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 40 - 47 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 48 - 55 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 56 - 63 */ +}; + +static u8 aia_get_iprio8(struct kvm_vcpu *vcpu, unsigned int irq) +{ + unsigned long hviprio; + int bitpos = aia_irq2bitpos[irq]; + + if (bitpos < 0) + return 0; + + switch (bitpos / BITS_PER_LONG) { + case 0: + hviprio = csr_read(CSR_HVIPRIO1); + break; + case 1: +#ifndef CONFIG_32BIT + hviprio = csr_read(CSR_HVIPRIO2); + break; +#else + hviprio = csr_read(CSR_HVIPRIO1H); + break; + case 2: + hviprio = csr_read(CSR_HVIPRIO2); + break; + case 3: + hviprio = csr_read(CSR_HVIPRIO2H); + break; +#endif + default: + return 0; + } + + return (hviprio >> (bitpos % BITS_PER_LONG)) & TOPI_IPRIO_MASK; +} + +static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio) +{ + unsigned long hviprio; + int bitpos = aia_irq2bitpos[irq]; + + if (bitpos < 0) + return; + + switch (bitpos / BITS_PER_LONG) { + case 0: + hviprio = csr_read(CSR_HVIPRIO1); + break; + case 1: +#ifndef CONFIG_32BIT + hviprio = csr_read(CSR_HVIPRIO2); + break; +#else + hviprio = csr_read(CSR_HVIPRIO1H); + break; + case 2: + hviprio = csr_read(CSR_HVIPRIO2); + break; + case 3: + hviprio = csr_read(CSR_HVIPRIO2H); + break; +#endif + default: + return; + } + + hviprio &= ~(TOPI_IPRIO_MASK << (bitpos % BITS_PER_LONG)); + hviprio |= (unsigned long)prio << (bitpos % BITS_PER_LONG); + + switch (bitpos / BITS_PER_LONG) { + case 0: + csr_write(CSR_HVIPRIO1, hviprio); + break; + case 1: +#ifndef CONFIG_32BIT + csr_write(CSR_HVIPRIO2, hviprio); + break; +#else + csr_write(CSR_HVIPRIO1H, hviprio); + break; + case 2: + csr_write(CSR_HVIPRIO2, hviprio); + break; + case 3: + csr_write(CSR_HVIPRIO2H, hviprio); + break; +#endif + default: + return; + } +} + +static int aia_rmw_iprio(struct kvm_vcpu *vcpu, unsigned int isel, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + int i, first_irq, nirqs; + unsigned long old_val; + u8 prio; + +#ifndef CONFIG_32BIT + if (isel & 0x1) + return KVM_INSN_ILLEGAL_TRAP; +#endif + + nirqs = 4 * (BITS_PER_LONG / 32); + first_irq = (isel - ISELECT_IPRIO0) * 4; + + old_val = 0; + for (i = 0; i < nirqs; i++) { + prio = aia_get_iprio8(vcpu, first_irq + i); + old_val |= (unsigned long)prio << (TOPI_IPRIO_BITS * i); + } + + if (val) + *val = old_val; + + if (wr_mask) { + new_val = (old_val & ~wr_mask) | (new_val & wr_mask); + for (i = 0; i < nirqs; i++) { + prio = (new_val >> (TOPI_IPRIO_BITS * i)) & + TOPI_IPRIO_MASK; + aia_set_iprio8(vcpu, first_irq + i, prio); + } + } + + return KVM_INSN_CONTINUE_NEXT_SEPC; +} + +#define IMSIC_FIRST 0x70 +#define IMSIC_LAST 0xff +int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + unsigned int isel; + + /* If AIA not available then redirect trap */ + if (!kvm_riscv_aia_available()) + return KVM_INSN_ILLEGAL_TRAP; + + /* First try to emulate in kernel space */ + isel = csr_read(CSR_VSISELECT) & ISELECT_MASK; + if (isel >= ISELECT_IPRIO0 && isel <= ISELECT_IPRIO15) + return aia_rmw_iprio(vcpu, isel, val, new_val, wr_mask); + else if (isel >= IMSIC_FIRST && isel <= IMSIC_LAST && + kvm_riscv_aia_initialized(vcpu->kvm)) + return kvm_riscv_vcpu_aia_imsic_rmw(vcpu, isel, val, new_val, + wr_mask); + + /* We can't handle it here so redirect to user space */ + return KVM_INSN_EXIT_TO_USER_SPACE; +} + void kvm_riscv_aia_enable(void) { if (!kvm_riscv_aia_available()) -- GitLab From 3d1793562858f2bc42cc722fe00ec9b2ff0618e1 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Thu, 9 Mar 2023 15:59:19 +0800 Subject: [PATCH 3756/5631] KVM: arm64: Fix repeated words in comments Delete the redundant word 'to'. Signed-off-by: Jingyu Wang Reviewed-by: Mukesh Ojha Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230309075919.169518-1-jingyuwang_vip@163.com --- arch/arm64/kvm/inject_fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) -- GitLab From 4c181e3d352e9280c84fb4b4c7a8940ce005374e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:14 +0000 Subject: [PATCH 3757/5631] KVM: arm64: Document check for TIF_FOREIGN_FPSTATE In kvm_arch_vcpu_load_fp() we unconditionally set the current FP state to FP_STATE_HOST_OWNED, this will be overridden to FP_STATE_NONE if TIF_FOREIGN_FPSTATE is set but the check is deferred until kvm_arch_vcpu_ctxflush_fp() where we are no longer preemptable. Add a comment to this effect to help avoid people being concerned about the lack of a check and discover where the check is done. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-1-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..3fd0ce6a3500 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,6 +81,11 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_kvm_prepare(); + /* + * We will check TIF_FOREIGN_FPSTATE just before entering the + * guest in kvm_arch_vcpu_ctxflush_fp() and override this to + * FP_STATE_FREE if the flag set. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); -- GitLab From d071cefdcca39fdbcdd4bf36868448820dbac34b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:15 +0000 Subject: [PATCH 3758/5631] KVM: arm64: Restructure check for SVE support in FP trap handler We share the same handler for general floating point and SVE traps with a check to make sure we don't handle any SVE traps if the system doesn't have SVE support. Since we will be adding SME support and wishing to handle that along with other FP related traps rewrite the check to be more scalable and a bit clearer too, ensuring we don't misidentify SME traps as SVE ones. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-2-57ba0082e9ff@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 07d37ff88a3f..d29d2ebf9126 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -176,9 +176,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ -- GitLab From aaa2f14e6f3f34de8edfb13566110a0fe0d88785 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:16 +0000 Subject: [PATCH 3759/5631] KVM: arm64: Clarify host SME state management Normally when running a guest we do not touch the floating point register state until first use of floating point by the guest, saving the current state and loading the guest state at that point. This has been found to offer a performance benefit in common cases. However currently if SME is active when switching to a guest then we exit streaming mode, disable ZA and invalidate the floating point register state prior to starting the guest. The exit from streaming mode is required for correct guest operation, if we leave streaming mode enabled then many non-SME operations can generate SME traps (eg, SVE operations will become streaming SVE operations). If EL1 leaves CPACR_EL1.SMEN disabled then the host is unable to intercept these traps. This will mean that a SME unaware guest will see SME exceptions which will confuse it. Disabling streaming mode also avoids creating spurious indications of usage of the SME hardware which could impact system performance, especially with shared SME implementations. Document the requirement to exit streaming mode clearly. There is no issue with guest operation caused by PSTATE.ZA so we can defer handling for that until first floating point usage, do so if the register state is not that of the current task and hence has already been saved. We could also do this for the case where the register state is that for the current task however this is very unlikely to happen and would require disproportionate effort so continue to save the state in that case. Saving this state on first use would require that we map and unmap storage for the host version of these registers for use by the hypervisor, taking care to deal with protected KVM and the fact that the host can free or reallocate the backing storage. Given that the strong recommendation is that applications should only keep PSTATE.ZA enabled when the state it enables is in active use it is difficult to see a case where a VMM would wish to do this, it would need to not only be using SME but also running the guest in the middle of SME usage. This can be revisited in the future if a use case does arises, in the interim such tasks will work but experience a performance overhead. This brings our handling of SME more into line with our handling of other floating point state and documents more clearly the constraints we have, especially around streaming mode. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-3-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 3fd0ce6a3500..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -92,20 +92,23 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); + /* + * If PSTATE.SM is enabled then save any pending FP + * state and disable PSTATE.SM. If we leave PSTATE.SM + * enabled and the guest does not enable SME via + * CPACR_EL1.SMEN then operations that should be valid + * may generate SME traps from EL1 to EL1 which we + * can't intercept and which would confuse the guest. + * + * Do the same for PSTATE.ZA in the case where there + * is state in the registers which has not already + * been saved, this is very unlikely to happen. + */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { vcpu->arch.fp_state = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); -- GitLab From 10af303192bc5490bb39b29541ecb0ead2eff1ce Mon Sep 17 00:00:00 2001 From: Daisuke Matsuda Date: Tue, 18 Apr 2023 18:06:42 +0900 Subject: [PATCH 3760/5631] RDMA/rxe: Fix spinlock recursion deadlock on requester The following deadlock is observed: Call Trace: _raw_spin_lock_bh+0x29/0x30 check_type_state.constprop.0+0x4e/0xc0 [rdma_rxe] rxe_rcv+0x173/0x3d0 [rdma_rxe] rxe_udp_encap_recv+0x69/0xd0 [rdma_rxe] ? __pfx_rxe_udp_encap_recv+0x10/0x10 [rdma_rxe] udp_queue_rcv_one_skb+0x258/0x520 udp_unicast_rcv_skb+0x75/0x90 __udp4_lib_rcv+0x364/0x5c0 ip_protocol_deliver_rcu+0xa7/0x160 ip_local_deliver_finish+0x73/0xa0 ip_sublist_rcv_finish+0x80/0x90 ip_sublist_rcv+0x191/0x220 ip_list_rcv+0x132/0x160 __netif_receive_skb_list_core+0x297/0x2c0 netif_receive_skb_list_internal+0x1c5/0x300 napi_complete_done+0x6f/0x1b0 virtnet_poll+0x1f4/0x2d0 [virtio_net] __napi_poll+0x2c/0x1b0 net_rx_action+0x293/0x350 ? __napi_schedule+0x79/0x90 __do_softirq+0xcb/0x2ab __irq_exit_rcu+0xb9/0xf0 common_interrupt+0x80/0xa0 asm_common_interrupt+0x22/0x40 RIP: 0010:_raw_spin_lock+0x17/0x30 rxe_requester+0xe4/0x8f0 [rdma_rxe] ? xas_load+0x9/0xa0 ? xa_load+0x70/0xb0 do_task+0x64/0x1f0 [rdma_rxe] rxe_post_send+0x54/0x110 [rdma_rxe] ib_uverbs_post_send+0x5f8/0x680 [ib_uverbs] ? netif_receive_skb_list_internal+0x1e3/0x300 ib_uverbs_write+0x3c8/0x500 [ib_uverbs] vfs_write+0xc5/0x3b0 ksys_write+0xab/0xe0 ? syscall_trace_enter.constprop.0+0x126/0x1a0 do_syscall_64+0x3b/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The deadlock is easily reproducible with perftest. Fix it by disabling softirq when acquiring the lock in process context. Fixes: f605f26ea196 ("RDMA/rxe: Protect QP state with qp->state_lock") Link: https://lore.kernel.org/r/20230418090642.1849358-1-matsuda-daisuke@fujitsu.com Signed-off-by: Daisuke Matsuda Acked-by: Zhu Yanjun Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_req.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 8e50d116d273..65134a9aefe7 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -180,13 +180,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) if (wqe == NULL) return NULL; - spin_lock(&qp->state_lock); + spin_lock_bh(&qp->state_lock); if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) { - spin_unlock(&qp->state_lock); + spin_unlock_bh(&qp->state_lock); return NULL; } - spin_unlock(&qp->state_lock); + spin_unlock_bh(&qp->state_lock); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; -- GitLab From 109205b40afbddd01baff796c627c5be3d804ef9 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 20 Apr 2023 09:48:08 -1000 Subject: [PATCH 3761/5631] RDMA/irdma: Drop spurious WQ_UNBOUND from alloc_ordered_workqueue() call Workqueue is in the process of cleaning up the distinction between unbound workqueues w/ @nr_active==1 and ordered workqueues. Explicit WQ_UNBOUND isn't needed for alloc_ordered_workqueue() and will trigger a warning in the future. Let's remove it. This doesn't cause any functional changes. Link: https://lore.kernel.org/r/ZEGW-IcFReR1juVM@slm.duckdns.org Signed-off-by: Tejun Heo Acked-by: Shiraz Saleem Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/irdma/hw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index f68353167c94..f5882625ad71 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -1908,8 +1908,8 @@ int irdma_ctrl_init_hw(struct irdma_pci_f *rf) break; rf->init_state = CEQ0_CREATED; /* Handles processing of CQP completions */ - rf->cqp_cmpl_wq = alloc_ordered_workqueue("cqp_cmpl_wq", - WQ_HIGHPRI | WQ_UNBOUND); + rf->cqp_cmpl_wq = + alloc_ordered_workqueue("cqp_cmpl_wq", WQ_HIGHPRI); if (!rf->cqp_cmpl_wq) { status = -ENOMEM; break; -- GitLab From 746aa3c8cb1a650ff2583497ac646e505831b9b9 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Thu, 20 Apr 2023 04:39:06 +0300 Subject: [PATCH 3762/5631] RDMA/mlx5: Use correct device num_ports when modify DC Just like other QP types, when modify DC, the port_num should be compared with dev->num_ports, instead of HCA_CAP.num_ports. Otherwise Multi-port vHCA on DC may not work. Fixes: 776a3906b692 ("IB/mlx5: Add support for DC target QP") Link: https://lore.kernel.org/r/20230420013906.1244185-1-markzhang@nvidia.com Signed-off-by: Mark Zhang Reviewed-by: Maor Gottlieb Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/mlx5/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 1093d3a0ed43..70ca8ffa9256 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4493,7 +4493,7 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr, return -EINVAL; if (attr->port_num == 0 || - attr->port_num > MLX5_CAP_GEN(dev->mdev, num_ports)) { + attr->port_num > dev->num_ports) { mlx5_ib_dbg(dev, "invalid port number %d. number of ports is %d\n", attr->port_num, dev->num_ports); return -EINVAL; -- GitLab From f6c73a11133ef991284311387ca707b48bf53912 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:42 -0700 Subject: [PATCH 3763/5631] fs.h: Add TRACE_IOCB_STRINGS for use in trace points Add TRACE_IOCB_STRINGS macro which can be used in the trace point patch to print different flag values with meaningful string output. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..75d24fa082e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -340,6 +340,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; -- GitLab From d3bff1fc50d4fcaccddbd63917dd94172e80c40e Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:43 -0700 Subject: [PATCH 3764/5631] iomap: Remove IOMAP_DIO_NOSYNC unused dio flag IOMAP_DIO_NOSYNC earlier was added for use in btrfs. But it seems for aio dsync writes this is not useful anyway. For aio dsync case, we we queue the request and return -EIOCBQUEUED. Now, since IOMAP_DIO_NOSYNC doesn't let iomap_dio_complete() to call generic_write_sync(), hence we may lose the sync write. Hence kill this flag as it is not in use by any FS now. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Ritesh Harjani (IBM) Signed-off-by: Darrick J. Wong --- fs/iomap/direct-io.c | 2 +- include/linux/iomap.h | 6 ------ 2 files changed, 1 insertion(+), 7 deletions(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index f771001574d0..36ab1152dbea 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -541,7 +541,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, } /* for data sync or sync, we need sync completion processing */ - if (iocb_is_dsync(iocb) && !(dio_flags & IOMAP_DIO_NOSYNC)) { + if (iocb_is_dsync(iocb)) { dio->flags |= IOMAP_DIO_NEED_SYNC; /* diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f8123504e5e..e2b836c2e119 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -377,12 +377,6 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) -/* - * The caller will sync the write if needed; do not sync it within - * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. - */ -#define IOMAP_DIO_NOSYNC (1 << 3) - ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); -- GitLab From 3fd41721cd5c30af37c860e6201c98db0a568fd2 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:43 -0700 Subject: [PATCH 3765/5631] iomap: Add DIO tracepoints Add trace_iomap_dio_rw_begin, trace_iomap_dio_rw_queued and trace_iomap_dio_complete tracepoint. trace_iomap_dio_rw_queued is mostly only to know that the request was queued and -EIOCBQUEUED was returned. It is mostly trace_iomap_dio_rw_begin & trace_iomap_dio_complete which has all the details. a.out-2073 [006] 134.225717: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x0 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT|WRITE dio_flags DIO_FORCE_WAIT aio 1 a.out-2073 [006] 134.226234: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT|WRITE aio 1 error 0 ret 4096 a.out-2074 [006] 136.225975: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 1 a.out-2074 [006] 136.226173: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 ksoftirqd/3-31 [003] 136.226389: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 1 error 0 ret 4096 a.out-2075 [003] 141.674969: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT|WRITE dio_flags aio 1 a.out-2075 [003] 141.676085: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 kworker/2:0-27 [002] 141.676432: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT|WRITE aio 1 error 0 ret 4096 a.out-2077 [006] 143.443746: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 1 a.out-2077 [006] 143.443866: iomap_dio_rw_queued: dev 7:7 ino 0xe size 0x1000 offset 0x1000 length 0x0 ksoftirqd/5-41 [005] 143.444134: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 1 error 0 ret 4096 a.out-2078 [007] 146.716833: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 0 a.out-2078 [007] 146.717639: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 0 error 0 ret 4096 a.out-2079 [006] 148.972605: iomap_dio_rw_begin: dev 7:7 ino 0xe size 0x1000 offset 0x0 length 0x1000 done_before 0x0 flags DIRECT dio_flags aio 0 a.out-2079 [006] 148.973099: iomap_dio_complete: dev 7:7 ino 0xe size 0x1000 offset 0x1000 flags DIRECT aio 0 error 0 ret 4096 Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- fs/iomap/direct-io.c | 7 +++- fs/iomap/trace.c | 1 + fs/iomap/trace.h | 78 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 1 deletion(-) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 36ab1152dbea..019cc87d0fb3 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -130,6 +130,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (ret > 0) ret += dio->done_before; + trace_iomap_dio_complete(iocb, dio->error, ret); kfree(dio); return ret; @@ -493,6 +494,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct blk_plug plug; struct iomap_dio *dio; + trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before); + if (!iomi.len) return NULL; @@ -650,8 +653,10 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, */ dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { - if (!wait_for_completion) + if (!wait_for_completion) { + trace_iomap_dio_rw_queued(inode, iomi.pos, iomi.len); return ERR_PTR(-EIOCBQUEUED); + } for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); diff --git a/fs/iomap/trace.c b/fs/iomap/trace.c index da217246b1a9..728d5443daf5 100644 --- a/fs/iomap/trace.c +++ b/fs/iomap/trace.c @@ -3,6 +3,7 @@ * Copyright (c) 2019 Christoph Hellwig */ #include +#include /* * We include this last to have the helpers above available for the trace diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h index f6ea9540d082..c16fd55f5595 100644 --- a/fs/iomap/trace.h +++ b/fs/iomap/trace.h @@ -83,6 +83,7 @@ DEFINE_RANGE_EVENT(iomap_writepage); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); +DEFINE_RANGE_EVENT(iomap_dio_rw_queued); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ @@ -107,6 +108,11 @@ DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } +#define IOMAP_DIO_STRINGS \ + {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ + {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ + {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } + DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), @@ -183,6 +189,78 @@ TRACE_EVENT(iomap_iter, (void *)__entry->caller) ); +TRACE_EVENT(iomap_dio_rw_begin, + TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, + unsigned int dio_flags, size_t done_before), + TP_ARGS(iocb, iter, dio_flags, done_before), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(size_t, count) + __field(size_t, done_before) + __field(int, ki_flags) + __field(unsigned int, dio_flags) + __field(bool, aio) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->count = iov_iter_count(iter); + __entry->done_before = done_before; + __entry->ki_flags = iocb->ki_flags; + __entry->dio_flags = dio_flags; + __entry->aio = !is_sync_kiocb(iocb); + ), + TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __entry->count, + __entry->done_before, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), + __entry->aio) +); + +TRACE_EVENT(iomap_dio_complete, + TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), + TP_ARGS(iocb, error, ret), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, isize) + __field(loff_t, pos) + __field(int, ki_flags) + __field(bool, aio) + __field(int, error) + __field(ssize_t, ret) + ), + TP_fast_assign( + __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; + __entry->ino = file_inode(iocb->ki_filp)->i_ino; + __entry->isize = file_inode(iocb->ki_filp)->i_size; + __entry->pos = iocb->ki_pos; + __entry->ki_flags = iocb->ki_flags; + __entry->aio = !is_sync_kiocb(iocb); + __entry->error = error; + __entry->ret = ret; + ), + TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __entry->isize, + __entry->pos, + __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), + __entry->aio, + __entry->error, + __entry->ret) +); + #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH -- GitLab From ef5031137b90c5338792f7073ba3bf38d14c8cf1 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Wed, 15 Feb 2023 09:21:17 +0800 Subject: [PATCH 3766/5631] ubi: Simplify bool conversion ./drivers/mtd/ubi/build.c:1261:33-38: WARNING: conversion to bool not needed here Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4061 Signed-off-by: Yang Li Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/build.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index ad025b2ee417..bb1a90bbc8ff 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1267,7 +1267,7 @@ static int __init ubi_init(void) mutex_lock(&ubi_devices_mutex); err = ubi_attach_mtd_dev(mtd, p->ubi_num, p->vid_hdr_offs, p->max_beb_per1024, - p->enable_fm == 0 ? true : false); + p->enable_fm == 0); mutex_unlock(&ubi_devices_mutex); if (err < 0) { pr_err("UBI error: cannot attach mtd%d\n", -- GitLab From 705b004ee377b789e39ae237519bab714297ac83 Mon Sep 17 00:00:00 2001 From: Yi Liu Date: Thu, 20 Apr 2023 22:36:11 -0700 Subject: [PATCH 3767/5631] docs: kvm: vfio: Suggest KVM_DEV_VFIO_GROUP_ADD vs VFIO_GROUP_GET_DEVICE_FD ordering as some vfio_device's open_device op requires kvm pointer and kvm pointer set is part of GROUP_ADD. Reviewed-by: Kevin Tian Signed-off-by: Yi Liu Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20230421053611.55839-1-yi.l.liu@intel.com Signed-off-by: Alex Williamson --- Documentation/virt/kvm/devices/vfio.rst | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/Documentation/virt/kvm/devices/vfio.rst b/Documentation/virt/kvm/devices/vfio.rst index 2d20dc561069..08b544212638 100644 --- a/Documentation/virt/kvm/devices/vfio.rst +++ b/Documentation/virt/kvm/devices/vfio.rst @@ -39,3 +39,8 @@ KVM_DEV_VFIO_GROUP attributes: - @groupfd is a file descriptor for a VFIO group; - @tablefd is a file descriptor for a TCE table allocated via KVM_CREATE_SPAPR_TCE. + +The GROUP_ADD operation above should be invoked prior to accessing the +device file descriptor via VFIO_GROUP_GET_DEVICE_FD in order to support +drivers which require a kvm pointer to be set in their .open_device() +callback. -- GitLab From c477d83c26b7acd526a30a32be7e9c0bab5da285 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Tue, 21 Mar 2023 15:11:36 +0800 Subject: [PATCH 3768/5631] ubifs: Remove return in compr_exit() It's redundant, let's remove it. Signed-off-by: Yangtao Li Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- fs/ubifs/compress.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c index 3a92e6af69b2..75461777c466 100644 --- a/fs/ubifs/compress.c +++ b/fs/ubifs/compress.c @@ -217,7 +217,6 @@ static void compr_exit(struct ubifs_compressor *compr) { if (compr->capi_name) crypto_free_comp(compr->cc); - return; } /** -- GitLab From 31a149d5c13c4cbcf97de3435817263a2d8c9d6e Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Tue, 28 Mar 2023 23:35:34 +0800 Subject: [PATCH 3769/5631] ubi: Fix return value overwrite issue in try_write_vid_and_data() The commit 2d78aee426d8 ("UBI: simplify LEB write and atomic LEB change code") adds helper function, try_write_vid_and_data(), to simplify the code, but this helper function has bug, it will return 0 (success) when ubi_io_write_vid_hdr() or the ubi_io_write_data() return error number (-EIO, etc), because the return value of ubi_wl_put_peb() will overwrite the original return value. This issue will cause unexpected data loss issue, because the caller of this function and UBIFS willn't know the data is lost. Fixes: 2d78aee426d8 ("UBI: simplify LEB write and atomic LEB change code") Cc: stable@vger.kernel.org Signed-off-by: Wang YanQing Reviewed-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- drivers/mtd/ubi/eba.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 403b79d6efd5..655ff41863e2 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -946,7 +946,7 @@ static int try_write_vid_and_data(struct ubi_volume *vol, int lnum, int offset, int len) { struct ubi_device *ubi = vol->ubi; - int pnum, opnum, err, vol_id = vol->vol_id; + int pnum, opnum, err, err2, vol_id = vol->vol_id; pnum = ubi_wl_get_peb(ubi); if (pnum < 0) { @@ -981,10 +981,19 @@ static int try_write_vid_and_data(struct ubi_volume *vol, int lnum, out_put: up_read(&ubi->fm_eba_sem); - if (err && pnum >= 0) - err = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1); - else if (!err && opnum >= 0) - err = ubi_wl_put_peb(ubi, vol_id, lnum, opnum, 0); + if (err && pnum >= 0) { + err2 = ubi_wl_put_peb(ubi, vol_id, lnum, pnum, 1); + if (err2) { + ubi_warn(ubi, "failed to return physical eraseblock %d, error %d", + pnum, err2); + } + } else if (!err && opnum >= 0) { + err2 = ubi_wl_put_peb(ubi, vol_id, lnum, opnum, 0); + if (err2) { + ubi_warn(ubi, "failed to return physical eraseblock %d, error %d", + opnum, err2); + } + } return err; } -- GitLab From c5733ae6dc895fa45032df0342c98dedc7051c2d Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Thu, 20 Apr 2023 21:01:32 -0400 Subject: [PATCH 3770/5631] NFS: set varaiable nfs_netfs_debug_id storage-class-specifier to static smatch reports fs/nfs/fscache.c:260:10: warning: symbol 'nfs_netfs_debug_id' was not declared. Should it be static? This variable is only used in its defining file, so it should be static Signed-off-by: Tom Rix Signed-off-by: Anna Schumaker --- fs/nfs/fscache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 95c2b3056e2b..8c35d88a84b1 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -257,7 +257,7 @@ int nfs_netfs_readahead(struct readahead_control *ractl) return 0; } -atomic_t nfs_netfs_debug_id; +static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); -- GitLab From 1fb815b38bb31d6af9bd0540b8652a0d6fe6cfd3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A5rten=20Lindahl?= Date: Thu, 30 Mar 2023 11:32:14 +0200 Subject: [PATCH 3771/5631] ubifs: Free memory for tmpfile name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When opening a ubifs tmpfile on an encrypted directory, function fscrypt_setup_filename allocates memory for the name that is to be stored in the directory entry, but after the name has been copied to the directory entry inode, the memory is not freed. When running kmemleak on it we see that it is registered as a leak. The report below is triggered by a simple program 'tmpfile' just opening a tmpfile: unreferenced object 0xffff88810178f380 (size 32): comm "tmpfile", pid 509, jiffies 4294934744 (age 1524.742s) backtrace: __kmem_cache_alloc_node __kmalloc fscrypt_setup_filename ubifs_tmpfile vfs_tmpfile path_openat Free this memory after it has been copied to the inode. Signed-off-by: Mårten Lindahl Reviewed-by: Zhihao Cheng Cc: stable@vger.kernel.org Signed-off-by: Richard Weinberger --- fs/ubifs/dir.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 1505539f6fe9..5f33dbad27f6 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -492,6 +492,7 @@ static int ubifs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, unlock_2_inodes(dir, inode); ubifs_release_budget(c, &req); + fscrypt_free_filename(&nm); return finish_open_simple(file, 0); -- GitLab From 3a36d20e012903f45714df2731261fdefac900cb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=C3=A5rten=20Lindahl?= Date: Thu, 30 Mar 2023 16:40:59 +0200 Subject: [PATCH 3772/5631] ubifs: Fix memory leak in do_rename MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If renaming a file in an encrypted directory, function fscrypt_setup_filename allocates memory for a file name. This name is never used, and before returning to the caller the memory for it is not freed. When running kmemleak on it we see that it is registered as a leak. The report below is triggered by a simple program 'rename' that renames a file in an encrypted directory: unreferenced object 0xffff888101502840 (size 32): comm "rename", pid 9404, jiffies 4302582475 (age 435.735s) backtrace: __kmem_cache_alloc_node __kmalloc fscrypt_setup_filename do_rename ubifs_rename vfs_rename do_renameat2 To fix this we can remove the call to fscrypt_setup_filename as it's not needed. Fixes: 278d9a243635f26 ("ubifs: Rename whiteout atomically") Reported-by: Zhihao Cheng Signed-off-by: Mårten Lindahl Reviewed-by: Zhihao Cheng Cc: stable@vger.kernel.org Signed-off-by: Richard Weinberger --- fs/ubifs/dir.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 5f33dbad27f6..ef0499edc248 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -358,7 +358,6 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) umode_t mode = S_IFCHR | WHITEOUT_MODE; struct inode *inode; struct ubifs_info *c = dir->i_sb->s_fs_info; - struct fscrypt_name nm; /* * Create an inode('nlink = 1') for whiteout without updating journal, @@ -369,10 +368,6 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) dbg_gen("dent '%pd', mode %#hx in dir ino %lu", dentry, mode, dir->i_ino); - err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm); - if (err) - return ERR_PTR(err); - inode = ubifs_new_inode(c, dir, mode, false); if (IS_ERR(inode)) { err = PTR_ERR(inode); @@ -395,7 +390,6 @@ static struct inode *create_whiteout(struct inode *dir, struct dentry *dentry) make_bad_inode(inode); iput(inode); out_free: - fscrypt_free_filename(&nm); ubifs_err(c, "cannot create whiteout file, error %d", err); return ERR_PTR(err); } -- GitLab From e025f0a73f6acb920d86549b2177a5883535421d Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Thu, 20 Apr 2023 12:17:35 -0400 Subject: [PATCH 3773/5631] NFS: Cleanup unused rpc_clnt variable The root rpc_clnt is not used here, clean it up. Fixes: 4dc73c679114 ("NFSv4: keep state manager thread active if swap is enabled") Signed-off-by: Benjamin Coddington Reviewed-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/nfs4state.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 660ccfaf463e..bbe49315d99e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1209,10 +1209,6 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) { struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; - struct rpc_clnt *cl = clp->cl_rpcclient; - - while (cl != cl->cl_parent) - cl = cl->cl_parent; set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); if (test_and_set_bit(NFS4CLNT_MANAGER_AVAILABLE, &clp->cl_state) != 0) { -- GitLab From a494aef23dfc732945cb42e22246a5c31174e4a5 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 20 Apr 2023 18:30:25 -0700 Subject: [PATCH 3774/5631] PCI: hv: Replace retarget_msi_interrupt_params with hyperv_pcpu_input_arg 4 commits are involved here: A (2016): commit 0de8ce3ee8e3 ("PCI: hv: Allocate physically contiguous hypercall params buffer") B (2017): commit be66b6736591 ("PCI: hv: Use page allocation for hbus structure") C (2019): commit 877b911a5ba0 ("PCI: hv: Avoid a kmemleak false positive caused by the hbus buffer") D (2018): commit 68bb7bfb7985 ("X86/Hyper-V: Enable IPI enlightenments") Patch D introduced the per-CPU hypercall input page "hyperv_pcpu_input_arg" in 2018. With patch D, we no longer need the per-Hyper-V-PCI-bus hypercall input page "hbus->retarget_msi_interrupt_params" that was added in patch A, and the issue addressed by patch B is no longer an issue, and we can also get rid of patch C. The change here is required for PCI device assignment to work for Confidential VMs (CVMs) running without a paravisor, because otherwise we would have to call set_memory_decrypted() for "hbus->retarget_msi_interrupt_params" before calling the hypercall HVCALL_RETARGET_INTERRUPT. Signed-off-by: Dexuan Cui Reviewed-by: Michael Kelley Acked-by: Lorenzo Pieralisi Link: https://lore.kernel.org/r/20230421013025.17152-1-decui@microsoft.com Signed-off-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 48 +++++------------------------ 1 file changed, 7 insertions(+), 41 deletions(-) diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 337f3b4a04fc..bc32662c6bb7 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -508,20 +508,11 @@ struct hv_pcibus_device { struct msi_domain_info msi_info; struct irq_domain *irq_domain; - spinlock_t retarget_msi_interrupt_lock; - struct workqueue_struct *wq; /* Highest slot of child device with resources allocated */ int wslot_res_allocated; bool use_calls; /* Use hypercalls to access mmio cfg space */ - - /* hypercall arg, must not cross page boundary */ - struct hv_retarget_device_interrupt retarget_msi_interrupt_params; - - /* - * Don't put anything here: retarget_msi_interrupt_params must be last - */ }; /* @@ -645,9 +636,9 @@ static void hv_arch_irq_unmask(struct irq_data *data) hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); int_desc = data->chip_data; - spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); + local_irq_save(flags); - params = &hbus->retarget_msi_interrupt_params; + params = *this_cpu_ptr(hyperv_pcpu_input_arg); memset(params, 0, sizeof(*params)); params->partition_id = HV_PARTITION_ID_SELF; params->int_entry.source = HV_INTERRUPT_SOURCE_MSI; @@ -680,7 +671,7 @@ static void hv_arch_irq_unmask(struct irq_data *data) if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) { res = 1; - goto exit_unlock; + goto out; } cpumask_and(tmp, dest, cpu_online_mask); @@ -689,7 +680,7 @@ static void hv_arch_irq_unmask(struct irq_data *data) if (nr_bank <= 0) { res = 1; - goto exit_unlock; + goto out; } /* @@ -708,8 +699,8 @@ static void hv_arch_irq_unmask(struct irq_data *data) res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17), params, NULL); -exit_unlock: - spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags); +out: + local_irq_restore(flags); /* * During hibernation, when a CPU is offlined, the kernel tries @@ -3598,35 +3589,11 @@ static int hv_pci_probe(struct hv_device *hdev, bool enter_d0_retry = true; int ret; - /* - * hv_pcibus_device contains the hypercall arguments for retargeting in - * hv_irq_unmask(). Those must not cross a page boundary. - */ - BUILD_BUG_ON(sizeof(*hbus) > HV_HYP_PAGE_SIZE); - bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); if (!bridge) return -ENOMEM; - /* - * With the recent 59bb47985c1d ("mm, sl[aou]b: guarantee natural - * alignment for kmalloc(power-of-two)"), kzalloc() is able to allocate - * a 4KB buffer that is guaranteed to be 4KB-aligned. Here the size and - * alignment of hbus is important because hbus's field - * retarget_msi_interrupt_params must not cross a 4KB page boundary. - * - * Here we prefer kzalloc to get_zeroed_page(), because a buffer - * allocated by the latter is not tracked and scanned by kmemleak, and - * hence kmemleak reports the pointer contained in the hbus buffer - * (i.e. the hpdev struct, which is created in new_pcichild_device() and - * is tracked by hbus->children) as memory leak (false positive). - * - * If the kernel doesn't have 59bb47985c1d, get_zeroed_page() *must* be - * used to allocate the hbus buffer and we can avoid the kmemleak false - * positive by using kmemleak_alloc() and kmemleak_free() to ask - * kmemleak to track and scan the hbus buffer. - */ - hbus = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + hbus = kzalloc(sizeof(*hbus), GFP_KERNEL); if (!hbus) return -ENOMEM; @@ -3683,7 +3650,6 @@ static int hv_pci_probe(struct hv_device *hdev, INIT_LIST_HEAD(&hbus->dr_list); spin_lock_init(&hbus->config_lock); spin_lock_init(&hbus->device_list_lock); - spin_lock_init(&hbus->retarget_msi_interrupt_lock); hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0, hbus->bridge->domain_nr); if (!hbus->wq) { -- GitLab From be41d814c6c7bbf3ffa66faeefa01f6cea8e3c98 Mon Sep 17 00:00:00 2001 From: Zqiang Date: Mon, 27 Mar 2023 20:00:19 +0800 Subject: [PATCH 3775/5631] kasan: fix lockdep report invalid wait context For kernels built with the following options and booting CONFIG_SLUB=y CONFIG_DEBUG_LOCKDEP=y CONFIG_PROVE_LOCKING=y CONFIG_PROVE_RAW_LOCK_NESTING=y [ 0.523115] [ BUG: Invalid wait context ] [ 0.523315] 6.3.0-rc1-yocto-standard+ #739 Not tainted [ 0.523649] ----------------------------- [ 0.523663] swapper/0/0 is trying to lock: [ 0.523663] ffff888035611360 (&c->lock){....}-{3:3}, at: put_cpu_partial+0x2e/0x1e0 [ 0.523663] other info that might help us debug this: [ 0.523663] context-{2:2} [ 0.523663] no locks held by swapper/0/0. [ 0.523663] stack backtrace: [ 0.523663] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.3.0-rc1-yocto-standard+ #739 [ 0.523663] Call Trace: [ 0.523663] [ 0.523663] dump_stack_lvl+0x64/0xb0 [ 0.523663] dump_stack+0x10/0x20 [ 0.523663] __lock_acquire+0x6c4/0x3c10 [ 0.523663] lock_acquire+0x188/0x460 [ 0.523663] put_cpu_partial+0x5a/0x1e0 [ 0.523663] __slab_free+0x39a/0x520 [ 0.523663] ___cache_free+0xa9/0xc0 [ 0.523663] qlist_free_all+0x7a/0x160 [ 0.523663] per_cpu_remove_cache+0x5c/0x70 [ 0.523663] __flush_smp_call_function_queue+0xfc/0x330 [ 0.523663] generic_smp_call_function_single_interrupt+0x13/0x20 [ 0.523663] __sysvec_call_function+0x86/0x2e0 [ 0.523663] sysvec_call_function+0x73/0x90 [ 0.523663] [ 0.523663] [ 0.523663] asm_sysvec_call_function+0x1b/0x20 [ 0.523663] RIP: 0010:default_idle+0x13/0x20 [ 0.523663] RSP: 0000:ffffffff83e07dc0 EFLAGS: 00000246 [ 0.523663] RAX: 0000000000000000 RBX: ffffffff83e1e200 RCX: ffffffff82a83293 [ 0.523663] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff8119a6b1 [ 0.523663] RBP: ffffffff83e07dc8 R08: 0000000000000001 R09: ffffed1006ac0d66 [ 0.523663] R10: ffff888035606b2b R11: ffffed1006ac0d65 R12: 0000000000000000 [ 0.523663] R13: ffffffff83e1e200 R14: ffffffff84a7d980 R15: 0000000000000000 [ 0.523663] default_idle_call+0x6c/0xa0 [ 0.523663] do_idle+0x2e1/0x330 [ 0.523663] cpu_startup_entry+0x20/0x30 [ 0.523663] rest_init+0x152/0x240 [ 0.523663] arch_call_rest_init+0x13/0x40 [ 0.523663] start_kernel+0x331/0x470 [ 0.523663] x86_64_start_reservations+0x18/0x40 [ 0.523663] x86_64_start_kernel+0xbb/0x120 [ 0.523663] secondary_startup_64_no_verify+0xe0/0xeb [ 0.523663] The local_lock_irqsave() is invoked in put_cpu_partial() and happens in IPI context, due to the CONFIG_PROVE_RAW_LOCK_NESTING=y (the LD_WAIT_CONFIG not equal to LD_WAIT_SPIN), so acquire local_lock in IPI context will trigger above calltrace. This commit therefore moves qlist_free_all() from hard-irq context to task context. Link: https://lkml.kernel.org/r/20230327120019.1027640-1-qiang1.zhang@intel.com Signed-off-by: Zqiang Acked-by: Marco Elver Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Signed-off-by: Andrew Morton --- mm/kasan/quarantine.c | 34 ++++++++-------------------------- 1 file changed, 8 insertions(+), 26 deletions(-) diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 75585077eb6d..152dca73f398 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -99,7 +99,6 @@ static unsigned long quarantine_size; static DEFINE_RAW_SPINLOCK(quarantine_lock); DEFINE_STATIC_SRCU(remove_cache_srcu); -#ifdef CONFIG_PREEMPT_RT struct cpu_shrink_qlist { raw_spinlock_t lock; struct qlist_head qlist; @@ -108,7 +107,6 @@ struct cpu_shrink_qlist { static DEFINE_PER_CPU(struct cpu_shrink_qlist, shrink_qlist) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(shrink_qlist.lock), }; -#endif /* Maximum size of the global queue. */ static unsigned long quarantine_max_size; @@ -319,16 +317,6 @@ static void qlist_move_cache(struct qlist_head *from, } } -#ifndef CONFIG_PREEMPT_RT -static void __per_cpu_remove_cache(struct qlist_head *q, void *arg) -{ - struct kmem_cache *cache = arg; - struct qlist_head to_free = QLIST_INIT; - - qlist_move_cache(q, &to_free, cache); - qlist_free_all(&to_free, cache); -} -#else static void __per_cpu_remove_cache(struct qlist_head *q, void *arg) { struct kmem_cache *cache = arg; @@ -340,7 +328,6 @@ static void __per_cpu_remove_cache(struct qlist_head *q, void *arg) qlist_move_cache(q, &sq->qlist, cache); raw_spin_unlock_irqrestore(&sq->lock, flags); } -#endif static void per_cpu_remove_cache(void *arg) { @@ -362,6 +349,8 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache) { unsigned long flags, i; struct qlist_head to_free = QLIST_INIT; + int cpu; + struct cpu_shrink_qlist *sq; /* * Must be careful to not miss any objects that are being moved from @@ -372,20 +361,13 @@ void kasan_quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); -#ifdef CONFIG_PREEMPT_RT - { - int cpu; - struct cpu_shrink_qlist *sq; - - for_each_online_cpu(cpu) { - sq = per_cpu_ptr(&shrink_qlist, cpu); - raw_spin_lock_irqsave(&sq->lock, flags); - qlist_move_cache(&sq->qlist, &to_free, cache); - raw_spin_unlock_irqrestore(&sq->lock, flags); - } - qlist_free_all(&to_free, cache); + for_each_online_cpu(cpu) { + sq = per_cpu_ptr(&shrink_qlist, cpu); + raw_spin_lock_irqsave(&sq->lock, flags); + qlist_move_cache(&sq->qlist, &to_free, cache); + raw_spin_unlock_irqrestore(&sq->lock, flags); } -#endif + qlist_free_all(&to_free, cache); raw_spin_lock_irqsave(&quarantine_lock, flags); for (i = 0; i < QUARANTINE_BATCHES; i++) { -- GitLab From 5a2f8d22ace4c8ac8798fab836dca7350fa710b1 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:12 -0400 Subject: [PATCH 3776/5631] mm/hugetlb: fix uffd-wp during fork() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm/hugetlb: More fixes around uffd-wp vs fork() / RO pins", v2. This patch (of 6): There're a bunch of things that were wrong: - Reading uffd-wp bit from a swap entry should use pte_swp_uffd_wp() rather than huge_pte_uffd_wp(). - When copying over a pte, we should drop uffd-wp bit when !EVENT_FORK (aka, when !userfaultfd_wp(dst_vma)). - When doing early CoW for private hugetlb (e.g. when the parent page was pinned), uffd-wp bit should be properly carried over if necessary. No bug reported probably because most people do not even care about these corner cases, but they are still bugs and can be exposed by the recent unit tests introduced, so fix all of them in one shot. Link: https://lkml.kernel.org/r/20230417195317.898696-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20230417195317.898696-2-peterx@redhat.com Fixes: bc70fbf269fd ("mm/hugetlb: handle uffd-wp during fork()") Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mika Penttilä Cc: Mike Kravetz Cc: Nadav Amit Cc: Signed-off-by: Andrew Morton --- mm/hugetlb.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a08fb47fb200..d105b0b6a274 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4953,11 +4953,15 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte) static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, - struct folio *new_folio) + struct folio *new_folio, pte_t old) { + pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); + __folio_mark_uptodate(new_folio); hugepage_add_new_anon_rmap(new_folio, vma, addr); - set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, &new_folio->page, 1)); + if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) + newpte = huge_pte_mkuffd_wp(newpte); + set_huge_pte_at(vma->vm_mm, addr, ptep, newpte); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } @@ -5032,14 +5036,12 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { - bool uffd_wp = huge_pte_uffd_wp(entry); - - if (!userfaultfd_wp(dst_vma) && uffd_wp) + if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); - bool uffd_wp = huge_pte_uffd_wp(entry); + bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* @@ -5050,10 +5052,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) - entry = huge_pte_mkuffd_wp(entry); + entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry); } - if (!userfaultfd_wp(dst_vma) && uffd_wp) + if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { @@ -5118,7 +5120,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, /* huge_ptep of dst_pte won't change as in child */ goto again; } - hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio); + hugetlb_install_folio(dst_vma, dst_pte, addr, + new_folio, src_pte_old); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; @@ -5136,6 +5139,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = huge_pte_wrprotect(entry); } + if (!userfaultfd_wp(dst_vma)) + entry = huge_pte_clear_uffd_wp(entry); + set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(npages, dst); } -- GitLab From 0f230bc24b6e1399b86b95642704a962d8aa40e6 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:13 -0400 Subject: [PATCH 3777/5631] mm/hugetlb: fix uffd-wp bit lost when unsharing happens MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we try to unshare a pinned page for a private hugetlb, uffd-wp bit can get lost during unsharing. When above condition met, one can lose uffd-wp bit on the privately mapped hugetlb page. It allows the page to be writable even if it should still be wr-protected. I assume it can mean data loss. This should be very rare, only if an unsharing happened on a private hugetlb page with uffd-wp protected (e.g. in a child which shares the same page with parent with UFFD_FEATURE_EVENT_FORK enabled). When I wrote the reproducer (provided in the last patch) I needed to use the newest gup_test cmd introduced by David to trigger it because I don't even know another way to do a proper RO longerm pin. Besides that, it needs a bunch of other conditions all met: (1) hugetlb being mapped privately, (2) userfaultfd registered with WP and EVENT_FORK, (3) the user app fork()s, then, (4) RO longterm pin onto a wr-protected anonymous page. If it's not impossible to hit in production I'd say extremely rare. Link: https://lkml.kernel.org/r/20230417195317.898696-3-peterx@redhat.com Fixes: 166f3ecc0daf ("mm/hugetlb: hook page faults for uffd write protection") Signed-off-by: Peter Xu Reported-by: Mike Kravetz Reviewed-by: David Hildenbrand Reviewed-by: Mike Kravetz Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mika Penttilä Cc: Nadav Amit Signed-off-by: Andrew Morton --- mm/hugetlb.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d105b0b6a274..7747160f6de8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5644,13 +5644,16 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma, spin_lock(ptl); ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { + pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); + /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); page_remove_rmap(old_page, vma, true); hugepage_add_new_anon_rmap(new_folio, vma, haddr); - set_huge_pte_at(mm, haddr, ptep, - make_huge_pte(vma, &new_folio->page, !unshare)); + if (huge_pte_uffd_wp(pte)) + newpte = huge_pte_mkuffd_wp(newpte); + set_huge_pte_at(mm, haddr, ptep, newpte); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = page_folio(old_page); -- GitLab From 21337f2af16cb36782ff5031f2553f9cf2f7c787 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:14 -0400 Subject: [PATCH 3778/5631] selftests/mm: add a few options for uffd-unit-test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Namely: "-f": add a wildcard filter for tests to run "-l": list tests rather than running any "-h": help msg Link: https://lkml.kernel.org/r/20230417195317.898696-4-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mika Penttilä Cc: Mike Kravetz Cc: Nadav Amit Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 52 +++++++++++++++++--- 1 file changed, 45 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index d871bf732e62..452ca05a829d 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -909,28 +909,65 @@ uffd_test_case_t uffd_tests[] = { }, }; +static void usage(const char *prog) +{ + printf("usage: %s [-f TESTNAME]\n", prog); + puts(""); + puts(" -f: test name to filter (e.g., event)"); + puts(" -h: show the help msg"); + puts(" -l: list tests only"); + puts(""); + exit(KSFT_FAIL); +} + int main(int argc, char *argv[]) { int n_tests = sizeof(uffd_tests) / sizeof(uffd_test_case_t); int n_mems = sizeof(mem_types) / sizeof(mem_type_t); + const char *test_filter = NULL; + bool list_only = false; uffd_test_case_t *test; mem_type_t *mem_type; uffd_test_args_t args; char test_name[128]; const char *errmsg; - int has_uffd; + int has_uffd, opt; int i, j; - has_uffd = test_uffd_api(false); - has_uffd |= test_uffd_api(true); + while ((opt = getopt(argc, argv, "f:hl")) != -1) { + switch (opt) { + case 'f': + test_filter = optarg; + break; + case 'l': + list_only = true; + break; + case 'h': + default: + /* Unknown */ + usage(argv[0]); + break; + } + } + + if (!test_filter && !list_only) { + has_uffd = test_uffd_api(false); + has_uffd |= test_uffd_api(true); - if (!has_uffd) { - printf("Userfaultfd not supported or unprivileged, skip all tests\n"); - exit(KSFT_SKIP); + if (!has_uffd) { + printf("Userfaultfd not supported or unprivileged, skip all tests\n"); + exit(KSFT_SKIP); + } } for (i = 0; i < n_tests; i++) { test = &uffd_tests[i]; + if (test_filter && !strstr(test->name, test_filter)) + continue; + if (list_only) { + printf("%s\n", test->name); + continue; + } for (j = 0; j < n_mems; j++) { mem_type = &mem_types[j]; if (!(test->mem_targets & mem_type->mem_flag)) @@ -952,7 +989,8 @@ int main(int argc, char *argv[]) } } - uffd_test_report(); + if (!list_only) + uffd_test_report(); return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS; } -- GitLab From cff294582798dce6ca2b2d08051f563c0f7a09c8 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:15 -0400 Subject: [PATCH 3779/5631] selftests/mm: extend and rename uffd pagemap test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend it to all types of mem, meanwhile add one parallel test when EVENT_FORK is enabled, where uffd-wp bits should be persisted rather than dropped. Since at it, rename the test to "wp-fork" to better show what it means. Making the new test called "wp-fork-with-event". Before: Testing pagemap on anon... done After: Testing wp-fork on anon... done Testing wp-fork on shmem... done Testing wp-fork on shmem-private... done Testing wp-fork on hugetlb... done Testing wp-fork on hugetlb-private... done Testing wp-fork-with-event on anon... done Testing wp-fork-with-event on shmem... done Testing wp-fork-with-event on shmem-private... done Testing wp-fork-with-event on hugetlb... done Testing wp-fork-with-event on hugetlb-private... done Link: https://lkml.kernel.org/r/20230417195317.898696-5-peterx@redhat.com Signed-off-by: Peter Xu Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Mika Penttilä Cc: Mike Kravetz Cc: Nadav Amit Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 130 +++++++++++++++---- 1 file changed, 106 insertions(+), 24 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 452ca05a829d..739fc4d30342 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -227,25 +227,65 @@ static int pagemap_open(void) err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ } while (0) -static int pagemap_test_fork(bool present) +typedef struct { + int parent_uffd, child_uffd; +} fork_event_args; + +static void *fork_event_consumer(void *data) { - pid_t child = fork(); + fork_event_args *args = data; + struct uffd_msg msg = { 0 }; + + /* Read until a full msg received */ + while (uffd_read_msg(args->parent_uffd, &msg)); + + if (msg.event != UFFD_EVENT_FORK) + err("wrong message: %u\n", msg.event); + + /* Just to be properly freed later */ + args->child_uffd = msg.arg.fork.ufd; + return NULL; +} + +static int pagemap_test_fork(int uffd, bool with_event) +{ + fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; + pthread_t thread; + pid_t child; uint64_t value; int fd, result; + /* Prepare a thread to resolve EVENT_FORK */ + if (with_event) { + if (pthread_create(&thread, NULL, fork_event_consumer, &args)) + err("pthread_create()"); + } + + child = fork(); if (!child) { /* Open the pagemap fd of the child itself */ fd = pagemap_open(); value = pagemap_get_entry(fd, area_dst); /* - * After fork() uffd-wp bit should be gone as long as we're - * without UFFD_FEATURE_EVENT_FORK + * After fork(), we should handle uffd-wp bit differently: + * + * (1) when with EVENT_FORK, it should persist + * (2) when without EVENT_FORK, it should be dropped */ - pagemap_check_wp(value, false); + pagemap_check_wp(value, with_event); /* Succeed */ exit(0); } waitpid(child, &result, 0); + + if (with_event) { + if (pthread_join(thread, NULL)) + err("pthread_join()"); + if (args.child_uffd < 0) + err("Didn't receive child uffd"); + close(args.child_uffd); + } + return result; } @@ -295,7 +335,8 @@ static void uffd_wp_unpopulated_test(uffd_test_args_t *args) uffd_test_pass(); } -static void uffd_pagemap_test(uffd_test_args_t *args) +static void uffd_wp_fork_test_common(uffd_test_args_t *args, + bool with_event) { int pagemap_fd; uint64_t value; @@ -311,23 +352,42 @@ static void uffd_pagemap_test(uffd_test_args_t *args) wp_range(uffd, (uint64_t)area_dst, page_size, true); value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(true)) - err("Detected stall uffd-wp bit in child"); - - /* Exclusive required or PAGEOUT won't work */ - if (!(value & PM_MMAP_EXCLUSIVE)) - err("multiple mapping detected: 0x%"PRIx64, value); + if (pagemap_test_fork(uffd, with_event)) { + uffd_test_fail("Detected %s uffd-wp bit in child in present pte", + with_event ? "missing" : "stall"); + goto out; + } - if (madvise(area_dst, page_size, MADV_PAGEOUT)) - err("madvise(MADV_PAGEOUT) failed"); + /* + * This is an attempt for zapping the pgtable so as to test the + * markers. + * + * For private mappings, PAGEOUT will only work on exclusive ptes + * (PM_MMAP_EXCLUSIVE) which we should satisfy. + * + * For shared, PAGEOUT may not work. Use DONTNEED instead which + * plays a similar role of zapping (rather than freeing the page) + * to expose pte markers. + */ + if (args->mem_type->shared) { + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("MADV_DONTNEED"); + } else { + /* + * NOTE: ignore retval because private-hugetlb doesn't yet + * support swapping, so it could fail. + */ + madvise(area_dst, page_size, MADV_PAGEOUT); + } /* Uffd-wp should persist even swapped out */ value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(false)) - err("Detected stall uffd-wp bit in child"); + if (pagemap_test_fork(uffd, with_event)) { + uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", + with_event ? "missing" : "stall"); + goto out; + } /* Unprotect; this tests swap pte modifications */ wp_range(uffd, (uint64_t)area_dst, page_size, false); @@ -338,9 +398,21 @@ static void uffd_pagemap_test(uffd_test_args_t *args) *area_dst = 2; value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, false); - - close(pagemap_fd); uffd_test_pass(); +out: + if (uffd_unregister(uffd, area_dst, nr_pages * page_size)) + err("unregister failed"); + close(pagemap_fd); +} + +static void uffd_wp_fork_test(uffd_test_args_t *args) +{ + uffd_wp_fork_test_common(args, false); +} + +static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) +{ + uffd_wp_fork_test_common(args, true); } static void check_memory_contents(char *p) @@ -836,10 +908,20 @@ uffd_test_case_t uffd_tests[] = { .uffd_feature_required = 0, }, { - .name = "pagemap", - .uffd_fn = uffd_pagemap_test, - .mem_targets = MEM_ANON, - .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP, + .name = "wp-fork", + .uffd_fn = uffd_wp_fork_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, + { + .name = "wp-fork-with-event", + .uffd_fn = uffd_wp_fork_with_event_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + /* when set, child process should inherit uffd-wp bits */ + UFFD_FEATURE_EVENT_FORK, }, { .name = "wp-unpopulated", -- GitLab From 71fc41eb98357d147fd26d3eb130ca9daf7a9bf3 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:16 -0400 Subject: [PATCH 3780/5631] selftests/mm: rename COW_EXTRA_LIBS to IOURING_EXTRA_LIBS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The macro and facility can be reused in other tests too. Make it general. Link: https://lkml.kernel.org/r/20230417195317.898696-6-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Mika Penttilä Cc: Mike Kravetz Cc: Nadav Amit Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/Makefile | 8 ++++---- tools/testing/selftests/mm/check_config.sh | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index de32f7dafa5d..63ed778ca8dc 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -161,8 +161,8 @@ warn_32bit_failure: endif endif -# cow_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. -$(OUTPUT)/cow: LDLIBS += $(COW_EXTRA_LIBS) +# IOURING_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. +$(OUTPUT)/cow: LDLIBS += $(IOURING_EXTRA_LIBS) $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap @@ -175,11 +175,11 @@ local_config.mk local_config.h: check_config.sh EXTRA_CLEAN += local_config.mk local_config.h -ifeq ($(COW_EXTRA_LIBS),) +ifeq ($(IOURING_EXTRA_LIBS),) all: warn_missing_liburing warn_missing_liburing: @echo ; \ - echo "Warning: missing liburing support. Some COW tests will be skipped." ; \ + echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif diff --git a/tools/testing/selftests/mm/check_config.sh b/tools/testing/selftests/mm/check_config.sh index bcba3af0acea..3954f4746161 100644 --- a/tools/testing/selftests/mm/check_config.sh +++ b/tools/testing/selftests/mm/check_config.sh @@ -21,11 +21,11 @@ $CC -c $tmpfile_c -o $tmpfile_o >/dev/null 2>&1 if [ -f $tmpfile_o ]; then echo "#define LOCAL_CONFIG_HAVE_LIBURING 1" > $OUTPUT_H_FILE - echo "COW_EXTRA_LIBS = -luring" > $OUTPUT_MKFILE + echo "IOURING_EXTRA_LIBS = -luring" > $OUTPUT_MKFILE else echo "// No liburing support found" > $OUTPUT_H_FILE echo "# No liburing support found, so:" > $OUTPUT_MKFILE - echo "COW_EXTRA_LIBS = " >> $OUTPUT_MKFILE + echo "IOURING_EXTRA_LIBS = " >> $OUTPUT_MKFILE fi rm ${tmpname}.* -- GitLab From 760aee0b71e34b4b9535e237347ff31b93961cbf Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Mon, 17 Apr 2023 15:53:17 -0400 Subject: [PATCH 3781/5631] selftests/mm: add tests for RO pinning vs fork() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a test suite (with 10 more sub-tests) to cover RO pinning against fork() over uffd-wp. It covers both: (1) Early CoW test in fork() when page pinned, (2) page unshare due to RO longterm pin. They are: Testing wp-fork-pin on anon... done Testing wp-fork-pin on shmem... done Testing wp-fork-pin on shmem-private... done Testing wp-fork-pin on hugetlb... done Testing wp-fork-pin on hugetlb-private... done Testing wp-fork-pin-with-event on anon... done Testing wp-fork-pin-with-event on shmem... done Testing wp-fork-pin-with-event on shmem-private... done Testing wp-fork-pin-with-event on hugetlb... done Testing wp-fork-pin-with-event on hugetlb-private... done CONFIG_GUP_TEST needed or they'll be skipped. Testing wp-fork-pin on anon... skipped [reason: Possibly CONFIG_GUP_TEST missing or unprivileged] Note that the major test goal is on private memory, but no hurt to also run all of them over shared because shared memory should work the same. Link: https://lkml.kernel.org/r/20230417195317.898696-7-peterx@redhat.com Signed-off-by: Peter Xu Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Mika Penttilä Cc: Mike Kravetz Cc: Nadav Amit Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/uffd-unit-tests.c | 144 ++++++++++++++++++- 1 file changed, 141 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 739fc4d30342..269c86768a02 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -7,6 +7,8 @@ #include "uffd-common.h" +#include "../../../../mm/gup_test.h" + #ifdef __NR_userfaultfd /* The unit test doesn't need a large or random size, make it 32MB for now */ @@ -247,7 +249,53 @@ static void *fork_event_consumer(void *data) return NULL; } -static int pagemap_test_fork(int uffd, bool with_event) +typedef struct { + int gup_fd; + bool pinned; +} pin_args; + +/* + * Returns 0 if succeed, <0 for errors. pin_pages() needs to be paired + * with unpin_pages(). Currently it needs to be RO longterm pin to satisfy + * all needs of the test cases (e.g., trigger unshare, trigger fork() early + * CoW, etc.). + */ +static int pin_pages(pin_args *args, void *buffer, size_t size) +{ + struct pin_longterm_test test = { + .addr = (uintptr_t)buffer, + .size = size, + /* Read-only pins */ + .flags = 0, + }; + + if (args->pinned) + err("already pinned"); + + args->gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (args->gup_fd < 0) + return -errno; + + if (ioctl(args->gup_fd, PIN_LONGTERM_TEST_START, &test)) { + /* Even if gup_test existed, can be an old gup_test / kernel */ + close(args->gup_fd); + return -errno; + } + args->pinned = true; + return 0; +} + +static void unpin_pages(pin_args *args) +{ + if (!args->pinned) + err("unpin without pin first"); + if (ioctl(args->gup_fd, PIN_LONGTERM_TEST_STOP)) + err("PIN_LONGTERM_TEST_STOP"); + close(args->gup_fd); + args->pinned = false; +} + +static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) { fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; pthread_t thread; @@ -264,7 +312,17 @@ static int pagemap_test_fork(int uffd, bool with_event) child = fork(); if (!child) { /* Open the pagemap fd of the child itself */ + pin_args args = {}; + fd = pagemap_open(); + + if (test_pin && pin_pages(&args, area_dst, page_size)) + /* + * Normally when reach here we have pinned in + * previous tests, so shouldn't fail anymore + */ + err("pin page failed in child"); + value = pagemap_get_entry(fd, area_dst); /* * After fork(), we should handle uffd-wp bit differently: @@ -273,6 +331,8 @@ static int pagemap_test_fork(int uffd, bool with_event) * (2) when without EVENT_FORK, it should be dropped */ pagemap_check_wp(value, with_event); + if (test_pin) + unpin_pages(&args); /* Succeed */ exit(0); } @@ -352,7 +412,7 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args, wp_range(uffd, (uint64_t)area_dst, page_size, true); value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event)) { + if (pagemap_test_fork(uffd, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in present pte", with_event ? "missing" : "stall"); goto out; @@ -383,7 +443,7 @@ static void uffd_wp_fork_test_common(uffd_test_args_t *args, /* Uffd-wp should persist even swapped out */ value = pagemap_get_entry(pagemap_fd, area_dst); pagemap_check_wp(value, true); - if (pagemap_test_fork(uffd, with_event)) { + if (pagemap_test_fork(uffd, with_event, false)) { uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", with_event ? "missing" : "stall"); goto out; @@ -415,6 +475,68 @@ static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) uffd_wp_fork_test_common(args, true); } +static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, + bool with_event) +{ + int pagemap_fd; + pin_args pin_args = {}; + + if (uffd_register(uffd, area_dst, page_size, false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Touch the page */ + *area_dst = 1; + wp_range(uffd, (uint64_t)area_dst, page_size, true); + + /* + * 1. First pin, then fork(). This tests fork() special path when + * doing early CoW if the page is private. + */ + if (pin_pages(&pin_args, area_dst, page_size)) { + uffd_test_skip("Possibly CONFIG_GUP_TEST missing " + "or unprivileged"); + close(pagemap_fd); + uffd_unregister(uffd, area_dst, page_size); + return; + } + + if (pagemap_test_fork(uffd, with_event, false)) { + uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()", + with_event ? "missing" : "stall"); + unpin_pages(&pin_args); + goto out; + } + + unpin_pages(&pin_args); + + /* + * 2. First fork(), then pin (in the child, where test_pin==true). + * This tests COR, aka, page unsharing on private memories. + */ + if (pagemap_test_fork(uffd, with_event, true)) { + uffd_test_fail("Detected %s uffd-wp bit when RO pin", + with_event ? "missing" : "stall"); + goto out; + } + uffd_test_pass(); +out: + if (uffd_unregister(uffd, area_dst, page_size)) + err("register failed"); + close(pagemap_fd); +} + +static void uffd_wp_fork_pin_test(uffd_test_args_t *args) +{ + uffd_wp_fork_pin_test_common(args, false); +} + +static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args) +{ + uffd_wp_fork_pin_test_common(args, true); +} + static void check_memory_contents(char *p) { unsigned long i, j; @@ -923,6 +1045,22 @@ uffd_test_case_t uffd_tests[] = { /* when set, child process should inherit uffd-wp bits */ UFFD_FEATURE_EVENT_FORK, }, + { + .name = "wp-fork-pin", + .uffd_fn = uffd_wp_fork_pin_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, + { + .name = "wp-fork-pin-with-event", + .uffd_fn = uffd_wp_fork_pin_with_event_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + /* when set, child process should inherit uffd-wp bits */ + UFFD_FEATURE_EVENT_FORK, + }, { .name = "wp-unpopulated", .uffd_fn = uffd_wp_unpopulated_test, -- GitLab From 465e5e6a1698f3325f5d2262d2875779b06b50c7 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:15 +0200 Subject: [PATCH 3782/5631] fs/buffer: add folio_set_bh helper Patch series "convert create_page_buffers to folio_create_buffers". One of the first kernel panic we hit when we try to increase the block size > 4k is inside create_page_buffers()[1]. Even though buffer.c function do not support large folios (folios > PAGE_SIZE) at the moment, these changes are required when we want to remove that constraint. This patch (of 4): The folio version of set_bh_page(). This is required to convert create_page_buffers() to folio_create_buffers() later in the series. Link: https://lkml.kernel.org/r/20230417123618.22094-1-p.raghav@samsung.com Link: https://lkml.kernel.org/r/20230417123618.22094-2-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- fs/buffer.c | 15 +++++++++++++++ include/linux/buffer_head.h | 2 ++ 2 files changed, 17 insertions(+) diff --git a/fs/buffer.c b/fs/buffer.c index 9e1e2add541e..009d950fbf42 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1485,6 +1485,21 @@ void set_bh_page(struct buffer_head *bh, } EXPORT_SYMBOL(set_bh_page); +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset) +{ + bh->b_folio = folio; + BUG_ON(offset >= folio_size(folio)); + if (folio_test_highmem(folio)) + /* + * This catches illegal uses and preserves the offset: + */ + bh->b_data = (char *)(0 + offset); + else + bh->b_data = folio_address(folio) + offset; +} +EXPORT_SYMBOL(folio_set_bh); + /* * Called when truncating a buffer on a page completely. */ diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8f14dca5fed7..7e92d23f4782 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -196,6 +196,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset); bool try_to_free_buffers(struct folio *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); -- GitLab From c71124a8afa441af203d2001a92c91f114446687 Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:16 +0200 Subject: [PATCH 3783/5631] buffer: add folio_alloc_buffers() helper Folio version of alloc_page_buffers() helper. This is required to convert create_page_buffers() to folio_create_buffers() later in the series. alloc_page_buffers() has been modified to call folio_alloc_buffers() which adds one call to compound_head() but folio_alloc_buffers() removes one call to compound_head() compared to the existing alloc_page_buffers() implementation. Link: https://lkml.kernel.org/r/20230417123618.22094-3-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- fs/buffer.c | 23 +++++++++++++++-------- include/linux/buffer_head.h | 2 ++ 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 009d950fbf42..bbd4aa670262 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -843,7 +843,7 @@ int remove_inode_buffers(struct inode *inode) } /* - * Create the appropriate buffers when given a page for data area and + * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. @@ -851,8 +851,8 @@ int remove_inode_buffers(struct inode *inode) * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ -struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - bool retry) +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + bool retry) { struct buffer_head *bh, *head; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; @@ -862,12 +862,12 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, if (retry) gfp |= __GFP_NOFAIL; - /* The page lock pins the memcg */ - memcg = page_memcg(page); + /* The folio lock pins the memcg */ + memcg = folio_memcg(folio); old_memcg = set_active_memcg(memcg); head = NULL; - offset = PAGE_SIZE; + offset = folio_size(folio); while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) @@ -879,8 +879,8 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bh->b_size = size; - /* Link the buffer to its page */ - set_bh_page(bh, page, offset); + /* Link the buffer to its folio */ + folio_set_bh(bh, folio, offset); } out: set_active_memcg(old_memcg); @@ -899,6 +899,13 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, goto out; } +EXPORT_SYMBOL_GPL(folio_alloc_buffers); + +struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, + bool retry) +{ + return folio_alloc_buffers(page_folio(page), size, retry); +} EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 7e92d23f4782..0b14eab41bd1 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -199,6 +199,8 @@ void set_bh_page(struct buffer_head *bh, void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset); bool try_to_free_buffers(struct folio *); +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + bool retry); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, -- GitLab From 8e2e17560bed73c2a73c94cbe378719f6cf850ee Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:17 +0200 Subject: [PATCH 3784/5631] fs/buffer: add folio_create_empty_buffers helper Folio version of create_empty_buffers(). This is required to convert create_page_buffers() to folio_create_buffers() later in the series. It removes several calls to compound_head() as it works directly on folio compared to create_empty_buffers(). Hence, create_empty_buffers() has been modified to call folio_create_empty_buffers(). Link: https://lkml.kernel.org/r/20230417123618.22094-4-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- fs/buffer.c | 28 +++++++++++++++++----------- include/linux/buffer_head.h | 2 ++ 2 files changed, 19 insertions(+), 11 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index bbd4aa670262..e6266bf7eeea 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1594,18 +1594,17 @@ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) } EXPORT_SYMBOL(block_invalidate_folio); - /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via private_lock. try_to_free_buffers - * is already excluded via the page lock. + * is already excluded via the folio lock. */ -void create_empty_buffers(struct page *page, - unsigned long blocksize, unsigned long b_state) +void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, + unsigned long b_state) { struct buffer_head *bh, *head, *tail; - head = alloc_page_buffers(page, blocksize, true); + head = folio_alloc_buffers(folio, blocksize, true); bh = head; do { bh->b_state |= b_state; @@ -1614,19 +1613,26 @@ void create_empty_buffers(struct page *page, } while (bh); tail->b_this_page = head; - spin_lock(&page->mapping->private_lock); - if (PageUptodate(page) || PageDirty(page)) { + spin_lock(&folio->mapping->private_lock); + if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { - if (PageDirty(page)) + if (folio_test_dirty(folio)) set_buffer_dirty(bh); - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } - attach_page_private(page, head); - spin_unlock(&page->mapping->private_lock); + folio_attach_private(folio, head); + spin_unlock(&folio->mapping->private_lock); +} +EXPORT_SYMBOL(folio_create_empty_buffers); + +void create_empty_buffers(struct page *page, + unsigned long blocksize, unsigned long b_state) +{ + folio_create_empty_buffers(page_folio(page), blocksize, b_state); } EXPORT_SYMBOL(create_empty_buffers); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 0b14eab41bd1..1520793c72da 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); +void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, + unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); -- GitLab From c6c8c3e7b47d7d20952202e7568389a5e3b043dd Mon Sep 17 00:00:00 2001 From: Pankaj Raghav Date: Mon, 17 Apr 2023 14:36:18 +0200 Subject: [PATCH 3785/5631] fs/buffer: convert create_page_buffers to folio_create_buffers fs/buffer do not support large folios as there are many assumptions on the folio size to be the host page size. This conversion is one step towards removing that assumption. Also this conversion will reduce calls to compound_head() if folio_create_buffers() calls folio_create_empty_buffers(). Link: https://lkml.kernel.org/r/20230417123618.22094-5-p.raghav@samsung.com Signed-off-by: Pankaj Raghav Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Hannes Reinecke Cc: Alexander Viro Cc: Christian Brauner Cc: Luis Chamberlain Signed-off-by: Andrew Morton --- fs/buffer.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index e6266bf7eeea..b0b8c5fba691 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1723,14 +1723,17 @@ static inline int block_size_bits(unsigned int blocksize) return ilog2(blocksize); } -static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) +static struct buffer_head *folio_create_buffers(struct folio *folio, + struct inode *inode, + unsigned int b_state) { - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), - b_state); - return page_buffers(page); + if (!folio_buffers(folio)) + folio_create_empty_buffers(folio, + 1 << READ_ONCE(inode->i_blkbits), + b_state); + return folio_buffers(folio); } /* @@ -1774,8 +1777,8 @@ int __block_write_full_page(struct inode *inode, struct page *page, int nr_underway = 0; blk_opf_t write_flags = wbc_to_write_flags(wbc); - head = create_page_buffers(page, inode, - (1 << BH_Dirty)|(1 << BH_Uptodate)); + head = folio_create_buffers(page_folio(page), inode, + (1 << BH_Dirty) | (1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from block_dirty_folio @@ -2038,7 +2041,7 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); - head = create_page_buffers(&folio->page, inode, 0); + head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); @@ -2324,7 +2327,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block) VM_BUG_ON_FOLIO(folio_test_large(folio), folio); - head = create_page_buffers(&folio->page, inode, 0); + head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); -- GitLab From 4bf4f155bfbc77a12ad2c9e12d9f57718adb9a5c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 17 Apr 2023 19:48:07 +0800 Subject: [PATCH 3786/5631] mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list() Both of them change the arg from page_list to folio_list when convert them to use a folio, but not the declaration, let's correct it, also move the reclaim_pages() from swap.h to internal.h as it only used in mm. Link: https://lkml.kernel.org/r/20230417114807.186786-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviwed-by: Matthew Wilcox (Oracle) Reviewed-by: SeongJae Park Reviewed-by: David Hildenbrand Cc: Hugh Dickins Signed-off-by: Andrew Morton --- include/linux/swap.h | 1 - mm/internal.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 7f7d5b9ddf7e..3c69cb653cb9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -442,7 +442,6 @@ extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); -extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; diff --git a/mm/internal.h b/mm/internal.h index 6483db57a31f..68410c6d97ac 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -783,8 +783,9 @@ extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); +unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, - struct list_head *page_list); + struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW -- GitLab From 13215e8a4bb336dac2af561d4f5c34a071810ee4 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Mon, 17 Apr 2023 11:52:26 +0800 Subject: [PATCH 3787/5631] lib/show_mem.c: use for_each_populated_zone() simplify code __show_mem() needs to iterate over all zones that have memory, we can simplify the code by using for_each_populated_zone(). Link: https://lkml.kernel.org/r/20230417035226.4013584-1-yajun.deng@linux.dev Signed-off-by: Yajun Deng Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton --- lib/show_mem.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/lib/show_mem.c b/lib/show_mem.c index 0d7585cde2a6..1485c87be935 100644 --- a/lib/show_mem.c +++ b/lib/show_mem.c @@ -10,26 +10,19 @@ void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { - pg_data_t *pgdat; unsigned long total = 0, reserved = 0, highmem = 0; + struct zone *zone; printk("Mem-Info:\n"); __show_free_areas(filter, nodemask, max_zone_idx); - for_each_online_pgdat(pgdat) { - int zoneid; + for_each_populated_zone(zone) { - for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { - struct zone *zone = &pgdat->node_zones[zoneid]; - if (!populated_zone(zone)) - continue; + total += zone->present_pages; + reserved += zone->present_pages - zone_managed_pages(zone); - total += zone->present_pages; - reserved += zone->present_pages - zone_managed_pages(zone); - - if (is_highmem_idx(zoneid)) - highmem += zone->present_pages; - } + if (is_highmem(zone)) + highmem += zone->present_pages; } printk("%lu pages RAM\n", total); -- GitLab From 686ea6e61da61e46ae7068f73167ca26e0c67efb Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Mon, 17 Apr 2023 08:39:19 +0800 Subject: [PATCH 3788/5631] userfaultfd: use helper function range_in_vma() We can use range_in_vma() to check if dst_start, dst_start + len are within the dst_vma range. Minor readability improvement. Link: https://lkml.kernel.org/r/20230417003919.930515-1-zhangpeng362@huawei.com Signed-off-by: ZhangPeng Reviewed-by: David Hildenbrand Cc: Kefeng Wang Cc: Mike Kravetz Cc: Nanyong Sun Signed-off-by: Andrew Morton --- mm/userfaultfd.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 11cfd82c6726..e97a0b4889fc 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -31,11 +31,7 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, struct vm_area_struct *dst_vma; dst_vma = find_vma(dst_mm, dst_start); - if (!dst_vma) - return NULL; - - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) + if (!range_in_vma(dst_vma, dst_start, dst_start + len)) return NULL; /* -- GitLab From 851ae6424697d1c4f085cb878c88168923ebcad1 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 17 Apr 2023 07:59:29 +0800 Subject: [PATCH 3789/5631] migrate_pages_batch: fix statistics for longterm pin retry In commit fd4a7ac32918 ("mm: migrate: try again if THP split is failed due to page refcnt"), if the THP splitting fails due to page reference count, we will retry to improve migration successful rate. But the failed splitting is counted as migration failure and migration retry, which will cause duplicated failure counting. So, in this patch, this is fixed via undoing the failure counting if we decide to retry. The patch is tested via failure injection. Link: https://lkml.kernel.org/r/20230416235929.1040194-1-ying.huang@intel.com Fixes: fd4a7ac32918 ("mm: migrate: try again if THP split is failed due to page refcnt") Signed-off-by: "Huang, Ying" Reviewed-by: Baolin Wang Cc: Alistair Popple Cc: David Hildenbrand Cc: Yang Shi Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/migrate.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/migrate.c b/mm/migrate.c index 41f2154d66ad..5d95e09b1618 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1710,6 +1710,9 @@ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page, large_retry++; thp_retry += is_thp; nr_retry_pages += nr_pages; + /* Undo duplicated failure counting. */ + nr_large_failed--; + stats->nr_thp_failed -= is_thp; break; } } -- GitLab From f3ebdf042df4e08bab1d5f8bf1c4b959d8741c10 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 18 Apr 2023 16:21:13 +0200 Subject: [PATCH 3790/5631] mm: don't check VMA write permissions if the PTE/PMD indicates write permissions Staring at the comment "Recheck VMA as permissions can change since migration started" in remove_migration_pte() can result in confusion, because if the source PTE/PMD indicates write permissions, then there should be no need to check VMA write permissions when restoring migration entries or PTE-mapping a PMD. Commit d3cb8bf6081b ("mm: migrate: Close race between migration completion and mprotect") introduced the maybe_mkwrite() handling in remove_migration_pte() in 2014, stating that a race between mprotect() and migration finishing would be possible, and that we could end up with a writable PTE that should be readable. However, mprotect() code first updates vma->vm_flags / vma->vm_page_prot and then walks the page tables to (a) set all present writable PTEs to read-only and (b) convert all writable migration entries to readable migration entries. While walking the page tables and modifying the entries, migration code has to grab the PT locks to synchronize against concurrent page table modifications. Assuming migration would find a writable migration entry (while holding the PT lock) and replace it with a writable present PTE, surely mprotect() code didn't stumble over the writable migration entry yet (converting it into a readable migration entry) and would instead wait for the PT lock to convert the now present writable PTE into a read-only PTE. As mprotect() didn't finish yet, the behavior is just like migration didn't happen: a writable PTE will be converted to a read-only PTE. So it's fine to rely on the writability information in the source PTE/PMD and not recheck against the VMA as long as we're holding the PT lock to synchronize with anyone who concurrently wants to downgrade write permissions (like mprotect()) by first adjusting vma->vm_flags / vma->vm_page_prot to then walk over the page tables to adjust the page table entries. Running test cases that should reveal such races -- mprotect(PROT_READ) racing with page migration or THP splitting -- for multiple hours did not reveal an issue with this cleanup. Link: https://lkml.kernel.org/r/20230418142113.439494-1-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Kirill A. Shutemov Reviewed-by: Alistair Popple Cc: Mel Gorman Cc: Peter Xu Signed-off-by: Andrew Morton --- mm/huge_memory.c | 4 ++-- mm/migrate.c | 5 +---- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c23fa39dec92..624671aaa60d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2234,7 +2234,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } else { entry = mk_pte(page + i, READ_ONCE(vma->vm_page_prot)); if (write) - entry = maybe_mkwrite(entry, vma); + entry = pte_mkwrite(entry); if (anon_exclusive) SetPageAnonExclusive(page + i); if (!young) @@ -3271,7 +3271,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) - pmde = maybe_pmd_mkwrite(pmde, vma); + pmde = pmd_mkwrite(pmde); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_mkuffd_wp(pmde); if (!is_migration_entry_young(entry)) diff --git a/mm/migrate.c b/mm/migrate.c index 5d95e09b1618..02cace7955d4 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -213,16 +213,13 @@ static bool remove_migration_pte(struct folio *folio, if (pte_swp_soft_dirty(*pvmw.pte)) pte = pte_mksoft_dirty(pte); - /* - * Recheck VMA as permissions can change since migration started - */ entry = pte_to_swp_entry(*pvmw.pte); if (!is_migration_entry_young(entry)) pte = pte_mkold(pte); if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) pte = pte_mkdirty(pte); if (is_writable_migration_entry(entry)) - pte = maybe_mkwrite(pte, vma); + pte = pte_mkwrite(pte); else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); -- GitLab From 2124f79de6a909630d1a62b01ecc32db9f967181 Mon Sep 17 00:00:00 2001 From: John Keeping Date: Tue, 18 Apr 2023 11:19:05 +0100 Subject: [PATCH 3791/5631] mm: shrinkers: fix debugfs file permissions The permissions for the files here are swapped as "count" is read-only and "scan" is write-only. While this doesn't really matter as these permissions don't stop the files being opened for reading/writing as appropriate, they are shown by "ls -l" and are confusing. Link: https://lkml.kernel.org/r/20230418101906.3131303-1-john@metanate.com Signed-off-by: John Keeping Signed-off-by: Andrew Morton --- mm/shrinker_debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index fdd155fd35ed..3f83b10c5031 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -189,9 +189,9 @@ int shrinker_debugfs_add(struct shrinker *shrinker) } shrinker->debugfs_entry = entry; - debugfs_create_file("count", 0220, entry, shrinker, + debugfs_create_file("count", 0440, entry, shrinker, &shrinker_debugfs_count_fops); - debugfs_create_file("scan", 0440, entry, shrinker, + debugfs_create_file("scan", 0220, entry, shrinker, &shrinker_debugfs_scan_fops); return 0; } -- GitLab From d7597f59d1d33e9efbffa7060deb9ee5bd119e62 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:40 -0700 Subject: [PATCH 3792/5631] mm: add new api to enable ksm per process Patch series "mm: process/cgroup ksm support", v9. So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. Use case 1: The madvise call is not available in the programming language. An example for this are programs with forked workloads using a garbage collected language without pointers. In such a language madvise cannot be made available. In addition the addresses of objects get moved around as they are garbage collected. KSM sharing needs to be enabled "from the outside" for these type of workloads. Use case 2: The same interpreter can also be used for workloads where KSM brings no benefit or even has overhead. We'd like to be able to enable KSM on a workload by workload basis. Use case 3: With the madvise call sharing opportunities are only enabled for the current process: it is a workload-local decision. A considerable number of sharing opportunities may exist across multiple workloads or jobs (if they are part of the same security domain). Only a higler level entity like a job scheduler or container can know for certain if its running one or more instances of a job. That job scheduler however doesn't have the necessary internal workload knowledge to make targeted madvise calls. Security concerns: In previous discussions security concerns have been brought up. The problem is that an individual workload does not have the knowledge about what else is running on a machine. Therefore it has to be very conservative in what memory areas can be shared or not. However, if the system is dedicated to running multiple jobs within the same security domain, its the job scheduler that has the knowledge that sharing can be safely enabled and is even desirable. Performance: Experiments with using UKSM have shown a capacity increase of around 20%. Here are the metrics from an instagram workload (taken from a machine with 64GB main memory): full_scans: 445 general_profit: 20158298048 max_page_sharing: 256 merge_across_nodes: 1 pages_shared: 129547 pages_sharing: 5119146 pages_to_scan: 4000 pages_unshared: 1760924 pages_volatile: 10761341 run: 1 sleep_millisecs: 20 stable_node_chains: 167 stable_node_chains_prune_millisecs: 2000 stable_node_dups: 2751 use_zero_pages: 0 zero_pages_sharing: 0 After the service is running for 30 minutes to an hour, 4 to 5 million shared pages are common for this workload when using KSM. Detailed changes: 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 3. Add general_profit metric The general_profit metric of KSM is specified in the documentation, but not calculated. This adds the general profit metric to /sys/kernel/debug/mm/ksm. 4. Add more metrics to ksm_stat This adds the process profit metric to /proc//ksm_stat. 5. Add more tests to ksm_tests and ksm_functional_tests This adds an option to specify the merge type to the ksm_tests. This allows to test madvise and prctl KSM. It also adds a two new tests to ksm_functional_tests: one to test the new prctl options and the other one is a fork test to verify that the KSM process setting is inherited by client processes. This patch (of 3): So far KSM can only be enabled by calling madvise for memory regions. To be able to use KSM for more workloads, KSM needs to have the ability to be enabled / disabled at the process / cgroup level. 1. New options for prctl system command This patch series adds two new options to the prctl system call. The first one allows to enable KSM at the process level and the second one to query the setting. The setting will be inherited by child processes. With the above setting, KSM can be enabled for the seed process of a cgroup and all processes in the cgroup will inherit the setting. 2. Changes to KSM processing When KSM is enabled at the process level, the KSM code will iterate over all the VMA's and enable KSM for the eligible VMA's. When forking a process that has KSM enabled, the setting will be inherited by the new child process. 1) Introduce new MMF_VM_MERGE_ANY flag This introduces the new flag MMF_VM_MERGE_ANY flag. When this flag is set, kernel samepage merging (ksm) gets enabled for all vma's of a process. 2) Setting VM_MERGEABLE on VMA creation When a VMA is created, if the MMF_VM_MERGE_ANY flag is set, the VM_MERGEABLE flag will be set for this VMA. 3) support disabling of ksm for a process This adds the ability to disable ksm for a process if ksm has been enabled for the process with prctl. 4) add new prctl option to get and set ksm for a process This adds two new options to the prctl system call - enable ksm for all vmas of a process (if the vmas support it). - query if ksm has been enabled for a process. 3. Disabling MMF_VM_MERGE_ANY for storage keys in s390 In the s390 architecture when storage keys are used, the MMF_VM_MERGE_ANY will be disabled. Link: https://lkml.kernel.org/r/20230418051342.1919757-1-shr@devkernel.io Link: https://lkml.kernel.org/r/20230418051342.1919757-2-shr@devkernel.io Signed-off-by: Stefan Roesch Acked-by: David Hildenbrand Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Bagas Sanjaya Signed-off-by: Andrew Morton --- arch/s390/mm/gmap.c | 7 +++ include/linux/ksm.h | 21 ++++++- include/linux/sched/coredump.h | 1 + include/uapi/linux/prctl.h | 2 + kernel/sys.c | 27 +++++++++ mm/ksm.c | 104 +++++++++++++++++++++++++++------ mm/mmap.c | 3 + 7 files changed, 146 insertions(+), 19 deletions(-) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 5a716bdcba05..0949811761e6 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2591,6 +2591,13 @@ int gmap_mark_unmergeable(void) int ret; VMA_ITERATOR(vmi, mm, 0); + /* + * Make sure to disable KSM (if enabled for the whole process or + * individual VMAs). Note that nothing currently hinders user space + * from re-enabling it. + */ + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); + for_each_vma(vmi, vma) { /* Copy vm_flags to avoid partial modifications in ksm_madvise */ vm_flags = vma->vm_flags; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index d9e701326a88..4647b0c70c12 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -18,13 +18,26 @@ #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); + +void ksm_add_vma(struct vm_area_struct *vma); +int ksm_enable_merge_any(struct mm_struct *mm); + int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); + int ret; + + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { + ret = __ksm_enter(mm); + if (ret) + return ret; + } + + if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) + set_bit(MMF_VM_MERGE_ANY, &mm->flags); + return 0; } @@ -57,6 +70,10 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill, #endif #else /* !CONFIG_KSM */ +static inline void ksm_add_vma(struct vm_area_struct *vma) +{ +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0e17ae7fbfd3..0ee96ea7a0e9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) +#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index b99c0be72577..f23d9a16507f 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -292,4 +292,6 @@ struct prctl_mm_map { #define PR_GET_AUXV 0x41555856 +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 26c1399e0654..72cdb16e2636 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -2687,6 +2688,32 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; +#ifdef CONFIG_KSM + case PR_SET_MEMORY_MERGE: + if (arg3 || arg4 || arg5) + return -EINVAL; + if (mmap_write_lock_killable(me->mm)) + return -EINTR; + + if (arg2) { + error = ksm_enable_merge_any(me->mm); + } else { + /* + * TODO: we might want disable KSM on all VMAs and + * trigger unsharing to completely disable KSM. + */ + clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); + error = 0; + } + mmap_write_unlock(me->mm); + break; + case PR_GET_MEMORY_MERGE: + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags); + break; +#endif default: error = -EINVAL; break; diff --git a/mm/ksm.c b/mm/ksm.c index 37c63310bc4e..35ac6c741572 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -515,6 +515,28 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } +static bool vma_ksm_compatible(struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP | + VM_IO | VM_DONTEXPAND | VM_HUGETLB | + VM_MIXEDMAP)) + return false; /* just ignore the advice */ + + if (vma_is_dax(vma)) + return false; + +#ifdef VM_SAO + if (vma->vm_flags & VM_SAO) + return false; +#endif +#ifdef VM_SPARC_ADI + if (vma->vm_flags & VM_SPARC_ADI) + return false; +#endif + + return true; +} + static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, unsigned long addr) { @@ -1026,6 +1048,7 @@ static int unmerge_and_remove_all_rmap_items(void) mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmdrop(mm); } else spin_unlock(&ksm_mmlist_lock); @@ -2408,6 +2431,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) mm_slot_free(mm_slot_cache, mm_slot); clear_bit(MMF_VM_MERGEABLE, &mm->flags); + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); mmap_read_unlock(mm); mmdrop(mm); } else { @@ -2485,6 +2509,66 @@ static int ksm_scan_thread(void *nothing) return 0; } +static void __ksm_add_vma(struct vm_area_struct *vma) +{ + unsigned long vm_flags = vma->vm_flags; + + if (vm_flags & VM_MERGEABLE) + return; + + if (vma_ksm_compatible(vma)) + vm_flags_set(vma, VM_MERGEABLE); +} + +/** + * ksm_add_vma - Mark vma as mergeable if compatible + * + * @vma: Pointer to vma + */ +void ksm_add_vma(struct vm_area_struct *vma) +{ + struct mm_struct *mm = vma->vm_mm; + + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + __ksm_add_vma(vma); +} + +static void ksm_add_vmas(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) + __ksm_add_vma(vma); +} + +/** + * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all + * compatible VMA's + * + * @mm: Pointer to mm + * + * Returns 0 on success, otherwise error code + */ +int ksm_enable_merge_any(struct mm_struct *mm) +{ + int err; + + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return 0; + + if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { + err = __ksm_enter(mm); + if (err) + return err; + } + + set_bit(MMF_VM_MERGE_ANY, &mm->flags); + ksm_add_vmas(mm); + + return 0; +} + int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { @@ -2493,25 +2577,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, switch (advice) { case MADV_MERGEABLE: - /* - * Be somewhat over-protective for now! - */ - if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | - VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_MIXEDMAP)) - return 0; /* just ignore the advice */ - - if (vma_is_dax(vma)) + if (vma->vm_flags & VM_MERGEABLE) return 0; - -#ifdef VM_SAO - if (*vm_flags & VM_SAO) + if (!vma_ksm_compatible(vma)) return 0; -#endif -#ifdef VM_SPARC_ADI - if (*vm_flags & VM_SPARC_ADI) - return 0; -#endif if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) { err = __ksm_enter(mm); @@ -2615,6 +2684,7 @@ void __ksm_exit(struct mm_struct *mm) if (easy_to_free) { mm_slot_free(mm_slot_cache, mm_slot); + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); clear_bit(MMF_VM_MERGEABLE, &mm->flags); mmdrop(mm); } else if (mm_slot) { diff --git a/mm/mmap.c b/mm/mmap.c index 790cc62c0038..51b6976fd525 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include @@ -2729,6 +2730,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (file && vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); file = vma->vm_file; + ksm_add_vma(vma); expanded: perf_event_mmap(vma); @@ -3001,6 +3003,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, goto mas_store_fail; mm->map_count++; + ksm_add_vma(vma); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; -- GitLab From d21077fbc2fc987c2e593c34dc3b4d84e546dc9f Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:41 -0700 Subject: [PATCH 3793/5631] mm: add new KSM process and sysfs knobs This adds the general_profit KSM sysfs knob and the process profit metric knobs to ksm_stat. 1) expose general_profit metric The documentation mentions a general profit metric, however this metric is not calculated. In addition the formula depends on the size of internal structures, which makes it more difficult for an administrator to make the calculation. Adding the metric for a better user experience. 2) document general_profit sysfs knob 3) calculate ksm process profit metric The ksm documentation mentions the process profit metric and how to calculate it. This adds the calculation of the metric. 4) mm: expose ksm process profit metric in ksm_stat This exposes the ksm process profit metric in /proc//ksm_stat. The documentation mentions the formula for the ksm process profit metric, however it does not calculate it. In addition the formula depends on the size of internal structures. So it makes sense to expose it. 5) document new procfs ksm knobs Link: https://lkml.kernel.org/r/20230418051342.1919757-3-shr@devkernel.io Signed-off-by: Stefan Roesch Reviewed-by: Bagas Sanjaya Acked-by: David Hildenbrand Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Signed-off-by: Andrew Morton --- Documentation/ABI/testing/sysfs-kernel-mm-ksm | 8 +++++++ Documentation/admin-guide/mm/ksm.rst | 5 ++++- fs/proc/base.c | 3 +++ include/linux/ksm.h | 5 +++++ mm/ksm.c | 21 +++++++++++++++++++ 5 files changed, 41 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm index d244674a9480..6041a025b65a 100644 --- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm +++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm @@ -51,3 +51,11 @@ Description: Control merging pages across different NUMA nodes. When it is set to 0 only pages from the same node are merged, otherwise pages from all nodes can be merged together (default). + +What: /sys/kernel/mm/ksm/general_profit +Date: April 2023 +KernelVersion: 6.4 +Contact: Linux memory management mailing list +Description: Measure how effective KSM is. + general_profit: how effective is KSM. The formula for the + calculation is in Documentation/admin-guide/mm/ksm.rst. diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst index eed51a910c94..551083a396fb 100644 --- a/Documentation/admin-guide/mm/ksm.rst +++ b/Documentation/admin-guide/mm/ksm.rst @@ -157,6 +157,8 @@ stable_node_chains_prune_millisecs The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``: +general_profit + how effective is KSM. The calculation is explained below. pages_shared how many shared pages are being used pages_sharing @@ -207,7 +209,8 @@ several times, which are unprofitable memory consumed. ksm_rmap_items * sizeof(rmap_item). where ksm_merging_pages is shown under the directory ``/proc//``, - and ksm_rmap_items is shown in ``/proc//ksm_stat``. + and ksm_rmap_items is shown in ``/proc//ksm_stat``. The process profit + is also shown in ``/proc//ksm_stat`` as ksm_process_profit. From the perspective of application, a high ratio of ``ksm_rmap_items`` to ``ksm_merging_pages`` means a bad madvise-applied policy, so developers or diff --git a/fs/proc/base.c b/fs/proc/base.c index 5e0e0ccd47aa..96a6a08c8235 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -96,6 +96,7 @@ #include #include #include +#include #include #include "internal.h" #include "fd.h" @@ -3207,6 +3208,8 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items); + seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages); + seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm)); mmput(mm); } diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 4647b0c70c12..7a9b76fb6c3f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -68,6 +68,11 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(struct page *page, struct list_head *to_kill, int force_early); #endif + +#ifdef CONFIG_PROC_FS +long ksm_process_profit(struct mm_struct *); +#endif /* CONFIG_PROC_FS */ + #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) diff --git a/mm/ksm.c b/mm/ksm.c index 35ac6c741572..9e48258985d2 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -3007,6 +3007,14 @@ static void wait_while_offlining(void) } #endif /* CONFIG_MEMORY_HOTREMOVE */ +#ifdef CONFIG_PROC_FS +long ksm_process_profit(struct mm_struct *mm) +{ + return mm->ksm_merging_pages * PAGE_SIZE - + mm->ksm_rmap_items * sizeof(struct ksm_rmap_item); +} +#endif /* CONFIG_PROC_FS */ + #ifdef CONFIG_SYSFS /* * This all compiles without CONFIG_SYSFS, but is a waste of space. @@ -3271,6 +3279,18 @@ static ssize_t pages_volatile_show(struct kobject *kobj, } KSM_ATTR_RO(pages_volatile); +static ssize_t general_profit_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + long general_profit; + + general_profit = ksm_pages_sharing * PAGE_SIZE - + ksm_rmap_items * sizeof(struct ksm_rmap_item); + + return sysfs_emit(buf, "%ld\n", general_profit); +} +KSM_ATTR_RO(general_profit); + static ssize_t stable_node_dups_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -3335,6 +3355,7 @@ static struct attribute *ksm_attrs[] = { &stable_node_dups_attr.attr, &stable_node_chains_prune_millisecs_attr.attr, &use_zero_pages_attr.attr, + &general_profit_attr.attr, NULL, }; -- GitLab From 07115fcc15b4aa5c268fb80b82ad15868a82a285 Mon Sep 17 00:00:00 2001 From: Stefan Roesch Date: Mon, 17 Apr 2023 22:13:42 -0700 Subject: [PATCH 3794/5631] selftests/mm: add new selftests for KSM This adds three new tests to the selftests for KSM. These tests use the new prctl API's to enable and disable KSM. 1) add new prctl flags to prctl header file in tools dir This adds the new prctl flags to the include file prct.h in the tools directory. This makes sure they are available for testing. 2) add KSM prctl merge test to ksm_tests This adds the -t option to the ksm_tests program. The -t flag allows to specify if it should use madvise or prctl ksm merging. 3) add two functions for debugging merge outcome for ksm_tests This adds two functions to report the metrics in /proc/self/ksm_stat and /sys/kernel/debug/mm/ksm. The debug output is enabled with the -d option. 4) add KSM prctl test to ksm_functional_tests This adds a test to the ksm_functional_test that verifies that the prctl system call to enable / disable KSM works. 5) add KSM fork test to ksm_functional_test Add fork test to verify that the MMF_VM_MERGE_ANY flag is inherited by the child process. Link: https://lkml.kernel.org/r/20230418051342.1919757-4-shr@devkernel.io Signed-off-by: Stefan Roesch Acked-by: David Hildenbrand Cc: Bagas Sanjaya Cc: David Hildenbrand Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Signed-off-by: Andrew Morton --- tools/include/uapi/linux/prctl.h | 2 + tools/testing/selftests/mm/Makefile | 2 +- .../selftests/mm/ksm_functional_tests.c | 91 ++++++++- tools/testing/selftests/mm/ksm_tests.c | 172 ++++++++++++++---- 4 files changed, 228 insertions(+), 39 deletions(-) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 1312a137f7fb..759b3f53e53f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,4 +290,6 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 63ed778ca8dc..f764f2b3e34b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -29,7 +29,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread TEST_GEN_PROGS = cow diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index d3f26050dfd7..7bc9fc17c9f0 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -15,8 +15,10 @@ #include #include #include +#include #include #include +#include #include #include "../kselftest.h" @@ -237,9 +239,93 @@ static void test_unmerge_uffd_wp(void) } #endif +/* Verify that KSM can be enabled / queried with prctl. */ +static void test_prctl(void) +{ + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret < 0) { + ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n"); + return; + } else if (ret != 1) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 not effective\n"); + return; + } + + ret = prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret < 0) { + ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n"); + return; + } else if (ret != 0) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 not effective\n"); + return; + } + + ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n"); +} + +/* Verify that prctl ksm flag is inherited. */ +static void test_prctl_fork(void) +{ + int ret, status; + pid_t child_pid; + + ksft_print_msg("[RUN] %s\n", __func__); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + child_pid = fork(); + if (!child_pid) { + exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0)); + } else if (child_pid < 0) { + ksft_test_result_fail("fork() failed\n"); + return; + } + + if (waitpid(child_pid, &status, 0) < 0) { + ksft_test_result_fail("waitpid() failed\n"); + return; + } else if (WEXITSTATUS(status) != 1) { + ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + return; + } + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); +} + int main(int argc, char **argv) { - unsigned int tests = 2; + unsigned int tests = 4; int err; #ifdef __NR_userfaultfd @@ -267,6 +353,9 @@ int main(int argc, char **argv) test_unmerge_uffd_wp(); #endif + test_prctl(); + test_prctl_fork(); + err = ksft_get_fail_cnt(); if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 74281593a124..435acebdc325 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include +#include +#include #include #include #include @@ -21,6 +23,7 @@ #define KSM_PROT_STR_DEFAULT "rw" #define KSM_USE_ZERO_PAGES_DEFAULT false #define KSM_MERGE_ACROSS_NODES_DEFAULT true +#define KSM_MERGE_TYPE_DEFAULT 0 #define MB (1ul << 20) struct ksm_sysfs { @@ -33,9 +36,16 @@ struct ksm_sysfs { unsigned long use_zero_pages; }; +enum ksm_merge_type { + KSM_MERGE_MADVISE, + KSM_MERGE_PRCTL, + KSM_MERGE_LAST = KSM_MERGE_PRCTL +}; + enum ksm_test_name { CHECK_KSM_MERGE, CHECK_KSM_UNMERGE, + CHECK_KSM_GET_MERGE_TYPE, CHECK_KSM_ZERO_PAGE_MERGE, CHECK_KSM_NUMA_MERGE, KSM_MERGE_TIME, @@ -44,6 +54,8 @@ enum ksm_test_name { KSM_COW_TIME }; +int debug; + static int ksm_write_sysfs(const char *file_path, unsigned long val) { FILE *f = fopen(file_path, "w"); @@ -82,6 +94,53 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val) return 0; } +static void ksm_print_sysfs(void) +{ + unsigned long max_page_sharing, pages_sharing, pages_shared; + unsigned long full_scans, pages_unshared, pages_volatile; + unsigned long stable_node_chains, stable_node_dups; + long general_profit; + + if (ksm_read_sysfs(KSM_FP("pages_shared"), &pages_shared) || + ksm_read_sysfs(KSM_FP("pages_sharing"), &pages_sharing) || + ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing) || + ksm_read_sysfs(KSM_FP("full_scans"), &full_scans) || + ksm_read_sysfs(KSM_FP("pages_unshared"), &pages_unshared) || + ksm_read_sysfs(KSM_FP("pages_volatile"), &pages_volatile) || + ksm_read_sysfs(KSM_FP("stable_node_chains"), &stable_node_chains) || + ksm_read_sysfs(KSM_FP("stable_node_dups"), &stable_node_dups) || + ksm_read_sysfs(KSM_FP("general_profit"), (unsigned long *)&general_profit)) + return; + + printf("pages_shared : %lu\n", pages_shared); + printf("pages_sharing : %lu\n", pages_sharing); + printf("max_page_sharing : %lu\n", max_page_sharing); + printf("full_scans : %lu\n", full_scans); + printf("pages_unshared : %lu\n", pages_unshared); + printf("pages_volatile : %lu\n", pages_volatile); + printf("stable_node_chains: %lu\n", stable_node_chains); + printf("stable_node_dups : %lu\n", stable_node_dups); + printf("general_profit : %ld\n", general_profit); +} + +static void ksm_print_procfs(void) +{ + const char *file_name = "/proc/self/ksm_stat"; + char buffer[512]; + FILE *f = fopen(file_name, "r"); + + if (!f) { + fprintf(stderr, "f %s\n", file_name); + perror("fopen"); + return; + } + + while (fgets(buffer, sizeof(buffer), f)) + printf("%s", buffer); + + fclose(f); +} + static int str_to_prot(char *prot_str) { int prot = 0; @@ -128,7 +187,12 @@ static void print_help(void) " Default: %d\n", KSM_USE_ZERO_PAGES_DEFAULT); printf(" -m: change merge_across_nodes tunable\n" " Default: %d\n", KSM_MERGE_ACROSS_NODES_DEFAULT); + printf(" -d: turn debugging output on\n"); printf(" -s: the size of duplicated memory area (in MiB)\n"); + printf(" -t: KSM merge type\n" + " Default: 0\n" + " 0: madvise merging\n" + " 1: prctl merging\n"); exit(0); } @@ -176,12 +240,21 @@ static int ksm_do_scan(int scan_count, struct timespec start_time, int timeout) return 0; } -static int ksm_merge_pages(void *addr, size_t size, struct timespec start_time, int timeout) +static int ksm_merge_pages(int merge_type, void *addr, size_t size, + struct timespec start_time, int timeout) { - if (madvise(addr, size, MADV_MERGEABLE)) { - perror("madvise"); - return 1; + if (merge_type == KSM_MERGE_MADVISE) { + if (madvise(addr, size, MADV_MERGEABLE)) { + perror("madvise"); + return 1; + } + } else if (merge_type == KSM_MERGE_PRCTL) { + if (prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0)) { + perror("prctl"); + return 1; + } } + if (ksm_write_sysfs(KSM_FP("run"), 1)) return 1; @@ -211,6 +284,11 @@ static bool assert_ksm_pages_count(long dupl_page_count) ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing)) return false; + if (debug) { + ksm_print_sysfs(); + ksm_print_procfs(); + } + /* * Since there must be at least 2 pages for merging and 1 page can be * shared with the limited number of pages (max_page_sharing), sometimes @@ -266,7 +344,8 @@ static int ksm_restore(struct ksm_sysfs *ksm_sysfs) return 0; } -static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, size_t page_size) +static int check_ksm_merge(int merge_type, int mapping, int prot, + long page_count, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -281,13 +360,15 @@ static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* verify that the right number of pages are merged */ if (assert_ksm_pages_count(page_count)) { printf("OK\n"); munmap(map_ptr, page_size * page_count); + if (merge_type == KSM_MERGE_PRCTL) + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); return KSFT_PASS; } @@ -297,7 +378,7 @@ static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, return KSFT_FAIL; } -static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_size) +static int check_ksm_unmerge(int merge_type, int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -313,7 +394,7 @@ static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_siz if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* change 1 byte in each of the 2 pages -- KSM must automatically unmerge them */ @@ -337,8 +418,8 @@ static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_siz return KSFT_FAIL; } -static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int timeout, - bool use_zero_pages, size_t page_size) +static int check_ksm_zero_page_merge(int merge_type, int mapping, int prot, long page_count, + int timeout, bool use_zero_pages, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -356,7 +437,7 @@ static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* @@ -402,8 +483,8 @@ static int get_first_mem_node(void) return get_next_mem_node(numa_max_node()); } -static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_across_nodes, - size_t page_size) +static int check_ksm_numa_merge(int merge_type, int mapping, int prot, int timeout, + bool merge_across_nodes, size_t page_size) { void *numa1_map_ptr, *numa2_map_ptr; struct timespec start_time; @@ -439,8 +520,8 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a memset(numa2_map_ptr, '*', page_size); /* try to merge the pages */ - if (ksm_merge_pages(numa1_map_ptr, page_size, start_time, timeout) || - ksm_merge_pages(numa2_map_ptr, page_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, numa1_map_ptr, page_size, start_time, timeout) || + ksm_merge_pages(merge_type, numa2_map_ptr, page_size, start_time, timeout)) goto err_out; /* @@ -466,7 +547,8 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a return KSFT_FAIL; } -static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, + int timeout, size_t map_size) { void *map_ptr, *map_ptr_orig; struct timespec start_time, end_time; @@ -508,7 +590,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { perror("clock_gettime"); @@ -533,7 +615,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m return KSFT_FAIL; } -static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_merge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size) { void *map_ptr; struct timespec start_time, end_time; @@ -549,7 +631,7 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { perror("clock_gettime"); @@ -574,7 +656,7 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) return KSFT_FAIL; } -static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_unmerge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size) { void *map_ptr; struct timespec start_time, end_time; @@ -589,7 +671,7 @@ static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { @@ -621,7 +703,7 @@ static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) return KSFT_FAIL; } -static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) +static int ksm_cow_time(int merge_type, int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time, end_time; @@ -660,7 +742,7 @@ static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) memset(map_ptr + page_size * i, '+', i / 2 + 1); memset(map_ptr + page_size * (i + 1), '+', i / 2 + 1); } - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { @@ -697,6 +779,7 @@ int main(int argc, char *argv[]) int ret, opt; int prot = 0; int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT; + int merge_type = KSM_MERGE_TYPE_DEFAULT; long page_count = KSM_PAGE_COUNT_DEFAULT; size_t page_size = sysconf(_SC_PAGESIZE); struct ksm_sysfs ksm_sysfs_old; @@ -705,7 +788,7 @@ int main(int argc, char *argv[]) bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT; long size_MB = 0; - while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) { + while ((opt = getopt(argc, argv, "dha:p:l:z:m:s:t:MUZNPCHD")) != -1) { switch (opt) { case 'a': prot = str_to_prot(optarg); @@ -739,12 +822,26 @@ int main(int argc, char *argv[]) else merge_across_nodes = 1; break; + case 'd': + debug = 1; + break; case 's': size_MB = atoi(optarg); if (size_MB <= 0) { printf("Size must be greater than 0\n"); return KSFT_FAIL; } + case 't': + { + int tmp = atoi(optarg); + + if (tmp < 0 || tmp > KSM_MERGE_LAST) { + printf("Invalid merge type\n"); + return KSFT_FAIL; + } + merge_type = tmp; + } + break; case 'M': break; case 'U': @@ -795,35 +892,36 @@ int main(int argc, char *argv[]) switch (test_name) { case CHECK_KSM_MERGE: - ret = check_ksm_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, + ret = check_ksm_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, ksm_scan_limit_sec, page_size); break; case CHECK_KSM_UNMERGE: - ret = check_ksm_unmerge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - page_size); + ret = check_ksm_unmerge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, page_size); break; case CHECK_KSM_ZERO_PAGE_MERGE: - ret = check_ksm_zero_page_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, - ksm_scan_limit_sec, use_zero_pages, page_size); + ret = check_ksm_zero_page_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + page_count, ksm_scan_limit_sec, use_zero_pages, + page_size); break; case CHECK_KSM_NUMA_MERGE: - ret = check_ksm_numa_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - merge_across_nodes, page_size); + ret = check_ksm_numa_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, merge_across_nodes, page_size); break; case KSM_MERGE_TIME: if (size_MB == 0) { printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_merge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - size_MB); + ret = ksm_merge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, size_MB); break; case KSM_MERGE_TIME_HUGE_PAGES: if (size_MB == 0) { printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ret = ksm_merge_hugepages_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; case KSM_UNMERGE_TIME: @@ -831,12 +929,12 @@ int main(int argc, char *argv[]) printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_unmerge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ret = ksm_unmerge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; case KSM_COW_TIME: - ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - page_size); + ret = ksm_cow_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, page_size); break; } -- GitLab From d2658f2052c7db6ec0a79977205f8cf1cb9effc2 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Tue, 18 Apr 2023 16:46:39 +0900 Subject: [PATCH 3795/5631] zsmalloc: allow only one active pool compaction context zsmalloc pool can be compacted concurrently by many contexts, e.g. cc1 handle_mm_fault() do_anonymous_page() __alloc_pages_slowpath() try_to_free_pages() do_try_to_free_pages( lru_gen_shrink_node() shrink_slab() do_shrink_slab() zs_shrinker_scan() zs_compact() Pool compaction is currently (basically) single-threaded as it is performed under pool->lock. Having multiple compaction threads results in unnecessary contention, as each thread competes for pool->lock. This, in turn, affects all zsmalloc operations such as zs_malloc(), zs_map_object(), zs_free(), etc. Introduce the pool->compaction_in_progress atomic variable, which ensures that only one compaction context can run at a time. This reduces overall pool->lock contention in (corner) cases when many contexts attempt to shrink zspool simultaneously. Link: https://lkml.kernel.org/r/20230418074639.1903197-1-senozhatsky@chromium.org Fixes: c0547d0b6a4b ("zsmalloc: consolidate zs_pool's migrate_lock and size_class's locks") Signed-off-by: Sergey Senozhatsky Reviewed-by: Yosry Ahmed Cc: Minchan Kim Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index cc81dfba05a0..44ddaf5d601e 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -264,6 +264,7 @@ struct zs_pool { struct work_struct free_work; #endif spinlock_t lock; + atomic_t compaction_in_progress; }; struct zspage { @@ -2274,6 +2275,15 @@ unsigned long zs_compact(struct zs_pool *pool) struct size_class *class; unsigned long pages_freed = 0; + /* + * Pool compaction is performed under pool->lock so it is basically + * single-threaded. Having more than one thread in __zs_compact() + * will increase pool->lock contention, which will impact other + * zsmalloc operations that need pool->lock. + */ + if (atomic_xchg(&pool->compaction_in_progress, 1)) + return 0; + for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; if (class->index != i) @@ -2281,6 +2291,7 @@ unsigned long zs_compact(struct zs_pool *pool) pages_freed += __zs_compact(pool, class); } atomic_long_add(pages_freed, &pool->stats.pages_compacted); + atomic_set(&pool->compaction_in_progress, 0); return pages_freed; } @@ -2388,6 +2399,7 @@ struct zs_pool *zs_create_pool(const char *name) init_deferred_free(pool); spin_lock_init(&pool->lock); + atomic_set(&pool->compaction_in_progress, 0); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) -- GitLab From 53156443a30368c0759c22e54a8d5cacc1b543cc Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 19 Apr 2023 10:58:36 -0700 Subject: [PATCH 3796/5631] mm: do not increment pgfault stats when page fault handler retries If the page fault handler requests a retry, we will count the fault multiple times. This is a relatively harmless problem as the retry paths are not often requested, and the only user-visible problem is that the fault counter will be slightly higher than it should be. Nevertheless, userspace only took one fault, and should not see the fact that the kernel had to retry the fault multiple times. Move page fault accounting into mm_account_fault() and skip incomplete faults which will be accounted upon completion. Link: https://lkml.kernel.org/r/20230419175836.3857458-1-surenb@google.com Fixes: d065bd810b6d ("mm: retry page fault when blocking on disk transfer") Signed-off-by: Suren Baghdasaryan Reviewed-by: Matthew Wilcox (Oracle) Acked-by: Peter Xu Cc: Davidlohr Bueso Cc: Jan Kara Cc: Johannes Weiner Cc: Josef Bacik Cc: Laurent Dufour Cc: Liam R. Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Michel Lespinasse Cc: Minchan Kim Cc: Punit Agrawal Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/memory.c | 46 +++++++++++++++++++++++++++------------------- 1 file changed, 27 insertions(+), 19 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index f7510a06a2d0..f69fbc251198 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5104,24 +5104,31 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ -static inline void mm_account_fault(struct pt_regs *regs, +static inline void mm_account_fault(struct mm_struct *mm, struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; + /* Incomplete faults will be accounted upon completion. */ + if (ret & VM_FAULT_RETRY) + return; + /* - * We don't do accounting for some specific faults: - * - * - Unsuccessful faults (e.g. when the address wasn't valid). That - * includes arch_vma_access_permitted() failing before reaching here. - * So this is not a "this many hardware page faults" counter. We - * should use the hw profiling for that. - * - * - Incomplete faults (VM_FAULT_RETRY). They will only be counted - * once they're completed. + * To preserve the behavior of older kernels, PGFAULT counters record + * both successful and failed faults, as opposed to perf counters, + * which ignore failed cases. */ - if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) + count_vm_event(PGFAULT); + count_memcg_event_mm(mm, PGFAULT); + + /* + * Do not account for unsuccessful faults (e.g. when the address wasn't + * valid). That includes arch_vma_access_permitted() failing before + * reaching here. So this is not a "this many hardware page faults" + * counter. We should use the hw profiling for that. + */ + if (ret & VM_FAULT_ERROR) return; /* @@ -5204,21 +5211,22 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma, vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { + /* If the fault handler drops the mmap_lock, vma may be freed */ + struct mm_struct *mm = vma->vm_mm; vm_fault_t ret; __set_current_state(TASK_RUNNING); - count_vm_event(PGFAULT); - count_memcg_event_mm(vma->vm_mm, PGFAULT); - ret = sanitize_fault_flags(vma, &flags); if (ret) - return ret; + goto out; if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, - flags & FAULT_FLAG_REMOTE)) - return VM_FAULT_SIGSEGV; + flags & FAULT_FLAG_REMOTE)) { + ret = VM_FAULT_SIGSEGV; + goto out; + } /* * Enable the memcg OOM handling for faults triggered in user @@ -5247,8 +5255,8 @@ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } - - mm_account_fault(regs, address, flags, ret); +out: + mm_account_fault(mm, regs, address, flags, ret); return ret; } -- GitLab From 29ad6bb313487370f9dfe5441fc8982593b6384e Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Wed, 19 Apr 2023 17:36:25 +0800 Subject: [PATCH 3797/5631] maple_tree: fix allocation in mas_sparse_area() In the case of reverse allocation, mas->index and mas->last do not point to the correct allocation range, which will cause users to get incorrect allocation results, so fix it. If the user does not use it in a specific way, this bug will not be triggered. This is a bug, but only VMA uses it now, the way VMA is used now will not trigger it. There is a possibility that a user will trigger it in the future. Also re-check whether the size is still satisfied after the lower bound was increased, which is a corner case and is incorrect in previous versions. Link: https://lkml.kernel.org/r/20230419093625.99201-1-zhangpeng.00@bytedance.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Peng Zhang Cc: Liam R. Howlett Signed-off-by: Andrew Morton --- lib/maple_tree.c | 41 ++++++++++++++++++++--------------------- 1 file changed, 20 insertions(+), 21 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 9172bcee94b4..110a36479dce 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5250,25 +5250,28 @@ static inline void mas_fill_gap(struct ma_state *mas, void *entry, * @size: The size of the gap * @fwd: Searching forward or back */ -static inline void mas_sparse_area(struct ma_state *mas, unsigned long min, +static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { - unsigned long start = 0; - - if (!unlikely(mas_is_none(mas))) - start++; + if (!unlikely(mas_is_none(mas)) && min == 0) { + min++; + /* + * At this time, min is increased, we need to recheck whether + * the size is satisfied. + */ + if (min > max || max - min + 1 < size) + return -EBUSY; + } /* mas_is_ptr */ - if (start < min) - start = min; - if (fwd) { - mas->index = start; - mas->last = start + size - 1; - return; + mas->index = min; + mas->last = min + size - 1; + } else { + mas->last = max; + mas->index = max - size + 1; } - - mas->index = max; + return 0; } /* @@ -5297,10 +5300,8 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, return -EBUSY; /* Empty set */ - if (mas_is_none(mas) || mas_is_ptr(mas)) { - mas_sparse_area(mas, min, max, size, true); - return 0; - } + if (mas_is_none(mas) || mas_is_ptr(mas)) + return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; @@ -5356,10 +5357,8 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, } /* Empty set. */ - if (mas_is_none(mas) || mas_is_ptr(mas)) { - mas_sparse_area(mas, min, max, size, false); - return 0; - } + if (mas_is_none(mas) || mas_is_ptr(mas)) + return mas_sparse_area(mas, min, max, size, false); /* The start of the window can only be within these values. */ mas->index = min; -- GitLab From f724392415b3e1ae844d2766669c0d955fe9a17b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 18 Apr 2023 22:22:02 -0700 Subject: [PATCH 3798/5631] hugetlb: pte_alloc_huge() to replace huge pte_alloc_map() Some architectures can have their hugetlb pages down at the lowest PTE level: their huge_pte_alloc() using pte_alloc_map(), but without any following pte_unmap(). Since none of these arches uses CONFIG_HIGHPTE, this is not seen as a problem at present; but would become a problem if forthcoming changes were to add an rcu_read_lock() into pte_offset_map(), with the rcu_read_unlock() expected in pte_unmap(). Similarly in their huge_pte_offset(): pte_offset_kernel() is good enough for that, but it's probably less confusing if we define pte_offset_huge() along with pte_alloc_huge(). Only define them without CONFIG_HIGHPTE: so there would be a build error to signal if ever more work is needed. For ease of development, define these now for 6.4-rc1, ahead of any use: then architectures can integrate patches using them, independent from mm. Link: https://lkml.kernel.org/r/ae9e7d98-8a3a-cfd9-4762-bcddffdf96cf@google.com Signed-off-by: Hugh Dickins Reviewed-by: Mike Kravetz Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 28703fe22386..cbe1e97a15a1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -191,6 +191,23 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ +#ifndef CONFIG_HIGHPTE +/* + * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures + * which may go down to the lowest PTE level in their huge_pte_offset() and + * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). + */ +static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) +{ + return pte_offset_kernel(pmd, address); +} +static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); +} +#endif + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* -- GitLab From 6b008640db7355d8de6ac18f74cedd7ccc92684f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 18 Apr 2023 17:40:09 -0400 Subject: [PATCH 3799/5631] mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area() Instead of having callers care about the mmap_min_addr logic for the lowest valid mapping address (and some of them getting it wrong), just move the logic into vm_unmapped_area() itself. One less thing for various architecture cases (and generic helpers) to worry about. We should really try to make much more of this be common code, but baby steps.. Without this, vm_unmapped_area() could return an address below mmap_min_addr (because some caller forgot about that). That then causes the mmap machinery to think it has found a workable address, but then later security_mmap_addr(addr) is unhappy about it and the mmap() returns with a nonsensical error (EPERM). The proper action is to either return ENOMEM (if the virtual address space is exhausted), or try to find another address (ie do a bottom-up search for free addresses after the top-down one failed). See commit 2afc745f3e30 ("mm: ensure get_unmapped_area() returns higher address than mmap_min_addr"), which fixed this for one call site (the generic arch_get_unmapped_area_topdown() fallback) but left other cases alone. Link: https://lkml.kernel.org/r/20230418214009.1142926-1-Liam.Howlett@oracle.com Signed-off-by: Linus Torvalds Signed-off-by: Liam R. Howlett Cc: Russell King Cc: Liam Howlett Signed-off-by: Andrew Morton --- arch/s390/mm/hugetlbpage.c | 2 +- arch/s390/mm/mmap.c | 2 +- fs/hugetlbfs/inode.c | 2 +- mm/mmap.c | 19 +++++++++++++------ 4 files changed, 16 insertions(+), 9 deletions(-) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index c299a18273ff..c718f2a0de94 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -273,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.low_limit = PAGE_SIZE; info.high_limit = current->mm->mmap_base; info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 3327c47bc181..fc9a7dc26c5e 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -136,7 +136,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; if (filp || (flags & MAP_SHARED)) info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 702d79639c0d..ecfdfb2529a3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -208,7 +208,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; diff --git a/mm/mmap.c b/mm/mmap.c index 51b6976fd525..536bbb8fa0ae 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1548,7 +1548,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) */ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { - unsigned long length, gap, low_limit; + unsigned long length, gap; + unsigned long low_limit, high_limit; struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); @@ -1559,8 +1560,11 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) return -ENOMEM; low_limit = info->low_limit; + if (low_limit < mmap_min_addr) + low_limit = mmap_min_addr; + high_limit = info->high_limit; retry: - if (mas_empty_area(&mas, low_limit, info->high_limit - 1, length)) + if (mas_empty_area(&mas, low_limit, high_limit - 1, length)) return -ENOMEM; gap = mas.index; @@ -1596,7 +1600,8 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) */ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { - unsigned long length, gap, high_limit, gap_end; + unsigned long length, gap, gap_end; + unsigned long low_limit, high_limit; struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); @@ -1605,10 +1610,12 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) if (length < info->length) return -ENOMEM; + low_limit = info->low_limit; + if (low_limit < mmap_min_addr) + low_limit = mmap_min_addr; high_limit = info->high_limit; retry: - if (mas_empty_area_rev(&mas, info->low_limit, high_limit - 1, - length)) + if (mas_empty_area_rev(&mas, low_limit, high_limit - 1, length)) return -ENOMEM; gap = mas.last + 1 - info->length; @@ -1743,7 +1750,7 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = max(PAGE_SIZE, mmap_min_addr); + info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; info.align_offset = 0; -- GitLab From f0ca8c25256dd22737db5780e33e2809ce297625 Mon Sep 17 00:00:00 2001 From: Li zeming Date: Sat, 22 Apr 2023 05:47:33 +0800 Subject: [PATCH 3800/5631] sparse: remove unnecessary 0 values from rc rc is assigned first, so it does not need to initialize the assignment. Link: https://lkml.kernel.org/r/20230421214733.2909-1-zeming@nfschina.com Signed-off-by: Li zeming Signed-off-by: Andrew Morton --- mm/sparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/sparse.c b/mm/sparse.c index fb7aeb1899a4..c2afdb26039e 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -832,7 +832,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn, struct mem_section *ms = __pfn_to_section(pfn); struct mem_section_usage *usage = NULL; struct page *memmap; - int rc = 0; + int rc; if (!ms->usage) { usage = kzalloc(mem_section_usage_size(), GFP_KERNEL); -- GitLab From 3647ebcfbfca384840231fe13fae665453238a61 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 16 Apr 2023 22:17:05 -0700 Subject: [PATCH 3801/5631] ia64: fix an addr to taddr in huge_pte_offset() I know nothing of ia64 htlbpage_to_page(), but guess that the p4d line should be using taddr rather than addr, like everywhere else. Link: https://lkml.kernel.org/r/732eae88-3beb-246-2c72-281de786740@google.com Fixes: c03ab9e32a2c ("ia64: add support for folded p4d page tables") Signed-off-by: Hugh Dickins Acked-by: Mike Rapoport (IBM) Cc: Ard Biesheuvel Cc: Signed-off-by: Andrew Morton --- arch/ia64/mm/hugetlbpage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 380d2f3966c9..9e8960e49962 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -58,7 +58,7 @@ huge_pte_offset (struct mm_struct *mm, unsigned long addr, unsigned long sz) pgd = pgd_offset(mm, taddr); if (pgd_present(*pgd)) { - p4d = p4d_offset(pgd, addr); + p4d = p4d_offset(pgd, taddr); if (p4d_present(*p4d)) { pud = pud_offset(p4d, taddr); if (pud_present(*pud)) { -- GitLab From 522dc4e5f51e3d51c4ff55ad1c725d12176b71ea Mon Sep 17 00:00:00 2001 From: Chunguang Wu Date: Sun, 16 Apr 2023 13:24:04 +0800 Subject: [PATCH 3802/5631] fs/proc: add Kthread flag to /proc/$pid/status The command `ps -ef ` and `top -c` mark kernel thread by '[' and ']', but sometimes the result is not correct. The task->flags in /proc/$pid/stat is good, but we need remember the value of PF_KTHREAD is 0x00200000 and convert dec to hex. If we have no binary program and shell script which read /proc/$pid/stat, we can know it directly by `cat /proc/$pid/status`. Link: https://lkml.kernel.org/r/20230416052404.2920-1-fullspring2018@gmail.com Signed-off-by: Chunguang Wu Reviewed-by: Randy Dunlap Cc: Alexey Dobriyan Cc: Jonathan Corbet Signed-off-by: Andrew Morton --- Documentation/filesystems/proc.rst | 2 ++ fs/proc/array.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 9d5fd9424e8b..8a563684586c 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -179,6 +179,7 @@ read the file /proc/PID/status:: Gid: 100 100 100 100 FDSize: 256 Groups: 100 14 16 + Kthread: 0 VmPeak: 5004 kB VmSize: 5004 kB VmLck: 0 kB @@ -256,6 +257,7 @@ It's slow but very precise. NSpid descendant namespace process ID hierarchy NSpgid descendant namespace process group ID hierarchy NSsid descendant namespace session ID hierarchy + Kthread kernel thread flag, 1 is yes, 0 is no VmPeak peak virtual memory size VmSize total program size VmLck locked memory size diff --git a/fs/proc/array.c b/fs/proc/array.c index 9b0315d34c58..425824ad85e1 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -219,6 +219,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns)); #endif seq_putc(m, '\n'); + + seq_printf(m, "Kthread:\t%c\n", p->flags & PF_KTHREAD ? '1' : '0'); } void render_sigset_t(struct seq_file *m, const char *header, -- GitLab From 09d49eb90fc8d03e1dab62dd7060389040f1d32b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Apr 2023 22:56:24 +0200 Subject: [PATCH 3803/5631] ocfs2: reduce ioctl stack usage On 32-bit architectures with KASAN_STACK enabled, the total stack usage of the ocfs2_ioctl function grows beyond the warning limit: fs/ocfs2/ioctl.c: In function 'ocfs2_ioctl': fs/ocfs2/ioctl.c:934:1: error: the frame size of 1448 bytes is larger than 1400 bytes [-Werror=frame-larger-than=] Move each of the variables into a basic block, and mark ocfs2_info_handle() as noinline_for_stack, in order to have the variable share stack slots. Link: https://lkml.kernel.org/r/20230417205631.1956027-1-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Joseph Qi Reviewed-by: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton --- fs/ocfs2/ioctl.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 811a6ea374bb..b1550ba73f96 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -803,8 +803,8 @@ static int ocfs2_get_request_ptr(struct ocfs2_info *info, int idx, * a better backward&forward compatibility, since a small piece of * request will be less likely to be broken if disk layout get changed. */ -static int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, - int compat_flag) +static noinline_for_stack int +ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, int compat_flag) { int i, status = 0; u64 req_addr; @@ -840,27 +840,26 @@ static int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); - int new_clusters; - int status; - struct ocfs2_space_resv sr; - struct ocfs2_new_group_input input; - struct reflink_arguments args; - const char __user *old_path; - const char __user *new_path; - bool preserve; - struct ocfs2_info info; void __user *argp = (void __user *)arg; + int status; switch (cmd) { case OCFS2_IOC_RESVSP: case OCFS2_IOC_RESVSP64: case OCFS2_IOC_UNRESVSP: case OCFS2_IOC_UNRESVSP64: + { + struct ocfs2_space_resv sr; + if (copy_from_user(&sr, (int __user *) arg, sizeof(sr))) return -EFAULT; return ocfs2_change_file_space(filp, cmd, &sr); + } case OCFS2_IOC_GROUP_EXTEND: + { + int new_clusters; + if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -873,8 +872,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) status = ocfs2_group_extend(inode, new_clusters); mnt_drop_write_file(filp); return status; + } case OCFS2_IOC_GROUP_ADD: case OCFS2_IOC_GROUP_ADD64: + { + struct ocfs2_new_group_input input; + if (!capable(CAP_SYS_RESOURCE)) return -EPERM; @@ -887,7 +890,14 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) status = ocfs2_group_add(inode, &input); mnt_drop_write_file(filp); return status; + } case OCFS2_IOC_REFLINK: + { + struct reflink_arguments args; + const char __user *old_path; + const char __user *new_path; + bool preserve; + if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; old_path = (const char __user *)(unsigned long)args.old_path; @@ -895,11 +905,16 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) preserve = (args.preserve != 0); return ocfs2_reflink_ioctl(inode, old_path, new_path, preserve); + } case OCFS2_IOC_INFO: + { + struct ocfs2_info info; + if (copy_from_user(&info, argp, sizeof(struct ocfs2_info))) return -EFAULT; return ocfs2_info_handle(inode, &info, 0); + } case FITRIM: { struct super_block *sb = inode->i_sb; -- GitLab From 22ba509dd4dad053ad88fc387b5a74c2a9296a01 Mon Sep 17 00:00:00 2001 From: Oleksandr Natalenko Date: Wed, 19 Apr 2023 15:47:34 +0200 Subject: [PATCH 3804/5631] mailmap: add entry for Oleksandr Map my corporate email to my personal one. Link: https://lkml.kernel.org/r/20230419134734.454630-1-oleksandr@natalenko.name Signed-off-by: Oleksandr Natalenko Cc: Jakub Kicinski Cc: Konrad Dybcio Signed-off-by: Andrew Morton --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index e2af78f67f7c..0d8940d37bf4 100644 --- a/.mailmap +++ b/.mailmap @@ -354,6 +354,7 @@ Nicolas Pitre Nicolas Saenz Julienne Nicolas Saenz Julienne Niklas Söderlund +Oleksandr Natalenko Oleksij Rempel Oleksij Rempel Oleksij Rempel -- GitLab From 531094dc7164718d28ebb581d729807d7e846363 Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Tue, 4 Apr 2023 15:43:13 +0000 Subject: [PATCH 3805/5631] RDMA/efa: Add rdma write capability to device caps Add rdma write capability that is propagated from the device to rdma-core. Enable MR creation with remote write permissions according to this device capability. Link: https://lore.kernel.org/r/20230404154313.35194-1-ynachum@amazon.com Reviewed-by: Firas Jahjah Reviewed-by: Michael Margolin Signed-off-by: Yonatan Nachum Signed-off-by: Jason Gunthorpe --- .../infiniband/hw/efa/efa_admin_cmds_defs.h | 12 ++++-- drivers/infiniband/hw/efa/efa_io_defs.h | 42 +++++++++++++------ drivers/infiniband/hw/efa/efa_verbs.c | 6 ++- include/uapi/rdma/efa-abi.h | 1 + 4 files changed, 44 insertions(+), 17 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h index 3db791e6c030..4e93ef7f84ee 100644 --- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h +++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h @@ -376,7 +376,9 @@ struct efa_admin_reg_mr_cmd { * 0 : local_write_enable - Local write permissions: * must be set for RQ buffers and buffers posted for * RDMA Read requests - * 1 : reserved1 - MBZ + * 1 : remote_write_enable - Remote write + * permissions: must be set to enable RDMA write to + * the region * 2 : remote_read_enable - Remote read permissions: * must be set to enable RDMA read from the region * 7:3 : reserved2 - MBZ @@ -620,7 +622,9 @@ struct efa_admin_feature_device_attr_desc { * modify QP command * 2 : data_polling_128 - If set, 128 bytes data * polling is supported - * 31:3 : reserved - MBZ + * 3 : rdma_write - If set, RDMA Write is supported + * on TX queues + * 31:4 : reserved - MBZ */ u32 device_caps; @@ -674,7 +678,7 @@ struct efa_admin_feature_queue_attr_desc { /* The maximum size of LLQ in bytes */ u32 max_llq_size; - /* Maximum number of SGEs for a single RDMA read WQE */ + /* Maximum number of SGEs for a single RDMA read/write WQE */ u16 max_wr_rdma_sges; /* @@ -979,6 +983,7 @@ struct efa_admin_host_info { #define EFA_ADMIN_REG_MR_CMD_PHYS_PAGE_SIZE_SHIFT_MASK GENMASK(4, 0) #define EFA_ADMIN_REG_MR_CMD_MEM_ADDR_PHY_MODE_EN_MASK BIT(7) #define EFA_ADMIN_REG_MR_CMD_LOCAL_WRITE_ENABLE_MASK BIT(0) +#define EFA_ADMIN_REG_MR_CMD_REMOTE_WRITE_ENABLE_MASK BIT(1) #define EFA_ADMIN_REG_MR_CMD_REMOTE_READ_ENABLE_MASK BIT(2) /* create_cq_cmd */ @@ -994,6 +999,7 @@ struct efa_admin_host_info { #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK BIT(0) #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK BIT(1) #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_DATA_POLLING_128_MASK BIT(2) +#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_WRITE_MASK BIT(3) /* create_eq_cmd */ #define EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS_MASK GENMASK(4, 0) diff --git a/drivers/infiniband/hw/efa/efa_io_defs.h b/drivers/infiniband/hw/efa/efa_io_defs.h index 17ba8984b11e..2d8eb96eaa81 100644 --- a/drivers/infiniband/hw/efa/efa_io_defs.h +++ b/drivers/infiniband/hw/efa/efa_io_defs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ /* - * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved. */ #ifndef _EFA_IO_H_ @@ -23,6 +23,8 @@ enum efa_io_send_op_type { EFA_IO_SEND = 0, /* RDMA read */ EFA_IO_RDMA_READ = 1, + /* RDMA write */ + EFA_IO_RDMA_WRITE = 2, }; enum efa_io_comp_status { @@ -62,8 +64,7 @@ struct efa_io_tx_meta_desc { /* * control flags - * 3:0 : op_type - operation type: send/rdma/fast mem - * ops/etc + * 3:0 : op_type - enum efa_io_send_op_type * 4 : has_imm - immediate_data field carries valid * data. * 5 : inline_msg - inline mode - inline message data @@ -219,21 +220,22 @@ struct efa_io_cdesc_common { * 2:1 : q_type - enum efa_io_queue_type: send/recv * 3 : has_imm - indicates that immediate data is * present - for RX completions only - * 7:4 : reserved28 - MBZ + * 6:4 : op_type - enum efa_io_send_op_type + * 7 : reserved31 - MBZ */ u8 flags; /* local QP number */ u16 qp_num; - - /* Transferred length */ - u16 length; }; /* Tx completion descriptor */ struct efa_io_tx_cdesc { /* Common completion info */ struct efa_io_cdesc_common common; + + /* MBZ */ + u16 reserved16; }; /* Rx Completion Descriptor */ @@ -241,6 +243,9 @@ struct efa_io_rx_cdesc { /* Common completion info */ struct efa_io_cdesc_common common; + /* Transferred length bits[15:0] */ + u16 length; + /* Remote Address Handle FW index, 0xFFFF indicates invalid ah */ u16 ah; @@ -250,16 +255,26 @@ struct efa_io_rx_cdesc { u32 imm; }; +/* Rx Completion Descriptor RDMA write info */ +struct efa_io_rx_cdesc_rdma_write { + /* Transferred length bits[31:16] */ + u16 length_hi; +}; + /* Extended Rx Completion Descriptor */ struct efa_io_rx_cdesc_ex { /* Base RX completion info */ - struct efa_io_rx_cdesc rx_cdesc_base; + struct efa_io_rx_cdesc base; - /* - * Valid only in case of unknown AH (0xFFFF) and CQ set_src_addr is - * enabled. - */ - u8 src_addr[16]; + union { + struct efa_io_rx_cdesc_rdma_write rdma_write; + + /* + * Valid only in case of unknown AH (0xFFFF) and CQ + * set_src_addr is enabled. + */ + u8 src_addr[16]; + } u; }; /* tx_meta_desc */ @@ -285,5 +300,6 @@ struct efa_io_rx_cdesc_ex { #define EFA_IO_CDESC_COMMON_PHASE_MASK BIT(0) #define EFA_IO_CDESC_COMMON_Q_TYPE_MASK GENMASK(2, 1) #define EFA_IO_CDESC_COMMON_HAS_IMM_MASK BIT(3) +#define EFA_IO_CDESC_COMMON_OP_TYPE_MASK GENMASK(6, 4) #endif /* _EFA_IO_H_ */ diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index c20136e9d3d1..8eca6c14d0cf 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -253,6 +253,9 @@ int efa_query_device(struct ib_device *ibdev, if (EFA_DEV_CAP(dev, DATA_POLLING_128)) resp.device_caps |= EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128; + if (EFA_DEV_CAP(dev, RDMA_WRITE)) + resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_WRITE; + if (dev->neqs) resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS; @@ -1572,7 +1575,8 @@ static struct efa_mr *efa_alloc_mr(struct ib_pd *ibpd, int access_flags, supp_access_flags = IB_ACCESS_LOCAL_WRITE | - (EFA_DEV_CAP(dev, RDMA_READ) ? IB_ACCESS_REMOTE_READ : 0); + (EFA_DEV_CAP(dev, RDMA_READ) ? IB_ACCESS_REMOTE_READ : 0) | + (EFA_DEV_CAP(dev, RDMA_WRITE) ? IB_ACCESS_REMOTE_WRITE : 0); access_flags &= ~IB_ACCESS_OPTIONAL; if (access_flags & ~supp_access_flags) { diff --git a/include/uapi/rdma/efa-abi.h b/include/uapi/rdma/efa-abi.h index 74406b4817ce..d94c32f28804 100644 --- a/include/uapi/rdma/efa-abi.h +++ b/include/uapi/rdma/efa-abi.h @@ -121,6 +121,7 @@ enum { EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2, EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID = 1 << 3, EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4, + EFA_QUERY_DEVICE_CAPS_RDMA_WRITE = 1 << 5, }; struct efa_ibv_ex_query_device_resp { -- GitLab From 76d4bd591e1101df69c44c819041e374c63f1194 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:32 -0300 Subject: [PATCH 3806/5631] rust: sync: introduce `Lock` and `Guard` They are generic Rust implementations of a lock and a lock guard that contain code that is common to all locks. Different backends will be introduced in subsequent commits. Reviewed-by: Martin Rodriguez Reboredo Suggested-by: Gary Guo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230411054543.21278-2-wedsonaf@gmail.com [ Fixed typo. ] Signed-off-by: Miguel Ojeda --- rust/kernel/sync.rs | 2 +- rust/kernel/sync/lock.rs | 162 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 163 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/sync/lock.rs diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 541d235ffbeb..81b0998eaa18 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -8,6 +8,7 @@ use crate::types::Opaque; mod arc; +pub mod lock; pub use arc::{Arc, ArcBorrow, UniqueArc}; @@ -25,7 +26,6 @@ impl LockClassKey { Self(Opaque::uninit()) } - #[allow(dead_code)] pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key { self.0.get() } diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs new file mode 100644 index 000000000000..f2dbdc496c23 --- /dev/null +++ b/rust/kernel/sync/lock.rs @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Generic kernel lock and guard. +//! +//! It contains a generic Rust lock and guard that allow for different backends (e.g., mutexes, +//! spinlocks, raw spinlocks) to be provided with minimal effort. + +use super::LockClassKey; +use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque}; +use core::{cell::UnsafeCell, marker::PhantomData, marker::PhantomPinned}; +use macros::pin_data; + +/// The "backend" of a lock. +/// +/// It is the actual implementation of the lock, without the need to repeat patterns used in all +/// locks. +/// +/// # Safety +/// +/// - Implementers must ensure that only one thread/CPU may access the protected data once the lock +/// is owned, that is, between calls to `lock` and `unlock`. +pub unsafe trait Backend { + /// The state required by the lock. + type State; + + /// The state required to be kept between lock and unlock. + type GuardState; + + /// Initialises the lock. + /// + /// # Safety + /// + /// `ptr` must be valid for write for the duration of the call, while `name` and `key` must + /// remain valid for read indefinitely. + unsafe fn init( + ptr: *mut Self::State, + name: *const core::ffi::c_char, + key: *mut bindings::lock_class_key, + ); + + /// Acquires the lock, making the caller its owner. + /// + /// # Safety + /// + /// Callers must ensure that [`Backend::init`] has been previously called. + #[must_use] + unsafe fn lock(ptr: *mut Self::State) -> Self::GuardState; + + /// Releases the lock, giving up its ownership. + /// + /// # Safety + /// + /// It must only be called by the current owner of the lock. + unsafe fn unlock(ptr: *mut Self::State, guard_state: &Self::GuardState); +} + +/// A mutual exclusion primitive. +/// +/// Exposes one of the kernel locking primitives. Which one is exposed depends on the lock backend +/// specified as the generic parameter `B`. +#[pin_data] +pub struct Lock { + /// The kernel lock object. + #[pin] + state: Opaque, + + /// Some locks are known to be self-referential (e.g., mutexes), while others are architecture + /// or config defined (e.g., spinlocks). So we conservatively require them to be pinned in case + /// some architecture uses self-references now or in the future. + #[pin] + _pin: PhantomPinned, + + /// The data protected by the lock. + data: UnsafeCell, +} + +// SAFETY: `Lock` can be transferred across thread boundaries iff the data it protects can. +unsafe impl Send for Lock {} + +// SAFETY: `Lock` serialises the interior mutability it provides, so it is `Sync` as long as the +// data it protects is `Send`. +unsafe impl Sync for Lock {} + +impl Lock { + /// Constructs a new lock initialiser. + #[allow(clippy::new_ret_no_self)] + pub fn new(t: T, name: &'static CStr, key: &'static LockClassKey) -> impl PinInit { + pin_init!(Self { + data: UnsafeCell::new(t), + _pin: PhantomPinned, + // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have + // static lifetimes so they live indefinitely. + state <- Opaque::ffi_init(|slot| unsafe { + B::init(slot, name.as_char_ptr(), key.as_ptr()) + }), + }) + } +} + +impl Lock { + /// Acquires the lock and gives the caller access to the data protected by it. + pub fn lock(&self) -> Guard<'_, T, B> { + // SAFETY: The constructor of the type calls `init`, so the existence of the object proves + // that `init` was called. + let state = unsafe { B::lock(self.state.get()) }; + // SAFETY: The lock was just acquired. + unsafe { Guard::new(self, state) } + } +} + +/// A lock guard. +/// +/// Allows mutual exclusion primitives that implement the `Backend` trait to automatically unlock +/// when a guard goes out of scope. It also provides a safe and convenient way to access the data +/// protected by the lock. +#[must_use = "the lock unlocks immediately when the guard is unused"] +pub struct Guard<'a, T: ?Sized, B: Backend> { + pub(crate) lock: &'a Lock, + pub(crate) state: B::GuardState, + _not_send: PhantomData<*mut ()>, +} + +// SAFETY: `Guard` is sync when the data protected by the lock is also sync. +unsafe impl Sync for Guard<'_, T, B> {} + +impl core::ops::Deref for Guard<'_, T, B> { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: The caller owns the lock, so it is safe to deref the protected data. + unsafe { &*self.lock.data.get() } + } +} + +impl core::ops::DerefMut for Guard<'_, T, B> { + fn deref_mut(&mut self) -> &mut Self::Target { + // SAFETY: The caller owns the lock, so it is safe to deref the protected data. + unsafe { &mut *self.lock.data.get() } + } +} + +impl Drop for Guard<'_, T, B> { + fn drop(&mut self) { + // SAFETY: The caller owns the lock, so it is safe to unlock it. + unsafe { B::unlock(self.lock.state.get(), &self.state) }; + } +} + +impl<'a, T: ?Sized, B: Backend> Guard<'a, T, B> { + /// Constructs a new immutable lock guard. + /// + /// # Safety + /// + /// The caller must ensure that it owns the lock. + pub(crate) unsafe fn new(lock: &'a Lock, state: B::GuardState) -> Self { + Self { + lock, + state, + _not_send: PhantomData, + } + } +} -- GitLab From 6d20d629c6d8575be98eeebe49a16fb2d7b32350 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:33 -0300 Subject: [PATCH 3807/5631] rust: lock: introduce `Mutex` This is the `struct mutex` lock backend and allows Rust code to use the kernel mutex idiomatically. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230411054543.21278-3-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/helpers.c | 7 ++ rust/kernel/sync.rs | 1 + rust/kernel/sync/lock.rs | 2 + rust/kernel/sync/lock/mutex.rs | 118 +++++++++++++++++++++++++++++++++ 4 files changed, 128 insertions(+) create mode 100644 rust/kernel/sync/lock/mutex.rs diff --git a/rust/helpers.c b/rust/helpers.c index 04b9be46e887..86af099d2d66 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -22,6 +22,7 @@ #include #include #include +#include __noreturn void rust_helper_BUG(void) { @@ -29,6 +30,12 @@ __noreturn void rust_helper_BUG(void) } EXPORT_SYMBOL_GPL(rust_helper_BUG); +void rust_helper_mutex_lock(struct mutex *lock) +{ + mutex_lock(lock); +} +EXPORT_SYMBOL_GPL(rust_helper_mutex_lock); + refcount_t rust_helper_REFCOUNT_INIT(int n) { return (refcount_t)REFCOUNT_INIT(n); diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 81b0998eaa18..693f0b7f4e4f 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -11,6 +11,7 @@ mod arc; pub mod lock; pub use arc::{Arc, ArcBorrow, UniqueArc}; +pub use lock::mutex::Mutex; /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. #[repr(transparent)] diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index f2dbdc496c23..2ea512a8dfab 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -10,6 +10,8 @@ use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque}; use core::{cell::UnsafeCell, marker::PhantomData, marker::PhantomPinned}; use macros::pin_data; +pub mod mutex; + /// The "backend" of a lock. /// /// It is the actual implementation of the lock, without the need to repeat patterns used in all diff --git a/rust/kernel/sync/lock/mutex.rs b/rust/kernel/sync/lock/mutex.rs new file mode 100644 index 000000000000..923472f04af4 --- /dev/null +++ b/rust/kernel/sync/lock/mutex.rs @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A kernel mutex. +//! +//! This module allows Rust code to use the kernel's `struct mutex`. + +use crate::bindings; + +/// Creates a [`Mutex`] initialiser with the given name and a newly-created lock class. +/// +/// It uses the name if one is given, otherwise it generates one based on the file name and line +/// number. +#[macro_export] +macro_rules! new_mutex { + ($inner:expr $(, $name:literal)? $(,)?) => { + $crate::sync::Mutex::new( + $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!()) + }; +} + +/// A mutual exclusion primitive. +/// +/// Exposes the kernel's [`struct mutex`]. When multiple threads attempt to lock the same mutex, +/// only one at a time is allowed to progress, the others will block (sleep) until the mutex is +/// unlocked, at which point another thread will be allowed to wake up and make progress. +/// +/// Since it may block, [`Mutex`] needs to be used with care in atomic contexts. +/// +/// Instances of [`Mutex`] need a lock class and to be pinned. The recommended way to create such +/// instances is with the [`pin_init`](crate::pin_init) and [`new_mutex`] macros. +/// +/// # Examples +/// +/// The following example shows how to declare, allocate and initialise a struct (`Example`) that +/// contains an inner struct (`Inner`) that is protected by a mutex. +/// +/// ``` +/// use kernel::{init::InPlaceInit, init::PinInit, new_mutex, pin_init, sync::Mutex}; +/// +/// struct Inner { +/// a: u32, +/// b: u32, +/// } +/// +/// #[pin_data] +/// struct Example { +/// c: u32, +/// #[pin] +/// d: Mutex, +/// } +/// +/// impl Example { +/// fn new() -> impl PinInit { +/// pin_init!(Self { +/// c: 10, +/// d <- new_mutex!(Inner { a: 20, b: 30 }), +/// }) +/// } +/// } +/// +/// // Allocate a boxed `Example`. +/// let e = Box::pin_init(Example::new())?; +/// assert_eq!(e.c, 10); +/// assert_eq!(e.d.lock().a, 20); +/// assert_eq!(e.d.lock().b, 30); +/// ``` +/// +/// The following example shows how to use interior mutability to modify the contents of a struct +/// protected by a mutex despite only having a shared reference: +/// +/// ``` +/// use kernel::sync::Mutex; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn example(m: &Mutex) { +/// let mut guard = m.lock(); +/// guard.a += 10; +/// guard.b += 20; +/// } +/// ``` +/// +/// [`struct mutex`]: ../../../../include/linux/mutex.h +pub type Mutex = super::Lock; + +/// A kernel `struct mutex` lock backend. +pub struct MutexBackend; + +// SAFETY: The underlying kernel `struct mutex` object ensures mutual exclusion. +unsafe impl super::Backend for MutexBackend { + type State = bindings::mutex; + type GuardState = (); + + unsafe fn init( + ptr: *mut Self::State, + name: *const core::ffi::c_char, + key: *mut bindings::lock_class_key, + ) { + // SAFETY: The safety requirements ensure that `ptr` is valid for writes, and `name` and + // `key` are valid for read indefinitely. + unsafe { bindings::__mutex_init(ptr, name, key) } + } + + unsafe fn lock(ptr: *mut Self::State) -> Self::GuardState { + // SAFETY: The safety requirements of this function ensure that `ptr` points to valid + // memory, and that it has been initialised before. + unsafe { bindings::mutex_lock(ptr) }; + } + + unsafe fn unlock(ptr: *mut Self::State, _guard_state: &Self::GuardState) { + // SAFETY: The safety requirements of this function ensure that `ptr` is valid and that the + // caller is the owner of the mutex. + unsafe { bindings::mutex_unlock(ptr) }; + } +} -- GitLab From c6d917a498bfef603f41bfc4d31e9699bb2909fc Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Wed, 19 Apr 2023 14:44:26 -0300 Subject: [PATCH 3808/5631] rust: lock: introduce `SpinLock` This is the `spinlock_t` lock backend and allows Rust code to use the kernel spinlock idiomatically. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230419174426.132207-1-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/helpers.c | 24 +++++++ rust/kernel/sync.rs | 2 +- rust/kernel/sync/lock.rs | 1 + rust/kernel/sync/lock/spinlock.rs | 116 ++++++++++++++++++++++++++++++ 4 files changed, 142 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/sync/lock/spinlock.rs diff --git a/rust/helpers.c b/rust/helpers.c index 86af099d2d66..446e3cfdb935 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -23,6 +23,7 @@ #include #include #include +#include __noreturn void rust_helper_BUG(void) { @@ -36,6 +37,29 @@ void rust_helper_mutex_lock(struct mutex *lock) } EXPORT_SYMBOL_GPL(rust_helper_mutex_lock); +void rust_helper___spin_lock_init(spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + __raw_spin_lock_init(spinlock_check(lock), name, key, LD_WAIT_CONFIG); +#else + spin_lock_init(lock); +#endif +} +EXPORT_SYMBOL_GPL(rust_helper___spin_lock_init); + +void rust_helper_spin_lock(spinlock_t *lock) +{ + spin_lock(lock); +} +EXPORT_SYMBOL_GPL(rust_helper_spin_lock); + +void rust_helper_spin_unlock(spinlock_t *lock) +{ + spin_unlock(lock); +} +EXPORT_SYMBOL_GPL(rust_helper_spin_unlock); + refcount_t rust_helper_REFCOUNT_INIT(int n) { return (refcount_t)REFCOUNT_INIT(n); diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 693f0b7f4e4f..c997ff7e951e 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -11,7 +11,7 @@ mod arc; pub mod lock; pub use arc::{Arc, ArcBorrow, UniqueArc}; -pub use lock::mutex::Mutex; +pub use lock::{mutex::Mutex, spinlock::SpinLock}; /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. #[repr(transparent)] diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 2ea512a8dfab..3c166e08f3d4 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -11,6 +11,7 @@ use core::{cell::UnsafeCell, marker::PhantomData, marker::PhantomPinned}; use macros::pin_data; pub mod mutex; +pub mod spinlock; /// The "backend" of a lock. /// diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs new file mode 100644 index 000000000000..a52d20fc9755 --- /dev/null +++ b/rust/kernel/sync/lock/spinlock.rs @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A kernel spinlock. +//! +//! This module allows Rust code to use the kernel's `spinlock_t`. + +use crate::bindings; + +/// Creates a [`SpinLock`] initialiser with the given name and a newly-created lock class. +/// +/// It uses the name if one is given, otherwise it generates one based on the file name and line +/// number. +#[macro_export] +macro_rules! new_spinlock { + ($inner:expr $(, $name:literal)? $(,)?) => { + $crate::sync::SpinLock::new( + $inner, $crate::optional_name!($($name)?), $crate::static_lock_class!()) + }; +} + +/// A spinlock. +/// +/// Exposes the kernel's [`spinlock_t`]. When multiple CPUs attempt to lock the same spinlock, only +/// one at a time is allowed to progress, the others will block (spinning) until the spinlock is +/// unlocked, at which point another CPU will be allowed to make progress. +/// +/// Instances of [`SpinLock`] need a lock class and to be pinned. The recommended way to create such +/// instances is with the [`pin_init`](crate::pin_init) and [`new_spinlock`] macros. +/// +/// # Examples +/// +/// The following example shows how to declare, allocate and initialise a struct (`Example`) that +/// contains an inner struct (`Inner`) that is protected by a spinlock. +/// +/// ``` +/// use kernel::{init::InPlaceInit, init::PinInit, new_spinlock, pin_init, sync::SpinLock}; +/// +/// struct Inner { +/// a: u32, +/// b: u32, +/// } +/// +/// #[pin_data] +/// struct Example { +/// c: u32, +/// #[pin] +/// d: SpinLock, +/// } +/// +/// impl Example { +/// fn new() -> impl PinInit { +/// pin_init!(Self { +/// c: 10, +/// d <- new_spinlock!(Inner { a: 20, b: 30 }), +/// }) +/// } +/// } +/// +/// // Allocate a boxed `Example`. +/// let e = Box::pin_init(Example::new())?; +/// assert_eq!(e.c, 10); +/// assert_eq!(e.d.lock().a, 20); +/// assert_eq!(e.d.lock().b, 30); +/// ``` +/// +/// The following example shows how to use interior mutability to modify the contents of a struct +/// protected by a spinlock despite only having a shared reference: +/// +/// ``` +/// use kernel::sync::SpinLock; +/// +/// struct Example { +/// a: u32, +/// b: u32, +/// } +/// +/// fn example(m: &SpinLock) { +/// let mut guard = m.lock(); +/// guard.a += 10; +/// guard.b += 20; +/// } +/// ``` +/// +/// [`spinlock_t`]: ../../../../include/linux/spinlock.h +pub type SpinLock = super::Lock; + +/// A kernel `spinlock_t` lock backend. +pub struct SpinLockBackend; + +// SAFETY: The underlying kernel `spinlock_t` object ensures mutual exclusion. +unsafe impl super::Backend for SpinLockBackend { + type State = bindings::spinlock_t; + type GuardState = (); + + unsafe fn init( + ptr: *mut Self::State, + name: *const core::ffi::c_char, + key: *mut bindings::lock_class_key, + ) { + // SAFETY: The safety requirements ensure that `ptr` is valid for writes, and `name` and + // `key` are valid for read indefinitely. + unsafe { bindings::__spin_lock_init(ptr, name, key) } + } + + unsafe fn lock(ptr: *mut Self::State) -> Self::GuardState { + // SAFETY: The safety requirements of this function ensure that `ptr` points to valid + // memory, and that it has been initialised before. + unsafe { bindings::spin_lock(ptr) } + } + + unsafe fn unlock(ptr: *mut Self::State, _guard_state: &Self::GuardState) { + // SAFETY: The safety requirements of this function ensure that `ptr` is valid and that the + // caller is the owner of the mutex. + unsafe { bindings::spin_unlock(ptr) } + } +} -- GitLab From f1fbd6a864d417443cdacd6bfdb7fd626993da7e Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:38 -0300 Subject: [PATCH 3809/5631] rust: introduce `ARef` This is an owned reference to an object that is always ref-counted. This is meant to be used in wrappers for C types that have their own ref counting functions, for example, tasks, files, inodes, dentries, etc. Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Reviewed-by: Gary Guo Link: https://lore.kernel.org/r/20230411054543.21278-8-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/types.rs | 107 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs index a4b1e3778da7..29db59d6119a 100644 --- a/rust/kernel/types.rs +++ b/rust/kernel/types.rs @@ -6,8 +6,10 @@ use crate::init::{self, PinInit}; use alloc::boxed::Box; use core::{ cell::UnsafeCell, + marker::PhantomData, mem::MaybeUninit, ops::{Deref, DerefMut}, + ptr::NonNull, }; /// Used to transfer ownership to and from foreign (non-Rust) languages. @@ -268,6 +270,111 @@ impl Opaque { } } +/// Types that are _always_ reference counted. +/// +/// It allows such types to define their own custom ref increment and decrement functions. +/// Additionally, it allows users to convert from a shared reference `&T` to an owned reference +/// [`ARef`]. +/// +/// This is usually implemented by wrappers to existing structures on the C side of the code. For +/// Rust code, the recommendation is to use [`Arc`](crate::sync::Arc) to create reference-counted +/// instances of a type. +/// +/// # Safety +/// +/// Implementers must ensure that increments to the reference count keep the object alive in memory +/// at least until matching decrements are performed. +/// +/// Implementers must also ensure that all instances are reference-counted. (Otherwise they +/// won't be able to honour the requirement that [`AlwaysRefCounted::inc_ref`] keep the object +/// alive.) +pub unsafe trait AlwaysRefCounted { + /// Increments the reference count on the object. + fn inc_ref(&self); + + /// Decrements the reference count on the object. + /// + /// Frees the object when the count reaches zero. + /// + /// # Safety + /// + /// Callers must ensure that there was a previous matching increment to the reference count, + /// and that the object is no longer used after its reference count is decremented (as it may + /// result in the object being freed), unless the caller owns another increment on the refcount + /// (e.g., it calls [`AlwaysRefCounted::inc_ref`] twice, then calls + /// [`AlwaysRefCounted::dec_ref`] once). + unsafe fn dec_ref(obj: NonNull); +} + +/// An owned reference to an always-reference-counted object. +/// +/// The object's reference count is automatically decremented when an instance of [`ARef`] is +/// dropped. It is also automatically incremented when a new instance is created via +/// [`ARef::clone`]. +/// +/// # Invariants +/// +/// The pointer stored in `ptr` is non-null and valid for the lifetime of the [`ARef`] instance. In +/// particular, the [`ARef`] instance owns an increment on the underlying object's reference count. +pub struct ARef { + ptr: NonNull, + _p: PhantomData, +} + +impl ARef { + /// Creates a new instance of [`ARef`]. + /// + /// It takes over an increment of the reference count on the underlying object. + /// + /// # Safety + /// + /// Callers must ensure that the reference count was incremented at least once, and that they + /// are properly relinquishing one increment. That is, if there is only one increment, callers + /// must not use the underlying object anymore -- it is only safe to do so via the newly + /// created [`ARef`]. + pub unsafe fn from_raw(ptr: NonNull) -> Self { + // INVARIANT: The safety requirements guarantee that the new instance now owns the + // increment on the refcount. + Self { + ptr, + _p: PhantomData, + } + } +} + +impl Clone for ARef { + fn clone(&self) -> Self { + self.inc_ref(); + // SAFETY: We just incremented the refcount above. + unsafe { Self::from_raw(self.ptr) } + } +} + +impl Deref for ARef { + type Target = T; + + fn deref(&self) -> &Self::Target { + // SAFETY: The type invariants guarantee that the object is valid. + unsafe { self.ptr.as_ref() } + } +} + +impl From<&T> for ARef { + fn from(b: &T) -> Self { + b.inc_ref(); + // SAFETY: We just incremented the refcount above. + unsafe { Self::from_raw(NonNull::from(b)) } + } +} + +impl Drop for ARef { + fn drop(&mut self) { + // SAFETY: The type invariants guarantee that the `ARef` owns the reference we're about to + // decrement. + unsafe { T::dec_ref(self.ptr) }; + } +} + /// A sum type that always holds either a value of type `L` or `R`. pub enum Either { /// Constructs an instance of [`Either`] containing a value of type `L`. -- GitLab From 313c4281bc9dfa98d76a71b16a684af1c52e7751 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:39 -0300 Subject: [PATCH 3810/5631] rust: add basic `Task` It is an abstraction for C's `struct task_struct`. It implements `AlwaysRefCounted`, so the refcount of the wrapped object is managed safely on the Rust side. Cc: Ingo Molnar Cc: Peter Zijlstra Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230411054543.21278-9-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/bindings/bindings_helper.h | 1 + rust/helpers.c | 19 +++++++++ rust/kernel/lib.rs | 1 + rust/kernel/task.rs | 75 +++++++++++++++++++++++++++++++++ 4 files changed, 96 insertions(+) create mode 100644 rust/kernel/task.rs diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 75d85bd6c592..03656a44a83f 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -8,6 +8,7 @@ #include #include +#include /* `bindgen` gets confused at certain things. */ const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; diff --git a/rust/helpers.c b/rust/helpers.c index 446e3cfdb935..6e5b2c953d36 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -24,6 +24,7 @@ #include #include #include +#include __noreturn void rust_helper_BUG(void) { @@ -60,6 +61,12 @@ void rust_helper_spin_unlock(spinlock_t *lock) } EXPORT_SYMBOL_GPL(rust_helper_spin_unlock); +int rust_helper_signal_pending(struct task_struct *t) +{ + return signal_pending(t); +} +EXPORT_SYMBOL_GPL(rust_helper_signal_pending); + refcount_t rust_helper_REFCOUNT_INIT(int n) { return (refcount_t)REFCOUNT_INIT(n); @@ -96,6 +103,18 @@ long rust_helper_PTR_ERR(__force const void *ptr) } EXPORT_SYMBOL_GPL(rust_helper_PTR_ERR); +void rust_helper_get_task_struct(struct task_struct *t) +{ + get_task_struct(t); +} +EXPORT_SYMBOL_GPL(rust_helper_get_task_struct); + +void rust_helper_put_task_struct(struct task_struct *t) +{ + put_task_struct(t); +} +EXPORT_SYMBOL_GPL(rust_helper_put_task_struct); + /* * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type * as the Rust `usize` type, so we can use it in contexts where Rust diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 2d7606135ef6..ee27e10da479 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -44,6 +44,7 @@ mod static_assert; pub mod std_vendor; pub mod str; pub mod sync; +pub mod task; pub mod types; #[doc(hidden)] diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs new file mode 100644 index 000000000000..d70cad131956 --- /dev/null +++ b/rust/kernel/task.rs @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Tasks (threads and processes). +//! +//! C header: [`include/linux/sched.h`](../../../../include/linux/sched.h). + +use crate::{bindings, types::Opaque}; +use core::ptr; + +/// Wraps the kernel's `struct task_struct`. +/// +/// # Invariants +/// +/// All instances are valid tasks created by the C portion of the kernel. +/// +/// Instances of this type are always ref-counted, that is, a call to `get_task_struct` ensures +/// that the allocation remains valid at least until the matching call to `put_task_struct`. +#[repr(transparent)] +pub struct Task(pub(crate) Opaque); + +// SAFETY: It's OK to access `Task` through references from other threads because we're either +// accessing properties that don't change (e.g., `pid`, `group_leader`) or that are properly +// synchronised by C code (e.g., `signal_pending`). +unsafe impl Sync for Task {} + +/// The type of process identifiers (PIDs). +type Pid = bindings::pid_t; + +impl Task { + /// Returns the group leader of the given task. + pub fn group_leader(&self) -> &Task { + // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always + // have a valid group_leader. + let ptr = unsafe { *ptr::addr_of!((*self.0.get()).group_leader) }; + + // SAFETY: The lifetime of the returned task reference is tied to the lifetime of `self`, + // and given that a task has a reference to its group leader, we know it must be valid for + // the lifetime of the returned task reference. + unsafe { &*ptr.cast() } + } + + /// Returns the PID of the given task. + pub fn pid(&self) -> Pid { + // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always + // have a valid pid. + unsafe { *ptr::addr_of!((*self.0.get()).pid) } + } + + /// Determines whether the given task has pending signals. + pub fn signal_pending(&self) -> bool { + // SAFETY: By the type invariant, we know that `self.0` is valid. + unsafe { bindings::signal_pending(self.0.get()) != 0 } + } + + /// Wakes up the task. + pub fn wake_up(&self) { + // SAFETY: By the type invariant, we know that `self.0.get()` is non-null and valid. + // And `wake_up_process` is safe to be called for any valid task, even if the task is + // running. + unsafe { bindings::wake_up_process(self.0.get()) }; + } +} + +// SAFETY: The type invariants guarantee that `Task` is always ref-counted. +unsafe impl crate::types::AlwaysRefCounted for Task { + fn inc_ref(&self) { + // SAFETY: The existence of a shared reference means that the refcount is nonzero. + unsafe { bindings::get_task_struct(self.0.get()) }; + } + + unsafe fn dec_ref(obj: ptr::NonNull) { + // SAFETY: The safety requirements guarantee that the refcount is nonzero. + unsafe { bindings::put_task_struct(obj.cast().as_ptr()) } + } +} -- GitLab From 8da7a2b7432e8f043f04515895687f72cdb3e0a8 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:40 -0300 Subject: [PATCH 3811/5631] rust: introduce `current` This allows Rust code to get a reference to the current task without having to increment the refcount, but still guaranteeing memory safety. Cc: Ingo Molnar Cc: Peter Zijlstra Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20230411054543.21278-10-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/helpers.c | 6 ++++ rust/kernel/prelude.rs | 2 ++ rust/kernel/task.rs | 82 +++++++++++++++++++++++++++++++++++++++++- 3 files changed, 89 insertions(+), 1 deletion(-) diff --git a/rust/helpers.c b/rust/helpers.c index 6e5b2c953d36..2cb7b82053d8 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -103,6 +103,12 @@ long rust_helper_PTR_ERR(__force const void *ptr) } EXPORT_SYMBOL_GPL(rust_helper_PTR_ERR); +struct task_struct *rust_helper_get_current(void) +{ + return current; +} +EXPORT_SYMBOL_GPL(rust_helper_get_current); + void rust_helper_get_task_struct(struct task_struct *t) { get_task_struct(t); diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index fcdc511d2ce8..c28587d68ebc 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -36,3 +36,5 @@ pub use super::error::{code::*, Error, Result}; pub use super::{str::CStr, ThisModule}; pub use super::init::{InPlaceInit, Init, PinInit}; + +pub use super::current; diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs index d70cad131956..526d29a0ae27 100644 --- a/rust/kernel/task.rs +++ b/rust/kernel/task.rs @@ -5,7 +5,17 @@ //! C header: [`include/linux/sched.h`](../../../../include/linux/sched.h). use crate::{bindings, types::Opaque}; -use core::ptr; +use core::{marker::PhantomData, ops::Deref, ptr}; + +/// Returns the currently running task. +#[macro_export] +macro_rules! current { + () => { + // SAFETY: Deref + addr-of below create a temporary `TaskRef` that cannot outlive the + // caller. + unsafe { &*$crate::task::Task::current() } + }; +} /// Wraps the kernel's `struct task_struct`. /// @@ -15,6 +25,42 @@ use core::ptr; /// /// Instances of this type are always ref-counted, that is, a call to `get_task_struct` ensures /// that the allocation remains valid at least until the matching call to `put_task_struct`. +/// +/// # Examples +/// +/// The following is an example of getting the PID of the current thread with zero additional cost +/// when compared to the C version: +/// +/// ``` +/// let pid = current!().pid(); +/// ``` +/// +/// Getting the PID of the current process, also zero additional cost: +/// +/// ``` +/// let pid = current!().group_leader().pid(); +/// ``` +/// +/// Getting the current task and storing it in some struct. The reference count is automatically +/// incremented when creating `State` and decremented when it is dropped: +/// +/// ``` +/// use kernel::{task::Task, types::ARef}; +/// +/// struct State { +/// creator: ARef, +/// index: u32, +/// } +/// +/// impl State { +/// fn new() -> Self { +/// Self { +/// creator: current!().into(), +/// index: 0, +/// } +/// } +/// } +/// ``` #[repr(transparent)] pub struct Task(pub(crate) Opaque); @@ -27,6 +73,40 @@ unsafe impl Sync for Task {} type Pid = bindings::pid_t; impl Task { + /// Returns a task reference for the currently executing task/thread. + /// + /// The recommended way to get the current task/thread is to use the + /// [`current`](crate::current) macro because it is safe. + /// + /// # Safety + /// + /// Callers must ensure that the returned object doesn't outlive the current task/thread. + pub unsafe fn current() -> impl Deref { + struct TaskRef<'a> { + task: &'a Task, + _not_send: PhantomData<*mut ()>, + } + + impl Deref for TaskRef<'_> { + type Target = Task; + + fn deref(&self) -> &Self::Target { + self.task + } + } + + // SAFETY: Just an FFI call with no additional safety requirements. + let ptr = unsafe { bindings::get_current() }; + + TaskRef { + // SAFETY: If the current thread is still running, the current task is valid. Given + // that `TaskRef` is not `Send`, we know it cannot be transferred to another thread + // (where it could potentially outlive the caller). + task: unsafe { &*ptr.cast() }, + _not_send: PhantomData, + } + } + /// Returns the group leader of the given task. pub fn group_leader(&self) -> &Task { // SAFETY: By the type invariant, we know that `self.0` is a valid task. Valid tasks always -- GitLab From 7b1f55e3a984aaed0121f90f9f8580f18b7b561e Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Tue, 11 Apr 2023 02:45:43 -0300 Subject: [PATCH 3812/5631] rust: sync: introduce `LockedBy` This allows us to have data protected by a lock despite not being wrapped by it. Access is granted by providing evidence that the lock is held by the caller. Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Reviewed-by: Benno Lossin Link: https://lore.kernel.org/r/20230411054543.21278-13-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/kernel/sync.rs | 2 + rust/kernel/sync/lock.rs | 2 +- rust/kernel/sync/locked_by.rs | 156 ++++++++++++++++++++++++++++++++++ 3 files changed, 159 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/sync/locked_by.rs diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index c997ff7e951e..5393b0d76619 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -9,9 +9,11 @@ use crate::types::Opaque; mod arc; pub mod lock; +mod locked_by; pub use arc::{Arc, ArcBorrow, UniqueArc}; pub use lock::{mutex::Mutex, spinlock::SpinLock}; +pub use locked_by::LockedBy; /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`. #[repr(transparent)] diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 3c166e08f3d4..46e3328b67a6 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -74,7 +74,7 @@ pub struct Lock { _pin: PhantomPinned, /// The data protected by the lock. - data: UnsafeCell, + pub(crate) data: UnsafeCell, } // SAFETY: `Lock` can be transferred across thread boundaries iff the data it protects can. diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs new file mode 100644 index 000000000000..b17ee5cd98f3 --- /dev/null +++ b/rust/kernel/sync/locked_by.rs @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A wrapper for data protected by a lock that does not wrap it. + +use super::{lock::Backend, lock::Lock}; +use crate::build_assert; +use core::{cell::UnsafeCell, mem::size_of, ptr}; + +/// Allows access to some data to be serialised by a lock that does not wrap it. +/// +/// In most cases, data protected by a lock is wrapped by the appropriate lock type, e.g., +/// [`super::Mutex`] or [`super::SpinLock`]. [`LockedBy`] is meant for cases when this is not +/// possible. For example, if a container has a lock and some data in the contained elements needs +/// to be protected by the same lock. +/// +/// [`LockedBy`] wraps the data in lieu of another locking primitive, and only allows access to it +/// when the caller shows evidence that the 'external' lock is locked. It panics if the evidence +/// refers to the wrong instance of the lock. +/// +/// # Examples +/// +/// The following is an example for illustrative purposes: `InnerDirectory::bytes_used` is an +/// aggregate of all `InnerFile::bytes_used` and must be kept consistent; so we wrap `InnerFile` in +/// a `LockedBy` so that it shares a lock with `InnerDirectory`. This allows us to enforce at +/// compile-time that access to `InnerFile` is only granted when an `InnerDirectory` is also +/// locked; we enforce at run time that the right `InnerDirectory` is locked. +/// +/// ``` +/// use kernel::sync::{LockedBy, Mutex}; +/// +/// struct InnerFile { +/// bytes_used: u64, +/// } +/// +/// struct File { +/// _ino: u32, +/// inner: LockedBy, +/// } +/// +/// struct InnerDirectory { +/// /// The sum of the bytes used by all files. +/// bytes_used: u64, +/// _files: Vec, +/// } +/// +/// struct Directory { +/// _ino: u32, +/// inner: Mutex, +/// } +/// +/// /// Prints `bytes_used` from both the directory and file. +/// fn print_bytes_used(dir: &Directory, file: &File) { +/// let guard = dir.inner.lock(); +/// let inner_file = file.inner.access(&guard); +/// pr_info!("{} {}", guard.bytes_used, inner_file.bytes_used); +/// } +/// +/// /// Increments `bytes_used` for both the directory and file. +/// fn inc_bytes_used(dir: &Directory, file: &File) { +/// let mut guard = dir.inner.lock(); +/// guard.bytes_used += 10; +/// +/// let file_inner = file.inner.access_mut(&mut guard); +/// file_inner.bytes_used += 10; +/// } +/// +/// /// Creates a new file. +/// fn new_file(ino: u32, dir: &Directory) -> File { +/// File { +/// _ino: ino, +/// inner: LockedBy::new(&dir.inner, InnerFile { bytes_used: 0 }), +/// } +/// } +/// ``` +pub struct LockedBy { + owner: *const U, + data: UnsafeCell, +} + +// SAFETY: `LockedBy` can be transferred across thread boundaries iff the data it protects can. +unsafe impl Send for LockedBy {} + +// SAFETY: `LockedBy` serialises the interior mutability it provides, so it is `Sync` as long as the +// data it protects is `Send`. +unsafe impl Sync for LockedBy {} + +impl LockedBy { + /// Constructs a new instance of [`LockedBy`]. + /// + /// It stores a raw pointer to the owner that is never dereferenced. It is only used to ensure + /// that the right owner is being used to access the protected data. If the owner is freed, the + /// data becomes inaccessible; if another instance of the owner is allocated *on the same + /// memory location*, the data becomes accessible again: none of this affects memory safety + /// because in any case at most one thread (or CPU) can access the protected data at a time. + pub fn new(owner: &Lock, data: T) -> Self { + build_assert!( + size_of::>() > 0, + "The lock type cannot be a ZST because it may be impossible to distinguish instances" + ); + Self { + owner: owner.data.get(), + data: UnsafeCell::new(data), + } + } +} + +impl LockedBy { + /// Returns a reference to the protected data when the caller provides evidence (via a + /// reference) that the owner is locked. + /// + /// `U` cannot be a zero-sized type (ZST) because there are ways to get an `&U` that matches + /// the data protected by the lock without actually holding it. + /// + /// # Panics + /// + /// Panics if `owner` is different from the data protected by the lock used in + /// [`new`](LockedBy::new). + pub fn access<'a>(&'a self, owner: &'a U) -> &'a T { + build_assert!( + size_of::() > 0, + "`U` cannot be a ZST because `owner` wouldn't be unique" + ); + if !ptr::eq(owner, self.owner) { + panic!("mismatched owners"); + } + + // SAFETY: `owner` is evidence that the owner is locked. + unsafe { &*self.data.get() } + } + + /// Returns a mutable reference to the protected data when the caller provides evidence (via a + /// mutable owner) that the owner is locked mutably. + /// + /// `U` cannot be a zero-sized type (ZST) because there are ways to get an `&mut U` that + /// matches the data protected by the lock without actually holding it. + /// + /// Showing a mutable reference to the owner is sufficient because we know no other references + /// can exist to it. + /// + /// # Panics + /// + /// Panics if `owner` is different from the data protected by the lock used in + /// [`new`](LockedBy::new). + pub fn access_mut<'a>(&'a self, owner: &'a mut U) -> &'a mut T { + build_assert!( + size_of::() > 0, + "`U` cannot be a ZST because `owner` wouldn't be unique" + ); + if !ptr::eq(owner, self.owner) { + panic!("mismatched owners"); + } + + // SAFETY: `owner` is evidence that there is only one reference to the owner. + unsafe { &mut *self.data.get() } + } +} -- GitLab From e32cca32c3d452a277884502b9155f3325caf80e Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Mon, 27 Mar 2023 15:43:08 -0300 Subject: [PATCH 3813/5631] rust: lock: add `Guard::do_unlocked` It releases the lock, executes some function provided by the caller, then reacquires the lock. This is preparation for the implementation of condvars, which will sleep after between unlocking and relocking. We need an explicit `relock` method for primitives like `SpinLock` that have an irqsave variant: we use the guard state to determine if the lock was originally acquired with the regular `lock` function or `lock_irqsave`. Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/rust-for-linux/20230412121431.41627-1-wedsonaf@gmail.com/ [ Removed the irqsave bits as discussed. ] Signed-off-by: Miguel Ojeda --- rust/kernel/sync/lock.rs | 29 ++++++++++++++++++++++++++++- rust/kernel/sync/lock/spinlock.rs | 3 ++- 2 files changed, 30 insertions(+), 2 deletions(-) diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 46e3328b67a6..802465d1fa54 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -6,7 +6,7 @@ //! spinlocks, raw spinlocks) to be provided with minimal effort. use super::LockClassKey; -use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque}; +use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque, types::ScopeGuard}; use core::{cell::UnsafeCell, marker::PhantomData, marker::PhantomPinned}; use macros::pin_data; @@ -22,6 +22,8 @@ pub mod spinlock; /// /// - Implementers must ensure that only one thread/CPU may access the protected data once the lock /// is owned, that is, between calls to `lock` and `unlock`. +/// - Implementers must also ensure that `relock` uses the same locking method as the original +/// lock operation. pub unsafe trait Backend { /// The state required by the lock. type State; @@ -55,6 +57,17 @@ pub unsafe trait Backend { /// /// It must only be called by the current owner of the lock. unsafe fn unlock(ptr: *mut Self::State, guard_state: &Self::GuardState); + + /// Reacquires the lock, making the caller its owner. + /// + /// # Safety + /// + /// Callers must ensure that `guard_state` comes from a previous call to [`Backend::lock`] (or + /// variant) that has been unlocked with [`Backend::unlock`] and will be relocked now. + unsafe fn relock(ptr: *mut Self::State, guard_state: &mut Self::GuardState) { + // SAFETY: The safety requirements ensure that the lock is initialised. + *guard_state = unsafe { Self::lock(ptr) }; + } } /// A mutual exclusion primitive. @@ -126,6 +139,20 @@ pub struct Guard<'a, T: ?Sized, B: Backend> { // SAFETY: `Guard` is sync when the data protected by the lock is also sync. unsafe impl Sync for Guard<'_, T, B> {} +impl Guard<'_, T, B> { + #[allow(dead_code)] + pub(crate) fn do_unlocked(&mut self, cb: impl FnOnce()) { + // SAFETY: The caller owns the lock, so it is safe to unlock it. + unsafe { B::unlock(self.lock.state.get(), &self.state) }; + + // SAFETY: The lock was just unlocked above and is being relocked now. + let _relock = + ScopeGuard::new(|| unsafe { B::relock(self.lock.state.get(), &mut self.state) }); + + cb(); + } +} + impl core::ops::Deref for Guard<'_, T, B> { type Target = T; diff --git a/rust/kernel/sync/lock/spinlock.rs b/rust/kernel/sync/lock/spinlock.rs index a52d20fc9755..979b56464a4e 100644 --- a/rust/kernel/sync/lock/spinlock.rs +++ b/rust/kernel/sync/lock/spinlock.rs @@ -87,7 +87,8 @@ pub type SpinLock = super::Lock; /// A kernel `spinlock_t` lock backend. pub struct SpinLockBackend; -// SAFETY: The underlying kernel `spinlock_t` object ensures mutual exclusion. +// SAFETY: The underlying kernel `spinlock_t` object ensures mutual exclusion. `relock` uses the +// default implementation that always calls the same locking method. unsafe impl super::Backend for SpinLockBackend { type State = bindings::spinlock_t; type GuardState = (); -- GitLab From 19096bce815716cf93fc1ef3965629c3affa26f1 Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Sun, 26 Mar 2023 00:57:38 -0300 Subject: [PATCH 3814/5631] rust: sync: introduce `CondVar` This is the traditional condition variable or monitor synchronisation primitive. It is implemented with C's `wait_queue_head_t`. It allows users to release a lock and go to sleep while guaranteeing that notifications won't be missed. This is achieved by enqueuing a wait entry before releasing the lock. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Wedson Almeida Filho Reviewed-by: Alice Ryhl Link: https://lore.kernel.org/r/20230411054543.21278-12-wedsonaf@gmail.com Signed-off-by: Miguel Ojeda --- rust/bindings/bindings_helper.h | 1 + rust/helpers.c | 7 ++ rust/kernel/sync.rs | 2 + rust/kernel/sync/condvar.rs | 174 ++++++++++++++++++++++++++++++++ rust/kernel/sync/lock.rs | 1 - 5 files changed, 184 insertions(+), 1 deletion(-) create mode 100644 rust/kernel/sync/condvar.rs diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 03656a44a83f..50e7a76d5455 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -8,6 +8,7 @@ #include #include +#include #include /* `bindgen` gets confused at certain things. */ diff --git a/rust/helpers.c b/rust/helpers.c index 2cb7b82053d8..81e80261d597 100644 --- a/rust/helpers.c +++ b/rust/helpers.c @@ -25,6 +25,7 @@ #include #include #include +#include __noreturn void rust_helper_BUG(void) { @@ -61,6 +62,12 @@ void rust_helper_spin_unlock(spinlock_t *lock) } EXPORT_SYMBOL_GPL(rust_helper_spin_unlock); +void rust_helper_init_wait(struct wait_queue_entry *wq_entry) +{ + init_wait(wq_entry); +} +EXPORT_SYMBOL_GPL(rust_helper_init_wait); + int rust_helper_signal_pending(struct task_struct *t) { return signal_pending(t); diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs index 5393b0d76619..d219ee518eff 100644 --- a/rust/kernel/sync.rs +++ b/rust/kernel/sync.rs @@ -8,10 +8,12 @@ use crate::types::Opaque; mod arc; +mod condvar; pub mod lock; mod locked_by; pub use arc::{Arc, ArcBorrow, UniqueArc}; +pub use condvar::CondVar; pub use lock::{mutex::Mutex, spinlock::SpinLock}; pub use locked_by::LockedBy; diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs new file mode 100644 index 000000000000..ed353399c4e5 --- /dev/null +++ b/rust/kernel/sync/condvar.rs @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! A condition variable. +//! +//! This module allows Rust code to use the kernel's [`struct wait_queue_head`] as a condition +//! variable. + +use super::{lock::Backend, lock::Guard, LockClassKey}; +use crate::{bindings, init::PinInit, pin_init, str::CStr, types::Opaque}; +use core::marker::PhantomPinned; +use macros::pin_data; + +/// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class. +#[macro_export] +macro_rules! new_condvar { + ($($name:literal)?) => { + $crate::sync::CondVar::new($crate::optional_name!($($name)?), $crate::static_lock_class!()) + }; +} + +/// A conditional variable. +/// +/// Exposes the kernel's [`struct wait_queue_head`] as a condition variable. It allows the caller to +/// atomically release the given lock and go to sleep. It reacquires the lock when it wakes up. And +/// it wakes up when notified by another thread (via [`CondVar::notify_one`] or +/// [`CondVar::notify_all`]) or because the thread received a signal. It may also wake up +/// spuriously. +/// +/// Instances of [`CondVar`] need a lock class and to be pinned. The recommended way to create such +/// instances is with the [`pin_init`](crate::pin_init) and [`new_condvar`] macros. +/// +/// # Examples +/// +/// The following is an example of using a condvar with a mutex: +/// +/// ``` +/// use kernel::sync::{CondVar, Mutex}; +/// use kernel::{new_condvar, new_mutex}; +/// +/// #[pin_data] +/// pub struct Example { +/// #[pin] +/// value: Mutex, +/// +/// #[pin] +/// value_changed: CondVar, +/// } +/// +/// /// Waits for `e.value` to become `v`. +/// fn wait_for_value(e: &Example, v: u32) { +/// let mut guard = e.value.lock(); +/// while *guard != v { +/// e.value_changed.wait_uninterruptible(&mut guard); +/// } +/// } +/// +/// /// Increments `e.value` and notifies all potential waiters. +/// fn increment(e: &Example) { +/// *e.value.lock() += 1; +/// e.value_changed.notify_all(); +/// } +/// +/// /// Allocates a new boxed `Example`. +/// fn new_example() -> Result>> { +/// Box::pin_init(pin_init!(Example { +/// value <- new_mutex!(0), +/// value_changed <- new_condvar!(), +/// })) +/// } +/// ``` +/// +/// [`struct wait_queue_head`]: ../../../include/linux/wait.h +#[pin_data] +pub struct CondVar { + #[pin] + pub(crate) wait_list: Opaque, + + /// A condvar needs to be pinned because it contains a [`struct list_head`] that is + /// self-referential, so it cannot be safely moved once it is initialised. + #[pin] + _pin: PhantomPinned, +} + +// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on any thread. +#[allow(clippy::non_send_fields_in_send_ty)] +unsafe impl Send for CondVar {} + +// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on multiple threads +// concurrently. +unsafe impl Sync for CondVar {} + +impl CondVar { + /// Constructs a new condvar initialiser. + #[allow(clippy::new_ret_no_self)] + pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit { + pin_init!(Self { + _pin: PhantomPinned, + // SAFETY: `slot` is valid while the closure is called and both `name` and `key` have + // static lifetimes so they live indefinitely. + wait_list <- Opaque::ffi_init(|slot| unsafe { + bindings::__init_waitqueue_head(slot, name.as_char_ptr(), key.as_ptr()) + }), + }) + } + + fn wait_internal(&self, wait_state: u32, guard: &mut Guard<'_, T, B>) { + let wait = Opaque::::uninit(); + + // SAFETY: `wait` points to valid memory. + unsafe { bindings::init_wait(wait.get()) }; + + // SAFETY: Both `wait` and `wait_list` point to valid memory. + unsafe { + bindings::prepare_to_wait_exclusive(self.wait_list.get(), wait.get(), wait_state as _) + }; + + // SAFETY: No arguments, switches to another thread. + guard.do_unlocked(|| unsafe { bindings::schedule() }); + + // SAFETY: Both `wait` and `wait_list` point to valid memory. + unsafe { bindings::finish_wait(self.wait_list.get(), wait.get()) }; + } + + /// Releases the lock and waits for a notification in interruptible mode. + /// + /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the + /// thread to sleep, reacquiring the lock on wake up. It wakes up when notified by + /// [`CondVar::notify_one`] or [`CondVar::notify_all`], or when the thread receives a signal. + /// It may also wake up spuriously. + /// + /// Returns whether there is a signal pending. + #[must_use = "wait returns if a signal is pending, so the caller must check the return value"] + pub fn wait(&self, guard: &mut Guard<'_, T, B>) -> bool { + self.wait_internal(bindings::TASK_INTERRUPTIBLE, guard); + crate::current!().signal_pending() + } + + /// Releases the lock and waits for a notification in uninterruptible mode. + /// + /// Similar to [`CondVar::wait`], except that the wait is not interruptible. That is, the + /// thread won't wake up due to signals. It may, however, wake up supirously. + pub fn wait_uninterruptible(&self, guard: &mut Guard<'_, T, B>) { + self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, guard) + } + + /// Calls the kernel function to notify the appropriate number of threads with the given flags. + fn notify(&self, count: i32, flags: u32) { + // SAFETY: `wait_list` points to valid memory. + unsafe { + bindings::__wake_up( + self.wait_list.get(), + bindings::TASK_NORMAL, + count, + flags as _, + ) + }; + } + + /// Wakes a single waiter up, if any. + /// + /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost + /// completely (as opposed to automatically waking up the next waiter). + pub fn notify_one(&self) { + self.notify(1, 0); + } + + /// Wakes all waiters up, if any. + /// + /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost + /// completely (as opposed to automatically waking up the next waiter). + pub fn notify_all(&self) { + self.notify(0, 0); + } +} diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index 802465d1fa54..a2216325632d 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -140,7 +140,6 @@ pub struct Guard<'a, T: ?Sized, B: Backend> { unsafe impl Sync for Guard<'_, T, B> {} impl Guard<'_, T, B> { - #[allow(dead_code)] pub(crate) fn do_unlocked(&mut self, cb: impl FnOnce()) { // SAFETY: The caller owns the lock, so it is safe to unlock it. unsafe { B::unlock(self.lock.state.get(), &self.state) }; -- GitLab From 4e1746656839ab1e88d76eec4d2fa0b41d585604 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 18:33:52 +0900 Subject: [PATCH 3815/5631] rust: uapi: Add UAPI crate This crate mirrors the `bindings` crate, but will contain only UAPI bindings. Unlike the bindings crate, drivers may directly use this crate if they have to interface with userspace. Initially, just bind the generic ioctl stuff. In the future, we would also like to add additional checks to ensure that all types exposed by this crate satisfy UAPI-safety guarantees (that is, they are safely castable to/from a "bag of bits"). [ Miguel: added support for the `rustdoc` and `rusttest` targets, since otherwise they fail, and we want to keep them working. ] Reviewed-by: Martin Rodriguez Reboredo Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230329-rust-uapi-v2-1-bca5fb4d4a12@asahilina.net Signed-off-by: Miguel Ojeda --- rust/.gitignore | 1 + rust/Makefile | 28 +++++++++++++++++++++++----- rust/kernel/lib.rs | 1 + rust/uapi/lib.rs | 27 +++++++++++++++++++++++++++ rust/uapi/uapi_helper.h | 9 +++++++++ 5 files changed, 61 insertions(+), 5 deletions(-) create mode 100644 rust/uapi/lib.rs create mode 100644 rust/uapi/uapi_helper.h diff --git a/rust/.gitignore b/rust/.gitignore index 168cb26a31b9..21552992b401 100644 --- a/rust/.gitignore +++ b/rust/.gitignore @@ -2,6 +2,7 @@ bindings_generated.rs bindings_helpers_generated.rs +uapi_generated.rs exports_*_generated.h doc/ test/ diff --git a/rust/Makefile b/rust/Makefile index f88d108fbef0..04bb52e88331 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -16,6 +16,9 @@ obj-$(CONFIG_RUST) += alloc.o bindings.o kernel.o always-$(CONFIG_RUST) += exports_alloc_generated.h exports_bindings_generated.h \ exports_kernel_generated.h +always-$(CONFIG_RUST) += uapi/uapi_generated.rs +obj-$(CONFIG_RUST) += uapi.o + ifdef CONFIG_RUST_BUILD_ASSERT_ALLOW obj-$(CONFIG_RUST) += build_error.o else @@ -113,7 +116,7 @@ rustdoc-alloc: $(src)/alloc/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE rustdoc-kernel: private rustc_target_flags = --extern alloc \ --extern build_error --extern macros=$(objtree)/$(obj)/libmacros.so \ - --extern bindings + --extern bindings --extern uapi rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \ rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \ $(obj)/bindings.o FORCE @@ -141,6 +144,9 @@ rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE $(call if_changed,rustc_test_library) +rusttestlib-uapi: $(src)/uapi/lib.rs rusttest-prepare FORCE + $(call if_changed,rustc_test_library) + quiet_cmd_rustdoc_test = RUSTDOC T $< cmd_rustdoc_test = \ OBJTREE=$(abspath $(objtree)) \ @@ -223,9 +229,10 @@ rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE $(call if_changed,rustdoc_test) rusttest-kernel: private rustc_target_flags = --extern alloc \ - --extern build_error --extern macros --extern bindings + --extern build_error --extern macros --extern bindings --extern uapi rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \ - rusttestlib-build_error rusttestlib-macros rusttestlib-bindings FORCE + rusttestlib-build_error rusttestlib-macros rusttestlib-bindings \ + rusttestlib-uapi FORCE $(call if_changed,rustc_test) $(call if_changed,rustc_test_library) @@ -288,6 +295,12 @@ $(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \ $(src)/bindgen_parameters FORCE $(call if_changed_dep,bindgen) +$(obj)/uapi/uapi_generated.rs: private bindgen_target_flags = \ + $(shell grep -v '^#\|^$$' $(srctree)/$(src)/bindgen_parameters) +$(obj)/uapi/uapi_generated.rs: $(src)/uapi/uapi_helper.h \ + $(src)/bindgen_parameters FORCE + $(call if_changed_dep,bindgen) + # See `CFLAGS_REMOVE_helpers.o` above. In addition, Clang on C does not warn # with `-Wmissing-declarations` (unlike GCC), so it is not strictly needed here # given it is `libclang`; but for consistency, future Clang changes and/or @@ -388,10 +401,15 @@ $(obj)/bindings.o: $(src)/bindings/lib.rs \ $(obj)/bindings/bindings_helpers_generated.rs FORCE $(call if_changed_dep,rustc_library) +$(obj)/uapi.o: $(src)/uapi/lib.rs \ + $(obj)/compiler_builtins.o \ + $(obj)/uapi/uapi_generated.rs FORCE + $(call if_changed_dep,rustc_library) + $(obj)/kernel.o: private rustc_target_flags = --extern alloc \ - --extern build_error --extern macros --extern bindings + --extern build_error --extern macros --extern bindings --extern uapi $(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o $(obj)/build_error.o \ - $(obj)/libmacros.so $(obj)/bindings.o FORCE + $(obj)/libmacros.so $(obj)/bindings.o $(obj)/uapi.o FORCE $(call if_changed_dep,rustc_library) endif # CONFIG_RUST diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index ee27e10da479..dd3b0d69fdd1 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -50,6 +50,7 @@ pub mod types; #[doc(hidden)] pub use bindings; pub use macros; +pub use uapi; #[doc(hidden)] pub use build_error::build_error; diff --git a/rust/uapi/lib.rs b/rust/uapi/lib.rs new file mode 100644 index 000000000000..29f69f3a52de --- /dev/null +++ b/rust/uapi/lib.rs @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! UAPI Bindings. +//! +//! Contains the bindings generated by `bindgen` for UAPI interfaces. +//! +//! This crate may be used directly by drivers that need to interact with +//! userspace APIs. + +#![no_std] +#![feature(core_ffi_c)] +// See . +#![cfg_attr(test, allow(deref_nullptr))] +#![cfg_attr(test, allow(unaligned_references))] +#![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))] +#![allow( + clippy::all, + missing_docs, + non_camel_case_types, + non_upper_case_globals, + non_snake_case, + improper_ctypes, + unreachable_pub, + unsafe_op_in_unsafe_fn +)] + +include!(concat!(env!("OBJTREE"), "/rust/uapi/uapi_generated.rs")); diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h new file mode 100644 index 000000000000..301f5207f023 --- /dev/null +++ b/rust/uapi/uapi_helper.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header that contains the headers for which Rust UAPI bindings + * will be automatically generated by `bindgen`. + * + * Sorted alphabetically. + */ + +#include -- GitLab From ea76e08f4d901a450619831a255e9e0a4c0ed162 Mon Sep 17 00:00:00 2001 From: Asahi Lina Date: Mon, 3 Apr 2023 18:33:53 +0900 Subject: [PATCH 3816/5631] rust: ioctl: Add ioctl number manipulation functions Add simple 1:1 wrappers of the C ioctl number manipulation functions. Since these are macros we cannot bindgen them directly, and since they should be usable in const context we cannot use helper wrappers, so we'll have to reimplement them in Rust. Thankfully, the C headers do declare defines for the relevant bitfield positions, so we don't need to duplicate that. Signed-off-by: Asahi Lina Link: https://lore.kernel.org/r/20230329-rust-uapi-v2-2-bca5fb4d4a12@asahilina.net [ Moved the `#![allow(non_snake_case)]` to the usual place. ] Signed-off-by: Miguel Ojeda --- rust/kernel/ioctl.rs | 72 ++++++++++++++++++++++++++++++++++++++++++++ rust/kernel/lib.rs | 1 + 2 files changed, 73 insertions(+) create mode 100644 rust/kernel/ioctl.rs diff --git a/rust/kernel/ioctl.rs b/rust/kernel/ioctl.rs new file mode 100644 index 000000000000..c49e1a8d3fd0 --- /dev/null +++ b/rust/kernel/ioctl.rs @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! ioctl() number definitions +//! +//! C header: [`include/asm-generic/ioctl.h`](../../../../include/asm-generic/ioctl.h) + +#![allow(non_snake_case)] + +use crate::build_assert; + +/// Build an ioctl number, analogous to the C macro of the same name. +#[inline(always)] +const fn _IOC(dir: u32, ty: u32, nr: u32, size: usize) -> u32 { + build_assert!(dir <= uapi::_IOC_DIRMASK); + build_assert!(ty <= uapi::_IOC_TYPEMASK); + build_assert!(nr <= uapi::_IOC_NRMASK); + build_assert!(size <= (uapi::_IOC_SIZEMASK as usize)); + + (dir << uapi::_IOC_DIRSHIFT) + | (ty << uapi::_IOC_TYPESHIFT) + | (nr << uapi::_IOC_NRSHIFT) + | ((size as u32) << uapi::_IOC_SIZESHIFT) +} + +/// Build an ioctl number for an argumentless ioctl. +#[inline(always)] +pub const fn _IO(ty: u32, nr: u32) -> u32 { + _IOC(uapi::_IOC_NONE, ty, nr, 0) +} + +/// Build an ioctl number for an read-only ioctl. +#[inline(always)] +pub const fn _IOR(ty: u32, nr: u32) -> u32 { + _IOC(uapi::_IOC_READ, ty, nr, core::mem::size_of::()) +} + +/// Build an ioctl number for an write-only ioctl. +#[inline(always)] +pub const fn _IOW(ty: u32, nr: u32) -> u32 { + _IOC(uapi::_IOC_WRITE, ty, nr, core::mem::size_of::()) +} + +/// Build an ioctl number for a read-write ioctl. +#[inline(always)] +pub const fn _IOWR(ty: u32, nr: u32) -> u32 { + _IOC( + uapi::_IOC_READ | uapi::_IOC_WRITE, + ty, + nr, + core::mem::size_of::(), + ) +} + +/// Get the ioctl direction from an ioctl number. +pub const fn _IOC_DIR(nr: u32) -> u32 { + (nr >> uapi::_IOC_DIRSHIFT) & uapi::_IOC_DIRMASK +} + +/// Get the ioctl type from an ioctl number. +pub const fn _IOC_TYPE(nr: u32) -> u32 { + (nr >> uapi::_IOC_TYPESHIFT) & uapi::_IOC_TYPEMASK +} + +/// Get the ioctl number from an ioctl number. +pub const fn _IOC_NR(nr: u32) -> u32 { + (nr >> uapi::_IOC_NRSHIFT) & uapi::_IOC_NRMASK +} + +/// Get the ioctl size from an ioctl number. +pub const fn _IOC_SIZE(nr: u32) -> usize { + ((nr >> uapi::_IOC_SIZESHIFT) & uapi::_IOC_SIZEMASK) as usize +} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index dd3b0d69fdd1..676995d4e460 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -37,6 +37,7 @@ mod allocator; mod build_assert; pub mod error; pub mod init; +pub mod ioctl; pub mod prelude; pub mod print; mod static_assert; -- GitLab From 0ea0a825192efdd44af4c016faaab1a3d2073c78 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 28 Feb 2023 07:16:48 -0800 Subject: [PATCH 3817/5631] watchdog: imx2_wdg: Declare local symbols static 0-day complains: drivers/watchdog/imx2_wdt.c:442:22: sparse: symbol 'imx_wdt' was not declared. Should it be static? drivers/watchdog/imx2_wdt.c:446:22: sparse: symbol 'imx_wdt_legacy' was not declared. Should it be static? Declare as static variables. Fixes: e42c73f1ef0d ("watchdog: imx2_wdg: suspend watchdog in WAIT mode") Cc: Andrej Picej Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20230228151648.4087637-1-linux@roeck-us.net Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/imx2_wdt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c index 19ab7b3d286b..6fcc3596103c 100644 --- a/drivers/watchdog/imx2_wdt.c +++ b/drivers/watchdog/imx2_wdt.c @@ -439,11 +439,11 @@ static int __maybe_unused imx2_wdt_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(imx2_wdt_pm_ops, imx2_wdt_suspend, imx2_wdt_resume); -struct imx2_wdt_data imx_wdt = { +static struct imx2_wdt_data imx_wdt = { .wdw_supported = true, }; -struct imx2_wdt_data imx_wdt_legacy = { +static struct imx2_wdt_data imx_wdt_legacy = { .wdw_supported = false, }; -- GitLab From 12cee6efb7b94918747d09ba7488dd5cb1bbe2be Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 4 Mar 2023 08:16:07 -0800 Subject: [PATCH 3818/5631] watchdog: core: Always set WDOG_HW_RUNNING when starting watchdog The use of WDOG_HW_RUNNING is currently inconsistent: If set by the driver, it will remain set until the watchdog device is opened and then closed. If set by the watchdog core, it is only set if the watchdog can not be stopped when closed. Subsequenty it is always only set while the watchdog is closed and the hardware watchdog is running. This is both misleading and inconsistent: The API states that watchdog_hw_running() indicates that the hardware watchdog is running. This is currently not always the case. Set WDOG_HW_RUNNING whenever a watchdog is successfully started for consistent behavior and to accurately report its status. This means that we no longer have to check for both watchdog_active() and watchdog_hw_running() to check if the watchdog is running because watchdog_hw_running() now implies watchdog_active(). Simplify the code accordingly where warranted. Cc: Wang Wensheng Signed-off-by: Guenter Roeck Link: https://lore.kernel.org/r/20230304161607.1418952-1-linux@roeck-us.net Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/watchdog_core.c | 2 +- drivers/watchdog/watchdog_dev.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/watchdog_core.c b/drivers/watchdog/watchdog_core.c index c777a612d932..d4c5a736fdcb 100644 --- a/drivers/watchdog/watchdog_core.c +++ b/drivers/watchdog/watchdog_core.c @@ -162,7 +162,7 @@ static int watchdog_reboot_notifier(struct notifier_block *nb, wdd = container_of(nb, struct watchdog_device, reboot_nb); if (code == SYS_DOWN || code == SYS_HALT) { - if (watchdog_active(wdd) || watchdog_hw_running(wdd)) { + if (watchdog_hw_running(wdd)) { int ret; ret = wdd->ops->stop(wdd); diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c index 0122e8796879..7102dc96573e 100644 --- a/drivers/watchdog/watchdog_dev.c +++ b/drivers/watchdog/watchdog_dev.c @@ -192,7 +192,7 @@ static int watchdog_ping(struct watchdog_device *wdd) { struct watchdog_core_data *wd_data = wdd->wd_data; - if (!watchdog_active(wdd) && !watchdog_hw_running(wdd)) + if (!watchdog_hw_running(wdd)) return 0; set_bit(_WDOG_KEEPALIVE, &wd_data->status); @@ -268,6 +268,7 @@ static int watchdog_start(struct watchdog_device *wdd) trace_watchdog_start(wdd, err); if (err == 0) { set_bit(WDOG_ACTIVE, &wdd->status); + set_bit(WDOG_HW_RUNNING, &wdd->status); wd_data->last_keepalive = started_at; wd_data->last_hw_keepalive = started_at; watchdog_update_worker(wdd); -- GitLab From 9b31b1ea125ca2e734ae89badc0c3073b4445842 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 4 Mar 2023 08:56:52 -0800 Subject: [PATCH 3819/5631] watchdog: s3c2410_wdt: Use devm_clk_get[_optional]_enabled() helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The devm_clk_get[_optional]_enabled() helpers: - call devm_clk_get[_optional]() - call clk_prepare_enable() and register what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code and avoids the calls to clk_disable_unprepare(). While at it, use dev_err_probe consistently, and use its return value to return the error code. Cc: Uwe Kleine-König Signed-off-by: Guenter Roeck Reviewed-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304165653.2179835-1-linux@roeck-us.net Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/s3c2410_wdt.c | 45 +++++++--------------------------- 1 file changed, 9 insertions(+), 36 deletions(-) diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 200ba236a72e..a1fcb79b0b7c 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -661,35 +661,17 @@ static int s3c2410wdt_probe(struct platform_device *pdev) if (IS_ERR(wdt->reg_base)) return PTR_ERR(wdt->reg_base); - wdt->bus_clk = devm_clk_get(dev, "watchdog"); - if (IS_ERR(wdt->bus_clk)) { - dev_err(dev, "failed to find bus clock\n"); - return PTR_ERR(wdt->bus_clk); - } - - ret = clk_prepare_enable(wdt->bus_clk); - if (ret < 0) { - dev_err(dev, "failed to enable bus clock\n"); - return ret; - } + wdt->bus_clk = devm_clk_get_enabled(dev, "watchdog"); + if (IS_ERR(wdt->bus_clk)) + return dev_err_probe(dev, PTR_ERR(wdt->bus_clk), "failed to get bus clock\n"); /* * "watchdog_src" clock is optional; if it's not present -- just skip it * and use "watchdog" clock as both bus and source clock. */ - wdt->src_clk = devm_clk_get_optional(dev, "watchdog_src"); - if (IS_ERR(wdt->src_clk)) { - dev_err_probe(dev, PTR_ERR(wdt->src_clk), - "failed to get source clock\n"); - ret = PTR_ERR(wdt->src_clk); - goto err_bus_clk; - } - - ret = clk_prepare_enable(wdt->src_clk); - if (ret) { - dev_err(dev, "failed to enable source clock\n"); - goto err_bus_clk; - } + wdt->src_clk = devm_clk_get_optional_enabled(dev, "watchdog_src"); + if (IS_ERR(wdt->src_clk)) + return dev_err_probe(dev, PTR_ERR(wdt->src_clk), "failed to get source clock\n"); wdt->wdt_device.min_timeout = 1; wdt->wdt_device.max_timeout = s3c2410wdt_max_timeout(wdt); @@ -710,7 +692,7 @@ static int s3c2410wdt_probe(struct platform_device *pdev) S3C2410_WATCHDOG_DEFAULT_TIME); } else { dev_err(dev, "failed to use default timeout\n"); - goto err_src_clk; + return ret; } } @@ -718,7 +700,7 @@ static int s3c2410wdt_probe(struct platform_device *pdev) pdev->name, pdev); if (ret != 0) { dev_err(dev, "failed to install irq (%d)\n", ret); - goto err_src_clk; + return ret; } watchdog_set_nowayout(&wdt->wdt_device, nowayout); @@ -744,7 +726,7 @@ static int s3c2410wdt_probe(struct platform_device *pdev) ret = watchdog_register_device(&wdt->wdt_device); if (ret) - goto err_src_clk; + return ret; ret = s3c2410wdt_enable(wdt, true); if (ret < 0) @@ -766,12 +748,6 @@ static int s3c2410wdt_probe(struct platform_device *pdev) err_unregister: watchdog_unregister_device(&wdt->wdt_device); - err_src_clk: - clk_disable_unprepare(wdt->src_clk); - - err_bus_clk: - clk_disable_unprepare(wdt->bus_clk); - return ret; } @@ -786,9 +762,6 @@ static int s3c2410wdt_remove(struct platform_device *dev) watchdog_unregister_device(&wdt->wdt_device); - clk_disable_unprepare(wdt->src_clk); - clk_disable_unprepare(wdt->bus_clk); - return 0; } -- GitLab From 89baf2522ba3a82b7aa61dba023a8092b8ff1d5b Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Sat, 4 Mar 2023 08:56:53 -0800 Subject: [PATCH 3820/5631] watchdog: s3c2410_wdt: Use devm_add_action_or_reset() to disable watchdog MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use devm_add_action_or_reset() to disable the watchdog when the driver is removed to simplify the code. With this in place, we can use devm_watchdog_register_device() to register the watchdog, and the removal function is no longer necessary. Cc: Uwe Kleine-König Signed-off-by: Guenter Roeck Acked-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230304165653.2179835-2-linux@roeck-us.net Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/s3c2410_wdt.c | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-) diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index a1fcb79b0b7c..58b262ca4e88 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -623,6 +623,11 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev) return variant; } +static void s3c2410wdt_wdt_disable_action(void *data) +{ + s3c2410wdt_enable(data, false); +} + static int s3c2410wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -724,13 +729,17 @@ static int s3c2410wdt_probe(struct platform_device *pdev) s3c2410wdt_stop(&wdt->wdt_device); } - ret = watchdog_register_device(&wdt->wdt_device); + ret = devm_watchdog_register_device(dev, &wdt->wdt_device); if (ret) return ret; ret = s3c2410wdt_enable(wdt, true); if (ret < 0) - goto err_unregister; + return ret; + + ret = devm_add_action_or_reset(dev, s3c2410wdt_wdt_disable_action, wdt); + if (ret) + return ret; platform_set_drvdata(pdev, wdt); @@ -744,25 +753,6 @@ static int s3c2410wdt_probe(struct platform_device *pdev) (wtcon & S3C2410_WTCON_INTEN) ? "en" : "dis"); return 0; - - err_unregister: - watchdog_unregister_device(&wdt->wdt_device); - - return ret; -} - -static int s3c2410wdt_remove(struct platform_device *dev) -{ - int ret; - struct s3c2410_wdt *wdt = platform_get_drvdata(dev); - - ret = s3c2410wdt_enable(wdt, false); - if (ret < 0) - return ret; - - watchdog_unregister_device(&wdt->wdt_device); - - return 0; } static void s3c2410wdt_shutdown(struct platform_device *dev) @@ -817,7 +807,6 @@ static DEFINE_SIMPLE_DEV_PM_OPS(s3c2410wdt_pm_ops, static struct platform_driver s3c2410wdt_driver = { .probe = s3c2410wdt_probe, - .remove = s3c2410wdt_remove, .shutdown = s3c2410wdt_shutdown, .id_table = s3c2410_wdt_ids, .driver = { -- GitLab From 88d2c181ee9f87b53e1a49cdeb1413e6e45a340e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:44 +0100 Subject: [PATCH 3821/5631] watchdog: acquirewdt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-3-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/acquirewdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/acquirewdt.c b/drivers/watchdog/acquirewdt.c index bc6f333565d3..53b04abd55b0 100644 --- a/drivers/watchdog/acquirewdt.c +++ b/drivers/watchdog/acquirewdt.c @@ -271,14 +271,12 @@ static int __init acq_probe(struct platform_device *dev) return ret; } -static int acq_remove(struct platform_device *dev) +static void acq_remove(struct platform_device *dev) { misc_deregister(&acq_miscdev); release_region(wdt_start, 1); if (wdt_stop != wdt_start) release_region(wdt_stop, 1); - - return 0; } static void acq_shutdown(struct platform_device *dev) @@ -288,7 +286,7 @@ static void acq_shutdown(struct platform_device *dev) } static struct platform_driver acquirewdt_driver = { - .remove = acq_remove, + .remove_new = acq_remove, .shutdown = acq_shutdown, .driver = { .name = DRV_NAME, -- GitLab From 8960d8ada73518ed9ea4d695347bbe0b3142142e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:45 +0100 Subject: [PATCH 3822/5631] watchdog: advantechwdt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-4-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/advantechwdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/advantechwdt.c b/drivers/watchdog/advantechwdt.c index 554fe85da50e..7a0acbc3e4dd 100644 --- a/drivers/watchdog/advantechwdt.c +++ b/drivers/watchdog/advantechwdt.c @@ -279,14 +279,12 @@ static int __init advwdt_probe(struct platform_device *dev) goto out; } -static int advwdt_remove(struct platform_device *dev) +static void advwdt_remove(struct platform_device *dev) { misc_deregister(&advwdt_miscdev); release_region(wdt_start, 1); if (wdt_stop != wdt_start) release_region(wdt_stop, 1); - - return 0; } static void advwdt_shutdown(struct platform_device *dev) @@ -296,7 +294,7 @@ static void advwdt_shutdown(struct platform_device *dev) } static struct platform_driver advwdt_driver = { - .remove = advwdt_remove, + .remove_new = advwdt_remove, .shutdown = advwdt_shutdown, .driver = { .name = DRV_NAME, -- GitLab From e676c92e9a3a987a496733df1be50b8cea872822 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:46 +0100 Subject: [PATCH 3823/5631] watchdog: ar7: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-5-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/ar7_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/ar7_wdt.c b/drivers/watchdog/ar7_wdt.c index 743e171d97a3..cdcaeb0961ac 100644 --- a/drivers/watchdog/ar7_wdt.c +++ b/drivers/watchdog/ar7_wdt.c @@ -290,12 +290,11 @@ static int ar7_wdt_probe(struct platform_device *pdev) return rc; } -static int ar7_wdt_remove(struct platform_device *pdev) +static void ar7_wdt_remove(struct platform_device *pdev) { misc_deregister(&ar7_wdt_miscdev); clk_put(vbus_clk); vbus_clk = NULL; - return 0; } static void ar7_wdt_shutdown(struct platform_device *pdev) @@ -306,7 +305,7 @@ static void ar7_wdt_shutdown(struct platform_device *pdev) static struct platform_driver ar7_wdt_driver = { .probe = ar7_wdt_probe, - .remove = ar7_wdt_remove, + .remove_new = ar7_wdt_remove, .shutdown = ar7_wdt_shutdown, .driver = { .name = "ar7_wdt", -- GitLab From c1e335c8d1b3ff8f818efcec0f250d91cd75af0b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:47 +0100 Subject: [PATCH 3824/5631] watchdog: at91rm9200: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Reviewed-by: Claudiu Beznea Link: https://lore.kernel.org/r/20230303213716.2123717-6-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/at91rm9200_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/at91rm9200_wdt.c b/drivers/watchdog/at91rm9200_wdt.c index d57409c1a4d1..d20ec27ba354 100644 --- a/drivers/watchdog/at91rm9200_wdt.c +++ b/drivers/watchdog/at91rm9200_wdt.c @@ -258,7 +258,7 @@ static int at91wdt_probe(struct platform_device *pdev) return 0; } -static int at91wdt_remove(struct platform_device *pdev) +static void at91wdt_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; int res; @@ -269,8 +269,6 @@ static int at91wdt_remove(struct platform_device *pdev) misc_deregister(&at91wdt_miscdev); at91wdt_miscdev.parent = NULL; - - return 0; } static void at91wdt_shutdown(struct platform_device *pdev) @@ -299,7 +297,7 @@ MODULE_DEVICE_TABLE(of, at91_wdt_dt_ids); static struct platform_driver at91wdt_driver = { .probe = at91wdt_probe, - .remove = at91wdt_remove, + .remove_new = at91wdt_remove, .shutdown = at91wdt_shutdown, .suspend = pm_ptr(at91wdt_suspend), .resume = pm_ptr(at91wdt_resume), -- GitLab From ec6de663274d886a32b4e22a6fb3cf4b2e99cfab Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:48 +0100 Subject: [PATCH 3825/5631] watchdog: ath79: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-7-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/ath79_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c index 0f18f06a21b6..b7b705060438 100644 --- a/drivers/watchdog/ath79_wdt.c +++ b/drivers/watchdog/ath79_wdt.c @@ -296,11 +296,10 @@ static int ath79_wdt_probe(struct platform_device *pdev) return err; } -static int ath79_wdt_remove(struct platform_device *pdev) +static void ath79_wdt_remove(struct platform_device *pdev) { misc_deregister(&ath79_wdt_miscdev); clk_disable_unprepare(wdt_clk); - return 0; } static void ath79_wdt_shutdown(struct platform_device *pdev) @@ -318,7 +317,7 @@ MODULE_DEVICE_TABLE(of, ath79_wdt_match); static struct platform_driver ath79_wdt_driver = { .probe = ath79_wdt_probe, - .remove = ath79_wdt_remove, + .remove_new = ath79_wdt_remove, .shutdown = ath79_wdt_shutdown, .driver = { .name = DRIVER_NAME, -- GitLab From 7ca823d5fa4574bef4636d2ae7946078dec6328b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:49 +0100 Subject: [PATCH 3826/5631] watchdog: bcm2835: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Florian Fainelli Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-8-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/bcm2835_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c index 94907176a0e4..7a855289ff5e 100644 --- a/drivers/watchdog/bcm2835_wdt.c +++ b/drivers/watchdog/bcm2835_wdt.c @@ -218,17 +218,15 @@ static int bcm2835_wdt_probe(struct platform_device *pdev) return 0; } -static int bcm2835_wdt_remove(struct platform_device *pdev) +static void bcm2835_wdt_remove(struct platform_device *pdev) { if (pm_power_off == bcm2835_power_off) pm_power_off = NULL; - - return 0; } static struct platform_driver bcm2835_wdt_driver = { .probe = bcm2835_wdt_probe, - .remove = bcm2835_wdt_remove, + .remove_new = bcm2835_wdt_remove, .driver = { .name = "bcm2835-wdt", }, -- GitLab From 0eddace4629996b24e4f028286802c33c8ea0621 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:51 +0100 Subject: [PATCH 3827/5631] watchdog: bcm_kona: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Florian Fainelli Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-10-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/bcm_kona_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/bcm_kona_wdt.c b/drivers/watchdog/bcm_kona_wdt.c index 8237c4e9c2a0..49e12d47b073 100644 --- a/drivers/watchdog/bcm_kona_wdt.c +++ b/drivers/watchdog/bcm_kona_wdt.c @@ -310,12 +310,10 @@ static int bcm_kona_wdt_probe(struct platform_device *pdev) return 0; } -static int bcm_kona_wdt_remove(struct platform_device *pdev) +static void bcm_kona_wdt_remove(struct platform_device *pdev) { bcm_kona_wdt_debug_exit(pdev); dev_dbg(&pdev->dev, "Watchdog driver disabled"); - - return 0; } static const struct of_device_id bcm_kona_wdt_of_match[] = { @@ -330,7 +328,7 @@ static struct platform_driver bcm_kona_wdt_driver = { .of_match_table = bcm_kona_wdt_of_match, }, .probe = bcm_kona_wdt_probe, - .remove = bcm_kona_wdt_remove, + .remove_new = bcm_kona_wdt_remove, }; module_platform_driver(bcm_kona_wdt_driver); -- GitLab From 5caafac4bb5873fea2b237d32dfcffda24dacd94 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:52 +0100 Subject: [PATCH 3828/5631] watchdog: cpwd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-11-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/cpwd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c index 1eafe0b4d71c..47250f9b68c7 100644 --- a/drivers/watchdog/cpwd.c +++ b/drivers/watchdog/cpwd.c @@ -614,7 +614,7 @@ static int cpwd_probe(struct platform_device *op) return err; } -static int cpwd_remove(struct platform_device *op) +static void cpwd_remove(struct platform_device *op) { struct cpwd *p = platform_get_drvdata(op); int i; @@ -638,8 +638,6 @@ static int cpwd_remove(struct platform_device *op) of_iounmap(&op->resource[0], p->regs, 4 * WD_TIMER_REGSZ); cpwd_device = NULL; - - return 0; } static const struct of_device_id cpwd_match[] = { @@ -656,7 +654,7 @@ static struct platform_driver cpwd_driver = { .of_match_table = cpwd_match, }, .probe = cpwd_probe, - .remove = cpwd_remove, + .remove_new = cpwd_remove, }; module_platform_driver(cpwd_driver); -- GitLab From 3a063f9bc4a1490ba913427a8b53ea973c55b043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:53 +0100 Subject: [PATCH 3829/5631] watchdog: dw: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-12-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/dw_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c index 462f15bd5ffa..6f88bd81f8a1 100644 --- a/drivers/watchdog/dw_wdt.c +++ b/drivers/watchdog/dw_wdt.c @@ -681,7 +681,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) return ret; } -static int dw_wdt_drv_remove(struct platform_device *pdev) +static void dw_wdt_drv_remove(struct platform_device *pdev) { struct dw_wdt *dw_wdt = platform_get_drvdata(pdev); @@ -691,8 +691,6 @@ static int dw_wdt_drv_remove(struct platform_device *pdev) reset_control_assert(dw_wdt->rst); clk_disable_unprepare(dw_wdt->pclk); clk_disable_unprepare(dw_wdt->clk); - - return 0; } #ifdef CONFIG_OF @@ -705,7 +703,7 @@ MODULE_DEVICE_TABLE(of, dw_wdt_of_match); static struct platform_driver dw_wdt_driver = { .probe = dw_wdt_drv_probe, - .remove = dw_wdt_drv_remove, + .remove_new = dw_wdt_drv_remove, .driver = { .name = "dw_wdt", .of_match_table = of_match_ptr(dw_wdt_of_match), -- GitLab From b5f2e366b148f84d98da2cabd1bbd863fc2d6487 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:54 +0100 Subject: [PATCH 3830/5631] watchdog: gef: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-13-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/gef_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c index df5406aa7d25..97afc907f659 100644 --- a/drivers/watchdog/gef_wdt.c +++ b/drivers/watchdog/gef_wdt.c @@ -283,15 +283,13 @@ static int gef_wdt_probe(struct platform_device *dev) return misc_register(&gef_wdt_miscdev); } -static int gef_wdt_remove(struct platform_device *dev) +static void gef_wdt_remove(struct platform_device *dev) { misc_deregister(&gef_wdt_miscdev); gef_wdt_handler_disable(); iounmap(gef_wdt_regs); - - return 0; } static const struct of_device_id gef_wdt_ids[] = { @@ -308,7 +306,7 @@ static struct platform_driver gef_wdt_driver = { .of_match_table = gef_wdt_ids, }, .probe = gef_wdt_probe, - .remove = gef_wdt_remove, + .remove_new = gef_wdt_remove, }; static int __init gef_wdt_init(void) -- GitLab From 5216a0a95d4fa65e26a67c00b739fdbd2c3a1b1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:55 +0100 Subject: [PATCH 3831/5631] watchdog: geodewdt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-14-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/geodewdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/geodewdt.c b/drivers/watchdog/geodewdt.c index 0b699c783d57..5186c37ad451 100644 --- a/drivers/watchdog/geodewdt.c +++ b/drivers/watchdog/geodewdt.c @@ -238,10 +238,9 @@ static int __init geodewdt_probe(struct platform_device *dev) return ret; } -static int geodewdt_remove(struct platform_device *dev) +static void geodewdt_remove(struct platform_device *dev) { misc_deregister(&geodewdt_miscdev); - return 0; } static void geodewdt_shutdown(struct platform_device *dev) @@ -250,7 +249,7 @@ static void geodewdt_shutdown(struct platform_device *dev) } static struct platform_driver geodewdt_driver = { - .remove = geodewdt_remove, + .remove_new = geodewdt_remove, .shutdown = geodewdt_shutdown, .driver = { .name = DRV_NAME, -- GitLab From 40529e7ed5c98b4bfbaec62b8e13e1e647d46df8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:56 +0100 Subject: [PATCH 3832/5631] watchdog: ib700wdt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-15-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/ib700wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/ib700wdt.c b/drivers/watchdog/ib700wdt.c index a0ddedc362fc..39ea97009abd 100644 --- a/drivers/watchdog/ib700wdt.c +++ b/drivers/watchdog/ib700wdt.c @@ -316,14 +316,13 @@ static int __init ibwdt_probe(struct platform_device *dev) return res; } -static int ibwdt_remove(struct platform_device *dev) +static void ibwdt_remove(struct platform_device *dev) { misc_deregister(&ibwdt_miscdev); release_region(WDT_START, 1); #if WDT_START != WDT_STOP release_region(WDT_STOP, 1); #endif - return 0; } static void ibwdt_shutdown(struct platform_device *dev) @@ -333,7 +332,7 @@ static void ibwdt_shutdown(struct platform_device *dev) } static struct platform_driver ibwdt_driver = { - .remove = ibwdt_remove, + .remove_new = ibwdt_remove, .shutdown = ibwdt_shutdown, .driver = { .name = DRV_NAME, -- GitLab From e395a471591392820ccfc7cec1b1581042c461ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:57 +0100 Subject: [PATCH 3833/5631] watchdog: ie6xx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-16-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/ie6xx_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/ie6xx_wdt.c b/drivers/watchdog/ie6xx_wdt.c index 8f28993fab8b..e5cbb409df25 100644 --- a/drivers/watchdog/ie6xx_wdt.c +++ b/drivers/watchdog/ie6xx_wdt.c @@ -266,7 +266,7 @@ static int ie6xx_wdt_probe(struct platform_device *pdev) return ret; } -static int ie6xx_wdt_remove(struct platform_device *pdev) +static void ie6xx_wdt_remove(struct platform_device *pdev) { struct resource *res; @@ -276,13 +276,11 @@ static int ie6xx_wdt_remove(struct platform_device *pdev) ie6xx_wdt_debugfs_exit(); release_region(res->start, resource_size(res)); ie6xx_wdt_data.sch_wdtba = 0; - - return 0; } static struct platform_driver ie6xx_wdt_driver = { .probe = ie6xx_wdt_probe, - .remove = ie6xx_wdt_remove, + .remove_new = ie6xx_wdt_remove, .driver = { .name = DRIVER_NAME, }, -- GitLab From fb22b9e95af8d2f668c95f8b51bed11646720948 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:58 +0100 Subject: [PATCH 3834/5631] watchdog: lpc18xx: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-17-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/lpc18xx_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/lpc18xx_wdt.c b/drivers/watchdog/lpc18xx_wdt.c index 1b9b5f21a0df..19535f4a2fd2 100644 --- a/drivers/watchdog/lpc18xx_wdt.c +++ b/drivers/watchdog/lpc18xx_wdt.c @@ -261,14 +261,12 @@ static int lpc18xx_wdt_probe(struct platform_device *pdev) return devm_watchdog_register_device(dev, &lpc18xx_wdt->wdt_dev); } -static int lpc18xx_wdt_remove(struct platform_device *pdev) +static void lpc18xx_wdt_remove(struct platform_device *pdev) { struct lpc18xx_wdt_dev *lpc18xx_wdt = platform_get_drvdata(pdev); dev_warn(&pdev->dev, "I quit now, hardware will probably reboot!\n"); del_timer_sync(&lpc18xx_wdt->timer); - - return 0; } static const struct of_device_id lpc18xx_wdt_match[] = { @@ -283,7 +281,7 @@ static struct platform_driver lpc18xx_wdt_driver = { .of_match_table = lpc18xx_wdt_match, }, .probe = lpc18xx_wdt_probe, - .remove = lpc18xx_wdt_remove, + .remove_new = lpc18xx_wdt_remove, }; module_platform_driver(lpc18xx_wdt_driver); -- GitLab From 62b6a8507c1cdcb375549481f02177e80d51c7f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:36:59 +0100 Subject: [PATCH 3835/5631] watchdog: mtx-1: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-18-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/mtx-1_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/mtx-1_wdt.c b/drivers/watchdog/mtx-1_wdt.c index ea1bbf5ee528..152e41ecbb14 100644 --- a/drivers/watchdog/mtx-1_wdt.c +++ b/drivers/watchdog/mtx-1_wdt.c @@ -221,7 +221,7 @@ static int mtx1_wdt_probe(struct platform_device *pdev) return 0; } -static int mtx1_wdt_remove(struct platform_device *pdev) +static void mtx1_wdt_remove(struct platform_device *pdev) { /* FIXME: do we need to lock this test ? */ if (mtx1_wdt_device.queue) { @@ -230,12 +230,11 @@ static int mtx1_wdt_remove(struct platform_device *pdev) } misc_deregister(&mtx1_wdt_misc); - return 0; } static struct platform_driver mtx1_wdt_driver = { .probe = mtx1_wdt_probe, - .remove = mtx1_wdt_remove, + .remove_new = mtx1_wdt_remove, .driver.name = "mtx1-wdt", .driver.owner = THIS_MODULE, }; -- GitLab From 55b0fb45375eddf89d8e9f06f22de5bac0285efa Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:00 +0100 Subject: [PATCH 3836/5631] watchdog: nic7018: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-19-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/nic7018_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/nic7018_wdt.c b/drivers/watchdog/nic7018_wdt.c index 2a46cc662943..c3f0a4926667 100644 --- a/drivers/watchdog/nic7018_wdt.c +++ b/drivers/watchdog/nic7018_wdt.c @@ -218,7 +218,7 @@ static int nic7018_probe(struct platform_device *pdev) return 0; } -static int nic7018_remove(struct platform_device *pdev) +static void nic7018_remove(struct platform_device *pdev) { struct nic7018_wdt *wdt = platform_get_drvdata(pdev); @@ -226,8 +226,6 @@ static int nic7018_remove(struct platform_device *pdev) /* Lock WDT register */ outb(LOCK, wdt->io_base + WDT_REG_LOCK); - - return 0; } static const struct acpi_device_id nic7018_device_ids[] = { @@ -238,7 +236,7 @@ MODULE_DEVICE_TABLE(acpi, nic7018_device_ids); static struct platform_driver watchdog_driver = { .probe = nic7018_probe, - .remove = nic7018_remove, + .remove_new = nic7018_remove, .driver = { .name = KBUILD_MODNAME, .acpi_match_table = ACPI_PTR(nic7018_device_ids), -- GitLab From 3a9731099f7141265471ba1e4ed4ee97dc32f200 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:01 +0100 Subject: [PATCH 3837/5631] watchdog: nv_tco: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-20-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/nv_tco.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/nv_tco.c b/drivers/watchdog/nv_tco.c index f6902a337422..ac4a9c16341d 100644 --- a/drivers/watchdog/nv_tco.c +++ b/drivers/watchdog/nv_tco.c @@ -446,12 +446,10 @@ static void nv_tco_cleanup(void) release_region(tcobase, 0x10); } -static int nv_tco_remove(struct platform_device *dev) +static void nv_tco_remove(struct platform_device *dev) { if (tcobase) nv_tco_cleanup(); - - return 0; } static void nv_tco_shutdown(struct platform_device *dev) @@ -469,7 +467,7 @@ static void nv_tco_shutdown(struct platform_device *dev) static struct platform_driver nv_tco_driver = { .probe = nv_tco_init, - .remove = nv_tco_remove, + .remove_new = nv_tco_remove, .shutdown = nv_tco_shutdown, .driver = { .name = TCO_MODULE_NAME, -- GitLab From 412cec3b5e4cd2652ff6dbf0ce69d7f75e49673d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:02 +0100 Subject: [PATCH 3838/5631] watchdog: omap: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-21-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/omap_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c index e75aa86f63cb..a7a12f2fe9de 100644 --- a/drivers/watchdog/omap_wdt.c +++ b/drivers/watchdog/omap_wdt.c @@ -306,14 +306,12 @@ static void omap_wdt_shutdown(struct platform_device *pdev) mutex_unlock(&wdev->lock); } -static int omap_wdt_remove(struct platform_device *pdev) +static void omap_wdt_remove(struct platform_device *pdev) { struct omap_wdt_dev *wdev = platform_get_drvdata(pdev); pm_runtime_disable(wdev->dev); watchdog_unregister_device(&wdev->wdog); - - return 0; } /* REVISIT ... not clear this is the best way to handle system suspend; and @@ -359,7 +357,7 @@ MODULE_DEVICE_TABLE(of, omap_wdt_of_match); static struct platform_driver omap_wdt_driver = { .probe = omap_wdt_probe, - .remove = omap_wdt_remove, + .remove_new = omap_wdt_remove, .shutdown = omap_wdt_shutdown, .suspend = pm_ptr(omap_wdt_suspend), .resume = pm_ptr(omap_wdt_resume), -- GitLab From e47f2a3b58e5dba92df861f905895b420a7db9ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:03 +0100 Subject: [PATCH 3839/5631] watchdog: orion: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-22-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/orion_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c index e25e6bf4647f..5ec2dd8fd5fa 100644 --- a/drivers/watchdog/orion_wdt.c +++ b/drivers/watchdog/orion_wdt.c @@ -649,7 +649,7 @@ static int orion_wdt_probe(struct platform_device *pdev) return ret; } -static int orion_wdt_remove(struct platform_device *pdev) +static void orion_wdt_remove(struct platform_device *pdev) { struct watchdog_device *wdt_dev = platform_get_drvdata(pdev); struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev); @@ -657,7 +657,6 @@ static int orion_wdt_remove(struct platform_device *pdev) watchdog_unregister_device(wdt_dev); clk_disable_unprepare(dev->clk); clk_put(dev->clk); - return 0; } static void orion_wdt_shutdown(struct platform_device *pdev) @@ -668,7 +667,7 @@ static void orion_wdt_shutdown(struct platform_device *pdev) static struct platform_driver orion_wdt_driver = { .probe = orion_wdt_probe, - .remove = orion_wdt_remove, + .remove_new = orion_wdt_remove, .shutdown = orion_wdt_shutdown, .driver = { .name = "orion_wdt", -- GitLab From c550440918fff34f5098f8165ffb227afde6bf33 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:04 +0100 Subject: [PATCH 3840/5631] watchdog: rc32434: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-23-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rc32434_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/rc32434_wdt.c b/drivers/watchdog/rc32434_wdt.c index e74802f3a32e..417f9b75679c 100644 --- a/drivers/watchdog/rc32434_wdt.c +++ b/drivers/watchdog/rc32434_wdt.c @@ -298,10 +298,9 @@ static int rc32434_wdt_probe(struct platform_device *pdev) return 0; } -static int rc32434_wdt_remove(struct platform_device *pdev) +static void rc32434_wdt_remove(struct platform_device *pdev) { misc_deregister(&rc32434_wdt_miscdev); - return 0; } static void rc32434_wdt_shutdown(struct platform_device *pdev) @@ -311,7 +310,7 @@ static void rc32434_wdt_shutdown(struct platform_device *pdev) static struct platform_driver rc32434_wdt_driver = { .probe = rc32434_wdt_probe, - .remove = rc32434_wdt_remove, + .remove_new = rc32434_wdt_remove, .shutdown = rc32434_wdt_shutdown, .driver = { .name = "rc32434_wdt", -- GitLab From 6645579b7081753e4f94946a2c98f5d4aeed9c9c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:05 +0100 Subject: [PATCH 3841/5631] watchdog: rdc321x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-24-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rdc321x_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/rdc321x_wdt.c b/drivers/watchdog/rdc321x_wdt.c index f0c94ea51c3e..6176f4343fc5 100644 --- a/drivers/watchdog/rdc321x_wdt.c +++ b/drivers/watchdog/rdc321x_wdt.c @@ -257,7 +257,7 @@ static int rdc321x_wdt_probe(struct platform_device *pdev) return 0; } -static int rdc321x_wdt_remove(struct platform_device *pdev) +static void rdc321x_wdt_remove(struct platform_device *pdev) { if (rdc321x_wdt_device.queue) { rdc321x_wdt_device.queue = 0; @@ -265,13 +265,11 @@ static int rdc321x_wdt_remove(struct platform_device *pdev) } misc_deregister(&rdc321x_wdt_misc); - - return 0; } static struct platform_driver rdc321x_wdt_driver = { .probe = rdc321x_wdt_probe, - .remove = rdc321x_wdt_remove, + .remove_new = rdc321x_wdt_remove, .driver = { .name = "rdc321x-wdt", }, -- GitLab From b481d57bb1a29b50086130e46e83b0a8ad61604e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:06 +0100 Subject: [PATCH 3842/5631] watchdog: renesas: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-25-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/renesas_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/renesas_wdt.c b/drivers/watchdog/renesas_wdt.c index 41d58ea5eb2f..12c41d6e5cd6 100644 --- a/drivers/watchdog/renesas_wdt.c +++ b/drivers/watchdog/renesas_wdt.c @@ -292,14 +292,12 @@ static int rwdt_probe(struct platform_device *pdev) return ret; } -static int rwdt_remove(struct platform_device *pdev) +static void rwdt_remove(struct platform_device *pdev) { struct rwdt_priv *priv = platform_get_drvdata(pdev); watchdog_unregister_device(&priv->wdev); pm_runtime_disable(&pdev->dev); - - return 0; } static int __maybe_unused rwdt_suspend(struct device *dev) @@ -339,7 +337,7 @@ static struct platform_driver rwdt_driver = { .pm = &rwdt_pm_ops, }, .probe = rwdt_probe, - .remove = rwdt_remove, + .remove_new = rwdt_remove, }; module_platform_driver(rwdt_driver); -- GitLab From 3628149f6eef811e1422ff407e28fd74e6bfdf83 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:07 +0100 Subject: [PATCH 3843/5631] watchdog: riowd: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-26-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/riowd.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/riowd.c b/drivers/watchdog/riowd.c index 747e346ed06c..c04b383e1712 100644 --- a/drivers/watchdog/riowd.c +++ b/drivers/watchdog/riowd.c @@ -217,14 +217,12 @@ static int riowd_probe(struct platform_device *op) return err; } -static int riowd_remove(struct platform_device *op) +static void riowd_remove(struct platform_device *op) { struct riowd *p = platform_get_drvdata(op); misc_deregister(&riowd_miscdev); of_iounmap(&op->resource[0], p->regs, 2); - - return 0; } static const struct of_device_id riowd_match[] = { @@ -241,7 +239,7 @@ static struct platform_driver riowd_driver = { .of_match_table = riowd_match, }, .probe = riowd_probe, - .remove = riowd_remove, + .remove_new = riowd_remove, }; module_platform_driver(riowd_driver); -- GitLab From 4ead88bf860a6fb13056e964985ab0a2e78f3a9c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:09 +0100 Subject: [PATCH 3844/5631] watchdog: rti: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-28-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rti_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/rti_wdt.c b/drivers/watchdog/rti_wdt.c index 6e9253761fc1..ce8f18e93aa9 100644 --- a/drivers/watchdog/rti_wdt.c +++ b/drivers/watchdog/rti_wdt.c @@ -304,15 +304,13 @@ static int rti_wdt_probe(struct platform_device *pdev) return ret; } -static int rti_wdt_remove(struct platform_device *pdev) +static void rti_wdt_remove(struct platform_device *pdev) { struct rti_wdt_device *wdt = platform_get_drvdata(pdev); watchdog_unregister_device(&wdt->wdd); pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); - - return 0; } static const struct of_device_id rti_wdt_of_match[] = { @@ -327,7 +325,7 @@ static struct platform_driver rti_wdt_driver = { .of_match_table = rti_wdt_of_match, }, .probe = rti_wdt_probe, - .remove = rti_wdt_remove, + .remove_new = rti_wdt_remove, }; module_platform_driver(rti_wdt_driver); -- GitLab From 4dca58a8cb7c65a5ab7385837acf60ff09c67e46 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:11 +0100 Subject: [PATCH 3845/5631] watchdog: sa1100: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-30-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/sa1100_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c index 82ac5d19f519..5d2df008b92a 100644 --- a/drivers/watchdog/sa1100_wdt.c +++ b/drivers/watchdog/sa1100_wdt.c @@ -229,19 +229,17 @@ static int sa1100dog_probe(struct platform_device *pdev) return ret; } -static int sa1100dog_remove(struct platform_device *pdev) +static void sa1100dog_remove(struct platform_device *pdev) { misc_deregister(&sa1100dog_miscdev); clk_disable_unprepare(clk); clk_put(clk); - - return 0; } static struct platform_driver sa1100dog_driver = { .driver.name = "sa1100_wdt", .probe = sa1100dog_probe, - .remove = sa1100dog_remove, + .remove_new = sa1100dog_remove, }; module_platform_driver(sa1100dog_driver); -- GitLab From f80e31b3abdbbdb82ee85d7d206229d20001f2d6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:12 +0100 Subject: [PATCH 3846/5631] watchdog: sch311x: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-31-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/sch311x_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/sch311x_wdt.c b/drivers/watchdog/sch311x_wdt.c index d8b77fe10eba..409d49880170 100644 --- a/drivers/watchdog/sch311x_wdt.c +++ b/drivers/watchdog/sch311x_wdt.c @@ -425,7 +425,7 @@ static int sch311x_wdt_probe(struct platform_device *pdev) return err; } -static int sch311x_wdt_remove(struct platform_device *pdev) +static void sch311x_wdt_remove(struct platform_device *pdev) { /* Stop the timer before we leave */ if (!nowayout) @@ -436,7 +436,6 @@ static int sch311x_wdt_remove(struct platform_device *pdev) release_region(sch311x_wdt_data.runtime_reg + WDT_TIME_OUT, 4); release_region(sch311x_wdt_data.runtime_reg + GP60, 1); sch311x_wdt_data.runtime_reg = 0; - return 0; } static void sch311x_wdt_shutdown(struct platform_device *dev) @@ -447,7 +446,7 @@ static void sch311x_wdt_shutdown(struct platform_device *dev) static struct platform_driver sch311x_wdt_driver = { .probe = sch311x_wdt_probe, - .remove = sch311x_wdt_remove, + .remove_new = sch311x_wdt_remove, .shutdown = sch311x_wdt_shutdown, .driver = { .name = DRV_NAME, -- GitLab From 70b5b2b2feb00be6ed479557269438d505f86642 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:13 +0100 Subject: [PATCH 3847/5631] watchdog: shwdt: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-32-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/shwdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/shwdt.c b/drivers/watchdog/shwdt.c index f55533e0e045..10f1fba78ec2 100644 --- a/drivers/watchdog/shwdt.c +++ b/drivers/watchdog/shwdt.c @@ -279,13 +279,11 @@ static int sh_wdt_probe(struct platform_device *pdev) return 0; } -static int sh_wdt_remove(struct platform_device *pdev) +static void sh_wdt_remove(struct platform_device *pdev) { watchdog_unregister_device(&sh_wdt_dev); pm_runtime_disable(&pdev->dev); - - return 0; } static void sh_wdt_shutdown(struct platform_device *pdev) @@ -299,7 +297,7 @@ static struct platform_driver sh_wdt_driver = { }, .probe = sh_wdt_probe, - .remove = sh_wdt_remove, + .remove_new = sh_wdt_remove, .shutdown = sh_wdt_shutdown, }; -- GitLab From e7a84d457d13775e864864703e88ae3ff4b5d36b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:14 +0100 Subject: [PATCH 3848/5631] watchdog: st_lpc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-33-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/st_lpc_wdt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/st_lpc_wdt.c b/drivers/watchdog/st_lpc_wdt.c index 39abecdb9dd1..d2aa43c00221 100644 --- a/drivers/watchdog/st_lpc_wdt.c +++ b/drivers/watchdog/st_lpc_wdt.c @@ -239,13 +239,11 @@ static int st_wdog_probe(struct platform_device *pdev) return ret; } -static int st_wdog_remove(struct platform_device *pdev) +static void st_wdog_remove(struct platform_device *pdev) { struct st_wdog *st_wdog = watchdog_get_drvdata(&st_wdog_dev); st_wdog_setup(st_wdog, false); - - return 0; } static int st_wdog_suspend(struct device *dev) @@ -295,7 +293,7 @@ static struct platform_driver st_wdog_driver = { .of_match_table = st_wdog_match, }, .probe = st_wdog_probe, - .remove = st_wdog_remove, + .remove_new = st_wdog_remove, }; module_platform_driver(st_wdog_driver); -- GitLab From 96c6e56d3ed46840d575102b7b76a760b28de55b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 3 Mar 2023 22:37:15 +0100 Subject: [PATCH 3849/5631] watchdog: stmp3xxx_rtc: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230303213716.2123717-34-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/stmp3xxx_rtc_wdt.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/watchdog/stmp3xxx_rtc_wdt.c b/drivers/watchdog/stmp3xxx_rtc_wdt.c index 7caf3aa71c6a..4b2caa9807ac 100644 --- a/drivers/watchdog/stmp3xxx_rtc_wdt.c +++ b/drivers/watchdog/stmp3xxx_rtc_wdt.c @@ -109,10 +109,9 @@ static int stmp3xxx_wdt_probe(struct platform_device *pdev) return 0; } -static int stmp3xxx_wdt_remove(struct platform_device *pdev) +static void stmp3xxx_wdt_remove(struct platform_device *pdev) { unregister_reboot_notifier(&wdt_notifier); - return 0; } static int __maybe_unused stmp3xxx_wdt_suspend(struct device *dev) @@ -144,7 +143,7 @@ static struct platform_driver stmp3xxx_wdt_driver = { .pm = &stmp3xxx_wdt_pm_ops, }, .probe = stmp3xxx_wdt_probe, - .remove = stmp3xxx_wdt_remove, + .remove_new = stmp3xxx_wdt_remove, }; module_platform_driver(stmp3xxx_wdt_driver); -- GitLab From 74d6c68c74fac3e6bdc28fba69889ed7ef05a7f8 Mon Sep 17 00:00:00 2001 From: Wang Wensheng Date: Wed, 1 Mar 2023 11:37:02 +0000 Subject: [PATCH 3850/5631] watchdog: sbsa: Test WDOG_HW_RUNNING bit in suspend and resume If the sbsa_gwdt is enabled by BIOS, the kernel set WDOG_HW_RUNNING bit and keep it alive before anyone else would open it. When system suspend, the sbsa_gwdt would not be disabled because WDOG_ACTIVE is not set. Then the sbsa_gwdt would reach timeout since no one touch it during system suspend. To solve this, just test WDOG_HW_RUNNING bit in suspend and disable the sbsa_gwdt if the bit is set, then reopen it accordingly in resume process. Signed-off-by: Wang Wensheng Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230301113702.76437-1-wangwensheng4@huawei.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/sbsa_gwdt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index 63862803421f..fd3cfdda4949 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -361,7 +361,7 @@ static int __maybe_unused sbsa_gwdt_suspend(struct device *dev) { struct sbsa_gwdt *gwdt = dev_get_drvdata(dev); - if (watchdog_active(&gwdt->wdd)) + if (watchdog_hw_running(&gwdt->wdd)) sbsa_gwdt_stop(&gwdt->wdd); return 0; @@ -372,7 +372,7 @@ static int __maybe_unused sbsa_gwdt_resume(struct device *dev) { struct sbsa_gwdt *gwdt = dev_get_drvdata(dev); - if (watchdog_active(&gwdt->wdd)) + if (watchdog_hw_running(&gwdt->wdd)) sbsa_gwdt_start(&gwdt->wdd); return 0; -- GitLab From 16da6fbb55532c375cee0a7f33817225ae27a49f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 08:04:02 +0100 Subject: [PATCH 3851/5631] watchdog: bcm47xx: Simplify using devm_watchdog_register_device() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows to drop the .remove() function as it only exists to unregister the watchdog device which is now done in a callback registered by devm_watchdog_register_device(). Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230307070404.2256308-2-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/bcm47xx_wdt.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/watchdog/bcm47xx_wdt.c b/drivers/watchdog/bcm47xx_wdt.c index 05425c1dfd4c..06a54c7de40b 100644 --- a/drivers/watchdog/bcm47xx_wdt.c +++ b/drivers/watchdog/bcm47xx_wdt.c @@ -202,7 +202,7 @@ static int bcm47xx_wdt_probe(struct platform_device *pdev) watchdog_set_restart_priority(&wdt->wdd, 64); watchdog_stop_on_reboot(&wdt->wdd); - ret = watchdog_register_device(&wdt->wdd); + ret = devm_watchdog_register_device(&pdev->dev, &wdt->wdd); if (ret) goto err_timer; @@ -218,21 +218,11 @@ static int bcm47xx_wdt_probe(struct platform_device *pdev) return ret; } -static int bcm47xx_wdt_remove(struct platform_device *pdev) -{ - struct bcm47xx_wdt *wdt = dev_get_platdata(&pdev->dev); - - watchdog_unregister_device(&wdt->wdd); - - return 0; -} - static struct platform_driver bcm47xx_wdt_driver = { .driver = { .name = "bcm47xx-wdt", }, .probe = bcm47xx_wdt_probe, - .remove = bcm47xx_wdt_remove, }; module_platform_driver(bcm47xx_wdt_driver); -- GitLab From 4095b94d3af8b05805b0fde192475b5578c73a48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 08:04:03 +0100 Subject: [PATCH 3852/5631] watchdog: rn5t618: Simplify using devm_watchdog_register_device() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows to drop the .remove() function as it only exists to unregister the watchdog device which is now done in a callback registered by devm_watchdog_register_device(). Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230307070404.2256308-3-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rn5t618_wdt.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) diff --git a/drivers/watchdog/rn5t618_wdt.c b/drivers/watchdog/rn5t618_wdt.c index 40d8ebd8c0ac..87d06d210ac9 100644 --- a/drivers/watchdog/rn5t618_wdt.c +++ b/drivers/watchdog/rn5t618_wdt.c @@ -178,21 +178,11 @@ static int rn5t618_wdt_probe(struct platform_device *pdev) platform_set_drvdata(pdev, wdt); - return watchdog_register_device(&wdt->wdt_dev); -} - -static int rn5t618_wdt_remove(struct platform_device *pdev) -{ - struct rn5t618_wdt *wdt = platform_get_drvdata(pdev); - - watchdog_unregister_device(&wdt->wdt_dev); - - return 0; + return devm_watchdog_register_device(dev, &wdt->wdt_dev); } static struct platform_driver rn5t618_wdt_driver = { .probe = rn5t618_wdt_probe, - .remove = rn5t618_wdt_remove, .driver = { .name = DRIVER_NAME, }, -- GitLab From 0e89b2c9a2a6984af43d09de9d1bb44da9822ba2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 08:04:04 +0100 Subject: [PATCH 3853/5631] watchdog: wm8350: Simplify using devm_watchdog_register_device() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows to drop the .remove() function as it only exists to unregister the watchdog device which is now done in a callback registered by devm_watchdog_register_device(). Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20230307070404.2256308-4-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/wm8350_wdt.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/watchdog/wm8350_wdt.c b/drivers/watchdog/wm8350_wdt.c index 33c62d51f00a..c82c1b77d91b 100644 --- a/drivers/watchdog/wm8350_wdt.c +++ b/drivers/watchdog/wm8350_wdt.c @@ -153,18 +153,11 @@ static int wm8350_wdt_probe(struct platform_device *pdev) /* Default to 4s timeout */ wm8350_wdt_set_timeout(&wm8350_wdt, 4); - return watchdog_register_device(&wm8350_wdt); -} - -static int wm8350_wdt_remove(struct platform_device *pdev) -{ - watchdog_unregister_device(&wm8350_wdt); - return 0; + return devm_watchdog_register_device(&pdev->dev, &wm8350_wdt); } static struct platform_driver wm8350_wdt_driver = { .probe = wm8350_wdt_probe, - .remove = wm8350_wdt_remove, .driver = { .name = "wm8350-wdt", }, -- GitLab From 16d477a1dba9f214d1229d0a122d6d3a9636aa79 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 07:56:02 +0100 Subject: [PATCH 3854/5631] watchdog: s3c2410: Make s3c2410_get_wdt_drv_data() return an int MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a preparation for making more use of dev_err_probe(). The idea is that s3c2410_get_wdt_drv_data() (as it's called only by .probe()) can make effective use of dev_err_probe() only if it returns an int. For that the assignment to wdt->drv_data has to happen in the function. The caller can then just pass on the return value in the error case. This seems to be nicer for the compiler: bloatometer reports for an ARCH=arm s3c6400_defconfig build: add/remove: 1/1 grow/shrink: 0/1 up/down: 4/-64 (-60) Function old new delta __initcall__kmod_s3c2410_wdt__209_821_s3c2410wdt_driver_init6 - 4 +4 __initcall__kmod_s3c2410_wdt__209_819_s3c2410wdt_driver_init6 4 - -4 s3c2410wdt_probe 1332 1272 -60 There is no semantical change. (Just one minor difference: Before this patch wdt->drv_data was always assigned, now that only happens in the non-error case. That doesn't matter however as *wdt is freed in the error case.) Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230307065603.2253054-2-u.kleine-koenig@pengutronix.de Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/s3c2410_wdt.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 58b262ca4e88..f3de8ef499c3 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -579,8 +579,8 @@ static inline unsigned int s3c2410wdt_get_bootstatus(struct s3c2410_wdt *wdt) return 0; } -static inline const struct s3c2410_wdt_variant * -s3c2410_get_wdt_drv_data(struct platform_device *pdev) +static inline int +s3c2410_get_wdt_drv_data(struct platform_device *pdev, struct s3c2410_wdt *wdt) { const struct s3c2410_wdt_variant *variant; struct device *dev = &pdev->dev; @@ -603,24 +603,26 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev) "samsung,cluster-index", &index); if (err) { dev_err(dev, "failed to get cluster index\n"); - return NULL; + return -EINVAL; } switch (index) { case 0: - return variant; + break; case 1: - return (variant == &drv_data_exynos850_cl0) ? + variant = (variant == &drv_data_exynos850_cl0) ? &drv_data_exynos850_cl1 : &drv_data_exynosautov9_cl1; + break; default: dev_err(dev, "wrong cluster index: %u\n", index); - return NULL; + return -EINVAL; } } #endif - return variant; + wdt->drv_data = variant; + return 0; } static void s3c2410wdt_wdt_disable_action(void *data) @@ -644,9 +646,9 @@ static int s3c2410wdt_probe(struct platform_device *pdev) spin_lock_init(&wdt->lock); wdt->wdt_device = s3c2410_wdd; - wdt->drv_data = s3c2410_get_wdt_drv_data(pdev); - if (!wdt->drv_data) - return -EINVAL; + ret = s3c2410_get_wdt_drv_data(pdev, wdt); + if (ret) + return ret; if (wdt->drv_data->quirks & QUIRKS_HAVE_PMUREG) { wdt->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node, -- GitLab From e0e0ee02e616269451dd00ff56be0328d5625a92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 7 Mar 2023 07:56:03 +0100 Subject: [PATCH 3855/5631] watchdog: s3c2410_wdt: Simplify using dev_err_probe() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Make use of dev_err_probe() also for error paths that don't have to handle -EPROBE_DEFER. While the code handing -EPROBE_DEFER isn't used for these error paths, it still simpler as it cares for pretty printing the error code and usually needs one code line less as it combines message emitting and error returning. This also unifies the format of the error messages. Signed-off-by: Uwe Kleine-König Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230307065603.2253054-3-u.kleine-koenig@pengutronix.de [groeck: Split long line to avoid checkpatch warning] Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/s3c2410_wdt.c | 30 +++++++++++------------------- 1 file changed, 11 insertions(+), 19 deletions(-) diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index f3de8ef499c3..0244e73da642 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -601,10 +601,8 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev, struct s3c2410_wdt *wdt) err = of_property_read_u32(dev->of_node, "samsung,cluster-index", &index); - if (err) { - dev_err(dev, "failed to get cluster index\n"); - return -EINVAL; - } + if (err) + return dev_err_probe(dev, -EINVAL, "failed to get cluster index\n"); switch (index) { case 0: @@ -615,8 +613,7 @@ s3c2410_get_wdt_drv_data(struct platform_device *pdev, struct s3c2410_wdt *wdt) &drv_data_exynosautov9_cl1; break; default: - dev_err(dev, "wrong cluster index: %u\n", index); - return -EINVAL; + return dev_err_probe(dev, -EINVAL, "wrong cluster index: %u\n", index); } } #endif @@ -653,10 +650,9 @@ static int s3c2410wdt_probe(struct platform_device *pdev) if (wdt->drv_data->quirks & QUIRKS_HAVE_PMUREG) { wdt->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node, "samsung,syscon-phandle"); - if (IS_ERR(wdt->pmureg)) { - dev_err(dev, "syscon regmap lookup failed.\n"); - return PTR_ERR(wdt->pmureg); - } + if (IS_ERR(wdt->pmureg)) + return dev_err_probe(dev, PTR_ERR(wdt->pmureg), + "syscon regmap lookup failed.\n"); } wdt_irq = platform_get_irq(pdev, 0); @@ -694,21 +690,17 @@ static int s3c2410wdt_probe(struct platform_device *pdev) if (ret) { ret = s3c2410wdt_set_heartbeat(&wdt->wdt_device, S3C2410_WATCHDOG_DEFAULT_TIME); - if (ret == 0) { + if (ret == 0) dev_warn(dev, "tmr_margin value out of range, default %d used\n", S3C2410_WATCHDOG_DEFAULT_TIME); - } else { - dev_err(dev, "failed to use default timeout\n"); - return ret; - } + else + return dev_err_probe(dev, ret, "failed to use default timeout\n"); } ret = devm_request_irq(dev, wdt_irq, s3c2410wdt_irq, 0, pdev->name, pdev); - if (ret != 0) { - dev_err(dev, "failed to install irq (%d)\n", ret); - return ret; - } + if (ret != 0) + return dev_err_probe(dev, ret, "failed to install irq (%d)\n", ret); watchdog_set_nowayout(&wdt->wdt_device, nowayout); watchdog_set_restart_priority(&wdt->wdt_device, 128); -- GitLab From 8fd15ace76a4aeb3648cf078541b5e6cfc91d5a2 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 31 Dec 2022 12:07:27 +0100 Subject: [PATCH 3856/5631] watchdog: ixp4xx: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code and avoids the need of a dedicated function used with devm_add_action_or_reset(). Signed-off-by: Christophe JAILLET Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/5d04e453a4da5cfafb56695a17157fa3ea296511.1672484831.git.christophe.jaillet@wanadoo.fr Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/ixp4xx_wdt.c | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c index 281a48d9889f..607ce4b8df57 100644 --- a/drivers/watchdog/ixp4xx_wdt.c +++ b/drivers/watchdog/ixp4xx_wdt.c @@ -112,12 +112,6 @@ static const struct watchdog_info ixp4xx_wdt_info = { .identity = KBUILD_MODNAME, }; -/* Devres-handled clock disablement */ -static void ixp4xx_clock_action(void *d) -{ - clk_disable_unprepare(d); -} - static int ixp4xx_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -139,16 +133,10 @@ static int ixp4xx_wdt_probe(struct platform_device *pdev) * Retrieve rate from a fixed clock from the device tree if * the parent has that, else use the default clock rate. */ - clk = devm_clk_get(dev->parent, NULL); - if (!IS_ERR(clk)) { - ret = clk_prepare_enable(clk); - if (ret) - return ret; - ret = devm_add_action_or_reset(dev, ixp4xx_clock_action, clk); - if (ret) - return ret; + clk = devm_clk_get_enabled(dev->parent, NULL); + if (!IS_ERR(clk)) iwdt->rate = clk_get_rate(clk); - } + if (!iwdt->rate) iwdt->rate = IXP4XX_TIMER_FREQ; -- GitLab From 07d41160b3b65c621f9352196c3791fdc7d2380d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 31 Dec 2022 12:14:30 +0100 Subject: [PATCH 3857/5631] watchdog: loongson1: Use devm_clk_get_enabled() helper The devm_clk_get_enabled() helper: - calls devm_clk_get() - calls clk_prepare_enable() and registers what is needed in order to call clk_disable_unprepare() when needed, as a managed resource. This simplifies the code and avoids the need of a dedicated function used with devm_add_action_or_reset(). Signed-off-by: Christophe JAILLET Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/624106aa86ef7e49f16b11b229528eabd63de8f7.1672485257.git.christophe.jaillet@wanadoo.fr Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/loongson1_wdt.c | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) diff --git a/drivers/watchdog/loongson1_wdt.c b/drivers/watchdog/loongson1_wdt.c index bb3d075c0633..c55656cfb403 100644 --- a/drivers/watchdog/loongson1_wdt.c +++ b/drivers/watchdog/loongson1_wdt.c @@ -79,11 +79,6 @@ static const struct watchdog_ops ls1x_wdt_ops = { .set_timeout = ls1x_wdt_set_timeout, }; -static void ls1x_clk_disable_unprepare(void *data) -{ - clk_disable_unprepare(data); -} - static int ls1x_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -100,20 +95,10 @@ static int ls1x_wdt_probe(struct platform_device *pdev) if (IS_ERR(drvdata->base)) return PTR_ERR(drvdata->base); - drvdata->clk = devm_clk_get(dev, pdev->name); + drvdata->clk = devm_clk_get_enabled(dev, pdev->name); if (IS_ERR(drvdata->clk)) return PTR_ERR(drvdata->clk); - err = clk_prepare_enable(drvdata->clk); - if (err) { - dev_err(dev, "clk enable failed\n"); - return err; - } - err = devm_add_action_or_reset(dev, ls1x_clk_disable_unprepare, - drvdata->clk); - if (err) - return err; - clk_rate = clk_get_rate(drvdata->clk); if (!clk_rate) return -EINVAL; -- GitLab From 76ad36bf0ea620b14d32a332108a248412886d54 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Wed, 1 Mar 2023 07:55:09 +0100 Subject: [PATCH 3858/5631] watchdog: rt2880-wdt: avoid static global declarations Instead of using static global definitions in driver code, refactor code introducing a new watchdog driver data structure and use it along the code. Signed-off-by: Sergio Paracuellos Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230301065510.2818425-1-sergio.paracuellos@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rt2880_wdt.c | 89 ++++++++++++++++++++--------------- 1 file changed, 50 insertions(+), 39 deletions(-) diff --git a/drivers/watchdog/rt2880_wdt.c b/drivers/watchdog/rt2880_wdt.c index 49aff800824d..e54737bcf939 100644 --- a/drivers/watchdog/rt2880_wdt.c +++ b/drivers/watchdog/rt2880_wdt.c @@ -40,10 +40,13 @@ #define TMR1CTL_PRESCALE_MASK 0xf #define TMR1CTL_PRESCALE_65536 0xf -static struct clk *rt288x_wdt_clk; -static unsigned long rt288x_wdt_freq; -static void __iomem *rt288x_wdt_base; -static struct reset_control *rt288x_wdt_reset; +struct rt2880_wdt_data { + void __iomem *base; + unsigned long freq; + struct clk *clk; + struct reset_control *rst; + struct watchdog_device wdt; +}; static bool nowayout = WATCHDOG_NOWAYOUT; module_param(nowayout, bool, 0); @@ -51,52 +54,56 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static inline void rt_wdt_w32(unsigned reg, u32 val) +static inline void rt_wdt_w32(void __iomem *base, unsigned reg, u32 val) { - iowrite32(val, rt288x_wdt_base + reg); + iowrite32(val, base + reg); } -static inline u32 rt_wdt_r32(unsigned reg) +static inline u32 rt_wdt_r32(void __iomem *base, unsigned reg) { - return ioread32(rt288x_wdt_base + reg); + return ioread32(base + reg); } static int rt288x_wdt_ping(struct watchdog_device *w) { - rt_wdt_w32(TIMER_REG_TMR1LOAD, w->timeout * rt288x_wdt_freq); + struct rt2880_wdt_data *drvdata = watchdog_get_drvdata(w); + + rt_wdt_w32(drvdata->base, TIMER_REG_TMR1LOAD, w->timeout * drvdata->freq); return 0; } static int rt288x_wdt_start(struct watchdog_device *w) { + struct rt2880_wdt_data *drvdata = watchdog_get_drvdata(w); u32 t; - t = rt_wdt_r32(TIMER_REG_TMR1CTL); + t = rt_wdt_r32(drvdata->base, TIMER_REG_TMR1CTL); t &= ~(TMR1CTL_MODE_MASK << TMR1CTL_MODE_SHIFT | TMR1CTL_PRESCALE_MASK); t |= (TMR1CTL_MODE_WDT << TMR1CTL_MODE_SHIFT | TMR1CTL_PRESCALE_65536); - rt_wdt_w32(TIMER_REG_TMR1CTL, t); + rt_wdt_w32(drvdata->base, TIMER_REG_TMR1CTL, t); rt288x_wdt_ping(w); - t = rt_wdt_r32(TIMER_REG_TMR1CTL); + t = rt_wdt_r32(drvdata->base, TIMER_REG_TMR1CTL); t |= TMR1CTL_ENABLE; - rt_wdt_w32(TIMER_REG_TMR1CTL, t); + rt_wdt_w32(drvdata->base, TIMER_REG_TMR1CTL, t); return 0; } static int rt288x_wdt_stop(struct watchdog_device *w) { + struct rt2880_wdt_data *drvdata = watchdog_get_drvdata(w); u32 t; rt288x_wdt_ping(w); - t = rt_wdt_r32(TIMER_REG_TMR1CTL); + t = rt_wdt_r32(drvdata->base, TIMER_REG_TMR1CTL); t &= ~TMR1CTL_ENABLE; - rt_wdt_w32(TIMER_REG_TMR1CTL, t); + rt_wdt_w32(drvdata->base, TIMER_REG_TMR1CTL, t); return 0; } @@ -130,41 +137,45 @@ static const struct watchdog_ops rt288x_wdt_ops = { .set_timeout = rt288x_wdt_set_timeout, }; -static struct watchdog_device rt288x_wdt_dev = { - .info = &rt288x_wdt_info, - .ops = &rt288x_wdt_ops, - .min_timeout = 1, -}; - static int rt288x_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct watchdog_device *wdt; + struct rt2880_wdt_data *drvdata; int ret; - rt288x_wdt_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(rt288x_wdt_base)) - return PTR_ERR(rt288x_wdt_base); + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(drvdata->base)) + return PTR_ERR(drvdata->base); - rt288x_wdt_clk = devm_clk_get(dev, NULL); - if (IS_ERR(rt288x_wdt_clk)) - return PTR_ERR(rt288x_wdt_clk); + drvdata->clk = devm_clk_get(dev, NULL); + if (IS_ERR(drvdata->clk)) + return PTR_ERR(drvdata->clk); - rt288x_wdt_reset = devm_reset_control_get_exclusive(dev, NULL); - if (!IS_ERR(rt288x_wdt_reset)) - reset_control_deassert(rt288x_wdt_reset); + drvdata->rst = devm_reset_control_get_exclusive(dev, NULL); + if (!IS_ERR(drvdata->rst)) + reset_control_deassert(drvdata->rst); - rt288x_wdt_freq = clk_get_rate(rt288x_wdt_clk) / RALINK_WDT_PRESCALE; + drvdata->freq = clk_get_rate(drvdata->clk) / RALINK_WDT_PRESCALE; - rt288x_wdt_dev.bootstatus = rt288x_wdt_bootcause(); - rt288x_wdt_dev.max_timeout = (0xfffful / rt288x_wdt_freq); - rt288x_wdt_dev.parent = dev; + wdt = &drvdata->wdt; + wdt->info = &rt288x_wdt_info; + wdt->ops = &rt288x_wdt_ops; + wdt->min_timeout = 1; + wdt->max_timeout = (0xfffful / drvdata->freq); + wdt->parent = dev; + wdt->bootstatus = rt288x_wdt_bootcause(); - watchdog_init_timeout(&rt288x_wdt_dev, rt288x_wdt_dev.max_timeout, - dev); - watchdog_set_nowayout(&rt288x_wdt_dev, nowayout); + watchdog_init_timeout(wdt, wdt->max_timeout, dev); + watchdog_set_nowayout(wdt, nowayout); + watchdog_set_drvdata(wdt, drvdata); - watchdog_stop_on_reboot(&rt288x_wdt_dev); - ret = devm_watchdog_register_device(dev, &rt288x_wdt_dev); + watchdog_stop_on_reboot(wdt); + ret = devm_watchdog_register_device(dev, &drvdata->wdt); if (!ret) dev_info(dev, "Initialized\n"); -- GitLab From af3ac8e41786440a5ca0fa37628685f8f514f0a6 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Wed, 1 Mar 2023 07:55:10 +0100 Subject: [PATCH 3859/5631] watchdog: rt2880-wdt: prefer unsigned int over unsigned Instead of declare 'reg' variable in read and write operations as a bare 'unsigned' type prefer to declate it as 'unsigned int'. Signed-off-by: Sergio Paracuellos Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230301065510.2818425-2-sergio.paracuellos@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/rt2880_wdt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/rt2880_wdt.c b/drivers/watchdog/rt2880_wdt.c index e54737bcf939..4499ba0eb5ea 100644 --- a/drivers/watchdog/rt2880_wdt.c +++ b/drivers/watchdog/rt2880_wdt.c @@ -54,12 +54,12 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static inline void rt_wdt_w32(void __iomem *base, unsigned reg, u32 val) +static inline void rt_wdt_w32(void __iomem *base, unsigned int reg, u32 val) { iowrite32(val, base + reg); } -static inline u32 rt_wdt_r32(void __iomem *base, unsigned reg) +static inline u32 rt_wdt_r32(void __iomem *base, unsigned int reg) { return ioread32(base + reg); } -- GitLab From fe5631bb3a4bf62208ed52600c21dd3d1787f412 Mon Sep 17 00:00:00 2001 From: Sergio Paracuellos Date: Thu, 2 Mar 2023 09:59:14 +0100 Subject: [PATCH 3860/5631] dt-bindings: watchdog: migrate rt2880 text bindings to YAML Ralink RT2880 Watchdog bindings used text format, so migrate them to YAML. There are some additions to the binding that were not in the original txt file. This binding is used in RT2880, RT3050, RT3352, RT3883, RT5350, and MT7620 SoCs. To properly align binding with driver code we need to add to the schema 'clocks' and 'resets' properties. Signed-off-by: Sergio Paracuellos Reviewed-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230302085914.2858645-1-sergio.paracuellos@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../bindings/watchdog/ralink,rt2880-wdt.yaml | 46 +++++++++++++++++++ .../bindings/watchdog/rt2880-wdt.txt | 18 -------- 2 files changed, 46 insertions(+), 18 deletions(-) create mode 100644 Documentation/devicetree/bindings/watchdog/ralink,rt2880-wdt.yaml delete mode 100644 Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt diff --git a/Documentation/devicetree/bindings/watchdog/ralink,rt2880-wdt.yaml b/Documentation/devicetree/bindings/watchdog/ralink,rt2880-wdt.yaml new file mode 100644 index 000000000000..51e00de947e9 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/ralink,rt2880-wdt.yaml @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/ralink,rt2880-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Ralink Watchdog Timers + +maintainers: + - Sergio Paracuellos + +allOf: + - $ref: watchdog.yaml# + +properties: + compatible: + const: ralink,rt2880-wdt + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + resets: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + watchdog@100 { + compatible = "ralink,rt2880-wdt"; + reg = <0x120 0x10>; + clocks = <&clkref>; + resets = <&rstctrl 8>; + interrupt-parent = <&intc>; + interrupts = <1>; + }; diff --git a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt b/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt deleted file mode 100644 index 05b95bfa2a89..000000000000 --- a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt +++ /dev/null @@ -1,18 +0,0 @@ -Ralink Watchdog Timers - -Required properties: -- compatible: must be "ralink,rt2880-wdt" -- reg: physical base address of the controller and length of the register range - -Optional properties: -- interrupts: Specify the INTC interrupt number - -Example: - - watchdog@120 { - compatible = "ralink,rt2880-wdt"; - reg = <0x120 0x10>; - - interrupt-parent = <&intc>; - interrupts = <1>; - }; -- GitLab From 4eda19cc8a29cde3580ed73bf11dc73b4e757697 Mon Sep 17 00:00:00 2001 From: Gregory Oakes Date: Thu, 16 Mar 2023 15:13:12 -0500 Subject: [PATCH 3861/5631] watchdog: sp5100_tco: Immediately trigger upon starting. The watchdog countdown is supposed to begin when the device file is opened. Instead, it would begin countdown upon the first write to or close of the device file. Now, the ping operation is called within the start operation which ensures the countdown begins. From experimenation, it does not appear possible to do this with a single write including both the start bit and the trigger bit. So, it is done as two distinct writes. Signed-off-by: Gregory Oakes Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230316201312.17538-1-gregory.oakes@amd.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/sp5100_tco.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/watchdog/sp5100_tco.c b/drivers/watchdog/sp5100_tco.c index fb426b7d81da..14f8d8d90920 100644 --- a/drivers/watchdog/sp5100_tco.c +++ b/drivers/watchdog/sp5100_tco.c @@ -115,6 +115,10 @@ static int tco_timer_start(struct watchdog_device *wdd) val |= SP5100_WDT_START_STOP_BIT; writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + /* This must be a distinct write. */ + val |= SP5100_WDT_TRIGGER_BIT; + writel(val, SP5100_WDT_CONTROL(tco->tcobase)); + return 0; } -- GitLab From bfeaadbc0b8231e81dacd0616b476520759641ae Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 10 Mar 2023 23:30:12 +0100 Subject: [PATCH 3862/5631] watchdog: aspeed: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it is not relevant here). drivers/watchdog/aspeed_wdt.c:56:34: error: ‘aspeed_wdt_of_table’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230310223012.315897-1-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/aspeed_wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/aspeed_wdt.c b/drivers/watchdog/aspeed_wdt.c index c1e79874a2bb..b72a858bbac7 100644 --- a/drivers/watchdog/aspeed_wdt.c +++ b/drivers/watchdog/aspeed_wdt.c @@ -465,7 +465,7 @@ static struct platform_driver aspeed_watchdog_driver = { .probe = aspeed_wdt_probe, .driver = { .name = KBUILD_MODNAME, - .of_match_table = of_match_ptr(aspeed_wdt_of_table), + .of_match_table = aspeed_wdt_of_table, }, }; -- GitLab From fc0c5db58f4c78b948acfbf9558eeaf6b343bf9a Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 21 Mar 2023 14:34:39 -0400 Subject: [PATCH 3863/5631] watchdog: s3c2410: remove unused freq_to_wdt and s3c2410wdt_is_running functions clang with W=1 reports drivers/watchdog/s3c2410_wdt.c:311:35: error: unused function 'freq_to_wdt' [-Werror,-Wunused-function] static inline struct s3c2410_wdt *freq_to_wdt(struct notifier_block *nb) ^ drivers/watchdog/s3c2410_wdt.c:446:19: error: unused function 's3c2410wdt_is_running' [-Werror,-Wunused-function] static inline int s3c2410wdt_is_running(struct s3c2410_wdt *wdt) ^ These functions are not used, so remove them. Signed-off-by: Tom Rix Reviewed-by: Andi Shyti Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230321183439.1826823-1-trix@redhat.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/s3c2410_wdt.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 0244e73da642..95416a9bdd4b 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -308,11 +308,6 @@ static inline unsigned int s3c2410wdt_max_timeout(struct s3c2410_wdt *wdt) / S3C2410_WTCON_MAXDIV); } -static inline struct s3c2410_wdt *freq_to_wdt(struct notifier_block *nb) -{ - return container_of(nb, struct s3c2410_wdt, freq_transition); -} - static int s3c2410wdt_disable_wdt_reset(struct s3c2410_wdt *wdt, bool mask) { const u32 mask_val = BIT(wdt->drv_data->mask_bit); @@ -443,11 +438,6 @@ static int s3c2410wdt_start(struct watchdog_device *wdd) return 0; } -static inline int s3c2410wdt_is_running(struct s3c2410_wdt *wdt) -{ - return readl(wdt->reg_base + S3C2410_WTCON) & S3C2410_WTCON_ENABLE; -} - static int s3c2410wdt_set_heartbeat(struct watchdog_device *wdd, unsigned int timeout) { -- GitLab From 33e4945352a2484c92fc1d5a16471b1939d67abb Mon Sep 17 00:00:00 2001 From: Jakob Koschel Date: Mon, 13 Mar 2023 14:59:19 +0100 Subject: [PATCH 3864/5631] watchdog: avoid usage of iterator after loop If potentially no valid element is found, 'p' would contain an invalid pointer past the iterator loop. To ensure 'p' is valid under any circumstances, the kfree() should be within the loop body. Additionally, Linus proposed to avoid any use of the list iterator variable after the loop, in the attempt to move the list iterator variable declaration into the macro to avoid any potential misuse after the loop [1]. Link: https://lore.kernel.org/all/CAHk-=wgRr_D8CB-D9Kg-c=EHreAsk5SqXPwr9Y7k9sA6cWXJ6w@mail.gmail.com/ [1] Signed-off-by: Jakob Koschel Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230301-watchdog-avoid-iter-after-loop-v2-1-8411e3bbe0de@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/watchdog_pretimeout.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/watchdog/watchdog_pretimeout.c b/drivers/watchdog/watchdog_pretimeout.c index 376a495ab80c..e5295c990fa1 100644 --- a/drivers/watchdog/watchdog_pretimeout.c +++ b/drivers/watchdog/watchdog_pretimeout.c @@ -207,10 +207,9 @@ void watchdog_unregister_pretimeout(struct watchdog_device *wdd) list_for_each_entry_safe(p, t, &pretimeout_list, entry) { if (p->wdd == wdd) { list_del(&p->entry); + kfree(p); break; } } spin_unlock_irq(&pretimeout_lock); - - kfree(p); } -- GitLab From dcd615ee6fd3651ab0357364c4cf65b1148a40be Mon Sep 17 00:00:00 2001 From: Shreeya Patel Date: Wed, 29 Mar 2023 02:30:48 +0530 Subject: [PATCH 3865/5631] dt-bindings: watchdog: rockchip: Add rockchip,rk3588-wdt string Add rockchip,rk3588-wdt compatible string. Signed-off-by: Shreeya Patel Reviewed-by: Heiko Stuebner Acked-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20230328210048.195124-3-shreeya.patel@collabora.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml index 92df6e453f64..e7a87ce94772 100644 --- a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml @@ -29,6 +29,7 @@ properties: - rockchip,rk3368-wdt - rockchip,rk3399-wdt - rockchip,rk3568-wdt + - rockchip,rk3588-wdt - rockchip,rv1108-wdt - const: snps,dw-wdt -- GitLab From 2cd55934d9774d23a7c683e415935cb9cd7dedff Mon Sep 17 00:00:00 2001 From: Kathiravan T Date: Mon, 20 Mar 2023 16:15:29 +0530 Subject: [PATCH 3866/5631] dt-bindings: watchdog: qcom-wdt: add qcom,apss-wdt-ipq5332 compatible Add a compatible for the IPQ5332 platform's APSS watchdog. Reviewed-by: Krzysztof Kozlowski Signed-off-by: Kathiravan T Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230320104530.30411-2-quic_kathirav@quicinc.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index 6448b633c970..8060a87d29da 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -18,6 +18,7 @@ properties: - items: - enum: - qcom,kpss-wdt-ipq4019 + - qcom,apss-wdt-ipq5332 - qcom,apss-wdt-msm8994 - qcom,apss-wdt-qcs404 - qcom,apss-wdt-sa8775p -- GitLab From ee0da40588e1eda1323e7abd8e91a2dfe359b87c Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Tue, 14 Mar 2023 13:52:56 +0100 Subject: [PATCH 3867/5631] dt-bindings: watchdog: qcom-wdt: add QCM2290 Document the QCM2290 KPSS watchdog. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230314-topic-2290_compats-v1-1-47e26c3c0365@linaro.org [groeck: Fixed context conflicts] Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index 8060a87d29da..b0ce80d6fbe2 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -19,7 +19,9 @@ properties: - enum: - qcom,kpss-wdt-ipq4019 - qcom,apss-wdt-ipq5332 + - qcom,apss-wdt-ipq9574 - qcom,apss-wdt-msm8994 + - qcom,apss-wdt-qcm2290 - qcom,apss-wdt-qcs404 - qcom,apss-wdt-sa8775p - qcom,apss-wdt-sc7180 -- GitLab From 64543b0d637bd28abed1a3311aa8c9b007ee52d7 Mon Sep 17 00:00:00 2001 From: Alexandre Mergnat Date: Fri, 7 Apr 2023 14:59:22 +0200 Subject: [PATCH 3868/5631] dt-bindings: watchdog: mediatek,mtk-wdt: add mt8365 Add binding description for mediatek,mt8365-wdt Acked-by: Krzysztof Kozlowski Reviewed-by: Matthias Brugger Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Alexandre Mergnat Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230203-evk-board-support-v5-3-1883c1b405ad@baylibre.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml b/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml index 55b34461df1b..66cacea8e47f 100644 --- a/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml @@ -38,6 +38,7 @@ properties: - mediatek,mt7623-wdt - mediatek,mt7629-wdt - mediatek,mt8173-wdt + - mediatek,mt8365-wdt - mediatek,mt8516-wdt - const: mediatek,mt6589-wdt -- GitLab From ab8da07609fc982196df9df8f9b4f9ba4bea4731 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Mon, 10 Apr 2023 11:09:26 -0400 Subject: [PATCH 3869/5631] watchdog: ebc-c384_wdt: Mark status as orphaned The current maintainer no longer has access to the device for testing, the original user of this driver indicates that they have moved on to another device, and the manufacturer WINSYSTEMS does not appear interested in taking over support for this code. Signed-off-by: William Breathitt Gray Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230410150926.3354-1-william.gray@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- MAINTAINERS | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 90abe83c02f3..a1f44c4d40a9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22512,9 +22512,8 @@ S: Maintained F: drivers/media/rc/winbond-cir.c WINSYSTEMS EBC-C384 WATCHDOG DRIVER -M: William Breathitt Gray L: linux-watchdog@vger.kernel.org -S: Maintained +S: Orphan F: drivers/watchdog/ebc-c384_wdt.c WINSYSTEMS WS16C48 GPIO DRIVER -- GitLab From 819d14135da5f8cd0e2104a6def805707e46d99b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:08 +0200 Subject: [PATCH 3870/5631] dt-bindings: watchdog: indentation, quotes and white-space cleanup Minor cleanup without functional impact: 1. Indent DTS examples to preferred four-spaces (more readable for DTS), 2. Drop unneeded quotes, 3. Add/drop blank lines to make the code readable. Signed-off-by: Krzysztof Kozlowski Acked-by: Sergio Paracuellos Acked-by: Justin Chen Acked-by: Neil Armstrong Acked-by: Nicolas Ferre Reviewed-by: Geert Uytterhoeven Reviewed-by: Wolfram Sang Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230415095112.51257-2-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../watchdog/amlogic,meson-gxbb-wdt.yaml | 10 +++--- .../bindings/watchdog/arm,sbsa-gwdt.yaml | 1 - .../bindings/watchdog/arm,twd-wdt.yaml | 6 ++-- .../bindings/watchdog/arm-smc-wdt.yaml | 7 ++-- .../bindings/watchdog/atmel,sama5d4-wdt.yaml | 14 ++++---- .../bindings/watchdog/brcm,bcm7038-wdt.yaml | 6 ++-- .../bindings/watchdog/faraday,ftwdt010.yaml | 16 +++++----- .../watchdog/mediatek,mt7621-wdt.yaml | 6 ++-- .../bindings/watchdog/qcom-wdt.yaml | 32 +++++++++---------- .../bindings/watchdog/renesas,wdt.yaml | 14 ++++---- .../bindings/watchdog/snps,dw-wdt.yaml | 32 +++++++++---------- .../bindings/watchdog/st,stm32-iwdg.yaml | 10 +++--- .../watchdog/xlnx,xps-timebase-wdt.yaml | 12 +++---- 13 files changed, 83 insertions(+), 83 deletions(-) diff --git a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml index 497d60408ea0..f5cc7aa1b93b 100644 --- a/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/amlogic,meson-gxbb-wdt.yaml @@ -2,8 +2,8 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/watchdog/amlogic,meson-gxbb-wdt.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/watchdog/amlogic,meson-gxbb-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Meson GXBB SoCs Watchdog timer @@ -36,7 +36,7 @@ unevaluatedProperties: false examples: - | watchdog@98d0 { - compatible = "amlogic,meson-gxbb-wdt"; - reg = <0x98d0 0x10>; - clocks = <&xtal>; + compatible = "amlogic,meson-gxbb-wdt"; + reg = <0x98d0 0x10>; + clocks = <&xtal>; }; diff --git a/Documentation/devicetree/bindings/watchdog/arm,sbsa-gwdt.yaml b/Documentation/devicetree/bindings/watchdog/arm,sbsa-gwdt.yaml index 6bfa46353c4e..aa804f96acba 100644 --- a/Documentation/devicetree/bindings/watchdog/arm,sbsa-gwdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/arm,sbsa-gwdt.yaml @@ -40,7 +40,6 @@ unevaluatedProperties: false examples: - | - watchdog@2a440000 { compatible = "arm,sbsa-gwdt"; reg = <0x2a440000 0x1000>, diff --git a/Documentation/devicetree/bindings/watchdog/arm,twd-wdt.yaml b/Documentation/devicetree/bindings/watchdog/arm,twd-wdt.yaml index bb8901854222..9646ac72051e 100644 --- a/Documentation/devicetree/bindings/watchdog/arm,twd-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/arm,twd-wdt.yaml @@ -44,7 +44,7 @@ examples: #include watchdog@2c000620 { - compatible = "arm,arm11mp-twd-wdt"; - reg = <0x2c000620 0x20>; - interrupts = ; + compatible = "arm,arm11mp-twd-wdt"; + reg = <0x2c000620 0x20>; + interrupts = ; }; diff --git a/Documentation/devicetree/bindings/watchdog/arm-smc-wdt.yaml b/Documentation/devicetree/bindings/watchdog/arm-smc-wdt.yaml index e3a1d79574e2..bbfa2bac6c36 100644 --- a/Documentation/devicetree/bindings/watchdog/arm-smc-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/arm-smc-wdt.yaml @@ -16,6 +16,7 @@ properties: compatible: enum: - arm,smc-wdt + arm,smc-id: $ref: /schemas/types.yaml#/definitions/uint32 description: | @@ -30,9 +31,9 @@ unevaluatedProperties: false examples: - | watchdog { - compatible = "arm,smc-wdt"; - arm,smc-id = <0x82003D06>; - timeout-sec = <15>; + compatible = "arm,smc-wdt"; + arm,smc-id = <0x82003D06>; + timeout-sec = <15>; }; ... diff --git a/Documentation/devicetree/bindings/watchdog/atmel,sama5d4-wdt.yaml b/Documentation/devicetree/bindings/watchdog/atmel,sama5d4-wdt.yaml index a9635c03761c..59e36d8ae45d 100644 --- a/Documentation/devicetree/bindings/watchdog/atmel,sama5d4-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/atmel,sama5d4-wdt.yaml @@ -65,13 +65,13 @@ examples: #include watchdog@fc068640 { - compatible = "atmel,sama5d4-wdt"; - reg = <0xfc068640 0x10>; - interrupts = <4 IRQ_TYPE_LEVEL_HIGH 5>; - timeout-sec = <10>; - atmel,watchdog-type = "hardware"; - atmel,dbg-halt; - atmel,idle-halt; + compatible = "atmel,sama5d4-wdt"; + reg = <0xfc068640 0x10>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH 5>; + timeout-sec = <10>; + atmel,watchdog-type = "hardware"; + atmel,dbg-halt; + atmel,idle-halt; }; ... diff --git a/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml b/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml index a926809352b8..94ae6565ed10 100644 --- a/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/brcm,bcm7038-wdt.yaml @@ -37,7 +37,7 @@ required: examples: - | watchdog@f040a7e8 { - compatible = "brcm,bcm7038-wdt"; - reg = <0xf040a7e8 0x16>; - clocks = <&upg_fixed>; + compatible = "brcm,bcm7038-wdt"; + reg = <0xf040a7e8 0x16>; + clocks = <&upg_fixed>; }; diff --git a/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.yaml b/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.yaml index 6ecd429f76b5..f1433d9b6cd9 100644 --- a/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.yaml +++ b/Documentation/devicetree/bindings/watchdog/faraday,ftwdt010.yaml @@ -52,16 +52,16 @@ examples: - | #include watchdog@41000000 { - compatible = "faraday,ftwdt010"; - reg = <0x41000000 0x1000>; - interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; - timeout-sec = <5>; + compatible = "faraday,ftwdt010"; + reg = <0x41000000 0x1000>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; + timeout-sec = <5>; }; - | watchdog: watchdog@98500000 { - compatible = "moxa,moxart-watchdog", "faraday,ftwdt010"; - reg = <0x98500000 0x10>; - clocks = <&clk_apb>; - clock-names = "PCLK"; + compatible = "moxa,moxart-watchdog", "faraday,ftwdt010"; + reg = <0x98500000 0x10>; + clocks = <&clk_apb>; + clock-names = "PCLK"; }; ... diff --git a/Documentation/devicetree/bindings/watchdog/mediatek,mt7621-wdt.yaml b/Documentation/devicetree/bindings/watchdog/mediatek,mt7621-wdt.yaml index a668d0c2f14b..18160869c378 100644 --- a/Documentation/devicetree/bindings/watchdog/mediatek,mt7621-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/mediatek,mt7621-wdt.yaml @@ -34,7 +34,7 @@ additionalProperties: false examples: - | watchdog@100 { - compatible = "mediatek,mt7621-wdt"; - reg = <0x100 0x100>; - mediatek,sysctl = <&sysc>; + compatible = "mediatek,mt7621-wdt"; + reg = <0x100 0x100>; + mediatek,sysctl = <&sysc>; }; diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index b0ce80d6fbe2..3c8fa2f3b0ba 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -116,26 +116,26 @@ examples: #include watchdog@17c10000 { - compatible = "qcom,apss-wdt-sm8150", "qcom,kpss-wdt"; - reg = <0x17c10000 0x1000>; - clocks = <&sleep_clk>; - interrupts = ; - timeout-sec = <10>; + compatible = "qcom,apss-wdt-sm8150", "qcom,kpss-wdt"; + reg = <0x17c10000 0x1000>; + clocks = <&sleep_clk>; + interrupts = ; + timeout-sec = <10>; }; - | #include watchdog@200a000 { - compatible = "qcom,kpss-wdt-ipq8064", "qcom,kpss-timer", "qcom,msm-timer"; - interrupts = , - , - , - , - ; - reg = <0x0200a000 0x100>; - clock-frequency = <25000000>; - clocks = <&sleep_clk>; - clock-names = "sleep"; - cpu-offset = <0x80000>; + compatible = "qcom,kpss-wdt-ipq8064", "qcom,kpss-timer", "qcom,msm-timer"; + interrupts = , + , + , + , + ; + reg = <0x0200a000 0x100>; + clock-frequency = <25000000>; + clocks = <&sleep_clk>; + clock-names = "sleep"; + cpu-offset = <0x80000>; }; diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml index e2c9bf1aec38..4ba262c06ca0 100644 --- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.yaml @@ -177,11 +177,11 @@ examples: #include #include wdt0: watchdog@e6020000 { - compatible = "renesas,r8a7795-wdt", "renesas,rcar-gen3-wdt"; - reg = <0xe6020000 0x0c>; - interrupts = ; - clocks = <&cpg CPG_MOD 402>; - power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; - resets = <&cpg 402>; - timeout-sec = <60>; + compatible = "renesas,r8a7795-wdt", "renesas,rcar-gen3-wdt"; + reg = <0xe6020000 0x0c>; + interrupts = ; + clocks = <&cpg CPG_MOD 402>; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 402>; + timeout-sec = <60>; }; diff --git a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml index e7a87ce94772..1b13a96abba9 100644 --- a/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/snps,dw-wdt.yaml @@ -83,25 +83,25 @@ required: examples: - | watchdog@ffd02000 { - compatible = "snps,dw-wdt"; - reg = <0xffd02000 0x1000>; - interrupts = <0 171 4>; - clocks = <&per_base_clk>; - resets = <&wdt_rst>; + compatible = "snps,dw-wdt"; + reg = <0xffd02000 0x1000>; + interrupts = <0 171 4>; + clocks = <&per_base_clk>; + resets = <&wdt_rst>; }; - | watchdog@ffd02000 { - compatible = "snps,dw-wdt"; - reg = <0xffd02000 0x1000>; - interrupts = <0 171 4>; - clocks = <&per_base_clk>; - clock-names = "tclk"; - snps,watchdog-tops = <0x000000FF 0x000001FF 0x000003FF - 0x000007FF 0x0000FFFF 0x0001FFFF - 0x0003FFFF 0x0007FFFF 0x000FFFFF - 0x001FFFFF 0x003FFFFF 0x007FFFFF - 0x00FFFFFF 0x01FFFFFF 0x03FFFFFF - 0x07FFFFFF>; + compatible = "snps,dw-wdt"; + reg = <0xffd02000 0x1000>; + interrupts = <0 171 4>; + clocks = <&per_base_clk>; + clock-names = "tclk"; + snps,watchdog-tops = <0x000000FF 0x000001FF 0x000003FF + 0x000007FF 0x0000FFFF 0x0001FFFF + 0x0003FFFF 0x0007FFFF 0x000FFFFF + 0x001FFFFF 0x003FFFFF 0x007FFFFF + 0x00FFFFFF 0x01FFFFFF 0x03FFFFFF + 0x07FFFFFF>; }; ... diff --git a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml index a8e266f80c20..144a0ce43952 100644 --- a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml +++ b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml @@ -48,11 +48,11 @@ examples: - | #include watchdog@5a002000 { - compatible = "st,stm32mp1-iwdg"; - reg = <0x5a002000 0x400>; - clocks = <&rcc IWDG2>, <&rcc CK_LSI>; - clock-names = "pclk", "lsi"; - timeout-sec = <32>; + compatible = "st,stm32mp1-iwdg"; + reg = <0x5a002000 0x400>; + clocks = <&rcc IWDG2>, <&rcc CK_LSI>; + clock-names = "pclk", "lsi"; + timeout-sec = <32>; }; ... diff --git a/Documentation/devicetree/bindings/watchdog/xlnx,xps-timebase-wdt.yaml b/Documentation/devicetree/bindings/watchdog/xlnx,xps-timebase-wdt.yaml index 493a1c954707..8444c56dd602 100644 --- a/Documentation/devicetree/bindings/watchdog/xlnx,xps-timebase-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/xlnx,xps-timebase-wdt.yaml @@ -58,11 +58,11 @@ unevaluatedProperties: false examples: - | watchdog@40100000 { - compatible = "xlnx,xps-timebase-wdt-1.00.a"; - reg = <0x40100000 0x1000>; - clock-frequency = <50000000>; - clocks = <&clkc 15>; - xlnx,wdt-enable-once = <0x0>; - xlnx,wdt-interval = <0x1b>; + compatible = "xlnx,xps-timebase-wdt-1.00.a"; + reg = <0x40100000 0x1000>; + clock-frequency = <50000000>; + clocks = <&clkc 15>; + xlnx,wdt-enable-once = <0x0>; + xlnx,wdt-interval = <0x1b>; }; ... -- GitLab From b24e265d6f0a0965ae0d0a19848544300c397a2e Mon Sep 17 00:00:00 2001 From: Xingyu Wu Date: Tue, 14 Mar 2023 21:24:35 +0800 Subject: [PATCH 3871/5631] dt-bindings: watchdog: Add watchdog for StarFive JH7100 and JH7110 Add bindings to describe the watchdog for the StarFive JH7100/JH7110 SoC. And Use JH7100 as first StarFive SoC with watchdog. Signed-off-by: Xingyu Wu Reviewed-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230314132437.121534-2-xingyu.wu@starfivetech.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../watchdog/starfive,jh7100-wdt.yaml | 71 +++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 Documentation/devicetree/bindings/watchdog/starfive,jh7100-wdt.yaml diff --git a/Documentation/devicetree/bindings/watchdog/starfive,jh7100-wdt.yaml b/Documentation/devicetree/bindings/watchdog/starfive,jh7100-wdt.yaml new file mode 100644 index 000000000000..68f3f6fd08a6 --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/starfive,jh7100-wdt.yaml @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/starfive,jh7100-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: StarFive Watchdog for JH7100 and JH7110 SoC + +maintainers: + - Xingyu Wu + - Samin Guo + +description: + The JH7100 and JH7110 watchdog both are 32 bit counters. JH7100 watchdog + has only one timeout phase and reboots. And JH7110 watchdog has two + timeout phases. At the first phase, the signal of watchdog interrupt + output(WDOGINT) will rise when counter is 0. The counter will reload + the timeout value. And then, if counter decreases to 0 again and WDOGINT + isn't cleared, the watchdog will reset the system unless the watchdog + reset is disabled. + +allOf: + - $ref: watchdog.yaml# + +properties: + compatible: + enum: + - starfive,jh7100-wdt + - starfive,jh7110-wdt + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + items: + - description: APB clock + - description: Core clock + + clock-names: + items: + - const: apb + - const: core + + resets: + items: + - description: APB reset + - description: Core reset + +required: + - compatible + - reg + - clocks + - clock-names + - resets + +unevaluatedProperties: false + +examples: + - | + watchdog@12480000 { + compatible = "starfive,jh7100-wdt"; + reg = <0x12480000 0x10000>; + clocks = <&clk 171>, + <&clk 172>; + clock-names = "apb", "core"; + resets = <&rst 99>, + <&rst 100>; + }; -- GitLab From db728ea9c7be137b4f4361295f11e0b56b6286ac Mon Sep 17 00:00:00 2001 From: Xingyu Wu Date: Tue, 14 Mar 2023 21:24:36 +0800 Subject: [PATCH 3872/5631] drivers: watchdog: Add StarFive Watchdog driver Add watchdog driver for the StarFive JH7100 and JH7110 SoC. Signed-off-by: Xingyu Wu Reviewed-by: Emil Renner Berthing Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230314132437.121534-3-xingyu.wu@starfivetech.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- MAINTAINERS | 7 + drivers/watchdog/Kconfig | 11 + drivers/watchdog/Makefile | 3 + drivers/watchdog/starfive-wdt.c | 606 ++++++++++++++++++++++++++++++++ 4 files changed, 627 insertions(+) create mode 100644 drivers/watchdog/starfive-wdt.c diff --git a/MAINTAINERS b/MAINTAINERS index a1f44c4d40a9..6d1fdacf304e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19951,6 +19951,13 @@ S: Supported F: Documentation/devicetree/bindings/rng/starfive* F: drivers/char/hw_random/jh7110-trng.c +STARFIVE WATCHDOG DRIVER +M: Xingyu Wu +M: Samin Guo +S: Supported +F: Documentation/devicetree/bindings/watchdog/starfive* +F: drivers/watchdog/starfive-wdt.c + STATIC BRANCH/CALL M: Peter Zijlstra M: Josh Poimboeuf diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index f0872970daf9..f22138709bf5 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -1999,6 +1999,17 @@ config WATCHDOG_RTAS To compile this driver as a module, choose M here. The module will be called wdrtas. +# RISC-V Architecture + +config STARFIVE_WATCHDOG + tristate "StarFive Watchdog support" + depends on ARCH_STARFIVE || COMPILE_TEST + select WATCHDOG_CORE + default ARCH_STARFIVE + help + Say Y here to support the watchdog of StarFive JH7100 and JH7110 + SoC. This driver can also be built as a module if choose M. + # S390 Architecture config DIAG288_WATCHDOG diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile index 9cbf6580f16c..b4c4ccf2d703 100644 --- a/drivers/watchdog/Makefile +++ b/drivers/watchdog/Makefile @@ -192,6 +192,9 @@ obj-$(CONFIG_MEN_A21_WDT) += mena21_wdt.o obj-$(CONFIG_PSERIES_WDT) += pseries-wdt.o obj-$(CONFIG_WATCHDOG_RTAS) += wdrtas.o +# RISC-V Architecture +obj-$(CONFIG_STARFIVE_WATCHDOG) += starfive-wdt.o + # S390 Architecture obj-$(CONFIG_DIAG288_WATCHDOG) += diag288_wdt.o diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c new file mode 100644 index 000000000000..1995cceca51e --- /dev/null +++ b/drivers/watchdog/starfive-wdt.c @@ -0,0 +1,606 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Starfive Watchdog driver + * + * Copyright (C) 2022 StarFive Technology Co., Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include + +/* JH7100 Watchdog register define */ +#define STARFIVE_WDT_JH7100_INTSTAUS 0x000 +#define STARFIVE_WDT_JH7100_CONTROL 0x104 +#define STARFIVE_WDT_JH7100_LOAD 0x108 +#define STARFIVE_WDT_JH7100_EN 0x110 +#define STARFIVE_WDT_JH7100_RELOAD 0x114 /* Write 0 or 1 to reload preset value */ +#define STARFIVE_WDT_JH7100_VALUE 0x118 +#define STARFIVE_WDT_JH7100_INTCLR 0x120 /* + * [0]: Write 1 to clear interrupt + * [1]: 1 mean clearing and 0 mean complete + * [31:2]: reserved. + */ +#define STARFIVE_WDT_JH7100_LOCK 0x13c /* write 0x378f0765 to unlock */ + +/* JH7110 Watchdog register define */ +#define STARFIVE_WDT_JH7110_LOAD 0x000 +#define STARFIVE_WDT_JH7110_VALUE 0x004 +#define STARFIVE_WDT_JH7110_CONTROL 0x008 /* + * [0]: reset enable; + * [1]: interrupt enable && watchdog enable + * [31:2]: reserved. + */ +#define STARFIVE_WDT_JH7110_INTCLR 0x00c /* clear intterupt and reload the counter */ +#define STARFIVE_WDT_JH7110_IMS 0x014 +#define STARFIVE_WDT_JH7110_LOCK 0xc00 /* write 0x1ACCE551 to unlock */ + +/* WDOGCONTROL */ +#define STARFIVE_WDT_ENABLE 0x1 +#define STARFIVE_WDT_EN_SHIFT 0 +#define STARFIVE_WDT_RESET_EN 0x1 +#define STARFIVE_WDT_JH7100_RST_EN_SHIFT 0 +#define STARFIVE_WDT_JH7110_RST_EN_SHIFT 1 + +/* WDOGLOCK */ +#define STARFIVE_WDT_JH7100_UNLOCK_KEY 0x378f0765 +#define STARFIVE_WDT_JH7110_UNLOCK_KEY 0x1acce551 + +/* WDOGINTCLR */ +#define STARFIVE_WDT_INTCLR 0x1 +#define STARFIVE_WDT_JH7100_INTCLR_AVA_SHIFT 1 /* Watchdog can clear interrupt when 0 */ + +#define STARFIVE_WDT_MAXCNT 0xffffffff +#define STARFIVE_WDT_DEFAULT_TIME (15) +#define STARFIVE_WDT_DELAY_US 0 +#define STARFIVE_WDT_TIMEOUT_US 10000 + +/* module parameter */ +#define STARFIVE_WDT_EARLY_ENA 0 + +static bool nowayout = WATCHDOG_NOWAYOUT; +static int heartbeat; +static bool early_enable = STARFIVE_WDT_EARLY_ENA; + +module_param(heartbeat, int, 0); +module_param(early_enable, bool, 0); +module_param(nowayout, bool, 0); + +MODULE_PARM_DESC(heartbeat, "Watchdog heartbeat in seconds. (default=" + __MODULE_STRING(STARFIVE_WDT_DEFAULT_TIME) ")"); +MODULE_PARM_DESC(early_enable, + "Watchdog is started at boot time if set to 1, default=" + __MODULE_STRING(STARFIVE_WDT_EARLY_ENA)); +MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" + __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); + +struct starfive_wdt_variant { + unsigned int control; /* Watchdog Control Resgister for reset enable */ + unsigned int load; /* Watchdog Load register */ + unsigned int reload; /* Watchdog Reload Control register */ + unsigned int enable; /* Watchdog Enable Register */ + unsigned int value; /* Watchdog Counter Value Register */ + unsigned int int_clr; /* Watchdog Interrupt Clear Register */ + unsigned int unlock; /* Watchdog Lock Register */ + unsigned int int_status; /* Watchdog Interrupt Status Register */ + + u32 unlock_key; + char enrst_shift; + char en_shift; + bool intclr_check; /* whether need to check it before clearing interrupt */ + char intclr_ava_shift; + bool double_timeout; /* The watchdog need twice timeout to reboot */ +}; + +struct starfive_wdt { + struct watchdog_device wdd; + spinlock_t lock; /* spinlock for register handling */ + void __iomem *base; + struct clk *core_clk; + struct clk *apb_clk; + const struct starfive_wdt_variant *variant; + unsigned long freq; + u32 count; /* count of timeout */ + u32 reload; /* restore the count */ +}; + +/* Register layout and configuration for the JH7100 */ +static const struct starfive_wdt_variant starfive_wdt_jh7100_variant = { + .control = STARFIVE_WDT_JH7100_CONTROL, + .load = STARFIVE_WDT_JH7100_LOAD, + .reload = STARFIVE_WDT_JH7100_RELOAD, + .enable = STARFIVE_WDT_JH7100_EN, + .value = STARFIVE_WDT_JH7100_VALUE, + .int_clr = STARFIVE_WDT_JH7100_INTCLR, + .unlock = STARFIVE_WDT_JH7100_LOCK, + .unlock_key = STARFIVE_WDT_JH7100_UNLOCK_KEY, + .int_status = STARFIVE_WDT_JH7100_INTSTAUS, + .enrst_shift = STARFIVE_WDT_JH7100_RST_EN_SHIFT, + .en_shift = STARFIVE_WDT_EN_SHIFT, + .intclr_check = true, + .intclr_ava_shift = STARFIVE_WDT_JH7100_INTCLR_AVA_SHIFT, + .double_timeout = false, +}; + +/* Register layout and configuration for the JH7110 */ +static const struct starfive_wdt_variant starfive_wdt_jh7110_variant = { + .control = STARFIVE_WDT_JH7110_CONTROL, + .load = STARFIVE_WDT_JH7110_LOAD, + .enable = STARFIVE_WDT_JH7110_CONTROL, + .value = STARFIVE_WDT_JH7110_VALUE, + .int_clr = STARFIVE_WDT_JH7110_INTCLR, + .unlock = STARFIVE_WDT_JH7110_LOCK, + .unlock_key = STARFIVE_WDT_JH7110_UNLOCK_KEY, + .int_status = STARFIVE_WDT_JH7110_IMS, + .enrst_shift = STARFIVE_WDT_JH7110_RST_EN_SHIFT, + .en_shift = STARFIVE_WDT_EN_SHIFT, + .intclr_check = false, + .double_timeout = true, +}; + +static int starfive_wdt_enable_clock(struct starfive_wdt *wdt) +{ + int ret; + + ret = clk_prepare_enable(wdt->apb_clk); + if (ret) + return dev_err_probe(wdt->wdd.parent, ret, "failed to enable apb clock\n"); + + ret = clk_prepare_enable(wdt->core_clk); + if (ret) + return dev_err_probe(wdt->wdd.parent, ret, "failed to enable core clock\n"); + + return 0; +} + +static void starfive_wdt_disable_clock(struct starfive_wdt *wdt) +{ + clk_disable_unprepare(wdt->core_clk); + clk_disable_unprepare(wdt->apb_clk); +} + +static inline int starfive_wdt_get_clock(struct starfive_wdt *wdt) +{ + struct device *dev = wdt->wdd.parent; + + wdt->apb_clk = devm_clk_get(dev, "apb"); + if (IS_ERR(wdt->apb_clk)) + return dev_err_probe(dev, PTR_ERR(wdt->apb_clk), "failed to get apb clock\n"); + + wdt->core_clk = devm_clk_get(dev, "core"); + if (IS_ERR(wdt->core_clk)) + return dev_err_probe(dev, PTR_ERR(wdt->core_clk), "failed to get core clock\n"); + + return 0; +} + +static inline int starfive_wdt_reset_init(struct device *dev) +{ + struct reset_control *rsts; + int ret; + + rsts = devm_reset_control_array_get_exclusive(dev); + if (IS_ERR(rsts)) + return dev_err_probe(dev, PTR_ERR(rsts), "failed to get resets\n"); + + ret = reset_control_deassert(rsts); + if (ret) + return dev_err_probe(dev, ret, "failed to deassert resets\n"); + + return 0; +} + +static u32 starfive_wdt_ticks_to_sec(struct starfive_wdt *wdt, u32 ticks) +{ + return DIV_ROUND_CLOSEST(ticks, wdt->freq); +} + +/* Write unlock-key to unlock. Write other value to lock. */ +static void starfive_wdt_unlock(struct starfive_wdt *wdt) +{ + spin_lock(&wdt->lock); + writel(wdt->variant->unlock_key, wdt->base + wdt->variant->unlock); +} + +static void starfive_wdt_lock(struct starfive_wdt *wdt) +{ + writel(~wdt->variant->unlock_key, wdt->base + wdt->variant->unlock); + spin_unlock(&wdt->lock); +} + +/* enable watchdog interrupt to reset/reboot */ +static void starfive_wdt_enable_reset(struct starfive_wdt *wdt) +{ + u32 val; + + val = readl(wdt->base + wdt->variant->control); + val |= STARFIVE_WDT_RESET_EN << wdt->variant->enrst_shift; + writel(val, wdt->base + wdt->variant->control); +} + +/* interrupt status whether has been raised from the counter */ +static bool starfive_wdt_raise_irq_status(struct starfive_wdt *wdt) +{ + return !!readl(wdt->base + wdt->variant->int_status); +} + +/* waiting interrupt can be free to clear */ +static int starfive_wdt_wait_int_free(struct starfive_wdt *wdt) +{ + u32 value; + + return readl_poll_timeout_atomic(wdt->base + wdt->variant->int_clr, value, + !(value & BIT(wdt->variant->intclr_ava_shift)), + STARFIVE_WDT_DELAY_US, STARFIVE_WDT_TIMEOUT_US); +} + +/* clear interrupt signal before initialization or reload */ +static int starfive_wdt_int_clr(struct starfive_wdt *wdt) +{ + int ret; + + if (wdt->variant->intclr_check) { + ret = starfive_wdt_wait_int_free(wdt); + if (ret) + return dev_err_probe(wdt->wdd.parent, ret, + "watchdog is not ready to clear interrupt.\n"); + } + writel(STARFIVE_WDT_INTCLR, wdt->base + wdt->variant->int_clr); + + return 0; +} + +static inline void starfive_wdt_set_count(struct starfive_wdt *wdt, u32 val) +{ + writel(val, wdt->base + wdt->variant->load); +} + +static inline u32 starfive_wdt_get_count(struct starfive_wdt *wdt) +{ + return readl(wdt->base + wdt->variant->value); +} + +/* enable watchdog */ +static inline void starfive_wdt_enable(struct starfive_wdt *wdt) +{ + u32 val; + + val = readl(wdt->base + wdt->variant->enable); + val |= STARFIVE_WDT_ENABLE << wdt->variant->en_shift; + writel(val, wdt->base + wdt->variant->enable); +} + +/* disable watchdog */ +static inline void starfive_wdt_disable(struct starfive_wdt *wdt) +{ + u32 val; + + val = readl(wdt->base + wdt->variant->enable); + val &= ~(STARFIVE_WDT_ENABLE << wdt->variant->en_shift); + writel(val, wdt->base + wdt->variant->enable); +} + +static inline void starfive_wdt_set_reload_count(struct starfive_wdt *wdt, u32 count) +{ + starfive_wdt_set_count(wdt, count); + + /* 7100 need set any value to reload register and could reload value to counter */ + if (wdt->variant->reload) + writel(0x1, wdt->base + wdt->variant->reload); +} + +static unsigned int starfive_wdt_max_timeout(struct starfive_wdt *wdt) +{ + if (wdt->variant->double_timeout) + return DIV_ROUND_UP(STARFIVE_WDT_MAXCNT, (wdt->freq / 2)) - 1; + + return DIV_ROUND_UP(STARFIVE_WDT_MAXCNT, wdt->freq) - 1; +} + +static unsigned int starfive_wdt_get_timeleft(struct watchdog_device *wdd) +{ + struct starfive_wdt *wdt = watchdog_get_drvdata(wdd); + u32 count; + + /* + * If the watchdog takes twice timeout and set half count value, + * timeleft value should add the count value before first timeout. + */ + count = starfive_wdt_get_count(wdt); + if (wdt->variant->double_timeout && !starfive_wdt_raise_irq_status(wdt)) + count += wdt->count; + + return starfive_wdt_ticks_to_sec(wdt, count); +} + +static int starfive_wdt_keepalive(struct watchdog_device *wdd) +{ + struct starfive_wdt *wdt = watchdog_get_drvdata(wdd); + int ret; + + starfive_wdt_unlock(wdt); + ret = starfive_wdt_int_clr(wdt); + if (ret) + goto exit; + + starfive_wdt_set_reload_count(wdt, wdt->count); + +exit: + /* exit with releasing spinlock and locking registers */ + starfive_wdt_lock(wdt); + return ret; +} + +static int starfive_wdt_start(struct starfive_wdt *wdt) +{ + int ret; + + starfive_wdt_unlock(wdt); + /* disable watchdog, to be safe */ + starfive_wdt_disable(wdt); + + starfive_wdt_enable_reset(wdt); + ret = starfive_wdt_int_clr(wdt); + if (ret) + goto exit; + + starfive_wdt_set_count(wdt, wdt->count); + starfive_wdt_enable(wdt); + +exit: + starfive_wdt_lock(wdt); + return ret; +} + +static void starfive_wdt_stop(struct starfive_wdt *wdt) +{ + starfive_wdt_unlock(wdt); + starfive_wdt_disable(wdt); + starfive_wdt_lock(wdt); +} + +static int starfive_wdt_pm_start(struct watchdog_device *wdd) +{ + struct starfive_wdt *wdt = watchdog_get_drvdata(wdd); + int ret = pm_runtime_get_sync(wdd->parent); + + if (ret < 0) + return ret; + + return starfive_wdt_start(wdt); +} + +static int starfive_wdt_pm_stop(struct watchdog_device *wdd) +{ + struct starfive_wdt *wdt = watchdog_get_drvdata(wdd); + + starfive_wdt_stop(wdt); + return pm_runtime_put_sync(wdd->parent); +} + +static int starfive_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int timeout) +{ + struct starfive_wdt *wdt = watchdog_get_drvdata(wdd); + unsigned long count = timeout * wdt->freq; + + /* some watchdogs take two timeouts to reset */ + if (wdt->variant->double_timeout) + count /= 2; + + wdt->count = count; + wdd->timeout = timeout; + + starfive_wdt_unlock(wdt); + starfive_wdt_disable(wdt); + starfive_wdt_set_reload_count(wdt, wdt->count); + starfive_wdt_enable(wdt); + starfive_wdt_lock(wdt); + + return 0; +} + +#define STARFIVE_WDT_OPTIONS (WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE) + +static const struct watchdog_info starfive_wdt_info = { + .options = STARFIVE_WDT_OPTIONS, + .identity = "StarFive Watchdog", +}; + +static const struct watchdog_ops starfive_wdt_ops = { + .owner = THIS_MODULE, + .start = starfive_wdt_pm_start, + .stop = starfive_wdt_pm_stop, + .ping = starfive_wdt_keepalive, + .set_timeout = starfive_wdt_set_timeout, + .get_timeleft = starfive_wdt_get_timeleft, +}; + +static int starfive_wdt_probe(struct platform_device *pdev) +{ + struct starfive_wdt *wdt; + int ret; + + wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL); + if (!wdt) + return -ENOMEM; + + wdt->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(wdt->base)) + return dev_err_probe(&pdev->dev, PTR_ERR(wdt->base), "error mapping registers\n"); + + wdt->wdd.parent = &pdev->dev; + ret = starfive_wdt_get_clock(wdt); + if (ret) + return ret; + + platform_set_drvdata(pdev, wdt); + pm_runtime_enable(&pdev->dev); + if (pm_runtime_enabled(&pdev->dev)) { + ret = pm_runtime_get_sync(&pdev->dev); + if (ret < 0) + return ret; + } else { + /* runtime PM is disabled but clocks need to be enabled */ + ret = starfive_wdt_enable_clock(wdt); + if (ret) + return ret; + } + + ret = starfive_wdt_reset_init(&pdev->dev); + if (ret) + goto err_exit; + + watchdog_set_drvdata(&wdt->wdd, wdt); + wdt->wdd.info = &starfive_wdt_info; + wdt->wdd.ops = &starfive_wdt_ops; + wdt->variant = of_device_get_match_data(&pdev->dev); + spin_lock_init(&wdt->lock); + + wdt->freq = clk_get_rate(wdt->core_clk); + if (!wdt->freq) { + dev_err(&pdev->dev, "get clock rate failed.\n"); + ret = -EINVAL; + goto err_exit; + } + + wdt->wdd.min_timeout = 1; + wdt->wdd.max_timeout = starfive_wdt_max_timeout(wdt); + wdt->wdd.timeout = STARFIVE_WDT_DEFAULT_TIME; + watchdog_init_timeout(&wdt->wdd, heartbeat, &pdev->dev); + starfive_wdt_set_timeout(&wdt->wdd, wdt->wdd.timeout); + + watchdog_set_nowayout(&wdt->wdd, nowayout); + watchdog_stop_on_reboot(&wdt->wdd); + watchdog_stop_on_unregister(&wdt->wdd); + + if (early_enable) { + ret = starfive_wdt_start(wdt); + if (ret) + goto err_exit; + set_bit(WDOG_HW_RUNNING, &wdt->wdd.status); + } else { + starfive_wdt_stop(wdt); + } + + ret = watchdog_register_device(&wdt->wdd); + if (ret) + goto err_exit; + + if (!early_enable) + return pm_runtime_put_sync(&pdev->dev); + + return 0; + +err_exit: + starfive_wdt_disable_clock(wdt); + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static int starfive_wdt_remove(struct platform_device *pdev) +{ + struct starfive_wdt *wdt = platform_get_drvdata(pdev); + + starfive_wdt_stop(wdt); + watchdog_unregister_device(&wdt->wdd); + + if (pm_runtime_enabled(&pdev->dev)) + pm_runtime_disable(&pdev->dev); + else + /* disable clock without PM */ + starfive_wdt_disable_clock(wdt); + + return 0; +} + +static void starfive_wdt_shutdown(struct platform_device *pdev) +{ + struct starfive_wdt *wdt = platform_get_drvdata(pdev); + + starfive_wdt_pm_stop(&wdt->wdd); +} + +#ifdef CONFIG_PM_SLEEP +static int starfive_wdt_suspend(struct device *dev) +{ + struct starfive_wdt *wdt = dev_get_drvdata(dev); + + /* Save watchdog state, and turn it off. */ + wdt->reload = starfive_wdt_get_count(wdt); + + /* Note that WTCNT doesn't need to be saved. */ + starfive_wdt_stop(wdt); + + return pm_runtime_force_suspend(dev); +} + +static int starfive_wdt_resume(struct device *dev) +{ + struct starfive_wdt *wdt = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + starfive_wdt_unlock(wdt); + /* Restore watchdog state. */ + starfive_wdt_set_reload_count(wdt, wdt->reload); + starfive_wdt_lock(wdt); + + return starfive_wdt_start(wdt); +} +#endif /* CONFIG_PM_SLEEP */ + +#ifdef CONFIG_PM +static int starfive_wdt_runtime_suspend(struct device *dev) +{ + struct starfive_wdt *wdt = dev_get_drvdata(dev); + + starfive_wdt_disable_clock(wdt); + + return 0; +} + +static int starfive_wdt_runtime_resume(struct device *dev) +{ + struct starfive_wdt *wdt = dev_get_drvdata(dev); + + return starfive_wdt_enable_clock(wdt); +} +#endif /* CONFIG_PM */ + +static const struct dev_pm_ops starfive_wdt_pm_ops = { + SET_RUNTIME_PM_OPS(starfive_wdt_runtime_suspend, starfive_wdt_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(starfive_wdt_suspend, starfive_wdt_resume) +}; + +static const struct of_device_id starfive_wdt_match[] = { + { .compatible = "starfive,jh7100-wdt", .data = &starfive_wdt_jh7100_variant }, + { .compatible = "starfive,jh7110-wdt", .data = &starfive_wdt_jh7110_variant }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, starfive_wdt_match); + +static struct platform_driver starfive_wdt_driver = { + .probe = starfive_wdt_probe, + .remove = starfive_wdt_remove, + .shutdown = starfive_wdt_shutdown, + .driver = { + .name = "starfive-wdt", + .pm = &starfive_wdt_pm_ops, + .of_match_table = of_match_ptr(starfive_wdt_match), + }, +}; +module_platform_driver(starfive_wdt_driver); + +MODULE_AUTHOR("Xingyu Wu "); +MODULE_AUTHOR("Samin Guo "); +MODULE_DESCRIPTION("StarFive Watchdog Device Driver"); +MODULE_LICENSE("GPL"); -- GitLab From edb10ace4dcd05f804d59dfdf2fee9121c92faee Mon Sep 17 00:00:00 2001 From: Yassine Oudjana Date: Thu, 2 Mar 2023 15:40:14 +0300 Subject: [PATCH 3873/5631] dt-bindings: reset: Add binding for MediaTek MT6735 TOPRGU/WDT Add a DT binding for the MT6735 top reset generation unit/watchdog timer. Signed-off-by: Yassine Oudjana Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230302124015.75546-2-y.oudjana@protonmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../bindings/watchdog/mediatek,mtk-wdt.yaml | 1 + include/dt-bindings/reset/mediatek,mt6735-wdt.h | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) create mode 100644 include/dt-bindings/reset/mediatek,mt6735-wdt.h diff --git a/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml b/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml index 66cacea8e47f..cc502838bc39 100644 --- a/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/mediatek,mtk-wdt.yaml @@ -22,6 +22,7 @@ properties: - enum: - mediatek,mt2712-wdt - mediatek,mt6589-wdt + - mediatek,mt6735-wdt - mediatek,mt6795-wdt - mediatek,mt7986-wdt - mediatek,mt8183-wdt diff --git a/include/dt-bindings/reset/mediatek,mt6735-wdt.h b/include/dt-bindings/reset/mediatek,mt6735-wdt.h new file mode 100644 index 000000000000..c6056e676d46 --- /dev/null +++ b/include/dt-bindings/reset/mediatek,mt6735-wdt.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ + +#ifndef _DT_BINDINGS_RESET_MEDIATEK_MT6735_WDT_H_ +#define _DT_BINDINGS_RESET_MEDIATEK_MT6735_WDT_H_ + +#define MT6735_TOPRGU_MM_RST 1 +#define MT6735_TOPRGU_MFG_RST 2 +#define MT6735_TOPRGU_VENC_RST 3 +#define MT6735_TOPRGU_VDEC_RST 4 +#define MT6735_TOPRGU_IMG_RST 5 +#define MT6735_TOPRGU_MD_RST 7 +#define MT6735_TOPRGU_CONN_RST 9 +#define MT6735_TOPRGU_C2K_SW_RST 14 +#define MT6735_TOPRGU_C2K_RST 15 +#define MT6735_TOPRGU_RST_NUM 9 + +#endif -- GitLab From 6c266971d5d700f283c73094caca9e1ebde2d67a Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:07 +0200 Subject: [PATCH 3874/5631] dt-bindings: watchdog: drop duplicated GPIO watchdog bindings Two conversions to DT schema of GPIO watchdog binding happened and came through different trees. Merge them into one: 1. Combine maintainers, 2. Use more descriptive property descriptions and constraints from gpio-wdt.yaml, 3. Switch to unevaluatedProperties:false, to allow generic watchdog properties. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Reviewed-by: Rob Herring Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20230415095112.51257-1-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../bindings/watchdog/gpio-wdt.yaml | 55 ------------------- .../bindings/watchdog/linux,wdt-gpio.yaml | 17 +++++- 2 files changed, 15 insertions(+), 57 deletions(-) delete mode 100644 Documentation/devicetree/bindings/watchdog/gpio-wdt.yaml diff --git a/Documentation/devicetree/bindings/watchdog/gpio-wdt.yaml b/Documentation/devicetree/bindings/watchdog/gpio-wdt.yaml deleted file mode 100644 index 155dc7965e9b..000000000000 --- a/Documentation/devicetree/bindings/watchdog/gpio-wdt.yaml +++ /dev/null @@ -1,55 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/watchdog/gpio-wdt.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: GPIO controlled watchdog - -maintainers: - - Robert Marko - -properties: - compatible: - const: linux,wdt-gpio - - gpios: - maxItems: 1 - description: GPIO connected to the WDT reset pin - - hw_algo: - $ref: /schemas/types.yaml#/definitions/string - description: Algorithm used by the driver - oneOf: - - description: - Either a high-to-low or a low-to-high transition clears the WDT counter. - The watchdog timer is disabled when GPIO is left floating or connected - to a three-state buffer. - const: toggle - - description: - Low or high level starts counting WDT timeout, the opposite level - disables the WDT. - Active level is determined by the GPIO flags. - const: level - - hw_margin_ms: - $ref: /schemas/types.yaml#/definitions/uint32 - description: Maximum time to reset watchdog circuit (in milliseconds) - minimum: 2 - maximum: 65535 - - always-running: - type: boolean - description: - If the watchdog timer cannot be disabled, add this flag to have the driver - keep toggling the signal without a client. - It will only cease to toggle the signal when the device is open and the - timeout elapsed. - -required: - - compatible - - gpios - - hw_algo - - hw_margin_ms - -unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/watchdog/linux,wdt-gpio.yaml b/Documentation/devicetree/bindings/watchdog/linux,wdt-gpio.yaml index 50af79af6416..499f1b7e03f9 100644 --- a/Documentation/devicetree/bindings/watchdog/linux,wdt-gpio.yaml +++ b/Documentation/devicetree/bindings/watchdog/linux,wdt-gpio.yaml @@ -8,6 +8,7 @@ title: GPIO-controlled Watchdog maintainers: - Guenter Roeck + - Robert Marko properties: compatible: @@ -19,11 +20,23 @@ properties: hw_algo: description: The algorithm used by the driver. - enum: [ level, toggle ] + oneOf: + - description: + Either a high-to-low or a low-to-high transition clears the WDT counter. + The watchdog timer is disabled when GPIO is left floating or connected + to a three-state buffer. + const: toggle + - description: + Low or high level starts counting WDT timeout, the opposite level + disables the WDT. + Active level is determined by the GPIO flags. + const: level hw_margin_ms: description: Maximum time to reset watchdog circuit (milliseconds). $ref: /schemas/types.yaml#/definitions/uint32 + minimum: 2 + maximum: 65535 always-running: type: boolean @@ -42,7 +55,7 @@ required: allOf: - $ref: watchdog.yaml# -additionalProperties: false +unevaluatedProperties: false examples: - | -- GitLab From f0d6e92ebb06ca9a360683e69932d09bfc70f551 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:09 +0200 Subject: [PATCH 3875/5631] dt-bindings: watchdog: arm,sp805: drop unneeded minItems There is no need to specify minItems when they are equal to maxItems, because it is implied by maxItems. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230415095112.51257-3-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/arm,sp805.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/watchdog/arm,sp805.yaml b/Documentation/devicetree/bindings/watchdog/arm,sp805.yaml index a69cac8ec208..7aea255b301b 100644 --- a/Documentation/devicetree/bindings/watchdog/arm,sp805.yaml +++ b/Documentation/devicetree/bindings/watchdog/arm,sp805.yaml @@ -43,7 +43,6 @@ properties: Clocks driving the watchdog timer hardware. The first clock is used for the actual watchdog counter. The second clock drives the register interface. - minItems: 2 maxItems: 2 clock-names: -- GitLab From d5e8f87e365ff944631889ac978a7000a6181b3d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:10 +0200 Subject: [PATCH 3876/5631] dt-bindings: watchdog: fsl-imx7ulp-wdt: simplify with unevaluatedProperties Allow generic watchdog properties by using unevaluatedProperties: false. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230415095112.51257-4-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml index 8562978aa0c8..f42cc0904d43 100644 --- a/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/fsl-imx7ulp-wdt.yaml @@ -30,15 +30,13 @@ properties: clocks: maxItems: 1 - timeout-sec: true - required: - compatible - interrupts - reg - clocks -additionalProperties: false +unevaluatedProperties: false examples: - | -- GitLab From 20f43c943d06f628f832658238581fdeb29f7f92 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:11 +0200 Subject: [PATCH 3877/5631] dt-bindings: watchdog: toshiba,visconti-wdt: simplify with unevaluatedProperties Allow generic watchdog properties by using unevaluatedProperties: false. Signed-off-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Acked-by: Nobuhiro Iwamatsu Reviewed-by: Rob Herring Link: https://lore.kernel.org/r/20230415095112.51257-5-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml b/Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml index eba083822d1f..51d03d5b08ad 100644 --- a/Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml @@ -24,14 +24,12 @@ properties: clocks: maxItems: 1 - timeout-sec: true - required: - compatible - reg - clocks -additionalProperties: false +unevaluatedProperties: false examples: - | -- GitLab From 495cbe36ee795dc06abccfb251e4384c6a26dc48 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 15 Apr 2023 11:51:12 +0200 Subject: [PATCH 3878/5631] dt-bindings: watchdog: realtek,otto-wdt: simplify requiring interrupt-names Required properties should be listed in "required:" block. Since interrupts are already there, the dependency of interrupt-names on the interrupts can be simplified. Signed-off-by: Krzysztof Kozlowski Acked-by: Sander Vanheule Reviewed-by: Rob Herring Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230415095112.51257-6-krzysztof.kozlowski@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../devicetree/bindings/watchdog/realtek,otto-wdt.yaml | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml b/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml index 099245fe7b10..1f5390a67cdb 100644 --- a/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/realtek,otto-wdt.yaml @@ -67,12 +67,10 @@ required: - reg - clocks - interrupts + - interrupt-names unevaluatedProperties: false -dependencies: - interrupts: [ interrupt-names ] - examples: - | watchdog: watchdog@3150 { -- GitLab From d0ee0e8aa97e6e1d443eaab8c94d580d0a6f5a89 Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Tue, 14 Mar 2023 10:43:51 +0530 Subject: [PATCH 3879/5631] dt-bindings: watchdog: Document Qualcomm SM6115 watchdog Add devicetree binding for watchdog present on Qualcomm SM6115 SoC. Acked-by: Krzysztof Kozlowski Signed-off-by: Bhupesh Sharma Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230314051351.1754321-1-bhupesh.sharma@linaro.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml index 3c8fa2f3b0ba..6d0fe6abd06a 100644 --- a/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml +++ b/Documentation/devicetree/bindings/watchdog/qcom-wdt.yaml @@ -31,6 +31,7 @@ properties: - qcom,apss-wdt-sdm845 - qcom,apss-wdt-sdx55 - qcom,apss-wdt-sdx65 + - qcom,apss-wdt-sm6115 - qcom,apss-wdt-sm6350 - qcom,apss-wdt-sm8150 - qcom,apss-wdt-sm8250 -- GitLab From 2a31bf20808aa3642a942ab9ce421ebb7585eb3a Mon Sep 17 00:00:00 2001 From: Keguang Zhang Date: Thu, 30 Mar 2023 19:20:51 +0800 Subject: [PATCH 3880/5631] watchdog: loongson1_wdt: Implement restart handler Implement restart handler for the Loongson-1 watchdog driver and define the watchdog registers instead of including the legacy header. Signed-off-by: Keguang Zhang Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230330112051.551648-3-keguang.zhang@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/loongson1_wdt.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/drivers/watchdog/loongson1_wdt.c b/drivers/watchdog/loongson1_wdt.c index c55656cfb403..3c651c50a98c 100644 --- a/drivers/watchdog/loongson1_wdt.c +++ b/drivers/watchdog/loongson1_wdt.c @@ -7,7 +7,11 @@ #include #include #include -#include + +/* Loongson 1 Watchdog Register Definitions */ +#define WDT_EN 0x0 +#define WDT_TIMER 0x4 +#define WDT_SET 0x8 #define DEFAULT_HEARTBEAT 30 @@ -66,6 +70,18 @@ static int ls1x_wdt_stop(struct watchdog_device *wdt_dev) return 0; } +static int ls1x_wdt_restart(struct watchdog_device *wdt_dev, + unsigned long action, void *data) +{ + struct ls1x_wdt_drvdata *drvdata = watchdog_get_drvdata(wdt_dev); + + writel(0x1, drvdata->base + WDT_EN); + writel(0x1, drvdata->base + WDT_TIMER); + writel(0x1, drvdata->base + WDT_SET); + + return 0; +} + static const struct watchdog_info ls1x_wdt_info = { .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE, .identity = "Loongson1 Watchdog", @@ -77,6 +93,7 @@ static const struct watchdog_ops ls1x_wdt_ops = { .stop = ls1x_wdt_stop, .ping = ls1x_wdt_ping, .set_timeout = ls1x_wdt_set_timeout, + .restart = ls1x_wdt_restart, }; static int ls1x_wdt_probe(struct platform_device *pdev) -- GitLab From a23c83a0ae0280632e734aff1dbf299f602a79c4 Mon Sep 17 00:00:00 2001 From: Om Parikh Date: Tue, 18 Apr 2023 05:16:10 +0000 Subject: [PATCH 3881/5631] dt-bindings: watchdog: alphascale-asm9260: convert to DT schema Makes alphascale-asm9260 dt bindings adhere to the dt json-schema by replacing txt file with yaml file. Signed-off-by: Om Parikh Reviewed-by: Krzysztof Kozlowski Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230418051446.24288-1-hack3r-0m@proton.me Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- .../watchdog/alphascale,asm9260-wdt.yaml | 70 +++++++++++++++++++ .../bindings/watchdog/alphascale-asm9260.txt | 35 ---------- 2 files changed, 70 insertions(+), 35 deletions(-) create mode 100644 Documentation/devicetree/bindings/watchdog/alphascale,asm9260-wdt.yaml delete mode 100644 Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt diff --git a/Documentation/devicetree/bindings/watchdog/alphascale,asm9260-wdt.yaml b/Documentation/devicetree/bindings/watchdog/alphascale,asm9260-wdt.yaml new file mode 100644 index 000000000000..fea84f5b7e6d --- /dev/null +++ b/Documentation/devicetree/bindings/watchdog/alphascale,asm9260-wdt.yaml @@ -0,0 +1,70 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/watchdog/alphascale,asm9260-wdt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Alphascale asm9260 Watchdog timer + +allOf: + - $ref: watchdog.yaml# + +maintainers: + - Oleksij Rempel + +properties: + compatible: + const: alphascale,asm9260-wdt + + reg: + maxItems: 1 + + clocks: + items: + - description: source clock, used for tick counter + - description: ahb gate + + clock-names: + items: + - const: mod + - const: ahb + + interrupts: + maxItems: 1 + + resets: + maxItems: 1 + + reset-names: + items: + - const: wdt_rst + + alphascale,mode: + description: | + Specifies the reset mode of operation. If set to sw, then reset is handled + via interrupt request, if set to debug, then it does nothing and logs. + $ref: /schemas/types.yaml#/definitions/string + enum: [hw, sw, debug] + default: hw + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + +unevaluatedProperties: false + +examples: + - | + #include + watchdog0: watchdog@80048000 { + compatible = "alphascale,asm9260-wdt"; + reg = <0x80048000 0x10>; + clocks = <&acc CLKID_SYS_WDT>, <&acc CLKID_AHB_WDT>; + clock-names = "mod", "ahb"; + interrupts = <55>; + timeout-sec = <30>; + alphascale,mode = "hw"; + }; diff --git a/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt b/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt deleted file mode 100644 index 75b265a04047..000000000000 --- a/Documentation/devicetree/bindings/watchdog/alphascale-asm9260.txt +++ /dev/null @@ -1,35 +0,0 @@ -Alphascale asm9260 Watchdog timer - -Required properties: - -- compatible : should be "alphascale,asm9260-wdt". -- reg : Specifies base physical address and size of the registers. -- clocks : the clocks feeding the watchdog timer. See clock-bindings.txt -- clock-names : should be set to - "mod" - source for tick counter. - "ahb" - ahb gate. -- resets : phandle pointing to the system reset controller with - line index for the watchdog. -- reset-names : should be set to "wdt_rst". - -Optional properties: -- timeout-sec : shall contain the default watchdog timeout in seconds, - if unset, the default timeout is 30 seconds. -- alphascale,mode : three modes are supported - "hw" - hw reset (default). - "sw" - sw reset. - "debug" - no action is taken. - -Example: - -watchdog0: watchdog@80048000 { - compatible = "alphascale,asm9260-wdt"; - reg = <0x80048000 0x10>; - clocks = <&acc CLKID_SYS_WDT>, <&acc CLKID_AHB_WDT>; - clock-names = "mod", "ahb"; - interrupts = <55>; - resets = <&rst WDT_RESET>; - reset-names = "wdt_rst"; - timeout-sec = <30>; - alphascale,mode = "hw"; -}; -- GitLab From 87b22656ca6a896d0378e9e60ffccb0c82f48b08 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 18 Apr 2023 19:25:30 +0200 Subject: [PATCH 3882/5631] watchdog: menz069_wdt: fix watchdog initialisation Doing a 'cat /dev/watchdog0' with menz069_wdt as watchdog0 will result in a NULL pointer dereference. This happens because we're passing the wrong pointer to watchdog_register_device(). Fix this by getting rid of the static watchdog_device structure and use the one embedded into the driver's per-instance private data. Signed-off-by: Johannes Thumshirn Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230418172531.177349-2-jth@kernel.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/menz69_wdt.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/drivers/watchdog/menz69_wdt.c b/drivers/watchdog/menz69_wdt.c index 8973f98bc6a5..bca0938f3429 100644 --- a/drivers/watchdog/menz69_wdt.c +++ b/drivers/watchdog/menz69_wdt.c @@ -98,14 +98,6 @@ static const struct watchdog_ops men_z069_ops = { .set_timeout = men_z069_wdt_set_timeout, }; -static struct watchdog_device men_z069_wdt = { - .info = &men_z069_info, - .ops = &men_z069_ops, - .timeout = MEN_Z069_DEFAULT_TIMEOUT, - .min_timeout = 1, - .max_timeout = MEN_Z069_WDT_COUNTER_MAX / MEN_Z069_TIMER_FREQ, -}; - static int men_z069_probe(struct mcb_device *dev, const struct mcb_device_id *id) { @@ -125,15 +117,19 @@ static int men_z069_probe(struct mcb_device *dev, goto release_mem; drv->mem = mem; + drv->wdt.info = &men_z069_info; + drv->wdt.ops = &men_z069_ops; + drv->wdt.timeout = MEN_Z069_DEFAULT_TIMEOUT; + drv->wdt.min_timeout = 1; + drv->wdt.max_timeout = MEN_Z069_WDT_COUNTER_MAX / MEN_Z069_TIMER_FREQ; - drv->wdt = men_z069_wdt; watchdog_init_timeout(&drv->wdt, 0, &dev->dev); watchdog_set_nowayout(&drv->wdt, nowayout); watchdog_set_drvdata(&drv->wdt, drv); drv->wdt.parent = &dev->dev; mcb_set_drvdata(dev, drv); - return watchdog_register_device(&men_z069_wdt); + return watchdog_register_device(&drv->wdt); release_mem: mcb_release_mem(mem); -- GitLab From bd858e494ceb3aac25bab9c6639f4cd764f534ba Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Tue, 18 Apr 2023 19:25:31 +0200 Subject: [PATCH 3883/5631] watchdog: menz069_wdt: fix timeout setting When setting the timeout for the menz069_wdt watchdog driver, we erroneously read from the 'watchdog value register' (WVR) instead of the 'watchdog timer register' (WTR) and then write the value back into WTR. This can potentially lead to wrong timeouts and wrong enable bit settings. Signed-off-by: Johannes Thumshirn Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230418172531.177349-3-jth@kernel.org Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/menz69_wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/menz69_wdt.c b/drivers/watchdog/menz69_wdt.c index bca0938f3429..3c98030b9fcd 100644 --- a/drivers/watchdog/menz69_wdt.c +++ b/drivers/watchdog/menz69_wdt.c @@ -77,7 +77,7 @@ static int men_z069_wdt_set_timeout(struct watchdog_device *wdt, wdt->timeout = timeout; val = timeout * MEN_Z069_TIMER_FREQ; - reg = readw(drv->base + MEN_Z069_WVR); + reg = readw(drv->base + MEN_Z069_WTR); ena = reg & MEN_Z069_WTR_WDEN; reg = ena | val; writew(reg, drv->base + MEN_Z069_WTR); -- GitLab From 66efce1d099a67d9d0bf635a9815ec478bfbc8a2 Mon Sep 17 00:00:00 2001 From: Srinivas Neeli Date: Thu, 20 Apr 2023 16:12:28 +0530 Subject: [PATCH 3884/5631] MAINTAINERS: Add fragment for Xilinx watchdog driver Added entry for Xilinx xps-timebase watchdog driver. Signed-off-by: Srinivas Neeli Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230420104231.2243079-2-srinivas.neeli@amd.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 6d1fdacf304e..7daa9e4ba146 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22969,6 +22969,14 @@ F: Documentation/devicetree/bindings/media/xilinx/ F: drivers/media/platform/xilinx/ F: include/uapi/linux/xilinx-v4l2-controls.h +XILINX WATCHDOG DRIVER +M: Srinivas Neeli +R: Shubhrajyoti Datta +R: Michal Simek +S: Maintained +F: Documentation/devicetree/bindings/watchdog/xlnx,xps-timebase-wdt.yaml +F: drivers/watchdog/of_xilinx_wdt.c + XILINX XDMA DRIVER M: Lizhi Hou M: Brian Xu -- GitLab From 267214a2319b5692bbc9b128a6514960291dcca8 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 21 Apr 2023 19:51:47 -0700 Subject: [PATCH 3885/5631] cxl/port: Fix port to pci device assumptions in read_cdat_data() Not all endpoint CXL ports are associated with PCI devices. The cxl_test infrastructure models 'struct cxl_port' instances hosted by platform devices. Teach read_cdat_data() to be careful about non-pci hosted cxl_memdev instances. Otherwise, cxl_test crashes with this signature: RIP: 0010:xas_start+0x6d/0x290 [..] Call Trace: xas_load+0xa/0x50 xas_find+0x25b/0x2f0 xa_find+0x118/0x1d0 pci_find_doe_mailbox+0x51/0xc0 read_cdat_data+0x45/0x190 [cxl_core] cxl_port_probe+0x10a/0x1e0 [cxl_port] cxl_bus_probe+0x17/0x50 [cxl_core] Some other cleanups are included like removing the single-use @uport variable, and removing the indirection through 'struct cxl_dev_state' to lookup the device that registered the memdev and may be a pci device. Fixes: af0a6c3587dc ("cxl/pci: Use CDAT DOE mailbox created by PCI core") Reviewed-by: Lukas Wunner Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/168213190748.708404.16215095414060364800.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 25b7e8125d5d..bdbd907884ce 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -536,17 +536,18 @@ static int cxl_cdat_read_table(struct device *dev, */ void read_cdat_data(struct cxl_port *port) { - struct pci_doe_mb *cdat_doe; + struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport); + struct device *host = cxlmd->dev.parent; struct device *dev = &port->dev; - struct device *uport = port->uport; - struct cxl_memdev *cxlmd = to_cxl_memdev(uport); - struct cxl_dev_state *cxlds = cxlmd->cxlds; - struct pci_dev *pdev = to_pci_dev(cxlds->dev); + struct pci_doe_mb *cdat_doe; size_t cdat_length; void *cdat_table; int rc; - cdat_doe = pci_find_doe_mailbox(pdev, PCI_DVSEC_VENDOR_ID_CXL, + if (!dev_is_pci(host)) + return; + cdat_doe = pci_find_doe_mailbox(to_pci_dev(host), + PCI_DVSEC_VENDOR_ID_CXL, CXL_DOE_PROTOCOL_TABLE_ACCESS); if (!cdat_doe) { dev_dbg(dev, "No CDAT mailbox\n"); -- GitLab From 95b5baf81001a80a8dd8b35306694db163bcb423 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 21 Apr 2023 09:11:26 -0700 Subject: [PATCH 3886/5631] MIPS: Mark check_bugs() as __init After commit ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING forcibly"), a compiler may choose not to inline a function marked with just 'inline'. If check_bugs() is not inlined into start_kernel(), which occurs when building with clang after commit 9ea7e6b62c2b ("init: Mark [arch_call_]rest_init() __noreturn"), modpost complains with: WARNING: modpost: vmlinux.o: section mismatch in reference: check_bugs (section: .text) -> check_bugs32 (section: .init.text) check_bugs() is only called from start_kernel(), which itself is marked __init, so there would not be any issues at run time. Make it obvious to modpost that this call chain is safe by marking check_bugs() as __init, which fixes the warning. Reported-by: Naresh Kamboju Link: https://lore.kernel.org/CA+G9fYt+4e57Gdy6cix=LeNK6XqWoui8du=mZWu=cf8vPYocKw@mail.gmail.com/ Signed-off-by: Nathan Chancellor Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/bugs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index d72dc6e1cf3c..047e14227c45 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -30,7 +30,7 @@ static inline void check_bugs_early(void) check_bugs64_early(); } -static inline void check_bugs(void) +static inline void __init check_bugs(void) { unsigned int cpu = smp_processor_id(); -- GitLab From f4670a1b30f886e843258ca4a69c442811a90302 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Fri, 21 Apr 2023 09:11:27 -0700 Subject: [PATCH 3887/5631] MIPS: Sink body of check_bugs_early() into its only call site If check_bugs_early() is not inlined, which a compiler is free to do after commit ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING forcibly"), modpost would warn that check_bugs_early(), a non-init function, refers to check_bugs64_early(), which is marked __init. This would not result in any run time issues, as check_bugs_early() is only called from setup_arch(), which is marked __init. To avoid this potential warning, just sink the body of check_bugs_early() into its single call site in setup_arch(). Signed-off-by: Nathan Chancellor Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/bugs.h | 6 ------ arch/mips/kernel/setup.c | 3 ++- 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h index 047e14227c45..653f78f3a685 100644 --- a/arch/mips/include/asm/bugs.h +++ b/arch/mips/include/asm/bugs.h @@ -24,12 +24,6 @@ extern void check_bugs64_early(void); extern void check_bugs32(void); extern void check_bugs64(void); -static inline void check_bugs_early(void) -{ - if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) - check_bugs64_early(); -} - static inline void __init check_bugs(void) { unsigned int cpu = smp_processor_id(); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index f1c88f8a1dc5..febdc5564638 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -786,7 +786,8 @@ void __init setup_arch(char **cmdline_p) setup_early_printk(); #endif cpu_report(); - check_bugs_early(); + if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) + check_bugs64_early(); #if defined(CONFIG_VT) #if defined(CONFIG_VGA_CONSOLE) -- GitLab From 3db166d6cf0ea73dd2c887036aad2e95e0884d9b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 18 Apr 2023 10:39:01 -0700 Subject: [PATCH 3888/5631] cxl/mbox: Deprecate poison commands The CXL subsystem is adding formal mechanisms for managing device poison. Minimize the maintenance burden going forward, and maximize the investment in common tooling by deprecating direct user access to poison commands outside of CXL_MEM_RAW_COMMANDS debug scenarios. A new cxl_deprecated_commands[] list is created for querying which command ids defined in previous kernels are now deprecated. CXL Media and Poison Management commands, opcodes 0x43XX, defined in CXL 3.0 Spec, Table 8-93 are deprecated with one exception: Get Scan Media Capabilities. Keep Get Scan Media Capabilities as it simply provides information and has no impact on the device state. Effectively all of the commands defined in: commit 87815ee9d006 ("cxl/pci: Add media provisioning required commands") ...were defined prematurely and should have waited until the kernel implementation was decided. To my knowledge there are no shipping devices with poison support and no known tools that would regress with this change. Co-developed-by: Alison Schofield Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/652197e9bc8885e6448d989405b9e50ee9d6b0a6.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 5 ----- include/uapi/linux/cxl_mem.h | 35 ++++++++++++++++++++++++++++++----- 2 files changed, 30 insertions(+), 10 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index f2addb457172..938cff2c948e 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -61,12 +61,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(SET_ALERT_CONFIG, 0xc, 0, 0), CXL_CMD(GET_SHUTDOWN_STATE, 0, 0x1, 0), CXL_CMD(SET_SHUTDOWN_STATE, 0x1, 0, 0), - CXL_CMD(GET_POISON, 0x10, CXL_VARIABLE_PAYLOAD, 0), - CXL_CMD(INJECT_POISON, 0x8, 0, 0), - CXL_CMD(CLEAR_POISON, 0x48, 0, 0), CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), - CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), - CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), }; /* diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 86bbacf2a315..14bc6e742148 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -40,19 +40,22 @@ ___C(SET_ALERT_CONFIG, "Set Alert Configuration"), \ ___C(GET_SHUTDOWN_STATE, "Get Shutdown State"), \ ___C(SET_SHUTDOWN_STATE, "Set Shutdown State"), \ - ___C(GET_POISON, "Get Poison List"), \ - ___C(INJECT_POISON, "Inject Poison"), \ - ___C(CLEAR_POISON, "Clear Poison"), \ + ___DEPRECATED(GET_POISON, "Get Poison List"), \ + ___DEPRECATED(INJECT_POISON, "Inject Poison"), \ + ___DEPRECATED(CLEAR_POISON, "Clear Poison"), \ ___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"), \ - ___C(SCAN_MEDIA, "Scan Media"), \ - ___C(GET_SCAN_MEDIA, "Get Scan Media Results"), \ + ___DEPRECATED(SCAN_MEDIA, "Scan Media"), \ + ___DEPRECATED(GET_SCAN_MEDIA, "Get Scan Media Results"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a +#define ___DEPRECATED(a, b) CXL_MEM_DEPRECATED_ID_##a enum { CXL_CMDS }; #undef ___C +#undef ___DEPRECATED #define ___C(a, b) { b } +#define ___DEPRECATED(a, b) { "Deprecated " b } static const struct { const char *name; } cxl_command_names[] __attribute__((__unused__)) = { CXL_CMDS }; @@ -68,6 +71,28 @@ static const struct { */ #undef ___C +#undef ___DEPRECATED +#define ___C(a, b) (0) +#define ___DEPRECATED(a, b) (1) + +static const __u8 cxl_deprecated_commands[] + __attribute__((__unused__)) = { CXL_CMDS }; + +/* + * Here's how this actually breaks out: + * cxl_deprecated_commands[] = { + * [CXL_MEM_COMMAND_ID_INVALID] = 0, + * [CXL_MEM_COMMAND_ID_IDENTIFY] = 0, + * ... + * [CXL_MEM_DEPRECATED_ID_GET_POISON] = 1, + * [CXL_MEM_DEPRECATED_ID_INJECT_POISON] = 1, + * [CXL_MEM_DEPRECATED_ID_CLEAR_POISON] = 1, + * ... + * }; + */ + +#undef ___C +#undef ___DEPRECATED /** * struct cxl_command_info - Command information returned from a query. -- GitLab From 31f735c65d4f4825c57620f39f2fa27aa01ac172 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 17 Apr 2023 23:25:47 +0900 Subject: [PATCH 3889/5631] kbuild: add srcdeb-pkg target This new target builds only the debian source package. Unify the build rules of deb-pkg, srcdeb-pkg, bindeb-pkg to avoid code duplication. --no-check-builddeps is added to srcdeb-pkg so that build dependencies will not be checked. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/Makefile.package | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/scripts/Makefile.package b/scripts/Makefile.package index 4d90691505b1..d8a36304b26e 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -5,7 +5,6 @@ include $(srctree)/scripts/Kbuild.include include $(srctree)/scripts/Makefile.lib KERNELPATH := kernel-$(subst -,_,$(KERNELRELEASE)) -KBUILD_PKG_ROOTCMD ?="fakeroot -u" # Include only those top-level files that are needed by make, plus the GPL copy TAR_CONTENT := Documentation LICENSES arch block certs crypto drivers fs \ include init io_uring ipc kernel lib mm net rust \ @@ -86,6 +85,9 @@ binrpm-pkg: +rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \ $(UTS_MACHINE)-linux -bb $(objtree)/binkernel.spec +# deb-pkg srcdeb-pkg bindeb-pkg +# --------------------------------------------------------------------------- + quiet_cmd_debianize = GEN $@ cmd_debianize = $(srctree)/scripts/package/mkdebian $(mkdebian-opts) @@ -104,14 +106,25 @@ debian-orig: linux.tar.gz debian cp $< ../$(orig-name); \ fi -PHONY += deb-pkg -deb-pkg: debian-orig - +dpkg-buildpackage -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch) $(DPKG_FLAGS) \ - --build=source,binary -nc -us -uc +KBUILD_PKG_ROOTCMD ?= 'fakeroot -u' + +PHONY += deb-pkg srcdeb-pkg bindeb-pkg + +deb-pkg: private build-type := source,binary +srcdeb-pkg: private build-type := source +bindeb-pkg: private build-type := binary -PHONY += bindeb-pkg +deb-pkg srcdeb-pkg: debian-orig bindeb-pkg: debian - +dpkg-buildpackage -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch) $(DPKG_FLAGS) -b -nc -uc +deb-pkg srcdeb-pkg bindeb-pkg: + +$(strip dpkg-buildpackage \ + --build=$(build-type) --no-pre-clean --unsigned-changes \ + $(if $(findstring source, $(build-type)), \ + --unsigned-source) \ + $(if $(findstring binary, $(build-type)), \ + -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \ + --no-check-builddeps) \ + $(DPKG_FLAGS)) PHONY += intdeb-pkg intdeb-pkg: @@ -208,6 +221,7 @@ help: @echo ' srcrpm-pkg - Build only the source kernel RPM package' @echo ' binrpm-pkg - Build only the binary kernel RPM package' @echo ' deb-pkg - Build both source and binary deb kernel packages' + @echo ' srcdeb-pkg - Build only the source kernel deb package' @echo ' bindeb-pkg - Build only the binary kernel deb package' @echo ' snap-pkg - Build only the binary kernel snap package' @echo ' (will connect to external hosts)' -- GitLab From dec441d32a9a1e4a891ccda3356cac61cc1ffe79 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:02 -0700 Subject: [PATCH 3890/5631] cxl/mbox: Restrict poison cmds to debugfs cxl_raw_allow_all The Get, Inject, and Clear poison commands are not available for direct user access because they require kernel driver controls to perform safely. Further restrict access to these commands by requiring the selection of the debugfs attribute 'cxl_raw_allow_all' to enable in raw mode. Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/0e5cb41ffae2bab800957d3b9003eedfd0a2dfd5.1681838291.git.alison.schofield@intel.com Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 938cff2c948e..fd1026970d3a 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -82,6 +82,9 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { * * CXL_MBOX_OP_[GET_]SCAN_MEDIA: The kernel provides a native error list that * is kept up to date with patrol notifications and error management. + * + * CXL_MBOX_OP_[GET_,INJECT_,CLEAR_]POISON: These commands require kernel + * driver orchestration for safety. */ static u16 cxl_disabled_raw_commands[] = { CXL_MBOX_OP_ACTIVATE_FW, @@ -90,6 +93,9 @@ static u16 cxl_disabled_raw_commands[] = { CXL_MBOX_OP_SET_SHUTDOWN_STATE, CXL_MBOX_OP_SCAN_MEDIA, CXL_MBOX_OP_GET_SCAN_MEDIA, + CXL_MBOX_OP_GET_POISON, + CXL_MBOX_OP_INJECT_POISON, + CXL_MBOX_OP_CLEAR_POISON, }; /* -- GitLab From d0abf5787adc0341a04667d3b4a23b4d0999af30 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:03 -0700 Subject: [PATCH 3891/5631] cxl/mbox: Initialize the poison state Driver reads of the poison list are synchronized to ensure that a reader does not get an incomplete list because their request overlapped (was interrupted or preceded by) another read request of the same DPA range. (CXL Spec 3.0 Section 8.2.9.8.4.1). The driver maintains state information to achieve this goal. To initialize the state, first recognize the poison commands in the CEL (Command Effects Log). If the device supports Get Poison List, allocate a single buffer for the poison list and protect it with a lock. Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/9078d180769be28a5087288b38cdfc827cae58bf.1681838291.git.alison.schofield@intel.com Reviewed-by: Jonathan Cameron Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 81 ++++++++++++++++++++++++++++++++++++++++- drivers/cxl/cxlmem.h | 34 +++++++++++++++++ drivers/cxl/pci.c | 4 ++ 3 files changed, 117 insertions(+), 2 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index fd1026970d3a..17737386283a 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -120,6 +121,43 @@ static bool cxl_is_security_command(u16 opcode) return false; } +static bool cxl_is_poison_command(u16 opcode) +{ +#define CXL_MBOX_OP_POISON_CMDS 0x43 + + if ((opcode >> 8) == CXL_MBOX_OP_POISON_CMDS) + return true; + + return false; +} + +static void cxl_set_poison_cmd_enabled(struct cxl_poison_state *poison, + u16 opcode) +{ + switch (opcode) { + case CXL_MBOX_OP_GET_POISON: + set_bit(CXL_POISON_ENABLED_LIST, poison->enabled_cmds); + break; + case CXL_MBOX_OP_INJECT_POISON: + set_bit(CXL_POISON_ENABLED_INJECT, poison->enabled_cmds); + break; + case CXL_MBOX_OP_CLEAR_POISON: + set_bit(CXL_POISON_ENABLED_CLEAR, poison->enabled_cmds); + break; + case CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS: + set_bit(CXL_POISON_ENABLED_SCAN_CAPS, poison->enabled_cmds); + break; + case CXL_MBOX_OP_SCAN_MEDIA: + set_bit(CXL_POISON_ENABLED_SCAN_MEDIA, poison->enabled_cmds); + break; + case CXL_MBOX_OP_GET_SCAN_MEDIA: + set_bit(CXL_POISON_ENABLED_SCAN_RESULTS, poison->enabled_cmds); + break; + default: + break; + } +} + static struct cxl_mem_command *cxl_mem_find_command(u16 opcode) { struct cxl_mem_command *c; @@ -635,13 +673,18 @@ static void cxl_walk_cel(struct cxl_dev_state *cxlds, size_t size, u8 *cel) u16 opcode = le16_to_cpu(cel_entry[i].opcode); struct cxl_mem_command *cmd = cxl_mem_find_command(opcode); - if (!cmd) { + if (!cmd && !cxl_is_poison_command(opcode)) { dev_dbg(cxlds->dev, "Opcode 0x%04x unsupported by driver\n", opcode); continue; } - set_bit(cmd->info.id, cxlds->enabled_cmds); + if (cmd) + set_bit(cmd->info.id, cxlds->enabled_cmds); + + if (cxl_is_poison_command(opcode)) + cxl_set_poison_cmd_enabled(&cxlds->poison, opcode); + dev_dbg(cxlds->dev, "Opcode 0x%04x enabled\n", opcode); } } @@ -1108,6 +1151,40 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL); +static void free_poison_buf(void *buf) +{ + kvfree(buf); +} + +/* Get Poison List output buffer is protected by cxlds->poison.lock */ +static int cxl_poison_alloc_buf(struct cxl_dev_state *cxlds) +{ + cxlds->poison.list_out = kvmalloc(cxlds->payload_size, GFP_KERNEL); + if (!cxlds->poison.list_out) + return -ENOMEM; + + return devm_add_action_or_reset(cxlds->dev, free_poison_buf, + cxlds->poison.list_out); +} + +int cxl_poison_state_init(struct cxl_dev_state *cxlds) +{ + int rc; + + if (!test_bit(CXL_POISON_ENABLED_LIST, cxlds->poison.enabled_cmds)) + return 0; + + rc = cxl_poison_alloc_buf(cxlds); + if (rc) { + clear_bit(CXL_POISON_ENABLED_LIST, cxlds->poison.enabled_cmds); + return rc; + } + + mutex_init(&cxlds->poison.lock); + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_poison_state_init, CXL); + struct cxl_dev_state *cxl_dev_state_create(struct device *dev) { struct cxl_dev_state *cxlds; diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 090acebba4fa..40de21fac128 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -215,6 +215,37 @@ struct cxl_event_state { struct mutex log_lock; }; +/* Device enabled poison commands */ +enum poison_cmd_enabled_bits { + CXL_POISON_ENABLED_LIST, + CXL_POISON_ENABLED_INJECT, + CXL_POISON_ENABLED_CLEAR, + CXL_POISON_ENABLED_SCAN_CAPS, + CXL_POISON_ENABLED_SCAN_MEDIA, + CXL_POISON_ENABLED_SCAN_RESULTS, + CXL_POISON_ENABLED_MAX +}; + +/** + * struct cxl_poison_state - Driver poison state info + * + * @max_errors: Maximum media error records held in device cache + * @enabled_cmds: All poison commands enabled in the CEL + * @list_out: The poison list payload returned by device + * @lock: Protect reads of the poison list + * + * Reads of the poison list are synchronized to ensure that a reader + * does not get an incomplete list because their request overlapped + * (was interrupted or preceded by) another read request of the same + * DPA range. CXL Spec 3.0 Section 8.2.9.8.4.1 + */ +struct cxl_poison_state { + u32 max_errors; + DECLARE_BITMAP(enabled_cmds, CXL_POISON_ENABLED_MAX); + struct cxl_mbox_poison_out *list_out; + struct mutex lock; /* Protect reads of poison list */ +}; + /** * struct cxl_dev_state - The driver device state * @@ -251,6 +282,7 @@ struct cxl_event_state { * @serial: PCIe Device Serial Number * @doe_mbs: PCI DOE mailbox array * @event: event log driver state + * @poison: poison driver state info * @mbox_send: @dev specific transport for transmitting mailbox commands * * See section 8.2.9.5.2 Capacity Configuration and Label Storage for @@ -290,6 +322,7 @@ struct cxl_dev_state { struct xarray doe_mbs; struct cxl_event_state event; + struct cxl_poison_state poison; int (*mbox_send)(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd); }; @@ -608,6 +641,7 @@ void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds); void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status); int cxl_set_timestamp(struct cxl_dev_state *cxlds); +int cxl_poison_state_init(struct cxl_dev_state *cxlds); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 60b23624d167..827ea0895778 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -769,6 +769,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; + rc = cxl_poison_state_init(cxlds); + if (rc) + return rc; + rc = cxl_dev_state_identify(cxlds); if (rc) return rc; -- GitLab From ed83f7ca398b3798b82c1d5d1113011c0e5a2198 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:04 -0700 Subject: [PATCH 3892/5631] cxl/mbox: Add GET_POISON_LIST mailbox command CXL devices maintain a list of locations that are poisoned or result in poison if the addresses are accessed by the host. Per the spec, (CXL 3.0 8.2.9.8.4.1), the device returns this Poison list as a set of Media Error Records that include the source of the error, the starting device physical address, and length. The length is the number of adjacent DPAs in the record and is in units of 64 bytes. Retrieve the poison list. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/a1f332e817834ef8e89c0ff32e760308fb903346.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 55 +++++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 46 ++++++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 17737386283a..05ff50ee8489 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -1038,6 +1039,7 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ struct cxl_mbox_identify id; struct cxl_mbox_cmd mbox_cmd; + u32 val; int rc; mbox_cmd = (struct cxl_mbox_cmd) { @@ -1061,6 +1063,11 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) cxlds->lsa_size = le32_to_cpu(id.lsa_size); memcpy(cxlds->firmware_version, id.fw_revision, sizeof(id.fw_revision)); + if (test_bit(CXL_POISON_ENABLED_LIST, cxlds->poison.enabled_cmds)) { + val = get_unaligned_le24(id.poison_list_max_mer); + cxlds->poison.max_errors = min_t(u32, val, CXL_POISON_LIST_MAX); + } + return 0; } EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL); @@ -1151,6 +1158,54 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL); +int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, + struct cxl_region *cxlr) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_poison_out *po; + struct cxl_mbox_poison_in pi; + struct cxl_mbox_cmd mbox_cmd; + int nr_records = 0; + int rc; + + rc = mutex_lock_interruptible(&cxlds->poison.lock); + if (rc) + return rc; + + po = cxlds->poison.list_out; + pi.offset = cpu_to_le64(offset); + pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT); + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_GET_POISON, + .size_in = sizeof(pi), + .payload_in = &pi, + .size_out = cxlds->payload_size, + .payload_out = po, + .min_out = struct_size(po, record, 0), + }; + + do { + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + break; + + /* TODO TRACE the media error records */ + + /* Protect against an uncleared _FLAG_MORE */ + nr_records = nr_records + le16_to_cpu(po->count); + if (nr_records >= cxlds->poison.max_errors) { + dev_dbg(&cxlmd->dev, "Max Error Records reached: %d\n", + nr_records); + break; + } + } while (po->flags & CXL_POISON_FLAG_MORE); + + mutex_unlock(&cxlds->poison.lock); + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_mem_get_poison, CXL); + static void free_poison_buf(void *buf) { kvfree(buf); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 40de21fac128..f2f0cdda5825 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -571,6 +571,50 @@ struct cxl_mbox_set_timestamp_in { } __packed; +/* Get Poison List CXL 3.0 Spec 8.2.9.8.4.1 */ +struct cxl_mbox_poison_in { + __le64 offset; + __le64 length; +} __packed; + +struct cxl_mbox_poison_out { + u8 flags; + u8 rsvd1; + __le64 overflow_ts; + __le16 count; + u8 rsvd2[20]; + struct cxl_poison_record { + __le64 address; + __le32 length; + __le32 rsvd; + } __packed record[]; +} __packed; + +/* + * Get Poison List address field encodes the starting + * address of poison, and the source of the poison. + */ +#define CXL_POISON_START_MASK GENMASK_ULL(63, 6) +#define CXL_POISON_SOURCE_MASK GENMASK(2, 0) + +/* Get Poison List record length is in units of 64 bytes */ +#define CXL_POISON_LEN_MULT 64 + +/* Kernel defined maximum for a list of poison errors */ +#define CXL_POISON_LIST_MAX 1024 + +/* Get Poison List: Payload out flags */ +#define CXL_POISON_FLAG_MORE BIT(0) +#define CXL_POISON_FLAG_OVERFLOW BIT(1) +#define CXL_POISON_FLAG_SCANNING BIT(2) + +/* Get Poison List: Poison Source */ +#define CXL_POISON_SOURCE_UNKNOWN 0 +#define CXL_POISON_SOURCE_EXTERNAL 1 +#define CXL_POISON_SOURCE_INTERNAL 2 +#define CXL_POISON_SOURCE_INJECTED 3 +#define CXL_POISON_SOURCE_VENDOR 7 + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -642,6 +686,8 @@ void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cm void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status); int cxl_set_timestamp(struct cxl_dev_state *cxlds); int cxl_poison_state_init(struct cxl_dev_state *cxlds); +int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, + struct cxl_region *cxlr); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- GitLab From ddf49d57b841e55e1b0aee1224a9f526e50e1bcc Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:05 -0700 Subject: [PATCH 3893/5631] cxl/trace: Add TRACE support for CXL media-error records CXL devices may support the retrieval of a device poison list. Add a new trace event that the CXL subsystem may use to log the media-error records returned in the poison list. Log each media-error record as a cxl_poison trace event of type 'List'. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/de6196f5269483d886ab1834744f82d27189a666.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/core.h | 4 ++ drivers/cxl/core/mbox.c | 5 ++- drivers/cxl/core/trace.h | 94 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 102 insertions(+), 1 deletion(-) diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index cde475e13216..e888e293943e 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -64,4 +64,8 @@ int cxl_memdev_init(void); void cxl_memdev_exit(void); void cxl_mbox_init(void); +enum cxl_poison_trace_type { + CXL_POISON_TRACE_LIST, +}; + #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 05ff50ee8489..2daeeedb16e1 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1190,7 +1190,10 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, if (rc) break; - /* TODO TRACE the media error records */ + for (int i = 0; i < le16_to_cpu(po->count); i++) + trace_cxl_poison(cxlmd, cxlr, &po->record[i], + po->flags, po->overflow_ts, + CXL_POISON_TRACE_LIST); /* Protect against an uncleared _FLAG_MORE */ nr_records = nr_records + le16_to_cpu(po->count); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 9b8d3d997834..17c24baaf740 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -7,10 +7,12 @@ #define _CXL_EVENTS_H #include +#include #include #include #include +#include "core.h" #define CXL_RAS_UC_CACHE_DATA_PARITY BIT(0) #define CXL_RAS_UC_CACHE_ADDR_PARITY BIT(1) @@ -600,6 +602,98 @@ TRACE_EVENT(cxl_memory_module, ) ); +#define show_poison_trace_type(type) \ + __print_symbolic(type, \ + { CXL_POISON_TRACE_LIST, "List" }) + +#define __show_poison_source(source) \ + __print_symbolic(source, \ + { CXL_POISON_SOURCE_UNKNOWN, "Unknown" }, \ + { CXL_POISON_SOURCE_EXTERNAL, "External" }, \ + { CXL_POISON_SOURCE_INTERNAL, "Internal" }, \ + { CXL_POISON_SOURCE_INJECTED, "Injected" }, \ + { CXL_POISON_SOURCE_VENDOR, "Vendor" }) + +#define show_poison_source(source) \ + (((source > CXL_POISON_SOURCE_INJECTED) && \ + (source != CXL_POISON_SOURCE_VENDOR)) ? "Reserved" \ + : __show_poison_source(source)) + +#define show_poison_flags(flags) \ + __print_flags(flags, "|", \ + { CXL_POISON_FLAG_MORE, "More" }, \ + { CXL_POISON_FLAG_OVERFLOW, "Overflow" }, \ + { CXL_POISON_FLAG_SCANNING, "Scanning" }) + +#define __cxl_poison_addr(record) \ + (le64_to_cpu(record->address)) +#define cxl_poison_record_dpa(record) \ + (__cxl_poison_addr(record) & CXL_POISON_START_MASK) +#define cxl_poison_record_source(record) \ + (__cxl_poison_addr(record) & CXL_POISON_SOURCE_MASK) +#define cxl_poison_record_dpa_length(record) \ + (le32_to_cpu(record->length) * CXL_POISON_LEN_MULT) +#define cxl_poison_overflow(flags, time) \ + (flags & CXL_POISON_FLAG_OVERFLOW ? le64_to_cpu(time) : 0) + +TRACE_EVENT(cxl_poison, + + TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region, + const struct cxl_poison_record *record, u8 flags, + __le64 overflow_ts, enum cxl_poison_trace_type trace_type), + + TP_ARGS(cxlmd, region, record, flags, overflow_ts, trace_type), + + TP_STRUCT__entry( + __string(memdev, dev_name(&cxlmd->dev)) + __string(host, dev_name(cxlmd->dev.parent)) + __field(u64, serial) + __field(u8, trace_type) + __string(region, region) + __field(u64, overflow_ts) + __field(u64, dpa) + __field(u32, dpa_length) + __array(char, uuid, 16) + __field(u8, source) + __field(u8, flags) + ), + + TP_fast_assign( + __assign_str(memdev, dev_name(&cxlmd->dev)); + __assign_str(host, dev_name(cxlmd->dev.parent)); + __entry->serial = cxlmd->cxlds->serial; + __entry->overflow_ts = cxl_poison_overflow(flags, overflow_ts); + __entry->dpa = cxl_poison_record_dpa(record); + __entry->dpa_length = cxl_poison_record_dpa_length(record); + __entry->source = cxl_poison_record_source(record); + __entry->trace_type = trace_type; + __entry->flags = flags; + if (region) { + __assign_str(region, dev_name(®ion->dev)); + memcpy(__entry->uuid, ®ion->params.uuid, 16); + } else { + __assign_str(region, ""); + memset(__entry->uuid, 0, 16); + } + ), + + TP_printk("memdev=%s host=%s serial=%lld trace_type=%s region=%s " \ + "region_uuid=%pU dpa=0x%llx dpa_length=0x%x source=%s " \ + "flags=%s overflow_time=%llu", + __get_str(memdev), + __get_str(host), + __entry->serial, + show_poison_trace_type(__entry->trace_type), + __get_str(region), + __entry->uuid, + __entry->dpa, + __entry->dpa_length, + show_poison_source(__entry->source), + show_poison_flags(__entry->flags), + __entry->overflow_ts + ) +); + #endif /* _CXL_EVENTS_H */ #define TRACE_INCLUDE_FILE trace -- GitLab From 7ff6ad1075885fdc71f6fea94b95109a582dec29 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:06 -0700 Subject: [PATCH 3894/5631] cxl/memdev: Add trigger_poison_list sysfs attribute When a boolean 'true' is written to this attribute the memdev driver retrieves the poison list from the device. The list consists of addresses that are poisoned, or would result in poison if accessed, and the source of the poison. This attribute is only visible for devices supporting the capability. The retrieved errors are logged as kernel events when cxl_poison event tracing is enabled. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/1081cfdc8a349dc754779642d584707e56db26ba.1681838291.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- Documentation/ABI/testing/sysfs-bus-cxl | 14 ++++++++ drivers/cxl/core/memdev.c | 43 +++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 3 +- drivers/cxl/mem.c | 43 +++++++++++++++++++++++++ 4 files changed, 102 insertions(+), 1 deletion(-) diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl index 3acf2f17a73f..48ac0d911801 100644 --- a/Documentation/ABI/testing/sysfs-bus-cxl +++ b/Documentation/ABI/testing/sysfs-bus-cxl @@ -415,3 +415,17 @@ Description: 1), and checks that the hardware accepts the commit request. Reading this value indicates whether the region is committed or not. + + +What: /sys/bus/cxl/devices/memX/trigger_poison_list +Date: April, 2023 +KernelVersion: v6.4 +Contact: linux-cxl@vger.kernel.org +Description: + (WO) When a boolean 'true' is written to this attribute the + memdev driver retrieves the poison list from the device. The + list consists of addresses that are poisoned, or would result + in poison if accessed, and the source of the poison. This + attribute is only visible for devices supporting the + capability. The retrieved errors are logged as kernel + events when cxl_poison event tracing is enabled. diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 28a05f2fe32d..8be01479d40b 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -106,6 +106,49 @@ static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(numa_node); +static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u64 offset, length; + int rc = 0; + + /* CXL 3.0 Spec 8.2.9.8.4.1 Separate pmem and ram poison requests */ + if (resource_size(&cxlds->pmem_res)) { + offset = cxlds->pmem_res.start; + length = resource_size(&cxlds->pmem_res); + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc) + return rc; + } + if (resource_size(&cxlds->ram_res)) { + offset = cxlds->ram_res.start; + length = resource_size(&cxlds->ram_res); + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + /* + * Invalid Physical Address is not an error for + * volatile addresses. Device support is optional. + */ + if (rc == -EFAULT) + rc = 0; + } + return rc; +} + +int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) +{ + int rc; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_get_poison_by_memdev(cxlmd); + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index f2f0cdda5825..bfb75bf0182e 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -145,7 +145,7 @@ struct cxl_mbox_cmd { C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"), \ C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"), \ C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"), \ - C(PADDR, -ENXIO, "physical address specified is invalid"), \ + C(PADDR, -EFAULT, "physical address specified is invalid"), \ C(POISONLMT, -ENXIO, "poison injection limit has been reached"), \ C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"), \ C(ABORT, -ENXIO, "background cmd was aborted by device"), \ @@ -688,6 +688,7 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds); int cxl_poison_state_init(struct cxl_dev_state *cxlds); int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr); +int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 39c4b54f0715..b6a413facbd7 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -176,10 +176,53 @@ static int cxl_mem_probe(struct device *dev) return devm_add_action_or_reset(dev, enable_suspend, NULL); } +static ssize_t trigger_poison_list_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + bool trigger; + int rc; + + if (kstrtobool(buf, &trigger) || !trigger) + return -EINVAL; + + rc = cxl_trigger_poison_list(to_cxl_memdev(dev)); + + return rc ? rc : len; +} +static DEVICE_ATTR_WO(trigger_poison_list); + +static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n) +{ + if (a == &dev_attr_trigger_poison_list.attr) { + struct device *dev = kobj_to_dev(kobj); + + if (!test_bit(CXL_POISON_ENABLED_LIST, + to_cxl_memdev(dev)->cxlds->poison.enabled_cmds)) + return 0; + } + return a->mode; +} + +static struct attribute *cxl_mem_attrs[] = { + &dev_attr_trigger_poison_list.attr, + NULL +}; + +static struct attribute_group cxl_mem_group = { + .attrs = cxl_mem_attrs, + .is_visible = cxl_mem_visible, +}; + +__ATTRIBUTE_GROUPS(cxl_mem); + static struct cxl_driver cxl_mem_driver = { .name = "cxl_mem", .probe = cxl_mem_probe, .id = CXL_DEVICE_MEMORY_EXPANDER, + .drv = { + .dev_groups = cxl_mem_groups, + }, }; module_cxl_driver(cxl_mem_driver); -- GitLab From f0832a58639691af575fa28ffaeb657c51f3ca06 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:07 -0700 Subject: [PATCH 3895/5631] cxl/region: Provide region info to the cxl_poison trace event User space may need to know which region, if any, maps the poison address(es) logged in a cxl_poison trace event. Since the mapping of DPAs (device physical addresses) to a region can change, the kernel must provide this information at the time the poison list is read. The event informs user space that at event this mapped to this , which is poisoned. The cxl_poison trace event is already wired up to log the region name and uuid if it receives param 'struct cxl_region'. In order to provide that cxl_region, add another method for gathering poison - by committed endpoint decoder mappings. This method is only available with CONFIG_CXL_REGION and is only used if a region actually maps the memdev where poison is being read. After the region driver reads the poison list for all the mapped resources, poison is read for any remaining unmapped resources. The default method remains: read the poison by memdev resource. Signed-off-by: Alison Schofield Tested-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/438b01ccaa70592539e8eda4eb2b1d617ba03160.1681838292.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/core.h | 5 ++ drivers/cxl/core/memdev.c | 13 +++- drivers/cxl/core/region.c | 124 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 141 insertions(+), 1 deletion(-) diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index e888e293943e..deb5f87d6d0a 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -25,7 +25,12 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled); #define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type) int cxl_region_init(void); void cxl_region_exit(void); +int cxl_get_poison_by_endpoint(struct cxl_port *port); #else +static inline int cxl_get_poison_by_endpoint(struct cxl_port *port) +{ + return 0; +} static inline void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled) { } diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 8be01479d40b..185b6d27b698 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -136,13 +136,24 @@ static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd) int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) { + struct cxl_port *port; int rc; + port = dev_get_drvdata(&cxlmd->dev); + if (!port || !is_cxl_endpoint(port)) + return -EINVAL; + rc = down_read_interruptible(&cxl_dpa_rwsem); if (rc) return rc; - rc = cxl_get_poison_by_memdev(cxlmd); + if (port->commit_end == -1) { + /* No regions mapped to this memdev */ + rc = cxl_get_poison_by_memdev(cxlmd); + } else { + /* Regions mapped, collect poison by endpoint */ + rc = cxl_get_poison_by_endpoint(port); + } up_read(&cxl_dpa_rwsem); return rc; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index b2fd67fcebfb..f822de44bee0 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -2238,6 +2238,130 @@ struct cxl_pmem_region *to_cxl_pmem_region(struct device *dev) } EXPORT_SYMBOL_NS_GPL(to_cxl_pmem_region, CXL); +struct cxl_poison_context { + struct cxl_port *port; + enum cxl_decoder_mode mode; + u64 offset; +}; + +static int cxl_get_poison_unmapped(struct cxl_memdev *cxlmd, + struct cxl_poison_context *ctx) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u64 offset, length; + int rc = 0; + + /* + * Collect poison for the remaining unmapped resources + * after poison is collected by committed endpoints. + * + * Knowing that PMEM must always follow RAM, get poison + * for unmapped resources based on the last decoder's mode: + * ram: scan remains of ram range, then any pmem range + * pmem: scan remains of pmem range + */ + + if (ctx->mode == CXL_DECODER_RAM) { + offset = ctx->offset; + length = resource_size(&cxlds->ram_res) - offset; + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc == -EFAULT) + rc = 0; + if (rc) + return rc; + } + if (ctx->mode == CXL_DECODER_PMEM) { + offset = ctx->offset; + length = resource_size(&cxlds->dpa_res) - offset; + if (!length) + return 0; + } else if (resource_size(&cxlds->pmem_res)) { + offset = cxlds->pmem_res.start; + length = resource_size(&cxlds->pmem_res); + } else { + return 0; + } + + return cxl_mem_get_poison(cxlmd, offset, length, NULL); +} + +static int poison_by_decoder(struct device *dev, void *arg) +{ + struct cxl_poison_context *ctx = arg; + struct cxl_endpoint_decoder *cxled; + struct cxl_memdev *cxlmd; + u64 offset, length; + int rc = 0; + + if (!is_endpoint_decoder(dev)) + return rc; + + cxled = to_cxl_endpoint_decoder(dev); + if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) + return rc; + + /* + * Regions are only created with single mode decoders: pmem or ram. + * Linux does not support mixed mode decoders. This means that + * reading poison per endpoint decoder adheres to the requirement + * that poison reads of pmem and ram must be separated. + * CXL 3.0 Spec 8.2.9.8.4.1 + */ + if (cxled->mode == CXL_DECODER_MIXED) { + dev_dbg(dev, "poison list read unsupported in mixed mode\n"); + return rc; + } + + cxlmd = cxled_to_memdev(cxled); + if (cxled->skip) { + offset = cxled->dpa_res->start - cxled->skip; + length = cxled->skip; + rc = cxl_mem_get_poison(cxlmd, offset, length, NULL); + if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM) + rc = 0; + if (rc) + return rc; + } + + offset = cxled->dpa_res->start; + length = cxled->dpa_res->end - offset + 1; + rc = cxl_mem_get_poison(cxlmd, offset, length, cxled->cxld.region); + if (rc == -EFAULT && cxled->mode == CXL_DECODER_RAM) + rc = 0; + if (rc) + return rc; + + /* Iterate until commit_end is reached */ + if (cxled->cxld.id == ctx->port->commit_end) { + ctx->offset = cxled->dpa_res->end + 1; + ctx->mode = cxled->mode; + return 1; + } + + return 0; +} + +int cxl_get_poison_by_endpoint(struct cxl_port *port) +{ + struct cxl_poison_context ctx; + int rc = 0; + + rc = down_read_interruptible(&cxl_region_rwsem); + if (rc) + return rc; + + ctx = (struct cxl_poison_context) { + .port = port + }; + + rc = device_for_each_child(&port->dev, &ctx, poison_by_decoder); + if (rc == 1) + rc = cxl_get_poison_unmapped(to_cxl_memdev(port->uport), &ctx); + + up_read(&cxl_region_rwsem); + return rc; +} + static struct lock_class_key cxl_pmem_region_key; static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr) -- GitLab From 28a3ae4ff66c622448f5dfb7416bbe753e182eb4 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:08 -0700 Subject: [PATCH 3896/5631] cxl/trace: Add an HPA to cxl_poison trace events When a cxl_poison trace event is reported for a region, the poisoned Device Physical Address (DPA) can be translated to a Host Physical Address (HPA) for consumption by user space. Translate and add the resulting HPA to the cxl_poison trace event. Follow the device decode logic as defined in the CXL Spec 3.0 Section 8.2.4.19.13. If no region currently maps the poison, assign ULLONG_MAX to the cxl_poison event hpa field. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/6d3cd726f9042a59902785b0a2cb3ddfb70e0219.1681838292.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/trace.c | 94 ++++++++++++++++++++++++++++++++++++++++ drivers/cxl/core/trace.h | 11 ++++- 2 files changed, 103 insertions(+), 2 deletions(-) diff --git a/drivers/cxl/core/trace.c b/drivers/cxl/core/trace.c index 29ae7ce81dc5..d0403dc3c8ab 100644 --- a/drivers/cxl/core/trace.c +++ b/drivers/cxl/core/trace.c @@ -1,5 +1,99 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#include +#include "core.h" + #define CREATE_TRACE_POINTS #include "trace.h" + +static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos) +{ + struct cxl_region_params *p = &cxlr->params; + int gran = p->interleave_granularity; + int ways = p->interleave_ways; + u64 offset; + + /* Is the hpa within this region at all */ + if (hpa < p->res->start || hpa > p->res->end) { + dev_dbg(&cxlr->dev, + "Addr trans fail: hpa 0x%llx not in region\n", hpa); + return false; + } + + /* Is the hpa in an expected chunk for its pos(-ition) */ + offset = hpa - p->res->start; + offset = do_div(offset, gran * ways); + if ((offset >= pos * gran) && (offset < (pos + 1) * gran)) + return true; + + dev_dbg(&cxlr->dev, + "Addr trans fail: hpa 0x%llx not in expected chunk\n", hpa); + + return false; +} + +static u64 cxl_dpa_to_hpa(u64 dpa, struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled) +{ + u64 dpa_offset, hpa_offset, bits_upper, mask_upper, hpa; + struct cxl_region_params *p = &cxlr->params; + int pos = cxled->pos; + u16 eig = 0; + u8 eiw = 0; + + ways_to_eiw(p->interleave_ways, &eiw); + granularity_to_eig(p->interleave_granularity, &eig); + + /* + * The device position in the region interleave set was removed + * from the offset at HPA->DPA translation. To reconstruct the + * HPA, place the 'pos' in the offset. + * + * The placement of 'pos' in the HPA is determined by interleave + * ways and granularity and is defined in the CXL Spec 3.0 Section + * 8.2.4.19.13 Implementation Note: Device Decode Logic + */ + + /* Remove the dpa base */ + dpa_offset = dpa - cxl_dpa_resource_start(cxled); + + mask_upper = GENMASK_ULL(51, eig + 8); + + if (eiw < 8) { + hpa_offset = (dpa_offset & mask_upper) << eiw; + hpa_offset |= pos << (eig + 8); + } else { + bits_upper = (dpa_offset & mask_upper) >> (eig + 8); + bits_upper = bits_upper * 3; + hpa_offset = ((bits_upper << (eiw - 8)) + pos) << (eig + 8); + } + + /* The lower bits remain unchanged */ + hpa_offset |= dpa_offset & GENMASK_ULL(eig + 7, 0); + + /* Apply the hpa_offset to the region base address */ + hpa = hpa_offset + p->res->start; + + if (!cxl_is_hpa_in_range(hpa, cxlr, cxled->pos)) + return ULLONG_MAX; + + return hpa; +} + +u64 cxl_trace_hpa(struct cxl_region *cxlr, struct cxl_memdev *cxlmd, + u64 dpa) +{ + struct cxl_region_params *p = &cxlr->params; + struct cxl_endpoint_decoder *cxled = NULL; + + for (int i = 0; i < p->nr_targets; i++) { + cxled = p->targets[i]; + if (cxlmd == cxled_to_memdev(cxled)) + break; + } + if (!cxled || cxlmd != cxled_to_memdev(cxled)) + return ULLONG_MAX; + + return cxl_dpa_to_hpa(dpa, cxlr, cxled); +} diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 17c24baaf740..220cc7e721b8 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -636,6 +636,8 @@ TRACE_EVENT(cxl_memory_module, #define cxl_poison_overflow(flags, time) \ (flags & CXL_POISON_FLAG_OVERFLOW ? le64_to_cpu(time) : 0) +u64 cxl_trace_hpa(struct cxl_region *cxlr, struct cxl_memdev *memdev, u64 dpa); + TRACE_EVENT(cxl_poison, TP_PROTO(struct cxl_memdev *cxlmd, struct cxl_region *region, @@ -651,6 +653,7 @@ TRACE_EVENT(cxl_poison, __field(u8, trace_type) __string(region, region) __field(u64, overflow_ts) + __field(u64, hpa) __field(u64, dpa) __field(u32, dpa_length) __array(char, uuid, 16) @@ -671,21 +674,25 @@ TRACE_EVENT(cxl_poison, if (region) { __assign_str(region, dev_name(®ion->dev)); memcpy(__entry->uuid, ®ion->params.uuid, 16); + __entry->hpa = cxl_trace_hpa(region, cxlmd, + __entry->dpa); } else { __assign_str(region, ""); memset(__entry->uuid, 0, 16); + __entry->hpa = ULLONG_MAX; } ), TP_printk("memdev=%s host=%s serial=%lld trace_type=%s region=%s " \ - "region_uuid=%pU dpa=0x%llx dpa_length=0x%x source=%s " \ - "flags=%s overflow_time=%llu", + "region_uuid=%pU hpa=0x%llx dpa=0x%llx dpa_length=0x%x " \ + "source=%s flags=%s overflow_time=%llu", __get_str(memdev), __get_str(host), __entry->serial, show_poison_trace_type(__entry->trace_type), __get_str(region), __entry->uuid, + __entry->hpa, __entry->dpa, __entry->dpa_length, show_poison_source(__entry->source), -- GitLab From f8d22bf50ca56a334ef58bf59ee299ed62940e42 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 10:39:09 -0700 Subject: [PATCH 3897/5631] tools/testing/cxl: Mock support for Get Poison List Make mock memdevs support the Get Poison List mailbox command. Return a fake poison error record when the get poison list command is issued. This supports testing the kernel tracing and cxl list capabilities for media errors. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Ira Weiny Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/14d661ce3e3a32b7d8e76b8ecc5eb88343b3d09c.1681838292.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 42 ++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 9263b04d35f7..cf7975db05ed 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include "trace.h" @@ -40,6 +41,10 @@ static struct cxl_cel_entry mock_cel[] = { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_HEALTH_INFO), .effect = cpu_to_le16(0), }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_GET_POISON), + .effect = cpu_to_le16(0), + }, }; /* See CXL 2.0 Table 181 Get Health Info Output Payload */ @@ -471,6 +476,8 @@ static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) cpu_to_le64(DEV_SIZE / CXL_CAPACITY_MULTIPLIER), }; + put_unaligned_le24(CXL_POISON_LIST_MAX, id.poison_list_max_mer); + if (cmd->size_out < sizeof(id)) return -EINVAL; @@ -888,6 +895,34 @@ static int mock_health_info(struct cxl_dev_state *cxlds, return 0; } +static int mock_get_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_poison_in *pi = cmd->payload_in; + + /* Mock one poison record at pi.offset for 64 bytes */ + struct { + struct cxl_mbox_poison_out po; + struct cxl_poison_record record; + } __packed mock_plist = { + .po = { + .count = cpu_to_le16(1), + }, + .record = { + .length = cpu_to_le32(1), + .address = cpu_to_le64(le64_to_cpu(pi->offset) + + CXL_POISON_SOURCE_INJECTED), + }, + }; + + if (cmd->size_out < sizeof(mock_plist)) + return -EINVAL; + + memcpy(cmd->payload_out, &mock_plist, sizeof(mock_plist)); + cmd->size_out = sizeof(mock_plist); + return 0; +} + static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct device *dev = cxlds->dev; @@ -942,6 +977,9 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE: rc = mock_passphrase_secure_erase(cxlds, cmd); break; + case CXL_MBOX_OP_GET_POISON: + rc = mock_get_poison(cxlds, cmd); + break; default: break; } @@ -1010,6 +1048,10 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + rc = cxl_poison_state_init(cxlds); + if (rc) + return rc; + rc = cxl_dev_state_identify(cxlds); if (rc) return rc; -- GitLab From d2fbc48658022f48625064ae192baff52057987d Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:25 -0700 Subject: [PATCH 3898/5631] cxl/memdev: Add support for the Inject Poison mailbox command CXL devices optionally support the INJECT POISON mailbox command. Add memdev driver support for the mailbox command. Per the CXL Specification (3.0 8.2.9.8.4.2), after receiving a valid inject poison request, the device will return poison when the address is accessed through the CXL.mem driver. Injecting poison adds the address to the device's Poison List and the error source is set to Injected. In addition, the device adds a poison creation event to its internal Informational Event log, updates the Event Status register, and if configured, interrupts the host. Also, per the CXL Specification, it is not an error to inject poison into an address that already has poison present and no error is returned from the device. If the address is not contained in the device's dpa resource, or is not 64 byte aligned, return -EINVAL without issuing the mbox command. Poison injection is intended for debug only and will be exposed to userspace through debugfs. Restrict compilation to CONFIG_DEBUG_FS. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/241c64115e6bd2effed9c7a20b08b3908dd7be8f.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 56 +++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 6 +++++ 2 files changed, 62 insertions(+) diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 185b6d27b698..8a3b7d7505fe 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -160,6 +160,62 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); +static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + if (!resource_size(&cxlds->dpa_res)) { + dev_dbg(cxlds->dev, "device has no dpa resource\n"); + return -EINVAL; + } + if (dpa < cxlds->dpa_res.start || dpa > cxlds->dpa_res.end) { + dev_dbg(cxlds->dev, "dpa:0x%llx not in resource:%pR\n", + dpa, &cxlds->dpa_res); + return -EINVAL; + } + if (!IS_ALIGNED(dpa, 64)) { + dev_dbg(cxlds->dev, "dpa:0x%llx is not 64-byte aligned\n", dpa); + return -EINVAL; + } + + return 0; +} + +int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_inject_poison inject; + struct cxl_mbox_cmd mbox_cmd; + int rc; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_validate_poison_dpa(cxlmd, dpa); + if (rc) + goto out; + + inject.address = cpu_to_le64(dpa); + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_INJECT_POISON, + .size_in = sizeof(inject), + .payload_in = &inject, + }; + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); +out: + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index bfb75bf0182e..2a0625e1d3aa 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -615,6 +615,11 @@ struct cxl_mbox_poison_out { #define CXL_POISON_SOURCE_INJECTED 3 #define CXL_POISON_SOURCE_VENDOR 7 +/* Inject & Clear Poison CXL 3.0 Spec 8.2.9.8.4.2/3 */ +struct cxl_mbox_inject_poison { + __le64 address; +}; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -689,6 +694,7 @@ int cxl_poison_state_init(struct cxl_dev_state *cxlds); int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr); int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); +int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- GitLab From 9690b07748d18ac667036a68442081c4aea33ba7 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:26 -0700 Subject: [PATCH 3899/5631] cxl/memdev: Add support for the Clear Poison mailbox command CXL devices optionally support the CLEAR POISON mailbox command. Add memdev driver support for clearing poison. Per the CXL Specification (3.0 8.2.9.8.4.3), after receiving a valid clear poison request, the device removes the address from the device's Poison List and writes 0 (zero) for 64 bytes starting at address. If the device cannot clear poison from the address, it returns a permanent media error and -ENXIO is returned to the user. Additionally, and per the spec also, it is not an error to clear poison of an address that is not poisoned. If the address is not contained in the device's dpa resource, or is not 64 byte aligned, the driver returns -EINVAL without sending the command to the device. Poison clearing is intended for debug only and will be exposed to userspace through debugfs. Restrict compilation to CONFIG_DEBUG_FS. Implementation note: Although the CXL specification defines the clear command to accept 64 bytes of 'write-data', this implementation always uses zeroes as write-data. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/8682c30ec24bd9c45af5feccb04b02be51e58c0a.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 43 +++++++++++++++++++++++++++++++++++++++ drivers/cxl/cxlmem.h | 7 +++++++ 2 files changed, 50 insertions(+) diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 8a3b7d7505fe..813fd1eeba3d 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -216,6 +216,49 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) } EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, CXL); +int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_mbox_clear_poison clear; + struct cxl_mbox_cmd mbox_cmd; + int rc; + + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) + return rc; + + rc = cxl_validate_poison_dpa(cxlmd, dpa); + if (rc) + goto out; + + /* + * In CXL 3.0 Spec 8.2.9.8.4.3, the Clear Poison mailbox command + * is defined to accept 64 bytes of write-data, along with the + * address to clear. This driver uses zeroes as write-data. + */ + clear = (struct cxl_mbox_clear_poison) { + .address = cpu_to_le64(dpa) + }; + + mbox_cmd = (struct cxl_mbox_cmd) { + .opcode = CXL_MBOX_OP_CLEAR_POISON, + .size_in = sizeof(clear), + .payload_in = &clear, + }; + + rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto out; +out: + up_read(&cxl_dpa_rwsem); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(cxl_clear_poison, CXL); + static struct attribute *cxl_memdev_attributes[] = { &dev_attr_serial.attr, &dev_attr_firmware_version.attr, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 2a0625e1d3aa..80276f37b78f 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -620,6 +620,12 @@ struct cxl_mbox_inject_poison { __le64 address; }; +/* Clear Poison CXL 3.0 Spec 8.2.9.8.4.3 */ +struct cxl_mbox_clear_poison { + __le64 address; + u8 write_data[CXL_POISON_LEN_MULT]; +} __packed; + /** * struct cxl_mem_command - Driver representation of a memory device command * @info: Command information as it exists for the UAPI @@ -695,6 +701,7 @@ int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len, struct cxl_region *cxlr); int cxl_trigger_poison_list(struct cxl_memdev *cxlmd); int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa); +int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa); #ifdef CONFIG_CXL_SUSPEND void cxl_mem_active_inc(void); -- GitLab From 0a105ab28a4de44eb738ce64e9ac74946aa5133b Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:27 -0700 Subject: [PATCH 3900/5631] cxl/memdev: Warn of poison inject or clear to a mapped region Inject and clear poison capabilities and intended for debug usage only. In order to be useful in debug environments, the driver needs to allow inject and clear operations on DPAs mapped in regions. dev_warn_once() when either operation occurs. Signed-off-by: Alison Schofield Link: https://lore.kernel.org/r/f911ca5277c9d0f9757b72d7e6842871bfff4fa2.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Reviewed-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 59 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 813fd1eeba3d..40ce74f5500a 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -160,6 +160,50 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL); +struct cxl_dpa_to_region_context { + struct cxl_region *cxlr; + u64 dpa; +}; + +static int __cxl_dpa_to_region(struct device *dev, void *arg) +{ + struct cxl_dpa_to_region_context *ctx = arg; + struct cxl_endpoint_decoder *cxled; + u64 dpa = ctx->dpa; + + if (!is_endpoint_decoder(dev)) + return 0; + + cxled = to_cxl_endpoint_decoder(dev); + if (!cxled->dpa_res || !resource_size(cxled->dpa_res)) + return 0; + + if (dpa > cxled->dpa_res->end || dpa < cxled->dpa_res->start) + return 0; + + dev_dbg(dev, "dpa:0x%llx mapped in region:%s\n", dpa, + dev_name(&cxled->cxld.region->dev)); + + ctx->cxlr = cxled->cxld.region; + + return 1; +} + +static struct cxl_region *cxl_dpa_to_region(struct cxl_memdev *cxlmd, u64 dpa) +{ + struct cxl_dpa_to_region_context ctx; + struct cxl_port *port; + + ctx = (struct cxl_dpa_to_region_context) { + .dpa = dpa, + }; + port = dev_get_drvdata(&cxlmd->dev); + if (port && is_cxl_endpoint(port) && port->commit_end != -1) + device_for_each_child(&port->dev, &ctx, __cxl_dpa_to_region); + + return ctx.cxlr; +} + static int cxl_validate_poison_dpa(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; @@ -189,6 +233,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_inject_poison inject; struct cxl_mbox_cmd mbox_cmd; + struct cxl_region *cxlr; int rc; if (!IS_ENABLED(CONFIG_DEBUG_FS)) @@ -209,6 +254,14 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) .payload_in = &inject, }; rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); + if (rc) + goto out; + + cxlr = cxl_dpa_to_region(cxlmd, dpa); + if (cxlr) + dev_warn_once(cxlds->dev, + "poison inject dpa:%#llx region: %s\n", dpa, + dev_name(&cxlr->dev)); out: up_read(&cxl_dpa_rwsem); @@ -221,6 +274,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_clear_poison clear; struct cxl_mbox_cmd mbox_cmd; + struct cxl_region *cxlr; int rc; if (!IS_ENABLED(CONFIG_DEBUG_FS)) @@ -252,6 +306,11 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) rc = cxl_internal_send_cmd(cxlds, &mbox_cmd); if (rc) goto out; + + cxlr = cxl_dpa_to_region(cxlmd, dpa); + if (cxlr) + dev_warn_once(cxlds->dev, "poison clear dpa:%#llx region: %s\n", + dpa, dev_name(&cxlr->dev)); out: up_read(&cxl_dpa_rwsem); -- GitLab From 98b6926562d9ccdbca69de9a0e0bf4f90d7f1326 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:28 -0700 Subject: [PATCH 3901/5631] cxl/memdev: Trace inject and clear poison as cxl_poison events The cxl_poison trace event allows users to view the history of poison list reads. With the addition of inject and clear poison capabilities, users will expect similar tracing. Add trace types 'Inject' and 'Clear' to the cxl_poison trace_event and trace successful operations only. If the driver finds that the DPA being injected or cleared of poison is mapped in a region, that region info is included in the cxl_poison trace event. Region reconfigurations can make this extra info useless if the debug operations are not carefully managed. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/e20eb7c3029137b480ece671998c183da0477e2e.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- drivers/cxl/core/core.h | 2 ++ drivers/cxl/core/memdev.c | 15 +++++++++++++++ drivers/cxl/core/trace.h | 8 +++++--- 3 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index deb5f87d6d0a..27f0968449de 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -71,6 +71,8 @@ void cxl_mbox_init(void); enum cxl_poison_trace_type { CXL_POISON_TRACE_LIST, + CXL_POISON_TRACE_INJECT, + CXL_POISON_TRACE_CLEAR, }; #endif /* __CXL_CORE_H__ */ diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 40ce74f5500a..057a43267290 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -6,6 +6,7 @@ #include #include #include +#include "trace.h" #include "core.h" static DECLARE_RWSEM(cxl_memdev_rwsem); @@ -232,6 +233,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_inject_poison inject; + struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; struct cxl_region *cxlr; int rc; @@ -262,6 +264,12 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) dev_warn_once(cxlds->dev, "poison inject dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); + + record = (struct cxl_poison_record) { + .address = cpu_to_le64(dpa), + .length = cpu_to_le32(1), + }; + trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); @@ -273,6 +281,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) { struct cxl_dev_state *cxlds = cxlmd->cxlds; struct cxl_mbox_clear_poison clear; + struct cxl_poison_record record; struct cxl_mbox_cmd mbox_cmd; struct cxl_region *cxlr; int rc; @@ -311,6 +320,12 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (cxlr) dev_warn_once(cxlds->dev, "poison clear dpa:%#llx region: %s\n", dpa, dev_name(&cxlr->dev)); + + record = (struct cxl_poison_record) { + .address = cpu_to_le64(dpa), + .length = cpu_to_le32(1), + }; + trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 220cc7e721b8..a0b5819bc70b 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -602,9 +602,11 @@ TRACE_EVENT(cxl_memory_module, ) ); -#define show_poison_trace_type(type) \ - __print_symbolic(type, \ - { CXL_POISON_TRACE_LIST, "List" }) +#define show_poison_trace_type(type) \ + __print_symbolic(type, \ + { CXL_POISON_TRACE_LIST, "List" }, \ + { CXL_POISON_TRACE_INJECT, "Inject" }, \ + { CXL_POISON_TRACE_CLEAR, "Clear" }) #define __show_poison_source(source) \ __print_symbolic(source, \ -- GitLab From 50d527f52cbf0680c87d11a254383ca730c5c19f Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:29 -0700 Subject: [PATCH 3902/5631] cxl/mem: Add debugfs attributes for poison inject and clear Inject and Clear Poison commands are optionally supported by CXL memdev devices and are intended for use in debug environments only. Add debugfs attributes for user access. Documentation/ABI/testing/debugfs-cxl describes the usage. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/0c9ea8e671b8e58465d18722788b60d325c675c7.1681874357.git.alison.schofield@intel.com Tested-by: Jonathan Cameron Signed-off-by: Dan Williams --- Documentation/ABI/testing/debugfs-cxl | 35 +++++++++++++++++++++++++++ drivers/cxl/mem.c | 28 +++++++++++++++++++++ 2 files changed, 63 insertions(+) create mode 100644 Documentation/ABI/testing/debugfs-cxl diff --git a/Documentation/ABI/testing/debugfs-cxl b/Documentation/ABI/testing/debugfs-cxl new file mode 100644 index 000000000000..fe61d372e3fa --- /dev/null +++ b/Documentation/ABI/testing/debugfs-cxl @@ -0,0 +1,35 @@ +What: /sys/kernel/debug/cxl/memX/inject_poison +Date: April, 2023 +KernelVersion: v6.4 +Contact: linux-cxl@vger.kernel.org +Description: + (WO) When a Device Physical Address (DPA) is written to this + attribute, the memdev driver sends an inject poison command to + the device for the specified address. The DPA must be 64-byte + aligned and the length of the injected poison is 64-bytes. If + successful, the device returns poison when the address is + accessed through the CXL.mem bus. Injecting poison adds the + address to the device's Poison List and the error source is set + to Injected. In addition, the device adds a poison creation + event to its internal Informational Event log, updates the + Event Status register, and if configured, interrupts the host. + It is not an error to inject poison into an address that + already has poison present and no error is returned. The + inject_poison attribute is only visible for devices supporting + the capability. + + +What: /sys/kernel/debug/memX/clear_poison +Date: April, 2023 +KernelVersion: v6.4 +Contact: linux-cxl@vger.kernel.org +Description: + (WO) When a Device Physical Address (DPA) is written to this + attribute, the memdev driver sends a clear poison command to + the device for the specified address. Clearing poison removes + the address from the device's Poison List and writes 0 (zero) + for 64 bytes starting at address. It is not an error to clear + poison from an address that does not have poison set. If the + device cannot clear poison from the address, -ENXIO is returned. + The clear_poison attribute is only visible for devices + supporting the capability. diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index b6a413facbd7..10caf180b3fa 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -94,6 +94,26 @@ static int devm_cxl_add_endpoint(struct device *host, struct cxl_memdev *cxlmd, return 0; } +static int cxl_debugfs_poison_inject(void *data, u64 dpa) +{ + struct cxl_memdev *cxlmd = data; + + return cxl_inject_poison(cxlmd, dpa); +} + +DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_inject_fops, NULL, + cxl_debugfs_poison_inject, "%llx\n"); + +static int cxl_debugfs_poison_clear(void *data, u64 dpa) +{ + struct cxl_memdev *cxlmd = data; + + return cxl_clear_poison(cxlmd, dpa); +} + +DEFINE_DEBUGFS_ATTRIBUTE(cxl_poison_clear_fops, NULL, + cxl_debugfs_poison_clear, "%llx\n"); + static int cxl_mem_probe(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); @@ -117,6 +137,14 @@ static int cxl_mem_probe(struct device *dev) dentry = cxl_debugfs_create_dir(dev_name(dev)); debugfs_create_devm_seqfile(dev, "dpamem", dentry, cxl_mem_dpa_show); + + if (test_bit(CXL_POISON_ENABLED_INJECT, cxlds->poison.enabled_cmds)) + debugfs_create_file("inject_poison", 0200, dentry, cxlmd, + &cxl_poison_inject_fops); + if (test_bit(CXL_POISON_ENABLED_CLEAR, cxlds->poison.enabled_cmds)) + debugfs_create_file("clear_poison", 0200, dentry, cxlmd, + &cxl_poison_clear_fops); + rc = devm_add_action_or_reset(dev, remove_debugfs, dentry); if (rc) return rc; -- GitLab From 371c16101ee8a076cbe93ab95bbefdb43927003e Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:30 -0700 Subject: [PATCH 3903/5631] tools/testing/cxl: Mock the Inject Poison mailbox command Mock the injection of poison by storing the device:address entries in mock_poison_list[]. Enforce a limit of 8 poison injections per memdev device and 128 total entries for the cxl_test mock driver. Introducing the mock_poison[] list here, makes it available for use in the mock of Clear Poison, and the mock of Get Poison List. Signed-off-by: Alison Schofield Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/f6b7f03541eaa8c2260d3eafadd04afe3f0d7962.1681874357.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 77 ++++++++++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index cf7975db05ed..2731ebbd175b 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -16,6 +16,9 @@ #define DEV_SIZE SZ_2G #define EFFECT(x) (1U << x) +#define MOCK_INJECT_DEV_MAX 8 +#define MOCK_INJECT_TEST_MAX 128 + static struct cxl_cel_entry mock_cel[] = { { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_SUPPORTED_LOGS), @@ -45,6 +48,10 @@ static struct cxl_cel_entry mock_cel[] = { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_POISON), .effect = cpu_to_le16(0), }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_INJECT_POISON), + .effect = cpu_to_le16(0), + }, }; /* See CXL 2.0 Table 181 Get Health Info Output Payload */ @@ -474,6 +481,7 @@ static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) cpu_to_le64(SZ_256M / CXL_CAPACITY_MULTIPLIER), .total_capacity = cpu_to_le64(DEV_SIZE / CXL_CAPACITY_MULTIPLIER), + .inject_poison_limit = cpu_to_le16(MOCK_INJECT_DEV_MAX), }; put_unaligned_le24(CXL_POISON_LIST_MAX, id.poison_list_max_mer); @@ -895,6 +903,11 @@ static int mock_health_info(struct cxl_dev_state *cxlds, return 0; } +static struct mock_poison { + struct cxl_dev_state *cxlds; + u64 dpa; +} mock_poison_list[MOCK_INJECT_TEST_MAX]; + static int mock_get_poison(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { @@ -923,6 +936,67 @@ static int mock_get_poison(struct cxl_dev_state *cxlds, return 0; } +static bool mock_poison_dev_max_injected(struct cxl_dev_state *cxlds) +{ + int count = 0; + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds) + count++; + } + return (count >= MOCK_INJECT_DEV_MAX); +} + +static bool mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa) +{ + if (mock_poison_dev_max_injected(cxlds)) { + dev_dbg(cxlds->dev, + "Device poison injection limit has been reached: %d\n", + MOCK_INJECT_DEV_MAX); + return false; + } + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (!mock_poison_list[i].cxlds) { + mock_poison_list[i].cxlds = cxlds; + mock_poison_list[i].dpa = dpa; + return true; + } + } + dev_dbg(cxlds->dev, + "Mock test poison injection limit has been reached: %d\n", + MOCK_INJECT_TEST_MAX); + + return false; +} + +static bool mock_poison_found(struct cxl_dev_state *cxlds, u64 dpa) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds && + mock_poison_list[i].dpa == dpa) + return true; + } + return false; +} + +static int mock_inject_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_inject_poison *pi = cmd->payload_in; + u64 dpa = le64_to_cpu(pi->address); + + if (mock_poison_found(cxlds, dpa)) { + /* Not an error to inject poison if already poisoned */ + dev_dbg(cxlds->dev, "DPA: 0x%llx already poisoned\n", dpa); + return 0; + } + if (!mock_poison_add(cxlds, dpa)) + return -ENXIO; + + return 0; +} + static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct device *dev = cxlds->dev; @@ -980,6 +1054,9 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_GET_POISON: rc = mock_get_poison(cxlds, cmd); break; + case CXL_MBOX_OP_INJECT_POISON: + rc = mock_inject_poison(cxlds, cmd); + break; default: break; } -- GitLab From 6ec4b6d23e3a5b653cc8b6a7b09c20c30190cfce Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:31 -0700 Subject: [PATCH 3904/5631] tools/testing/cxl: Mock the Clear Poison mailbox command Mock the clear of poison by deleting the device:address entry from the mock_poison_list[]. Behave like a real CXL device and do not fail if the address is not in the poison list, but offer a dev_dbg() message. Signed-off-by: Alison Schofield Reviewed-by: Jonathan Cameron Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/ecf19743c6572e60971bbd078f67d520cf5bca5d.1681874357.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 2731ebbd175b..3c3909d30d03 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -52,6 +52,10 @@ static struct cxl_cel_entry mock_cel[] = { .opcode = cpu_to_le16(CXL_MBOX_OP_INJECT_POISON), .effect = cpu_to_le16(0), }, + { + .opcode = cpu_to_le16(CXL_MBOX_OP_CLEAR_POISON), + .effect = cpu_to_le16(0), + }, }; /* See CXL 2.0 Table 181 Get Health Info Output Payload */ @@ -997,6 +1001,35 @@ static int mock_inject_poison(struct cxl_dev_state *cxlds, return 0; } +static bool mock_poison_del(struct cxl_dev_state *cxlds, u64 dpa) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds == cxlds && + mock_poison_list[i].dpa == dpa) { + mock_poison_list[i].cxlds = NULL; + return true; + } + } + return false; +} + +static int mock_clear_poison(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mbox_clear_poison *pi = cmd->payload_in; + u64 dpa = le64_to_cpu(pi->address); + + /* + * A real CXL device will write pi->write_data to the address + * being cleared. In this mock, just delete this address from + * the mock poison list. + */ + if (!mock_poison_del(cxlds, dpa)) + dev_dbg(cxlds->dev, "DPA: 0x%llx not in poison list\n", dpa); + + return 0; +} + static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct device *dev = cxlds->dev; @@ -1057,6 +1090,9 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * case CXL_MBOX_OP_INJECT_POISON: rc = mock_inject_poison(cxlds, cmd); break; + case CXL_MBOX_OP_CLEAR_POISON: + rc = mock_clear_poison(cxlds, cmd); + break; default: break; } -- GitLab From 8eac7ea72593010726713c5359a4b6aedf29b6fe Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:32 -0700 Subject: [PATCH 3905/5631] tools/testing/cxl: Use injected poison for get poison list Prior to poison inject support, the mock of 'Get Poison List' returned a poison list containing a single mocked error record. Following the addition of poison inject and clear support to the mock driver, use the mock_poison_list[], rather than faking an error record. Mock_poison_list[] list tracks the actual poison inject and clear requests issued by userspace. Signed-off-by: Alison Schofield Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/0f4242c81821f4982b02cb1009c22783ef66b2f1.1681874357.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 62 +++++++++++++++++++++++++----------- 1 file changed, 43 insertions(+), 19 deletions(-) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 3c3909d30d03..8b053de23504 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -912,31 +912,55 @@ static struct mock_poison { u64 dpa; } mock_poison_list[MOCK_INJECT_TEST_MAX]; +static struct cxl_mbox_poison_out * +cxl_get_injected_po(struct cxl_dev_state *cxlds, u64 offset, u64 length) +{ + struct cxl_mbox_poison_out *po; + int nr_records = 0; + u64 dpa; + + po = kzalloc(struct_size(po, record, MOCK_INJECT_DEV_MAX), GFP_KERNEL); + if (!po) + return NULL; + + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds != cxlds) + continue; + if (mock_poison_list[i].dpa < offset || + mock_poison_list[i].dpa > offset + length - 1) + continue; + + dpa = mock_poison_list[i].dpa + CXL_POISON_SOURCE_INJECTED; + po->record[nr_records].address = cpu_to_le64(dpa); + po->record[nr_records].length = cpu_to_le32(1); + nr_records++; + if (nr_records == MOCK_INJECT_DEV_MAX) + break; + } + + /* Always return count, even when zero */ + po->count = cpu_to_le16(nr_records); + + return po; +} + static int mock_get_poison(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct cxl_mbox_poison_in *pi = cmd->payload_in; + struct cxl_mbox_poison_out *po; + u64 offset = le64_to_cpu(pi->offset); + u64 length = le64_to_cpu(pi->length); + int nr_records; - /* Mock one poison record at pi.offset for 64 bytes */ - struct { - struct cxl_mbox_poison_out po; - struct cxl_poison_record record; - } __packed mock_plist = { - .po = { - .count = cpu_to_le16(1), - }, - .record = { - .length = cpu_to_le32(1), - .address = cpu_to_le64(le64_to_cpu(pi->offset) + - CXL_POISON_SOURCE_INJECTED), - }, - }; - - if (cmd->size_out < sizeof(mock_plist)) - return -EINVAL; + po = cxl_get_injected_po(cxlds, offset, length); + if (!po) + return -ENOMEM; + nr_records = le16_to_cpu(po->count); + memcpy(cmd->payload_out, po, struct_size(po, record, nr_records)); + cmd->size_out = struct_size(po, record, nr_records); + kfree(po); - memcpy(cmd->payload_out, &mock_plist, sizeof(mock_plist)); - cmd->size_out = sizeof(mock_plist); return 0; } -- GitLab From 98980d76c3fc3d56b34e425eb102b10355ccc743 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:33 -0700 Subject: [PATCH 3906/5631] tools/testing/cxl: Add a sysfs attr to test poison inject limits CXL devices may report a maximum number of addresses that a device allows to be poisoned using poison injection. When cxl_test creates mock CXL memory devices, it defaults to MOCK_INJECT_DEV_MAX==88 for all mocked memdevs. Add a sysfs attribute, poison_inject_max to module cxl_mock_mem so that users can set a custom device injection limit. Fail, and return -EBUSY, if the mock poison list is not empty. /sys/bus/platform/drivers/cxl_mock_mem/poison_inject_max A simple usage model is to set the attribute before running a test in order to emulate a device's poison handling. Signed-off-by: Alison Schofield Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/0f25b2862b90013545450222d2199e435c6cc11a.1681874357.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 52 +++++++++++++++++++++++++++++++++--- 1 file changed, 48 insertions(+), 4 deletions(-) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 8b053de23504..0fd7e7b8b44a 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -19,6 +19,8 @@ #define MOCK_INJECT_DEV_MAX 8 #define MOCK_INJECT_TEST_MAX 128 +static unsigned int poison_inject_dev_max = MOCK_INJECT_DEV_MAX; + static struct cxl_cel_entry mock_cel[] = { { .opcode = cpu_to_le16(CXL_MBOX_OP_GET_SUPPORTED_LOGS), @@ -485,7 +487,7 @@ static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) cpu_to_le64(SZ_256M / CXL_CAPACITY_MULTIPLIER), .total_capacity = cpu_to_le64(DEV_SIZE / CXL_CAPACITY_MULTIPLIER), - .inject_poison_limit = cpu_to_le16(MOCK_INJECT_DEV_MAX), + .inject_poison_limit = cpu_to_le16(MOCK_INJECT_TEST_MAX), }; put_unaligned_le24(CXL_POISON_LIST_MAX, id.poison_list_max_mer); @@ -919,7 +921,7 @@ cxl_get_injected_po(struct cxl_dev_state *cxlds, u64 offset, u64 length) int nr_records = 0; u64 dpa; - po = kzalloc(struct_size(po, record, MOCK_INJECT_DEV_MAX), GFP_KERNEL); + po = kzalloc(struct_size(po, record, poison_inject_dev_max), GFP_KERNEL); if (!po) return NULL; @@ -934,7 +936,7 @@ cxl_get_injected_po(struct cxl_dev_state *cxlds, u64 offset, u64 length) po->record[nr_records].address = cpu_to_le64(dpa); po->record[nr_records].length = cpu_to_le32(1); nr_records++; - if (nr_records == MOCK_INJECT_DEV_MAX) + if (nr_records == poison_inject_dev_max) break; } @@ -972,7 +974,7 @@ static bool mock_poison_dev_max_injected(struct cxl_dev_state *cxlds) if (mock_poison_list[i].cxlds == cxlds) count++; } - return (count >= MOCK_INJECT_DEV_MAX); + return (count >= poison_inject_dev_max); } static bool mock_poison_add(struct cxl_dev_state *cxlds, u64 dpa) @@ -1054,6 +1056,47 @@ static int mock_clear_poison(struct cxl_dev_state *cxlds, return 0; } +static bool mock_poison_list_empty(void) +{ + for (int i = 0; i < MOCK_INJECT_TEST_MAX; i++) { + if (mock_poison_list[i].cxlds) + return false; + } + return true; +} + +static ssize_t poison_inject_max_show(struct device_driver *drv, char *buf) +{ + return sysfs_emit(buf, "%u\n", poison_inject_dev_max); +} + +static ssize_t poison_inject_max_store(struct device_driver *drv, + const char *buf, size_t len) +{ + int val; + + if (kstrtoint(buf, 0, &val) < 0) + return -EINVAL; + + if (!mock_poison_list_empty()) + return -EBUSY; + + if (val <= MOCK_INJECT_TEST_MAX) + poison_inject_dev_max = val; + else + return -EINVAL; + + return len; +} + +static DRIVER_ATTR_RW(poison_inject_max); + +static struct attribute *cxl_mock_mem_core_attrs[] = { + &driver_attr_poison_inject_max.attr, + NULL +}; +ATTRIBUTE_GROUPS(cxl_mock_mem_core); + static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd) { struct device *dev = cxlds->dev; @@ -1262,6 +1305,7 @@ static struct platform_driver cxl_mock_mem_driver = { .driver = { .name = KBUILD_MODNAME, .dev_groups = cxl_mock_mem_groups, + .groups = cxl_mock_mem_core_groups, }, }; -- GitLab From 30a8a105f0ce9f2c83063b289f76833386d4a120 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 18 Apr 2023 20:26:34 -0700 Subject: [PATCH 3907/5631] tools/testing/cxl: Require CONFIG_DEBUG_FS The cxl_mem driver uses debugfs to support poison inject and clear. Add debugfs to the list of required symbols so that cxl_test can emulate those poison operations. Signed-off-by: Alison Schofield Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/4f3aab57fbf1cc3ccde2eb887c5d90566c8d0e90.1681874357.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/config_check.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/cxl/config_check.c b/tools/testing/cxl/config_check.c index 99b56b5f6edf..0902c5d6e410 100644 --- a/tools/testing/cxl/config_check.c +++ b/tools/testing/cxl/config_check.c @@ -13,4 +13,5 @@ void check(void) BUILD_BUG_ON(!IS_MODULE(CONFIG_CXL_PMEM)); BUILD_BUG_ON(!IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)); BUILD_BUG_ON(!IS_ENABLED(CONFIG_NVDIMM_SECURITY_TEST)); + BUILD_BUG_ON(!IS_ENABLED(CONFIG_DEBUG_FS)); } -- GitLab From bfe58458fd2557c9a81b89bc0ff10eb03d6c0745 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 6 Mar 2023 20:26:55 -0800 Subject: [PATCH 3908/5631] cxl/mbox: Update CMD_RC_TABLE As of CXL 3.0 there have some added return codes, update the driver accordingly. Signed-off-by: Davidlohr Bueso Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230307042655.6714-1-dave@stgolabs.net Signed-off-by: Dan Williams --- drivers/cxl/cxlmem.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 6090611669a6..db12b6313afb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -127,7 +127,7 @@ struct cxl_mbox_cmd { }; /* - * Per CXL 2.0 Section 8.2.8.4.5.1 + * Per CXL 3.0 Section 8.2.8.4.5.1 */ #define CMD_CMD_RC_TABLE \ C(SUCCESS, 0, NULL), \ @@ -152,7 +152,15 @@ struct cxl_mbox_cmd { C(SECURITY, -ENXIO, "not valid in the current security state"), \ C(PASSPHRASE, -ENXIO, "phrase doesn't match current set passphrase"), \ C(MBUNSUPPORTED, -ENXIO, "unsupported on the mailbox it was issued on"),\ - C(PAYLOADLEN, -ENXIO, "invalid payload length") + C(PAYLOADLEN, -ENXIO, "invalid payload length"), \ + C(LOG, -ENXIO, "invalid or unsupported log page"), \ + C(INTERRUPTED, -ENXIO, "asynchronous event occured"), \ + C(FEATUREVERSION, -ENXIO, "unsupported feature version"), \ + C(FEATURESELVALUE, -ENXIO, "unsupported feature selection value"), \ + C(FEATURETRANSFERIP, -ENXIO, "feature transfer in progress"), \ + C(FEATURETRANSFEROOO, -ENXIO, "feature transfer out of order"), \ + C(RESOURCEEXHAUSTED, -ENXIO, "resources are exhausted"), \ + C(EXTLIST, -ENXIO, "invalid Extent List"), \ #undef C #define C(a, b, c) CXL_MBOX_CMD_RC_##a -- GitLab From 7d01cb27f6aebc54efbe28d8961a973b8f795b13 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 1 Mar 2023 20:29:18 +0800 Subject: [PATCH 3909/5631] Revert "ubifs: dirty_cow_znode: Fix memleak in error handling path" This reverts commit 122deabfe1428 (ubifs: dirty_cow_znode: Fix memleak in error handling path). After commit 122deabfe1428 applied, if insert_old_idx() failed, old index neither exists in TNC nor in old-index tree. Which means that old index node could be overwritten in layout_leb_in_gaps(), then ubifs image will be corrupted in power-cut. Fixes: 122deabfe1428 (ubifs: dirty_cow_znode: Fix memleak ... path) Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- fs/ubifs/tnc.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 2469f72eeaab..2df56bbc6865 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -267,18 +267,11 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, if (zbr->len) { err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) - /* - * Obsolete znodes will be freed by tnc_destroy_cnext() - * or free_obsolete_znodes(), copied up znodes should - * be added back to tnc and freed by - * ubifs_destroy_tnc_subtree(). - */ - goto out; + return ERR_PTR(err); err = add_idx_dirt(c, zbr->lnum, zbr->len); } else err = 0; -out: zbr->znode = zn; zbr->lnum = 0; zbr->offs = 0; -- GitLab From b5fda08ef213352ac2df7447611eb4d383cce929 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Wed, 1 Mar 2023 20:29:19 +0800 Subject: [PATCH 3910/5631] ubifs: Fix memleak when insert_old_idx() failed Following process will cause a memleak for copied up znode: dirty_cow_znode zn = copy_znode(c, znode); err = insert_old_idx(c, zbr->lnum, zbr->offs); if (unlikely(err)) return ERR_PTR(err); // No one refers to zn. Fetch a reproducer in [Link]. Function copy_znode() is split into 2 parts: resource allocation and znode replacement, insert_old_idx() is split in similar way, so resource cleanup could be done in error handling path without corrupting metadata(mem & disk). It's okay that old index inserting is put behind of add_idx_dirt(), old index is used in layout_leb_in_gaps(), so the two processes do not depend on each other. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216705 Fixes: 1e51764a3c2a ("UBIFS: add new flash file system") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng Signed-off-by: Richard Weinberger --- fs/ubifs/tnc.c | 137 +++++++++++++++++++++++++++++++------------------ 1 file changed, 87 insertions(+), 50 deletions(-) diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 2df56bbc6865..6b7d95b65f4b 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -44,6 +44,33 @@ enum { NOT_ON_MEDIA = 3, }; +static void do_insert_old_idx(struct ubifs_info *c, + struct ubifs_old_idx *old_idx) +{ + struct ubifs_old_idx *o; + struct rb_node **p, *parent = NULL; + + p = &c->old_idx.rb_node; + while (*p) { + parent = *p; + o = rb_entry(parent, struct ubifs_old_idx, rb); + if (old_idx->lnum < o->lnum) + p = &(*p)->rb_left; + else if (old_idx->lnum > o->lnum) + p = &(*p)->rb_right; + else if (old_idx->offs < o->offs) + p = &(*p)->rb_left; + else if (old_idx->offs > o->offs) + p = &(*p)->rb_right; + else { + ubifs_err(c, "old idx added twice!"); + kfree(old_idx); + } + } + rb_link_node(&old_idx->rb, parent, p); + rb_insert_color(&old_idx->rb, &c->old_idx); +} + /** * insert_old_idx - record an index node obsoleted since the last commit start. * @c: UBIFS file-system description object @@ -69,35 +96,15 @@ enum { */ static int insert_old_idx(struct ubifs_info *c, int lnum, int offs) { - struct ubifs_old_idx *old_idx, *o; - struct rb_node **p, *parent = NULL; + struct ubifs_old_idx *old_idx; old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); if (unlikely(!old_idx)) return -ENOMEM; old_idx->lnum = lnum; old_idx->offs = offs; + do_insert_old_idx(c, old_idx); - p = &c->old_idx.rb_node; - while (*p) { - parent = *p; - o = rb_entry(parent, struct ubifs_old_idx, rb); - if (lnum < o->lnum) - p = &(*p)->rb_left; - else if (lnum > o->lnum) - p = &(*p)->rb_right; - else if (offs < o->offs) - p = &(*p)->rb_left; - else if (offs > o->offs) - p = &(*p)->rb_right; - else { - ubifs_err(c, "old idx added twice!"); - kfree(old_idx); - return 0; - } - } - rb_link_node(&old_idx->rb, parent, p); - rb_insert_color(&old_idx->rb, &c->old_idx); return 0; } @@ -199,23 +206,6 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); - ubifs_assert(c, !ubifs_zn_obsolete(znode)); - __set_bit(OBSOLETE_ZNODE, &znode->flags); - - if (znode->level != 0) { - int i; - const int n = zn->child_cnt; - - /* The children now have new parent */ - for (i = 0; i < n; i++) { - struct ubifs_zbranch *zbr = &zn->zbranch[i]; - - if (zbr->znode) - zbr->znode->parent = zn; - } - } - - atomic_long_inc(&c->dirty_zn_cnt); return zn; } @@ -233,6 +223,42 @@ static int add_idx_dirt(struct ubifs_info *c, int lnum, int dirt) return ubifs_add_dirt(c, lnum, dirt); } +/** + * replace_znode - replace old znode with new znode. + * @c: UBIFS file-system description object + * @new_zn: new znode + * @old_zn: old znode + * @zbr: the branch of parent znode + * + * Replace old znode with new znode in TNC. + */ +static void replace_znode(struct ubifs_info *c, struct ubifs_znode *new_zn, + struct ubifs_znode *old_zn, struct ubifs_zbranch *zbr) +{ + ubifs_assert(c, !ubifs_zn_obsolete(old_zn)); + __set_bit(OBSOLETE_ZNODE, &old_zn->flags); + + if (old_zn->level != 0) { + int i; + const int n = new_zn->child_cnt; + + /* The children now have new parent */ + for (i = 0; i < n; i++) { + struct ubifs_zbranch *child = &new_zn->zbranch[i]; + + if (child->znode) + child->znode->parent = new_zn; + } + } + + zbr->znode = new_zn; + zbr->lnum = 0; + zbr->offs = 0; + zbr->len = 0; + + atomic_long_inc(&c->dirty_zn_cnt); +} + /** * dirty_cow_znode - ensure a znode is not being committed. * @c: UBIFS file-system description object @@ -265,21 +291,32 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, return zn; if (zbr->len) { - err = insert_old_idx(c, zbr->lnum, zbr->offs); - if (unlikely(err)) - return ERR_PTR(err); + struct ubifs_old_idx *old_idx; + + old_idx = kmalloc(sizeof(struct ubifs_old_idx), GFP_NOFS); + if (unlikely(!old_idx)) { + err = -ENOMEM; + goto out; + } + old_idx->lnum = zbr->lnum; + old_idx->offs = zbr->offs; + err = add_idx_dirt(c, zbr->lnum, zbr->len); - } else - err = 0; + if (err) { + kfree(old_idx); + goto out; + } - zbr->znode = zn; - zbr->lnum = 0; - zbr->offs = 0; - zbr->len = 0; + do_insert_old_idx(c, old_idx); + } + + replace_znode(c, zn, znode, zbr); - if (unlikely(err)) - return ERR_PTR(err); return zn; + +out: + kfree(zn); + return ERR_PTR(err); } /** -- GitLab From f3948874c340cddb8c6d93d36f35742184d601a7 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Mon, 6 Mar 2023 12:58:14 +0900 Subject: [PATCH 3911/5631] MAINTAINERS: replace maintainer of FireWire subsystem In the last few years, I have reviewed patches for FireWire subsystem and requested sound subsystem maintainer to sent them to mainline, since FireWire subsystem maintainer has been long absent. This situation is not preferable since we have some user of sound hardware in IEEE 1394 bus. I will stand for the maintainer, and work for FireWire core functions and 1394 OHCI driver, as well as sound drivers. This commit replaces the corresponding entry. As you know, IEEE 1394 is enough legacy. I would like to schedule the end of my work in the subsystem. My effort will last next 6 years. In 2026, I will start strong announcement for users to migrate their work load from IEEE 1394 bus (e.g. by purchasing alternative devices in USB and hardening system for them), then in 2029 let me resign the maintainer and close Linux 1394 project. My current work focuses on real time data (sampling data) transmission protocol in packet-oriented communication, thus I would provide less help to implementations for the other type of protocol; i.e. IPv4/IPv6 over IEEE 1394 bus (firewire-net), SCSI transport protocol over IEEE 1394 bus (firewire-sbp2) and iSCSI target (sbp-target). If receiving few objections from developers, I will start my work to send fixes for v6.3 prepatch, and PR for future v6.4 or later. I'm pleased if getting any help until the end. Reference: commit b32744751e75 ("firewire: add to MAINTAINERS") Acked-by: Stefan Richter Acked-by: Takashi Iwai Acked-by: Randy Dunlap Link: https://lore.kernel.org/r/20230306035814.78455-1-o-takashi@sakamocchi.jp Signed-off-by: Takashi Sakamoto --- MAINTAINERS | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c6545eb54104..5cdf9f81ead6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7954,10 +7954,11 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/lio-core-2.6.git master F: drivers/target/sbp/ FIREWIRE SUBSYSTEM -M: Stefan Richter +M: Takashi Sakamoto +M: Takashi Sakamoto L: linux1394-devel@lists.sourceforge.net S: Maintained -W: http://ieee1394.wiki.kernel.org/ +W: http://ieee1394.docs.kernel.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394.git F: drivers/firewire/ F: include/linux/firewire.h -- GitLab From 02dc51a0a07a379539b4661ecb56eeb5b19b3928 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 9 Apr 2023 18:13:06 -0700 Subject: [PATCH 3912/5631] firewire: init_ohci1394_dma: use correct function names in comments Prevent kernel-doc complaints by using the correct function names in kernel-doc comments: drivers/firewire/init_ohci1394_dma.c:258: warning: expecting prototype for debug_init_ohci1394_dma(). Prototype was for init_ohci1394_dma_on_all_controllers() instead drivers/firewire/init_ohci1394_dma.c:289: warning: expecting prototype for setup_init_ohci1394_early(). Prototype was for setup_ohci1394_dma() instead Signed-off-by: Randy Dunlap Cc: Stefan Richter Cc: linux1394-devel@lists.sourceforge.net Cc: Andrew Morton Cc: Takashi Sakamoto Link: https://lore.kernel.org/r/20230410011306.26268-1-rdunlap@infradead.org Signed-off-by: Takashi Sakamoto --- drivers/firewire/init_ohci1394_dma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firewire/init_ohci1394_dma.c b/drivers/firewire/init_ohci1394_dma.c index 659256927b42..48b879e9e831 100644 --- a/drivers/firewire/init_ohci1394_dma.c +++ b/drivers/firewire/init_ohci1394_dma.c @@ -251,7 +251,7 @@ static inline void __init init_ohci1394_controller(int num, int slot, int func) } /** - * debug_init_ohci1394_dma - scan for OHCI1394 controllers and init DMA on them + * init_ohci1394_dma_on_all_controllers - scan for OHCI1394 controllers and init DMA on them * Scans the whole PCI space for OHCI1394 controllers and inits DMA on them */ void __init init_ohci1394_dma_on_all_controllers(void) @@ -283,7 +283,7 @@ void __init init_ohci1394_dma_on_all_controllers(void) } /** - * setup_init_ohci1394_early - enables early OHCI1394 DMA initialization + * setup_ohci1394_dma - enables early OHCI1394 DMA initialization */ static int __init setup_ohci1394_dma(char *opt) { -- GitLab From 5ec629e037ac5872139ebcac0c6af7d8675bbe6b Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Thu, 30 Mar 2023 12:04:45 +0000 Subject: [PATCH 3913/5631] cifs: Simplify SMB2_open_init() We can point to the create contexts in just one place, we don't have to do this in every add_*_context routine. Signed-off-by: Volker Lendecke Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 45 +++++++++++++-------------------------------- 1 file changed, 13 insertions(+), 32 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 366f0c3b799b..4f0d7c4bdb98 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -830,10 +830,6 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) + - iov[num - 1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_posix)); *num_iovec = num + 1; return 0; @@ -2183,10 +2179,6 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, return -ENOMEM; iov[num].iov_len = server->vals->create_lease_size; req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE; - if (!req->CreateContextsOffset) - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) + - iov[num - 1].iov_len); le32_add_cpu(&req->CreateContextsLength, server->vals->create_lease_size); *num_iovec = num + 1; @@ -2274,10 +2266,6 @@ add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = - cpu_to_le32(sizeof(struct smb2_create_req) + - iov[1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_v2)); *num_iovec = num + 1; return 0; @@ -2297,10 +2285,6 @@ add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec, if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_handle_reconnect_v2); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = - cpu_to_le32(sizeof(struct smb2_create_req) + - iov[1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_handle_reconnect_v2)); *num_iovec = num + 1; @@ -2331,10 +2315,6 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec, if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = - cpu_to_le32(sizeof(struct smb2_create_req) + - iov[1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable)); *num_iovec = num + 1; return 0; @@ -2376,10 +2356,6 @@ add_twarp_context(struct kvec *iov, unsigned int *num_iovec, __u64 timewarp) if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct crt_twarp_ctxt); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) + - iov[num - 1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_twarp_ctxt)); *num_iovec = num + 1; return 0; @@ -2511,10 +2487,6 @@ add_sd_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode, bool set if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = len; - if (!req->CreateContextsOffset) - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) + - iov[num - 1].iov_len); le32_add_cpu(&req->CreateContextsLength, len); *num_iovec = num + 1; return 0; @@ -2553,10 +2525,6 @@ add_query_id_context(struct kvec *iov, unsigned int *num_iovec) if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct crt_query_id_ctxt); - if (!req->CreateContextsOffset) - req->CreateContextsOffset = cpu_to_le32( - sizeof(struct smb2_create_req) + - iov[num - 1].iov_len); le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_query_id_ctxt)); *num_iovec = num + 1; return 0; @@ -2720,6 +2688,9 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, rc = add_posix_context(iov, &n_iov, mode); if (rc) goto err_free_req; + req->CreateContextsOffset = cpu_to_le32( + sizeof(struct smb2_create_req) + + iov[1].iov_len); pc_buf = iov[n_iov-1].iov_base; } @@ -2943,6 +2914,16 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } add_query_id_context(iov, &n_iov); + if (n_iov > 2) { + /* + * We have create contexts behind iov[1] (the file + * name), point at them from the main create request + */ + req->CreateContextsOffset = cpu_to_le32( + sizeof(struct smb2_create_req) + + iov[1].iov_len); + } + rqst->rq_nvec = n_iov; return 0; } -- GitLab From 2a8d1387ed985341364b471ad63e323431ef6c4a Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Thu, 30 Mar 2023 12:04:46 +0000 Subject: [PATCH 3914/5631] cifs: Simplify SMB2_open_init() Reduce code duplication by stitching together create contexts in one place. Signed-off-by: Volker Lendecke Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 42 +++++++++--------------------------------- 1 file changed, 9 insertions(+), 33 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 4f0d7c4bdb98..d9c2590d6150 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2835,14 +2835,6 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) { - /* need to set Next field of lease context if we request it */ - if (server->capabilities & SMB2_GLOBAL_CAP_LEASING) { - struct create_context *ccontext = - (struct create_context *)iov[n_iov-1].iov_base; - ccontext->Next = - cpu_to_le32(server->vals->create_lease_size); - } - rc = add_durable_context(iov, &n_iov, oparms, tcon->use_persistent); if (rc) @@ -2850,13 +2842,6 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } if (tcon->posix_extensions) { - if (n_iov > 2) { - struct create_context *ccontext = - (struct create_context *)iov[n_iov-1].iov_base; - ccontext->Next = - cpu_to_le32(iov[n_iov-1].iov_len); - } - rc = add_posix_context(iov, &n_iov, oparms->mode); if (rc) return rc; @@ -2864,13 +2849,6 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, if (tcon->snapshot_time) { cifs_dbg(FYI, "adding snapshot context\n"); - if (n_iov > 2) { - struct create_context *ccontext = - (struct create_context *)iov[n_iov-1].iov_base; - ccontext->Next = - cpu_to_le32(iov[n_iov-1].iov_len); - } - rc = add_twarp_context(iov, &n_iov, tcon->snapshot_time); if (rc) return rc; @@ -2894,12 +2872,6 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, set_owner = false; if (set_owner | set_mode) { - if (n_iov > 2) { - struct create_context *ccontext = - (struct create_context *)iov[n_iov-1].iov_base; - ccontext->Next = cpu_to_le32(iov[n_iov-1].iov_len); - } - cifs_dbg(FYI, "add sd with mode 0x%x\n", oparms->mode); rc = add_sd_context(iov, &n_iov, oparms->mode, set_owner); if (rc) @@ -2907,11 +2879,6 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } } - if (n_iov > 2) { - struct create_context *ccontext = - (struct create_context *)iov[n_iov-1].iov_base; - ccontext->Next = cpu_to_le32(iov[n_iov-1].iov_len); - } add_query_id_context(iov, &n_iov); if (n_iov > 2) { @@ -2922,6 +2889,15 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->CreateContextsOffset = cpu_to_le32( sizeof(struct smb2_create_req) + iov[1].iov_len); + + for (unsigned int i = 2; i < (n_iov-1); i++) { + struct kvec *v = &iov[i]; + size_t len = v->iov_len; + struct create_context *cctx = + (struct create_context *)v->iov_base; + + cctx->Next = cpu_to_le32(len); + } } rqst->rq_nvec = n_iov; -- GitLab From d2ec43b51521b4c83313df60d8b03a6640374c20 Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Thu, 30 Mar 2023 12:04:47 +0000 Subject: [PATCH 3915/5631] cifs: Simplify SMB2_open_init() Reduce code duplication by calculating req->CreateContextsLength in one place. This is the last reference to "req" in the add_*_context functions, remove that parameter. Signed-off-by: Volker Lendecke Reviewed-by: Enzo Matsumiya Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index d9c2590d6150..875862ce6051 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -821,7 +821,6 @@ create_posix_buf(umode_t mode) static int add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; iov[num].iov_base = create_posix_buf(mode); @@ -830,7 +829,6 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode) if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_posix); - le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_posix)); *num_iovec = num + 1; return 0; } @@ -2179,8 +2177,6 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, return -ENOMEM; iov[num].iov_len = server->vals->create_lease_size; req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_LEASE; - le32_add_cpu(&req->CreateContextsLength, - server->vals->create_lease_size); *num_iovec = num + 1; return 0; } @@ -2259,14 +2255,12 @@ static int add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct cifs_open_parms *oparms) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; iov[num].iov_base = create_durable_v2_buf(oparms); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2); - le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable_v2)); *num_iovec = num + 1; return 0; } @@ -2275,7 +2269,6 @@ static int add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec, struct cifs_open_parms *oparms) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; /* indicate that we don't need to relock the file */ @@ -2285,8 +2278,6 @@ add_durable_reconnect_v2_context(struct kvec *iov, unsigned int *num_iovec, if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_handle_reconnect_v2); - le32_add_cpu(&req->CreateContextsLength, - sizeof(struct create_durable_handle_reconnect_v2)); *num_iovec = num + 1; return 0; } @@ -2295,7 +2286,6 @@ static int add_durable_context(struct kvec *iov, unsigned int *num_iovec, struct cifs_open_parms *oparms, bool use_persistent) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; if (use_persistent) { @@ -2315,7 +2305,6 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec, if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable); - le32_add_cpu(&req->CreateContextsLength, sizeof(struct create_durable)); *num_iovec = num + 1; return 0; } @@ -2349,14 +2338,12 @@ create_twarp_buf(__u64 timewarp) static int add_twarp_context(struct kvec *iov, unsigned int *num_iovec, __u64 timewarp) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; iov[num].iov_base = create_twarp_buf(timewarp); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct crt_twarp_ctxt); - le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_twarp_ctxt)); *num_iovec = num + 1; return 0; } @@ -2479,7 +2466,6 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) static int add_sd_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode, bool set_owner) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; unsigned int len = 0; @@ -2487,7 +2473,6 @@ add_sd_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode, bool set if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = len; - le32_add_cpu(&req->CreateContextsLength, len); *num_iovec = num + 1; return 0; } @@ -2518,14 +2503,12 @@ create_query_id_buf(void) static int add_query_id_context(struct kvec *iov, unsigned int *num_iovec) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; iov[num].iov_base = create_query_id_buf(); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct crt_query_id_ctxt); - le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_query_id_ctxt)); *num_iovec = num + 1; return 0; } @@ -2889,6 +2872,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->CreateContextsOffset = cpu_to_le32( sizeof(struct smb2_create_req) + iov[1].iov_len); + req->CreateContextsLength = 0; for (unsigned int i = 2; i < (n_iov-1); i++) { struct kvec *v = &iov[i]; @@ -2897,7 +2881,10 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, (struct create_context *)v->iov_base; cctx->Next = cpu_to_le32(len); + le32_add_cpu(&req->CreateContextsLength, len); } + le32_add_cpu(&req->CreateContextsLength, + iov[n_iov-1].iov_len); } rqst->rq_nvec = n_iov; -- GitLab From 919e57c3147ce66ed0887168e622c5e7a8f04440 Mon Sep 17 00:00:00 2001 From: Volker Lendecke Date: Fri, 17 Mar 2023 11:15:22 +0000 Subject: [PATCH 3916/5631] cifs: Avoid a cast in add_lease_context() We have the correctly-typed struct smb2_create_req * available in the caller. Signed-off-by: Volker Lendecke Reviewed-by Ralph Boehme Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 875862ce6051..281e0b12658d 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2166,10 +2166,11 @@ smb2_parse_contexts(struct TCP_Server_Info *server, } static int -add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, +add_lease_context(struct TCP_Server_Info *server, + struct smb2_create_req *req, + struct kvec *iov, unsigned int *num_iovec, u8 *lease_key, __u8 *oplock) { - struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock); @@ -2811,7 +2812,7 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, (oparms->create_options & CREATE_NOT_FILE)) req->RequestedOplockLevel = *oplock; /* no srv lease support */ else { - rc = add_lease_context(server, iov, &n_iov, + rc = add_lease_context(server, req, iov, &n_iov, oparms->fid->lease_key, oplock); if (rc) return rc; -- GitLab From 34e8ccf9ce24b6b2e275bbe35cd392e18fbbd369 Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Mon, 3 Apr 2023 11:29:55 +0200 Subject: [PATCH 3917/5631] ksmbd: set NegotiateContextCount once instead of every inc There are no early returns, so marshalling the incremented NegotiateContextCount with every context is unnecessary. Signed-off-by: David Disseldorp Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 67b7e766a06b..bc6bf6f3f609 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -817,7 +817,6 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, "assemble SMB2_PREAUTH_INTEGRITY_CAPABILITIES context\n"); build_preauth_ctxt((struct smb2_preauth_neg_context *)pneg_ctxt, conn->preauth_info->Preauth_HashId); - rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING); ctxt_size = sizeof(struct smb2_preauth_neg_context); /* Round to 8 byte boundary */ @@ -829,7 +828,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, "assemble SMB2_ENCRYPTION_CAPABILITIES context\n"); build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt, conn->cipher_type); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_encryption_neg_context) + 2; /* Round to 8 byte boundary */ pneg_ctxt += @@ -844,7 +843,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, /* Temporarily set to SMB3_COMPRESS_NONE */ build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt, conn->compress_algorithm); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; /* Round to 8 byte boundary */ pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2, @@ -856,7 +855,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ksmbd_debug(SMB, "assemble SMB2_POSIX_EXTENSIONS_AVAILABLE context\n"); build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_posix_neg_context); /* Round to 8 byte boundary */ pneg_ctxt += round_up(sizeof(struct smb2_posix_neg_context), 8); @@ -868,10 +867,11 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, "assemble SMB2_SIGNING_CAPABILITIES context\n"); build_sign_cap_ctxt((struct smb2_signing_capabilities *)pneg_ctxt, conn->signing_algorithm); - rsp->NegotiateContextCount = cpu_to_le16(++neg_ctxt_cnt); + neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_signing_capabilities) + 2; } + rsp->NegotiateContextCount = cpu_to_le16(neg_ctxt_cnt); inc_rfc1001_len(smb2_buf_len, ctxt_size); } -- GitLab From a12a07a85aff72e19520328f78b1c64d2281a1ec Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Tue, 4 Apr 2023 00:47:48 +0200 Subject: [PATCH 3918/5631] ksmbd: avoid duplicate negotiate ctx offset increments Both pneg_ctxt and ctxt_size change in unison, with each adding the length of the previously added context, rounded up to an eight byte boundary. Drop pneg_ctxt increments and instead use the ctxt_size offset when passing output pointers to per-context helper functions. This slightly simplifies offset tracking and shaves off a few text bytes. Before (x86-64 gcc 7.5): text data bss dec hex filename 213234 8677 672 222583 36577 ksmbd.ko After: text data bss dec hex filename 213218 8677 672 222567 36567 ksmbd.ko Signed-off-by: David Disseldorp Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index bc6bf6f3f609..857809100e85 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -808,7 +808,7 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, struct smb2_negotiate_rsp *rsp, void *smb2_buf_len) { - char *pneg_ctxt = (char *)rsp + + char * const pneg_ctxt = (char *)rsp + le32_to_cpu(rsp->NegotiateContextOffset); int neg_ctxt_cnt = 1; int ctxt_size; @@ -819,21 +819,17 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, conn->preauth_info->Preauth_HashId); inc_rfc1001_len(smb2_buf_len, AUTH_GSS_PADDING); ctxt_size = sizeof(struct smb2_preauth_neg_context); - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_preauth_neg_context), 8); if (conn->cipher_type) { + /* Round to 8 byte boundary */ ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_ENCRYPTION_CAPABILITIES context\n"); - build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt, + build_encrypt_ctxt((struct smb2_encryption_neg_context *) + (pneg_ctxt + ctxt_size), conn->cipher_type); neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_encryption_neg_context) + 2; - /* Round to 8 byte boundary */ - pneg_ctxt += - round_up(sizeof(struct smb2_encryption_neg_context) + 2, - 8); } if (conn->compress_algorithm) { @@ -841,31 +837,29 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ksmbd_debug(SMB, "assemble SMB2_COMPRESSION_CAPABILITIES context\n"); /* Temporarily set to SMB3_COMPRESS_NONE */ - build_compression_ctxt((struct smb2_compression_capabilities_context *)pneg_ctxt, + build_compression_ctxt((struct smb2_compression_capabilities_context *) + (pneg_ctxt + ctxt_size), conn->compress_algorithm); neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_compression_capabilities_context) + 2, - 8); } if (conn->posix_ext_supported) { ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_POSIX_EXTENSIONS_AVAILABLE context\n"); - build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt); + build_posix_ctxt((struct smb2_posix_neg_context *) + (pneg_ctxt + ctxt_size)); neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_posix_neg_context); - /* Round to 8 byte boundary */ - pneg_ctxt += round_up(sizeof(struct smb2_posix_neg_context), 8); } if (conn->signing_negotiated) { ctxt_size = round_up(ctxt_size, 8); ksmbd_debug(SMB, "assemble SMB2_SIGNING_CAPABILITIES context\n"); - build_sign_cap_ctxt((struct smb2_signing_capabilities *)pneg_ctxt, + build_sign_cap_ctxt((struct smb2_signing_capabilities *) + (pneg_ctxt + ctxt_size), conn->signing_algorithm); neg_ctxt_cnt++; ctxt_size += sizeof(struct smb2_signing_capabilities) + 2; -- GitLab From af36c51e0e111de4e908328d49cba49de758f66e Mon Sep 17 00:00:00 2001 From: David Disseldorp Date: Tue, 4 Apr 2023 16:29:54 +0200 Subject: [PATCH 3919/5631] ksmbd: remove unused compression negotiate ctx packing build_compression_ctxt() is currently unreachable due to conn.compress_algorithm remaining zero (SMB3_COMPRESS_NONE). It appears to have been broken in a couple of subtle ways over the years: - prior to d6c9ad23b421 ("ksmbd: use the common definitions for NEGOTIATE_PROTOCOL") smb2_compression_ctx.DataLength was set to 8, which didn't account for the single CompressionAlgorithms flexible array member. - post d6c9ad23b421 smb2_compression_capabilities_context CompressionAlgorithms is a three member array, while CompressionAlgorithmCount is set to indicate only one member. assemble_neg_contexts() ctxt_size is also incorrectly incremented by sizeof(struct smb2_compression_capabilities_context) + 2, which assumes one flexible array member. Signed-off-by: David Disseldorp Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 26 ++------------------------ 1 file changed, 2 insertions(+), 24 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 857809100e85..215fea2883f6 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -756,19 +756,6 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt, pneg_ctxt->Ciphers[0] = cipher_type; } -static void build_compression_ctxt(struct smb2_compression_capabilities_context *pneg_ctxt, - __le16 comp_algo) -{ - pneg_ctxt->ContextType = SMB2_COMPRESSION_CAPABILITIES; - pneg_ctxt->DataLength = - cpu_to_le16(sizeof(struct smb2_compression_capabilities_context) - - sizeof(struct smb2_neg_context)); - pneg_ctxt->Reserved = cpu_to_le32(0); - pneg_ctxt->CompressionAlgorithmCount = cpu_to_le16(1); - pneg_ctxt->Flags = cpu_to_le32(0); - pneg_ctxt->CompressionAlgorithms[0] = comp_algo; -} - static void build_sign_cap_ctxt(struct smb2_signing_capabilities *pneg_ctxt, __le16 sign_algo) { @@ -832,17 +819,8 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, ctxt_size += sizeof(struct smb2_encryption_neg_context) + 2; } - if (conn->compress_algorithm) { - ctxt_size = round_up(ctxt_size, 8); - ksmbd_debug(SMB, - "assemble SMB2_COMPRESSION_CAPABILITIES context\n"); - /* Temporarily set to SMB3_COMPRESS_NONE */ - build_compression_ctxt((struct smb2_compression_capabilities_context *) - (pneg_ctxt + ctxt_size), - conn->compress_algorithm); - neg_ctxt_cnt++; - ctxt_size += sizeof(struct smb2_compression_capabilities_context) + 2; - } + /* compression context not yet supported */ + WARN_ON(conn->compress_algorithm != SMB3_COMPRESS_NONE); if (conn->posix_ext_supported) { ctxt_size = round_up(ctxt_size, 8); -- GitLab From 74d7970febf7e9005375aeda0df821d2edffc9f7 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Fri, 21 Apr 2023 16:09:01 +0900 Subject: [PATCH 3920/5631] ksmbd: fix racy issue from using ->d_parent and ->d_name Al pointed out that ksmbd has racy issue from using ->d_parent and ->d_name in ksmbd_vfs_unlink and smb2_vfs_rename(). and use new lock_rename_child() to lock stable parent while underlying rename racy. Introduce vfs_path_parent_lookup helper to avoid out of share access and export vfs functions like the following ones to use vfs_path_parent_lookup(). - rename __lookup_hash() to lookup_one_qstr_excl(). - export lookup_one_qstr_excl(). - export getname_kernel() and putname(). vfs_path_parent_lookup() is used for parent lookup of destination file using absolute pathname given from FILE_RENAME_INFORMATION request. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 147 ++++---------- fs/ksmbd/vfs.c | 435 ++++++++++++++++++------------------------ fs/ksmbd/vfs.h | 19 +- fs/ksmbd/vfs_cache.c | 5 +- fs/namei.c | 57 ++++-- include/linux/namei.h | 6 + 6 files changed, 283 insertions(+), 386 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 215fea2883f6..bbc9e92935fb 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2408,7 +2408,7 @@ static int smb2_creat(struct ksmbd_work *work, struct path *path, char *name, return rc; } - rc = ksmbd_vfs_kern_path(work, name, 0, path, 0); + rc = ksmbd_vfs_kern_path_locked(work, name, 0, path, 0); if (rc) { pr_err("cannot get linux path (%s), err = %d\n", name, rc); @@ -2699,8 +2699,10 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, 1); + rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS, &path, 1); if (!rc) { + file_present = true; + if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { /* * If file exists with under flags, return access @@ -2709,7 +2711,6 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateDisposition == FILE_OVERWRITE_IF_LE || req->CreateDisposition == FILE_OPEN_IF_LE) { rc = -EACCES; - path_put(&path); goto err_out; } @@ -2717,26 +2718,23 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "User does not have write permission\n"); rc = -EACCES; - path_put(&path); goto err_out; } } else if (d_is_symlink(path.dentry)) { rc = -EACCES; - path_put(&path); goto err_out; } - } - if (rc) { + file_present = true; + idmap = mnt_idmap(path.mnt); + } else { if (rc != -ENOENT) goto err_out; ksmbd_debug(SMB, "can not get linux path for %s, rc = %d\n", name, rc); rc = 0; - } else { - file_present = true; - idmap = mnt_idmap(path.mnt); } + if (stream_name) { if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { if (s_type == DATA_STREAM) { @@ -2864,8 +2862,9 @@ int smb2_open(struct ksmbd_work *work) if ((daccess & FILE_DELETE_LE) || (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE)) { - rc = ksmbd_vfs_may_delete(idmap, - path.dentry); + rc = inode_permission(idmap, + d_inode(path.dentry->d_parent), + MAY_EXEC | MAY_WRITE); if (rc) goto err_out; } @@ -3236,10 +3235,13 @@ int smb2_open(struct ksmbd_work *work) } err_out: - if (file_present || created) - path_put(&path); + if (file_present || created) { + inode_unlock(d_inode(path.dentry->d_parent)); + dput(path.dentry); + } ksmbd_revert_fsids(work); err_out1: + if (rc) { if (rc == -EINVAL) rsp->hdr.Status = STATUS_INVALID_PARAMETER; @@ -5390,44 +5392,19 @@ int smb2_echo(struct ksmbd_work *work) static int smb2_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - struct mnt_idmap *idmap, struct smb2_file_rename_info *file_info, struct nls_table *local_nls) { struct ksmbd_share_config *share = fp->tcon->share_conf; - char *new_name = NULL, *abs_oldname = NULL, *old_name = NULL; - char *pathname = NULL; - struct path path; - bool file_present = true; - int rc; + char *new_name = NULL; + int rc, flags = 0; ksmbd_debug(SMB, "setting FILE_RENAME_INFO\n"); - pathname = kmalloc(PATH_MAX, GFP_KERNEL); - if (!pathname) - return -ENOMEM; - - abs_oldname = file_path(fp->filp, pathname, PATH_MAX); - if (IS_ERR(abs_oldname)) { - rc = -EINVAL; - goto out; - } - old_name = strrchr(abs_oldname, '/'); - if (old_name && old_name[1] != '\0') { - old_name++; - } else { - ksmbd_debug(SMB, "can't get last component in path %s\n", - abs_oldname); - rc = -ENOENT; - goto out; - } - new_name = smb2_get_name(file_info->FileName, le32_to_cpu(file_info->FileNameLength), local_nls); - if (IS_ERR(new_name)) { - rc = PTR_ERR(new_name); - goto out; - } + if (IS_ERR(new_name)) + return PTR_ERR(new_name); if (strchr(new_name, ':')) { int s_type; @@ -5453,7 +5430,7 @@ static int smb2_rename(struct ksmbd_work *work, if (rc) goto out; - rc = ksmbd_vfs_setxattr(idmap, + rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp), fp->filp->f_path.dentry, xattr_stream_name, NULL, 0, 0); @@ -5468,47 +5445,18 @@ static int smb2_rename(struct ksmbd_work *work, } ksmbd_debug(SMB, "new name %s\n", new_name); - rc = ksmbd_vfs_kern_path(work, new_name, LOOKUP_NO_SYMLINKS, &path, 1); - if (rc) { - if (rc != -ENOENT) - goto out; - file_present = false; - } else { - path_put(&path); - } - if (ksmbd_share_veto_filename(share, new_name)) { rc = -ENOENT; ksmbd_debug(SMB, "Can't rename vetoed file: %s\n", new_name); goto out; } - if (file_info->ReplaceIfExists) { - if (file_present) { - rc = ksmbd_vfs_remove_file(work, new_name); - if (rc) { - if (rc != -ENOTEMPTY) - rc = -EINVAL; - ksmbd_debug(SMB, "cannot delete %s, rc %d\n", - new_name, rc); - goto out; - } - } - } else { - if (file_present && - strncmp(old_name, path.dentry->d_name.name, strlen(old_name))) { - rc = -EEXIST; - ksmbd_debug(SMB, - "cannot rename already existing file\n"); - goto out; - } - } + if (!file_info->ReplaceIfExists) + flags = RENAME_NOREPLACE; - rc = ksmbd_vfs_fp_rename(work, fp, new_name); + rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags); out: - kfree(pathname); - if (!IS_ERR(new_name)) - kfree(new_name); + kfree(new_name); return rc; } @@ -5548,18 +5496,17 @@ static int smb2_create_link(struct ksmbd_work *work, } ksmbd_debug(SMB, "target name is %s\n", target_name); - rc = ksmbd_vfs_kern_path(work, link_name, LOOKUP_NO_SYMLINKS, &path, 0); + rc = ksmbd_vfs_kern_path_locked(work, link_name, LOOKUP_NO_SYMLINKS, + &path, 0); if (rc) { if (rc != -ENOENT) goto out; file_present = false; - } else { - path_put(&path); } if (file_info->ReplaceIfExists) { if (file_present) { - rc = ksmbd_vfs_remove_file(work, link_name); + rc = ksmbd_vfs_remove_file(work, &path); if (rc) { rc = -EINVAL; ksmbd_debug(SMB, "cannot delete %s\n", @@ -5579,6 +5526,10 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) rc = -EINVAL; out: + if (file_present) { + inode_unlock(d_inode(path.dentry->d_parent)); + path_put(&path); + } if (!IS_ERR(link_name)) kfree(link_name); kfree(pathname); @@ -5756,12 +5707,6 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, struct smb2_file_rename_info *rename_info, unsigned int buf_len) { - struct mnt_idmap *idmap; - struct ksmbd_file *parent_fp; - struct dentry *parent; - struct dentry *dentry = fp->filp->f_path.dentry; - int ret; - if (!(fp->daccess & FILE_DELETE_LE)) { pr_err("no right to delete : 0x%x\n", fp->daccess); return -EACCES; @@ -5771,32 +5716,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, le32_to_cpu(rename_info->FileNameLength)) return -EINVAL; - idmap = file_mnt_idmap(fp->filp); - if (ksmbd_stream_fd(fp)) - goto next; - - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); - if (ret) { - dput(parent); - return ret; - } - - parent_fp = ksmbd_lookup_fd_inode(d_inode(parent)); - inode_unlock(d_inode(parent)); - dput(parent); + if (!le32_to_cpu(rename_info->FileNameLength)) + return -EINVAL; - if (parent_fp) { - if (parent_fp->daccess & FILE_DELETE_LE) { - pr_err("parent dir is opened with delete access\n"); - ksmbd_fd_put(work, parent_fp); - return -ESHARE; - } - ksmbd_fd_put(work, parent_fp); - } -next: - return smb2_rename(work, fp, idmap, rename_info, - work->conn->local_nls); + return smb2_rename(work, fp, rename_info, work->conn->local_nls); } static int set_file_disposition_info(struct ksmbd_file *fp, diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index cef07d7fb7dc..778c152708e4 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "glob.h" #include "oplock.h" @@ -35,19 +36,6 @@ #include "mgmt/user_session.h" #include "mgmt/user_config.h" -static char *extract_last_component(char *path) -{ - char *p = strrchr(path, '/'); - - if (p && p[1] != '\0') { - *p = '\0'; - p++; - } else { - p = NULL; - } - return p; -} - static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, struct inode *parent_inode, struct inode *inode) @@ -61,65 +49,77 @@ static void ksmbd_vfs_inherit_owner(struct ksmbd_work *work, /** * ksmbd_vfs_lock_parent() - lock parent dentry if it is stable - * - * the parent dentry got by dget_parent or @parent could be - * unstable, we try to lock a parent inode and lookup the - * child dentry again. - * - * the reference count of @parent isn't incremented. */ -int ksmbd_vfs_lock_parent(struct mnt_idmap *idmap, struct dentry *parent, - struct dentry *child) +int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child) { - struct dentry *dentry; - int ret = 0; - inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); - dentry = lookup_one(idmap, child->d_name.name, parent, - child->d_name.len); - if (IS_ERR(dentry)) { - ret = PTR_ERR(dentry); - goto out_err; - } - - if (dentry != child) { - ret = -ESTALE; - dput(dentry); - goto out_err; + if (child->d_parent != parent) { + inode_unlock(d_inode(parent)); + return -ENOENT; } - dput(dentry); return 0; -out_err: - inode_unlock(d_inode(parent)); - return ret; } -int ksmbd_vfs_may_delete(struct mnt_idmap *idmap, - struct dentry *dentry) +static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, + char *pathname, unsigned int flags, + struct path *path) { - struct dentry *parent; - int ret; + struct qstr last; + struct filename *filename; + struct path *root_share_path = &share_conf->vfs_path; + int err, type; + struct path parent_path; + struct dentry *d; + + if (pathname[0] == '\0') { + pathname = share_conf->path; + root_share_path = NULL; + } else { + flags |= LOOKUP_BENEATH; + } - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); - if (ret) { - dput(parent); - return ret; + filename = getname_kernel(pathname); + if (IS_ERR(filename)) + return PTR_ERR(filename); + + err = vfs_path_parent_lookup(filename, flags, + &parent_path, &last, &type, + root_share_path); + putname(filename); + if (err) + return err; + + if (unlikely(type != LAST_NORM)) { + path_put(&parent_path); + return -ENOENT; } - ret = inode_permission(idmap, d_inode(parent), - MAY_EXEC | MAY_WRITE); + inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT); + d = lookup_one_qstr_excl(&last, parent_path.dentry, 0); + if (IS_ERR(d)) + goto err_out; - inode_unlock(d_inode(parent)); - dput(parent); - return ret; + if (d_is_negative(d)) { + dput(d); + goto err_out; + } + + path->dentry = d; + path->mnt = share_conf->vfs_path.mnt; + path_put(&parent_path); + + return 0; + +err_out: + inode_unlock(parent_path.dentry->d_inode); + path_put(&parent_path); + return -ENOENT; } int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap, struct dentry *dentry, __le32 *daccess) { - struct dentry *parent; int ret = 0; *daccess = cpu_to_le32(FILE_READ_ATTRIBUTES | READ_CONTROL); @@ -136,18 +136,9 @@ int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap, if (!inode_permission(idmap, d_inode(dentry), MAY_OPEN | MAY_EXEC)) *daccess |= FILE_EXECUTE_LE; - parent = dget_parent(dentry); - ret = ksmbd_vfs_lock_parent(idmap, parent, dentry); - if (ret) { - dput(parent); - return ret; - } - - if (!inode_permission(idmap, d_inode(parent), MAY_EXEC | MAY_WRITE)) + if (!inode_permission(idmap, d_inode(dentry->d_parent), MAY_EXEC | MAY_WRITE)) *daccess |= FILE_DELETE_LE; - inode_unlock(d_inode(parent)); - dput(parent); return ret; } @@ -580,54 +571,32 @@ int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id) * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name) +int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) { struct mnt_idmap *idmap; - struct path path; - struct dentry *parent; + struct dentry *parent = path->dentry->d_parent; int err; if (ksmbd_override_fsids(work)) return -ENOMEM; - err = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, false); - if (err) { - ksmbd_debug(VFS, "can't get %s, err %d\n", name, err); - ksmbd_revert_fsids(work); - return err; - } - - idmap = mnt_idmap(path.mnt); - parent = dget_parent(path.dentry); - err = ksmbd_vfs_lock_parent(idmap, parent, path.dentry); - if (err) { - dput(parent); - path_put(&path); - ksmbd_revert_fsids(work); - return err; - } - - if (!d_inode(path.dentry)->i_nlink) { + if (!d_inode(path->dentry)->i_nlink) { err = -ENOENT; goto out_err; } - if (S_ISDIR(d_inode(path.dentry)->i_mode)) { - err = vfs_rmdir(idmap, d_inode(parent), path.dentry); + idmap = mnt_idmap(path->mnt); + if (S_ISDIR(d_inode(path->dentry)->i_mode)) { + err = vfs_rmdir(idmap, d_inode(parent), path->dentry); if (err && err != -ENOTEMPTY) - ksmbd_debug(VFS, "%s: rmdir failed, err %d\n", name, - err); + ksmbd_debug(VFS, "rmdir failed, err %d\n", err); } else { - err = vfs_unlink(idmap, d_inode(parent), path.dentry, NULL); + err = vfs_unlink(idmap, d_inode(parent), path->dentry, NULL); if (err) - ksmbd_debug(VFS, "%s: unlink failed, err %d\n", name, - err); + ksmbd_debug(VFS, "unlink failed, err %d\n", err); } out_err: - inode_unlock(d_inode(parent)); - dput(parent); - path_put(&path); ksmbd_revert_fsids(work); return err; } @@ -686,149 +655,114 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, return err; } -static int ksmbd_validate_entry_in_use(struct dentry *src_dent) +int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, + char *newname, int flags) { - struct dentry *dst_dent; - - spin_lock(&src_dent->d_lock); - list_for_each_entry(dst_dent, &src_dent->d_subdirs, d_child) { - struct ksmbd_file *child_fp; + struct dentry *old_parent, *new_dentry, *trap; + struct dentry *old_child = old_path->dentry; + struct path new_path; + struct qstr new_last; + struct renamedata rd; + struct filename *to; + struct ksmbd_share_config *share_conf = work->tcon->share_conf; + struct ksmbd_file *parent_fp; + int new_type; + int err, lookup_flags = LOOKUP_NO_SYMLINKS; - if (d_really_is_negative(dst_dent)) - continue; + if (ksmbd_override_fsids(work)) + return -ENOMEM; - child_fp = ksmbd_lookup_fd_inode(d_inode(dst_dent)); - if (child_fp) { - spin_unlock(&src_dent->d_lock); - ksmbd_debug(VFS, "Forbid rename, sub file/dir is in use\n"); - return -EACCES; - } + to = getname_kernel(newname); + if (IS_ERR(to)) { + err = PTR_ERR(to); + goto revert_fsids; } - spin_unlock(&src_dent->d_lock); - return 0; -} +retry: + err = vfs_path_parent_lookup(to, lookup_flags | LOOKUP_BENEATH, + &new_path, &new_last, &new_type, + &share_conf->vfs_path); + if (err) + goto out1; -static int __ksmbd_vfs_rename(struct ksmbd_work *work, - struct mnt_idmap *src_idmap, - struct dentry *src_dent_parent, - struct dentry *src_dent, - struct mnt_idmap *dst_idmap, - struct dentry *dst_dent_parent, - struct dentry *trap_dent, - char *dst_name) -{ - struct dentry *dst_dent; - int err; + if (old_path->mnt != new_path.mnt) { + err = -EXDEV; + goto out2; + } - if (!work->tcon->posix_extensions) { - err = ksmbd_validate_entry_in_use(src_dent); - if (err) - return err; + trap = lock_rename_child(old_child, new_path.dentry); + + old_parent = dget(old_child->d_parent); + if (d_unhashed(old_child)) { + err = -EINVAL; + goto out3; } - if (d_really_is_negative(src_dent_parent)) - return -ENOENT; - if (d_really_is_negative(dst_dent_parent)) - return -ENOENT; - if (d_really_is_negative(src_dent)) - return -ENOENT; - if (src_dent == trap_dent) - return -EINVAL; + parent_fp = ksmbd_lookup_fd_inode(d_inode(old_child->d_parent)); + if (parent_fp) { + if (parent_fp->daccess & FILE_DELETE_LE) { + pr_err("parent dir is opened with delete access\n"); + err = -ESHARE; + ksmbd_fd_put(work, parent_fp); + goto out3; + } + ksmbd_fd_put(work, parent_fp); + } - if (ksmbd_override_fsids(work)) - return -ENOMEM; + new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, + lookup_flags | LOOKUP_RENAME_TARGET); + if (IS_ERR(new_dentry)) { + err = PTR_ERR(new_dentry); + goto out3; + } - dst_dent = lookup_one(dst_idmap, dst_name, - dst_dent_parent, strlen(dst_name)); - err = PTR_ERR(dst_dent); - if (IS_ERR(dst_dent)) { - pr_err("lookup failed %s [%d]\n", dst_name, err); - goto out; + if (d_is_symlink(new_dentry)) { + err = -EACCES; + goto out4; } - err = -ENOTEMPTY; - if (dst_dent != trap_dent && !d_really_is_positive(dst_dent)) { - struct renamedata rd = { - .old_mnt_idmap = src_idmap, - .old_dir = d_inode(src_dent_parent), - .old_dentry = src_dent, - .new_mnt_idmap = dst_idmap, - .new_dir = d_inode(dst_dent_parent), - .new_dentry = dst_dent, - }; - err = vfs_rename(&rd); + if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) { + err = -EEXIST; + goto out4; } - if (err) - pr_err("vfs_rename failed err %d\n", err); - if (dst_dent) - dput(dst_dent); -out: - ksmbd_revert_fsids(work); - return err; -} -int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - char *newname) -{ - struct mnt_idmap *idmap; - struct path dst_path; - struct dentry *src_dent_parent, *dst_dent_parent; - struct dentry *src_dent, *trap_dent, *src_child; - char *dst_name; - int err; + if (old_child == trap) { + err = -EINVAL; + goto out4; + } - dst_name = extract_last_component(newname); - if (!dst_name) { - dst_name = newname; - newname = ""; + if (new_dentry == trap) { + err = -ENOTEMPTY; + goto out4; } - src_dent_parent = dget_parent(fp->filp->f_path.dentry); - src_dent = fp->filp->f_path.dentry; + rd.old_mnt_idmap = mnt_idmap(old_path->mnt), + rd.old_dir = d_inode(old_parent), + rd.old_dentry = old_child, + rd.new_mnt_idmap = mnt_idmap(new_path.mnt), + rd.new_dir = new_path.dentry->d_inode, + rd.new_dentry = new_dentry, + rd.flags = flags, + err = vfs_rename(&rd); + if (err) + ksmbd_debug(VFS, "vfs_rename failed err %d\n", err); - err = ksmbd_vfs_kern_path(work, newname, - LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY, - &dst_path, false); - if (err) { - ksmbd_debug(VFS, "Cannot get path for %s [%d]\n", newname, err); - goto out; +out4: + dput(new_dentry); +out3: + dput(old_parent); + unlock_rename(old_parent, new_path.dentry); +out2: + path_put(&new_path); + + if (retry_estale(err, lookup_flags)) { + lookup_flags |= LOOKUP_REVAL; + goto retry; } - dst_dent_parent = dst_path.dentry; - - trap_dent = lock_rename(src_dent_parent, dst_dent_parent); - dget(src_dent); - dget(dst_dent_parent); - idmap = file_mnt_idmap(fp->filp); - src_child = lookup_one(idmap, src_dent->d_name.name, src_dent_parent, - src_dent->d_name.len); - if (IS_ERR(src_child)) { - err = PTR_ERR(src_child); - goto out_lock; - } - - if (src_child != src_dent) { - err = -ESTALE; - dput(src_child); - goto out_lock; - } - dput(src_child); - - err = __ksmbd_vfs_rename(work, - idmap, - src_dent_parent, - src_dent, - mnt_idmap(dst_path.mnt), - dst_dent_parent, - trap_dent, - dst_name); -out_lock: - dput(src_dent); - dput(dst_dent_parent); - unlock_rename(src_dent_parent, dst_dent_parent); - path_put(&dst_path); -out: - dput(src_dent_parent); +out1: + putname(to); +revert_fsids: + ksmbd_revert_fsids(work); return err; } @@ -1079,14 +1013,16 @@ int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, return vfs_removexattr(idmap, dentry, attr_name); } -int ksmbd_vfs_unlink(struct mnt_idmap *idmap, - struct dentry *dir, struct dentry *dentry) +int ksmbd_vfs_unlink(struct file *filp) { int err = 0; + struct dentry *dir, *dentry = filp->f_path.dentry; + struct mnt_idmap *idmap = file_mnt_idmap(filp); - err = ksmbd_vfs_lock_parent(idmap, dir, dentry); + dir = dget_parent(dentry); + err = ksmbd_vfs_lock_parent(dir, dentry); if (err) - return err; + goto out; dget(dentry); if (S_ISDIR(d_inode(dentry)->i_mode)) @@ -1098,6 +1034,8 @@ int ksmbd_vfs_unlink(struct mnt_idmap *idmap, inode_unlock(d_inode(dir)); if (err) ksmbd_debug(VFS, "failed to delete, err %d\n", err); +out: + dput(dir); return err; } @@ -1200,7 +1138,7 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name, } /** - * ksmbd_vfs_kern_path() - lookup a file and get path info + * ksmbd_vfs_kern_path_locked() - lookup a file and get path info * @name: file path that is relative to share * @flags: lookup flags * @path: if lookup succeed, return path info @@ -1208,24 +1146,20 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name, * * Return: 0 on success, otherwise error */ -int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, - unsigned int flags, struct path *path, bool caseless) +int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, + unsigned int flags, struct path *path, + bool caseless) { struct ksmbd_share_config *share_conf = work->tcon->share_conf; int err; + struct path parent_path; - flags |= LOOKUP_BENEATH; - err = vfs_path_lookup(share_conf->vfs_path.dentry, - share_conf->vfs_path.mnt, - name, - flags, - path); + err = ksmbd_vfs_path_lookup_locked(share_conf, name, flags, path); if (!err) - return 0; + return err; if (caseless) { char *filepath; - struct path parent; size_t path_len, remain_len; filepath = kstrdup(name, GFP_KERNEL); @@ -1235,10 +1169,10 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, path_len = strlen(filepath); remain_len = path_len; - parent = share_conf->vfs_path; - path_get(&parent); + parent_path = share_conf->vfs_path; + path_get(&parent_path); - while (d_can_lookup(parent.dentry)) { + while (d_can_lookup(parent_path.dentry)) { char *filename = filepath + path_len - remain_len; char *next = strchrnul(filename, '/'); size_t filename_len = next - filename; @@ -1247,12 +1181,11 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, if (filename_len == 0) break; - err = ksmbd_vfs_lookup_in_dir(&parent, filename, + err = ksmbd_vfs_lookup_in_dir(&parent_path, filename, filename_len, work->conn->um); - path_put(&parent); if (err) - goto out; + goto out2; next[0] = '\0'; @@ -1260,23 +1193,31 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *name, share_conf->vfs_path.mnt, filepath, flags, - &parent); + path); if (err) - goto out; - else if (is_last) { - *path = parent; - goto out; - } + goto out2; + else if (is_last) + goto out1; + path_put(&parent_path); + parent_path = *path; next[0] = '/'; remain_len -= filename_len + 1; } - path_put(&parent); err = -EINVAL; -out: +out2: + path_put(&parent_path); +out1: kfree(filepath); } + + if (!err) { + err = ksmbd_vfs_lock_parent(parent_path.dentry, path->dentry); + if (err) + dput(path->dentry); + path_put(&parent_path); + } return err; } diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index 9d676ab0cd25..a4ae89f3230d 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -71,9 +71,7 @@ struct ksmbd_kstat { __le32 file_attributes; }; -int ksmbd_vfs_lock_parent(struct mnt_idmap *idmap, struct dentry *parent, - struct dentry *child); -int ksmbd_vfs_may_delete(struct mnt_idmap *idmap, struct dentry *dentry); +int ksmbd_vfs_lock_parent(struct dentry *parent, struct dentry *child); int ksmbd_vfs_query_maximal_access(struct mnt_idmap *idmap, struct dentry *dentry, __le32 *daccess); int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode); @@ -84,12 +82,12 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, char *buf, size_t count, loff_t *pos, bool sync, ssize_t *written); int ksmbd_vfs_fsync(struct ksmbd_work *work, u64 fid, u64 p_id); -int ksmbd_vfs_remove_file(struct ksmbd_work *work, char *name); +int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path); int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, const char *newname); int ksmbd_vfs_getattr(const struct path *path, struct kstat *stat); -int ksmbd_vfs_fp_rename(struct ksmbd_work *work, struct ksmbd_file *fp, - char *newname); +int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, + char *newname, int flags); int ksmbd_vfs_truncate(struct ksmbd_work *work, struct ksmbd_file *fp, loff_t size); struct srv_copychunk; @@ -116,9 +114,9 @@ int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, struct dentry *dentry, char *attr_name); -int ksmbd_vfs_kern_path(struct ksmbd_work *work, - char *name, unsigned int flags, struct path *path, - bool caseless); +int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, + unsigned int flags, struct path *path, + bool caseless); struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, @@ -131,8 +129,7 @@ struct file_allocated_range_buffer; int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, struct file_allocated_range_buffer *ranges, unsigned int in_count, unsigned int *out_count); -int ksmbd_vfs_unlink(struct mnt_idmap *idmap, struct dentry *dir, - struct dentry *dentry); +int ksmbd_vfs_unlink(struct file *filp); void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat); int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct mnt_idmap *idmap, diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index 054a7d2e0f48..2d0138e72d78 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -244,7 +244,6 @@ void ksmbd_release_inode_hash(void) static void __ksmbd_inode_close(struct ksmbd_file *fp) { - struct dentry *dir, *dentry; struct ksmbd_inode *ci = fp->f_ci; int err; struct file *filp; @@ -263,11 +262,9 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) if (atomic_dec_and_test(&ci->m_count)) { write_lock(&ci->m_lock); if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_PENDING)) { - dentry = filp->f_path.dentry; - dir = dentry->d_parent; ci->m_flags &= ~(S_DEL_ON_CLS | S_DEL_PENDING); write_unlock(&ci->m_lock); - ksmbd_vfs_unlink(file_mnt_idmap(filp), dir, dentry); + ksmbd_vfs_unlink(filp); write_lock(&ci->m_lock); } write_unlock(&ci->m_lock); diff --git a/fs/namei.c b/fs/namei.c index 6bc1964e2214..c1d59ae5af83 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -254,6 +254,7 @@ getname_kernel(const char * filename) return result; } +EXPORT_SYMBOL(getname_kernel); void putname(struct filename *name) { @@ -271,6 +272,7 @@ void putname(struct filename *name) } else __putname(name); } +EXPORT_SYMBOL(putname); /** * check_acl - perform ACL permission checking @@ -1581,8 +1583,9 @@ static struct dentry *lookup_dcache(const struct qstr *name, * when directory is guaranteed to have no in-lookup children * at all. */ -static struct dentry *__lookup_hash(const struct qstr *name, - struct dentry *base, unsigned int flags) +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; @@ -1606,6 +1609,7 @@ static struct dentry *__lookup_hash(const struct qstr *name, } return dentry; } +EXPORT_SYMBOL(lookup_one_qstr_excl); static struct dentry *lookup_fast(struct nameidata *nd) { @@ -2532,16 +2536,17 @@ static int path_parentat(struct nameidata *nd, unsigned flags, } /* Note: this does not consume "name" */ -static int filename_parentat(int dfd, struct filename *name, - unsigned int flags, struct path *parent, - struct qstr *last, int *type) +static int __filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type, + const struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); - set_nameidata(&nd, dfd, name, NULL); + set_nameidata(&nd, dfd, name, root); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); @@ -2556,6 +2561,13 @@ static int filename_parentat(int dfd, struct filename *name, return retval; } +static int filename_parentat(int dfd, struct filename *name, + unsigned int flags, struct path *parent, + struct qstr *last, int *type) +{ + return __filename_parentat(dfd, name, flags, parent, last, type, NULL); +} + /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(struct filename *name, struct path *path) { @@ -2571,7 +2583,7 @@ static struct dentry *__kern_path_locked(struct filename *name, struct path *pat return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - d = __lookup_hash(&last, path->dentry, 0); + d = lookup_one_qstr_excl(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); @@ -2599,6 +2611,24 @@ int kern_path(const char *name, unsigned int flags, struct path *path) } EXPORT_SYMBOL(kern_path); +/** + * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair + * @filename: filename structure + * @flags: lookup flags + * @parent: pointer to struct path to fill + * @last: last component + * @type: type of the last component + * @root: pointer to struct path of the base directory + */ +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root) +{ + return __filename_parentat(AT_FDCWD, filename, flags, parent, last, + type, root); +} +EXPORT_SYMBOL(vfs_path_parent_lookup); + /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory @@ -3852,7 +3882,8 @@ static struct dentry *filename_create(int dfd, struct filename *name, if (last.name[last.len] && !want_dir) create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); + dentry = lookup_one_qstr_excl(&last, path->dentry, + reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -4212,7 +4243,7 @@ int do_rmdir(int dfd, struct filename *name) goto exit2; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit3; @@ -4345,7 +4376,7 @@ int do_unlinkat(int dfd, struct filename *name) goto exit2; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path.dentry, lookup_flags); + dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { @@ -4909,7 +4940,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd, retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); - old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); + old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry, + lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; @@ -4917,7 +4949,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd, error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; - new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); + new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry, + lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; diff --git a/include/linux/namei.h b/include/linux/namei.h index 5864e4d82e56..1463cbda4888 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,12 +57,18 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); -- GitLab From fae65ef3a148079103ae935107c62f7830ab52c5 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 28 Mar 2023 10:45:49 +0200 Subject: [PATCH 3921/5631] xen/pciback: don't call pcistub_device_put() under lock pcistub_device_put() shouldn't be called under spinlock, as it can sleep. For this reason pcistub_device_get_pci_dev() needs to be modified: instead of always calling pcistub_device_get() just do the call of pcistub_device_get() only if it is really needed. This removes the need to call pcistub_device_put(). Reported-by: Dan Carpenter Link: https://lore.kernel.org/lkml/Y+JUIl64UDmdkboh@kadam/ Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Link: https://lore.kernel.org/r/20230328084549.20695-1-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/xen/xen-pciback/pci_stub.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index bba527620507..e34b623e4b41 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -194,8 +194,6 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *pci_dev = NULL; unsigned long flags; - pcistub_device_get(psdev); - spin_lock_irqsave(&psdev->lock, flags); if (!psdev->pdev) { psdev->pdev = pdev; @@ -203,8 +201,8 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, } spin_unlock_irqrestore(&psdev->lock, flags); - if (!pci_dev) - pcistub_device_put(psdev); + if (pci_dev) + pcistub_device_get(psdev); return pci_dev; } -- GitLab From b2c042cc802fe96d431821bf1cf2f0f04a3eda7d Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 28 Mar 2023 10:46:02 +0200 Subject: [PATCH 3922/5631] xen/scsiback: don't call scsiback_free_translation_entry() under lock scsiback_free_translation_entry() shouldn't be called under spinlock, as it can sleep. This requires to split removing a translation entry from the v2p list from actually calling kref_put() for the entry. Reported-by: Dan Carpenter Link: https://lore.kernel.org/lkml/Y+JUIl64UDmdkboh@kadam/ Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Link: https://lore.kernel.org/r/20230328084602.20729-1-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/xen/xen-scsiback.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 954188b0b858..294f29cdc7aa 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1010,12 +1010,6 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, return err; } -static void __scsiback_del_translation_entry(struct v2p_entry *entry) -{ - list_del(&entry->l); - kref_put(&entry->kref, scsiback_free_translation_entry); -} - /* Delete the translation entry specified */ @@ -1024,18 +1018,20 @@ static int scsiback_del_translation_entry(struct vscsibk_info *info, { struct v2p_entry *entry; unsigned long flags; - int ret = 0; spin_lock_irqsave(&info->v2p_lock, flags); /* Find out the translation entry specified */ entry = scsiback_chk_translation_entry(info, v); if (entry) - __scsiback_del_translation_entry(entry); - else - ret = -ENOENT; + list_del(&entry->l); spin_unlock_irqrestore(&info->v2p_lock, flags); - return ret; + + if (!entry) + return -ENOENT; + + kref_put(&entry->kref, scsiback_free_translation_entry); + return 0; } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, @@ -1239,14 +1235,19 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info) { struct v2p_entry *entry, *tmp; struct list_head *head = &(info->v2p_entry_lists); + struct list_head tmp_list; unsigned long flags; spin_lock_irqsave(&info->v2p_lock, flags); - list_for_each_entry_safe(entry, tmp, head, l) - __scsiback_del_translation_entry(entry); + list_cut_before(&tmp_list, head, head); spin_unlock_irqrestore(&info->v2p_lock, flags); + + list_for_each_entry_safe(entry, tmp, &tmp_list, l) { + list_del(&entry->l); + kref_put(&entry->kref, scsiback_free_translation_entry); + } } static void scsiback_remove(struct xenbus_device *dev) -- GitLab From c66bb48edd58c3a22072b4f68312c225dc1b0009 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 3 Apr 2023 11:27:11 +0200 Subject: [PATCH 3923/5631] xen/pvcalls: don't call bind_evtchn_to_irqhandler() under lock bind_evtchn_to_irqhandler() shouldn't be called under spinlock, as it can sleep. This requires to move the calls of create_active() out of the locked regions. This is no problem, as the worst which could happen would be a spurious call of the interrupt handler, causing a spurious wake_up(). Reported-by: Dan Carpenter Link: https://lore.kernel.org/lkml/Y+JUIl64UDmdkboh@kadam/ Signed-off-by: Juergen Gross Reviewed-by: Oleksandr Tyshchenko Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/20230403092711.15285-1-jgross@suse.com Signed-off-by: Juergen Gross --- drivers/xen/pvcalls-front.c | 46 +++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 20 deletions(-) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index d5d589bda243..b72ee9379d77 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -227,22 +227,30 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) static void free_active_ring(struct sock_mapping *map); -static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, - struct sock_mapping *map) +static void pvcalls_front_destroy_active(struct pvcalls_bedata *bedata, + struct sock_mapping *map) { int i; unbind_from_irqhandler(map->active.irq, map); - spin_lock(&bedata->socket_lock); - if (!list_empty(&map->list)) - list_del_init(&map->list); - spin_unlock(&bedata->socket_lock); + if (bedata) { + spin_lock(&bedata->socket_lock); + if (!list_empty(&map->list)) + list_del_init(&map->list); + spin_unlock(&bedata->socket_lock); + } for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++) gnttab_end_foreign_access(map->active.ring->ref[i], NULL); gnttab_end_foreign_access(map->active.ref, NULL); free_active_ring(map); +} + +static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, + struct sock_mapping *map) +{ + pvcalls_front_destroy_active(bedata, map); kfree(map); } @@ -433,19 +441,18 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } - - spin_lock(&bedata->socket_lock); - ret = get_request(bedata, &req_id); + ret = create_active(map, &evtchn); if (ret < 0) { - spin_unlock(&bedata->socket_lock); free_active_ring(map); pvcalls_exit_sock(sock); return ret; } - ret = create_active(map, &evtchn); + + spin_lock(&bedata->socket_lock); + ret = get_request(bedata, &req_id); if (ret < 0) { spin_unlock(&bedata->socket_lock); - free_active_ring(map); + pvcalls_front_destroy_active(NULL, map); pvcalls_exit_sock(sock); return ret; } @@ -821,28 +828,27 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) pvcalls_exit_sock(sock); return ret; } - spin_lock(&bedata->socket_lock); - ret = get_request(bedata, &req_id); + ret = create_active(map2, &evtchn); if (ret < 0) { - clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, - (void *)&map->passive.flags); - spin_unlock(&bedata->socket_lock); free_active_ring(map2); kfree(map2); + clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, + (void *)&map->passive.flags); pvcalls_exit_sock(sock); return ret; } - ret = create_active(map2, &evtchn); + spin_lock(&bedata->socket_lock); + ret = get_request(bedata, &req_id); if (ret < 0) { - free_active_ring(map2); - kfree(map2); clear_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, (void *)&map->passive.flags); spin_unlock(&bedata->socket_lock); + pvcalls_front_free_map(bedata, map2); pvcalls_exit_sock(sock); return ret; } + list_add_tail(&map2->list, &bedata->socket_mappings); req = RING_GET_REQUEST(&bedata->ring, req_id); -- GitLab From 1492c6b1874ac5ed57d8ffef89e2b5c59f804aa8 Mon Sep 17 00:00:00 2001 From: Henry Willard Date: Wed, 12 Apr 2023 15:29:53 -0600 Subject: [PATCH 3924/5631] MIPS: Don't clear _PAGE_SPECIAL in _PAGE_CHG_MASK In the special case where p = mmap(NULL, ALLOC_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, -1, 0); is followed by rc = mprotect(p, ALLOC_SIZE, PROT_NONE); the _PAGE_SPECIAL bit in the page tables will be cleared by mistake and the later unmapped operations will incorrectly modify the struct page for the the zero page. This sequence occurs in the madvise05 test of the Linux Test Project suite of tests. This was discovered while testing an older version of the kernel (5.4.17) on a MIPS device. Unfortunately, support for this device is not available in newer kernels, so I can't test this with the latest Linux kernel code. It looks like the problem exists in newer kernels, but I can't verify it. Except for the LTP test, this sequence of calls is probably not common. Passing it along in the hope it will be useful to someone. Signed-off-by: Henry Willard Signed-off-by: Thomas Bogendoerfer --- arch/mips/include/asm/pgtable-bits.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index 2362842ee2b5..1c576679aa87 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -280,6 +280,7 @@ static inline uint64_t pte_to_entrylo(unsigned long pte_val) #define __WRITEABLE (_PAGE_SILENT_WRITE | _PAGE_WRITE | _PAGE_MODIFIED) #define _PAGE_CHG_MASK (_PAGE_ACCESSED | _PAGE_MODIFIED | \ - _PAGE_SOFT_DIRTY | _PFN_MASK | _CACHE_MASK) + _PAGE_SOFT_DIRTY | _PFN_MASK | \ + _CACHE_MASK | _PAGE_SPECIAL) #endif /* _ASM_PGTABLE_BITS_H */ -- GitLab From 46e614cc91f7bd6f7872e434e6bcfda44454aac3 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Sun, 23 Apr 2023 09:38:03 +0800 Subject: [PATCH 3925/5631] MIPS: uprobes: Restore thread.trap_nr thread.trap_nr is saved in arch_uprobe_pre_xol(), it should be restored in arch_uprobe_{post,abort}_xol() accordingly, actually it was only done in the post function, just do it in the abort function too, this change is similar with x86 and powerpc. Signed-off-by: Tiezhu Yang Signed-off-by: Thomas Bogendoerfer --- arch/mips/kernel/uprobes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/kernel/uprobes.c b/arch/mips/kernel/uprobes.c index 6b630ed4438d..401b148f8917 100644 --- a/arch/mips/kernel/uprobes.c +++ b/arch/mips/kernel/uprobes.c @@ -191,6 +191,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *aup, { struct uprobe_task *utask = current->utask; + current->thread.trap_nr = utask->autask.saved_trap_nr; instruction_pointer_set(regs, utask->vaddr); } -- GitLab From d944eafed618a8507270b324ad9d5405bb7f0b3e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 18 Apr 2023 20:55:14 +0300 Subject: [PATCH 3926/5631] drm/i915: Check pipe source size when using skl+ scalers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The skl+ scalers only sample 12 bits of PIPESRC so we can't do any plane scaling at all when the pipe source size is >4k. Make sure the pipe source size is also below the scaler's src size limits. Might not be 100% accurate, but should at least be safe. We can refine the limits later if we discover that recent hw is less restricted. Cc: stable@vger.kernel.org Tested-by: Ross Zwisler Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/8357 Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20230418175528.13117-2-ville.syrjala@linux.intel.com Reviewed-by: Jani Nikula (cherry picked from commit 691248d4135fe3fae64b4ee0676bc96a7fd6950c) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/skl_scaler.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 473d53610b92..0e7e014fcc71 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -111,6 +111,8 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; + int pipe_src_w = drm_rect_width(&crtc_state->pipe_src); + int pipe_src_h = drm_rect_height(&crtc_state->pipe_src); int min_src_w, min_src_h, min_dst_w, min_dst_h; int max_src_w, max_src_h, max_dst_w, max_dst_h; @@ -207,6 +209,21 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, return -EINVAL; } + /* + * The pipe scaler does not use all the bits of PIPESRC, at least + * on the earlier platforms. So even when we're scaling a plane + * the *pipe* source size must not be too large. For simplicity + * we assume the limits match the scaler source size limits. Might + * not be 100% accurate on all platforms, but good enough for now. + */ + if (pipe_src_w > max_src_w || pipe_src_h > max_src_h) { + drm_dbg_kms(&dev_priv->drm, + "scaler_user index %u.%u: pipe src size %ux%u " + "is out of scaler range\n", + crtc->pipe, scaler_user, pipe_src_w, pipe_src_h); + return -EINVAL; + } + /* mark this plane as a scaler user in crtc_state */ scaler_state->scaler_users |= (1 << scaler_user); drm_dbg_kms(&dev_priv->drm, "scaler_user index %u.%u: " -- GitLab From 36cd9fb5344675e9b9d9f96eabcb3cdfdbacc841 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Wed, 19 Apr 2023 13:18:05 +0200 Subject: [PATCH 3927/5631] dt-bindings: leds: Add ROHM BD2606MVV LED Document ROHM BD2606MVV LED driver devicetree bindings. Signed-off-by: Andreas Kemnade Reviewed-by: Matti Vaittinen Reviewed-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230419111806.1100437-2-andreas@kemnade.info --- .../bindings/leds/rohm,bd2606mvv.yaml | 81 +++++++++++++++++++ 1 file changed, 81 insertions(+) create mode 100644 Documentation/devicetree/bindings/leds/rohm,bd2606mvv.yaml diff --git a/Documentation/devicetree/bindings/leds/rohm,bd2606mvv.yaml b/Documentation/devicetree/bindings/leds/rohm,bd2606mvv.yaml new file mode 100644 index 000000000000..14700a2e5fea --- /dev/null +++ b/Documentation/devicetree/bindings/leds/rohm,bd2606mvv.yaml @@ -0,0 +1,81 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/leds/rohm,bd2606mvv.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ROHM BD2606MVV LED controller + +maintainers: + - Andreas Kemnade + +description: + The BD2606 MVV is a programmable LED controller connected via I2C that can + drive 6 separate lines. Each of them can be individually switched on and off, + but the brightness setting is shared between pairs of them. + + Datasheet is available at + https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/led_driver/bd2606mvv_1-e.pdf + +properties: + compatible: + const: rohm,bd2606mvv + + reg: + maxItems: 1 + + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + + enable-gpios: + maxItems: 1 + description: GPIO pin to enable/disable the device. + +patternProperties: + "^led@[0-6]$": + type: object + $ref: common.yaml# + unevaluatedProperties: false + + properties: + reg: + minimum: 0 + maximum: 6 + + required: + - reg + +additionalProperties: false + +examples: + - | + #include + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + led-controller@66 { + compatible = "rohm,bd2606mvv"; + reg = <0x66>; + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0x0>; + color = ; + function = LED_FUNCTION_POWER; + }; + + led@2 { + reg = <0x2>; + color = ; + function = LED_FUNCTION_STATUS; + }; + }; + }; + +... -- GitLab From 32c2f2a46db1322caaf78d5ea747ed5c56d2e353 Mon Sep 17 00:00:00 2001 From: Andrew Halaney Date: Thu, 13 Apr 2023 14:15:39 -0500 Subject: [PATCH 3928/5631] clk: qcom: gcc-sc8280xp: Add EMAC GDSCs Add the EMAC GDSCs to allow the EMAC hardware to be enabled. Acked-by: Stephen Boyd Reviewed-by: Konrad Dybcio Tested-by: Brian Masney Signed-off-by: Andrew Halaney Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20230413191541.1073027-2-ahalaney@redhat.com --- drivers/clk/qcom/gcc-sc8280xp.c | 18 ++++++++++++++++++ include/dt-bindings/clock/qcom,gcc-sc8280xp.h | 2 ++ 2 files changed, 20 insertions(+) diff --git a/drivers/clk/qcom/gcc-sc8280xp.c b/drivers/clk/qcom/gcc-sc8280xp.c index b3198784e1c3..04a99dbaa57e 100644 --- a/drivers/clk/qcom/gcc-sc8280xp.c +++ b/drivers/clk/qcom/gcc-sc8280xp.c @@ -6873,6 +6873,22 @@ static struct gdsc usb30_sec_gdsc = { .pwrsts = PWRSTS_RET_ON, }; +static struct gdsc emac_0_gdsc = { + .gdscr = 0xaa004, + .pd = { + .name = "emac_0_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + +static struct gdsc emac_1_gdsc = { + .gdscr = 0xba004, + .pd = { + .name = "emac_1_gdsc", + }, + .pwrsts = PWRSTS_OFF_ON, +}; + static struct clk_regmap *gcc_sc8280xp_clocks[] = { [GCC_AGGRE_NOC_PCIE0_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie0_tunnel_axi_clk.clkr, [GCC_AGGRE_NOC_PCIE1_TUNNEL_AXI_CLK] = &gcc_aggre_noc_pcie1_tunnel_axi_clk.clkr, @@ -7351,6 +7367,8 @@ static struct gdsc *gcc_sc8280xp_gdscs[] = { [USB30_MP_GDSC] = &usb30_mp_gdsc, [USB30_PRIM_GDSC] = &usb30_prim_gdsc, [USB30_SEC_GDSC] = &usb30_sec_gdsc, + [EMAC_0_GDSC] = &emac_0_gdsc, + [EMAC_1_GDSC] = &emac_1_gdsc, }; static const struct clk_rcg_dfs_data gcc_dfs_clocks[] = { diff --git a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h index cb2fb638825c..721105ea4fad 100644 --- a/include/dt-bindings/clock/qcom,gcc-sc8280xp.h +++ b/include/dt-bindings/clock/qcom,gcc-sc8280xp.h @@ -492,5 +492,7 @@ #define USB30_MP_GDSC 9 #define USB30_PRIM_GDSC 10 #define USB30_SEC_GDSC 11 +#define EMAC_0_GDSC 12 +#define EMAC_1_GDSC 13 #endif -- GitLab From 83794367dcc6749662b17a1e4b8ec085023fc53b Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 24 Apr 2023 22:13:18 +0900 Subject: [PATCH 3929/5631] block: Cleanup set_capacity()/bdev_set_nr_sectors() The code for setting a block device capacity (bd_nr_sectors field of struct block_device) is duplicated in set_capacity() and bdev_set_nr_sectors(). Clean this up by making bdev_set_nr_sectors() a block layer internal function defined in block/bdev.c instead of having this function statically defined in block/partitions/core.c. With this change, set_capacity() implementation can be simplified to only calling bdev_set_nr_sectors(). Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230424131318.79935-1-dlemoal@kernel.org Signed-off-by: Jens Axboe --- block/bdev.c | 8 ++++++++ block/blk.h | 2 ++ block/genhd.c | 7 +------ block/partitions/core.c | 8 -------- 4 files changed, 11 insertions(+), 14 deletions(-) diff --git a/block/bdev.c b/block/bdev.c index 850852fe4b78..717089a5726f 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -428,6 +428,14 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) return bdev; } +void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) +{ + spin_lock(&bdev->bd_size_lock); + i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + bdev->bd_nr_sectors = sectors; + spin_unlock(&bdev->bd_size_lock); +} + void bdev_add(struct block_device *bdev, dev_t dev) { bdev->bd_dev = dev; diff --git a/block/blk.h b/block/blk.h index 2da831103471..564119a76bc5 100644 --- a/block/blk.h +++ b/block/blk.h @@ -419,6 +419,8 @@ int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); void blk_drop_partitions(struct gendisk *disk); +void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); + struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, struct lock_class_key *lkclass); diff --git a/block/genhd.c b/block/genhd.c index cadcb472dfc3..8d56fb5f08b2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -57,12 +57,7 @@ static DEFINE_IDA(ext_devt_ida); void set_capacity(struct gendisk *disk, sector_t sectors) { - struct block_device *bdev = disk->part0; - - spin_lock(&bdev->bd_size_lock); - i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - bdev->bd_nr_sectors = sectors; - spin_unlock(&bdev->bd_size_lock); + bdev_set_nr_sectors(disk->part0, sectors); } EXPORT_SYMBOL(set_capacity); diff --git a/block/partitions/core.c b/block/partitions/core.c index 7b8ef6296abd..49e0496ff23c 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -85,14 +85,6 @@ static int (*check_part[])(struct parsed_partitions *) = { NULL }; -static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) -{ - spin_lock(&bdev->bd_size_lock); - i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); - bdev->bd_nr_sectors = sectors; - spin_unlock(&bdev->bd_size_lock); -} - static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; -- GitLab From fd3f088f35f610a7ee3045b7d172b362342e43c6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 3 Apr 2023 11:40:17 +0200 Subject: [PATCH 3930/5631] clocksource/drivers/exynos_mct: Explicitly return 0 for shared timer For a shared timers, the mct_init_dt() should not initialize the clock even with global comparator. This is not an error, thus the function should simply return 0, not 'ret'. This also fixes smatch warning: drivers/clocksource/exynos_mct.c:635 mct_init_dt() warn: missing error code? 'ret' Reported-by: kernel test robot Reported-by: Dan Carpenter Link: https://lore.kernel.org/r/202304021446.46XVKag0-lkp@intel.com/ Signed-off-by: Krzysztof Kozlowski Reviewed-by: Vincent Whitchurch Reviewed-by: Alim Akhtar Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230403094017.9556-1-krzysztof.kozlowski@linaro.org --- drivers/clocksource/exynos_mct.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c index bfd60093ee1c..ef8cb1b71be4 100644 --- a/drivers/clocksource/exynos_mct.c +++ b/drivers/clocksource/exynos_mct.c @@ -682,7 +682,7 @@ static int __init mct_init_dt(struct device_node *np, unsigned int int_type) * processor cannot use the global comparator. */ if (frc_shared) - return ret; + return 0; return exynos4_clockevent_init(); } -- GitLab From 49d576ea72a4fa5be15717babfa308b70b2bc5a4 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Thu, 9 Mar 2023 11:39:13 +0100 Subject: [PATCH 3931/5631] clocksource/drivers/timer-mediatek: Split out CPUXGPT timers On MediaTek platforms, CPUXGPT is the source for the AArch64 System Timer, read through CNTVCT_EL0. The handling for starting this timer ASAP was introduced in commit 327e93cf9a59 ("clocksource/drivers/timer-mediatek: Implement CPUXGPT timers") which description also contains an important full explanation of the reasons why this driver is necessary and cannot be a module. In preparation for an eventual conversion of timer-mediatek to a platform_driver that would be possibly built as a module, split out the CPUXGPT timers driver to a new timer-mediatek-cpux.c driver. This commit brings no functional changes. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Walter Chang Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230309103913.116775-1-angelogioacchino.delregno@collabora.com --- drivers/clocksource/Kconfig | 9 ++ drivers/clocksource/Makefile | 1 + drivers/clocksource/timer-mediatek-cpux.c | 140 ++++++++++++++++++++++ drivers/clocksource/timer-mediatek.c | 114 ------------------ 4 files changed, 150 insertions(+), 114 deletions(-) create mode 100644 drivers/clocksource/timer-mediatek-cpux.c diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 5fc8f0e7fb38..526382dc7482 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -479,6 +479,15 @@ config MTK_TIMER help Support for Mediatek timer driver. +config MTK_CPUX_TIMER + bool "MediaTek CPUX timer driver" if COMPILE_TEST + depends on HAS_IOMEM + default ARCH_MEDIATEK + select TIMER_OF + select CLKSRC_MMIO + help + Support for MediaTek CPUXGPT timer driver. + config SPRD_TIMER bool "Spreadtrum timer driver" if EXPERT depends on HAS_IOMEM diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index 64ab547de97b..f12d3987a960 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -51,6 +51,7 @@ obj-$(CONFIG_FSL_FTM_TIMER) += timer-fsl-ftm.o obj-$(CONFIG_VF_PIT_TIMER) += timer-vf-pit.o obj-$(CONFIG_CLKSRC_QCOM) += timer-qcom.o obj-$(CONFIG_MTK_TIMER) += timer-mediatek.o +obj-$(CONFIG_MTK_CPUX_TIMER) += timer-mediatek-cpux.o obj-$(CONFIG_CLKSRC_PISTACHIO) += timer-pistachio.o obj-$(CONFIG_CLKSRC_TI_32K) += timer-ti-32k.o obj-$(CONFIG_OXNAS_RPS_TIMER) += timer-oxnas-rps.o diff --git a/drivers/clocksource/timer-mediatek-cpux.c b/drivers/clocksource/timer-mediatek-cpux.c new file mode 100644 index 000000000000..a8e3df4c09fd --- /dev/null +++ b/drivers/clocksource/timer-mediatek-cpux.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * MediaTek SoCs CPUX General Purpose Timer handling + * + * Based on timer-mediatek.c: + * Copyright (C) 2014 Matthias Brugger + * + * Copyright (C) 2022 Collabora Ltd. + * AngeloGioacchino Del Regno + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include "timer-of.h" + +#define TIMER_SYNC_TICKS 3 + +/* cpux mcusys wrapper */ +#define CPUX_CON_REG 0x0 +#define CPUX_IDX_REG 0x4 + +/* cpux */ +#define CPUX_IDX_GLOBAL_CTRL 0x0 + #define CPUX_ENABLE BIT(0) + #define CPUX_CLK_DIV_MASK GENMASK(10, 8) + #define CPUX_CLK_DIV1 BIT(8) + #define CPUX_CLK_DIV2 BIT(9) + #define CPUX_CLK_DIV4 BIT(10) +#define CPUX_IDX_GLOBAL_IRQ 0x30 + +static u32 mtk_cpux_readl(u32 reg_idx, struct timer_of *to) +{ + writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG); + return readl(timer_of_base(to) + CPUX_CON_REG); +} + +static void mtk_cpux_writel(u32 val, u32 reg_idx, struct timer_of *to) +{ + writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG); + writel(val, timer_of_base(to) + CPUX_CON_REG); +} + +static void mtk_cpux_set_irq(struct timer_of *to, bool enable) +{ + const unsigned long *irq_mask = cpumask_bits(cpu_possible_mask); + u32 val; + + val = mtk_cpux_readl(CPUX_IDX_GLOBAL_IRQ, to); + + if (enable) + val |= *irq_mask; + else + val &= ~(*irq_mask); + + mtk_cpux_writel(val, CPUX_IDX_GLOBAL_IRQ, to); +} + +static int mtk_cpux_clkevt_shutdown(struct clock_event_device *clkevt) +{ + /* Clear any irq */ + mtk_cpux_set_irq(to_timer_of(clkevt), false); + + /* + * Disabling CPUXGPT timer will crash the platform, especially + * if Trusted Firmware is using it (usually, for sleep states), + * so we only mask the IRQ and call it a day. + */ + return 0; +} + +static int mtk_cpux_clkevt_resume(struct clock_event_device *clkevt) +{ + mtk_cpux_set_irq(to_timer_of(clkevt), true); + return 0; +} + +static struct timer_of to = { + /* + * There are per-cpu interrupts for the CPUX General Purpose Timer + * but since this timer feeds the AArch64 System Timer we can rely + * on the CPU timer PPIs as well, so we don't declare TIMER_OF_IRQ. + */ + .flags = TIMER_OF_BASE | TIMER_OF_CLOCK, + + .clkevt = { + .name = "mtk-cpuxgpt", + .cpumask = cpu_possible_mask, + .rating = 10, + .set_state_shutdown = mtk_cpux_clkevt_shutdown, + .tick_resume = mtk_cpux_clkevt_resume, + }, +}; + +static int __init mtk_cpux_init(struct device_node *node) +{ + u32 freq, val; + int ret; + + /* If this fails, bad things are about to happen... */ + ret = timer_of_init(node, &to); + if (ret) { + WARN(1, "Cannot start CPUX timers.\n"); + return ret; + } + + /* + * Check if we're given a clock with the right frequency for this + * timer, otherwise warn but keep going with the setup anyway, as + * that makes it possible to still boot the kernel, even though + * it may not work correctly (random lockups, etc). + * The reason behind this is that having an early UART may not be + * possible for everyone and this gives a chance to retrieve kmsg + * for eventual debugging even on consumer devices. + */ + freq = timer_of_rate(&to); + if (freq > 13000000) + WARN(1, "Requested unsupported timer frequency %u\n", freq); + + /* Clock input is 26MHz, set DIV2 to achieve 13MHz clock */ + val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to); + val &= ~CPUX_CLK_DIV_MASK; + val |= CPUX_CLK_DIV2; + mtk_cpux_writel(val, CPUX_IDX_GLOBAL_CTRL, &to); + + /* Enable all CPUXGPT timers */ + val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to); + mtk_cpux_writel(val | CPUX_ENABLE, CPUX_IDX_GLOBAL_CTRL, &to); + + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), + TIMER_SYNC_TICKS, 0xffffffff); + + return 0; +} +TIMER_OF_DECLARE(mtk_mt6795, "mediatek,mt6795-systimer", mtk_cpux_init); diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c index d5b29fd03ca2..7bcb4a3f26fb 100644 --- a/drivers/clocksource/timer-mediatek.c +++ b/drivers/clocksource/timer-mediatek.c @@ -22,19 +22,6 @@ #define TIMER_SYNC_TICKS (3) -/* cpux mcusys wrapper */ -#define CPUX_CON_REG 0x0 -#define CPUX_IDX_REG 0x4 - -/* cpux */ -#define CPUX_IDX_GLOBAL_CTRL 0x0 - #define CPUX_ENABLE BIT(0) - #define CPUX_CLK_DIV_MASK GENMASK(10, 8) - #define CPUX_CLK_DIV1 BIT(8) - #define CPUX_CLK_DIV2 BIT(9) - #define CPUX_CLK_DIV4 BIT(10) -#define CPUX_IDX_GLOBAL_IRQ 0x30 - /* gpt */ #define GPT_IRQ_EN_REG 0x00 #define GPT_IRQ_ENABLE(val) BIT((val) - 1) @@ -85,52 +72,6 @@ static void __iomem *gpt_sched_reg __read_mostly; -static u32 mtk_cpux_readl(u32 reg_idx, struct timer_of *to) -{ - writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG); - return readl(timer_of_base(to) + CPUX_CON_REG); -} - -static void mtk_cpux_writel(u32 val, u32 reg_idx, struct timer_of *to) -{ - writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG); - writel(val, timer_of_base(to) + CPUX_CON_REG); -} - -static void mtk_cpux_set_irq(struct timer_of *to, bool enable) -{ - const unsigned long *irq_mask = cpumask_bits(cpu_possible_mask); - u32 val; - - val = mtk_cpux_readl(CPUX_IDX_GLOBAL_IRQ, to); - - if (enable) - val |= *irq_mask; - else - val &= ~(*irq_mask); - - mtk_cpux_writel(val, CPUX_IDX_GLOBAL_IRQ, to); -} - -static int mtk_cpux_clkevt_shutdown(struct clock_event_device *clkevt) -{ - /* Clear any irq */ - mtk_cpux_set_irq(to_timer_of(clkevt), false); - - /* - * Disabling CPUXGPT timer will crash the platform, especially - * if Trusted Firmware is using it (usually, for sleep states), - * so we only mask the IRQ and call it a day. - */ - return 0; -} - -static int mtk_cpux_clkevt_resume(struct clock_event_device *clkevt) -{ - mtk_cpux_set_irq(to_timer_of(clkevt), true); - return 0; -} - static void mtk_syst_ack_irq(struct timer_of *to) { /* Clear and disable interrupt */ @@ -340,60 +281,6 @@ static struct timer_of to = { }, }; -static int __init mtk_cpux_init(struct device_node *node) -{ - static struct timer_of to_cpux; - u32 freq, val; - int ret; - - /* - * There are per-cpu interrupts for the CPUX General Purpose Timer - * but since this timer feeds the AArch64 System Timer we can rely - * on the CPU timer PPIs as well, so we don't declare TIMER_OF_IRQ. - */ - to_cpux.flags = TIMER_OF_BASE | TIMER_OF_CLOCK; - to_cpux.clkevt.name = "mtk-cpuxgpt"; - to_cpux.clkevt.rating = 10; - to_cpux.clkevt.cpumask = cpu_possible_mask; - to_cpux.clkevt.set_state_shutdown = mtk_cpux_clkevt_shutdown; - to_cpux.clkevt.tick_resume = mtk_cpux_clkevt_resume; - - /* If this fails, bad things are about to happen... */ - ret = timer_of_init(node, &to_cpux); - if (ret) { - WARN(1, "Cannot start CPUX timers.\n"); - return ret; - } - - /* - * Check if we're given a clock with the right frequency for this - * timer, otherwise warn but keep going with the setup anyway, as - * that makes it possible to still boot the kernel, even though - * it may not work correctly (random lockups, etc). - * The reason behind this is that having an early UART may not be - * possible for everyone and this gives a chance to retrieve kmsg - * for eventual debugging even on consumer devices. - */ - freq = timer_of_rate(&to_cpux); - if (freq > 13000000) - WARN(1, "Requested unsupported timer frequency %u\n", freq); - - /* Clock input is 26MHz, set DIV2 to achieve 13MHz clock */ - val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to_cpux); - val &= ~CPUX_CLK_DIV_MASK; - val |= CPUX_CLK_DIV2; - mtk_cpux_writel(val, CPUX_IDX_GLOBAL_CTRL, &to_cpux); - - /* Enable all CPUXGPT timers */ - val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to_cpux); - mtk_cpux_writel(val | CPUX_ENABLE, CPUX_IDX_GLOBAL_CTRL, &to_cpux); - - clockevents_config_and_register(&to_cpux.clkevt, timer_of_rate(&to_cpux), - TIMER_SYNC_TICKS, 0xffffffff); - - return 0; -} - static int __init mtk_syst_init(struct device_node *node) { int ret; @@ -452,4 +339,3 @@ static int __init mtk_gpt_init(struct device_node *node) } TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init); TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init); -TIMER_OF_DECLARE(mtk_mt6795, "mediatek,mt6795-systimer", mtk_cpux_init); -- GitLab From f68a40ee4732731f149961abab27a45b6c11f413 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Tue, 7 Mar 2023 09:43:13 -0300 Subject: [PATCH 3932/5631] clocksource/drivers/timer-imx-gpt: Remove non-DT function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mxc_timer_init() was originally only used by non-DT i.MX platforms. i.MX has already been converted to be a DT-only platform. Remove the unused mxc_timer_init() function. Signed-off-by: Fabio Estevam Acked-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230307124313.708255-1-festevam@denx.de --- drivers/clocksource/timer-imx-gpt.c | 19 ------------------- include/soc/imx/timer.h | 7 ------- 2 files changed, 26 deletions(-) diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index 7b2c70f2f353..ca3e4cbc80c6 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -420,25 +420,6 @@ static int __init _mxc_timer_init(struct imx_timer *imxtm) return mxc_clockevent_init(imxtm); } -void __init mxc_timer_init(unsigned long pbase, int irq, enum imx_gpt_type type) -{ - struct imx_timer *imxtm; - - imxtm = kzalloc(sizeof(*imxtm), GFP_KERNEL); - BUG_ON(!imxtm); - - imxtm->clk_per = clk_get_sys("imx-gpt.0", "per"); - imxtm->clk_ipg = clk_get_sys("imx-gpt.0", "ipg"); - - imxtm->base = ioremap(pbase, SZ_4K); - BUG_ON(!imxtm->base); - - imxtm->type = type; - imxtm->irq = irq; - - _mxc_timer_init(imxtm); -} - static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type type) { struct imx_timer *imxtm; diff --git a/include/soc/imx/timer.h b/include/soc/imx/timer.h index b888d5076b4d..25f29c6bbd0b 100644 --- a/include/soc/imx/timer.h +++ b/include/soc/imx/timer.h @@ -13,11 +13,4 @@ enum imx_gpt_type { GPT_TYPE_IMX6DL, /* i.MX6DL/SX/SL */ }; -/* - * This is a stop-gap solution for clock drivers like imx1/imx21 which call - * mxc_timer_init() to initialize timer for non-DT boot. It can be removed - * when these legacy non-DT support is converted or dropped. - */ -void mxc_timer_init(unsigned long pbase, int irq, enum imx_gpt_type type); - #endif /* __SOC_IMX_TIMER_H__ */ -- GitLab From 0fabf9f3a0c1ca44e01c5c4dccacfe69143413c5 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 19 Mar 2023 11:32:20 -0500 Subject: [PATCH 3933/5631] clocksource/drivers/timer-ti-dm: Use of_address_to_resource() Replace of_get_address() and of_translate_address() calls with single call to of_address_to_resource(). Signed-off-by: Rob Herring Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230319163220.226273-1-robh@kernel.org --- drivers/clocksource/timer-ti-dm-systimer.c | 57 ++++++++++------------ 1 file changed, 27 insertions(+), 30 deletions(-) diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 632523c1232f..3b98a3c04f87 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -251,24 +251,22 @@ static void __init dmtimer_systimer_assign_alwon(void) counter_32k = -ENODEV; for_each_matching_node(np, dmtimer_match_table) { + struct resource res; if (!dmtimer_is_preferred(np)) continue; - if (of_property_read_bool(np, "ti,timer-alwon")) { - const __be32 *addr; - - addr = of_get_address(np, 0, NULL, NULL); - pa = of_translate_address(np, addr); - if (pa) { - /* Quirky omap3 boards must use dmtimer12 */ - if (quirk_unreliable_oscillator && - pa == 0x48318000) - continue; - - of_node_put(np); - break; - } - } + if (!of_property_read_bool(np, "ti,timer-alwon")) + continue; + + if (of_address_to_resource(np, 0, &res)) + continue; + + /* Quirky omap3 boards must use dmtimer12 */ + if (quirk_unreliable_oscillator && res.start == 0x48318000) + continue; + + of_node_put(np); + break; } /* Usually no need for dmtimer clocksource if we have counter32 */ @@ -285,24 +283,22 @@ static void __init dmtimer_systimer_assign_alwon(void) static u32 __init dmtimer_systimer_find_first_available(void) { struct device_node *np; - const __be32 *addr; u32 pa = 0; for_each_matching_node(np, dmtimer_match_table) { + struct resource res; if (!dmtimer_is_preferred(np)) continue; - addr = of_get_address(np, 0, NULL, NULL); - pa = of_translate_address(np, addr); - if (pa) { - if (pa == clocksource || pa == clockevent) { - pa = 0; - continue; - } - - of_node_put(np); - break; - } + if (of_address_to_resource(np, 0, &res)) + continue; + + if (res.start == clocksource || res.start == clockevent) + continue; + + pa = res.start; + of_node_put(np); + break; } return pa; @@ -812,7 +808,7 @@ static int __init dmtimer_clocksource_init(struct device_node *np) */ static int __init dmtimer_systimer_init(struct device_node *np) { - const __be32 *addr; + struct resource res; u32 pa; /* One time init for the preferred timer configuration */ @@ -826,8 +822,9 @@ static int __init dmtimer_systimer_init(struct device_node *np) return -EINVAL; } - addr = of_get_address(np, 0, NULL, NULL); - pa = of_translate_address(np, addr); + + of_address_to_resource(np, 0, &res); + pa = (u32)res.start; if (!pa) return -EINVAL; -- GitLab From 78012e3880a62e0eb130a0b5a10230162ad42a06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 08:54:26 +0100 Subject: [PATCH 3934/5631] clocksource/drivers/sh_mtu2: Mark driver as non-removable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The comment in the remove callback suggests that the driver is not supposed to be unbound. However returning an error code in the remove callback doesn't accomplish that. Instead set the suppress_bind_attrs property (which makes it impossible to unbind the driver via sysfs). The only remaining way to unbind a sh_tmu2 device would be module unloading, but that doesn't apply here, as the driver cannot be built as a module. Also drop the useless remove callback. Signed-off-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230313075430.2730803-2-u.kleine-koenig@pengutronix.de --- drivers/clocksource/sh_mtu2.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c index 169a1fccc497..6bd2d0299397 100644 --- a/drivers/clocksource/sh_mtu2.c +++ b/drivers/clocksource/sh_mtu2.c @@ -484,11 +484,6 @@ static int sh_mtu2_probe(struct platform_device *pdev) return 0; } -static int sh_mtu2_remove(struct platform_device *pdev) -{ - return -EBUSY; /* cannot unregister clockevent */ -} - static const struct platform_device_id sh_mtu2_id_table[] = { { "sh-mtu2", 0 }, { }, @@ -503,10 +498,10 @@ MODULE_DEVICE_TABLE(of, sh_mtu2_of_table); static struct platform_driver sh_mtu2_device_driver = { .probe = sh_mtu2_probe, - .remove = sh_mtu2_remove, .driver = { .name = "sh_mtu2", .of_match_table = of_match_ptr(sh_mtu2_of_table), + .suppress_bind_attrs = true, }, .id_table = sh_mtu2_id_table, }; -- GitLab From ede38f924a9e3c60382a13576347dc41967e8762 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 08:54:27 +0100 Subject: [PATCH 3935/5631] clocksource/drivers/timer-stm32-lp: Mark driver as non-removable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The comment in the remove callback suggests that the driver is not supposed to be unbound. However returning an error code in the remove callback doesn't accomplish that. Instead set the suppress_bind_attrs property (which makes it impossible to unbind the driver via sysfs). The only remaining way to unbind an stm32-lp device would be module unloading, but that doesn't apply here, as the driver cannot be built as a module. Also drop the useless remove callback. [dlezcano] : Fixed up the wrong function removed Signed-off-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230313075430.2730803-3-u.kleine-koenig@pengutronix.de --- drivers/clocksource/timer-stm32-lp.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c index db2841d0beb8..0adf22d30ba1 100644 --- a/drivers/clocksource/timer-stm32-lp.c +++ b/drivers/clocksource/timer-stm32-lp.c @@ -195,11 +195,6 @@ static int stm32_clkevent_lp_probe(struct platform_device *pdev) return ret; } -static int stm32_clkevent_lp_remove(struct platform_device *pdev) -{ - return -EBUSY; /* cannot unregister clockevent */ -} - static const struct of_device_id stm32_clkevent_lp_of_match[] = { { .compatible = "st,stm32-lptimer-timer", }, {}, @@ -207,11 +202,11 @@ static const struct of_device_id stm32_clkevent_lp_of_match[] = { MODULE_DEVICE_TABLE(of, stm32_clkevent_lp_of_match); static struct platform_driver stm32_clkevent_lp_driver = { - .probe = stm32_clkevent_lp_probe, - .remove = stm32_clkevent_lp_remove, + .probe = stm32_clkevent_lp_probe, .driver = { .name = "stm32-lptimer-timer", .of_match_table = of_match_ptr(stm32_clkevent_lp_of_match), + .suppress_bind_attrs = true, }, }; module_platform_driver(stm32_clkevent_lp_driver); -- GitLab From 8efcbe927c5129d5b2528bbb40034c7dde87a6b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 08:54:28 +0100 Subject: [PATCH 3936/5631] clocksource/drivers/timer-ti-dm: Improve error message in .remove MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If a platform driver's remove callback returns an error code, the driver core emits a generic (and thus little helpful) error message. Instead emit a more specifc error message about the actual error and return zero to suppress the core's message. Note that returning zero has no side effects apart from not emitting said error message. This prepares converting platform driver's remove message to return void. Signed-off-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230313075430.2730803-4-u.kleine-koenig@pengutronix.de --- drivers/clocksource/timer-ti-dm.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index b24b903a8822..098562bda487 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -1197,7 +1197,10 @@ static int omap_dm_timer_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); - return ret; + if (ret) + dev_err(&pdev->dev, "Unable to determine timer entry in list of drivers on remove\n"); + + return 0; } static const struct omap_dm_timer_ops dmtimer_ops = { -- GitLab From d7b76421c03fa58d16a52eb839302f582602997a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 08:54:29 +0100 Subject: [PATCH 3937/5631] clocksource/drivers/timer-tegra186: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230313075430.2730803-5-u.kleine-koenig@pengutronix.de --- drivers/clocksource/timer-tegra186.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-tegra186.c b/drivers/clocksource/timer-tegra186.c index ea742889ee06..ccc762d32422 100644 --- a/drivers/clocksource/timer-tegra186.c +++ b/drivers/clocksource/timer-tegra186.c @@ -447,15 +447,13 @@ static int tegra186_timer_probe(struct platform_device *pdev) return err; } -static int tegra186_timer_remove(struct platform_device *pdev) +static void tegra186_timer_remove(struct platform_device *pdev) { struct tegra186_timer *tegra = platform_get_drvdata(pdev); clocksource_unregister(&tegra->usec); clocksource_unregister(&tegra->osc); clocksource_unregister(&tegra->tsc); - - return 0; } static int __maybe_unused tegra186_timer_suspend(struct device *dev) @@ -505,7 +503,7 @@ static struct platform_driver tegra186_wdt_driver = { .of_match_table = tegra186_timer_of_match, }, .probe = tegra186_timer_probe, - .remove = tegra186_timer_remove, + .remove_new = tegra186_timer_remove, }; module_platform_driver(tegra186_wdt_driver); -- GitLab From b1f0390048e2641d3451f8cdbbef24c79d1a8fdd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 13 Mar 2023 08:54:30 +0100 Subject: [PATCH 3938/5631] clocksource/drivers/timer-ti-dm: Convert to platform remove callback returning void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The .remove() callback for a platform driver returns an int which makes many driver authors wrongly assume it's possible to do error handling by returning an error code. However the value returned is (mostly) ignored and this typically results in resource leaks. To improve here there is a quest to make the remove callback return void. In the first step of this quest all drivers are converted to .remove_new() which already returns void. Trivially convert this driver from always returning zero in the remove callback to the void returning variant. Signed-off-by: Uwe Kleine-König Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230313075430.2730803-6-u.kleine-koenig@pengutronix.de --- drivers/clocksource/timer-ti-dm.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 098562bda487..ab7a6caa36c5 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -1177,7 +1177,7 @@ static int omap_dm_timer_probe(struct platform_device *pdev) * In addition to freeing platform resources it also deletes the timer * entry from the local list. */ -static int omap_dm_timer_remove(struct platform_device *pdev) +static void omap_dm_timer_remove(struct platform_device *pdev) { struct dmtimer *timer; unsigned long flags; @@ -1199,8 +1199,6 @@ static int omap_dm_timer_remove(struct platform_device *pdev) if (ret) dev_err(&pdev->dev, "Unable to determine timer entry in list of drivers on remove\n"); - - return 0; } static const struct omap_dm_timer_ops dmtimer_ops = { @@ -1275,7 +1273,7 @@ MODULE_DEVICE_TABLE(of, omap_timer_match); static struct platform_driver omap_dm_timer_driver = { .probe = omap_dm_timer_probe, - .remove = omap_dm_timer_remove, + .remove_new = omap_dm_timer_remove, .driver = { .name = "omap_timer", .of_match_table = omap_timer_match, -- GitLab From b6f228e800ccf285906bb1c4c366ce3848a5443e Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 18:38:03 +0100 Subject: [PATCH 3939/5631] clocksource/drivers/stm32-lp: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/clocksource/timer-stm32-lp.c:203:34: error: ‘stm32_clkevent_lp_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230311173803.263446-1-krzysztof.kozlowski@linaro.org --- drivers/clocksource/timer-stm32-lp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c index 0adf22d30ba1..d14a17549fe8 100644 --- a/drivers/clocksource/timer-stm32-lp.c +++ b/drivers/clocksource/timer-stm32-lp.c @@ -205,7 +205,7 @@ static struct platform_driver stm32_clkevent_lp_driver = { .probe = stm32_clkevent_lp_probe, .driver = { .name = "stm32-lptimer-timer", - .of_match_table = of_match_ptr(stm32_clkevent_lp_of_match), + .of_match_table = stm32_clkevent_lp_of_match, .suppress_bind_attrs = true, }, }; -- GitLab From fb73556386e074e9bee9fa2d253aeaefe4e063e0 Mon Sep 17 00:00:00 2001 From: Qinrun Dai Date: Thu, 13 Apr 2023 13:50:37 +0000 Subject: [PATCH 3940/5631] clocksource/drivers/davinci: Fix memory leak in davinci_timer_register when init fails Smatch reports: drivers/clocksource/timer-davinci.c:332 davinci_timer_register() warn: 'base' from ioremap() not released on lines: 274. Fix this and other potential memory leak problems by adding a set of corresponding exit lables. Fixes: 721154f972aa ("clocksource/drivers/davinci: Add support for clockevents") Signed-off-by: Qinrun Dai Link: https://lore.kernel.org/r/20230413135037.1505799-1-flno@hust.edu.cn Signed-off-by: Daniel Lezcano --- drivers/clocksource/timer-davinci.c | 30 +++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) diff --git a/drivers/clocksource/timer-davinci.c b/drivers/clocksource/timer-davinci.c index 9996c0542520..b1c248498be4 100644 --- a/drivers/clocksource/timer-davinci.c +++ b/drivers/clocksource/timer-davinci.c @@ -257,21 +257,25 @@ int __init davinci_timer_register(struct clk *clk, resource_size(&timer_cfg->reg), "davinci-timer")) { pr_err("Unable to request memory region\n"); - return -EBUSY; + rv = -EBUSY; + goto exit_clk_disable; } base = ioremap(timer_cfg->reg.start, resource_size(&timer_cfg->reg)); if (!base) { pr_err("Unable to map the register range\n"); - return -ENOMEM; + rv = -ENOMEM; + goto exit_mem_region; } davinci_timer_init(base); tick_rate = clk_get_rate(clk); clockevent = kzalloc(sizeof(*clockevent), GFP_KERNEL); - if (!clockevent) - return -ENOMEM; + if (!clockevent) { + rv = -ENOMEM; + goto exit_iounmap_base; + } clockevent->dev.name = "tim12"; clockevent->dev.features = CLOCK_EVT_FEAT_ONESHOT; @@ -296,7 +300,7 @@ int __init davinci_timer_register(struct clk *clk, "clockevent/tim12", clockevent); if (rv) { pr_err("Unable to request the clockevent interrupt\n"); - return rv; + goto exit_free_clockevent; } davinci_clocksource.dev.rating = 300; @@ -323,13 +327,27 @@ int __init davinci_timer_register(struct clk *clk, rv = clocksource_register_hz(&davinci_clocksource.dev, tick_rate); if (rv) { pr_err("Unable to register clocksource\n"); - return rv; + goto exit_free_irq; } sched_clock_register(davinci_timer_read_sched_clock, DAVINCI_TIMER_CLKSRC_BITS, tick_rate); return 0; + +exit_free_irq: + free_irq(timer_cfg->irq[DAVINCI_TIMER_CLOCKEVENT_IRQ].start, + clockevent); +exit_free_clockevent: + kfree(clockevent); +exit_iounmap_base: + iounmap(base); +exit_mem_region: + release_mem_region(timer_cfg->reg.start, + resource_size(&timer_cfg->reg)); +exit_clk_disable: + clk_disable_unprepare(clk); + return rv; } static int __init of_davinci_timer_register(struct device_node *np) -- GitLab From 8d7aac5153f21108365137b76e395dcf9bb3a800 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 12 Apr 2023 09:41:41 +0300 Subject: [PATCH 3941/5631] clocksource/drivers/timer-ti-dm: Fix finding alwon timer Clean-up commit b6999fa1c847 ("clocksource/drivers/timer-ti-dm: Use of_address_to_resource()") caused a regression where pa is never set making all related SoCs fail to boot. Let's fix this by setting pa if found. Fixes: b6999fa1c847 ("clocksource/drivers/timer-ti-dm: Use of_address_to_resource()") Cc: Rob Herring Signed-off-by: Tony Lindgren Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230412064142.12726-1-tony@atomide.com --- drivers/clocksource/timer-ti-dm-systimer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 3b98a3c04f87..4fa68f657056 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -261,8 +261,10 @@ static void __init dmtimer_systimer_assign_alwon(void) if (of_address_to_resource(np, 0, &res)) continue; + pa = res.start; + /* Quirky omap3 boards must use dmtimer12 */ - if (quirk_unreliable_oscillator && res.start == 0x48318000) + if (quirk_unreliable_oscillator && pa == 0x48318000) continue; of_node_put(np); -- GitLab From 87dd04f9b1a37a92ebbea5eb46e4941551d3547e Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:01 -0600 Subject: [PATCH 3942/5631] clocksource/drivers/ti: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230310144702.1541660-1-robh@kernel.org --- drivers/clocksource/timer-ti-dm-systimer.c | 4 ++-- drivers/clocksource/timer-ti-dm.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 4fa68f657056..c2dcd8d68e45 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -584,7 +584,7 @@ static int __init dmtimer_clkevt_init_common(struct dmtimer_clockevent *clkevt, writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->wakeup); pr_info("TI gptimer %s: %s%lu Hz at %pOF\n", - name, of_find_property(np, "ti,timer-alwon", NULL) ? + name, of_property_read_bool(np, "ti,timer-alwon") ? "always-on " : "", t->rate, np->parent); return 0; @@ -785,7 +785,7 @@ static int __init dmtimer_clocksource_init(struct device_node *np) t->base + t->ctrl); pr_info("TI gptimer clocksource: %s%pOF\n", - of_find_property(np, "ti,timer-alwon", NULL) ? + of_property_read_bool(np, "ti,timer-alwon") ? "always-on " : "", np->parent); if (!dmtimer_sched_clock_counter) { diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index ab7a6caa36c5..1d3ad51e4634 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -1104,13 +1104,13 @@ static int omap_dm_timer_probe(struct platform_device *pdev) platform_set_drvdata(pdev, timer); if (dev->of_node) { - if (of_find_property(dev->of_node, "ti,timer-alwon", NULL)) + if (of_property_read_bool(dev->of_node, "ti,timer-alwon")) timer->capability |= OMAP_TIMER_ALWON; - if (of_find_property(dev->of_node, "ti,timer-dsp", NULL)) + if (of_property_read_bool(dev->of_node, "ti,timer-dsp")) timer->capability |= OMAP_TIMER_HAS_DSP_IRQ; - if (of_find_property(dev->of_node, "ti,timer-pwm", NULL)) + if (of_property_read_bool(dev->of_node, "ti,timer-pwm")) timer->capability |= OMAP_TIMER_HAS_PWM; - if (of_find_property(dev->of_node, "ti,timer-secure", NULL)) + if (of_property_read_bool(dev->of_node, "ti,timer-secure")) timer->capability |= OMAP_TIMER_SECURE; } else { timer->id = pdev->id; -- GitLab From 51010c1dc487e7764b7e1ec1c4954068e5880757 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 19 Apr 2023 21:13:07 +0300 Subject: [PATCH 3943/5631] dt-bindings: timer: rockchip: Drop superfluous rk3288 compatible The compatible string for Rockchip RK3288 is wrongly provided in the 'enum' item, in addition to the subsequent 'const', which allows the usage of an incorrect specification: compatible = "rockchip,rk3288-timer", "rockchip,rk3288-timer"; As the rk3288 string is also specified in the top-most 'const' item, the binding already allows the usage of the correct variant: compatible = "rockchip,rk3288-timer"; Drop the unwanted rk3288 entry from the enum. Fixes: faa186adbd06 ("dt-bindings: timer: convert rockchip,rk-timer.txt to YAML") Signed-off-by: Cristian Ciocaltea Reviewed-by: Heiko Stuebner Reviewed-by: Krzysztof Kozlowski Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419181309.338354-2-cristian.ciocaltea@collabora.com --- Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml index 65e59836a660..2bdb6e6bdb21 100644 --- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml +++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml @@ -23,7 +23,6 @@ properties: - rockchip,rk3188-timer - rockchip,rk3228-timer - rockchip,rk3229-timer - - rockchip,rk3288-timer - rockchip,rk3368-timer - rockchip,px30-timer - const: rockchip,rk3288-timer -- GitLab From e2a1406c84c43bd104e2f85c4d8ab0b0b1609ab0 Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Wed, 19 Apr 2023 21:13:08 +0300 Subject: [PATCH 3944/5631] dt-bindings: timer: rockchip: Add rk3588 compatible Add compatible string for Rockchip RK3588 timer. Signed-off-by: Cristian Ciocaltea Reviewed-by: Heiko Stuebner Acked-by: Krzysztof Kozlowski Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419181309.338354-3-cristian.ciocaltea@collabora.com --- Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml index 2bdb6e6bdb21..19e56b7577a0 100644 --- a/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml +++ b/Documentation/devicetree/bindings/timer/rockchip,rk-timer.yaml @@ -24,6 +24,7 @@ properties: - rockchip,rk3228-timer - rockchip,rk3229-timer - rockchip,rk3368-timer + - rockchip,rk3588-timer - rockchip,px30-timer - const: rockchip,rk3288-timer reg: -- GitLab From 9e868ca1f269dec9f2062bb8de42b8a94773924e Mon Sep 17 00:00:00 2001 From: Maxim Kochetkov Date: Sat, 22 Apr 2023 00:19:50 +0300 Subject: [PATCH 3945/5631] ASoC: max98090: make it selectable There is no way to select max98090 from menuconfig right now. Add a Kconfig menu description to allow building the driver standalone. It will allow this codec to be used by any other I2S master without adding extra sound card entry in Kconfig. Signed-off-by: Maxim Kochetkov Link: https://lore.kernel.org/r/20230421211950.20972-1-fido_max@inbox.ru Signed-off-by: Mark Brown --- sound/soc/codecs/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 79d2362ad055..8020097d4e4c 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -1090,7 +1090,7 @@ config SND_SOC_MAX98088 depends on I2C config SND_SOC_MAX98090 - tristate + tristate "Maxim MAX98090 CODEC" depends on I2C config SND_SOC_MAX98095 -- GitLab From c963e2ec095cb3f855890be53f56f5a6c6fbe371 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 21 Apr 2023 20:37:14 +0200 Subject: [PATCH 3946/5631] ASoC: Intel: soc-acpi-byt: Fix "WM510205" match no longer working Commit 7e1d728a94ca ("ASoC: Intel: soc-acpi-byt: Add new WM5102 ACPI HID") added an extra HID to wm5102_comp_ids.codecs, but it forgot to bump wm5102_comp_ids.num_codecs, causing the last codec HID in the codecs list to no longer work. Bump wm5102_comp_ids.num_codecs to fix this. Fixes: 7e1d728a94ca ("ASoC: Intel: soc-acpi-byt: Add new WM5102 ACPI HID") Signed-off-by: Hans de Goede Acked-by: Pierre-Louis Bossart Link: https://lore.kernel.org/r/20230421183714.35186-1-hdegoede@redhat.com Signed-off-by: Mark Brown --- sound/soc/intel/common/soc-acpi-intel-byt-match.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/intel/common/soc-acpi-intel-byt-match.c b/sound/soc/intel/common/soc-acpi-intel-byt-match.c index db5a92b9875a..87c44f284971 100644 --- a/sound/soc/intel/common/soc-acpi-intel-byt-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-byt-match.c @@ -124,7 +124,7 @@ static const struct snd_soc_acpi_codecs rt5640_comp_ids = { }; static const struct snd_soc_acpi_codecs wm5102_comp_ids = { - .num_codecs = 2, + .num_codecs = 3, .codecs = { "10WM5102", "WM510204", "WM510205"}, }; -- GitLab From ce1d3bc2733224573600e5564203345caea814eb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 20 Apr 2023 15:54:11 -0300 Subject: [PATCH 3947/5631] perf evsel: Introduce evsel__name_is() method to check if the evsel name is equal to a given string This makes the logic a bit clear by avoiding the !strcmp() pattern and also a way to intercept the pointer if we need to do extra validation on it or to do lazy setting of evsel->name via evsel__name(evsel). Reviewed-by: "Liang, Kan" Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZEGLM8VehJbS0gP2@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/kvm-stat.c | 4 ++-- tools/perf/arch/powerpc/util/kvm-stat.c | 4 ++-- tools/perf/arch/x86/util/kvm-stat.c | 8 ++++---- tools/perf/builtin-kvm.c | 6 +++--- tools/perf/builtin-stat.c | 2 +- tools/perf/tests/expand-cgroup.c | 2 +- tools/perf/tests/parse-events.c | 12 ++++++------ tools/perf/tests/parse-metric.c | 2 +- tools/perf/tests/pmu-events.c | 2 +- tools/perf/util/evlist.c | 4 ++-- tools/perf/util/evsel.c | 7 ++++++- tools/perf/util/evsel.h | 1 + tools/perf/util/sort.c | 2 +- 13 files changed, 31 insertions(+), 25 deletions(-) diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 72ca9bb45804..6611aa21cba9 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -44,14 +44,14 @@ static bool event_begin(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { - return !strcmp(evsel->name, kvm_entry_trace); + return evsel__name_is(evsel, kvm_entry_trace); } static bool event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, kvm_exit_trace)) { + if (evsel__name_is(evsel, kvm_exit_trace)) { event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c index d04a08c9fd19..ea1220d66b67 100644 --- a/tools/perf/arch/powerpc/util/kvm-stat.c +++ b/tools/perf/arch/powerpc/util/kvm-stat.c @@ -60,13 +60,13 @@ static bool hcall_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { - return (!strcmp(evsel->name, kvm_events_tp[3])); + return (evsel__name_is(evsel, kvm_events_tp[3])); } static bool hcall_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, kvm_events_tp[2])) { + if (evsel__name_is(evsel, kvm_events_tp[2])) { hcall_event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index ef513def03ba..424716518b75 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -46,7 +46,7 @@ static bool mmio_event_begin(struct evsel *evsel, return true; /* MMIO write begin event in kernel. */ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && + if (evsel__name_is(evsel, "kvm:kvm_mmio") && evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) { mmio_event_get_key(evsel, sample, key); return true; @@ -63,7 +63,7 @@ static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, return true; /* MMIO read end event in kernel.*/ - if (!strcmp(evsel->name, "kvm:kvm_mmio") && + if (evsel__name_is(evsel, "kvm:kvm_mmio") && evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) { mmio_event_get_key(evsel, sample, key); return true; @@ -101,7 +101,7 @@ static bool ioport_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, "kvm:kvm_pio")) { + if (evsel__name_is(evsel, "kvm:kvm_pio")) { ioport_event_get_key(evsel, sample, key); return true; } @@ -145,7 +145,7 @@ static bool msr_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { - if (!strcmp(evsel->name, "kvm:kvm_msr")) { + if (evsel__name_is(evsel, "kvm:kvm_msr")) { msr_event_get_key(evsel, sample, key); return true; } diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index 747d19336340..71165036e4ca 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -625,7 +625,7 @@ void exit_event_get_key(struct evsel *evsel, bool kvm_exit_event(struct evsel *evsel) { - return !strcmp(evsel->name, kvm_exit_trace); + return evsel__name_is(evsel, kvm_exit_trace); } bool exit_event_begin(struct evsel *evsel, @@ -641,7 +641,7 @@ bool exit_event_begin(struct evsel *evsel, bool kvm_entry_event(struct evsel *evsel) { - return !strcmp(evsel->name, kvm_entry_trace); + return evsel__name_is(evsel, kvm_entry_trace); } bool exit_event_end(struct evsel *evsel, @@ -878,7 +878,7 @@ static bool is_child_event(struct perf_kvm_stat *kvm, return false; for (; child_ops->name; child_ops++) { - if (!strcmp(evsel->name, child_ops->name)) { + if (evsel__name_is(evsel, child_ops->name)) { child_ops->get_key(evsel, sample, key); return true; } diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d3cbee7460fc..efda63f6bf32 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2170,7 +2170,7 @@ static void setup_system_wide(int forks) evlist__for_each_entry(evsel_list, counter) { if (!counter->core.requires_cpu && - strcmp(counter->name, "duration_time")) { + !evsel__name_is(counter, "duration_time")) { return; } } diff --git a/tools/perf/tests/expand-cgroup.c b/tools/perf/tests/expand-cgroup.c index ec340880a848..9c1a1f18db75 100644 --- a/tools/perf/tests/expand-cgroup.c +++ b/tools/perf/tests/expand-cgroup.c @@ -61,7 +61,7 @@ static int test_expand_events(struct evlist *evlist, i = 0; evlist__for_each_entry(evlist, evsel) { - if (strcmp(evsel->name, ev_name[i % nr_events])) { + if (!evsel__name_is(evsel, ev_name[i % nr_events])) { pr_debug("event name doesn't match:\n"); pr_debug(" evsel[%d]: %s\n expected: %s\n", i, evsel->name, ev_name[i % nr_events]); diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 6eb1400443ad..8068cfd89b84 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1401,7 +1401,7 @@ static int test__checkevent_config_symbol(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "insn")); return TEST_OK; } @@ -1409,7 +1409,7 @@ static int test__checkevent_config_raw(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "rawpmu")); return TEST_OK; } @@ -1417,7 +1417,7 @@ static int test__checkevent_config_num(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "numpmu")); return TEST_OK; } @@ -1425,7 +1425,7 @@ static int test__checkevent_config_cache(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "cachepmu")); return TEST_OK; } @@ -1438,7 +1438,7 @@ static int test__intel_pt(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0); + TEST_ASSERT_VAL("wrong name setting", evsel__name_is(evsel, "intel_pt//u")); return TEST_OK; } @@ -1446,7 +1446,7 @@ static int test__checkevent_complex_name(struct evlist *evlist) { struct evsel *evsel = evlist__first(evlist); - TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0); + TEST_ASSERT_VAL("wrong complex name parsing", evsel__name_is(evsel, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks")); return TEST_OK; } diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index c43b056f9fa3..1185b79e6274 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -39,7 +39,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); evsel->stats->aggr->counts.val = count; - if (!strcmp(evsel->name, "duration_time")) + if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); } } diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index 7f8e86452527..1dff863b9711 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -866,7 +866,7 @@ static int test__parsing_callback(const struct pmu_metric *pm, evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { evsel->stats->aggr->counts.val = k; - if (!strcmp(evsel->name, "duration_time")) + if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, k); k++; } diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 2260e27adf44..a0504316b06f 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -467,7 +467,7 @@ static int evsel__strcmp(struct evsel *pos, char *evsel_name) return 0; if (evsel__is_dummy_event(pos)) return 1; - return strcmp(pos->name, evsel_name); + return !evsel__name_is(pos, evsel_name); } static int evlist__is_enabled(struct evlist *evlist) @@ -1706,7 +1706,7 @@ struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str) evlist__for_each_entry(evlist, evsel) { if (!evsel->name) continue; - if (strcmp(str, evsel->name) == 0) + if (evsel__name_is(evsel, str)) return evsel; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a85a987128aa..356c07f03be6 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -821,6 +821,11 @@ const char *evsel__name(struct evsel *evsel) return "unknown"; } +bool evsel__name_is(struct evsel *evsel, const char *name) +{ + return !strcmp(evsel__name(evsel), name); +} + const char *evsel__group_pmu_name(const struct evsel *evsel) { const struct evsel *leader; @@ -1146,7 +1151,7 @@ static void evsel__set_default_freq_period(struct record_opts *opts, static bool evsel__is_offcpu_event(struct evsel *evsel) { - return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT); + return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT); } /* diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 68072ec655ce..1e5d640e4a9b 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -282,6 +282,7 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size); int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size); const char *evsel__name(struct evsel *evsel); +bool evsel__name_is(struct evsel *evsel, const char *name); const char *evsel__group_pmu_name(const struct evsel *evsel); const char *evsel__metric_id(const struct evsel *evsel); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 31b1cd0935e2..650cd8df4041 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2893,7 +2893,7 @@ static struct evsel *find_evsel(struct evlist *evlist, char *event_name) full_name = !!strchr(event_name, ':'); evlist__for_each_entry(evlist, pos) { /* case 2 */ - if (full_name && !strcmp(pos->name, event_name)) + if (full_name && evsel__name_is(pos, event_name)) return pos; /* case 3 */ if (!full_name && strstr(pos->name, event_name)) { -- GitLab From 449067f3fc9f340da54e383738286881e6634d0b Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:41 +0100 Subject: [PATCH 3948/5631] perf cs-etm: Fix timeless decode mode detection In this context, timeless refers to the trace data rather than the perf event data. But when detecting whether there are timestamps in the trace data or not, the presence of a timestamp flag on any perf event is used. Since commit f42c0ce573df ("perf record: Always get text_poke events with --kcore option") timestamps were added to a tracking event when --kcore is used which breaks this detection mechanism. Fix it by detecting if trace timestamps exist by looking at the ETM config flags. This would have always been a more accurate way of doing it anyway. This fixes the following error message when using --kcore with Coresight: $ perf record --kcore -e cs_etm// --per-thread $ perf report The perf.data/data data has no samples! Fixes: f42c0ce573df79d1 ("perf record: Always get text_poke events with --kcore option") Reported-by: Yang Shi Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: denik@google.com Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/lkml/CAHbLzkrJQTrYBtPkf=jf3OpQ-yBcJe7XkvQstX9j2frz4WF-SQ@mail.gmail.com/ Link: https://lore.kernel.org/r/20230424134748.228137-2-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 8dd81ddd9e4e..50593289d53c 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2684,26 +2684,29 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, return 0; } -static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm) +static int cs_etm__setup_timeless_decoding(struct cs_etm_auxtrace *etm) { struct evsel *evsel; struct evlist *evlist = etm->session->evlist; - bool timeless_decoding = true; /* Override timeless mode with user input from --itrace=Z */ - if (etm->synth_opts.timeless_decoding) - return true; + if (etm->synth_opts.timeless_decoding) { + etm->timeless_decoding = true; + return 0; + } /* - * Circle through the list of event and complain if we find one - * with the time bit set. + * Find the cs_etm evsel and look at what its timestamp setting was */ - evlist__for_each_entry(evlist, evsel) { - if ((evsel->core.attr.sample_type & PERF_SAMPLE_TIME)) - timeless_decoding = false; - } + evlist__for_each_entry(evlist, evsel) + if (cs_etm__evsel_is_auxtrace(etm->session, evsel)) { + etm->timeless_decoding = + !(evsel->core.attr.config & BIT(ETM_OPT_TS)); + return 0; + } - return timeless_decoding; + pr_err("CS ETM: Couldn't find ETM evsel\n"); + return -EINVAL; } /* @@ -3155,7 +3158,6 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->snapshot_mode = (ptr[CS_ETM_SNAPSHOT] != 0); etm->metadata = metadata; etm->auxtrace_type = auxtrace_info->type; - etm->timeless_decoding = cs_etm__is_timeless_decoding(etm); /* Use virtual timestamps if all ETMs report ts_source = 1 */ etm->has_virtual_ts = cs_etm__has_virtual_ts(metadata, num_cpu); @@ -3172,6 +3174,10 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event, etm->auxtrace.evsel_is_auxtrace = cs_etm__evsel_is_auxtrace; session->auxtrace = &etm->auxtrace; + err = cs_etm__setup_timeless_decoding(etm); + if (err) + return err; + etm->unknown_thread = thread__new(999999999, 999999999); if (!etm->unknown_thread) { err = -ENOMEM; -- GitLab From 6593f019c26cbdee3432f28a3d1ffac9605cf562 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:42 +0100 Subject: [PATCH 3949/5631] perf tools: Add util function for overriding user set config values There is some duplicated code to only override config values if they haven't already been set by the user so make a util function for this. Signed-off-by: James Clark Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-3-james.clark@arm.com [ Moved evsel__set_config_if_unset() to util/pmu.c to avoid dragging stuff into the python binding ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/arm-spe.c | 26 ++---------------------- tools/perf/arch/x86/util/intel-pt.c | 22 ++------------------ tools/perf/util/evsel.h | 3 +++ tools/perf/util/pmu.c | 30 ++++++++++++++++++++++++++++ 4 files changed, 37 insertions(+), 44 deletions(-) diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index ef497a29e814..3b1676ff03f9 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -36,29 +36,6 @@ struct arm_spe_recording { bool *wrapped; }; -static void arm_spe_set_timestamp(struct auxtrace_record *itr, - struct evsel *evsel) -{ - struct arm_spe_recording *ptr; - struct perf_pmu *arm_spe_pmu; - struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG); - u64 user_bits = 0, bit; - - ptr = container_of(itr, struct arm_spe_recording, itr); - arm_spe_pmu = ptr->arm_spe_pmu; - - if (term) - user_bits = term->val.cfg_chg; - - bit = perf_pmu__format_bits(&arm_spe_pmu->format, "ts_enable"); - - /* Skip if user has set it */ - if (bit & user_bits) - return; - - evsel->core.attr.config |= bit; -} - static size_t arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused, struct evlist *evlist __maybe_unused) @@ -238,7 +215,8 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, */ if (!perf_cpu_map__empty(cpus)) { evsel__set_sample_bit(arm_spe_evsel, CPU); - arm_spe_set_timestamp(itr, arm_spe_evsel); + evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel, + "ts_enable", 1); } /* diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 2cff11de9d8a..17336da08b58 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -576,25 +576,6 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, return err; } -static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu, - struct evsel *evsel) -{ - u64 user_bits = 0, bits; - struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG); - - if (term) - user_bits = term->val.cfg_chg; - - bits = perf_pmu__format_bits(&intel_pt_pmu->format, "psb_period"); - - /* Did user change psb_period */ - if (bits & user_bits) - return; - - /* Set psb_period to 0 */ - evsel->core.attr.config &= ~bits; -} - static void intel_pt_min_max_sample_sz(struct evlist *evlist, size_t *min_sz, size_t *max_sz) { @@ -686,7 +667,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, return 0; if (opts->auxtrace_sample_mode) - intel_pt_config_sample_mode(intel_pt_pmu, intel_pt_evsel); + evsel__set_config_if_unset(intel_pt_pmu, intel_pt_evsel, + "psb_period", 0); err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel); if (err) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 1e5d640e4a9b..35805dcdb1b9 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -530,4 +530,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel); ((((src) >> (pos)) & ((1ull << (size)) - 1)) << (63 - ((pos) + (size) - 1))) u64 evsel__bitfield_swap_branch_flags(u64 value); +void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, + const char *config_name, u64 val); + #endif /* __PERF_EVSEL_H */ diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 65d0eb9a740a..ad209c88a124 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -33,6 +33,7 @@ #include "strbuf.h" #include "fncache.h" #include "pmu-hybrid.h" +#include "util/evsel_config.h" struct perf_pmu perf_pmu__fake; @@ -1056,6 +1057,35 @@ bool evsel__is_aux_event(const struct evsel *evsel) return pmu && pmu->auxtrace; } +/* + * Set @config_name to @val as long as the user hasn't already set or cleared it + * by passing a config term on the command line. + * + * @val is the value to put into the bits specified by @config_name rather than + * the bit pattern. It is shifted into position by this function, so to set + * something to true, pass 1 for val rather than a pre shifted value. + */ +#define field_prep(_mask, _val) (((_val) << (ffsll(_mask) - 1)) & (_mask)) +void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, + const char *config_name, u64 val) +{ + u64 user_bits = 0, bits; + struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG); + + if (term) + user_bits = term->val.cfg_chg; + + bits = perf_pmu__format_bits(&pmu->format, config_name); + + /* Do nothing if the user changed the value */ + if (bits & user_bits) + return; + + /* Otherwise replace it */ + evsel->core.attr.config &= ~bits; + evsel->core.attr.config |= field_prep(bits, val); +} + struct perf_pmu *perf_pmu__find(const char *name) { struct perf_pmu *pmu; -- GitLab From 3963d84b1bf0af98f604c85436076a1eb46373f3 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:43 +0100 Subject: [PATCH 3950/5631] perf cs-etm: Don't test full_auxtrace because it's always set There is no path in cs-etm where this isn't true so it doesn't need to be tested. Also re-order the beginning of cs_etm_recording_options() so that nothing is done until the early exit is passed. Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-4-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 56 ++++++++++++++----------------- 1 file changed, 25 insertions(+), 31 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index e02a9bfc3d42..f9b9ebf7fffc 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -319,13 +319,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, bool privileged = perf_event_paranoid_check(-1); int err = 0; - ptr->evlist = evlist; - ptr->snapshot_mode = opts->auxtrace_snapshot_mode; - - if (!record_opts__no_switch_events(opts) && - perf_can_record_switch_events()) - opts->record_switch_events = true; - evlist__for_each_entry(evlist, evsel) { if (evsel->core.attr.type == cs_etm_pmu->type) { if (cs_etm_evsel) { @@ -333,11 +326,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, CORESIGHT_ETM_PMU_NAME); return -EINVAL; } - evsel->core.attr.freq = 0; - evsel->core.attr.sample_period = 1; - evsel->needs_auxtrace_mmap = true; cs_etm_evsel = evsel; - opts->full_auxtrace = true; } } @@ -345,6 +334,18 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, if (!cs_etm_evsel) return 0; + ptr->evlist = evlist; + ptr->snapshot_mode = opts->auxtrace_snapshot_mode; + + if (!record_opts__no_switch_events(opts) && + perf_can_record_switch_events()) + opts->record_switch_events = true; + + cs_etm_evsel->core.attr.freq = 0; + cs_etm_evsel->core.attr.sample_period = 1; + cs_etm_evsel->needs_auxtrace_mmap = true; + opts->full_auxtrace = true; + ret = cs_etm_set_sink_attr(cs_etm_pmu, cs_etm_evsel); if (ret) return ret; @@ -414,8 +415,8 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } } - /* We are in full trace mode but '-m,xyz' wasn't specified */ - if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { + /* Buffer sizes weren't specified with '-m,xyz' so give some defaults */ + if (!opts->auxtrace_mmap_pages) { if (privileged) { opts->auxtrace_mmap_pages = MiB(4) / page_size; } else { @@ -423,7 +424,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, if (opts->mmap_pages == UINT_MAX) opts->mmap_pages = KiB(256) / page_size; } - } if (opts->auxtrace_snapshot_mode) @@ -454,23 +454,17 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, } /* Add dummy event to keep tracking */ - if (opts->full_auxtrace) { - struct evsel *tracking_evsel; - - err = parse_event(evlist, "dummy:u"); - if (err) - goto out; - - tracking_evsel = evlist__last(evlist); - evlist__set_tracking_event(evlist, tracking_evsel); - - tracking_evsel->core.attr.freq = 0; - tracking_evsel->core.attr.sample_period = 1; - - /* In per-cpu case, always need the time of mmap events etc */ - if (!perf_cpu_map__empty(cpus)) - evsel__set_sample_bit(tracking_evsel, TIME); - } + err = parse_event(evlist, "dummy:u"); + if (err) + goto out; + evsel = evlist__last(evlist); + evlist__set_tracking_event(evlist, evsel); + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; + + /* In per-cpu case, always need the time of mmap events etc */ + if (!perf_cpu_map__empty(cpus)) + evsel__set_sample_bit(evsel, TIME); out: return err; -- GitLab From 35c51f83dd1ed5db9ddf90e90caf5cb2aa608a35 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:44 +0100 Subject: [PATCH 3951/5631] perf cs-etm: Validate options after applying them Currently the cs_etm_set_option() function both validates and applies the config options. Because it's only called when they are added automatically, there are some paths where the user can apply the option on the command line and skip the validation. By moving it to the end it covers both cases. Also, options don't need to be re-applied anyway, Perf handles parsing and applying the config terms automatically. Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-5-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 152 +++++++++++++----------------- 1 file changed, 68 insertions(+), 84 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index f9b9ebf7fffc..af0a2400c655 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -69,21 +69,29 @@ static const char * const metadata_ete_ro[] = { static bool cs_etm_is_etmv4(struct auxtrace_record *itr, int cpu); static bool cs_etm_is_ete(struct auxtrace_record *itr, int cpu); -static int cs_etm_set_context_id(struct auxtrace_record *itr, - struct evsel *evsel, int cpu) +static int cs_etm_validate_context_id(struct auxtrace_record *itr, + struct evsel *evsel, int cpu) { - struct cs_etm_recording *ptr; - struct perf_pmu *cs_etm_pmu; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; char path[PATH_MAX]; - int err = -EINVAL; + int err; u32 val; - u64 contextid; + u64 contextid = + evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); - ptr = container_of(itr, struct cs_etm_recording, itr); - cs_etm_pmu = ptr->cs_etm_pmu; + if (!contextid) + return 0; - if (!cs_etm_is_etmv4(itr, cpu)) - goto out; + /* Not supported in etmv3 */ + if (!cs_etm_is_etmv4(itr, cpu)) { + pr_err("%s: contextid not supported in ETMv3, disable with %s/contextid=0/\n", + CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } /* Get a handle on TRCIDR2 */ snprintf(path, PATH_MAX, "cpu%d/%s", @@ -92,27 +100,13 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, /* There was a problem reading the file, bailing out */ if (err != 1) { - pr_err("%s: can't read file %s\n", - CORESIGHT_ETM_PMU_NAME, path); - goto out; + pr_err("%s: can't read file %s\n", CORESIGHT_ETM_PMU_NAME, + path); + return err; } - /* User has configured for PID tracing, respects it. */ - contextid = evsel->core.attr.config & - (BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_CTXTID2)); - - /* - * If user doesn't configure the contextid format, parse PMU format and - * enable PID tracing according to the "contextid" format bits: - * - * If bit ETM_OPT_CTXTID is set, trace CONTEXTIDR_EL1; - * If bit ETM_OPT_CTXTID2 is set, trace CONTEXTIDR_EL2. - */ - if (!contextid) - contextid = perf_pmu__format_bits(&cs_etm_pmu->format, - "contextid"); - - if (contextid & BIT(ETM_OPT_CTXTID)) { + if (contextid & + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1")) { /* * TRCIDR2.CIDSIZE, bit [9-5], indicates whether contextID * tracing is supported: @@ -122,14 +116,14 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, */ val = BMVAL(val, 5, 9); if (!val || val != 0x4) { - pr_err("%s: CONTEXTIDR_EL1 isn't supported\n", - CORESIGHT_ETM_PMU_NAME); - err = -EINVAL; - goto out; + pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", + CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); + return -EINVAL; } } - if (contextid & BIT(ETM_OPT_CTXTID2)) { + if (contextid & + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")) { /* * TRCIDR2.VMIDOPT[30:29] != 0 and * TRCIDR2.VMIDSIZE[14:10] == 0b00100 (32bit virtual contextid) @@ -138,35 +132,34 @@ static int cs_etm_set_context_id(struct auxtrace_record *itr, * Any value of VMIDSIZE >= 4 (i.e, > 32bit) is fine for us. */ if (!BMVAL(val, 29, 30) || BMVAL(val, 10, 14) < 4) { - pr_err("%s: CONTEXTIDR_EL2 isn't supported\n", - CORESIGHT_ETM_PMU_NAME); - err = -EINVAL; - goto out; + pr_err("%s: CONTEXTIDR_EL2 isn't supported, disable with %s/contextid2=0/\n", + CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); + return -EINVAL; } } - /* All good, let the kernel know */ - evsel->core.attr.config |= contextid; - err = 0; - -out: - return err; + return 0; } -static int cs_etm_set_timestamp(struct auxtrace_record *itr, - struct evsel *evsel, int cpu) +static int cs_etm_validate_timestamp(struct auxtrace_record *itr, + struct evsel *evsel, int cpu) { - struct cs_etm_recording *ptr; - struct perf_pmu *cs_etm_pmu; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu; char path[PATH_MAX]; - int err = -EINVAL; + int err; u32 val; - ptr = container_of(itr, struct cs_etm_recording, itr); - cs_etm_pmu = ptr->cs_etm_pmu; + if (!(evsel->core.attr.config & + perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp"))) + return 0; - if (!cs_etm_is_etmv4(itr, cpu)) - goto out; + if (!cs_etm_is_etmv4(itr, cpu)) { + pr_err("%s: timestamp not supported in ETMv3, disable with %s/timestamp=0/\n", + CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); + return -EINVAL; + } /* Get a handle on TRCIRD0 */ snprintf(path, PATH_MAX, "cpu%d/%s", @@ -177,7 +170,7 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr, if (err != 1) { pr_err("%s: can't read file %s\n", CORESIGHT_ETM_PMU_NAME, path); - goto out; + return err; } /* @@ -189,24 +182,21 @@ static int cs_etm_set_timestamp(struct auxtrace_record *itr, */ val &= GENMASK(28, 24); if (!val) { - err = -EINVAL; - goto out; + return -EINVAL; } - /* All good, let the kernel know */ - evsel->core.attr.config |= (1 << ETM_OPT_TS); - err = 0; - -out: - return err; + return 0; } -#define ETM_SET_OPT_CTXTID (1 << 0) -#define ETM_SET_OPT_TS (1 << 1) -#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS) - -static int cs_etm_set_option(struct auxtrace_record *itr, - struct evsel *evsel, u32 option) +/* + * Check whether the requested timestamp and contextid options should be + * available on all requested CPUs and if not, tell the user how to override. + * The kernel will silently disable any unavailable options so a warning here + * first is better. In theory the kernel could still disable the option for + * some other reason so this is best effort only. + */ +static int cs_etm_validate_config(struct auxtrace_record *itr, + struct evsel *evsel) { int i, err = -EINVAL; struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus; @@ -220,18 +210,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr, !perf_cpu_map__has(online_cpus, cpu)) continue; - if (option & BIT(ETM_OPT_CTXTID)) { - err = cs_etm_set_context_id(itr, evsel, i); - if (err) - goto out; - } - if (option & BIT(ETM_OPT_TS)) { - err = cs_etm_set_timestamp(itr, evsel, i); - if (err) - goto out; - } - if (option & ~(BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS))) - /* Nothing else is currently supported */ + err = cs_etm_validate_context_id(itr, evsel, i); + if (err) + goto out; + err = cs_etm_validate_timestamp(itr, evsel, i); + if (err) goto out; } @@ -447,10 +430,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * when a context switch happened. */ if (!perf_cpu_map__empty(cpus)) { - err = cs_etm_set_option(itr, cs_etm_evsel, - BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS)); - if (err) - goto out; + cs_etm_evsel->core.attr.config |= + perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp"); + cs_etm_evsel->core.attr.config |= + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid"); } /* Add dummy event to keep tracking */ @@ -466,6 +449,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, if (!perf_cpu_map__empty(cpus)) evsel__set_sample_bit(evsel, TIME); + err = cs_etm_validate_config(itr, cs_etm_evsel); out: return err; } -- GitLab From 7bfc1544d91121dddd3a6e7a289b03b63c660b57 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:45 +0100 Subject: [PATCH 3952/5631] perf cs-etm: Allow user to override timestamp and contextid settings Timestamps and context tracking are automatically enabled in per-core mode and it's impossible to override this. Use the new utility function to set them conditionally. Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-6-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 29 +++++++++++++++++++++++------ tools/perf/arch/arm/util/pmu.c | 2 ++ tools/perf/util/cs-etm.h | 2 ++ 3 files changed, 27 insertions(+), 6 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index af0a2400c655..77cb03e6ff87 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -324,8 +324,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, perf_can_record_switch_events()) opts->record_switch_events = true; - cs_etm_evsel->core.attr.freq = 0; - cs_etm_evsel->core.attr.sample_period = 1; cs_etm_evsel->needs_auxtrace_mmap = true; opts->full_auxtrace = true; @@ -430,10 +428,10 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, * when a context switch happened. */ if (!perf_cpu_map__empty(cpus)) { - cs_etm_evsel->core.attr.config |= - perf_pmu__format_bits(&cs_etm_pmu->format, "timestamp"); - cs_etm_evsel->core.attr.config |= - perf_pmu__format_bits(&cs_etm_pmu->format, "contextid"); + evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, + "timestamp", 1); + evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, + "contextid", 1); } /* Add dummy event to keep tracking */ @@ -914,3 +912,22 @@ struct auxtrace_record *cs_etm_record_init(int *err) out: return NULL; } + +/* + * Set a default config to enable the user changed config tracking mechanism + * (CFG_CHG and evsel__set_config_if_unset()). If no default is set then user + * changes aren't tracked. + */ +struct perf_event_attr * +cs_etm_get_default_config(struct perf_pmu *pmu __maybe_unused) +{ + struct perf_event_attr *attr; + + attr = zalloc(sizeof(struct perf_event_attr)); + if (!attr) + return NULL; + + attr->sample_period = 1; + + return attr; +} diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index 887c8addc491..860a8b42b4b5 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -12,6 +12,7 @@ #include "arm-spe.h" #include "hisi-ptt.h" #include "../../../util/pmu.h" +#include "../cs-etm.h" struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) @@ -20,6 +21,7 @@ struct perf_event_attr if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { /* add ETM default config here */ pmu->selectable = true; + return cs_etm_get_default_config(pmu); #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { return arm_spe_pmu_default_config(pmu); diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 661f029322e4..16333d35bed4 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -12,6 +12,7 @@ #include struct perf_session; +struct perf_pmu; /* * Versioning header in case things need to change in the future. That way @@ -228,6 +229,7 @@ struct cs_etm_packet_queue { int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); +struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); #ifdef HAVE_CSTRACE_SUPPORT int cs_etm__get_cpu(u8 trace_chan_id, int *cpu); -- GitLab From 1764ce069bb05c630de2f108aadb66eaa470131e Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:46 +0100 Subject: [PATCH 3953/5631] perf cs-etm: Use bool type for boolean values Using u8 for boolean values makes the code a bit more difficult to read so be more explicit by using bool. Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-7-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm-decoder/cs-etm-decoder.h | 8 ++++---- tools/perf/util/cs-etm.c | 8 ++++---- tools/perf/util/cs-etm.h | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h index 92a855fbe5b8..21d403f55d96 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h @@ -60,10 +60,10 @@ struct cs_etm_decoder_params { int operation; void (*packet_printer)(const char *msg); cs_etm_mem_cb_type mem_acc_cb; - u8 formatted; - u8 fsyncs; - u8 hsyncs; - u8 frame_aligned; + bool formatted; + bool fsyncs; + bool hsyncs; + bool frame_aligned; void *data; }; diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 50593289d53c..e048949bf655 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -50,10 +50,10 @@ struct cs_etm_auxtrace { struct thread *unknown_thread; struct perf_tsc_conversion tc; - u8 timeless_decoding; - u8 snapshot_mode; - u8 data_queued; - u8 has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */ + bool timeless_decoding; + bool snapshot_mode; + bool data_queued; + bool has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */ int num_cpu; u64 latest_kernel_timestamp; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 16333d35bed4..70cac0375b34 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -179,8 +179,8 @@ struct cs_etm_packet { u32 last_instr_subtype; u32 flags; u32 exception_number; - u8 last_instr_cond; - u8 last_instr_taken_branch; + bool last_instr_cond; + bool last_instr_taken_branch; u8 last_instr_size; u8 trace_chan_id; int cpu; -- GitLab From d1efa4a0a696e487f349f837f53a0db88f8f0d74 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 24 Apr 2023 14:47:47 +0100 Subject: [PATCH 3954/5631] perf cs-etm: Add separate decode paths for timeless and per-thread modes Timeless and per-thread are orthogonal concepts that are currently treated as if they are the same (per-thread == timeless). This breaks when you modify the command line or itrace options to something that the current logic doesn't expect. For example: # Force timeless with Z --itrace=Zi10i # Or inconsistent record options -e cs_etm/timestamp=1/ --per-thread Adding Z for decoding in per-cpu mode is particularly bad because in per-thread mode trace channel IDs are discarded and all assumed to be 0, which would mix trace from different CPUs in per-cpu mode. Although the results might not be perfect in all scenarios, if the user requests no timestamps, it should still be possible to decode in either mode. Especially if the relative times of samples in different processes aren't interesting, quite a bit of space can be saved by turning off timestamps in per-cpu mode. Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Denis Nikitin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: Yang Shi Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230424134748.228137-8-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_arm_coresight.sh | 24 +++ tools/perf/util/cs-etm.c | 162 ++++++++++++++----- 2 files changed, 148 insertions(+), 38 deletions(-) diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 565ce525c40b..482009e17bda 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -150,6 +150,8 @@ arm_cs_etm_system_wide_test() { echo "Recording trace with system wide mode" perf record -o ${perfdata} -e cs_etm// -a -- ls > /dev/null 2>&1 + # System-wide mode should include perf samples so test for that + # instead of ls perf_script_branch_samples perf && perf_report_branch_samples perf && perf_report_instruction_samples perf @@ -182,7 +184,29 @@ arm_cs_etm_snapshot_test() { arm_cs_report "CoreSight snapshot testing" $err } +arm_cs_etm_basic_test() { + echo "Recording trace with '$*'" + perf record -o ${perfdata} "$@" -- ls > /dev/null 2>&1 + + perf_script_branch_samples ls && + perf_report_branch_samples ls && + perf_report_instruction_samples ls + + err=$? + arm_cs_report "CoreSight basic testing with '$*'" $err +} + arm_cs_etm_traverse_path_test arm_cs_etm_system_wide_test arm_cs_etm_snapshot_test + +# Test all combinations of per-thread, system-wide and normal mode with +# and without timestamps +arm_cs_etm_basic_test -e cs_etm/timestamp=0/ --per-thread +arm_cs_etm_basic_test -e cs_etm/timestamp=1/ --per-thread +arm_cs_etm_basic_test -e cs_etm/timestamp=0/ -a +arm_cs_etm_basic_test -e cs_etm/timestamp=1/ -a +arm_cs_etm_basic_test -e cs_etm/timestamp=0/ +arm_cs_etm_basic_test -e cs_etm/timestamp=1/ + exit $glb_err diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index e048949bf655..456994564d6e 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -50,7 +50,22 @@ struct cs_etm_auxtrace { struct thread *unknown_thread; struct perf_tsc_conversion tc; + /* + * Timeless has no timestamps in the trace so overlapping mmap lookups + * are less accurate but produces smaller trace data. We use context IDs + * in the trace instead of matching timestamps with fork records so + * they're not really needed in the general case. Overlapping mmaps + * happen in cases like between a fork and an exec. + */ bool timeless_decoding; + + /* + * Per-thread ignores the trace channel ID and instead assumes that + * everything in a buffer comes from the same process regardless of + * which CPU it ran on. It also implies no context IDs so the TID is + * taken from the auxtrace buffer. + */ + bool per_thread_decoding; bool snapshot_mode; bool data_queued; bool has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */ @@ -98,7 +113,7 @@ struct cs_etm_queue { /* RB tree for quick conversion between traceID and metadata pointers */ static struct intlist *traceid_list; -static int cs_etm__process_queues(struct cs_etm_auxtrace *etm); +static int cs_etm__process_timestamped_queues(struct cs_etm_auxtrace *etm); static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, pid_t tid); static int cs_etm__get_data_block(struct cs_etm_queue *etmq); @@ -492,7 +507,7 @@ static struct cs_etm_traceid_queue struct cs_etm_traceid_queue *tidq, **traceid_queues; struct cs_etm_auxtrace *etm = etmq->etm; - if (etm->timeless_decoding) + if (etm->per_thread_decoding) trace_chan_id = CS_ETM_PER_THREAD_TRACEID; traceid_queues_list = etmq->traceid_queues_list; @@ -731,10 +746,15 @@ static int cs_etm__flush_events(struct perf_session *session, if (!tool->ordered_events) return -EINVAL; - if (etm->timeless_decoding) + if (etm->timeless_decoding) { + /* + * Pass tid = -1 to process all queues. But likely they will have + * already been processed on PERF_RECORD_EXIT anyway. + */ return cs_etm__process_timeless_queues(etm, -1); + } - return cs_etm__process_queues(etm); + return cs_etm__process_timestamped_queues(etm); } static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq) @@ -1066,7 +1086,7 @@ static int cs_etm__queue_first_cs_timestamp(struct cs_etm_auxtrace *etm, * chronological order. * * Note that packets decoded above are still in the traceID's packet - * queue and will be processed in cs_etm__process_queues(). + * queue and will be processed in cs_etm__process_timestamped_queues(). */ cs_queue_nr = TO_CS_QUEUE_NR(queue_nr, trace_chan_id); ret = auxtrace_heap__add(&etm->heap, cs_queue_nr, cs_timestamp); @@ -1347,9 +1367,7 @@ static inline u64 cs_etm__resolve_sample_time(struct cs_etm_queue *etmq, struct cs_etm_auxtrace *etm = etmq->etm; struct cs_etm_packet_queue *packet_queue = &tidq->packet_queue; - if (etm->timeless_decoding) - return 0; - else if (etm->has_virtual_ts) + if (!etm->timeless_decoding && etm->has_virtual_ts) return packet_queue->cs_timestamp; else return etm->latest_kernel_timestamp; @@ -2329,7 +2347,7 @@ static void cs_etm__clear_all_traceid_queues(struct cs_etm_queue *etmq) } } -static int cs_etm__run_decoder(struct cs_etm_queue *etmq) +static int cs_etm__run_per_thread_timeless_decoder(struct cs_etm_queue *etmq) { int err = 0; struct cs_etm_traceid_queue *tidq; @@ -2367,6 +2385,51 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq) return err; } +static int cs_etm__run_per_cpu_timeless_decoder(struct cs_etm_queue *etmq) +{ + int idx, err = 0; + struct cs_etm_traceid_queue *tidq; + struct int_node *inode; + + /* Go through each buffer in the queue and decode them one by one */ + while (1) { + err = cs_etm__get_data_block(etmq); + if (err <= 0) + return err; + + /* Run trace decoder until buffer consumed or end of trace */ + do { + err = cs_etm__decode_data_block(etmq); + if (err) + return err; + + /* + * cs_etm__run_per_thread_timeless_decoder() runs on a + * single traceID queue because each TID has a separate + * buffer. But here in per-cpu mode we need to iterate + * over each channel instead. + */ + intlist__for_each_entry(inode, + etmq->traceid_queues_list) { + idx = (int)(intptr_t)inode->priv; + tidq = etmq->traceid_queues[idx]; + cs_etm__process_traceid_queue(etmq, tidq); + } + } while (etmq->buf_len); + + intlist__for_each_entry(inode, etmq->traceid_queues_list) { + idx = (int)(intptr_t)inode->priv; + tidq = etmq->traceid_queues[idx]; + /* Flush any remaining branch stack entries */ + err = cs_etm__end_block(etmq, tidq); + if (err) + return err; + } + } + + return err; +} + static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, pid_t tid) { @@ -2381,22 +2444,30 @@ static int cs_etm__process_timeless_queues(struct cs_etm_auxtrace *etm, if (!etmq) continue; - tidq = cs_etm__etmq_get_traceid_queue(etmq, - CS_ETM_PER_THREAD_TRACEID); + /* + * Per-cpu mode has contextIDs in the trace and the decoder + * calls cs_etm__set_pid_tid_cpu() automatically so no need + * to do this here + */ + if (etm->per_thread_decoding) { + tidq = cs_etm__etmq_get_traceid_queue( + etmq, CS_ETM_PER_THREAD_TRACEID); - if (!tidq) - continue; + if (!tidq) + continue; - if ((tid == -1) || (tidq->tid == tid)) { - cs_etm__set_pid_tid_cpu(etm, tidq); - cs_etm__run_decoder(etmq); - } + if ((tid == -1) || (tidq->tid == tid)) { + cs_etm__set_pid_tid_cpu(etm, tidq); + cs_etm__run_per_thread_timeless_decoder(etmq); + } + } else + cs_etm__run_per_cpu_timeless_decoder(etmq); } return 0; } -static int cs_etm__process_queues(struct cs_etm_auxtrace *etm) +static int cs_etm__process_timestamped_queues(struct cs_etm_auxtrace *etm) { int ret = 0; unsigned int cs_queue_nr, queue_nr, i; @@ -2573,7 +2644,6 @@ static int cs_etm__process_event(struct perf_session *session, struct perf_sample *sample, struct perf_tool *tool) { - u64 sample_kernel_timestamp; struct cs_etm_auxtrace *etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace); @@ -2586,33 +2656,39 @@ static int cs_etm__process_event(struct perf_session *session, return -EINVAL; } - if (sample->time && (sample->time != (u64) -1)) - sample_kernel_timestamp = sample->time; - else - sample_kernel_timestamp = 0; - - /* - * Don't wait for cs_etm__flush_events() in per-thread/timeless mode to start the decode. We - * need the tid of the PERF_RECORD_EXIT event to assign to the synthesised samples because - * ETM_OPT_CTXTID is not enabled. - */ - if (etm->timeless_decoding && - event->header.type == PERF_RECORD_EXIT) - return cs_etm__process_timeless_queues(etm, - event->fork.tid); + switch (event->header.type) { + case PERF_RECORD_EXIT: + /* + * Don't need to wait for cs_etm__flush_events() in per-thread mode to + * start the decode because we know there will be no more trace from + * this thread. All this does is emit samples earlier than waiting for + * the flush in other modes, but with timestamps it makes sense to wait + * for flush so that events from different threads are interleaved + * properly. + */ + if (etm->per_thread_decoding && etm->timeless_decoding) + return cs_etm__process_timeless_queues(etm, + event->fork.tid); + break; - if (event->header.type == PERF_RECORD_ITRACE_START) + case PERF_RECORD_ITRACE_START: return cs_etm__process_itrace_start(etm, event); - else if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) + + case PERF_RECORD_SWITCH_CPU_WIDE: return cs_etm__process_switch_cpu_wide(etm, event); - if (!etm->timeless_decoding && event->header.type == PERF_RECORD_AUX) { + case PERF_RECORD_AUX: /* * Record the latest kernel timestamp available in the header * for samples so that synthesised samples occur from this point * onwards. */ - etm->latest_kernel_timestamp = sample_kernel_timestamp; + if (sample->time && (sample->time != (u64)-1)) + etm->latest_kernel_timestamp = sample->time; + break; + + default: + break; } return 0; @@ -2821,10 +2897,20 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o * Return 'not found' if mismatch. */ if (auxtrace_event->cpu == (__u32) -1) { + etm->per_thread_decoding = true; if (auxtrace_event->tid != sample->tid) return 1; - } else if (auxtrace_event->cpu != sample->cpu) + } else if (auxtrace_event->cpu != sample->cpu) { + if (etm->per_thread_decoding) { + /* + * Found a per-cpu buffer after a per-thread one was + * already found + */ + pr_err("CS ETM: Inconsistent per-thread/per-cpu mode.\n"); + return -EINVAL; + } return 1; + } if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { /* -- GitLab From fd35fdcbf75b5f31dba6c284886b676bb2145fe6 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Sun, 23 Apr 2023 15:12:31 -0700 Subject: [PATCH 3955/5631] cxl/test: Add mock test for set_timestamp Support the command testing in a unit-test fashion. Reviewed-by: Ira Weiny Signed-off-by: Davidlohr Bueso Link: https://lore.kernel.org/r/20230423221231.6357-1-dave@stgolabs.net Signed-off-by: Dan Williams --- tools/testing/cxl/test/mem.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 0fd7e7b8b44a..ba572d03c687 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -116,6 +116,7 @@ struct cxl_mockmem_data { int master_limit; struct mock_event_store mes; u8 event_buf[SZ_4K]; + u64 timestamp; }; static struct mock_event_log *event_find_log(struct device *dev, int log_type) @@ -379,6 +380,22 @@ struct cxl_event_mem_module mem_module = { } }; +static int mock_set_timestamp(struct cxl_dev_state *cxlds, + struct cxl_mbox_cmd *cmd) +{ + struct cxl_mockmem_data *mdata = dev_get_drvdata(cxlds->dev); + struct cxl_mbox_set_timestamp_in *ts = cmd->payload_in; + + if (cmd->size_in != sizeof(*ts)) + return -EINVAL; + + if (cmd->size_out != 0) + return -EINVAL; + + mdata->timestamp = le64_to_cpu(ts->timestamp); + return 0; +} + static void cxl_mock_add_event_logs(struct mock_event_store *mes) { put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, @@ -1103,6 +1120,9 @@ static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd * int rc = -EIO; switch (cmd->opcode) { + case CXL_MBOX_OP_SET_TIMESTAMP: + rc = mock_set_timestamp(cxlds, cmd); + break; case CXL_MBOX_OP_GET_SUPPORTED_LOGS: rc = mock_gsl(cmd); break; @@ -1232,6 +1252,10 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + rc = cxl_set_timestamp(cxlds); + if (rc) + return rc; + rc = cxl_dev_state_identify(cxlds); if (rc) return rc; -- GitLab From 13525645e2246ebc8a21bd656248d86022a6ee8f Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 6 Apr 2023 16:46:14 +0300 Subject: [PATCH 3956/5631] drm/dsc: fix drm_edp_dsc_sink_output_bpp() DPCD high byte usage The operator precedence between << and & is wrong, leading to the high byte being completely ignored. For example, with the 6.4 format, 32 becomes 0 and 24 becomes 8. Fix it, and remove the slightly confusing and unnecessary DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT macro while at it. Fixes: 0575650077ea ("drm/dp: DRM DP helper/macros to get DP sink DSC parameters") Cc: Stanislav Lisovskiy Cc: Manasi Navare Cc: Anusha Srivatsa Cc: # v5.0+ Signed-off-by: Jani Nikula Reviewed-by: Ankit Nautiyal Link: https://patchwork.freedesktop.org/patch/msgid/20230406134615.1422509-1-jani.nikula@intel.com --- include/drm/display/drm_dp.h | 1 - include/drm/display/drm_dp_helper.h | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 632376c291db..4545ed610958 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -286,7 +286,6 @@ #define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ # define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT 8 # define DP_DSC_MAX_BPP_DELTA_VERSION_MASK 0x06 # define DP_DSC_MAX_BPP_DELTA_AVAILABILITY 0x08 diff --git a/include/drm/display/drm_dp_helper.h b/include/drm/display/drm_dp_helper.h index ab55453f2d2c..ade9df59e156 100644 --- a/include/drm/display/drm_dp_helper.h +++ b/include/drm/display/drm_dp_helper.h @@ -181,9 +181,8 @@ static inline u16 drm_edp_dsc_sink_output_bpp(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { return dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_LOW - DP_DSC_SUPPORT] | - (dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & - DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK << - DP_DSC_MAX_BITS_PER_PIXEL_HI_SHIFT); + ((dsc_dpcd[DP_DSC_MAX_BITS_PER_PIXEL_HI - DP_DSC_SUPPORT] & + DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK) << 8); } static inline u32 -- GitLab From 0d68683838f2850dd8ff31f1121e05bfb7a2def0 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 6 Apr 2023 16:46:15 +0300 Subject: [PATCH 3957/5631] drm/dsc: fix DP_DSC_MAX_BPP_DELTA_* macro values The macro values just don't match the specs. Fix them. Fixes: 1482ec00be4a ("drm: Add missing DP DSC extended capability definitions.") Cc: Vinod Govindapillai Cc: Stanislav Lisovskiy Signed-off-by: Jani Nikula Reviewed-by: Ankit Nautiyal Link: https://patchwork.freedesktop.org/patch/msgid/20230406134615.1422509-2-jani.nikula@intel.com --- include/drm/display/drm_dp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index 4545ed610958..b8b7f990d67f 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -286,8 +286,8 @@ #define DP_DSC_MAX_BITS_PER_PIXEL_HI 0x068 /* eDP 1.4 */ # define DP_DSC_MAX_BITS_PER_PIXEL_HI_MASK (0x3 << 0) -# define DP_DSC_MAX_BPP_DELTA_VERSION_MASK 0x06 -# define DP_DSC_MAX_BPP_DELTA_AVAILABILITY 0x08 +# define DP_DSC_MAX_BPP_DELTA_VERSION_MASK (0x3 << 5) /* eDP 1.5 & DP 2.0 */ +# define DP_DSC_MAX_BPP_DELTA_AVAILABILITY (1 << 7) /* eDP 1.5 & DP 2.0 */ #define DP_DSC_DEC_COLOR_FORMAT_CAP 0x069 # define DP_DSC_RGB (1 << 0) -- GitLab From ce902336d9b3472d6104316e876e1a8752531916 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 18 Apr 2023 09:41:58 -0700 Subject: [PATCH 3958/5631] drm/msm/atomic: Don't try async if crtc not active For a similar reason as commit f2c7ca890182 ("drm/atomic-helper: Don't set deadline for modesets"), we need the crtc to be already active in order to compute a target vblank time for an async commit. Otherwise we get this splat reminding us that we are doing it wrong: ------------[ cut here ]------------ msm_dpu ae01000.mdp: drm_WARN_ON_ONCE(drm_drv_uses_atomic_modeset(dev)) WARNING: CPU: 7 PID: 1923 at drivers/gpu/drm/drm_vblank.c:728 drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 Modules linked in: snd_seq_dummy snd_seq snd_seq_device bridge stp llc tun vhost_vsock vhost vhost_iotlb vmw_vsock_virtio_transport_common vsock uinput rfcomm algif_hash algif_skcipher af_alg veth venus_dec venus_enc cros_ec_typec typec qcom_spmi_temp_alarm qcom_spmi_adc_tm5 qcom_spmi_adc5 xt_cgroup qcom_vadc_common qcom_stats hci_uart btqca xt_MASQUERADE venus_core 8021q coresight_tmc coresight_funnel coresight_etm4x coresight_replicator snd_soc_lpass_sc7180 coresight snd_soc_sc7180 ip6table_nat fuse ath10k_snoc ath10k_core ath mac80211 iio_trig_sysfs bluetooth cfg80211 cros_ec_sensors cros_ec_sensors_core ecdh_generic industrialio_triggered_buffer ecc kfifo_buf cros_ec_sensorhub r8153_ecm cdc_ether usbnet r8152 mii lzo_rle lzo_compress zram hid_vivaldi hid_google_hammer hid_vivaldi_common joydev CPU: 7 PID: 1923 Comm: DrmThread Not tainted 5.15.107-18853-g3be267609a0b-dirty #16 a1ffc1a66e79c21c3536d8c9a42e819236e39714 Hardware name: Google Wormdingler rev1+ BOE panel board (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 lr : drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x144/0x370 sp : ffffffc012e2b800 x29: ffffffc012e2b840 x28: ffffff8083676094 x27: ffffffc012e2bb28 x26: ffffff8084539800 x25: 0000000000000000 x24: ffffff8083676000 x23: ffffffd3c8cdc5a0 x22: ffffff80845b9d00 x21: ffffffc012e2b8b4 x20: ffffffc012e2b910 x19: 0000000000000001 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000010 x15: ffffffd3c8451a88 x14: 0000000000000003 x13: 0000000000000004 x12: 0000000000000001 x11: c0000000ffffdfff x10: ffffffd3c973ef58 x9 : 8ea3526b3cc95900 x8 : 8ea3526b3cc95900 x7 : 0000000000000000 x6 : 000000000000003a x5 : ffffffd3c99676cd x4 : 0000000000000000 x3 : ffffffc012e2b4b8 x2 : ffffffc012e2b4c0 x1 : 00000000ffffdfff x0 : 0000000000000000 Call trace: drm_crtc_vblank_helper_get_vblank_timestamp_internal+0x148/0x370 drm_crtc_vblank_helper_get_vblank_timestamp+0x20/0x30 drm_crtc_get_last_vbltimestamp+0x68/0xb0 drm_crtc_next_vblank_start+0x5c/0xa8 msm_atomic_commit_tail+0x264/0x664 commit_tail+0xac/0x160 drm_atomic_helper_commit+0x160/0x168 drm_atomic_commit+0xfc/0x128 drm_atomic_helper_disable_plane+0x8c/0x110 __setplane_atomic+0x10c/0x138 drm_mode_cursor_common+0x3a8/0x410 drm_mode_cursor_ioctl+0x48/0x70 drm_ioctl_kernel+0xe0/0x158 drm_ioctl+0x25c/0x4d8 __arm64_sys_ioctl+0x98/0xd0 invoke_syscall+0x4c/0x100 el0_svc_common+0x98/0x104 do_el0_svc+0x30/0x90 el0_svc+0x20/0x50 el0t_64_sync_handler+0x78/0x108 el0t_64_sync+0x1a4/0x1a8 ---[ end trace a0f587e1ab9589e8 ]--- Fixes: 52ff0d3073d2 ("drm/msm/atomic: Switch to vblank_start helper") Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532727/ Link: https://lore.kernel.org/r/20230418164158.549873-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_atomic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index d77fa9793c54..9c45d641b521 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -155,6 +155,8 @@ static bool can_do_async(struct drm_atomic_state *state, for_each_new_crtc_in_state(state, crtc, crtc_state, i) { if (drm_atomic_crtc_needs_modeset(crtc_state)) return false; + if (!crtc_state->active) + return false; if (++num_crtcs > 1) return false; *async_crtc = crtc; -- GitLab From 16eb51aba0a72b8f60c6b98d1493844230293450 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Mon, 17 Apr 2023 15:55:04 -0700 Subject: [PATCH 3959/5631] drm/msm: Fix vmap madv warning Commit d6ae7d1cd58e ("drm/msm/gem: Simplify vmap vs LRU tracking") introduced a splat in the pin_pages_locked() path for buffers that had been MADV_DONTNEED. ------------[ cut here ]------------ msm_obj->madv != 0 WARNING: CPU: 1 PID: 144 at drivers/gpu/drm/msm/msm_gem.c:230 msm_gem_pin_pages_locked+0x9c/0xd4 Modules linked in: lzo_rle cros_ec_lid_angle cros_ec_sensors cros_ec_sensors_core venus_dec venus_enc videobuf2_dma_contig cdc_ether usbnet mii uvcvideo videobuf2_vmalloc hci_uart btqca qcom_spmi_adc5 uvc qcom_spmi_temp_alarm qcom_vadc_common cros_ec_sensorhub videobuf2_memops cros_ec_typec sx9324 sx_common typec joydev bluetooth industrialio_triggered_buffer ecdh_generic kfifo_buf ecc venus_core qcom_stats v4l2_mem2mem videobuf2_v4l2 videobuf2_common ath11k_ahb ath11k mac80211 cfg80211 fuse zram zsmalloc CPU: 1 PID: 144 Comm: ring0 Tainted: G W 6.3.0-rc2-debug+ #622 Hardware name: Google Villager (rev1+) with LTE (DT) pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : msm_gem_pin_pages_locked+0x9c/0xd4 lr : msm_gem_pin_pages_locked+0x9c/0xd4 sp : ffffffc009ffbab0 x29: ffffffc009ffbab0 x28: ffffffee8da75008 x27: ffffff80a10274d0 x26: ffffff8087fe3bf8 x25: ffffff8087fe3c08 x24: 0000000000000001 x23: ffffff80891d5800 x22: ffffff809d0de480 x21: ffffff8081e5a080 x20: 0000000000000002 x19: ffffff80a3564c00 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000000a9620 x14: 0000000000000000 x13: 2d2d2d2d2d2d2d2d x12: 2d2d2d2d5d206572 x11: 656820747563205b x10: 2d2d2d2d2d2d2d2d x9 : ffffffee8c705dfc x8 : ffffffee8da75000 x7 : ffffffee8d34e6d0 x6 : 0000000000000000 x5 : 00000000000affa8 x4 : 000000000000000d x3 : ffffffee8da75008 x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffffff8088048040 Call trace: msm_gem_pin_pages_locked+0x9c/0xd4 get_vaddr+0xb0/0x150 msm_gem_get_vaddr_active+0x1c/0x28 snapshot_buf+0x90/0x10c msm_rd_dump_submit+0x30c/0x380 msm_gpu_submit+0x88/0x174 msm_job_run+0x68/0x118 drm_sched_main+0x2b8/0x3a0 kthread+0xf0/0x100 ret_from_fork+0x10/0x20 irq event stamp: 3358 hardirqs last enabled at (3357): [] __up_console_sem+0x7c/0x80 hardirqs last disabled at (3358): [] el1_dbg+0x24/0x80 softirqs last enabled at (3330): [] __do_softirq+0x21c/0x4bc softirqs last disabled at (3325): [] ____do_softirq+0x18/0x24 ---[ end trace 0000000000000000 ]--- But, as with msm_gem_get_vaddr_active(), this is a special case because we know that the buffer won't be purged evicted until it's fence is signaled. We just forgot to propagate the logic get_vaddr() to pin_pages_locked(). Fixes: d6ae7d1cd58e ("drm/msm/gem: Simplify vmap vs LRU tracking") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/532616/ Link: https://lore.kernel.org/r/20230417225504.494934-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index db6c4e281d75..cd39b9d8abdb 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -219,7 +219,8 @@ static void put_pages(struct drm_gem_object *obj) } } -static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) +static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj, + unsigned madv) { struct msm_drm_private *priv = obj->dev->dev_private; struct msm_gem_object *msm_obj = to_msm_bo(obj); @@ -227,7 +228,9 @@ static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { + if (GEM_WARN_ON(msm_obj->madv > madv)) { + DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", + msm_obj->madv, madv); return ERR_PTR(-EBUSY); } @@ -248,7 +251,7 @@ struct page **msm_gem_pin_pages(struct drm_gem_object *obj) struct page **p; msm_gem_lock(obj); - p = msm_gem_pin_pages_locked(obj); + p = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); msm_gem_unlock(obj); return p; @@ -473,10 +476,7 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma) msm_gem_assert_locked(obj); - if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) - return -EBUSY; - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, MSM_MADV_WILLNEED); if (IS_ERR(pages)) return PTR_ERR(pages); @@ -699,13 +699,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) if (obj->import_attach) return ERR_PTR(-ENODEV); - if (GEM_WARN_ON(msm_obj->madv > madv)) { - DRM_DEV_ERROR(obj->dev->dev, "Invalid madv state: %u vs %u\n", - msm_obj->madv, madv); - return ERR_PTR(-EBUSY); - } - - pages = msm_gem_pin_pages_locked(obj); + pages = msm_gem_pin_pages_locked(obj, madv); if (IS_ERR(pages)) return ERR_CAST(pages); -- GitLab From 1d29b4c223811871017542e96ac00ee562a37497 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 17 Apr 2023 23:25:48 +0900 Subject: [PATCH 3960/5631] kbuild: deb-pkg: add KDEB_SOURCE_COMPRESS to specify source compression Add KDEB_SOURCE_COMPRESS to specify the compression for the orig and debian tarballs. (cf. the existing KDEB_COMPRESS is used to specify the compression for binary packages.) Supported algorithms are gzip, bzip2, lzma, and xz, all of which are supported by dpkg-source. The current default is gzip. You can change it via the environment variable, for example, 'KDEB_SOURCE_COMPRESS=xz make deb-pkg'. Signed-off-by: Masahiro Yamada Reviewed-by: Nicolas Schier --- scripts/Makefile.package | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/scripts/Makefile.package b/scripts/Makefile.package index d8a36304b26e..b64042f62def 100644 --- a/scripts/Makefile.package +++ b/scripts/Makefile.package @@ -41,19 +41,25 @@ check-git: false; \ fi -git-config-tar.gz = -c tar.tar.gz.command="$(KGZIP)" -git-config-tar.bz2 = -c tar.tar.bz2.command="$(KBZIP2)" -git-config-tar.xz = -c tar.tar.xz.command="$(XZ)" -git-config-tar.zst = -c tar.tar.zst.command="$(ZSTD)" +git-config-tar.gz = -c tar.tar.gz.command="$(KGZIP)" +git-config-tar.bz2 = -c tar.tar.bz2.command="$(KBZIP2)" +git-config-tar.lzma = -c tar.tar.lzma.command="$(LZMA)" +git-config-tar.xz = -c tar.tar.xz.command="$(XZ)" +git-config-tar.zst = -c tar.tar.zst.command="$(ZSTD)" quiet_cmd_archive = ARCHIVE $@ cmd_archive = git -C $(srctree) $(git-config-tar$(suffix $@)) archive \ --output=$$(realpath $@) --prefix=$(basename $@)/ $(archive-args) +suffix-gzip := .gz +suffix-bzip2 := .bz2 +suffix-lzma := .lzma +suffix-xz := .xz + # Linux source tarball # --------------------------------------------------------------------------- -linux-tarballs := $(addprefix linux, .tar.gz) +linux-tarballs := $(addprefix linux, .tar.gz .tar.bz2 .tar.lzma .tar.xz) targets += $(linux-tarballs) $(linux-tarballs): archive-args = $$(cat $<) @@ -88,6 +94,19 @@ binrpm-pkg: # deb-pkg srcdeb-pkg bindeb-pkg # --------------------------------------------------------------------------- +KDEB_SOURCE_COMPRESS ?= gzip + +supported-deb-source-compress := gzip bzip2 lzma xz + +PHONY += linux.tar.unsupported-deb-src-compress +linux.tar.unsupported-deb-src-compress: + @echo "error: KDEB_SOURCE_COMPRESS=$(KDEB_SOURCE_COMPRESS) is not supported. The supported values are: $(supported-deb-source-compress)" >&2 + @false + +debian-orig-suffix := \ + $(strip $(if $(filter $(supported-deb-source-compress), $(KDEB_SOURCE_COMPRESS)), \ + $(suffix-$(KDEB_SOURCE_COMPRESS)),.unsupported-deb-src-compress)) + quiet_cmd_debianize = GEN $@ cmd_debianize = $(srctree)/scripts/package/mkdebian $(mkdebian-opts) @@ -97,9 +116,9 @@ debian: FORCE PHONY += debian-orig debian-orig: private source = $(shell dpkg-parsechangelog -S Source) debian-orig: private version = $(shell dpkg-parsechangelog -S Version | sed 's/-[^-]*$$//') -debian-orig: private orig-name = $(source)_$(version).orig.tar.gz +debian-orig: private orig-name = $(source)_$(version).orig.tar$(debian-orig-suffix) debian-orig: mkdebian-opts = --need-source -debian-orig: linux.tar.gz debian +debian-orig: linux.tar$(debian-orig-suffix) debian $(Q)if [ "$(df --output=target .. 2>/dev/null)" = "$(df --output=target $< 2>/dev/null)" ]; then \ ln -f $< ../$(orig-name); \ else \ @@ -120,7 +139,7 @@ deb-pkg srcdeb-pkg bindeb-pkg: +$(strip dpkg-buildpackage \ --build=$(build-type) --no-pre-clean --unsigned-changes \ $(if $(findstring source, $(build-type)), \ - --unsigned-source) \ + --unsigned-source --compression=$(KDEB_SOURCE_COMPRESS)) \ $(if $(findstring binary, $(build-type)), \ -r$(KBUILD_PKG_ROOTCMD) -a$$(cat debian/arch), \ --no-check-builddeps) \ -- GitLab From c90b3bbff2a097f4b6861c6d1aac18ed66f15261 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Mon, 17 Apr 2023 23:35:35 +0900 Subject: [PATCH 3961/5631] kbuild: rpm-pkg: remove kernel-drm PROVIDES This code was added more than 20 years ago. [1] I checked the kernel spec files in Fedora and OpenSUSE, but did not see 'kernel-drm'. I do not know if there exists a distro that uses it in RPM dependency. Remove this, and let's see if somebody complains about it. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/history/history.git/commit/?id=6d956df7d6b716b28c910c4f5b360c4d44d96c4d Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- scripts/package/mkspec | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index fc8ad3fbc0a9..8049f0e2c110 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -28,11 +28,6 @@ else M=DEL fi -if grep -q CONFIG_DRM=y include/config/auto.conf; then - PROVIDES=kernel-drm -fi - -PROVIDES="$PROVIDES kernel-$KERNELRELEASE" __KERNELRELEASE=$(echo $KERNELRELEASE | sed -e "s/-/_/g") EXCLUDES="$RCS_TAR_IGNORE --exclude=*vmlinux* --exclude=*.mod \ --exclude=*.o --exclude=*.ko --exclude=*.cmd --exclude=Documentation \ @@ -55,7 +50,7 @@ sed -e '/^DEL/d' -e 's/^\t*//' < Date: Tue, 11 Apr 2023 23:06:50 +0000 Subject: [PATCH 3962/5631] scsi: pm80xx: Log device registration Log combination of phy_id and device_id in device registration response. Signed-off-by: Akshat Jain Signed-off-by: Pranav Prasad Link: https://lore.kernel.org/r/20230411230650.1760757-1-pranavpp@google.com Acked-by: Jack Wang Signed-off-by: Martin K. Petersen --- drivers/scsi/pm8001/pm8001_hwi.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index ec1a9ab61814..73cd25f30ca5 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -3362,8 +3362,9 @@ int pm8001_mpi_reg_resp(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_dev = ccb->device; status = le32_to_cpu(registerRespPayload->status); device_id = le32_to_cpu(registerRespPayload->device_id); - pm8001_dbg(pm8001_ha, MSG, " register device is status = %d\n", - status); + pm8001_dbg(pm8001_ha, INIT, + "register device status %d phy_id 0x%x device_id %d\n", + status, pm8001_dev->attached_phy, device_id); switch (status) { case DEVREG_SUCCESS: pm8001_dbg(pm8001_ha, MSG, "DEVREG_SUCCESS\n"); @@ -4278,7 +4279,7 @@ int pm8001_chip_dereg_dev_req(struct pm8001_hba_info *pm8001_ha, memset(&payload, 0, sizeof(payload)); payload.tag = cpu_to_le32(1); payload.device_id = cpu_to_le32(device_id); - pm8001_dbg(pm8001_ha, MSG, "unregister device device_id = %d\n", + pm8001_dbg(pm8001_ha, INIT, "unregister device device_id %d\n", device_id); return pm8001_mpi_build_cmd(pm8001_ha, 0, opc, &payload, -- GitLab From 392e4daa8a7e3d9b103c64acef08f62f19d421aa Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Thu, 20 Apr 2023 08:50:35 -0400 Subject: [PATCH 3963/5631] scsi: ipr: Remove several unused variables MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 reports drivers/scsi/ipr.c: In function ‘ipr_init_res_entry’: drivers/scsi/ipr.c:1104:22: error: variable ‘proto’ set but not used [-Werror=unused-but-set-variable] 1104 | unsigned int proto; | ^~~~~ drivers/scsi/ipr.c: In function ‘ipr_update_res_entry’: drivers/scsi/ipr.c:1261:22: error: variable ‘proto’ set but not used [-Werror=unused-but-set-variable] 1261 | unsigned int proto; | ^~~~~ drivers/scsi/ipr.c: In function ‘ipr_change_queue_depth’: drivers/scsi/ipr.c:4417:36: error: variable ‘res’ set but not used [-Werror=unused-but-set-variable] 4417 | struct ipr_resource_entry *res; | ^~~ These variables are not used, so remove them. The lock around res is not needed so remove that. This makes ioa_cfg and lock_flags unneeded so remove them as well. Fixes: 65a15d6560df ("scsi: ipr: Remove SATA support") Signed-off-by: Tom Rix Link: https://lore.kernel.org/r/20230420125035.3888188-1-trix@redhat.com Acked-by: Brian King Signed-off-by: Martin K. Petersen --- drivers/scsi/ipr.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index d81189ba8773..4e13797b2a4a 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -1101,7 +1101,6 @@ static void ipr_init_res_entry(struct ipr_resource_entry *res, struct ipr_config_table_entry_wrapper *cfgtew) { int found = 0; - unsigned int proto; struct ipr_ioa_cfg *ioa_cfg = res->ioa_cfg; struct ipr_resource_entry *gscsi_res = NULL; @@ -1114,7 +1113,6 @@ static void ipr_init_res_entry(struct ipr_resource_entry *res, res->sdev = NULL; if (ioa_cfg->sis64) { - proto = cfgtew->u.cfgte64->proto; res->flags = be16_to_cpu(cfgtew->u.cfgte64->flags); res->res_flags = be16_to_cpu(cfgtew->u.cfgte64->res_flags); res->qmodel = IPR_QUEUEING_MODEL64(res); @@ -1160,7 +1158,6 @@ static void ipr_init_res_entry(struct ipr_resource_entry *res, set_bit(res->target, ioa_cfg->target_ids); } } else { - proto = cfgtew->u.cfgte->proto; res->qmodel = IPR_QUEUEING_MODEL(res); res->flags = cfgtew->u.cfgte->flags; if (res->flags & IPR_IS_IOA_RESOURCE) @@ -1258,7 +1255,6 @@ static void ipr_update_res_entry(struct ipr_resource_entry *res, struct ipr_config_table_entry_wrapper *cfgtew) { char buffer[IPR_MAX_RES_PATH_LENGTH]; - unsigned int proto; int new_path = 0; if (res->ioa_cfg->sis64) { @@ -1270,7 +1266,6 @@ static void ipr_update_res_entry(struct ipr_resource_entry *res, sizeof(struct ipr_std_inq_data)); res->qmodel = IPR_QUEUEING_MODEL64(res); - proto = cfgtew->u.cfgte64->proto; res->res_handle = cfgtew->u.cfgte64->res_handle; res->dev_id = cfgtew->u.cfgte64->dev_id; @@ -1299,7 +1294,6 @@ static void ipr_update_res_entry(struct ipr_resource_entry *res, sizeof(struct ipr_std_inq_data)); res->qmodel = IPR_QUEUEING_MODEL(res); - proto = cfgtew->u.cfgte->proto; res->res_handle = cfgtew->u.cfgte->res_handle; } } @@ -4413,14 +4407,6 @@ static int ipr_free_dump(struct ipr_ioa_cfg *ioa_cfg) { return 0; }; **/ static int ipr_change_queue_depth(struct scsi_device *sdev, int qdepth) { - struct ipr_ioa_cfg *ioa_cfg = (struct ipr_ioa_cfg *)sdev->host->hostdata; - struct ipr_resource_entry *res; - unsigned long lock_flags = 0; - - spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - res = (struct ipr_resource_entry *)sdev->hostdata; - spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); - scsi_change_queue_depth(sdev, qdepth); return sdev->queue_depth; } -- GitLab From 948afc69615167a3c82430f99bfd046332b89912 Mon Sep 17 00:00:00 2001 From: Alice Chao Date: Mon, 24 Apr 2023 16:03:56 +0800 Subject: [PATCH 3964/5631] scsi: ufs: core: mcq: Fix &hwq->cq_lock deadlock issue When ufshcd_err_handler() is executed, CQ event interrupt can enter waiting for the same lock. This can happen in ufshcd_handle_mcq_cq_events() and also in ufs_mtk_mcq_intr(). The following warning message will be generated when &hwq->cq_lock is used in IRQ context with IRQ enabled. Use ufshcd_mcq_poll_cqe_lock() with spin_lock_irqsave instead of spin_lock to resolve the deadlock issue. [name:lockdep&]WARNING: inconsistent lock state [name:lockdep&]-------------------------------- [name:lockdep&]inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. [name:lockdep&]kworker/u16:4/260 [HC0[0]:SC0[0]:HE1:SE1] takes: ffffff8028444600 (&hwq->cq_lock){?.-.}-{2:2}, at: ufshcd_mcq_poll_cqe_lock+0x30/0xe0 [name:lockdep&]{IN-HARDIRQ-W} state was registered at: lock_acquire+0x17c/0x33c _raw_spin_lock+0x5c/0x7c ufshcd_mcq_poll_cqe_lock+0x30/0xe0 ufs_mtk_mcq_intr+0x60/0x1bc [ufs_mediatek_mod] __handle_irq_event_percpu+0x140/0x3ec handle_irq_event+0x50/0xd8 handle_fasteoi_irq+0x148/0x2b0 generic_handle_domain_irq+0x4c/0x6c gic_handle_irq+0x58/0x134 call_on_irq_stack+0x40/0x74 do_interrupt_handler+0x84/0xe4 el1_interrupt+0x3c/0x78 Possible unsafe locking scenario: CPU0 ---- lock(&hwq->cq_lock); lock(&hwq->cq_lock); *** DEADLOCK *** 2 locks held by kworker/u16:4/260: [name:lockdep&] stack backtrace: CPU: 7 PID: 260 Comm: kworker/u16:4 Tainted: G S W OE 6.1.17-mainline-android14-2-g277223301adb #1 Workqueue: ufs_eh_wq_0 ufshcd_err_handler Call trace: dump_backtrace+0x10c/0x160 show_stack+0x20/0x30 dump_stack_lvl+0x98/0xd8 dump_stack+0x20/0x60 print_usage_bug+0x584/0x76c mark_lock_irq+0x488/0x510 mark_lock+0x1ec/0x25c __lock_acquire+0x4d8/0xffc lock_acquire+0x17c/0x33c _raw_spin_lock+0x5c/0x7c ufshcd_mcq_poll_cqe_lock+0x30/0xe0 ufshcd_poll+0x68/0x1b0 ufshcd_transfer_req_compl+0x9c/0xc8 ufshcd_err_handler+0x3bc/0xea0 process_one_work+0x2f4/0x7e8 worker_thread+0x234/0x450 kthread+0x110/0x134 ret_from_fork+0x10/0x20 Fixes: ed975065c31c ("scsi: ufs: core: mcq: Add completion support in poll") Reviewed-by: Can Guo Reviewed-by: Stanley Chu Signed-off-by: Alice Chao Link: https://lore.kernel.org/r/20230424080400.8955-1-alice.chao@mediatek.com Reviewed-by: AngeloGioacchino Del Regno Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 31df052fbc41..202ff71e1b58 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -299,11 +299,11 @@ EXPORT_SYMBOL_GPL(ufshcd_mcq_poll_cqe_nolock); unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba, struct ufs_hw_queue *hwq) { - unsigned long completed_reqs; + unsigned long completed_reqs, flags; - spin_lock(&hwq->cq_lock); + spin_lock_irqsave(&hwq->cq_lock, flags); completed_reqs = ufshcd_mcq_poll_cqe_nolock(hba, hwq); - spin_unlock(&hwq->cq_lock); + spin_unlock_irqrestore(&hwq->cq_lock, flags); return completed_reqs; } -- GitLab From c5749639f2d0a1f6cbe187d05f70c2e7c544d748 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 13 Apr 2023 11:34:22 +0800 Subject: [PATCH 3965/5631] scsi: qedi: Fix use after free bug in qedi_remove() In qedi_probe() we call __qedi_probe() which initializes &qedi->recovery_work with qedi_recovery_handler() and &qedi->board_disable_work with qedi_board_disable_work(). When qedi_schedule_recovery_handler() is called, schedule_delayed_work() will finally start the work. In qedi_remove(), which is called to remove the driver, the following sequence may be observed: Fix this by finishing the work before cleanup in qedi_remove(). CPU0 CPU1 |qedi_recovery_handler qedi_remove | __qedi_remove | iscsi_host_free | scsi_host_put | //free shost | |iscsi_host_for_each_session |//use qedi->shost Cancel recovery_work and board_disable_work in __qedi_remove(). Fixes: 4b1068f5d74b ("scsi: qedi: Add MFW error recovery process") Signed-off-by: Zheng Wang Link: https://lore.kernel.org/r/20230413033422.28003-1-zyytlz.wz@163.com Acked-by: Manish Rangankar Reviewed-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/scsi/qedi/qedi_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index f2ee49756df8..45d359554182 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -2450,6 +2450,9 @@ static void __qedi_remove(struct pci_dev *pdev, int mode) qedi_ops->ll2->stop(qedi->cdev); } + cancel_delayed_work_sync(&qedi->recovery_work); + cancel_delayed_work_sync(&qedi->board_disable_work); + qedi_free_iscsi_pf_param(qedi); rval = qedi_ops->common->update_drv_state(qedi->cdev, false); -- GitLab From 8bc6666f13fe1971cb870e5e0c3082435e3caa9c Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 23 Mar 2023 11:18:07 +0100 Subject: [PATCH 3966/5631] sh: Use generic GCC library routines The C implementations of __ashldi3(), __ashrdi3__(), and __lshrdi3() in arch/sh/lib/ are identical to the generic C implementations in lib/. Reduce duplication by switching SH to the generic versions. Update the include path in arch/sh/boot/compressed accordingly. Signed-off-by: Geert Uytterhoeven Acked-by: Palmer Dabbelt Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/74dbe68dc8e2ffb6180092f73723fe21ab692c7a.1679566500.git.geert+renesas@glider.be Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/Kconfig | 3 +++ arch/sh/boot/compressed/ashldi3.c | 4 ++-- arch/sh/lib/Makefile | 4 +--- arch/sh/lib/ashldi3.c | 30 ----------------------------- arch/sh/lib/ashrdi3.c | 32 ------------------------------- arch/sh/lib/lshrdi3.c | 30 ----------------------------- 6 files changed, 6 insertions(+), 97 deletions(-) delete mode 100644 arch/sh/lib/ashldi3.c delete mode 100644 arch/sh/lib/ashrdi3.c delete mode 100644 arch/sh/lib/lshrdi3.c diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 0665ac0add0b..d08579ac6f0b 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -21,6 +21,9 @@ config SUPERH select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_SHOW + select GENERIC_LIB_ASHLDI3 + select GENERIC_LIB_ASHRDI3 + select GENERIC_LIB_LSHRDI3 select GENERIC_PCI_IOMAP if PCI select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD diff --git a/arch/sh/boot/compressed/ashldi3.c b/arch/sh/boot/compressed/ashldi3.c index 7cebd646df83..7c1212170230 100644 --- a/arch/sh/boot/compressed/ashldi3.c +++ b/arch/sh/boot/compressed/ashldi3.c @@ -1,2 +1,2 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include "../../lib/ashldi3.c" +// SPDX-License-Identifier: GPL-2.0-or-later +#include "../../../../lib/ashldi3.c" diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile index eb473d373ca4..d20a0768b31f 100644 --- a/arch/sh/lib/Makefile +++ b/arch/sh/lib/Makefile @@ -7,9 +7,7 @@ lib-y = delay.o memmove.o memchr.o \ checksum.o strlen.o div64.o div64-generic.o # Extracted from libgcc -obj-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \ - ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \ - udiv_qrnnd.o +obj-y += movmem.o ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o udiv_qrnnd.o udivsi3-y := udivsi3_i4i-Os.o diff --git a/arch/sh/lib/ashldi3.c b/arch/sh/lib/ashldi3.c deleted file mode 100644 index e5afe0935847..000000000000 --- a/arch/sh/lib/ashldi3.c +++ /dev/null @@ -1,30 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __ashldi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - w.s.low = 0; - w.s.high = (unsigned int) uu.s.low << -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.low >> bm; - - w.s.low = (unsigned int) uu.s.low << b; - w.s.high = ((unsigned int) uu.s.high << b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__ashldi3); diff --git a/arch/sh/lib/ashrdi3.c b/arch/sh/lib/ashrdi3.c deleted file mode 100644 index ae263fbf2538..000000000000 --- a/arch/sh/lib/ashrdi3.c +++ /dev/null @@ -1,32 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __ashrdi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - /* w.s.high = 1..1 or 0..0 */ - w.s.high = - uu.s.high >> 31; - w.s.low = uu.s.high >> -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.high << bm; - - w.s.high = uu.s.high >> b; - w.s.low = ((unsigned int) uu.s.low >> b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__ashrdi3); diff --git a/arch/sh/lib/lshrdi3.c b/arch/sh/lib/lshrdi3.c deleted file mode 100644 index 33eaa1edbc3c..000000000000 --- a/arch/sh/lib/lshrdi3.c +++ /dev/null @@ -1,30 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include - -#include "libgcc.h" - -long long __lshrdi3(long long u, word_type b) -{ - DWunion uu, w; - word_type bm; - - if (b == 0) - return u; - - uu.ll = u; - bm = 32 - b; - - if (bm <= 0) { - w.s.high = 0; - w.s.low = (unsigned int) uu.s.high >> -bm; - } else { - const unsigned int carries = (unsigned int) uu.s.high << bm; - - w.s.high = (unsigned int) uu.s.high >> b; - w.s.low = ((unsigned int) uu.s.low >> b) | carries; - } - - return w.ll; -} - -EXPORT_SYMBOL(__lshrdi3); -- GitLab From e5c23bec0f121b4160dc8ca61e751e734652bd05 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 23 Mar 2023 11:22:59 +0100 Subject: [PATCH 3967/5631] sh: Replace by As arch/sh/include/uapi/asm/types.h doesn't exist, sh doesn't provide any sh-specific uapi definitions, and it can just include , like most other architectures. Signed-off-by: Geert Uytterhoeven Reviewed-by: John Paul Adrian Glaubitz Link: https://lore.kernel.org/r/26932016c83c2ad350db59f5daf96117a38bbbd8.1679566927.git.geert@linux-m68k.org Signed-off-by: John Paul Adrian Glaubitz --- arch/sh/include/asm/types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/asm/types.h b/arch/sh/include/asm/types.h index 68eb24ad2013..9b3fc923ee28 100644 --- a/arch/sh/include/asm/types.h +++ b/arch/sh/include/asm/types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SH_TYPES_H #define __ASM_SH_TYPES_H -#include +#include /* * These aren't exported outside the kernel to avoid name space clashes -- GitLab From 5fc46f94219d1d103ffb5f0832be9da674d85a73 Mon Sep 17 00:00:00 2001 From: Martin Willi Date: Tue, 25 Apr 2023 09:46:18 +0200 Subject: [PATCH 3968/5631] Revert "Fix XFRM-I support for nested ESP tunnels" This reverts commit b0355dbbf13c0052931dd14c38c789efed64d3de. The reverted commit clears the secpath on packets received via xfrm interfaces to support nested IPsec tunnels. This breaks Netfilter policy matching using xt_policy in the FORWARD chain, as the secpath is missing during forwarding. Additionally, Benedict Wong reports that it breaks Transport-in-Tunnel mode. Fix this regression by reverting the commit until we have a better approach for nested IPsec tunnels. Fixes: b0355dbbf13c ("Fix XFRM-I support for nested ESP tunnels") Link: https://lore.kernel.org/netdev/20230412085615.124791-1-martin@strongswan.org/ Signed-off-by: Martin Willi Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_interface_core.c | 54 +++------------------------------- net/xfrm/xfrm_policy.c | 3 -- 2 files changed, 4 insertions(+), 53 deletions(-) diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 35279c220bd7..1f99dc469027 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,52 +310,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } -static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type, unsigned short family) -{ - struct sec_path *sp; - - sp = skb_sec_path(skb); - if (sp && (sp->len || sp->olen) && - !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) - goto discard; - - XFRM_SPI_SKB_CB(skb)->family = family; - if (family == AF_INET) { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; - } else { - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); - XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; - } - - return xfrm_input(skb, nexthdr, spi, encap_type); -discard: - kfree_skb(skb); - return 0; -} - -static int xfrmi4_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); -} - -static int xfrmi6_rcv(struct sk_buff *skb) -{ - return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], - 0, 0, AF_INET6); -} - -static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); -} - -static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) -{ - return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); -} - static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -991,8 +945,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrmi6_rcv, - .input_handler = xfrmi6_input, + .handler = xfrm6_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -1042,8 +996,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrmi4_rcv, - .input_handler = xfrmi4_input, + .handler = xfrm4_rcv, + .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 62be042f2ebc..21a3a1cd3d6d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3739,9 +3739,6 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } - if (if_id) - secpath_reset(skb); - xfrm_pols_put(pols, npols); return 1; } -- GitLab From 6935321eccf32555e6f7e6d29f4cccf84a5c1e3a Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 12 Dec 2022 09:41:34 +0100 Subject: [PATCH 3969/5631] xen/blkback: fix white space code style issues MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Juergen Gross Acked-by: Roger Pau Monné Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/blkback.c | 2 +- drivers/block/xen-blkback/common.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index a5cf7f1e871c..6e2163aaf362 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -891,7 +891,7 @@ static int xen_blkbk_map(struct xen_blkif_ring *ring, out: for (i = last_map; i < num; i++) { /* Don't zap current batch's valid persistent grants. */ - if(i >= map_until) + if (i >= map_until) pages[i]->persistent_gnt = NULL; pages[i]->handle = BLKBACK_INVALID_HANDLE; } diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index a28473470e66..9a13a6b420a6 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -296,7 +296,7 @@ struct xen_blkif_ring { struct work_struct free_work; /* Thread shutdown wait queue. */ wait_queue_head_t shutdown_wq; - struct xen_blkif *blkif; + struct xen_blkif *blkif; }; struct xen_blkif { @@ -315,7 +315,7 @@ struct xen_blkif { atomic_t drain; struct work_struct free_work; - unsigned int nr_ring_pages; + unsigned int nr_ring_pages; bool multi_ref; /* All rings for this device. */ struct xen_blkif_ring *rings; @@ -329,7 +329,7 @@ struct seg_buf { }; struct grant_page { - struct page *page; + struct page *page; struct persistent_gnt *persistent_gnt; grant_handle_t handle; grant_ref_t gref; -- GitLab From 656f3c1d7966ea65f9b51d17db3008ce5dbb4090 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 12 Dec 2022 09:43:28 +0100 Subject: [PATCH 3970/5631] xen/blkback: remove stale prototype MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no function xen_blkif_purge_persistent(), so remove its prototype from common.h. Signed-off-by: Juergen Gross Acked-by: Roger Pau Monné Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/common.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 9a13a6b420a6..fab8a8dee0da 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -384,7 +384,6 @@ void xen_blkif_xenbus_fini(void); irqreturn_t xen_blkif_be_int(int irq, void *dev_id); int xen_blkif_schedule(void *arg); -int xen_blkif_purge_persistent(void *arg); void xen_blkbk_free_caches(struct xen_blkif_ring *ring); int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, -- GitLab From e7b4c07d4b42676691f3c815f05c1bbf071dc718 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 12 Dec 2022 10:37:42 +0100 Subject: [PATCH 3971/5631] xen/blkback: simplify free_persistent_gnts() interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The interface of free_persistent_gnts() can be simplified, as there is only a single caller of free_persistent_gnts() and the 2nd and 3rd parameters are easily obtainable via the ring pointer, which is passed as the first parameter anyway. Signed-off-by: Juergen Gross Acked-by: Roger Pau Monné Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/blkback.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 6e2163aaf362..243712b59a05 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -239,9 +239,9 @@ static void put_persistent_gnt(struct xen_blkif_ring *ring, atomic_dec(&ring->persistent_gnt_in_use); } -static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *root, - unsigned int num) +static void free_persistent_gnts(struct xen_blkif_ring *ring) { + struct rb_root *root = &ring->persistent_gnts; struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct persistent_gnt *persistent_gnt; @@ -249,6 +249,9 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro int segs_to_unmap = 0; struct gntab_unmap_queue_data unmap_data; + if (RB_EMPTY_ROOT(root)) + return; + unmap_data.pages = pages; unmap_data.unmap_ops = unmap; unmap_data.kunmap_ops = NULL; @@ -277,9 +280,11 @@ static void free_persistent_gnts(struct xen_blkif_ring *ring, struct rb_root *ro rb_erase(&persistent_gnt->node, root); kfree(persistent_gnt); - num--; + ring->persistent_gnt_c--; } - BUG_ON(num != 0); + + BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); + BUG_ON(ring->persistent_gnt_c != 0); } void xen_blkbk_unmap_purged_grants(struct work_struct *work) @@ -631,12 +636,7 @@ int xen_blkif_schedule(void *arg) void xen_blkbk_free_caches(struct xen_blkif_ring *ring) { /* Free all persistent grant pages */ - if (!RB_EMPTY_ROOT(&ring->persistent_gnts)) - free_persistent_gnts(ring, &ring->persistent_gnts, - ring->persistent_gnt_c); - - BUG_ON(!RB_EMPTY_ROOT(&ring->persistent_gnts)); - ring->persistent_gnt_c = 0; + free_persistent_gnts(ring); /* Since we are shutting down remove all pages from the buffer */ gnttab_page_cache_shrink(&ring->free_pages, 0 /* All */); -- GitLab From cbfac7707ba16619006a4fd60faac46303fd2f3e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 16 Dec 2022 14:49:18 +0100 Subject: [PATCH 3972/5631] xen/blkback: move blkif_get_x86_*_req() into blkback.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There is no need to have the functions blkif_get_x86_32_req() and blkif_get_x86_64_req() in a header file, as they are used in one place only. So move them into the using source file and drop the inline qualifier. While at it fix some style issues, and simplify the code by variable reusing and using min() instead of open coding it. Instead of using barrier() use READ_ONCE() for avoiding multiple reads of nr_segments. Signed-off-by: Juergen Gross Acked-by: Roger Pau Monné Signed-off-by: Juergen Gross --- drivers/block/xen-blkback/blkback.c | 104 ++++++++++++++++++++++++++++ drivers/block/xen-blkback/common.h | 96 ------------------------- 2 files changed, 104 insertions(+), 96 deletions(-) diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 243712b59a05..c362f4ad80ab 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -1072,7 +1072,111 @@ static void end_block_io_op(struct bio *bio) bio_put(bio); } +static void blkif_get_x86_32_req(struct blkif_request *dst, + const struct blkif_x86_32_request *src) +{ + unsigned int i, n; + + dst->operation = READ_ONCE(src->operation); + + switch (dst->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments); + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST, + dst->u.rw.nr_segments); + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = + READ_ONCE(src->u.indirect.nr_segments); + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + n = min(MAX_INDIRECT_PAGES, + INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < n; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} +static void blkif_get_x86_64_req(struct blkif_request *dst, + const struct blkif_x86_64_request *src) +{ + unsigned int i, n; + + dst->operation = READ_ONCE(src->operation); + + switch (dst->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = READ_ONCE(src->u.rw.nr_segments); + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + n = min_t(unsigned int, BLKIF_MAX_SEGMENTS_PER_REQUEST, + dst->u.rw.nr_segments); + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = + READ_ONCE(src->u.indirect.nr_segments); + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + n = min(MAX_INDIRECT_PAGES, + INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < n; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} /* * Function to copy the from the ring buffer the 'struct blkif_request' diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index fab8a8dee0da..40f67bfc052d 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -394,100 +394,4 @@ int xen_blkbk_barrier(struct xenbus_transaction xbt, struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be); void xen_blkbk_unmap_purged_grants(struct work_struct *work); -static inline void blkif_get_x86_32_req(struct blkif_request *dst, - struct blkif_x86_32_request *src) -{ - int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = READ_ONCE(src->operation); - switch (dst->operation) { - case BLKIF_OP_READ: - case BLKIF_OP_WRITE: - case BLKIF_OP_WRITE_BARRIER: - case BLKIF_OP_FLUSH_DISKCACHE: - dst->u.rw.nr_segments = src->u.rw.nr_segments; - dst->u.rw.handle = src->u.rw.handle; - dst->u.rw.id = src->u.rw.id; - dst->u.rw.sector_number = src->u.rw.sector_number; - barrier(); - if (n > dst->u.rw.nr_segments) - n = dst->u.rw.nr_segments; - for (i = 0; i < n; i++) - dst->u.rw.seg[i] = src->u.rw.seg[i]; - break; - case BLKIF_OP_DISCARD: - dst->u.discard.flag = src->u.discard.flag; - dst->u.discard.id = src->u.discard.id; - dst->u.discard.sector_number = src->u.discard.sector_number; - dst->u.discard.nr_sectors = src->u.discard.nr_sectors; - break; - case BLKIF_OP_INDIRECT: - dst->u.indirect.indirect_op = src->u.indirect.indirect_op; - dst->u.indirect.nr_segments = src->u.indirect.nr_segments; - dst->u.indirect.handle = src->u.indirect.handle; - dst->u.indirect.id = src->u.indirect.id; - dst->u.indirect.sector_number = src->u.indirect.sector_number; - barrier(); - j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); - for (i = 0; i < j; i++) - dst->u.indirect.indirect_grefs[i] = - src->u.indirect.indirect_grefs[i]; - break; - default: - /* - * Don't know how to translate this op. Only get the - * ID so failure can be reported to the frontend. - */ - dst->u.other.id = src->u.other.id; - break; - } -} - -static inline void blkif_get_x86_64_req(struct blkif_request *dst, - struct blkif_x86_64_request *src) -{ - int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; - dst->operation = READ_ONCE(src->operation); - switch (dst->operation) { - case BLKIF_OP_READ: - case BLKIF_OP_WRITE: - case BLKIF_OP_WRITE_BARRIER: - case BLKIF_OP_FLUSH_DISKCACHE: - dst->u.rw.nr_segments = src->u.rw.nr_segments; - dst->u.rw.handle = src->u.rw.handle; - dst->u.rw.id = src->u.rw.id; - dst->u.rw.sector_number = src->u.rw.sector_number; - barrier(); - if (n > dst->u.rw.nr_segments) - n = dst->u.rw.nr_segments; - for (i = 0; i < n; i++) - dst->u.rw.seg[i] = src->u.rw.seg[i]; - break; - case BLKIF_OP_DISCARD: - dst->u.discard.flag = src->u.discard.flag; - dst->u.discard.id = src->u.discard.id; - dst->u.discard.sector_number = src->u.discard.sector_number; - dst->u.discard.nr_sectors = src->u.discard.nr_sectors; - break; - case BLKIF_OP_INDIRECT: - dst->u.indirect.indirect_op = src->u.indirect.indirect_op; - dst->u.indirect.nr_segments = src->u.indirect.nr_segments; - dst->u.indirect.handle = src->u.indirect.handle; - dst->u.indirect.id = src->u.indirect.id; - dst->u.indirect.sector_number = src->u.indirect.sector_number; - barrier(); - j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); - for (i = 0; i < j; i++) - dst->u.indirect.indirect_grefs[i] = - src->u.indirect.indirect_grefs[i]; - break; - default: - /* - * Don't know how to translate this op. Only get the - * ID so failure can be reported to the frontend. - */ - dst->u.other.id = src->u.other.id; - break; - } -} - #endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */ -- GitLab From c915d8f5918bea7c3962b09b8884ca128bfd9b0c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 24 Apr 2023 18:32:19 +0200 Subject: [PATCH 3973/5631] inotify: Avoid reporting event with invalid wd When inotify_freeing_mark() races with inotify_handle_inode_event() it can happen that inotify_handle_inode_event() sees that i_mark->wd got already reset to -1 and reports this value to userspace which can confuse the inotify listener. Avoid the problem by validating that wd is sensible (and pretend the mark got removed before the event got generated otherwise). CC: stable@vger.kernel.org Fixes: 7e790dd5fc93 ("inotify: fix error paths in inotify_update_watch") Message-Id: <20230424163219.9250-1-jack@suse.cz> Reported-by: syzbot+4a06d4373fd52f0b2f9c@syzkaller.appspotmail.com Reviewed-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/inotify/inotify_fsnotify.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 49cfe2ae6d23..993375f0db67 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -65,7 +65,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, struct fsnotify_event *fsn_event; struct fsnotify_group *group = inode_mark->group; int ret; - int len = 0; + int len = 0, wd; int alloc_len = sizeof(struct inotify_event_info); struct mem_cgroup *old_memcg; @@ -80,6 +80,13 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); + /* + * We can be racing with mark being detached. Don't report event with + * invalid wd. + */ + wd = READ_ONCE(i_mark->wd); + if (wd == -1) + return 0; /* * Whoever is interested in the event, pays for the allocation. Do not * trigger OOM killer in the target monitoring memcg as it may have @@ -110,7 +117,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, fsn_event = &event->fse; fsnotify_init_event(fsn_event); event->mask = mask; - event->wd = i_mark->wd; + event->wd = wd; event->sync_cookie = cookie; event->name_len = len; if (len) -- GitLab From 38c8e3dfb2a1be863b7f5aad7755d5e9727da8a5 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 25 Apr 2023 11:41:54 +0800 Subject: [PATCH 3974/5631] block: sync part's ->bd_has_submit_bio with disk's submit_bio() always uses bio->bi_bdev->bd_has_submit_bio to decide if disk's ->submit_bio() is called, and bio->bi_bdev could point to one partition device. So we have to sync part bdev's ->bd_has_submit_bio with disk's. Reported-by: Changhui Zhong Link: https://lore.kernel.org/linux-block/ZEdItaPqif8fp85H@ovpn-8-24.pek2.redhat.com/T/#t Fixes: 9f4107b07b17 ("block: store bdev->bd_disk->fops->submit_bio state in bdev") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230425034154.110099-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/bdev.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/block/bdev.c b/block/bdev.c index 717089a5726f..21c63bfef323 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -418,8 +418,11 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) bdev->bd_partno = partno; bdev->bd_inode = inode; bdev->bd_queue = disk->queue; + if (partno) + bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio; + else + bdev->bd_has_submit_bio = false; bdev->bd_stats = alloc_percpu(struct disk_stats); - bdev->bd_has_submit_bio = false; if (!bdev->bd_stats) { iput(inode); return NULL; -- GitLab From 3f89ac587baa0c0460c977d1596e16f950815f05 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 24 Apr 2023 16:46:28 -0700 Subject: [PATCH 3975/5631] block/drivers: remove dead clear of random flag QUEUE_FLAG_ADD_RANDOM is not set before we clear it for "null_blk", "brd", "nbd", "zram", and "bcache" since by default we don't set "QUEUE_FLAG_ADD_RANDOM" to MQ ops. Remove dead clear of QUEUE_FLAG_ADD_RANDOM in above listed drivers. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Sergey Senozhatsky #zram Link: https://lore.kernel.org/r/20230424234628.45544-2-kch@nvidia.com Signed-off-by: Jens Axboe --- drivers/block/brd.c | 1 - drivers/block/nbd.c | 1 - drivers/block/null_blk/main.c | 1 - drivers/block/zram/zram_drv.c | 1 - drivers/md/bcache/super.c | 1 - 5 files changed, 5 deletions(-) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 34177f1bd97d..bcad9b926b0c 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -404,7 +404,6 @@ static int brd_alloc(int i) /* Tell the block layer that this is not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); blk_queue_flag_set(QUEUE_FLAG_NOWAIT, disk->queue); err = add_disk(disk); if (err) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index d445fd0934bd..7c96ec4e99df 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1805,7 +1805,6 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) * Tell the block layer that we are not a rotational device */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); disk->queue->limits.discard_granularity = 0; blk_queue_max_discard_sectors(disk->queue, 0); blk_queue_max_segment_size(disk->queue, UINT_MAX); diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index fcb61f1d5437..a60671a42de9 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -2145,7 +2145,6 @@ static int null_add_dev(struct nullb_device *dev) nullb->q->queuedata = nullb; blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q); mutex_lock(&lock); rv = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index aa490da3cef2..f7d4c0d5ad0d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -2323,7 +2323,6 @@ static int zram_add(void) /* zram devices sort of resembles non-rotational disks */ blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue); blk_queue_flag_set(QUEUE_FLAG_SYNCHRONOUS, zram->disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); /* * To ensure that we always get PAGE_SIZE aligned diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index ba3909bb6bea..7e9d19fd21dd 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -971,7 +971,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, } blk_queue_flag_set(QUEUE_FLAG_NONROT, d->disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, d->disk->queue); blk_queue_write_cache(q, true, true); -- GitLab From 0f99fc513ddd28de155c58547824a9fd63daacea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 24 Apr 2023 16:32:55 -0600 Subject: [PATCH 3976/5631] splice: clear FMODE_NOWAIT on file if splice/vmsplice is used In preparation for pipes setting FMODE_NOWAIT on pipes to indicate that RWF_NOWAIT/IOCB_NOWAIT is fully supported, have splice and vmsplice clear that file flag. Splice holds the pipe lock around IO and cannot easily be refactored to avoid that, as splice and pipes are inherently tied together. By clearing FMODE_NOWAIT if splice is being used on a pipe, other users of the pipe will know that the pipe is no longer safe for RWF_NOWAIT and friends. Suggested-by: Linus Torvalds Signed-off-by: Jens Axboe --- fs/splice.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/fs/splice.c b/fs/splice.c index 2c3dec2b6dfa..7aa90cfe91ba 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -37,6 +37,22 @@ #include "internal.h" +/* + * Splice doesn't support FMODE_NOWAIT. Since pipes may set this flag to + * indicate they support non-blocking reads or writes, we must clear it + * here if set to avoid blocking other users of this pipe if splice is + * being done on it. + */ +static noinline void noinline pipe_clear_nowait(struct file *file) +{ + fmode_t fmode = READ_ONCE(file->f_mode); + + do { + if (!(fmode & FMODE_NOWAIT)) + break; + } while (!try_cmpxchg(&file->f_mode, &fmode, fmode & ~FMODE_NOWAIT)); +} + /* * Attempt to steal a page from a pipe buffer. This should perhaps go into * a vm helper function, it's already simplified quite a bit by the @@ -1211,10 +1227,16 @@ static long __do_splice(struct file *in, loff_t __user *off_in, ipipe = get_pipe_info(in, true); opipe = get_pipe_info(out, true); - if (ipipe && off_in) - return -ESPIPE; - if (opipe && off_out) - return -ESPIPE; + if (ipipe) { + if (off_in) + return -ESPIPE; + pipe_clear_nowait(in); + } + if (opipe) { + if (off_out) + return -ESPIPE; + pipe_clear_nowait(out); + } if (off_out) { if (copy_from_user(&offset, off_out, sizeof(loff_t))) @@ -1311,6 +1333,8 @@ static long vmsplice_to_user(struct file *file, struct iov_iter *iter, if (!pipe) return -EBADF; + pipe_clear_nowait(file); + if (sd.total_len) { pipe_lock(pipe); ret = __splice_from_pipe(pipe, &sd, pipe_to_user); @@ -1339,6 +1363,8 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter, if (!pipe) return -EBADF; + pipe_clear_nowait(file); + pipe_lock(pipe); ret = wait_for_space(pipe, flags); if (!ret) -- GitLab From afed6271f5b0d78ca1a3739c1da4aa3629b26bba Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Mar 2023 17:56:28 -0700 Subject: [PATCH 3977/5631] pipe: set FMODE_NOWAIT on pipes Pipes themselves do not hold the the pipe lock across IO, and hence are safe for RWF_NOWAIT/IOCB_NOWAIT usage. The "contract" for NOWAIT is really "should not do IO under this lock", not strictly that we cannot block or that the below code is in any way atomic. Pipes fulfil that criteria. Acked-by: Dave Chinner Reviewed-by: Christian Brauner Signed-off-by: Jens Axboe --- fs/pipe.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/pipe.c b/fs/pipe.c index 42c7ff41c2db..ceb17d2dfa19 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -976,6 +976,9 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags) audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; + /* pipe groks IOCB_NOWAIT */ + files[0]->f_mode |= FMODE_NOWAIT; + files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: -- GitLab From a99d0d5f4a53f31e0d9c8f3d03436d9709116b6b Mon Sep 17 00:00:00 2001 From: Rong Tao Date: Mon, 24 Apr 2023 18:46:06 +0800 Subject: [PATCH 3978/5631] rtla: Add .gitignore file Add .gitignore file to ignore the rtla binary. Link: https://lore.kernel.org/linux-trace-devel/tencent_3C22A3418CD06196C2E5A84AE3EBC2281206@qq.com Signed-off-by: Rong Tao Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- tools/tracing/rtla/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/tracing/rtla/.gitignore diff --git a/tools/tracing/rtla/.gitignore b/tools/tracing/rtla/.gitignore new file mode 100644 index 000000000000..e9df32419b2b --- /dev/null +++ b/tools/tracing/rtla/.gitignore @@ -0,0 +1 @@ +/rtla -- GitLab From 54a0dffa62de0c91b406ff32082a121ccfa0d7f1 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Mon, 24 Apr 2023 10:47:30 +0100 Subject: [PATCH 3979/5631] rv: Fix addition on an uninitialized variable 'run' The variable run is not initialized however it is being accumulated by the return value from the call to ikm_run_monitor. Fix this by initializing run to zero at the start of the function. Link: https://lkml.kernel.org/r/20230424094730.105313-1-colin.i.king@gmail.com Fixes: 4bc4b131d44c ("rv: Add rv tool") Signed-off-by: Colin Ian King Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- tools/verification/rv/src/rv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/verification/rv/src/rv.c b/tools/verification/rv/src/rv.c index e601cd9c411e..1ddb85532816 100644 --- a/tools/verification/rv/src/rv.c +++ b/tools/verification/rv/src/rv.c @@ -74,7 +74,7 @@ static void rv_list(int argc, char **argv) static void rv_mon(int argc, char **argv) { char *monitor_name; - int i, run; + int i, run = 0; static const char *const usage[] = { "", -- GitLab From 73e053cbd00ed890abfc812d6c602cbfa8d234dc Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 18 Apr 2023 16:00:18 +0100 Subject: [PATCH 3980/5631] rv: Remove redundant assignment to variable retval Variable retval is being assigned a value that is never read, it is being re-assigned a new value in both paths of a following if statement. Remove the assignment. Cleans up clang-scan warning: kernel/trace/rv/rv.c:293:2: warning: Value stored to 'retval' is never read [deadcode.DeadStores] retval = count; Link: https://lkml.kernel.org/r/20230418150018.3123753-1-colin.i.king@gmail.com Cc: Masami Hiramatsu Signed-off-by: Colin Ian King Acked-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 7e9061828c24..2f68e93fff0b 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -290,8 +290,6 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u if (retval) return retval; - retval = count; - mutex_lock(&rv_interface_lock); if (val) -- GitLab From 9fa48a2477de747b644c778a1e35d679cabcd917 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Wed, 29 Mar 2023 18:23:32 +0200 Subject: [PATCH 3981/5631] rtla/timerlat: Add auto-analysis only option Parsing and formating timerlat data might consume a reasonable amount of CPU time on very large systems, or when timerlat has a too short period. Add an option to run timerlat with auto-analysis enabled while skipping the statistics parsing. In this mode, rtla timerlat periodically checks if the tracing is on, going to sleep waiting for the stop tracing condition to stop tracing, or for the tracing session to finish. If the stop tracing condition is hit, the tool prints the auto analysis. Otherwise, the tool prints the max observed latency and exit. The max observed latency is captured via tracing_max_latency. Link: https://lore.kernel.org/linux-trace-devel/4dc514d1d5dc353c537a466a9b5af44c266b6da2.1680106912.git.bristot@kernel.org Cc: Jonathan Corbet Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- .../tools/rtla/common_timerlat_aa.rst | 7 +++ tools/tracing/rtla/src/timerlat_top.c | 49 +++++++++++++++++-- 2 files changed, 51 insertions(+), 5 deletions(-) diff --git a/Documentation/tools/rtla/common_timerlat_aa.rst b/Documentation/tools/rtla/common_timerlat_aa.rst index 077029e6b289..795b9fbcbc6d 100644 --- a/Documentation/tools/rtla/common_timerlat_aa.rst +++ b/Documentation/tools/rtla/common_timerlat_aa.rst @@ -5,3 +5,10 @@ **--no-aa** disable auto-analysis, reducing rtla timerlat cpu usage + +**--aa-only** *us* + + Set stop tracing conditions and run without collecting and displaying statistics. + Print the auto-analysis if the system hits the stop tracing condition. This option + is useful to reduce rtla timerlat CPU, enabling the debug without the overhead of + collecting the statistics. diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c index eea5b3357e27..92c658c64f28 100644 --- a/tools/tracing/rtla/src/timerlat_top.c +++ b/tools/tracing/rtla/src/timerlat_top.c @@ -33,6 +33,7 @@ struct timerlat_top_params { int set_sched; int dma_latency; int no_aa; + int aa_only; int dump_tasks; struct sched_attr sched_param; struct trace_events *events; @@ -142,10 +143,12 @@ timerlat_top_handler(struct trace_seq *s, struct tep_record *record, top = container_of(trace, struct osnoise_tool, trace); params = top->params; - tep_get_field_val(s, event, "context", record, &thread, 1); - tep_get_field_val(s, event, "timer_latency", record, &latency, 1); + if (!params->aa_only) { + tep_get_field_val(s, event, "context", record, &thread, 1); + tep_get_field_val(s, event, "timer_latency", record, &latency, 1); - timerlat_top_update(top, cpu, thread, latency); + timerlat_top_update(top, cpu, thread, latency); + } if (!params->no_aa) timerlat_aa_handler(s, record, event, context); @@ -250,6 +253,9 @@ timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *to static int nr_cpus = -1; int i; + if (params->aa_only) + return; + if (nr_cpus == -1) nr_cpus = sysconf(_SC_NPROCESSORS_CONF); @@ -279,10 +285,11 @@ static void timerlat_top_usage(char *usage) "", " usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\", " [[-t[=file]] [-e sys[:event]] [--filter ] [--trigger ] [-c cpu-list] \\", - " [-P priority] [--dma-latency us]", + " [-P priority] [--dma-latency us] [--aa-only us]", "", " -h/--help: print this menu", " -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit", + " --aa-only us: stop if latency is hit, only printing the auto analysis (reduces CPU usage)", " -p/--period us: timerlat period in us", " -i/--irq us: stop trace if the irq latency is higher than the argument in us", " -T/--thread us: stop trace if the thread latency is higher than the argument in us", @@ -362,13 +369,14 @@ static struct timerlat_top_params {"dma-latency", required_argument, 0, '2'}, {"no-aa", no_argument, 0, '3'}, {"dump-tasks", no_argument, 0, '4'}, + {"aa-only", required_argument, 0, '5'}, {0, 0, 0, 0} }; /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:34", + c = getopt_long(argc, argv, "a:c:d:De:hi:np:P:qs:t::T:0:1:2:345:", long_options, &option_index); /* detect the end of the options. */ @@ -389,6 +397,20 @@ static struct timerlat_top_params /* set trace */ params->trace_output = "timerlat_trace.txt"; break; + case '5': + /* it is here because it is similar to -a */ + auto_thresh = get_llong_from_str(optarg); + + /* set thread stop to auto_thresh */ + params->stop_total_us = auto_thresh; + params->stop_us = auto_thresh; + + /* get stack trace */ + params->print_stack = auto_thresh; + + /* set aa_only to avoid parsing the trace */ + params->aa_only = 1; + break; case 'c': retval = parse_cpu_list(optarg, ¶ms->monitored_cpus); if (retval) @@ -503,6 +525,9 @@ static struct timerlat_top_params if (!params->stop_us && !params->stop_total_us) params->no_aa = 1; + if (params->no_aa && params->aa_only) + timerlat_top_usage("--no-aa and --aa-only are mutually exclusive!"); + return params; } @@ -634,6 +659,7 @@ int timerlat_top_main(int argc, char *argv[]) struct trace_instance *trace; int dma_latency_fd = -1; int return_value = 1; + char *max_lat; int retval; params = timerlat_top_parse_args(argc, argv); @@ -700,6 +726,9 @@ int timerlat_top_main(int argc, char *argv[]) while (!stop_tracing) { sleep(params->sleep_time); + if (params->aa_only && !trace_is_off(&top->trace, &record->trace)) + continue; + retval = tracefs_iterate_raw_events(trace->tep, trace->inst, NULL, @@ -733,6 +762,16 @@ int timerlat_top_main(int argc, char *argv[]) printf(" Saving trace to %s\n", params->trace_output); save_trace_to_file(record->trace.inst, params->trace_output); } + } else if (params->aa_only) { + /* + * If the trace did not stop with --aa-only, at least print the + * max known latency. + */ + max_lat = tracefs_instance_file_read(trace->inst, "tracing_max_latency", NULL); + if (max_lat) { + printf(" Max latency was %s\n", max_lat); + free(max_lat); + } } out_top: -- GitLab From 82253a271aae9271fcf0aaa5e0ecc6dd38fb872b Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Fri, 24 Mar 2023 20:26:42 +0100 Subject: [PATCH 3982/5631] rtla/timerlat: Fix "Previous IRQ" auto analysis' line The "Previous IRQ interference" line is misaligned and without a \n, breaking the tool's output: ## CPU 12 hit stop tracing, analyzing it ## Previous IRQ interference: up to 2.22 us IRQ handler delay: 18.06 us (0.00 %) IRQ latency: 18.52 us Timerlat IRQ duration: 4.41 us (0.00 %) Blocking thread: 216.93 us (0.03 %) Fix the output: ## CPU 7 hit stop tracing, analyzing it ## Previous IRQ interference: up to 8.93 us IRQ handler delay: 0.98 us (0.00 %) IRQ latency: 2.95 us Timerlat IRQ duration: 11.26 us (0.03 %) Link: https://lore.kernel.org/linux-trace-devel/8b5819077f15ccf24745c9bf3205451e16ee32d9.1679685525.git.bristot@kernel.org Fixes: 27e348b221f6 ("rtla/timerlat: Add auto-analysis core") Cc: Masami Hiramatsu Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Steven Rostedt (Google) --- tools/tracing/rtla/src/timerlat_aa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c index ec4e0f4b0e6c..1843fff66da5 100644 --- a/tools/tracing/rtla/src/timerlat_aa.c +++ b/tools/tracing/rtla/src/timerlat_aa.c @@ -548,7 +548,7 @@ static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu, exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay; if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) - printf(" Previous IRQ interference: \t up to %9.2f us", + printf(" Previous IRQ interference: \t\t up to %9.2f us\n", ns_to_usf(taa_data->prev_irq_duration)); /* -- GitLab From 625ed52717603f0de4c8b5cf163a3bba5cd9a362 Mon Sep 17 00:00:00 2001 From: Zheng Yejian Date: Fri, 14 Apr 2023 15:17:29 +0800 Subject: [PATCH 3983/5631] ring-buffer: Clearly check null ptr returned by rb_set_head_page() In error case, 'buffer_page' returned by rb_set_head_page() is NULL, currently check '&buffer_page->list' is equivalent to check 'buffer_page' due to 'list' is the first member of 'buffer_page', but suppose it is not some time, 'head_page' would be wild memory while check would be bypassed. Link: https://lore.kernel.org/linux-trace-kernel/20230414071729.57312-1-zhengyejian1@huawei.com Cc: Signed-off-by: Zheng Yejian Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2d5c3caff32d..58be5b409f72 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2054,10 +2054,11 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head_page, *prev_page, *r; struct list_head *last_page, *first_page; struct list_head *head_page_with_bit; + struct buffer_page *hpage = rb_set_head_page(cpu_buffer); - head_page = &rb_set_head_page(cpu_buffer)->list; - if (!head_page) + if (!hpage) break; + head_page = &hpage->list; prev_page = head_page->prev; first_page = pages->next; -- GitLab From 9872c07b14e5ad3e3a89a7fd43e9488072007118 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 19 Apr 2023 14:41:39 -0700 Subject: [PATCH 3984/5631] tracing/user_events: Set event filter_type from type Users expect that events can be filtered by the kernel. User events currently sets all event fields as FILTER_OTHER which limits to binary filters only. When strings are being used, functionality is reduced. Use filter_assign_type() to find the most appropriate filter type for each field in user events to ensure full kernel capabilities. Link: https://lkml.kernel.org/r/20230419214140.4158-2-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index cc8c6d8b69b5..eadb58a3efba 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -918,6 +918,9 @@ static int user_event_add_field(struct user_event *user, const char *type, field->is_signed = is_signed; field->filter_type = filter_type; + if (filter_type == FILTER_OTHER) + field->filter_type = filter_assign_type(type); + list_add(&field->link, &user->fields); /* -- GitLab From c7bdb07902e0b633795372665d0154e7267ecd0e Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Wed, 19 Apr 2023 14:41:40 -0700 Subject: [PATCH 3985/5631] tracing: Fix print_fields() for __dyn_loc/__rel_loc Both print_fields() and print_array() do not handle if dynamic data ends at the last byte of the payload for both __dyn_loc and __rel_loc field types. For __rel_loc, the offset was off by 4 bytes, leading to incorrect strings and data being printed out. In print_array() the buffer pos was missed from being advanced, which results in the first payload byte being used as the offset base instead of the field offset. Advance __rel_loc offset by 4 to ensure correct offset and advance pos to the field offset to ensure correct data is displayed when printing arrays. Change >= to > when checking if data is in-bounds, since it's valid for dynamic data to include the last byte of the payload. Example outputs for event format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:__rel_loc char text[]; offset:8; size:4; signed:1; Output before: tp_rel_loc: text= Output after: tp_rel_loc: text=Test Link: https://lkml.kernel.org/r/20230419214140.4158-3-beaub@linux.microsoft.com Fixes: 80a76994b2d8 ("tracing: Add "fields" option to show raw trace event fields") Reported-by: Doug Cook Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_output.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 780c6971c944..952cc8aa8e59 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -819,13 +819,15 @@ static void print_array(struct trace_iterator *iter, void *pos, len = *(int *)pos >> 16; if (field) - offset += field->offset; + offset += field->offset + sizeof(int); - if (offset + len >= iter->ent_size) { + if (offset + len > iter->ent_size) { trace_seq_puts(&iter->seq, ""); return; } + pos = (void *)iter->ent + offset; + for (i = 0; i < len; i++, pos++) { if (i) trace_seq_putc(&iter->seq, ','); @@ -861,9 +863,9 @@ static void print_fields(struct trace_iterator *iter, struct trace_event_call *c len = *(int *)pos >> 16; if (field->filter_type == FILTER_RDYN_STRING) - offset += field->offset; + offset += field->offset + sizeof(int); - if (offset + len >= iter->ent_size) { + if (offset + len > iter->ent_size) { trace_seq_puts(&iter->seq, ""); break; } -- GitLab From 96928d9032a7c34f12a88df879665562bcebf59a Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Sat, 15 Apr 2023 19:01:10 +0900 Subject: [PATCH 3986/5631] seq_buf: Add seq_buf_do_printk() helper Sometimes we use seq_buf to format a string buffer, which we then pass to printk(). However, in certain situations the seq_buf string buffer can get too big, exceeding the PRINTKRB_RECORD_MAX bytes limit, and causing printk() to truncate the string. Add a new seq_buf helper. This helper prints the seq_buf string buffer line by line, using \n as a delimiter, rather than passing the whole string buffer to printk() at once. Link: https://lkml.kernel.org/r/20230415100110.1419872-1-senozhatsky@chromium.org Cc: Andrew Morton Signed-off-by: Sergey Senozhatsky Reviewed-by: Petr Mladek Tested-by: Yosry Ahmed Signed-off-by: Steven Rostedt (Google) --- include/linux/seq_buf.h | 2 ++ lib/seq_buf.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 5b31c5147969..515d7fcb9634 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -159,4 +159,6 @@ extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif +void seq_buf_do_printk(struct seq_buf *s, const char *lvl); + #endif /* _LINUX_SEQ_BUF_H */ diff --git a/lib/seq_buf.c b/lib/seq_buf.c index 0a68f7aa85d6..45c450f423fa 100644 --- a/lib/seq_buf.c +++ b/lib/seq_buf.c @@ -93,6 +93,38 @@ int seq_buf_printf(struct seq_buf *s, const char *fmt, ...) } EXPORT_SYMBOL_GPL(seq_buf_printf); +/** + * seq_buf_do_printk - printk seq_buf line by line + * @s: seq_buf descriptor + * @lvl: printk level + * + * printk()-s a multi-line sequential buffer line by line. The function + * makes sure that the buffer in @s is nul terminated and safe to read + * as a string. + */ +void seq_buf_do_printk(struct seq_buf *s, const char *lvl) +{ + const char *start, *lf; + + if (s->size == 0 || s->len == 0) + return; + + seq_buf_terminate(s); + + start = s->buffer; + while ((lf = strchr(start, '\n'))) { + int len = lf - start + 1; + + printk("%s%.*s", lvl, len, start); + start = ++lf; + } + + /* No trailing LF */ + if (start < s->buffer + s->len) + printk("%s%s\n", lvl, start); +} +EXPORT_SYMBOL_GPL(seq_buf_do_printk); + #ifdef CONFIG_BINARY_PRINTF /** * seq_buf_bprintf - Write the printf string from binary arguments -- GitLab From cd98c93286a30cc4588dfd02453bec63c2f4acf4 Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 25 Apr 2023 15:51:04 -0700 Subject: [PATCH 3987/5631] tracing/user_events: Ensure write index cannot be negative The write index indicates which event the data is for and accesses a per-file array. The index is passed by user processes during write() calls as the first 4 bytes. Ensure that it cannot be negative by returning -EINVAL to prevent out of bounds accesses. Update ftrace self-test to ensure this occurs properly. Link: https://lkml.kernel.org/r/20230425225107.8525-2-beaub@linux.microsoft.com Fixes: 7f5a08c79df3 ("user_events: Add minimal support for trace_event into ftrace") Reported-by: Doug Cook Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 3 +++ tools/testing/selftests/user_events/ftrace_test.c | 5 +++++ 2 files changed, 8 insertions(+) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index eadb58a3efba..546d47a57520 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -1824,6 +1824,9 @@ static ssize_t user_events_write_core(struct file *file, struct iov_iter *i) if (unlikely(copy_from_iter(&idx, sizeof(idx), i) != sizeof(idx))) return -EFAULT; + if (idx < 0) + return -EINVAL; + rcu_read_lock_sched(); refs = rcu_dereference_sched(info->refs); diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index aceafacfb126..91272f9d6fce 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -296,6 +296,11 @@ TEST_F(user, write_events) { ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3)); after = trace_bytes(); ASSERT_GT(after, before); + + /* Negative index should fail with EINVAL */ + reg.write_index = -1; + ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3)); + ASSERT_EQ(EINVAL, errno); } TEST_F(user, write_fault) { -- GitLab From 17b439db21d5dbe70c419e982262621e5e6aba7f Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 25 Apr 2023 15:51:05 -0700 Subject: [PATCH 3988/5631] tracing/user_events: Ensure bit is cleared on unregister If an event is enabled and a user process unregisters user_events, the bit is left set. Fix this by always clearing the bit in the user process if unregister is successful. Update abi self-test to ensure this occurs properly. Link: https://lkml.kernel.org/r/20230425225107.8525-3-beaub@linux.microsoft.com Suggested-by: Doug Cook Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 34 +++++++++++++++++++ .../testing/selftests/user_events/abi_test.c | 9 +++-- 2 files changed, 40 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 546d47a57520..4f9ae63dfc5d 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2149,6 +2149,35 @@ static long user_unreg_get(struct user_unreg __user *ureg, return ret; } +static int user_event_mm_clear_bit(struct user_event_mm *user_mm, + unsigned long uaddr, unsigned char bit) +{ + struct user_event_enabler enabler; + int result; + + memset(&enabler, 0, sizeof(enabler)); + enabler.addr = uaddr; + enabler.values = bit; +retry: + /* Prevents state changes from racing with new enablers */ + mutex_lock(&event_mutex); + + /* Force the bit to be cleared, since no event is attached */ + mmap_read_lock(user_mm->mm); + result = user_event_enabler_write(user_mm, &enabler, false); + mmap_read_unlock(user_mm->mm); + + mutex_unlock(&event_mutex); + + if (result) { + /* Attempt to fault-in and retry if it worked */ + if (!user_event_mm_fault_in(user_mm, uaddr)) + goto retry; + } + + return result; +} + /* * Unregisters an enablement address/bit within a task/user mm. */ @@ -2193,6 +2222,11 @@ static long user_events_ioctl_unreg(unsigned long uarg) mutex_unlock(&event_mutex); + /* Ensure bit is now cleared for user, regardless of event status */ + if (!ret) + ret = user_event_mm_clear_bit(mm, reg.disable_addr, + reg.disable_bit); + return ret; } diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index e0323d3777a7..5125c42efe65 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -109,13 +109,16 @@ TEST_F(user, enablement) { ASSERT_EQ(0, change_event(false)); ASSERT_EQ(0, self->check); - /* Should not change after disable */ + /* Ensure kernel clears bit after disable */ ASSERT_EQ(0, change_event(true)); ASSERT_EQ(1, self->check); ASSERT_EQ(0, reg_disable(&self->check, 0)); + ASSERT_EQ(0, self->check); + + /* Ensure doesn't change after unreg */ + ASSERT_EQ(0, change_event(true)); + ASSERT_EQ(0, self->check); ASSERT_EQ(0, change_event(false)); - ASSERT_EQ(1, self->check); - self->check = 0; } TEST_F(user, bit_sizes) { -- GitLab From 97bbce89bfdec9219dfcb60cd62b815a97cb29cb Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 25 Apr 2023 15:51:06 -0700 Subject: [PATCH 3989/5631] tracing/user_events: Prevent same address and bit per process User processes register an address and bit pair for events. If the same address and bit pair are registered multiple times in the same process, it can cause undefined behavior when events are enabled/disabled. When more than one are used, the bit could be turned off by another event being disabled, while the original event is still enabled. Prevent undefined behavior by checking the current mm to see if any event has already been registered for the address and bit pair. Return EADDRINUSE back to the user process if it's already being used. Update ftrace self-test to ensure this occurs properly. Link: https://lkml.kernel.org/r/20230425225107.8525-4-beaub@linux.microsoft.com Suggested-by: Doug Cook Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 41 +++++++++++++++++++ .../selftests/user_events/ftrace_test.c | 9 +++- 2 files changed, 49 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 4f9ae63dfc5d..a29cd13caf55 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -419,6 +419,21 @@ static int user_event_enabler_write(struct user_event_mm *mm, return 0; } +static bool user_event_enabler_exists(struct user_event_mm *mm, + unsigned long uaddr, unsigned char bit) +{ + struct user_event_enabler *enabler; + struct user_event_enabler *next; + + list_for_each_entry_safe(enabler, next, &mm->enablers, link) { + if (enabler->addr == uaddr && + (enabler->values & ENABLE_VAL_BIT_MASK) == bit) + return true; + } + + return false; +} + static void user_event_enabler_update(struct user_event *user) { struct user_event_enabler *enabler; @@ -657,6 +672,22 @@ void user_event_mm_dup(struct task_struct *t, struct user_event_mm *old_mm) user_event_mm_remove(t); } +static bool current_user_event_enabler_exists(unsigned long uaddr, + unsigned char bit) +{ + struct user_event_mm *user_mm = current_user_event_mm(); + bool exists; + + if (!user_mm) + return false; + + exists = user_event_enabler_exists(user_mm, uaddr, bit); + + user_event_mm_put(user_mm); + + return exists; +} + static struct user_event_enabler *user_event_enabler_create(struct user_reg *reg, struct user_event *user, int *write_result) @@ -2048,6 +2079,16 @@ static long user_events_ioctl_reg(struct user_event_file_info *info, if (ret) return ret; + /* + * Prevent users from using the same address and bit multiple times + * within the same mm address space. This can cause unexpected behavior + * for user processes that is far easier to debug if this is explictly + * an error upon registering. + */ + if (current_user_event_enabler_exists((unsigned long)reg.enable_addr, + reg.enable_bit)) + return -EADDRINUSE; + name = strndup_user((const char __user *)(uintptr_t)reg.name_args, MAX_EVENT_DESC); diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 91272f9d6fce..7c99cef94a65 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -219,7 +219,12 @@ TEST_F(user, register_events) { ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); - /* Multiple registers should result in same index */ + /* Multiple registers to the same addr + bit should fail */ + ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSREG, ®)); + ASSERT_EQ(EADDRINUSE, errno); + + /* Multiple registers to same name should result in same index */ + reg.enable_bit = 30; ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, ®)); ASSERT_EQ(0, reg.write_index); @@ -242,6 +247,8 @@ TEST_F(user, register_events) { /* Unregister */ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); + unreg.disable_bit = 30; + ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSUNREG, &unreg)); /* Delete should work only after close and unregister */ close(self->data_fd); -- GitLab From 41d8fba193b36ac1208d8f8489390b93675fab7b Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Tue, 25 Apr 2023 15:51:07 -0700 Subject: [PATCH 3990/5631] tracing/user_events: Limit max fault-in attempts When event enablement changes, user_events attempts to update a bit in the user process. If a fault is hit, an attempt to fault-in the page and the write is retried if the page made it in. While this normally requires a couple attempts, it is possible a bad user process could attempt to cause infinite loops. Ensure fault-in attempts either sync or async are limited to a max of 10 attempts for each update. When the max is hit, return -EFAULT so another attempt is not made in all cases. Link: https://lkml.kernel.org/r/20230425225107.8525-5-beaub@linux.microsoft.com Suggested-by: Steven Rostedt (Google) Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events_user.c | 49 +++++++++++++++++++++++--------- 1 file changed, 35 insertions(+), 14 deletions(-) diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index a29cd13caf55..b1ecd7677642 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -123,6 +123,7 @@ struct user_event_enabler_fault { struct work_struct work; struct user_event_mm *mm; struct user_event_enabler *enabler; + int attempt; }; static struct kmem_cache *fault_cache; @@ -266,11 +267,19 @@ static void user_event_enabler_destroy(struct user_event_enabler *enabler) kfree(enabler); } -static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr) +static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr, + int attempt) { bool unlocked; int ret; + /* + * Normally this is low, ensure that it cannot be taken advantage of by + * bad user processes to cause excessive looping. + */ + if (attempt > 10) + return -EFAULT; + mmap_read_lock(mm->mm); /* Ensure MM has tasks, cannot use after exit_mm() */ @@ -289,7 +298,7 @@ static int user_event_mm_fault_in(struct user_event_mm *mm, unsigned long uaddr) static int user_event_enabler_write(struct user_event_mm *mm, struct user_event_enabler *enabler, - bool fixup_fault); + bool fixup_fault, int *attempt); static void user_event_enabler_fault_fixup(struct work_struct *work) { @@ -298,9 +307,10 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) struct user_event_enabler *enabler = fault->enabler; struct user_event_mm *mm = fault->mm; unsigned long uaddr = enabler->addr; + int attempt = fault->attempt; int ret; - ret = user_event_mm_fault_in(mm, uaddr); + ret = user_event_mm_fault_in(mm, uaddr, attempt); if (ret && ret != -ENOENT) { struct user_event *user = enabler->event; @@ -329,7 +339,7 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) if (!ret) { mmap_read_lock(mm->mm); - user_event_enabler_write(mm, enabler, true); + user_event_enabler_write(mm, enabler, true, &attempt); mmap_read_unlock(mm->mm); } out: @@ -341,7 +351,8 @@ static void user_event_enabler_fault_fixup(struct work_struct *work) } static bool user_event_enabler_queue_fault(struct user_event_mm *mm, - struct user_event_enabler *enabler) + struct user_event_enabler *enabler, + int attempt) { struct user_event_enabler_fault *fault; @@ -353,6 +364,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm, INIT_WORK(&fault->work, user_event_enabler_fault_fixup); fault->mm = user_event_mm_get(mm); fault->enabler = enabler; + fault->attempt = attempt; /* Don't try to queue in again while we have a pending fault */ set_bit(ENABLE_VAL_FAULTING_BIT, ENABLE_BITOPS(enabler)); @@ -372,7 +384,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm, static int user_event_enabler_write(struct user_event_mm *mm, struct user_event_enabler *enabler, - bool fixup_fault) + bool fixup_fault, int *attempt) { unsigned long uaddr = enabler->addr; unsigned long *ptr; @@ -383,6 +395,8 @@ static int user_event_enabler_write(struct user_event_mm *mm, lockdep_assert_held(&event_mutex); mmap_assert_locked(mm->mm); + *attempt += 1; + /* Ensure MM has tasks, cannot use after exit_mm() */ if (refcount_read(&mm->tasks) == 0) return -ENOENT; @@ -398,7 +412,7 @@ static int user_event_enabler_write(struct user_event_mm *mm, if (!fixup_fault) return -EFAULT; - if (!user_event_enabler_queue_fault(mm, enabler)) + if (!user_event_enabler_queue_fault(mm, enabler, *attempt)) pr_warn("user_events: Unable to queue fault handler\n"); return -EFAULT; @@ -439,15 +453,19 @@ static void user_event_enabler_update(struct user_event *user) struct user_event_enabler *enabler; struct user_event_mm *mm = user_event_mm_get_all(user); struct user_event_mm *next; + int attempt; while (mm) { next = mm->next; mmap_read_lock(mm->mm); rcu_read_lock(); - list_for_each_entry_rcu(enabler, &mm->enablers, link) - if (enabler->event == user) - user_event_enabler_write(mm, enabler, true); + list_for_each_entry_rcu(enabler, &mm->enablers, link) { + if (enabler->event == user) { + attempt = 0; + user_event_enabler_write(mm, enabler, true, &attempt); + } + } rcu_read_unlock(); mmap_read_unlock(mm->mm); @@ -695,6 +713,7 @@ static struct user_event_enabler struct user_event_enabler *enabler; struct user_event_mm *user_mm; unsigned long uaddr = (unsigned long)reg->enable_addr; + int attempt = 0; user_mm = current_user_event_mm(); @@ -715,7 +734,8 @@ static struct user_event_enabler /* Attempt to reflect the current state within the process */ mmap_read_lock(user_mm->mm); - *write_result = user_event_enabler_write(user_mm, enabler, false); + *write_result = user_event_enabler_write(user_mm, enabler, false, + &attempt); mmap_read_unlock(user_mm->mm); /* @@ -735,7 +755,7 @@ static struct user_event_enabler if (*write_result) { /* Attempt to fault-in and retry if it worked */ - if (!user_event_mm_fault_in(user_mm, uaddr)) + if (!user_event_mm_fault_in(user_mm, uaddr, attempt)) goto retry; kfree(enabler); @@ -2195,6 +2215,7 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm, { struct user_event_enabler enabler; int result; + int attempt = 0; memset(&enabler, 0, sizeof(enabler)); enabler.addr = uaddr; @@ -2205,14 +2226,14 @@ static int user_event_mm_clear_bit(struct user_event_mm *user_mm, /* Force the bit to be cleared, since no event is attached */ mmap_read_lock(user_mm->mm); - result = user_event_enabler_write(user_mm, &enabler, false); + result = user_event_enabler_write(user_mm, &enabler, false, &attempt); mmap_read_unlock(user_mm->mm); mutex_unlock(&event_mutex); if (result) { /* Attempt to fault-in and retry if it worked */ - if (!user_event_mm_fault_in(user_mm, uaddr)) + if (!user_event_mm_fault_in(user_mm, uaddr, attempt)) goto retry; } -- GitLab From fa359d068574d29e7d2f0fdd0ebe4c6a12b5cfb9 Mon Sep 17 00:00:00 2001 From: Hao Zeng Date: Wed, 26 Apr 2023 09:05:27 +0800 Subject: [PATCH 3991/5631] recordmcount: Fix memory leaks in the uwrite function Common realloc mistake: 'file_append' nulled but not freed upon failure Link: https://lkml.kernel.org/r/20230426010527.703093-1-zenghao@kylinos.cn Signed-off-by: Hao Zeng Suggested-by: Steven Rostedt Signed-off-by: Steven Rostedt (Google) --- scripts/recordmcount.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index e30216525325..40ae6b2c7a6d 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -110,6 +110,7 @@ static ssize_t uwrite(void const *const buf, size_t const count) { size_t cnt = count; off_t idx = 0; + void *p = NULL; file_updated = 1; @@ -117,7 +118,10 @@ static ssize_t uwrite(void const *const buf, size_t const count) off_t aoffset = (file_ptr + count) - file_end; if (aoffset > file_append_size) { - file_append = realloc(file_append, aoffset); + p = realloc(file_append, aoffset); + if (!p) + free(file_append); + file_append = p; file_append_size = aoffset; } if (!file_append) { -- GitLab From bb3f89487fd936df7cc5165bae37ca2669056c5c Mon Sep 17 00:00:00 2001 From: Evan Green Date: Thu, 20 Apr 2023 12:49:34 -0700 Subject: [PATCH 3992/5631] RISC-V: hwprobe: Remove __init on probe_vendor_features() probe_vendor_features() is now called from smp_callin(), which is not __init code and runs during cpu hotplug events. Remove the __init_or_module decoration from it and the functions it calls to avoid walking into outer space. Fixes: 62a31d6e38bd ("RISC-V: hwprobe: Support probing of misaligned access performance") Signed-off-by: Evan Green Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230420194934.1871356-1-evan@rivosinc.com Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/thead/errata.c | 6 +++--- arch/riscv/include/asm/alternative.h | 2 +- arch/riscv/kernel/alternative.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index 1036b8f933ec..a86c4facc2a6 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -118,9 +118,9 @@ void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct al local_flush_icache_all(); } -void __init_or_module thead_feature_probe_func(unsigned int cpu, - unsigned long archid, - unsigned long impid) +void thead_feature_probe_func(unsigned int cpu, + unsigned long archid, + unsigned long impid) { if ((archid == 0) && (impid == 0)) per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_FAST; diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h index a8f5cf6694a1..6a41537826a7 100644 --- a/arch/riscv/include/asm/alternative.h +++ b/arch/riscv/include/asm/alternative.h @@ -30,7 +30,7 @@ #define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset) #define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset) -void __init probe_vendor_features(unsigned int cpu); +void probe_vendor_features(unsigned int cpu); void __init apply_boot_alternatives(void); void __init apply_early_boot_alternatives(void); void apply_module_alternatives(void *start, size_t length); diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c index fc65c9293ac5..6b75788c18e6 100644 --- a/arch/riscv/kernel/alternative.c +++ b/arch/riscv/kernel/alternative.c @@ -31,7 +31,7 @@ struct cpu_manufacturer_info_t { unsigned long impid); }; -static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) +static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) { #ifdef CONFIG_RISCV_M_MODE cpu_mfr_info->vendor_id = csr_read(CSR_MVENDORID); @@ -144,7 +144,7 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, } /* Called on each CPU as it starts */ -void __init_or_module probe_vendor_features(unsigned int cpu) +void probe_vendor_features(unsigned int cpu) { struct cpu_manufacturer_info_t cpu_mfr_info; -- GitLab From 0c993300d52bf5ce9b951c3b6b25d0d14acc49a9 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 26 Apr 2023 15:58:38 +1000 Subject: [PATCH 3993/5631] powerpc: Fix merge conflict between pcrel and copy_thread changes Fix a conflict between commit 4e991e3c16a35 ("powerpc: add CFUNC assembly label annotation") and commit b504b6aade040 ("powerpc: differentiate kthread from user kernel thread start"). Fixes: 4e991e3c16a35 ("powerpc: add CFUNC assembly label annotation") Fixes: b504b6aade040 ("powerpc: differentiate kthread from user kernel thread start") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230426055848.402993-2-npiggin@gmail.com --- arch/powerpc/kernel/interrupt_64.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 6730d676284c..bd863702d812 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -756,7 +756,7 @@ _GLOBAL(ret_from_kernel_user_thread) b .Lsyscall_exit _GLOBAL(start_kernel_thread) - bl schedule_tail + bl CFUNC(schedule_tail) mtctr r14 mr r3,r15 #ifdef CONFIG_PPC64_ELF_ABI_V2 -- GitLab From 169f8997968ab620d750d9a45e15c5288d498356 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 26 Apr 2023 15:58:39 +1000 Subject: [PATCH 3994/5631] powerpc/64s: Disable pcrel code model on Clang Clang has a bug that casues the pcrel code model not to be used when any of -msoft-float, -mno-altivec, or -mno-vsx are set. Leaving these off causes FP/vector instructions to be generated, causing crashes. So disable pcrel for clang for now. Fixes: 7e3a68be42e10 ("powerpc/64: vmlinux support building with PCREL addresing") Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman Link: https://msgid.link/20230426055848.402993-3-npiggin@gmail.com --- arch/powerpc/Kconfig | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7a0f25a09759..520e577f3106 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -8,7 +8,12 @@ config CC_HAS_PREFIXED def_bool PPC64 && $(cc-option, -mcpu=power10 -mprefixed) config CC_HAS_PCREL - def_bool PPC64 && $(cc-option, -mcpu=power10 -mpcrel) + # Clang has a bug (https://github.com/llvm/llvm-project/issues/62372) + # where pcrel code is not generated if -msoft-float, -mno-altivec, or + # -mno-vsx options are also given. Without these options, fp/vec + # instructions are generated from regular kernel code. So Clang can't + # do pcrel yet. + def_bool PPC64 && CC_IS_GCC && $(cc-option, -mcpu=power10 -mpcrel) config 32BIT bool -- GitLab From 4e8f6e44bce8da3b0e2df37b12839f4bc9c9cabe Mon Sep 17 00:00:00 2001 From: Neeraj Upadhyay Date: Tue, 25 Apr 2023 15:27:00 +0530 Subject: [PATCH 3995/5631] arm64: Fix label placement in record_mmu_state() Fix label so that pre_disable_mmu_workaround() is called before clearing sctlr_el1.M. Fixes: 2ced0f30a426 ("arm64: head: Switch endianness before populating the ID map") Signed-off-by: Neeraj Upadhyay Acked-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20230425095700.22005-1-quic_neeraju@quicinc.com Signed-off-by: Will Deacon --- arch/arm64/kernel/head.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b98970907226..e92caebff46a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -150,8 +150,8 @@ CPU_BE( tbz x19, #SCTLR_ELx_EE_SHIFT, 1f ) pre_disable_mmu_workaround msr sctlr_el2, x19 b 3f - pre_disable_mmu_workaround -2: msr sctlr_el1, x19 +2: pre_disable_mmu_workaround + msr sctlr_el1, x19 3: isb mov x19, xzr ret -- GitLab From a8a2330753bc280c87aa72d690b41b8515fda214 Mon Sep 17 00:00:00 2001 From: Stefan Wahren Date: Mon, 10 Apr 2023 22:58:00 +0200 Subject: [PATCH 3996/5631] dt-bindings: imx-thermal: Add imx6sll and imx6ul compatible Currently the dtbs_check for imx6 generates warnings like this: ['fsl,imx6sll-tempmon', 'fsl,imx6sx-tempmon'] is too long So add them to the devicetree binding. Signed-off-by: Stefan Wahren Reviewed-by: Krzysztof Kozlowski Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230410205803.45853-4-stefan.wahren@i2se.com --- .../devicetree/bindings/thermal/imx-thermal.yaml | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml index fe599e443eaf..3aecea77869f 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml @@ -12,10 +12,16 @@ maintainers: properties: compatible: - enum: - - fsl,imx6q-tempmon - - fsl,imx6sx-tempmon - - fsl,imx7d-tempmon + oneOf: + - enum: + - fsl,imx6q-tempmon + - fsl,imx6sx-tempmon + - fsl,imx7d-tempmon + - items: + - enum: + - fsl,imx6sll-tempmon + - fsl,imx6ul-tempmon + - const: fsl,imx6sx-tempmon interrupts: description: | -- GitLab From d9f7eeaf24aedfdf47bddf0cf88e1021b7f652f5 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Mon, 10 Apr 2023 22:29:15 +0200 Subject: [PATCH 3997/5631] dt-bindings: thermal: Use generic ADC node name in examples Update the examples to reflect a future requirement for the generic `channel` node name on ADC channel nodes, while conveying the board name of the channel in a label instead. Signed-off-by: Marijn Suijten Acked-by: Krzysztof Kozlowski Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230410202917.247666-4-marijn.suijten@somainline.org --- .../devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml | 4 ++-- .../devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml | 9 ++++++--- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml index 8273ac55b63f..01253d58bf9f 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm-hc.yaml @@ -124,8 +124,8 @@ examples: #size-cells = <0>; #io-channel-cells = <1>; - /* Other propreties are omitted */ - adc-chan@4c { + /* Other properties are omitted */ + channel@4c { reg = ; }; }; diff --git a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml index 52ec18cf1eda..3c81def03c84 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-spmi-adc-tm5.yaml @@ -178,10 +178,11 @@ examples: #io-channel-cells = <1>; /* Other properties are omitted */ - conn-therm@4f { + channel@4f { reg = ; qcom,ratiometric; qcom,hw-settle-time = <200>; + label = "conn_therm"; }; }; @@ -217,16 +218,18 @@ examples: #io-channel-cells = <1>; /* Other properties are omitted */ - xo-therm@44 { + channel@44 { reg = ; qcom,ratiometric; qcom,hw-settle-time = <200>; + label = "xo_therm"; }; - conn-therm@147 { + channel@147 { reg = ; qcom,ratiometric; qcom,hw-settle-time = <200>; + label = "conn_therm"; }; }; -- GitLab From 2912d341800bb9781c0a0ed2bedc10b2c1fd5909 Mon Sep 17 00:00:00 2001 From: Chenggang Wang Date: Tue, 18 Apr 2023 11:38:28 +0800 Subject: [PATCH 3998/5631] thermal/drivers/cpuidle_cooling: Delete unmatched comments The function no longer returns a value, synchronize the comments. Signed-off-by: wangchenggang@vivo.com Acked-by: Viresh Kumar Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/1681789108-28130-1-git-send-email-wangchenggang@vivo.com --- drivers/thermal/cpuidle_cooling.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/thermal/cpuidle_cooling.c b/drivers/thermal/cpuidle_cooling.c index 4f41102e8b16..7779739fc8ac 100644 --- a/drivers/thermal/cpuidle_cooling.c +++ b/drivers/thermal/cpuidle_cooling.c @@ -236,9 +236,6 @@ static int __cpuidle_cooling_register(struct device_node *np, * * This function is in charge of creating a cooling device per cpuidle * driver and register it to the thermal framework. - * - * Return: zero on success, or negative value corresponding to the - * error detected in the underlying subsystems. */ void cpuidle_cooling_register(struct cpuidle_driver *drv) { -- GitLab From 0a677eea71fd58aa3bc805edfdbe8b0f11815c7d Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 19 Apr 2023 08:11:45 +0200 Subject: [PATCH 3999/5631] Revert "thermal/drivers/mediatek: Add delay after thermal banks initialization" Some more testing revealed that this commit introduces a regression on some MT8173 Chromebooks and at least on one MT6795 Sony Xperia M5 smartphone due to the delay being apparently variable and machine specific. Another solution would be to delay for a bit more (~70ms) but this is not feasible for two reasons: first of all, we're adding an even bigger delay in a probe function; second, some machines need less, some may need even more, making the msleep at probe solution highly suboptimal. This reverts commit 10debf8c2da8011c8009dd4b3f6d0ab85891c81b. Fixes: 10debf8c2da8 ("thermal/drivers/mediatek: Add delay after thermal banks initialization") Reported-by: "kernelci.org bot" Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419061146.22246-2-angelogioacchino.delregno@collabora.com --- drivers/thermal/mediatek/auxadc_thermal.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index b6bb9eaafb74..3c959a827451 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -816,6 +816,14 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank) mt, conf->bank_data[bank->id].sensors[i], raw); + /* + * The first read of a sensor often contains very high bogus + * temperature value. Filter these out so that the system does + * not immediately shut down. + */ + if (temp > 200000) + temp = 0; + if (temp > max) max = temp; } @@ -1273,9 +1281,6 @@ static int mtk_thermal_probe(struct platform_device *pdev) platform_set_drvdata(pdev, mt); - /* Delay for thermal banks to be ready */ - msleep(30); - tzdev = devm_thermal_of_zone_register(&pdev->dev, 0, mt, &mtk_thermal_ops); if (IS_ERR(tzdev)) { -- GitLab From 47cbb0467b8b3c76faba3c2dd34b20070e6103ca Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Wed, 19 Apr 2023 08:11:46 +0200 Subject: [PATCH 4000/5631] thermal/drivers/mediatek: Add temperature constraints to validate read MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The AUXADC thermal v1 allows reading temperature range between -20°C to 150°C and any value out of this range is invalid. Add new definitions for MT8173_TEMP_{MIN_MAX} and a new small helper mtk_thermal_temp_is_valid() to check if new readings are in range: if not, we tell to the API that the reading is invalid by returning THERMAL_TEMP_INVALID. It was chosen to introduce the helper function because, even though this temperature range is realistically ok for all, it comes from a downstream kernel driver for version 1, but here we also support v2 and v3 which may may have wider constraints. Signed-off-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419061146.22246-3-angelogioacchino.delregno@collabora.com --- drivers/thermal/mediatek/auxadc_thermal.c | 24 +++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index 3c959a827451..e908c8e9d558 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -116,6 +116,10 @@ /* The calibration coefficient of sensor */ #define MT8173_CALIBRATION 165 +/* Valid temperatures range */ +#define MT8173_TEMP_MIN -20000 +#define MT8173_TEMP_MAX 150000 + /* * Layout of the fuses providing the calibration data * These macros could be used for MT8183, MT8173, MT2701, and MT2712. @@ -689,6 +693,11 @@ static const struct mtk_thermal_data mt7986_thermal_data = { .version = MTK_THERMAL_V3, }; +static bool mtk_thermal_temp_is_valid(int temp) +{ + return (temp >= MT8173_TEMP_MIN) && (temp <= MT8173_TEMP_MAX); +} + /** * raw_to_mcelsius_v1 - convert a raw ADC value to mcelsius * @mt: The thermal controller @@ -815,14 +824,17 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank) temp = mt->raw_to_mcelsius( mt, conf->bank_data[bank->id].sensors[i], raw); - /* - * The first read of a sensor often contains very high bogus - * temperature value. Filter these out so that the system does - * not immediately shut down. + * Depending on the filt/sen intervals and ADC polling time, + * we may need up to 60 milliseconds after initialization: this + * will result in the first reading containing an out of range + * temperature value. + * Validate the reading to both address the aforementioned issue + * and to eventually avoid bogus readings during runtime in the + * event that the AUXADC gets unstable due to high EMI, etc. */ - if (temp > 200000) - temp = 0; + if (!mtk_thermal_temp_is_valid(temp)) + temp = THERMAL_TEMP_INVALID; if (temp > max) max = temp; -- GitLab From f05c7b7d9ea9477fcc388476c6f4ade8c66d2d26 Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Wed, 19 Apr 2023 10:07:48 +0800 Subject: [PATCH 4001/5631] thermal/drivers/mediatek: Use devm_of_iomap to avoid resource leak in mtk_thermal_probe Smatch reports: 1. mtk_thermal_probe() warn: 'apmixed_base' from of_iomap() not released. 2. mtk_thermal_probe() warn: 'auxadc_base' from of_iomap() not released. The original code forgets to release iomap resource when handling errors, fix it by switch to devm_of_iomap. Fixes: 89945047b166 ("thermal: mediatek: Add tsensor support for V2 thermal system") Signed-off-by: Kang Chen Reviewed-by: Dongliang Mu Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419020749.621257-1-void0red@hust.edu.cn --- drivers/thermal/mediatek/auxadc_thermal.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index e908c8e9d558..49bcd5304802 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -1232,7 +1232,12 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - auxadc_base = of_iomap(auxadc, 0); + auxadc_base = devm_of_iomap(&pdev->dev, auxadc, 0, NULL); + if (IS_ERR(auxadc_base)) { + of_node_put(auxadc); + return PTR_ERR(auxadc_base); + } + auxadc_phys_base = of_get_phys_base(auxadc); of_node_put(auxadc); @@ -1248,7 +1253,12 @@ static int mtk_thermal_probe(struct platform_device *pdev) return -ENODEV; } - apmixed_base = of_iomap(apmixedsys, 0); + apmixed_base = devm_of_iomap(&pdev->dev, apmixedsys, 0, NULL); + if (IS_ERR(apmixed_base)) { + of_node_put(apmixedsys); + return PTR_ERR(apmixed_base); + } + apmixed_phys_base = of_get_phys_base(apmixedsys); of_node_put(apmixedsys); -- GitLab From a3e9a9a5971164933e0d247125897c2e54587c6b Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Wed, 19 Apr 2023 10:07:49 +0800 Subject: [PATCH 4002/5631] thermal/drivers/mediatek: Change clk_prepare_enable to devm_clk_get_enabled in mtk_thermal_probe Use devm_clk_get_enabled to do automatic resource management. Meanwhile, remove error handling labels in the probe function and the whole remove function. Signed-off-by: Kang Chen Reviewed-by: Dongliang Mu Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230419020749.621257-2-void0red@hust.edu.cn --- drivers/thermal/mediatek/auxadc_thermal.c | 44 +++++------------------ 1 file changed, 9 insertions(+), 35 deletions(-) diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index 49bcd5304802..b59fe4307b0a 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -1206,14 +1206,6 @@ static int mtk_thermal_probe(struct platform_device *pdev) mt->conf = of_device_get_match_data(&pdev->dev); - mt->clk_peri_therm = devm_clk_get(&pdev->dev, "therm"); - if (IS_ERR(mt->clk_peri_therm)) - return PTR_ERR(mt->clk_peri_therm); - - mt->clk_auxadc = devm_clk_get(&pdev->dev, "auxadc"); - if (IS_ERR(mt->clk_auxadc)) - return PTR_ERR(mt->clk_auxadc); - mt->thermal_base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(mt->thermal_base)) return PTR_ERR(mt->thermal_base); @@ -1272,16 +1264,18 @@ static int mtk_thermal_probe(struct platform_device *pdev) if (ret) return ret; - ret = clk_prepare_enable(mt->clk_auxadc); - if (ret) { + mt->clk_auxadc = devm_clk_get_enabled(&pdev->dev, "auxadc"); + if (IS_ERR(mt->clk_auxadc)) { + ret = PTR_ERR(mt->clk_auxadc); dev_err(&pdev->dev, "Can't enable auxadc clk: %d\n", ret); return ret; } - ret = clk_prepare_enable(mt->clk_peri_therm); - if (ret) { + mt->clk_peri_therm = devm_clk_get_enabled(&pdev->dev, "therm"); + if (IS_ERR(mt->clk_peri_therm)) { + ret = PTR_ERR(mt->clk_peri_therm); dev_err(&pdev->dev, "Can't enable peri clk: %d\n", ret); - goto err_disable_clk_auxadc; + return ret; } mtk_thermal_turn_on_buffer(mt, apmixed_base); @@ -1305,38 +1299,18 @@ static int mtk_thermal_probe(struct platform_device *pdev) tzdev = devm_thermal_of_zone_register(&pdev->dev, 0, mt, &mtk_thermal_ops); - if (IS_ERR(tzdev)) { - ret = PTR_ERR(tzdev); - goto err_disable_clk_peri_therm; - } + if (IS_ERR(tzdev)) + return PTR_ERR(tzdev); ret = devm_thermal_add_hwmon_sysfs(&pdev->dev, tzdev); if (ret) dev_warn(&pdev->dev, "error in thermal_add_hwmon_sysfs"); return 0; - -err_disable_clk_peri_therm: - clk_disable_unprepare(mt->clk_peri_therm); -err_disable_clk_auxadc: - clk_disable_unprepare(mt->clk_auxadc); - - return ret; -} - -static int mtk_thermal_remove(struct platform_device *pdev) -{ - struct mtk_thermal *mt = platform_get_drvdata(pdev); - - clk_disable_unprepare(mt->clk_peri_therm); - clk_disable_unprepare(mt->clk_auxadc); - - return 0; } static struct platform_driver mtk_thermal_driver = { .probe = mtk_thermal_probe, - .remove = mtk_thermal_remove, .driver = { .name = "mtk-thermal", .of_match_table = mtk_thermal_of_match, -- GitLab From f0fb67c27160eb1aed1524cf5bf7dbbc3174f1b9 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Sun, 19 Mar 2023 11:32:31 -0500 Subject: [PATCH 4003/5631] thermal/drivers/mediatek: Use of_address_to_resource() Replace of_get_address() and of_translate_address() calls with single call to of_address_to_resource(). Signed-off-by: Rob Herring Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230319163231.226738-1-robh@kernel.org --- drivers/thermal/mediatek/auxadc_thermal.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/thermal/mediatek/auxadc_thermal.c b/drivers/thermal/mediatek/auxadc_thermal.c index b59fe4307b0a..0b5528804bbd 100644 --- a/drivers/thermal/mediatek/auxadc_thermal.c +++ b/drivers/thermal/mediatek/auxadc_thermal.c @@ -979,14 +979,12 @@ static void mtk_thermal_init_bank(struct mtk_thermal *mt, int num, static u64 of_get_phys_base(struct device_node *np) { - u64 size64; - const __be32 *regaddr_p; + struct resource res; - regaddr_p = of_get_address(np, 0, &size64, NULL); - if (!regaddr_p) + if (of_address_to_resource(np, 0, &res)) return OF_BAD_ADDR; - return of_translate_address(np, regaddr_p); + return res.start; } static int mtk_thermal_extract_efuse_v1(struct mtk_thermal *mt, u32 *buf) -- GitLab From 2afa82d1fc648c8d4c2ef9e876626abb1089f9ab Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 20 Apr 2023 09:24:29 +0200 Subject: [PATCH 4004/5631] dt-bindings: thermal: qcom-tsens: Correct unit address Match unit-address to first reg entry. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Acked-by: Amit Kucheria Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20230420072429.36255-1-krzysztof.kozlowski@linaro.org --- Documentation/devicetree/bindings/thermal/qcom-tsens.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml index 926e9c51c93c..d1ec963a6834 100644 --- a/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml +++ b/Documentation/devicetree/bindings/thermal/qcom-tsens.yaml @@ -326,7 +326,7 @@ examples: - | #include // Example 1 (new calbiration data: for pre v1 IP): - thermal-sensor@900000 { + thermal-sensor@4a9000 { compatible = "qcom,msm8916-tsens", "qcom,tsens-v0_1"; reg = <0x4a9000 0x1000>, /* TM */ <0x4a8000 0x1000>; /* SROT */ @@ -356,7 +356,7 @@ examples: - | #include // Example 1 (legacy: for pre v1 IP): - tsens1: thermal-sensor@900000 { + tsens1: thermal-sensor@4a9000 { compatible = "qcom,msm8916-tsens", "qcom,tsens-v0_1"; reg = <0x4a9000 0x1000>, /* TM */ <0x4a8000 0x1000>; /* SROT */ -- GitLab From f736d2c0caa8348b0bcd897972e470f7a596caad Mon Sep 17 00:00:00 2001 From: David Virag Date: Tue, 31 Jan 2023 19:30:06 +0100 Subject: [PATCH 4005/5631] mfd: sec: Remove PMICs without compatibles The S5M8751 and S5M8763 PMIC chips have no corresponding compatible values, so since board file support was removed for this driver, there is no way to specify these PMICs as present in boards anymore. Remove leftovers of these chips since it's dead code. Signed-off-by: David Virag Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230131183008.4451-2-virag.david003@gmail.com --- drivers/mfd/sec-core.c | 46 --------------- drivers/mfd/sec-irq.c | 89 ---------------------------- include/linux/mfd/samsung/core.h | 1 - include/linux/mfd/samsung/s5m8763.h | 90 ----------------------------- 4 files changed, 226 deletions(-) delete mode 100644 include/linux/mfd/samsung/s5m8763.h diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index b03edda56009..c2d0ed496959 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -24,22 +24,9 @@ #include #include #include -#include #include #include -static const struct mfd_cell s5m8751_devs[] = { - { .name = "s5m8751-pmic", }, - { .name = "s5m-charger", }, - { .name = "s5m8751-codec", }, -}; - -static const struct mfd_cell s5m8763_devs[] = { - { .name = "s5m8763-pmic", }, - { .name = "s5m-rtc", }, - { .name = "s5m-charger", }, -}; - static const struct mfd_cell s5m8767_devs[] = { { .name = "s5m8767-pmic", }, { .name = "s5m-rtc", }, @@ -158,19 +145,6 @@ static bool s2mpu02_volatile(struct device *dev, unsigned int reg) } } -static bool s5m8763_volatile(struct device *dev, unsigned int reg) -{ - switch (reg) { - case S5M8763_REG_IRQM1: - case S5M8763_REG_IRQM2: - case S5M8763_REG_IRQM3: - case S5M8763_REG_IRQM4: - return false; - default: - return true; - } -} - static const struct regmap_config sec_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -230,15 +204,6 @@ static const struct regmap_config s2mpu02_regmap_config = { .cache_type = REGCACHE_FLAT, }; -static const struct regmap_config s5m8763_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - - .max_register = S5M8763_REG_LBCNFG2, - .volatile_reg = s5m8763_volatile, - .cache_type = REGCACHE_FLAT, -}; - static const struct regmap_config s5m8767_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -348,9 +313,6 @@ static int sec_pmic_probe(struct i2c_client *i2c) case S2MPS15X: regmap = &s2mps15_regmap_config; break; - case S5M8763X: - regmap = &s5m8763_regmap_config; - break; case S5M8767X: regmap = &s5m8767_regmap_config; break; @@ -375,14 +337,6 @@ static int sec_pmic_probe(struct i2c_client *i2c) pm_runtime_set_active(sec_pmic->dev); switch (sec_pmic->device_type) { - case S5M8751X: - sec_devs = s5m8751_devs; - num_sec_devs = ARRAY_SIZE(s5m8751_devs); - break; - case S5M8763X: - sec_devs = s5m8763_devs; - num_sec_devs = ARRAY_SIZE(s5m8763_devs); - break; case S5M8767X: sec_devs = s5m8767_devs; num_sec_devs = ARRAY_SIZE(s5m8767_devs); diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c index f5f59fdc72fe..e191aeb0c07c 100644 --- a/drivers/mfd/sec-irq.c +++ b/drivers/mfd/sec-irq.c @@ -14,7 +14,6 @@ #include #include #include -#include #include static const struct regmap_irq s2mps11_irqs[] = { @@ -297,81 +296,6 @@ static const struct regmap_irq s5m8767_irqs[] = { }, }; -static const struct regmap_irq s5m8763_irqs[] = { - [S5M8763_IRQ_DCINF] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_DCINF_MASK, - }, - [S5M8763_IRQ_DCINR] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_DCINR_MASK, - }, - [S5M8763_IRQ_JIGF] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_JIGF_MASK, - }, - [S5M8763_IRQ_JIGR] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_JIGR_MASK, - }, - [S5M8763_IRQ_PWRONF] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_PWRONF_MASK, - }, - [S5M8763_IRQ_PWRONR] = { - .reg_offset = 0, - .mask = S5M8763_IRQ_PWRONR_MASK, - }, - [S5M8763_IRQ_WTSREVNT] = { - .reg_offset = 1, - .mask = S5M8763_IRQ_WTSREVNT_MASK, - }, - [S5M8763_IRQ_SMPLEVNT] = { - .reg_offset = 1, - .mask = S5M8763_IRQ_SMPLEVNT_MASK, - }, - [S5M8763_IRQ_ALARM1] = { - .reg_offset = 1, - .mask = S5M8763_IRQ_ALARM1_MASK, - }, - [S5M8763_IRQ_ALARM0] = { - .reg_offset = 1, - .mask = S5M8763_IRQ_ALARM0_MASK, - }, - [S5M8763_IRQ_ONKEY1S] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_ONKEY1S_MASK, - }, - [S5M8763_IRQ_TOPOFFR] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_TOPOFFR_MASK, - }, - [S5M8763_IRQ_DCINOVPR] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_DCINOVPR_MASK, - }, - [S5M8763_IRQ_CHGRSTF] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_CHGRSTF_MASK, - }, - [S5M8763_IRQ_DONER] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_DONER_MASK, - }, - [S5M8763_IRQ_CHGFAULT] = { - .reg_offset = 2, - .mask = S5M8763_IRQ_CHGFAULT_MASK, - }, - [S5M8763_IRQ_LOBAT1] = { - .reg_offset = 3, - .mask = S5M8763_IRQ_LOBAT1_MASK, - }, - [S5M8763_IRQ_LOBAT2] = { - .reg_offset = 3, - .mask = S5M8763_IRQ_LOBAT2_MASK, - }, -}; - static const struct regmap_irq_chip s2mps11_irq_chip = { .name = "s2mps11", .irqs = s2mps11_irqs, @@ -425,16 +349,6 @@ static const struct regmap_irq_chip s5m8767_irq_chip = { .ack_base = S5M8767_REG_INT1, }; -static const struct regmap_irq_chip s5m8763_irq_chip = { - .name = "s5m8763", - .irqs = s5m8763_irqs, - .num_irqs = ARRAY_SIZE(s5m8763_irqs), - .num_regs = 4, - .status_base = S5M8763_REG_IRQ1, - .mask_base = S5M8763_REG_IRQM1, - .ack_base = S5M8763_REG_IRQ1, -}; - int sec_irq_init(struct sec_pmic_dev *sec_pmic) { int ret = 0; @@ -448,9 +362,6 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic) } switch (type) { - case S5M8763X: - sec_irq_chip = &s5m8763_irq_chip; - break; case S5M8767X: sec_irq_chip = &s5m8767_irq_chip; break; diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index f92fe090473d..07aae649a86f 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -36,7 +36,6 @@ struct gpio_desc; enum sec_device_type { - S5M8751X, S5M8763X, S5M8767X, S2MPA01, diff --git a/include/linux/mfd/samsung/s5m8763.h b/include/linux/mfd/samsung/s5m8763.h deleted file mode 100644 index c534f086ca16..000000000000 --- a/include/linux/mfd/samsung/s5m8763.h +++ /dev/null @@ -1,90 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright (c) 2011 Samsung Electronics Co., Ltd - * http://www.samsung.com - */ - -#ifndef __LINUX_MFD_S5M8763_H -#define __LINUX_MFD_S5M8763_H - -/* S5M8763 registers */ -enum s5m8763_reg { - S5M8763_REG_IRQ1, - S5M8763_REG_IRQ2, - S5M8763_REG_IRQ3, - S5M8763_REG_IRQ4, - S5M8763_REG_IRQM1, - S5M8763_REG_IRQM2, - S5M8763_REG_IRQM3, - S5M8763_REG_IRQM4, - S5M8763_REG_STATUS1, - S5M8763_REG_STATUS2, - S5M8763_REG_STATUSM1, - S5M8763_REG_STATUSM2, - S5M8763_REG_CHGR1, - S5M8763_REG_CHGR2, - S5M8763_REG_LDO_ACTIVE_DISCHARGE1, - S5M8763_REG_LDO_ACTIVE_DISCHARGE2, - S5M8763_REG_BUCK_ACTIVE_DISCHARGE3, - S5M8763_REG_ONOFF1, - S5M8763_REG_ONOFF2, - S5M8763_REG_ONOFF3, - S5M8763_REG_ONOFF4, - S5M8763_REG_BUCK1_VOLTAGE1, - S5M8763_REG_BUCK1_VOLTAGE2, - S5M8763_REG_BUCK1_VOLTAGE3, - S5M8763_REG_BUCK1_VOLTAGE4, - S5M8763_REG_BUCK2_VOLTAGE1, - S5M8763_REG_BUCK2_VOLTAGE2, - S5M8763_REG_BUCK3, - S5M8763_REG_BUCK4, - S5M8763_REG_LDO1_LDO2, - S5M8763_REG_LDO3, - S5M8763_REG_LDO4, - S5M8763_REG_LDO5, - S5M8763_REG_LDO6, - S5M8763_REG_LDO7, - S5M8763_REG_LDO7_LDO8, - S5M8763_REG_LDO9_LDO10, - S5M8763_REG_LDO11, - S5M8763_REG_LDO12, - S5M8763_REG_LDO13, - S5M8763_REG_LDO14, - S5M8763_REG_LDO15, - S5M8763_REG_LDO16, - S5M8763_REG_BKCHR, - S5M8763_REG_LBCNFG1, - S5M8763_REG_LBCNFG2, -}; - -/* S5M8763 regulator ids */ -enum s5m8763_regulators { - S5M8763_LDO1, - S5M8763_LDO2, - S5M8763_LDO3, - S5M8763_LDO4, - S5M8763_LDO5, - S5M8763_LDO6, - S5M8763_LDO7, - S5M8763_LDO8, - S5M8763_LDO9, - S5M8763_LDO10, - S5M8763_LDO11, - S5M8763_LDO12, - S5M8763_LDO13, - S5M8763_LDO14, - S5M8763_LDO15, - S5M8763_LDO16, - S5M8763_BUCK1, - S5M8763_BUCK2, - S5M8763_BUCK3, - S5M8763_BUCK4, - S5M8763_AP_EN32KHZ, - S5M8763_CP_EN32KHZ, - S5M8763_ENCHGVI, - S5M8763_ESAFEUSB1, - S5M8763_ESAFEUSB2, -}; - -#define S5M8763_ENRAMP (1 << 4) -#endif /* __LINUX_MFD_S5M8763_H */ -- GitLab From a3165abaa9bda3e729b434a3e684fcfa205f252a Mon Sep 17 00:00:00 2001 From: David Virag Date: Tue, 31 Jan 2023 19:30:07 +0100 Subject: [PATCH 4006/5631] rtc: s5m: Drop S5M8763 support The S5M8763 MFD has no device tree compatible, and since board file support for it was removed, there's no way to use this MFD. After removing the remaining code for it from the MFD driver, also remove support for it in the s5m RTC driver, and all remaining references to it. Signed-off-by: David Virag Acked-by: Alexandre Belloni Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230131183008.4451-3-virag.david003@gmail.com --- drivers/rtc/rtc-s5m.c | 82 ++------------------------------ include/linux/mfd/samsung/core.h | 1 - include/linux/mfd/samsung/irq.h | 50 ------------------- 3 files changed, 3 insertions(+), 130 deletions(-) diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index 4243fe6d3842..dad294a0ce2a 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -85,7 +85,7 @@ struct s5m_rtc_reg_config { unsigned int write_alarm_udr_mask; }; -/* Register map for S5M8763 and S5M8767 */ +/* Register map for S5M8767 */ static const struct s5m_rtc_reg_config s5m_rtc_regs = { .regs_count = 8, .time = S5M_RTC_SEC, @@ -236,7 +236,6 @@ static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info, switch (info->device_type) { case S5M8767X: - case S5M8763X: ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val); val &= S5M_ALARM0_STATUS; break; @@ -299,7 +298,6 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) data |= info->regs->write_alarm_udr_mask; switch (info->device_type) { - case S5M8763X: case S5M8767X: data &= ~S5M_RTC_TIME_EN_MASK; break; @@ -329,38 +327,6 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info) return ret; } -static void s5m8763_data_to_tm(u8 *data, struct rtc_time *tm) -{ - tm->tm_sec = bcd2bin(data[RTC_SEC]); - tm->tm_min = bcd2bin(data[RTC_MIN]); - - if (data[RTC_HOUR] & HOUR_12) { - tm->tm_hour = bcd2bin(data[RTC_HOUR] & 0x1f); - if (data[RTC_HOUR] & HOUR_PM) - tm->tm_hour += 12; - } else { - tm->tm_hour = bcd2bin(data[RTC_HOUR] & 0x3f); - } - - tm->tm_wday = data[RTC_WEEKDAY] & 0x07; - tm->tm_mday = bcd2bin(data[RTC_DATE]); - tm->tm_mon = bcd2bin(data[RTC_MONTH]); - tm->tm_year = bcd2bin(data[RTC_YEAR1]) + bcd2bin(data[RTC_YEAR2]) * 100; - tm->tm_year -= 1900; -} - -static void s5m8763_tm_to_data(struct rtc_time *tm, u8 *data) -{ - data[RTC_SEC] = bin2bcd(tm->tm_sec); - data[RTC_MIN] = bin2bcd(tm->tm_min); - data[RTC_HOUR] = bin2bcd(tm->tm_hour); - data[RTC_WEEKDAY] = tm->tm_wday; - data[RTC_DATE] = bin2bcd(tm->tm_mday); - data[RTC_MONTH] = bin2bcd(tm->tm_mon); - data[RTC_YEAR1] = bin2bcd(tm->tm_year % 100); - data[RTC_YEAR2] = bin2bcd((tm->tm_year + 1900) / 100); -} - static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) { struct s5m_rtc_info *info = dev_get_drvdata(dev); @@ -385,10 +351,6 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm) return ret; switch (info->device_type) { - case S5M8763X: - s5m8763_data_to_tm(data, tm); - break; - case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -412,9 +374,6 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm) int ret = 0; switch (info->device_type) { - case S5M8763X: - s5m8763_tm_to_data(tm, data); - break; case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -444,7 +403,6 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) { struct s5m_rtc_info *info = dev_get_drvdata(dev); u8 data[RTC_MAX_NUM_TIME_REGS]; - unsigned int val; int ret, i; ret = regmap_bulk_read(info->regmap, info->regs->alarm0, data, @@ -453,15 +411,6 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) return ret; switch (info->device_type) { - case S5M8763X: - s5m8763_data_to_tm(data, &alrm->time); - ret = regmap_read(info->regmap, S5M_ALARM0_CONF, &val); - if (ret < 0) - return ret; - - alrm->enabled = !!val; - break; - case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -500,10 +449,6 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info) dev_dbg(info->dev, "%s: %ptR(%d)\n", __func__, &tm, tm.tm_wday); switch (info->device_type) { - case S5M8763X: - ret = regmap_write(info->regmap, S5M_ALARM0_CONF, 0); - break; - case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -531,7 +476,6 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info) { int ret; u8 data[RTC_MAX_NUM_TIME_REGS]; - u8 alarm0_conf; struct rtc_time tm; ret = regmap_bulk_read(info->regmap, info->regs->alarm0, data, @@ -543,11 +487,6 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info) dev_dbg(info->dev, "%s: %ptR(%d)\n", __func__, &tm, tm.tm_wday); switch (info->device_type) { - case S5M8763X: - alarm0_conf = 0x77; - ret = regmap_write(info->regmap, S5M_ALARM0_CONF, alarm0_conf); - break; - case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -585,10 +524,6 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) int ret; switch (info->device_type) { - case S5M8763X: - s5m8763_tm_to_data(&alrm->time, data); - break; - case S5M8767X: case S2MPS15X: case S2MPS14X: @@ -655,7 +590,6 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info) int ret; switch (info->device_type) { - case S5M8763X: case S5M8767X: /* UDR update time. Default of 7.32 ms is too long. */ ret = regmap_update_bits(info->regmap, S5M_RTC_UDR_CON, @@ -729,11 +663,6 @@ static int s5m_rtc_probe(struct platform_device *pdev) info->regs = &s2mps13_rtc_regs; alarm_irq = S2MPS14_IRQ_RTCA0; break; - case S5M8763X: - regmap_cfg = &s5m_rtc_regmap_config; - info->regs = &s5m_rtc_regs; - alarm_irq = S5M8763_IRQ_ALARM0; - break; case S5M8767X: regmap_cfg = &s5m_rtc_regmap_config; info->regs = &s5m_rtc_regs; @@ -786,13 +715,8 @@ static int s5m_rtc_probe(struct platform_device *pdev) info->rtc_dev->ops = &s5m_rtc_ops; - if (info->device_type == S5M8763X) { - info->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_0000; - info->rtc_dev->range_max = RTC_TIMESTAMP_END_9999; - } else { - info->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_2000; - info->rtc_dev->range_max = RTC_TIMESTAMP_END_2099; - } + info->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_2000; + info->rtc_dev->range_max = RTC_TIMESTAMP_END_2099; if (!info->irq) { clear_bit(RTC_FEATURE_ALARM, info->rtc_dev->features); diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 07aae649a86f..a212b9f72bc9 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -36,7 +36,6 @@ struct gpio_desc; enum sec_device_type { - S5M8763X, S5M8767X, S2MPA01, S2MPS11X, diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h index 6cfe4201a106..3fd2775eb9bb 100644 --- a/include/linux/mfd/samsung/irq.h +++ b/include/linux/mfd/samsung/irq.h @@ -194,54 +194,4 @@ enum s5m8767_irq { #define S5M8767_IRQ_RTC1S_MASK (1 << 4) #define S5M8767_IRQ_WTSR_MASK (1 << 5) -enum s5m8763_irq { - S5M8763_IRQ_DCINF, - S5M8763_IRQ_DCINR, - S5M8763_IRQ_JIGF, - S5M8763_IRQ_JIGR, - S5M8763_IRQ_PWRONF, - S5M8763_IRQ_PWRONR, - - S5M8763_IRQ_WTSREVNT, - S5M8763_IRQ_SMPLEVNT, - S5M8763_IRQ_ALARM1, - S5M8763_IRQ_ALARM0, - - S5M8763_IRQ_ONKEY1S, - S5M8763_IRQ_TOPOFFR, - S5M8763_IRQ_DCINOVPR, - S5M8763_IRQ_CHGRSTF, - S5M8763_IRQ_DONER, - S5M8763_IRQ_CHGFAULT, - - S5M8763_IRQ_LOBAT1, - S5M8763_IRQ_LOBAT2, - - S5M8763_IRQ_NR, -}; - -#define S5M8763_IRQ_DCINF_MASK (1 << 2) -#define S5M8763_IRQ_DCINR_MASK (1 << 3) -#define S5M8763_IRQ_JIGF_MASK (1 << 4) -#define S5M8763_IRQ_JIGR_MASK (1 << 5) -#define S5M8763_IRQ_PWRONF_MASK (1 << 6) -#define S5M8763_IRQ_PWRONR_MASK (1 << 7) - -#define S5M8763_IRQ_WTSREVNT_MASK (1 << 0) -#define S5M8763_IRQ_SMPLEVNT_MASK (1 << 1) -#define S5M8763_IRQ_ALARM1_MASK (1 << 2) -#define S5M8763_IRQ_ALARM0_MASK (1 << 3) - -#define S5M8763_IRQ_ONKEY1S_MASK (1 << 0) -#define S5M8763_IRQ_TOPOFFR_MASK (1 << 2) -#define S5M8763_IRQ_DCINOVPR_MASK (1 << 3) -#define S5M8763_IRQ_CHGRSTF_MASK (1 << 4) -#define S5M8763_IRQ_DONER_MASK (1 << 5) -#define S5M8763_IRQ_CHGFAULT_MASK (1 << 7) - -#define S5M8763_IRQ_LOBAT1_MASK (1 << 0) -#define S5M8763_IRQ_LOBAT2_MASK (1 << 1) - -#define S5M8763_ENRAMP (1 << 4) - #endif /* __LINUX_MFD_SEC_IRQ_H */ -- GitLab From ded99b89d25fd73a1d7bd910378e0339fd9d4c4a Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 1 Mar 2023 10:54:02 +0100 Subject: [PATCH 4007/5631] mfd: intel_soc_pmic_chtwc: Add Lenovo Yoga Book X90F to intel_cht_wc_models The Android Lenovo Yoga Book X90F / X90L uses the same charger / fuelgauge setup as the already supported Windows Lenovo Yoga Book X91F/L, add a DMI match for this to intel_cht_wc_models with driver_data set to INTEL_CHT_WC_LENOVO_YOGABOOK1. When the quirk for the X91F/L was initially added it was written to also apply to the X90F/L but this does not work because the Android version of the Yoga Book uses completely different DMI strings. Also adjust the X91F/L quirk to reflect that it only applies to the X91F/L models. Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230301095402.28582-1-hdegoede@redhat.com --- drivers/mfd/intel_soc_pmic_chtwc.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/intel_soc_pmic_chtwc.c b/drivers/mfd/intel_soc_pmic_chtwc.c index d53dae255490..871776d511e3 100644 --- a/drivers/mfd/intel_soc_pmic_chtwc.c +++ b/drivers/mfd/intel_soc_pmic_chtwc.c @@ -159,11 +159,19 @@ static const struct dmi_system_id cht_wc_model_dmi_ids[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Mipad2"), }, }, { - /* Lenovo Yoga Book X90F / X91F / X91L */ + /* Lenovo Yoga Book X90F / X90L */ .driver_data = (void *)(long)INTEL_CHT_WC_LENOVO_YOGABOOK1, .matches = { - /* Non exact match to match all versions */ - DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9"), + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "YETI-11"), + }, + }, { + /* Lenovo Yoga Book X91F / X91L */ + .driver_data = (void *)(long)INTEL_CHT_WC_LENOVO_YOGABOOK1, + .matches = { + /* Non exact match to match F + L versions */ + DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X91"), }, }, { /* Lenovo Yoga Tab 3 Pro YT3-X90F */ -- GitLab From d16fc6858777f861717f7b2c0ef3676e419f52a0 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Mon, 6 Feb 2023 11:22:31 +0800 Subject: [PATCH 4008/5631] mfd: si476x-cmd: Fix several issues reported by codespell Fix some typo, find by 'codespell drivers/mfd/si476x-cmd.c' succsess -> success interace -> interface comand -> command failre -> failure Reported-by: k2ci Signed-off-by: Jackie Liu Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230206032231.3208296-1-liu.yun@linux.dev --- drivers/mfd/si476x-cmd.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/mfd/si476x-cmd.c b/drivers/mfd/si476x-cmd.c index f32f1fb93e37..c9a0ec084aa8 100644 --- a/drivers/mfd/si476x-cmd.c +++ b/drivers/mfd/si476x-cmd.c @@ -251,7 +251,7 @@ static int si476x_core_parse_and_nag_about_error(struct si476x_core *core) * @usecs: amount of time to wait before reading the response (in * usecs) * - * Function returns 0 on succsess and negative error code on + * Function returns 0 on success and negative error code on * failure */ static int si476x_core_send_command(struct si476x_core *core, @@ -398,7 +398,7 @@ static int si476x_cmd_tune_seek_freq(struct si476x_core *core, * The command requests the firmware and patch version for currently * loaded firmware (dependent on the function of the device FM/AM/WB) * - * Function returns 0 on succsess and negative error code on + * Function returns 0 on success and negative error code on * failure */ int si476x_core_cmd_func_info(struct si476x_core *core, @@ -429,7 +429,7 @@ EXPORT_SYMBOL_GPL(si476x_core_cmd_func_info); * @property: property address * @value: property value * - * Function returns 0 on succsess and negative error code on + * Function returns 0 on success and negative error code on * failure */ int si476x_core_cmd_set_property(struct si476x_core *core, @@ -545,13 +545,13 @@ EXPORT_SYMBOL_GPL(si476x_core_cmd_dig_audio_pin_cfg); * SI476X_IQCLK_NOOP - do not modify the behaviour * SI476X_IQCLK_TRISTATE - put the pin in tristate condition, * enable 1MOhm pulldown - * SI476X_IQCLK_IQ - set pin to be a part of I/Q interace + * SI476X_IQCLK_IQ - set pin to be a part of I/Q interface * in master mode * @iqfs: - IQFS pin function configuration: * SI476X_IQFS_NOOP - do not modify the behaviour * SI476X_IQFS_TRISTATE - put the pin in tristate condition, * enable 1MOhm pulldown - * SI476X_IQFS_IQ - set pin to be a part of I/Q interace + * SI476X_IQFS_IQ - set pin to be a part of I/Q interface * in master mode * @iout: - IOUT pin function configuration: * SI476X_IOUT_NOOP - do not modify the behaviour @@ -589,7 +589,7 @@ EXPORT_SYMBOL_GPL(si476x_core_cmd_zif_pin_cfg); /** * si476x_core_cmd_ic_link_gpo_ctl_pin_cfg - send - * 'IC_LINK_GPIO_CTL_PIN_CFG' comand to the device + * 'IC_LINK_GPIO_CTL_PIN_CFG' command to the device * @core: - device to send the command to * @icin: - ICIN pin function configuration: * SI476X_ICIN_NOOP - do not modify the behaviour @@ -1014,7 +1014,7 @@ EXPORT_SYMBOL_GPL(si476x_core_cmd_fm_phase_diversity); * NOTE caller must hold core lock * * Function returns the value of the status bit in case of success and - * negative error code in case of failre. + * negative error code in case of failure. */ int si476x_core_cmd_fm_phase_div_status(struct si476x_core *core) { -- GitLab From 74d3de876a3aa9c91ccf8e5559f41b30ed8a9cd1 Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:33:01 +0800 Subject: [PATCH 4009/5631] mfd: hi6421-pmic: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081733017704501@zte.com.cn --- drivers/mfd/hi6421-pmic-core.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/hi6421-pmic-core.c b/drivers/mfd/hi6421-pmic-core.c index eba88b80d969..cb5cf4a81c06 100644 --- a/drivers/mfd/hi6421-pmic-core.c +++ b/drivers/mfd/hi6421-pmic-core.c @@ -50,7 +50,6 @@ MODULE_DEVICE_TABLE(of, of_hi6421_pmic_match); static int hi6421_pmic_probe(struct platform_device *pdev) { struct hi6421_pmic *pmic; - struct resource *res; const struct of_device_id *id; const struct mfd_cell *subdevs; enum hi6421_type type; @@ -66,8 +65,7 @@ static int hi6421_pmic_probe(struct platform_device *pdev) if (!pmic) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&pdev->dev, res); + base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(base)) return PTR_ERR(base); -- GitLab From 4239bff3455dd28733d719b79400df1b65b4d9fa Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:33:54 +0800 Subject: [PATCH 4010/5631] mfd: ipaq-micro: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081733542304522@zte.com.cn --- drivers/mfd/ipaq-micro.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/ipaq-micro.c b/drivers/mfd/ipaq-micro.c index 4cd5ecc72211..6d3968458e81 100644 --- a/drivers/mfd/ipaq-micro.c +++ b/drivers/mfd/ipaq-micro.c @@ -381,7 +381,6 @@ static int __maybe_unused micro_resume(struct device *dev) static int __init micro_probe(struct platform_device *pdev) { struct ipaq_micro *micro; - struct resource *res; int ret; int irq; @@ -391,8 +390,7 @@ static int __init micro_probe(struct platform_device *pdev) micro->dev = &pdev->dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - micro->base = devm_ioremap_resource(&pdev->dev, res); + micro->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(micro->base)) return PTR_ERR(micro->base); -- GitLab From 0479ed2cf70c69fa703a1e6cbb4d5c2e7e4442a2 Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:35:44 +0800 Subject: [PATCH 4011/5631] mfd: ssbi: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081735440864562@zte.com.cn --- drivers/mfd/ssbi.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/ssbi.c b/drivers/mfd/ssbi.c index 94f60df0decd..dee89db3471d 100644 --- a/drivers/mfd/ssbi.c +++ b/drivers/mfd/ssbi.c @@ -262,7 +262,6 @@ EXPORT_SYMBOL_GPL(ssbi_write); static int ssbi_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct resource *mem_res; struct ssbi *ssbi; const char *type; @@ -270,8 +269,7 @@ static int ssbi_probe(struct platform_device *pdev) if (!ssbi) return -ENOMEM; - mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ssbi->base = devm_ioremap_resource(&pdev->dev, mem_res); + ssbi->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(ssbi->base)) return PTR_ERR(ssbi->base); -- GitLab From 4723d2ef5329f28f569bf9e855bd5bd4b691aa37 Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:36:50 +0800 Subject: [PATCH 4012/5631] mfd: sun4i-gpadc: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081736500534579@zte.com.cn --- drivers/mfd/sun4i-gpadc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/sun4i-gpadc.c b/drivers/mfd/sun4i-gpadc.c index edc180d83a4b..d1cbea27b136 100644 --- a/drivers/mfd/sun4i-gpadc.c +++ b/drivers/mfd/sun4i-gpadc.c @@ -93,7 +93,6 @@ MODULE_DEVICE_TABLE(of, sun4i_gpadc_of_match); static int sun4i_gpadc_probe(struct platform_device *pdev) { struct sun4i_gpadc_dev *dev; - struct resource *mem; const struct of_device_id *of_id; const struct mfd_cell *cells; unsigned int irq, size; @@ -124,8 +123,7 @@ static int sun4i_gpadc_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dev->base = devm_ioremap_resource(&pdev->dev, mem); + dev->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(dev->base)) return PTR_ERR(dev->base); -- GitLab From ccb92c4d1608eb07c0d6b677c3bc7745db7fa33d Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:31:59 +0800 Subject: [PATCH 4013/5631] mfd: atmel-flexcom: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081731593374472@zte.com.cn --- drivers/mfd/atmel-flexcom.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/atmel-flexcom.c b/drivers/mfd/atmel-flexcom.c index 33caa4fba6af..b52f7ffdad35 100644 --- a/drivers/mfd/atmel-flexcom.c +++ b/drivers/mfd/atmel-flexcom.c @@ -37,7 +37,6 @@ struct atmel_flexcom { static int atmel_flexcom_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct resource *res; struct atmel_flexcom *ddata; int err; @@ -55,8 +54,7 @@ static int atmel_flexcom_probe(struct platform_device *pdev) ddata->opmode > ATMEL_FLEXCOM_MODE_TWI) return -EINVAL; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ddata->base = devm_ioremap_resource(&pdev->dev, res); + ddata->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(ddata->base)) return PTR_ERR(ddata->base); -- GitLab From 2e9de58c65f76ac9617b0028254edaca01529208 Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 8 Feb 2023 17:34:51 +0800 Subject: [PATCH 4014/5631] mfd: qcom_rpm: Use devm_platform_get_and_ioremap_resource() Convert platform_get_resource(), devm_ioremap_resource() to a single call to devm_platform_get_and_ioremap_resource(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Reviewed-by: Konrad Dybcio Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/202302081734511884545@zte.com.cn --- drivers/mfd/qcom_rpm.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/mfd/qcom_rpm.c b/drivers/mfd/qcom_rpm.c index 8fea0e511550..086611322874 100644 --- a/drivers/mfd/qcom_rpm.c +++ b/drivers/mfd/qcom_rpm.c @@ -530,7 +530,6 @@ static int qcom_rpm_probe(struct platform_device *pdev) { const struct of_device_id *match; struct device_node *syscon_np; - struct resource *res; struct qcom_rpm *rpm; u32 fw_version[3]; int irq_wakeup; @@ -576,8 +575,7 @@ static int qcom_rpm_probe(struct platform_device *pdev) return -ENODEV; rpm->data = match->data; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - rpm->status_regs = devm_ioremap_resource(&pdev->dev, res); + rpm->status_regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(rpm->status_regs)) return PTR_ERR(rpm->status_regs); rpm->ctrl_regs = rpm->status_regs + 0x400; -- GitLab From b09ed62f2d985c8eb2d5d5b560bebac653fdba20 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Mon, 13 Feb 2023 21:13:37 +0100 Subject: [PATCH 4015/5631] dt-bindings: mfd: qcom,spmi-pmic: Allow RRADC as adc@ subnode This was omitted when adding the RRADC bindings. Fixes: 7ea58c951ab3 ("dt-bindings: iio: adc: document qcom-spmi-rradc") Signed-off-by: Konrad Dybcio Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230213201337.2089970-1-konrad.dybcio@linaro.org --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index adf88245c409..8f076bb622b1 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -115,6 +115,7 @@ patternProperties: type: object oneOf: - $ref: /schemas/iio/adc/qcom,spmi-iadc.yaml# + - $ref: /schemas/iio/adc/qcom,spmi-rradc.yaml# - $ref: /schemas/iio/adc/qcom,spmi-vadc.yaml# "^adc-tm@[0-9a-f]+$": -- GitLab From 86c6bb0edffa9fc02b4e3801b48c8e82114f1352 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 14 Feb 2023 09:58:59 +0100 Subject: [PATCH 4016/5631] mfd: core: Reorder fields in 'struct mfd_cell' to save some memory Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size from 144 to 128 bytes. As an example: $ size drivers/mfd/as3722.o (Before) text data bss dec hex filename 9441 680 16 10137 2799 drivers/mfd/as3722.o $ size drivers/mfd/as3722.o (After) text data bss dec hex filename 9345 680 16 10041 2739 drivers/mfd/as3722.o Signed-off-by: Christophe JAILLET Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/bb631974888dfe1af593b6280cf30fb913d2d1a4.1676365116.git.christophe.jaillet@wanadoo.fr --- include/linux/mfd/core.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index 14ca7b471576..fc4a0e9fb3bb 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -78,6 +78,9 @@ struct mfd_cell { void *platform_data; size_t pdata_size; + /* Matches ACPI */ + const struct mfd_cell_acpi_match *acpi_match; + /* Software node for the device. */ const struct software_node *swnode; @@ -97,9 +100,6 @@ struct mfd_cell { /* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */ bool use_of_reg; - /* Matches ACPI */ - const struct mfd_cell_acpi_match *acpi_match; - /* * These resources can be specified relative to the parent device. * For accessing hardware you should use resources from the platform dev @@ -119,8 +119,8 @@ struct mfd_cell { /* A list of regulator supplies that should be mapped to the MFD * device rather than the child device when requested */ - const char * const *parent_supplies; int num_parent_supplies; + const char * const *parent_supplies; }; /* -- GitLab From c301311a523bcc48d6d626cbd4654463a105e089 Mon Sep 17 00:00:00 2001 From: Poovendhan Selvaraj Date: Wed, 8 Feb 2023 11:03:32 +0530 Subject: [PATCH 4017/5631] dt-bindings: mfd: Add the tcsr compatible for IPQ9574 Add the tcsr compatible string for IPQ9574 SoC Signed-off-by: Poovendhan Selvaraj Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230208053332.16537-6-quic_poovendh@quicinc.com --- Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml index 2eeebe920e6e..203fc890c9a3 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml @@ -31,6 +31,7 @@ properties: - qcom,tcsr-ipq5332 - qcom,tcsr-ipq6018 - qcom,tcsr-ipq8064 + - qcom,tcsr-ipq9574 - qcom,tcsr-mdm9615 - qcom,tcsr-msm8226 - qcom,tcsr-msm8660 -- GitLab From 172a293707a55ba62e55a386eb601c8ef4824c85 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 16 Feb 2023 22:22:11 +0000 Subject: [PATCH 4018/5631] mfd: qcom-pm8008: Fix swapped mask/unmask in irq chip The usual behavior of mask registers is writing a '1' bit to disable (mask) an interrupt; similarly, writing a '1' bit to an unmask register enables (unmasks) an interrupt. Due to a longstanding issue in regmap-irq, mask and unmask registers were inverted when both kinds of registers were present on the same chip, ie. regmap-irq actually wrote '1's to the mask register to enable an IRQ and '1's to the unmask register to disable an IRQ. This was fixed by commit e8ffb12e7f06 ("regmap-irq: Fix inverted handling of unmask registers") but the fix is opt-in via mask_unmask_non_inverted = true because it requires manual changes for each affected driver. The new behavior will become the default once all drivers have been updated. The PM8008 appears to rely on the inverted behavior. It has separate set & clear registers for a register called INT_EN, which presumably enables interrupts by writing '1's. Opt in to the new non-inverted behavior & swap mask_base/unmask_base. Signed-off-by: Aidan MacDonald Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230216222214.138671-2-aidanmacdonald.0x0@gmail.com --- drivers/mfd/qcom-pm8008.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/mfd/qcom-pm8008.c b/drivers/mfd/qcom-pm8008.c index 9f3c4a01b4c1..39fd2a792e73 100644 --- a/drivers/mfd/qcom-pm8008.c +++ b/drivers/mfd/qcom-pm8008.c @@ -45,8 +45,8 @@ enum { #define PM8008_GPIO2_ADDR PM8008_PERIPH_3_BASE #define PM8008_STATUS_BASE (PM8008_PERIPH_0_BASE | INT_LATCHED_STS_OFFSET) -#define PM8008_MASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_SET_OFFSET) -#define PM8008_UNMASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_CLR_OFFSET) +#define PM8008_MASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_CLR_OFFSET) +#define PM8008_UNMASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_SET_OFFSET) #define PM8008_TYPE_BASE (PM8008_PERIPH_0_BASE | INT_SET_TYPE_OFFSET) #define PM8008_ACK_BASE (PM8008_PERIPH_0_BASE | INT_LATCHED_CLR_OFFSET) #define PM8008_POLARITY_HI_BASE (PM8008_PERIPH_0_BASE | INT_POL_HIGH_OFFSET) @@ -131,6 +131,7 @@ static struct regmap_irq_chip pm8008_irq_chip = { .status_base = PM8008_STATUS_BASE, .mask_base = PM8008_MASK_BASE, .unmask_base = PM8008_UNMASK_BASE, + .mask_unmask_non_inverted = true, .type_base = PM8008_TYPE_BASE, .ack_base = PM8008_ACK_BASE, .virt_reg_base = pm8008_virt_regs, -- GitLab From fd0a2afa5ab2fb3ba5646e3bf907f2c4a8b4a291 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 16 Feb 2023 22:22:12 +0000 Subject: [PATCH 4019/5631] mfd: qcom-pm8008: Convert irq chip to config regs Replace type and virtual registers, which are both deprecated, with config registers. This also simplifies the driver because IRQ types are set in one place, the set_type_config() callback. Signed-off-by: Aidan MacDonald [Lee: Squashed in fix-up patch from Stephen Rothwell adapting to new .set_type_config() API] Signed-off-by: Stephen Rothwell Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230216222214.138671-3-aidanmacdonald.0x0@gmail.com --- drivers/mfd/qcom-pm8008.c | 51 ++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 25 deletions(-) diff --git a/drivers/mfd/qcom-pm8008.c b/drivers/mfd/qcom-pm8008.c index 39fd2a792e73..d502ecf05590 100644 --- a/drivers/mfd/qcom-pm8008.c +++ b/drivers/mfd/qcom-pm8008.c @@ -66,15 +66,16 @@ static struct regmap_irq_sub_irq_map pm8008_sub_reg_offsets[] = { REGMAP_IRQ_MAIN_REG_OFFSET(p3_offs), }; -static unsigned int pm8008_virt_regs[] = { - PM8008_POLARITY_HI_BASE, - PM8008_POLARITY_LO_BASE, -}; - enum { + SET_TYPE_INDEX, POLARITY_HI_INDEX, POLARITY_LO_INDEX, - PM8008_NUM_VIRT_REGS, +}; + +static unsigned int pm8008_config_regs[] = { + PM8008_TYPE_BASE, + PM8008_POLARITY_HI_BASE, + PM8008_POLARITY_LO_BASE, }; static struct regmap_irq pm8008_irqs[] = { @@ -88,32 +89,37 @@ static struct regmap_irq pm8008_irqs[] = { REGMAP_IRQ_REG(PM8008_IRQ_GPIO2, PM8008_GPIO2, BIT(0)), }; -static int pm8008_set_type_virt(unsigned int **virt_buf, - unsigned int type, unsigned long hwirq, - int reg) +static int pm8008_set_type_config(unsigned int **buf, unsigned int type, + const struct regmap_irq *irq_data, int idx, + void *irq_drv_data) { switch (type) { case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_LEVEL_LOW: - virt_buf[POLARITY_HI_INDEX][reg] &= ~pm8008_irqs[hwirq].mask; - virt_buf[POLARITY_LO_INDEX][reg] |= pm8008_irqs[hwirq].mask; + buf[POLARITY_HI_INDEX][idx] &= ~irq_data->mask; + buf[POLARITY_LO_INDEX][idx] |= irq_data->mask; break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_LEVEL_HIGH: - virt_buf[POLARITY_HI_INDEX][reg] |= pm8008_irqs[hwirq].mask; - virt_buf[POLARITY_LO_INDEX][reg] &= ~pm8008_irqs[hwirq].mask; + buf[POLARITY_HI_INDEX][idx] |= irq_data->mask; + buf[POLARITY_LO_INDEX][idx] &= ~irq_data->mask; break; case IRQ_TYPE_EDGE_BOTH: - virt_buf[POLARITY_HI_INDEX][reg] |= pm8008_irqs[hwirq].mask; - virt_buf[POLARITY_LO_INDEX][reg] |= pm8008_irqs[hwirq].mask; + buf[POLARITY_HI_INDEX][idx] |= irq_data->mask; + buf[POLARITY_LO_INDEX][idx] |= irq_data->mask; break; default: return -EINVAL; } + if (type & IRQ_TYPE_EDGE_BOTH) + buf[SET_TYPE_INDEX][idx] |= irq_data->mask; + else + buf[SET_TYPE_INDEX][idx] &= ~irq_data->mask; + return 0; } @@ -121,21 +127,20 @@ static struct regmap_irq_chip pm8008_irq_chip = { .name = "pm8008_irq", .main_status = I2C_INTR_STATUS_BASE, .num_main_regs = 1, - .num_virt_regs = PM8008_NUM_VIRT_REGS, .irqs = pm8008_irqs, .num_irqs = ARRAY_SIZE(pm8008_irqs), .num_regs = PM8008_NUM_PERIPHS, .not_fixed_stride = true, .sub_reg_offsets = pm8008_sub_reg_offsets, - .set_type_virt = pm8008_set_type_virt, .status_base = PM8008_STATUS_BASE, .mask_base = PM8008_MASK_BASE, .unmask_base = PM8008_UNMASK_BASE, .mask_unmask_non_inverted = true, - .type_base = PM8008_TYPE_BASE, .ack_base = PM8008_ACK_BASE, - .virt_reg_base = pm8008_virt_regs, - .num_type_reg = PM8008_NUM_PERIPHS, + .config_base = pm8008_config_regs, + .num_config_bases = ARRAY_SIZE(pm8008_config_regs), + .num_config_regs = PM8008_NUM_PERIPHS, + .set_type_config = pm8008_set_type_config, }; static struct regmap_config qcom_mfd_regmap_cfg = { @@ -185,11 +190,7 @@ static int pm8008_probe_irq_peripherals(struct device *dev, for (i = 0; i < ARRAY_SIZE(pm8008_irqs); i++) { type = &pm8008_irqs[i].type; - type->type_reg_offset = pm8008_irqs[i].reg_offset; - type->type_rising_val = pm8008_irqs[i].mask; - type->type_falling_val = pm8008_irqs[i].mask; - type->type_level_high_val = 0; - type->type_level_low_val = 0; + type->type_reg_offset = pm8008_irqs[i].reg_offset; if (type->type_reg_offset == PM8008_MISC) type->types_supported = IRQ_TYPE_EDGE_RISING; -- GitLab From ba97b5a505627fc2fb9c85f06afaef918e19032e Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 16 Feb 2023 22:22:13 +0000 Subject: [PATCH 4020/5631] mfd: qcom-pm8008: Use .get_irq_reg() for irq chip Replace the deprecated not_fixed_stride flag and the associated hierarchy of offsets with a .get_irq_reg() callback. Signed-off-by: Aidan MacDonald Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230216222214.138671-4-aidanmacdonald.0x0@gmail.com --- drivers/mfd/qcom-pm8008.c | 56 +++++++++++++++++---------------------- 1 file changed, 25 insertions(+), 31 deletions(-) diff --git a/drivers/mfd/qcom-pm8008.c b/drivers/mfd/qcom-pm8008.c index d502ecf05590..54fc9c298c03 100644 --- a/drivers/mfd/qcom-pm8008.c +++ b/drivers/mfd/qcom-pm8008.c @@ -44,28 +44,6 @@ enum { #define PM8008_GPIO1_ADDR PM8008_PERIPH_2_BASE #define PM8008_GPIO2_ADDR PM8008_PERIPH_3_BASE -#define PM8008_STATUS_BASE (PM8008_PERIPH_0_BASE | INT_LATCHED_STS_OFFSET) -#define PM8008_MASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_CLR_OFFSET) -#define PM8008_UNMASK_BASE (PM8008_PERIPH_0_BASE | INT_EN_SET_OFFSET) -#define PM8008_TYPE_BASE (PM8008_PERIPH_0_BASE | INT_SET_TYPE_OFFSET) -#define PM8008_ACK_BASE (PM8008_PERIPH_0_BASE | INT_LATCHED_CLR_OFFSET) -#define PM8008_POLARITY_HI_BASE (PM8008_PERIPH_0_BASE | INT_POL_HIGH_OFFSET) -#define PM8008_POLARITY_LO_BASE (PM8008_PERIPH_0_BASE | INT_POL_LOW_OFFSET) - -#define PM8008_PERIPH_OFFSET(paddr) (paddr - PM8008_PERIPH_0_BASE) - -static unsigned int p0_offs[] = {PM8008_PERIPH_OFFSET(PM8008_PERIPH_0_BASE)}; -static unsigned int p1_offs[] = {PM8008_PERIPH_OFFSET(PM8008_PERIPH_1_BASE)}; -static unsigned int p2_offs[] = {PM8008_PERIPH_OFFSET(PM8008_PERIPH_2_BASE)}; -static unsigned int p3_offs[] = {PM8008_PERIPH_OFFSET(PM8008_PERIPH_3_BASE)}; - -static struct regmap_irq_sub_irq_map pm8008_sub_reg_offsets[] = { - REGMAP_IRQ_MAIN_REG_OFFSET(p0_offs), - REGMAP_IRQ_MAIN_REG_OFFSET(p1_offs), - REGMAP_IRQ_MAIN_REG_OFFSET(p2_offs), - REGMAP_IRQ_MAIN_REG_OFFSET(p3_offs), -}; - enum { SET_TYPE_INDEX, POLARITY_HI_INDEX, @@ -73,9 +51,9 @@ enum { }; static unsigned int pm8008_config_regs[] = { - PM8008_TYPE_BASE, - PM8008_POLARITY_HI_BASE, - PM8008_POLARITY_LO_BASE, + INT_SET_TYPE_OFFSET, + INT_POL_HIGH_OFFSET, + INT_POL_LOW_OFFSET, }; static struct regmap_irq pm8008_irqs[] = { @@ -89,6 +67,23 @@ static struct regmap_irq pm8008_irqs[] = { REGMAP_IRQ_REG(PM8008_IRQ_GPIO2, PM8008_GPIO2, BIT(0)), }; +static const unsigned int pm8008_periph_base[] = { + PM8008_PERIPH_0_BASE, + PM8008_PERIPH_1_BASE, + PM8008_PERIPH_2_BASE, + PM8008_PERIPH_3_BASE, +}; + +static unsigned int pm8008_get_irq_reg(struct regmap_irq_chip_data *data, + unsigned int base, int index) +{ + /* Simple linear addressing for the main status register */ + if (base == I2C_INTR_STATUS_BASE) + return base + index; + + return pm8008_periph_base[index] + base; +} + static int pm8008_set_type_config(unsigned int **buf, unsigned int type, const struct regmap_irq *irq_data, int idx, void *irq_drv_data) @@ -130,17 +125,16 @@ static struct regmap_irq_chip pm8008_irq_chip = { .irqs = pm8008_irqs, .num_irqs = ARRAY_SIZE(pm8008_irqs), .num_regs = PM8008_NUM_PERIPHS, - .not_fixed_stride = true, - .sub_reg_offsets = pm8008_sub_reg_offsets, - .status_base = PM8008_STATUS_BASE, - .mask_base = PM8008_MASK_BASE, - .unmask_base = PM8008_UNMASK_BASE, + .status_base = INT_LATCHED_STS_OFFSET, + .mask_base = INT_EN_CLR_OFFSET, + .unmask_base = INT_EN_SET_OFFSET, .mask_unmask_non_inverted = true, - .ack_base = PM8008_ACK_BASE, + .ack_base = INT_LATCHED_CLR_OFFSET, .config_base = pm8008_config_regs, .num_config_bases = ARRAY_SIZE(pm8008_config_regs), .num_config_regs = PM8008_NUM_PERIPHS, .set_type_config = pm8008_set_type_config, + .get_irq_reg = pm8008_get_irq_reg, }; static struct regmap_config qcom_mfd_regmap_cfg = { -- GitLab From c8bce48225eff37d87d1eab12c907c813befa8e9 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Thu, 16 Feb 2023 22:22:14 +0000 Subject: [PATCH 4021/5631] mfd: qcom-pm8008: Remove workaround for a regmap-irq quirk Remove pm8008_init(), which according to the comments exists only as a workaround for regmap-irq's odd treatment of type registers. This workaround shouldn't be needed anymore because this driver uses config registers, which are always programmed by regmap-irq no matter what the initial register state is. Signed-off-by: Aidan MacDonald Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230216222214.138671-5-aidanmacdonald.0x0@gmail.com --- drivers/mfd/qcom-pm8008.c | 30 ------------------------------ 1 file changed, 30 deletions(-) diff --git a/drivers/mfd/qcom-pm8008.c b/drivers/mfd/qcom-pm8008.c index 54fc9c298c03..837246aab4ac 100644 --- a/drivers/mfd/qcom-pm8008.c +++ b/drivers/mfd/qcom-pm8008.c @@ -143,30 +143,6 @@ static struct regmap_config qcom_mfd_regmap_cfg = { .max_register = 0xFFFF, }; -static int pm8008_init(struct regmap *regmap) -{ - int rc; - - /* - * Set TEMP_ALARM peripheral's TYPE so that the regmap-irq framework - * reads this as the default value instead of zero, the HW default. - * This is required to enable the writing of TYPE registers in - * regmap_irq_sync_unlock(). - */ - rc = regmap_write(regmap, (PM8008_TEMP_ALARM_ADDR | INT_SET_TYPE_OFFSET), BIT(0)); - if (rc) - return rc; - - /* Do the same for GPIO1 and GPIO2 peripherals */ - rc = regmap_write(regmap, (PM8008_GPIO1_ADDR | INT_SET_TYPE_OFFSET), BIT(0)); - if (rc) - return rc; - - rc = regmap_write(regmap, (PM8008_GPIO2_ADDR | INT_SET_TYPE_OFFSET), BIT(0)); - - return rc; -} - static int pm8008_probe_irq_peripherals(struct device *dev, struct regmap *regmap, int client_irq) @@ -175,12 +151,6 @@ static int pm8008_probe_irq_peripherals(struct device *dev, struct regmap_irq_type *type; struct regmap_irq_chip_data *irq_data; - rc = pm8008_init(regmap); - if (rc) { - dev_err(dev, "Init failed: %d\n", rc); - return rc; - } - for (i = 0; i < ARRAY_SIZE(pm8008_irqs); i++) { type = &pm8008_irqs[i].type; -- GitLab From 679532c2f6df69ad65b8717c71b06e957d2f60e6 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Fri, 24 Feb 2023 15:08:05 +0000 Subject: [PATCH 4022/5631] mfd: bcm2835-pm: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Suggested-by: Luis Chamberlain Signed-off-by: Nick Alcock Reviewed-by: Florian Fainelli Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230224150811.80316-22-nick.alcock@oracle.com --- drivers/mfd/bcm2835-pm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/bcm2835-pm.c b/drivers/mfd/bcm2835-pm.c index 49cd1f03884a..2c0aa2a2c893 100644 --- a/drivers/mfd/bcm2835-pm.c +++ b/drivers/mfd/bcm2835-pm.c @@ -123,4 +123,3 @@ module_platform_driver(bcm2835_pm_driver); MODULE_AUTHOR("Eric Anholt "); MODULE_DESCRIPTION("Driver for Broadcom BCM2835 PM MFD"); -MODULE_LICENSE("GPL"); -- GitLab From cf973869b9c46a9c817831bc31d89a2c38b65ba0 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Fri, 24 Feb 2023 15:07:48 +0000 Subject: [PATCH 4023/5631] mfd: intel_soc_pmic_crc: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Suggested-by: Luis Chamberlain Signed-off-by: Nick Alcock Reviewed-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230224150811.80316-5-nick.alcock@oracle.com --- drivers/mfd/intel_soc_pmic_crc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/intel_soc_pmic_crc.c b/drivers/mfd/intel_soc_pmic_crc.c index b1548a933dc3..b745ace46e5b 100644 --- a/drivers/mfd/intel_soc_pmic_crc.c +++ b/drivers/mfd/intel_soc_pmic_crc.c @@ -271,6 +271,5 @@ static struct i2c_driver crystal_cove_i2c_driver = { module_i2c_driver(crystal_cove_i2c_driver); MODULE_DESCRIPTION("I2C driver for Intel SoC PMIC"); -MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Yang, Bin "); MODULE_AUTHOR("Zhu, Lejun "); -- GitLab From 4d820dda94162968ea743675d9338ff5df6f62d0 Mon Sep 17 00:00:00 2001 From: Emil Renner Berthing Date: Sat, 11 Feb 2023 05:18:15 +0200 Subject: [PATCH 4024/5631] dt-bindings: mfd: syscon: Add StarFive JH7100 sysmain compatible Document StarFive JH7100 SoC compatible for sysmain registers. Signed-off-by: Emil Renner Berthing Signed-off-by: Cristian Ciocaltea Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230211031821.976408-7-cristian.ciocaltea@collabora.com --- Documentation/devicetree/bindings/mfd/syscon.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/syscon.yaml b/Documentation/devicetree/bindings/mfd/syscon.yaml index c828c4f5e4a7..43f564be709f 100644 --- a/Documentation/devicetree/bindings/mfd/syscon.yaml +++ b/Documentation/devicetree/bindings/mfd/syscon.yaml @@ -67,6 +67,7 @@ properties: - rockchip,rk3568-qos - rockchip,rk3588-qos - rockchip,rv1126-qos + - starfive,jh7100-sysmain - const: syscon -- GitLab From 1be1b23696b3d4b0231c694f5e0767b4471d33a9 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:44 +0100 Subject: [PATCH 4025/5631] mfd: tqmx86: Do not access I2C_DETECT register through io_base The I2C_DETECT register is at IO port 0x1a7, which is outside the range passed to devm_ioport_map() for io_base, and was only working because there aren't actually any bounds checks for IO port accesses. Extending the range does not seem like a good solution here, as it would then conflict with the IO resource assigned to the I2C controller. As this is just a one-off access during probe, use a simple inb() instead. While we're at it, drop the unused define TQMX86_REG_I2C_INT_EN. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/e8300a30f0791afb67d79db8089fb6004855f378.1676892223.git.matthias.schiffer@ew.tq-group.com --- drivers/mfd/tqmx86.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 7ae906ff8e35..31d0efb5aacf 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -49,9 +49,8 @@ #define TQMX86_REG_IO_EXT_INT_MASK 0x3 #define TQMX86_REG_IO_EXT_INT_GPIO_SHIFT 4 -#define TQMX86_REG_I2C_DETECT 0x47 +#define TQMX86_REG_I2C_DETECT 0x1a7 #define TQMX86_REG_I2C_DETECT_SOFT 0xa5 -#define TQMX86_REG_I2C_INT_EN 0x49 static uint gpio_irq; module_param(gpio_irq, uint, 0); @@ -213,7 +212,12 @@ static int tqmx86_probe(struct platform_device *pdev) "Found %s - Board ID %d, PCB Revision %d, PLD Revision %d\n", board_name, board_id, rev >> 4, rev & 0xf); - i2c_det = ioread8(io_base + TQMX86_REG_I2C_DETECT); + /* + * The I2C_DETECT register is in the range assigned to the I2C driver + * later, so we don't extend TQMX86_IOSIZE. Use inb() for this one-off + * access instead of ioport_map + unmap. + */ + i2c_det = inb(TQMX86_REG_I2C_DETECT); if (gpio_irq_cfg) { io_ext_int_val = -- GitLab From 051c69ff4f607aa114c7bbdd7c41ed881367aeee Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:45 +0100 Subject: [PATCH 4026/5631] mfd: tqmx86: Specify IO port register range more precisely Registers 0x160..0x17f are unassigned. Use 0x180 as base register and update offets accordingly. Also change the size of the range to include 0x19f. While 0x19f is currently reserved for future extensions, so are several of the previous registers up to 0x19e, and it is weird to leave out just the last one. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/db4677ac318b1283c8956f637f409995a30a31c3.1676892223.git.matthias.schiffer@ew.tq-group.com --- drivers/mfd/tqmx86.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 31d0efb5aacf..958334f14eb0 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -16,8 +16,8 @@ #include #include -#define TQMX86_IOBASE 0x160 -#define TQMX86_IOSIZE 0x3f +#define TQMX86_IOBASE 0x180 +#define TQMX86_IOSIZE 0x20 #define TQMX86_IOBASE_I2C 0x1a0 #define TQMX86_IOSIZE_I2C 0xa #define TQMX86_IOBASE_WATCHDOG 0x18b @@ -25,7 +25,7 @@ #define TQMX86_IOBASE_GPIO 0x18d #define TQMX86_IOSIZE_GPIO 0x4 -#define TQMX86_REG_BOARD_ID 0x20 +#define TQMX86_REG_BOARD_ID 0x00 #define TQMX86_REG_BOARD_ID_E38M 1 #define TQMX86_REG_BOARD_ID_50UC 2 #define TQMX86_REG_BOARD_ID_E38C 3 @@ -40,8 +40,8 @@ #define TQMX86_REG_BOARD_ID_E40S 13 #define TQMX86_REG_BOARD_ID_E40C1 14 #define TQMX86_REG_BOARD_ID_E40C2 15 -#define TQMX86_REG_BOARD_REV 0x21 -#define TQMX86_REG_IO_EXT_INT 0x26 +#define TQMX86_REG_BOARD_REV 0x01 +#define TQMX86_REG_IO_EXT_INT 0x06 #define TQMX86_REG_IO_EXT_INT_NONE 0 #define TQMX86_REG_IO_EXT_INT_7 1 #define TQMX86_REG_IO_EXT_INT_9 2 -- GitLab From f376c479668557bcc2fd9e9fbc0f53e7819a11cd Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 20 Feb 2023 12:25:46 +0100 Subject: [PATCH 4027/5631] mfd: tqmx86: Correct board names for TQMxE39x It seems that this driver was developed based on preliminary documentation. Report the correct names for all TQMxE39x variants, as they are used by the released hardware revisions: - Fix names for TQMxE39C1/C2 board IDs - Distinguish TQMxE39M and TQMxE39S, which use the same board ID The TQMxE39M/S are distinguished using the SAUC (Sanctioned Alternate Uses Configuration) register of the GPIO controller. This also prepares for the correct handling of the differences between the GPIO controllers of our COMe and SMARC modules. Fixes: 2f17dd34ffed ("mfd: tqmx86: IO controller with I2C, Wachdog and GPIO") Signed-off-by: Matthias Schiffer Reviewed-by: Andrew Lunn Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/aca9a7cb42a85181bcb456c437554d2728e708ec.1676892223.git.matthias.schiffer@ew.tq-group.com --- drivers/mfd/tqmx86.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c index 958334f14eb0..fac02875fe7d 100644 --- a/drivers/mfd/tqmx86.c +++ b/drivers/mfd/tqmx86.c @@ -30,9 +30,9 @@ #define TQMX86_REG_BOARD_ID_50UC 2 #define TQMX86_REG_BOARD_ID_E38C 3 #define TQMX86_REG_BOARD_ID_60EB 4 -#define TQMX86_REG_BOARD_ID_E39M 5 -#define TQMX86_REG_BOARD_ID_E39C 6 -#define TQMX86_REG_BOARD_ID_E39x 7 +#define TQMX86_REG_BOARD_ID_E39MS 5 +#define TQMX86_REG_BOARD_ID_E39C1 6 +#define TQMX86_REG_BOARD_ID_E39C2 7 #define TQMX86_REG_BOARD_ID_70EB 8 #define TQMX86_REG_BOARD_ID_80UC 9 #define TQMX86_REG_BOARD_ID_110EB 11 @@ -48,6 +48,7 @@ #define TQMX86_REG_IO_EXT_INT_12 3 #define TQMX86_REG_IO_EXT_INT_MASK 0x3 #define TQMX86_REG_IO_EXT_INT_GPIO_SHIFT 4 +#define TQMX86_REG_SAUC 0x17 #define TQMX86_REG_I2C_DETECT 0x1a7 #define TQMX86_REG_I2C_DETECT_SOFT 0xa5 @@ -110,7 +111,7 @@ static const struct mfd_cell tqmx86_devs[] = { }, }; -static const char *tqmx86_board_id_to_name(u8 board_id) +static const char *tqmx86_board_id_to_name(u8 board_id, u8 sauc) { switch (board_id) { case TQMX86_REG_BOARD_ID_E38M: @@ -121,12 +122,12 @@ static const char *tqmx86_board_id_to_name(u8 board_id) return "TQMxE38C"; case TQMX86_REG_BOARD_ID_60EB: return "TQMx60EB"; - case TQMX86_REG_BOARD_ID_E39M: - return "TQMxE39M"; - case TQMX86_REG_BOARD_ID_E39C: - return "TQMxE39C"; - case TQMX86_REG_BOARD_ID_E39x: - return "TQMxE39x"; + case TQMX86_REG_BOARD_ID_E39MS: + return (sauc == 0xff) ? "TQMxE39M" : "TQMxE39S"; + case TQMX86_REG_BOARD_ID_E39C1: + return "TQMxE39C1"; + case TQMX86_REG_BOARD_ID_E39C2: + return "TQMxE39C2"; case TQMX86_REG_BOARD_ID_70EB: return "TQMx70EB"; case TQMX86_REG_BOARD_ID_80UC: @@ -159,9 +160,9 @@ static int tqmx86_board_id_to_clk_rate(struct device *dev, u8 board_id) case TQMX86_REG_BOARD_ID_E40C1: case TQMX86_REG_BOARD_ID_E40C2: return 24000; - case TQMX86_REG_BOARD_ID_E39M: - case TQMX86_REG_BOARD_ID_E39C: - case TQMX86_REG_BOARD_ID_E39x: + case TQMX86_REG_BOARD_ID_E39MS: + case TQMX86_REG_BOARD_ID_E39C1: + case TQMX86_REG_BOARD_ID_E39C2: return 25000; case TQMX86_REG_BOARD_ID_E38M: case TQMX86_REG_BOARD_ID_E38C: @@ -175,7 +176,7 @@ static int tqmx86_board_id_to_clk_rate(struct device *dev, u8 board_id) static int tqmx86_probe(struct platform_device *pdev) { - u8 board_id, rev, i2c_det, io_ext_int_val; + u8 board_id, sauc, rev, i2c_det, io_ext_int_val; struct device *dev = &pdev->dev; u8 gpio_irq_cfg, readback; const char *board_name; @@ -205,7 +206,8 @@ static int tqmx86_probe(struct platform_device *pdev) return -ENOMEM; board_id = ioread8(io_base + TQMX86_REG_BOARD_ID); - board_name = tqmx86_board_id_to_name(board_id); + sauc = ioread8(io_base + TQMX86_REG_SAUC); + board_name = tqmx86_board_id_to_name(board_id, sauc); rev = ioread8(io_base + TQMX86_REG_BOARD_REV); dev_info(dev, -- GitLab From 21a8d573d967214e66abe2a1d69152d59e2a3521 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Thu, 2 Feb 2023 16:41:24 +0530 Subject: [PATCH 4028/5631] dt-bindings: mfd: qcom,tcsr: Add compatible for sm8450 Document the qcom,sm8450-tcsr compatible. Signed-off-by: Mukesh Ojha Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1675336284-548-1-git-send-email-quic_mojha@quicinc.com --- Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml index 203fc890c9a3..5059bc2e676d 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml @@ -26,6 +26,7 @@ properties: - qcom,sdm630-tcsr - qcom,sdm845-tcsr - qcom,sm8150-tcsr + - qcom,sm8450-tcsr - qcom,tcsr-apq8064 - qcom,tcsr-apq8084 - qcom,tcsr-ipq5332 -- GitLab From b8fd17d9505e18001d10ceaa350c118a82b467bb Mon Sep 17 00:00:00 2001 From: Jakob Hauser Date: Tue, 28 Feb 2023 23:32:20 +0100 Subject: [PATCH 4029/5631] mfd: rt5033: Fix comments and style in includes Fix comments and remove some empty lines in rt5033-private.h. Align struct rt5033_charger in rt5033.h. Signed-off-by: Jakob Hauser Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/606950da6f4b36f5a124ff13756c78644fc89804.1677620677.git.jahau@rocketmail.com --- include/linux/mfd/rt5033-private.h | 17 +++++++---------- include/linux/mfd/rt5033.h | 7 +++---- 2 files changed, 10 insertions(+), 14 deletions(-) diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h index 2d1895c3efbf..6bb432f6a96c 100644 --- a/include/linux/mfd/rt5033-private.h +++ b/include/linux/mfd/rt5033-private.h @@ -107,14 +107,13 @@ enum rt5033_reg { #define RT5033_LDO_CTRL_MASK 0x1f /* RT5033 charger property - model, manufacturer */ - #define RT5033_CHARGER_MODEL "RT5033WSC Charger" #define RT5033_MANUFACTURER "Richtek Technology Corporation" /* - * RT5033 charger fast-charge current lmits (as in CHGCTRL1 register), - * AICR mode limits the input current for example, - * the AIRC 100 mode limits the input current to 100 mA. + * While RT5033 charger can limit the fast-charge current (as in CHGCTRL1 + * register), AICR mode limits the input current. For example, the AIRC 100 + * mode limits the input current to 100 mA. */ #define RT5033_AICR_100_MODE 0x20 #define RT5033_AICR_500_MODE 0x40 @@ -139,10 +138,9 @@ enum rt5033_reg { #define RT5033_TE_ENABLE_MASK 0x08 /* - * RT5033 charger opa mode. RT50300 have two opa mode charger mode - * and boost mode for OTG + * RT5033 charger opa mode. RT5033 has two opa modes for OTG: charger mode + * and boost mode. */ - #define RT5033_CHARGER_MODE 0x00 #define RT5033_BOOST_MODE 0x01 @@ -181,18 +179,17 @@ enum rt5033_reg { * RT5033 charger pre-charge threshold volt limits * (as in CHGCTRL5 register), uV */ - #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MIN 2300000U #define RT5033_CHARGER_PRE_THRESHOLD_STEP_NUM 100000U #define RT5033_CHARGER_PRE_THRESHOLD_LIMIT_MAX 3800000U /* - * RT5033 charger enable UUG, If UUG enable MOS auto control by H/W charger + * RT5033 charger UUG. It enables MOS auto control by H/W charger * circuit. */ #define RT5033_CHARGER_UUG_ENABLE 0x02 -/* RT5033 charger High impedance mode */ +/* RT5033 charger high impedance mode */ #define RT5033_CHARGER_HZ_DISABLE 0x00 #define RT5033_CHARGER_HZ_ENABLE 0x01 diff --git a/include/linux/mfd/rt5033.h b/include/linux/mfd/rt5033.h index 3c23b6220c04..8f306ac15a27 100644 --- a/include/linux/mfd/rt5033.h +++ b/include/linux/mfd/rt5033.h @@ -49,10 +49,9 @@ struct rt5033_charger_data { }; struct rt5033_charger { - struct device *dev; - struct rt5033_dev *rt5033; - struct power_supply psy; - + struct device *dev; + struct rt5033_dev *rt5033; + struct power_supply psy; struct rt5033_charger_data *chg; }; -- GitLab From c5a4b6fd31e8cbc749f7ac9ff6c3a6118f3e5011 Mon Sep 17 00:00:00 2001 From: Ye Xiang Date: Sat, 25 Feb 2023 22:01:15 +0800 Subject: [PATCH 4030/5631] gpio: Add support for Intel LJCA USB GPIO driver This patch implements the GPIO function of Intel USB-I2C/GPIO/SPI adapter device named "La Jolla Cove Adapter" (LJCA). It communicate with LJCA GPIO module with specific protocol through interfaces exported by LJCA USB driver. Signed-off-by: Ye Xiang Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230225140118.2037220-3-xiang.ye@intel.com --- drivers/gpio/Kconfig | 12 ++ drivers/gpio/Makefile | 1 + drivers/gpio/gpio-ljca.c | 454 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 467 insertions(+) create mode 100644 drivers/gpio/gpio-ljca.c diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 13be729710f2..8be697f9f621 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1253,6 +1253,18 @@ config GPIO_KEMPLD This driver can also be built as a module. If so, the module will be called gpio-kempld. +config GPIO_LJCA + tristate "INTEL La Jolla Cove Adapter GPIO support" + depends on MFD_LJCA + select GPIOLIB_IRQCHIP + default MFD_LJCA + help + Select this option to enable GPIO driver for the INTEL + La Jolla Cove Adapter (LJCA) board. + + This driver can also be built as a module. If so, the module + will be called gpio-ljca. + config GPIO_LP3943 tristate "TI/National Semiconductor LP3943 GPIO expander" depends on MFD_LP3943 diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile index c048ba003367..eb59524d18c0 100644 --- a/drivers/gpio/Makefile +++ b/drivers/gpio/Makefile @@ -77,6 +77,7 @@ obj-$(CONFIG_GPIO_IXP4XX) += gpio-ixp4xx.o obj-$(CONFIG_GPIO_JANZ_TTL) += gpio-janz-ttl.o obj-$(CONFIG_GPIO_KEMPLD) += gpio-kempld.o obj-$(CONFIG_GPIO_LATCH) += gpio-latch.o +obj-$(CONFIG_GPIO_LJCA) += gpio-ljca.o obj-$(CONFIG_GPIO_LOGICVC) += gpio-logicvc.o obj-$(CONFIG_GPIO_LOONGSON1) += gpio-loongson1.o obj-$(CONFIG_GPIO_LOONGSON) += gpio-loongson.o diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c new file mode 100644 index 000000000000..87863f0230f5 --- /dev/null +++ b/drivers/gpio/gpio-ljca.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Intel La Jolla Cove Adapter USB-GPIO driver + * + * Copyright (c) 2023, Intel Corporation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* GPIO commands */ +#define LJCA_GPIO_CONFIG 1 +#define LJCA_GPIO_READ 2 +#define LJCA_GPIO_WRITE 3 +#define LJCA_GPIO_INT_EVENT 4 +#define LJCA_GPIO_INT_MASK 5 +#define LJCA_GPIO_INT_UNMASK 6 + +#define LJCA_GPIO_CONF_DISABLE BIT(0) +#define LJCA_GPIO_CONF_INPUT BIT(1) +#define LJCA_GPIO_CONF_OUTPUT BIT(2) +#define LJCA_GPIO_CONF_PULLUP BIT(3) +#define LJCA_GPIO_CONF_PULLDOWN BIT(4) +#define LJCA_GPIO_CONF_DEFAULT BIT(5) +#define LJCA_GPIO_CONF_INTERRUPT BIT(6) +#define LJCA_GPIO_INT_TYPE BIT(7) + +#define LJCA_GPIO_CONF_EDGE FIELD_PREP(LJCA_GPIO_INT_TYPE, 1) +#define LJCA_GPIO_CONF_LEVEL FIELD_PREP(LJCA_GPIO_INT_TYPE, 0) + +/* Intentional overlap with PULLUP / PULLDOWN */ +#define LJCA_GPIO_CONF_SET BIT(3) +#define LJCA_GPIO_CONF_CLR BIT(4) + +struct gpio_op { + u8 index; + u8 value; +} __packed; + +struct gpio_packet { + u8 num; + struct gpio_op item[]; +} __packed; + +#define LJCA_GPIO_BUF_SIZE 60 +struct ljca_gpio_dev { + struct platform_device *pdev; + struct gpio_chip gc; + struct ljca_gpio_info *gpio_info; + DECLARE_BITMAP(unmasked_irqs, LJCA_MAX_GPIO_NUM); + DECLARE_BITMAP(enabled_irqs, LJCA_MAX_GPIO_NUM); + DECLARE_BITMAP(reenable_irqs, LJCA_MAX_GPIO_NUM); + u8 *connect_mode; + /* mutex to protect irq bus */ + struct mutex irq_lock; + struct work_struct work; + /* lock to protect package transfer to Hardware */ + struct mutex trans_lock; + + u8 obuf[LJCA_GPIO_BUF_SIZE]; + u8 ibuf[LJCA_GPIO_BUF_SIZE]; +}; + +static int gpio_config(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id, u8 config) +{ + struct gpio_packet *packet = (struct gpio_packet *)ljca_gpio->obuf; + int ret; + + mutex_lock(&ljca_gpio->trans_lock); + packet->item[0].index = gpio_id; + packet->item[0].value = config | ljca_gpio->connect_mode[gpio_id]; + packet->num = 1; + + ret = ljca_transfer(ljca_gpio->gpio_info->ljca, LJCA_GPIO_CONFIG, packet, + struct_size(packet, item, packet->num), NULL, NULL); + mutex_unlock(&ljca_gpio->trans_lock); + return ret; +} + +static int ljca_gpio_read(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id) +{ + struct gpio_packet *packet = (struct gpio_packet *)ljca_gpio->obuf; + struct gpio_packet *ack_packet = (struct gpio_packet *)ljca_gpio->ibuf; + unsigned int ibuf_len = LJCA_GPIO_BUF_SIZE; + int ret; + + mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; + packet->item[0].index = gpio_id; + ret = ljca_transfer(ljca_gpio->gpio_info->ljca, LJCA_GPIO_READ, packet, + struct_size(packet, item, packet->num), ljca_gpio->ibuf, &ibuf_len); + if (ret) + goto out_unlock; + + if (!ibuf_len || ack_packet->num != packet->num) { + dev_err(&ljca_gpio->pdev->dev, "failed gpio_id:%u %u", gpio_id, ack_packet->num); + ret = -EIO; + } + +out_unlock: + mutex_unlock(&ljca_gpio->trans_lock); + if (ret) + return ret; + return ack_packet->item[0].value > 0; +} + +static int ljca_gpio_write(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id, + int value) +{ + struct gpio_packet *packet = (struct gpio_packet *)ljca_gpio->obuf; + int ret; + + mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; + packet->item[0].index = gpio_id; + packet->item[0].value = value & 1; + + ret = ljca_transfer(ljca_gpio->gpio_info->ljca, LJCA_GPIO_WRITE, packet, + struct_size(packet, item, packet->num), NULL, NULL); + mutex_unlock(&ljca_gpio->trans_lock); + return ret; +} + +static int ljca_gpio_get_value(struct gpio_chip *chip, unsigned int offset) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + + return ljca_gpio_read(ljca_gpio, offset); +} + +static void ljca_gpio_set_value(struct gpio_chip *chip, unsigned int offset, + int val) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + int ret; + + ret = ljca_gpio_write(ljca_gpio, offset, val); + if (ret) + dev_err(chip->parent, "offset:%u val:%d set value failed %d\n", offset, val, ret); +} + +static int ljca_gpio_direction_input(struct gpio_chip *chip, + unsigned int offset) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + u8 config = LJCA_GPIO_CONF_INPUT | LJCA_GPIO_CONF_CLR; + + return gpio_config(ljca_gpio, offset, config); +} + +static int ljca_gpio_direction_output(struct gpio_chip *chip, + unsigned int offset, int val) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + u8 config = LJCA_GPIO_CONF_OUTPUT | LJCA_GPIO_CONF_CLR; + int ret; + + ret = gpio_config(ljca_gpio, offset, config); + if (ret) + return ret; + + ljca_gpio_set_value(chip, offset, val); + return 0; +} + +static int ljca_gpio_set_config(struct gpio_chip *chip, unsigned int offset, + unsigned long config) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + + ljca_gpio->connect_mode[offset] = 0; + switch (pinconf_to_config_param(config)) { + case PIN_CONFIG_BIAS_PULL_UP: + ljca_gpio->connect_mode[offset] |= LJCA_GPIO_CONF_PULLUP; + break; + case PIN_CONFIG_BIAS_PULL_DOWN: + ljca_gpio->connect_mode[offset] |= LJCA_GPIO_CONF_PULLDOWN; + break; + case PIN_CONFIG_DRIVE_PUSH_PULL: + case PIN_CONFIG_PERSIST_STATE: + break; + default: + return -ENOTSUPP; + } + + return 0; +} + +static int ljca_gpio_init_valid_mask(struct gpio_chip *chip, unsigned long *valid_mask, + unsigned int ngpios) +{ + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(chip); + + WARN_ON_ONCE(ngpios != ljca_gpio->gpio_info->num); + bitmap_copy(valid_mask, ljca_gpio->gpio_info->valid_pin_map, ngpios); + + return 0; +} + +static void ljca_gpio_irq_init_valid_mask(struct gpio_chip *chip, unsigned long *valid_mask, + unsigned int ngpios) +{ + ljca_gpio_init_valid_mask(chip, valid_mask, ngpios); +} + +static int ljca_enable_irq(struct ljca_gpio_dev *ljca_gpio, int gpio_id, bool enable) +{ + struct gpio_packet *packet = (struct gpio_packet *)ljca_gpio->obuf; + int ret; + + mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; + packet->item[0].index = gpio_id; + packet->item[0].value = 0; + + ret = ljca_transfer(ljca_gpio->gpio_info->ljca, + enable ? LJCA_GPIO_INT_UNMASK : LJCA_GPIO_INT_MASK, packet, + struct_size(packet, item, packet->num), NULL, NULL); + mutex_unlock(&ljca_gpio->trans_lock); + return ret; +} + +static void ljca_gpio_async(struct work_struct *work) +{ + struct ljca_gpio_dev *ljca_gpio = container_of(work, struct ljca_gpio_dev, work); + int gpio_id; + int unmasked; + + for_each_set_bit(gpio_id, ljca_gpio->reenable_irqs, ljca_gpio->gc.ngpio) { + clear_bit(gpio_id, ljca_gpio->reenable_irqs); + unmasked = test_bit(gpio_id, ljca_gpio->unmasked_irqs); + if (unmasked) + ljca_enable_irq(ljca_gpio, gpio_id, true); + } +} + +static void ljca_gpio_event_cb(void *context, u8 cmd, const void *evt_data, int len) +{ + const struct gpio_packet *packet = evt_data; + struct ljca_gpio_dev *ljca_gpio = context; + int i; + int irq; + + if (cmd != LJCA_GPIO_INT_EVENT) + return; + + for (i = 0; i < packet->num; i++) { + irq = irq_find_mapping(ljca_gpio->gc.irq.domain, packet->item[i].index); + if (!irq) { + dev_err(ljca_gpio->gc.parent, "gpio_id %u does not mapped to IRQ yet\n", + packet->item[i].index); + return; + } + + generic_handle_domain_irq(ljca_gpio->gc.irq.domain, irq); + set_bit(packet->item[i].index, ljca_gpio->reenable_irqs); + } + + schedule_work(&ljca_gpio->work); +} + +static void ljca_irq_unmask(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(gc); + int gpio_id = irqd_to_hwirq(irqd); + + gpiochip_enable_irq(gc, gpio_id); + set_bit(gpio_id, ljca_gpio->unmasked_irqs); +} + +static void ljca_irq_mask(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(gc); + int gpio_id = irqd_to_hwirq(irqd); + + clear_bit(gpio_id, ljca_gpio->unmasked_irqs); + gpiochip_disable_irq(gc, gpio_id); +} + +static int ljca_irq_set_type(struct irq_data *irqd, unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(gc); + int gpio_id = irqd_to_hwirq(irqd); + + ljca_gpio->connect_mode[gpio_id] = LJCA_GPIO_CONF_INTERRUPT; + switch (type) { + case IRQ_TYPE_LEVEL_HIGH: + ljca_gpio->connect_mode[gpio_id] |= (LJCA_GPIO_CONF_LEVEL | LJCA_GPIO_CONF_PULLUP); + break; + case IRQ_TYPE_LEVEL_LOW: + ljca_gpio->connect_mode[gpio_id] |= (LJCA_GPIO_CONF_LEVEL | LJCA_GPIO_CONF_PULLDOWN); + break; + case IRQ_TYPE_EDGE_BOTH: + break; + case IRQ_TYPE_EDGE_RISING: + ljca_gpio->connect_mode[gpio_id] |= (LJCA_GPIO_CONF_EDGE | LJCA_GPIO_CONF_PULLUP); + break; + case IRQ_TYPE_EDGE_FALLING: + ljca_gpio->connect_mode[gpio_id] |= (LJCA_GPIO_CONF_EDGE | LJCA_GPIO_CONF_PULLDOWN); + break; + default: + return -EINVAL; + } + + return 0; +} + +static void ljca_irq_bus_lock(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(gc); + + mutex_lock(&ljca_gpio->irq_lock); +} + +static void ljca_irq_bus_unlock(struct irq_data *irqd) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(irqd); + struct ljca_gpio_dev *ljca_gpio = gpiochip_get_data(gc); + int gpio_id = irqd_to_hwirq(irqd); + int enabled; + int unmasked; + + enabled = test_bit(gpio_id, ljca_gpio->enabled_irqs); + unmasked = test_bit(gpio_id, ljca_gpio->unmasked_irqs); + + if (enabled != unmasked) { + if (unmasked) { + gpio_config(ljca_gpio, gpio_id, 0); + ljca_enable_irq(ljca_gpio, gpio_id, true); + set_bit(gpio_id, ljca_gpio->enabled_irqs); + } else { + ljca_enable_irq(ljca_gpio, gpio_id, false); + clear_bit(gpio_id, ljca_gpio->enabled_irqs); + } + } + + mutex_unlock(&ljca_gpio->irq_lock); +} + +static const struct irq_chip ljca_gpio_irqchip = { + .name = "ljca-irq", + .irq_mask = ljca_irq_mask, + .irq_unmask = ljca_irq_unmask, + .irq_set_type = ljca_irq_set_type, + .irq_bus_lock = ljca_irq_bus_lock, + .irq_bus_sync_unlock = ljca_irq_bus_unlock, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + +static int ljca_gpio_probe(struct platform_device *pdev) +{ + struct ljca_gpio_dev *ljca_gpio; + struct gpio_irq_chip *girq; + int ret; + + ljca_gpio = devm_kzalloc(&pdev->dev, sizeof(*ljca_gpio), GFP_KERNEL); + if (!ljca_gpio) + return -ENOMEM; + + ljca_gpio->gpio_info = dev_get_platdata(&pdev->dev); + ljca_gpio->connect_mode = devm_kcalloc(&pdev->dev, ljca_gpio->gpio_info->num, + sizeof(*ljca_gpio->connect_mode), GFP_KERNEL); + if (!ljca_gpio->connect_mode) + return -ENOMEM; + + mutex_init(&ljca_gpio->irq_lock); + mutex_init(&ljca_gpio->trans_lock); + ljca_gpio->pdev = pdev; + ljca_gpio->gc.direction_input = ljca_gpio_direction_input; + ljca_gpio->gc.direction_output = ljca_gpio_direction_output; + ljca_gpio->gc.get = ljca_gpio_get_value; + ljca_gpio->gc.set = ljca_gpio_set_value; + ljca_gpio->gc.set_config = ljca_gpio_set_config; + ljca_gpio->gc.init_valid_mask = ljca_gpio_init_valid_mask; + ljca_gpio->gc.can_sleep = true; + ljca_gpio->gc.parent = &pdev->dev; + + ljca_gpio->gc.base = -1; + ljca_gpio->gc.ngpio = ljca_gpio->gpio_info->num; + ljca_gpio->gc.label = ACPI_COMPANION(&pdev->dev) ? + acpi_dev_name(ACPI_COMPANION(&pdev->dev)) : + dev_name(&pdev->dev); + ljca_gpio->gc.owner = THIS_MODULE; + + platform_set_drvdata(pdev, ljca_gpio); + ljca_register_event_cb(ljca_gpio->gpio_info->ljca, ljca_gpio_event_cb, ljca_gpio); + + girq = &ljca_gpio->gc.irq; + gpio_irq_chip_set_chip(girq, &ljca_gpio_irqchip); + girq->parent_handler = NULL; + girq->num_parents = 0; + girq->parents = NULL; + girq->default_type = IRQ_TYPE_NONE; + girq->handler = handle_simple_irq; + girq->init_valid_mask = ljca_gpio_irq_init_valid_mask; + + INIT_WORK(&ljca_gpio->work, ljca_gpio_async); + ret = gpiochip_add_data(&ljca_gpio->gc, ljca_gpio); + if (ret) { + ljca_unregister_event_cb(ljca_gpio->gpio_info->ljca); + mutex_destroy(&ljca_gpio->irq_lock); + mutex_destroy(&ljca_gpio->trans_lock); + } + + return ret; +} + +static int ljca_gpio_remove(struct platform_device *pdev) +{ + struct ljca_gpio_dev *ljca_gpio = platform_get_drvdata(pdev); + + gpiochip_remove(&ljca_gpio->gc); + ljca_unregister_event_cb(ljca_gpio->gpio_info->ljca); + mutex_destroy(&ljca_gpio->irq_lock); + mutex_destroy(&ljca_gpio->trans_lock); + return 0; +} + +#define LJCA_GPIO_DRV_NAME "ljca-gpio" +static const struct platform_device_id ljca_gpio_id[] = { + { LJCA_GPIO_DRV_NAME, 0 }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(platform, ljca_gpio_id); + +static struct platform_driver ljca_gpio_driver = { + .driver.name = LJCA_GPIO_DRV_NAME, + .probe = ljca_gpio_probe, + .remove = ljca_gpio_remove, +}; +module_platform_driver(ljca_gpio_driver); + +MODULE_AUTHOR("Ye Xiang "); +MODULE_AUTHOR("Wang Zhifeng "); +MODULE_AUTHOR("Zhang Lixu "); +MODULE_DESCRIPTION("Intel La Jolla Cove Adapter USB-GPIO driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(LJCA); -- GitLab From 2c6a1bde024ccb0e64ea4bc112d15438abc08949 Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 8 Mar 2023 17:49:48 +0530 Subject: [PATCH 4031/5631] dt-bindings: mfd: qcom,tcsr: Add compatible for sdx65 Add the qcom,sdx65-tcsr compatible. Signed-off-by: Rohit Agarwal Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1678277993-18836-2-git-send-email-quic_rohiagar@quicinc.com --- Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml index 5059bc2e676d..51fa614c3f51 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml @@ -25,6 +25,7 @@ properties: - qcom,sc8280xp-tcsr - qcom,sdm630-tcsr - qcom,sdm845-tcsr + - qcom,sdx65-tcsr - qcom,sm8150-tcsr - qcom,sm8450-tcsr - qcom,tcsr-apq8064 -- GitLab From ba2b13df8ab005cee919d2ca31829a3c639fded2 Mon Sep 17 00:00:00 2001 From: Marcello Sylvester Bauer Date: Tue, 7 Mar 2023 13:12:44 +0100 Subject: [PATCH 4032/5631] dt-bindings: mfd: Add MAX5970 and MAX5978 The MAX597x is a hot swap controller with configurable fault protection. It also has 10bit ADC for current & voltage measurements. ... Changes in V12: - Update title Signed-off-by: Marcello Sylvester Bauer Co-developed-by: Patrick Rudolph Signed-off-by: Patrick Rudolph Co-developed-by: Naresh Solanki Signed-off-by: Naresh Solanki Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230307121246.127425-1-Naresh.Solanki@9elements.com --- .../bindings/mfd/maxim,max5970.yaml | 151 ++++++++++++++++++ 1 file changed, 151 insertions(+) create mode 100644 Documentation/devicetree/bindings/mfd/maxim,max5970.yaml diff --git a/Documentation/devicetree/bindings/mfd/maxim,max5970.yaml b/Documentation/devicetree/bindings/mfd/maxim,max5970.yaml new file mode 100644 index 000000000000..da67742c5aa9 --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/maxim,max5970.yaml @@ -0,0 +1,151 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/maxim,max5970.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Regulator for MAX5970 Smart Switch from Maxim Integrated + +maintainers: + - Patrick Rudolph + +description: | + The smart switch provides no output regulation, but independent fault protection + and voltage and current sensing. + Programming is done through I2C bus. + + Datasheets: + https://datasheets.maximintegrated.com/en/ds/MAX5970.pdf + https://datasheets.maximintegrated.com/en/ds/MAX5978.pdf + +properties: + compatible: + enum: + - maxim,max5970 + - maxim,max5978 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + leds: + type: object + description: + Properties for four LEDS. + + properties: + "#address-cells": + const: 1 + + "#size-cells": + const: 0 + + patternProperties: + "^led@[0-3]$": + $ref: /schemas/leds/common.yaml# + type: object + + additionalProperties: false + + vss1-supply: + description: Supply of the first channel. + + vss2-supply: + description: Supply of the second channel. + + regulators: + type: object + description: + Properties for both hot swap control/switch. + + patternProperties: + "^sw[0-1]$": + $ref: /schemas/regulator/regulator.yaml# + type: object + properties: + shunt-resistor-micro-ohms: + description: | + The value of current sense resistor in microohms. + + required: + - shunt-resistor-micro-ohms + + unevaluatedProperties: false + + additionalProperties: false + +required: + - compatible + - reg + - regulators + - vss1-supply + +allOf: + - if: + properties: + compatible: + enum: + - maxim,max5970 + then: + required: + - vss2-supply + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + regulator@3a { + compatible = "maxim,max5978"; + reg = <0x3a>; + vss1-supply = <&p3v3>; + + regulators { + sw0_ref_0: sw0 { + shunt-resistor-micro-ohms = <12000>; + }; + }; + + leds { + #address-cells = <1>; + #size-cells = <0>; + led@0 { + reg = <0>; + label = "led0"; + default-state = "on"; + }; + led@1 { + reg = <1>; + label = "led1"; + default-state = "on"; + }; + }; + }; + }; + + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + regulator@3a { + compatible = "maxim,max5970"; + reg = <0x3a>; + vss1-supply = <&p3v3>; + vss2-supply = <&p5v>; + + regulators { + sw0_ref_1: sw0 { + shunt-resistor-micro-ohms = <12000>; + }; + sw1_ref_1: sw1 { + shunt-resistor-micro-ohms = <10000>; + }; + }; + }; + }; +... -- GitLab From 0742c2a6335281608ac9e9aee67493e9e30f6195 Mon Sep 17 00:00:00 2001 From: Patrick Rudolph Date: Tue, 7 Mar 2023 13:12:45 +0100 Subject: [PATCH 4033/5631] mfd: max597x: Add support for MAX5970 and MAX5978 Implement a regulator driver with IRQ support for fault management. Written against documentation [1] and [2] and tested on real hardware. Every channel has it's own regulator supply nammed 'vss1-supply' and 'vss2-supply'. The regulator supply is used to determine the output voltage, as the smart switch provides no output regulation. The driver requires the 'shunt-resistor-micro-ohms' to be present in the devicetree to properly calculate current related values. You must specify compatible devictree layout: regulator@3a { reg = <0x3a>; vss1-supply = <&p3v3>; compatible = "maxim,max5978"; ... regulators { sw0_ref: SW0 { regulator-compatible = "SW0"; shunt-resistor-micro-ohms = <12000>; ... } } } 1: https://datasheets.maximintegrated.com/en/ds/MAX5970.pdf 2: https://datasheets.maximintegrated.com/en/ds/MAX5978.pdf ... Changes in V12: - Use simple_mfd_i2c driver and remove previous implementation. - Remove newline - Use _MFD_MAX597X_H in header file - Successfull build need following patch from regulator: https://lore.kernel.org/r/20230216075302.68935-1-Naresh.Solanki@9elements.com https://lore.kernel.org/r/20230210163225.1208035-1-Naresh.Solanki@9elements.com Signed-off-by: Patrick Rudolph Signed-off-by: Marcello Sylvester Bauer Signed-off-by: Naresh Solanki Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230307121246.127425-2-Naresh.Solanki@9elements.com --- drivers/mfd/Kconfig | 10 ++++ drivers/mfd/simple-mfd-i2c.c | 13 +++++ include/linux/mfd/max597x.h | 96 ++++++++++++++++++++++++++++++++++++ 3 files changed, 119 insertions(+) create mode 100644 include/linux/mfd/max597x.h diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index fcc141e067b9..d381d0e63455 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -266,6 +266,16 @@ config MFD_MADERA_SPI Support for the Cirrus Logic Madera platform audio SoC core functionality controlled via SPI. +config MFD_MAX597X + tristate "Maxim 597x power switch and monitor" + depends on (I2C && OF) + select MFD_SIMPLE_MFD_I2C + help + This driver controls a Maxim 5970/5978 switch via I2C bus. + The MAX5970/5978 is a smart switch with no output regulation, but + fault protection and voltage and current monitoring capabilities. + Also it supports upto 4 indication leds. + config MFD_CS47L15 bool "Cirrus Logic CS47L15" select PINCTRL_CS47L15 diff --git a/drivers/mfd/simple-mfd-i2c.c b/drivers/mfd/simple-mfd-i2c.c index e31f13fd6a79..20782b4dd172 100644 --- a/drivers/mfd/simple-mfd-i2c.c +++ b/drivers/mfd/simple-mfd-i2c.c @@ -72,9 +72,22 @@ static const struct simple_mfd_data silergy_sy7636a = { .mfd_cell_size = ARRAY_SIZE(sy7636a_cells), }; +static const struct mfd_cell max597x_cells[] = { + { .name = "max597x-regulator", }, + { .name = "max597x-iio", }, + { .name = "max597x-led", }, +}; + +static const struct simple_mfd_data maxim_max597x = { + .mfd_cell = max597x_cells, + .mfd_cell_size = ARRAY_SIZE(max597x_cells), +}; + static const struct of_device_id simple_mfd_i2c_of_match[] = { { .compatible = "kontron,sl28cpld" }, { .compatible = "silergy,sy7636a", .data = &silergy_sy7636a}, + { .compatible = "maxim,max5970", .data = &maxim_max597x}, + { .compatible = "maxim,max5978", .data = &maxim_max597x}, {} }; MODULE_DEVICE_TABLE(of, simple_mfd_i2c_of_match); diff --git a/include/linux/mfd/max597x.h b/include/linux/mfd/max597x.h new file mode 100644 index 000000000000..a850b2e02e6a --- /dev/null +++ b/include/linux/mfd/max597x.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Device driver for regulators in MAX5970 and MAX5978 IC + * + * Copyright (c) 2022 9elements GmbH + * + * Author: Patrick Rudolph + */ + +#ifndef _MFD_MAX597X_H +#define _MFD_MAX597X_H + +#include + +#define MAX5970_NUM_SWITCHES 2 +#define MAX5978_NUM_SWITCHES 1 +#define MAX597X_NUM_LEDS 4 + +struct max597x_data { + int num_switches; + u32 irng[MAX5970_NUM_SWITCHES]; + u32 mon_rng[MAX5970_NUM_SWITCHES]; + u32 shunt_micro_ohms[MAX5970_NUM_SWITCHES]; +}; + +enum max597x_chip_type { + MAX597x_TYPE_MAX5978 = 1, + MAX597x_TYPE_MAX5970, +}; + +#define MAX5970_REG_CURRENT_L(ch) (0x01 + (ch) * 4) +#define MAX5970_REG_CURRENT_H(ch) (0x00 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_L(ch) (0x03 + (ch) * 4) +#define MAX5970_REG_VOLTAGE_H(ch) (0x02 + (ch) * 4) +#define MAX5970_REG_MON_RANGE 0x18 +#define MAX5970_MON_MASK 0x3 +#define MAX5970_MON(reg, ch) (((reg) >> ((ch) * 2)) & MAX5970_MON_MASK) +#define MAX5970_MON_MAX_RANGE_UV 16000000 + +#define MAX5970_REG_CH_UV_WARN_H(ch) (0x1A + (ch) * 10) +#define MAX5970_REG_CH_UV_WARN_L(ch) (0x1B + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_H(ch) (0x1C + (ch) * 10) +#define MAX5970_REG_CH_UV_CRIT_L(ch) (0x1D + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_H(ch) (0x1E + (ch) * 10) +#define MAX5970_REG_CH_OV_WARN_L(ch) (0x1F + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_H(ch) (0x20 + (ch) * 10) +#define MAX5970_REG_CH_OV_CRIT_L(ch) (0x21 + (ch) * 10) + +#define MAX5970_VAL2REG_H(x) (((x) >> 2) & 0xFF) +#define MAX5970_VAL2REG_L(x) ((x) & 0x3) + +#define MAX5970_REG_DAC_FAST(ch) (0x2E + (ch)) + +#define MAX5970_FAST2SLOW_RATIO 200 + +#define MAX5970_REG_STATUS0 0x31 +#define MAX5970_CB_IFAULTF(ch) (1 << (ch)) +#define MAX5970_CB_IFAULTS(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_STATUS1 0x32 +#define STATUS1_PROT_MASK 0x3 +#define STATUS1_PROT(reg) \ + (((reg) >> 6) & STATUS1_PROT_MASK) +#define STATUS1_PROT_SHUTDOWN 0 +#define STATUS1_PROT_CLEAR_PG 1 +#define STATUS1_PROT_ALERT_ONLY 2 + +#define MAX5970_REG_STATUS2 0x33 +#define MAX5970_IRNG_MASK 0x3 +#define MAX5970_IRNG(reg, ch) \ + (((reg) >> ((ch) * 2)) & MAX5970_IRNG_MASK) + +#define MAX5970_REG_STATUS3 0x34 +#define MAX5970_STATUS3_ALERT BIT(4) +#define MAX5970_STATUS3_PG(ch) BIT(ch) + +#define MAX5970_REG_FAULT0 0x35 +#define UV_STATUS_WARN(ch) (1 << (ch)) +#define UV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT1 0x36 +#define OV_STATUS_WARN(ch) (1 << (ch)) +#define OV_STATUS_CRIT(ch) (1 << ((ch) + 4)) + +#define MAX5970_REG_FAULT2 0x37 +#define OC_STATUS_WARN(ch) (1 << (ch)) + +#define MAX5970_REG_CHXEN 0x3b +#define CHXEN(ch) (3 << ((ch) * 2)) + +#define MAX5970_REG_LED_FLASH 0x43 + +#define MAX_REGISTERS 0x49 +#define ADC_MASK 0x3FF + +#endif /* _MFD_MAX597X_H */ -- GitLab From e8e9837dde98b18b694f79f6268afff7a610bf30 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 6 Mar 2023 08:26:17 +0100 Subject: [PATCH 4034/5631] dt-bindings: mfd: qcom,tcsr: Document SDX55 TCSR Add compatible for SDX55 TCSR block. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230306072618.10770-1-krzysztof.kozlowski@linaro.org --- Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml index 51fa614c3f51..fe790af7b4fb 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,tcsr.yaml @@ -25,6 +25,7 @@ properties: - qcom,sc8280xp-tcsr - qcom,sdm630-tcsr - qcom,sdm845-tcsr + - qcom,sdx55-tcsr - qcom,sdx65-tcsr - qcom,sm8150-tcsr - qcom,sm8450-tcsr -- GitLab From a0b9becad8a7d62a81530035a69f744c0e389737 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 8 Mar 2023 10:12:57 +0100 Subject: [PATCH 4035/5631] mfd: core: Remove .enable() and .disable() callbacks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With commit dd77f5fa97d3 ("mfd: Remove toshiba tmio drivers") the last mfd driver that implements these callbacks is gone and since commit 652719b1003a ("w1: remove ds1wm driver") the last user is gone. The corresponding functions mfd_cell_enable() and mfd_cell_disable() are also unused (since commit 0ca222c81977 ("leds: Remove asic3 driver")). Signed-off-by: Uwe Kleine-König Acked-by: Arnd Bergmann Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308091257.2404932-1-u.kleine-koenig@pengutronix.de --- drivers/mfd/mfd-core.c | 26 -------------------------- include/linux/mfd/core.h | 12 ------------ 2 files changed, 38 deletions(-) diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 16d1861e9682..695d50b3bac6 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -33,32 +33,6 @@ static struct device_type mfd_dev_type = { .name = "mfd_device", }; -int mfd_cell_enable(struct platform_device *pdev) -{ - const struct mfd_cell *cell = mfd_get_cell(pdev); - - if (!cell->enable) { - dev_dbg(&pdev->dev, "No .enable() call-back registered\n"); - return 0; - } - - return cell->enable(pdev); -} -EXPORT_SYMBOL(mfd_cell_enable); - -int mfd_cell_disable(struct platform_device *pdev) -{ - const struct mfd_cell *cell = mfd_get_cell(pdev); - - if (!cell->disable) { - dev_dbg(&pdev->dev, "No .disable() call-back registered\n"); - return 0; - } - - return cell->disable(pdev); -} -EXPORT_SYMBOL(mfd_cell_disable); - #if IS_ENABLED(CONFIG_ACPI) struct match_ids_walk_data { struct acpi_device_id *ids; diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h index fc4a0e9fb3bb..47e7a3a61ce6 100644 --- a/include/linux/mfd/core.h +++ b/include/linux/mfd/core.h @@ -68,9 +68,6 @@ struct mfd_cell { int id; int level; - int (*enable)(struct platform_device *dev); - int (*disable)(struct platform_device *dev); - int (*suspend)(struct platform_device *dev); int (*resume)(struct platform_device *dev); @@ -123,15 +120,6 @@ struct mfd_cell { const char * const *parent_supplies; }; -/* - * Convenience functions for clients using shared cells. Refcounting - * happens automatically, with the cell's enable/disable callbacks - * being called only when a device is first being enabled or no other - * clients are making use of it. - */ -extern int mfd_cell_enable(struct platform_device *pdev); -extern int mfd_cell_disable(struct platform_device *pdev); - /* * Given a platform device that's been created by mfd_add_devices(), fetch * the mfd_cell that created it. -- GitLab From 6e264e72299c1aff75b9cf45c4cbebaea2cb5fd6 Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Wed, 8 Mar 2023 10:55:48 -0600 Subject: [PATCH 4036/5631] dt-bindings: mfd: Add TI-Nspire misc registers The TI Nspire devices contain a set of registers with a seemingly miscellaneous set of functionality. This area is known simply as the "misc" region. Signed-off-by: Andrew Davis Reviewed-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308165557.2242-2-afd@ti.com --- .../bindings/mfd/ti,nspire-misc.yaml | 51 +++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 Documentation/devicetree/bindings/mfd/ti,nspire-misc.yaml diff --git a/Documentation/devicetree/bindings/mfd/ti,nspire-misc.yaml b/Documentation/devicetree/bindings/mfd/ti,nspire-misc.yaml new file mode 100644 index 000000000000..28cd5164d46f --- /dev/null +++ b/Documentation/devicetree/bindings/mfd/ti,nspire-misc.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +# Copyright (C) 2022-2023 Texas Instruments Incorporated - https://www.ti.com/ +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/mfd/ti,nspire-misc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: TI Nspire MISC hardware block + +maintainers: + - Andrew Davis + +description: + System controller node represents a register region containing a set + of miscellaneous registers. The registers are not cohesive enough to + represent as any specific type of device. Currently there is a reset + controller. + +properties: + compatible: + items: + - enum: + - ti,nspire-misc + - const: syscon + - const: simple-mfd + + reg: + maxItems: 1 + + reboot: + $ref: /schemas/power/reset/syscon-reboot.yaml# + +required: + - compatible + - reg + - reboot + +additionalProperties: false + +examples: + - | + misc: misc@900a0000 { + compatible = "ti,nspire-misc", "syscon", "simple-mfd"; + reg = <0x900a0000 0x1000>; + + reboot { + compatible = "syscon-reboot"; + offset = <0x08>; + value = <0x02>; + }; + }; -- GitLab From 7d61f6313e90cdbe592eba5e0ae6d1c367b03548 Mon Sep 17 00:00:00 2001 From: Christoph Niedermaier Date: Thu, 9 Mar 2023 10:22:52 +0100 Subject: [PATCH 4037/5631] mfd: da9062: Use MFD_CELL_OF macro Use MFD_CELL_OF macro helper instead of plain struct properties, which makes the code a bit shorter and to have commonly defined MFD cell attributes. Signed-off-by: Christoph Niedermaier Acked-by: Adam Ward Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230309092254.56279-1-cniedermaier@dh-electronics.com --- drivers/mfd/da9062-core.c | 92 ++++++++++----------------------------- 1 file changed, 24 insertions(+), 68 deletions(-) diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c index 40cde51e5719..9418c58c2b06 100644 --- a/drivers/mfd/da9062-core.c +++ b/drivers/mfd/da9062-core.c @@ -182,34 +182,16 @@ static const struct resource da9061_onkey_resources[] = { }; static const struct mfd_cell da9061_devs[] = { - { - .name = "da9061-core", - .num_resources = ARRAY_SIZE(da9061_core_resources), - .resources = da9061_core_resources, - }, - { - .name = "da9062-regulators", - .num_resources = ARRAY_SIZE(da9061_regulators_resources), - .resources = da9061_regulators_resources, - }, - { - .name = "da9061-watchdog", - .num_resources = ARRAY_SIZE(da9061_wdt_resources), - .resources = da9061_wdt_resources, - .of_compatible = "dlg,da9061-watchdog", - }, - { - .name = "da9061-thermal", - .num_resources = ARRAY_SIZE(da9061_thermal_resources), - .resources = da9061_thermal_resources, - .of_compatible = "dlg,da9061-thermal", - }, - { - .name = "da9061-onkey", - .num_resources = ARRAY_SIZE(da9061_onkey_resources), - .resources = da9061_onkey_resources, - .of_compatible = "dlg,da9061-onkey", - }, + MFD_CELL_OF("da9061-core", da9061_core_resources, NULL, 0, 0, + NULL), + MFD_CELL_OF("da9062-regulators", da9061_regulators_resources, NULL, 0, 0, + NULL), + MFD_CELL_OF("da9061-watchdog", da9061_wdt_resources, NULL, 0, 0, + "dlg,da9061-watchdog"), + MFD_CELL_OF("da9061-thermal", da9061_thermal_resources, NULL, 0, 0, + "dlg,da9061-thermal"), + MFD_CELL_OF("da9061-onkey", da9061_onkey_resources, NULL, 0, 0, + "dlg,da9061-onkey"), }; static const struct resource da9062_core_resources[] = { @@ -246,46 +228,20 @@ static const struct resource da9062_gpio_resources[] = { }; static const struct mfd_cell da9062_devs[] = { - { - .name = "da9062-core", - .num_resources = ARRAY_SIZE(da9062_core_resources), - .resources = da9062_core_resources, - }, - { - .name = "da9062-regulators", - .num_resources = ARRAY_SIZE(da9062_regulators_resources), - .resources = da9062_regulators_resources, - }, - { - .name = "da9062-watchdog", - .num_resources = ARRAY_SIZE(da9062_wdt_resources), - .resources = da9062_wdt_resources, - .of_compatible = "dlg,da9062-watchdog", - }, - { - .name = "da9062-thermal", - .num_resources = ARRAY_SIZE(da9062_thermal_resources), - .resources = da9062_thermal_resources, - .of_compatible = "dlg,da9062-thermal", - }, - { - .name = "da9062-rtc", - .num_resources = ARRAY_SIZE(da9062_rtc_resources), - .resources = da9062_rtc_resources, - .of_compatible = "dlg,da9062-rtc", - }, - { - .name = "da9062-onkey", - .num_resources = ARRAY_SIZE(da9062_onkey_resources), - .resources = da9062_onkey_resources, - .of_compatible = "dlg,da9062-onkey", - }, - { - .name = "da9062-gpio", - .num_resources = ARRAY_SIZE(da9062_gpio_resources), - .resources = da9062_gpio_resources, - .of_compatible = "dlg,da9062-gpio", - }, + MFD_CELL_OF("da9062-core", da9062_core_resources, NULL, 0, 0, + NULL), + MFD_CELL_OF("da9062-regulators", da9062_regulators_resources, NULL, 0, 0, + NULL), + MFD_CELL_OF("da9062-watchdog", da9062_wdt_resources, NULL, 0, 0, + "dlg,da9062-watchdog"), + MFD_CELL_OF("da9062-thermal", da9062_thermal_resources, NULL, 0, 0, + "dlg,da9062-thermal"), + MFD_CELL_OF("da9062-rtc", da9062_rtc_resources, NULL, 0, 0, + "dlg,da9062-rtc"), + MFD_CELL_OF("da9062-onkey", da9062_onkey_resources, NULL, 0, 0, + "dlg,da9062-onkey"), + MFD_CELL_OF("da9062-gpio", da9062_gpio_resources, NULL, 0, 0, + "dlg,da9062-gpio"), }; static int da9062_clear_fault_log(struct da9062 *chip) -- GitLab From c923d5001ba054df10ed3441d24f8f2c01db7e00 Mon Sep 17 00:00:00 2001 From: Christoph Niedermaier Date: Thu, 9 Mar 2023 10:22:53 +0100 Subject: [PATCH 4038/5631] mfd: da9062: Remove IRQ requirement This patch removes the requirement for an IRQ, because for the core functionality IRQ isn't needed. So this makes the DA9061/62 chip usable for designs which haven't connected the IRQ pin. Signed-off-by: Christoph Niedermaier Acked-by: Adam Ward Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230309092254.56279-2-cniedermaier@dh-electronics.com --- drivers/mfd/da9062-core.c | 84 +++++++++++++++++++++++++-------------- 1 file changed, 55 insertions(+), 29 deletions(-) diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c index 9418c58c2b06..d073d5f106ec 100644 --- a/drivers/mfd/da9062-core.c +++ b/drivers/mfd/da9062-core.c @@ -181,7 +181,7 @@ static const struct resource da9061_onkey_resources[] = { DEFINE_RES_IRQ_NAMED(DA9061_IRQ_ONKEY, "ONKEY"), }; -static const struct mfd_cell da9061_devs[] = { +static const struct mfd_cell da9061_devs_irq[] = { MFD_CELL_OF("da9061-core", da9061_core_resources, NULL, 0, 0, NULL), MFD_CELL_OF("da9062-regulators", da9061_regulators_resources, NULL, 0, 0, @@ -194,6 +194,14 @@ static const struct mfd_cell da9061_devs[] = { "dlg,da9061-onkey"), }; +static const struct mfd_cell da9061_devs_noirq[] = { + MFD_CELL_OF("da9061-core", NULL, NULL, 0, 0, NULL), + MFD_CELL_OF("da9062-regulators", NULL, NULL, 0, 0, NULL), + MFD_CELL_OF("da9061-watchdog", NULL, NULL, 0, 0, "dlg,da9061-watchdog"), + MFD_CELL_OF("da9061-thermal", NULL, NULL, 0, 0, "dlg,da9061-thermal"), + MFD_CELL_OF("da9061-onkey", NULL, NULL, 0, 0, "dlg,da9061-onkey"), +}; + static const struct resource da9062_core_resources[] = { DEFINE_RES_NAMED(DA9062_IRQ_VDD_WARN, 1, "VDD_WARN", IORESOURCE_IRQ), }; @@ -227,7 +235,7 @@ static const struct resource da9062_gpio_resources[] = { DEFINE_RES_NAMED(DA9062_IRQ_GPI4, 1, "GPI4", IORESOURCE_IRQ), }; -static const struct mfd_cell da9062_devs[] = { +static const struct mfd_cell da9062_devs_irq[] = { MFD_CELL_OF("da9062-core", da9062_core_resources, NULL, 0, 0, NULL), MFD_CELL_OF("da9062-regulators", da9062_regulators_resources, NULL, 0, 0, @@ -244,6 +252,16 @@ static const struct mfd_cell da9062_devs[] = { "dlg,da9062-gpio"), }; +static const struct mfd_cell da9062_devs_noirq[] = { + MFD_CELL_OF("da9062-core", NULL, NULL, 0, 0, NULL), + MFD_CELL_OF("da9062-regulators", NULL, NULL, 0, 0, NULL), + MFD_CELL_OF("da9062-watchdog", NULL, NULL, 0, 0, "dlg,da9062-watchdog"), + MFD_CELL_OF("da9062-thermal", NULL, NULL, 0, 0, "dlg,da9062-thermal"), + MFD_CELL_OF("da9062-rtc", NULL, NULL, 0, 0, "dlg,da9062-rtc"), + MFD_CELL_OF("da9062-onkey", NULL, NULL, 0, 0, "dlg,da9062-onkey"), + MFD_CELL_OF("da9062-gpio", NULL, NULL, 0, 0, "dlg,da9062-gpio"), +}; + static int da9062_clear_fault_log(struct da9062 *chip) { int ret; @@ -581,7 +599,7 @@ static int da9062_i2c_probe(struct i2c_client *i2c) { const struct i2c_device_id *id = i2c_client_get_device_id(i2c); struct da9062 *chip; - unsigned int irq_base; + unsigned int irq_base = 0; const struct mfd_cell *cell; const struct regmap_irq_chip *irq_chip; const struct regmap_config *config; @@ -601,22 +619,16 @@ static int da9062_i2c_probe(struct i2c_client *i2c) i2c_set_clientdata(i2c, chip); chip->dev = &i2c->dev; - if (!i2c->irq) { - dev_err(chip->dev, "No IRQ configured\n"); - return -EINVAL; - } - + /* Start with a base configuration without IRQ */ switch (chip->chip_type) { case COMPAT_TYPE_DA9061: - cell = da9061_devs; - cell_num = ARRAY_SIZE(da9061_devs); - irq_chip = &da9061_irq_chip; + cell = da9061_devs_noirq; + cell_num = ARRAY_SIZE(da9061_devs_noirq); config = &da9061_regmap_config; break; case COMPAT_TYPE_DA9062: - cell = da9062_devs; - cell_num = ARRAY_SIZE(da9062_devs); - irq_chip = &da9062_irq_chip; + cell = da9062_devs_noirq; + cell_num = ARRAY_SIZE(da9062_devs_noirq); config = &da9062_regmap_config; break; default: @@ -651,29 +663,43 @@ static int da9062_i2c_probe(struct i2c_client *i2c) if (ret) return ret; - ret = da9062_configure_irq_type(chip, i2c->irq, &trigger_type); - if (ret < 0) { - dev_err(chip->dev, "Failed to configure IRQ type\n"); - return ret; - } + /* If IRQ is available, reconfigure it accordingly */ + if (i2c->irq) { + if (chip->chip_type == COMPAT_TYPE_DA9061) { + cell = da9061_devs_irq; + cell_num = ARRAY_SIZE(da9061_devs_irq); + irq_chip = &da9061_irq_chip; + } else { + cell = da9062_devs_irq; + cell_num = ARRAY_SIZE(da9062_devs_irq); + irq_chip = &da9062_irq_chip; + } - ret = regmap_add_irq_chip(chip->regmap, i2c->irq, - trigger_type | IRQF_SHARED | IRQF_ONESHOT, - -1, irq_chip, &chip->regmap_irq); - if (ret) { - dev_err(chip->dev, "Failed to request IRQ %d: %d\n", - i2c->irq, ret); - return ret; - } + ret = da9062_configure_irq_type(chip, i2c->irq, &trigger_type); + if (ret < 0) { + dev_err(chip->dev, "Failed to configure IRQ type\n"); + return ret; + } - irq_base = regmap_irq_chip_get_base(chip->regmap_irq); + ret = regmap_add_irq_chip(chip->regmap, i2c->irq, + trigger_type | IRQF_SHARED | IRQF_ONESHOT, + -1, irq_chip, &chip->regmap_irq); + if (ret) { + dev_err(chip->dev, "Failed to request IRQ %d: %d\n", + i2c->irq, ret); + return ret; + } + + irq_base = regmap_irq_chip_get_base(chip->regmap_irq); + } ret = mfd_add_devices(chip->dev, PLATFORM_DEVID_NONE, cell, cell_num, NULL, irq_base, NULL); if (ret) { dev_err(chip->dev, "Cannot register child devices\n"); - regmap_del_irq_chip(i2c->irq, chip->regmap_irq); + if (i2c->irq) + regmap_del_irq_chip(i2c->irq, chip->regmap_irq); return ret; } -- GitLab From 75a6ff48fe16e4221be68eb354747bb207d61535 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:59 +0000 Subject: [PATCH 4039/5631] mfd: da9055: Do not cite as modular This driver cannot be built as a module, so don't suggest otherwise in Kconfig help. Suggested-by: Lee Jones Signed-off-by: Nick Alcock Reviewed-by: Vincenzo Palazzo Signed-off-by: Lee Jones --- drivers/mfd/Kconfig | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index d381d0e63455..51d54a1b8673 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -363,9 +363,6 @@ config MFD_DA9055 Additional drivers must be enabled in order to use the functionality of the device. - This driver can be built as a module. If built as a module it will be - called "da9055" - config MFD_DA9062 tristate "Dialog Semiconductor DA9062/61 PMIC Support" select MFD_CORE -- GitLab From 3a101f09b1066991569ce9f4fd1e90a07e97fb3a Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:07 +0000 Subject: [PATCH 4040/5631] mfd: twl6040: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/twl6040.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c index fc97fa5a2d0c..e982119bbefa 100644 --- a/drivers/mfd/twl6040.c +++ b/drivers/mfd/twl6040.c @@ -839,4 +839,3 @@ module_i2c_driver(twl6040_driver); MODULE_DESCRIPTION("TWL6040 MFD"); MODULE_AUTHOR("Misael Lopez Cruz "); MODULE_AUTHOR("Jorge Eduardo Candelaria "); -MODULE_LICENSE("GPL"); -- GitLab From b22f3152494e3b1e2fce4d61ad828420d16e9e5d Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:06 +0000 Subject: [PATCH 4041/5631] mfd: twl4030-audio: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/twl4030-audio.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c index 4536d829b43e..88002f8941e5 100644 --- a/drivers/mfd/twl4030-audio.c +++ b/drivers/mfd/twl4030-audio.c @@ -285,5 +285,4 @@ module_platform_driver(twl4030_audio_driver); MODULE_AUTHOR("Peter Ujfalusi "); MODULE_DESCRIPTION("TWL4030 audio block MFD driver"); -MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:twl4030-audio"); -- GitLab From f580386425518643c4027286b48cfa545390be07 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:03 +0000 Subject: [PATCH 4042/5631] mfd: lp8788: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/lp8788.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/lp8788.c b/drivers/mfd/lp8788.c index fe809b64147e..18583addaae2 100644 --- a/drivers/mfd/lp8788.c +++ b/drivers/mfd/lp8788.c @@ -244,4 +244,3 @@ module_exit(lp8788_exit); MODULE_DESCRIPTION("TI LP8788 MFD Driver"); MODULE_AUTHOR("Milo Kim"); -MODULE_LICENSE("GPL"); -- GitLab From fb2455985b5981e4f8a72667bb3d4bd5b7ca2b12 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:01 +0000 Subject: [PATCH 4043/5631] mfd: tps6586x: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/tps6586x.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c index 2d947f3f606a..90e23232b6b0 100644 --- a/drivers/mfd/tps6586x.c +++ b/drivers/mfd/tps6586x.c @@ -638,4 +638,3 @@ module_exit(tps6586x_exit); MODULE_DESCRIPTION("TPS6586X core driver"); MODULE_AUTHOR("Mike Rapoport "); -MODULE_LICENSE("GPL"); -- GitLab From 85aebcd54e2d22c00e0964442dc5330128e43f9b Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:05 +0000 Subject: [PATCH 4044/5631] mfd: omap-usb-tll: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/omap-usb-tll.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c index 080d7970a377..8ca4067da6cd 100644 --- a/drivers/mfd/omap-usb-tll.c +++ b/drivers/mfd/omap-usb-tll.c @@ -450,7 +450,6 @@ EXPORT_SYMBOL_GPL(omap_tll_disable); MODULE_AUTHOR("Keshava Munegowda "); MODULE_AUTHOR("Roger Quadros "); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("usb tll driver for TI OMAP EHCI and OHCI controllers"); static int __init omap_usbtll_drvinit(void) -- GitLab From e3dfb3dbd67805914ebda52430257b370554e479 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:04 +0000 Subject: [PATCH 4045/5631] mfd: omap-usb-host: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/omap-usb-host.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 787d2ae86375..7f5775109593 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -853,7 +853,6 @@ static struct platform_driver usbhs_omap_driver = { MODULE_AUTHOR("Keshava Munegowda "); MODULE_AUTHOR("Roger Quadros "); MODULE_ALIAS("platform:" USBHS_DRIVER_NAME); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("usb host common core driver for omap EHCI and OHCI"); static int omap_usbhs_drvinit(void) -- GitLab From 0607ad38c2fb0182eba20d4f476558b0547d58a5 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:02 +0000 Subject: [PATCH 4046/5631] mfd: ezx-pcap: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/ezx-pcap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c index 3d5ce18aa9ae..8d006f6be48c 100644 --- a/drivers/mfd/ezx-pcap.c +++ b/drivers/mfd/ezx-pcap.c @@ -528,7 +528,6 @@ static void __exit ezx_pcap_exit(void) subsys_initcall(ezx_pcap_init); module_exit(ezx_pcap_exit); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Ribeiro / Harald Welte"); MODULE_DESCRIPTION("Motorola PCAP2 ASIC Driver"); MODULE_ALIAS("spi:ezx-pcap"); -- GitLab From 65edd14d790cfe076be0da58c457f75b35395c27 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:43:00 +0000 Subject: [PATCH 4047/5631] mfd: tc3589x: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/tc3589x.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/tc3589x.c b/drivers/mfd/tc3589x.c index 1f6e0d682cd9..cbfe19d1b145 100644 --- a/drivers/mfd/tc3589x.c +++ b/drivers/mfd/tc3589x.c @@ -502,6 +502,5 @@ static void __exit tc3589x_exit(void) } module_exit(tc3589x_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("TC3589x MFD core driver"); MODULE_AUTHOR("Hanumath Prasad, Rabin Vincent"); -- GitLab From ce1b2783136a1b44b619336fbe76776ae2c8f3ab Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:58 +0000 Subject: [PATCH 4048/5631] mfd: 88pm860x: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/88pm860x-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c index 6ba7169cb953..3c57e537d57f 100644 --- a/drivers/mfd/88pm860x-core.c +++ b/drivers/mfd/88pm860x-core.c @@ -1276,4 +1276,3 @@ module_exit(pm860x_i2c_exit); MODULE_DESCRIPTION("PMIC Driver for Marvell 88PM860x"); MODULE_AUTHOR("Haojian Zhuang "); -MODULE_LICENSE("GPL"); -- GitLab From 9ca834bd404c2b1e1e7010e7c22c5a1810fd7cd5 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:57 +0000 Subject: [PATCH 4049/5631] mfd: stmpe-spi: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/stmpe-spi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c index e9cbf33502b3..792236f56399 100644 --- a/drivers/mfd/stmpe-spi.c +++ b/drivers/mfd/stmpe-spi.c @@ -154,6 +154,5 @@ static void __exit stmpe_exit(void) } module_exit(stmpe_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("STMPE MFD SPI Interface Driver"); MODULE_AUTHOR("Viresh Kumar "); -- GitLab From 9e646615df195f1864e2384133a42a832a809059 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:56 +0000 Subject: [PATCH 4050/5631] mfd: stmpe-i2c: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/stmpe-i2c.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/stmpe-i2c.c b/drivers/mfd/stmpe-i2c.c index d4944fc1feb1..7998e0db1e15 100644 --- a/drivers/mfd/stmpe-i2c.c +++ b/drivers/mfd/stmpe-i2c.c @@ -135,6 +135,5 @@ static void __exit stmpe_exit(void) } module_exit(stmpe_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("STMPE MFD I2C Interface Driver"); MODULE_AUTHOR("Rabin Vincent "); -- GitLab From e7bf264def565d77474dd074109cc84948a5058e Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:55 +0000 Subject: [PATCH 4051/5631] mfd: da9055-i2c: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/da9055-i2c.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c index 702abff506a1..537fd5de3e6d 100644 --- a/drivers/mfd/da9055-i2c.c +++ b/drivers/mfd/da9055-i2c.c @@ -97,4 +97,3 @@ module_exit(da9055_i2c_exit); MODULE_AUTHOR("David Dajun Chen "); MODULE_DESCRIPTION("I2C driver for Dialog DA9055 PMIC"); -MODULE_LICENSE("GPL"); -- GitLab From 1247f3c3e1f29fc78027dfe4043f6c0413612126 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:54 +0000 Subject: [PATCH 4052/5631] mfd: da9055: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/da9055-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da9055-core.c b/drivers/mfd/da9055-core.c index c3bcbd8905c6..768302e05baa 100644 --- a/drivers/mfd/da9055-core.c +++ b/drivers/mfd/da9055-core.c @@ -398,5 +398,4 @@ void da9055_device_exit(struct da9055 *da9055) } MODULE_DESCRIPTION("Core support for the DA9055 PMIC"); -MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Dajun Chen "); -- GitLab From fca17373d26c5e4e98134f97601aff688d164813 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:53 +0000 Subject: [PATCH 4053/5631] mfd: da9052-spi: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/da9052-spi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c index b79a57b45c1e..be5f2b34e18a 100644 --- a/drivers/mfd/da9052-spi.c +++ b/drivers/mfd/da9052-spi.c @@ -102,4 +102,3 @@ module_exit(da9052_spi_exit); MODULE_AUTHOR("David Dajun Chen "); MODULE_DESCRIPTION("SPI driver for Dialog DA9052 PMIC"); -MODULE_LICENSE("GPL"); -- GitLab From adefecd9b506a6f9981cdcda97ae6803bdea0180 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:52 +0000 Subject: [PATCH 4054/5631] mfd: da9052-i2c: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/da9052-i2c.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c index ecb8077cdaaf..03db7a2ccf7a 100644 --- a/drivers/mfd/da9052-i2c.c +++ b/drivers/mfd/da9052-i2c.c @@ -209,4 +209,3 @@ module_exit(da9052_i2c_exit); MODULE_AUTHOR("David Dajun Chen "); MODULE_DESCRIPTION("I2C driver for Dialog DA9052 PMIC"); -MODULE_LICENSE("GPL"); -- GitLab From ca9642a623dfc43a8ec8b0ba4694605ea74cef20 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:51 +0000 Subject: [PATCH 4055/5631] mfd: da9052: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones --- drivers/mfd/da9052-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c index 8b42d2f7024f..150448cd2eb0 100644 --- a/drivers/mfd/da9052-core.c +++ b/drivers/mfd/da9052-core.c @@ -653,4 +653,3 @@ void da9052_device_exit(struct da9052 *da9052) MODULE_AUTHOR("David Dajun Chen "); MODULE_DESCRIPTION("DA9052 MFD Core"); -MODULE_LICENSE("GPL"); -- GitLab From 2ddbddaf19dcdc60e05c720611faca7ba5176ed9 Mon Sep 17 00:00:00 2001 From: Nick Alcock Date: Wed, 8 Mar 2023 19:42:50 +0000 Subject: [PATCH 4056/5631] mfd: da903x: Remove MODULE_LICENSE in non-modules Since commit 8b41fc4454e ("kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf"), MODULE_LICENSE declarations are used to identify modules. As a consequence, uses of the macro in non-modules will cause modprobe to misidentify their containing object file as a module when it is not (false positives), and modprobe might succeed rather than failing with a suitable error message. So remove it in the files in this commit, none of which can be built as modules. Signed-off-by: Nick Alcock Suggested-by: Luis Chamberlain Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230308194307.374789-1-nick.alcock@oracle.com --- drivers/mfd/da903x.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c index 44a25d642ce9..6570b33a5a77 100644 --- a/drivers/mfd/da903x.c +++ b/drivers/mfd/da903x.c @@ -563,4 +563,3 @@ module_exit(da903x_exit); MODULE_DESCRIPTION("PMIC Driver for Dialog Semiconductor DA9034"); MODULE_AUTHOR("Eric Miao "); MODULE_AUTHOR("Mike Rapoport "); -MODULE_LICENSE("GPL v2"); -- GitLab From 1ba58fbbe619125af113d0583c4b6bade94168d1 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:12 -0600 Subject: [PATCH 4057/5631] mfd: various: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230310144712.1543379-1-robh@kernel.org --- drivers/mfd/bcm2835-pm.c | 2 +- drivers/mfd/khadas-mcu.c | 2 +- drivers/mfd/stmpe.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/bcm2835-pm.c b/drivers/mfd/bcm2835-pm.c index 2c0aa2a2c893..3cb2b9423121 100644 --- a/drivers/mfd/bcm2835-pm.c +++ b/drivers/mfd/bcm2835-pm.c @@ -28,7 +28,7 @@ static const struct mfd_cell bcm2835_power_devs[] = { static int bcm2835_pm_get_pdata(struct platform_device *pdev, struct bcm2835_pm *pm) { - if (of_find_property(pm->dev->of_node, "reg-names", NULL)) { + if (of_property_present(pm->dev->of_node, "reg-names")) { struct resource *res; pm->base = devm_platform_ioremap_resource_byname(pdev, "pm"); diff --git a/drivers/mfd/khadas-mcu.c b/drivers/mfd/khadas-mcu.c index 7338cc16f327..1c807c0e6d25 100644 --- a/drivers/mfd/khadas-mcu.c +++ b/drivers/mfd/khadas-mcu.c @@ -112,7 +112,7 @@ static int khadas_mcu_probe(struct i2c_client *client) if (ret) return ret; - if (of_find_property(dev->of_node, "#cooling-cells", NULL)) + if (of_property_present(dev->of_node, "#cooling-cells")) return devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, khadas_mcu_fan_cells, ARRAY_SIZE(khadas_mcu_fan_cells), diff --git a/drivers/mfd/stmpe.c b/drivers/mfd/stmpe.c index c304d20bb988..a92301dfc712 100644 --- a/drivers/mfd/stmpe.c +++ b/drivers/mfd/stmpe.c @@ -1378,7 +1378,7 @@ int stmpe_probe(struct stmpe_client_info *ci, enum stmpe_partnum partnum) stmpe_of_probe(pdata, np); - if (of_find_property(np, "interrupts", NULL) == NULL) + if (!of_property_present(np, "interrupts")) ci->irq = -1; stmpe = devm_kzalloc(ci->dev, sizeof(struct stmpe), GFP_KERNEL); -- GitLab From 01330edcc5ecc92eb9152b27f326618735900502 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:12 -0600 Subject: [PATCH 4058/5631] mfd: various: Use of_property_read_bool() for boolean properties It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. Convert reading boolean properties to to of_property_read_bool(). Signed-off-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230310144712.1543449-1-robh@kernel.org --- drivers/mfd/88pm860x-core.c | 3 +-- drivers/mfd/wm8994-core.c | 19 +++++-------------- 2 files changed, 6 insertions(+), 16 deletions(-) diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c index 3c57e537d57f..aabac37c3502 100644 --- a/drivers/mfd/88pm860x-core.c +++ b/drivers/mfd/88pm860x-core.c @@ -1117,8 +1117,7 @@ static int pm860x_dt_init(struct device_node *np, { int ret; - if (of_get_property(np, "marvell,88pm860x-irq-read-clr", NULL)) - pdata->irq_mode = 1; + pdata->irq_mode = of_property_read_bool(np, "marvell,88pm860x-irq-read-clr"); ret = of_property_read_u32(np, "marvell,88pm860x-slave-addr", &pdata->companion_addr); if (ret) { diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index a89221bffde5..c419ab0c0eae 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -279,20 +279,11 @@ static int wm8994_set_pdata_from_of(struct wm8994 *wm8994) of_property_read_u32_array(np, "wlf,micbias-cfg", pdata->micbias, ARRAY_SIZE(pdata->micbias)); - pdata->lineout1_diff = true; - pdata->lineout2_diff = true; - if (of_find_property(np, "wlf,lineout1-se", NULL)) - pdata->lineout1_diff = false; - if (of_find_property(np, "wlf,lineout2-se", NULL)) - pdata->lineout2_diff = false; - - if (of_find_property(np, "wlf,lineout1-feedback", NULL)) - pdata->lineout1fb = true; - if (of_find_property(np, "wlf,lineout2-feedback", NULL)) - pdata->lineout2fb = true; - - if (of_find_property(np, "wlf,ldoena-always-driven", NULL)) - pdata->lineout2fb = true; + pdata->lineout1_diff = !of_property_read_bool(np, "wlf,lineout1-se"); + pdata->lineout2_diff = !of_property_read_bool(np, "wlf,lineout2-se"); + pdata->lineout1fb = of_property_read_bool(np, "wlf,lineout1-feedback"); + pdata->lineout2fb = of_property_read_bool(np, "wlf,lineout2-feedback") || + of_property_read_bool(np, "wlf,ldoena-always-driven"); pdata->spkmode_pu = of_property_read_bool(np, "wlf,spkmode-pu"); -- GitLab From f130faebcdb6c7fd04c1db9e589d593361b81c13 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:16:28 +0100 Subject: [PATCH 4059/5631] mfd: atmel-smc: Mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/mfd/atmel-smc.c:326:34: error: ‘atmel_smc_ids’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230311111629.251830-1-krzysztof.kozlowski@linaro.org --- drivers/mfd/atmel-smc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/atmel-smc.c b/drivers/mfd/atmel-smc.c index f3bad2b52f17..e560066e5885 100644 --- a/drivers/mfd/atmel-smc.c +++ b/drivers/mfd/atmel-smc.c @@ -323,7 +323,7 @@ static const struct atmel_hsmc_reg_layout sama5d2_reg_layout = { .timing_regs_offset = 0x700, }; -static const struct of_device_id atmel_smc_ids[] = { +static const struct of_device_id atmel_smc_ids[] __maybe_unused = { { .compatible = "atmel,at91sam9260-smc", .data = NULL }, { .compatible = "atmel,sama5d3-smc", .data = &sama5d3_reg_layout }, { .compatible = "atmel,sama5d2-smc", .data = &sama5d2_reg_layout }, -- GitLab From 9bb8ccead3b0162cf98091c4ff25e772fd97d953 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:16:29 +0100 Subject: [PATCH 4060/5631] mfd: atc260x-i2c: Drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/mfd/atc260x-i2c.c:44:34: error: ‘atc260x_i2c_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230311111629.251830-2-krzysztof.kozlowski@linaro.org --- drivers/mfd/atc260x-i2c.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mfd/atc260x-i2c.c b/drivers/mfd/atc260x-i2c.c index 19e248ed7966..8e1491167160 100644 --- a/drivers/mfd/atc260x-i2c.c +++ b/drivers/mfd/atc260x-i2c.c @@ -51,7 +51,7 @@ MODULE_DEVICE_TABLE(of, atc260x_i2c_of_match); static struct i2c_driver atc260x_i2c_driver = { .driver = { .name = "atc260x", - .of_match_table = of_match_ptr(atc260x_i2c_of_match), + .of_match_table = atc260x_i2c_of_match, }, .probe_new = atc260x_i2c_probe, }; -- GitLab From e90978ecdf9d016e31f6aff36da77255b42fb4fd Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 13 Mar 2023 11:58:33 +0100 Subject: [PATCH 4061/5631] mfd: rsmu_spi: Remove unneeded casts of void * There is no need to cast a "void *" to a different type of pointer. Signed-off-by: Geert Uytterhoeven Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/ae84c1751e79cb49ab584557f4ecd835a8493d7c.1678704562.git.geert+renesas@glider.be --- drivers/mfd/rsmu_spi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mfd/rsmu_spi.c b/drivers/mfd/rsmu_spi.c index d2f3d8f1e05a..2428aaa9aaed 100644 --- a/drivers/mfd/rsmu_spi.c +++ b/drivers/mfd/rsmu_spi.c @@ -129,7 +129,7 @@ static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u16 reg) static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) { - struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + struct rsmu_ddata *rsmu = spi_get_drvdata(context); u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); int err; @@ -146,7 +146,7 @@ static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) static int rsmu_reg_write(void *context, unsigned int reg, unsigned int val) { - struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + struct rsmu_ddata *rsmu = spi_get_drvdata(context); u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); u8 data = (u8)val; int err; -- GitLab From 44604617ce7aa0c24fd198b5a8760e018549922f Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Wed, 15 Mar 2023 19:38:19 +0100 Subject: [PATCH 4062/5631] dt-bindings: mfd: qcom,spmi-pmic: Add PM2250 Add a compatible for PM2250, commonly found with QCM2290. Signed-off-by: Konrad Dybcio Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230315183819.3563704-1-konrad.dybcio@linaro.org --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index 8f076bb622b1..975c30aad23c 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -33,6 +33,7 @@ properties: compatible: items: - enum: + - qcom,pm2250 - qcom,pm6125 - qcom,pm6150 - qcom,pm6150l -- GitLab From 881656790e9bd246b7cf6eb537feb04f09140a40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Apitzsch?= Date: Sun, 19 Mar 2023 13:41:53 +0100 Subject: [PATCH 4063/5631] mfd: arizona-i2c: Add the missing device table IDs for OF MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds missing MODULE_DEVICE_TABLE definition which generates correct modalias for automatic loading of this driver when it is built as a module. Signed-off-by: André Apitzsch Acked-by: Charles Keepax Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230319124153.35294-1-git@apitzsch.eu --- drivers/mfd/arizona-i2c.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/arizona-i2c.c b/drivers/mfd/arizona-i2c.c index b2301586adbc..43e393c8608d 100644 --- a/drivers/mfd/arizona-i2c.c +++ b/drivers/mfd/arizona-i2c.c @@ -112,6 +112,7 @@ static const struct of_device_id arizona_i2c_of_match[] = { { .compatible = "wlf,wm1814", .data = (void *)WM1814 }, {}, }; +MODULE_DEVICE_TABLE(of, arizona_i2c_of_match); #endif static struct i2c_driver arizona_i2c_driver = { -- GitLab From 3e0475ec8d9114b600586b0bfb4056565a679a3d Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 14 Mar 2023 19:30:33 +0100 Subject: [PATCH 4064/5631] dt-bindings: mfd: qcom,spmi-pmic: Add compatible for pmm8654au PMM8654au is the SPMI PMIC variant used on sa8775p-ride. Add a compatible for it. Signed-off-by: Bartosz Golaszewski Acked-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230314183043.619997-5-brgl@bgdev.pl --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index 975c30aad23c..0f7dd7ac9630 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -79,6 +79,7 @@ properties: - qcom,pmk8350 - qcom,pmk8550 - qcom,pmm8155au + - qcom,pmm8654au - qcom,pmp8074 - qcom,pmr735a - qcom,pmr735b -- GitLab From 75c0a1b3fc1c09ed67d22235900cb7e762af1dfd Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 22 Mar 2023 07:58:38 -0400 Subject: [PATCH 4065/5631] mfd: twl-core: Remove unused add_child() and add_numbered_child() functions Clang with W=1 reports: drivers/mfd/twl-core.c:654:30: error: unused function 'add_child' [-Werror,-Wunused-function] static inline struct device *add_child(unsigned mod_no, const char *name, ^ add_numbered_child() and its only caller add_child() are not used, so remove them. Signed-off-by: Tom Rix Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230322115838.2569414-1-trix@redhat.com --- drivers/mfd/twl-core.c | 65 ------------------------------------------ 1 file changed, 65 deletions(-) diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index e2d9a93be43b..e801b7ce010f 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -594,71 +594,6 @@ int twl_get_hfclk_rate(void) } EXPORT_SYMBOL_GPL(twl_get_hfclk_rate); -static struct device * -add_numbered_child(unsigned mod_no, const char *name, int num, - void *pdata, unsigned pdata_len, - bool can_wakeup, int irq0, int irq1) -{ - struct platform_device *pdev; - struct twl_client *twl; - int status, sid; - - if (unlikely(mod_no >= twl_get_last_module())) { - pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no); - return ERR_PTR(-EPERM); - } - sid = twl_priv->twl_map[mod_no].sid; - twl = &twl_priv->twl_modules[sid]; - - pdev = platform_device_alloc(name, num); - if (!pdev) - return ERR_PTR(-ENOMEM); - - pdev->dev.parent = &twl->client->dev; - - if (pdata) { - status = platform_device_add_data(pdev, pdata, pdata_len); - if (status < 0) { - dev_dbg(&pdev->dev, "can't add platform_data\n"); - goto put_device; - } - } - - if (irq0) { - struct resource r[2] = { - { .start = irq0, .flags = IORESOURCE_IRQ, }, - { .start = irq1, .flags = IORESOURCE_IRQ, }, - }; - - status = platform_device_add_resources(pdev, r, irq1 ? 2 : 1); - if (status < 0) { - dev_dbg(&pdev->dev, "can't add irqs\n"); - goto put_device; - } - } - - status = platform_device_add(pdev); - if (status) - goto put_device; - - device_init_wakeup(&pdev->dev, can_wakeup); - - return &pdev->dev; - -put_device: - platform_device_put(pdev); - dev_err(&twl->client->dev, "failed to add device %s\n", name); - return ERR_PTR(status); -} - -static inline struct device *add_child(unsigned mod_no, const char *name, - void *pdata, unsigned pdata_len, - bool can_wakeup, int irq0, int irq1) -{ - return add_numbered_child(mod_no, name, -1, pdata, pdata_len, - can_wakeup, irq0, irq1); -} - /*----------------------------------------------------------------------*/ /* -- GitLab From 4363f2113d04db9bafcc79487050ee0c10875c5a Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Wed, 22 Mar 2023 08:58:03 -0400 Subject: [PATCH 4066/5631] mfd: omap-usb-tll: Remove unused usbtll_readb() function Clang with W=1 reports: drivers/mfd/omap-usb-tll.c:128:18: error: unused function 'usbtll_readb' [-Werror,-Wunused-function] static inline u8 usbtll_readb(void __iomem *base, u32 reg) ^ This function is not used so remove it. Signed-off-by: Tom Rix Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230322125803.2570968-1-trix@redhat.com --- drivers/mfd/omap-usb-tll.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c index 8ca4067da6cd..69cbc2097911 100644 --- a/drivers/mfd/omap-usb-tll.c +++ b/drivers/mfd/omap-usb-tll.c @@ -125,11 +125,6 @@ static inline void usbtll_writeb(void __iomem *base, u32 reg, u8 val) writeb_relaxed(val, base + reg); } -static inline u8 usbtll_readb(void __iomem *base, u32 reg) -{ - return readb_relaxed(base + reg); -} - /*-------------------------------------------------------------------------*/ static bool is_ohci_port(enum usbhs_omap_port_mode pmode) -- GitLab From f0484d2f80a72022b7fac72bcb406392900ef1eb Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Wed, 22 Mar 2023 07:11:30 -0700 Subject: [PATCH 4067/5631] mfd: ocelot-spi: Fix unsupported bulk read Ocelot chips (VSC7511, VSC7512, VSC7513, VSC7514) don't support bulk read operations over SPI. Many SPI buses have hardware that can optimize consecutive reads. Essentially an address is written to the chip, and if the SPI controller continues to toggle the clock, subsequent register values are reported. This can lead to significant optimizations, because the time between "address is written to the chip" and "chip starts to report data" can often take a fixed amount of time. When support for Ocelot chips were added in commit f3e893626abe ("mfd: ocelot: Add support for the vsc7512 chip via spi") it was believed that this optimization was supported. However it is not. Most register transactions with the Ocelot chips are not done in bulk, so this bug could go unnoticed. The one scenario where bulk register operations _are_ performed is when polling port statistics counters, which was added in commit d87b1c08f38a ("net: mscc: ocelot: use bulk reads for stats"). Things get slightly more complicated here... A bug was introduced in commit d4c367650704 ("net: mscc: ocelot: keep ocelot_stat_layout by reg address, not offset") that broke the optimization of bulk reads. This means that when Ethernet support for the VSC7512 chip was added in commit 3d7316ac81ac ("net: dsa: ocelot: add external ocelot switch control") things were actually working "as expected". The bulk read opmtimization was discovered, and fixed in commit 6acc72a43eac ("net: mscc: ocelot: fix stats region batching") and the timing optimizations for SPI were noticed. A bulk read went from ~14ms to ~2ms. But this timing improvement came at the cost of every register reading zero due the fact that bulk reads don't work. The read timings increase back to 13-14ms, but that's a price worth paying in order to receive valid data. This is verified in a DSA setup (cpsw-new switch tied to port 0 on the VSC7512, after having been running overnight) Rx Octets: 16222055 # Counters from CPSW switch Tx Octets: 12034702 Net Octets: 28256757 p00_rx_octets: 12034702 # Counters from Ocelot switch p00_rx_frames_below_65_octets: 0 p00_rx_frames_65_to_127_octets: 88188 p00_rx_frames_128_to_255_octets: 13 p00_rx_frames_256_to_511_octets: 0 p00_rx_frames_512_to_1023_octets: 0 p00_rx_frames_over_1526_octets: 3306 p00_tx_octets: 16222055 Fixes: f3e893626abe ("mfd: ocelot: Add support for the vsc7512 chip via spi") Signed-off-by: Colin Foster Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230322141130.2531256-1-colin.foster@in-advantage.com --- drivers/mfd/ocelot-spi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/ocelot-spi.c b/drivers/mfd/ocelot-spi.c index 2ecd271de2fb..85021f94e587 100644 --- a/drivers/mfd/ocelot-spi.c +++ b/drivers/mfd/ocelot-spi.c @@ -130,6 +130,7 @@ static const struct regmap_config ocelot_spi_regmap_config = { .write_flag_mask = 0x80, + .use_single_read = true, .use_single_write = true, .can_multi_write = false, -- GitLab From 9896a19caf79f83692f13ab688d34c85ecfa92b2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 22 Mar 2023 12:35:18 -0500 Subject: [PATCH 4068/5631] dt-bindings: mfd: Drop unneeded quotes in 'ref', 'id' and 'schema' entries Cleanup bindings dropping unneeded quotes. Once all these are fixed, checking for this can be enabled in yamllint. Signed-off-by: Rob Herring Reviewed-by: Damien Le Moal Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230322173519.3971434-1-robh@kernel.org --- .../bindings/mfd/canaan,k210-sysctl.yaml | 6 ++--- .../bindings/mfd/google,cros-ec.yaml | 22 +++++++++---------- .../mfd/hisilicon,hi6421-spmi-pmic.yaml | 2 +- .../devicetree/bindings/mfd/qcom-pm8xxx.yaml | 2 +- .../bindings/mfd/rohm,bd71815-pmic.yaml | 2 +- .../bindings/mfd/rohm,bd71828-pmic.yaml | 2 +- .../devicetree/bindings/mfd/wlf,arizona.yaml | 2 +- .../bindings/mfd/x-powers,ac100.yaml | 4 ++-- .../bindings/mfd/xylon,logicvc.yaml | 4 ++-- 9 files changed, 23 insertions(+), 23 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml index e2046f07a40e..8459d3642205 100644 --- a/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml +++ b/Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml @@ -36,7 +36,7 @@ properties: clock-controller: # Child node type: object - $ref: "../clock/canaan,k210-clk.yaml" + $ref: ../clock/canaan,k210-clk.yaml description: Clock controller for the SoC clocks. This child node definition should follow the bindings specified in @@ -45,7 +45,7 @@ properties: reset-controller: # Child node type: object - $ref: "../reset/canaan,k210-rst.yaml" + $ref: ../reset/canaan,k210-rst.yaml description: Reset controller for the SoC. This child node definition should follow the bindings specified in @@ -54,7 +54,7 @@ properties: syscon-reboot: # Child node type: object - $ref: "../power/reset/syscon-reboot.yaml" + $ref: ../power/reset/syscon-reboot.yaml description: Reboot method for the SoC. This child node definition should follow the bindings specified in diff --git a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml index cdf1d719efe9..456465e35114 100644 --- a/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml +++ b/Documentation/devicetree/bindings/mfd/google,cros-ec.yaml @@ -65,7 +65,7 @@ properties: ARM Cortex M4 Co-processor. Contains the name of the rpmsg device. Used to match the subnode to the rpmsg device announced by the SCP. - $ref: "/schemas/types.yaml#/definitions/string" + $ref: /schemas/types.yaml#/definitions/string spi-max-frequency: true @@ -94,23 +94,23 @@ properties: const: 0 typec: - $ref: "/schemas/chrome/google,cros-ec-typec.yaml#" + $ref: /schemas/chrome/google,cros-ec-typec.yaml# ec-pwm: - $ref: "/schemas/pwm/google,cros-ec-pwm.yaml#" + $ref: /schemas/pwm/google,cros-ec-pwm.yaml# deprecated: true pwm: - $ref: "/schemas/pwm/google,cros-ec-pwm.yaml#" + $ref: /schemas/pwm/google,cros-ec-pwm.yaml# kbd-led-backlight: - $ref: "/schemas/chrome/google,cros-kbd-led-backlight.yaml#" + $ref: /schemas/chrome/google,cros-kbd-led-backlight.yaml# keyboard-controller: - $ref: "/schemas/input/google,cros-ec-keyb.yaml#" + $ref: /schemas/input/google,cros-ec-keyb.yaml# proximity: - $ref: "/schemas/iio/proximity/google,cros-ec-mkbp-proximity.yaml#" + $ref: /schemas/iio/proximity/google,cros-ec-mkbp-proximity.yaml# codecs: type: object @@ -126,7 +126,7 @@ properties: patternProperties: "^ec-codec@[a-f0-9]+$": type: object - $ref: "/schemas/sound/google,cros-ec-codec.yaml#" + $ref: /schemas/sound/google,cros-ec-codec.yaml# required: - "#address-cells" @@ -151,15 +151,15 @@ properties: patternProperties: "^i2c-tunnel[0-9]*$": type: object - $ref: "/schemas/i2c/google,cros-ec-i2c-tunnel.yaml#" + $ref: /schemas/i2c/google,cros-ec-i2c-tunnel.yaml# "^regulator@[0-9]+$": type: object - $ref: "/schemas/regulator/google,cros-ec-regulator.yaml#" + $ref: /schemas/regulator/google,cros-ec-regulator.yaml# "^extcon[0-9]*$": type: object - $ref: "/schemas/extcon/extcon-usbc-cros-ec.yaml#" + $ref: /schemas/extcon/extcon-usbc-cros-ec.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml index 22edcb4b212f..bdff5b653453 100644 --- a/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/hisilicon,hi6421-spmi-pmic.yaml @@ -53,7 +53,7 @@ properties: '^ldo[0-9]+$': type: object - $ref: "/schemas/regulator/regulator.yaml#" + $ref: /schemas/regulator/regulator.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.yaml b/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.yaml index 9acad9d326eb..9c51c1b19067 100644 --- a/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom-pm8xxx.yaml @@ -49,7 +49,7 @@ patternProperties: "rtc@[0-9a-f]+$": type: object - $ref: "../rtc/qcom-pm8xxx-rtc.yaml" + $ref: ../rtc/qcom-pm8xxx-rtc.yaml required: - compatible diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml index d6d120a78094..05747e012516 100644 --- a/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/rohm,bd71815-pmic.yaml @@ -46,7 +46,7 @@ properties: rohm,clkout-open-drain: description: clk32kout mode. Set to 1 for "open-drain" or 0 for "cmos". - $ref: "/schemas/types.yaml#/definitions/uint32" + $ref: /schemas/types.yaml#/definitions/uint32 minimum: 0 maximum: 1 diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml index ec3adcd3483d..11089aa89ec6 100644 --- a/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml @@ -46,7 +46,7 @@ properties: rohm,clkout-open-drain: description: clk32kout mode. Set to 1 for "open-drain" or 0 for "cmos". - $ref: "/schemas/types.yaml#/definitions/uint32" + $ref: /schemas/types.yaml#/definitions/uint32 minimum: 0 maximum: 1 diff --git a/Documentation/devicetree/bindings/mfd/wlf,arizona.yaml b/Documentation/devicetree/bindings/mfd/wlf,arizona.yaml index ea3337dafaf5..7902f3c5d289 100644 --- a/Documentation/devicetree/bindings/mfd/wlf,arizona.yaml +++ b/Documentation/devicetree/bindings/mfd/wlf,arizona.yaml @@ -156,7 +156,7 @@ properties: entry has a value that is out of range for a 16 bit register then the chip default will be used. If present exactly five values must be specified. - $ref: "/schemas/types.yaml#/definitions/uint32-array" + $ref: /schemas/types.yaml#/definitions/uint32-array minItems: 1 maxItems: 5 diff --git a/Documentation/devicetree/bindings/mfd/x-powers,ac100.yaml b/Documentation/devicetree/bindings/mfd/x-powers,ac100.yaml index 309606d2d806..f3d8394b27e7 100644 --- a/Documentation/devicetree/bindings/mfd/x-powers,ac100.yaml +++ b/Documentation/devicetree/bindings/mfd/x-powers,ac100.yaml @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 %YAML 1.2 --- -$id: "http://devicetree.org/schemas/mfd/x-powers,ac100.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/mfd/x-powers,ac100.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: X-Powers AC100 diff --git a/Documentation/devicetree/bindings/mfd/xylon,logicvc.yaml b/Documentation/devicetree/bindings/mfd/xylon,logicvc.yaml index 9efd49c39bd2..6e880a46d7ee 100644 --- a/Documentation/devicetree/bindings/mfd/xylon,logicvc.yaml +++ b/Documentation/devicetree/bindings/mfd/xylon,logicvc.yaml @@ -2,8 +2,8 @@ # Copyright 2019 Bootlin %YAML 1.2 --- -$id: "http://devicetree.org/schemas/mfd/xylon,logicvc.yaml#" -$schema: "http://devicetree.org/meta-schemas/core.yaml#" +$id: http://devicetree.org/schemas/mfd/xylon,logicvc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# title: Xylon LogiCVC multi-function device -- GitLab From 972c91fd7beddc3f19c8c855f6e60e7dbd435cbd Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 23 Mar 2023 13:41:38 +0000 Subject: [PATCH 4069/5631] mfd: arizona-spi: Add missing MODULE_DEVICE_TABLE This patch adds missing MODULE_DEVICE_TABLE definition which generates correct modalias for automatic loading of this driver when it is built as a module. Fixes: 3f65555c417c ("mfd: arizona: Split of_match table into I2C and SPI versions") Signed-off-by: Charles Keepax Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230323134138.834369-1-ckeepax@opensource.cirrus.com --- drivers/mfd/arizona-spi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/arizona-spi.c b/drivers/mfd/arizona-spi.c index da05b966d48c..02cf4f3e91d7 100644 --- a/drivers/mfd/arizona-spi.c +++ b/drivers/mfd/arizona-spi.c @@ -277,6 +277,7 @@ static const struct of_device_id arizona_spi_of_match[] = { { .compatible = "cirrus,cs47l24", .data = (void *)CS47L24 }, {}, }; +MODULE_DEVICE_TABLE(of, arizona_spi_of_match); #endif static struct spi_driver arizona_spi_driver = { -- GitLab From fb9d4960a876e9344ab2c8a22c5c0fcd8c64210d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 20 Mar 2023 14:57:10 +0100 Subject: [PATCH 4070/5631] dt-bindings: mfd: qcom,spmi-pmic: Add nvram function Add an 'nvram' pattern property and a reference to the corresponding SDAM DT schema. Signed-off-by: Johan Hovold Acked-by: Rob Herring Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230320135710.1989-4-johan+linaro@kernel.org --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index 0f7dd7ac9630..84620ebc1efe 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -138,6 +138,10 @@ patternProperties: type: object $ref: /schemas/pinctrl/qcom,pmic-gpio.yaml# + "^nvram@[0-9a-f]+$": + type: object + $ref: /schemas/nvmem/qcom,spmi-sdam.yaml# + "pon@[0-9a-f]+$": type: object $ref: /schemas/power/reset/qcom,pon.yaml# -- GitLab From 67d6c76fc815cddc77de9529221f9ff8dd1fb10e Mon Sep 17 00:00:00 2001 From: Min Li Date: Mon, 27 Mar 2023 14:39:53 -0400 Subject: [PATCH 4071/5631] mfd: rsmu: Support 32-bit address space We used to assume 0x2010xxxx address. Now that we need to access 0x2011xxxx address, we need to support read/write the whole 32-bit address space. Also defined RSMU_MAX_WRITE_COUNT and RSMU_MAX_READ_COUNT for readability Signed-off-by: Min Li Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/MW5PR03MB693295AF31ABCAF6AE52EE74A08B9@MW5PR03MB6932.namprd03.prod.outlook.com --- drivers/mfd/rsmu.h | 2 + drivers/mfd/rsmu_i2c.c | 171 ++++++++++++++++++++++++++++++--------- drivers/mfd/rsmu_spi.c | 52 +++++++----- include/linux/mfd/rsmu.h | 5 +- 4 files changed, 174 insertions(+), 56 deletions(-) diff --git a/drivers/mfd/rsmu.h b/drivers/mfd/rsmu.h index bb88597d189f..1bb04cafa45d 100644 --- a/drivers/mfd/rsmu.h +++ b/drivers/mfd/rsmu.h @@ -10,6 +10,8 @@ #include +#define RSMU_CM_SCSR_BASE 0x20100000 + int rsmu_core_init(struct rsmu_ddata *rsmu); void rsmu_core_exit(struct rsmu_ddata *rsmu); diff --git a/drivers/mfd/rsmu_i2c.c b/drivers/mfd/rsmu_i2c.c index 15d25b081434..221023faaadf 100644 --- a/drivers/mfd/rsmu_i2c.c +++ b/drivers/mfd/rsmu_i2c.c @@ -18,11 +18,12 @@ #include "rsmu.h" /* - * 16-bit register address: the lower 8 bits of the register address come - * from the offset addr byte and the upper 8 bits come from the page register. + * 32-bit register address: the lower 8 bits of the register address come + * from the offset addr byte and the upper 24 bits come from the page register. */ -#define RSMU_CM_PAGE_ADDR 0xFD -#define RSMU_CM_PAGE_WINDOW 256 +#define RSMU_CM_PAGE_ADDR 0xFC +#define RSMU_CM_PAGE_MASK 0xFFFFFF00 +#define RSMU_CM_ADDRESS_MASK 0x000000FF /* * 15-bit register address: the lower 7 bits of the register address come @@ -31,18 +32,6 @@ #define RSMU_SABRE_PAGE_ADDR 0x7F #define RSMU_SABRE_PAGE_WINDOW 128 -static const struct regmap_range_cfg rsmu_cm_range_cfg[] = { - { - .range_min = 0, - .range_max = 0xD000, - .selector_reg = RSMU_CM_PAGE_ADDR, - .selector_mask = 0xFF, - .selector_shift = 0, - .window_start = 0, - .window_len = RSMU_CM_PAGE_WINDOW, - } -}; - static const struct regmap_range_cfg rsmu_sabre_range_cfg[] = { { .range_min = 0, @@ -55,35 +44,141 @@ static const struct regmap_range_cfg rsmu_sabre_range_cfg[] = { } }; -static bool rsmu_cm_volatile_reg(struct device *dev, unsigned int reg) +static bool rsmu_sabre_volatile_reg(struct device *dev, unsigned int reg) { switch (reg) { - case RSMU_CM_PAGE_ADDR: + case RSMU_SABRE_PAGE_ADDR: return false; default: return true; } } -static bool rsmu_sabre_volatile_reg(struct device *dev, unsigned int reg) +static int rsmu_read_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes) { - switch (reg) { - case RSMU_SABRE_PAGE_ADDR: - return false; - default: - return true; + struct i2c_client *client = to_i2c_client(rsmu->dev); + struct i2c_msg msg[2]; + int cnt; + + msg[0].addr = client->addr; + msg[0].flags = 0; + msg[0].len = 1; + msg[0].buf = ® + + msg[1].addr = client->addr; + msg[1].flags = I2C_M_RD; + msg[1].len = bytes; + msg[1].buf = buf; + + cnt = i2c_transfer(client->adapter, msg, 2); + + if (cnt < 0) { + dev_err(rsmu->dev, "i2c_transfer failed at addr: %04x!", reg); + return cnt; + } else if (cnt != 2) { + dev_err(rsmu->dev, + "i2c_transfer sent only %d of 2 messages", cnt); + return -EIO; + } + + return 0; +} + +static int rsmu_write_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes) +{ + struct i2c_client *client = to_i2c_client(rsmu->dev); + u8 msg[RSMU_MAX_WRITE_COUNT + 1]; /* 1 Byte added for the device register */ + int cnt; + + if (bytes > RSMU_MAX_WRITE_COUNT) + return -EINVAL; + + msg[0] = reg; + memcpy(&msg[1], buf, bytes); + + cnt = i2c_master_send(client, msg, bytes + 1); + + if (cnt < 0) { + dev_err(&client->dev, + "i2c_master_send failed at addr: %04x!", reg); + return cnt; } + + return 0; +} + +static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u32 reg) +{ + u32 page = reg & RSMU_CM_PAGE_MASK; + u8 buf[4]; + int err; + + /* Do not modify offset register for none-scsr registers */ + if (reg < RSMU_CM_SCSR_BASE) + return 0; + + /* Simply return if we are on the same page */ + if (rsmu->page == page) + return 0; + + buf[0] = 0x0; + buf[1] = (u8)((page >> 8) & 0xFF); + buf[2] = (u8)((page >> 16) & 0xFF); + buf[3] = (u8)((page >> 24) & 0xFF); + + err = rsmu_write_device(rsmu, RSMU_CM_PAGE_ADDR, buf, sizeof(buf)); + if (err) + dev_err(rsmu->dev, "Failed to set page offset 0x%x\n", page); + else + /* Remember the last page */ + rsmu->page = page; + + return err; +} + +static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) +{ + struct rsmu_ddata *rsmu = i2c_get_clientdata((struct i2c_client *)context); + u8 addr = (u8)(reg & RSMU_CM_ADDRESS_MASK); + int err; + + err = rsmu_write_page_register(rsmu, reg); + if (err) + return err; + + err = rsmu_read_device(rsmu, addr, (u8 *)val, 1); + if (err) + dev_err(rsmu->dev, "Failed to read offset address 0x%x\n", addr); + + return err; +} + +static int rsmu_reg_write(void *context, unsigned int reg, unsigned int val) +{ + struct rsmu_ddata *rsmu = i2c_get_clientdata((struct i2c_client *)context); + u8 addr = (u8)(reg & RSMU_CM_ADDRESS_MASK); + u8 data = (u8)val; + int err; + + err = rsmu_write_page_register(rsmu, reg); + if (err) + return err; + + err = rsmu_write_device(rsmu, addr, &data, 1); + if (err) + dev_err(rsmu->dev, + "Failed to write offset address 0x%x\n", addr); + + return err; } static const struct regmap_config rsmu_cm_regmap_config = { - .reg_bits = 8, + .reg_bits = 32, .val_bits = 8, - .max_register = 0xD000, - .ranges = rsmu_cm_range_cfg, - .num_ranges = ARRAY_SIZE(rsmu_cm_range_cfg), - .volatile_reg = rsmu_cm_volatile_reg, - .cache_type = REGCACHE_RBTREE, - .can_multi_write = true, + .max_register = 0x20120000, + .reg_read = rsmu_reg_read, + .reg_write = rsmu_reg_write, + .cache_type = REGCACHE_NONE, }; static const struct regmap_config rsmu_sabre_regmap_config = { @@ -101,14 +196,14 @@ static const struct regmap_config rsmu_sl_regmap_config = { .reg_bits = 16, .val_bits = 8, .reg_format_endian = REGMAP_ENDIAN_BIG, - .max_register = 0x339, + .max_register = 0x340, .cache_type = REGCACHE_NONE, .can_multi_write = true, }; -static int rsmu_i2c_probe(struct i2c_client *client) +static int rsmu_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) { - const struct i2c_device_id *id = i2c_client_get_device_id(client); const struct regmap_config *cfg; struct rsmu_ddata *rsmu; int ret; @@ -136,7 +231,11 @@ static int rsmu_i2c_probe(struct i2c_client *client) dev_err(rsmu->dev, "Unsupported RSMU device type: %d\n", rsmu->type); return -ENODEV; } - rsmu->regmap = devm_regmap_init_i2c(client, cfg); + + if (rsmu->type == RSMU_CM) + rsmu->regmap = devm_regmap_init(&client->dev, NULL, client, cfg); + else + rsmu->regmap = devm_regmap_init_i2c(client, cfg); if (IS_ERR(rsmu->regmap)) { ret = PTR_ERR(rsmu->regmap); dev_err(rsmu->dev, "Failed to allocate register map: %d\n", ret); @@ -180,7 +279,7 @@ static struct i2c_driver rsmu_i2c_driver = { .name = "rsmu-i2c", .of_match_table = of_match_ptr(rsmu_i2c_of_match), }, - .probe_new = rsmu_i2c_probe, + .probe = rsmu_i2c_probe, .remove = rsmu_i2c_remove, .id_table = rsmu_i2c_id, }; diff --git a/drivers/mfd/rsmu_spi.c b/drivers/mfd/rsmu_spi.c index 2428aaa9aaed..a4a595bb8d0d 100644 --- a/drivers/mfd/rsmu_spi.c +++ b/drivers/mfd/rsmu_spi.c @@ -19,19 +19,21 @@ #define RSMU_CM_PAGE_ADDR 0x7C #define RSMU_SABRE_PAGE_ADDR 0x7F -#define RSMU_HIGHER_ADDR_MASK 0xFF80 -#define RSMU_HIGHER_ADDR_SHIFT 7 -#define RSMU_LOWER_ADDR_MASK 0x7F +#define RSMU_PAGE_MASK 0xFFFFFF80 +#define RSMU_ADDR_MASK 0x7F static int rsmu_read_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes) { struct spi_device *client = to_spi_device(rsmu->dev); struct spi_transfer xfer = {0}; struct spi_message msg; - u8 cmd[256] = {0}; - u8 rsp[256] = {0}; + u8 cmd[RSMU_MAX_READ_COUNT + 1] = {0}; + u8 rsp[RSMU_MAX_READ_COUNT + 1] = {0}; int ret; + if (bytes > RSMU_MAX_READ_COUNT) + return -EINVAL; + cmd[0] = reg | 0x80; xfer.rx_buf = rsp; xfer.len = bytes + 1; @@ -66,7 +68,10 @@ static int rsmu_write_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes struct spi_device *client = to_spi_device(rsmu->dev); struct spi_transfer xfer = {0}; struct spi_message msg; - u8 cmd[256] = {0}; + u8 cmd[RSMU_MAX_WRITE_COUNT + 1] = {0}; + + if (bytes > RSMU_MAX_WRITE_COUNT) + return -EINVAL; cmd[0] = reg; memcpy(&cmd[1], buf, bytes); @@ -86,26 +91,35 @@ static int rsmu_write_device(struct rsmu_ddata *rsmu, u8 reg, u8 *buf, u16 bytes * 16-bit register address: the lower 7 bits of the register address come * from the offset addr byte and the upper 9 bits come from the page register. */ -static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u16 reg) +static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u32 reg) { u8 page_reg; - u8 buf[2]; + u8 buf[4]; u16 bytes; - u16 page; + u32 page; int err; switch (rsmu->type) { case RSMU_CM: + /* Do not modify page register for none-scsr registers */ + if (reg < RSMU_CM_SCSR_BASE) + return 0; page_reg = RSMU_CM_PAGE_ADDR; - page = reg & RSMU_HIGHER_ADDR_MASK; + page = reg & RSMU_PAGE_MASK; buf[0] = (u8)(page & 0xff); buf[1] = (u8)((page >> 8) & 0xff); - bytes = 2; + buf[2] = (u8)((page >> 16) & 0xff); + buf[3] = (u8)((page >> 24) & 0xff); + bytes = 4; break; case RSMU_SABRE: + /* Do not modify page register if reg is page register itself */ + if ((reg & RSMU_ADDR_MASK) == RSMU_ADDR_MASK) + return 0; page_reg = RSMU_SABRE_PAGE_ADDR; - page = reg >> RSMU_HIGHER_ADDR_SHIFT; - buf[0] = (u8)(page & 0xff); + page = reg & RSMU_PAGE_MASK; + /* The three page bits are located in the single Page Register */ + buf[0] = (u8)((page >> 7) & 0x7); bytes = 1; break; default: @@ -129,8 +143,8 @@ static int rsmu_write_page_register(struct rsmu_ddata *rsmu, u16 reg) static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) { - struct rsmu_ddata *rsmu = spi_get_drvdata(context); - u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); + struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + u8 addr = (u8)(reg & RSMU_ADDR_MASK); int err; err = rsmu_write_page_register(rsmu, reg); @@ -146,8 +160,8 @@ static int rsmu_reg_read(void *context, unsigned int reg, unsigned int *val) static int rsmu_reg_write(void *context, unsigned int reg, unsigned int val) { - struct rsmu_ddata *rsmu = spi_get_drvdata(context); - u8 addr = (u8)(reg & RSMU_LOWER_ADDR_MASK); + struct rsmu_ddata *rsmu = spi_get_drvdata((struct spi_device *)context); + u8 addr = (u8)(reg & RSMU_ADDR_MASK); u8 data = (u8)val; int err; @@ -164,9 +178,9 @@ static int rsmu_reg_write(void *context, unsigned int reg, unsigned int val) } static const struct regmap_config rsmu_cm_regmap_config = { - .reg_bits = 16, + .reg_bits = 32, .val_bits = 8, - .max_register = 0xD000, + .max_register = 0x20120000, .reg_read = rsmu_reg_read, .reg_write = rsmu_reg_write, .cache_type = REGCACHE_NONE, diff --git a/include/linux/mfd/rsmu.h b/include/linux/mfd/rsmu.h index 6870de608233..0379aa207428 100644 --- a/include/linux/mfd/rsmu.h +++ b/include/linux/mfd/rsmu.h @@ -8,6 +8,9 @@ #ifndef __LINUX_MFD_RSMU_H #define __LINUX_MFD_RSMU_H +#define RSMU_MAX_WRITE_COUNT (255) +#define RSMU_MAX_READ_COUNT (255) + /* The supported devices are ClockMatrix, Sabre and SnowLotus */ enum rsmu_type { RSMU_CM = 0x34000, @@ -31,6 +34,6 @@ struct rsmu_ddata { struct regmap *regmap; struct mutex lock; enum rsmu_type type; - u16 page; + u32 page; }; #endif /* __LINUX_MFD_RSMU_H */ -- GitLab From 66c8d55966fd169a36fa2ca6e80517080492e87f Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 25 Mar 2023 12:43:53 +0100 Subject: [PATCH 4072/5631] dt-bindings: mfd: x-powers,axp152: Simplify disallowing properties The syntax to disallow x-powers,drive-vbus-en, x-powers,self-working-mode and x-powers,master-mode for certain variants can be made simpler. Also this produces much nicer warning message when the condition hits wrong DTS. Signed-off-by: Krzysztof Kozlowski Acked-by: Chen-Yu Tsai Reviewed-by: Andre Przywara Tested-by: Andre Przywara Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230325114353.50293-1-krzysztof.kozlowski@linaro.org --- .../devicetree/bindings/mfd/x-powers,axp152.yaml | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml index b7a8747d5fa0..2691ac08f536 100644 --- a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml +++ b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml @@ -47,9 +47,8 @@ allOf: - x-powers,axp209 then: - not: - required: - - x-powers,drive-vbus-en + properties: + x-powers,drive-vbus-en: false - if: not: @@ -59,14 +58,9 @@ allOf: const: x-powers,axp806 then: - allOf: - - not: - required: - - x-powers,self-working-mode - - - not: - required: - - x-powers,master-mode + properties: + x-powers,self-working-mode: false + x-powers,master-mode: false - if: not: -- GitLab From 2405fbfb384ef39e9560d76d3f6e4c90519f90aa Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 29 Mar 2023 22:55:44 +0200 Subject: [PATCH 4073/5631] mfd: axp20x: Fix axp288 writable-ranges Register AXP288_POWER_REASON is writable and needs to be written to reset the reset- / power-on-reason bits. Add it to the axp288 writable-ranges so that the extcon-axp288 driver can properly clear the reset- / power-on-reason bits. Signed-off-by: Hans de Goede Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230329205544.1051393-1-hdegoede@redhat.com --- drivers/mfd/axp20x.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index 01a6bbb6d266..7720ac15c7d4 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -119,6 +119,7 @@ static const struct regmap_access_table axp22x_volatile_table = { /* AXP288 ranges are shared with the AXP803, as they cover the same range */ static const struct regmap_range axp288_writeable_ranges[] = { + regmap_reg_range(AXP288_POWER_REASON, AXP288_POWER_REASON), regmap_reg_range(AXP20X_DATACACHE(0), AXP20X_IRQ6_STATE), regmap_reg_range(AXP20X_DCDC_MODE, AXP288_FG_TUNE5), }; -- GitLab From 96da8f148396329ba769246cb8ceaa35f1ddfc48 Mon Sep 17 00:00:00 2001 From: Qiang Ning Date: Thu, 30 Mar 2023 10:43:53 +0800 Subject: [PATCH 4074/5631] mfd: dln2: Fix memory leak in dln2_probe() When dln2_setup_rx_urbs() in dln2_probe() fails, error out_free forgets to call usb_put_dev() to decrease the refcount of dln2->usb_dev. Fix this by adding usb_put_dev() in the error handling code of dln2_probe(). Signed-off-by: Qiang Ning Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330024353.4503-1-qning0106@126.com --- drivers/mfd/dln2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c index 6cd0b0c752d6..c3149729cec2 100644 --- a/drivers/mfd/dln2.c +++ b/drivers/mfd/dln2.c @@ -827,6 +827,7 @@ static int dln2_probe(struct usb_interface *interface, dln2_stop_rx_urbs(dln2); out_free: + usb_put_dev(dln2->usb_dev); dln2_free(dln2); return ret; -- GitLab From 72d4a1683741ee578da0e265886e6a7f3d42266c Mon Sep 17 00:00:00 2001 From: Jarkko Nikula Date: Thu, 30 Mar 2023 16:26:18 +0300 Subject: [PATCH 4075/5631] mfd: intel-lpss: Add Intel Meteor Lake PCH-S LPSS PCI IDs Add Intel Meteor Lake PCH-S also called as Meteor Point-S LPSS PCI IDs. Signed-off-by: Jarkko Nikula Acked-by: Andy Shevchenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330132618.4108665-1-jarkko.nikula@linux.intel.com --- drivers/mfd/intel-lpss-pci.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c index dde31c50a632..699f44ffff0e 100644 --- a/drivers/mfd/intel-lpss-pci.c +++ b/drivers/mfd/intel-lpss-pci.c @@ -447,6 +447,21 @@ static const struct pci_device_id intel_lpss_pci_ids[] = { { PCI_VDEVICE(INTEL, 0x7e79), (kernel_ulong_t)&bxt_i2c_info }, { PCI_VDEVICE(INTEL, 0x7e7a), (kernel_ulong_t)&bxt_i2c_info }, { PCI_VDEVICE(INTEL, 0x7e7b), (kernel_ulong_t)&bxt_i2c_info }, + /* MTP-S */ + { PCI_VDEVICE(INTEL, 0x7f28), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0x7f29), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0x7f2a), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0x7f2b), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0x7f4c), (kernel_ulong_t)&bxt_i2c_info }, + { PCI_VDEVICE(INTEL, 0x7f4d), (kernel_ulong_t)&bxt_i2c_info }, + { PCI_VDEVICE(INTEL, 0x7f4e), (kernel_ulong_t)&bxt_i2c_info }, + { PCI_VDEVICE(INTEL, 0x7f4f), (kernel_ulong_t)&bxt_i2c_info }, + { PCI_VDEVICE(INTEL, 0x7f5c), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0x7f5d), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0x7f5e), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0x7f5f), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0x7f7a), (kernel_ulong_t)&bxt_i2c_info }, + { PCI_VDEVICE(INTEL, 0x7f7b), (kernel_ulong_t)&bxt_i2c_info }, /* LKF */ { PCI_VDEVICE(INTEL, 0x98a8), (kernel_ulong_t)&bxt_uart_info }, { PCI_VDEVICE(INTEL, 0x98a9), (kernel_ulong_t)&bxt_uart_info }, -- GitLab From a29f5a3eeb81717245d28f9fc212229f5407c8d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 31 Mar 2023 09:03:44 +0200 Subject: [PATCH 4076/5631] mfd: rsmu_i2c: Convert to i2c's .probe_new() again MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit reapplies commit 601e6d48ee35 ("mfd: rsmu_i2c: Convert to i2c's .probe_new()") which was accidently reverted by commit 1b3b1d6c27cc ("mfd: rsmu: Support 32-bit address space"). Without this change the driver fails to build in combination with commit 03c835f498b5 ("i2c: Switch .probe() to not take an id parameter") which is contained in v6.3-rc2. Fixes: 1b3b1d6c27cc ("mfd: rsmu: Support 32-bit address space") Signed-off-by: Uwe Kleine-König Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230331070344.czphnnmvu2ojzo5l@pengutronix.de --- drivers/mfd/rsmu_i2c.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/mfd/rsmu_i2c.c b/drivers/mfd/rsmu_i2c.c index 221023faaadf..807c32101460 100644 --- a/drivers/mfd/rsmu_i2c.c +++ b/drivers/mfd/rsmu_i2c.c @@ -201,9 +201,9 @@ static const struct regmap_config rsmu_sl_regmap_config = { .can_multi_write = true, }; -static int rsmu_i2c_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int rsmu_i2c_probe(struct i2c_client *client) { + const struct i2c_device_id *id = i2c_client_get_device_id(client); const struct regmap_config *cfg; struct rsmu_ddata *rsmu; int ret; @@ -279,7 +279,7 @@ static struct i2c_driver rsmu_i2c_driver = { .name = "rsmu-i2c", .of_match_table = of_match_ptr(rsmu_i2c_of_match), }, - .probe = rsmu_i2c_probe, + .probe_new = rsmu_i2c_probe, .remove = rsmu_i2c_remove, .id_table = rsmu_i2c_id, }; -- GitLab From 0a9d6b54297e216199cbfd08c5e6a35cce152477 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:27 +0100 Subject: [PATCH 4077/5631] dt-bindings: timer: Document RZ/G2L MTU3a bindings The RZ/G2L multi-function timer pulse unit 3 (MTU3a) is embedded in the Renesas RZ/G2L family SoC's. It consists of eight 16-bit timer channels and one 32-bit timer channel. It supports the following functions - Counter - Timer - PWM Signed-off-by: Biju Das Reviewed-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-2-biju.das.jz@bp.renesas.com --- .../bindings/timer/renesas,rz-mtu3.yaml | 302 ++++++++++++++++++ 1 file changed, 302 insertions(+) create mode 100644 Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml diff --git a/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml new file mode 100644 index 000000000000..bffdab0b0185 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml @@ -0,0 +1,302 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/renesas,rz-mtu3.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Renesas RZ/G2L Multi-Function Timer Pulse Unit 3 (MTU3a) + +maintainers: + - Biju Das + +description: | + This hardware block consists of eight 16-bit timer channels and one + 32- bit timer channel. It supports the following specifications: + - Pulse input/output: 28 lines max. + - Pulse input 3 lines + - Count clock 11 clocks for each channel (14 clocks for MTU0, 12 clocks + for MTU2, and 10 clocks for MTU5, four clocks for MTU1-MTU2 combination + (when LWA = 1)) + - Operating frequency Up to 100 MHz + - Available operations [MTU0 to MTU4, MTU6, MTU7, and MTU8] + - Waveform output on compare match + - Input capture function (noise filter setting available) + - Counter-clearing operation + - Simultaneous writing to multiple timer counters (TCNT) + (excluding MTU8). + - Simultaneous clearing on compare match or input capture + (excluding MTU8). + - Simultaneous input and output to registers in synchronization with + counter operations (excluding MTU8). + - Up to 12-phase PWM output in combination with synchronous operation + (excluding MTU8) + - [MTU0 MTU3, MTU4, MTU6, MTU7, and MTU8] + - Buffer operation specifiable + - [MTU1, MTU2] + - Phase counting mode can be specified independently + - 32-bit phase counting mode can be specified for interlocked operation + of MTU1 and MTU2 (when TMDR3.LWA = 1) + - Cascade connection operation available + - [MTU3, MTU4, MTU6, and MTU7] + - Through interlocked operation of MTU3/4 and MTU6/7, the positive and + negative signals in six phases (12 phases in total) can be output in + complementary PWM and reset-synchronized PWM operation. + - In complementary PWM mode, values can be transferred from buffer + registers to temporary registers at crests and troughs of the timer- + counter values or when the buffer registers (TGRD registers in MTU4 + and MTU7) are written to. + - Double-buffering selectable in complementary PWM mode. + - [MTU3 and MTU4] + - Through interlocking with MTU0, a mode for driving AC synchronous + motors (brushless DC motors) by using complementary PWM output and + reset-synchronized PWM output is settable and allows the selection + of two types of waveform output (chopping or level). + - [MTU5] + - Capable of operation as a dead-time compensation counter. + - [MTU0/MTU5, MTU1, MTU2, and MTU8] + - 32-bit phase counting mode specifiable by combining MTU1 and MTU2 and + through interlocked operation with MTU0/MTU5 and MTU8. + - Interrupt-skipping function + - In complementary PWM mode, interrupts on crests and troughs of counter + values and triggers to start conversion by the A/D converter can be + skipped. + - Interrupt sources: 43 sources. + - Buffer operation: + - Automatic transfer of register data (transfer from the buffer + register to the timer register). + - Trigger generation + - A/D converter start triggers can be generated + - A/D converter start request delaying function enables A/D converter + to be started with any desired timing and to be synchronized with + PWM output. + - Low power consumption function + - The MTU3a can be placed in the module-stop state. + + There are two phase counting modes. 16-bit phase counting mode in which + MTU1 and MTU2 operate independently, and cascade connection 32-bit phase + counting mode in which MTU1 and MTU2 are cascaded. + + In phase counting mode, the phase difference between two external input + clocks is detected and the corresponding TCNT is incremented or + decremented. + The below counters are supported + count0 - MTU1 16-bit phase counting + count1 - MTU2 16-bit phase counting + count2 - MTU1+ MTU2 32-bit phase counting + + The module supports PWM mode{1,2}, Reset-synchronized PWM mode and + complementary PWM mode{1,2,3}. + + In complementary PWM mode, six positive-phase and six negative-phase PWM + waveforms (12 phases in total) with dead time can be output by + combining MTU{3,4} and MTU{6,7}. + + The below pwm channels are supported in pwm mode 1. + pwm0 - MTU0.MTIOC0A PWM mode 1 + pwm1 - MTU0.MTIOC0C PWM mode 1 + pwm2 - MTU1.MTIOC1A PWM mode 1 + pwm3 - MTU2.MTIOC2A PWM mode 1 + pwm4 - MTU3.MTIOC3A PWM mode 1 + pwm5 - MTU3.MTIOC3C PWM mode 1 + pwm6 - MTU4.MTIOC4A PWM mode 1 + pwm7 - MTU4.MTIOC4C PWM mode 1 + pwm8 - MTU6.MTIOC6A PWM mode 1 + pwm9 - MTU6.MTIOC6C PWM mode 1 + pwm10 - MTU7.MTIOC7A PWM mode 1 + pwm11 - MTU7.MTIOC7C PWM mode 1 + +properties: + compatible: + items: + - enum: + - renesas,r9a07g044-mtu3 # RZ/G2{L,LC} + - renesas,r9a07g054-mtu3 # RZ/V2L + - const: renesas,rz-mtu3 + + reg: + maxItems: 1 + + interrupts: + items: + - description: MTU0.TGRA input capture/compare match + - description: MTU0.TGRB input capture/compare match + - description: MTU0.TGRC input capture/compare match + - description: MTU0.TGRD input capture/compare match + - description: MTU0.TCNT overflow + - description: MTU0.TGRE compare match + - description: MTU0.TGRF compare match + - description: MTU1.TGRA input capture/compare match + - description: MTU1.TGRB input capture/compare match + - description: MTU1.TCNT overflow + - description: MTU1.TCNT underflow + - description: MTU2.TGRA input capture/compare match + - description: MTU2.TGRB input capture/compare match + - description: MTU2.TCNT overflow + - description: MTU2.TCNT underflow + - description: MTU3.TGRA input capture/compare match + - description: MTU3.TGRB input capture/compare match + - description: MTU3.TGRC input capture/compare match + - description: MTU3.TGRD input capture/compare match + - description: MTU3.TCNT overflow + - description: MTU4.TGRA input capture/compare match + - description: MTU4.TGRB input capture/compare match + - description: MTU4.TGRC input capture/compare match + - description: MTU4.TGRD input capture/compare match + - description: MTU4.TCNT overflow/underflow + - description: MTU5.TGRU input capture/compare match + - description: MTU5.TGRV input capture/compare match + - description: MTU5.TGRW input capture/compare match + - description: MTU6.TGRA input capture/compare match + - description: MTU6.TGRB input capture/compare match + - description: MTU6.TGRC input capture/compare match + - description: MTU6.TGRD input capture/compare match + - description: MTU6.TCNT overflow + - description: MTU7.TGRA input capture/compare match + - description: MTU7.TGRB input capture/compare match + - description: MTU7.TGRC input capture/compare match + - description: MTU7.TGRD input capture/compare match + - description: MTU7.TCNT overflow/underflow + - description: MTU8.TGRA input capture/compare match + - description: MTU8.TGRB input capture/compare match + - description: MTU8.TGRC input capture/compare match + - description: MTU8.TGRD input capture/compare match + - description: MTU8.TCNT overflow + - description: MTU8.TCNT underflow + + interrupt-names: + items: + - const: tgia0 + - const: tgib0 + - const: tgic0 + - const: tgid0 + - const: tgiv0 + - const: tgie0 + - const: tgif0 + - const: tgia1 + - const: tgib1 + - const: tgiv1 + - const: tgiu1 + - const: tgia2 + - const: tgib2 + - const: tgiv2 + - const: tgiu2 + - const: tgia3 + - const: tgib3 + - const: tgic3 + - const: tgid3 + - const: tgiv3 + - const: tgia4 + - const: tgib4 + - const: tgic4 + - const: tgid4 + - const: tgiv4 + - const: tgiu5 + - const: tgiv5 + - const: tgiw5 + - const: tgia6 + - const: tgib6 + - const: tgic6 + - const: tgid6 + - const: tgiv6 + - const: tgia7 + - const: tgib7 + - const: tgic7 + - const: tgid7 + - const: tgiv7 + - const: tgia8 + - const: tgib8 + - const: tgic8 + - const: tgid8 + - const: tgiv8 + - const: tgiu8 + + clocks: + maxItems: 1 + + power-domains: + maxItems: 1 + + resets: + maxItems: 1 + + "#pwm-cells": + const: 2 + +required: + - compatible + - reg + - interrupts + - interrupt-names + - clocks + - power-domains + - resets + +additionalProperties: false + +examples: + - | + #include + #include + + mtu3: timer@10001200 { + compatible = "renesas,r9a07g044-mtu3", "renesas,rz-mtu3"; + reg = <0x10001200 0xb00>; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", "tgiv0", "tgie0", + "tgif0", + "tgia1", "tgib1", "tgiv1", "tgiu1", + "tgia2", "tgib2", "tgiv2", "tgiu2", + "tgia3", "tgib3", "tgic3", "tgid3", "tgiv3", + "tgia4", "tgib4", "tgic4", "tgid4", "tgiv4", + "tgiu5", "tgiv5", "tgiw5", + "tgia6", "tgib6", "tgic6", "tgid6", "tgiv6", + "tgia7", "tgib7", "tgic7", "tgid7", "tgiv7", + "tgia8", "tgib8", "tgic8", "tgid8", "tgiv8", "tgiu8"; + clocks = <&cpg CPG_MOD R9A07G044_MTU_X_MCK_MTU3>; + power-domains = <&cpg>; + resets = <&cpg R9A07G044_MTU_X_PRESET_MTU3>; + #pwm-cells = <2>; + }; -- GitLab From 654c293e1687b31819f9bf1ac71b5a85a8053210 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:28 +0100 Subject: [PATCH 4078/5631] mfd: Add Renesas RZ/G2L MTU3a core driver The RZ/G2L multi-function timer pulse unit 3 (MTU3a) is embedded in the Renesas RZ/G2L family SoCs. It consists of eight 16-bit timer channels and one 32-bit timer channel. It supports the following functions - Counter - Timer - PWM The 8/16/32 bit registers are mixed in each channel. Add MTU3a core driver for RZ/G2L SoC. The core driver shares the clk and channel register access for the other child devices like Counter, PWM and Clock event. Signed-off-by: Biju Das Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-3-biju.das.jz@bp.renesas.com --- drivers/mfd/Kconfig | 10 + drivers/mfd/Makefile | 1 + drivers/mfd/rz-mtu3.c | 391 ++++++++++++++++++++++++++++++++++++ drivers/mfd/rz-mtu3.h | 147 ++++++++++++++ include/linux/mfd/rz-mtu3.h | 257 ++++++++++++++++++++++++ 5 files changed, 806 insertions(+) create mode 100644 drivers/mfd/rz-mtu3.c create mode 100644 drivers/mfd/rz-mtu3.h create mode 100644 include/linux/mfd/rz-mtu3.h diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 51d54a1b8673..e90463c4441c 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1315,6 +1315,16 @@ config MFD_SC27XX_PMIC This driver provides common support for accessing the SC27xx PMICs, and it also adds the irq_chip parts for handling the PMIC chip events. +config RZ_MTU3 + bool "Renesas RZ/G2L MTU3a core driver" + depends on (ARCH_RZG2L && OF) || COMPILE_TEST + help + Select this option to enable Renesas RZ/G2L MTU3a core driver for + the Multi-Function Timer Pulse Unit 3 (MTU3a) hardware available + on SoCs from Renesas. The core driver shares the clk and channel + register access for the other child devices like Counter, PWM, + Clock Source, and Clock event. + config ABX500_CORE bool "ST-Ericsson ABX500 Mixed Signal Circuit register functions" depends on ARCH_U8500 || COMPILE_TEST diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 2f6c89d1e277..1d2392f06f78 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -174,6 +174,7 @@ pcf50633-objs := pcf50633-core.o pcf50633-irq.o obj-$(CONFIG_MFD_PCF50633) += pcf50633.o obj-$(CONFIG_PCF50633_ADC) += pcf50633-adc.o obj-$(CONFIG_PCF50633_GPIO) += pcf50633-gpio.o +obj-$(CONFIG_RZ_MTU3) += rz-mtu3.o obj-$(CONFIG_ABX500_CORE) += abx500-core.o obj-$(CONFIG_MFD_DB8500_PRCMU) += db8500-prcmu.o # ab8500-core need to come after db8500-prcmu (which provides the channel) diff --git a/drivers/mfd/rz-mtu3.c b/drivers/mfd/rz-mtu3.c new file mode 100644 index 000000000000..04006f4aa702 --- /dev/null +++ b/drivers/mfd/rz-mtu3.c @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Renesas RZ/G2L Multi-Function Timer Pulse Unit 3(MTU3a) Core driver + * + * Copyright (C) 2023 Renesas Electronics Corporation + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rz-mtu3.h" + +struct rz_mtu3_priv { + void __iomem *mmio; + struct reset_control *rstc; + raw_spinlock_t lock; +}; + +/******* MTU3 registers (original offset is +0x1200) *******/ +static const unsigned long rz_mtu3_8bit_ch_reg_offs[][13] = { + [RZ_MTU3_CHAN_0] = MTU_8BIT_CH_0(0x104, 0x090, 0x100, 0x128, 0x101, 0x102, 0x103, 0x126), + [RZ_MTU3_CHAN_1] = MTU_8BIT_CH_1_2(0x184, 0x091, 0x185, 0x180, 0x194, 0x181, 0x182), + [RZ_MTU3_CHAN_2] = MTU_8BIT_CH_1_2(0x204, 0x092, 0x205, 0x200, 0x20c, 0x201, 0x202), + [RZ_MTU3_CHAN_3] = MTU_8BIT_CH_3_4_6_7(0x008, 0x093, 0x02c, 0x000, 0x04c, 0x002, 0x004, 0x005, 0x038), + [RZ_MTU3_CHAN_4] = MTU_8BIT_CH_3_4_6_7(0x009, 0x094, 0x02d, 0x001, 0x04d, 0x003, 0x006, 0x007, 0x039), + [RZ_MTU3_CHAN_5] = MTU_8BIT_CH_5(0xab2, 0x1eb, 0xab4, 0xab6, 0xa84, 0xa85, 0xa86, 0xa94, 0xa95, 0xa96, 0xaa4, 0xaa5, 0xaa6), + [RZ_MTU3_CHAN_6] = MTU_8BIT_CH_3_4_6_7(0x808, 0x893, 0x82c, 0x800, 0x84c, 0x802, 0x804, 0x805, 0x838), + [RZ_MTU3_CHAN_7] = MTU_8BIT_CH_3_4_6_7(0x809, 0x894, 0x82d, 0x801, 0x84d, 0x803, 0x806, 0x807, 0x839), + [RZ_MTU3_CHAN_8] = MTU_8BIT_CH_8(0x404, 0x098, 0x400, 0x406, 0x401, 0x402, 0x403) +}; + +static const unsigned long rz_mtu3_16bit_ch_reg_offs[][12] = { + [RZ_MTU3_CHAN_0] = MTU_16BIT_CH_0(0x106, 0x108, 0x10a, 0x10c, 0x10e, 0x120, 0x122), + [RZ_MTU3_CHAN_1] = MTU_16BIT_CH_1_2(0x186, 0x188, 0x18a), + [RZ_MTU3_CHAN_2] = MTU_16BIT_CH_1_2(0x206, 0x208, 0x20a), + [RZ_MTU3_CHAN_3] = MTU_16BIT_CH_3_6(0x010, 0x018, 0x01a, 0x024, 0x026, 0x072), + [RZ_MTU3_CHAN_4] = MTU_16BIT_CH_4_7(0x012, 0x01c, 0x01e, 0x028, 0x2a, 0x074, 0x076, 0x040, 0x044, 0x046, 0x048, 0x04a), + [RZ_MTU3_CHAN_5] = MTU_16BIT_CH_5(0xa80, 0xa82, 0xa90, 0xa92, 0xaa0, 0xaa2), + [RZ_MTU3_CHAN_6] = MTU_16BIT_CH_3_6(0x810, 0x818, 0x81a, 0x824, 0x826, 0x872), + [RZ_MTU3_CHAN_7] = MTU_16BIT_CH_4_7(0x812, 0x81c, 0x81e, 0x828, 0x82a, 0x874, 0x876, 0x840, 0x844, 0x846, 0x848, 0x84a) +}; + +static const unsigned long rz_mtu3_32bit_ch_reg_offs[][5] = { + [RZ_MTU3_CHAN_1] = MTU_32BIT_CH_1(0x1a0, 0x1a4, 0x1a8), + [RZ_MTU3_CHAN_8] = MTU_32BIT_CH_8(0x408, 0x40c, 0x410, 0x414, 0x418) +}; + +static bool rz_mtu3_is_16bit_shared_reg(u16 offset) +{ + return (offset == RZ_MTU3_TDDRA || offset == RZ_MTU3_TDDRB || + offset == RZ_MTU3_TCDRA || offset == RZ_MTU3_TCDRB || + offset == RZ_MTU3_TCBRA || offset == RZ_MTU3_TCBRB || + offset == RZ_MTU3_TCNTSA || offset == RZ_MTU3_TCNTSB); +} + +u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 offset) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + + if (rz_mtu3_is_16bit_shared_reg(offset)) + return readw(priv->mmio + offset); + else + return readb(priv->mmio + offset); +} +EXPORT_SYMBOL_GPL(rz_mtu3_shared_reg_read); + +u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 offset) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + ch_offs = rz_mtu3_8bit_ch_reg_offs[ch->channel_number][offset]; + + return readb(priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_8bit_ch_read); + +u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 offset) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + /* MTU8 doesn't have 16-bit registers */ + if (ch->channel_number == RZ_MTU3_CHAN_8) + return 0; + + ch_offs = rz_mtu3_16bit_ch_reg_offs[ch->channel_number][offset]; + + return readw(priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_16bit_ch_read); + +u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 offset) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + if (ch->channel_number != RZ_MTU3_CHAN_1 && ch->channel_number != RZ_MTU3_CHAN_8) + return 0; + + ch_offs = rz_mtu3_32bit_ch_reg_offs[ch->channel_number][offset]; + + return readl(priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_32bit_ch_read); + +void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 offset, u8 val) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + ch_offs = rz_mtu3_8bit_ch_reg_offs[ch->channel_number][offset]; + writeb(val, priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_8bit_ch_write); + +void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 offset, u16 val) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + /* MTU8 doesn't have 16-bit registers */ + if (ch->channel_number == RZ_MTU3_CHAN_8) + return; + + ch_offs = rz_mtu3_16bit_ch_reg_offs[ch->channel_number][offset]; + writew(val, priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_16bit_ch_write); + +void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 offset, u32 val) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + u16 ch_offs; + + if (ch->channel_number != RZ_MTU3_CHAN_1 && ch->channel_number != RZ_MTU3_CHAN_8) + return; + + ch_offs = rz_mtu3_32bit_ch_reg_offs[ch->channel_number][offset]; + writel(val, priv->mmio + ch_offs); +} +EXPORT_SYMBOL_GPL(rz_mtu3_32bit_ch_write); + +void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 offset, u16 value) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + + if (rz_mtu3_is_16bit_shared_reg(offset)) + writew(value, priv->mmio + offset); + else + writeb((u8)value, priv->mmio + offset); +} +EXPORT_SYMBOL_GPL(rz_mtu3_shared_reg_write); + +void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, u16 offset, + u16 pos, u8 val) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + unsigned long tmdr, flags; + + raw_spin_lock_irqsave(&priv->lock, flags); + tmdr = rz_mtu3_shared_reg_read(ch, offset); + __assign_bit(pos, &tmdr, !!val); + rz_mtu3_shared_reg_write(ch, offset, tmdr); + raw_spin_unlock_irqrestore(&priv->lock, flags); +} +EXPORT_SYMBOL_GPL(rz_mtu3_shared_reg_update_bit); + +static u16 rz_mtu3_get_tstr_offset(struct rz_mtu3_channel *ch) +{ + u16 offset; + + switch (ch->channel_number) { + case RZ_MTU3_CHAN_0: + case RZ_MTU3_CHAN_1: + case RZ_MTU3_CHAN_2: + case RZ_MTU3_CHAN_3: + case RZ_MTU3_CHAN_4: + case RZ_MTU3_CHAN_8: + offset = RZ_MTU3_TSTRA; + break; + case RZ_MTU3_CHAN_5: + offset = RZ_MTU3_TSTR; + break; + case RZ_MTU3_CHAN_6: + case RZ_MTU3_CHAN_7: + offset = RZ_MTU3_TSTRB; + break; + default: + offset = 0; + break; + } + + return offset; +} + +static u8 rz_mtu3_get_tstr_bit_pos(struct rz_mtu3_channel *ch) +{ + u8 bitpos; + + switch (ch->channel_number) { + case RZ_MTU3_CHAN_0: + case RZ_MTU3_CHAN_1: + case RZ_MTU3_CHAN_2: + case RZ_MTU3_CHAN_6: + case RZ_MTU3_CHAN_7: + bitpos = ch->channel_number; + break; + case RZ_MTU3_CHAN_3: + bitpos = 6; + break; + case RZ_MTU3_CHAN_4: + bitpos = 7; + break; + case RZ_MTU3_CHAN_5: + bitpos = 2; + break; + case RZ_MTU3_CHAN_8: + bitpos = 3; + break; + default: + bitpos = 0; + break; + } + + return bitpos; +} + +static void rz_mtu3_start_stop_ch(struct rz_mtu3_channel *ch, bool start) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + unsigned long flags, tstr; + u16 offset; + u8 bitpos; + + /* start stop register shared by multiple timer channels */ + raw_spin_lock_irqsave(&priv->lock, flags); + + offset = rz_mtu3_get_tstr_offset(ch); + bitpos = rz_mtu3_get_tstr_bit_pos(ch); + tstr = rz_mtu3_shared_reg_read(ch, offset); + __assign_bit(bitpos, &tstr, start); + rz_mtu3_shared_reg_write(ch, offset, tstr); + + raw_spin_unlock_irqrestore(&priv->lock, flags); +} + +bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(ch->dev->parent); + struct rz_mtu3_priv *priv = mtu->priv_data; + unsigned long flags, tstr; + bool ret = false; + u16 offset; + u8 bitpos; + + /* start stop register shared by multiple timer channels */ + raw_spin_lock_irqsave(&priv->lock, flags); + + offset = rz_mtu3_get_tstr_offset(ch); + bitpos = rz_mtu3_get_tstr_bit_pos(ch); + tstr = rz_mtu3_shared_reg_read(ch, offset); + ret = tstr & BIT(bitpos); + + raw_spin_unlock_irqrestore(&priv->lock, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(rz_mtu3_is_enabled); + +int rz_mtu3_enable(struct rz_mtu3_channel *ch) +{ + /* enable channel */ + rz_mtu3_start_stop_ch(ch, true); + + return 0; +} +EXPORT_SYMBOL_GPL(rz_mtu3_enable); + +void rz_mtu3_disable(struct rz_mtu3_channel *ch) +{ + /* disable channel */ + rz_mtu3_start_stop_ch(ch, false); +} +EXPORT_SYMBOL_GPL(rz_mtu3_disable); + +static void rz_mtu3_reset_assert(void *data) +{ + struct rz_mtu3 *mtu = dev_get_drvdata(data); + struct rz_mtu3_priv *priv = mtu->priv_data; + + mfd_remove_devices(data); + reset_control_assert(priv->rstc); +} + +static const struct mfd_cell rz_mtu3_devs[] = { + { + .name = "rz-mtu3-counter", + }, + { + .name = "pwm-rz-mtu3", + }, +}; + +static int rz_mtu3_probe(struct platform_device *pdev) +{ + struct rz_mtu3_priv *priv; + struct rz_mtu3 *ddata; + unsigned int i; + int ret; + + ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + ddata->priv_data = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!ddata->priv_data) + return -ENOMEM; + + priv = ddata->priv_data; + + priv->mmio = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(priv->mmio)) + return PTR_ERR(priv->mmio); + + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(priv->rstc)) + return PTR_ERR(priv->rstc); + + ddata->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(ddata->clk)) + return PTR_ERR(ddata->clk); + + reset_control_deassert(priv->rstc); + raw_spin_lock_init(&priv->lock); + platform_set_drvdata(pdev, ddata); + + for (i = 0; i < RZ_MTU_NUM_CHANNELS; i++) { + ddata->channels[i].channel_number = i; + ddata->channels[i].is_busy = false; + mutex_init(&ddata->channels[i].lock); + } + + ret = mfd_add_devices(&pdev->dev, 0, rz_mtu3_devs, + ARRAY_SIZE(rz_mtu3_devs), NULL, 0, NULL); + if (ret < 0) + goto err_assert; + + return devm_add_action_or_reset(&pdev->dev, rz_mtu3_reset_assert, + &pdev->dev); + +err_assert: + reset_control_assert(priv->rstc); + return ret; +} + +static const struct of_device_id rz_mtu3_of_match[] = { + { .compatible = "renesas,rz-mtu3", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, rz_mtu3_of_match); + +static struct platform_driver rz_mtu3_driver = { + .probe = rz_mtu3_probe, + .driver = { + .name = "rz-mtu3", + .of_match_table = rz_mtu3_of_match, + }, +}; +module_platform_driver(rz_mtu3_driver); + +MODULE_AUTHOR("Biju Das "); +MODULE_DESCRIPTION("Renesas RZ/G2L MTU3a Core Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/mfd/rz-mtu3.h b/drivers/mfd/rz-mtu3.h new file mode 100644 index 000000000000..51a1298b0613 --- /dev/null +++ b/drivers/mfd/rz-mtu3.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * MFD internals for Renesas RZ/G2L MTU3 Core driver + * + * Copyright (C) 2023 Renesas Electronics Corporation + */ + +#ifndef RZ_MTU3_MFD_H +#define RZ_MTU3_MFD_H + +#define MTU_8BIT_CH_0(_tier, _nfcr, _tcr, _tcr2, _tmdr1, _tiorh, _tiorl, _tbtm) \ + { \ + [RZ_MTU3_TIER] = _tier, \ + [RZ_MTU3_NFCR] = _nfcr, \ + [RZ_MTU3_TCR] = _tcr, \ + [RZ_MTU3_TCR2] = _tcr2, \ + [RZ_MTU3_TMDR1] = _tmdr1, \ + [RZ_MTU3_TIORH] = _tiorh, \ + [RZ_MTU3_TIORL] = _tiorl, \ + [RZ_MTU3_TBTM] = _tbtm \ + } + +#define MTU_8BIT_CH_1_2(_tier, _nfcr, _tsr, _tcr, _tcr2, _tmdr1, _tior) \ + { \ + [RZ_MTU3_TIER] = _tier, \ + [RZ_MTU3_NFCR] = _nfcr, \ + [RZ_MTU3_TSR] = _tsr, \ + [RZ_MTU3_TCR] = _tcr, \ + [RZ_MTU3_TCR2] = _tcr2, \ + [RZ_MTU3_TMDR1] = _tmdr1, \ + [RZ_MTU3_TIOR] = _tior \ + } \ + +#define MTU_8BIT_CH_3_4_6_7(_tier, _nfcr, _tsr, _tcr, _tcr2, _tmdr1, _tiorh, _tiorl, _tbtm) \ + { \ + [RZ_MTU3_TIER] = _tier, \ + [RZ_MTU3_NFCR] = _nfcr, \ + [RZ_MTU3_TSR] = _tsr, \ + [RZ_MTU3_TCR] = _tcr, \ + [RZ_MTU3_TCR2] = _tcr2, \ + [RZ_MTU3_TMDR1] = _tmdr1, \ + [RZ_MTU3_TIORH] = _tiorh, \ + [RZ_MTU3_TIORL] = _tiorl, \ + [RZ_MTU3_TBTM] = _tbtm \ + } \ + +#define MTU_8BIT_CH_5(_tier, _nfcr, _tstr, _tcntcmpclr, _tcru, _tcr2u, _tioru, \ + _tcrv, _tcr2v, _tiorv, _tcrw, _tcr2w, _tiorw) \ + { \ + [RZ_MTU3_TIER] = _tier, \ + [RZ_MTU3_NFCR] = _nfcr, \ + [RZ_MTU3_TSTR] = _tstr, \ + [RZ_MTU3_TCNTCMPCLR] = _tcntcmpclr, \ + [RZ_MTU3_TCRU] = _tcru, \ + [RZ_MTU3_TCR2U] = _tcr2u, \ + [RZ_MTU3_TIORU] = _tioru, \ + [RZ_MTU3_TCRV] = _tcrv, \ + [RZ_MTU3_TCR2V] = _tcr2v, \ + [RZ_MTU3_TIORV] = _tiorv, \ + [RZ_MTU3_TCRW] = _tcrw, \ + [RZ_MTU3_TCR2W] = _tcr2w, \ + [RZ_MTU3_TIORW] = _tiorw \ + } \ + +#define MTU_8BIT_CH_8(_tier, _nfcr, _tcr, _tcr2, _tmdr1, _tiorh, _tiorl) \ + { \ + [RZ_MTU3_TIER] = _tier, \ + [RZ_MTU3_NFCR] = _nfcr, \ + [RZ_MTU3_TCR] = _tcr, \ + [RZ_MTU3_TCR2] = _tcr2, \ + [RZ_MTU3_TMDR1] = _tmdr1, \ + [RZ_MTU3_TIORH] = _tiorh, \ + [RZ_MTU3_TIORL] = _tiorl \ + } \ + +#define MTU_16BIT_CH_0(_tcnt, _tgra, _tgrb, _tgrc, _tgrd, _tgre, _tgrf) \ + { \ + [RZ_MTU3_TCNT] = _tcnt, \ + [RZ_MTU3_TGRA] = _tgra, \ + [RZ_MTU3_TGRB] = _tgrb, \ + [RZ_MTU3_TGRC] = _tgrc, \ + [RZ_MTU3_TGRD] = _tgrd, \ + [RZ_MTU3_TGRE] = _tgre, \ + [RZ_MTU3_TGRF] = _tgrf \ + } + +#define MTU_16BIT_CH_1_2(_tcnt, _tgra, _tgrb) \ + { \ + [RZ_MTU3_TCNT] = _tcnt, \ + [RZ_MTU3_TGRA] = _tgra, \ + [RZ_MTU3_TGRB] = _tgrb \ + } + +#define MTU_16BIT_CH_3_6(_tcnt, _tgra, _tgrb, _tgrc, _tgrd, _tgre) \ + { \ + [RZ_MTU3_TCNT] = _tcnt, \ + [RZ_MTU3_TGRA] = _tgra, \ + [RZ_MTU3_TGRB] = _tgrb, \ + [RZ_MTU3_TGRC] = _tgrc, \ + [RZ_MTU3_TGRD] = _tgrd, \ + [RZ_MTU3_TGRE] = _tgre \ + } + +#define MTU_16BIT_CH_4_7(_tcnt, _tgra, _tgrb, _tgrc, _tgrd, _tgre, _tgrf, \ + _tadcr, _tadcora, _tadcorb, _tadcobra, _tadcobrb) \ + { \ + [RZ_MTU3_TCNT] = _tcnt, \ + [RZ_MTU3_TGRA] = _tgra, \ + [RZ_MTU3_TGRB] = _tgrb, \ + [RZ_MTU3_TGRC] = _tgrc, \ + [RZ_MTU3_TGRD] = _tgrd, \ + [RZ_MTU3_TGRE] = _tgre, \ + [RZ_MTU3_TGRF] = _tgrf, \ + [RZ_MTU3_TADCR] = _tadcr, \ + [RZ_MTU3_TADCORA] = _tadcora, \ + [RZ_MTU3_TADCORB] = _tadcorb, \ + [RZ_MTU3_TADCOBRA] = _tadcobra, \ + [RZ_MTU3_TADCOBRB] = _tadcobrb \ + } + +#define MTU_16BIT_CH_5(_tcntu, _tgru, _tcntv, _tgrv, _tcntw, _tgrw) \ + { \ + [RZ_MTU3_TCNTU] = _tcntu, \ + [RZ_MTU3_TGRU] = _tgru, \ + [RZ_MTU3_TCNTV] = _tcntv, \ + [RZ_MTU3_TGRV] = _tgrv, \ + [RZ_MTU3_TCNTW] = _tcntw, \ + [RZ_MTU3_TGRW] = _tgrw \ + } + +#define MTU_32BIT_CH_1(_tcntlw, _tgralw, _tgrblw) \ + { \ + [RZ_MTU3_TCNTLW] = _tcntlw, \ + [RZ_MTU3_TGRALW] = _tgralw, \ + [RZ_MTU3_TGRBLW] = _tgrblw \ + } + +#define MTU_32BIT_CH_8(_tcnt, _tgra, _tgrb, _tgrc, _tgrd) \ + { \ + [RZ_MTU3_TCNT] = _tcnt, \ + [RZ_MTU3_TGRA] = _tgra, \ + [RZ_MTU3_TGRB] = _tgrb, \ + [RZ_MTU3_TGRC] = _tgrc, \ + [RZ_MTU3_TGRD] = _tgrd \ + } + +#endif diff --git a/include/linux/mfd/rz-mtu3.h b/include/linux/mfd/rz-mtu3.h new file mode 100644 index 000000000000..c5173bc06270 --- /dev/null +++ b/include/linux/mfd/rz-mtu3.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Renesas Electronics Corporation + */ +#ifndef __MFD_RZ_MTU3_H__ +#define __MFD_RZ_MTU3_H__ + +#include +#include +#include + +/* 8-bit shared register offsets macros */ +#define RZ_MTU3_TSTRA 0x080 /* Timer start register A */ +#define RZ_MTU3_TSTRB 0x880 /* Timer start register B */ + +/* 16-bit shared register offset macros */ +#define RZ_MTU3_TDDRA 0x016 /* Timer dead time data register A */ +#define RZ_MTU3_TDDRB 0x816 /* Timer dead time data register B */ +#define RZ_MTU3_TCDRA 0x014 /* Timer cycle data register A */ +#define RZ_MTU3_TCDRB 0x814 /* Timer cycle data register B */ +#define RZ_MTU3_TCBRA 0x022 /* Timer cycle buffer register A */ +#define RZ_MTU3_TCBRB 0x822 /* Timer cycle buffer register B */ +#define RZ_MTU3_TCNTSA 0x020 /* Timer subcounter A */ +#define RZ_MTU3_TCNTSB 0x820 /* Timer subcounter B */ + +/* + * MTU5 contains 3 timer counter registers and is totaly different + * from other channels, so we must separate its offset + */ + +/* 8-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TIER 0 /* Timer interrupt register */ +#define RZ_MTU3_NFCR 1 /* Noise filter control register */ +#define RZ_MTU3_TSR 2 /* Timer status register */ +#define RZ_MTU3_TCR 3 /* Timer control register */ +#define RZ_MTU3_TCR2 4 /* Timer control register 2 */ + +/* Timer mode register 1 */ +#define RZ_MTU3_TMDR1 5 +#define RZ_MTU3_TMDR1_MD GENMASK(3, 0) +#define RZ_MTU3_TMDR1_MD_NORMAL FIELD_PREP(RZ_MTU3_TMDR1_MD, 0) +#define RZ_MTU3_TMDR1_MD_PWMMODE1 FIELD_PREP(RZ_MTU3_TMDR1_MD, 2) + +#define RZ_MTU3_TIOR 6 /* Timer I/O control register */ +#define RZ_MTU3_TIORH 6 /* Timer I/O control register H */ +#define RZ_MTU3_TIORL 7 /* Timer I/O control register L */ +/* Only MTU3/4/6/7 have TBTM registers */ +#define RZ_MTU3_TBTM 8 /* Timer buffer operation transfer mode register */ + +/* 8-bit MTU5 register offset macros */ +#define RZ_MTU3_TSTR 2 /* MTU5 Timer start register */ +#define RZ_MTU3_TCNTCMPCLR 3 /* MTU5 Timer compare match clear register */ +#define RZ_MTU3_TCRU 4 /* Timer control register U */ +#define RZ_MTU3_TCR2U 5 /* Timer control register 2U */ +#define RZ_MTU3_TIORU 6 /* Timer I/O control register U */ +#define RZ_MTU3_TCRV 7 /* Timer control register V */ +#define RZ_MTU3_TCR2V 8 /* Timer control register 2V */ +#define RZ_MTU3_TIORV 9 /* Timer I/O control register V */ +#define RZ_MTU3_TCRW 10 /* Timer control register W */ +#define RZ_MTU3_TCR2W 11 /* Timer control register 2W */ +#define RZ_MTU3_TIORW 12 /* Timer I/O control register W */ + +/* 16-bit register offset macros of MTU3 channels except MTU5 */ +#define RZ_MTU3_TCNT 0 /* Timer counter */ +#define RZ_MTU3_TGRA 1 /* Timer general register A */ +#define RZ_MTU3_TGRB 2 /* Timer general register B */ +#define RZ_MTU3_TGRC 3 /* Timer general register C */ +#define RZ_MTU3_TGRD 4 /* Timer general register D */ +#define RZ_MTU3_TGRE 5 /* Timer general register E */ +#define RZ_MTU3_TGRF 6 /* Timer general register F */ +/* Timer A/D converter start request registers */ +#define RZ_MTU3_TADCR 7 /* control register */ +#define RZ_MTU3_TADCORA 8 /* cycle set register A */ +#define RZ_MTU3_TADCORB 9 /* cycle set register B */ +#define RZ_MTU3_TADCOBRA 10 /* cycle set buffer register A */ +#define RZ_MTU3_TADCOBRB 11 /* cycle set buffer register B */ + +/* 16-bit MTU5 register offset macros */ +#define RZ_MTU3_TCNTU 0 /* MTU5 Timer counter U */ +#define RZ_MTU3_TGRU 1 /* MTU5 Timer general register U */ +#define RZ_MTU3_TCNTV 2 /* MTU5 Timer counter V */ +#define RZ_MTU3_TGRV 3 /* MTU5 Timer general register V */ +#define RZ_MTU3_TCNTW 4 /* MTU5 Timer counter W */ +#define RZ_MTU3_TGRW 5 /* MTU5 Timer general register W */ + +/* 32-bit register offset */ +#define RZ_MTU3_TCNTLW 0 /* Timer longword counter */ +#define RZ_MTU3_TGRALW 1 /* Timer longword general register A */ +#define RZ_MTU3_TGRBLW 2 /* Timer longowrd general register B */ + +#define RZ_MTU3_TMDR3 0x191 /* MTU1 Timer Mode Register 3 */ + +/* Macros for setting registers */ +#define RZ_MTU3_TCR_CCLR GENMASK(7, 5) +#define RZ_MTU3_TCR_CKEG GENMASK(4, 3) +#define RZ_MTU3_TCR_TPCS GENMASK(2, 0) +#define RZ_MTU3_TCR_CCLR_TGRA BIT(5) +#define RZ_MTU3_TCR_CCLR_TGRC FIELD_PREP(RZ_MTU3_TCR_CCLR, 5) +#define RZ_MTU3_TCR_CKEG_RISING FIELD_PREP(RZ_MTU3_TCR_CKEG, 0) + +#define RZ_MTU3_TIOR_IOB GENMASK(7, 4) +#define RZ_MTU3_TIOR_IOA GENMASK(3, 0) +#define RZ_MTU3_TIOR_OC_RETAIN 0 +#define RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT 2 +#define RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT 7 + +#define RZ_MTU3_TIOR_OC_IOA_H_COMP_MATCH \ + FIELD_PREP(RZ_MTU3_TIOR_IOA, RZ_MTU3_TIOR_OC_INIT_OUT_LO_HI_OUT) +#define RZ_MTU3_TIOR_OC_IOB_TOGGLE \ + FIELD_PREP(RZ_MTU3_TIOR_IOB, RZ_MTU3_TIOR_OC_INIT_OUT_HI_TOGGLE_OUT) + +enum rz_mtu3_channels { + RZ_MTU3_CHAN_0, + RZ_MTU3_CHAN_1, + RZ_MTU3_CHAN_2, + RZ_MTU3_CHAN_3, + RZ_MTU3_CHAN_4, + RZ_MTU3_CHAN_5, + RZ_MTU3_CHAN_6, + RZ_MTU3_CHAN_7, + RZ_MTU3_CHAN_8, + RZ_MTU_NUM_CHANNELS +}; + +/** + * struct rz_mtu3_channel - MTU3 channel private data + * + * @dev: device handle + * @channel_number: channel number + * @lock: Lock to protect channel state + * @is_busy: channel state + */ +struct rz_mtu3_channel { + struct device *dev; + unsigned int channel_number; + struct mutex lock; + bool is_busy; +}; + +/** + * struct rz_mtu3 - MTU3 core private data + * + * @clk: MTU3 module clock + * @rz_mtu3_channel: HW channels + * @priv_data: MTU3 core driver private data + */ +struct rz_mtu3 { + struct clk *clk; + struct rz_mtu3_channel channels[RZ_MTU_NUM_CHANNELS]; + + void *priv_data; +}; + +#if IS_ENABLED(CONFIG_RZ_MTU3) +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + if (ch->is_busy) { + mutex_unlock(&ch->lock); + return false; + } + + ch->is_busy = true; + mutex_unlock(&ch->lock); + + return true; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ + mutex_lock(&ch->lock); + ch->is_busy = false; + mutex_unlock(&ch->lock); +} + +bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch); +void rz_mtu3_disable(struct rz_mtu3_channel *ch); +int rz_mtu3_enable(struct rz_mtu3_channel *ch); + +u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off); +u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off); + +void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val); +void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val); +void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val); +void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, u16 off, + u16 pos, u8 val); +#else +static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch) +{ +} + +static inline bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch) +{ + return false; +} + +static inline void rz_mtu3_disable(struct rz_mtu3_channel *ch) +{ +} + +static inline int rz_mtu3_enable(struct rz_mtu3_channel *ch) +{ + return 0; +} + +static inline u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off) +{ + return 0; +} + +static inline void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val) +{ +} + +static inline void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val) +{ +} + +static inline void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val) +{ +} + +static inline void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, + u16 off, u16 pos, u8 val) +{ +} +#endif + +#endif /* __MFD_RZ_MTU3_H__ */ -- GitLab From 7bb985ac03c4a91d185c006f68c4fadfb71e1cca Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:29 +0100 Subject: [PATCH 4079/5631] Documentation: ABI: sysfs-bus-counter: add cascade_counts_enable and external_input_phase_clock_select This commit adds cascade_counts_enable and external_input_phase_ clock_select items to counter ABI file. (e.g. for Renesas MTU3 hardware used for phase counting). Signed-off-by: Biju Das Reviewed-by: William Breathitt Gray Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-4-biju.das.jz@bp.renesas.com --- Documentation/ABI/testing/sysfs-bus-counter | 32 +++++++++++++++++++++ 1 file changed, 32 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-counter b/Documentation/ABI/testing/sysfs-bus-counter index ff83320b4255..1417c4272c6c 100644 --- a/Documentation/ABI/testing/sysfs-bus-counter +++ b/Documentation/ABI/testing/sysfs-bus-counter @@ -1,3 +1,33 @@ +What: /sys/bus/counter/devices/counterX/cascade_counts_enable +KernelVersion: 6.4 +Contact: linux-iio@vger.kernel.org +Description: + Indicates the cascading of Counts on Counter X. + + Valid attribute values are boolean. + +What: /sys/bus/counter/devices/counterX/external_input_phase_clock_select +KernelVersion: 6.4 +Contact: linux-iio@vger.kernel.org +Description: + Selects the external clock pin for phase counting mode of + Counter X. + + MTCLKA-MTCLKB: + MTCLKA and MTCLKB pins are selected for the external + phase clock. + + MTCLKC-MTCLKD: + MTCLKC and MTCLKD pins are selected for the external + phase clock. + +What: /sys/bus/counter/devices/counterX/external_input_phase_clock_select_available +KernelVersion: 6.4 +Contact: linux-iio@vger.kernel.org +Description: + Discrete set of available values for the respective device + configuration are listed in this file. + What: /sys/bus/counter/devices/counterX/countY/count KernelVersion: 5.2 Contact: linux-iio@vger.kernel.org @@ -215,6 +245,8 @@ Contact: linux-iio@vger.kernel.org Description: This attribute indicates the number of overflows of count Y. +What: /sys/bus/counter/devices/counterX/cascade_counts_enable_component_id +What: /sys/bus/counter/devices/counterX/external_input_phase_clock_select_component_id What: /sys/bus/counter/devices/counterX/countY/capture_component_id What: /sys/bus/counter/devices/counterX/countY/ceiling_component_id What: /sys/bus/counter/devices/counterX/countY/floor_component_id -- GitLab From 0be8907359df4c62319f5cb2c6981ff0d9ebf35a Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:30 +0100 Subject: [PATCH 4080/5631] counter: Add Renesas RZ/G2L MTU3a counter driver Add RZ/G2L MTU3a counter driver. This IP supports the following phase counting modes on MTU1 and MTU2 channels 1) 16-bit phase counting modes on MTU1 and MTU2 channels. 2) 32-bit phase counting mode by cascading MTU1 and MTU2 channels. This patch adds 3 counter value channels. count0: 16-bit phase counter value channel on MTU1 count1: 16-bit phase counter value channel on MTU2 count2: 32-bit phase counter value channel by cascading MTU1 and MTU2 channels. The external input phase clock pin for the counter value channels are as follows: count0: "MTCLKA-MTCLKB" count1: "MTCLKA-MTCLKB" or "MTCLKC-MTCLKD" count2: "MTCLKA-MTCLKB" or "MTCLKC-MTCLKD" Use the sysfs variable "external_input_phase_clock_select" to select the external input phase clock pin and "cascade_counts_enable" to enable/ disable cascading of channels. Signed-off-by: Biju Das Reviewed-by: William Breathitt Gray Acked-by: William Breathitt Gray Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-5-biju.das.jz@bp.renesas.com --- drivers/counter/Kconfig | 11 + drivers/counter/Makefile | 1 + drivers/counter/rz-mtu3-cnt.c | 902 ++++++++++++++++++++++++++++++++++ 3 files changed, 914 insertions(+) create mode 100644 drivers/counter/rz-mtu3-cnt.c diff --git a/drivers/counter/Kconfig b/drivers/counter/Kconfig index b5ba8fb02cf7..4228be917038 100644 --- a/drivers/counter/Kconfig +++ b/drivers/counter/Kconfig @@ -73,6 +73,17 @@ config MICROCHIP_TCB_CAPTURE To compile this driver as a module, choose M here: the module will be called microchip-tcb-capture. +config RZ_MTU3_CNT + tristate "Renesas RZ/G2L MTU3a counter driver" + depends on RZ_MTU3 || COMPILE_TEST + help + Enable support for MTU3a counter driver found on Renesas RZ/G2L alike + SoCs. This IP supports both 16-bit and 32-bit phase counting mode + support. + + To compile this driver as a module, choose M here: the + module will be called rz-mtu3-cnt. + config STM32_LPTIMER_CNT tristate "STM32 LP Timer encoder counter driver" depends on MFD_STM32_LPTIMER || COMPILE_TEST diff --git a/drivers/counter/Makefile b/drivers/counter/Makefile index b9a369e0d4fc..933fdd50b3e4 100644 --- a/drivers/counter/Makefile +++ b/drivers/counter/Makefile @@ -8,6 +8,7 @@ counter-y := counter-core.o counter-sysfs.o counter-chrdev.o obj-$(CONFIG_104_QUAD_8) += 104-quad-8.o obj-$(CONFIG_INTERRUPT_CNT) += interrupt-cnt.o +obj-$(CONFIG_RZ_MTU3_CNT) += rz-mtu3-cnt.o obj-$(CONFIG_STM32_TIMER_CNT) += stm32-timer-cnt.o obj-$(CONFIG_STM32_LPTIMER_CNT) += stm32-lptimer-cnt.o obj-$(CONFIG_TI_EQEP) += ti-eqep.o diff --git a/drivers/counter/rz-mtu3-cnt.c b/drivers/counter/rz-mtu3-cnt.c new file mode 100644 index 000000000000..a371bab68499 --- /dev/null +++ b/drivers/counter/rz-mtu3-cnt.c @@ -0,0 +1,902 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Renesas RZ/G2L MTU3a Counter driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + */ + +#include +#include +#include +#include +#include +#include +#include + +/* + * Register descriptions + * TSR: Timer Status Register + * TMDR1: Timer Mode Register 1 + * TMDR3: Timer Mode Register 3 + * TIOR: Timer I/O Control Register + * TCR: Timer Control Register + * TCNT: Timer Counter + * TGRA: Timer general register A + * TCNTLW: Timer Longword Counter + * TGRALW: Timer longword general register A + */ + +#define RZ_MTU3_TSR_TCFD BIT(7) /* Count Direction Flag */ + +#define RZ_MTU3_TMDR1_PH_CNT_MODE_1 (4) /* Phase counting mode 1 */ +#define RZ_MTU3_TMDR1_PH_CNT_MODE_2 (5) /* Phase counting mode 2 */ +#define RZ_MTU3_TMDR1_PH_CNT_MODE_3 (6) /* Phase counting mode 3 */ +#define RZ_MTU3_TMDR1_PH_CNT_MODE_4 (7) /* Phase counting mode 4 */ +#define RZ_MTU3_TMDR1_PH_CNT_MODE_5 (9) /* Phase counting mode 5 */ +#define RZ_MTU3_TMDR1_PH_CNT_MODE_MASK (0xf) + +/* + * LWA: MTU1/MTU2 Combination Longword Access Control + * 0: 16-bit, 1: 32-bit + */ +#define RZ_MTU3_TMDR3_LWA (0) + +/* + * PHCKSEL: External Input Phase Clock Select + * 0: MTCLKA and MTCLKB, 1: MTCLKC and MTCLKD + */ +#define RZ_MTU3_TMDR3_PHCKSEL (1) + +#define RZ_MTU3_16_BIT_MTU1_CH (0) +#define RZ_MTU3_16_BIT_MTU2_CH (1) +#define RZ_MTU3_32_BIT_CH (2) + +#define RZ_MTU3_TIOR_NO_OUTPUT (0) /* Output prohibited */ +#define RZ_MTU3_TIOR_IC_BOTH (10) /* Input capture at both edges */ + +#define SIGNAL_A_ID (0) +#define SIGNAL_B_ID (1) +#define SIGNAL_C_ID (2) +#define SIGNAL_D_ID (3) + +#define RZ_MTU3_MAX_HW_CNTR_CHANNELS (2) +#define RZ_MTU3_MAX_LOGICAL_CNTR_CHANNELS (3) + +/** + * struct rz_mtu3_cnt - MTU3 counter private data + * + * @clk: MTU3 module clock + * @lock: Lock to prevent concurrent access for ceiling and count + * @ch: HW channels for the counters + * @count_is_enabled: Enabled state of Counter value channel + * @mtu_16bit_max: Cache for 16-bit counters + * @mtu_32bit_max: Cache for 32-bit counters + */ +struct rz_mtu3_cnt { + struct clk *clk; + struct mutex lock; + struct rz_mtu3_channel *ch; + bool count_is_enabled[RZ_MTU3_MAX_LOGICAL_CNTR_CHANNELS]; + union { + u16 mtu_16bit_max[RZ_MTU3_MAX_HW_CNTR_CHANNELS]; + u32 mtu_32bit_max; + }; +}; + +static const enum counter_function rz_mtu3_count_functions[] = { + COUNTER_FUNCTION_QUADRATURE_X4, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X2_B, +}; + +static inline size_t rz_mtu3_get_hw_ch(const size_t id) +{ + return (id == RZ_MTU3_32_BIT_CH) ? 0 : id; +} + +static inline struct rz_mtu3_channel *rz_mtu3_get_ch(struct counter_device *counter, int id) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + const size_t ch_id = rz_mtu3_get_hw_ch(id); + + return &priv->ch[ch_id]; +} + +static bool rz_mtu3_is_counter_invalid(struct counter_device *counter, int id) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + unsigned long tmdr; + + pm_runtime_get_sync(priv->ch->dev); + tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3); + pm_runtime_put(priv->ch->dev); + + if (id == RZ_MTU3_32_BIT_CH && test_bit(RZ_MTU3_TMDR3_LWA, &tmdr)) + return false; + + if (id != RZ_MTU3_32_BIT_CH && !test_bit(RZ_MTU3_TMDR3_LWA, &tmdr)) + return false; + + return true; +} + +static int rz_mtu3_lock_if_counter_is_valid(struct counter_device *counter, + struct rz_mtu3_channel *const ch, + struct rz_mtu3_cnt *const priv, + int id) +{ + mutex_lock(&priv->lock); + + if (ch->is_busy && !priv->count_is_enabled[id]) { + mutex_unlock(&priv->lock); + return -EINVAL; + } + + if (rz_mtu3_is_counter_invalid(counter, id)) { + mutex_unlock(&priv->lock); + return -EBUSY; + } + + return 0; +} + +static int rz_mtu3_lock_if_count_is_enabled(struct rz_mtu3_channel *const ch, + struct rz_mtu3_cnt *const priv, + int id) +{ + mutex_lock(&priv->lock); + + if (ch->is_busy && !priv->count_is_enabled[id]) { + mutex_unlock(&priv->lock); + return -EINVAL; + } + + return 0; +} + +static int rz_mtu3_count_read(struct counter_device *counter, + struct counter_count *count, u64 *val) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_counter_is_valid(counter, ch, priv, count->id); + if (ret) + return ret; + + pm_runtime_get_sync(ch->dev); + if (count->id == RZ_MTU3_32_BIT_CH) + *val = rz_mtu3_32bit_ch_read(ch, RZ_MTU3_TCNTLW); + else + *val = rz_mtu3_16bit_ch_read(ch, RZ_MTU3_TCNT); + pm_runtime_put(ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_count_write(struct counter_device *counter, + struct counter_count *count, const u64 val) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_counter_is_valid(counter, ch, priv, count->id); + if (ret) + return ret; + + pm_runtime_get_sync(ch->dev); + if (count->id == RZ_MTU3_32_BIT_CH) + rz_mtu3_32bit_ch_write(ch, RZ_MTU3_TCNTLW, val); + else + rz_mtu3_16bit_ch_write(ch, RZ_MTU3_TCNT, val); + pm_runtime_put(ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_count_function_read_helper(struct rz_mtu3_channel *const ch, + struct rz_mtu3_cnt *const priv, + enum counter_function *function) +{ + u8 timer_mode; + + pm_runtime_get_sync(ch->dev); + timer_mode = rz_mtu3_8bit_ch_read(ch, RZ_MTU3_TMDR1); + pm_runtime_put(ch->dev); + + switch (timer_mode & RZ_MTU3_TMDR1_PH_CNT_MODE_MASK) { + case RZ_MTU3_TMDR1_PH_CNT_MODE_1: + *function = COUNTER_FUNCTION_QUADRATURE_X4; + return 0; + case RZ_MTU3_TMDR1_PH_CNT_MODE_2: + *function = COUNTER_FUNCTION_PULSE_DIRECTION; + return 0; + case RZ_MTU3_TMDR1_PH_CNT_MODE_4: + *function = COUNTER_FUNCTION_QUADRATURE_X2_B; + return 0; + default: + /* + * TODO: + * - need to add RZ_MTU3_TMDR1_PH_CNT_MODE_3 + * - need to add RZ_MTU3_TMDR1_PH_CNT_MODE_5 + */ + return -EINVAL; + } +} + +static int rz_mtu3_count_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_count_is_enabled(ch, priv, count->id); + if (ret) + return ret; + + ret = rz_mtu3_count_function_read_helper(ch, priv, function); + mutex_unlock(&priv->lock); + + return ret; +} + +static int rz_mtu3_count_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + u8 timer_mode; + int ret; + + ret = rz_mtu3_lock_if_count_is_enabled(ch, priv, count->id); + if (ret) + return ret; + + switch (function) { + case COUNTER_FUNCTION_QUADRATURE_X4: + timer_mode = RZ_MTU3_TMDR1_PH_CNT_MODE_1; + break; + case COUNTER_FUNCTION_PULSE_DIRECTION: + timer_mode = RZ_MTU3_TMDR1_PH_CNT_MODE_2; + break; + case COUNTER_FUNCTION_QUADRATURE_X2_B: + timer_mode = RZ_MTU3_TMDR1_PH_CNT_MODE_4; + break; + default: + /* + * TODO: + * - need to add RZ_MTU3_TMDR1_PH_CNT_MODE_3 + * - need to add RZ_MTU3_TMDR1_PH_CNT_MODE_5 + */ + mutex_unlock(&priv->lock); + return -EINVAL; + } + + pm_runtime_get_sync(ch->dev); + rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TMDR1, timer_mode); + pm_runtime_put(ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_count_direction_read(struct counter_device *counter, + struct counter_count *count, + enum counter_count_direction *direction) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + u8 tsr; + + ret = rz_mtu3_lock_if_count_is_enabled(ch, priv, count->id); + if (ret) + return ret; + + pm_runtime_get_sync(ch->dev); + tsr = rz_mtu3_8bit_ch_read(ch, RZ_MTU3_TSR); + pm_runtime_put(ch->dev); + + *direction = (tsr & RZ_MTU3_TSR_TCFD) ? + COUNTER_COUNT_DIRECTION_FORWARD : COUNTER_COUNT_DIRECTION_BACKWARD; + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_count_ceiling_read(struct counter_device *counter, + struct counter_count *count, + u64 *ceiling) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + const size_t ch_id = rz_mtu3_get_hw_ch(count->id); + int ret; + + ret = rz_mtu3_lock_if_counter_is_valid(counter, ch, priv, count->id); + if (ret) + return ret; + + switch (count->id) { + case RZ_MTU3_16_BIT_MTU1_CH: + case RZ_MTU3_16_BIT_MTU2_CH: + *ceiling = priv->mtu_16bit_max[ch_id]; + break; + case RZ_MTU3_32_BIT_CH: + *ceiling = priv->mtu_32bit_max; + break; + default: + /* should never reach this path */ + mutex_unlock(&priv->lock); + return -EINVAL; + } + + mutex_unlock(&priv->lock); + return 0; +} + +static int rz_mtu3_count_ceiling_write(struct counter_device *counter, + struct counter_count *count, + u64 ceiling) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + const size_t ch_id = rz_mtu3_get_hw_ch(count->id); + int ret; + + ret = rz_mtu3_lock_if_counter_is_valid(counter, ch, priv, count->id); + if (ret) + return ret; + + switch (count->id) { + case RZ_MTU3_16_BIT_MTU1_CH: + case RZ_MTU3_16_BIT_MTU2_CH: + if (ceiling > U16_MAX) + return -ERANGE; + priv->mtu_16bit_max[ch_id] = ceiling; + break; + case RZ_MTU3_32_BIT_CH: + if (ceiling > U32_MAX) + return -ERANGE; + priv->mtu_32bit_max = ceiling; + break; + default: + /* should never reach this path */ + mutex_unlock(&priv->lock); + return -EINVAL; + } + + pm_runtime_get_sync(ch->dev); + if (count->id == RZ_MTU3_32_BIT_CH) + rz_mtu3_32bit_ch_write(ch, RZ_MTU3_TGRALW, ceiling); + else + rz_mtu3_16bit_ch_write(ch, RZ_MTU3_TGRA, ceiling); + + rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TCR, RZ_MTU3_TCR_CCLR_TGRA); + pm_runtime_put(ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static void rz_mtu3_32bit_cnt_setting(struct counter_device *counter) +{ + struct rz_mtu3_channel *const ch1 = rz_mtu3_get_ch(counter, 0); + struct rz_mtu3_channel *const ch2 = rz_mtu3_get_ch(counter, 1); + + /* Phase counting mode 1 is used as default in initialization. */ + rz_mtu3_8bit_ch_write(ch1, RZ_MTU3_TMDR1, RZ_MTU3_TMDR1_PH_CNT_MODE_1); + + rz_mtu3_8bit_ch_write(ch1, RZ_MTU3_TCR, RZ_MTU3_TCR_CCLR_TGRA); + rz_mtu3_8bit_ch_write(ch1, RZ_MTU3_TIOR, RZ_MTU3_TIOR_IC_BOTH); + + rz_mtu3_enable(ch1); + rz_mtu3_enable(ch2); +} + +static void rz_mtu3_16bit_cnt_setting(struct counter_device *counter, int id) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, id); + + /* Phase counting mode 1 is used as default in initialization. */ + rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TMDR1, RZ_MTU3_TMDR1_PH_CNT_MODE_1); + + rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TCR, RZ_MTU3_TCR_CCLR_TGRA); + rz_mtu3_8bit_ch_write(ch, RZ_MTU3_TIOR, RZ_MTU3_TIOR_NO_OUTPUT); + rz_mtu3_enable(ch); +} + +static int rz_mtu3_initialize_counter(struct counter_device *counter, int id) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, id); + struct rz_mtu3_channel *const ch1 = rz_mtu3_get_ch(counter, 0); + struct rz_mtu3_channel *const ch2 = rz_mtu3_get_ch(counter, 1); + + switch (id) { + case RZ_MTU3_16_BIT_MTU1_CH: + case RZ_MTU3_16_BIT_MTU2_CH: + if (!rz_mtu3_request_channel(ch)) + return -EBUSY; + + rz_mtu3_16bit_cnt_setting(counter, id); + return 0; + case RZ_MTU3_32_BIT_CH: + /* + * 32-bit phase counting need MTU1 and MTU2 to create 32-bit + * cascade counter. + */ + if (!rz_mtu3_request_channel(ch1)) + return -EBUSY; + + if (!rz_mtu3_request_channel(ch2)) { + rz_mtu3_release_channel(ch1); + return -EBUSY; + } + + rz_mtu3_32bit_cnt_setting(counter); + return 0; + default: + /* should never reach this path */ + return -EINVAL; + } +} + +static void rz_mtu3_terminate_counter(struct counter_device *counter, int id) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, id); + struct rz_mtu3_channel *const ch1 = rz_mtu3_get_ch(counter, 0); + struct rz_mtu3_channel *const ch2 = rz_mtu3_get_ch(counter, 1); + + if (id == RZ_MTU3_32_BIT_CH) { + rz_mtu3_release_channel(ch2); + rz_mtu3_release_channel(ch1); + rz_mtu3_disable(ch2); + rz_mtu3_disable(ch1); + } else { + rz_mtu3_release_channel(ch); + rz_mtu3_disable(ch); + } +} + +static int rz_mtu3_count_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_channel *const ch1 = rz_mtu3_get_ch(counter, 0); + struct rz_mtu3_channel *const ch2 = rz_mtu3_get_ch(counter, 1); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_count_is_enabled(ch, priv, count->id); + if (ret) + return ret; + + if (count->id == RZ_MTU3_32_BIT_CH) + *enable = rz_mtu3_is_enabled(ch1) && rz_mtu3_is_enabled(ch2); + else + *enable = rz_mtu3_is_enabled(ch); + + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_count_enable_write(struct counter_device *counter, + struct counter_count *count, u8 enable) +{ + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret = 0; + + if (enable) { + pm_runtime_get_sync(ch->dev); + mutex_lock(&priv->lock); + ret = rz_mtu3_initialize_counter(counter, count->id); + if (ret == 0) + priv->count_is_enabled[count->id] = true; + mutex_unlock(&priv->lock); + } else { + mutex_lock(&priv->lock); + rz_mtu3_terminate_counter(counter, count->id); + priv->count_is_enabled[count->id] = false; + mutex_unlock(&priv->lock); + pm_runtime_put(ch->dev); + } + + return ret; +} + +static int rz_mtu3_lock_if_ch0_is_enabled(struct rz_mtu3_cnt *const priv) +{ + mutex_lock(&priv->lock); + if (priv->ch->is_busy && !(priv->count_is_enabled[RZ_MTU3_16_BIT_MTU1_CH] || + priv->count_is_enabled[RZ_MTU3_32_BIT_CH])) { + mutex_unlock(&priv->lock); + return -EINVAL; + } + + return 0; +} + +static int rz_mtu3_cascade_counts_enable_get(struct counter_device *counter, + u8 *cascade_enable) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + unsigned long tmdr; + int ret; + + ret = rz_mtu3_lock_if_ch0_is_enabled(priv); + if (ret) + return ret; + + pm_runtime_get_sync(priv->ch->dev); + tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3); + pm_runtime_put(priv->ch->dev); + *cascade_enable = test_bit(RZ_MTU3_TMDR3_LWA, &tmdr); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_cascade_counts_enable_set(struct counter_device *counter, + u8 cascade_enable) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_ch0_is_enabled(priv); + if (ret) + return ret; + + pm_runtime_get_sync(priv->ch->dev); + rz_mtu3_shared_reg_update_bit(priv->ch, RZ_MTU3_TMDR3, + RZ_MTU3_TMDR3_LWA, cascade_enable); + pm_runtime_put(priv->ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_ext_input_phase_clock_select_get(struct counter_device *counter, + u32 *ext_input_phase_clock_select) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + unsigned long tmdr; + int ret; + + ret = rz_mtu3_lock_if_ch0_is_enabled(priv); + if (ret) + return ret; + + pm_runtime_get_sync(priv->ch->dev); + tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3); + pm_runtime_put(priv->ch->dev); + *ext_input_phase_clock_select = test_bit(RZ_MTU3_TMDR3_PHCKSEL, &tmdr); + mutex_unlock(&priv->lock); + + return 0; +} + +static int rz_mtu3_ext_input_phase_clock_select_set(struct counter_device *counter, + u32 ext_input_phase_clock_select) +{ + struct rz_mtu3_cnt *const priv = counter_priv(counter); + int ret; + + ret = rz_mtu3_lock_if_ch0_is_enabled(priv); + if (ret) + return ret; + + pm_runtime_get_sync(priv->ch->dev); + rz_mtu3_shared_reg_update_bit(priv->ch, RZ_MTU3_TMDR3, + RZ_MTU3_TMDR3_PHCKSEL, + ext_input_phase_clock_select); + pm_runtime_put(priv->ch->dev); + mutex_unlock(&priv->lock); + + return 0; +} + +static struct counter_comp rz_mtu3_count_ext[] = { + COUNTER_COMP_DIRECTION(rz_mtu3_count_direction_read), + COUNTER_COMP_ENABLE(rz_mtu3_count_enable_read, + rz_mtu3_count_enable_write), + COUNTER_COMP_CEILING(rz_mtu3_count_ceiling_read, + rz_mtu3_count_ceiling_write), +}; + +static const enum counter_synapse_action rz_mtu3_synapse_actions[] = { + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_NONE, +}; + +static int rz_mtu3_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) +{ + const bool is_signal_ab = (synapse->signal->id == SIGNAL_A_ID) || + (synapse->signal->id == SIGNAL_B_ID); + struct rz_mtu3_channel *const ch = rz_mtu3_get_ch(counter, count->id); + struct rz_mtu3_cnt *const priv = counter_priv(counter); + enum counter_function function; + bool mtclkc_mtclkd; + unsigned long tmdr; + int ret; + + ret = rz_mtu3_lock_if_count_is_enabled(ch, priv, count->id); + if (ret) + return ret; + + ret = rz_mtu3_count_function_read_helper(ch, priv, &function); + if (ret) { + mutex_unlock(&priv->lock); + return ret; + } + + /* Default action mode */ + *action = COUNTER_SYNAPSE_ACTION_NONE; + + if (count->id != RZ_MTU3_16_BIT_MTU1_CH) { + tmdr = rz_mtu3_shared_reg_read(priv->ch, RZ_MTU3_TMDR3); + mtclkc_mtclkd = test_bit(RZ_MTU3_TMDR3_PHCKSEL, &tmdr); + if ((mtclkc_mtclkd && is_signal_ab) || + (!mtclkc_mtclkd && !is_signal_ab)) { + mutex_unlock(&priv->lock); + return 0; + } + } + + switch (function) { + case COUNTER_FUNCTION_PULSE_DIRECTION: + /* + * Rising edges on signal A (signal C) updates the respective + * count. The input level of signal B (signal D) determines + * direction. + */ + if (synapse->signal->id == SIGNAL_A_ID || + synapse->signal->id == SIGNAL_C_ID) + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; + break; + case COUNTER_FUNCTION_QUADRATURE_X2_B: + /* + * Any state transition on quadrature pair signal B (signal D) + * updates the respective count. + */ + if (synapse->signal->id == SIGNAL_B_ID || + synapse->signal->id == SIGNAL_D_ID) + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; + break; + case COUNTER_FUNCTION_QUADRATURE_X4: + /* counts up/down on both edges of A (C) and B (D) signal */ + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; + break; + default: + /* should never reach this path */ + mutex_unlock(&priv->lock); + return -EINVAL; + } + + mutex_unlock(&priv->lock); + + return 0; +} + +static const struct counter_ops rz_mtu3_cnt_ops = { + .count_read = rz_mtu3_count_read, + .count_write = rz_mtu3_count_write, + .function_read = rz_mtu3_count_function_read, + .function_write = rz_mtu3_count_function_write, + .action_read = rz_mtu3_action_read, +}; + +#define RZ_MTU3_PHASE_SIGNAL(_id, _name) { \ + .id = (_id), \ + .name = (_name), \ +} + +static struct counter_signal rz_mtu3_signals[] = { + RZ_MTU3_PHASE_SIGNAL(SIGNAL_A_ID, "MTU1 MTCLKA"), + RZ_MTU3_PHASE_SIGNAL(SIGNAL_B_ID, "MTU1 MTCLKB"), + RZ_MTU3_PHASE_SIGNAL(SIGNAL_C_ID, "MTU2 MTCLKC"), + RZ_MTU3_PHASE_SIGNAL(SIGNAL_D_ID, "MTU2 MTCLKD"), +}; + +static struct counter_synapse rz_mtu3_mtu1_count_synapses[] = { + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals, + }, + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals + 1, + } +}; + +static struct counter_synapse rz_mtu3_mtu2_count_synapses[] = { + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals, + }, + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals + 1, + }, + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals + 2, + }, + { + .actions_list = rz_mtu3_synapse_actions, + .num_actions = ARRAY_SIZE(rz_mtu3_synapse_actions), + .signal = rz_mtu3_signals + 3, + } +}; + +static struct counter_count rz_mtu3_counts[] = { + { + .id = RZ_MTU3_16_BIT_MTU1_CH, + .name = "Channel 1 Count", + .functions_list = rz_mtu3_count_functions, + .num_functions = ARRAY_SIZE(rz_mtu3_count_functions), + .synapses = rz_mtu3_mtu1_count_synapses, + .num_synapses = ARRAY_SIZE(rz_mtu3_mtu1_count_synapses), + .ext = rz_mtu3_count_ext, + .num_ext = ARRAY_SIZE(rz_mtu3_count_ext), + }, + { + .id = RZ_MTU3_16_BIT_MTU2_CH, + .name = "Channel 2 Count", + .functions_list = rz_mtu3_count_functions, + .num_functions = ARRAY_SIZE(rz_mtu3_count_functions), + .synapses = rz_mtu3_mtu2_count_synapses, + .num_synapses = ARRAY_SIZE(rz_mtu3_mtu2_count_synapses), + .ext = rz_mtu3_count_ext, + .num_ext = ARRAY_SIZE(rz_mtu3_count_ext), + }, + { + .id = RZ_MTU3_32_BIT_CH, + .name = "Channel 1 and 2 (cascaded) Count", + .functions_list = rz_mtu3_count_functions, + .num_functions = ARRAY_SIZE(rz_mtu3_count_functions), + .synapses = rz_mtu3_mtu2_count_synapses, + .num_synapses = ARRAY_SIZE(rz_mtu3_mtu2_count_synapses), + .ext = rz_mtu3_count_ext, + .num_ext = ARRAY_SIZE(rz_mtu3_count_ext), + } +}; + +static const char *const rz_mtu3_ext_input_phase_clock_select[] = { + "MTCLKA-MTCLKB", + "MTCLKC-MTCLKD", +}; + +static DEFINE_COUNTER_ENUM(rz_mtu3_ext_input_phase_clock_select_enum, + rz_mtu3_ext_input_phase_clock_select); + +static struct counter_comp rz_mtu3_device_ext[] = { + COUNTER_COMP_DEVICE_BOOL("cascade_counts_enable", + rz_mtu3_cascade_counts_enable_get, + rz_mtu3_cascade_counts_enable_set), + COUNTER_COMP_DEVICE_ENUM("external_input_phase_clock_select", + rz_mtu3_ext_input_phase_clock_select_get, + rz_mtu3_ext_input_phase_clock_select_set, + rz_mtu3_ext_input_phase_clock_select_enum), +}; + +static int rz_mtu3_cnt_pm_runtime_suspend(struct device *dev) +{ + struct clk *const clk = dev_get_drvdata(dev); + + clk_disable_unprepare(clk); + + return 0; +} + +static int rz_mtu3_cnt_pm_runtime_resume(struct device *dev) +{ + struct clk *const clk = dev_get_drvdata(dev); + + clk_prepare_enable(clk); + + return 0; +} + +static DEFINE_RUNTIME_DEV_PM_OPS(rz_mtu3_cnt_pm_ops, + rz_mtu3_cnt_pm_runtime_suspend, + rz_mtu3_cnt_pm_runtime_resume, NULL); + +static void rz_mtu3_cnt_pm_disable(void *data) +{ + struct device *dev = data; + + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); +} + +static int rz_mtu3_cnt_probe(struct platform_device *pdev) +{ + struct rz_mtu3 *ddata = dev_get_drvdata(pdev->dev.parent); + struct device *dev = &pdev->dev; + struct counter_device *counter; + struct rz_mtu3_channel *ch; + struct rz_mtu3_cnt *priv; + unsigned int i; + int ret; + + counter = devm_counter_alloc(dev, sizeof(*priv)); + if (!counter) + return -ENOMEM; + + priv = counter_priv(counter); + priv->clk = ddata->clk; + priv->mtu_32bit_max = U32_MAX; + priv->ch = &ddata->channels[RZ_MTU3_CHAN_1]; + ch = &priv->ch[0]; + for (i = 0; i < RZ_MTU3_MAX_HW_CNTR_CHANNELS; i++) { + ch->dev = dev; + priv->mtu_16bit_max[i] = U16_MAX; + ch++; + } + + mutex_init(&priv->lock); + platform_set_drvdata(pdev, priv->clk); + clk_prepare_enable(priv->clk); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + ret = devm_add_action_or_reset(&pdev->dev, rz_mtu3_cnt_pm_disable, dev); + if (ret < 0) + goto disable_clock; + + counter->name = dev_name(dev); + counter->parent = dev; + counter->ops = &rz_mtu3_cnt_ops; + counter->counts = rz_mtu3_counts; + counter->num_counts = ARRAY_SIZE(rz_mtu3_counts); + counter->signals = rz_mtu3_signals; + counter->num_signals = ARRAY_SIZE(rz_mtu3_signals); + counter->ext = rz_mtu3_device_ext; + counter->num_ext = ARRAY_SIZE(rz_mtu3_device_ext); + + /* Register Counter device */ + ret = devm_counter_add(dev, counter); + if (ret < 0) { + dev_err_probe(dev, ret, "Failed to add counter\n"); + goto disable_clock; + } + + return 0; + +disable_clock: + clk_disable_unprepare(priv->clk); + + return ret; +} + +static struct platform_driver rz_mtu3_cnt_driver = { + .probe = rz_mtu3_cnt_probe, + .driver = { + .name = "rz-mtu3-counter", + .pm = pm_ptr(&rz_mtu3_cnt_pm_ops), + }, +}; +module_platform_driver(rz_mtu3_cnt_driver); + +MODULE_AUTHOR("Biju Das "); +MODULE_ALIAS("platform:rz-mtu3-counter"); +MODULE_DESCRIPTION("Renesas RZ/G2L MTU3a counter driver"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(COUNTER); -- GitLab From 5dee9439cc2d60ff35cad04b618ee53f48a7cfc2 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 30 Mar 2023 12:16:31 +0100 Subject: [PATCH 4081/5631] MAINTAINERS: Add entries for Renesas RZ/G2L MTU3a counter driver Add the MAINTAINERS entries for the Renesas RZ/G2L MTU3a counter driver. Signed-off-by: Biju Das Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230330111632.169434-6-biju.das.jz@bp.renesas.com --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index d8ebab595b2a..734d9b8de9cb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17847,6 +17847,14 @@ S: Supported F: Documentation/devicetree/bindings/iio/adc/renesas,rzg2l-adc.yaml F: drivers/iio/adc/rzg2l_adc.c +RENESAS RZ/G2L MTU3a COUNTER DRIVER +M: Biju Das +L: linux-iio@vger.kernel.org +L: linux-renesas-soc@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml +F: drivers/counter/rz-mtu3-cnt.c + RENESAS RZ/N1 A5PSW SWITCH DRIVER M: Clément Léger L: linux-renesas-soc@vger.kernel.org -- GitLab From dbc5e57200e9ed14f08c5493c8633200cf07d700 Mon Sep 17 00:00:00 2001 From: Jacky Huang Date: Tue, 28 Mar 2023 02:19:05 +0000 Subject: [PATCH 4082/5631] dt-bindings: mfd: syscon: Add nuvoton,ma35d1-sys compatible Add Nuvoton ma35d1 system registers compatible. Signed-off-by: Jacky Huang Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230328021912.177301-6-ychuang570808@gmail.com --- Documentation/devicetree/bindings/mfd/syscon.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mfd/syscon.yaml b/Documentation/devicetree/bindings/mfd/syscon.yaml index 43f564be709f..8103154bbb52 100644 --- a/Documentation/devicetree/bindings/mfd/syscon.yaml +++ b/Documentation/devicetree/bindings/mfd/syscon.yaml @@ -56,6 +56,7 @@ properties: - microchip,lan966x-cpu-syscon - microchip,sparx5-cpu-syscon - mstar,msc313-pmsleep + - nuvoton,ma35d1-sys - nuvoton,wpcm450-shm - rockchip,px30-qos - rockchip,rk3036-qos -- GitLab From b24e335b7d73b5d65d09144319c62aa967b6abc8 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Mon, 10 Apr 2023 22:29:16 +0200 Subject: [PATCH 4083/5631] dt-bindings: mfd: qcom,spmi-pmic: Use generic ADC node name in examples Update the examples to reflect a future requirement for the generic `channel` node name on ADC channel nodes, while conveying the board name of the channel in a label instead. Signed-off-by: Marijn Suijten Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230410202917.247666-5-marijn.suijten@somainline.org --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index 84620ebc1efe..9f4c75c35aae 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -283,12 +283,12 @@ examples: #size-cells = <0>; #io-channel-cells = <1>; - adc-chan@6 { + channel@6 { reg = ; label = "die_temp"; }; - adc-chan@4f { + channel@4f { reg = ; qcom,ratiometric; qcom,hw-settle-time = <200>; -- GitLab From 378b0e9f247450c9c4e49f02d9d79799a0c7c349 Mon Sep 17 00:00:00 2001 From: Patrick Delaunay Date: Mon, 17 Apr 2023 18:14:06 +0200 Subject: [PATCH 4084/5631] dt-bindings: mfd: stm32: Remove unnecessary blank lines Remove double blank line. Signed-off-by: Patrick Delaunay Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230417181342.v2.1.I483a676579cc7e3ac07e1db649091553743fecc8@changeid --- include/dt-bindings/mfd/stm32f4-rcc.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/dt-bindings/mfd/stm32f4-rcc.h b/include/dt-bindings/mfd/stm32f4-rcc.h index 309e8c79f27b..36448a5619a1 100644 --- a/include/dt-bindings/mfd/stm32f4-rcc.h +++ b/include/dt-bindings/mfd/stm32f4-rcc.h @@ -34,7 +34,6 @@ #define STM32F4_AHB1_RESET(bit) (STM32F4_RCC_AHB1_##bit + (0x10 * 8)) #define STM32F4_AHB1_CLOCK(bit) (STM32F4_RCC_AHB1_##bit) - /* AHB2 */ #define STM32F4_RCC_AHB2_DCMI 0 #define STM32F4_RCC_AHB2_CRYP 4 -- GitLab From 1706636eafcab76e08784f66f80f00d9aa59bed1 Mon Sep 17 00:00:00 2001 From: Benjamin Bara Date: Wed, 5 Apr 2023 19:14:36 +0200 Subject: [PATCH 4085/5631] dt-bindings: mfd: dlg,da9063: Document voltage monitoring Document that the da9063 only provides under- *and* over-voltage monitoring in one, and therefore requires both to be configured with the same severity and value. Add an example for clarification. Signed-off-by: Benjamin Bara Acked-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230403-da9063-disable-unused-v3-3-cc4dc698864c@skidata.com --- .../devicetree/bindings/mfd/dlg,da9063.yaml | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/dlg,da9063.yaml b/Documentation/devicetree/bindings/mfd/dlg,da9063.yaml index e8e74e91070c..c5a7e10d7d80 100644 --- a/Documentation/devicetree/bindings/mfd/dlg,da9063.yaml +++ b/Documentation/devicetree/bindings/mfd/dlg,da9063.yaml @@ -12,6 +12,11 @@ maintainers: description: | For device-tree bindings of other sub-modules refer to the binding documents under the respective sub-system directories. + Using regulator-{uv,ov}-{warn,error,protection}-microvolt requires special + handling: First, when GP_FB2 is used, it must be ensured that there is no + moment where all voltage monitors are disabled. Next, as da9063 only supports + UV *and* OV monitoring, both must be set to the same severity and value + (0: disable, 1: enable). properties: compatible: @@ -121,11 +126,19 @@ examples: regulator-max-microamp = <2000000>; regulator-boot-on; }; + ldo6 { + /* UNUSED */ + regulator-name = "LDO_6"; + regulator-uv-protection-microvolt = <0>; + regulator-ov-protection-microvolt = <0>; + }; ldo11 { regulator-name = "LDO_11"; regulator-min-microvolt = <900000>; - regulator-max-microvolt = <3600000>; - regulator-boot-on; + regulator-max-microvolt = <900000>; + regulator-uv-protection-microvolt = <1>; + regulator-ov-protection-microvolt = <1>; + regulator-always-on; }; }; }; -- GitLab From 1e28dfdf40d7293882ba7eb70a3bc0e9ab625377 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 20 Apr 2023 18:02:11 +0300 Subject: [PATCH 4086/5631] counter: rz-mtu3-cnt: Unlock on error in rz_mtu3_count_ceiling_write() These error paths need to call mutex_unlock(&priv->lock) before returning. The lock is taken in rz_mtu3_lock_if_counter_is_valid(). Fixes: 25d21447d896 ("counter: Add Renesas RZ/G2L MTU3a counter driver") Signed-off-by: Dan Carpenter Acked-by: William Breathitt Gray Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/7b535d6b-6031-493a-84f6-82842089e637@kili.mountain --- drivers/counter/rz-mtu3-cnt.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/counter/rz-mtu3-cnt.c b/drivers/counter/rz-mtu3-cnt.c index a371bab68499..48c83933aa2f 100644 --- a/drivers/counter/rz-mtu3-cnt.c +++ b/drivers/counter/rz-mtu3-cnt.c @@ -358,13 +358,17 @@ static int rz_mtu3_count_ceiling_write(struct counter_device *counter, switch (count->id) { case RZ_MTU3_16_BIT_MTU1_CH: case RZ_MTU3_16_BIT_MTU2_CH: - if (ceiling > U16_MAX) + if (ceiling > U16_MAX) { + mutex_unlock(&priv->lock); return -ERANGE; + } priv->mtu_16bit_max[ch_id] = ceiling; break; case RZ_MTU3_32_BIT_CH: - if (ceiling > U32_MAX) + if (ceiling > U32_MAX) { + mutex_unlock(&priv->lock); return -ERANGE; + } priv->mtu_32bit_max = ceiling; break; default: -- GitLab From a33c6a22f6d616caab6f5a5bfaa7ee01ea567d82 Mon Sep 17 00:00:00 2001 From: Martin Botka Date: Sat, 1 Apr 2023 01:18:48 +0100 Subject: [PATCH 4087/5631] dt-bindings: mfd: x-powers,axp152: Document the AXP313a variant The X-Powers AXP313a is a PMIC used on some devices with the Allwinner H616 or H313 SoC. According to the datasheet, the DC/DC converter PWM frequency is fixed (to 3 MHz), so disallow the property that lets us set this frequency for the other PMICs. Signed-off-by: Martin Botka Signed-off-by: Andre Przywara Reviewed-by: Krzysztof Kozlowski Acked-by: Chen-Yu Tsai Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230401001850.4988-2-andre.przywara@arm.com (cherry picked from commit 2a9e8a1a7c4caadf690e5a77fe4162c5edab4a9c) Signed-off-by: Lee Jones --- .../devicetree/bindings/mfd/x-powers,axp152.yaml | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml index 2691ac08f536..ed76b1c58cdf 100644 --- a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml +++ b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml @@ -73,6 +73,16 @@ allOf: required: - interrupts + - if: + properties: + compatible: + contains: + const: x-powers,axp313a + + then: + properties: + x-powers,dcdc-freq: false + properties: compatible: oneOf: @@ -82,6 +92,7 @@ properties: - x-powers,axp209 - x-powers,axp221 - x-powers,axp223 + - x-powers,axp313a - x-powers,axp803 - x-powers,axp806 - x-powers,axp809 -- GitLab From c51e431052e2eacfb23fbf6b39bc6c8770d9827a Mon Sep 17 00:00:00 2001 From: jasontao Date: Wed, 26 Apr 2023 09:30:59 +0800 Subject: [PATCH 4088/5631] ALSA: hda: Glenfly: add HD Audio PCI IDs and HDMI Codec Vendor IDs. Add a set of HD Audio PCI IDS, and the HDMI codec vendor IDs for Glenfly Gpus. - In default_bdl_pos_adj, set bdl to 128 as Glenfly Gpus have hardware limitation, need to increase hdac interrupt interval. - In azx_first_init, enable polling mode for Glenfly Gpu. When the codec complete the command, it sends interrupt and writes response entries to memory, howerver, the write requests sometimes are not actually synchronized to memory when driver handle hdac interrupt on Glenfly Gpus. If the RIRB status is not updated in the interrupt handler, azx_rirb_get_response keeps trying to recevie a response from rirb until 1s timeout. Enabling polling mode for Glenfly Gpu can fix the issue. - In patch_gf_hdmi, set Glenlfy Gpu Codec's no_sticky_stream as it need driver to do actual clean-ups for the linked codec when switch from one codec to another. Signed-off-by: jasontao Signed-off-by: Reaper Li Link: https://lore.kernel.org/r/20230426013059.4329-1-reaperlioc@glenfly.com Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 21 +++++++++++++++++++++ sound/pci/hda/patch_hdmi.c | 22 ++++++++++++++++++++++ 2 files changed, 43 insertions(+) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 881b2f3a1551..3226691ac923 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -227,6 +227,7 @@ enum { AZX_DRIVER_ATI, AZX_DRIVER_ATIHDMI, AZX_DRIVER_ATIHDMI_NS, + AZX_DRIVER_GFHDMI, AZX_DRIVER_VIA, AZX_DRIVER_SIS, AZX_DRIVER_ULI, @@ -349,6 +350,7 @@ static const char * const driver_short_names[] = { [AZX_DRIVER_ATI] = "HDA ATI SB", [AZX_DRIVER_ATIHDMI] = "HDA ATI HDMI", [AZX_DRIVER_ATIHDMI_NS] = "HDA ATI HDMI", + [AZX_DRIVER_GFHDMI] = "HDA GF HDMI", [AZX_DRIVER_VIA] = "HDA VIA VT82xx", [AZX_DRIVER_SIS] = "HDA SIS966", [AZX_DRIVER_ULI] = "HDA ULI M5461", @@ -1743,6 +1745,12 @@ static int default_bdl_pos_adj(struct azx *chip) } switch (chip->driver_type) { + /* + * increase the bdl size for Glenfly Gpus for hardware + * limitation on hdac interrupt interval + */ + case AZX_DRIVER_GFHDMI: + return 128; case AZX_DRIVER_ICH: case AZX_DRIVER_PCH: return 1; @@ -1858,6 +1866,12 @@ static int azx_first_init(struct azx *chip) pci_write_config_dword(pci, PCI_BASE_ADDRESS_1, 0); } #endif + /* + * Fix response write request not synced to memory when handle + * hdac interrupt on Glenfly Gpus + */ + if (chip->driver_type == AZX_DRIVER_GFHDMI) + bus->polling_mode = 1; err = pcim_iomap_regions(pci, 1 << 0, "ICH HD audio"); if (err < 0) @@ -1959,6 +1973,7 @@ static int azx_first_init(struct azx *chip) chip->playback_streams = ATIHDMI_NUM_PLAYBACK; chip->capture_streams = ATIHDMI_NUM_CAPTURE; break; + case AZX_DRIVER_GFHDMI: case AZX_DRIVER_GENERIC: default: chip->playback_streams = ICH6_NUM_PLAYBACK; @@ -2727,6 +2742,12 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE(0x1002, 0xab38), .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS | AZX_DCAPS_PM_RUNTIME }, + /* GLENFLY */ + { PCI_DEVICE(0x6766, PCI_ANY_ID), + .class = PCI_CLASS_MULTIMEDIA_HD_AUDIO << 8, + .class_mask = 0xffffff, + .driver_data = AZX_DRIVER_GFHDMI | AZX_DCAPS_POSFIX_LPIB | + AZX_DCAPS_NO_MSI | AZX_DCAPS_NO_64BIT }, /* VIA VT8251/VT8237A */ { PCI_DEVICE(0x1106, 0x3288), .driver_data = AZX_DRIVER_VIA }, /* VIA GFX VT7122/VX900 */ diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index ae17e21e57c3..595b8f6f9892 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4474,6 +4474,22 @@ static int patch_via_hdmi(struct hda_codec *codec) return patch_simple_hdmi(codec, VIAHDMI_CVT_NID, VIAHDMI_PIN_NID); } +static int patch_gf_hdmi(struct hda_codec *codec) +{ + int err; + + err = patch_generic_hdmi(codec); + if (err) + return err; + + /* + * Glenfly GPUs have two codecs, stream switches from one codec to + * another, need to do actual clean-ups in codec_cleanup_stream + */ + codec->no_sticky_stream = 1; + return 0; +} + /* * patch entries */ @@ -4564,6 +4580,12 @@ HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), +HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d83, "Arise 83 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d84, "Arise 84 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d85, "Arise 85 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d86, "Arise 86 HDMI/DP", patch_gf_hdmi), +HDA_CODEC_ENTRY(0x67663d87, "Arise 87 HDMI/DP", patch_gf_hdmi), HDA_CODEC_ENTRY(0x11069f80, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f81, "VX900 HDMI/DP", patch_via_hdmi), HDA_CODEC_ENTRY(0x11069f84, "VX11 HDMI/DP", patch_generic_hdmi), -- GitLab From dbb5f7c3fae38de3e69d48b984e6f539993a02d3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 13 Apr 2023 13:38:57 -0700 Subject: [PATCH 4089/5631] sparc: unify sparc32/sparc64 archhelp Currently, entering $ make ARCH=sparc32 help prints the archhelp text for sparc64. ["sparc32" is documented (Documentation/kbuild/kbuild.rst) to be a recognized alias for 32-bit sparc.] Instead of handling ARCH=sparc or ARCH=sparc32 or ARCH=sparc64, just unify all SPARC archhelp text in one place. Fixes: 5e53879008b9 ("sparc,sparc64: unify Makefile") Signed-off-by: Randy Dunlap Suggested-by: Masahiro Yamada Signed-off-by: Masahiro Yamada --- arch/sparc/Makefile | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index a4ea5b05f288..74be90529a18 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -83,18 +83,11 @@ vdso_install: KBUILD_IMAGE := $(boot)/zImage # Don't use tabs in echo arguments. -ifeq ($(ARCH),sparc) define archhelp - echo '* image - kernel image ($(boot)/image)' - echo '* zImage - stripped kernel image ($(boot)/zImage)' + echo '* vmlinux - standard SPARC kernel' + echo ' image - kernel image ($(boot)/image)' + echo '* zImage - stripped/compressed kernel image ($(boot)/zImage)' echo ' uImage - U-Boot SPARC32 Image (only for LEON)' + echo ' vmlinux.aout - a.out kernel for SPARC64' echo ' tftpboot.img - image prepared for tftp' endef -else -define archhelp - echo '* vmlinux - standard sparc64 kernel' - echo '* zImage - stripped and compressed sparc64 kernel ($(boot)/zImage)' - echo ' vmlinux.aout - a.out kernel for sparc64' - echo ' tftpboot.img - image prepared for tftp' -endef -endif -- GitLab From 9892bd72efdc9daa7c07ca9f427ac7e5928c7704 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 25 Apr 2023 20:08:59 +0900 Subject: [PATCH 4090/5631] kbuild: deb-pkg: specify targets in debian/rules as .PHONY If a file with the same name exists, the target is not run. For example, the following command fails. $ make O=build-arch bindeb-pkg [ snip ] sed: can't read modules.order: No such file or directory make[6]: *** [../Makefile:1577: __modinst_pre] Error 2 make[5]: *** [../scripts/Makefile.package:150: intdeb-pkg] Error 2 make[4]: *** [../Makefile:1657: intdeb-pkg] Error 2 make[3]: *** [debian/rules:14: binary-arch] Error 2 dpkg-buildpackage: error: debian/rules binary subprocess returned exit status 2 make[2]: *** [../scripts/Makefile.package:139: bindeb-pkg] Error 2 Signed-off-by: Masahiro Yamada Reviewed-by: Nathan Chancellor --- scripts/package/mkdebian | 2 ++ 1 file changed, 2 insertions(+) diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index a4c2c2276223..b6cb95473548 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -269,6 +269,8 @@ cat < debian/rules srctree ?= . KERNELRELEASE = ${KERNELRELEASE} +.PHONY: clean build build-arch build-indep binary binary-arch binary-indep + build-indep: build-arch: \$(MAKE) -f \$(srctree)/Makefile ARCH=${ARCH} \ -- GitLab From b8bea9f6cdd7236c7c2238d022145e9b2f8aac22 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Jan 2023 07:15:09 -0500 Subject: [PATCH 4091/5631] nfsd: don't open-code clear_and_wake_up_bit Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 6e8712bd7c99..5b5d39ec7b01 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1174,9 +1174,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, status = nfserr_jukebox; if (status != nfs_ok) nfsd_file_unhash(nf); - clear_bit_unlock(NFSD_FILE_PENDING, &nf->nf_flags); - smp_mb__after_atomic(); - wake_up_bit(&nf->nf_flags, NFSD_FILE_PENDING); + clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); goto out; } -- GitLab From 6c31e4c98853a4ba47355ea151b36a77c42b7734 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 6 Jan 2023 10:39:00 -0500 Subject: [PATCH 4092/5631] nfsd: NFSD_FILE_KEY_INODE only needs to find GC'ed entries Since v4 files are expected to be long-lived, there's little value in closing them out of the cache when there is conflicting access. Change the comparator to also match the gc value in the key. Change both of the current users of that key to set the gc value in the key to "true". Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 5b5d39ec7b01..c36e3032d438 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -175,6 +175,8 @@ static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, switch (key->type) { case NFSD_FILE_KEY_INODE: + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) + return 1; if (nf->nf_inode != key->inode) return 1; break; @@ -695,6 +697,7 @@ nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) struct nfsd_file_lookup_key key = { .type = NFSD_FILE_KEY_INODE, .inode = inode, + .gc = true, }; struct nfsd_file *nf; @@ -1049,6 +1052,7 @@ nfsd_file_is_cached(struct inode *inode) struct nfsd_file_lookup_key key = { .type = NFSD_FILE_KEY_INODE, .inode = inode, + .gc = true, }; bool ret = false; -- GitLab From d69b8dbfd0866abc5ec84652cc1c10fc3d4d91ef Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 6 Jan 2023 10:39:01 -0500 Subject: [PATCH 4093/5631] nfsd: simplify test_bit return in NFSD_FILE_KEY_FULL comparator test_bit returns bool, so we can just compare the result of that to the key->gc value without the "!!". Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c36e3032d438..568963b8a477 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -189,7 +189,7 @@ static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, return 1; if (!nfsd_match_cred(nf->nf_cred, key->cred)) return 1; - if (!!test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) return 1; if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) return 1; -- GitLab From c6593366c0bf222be9c7561354dfb921c611745e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Jan 2023 07:15:11 -0500 Subject: [PATCH 4094/5631] nfsd: don't kill nfsd_files because of lease break error An error from break_lease is non-fatal, so we needn't destroy the nfsd_file in that case. Just put the reference like we normally would and return the error. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 29 +++++++++++++++-------------- 1 file changed, 15 insertions(+), 14 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 568963b8a477..ab37b85b7207 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1102,7 +1102,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, nf = nfsd_file_alloc(&key, may_flags); if (!nf) { status = nfserr_jukebox; - goto out_status; + goto out; } ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, @@ -1111,13 +1111,11 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, if (likely(ret == 0)) goto open_file; - nfsd_file_slab_free(&nf->nf_rcu); - nf = NULL; if (ret == -EEXIST) goto retry; trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret); status = nfserr_jukebox; - goto out_status; + goto construction_err; wait_for_construction: wait_on_bit(&nf->nf_flags, NFSD_FILE_PENDING, TASK_UNINTERRUPTIBLE); @@ -1127,29 +1125,25 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; - goto out; + goto construction_err; } open_retry = false; - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); goto retry; } - this_cpu_inc(nfsd_file_cache_hits); status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); + if (status != nfs_ok) { + nfsd_file_put(nf); + nf = NULL; + } + out: if (status == nfs_ok) { this_cpu_inc(nfsd_file_acquisitions); nfsd_file_check_write_error(nf); *pnf = nf; - } else { - if (refcount_dec_and_test(&nf->nf_ref)) - nfsd_file_free(nf); - nf = NULL; } - -out_status: put_cred(key.cred); trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; @@ -1179,6 +1173,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, if (status != nfs_ok) nfsd_file_unhash(nf); clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); + if (status == nfs_ok) + goto out; + +construction_err: + if (refcount_dec_and_test(&nf->nf_ref)) + nfsd_file_free(nf); + nf = NULL; goto out; } -- GitLab From b680cb9b737331aad271feebbedafb865504e234 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 5 Jan 2023 07:15:12 -0500 Subject: [PATCH 4095/5631] nfsd: add some comments to nfsd_file_do_acquire David Howells mentioned that he found this bit of code confusing, so sprinkle in some comments to clarify. Reported-by: David Howells Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index ab37b85b7207..50349449a4e5 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1094,6 +1094,11 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, rcu_read_unlock(); if (nf) { + /* + * If the nf is on the LRU then it holds an extra reference + * that must be put if it's removed. It had better not be + * the last one however, since we should hold another. + */ if (nfsd_file_lru_remove(nf)) WARN_ON_ONCE(refcount_dec_and_test(&nf->nf_ref)); goto wait_for_construction; -- GitLab From b2ff1bd71db2a1b193a6dde0845adcd69cbcf75e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 18 Jan 2023 12:31:37 -0500 Subject: [PATCH 4096/5631] nfsd: don't take/put an extra reference when putting a file The last thing that filp_close does is an fput, so don't bother taking and putting the extra reference. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 50349449a4e5..51e2947c21a7 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -382,10 +382,8 @@ nfsd_file_free(struct nfsd_file *nf) if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { - get_file(nf->nf_file); - filp_close(nf->nf_file, NULL); nfsd_file_check_write_error(nf); - fput(nf->nf_file); + filp_close(nf->nf_file, NULL); } /* -- GitLab From 972cc0e0924598cb293b919d39c848dc038b2c28 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 26 Jan 2023 12:21:16 -0500 Subject: [PATCH 4097/5631] nfsd: update comment over __nfsd_file_cache_purge Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 51e2947c21a7..9b7082fdd211 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -907,7 +907,8 @@ nfsd_file_cache_init(void) * @net: net-namespace to shut down the cache (may be NULL) * * Walk the nfsd_file cache and close out any that match @net. If @net is NULL, - * then close out everything. Called when an nfsd instance is being shut down. + * then close out everything. Called when an nfsd instance is being shut down, + * and when the exports table is flushed. */ static void __nfsd_file_cache_purge(struct net *net) -- GitLab From dcb779fcd4ed5984ad15991d574943d12a8693d1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 15 Feb 2023 06:53:54 -0500 Subject: [PATCH 4098/5631] nfsd: allow reaping files still under writeback On most filesystems, there is no reason to delay reaping an nfsd_file just because its underlying inode is still under writeback. nfsd just relies on client activity or the local flusher threads to do writeback. The main exception is NFS, which flushes all of its dirty data on last close. Add a new EXPORT_OP_FLUSH_ON_CLOSE flag to allow filesystems to signal that they do this, and only skip closing files under writeback on such filesystems. Also, remove a redundant NULL file pointer check in nfsd_file_check_writeback, and clean up nfs's export op flag definitions. Signed-off-by: Jeff Layton Acked-by: Anna Schumaker Signed-off-by: Chuck Lever --- fs/nfs/export.c | 9 ++++++--- fs/nfsd/filecache.c | 12 +++++++++++- include/linux/exportfs.h | 1 + 3 files changed, 18 insertions(+), 4 deletions(-) diff --git a/fs/nfs/export.c b/fs/nfs/export.c index d6a6d1ebb8fd..be686b8e0c54 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -149,7 +149,10 @@ const struct export_operations nfs_export_ops = { .encode_fh = nfs_encode_fh, .fh_to_dentry = nfs_fh_to_dentry, .get_parent = nfs_get_parent, - .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| - EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR, + .flags = EXPORT_OP_NOWCC | + EXPORT_OP_NOSUBTREECHK | + EXPORT_OP_CLOSE_BEFORE_UNLINK | + EXPORT_OP_REMOTE_FS | + EXPORT_OP_NOATOMIC_ATTR | + EXPORT_OP_FLUSH_ON_CLOSE, }; diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 9b7082fdd211..a6fa6e980277 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -402,13 +402,23 @@ nfsd_file_check_writeback(struct nfsd_file *nf) struct file *file = nf->nf_file; struct address_space *mapping; - if (!file || !(file->f_mode & FMODE_WRITE)) + /* File not open for write? */ + if (!(file->f_mode & FMODE_WRITE)) return false; + + /* + * Some filesystems (e.g. NFS) flush all dirty data on close. + * On others, there is no need to wait for writeback. + */ + if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE)) + return false; + mapping = file->f_mapping; return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) || mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); } + static bool nfsd_file_lru_add(struct nfsd_file *nf) { set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 601700fedc91..9edb29101ec8 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -220,6 +220,7 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ unsigned long flags; }; -- GitLab From c4c649ab413ba6a785b25f0edbb12f617c87db2a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 24 Nov 2022 15:09:04 -0500 Subject: [PATCH 4099/5631] NFSD: Convert filecache to rhltable While we were converting the nfs4_file hashtable to use the kernel's resizable hashtable data structure, Neil Brown observed that the list variant (rhltable) would be better for managing nfsd_file items as well. The nfsd_file hash table will contain multiple entries for the same inode -- these should be kept together on a list. And, it could be possible for exotic or malicious client behavior to cause the hash table to resize itself on every insertion. A nice simplification is that rhltable_lookup() can return a list that contains only nfsd_file items that match a given inode, which enables us to eliminate specialized hash table helper functions and use the default functions provided by the rhashtable implementation). Since we are now storing nfsd_file items for the same inode on a single list, that effectively reduces the number of hash entries that have to be tracked in the hash table. The mininum bucket count is therefore lowered. Light testing with fstests generic/531 show no regressions. Suggested-by: Neil Brown Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 311 ++++++++++++++++++-------------------------- fs/nfsd/filecache.h | 9 +- 2 files changed, 133 insertions(+), 187 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index a6fa6e980277..2f0b2d964cbb 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -74,70 +74,9 @@ static struct list_lru nfsd_file_lru; static unsigned long nfsd_file_flags; static struct fsnotify_group *nfsd_file_fsnotify_group; static struct delayed_work nfsd_filecache_laundrette; -static struct rhashtable nfsd_file_rhash_tbl +static struct rhltable nfsd_file_rhltable ____cacheline_aligned_in_smp; -enum nfsd_file_lookup_type { - NFSD_FILE_KEY_INODE, - NFSD_FILE_KEY_FULL, -}; - -struct nfsd_file_lookup_key { - struct inode *inode; - struct net *net; - const struct cred *cred; - unsigned char need; - bool gc; - enum nfsd_file_lookup_type type; -}; - -/* - * The returned hash value is based solely on the address of an in-code - * inode, a pointer to a slab-allocated object. The entropy in such a - * pointer is concentrated in its middle bits. - */ -static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed) -{ - unsigned long ptr = (unsigned long)inode; - u32 k; - - k = ptr >> L1_CACHE_SHIFT; - k &= 0x00ffffff; - return jhash2(&k, 1, seed); -} - -/** - * nfsd_file_key_hashfn - Compute the hash value of a lookup key - * @data: key on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file_lookup_key *key = data; - - return nfsd_file_inode_hash(key->inode, seed); -} - -/** - * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file - * @data: object on which to compute the hash value - * @len: rhash table's key_len parameter (unused) - * @seed: rhash table's random seed of the day - * - * Return value: - * Computed 32-bit hash value - */ -static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed) -{ - const struct nfsd_file *nf = data; - - return nfsd_file_inode_hash(nf->nf_inode, seed); -} - static bool nfsd_match_cred(const struct cred *c1, const struct cred *c2) { @@ -158,55 +97,16 @@ nfsd_match_cred(const struct cred *c1, const struct cred *c2) return true; } -/** - * nfsd_file_obj_cmpfn - Match a cache item against search criteria - * @arg: search criteria - * @ptr: cache item to check - * - * Return values: - * %0 - Item matches search criteria - * %1 - Item does not match search criteria - */ -static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct nfsd_file_lookup_key *key = arg->key; - const struct nfsd_file *nf = ptr; - - switch (key->type) { - case NFSD_FILE_KEY_INODE: - if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) - return 1; - if (nf->nf_inode != key->inode) - return 1; - break; - case NFSD_FILE_KEY_FULL: - if (nf->nf_inode != key->inode) - return 1; - if (nf->nf_may != key->need) - return 1; - if (nf->nf_net != key->net) - return 1; - if (!nfsd_match_cred(nf->nf_cred, key->cred)) - return 1; - if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc) - return 1; - if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) - return 1; - break; - } - return 0; -} - static const struct rhashtable_params nfsd_file_rhash_params = { .key_len = sizeof_field(struct nfsd_file, nf_inode), .key_offset = offsetof(struct nfsd_file, nf_inode), - .head_offset = offsetof(struct nfsd_file, nf_rhash), - .hashfn = nfsd_file_key_hashfn, - .obj_hashfn = nfsd_file_obj_hashfn, - .obj_cmpfn = nfsd_file_obj_cmpfn, - /* Reduce resizing churn on light workloads */ - .min_size = 512, /* buckets */ + .head_offset = offsetof(struct nfsd_file, nf_rlist), + + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, .automatic_shrinking = true, }; @@ -309,27 +209,27 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode) } static struct nfsd_file * -nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) +nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need, + bool want_gc) { struct nfsd_file *nf; nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL); - if (nf) { - INIT_LIST_HEAD(&nf->nf_lru); - nf->nf_birthtime = ktime_get(); - nf->nf_file = NULL; - nf->nf_cred = get_current_cred(); - nf->nf_net = key->net; - nf->nf_flags = 0; - __set_bit(NFSD_FILE_HASHED, &nf->nf_flags); - __set_bit(NFSD_FILE_PENDING, &nf->nf_flags); - if (key->gc) - __set_bit(NFSD_FILE_GC, &nf->nf_flags); - nf->nf_inode = key->inode; - refcount_set(&nf->nf_ref, 1); - nf->nf_may = key->need; - nf->nf_mark = NULL; - } + if (unlikely(!nf)) + return NULL; + + INIT_LIST_HEAD(&nf->nf_lru); + nf->nf_birthtime = ktime_get(); + nf->nf_file = NULL; + nf->nf_cred = get_current_cred(); + nf->nf_net = net; + nf->nf_flags = want_gc ? + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) : + BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING); + nf->nf_inode = inode; + refcount_set(&nf->nf_ref, 1); + nf->nf_may = need; + nf->nf_mark = NULL; return nf; } @@ -354,8 +254,8 @@ static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); - rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, - nfsd_file_rhash_params); + rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); } static bool @@ -688,8 +588,8 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out * - * An nfsd_file represents a struct file being held open on behalf of nfsd. An - * open file however can block other activity (such as leases), or cause + * An nfsd_file represents a struct file being held open on behalf of nfsd. + * An open file however can block other activity (such as leases), or cause * undesirable behavior (e.g. spurious silly-renames when reexporting NFS). * * This function is intended to find open nfsd_files when this sort of @@ -702,21 +602,17 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) static void nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - .gc = true, - }; + struct rhlist_head *tmp, *list; struct nfsd_file *nf; rcu_read_lock(); - do { - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - if (!nf) - break; + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (!test_bit(NFSD_FILE_GC, &nf->nf_flags)) + continue; nfsd_file_cond_queue(nf, dispose); - } while (1); + } rcu_read_unlock(); } @@ -840,7 +736,7 @@ nfsd_file_cache_init(void) if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1) return 0; - ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params); + ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params); if (ret) return ret; @@ -908,7 +804,7 @@ nfsd_file_cache_init(void) nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); goto out; } @@ -927,7 +823,7 @@ __nfsd_file_cache_purge(struct net *net) struct nfsd_file *nf; LIST_HEAD(dispose); - rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter); + rhltable_walk_enter(&nfsd_file_rhltable, &iter); do { rhashtable_walk_start(&iter); @@ -1033,7 +929,7 @@ nfsd_file_cache_shutdown(void) nfsd_file_mark_slab = NULL; destroy_workqueue(nfsd_filecache_wq); nfsd_filecache_wq = NULL; - rhashtable_destroy(&nfsd_file_rhash_tbl); + rhltable_destroy(&nfsd_file_rhltable); for_each_possible_cpu(i) { per_cpu(nfsd_file_cache_hits, i) = 0; @@ -1044,6 +940,35 @@ nfsd_file_cache_shutdown(void) } } +static struct nfsd_file * +nfsd_file_lookup_locked(const struct net *net, const struct cred *cred, + struct inode *inode, unsigned char need, + bool want_gc) +{ + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; + + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) { + if (nf->nf_may != need) + continue; + if (nf->nf_net != net) + continue; + if (!nfsd_match_cred(nf->nf_cred, cred)) + continue; + if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc) + continue; + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) + continue; + + if (!nfsd_file_get(nf)) + continue; + return nf; + } + return NULL; +} + /** * nfsd_file_is_cached - are there any cached open files for this inode? * @inode: inode to check @@ -1058,16 +983,20 @@ nfsd_file_cache_shutdown(void) bool nfsd_file_is_cached(struct inode *inode) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_INODE, - .inode = inode, - .gc = true, - }; + struct rhlist_head *tmp, *list; + struct nfsd_file *nf; bool ret = false; - if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params) != NULL) - ret = true; + rcu_read_lock(); + list = rhltable_lookup(&nfsd_file_rhltable, &inode, + nfsd_file_rhash_params); + rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) + if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) { + ret = true; + break; + } + rcu_read_unlock(); + trace_nfsd_file_is_cached(inode, (int)ret); return ret; } @@ -1077,14 +1006,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct file *file, struct nfsd_file **pnf, bool want_gc) { - struct nfsd_file_lookup_key key = { - .type = NFSD_FILE_KEY_FULL, - .need = may_flags & NFSD_FILE_MAY_MASK, - .net = SVC_NET(rqstp), - .gc = want_gc, - }; + unsigned char need = may_flags & NFSD_FILE_MAY_MASK; + struct net *net = SVC_NET(rqstp); + struct nfsd_file *new, *nf; + const struct cred *cred; bool open_retry = true; - struct nfsd_file *nf; + struct inode *inode; __be32 status; int ret; @@ -1092,14 +1019,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, may_flags|NFSD_MAY_OWNER_OVERRIDE); if (status != nfs_ok) return status; - key.inode = d_inode(fhp->fh_dentry); - key.cred = get_current_cred(); + inode = d_inode(fhp->fh_dentry); + cred = get_current_cred(); retry: rcu_read_lock(); - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, - nfsd_file_rhash_params); - nf = nfsd_file_get(nf); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); rcu_read_unlock(); if (nf) { @@ -1113,21 +1038,32 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, goto wait_for_construction; } - nf = nfsd_file_alloc(&key, may_flags); - if (!nf) { + new = nfsd_file_alloc(net, inode, need, want_gc); + if (!new) { status = nfserr_jukebox; goto out; } - ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl, - &key, &nf->nf_rhash, - nfsd_file_rhash_params); + rcu_read_lock(); + spin_lock(&inode->i_lock); + nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc); + if (unlikely(nf)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + nfsd_file_slab_free(&new->nf_rcu); + goto wait_for_construction; + } + nf = new; + ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist, + nfsd_file_rhash_params); + spin_unlock(&inode->i_lock); + rcu_read_unlock(); if (likely(ret == 0)) goto open_file; if (ret == -EEXIST) goto retry; - trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret); + trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret); status = nfserr_jukebox; goto construction_err; @@ -1136,7 +1072,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, /* Did construction of this file fail? */ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) { - trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf); + trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf); if (!open_retry) { status = nfserr_jukebox; goto construction_err; @@ -1158,13 +1094,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_file_check_write_error(nf); *pnf = nf; } - put_cred(key.cred); - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + put_cred(cred); + trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); - nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); + nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode); if (nf->nf_mark) { if (file) { get_file(file); @@ -1182,7 +1118,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * If construction failed, or we raced with a call to unlink() * then unhash. */ - if (status == nfs_ok && key.inode->i_nlink == 0) + if (status != nfs_ok || inode->i_nlink == 0) status = nfserr_jukebox; if (status != nfs_ok) nfsd_file_unhash(nf); @@ -1209,8 +1145,11 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * seconds after the final nfsd_file_put() in case the caller * wants to re-use it. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1230,8 +1169,11 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, * but not garbage-collected. The object is unhashed after the * final nfsd_file_put(). * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1252,8 +1194,11 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * and @file is non-NULL, use it to instantiate a new nfsd_file instead of * opening a new one. * - * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in - * network byte order is returned. + * Return values: + * %nfs_ok - @pnf points to an nfsd_file with its reference + * count boosted. + * + * On error, an nfsstat value in network byte order is returned. */ __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, @@ -1284,7 +1229,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) lru = list_lru_count(&nfsd_file_lru); rcu_read_lock(); - ht = &nfsd_file_rhash_tbl; + ht = &nfsd_file_rhltable.ht; count = atomic_read(&ht->nelems); tbl = rht_dereference_rcu(ht->tbl, ht); buckets = tbl->size; @@ -1300,7 +1245,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v) evictions += per_cpu(nfsd_file_evictions, i); } - seq_printf(m, "total entries: %u\n", count); + seq_printf(m, "total inodes: %u\n", count); seq_printf(m, "hash buckets: %u\n", buckets); seq_printf(m, "lru entries: %lu\n", lru); seq_printf(m, "cache hits: %lu\n", hits); diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index 41516a4263ea..e54165a3224f 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -29,9 +29,8 @@ struct nfsd_file_mark { * never be dereferenced, only used for comparison. */ struct nfsd_file { - struct rhash_head nf_rhash; - struct list_head nf_lru; - struct rcu_head nf_rcu; + struct rhlist_head nf_rlist; + void *nf_inode; struct file *nf_file; const struct cred *nf_cred; struct net *nf_net; @@ -40,10 +39,12 @@ struct nfsd_file { #define NFSD_FILE_REFERENCED (2) #define NFSD_FILE_GC (3) unsigned long nf_flags; - struct inode *nf_inode; /* don't deref */ refcount_t nf_ref; unsigned char nf_may; + struct nfsd_file_mark *nf_mark; + struct list_head nf_lru; + struct rcu_head nf_rcu; ktime_t nf_birthtime; }; -- GitLab From bfca7a6f0c75f5d97f5efc2c80cca55bdbf5f79a Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:15:57 -0500 Subject: [PATCH 4100/5631] lockd: purge resources held on behalf of nlm clients when shutting down It's easily possible for the server to have an outstanding lock when we go to shut down. When that happens, we often get a warning like this in the kernel log: lockd: couldn't shutdown host module for net f0000000! This is because the shutdown procedures skip removing any hosts that still have outstanding resources (locks). Eventually, things seem to get cleaned up anyway, but the log message is unsettling, and server shutdown doesn't seem to be working the way it was intended. Ensure that we tear down any resources held on behalf of a client when tearing one down for server shutdown. Reported-by: Yongcheng Yang Link: https://bugzilla.redhat.com/show_bug.cgi?id=2063818 Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/host.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/lockd/host.c b/fs/lockd/host.c index cdc8e12cdac4..127a728fcbc8 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -629,6 +629,7 @@ nlm_shutdown_hosts_net(struct net *net) rpc_shutdown_client(host->h_rpcclnt); host->h_rpcclnt = NULL; } + nlmsvc_free_host_resources(host); } /* Then, perform a garbage collection pass */ -- GitLab From c88c680c6de5077292667fae4a147fd5a6523479 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:15:58 -0500 Subject: [PATCH 4101/5631] lockd: remove 2 unused helper functions Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/lockd/lockd.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0168ac9fdda8..26c2aed31a0c 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -99,21 +99,11 @@ struct nsm_handle { /* * Rigorous type checking on sockaddr type conversions */ -static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_addr; -} - static inline struct sockaddr *nlm_addr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_addr; } -static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_srcaddr; -} - static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_srcaddr; -- GitLab From f0aa4852e63f9c1cfd4322c770e69d7e6817e906 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:15:59 -0500 Subject: [PATCH 4102/5631] lockd: move struct nlm_wait to lockd.h The next patch needs struct nlm_wait in fs/lockd/clntproc.c, so move the definition to a shared header file. As an added clean-up, drop the unused b_reclaim field. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/clntlock.c | 12 ------------ include/linux/lockd/lockd.h | 11 ++++++++++- 2 files changed, 10 insertions(+), 13 deletions(-) diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 82b19a30e0f0..464cb15c1a06 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -29,18 +29,6 @@ static int reclaimer(void *ptr); * client perspective. */ -/* - * This is the representation of a blocked client lock. - */ -struct nlm_wait { - struct list_head b_list; /* linked list */ - wait_queue_head_t b_wait; /* where to wait on */ - struct nlm_host * b_host; - struct file_lock * b_lock; /* local file lock */ - unsigned short b_reclaim; /* got to reclaim lock */ - __be32 b_status; /* grant callback status */ -}; - static LIST_HEAD(nlm_blocked); static DEFINE_SPINLOCK(nlm_blocked_lock); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 26c2aed31a0c..de5ad2c2179a 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -121,7 +121,16 @@ struct nlm_lockowner { uint32_t pid; }; -struct nlm_wait; +/* + * This is the representation of a blocked client lock. + */ +struct nlm_wait { + struct list_head b_list; /* linked list */ + wait_queue_head_t b_wait; /* where to wait on */ + struct nlm_host *b_host; + struct file_lock *b_lock; /* local file lock */ + __be32 b_status; /* grant callback status */ +}; /* * Memory chunk for NLM client RPC request. -- GitLab From 2005f5b9c35bd736c81e9f24f5c5051967c022ee Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:00 -0500 Subject: [PATCH 4103/5631] lockd: fix races in client GRANTED_MSG wait logic After the wait for a grant is done (for whatever reason), nlmclnt_block updates the status of the nlm_rqst with the status of the block. At the point it does this, however, the block is still queued its status could change at any time. This is particularly a problem when the waiting task is signaled during the wait. We can end up giving up on the lock just before the GRANTED_MSG callback comes in, and accept it even though the lock request gets back an error, leaving a dangling lock on the server. Since the nlm_wait never lives beyond the end of nlmclnt_lock, put it on the stack and add functions to allow us to enqueue and dequeue the block. Enqueue it just before the lock/wait loop, and dequeue it just after we exit the loop instead of waiting until the end of the function. Also, scrape the status at the time that we dequeue it to ensure that it's final. Reported-by: Yongcheng Yang Link: https://bugzilla.redhat.com/show_bug.cgi?id=2063818 Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/clntlock.c | 42 ++++++++++++++++++------------------- fs/lockd/clntproc.c | 28 ++++++++++++++++--------- include/linux/lockd/lockd.h | 8 ++++--- 3 files changed, 44 insertions(+), 34 deletions(-) diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 464cb15c1a06..c374ee072db3 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -82,41 +82,42 @@ void nlmclnt_done(struct nlm_host *host) } EXPORT_SYMBOL_GPL(nlmclnt_done); +void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, struct file_lock *fl) +{ + block->b_host = host; + block->b_lock = fl; + init_waitqueue_head(&block->b_wait); + block->b_status = nlm_lck_blocked; +} + /* * Queue up a lock for blocking so that the GRANTED request can see it */ -struct nlm_wait *nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl) +void nlmclnt_queue_block(struct nlm_wait *block) { - struct nlm_wait *block; - - block = kmalloc(sizeof(*block), GFP_KERNEL); - if (block != NULL) { - block->b_host = host; - block->b_lock = fl; - init_waitqueue_head(&block->b_wait); - block->b_status = nlm_lck_blocked; - - spin_lock(&nlm_blocked_lock); - list_add(&block->b_list, &nlm_blocked); - spin_unlock(&nlm_blocked_lock); - } - return block; + spin_lock(&nlm_blocked_lock); + list_add(&block->b_list, &nlm_blocked); + spin_unlock(&nlm_blocked_lock); } -void nlmclnt_finish_block(struct nlm_wait *block) +/* + * Dequeue the block and return its final status + */ +__be32 nlmclnt_dequeue_block(struct nlm_wait *block) { - if (block == NULL) - return; + __be32 status; + spin_lock(&nlm_blocked_lock); list_del(&block->b_list); + status = block->b_status; spin_unlock(&nlm_blocked_lock); - kfree(block); + return status; } /* * Block on a lock */ -int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) +int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout) { long ret; @@ -142,7 +143,6 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout) /* Reset the lock status after a server reboot so we resend */ if (block->b_status == nlm_lck_denied_grace_period) block->b_status = nlm_lck_blocked; - req->a_res.status = block->b_status; return 0; } diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index 16b4de868cd2..a14c9110719c 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -516,9 +516,10 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) const struct cred *cred = nfs_file_cred(fl->fl_file); struct nlm_host *host = req->a_host; struct nlm_res *resp = &req->a_res; - struct nlm_wait *block = NULL; + struct nlm_wait block; unsigned char fl_flags = fl->fl_flags; unsigned char fl_type; + __be32 b_status; int status = -ENOLCK; if (nsm_monitor(host) < 0) @@ -531,31 +532,41 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) if (status < 0) goto out; - block = nlmclnt_prepare_block(host, fl); + nlmclnt_prepare_block(&block, host, fl); again: /* * Initialise resp->status to a valid non-zero value, * since 0 == nlm_lck_granted */ resp->status = nlm_lck_blocked; - for(;;) { + + /* + * A GRANTED callback can come at any time -- even before the reply + * to the LOCK request arrives, so we queue the wait before + * requesting the lock. + */ + nlmclnt_queue_block(&block); + for (;;) { /* Reboot protection */ fl->fl_u.nfs_fl.state = host->h_state; status = nlmclnt_call(cred, req, NLMPROC_LOCK); if (status < 0) break; /* Did a reclaimer thread notify us of a server reboot? */ - if (resp->status == nlm_lck_denied_grace_period) + if (resp->status == nlm_lck_denied_grace_period) continue; if (resp->status != nlm_lck_blocked) break; /* Wait on an NLM blocking lock */ - status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT); + status = nlmclnt_wait(&block, req, NLMCLNT_POLL_TIMEOUT); if (status < 0) break; - if (resp->status != nlm_lck_blocked) + if (block.b_status != nlm_lck_blocked) break; } + b_status = nlmclnt_dequeue_block(&block); + if (resp->status == nlm_lck_blocked) + resp->status = b_status; /* if we were interrupted while blocking, then cancel the lock request * and exit @@ -564,7 +575,7 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) if (!req->a_args.block) goto out_unlock; if (nlmclnt_cancel(host, req->a_args.block, fl) == 0) - goto out_unblock; + goto out; } if (resp->status == nlm_granted) { @@ -593,8 +604,6 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) status = -ENOLCK; else status = nlm_stat_to_errno(resp->status); -out_unblock: - nlmclnt_finish_block(block); out: nlmclnt_release_call(req); return status; @@ -602,7 +611,6 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) /* Fatal error: ensure that we remove the lock altogether */ dprintk("lockd: lock attempt ended in fatal error.\n" " Attempting to unlock.\n"); - nlmclnt_finish_block(block); fl_type = fl->fl_type; fl->fl_type = F_UNLCK; down_read(&host->h_rwsem); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index de5ad2c2179a..f42594a9efe0 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -211,9 +211,11 @@ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host); int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *); int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); void nlmclnt_release_call(struct nlm_rqst *); -struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); -void nlmclnt_finish_block(struct nlm_wait *block); -int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); +void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, + struct file_lock *fl); +void nlmclnt_queue_block(struct nlm_wait *block); +__be32 nlmclnt_dequeue_block(struct nlm_wait *block); +int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout); __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock); void nlmclnt_recovery(struct nlm_host *); -- GitLab From 244cc19196d2f6691d34e8cd9bc34a55e4f778e5 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:01 -0500 Subject: [PATCH 4104/5631] lockd: server should unlock lock if client rejects the grant Currently lockd just dequeues the block and ignores it if the client sends a GRANT_RES with a status of nlm_lck_denied. That status is an indicator that the client has rejected the lock, so the right thing to do is to unlock the lock we were trying to grant. Reported-by: Yongcheng Yang Link: https://bugzilla.redhat.com/show_bug.cgi?id=2063818 Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svclock.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 4e30f3c50970..c43ccdf28ed9 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -954,19 +954,32 @@ void nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status) { struct nlm_block *block; + struct file_lock *fl; + int error; dprintk("grant_reply: looking for cookie %x, s=%d \n", *(unsigned int *)(cookie->data), status); if (!(block = nlmsvc_find_block(cookie))) return; - if (status == nlm_lck_denied_grace_period) { + switch (status) { + case nlm_lck_denied_grace_period: /* Try again in a couple of seconds */ nlmsvc_insert_block(block, 10 * HZ); - } else { + break; + case nlm_lck_denied: + /* Client doesn't want it, just unlock it */ + nlmsvc_unlink_block(block); + fl = &block->b_call->a_args.lock.fl; + fl->fl_type = F_UNLCK; + error = vfs_lock_file(fl->fl_file, F_SETLK, fl, NULL); + if (error) + pr_warn("lockd: unable to unlock lock rejected by client!\n"); + break; + default: /* - * Lock is now held by client, or has been rejected. - * In both cases, the block should be removed. + * Either it was accepted or the status makes no sense + * just unlink it either way. */ nlmsvc_unlink_block(block); } -- GitLab From e59fb6749ed833deee5b3cfd7e89925296d41f49 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:02 -0500 Subject: [PATCH 4105/5631] nfs: move nfs_fhandle_hash to common include file lockd needs to be able to hash filehandles for tracepoints. Move the nfs_fhandle_hash() helper to a common nfs include file. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfs/internal.h | 15 --------------- include/linux/nfs.h | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 15 deletions(-) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2a65fe2a63ab..10fb5e7573eb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -846,27 +846,12 @@ u64 nfs_timespec_to_change_attr(const struct timespec64 *ts) } #ifdef CONFIG_CRC32 -/** - * nfs_fhandle_hash - calculate the crc32 hash for the filehandle - * @fh - pointer to filehandle - * - * returns a crc32 hash for the filehandle that is compatible with - * the one displayed by "wireshark". - */ -static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) -{ - return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); -} static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid) { return ~crc32_le(0xFFFFFFFF, &stateid->other[0], NFS4_STATEID_OTHER_SIZE); } #else -static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) -{ - return 0; -} static inline u32 nfs_stateid_hash(nfs4_stateid *stateid) { return 0; diff --git a/include/linux/nfs.h b/include/linux/nfs.h index b06375e88e58..ceb70a926b95 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -10,6 +10,7 @@ #include #include +#include #include /* @@ -44,4 +45,23 @@ enum nfs3_stable_how { /* used by direct.c to mark verf as invalid */ NFS_INVALID_STABLE_HOW = -1 }; + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else /* CONFIG_CRC32 */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif /* CONFIG_CRC32 */ #endif /* _LINUX_NFS_H */ -- GitLab From 2f90e18ffec47c265c14e313047189b79784bc0e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 3 Mar 2023 07:16:03 -0500 Subject: [PATCH 4106/5631] lockd: add some client-side tracepoints Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/Makefile | 6 ++- fs/lockd/clntlock.c | 4 ++ fs/lockd/clntproc.c | 14 ++++++ fs/lockd/trace.c | 3 ++ fs/lockd/trace.h | 106 ++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 131 insertions(+), 2 deletions(-) create mode 100644 fs/lockd/trace.c create mode 100644 fs/lockd/trace.h diff --git a/fs/lockd/Makefile b/fs/lockd/Makefile index 6d5e83ed4476..ac9f9d84510e 100644 --- a/fs/lockd/Makefile +++ b/fs/lockd/Makefile @@ -3,10 +3,12 @@ # Makefile for the linux lock manager stuff # +ccflags-y += -I$(src) # needed for trace events + obj-$(CONFIG_LOCKD) += lockd.o -lockd-objs-y := clntlock.o clntproc.o clntxdr.o host.o svc.o svclock.o \ - svcshare.o svcproc.o svcsubs.o mon.o xdr.o +lockd-objs-y += clntlock.o clntproc.o clntxdr.o host.o svc.o svclock.o \ + svcshare.o svcproc.o svcsubs.o mon.o trace.o xdr.o lockd-objs-$(CONFIG_LOCKD_V4) += clnt4xdr.o xdr4.o svc4proc.o lockd-objs-$(CONFIG_PROC_FS) += procfs.o lockd-objs := $(lockd-objs-y) diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index c374ee072db3..e3972aa3045a 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -14,9 +14,12 @@ #include #include #include +#include #include #include +#include "trace.h" + #define NLMDBG_FACILITY NLMDBG_CLIENT /* @@ -186,6 +189,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock) res = nlm_granted; } spin_unlock(&nlm_blocked_lock); + trace_nlmclnt_grant(lock, addr, svc_addr_len(addr), res); return res; } diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index a14c9110719c..fba6c7fa7474 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -20,6 +20,8 @@ #include #include +#include "trace.h" + #define NLMDBG_FACILITY NLMDBG_CLIENT #define NLMCLNT_GRACE_WAIT (5*HZ) #define NLMCLNT_POLL_TIMEOUT (30*HZ) @@ -451,6 +453,9 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl) status = nlm_stat_to_errno(req->a_res.status); } out: + trace_nlmclnt_test(&req->a_args.lock, + (const struct sockaddr *)&req->a_host->h_addr, + req->a_host->h_addrlen, req->a_res.status); nlmclnt_release_call(req); return status; } @@ -605,10 +610,16 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) else status = nlm_stat_to_errno(resp->status); out: + trace_nlmclnt_lock(&req->a_args.lock, + (const struct sockaddr *)&req->a_host->h_addr, + req->a_host->h_addrlen, req->a_res.status); nlmclnt_release_call(req); return status; out_unlock: /* Fatal error: ensure that we remove the lock altogether */ + trace_nlmclnt_lock(&req->a_args.lock, + (const struct sockaddr *)&req->a_host->h_addr, + req->a_host->h_addrlen, req->a_res.status); dprintk("lockd: lock attempt ended in fatal error.\n" " Attempting to unlock.\n"); fl_type = fl->fl_type; @@ -704,6 +715,9 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl) /* What to do now? I'm out of my depth... */ status = -ENOLCK; out: + trace_nlmclnt_unlock(&req->a_args.lock, + (const struct sockaddr *)&req->a_host->h_addr, + req->a_host->h_addrlen, req->a_res.status); nlmclnt_release_call(req); return status; } diff --git a/fs/lockd/trace.c b/fs/lockd/trace.c new file mode 100644 index 000000000000..d9a6ff6e673c --- /dev/null +++ b/fs/lockd/trace.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define CREATE_TRACE_POINTS +#include "trace.h" diff --git a/fs/lockd/trace.h b/fs/lockd/trace.h new file mode 100644 index 000000000000..7461b13b6e74 --- /dev/null +++ b/fs/lockd/trace.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM lockd + +#if !defined(_TRACE_LOCKD_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_LOCKD_H + +#include +#include +#include +#include + +#ifdef CONFIG_LOCKD_V4 +#define NLM_STATUS_LIST \ + nlm_status_code(LCK_GRANTED) \ + nlm_status_code(LCK_DENIED) \ + nlm_status_code(LCK_DENIED_NOLOCKS) \ + nlm_status_code(LCK_BLOCKED) \ + nlm_status_code(LCK_DENIED_GRACE_PERIOD) \ + nlm_status_code(DEADLCK) \ + nlm_status_code(ROFS) \ + nlm_status_code(STALE_FH) \ + nlm_status_code(FBIG) \ + nlm_status_code_end(FAILED) +#else +#define NLM_STATUS_LIST \ + nlm_status_code(LCK_GRANTED) \ + nlm_status_code(LCK_DENIED) \ + nlm_status_code(LCK_DENIED_NOLOCKS) \ + nlm_status_code(LCK_BLOCKED) \ + nlm_status_code_end(LCK_DENIED_GRACE_PERIOD) +#endif + +#undef nlm_status_code +#undef nlm_status_code_end +#define nlm_status_code(x) TRACE_DEFINE_ENUM(NLM_##x); +#define nlm_status_code_end(x) TRACE_DEFINE_ENUM(NLM_##x); + +NLM_STATUS_LIST + +#undef nlm_status_code +#undef nlm_status_code_end +#define nlm_status_code(x) { NLM_##x, #x }, +#define nlm_status_code_end(x) { NLM_##x, #x } + +#define show_nlm_status(x) __print_symbolic(x, NLM_STATUS_LIST) + +DECLARE_EVENT_CLASS(nlmclnt_lock_event, + TP_PROTO( + const struct nlm_lock *lock, + const struct sockaddr *addr, + unsigned int addrlen, + __be32 status + ), + + TP_ARGS(lock, addr, addrlen, status), + + TP_STRUCT__entry( + __field(u32, oh) + __field(u32, svid) + __field(u32, fh) + __field(unsigned long, status) + __field(u64, start) + __field(u64, len) + __sockaddr(addr, addrlen) + ), + + TP_fast_assign( + __entry->oh = ~crc32_le(0xffffffff, lock->oh.data, lock->oh.len); + __entry->svid = lock->svid; + __entry->fh = nfs_fhandle_hash(&lock->fh); + __entry->start = lock->lock_start; + __entry->len = lock->lock_len; + __entry->status = be32_to_cpu(status); + __assign_sockaddr(addr, addr, addrlen); + ), + + TP_printk( + "addr=%pISpc oh=0x%08x svid=0x%08x fh=0x%08x start=%llu len=%llu status=%s", + __get_sockaddr(addr), __entry->oh, __entry->svid, + __entry->fh, __entry->start, __entry->len, + show_nlm_status(__entry->status) + ) +); + +#define DEFINE_NLMCLNT_EVENT(name) \ + DEFINE_EVENT(nlmclnt_lock_event, name, \ + TP_PROTO( \ + const struct nlm_lock *lock, \ + const struct sockaddr *addr, \ + unsigned int addrlen, \ + __be32 status \ + ), \ + TP_ARGS(lock, addr, addrlen, status)) + +DEFINE_NLMCLNT_EVENT(nlmclnt_test); +DEFINE_NLMCLNT_EVENT(nlmclnt_lock); +DEFINE_NLMCLNT_EVENT(nlmclnt_unlock); +DEFINE_NLMCLNT_EVENT(nlmclnt_grant); + +#endif /* _TRACE_LOCKD_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE trace +#include -- GitLab From cf64b9bce95095b80f4589e4f54572cc5d8c1538 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 8 Mar 2023 17:51:00 +1100 Subject: [PATCH 4107/5631] SUNRPC: return proper error from get_expiry() The get_expiry() function currently returns a timestamp, and uses the special return value of 0 to indicate an error. Unfortunately this causes a problem when 0 is the correct return value. On a system with no RTC it is possible that the boot time will be seen to be "3". When exportfs probes to see if a particular filesystem supports NFS export it tries to cache information with an expiry time of "3". The intention is for this to be "long in the past". Even with no RTC it will not be far in the future (at most a second or two) so this is harmless. But if the boot time happens to have been calculated to be "3", then get_expiry will fail incorrectly as it converts the number to "seconds since bootime" - 0. To avoid this problem we change get_expiry() to report the error quite separately from the expiry time. The error is now the return value. The expiry time is reported through a by-reference parameter. Reported-by: Jerry Zhang Tested-by: Jerry Zhang Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/export.c | 13 ++++++------- fs/nfsd/nfs4idmap.c | 8 ++++---- include/linux/sunrpc/cache.h | 15 ++++++++------- net/sunrpc/auth_gss/svcauth_gss.c | 12 ++++++------ net/sunrpc/svcauth_unix.c | 12 ++++++------ 5 files changed, 30 insertions(+), 30 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 668c7527b17e..6da74aebe1fb 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -123,11 +123,11 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) /* OK, we seem to have a valid key */ key.h.flags = 0; - key.h.expiry_time = get_expiry(&mesg); - if (key.h.expiry_time == 0) + err = get_expiry(&mesg, &key.h.expiry_time); + if (err) goto out; - key.ek_client = dom; + key.ek_client = dom; key.ek_fsidtype = fsidtype; memcpy(key.ek_fsid, buf, len); @@ -610,9 +610,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_devid_map = NULL; /* expiry */ - err = -EINVAL; - exp.h.expiry_time = get_expiry(&mesg); - if (exp.h.expiry_time == 0) + err = get_expiry(&mesg, &exp.h.expiry_time); + if (err) goto out3; /* flags */ @@ -624,7 +623,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (err || an_int < 0) goto out3; exp.ex_flags= an_int; - + /* anon uid */ err = get_int(&mesg, &an_int); if (err) diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 5e9809aff37e..7a806ac13e31 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -240,8 +240,8 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) goto out; /* expiry */ - ent.h.expiry_time = get_expiry(&buf); - if (ent.h.expiry_time == 0) + error = get_expiry(&buf, &ent.h.expiry_time); + if (error) goto out; error = -ENOMEM; @@ -408,8 +408,8 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen) memcpy(ent.name, buf1, sizeof(ent.name)); /* expiry */ - ent.h.expiry_time = get_expiry(&buf); - if (ent.h.expiry_time == 0) + error = get_expiry(&buf, &ent.h.expiry_time); + if (error) goto out; /* ID */ diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ec5a555df96f..518bd28f5ab8 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -300,17 +300,18 @@ static inline int get_time(char **bpp, time64_t *time) return 0; } -static inline time64_t get_expiry(char **bpp) +static inline int get_expiry(char **bpp, time64_t *rvp) { - time64_t rv; + int error; struct timespec64 boot; - if (get_time(bpp, &rv)) - return 0; - if (rv < 0) - return 0; + error = get_time(bpp, rvp); + if (error) + return error; + getboottime64(&boot); - return rv - boot.tv_sec; + (*rvp) -= boot.tv_sec; + return 0; } #endif /* _LINUX_SUNRPC_CACHE_H_ */ diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 9c843974bb48..c4a566737085 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -257,11 +257,11 @@ static int rsi_parse(struct cache_detail *cd, rsii.h.flags = 0; /* expiry */ - expiry = get_expiry(&mesg); - status = -EINVAL; - if (expiry == 0) + status = get_expiry(&mesg, &expiry); + if (status) goto out; + status = -EINVAL; /* major/minor */ len = qword_get(&mesg, buf, mlen); if (len <= 0) @@ -483,11 +483,11 @@ static int rsc_parse(struct cache_detail *cd, rsci.h.flags = 0; /* expiry */ - expiry = get_expiry(&mesg); - status = -EINVAL; - if (expiry == 0) + status = get_expiry(&mesg, &expiry); + if (status) goto out; + status = -EINVAL; rscp = rsc_lookup(cd, &rsci); if (!rscp) goto out; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 4246363cb095..4485088ce27b 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -225,9 +225,9 @@ static int ip_map_parse(struct cache_detail *cd, return -EINVAL; } - expiry = get_expiry(&mesg); - if (expiry ==0) - return -EINVAL; + err = get_expiry(&mesg, &expiry); + if (err) + return err; /* domainname, or empty for NEGATIVE */ len = qword_get(&mesg, buf, mlen); @@ -506,9 +506,9 @@ static int unix_gid_parse(struct cache_detail *cd, uid = make_kuid(current_user_ns(), id); ug.uid = uid; - expiry = get_expiry(&mesg); - if (expiry == 0) - return -EINVAL; + err = get_expiry(&mesg, &expiry); + if (err) + return err; rv = get_int(&mesg, &gids); if (rv || gids < 0 || gids > 8192) -- GitLab From 376bcd9b37632cf191711a68aa25ab42f0048c2e Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Sat, 11 Mar 2023 15:39:40 -0800 Subject: [PATCH 4108/5631] sunrpc: simplify two-level sysctl registration for svcrdma_parm_table There is no need to declare two tables to just create directories, this can be easily be done with a prefix path with register_sysctl(). Simplify this registration. Signed-off-by: Luis Chamberlain Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- net/sunrpc/xprtrdma/svc_rdma.c | 21 ++------------------- 1 file changed, 2 insertions(+), 19 deletions(-) diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 5bc20e9d09cd..f0d5eeed4c88 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -212,24 +212,6 @@ static struct ctl_table svcrdma_parm_table[] = { { }, }; -static struct ctl_table svcrdma_table[] = { - { - .procname = "svc_rdma", - .mode = 0555, - .child = svcrdma_parm_table - }, - { }, -}; - -static struct ctl_table svcrdma_root_table[] = { - { - .procname = "sunrpc", - .mode = 0555, - .child = svcrdma_table - }, - { }, -}; - static void svc_rdma_proc_cleanup(void) { if (!svcrdma_table_header) @@ -263,7 +245,8 @@ static int svc_rdma_proc_init(void) if (rc) goto out_err; - svcrdma_table_header = register_sysctl_table(svcrdma_root_table); + svcrdma_table_header = register_sysctl("sunrpc/svc_rdma", + svcrdma_parm_table); return 0; out_err: -- GitLab From 0f5162480bd25bd97b91c9153db7afbd89698804 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 17 Mar 2023 17:09:20 -0400 Subject: [PATCH 4109/5631] NFSD: Watch for rq_pages bounds checking errors in nfsd_splice_actor() There have been several bugs over the years where the NFSD splice actor has attempted to write outside the rq_pages array. This is a "should never happen" condition, but if for some reason the pipe splice actor should attempt to walk past the end of rq_pages, it needs to terminate the READ operation to prevent corruption of the pointer addresses in the fields just beyond the array. A server crash is thus prevented. Since the code is not behaving, the READ operation returns -EIO to the client. None of the READ payload data can be trusted if the splice actor isn't operating as expected. Suggested-by: Jeff Layton Signed-off-by: Chuck Lever Reviewed-by: Jeff Layton --- fs/nfsd/vfs.c | 6 +++++- include/linux/sunrpc/svc.h | 2 +- include/trace/events/sunrpc.h | 25 +++++++++++++++++++++++++ net/sunrpc/svc.c | 15 ++++++++++++++- 4 files changed, 45 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 5783209f17fc..10aa68ca82ef 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -930,6 +930,9 @@ nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, * Grab and keep cached pages associated with a file in the svc_rqst * so that they can be passed to the network sendmsg/sendpage routines * directly. They will be released after the sending has completed. + * + * Return values: Number of bytes consumed, or -EIO if there are no + * remaining pages in rqstp->rq_pages. */ static int nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, @@ -948,7 +951,8 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf, */ if (page == *(rqstp->rq_next_page - 1)) continue; - svc_rqst_replace_page(rqstp, page); + if (unlikely(!svc_rqst_replace_page(rqstp, page))) + return -EIO; } if (rqstp->rq_res.page_len == 0) // first call rqstp->rq_res.page_base = offset % PAGE_SIZE; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 877891536c2f..f5af055280ff 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -422,7 +422,7 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -void svc_rqst_replace_page(struct svc_rqst *rqstp, +bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 3ca54536f8f7..5a3bb42e1f50 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1790,6 +1790,31 @@ DEFINE_EVENT(svc_rqst_status, svc_send, TP_PROTO(const struct svc_rqst *rqst, int status), TP_ARGS(rqst, status)); +TRACE_EVENT(svc_replace_page_err, + TP_PROTO(const struct svc_rqst *rqst), + + TP_ARGS(rqst), + TP_STRUCT__entry( + SVC_RQST_ENDPOINT_FIELDS(rqst) + + __field(const void *, begin) + __field(const void *, respages) + __field(const void *, nextpage) + ), + + TP_fast_assign( + SVC_RQST_ENDPOINT_ASSIGNMENTS(rqst); + + __entry->begin = rqst->rq_pages; + __entry->respages = rqst->rq_respages; + __entry->nextpage = rqst->rq_next_page; + ), + + TP_printk(SVC_RQST_ENDPOINT_FORMAT " begin=%p respages=%p nextpage=%p", + SVC_RQST_ENDPOINT_VARARGS, + __entry->begin, __entry->respages, __entry->nextpage) +); + TRACE_EVENT(svc_stats_latency, TP_PROTO( const struct svc_rqst *rqst diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index fea7ce8fba14..633aa1eb476b 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -842,9 +842,21 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads); * * When replacing a page in rq_pages, batch the release of the * replaced pages to avoid hammering the page allocator. + * + * Return values: + * %true: page replaced + * %false: array bounds checking failed */ -void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) +bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) { + struct page **begin = rqstp->rq_pages; + struct page **end = &rqstp->rq_pages[RPCSVC_MAXPAGES]; + + if (unlikely(rqstp->rq_next_page < begin || rqstp->rq_next_page > end)) { + trace_svc_replace_page_err(rqstp); + return false; + } + if (*rqstp->rq_next_page) { if (!pagevec_space(&rqstp->rq_pvec)) __pagevec_release(&rqstp->rq_pvec); @@ -853,6 +865,7 @@ void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) get_page(page); *(rqstp->rq_next_page++) = page; + return true; } EXPORT_SYMBOL_GPL(svc_rqst_replace_page); -- GitLab From ae0d77708aae219a9264a74188d5c1b1a5754da6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 7 Mar 2023 09:14:46 -0500 Subject: [PATCH 4110/5631] SUNRPC: Ensure server-side sockets have a sock->file The TLS handshake upcall mechanism requires a non-NULL sock->file on the socket it hands to user space. svc_sock_free() already releases sock->file properly if one exists. Signed-off-by: Chuck Lever --- net/sunrpc/svcsock.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 03a4f5615086..302a14dd7882 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1293,26 +1293,37 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct socket *sock, int flags) { + struct file *filp = NULL; struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); - int err = 0; svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); if (!svsk) return ERR_PTR(-ENOMEM); + if (!sock->file) { + filp = sock_alloc_file(sock, O_NONBLOCK, NULL); + if (IS_ERR(filp)) { + kfree(svsk); + return ERR_CAST(filp); + } + } + inet = sock->sk; - /* Register socket with portmapper */ - if (pmap_register) + if (pmap_register) { + int err; + err = svc_register(serv, sock_net(sock->sk), inet->sk_family, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); - - if (err < 0) { - kfree(svsk); - return ERR_PTR(err); + if (err < 0) { + if (filp) + fput(filp); + kfree(svsk); + return ERR_PTR(err); + } } svsk->sk_sock = sock; -- GitLab From 55fcc7d9159de886296626e47db2c81f8578c7e1 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 3 Apr 2023 13:53:07 -0400 Subject: [PATCH 4111/5631] SUNRPC: Ignore return value of ->xpo_sendto Clean up: All callers of svc_process() ignore its return value, so svc_process() can safely be converted to return void. Ditto for svc_send(). The return value of ->xpo_sendto() is now used only as part of a trace event. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 2 +- include/linux/sunrpc/svcsock.h | 2 +- net/sunrpc/svc.c | 13 +++++++------ net/sunrpc/svc_xprt.c | 21 +++++++++------------ 4 files changed, 18 insertions(+), 20 deletions(-) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index f5af055280ff..2d31121fc2e6 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -430,7 +430,7 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -int svc_process(struct svc_rqst *); +void svc_process(struct svc_rqst *rqstp); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); int svc_register(const struct svc_serv *, struct net *, const int, diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index bcc555c7ae9c..dd73fa174af5 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -56,7 +56,7 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_close_net(struct svc_serv *, struct net *); int svc_recv(struct svc_rqst *, long); -int svc_send(struct svc_rqst *); +void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); bool svc_alien_sock(struct net *net, int fd); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 633aa1eb476b..0aa8892fad63 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1444,11 +1444,12 @@ svc_process_common(struct svc_rqst *rqstp) goto sendit; } -/* - * Process the RPC request. +/** + * svc_process - Execute one RPC transaction + * @rqstp: RPC transaction context + * */ -int -svc_process(struct svc_rqst *rqstp) +void svc_process(struct svc_rqst *rqstp) { struct kvec *resv = &rqstp->rq_res.head[0]; __be32 *p; @@ -1484,7 +1485,8 @@ svc_process(struct svc_rqst *rqstp) if (!svc_process_common(rqstp)) goto out_drop; - return svc_send(rqstp); + svc_send(rqstp); + return; out_baddir: svc_printk(rqstp, "bad direction 0x%08x, dropping request\n", @@ -1492,7 +1494,6 @@ svc_process(struct svc_rqst *rqstp) rqstp->rq_server->sv_stats->rpcbadfmt++; out_drop: svc_drop(rqstp); - return 0; } EXPORT_SYMBOL_GPL(svc_process); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index ba629297da4e..36c79b718323 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -909,18 +909,20 @@ void svc_drop(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_drop); -/* - * Return reply to client. +/** + * svc_send - Return reply to client + * @rqstp: RPC transaction context + * */ -int svc_send(struct svc_rqst *rqstp) +void svc_send(struct svc_rqst *rqstp) { struct svc_xprt *xprt; - int len = -EFAULT; struct xdr_buf *xb; + int status; xprt = rqstp->rq_xprt; if (!xprt) - goto out; + return; /* calculate over-all length */ xb = &rqstp->rq_res; @@ -930,15 +932,10 @@ int svc_send(struct svc_rqst *rqstp) trace_svc_xdr_sendto(rqstp->rq_xid, xb); trace_svc_stats_latency(rqstp); - len = xprt->xpt_ops->xpo_sendto(rqstp); + status = xprt->xpt_ops->xpo_sendto(rqstp); - trace_svc_send(rqstp, len); + trace_svc_send(rqstp, status); svc_xprt_release(rqstp); - - if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN) - len = 0; -out: - return len; } /* -- GitLab From 92e4a6733f922f0fef1d0995f7b2d0eaff86c7ea Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 14 Apr 2023 17:31:44 -0400 Subject: [PATCH 4112/5631] nfsd: simplify the delayed disposal list code When queueing a dispose list to the appropriate "freeme" lists, it pointlessly queues the objects one at a time to an intermediate list. Remove a few helpers and just open code a list_move to make it more clear and efficient. Better document the resulting functions with kerneldoc comments. Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 64 ++++++++++++++++----------------------------- 1 file changed, 22 insertions(+), 42 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 2f0b2d964cbb..f40d8f3b35a4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -402,49 +402,26 @@ nfsd_file_dispose_list(struct list_head *dispose) } } -static void -nfsd_file_list_remove_disposal(struct list_head *dst, - struct nfsd_fcache_disposal *l) -{ - spin_lock(&l->lock); - list_splice_init(&l->freeme, dst); - spin_unlock(&l->lock); -} - -static void -nfsd_file_list_add_disposal(struct list_head *files, struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; - - spin_lock(&l->lock); - list_splice_tail_init(files, &l->freeme); - spin_unlock(&l->lock); - queue_work(nfsd_filecache_wq, &l->work); -} - -static void -nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src, - struct net *net) -{ - struct nfsd_file *nf, *tmp; - - list_for_each_entry_safe(nf, tmp, src, nf_lru) { - if (nf->nf_net == net) - list_move_tail(&nf->nf_lru, dst); - } -} - +/** + * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * @dispose: list of nfsd_files to be disposed + * + * Transfers each file to the "freeme" list for its nfsd_net, to eventually + * be disposed of by the per-net garbage collector. + */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { - LIST_HEAD(list); - struct nfsd_file *nf; - while(!list_empty(dispose)) { - nf = list_first_entry(dispose, struct nfsd_file, nf_lru); - nfsd_file_list_add_pernet(&list, dispose, nf->nf_net); - nfsd_file_list_add_disposal(&list, nf->nf_net); + struct nfsd_file *nf = list_first_entry(dispose, + struct nfsd_file, nf_lru); + struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); + struct nfsd_fcache_disposal *l = nn->fcache_disposal; + + spin_lock(&l->lock); + list_move_tail(&nf->nf_lru, &l->freeme); + spin_unlock(&l->lock); + queue_work(nfsd_filecache_wq, &l->work); } } @@ -665,8 +642,8 @@ nfsd_file_close_inode_sync(struct inode *inode) * nfsd_file_delayed_close - close unused nfsd_files * @work: dummy * - * Walk the LRU list and destroy any entries that have not been used since - * the last scan. + * Scrape the freeme list for this nfsd_net, and then dispose of them + * all. */ static void nfsd_file_delayed_close(struct work_struct *work) @@ -675,7 +652,10 @@ nfsd_file_delayed_close(struct work_struct *work) struct nfsd_fcache_disposal *l = container_of(work, struct nfsd_fcache_disposal, work); - nfsd_file_list_remove_disposal(&head, l); + spin_lock(&l->lock); + list_splice_init(&l->freeme, &head); + spin_unlock(&l->lock); + nfsd_file_dispose_list(&head); } -- GitLab From b20cb39def085723868972182fb58fa906839a4f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Apr 2023 20:17:56 -0400 Subject: [PATCH 4113/5631] SUNRPC: Relocate svc_free_res_pages() Clean-up: There doesn't seem to be a reason why this function is stuck in a header. One thing it prevents is the convenient addition of tracing. Moving it to a source file also makes the rq_respages clean-up logic easier to find. Reviewed-by: Calum Mackay Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 12 +----------- net/sunrpc/svc.c | 19 +++++++++++++++++++ net/sunrpc/svc_xprt.c | 2 +- 3 files changed, 21 insertions(+), 12 deletions(-) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 2d31121fc2e6..762d7231e574 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -309,17 +309,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } -static inline void svc_free_res_pages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_next_page != rqstp->rq_respages) { - struct page **pp = --rqstp->rq_next_page; - if (*pp) { - put_page(*pp); - *pp = NULL; - } - } -} - struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -424,6 +413,7 @@ struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); +void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0aa8892fad63..0fc70cc405b2 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -869,6 +869,25 @@ bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page) } EXPORT_SYMBOL_GPL(svc_rqst_replace_page); +/** + * svc_rqst_release_pages - Release Reply buffer pages + * @rqstp: RPC transaction context + * + * Release response pages that might still be in flight after + * svc_send, and any spliced filesystem-owned pages. + */ +void svc_rqst_release_pages(struct svc_rqst *rqstp) +{ + while (rqstp->rq_next_page != rqstp->rq_respages) { + struct page **pp = --rqstp->rq_next_page; + + if (*pp) { + put_page(*pp); + *pp = NULL; + } + } +} + /* * Called from a server thread as it's exiting. Caller must hold the "service * mutex" for the service. diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 36c79b718323..533e08c4f319 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -542,7 +542,7 @@ static void svc_xprt_release(struct svc_rqst *rqstp) rqstp->rq_deferred = NULL; pagevec_release(&rqstp->rq_pvec); - svc_free_res_pages(rqstp); + svc_rqst_release_pages(rqstp); rqstp->rq_res.page_len = 0; rqstp->rq_res.page_base = 0; -- GitLab From 647a2a6428f2cd01e53079ac16e17fdeff229e68 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Apr 2023 20:18:02 -0400 Subject: [PATCH 4114/5631] SUNRPC: Convert svc_xprt_release() to the release_pages() API Instead of invoking put_page() one-at-a-time, pass the "response" portion of rq_pages directly to release_pages() to reduce the number of times each nfsd thread invokes a page allocator API. Since svc_xprt_release() is not invoked while a client is waiting for an RPC Reply, this is not expected to directly impact mean request latencies on a lightly or moderately loaded server. However as workload intensity increases, I expect somewhat better scalability: the same number of server threads should be able to handle more work. Reviewed-by: Calum Mackay Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 0fc70cc405b2..b982f802f2a0 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -878,13 +878,12 @@ EXPORT_SYMBOL_GPL(svc_rqst_replace_page); */ void svc_rqst_release_pages(struct svc_rqst *rqstp) { - while (rqstp->rq_next_page != rqstp->rq_respages) { - struct page **pp = --rqstp->rq_next_page; + int i, count = rqstp->rq_next_page - rqstp->rq_respages; - if (*pp) { - put_page(*pp); - *pp = NULL; - } + if (count) { + release_pages(rqstp->rq_respages, count); + for (i = 0; i < count; i++) + rqstp->rq_respages[i] = NULL; } } -- GitLab From 7c339fb4d8577792378136c15fde773cfb863cb8 Mon Sep 17 00:00:00 2001 From: Tze-nan Wu Date: Wed, 26 Apr 2023 14:20:23 +0800 Subject: [PATCH 4115/5631] ring-buffer: Ensure proper resetting of atomic variables in ring_buffer_reset_online_cpus In ring_buffer_reset_online_cpus, the buffer_size_kb write operation may permanently fail if the cpu_online_mask changes between two for_each_online_buffer_cpu loops. The number of increases and decreases on both cpu_buffer->resize_disabled and cpu_buffer->record_disabled may be inconsistent, causing some CPUs to have non-zero values for these atomic variables after the function returns. This issue can be reproduced by "echo 0 > trace" while hotplugging cpu. After reproducing success, we can find out buffer_size_kb will not be functional anymore. To prevent leaving 'resize_disabled' and 'record_disabled' non-zero after ring_buffer_reset_online_cpus returns, we ensure that each atomic variable has been set up before atomic_sub() to it. Link: https://lore.kernel.org/linux-trace-kernel/20230426062027.17451-1-Tze-nan.Wu@mediatek.com Cc: stable@vger.kernel.org Cc: Cc: npiggin@gmail.com Fixes: b23d7a5f4a07 ("ring-buffer: speed up buffer resets by avoiding synchronize_rcu for each CPU") Reviewed-by: Cheng-Jui Wang Signed-off-by: Tze-nan Wu Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 58be5b409f72..9a0cb94c3972 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5326,6 +5326,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); +/* Flag to ensure proper resetting of atomic variables */ +#define RESET_BIT (1 << 30) + /** * ring_buffer_reset_online_cpus - reset a ring buffer per CPU buffer * @buffer: The ring buffer to reset a per cpu buffer of @@ -5342,20 +5345,27 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer) for_each_online_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; - atomic_inc(&cpu_buffer->resize_disabled); + atomic_add(RESET_BIT, &cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); } /* Make sure all commits have finished */ synchronize_rcu(); - for_each_online_buffer_cpu(buffer, cpu) { + for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; + /* + * If a CPU came online during the synchronize_rcu(), then + * ignore it. + */ + if (!(atomic_read(&cpu_buffer->resize_disabled) & RESET_BIT)) + continue; + reset_disabled_cpu_buffer(cpu_buffer); atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&cpu_buffer->resize_disabled); + atomic_sub(RESET_BIT, &cpu_buffer->resize_disabled); } mutex_unlock(&buffer->mutex); -- GitLab From adace4408252cc1c9913958d71e81a688af90a30 Mon Sep 17 00:00:00 2001 From: Ken Lin Date: Wed, 26 Apr 2023 03:22:57 +0000 Subject: [PATCH 4116/5631] tracing: Add missing spaces in trace_print_hex_seq() If the buffer length is larger than 16 and concatenate is set to false, there would be missing spaces every 16 bytes. Example: Before: c5 11 10 50 05 4d 31 40 00 40 00 40 00 4d 31 4000 40 00 After: c5 11 10 50 05 4d 31 40 00 40 00 40 00 4d 31 40 00 40 00 Link: https://lore.kernel.org/linux-trace-kernel/20230426032257.3157247-1-lyenting@google.com Signed-off-by: Ken Lin Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_output.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 952cc8aa8e59..15f05faaae44 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -221,8 +221,11 @@ trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len, const char *ret = trace_seq_buffer_ptr(p); const char *fmt = concatenate ? "%*phN" : "%*ph"; - for (i = 0; i < buf_len; i += 16) + for (i = 0; i < buf_len; i += 16) { + if (!concatenate && i != 0) + trace_seq_putc(p, ' '); trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]); + } trace_seq_putc(p, 0); return ret; -- GitLab From 812489ac4dd91144a74ce65ecf232252a2e406fb Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Sat, 11 Feb 2023 19:14:06 +0900 Subject: [PATCH 4117/5631] openrisc: Properly store r31 to pt_regs on unhandled exceptions In commit 91993c8c2ed5 ("openrisc: use shadow registers to save regs on exception") the unhandled exception path was changed to do an early store of r30 instead of r31. The entry code was not updated and r31 is not getting stored to pt_regs. This patch updates the entry handler to store r31 instead of r30. We also remove some misleading commented out store r30 and r31 instructrions. I noticed this while working on adding floating point exception handling, This issue probably would never impact anything since we kill the process or Oops right away on unhandled exceptions. Fixes: 91993c8c2ed5 ("openrisc: use shadow registers to save regs on exception") Signed-off-by: Stafford Horne --- arch/openrisc/kernel/entry.S | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index 54a87bba35ca..a130c4dac48d 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -173,7 +173,6 @@ handler: ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ /* r30 already save */ ;\ -/* l.sw PT_GPR30(r1),r30*/ ;\ l.sw PT_GPR31(r1),r31 ;\ TRACE_IRQS_OFF_ENTRY ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ @@ -211,9 +210,8 @@ handler: ;\ l.sw PT_GPR27(r1),r27 ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ - /* r31 already saved */ ;\ - l.sw PT_GPR30(r1),r30 ;\ -/* l.sw PT_GPR31(r1),r31 */ ;\ + /* r30 already saved */ ;\ + l.sw PT_GPR31(r1),r31 ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 ;\ -- GitLab From 63d7f9f11e5e81de2ce8f1c7a8aaed5b0288eddf Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Fri, 14 Apr 2023 08:25:58 +0100 Subject: [PATCH 4118/5631] openrisc: Support storing and restoring fpu state OpenRISC floating point state is not so expensive to save as OpenRISC uses general purpose registers for floating point instructions. We need to save only the floating point status and control register, FPCSR. Add support to maintain the FPCSR unconditionally upon exceptions and switches. On machines that do not support FPU this will always just store 0x0 and restore is a no-op. On FPU systems this adds an additional special purpose register read/write and read/write to memory (already cached). Signed-off-by: Stafford Horne --- arch/openrisc/include/asm/ptrace.h | 4 ++-- arch/openrisc/kernel/entry.S | 14 ++++++++++++++ arch/openrisc/kernel/traps.c | 5 +++-- 3 files changed, 19 insertions(+), 4 deletions(-) diff --git a/arch/openrisc/include/asm/ptrace.h b/arch/openrisc/include/asm/ptrace.h index 01f81d4e97dc..375147ff71fc 100644 --- a/arch/openrisc/include/asm/ptrace.h +++ b/arch/openrisc/include/asm/ptrace.h @@ -59,7 +59,7 @@ struct pt_regs { * -1 for all other exceptions. */ long orig_gpr11; /* For restarting system calls */ - long dummy; /* Cheap alignment fix */ + long fpcsr; /* Floating point control status register. */ long dummy2; /* Cheap alignment fix */ }; @@ -115,6 +115,6 @@ static inline long regs_return_value(struct pt_regs *regs) #define PT_GPR31 124 #define PT_PC 128 #define PT_ORIG_GPR11 132 -#define PT_SYSCALLNO 136 +#define PT_FPCSR 136 #endif /* __ASM_OPENRISC_PTRACE_H */ diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index a130c4dac48d..c7b47e571220 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -106,6 +106,8 @@ l.mtspr r0,r3,SPR_EPCR_BASE ;\ l.lwz r3,PT_SR(r1) ;\ l.mtspr r0,r3,SPR_ESR_BASE ;\ + l.lwz r3,PT_FPCSR(r1) ;\ + l.mtspr r0,r3,SPR_FPCSR ;\ l.lwz r2,PT_GPR2(r1) ;\ l.lwz r3,PT_GPR3(r1) ;\ l.lwz r4,PT_GPR4(r1) ;\ @@ -175,6 +177,8 @@ handler: ;\ /* r30 already save */ ;\ l.sw PT_GPR31(r1),r31 ;\ TRACE_IRQS_OFF_ENTRY ;\ + l.mfspr r30,r0,SPR_FPCSR ;\ + l.sw PT_FPCSR(r1),r30 ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 @@ -215,6 +219,8 @@ handler: ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 ;\ + l.mfspr r30,r0,SPR_FPCSR ;\ + l.sw PT_FPCSR(r1),r30 ;\ l.addi r3,r1,0 ;\ /* r4 is exception EA */ ;\ l.addi r5,r0,vector ;\ @@ -1087,6 +1093,10 @@ ENTRY(_switch) l.sw PT_GPR28(r1),r28 l.sw PT_GPR30(r1),r30 + /* Store the old FPU state to new pt_regs */ + l.mfspr r29,r0,SPR_FPCSR + l.sw PT_FPCSR(r1),r29 + l.addi r11,r10,0 /* Save old 'current' to 'last' return value*/ /* We use thread_info->ksp for storing the address of the above @@ -1109,6 +1119,10 @@ ENTRY(_switch) l.lwz r29,PT_SP(r1) l.sw TI_KSP(r10),r29 + /* Restore the old value of FPCSR */ + l.lwz r29,PT_FPCSR(r1) + l.mtspr r0,r29,SPR_FPCSR + /* ...and restore the registers, except r11 because the return value * has already been set above. */ diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index fd9a0f2b66c4..f5bbe6b55849 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -75,8 +75,9 @@ void show_registers(struct pt_regs *regs) in_kernel = 0; printk("CPU #: %d\n" - " PC: %08lx SR: %08lx SP: %08lx\n", - smp_processor_id(), regs->pc, regs->sr, regs->sp); + " PC: %08lx SR: %08lx SP: %08lx FPCSR: %08lx\n", + smp_processor_id(), regs->pc, regs->sr, regs->sp, + regs->fpcsr); printk("GPR00: %08lx GPR01: %08lx GPR02: %08lx GPR03: %08lx\n", 0L, regs->gpr[1], regs->gpr[2], regs->gpr[3]); printk("GPR04: %08lx GPR05: %08lx GPR06: %08lx GPR07: %08lx\n", -- GitLab From 27267655c5313ba0f5a3caa9ad35d887d9a12574 Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Fri, 14 Apr 2023 08:27:51 +0100 Subject: [PATCH 4119/5631] openrisc: Support floating point user api Add support for handling floating point exceptions and forwarding the SIGFPE signal to processes. Also, add fpu state to sigcontext. Signed-off-by: Stafford Horne --- arch/openrisc/include/uapi/asm/elf.h | 3 +-- arch/openrisc/include/uapi/asm/ptrace.h | 4 ++++ arch/openrisc/include/uapi/asm/sigcontext.h | 1 + arch/openrisc/kernel/entry.S | 11 +++++++++-- arch/openrisc/kernel/head.S | 4 ++-- arch/openrisc/kernel/signal.c | 2 ++ arch/openrisc/kernel/traps.c | 22 +++++++++++++++++++++ 7 files changed, 41 insertions(+), 6 deletions(-) diff --git a/arch/openrisc/include/uapi/asm/elf.h b/arch/openrisc/include/uapi/asm/elf.h index e892d5061685..6868f81c281e 100644 --- a/arch/openrisc/include/uapi/asm/elf.h +++ b/arch/openrisc/include/uapi/asm/elf.h @@ -53,8 +53,7 @@ typedef unsigned long elf_greg_t; #define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t)) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; -/* A placeholder; OR32 does not have fp support yes, so no fp regs for now. */ -typedef unsigned long elf_fpregset_t; +typedef struct __or1k_fpu_state elf_fpregset_t; /* EM_OPENRISC is defined in linux/elf-em.h */ #define EM_OR32 0x8472 diff --git a/arch/openrisc/include/uapi/asm/ptrace.h b/arch/openrisc/include/uapi/asm/ptrace.h index d4fab268f6aa..a77cc9915ca8 100644 --- a/arch/openrisc/include/uapi/asm/ptrace.h +++ b/arch/openrisc/include/uapi/asm/ptrace.h @@ -30,6 +30,10 @@ struct user_regs_struct { unsigned long pc; unsigned long sr; }; + +struct __or1k_fpu_state { + unsigned long fpcsr; +}; #endif diff --git a/arch/openrisc/include/uapi/asm/sigcontext.h b/arch/openrisc/include/uapi/asm/sigcontext.h index 8ab775fc3450..ca585e4af6b8 100644 --- a/arch/openrisc/include/uapi/asm/sigcontext.h +++ b/arch/openrisc/include/uapi/asm/sigcontext.h @@ -28,6 +28,7 @@ struct sigcontext { struct user_regs_struct regs; /* needs to be first */ + struct __or1k_fpu_state fpu; unsigned long oldmask; }; diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index c7b47e571220..c9f48e750b72 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -848,9 +848,16 @@ _syscall_badsys: /******* END SYSCALL HANDLING *******/ -/* ---[ 0xd00: Trap exception ]------------------------------------------ */ +/* ---[ 0xd00: Floating Point exception ]-------------------------------- */ -UNHANDLED_EXCEPTION(_vector_0xd00,0xd00) +EXCEPTION_ENTRY(_fpe_trap_handler) + CLEAR_LWA_FLAG(r3) + /* r4: EA of fault (set by EXCEPTION_HANDLE) */ + l.jal do_fpe_trap + l.addi r3,r1,0 /* pt_regs */ + + l.j _ret_from_exception + l.nop /* ---[ 0xe00: Trap exception ]------------------------------------------ */ diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index e11699f3d6bd..439e00f81e5d 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -424,9 +424,9 @@ _dispatch_do_ipage_fault: .org 0xc00 EXCEPTION_HANDLE(_sys_call_handler) -/* ---[ 0xd00: Trap exception ]------------------------------------------ */ +/* ---[ 0xd00: Floating point exception ]--------------------------------- */ .org 0xd00 - UNHANDLED_EXCEPTION(_vector_0xd00) + EXCEPTION_HANDLE(_fpe_trap_handler) /* ---[ 0xe00: Trap exception ]------------------------------------------ */ .org 0xe00 diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 80f69740c731..4664a18f0787 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -50,6 +50,7 @@ static int restore_sigcontext(struct pt_regs *regs, err |= __copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long)); err |= __copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long)); err |= __copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long)); + err |= __copy_from_user(®s->fpcsr, &sc->fpu.fpcsr, sizeof(unsigned long)); /* make sure the SM-bit is cleared so user-mode cannot fool us */ regs->sr &= ~SPR_SR_SM; @@ -112,6 +113,7 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long)); err |= __copy_to_user(&sc->regs.pc, ®s->pc, sizeof(unsigned long)); err |= __copy_to_user(&sc->regs.sr, ®s->sr, sizeof(unsigned long)); + err |= __copy_to_user(&sc->fpu.fpcsr, ®s->fpcsr, sizeof(unsigned long)); return err; } diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index f5bbe6b55849..0aa6b07efda1 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -243,6 +243,28 @@ asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector) die("Oops", regs, 9); } +asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address) +{ + int code = FPE_FLTUNK; + unsigned long fpcsr = regs->fpcsr; + + if (fpcsr & SPR_FPCSR_IVF) + code = FPE_FLTINV; + else if (fpcsr & SPR_FPCSR_OVF) + code = FPE_FLTOVF; + else if (fpcsr & SPR_FPCSR_UNF) + code = FPE_FLTUND; + else if (fpcsr & SPR_FPCSR_DZF) + code = FPE_FLTDIV; + else if (fpcsr & SPR_FPCSR_IXF) + code = FPE_FLTRES; + + /* Clear all flags */ + regs->fpcsr &= ~SPR_FPCSR_ALLF; + + force_sig_fault(SIGFPE, code, (void __user *)regs->pc); +} + asmlinkage void do_trap(struct pt_regs *regs, unsigned long address) { force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); -- GitLab From c91b4a07655d5ba67962a08dfac8bd7f45ad049c Mon Sep 17 00:00:00 2001 From: Stafford Horne Date: Fri, 14 Apr 2023 08:31:08 +0100 Subject: [PATCH 4120/5631] openrisc: Add floating point regset Define REGSET_FPU to allow reading and writing the FPCSR fpu state register. This will be used primarily by debuggers like GDB. Signed-off-by: Stafford Horne --- arch/openrisc/kernel/ptrace.c | 37 +++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c index 85ace93fc251..0b7d2ca6ba3b 100644 --- a/arch/openrisc/kernel/ptrace.c +++ b/arch/openrisc/kernel/ptrace.c @@ -84,11 +84,40 @@ static int genregs_set(struct task_struct *target, return ret; } +/* + * As OpenRISC shares GPRs and floating point registers we don't need to export + * the floating point registers again. So here we only export the fpcsr special + * purpose register. + */ +static int fpregs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + const struct pt_regs *regs = task_pt_regs(target); + + return membuf_store(&to, regs->fpcsr); +} + +static int fpregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_regs *regs = task_pt_regs(target); + int ret; + + /* FPCSR */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ®s->fpcsr, 0, 4); + return ret; +} + /* * Define the register sets available on OpenRISC under Linux */ enum or1k_regset { REGSET_GENERAL, + REGSET_FPU, }; static const struct user_regset or1k_regsets[] = { @@ -100,6 +129,14 @@ static const struct user_regset or1k_regsets[] = { .regset_get = genregs_get, .set = genregs_set, }, + [REGSET_FPU] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct __or1k_fpu_state) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = fpregs_get, + .set = fpregs_set, + }, }; static const struct user_regset_view user_or1k_native_view = { -- GitLab From e0f8ad2a705367518b5c56bf9d6da89681467c02 Mon Sep 17 00:00:00 2001 From: Shengyu Qu Date: Fri, 21 Apr 2023 23:08:15 +0800 Subject: [PATCH 4121/5631] mfd: axp20x: Add support for AXP15060 PMIC The AXP15060 is a PMIC chip produced by X-Powers, and could be connected via an I2C bus. Describe the regmap and the MFD bits, along with the registers exposed via I2C. Eventually advertise the device using a new compatible string and add support for power off the system. The driver would disable PEK function if IRQ is not configured in device tree, since some boards (For example, Starfive Visionfive 2) didn't connect IRQ line of PMIC to SOC. GPIO function isn't enabled in this commit, since its configuration operation is different from any existing AXP PMICs and needs logic modification on existing driver. GPIO support might come in later patches. Signed-off-by: Shengyu Qu Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/TY3P286MB261162D57695AC8164ED50E298609@TY3P286MB2611.JPNP286.PROD.OUTLOOK.COM --- drivers/mfd/axp20x-i2c.c | 2 + drivers/mfd/axp20x.c | 107 +++++++++++++++++++++++++++++++++++++ include/linux/mfd/axp20x.h | 85 +++++++++++++++++++++++++++++ 3 files changed, 194 insertions(+) diff --git a/drivers/mfd/axp20x-i2c.c b/drivers/mfd/axp20x-i2c.c index f49fbd307958..b4f5cb457117 100644 --- a/drivers/mfd/axp20x-i2c.c +++ b/drivers/mfd/axp20x-i2c.c @@ -65,6 +65,7 @@ static const struct of_device_id axp20x_i2c_of_match[] = { { .compatible = "x-powers,axp223", .data = (void *)AXP223_ID }, { .compatible = "x-powers,axp803", .data = (void *)AXP803_ID }, { .compatible = "x-powers,axp806", .data = (void *)AXP806_ID }, + { .compatible = "x-powers,axp15060", .data = (void *)AXP15060_ID }, { }, }; MODULE_DEVICE_TABLE(of, axp20x_i2c_of_match); @@ -78,6 +79,7 @@ static const struct i2c_device_id axp20x_i2c_id[] = { { "axp223", 0 }, { "axp803", 0 }, { "axp806", 0 }, + { "axp15060", 0 }, { }, }; MODULE_DEVICE_TABLE(i2c, axp20x_i2c_id); diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index 7720ac15c7d4..72b87aae60cc 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -43,6 +43,7 @@ static const char * const axp20x_model_names[] = { "AXP806", "AXP809", "AXP813", + "AXP15060", }; static const struct regmap_range axp152_writeable_ranges[] = { @@ -169,6 +170,31 @@ static const struct regmap_access_table axp806_volatile_table = { .n_yes_ranges = ARRAY_SIZE(axp806_volatile_ranges), }; +static const struct regmap_range axp15060_writeable_ranges[] = { + regmap_reg_range(AXP15060_PWR_OUT_CTRL1, AXP15060_DCDC_MODE_CTRL2), + regmap_reg_range(AXP15060_OUTPUT_MONITOR_DISCHARGE, AXP15060_CPUSLDO_V_CTRL), + regmap_reg_range(AXP15060_PWR_WAKEUP_CTRL, AXP15060_PWR_DISABLE_DOWN_SEQ), + regmap_reg_range(AXP15060_PEK_KEY, AXP15060_PEK_KEY), + regmap_reg_range(AXP15060_IRQ1_EN, AXP15060_IRQ2_EN), + regmap_reg_range(AXP15060_IRQ1_STATE, AXP15060_IRQ2_STATE), +}; + +static const struct regmap_range axp15060_volatile_ranges[] = { + regmap_reg_range(AXP15060_STARTUP_SRC, AXP15060_STARTUP_SRC), + regmap_reg_range(AXP15060_PWR_WAKEUP_CTRL, AXP15060_PWR_DISABLE_DOWN_SEQ), + regmap_reg_range(AXP15060_IRQ1_STATE, AXP15060_IRQ2_STATE), +}; + +static const struct regmap_access_table axp15060_writeable_table = { + .yes_ranges = axp15060_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(axp15060_writeable_ranges), +}; + +static const struct regmap_access_table axp15060_volatile_table = { + .yes_ranges = axp15060_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(axp15060_volatile_ranges), +}; + static const struct resource axp152_pek_resources[] = { DEFINE_RES_IRQ_NAMED(AXP152_IRQ_PEK_RIS_EDGE, "PEK_DBR"), DEFINE_RES_IRQ_NAMED(AXP152_IRQ_PEK_FAL_EDGE, "PEK_DBF"), @@ -237,6 +263,11 @@ static const struct resource axp809_pek_resources[] = { DEFINE_RES_IRQ_NAMED(AXP809_IRQ_PEK_FAL_EDGE, "PEK_DBF"), }; +static const struct resource axp15060_pek_resources[] = { + DEFINE_RES_IRQ_NAMED(AXP15060_IRQ_PEK_RIS_EDGE, "PEK_DBR"), + DEFINE_RES_IRQ_NAMED(AXP15060_IRQ_PEK_FAL_EDGE, "PEK_DBF"), +}; + static const struct regmap_config axp152_regmap_config = { .reg_bits = 8, .val_bits = 8, @@ -282,6 +313,15 @@ static const struct regmap_config axp806_regmap_config = { .cache_type = REGCACHE_RBTREE, }; +static const struct regmap_config axp15060_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .wr_table = &axp15060_writeable_table, + .volatile_table = &axp15060_volatile_table, + .max_register = AXP15060_IRQ2_STATE, + .cache_type = REGCACHE_RBTREE, +}; + #define INIT_REGMAP_IRQ(_variant, _irq, _off, _mask) \ [_variant##_IRQ_##_irq] = { .reg_offset = (_off), .mask = BIT(_mask) } @@ -503,6 +543,23 @@ static const struct regmap_irq axp809_regmap_irqs[] = { INIT_REGMAP_IRQ(AXP809, GPIO0_INPUT, 4, 0), }; +static const struct regmap_irq axp15060_regmap_irqs[] = { + INIT_REGMAP_IRQ(AXP15060, DIE_TEMP_HIGH_LV1, 0, 0), + INIT_REGMAP_IRQ(AXP15060, DIE_TEMP_HIGH_LV2, 0, 1), + INIT_REGMAP_IRQ(AXP15060, DCDC1_V_LOW, 0, 2), + INIT_REGMAP_IRQ(AXP15060, DCDC2_V_LOW, 0, 3), + INIT_REGMAP_IRQ(AXP15060, DCDC3_V_LOW, 0, 4), + INIT_REGMAP_IRQ(AXP15060, DCDC4_V_LOW, 0, 5), + INIT_REGMAP_IRQ(AXP15060, DCDC5_V_LOW, 0, 6), + INIT_REGMAP_IRQ(AXP15060, DCDC6_V_LOW, 0, 7), + INIT_REGMAP_IRQ(AXP15060, PEK_LONG, 1, 0), + INIT_REGMAP_IRQ(AXP15060, PEK_SHORT, 1, 1), + INIT_REGMAP_IRQ(AXP15060, GPIO1_INPUT, 1, 2), + INIT_REGMAP_IRQ(AXP15060, PEK_FAL_EDGE, 1, 3), + INIT_REGMAP_IRQ(AXP15060, PEK_RIS_EDGE, 1, 4), + INIT_REGMAP_IRQ(AXP15060, GPIO2_INPUT, 1, 5), +}; + static const struct regmap_irq_chip axp152_regmap_irq_chip = { .name = "axp152_irq_chip", .status_base = AXP152_IRQ1_STATE, @@ -582,6 +639,17 @@ static const struct regmap_irq_chip axp809_regmap_irq_chip = { .num_regs = 5, }; +static const struct regmap_irq_chip axp15060_regmap_irq_chip = { + .name = "axp15060", + .status_base = AXP15060_IRQ1_STATE, + .ack_base = AXP15060_IRQ1_STATE, + .unmask_base = AXP15060_IRQ1_EN, + .init_ack_masked = true, + .irqs = axp15060_regmap_irqs, + .num_irqs = ARRAY_SIZE(axp15060_regmap_irqs), + .num_regs = 2, +}; + static const struct mfd_cell axp20x_cells[] = { { .name = "axp20x-gpio", @@ -826,6 +894,23 @@ static const struct mfd_cell axp813_cells[] = { }, }; +static const struct mfd_cell axp15060_cells[] = { + { + .name = "axp221-pek", + .num_resources = ARRAY_SIZE(axp15060_pek_resources), + .resources = axp15060_pek_resources, + }, { + .name = "axp20x-regulator", + }, +}; + +/* For boards that don't have IRQ line connected to SOC. */ +static const struct mfd_cell axp_regulator_only_cells[] = { + { + .name = "axp20x-regulator", + }, +}; + static int axp20x_power_off(struct sys_off_data *data) { struct axp20x_dev *axp20x = data->cb_data; @@ -935,6 +1020,28 @@ int axp20x_match_device(struct axp20x_dev *axp20x) */ axp20x->regmap_irq_chip = &axp803_regmap_irq_chip; break; + case AXP15060_ID: + /* + * Don't register the power key part if there is no interrupt + * line. + * + * Since most use cases of AXP PMICs are Allwinner SOCs, board + * designers follow Allwinner's reference design and connects + * IRQ line to SOC, there's no need for those variants to deal + * with cases that IRQ isn't connected. However, AXP15660 is + * used by some other vendors' SOCs that didn't connect IRQ + * line, we need to deal with this case. + */ + if (axp20x->irq > 0) { + axp20x->nr_cells = ARRAY_SIZE(axp15060_cells); + axp20x->cells = axp15060_cells; + } else { + axp20x->nr_cells = ARRAY_SIZE(axp_regulator_only_cells); + axp20x->cells = axp_regulator_only_cells; + } + axp20x->regmap_cfg = &axp15060_regmap_config; + axp20x->regmap_irq_chip = &axp15060_regmap_irq_chip; + break; default: dev_err(dev, "unsupported AXP20X ID %lu\n", axp20x->variant); return -EINVAL; diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 2058194807bd..beb3f44f85c5 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -21,6 +21,7 @@ enum axp20x_variants { AXP806_ID, AXP809_ID, AXP813_ID, + AXP15060_ID, NR_AXP20X_VARIANTS, }; @@ -131,6 +132,39 @@ enum axp20x_variants { /* Other DCDC regulator control registers are the same as AXP803 */ #define AXP813_DCDC7_V_OUT 0x26 +#define AXP15060_STARTUP_SRC 0x00 +#define AXP15060_PWR_OUT_CTRL1 0x10 +#define AXP15060_PWR_OUT_CTRL2 0x11 +#define AXP15060_PWR_OUT_CTRL3 0x12 +#define AXP15060_DCDC1_V_CTRL 0x13 +#define AXP15060_DCDC2_V_CTRL 0x14 +#define AXP15060_DCDC3_V_CTRL 0x15 +#define AXP15060_DCDC4_V_CTRL 0x16 +#define AXP15060_DCDC5_V_CTRL 0x17 +#define AXP15060_DCDC6_V_CTRL 0x18 +#define AXP15060_ALDO1_V_CTRL 0x19 +#define AXP15060_DCDC_MODE_CTRL1 0x1a +#define AXP15060_DCDC_MODE_CTRL2 0x1b +#define AXP15060_OUTPUT_MONITOR_DISCHARGE 0x1e +#define AXP15060_IRQ_PWROK_VOFF 0x1f +#define AXP15060_ALDO2_V_CTRL 0x20 +#define AXP15060_ALDO3_V_CTRL 0x21 +#define AXP15060_ALDO4_V_CTRL 0x22 +#define AXP15060_ALDO5_V_CTRL 0x23 +#define AXP15060_BLDO1_V_CTRL 0x24 +#define AXP15060_BLDO2_V_CTRL 0x25 +#define AXP15060_BLDO3_V_CTRL 0x26 +#define AXP15060_BLDO4_V_CTRL 0x27 +#define AXP15060_BLDO5_V_CTRL 0x28 +#define AXP15060_CLDO1_V_CTRL 0x29 +#define AXP15060_CLDO2_V_CTRL 0x2a +#define AXP15060_CLDO3_V_CTRL 0x2b +#define AXP15060_CLDO4_V_CTRL 0x2d +#define AXP15060_CPUSLDO_V_CTRL 0x2e +#define AXP15060_PWR_WAKEUP_CTRL 0x31 +#define AXP15060_PWR_DISABLE_DOWN_SEQ 0x32 +#define AXP15060_PEK_KEY 0x36 + /* Interrupt */ #define AXP152_IRQ1_EN 0x40 #define AXP152_IRQ2_EN 0x41 @@ -152,6 +186,11 @@ enum axp20x_variants { #define AXP20X_IRQ5_STATE 0x4c #define AXP20X_IRQ6_STATE 0x4d +#define AXP15060_IRQ1_EN 0x40 +#define AXP15060_IRQ2_EN 0x41 +#define AXP15060_IRQ1_STATE 0x48 +#define AXP15060_IRQ2_STATE 0x49 + /* ADC */ #define AXP20X_ACIN_V_ADC_H 0x56 #define AXP20X_ACIN_V_ADC_L 0x57 @@ -222,6 +261,8 @@ enum axp20x_variants { #define AXP22X_GPIO_STATE 0x94 #define AXP22X_GPIO_PULL_DOWN 0x95 +#define AXP15060_CLDO4_GPIO2_MODESET 0x2c + /* Battery */ #define AXP20X_CHRG_CC_31_24 0xb0 #define AXP20X_CHRG_CC_23_16 0xb1 @@ -419,6 +460,33 @@ enum { AXP813_REG_ID_MAX, }; +enum { + AXP15060_DCDC1 = 0, + AXP15060_DCDC2, + AXP15060_DCDC3, + AXP15060_DCDC4, + AXP15060_DCDC5, + AXP15060_DCDC6, + AXP15060_ALDO1, + AXP15060_ALDO2, + AXP15060_ALDO3, + AXP15060_ALDO4, + AXP15060_ALDO5, + AXP15060_BLDO1, + AXP15060_BLDO2, + AXP15060_BLDO3, + AXP15060_BLDO4, + AXP15060_BLDO5, + AXP15060_CLDO1, + AXP15060_CLDO2, + AXP15060_CLDO3, + AXP15060_CLDO4, + AXP15060_CPUSLDO, + AXP15060_SW, + AXP15060_RTC_LDO, + AXP15060_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, @@ -637,6 +705,23 @@ enum axp809_irqs { AXP809_IRQ_GPIO0_INPUT, }; +enum axp15060_irqs { + AXP15060_IRQ_DIE_TEMP_HIGH_LV1 = 1, + AXP15060_IRQ_DIE_TEMP_HIGH_LV2, + AXP15060_IRQ_DCDC1_V_LOW, + AXP15060_IRQ_DCDC2_V_LOW, + AXP15060_IRQ_DCDC3_V_LOW, + AXP15060_IRQ_DCDC4_V_LOW, + AXP15060_IRQ_DCDC5_V_LOW, + AXP15060_IRQ_DCDC6_V_LOW, + AXP15060_IRQ_PEK_LONG, + AXP15060_IRQ_PEK_SHORT, + AXP15060_IRQ_GPIO1_INPUT, + AXP15060_IRQ_PEK_FAL_EDGE, + AXP15060_IRQ_PEK_RIS_EDGE, + AXP15060_IRQ_GPIO2_INPUT, +}; + struct axp20x_dev { struct device *dev; int irq; -- GitLab From 34480c6e1746138880778af9b86e86a95e0264fb Mon Sep 17 00:00:00 2001 From: Shengyu Qu Date: Fri, 21 Apr 2023 23:08:14 +0800 Subject: [PATCH 4122/5631] dt-bindings: mfd: x-powers,axp152: Document the AXP15060 variant The X-Powers AXP15060 is a PMIC seen on Starfive Visionfive 2 board. Add relative compatible item and CPUSLDO support and disables DC-DC frequency setting for it. Signed-off-by: Shengyu Qu Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/TY3P286MB261177CF7AA2959BD9517DA998609@TY3P286MB2611.JPNP286.PROD.OUTLOOK.COM --- Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml index ed76b1c58cdf..9234df27c6aa 100644 --- a/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml +++ b/Documentation/devicetree/bindings/mfd/x-powers,axp152.yaml @@ -77,7 +77,9 @@ allOf: properties: compatible: contains: - const: x-powers,axp313a + enum: + - x-powers,axp313a + - x-powers,axp15060 then: properties: @@ -97,6 +99,7 @@ properties: - x-powers,axp806 - x-powers,axp809 - x-powers,axp813 + - x-powers,axp15060 - items: - const: x-powers,axp228 - const: x-powers,axp221 @@ -265,7 +268,7 @@ properties: Defines the work frequency of DC-DC in kHz. patternProperties: - "^(([a-f])?ldo[0-9]|dcdc[0-7a-e]|ldo(_|-)io(0|1)|(dc1)?sw|rtc(_|-)ldo|drivevbus|dc5ldo)$": + "^(([a-f])?ldo[0-9]|dcdc[0-7a-e]|ldo(_|-)io(0|1)|(dc1)?sw|rtc(_|-)ldo|cpusldo|drivevbus|dc5ldo)$": $ref: /schemas/regulator/regulator.yaml# type: object unevaluatedProperties: false -- GitLab From 9f0184ac1dcb48efe724ec6482f88d85579b52df Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 16 Apr 2023 14:32:03 +0200 Subject: [PATCH 4123/5631] dt-bindings: mfd: qcom,spmi-pmic: Document flash LED controller The Qualcomm SPMI PMIC come also with a LED controller for flash LEDs, already used in DTS: sm8250-hdk.dtb: pmic@5: 'led-controller@d300' does not match any of the regexes: ... From schema: Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml Signed-off-by: Krzysztof Kozlowski Reviewed-by: Rob Herring Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230416123203.299740-1-krzysztof.kozlowski@linaro.org --- Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml index 9f4c75c35aae..36de335a33aa 100644 --- a/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml +++ b/Documentation/devicetree/bindings/mfd/qcom,spmi-pmic.yaml @@ -138,6 +138,10 @@ patternProperties: type: object $ref: /schemas/pinctrl/qcom,pmic-gpio.yaml# + "^led-controller@[0-9a-f]+$": + type: object + $ref: /schemas/leds/qcom,spmi-flash-led.yaml# + "^nvram@[0-9a-f]+$": type: object $ref: /schemas/nvmem/qcom,spmi-sdam.yaml# -- GitLab From 3808b8424b476ceb8ac7610ff3bb377ad1893847 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Wed, 19 Apr 2023 13:18:06 +0200 Subject: [PATCH 4124/5631] leds: bd2606mvv: Driver for the Rohm 6 Channel i2c LED driver The device provides 6 channels which can be individually turned off and on but groups of two channels share a common brightness register. Limitation: The GPIO to enable the device is not used yet. Signed-off-by: Andreas Kemnade Reviewed-by: Matti Vaittinen Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230419111806.1100437-3-andreas@kemnade.info --- drivers/leds/Kconfig | 14 +++ drivers/leds/Makefile | 1 + drivers/leds/leds-bd2606mvv.c | 160 ++++++++++++++++++++++++++++++++++ 3 files changed, 175 insertions(+) create mode 100644 drivers/leds/leds-bd2606mvv.c diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index 9dbce09eabac..09afc56f54f1 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -551,6 +551,20 @@ config LEDS_REGULATOR help This option enables support for regulator driven LEDs. +config LEDS_BD2606MVV + tristate "LED driver for BD2606MVV" + depends on LEDS_CLASS + depends on I2C + select REGMAP_I2C + help + This option enables support for BD2606MVV LED driver chips + accessed via the I2C bus. It supports setting brightness, with + the limitiation that there are groups of two channels sharing + a brightness setting, but not the on/off setting. + + To compile this driver as a module, choose M here: the module will + be called leds-bd2606mvv. + config LEDS_BD2802 tristate "LED driver for BD2802 RGB LED" depends on LEDS_CLASS diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index d30395d11fd8..c07d1512c745 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_LEDS_ARIEL) += leds-ariel.o obj-$(CONFIG_LEDS_AW2013) += leds-aw2013.o obj-$(CONFIG_LEDS_BCM6328) += leds-bcm6328.o obj-$(CONFIG_LEDS_BCM6358) += leds-bcm6358.o +obj-$(CONFIG_LEDS_BD2606MVV) += leds-bd2606mvv.o obj-$(CONFIG_LEDS_BD2802) += leds-bd2802.o obj-$(CONFIG_LEDS_BLINKM) += leds-blinkm.o obj-$(CONFIG_LEDS_CLEVO_MAIL) += leds-clevo-mail.o diff --git a/drivers/leds/leds-bd2606mvv.c b/drivers/leds/leds-bd2606mvv.c new file mode 100644 index 000000000000..76f9d4d70f9a --- /dev/null +++ b/drivers/leds/leds-bd2606mvv.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Andreas Kemnade + * + * Datasheet: + * https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/led_driver/bd2606mvv_1-e.pdf + * + * If LED brightness cannot be controlled independently due to shared + * brightness registers, max_brightness is set to 1 and only on/off + * is possible for the affected LED pair. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define BD2606_MAX_LEDS 6 +#define BD2606_MAX_BRIGHTNESS 63 +#define BD2606_REG_PWRCNT 3 +#define ldev_to_led(c) container_of(c, struct bd2606mvv_led, ldev) + +struct bd2606mvv_led { + unsigned int led_no; + struct led_classdev ldev; + struct bd2606mvv_priv *priv; +}; + +struct bd2606mvv_priv { + struct bd2606mvv_led leds[BD2606_MAX_LEDS]; + struct regmap *regmap; +}; + +static int +bd2606mvv_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct bd2606mvv_led *led = ldev_to_led(led_cdev); + struct bd2606mvv_priv *priv = led->priv; + int err; + + if (brightness == 0) + return regmap_update_bits(priv->regmap, + BD2606_REG_PWRCNT, + 1 << led->led_no, + 0); + + /* shared brightness register */ + err = regmap_write(priv->regmap, led->led_no / 2, + led_cdev->max_brightness == 1 ? + BD2606_MAX_BRIGHTNESS : brightness); + if (err) + return err; + + return regmap_update_bits(priv->regmap, + BD2606_REG_PWRCNT, + 1 << led->led_no, + 1 << led->led_no); +} + +static const struct regmap_config bd2606mvv_regmap = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x3, +}; + +static int bd2606mvv_probe(struct i2c_client *client) +{ + struct fwnode_handle *np, *child; + struct device *dev = &client->dev; + struct bd2606mvv_priv *priv; + struct fwnode_handle *led_fwnodes[BD2606_MAX_LEDS] = { 0 }; + int active_pairs[BD2606_MAX_LEDS / 2] = { 0 }; + int err, reg; + int i; + + np = dev_fwnode(dev); + if (!np) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->regmap = devm_regmap_init_i2c(client, &bd2606mvv_regmap); + if (IS_ERR(priv->regmap)) { + err = PTR_ERR(priv->regmap); + dev_err(dev, "Failed to allocate register map: %d\n", err); + return err; + } + + i2c_set_clientdata(client, priv); + + fwnode_for_each_available_child_node(np, child) { + struct bd2606mvv_led *led; + + err = fwnode_property_read_u32(child, "reg", ®); + if (err) { + fwnode_handle_put(child); + return err; + } + if (reg < 0 || reg >= BD2606_MAX_LEDS || led_fwnodes[reg]) { + fwnode_handle_put(child); + return -EINVAL; + } + led = &priv->leds[reg]; + led_fwnodes[reg] = child; + active_pairs[reg / 2]++; + led->priv = priv; + led->led_no = reg; + led->ldev.brightness_set_blocking = bd2606mvv_brightness_set; + led->ldev.max_brightness = BD2606_MAX_BRIGHTNESS; + } + + for (i = 0; i < BD2606_MAX_LEDS; i++) { + struct led_init_data init_data = {}; + + if (!led_fwnodes[i]) + continue; + + init_data.fwnode = led_fwnodes[i]; + /* Check whether brightness can be independently adjusted. */ + if (active_pairs[i / 2] == 2) + priv->leds[i].ldev.max_brightness = 1; + + err = devm_led_classdev_register_ext(dev, + &priv->leds[i].ldev, + &init_data); + if (err < 0) { + fwnode_handle_put(child); + return dev_err_probe(dev, err, + "couldn't register LED %s\n", + priv->leds[i].ldev.name); + } + } + return 0; +} + +static const struct of_device_id __maybe_unused of_bd2606mvv_leds_match[] = { + { .compatible = "rohm,bd2606mvv", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_bd2606mvv_leds_match); + +static struct i2c_driver bd2606mvv_driver = { + .driver = { + .name = "leds-bd2606mvv", + .of_match_table = of_match_ptr(of_bd2606mvv_leds_match), + }, + .probe_new = bd2606mvv_probe, +}; + +module_i2c_driver(bd2606mvv_driver); + +MODULE_AUTHOR("Andreas Kemnade "); +MODULE_DESCRIPTION("BD2606 LED driver"); +MODULE_LICENSE("GPL"); -- GitLab From 9e9ff39243ea8795a4833708613f884b39dc91f9 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Mon, 17 Apr 2023 20:00:19 -0500 Subject: [PATCH 4125/5631] dt-bindings: mfd: ti,j721e-system-controller: Add SoC chip ID The system-controller node also contains the chip-id node that is used to identify the SoC specific properties. Add a pattern property to match to the same, and add to the example. Signed-off-by: Nishanth Menon Acked-by: Krzysztof Kozlowski Reviewed-by: Roger Quadros Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230418010019.1222431-1-nm@ti.com --- .../bindings/mfd/ti,j721e-system-controller.yaml | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml b/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml index 76ef4352e13c..0c98d913747b 100644 --- a/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml +++ b/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml @@ -62,6 +62,12 @@ patternProperties: description: The phy node corresponding to the ethernet MAC. + "^chipid@[0-9a-f]+$": + type: object + $ref: /schemas/hwinfo/ti,k3-socinfo.yaml# + description: + The node corresponding to SoC chip identification. + required: - compatible - reg @@ -99,5 +105,10 @@ examples: reg = <0x4140 0x18>; #clock-cells = <1>; }; + + chipid@14 { + compatible = "ti,am654-chipid"; + reg = <0x14 0x4>; + }; }; ... -- GitLab From d4dda690b44a5e36b4bf108c48177cef40c80d24 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Mon, 24 Apr 2023 18:05:43 +0100 Subject: [PATCH 4126/5631] dt-bindings: riscv: add sv57 mmu-type Dumping the dtb from new versions of QEMU warns that sv57 is an undocumented mmu-type. The kernel has supported sv57 for about a year, so bring it into the fold. Signed-off-by: Conor Dooley Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230424-rival-habitual-478567c516f0@spud Signed-off-by: Palmer Dabbelt --- Documentation/devicetree/bindings/riscv/cpus.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index f24cf9601c6e..9b512c1d93fe 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -65,6 +65,7 @@ properties: - riscv,sv32 - riscv,sv39 - riscv,sv48 + - riscv,sv57 - riscv,none riscv,cbom-block-size: -- GitLab From 26e7aacb83dfd04330673c5c9ac336560da52bb3 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Mon, 24 Apr 2023 11:23:13 +0200 Subject: [PATCH 4127/5631] riscv: Allow to downgrade paging mode from the command line MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add 2 early command line parameters that allow to downgrade satp mode (using the same naming as x86): - "no5lvl": use a 4-level page table (down from sv57 to sv48) - "no4lvl": use a 3-level page table (down from sv57/sv48 to sv39) Note that going through the device tree to get the kernel command line works with ACPI too since the efi stub creates a device tree anyway with the command line. In KASAN kernels, we can't use the libfdt that early in the boot process since we are not ready to execute instrumented functions. So instead of using the "generic" libfdt, we compile our own versions of those functions that are not instrumented and that are prefixed so that they do not conflict with the generic ones. We also need the non-instrumented versions of the string functions and the prefixed versions of memcpy/memmove. This is largely inspired by commit aacd149b6238 ("arm64: head: avoid relocating the kernel twice for KASLR") from which I removed compilation flags that were not relevant to RISC-V at the moment (LTO, SCS). Also note that we have to link with -z norelro to avoid ld.lld to throw a warning with the new .got sections, like in commit 311bea3cb9ee ("arm64: link with -z norelro for LLD or aarch64-elf"). Signed-off-by: Alexandre Ghiti Tested-by: Björn Töpel Reviewed-by: Björn Töpel Link: https://lore.kernel.org/r/20230424092313.178699-2-alexghiti@rivosinc.com Signed-off-by: Palmer Dabbelt --- .../admin-guide/kernel-parameters.txt | 5 +- arch/riscv/Makefile | 3 +- arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/pi/Makefile | 39 ++++++++++++ arch/riscv/kernel/pi/cmdline_early.c | 62 +++++++++++++++++++ arch/riscv/kernel/vmlinux.lds.S | 11 +++- arch/riscv/lib/memcpy.S | 2 + arch/riscv/lib/memmove.S | 2 + arch/riscv/lib/strlen.S | 1 + arch/riscv/mm/init.c | 36 +++++++++-- 10 files changed, 154 insertions(+), 9 deletions(-) create mode 100644 arch/riscv/kernel/pi/Makefile create mode 100644 arch/riscv/kernel/pi/cmdline_early.c diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6221a1d057dd..accc400b43f1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3576,7 +3576,10 @@ emulation library even if a 387 maths coprocessor is present. - no5lvl [X86-64] Disable 5-level paging mode. Forces + no4lvl [RISCV] Disable 4-level and 5-level paging modes. Forces + kernel to use 3-level paging instead. + + no5lvl [X86-64,RISCV] Disable 5-level paging mode. Forces kernel to use 4-level paging instead. nofsgsbase [X86] Disables FSGSBASE instructions. diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index e859e1721a8f..d44d0fb98168 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -7,8 +7,9 @@ # OBJCOPYFLAGS := -O binary +LDFLAGS_vmlinux := -z norelro ifeq ($(CONFIG_RELOCATABLE),y) - LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro --emit-relocs + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext --emit-relocs KBUILD_CFLAGS += -fPIE endif ifeq ($(CONFIG_DYNAMIC_FTRACE),y) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 392fa6e35d4a..0fee73a20c87 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -87,3 +87,5 @@ obj-$(CONFIG_EFI) += efi.o obj-$(CONFIG_COMPAT) += compat_syscall_table.o obj-$(CONFIG_COMPAT) += compat_signal.o obj-$(CONFIG_COMPAT) += compat_vdso/ + +obj-$(CONFIG_64BIT) += pi/ diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile new file mode 100644 index 000000000000..5d7cb991f2b8 --- /dev/null +++ b/arch/riscv/kernel/pi/Makefile @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: GPL-2.0 +# This file was copied from arm64/kernel/pi/Makefile. + +KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ + -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \ + $(call cc-option,-mbranch-protection=none) \ + -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ + -D__DISABLE_EXPORTS -ffreestanding \ + -fno-asynchronous-unwind-tables -fno-unwind-tables \ + $(call cc-option,-fno-addrsig) + +KBUILD_CFLAGS += -mcmodel=medany + +CFLAGS_cmdline_early.o += -D__NO_FORTIFY +CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY + +GCOV_PROFILE := n +KASAN_SANITIZE := n +KCSAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +$(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ + --remove-section=.note.gnu.property \ + --prefix-alloc-sections=.init +$(obj)/%.pi.o: $(obj)/%.o FORCE + $(call if_changed,objcopy) + +$(obj)/lib-%.o: $(srctree)/lib/%.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/string.o: $(srctree)/lib/string.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE + $(call if_changed_rule,cc_o_c) + +obj-y := cmdline_early.pi.o string.pi.o ctype.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c new file mode 100644 index 000000000000..05652d13c746 --- /dev/null +++ b/arch/riscv/kernel/pi/cmdline_early.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include + +static char early_cmdline[COMMAND_LINE_SIZE]; + +/* + * Declare the functions that are exported (but prefixed) here so that LLVM + * does not complain it lacks the 'static' keyword (which, if added, makes + * LLVM complain because the function is actually unused in this file). + */ +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa); + +static char *get_early_cmdline(uintptr_t dtb_pa) +{ + const char *fdt_cmdline = NULL; + unsigned int fdt_cmdline_size = 0; + int chosen_node; + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { + chosen_node = fdt_path_offset((void *)dtb_pa, "/chosen"); + if (chosen_node >= 0) { + fdt_cmdline = fdt_getprop((void *)dtb_pa, chosen_node, + "bootargs", NULL); + if (fdt_cmdline) { + fdt_cmdline_size = strlen(fdt_cmdline); + strscpy(early_cmdline, fdt_cmdline, + COMMAND_LINE_SIZE); + } + } + } + + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || + IS_ENABLED(CONFIG_CMDLINE_FORCE) || + fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) { + strncat(early_cmdline, CONFIG_CMDLINE, + COMMAND_LINE_SIZE - fdt_cmdline_size); + } + + return early_cmdline; +} + +static u64 match_noXlvl(char *cmdline) +{ + if (strstr(cmdline, "no4lvl")) + return SATP_MODE_48; + else if (strstr(cmdline, "no5lvl")) + return SATP_MODE_57; + + return 0; +} + +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa) +{ + char *cmdline = get_early_cmdline(dtb_pa); + + return match_noXlvl(cmdline); +} diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 615ff5842690..305877d85e96 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -83,6 +83,14 @@ SECTIONS /* Start of init data section */ __init_data_begin = .; INIT_DATA_SECTION(16) + + /* Those sections result from the compilation of kernel/pi/string.c */ + .init.pidata : { + *(.init.srodata.cst8*) + *(.init__bug_table*) + *(.init.sdata*) + } + .init.bss : { *(.init.bss) /* from the EFI stub */ } @@ -128,9 +136,10 @@ SECTIONS __rela_dyn_end = .; } + .got : { *(.got*) } + #ifdef CONFIG_RELOCATABLE .data.rel : { *(.data.rel*) } - .got : { *(.got*) } .plt : { *(.plt) } .dynamic : { *(.dynamic) } .dynsym : { *(.dynsym) } diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S index 51ab716253fa..1a40d01a9543 100644 --- a/arch/riscv/lib/memcpy.S +++ b/arch/riscv/lib/memcpy.S @@ -106,3 +106,5 @@ WEAK(memcpy) 6: ret END(__memcpy) +SYM_FUNC_ALIAS(__pi_memcpy, __memcpy) +SYM_FUNC_ALIAS(__pi___memcpy, __memcpy) diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S index e0609e1f0864..838ff2022fe3 100644 --- a/arch/riscv/lib/memmove.S +++ b/arch/riscv/lib/memmove.S @@ -314,3 +314,5 @@ return_from_memmove: SYM_FUNC_END(memmove) SYM_FUNC_END(__memmove) +SYM_FUNC_ALIAS(__pi_memmove, __memmove) +SYM_FUNC_ALIAS(__pi___memmove, __memmove) diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S index db3d42d99b78..8ae3064e45ff 100644 --- a/arch/riscv/lib/strlen.S +++ b/arch/riscv/lib/strlen.S @@ -130,3 +130,4 @@ strlen_zbb: .option pop #endif SYM_FUNC_END(strlen) +SYM_FUNC_ALIAS(__pi_strlen, strlen) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bce899b180cd..3ad771571c2d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -746,6 +746,8 @@ static __init pgprot_t pgprot_from_va(uintptr_t va) #endif /* CONFIG_STRICT_KERNEL_RWX */ #if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL) +u64 __pi_set_satp_mode_from_cmdline(uintptr_t dtb_pa); + static void __init disable_pgtable_l5(void) { pgtable_l5_enabled = false; @@ -760,17 +762,39 @@ static void __init disable_pgtable_l4(void) satp_mode = SATP_MODE_39; } +static int __init print_no4lvl(char *p) +{ + pr_info("Disabled 4-level and 5-level paging"); + return 0; +} +early_param("no4lvl", print_no4lvl); + +static int __init print_no5lvl(char *p) +{ + pr_info("Disabled 5-level paging"); + return 0; +} +early_param("no5lvl", print_no5lvl); + /* * There is a simple way to determine if 4-level is supported by the * underlying hardware: establish 1:1 mapping in 4-level page table mode * then read SATP to see if the configuration was taken into account * meaning sv48 is supported. */ -static __init void set_satp_mode(void) +static __init void set_satp_mode(uintptr_t dtb_pa) { u64 identity_satp, hw_satp; uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK; - bool check_l4 = false; + u64 satp_mode_cmdline = __pi_set_satp_mode_from_cmdline(dtb_pa); + + if (satp_mode_cmdline == SATP_MODE_57) { + disable_pgtable_l5(); + } else if (satp_mode_cmdline == SATP_MODE_48) { + disable_pgtable_l5(); + disable_pgtable_l4(); + return; + } create_p4d_mapping(early_p4d, set_satp_mode_pmd, (uintptr_t)early_pud, @@ -789,7 +813,8 @@ static __init void set_satp_mode(void) retry: create_pgd_mapping(early_pg_dir, set_satp_mode_pmd, - check_l4 ? (uintptr_t)early_pud : (uintptr_t)early_p4d, + pgtable_l5_enabled ? + (uintptr_t)early_p4d : (uintptr_t)early_pud, PGDIR_SIZE, PAGE_TABLE); identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode; @@ -800,9 +825,8 @@ static __init void set_satp_mode(void) local_flush_tlb_all(); if (hw_satp != identity_satp) { - if (!check_l4) { + if (pgtable_l5_enabled) { disable_pgtable_l5(); - check_l4 = true; memset(early_pg_dir, 0, PAGE_SIZE); goto retry; } @@ -1031,7 +1055,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #endif #if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL) - set_satp_mode(); + set_satp_mode(dtb_pa); #endif /* -- GitLab From 08dc107594681040587c23a097cfa678e51f5af2 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 26 Apr 2023 16:13:32 +0200 Subject: [PATCH 4128/5631] RISC-V: hwprobe: There can only be one first Only capture the first cpu_id in order for the comparison below to be of any use. Fixes: ea3de9ce8aa2 ("RISC-V: Add a syscall for HW probing") Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Evan Green Link: https://lore.kernel.org/r/20230426141333.10063-2-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sys_riscv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 849b4170629d..c569dac7452e 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -103,8 +103,10 @@ static void hwprobe_arch_id(struct riscv_hwprobe *pair, break; } - if (first) + if (first) { id = cpu_id; + first = false; + } /* * If there's a mismatch for the given set, return -1 in the -- GitLab From b09313dd2e726fe5e1fa574cd73f5e326c6030a4 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 26 Apr 2023 16:13:33 +0200 Subject: [PATCH 4129/5631] RISC-V: hwprobe: Explicity check for -1 in vdso init id_bitsmash is unsigned. We need to explicitly check for -1, rather than use > 0. Fixes: aa5af0aa90ba ("RISC-V: Add hwprobe vDSO function and data") Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Reviewed-by: Evan Green Link: https://lore.kernel.org/r/20230426141333.10063-3-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/sys_riscv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index c569dac7452e..5db29683ebee 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -282,7 +282,7 @@ static int __init init_hwprobe_vdso_data(void) * populated) or any value returns -1 (varies across CPUs), then the * vDSO should defer to the kernel for exotic cpu masks. */ - avd->homogeneous_cpus = (id_bitsmash > 0); + avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1; return 0; } -- GitLab From 45dd403da851124412d32e3193c21de4a51d29da Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:49 +0200 Subject: [PATCH 4130/5631] efi/zboot: arm64: Inject kernel code size symbol into the zboot payload The EFI zboot code is not built as part of the kernel proper, like the ordinary EFI stub, but still needs access to symbols that are defined only internally in the kernel, and are left unexposed deliberately to avoid creating ABI inadvertently that we're stuck with later. So capture the kernel code size of the kernel image, and inject it as an ELF symbol into the object that contains the compressed payload, where it will be accessible to zboot code that needs it. Signed-off-by: Ard Biesheuvel Acked-by: Mark Rutland --- arch/arm64/boot/Makefile | 3 +++ arch/arm64/kernel/image-vars.h | 4 ++++ drivers/firmware/efi/libstub/Makefile.zboot | 2 +- drivers/firmware/efi/libstub/zboot.lds | 7 +++++++ 4 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index ae645fda90bc..1761f5972443 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -44,4 +44,7 @@ EFI_ZBOOT_BFD_TARGET := elf64-littleaarch64 EFI_ZBOOT_MACH_TYPE := ARM64 EFI_ZBOOT_FORWARD_CFI := $(CONFIG_ARM64_BTI_KERNEL) +EFI_ZBOOT_OBJCOPY_FLAGS = --add-symbol zboot_code_size=0x$(shell \ + $(NM) vmlinux|grep _kernel_codesize|cut -d' ' -f1) + include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 8309197c0ebd..35f3c7959513 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -108,4 +108,8 @@ KVM_NVHE_ALIAS(kvm_protected_mode_initialized); #endif /* CONFIG_KVM */ +#ifdef CONFIG_EFI_ZBOOT +_kernel_codesize = ABSOLUTE(__inittext_end - _text); +#endif + #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 0a9dcc2b1373..1b101d9076fd 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -40,7 +40,7 @@ quiet_cmd_compwithsize = $(quiet_cmd_$(zboot-method-y)) $(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE $(call if_changed,compwithsize) -OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) \ +OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ --rename-section .data=.gzdata,load,alloc,readonly,contents $(obj)/vmlinuz.o: $(obj)/vmlinuz FORCE $(call if_changed,objcopy) diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds index 93d33f68333b..ac8c0ef85158 100644 --- a/drivers/firmware/efi/libstub/zboot.lds +++ b/drivers/firmware/efi/libstub/zboot.lds @@ -2,6 +2,8 @@ ENTRY(__efistub_efi_zboot_header); +PROVIDE(zboot_code_size = ABSOLUTE(0)); + SECTIONS { .head : ALIGN(4096) { @@ -17,6 +19,11 @@ SECTIONS *(.gzdata) __efistub__gzdata_end = .; *(.rodata* .init.rodata* .srodata*) + + . = ALIGN(4); + __efistub_code_size = .; + LONG(zboot_code_size); + _etext = ALIGN(4096); . = _etext; } -- GitLab From 3ee23096add52c84aae23b8569a4d6fc8d47f2ac Mon Sep 17 00:00:00 2001 From: Fabio Fantoni Date: Tue, 25 Apr 2023 13:01:58 +0200 Subject: [PATCH 4131/5631] doc:it_IT: fix some typos Fix of some typos spotted reading documentation in italian and latest changes for 6.4 Signed-off-by: Fabio Fantoni Reviewed-by: Federico Vaga Link: https://lore.kernel.org/r/20230425110158.9755-1-fantonifabio@tiscali.it Signed-off-by: Jonathan Corbet --- Documentation/translations/it_IT/kernel-hacking/locking.rst | 2 +- Documentation/translations/it_IT/process/deprecated.rst | 2 +- .../translations/it_IT/process/submitting-patches.rst | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/translations/it_IT/kernel-hacking/locking.rst b/Documentation/translations/it_IT/kernel-hacking/locking.rst index a9e781d2e323..4c21cf60f775 100644 --- a/Documentation/translations/it_IT/kernel-hacking/locking.rst +++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst @@ -1030,7 +1030,7 @@ alle corse critiche, dovreste usare timer_delete_sync() (``include/linux/timer.h``) per gestire questo caso. Prima di rilasciare un temporizzatore dovreste chiamare la funzione -timer_shutdown() o timer_shutdown_sync() di modo che non venga più ricarmato. +timer_shutdown() o timer_shutdown_sync() di modo che non venga più riarmato. Ogni successivo tentativo di riarmare il temporizzatore verrà silenziosamente ignorato. diff --git a/Documentation/translations/it_IT/process/deprecated.rst b/Documentation/translations/it_IT/process/deprecated.rst index 57b501f0dfa4..ba0ed7dc154c 100644 --- a/Documentation/translations/it_IT/process/deprecated.rst +++ b/Documentation/translations/it_IT/process/deprecated.rst @@ -386,7 +386,7 @@ combinazione con struct_size() e flex_array_size():: Ci sono due casi speciali dove è necessario usare la macro DECLARE_FLEX_ARRAY() (da notare che la stessa macro è chiamata __DECLARE_FLEX_ARRAY() nei file di intestazione UAPI). Uno è quando l'array flessibile è l'unico elemento di una -struttura, e l'altro è quando è parti un unione. Per motivi non tecnici, entrambi +struttura, e l'altro quando è parte di un unione. Per motivi non tecnici, entrambi i casi d'uso non sono permessi dalla specifica C99. Per esempio, per convertire il seguente codice:: diff --git a/Documentation/translations/it_IT/process/submitting-patches.rst b/Documentation/translations/it_IT/process/submitting-patches.rst index 5131a3963e7e..06399d497843 100644 --- a/Documentation/translations/it_IT/process/submitting-patches.rst +++ b/Documentation/translations/it_IT/process/submitting-patches.rst @@ -532,7 +532,7 @@ manutentori che qualche verifica è stata fatta, fornisce un mezzo per trovare persone che possano verificare il codice in futuro, e garantisce che queste stesse persone ricevano credito per il loro lavoro. -Reviewd-by:, invece, indica che la patch è stata revisionata ed è stata +Reviewed-by:, invece, indica che la patch è stata revisionata ed è stata considerata accettabile in accordo con la dichiarazione dei revisori: Dichiarazione di svista dei revisori @@ -563,13 +563,13 @@ una modifica che si ritiene appropriata e senza alcun problema tecnico importante. Qualsiasi revisore interessato (quelli che lo hanno fatto) possono offrire il proprio Reviewed-by per la patch. Questa etichetta serve a dare credito ai revisori e a informare i manutentori sul livello di revisione -che è stato fatto sulla patch. L'etichetta Reviewd-by, quando fornita da +che è stato fatto sulla patch. L'etichetta Reviewed-by, quando fornita da revisori conosciuti per la loro conoscenza sulla materia in oggetto e per la loro serietà nella revisione, accrescerà le probabilità che la vostra patch venga integrate nel kernel. Quando si riceve una email sulla lista di discussione da un tester o -un revisore, le etichette Tested-by o Reviewd-by devono essere +un revisore, le etichette Tested-by o Reviewed-by devono essere aggiunte dall'autore quando invierà nuovamente la patch. Tuttavia, se la patch è cambiata in modo significativo, queste etichette potrebbero non avere più senso e quindi andrebbero rimosse. Solitamente si tiene traccia -- GitLab From 0b656310bfc33c5e044df9cf6013df8280ec69cc Mon Sep 17 00:00:00 2001 From: Donald Hunter Date: Mon, 24 Apr 2023 09:03:05 +0100 Subject: [PATCH 4132/5631] docs/admin-guide/mm/ksm.rst fix intraface -> interface typo Fix typo from 'intraface' to 'interface' in admin guide for KSM. Signed-off-by: Donald Hunter Link: https://lore.kernel.org/r/20230424080305.2985-1-donald.hunter@gmail.com Signed-off-by: Jonathan Corbet --- Documentation/admin-guide/mm/ksm.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst index eed51a910c94..ca0c3a384f85 100644 --- a/Documentation/admin-guide/mm/ksm.rst +++ b/Documentation/admin-guide/mm/ksm.rst @@ -20,7 +20,7 @@ content which can be replaced by a single write-protected page (which is automatically copied if a process later wants to update its content). The amount of pages that KSM daemon scans in a single pass and the time between the passes are configured using :ref:`sysfs -intraface ` +interface ` KSM only merges anonymous (private) pages, never pagecache (file) pages. KSM's merged pages were originally locked into kernel memory, but can now -- GitLab From 026b85796ab4d52af56f8a1c60d2613983ecd845 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 18 Apr 2023 15:49:52 +0200 Subject: [PATCH 4133/5631] efi/zboot: arm64: Grab code size from ELF symbol in payload Instead of relying on a dodgy dd hack to copy the image code size from the uncompressed image's PE header to the end of the compressed image, let's grab the code size from the symbol that is injected into the ELF object by the Kbuild rules that generate the compressed payload. Signed-off-by: Ard Biesheuvel Acked-by: Mark Rutland --- drivers/firmware/efi/libstub/Makefile.zboot | 14 +++----------- drivers/firmware/efi/libstub/arm64.c | 19 +++++++++++++------ drivers/firmware/efi/libstub/efistub.h | 3 +-- drivers/firmware/efi/libstub/zboot.c | 15 ++++----------- 4 files changed, 21 insertions(+), 30 deletions(-) diff --git a/drivers/firmware/efi/libstub/Makefile.zboot b/drivers/firmware/efi/libstub/Makefile.zboot index 1b101d9076fd..89ef820f3b34 100644 --- a/drivers/firmware/efi/libstub/Makefile.zboot +++ b/drivers/firmware/efi/libstub/Makefile.zboot @@ -24,21 +24,13 @@ comp-type-$(CONFIG_KERNEL_ZSTD) := zstd22 # causing the original tools to complain when checking image integrity. # So disregard it when calculating the payload size in the zimage header. zboot-method-y := $(comp-type-y)_with_size -zboot-size-len-y := 12 +zboot-size-len-y := 4 zboot-method-$(CONFIG_KERNEL_GZIP) := gzip -zboot-size-len-$(CONFIG_KERNEL_GZIP) := 8 - -# Copy the SizeOfHeaders and SizeOfCode fields from the payload to the end of -# the compressed image. Note that this presupposes a PE header offset of 64 -# bytes, which is what arm64, RISC-V and LoongArch use. -quiet_cmd_compwithsize = $(quiet_cmd_$(zboot-method-y)) - cmd_compwithsize = $(cmd_$(zboot-method-y)) && ( \ - dd status=none if=$< bs=4 count=1 skip=37 ; \ - dd status=none if=$< bs=4 count=1 skip=23 ) >> $@ +zboot-size-len-$(CONFIG_KERNEL_GZIP) := 0 $(obj)/vmlinuz: $(obj)/vmlinux.bin FORCE - $(call if_changed,compwithsize) + $(call if_changed,$(zboot-method-y)) OBJCOPYFLAGS_vmlinuz.o := -I binary -O $(EFI_ZBOOT_BFD_TARGET) $(EFI_ZBOOT_OBJCOPY_FLAGS) \ --rename-section .data=.gzdata,load,alloc,readonly,contents diff --git a/drivers/firmware/efi/libstub/arm64.c b/drivers/firmware/efi/libstub/arm64.c index 8aad8c49d43f..446e35eaf3d9 100644 --- a/drivers/firmware/efi/libstub/arm64.c +++ b/drivers/firmware/efi/libstub/arm64.c @@ -9,6 +9,7 @@ #include #include +#include #include #include @@ -88,9 +89,10 @@ efi_status_t check_platform_features(void) #define DCTYPE "cvau" #endif +u32 __weak code_size; + void efi_cache_sync_image(unsigned long image_base, - unsigned long alloc_size, - unsigned long code_size) + unsigned long alloc_size) { u32 ctr = read_cpuid_effective_cachetype(); u64 lsize = 4 << cpuid_feature_extract_unsigned_field(ctr, @@ -98,16 +100,21 @@ void efi_cache_sync_image(unsigned long image_base, /* only perform the cache maintenance if needed for I/D coherency */ if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) { + unsigned long base = image_base; + unsigned long size = code_size; + do { - asm("dc " DCTYPE ", %0" :: "r"(image_base)); - image_base += lsize; - code_size -= lsize; - } while (code_size >= lsize); + asm("dc " DCTYPE ", %0" :: "r"(base)); + base += lsize; + size -= lsize; + } while (size >= lsize); } asm("ic ialluis"); dsb(ish); isb(); + + efi_remap_image(image_base, alloc_size, code_size); } unsigned long __weak primary_entry_offset(void) diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index 148013bcb5f8..67d5a20802e0 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -1066,8 +1066,7 @@ struct screen_info *__alloc_screen_info(void); void free_screen_info(struct screen_info *si); void efi_cache_sync_image(unsigned long image_base, - unsigned long alloc_size, - unsigned long code_size); + unsigned long alloc_size); struct efi_smbios_record { u8 type; diff --git a/drivers/firmware/efi/libstub/zboot.c b/drivers/firmware/efi/libstub/zboot.c index 63ece4800900..e5d7fa1f1d8f 100644 --- a/drivers/firmware/efi/libstub/zboot.c +++ b/drivers/firmware/efi/libstub/zboot.c @@ -50,8 +50,7 @@ static unsigned long alloc_preferred_address(unsigned long alloc_size) } void __weak efi_cache_sync_image(unsigned long image_base, - unsigned long alloc_size, - unsigned long code_size) + unsigned long alloc_size) { // Provided by the arch to perform the cache maintenance necessary for // executable code loaded into memory to be safe for execution. @@ -66,7 +65,7 @@ asmlinkage efi_status_t __efiapi efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) { unsigned long compressed_size = _gzdata_end - _gzdata_start; - unsigned long image_base, alloc_size, code_size; + unsigned long image_base, alloc_size; efi_loaded_image_t *image; efi_status_t status; char *cmdline_ptr; @@ -91,13 +90,9 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) efi_info("Decompressing Linux Kernel...\n"); // SizeOfImage from the compressee's PE/COFF header - alloc_size = round_up(get_unaligned_le32(_gzdata_end - 12), + alloc_size = round_up(get_unaligned_le32(_gzdata_end - 4), EFI_ALLOC_ALIGN); - // SizeOfHeaders and SizeOfCode from the compressee's PE/COFF header - code_size = get_unaligned_le32(_gzdata_end - 4) + - get_unaligned_le32(_gzdata_end - 8); - // If the architecture has a preferred address for the image, // try that first. image_base = alloc_preferred_address(alloc_size); @@ -140,9 +135,7 @@ efi_zboot_entry(efi_handle_t handle, efi_system_table_t *systab) goto free_image; } - efi_cache_sync_image(image_base, alloc_size, code_size); - - efi_remap_image(image_base, alloc_size, code_size); + efi_cache_sync_image(image_base, alloc_size); status = efi_stub_common(handle, image, image_base, cmdline_ptr); -- GitLab From 158009f1b4a33bc0f354b994eea361362bd83226 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Apr 2023 15:43:34 +0200 Subject: [PATCH 4134/5631] timekeeping: Fix references to nonexistent ktime_get_fast_ns() There was never a function named ktime_get_fast_ns(). Presumably these should refer to ktime_get_mono_fast_ns() instead. Fixes: c1ce406e80fb15fa ("timekeeping: Fix up function documentation for the NMI safe accessors") Signed-off-by: Geert Uytterhoeven Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/r/06df7b3cbd94f016403bbf6cd2b38e4368e7468f.1682516546.git.geert+renesas@glider.be --- kernel/time/timekeeping.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 5579ead449f2..09d594900ee0 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -526,7 +526,7 @@ EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * - * The caveats vs. timestamp ordering as documented for ktime_get_fast_ns() + * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) @@ -576,7 +576,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * - * See ktime_get_fast_ns() for documentation of the time stamp ordering. + * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { -- GitLab From fdd1e3489b30ba6ba3075d38ce6f448e04119c71 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:47 -0700 Subject: [PATCH 4135/5631] MAINTAINERS: Add HTE/timestamp subsystem details Add tree, mailing list and patchwork details. Signed-off-by: Dipen Patel Acked-by: Thierry Reding --- MAINTAINERS | 3 +++ 1 file changed, 3 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..65b58963f0d2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9425,6 +9425,9 @@ F: drivers/input/touchscreen/htcpen.c HTE SUBSYSTEM M: Dipen Patel +L: timestamp@lists.linux.dev +T: git git://git.kernel.org/pub/scm/linux/kernel/git/pateldipen1984/linux.git +Q: https://patchwork.kernel.org/project/timestamp/list/ S: Maintained F: Documentation/devicetree/bindings/timestamp/ F: Documentation/driver-api/hte/ -- GitLab From d0672fa4931dcb9d9d53002e855f25dd7507a300 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:48 -0700 Subject: [PATCH 4136/5631] dt-bindings: timestamp: Add Tegra234 support Added timestamp provider support for the Tegra234 in devicetree bindings. From Tegra234 SoC onwards, the nvidia,gpio-controller property is required. This is needed as the tegra always-on (AON) GPIO HTE/GTE provider depends on the AON GPIO controller where it needs to do namespace conversion between GPIO line number (belonging to AON GPIO controller instance) and the GTE slice bits. Signed-off-by: Dipen Patel Reviewed-by: Krzysztof Kozlowski --- .../timestamp/nvidia,tegra194-hte.yaml | 60 +++++++++++++++++-- 1 file changed, 56 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml b/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml index c31e207d1652..5de1eca9cbcd 100644 --- a/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml +++ b/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/timestamp/nvidia,tegra194-hte.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Tegra194 on chip generic hardware timestamping engine (HTE) +title: Tegra on chip generic hardware timestamping engine (HTE) provider maintainers: - Dipen Patel @@ -23,6 +23,8 @@ properties: enum: - nvidia,tegra194-gte-aon - nvidia,tegra194-gte-lic + - nvidia,tegra234-gte-aon + - nvidia,tegra234-gte-lic reg: maxItems: 1 @@ -43,9 +45,14 @@ properties: description: HTE lines are arranged in 32 bit slice where each bit represents different line/signal that it can enable/configure for the timestamp. It is u32 - property and depends on the HTE instance in the chip. The value 3 is for - GPIO GTE and 11 for IRQ GTE. - enum: [3, 11] + property and the value depends on the HTE instance in the chip. + enum: [3, 11, 17] + + nvidia,gpio-controller: + $ref: /schemas/types.yaml#/definitions/phandle + description: + The phandle to AON gpio controller instance. This is required to handle + namespace conversion between GPIO and GTE. '#timestamp-cells': description: @@ -62,6 +69,51 @@ required: - nvidia,slices - "#timestamp-cells" +allOf: + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra194-gte-aon + - nvidia,tegra234-gte-aon + then: + properties: + nvidia,slices: + const: 3 + + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra194-gte-lic + then: + properties: + nvidia,slices: + const: 11 + + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra234-gte-lic + then: + properties: + nvidia,slices: + const: 17 + + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra234-gte-aon + then: + required: + - nvidia,gpio-controller + additionalProperties: false examples: -- GitLab From 1815e37b6e67f2a543e36628bfe6a834aad3ea1b Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:49 -0700 Subject: [PATCH 4137/5631] dt-bindings: timestamp: Deprecate nvidia,slices property The property is not necessary as it is a constant value and can be hardcoded in the driver code. Signed-off-by: Dipen Patel Reviewed-by: Linus Walleij Acked-by: Rob Herring --- .../bindings/timestamp/nvidia,tegra194-hte.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml b/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml index 5de1eca9cbcd..456797967adc 100644 --- a/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml +++ b/Documentation/devicetree/bindings/timestamp/nvidia,tegra194-hte.yaml @@ -42,10 +42,13 @@ properties: nvidia,slices: $ref: /schemas/types.yaml#/definitions/uint32 + deprecated: true description: HTE lines are arranged in 32 bit slice where each bit represents different line/signal that it can enable/configure for the timestamp. It is u32 - property and the value depends on the HTE instance in the chip. + property and the value depends on the HTE instance in the chip. The AON + GTE instances for both Tegra194 and Tegra234 has 3 slices. The Tegra194 + LIC instance has 11 slices and Tegra234 LIC has 17 slices. enum: [3, 11, 17] nvidia,gpio-controller: @@ -66,7 +69,6 @@ required: - compatible - reg - interrupts - - nvidia,slices - "#timestamp-cells" allOf: @@ -123,7 +125,6 @@ examples: reg = <0xc1e0000 0x10000>; interrupts = <0 13 0x4>; nvidia,int-threshold = <1>; - nvidia,slices = <3>; #timestamp-cells = <1>; }; @@ -133,7 +134,6 @@ examples: reg = <0x3aa0000 0x10000>; interrupts = <0 11 0x4>; nvidia,int-threshold = <1>; - nvidia,slices = <11>; #timestamp-cells = <1>; }; -- GitLab From 29662d622641af8866aac904c8aa264844086af3 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:50 -0700 Subject: [PATCH 4138/5631] arm64: tegra: Add Tegra234 GTE nodes Add GTE LIC and AON GPIO nodes for the tegra234 SoC. Signed-off-by: Dipen Patel Acked-by: Thierry Reding --- arch/arm64/boot/dts/nvidia/tegra234.dtsi | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 8fe8eda7654d..54790c6b6a2c 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -1156,6 +1156,14 @@ clock-names = "fuse"; }; + hte_lic: hardware-timestamp@3aa0000 { + compatible = "nvidia,tegra234-gte-lic"; + reg = <0x0 0x3aa0000 0x0 0x10000>; + interrupts = ; + nvidia,int-threshold = <1>; + #timestamp-cells = <1>; + }; + hsp_top0: hsp@3c00000 { compatible = "nvidia,tegra234-hsp", "nvidia,tegra194-hsp"; reg = <0x0 0x03c00000 0x0 0xa0000>; @@ -1673,6 +1681,15 @@ #mbox-cells = <2>; }; + hte_aon: hardware-timestamp@c1e0000 { + compatible = "nvidia,tegra234-gte-aon"; + reg = <0x0 0xc1e0000 0x0 0x10000>; + interrupts = ; + nvidia,int-threshold = <1>; + nvidia,gpio-controller = <&gpio_aon>; + #timestamp-cells = <1>; + }; + gen2_i2c: i2c@c240000 { compatible = "nvidia,tegra194-i2c"; reg = <0x0 0xc240000 0x0 0x100>; -- GitLab From 59cc80a6d8695e7b4b51154ea2d08af551b6c359 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:51 -0700 Subject: [PATCH 4139/5631] hte: Re-phrase tegra API document Make Tegra194 API document generic to make it applicable for current and future tegra hte providers. Signed-off-by: Dipen Patel Reviewed-by: Bagas Sanjaya --- Documentation/driver-api/hte/index.rst | 2 +- .../hte/{tegra194-hte.rst => tegra-hte.rst} | 33 +++++++++---------- 2 files changed, 17 insertions(+), 18 deletions(-) rename Documentation/driver-api/hte/{tegra194-hte.rst => tegra-hte.rst} (50%) diff --git a/Documentation/driver-api/hte/index.rst b/Documentation/driver-api/hte/index.rst index 9f43301c05dc..29011de9a4b8 100644 --- a/Documentation/driver-api/hte/index.rst +++ b/Documentation/driver-api/hte/index.rst @@ -18,5 +18,5 @@ HTE Tegra Provider .. toctree:: :maxdepth: 1 - tegra194-hte + tegra-hte diff --git a/Documentation/driver-api/hte/tegra194-hte.rst b/Documentation/driver-api/hte/tegra-hte.rst similarity index 50% rename from Documentation/driver-api/hte/tegra194-hte.rst rename to Documentation/driver-api/hte/tegra-hte.rst index f2d617265546..85e654772782 100644 --- a/Documentation/driver-api/hte/tegra194-hte.rst +++ b/Documentation/driver-api/hte/tegra-hte.rst @@ -5,25 +5,25 @@ HTE Kernel provider driver Description ----------- -The Nvidia tegra194 HTE provider driver implements two GTE -(Generic Timestamping Engine) instances: 1) GPIO GTE and 2) LIC -(Legacy Interrupt Controller) IRQ GTE. Both GTE instances get the -timestamp from the system counter TSC which has 31.25MHz clock rate, and the -driver converts clock tick rate to nanoseconds before storing it as timestamp -value. +The Nvidia tegra HTE provider also known as GTE (Generic Timestamping Engine) +driver implements two GTE instances: 1) GPIO GTE and 2) LIC +(Legacy Interrupt Controller) IRQ GTE. Both GTE instances get the timestamp +from the system counter TSC which has 31.25MHz clock rate, and the driver +converts clock tick rate to nanoseconds before storing it as timestamp value. GPIO GTE -------- This GTE instance timestamps GPIO in real time. For that to happen GPIO -needs to be configured as input. The always on (AON) GPIO controller instance -supports timestamping GPIOs in real time and it has 39 GPIO lines. The GPIO GTE -and AON GPIO controller are tightly coupled as it requires very specific bits -to be set in GPIO config register before GPIO GTE can be used, for that GPIOLIB -adds two optional APIs as below. The GPIO GTE code supports both kernel -and userspace consumers. The kernel space consumers can directly talk to HTE -subsystem while userspace consumers timestamp requests go through GPIOLIB CDEV -framework to HTE subsystem. +needs to be configured as input. Only the always on (AON) GPIO controller +instance supports timestamping GPIOs in real time as it is tightly coupled with +the GPIO GTE. To support this, GPIOLIB adds two optional APIs as mentioned +below. The GPIO GTE code supports both kernel and userspace consumers. The +kernel space consumers can directly talk to HTE subsystem while userspace +consumers timestamp requests go through GPIOLIB CDEV framework to HTE +subsystem. The hte devicetree binding described at +``Documentation/devicetree/bindings/timestamp`` provides an example of how a +consumer can request an GPIO line. See gpiod_enable_hw_timestamp_ns() and gpiod_disable_hw_timestamp_ns(). @@ -34,9 +34,8 @@ returns the timestamp in nanoseconds. LIC (Legacy Interrupt Controller) IRQ GTE ----------------------------------------- -This GTE instance timestamps LIC IRQ lines in real time. There are 352 IRQ -lines which this instance can add timestamps to in real time. The hte -devicetree binding described at ``Documentation/devicetree/bindings/timestamp`` +This GTE instance timestamps LIC IRQ lines in real time. The hte devicetree +binding described at ``Documentation/devicetree/bindings/timestamp`` provides an example of how a consumer can request an IRQ line. Since it is a one-to-one mapping with IRQ GTE provider, consumers can simply specify the IRQ number that they are interested in. There is no userspace consumer support for -- GitLab From b003fb5c9df8a8923bf46e0c00cc54edcfb0fbe3 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:52 -0700 Subject: [PATCH 4140/5631] hte: Add Tegra234 provider The Tegra234 AON GPIO instance and LIC IRQ support HTE. For the GPIO HTE support, it also requires to add mapping between GPIO and HTE framework same as it was done with Tegra194 SoC. Signed-off-by: Dipen Patel --- drivers/hte/hte-tegra194-test.c | 2 +- drivers/hte/hte-tegra194.c | 124 ++++++++++++++++++++++++++++++-- 2 files changed, 121 insertions(+), 5 deletions(-) diff --git a/drivers/hte/hte-tegra194-test.c b/drivers/hte/hte-tegra194-test.c index 5d776a185bd6..d79c28a80517 100644 --- a/drivers/hte/hte-tegra194-test.c +++ b/drivers/hte/hte-tegra194-test.c @@ -16,7 +16,7 @@ #include /* - * This sample HTE GPIO test driver demonstrates HTE API usage by enabling + * This sample HTE test driver demonstrates HTE API usage by enabling * hardware timestamp on gpio_in and specified LIC IRQ lines. * * Note: gpio_out and gpio_in need to be shorted externally in order for this diff --git a/drivers/hte/hte-tegra194.c b/drivers/hte/hte-tegra194.c index 49a27af22742..5d1f947db0f6 100644 --- a/drivers/hte/hte-tegra194.c +++ b/drivers/hte/hte-tegra194.c @@ -62,6 +62,10 @@ #define NV_AON_HTE_SLICE2_IRQ_GPIO_25 25 #define NV_AON_HTE_SLICE2_IRQ_GPIO_26 26 #define NV_AON_HTE_SLICE2_IRQ_GPIO_27 27 +#define NV_AON_HTE_SLICE2_IRQ_GPIO_28 28 +#define NV_AON_HTE_SLICE2_IRQ_GPIO_29 29 +#define NV_AON_HTE_SLICE2_IRQ_GPIO_30 30 +#define NV_AON_HTE_SLICE2_IRQ_GPIO_31 31 #define HTE_TECTRL 0x0 #define HTE_TETSCH 0x4 @@ -220,7 +224,100 @@ static const struct tegra_hte_line_mapped tegra194_aon_gpio_sec_map[] = { [39] = {NV_AON_SLICE_INVALID, 0}, }; -static const struct tegra_hte_data aon_hte = { +static const struct tegra_hte_line_mapped tegra234_aon_gpio_map[] = { + /* gpio, slice, bit_index */ + /* AA port */ + [0] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_11}, + [1] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_10}, + [2] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_9}, + [3] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_8}, + [4] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_7}, + [5] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_6}, + [6] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_5}, + [7] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_4}, + /* BB port */ + [8] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_3}, + [9] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_2}, + [10] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_1}, + [11] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_0}, + /* CC port */ + [12] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_22}, + [13] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_21}, + [14] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_20}, + [15] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_19}, + [16] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_18}, + [17] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_17}, + [18] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_16}, + [19] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_15}, + /* DD port */ + [20] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_14}, + [21] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_13}, + [22] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_12}, + /* EE port */ + [23] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_31}, + [24] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_30}, + [25] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_29}, + [26] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_28}, + [27] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_27}, + [28] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_26}, + [29] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_25}, + [30] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_24}, + /* GG port */ + [31] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_23}, +}; + +static const struct tegra_hte_line_mapped tegra234_aon_gpio_sec_map[] = { + /* gpio, slice, bit_index */ + /* AA port */ + [0] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_11}, + [1] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_10}, + [2] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_9}, + [3] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_8}, + [4] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_7}, + [5] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_6}, + [6] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_5}, + [7] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_4}, + /* BB port */ + [8] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_3}, + [9] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_2}, + [10] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_1}, + [11] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_0}, + [12] = {NV_AON_SLICE_INVALID, 0}, + [13] = {NV_AON_SLICE_INVALID, 0}, + [14] = {NV_AON_SLICE_INVALID, 0}, + [15] = {NV_AON_SLICE_INVALID, 0}, + /* CC port */ + [16] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_22}, + [17] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_21}, + [18] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_20}, + [19] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_19}, + [20] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_18}, + [21] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_17}, + [22] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_16}, + [23] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_15}, + /* DD port */ + [24] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_14}, + [25] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_13}, + [26] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_12}, + [27] = {NV_AON_SLICE_INVALID, 0}, + [28] = {NV_AON_SLICE_INVALID, 0}, + [29] = {NV_AON_SLICE_INVALID, 0}, + [30] = {NV_AON_SLICE_INVALID, 0}, + [31] = {NV_AON_SLICE_INVALID, 0}, + /* EE port */ + [32] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_31}, + [33] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_30}, + [34] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_29}, + [35] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_28}, + [36] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_27}, + [37] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_26}, + [38] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_25}, + [39] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_24}, + /* GG port */ + [40] = {2, NV_AON_HTE_SLICE2_IRQ_GPIO_23}, +}; + +static const struct tegra_hte_data t194_aon_hte = { .map_sz = ARRAY_SIZE(tegra194_aon_gpio_map), .map = tegra194_aon_gpio_map, .sec_map_sz = ARRAY_SIZE(tegra194_aon_gpio_sec_map), @@ -228,6 +325,14 @@ static const struct tegra_hte_data aon_hte = { .type = HTE_TEGRA_TYPE_GPIO, }; +static const struct tegra_hte_data t234_aon_hte = { + .map_sz = ARRAY_SIZE(tegra234_aon_gpio_map), + .map = tegra234_aon_gpio_map, + .sec_map_sz = ARRAY_SIZE(tegra234_aon_gpio_sec_map), + .sec_map = tegra234_aon_gpio_sec_map, + .type = HTE_TEGRA_TYPE_GPIO, +}; + static const struct tegra_hte_data lic_hte = { .map_sz = 0, .map = NULL, @@ -535,7 +640,9 @@ static bool tegra_hte_match_from_linedata(const struct hte_chip *chip, static const struct of_device_id tegra_hte_of_match[] = { { .compatible = "nvidia,tegra194-gte-lic", .data = &lic_hte}, - { .compatible = "nvidia,tegra194-gte-aon", .data = &aon_hte}, + { .compatible = "nvidia,tegra194-gte-aon", .data = &t194_aon_hte}, + { .compatible = "nvidia,tegra234-gte-lic", .data = &lic_hte}, + { .compatible = "nvidia,tegra234-gte-aon", .data = &t234_aon_hte}, { } }; MODULE_DEVICE_TABLE(of, tegra_hte_of_match); @@ -635,8 +742,17 @@ static int tegra_hte_probe(struct platform_device *pdev) gc->match_from_linedata = tegra_hte_match_from_linedata; - hte_dev->c = gpiochip_find("tegra194-gpio-aon", - tegra_get_gpiochip_from_name); + if (of_device_is_compatible(dev->of_node, + "nvidia,tegra194-gte-aon")) + hte_dev->c = gpiochip_find("tegra194-gpio-aon", + tegra_get_gpiochip_from_name); + else if (of_device_is_compatible(dev->of_node, + "nvidia,tegra234-gte-aon")) + hte_dev->c = gpiochip_find("tegra234-gpio-aon", + tegra_get_gpiochip_from_name); + else + return -ENODEV; + if (!hte_dev->c) return dev_err_probe(dev, -EPROBE_DEFER, "wait for gpio controller\n"); -- GitLab From 0ebc475fb636df12222faa04dd989a4e3c87f31a Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:53 -0700 Subject: [PATCH 4141/5631] hte: Deprecate nvidia,slices property The relevant DT bindings deprecates nvidia,slices property from Tegra234 SoC onwards, moving the slices value per SoC data structure instead. Signed-off-by: Dipen Patel --- drivers/hte/hte-tegra194.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/drivers/hte/hte-tegra194.c b/drivers/hte/hte-tegra194.c index 5d1f947db0f6..945c68c5e476 100644 --- a/drivers/hte/hte-tegra194.c +++ b/drivers/hte/hte-tegra194.c @@ -118,6 +118,7 @@ struct tegra_hte_line_data { struct tegra_hte_data { enum tegra_hte_type type; + u32 slices; u32 map_sz; u32 sec_map_sz; const struct tegra_hte_line_mapped *map; @@ -323,6 +324,7 @@ static const struct tegra_hte_data t194_aon_hte = { .sec_map_sz = ARRAY_SIZE(tegra194_aon_gpio_sec_map), .sec_map = tegra194_aon_gpio_sec_map, .type = HTE_TEGRA_TYPE_GPIO, + .slices = 3, }; static const struct tegra_hte_data t234_aon_hte = { @@ -331,12 +333,21 @@ static const struct tegra_hte_data t234_aon_hte = { .sec_map_sz = ARRAY_SIZE(tegra234_aon_gpio_sec_map), .sec_map = tegra234_aon_gpio_sec_map, .type = HTE_TEGRA_TYPE_GPIO, + .slices = 3, }; -static const struct tegra_hte_data lic_hte = { +static const struct tegra_hte_data t194_lic_hte = { .map_sz = 0, .map = NULL, .type = HTE_TEGRA_TYPE_LIC, + .slices = 11, +}; + +static const struct tegra_hte_data t234_lic_hte = { + .map_sz = 0, + .map = NULL, + .type = HTE_TEGRA_TYPE_LIC, + .slices = 17, }; static inline u32 tegra_hte_readl(struct tegra_hte_soc *hte, u32 reg) @@ -639,9 +650,9 @@ static bool tegra_hte_match_from_linedata(const struct hte_chip *chip, } static const struct of_device_id tegra_hte_of_match[] = { - { .compatible = "nvidia,tegra194-gte-lic", .data = &lic_hte}, + { .compatible = "nvidia,tegra194-gte-lic", .data = &t194_lic_hte}, { .compatible = "nvidia,tegra194-gte-aon", .data = &t194_aon_hte}, - { .compatible = "nvidia,tegra234-gte-lic", .data = &lic_hte}, + { .compatible = "nvidia,tegra234-gte-lic", .data = &t234_lic_hte}, { .compatible = "nvidia,tegra234-gte-aon", .data = &t234_aon_hte}, { } }; @@ -679,13 +690,6 @@ static int tegra_hte_probe(struct platform_device *pdev) dev = &pdev->dev; - ret = of_property_read_u32(dev->of_node, "nvidia,slices", &slices); - if (ret != 0) { - dev_err(dev, "Could not read slices\n"); - return -EINVAL; - } - nlines = slices << 5; - hte_dev = devm_kzalloc(dev, sizeof(*hte_dev), GFP_KERNEL); if (!hte_dev) return -ENOMEM; @@ -697,6 +701,13 @@ static int tegra_hte_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, hte_dev); hte_dev->prov_data = of_device_get_match_data(&pdev->dev); + ret = of_property_read_u32(dev->of_node, "nvidia,slices", &slices); + if (ret != 0) + slices = hte_dev->prov_data->slices; + + dev_dbg(dev, "slices:%d\n", slices); + nlines = slices << 5; + hte_dev->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hte_dev->regs)) return PTR_ERR(hte_dev->regs); -- GitLab From d02b1cabc7c6fe0e237bf8a2a6a8813302cfd87c Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:54 -0700 Subject: [PATCH 4142/5631] hte: handle nvidia,gpio-controller property The dt binding adds nvidia,gpio-controller property from Tegra234 SoC onwards to simplify code handling gpio chip search. The gpio chip search is needed for the AON GPIO GTE instances to map the hardware timestamp GPIO request (coming from the GPIO framework) to the tegra HTE providers. The patch also adds new gpio chip match function to match from the fwnode instead of the gpio controller label. The addition of the property does not break ABI for the existing Tegra194 code. Signed-off-by: Dipen Patel Reviewed-by: Linus Walleij --- drivers/hte/hte-tegra194.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/hte/hte-tegra194.c b/drivers/hte/hte-tegra194.c index 945c68c5e476..2c485ff5be22 100644 --- a/drivers/hte/hte-tegra194.c +++ b/drivers/hte/hte-tegra194.c @@ -679,6 +679,11 @@ static int tegra_get_gpiochip_from_name(struct gpio_chip *chip, void *data) return !strcmp(chip->label, data); } +static int tegra_gpiochip_match(struct gpio_chip *chip, void *data) +{ + return chip->fwnode == of_node_to_fwnode(data); +} + static int tegra_hte_probe(struct platform_device *pdev) { int ret; @@ -687,6 +692,7 @@ static int tegra_hte_probe(struct platform_device *pdev) struct device *dev; struct tegra_hte_soc *hte_dev; struct hte_chip *gc; + struct device_node *gpio_ctrl; dev = &pdev->dev; @@ -754,15 +760,23 @@ static int tegra_hte_probe(struct platform_device *pdev) gc->match_from_linedata = tegra_hte_match_from_linedata; if (of_device_is_compatible(dev->of_node, - "nvidia,tegra194-gte-aon")) + "nvidia,tegra194-gte-aon")) { hte_dev->c = gpiochip_find("tegra194-gpio-aon", tegra_get_gpiochip_from_name); - else if (of_device_is_compatible(dev->of_node, - "nvidia,tegra234-gte-aon")) - hte_dev->c = gpiochip_find("tegra234-gpio-aon", - tegra_get_gpiochip_from_name); - else - return -ENODEV; + } else { + gpio_ctrl = of_parse_phandle(dev->of_node, + "nvidia,gpio-controller", + 0); + if (!gpio_ctrl) { + dev_err(dev, + "gpio controller node not found\n"); + return -ENODEV; + } + + hte_dev->c = gpiochip_find(gpio_ctrl, + tegra_gpiochip_match); + of_node_put(gpio_ctrl); + } if (!hte_dev->c) return dev_err_probe(dev, -EPROBE_DEFER, -- GitLab From 7d507452048d9a6971998339243d16a09c95a842 Mon Sep 17 00:00:00 2001 From: Dipen Patel Date: Thu, 13 Apr 2023 17:44:55 -0700 Subject: [PATCH 4143/5631] gpio: tegra186: Add Tegra234 hte support To enable timestamp support for the Tegra234, has_gte variable needs to be set true. Signed-off-by: Dipen Patel Acked-by: Thierry Reding Acked-by: Bartosz Golaszewski Reviewed-by: Linus Walleij --- drivers/gpio/gpio-tegra186.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 14c872b6ad05..b904de0b1784 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -1134,6 +1134,7 @@ static const struct tegra_gpio_soc tegra234_aon_soc = { .name = "tegra234-gpio-aon", .instance = 1, .num_irqs_per_bank = 8, + .has_gte = true, }; #define TEGRA241_MAIN_GPIO_PORT(_name, _bank, _port, _pins) \ -- GitLab From 902dea62b3dda532172c0f4d0410fe595266b22c Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 10 Mar 2023 08:47:06 -0600 Subject: [PATCH 4144/5631] hte: Use of_property_present() for testing DT property presence It is preferred to use typed property access functions (i.e. of_property_read_ functions) rather than low-level of_get_property/of_find_property functions for reading properties. As part of this, convert of_get_property/of_find_property calls to the recently added of_property_present() helper when we just want to test for presence of a property and nothing more. Signed-off-by: Rob Herring Acked-by: Dipen Patel Signed-off-by: Dipen Patel --- drivers/hte/hte.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hte/hte.c b/drivers/hte/hte.c index 7c3b4476f890..9f3221462e75 100644 --- a/drivers/hte/hte.c +++ b/drivers/hte/hte.c @@ -518,7 +518,7 @@ static struct hte_device *hte_of_get_dev(struct device *dev, np = dev->of_node; - if (!of_find_property(np, "timestamp-names", NULL)) { + if (!of_property_present(np, "timestamp-names")) { /* Let hte core construct it during request time */ desc->attr.name = NULL; } else { -- GitLab From 6680c835ada1b34e882d0a32612f7294c62e27e0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 15 Dec 2022 17:46:19 +0100 Subject: [PATCH 4145/5631] hte: tegra: fix 'struct of_device_id' build error Without the extra #include, this driver produces a build failure in some configurations. drivers/hte/hte-tegra194-test.c:96:34: error: array type has incomplete element type 'struct of_device_id' 96 | static const struct of_device_id tegra_hte_test_of_match[] = { Fixes: 9a75a7cd03c9 ("hte: Add Tegra HTE test driver") Signed-off-by: Arnd Bergmann Acked-by: Dipen Patel Signed-off-by: Dipen Patel --- drivers/hte/hte-tegra194-test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hte/hte-tegra194-test.c b/drivers/hte/hte-tegra194-test.c index d79c28a80517..98d1fd6de071 100644 --- a/drivers/hte/hte-tegra194-test.c +++ b/drivers/hte/hte-tegra194-test.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include -- GitLab From e078180d66848a6a890daf0a3ce28dc43cc66790 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 19 Apr 2023 17:30:00 +0300 Subject: [PATCH 4146/5631] hte: tegra-194: Fix off by one in tegra_hte_map_to_line_id() The "map_sz" is the number of elements in the "m" array so the > comparison needs to be changed to >= to prevent an out of bounds read. Fixes: 09574cca6ad6 ("hte: Add Tegra194 HTE kernel provider") Signed-off-by: Dan Carpenter Acked-by: Dipen Patel Signed-off-by: Dipen Patel --- drivers/hte/hte-tegra194.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hte/hte-tegra194.c b/drivers/hte/hte-tegra194.c index 2c485ff5be22..06ef349a2265 100644 --- a/drivers/hte/hte-tegra194.c +++ b/drivers/hte/hte-tegra194.c @@ -367,7 +367,7 @@ static int tegra_hte_map_to_line_id(u32 eid, { if (m) { - if (eid > map_sz) + if (eid >= map_sz) return -EINVAL; if (m[eid].slice == NV_AON_SLICE_INVALID) return -EINVAL; -- GitLab From 9e0c2d40a40733fba605ff47a08f3eba2fab4fbb Mon Sep 17 00:00:00 2001 From: ye xingchen Date: Thu, 17 Nov 2022 15:17:29 +0800 Subject: [PATCH 4147/5631] hte: Use device_match_of_node() Replace the open-code with device_match_of_node(). Signed-off-by: ye xingchen Acked-by: Dipen Patel Signed-off-by: Dipen Patel --- drivers/hte/hte.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hte/hte.c b/drivers/hte/hte.c index 9f3221462e75..67c15724ee78 100644 --- a/drivers/hte/hte.c +++ b/drivers/hte/hte.c @@ -444,7 +444,7 @@ static struct hte_device *of_node_to_htedevice(struct device_node *np) list_for_each_entry(gdev, &hte_devices, list) if (gdev->chip && gdev->chip->dev && - gdev->chip->dev->of_node == np) { + device_match_of_node(gdev->chip->dev, np)) { spin_unlock(&hte_lock); return gdev; } -- GitLab From ca3d1a4b419acad3fca6828884acb03614f7558b Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 8 Feb 2023 19:33:28 +0200 Subject: [PATCH 4148/5631] hte: tegra-194: Use proper includes The test driver uses the gpiod consumer API so include the right header. This may cause a problem with struct of_device_id being implcitly pulled in by the legacy header so include explicitly as well. While at it, drop explicit moduleparam.h (it's included with module.h) and sort the headers. Signed-off-by: Linus Walleij Signed-off-by: Andy Shevchenko Acked-by: Dipen Patel Signed-off-by: Dipen Patel --- drivers/hte/hte-tegra194-test.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/hte/hte-tegra194-test.c b/drivers/hte/hte-tegra194-test.c index 98d1fd6de071..ba37a5efbf82 100644 --- a/drivers/hte/hte-tegra194-test.c +++ b/drivers/hte/hte-tegra194-test.c @@ -6,15 +6,14 @@ */ #include +#include +#include +#include #include #include -#include -#include -#include -#include #include +#include #include -#include /* * This sample HTE test driver demonstrates HTE API usage by enabling -- GitLab From edbdb43fc96b11b3bfa531be306a1993d9fe89ec Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 26 Apr 2023 15:03:23 -0700 Subject: [PATCH 4149/5631] KVM: x86: Preserve TDP MMU roots until they are explicitly invalidated Preserve TDP MMU roots until they are explicitly invalidated by gifting the TDP MMU itself a reference to a root when it is allocated. Keeping a reference in the TDP MMU fixes a flaw where the TDP MMU exhibits terrible performance, and can potentially even soft-hang a vCPU, if a vCPU frequently unloads its roots, e.g. when KVM is emulating SMI+RSM. When KVM emulates something that invalidates _all_ TLB entries, e.g. SMI and RSM, KVM unloads all of the vCPUs roots (KVM keeps a small per-vCPU cache of previous roots). Unloading roots is a simple way to ensure KVM flushes and synchronizes all roots for the vCPU, as KVM flushes and syncs when allocating a "new" root (from the vCPU's perspective). In the shadow MMU, KVM keeps track of all shadow pages, roots included, in a per-VM hash table. Unloading a shadow MMU root just wipes it from the per-vCPU cache; the root is still tracked in the per-VM hash table. When KVM loads a "new" root for the vCPU, KVM will find the old, unloaded root in the per-VM hash table. Unlike the shadow MMU, the TDP MMU doesn't track "inactive" roots in a per-VM structure, where "active" in this case means a root is either in-use or cached as a previous root by at least one vCPU. When a TDP MMU root becomes inactive, i.e. the last vCPU reference to the root is put, KVM immediately frees the root (asterisk on "immediately" as the actual freeing may be done by a worker, but for all intents and purposes the root is gone). The TDP MMU behavior is especially problematic for 1-vCPU setups, as unloading all roots effectively frees all roots. The issue is mitigated to some degree in multi-vCPU setups as a different vCPU usually holds a reference to an unloaded root and thus keeps the root alive, allowing the vCPU to reuse its old root after unloading (with a flush+sync). The TDP MMU flaw has been known for some time, as until very recently, KVM's handling of CR0.WP also triggered unloading of all roots. The CR0.WP toggling scenario was eventually addressed by not unloading roots when _only_ CR0.WP is toggled, but such an approach doesn't Just Work for emulating SMM as KVM must emulate a full TLB flush on entry and exit to/from SMM. Given that the shadow MMU plays nice with unloading roots at will, teaching the TDP MMU to do the same is far less complex than modifying KVM to track which roots need to be flushed before reuse. Note, preserving all possible TDP MMU roots is not a concern with respect to memory consumption. Now that the role for direct MMUs doesn't include information about the guest, e.g. CR0.PG, CR0.WP, CR4.SMEP, etc., there are _at most_ six possible roots (where "guest_mode" here means L2): 1. 4-level !SMM !guest_mode 2. 4-level SMM !guest_mode 3. 5-level !SMM !guest_mode 4. 5-level SMM !guest_mode 5. 4-level !SMM guest_mode 6. 5-level !SMM guest_mode And because each vCPU can track 4 valid roots, a VM can already have all 6 root combinations live at any given time. Not to mention that, in practice, no sane VMM will advertise different guest.MAXPHYADDR values across vCPUs, i.e. KVM won't ever use both 4-level and 5-level roots for a single VM. Furthermore, the vast majority of modern hypervisors will utilize EPT/NPT when available, thus the guest_mode=%true cases are also unlikely to be utilized. Reported-by: Jeremi Piotrowski Link: https://lore.kernel.org/all/959c5bce-beb5-b463-7158-33fc4a4f910c@linux.microsoft.com Link: https://lkml.kernel.org/r/20220209170020.1775368-1-pbonzini%40redhat.com Link: https://lore.kernel.org/all/20230322013731.102955-1-minipli@grsecurity.net Link: https://lore.kernel.org/all/000000000000a0bc2b05f9dd7fab@google.com Link: https://lore.kernel.org/all/000000000000eca0b905fa0f7756@google.com Cc: Ben Gardon Cc: David Matlack Cc: stable@vger.kernel.org Tested-by: Jeremi Piotrowski Link: https://lore.kernel.org/r/20230426220323.3079789-1-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/mmu/tdp_mmu.c | 121 +++++++++++++++++-------------------- 1 file changed, 56 insertions(+), 65 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index b2fca11b91ff..08340219c35a 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -40,7 +40,17 @@ static __always_inline bool kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) { - /* Also waits for any queued work items. */ + /* + * Invalidate all roots, which besides the obvious, schedules all roots + * for zapping and thus puts the TDP MMU's reference to each root, i.e. + * ultimately frees all roots. + */ + kvm_tdp_mmu_invalidate_all_roots(kvm); + + /* + * Destroying a workqueue also first flushes the workqueue, i.e. no + * need to invoke kvm_tdp_mmu_zap_invalidated_roots(). + */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); @@ -116,16 +126,6 @@ static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work); } -static inline bool kvm_tdp_root_mark_invalid(struct kvm_mmu_page *page) -{ - union kvm_mmu_page_role role = page->role; - role.invalid = true; - - /* No need to use cmpxchg, only the invalid bit can change. */ - role.word = xchg(&page->role.word, role.word); - return role.invalid; -} - void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { @@ -134,45 +134,12 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!is_tdp_mmu_page(root)); - /* - * The root now has refcount=0. It is valid, but readers already - * cannot acquire a reference to it because kvm_tdp_mmu_get_root() - * rejects it. This remains true for the rest of the execution - * of this function, because readers visit valid roots only - * (except for tdp_mmu_zap_root_work(), which however - * does not acquire any reference itself). - * - * Even though there are flows that need to visit all roots for - * correctness, they all take mmu_lock for write, so they cannot yet - * run concurrently. The same is true after kvm_tdp_root_mark_invalid, - * since the root still has refcount=0. - * - * However, tdp_mmu_zap_root can yield, and writers do not expect to - * see refcount=0 (see for example kvm_tdp_mmu_invalidate_all_roots()). - * So the root temporarily gets an extra reference, going to refcount=1 - * while staying invalid. Readers still cannot acquire any reference; - * but writers are now allowed to run if tdp_mmu_zap_root yields and - * they might take an extra reference if they themselves yield. - * Therefore, when the reference is given back by the worker, - * there is no guarantee that the refcount is still 1. If not, whoever - * puts the last reference will free the page, but they will not have to - * zap the root because a root cannot go from invalid to valid. + * The TDP MMU itself holds a reference to each root until the root is + * explicitly invalidated, i.e. the final reference should be never be + * put for a valid root. */ - if (!kvm_tdp_root_mark_invalid(root)) { - refcount_set(&root->tdp_mmu_root_count, 1); - - /* - * Zapping the root in a worker is not just "nice to have"; - * it is required because kvm_tdp_mmu_invalidate_all_roots() - * skips already-invalid roots. If kvm_tdp_mmu_put_root() did - * not add the root to the workqueue, kvm_tdp_mmu_zap_all_fast() - * might return with some roots not zapped yet. - */ - tdp_mmu_schedule_zap_root(kvm, root); - return; - } + KVM_BUG_ON(!is_tdp_mmu_page(root) || !root->role.invalid, kvm); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_del_rcu(&root->link); @@ -320,7 +287,14 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) root = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_sp(root, NULL, 0, role); - refcount_set(&root->tdp_mmu_root_count, 1); + /* + * TDP MMU roots are kept until they are explicitly invalidated, either + * by a memslot update or by the destruction of the VM. Initialize the + * refcount to two; one reference for the vCPU, and one reference for + * the TDP MMU itself, which is held until the root is invalidated and + * is ultimately put by tdp_mmu_zap_root_work(). + */ + refcount_set(&root->tdp_mmu_root_count, 2); spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); @@ -946,32 +920,49 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) /* * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that * is about to be zapped, e.g. in response to a memslots update. The actual - * zapping is performed asynchronously, so a reference is taken on all roots. - * Using a separate workqueue makes it easy to ensure that the destruction is - * performed before the "fast zap" completes, without keeping a separate list - * of invalidated roots; the list is effectively the list of work items in - * the workqueue. - * - * Get a reference even if the root is already invalid, the asynchronous worker - * assumes it was gifted a reference to the root it processes. Because mmu_lock - * is held for write, it should be impossible to observe a root with zero refcount, - * i.e. the list of roots cannot be stale. + * zapping is performed asynchronously. Using a separate workqueue makes it + * easy to ensure that the destruction is performed before the "fast zap" + * completes, without keeping a separate list of invalidated roots; the list is + * effectively the list of work items in the workqueue. * - * This has essentially the same effect for the TDP MMU - * as updating mmu_valid_gen does for the shadow MMU. + * Note, the asynchronous worker is gifted the TDP MMU's reference. + * See kvm_tdp_mmu_get_vcpu_root_hpa(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); - list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { - if (!root->role.invalid && - !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) { + /* + * mmu_lock must be held for write to ensure that a root doesn't become + * invalid while there are active readers (invalidating a root while + * there are active readers may or may not be problematic in practice, + * but it's uncharted territory and not supported). + * + * Waive the assertion if there are no users of @kvm, i.e. the VM is + * being destroyed after all references have been put, or if no vCPUs + * have been created (which means there are no roots), i.e. the VM is + * being destroyed in an error path of KVM_CREATE_VM. + */ + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + refcount_read(&kvm->users_count) && kvm->created_vcpus) + lockdep_assert_held_write(&kvm->mmu_lock); + + /* + * As above, mmu_lock isn't held when destroying the VM! There can't + * be other references to @kvm, i.e. nothing else can invalidate roots + * or be consuming roots, but walking the list of roots does need to be + * guarded against roots being deleted by the asynchronous zap worker. + */ + rcu_read_lock(); + + list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) { + if (!root->role.invalid) { root->role.invalid = true; tdp_mmu_schedule_zap_root(kvm, root); } } + + rcu_read_unlock(); } /* -- GitLab From 9419092fb2630c30e4ffeb9ef61007ef0c61827a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 27 Apr 2023 09:02:11 +1000 Subject: [PATCH 4150/5631] xfs: fix livelock in delayed allocation at ENOSPC On a filesystem with a non-zero stripe unit and a large sequential write, delayed allocation will set a minimum allocation length of the stripe unit. If allocation fails because there are no extents long enough for an aligned minlen allocation, it is supposed to fall back to unaligned allocation which allows single block extents to be allocated. When the allocator code was rewritting in the 6.3 cycle, this fallback was broken - the old code used args->fsbno as the both the allocation target and the allocation result, the new code passes the target as a separate parameter. The conversion didn't handle the aligned->unaligned fallback path correctly - it reset args->fsbno to the target fsbno on failure which broke allocation failure detection in the high level code and so it never fell back to unaligned allocations. This resulted in a loop in writeback trying to allocate an aligned block, getting a false positive success, trying to insert the result in the BMBT. This did nothing because the extent already was in the BMBT (merge results in an unchanged extent) and so it returned the prior extent to the conversion code as the current iomap. Because the iomap returned didn't cover the offset we tried to map, xfs_convert_blocks() then retries the allocation, which fails in the same way and now we have a livelock. Reported-and-tested-by: Brian Foster Fixes: 85843327094f ("xfs: factor xfs_bmap_btalloc()") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_bmap.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1a4e446194dd..b512de0540d5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3540,7 +3540,6 @@ xfs_bmap_btalloc_at_eof( * original non-aligned state so the caller can proceed on allocation * failure as if this function was never called. */ - args->fsbno = ap->blkno; args->alignment = 1; return 0; } -- GitLab From 85c636284cb63b7740b4ae98881ace92158068d3 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Fri, 21 Apr 2023 15:56:57 +0100 Subject: [PATCH 4151/5631] drm/msm/dp: unregister audio driver during unbind while binding the code always registers a audio driver, however there is no corresponding unregistration done in unbind. This leads to multiple redundant audio platform devices if dp_display_bind and dp_display_unbind happens multiple times during startup. On X13s platform this resulted in 6 to 9 audio codec device instead of just 3 codec devices for 3 dp ports. Fix this by unregistering codecs on unbind. Signed-off-by: Srinivas Kandagatla Fixes: d13e36d7d222 ("drm/msm/dp: add audio support for Display Port on MSM") Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/533324/ Link: https://lore.kernel.org/r/20230421145657.12186-1-srinivas.kandagatla@linaro.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/dp/dp_audio.c | 12 ++++++++++++ drivers/gpu/drm/msm/dp/dp_audio.h | 2 ++ drivers/gpu/drm/msm/dp/dp_display.c | 1 + 3 files changed, 15 insertions(+) diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 6666783e1468..1245c7aa49df 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -593,6 +593,18 @@ static struct hdmi_codec_pdata codec_data = { .i2s = 1, }; +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio) +{ + struct dp_audio_private *audio_priv; + + audio_priv = container_of(dp_audio, struct dp_audio_private, dp_audio); + + if (audio_priv->audio_pdev) { + platform_device_unregister(audio_priv->audio_pdev); + audio_priv->audio_pdev = NULL; + } +} + int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio) { diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 84e5f4a5d26b..4ab78880af82 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -53,6 +53,8 @@ struct dp_audio *dp_audio_get(struct platform_device *pdev, int dp_register_audio_driver(struct device *dev, struct dp_audio *dp_audio); +void dp_unregister_audio_driver(struct device *dev, struct dp_audio *dp_audio); + /** * dp_audio_put() * diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 3e13acdfa7e5..99a38dbe51c0 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -326,6 +326,7 @@ static void dp_display_unbind(struct device *dev, struct device *master, kthread_stop(dp->ev_tsk); dp_power_client_deinit(dp->power); + dp_unregister_audio_driver(dev, dp->audio); dp_aux_unregister(dp->aux); dp->drm_dev = NULL; dp->aux->drm_dev = NULL; -- GitLab From a432fc31f03db2546a48bcf5dd69ca28ceb732bf Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Wed, 26 Apr 2023 01:11:09 +0200 Subject: [PATCH 4152/5631] drm/msm/dpu: Assign missing writeback log_mask The WB debug log mask ended up never being assigned, leading to writes to this block to never be logged even if the mask is enabled in dpu_hw_util_log_mask via debugfs. Fixes: 84a33d0fd921 ("drm/msm/dpu: add dpu_hw_wb abstraction for writeback blocks") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/533860/ Link: https://lore.kernel.org/r/20230418-dpu-drop-useless-for-lookup-v3-1-e8d869eea455@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index 2d28afdf860e..a3e413d27717 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -61,6 +61,7 @@ static const struct dpu_wb_cfg *_wb_offset(enum dpu_wb wb, for (i = 0; i < m->wb_count; i++) { if (wb == m->wb[i].id) { b->blk_addr = addr + m->wb[i].base; + b->log_mask = DPU_DBG_MASK_WB; return &m->wb[i]; } } -- GitLab From 3f23a52fc2b890884828747111f7a3291d2a1b3d Mon Sep 17 00:00:00 2001 From: Arnaud Vrac Date: Wed, 19 Apr 2023 16:41:08 +0200 Subject: [PATCH 4153/5631] drm/msm/dpu: tweak msm8998 hw catalog values Match the values found in the downstream msm-4.4 kernel sde driver. Signed-off-by: Arnaud Vrac Fixes: 94391a14fc27 ("drm/msm/dpu1: Add MSM8998 to hw catalog") Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532900/ Link: https://lore.kernel.org/r/20230419-dpu-tweaks-v1-1-d1bac46db075@freebox.fr Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h | 8 ++++---- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 15 +++++---------- 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 2b3ae84057df..b07e8a9941f7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -134,10 +134,10 @@ static const struct dpu_dspp_cfg msm8998_dspp[] = { }; static const struct dpu_intf_cfg msm8998_intf[] = { - INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), - INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), - INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), - INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 25, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), + INTF_BLK("intf_0", INTF_0, 0x6a000, 0x280, INTF_DP, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 24, 25), + INTF_BLK("intf_1", INTF_1, 0x6a800, 0x280, INTF_DSI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 26, 27), + INTF_BLK("intf_2", INTF_2, 0x6b000, 0x280, INTF_DSI, 1, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 28, 29), + INTF_BLK("intf_3", INTF_3, 0x6b800, 0x280, INTF_HDMI, 0, 21, INTF_SDM845_MASK, MDP_SSPP_TOP0_INTR, 30, 31), }; static const struct dpu_perf_cfg msm8998_perf_data = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 03f162af1a50..8d5d782a4339 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -587,12 +587,12 @@ static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3}; static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { { - .pps = 1088 * 1920 * 30, + .pps = 1920 * 1080 * 30, .ot_limit = 2, }, { - .pps = 1088 * 1920 * 60, - .ot_limit = 6, + .pps = 1920 * 1080 * 60, + .ot_limit = 4, }, { .pps = 3840 * 2160 * 30, @@ -705,10 +705,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_linear[] = { {.fl = 10, .lut = 0x1555b}, {.fl = 11, .lut = 0x5555b}, {.fl = 12, .lut = 0x15555b}, - {.fl = 13, .lut = 0x55555b}, - {.fl = 14, .lut = 0}, - {.fl = 1, .lut = 0x1b}, - {.fl = 0, .lut = 0} + {.fl = 0, .lut = 0x55555b} }; static const struct dpu_qos_lut_entry sdm845_qos_linear[] = { @@ -730,9 +727,7 @@ static const struct dpu_qos_lut_entry msm8998_qos_macrotile[] = { {.fl = 10, .lut = 0x1aaff}, {.fl = 11, .lut = 0x5aaff}, {.fl = 12, .lut = 0x15aaff}, - {.fl = 13, .lut = 0x55aaff}, - {.fl = 1, .lut = 0x1aaff}, - {.fl = 0, .lut = 0}, + {.fl = 0, .lut = 0x55aaff}, }; static const struct dpu_qos_lut_entry sc7180_qos_linear[] = { -- GitLab From 686eb89b103631a41c7f69b8ac5fbca4a6b07fa0 Mon Sep 17 00:00:00 2001 From: Arnaud Vrac Date: Wed, 19 Apr 2023 16:41:17 +0200 Subject: [PATCH 4154/5631] drm/msm/dpu: tweak lm pairings in msm8998 hw catalog Change lm blocks pairs so that lm blocks with the same features are paired together: LM_0 and LM_1 with PP and DSPP LM_2 and LM_5 with PP LM_3 and LM_4 This matches the sdm845 configuration and allows using pp or dspp when 2 lm blocks are needed in the topology. In the previous config the reservation code could never find an lm pair without a matching feature set. Signed-off-by: Arnaud Vrac Fixes: 94391a14fc27 ("drm/msm/dpu1: Add MSM8998 to hw catalog") Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/532905/ Link: https://lore.kernel.org/r/20230419-dpu-tweaks-v1-10-d1bac46db075@freebox.fr Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index b07e8a9941f7..bdcd554fc8a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -98,17 +98,17 @@ static const struct dpu_sspp_cfg msm8998_sspp[] = { static const struct dpu_lm_cfg msm8998_lm[] = { LM_BLK("lm_0", LM_0, 0x44000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_0, LM_2, DSPP_0), + &msm8998_lm_sblk, PINGPONG_0, LM_1, DSPP_0), LM_BLK("lm_1", LM_1, 0x45000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_1, LM_5, DSPP_1), + &msm8998_lm_sblk, PINGPONG_1, LM_0, DSPP_1), LM_BLK("lm_2", LM_2, 0x46000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_2, LM_0, 0), + &msm8998_lm_sblk, PINGPONG_2, LM_5, 0), LM_BLK("lm_3", LM_3, 0x47000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_4", LM_4, 0x48000, MIXER_MSM8998_MASK, &msm8998_lm_sblk, PINGPONG_MAX, 0, 0), LM_BLK("lm_5", LM_5, 0x49000, MIXER_MSM8998_MASK, - &msm8998_lm_sblk, PINGPONG_3, LM_1, 0), + &msm8998_lm_sblk, PINGPONG_3, LM_2, 0), }; static const struct dpu_pingpong_cfg msm8998_pp[] = { -- GitLab From f9d5bb73c260f0478f43b07d9fb3dae7d7a8b36b Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:15 +0200 Subject: [PATCH 4155/5631] drm/msm/dpu: Remove unused INTF0 interrupt mask from SM6115/QCM2290 Neither of these SoCs has INTF0, they only have a DSI interface on index 1. Stop enabling an interrupt that can't fire. Fixes: 3581b7062cec ("drm/msm/disp/dpu1: add support for display on SM6115") Fixes: 5334087ee743 ("drm/msm: add support for QCM2290 MDSS") Signed-off-by: Marijn Suijten Reviewed-by: Dmitry Baryshkov Reviewed-by: Konrad Dybcio Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534204/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-1-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h | 1 - drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h | 1 - 2 files changed, 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h index 6f04d8f85c92..988d820f7ef2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h @@ -122,7 +122,6 @@ const struct dpu_mdss_cfg dpu_sm6115_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h index 303492d62a5c..c9003dcc1a59 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h @@ -112,7 +112,6 @@ const struct dpu_mdss_cfg dpu_qcm2290_cfg = { .mdss_irqs = BIT(MDP_SSPP_TOP0_INTR) | \ BIT(MDP_SSPP_TOP0_INTR2) | \ BIT(MDP_SSPP_TOP0_HIST_INTR) | \ - BIT(MDP_INTF0_INTR) | \ BIT(MDP_INTF1_INTR), }; -- GitLab From cfbc21d1c0f9bc2f74acab84031fbaefdbb49ae1 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:16 +0200 Subject: [PATCH 4156/5631] drm/msm/dpu: Remove TE2 block and feature from DPU >= 5.0.0 hardware No hardware beyond kona (sm8250, DPU 6.0.0) defines the TE2 PINGPONG sub-block offset downstream, and according to insiders no DPU >= 5.0.0 hardware has support for it either. Especially since neither downstream nor upstream utilize these registers in any way, remove the erroneous specification from SM8150, SC8180X, SM8250, SC7180, SM8350, SC8280XP and SM8450 to prevent confusion. Note that downstream enables the PPSPLIT (split-FIFO) topology (single LM for 2 PP and 2 INTF) based on the presence of a TE2 block. Fixes: 386fced3f76f ("drm/msm/dpu: add SM8150 to hw catalog") Fixes: 7bdc0c4b8126 ("msm:disp:dpu1: add support for display for SC7180 target") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534210/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-2-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../msm/disp/dpu1/catalog/dpu_5_0_sm8150.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_6_0_sm8250.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_6_2_sc7180.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 4 ++-- .../msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 24 +++++++++---------- .../msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 4 ++-- 7 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 282d410269ff..42b0e58624d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8150_dspp[] = { }; static const struct dpu_pingpong_cfg sm8150_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index c57400265f28..e3bdfe7b30f1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -116,10 +116,10 @@ static const struct dpu_lm_cfg sc8180x_lm[] = { }; static const struct dpu_pingpong_cfg sc8180x_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index 2c40229ea515..ed130582873c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -129,10 +129,10 @@ static const struct dpu_dspp_cfg sm8250_dspp[] = { }; static const struct dpu_pingpong_cfg sm8250_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x71000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 8799ed757119..a46b11730a4d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -80,8 +80,8 @@ static const struct dpu_dspp_cfg sc7180_dspp[] = { }; static const struct dpu_pingpong_cfg sc7180_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk_te, -1, -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk_te, -1, -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x70000, 0, sdm845_pp_sblk, -1, -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x70800, 0, sdm845_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7180_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index ca107ca8de46..41ef0c8fc993 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,10 +127,10 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 9aab110b8c44..f3d935f346b2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,18 +121,18 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_TE("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_TE("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_TE("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_TE("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk_te, - DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; static const struct dpu_merge_3d_cfg sc8280xp_merge_3d[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index 02a259b6b426..e409c119b0a2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,10 +128,10 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK_TE("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK_TE("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk_te, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, -- GitLab From e9d9ce5462fecdeefec87953de71df4d025cbc72 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:17 +0200 Subject: [PATCH 4157/5631] drm/msm/dpu: Move non-MDP_TOP INTF_INTR offsets out of hwio header These offsets do not fall under the MDP TOP block and do not fit the comment right above. Move them to dpu_hw_interrupts.c next to the repsective MDP_INTF_x_OFF interrupt block offsets. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534203/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-3-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c | 5 ++++- drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h | 3 --- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 53326f25e40e..85c0bda3ff90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -15,7 +15,7 @@ /* * Register offsets in MDSS register file for the interrupt registers - * w.r.t. to the MDP base + * w.r.t. the MDP base */ #define MDP_SSPP_TOP0_OFF 0x0 #define MDP_INTF_0_OFF 0x6A000 @@ -24,6 +24,9 @@ #define MDP_INTF_3_OFF 0x6B800 #define MDP_INTF_4_OFF 0x6C000 #define MDP_INTF_5_OFF 0x6C800 +#define INTF_INTR_EN 0x1c0 +#define INTF_INTR_STATUS 0x1c4 +#define INTF_INTR_CLEAR 0x1c8 #define MDP_AD4_0_OFF 0x7C000 #define MDP_AD4_1_OFF 0x7D000 #define MDP_AD4_INTR_EN_OFF 0x41c diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h index feb9a729844a..5acd5683d25a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h @@ -21,9 +21,6 @@ #define HIST_INTR_EN 0x01c #define HIST_INTR_STATUS 0x020 #define HIST_INTR_CLEAR 0x024 -#define INTF_INTR_EN 0x1C0 -#define INTF_INTR_STATUS 0x1C4 -#define INTF_INTR_CLEAR 0x1C8 #define SPLIT_DISPLAY_EN 0x2F4 #define SPLIT_DISPLAY_UPPER_PIPE_CTRL 0x2F8 #define DSPP_IGC_COLOR0_RAM_LUTN 0x300 -- GitLab From 85340c0256f9b85b47c5867e411df37d76df5858 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:18 +0200 Subject: [PATCH 4158/5631] drm/msm/dpu: Reindent REV_7xxx interrupt masks with tabs Use tabs for consistency with the other interrupt register definitions, rather than spaces. Fixes: ed6154a136e4 ("drm/msm/disp/dpu1: add intf offsets for SC7280 target") Fixes: 89688e2119b2 ("drm/msm/dpu: Add more of the INTF interrupt regions") Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/534212/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-4-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c index 85c0bda3ff90..17f3e7e4f194 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c @@ -32,15 +32,15 @@ #define MDP_AD4_INTR_EN_OFF 0x41c #define MDP_AD4_INTR_CLEAR_OFF 0x424 #define MDP_AD4_INTR_STATUS_OFF 0x420 -#define MDP_INTF_0_OFF_REV_7xxx 0x34000 -#define MDP_INTF_1_OFF_REV_7xxx 0x35000 -#define MDP_INTF_2_OFF_REV_7xxx 0x36000 -#define MDP_INTF_3_OFF_REV_7xxx 0x37000 -#define MDP_INTF_4_OFF_REV_7xxx 0x38000 -#define MDP_INTF_5_OFF_REV_7xxx 0x39000 -#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 -#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 -#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 +#define MDP_INTF_0_OFF_REV_7xxx 0x34000 +#define MDP_INTF_1_OFF_REV_7xxx 0x35000 +#define MDP_INTF_2_OFF_REV_7xxx 0x36000 +#define MDP_INTF_3_OFF_REV_7xxx 0x37000 +#define MDP_INTF_4_OFF_REV_7xxx 0x38000 +#define MDP_INTF_5_OFF_REV_7xxx 0x39000 +#define MDP_INTF_6_OFF_REV_7xxx 0x3a000 +#define MDP_INTF_7_OFF_REV_7xxx 0x3b000 +#define MDP_INTF_8_OFF_REV_7xxx 0x3c000 /** * struct dpu_intr_reg - array of DPU register sets -- GitLab From 701f69183d4d52533fb2af0d6948b7d1b00d1a09 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:19 +0200 Subject: [PATCH 4159/5631] drm/msm/dpu: Fix PP_BLK_DIPHER -> DITHER typo SM8550 exclusively has a DITHER sub-block inside the PINGPONG block and no other registers, hence the DITHER name of the macro and a corresponding PINGPONG block length of zero. However, the PP_BLK_ macro name was typo'd to DIPHER rather than DITHER. Fixes: efcd0107727c ("drm/msm/dpu: add support for SM8550") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534214/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-5-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h | 16 ++++++++-------- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index 9e403034093f..d0ab351b6a8b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -132,28 +132,28 @@ static const struct dpu_dspp_cfg sm8550_dspp[] = { &sm8150_dspp_sblk), }; static const struct dpu_pingpong_cfg sm8550_pp[] = { - PP_BLK_DIPHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK_DIPHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK_DIPHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK_DIPHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK_DIPHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK_DIPHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK_DIPHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x66000, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK_DIPHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x66400, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 8d5d782a4339..5d994bce696f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -491,7 +491,7 @@ static const struct dpu_pingpong_sub_blks sc7280_pp_sblk = { .len = 0x20, .version = 0x20000}, }; -#define PP_BLK_DIPHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ +#define PP_BLK_DITHER(_name, _id, _base, _merge_3d, _sblk, _done, _rdptr) \ {\ .name = _name, .id = _id, \ .base = _base, .len = 0, \ -- GitLab From fe47a3084789fd653a3465ba39ea4afe33fc6d19 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:20 +0200 Subject: [PATCH 4160/5631] drm/msm/dpu: Use V2 DITHER PINGPONG sub-block in SM8[34]50/SC8280XP According to downstream sources this DITHER sub-block sits at an offset of 0xe0 with version 0x20000. Lets fix this by using sc7280_pp_sblk instead of sdm845_pp_sblk. Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534208/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-6-27ce1a5ab5c6@somainline.org [quic_abhinavk@quicinc.com: minor fix in the commit message] Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 16 ++++++++-------- 3 files changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index 41ef0c8fc993..4c1bb88029cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index f3d935f346b2..a502e173f2c0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,17 +121,17 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index e409c119b0a2..ec296a52076c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sdm845_pp_sblk, + PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sdm845_pp_sblk, + PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sdm845_pp_sblk, + PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sdm845_pp_sblk, + PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; -- GitLab From 7557f58b6383e560dd5dc5267aceb8372f2a4426 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:21 +0200 Subject: [PATCH 4161/5631] drm/msm/dpu: Set PINGPONG block length to zero for DPU >= 7.0.0 Despite downstream DTS stating otherwise, the PINGPONG block has no registers starting with DPU revision 7.0.0. TEAR registers are gone since DPU 5.0.0 after being moved to the INTF block, and DSC registers are gone since 7.0.0, leaving only the dither sub-block. A future patch, part of the DSC 1.2 series, should disable DSC functions on the PINGPONG block for all DPU >= 7.0.0 hardware. Fixes: 4a352c2fc15a ("drm/msm/dpu: Introduce SC8280XP") Fixes: 0e91bcbb0016 ("drm/msm/dpu: Add SM8350 to hw catalog") Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450") Signed-off-by: Marijn Suijten Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534206/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-7-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- .../drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h | 8 ++++---- .../drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 12 ++++++------ .../drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 16 ++++++++-------- 4 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index 4c1bb88029cd..4f6a965bcd90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -127,22 +127,22 @@ static const struct dpu_dspp_cfg sm8350_dspp[] = { }; static const struct dpu_pingpong_cfg sm8350_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 5957de185984..6b2c7eae71d9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -87,10 +87,10 @@ static const struct dpu_dspp_cfg sc7280_dspp[] = { }; static const struct dpu_pingpong_cfg sc7280_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, 0, sc7280_pp_sblk, -1, -1), + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, 0, sc7280_pp_sblk, -1, -1), }; static const struct dpu_intf_cfg sc7280_intf[] = { diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index a502e173f2c0..706d0f13b598 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -121,17 +121,17 @@ static const struct dpu_dspp_cfg sc8280xp_dspp[] = { }; static const struct dpu_pingpong_cfg sc8280xp_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), -1), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), -1), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), -1), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), -1), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index ec296a52076c..4ecb3df5cbc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -128,28 +128,28 @@ static const struct dpu_dspp_cfg sm8450_dspp[] = { }; /* FIXME: interrupts */ static const struct dpu_pingpong_cfg sm8450_pp[] = { - PP_BLK("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_0", PINGPONG_0, 0x69000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12)), - PP_BLK("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_1", PINGPONG_1, 0x6a000, MERGE_3D_0, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13)), - PP_BLK("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_2", PINGPONG_2, 0x6b000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14)), - PP_BLK("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_3", PINGPONG_3, 0x6c000, MERGE_3D_1, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 15)), - PP_BLK("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_4", PINGPONG_4, 0x6d000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), -1), - PP_BLK("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_5", PINGPONG_5, 0x6e000, MERGE_3D_2, sc7280_pp_sblk, DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), -1), - PP_BLK("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_6", PINGPONG_6, 0x65800, MERGE_3D_3, sc7280_pp_sblk, -1, -1), - PP_BLK("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, + PP_BLK_DITHER("pingpong_7", PINGPONG_7, 0x65c00, MERGE_3D_3, sc7280_pp_sblk, -1, -1), }; -- GitLab From 202c044203ac5860e3025169105368d99f9bc6a2 Mon Sep 17 00:00:00 2001 From: Marijn Suijten Date: Thu, 27 Apr 2023 00:37:22 +0200 Subject: [PATCH 4162/5631] drm/msm/dpu: Remove duplicate register defines from INTF The INTF_FRAME_LINE_COUNT_EN, INTF_FRAME_COUNT and INTF_LINE_COUNT registers are already defined higher up, in the right place when sorted numerically. Fixes: 25fdd5933e4c ("drm/msm: Add SDM845 DPU support") Signed-off-by: Marijn Suijten Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534231/ Link: https://lore.kernel.org/r/20230411-dpu-intf-te-v4-8-27ce1a5ab5c6@somainline.org Signed-off-by: Abhinav Kumar --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c index 84ee2efa9c66..b9dddf576c02 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c @@ -56,11 +56,6 @@ #define INTF_TPG_RGB_MAPPING 0x11C #define INTF_PROG_FETCH_START 0x170 #define INTF_PROG_ROT_START 0x174 - -#define INTF_FRAME_LINE_COUNT_EN 0x0A8 -#define INTF_FRAME_COUNT 0x0AC -#define INTF_LINE_COUNT 0x0B0 - #define INTF_MUX 0x25C #define INTF_STATUS 0x26C -- GitLab From 3315e169b446249c1b61ff988d157238f4b2c5a0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Mar 2023 17:36:23 +0000 Subject: [PATCH 4163/5631] blk-integrity: use sysfs_emit MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The correct way to emit data into sysfs is via sysfs_emit(), use it. Also perform some trivial syntactic cleanups. Signed-off-by: Thomas Weißschuh Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20230309-kobj_release-gendisk_integrity-v3-1-ceccb4493c46@weissschuh.net Signed-off-by: Jens Axboe --- block/blk-integrity.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 8f01d786f5cb..aca8c783d749 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -248,20 +248,19 @@ static ssize_t integrity_attr_store(struct kobject *kobj, static ssize_t integrity_format_show(struct blk_integrity *bi, char *page) { if (bi->profile && bi->profile->name) - return sprintf(page, "%s\n", bi->profile->name); - else - return sprintf(page, "none\n"); + return sysfs_emit(page, "%s\n", bi->profile->name); + return sysfs_emit(page, "none\n"); } static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page) { - return sprintf(page, "%u\n", bi->tag_size); + return sysfs_emit(page, "%u\n", bi->tag_size); } static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page) { - return sprintf(page, "%u\n", - bi->interval_exp ? 1 << bi->interval_exp : 0); + return sysfs_emit(page, "%u\n", + bi->interval_exp ? 1 << bi->interval_exp : 0); } static ssize_t integrity_verify_store(struct blk_integrity *bi, @@ -280,7 +279,7 @@ static ssize_t integrity_verify_store(struct blk_integrity *bi, static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page) { - return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0); + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY)); } static ssize_t integrity_generate_store(struct blk_integrity *bi, @@ -299,13 +298,13 @@ static ssize_t integrity_generate_store(struct blk_integrity *bi, static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page) { - return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0); + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE)); } static ssize_t integrity_device_show(struct blk_integrity *bi, char *page) { - return sprintf(page, "%u\n", - (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0); + return sysfs_emit(page, "%u\n", + !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } static struct integrity_sysfs_entry integrity_format_entry = { -- GitLab From 76b8c319f02715e14abdbbbdd6508e83a1059bcc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Mar 2023 17:36:24 +0000 Subject: [PATCH 4164/5631] blk-integrity: convert to struct device_attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An upcoming patch will register the integrity attributes directly with the struct device kobject. For this the attributes have to be implemented in terms of struct device_attribute. Signed-off-by: Thomas Weißschuh Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20230309-kobj_release-gendisk_integrity-v3-2-ceccb4493c46@weissschuh.net Signed-off-by: Jens Axboe --- block/blk-integrity.c | 127 +++++++++++++++++++++--------------------- 1 file changed, 62 insertions(+), 65 deletions(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index aca8c783d749..1cbfdea88c72 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -212,21 +212,15 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, return true; } -struct integrity_sysfs_entry { - struct attribute attr; - ssize_t (*show)(struct blk_integrity *, char *); - ssize_t (*store)(struct blk_integrity *, const char *, size_t); -}; - static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct blk_integrity *bi = &disk->queue->integrity; - struct integrity_sysfs_entry *entry = - container_of(attr, struct integrity_sysfs_entry, attr); + struct device *dev = disk_to_dev(disk); + struct device_attribute *dev_attr = + container_of(attr, struct device_attribute, attr); - return entry->show(bi, page); + return dev_attr->show(dev, dev_attr, page); } static ssize_t integrity_attr_store(struct kobject *kobj, @@ -234,38 +228,53 @@ static ssize_t integrity_attr_store(struct kobject *kobj, size_t count) { struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct blk_integrity *bi = &disk->queue->integrity; - struct integrity_sysfs_entry *entry = - container_of(attr, struct integrity_sysfs_entry, attr); - ssize_t ret = 0; + struct device *dev = disk_to_dev(disk); + struct device_attribute *dev_attr = + container_of(attr, struct device_attribute, attr); - if (entry->store) - ret = entry->store(bi, page, count); + if (!dev_attr->store) + return 0; + return dev_attr->store(dev, dev_attr, page, count); +} - return ret; +static inline struct blk_integrity *dev_to_bi(struct device *dev) +{ + return &dev_to_disk(dev)->queue->integrity; } -static ssize_t integrity_format_show(struct blk_integrity *bi, char *page) +static ssize_t format_show(struct device *dev, struct device_attribute *attr, + char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + if (bi->profile && bi->profile->name) return sysfs_emit(page, "%s\n", bi->profile->name); return sysfs_emit(page, "none\n"); } -static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page) +static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, + char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + return sysfs_emit(page, "%u\n", bi->tag_size); } -static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page) +static ssize_t protection_interval_bytes_show(struct device *dev, + struct device_attribute *attr, + char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + return sysfs_emit(page, "%u\n", bi->interval_exp ? 1 << bi->interval_exp : 0); } -static ssize_t integrity_verify_store(struct blk_integrity *bi, - const char *page, size_t count) +static ssize_t read_verify_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t count) { + struct blk_integrity *bi = dev_to_bi(dev); char *p = (char *) page; unsigned long val = simple_strtoul(p, &p, 10); @@ -277,14 +286,20 @@ static ssize_t integrity_verify_store(struct blk_integrity *bi, return count; } -static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page) +static ssize_t read_verify_show(struct device *dev, + struct device_attribute *attr, char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY)); } -static ssize_t integrity_generate_store(struct blk_integrity *bi, - const char *page, size_t count) +static ssize_t write_generate_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t count) { + struct blk_integrity *bi = dev_to_bi(dev); + char *p = (char *) page; unsigned long val = simple_strtoul(p, &p, 10); @@ -296,57 +311,39 @@ static ssize_t integrity_generate_store(struct blk_integrity *bi, return count; } -static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page) +static ssize_t write_generate_show(struct device *dev, + struct device_attribute *attr, char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE)); } -static ssize_t integrity_device_show(struct blk_integrity *bi, char *page) +static ssize_t device_is_integrity_capable_show(struct device *dev, + struct device_attribute *attr, + char *page) { + struct blk_integrity *bi = dev_to_bi(dev); + return sysfs_emit(page, "%u\n", !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } -static struct integrity_sysfs_entry integrity_format_entry = { - .attr = { .name = "format", .mode = 0444 }, - .show = integrity_format_show, -}; - -static struct integrity_sysfs_entry integrity_tag_size_entry = { - .attr = { .name = "tag_size", .mode = 0444 }, - .show = integrity_tag_size_show, -}; - -static struct integrity_sysfs_entry integrity_interval_entry = { - .attr = { .name = "protection_interval_bytes", .mode = 0444 }, - .show = integrity_interval_show, -}; - -static struct integrity_sysfs_entry integrity_verify_entry = { - .attr = { .name = "read_verify", .mode = 0644 }, - .show = integrity_verify_show, - .store = integrity_verify_store, -}; - -static struct integrity_sysfs_entry integrity_generate_entry = { - .attr = { .name = "write_generate", .mode = 0644 }, - .show = integrity_generate_show, - .store = integrity_generate_store, -}; - -static struct integrity_sysfs_entry integrity_device_entry = { - .attr = { .name = "device_is_integrity_capable", .mode = 0444 }, - .show = integrity_device_show, -}; +static DEVICE_ATTR_RO(format); +static DEVICE_ATTR_RO(tag_size); +static DEVICE_ATTR_RO(protection_interval_bytes); +static DEVICE_ATTR_RW(read_verify); +static DEVICE_ATTR_RW(write_generate); +static DEVICE_ATTR_RO(device_is_integrity_capable); static struct attribute *integrity_attrs[] = { - &integrity_format_entry.attr, - &integrity_tag_size_entry.attr, - &integrity_interval_entry.attr, - &integrity_verify_entry.attr, - &integrity_generate_entry.attr, - &integrity_device_entry.attr, - NULL, + &dev_attr_format.attr, + &dev_attr_tag_size.attr, + &dev_attr_protection_interval_bytes.attr, + &dev_attr_read_verify.attr, + &dev_attr_write_generate.attr, + &dev_attr_device_is_integrity_capable.attr, + NULL }; ATTRIBUTE_GROUPS(integrity); -- GitLab From ff53cd52d9bdbf4074d2bbe9b591729997780bd3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 18 Mar 2023 17:36:25 +0000 Subject: [PATCH 4165/5631] blk-integrity: register sysfs attributes on struct device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The "integrity" kobject only acted as a holder for static sysfs entries. It also was embedded into struct gendisk without managing it, violating assumptions of the driver core. Instead register the sysfs entries directly onto the struct device. Also drop the now unused member integrity_kobj from struct gendisk. Suggested-by: Christoph Hellwig Signed-off-by: Thomas Weißschuh Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20230309-kobj_release-gendisk_integrity-v3-3-ceccb4493c46@weissschuh.net Signed-off-by: Jens Axboe --- block/blk-integrity.c | 55 +++--------------------------------------- block/blk.h | 10 +------- block/genhd.c | 12 +++------ include/linux/blkdev.h | 3 --- 4 files changed, 8 insertions(+), 72 deletions(-) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 1cbfdea88c72..d4e9b4556d14 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -212,31 +212,6 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, return true; } -static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr, - char *page) -{ - struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct device *dev = disk_to_dev(disk); - struct device_attribute *dev_attr = - container_of(attr, struct device_attribute, attr); - - return dev_attr->show(dev, dev_attr, page); -} - -static ssize_t integrity_attr_store(struct kobject *kobj, - struct attribute *attr, const char *page, - size_t count) -{ - struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct device *dev = disk_to_dev(disk); - struct device_attribute *dev_attr = - container_of(attr, struct device_attribute, attr); - - if (!dev_attr->store) - return 0; - return dev_attr->store(dev, dev_attr, page, count); -} - static inline struct blk_integrity *dev_to_bi(struct device *dev) { return &dev_to_disk(dev)->queue->integrity; @@ -345,16 +320,10 @@ static struct attribute *integrity_attrs[] = { &dev_attr_device_is_integrity_capable.attr, NULL }; -ATTRIBUTE_GROUPS(integrity); -static const struct sysfs_ops integrity_ops = { - .show = &integrity_attr_show, - .store = &integrity_attr_store, -}; - -static const struct kobj_type integrity_ktype = { - .default_groups = integrity_groups, - .sysfs_ops = &integrity_ops, +const struct attribute_group blk_integrity_attr_group = { + .name = "integrity", + .attrs = integrity_attrs, }; static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter) @@ -433,21 +402,3 @@ void blk_integrity_unregister(struct gendisk *disk) memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); - -int blk_integrity_add(struct gendisk *disk) -{ - int ret; - - ret = kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, - &disk_to_dev(disk)->kobj, "%s", "integrity"); - if (!ret) - kobject_uevent(&disk->integrity_kobj, KOBJ_ADD); - return ret; -} - -void blk_integrity_del(struct gendisk *disk) -{ - kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE); - kobject_del(&disk->integrity_kobj); - kobject_put(&disk->integrity_kobj); -} diff --git a/block/blk.h b/block/blk.h index 564119a76bc5..45547bcf1119 100644 --- a/block/blk.h +++ b/block/blk.h @@ -214,8 +214,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } -int blk_integrity_add(struct gendisk *disk); -void blk_integrity_del(struct gendisk *); +extern const struct attribute_group blk_integrity_attr_group; #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline bool blk_integrity_merge_rq(struct request_queue *rq, struct request *r1, struct request *r2) @@ -248,13 +247,6 @@ static inline bool bio_integrity_endio(struct bio *bio) static inline void bio_integrity_free(struct bio *bio) { } -static inline int blk_integrity_add(struct gendisk *disk) -{ - return 0; -} -static inline void blk_integrity_del(struct gendisk *disk) -{ -} #endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout); diff --git a/block/genhd.c b/block/genhd.c index 8d56fb5f08b2..9fa4a7cd978c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -478,15 +478,11 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, */ pm_runtime_set_memalloc_noio(ddev, true); - ret = blk_integrity_add(disk); - if (ret) - goto out_del_block_link; - disk->part0->bd_holder_dir = kobject_create_and_add("holders", &ddev->kobj); if (!disk->part0->bd_holder_dir) { ret = -ENOMEM; - goto out_del_integrity; + goto out_del_block_link; } disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (!disk->slave_dir) { @@ -549,8 +545,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, disk->slave_dir = NULL; out_put_holder_dir: kobject_put(disk->part0->bd_holder_dir); -out_del_integrity: - blk_integrity_del(disk); out_del_block_link: if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(ddev)); @@ -613,7 +607,6 @@ void del_gendisk(struct gendisk *disk) if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN))) return; - blk_integrity_del(disk); disk_del_events(disk); mutex_lock(&disk->open_mutex); @@ -1150,6 +1143,9 @@ static const struct attribute_group *disk_attr_groups[] = { &disk_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, +#endif +#ifdef CONFIG_BLK_DEV_INTEGRITY + &blk_integrity_attr_group, #endif NULL }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6ede578dfbc6..aac5c8d7a9ff 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -157,9 +157,6 @@ struct gendisk { struct timer_rand_state *random; atomic_t sync_io; /* RAID */ struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_DEV_ZONED /* -- GitLab From 474f01015ffdb74e01c2eb3584a2822c64e7b2be Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Thu, 3 Nov 2022 22:29:31 -0400 Subject: [PATCH 4166/5631] drm/amd/display: Do not set drr on pipe commit [WHY] Writing to DRR registers such as OTG_V_TOTAL_MIN on the same frame as a pipe commit can cause underflow. [HOW] Move DMUB p-state delegate into optimze_bandwidth; enabling FAMS sets optimized_required. This change expects that Freesync requests are blocked when optimized_required is true. Reviewed-by: Rodrigo Siqueira Signed-off-by: Wesley Chalmers Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 ++++++ drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c | 7 +++++++ 2 files changed, 13 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 5403e9399a46..6ce10fd4bb1a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2113,6 +2113,12 @@ void dcn20_optimize_bandwidth( if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + dc_dmub_srv_p_state_delegate(dc, + true, context); + context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + } + dc->clk_mgr->funcs->update_clocks( dc->clk_mgr, context, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 0e071fbc9154..0411867654dd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -985,11 +985,18 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, void dcn30_prepare_bandwidth(struct dc *dc, struct dc_state *context) { + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + dc->optimized_required = true; + context->bw_ctx.bw.dcn.clk.p_state_change_support = false; + } + if (dc->clk_mgr->dc_mode_softmax_enabled) if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 && context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000) dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); + + dc_dmub_srv_p_state_delegate(dc, false, context); } -- GitLab From ce560ac40272a5c8b5b68a9d63a75edd9e66aed2 Mon Sep 17 00:00:00 2001 From: Wesley Chalmers Date: Tue, 28 Feb 2023 13:48:00 -0500 Subject: [PATCH 4167/5631] drm/amd/display: Block optimize on consecutive FAMS enables [WHY] It is possible to commit state multiple times in rapid succession with FAMS enabled; if each of these commits were to set optimized_required, then the user may see latency. [HOW] fw_based_mclk_switching is currently not used in dc->clk_mgr; use it to track whether the current state has FAMS enabled; if it has, then do not disable FAMS in prepare_bandwidth, and do not set optimized_required. Reviewed-by: Rodrigo Siqueira Signed-off-by: Wesley Chalmers Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn20/dcn20_hwseq.c | 3 +++ .../drm/amd/display/dc/dcn30/dcn30_hwseq.c | 22 ++++++++++++++++--- 2 files changed, 22 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 6ce10fd4bb1a..422fbf79da64 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -2117,6 +2117,9 @@ void dcn20_optimize_bandwidth( dc_dmub_srv_p_state_delegate(dc, true, context); context->bw_ctx.bw.dcn.clk.p_state_change_support = true; + dc->clk_mgr->clks.fw_based_mclk_switching = true; + } else { + dc->clk_mgr->clks.fw_based_mclk_switching = false; } dc->clk_mgr->funcs->update_clocks( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 0411867654dd..8263a07f265f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -983,9 +983,13 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc, } void dcn30_prepare_bandwidth(struct dc *dc, - struct dc_state *context) + struct dc_state *context) { - if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) { + bool p_state_change_support = context->bw_ctx.bw.dcn.clk.p_state_change_support; + /* Any transition into an FPO config should disable MCLK switching first to avoid + * driver and FW P-State synchronization issues. + */ + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { dc->optimized_required = true; context->bw_ctx.bw.dcn.clk.p_state_change_support = false; } @@ -996,7 +1000,19 @@ void dcn30_prepare_bandwidth(struct dc *dc, dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz); dcn20_prepare_bandwidth(dc, context); + /* + * enabled -> enabled: do not disable + * enabled -> disabled: disable + * disabled -> enabled: don't care + * disabled -> disabled: don't care + */ + if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) + dc_dmub_srv_p_state_delegate(dc, false, context); - dc_dmub_srv_p_state_delegate(dc, false, context); + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) { + /* After disabling P-State, restore the original value to ensure we get the correct P-State + * on the next optimize. */ + context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support; + } } -- GitLab From 822b84ecfc646da0f87fd947fa00dc3be5e45ecc Mon Sep 17 00:00:00 2001 From: Rodrigo Siqueira Date: Tue, 4 Apr 2023 14:54:05 -0600 Subject: [PATCH 4168/5631] drm/amd/display: Add missing WA and MCLK validation When the commit fff7eb56b376 ("drm/amd/display: Don't set dram clock change requirement for SubVP") was merged, we missed some parts associated with the MCLK switch. This commit adds all the missing parts. Fixes: fff7eb56b376 ("drm/amd/display: Don't set dram clock change requirement for SubVP") Reviewed-by: Aurabindo Pillai Signed-off-by: Rodrigo Siqueira Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c | 1 + .../drm/amd/display/dc/dcn32/dcn32_resource.c | 2 +- .../drm/amd/display/dc/dml/dcn30/dcn30_fpu.c | 18 +++++++++++++++++- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index db0974fe58ab..1f5ee5cde6e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -948,6 +948,7 @@ void dcn32_init_hw(struct dc *dc) if (dc->ctx->dmub_srv) { dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; + dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch; } } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index 0beb11d95eb7..a876e6eb6cd8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -2023,7 +2023,7 @@ int dcn32_populate_dml_pipes_from_context( // In general cases we want to keep the dram clock change requirement // (prefer configs that support MCLK switch). Only override to false // for SubVP - if (subvp_in_use) + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || subvp_in_use) context->bw_ctx.dml.soc.dram_clock_change_requirement_final = false; else context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c index 80972ee5e55b..a352c703e258 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c @@ -368,7 +368,9 @@ void dcn30_fpu_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) dc_assert_fp_enabled(); if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; + if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || + context->bw_ctx.dml.soc.dram_clock_change_latency_us == 0) + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us; context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us; } @@ -563,6 +565,20 @@ void dcn30_fpu_calculate_wm_and_dlg( pipe_idx++; } + // WA: restrict FPO to use first non-strobe mode (NV24 BW issue) + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && + dc->dml.soc.num_chans <= 4 && + context->bw_ctx.dml.vba.DRAMSpeed <= 1700 && + context->bw_ctx.dml.vba.DRAMSpeed >= 1500) { + + for (i = 0; i < dc->dml.soc.num_states; i++) { + if (dc->dml.soc.clock_limits[i].dram_speed_mts > 1700) { + context->bw_ctx.dml.vba.DRAMSpeed = dc->dml.soc.clock_limits[i].dram_speed_mts; + break; + } + } + } + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); if (!pstate_en) -- GitLab From f11aee97b13ea6817287cd8dbed9b09a260ff0e7 Mon Sep 17 00:00:00 2001 From: Josip Pavic Date: Fri, 14 May 2021 14:04:02 -0400 Subject: [PATCH 4169/5631] drm/amd/display: copy dmub caps to dc on dcn31 [Why & How] Add code path to copy dmub caps to dc, which is missing on dcn31 Acked-by: Qingqing Zhuo Signed-off-by: Josip Pavic Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 7ac6e69cff37..62ce36c75c4d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -295,6 +295,10 @@ void dcn31_init_hw(struct dc *dc) if (dc->res_pool->hubbub->funcs->init_crb) dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); #endif + + // Get DMCUB capabilities + dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); + dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; } void dcn31_dsc_pg_control( -- GitLab From 3fb7efd6866e5d43770e999b33d619a3b345dc2f Mon Sep 17 00:00:00 2001 From: Alex Hung Date: Wed, 15 Mar 2023 19:09:15 +0800 Subject: [PATCH 4170/5631] drm/amd/display: allow edp updates for virtual signal [Why] When IGT's kms_hdmi_inject forces EDID for HDMI audio, dc rejects the request because virtual signal is not in dc_is_audio_capable_signal function. [How] Includes SIGNAL_TYPE_VIRTUAL as audio capable. Reviewed-by: Chao-kai Wang Acked-by: Qingqing Zhuo Signed-off-by: Alex Hung Signed-off-by: Wenchieh Chien Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/include/signal_types.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h index beed70179bb5..23a308c3eccb 100644 --- a/drivers/gpu/drm/amd/display/include/signal_types.h +++ b/drivers/gpu/drm/amd/display/include/signal_types.h @@ -104,6 +104,7 @@ static inline bool dc_is_audio_capable_signal(enum signal_type signal) { return (signal == SIGNAL_TYPE_DISPLAY_PORT || signal == SIGNAL_TYPE_DISPLAY_PORT_MST || + signal == SIGNAL_TYPE_VIRTUAL || dc_is_hdmi_signal(signal)); } -- GitLab From da5e14909776edea4462672fb4a3007802d262e7 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Fri, 24 Mar 2023 10:42:37 -0400 Subject: [PATCH 4171/5631] drm/amd/display: Fix hang when skipping modeset [Why&How] When skipping full modeset since the only state change was a front porch change, the DC commit sequence requires extra checks to handle non existant plane states being asked to be removed from context. Reviewed-by: Alvin Lee Acked-by: Qingqing Zhuo Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++++- drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 3 +++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6cacb76f389e..c432436cd66d 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7972,6 +7972,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, continue; dc_plane = dm_new_plane_state->dc_state; + if (!dc_plane) + continue; bundle->surface_updates[planes_count].surface = dc_plane; if (new_pcrtc_state->color_mgmt_changed) { @@ -9620,8 +9622,9 @@ static int dm_update_plane_state(struct dc *dc, return -EINVAL; } + if (dm_old_plane_state->dc_state) + dc_plane_state_release(dm_old_plane_state->dc_state); - dc_plane_state_release(dm_old_plane_state->dc_state); dm_new_plane_state->dc_state = NULL; *lock_and_validation_needed = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 85d54bfb595c..117d80cb36fb 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1707,6 +1707,9 @@ bool dc_remove_plane_from_context( struct dc_stream_status *stream_status = NULL; struct resource_pool *pool = dc->res_pool; + if (!plane_state) + return true; + for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { stream_status = &context->stream_status[i]; -- GitLab From 025ce392b5f213696ca0af3e07735d0fae020694 Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Mon, 27 Mar 2023 09:10:48 -0400 Subject: [PATCH 4172/5631] drm/amd/display: fix memleak in aconnector->timing_requested [Why] when amdgpu_dm_update_connector_after_detect is called two times successively with valid sink, memory allocated of aconnector->timing_requested for the first call is not free. this causes memeleak. [How] allocate memory only when aconnector->timing_requested is null. Reviewed-by: Qingqing Zhuo Acked-by: Qingqing Zhuo Signed-off-by: Hersen Wu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c432436cd66d..8b03c8d8f0b8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3128,9 +3128,12 @@ void amdgpu_dm_update_connector_after_detect( aconnector->edid); } - aconnector->timing_requested = kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL); - if (!aconnector->timing_requested) - dm_error("%s: failed to create aconnector->requested_timing\n", __func__); + if (!aconnector->timing_requested) { + aconnector->timing_requested = + kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL); + if (!aconnector->timing_requested) + dm_error("failed to create aconnector->requested_timing\n"); + } drm_connector_update_edid_property(connector, aconnector->edid); amdgpu_dm_update_freesync_caps(connector, aconnector->edid); -- GitLab From 0c0463ff010b80a0c03937ca8cf85587ded2f20e Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Tue, 28 Mar 2023 09:53:33 -0400 Subject: [PATCH 4173/5631] drm/amd/display: Reduce SubVP + DRR stretch margin [Description] - Having excessively large margin causes failure in the static schedulability check in some cases for SubVP + DRR - 100us of DRR margin is sufficient based on a weeks worth of stress testing on different display configs Reviewed-by: Michael Strauss Acked-by: Qingqing Zhuo Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dc_stream.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 181a3408cc61..25284006019c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -144,7 +144,7 @@ struct test_pattern { unsigned int cust_pattern_size; }; -#define SUBVP_DRR_MARGIN_US 600 // 600us for DRR margin (SubVP + DRR) +#define SUBVP_DRR_MARGIN_US 100 // 100us for DRR margin (SubVP + DRR) enum mall_stream_type { SUBVP_NONE, // subvp not in use -- GitLab From 3cf7cd3f770a0b89dc5f06e19edb52e65b93b214 Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Tue, 28 Mar 2023 10:45:24 -0400 Subject: [PATCH 4174/5631] drm/amd/display: fix access hdcp_workqueue assert MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] hdcp are enabled for asics from raven. for old asics which hdcp are not enabled, hdcp_workqueue are null. some access to hdcp work queue are not guarded with pointer check. [How] add hdcp_workqueue pointer check before access workqueue. Fixes: 82986fd631fa ("drm/amd/display: save restore hdcp state when display is unplugged from mst hub") Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2444 Reported-by: Niklāvs Koļesņikovs <89q1r14hd@relay.firefox.com> Reviewed-by: Bhawanpreet Lakha Acked-by: Qingqing Zhuo Signed-off-by: Hersen Wu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 ++++++ .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 16 ++++++++++------ 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 8b03c8d8f0b8..fc08b4191e24 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8559,6 +8559,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + if (!adev->dm.hdcp_workqueue) + continue; + pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i); if (!connector) @@ -8607,6 +8610,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc); struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + if (!adev->dm.hdcp_workqueue) + continue; + new_crtc_state = NULL; old_crtc_state = NULL; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 994ba426ca66..5dc79b753d5f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -379,13 +379,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector) if (aconnector->dc_sink && connector->state) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = drm_to_adev(dev); - struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; - struct hdcp_workqueue *hdcp_w = &hdcp_work[aconnector->dc_link->link_index]; - connector->state->hdcp_content_type = - hdcp_w->hdcp_content_type[connector->index]; - connector->state->content_protection = - hdcp_w->content_protection[connector->index]; + if (adev->dm.hdcp_workqueue) { + struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue; + struct hdcp_workqueue *hdcp_w = + &hdcp_work[aconnector->dc_link->link_index]; + + connector->state->hdcp_content_type = + hdcp_w->hdcp_content_type[connector->index]; + connector->state->content_protection = + hdcp_w->content_protection[connector->index]; + } } if (aconnector->dc_sink) { -- GitLab From 56d8ce9d8c17bea955b0c2551ee86149486890ae Mon Sep 17 00:00:00 2001 From: Michael Mityushkin Date: Thu, 30 Mar 2023 11:35:08 -0400 Subject: [PATCH 4175/5631] drm/amd/display: Apply correct panel mode when reinitializing hardware [Why] When link training during engine recovery, ASSR might fail causing panel mode to be reset to default. This should not happen for eDP as it will prevent the panel from turning back on. [How] Added dp_panel_mode to struct dc_link to remember previously applied panel mode. Do not reset panel mode to default while performing link training if previously used panel mode = eDP. Reviewed-by: Nicholas Kazlauskas Acked-by: Qingqing Zhuo Signed-off-by: Michael Mityushkin Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dc.h | 1 + .../gpu/drm/amd/display/dc/link/protocols/link_dp_training.c | 5 ++++- .../amd/display/dc/link/protocols/link_edp_panel_control.c | 1 + 3 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 23ee63b98dcd..30f0ba05a6e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1454,6 +1454,7 @@ struct dc_link { struct ddc_service *ddc; + enum dp_panel_mode panel_mode; bool aux_mode; /* Private to DC core */ diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c index 170f33835930..579fa222810d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c @@ -1596,7 +1596,10 @@ bool perform_link_training_with_retries( * Report and continue with eDP panel mode to * perform eDP link training with right settings */ - cp_psp->funcs.enable_assr(cp_psp->handle, link); + bool result; + result = cp_psp->funcs.enable_assr(cp_psp->handle, link); + if (!result && link->panel_mode != DP_PANEL_MODE_EDP) + panel_mode = DP_PANEL_MODE_DEFAULT; } } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index d895046787bc..8d1df863659c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -83,6 +83,7 @@ void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode) ASSERT(result == DC_OK); } } + link->panel_mode = panel_mode; DC_LOG_DETECTION_DP_CAPS("Link: %d eDP panel mode supported: %d " "eDP panel mode enabled: %d \n", link->link_index, -- GitLab From e0cce122514ff76c3c986103c94de68fbb401949 Mon Sep 17 00:00:00 2001 From: Jingwen Zhu Date: Thu, 30 Mar 2023 16:38:59 +0800 Subject: [PATCH 4176/5631] drm/amd/display: Improvement for handling edp link training fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] The eDP retrain will cause the DPCD 300 to be reset to default. And cause the brightness can't be set correctly. [How] delete the call to edp panel power control in both enable_link_output/disable_link_output entirely and only call edp panel control in enable_link_dp and  disable_link_dp once. Reviewed-by: Charlene Liu Acked-by: Qingqing Zhuo Signed-off-by: Jingwen Zhu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../display/dc/dce110/dce110_hw_sequencer.c | 19 +++++++++++-------- .../gpu/drm/amd/display/dc/link/link_dpms.c | 5 +++++ 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 9fe0ce91db00..8d2460d06bce 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -3031,10 +3031,12 @@ void dce110_enable_dp_link_output( const struct link_hwss *link_hwss = get_link_hwss(link, link_res); unsigned int i; - + /* + * Add the logic to extract BOTH power up and power down sequences + * from enable/disable link output and only call edp panel control + * in enable_link_dp and disable_link_dp once. + */ if (link->connector_signal == SIGNAL_TYPE_EDP) { - if (!link->dc->config.edp_no_power_sequencing) - link->dc->hwss.edp_power_control(link, true); link->dc->hwss.edp_wait_for_hpd_ready(link, true); } @@ -3096,11 +3098,12 @@ void dce110_disable_link_output(struct dc_link *link, link_hwss->disable_link_output(link, link_res, signal); link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; - - if (signal == SIGNAL_TYPE_EDP && - link->dc->hwss.edp_backlight_control) - link->dc->hwss.edp_power_control(link, false); - else if (dmcu != NULL && dmcu->funcs->lock_phy) + /* + * Add the logic to extract BOTH power up and power down sequences + * from enable/disable link output and only call edp panel control + * in enable_link_dp and disable_link_dp once. + */ + if (dmcu != NULL && dmcu->funcs->lock_phy) dmcu->funcs->unlock_phy(dmcu); dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); } diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 027ad1f0144d..2267fb097830 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -1927,6 +1927,11 @@ static void disable_link_dp(struct dc_link *link, dp_disable_link_phy(link, link_res, signal); + if (link->connector_signal == SIGNAL_TYPE_EDP) { + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, false); + } + if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) /* set the sink to SST mode after disabling the link */ enable_mst_on_sink(link, false); -- GitLab From dd24662d9dfbad281bbf030f06d68c7938fa0c66 Mon Sep 17 00:00:00 2001 From: Hersen Wu Date: Sun, 29 May 2022 10:54:30 -0400 Subject: [PATCH 4177/5631] drm/amd/display: Return error code on DSC atomic check failure [Why&How] We were not returning -EINVAL on DSC atomic check fail. Add it. Fixes: 71be4b16d39a ("drm/amd/display: dsc validate fail not pass to atomic check") Reviewed-by: Aurabindo Pillai Signed-off-by: Hersen Wu Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 + drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 1 + 2 files changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index fc08b4191e24..b619d7cdb525 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -10170,6 +10170,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); if (ret) { DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 5dc79b753d5f..810ab682f424 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1410,6 +1410,7 @@ int pre_validate_dsc(struct drm_atomic_state *state, ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars); if (ret != 0) { DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; goto clean_exit; } -- GitLab From fc3888fe2c63b35a22db8234d142823a5ffda9d8 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Wed, 5 Apr 2023 16:17:42 -0400 Subject: [PATCH 4178/5631] drm/amd/display: remove incorrect early return [Why&How] Remove incorrect early return in a device specific fifo reset workaround Reviewed-by: Leo Li Reviewed-by: Qingqing Zhuo Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 330ab036c830..c6ce2b7123b7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -687,7 +687,6 @@ static void apply_synaptics_fifo_reset_wa(struct drm_dp_aux *aux) return; data[0] |= (1 << 1); // set bit 1 to 1 - return; if (!execute_synaptics_rc_command(aux, false, 0x31, 4, 0x221198, data)) return; -- GitLab From b1bcdd409d2d158867ce0b71cfa9bcefe83ce07f Mon Sep 17 00:00:00 2001 From: Tianci Yin Date: Mon, 6 Feb 2023 15:58:46 +0800 Subject: [PATCH 4179/5631] drm/amd/display: Disable migration to ensure consistency of per-CPU variable [why] Since the variable fpu_recursion_depth is per-CPU type, it has one copy on each CPU, thread migration causes data consistency issue, then the call trace shows up. And preemption disabling can't prevent migration. [how] Disable migration to ensure consistency of fpu_recursion_depth. Reviewed-by: Aurabindo Pillai Signed-off-by: Tianci Yin Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c index 1743ca0a3641..c42aa947c969 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c @@ -89,6 +89,7 @@ void dc_fpu_begin(const char *function_name, const int line) if (*pcpu == 1) { #if defined(CONFIG_X86) + migrate_disable(); kernel_fpu_begin(); #elif defined(CONFIG_PPC64) if (cpu_has_feature(CPU_FTR_VSX_COMP)) { @@ -129,6 +130,7 @@ void dc_fpu_end(const char *function_name, const int line) if (*pcpu <= 0) { #if defined(CONFIG_X86) kernel_fpu_end(); + migrate_enable(); #elif defined(CONFIG_PPC64) if (cpu_has_feature(CPU_FTR_VSX_COMP)) { disable_kernel_vsx(); -- GitLab From d1c5c3e252b8a911a524e6ee33b82aca81397745 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Thu, 6 Apr 2023 12:28:59 -0400 Subject: [PATCH 4180/5631] drm/amd/display: Fixes for dcn32_clk_mgr implementation [Why&How] Fix CLK MGR early initialization and add logging. Fixes: 265280b99822 ("drm/amd/display: add CLKMGR changes for DCN32/321") Reviewed-by: Leo Li Reviewed-by: Qingqing Zhuo Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index ea753f8fa175..8d9444db092a 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -878,6 +878,8 @@ void dcn32_clk_mgr_construct( struct pp_smu_funcs *pp_smu, struct dccg *dccg) { + struct clk_log_info log_info = {0}; + clk_mgr->base.ctx = ctx; clk_mgr->base.funcs = &dcn32_funcs; if (ASICREV_IS_GC_11_0_2(clk_mgr->base.ctx->asic_id.hw_internal_rev)) { @@ -911,6 +913,7 @@ void dcn32_clk_mgr_construct( clk_mgr->base.clks.ref_dtbclk_khz = 268750; } + /* integer part is now VCO frequency in kHz */ clk_mgr->base.dentist_vco_freq_khz = dcn32_get_vco_frequency_from_reg(clk_mgr); @@ -918,6 +921,8 @@ void dcn32_clk_mgr_construct( if (clk_mgr->base.dentist_vco_freq_khz == 0) clk_mgr->base.dentist_vco_freq_khz = 4300000; /* Updated as per HW docs */ + dcn32_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); + if (ctx->dc->debug.disable_dtb_ref_clk_switch && clk_mgr->base.clks.ref_dtbclk_khz != clk_mgr->base.boot_snapshot.dtbclk) { clk_mgr->base.clks.ref_dtbclk_khz = clk_mgr->base.boot_snapshot.dtbclk; -- GitLab From 425afa0ac99a05b39e6cd00704fa0e3e925cee2b Mon Sep 17 00:00:00 2001 From: Cruise Hung Date: Fri, 13 May 2022 09:16:42 +0800 Subject: [PATCH 4181/5631] drm/amd/display: Reset OUTBOX0 r/w pointer on DMUB reset [Why & How] We missed resetting OUTBOX0 mailbox r/w pointer on DMUB reset. Fix it. Fixes: 6ecf9773a503 ("drm/amd/display: Fix DMUB outbox trace in S4 (#4465)") Signed-off-by: Cruise Hung Acked-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c index a76da0131add..b0adbf783aae 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c @@ -130,6 +130,8 @@ void dmub_dcn32_reset(struct dmub_srv *dmub) REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); REG_WRITE(DMCUB_OUTBOX1_WPTR, 0); + REG_WRITE(DMCUB_OUTBOX0_RPTR, 0); + REG_WRITE(DMCUB_OUTBOX0_WPTR, 0); REG_WRITE(DMCUB_SCRATCH0, 0); } -- GitLab From 99d92eaca5d915763b240aae24669f5bf3227ecf Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Thu, 6 Apr 2023 15:48:48 -0400 Subject: [PATCH 4182/5631] drm/amd/display: Do not clear GPINT register when releasing DMUB from reset [Why & How] There's no need to clear GPINT register for DMUB when releasing it from reset. Fix that. Fixes: ac2e555e0a7f ("drm/amd/display: Add DMCUB source files and changes for DCN32/321") Reviewed-by: Leo Li Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c index b0adbf783aae..9c20516be066 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c @@ -137,7 +137,6 @@ void dmub_dcn32_reset(struct dmub_srv *dmub) void dmub_dcn32_reset_release(struct dmub_srv *dmub) { - REG_WRITE(DMCUB_GPINT_DATAIN1, 0); REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0); REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF); REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1); -- GitLab From 989cd3e76a4aab76fe7dd50090ac3fa501c537f6 Mon Sep 17 00:00:00 2001 From: Aurabindo Pillai Date: Thu, 6 Apr 2023 15:59:45 -0400 Subject: [PATCH 4183/5631] drm/amd/display: Update bounding box values for DCN321 [Why&how] Update bounding box values as per hardware spec Fixes: 197485c69543 ("drm/amd/display: Create dcn321_fpu file") Acked-by: Leo Li Signed-off-by: Aurabindo Pillai Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../amd/display/dc/dml/dcn321/dcn321_fpu.c | 24 +++++++++---------- 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index 57b9bd896678..342a1bcb4927 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -106,16 +106,16 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .clock_limits = { { .state = 0, - .dcfclk_mhz = 1564.0, - .fabricclk_mhz = 400.0, - .dispclk_mhz = 2150.0, - .dppclk_mhz = 2150.0, + .dcfclk_mhz = 1434.0, + .fabricclk_mhz = 2250.0, + .dispclk_mhz = 1720.0, + .dppclk_mhz = 1720.0, .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, - .phyclk_d32_mhz = 625.0, + .phyclk_d32_mhz = 313.0, .socclk_mhz = 1200.0, - .dscclk_mhz = 716.667, - .dram_speed_mts = 1600.0, + .dscclk_mhz = 573.333, + .dram_speed_mts = 16000.0, .dtbclk_mhz = 1564.0, }, }, @@ -125,14 +125,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .sr_exit_z8_time_us = 285.0, .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, - .round_trip_ping_latency_dcfclk_cycles = 263, + .round_trip_ping_latency_dcfclk_cycles = 207, .urgent_latency_pixel_data_only_us = 4, .urgent_latency_pixel_mixed_with_vm_data_us = 4, .urgent_latency_vm_data_only_us = 4, - .fclk_change_latency_us = 20, - .usr_retraining_latency_us = 2, - .smn_latency_us = 2, - .mall_allocated_for_dcn_mbytes = 64, + .fclk_change_latency_us = 7, + .usr_retraining_latency_us = 0, + .smn_latency_us = 0, + .mall_allocated_for_dcn_mbytes = 32, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, -- GitLab From 3caab67db1f69e077fb12ac194d3cd2a4de06d8d Mon Sep 17 00:00:00 2001 From: Jasdeep Dhillon Date: Tue, 28 Feb 2023 11:46:31 -0500 Subject: [PATCH 4184/5631] drm/amd/display: Isolate remaining FPU code in DCN32 [Why] DCN32 resource contains code that uses FPU. [How] Moved code into DCN32 FPU Reviewed-by: Rodrigo Siqueira Signed-off-by: Jasdeep Dhillon Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 6 ++++++ drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h | 2 ++ 2 files changed, 8 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 23a972f2885f..47beb4ea779d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -2876,3 +2876,9 @@ bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint } return vactive_found; } + +void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb) +{ + dc_assert_fp_enabled(); + dcn3_2_soc.clock_limits[0].dcfclk_mhz = 1200.0; +} diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h index 9a0806a0e2ef..dcf512cd3072 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h @@ -80,4 +80,6 @@ void dcn32_assign_fpo_vactive_candidate(struct dc *dc, const struct dc_state *co bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint32_t vactive_margin_req); +void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb); + #endif -- GitLab From 9675b3ba99ec79273d94afa09e9b69e2b8c0d238 Mon Sep 17 00:00:00 2001 From: Igor Kravchenko Date: Fri, 10 Jul 2020 16:24:30 -0400 Subject: [PATCH 4185/5631] drm/amd/display: Set min_width and min_height capability for DCN30 Add min_width, min_height fields to dc_plane_cap structure. Set values to 16x16 for discrete ASICs, and 64x64 for others. Reviewed-by: Rodrigo Siqueira Signed-off-by: Igor Kravchenko Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 965f5ceb33f7..67a34cda3774 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -701,7 +701,9 @@ static const struct dc_plane_cap plane_cap = { .argb8888 = 167, .nv12 = 167, .fp16 = 167 - } + }, + 16, + 16 }; static const struct dc_debug_options debug_defaults_drv = { -- GitLab From 08da182175db4c7f80850354849d95f2670e8cd9 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Fri, 14 Apr 2023 14:26:27 -0400 Subject: [PATCH 4186/5631] drm/amd/display: fix flickering caused by S/G mode Currently, on a handful of ASICs. We allow the framebuffer for a given plane to exist in either VRAM or GTT. However, if the plane's new framebuffer is in a different memory domain than it's previous framebuffer, flipping between them can cause the screen to flicker. So, to fix this, don't perform an immediate flip in the aforementioned case. Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2354 Reviewed-by: Roman Li Fixes: 81d0bcf99009 ("drm/amdgpu: make display pinning more flexible (v2)") Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b619d7cdb525..8d17fd5a817e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7901,6 +7901,13 @@ static void amdgpu_dm_commit_cursors(struct drm_atomic_state *state) amdgpu_dm_plane_handle_cursor_update(plane, old_plane_state); } +static inline uint32_t get_mem_type(struct drm_framebuffer *fb) +{ + struct amdgpu_bo *abo = gem_to_amdgpu_bo(fb->obj[0]); + + return abo->tbo.resource ? abo->tbo.resource->mem_type : 0; +} + static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct dc_state *dc_state, struct drm_device *dev, @@ -8043,11 +8050,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, /* * Only allow immediate flips for fast updates that don't - * change FB pitch, DCC state, rotation or mirroing. + * change memory domain, FB pitch, DCC state, rotation or + * mirroring. */ bundle->flip_addrs[planes_count].flip_immediate = crtc->state->async_flip && - acrtc_state->update_type == UPDATE_TYPE_FAST; + acrtc_state->update_type == UPDATE_TYPE_FAST && + get_mem_type(old_plane_state->fb) == get_mem_type(fb); timestamp_ns = ktime_get_ns(); bundle->flip_addrs[planes_count].flip_timestamp_in_us = div_u64(timestamp_ns, 1000); -- GitLab From d893f39320e1248d1c97fde0d6e51e5ea008a76b Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Tue, 11 Apr 2023 10:49:38 -0400 Subject: [PATCH 4187/5631] drm/amd/display: Lowering min Z8 residency time [Why & How] Per HW team request, we're lowering the minimum Z8 residency time to 2000us. This enables Z8 support for additional modes we were previously blocking like 2k>60hz Cc: stable@vger.kernel.org Tested-by: Daniel Wheeler Reviewed-by: Nicholas Kazlauskas Acked-by: Rodrigo Siqueira Signed-off-by: Leo Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index 50ed7e09d5ba..2f7df8d34a91 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -885,7 +885,7 @@ static const struct dc_plane_cap plane_cap = { static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .enable_z9_disable_interface = true, - .minimum_z8_residency_time = 3080, + .minimum_z8_residency_time = 2000, .psr_skip_crtc_disable = true, .disable_dmcu = true, .force_abm_enable = false, -- GitLab From 2b5fdc0f5caa505afe34d608e2eefadadf2ee67a Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 25 Apr 2023 13:56:35 +0100 Subject: [PATCH 4188/5631] rxrpc: Fix potential data race in rxrpc_wait_to_be_connected() Inside the loop in rxrpc_wait_to_be_connected() it checks call->error to see if it should exit the loop without first checking the call state. This is probably safe as if call->error is set, the call is dead anyway, but we should probably wait for the call state to have been set to completion first, lest it cause surprise on the way out. Fix this by only accessing call->error if the call is complete. We don't actually need to access the error inside the loop as we'll do that after. This caused the following report: BUG: KCSAN: data-race in rxrpc_send_data / rxrpc_set_call_completion write to 0xffff888159cf3c50 of 4 bytes by task 25673 on cpu 1: rxrpc_set_call_completion+0x71/0x1c0 net/rxrpc/call_state.c:22 rxrpc_send_data_packet+0xba9/0x1650 net/rxrpc/output.c:479 rxrpc_transmit_one+0x1e/0x130 net/rxrpc/output.c:714 rxrpc_decant_prepared_tx net/rxrpc/call_event.c:326 [inline] rxrpc_transmit_some_data+0x496/0x600 net/rxrpc/call_event.c:350 rxrpc_input_call_event+0x564/0x1220 net/rxrpc/call_event.c:464 rxrpc_io_thread+0x307/0x1d80 net/rxrpc/io_thread.c:461 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 read to 0xffff888159cf3c50 of 4 bytes by task 25672 on cpu 0: rxrpc_send_data+0x29e/0x1950 net/rxrpc/sendmsg.c:296 rxrpc_do_sendmsg+0xb7a/0xc20 net/rxrpc/sendmsg.c:726 rxrpc_sendmsg+0x413/0x520 net/rxrpc/af_rxrpc.c:565 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2501 ___sys_sendmsg net/socket.c:2555 [inline] __sys_sendmmsg+0x263/0x500 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0x57/0x60 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00000000 -> 0xffffffea Fixes: 9d35d880e0e4 ("rxrpc: Move client call connection to the I/O thread") Reported-by: syzbot+ebc945fdb4acd72cba78@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/000000000000e7c6d205fa10a3cd@google.com/ Signed-off-by: David Howells cc: Marc Dionne cc: Dmitry Vyukov cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: linux-fsdevel@vger.kernel.org cc: netdev@vger.kernel.org Link: https://lore.kernel.org/r/508133.1682427395@warthog.procyon.org.uk Signed-off-by: Paolo Abeni --- net/rxrpc/sendmsg.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index da49fcf1c456..6caa47d352ed 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -50,15 +50,11 @@ static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) _enter("%d", call->debug_id); if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) - return call->error; + goto no_wait; add_wait_queue_exclusive(&call->waitq, &myself); for (;;) { - ret = call->error; - if (ret < 0) - break; - switch (call->interruptibility) { case RXRPC_INTERRUPTIBLE: case RXRPC_PREINTERRUPTIBLE: @@ -69,10 +65,9 @@ static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) set_current_state(TASK_UNINTERRUPTIBLE); break; } - if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) { - ret = call->error; + + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) break; - } if ((call->interruptibility == RXRPC_INTERRUPTIBLE || call->interruptibility == RXRPC_PREINTERRUPTIBLE) && signal_pending(current)) { @@ -85,6 +80,7 @@ static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); +no_wait: if (ret == 0 && rxrpc_call_is_complete(call)) ret = call->error; -- GitLab From 32eff6bacec2cb574677c15378169a9fa30043ef Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Tue, 25 Apr 2023 16:06:04 +0200 Subject: [PATCH 4189/5631] net/sched: flower: Fix wrong handle assignment during filter change Commit 08a0063df3ae ("net/sched: flower: Move filter handle initialization earlier") moved filter handle initialization but an assignment of the handle to fnew->handle is done regardless of fold value. This is wrong because if fold != NULL (so fold->handle == handle) no new handle is allocated and passed handle is assigned to fnew->handle. Then if any subsequent action in fl_change() fails then the handle value is removed from IDR that is incorrect as we will have still valid old filter instance with handle that is not present in IDR. Fix this issue by moving the assignment so it is done only when passed fold == NULL. Prior the patch: [root@machine tc-testing]# ./tdc.py -d enp1s0f0np0 -e 14be Test 14be: Concurrently replace same range of 100k flower filters from 10 tc instances exit: 123 exit: 0 RTNETLINK answers: Invalid argument We have an error talking to the kernel Command failed tmp/replace_6:1885 All test results: 1..1 not ok 1 14be - Concurrently replace same range of 100k flower filters from 10 tc instances Command exited with 123, expected 0 RTNETLINK answers: Invalid argument We have an error talking to the kernel Command failed tmp/replace_6:1885 After the patch: [root@machine tc-testing]# ./tdc.py -d enp1s0f0np0 -e 14be Test 14be: Concurrently replace same range of 100k flower filters from 10 tc instances All test results: 1..1 ok 1 14be - Concurrently replace same range of 100k flower filters from 10 tc instances Fixes: 08a0063df3ae ("net/sched: flower: Move filter handle initialization earlier") Signed-off-by: Ivan Vecera Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230425140604.169881-1-ivecera@redhat.com Signed-off-by: Paolo Abeni --- net/sched/cls_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index cc49256d5318..6ab6aadc07b8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2231,8 +2231,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(fnew); goto errout_tb; } + fnew->handle = handle; } - fnew->handle = handle; err = tcf_exts_init_ex(&fnew->exts, net, TCA_FLOWER_ACT, 0, tp, handle, !tc_skip_hw(fnew->flags)); -- GitLab From 1b483d9f5805c7e3d628d4995e97f4311fcb82eb Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 25 Apr 2023 11:47:25 -0300 Subject: [PATCH 4190/5631] net/sched: act_pedit: free pedit keys on bail from offset check Ido Schimmel reports a memleak on a syzkaller instance: BUG: memory leak unreferenced object 0xffff88803d45e400 (size 1024): comm "syz-executor292", pid 563, jiffies 4295025223 (age 51.781s) hex dump (first 32 bytes): 28 bd 70 00 fb db df 25 02 00 14 1f ff 02 00 02 (.p....%........ 00 32 00 00 1f 00 00 00 ac 14 14 3e 08 00 07 00 .2.........>.... backtrace: [] kmemleak_alloc_recursive include/linux/kmemleak.h:42 [inline] [] slab_post_alloc_hook mm/slab.h:772 [inline] [] slab_alloc_node mm/slub.c:3452 [inline] [] __kmem_cache_alloc_node+0x25c/0x320 mm/slub.c:3491 [] __do_kmalloc_node mm/slab_common.c:966 [inline] [] __kmalloc+0x59/0x1a0 mm/slab_common.c:980 [] kmalloc include/linux/slab.h:584 [inline] [] tcf_pedit_init+0x793/0x1ae0 net/sched/act_pedit.c:245 [] tcf_action_init_1+0x453/0x6e0 net/sched/act_api.c:1394 [] tcf_action_init+0x5a8/0x950 net/sched/act_api.c:1459 [] tcf_action_add+0x118/0x4e0 net/sched/act_api.c:1985 [] tc_ctl_action+0x377/0x490 net/sched/act_api.c:2044 [] rtnetlink_rcv_msg+0x46d/0xd70 net/core/rtnetlink.c:6395 [] netlink_rcv_skb+0x185/0x490 net/netlink/af_netlink.c:2575 [] rtnetlink_rcv+0x26/0x30 net/core/rtnetlink.c:6413 [] netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] [] netlink_unicast+0x5be/0x8a0 net/netlink/af_netlink.c:1365 [] netlink_sendmsg+0x9af/0xed0 net/netlink/af_netlink.c:1942 [] sock_sendmsg_nosec net/socket.c:724 [inline] [] sock_sendmsg net/socket.c:747 [inline] [] ____sys_sendmsg+0x3ef/0xaa0 net/socket.c:2503 [] ___sys_sendmsg+0x122/0x1c0 net/socket.c:2557 [] __sys_sendmsg+0x11f/0x200 net/socket.c:2586 [] __do_sys_sendmsg net/socket.c:2595 [inline] [] __se_sys_sendmsg net/socket.c:2593 [inline] [] __x64_sys_sendmsg+0x80/0xc0 net/socket.c:2593 The recently added static offset check missed a free to the key buffer when bailing out on error. Fixes: e1201bc781c2 ("net/sched: act_pedit: check static offsets a priori") Reported-by: Ido Schimmel Signed-off-by: Pedro Tammela Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Link: https://lore.kernel.org/r/20230425144725.669262-1-pctammela@mojatatu.com Signed-off-by: Paolo Abeni --- net/sched/act_pedit.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index fb93d4c1faca..fc945c7e4123 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -258,7 +258,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!offmask && cur % 4) { NL_SET_ERR_MSG_MOD(extack, "Offsets must be on 32bit boundaries"); ret = -EINVAL; - goto put_chain; + goto out_free_keys; } /* sanitize the shift value for any later use */ @@ -291,6 +291,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, return ret; +out_free_keys: + kfree(nparms->tcfp_keys); put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); -- GitLab From c23ae5091a8b3e50fe755257df020907e7c029bb Mon Sep 17 00:00:00 2001 From: John Hickey Date: Tue, 25 Apr 2023 10:03:08 -0700 Subject: [PATCH 4191/5631] ixgbe: Fix panic during XDP_TX with > 64 CPUs Commit 4fe815850bdc ("ixgbe: let the xdpdrv work with more than 64 cpus") adds support to allow XDP programs to run on systems with more than 64 CPUs by locking the XDP TX rings and indexing them using cpu % 64 (IXGBE_MAX_XDP_QS). Upon trying this out patch on a system with more than 64 cores, the kernel paniced with an array-index-out-of-bounds at the return in ixgbe_determine_xdp_ring in ixgbe.h, which means ixgbe_determine_xdp_q_idx was just returning the cpu instead of cpu % IXGBE_MAX_XDP_QS. An example splat: ========================================================================== UBSAN: array-index-out-of-bounds in /var/lib/dkms/ixgbe/5.18.6+focal-1/build/src/ixgbe.h:1147:26 index 65 is out of range for type 'ixgbe_ring *[64]' ========================================================================== BUG: kernel NULL pointer dereference, address: 0000000000000058 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP NOPTI CPU: 65 PID: 408 Comm: ksoftirqd/65 Tainted: G IOE 5.15.0-48-generic #54~20.04.1-Ubuntu Hardware name: Dell Inc. PowerEdge R640/0W23H8, BIOS 2.5.4 01/13/2020 RIP: 0010:ixgbe_xmit_xdp_ring+0x1b/0x1c0 [ixgbe] Code: 3b 52 d4 cf e9 42 f2 ff ff 66 0f 1f 44 00 00 0f 1f 44 00 00 55 b9 00 00 00 00 48 89 e5 41 57 41 56 41 55 41 54 53 48 83 ec 08 <44> 0f b7 47 58 0f b7 47 5a 0f b7 57 54 44 0f b7 76 08 66 41 39 c0 RSP: 0018:ffffbc3fcd88fcb0 EFLAGS: 00010282 RAX: ffff92a253260980 RBX: ffffbc3fe68b00a0 RCX: 0000000000000000 RDX: ffff928b5f659000 RSI: ffff928b5f659000 RDI: 0000000000000000 RBP: ffffbc3fcd88fce0 R08: ffff92b9dfc20580 R09: 0000000000000001 R10: 3d3d3d3d3d3d3d3d R11: 3d3d3d3d3d3d3d3d R12: 0000000000000000 R13: ffff928b2f0fa8c0 R14: ffff928b9be20050 R15: 000000000000003c FS: 0000000000000000(0000) GS:ffff92b9dfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000058 CR3: 000000011dd6a002 CR4: 00000000007706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: ixgbe_poll+0x103e/0x1280 [ixgbe] ? sched_clock_cpu+0x12/0xe0 __napi_poll+0x30/0x160 net_rx_action+0x11c/0x270 __do_softirq+0xda/0x2ee run_ksoftirqd+0x2f/0x50 smpboot_thread_fn+0xb7/0x150 ? sort_range+0x30/0x30 kthread+0x127/0x150 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x1f/0x30 I think this is how it happens: Upon loading the first XDP program on a system with more than 64 CPUs, ixgbe_xdp_locking_key is incremented in ixgbe_xdp_setup. However, immediately after this, the rings are reconfigured by ixgbe_setup_tc. ixgbe_setup_tc calls ixgbe_clear_interrupt_scheme which calls ixgbe_free_q_vectors which calls ixgbe_free_q_vector in a loop. ixgbe_free_q_vector decrements ixgbe_xdp_locking_key once per call if it is non-zero. Commenting out the decrement in ixgbe_free_q_vector stopped my system from panicing. I suspect to make the original patch work, I would need to load an XDP program and then replace it in order to get ixgbe_xdp_locking_key back above 0 since ixgbe_setup_tc is only called when transitioning between XDP and non-XDP ring configurations, while ixgbe_xdp_locking_key is incremented every time ixgbe_xdp_setup is called. Also, ixgbe_setup_tc can be called via ethtool --set-channels, so this becomes another path to decrement ixgbe_xdp_locking_key to 0 on systems with more than 64 CPUs. Since ixgbe_xdp_locking_key only protects the XDP_TX path and is tied to the number of CPUs present, there is no reason to disable it upon unloading an XDP program. To avoid confusion, I have moved enabling ixgbe_xdp_locking_key into ixgbe_sw_init, which is part of the probe path. Fixes: 4fe815850bdc ("ixgbe: let the xdpdrv work with more than 64 cpus") Signed-off-by: John Hickey Reviewed-by: Maciej Fijalkowski Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Link: https://lore.kernel.org/r/20230425170308.2522429-1-anthony.l.nguyen@intel.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c | 3 --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index f8156fe4b1dc..0ee943db3dc9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1035,9 +1035,6 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) adapter->q_vector[v_idx] = NULL; __netif_napi_del(&q_vector->napi); - if (static_key_enabled(&ixgbe_xdp_locking_key)) - static_branch_dec(&ixgbe_xdp_locking_key); - /* * after a call to __netif_napi_del() napi may still be used and * ixgbe_get_stats64() might access the rings on this vector, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index e961ef4bbf4d..5d83c887a3fc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6487,6 +6487,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, set_bit(0, adapter->fwd_bitmask); set_bit(__IXGBE_DOWN, &adapter->state); + /* enable locking for XDP_TX if we have more CPUs than queues */ + if (nr_cpu_ids > IXGBE_MAX_XDP_QS) + static_branch_enable(&ixgbe_xdp_locking_key); + return 0; } @@ -10270,8 +10274,6 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) */ if (nr_cpu_ids > IXGBE_MAX_XDP_QS * 2) return -ENOMEM; - else if (nr_cpu_ids > IXGBE_MAX_XDP_QS) - static_branch_inc(&ixgbe_xdp_locking_key); old_prog = xchg(&adapter->xdp_prog, prog); need_reset = (!!prog != !!old_prog); -- GitLab From c222b292a3568754828ffd30338d2909b14ed160 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Wed, 26 Apr 2023 11:55:20 +0530 Subject: [PATCH 4192/5631] octeonxt2-af: mcs: Fix per port bypass config For each lmac port, MCS has two MCS_TOP_SLAVE_CHANNEL_CONFIGX registers. For CN10KB both register need to be configured for the port level mcs bypass to work. This patch also sets bitmap of flowid/secy entry reserved for default bypass so that these entries can be shown in debugfs. Fixes: bd69476e86fc ("octeontx2-af: cn10k: mcs: Install a default TCAM for normal traffic") Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Goutham Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- drivers/net/ethernet/marvell/octeontx2/af/mcs.c | 11 ++++++++++- .../net/ethernet/marvell/octeontx2/af/rvu_debugfs.c | 5 +++-- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index f68a6a0e3aa4..492baa0b594c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -494,6 +494,9 @@ int mcs_install_flowid_bypass_entry(struct mcs *mcs) /* Flow entry */ flow_id = mcs->hw->tcam_entries - MCS_RSRC_RSVD_CNT; + __set_bit(flow_id, mcs->rx.flow_ids.bmap); + __set_bit(flow_id, mcs->tx.flow_ids.bmap); + for (reg_id = 0; reg_id < 4; reg_id++) { reg = MCSX_CPM_RX_SLAVE_FLOWID_TCAM_MASKX(reg_id, flow_id); mcs_reg_write(mcs, reg, GENMASK_ULL(63, 0)); @@ -504,6 +507,8 @@ int mcs_install_flowid_bypass_entry(struct mcs *mcs) } /* secy */ secy_id = mcs->hw->secy_entries - MCS_RSRC_RSVD_CNT; + __set_bit(secy_id, mcs->rx.secy.bmap); + __set_bit(secy_id, mcs->tx.secy.bmap); /* Set validate frames to NULL and enable control port */ plcy = 0x7ull; @@ -528,6 +533,7 @@ int mcs_install_flowid_bypass_entry(struct mcs *mcs) /* Enable Flowid entry */ mcs_ena_dis_flowid_entry(mcs, flow_id, MCS_RX, true); mcs_ena_dis_flowid_entry(mcs, flow_id, MCS_TX, true); + return 0; } @@ -1325,8 +1331,11 @@ void mcs_reset_port(struct mcs *mcs, u8 port_id, u8 reset) void mcs_set_lmac_mode(struct mcs *mcs, int lmac_id, u8 mode) { u64 reg; + int id = lmac_id * 2; - reg = MCSX_MCS_TOP_SLAVE_CHANNEL_CFG(lmac_id * 2); + reg = MCSX_MCS_TOP_SLAVE_CHANNEL_CFG(id); + mcs_reg_write(mcs, reg, (u64)mode); + reg = MCSX_MCS_TOP_SLAVE_CHANNEL_CFG((id + 1)); mcs_reg_write(mcs, reg, (u64)mode); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 26cfa501f1a1..9533b1d92960 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -497,8 +497,9 @@ static int rvu_dbg_mcs_rx_secy_stats_display(struct seq_file *filp, void *unused stats.octet_validated_cnt); seq_printf(filp, "secy%d: Pkts on disable port: %lld\n", secy_id, stats.pkt_port_disabled_cnt); - seq_printf(filp, "secy%d: Octets validated: %lld\n", secy_id, stats.pkt_badtag_cnt); - seq_printf(filp, "secy%d: Octets validated: %lld\n", secy_id, stats.pkt_nosa_cnt); + seq_printf(filp, "secy%d: Pkts with badtag: %lld\n", secy_id, stats.pkt_badtag_cnt); + seq_printf(filp, "secy%d: Pkts with no SA(sectag.tci.c=0): %lld\n", secy_id, + stats.pkt_nosa_cnt); seq_printf(filp, "secy%d: Pkts with nosaerror: %lld\n", secy_id, stats.pkt_nosaerror_cnt); seq_printf(filp, "secy%d: Tagged ctrl pkts: %lld\n", secy_id, -- GitLab From b51612198603fce33d6cf57b4864e3018a1cd9b8 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:21 +0530 Subject: [PATCH 4193/5631] octeontx2-af: mcs: Write TCAM_DATA and TCAM_MASK registers at once As per hardware errata on CN10KB, all the four TCAM_DATA and TCAM_MASK registers has to be written at once otherwise write to individual registers will fail. Hence write to all TCAM_DATA registers and then to all TCAM_MASK registers. Fixes: cfc14181d497 ("octeontx2-af: cn10k: mcs: Manage the MCS block hardware resources") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- drivers/net/ethernet/marvell/octeontx2/af/mcs.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index 492baa0b594c..148417d633a5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -473,6 +473,8 @@ void mcs_flowid_entry_write(struct mcs *mcs, u64 *data, u64 *mask, int flow_id, for (reg_id = 0; reg_id < 4; reg_id++) { reg = MCSX_CPM_RX_SLAVE_FLOWID_TCAM_DATAX(reg_id, flow_id); mcs_reg_write(mcs, reg, data[reg_id]); + } + for (reg_id = 0; reg_id < 4; reg_id++) { reg = MCSX_CPM_RX_SLAVE_FLOWID_TCAM_MASKX(reg_id, flow_id); mcs_reg_write(mcs, reg, mask[reg_id]); } @@ -480,6 +482,8 @@ void mcs_flowid_entry_write(struct mcs *mcs, u64 *data, u64 *mask, int flow_id, for (reg_id = 0; reg_id < 4; reg_id++) { reg = MCSX_CPM_TX_SLAVE_FLOWID_TCAM_DATAX(reg_id, flow_id); mcs_reg_write(mcs, reg, data[reg_id]); + } + for (reg_id = 0; reg_id < 4; reg_id++) { reg = MCSX_CPM_TX_SLAVE_FLOWID_TCAM_MASKX(reg_id, flow_id); mcs_reg_write(mcs, reg, mask[reg_id]); } -- GitLab From 65cdc2b637a5749c7dec0ce14fe2c48f1f91f671 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Wed, 26 Apr 2023 11:55:22 +0530 Subject: [PATCH 4194/5631] octeontx2-af: mcs: Config parser to skip 8B header When ptp timestamp is enabled in RPM, RPM will append 8B timestamp header for all RX traffic. MCS need to skip these 8 bytes header while parsing the packet header, so that correct tcam key is created for lookup. This patch fixes the mcs parser configuration to skip this 8B header for ptp packets. Fixes: ca7f49ff8846 ("octeontx2-af: cn10k: Introduce driver for macsec block.") Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../ethernet/marvell/octeontx2/af/mcs_reg.h | 1 + .../marvell/octeontx2/af/mcs_rvu_if.c | 37 +++++++++++++++++++ .../net/ethernet/marvell/octeontx2/af/rvu.h | 1 + .../ethernet/marvell/octeontx2/af/rvu_cgx.c | 2 + 4 files changed, 41 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h index c95a8b8f5eaf..7427e3b1490f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h @@ -97,6 +97,7 @@ #define MCSX_PEX_TX_SLAVE_VLAN_CFGX(a) (0x46f8ull + (a) * 0x8ull) #define MCSX_PEX_TX_SLAVE_CUSTOM_TAG_REL_MODE_SEL(a) (0x788ull + (a) * 0x8ull) #define MCSX_PEX_TX_SLAVE_PORT_CONFIG(a) (0x4738ull + (a) * 0x8ull) +#define MCSX_PEX_RX_SLAVE_PORT_CFGX(a) (0x3b98ull + (a) * 0x8ull) #define MCSX_PEX_RX_SLAVE_RULE_ETYPE_CFGX(a) ({ \ u64 offset; \ \ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c index eb25e458266c..dfd23580e3b8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c @@ -11,6 +11,7 @@ #include "mcs.h" #include "rvu.h" +#include "mcs_reg.h" #include "lmac_common.h" #define M(_name, _id, _fn_name, _req_type, _rsp_type) \ @@ -32,6 +33,42 @@ static struct _req_type __maybe_unused \ MBOX_UP_MCS_MESSAGES #undef M +void rvu_mcs_ptp_cfg(struct rvu *rvu, u8 rpm_id, u8 lmac_id, bool ena) +{ + struct mcs *mcs; + u64 cfg; + u8 port; + + if (!rvu->mcs_blk_cnt) + return; + + /* When ptp is enabled, RPM appends 8B header for all + * RX packets. MCS PEX need to configure to skip 8B + * during packet parsing. + */ + + /* CNF10K-B */ + if (rvu->mcs_blk_cnt > 1) { + mcs = mcs_get_pdata(rpm_id); + cfg = mcs_reg_read(mcs, MCSX_PEX_RX_SLAVE_PEX_CONFIGURATION); + if (ena) + cfg |= BIT_ULL(lmac_id); + else + cfg &= ~BIT_ULL(lmac_id); + mcs_reg_write(mcs, MCSX_PEX_RX_SLAVE_PEX_CONFIGURATION, cfg); + return; + } + /* CN10KB */ + mcs = mcs_get_pdata(0); + port = (rpm_id * rvu->hw->lmac_per_cgx) + lmac_id; + cfg = mcs_reg_read(mcs, MCSX_PEX_RX_SLAVE_PORT_CFGX(port)); + if (ena) + cfg |= BIT_ULL(0); + else + cfg &= ~BIT_ULL(0); + mcs_reg_write(mcs, MCSX_PEX_RX_SLAVE_PORT_CFGX(port), cfg); +} + int rvu_mbox_handler_mcs_set_lmac_mode(struct rvu *rvu, struct mcs_set_lmac_mode *req, struct msg_rsp *rsp) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index ef721caeac49..d655bf04a483 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -920,6 +920,7 @@ int rvu_get_hwvf(struct rvu *rvu, int pcifunc); /* CN10K MCS */ int rvu_mcs_init(struct rvu *rvu); int rvu_mcs_flr_handler(struct rvu *rvu, u16 pcifunc); +void rvu_mcs_ptp_cfg(struct rvu *rvu, u8 rpm_id, u8 lmac_id, bool ena); void rvu_mcs_exit(struct rvu *rvu); #endif /* RVU_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 438b212fb54a..83b342fa8d75 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -773,6 +773,8 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) /* This flag is required to clean up CGX conf if app gets killed */ pfvf->hw_rx_tstamp_en = enable; + /* Inform MCS about 8B RX header */ + rvu_mcs_ptp_cfg(rvu, cgx_id, lmac_id, enable); return 0; } -- GitLab From b8aebeaaf9ffb1e99c642eb3751e28981f9be475 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Wed, 26 Apr 2023 11:55:23 +0530 Subject: [PATCH 4195/5631] octeontx2-af: mcs: Fix MCS block interrupt On CN10KB, MCS IP vector number, BBE and PAB interrupt mask got changed to support more block level interrupts. To address this changes, this patch fixes the bbe and pab interrupt handlers. Fixes: 6c635f78c474 ("octeontx2-af: cn10k: mcs: Handle MCS block interrupts") Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../net/ethernet/marvell/octeontx2/af/mcs.c | 95 ++++++++----------- .../net/ethernet/marvell/octeontx2/af/mcs.h | 26 +++-- .../marvell/octeontx2/af/mcs_cnf10kb.c | 63 ++++++++++++ .../ethernet/marvell/octeontx2/af/mcs_reg.h | 5 +- 4 files changed, 119 insertions(+), 70 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index 148417d633a5..c43f19dfbd74 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -936,60 +936,42 @@ static void mcs_tx_misc_intr_handler(struct mcs *mcs, u64 intr) mcs_add_intr_wq_entry(mcs, &event); } -static void mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir) +void cn10kb_mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, + enum mcs_direction dir) { - struct mcs_intr_event event = { 0 }; - int i; + u64 val, reg; + int lmac; - if (!(intr & MCS_BBE_INT_MASK)) + if (!(intr & 0x6ULL)) return; - event.mcs_id = mcs->mcs_id; - event.pcifunc = mcs->pf_map[0]; + if (intr & BIT_ULL(1)) + reg = (dir == MCS_RX) ? MCSX_BBE_RX_SLAVE_DFIFO_OVERFLOW_0 : + MCSX_BBE_TX_SLAVE_DFIFO_OVERFLOW_0; + else + reg = (dir == MCS_RX) ? MCSX_BBE_RX_SLAVE_PLFIFO_OVERFLOW_0 : + MCSX_BBE_TX_SLAVE_PLFIFO_OVERFLOW_0; + val = mcs_reg_read(mcs, reg); - for (i = 0; i < MCS_MAX_BBE_INT; i++) { - if (!(intr & BIT_ULL(i))) + /* policy/data over flow occurred */ + for (lmac = 0; lmac < mcs->hw->lmac_cnt; lmac++) { + if (!(val & BIT_ULL(lmac))) continue; - - /* Lower nibble denotes data fifo overflow interrupts and - * upper nibble indicates policy fifo overflow interrupts. - */ - if (intr & 0xFULL) - event.intr_mask = (dir == MCS_RX) ? - MCS_BBE_RX_DFIFO_OVERFLOW_INT : - MCS_BBE_TX_DFIFO_OVERFLOW_INT; - else - event.intr_mask = (dir == MCS_RX) ? - MCS_BBE_RX_PLFIFO_OVERFLOW_INT : - MCS_BBE_TX_PLFIFO_OVERFLOW_INT; - - /* Notify the lmac_id info which ran into BBE fatal error */ - event.lmac_id = i & 0x3ULL; - mcs_add_intr_wq_entry(mcs, &event); + dev_warn(mcs->dev, "BEE:Policy or data overflow occurred on lmac:%d\n", lmac); } } -static void mcs_pab_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir) +void cn10kb_mcs_pab_intr_handler(struct mcs *mcs, u64 intr, + enum mcs_direction dir) { - struct mcs_intr_event event = { 0 }; - int i; + int lmac; - if (!(intr & MCS_PAB_INT_MASK)) + if (!(intr & 0xFFFFFULL)) return; - event.mcs_id = mcs->mcs_id; - event.pcifunc = mcs->pf_map[0]; - - for (i = 0; i < MCS_MAX_PAB_INT; i++) { - if (!(intr & BIT_ULL(i))) - continue; - - event.intr_mask = (dir == MCS_RX) ? MCS_PAB_RX_CHAN_OVERFLOW_INT : - MCS_PAB_TX_CHAN_OVERFLOW_INT; - - /* Notify the lmac_id info which ran into PAB fatal error */ - event.lmac_id = i; - mcs_add_intr_wq_entry(mcs, &event); + for (lmac = 0; lmac < mcs->hw->lmac_cnt; lmac++) { + if (intr & BIT_ULL(lmac)) + dev_warn(mcs->dev, "PAB: overflow occurred on lmac:%d\n", lmac); } } @@ -998,9 +980,8 @@ static irqreturn_t mcs_ip_intr_handler(int irq, void *mcs_irq) struct mcs *mcs = (struct mcs *)mcs_irq; u64 intr, cpm_intr, bbe_intr, pab_intr; - /* Disable and clear the interrupt */ + /* Disable the interrupt */ mcs_reg_write(mcs, MCSX_IP_INT_ENA_W1C, BIT_ULL(0)); - mcs_reg_write(mcs, MCSX_IP_INT, BIT_ULL(0)); /* Check which block has interrupt*/ intr = mcs_reg_read(mcs, MCSX_TOP_SLAVE_INT_SUM); @@ -1047,7 +1028,7 @@ static irqreturn_t mcs_ip_intr_handler(int irq, void *mcs_irq) /* BBE RX */ if (intr & MCS_BBE_RX_INT_ENA) { bbe_intr = mcs_reg_read(mcs, MCSX_BBE_RX_SLAVE_BBE_INT); - mcs_bbe_intr_handler(mcs, bbe_intr, MCS_RX); + mcs->mcs_ops->mcs_bbe_intr_handler(mcs, bbe_intr, MCS_RX); /* Clear the interrupt */ mcs_reg_write(mcs, MCSX_BBE_RX_SLAVE_BBE_INT_INTR_RW, 0); @@ -1057,7 +1038,7 @@ static irqreturn_t mcs_ip_intr_handler(int irq, void *mcs_irq) /* BBE TX */ if (intr & MCS_BBE_TX_INT_ENA) { bbe_intr = mcs_reg_read(mcs, MCSX_BBE_TX_SLAVE_BBE_INT); - mcs_bbe_intr_handler(mcs, bbe_intr, MCS_TX); + mcs->mcs_ops->mcs_bbe_intr_handler(mcs, bbe_intr, MCS_TX); /* Clear the interrupt */ mcs_reg_write(mcs, MCSX_BBE_TX_SLAVE_BBE_INT_INTR_RW, 0); @@ -1067,7 +1048,7 @@ static irqreturn_t mcs_ip_intr_handler(int irq, void *mcs_irq) /* PAB RX */ if (intr & MCS_PAB_RX_INT_ENA) { pab_intr = mcs_reg_read(mcs, MCSX_PAB_RX_SLAVE_PAB_INT); - mcs_pab_intr_handler(mcs, pab_intr, MCS_RX); + mcs->mcs_ops->mcs_pab_intr_handler(mcs, pab_intr, MCS_RX); /* Clear the interrupt */ mcs_reg_write(mcs, MCSX_PAB_RX_SLAVE_PAB_INT_INTR_RW, 0); @@ -1077,14 +1058,15 @@ static irqreturn_t mcs_ip_intr_handler(int irq, void *mcs_irq) /* PAB TX */ if (intr & MCS_PAB_TX_INT_ENA) { pab_intr = mcs_reg_read(mcs, MCSX_PAB_TX_SLAVE_PAB_INT); - mcs_pab_intr_handler(mcs, pab_intr, MCS_TX); + mcs->mcs_ops->mcs_pab_intr_handler(mcs, pab_intr, MCS_TX); /* Clear the interrupt */ mcs_reg_write(mcs, MCSX_PAB_TX_SLAVE_PAB_INT_INTR_RW, 0); mcs_reg_write(mcs, MCSX_PAB_TX_SLAVE_PAB_INT, pab_intr); } - /* Enable the interrupt */ + /* Clear and enable the interrupt */ + mcs_reg_write(mcs, MCSX_IP_INT, BIT_ULL(0)); mcs_reg_write(mcs, MCSX_IP_INT_ENA_W1S, BIT_ULL(0)); return IRQ_HANDLED; @@ -1166,7 +1148,7 @@ static int mcs_register_interrupts(struct mcs *mcs) return ret; } - ret = request_irq(pci_irq_vector(mcs->pdev, MCS_INT_VEC_IP), + ret = request_irq(pci_irq_vector(mcs->pdev, mcs->hw->ip_vec), mcs_ip_intr_handler, 0, "MCS_IP", mcs); if (ret) { dev_err(mcs->dev, "MCS IP irq registration failed\n"); @@ -1185,11 +1167,11 @@ static int mcs_register_interrupts(struct mcs *mcs) mcs_reg_write(mcs, MCSX_CPM_TX_SLAVE_TX_INT_ENB, 0x7ULL); mcs_reg_write(mcs, MCSX_CPM_RX_SLAVE_RX_INT_ENB, 0x7FULL); - mcs_reg_write(mcs, MCSX_BBE_RX_SLAVE_BBE_INT_ENB, 0xff); - mcs_reg_write(mcs, MCSX_BBE_TX_SLAVE_BBE_INT_ENB, 0xff); + mcs_reg_write(mcs, MCSX_BBE_RX_SLAVE_BBE_INT_ENB, 0xFFULL); + mcs_reg_write(mcs, MCSX_BBE_TX_SLAVE_BBE_INT_ENB, 0xFFULL); - mcs_reg_write(mcs, MCSX_PAB_RX_SLAVE_PAB_INT_ENB, 0xff); - mcs_reg_write(mcs, MCSX_PAB_TX_SLAVE_PAB_INT_ENB, 0xff); + mcs_reg_write(mcs, MCSX_PAB_RX_SLAVE_PAB_INT_ENB, 0xFFFFFULL); + mcs_reg_write(mcs, MCSX_PAB_TX_SLAVE_PAB_INT_ENB, 0xFFFFFULL); mcs->tx_sa_active = alloc_mem(mcs, mcs->hw->sc_entries); if (!mcs->tx_sa_active) { @@ -1200,7 +1182,7 @@ static int mcs_register_interrupts(struct mcs *mcs) return ret; free_irq: - free_irq(pci_irq_vector(mcs->pdev, MCS_INT_VEC_IP), mcs); + free_irq(pci_irq_vector(mcs->pdev, mcs->hw->ip_vec), mcs); exit: pci_free_irq_vectors(mcs->pdev); mcs->num_vec = 0; @@ -1497,6 +1479,7 @@ void cn10kb_mcs_set_hw_capabilities(struct mcs *mcs) hw->lmac_cnt = 20; /* lmacs/ports per mcs block */ hw->mcs_x2p_intf = 5; /* x2p clabration intf */ hw->mcs_blks = 1; /* MCS blocks */ + hw->ip_vec = MCS_CN10KB_INT_VEC_IP; /* IP vector */ } static struct mcs_ops cn10kb_mcs_ops = { @@ -1505,6 +1488,8 @@ static struct mcs_ops cn10kb_mcs_ops = { .mcs_tx_sa_mem_map_write = cn10kb_mcs_tx_sa_mem_map_write, .mcs_rx_sa_mem_map_write = cn10kb_mcs_rx_sa_mem_map_write, .mcs_flowid_secy_map = cn10kb_mcs_flowid_secy_map, + .mcs_bbe_intr_handler = cn10kb_mcs_bbe_intr_handler, + .mcs_pab_intr_handler = cn10kb_mcs_pab_intr_handler, }; static int mcs_probe(struct pci_dev *pdev, const struct pci_device_id *id) @@ -1605,7 +1590,7 @@ static void mcs_remove(struct pci_dev *pdev) /* Set MCS to external bypass */ mcs_set_external_bypass(mcs, true); - free_irq(pci_irq_vector(pdev, MCS_INT_VEC_IP), mcs); + free_irq(pci_irq_vector(pdev, mcs->hw->ip_vec), mcs); pci_free_irq_vectors(pdev); pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h index 64dc2b80e15d..0f89dcb76465 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h @@ -43,24 +43,15 @@ /* Reserved resources for default bypass entry */ #define MCS_RSRC_RSVD_CNT 1 -/* MCS Interrupt Vector Enumeration */ -enum mcs_int_vec_e { - MCS_INT_VEC_MIL_RX_GBL = 0x0, - MCS_INT_VEC_MIL_RX_LMACX = 0x1, - MCS_INT_VEC_MIL_TX_LMACX = 0x5, - MCS_INT_VEC_HIL_RX_GBL = 0x9, - MCS_INT_VEC_HIL_RX_LMACX = 0xa, - MCS_INT_VEC_HIL_TX_GBL = 0xe, - MCS_INT_VEC_HIL_TX_LMACX = 0xf, - MCS_INT_VEC_IP = 0x13, - MCS_INT_VEC_CNT = 0x14, -}; +/* MCS Interrupt Vector */ +#define MCS_CNF10KB_INT_VEC_IP 0x13 +#define MCS_CN10KB_INT_VEC_IP 0x53 #define MCS_MAX_BBE_INT 8ULL #define MCS_BBE_INT_MASK 0xFFULL -#define MCS_MAX_PAB_INT 4ULL -#define MCS_PAB_INT_MASK 0xFULL +#define MCS_MAX_PAB_INT 8ULL +#define MCS_PAB_INT_MASK 0xFULL #define MCS_BBE_RX_INT_ENA BIT_ULL(0) #define MCS_BBE_TX_INT_ENA BIT_ULL(1) @@ -137,6 +128,7 @@ struct hwinfo { u8 lmac_cnt; u8 mcs_blks; unsigned long lmac_bmap; /* bitmap of enabled mcs lmac */ + u16 ip_vec; }; struct mcs { @@ -165,6 +157,8 @@ struct mcs_ops { void (*mcs_tx_sa_mem_map_write)(struct mcs *mcs, struct mcs_tx_sc_sa_map *map); void (*mcs_rx_sa_mem_map_write)(struct mcs *mcs, struct mcs_rx_sc_sa_map *map); void (*mcs_flowid_secy_map)(struct mcs *mcs, struct secy_mem_map *map, int dir); + void (*mcs_bbe_intr_handler)(struct mcs *mcs, u64 intr, enum mcs_direction dir); + void (*mcs_pab_intr_handler)(struct mcs *mcs, u64 intr, enum mcs_direction dir); }; extern struct pci_driver mcs_driver; @@ -219,6 +213,8 @@ void cn10kb_mcs_tx_sa_mem_map_write(struct mcs *mcs, struct mcs_tx_sc_sa_map *ma void cn10kb_mcs_flowid_secy_map(struct mcs *mcs, struct secy_mem_map *map, int dir); void cn10kb_mcs_rx_sa_mem_map_write(struct mcs *mcs, struct mcs_rx_sc_sa_map *map); void cn10kb_mcs_parser_cfg(struct mcs *mcs); +void cn10kb_mcs_pab_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir); +void cn10kb_mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir); /* CNF10K-B APIs */ struct mcs_ops *cnf10kb_get_mac_ops(void); @@ -229,6 +225,8 @@ void cnf10kb_mcs_rx_sa_mem_map_write(struct mcs *mcs, struct mcs_rx_sc_sa_map *m void cnf10kb_mcs_parser_cfg(struct mcs *mcs); void cnf10kb_mcs_tx_pn_thresh_reached_handler(struct mcs *mcs); void cnf10kb_mcs_tx_pn_wrapped_handler(struct mcs *mcs); +void cnf10kb_mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir); +void cnf10kb_mcs_pab_intr_handler(struct mcs *mcs, u64 intr, enum mcs_direction dir); /* Stats APIs */ void mcs_get_sc_stats(struct mcs *mcs, struct mcs_sc_stats *stats, int id, int dir); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_cnf10kb.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_cnf10kb.c index 7b6205414428..9f9b904ab2cd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_cnf10kb.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_cnf10kb.c @@ -13,6 +13,8 @@ static struct mcs_ops cnf10kb_mcs_ops = { .mcs_tx_sa_mem_map_write = cnf10kb_mcs_tx_sa_mem_map_write, .mcs_rx_sa_mem_map_write = cnf10kb_mcs_rx_sa_mem_map_write, .mcs_flowid_secy_map = cnf10kb_mcs_flowid_secy_map, + .mcs_bbe_intr_handler = cnf10kb_mcs_bbe_intr_handler, + .mcs_pab_intr_handler = cnf10kb_mcs_pab_intr_handler, }; struct mcs_ops *cnf10kb_get_mac_ops(void) @@ -31,6 +33,7 @@ void cnf10kb_mcs_set_hw_capabilities(struct mcs *mcs) hw->lmac_cnt = 4; /* lmacs/ports per mcs block */ hw->mcs_x2p_intf = 1; /* x2p clabration intf */ hw->mcs_blks = 7; /* MCS blocks */ + hw->ip_vec = MCS_CNF10KB_INT_VEC_IP; /* IP vector */ } void cnf10kb_mcs_parser_cfg(struct mcs *mcs) @@ -212,3 +215,63 @@ void cnf10kb_mcs_tx_pn_wrapped_handler(struct mcs *mcs) mcs_add_intr_wq_entry(mcs, &event); } } + +void cnf10kb_mcs_bbe_intr_handler(struct mcs *mcs, u64 intr, + enum mcs_direction dir) +{ + struct mcs_intr_event event = { 0 }; + int i; + + if (!(intr & MCS_BBE_INT_MASK)) + return; + + event.mcs_id = mcs->mcs_id; + event.pcifunc = mcs->pf_map[0]; + + for (i = 0; i < MCS_MAX_BBE_INT; i++) { + if (!(intr & BIT_ULL(i))) + continue; + + /* Lower nibble denotes data fifo overflow interrupts and + * upper nibble indicates policy fifo overflow interrupts. + */ + if (intr & 0xFULL) + event.intr_mask = (dir == MCS_RX) ? + MCS_BBE_RX_DFIFO_OVERFLOW_INT : + MCS_BBE_TX_DFIFO_OVERFLOW_INT; + else + event.intr_mask = (dir == MCS_RX) ? + MCS_BBE_RX_PLFIFO_OVERFLOW_INT : + MCS_BBE_TX_PLFIFO_OVERFLOW_INT; + + /* Notify the lmac_id info which ran into BBE fatal error */ + event.lmac_id = i & 0x3ULL; + mcs_add_intr_wq_entry(mcs, &event); + } +} + +void cnf10kb_mcs_pab_intr_handler(struct mcs *mcs, u64 intr, + enum mcs_direction dir) +{ + struct mcs_intr_event event = { 0 }; + int i; + + if (!(intr & MCS_PAB_INT_MASK)) + return; + + event.mcs_id = mcs->mcs_id; + event.pcifunc = mcs->pf_map[0]; + + for (i = 0; i < MCS_MAX_PAB_INT; i++) { + if (!(intr & BIT_ULL(i))) + continue; + + event.intr_mask = (dir == MCS_RX) ? + MCS_PAB_RX_CHAN_OVERFLOW_INT : + MCS_PAB_TX_CHAN_OVERFLOW_INT; + + /* Notify the lmac_id info which ran into PAB fatal error */ + event.lmac_id = i; + mcs_add_intr_wq_entry(mcs, &event); + } +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h index 7427e3b1490f..f3ab01fc363c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h @@ -276,7 +276,10 @@ #define MCSX_BBE_RX_SLAVE_CAL_ENTRY 0x180ull #define MCSX_BBE_RX_SLAVE_CAL_LEN 0x188ull #define MCSX_PAB_RX_SLAVE_FIFO_SKID_CFGX(a) (0x290ull + (a) * 0x40ull) - +#define MCSX_BBE_RX_SLAVE_DFIFO_OVERFLOW_0 0xe20 +#define MCSX_BBE_TX_SLAVE_DFIFO_OVERFLOW_0 0x1298 +#define MCSX_BBE_RX_SLAVE_PLFIFO_OVERFLOW_0 0xe40 +#define MCSX_BBE_TX_SLAVE_PLFIFO_OVERFLOW_0 0x12b8 #define MCSX_BBE_RX_SLAVE_BBE_INT ({ \ u64 offset; \ \ -- GitLab From 699af748c61574125d269db260dabbe20436d74e Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:24 +0530 Subject: [PATCH 4196/5631] octeontx2-pf: mcs: Fix NULL pointer dereferences When system is rebooted after creating macsec interface below NULL pointer dereference crashes occurred. This patch fixes those crashes by using correct order of teardown [ 3324.406942] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 3324.415726] Mem abort info: [ 3324.418510] ESR = 0x96000006 [ 3324.421557] EC = 0x25: DABT (current EL), IL = 32 bits [ 3324.426865] SET = 0, FnV = 0 [ 3324.429913] EA = 0, S1PTW = 0 [ 3324.433047] Data abort info: [ 3324.435921] ISV = 0, ISS = 0x00000006 [ 3324.439748] CM = 0, WnR = 0 .... [ 3324.575915] Call trace: [ 3324.578353] cn10k_mdo_del_secy+0x24/0x180 [ 3324.582440] macsec_common_dellink+0xec/0x120 [ 3324.586788] macsec_notify+0x17c/0x1c0 [ 3324.590529] raw_notifier_call_chain+0x50/0x70 [ 3324.594965] call_netdevice_notifiers_info+0x34/0x7c [ 3324.599921] rollback_registered_many+0x354/0x5bc [ 3324.604616] unregister_netdevice_queue+0x88/0x10c [ 3324.609399] unregister_netdev+0x20/0x30 [ 3324.613313] otx2_remove+0x8c/0x310 [ 3324.616794] pci_device_shutdown+0x30/0x70 [ 3324.620882] device_shutdown+0x11c/0x204 [ 966.664930] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 966.673712] Mem abort info: [ 966.676497] ESR = 0x96000006 [ 966.679543] EC = 0x25: DABT (current EL), IL = 32 bits [ 966.684848] SET = 0, FnV = 0 [ 966.687895] EA = 0, S1PTW = 0 [ 966.691028] Data abort info: [ 966.693900] ISV = 0, ISS = 0x00000006 [ 966.697729] CM = 0, WnR = 0 [ 966.833467] Call trace: [ 966.835904] cn10k_mdo_stop+0x20/0xa0 [ 966.839557] macsec_dev_stop+0xe8/0x11c [ 966.843384] __dev_close_many+0xbc/0x140 [ 966.847298] dev_close_many+0x84/0x120 [ 966.851039] rollback_registered_many+0x114/0x5bc [ 966.855735] unregister_netdevice_many.part.0+0x14/0xa0 [ 966.860952] unregister_netdevice_many+0x18/0x24 [ 966.865560] macsec_notify+0x1ac/0x1c0 [ 966.869303] raw_notifier_call_chain+0x50/0x70 [ 966.873738] call_netdevice_notifiers_info+0x34/0x7c [ 966.878694] rollback_registered_many+0x354/0x5bc [ 966.883390] unregister_netdevice_queue+0x88/0x10c [ 966.888173] unregister_netdev+0x20/0x30 [ 966.892090] otx2_remove+0x8c/0x310 [ 966.895571] pci_device_shutdown+0x30/0x70 [ 966.899660] device_shutdown+0x11c/0x204 [ 966.903574] __do_sys_reboot+0x208/0x290 [ 966.907487] __arm64_sys_reboot+0x20/0x30 [ 966.911489] el0_svc_handler+0x80/0x1c0 [ 966.915316] el0_svc+0x8/0x180 [ 966.918362] Code: f9400000 f9400a64 91220014 f94b3403 (f9400060) [ 966.924448] ---[ end trace 341778e799c3d8d7 ]--- Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 179433d0a54a..a75c944cc739 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -3073,8 +3073,6 @@ static void otx2_remove(struct pci_dev *pdev) otx2_config_pause_frm(pf); } - cn10k_mcs_free(pf); - #ifdef CONFIG_DCB /* Disable PFC config */ if (pf->pfc_en) { @@ -3088,6 +3086,7 @@ static void otx2_remove(struct pci_dev *pdev) otx2_unregister_dl(pf); unregister_netdev(netdev); + cn10k_mcs_free(pf); otx2_sriov_disable(pf->pdev); otx2_sriov_vfcfg_cleanup(pf); if (pf->otx2_wq) -- GitLab From 57d00d4364f314485092667d2a48718985515deb Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:25 +0530 Subject: [PATCH 4197/5631] octeontx2-pf: mcs: Match macsec ethertype along with DMAC On CN10KB silicon a single hardware macsec block is present and offloads macsec operations for all the ethernet LMACs. TCAM match with macsec ethertype 0x88e5 alone at RX side is not sufficient to distinguish all the macsec interfaces created on top of netdevs. Hence append the DMAC of the macsec interface too. Otherwise the first created macsec interface only receives all the macsec traffic. Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 9ec5f38d38a8..f699209978fe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -9,6 +9,7 @@ #include #include "otx2_common.h" +#define MCS_TCAM0_MAC_DA_MASK GENMASK_ULL(47, 0) #define MCS_TCAM0_MAC_SA_MASK GENMASK_ULL(63, 48) #define MCS_TCAM1_MAC_SA_MASK GENMASK_ULL(31, 0) #define MCS_TCAM1_ETYPE_MASK GENMASK_ULL(47, 32) @@ -237,8 +238,10 @@ static int cn10k_mcs_write_rx_flowid(struct otx2_nic *pfvf, struct cn10k_mcs_rxsc *rxsc, u8 hw_secy_id) { struct macsec_rx_sc *sw_rx_sc = rxsc->sw_rxsc; + struct macsec_secy *secy = rxsc->sw_secy; struct mcs_flowid_entry_write_req *req; struct mbox *mbox = &pfvf->mbox; + u64 mac_da; int ret; mutex_lock(&mbox->lock); @@ -249,11 +252,16 @@ static int cn10k_mcs_write_rx_flowid(struct otx2_nic *pfvf, goto fail; } + mac_da = ether_addr_to_u64(secy->netdev->dev_addr); + + req->data[0] = FIELD_PREP(MCS_TCAM0_MAC_DA_MASK, mac_da); + req->mask[0] = ~0ULL; + req->mask[0] = ~MCS_TCAM0_MAC_DA_MASK; + req->data[1] = FIELD_PREP(MCS_TCAM1_ETYPE_MASK, ETH_P_MACSEC); req->mask[1] = ~0ULL; req->mask[1] &= ~MCS_TCAM1_ETYPE_MASK; - req->mask[0] = ~0ULL; req->mask[2] = ~0ULL; req->mask[3] = ~0ULL; -- GitLab From 815debbbf7b52026462c37eea3be70d6377a7a9a Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:26 +0530 Subject: [PATCH 4198/5631] octeontx2-pf: mcs: Clear stats before freeing resource When freeing MCS hardware resources like SecY, SC and SA the corresponding stats needs to be cleared. Otherwise previous stats are shown in newly created macsec interfaces. Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index f699209978fe..13faca9add9f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -150,11 +150,20 @@ static void cn10k_mcs_free_rsrc(struct otx2_nic *pfvf, enum mcs_direction dir, enum mcs_rsrc_type type, u16 hw_rsrc_id, bool all) { + struct mcs_clear_stats *clear_req; struct mbox *mbox = &pfvf->mbox; struct mcs_free_rsrc_req *req; mutex_lock(&mbox->lock); + clear_req = otx2_mbox_alloc_msg_mcs_clear_stats(mbox); + if (!clear_req) + goto fail; + + clear_req->id = hw_rsrc_id; + clear_req->type = type; + clear_req->dir = dir; + req = otx2_mbox_alloc_msg_mcs_free_resources(mbox); if (!req) goto fail; -- GitLab From 9bdfe61054fb2b989eb58df20bf99c0cf67e3038 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:27 +0530 Subject: [PATCH 4199/5631] octeontx2-pf: mcs: Fix shared counters logic Macsec stats like InPktsLate and InPktsDelayed share same counter in hardware. If SecY replay_protect is true then counter represents InPktsLate otherwise InPktsDelayed. This mode change was tracked based on protect_frames instead of replay_protect mistakenly. Similarly InPktsUnchecked and InPktsOk share same counter and mode change was tracked based on validate_check instead of validate_disabled. This patch fixes those problems. Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 14 +++++++------- .../ethernet/marvell/octeontx2/nic/otx2_common.h | 2 +- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 13faca9add9f..3ad8d7ef20be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -1014,7 +1014,7 @@ static void cn10k_mcs_sync_stats(struct otx2_nic *pfvf, struct macsec_secy *secy /* Check if sync is really needed */ if (secy->validate_frames == txsc->last_validate_frames && - secy->protect_frames == txsc->last_protect_frames) + secy->replay_protect == txsc->last_replay_protect) return; cn10k_mcs_secy_stats(pfvf, txsc->hw_secy_id_rx, &rx_rsp, MCS_RX, true); @@ -1036,19 +1036,19 @@ static void cn10k_mcs_sync_stats(struct otx2_nic *pfvf, struct macsec_secy *secy rxsc->stats.InPktsInvalid += sc_rsp.pkt_invalid_cnt; rxsc->stats.InPktsNotValid += sc_rsp.pkt_notvalid_cnt; - if (txsc->last_protect_frames) + if (txsc->last_replay_protect) rxsc->stats.InPktsLate += sc_rsp.pkt_late_cnt; else rxsc->stats.InPktsDelayed += sc_rsp.pkt_late_cnt; - if (txsc->last_validate_frames == MACSEC_VALIDATE_CHECK) + if (txsc->last_validate_frames == MACSEC_VALIDATE_DISABLED) rxsc->stats.InPktsUnchecked += sc_rsp.pkt_unchecked_cnt; else rxsc->stats.InPktsOK += sc_rsp.pkt_unchecked_cnt; } txsc->last_validate_frames = secy->validate_frames; - txsc->last_protect_frames = secy->protect_frames; + txsc->last_replay_protect = secy->replay_protect; } static int cn10k_mdo_open(struct macsec_context *ctx) @@ -1117,7 +1117,7 @@ static int cn10k_mdo_add_secy(struct macsec_context *ctx) txsc->sw_secy = secy; txsc->encoding_sa = secy->tx_sc.encoding_sa; txsc->last_validate_frames = secy->validate_frames; - txsc->last_protect_frames = secy->protect_frames; + txsc->last_replay_protect = secy->replay_protect; list_add(&txsc->entry, &cfg->txsc_list); @@ -1538,12 +1538,12 @@ static int cn10k_mdo_get_rx_sc_stats(struct macsec_context *ctx) rxsc->stats.InPktsInvalid += rsp.pkt_invalid_cnt; rxsc->stats.InPktsNotValid += rsp.pkt_notvalid_cnt; - if (secy->protect_frames) + if (secy->replay_protect) rxsc->stats.InPktsLate += rsp.pkt_late_cnt; else rxsc->stats.InPktsDelayed += rsp.pkt_late_cnt; - if (secy->validate_frames == MACSEC_VALIDATE_CHECK) + if (secy->validate_frames == MACSEC_VALIDATE_DISABLED) rxsc->stats.InPktsUnchecked += rsp.pkt_unchecked_cnt; else rxsc->stats.InPktsOK += rsp.pkt_unchecked_cnt; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 3d22cc6a2804..f42b2b65bfd7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -389,7 +389,7 @@ struct cn10k_mcs_txsc { struct cn10k_txsc_stats stats; struct list_head entry; enum macsec_validation_type last_validate_frames; - bool last_protect_frames; + bool last_replay_protect; u16 hw_secy_id_tx; u16 hw_secy_id_rx; u16 hw_flow_id; -- GitLab From 3c99bace4ad08ad0264285ba8ad73117560992c2 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 26 Apr 2023 11:55:28 +0530 Subject: [PATCH 4200/5631] octeontx2-pf: mcs: Do not reset PN while updating secy After creating SecYs, SCs and SAs a SecY can be modified to change attributes like validation mode, protect frames mode etc. During this SecY update, packet number is reset to initial user given value by mistake. Hence do not reset PN when updating SecY parameters. Fixes: c54ffc73601c ("octeontx2-pf: mcs: Introduce MACSEC hardware offloading") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Goutham Signed-off-by: Geetha sowjanya Reviewed-by: Leon Romanovsky Signed-off-by: Paolo Abeni --- .../ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 3ad8d7ef20be..a487a98eac88 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -1134,6 +1134,7 @@ static int cn10k_mdo_upd_secy(struct macsec_context *ctx) struct macsec_secy *secy = ctx->secy; struct macsec_tx_sa *sw_tx_sa; struct cn10k_mcs_txsc *txsc; + bool active; u8 sa_num; int err; @@ -1141,15 +1142,19 @@ static int cn10k_mdo_upd_secy(struct macsec_context *ctx) if (!txsc) return -ENOENT; - txsc->encoding_sa = secy->tx_sc.encoding_sa; - - sa_num = txsc->encoding_sa; - sw_tx_sa = rcu_dereference_bh(secy->tx_sc.sa[sa_num]); + /* Encoding SA got changed */ + if (txsc->encoding_sa != secy->tx_sc.encoding_sa) { + txsc->encoding_sa = secy->tx_sc.encoding_sa; + sa_num = txsc->encoding_sa; + sw_tx_sa = rcu_dereference_bh(secy->tx_sc.sa[sa_num]); + active = sw_tx_sa ? sw_tx_sa->active : false; + cn10k_mcs_link_tx_sa2sc(pfvf, secy, txsc, sa_num, active); + } if (netif_running(secy->netdev)) { cn10k_mcs_sync_stats(pfvf, secy, txsc); - err = cn10k_mcs_secy_tx_cfg(pfvf, secy, txsc, sw_tx_sa, sa_num); + err = cn10k_mcs_secy_tx_cfg(pfvf, secy, txsc, NULL, 0); if (err) return err; } -- GitLab From 067eb084592819ad59d07afcb5de3e61cee2757c Mon Sep 17 00:00:00 2001 From: Vitaly Rodionov Date: Thu, 27 Apr 2023 12:04:52 +0100 Subject: [PATCH 4201/5631] ALSA: hda/realtek: Add quirk for ThinkPad P1 Gen 6 Lenovo ThinkPad P1 Gen 6 laptop has 2 CS35L41 amplifies on I2C bus connected to Realtek codec. Signed-off-by: Vitaly Rodionov Cc: Link: https://lore.kernel.org/r/20230427110452.13787-1-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f70d6a33421d..4bb2179719e4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9689,6 +9689,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x22f1, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x22f2, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x22f3, "Thinkpad", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x2316, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x2317, "Thinkpad P1 Gen 6", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x2318, "Thinkpad Z13 Gen2", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x2319, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_CS35L41_I2C_2), -- GitLab From ab9ddc87a9055c4bebd6524d5d761d605d52e557 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Thu, 20 Apr 2023 13:54:33 +0000 Subject: [PATCH 4202/5631] SMB3: Add missing locks to protect deferred close file list cifs_del_deferred_close function has a critical section which modifies the deferred close file list. We must acquire deferred_lock before calling cifs_del_deferred_close function. Fixes: ca08d0eac020 ("cifs: Fix memory leak on the deferred close") Signed-off-by: Bharath SM Acked-off-by: Paulo Alcantara (SUSE) Acked-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/misc.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 7f085ed2d866..f76e9bb7d742 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -749,7 +749,9 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + spin_lock(&cifs_inode->deferred_lock); cifs_del_deferred_close(cfile); + spin_unlock(&cifs_inode->deferred_lock); tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) @@ -780,7 +782,9 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) list_for_each_entry(cfile, &tcon->openFileList, tlist) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); cifs_del_deferred_close(cfile); + spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) @@ -815,7 +819,9 @@ cifs_close_deferred_file_under_dentry(struct cifs_tcon *tcon, const char *path) if (strstr(full_path, path)) { if (delayed_work_pending(&cfile->deferred)) { if (cancel_delayed_work(&cfile->deferred)) { + spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); cifs_del_deferred_close(cfile); + spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); if (tmp_list == NULL) -- GitLab From f30ec5df80a0a3328ad6b9c2434ccaa331505307 Mon Sep 17 00:00:00 2001 From: Chris Paterson Date: Wed, 26 Apr 2023 11:07:36 +0100 Subject: [PATCH 4203/5631] dt-bindings: i2c: renesas,rzv2m: Change maintainer to Fabrizio Castro Phil no longer works for Renesas. Signed-off-by: Chris Paterson Acked-by: Fabrizio Castro Link: https://lore.kernel.org/r/20230426100736.11808-1-chris.paterson2@renesas.com Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml index 92e899905ef8..5d1e7885b64a 100644 --- a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml +++ b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas RZ/V2M I2C Bus Interface maintainers: - - Phil Edworthy + - Fabrizio Castro allOf: - $ref: /schemas/i2c/i2c-controller.yaml# -- GitLab From ae98cbffcb4b15140f36ec3172b085deffda48f4 Mon Sep 17 00:00:00 2001 From: Chris Paterson Date: Wed, 26 Apr 2023 11:08:02 +0100 Subject: [PATCH 4204/5631] dt-bindings: pinctrl: renesas,rzn1: Change maintainer to Fabrizio Castro Gareth no longer works for Renesas. Signed-off-by: Chris Paterson Acked-by: Fabrizio Castro Link: https://lore.kernel.org/r/20230426100802.11860-1-chris.paterson2@renesas.com Signed-off-by: Rob Herring --- .../devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml index 70b1788ab594..5be017022e19 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzn1-pinctrl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas RZ/N1 Pin Controller maintainers: - - Gareth Williams + - Fabrizio Castro - Geert Uytterhoeven properties: -- GitLab From d25728563dc950c813ee963c14a8493931612e8d Mon Sep 17 00:00:00 2001 From: Chris Paterson Date: Wed, 26 Apr 2023 11:08:32 +0100 Subject: [PATCH 4205/5631] dt-bindings: pinctrl: renesas,rzv2m: Change maintainer to Fabrizio Castro Phil no longer works for Renesas. Signed-off-by: Chris Paterson Acked-by: Fabrizio Castro Link: https://lore.kernel.org/r/20230426100832.11945-1-chris.paterson2@renesas.com Signed-off-by: Rob Herring --- .../devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml index eac6245db7dc..22be1ac0ca4f 100644 --- a/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/renesas,rzv2m-pinctrl.yaml @@ -7,8 +7,8 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas RZ/V2M combined Pin and GPIO controller maintainers: + - Fabrizio Castro - Geert Uytterhoeven - - Phil Edworthy description: The Renesas RZ/V2M SoC features a combined Pin and GPIO controller. -- GitLab From 6e0c2bf2ca34046fe17a978a092925d411ce3a8c Mon Sep 17 00:00:00 2001 From: Chris Paterson Date: Wed, 26 Apr 2023 11:09:25 +0100 Subject: [PATCH 4206/5631] dt-bindings: clock: r9a06g032-sysctrl: Change maintainer to Fabrizio Castro Gareth no longer works for Renesas. Signed-off-by: Chris Paterson Acked-by: Fabrizio Castro Link: https://lore.kernel.org/r/20230426100925.12063-1-chris.paterson2@renesas.com Signed-off-by: Rob Herring --- .../devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml b/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml index 95bf485c6cec..99686085f751 100644 --- a/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Renesas RZ/N1D (R9A06G032) System Controller maintainers: - - Gareth Williams + - Fabrizio Castro - Geert Uytterhoeven properties: -- GitLab From d906be3fa571f6fc9381911304a0eca99f1b6951 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Wed, 26 Apr 2023 14:05:16 +0000 Subject: [PATCH 4207/5631] SMB3: Close deferred file handles in case of handle lease break We should not cache deferred file handles if we dont have handle lease on a file. And we should immediately close all deferred handles in case of handle lease break. Fixes: 9e31678fb403 ("SMB3: fix lease break timeout when multiple deferred close handles for the same file.") Signed-off-by: Bharath SM Signed-off-by: Steve French --- fs/cifs/file.c | 16 ++++++++++++++++ fs/cifs/misc.c | 2 +- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index b33d2e7b0f98..c5fcefdfd797 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4882,6 +4882,8 @@ void cifs_oplock_break(struct work_struct *work) struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; bool purge_cache = false; + struct cifs_deferred_close *dclose; + bool is_deferred = false; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4917,6 +4919,20 @@ void cifs_oplock_break(struct work_struct *work) cifs_dbg(VFS, "Push locks rc = %d\n", rc); oplock_break_ack: + /* + * When oplock break is received and there are no active + * file handles but cached, then schedule deferred close immediately. + * So, new open will not use cached handle. + */ + spin_lock(&CIFS_I(inode)->deferred_lock); + is_deferred = cifs_is_deferred_close(cfile, &dclose); + spin_unlock(&CIFS_I(inode)->deferred_lock); + + if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && + cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + cifs_close_deferred_file(cinode); + } + /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index f76e9bb7d742..cd914be905b2 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -764,7 +764,7 @@ cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) spin_unlock(&cifs_inode->open_file_lock); list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { - _cifsFileInfo_put(tmp_list->cfile, true, false); + _cifsFileInfo_put(tmp_list->cfile, false, false); list_del(&tmp_list->list); kfree(tmp_list); } -- GitLab From 8325642d2757eba80210dec727bb0bcffb837ff1 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Wed, 19 Apr 2023 13:18:06 +0200 Subject: [PATCH 4208/5631] leds: bd2606mvv: Driver for the Rohm 6 Channel i2c LED driver The device provides 6 channels which can be individually turned off and on but groups of two channels share a common brightness register. Limitation: The GPIO to enable the device is not used yet. Signed-off-by: Andreas Kemnade Reviewed-by: Matti Vaittinen Acked-by: Pavel Machek Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20230419111806.1100437-3-andreas@kemnade.info --- drivers/leds/Kconfig | 14 +++ drivers/leds/Makefile | 1 + drivers/leds/leds-bd2606mvv.c | 160 ++++++++++++++++++++++++++++++++++ 3 files changed, 175 insertions(+) create mode 100644 drivers/leds/leds-bd2606mvv.c diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index aaa9140bc351..2c5fdf848210 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -551,6 +551,20 @@ config LEDS_REGULATOR help This option enables support for regulator driven LEDs. +config LEDS_BD2606MVV + tristate "LED driver for BD2606MVV" + depends on LEDS_CLASS + depends on I2C + select REGMAP_I2C + help + This option enables support for BD2606MVV LED driver chips + accessed via the I2C bus. It supports setting brightness, with + the limitiation that there are groups of two channels sharing + a brightness setting, but not the on/off setting. + + To compile this driver as a module, choose M here: the module will + be called leds-bd2606mvv. + config LEDS_BD2802 tristate "LED driver for BD2802 RGB LED" depends on LEDS_CLASS diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index d30395d11fd8..c07d1512c745 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_LEDS_ARIEL) += leds-ariel.o obj-$(CONFIG_LEDS_AW2013) += leds-aw2013.o obj-$(CONFIG_LEDS_BCM6328) += leds-bcm6328.o obj-$(CONFIG_LEDS_BCM6358) += leds-bcm6358.o +obj-$(CONFIG_LEDS_BD2606MVV) += leds-bd2606mvv.o obj-$(CONFIG_LEDS_BD2802) += leds-bd2802.o obj-$(CONFIG_LEDS_BLINKM) += leds-blinkm.o obj-$(CONFIG_LEDS_CLEVO_MAIL) += leds-clevo-mail.o diff --git a/drivers/leds/leds-bd2606mvv.c b/drivers/leds/leds-bd2606mvv.c new file mode 100644 index 000000000000..76f9d4d70f9a --- /dev/null +++ b/drivers/leds/leds-bd2606mvv.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Andreas Kemnade + * + * Datasheet: + * https://fscdn.rohm.com/en/products/databook/datasheet/ic/power/led_driver/bd2606mvv_1-e.pdf + * + * If LED brightness cannot be controlled independently due to shared + * brightness registers, max_brightness is set to 1 and only on/off + * is possible for the affected LED pair. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define BD2606_MAX_LEDS 6 +#define BD2606_MAX_BRIGHTNESS 63 +#define BD2606_REG_PWRCNT 3 +#define ldev_to_led(c) container_of(c, struct bd2606mvv_led, ldev) + +struct bd2606mvv_led { + unsigned int led_no; + struct led_classdev ldev; + struct bd2606mvv_priv *priv; +}; + +struct bd2606mvv_priv { + struct bd2606mvv_led leds[BD2606_MAX_LEDS]; + struct regmap *regmap; +}; + +static int +bd2606mvv_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct bd2606mvv_led *led = ldev_to_led(led_cdev); + struct bd2606mvv_priv *priv = led->priv; + int err; + + if (brightness == 0) + return regmap_update_bits(priv->regmap, + BD2606_REG_PWRCNT, + 1 << led->led_no, + 0); + + /* shared brightness register */ + err = regmap_write(priv->regmap, led->led_no / 2, + led_cdev->max_brightness == 1 ? + BD2606_MAX_BRIGHTNESS : brightness); + if (err) + return err; + + return regmap_update_bits(priv->regmap, + BD2606_REG_PWRCNT, + 1 << led->led_no, + 1 << led->led_no); +} + +static const struct regmap_config bd2606mvv_regmap = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x3, +}; + +static int bd2606mvv_probe(struct i2c_client *client) +{ + struct fwnode_handle *np, *child; + struct device *dev = &client->dev; + struct bd2606mvv_priv *priv; + struct fwnode_handle *led_fwnodes[BD2606_MAX_LEDS] = { 0 }; + int active_pairs[BD2606_MAX_LEDS / 2] = { 0 }; + int err, reg; + int i; + + np = dev_fwnode(dev); + if (!np) + return -ENODEV; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->regmap = devm_regmap_init_i2c(client, &bd2606mvv_regmap); + if (IS_ERR(priv->regmap)) { + err = PTR_ERR(priv->regmap); + dev_err(dev, "Failed to allocate register map: %d\n", err); + return err; + } + + i2c_set_clientdata(client, priv); + + fwnode_for_each_available_child_node(np, child) { + struct bd2606mvv_led *led; + + err = fwnode_property_read_u32(child, "reg", ®); + if (err) { + fwnode_handle_put(child); + return err; + } + if (reg < 0 || reg >= BD2606_MAX_LEDS || led_fwnodes[reg]) { + fwnode_handle_put(child); + return -EINVAL; + } + led = &priv->leds[reg]; + led_fwnodes[reg] = child; + active_pairs[reg / 2]++; + led->priv = priv; + led->led_no = reg; + led->ldev.brightness_set_blocking = bd2606mvv_brightness_set; + led->ldev.max_brightness = BD2606_MAX_BRIGHTNESS; + } + + for (i = 0; i < BD2606_MAX_LEDS; i++) { + struct led_init_data init_data = {}; + + if (!led_fwnodes[i]) + continue; + + init_data.fwnode = led_fwnodes[i]; + /* Check whether brightness can be independently adjusted. */ + if (active_pairs[i / 2] == 2) + priv->leds[i].ldev.max_brightness = 1; + + err = devm_led_classdev_register_ext(dev, + &priv->leds[i].ldev, + &init_data); + if (err < 0) { + fwnode_handle_put(child); + return dev_err_probe(dev, err, + "couldn't register LED %s\n", + priv->leds[i].ldev.name); + } + } + return 0; +} + +static const struct of_device_id __maybe_unused of_bd2606mvv_leds_match[] = { + { .compatible = "rohm,bd2606mvv", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_bd2606mvv_leds_match); + +static struct i2c_driver bd2606mvv_driver = { + .driver = { + .name = "leds-bd2606mvv", + .of_match_table = of_match_ptr(of_bd2606mvv_leds_match), + }, + .probe_new = bd2606mvv_probe, +}; + +module_i2c_driver(bd2606mvv_driver); + +MODULE_AUTHOR("Andreas Kemnade "); +MODULE_DESCRIPTION("BD2606 LED driver"); +MODULE_LICENSE("GPL"); -- GitLab From 9b04d99788cf475cbd277f30ec66230ccb7e99f4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 20 Apr 2023 13:02:20 +0200 Subject: [PATCH 4209/5631] ACPI: PM: Do not turn of unused power resources on the Toshiba Click Mini MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CPR3 power resource on the Toshiba Click Mini toggles a GPIO which is called SISP (for SIS touchscreen power?) on/off. This CPR3 power resource is not listed in any _PR? lists, let alone in a _PR0 list for the SIS0817 touchscreen ACPI device which needs it. Before commit a1224f34d72a ("ACPI: PM: Check states of power resources during initialization") this was not an issue because since nothing referenced the CPR3 power resource its state was always ACPI_POWER_RESOURCE_STATE_UNKNOWN and power resources with this state get ignored by acpi_turn_off_unused_power_resources(). This clearly is a bug in the DSDT of this device. Add a DMI quirk to make acpi_turn_off_unused_power_resources() a no-op on this model to fix the touchscreen no longer working since kernel 5.16 . This quirk also causes 2 other power resources to not get turned off, but the _OFF method on these already was a no-op, so this makes no difference for the other 2 power resources. Fixes: a1224f34d72a ("ACPI: PM: Check states of power resources during initialization") Reported-by: Gé Koerkamp Link: https://bugzilla.kernel.org/show_bug.cgi?id=216946 Link: https://lore.kernel.org/regressions/32a14a8a-9795-4c8c-7e00-da9012f548f8@leemhuis.info/ Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- drivers/acpi/power.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 23507d29f000..c2c70139c4f1 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -23,6 +23,7 @@ #define pr_fmt(fmt) "ACPI: PM: " fmt +#include #include #include #include @@ -1022,6 +1023,21 @@ void acpi_resume_power_resources(void) } #endif +static const struct dmi_system_id dmi_leave_unused_power_resources_on[] = { + { + /* + * The Toshiba Click Mini has a CPR3 power-resource which must + * be on for the touchscreen to work, but which is not in any + * _PR? lists. The other 2 affected power-resources are no-ops. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE Click Mini L9W-B"), + }, + }, + {} +}; + /** * acpi_turn_off_unused_power_resources - Turn off power resources not in use. */ @@ -1029,6 +1045,9 @@ void acpi_turn_off_unused_power_resources(void) { struct acpi_power_resource *resource; + if (dmi_check_system(dmi_leave_unused_power_resources_on)) + return; + mutex_lock(&power_resource_list_lock); list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) { -- GitLab From 61711941d8515c6d2a8a95d89e132902b56feebd Mon Sep 17 00:00:00 2001 From: Marius Hoch Date: Sat, 22 Apr 2023 18:44:01 +0200 Subject: [PATCH 4210/5631] ACPI: x86: utils: Remove Lenovo Yoga Tablet 2's MAGN0001 The LSM303D on the Lenovo Yoga Tablet 2 series is present as both ACCL0001 and MAGN0001. As we can only ever register an i2c client for one of them, ignore MAGN0001. Currently this errors: i2c i2c-4: Failed to register i2c client MAGN0001:00 at 0x1d (-16) Tested on a Lenovo Yoga Tablet 2 1051-F. Signed-off-by: Marius Hoch Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/utils.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index ba420a28a4aa..9c2d6f35f88a 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -143,6 +143,16 @@ static const struct override_status_id override_status_ids[] = { DMI_EXACT_MATCH(DMI_BOARD_SERIAL, "Default string"), DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Default string"), }), + + /* + * The LSM303D on the Lenovo Yoga Tablet 2 series is present + * as both ACCL0001 and MAGN0001. As we can only ever register an + * i2c client for one of them, ignore MAGN0001. + */ + NOT_PRESENT_ENTRY_HID("MAGN0001", "1", ATOM_SILVERMONT, { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "YOGATablet2"), + }), }; bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *status) -- GitLab From 9bde7fb8940f636f4338bf233883ae37844dcdb7 Mon Sep 17 00:00:00 2001 From: Hector Martin Date: Mon, 24 Apr 2023 15:46:57 +0900 Subject: [PATCH 4211/5631] ACPI: property: Support strings in Apple _DSM props The Wi-Fi module in x86 Apple machines has a "module-instance" device property that specifies the platform type and is used for firmware selection. Its value is a string, so add support for string values in acpi_extract_apple_properties(). Reviewed-by: Lukas Wunner Acked-by: Linus Walleij Signed-off-by: Hector Martin Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/apple.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/x86/apple.c b/drivers/acpi/x86/apple.c index 8812ecd03d55..45d0f16f374f 100644 --- a/drivers/acpi/x86/apple.c +++ b/drivers/acpi/x86/apple.c @@ -71,13 +71,16 @@ void acpi_extract_apple_properties(struct acpi_device *adev) if ( key->type != ACPI_TYPE_STRING || (val->type != ACPI_TYPE_INTEGER && - val->type != ACPI_TYPE_BUFFER)) + val->type != ACPI_TYPE_BUFFER && + val->type != ACPI_TYPE_STRING)) continue; /* skip invalid properties */ __set_bit(i, valid); newsize += key->string.length + 1; if ( val->type == ACPI_TYPE_BUFFER) newsize += val->buffer.length; + else if (val->type == ACPI_TYPE_STRING) + newsize += val->string.length + 1; } numvalid = bitmap_weight(valid, numprops); @@ -119,6 +122,12 @@ void acpi_extract_apple_properties(struct acpi_device *adev) newprops[v].type = val->type; if (val->type == ACPI_TYPE_INTEGER) { newprops[v].integer.value = val->integer.value; + } else if (val->type == ACPI_TYPE_STRING) { + newprops[v].string.length = val->string.length; + newprops[v].string.pointer = free_space; + memcpy(free_space, val->string.pointer, + val->string.length); + free_space += val->string.length + 1; } else { newprops[v].buffer.length = val->buffer.length; newprops[v].buffer.pointer = free_space; -- GitLab From 08169a162f97819d3e5b4a342bb9cf5137787154 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 14 Apr 2023 20:10:26 +0800 Subject: [PATCH 4212/5631] PM: hibernate: Turn snapshot_test into global variable There is need to check snapshot_test and open block device in different mode, so as to avoid the race condition. No functional changes intended. Suggested-by: Pavankumar Kondeti Signed-off-by: Chen Yu Signed-off-by: Rafael J. Wysocki --- kernel/power/hibernate.c | 7 ++++++- kernel/power/power.h | 1 + 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 793c55a2becb..aa551b093c3f 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -64,6 +64,7 @@ enum { static int hibernation_mode = HIBERNATION_SHUTDOWN; bool freezer_test_done; +bool snapshot_test; static const struct platform_hibernation_ops *hibernation_ops; @@ -716,7 +717,6 @@ static int load_image_and_restore(void) */ int hibernate(void) { - bool snapshot_test = false; unsigned int sleep_flags; int error; @@ -744,6 +744,9 @@ int hibernate(void) if (error) goto Exit; + /* protected by system_transition_mutex */ + snapshot_test = false; + lock_device_hotplug(); /* Allocate memory management structures */ error = create_basic_memory_bitmaps(); @@ -940,6 +943,8 @@ static int software_resume(void) */ mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING); + snapshot_test = false; + if (swsusp_resume_device) goto Check_image; diff --git a/kernel/power/power.h b/kernel/power/power.h index b4f433943209..b83c8d5e188d 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -59,6 +59,7 @@ asmlinkage int swsusp_save(void); /* kernel/power/hibernate.c */ extern bool freezer_test_done; +extern bool snapshot_test; extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); -- GitLab From 5904de0d735bbb3b4afe9375c5b4f9748f882945 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Fri, 14 Apr 2023 20:10:42 +0800 Subject: [PATCH 4213/5631] PM: hibernate: Do not get block device exclusively in test_resume mode The system refused to do a test_resume because it found that the swap device has already been taken by someone else. Specifically, the swsusp_check()->blkdev_get_by_dev(FMODE_EXCL) is supposed to do this check. Steps to reproduce: dd if=/dev/zero of=/swapfile bs=$(cat /proc/meminfo | awk '/MemTotal/ {print $2}') count=1024 conv=notrunc mkswap /swapfile swapon /swapfile swap-offset /swapfile echo 34816 > /sys/power/resume_offset echo test_resume > /sys/power/disk echo disk > /sys/power/state PM: Using 3 thread(s) for compression PM: Compressing and saving image data (293150 pages)... PM: Image saving progress: 0% PM: Image saving progress: 10% ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) ata1.00: configured for UDMA/100 ata2: SATA link down (SStatus 0 SControl 300) ata5: SATA link down (SStatus 0 SControl 300) ata6: SATA link down (SStatus 0 SControl 300) ata3: SATA link down (SStatus 0 SControl 300) ata4: SATA link down (SStatus 0 SControl 300) PM: Image saving progress: 20% PM: Image saving progress: 30% PM: Image saving progress: 40% PM: Image saving progress: 50% pcieport 0000:00:02.5: pciehp: Slot(0-5): No device found PM: Image saving progress: 60% PM: Image saving progress: 70% PM: Image saving progress: 80% PM: Image saving progress: 90% PM: Image saving done PM: hibernation: Wrote 1172600 kbytes in 2.70 seconds (434.29 MB/s) PM: S| PM: hibernation: Basic memory bitmaps freed PM: Image not found (code -16) This is because when using the swapfile as the hibernation storage, the block device where the swapfile is located has already been mounted by the OS distribution(usually mounted as the rootfs). This is not an issue for normal hibernation, because software_resume()->swsusp_check() happens before the block device(rootfs) mount. But it is a problem for the test_resume mode. Because when test_resume happens, the block device has been mounted already. Thus remove the FMODE_EXCL for test_resume mode. This would not be a problem because in test_resume stage, the processes have already been frozen, and the race condition described in Commit 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") is unlikely to happen. Fixes: 39fbef4b0f77 ("PM: hibernate: Get block device exclusively in swsusp_check()") Reported-by: Yifan Li Suggested-by: Pavankumar Kondeti Tested-by: Pavankumar Kondeti Tested-by: Wendy Wang Signed-off-by: Chen Yu Signed-off-by: Rafael J. Wysocki --- kernel/power/hibernate.c | 8 ++++++-- kernel/power/swap.c | 8 ++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aa551b093c3f..30d1274f03f6 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -688,18 +688,22 @@ static int load_image_and_restore(void) { int error; unsigned int flags; + fmode_t mode = FMODE_READ; + + if (snapshot_test) + mode |= FMODE_EXCL; pm_pr_dbg("Loading hibernation image.\n"); lock_device_hotplug(); error = create_basic_memory_bitmaps(); if (error) { - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(mode); goto Unlock; } error = swsusp_read(&flags); - swsusp_close(FMODE_READ | FMODE_EXCL); + swsusp_close(mode); if (!error) error = hibernation_restore(flags & SF_PLATFORM_MODE); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 36a1df48280c..92e41ed292ad 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1518,9 +1518,13 @@ int swsusp_check(void) { int error; void *holder; + fmode_t mode = FMODE_READ; + + if (snapshot_test) + mode |= FMODE_EXCL; hib_resume_bdev = blkdev_get_by_dev(swsusp_resume_device, - FMODE_READ | FMODE_EXCL, &holder); + mode, &holder); if (!IS_ERR(hib_resume_bdev)) { set_blocksize(hib_resume_bdev, PAGE_SIZE); clear_page(swsusp_header); @@ -1547,7 +1551,7 @@ int swsusp_check(void) put: if (error) - blkdev_put(hib_resume_bdev, FMODE_READ | FMODE_EXCL); + blkdev_put(hib_resume_bdev, mode); else pr_debug("Image signature found, resuming\n"); } else { -- GitLab From cead266cdbcfa471f54590ebfd3ebf303f99123f Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 21 Mar 2023 13:47:13 +0800 Subject: [PATCH 4214/5631] thermal: gov_step_wise: Delete obsolete comment Commit 4102c4042a33 ("thermal/core: Remove DROP_FULL and RAISE_FULL") removes support for THERMAL_TREND_RAISE_FULL/DROP_FULL but leaves the comment unchanged. Delete the obsolte comment about THERMAL_TREND_RAISE_FULL/DROP_FULL. Fixes: 4102c4042a33 ("thermal/core: Remove DROP_FULL and RAISE_FULL") Signed-off-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/thermal/gov_step_wise.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c index 3d3067804df2..3f72a8eaf2f7 100644 --- a/drivers/thermal/gov_step_wise.c +++ b/drivers/thermal/gov_step_wise.c @@ -21,19 +21,11 @@ * a. if the trend is THERMAL_TREND_RAISING, use higher cooling * state for this trip point * b. if the trend is THERMAL_TREND_DROPPING, do nothing - * c. if the trend is THERMAL_TREND_RAISE_FULL, use upper limit - * for this trip point - * d. if the trend is THERMAL_TREND_DROP_FULL, use lower limit - * for this trip point * If the temperature is lower than a trip point, * a. if the trend is THERMAL_TREND_RAISING, do nothing * b. if the trend is THERMAL_TREND_DROPPING, use lower cooling * state for this trip point, if the cooling state already * equals lower limit, deactivate the thermal instance - * c. if the trend is THERMAL_TREND_RAISE_FULL, do nothing - * d. if the trend is THERMAL_TREND_DROP_FULL, use lower limit, - * if the cooling state already equals lower limit, - * deactivate the thermal instance */ static unsigned long get_target_state(struct thermal_instance *instance, enum thermal_trend trend, bool throttle) -- GitLab From e4006bfec12cec4fb251de860d384dd34e6df346 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 21 Mar 2023 13:47:14 +0800 Subject: [PATCH 4215/5631] thermal: gov_step_wise: Adjust code logic to match comment For the algorithm of choosing the next target state in step_wise governor, the code does the right thing but is implemented in a way different from what the comment describes. And this hurts the code readability. As the logic in the comment is simpler, adjust the code logic to align with the comment. No functional change. Signed-off-by: Zhang Rui [ rjw: Subject edit ] Signed-off-by: Rafael J. Wysocki --- drivers/thermal/gov_step_wise.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c index 3f72a8eaf2f7..1050fb4d94c2 100644 --- a/drivers/thermal/gov_step_wise.c +++ b/drivers/thermal/gov_step_wise.c @@ -53,24 +53,16 @@ static unsigned long get_target_state(struct thermal_instance *instance, return next_target; } - switch (trend) { - case THERMAL_TREND_RAISING: - if (throttle) { + if (throttle) { + if (trend == THERMAL_TREND_RAISING) next_target = clamp((cur_state + 1), instance->lower, instance->upper); - } - break; - case THERMAL_TREND_DROPPING: - if (cur_state <= instance->lower) { - if (!throttle) + } else { + if (trend == THERMAL_TREND_DROPPING) { + if (cur_state <= instance->lower) next_target = THERMAL_NO_TARGET; - } else { - if (!throttle) { + else next_target = clamp((cur_state - 1), instance->lower, instance->upper); - } } - break; - default: - break; } return next_target; -- GitLab From 7cefbaf081eb7c114299f7478ed4fa0d90ec90bb Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 19 Apr 2023 10:33:38 +0200 Subject: [PATCH 4216/5631] thermal: core: Encapsulate tz->device field There are still some drivers needing to play with the thermal zone device internals. That is not the best but until we can figure out if the information is really needed, let's encapsulate the field used in the thermal zone device structure, so we can move forward relocating the thermal zone device structure definition in the thermal framework private headers. Some drivers are accessing tz->device, that implies they need to have the knowledge of the thermal_zone_device structure but we want to self-encapsulate this structure and reduce the scope of the structure to the thermal core only. By adding this wrapper, these drivers won't need the thermal zone device structure definition and are no longer an obstacle to its relocation to the private thermal core headers. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/thermal/thermal_core.c | 6 ++++++ include/linux/thermal.h | 1 + 2 files changed, 7 insertions(+) diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index c5025aca22ee..842f678c1c3e 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1398,6 +1398,12 @@ int thermal_zone_device_id(struct thermal_zone_device *tzd) } EXPORT_SYMBOL_GPL(thermal_zone_device_id); +struct device *thermal_zone_device(struct thermal_zone_device *tzd) +{ + return &tzd->device; +} +EXPORT_SYMBOL_GPL(thermal_zone_device); + /** * thermal_zone_device_unregister - removes the registered thermal zone device * @tz: the thermal zone device to remove diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 82ddb32f9876..87837094d549 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -313,6 +313,7 @@ thermal_zone_device_register_with_trips(const char *, struct thermal_trip *, int void *thermal_zone_device_priv(struct thermal_zone_device *tzd); const char *thermal_zone_device_type(struct thermal_zone_device *tzd); int thermal_zone_device_id(struct thermal_zone_device *tzd); +struct device *thermal_zone_device(struct thermal_zone_device *tzd); int thermal_zone_bind_cooling_device(struct thermal_zone_device *, int, struct thermal_cooling_device *, -- GitLab From ba7894be5e57d5c154c793e5411889275e68644e Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 19 Apr 2023 10:33:39 +0200 Subject: [PATCH 4217/5631] thermal: intel: pch_thermal: Use thermal driver device to write a trace The pch_critical() callback accesses the thermal zone device structure internals, it dereferences the thermal zone struct device and the 'type'. Use the available accessors instead of accessing the structure directly. Signed-off-by: Daniel Lezcano Signed-off-by: Rafael J. Wysocki --- drivers/thermal/intel/intel_pch_thermal.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c index dce50d239357..b3905e34c507 100644 --- a/drivers/thermal/intel/intel_pch_thermal.c +++ b/drivers/thermal/intel/intel_pch_thermal.c @@ -127,7 +127,8 @@ static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) static void pch_critical(struct thermal_zone_device *tzd) { - dev_dbg(&tzd->device, "%s: critical temperature reached\n", tzd->type); + dev_dbg(thermal_zone_device(tzd), "%s: critical temperature reached\n", + thermal_zone_device_type(tzd)); } static struct thermal_zone_device_ops tzd_ops = { -- GitLab From 66d39e74bf490fb1ef90e13086b68d6df6e6ad06 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 19 Apr 2023 10:33:40 +0200 Subject: [PATCH 4218/5631] ACPI: thermal: Use thermal_zone_device() In order to get the device associated with the thermal zone, let's use the wrapper thermal_zone_device() instead of accessing directly the content of the thermal zone device structure. Signed-off-by: Daniel Lezcano [ rjw: Subject adjustment, removal of trailing white space ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/thermal.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 255efa73ed70..3682f181d51e 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -789,6 +789,7 @@ static struct thermal_zone_device_ops acpi_thermal_zone_ops = { static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) { + struct device *tzdev; int trips = 0; int result; acpi_status status; @@ -820,12 +821,14 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) if (IS_ERR(tz->thermal_zone)) return -ENODEV; + tzdev = thermal_zone_device(tz->thermal_zone); + result = sysfs_create_link(&tz->device->dev.kobj, - &tz->thermal_zone->device.kobj, "thermal_zone"); + &tzdev->kobj, "thermal_zone"); if (result) goto unregister_tzd; - result = sysfs_create_link(&tz->thermal_zone->device.kobj, + result = sysfs_create_link(&tzdev->kobj, &tz->device->dev.kobj, "device"); if (result) goto remove_tz_link; @@ -849,7 +852,7 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) acpi_bus_detach: acpi_bus_detach_private_data(tz->device->handle); remove_dev_link: - sysfs_remove_link(&tz->thermal_zone->device.kobj, "device"); + sysfs_remove_link(&tzdev->kobj, "device"); remove_tz_link: sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); unregister_tzd: @@ -860,8 +863,10 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz) { + struct device *tzdev = thermal_zone_device(tz->thermal_zone); + sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); - sysfs_remove_link(&tz->thermal_zone->device.kobj, "device"); + sysfs_remove_link(&tzdev->kobj, "device"); thermal_zone_device_unregister(tz->thermal_zone); tz->thermal_zone = NULL; acpi_bus_detach_private_data(tz->device->handle); -- GitLab From a4b81715a58e0ddf10bc2df2185566b73b9ae616 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 19 Apr 2023 10:33:42 +0200 Subject: [PATCH 4219/5631] ACPI: thermal: Move to dedicated function sysfs extra attr creation The ACPI thermal driver creates extra sysfs attributes in its own directory pointing to the thermal zone it is related to and add a pointer to the sysfs ACPI thermal device from the thermal zone sysfs entry. This is very specific to this ACPI thermal driver, let's encapsulate the related creation/deletion code to group it inside a function we can identify later for removal if needed. Signed-off-by: Daniel Lezcano [ rjw: Subject adjustment, removal of trailing white space ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/thermal.c | 50 ++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 19 deletions(-) diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 3682f181d51e..38bc81b88ea0 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -787,9 +787,34 @@ static struct thermal_zone_device_ops acpi_thermal_zone_ops = { .critical = acpi_thermal_zone_device_critical, }; +static int acpi_thermal_zone_sysfs_add(struct acpi_thermal *tz) +{ + struct device *tzdev = thermal_zone_device(tz->thermal_zone); + int ret; + + ret = sysfs_create_link(&tz->device->dev.kobj, + &tzdev->kobj, "thermal_zone"); + if (ret) + return ret; + + ret = sysfs_create_link(&tzdev->kobj, + &tz->device->dev.kobj, "device"); + if (ret) + sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); + + return ret; +} + +static void acpi_thermal_zone_sysfs_remove(struct acpi_thermal *tz) +{ + struct device *tzdev = thermal_zone_device(tz->thermal_zone); + + sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); + sysfs_remove_link(&tzdev->kobj, "device"); +} + static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) { - struct device *tzdev; int trips = 0; int result; acpi_status status; @@ -821,23 +846,15 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) if (IS_ERR(tz->thermal_zone)) return -ENODEV; - tzdev = thermal_zone_device(tz->thermal_zone); - - result = sysfs_create_link(&tz->device->dev.kobj, - &tzdev->kobj, "thermal_zone"); + result = acpi_thermal_zone_sysfs_add(tz); if (result) goto unregister_tzd; - result = sysfs_create_link(&tzdev->kobj, - &tz->device->dev.kobj, "device"); - if (result) - goto remove_tz_link; - status = acpi_bus_attach_private_data(tz->device->handle, tz->thermal_zone); if (ACPI_FAILURE(status)) { result = -ENODEV; - goto remove_dev_link; + goto remove_links; } result = thermal_zone_device_enable(tz->thermal_zone); @@ -851,10 +868,8 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) acpi_bus_detach: acpi_bus_detach_private_data(tz->device->handle); -remove_dev_link: - sysfs_remove_link(&tzdev->kobj, "device"); -remove_tz_link: - sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); +remove_links: + acpi_thermal_zone_sysfs_remove(tz); unregister_tzd: thermal_zone_device_unregister(tz->thermal_zone); @@ -863,10 +878,7 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz) static void acpi_thermal_unregister_thermal_zone(struct acpi_thermal *tz) { - struct device *tzdev = thermal_zone_device(tz->thermal_zone); - - sysfs_remove_link(&tz->device->dev.kobj, "thermal_zone"); - sysfs_remove_link(&tzdev->kobj, "device"); + acpi_thermal_zone_sysfs_remove(tz); thermal_zone_device_unregister(tz->thermal_zone); tz->thermal_zone = NULL; acpi_bus_detach_private_data(tz->device->handle); -- GitLab From 2b6a7409ac390d3edb49822ea602ac129486ea3f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 26 Apr 2023 18:46:05 +0200 Subject: [PATCH 4220/5631] thermal: intel: menlow: Get rid of this driver According to my information, there are no active users of this driver in the field. Moreover, it does some really questionable things and gets in the way of thermal core improvements, so drop it. Signed-off-by: Rafael J. Wysocki Acked-by: Daniel Lezcano --- drivers/thermal/intel/Kconfig | 9 - drivers/thermal/intel/Makefile | 1 - drivers/thermal/intel/intel_menlow.c | 521 --------------------------- 3 files changed, 531 deletions(-) delete mode 100644 drivers/thermal/intel/intel_menlow.c diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig index cb7e7697cf1e..ecd7e07eece0 100644 --- a/drivers/thermal/intel/Kconfig +++ b/drivers/thermal/intel/Kconfig @@ -103,15 +103,6 @@ config INTEL_TCC_COOLING on how fast the setting takes effect, and how much the CPU frequency is reduced. -config INTEL_MENLOW - tristate "Thermal Management driver for Intel menlow platform" - depends on ACPI_THERMAL - help - ACPI thermal management enhancement driver on - Intel Menlow platform. - - If unsure, say N. - config INTEL_HFI_THERMAL bool "Intel Hardware Feedback Interface" depends on NET diff --git a/drivers/thermal/intel/Makefile b/drivers/thermal/intel/Makefile index 5d8833c82ab6..182b3411300a 100644 --- a/drivers/thermal/intel/Makefile +++ b/drivers/thermal/intel/Makefile @@ -13,5 +13,4 @@ obj-$(CONFIG_INTEL_BXT_PMIC_THERMAL) += intel_bxt_pmic_thermal.o obj-$(CONFIG_INTEL_PCH_THERMAL) += intel_pch_thermal.o obj-$(CONFIG_INTEL_TCC_COOLING) += intel_tcc_cooling.o obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o -obj-$(CONFIG_INTEL_MENLOW) += intel_menlow.o obj-$(CONFIG_INTEL_HFI_THERMAL) += intel_hfi.o diff --git a/drivers/thermal/intel/intel_menlow.c b/drivers/thermal/intel/intel_menlow.c deleted file mode 100644 index 5a6ad0552311..000000000000 --- a/drivers/thermal/intel/intel_menlow.c +++ /dev/null @@ -1,521 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Intel menlow Driver for thermal management extension - * - * Copyright (C) 2008 Intel Corp - * Copyright (C) 2008 Sujith Thomas - * Copyright (C) 2008 Zhang Rui - * - * This driver creates the sys I/F for programming the sensors. - * It also implements the driver for intel menlow memory controller (hardware - * id is INT0002) which makes use of the platform specific ACPI methods - * to get/set bandwidth. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -MODULE_AUTHOR("Thomas Sujith"); -MODULE_AUTHOR("Zhang Rui"); -MODULE_DESCRIPTION("Intel Menlow platform specific driver"); -MODULE_LICENSE("GPL v2"); - -/* - * Memory controller device control - */ - -#define MEMORY_GET_BANDWIDTH "GTHS" -#define MEMORY_SET_BANDWIDTH "STHS" -#define MEMORY_ARG_CUR_BANDWIDTH 1 -#define MEMORY_ARG_MAX_BANDWIDTH 0 - -static void intel_menlow_unregister_sensor(void); - -/* - * GTHS returning 'n' would mean that [0,n-1] states are supported - * In that case max_cstate would be n-1 - * GTHS returning '0' would mean that no bandwidth control states are supported - */ -static int memory_get_max_bandwidth(struct thermal_cooling_device *cdev, - unsigned long *max_state) -{ - struct acpi_device *device = cdev->devdata; - acpi_handle handle = device->handle; - unsigned long long value; - struct acpi_object_list arg_list; - union acpi_object arg; - acpi_status status = AE_OK; - - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = MEMORY_ARG_MAX_BANDWIDTH; - status = acpi_evaluate_integer(handle, MEMORY_GET_BANDWIDTH, - &arg_list, &value); - if (ACPI_FAILURE(status)) - return -EFAULT; - - if (!value) - return -EINVAL; - - *max_state = value - 1; - return 0; -} - -static int memory_get_cur_bandwidth(struct thermal_cooling_device *cdev, - unsigned long *value) -{ - struct acpi_device *device = cdev->devdata; - acpi_handle handle = device->handle; - unsigned long long result; - struct acpi_object_list arg_list; - union acpi_object arg; - acpi_status status = AE_OK; - - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = MEMORY_ARG_CUR_BANDWIDTH; - status = acpi_evaluate_integer(handle, MEMORY_GET_BANDWIDTH, - &arg_list, &result); - if (ACPI_FAILURE(status)) - return -EFAULT; - - *value = result; - return 0; -} - -static int memory_set_cur_bandwidth(struct thermal_cooling_device *cdev, - unsigned long state) -{ - struct acpi_device *device = cdev->devdata; - acpi_handle handle = device->handle; - struct acpi_object_list arg_list; - union acpi_object arg; - acpi_status status; - unsigned long long temp; - unsigned long max_state; - - if (memory_get_max_bandwidth(cdev, &max_state)) - return -EFAULT; - - if (state > max_state) - return -EINVAL; - - arg_list.count = 1; - arg_list.pointer = &arg; - arg.type = ACPI_TYPE_INTEGER; - arg.integer.value = state; - - status = - acpi_evaluate_integer(handle, MEMORY_SET_BANDWIDTH, &arg_list, - &temp); - - pr_info("Bandwidth value was %ld: status is %d\n", state, status); - if (ACPI_FAILURE(status)) - return -EFAULT; - - return 0; -} - -static const struct thermal_cooling_device_ops memory_cooling_ops = { - .get_max_state = memory_get_max_bandwidth, - .get_cur_state = memory_get_cur_bandwidth, - .set_cur_state = memory_set_cur_bandwidth, -}; - -/* - * Memory Device Management - */ -static int intel_menlow_memory_add(struct acpi_device *device) -{ - int result = -ENODEV; - struct thermal_cooling_device *cdev; - - if (!device) - return -EINVAL; - - if (!acpi_has_method(device->handle, MEMORY_GET_BANDWIDTH)) - goto end; - - if (!acpi_has_method(device->handle, MEMORY_SET_BANDWIDTH)) - goto end; - - cdev = thermal_cooling_device_register("Memory controller", device, - &memory_cooling_ops); - if (IS_ERR(cdev)) { - result = PTR_ERR(cdev); - goto end; - } - - device->driver_data = cdev; - result = sysfs_create_link(&device->dev.kobj, - &cdev->device.kobj, "thermal_cooling"); - if (result) - goto unregister; - - result = sysfs_create_link(&cdev->device.kobj, - &device->dev.kobj, "device"); - if (result) { - sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); - goto unregister; - } - - end: - return result; - - unregister: - thermal_cooling_device_unregister(cdev); - return result; - -} - -static void intel_menlow_memory_remove(struct acpi_device *device) -{ - struct thermal_cooling_device *cdev; - - if (!device) - return; - - cdev = acpi_driver_data(device); - if (!cdev) - return; - - sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); - sysfs_remove_link(&cdev->device.kobj, "device"); - thermal_cooling_device_unregister(cdev); -} - -static const struct acpi_device_id intel_menlow_memory_ids[] = { - {"INT0002", 0}, - {"", 0}, -}; - -static struct acpi_driver intel_menlow_memory_driver = { - .name = "intel_menlow_thermal_control", - .ids = intel_menlow_memory_ids, - .ops = { - .add = intel_menlow_memory_add, - .remove = intel_menlow_memory_remove, - }, -}; - -/* - * Sensor control on menlow platform - */ - -#define THERMAL_AUX0 0 -#define THERMAL_AUX1 1 -#define GET_AUX0 "GAX0" -#define GET_AUX1 "GAX1" -#define SET_AUX0 "SAX0" -#define SET_AUX1 "SAX1" - -struct intel_menlow_attribute { - struct device_attribute attr; - struct device *device; - acpi_handle handle; - struct list_head node; -}; - -static LIST_HEAD(intel_menlow_attr_list); -static DEFINE_MUTEX(intel_menlow_attr_lock); - -/* - * sensor_get_auxtrip - get the current auxtrip value from sensor - * @handle: Object handle - * @index : GET_AUX1/GET_AUX0 - * @value : The address will be fill by the value - */ -static int sensor_get_auxtrip(acpi_handle handle, int index, - unsigned long long *value) -{ - acpi_status status; - - if ((index != 0 && index != 1) || !value) - return -EINVAL; - - status = acpi_evaluate_integer(handle, index ? GET_AUX1 : GET_AUX0, - NULL, value); - if (ACPI_FAILURE(status)) - return -EIO; - - return 0; -} - -/* - * sensor_set_auxtrip - set the new auxtrip value to sensor - * @handle: Object handle - * @index : GET_AUX1/GET_AUX0 - * @value : The value will be set - */ -static int sensor_set_auxtrip(acpi_handle handle, int index, int value) -{ - acpi_status status; - union acpi_object arg = { - ACPI_TYPE_INTEGER - }; - struct acpi_object_list args = { - 1, &arg - }; - unsigned long long temp; - - if (index != 0 && index != 1) - return -EINVAL; - - status = acpi_evaluate_integer(handle, index ? GET_AUX0 : GET_AUX1, - NULL, &temp); - if (ACPI_FAILURE(status)) - return -EIO; - if ((index && value < temp) || (!index && value > temp)) - return -EINVAL; - - arg.integer.value = value; - status = acpi_evaluate_integer(handle, index ? SET_AUX1 : SET_AUX0, - &args, &temp); - if (ACPI_FAILURE(status)) - return -EIO; - - /* do we need to check the return value of SAX0/SAX1 ? */ - - return 0; -} - -#define to_intel_menlow_attr(_attr) \ - container_of(_attr, struct intel_menlow_attribute, attr) - -static ssize_t aux_show(struct device *dev, struct device_attribute *dev_attr, - char *buf, int idx) -{ - struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr); - unsigned long long value; - int result; - - result = sensor_get_auxtrip(attr->handle, idx, &value); - if (result) - return result; - - return sprintf(buf, "%lu", deci_kelvin_to_celsius(value)); -} - -static ssize_t aux0_show(struct device *dev, - struct device_attribute *dev_attr, char *buf) -{ - return aux_show(dev, dev_attr, buf, 0); -} - -static ssize_t aux1_show(struct device *dev, - struct device_attribute *dev_attr, char *buf) -{ - return aux_show(dev, dev_attr, buf, 1); -} - -static ssize_t aux_store(struct device *dev, struct device_attribute *dev_attr, - const char *buf, size_t count, int idx) -{ - struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr); - int value; - int result; - - /*Sanity check; should be a positive integer */ - if (!sscanf(buf, "%d", &value)) - return -EINVAL; - - if (value < 0) - return -EINVAL; - - result = sensor_set_auxtrip(attr->handle, idx, - celsius_to_deci_kelvin(value)); - return result ? result : count; -} - -static ssize_t aux0_store(struct device *dev, - struct device_attribute *dev_attr, - const char *buf, size_t count) -{ - return aux_store(dev, dev_attr, buf, count, 0); -} - -static ssize_t aux1_store(struct device *dev, - struct device_attribute *dev_attr, - const char *buf, size_t count) -{ - return aux_store(dev, dev_attr, buf, count, 1); -} - -/* BIOS can enable/disable the thermal user application in dabney platform */ -#define BIOS_ENABLED "\\_TZ.GSTS" -static ssize_t bios_enabled_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - acpi_status status; - unsigned long long bios_enabled; - - status = acpi_evaluate_integer(NULL, BIOS_ENABLED, NULL, &bios_enabled); - if (ACPI_FAILURE(status)) - return -ENODEV; - - return sprintf(buf, "%s\n", bios_enabled ? "enabled" : "disabled"); -} - -static int intel_menlow_add_one_attribute(char *name, umode_t mode, void *show, - void *store, struct device *dev, - acpi_handle handle) -{ - struct intel_menlow_attribute *attr; - int result; - - attr = kzalloc(sizeof(struct intel_menlow_attribute), GFP_KERNEL); - if (!attr) - return -ENOMEM; - - sysfs_attr_init(&attr->attr.attr); /* That is consistent naming :D */ - attr->attr.attr.name = name; - attr->attr.attr.mode = mode; - attr->attr.show = show; - attr->attr.store = store; - attr->device = dev; - attr->handle = handle; - - result = device_create_file(dev, &attr->attr); - if (result) { - kfree(attr); - return result; - } - - mutex_lock(&intel_menlow_attr_lock); - list_add_tail(&attr->node, &intel_menlow_attr_list); - mutex_unlock(&intel_menlow_attr_lock); - - return 0; -} - -static acpi_status intel_menlow_register_sensor(acpi_handle handle, u32 lvl, - void *context, void **rv) -{ - acpi_status status; - acpi_handle dummy; - struct thermal_zone_device *thermal; - int result; - - result = acpi_bus_get_private_data(handle, (void **)&thermal); - if (result) - return 0; - - /* _TZ must have the AUX0/1 methods */ - status = acpi_get_handle(handle, GET_AUX0, &dummy); - if (ACPI_FAILURE(status)) - return (status == AE_NOT_FOUND) ? AE_OK : status; - - status = acpi_get_handle(handle, SET_AUX0, &dummy); - if (ACPI_FAILURE(status)) - return (status == AE_NOT_FOUND) ? AE_OK : status; - - result = intel_menlow_add_one_attribute("aux0", 0644, - aux0_show, aux0_store, - &thermal->device, handle); - if (result) - return AE_ERROR; - - status = acpi_get_handle(handle, GET_AUX1, &dummy); - if (ACPI_FAILURE(status)) - goto aux1_not_found; - - status = acpi_get_handle(handle, SET_AUX1, &dummy); - if (ACPI_FAILURE(status)) - goto aux1_not_found; - - result = intel_menlow_add_one_attribute("aux1", 0644, - aux1_show, aux1_store, - &thermal->device, handle); - if (result) { - intel_menlow_unregister_sensor(); - return AE_ERROR; - } - - /* - * create the "dabney_enabled" attribute which means the user app - * should be loaded or not - */ - - result = intel_menlow_add_one_attribute("bios_enabled", 0444, - bios_enabled_show, NULL, - &thermal->device, handle); - if (result) { - intel_menlow_unregister_sensor(); - return AE_ERROR; - } - - return AE_OK; - - aux1_not_found: - if (status == AE_NOT_FOUND) - return AE_OK; - - intel_menlow_unregister_sensor(); - return status; -} - -static void intel_menlow_unregister_sensor(void) -{ - struct intel_menlow_attribute *pos, *next; - - mutex_lock(&intel_menlow_attr_lock); - list_for_each_entry_safe(pos, next, &intel_menlow_attr_list, node) { - list_del(&pos->node); - device_remove_file(pos->device, &pos->attr); - kfree(pos); - } - mutex_unlock(&intel_menlow_attr_lock); - - return; -} - -static int __init intel_menlow_module_init(void) -{ - int result = -ENODEV; - acpi_status status; - unsigned long long enable; - - if (acpi_disabled) - return result; - - /* Looking for the \_TZ.GSTS method */ - status = acpi_evaluate_integer(NULL, BIOS_ENABLED, NULL, &enable); - if (ACPI_FAILURE(status) || !enable) - return -ENODEV; - - /* Looking for ACPI device MEM0 with hardware id INT0002 */ - result = acpi_bus_register_driver(&intel_menlow_memory_driver); - if (result) - return result; - - /* Looking for sensors in each ACPI thermal zone */ - status = acpi_walk_namespace(ACPI_TYPE_THERMAL, ACPI_ROOT_OBJECT, - ACPI_UINT32_MAX, - intel_menlow_register_sensor, NULL, NULL, NULL); - if (ACPI_FAILURE(status)) { - acpi_bus_unregister_driver(&intel_menlow_memory_driver); - return -ENODEV; - } - - return 0; -} - -static void __exit intel_menlow_module_exit(void) -{ - acpi_bus_unregister_driver(&intel_menlow_memory_driver); - intel_menlow_unregister_sensor(); -} - -module_init(intel_menlow_module_init); -module_exit(intel_menlow_module_exit); -- GitLab From 91048ce4227868000bfe624707e42274ef2198aa Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 19 Apr 2023 17:39:41 +0300 Subject: [PATCH 4221/5631] intel_idle: use pr_info() instead of printk() Substitute 'printk()' with 'pr_info()', because 'intel_idle' already uses 'pr_debug()', so using 'pr_info()' will be more consistent. In addition to this, this patch addresses the following checkpatch.pl warning: WARNING: printk() should include KERN_ facility level Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 938c17f25d94..726a361da422 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1895,7 +1895,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) drv->states[drv->state_count] = cpuidle_state_table[cstate]; if ((cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { - printk("intel_idle: forced intel_idle_irq for state %d\n", cstate); + pr_info("forced intel_idle_irq for state %d\n", cstate); drv->states[drv->state_count].enter = intel_idle_irq; } -- GitLab From a78032e94bf16e9c53238cd83c82095b4a251d4b Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 20 Apr 2023 09:47:18 +0300 Subject: [PATCH 4222/5631] intel_idle: clean up intel_idle_init_cstates_icpu() The intel_idle_init_cstates_icpu() function includes a loop that iterates over every C-state. Inside the loop, the same C-state data is referenced 2 ways: 1. as cpuidle_state_table[cstate] 2. as drv->states[drv->state_count] (but it is a copy of #1, not the same object). Make the code be more consistent and easier to read by using only the 2nd way. So the code structure would be as follows: 1. Use cpuidle_state_table[cstate] 2. Copy cpuidle_state_table[cstate] to drv->states[drv->state_count] 3. Use only drv->states[drv->state_count] from this point. Note, this change introduces a checkpatch.pl warning (too long line), but it will be addressed in the next patch. Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 726a361da422..190410fc9ce5 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1894,24 +1894,24 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) /* Structure copy. */ drv->states[drv->state_count] = cpuidle_state_table[cstate]; - if ((cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { + if ((drv->states[drv->state_count].flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { pr_info("forced intel_idle_irq for state %d\n", cstate); drv->states[drv->state_count].enter = intel_idle_irq; } if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && - cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IBRS) { - WARN_ON_ONCE(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_IRQ_ENABLE); + drv->states[drv->state_count].flags & CPUIDLE_FLAG_IBRS) { + WARN_ON_ONCE(drv->states[drv->state_count].flags & CPUIDLE_FLAG_IRQ_ENABLE); drv->states[drv->state_count].enter = intel_idle_ibrs; } - if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_INIT_XSTATE) + if (drv->states[drv->state_count].flags & CPUIDLE_FLAG_INIT_XSTATE) drv->states[drv->state_count].enter = intel_idle_xstate; if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && intel_idle_off_by_default(mwait_hint) && - !(cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) + !(drv->states[drv->state_count].flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF; if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count])) -- GitLab From 1abffbd827668b3b44c34b168ccb5ee2866714a8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 19 Apr 2023 17:39:43 +0300 Subject: [PATCH 4223/5631] intel_idle: further intel_idle_init_cstates_icpu() cleanup Introduce a temporary 'state' variable for referencing the currently processed C-state in the intel_idle_init_cstates_icpu() function. This makes code lines shorter and easier to read. Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 190410fc9ce5..73ddb1d8cfcf 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1871,6 +1871,7 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) } for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { + struct cpuidle_state *state; unsigned int mwait_hint; if (intel_idle_max_cstate_reached(cstate)) @@ -1893,29 +1894,30 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) /* Structure copy. */ drv->states[drv->state_count] = cpuidle_state_table[cstate]; + state = &drv->states[drv->state_count]; - if ((drv->states[drv->state_count].flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { + if ((state->flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { pr_info("forced intel_idle_irq for state %d\n", cstate); - drv->states[drv->state_count].enter = intel_idle_irq; + state->enter = intel_idle_irq; } if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && - drv->states[drv->state_count].flags & CPUIDLE_FLAG_IBRS) { - WARN_ON_ONCE(drv->states[drv->state_count].flags & CPUIDLE_FLAG_IRQ_ENABLE); - drv->states[drv->state_count].enter = intel_idle_ibrs; + state->flags & CPUIDLE_FLAG_IBRS) { + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); + state->enter = intel_idle_ibrs; } - if (drv->states[drv->state_count].flags & CPUIDLE_FLAG_INIT_XSTATE) - drv->states[drv->state_count].enter = intel_idle_xstate; + if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) + state->enter = intel_idle_xstate; if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && intel_idle_off_by_default(mwait_hint) && - !(drv->states[drv->state_count].flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) - drv->states[drv->state_count].flags |= CPUIDLE_FLAG_OFF; + !(state->flags & CPUIDLE_FLAG_ALWAYS_ENABLE))) + state->flags |= CPUIDLE_FLAG_OFF; - if (intel_idle_state_needs_timer_stop(&drv->states[drv->state_count])) - drv->states[drv->state_count].flags |= CPUIDLE_FLAG_TIMER_STOP; + if (intel_idle_state_needs_timer_stop(state)) + state->flags |= CPUIDLE_FLAG_TIMER_STOP; drv->state_count++; } -- GitLab From 00433eae1771d355f20c152ddc5976baedb427e2 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 19 Apr 2023 17:39:44 +0300 Subject: [PATCH 4224/5631] intel_idle: improve C-state flags handling robustness The following C-state flags are currently mutually-exclusive and should not be combined: * IRQ_ENABLE * IBRS * XSTATE There is a warning for the situation when the IRQ_ENABLE flag is combined with the IBRS flag, but no warnings for other combinations. This is inconsistent and prone to errors. Improve the situation by adding warnings for all the unexpected combinations. Add a couple of helpful commentaries too. Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 73ddb1d8cfcf..1de36df15d5a 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1896,20 +1896,28 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) drv->states[drv->state_count] = cpuidle_state_table[cstate]; state = &drv->states[drv->state_count]; - if ((state->flags & CPUIDLE_FLAG_IRQ_ENABLE) || force_irq_on) { - pr_info("forced intel_idle_irq for state %d\n", cstate); - state->enter = intel_idle_irq; - } - - if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && - state->flags & CPUIDLE_FLAG_IBRS) { + if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) { + /* + * Combining with XSTATE with IBRS or IRQ_ENABLE flags + * is not currently supported but this driver. + */ + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IBRS); + WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); + state->enter = intel_idle_xstate; + } else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) && + state->flags & CPUIDLE_FLAG_IBRS) { + /* + * IBRS mitigation requires that C-states are entered + * with interrupts disabled. + */ WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); state->enter = intel_idle_ibrs; + } else if ((state->flags & CPUIDLE_FLAG_IRQ_ENABLE) || + force_irq_on) { + pr_info("forced intel_idle_irq for state %d\n", cstate); + state->enter = intel_idle_irq; } - if (state->flags & CPUIDLE_FLAG_INIT_XSTATE) - state->enter = intel_idle_xstate; - if ((disabled_states_mask & BIT(drv->state_count)) || ((icpu->use_acpi || force_use_acpi) && intel_idle_off_by_default(mwait_hint) && -- GitLab From db1ae0c99950502d10e09d0c57ed1e16cd854b20 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 19 Apr 2023 17:39:45 +0300 Subject: [PATCH 4225/5631] intel_idle: fix confusing message By default, all non-POLL C-states are entered with interrupts disabled. There are 2 ways to make 'intel_idle' enter C-states with interrupts enabled: 1. Mark the C-state with the CPUIDLE_FLAG_IRQ_ENABLE flag. 2. Use the force_irq_on module parameter. The former is the "proper" way of doing it, it is per-C-state and per-platform. The latter is for debugging purposes only. The problem is that intel_idle prints the "forced intel_idle_irq" message in both cases, even though the former case does not needed this message, because nothing is forced there. This patch addresses the problem. Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 1de36df15d5a..bff0d17aeda4 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1912,8 +1912,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) */ WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE); state->enter = intel_idle_ibrs; - } else if ((state->flags & CPUIDLE_FLAG_IRQ_ENABLE) || - force_irq_on) { + } else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) { + state->enter = intel_idle_irq; + } else if (force_irq_on) { pr_info("forced intel_idle_irq for state %d\n", cstate); state->enter = intel_idle_irq; } -- GitLab From 4152379a701ad66b6c4e1c9fc93704d993e49615 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Thu, 20 Apr 2023 09:47:21 +0300 Subject: [PATCH 4226/5631] intel_idle: do not sprinkle module parameter definitions around This is a cleanup which improves code consistency. Move the force_irq_on module parameter variable and definition to the same place where we have variables and definitions for other module parameters. Signed-off-by: Artem Bityutskiy Reviewed-by: Zhang Rui Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index bff0d17aeda4..35bd284f7763 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -68,6 +68,7 @@ static struct cpuidle_driver intel_idle_driver = { static int max_cstate = CPUIDLE_STATE_MAX - 1; static unsigned int disabled_states_mask; static unsigned int preferred_states_mask; +static bool force_irq_on __read_mostly; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; @@ -1838,9 +1839,6 @@ static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) return true; } -static bool force_irq_on __read_mostly; -module_param(force_irq_on, bool, 0444); - static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) { int cstate; @@ -2157,3 +2155,9 @@ MODULE_PARM_DESC(states_off, "Mask of disabled idle states"); */ module_param_named(preferred_cstates, preferred_states_mask, uint, 0444); MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states"); +/* + * Debugging option that forces the driver to enter all C-states with + * interrupts enabled. Does not apply to C-states with + * 'CPUIDLE_FLAG_INIT_XSTATE' and 'CPUIDLE_FLAG_IBRS' flags. + */ +module_param(force_irq_on, bool, 0444); -- GitLab From bd4468295e7a335319c10affdf594b56f1e6c0a4 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 19 Apr 2023 17:39:47 +0300 Subject: [PATCH 4227/5631] intel_idle: mark few variables as __read_mostly The intention is to clean up the code and make it look a bit more consistent. Mark all unitialized module parameter variables as __read_mostly, not just one of them. The other parameters are read-mostly too. Signed-off-by: Artem Bityutskiy Signed-off-by: Rafael J. Wysocki --- drivers/idle/intel_idle.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 35bd284f7763..aa2d19db2b1d 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -66,8 +66,8 @@ static struct cpuidle_driver intel_idle_driver = { }; /* intel_idle.max_cstate=0 disables driver */ static int max_cstate = CPUIDLE_STATE_MAX - 1; -static unsigned int disabled_states_mask; -static unsigned int preferred_states_mask; +static unsigned int disabled_states_mask __read_mostly; +static unsigned int preferred_states_mask __read_mostly; static bool force_irq_on __read_mostly; static struct cpuidle_device __percpu *intel_idle_cpuidle_devices; -- GitLab From 0175ab610c2df7c21d93e4bd63b4e67cfa86737c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 22 Apr 2023 21:47:20 -0700 Subject: [PATCH 4228/5631] mm/khugepaged: fix conflicting mods to collapse_file() Inserting Ivan Orlov's syzbot fix commit 2ce0bdfebc74 ("mm: khugepaged: fix kernel BUG in hpage_collapse_scan_file()") ahead of Jiaqi Yan's and David Stevens's commits 12904d953364 ("mm/khugepaged: recover from poisoned file-backed memory") cae106dd67b9 ("mm/khugepaged: refactor collapse_file control flow") ac492b9c70ca ("mm/khugepaged: skip shmem with userfaultfd") (all of which restructure collapse_file()) did not work out well. xfstests generic/086 on huge tmpfs (with accelerated khugepaged) freezes (if not on the first attempt, then the 2nd or 3rd) in find_lock_entries() while doing drop_caches: the file's xarray seems to have been corrupted, with find_get_entry() returning nonsense which makes no progress. Bisection led to ac492b9c70ca; and diff against earlier working linux-next suggested that it's probably down to an errant xas_store(), which does not belong with the later changes (and nor does the positioning of warnings). The later changes look as if they fix the syzbot issue independently. Remove most of what's left of 2ce0bdfebc74: just leave one WARN_ON_ONCE (xas_error) after the final xas_store() of the multi-index entry. Link: https://lkml.kernel.org/r/b6c881-c352-bb91-85a8-febeb09dfd71@google.com Signed-off-by: Hugh Dickins Cc: David Stevens Cc: Ivan Orlov Cc: Jiaqi Yan Signed-off-by: Andrew Morton --- mm/khugepaged.c | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index d72e74e007fc..6b9d39d65b73 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1941,16 +1941,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, result = SCAN_FAIL; goto xa_locked; } - xas_store(&xas, hpage); - if (xas_error(&xas)) { - /* revert shmem_charge performed - * in the previous condition - */ - mapping->nrpages--; - shmem_uncharge(mapping->host, 1); - result = SCAN_STORE_FAILED; - goto xa_locked; - } nr_none++; continue; } @@ -2105,13 +2095,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, * Accumulate the pages that are being collapsed. */ list_add_tail(&page->lru, &pagelist); - - /* - * We can't get an ENOMEM here (because the allocation happened - * before) but let's check for errors (XArray implementation - * can be changed in the future) - */ - WARN_ON_ONCE(xas_error(&xas)); continue; out_unlock: unlock_page(page); @@ -2134,11 +2117,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } } - /* Here we can't get an ENOMEM (because entries were - * previously allocated) But let's check for errors - * (XArray implementation can be changed in the future) - */ - WARN_ON_ONCE(xas_error(&xas)); xa_locked: xas_unlock_irq(&xas); xa_unlocked: @@ -2259,6 +2237,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, hpage); + WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* -- GitLab From 01106e140835ff94fdef79d66f166b87b0c89824 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 20 Apr 2023 10:57:43 +0200 Subject: [PATCH 4229/5631] shmem: restrict noswap option to initial user namespace Prevent tmpfs instances mounted in an unprivileged namespaces from evading accounting of locked memory by using the "noswap" mount option. Link: https://lkml.kernel.org/r/20230420-faxen-advokat-40abb4c1a152@brauner Signed-off-by: Christian Brauner Reported-by: Hugh Dickins Link: https://lore.kernel.org/lkml/79eae9fe-7818-a65c-89c6-138b55d609a@google.com Reviewed-by: Luis Chamberlain Cc: Adam Manzanares Cc: Davidlohr Bueso Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Pankaj Raghav Cc: Yosry Ahmed Signed-off-by: Andrew Morton --- mm/shmem.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/mm/shmem.c b/mm/shmem.c index 3531ebb3494e..1a6263f54ada 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3582,6 +3582,10 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) ctx->seen |= SHMEM_SEEN_INUMS; break; case Opt_noswap: + if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) { + return invalfc(fc, + "Turning off swap in unprivileged tmpfs mounts unsupported"); + } ctx->noswap = true; ctx->seen |= SHMEM_SEEN_NOSWAP; break; -- GitLab From 4d4b6d66db63ceed399f1fb1a4b24081d2590eb1 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 24 Apr 2023 14:54:08 +0800 Subject: [PATCH 4230/5631] mm,unmap: avoid flushing TLB in batch if PTE is inaccessible 0Day/LKP reported a performance regression for commit 7e12beb8ca2a ("migrate_pages: batch flushing TLB"). In the commit, the TLB flushing during page migration is batched. So, in try_to_migrate_one(), ptep_clear_flush() is replaced with set_tlb_ubc_flush_pending(). In further investigation, it is found that the TLB flushing can be avoided in ptep_clear_flush() if the PTE is inaccessible. In fact, we can optimize in similar way for the batched TLB flushing too to improve the performance. So in this patch, we check pte_accessible() before set_tlb_ubc_flush_pending() in try_to_unmap/migrate_one(). Tests show that the benchmark score of the anon-cow-rand-mt test case of vm-scalability test suite can improve up to 2.1% with the patch on a Intel server machine. The TLB flushing IPI can reduce up to 44.3%. Link: https://lore.kernel.org/oe-lkp/202303192325.ecbaf968-yujie.liu@intel.com Link: https://lore.kernel.org/oe-lkp/ab92aaddf1b52ede15e2c608696c36765a2602c1.camel@intel.com/ Link: https://lkml.kernel.org/r/20230424065408.188498-1-ying.huang@intel.com Fixes: 7e12beb8ca2a ("migrate_pages: batch flushing TLB") Signed-off-by: "Huang, Ying" Reported-by: kernel test robot Reviewed-by: Nadav Amit Reviewed-by: Xin Hao Cc: Mel Gorman Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: David Hildenbrand Signed-off-by: Andrew Morton --- mm/rmap.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index ba901c416785..19392e090bec 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -642,10 +642,14 @@ void try_to_unmap_flush_dirty(void) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; + bool writable = pte_dirty(pteval); + + if (!pte_accessible(mm, pteval)) + return; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; @@ -729,7 +733,7 @@ void flush_tlb_batched_pending(struct mm_struct *mm) } } #else -static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) +static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval) { } @@ -1580,7 +1584,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); - set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + set_tlb_ubc_flush_pending(mm, pteval); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } @@ -1961,7 +1965,7 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); - set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); + set_tlb_ubc_flush_pending(mm, pteval); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } -- GitLab From 4f20b7471c57032860065591a17efd3325216bde Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 21 Apr 2023 16:54:24 +0200 Subject: [PATCH 4231/5631] libgcc: add forward declarations for generic library routines With W=1 on platforms that use the generic gcc library routines (csky/loongarch/mips/riscv/sh/xtensa): lib/ashldi3.c:9:19: warning: no previous prototype for '__ashldi3' [-Wmissing-prototypes] 9 | long long notrace __ashldi3(long long u, word_type b) | ^~~~~~~~~ CC lib/ashrdi3.o lib/ashrdi3.c:9:19: warning: no previous prototype for '__ashrdi3' [-Wmissing-prototypes] 9 | long long notrace __ashrdi3(long long u, word_type b) | ^~~~~~~~~ CC lib/cmpdi2.o lib/cmpdi2.c:9:19: warning: no previous prototype for '__cmpdi2' [-Wmissing-prototypes] 9 | word_type notrace __cmpdi2(long long a, long long b) | ^~~~~~~~ CC lib/lshrdi3.o lib/lshrdi3.c:9:19: warning: no previous prototype for '__lshrdi3' [-Wmissing-prototypes] 9 | long long notrace __lshrdi3(long long u, word_type b) | ^~~~~~~~~ CC lib/muldi3.o lib/muldi3.c:49:19: warning: no previous prototype for '__muldi3' [-Wmissing-prototypes] 49 | long long notrace __muldi3(long long u, long long v) | ^~~~~~~~ CC lib/ucmpdi2.o lib/ucmpdi2.c:8:19: warning: no previous prototype for '__ucmpdi2' [-Wmissing-prototypes] 8 | word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b) | ^~~~~~~~~ Fix this by adding forward declarations to the common libgcc header file. Link: https://lkml.kernel.org/r/5cdbe08296693dd53849f199c3933e16e97b33c1.1682088593.git.geert+renesas@glider.be Signed-off-by: Geert Uytterhoeven Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202303272214.RxzpA6bP-lkp@intel.com/ Acked-by: Arnd Bergmann Cc: Chris Zankel Cc: Max Filippov Signed-off-by: Andrew Morton --- include/linux/libgcc.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index b8dc75f0c830..fc388da6a027 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -27,4 +27,11 @@ typedef union { long long ll; } DWunion; +long long notrace __ashldi3(long long u, word_type b); +long long notrace __ashrdi3(long long u, word_type b); +word_type notrace __cmpdi2(long long a, long long b); +long long notrace __lshrdi3(long long u, word_type b); +long long notrace __muldi3(long long u, long long v); +word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); + #endif /* __ASM_LIBGCC_H */ -- GitLab From d88f2f72ca89ead8743ee15e547274ba248e7c59 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 24 Apr 2023 17:01:32 +1000 Subject: [PATCH 4232/5631] mailmap: add entries for Paul Mackerras Link: https://lkml.kernel.org/r/ZEYpTAufVHTvsO1n@cleo Signed-off-by: Paul Mackerras Signed-off-by: Andrew Morton --- .mailmap | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.mailmap b/.mailmap index 0d8940d37bf4..347d47e27da2 100644 --- a/.mailmap +++ b/.mailmap @@ -370,6 +370,8 @@ Paul E. McKenney Paul E. McKenney Paul E. McKenney Paul E. McKenney +Paul Mackerras +Paul Mackerras Peter A Jonsson Peter Oruba Peter Oruba -- GitLab From b413281876292de44ae84e9a9ce9d62e47f266e9 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Mon, 24 Apr 2023 12:38:46 +0100 Subject: [PATCH 4233/5631] of: fdt: Scan /memreserve/ last Change the scanning /memreserve/ and /reserved-memory node order to fix Kernel panic on Khadas Vim3 Board. If /memreserve/ goes first, the memory is reserved, but nomap can't be applied to the region. So the memory won't be used by Linux, but it is still present in the linear map as normal memory, which allows speculation. Legitimate access to adjacent pages will cause the CPU to end up prefetching into them leading to Kernel panic. So /reserved-memory node should go first, as it has a more updated description of the memory regions and can apply flags, like nomap. Link: https://lore.kernel.org/all/CAJX_Q+1Tjc+-TjZ6JW9X0NxEdFe=82a9626yL63j7uVD4LpxEA@mail.gmail.com/ Signed-off-by: Lucas Tanure Link: https://lore.kernel.org/r/20230424113846.46382-1-tanure@linux.com Signed-off-by: Rob Herring --- drivers/of/fdt.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index d1a68b6d03b3..c28aedd7ae1f 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -635,6 +635,9 @@ void __init early_init_fdt_scan_reserved_mem(void) if (!initial_boot_params) return; + fdt_scan_reserved_mem(); + fdt_reserve_elfcorehdr(); + /* Process header /memreserve/ fields */ for (n = 0; ; n++) { fdt_get_mem_rsv(initial_boot_params, n, &base, &size); @@ -643,8 +646,6 @@ void __init early_init_fdt_scan_reserved_mem(void) memblock_reserve(base, size); } - fdt_scan_reserved_mem(); - fdt_reserve_elfcorehdr(); fdt_init_reserved_mem(); } -- GitLab From 110ccfa9dd6ca1272e50fbea614aa31f01d2c17e Mon Sep 17 00:00:00 2001 From: Enrico Belleri Date: Thu, 27 Apr 2023 21:16:45 +0200 Subject: [PATCH 4234/5631] ASoC: amd: yc: Add ASUS M3402RA into DMI table Fix builtin microphone on ASUS Vivobook S 14 OLED 2022 (M3402RA) Same issue with this model as apparently with other Rembrandt laptops: https://bugzilla.kernel.org/show_bug.cgi?id=216270 Signed-off-by: Enrico Belleri Link: https://lore.kernel.org/r/20230427191645.24519-1-kilgore.trout@idesmi.eu Signed-off-by: Mark Brown --- sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index b9958e555367..69b363dd0d10 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -227,6 +227,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M3402RA"), + } + }, { .driver_data = &acp6x_card, .matches = { -- GitLab From 3302212f0384ab286b65683bc340f3953f88f70a Mon Sep 17 00:00:00 2001 From: Philippe De Muyter Date: Wed, 26 Apr 2023 21:33:02 +0200 Subject: [PATCH 4235/5631] regulator: consumer.rst: fix 'regulator_enable' typo. Removing an erroneous 'd' at the end of 'regulator_enable'. Signed-off-by: Philippe De Muyter Cc: Liam Girdwood Cc: Mark Brown Link: https://lore.kernel.org/r/1682537582-2314-1-git-send-email-Philippe.DeMuyter@macq.eu Signed-off-by: Mark Brown --- Documentation/power/regulator/consumer.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/power/regulator/consumer.rst b/Documentation/power/regulator/consumer.rst index 0cd8cc1275a7..85c2bf5ac07e 100644 --- a/Documentation/power/regulator/consumer.rst +++ b/Documentation/power/regulator/consumer.rst @@ -41,7 +41,7 @@ A consumer can enable its power supply by calling:: int regulator_enable(regulator); NOTE: - The supply may already be enabled before regulator_enabled() is called. + The supply may already be enabled before regulator_enable() is called. This may happen if the consumer shares the regulator or the regulator has been previously enabled by bootloader or kernel board initialization code. -- GitLab From 67df5ce9dd8870d3e53de5ebd6aecf609b713044 Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Thu, 30 Mar 2023 14:15:32 +0800 Subject: [PATCH 4236/5631] i3c: dw: Return the length from a read priv_xfer We currently assume that the rx_len of a read command will be as submitted, but we may have a shorter read than expected. This change populates the output i3c xfer length from the actually-read length. Signed-off-by: Matt Johnston Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/f4fff7ab18dee1f662dc7a5a4111fcd921e6792b.1680156630.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 61ad03c4c2c9..e95d73e71574 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -887,6 +887,13 @@ static int dw_i3c_master_priv_xfers(struct i3c_dev_desc *dev, if (!wait_for_completion_timeout(&xfer->comp, XFER_TIMEOUT)) dw_i3c_master_dequeue_xfer(master, xfer); + for (i = 0; i < i3c_nxfers; i++) { + struct dw_i3c_cmd *cmd = &xfer->cmds[i]; + + if (i3c_xfers[i].rnw) + i3c_xfers[i].len = cmd->rx_len; + } + ret = xfer->ret; dw_i3c_master_free_xfer(xfer); -- GitLab From 66b32e3d2c6daeeafb80fa41f3a41e4c0ab85cc6 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 14:15:33 +0800 Subject: [PATCH 4237/5631] i3c: dw: use bus mode rather than device reg for conditional tCAS setting In the clock setup path, we set the hardware DEV_CTRL_I2C_SLAVE_PRESENT bit on a shared mode bus, then read-back this bit for the conditional tCAS set. Instead, just use the bus->mode setting for the conditional test. While we're at it, add a little comment about why the conditional is there. Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/92a933566f7846708a00ad7f5a16ee8e6ed32d0e.1680156630.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index e95d73e71574..9ae2e5b2723f 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -538,7 +538,11 @@ static int dw_i3c_clk_cfg(struct dw_i3c_master *master) scl_timing = SCL_I3C_TIMING_HCNT(hcnt) | SCL_I3C_TIMING_LCNT(lcnt); writel(scl_timing, master->regs + SCL_I3C_PP_TIMING); - if (!(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_I2C_SLAVE_PRESENT)) + /* + * In pure i3c mode, MST_FREE represents tCAS. In shared mode, this + * will be set up by dw_i2c_clk_cfg as tLOW. + */ + if (master->base.bus.mode == I3C_BUS_MODE_PURE) writel(BUS_I3C_MST_FREE(lcnt), master->regs + BUS_FREE_TIMING); lcnt = max_t(u8, -- GitLab From 675751bb20634f981498c7d66161584080cc061e Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 27 Apr 2023 17:59:20 +0200 Subject: [PATCH 4238/5631] ring-buffer: Sync IRQ works before buffer destruction If something was written to the buffer just before destruction, it may be possible (maybe not in a real system, but it did happen in ARCH=um with time-travel) to destroy the ringbuffer before the IRQ work ran, leading this KASAN report (or a crash without KASAN): BUG: KASAN: slab-use-after-free in irq_work_run_list+0x11a/0x13a Read of size 8 at addr 000000006d640a48 by task swapper/0 CPU: 0 PID: 0 Comm: swapper Tainted: G W O 6.3.0-rc1 #7 Stack: 60c4f20f 0c203d48 41b58ab3 60f224fc 600477fa 60f35687 60c4f20f 601273dd 00000008 6101eb00 6101eab0 615be548 Call Trace: [<60047a58>] show_stack+0x25e/0x282 [<60c609e0>] dump_stack_lvl+0x96/0xfd [<60c50d4c>] print_report+0x1a7/0x5a8 [<603078d3>] kasan_report+0xc1/0xe9 [<60308950>] __asan_report_load8_noabort+0x1b/0x1d [<60232844>] irq_work_run_list+0x11a/0x13a [<602328b4>] irq_work_tick+0x24/0x34 [<6017f9dc>] update_process_times+0x162/0x196 [<6019f335>] tick_sched_handle+0x1a4/0x1c3 [<6019fd9e>] tick_sched_timer+0x79/0x10c [<601812b9>] __hrtimer_run_queues.constprop.0+0x425/0x695 [<60182913>] hrtimer_interrupt+0x16c/0x2c4 [<600486a3>] um_timer+0x164/0x183 [...] Allocated by task 411: save_stack_trace+0x99/0xb5 stack_trace_save+0x81/0x9b kasan_save_stack+0x2d/0x54 kasan_set_track+0x34/0x3e kasan_save_alloc_info+0x25/0x28 ____kasan_kmalloc+0x8b/0x97 __kasan_kmalloc+0x10/0x12 __kmalloc+0xb2/0xe8 load_elf_phdrs+0xee/0x182 [...] The buggy address belongs to the object at 000000006d640800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 584 bytes inside of freed 1024-byte region [000000006d640800, 000000006d640c00) Add the appropriate irq_work_sync() so the work finishes before the buffers are destroyed. Prior to the commit in the Fixes tag below, there was only a single global IRQ work, so this issue didn't exist. Link: https://lore.kernel.org/linux-trace-kernel/20230427175920.a76159263122.I8295e405c44362a86c995e9c2c37e3e03810aa56@changeid Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Fixes: 15693458c4bc ("tracing/ring-buffer: Move poll wake ups into ring buffer code") Signed-off-by: Johannes Berg Signed-off-by: Steven Rostedt (Google) --- kernel/trace/ring_buffer.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9a0cb94c3972..0d748f1f79ff 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1767,6 +1767,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) struct list_head *head = cpu_buffer->pages; struct buffer_page *bpage, *tmp; + irq_work_sync(&cpu_buffer->irq_work.work); + free_buffer_page(cpu_buffer->reader_page); if (head) { @@ -1873,6 +1875,8 @@ ring_buffer_free(struct trace_buffer *buffer) cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); + irq_work_sync(&buffer->irq_work.work); + for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); -- GitLab From 6a0cdf56bfc9a1791ddd6955d60f3678523e599c Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 14 Apr 2023 20:18:15 -0400 Subject: [PATCH 4239/5631] SUNRPC: Be even lazier about releasing pages A single RPC transaction that touches only a couple of pages means rq_pvec will not be even close to full in svc_xpt_release(). This is a common case. Instead, just leave the pages in rq_pvec until it is completely full. This improves the efficiency of the batch release mechanism on workloads that involve small RPC messages. The rq_pvec is also fully emptied just before thread exit. Reviewed-by: Calum Mackay Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 3 +++ net/sunrpc/svc_xprt.c | 3 --- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index b982f802f2a0..26367cf4c17a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -649,6 +649,8 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) if (!rqstp) return rqstp; + pagevec_init(&rqstp->rq_pvec); + __set_bit(RQ_BUSY, &rqstp->rq_flags); rqstp->rq_server = serv; rqstp->rq_pool = pool; @@ -894,6 +896,7 @@ void svc_rqst_release_pages(struct svc_rqst *rqstp) void svc_rqst_free(struct svc_rqst *rqstp) { + pagevec_release(&rqstp->rq_pvec); svc_release_buffer(rqstp); if (rqstp->rq_scratch_page) put_page(rqstp->rq_scratch_page); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 533e08c4f319..e3952b690f54 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -541,7 +541,6 @@ static void svc_xprt_release(struct svc_rqst *rqstp) kfree(rqstp->rq_deferred); rqstp->rq_deferred = NULL; - pagevec_release(&rqstp->rq_pvec); svc_rqst_release_pages(rqstp); rqstp->rq_res.page_len = 0; rqstp->rq_res.page_base = 0; @@ -667,8 +666,6 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) struct xdr_buf *arg = &rqstp->rq_arg; unsigned long pages, filled, ret; - pagevec_init(&rqstp->rq_pvec); - pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT; if (pages > RPCSVC_MAXPAGES) { pr_warn_once("svc: warning: pages=%lu > RPCSVC_MAXPAGES=%lu\n", -- GitLab From 5e052dda121e2870dd87181783da4a95d7d2927b Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 17 Apr 2023 09:42:14 -0400 Subject: [PATCH 4240/5631] SUNRPC: Recognize control messages in server-side TCP socket code To support kTLS, the server-side TCP socket receive path needs to watch for CMSGs. Acked-by: Jakub Kicinski Signed-off-by: Chuck Lever --- include/net/tls.h | 2 ++ net/sunrpc/svcsock.c | 48 ++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 48 insertions(+), 2 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index 154949c7b0c8..6056ce5a2aa5 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -69,6 +69,8 @@ extern const struct tls_cipher_size_desc tls_cipher_size_desc[]; #define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) +#define TLS_RECORD_TYPE_ALERT 0x15 +#define TLS_RECORD_TYPE_HANDSHAKE 0x16 #define TLS_RECORD_TYPE_DATA 0x17 #define TLS_AAD_SPACE_SIZE 13 diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 302a14dd7882..c5b74f523fc4 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -216,6 +217,49 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) return len; } +static int +svc_tcp_sock_process_cmsg(struct svc_sock *svsk, struct msghdr *msg, + struct cmsghdr *cmsg, int ret) +{ + if (cmsg->cmsg_level == SOL_TLS && + cmsg->cmsg_type == TLS_GET_RECORD_TYPE) { + u8 content_type = *((u8 *)CMSG_DATA(cmsg)); + + switch (content_type) { + case TLS_RECORD_TYPE_DATA: + /* TLS sets EOR at the end of each application data + * record, even though there might be more frames + * waiting to be decrypted. + */ + msg->msg_flags &= ~MSG_EOR; + break; + case TLS_RECORD_TYPE_ALERT: + ret = -ENOTCONN; + break; + default: + ret = -EAGAIN; + } + } + return ret; +} + +static int +svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +{ + union { + struct cmsghdr cmsg; + u8 buf[CMSG_SPACE(sizeof(u8))]; + } u; + int ret; + + msg->msg_control = &u; + msg->msg_controllen = sizeof(u); + ret = sock_recvmsg(svsk->sk_sock, msg, MSG_DONTWAIT); + if (unlikely(msg->msg_controllen != sizeof(u))) + ret = svc_tcp_sock_process_cmsg(svsk, msg, &u.cmsg, ret); + return ret; +} + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek) { @@ -263,7 +307,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT); + len = svc_tcp_sock_recv_cmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -877,7 +921,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT); + len = svc_tcp_sock_recv_cmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; -- GitLab From 695bc1f32c6bc806218b322096b23dfd601e59ca Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 17 Apr 2023 22:15:28 -0400 Subject: [PATCH 4241/5631] SUNRPC: Clear rq_xid when receiving a new RPC Call This is an eye-catcher for tracepoints that record the XID: it means svc_rqst() has not received a full RPC Call with an XID yet. Signed-off-by: Chuck Lever --- net/sunrpc/svc_xprt.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index e3952b690f54..3b9708b39e35 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -701,6 +701,8 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) arg->page_len = (pages-2)*PAGE_SIZE; arg->len = (pages-1)*PAGE_SIZE; arg->tail[0].iov_len = 0; + + rqstp->rq_xid = xdr_zero; return 0; } -- GitLab From 147abcacee33781e75588869e944ddb07528a897 Mon Sep 17 00:00:00 2001 From: Dai Ngo Date: Wed, 19 Apr 2023 10:53:18 -0700 Subject: [PATCH 4242/5631] NFSD: Fix problem of COMMIT and NFS4ERR_DELAY in infinite loop The following request sequence to the same file causes the NFS client and server getting into an infinite loop with COMMIT and NFS4ERR_DELAY: OPEN REMOVE WRITE COMMIT Problem reported by recall11, recall12, recall14, recall20, recall22, recall40, recall42, recall48, recall50 of nfstest suite. This patch restores the handling of race condition in nfsd_file_do_acquire with unlink to that prior of the regression. Fixes: ac3a2585f018 ("nfsd: rework refcounting in filecache") Signed-off-by: Dai Ngo Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/filecache.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index f40d8f3b35a4..ee9c923192e0 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1099,8 +1099,6 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, * then unhash. */ if (status != nfs_ok || inode->i_nlink == 0) - status = nfserr_jukebox; - if (status != nfs_ok) nfsd_file_unhash(nf); clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags); if (status == nfs_ok) -- GitLab From 22b620ec0bf454cfd1c464f57cfce9afb3fb1e70 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 20 Apr 2023 11:02:33 -0400 Subject: [PATCH 4243/5631] NFSD: Clean up xattr memory allocation flags Tetsuo Handa points out: > Since GFP_KERNEL is "GFP_NOFS | __GFP_FS", usage like > "GFP_KERNEL | GFP_NOFS" does not make sense. The original intent was to hold the inode lock while estimating the buffer requirements for the requested information. Frank van der Linden, the author of NFSD's xattr code, says: > ... you need inode_lock to get an atomic view of an xattr. Since > both nfsd_getxattr and nfsd_listxattr to the standard trick of > querying the xattr length with a NULL buf argument (just getting > the length back), allocating the right buffer size, and then > querying again, they need to hold the inode lock to avoid having > the xattr changed from under them while doing that. > > From that then flows the requirement that GFP_FS could cause > problems while holding i_rwsem, so I added GFP_NOFS. However, Dave Chinner states: > You can do GFP_KERNEL allocations holding the i_rwsem just fine. > All that it requires is the caller holds a reference to the > inode ... Since these code paths acquire a dentry, they do indeed hold a reference. It is therefore safe to use GFP_KERNEL for these memory allocations. In particular, that's what this code is already doing; but now the C source code looks sane too. At a later time we can revisit in order to remove the inode lock in favor of simply retrying if the estimated buffer size is too small. Reported-by: Tetsuo Handa Signed-off-by: Chuck Lever --- fs/nfsd/vfs.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 10aa68ca82ef..bb9d47172162 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -2168,7 +2168,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, goto out; } - buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + buf = kvmalloc(len, GFP_KERNEL); if (buf == NULL) { err = nfserr_jukebox; goto out; @@ -2231,10 +2231,7 @@ nfsd_listxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char **bufp, goto out; } - /* - * We're holding i_rwsem - use GFP_NOFS. - */ - buf = kvmalloc(len, GFP_KERNEL | GFP_NOFS); + buf = kvmalloc(len, GFP_KERNEL); if (buf == NULL) { err = nfserr_jukebox; goto out; -- GitLab From b3cbf98e2fdf3cb147a95161560cd25987284330 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 20 Apr 2023 13:56:24 -0400 Subject: [PATCH 4244/5631] SUNRPC: Support TLS handshake in the server-side TCP socket code This patch adds opportunitistic RPC-with-TLS to the Linux in-kernel NFS server. If the client requests RPC-with-TLS and the user space handshake agent is running, the server will set up a TLS session. There are no policy settings yet. For example, the server cannot yet require the use of RPC-with-TLS to access its data. Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_xprt.h | 5 +- include/linux/sunrpc/svcsock.h | 2 + include/trace/events/sunrpc.h | 16 ++++- net/sunrpc/svc_xprt.c | 5 +- net/sunrpc/svcauth_unix.c | 11 +++- net/sunrpc/svcsock.c | 101 +++++++++++++++++++++++++++++++- 6 files changed, 132 insertions(+), 8 deletions(-) diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 775368802762..867479204840 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -27,7 +27,7 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); - void (*xpo_start_tls)(struct svc_xprt *); + void (*xpo_handshake)(struct svc_xprt *xprt); }; struct svc_xprt_class { @@ -70,6 +70,9 @@ struct svc_xprt { #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ #define XPT_CONG_CTRL 14 /* has congestion control */ +#define XPT_HANDSHAKE 15 /* xprt requests a handshake */ +#define XPT_TLS_SESSION 16 /* transport-layer security established */ +#define XPT_PEER_AUTH 17 /* peer has been authenticated */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index dd73fa174af5..d16ae621782c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -38,6 +38,8 @@ struct svc_sock { /* Number of queued send requests */ atomic_t sk_sendqlen; + struct completion sk_handshake_done; + struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 5a3bb42e1f50..31bc7025cb44 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1857,7 +1857,10 @@ TRACE_EVENT(svc_stats_latency, { BIT(XPT_CACHE_AUTH), "CACHE_AUTH" }, \ { BIT(XPT_LOCAL), "LOCAL" }, \ { BIT(XPT_KILL_TEMP), "KILL_TEMP" }, \ - { BIT(XPT_CONG_CTRL), "CONG_CTRL" }) + { BIT(XPT_CONG_CTRL), "CONG_CTRL" }, \ + { BIT(XPT_HANDSHAKE), "HANDSHAKE" }, \ + { BIT(XPT_TLS_SESSION), "TLS_SESSION" }, \ + { BIT(XPT_PEER_AUTH), "PEER_AUTH" }) TRACE_EVENT(svc_xprt_create_err, TP_PROTO( @@ -1990,6 +1993,17 @@ DEFINE_SVC_XPRT_EVENT(close); DEFINE_SVC_XPRT_EVENT(detach); DEFINE_SVC_XPRT_EVENT(free); +#define DEFINE_SVC_TLS_EVENT(name) \ + DEFINE_EVENT(svc_xprt_event, svc_tls_##name, \ + TP_PROTO(const struct svc_xprt *xprt), \ + TP_ARGS(xprt)) + +DEFINE_SVC_TLS_EVENT(start); +DEFINE_SVC_TLS_EVENT(upcall); +DEFINE_SVC_TLS_EVENT(unavailable); +DEFINE_SVC_TLS_EVENT(not_started); +DEFINE_SVC_TLS_EVENT(timed_out); + TRACE_EVENT(svc_xprt_accept, TP_PROTO( const struct svc_xprt *xprt, diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 3b9708b39e35..84e5d7d31481 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -427,7 +427,7 @@ static bool svc_xprt_ready(struct svc_xprt *xprt) if (xpt_flags & BIT(XPT_BUSY)) return false; - if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE))) + if (xpt_flags & (BIT(XPT_CONN) | BIT(XPT_CLOSE) | BIT(XPT_HANDSHAKE))) return true; if (xpt_flags & (BIT(XPT_DATA) | BIT(XPT_DEFERRED))) { if (xprt->xpt_ops->xpo_has_wspace(xprt) && @@ -828,6 +828,9 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) module_put(xprt->xpt_class->xcl_owner); } svc_xprt_received(xprt); + } else if (test_bit(XPT_HANDSHAKE, &xprt->xpt_flags)) { + xprt->xpt_ops->xpo_handshake(xprt); + svc_xprt_received(xprt); } else if (svc_xprt_reserve_slot(rqstp, xprt)) { /* XPT_DATA|XPT_DEFERRED case: */ dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n", diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 4485088ce27b..174783f804fa 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -17,8 +17,9 @@ #include #include #include -#define RPCDBG_FACILITY RPCDBG_AUTH +#include +#define RPCDBG_FACILITY RPCDBG_AUTH #include "netns.h" @@ -832,6 +833,7 @@ svcauth_tls_accept(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct svc_cred *cred = &rqstp->rq_cred; + struct svc_xprt *xprt = rqstp->rq_xprt; u32 flavor, len; void *body; __be32 *p; @@ -865,14 +867,19 @@ svcauth_tls_accept(struct svc_rqst *rqstp) if (cred->cr_group_info == NULL) return SVC_CLOSE; - if (rqstp->rq_xprt->xpt_ops->xpo_start_tls) { + if (xprt->xpt_ops->xpo_handshake) { p = xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2 + 8); if (!p) return SVC_CLOSE; + trace_svc_tls_start(xprt); *p++ = rpc_auth_null; *p++ = cpu_to_be32(8); memcpy(p, "STARTTLS", 8); + + set_bit(XPT_HANDSHAKE, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); } else { + trace_svc_tls_unavailable(xprt); if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index c5b74f523fc4..a51c9b989d58 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -44,9 +44,11 @@ #include #include #include +#include #include #include #include +#include #include #include @@ -64,6 +66,12 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT +/* To-do: to avoid tying up an nfsd thread while waiting for a + * handshake request, the request could instead be deferred. + */ +enum { + SVC_HANDSHAKE_TO = 5U * HZ +}; static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *, int flags); @@ -359,6 +367,8 @@ static void svc_data_ready(struct sock *sk) rmb(); svsk->sk_odata(sk); trace_svcsock_data_ready(&svsk->sk_xprt, 0); + if (test_bit(XPT_HANDSHAKE, &svsk->sk_xprt.xpt_flags)) + return; if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags)) svc_xprt_enqueue(&svsk->sk_xprt); } @@ -396,6 +406,88 @@ static void svc_tcp_kill_temp_xprt(struct svc_xprt *xprt) sock_no_linger(svsk->sk_sock->sk); } +/** + * svc_tcp_handshake_done - Handshake completion handler + * @data: address of xprt to wake + * @status: status of handshake + * @peerid: serial number of key containing the remote peer's identity + * + * If a security policy is specified as an export option, we don't + * have a specific export here to check. So we set a "TLS session + * is present" flag on the xprt and let an upper layer enforce local + * security policy. + */ +static void svc_tcp_handshake_done(void *data, int status, key_serial_t peerid) +{ + struct svc_xprt *xprt = data; + struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); + + if (!status) { + if (peerid != TLS_NO_PEERID) + set_bit(XPT_PEER_AUTH, &xprt->xpt_flags); + set_bit(XPT_TLS_SESSION, &xprt->xpt_flags); + } + clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags); + complete_all(&svsk->sk_handshake_done); +} + +/** + * svc_tcp_handshake - Perform a transport-layer security handshake + * @xprt: connected transport endpoint + * + */ +static void svc_tcp_handshake(struct svc_xprt *xprt) +{ + struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); + struct sock *sk = svsk->sk_sock->sk; + struct tls_handshake_args args = { + .ta_sock = svsk->sk_sock, + .ta_done = svc_tcp_handshake_done, + .ta_data = xprt, + }; + int ret; + + trace_svc_tls_upcall(xprt); + + clear_bit(XPT_TLS_SESSION, &xprt->xpt_flags); + init_completion(&svsk->sk_handshake_done); + + ret = tls_server_hello_x509(&args, GFP_KERNEL); + if (ret) { + trace_svc_tls_not_started(xprt); + goto out_failed; + } + + ret = wait_for_completion_interruptible_timeout(&svsk->sk_handshake_done, + SVC_HANDSHAKE_TO); + if (ret <= 0) { + if (tls_handshake_cancel(sk)) { + trace_svc_tls_timed_out(xprt); + goto out_close; + } + } + + if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) { + trace_svc_tls_unavailable(xprt); + goto out_close; + } + + /* Mark the transport ready in case the remote sent RPC + * traffic before the kernel received the handshake + * completion downcall. + */ + set_bit(XPT_DATA, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); + return; + +out_close: + set_bit(XPT_CLOSE, &xprt->xpt_flags); +out_failed: + clear_bit(XPT_HANDSHAKE, &xprt->xpt_flags); + set_bit(XPT_DATA, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); +} + /* * See net/ipv6/ip_sockglue.c : ip_cmsg_recv_pktinfo */ @@ -1257,6 +1349,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_kill_temp_xprt = svc_tcp_kill_temp_xprt, + .xpo_handshake = svc_tcp_handshake, }; static struct svc_xprt_class svc_tcp_class = { @@ -1580,10 +1673,12 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) static void svc_sock_free(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); + struct socket *sock = svsk->sk_sock; - if (svsk->sk_sock->file) - sockfd_put(svsk->sk_sock); + tls_handshake_cancel(sock->sk); + if (sock->file) + sockfd_put(sock); else - sock_release(svsk->sk_sock); + sock_release(sock); kfree(svsk); } -- GitLab From 9280c577431401544e63dfb489a830a42bee25eb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 20 Apr 2023 13:56:31 -0400 Subject: [PATCH 4245/5631] NFSD: Handle new xprtsec= export option Enable administrators to require clients to use transport layer security when accessing particular exports. Signed-off-by: Chuck Lever --- fs/nfsd/export.c | 51 ++++++++++++++++++++++++++++++-- fs/nfsd/export.h | 1 + include/uapi/linux/nfsd/export.h | 13 ++++++++ 3 files changed, 62 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 6da74aebe1fb..ae85257b4238 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -439,7 +439,6 @@ static int check_export(struct path *path, int *flags, unsigned char *uuid) return -EINVAL; } return 0; - } #ifdef CONFIG_NFSD_V4 @@ -546,6 +545,29 @@ static inline int secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif +static int xprtsec_parse(char **mesg, char *buf, struct svc_export *exp) +{ + unsigned int i, mode, listsize; + int err; + + err = get_uint(mesg, &listsize); + if (err) + return err; + if (listsize > NFSEXP_XPRTSEC_NUM) + return -EINVAL; + + exp->ex_xprtsec_modes = 0; + for (i = 0; i < listsize; i++) { + err = get_uint(mesg, &mode); + if (err) + return err; + if (mode > NFSEXP_XPRTSEC_MTLS) + return -EINVAL; + exp->ex_xprtsec_modes |= mode; + } + return 0; +} + static inline int nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid) { @@ -608,6 +630,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) exp.ex_client = dom; exp.cd = cd; exp.ex_devid_map = NULL; + exp.ex_xprtsec_modes = NFSEXP_XPRTSEC_ALL; /* expiry */ err = get_expiry(&mesg, &exp.h.expiry_time); @@ -649,6 +672,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid); else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); + else if (strcmp(buf, "xprtsec") == 0) + err = xprtsec_parse(&mesg, buf, &exp); else /* quietly ignore unknown words and anything * following. Newer user-space can try to set @@ -662,6 +687,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = check_export(&exp.ex_path, &exp.ex_flags, exp.ex_uuid); if (err) goto out4; + /* * No point caching this if it would immediately expire. * Also, this protects exportfs's dummy export from the @@ -823,6 +849,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem) for (i = 0; i < MAX_SECINFO_LIST; i++) { new->ex_flavors[i] = item->ex_flavors[i]; } + new->ex_xprtsec_modes = item->ex_xprtsec_modes; } static struct cache_head *svc_export_alloc(void) @@ -1034,9 +1061,26 @@ static struct svc_export *exp_find(struct cache_detail *cd, __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) { - struct exp_flavor_info *f; - struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; + struct exp_flavor_info *f, *end = exp->ex_flavors + exp->ex_nflavors; + struct svc_xprt *xprt = rqstp->rq_xprt; + + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_NONE) { + if (!test_bit(XPT_TLS_SESSION, &xprt->xpt_flags)) + goto ok; + } + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_TLS) { + if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && + !test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) + goto ok; + } + if (exp->ex_xprtsec_modes & NFSEXP_XPRTSEC_MTLS) { + if (test_bit(XPT_TLS_SESSION, &xprt->xpt_flags) && + test_bit(XPT_PEER_AUTH, &xprt->xpt_flags)) + goto ok; + } + goto denied; +ok: /* legacy gss-only clients are always OK: */ if (exp->ex_client == rqstp->rq_gssclient) return 0; @@ -1061,6 +1105,7 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) if (nfsd4_spo_must_allow(rqstp)) return 0; +denied: return rqstp->rq_vers < 4 ? nfserr_acces : nfserr_wrongsec; } diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index d03f7f6a8642..2df8ae25aad3 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -77,6 +77,7 @@ struct svc_export { struct cache_detail *cd; struct rcu_head ex_rcu; struct export_stats ex_stats; + unsigned long ex_xprtsec_modes; }; /* an "export key" (expkey) maps a filehandlefragement to an diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h index 2124ba904779..a73ca3703abb 100644 --- a/include/uapi/linux/nfsd/export.h +++ b/include/uapi/linux/nfsd/export.h @@ -62,5 +62,18 @@ | NFSEXP_ALLSQUASH \ | NFSEXP_INSECURE_PORT) +/* + * Transport layer security policies that are permitted to access + * an export + */ +#define NFSEXP_XPRTSEC_NONE 0x0001 +#define NFSEXP_XPRTSEC_TLS 0x0002 +#define NFSEXP_XPRTSEC_MTLS 0x0004 + +#define NFSEXP_XPRTSEC_NUM (3) + +#define NFSEXP_XPRTSEC_ALL (NFSEXP_XPRTSEC_NONE | \ + NFSEXP_XPRTSEC_TLS | \ + NFSEXP_XPRTSEC_MTLS) #endif /* _UAPINFSD_EXPORT_H */ -- GitLab From d06f5a3f7140921ada47d49574ae6fa4de5e2a89 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 27 Apr 2023 16:21:32 -0700 Subject: [PATCH 4246/5631] cdx: fix build failure due to sysfs 'bus_type' argument needing to be const Commit 75cff725d956 ("driver core: bus: mark the struct bus_type for sysfs callbacks as constant") missed at least one case - the CDX bus driver. Probably because Greg didn't notice the build failure, because it only ends up being enabled on arm64. And I missed it during the merge, because while I do arm64 builds these days, I don't do them in between each pull. So it took a while for me to notice the breakage, rather than me just fixing it in the driver core merge that brought this failure case in. Maybe we should remove the CDX_BUS dependency on arm64 when COMPILE_TEST is on? Cc: Greg Kroah-Hartman Cc: Nipun Gupta Cc: Nikhil Agarwal Signed-off-by: Linus Torvalds --- drivers/cdx/cdx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c index 67c32cb2c006..38511fd36325 100644 --- a/drivers/cdx/cdx.c +++ b/drivers/cdx/cdx.c @@ -363,7 +363,7 @@ static struct attribute *cdx_dev_attrs[] = { }; ATTRIBUTE_GROUPS(cdx_dev); -static ssize_t rescan_store(struct bus_type *bus, +static ssize_t rescan_store(const struct bus_type *bus, const char *buf, size_t count) { struct cdx_controller *cdx; -- GitLab From daf376a366fd2d469d66ab83dfdc074777462bab Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Mon, 10 Apr 2023 13:06:08 -0500 Subject: [PATCH 4247/5631] uapi nbd: improve doc links to userspace spec The uapi header intentionally documents only the NBD server features that the kernel module will utilize as a client. But while it already had one mention of skipped bits due to userspace extensions, it did not actually direct the reader to the canonical source to learn about those extensions. While touching comments, fix an outdated reference that listed only READ and WRITE as commands. Signed-off-by: Eric Blake Reviewed-by: Ming Lei Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20230410180611.1051618-2-eblake@redhat.com Signed-off-by: Jens Axboe --- include/uapi/linux/nbd.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index 20d6cc91435d..8797387caaf7 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -11,6 +11,8 @@ * Cleanup PARANOIA usage & code. * 2004/02/19 Paul Clements * Removed PARANOIA, plus various cleanup and comments + * 2023 Copyright Red Hat + * Link to userspace extensions. */ #ifndef _UAPILINUX_NBD_H @@ -30,12 +32,18 @@ #define NBD_SET_TIMEOUT _IO( 0xab, 9 ) #define NBD_SET_FLAGS _IO( 0xab, 10) +/* + * See also https://github.com/NetworkBlockDevice/nbd/blob/master/doc/proto.md + * for additional userspace extensions not yet utilized in the kernel module. + */ + enum { NBD_CMD_READ = 0, NBD_CMD_WRITE = 1, NBD_CMD_DISC = 2, NBD_CMD_FLUSH = 3, NBD_CMD_TRIM = 4 + /* userspace defines additional extension commands */ }; /* values for flags field, these are server interaction specific. */ @@ -64,14 +72,15 @@ enum { #define NBD_REQUEST_MAGIC 0x25609513 #define NBD_REPLY_MAGIC 0x67446698 /* Do *not* use magics: 0x12560953 0x96744668. */ +/* magic 0x668e33ef for structured reply not supported by kernel yet */ /* * This is the packet used for communication between client and * server. All data are in network byte order. */ struct nbd_request { - __be32 magic; - __be32 type; /* == READ || == WRITE */ + __be32 magic; /* NBD_REQUEST_MAGIC */ + __be32 type; /* See NBD_CMD_* */ char handle[8]; __be64 from; __be32 len; @@ -82,7 +91,7 @@ struct nbd_request { * it has completed an I/O request (or an error occurs). */ struct nbd_reply { - __be32 magic; + __be32 magic; /* NBD_REPLY_MAGIC */ __be32 error; /* 0 = ok, else error */ char handle[8]; /* handle you got from request */ }; -- GitLab From 2686eb845da7762ee98b17e578b0c081aafb77b9 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Mon, 10 Apr 2023 13:06:09 -0500 Subject: [PATCH 4248/5631] uapi nbd: add cookie alias to handle The uapi header declares a 'char handle[8]' per request; which is overloaded in English (are you referring to "handle" the verb, such as handling a signal or writing a callback handler, or "handle" the noun, the value used in a lookup table to correlate a response back to the request). Many user-space NBD implementations (both servers and clients) have instead used 'uint64_t cookie' or similar, as it is easier to directly assign an integer than to futz around with memcpy. In fact, upstream documentation is now encouraging this shift in terminology: https://github.com/NetworkBlockDevice/nbd/commit/ca4392eb2b Accomplish this by use of an anonymous union to provide the alias for anyone getting the definition from the uapi; this does not break existing clients, while exposing the nicer name for those who prefer it. Note that block/nbd.c still uses the term handle (in fact, it actually combines a 32-bit cookie and a 32-bit tag into the 64-bit handle), but that internal usage is not changed by the public uapi, since no compliant NBD server has any reason to inspect or alter the 64 bits sent over the socket. Signed-off-by: Eric Blake Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20230410180611.1051618-3-eblake@redhat.com Signed-off-by: Jens Axboe --- include/uapi/linux/nbd.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/include/uapi/linux/nbd.h b/include/uapi/linux/nbd.h index 8797387caaf7..80ce0ef43afd 100644 --- a/include/uapi/linux/nbd.h +++ b/include/uapi/linux/nbd.h @@ -12,7 +12,7 @@ * 2004/02/19 Paul Clements * Removed PARANOIA, plus various cleanup and comments * 2023 Copyright Red Hat - * Link to userspace extensions. + * Link to userspace extensions, favor cookie over handle. */ #ifndef _UAPILINUX_NBD_H @@ -81,7 +81,10 @@ enum { struct nbd_request { __be32 magic; /* NBD_REQUEST_MAGIC */ __be32 type; /* See NBD_CMD_* */ - char handle[8]; + union { + __be64 cookie; /* Opaque identifier for request */ + char handle[8]; /* older spelling of cookie */ + }; __be64 from; __be32 len; } __attribute__((packed)); @@ -93,6 +96,9 @@ struct nbd_request { struct nbd_reply { __be32 magic; /* NBD_REPLY_MAGIC */ __be32 error; /* 0 = ok, else error */ - char handle[8]; /* handle you got from request */ + union { + __be64 cookie; /* Opaque identifier from request */ + char handle[8]; /* older spelling of cookie */ + }; }; #endif /* _UAPILINUX_NBD_H */ -- GitLab From bd9e9916c32fd4b4fb4e879e05bd1568ee02ec93 Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Mon, 10 Apr 2023 13:06:10 -0500 Subject: [PATCH 4249/5631] block nbd: use req.cookie instead of req.handle The NBD spec was recently changed [1] to refer to the opaque client identifier as a 'cookie' rather than a 'handle', but has for a much longer time listed it as a 64-bit value, and declares that all values in the NBD protocol are sent in network byte order (big-endian). Because the value is opaque to the server, it doesn't usually matter what endianness we send as the client - as long as we are consistent that either we byte-swap on both write and read, or on neither, then we can match server replies back to our requests. That said, our internal use of the cookie is as a 64-bit number (well, as two 32-bit numbers concatenated together), rather than as 8 individual bytes; so prior to this commit, we ARE leaking the native endianness of our internals as a client out to the server. We don't know of any server that will actually inspect the opaque value and behave differently depending on whether a little-endian or big-endian client is sending requests, but since we DO log the cookie value, a wireshark capture of the network traffic is easier to correlate back to the kernel traffic of a big-endian host (where the u64 and char[8] representations are the same) than of a little-endian host (where if wireshark honors the NBD spec and displays a u64 in network byte order, it is byte-swapped from what the kernel logged). The fix in this patch is thus two-part: it now consistently uses network byte order for the opaque value (no difference to a big-endian machine, but an extra byteswap on a little-endian machine; probably in the noise compared to the overhead of network traffic in general), and now uses a 64-bit integer instead of char[8] as its preferred access to the opaque value (direct assignment instead of memcpy()). Signed-off-by: Eric Blake Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20230410180611.1051618-4-eblake@redhat.com Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7c96ec4e99df..9c35c958f2c8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -609,7 +609,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.len = htonl(size); } handle = nbd_cmd_handle(cmd); - memcpy(request.handle, &handle, sizeof(handle)); + request.cookie = cpu_to_be64(handle); trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd)); @@ -621,7 +621,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) trace_nbd_header_sent(req, handle); if (result < 0) { if (was_interrupted(result)) { - /* If we havne't sent anything we can just return BUSY, + /* If we haven't sent anything we can just return BUSY, * however if we have sent something we need to make * sure we only allow this req to be sent until we are * completely done. @@ -735,7 +735,7 @@ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index, u32 tag; int ret = 0; - memcpy(&handle, reply->handle, sizeof(handle)); + handle = be64_to_cpu(reply->cookie); tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) -- GitLab From 952aa344bf4305ab6fa0d9962ef8c2caa2afef4c Mon Sep 17 00:00:00 2001 From: Eric Blake Date: Mon, 10 Apr 2023 13:06:11 -0500 Subject: [PATCH 4250/5631] docs nbd: userspace NBD now favors github over sourceforge While the sourceforge site for userspace NBD still exists, the code repository moved to github several years ago. Then with a recent patch[1], the github landing page contains just as much information as the sourceforge page, so we might as well point to a single location that also provides the code. [1] https://lists.debian.org/nbd/2023/03/msg00051.html Signed-off-by: Eric Blake Reviewed-by: Josef Bacik Link: https://lore.kernel.org/r/20230410180611.1051618-5-eblake@redhat.com Signed-off-by: Jens Axboe --- Documentation/admin-guide/blockdev/nbd.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/admin-guide/blockdev/nbd.rst b/Documentation/admin-guide/blockdev/nbd.rst index d78dfe559dcf..faf2ac4b1509 100644 --- a/Documentation/admin-guide/blockdev/nbd.rst +++ b/Documentation/admin-guide/blockdev/nbd.rst @@ -14,7 +14,7 @@ to borrow disk space from another computer. Unlike NFS, it is possible to put any filesystem on it, etc. For more information, or to download the nbd-client and nbd-server -tools, go to http://nbd.sf.net/. +tools, go to https://github.com/NetworkBlockDevice/nbd. The nbd kernel module need only be installed on the client system, as the nbd-server is completely in userspace. In fact, -- GitLab From c7a639dac8e4d7e63450bef2f3a19fb331566fb1 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Sun, 9 Apr 2023 09:25:44 -0700 Subject: [PATCH 4251/5631] rtc: jz4740: Make sure clock provider gets removed The jz4740 RTC driver registers a clock provider, but never removes it. This leaves a stale clock provider behind that references freed clocks when the device is unbound. Use the managed `devm_of_clk_add_hw_provider()` instead of `of_clk_add_hw_provider()` to make sure the provider gets automatically removed on unbind. Fixes: 5ddfa148de8c ("rtc: jz4740: Register clock provider for the CLK32K pin") Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230409162544.16155-1-lars@metafoo.de Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-jz4740.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c index 59d279e3e6f5..36453b008139 100644 --- a/drivers/rtc/rtc-jz4740.c +++ b/drivers/rtc/rtc-jz4740.c @@ -414,7 +414,8 @@ static int jz4740_rtc_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "Unable to register clk32k clock\n"); - ret = of_clk_add_hw_provider(np, of_clk_hw_simple_get, &rtc->clk32k); + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, + &rtc->clk32k); if (ret) return dev_err_probe(dev, ret, "Unable to register clk32k clock provider\n"); -- GitLab From 916890539bc8a5674d363a1fc985633200c2117a Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 22 Mar 2023 11:31:58 +0800 Subject: [PATCH 4252/5631] rtc: sunplus: use devm_platform_ioremap_resource_byname() Convert platform_get_resource_byname(),devm_ioremap_resource() to a single call to devm_platform_ioremap_resource_byname(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Link: https://lore.kernel.org/r/202303221131581039486@zte.com.cn Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-sunplus.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index 44b8083603c2..f33dc301f301 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -235,8 +235,7 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (!sp_rtc) return -ENOMEM; - sp_rtc->res = platform_get_resource_byname(plat_dev, IORESOURCE_MEM, RTC_REG_NAME); - sp_rtc->reg_base = devm_ioremap_resource(&plat_dev->dev, sp_rtc->res); + sp_rtc->reg_base = devm_platform_ioremap_resource_byname(plat_dev, RTC_REG_NAME); if (IS_ERR(sp_rtc->reg_base)) return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base), "%s devm_ioremap_resource fail\n", RTC_REG_NAME); -- GitLab From e99ab4abebf825de2ce65f6c6c32ee30e00bb077 Mon Sep 17 00:00:00 2001 From: Ye Xingchen Date: Wed, 22 Mar 2023 11:30:31 +0800 Subject: [PATCH 4253/5631] rtc: armada38x: use devm_platform_ioremap_resource_byname() Convert platform_get_resource_byname(),devm_ioremap_resource() to a single call to devm_platform_ioremap_resource_byname(), as this is exactly what this function does. Signed-off-by: Ye Xingchen Link: https://lore.kernel.org/r/202303221130316049449@zte.com.cn Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-armada38x.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c index cc542e6b1d5b..b4139c200676 100644 --- a/drivers/rtc/rtc-armada38x.c +++ b/drivers/rtc/rtc-armada38x.c @@ -491,7 +491,6 @@ MODULE_DEVICE_TABLE(of, armada38x_rtc_of_match_table); static __init int armada38x_rtc_probe(struct platform_device *pdev) { - struct resource *res; struct armada38x_rtc *rtc; rtc = devm_kzalloc(&pdev->dev, sizeof(struct armada38x_rtc), @@ -508,12 +507,10 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev) spin_lock_init(&rtc->lock); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rtc"); - rtc->regs = devm_ioremap_resource(&pdev->dev, res); + rtc->regs = devm_platform_ioremap_resource_byname(pdev, "rtc"); if (IS_ERR(rtc->regs)) return PTR_ERR(rtc->regs); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rtc-soc"); - rtc->regs_soc = devm_ioremap_resource(&pdev->dev, res); + rtc->regs_soc = devm_platform_ioremap_resource_byname(pdev, "rtc-soc"); if (IS_ERR(rtc->regs_soc)) return PTR_ERR(rtc->regs_soc); -- GitLab From d782188cbb05a196e46a4838484f020ceeb889ec Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 31 Mar 2023 17:14:59 +0800 Subject: [PATCH 4254/5631] i3c: dw: Add infrastructure for platform-specific implementations The dw i3c core can be integrated into various SoC devices. Platforms that use this core may need a little configuration that is specific to that platform. Add some infrastructure to allow platform-specific behaviour: common probe/remove functions, a set of platform hook operations, and a pointer for platform-specific data in struct dw_i3c_master. Move the common api into a new (i3c local) header file. Platforms will provide their own struct platform_driver, which allocates struct dw_i3c_master, does any platform-specific probe behaviour, and calls into the common probe. A future change will add new platform support that uses this infrastructure. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20230331091501.3800299-2-jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 77 +++++++++++++++++------------- drivers/i3c/master/dw-i3c-master.h | 54 +++++++++++++++++++++ 2 files changed, 97 insertions(+), 34 deletions(-) create mode 100644 drivers/i3c/master/dw-i3c-master.h diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 9ae2e5b2723f..00163b5081bd 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -21,6 +21,8 @@ #include #include +#include "dw-i3c-master.h" + #define DEVICE_CTRL 0x0 #define DEV_CTRL_ENABLE BIT(31) #define DEV_CTRL_RESUME BIT(30) @@ -189,8 +191,6 @@ #define DEV_ADDR_TABLE_STATIC_ADDR(x) ((x) & GENMASK(6, 0)) #define DEV_ADDR_TABLE_LOC(start, idx) ((start) + ((idx) << 2)) -#define MAX_DEVS 32 - #define I3C_BUS_SDR1_SCL_RATE 8000000 #define I3C_BUS_SDR2_SCL_RATE 6000000 #define I3C_BUS_SDR3_SCL_RATE 4000000 @@ -201,11 +201,6 @@ #define XFER_TIMEOUT (msecs_to_jiffies(1000)) -struct dw_i3c_master_caps { - u8 cmdfifodepth; - u8 datafifodepth; -}; - struct dw_i3c_cmd { u32 cmd_lo; u32 cmd_hi; @@ -224,25 +219,6 @@ struct dw_i3c_xfer { struct dw_i3c_cmd cmds[]; }; -struct dw_i3c_master { - struct i3c_master_controller base; - u16 maxdevs; - u16 datstartaddr; - u32 free_pos; - struct { - struct list_head list; - struct dw_i3c_xfer *cur; - spinlock_t lock; - } xferqueue; - struct dw_i3c_master_caps caps; - void __iomem *regs; - struct reset_control *core_rst; - struct clk *core_clk; - char version[5]; - char type[5]; - u8 addrs[MAX_DEVS]; -}; - struct dw_i3c_i2c_dev_data { u8 index; }; @@ -602,6 +578,10 @@ static int dw_i3c_master_bus_init(struct i3c_master_controller *m) u32 thld_ctrl; int ret; + ret = master->platform_ops->init(master); + if (ret) + return ret; + switch (bus->mode) { case I3C_BUS_MODE_MIXED_FAST: case I3C_BUS_MODE_MIXED_LIMITED: @@ -1124,14 +1104,23 @@ static const struct i3c_master_controller_ops dw_mipi_i3c_ops = { .i2c_xfers = dw_i3c_master_i2c_xfers, }; -static int dw_i3c_probe(struct platform_device *pdev) +/* default platform ops implementations */ +static int dw_i3c_platform_init_nop(struct dw_i3c_master *i3c) +{ + return 0; +} + +static const struct dw_i3c_platform_ops dw_i3c_platform_ops_default = { + .init = dw_i3c_platform_init_nop, +}; + +int dw_i3c_common_probe(struct dw_i3c_master *master, + struct platform_device *pdev) { - struct dw_i3c_master *master; int ret, irq; - master = devm_kzalloc(&pdev->dev, sizeof(*master), GFP_KERNEL); - if (!master) - return -ENOMEM; + if (!master->platform_ops) + master->platform_ops = &dw_i3c_platform_ops_default; master->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(master->regs)) @@ -1192,17 +1181,37 @@ static int dw_i3c_probe(struct platform_device *pdev) return ret; } +EXPORT_SYMBOL_GPL(dw_i3c_common_probe); -static void dw_i3c_remove(struct platform_device *pdev) +void dw_i3c_common_remove(struct dw_i3c_master *master) { - struct dw_i3c_master *master = platform_get_drvdata(pdev); - i3c_master_unregister(&master->base); reset_control_assert(master->core_rst); clk_disable_unprepare(master->core_clk); } +EXPORT_SYMBOL_GPL(dw_i3c_common_remove); + +/* base platform implementation */ + +static int dw_i3c_probe(struct platform_device *pdev) +{ + struct dw_i3c_master *master; + + master = devm_kzalloc(&pdev->dev, sizeof(*master), GFP_KERNEL); + if (!master) + return -ENOMEM; + + return dw_i3c_common_probe(master, pdev); +} + +static void dw_i3c_remove(struct platform_device *pdev) +{ + struct dw_i3c_master *master = platform_get_drvdata(pdev); + + dw_i3c_common_remove(master); +} static const struct of_device_id dw_i3c_master_of_match[] = { { .compatible = "snps,dw-i3c-master-1.00a", }, diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h new file mode 100644 index 000000000000..915dd0f2c069 --- /dev/null +++ b/drivers/i3c/master/dw-i3c-master.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Code Construct + * + * Author: Jeremy Kerr + */ + +#include +#include +#include +#include + +#define DW_I3C_MAX_DEVS 32 + +struct dw_i3c_master_caps { + u8 cmdfifodepth; + u8 datafifodepth; +}; + +struct dw_i3c_master { + struct i3c_master_controller base; + u16 maxdevs; + u16 datstartaddr; + u32 free_pos; + struct { + struct list_head list; + struct dw_i3c_xfer *cur; + spinlock_t lock; + } xferqueue; + struct dw_i3c_master_caps caps; + void __iomem *regs; + struct reset_control *core_rst; + struct clk *core_clk; + char version[5]; + char type[5]; + u8 addrs[DW_I3C_MAX_DEVS]; + + /* platform-specific data */ + const struct dw_i3c_platform_ops *platform_ops; +}; + +struct dw_i3c_platform_ops { + /* + * Called on early bus init: the i3c has been set up, but before any + * transactions have taken place. Platform implementations may use to + * perform actual device enabling with the i3c core ready. + */ + int (*init)(struct dw_i3c_master *i3c); +}; + +extern int dw_i3c_common_probe(struct dw_i3c_master *master, + struct platform_device *pdev); +extern void dw_i3c_common_remove(struct dw_i3c_master *master); + -- GitLab From 21203e098cd3c1760de8112d750ceeedf09a6dad Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 31 Mar 2023 17:15:00 +0800 Subject: [PATCH 4255/5631] dt-bindings: i3c: Add AST2600 i3c controller Add a devicetree binding for the ast2600 i3c controller hardware. This is heavily based on the designware i3c core, plus a reset facility and two platform-specific properties: - sda-pullup-ohms: to specify the value of the configurable pullup resistors on the SDA line - aspeed,global-regs: to reference the (ast2600-specific) i3c global register block, and the device index to use within it. Reviewed-by: Krzysztof Kozlowski (on v1) Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20230331091501.3800299-3-jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- .../bindings/i3c/aspeed,ast2600-i3c.yaml | 72 +++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml diff --git a/Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml b/Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml new file mode 100644 index 000000000000..fcc3dbff9c9a --- /dev/null +++ b/Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/i3c/aspeed,ast2600-i3c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ASPEED AST2600 i3c controller + +maintainers: + - Jeremy Kerr + +allOf: + - $ref: i3c.yaml# + +properties: + compatible: + const: aspeed,ast2600-i3c + + reg: + maxItems: 1 + + clocks: + maxItems: 1 + + resets: + maxItems: 1 + + interrupts: + maxItems: 1 + + sda-pullup-ohms: + enum: [545, 750, 2000] + default: 2000 + description: | + Value to configure SDA pullup resistor, in Ohms. + + aspeed,global-regs: + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: phandle to i3c global register syscon node + - description: index of this i3c controller in the global register set + description: | + A (phandle, controller index) reference to the i3c global register set + used for this device. + +required: + - compatible + - reg + - clocks + - interrupts + - aspeed,global-regs + +unevaluatedProperties: false + +examples: + - | + #include + + i3c-master@2000 { + compatible = "aspeed,ast2600-i3c"; + reg = <0x2000 0x1000>; + #address-cells = <3>; + #size-cells = <0>; + clocks = <&syscon 0>; + resets = <&syscon 0>; + aspeed,global-regs = <&i3c_global 0>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i3c1_default>; + interrupts = ; + }; +... -- GitLab From 5844564143575a8dbcbcece0084da059faeca5df Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 31 Mar 2023 17:15:01 +0800 Subject: [PATCH 4256/5631] i3c: ast2600: Add AST2600 platform-specific driver Now that we have platform-specific infrastructure for the dw i3c driver, add platform support for the ASPEED AST2600 SoC. The AST2600 has a small set of "i3c global" registers, providing platform-level i3c configuration outside of the i3c core. For the ast2600, we need a couple of extra setup operations: - on probe: find the i3c global register set and parse the SDA pullup resistor values - on init: set the pullups accordingly, and set the i3c instance IDs Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/20230331091501.3800299-4-jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- MAINTAINERS | 6 + drivers/i3c/master/Kconfig | 14 ++ drivers/i3c/master/Makefile | 1 + drivers/i3c/master/ast2600-i3c-master.c | 168 ++++++++++++++++++++++++ 4 files changed, 189 insertions(+) create mode 100644 drivers/i3c/master/ast2600-i3c-master.c diff --git a/MAINTAINERS b/MAINTAINERS index 8d5bc223f305..cb91cc18df58 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9713,6 +9713,12 @@ S: Orphan F: Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml F: drivers/i3c/master/dw* +I3C DRIVER FOR ASPEED AST2600 +M: Jeremy Kerr +S: Maintained +F: Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml +F: drivers/i3c/master/ast2600-i3c-master.c + I3C SUBSYSTEM M: Alexandre Belloni L: linux-i3c@lists.infradead.org (moderated for non-subscribers) diff --git a/drivers/i3c/master/Kconfig b/drivers/i3c/master/Kconfig index 3b8f95916f46..90dee3ec5520 100644 --- a/drivers/i3c/master/Kconfig +++ b/drivers/i3c/master/Kconfig @@ -22,6 +22,20 @@ config DW_I3C_MASTER This driver can also be built as a module. If so, the module will be called dw-i3c-master. +config AST2600_I3C_MASTER + tristate "ASPEED AST2600 I3C master driver" + depends on DW_I3C_MASTER + depends on ARCH_ASPEED || COMPILE_TEST + select MFD_SYSCON + help + Support for ASPEED AST2600 I3C Controller. + + This hardware is an instance of the DW I3C controller; this + driver adds platform- specific support for AST2600 hardware. + + This driver can also be built as a module. If so, the module + will be called ast2600-i3c-master. + config SVC_I3C_MASTER tristate "Silvaco I3C Dual-Role Master driver" depends on I3C diff --git a/drivers/i3c/master/Makefile b/drivers/i3c/master/Makefile index b3fee0f690b2..3e97960160bc 100644 --- a/drivers/i3c/master/Makefile +++ b/drivers/i3c/master/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_CDNS_I3C_MASTER) += i3c-master-cdns.o obj-$(CONFIG_DW_I3C_MASTER) += dw-i3c-master.o +obj-$(CONFIG_AST2600_I3C_MASTER) += ast2600-i3c-master.o obj-$(CONFIG_SVC_I3C_MASTER) += svc-i3c-master.o obj-$(CONFIG_MIPI_I3C_HCI) += mipi-i3c-hci/ diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c new file mode 100644 index 000000000000..b3f0fe1e63c3 --- /dev/null +++ b/drivers/i3c/master/ast2600-i3c-master.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Code Construct + * + * Author: Jeremy Kerr + */ + +#include +#include +#include +#include +#include +#include + +#include "dw-i3c-master.h" + +/* AST2600-specific global register set */ +#define AST2600_I3CG_REG0(idx) (((idx) * 4 * 4) + 0x10) +#define AST2600_I3CG_REG1(idx) (((idx) * 4 * 4) + 0x14) + +#define AST2600_I3CG_REG0_SDA_PULLUP_EN_MASK GENMASK(29, 28) +#define AST2600_I3CG_REG0_SDA_PULLUP_EN_2K (0x0 << 28) +#define AST2600_I3CG_REG0_SDA_PULLUP_EN_750 (0x2 << 28) + +#define AST2600_I3CG_REG1_I2C_MODE BIT(0) +#define AST2600_I3CG_REG1_TEST_MODE BIT(1) +#define AST2600_I3CG_REG1_ACT_MODE_MASK GENMASK(3, 2) +#define AST2600_I3CG_REG1_ACT_MODE(x) (((x) << 2) & AST2600_I3CG_REG1_ACT_MODE_MASK) +#define AST2600_I3CG_REG1_PENDING_INT_MASK GENMASK(7, 4) +#define AST2600_I3CG_REG1_PENDING_INT(x) (((x) << 4) & AST2600_I3CG_REG1_PENDING_INT_MASK) +#define AST2600_I3CG_REG1_SA_MASK GENMASK(14, 8) +#define AST2600_I3CG_REG1_SA(x) (((x) << 8) & AST2600_I3CG_REG1_SA_MASK) +#define AST2600_I3CG_REG1_SA_EN BIT(15) +#define AST2600_I3CG_REG1_INST_ID_MASK GENMASK(19, 16) +#define AST2600_I3CG_REG1_INST_ID(x) (((x) << 16) & AST2600_I3CG_REG1_INST_ID_MASK) + +#define AST2600_DEFAULT_SDA_PULLUP_OHMS 2000 + +struct ast2600_i3c { + struct dw_i3c_master dw; + struct regmap *global_regs; + unsigned int global_idx; + unsigned int sda_pullup; +}; + +static struct ast2600_i3c *to_ast2600_i3c(struct dw_i3c_master *dw) +{ + return container_of(dw, struct ast2600_i3c, dw); +} + +static int ast2600_i3c_pullup_to_reg(unsigned int ohms, u32 *regp) +{ + u32 reg; + + switch (ohms) { + case 2000: + reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_2K; + break; + case 750: + reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_750; + break; + case 545: + reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_2K | + AST2600_I3CG_REG0_SDA_PULLUP_EN_750; + break; + default: + return -EINVAL; + } + + if (regp) + *regp = reg; + + return 0; +} + +static int ast2600_i3c_init(struct dw_i3c_master *dw) +{ + struct ast2600_i3c *i3c = to_ast2600_i3c(dw); + u32 reg = 0; + int rc; + + /* reg0: set SDA pullup values */ + rc = ast2600_i3c_pullup_to_reg(i3c->sda_pullup, ®); + if (rc) + return rc; + + rc = regmap_write(i3c->global_regs, + AST2600_I3CG_REG0(i3c->global_idx), reg); + if (rc) + return rc; + + /* reg1: set up the instance id, but leave everything else disabled, + * as it's all for client mode + */ + reg = AST2600_I3CG_REG1_INST_ID(i3c->global_idx); + rc = regmap_write(i3c->global_regs, + AST2600_I3CG_REG1(i3c->global_idx), reg); + + return rc; +} + +const struct dw_i3c_platform_ops ast2600_i3c_ops = { + .init = ast2600_i3c_init, +}; + +static int ast2600_i3c_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct of_phandle_args gspec; + struct ast2600_i3c *i3c; + int rc; + + i3c = devm_kzalloc(&pdev->dev, sizeof(*i3c), GFP_KERNEL); + if (!i3c) + return -ENOMEM; + + rc = of_parse_phandle_with_fixed_args(np, "aspeed,global-regs", 1, 0, + &gspec); + if (rc) + return -ENODEV; + + i3c->global_regs = syscon_node_to_regmap(gspec.np); + of_node_put(gspec.np); + + if (IS_ERR(i3c->global_regs)) + return PTR_ERR(i3c->global_regs); + + i3c->global_idx = gspec.args[0]; + + rc = of_property_read_u32(np, "sda-pullup-ohms", &i3c->sda_pullup); + if (rc) + i3c->sda_pullup = AST2600_DEFAULT_SDA_PULLUP_OHMS; + + rc = ast2600_i3c_pullup_to_reg(i3c->sda_pullup, NULL); + if (rc) + dev_err(&pdev->dev, "invalid sda-pullup value %d\n", + i3c->sda_pullup); + + i3c->dw.platform_ops = &ast2600_i3c_ops; + return dw_i3c_common_probe(&i3c->dw, pdev); +} + +static void ast2600_i3c_remove(struct platform_device *pdev) +{ + struct dw_i3c_master *dw_i3c = platform_get_drvdata(pdev); + + dw_i3c_common_remove(dw_i3c); +} + +static const struct of_device_id ast2600_i3c_master_of_match[] = { + { .compatible = "aspeed,ast2600-i3c", }, + {}, +}; +MODULE_DEVICE_TABLE(of, ast2600_i3c_master_of_match); + +static struct platform_driver ast2600_i3c_driver = { + .probe = ast2600_i3c_probe, + .remove_new = ast2600_i3c_remove, + .driver = { + .name = "ast2600-i3c-master", + .of_match_table = ast2600_i3c_master_of_match, + }, +}; +module_platform_driver(ast2600_i3c_driver); + +MODULE_AUTHOR("Jeremy Kerr "); +MODULE_DESCRIPTION("ASPEED AST2600 I3C driver"); +MODULE_LICENSE("GPL"); -- GitLab From 7dc2e0a875645a79f5c1c063019397e8e94008f5 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Wed, 5 Apr 2023 17:41:49 +0800 Subject: [PATCH 4257/5631] i3c: Allow OF-alias-based persistent bus numbering Parse the /aliases node to assign any fixed bus numbers, as is done with the i2c subsystem. Numbering for non-aliased busses will start after the highest fixed bus number. This allows an alias node such as: aliases { i3c0 = &bus_a, i3c4 = &bus_b, }; to set the numbering for a set of i3c controllers: /* fixed-numbered bus, assigned "i3c-0" */ bus_a: i3c-master { }; /* another fixed-numbered bus, assigned "i3c-4" */ bus_b: i3c-master { }; /* dynamic-numbered bus, likely assigned "i3c-5" */ bus_c: i3c-master { }; If no i3c device aliases are present, the numbering will stay as-is, starting from 0. Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230405094149.1513209-1-jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index 04d6d54d2ab8..08aeb69a7800 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -21,6 +21,7 @@ static DEFINE_IDR(i3c_bus_idr); static DEFINE_MUTEX(i3c_core_lock); +static int __i3c_first_dynamic_bus_num; /** * i3c_bus_maintenance_lock - Lock the bus for a maintenance operation @@ -419,9 +420,9 @@ static void i3c_bus_cleanup(struct i3c_bus *i3cbus) mutex_unlock(&i3c_core_lock); } -static int i3c_bus_init(struct i3c_bus *i3cbus) +static int i3c_bus_init(struct i3c_bus *i3cbus, struct device_node *np) { - int ret; + int ret, start, end, id = -1; init_rwsem(&i3cbus->lock); INIT_LIST_HEAD(&i3cbus->devs.i2c); @@ -429,8 +430,19 @@ static int i3c_bus_init(struct i3c_bus *i3cbus) i3c_bus_init_addrslots(i3cbus); i3cbus->mode = I3C_BUS_MODE_PURE; + if (np) + id = of_alias_get_id(np, "i3c"); + mutex_lock(&i3c_core_lock); - ret = idr_alloc(&i3c_bus_idr, i3cbus, 0, 0, GFP_KERNEL); + if (id >= 0) { + start = id; + end = start + 1; + } else { + start = __i3c_first_dynamic_bus_num; + end = 0; + } + + ret = idr_alloc(&i3c_bus_idr, i3cbus, start, end, GFP_KERNEL); mutex_unlock(&i3c_core_lock); if (ret < 0) @@ -2606,7 +2618,7 @@ int i3c_master_register(struct i3c_master_controller *master, INIT_LIST_HEAD(&master->boardinfo.i2c); INIT_LIST_HEAD(&master->boardinfo.i3c); - ret = i3c_bus_init(i3cbus); + ret = i3c_bus_init(i3cbus, master->dev.of_node); if (ret) return ret; @@ -2830,8 +2842,16 @@ void i3c_dev_free_ibi_locked(struct i3c_dev_desc *dev) static int __init i3c_init(void) { - int res = bus_register_notifier(&i2c_bus_type, &i2cdev_notifier); + int res; + + res = of_alias_get_highest_id("i3c"); + if (res >= 0) { + mutex_lock(&i3c_core_lock); + __i3c_first_dynamic_bus_num = res + 1; + mutex_unlock(&i3c_core_lock); + } + res = bus_register_notifier(&i2c_bus_type, &i2cdev_notifier); if (res) return res; -- GitLab From 79f42b31c2ec78416bc7dd6c9f21c3334879c43a Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 15:50:32 +0800 Subject: [PATCH 4258/5631] i3c: dw: Create a generic fifo read function In a future change we'll want to read from the IBI FIFO too, so turn dw_i3c_read_rx_fifo() into a generic read with the FIFO register as a parameter. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/827204789583dd86addffb47ecaeab9d67cf95d5.1680161823.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 00163b5081bd..c2011447f757 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -318,18 +318,24 @@ static void dw_i3c_master_wr_tx_fifo(struct dw_i3c_master *master, } } -static void dw_i3c_master_read_rx_fifo(struct dw_i3c_master *master, - u8 *bytes, int nbytes) +static void dw_i3c_master_read_fifo(struct dw_i3c_master *master, + int reg, u8 *bytes, int nbytes) { - readsl(master->regs + RX_TX_DATA_PORT, bytes, nbytes / 4); + readsl(master->regs + reg, bytes, nbytes / 4); if (nbytes & 3) { u32 tmp; - readsl(master->regs + RX_TX_DATA_PORT, &tmp, 1); + readsl(master->regs + reg, &tmp, 1); memcpy(bytes + (nbytes & ~3), &tmp, nbytes & 3); } } +static void dw_i3c_master_read_rx_fifo(struct dw_i3c_master *master, + u8 *bytes, int nbytes) +{ + return dw_i3c_master_read_fifo(master, RX_TX_DATA_PORT, bytes, nbytes); +} + static struct dw_i3c_xfer * dw_i3c_master_alloc_xfer(struct dw_i3c_master *master, unsigned int ncmds) { -- GitLab From e2d43101f61d6e79510d1cd9e7052b4745b8d809 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 15:50:33 +0800 Subject: [PATCH 4259/5631] i3c: dw: Turn DAT array entry into a struct In an upcoming change, we will want to store additional data about the devices we have in the data address table. Change the type of the DAT entries into a struct, which currently just has the address data. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/9dc0d9e2857e851a0cf04819df48e5d31921f83e.1680161823.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 22 +++++++++++----------- drivers/i3c/master/dw-i3c-master.h | 11 ++++++++++- 2 files changed, 21 insertions(+), 12 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index c2011447f757..0552a82c694f 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -291,7 +291,7 @@ static int dw_i3c_master_get_addr_pos(struct dw_i3c_master *master, u8 addr) int pos; for (pos = 0; pos < master->maxdevs; pos++) { - if (addr == master->addrs[pos]) + if (addr == master->devs[pos].addr) return pos; } @@ -769,7 +769,7 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m) if (ret < 0) return -ENOSPC; - master->addrs[pos] = ret; + master->devs[pos].addr = ret; p = even_parity(ret); last_addr = ret; ret |= (p << 7); @@ -806,7 +806,7 @@ static int dw_i3c_master_daa(struct i3c_master_controller *m) for (pos = 0; pos < master->maxdevs; pos++) { if (newdevs & BIT(pos)) - i3c_master_add_i3c_dev_locked(m, master->addrs[pos]); + i3c_master_add_i3c_dev_locked(m, master->devs[pos].addr); } dw_i3c_master_free_xfer(xfer); @@ -905,11 +905,11 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); - master->addrs[data->index] = 0; + master->devs[data->index].addr = 0; master->free_pos |= BIT(data->index); data->index = pos; - master->addrs[pos] = dev->info.dyn_addr; + master->devs[pos].addr = dev->info.dyn_addr; master->free_pos &= ~BIT(pos); } @@ -917,7 +917,7 @@ static int dw_i3c_master_reattach_i3c_dev(struct i3c_dev_desc *dev, master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); - master->addrs[data->index] = dev->info.dyn_addr; + master->devs[data->index].addr = dev->info.dyn_addr; return 0; } @@ -938,11 +938,11 @@ static int dw_i3c_master_attach_i3c_dev(struct i3c_dev_desc *dev) return -ENOMEM; data->index = pos; - master->addrs[pos] = dev->info.dyn_addr ? : dev->info.static_addr; + master->devs[pos].addr = dev->info.dyn_addr ? : dev->info.static_addr; master->free_pos &= ~BIT(pos); i3c_dev_set_master_data(dev, data); - writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->addrs[pos]), + writel(DEV_ADDR_TABLE_DYNAMIC_ADDR(master->devs[pos].addr), master->regs + DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); @@ -960,7 +960,7 @@ static void dw_i3c_master_detach_i3c_dev(struct i3c_dev_desc *dev) DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); i3c_dev_set_master_data(dev, NULL); - master->addrs[data->index] = 0; + master->devs[data->index].addr = 0; master->free_pos |= BIT(data->index); kfree(data); } @@ -1046,7 +1046,7 @@ static int dw_i3c_master_attach_i2c_dev(struct i2c_dev_desc *dev) return -ENOMEM; data->index = pos; - master->addrs[pos] = dev->addr; + master->devs[pos].addr = dev->addr; master->free_pos &= ~BIT(pos); i2c_dev_set_master_data(dev, data); @@ -1069,7 +1069,7 @@ static void dw_i3c_master_detach_i2c_dev(struct i2c_dev_desc *dev) DEV_ADDR_TABLE_LOC(master->datstartaddr, data->index)); i2c_dev_set_master_data(dev, NULL); - master->addrs[data->index] = 0; + master->devs[data->index].addr = 0; master->free_pos |= BIT(data->index); kfree(data); } diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h index 915dd0f2c069..5fb620727639 100644 --- a/drivers/i3c/master/dw-i3c-master.h +++ b/drivers/i3c/master/dw-i3c-master.h @@ -17,6 +17,10 @@ struct dw_i3c_master_caps { u8 datafifodepth; }; +struct dw_i3c_dat_entry { + u8 addr; +}; + struct dw_i3c_master { struct i3c_master_controller base; u16 maxdevs; @@ -33,7 +37,12 @@ struct dw_i3c_master { struct clk *core_clk; char version[5]; char type[5]; - u8 addrs[DW_I3C_MAX_DEVS]; + + /* + * Per-device hardware data, used to manage the device address table + * (DAT) + */ + struct dw_i3c_dat_entry devs[DW_I3C_MAX_DEVS]; /* platform-specific data */ const struct dw_i3c_platform_ops *platform_ops; -- GitLab From e389b1d72a6241b326071dd75e1b33f9e8818cd1 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 15:50:34 +0800 Subject: [PATCH 4260/5631] i3c: dw: Add support for in-band interrupts This change adds support for receiving and dequeueing i3c IBIs. By setting struct dw_i3c_master->ibi_capable before probe, a platform implementation can select the IBI-enabled version of the i3c_master_ops, enabling the global IBI infrastrcture for that controller. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/79daeefd7ccb7c935d0c159149df21a6c9a73ffa.1680161823.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 281 ++++++++++++++++++++++++++++- drivers/i3c/master/dw-i3c-master.h | 11 ++ 2 files changed, 289 insertions(+), 3 deletions(-) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 0552a82c694f..05f896d6e2cb 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -76,7 +76,22 @@ #define RX_TX_DATA_PORT 0x14 #define IBI_QUEUE_STATUS 0x18 +#define IBI_QUEUE_STATUS_IBI_ID(x) (((x) & GENMASK(15, 8)) >> 8) +#define IBI_QUEUE_STATUS_DATA_LEN(x) ((x) & GENMASK(7, 0)) +#define IBI_QUEUE_IBI_ADDR(x) (IBI_QUEUE_STATUS_IBI_ID(x) >> 1) +#define IBI_QUEUE_IBI_RNW(x) (IBI_QUEUE_STATUS_IBI_ID(x) & BIT(0)) +#define IBI_TYPE_MR(x) \ + ((IBI_QUEUE_IBI_ADDR(x) != I3C_HOT_JOIN_ADDR) && !IBI_QUEUE_IBI_RNW(x)) +#define IBI_TYPE_HJ(x) \ + ((IBI_QUEUE_IBI_ADDR(x) == I3C_HOT_JOIN_ADDR) && !IBI_QUEUE_IBI_RNW(x)) +#define IBI_TYPE_SIRQ(x) \ + ((IBI_QUEUE_IBI_ADDR(x) != I3C_HOT_JOIN_ADDR) && IBI_QUEUE_IBI_RNW(x)) + #define QUEUE_THLD_CTRL 0x1c +#define QUEUE_THLD_CTRL_IBI_STAT_MASK GENMASK(31, 24) +#define QUEUE_THLD_CTRL_IBI_STAT(x) (((x) - 1) << 24) +#define QUEUE_THLD_CTRL_IBI_DATA_MASK GENMASK(20, 16) +#define QUEUE_THLD_CTRL_IBI_DATA(x) ((x) << 16) #define QUEUE_THLD_CTRL_RESP_BUF_MASK GENMASK(15, 8) #define QUEUE_THLD_CTRL_RESP_BUF(x) (((x) - 1) << 8) @@ -186,6 +201,8 @@ #define EXTENDED_CAPABILITY 0xe8 #define SLAVE_CONFIG 0xec +#define DEV_ADDR_TABLE_IBI_MDB BIT(12) +#define DEV_ADDR_TABLE_SIR_REJECT BIT(13) #define DEV_ADDR_TABLE_LEGACY_I2C_DEV BIT(31) #define DEV_ADDR_TABLE_DYNAMIC_ADDR(x) (((x) << 16) & GENMASK(23, 16)) #define DEV_ADDR_TABLE_STATIC_ADDR(x) ((x) & GENMASK(6, 0)) @@ -221,6 +238,7 @@ struct dw_i3c_xfer { struct dw_i3c_i2c_dev_data { u8 index; + struct i3c_generic_ibi_pool *ibi_pool; }; static u8 even_parity(u8 p) @@ -336,6 +354,12 @@ static void dw_i3c_master_read_rx_fifo(struct dw_i3c_master *master, return dw_i3c_master_read_fifo(master, RX_TX_DATA_PORT, bytes, nbytes); } +static void dw_i3c_master_read_ibi_fifo(struct dw_i3c_master *master, + u8 *bytes, int nbytes) +{ + return dw_i3c_master_read_fifo(master, IBI_QUEUE_STATUS, bytes, nbytes); +} + static struct dw_i3c_xfer * dw_i3c_master_alloc_xfer(struct dw_i3c_master *master, unsigned int ncmds) { @@ -605,7 +629,11 @@ static int dw_i3c_master_bus_init(struct i3c_master_controller *m) } thld_ctrl = readl(master->regs + QUEUE_THLD_CTRL); - thld_ctrl &= ~QUEUE_THLD_CTRL_RESP_BUF_MASK; + thld_ctrl &= ~(QUEUE_THLD_CTRL_RESP_BUF_MASK | + QUEUE_THLD_CTRL_IBI_STAT_MASK | + QUEUE_THLD_CTRL_IBI_STAT_MASK); + thld_ctrl |= QUEUE_THLD_CTRL_IBI_STAT(1) | + QUEUE_THLD_CTRL_IBI_DATA(31); writel(thld_ctrl, master->regs + QUEUE_THLD_CTRL); thld_ctrl = readl(master->regs + DATA_BUFFER_THLD_CTRL); @@ -1074,6 +1102,226 @@ static void dw_i3c_master_detach_i2c_dev(struct i2c_dev_desc *dev) kfree(data); } +static int dw_i3c_master_request_ibi(struct i3c_dev_desc *dev, + const struct i3c_ibi_setup *req) +{ + struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct dw_i3c_master *master = to_dw_i3c_master(m); + unsigned long flags; + + data->ibi_pool = i3c_generic_ibi_alloc_pool(dev, req); + if (IS_ERR(data->ibi_pool)) + return PTR_ERR(data->ibi_pool); + + spin_lock_irqsave(&master->devs_lock, flags); + master->devs[data->index].ibi_dev = dev; + spin_unlock_irqrestore(&master->devs_lock, flags); + + return 0; +} + +static void dw_i3c_master_free_ibi(struct i3c_dev_desc *dev) +{ + struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct dw_i3c_master *master = to_dw_i3c_master(m); + unsigned long flags; + + spin_lock_irqsave(&master->devs_lock, flags); + master->devs[data->index].ibi_dev = NULL; + spin_unlock_irqrestore(&master->devs_lock, flags); + + i3c_generic_ibi_free_pool(data->ibi_pool); + data->ibi_pool = NULL; +} + +static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master, + struct i3c_dev_desc *dev, + u8 idx, bool enable) +{ + unsigned long flags; + u32 dat_entry, reg; + bool global; + + dat_entry = DEV_ADDR_TABLE_LOC(master->datstartaddr, idx); + + spin_lock_irqsave(&master->devs_lock, flags); + reg = readl(master->regs + dat_entry); + if (enable) { + reg &= ~DEV_ADDR_TABLE_SIR_REJECT; + if (dev->info.bcr & I3C_BCR_IBI_PAYLOAD) + reg |= DEV_ADDR_TABLE_IBI_MDB; + } else { + reg |= DEV_ADDR_TABLE_SIR_REJECT; + } + writel(reg, master->regs + dat_entry); + + reg = readl(master->regs + IBI_SIR_REQ_REJECT); + if (enable) { + global = reg == 0xffffffff; + reg &= ~BIT(idx); + } else { + global = reg == 0; + reg |= BIT(idx); + } + writel(reg, master->regs + IBI_SIR_REQ_REJECT); + + if (global) { + reg = readl(master->regs + INTR_STATUS_EN); + reg &= ~INTR_IBI_THLD_STAT; + if (enable) + reg |= INTR_IBI_THLD_STAT; + writel(reg, master->regs + INTR_STATUS_EN); + + reg = readl(master->regs + INTR_SIGNAL_EN); + reg &= ~INTR_IBI_THLD_STAT; + if (enable) + reg |= INTR_IBI_THLD_STAT; + writel(reg, master->regs + INTR_SIGNAL_EN); + } + + spin_unlock_irqrestore(&master->devs_lock, flags); +} + +static int dw_i3c_master_enable_ibi(struct i3c_dev_desc *dev) +{ + struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct dw_i3c_master *master = to_dw_i3c_master(m); + int rc; + + dw_i3c_master_set_sir_enabled(master, dev, data->index, true); + + rc = i3c_master_enec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR); + + if (rc) + dw_i3c_master_set_sir_enabled(master, dev, data->index, false); + + return rc; +} + +static int dw_i3c_master_disable_ibi(struct i3c_dev_desc *dev) +{ + struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + struct i3c_master_controller *m = i3c_dev_get_master(dev); + struct dw_i3c_master *master = to_dw_i3c_master(m); + int rc; + + rc = i3c_master_disec_locked(m, dev->info.dyn_addr, I3C_CCC_EVENT_SIR); + if (rc) + return rc; + + dw_i3c_master_set_sir_enabled(master, dev, data->index, false); + + return 0; +} + +static void dw_i3c_master_recycle_ibi_slot(struct i3c_dev_desc *dev, + struct i3c_ibi_slot *slot) +{ + struct dw_i3c_i2c_dev_data *data = i3c_dev_get_master_data(dev); + + i3c_generic_ibi_recycle_slot(data->ibi_pool, slot); +} + +static void dw_i3c_master_drain_ibi_queue(struct dw_i3c_master *master, + int len) +{ + int i; + + for (i = 0; i < DIV_ROUND_UP(len, 4); i++) + readl(master->regs + IBI_QUEUE_STATUS); +} + +static void dw_i3c_master_handle_ibi_sir(struct dw_i3c_master *master, + u32 status) +{ + struct dw_i3c_i2c_dev_data *data; + struct i3c_ibi_slot *slot; + struct i3c_dev_desc *dev; + unsigned long flags; + u8 addr, len; + int idx; + + addr = IBI_QUEUE_IBI_ADDR(status); + len = IBI_QUEUE_STATUS_DATA_LEN(status); + + spin_lock_irqsave(&master->devs_lock, flags); + idx = dw_i3c_master_get_addr_pos(master, addr); + if (idx < 0) { + dev_dbg_ratelimited(&master->base.dev, + "IBI from unknown addr 0x%x\n", addr); + goto err_drain; + } + + dev = master->devs[idx].ibi_dev; + if (!dev || !dev->ibi) { + dev_dbg_ratelimited(&master->base.dev, + "IBI from non-requested dev idx %d\n", idx); + goto err_drain; + } + + data = i3c_dev_get_master_data(dev); + slot = i3c_generic_ibi_get_free_slot(data->ibi_pool); + if (!slot) { + dev_dbg_ratelimited(&master->base.dev, + "No IBI slots available\n"); + goto err_drain; + } + + if (dev->ibi->max_payload_len < len) { + dev_dbg_ratelimited(&master->base.dev, + "IBI payload len %d greater than max %d\n", + len, dev->ibi->max_payload_len); + goto err_drain; + } + + if (len) { + dw_i3c_master_read_ibi_fifo(master, slot->data, len); + slot->len = len; + } + i3c_master_queue_ibi(dev, slot); + + spin_unlock_irqrestore(&master->devs_lock, flags); + + return; + +err_drain: + dw_i3c_master_drain_ibi_queue(master, len); + + spin_unlock_irqrestore(&master->devs_lock, flags); +} + +/* "ibis": referring to In-Band Interrupts, and not + * https://en.wikipedia.org/wiki/Australian_white_ibis. The latter should + * not be handled. + */ +static void dw_i3c_master_irq_handle_ibis(struct dw_i3c_master *master) +{ + unsigned int i, len, n_ibis; + u32 reg; + + reg = readl(master->regs + QUEUE_STATUS_LEVEL); + n_ibis = QUEUE_STATUS_IBI_STATUS_CNT(reg); + if (!n_ibis) + return; + + for (i = 0; i < n_ibis; i++) { + reg = readl(master->regs + IBI_QUEUE_STATUS); + + if (IBI_TYPE_SIRQ(reg)) { + dw_i3c_master_handle_ibi_sir(master, reg); + } else { + len = IBI_QUEUE_STATUS_DATA_LEN(reg); + dev_info(&master->base.dev, + "unsupported IBI type 0x%lx len %d\n", + IBI_QUEUE_STATUS_IBI_ID(reg), len); + dw_i3c_master_drain_ibi_queue(master, len); + } + } +} + static irqreturn_t dw_i3c_master_irq_handler(int irq, void *dev_id) { struct dw_i3c_master *master = dev_id; @@ -1092,6 +1340,9 @@ static irqreturn_t dw_i3c_master_irq_handler(int irq, void *dev_id) writel(INTR_TRANSFER_ERR_STAT, master->regs + INTR_STATUS); spin_unlock(&master->xferqueue.lock); + if (status & INTR_IBI_THLD_STAT) + dw_i3c_master_irq_handle_ibis(master); + return IRQ_HANDLED; } @@ -1110,6 +1361,26 @@ static const struct i3c_master_controller_ops dw_mipi_i3c_ops = { .i2c_xfers = dw_i3c_master_i2c_xfers, }; +static const struct i3c_master_controller_ops dw_mipi_i3c_ibi_ops = { + .bus_init = dw_i3c_master_bus_init, + .bus_cleanup = dw_i3c_master_bus_cleanup, + .attach_i3c_dev = dw_i3c_master_attach_i3c_dev, + .reattach_i3c_dev = dw_i3c_master_reattach_i3c_dev, + .detach_i3c_dev = dw_i3c_master_detach_i3c_dev, + .do_daa = dw_i3c_master_daa, + .supports_ccc_cmd = dw_i3c_master_supports_ccc_cmd, + .send_ccc_cmd = dw_i3c_master_send_ccc_cmd, + .priv_xfers = dw_i3c_master_priv_xfers, + .attach_i2c_dev = dw_i3c_master_attach_i2c_dev, + .detach_i2c_dev = dw_i3c_master_detach_i2c_dev, + .i2c_xfers = dw_i3c_master_i2c_xfers, + .request_ibi = dw_i3c_master_request_ibi, + .free_ibi = dw_i3c_master_free_ibi, + .enable_ibi = dw_i3c_master_enable_ibi, + .disable_ibi = dw_i3c_master_disable_ibi, + .recycle_ibi_slot = dw_i3c_master_recycle_ibi_slot, +}; + /* default platform ops implementations */ static int dw_i3c_platform_init_nop(struct dw_i3c_master *i3c) { @@ -1123,6 +1394,7 @@ static const struct dw_i3c_platform_ops dw_i3c_platform_ops_default = { int dw_i3c_common_probe(struct dw_i3c_master *master, struct platform_device *pdev) { + const struct i3c_master_controller_ops *ops; int ret, irq; if (!master->platform_ops) @@ -1172,8 +1444,11 @@ int dw_i3c_common_probe(struct dw_i3c_master *master, master->maxdevs = ret >> 16; master->free_pos = GENMASK(master->maxdevs - 1, 0); - ret = i3c_master_register(&master->base, &pdev->dev, - &dw_mipi_i3c_ops, false); + ops = &dw_mipi_i3c_ops; + if (master->ibi_capable) + ops = &dw_mipi_i3c_ibi_ops; + + ret = i3c_master_register(&master->base, &pdev->dev, ops, false); if (ret) goto err_assert_rst; diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h index 5fb620727639..a5425fa6b7d4 100644 --- a/drivers/i3c/master/dw-i3c-master.h +++ b/drivers/i3c/master/dw-i3c-master.h @@ -19,6 +19,7 @@ struct dw_i3c_master_caps { struct dw_i3c_dat_entry { u8 addr; + struct i3c_dev_desc *ibi_dev; }; struct dw_i3c_master { @@ -37,12 +38,22 @@ struct dw_i3c_master { struct clk *core_clk; char version[5]; char type[5]; + bool ibi_capable; /* * Per-device hardware data, used to manage the device address table * (DAT) + * + * Locking: the devs array may be referenced in IRQ context while + * processing an IBI. However, IBIs (for a specific device, which + * implies a specific DAT entry) can only happen while interrupts are + * requested for that device, which is serialised against other + * insertions/removals from the array by the global i3c infrastructure. + * So, devs_lock protects against concurrent updates to devs->ibi_dev + * between request_ibi/free_ibi and the IBI irq event. */ struct dw_i3c_dat_entry devs[DW_I3C_MAX_DEVS]; + spinlock_t devs_lock; /* platform-specific data */ const struct dw_i3c_platform_ops *platform_ops; -- GitLab From f3a3553a51e64379dbb2e980f0024f7a28b74977 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 15:50:35 +0800 Subject: [PATCH 4261/5631] i3c: dw: Add a platform facility for IBI PEC workarounds On the AST2600 i3c controller, we'll need to apply a workaround for a hardware issue with IBI payloads. Introduce a platform hook to allow dw i3c platform implementations to modify the DAT entry in IBI enable/disable to allow this workaround in a future change. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/d5d76a8d2336d2a71886537f42e71d51db184df6.1680161823.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/dw-i3c-master.c | 19 +++++++++++++++++++ drivers/i3c/master/dw-i3c-master.h | 10 ++++++++++ 2 files changed, 29 insertions(+) diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index 05f896d6e2cb..9332ae5f6419 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -1155,6 +1155,7 @@ static void dw_i3c_master_set_sir_enabled(struct dw_i3c_master *master, } else { reg |= DEV_ADDR_TABLE_SIR_REJECT; } + master->platform_ops->set_dat_ibi(master, dev, enable, ®); writel(reg, master->regs + dat_entry); reg = readl(master->regs + IBI_SIR_REQ_REJECT); @@ -1247,6 +1248,17 @@ static void dw_i3c_master_handle_ibi_sir(struct dw_i3c_master *master, addr = IBI_QUEUE_IBI_ADDR(status); len = IBI_QUEUE_STATUS_DATA_LEN(status); + /* + * We be tempted to check the error status in bit 30; however, due + * to the PEC errata workaround on some platform implementations (see + * ast2600_i3c_set_dat_ibi()), those will almost always have a PEC + * error on IBI payload data, as well as losing the last byte of + * payload. + * + * If we implement error status checking on that bit, we may need + * a new platform op to validate it. + */ + spin_lock_irqsave(&master->devs_lock, flags); idx = dw_i3c_master_get_addr_pos(master, addr); if (idx < 0) { @@ -1387,8 +1399,15 @@ static int dw_i3c_platform_init_nop(struct dw_i3c_master *i3c) return 0; } +static void dw_i3c_platform_set_dat_ibi_nop(struct dw_i3c_master *i3c, + struct i3c_dev_desc *dev, + bool enable, u32 *dat) +{ +} + static const struct dw_i3c_platform_ops dw_i3c_platform_ops_default = { .init = dw_i3c_platform_init_nop, + .set_dat_ibi = dw_i3c_platform_set_dat_ibi_nop, }; int dw_i3c_common_probe(struct dw_i3c_master *master, diff --git a/drivers/i3c/master/dw-i3c-master.h b/drivers/i3c/master/dw-i3c-master.h index a5425fa6b7d4..ab862c5d15fe 100644 --- a/drivers/i3c/master/dw-i3c-master.h +++ b/drivers/i3c/master/dw-i3c-master.h @@ -66,6 +66,16 @@ struct dw_i3c_platform_ops { * perform actual device enabling with the i3c core ready. */ int (*init)(struct dw_i3c_master *i3c); + + /* + * Initialise a DAT entry to enable/disable IBIs. Allows the platform + * to perform any device workarounds on the DAT entry before + * inserting into the hardware table. + * + * Called with the DAT lock held; must not sleep. + */ + void (*set_dat_ibi)(struct dw_i3c_master *i3c, + struct i3c_dev_desc *dev, bool enable, u32 *reg); }; extern int dw_i3c_common_probe(struct dw_i3c_master *master, -- GitLab From f2539c20791eb474ae083f60a572f207ffbc3a67 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Thu, 30 Mar 2023 15:50:36 +0800 Subject: [PATCH 4262/5631] i3c: ast2600: enable IBI support The ast2600 i3c hardware is capable of IBIs, but we need a workaround for a hardware issue with the I3C state machine handling IBI payloads of specific lengths when PEC is not enabled. To avoid this, we need to unconditionally enable PECs, at the consquence of losing a byte of data when the device does not send a PEC. Enable IBIs on the ast2600 platform, including an implementation of the PEC workaround, which prints a warning when triggered. Signed-off-by: Jeremy Kerr Reviewed-by: Joel Stanley Link: https://lore.kernel.org/r/ba923b96d6d129024c975e8a0472c5b2fcb3af32.1680161823.git.jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/ast2600-i3c-master.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c index b3f0fe1e63c3..6715d1f044b6 100644 --- a/drivers/i3c/master/ast2600-i3c-master.c +++ b/drivers/i3c/master/ast2600-i3c-master.c @@ -36,6 +36,8 @@ #define AST2600_DEFAULT_SDA_PULLUP_OHMS 2000 +#define DEV_ADDR_TABLE_IBI_PEC BIT(11) + struct ast2600_i3c { struct dw_i3c_master dw; struct regmap *global_regs; @@ -99,8 +101,26 @@ static int ast2600_i3c_init(struct dw_i3c_master *dw) return rc; } +static void ast2600_i3c_set_dat_ibi(struct dw_i3c_master *i3c, + struct i3c_dev_desc *dev, + bool enable, u32 *dat) +{ + /* + * The ast2600 i3c controller will lock up on receiving 4n+1-byte IBIs + * if the PEC is disabled. We have no way to restrict the length of + * IBIs sent to the controller, so we need to unconditionally enable + * PEC checking, which means we drop a byte of payload data + */ + if (enable && dev->info.bcr & I3C_BCR_IBI_PAYLOAD) { + dev_warn_once(&i3c->base.dev, + "Enabling PEC workaround. IBI payloads will be truncated\n"); + *dat |= DEV_ADDR_TABLE_IBI_PEC; + } +} + const struct dw_i3c_platform_ops ast2600_i3c_ops = { .init = ast2600_i3c_init, + .set_dat_ibi = ast2600_i3c_set_dat_ibi, }; static int ast2600_i3c_probe(struct platform_device *pdev) @@ -137,6 +157,7 @@ static int ast2600_i3c_probe(struct platform_device *pdev) i3c->sda_pullup); i3c->dw.platform_ops = &ast2600_i3c_ops; + i3c->dw.ibi_capable = true; return dw_i3c_common_probe(&i3c->dw, pdev); } -- GitLab From 8c6c78ee3b3330cf8a00a3c6bdecc18d42e969d7 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 28 Apr 2023 08:18:49 +0800 Subject: [PATCH 4263/5631] i3c: ast2600: fix register setting for 545 ohm pullups The 2k register setting is zero, OR-ing it in doesn't parallel the 2k and 750 ohm pullups. We need a separate value for the 545 ohm setting. Reported-by: Lukwinski Zbigniew Signed-off-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230428001849.1775559-1-jk@codeconstruct.com.au Signed-off-by: Alexandre Belloni --- drivers/i3c/master/ast2600-i3c-master.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c index 6715d1f044b6..b72c12c5168f 100644 --- a/drivers/i3c/master/ast2600-i3c-master.c +++ b/drivers/i3c/master/ast2600-i3c-master.c @@ -21,6 +21,7 @@ #define AST2600_I3CG_REG0_SDA_PULLUP_EN_MASK GENMASK(29, 28) #define AST2600_I3CG_REG0_SDA_PULLUP_EN_2K (0x0 << 28) #define AST2600_I3CG_REG0_SDA_PULLUP_EN_750 (0x2 << 28) +#define AST2600_I3CG_REG0_SDA_PULLUP_EN_545 (0x3 << 28) #define AST2600_I3CG_REG1_I2C_MODE BIT(0) #define AST2600_I3CG_REG1_TEST_MODE BIT(1) @@ -62,8 +63,7 @@ static int ast2600_i3c_pullup_to_reg(unsigned int ohms, u32 *regp) reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_750; break; case 545: - reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_2K | - AST2600_I3CG_REG0_SDA_PULLUP_EN_750; + reg = AST2600_I3CG_REG0_SDA_PULLUP_EN_545; break; default: return -EINVAL; -- GitLab From 6f75cd166a5a3c0bc50441faa8b8304f60522fdd Mon Sep 17 00:00:00 2001 From: Cosmo Chou Date: Wed, 26 Apr 2023 16:13:50 +0800 Subject: [PATCH 4264/5631] net/ncsi: clear Tx enable mode when handling a Config required AEN ncsi_channel_is_tx() determines whether a given channel should be used for Tx or not. However, when reconfiguring the channel by handling a Configuration Required AEN, there is a misjudgment that the channel Tx has already been enabled, which results in the Enable Channel Network Tx command not being sent. Clear the channel Tx enable flag before reconfiguring the channel to avoid the misjudgment. Fixes: 8d951a75d022 ("net/ncsi: Configure multi-package, multi-channel modes with failover") Signed-off-by: Cosmo Chou Signed-off-by: David S. Miller --- net/ncsi/ncsi-aen.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index b635c194f0a8..62fb1031763d 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -165,6 +165,7 @@ static int ncsi_aen_handler_cr(struct ncsi_dev_priv *ndp, nc->state = NCSI_CHANNEL_INACTIVE; list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); + nc->modes[NCSI_MODE_TX_ENABLE].enable = 0; return ncsi_process_next_channel(ndp); } -- GitLab From 7e692df3933628d974acb9f5b334d2b3e885e2a6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 28 Apr 2023 04:32:31 +0000 Subject: [PATCH 4265/5631] tcp: fix skb_copy_ubufs() vs BIG TCP David Ahern reported crashes in skb_copy_ubufs() caused by TCP tx zerocopy using hugepages, and skb length bigger than ~68 KB. skb_copy_ubufs() assumed it could copy all payload using up to MAX_SKB_FRAGS order-0 pages. This assumption broke when BIG TCP was able to put up to 512 KB per skb. We did not hit this bug at Google because we use CONFIG_MAX_SKB_FRAGS=45 and limit gso_max_size to 180000. A solution is to use higher order pages if needed. v2: add missing __GFP_COMP, or we leak memory. Fixes: 7c4e983c4f3c ("net: allow gso_max_size to exceed 65536") Reported-by: David Ahern Link: https://lore.kernel.org/netdev/c70000f6-baa4-4a05-46d0-4b3e0dc1ccc8@gmail.com/T/ Signed-off-by: Eric Dumazet Cc: Xin Long Cc: Willem de Bruijn Cc: Coco Li Signed-off-by: David S. Miller --- net/core/skbuff.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2112146092bf..26a586007d8b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1758,7 +1758,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) { int num_frags = skb_shinfo(skb)->nr_frags; struct page *page, *head = NULL; - int i, new_frags; + int i, order, psize, new_frags; u32 d_off; if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) @@ -1767,9 +1767,17 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) if (!num_frags) goto release; - new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT; + /* We might have to allocate high order pages, so compute what minimum + * page order is needed. + */ + order = 0; + while ((PAGE_SIZE << order) * MAX_SKB_FRAGS < __skb_pagelen(skb)) + order++; + psize = (PAGE_SIZE << order); + + new_frags = (__skb_pagelen(skb) + psize - 1) >> (PAGE_SHIFT + order); for (i = 0; i < new_frags; i++) { - page = alloc_page(gfp_mask); + page = alloc_pages(gfp_mask | __GFP_COMP, order); if (!page) { while (head) { struct page *next = (struct page *)page_private(head); @@ -1796,11 +1804,11 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) vaddr = kmap_atomic(p); while (done < p_len) { - if (d_off == PAGE_SIZE) { + if (d_off == psize) { d_off = 0; page = (struct page *)page_private(page); } - copy = min_t(u32, PAGE_SIZE - d_off, p_len - done); + copy = min_t(u32, psize - d_off, p_len - done); memcpy(page_address(page) + d_off, vaddr + p_off + done, copy); done += copy; @@ -1816,7 +1824,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) /* skb frags point to kernel buffers */ for (i = 0; i < new_frags - 1; i++) { - __skb_fill_page_desc(skb, i, head, 0, PAGE_SIZE); + __skb_fill_page_desc(skb, i, head, 0, psize); head = (struct page *)page_private(head); } __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); -- GitLab From e0807c430239d62d8dd7a25552e469aad8c3dd28 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 27 Apr 2023 15:39:48 +0200 Subject: [PATCH 4266/5631] mISDN: Use list_count_nodes() count_list_member() really looks the same as list_count_nodes(), so use the latter instead of hand writing it. The first one return an int and the other a size_t, but that should be fine. It is really unlikely that we get so many parties in a conference. Signed-off-by: Christophe JAILLET Signed-off-by: David S. Miller --- drivers/isdn/mISDN/dsp_cmx.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 6d2088fbaf69..357b87592eb4 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -141,17 +141,6 @@ /*#define CMX_DELAY_DEBUG * gives rx-buffer delay overview */ /*#define CMX_TX_DEBUG * massive read/write on tx-buffer with content */ -static inline int -count_list_member(struct list_head *head) -{ - int cnt = 0; - struct list_head *m; - - list_for_each(m, head) - cnt++; - return cnt; -} - /* * debug cmx memory structure */ @@ -1672,7 +1661,7 @@ dsp_cmx_send(void *arg) mustmix = 0; members = 0; if (conf) { - members = count_list_member(&conf->mlist); + members = list_count_nodes(&conf->mlist); #ifdef CMX_CONF_DEBUG if (conf->software && members > 1) #else @@ -1695,7 +1684,7 @@ dsp_cmx_send(void *arg) /* loop all members that require conference mixing */ list_for_each_entry(conf, &conf_ilist, list) { /* count members and check hardware */ - members = count_list_member(&conf->mlist); + members = list_count_nodes(&conf->mlist); #ifdef CMX_CONF_DEBUG if (conf->software && members > 1) { #else -- GitLab From da94a7781fc3c92e7df7832bc2746f4d39bc624e Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 26 Apr 2023 14:31:11 +0200 Subject: [PATCH 4267/5631] net/sched: cls_api: remove block_cb from driver_list before freeing Error handler of tcf_block_bind() frees the whole bo->cb_list on error. However, by that time the flow_block_cb instances are already in the driver list because driver ndo_setup_tc() callback is called before that up the call chain in tcf_block_offload_cmd(). This leaves dangling pointers to freed objects in the list and causes use-after-free[0]. Fix it by also removing flow_block_cb instances from driver_list before deallocating them. [0]: [ 279.868433] ================================================================== [ 279.869964] BUG: KASAN: slab-use-after-free in flow_block_cb_setup_simple+0x631/0x7c0 [ 279.871527] Read of size 8 at addr ffff888147e2bf20 by task tc/2963 [ 279.873151] CPU: 6 PID: 2963 Comm: tc Not tainted 6.3.0-rc6+ #4 [ 279.874273] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 279.876295] Call Trace: [ 279.876882] [ 279.877413] dump_stack_lvl+0x33/0x50 [ 279.878198] print_report+0xc2/0x610 [ 279.878987] ? flow_block_cb_setup_simple+0x631/0x7c0 [ 279.879994] kasan_report+0xae/0xe0 [ 279.880750] ? flow_block_cb_setup_simple+0x631/0x7c0 [ 279.881744] ? mlx5e_tc_reoffload_flows_work+0x240/0x240 [mlx5_core] [ 279.883047] flow_block_cb_setup_simple+0x631/0x7c0 [ 279.884027] tcf_block_offload_cmd.isra.0+0x189/0x2d0 [ 279.885037] ? tcf_block_setup+0x6b0/0x6b0 [ 279.885901] ? mutex_lock+0x7d/0xd0 [ 279.886669] ? __mutex_unlock_slowpath.constprop.0+0x2d0/0x2d0 [ 279.887844] ? ingress_init+0x1c0/0x1c0 [sch_ingress] [ 279.888846] tcf_block_get_ext+0x61c/0x1200 [ 279.889711] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.890682] ? clsact_init+0x2b0/0x2b0 [sch_ingress] [ 279.891701] qdisc_create+0x401/0xea0 [ 279.892485] ? qdisc_tree_reduce_backlog+0x470/0x470 [ 279.893473] tc_modify_qdisc+0x6f7/0x16d0 [ 279.894344] ? tc_get_qdisc+0xac0/0xac0 [ 279.895213] ? mutex_lock+0x7d/0xd0 [ 279.896005] ? __mutex_lock_slowpath+0x10/0x10 [ 279.896910] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.897770] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 279.898672] ? __sys_sendmsg+0xb5/0x140 [ 279.899494] ? do_syscall_64+0x3d/0x90 [ 279.900302] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.901337] ? kasan_save_stack+0x2e/0x40 [ 279.902177] ? kasan_save_stack+0x1e/0x40 [ 279.903058] ? kasan_set_track+0x21/0x30 [ 279.903913] ? kasan_save_free_info+0x2a/0x40 [ 279.904836] ? ____kasan_slab_free+0x11a/0x1b0 [ 279.905741] ? kmem_cache_free+0x179/0x400 [ 279.906599] netlink_rcv_skb+0x12c/0x360 [ 279.907450] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 279.908360] ? netlink_ack+0x1550/0x1550 [ 279.909192] ? rhashtable_walk_peek+0x170/0x170 [ 279.910135] ? kmem_cache_alloc_node+0x1af/0x390 [ 279.911086] ? _copy_from_iter+0x3d6/0xc70 [ 279.912031] netlink_unicast+0x553/0x790 [ 279.912864] ? netlink_attachskb+0x6a0/0x6a0 [ 279.913763] ? netlink_recvmsg+0x416/0xb50 [ 279.914627] netlink_sendmsg+0x7a1/0xcb0 [ 279.915473] ? netlink_unicast+0x790/0x790 [ 279.916334] ? iovec_from_user.part.0+0x4d/0x220 [ 279.917293] ? netlink_unicast+0x790/0x790 [ 279.918159] sock_sendmsg+0xc5/0x190 [ 279.918938] ____sys_sendmsg+0x535/0x6b0 [ 279.919813] ? import_iovec+0x7/0x10 [ 279.920601] ? kernel_sendmsg+0x30/0x30 [ 279.921423] ? __copy_msghdr+0x3c0/0x3c0 [ 279.922254] ? import_iovec+0x7/0x10 [ 279.923041] ___sys_sendmsg+0xeb/0x170 [ 279.923854] ? copy_msghdr_from_user+0x110/0x110 [ 279.924797] ? ___sys_recvmsg+0xd9/0x130 [ 279.925630] ? __perf_event_task_sched_in+0x183/0x470 [ 279.926656] ? ___sys_sendmsg+0x170/0x170 [ 279.927529] ? ctx_sched_in+0x530/0x530 [ 279.928369] ? update_curr+0x283/0x4f0 [ 279.929185] ? perf_event_update_userpage+0x570/0x570 [ 279.930201] ? __fget_light+0x57/0x520 [ 279.931023] ? __switch_to+0x53d/0xe70 [ 279.931846] ? sockfd_lookup_light+0x1a/0x140 [ 279.932761] __sys_sendmsg+0xb5/0x140 [ 279.933560] ? __sys_sendmsg_sock+0x20/0x20 [ 279.934436] ? fpregs_assert_state_consistent+0x1d/0xa0 [ 279.935490] do_syscall_64+0x3d/0x90 [ 279.936300] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.937311] RIP: 0033:0x7f21c814f887 [ 279.938085] Code: 0a 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 279.941448] RSP: 002b:00007fff11efd478 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 279.942964] RAX: ffffffffffffffda RBX: 0000000064401979 RCX: 00007f21c814f887 [ 279.944337] RDX: 0000000000000000 RSI: 00007fff11efd4e0 RDI: 0000000000000003 [ 279.945660] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 [ 279.947003] R10: 00007f21c8008708 R11: 0000000000000246 R12: 0000000000000001 [ 279.948345] R13: 0000000000409980 R14: 000000000047e538 R15: 0000000000485400 [ 279.949690] [ 279.950706] Allocated by task 2960: [ 279.951471] kasan_save_stack+0x1e/0x40 [ 279.952338] kasan_set_track+0x21/0x30 [ 279.953165] __kasan_kmalloc+0x77/0x90 [ 279.954006] flow_block_cb_setup_simple+0x3dd/0x7c0 [ 279.955001] tcf_block_offload_cmd.isra.0+0x189/0x2d0 [ 279.956020] tcf_block_get_ext+0x61c/0x1200 [ 279.956881] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.957873] qdisc_create+0x401/0xea0 [ 279.958656] tc_modify_qdisc+0x6f7/0x16d0 [ 279.959506] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.960392] netlink_rcv_skb+0x12c/0x360 [ 279.961216] netlink_unicast+0x553/0x790 [ 279.962044] netlink_sendmsg+0x7a1/0xcb0 [ 279.962906] sock_sendmsg+0xc5/0x190 [ 279.963702] ____sys_sendmsg+0x535/0x6b0 [ 279.964534] ___sys_sendmsg+0xeb/0x170 [ 279.965343] __sys_sendmsg+0xb5/0x140 [ 279.966132] do_syscall_64+0x3d/0x90 [ 279.966908] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.968407] Freed by task 2960: [ 279.969114] kasan_save_stack+0x1e/0x40 [ 279.969929] kasan_set_track+0x21/0x30 [ 279.970729] kasan_save_free_info+0x2a/0x40 [ 279.971603] ____kasan_slab_free+0x11a/0x1b0 [ 279.972483] __kmem_cache_free+0x14d/0x280 [ 279.973337] tcf_block_setup+0x29d/0x6b0 [ 279.974173] tcf_block_offload_cmd.isra.0+0x226/0x2d0 [ 279.975186] tcf_block_get_ext+0x61c/0x1200 [ 279.976080] ingress_init+0x112/0x1c0 [sch_ingress] [ 279.977065] qdisc_create+0x401/0xea0 [ 279.977857] tc_modify_qdisc+0x6f7/0x16d0 [ 279.978695] rtnetlink_rcv_msg+0x5fe/0x9d0 [ 279.979562] netlink_rcv_skb+0x12c/0x360 [ 279.980388] netlink_unicast+0x553/0x790 [ 279.981214] netlink_sendmsg+0x7a1/0xcb0 [ 279.982043] sock_sendmsg+0xc5/0x190 [ 279.982827] ____sys_sendmsg+0x535/0x6b0 [ 279.983703] ___sys_sendmsg+0xeb/0x170 [ 279.984510] __sys_sendmsg+0xb5/0x140 [ 279.985298] do_syscall_64+0x3d/0x90 [ 279.986076] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 279.987532] The buggy address belongs to the object at ffff888147e2bf00 which belongs to the cache kmalloc-192 of size 192 [ 279.989747] The buggy address is located 32 bytes inside of freed 192-byte region [ffff888147e2bf00, ffff888147e2bfc0) [ 279.992367] The buggy address belongs to the physical page: [ 279.993430] page:00000000550f405c refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x147e2a [ 279.995182] head:00000000550f405c order:1 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [ 279.996713] anon flags: 0x200000000010200(slab|head|node=0|zone=2) [ 279.997878] raw: 0200000000010200 ffff888100042a00 0000000000000000 dead000000000001 [ 279.999384] raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000 [ 280.000894] page dumped because: kasan: bad access detected [ 280.002386] Memory state around the buggy address: [ 280.003338] ffff888147e2be00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.004781] ffff888147e2be80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 280.006224] >ffff888147e2bf00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.007700] ^ [ 280.008592] ffff888147e2bf80: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 280.010035] ffff888147e2c000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [ 280.011564] ================================================================== Fixes: 59094b1e5094 ("net: sched: use flow block API") Signed-off-by: Vlad Buslov Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/sched/cls_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3c3629c9e7b6..2621550bfddc 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1589,6 +1589,7 @@ static int tcf_block_bind(struct tcf_block *block, err_unroll: list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { + list_del(&block_cb->driver_list); if (i-- > 0) { list_del(&block_cb->list); tcf_block_playback_offloads(block, block_cb->cb, -- GitLab From c88f8d5cd95fd039cff95d682b8e71100c001df0 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 26 Apr 2023 23:00:06 -0700 Subject: [PATCH 4268/5631] sit: update dev->needed_headroom in ipip6_tunnel_bind_dev() When a tunnel device is bound with the underlying device, its dev->needed_headroom needs to be updated properly. IPv4 tunnels already do the same in ip_tunnel_bind_dev(). Otherwise we may not have enough header room for skb, especially after commit b17f709a2401 ("gue: TX support for using remote checksum offload option"). Fixes: 32b8a8e59c9c ("sit: add IPv4 over IPv4 support") Reported-by: Palash Oswal Link: https://lore.kernel.org/netdev/CAGyP=7fDcSPKu6nttbGwt7RXzE3uyYxLjCSE97J64pRxJP8jPA@mail.gmail.com/ Cc: Kuniyuki Iwashima Cc: Eric Dumazet Signed-off-by: Cong Wang Reviewed-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv6/sit.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 063560e2cb1a..cc24cefdb85c 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1095,12 +1095,13 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, static void ipip6_tunnel_bind_dev(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; + int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; - tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { @@ -1123,14 +1124,15 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { - int t_hlen = tunnel->hlen + sizeof(struct iphdr); int mtu; mtu = tdev->mtu - t_hlen; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); + hlen = tdev->hard_header_len + tdev->needed_headroom; } + dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, -- GitLab From 042334a8d424a1917e916e611a8dda7f8caf1491 Mon Sep 17 00:00:00 2001 From: wuych Date: Thu, 27 Apr 2023 18:25:31 +0800 Subject: [PATCH 4269/5631] atlantic:hw_atl2:hw_atl2_utils_fw: Remove unnecessary (void*) conversions Pointer variables of void * type do not require type cast. Signed-off-by: wuych Signed-off-by: David S. Miller --- .../net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c index 58d426dda3ed..674683b54304 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2_utils_fw.c @@ -336,7 +336,7 @@ static int aq_a2_fw_get_mac_permanent(struct aq_hw_s *self, u8 *mac) static void aq_a2_fill_a0_stats(struct aq_hw_s *self, struct statistics_s *stats) { - struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv; + struct hw_atl2_priv *priv = self->priv; struct aq_stats_s *cs = &self->curr_stats; struct aq_stats_s curr_stats = *cs; bool corrupted_stats = false; @@ -378,7 +378,7 @@ do { \ static void aq_a2_fill_b0_stats(struct aq_hw_s *self, struct statistics_s *stats) { - struct hw_atl2_priv *priv = (struct hw_atl2_priv *)self->priv; + struct hw_atl2_priv *priv = self->priv; struct aq_stats_s *cs = &self->curr_stats; struct aq_stats_s curr_stats = *cs; bool corrupted_stats = false; -- GitLab From 46ef24c60f8ee70662968ac55325297ed4624d61 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Thu, 27 Apr 2023 11:49:23 +0200 Subject: [PATCH 4270/5631] selftests: srv6: make srv6_end_dt46_l3vpn_test more robust On some distributions, the rp_filter is automatically set (=1) by default on a netdev basis (also on VRFs). In an SRv6 End.DT46 behavior, decapsulated IPv4 packets are routed using the table associated with the VRF bound to that tunnel. During lookup operations, the rp_filter can lead to packet loss when activated on the VRF. Therefore, we chose to make this selftest more robust by explicitly disabling the rp_filter during tests (as it is automatically set by some Linux distributions). Fixes: 03a0b567a03d ("selftests: seg6: add selftest for SRv6 End.DT46 Behavior") Reported-by: Hangbin Liu Signed-off-by: Andrea Mayer Tested-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: David S. Miller --- .../testing/selftests/net/srv6_end_dt46_l3vpn_test.sh | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh index aebaab8ce44c..441eededa031 100755 --- a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh @@ -292,6 +292,11 @@ setup_hs() ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad @@ -316,11 +321,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } -- GitLab From dc6456e938e938d64ffb6383a286b2ac9790a37f Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Thu, 27 Apr 2023 11:21:59 +0200 Subject: [PATCH 4271/5631] net: ipv6: fix skb hash for some RST packets The skb hash comes from sk->sk_txhash when using TCP, except for some IPv6 RST packets. This is because in tcp_v6_send_reset when not in TIME_WAIT the hash is taken from sk->sk_hash, while it should come from sk->sk_txhash as those two hashes are not computed the same way. Packetdrill script to test the above, 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) +0 > (flowlabel 0x1) S 0:0(0) <...> // Wrong ack seq, trigger a rst. +0 < S. 0:0(0) ack 0 win 4000 // Check the flowlabel matches prior one from SYN. +0 > (flowlabel 0x1) R 0:0(0) <...> Fixes: 9258b8b1be2e ("ipv6: tcp: send consistent autoflowlabel in RST packets") Signed-off-by: Antoine Tenart Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 244cf86c4cbb..7132eb213a7a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1065,7 +1065,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) if (np->repflow) label = ip6_flowlabel(ipv6h); priority = sk->sk_priority; - txhash = sk->sk_hash; + txhash = sk->sk_txhash; } if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); -- GitLab From 6686317855c6997671982d4489ccdd946f644957 Mon Sep 17 00:00:00 2001 From: Angelo Dureghello Date: Wed, 26 Apr 2023 22:28:15 +0200 Subject: [PATCH 4272/5631] net: dsa: mv88e6xxx: add mv88e6321 rsvd2cpu Add rsvd2cpu capability for mv88e6321 model, to allow proper bpdu processing. Signed-off-by: Angelo Dureghello Fixes: 51c901a775621 ("net: dsa: mv88e6xxx: distinguish Global 2 Rsvd2CPU") Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index dc263cea205f..64a2f2f83735 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -5194,6 +5194,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .set_cpu_port = mv88e6095_g1_set_cpu_port, .set_egress_port = mv88e6095_g1_set_egress_port, .watchdog_ops = &mv88e6390_watchdog_ops, + .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, -- GitLab From 9d2f38638a145f0c6102bee6533204aa3e5a9c07 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Fri, 28 Apr 2023 10:07:32 +0200 Subject: [PATCH 4273/5631] ALSA: emu10k1: use more existing defines instead of open-coded numbers Using the *_MASK defines for "maximal value" is debatable. I got the idea from FreeBSD, and it sorta makes sense to me. Some hunks look a bit incomplete, because code that is going to be subsequently removed is not touched here. Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230428080732.1697695-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/pci/emu10k1/emu10k1_callback.c | 15 ++++----- sound/pci/emu10k1/emu10k1_main.c | 46 ++++++++++++++-------------- sound/pci/emu10k1/emufx.c | 6 ++-- sound/pci/emu10k1/emumixer.c | 8 ++--- sound/pci/emu10k1/emupcm.c | 12 ++++---- sound/pci/emu10k1/io.c | 18 +++++------ sound/pci/emu10k1/p16v.c | 29 ++++++++++-------- 7 files changed, 69 insertions(+), 65 deletions(-) diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c index c6d152575181..9455df18f7b2 100644 --- a/sound/pci/emu10k1/emu10k1_callback.c +++ b/sound/pci/emu10k1/emu10k1_callback.c @@ -120,9 +120,9 @@ release_voice(struct snd_emux_voice *vp) struct snd_emu10k1 *hw; hw = vp->hw; - dcysusv = 0x8000 | (unsigned char)vp->reg.parm.modrelease; + dcysusv = (unsigned char)vp->reg.parm.modrelease | DCYSUSM_PHASE1_MASK; snd_emu10k1_ptr_write(hw, DCYSUSM, vp->ch, dcysusv); - dcysusv = 0x8000 | (unsigned char)vp->reg.parm.volrelease | DCYSUSV_CHANNELENABLE_MASK; + dcysusv = (unsigned char)vp->reg.parm.volrelease | DCYSUSV_PHASE1_MASK | DCYSUSV_CHANNELENABLE_MASK; snd_emu10k1_ptr_write(hw, DCYSUSV, vp->ch, dcysusv); } @@ -138,7 +138,8 @@ terminate_voice(struct snd_emux_voice *vp) if (snd_BUG_ON(!vp)) return; hw = vp->hw; - snd_emu10k1_ptr_write(hw, DCYSUSV, vp->ch, 0x807f | DCYSUSV_CHANNELENABLE_MASK); + snd_emu10k1_ptr_write(hw, DCYSUSV, vp->ch, + DCYSUSV_PHASE1_MASK | DCYSUSV_DECAYTIME_MASK | DCYSUSV_CHANNELENABLE_MASK); if (vp->block) { struct snd_emu10k1_memblk *emem; emem = (struct snd_emu10k1_memblk *)vp->block; @@ -347,9 +348,9 @@ start_voice(struct snd_emux_voice *vp) } /* channel to be silent and idle */ - snd_emu10k1_ptr_write(hw, DCYSUSV, ch, 0x0000); - snd_emu10k1_ptr_write(hw, VTFT, ch, 0x0000FFFF); - snd_emu10k1_ptr_write(hw, CVCF, ch, 0x0000FFFF); + snd_emu10k1_ptr_write(hw, DCYSUSV, ch, 0); + snd_emu10k1_ptr_write(hw, VTFT, ch, VTFT_FILTERTARGET_MASK); + snd_emu10k1_ptr_write(hw, CVCF, ch, CVCF_CURRENTFILTER_MASK); snd_emu10k1_ptr_write(hw, PTRX, ch, 0); snd_emu10k1_ptr_write(hw, CPF, ch, 0); @@ -453,7 +454,7 @@ start_voice(struct snd_emux_voice *vp) /* reset volume */ temp = (unsigned int)vp->vtarget << 16; snd_emu10k1_ptr_write(hw, VTFT, ch, temp | vp->ftarget); - snd_emu10k1_ptr_write(hw, CVCF, ch, temp | 0xff00); + snd_emu10k1_ptr_write(hw, CVCF, ch, temp | CVCF_CURRENTFILTER_MASK); return 0; } diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index 3abdaf1b9624..192208c291d6 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -59,8 +59,8 @@ void snd_emu10k1_voice_init(struct snd_emu10k1 *emu, int ch) { snd_emu10k1_ptr_write(emu, DCYSUSV, ch, 0); snd_emu10k1_ptr_write(emu, IP, ch, 0); - snd_emu10k1_ptr_write(emu, VTFT, ch, 0xffff); - snd_emu10k1_ptr_write(emu, CVCF, ch, 0xffff); + snd_emu10k1_ptr_write(emu, VTFT, ch, VTFT_FILTERTARGET_MASK); + snd_emu10k1_ptr_write(emu, CVCF, ch, CVCF_CURRENTFILTER_MASK); snd_emu10k1_ptr_write(emu, PTRX, ch, 0); snd_emu10k1_ptr_write(emu, CPF, ch, 0); snd_emu10k1_ptr_write(emu, CCR, ch, 0); @@ -74,7 +74,7 @@ void snd_emu10k1_voice_init(struct snd_emu10k1 *emu, int ch) snd_emu10k1_ptr_write(emu, ATKHLDM, ch, 0); snd_emu10k1_ptr_write(emu, DCYSUSM, ch, 0); - snd_emu10k1_ptr_write(emu, IFATN, ch, 0xffff); + snd_emu10k1_ptr_write(emu, IFATN, ch, IFATN_FILTERCUTOFF_MASK | IFATN_ATTENUATION_MASK); snd_emu10k1_ptr_write(emu, PEFE, ch, 0); snd_emu10k1_ptr_write(emu, FMMOD, ch, 0); snd_emu10k1_ptr_write(emu, TREMFRQ, ch, 24); /* 1 Hz */ @@ -90,10 +90,10 @@ void snd_emu10k1_voice_init(struct snd_emu10k1 *emu, int ch) /* Audigy extra stuffs */ if (emu->audigy) { - snd_emu10k1_ptr_write(emu, 0x4c, ch, 0); /* ?? */ - snd_emu10k1_ptr_write(emu, 0x4d, ch, 0); /* ?? */ - snd_emu10k1_ptr_write(emu, 0x4e, ch, 0); /* ?? */ - snd_emu10k1_ptr_write(emu, 0x4f, ch, 0); /* ?? */ + snd_emu10k1_ptr_write(emu, A_CSBA, ch, 0); + snd_emu10k1_ptr_write(emu, A_CSDC, ch, 0); + snd_emu10k1_ptr_write(emu, A_CSFE, ch, 0); + snd_emu10k1_ptr_write(emu, A_CSHG, ch, 0); snd_emu10k1_ptr_write(emu, A_FXRT1, ch, 0x03020100); snd_emu10k1_ptr_write(emu, A_FXRT2, ch, 0x3f3f3f3f); snd_emu10k1_ptr_write(emu, A_SENDAMOUNTS, ch, 0); @@ -259,7 +259,7 @@ static int snd_emu10k1_init(struct snd_emu10k1 *emu, int enable_ir) snd_emu10k1_ptr_write(emu, PTB, 0, emu->ptb_pages.addr); snd_emu10k1_ptr_write(emu, TCB, 0, 0); /* taken from original driver */ - snd_emu10k1_ptr_write(emu, TCBS, 0, 4); /* taken from original driver */ + snd_emu10k1_ptr_write(emu, TCBS, 0, TCBS_BUFFSIZE_256K); /* taken from original driver */ silent_page = (emu->silent_page.addr << emu->address_mode) | (emu->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0); for (ch = 0; ch < NUM_G; ch++) { @@ -818,7 +818,7 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) /* FPGA netlist already present so clear it */ /* Return to programming mode */ - snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, 0x02); + snd_emu1010_fpga_write(emu, EMU_HANA_FPGA_CONFIG, EMU_HANA_FPGA_CONFIG_HANA); } snd_emu1010_fpga_read(emu, EMU_HANA_ID, ®); dev_dbg(emu->card->dev, "reg2 = 0x%x\n", reg); @@ -858,36 +858,36 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) /* Optical -> ADAT I/O */ emu->emu1010.optical_in = 1; /* IN_ADAT */ emu->emu1010.optical_out = 1; /* OUT_ADAT */ - tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : 0) | - (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : 0); + tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) | + (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF); snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp); /* Set no attenuation on Audio Dock pads. */ - snd_emu1010_fpga_write(emu, EMU_HANA_ADC_PADS, 0x00); emu->emu1010.adc_pads = 0x00; + snd_emu1010_fpga_write(emu, EMU_HANA_ADC_PADS, emu->emu1010.adc_pads); /* Unmute Audio dock DACs, Headphone source DAC-4. */ - snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_MISC, 0x30); + snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_MISC, EMU_HANA_DOCK_PHONES_192_DAC4); /* DAC PADs. */ - snd_emu1010_fpga_write(emu, EMU_HANA_DAC_PADS, 0x0f); - emu->emu1010.dac_pads = 0x0f; + emu->emu1010.dac_pads = EMU_HANA_DOCK_DAC_PAD1 | EMU_HANA_DOCK_DAC_PAD2 | + EMU_HANA_DOCK_DAC_PAD3 | EMU_HANA_DOCK_DAC_PAD4; + snd_emu1010_fpga_write(emu, EMU_HANA_DAC_PADS, emu->emu1010.dac_pads); /* SPDIF Format. Set Consumer mode, 24bit, copy enable */ - snd_emu1010_fpga_write(emu, EMU_HANA_SPDIF_MODE, 0x10); + snd_emu1010_fpga_write(emu, EMU_HANA_SPDIF_MODE, EMU_HANA_SPDIF_MODE_RX_INVALID); /* MIDI routing */ - snd_emu1010_fpga_write(emu, EMU_HANA_MIDI_IN, 0x19); - /* Unknown. */ - snd_emu1010_fpga_write(emu, EMU_HANA_MIDI_OUT, 0x0c); + snd_emu1010_fpga_write(emu, EMU_HANA_MIDI_IN, EMU_HANA_MIDI_INA_FROM_HAMOA | EMU_HANA_MIDI_INB_FROM_DOCK2); + snd_emu1010_fpga_write(emu, EMU_HANA_MIDI_OUT, EMU_HANA_MIDI_OUT_DOCK2 | EMU_HANA_MIDI_OUT_SYNC2); /* IRQ Enable: All on */ - /* snd_emu1010_fpga_write(emu, 0x09, 0x0f ); */ + /* snd_emu1010_fpga_write(emu, EMU_HANA_IRQ_ENABLE, 0x0f); */ /* IRQ Enable: All off */ snd_emu1010_fpga_write(emu, EMU_HANA_IRQ_ENABLE, 0x00); emu->emu1010.internal_clock = 1; /* 48000 */ /* Default WCLK set to 48kHz. */ - snd_emu1010_fpga_write(emu, EMU_HANA_DEFCLOCK, 0x00); + snd_emu1010_fpga_write(emu, EMU_HANA_DEFCLOCK, EMU_HANA_DEFCLOCK_48K); /* Word Clock source, Internal 48kHz x1 */ snd_emu1010_fpga_write(emu, EMU_HANA_WCLOCK, EMU_HANA_WCLOCK_INT_48K); /* snd_emu1010_fpga_write(emu, EMU_HANA_WCLOCK, EMU_HANA_WCLOCK_INT_48K | EMU_HANA_WCLOCK_4X); */ /* Audio Dock LEDs. */ - snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_LEDS_2, 0x12); + snd_emu1010_fpga_write(emu, EMU_HANA_DOCK_LEDS_2, EMU_HANA_DOCK_LEDS_2_LOCK | EMU_HANA_DOCK_LEDS_2_48K); #if 0 /* For 96kHz */ @@ -1014,7 +1014,7 @@ static int snd_emu10k1_emu1010_init(struct snd_emu10k1 *emu) EMU_DST_ALICE_I2S2_LEFT, EMU_SRC_DOCK_ADC3_LEFT1); snd_emu1010_fpga_link_dst_src_write(emu, EMU_DST_ALICE_I2S2_RIGHT, EMU_SRC_DOCK_ADC3_RIGHT1); - snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, 0x01); /* Unmute all */ + snd_emu1010_fpga_write(emu, EMU_HANA_UNMUTE, EMU_UNMUTE); #if 0 snd_emu1010_fpga_link_dst_src_write(emu, diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index db211a6e8a47..3f64ccab0e63 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -1355,7 +1355,7 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) gpr += 2; /* mic capture buffer */ - A_OP(icode, &ptr, iINTERP, A_EXTOUT(A_EXTOUT_MIC_CAP), A_EXTIN(A_EXTIN_AC97_L), 0xcd, A_EXTIN(A_EXTIN_AC97_R)); + A_OP(icode, &ptr, iINTERP, A_EXTOUT(A_EXTOUT_MIC_CAP), A_EXTIN(A_EXTIN_AC97_L), A_C_40000000, A_EXTIN(A_EXTIN_AC97_R)); /* Audigy CD Playback Volume */ A_ADD_VOLUME_IN(stereo_mix, gpr, A_EXTIN_SPDIF_CD_L); @@ -1438,7 +1438,7 @@ A_OP(icode, &ptr, iMAC0, A_GPR(var), A_GPR(var), A_GPR(vol), A_EXTIN(input)) /* Stereo Mix Center Playback */ /* Center = sub = Left/2 + Right/2 */ - A_OP(icode, &ptr, iINTERP, A_GPR(tmp), A_GPR(stereo_mix), 0xcd, A_GPR(stereo_mix+1)); + A_OP(icode, &ptr, iINTERP, A_GPR(tmp), A_GPR(stereo_mix), A_C_40000000, A_GPR(stereo_mix+1)); A_OP(icode, &ptr, iMAC0, A_GPR(playback+4), A_GPR(playback+4), A_GPR(gpr), A_GPR(tmp)); snd_emu10k1_init_mono_control(&controls[nctl++], "Center Playback Volume", gpr, 0); gpr++; @@ -2478,7 +2478,7 @@ int snd_emu10k1_fx8010_tram_setup(struct snd_emu10k1 *emu, u32 size) outl(HCFG_LOCKTANKCACHE_MASK | inl(emu->port + HCFG), emu->port + HCFG); spin_unlock_irq(&emu->emu_lock); snd_emu10k1_ptr_write(emu, TCB, 0, 0); - snd_emu10k1_ptr_write(emu, TCBS, 0, 0); + snd_emu10k1_ptr_write(emu, TCBS, 0, TCBS_BUFFSIZE_16K); if (emu->fx8010.etram_pages.area != NULL) { snd_dma_free_pages(&emu->fx8010.etram_pages); emu->fx8010.etram_pages.area = NULL; diff --git a/sound/pci/emu10k1/emumixer.c b/sound/pci/emu10k1/emumixer.c index 8fce3413f4ae..3ebc7c36a444 100644 --- a/sound/pci/emu10k1/emumixer.c +++ b/sound/pci/emu10k1/emumixer.c @@ -827,8 +827,8 @@ static int snd_emu1010_optical_out_put(struct snd_kcontrol *kcontrol, change = (emu->emu1010.optical_out != val); if (change) { emu->emu1010.optical_out = val; - tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : 0) | - (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : 0); + tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) | + (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF); snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp); } return change; @@ -878,8 +878,8 @@ static int snd_emu1010_optical_in_put(struct snd_kcontrol *kcontrol, change = (emu->emu1010.optical_in != val); if (change) { emu->emu1010.optical_in = val; - tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : 0) | - (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : 0); + tmp = (emu->emu1010.optical_in ? EMU_HANA_OPTICAL_IN_ADAT : EMU_HANA_OPTICAL_IN_SPDIF) | + (emu->emu1010.optical_out ? EMU_HANA_OPTICAL_OUT_ADAT : EMU_HANA_OPTICAL_OUT_SPDIF); snd_emu1010_fpga_write(emu, EMU_HANA_OPTICAL_TYPE, tmp); } return change; diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index b0c0ef342756..e8d2f0f6fbb3 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -352,8 +352,8 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu, snd_emu10k1_ptr_write(emu, MAPA, voice, silent_page); snd_emu10k1_ptr_write(emu, MAPB, voice, silent_page); /* modulation envelope */ - snd_emu10k1_ptr_write(emu, CVCF, voice, 0xffff); - snd_emu10k1_ptr_write(emu, VTFT, voice, 0xffff); + snd_emu10k1_ptr_write(emu, VTFT, voice, VTFT_FILTERTARGET_MASK); + snd_emu10k1_ptr_write(emu, CVCF, voice, CVCF_CURRENTFILTER_MASK); snd_emu10k1_ptr_write(emu, ATKHLDM, voice, 0); snd_emu10k1_ptr_write(emu, DCYSUSM, voice, 0x007f); snd_emu10k1_ptr_write(emu, LFOVAL1, voice, 0x8000); @@ -621,8 +621,8 @@ static void snd_emu10k1_playback_prepare_voice(struct snd_emu10k1 *emu, struct s tmp = runtime->channels == 2 ? (master ? 1 : 2) : 0; vattn = mix != NULL ? (mix->attn[tmp] << 16) : 0; snd_emu10k1_ptr_write(emu, IFATN, voice, attn); - snd_emu10k1_ptr_write(emu, VTFT, voice, vattn | 0xffff); - snd_emu10k1_ptr_write(emu, CVCF, voice, vattn | 0xffff); + snd_emu10k1_ptr_write(emu, VTFT, voice, vattn | VTFT_FILTERTARGET_MASK); + snd_emu10k1_ptr_write(emu, CVCF, voice, vattn | CVCF_CURRENTFILTER_MASK); snd_emu10k1_ptr_write(emu, DCYSUSV, voice, 0x7f7f); snd_emu10k1_voice_clear_loop_stop(emu, voice); } @@ -663,8 +663,8 @@ static void snd_emu10k1_playback_stop_voice(struct snd_emu10k1 *emu, struct snd_ snd_emu10k1_ptr_write(emu, PTRX_PITCHTARGET, voice, 0); snd_emu10k1_ptr_write(emu, CPF_CURRENTPITCH, voice, 0); snd_emu10k1_ptr_write(emu, IFATN, voice, 0xffff); - snd_emu10k1_ptr_write(emu, VTFT, voice, 0xffff); - snd_emu10k1_ptr_write(emu, CVCF, voice, 0xffff); + snd_emu10k1_ptr_write(emu, VTFT, voice, VTFT_FILTERTARGET_MASK); + snd_emu10k1_ptr_write(emu, CVCF, voice, CVCF_CURRENTFILTER_MASK); snd_emu10k1_ptr_write(emu, IP, voice, 0); } diff --git a/sound/pci/emu10k1/io.c b/sound/pci/emu10k1/io.c index c60573f14ea8..cfb96a67aa35 100644 --- a/sound/pci/emu10k1/io.c +++ b/sound/pci/emu10k1/io.c @@ -95,8 +95,8 @@ unsigned int snd_emu10k1_ptr20_read(struct snd_emu10k1 * emu, regptr = (reg << 16) | chn; spin_lock_irqsave(&emu->emu_lock, flags); - outl(regptr, emu->port + 0x20 + PTR); - val = inl(emu->port + 0x20 + DATA); + outl(regptr, emu->port + PTR2); + val = inl(emu->port + DATA2); spin_unlock_irqrestore(&emu->emu_lock, flags); return val; } @@ -112,8 +112,8 @@ void snd_emu10k1_ptr20_write(struct snd_emu10k1 *emu, regptr = (reg << 16) | chn; spin_lock_irqsave(&emu->emu_lock, flags); - outl(regptr, emu->port + 0x20 + PTR); - outl(data, emu->port + 0x20 + DATA); + outl(regptr, emu->port + PTR2); + outl(data, emu->port + DATA2); spin_unlock_irqrestore(&emu->emu_lock, flags); } @@ -128,7 +128,7 @@ int snd_emu10k1_spi_write(struct snd_emu10k1 * emu, /* This function is not re-entrant, so protect against it. */ spin_lock(&emu->spi_lock); if (emu->card_capabilities->ca0108_chip) - reg = 0x3c; /* PTR20, reg 0x3c */ + reg = P17V_SPI; else { /* For other chip types the SPI register * is currently unknown. */ @@ -280,10 +280,10 @@ void snd_emu1010_fpga_link_dst_src_write(struct snd_emu10k1 *emu, u32 dst, u32 s return; if (snd_BUG_ON(src & ~0x71f)) return; - snd_emu1010_fpga_write(emu, 0x00, dst >> 8); - snd_emu1010_fpga_write(emu, 0x01, dst & 0x1f); - snd_emu1010_fpga_write(emu, 0x02, src >> 8); - snd_emu1010_fpga_write(emu, 0x03, src & 0x1f); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTHI, dst >> 8); + snd_emu1010_fpga_write(emu, EMU_HANA_DESTLO, dst & 0x1f); + snd_emu1010_fpga_write(emu, EMU_HANA_SRCHI, src >> 8); + snd_emu1010_fpga_write(emu, EMU_HANA_SRCLO, src & 0x1f); } void snd_emu10k1_intr_enable(struct snd_emu10k1 *emu, unsigned int intrenb) diff --git a/sound/pci/emu10k1/p16v.c b/sound/pci/emu10k1/p16v.c index ce4d3450959c..e7f097cae574 100644 --- a/sound/pci/emu10k1/p16v.c +++ b/sound/pci/emu10k1/p16v.c @@ -254,19 +254,24 @@ static int snd_p16v_pcm_prepare_playback(struct snd_pcm_substream *substream) emu->p16v_buffer->bytes); #endif /* debug */ tmp = snd_emu10k1_ptr_read(emu, A_SPDIF_SAMPLERATE, channel); + tmp &= ~(A_SPDIF_RATE_MASK | A_EHC_SRC48_MASK); switch (runtime->rate) { case 44100: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0xe0e0) | 0x8080); + snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, + tmp | A_SPDIF_44100 | A_EHC_SRC48_44); break; case 96000: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0xe0e0) | 0x4040); + snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, + tmp | A_SPDIF_96000 | A_EHC_SRC48_96); break; case 192000: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0xe0e0) | 0x2020); + snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, + tmp | A_SPDIF_192000 | A_EHC_SRC48_192); break; case 48000: default: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0xe0e0) | 0x0000); + snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, + tmp | A_SPDIF_48000 | A_EHC_SRC48_BYPASS); break; } /* FIXME: Check emu->buffer.size before actually writing to it. */ @@ -282,8 +287,8 @@ static int snd_p16v_pcm_prepare_playback(struct snd_pcm_substream *substream) //snd_emu10k1_ptr20_write(emu, PLAYBACK_PERIOD_SIZE, channel, frames_to_bytes(runtime, runtime->period_size)<<16); // buffer size in bytes snd_emu10k1_ptr20_write(emu, PLAYBACK_PERIOD_SIZE, channel, 0); // buffer size in bytes snd_emu10k1_ptr20_write(emu, PLAYBACK_POINTER, channel, 0); - snd_emu10k1_ptr20_write(emu, 0x07, channel, 0x0); - snd_emu10k1_ptr20_write(emu, 0x08, channel, 0); + snd_emu10k1_ptr20_write(emu, PLAYBACK_FIFO_END_ADDRESS, channel, 0); + snd_emu10k1_ptr20_write(emu, PLAYBACK_FIFO_POINTER, channel, 0); return 0; } @@ -294,7 +299,6 @@ static int snd_p16v_pcm_prepare_capture(struct snd_pcm_substream *substream) struct snd_emu10k1 *emu = snd_pcm_substream_chip(substream); struct snd_pcm_runtime *runtime = substream->runtime; int channel = substream->pcm->device - emu->p16v_device_offset; - u32 tmp; /* dev_dbg(emu->card->dev, "prepare capture:channel_number=%d, rate=%d, " @@ -304,24 +308,23 @@ static int snd_p16v_pcm_prepare_capture(struct snd_pcm_substream *substream) runtime->buffer_size, runtime->period_size, frames_to_bytes(runtime, 1)); */ - tmp = snd_emu10k1_ptr_read(emu, A_SPDIF_SAMPLERATE, channel); switch (runtime->rate) { case 44100: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0x0e00) | 0x0800); + snd_emu10k1_ptr_write(emu, A_I2S_CAPTURE_RATE, channel, A_I2S_CAPTURE_44100); break; case 96000: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0x0e00) | 0x0400); + snd_emu10k1_ptr_write(emu, A_I2S_CAPTURE_RATE, channel, A_I2S_CAPTURE_96000); break; case 192000: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0x0e00) | 0x0200); + snd_emu10k1_ptr_write(emu, A_I2S_CAPTURE_RATE, channel, A_I2S_CAPTURE_192000); break; case 48000: default: - snd_emu10k1_ptr_write(emu, A_SPDIF_SAMPLERATE, channel, (tmp & ~0x0e00) | 0x0000); + snd_emu10k1_ptr_write(emu, A_I2S_CAPTURE_RATE, channel, A_I2S_CAPTURE_48000); break; } /* FIXME: Check emu->buffer.size before actually writing to it. */ - snd_emu10k1_ptr20_write(emu, 0x13, channel, 0); + snd_emu10k1_ptr20_write(emu, CAPTURE_FIFO_POINTER, channel, 0); snd_emu10k1_ptr20_write(emu, CAPTURE_DMA_ADDR, channel, runtime->dma_addr); snd_emu10k1_ptr20_write(emu, CAPTURE_BUFFER_SIZE, channel, frames_to_bytes(runtime, runtime->buffer_size) << 16); // buffer size in bytes snd_emu10k1_ptr20_write(emu, CAPTURE_POINTER, channel, 0); -- GitLab From 8fd91151ebcb21b3f2f2bf158ac6092192550b2b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 17 Apr 2023 22:25:09 +0200 Subject: [PATCH 4274/5631] crypto: sun8i-ss - Fix a test in sun8i_ss_setup_ivs() SS_ENCRYPTION is (0 << 7 = 0), so the test can never be true. Use a direct comparison to SS_ENCRYPTION instead. The same king of test is already done the same way in sun8i_ss_run_task(). Fixes: 359e893e8af4 ("crypto: sun8i-ss - rework handling of IV") Signed-off-by: Christophe JAILLET Signed-off-by: Herbert Xu --- drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index 83c6dfad77e1..16966cc94e24 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -151,7 +151,7 @@ static int sun8i_ss_setup_ivs(struct skcipher_request *areq) } rctx->p_iv[i] = a; /* we need to setup all others IVs only in the decrypt way */ - if (rctx->op_dir & SS_ENCRYPTION) + if (rctx->op_dir == SS_ENCRYPTION) return 0; todo = min(len, sg_dma_len(sg)); len -= todo; -- GitLab From 4140aafcff167b5b9e8dae6a1709a6de7cac6f74 Mon Sep 17 00:00:00 2001 From: Olivier Bacon Date: Thu, 20 Apr 2023 11:00:35 -0400 Subject: [PATCH 4275/5631] crypto: engine - fix crypto_queue backlog handling CRYPTO_TFM_REQ_MAY_BACKLOG tells the crypto driver that it should internally backlog requests until the crypto hw's queue becomes full. At that point, crypto_engine backlogs the request and returns -EBUSY. Calling driver such as dm-crypt then waits until the complete() function is called with a status of -EINPROGRESS before sending a new request. The problem lies in the call to complete() with a value of -EINPROGRESS that is made when a backlog item is present on the queue. The call is done before the successful execution of the crypto request. In the case that do_one_request() returns < 0 and the retry support is available, the request is put back in the queue. This leads upper drivers to send a new request even if the queue is still full. The problem can be reproduced by doing a large dd into a crypto dm-crypt device. This is pretty easy to see when using Freescale CAAM crypto driver and SWIOTLB dma. Since the actual amount of requests that can be hold in the queue is unlimited we get IOs error and dma allocation. The fix is to call complete with a value of -EINPROGRESS only if the request is not enqueued back in crypto_queue. This is done by calling complete() later in the code. In order to delay the decision, crypto_queue is modified to correctly set the backlog pointer when a request is enqueued back. Fixes: 6a89f492f8e5 ("crypto: engine - support for parallel requests based on retry mechanism") Co-developed-by: Sylvain Ouellet Signed-off-by: Sylvain Ouellet Signed-off-by: Olivier Bacon Signed-off-by: Herbert Xu --- crypto/algapi.c | 3 +++ crypto/crypto_engine.c | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/crypto/algapi.c b/crypto/algapi.c index d7eb8f9e9883..5e7cd603d489 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -961,6 +961,9 @@ EXPORT_SYMBOL_GPL(crypto_enqueue_request); void crypto_enqueue_request_head(struct crypto_queue *queue, struct crypto_async_request *request) { + if (unlikely(queue->qlen >= queue->max_qlen)) + queue->backlog = queue->backlog->prev; + queue->qlen++; list_add(&request->list, &queue->list); } diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c index 21f791615114..74fcc0897041 100644 --- a/crypto/crypto_engine.c +++ b/crypto/crypto_engine.c @@ -129,9 +129,6 @@ static void crypto_pump_requests(struct crypto_engine *engine, if (!engine->retry_support) engine->cur_req = async_req; - if (backlog) - crypto_request_complete(backlog, -EINPROGRESS); - if (engine->busy) was_busy = true; else @@ -217,6 +214,9 @@ static void crypto_pump_requests(struct crypto_engine *engine, crypto_request_complete(async_req, ret); retry: + if (backlog) + crypto_request_complete(backlog, -EINPROGRESS); + /* If retry mechanism is supported, send new requests to engine */ if (engine->retry_support) { spin_lock_irqsave(&engine->queue_lock, flags); -- GitLab From 0c8862de05c1a087795ee0a87bf61a6394306cc0 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 21:49:37 +0300 Subject: [PATCH 4276/5631] tpm: Re-enable TPM chip boostrapping non-tpm_tis TPM drivers TPM chip bootstrapping was removed from tpm_chip_register(), and it was relocated to tpm_tis_core. This breaks all drivers which are not based on tpm_tis because the chip will not get properly initialized. Take the corrective steps: 1. Rename tpm_chip_startup() as tpm_chip_bootstrap() and make it one-shot. 2. Call tpm_chip_bootstrap() in tpm_chip_register(), which reverts the things as tehy used to be. Cc: Lino Sanfilippo Fixes: 548eb516ec0f ("tpm, tpm_tis: startup chip before testing for interrupts") Reported-by: Pengfei Xu Link: https://lore.kernel.org/all/ZEjqhwHWBnxcaRV5@xpf.sh.intel.com/ Tested-by: Pengfei Xu Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 22 +++++++++++++++++++--- drivers/char/tpm/tpm.h | 2 +- drivers/char/tpm/tpm_tis_core.c | 2 +- include/linux/tpm.h | 13 +++++++------ 4 files changed, 28 insertions(+), 11 deletions(-) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 6fdfa65a00c3..9c0a6aad8114 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -606,13 +606,19 @@ static int tpm_get_pcr_allocation(struct tpm_chip *chip) } /* - * tpm_chip_startup() - performs auto startup and allocates the PCRs + * tpm_chip_bootstrap() - Boostrap TPM chip after power on * @chip: TPM chip to use. + * + * Initialize TPM chip after power on. This a one-shot function: subsequent + * calls will have no effect. */ -int tpm_chip_startup(struct tpm_chip *chip) +int tpm_chip_bootstrap(struct tpm_chip *chip) { int rc; + if (chip->flags & TPM_CHIP_FLAG_BOOTSTRAPPED) + return 0; + rc = tpm_chip_start(chip); if (rc) return rc; @@ -625,9 +631,15 @@ int tpm_chip_startup(struct tpm_chip *chip) stop: tpm_chip_stop(chip); + /* + * Unconditionally set, as driver initialization should cease, when the + * boostrapping process fails. + */ + chip->flags |= TPM_CHIP_FLAG_BOOTSTRAPPED; + return rc; } -EXPORT_SYMBOL_GPL(tpm_chip_startup); +EXPORT_SYMBOL_GPL(tpm_chip_bootstrap); /* * tpm_chip_register() - create a character device for the TPM chip @@ -644,6 +656,10 @@ int tpm_chip_register(struct tpm_chip *chip) { int rc; + rc = tpm_chip_bootstrap(chip); + if (rc) + return rc; + tpm_sysfs_add_device(chip); tpm_bios_log_setup(chip); diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 88d3bd76e076..f6c99b3f0045 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -263,7 +263,7 @@ static inline void tpm_msleep(unsigned int delay_msec) delay_msec * 1000); }; -int tpm_chip_startup(struct tpm_chip *chip); +int tpm_chip_bootstrap(struct tpm_chip *chip); int tpm_chip_start(struct tpm_chip *chip); void tpm_chip_stop(struct tpm_chip *chip); struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip); diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index c2421162cf34..02945d53fcef 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1139,7 +1139,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, init_waitqueue_head(&priv->read_queue); init_waitqueue_head(&priv->int_queue); - rc = tpm_chip_startup(chip); + rc = tpm_chip_bootstrap(chip); if (rc) goto out_err; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4dc97b9f65fb..77693389c3f9 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -274,13 +274,14 @@ enum tpm2_cc_attrs { #define TPM_VID_ATML 0x1114 enum tpm_chip_flags { - TPM_CHIP_FLAG_TPM2 = BIT(1), - TPM_CHIP_FLAG_IRQ = BIT(2), - TPM_CHIP_FLAG_VIRTUAL = BIT(3), - TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), - TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_BOOTSTRAPPED = BIT(0), + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), - TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- GitLab From 6f932d4ef007d6a4ae03badcb749fbb8f49196f6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 12 Apr 2023 11:33:09 +0100 Subject: [PATCH 4277/5631] btrfs: fix btrfs_prev_leaf() to not return the same key twice A call to btrfs_prev_leaf() may end up returning a path that points to the same item (key) again. This happens if while btrfs_prev_leaf(), after we release the path, a concurrent insertion happens, which moves items off from a sibling into the front of the previous leaf, and an item with the computed previous key does not exists. For example, suppose we have the two following leaves: Leaf A ------------------------------------------------------------- | ... key (300 96 10) key (300 96 15) key (300 96 16) | ------------------------------------------------------------- slot 20 slot 21 slot 22 Leaf B ------------------------------------------------------------- | key (300 96 20) key (300 96 21) key (300 96 22) ... | ------------------------------------------------------------- slot 0 slot 1 slot 2 If we call btrfs_prev_leaf(), from btrfs_previous_item() for example, with a path pointing to leaf B and slot 0 and the following happens: 1) At btrfs_prev_leaf() we compute the previous key to search as: (300 96 19), which is a key that does not exists in the tree; 2) Then we call btrfs_release_path() at btrfs_prev_leaf(); 3) Some other task inserts a key at leaf A, that sorts before the key at slot 20, for example it has an objectid of 299. In order to make room for the new key, the key at slot 22 is moved to the front of leaf B. This happens at push_leaf_right(), called from split_leaf(). After this leaf B now looks like: -------------------------------------------------------------------------------- | key (300 96 16) key (300 96 20) key (300 96 21) key (300 96 22) ... | -------------------------------------------------------------------------------- slot 0 slot 1 slot 2 slot 3 4) At btrfs_prev_leaf() we call btrfs_search_slot() for the computed previous key: (300 96 19). Since the key does not exists, btrfs_search_slot() returns 1 and with a path pointing to leaf B and slot 1, the item with key (300 96 20); 5) This makes btrfs_prev_leaf() return a path that points to slot 1 of leaf B, the same key as before it was called, since the key at slot 0 of leaf B (300 96 16) is less than the computed previous key, which is (300 96 19); 6) As a consequence btrfs_previous_item() returns a path that points again to the item with key (300 96 20). For some users of btrfs_prev_leaf() or btrfs_previous_item() this may not be functional a problem, despite not making sense to return a new path pointing again to the same item/key. However for a caller such as tree-log.c:log_dir_items(), this has a bad consequence, as it can result in not logging some dir index deletions in case the directory is being logged without holding the inode's VFS lock (logging triggered while logging a child inode for example) - for the example scenario above, in case the dir index keys 17, 18 and 19 were deleted in the current transaction. CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 3c983c70028a..16414bd9e496 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -4478,10 +4478,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) { struct btrfs_key key; + struct btrfs_key orig_key; struct btrfs_disk_key found_key; int ret; btrfs_item_key_to_cpu(path->nodes[0], &key, 0); + orig_key = key; if (key.offset > 0) { key.offset--; @@ -4498,8 +4500,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path) btrfs_release_path(path); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) + if (ret <= 0) return ret; + + /* + * Previous key not found. Even if we were at slot 0 of the leaf we had + * before releasing the path and calling btrfs_search_slot(), we now may + * be in a slot pointing to the same original key - this can happen if + * after we released the path, one of more items were moved from a + * sibling leaf into the front of the leaf we had due to an insertion + * (see push_leaf_right()). + * If we hit this case and our slot is > 0 and just decrement the slot + * so that the caller does not process the same key again, which may or + * may not break the caller, depending on its logic. + */ + if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) { + btrfs_item_key(path->nodes[0], &found_key, path->slots[0]); + ret = comp_keys(&found_key, &orig_key); + if (ret == 0) { + if (path->slots[0] > 0) { + path->slots[0]--; + return 0; + } + /* + * At slot 0, same key as before, it means orig_key is + * the lowest, leftmost, key in the tree. We're done. + */ + return 1; + } + } + btrfs_item_key(path->nodes[0], &found_key, 0); ret = comp_keys(&found_key, &key); /* -- GitLab From ac868bc9d136cde6e3eb5de77019a63d57a540ff Mon Sep 17 00:00:00 2001 From: xiaoshoukui Date: Thu, 13 Apr 2023 05:55:07 -0400 Subject: [PATCH 4278/5631] btrfs: fix assertion of exclop condition when starting balance Balance as exclusive state is compatible with paused balance and device add, which makes some things more complicated. The assertion of valid states when starting from paused balance needs to take into account two more states, the combinations can be hit when there are several threads racing to start balance and device add. This won't typically happen when the commands are started from command line. Scenario 1: With exclusive_operation state == BTRFS_EXCLOP_NONE. Concurrently adding multiple devices to the same mount point and btrfs_exclop_finish executed finishes before assertion in btrfs_exclop_balance, exclusive_operation will changed to BTRFS_EXCLOP_NONE state which lead to assertion failed: fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD, in fs/btrfs/ioctl.c:456 Call Trace: btrfs_exclop_balance+0x13c/0x310 ? memdup_user+0xab/0xc0 ? PTR_ERR+0x17/0x20 btrfs_ioctl_add_dev+0x2ee/0x320 btrfs_ioctl+0x9d5/0x10d0 ? btrfs_ioctl_encoded_write+0xb80/0xb80 __x64_sys_ioctl+0x197/0x210 do_syscall_64+0x3c/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd Scenario 2: With exclusive_operation state == BTRFS_EXCLOP_BALANCE_PAUSED. Concurrently adding multiple devices to the same mount point and btrfs_exclop_balance executed finish before the latter thread execute assertion in btrfs_exclop_balance, exclusive_operation will changed to BTRFS_EXCLOP_BALANCE_PAUSED state which lead to assertion failed: fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || fs_info->exclusive_operation == BTRFS_EXCLOP_NONE, fs/btrfs/ioctl.c:458 Call Trace: btrfs_exclop_balance+0x240/0x410 ? memdup_user+0xab/0xc0 ? PTR_ERR+0x17/0x20 btrfs_ioctl_add_dev+0x2ee/0x320 btrfs_ioctl+0x9d5/0x10d0 ? btrfs_ioctl_encoded_write+0xb80/0xb80 __x64_sys_ioctl+0x197/0x210 do_syscall_64+0x3c/0xb0 entry_SYSCALL_64_after_hwframe+0x63/0xcd An example of the failed assertion is below, which shows that the paused balance is also needed to be checked. root@syzkaller:/home/xsk# ./repro Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 [ 416.611428][ T7970] BTRFS info (device loop0): fs_info exclusive_operation: 0 Failed to add device /dev/vda, errno 14 [ 416.613973][ T7971] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.615456][ T7972] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.617528][ T7973] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.618359][ T7974] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.622589][ T7975] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.624034][ T7976] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.626420][ T7977] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.627643][ T7978] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.629006][ T7979] BTRFS info (device loop0): fs_info exclusive_operation: 3 [ 416.630298][ T7980] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 Failed to add device /dev/vda, errno 14 [ 416.632787][ T7981] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.634282][ T7982] BTRFS info (device loop0): fs_info exclusive_operation: 3 Failed to add device /dev/vda, errno 14 [ 416.636202][ T7983] BTRFS info (device loop0): fs_info exclusive_operation: 3 [ 416.637012][ T7984] BTRFS info (device loop0): fs_info exclusive_operation: 1 Failed to add device /dev/vda, errno 14 [ 416.637759][ T7984] assertion failed: fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || fs_info->exclusive_operation == BTRFS_EXCLOP_NONE, in fs/btrfs/ioctl.c:458 [ 416.639845][ T7984] invalid opcode: 0000 [#1] PREEMPT SMP KASAN [ 416.640485][ T7984] CPU: 0 PID: 7984 Comm: repro Not tainted 6.2.0 #7 [ 416.641172][ T7984] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 [ 416.642090][ T7984] RIP: 0010:btrfs_assertfail+0x2c/0x2e [ 416.644423][ T7984] RSP: 0018:ffffc90003ea7e28 EFLAGS: 00010282 [ 416.645018][ T7984] RAX: 00000000000000cc RBX: 0000000000000000 RCX: 0000000000000000 [ 416.645763][ T7984] RDX: ffff88801d030000 RSI: ffffffff81637e7c RDI: fffff520007d4fb7 [ 416.646554][ T7984] RBP: ffffffff8a533de0 R08: 00000000000000cc R09: 0000000000000000 [ 416.647299][ T7984] R10: 0000000000000001 R11: 0000000000000001 R12: ffffffff8a533da0 [ 416.648041][ T7984] R13: 00000000000001ca R14: 000000005000940a R15: 0000000000000000 [ 416.648785][ T7984] FS: 00007fa2985d4640(0000) GS:ffff88802cc00000(0000) knlGS:0000000000000000 [ 416.649616][ T7984] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 416.650238][ T7984] CR2: 0000000000000000 CR3: 0000000018e5e000 CR4: 0000000000750ef0 [ 416.650980][ T7984] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 416.651725][ T7984] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 416.652502][ T7984] PKRU: 55555554 [ 416.652888][ T7984] Call Trace: [ 416.653241][ T7984] [ 416.653527][ T7984] btrfs_exclop_balance+0x240/0x410 [ 416.654036][ T7984] ? memdup_user+0xab/0xc0 [ 416.654465][ T7984] ? PTR_ERR+0x17/0x20 [ 416.654874][ T7984] btrfs_ioctl_add_dev+0x2ee/0x320 [ 416.655380][ T7984] btrfs_ioctl+0x9d5/0x10d0 [ 416.655822][ T7984] ? btrfs_ioctl_encoded_write+0xb80/0xb80 [ 416.656400][ T7984] __x64_sys_ioctl+0x197/0x210 [ 416.656874][ T7984] do_syscall_64+0x3c/0xb0 [ 416.657346][ T7984] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 416.657922][ T7984] RIP: 0033:0x4546af [ 416.660170][ T7984] RSP: 002b:00007fa2985d4150 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 416.660972][ T7984] RAX: ffffffffffffffda RBX: 00007fa2985d4640 RCX: 00000000004546af [ 416.661714][ T7984] RDX: 0000000000000000 RSI: 000000005000940a RDI: 0000000000000003 [ 416.662449][ T7984] RBP: 00007fa2985d41d0 R08: 0000000000000000 R09: 00007ffee37a4c4f [ 416.663195][ T7984] R10: 0000000000000000 R11: 0000000000000246 R12: 00007fa2985d4640 [ 416.663951][ T7984] R13: 0000000000000009 R14: 000000000041b320 R15: 00007fa297dd4000 [ 416.664703][ T7984] [ 416.665040][ T7984] Modules linked in: [ 416.665590][ T7984] ---[ end trace 0000000000000000 ]--- [ 416.666176][ T7984] RIP: 0010:btrfs_assertfail+0x2c/0x2e [ 416.668775][ T7984] RSP: 0018:ffffc90003ea7e28 EFLAGS: 00010282 [ 416.669425][ T7984] RAX: 00000000000000cc RBX: 0000000000000000 RCX: 0000000000000000 [ 416.670235][ T7984] RDX: ffff88801d030000 RSI: ffffffff81637e7c RDI: fffff520007d4fb7 [ 416.671050][ T7984] RBP: ffffffff8a533de0 R08: 00000000000000cc R09: 0000000000000000 [ 416.671867][ T7984] R10: 0000000000000001 R11: 0000000000000001 R12: ffffffff8a533da0 [ 416.672685][ T7984] R13: 00000000000001ca R14: 000000005000940a R15: 0000000000000000 [ 416.673501][ T7984] FS: 00007fa2985d4640(0000) GS:ffff88802cc00000(0000) knlGS:0000000000000000 [ 416.674425][ T7984] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 416.675114][ T7984] CR2: 0000000000000000 CR3: 0000000018e5e000 CR4: 0000000000750ef0 [ 416.675933][ T7984] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 416.676760][ T7984] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Link: https://lore.kernel.org/linux-btrfs/20230324031611.98986-1-xiaoshoukui@gmail.com/ CC: stable@vger.kernel.org # 6.1+ Signed-off-by: xiaoshoukui Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 25833b4eeaf5..2fa36f694daa 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -454,7 +454,9 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, case BTRFS_EXCLOP_BALANCE_PAUSED: spin_lock(&fs_info->super_lock); ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE || - fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD); + fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD || + fs_info->exclusive_operation == BTRFS_EXCLOP_NONE || + fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED); fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED; spin_unlock(&fs_info->super_lock); break; -- GitLab From 611ccc58e1f2ccd4a85258a646d5f9b4d5b1b4f6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 26 Apr 2023 18:13:00 +0100 Subject: [PATCH 4279/5631] btrfs: fix leak of source device allocation state after device replace When a device replace finishes, the source device is freed by calling btrfs_free_device() at btrfs_rm_dev_replace_free_srcdev(), but the allocation state, tracked in the device's alloc_state io tree, is never freed. This is a regression recently introduced by commit f0bb5474cff0 ("btrfs: remove redundant release of btrfs_device::alloc_state"), which removed a call to extent_io_tree_release() from btrfs_free_device(), with the rationale that btrfs_close_one_device() already releases the allocation state from a device and btrfs_close_one_device() is always called before a device is freed with btrfs_free_device(). However that is not true for the device replace case, as btrfs_free_device() is called without any previous call to btrfs_close_one_device(). The issue is trivial to reproduce, for example, by running test btrfs/027 from fstests: $ ./check btrfs/027 $ rmmod btrfs $ dmesg (...) [84519.395485] BTRFS info (device sdc): dev_replace from (devid 2) to /dev/sdg started [84519.466224] BTRFS info (device sdc): dev_replace from (devid 2) to /dev/sdg finished [84519.552251] BTRFS info (device sdc): scrub: started on devid 1 [84519.552277] BTRFS info (device sdc): scrub: started on devid 2 [84519.552332] BTRFS info (device sdc): scrub: started on devid 3 [84519.552705] BTRFS info (device sdc): scrub: started on devid 4 [84519.604261] BTRFS info (device sdc): scrub: finished on devid 4 with status: 0 [84519.609374] BTRFS info (device sdc): scrub: finished on devid 3 with status: 0 [84519.610818] BTRFS info (device sdc): scrub: finished on devid 1 with status: 0 [84519.610927] BTRFS info (device sdc): scrub: finished on devid 2 with status: 0 [84559.503795] BTRFS: state leak: start 1048576 end 1351614463 state 1 in tree 1 refs 1 [84559.506764] BTRFS: state leak: start 1048576 end 1347420159 state 1 in tree 1 refs 1 [84559.510294] BTRFS: state leak: start 1048576 end 1351614463 state 1 in tree 1 refs 1 So fix this by adding back the call to extent_io_tree_release() at btrfs_free_device(). Fixes: f0bb5474cff0 ("btrfs: remove redundant release of btrfs_device::alloc_state") Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 03f52e4a20aa..841e799dece5 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -395,6 +395,7 @@ void btrfs_free_device(struct btrfs_device *device) { WARN_ON(!list_empty(&device->post_commit_list)); rcu_string_free(device->name); + extent_io_tree_release(&device->alloc_state); btrfs_destroy_dev_zone_info(device); kfree(device); } -- GitLab From 9ae5afd02a03d4e22a17a9609b19400b77c36273 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 26 Apr 2023 11:51:35 +0100 Subject: [PATCH 4280/5631] btrfs: abort transaction when sibling keys check fails for leaves If the sibling keys check fails before we move keys from one sibling leaf to another, we are not aborting the transaction - we leave that to some higher level caller of btrfs_search_slot() (or anything else that uses it to insert items into a b+tree). This means that the transaction abort will provide a stack trace that omits the b+tree modification call chain. So change this to immediately abort the transaction and therefore get a more useful stack trace that shows us the call chain in the bt+tree modification code. It's also important to immediately abort the transaction just in case some higher level caller is not doing it, as this indicates a very serious corruption and we should stop the possibility of doing further damage. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 16414bd9e496..adfc04bd362e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -3215,6 +3215,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root if (check_sibling_keys(left, right)) { ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); btrfs_tree_unlock(right); free_extent_buffer(right); return ret; @@ -3433,6 +3434,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root if (check_sibling_keys(left, right)) { ret = -EUCLEAN; + btrfs_abort_transaction(trans, ret); goto out; } return __push_leaf_left(trans, path, min_data_size, empty, left, -- GitLab From a2cea677db6099d71c9f70de7f907d3d7e6bec3b Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 26 Apr 2023 11:51:36 +0100 Subject: [PATCH 4281/5631] btrfs: print extent buffers when sibling keys check fails When trying to move keys from one node/leaf to another sibling node/leaf, if the sibling keys check fails we just print an error message with the last key of the left sibling and the first key of the right sibling. However it's also useful to print all the keys of each sibling, as it may provide some clues to what went wrong, which code path may be inserting keys in an incorrect order. So just do that, print the siblings with btrfs_print_tree(), as it works for both leaves and nodes. Reviewed-by: Qu Wenruo Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index adfc04bd362e..2ff2961b1183 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2627,6 +2627,10 @@ static bool check_sibling_keys(struct extent_buffer *left, } if (btrfs_comp_cpu_keys(&left_last, &right_first) >= 0) { + btrfs_crit(left->fs_info, "left extent buffer:"); + btrfs_print_tree(left, false); + btrfs_crit(left->fs_info, "right extent buffer:"); + btrfs_print_tree(right, false); btrfs_crit(left->fs_info, "bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)", left_last.objectid, left_last.type, -- GitLab From 64b5d5b2852661284ccbb038c697562cc56231bf Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 27 Apr 2023 09:45:32 +0800 Subject: [PATCH 4282/5631] btrfs: properly reject clear_cache and v1 cache for block-group-tree [BUG] With block-group-tree feature enabled, mounting it with clear_cache would cause the following transaction abort at mount or remount: BTRFS info (device dm-4): force clearing of disk cache BTRFS info (device dm-4): using free space tree BTRFS info (device dm-4): auto enabling async discard BTRFS info (device dm-4): clearing free space tree BTRFS info (device dm-4): clearing compat-ro feature flag for FREE_SPACE_TREE (0x1) BTRFS info (device dm-4): clearing compat-ro feature flag for FREE_SPACE_TREE_VALID (0x2) BTRFS error (device dm-4): block-group-tree feature requires fres-space-tree and no-holes BTRFS error (device dm-4): super block corruption detected before writing it to disk BTRFS: error (device dm-4) in write_all_supers:4288: errno=-117 Filesystem corrupted (unexpected superblock corruption detected) BTRFS warning (device dm-4: state E): Skipping commit of aborted transaction. [CAUSE] For block-group-tree feature, we have an artificial dependency on free-space-tree. This means if we detect block-group-tree without v2 cache, we consider it a corruption and cause the problem. For clear_cache mount option, it would temporary disable v2 cache, then re-enable it. But unfortunately for that temporary v2 cache disabled status, we refuse to write a superblock with bg tree only flag, thus leads to the above transaction abortion. [FIX] For now, just reject clear_cache and v1 cache mount option for block group tree. So now we got a graceful rejection other than a transaction abort: BTRFS info (device dm-4): force clearing of disk cache BTRFS error (device dm-4): cannot disable free space tree with block-group-tree feature BTRFS error (device dm-4): open_ctree failed CC: stable@vger.kernel.org # 6.1+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6cb97efee976..0f2f915e42b0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -826,7 +826,12 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, !btrfs_test_opt(info, CLEAR_CACHE)) { btrfs_err(info, "cannot disable free space tree"); ret = -EINVAL; - + } + if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) && + (btrfs_test_opt(info, CLEAR_CACHE) || + !btrfs_test_opt(info, FREE_SPACE_TREE))) { + btrfs_err(info, "cannot disable free space tree with block-group-tree feature"); + ret = -EINVAL; } if (!ret) ret = btrfs_check_mountopts_zoned(info); -- GitLab From 1dedde690303c05ef732b7c5c8356fdf60a4ade3 Mon Sep 17 00:00:00 2001 From: Zhihao Cheng Date: Tue, 21 Mar 2023 09:37:21 +0800 Subject: [PATCH 4283/5631] ext4: fix i_disksize exceeding i_size problem in paritally written case It is possible for i_disksize can exceed i_size, triggering a warning. generic_perform_write copied = iov_iter_copy_from_user_atomic(len) // copied < len ext4_da_write_end | ext4_update_i_disksize | new_i_size = pos + copied; | WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize) // update i_disksize | generic_write_end | copied = block_write_end(copied, len) // copied = 0 | if (unlikely(copied < len)) | if (!PageUptodate(page)) | copied = 0; | if (pos + copied > inode->i_size) // return false if (unlikely(copied == 0)) goto again; if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } We get i_disksize greater than i_size here, which could trigger WARNING check 'i_size_read(inode) < EXT4_I(inode)->i_disksize' while doing dio: ext4_dio_write_iter iomap_dio_rw __iomap_dio_rw // return err, length is not aligned to 512 ext4_handle_inode_extension WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize) // Oops WARNING: CPU: 2 PID: 2609 at fs/ext4/file.c:319 CPU: 2 PID: 2609 Comm: aa Not tainted 6.3.0-rc2 RIP: 0010:ext4_file_write_iter+0xbc7 Call Trace: vfs_write+0x3b1 ksys_write+0x77 do_syscall_64+0x39 Fix it by updating 'copied' value before updating i_disksize just like ext4_write_inline_data_end() does. A reproducer can be found in the buganizer link below. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217209 Fixes: 64769240bd07 ("ext4: Add delayed allocation support in data=writeback mode") Signed-off-by: Zhihao Cheng Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230321013721.89818-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8dbd352e3986..1cfbb929c694 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2982,6 +2982,9 @@ static int ext4_da_write_end(struct file *file, ext4_has_inline_data(inode)) return ext4_write_inline_data_end(inode, pos, len, copied, page); + if (unlikely(copied < len) && !PageUptodate(page)) + copied = 0; + start = pos & (PAGE_SIZE - 1); end = start + copied - 1; -- GitLab From 631003e2333c12cc1b52df06a707365b7363a159 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 18 Apr 2023 17:45:24 +0900 Subject: [PATCH 4284/5631] btrfs: zoned: fix wrong use of bitops API in btrfs_ensure_empty_zones find_next_bit and find_next_zero_bit take @size as the second parameter and @offset as the third parameter. They are specified opposite in btrfs_ensure_empty_zones(). Thanks to the later loop, it never failed to detect the empty zones. Fix them and (maybe) return the result a bit faster. Note: the naming is a bit confusing, size has two meanings here, bitmap and our range size. Fixes: 1cd6121f2a38 ("btrfs: zoned: implement zoned chunk allocator") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a9b32ba6b2ce..d51057608fc3 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1168,12 +1168,12 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size) return -ERANGE; /* All the zones are conventional */ - if (find_next_bit(zinfo->seq_zones, begin, end) == end) + if (find_next_bit(zinfo->seq_zones, end, begin) == end) return 0; /* All the zones are sequential and empty */ - if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end && - find_next_zero_bit(zinfo->empty_zones, begin, end) == end) + if (find_next_zero_bit(zinfo->seq_zones, end, begin) == end && + find_next_zero_bit(zinfo->empty_zones, end, begin) == end) return 0; for (pos = start; pos < start + size; pos += zinfo->zone_size) { -- GitLab From 6d2ed653185baa5ba601306cbd6cd7192642045d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 27 Apr 2023 20:09:16 -0700 Subject: [PATCH 4285/5631] lsm: move hook comments docs to security/security.c Fix one kernel-doc warning, but invesigating that led to other kernel-doc movement (lsm_hooks.h to security.c) that needs to be fixed also. include/linux/lsm_hooks.h:1: warning: no structured comments found Fixes: e261301c851a ("lsm: move the remaining LSM hook comments to security/security.c") Fixes: 1cd2aca64a5d ("lsm: move the io_uring hook comments to security/security.c") Fixes: 452b670c7222 ("lsm: move the perf hook comments to security/security.c") Fixes: 55e853201a9e ("lsm: move the bpf hook comments to security/security.c") Fixes: b14faf9c94a6 ("lsm: move the audit hook comments to security/security.c") Fixes: 1427ddbe5cc1 ("lsm: move the binder hook comments to security/security.c") Fixes: 43fad2821876 ("lsm: move the sysv hook comments to security/security.c") Fixes: ecc419a44535 ("lsm: move the key hook comments to security/security.c") Fixes: 742b99456e86 ("lsm: move the xfrm hook comments to security/security.c") Fixes: ac318aed5498 ("lsm: move the Infiniband hook comments to security/security.c") Fixes: 4a49f592e931 ("lsm: move the SCTP hook comments to security/security.c") Fixes: 6b6bbe8c02a1 ("lsm: move the socket hook comments to security/security.c") Fixes: 2c2442fd46cd ("lsm: move the AF_UNIX hook comments to security/security.c") Fixes: 2bcf51bf2f03 ("lsm: move the netlink hook comments to security/security.c") Fixes: 130c53bfee4b ("lsm: move the task hook comments to security/security.c") Fixes: a0fd6480de48 ("lsm: move the file hook comments to security/security.c") Fixes: 9348944b775d ("lsm: move the kernfs hook comments to security/security.c") Fixes: 916e32584dfa ("lsm: move the inode hook comments to security/security.c") Fixes: 08526a902cc4 ("lsm: move the filesystem hook comments to security/security.c") Fixes: 36819f185590 ("lsm: move the fs_context hook comments to security/security.c") Fixes: 1661372c912d ("lsm: move the program execution hook comments to security/security.c") Signed-off-by: Randy Dunlap Cc: Paul Moore Cc: James Morris Cc: "Serge E. Hallyn" Cc: linux-security-module@vger.kernel.org Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Cc: KP Singh Cc: bpf@vger.kernel.org Signed-off-by: Paul Moore --- Documentation/bpf/prog_lsm.rst | 2 +- Documentation/security/lsm-development.rst | 6 +++--- Documentation/security/lsm.rst | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/bpf/prog_lsm.rst b/Documentation/bpf/prog_lsm.rst index 0dc3fb0d9544..ad2be02f30c2 100644 --- a/Documentation/bpf/prog_lsm.rst +++ b/Documentation/bpf/prog_lsm.rst @@ -18,7 +18,7 @@ LSM hook: .. c:function:: int file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot); Other LSM hooks which can be instrumented can be found in -``include/linux/lsm_hooks.h``. +``security/security.c``. eBPF programs that use Documentation/bpf/btf.rst do not need to include kernel headers for accessing information from the attached eBPF program's context. diff --git a/Documentation/security/lsm-development.rst b/Documentation/security/lsm-development.rst index ac53e5065f79..5895e529da7f 100644 --- a/Documentation/security/lsm-development.rst +++ b/Documentation/security/lsm-development.rst @@ -11,7 +11,7 @@ that end users and distros can make a more informed decision about which LSMs suit their requirements. For extensive documentation on the available LSM hook interfaces, please -see ``include/linux/lsm_hooks.h`` and associated structures: +see ``security/security.c`` and associated structures: -.. kernel-doc:: include/linux/lsm_hooks.h - :internal: +.. kernel-doc:: security/security.c + :export: diff --git a/Documentation/security/lsm.rst b/Documentation/security/lsm.rst index 6a2a2e973080..c20c7c72e2d6 100644 --- a/Documentation/security/lsm.rst +++ b/Documentation/security/lsm.rst @@ -98,7 +98,7 @@ associate these values with real security attributes. LSM hooks are maintained in lists. A list is maintained for each hook, and the hooks are called in the order specified by CONFIG_LSM. Detailed documentation for each hook is -included in the `include/linux/lsm_hooks.h` header file. +included in the `security/security.c` source file. The LSM framework provides for a close approximation of general security module stacking. It defines -- GitLab From fc05e06e6098ca2c28f7a10da0e00aeea20fa59e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Apr 2023 19:15:37 +0200 Subject: [PATCH 4286/5631] md/raid5: Improve performance for sequential IO Commit 7e55c60acfbb ("md/raid5: Pivot raid5_make_request()") changed the order in which requests for underlying disks are created. Since for large sequential IO adding of requests frequently races with md_raid5 thread submitting bios to underlying disks, this results in a change in IO pattern because intermediate states of new order of request creation result in more smaller discontiguous requests. For RAID5 on top of three rotational disks our performance testing revealed this results in regression in write throughput: iozone -a -s 131072000 -y 4 -q 8 -i 0 -i 1 -R before 7e55c60acfbb: KB reclen write rewrite read reread 131072000 4 493670 525964 524575 513384 131072000 8 540467 532880 512028 513703 after 7e55c60acfbb: KB reclen write rewrite read reread 131072000 4 421785 456184 531278 509248 131072000 8 459283 456354 528449 543834 To reduce the amount of discontiguous requests we can start generating requests with the stripe with the lowest chunk offset as that has the best chance of being adjacent to IO queued previously. This improves the performance to: KB reclen write rewrite read reread 131072000 4 497682 506317 518043 514559 131072000 8 514048 501886 506453 504319 restoring big part of the regression. Fixes: 7e55c60acfbb ("md/raid5: Pivot raid5_make_request()") Cc: stable@vger.kernel.org # v6.0+ Signed-off-by: Jan Kara Reviewed-by: Logan Gunthorpe Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230417171537.17899-1-jack@suse.cz --- drivers/md/raid5.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 812a12e3e41a..4739ed891e75 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6079,6 +6079,38 @@ static enum stripe_result make_stripe_request(struct mddev *mddev, return ret; } +/* + * If the bio covers multiple data disks, find sector within the bio that has + * the lowest chunk offset in the first chunk. + */ +static sector_t raid5_bio_lowest_chunk_sector(struct r5conf *conf, + struct bio *bi) +{ + int sectors_per_chunk = conf->chunk_sectors; + int raid_disks = conf->raid_disks; + int dd_idx; + struct stripe_head sh; + unsigned int chunk_offset; + sector_t r_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1); + sector_t sector; + + /* We pass in fake stripe_head to get back parity disk numbers */ + sector = raid5_compute_sector(conf, r_sector, 0, &dd_idx, &sh); + chunk_offset = sector_div(sector, sectors_per_chunk); + if (sectors_per_chunk - chunk_offset >= bio_sectors(bi)) + return r_sector; + /* + * Bio crosses to the next data disk. Check whether it's in the same + * chunk. + */ + dd_idx++; + while (dd_idx == sh.pd_idx || dd_idx == sh.qd_idx) + dd_idx++; + if (dd_idx >= raid_disks) + return r_sector; + return r_sector + sectors_per_chunk - chunk_offset; +} + static bool raid5_make_request(struct mddev *mddev, struct bio * bi) { DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -6150,6 +6182,17 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) } md_account_bio(mddev, &bi); + /* + * Lets start with the stripe with the lowest chunk offset in the first + * chunk. That has the best chances of creating IOs adjacent to + * previous IOs in case of sequential IO and thus creates the most + * sequential IO pattern. We don't bother with the optimization when + * reshaping as the performance benefit is not worth the complexity. + */ + if (likely(conf->reshape_progress == MaxSector)) + logical_sector = raid5_bio_lowest_chunk_sector(conf, bi); + s = (logical_sector - ctx.first_sector) >> RAID5_STRIPE_SHIFT(conf); + add_wait_queue(&conf->wait_for_overlap, &wait); while (1) { res = make_stripe_request(mddev, conf, &ctx, logical_sector, @@ -6178,7 +6221,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) continue; } - s = find_first_bit(ctx.sectors_to_do, stripe_cnt); + s = find_next_bit_wrap(ctx.sectors_to_do, stripe_cnt, s); if (s == stripe_cnt) break; -- GitLab From b1211978ecf19bceb63a04f53fea4b5d73832a4a Mon Sep 17 00:00:00 2001 From: Jonathan Derrick Date: Mon, 24 Apr 2023 19:14:38 -0600 Subject: [PATCH 4287/5631] md: Fix bitmap offset type in sb writer Bitmap offset is allowed to be negative, indicating that bitmap precedes metadata. Change the type back from sector_t to loff_t to satisfy conditionals and calculations. Reported-by: Dan Carpenter Link: https://lore.kernel.org/linux-raid/CAPhsuW6HuaUJ5WcyPajVgUfkQFYp2D_cy1g6qxN4CU_gP2=z7g@mail.gmail.com/ Fixes: 10172f200b67 ("md: Fix types in sb writer") Signed-off-by: Jonathan Derrick Suggested-by: Yu Kuai Reviewed-by: Yu Kuai Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230425011438.71046-1-jonathan.derrick@linux.dev --- drivers/md/md-bitmap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 920bb68156d2..bc8d7565171d 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -219,7 +219,7 @@ static unsigned int optimal_io_size(struct block_device *bdev, } static unsigned int bitmap_io_size(unsigned int io_size, unsigned int opt_size, - sector_t start, sector_t boundary) + loff_t start, loff_t boundary) { if (io_size != opt_size && start + opt_size / SECTOR_SIZE <= boundary) @@ -237,8 +237,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, struct block_device *bdev; struct mddev *mddev = bitmap->mddev; struct bitmap_storage *store = &bitmap->storage; - sector_t offset = mddev->bitmap_info.offset; - sector_t ps, sboff, doff; + loff_t sboff, offset = mddev->bitmap_info.offset; + sector_t ps, doff; unsigned int size = PAGE_SIZE; unsigned int opt_size = PAGE_SIZE; -- GitLab From 3e46c89c74f2c38e5337d2cf44b0b551adff1cb4 Mon Sep 17 00:00:00 2001 From: Maxim Korotkov Date: Thu, 19 Jan 2023 13:44:43 +0300 Subject: [PATCH 4288/5631] writeback: fix call of incorrect macro the variable 'history' is of type u16, it may be an error that the hweight32 macro was used for it I guess macro hweight16 should be used Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: 2a81490811d0 ("writeback: implement foreign cgroup inode detection") Signed-off-by: Maxim Korotkov Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230119104443.3002-1-korotkov.maxim.s@gmail.com Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 195dc23e0d83..6faeb45234ed 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -829,7 +829,7 @@ void wbc_detach_inode(struct writeback_control *wbc) * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ - if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) + if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } -- GitLab From 835659598c67907b98cd2aa57bb951dfaf675c69 Mon Sep 17 00:00:00 2001 From: Ye Bin Date: Thu, 6 Apr 2023 11:16:27 +0000 Subject: [PATCH 4289/5631] ext4: fix use-after-free read in ext4_find_extent for bigalloc + inline Syzbot found the following issue: loop0: detected capacity change from 0 to 2048 EXT4-fs (loop0): mounted filesystem 00000000-0000-0000-0000-000000000000 without journal. Quota mode: none. ================================================================== BUG: KASAN: use-after-free in ext4_ext_binsearch_idx fs/ext4/extents.c:768 [inline] BUG: KASAN: use-after-free in ext4_find_extent+0x76e/0xd90 fs/ext4/extents.c:931 Read of size 4 at addr ffff888073644750 by task syz-executor420/5067 CPU: 0 PID: 5067 Comm: syz-executor420 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 ext4_ext_binsearch_idx fs/ext4/extents.c:768 [inline] ext4_find_extent+0x76e/0xd90 fs/ext4/extents.c:931 ext4_clu_mapped+0x117/0x970 fs/ext4/extents.c:5809 ext4_insert_delayed_block fs/ext4/inode.c:1696 [inline] ext4_da_map_blocks fs/ext4/inode.c:1806 [inline] ext4_da_get_block_prep+0x9e8/0x13c0 fs/ext4/inode.c:1870 ext4_block_write_begin+0x6a8/0x2290 fs/ext4/inode.c:1098 ext4_da_write_begin+0x539/0x760 fs/ext4/inode.c:3082 generic_perform_write+0x2e4/0x5e0 mm/filemap.c:3772 ext4_buffered_write_iter+0x122/0x3a0 fs/ext4/file.c:285 ext4_file_write_iter+0x1d0/0x18f0 call_write_iter include/linux/fs.h:2186 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x7dc/0xc50 fs/read_write.c:584 ksys_write+0x177/0x2a0 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f4b7a9737b9 RSP: 002b:00007ffc5cac3668 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f4b7a9737b9 RDX: 00000000175d9003 RSI: 0000000020000200 RDI: 0000000000000004 RBP: 00007f4b7a933050 R08: 0000000000000000 R09: 0000000000000000 R10: 000000000000079f R11: 0000000000000246 R12: 00007f4b7a9330e0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 Above issue is happens when enable bigalloc and inline data feature. As commit 131294c35ed6 fixed delayed allocation bug in ext4_clu_mapped for bigalloc + inline. But it only resolved issue when has inline data, if inline data has been converted to extent(ext4_da_convert_inline_data_to_extent) before writepages, there is no EXT4_STATE_MAY_INLINE_DATA flag. However i_data is still store inline data in this scene. Then will trigger UAF when find extent. To resolve above issue, there is need to add judge "ext4_has_inline_data(inode)" in ext4_clu_mapped(). Fixes: 131294c35ed6 ("ext4: fix delayed allocation bug in ext4_clu_mapped for bigalloc + inline") Reported-by: syzbot+bf4bb7731ef73b83a3b4@syzkaller.appspotmail.com Reviewed-by: Jan Kara Reviewed-by: Ye Bin Reviewed-by: Tudor Ambarus Tested-by: Tudor Ambarus Link: https://lore.kernel.org/r/20230406111627.1916759-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index e79c767cc5e0..35703dce23a3 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5795,7 +5795,8 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) * mapped - no physical clusters have been allocated, and the * file has no extents */ - if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) + if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || + ext4_has_inline_data(inode)) return 0; /* search for the extent closest to the first block in the cluster */ -- GitLab From 856dd6c5981260b4d1aa84b78373ad54a203db48 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 20 Apr 2023 09:51:24 -0700 Subject: [PATCH 4290/5631] ext4: fix unused iterator variable warnings When CONFIG_QUOTA is disabled, there are warnings around unused iterator variables: fs/ext4/super.c: In function 'ext4_put_super': fs/ext4/super.c:1262:13: error: unused variable 'i' [-Werror=unused-variable] 1262 | int i, err; | ^ fs/ext4/super.c: In function '__ext4_fill_super': fs/ext4/super.c:5200:22: error: unused variable 'i' [-Werror=unused-variable] 5200 | unsigned int i; | ^ cc1: all warnings being treated as errors The kernel has updated to GNU11, allowing the variables to be declared within the for loop. Do so to clear up the warnings. Fixes: dcbf87589d90 ("ext4: factor out ext4_flex_groups_free()") Signed-off-by: Nathan Chancellor Reviewed-by: Geert Uytterhoeven Reviewed-by: Jan Kara Reviewed-by: Jason Yan Link: https://lore.kernel.org/r/20230420-ext4-unused-variables-super-c-v1-1-138b6db6c21c@kernel.org Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 403cc0e6cd65..f16492b8c98d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1259,7 +1259,7 @@ static void ext4_put_super(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; int aborted = 0; - int i, err; + int err; /* * Unregister sysfs before destroying jbd2 journal. @@ -1311,7 +1311,7 @@ static void ext4_put_super(struct super_block *sb) ext4_flex_groups_free(sbi); ext4_percpu_param_destroy(sbi); #ifdef CONFIG_QUOTA - for (i = 0; i < EXT4_MAXQUOTAS; i++) + for (int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif @@ -5197,7 +5197,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_fsblk_t logical_sb_block; struct inode *root; int ret = -ENOMEM; - unsigned int i; int needs_recovery; int err = 0; ext4_group_t first_not_zeroed; @@ -5628,7 +5627,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) #endif #ifdef CONFIG_QUOTA - for (i = 0; i < EXT4_MAXQUOTAS; i++) + for (unsigned int i = 0; i < EXT4_MAXQUOTAS; i++) kfree(get_qf_name(sb, sbi, i)); #endif fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); -- GitLab From d5e72c4e3256335d6fb75c2e321144f93141f4f5 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 27 Apr 2023 19:18:01 -0400 Subject: [PATCH 4291/5631] ext4: fix lost error code reporting in __ext4_fill_super() When code was factored out of __ext4_fill_super() into ext4_percpu_param_init() the error return was discarded. This meant that it was possible for __ext4_fill_super() to return zero, indicating success, without the struct super getting completely filled in, leading to a potential NULL pointer dereference. Reported-by: syzbot+bbf0f9a213c94f283a5c@syzkaller.appspotmail.com Fixes: 1f79467c8a6b ("ext4: factor out ext4_percpu_param_init() ...") Link: https://syzkaller.appspot.com/bug?id=6dac47d5e58af770c0055f680369586ec32e144c Signed-off-by: Theodore Ts'o Reviewed-by: Jason Yan --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f16492b8c98d..8ed6450effaa 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5502,7 +5502,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; - if (ext4_percpu_param_init(sbi)) + err = ext4_percpu_param_init(sbi); + if (err) goto failed_mount6; if (ext4_has_feature_flex_bg(sb)) -- GitLab From 3b50d5018ed06a647bb26c44bb5ae74e59c903c7 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 27 Apr 2023 22:49:34 -0400 Subject: [PATCH 4292/5631] ext4: reflect error codes from ext4_multi_mount_protect() to its callers This will allow more fine-grained errno codes to be returned by the mount system call. Cc: Andreas Dilger Signed-off-by: Theodore Ts'o --- fs/ext4/mmp.c | 9 ++++++++- fs/ext4/super.c | 16 +++++++++------- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 4681fff6665f..4022bc713421 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -282,6 +282,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (mmp_block < le32_to_cpu(es->s_first_data_block) || mmp_block >= ext4_blocks_count(es)) { ext4_warning(sb, "Invalid MMP block in superblock"); + retval = -EINVAL; goto failed; } @@ -307,6 +308,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (seq == EXT4_MMP_SEQ_FSCK) { dump_mmp_msg(sb, mmp, "fsck is running on the filesystem"); + retval = -EBUSY; goto failed; } @@ -320,6 +322,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (schedule_timeout_interruptible(HZ * wait_time) != 0) { ext4_warning(sb, "MMP startup interrupted, failing mount\n"); + retval = -ETIMEDOUT; goto failed; } @@ -330,6 +333,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); + retval = -EBUSY; goto failed; } @@ -349,6 +353,7 @@ int ext4_multi_mount_protect(struct super_block *sb, */ if (schedule_timeout_interruptible(HZ * wait_time) != 0) { ext4_warning(sb, "MMP startup interrupted, failing mount"); + retval = -ETIMEDOUT; goto failed; } @@ -359,6 +364,7 @@ int ext4_multi_mount_protect(struct super_block *sb, if (seq != le32_to_cpu(mmp->mmp_seq)) { dump_mmp_msg(sb, mmp, "Device is already active on another node."); + retval = -EBUSY; goto failed; } @@ -378,6 +384,7 @@ int ext4_multi_mount_protect(struct super_block *sb, EXT4_SB(sb)->s_mmp_tsk = NULL; ext4_warning(sb, "Unable to create kmmpd thread for %s.", sb->s_id); + retval = -ENOMEM; goto failed; } @@ -385,5 +392,5 @@ int ext4_multi_mount_protect(struct super_block *sb, failed: brelse(bh); - return 1; + return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8ed6450effaa..c8ae6b7e8615 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5328,9 +5328,11 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_has_feature_orphan_present(sb) || ext4_has_feature_journal_needs_recovery(sb)); - if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) - if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) + if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) { + err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); + if (err) goto failed_mount3a; + } /* * The first inode we look at is the journal inode. Don't try @@ -6565,12 +6567,12 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) goto restore_opts; sb->s_flags &= ~SB_RDONLY; - if (ext4_has_feature_mmp(sb)) - if (ext4_multi_mount_protect(sb, - le64_to_cpu(es->s_mmp_block))) { - err = -EROFS; + if (ext4_has_feature_mmp(sb)) { + err = ext4_multi_mount_protect(sb, + le64_to_cpu(es->s_mmp_block)); + if (err) goto restore_opts; - } + } #ifdef CONFIG_QUOTA enable_quota = 1; #endif -- GitLab From d4fab7b28e2f5d74790d47a8d298da0abfb5132f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 27 Apr 2023 23:01:41 -0400 Subject: [PATCH 4293/5631] ext4: clean up error handling in __ext4_fill_super() There were two ways to return an error code; one was via setting the 'err' variable, and the second, if err was zero, was via the 'ret' variable. This was both confusing and fragile, and when code was factored out of __ext4_fill_super(), some of the error codes returned by the original code was replaced by -EINVAL, and in one case, the error code was placed by 0, triggering a kernel null pointer dereference. Clean this up by removing the 'ret' variable, leaving only one way to set the error code to be returned, and restore the errno codes that were returned via the the mount system call as they were before we started refactoring __ext4_fill_super(). Signed-off-by: Theodore Ts'o Reviewed-by: Jason Yan --- fs/ext4/super.c | 51 ++++++++++++++++++++++++++++--------------------- 1 file changed, 29 insertions(+), 22 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c8ae6b7e8615..39f00f05f981 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5196,9 +5196,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t logical_sb_block; struct inode *root; - int ret = -ENOMEM; int needs_recovery; - int err = 0; + int err; ext4_group_t first_not_zeroed; struct ext4_fs_context *ctx = fc->fs_private; int silent = fc->sb_flags & SB_SILENT; @@ -5211,8 +5210,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sbi->s_sectors_written_start = part_stat_read(sb->s_bdev, sectors[STAT_WRITE]); - /* -EINVAL is default */ - ret = -EINVAL; err = ext4_load_super(sb, &logical_sb_block, silent); if (err) goto out_fail; @@ -5238,7 +5235,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) */ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT; - if (ext4_inode_info_init(sb, es)) + err = ext4_inode_info_init(sb, es); + if (err) goto failed_mount; err = parse_apply_sb_mount_options(sb, ctx); @@ -5254,10 +5252,12 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_apply_options(fc, sb); - if (ext4_encoding_init(sb, es)) + err = ext4_encoding_init(sb, es); + if (err) goto failed_mount; - if (ext4_check_journal_data_mode(sb)) + err = ext4_check_journal_data_mode(sb); + if (err) goto failed_mount; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -5266,18 +5266,22 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) /* i_version is always enabled now */ sb->s_flags |= SB_I_VERSION; - if (ext4_check_feature_compatibility(sb, es, silent)) + err = ext4_check_feature_compatibility(sb, es, silent); + if (err) goto failed_mount; - if (ext4_block_group_meta_init(sb, silent)) + err = ext4_block_group_meta_init(sb, silent); + if (err) goto failed_mount; ext4_hash_info_init(sb); - if (ext4_handle_clustersize(sb)) + err = ext4_handle_clustersize(sb); + if (err) goto failed_mount; - if (ext4_check_geometry(sb, es)) + err = ext4_check_geometry(sb, es); + if (err) goto failed_mount; timer_setup(&sbi->s_err_report, print_daily_error_info, 0); @@ -5288,8 +5292,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err) goto failed_mount3; - /* Register extent status tree shrinker */ - if (ext4_es_register_shrinker(sbi)) + err = ext4_es_register_shrinker(sbi); + if (err) goto failed_mount3; sbi->s_stripe = ext4_get_stripe_size(sbi); @@ -5334,6 +5338,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) goto failed_mount3a; } + err = -EINVAL; /* * The first inode we look at is the journal inode. Don't try * root first: it may be modified in the journal! @@ -5385,6 +5390,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (!sbi->s_ea_block_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); + err = -EINVAL; goto failed_mount_wq; } @@ -5393,6 +5399,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (!sbi->s_ea_inode_cache) { ext4_msg(sb, KERN_ERR, "Failed to create ea_inode_cache"); + err = -EINVAL; goto failed_mount_wq; } } @@ -5427,7 +5434,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!EXT4_SB(sb)->rsv_conversion_wq) { printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); - ret = -ENOMEM; + err = -ENOMEM; goto failed_mount4; } @@ -5439,28 +5446,28 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) root = ext4_iget(sb, EXT4_ROOT_INO, EXT4_IGET_SPECIAL); if (IS_ERR(root)) { ext4_msg(sb, KERN_ERR, "get root inode failed"); - ret = PTR_ERR(root); + err = PTR_ERR(root); root = NULL; goto failed_mount4; } if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { ext4_msg(sb, KERN_ERR, "corrupt root inode, run e2fsck"); iput(root); + err = -EFSCORRUPTED; goto failed_mount4; } sb->s_root = d_make_root(root); if (!sb->s_root) { ext4_msg(sb, KERN_ERR, "get root dentry failed"); - ret = -ENOMEM; + err = -ENOMEM; goto failed_mount4; } - ret = ext4_setup_super(sb, es, sb_rdonly(sb)); - if (ret == -EROFS) { + err = ext4_setup_super(sb, es, sb_rdonly(sb)); + if (err == -EROFS) { sb->s_flags |= SB_RDONLY; - ret = 0; - } else if (ret) + } else if (err) goto failed_mount4a; ext4_set_resv_clusters(sb); @@ -5513,7 +5520,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); - ret = -ENOMEM; + err = -ENOMEM; goto failed_mount6; } @@ -5639,7 +5646,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) ext4_blkdev_remove(sbi); out_fail: sb->s_fs_info = NULL; - return err ? err : ret; + return err; } static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) -- GitLab From 21e26d5e54ab7cfe6b488fd27d4d70956d07e03b Mon Sep 17 00:00:00 2001 From: Eric Van Hensbergen Date: Wed, 26 Apr 2023 16:18:49 +0000 Subject: [PATCH 4294/5631] fs/9p: Fix bit operation logic error This re-introduces a fix that somehow got dropped during rebase of the current series in for-next. When writeback is enabled, opens are forced to support both read and write operations but with the logic error other flags may be dropped unintentionaly. Reported-by: Christophe Jaillet Signed-off-by: Eric Van Hensbergen --- fs/9p/vfs_inode.c | 2 +- fs/9p/vfs_inode_dotl.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 54dfe4f10f43..3791f642c502 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -823,7 +823,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, p9_omode = v9fs_uflags2omode(flags, v9fs_proto_dotu(v9ses)); if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { - p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; + p9_omode = (p9_omode & ~P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index f9371b5b70ea..3acf2bcb69cc 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -288,7 +288,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, } if ((v9ses->cache & CACHE_WRITEBACK) && (p9_omode & P9_OWRITE)) { - p9_omode = (p9_omode & !P9_OWRITE) | P9_ORDWR; + p9_omode = (p9_omode & ~P9_OWRITE) | P9_ORDWR; p9_debug(P9_DEBUG_CACHE, "write-only file with writeback enabled, creating w/ O_RDWR\n"); } -- GitLab From 8176080d59e6d4ff9fc97ae534063073b4f7a715 Mon Sep 17 00:00:00 2001 From: Tao Su Date: Fri, 28 Apr 2023 12:51:49 +0800 Subject: [PATCH 4295/5631] block: Skip destroyed blkg when restart in blkg_destroy_all() Kernel hang in blkg_destroy_all() when total blkg greater than BLKG_DESTROY_BATCH_SIZE, because of not removing destroyed blkg in blkg_list. So the size of blkg_list is same after destroying a batch of blkg, and the infinite 'restart' occurs. Since blkg should stay on the queue list until blkg_free_workfn(), skip destroyed blkg when restart a new round, which will solve this kernel hang issue and satisfy the previous will to restart. Reported-by: Xiangfei Ma Tested-by: Xiangfei Ma Tested-by: Farrah Chen Signed-off-by: Tao Su Fixes: f1c006f1c685 ("blk-cgroup: synchronize pd_free_fn() from blkg_free_workfn() and blkcg_deactivate_policy()") Suggested-and-reviewed-by: Yu Kuai Link: https://lore.kernel.org/r/20230428045149.1310073-1-tao1.su@linux.intel.com Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 1c1ebeb51003..0ecb4cce8af2 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -527,6 +527,9 @@ static void blkg_destroy_all(struct gendisk *disk) list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; + if (hlist_unhashed(&blkg->blkcg_node)) + continue; + spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); -- GitLab From 25feda6fbd0cfefcb69308fb20d4d4815a107c5e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 4 Feb 2023 10:43:10 -0800 Subject: [PATCH 4296/5631] drm/nouveau/disp: More DP_RECEIVER_CAP_SIZE array fixes More arrays (and arguments) for dcpd were set to 16, when it looks like DP_RECEIVER_CAP_SIZE (15) should be used. Fix the remaining cases, seen with GCC 13: ../drivers/gpu/drm/nouveau/nvif/outp.c: In function 'nvif_outp_acquire_dp': ../include/linux/fortify-string.h:57:33: warning: array subscript 'unsigned char[16][0]' is partly outside array bounds of 'u8[15]' {aka 'unsigned char[15]'} [-Warray-bounds=] 57 | #define __underlying_memcpy __builtin_memcpy | ^ ... ../drivers/gpu/drm/nouveau/nvif/outp.c:140:9: note: in expansion of macro 'memcpy' 140 | memcpy(args.dp.dpcd, dpcd, sizeof(args.dp.dpcd)); | ^~~~~~ ../drivers/gpu/drm/nouveau/nvif/outp.c:130:49: note: object 'dpcd' of size [0, 15] 130 | nvif_outp_acquire_dp(struct nvif_outp *outp, u8 dpcd[DP_RECEIVER_CAP_SIZE], | ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~ Fixes: 813443721331 ("drm/nouveau/disp: move DP link config into acquire") Cc: Ben Skeggs Cc: Lyude Paul Cc: Karol Herbst Cc: David Airlie Cc: Daniel Vetter Cc: Dave Airlie Cc: "Gustavo A. R. Silva" Cc: dri-devel@lists.freedesktop.org Cc: nouveau@lists.freedesktop.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Karol Herbst Signed-off-by: Karol Herbst Link: https://patchwork.freedesktop.org/patch/msgid/20230204184307.never.825-kees@kernel.org --- drivers/gpu/drm/nouveau/include/nvif/if0012.h | 4 +++- drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h | 3 ++- drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c | 2 +- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/include/nvif/if0012.h b/drivers/gpu/drm/nouveau/include/nvif/if0012.h index eb99d84eb844..16d4ad5023a3 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/if0012.h +++ b/drivers/gpu/drm/nouveau/include/nvif/if0012.h @@ -2,6 +2,8 @@ #ifndef __NVIF_IF0012_H__ #define __NVIF_IF0012_H__ +#include + union nvif_outp_args { struct nvif_outp_v0 { __u8 version; @@ -63,7 +65,7 @@ union nvif_outp_acquire_args { __u8 hda; __u8 mst; __u8 pad04[4]; - __u8 dpcd[16]; + __u8 dpcd[DP_RECEIVER_CAP_SIZE]; } dp; }; } v0; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h index b7631c1ab242..4e7f873f66e2 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h @@ -3,6 +3,7 @@ #define __NVKM_DISP_OUTP_H__ #include "priv.h" +#include #include #include #include @@ -42,7 +43,7 @@ struct nvkm_outp { bool aux_pwr_pu; u8 lttpr[6]; u8 lttprs; - u8 dpcd[16]; + u8 dpcd[DP_RECEIVER_CAP_SIZE]; struct { int dpcd; /* -1, or index into SUPPORTED_LINK_RATES table */ diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c index 4f0ca709c85a..fc283a4a1522 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uoutp.c @@ -146,7 +146,7 @@ nvkm_uoutp_mthd_release(struct nvkm_outp *outp, void *argv, u32 argc) } static int -nvkm_uoutp_mthd_acquire_dp(struct nvkm_outp *outp, u8 dpcd[16], +nvkm_uoutp_mthd_acquire_dp(struct nvkm_outp *outp, u8 dpcd[DP_RECEIVER_CAP_SIZE], u8 link_nr, u8 link_bw, bool hda, bool mst) { int ret; -- GitLab From ca29699a57ecee6084a4056f5bfd6f11dd359a71 Mon Sep 17 00:00:00 2001 From: Jianhua Lu Date: Thu, 27 Apr 2023 20:21:32 +0800 Subject: [PATCH 4297/5631] dt-bindings: display/msm: dsi-controller-main: Document qcom, master-dsi and qcom, sync-dual-dsi This fixes warning: sm8250-xiaomi-elish-csot.dtb: dsi@ae94000: Unevaluated properties are not allowed ('qcom,master-dsi', 'qcom,sync-dual-dsi' were unexpected) Reviewed-by: Dmitry Baryshkov Acked-by: Rob Herring Signed-off-by: Jianhua Lu Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings") Reviewed-by: Abhinav Kumar Patchwork: https://patchwork.freedesktop.org/patch/534306/ Link: https://lore.kernel.org/r/20230427122132.24840-1-lujianhua000@gmail.com Signed-off-by: Abhinav Kumar --- .../bindings/display/msm/dsi-controller-main.yaml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index c8884a84e73d..51808b1d2726 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -82,6 +82,18 @@ properties: Indicates if the DSI controller is driving a panel which needs 2 DSI links. + qcom,master-dsi: + type: boolean + description: | + Indicates if the DSI controller is the master DSI controller when + qcom,dual-dsi-mode enabled. + + qcom,sync-dual-dsi: + type: boolean + description: | + Indicates if the DSI controller needs to sync the other DSI controller + with MIPI DCS commands when qcom,dual-dsi-mode enabled. + assigned-clocks: minItems: 2 maxItems: 4 -- GitLab From fbd2a05f29a95d5b42b294bf47e55a711424965b Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Thu, 6 Apr 2023 15:16:52 -0400 Subject: [PATCH 4298/5631] NFSv4.2: Rework scratch handling for READ_PLUS Instead of using a tiny, static scratch buffer, we should use a kmalloc()-ed buffer that is allocated when checking for read plus usage. This lets us use the buffer before decoding any part of the READ_PLUS operation instead of setting it right before segment decoding, meaning it should be a little more robust. Signed-off-by: Anna Schumaker --- fs/nfs/nfs42xdr.c | 4 ++-- fs/nfs/nfs4proc.c | 17 ++++++++++++----- include/linux/nfs_xdr.h | 1 + 3 files changed, 15 insertions(+), 7 deletions(-) diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index d80ee88ca996..a6df815a140c 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1122,7 +1122,6 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) uint32_t segments; struct read_plus_segment *segs; int status, i; - char scratch_buf[16]; __be32 *p; status = decode_op_hdr(xdr, OP_READ_PLUS); @@ -1143,7 +1142,6 @@ static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res) if (!segs) return -ENOMEM; - xdr_set_scratch_buffer(xdr, &scratch_buf, sizeof(scratch_buf)); status = -EIO; for (i = 0; i < segments; i++) { status = decode_read_plus_segment(xdr, &segs[i]); @@ -1348,6 +1346,8 @@ static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp, struct compound_hdr hdr; int status; + xdr_set_scratch_buffer(xdr, res->scratch, sizeof(res->scratch)); + status = decode_compound_hdr(xdr, &hdr); if (status) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5607b1e2b821..18f25ff4bff7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5439,6 +5439,8 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) { + if (hdr->res.scratch) + kfree(hdr->res.scratch); if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) @@ -5452,17 +5454,22 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) } #if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS -static void nfs42_read_plus_support(struct nfs_pgio_header *hdr, +static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, struct rpc_message *msg) { /* Note: We don't use READ_PLUS with pNFS yet */ - if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) + if (nfs_server_capable(hdr->inode, NFS_CAP_READ_PLUS) && !hdr->ds_clp) { msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS]; + hdr->res.scratch = kmalloc(32, GFP_KERNEL); + return hdr->res.scratch != NULL; + } + return false; } #else -static void nfs42_read_plus_support(struct nfs_pgio_header *hdr, +static bool nfs42_read_plus_support(struct nfs_pgio_header *hdr, struct rpc_message *msg) { + return false; } #endif /* CONFIG_NFS_V4_2 */ @@ -5472,8 +5479,8 @@ static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr, hdr->timestamp = jiffies; if (!hdr->pgio_done_cb) hdr->pgio_done_cb = nfs4_read_done_cb; - msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; - nfs42_read_plus_support(hdr, msg); + if (!nfs42_read_plus_support(hdr, msg)) + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ]; nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e196ef595908..29a1b39794bf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ -- GitLab From 0463ca3d7159bb86efa6f36ca70a41bb711bc6f8 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 26 Apr 2023 00:00:17 -0700 Subject: [PATCH 4299/5631] perf stat: Avoid SEGV on counter->name Switch to use evsel__name() that doesn't return NULL for hardware and similar events. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230426070050.1315519-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/stat-display.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index e6035ecbeee8..73b2ff2ddf29 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -747,7 +747,7 @@ static void uniquify_event_name(struct evsel *counter) int ret = 0; if (counter->uniquified_name || counter->use_config_name || - !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + !counter->pmu_name || !strncmp(evsel__name(counter), counter->pmu_name, strlen(counter->pmu_name))) return; -- GitLab From 06bff3d98cf2cfef225f8190bb679f3f8cb89912 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 28 Apr 2023 00:37:27 -0700 Subject: [PATCH 4300/5631] perf stat: Disable TopdownL1 on hybrid Bugs with event parsing, event grouping and metrics causes the TopdownL1 metricgroup to crash the perf command. Temporarily disable the group if no events/metrics are spcecified. Reviewed-by: Kan Liang Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230428073809.1803624-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index efda63f6bf32..be9677aa642f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1885,7 +1885,12 @@ static int add_default_attributes(void) * Add TopdownL1 metrics if they exist. To minimize * multiplexing, don't request threshold computation. */ - if (metricgroup__has_metric("TopdownL1") && + /* + * TODO: TopdownL1 is disabled on hybrid CPUs to avoid a crashes + * caused by exposing latent bugs. This is fixed properly in: + * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ + */ + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && metricgroup__parse_groups(evsel_list, "TopdownL1", /*metric_no_group=*/false, /*metric_no_merge=*/false, @@ -1894,6 +1899,7 @@ static int add_default_attributes(void) stat_config.system_wide, &stat_config.metric_events) < 0) return -1; + /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) return -1; -- GitLab From 943fb67b090212f1d3789eb7796b1c9045c62fd6 Mon Sep 17 00:00:00 2001 From: Steve French Date: Wed, 26 Apr 2023 22:01:31 -0500 Subject: [PATCH 4301/5631] cifs: missing lock when updating session status Coverity noted a place where we were not grabbing the ses_lock when setting (and checking) ses_status. Addresses-Coverity: 1536833 ("Data race condition (MISSING_LOCK)") Reviewed-by: Paulo Alcantara (SUSE) Reviewed-by: Bharath SM Signed-off-by: Steve French --- fs/cifs/connect.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1cbb90587995..7bfef741f758 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1916,18 +1916,22 @@ void cifs_put_smb_ses(struct cifs_ses *ses) /* ses_count can never go negative */ WARN_ON(ses->ses_count < 0); + spin_lock(&ses->ses_lock); if (ses->ses_status == SES_GOOD) ses->ses_status = SES_EXITING; - cifs_free_ipc(ses); - if (ses->ses_status == SES_EXITING && server->ops->logoff) { + spin_unlock(&ses->ses_lock); + cifs_free_ipc(ses); xid = get_xid(); rc = server->ops->logoff(xid, ses); if (rc) cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n", __func__, rc); _free_xid(xid); + } else { + spin_unlock(&ses->ses_lock); + cifs_free_ipc(ses); } spin_lock(&cifs_tcp_ses_lock); -- GitLab From c09ba02cfaf35732f7e36f291dd9679a6f109a12 Mon Sep 17 00:00:00 2001 From: Steve French Date: Thu, 27 Apr 2023 12:45:54 -0500 Subject: [PATCH 4302/5631] SMB3.1.1: add new tree connect ShareFlags Also update these flag names in a few places to match the simpler easier to understand names now used in the protocol documentation (see MS-SMB2 section 2.2.10) Acked-by: Bharath SM Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/smbfs_common/smb2pdu.h | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h index ace133cf6072..334f11ed5146 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smbfs_common/smb2pdu.h @@ -327,17 +327,18 @@ struct smb2_tree_connect_req { #define SMB2_SHAREFLAG_NO_CACHING 0x00000030 #define SHI1005_FLAGS_DFS 0x00000001 #define SHI1005_FLAGS_DFS_ROOT 0x00000002 -#define SHI1005_FLAGS_RESTRICT_EXCLUSIVE_OPENS 0x00000100 -#define SHI1005_FLAGS_FORCE_SHARED_DELETE 0x00000200 -#define SHI1005_FLAGS_ALLOW_NAMESPACE_CACHING 0x00000400 -#define SHI1005_FLAGS_ACCESS_BASED_DIRECTORY_ENUM 0x00000800 -#define SHI1005_FLAGS_FORCE_LEVELII_OPLOCK 0x00001000 -#define SHI1005_FLAGS_ENABLE_HASH_V1 0x00002000 -#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000 +#define SMB2_SHAREFLAG_RESTRICT_EXCLUSIVE_OPENS 0x00000100 +#define SMB2_SHAREFLAG_FORCE_SHARED_DELETE 0x00000200 +#define SMB2_SHAREFLAG_ALLOW_NAMESPACE_CACHING 0x00000400 +#define SMB2_SHAREFLAG_ACCESS_BASED_DIRECTORY_ENUM 0x00000800 +#define SMB2_SHAREFLAG_FORCE_LEVELII_OPLOCK 0x00001000 +#define SMB2_SHAREFLAG_ENABLE_HASH_V1 0x00002000 +#define SMB2_SHAREFLAG_ENABLE_HASH_V2 0x00004000 #define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000 #define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */ #define SMB2_SHAREFLAG_COMPRESS_DATA 0x00100000 /* 3.1.1 */ -#define SHI1005_FLAGS_ALL 0x0014FF33 +#define SMB2_SHAREFLAG_ISOLATED_TRANSPORT 0x00200000 +#define SHI1005_FLAGS_ALL 0x0034FF33 /* Possible share capabilities */ #define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */ -- GitLab From 1149c8467ddebfb6bb9aab37830f70a49cab7085 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 28 Apr 2023 00:21:10 -0500 Subject: [PATCH 4303/5631] smb3: make query_on_disk_id open context consistent and move to common code cifs and ksmbd were using a slightly different version of the query_on_disk_id struct which could be confusing. Use the ksmbd version of this struct, and move it to common code. Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 2 +- fs/cifs/smb2pdu.h | 9 --------- fs/ksmbd/smb2pdu.h | 8 -------- fs/smbfs_common/smb2pdu.h | 11 +++++++++++ 4 files changed, 12 insertions(+), 18 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 281e0b12658d..0521aa1da644 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2063,7 +2063,7 @@ create_reconnect_durable_buf(struct cifs_fid *fid) static void parse_query_id_ctxt(struct create_context *cc, struct smb2_file_all_info *buf) { - struct create_on_disk_id *pdisk_id = (struct create_on_disk_id *)cc; + struct create_disk_id_rsp *pdisk_id = (struct create_disk_id_rsp *)cc; cifs_dbg(FYI, "parse query id context 0x%llx 0x%llx\n", pdisk_id->DiskFileId, pdisk_id->VolumeId); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 2114e8a0c63a..efe55a572e4c 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -170,15 +170,6 @@ struct durable_reconnect_context_v2 { __le32 Flags; /* see above DHANDLE_FLAG_PERSISTENT */ } __packed; -/* See MS-SMB2 2.2.14.2.9 */ -struct create_on_disk_id { - struct create_context ccontext; - __u8 Name[8]; - __le64 DiskFileId; - __le64 VolumeId; - __u32 Reserved[4]; -} __packed; - /* See MS-SMB2 2.2.14.2.12 */ struct durable_reconnect_context_v2_rsp { __le32 Timeout; diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 9420dd2813fb..bcf71fd4dc1e 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -144,14 +144,6 @@ struct create_mxac_rsp { __le32 MaximalAccess; } __packed; -struct create_disk_id_rsp { - struct create_context ccontext; - __u8 Name[8]; - __le64 DiskFileId; - __le64 VolumeId; - __u8 Reserved[16]; -} __packed; - /* equivalent of the contents of SMB3.1.1 POSIX open context response */ struct create_posix_rsp { struct create_context ccontext; diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h index 334f11ed5146..43c92e898ee9 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smbfs_common/smb2pdu.h @@ -1181,6 +1181,7 @@ struct create_posix { #define SMB2_LEASE_KEY_SIZE 16 +/* See MS-SMB2 2.2.13.2.8 */ struct lease_context { __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; @@ -1188,6 +1189,7 @@ struct lease_context { __le64 LeaseDuration; } __packed; +/* See MS-SMB2 2.2.13.2.10 */ struct lease_context_v2 { __u8 LeaseKey[SMB2_LEASE_KEY_SIZE]; __le32 LeaseState; @@ -1211,6 +1213,15 @@ struct create_lease_v2 { __u8 Pad[4]; } __packed; +/* See MS-SMB2 2.2.14.2.9 */ +struct create_disk_id_rsp { + struct create_context ccontext; + __u8 Name[8]; + __le64 DiskFileId; + __le64 VolumeId; + __u8 Reserved[16]; +} __packed; + /* See MS-SMB2 2.2.31 and 2.2.32 */ struct smb2_ioctl_req { struct smb2_hdr hdr; -- GitLab From 2fe187dca6030dd5dbecfe38e9610544d46e8c02 Mon Sep 17 00:00:00 2001 From: Steve French Date: Fri, 28 Apr 2023 00:41:58 -0500 Subject: [PATCH 4304/5631] smb3: move some common open context structs to smbfs_common create durable and create durable reconnect context and the maximal access create context struct definitions can be put in common code in smbfs_common Reviewed-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2pdu.h | 11 ----------- fs/ksmbd/smb2pdu.h | 25 ------------------------- fs/smbfs_common/smb2pdu.h | 28 ++++++++++++++++++++++++++++ 3 files changed, 28 insertions(+), 36 deletions(-) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index efe55a572e4c..220994d0a0f7 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -132,17 +132,6 @@ struct share_redirect_error_context_rsp { #define SMB2_LEASE_HANDLE_CACHING_HE 0x02 #define SMB2_LEASE_WRITE_CACHING_HE 0x04 -struct create_durable { - struct create_context ccontext; - __u8 Name[8]; - union { - __u8 Reserved[16]; - struct { - __u64 PersistentFileId; - __u64 VolatileFileId; - } Fid; - } Data; -} __packed; /* See MS-SMB2 2.2.13.2.11 */ /* Flags */ diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index bcf71fd4dc1e..67dc552f2ef7 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -70,18 +70,6 @@ struct create_durable_req_v2 { __u8 CreateGuid[16]; } __packed; -struct create_durable_reconn_req { - struct create_context ccontext; - __u8 Name[8]; - union { - __u8 Reserved[16]; - struct { - __u64 PersistentFileId; - __u64 VolatileFileId; - } Fid; - } Data; -} __packed; - struct create_durable_reconn_v2_req { struct create_context ccontext; __u8 Name[8]; @@ -109,12 +97,6 @@ struct create_app_inst_id_vers { __le64 AppInstanceVersionLow; } __packed; -struct create_mxac_req { - struct create_context ccontext; - __u8 Name[8]; - __le64 Timestamp; -} __packed; - struct create_alloc_size_req { struct create_context ccontext; __u8 Name[8]; @@ -137,13 +119,6 @@ struct create_durable_v2_rsp { __le32 Flags; } __packed; -struct create_mxac_rsp { - struct create_context ccontext; - __u8 Name[8]; - __le32 QueryStatus; - __le32 MaximalAccess; -} __packed; - /* equivalent of the contents of SMB3.1.1 POSIX open context response */ struct create_posix_rsp { struct create_context ccontext; diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h index 43c92e898ee9..3b43a51e6f7e 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smbfs_common/smb2pdu.h @@ -1172,6 +1172,34 @@ struct create_posix { __u32 Reserved; } __packed; +/* See MS-SMB2 2.2.13.2.3 and MS-SMB2 2.2.13.2.4 */ +struct create_durable { + struct create_context ccontext; + __u8 Name[8]; + union { + __u8 Reserved[16]; + struct { + __u64 PersistentFileId; + __u64 VolatileFileId; + } Fid; + } Data; +} __packed; + +/* See MS-SMB2 2.2.13.2.5 */ +struct create_mxac_req { + struct create_context ccontext; + __u8 Name[8]; + __le64 Timestamp; +} __packed; + +/* See MS-SMB2 2.2.14.2.5 */ +struct create_mxac_rsp { + struct create_context ccontext; + __u8 Name[8]; + __le32 QueryStatus; + __le32 MaximalAccess; +} __packed; + #define SMB2_LEASE_NONE_LE cpu_to_le32(0x00) #define SMB2_LEASE_READ_CACHING_LE cpu_to_le32(0x01) #define SMB2_LEASE_HANDLE_CACHING_LE cpu_to_le32(0x02) -- GitLab From 9be11a69315e26363a4de8930bc50d0901a96775 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 23 Apr 2023 01:19:28 -0500 Subject: [PATCH 4305/5631] cifs: update internal module version number for cifs.ko From 2.42 to 2.43 Signed-off-by: Steve French --- fs/cifs/cifsfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 415176b2cf32..74cd6fafb33e 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -162,6 +162,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 41 -#define CIFS_VERSION "2.42" +#define SMB3_PRODUCT_BUILD 43 +#define CIFS_VERSION "2.43" #endif /* _CIFSFS_H */ -- GitLab From 90211b58828924577b589e59814f53aec4557fb9 Mon Sep 17 00:00:00 2001 From: Xingyu Wu Date: Wed, 26 Apr 2023 11:12:16 +0800 Subject: [PATCH 4306/5631] watchdog: starfive: Fix the probe return error if PM and early_enable are both disabled When the starfive watchdog driver uses 'pm_runtime_put_sync()' as probe return value at last and 'early_enable' is disabled, it could return the error '-ENOSYS' if the CONFIG_PM is disabled, but the driver should works normally. Drop the 'return' and keep the 'pm_runtime_put_sync()', but do not use it as the return value. Fixes: db728ea9c7be ("drivers: watchdog: Add StarFive Watchdog driver") Signed-off-by: Xingyu Wu Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230426031216.37981-1-xingyu.wu@starfivetech.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/starfive-wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c index 1995cceca51e..8f378900624d 100644 --- a/drivers/watchdog/starfive-wdt.c +++ b/drivers/watchdog/starfive-wdt.c @@ -492,7 +492,7 @@ static int starfive_wdt_probe(struct platform_device *pdev) goto err_exit; if (!early_enable) - return pm_runtime_put_sync(&pdev->dev); + pm_runtime_put_sync(&pdev->dev); return 0; -- GitLab From b23c1f807cb20a9a4c42b63c3d80f63b045a43ef Mon Sep 17 00:00:00 2001 From: Xingyu Wu Date: Thu, 27 Apr 2023 15:44:00 +0800 Subject: [PATCH 4307/5631] watchdog: starfive: Fix the warning of starfive_wdt_match Drop the function of of_match_ptr() to fix the warning of unused variable 'starfive_wdt_match'. Fixes: db728ea9c7be ("drivers: watchdog: Add StarFive Watchdog driver") Signed-off-by: Xingyu Wu Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20230427074400.55380-1-xingyu.wu@starfivetech.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/starfive-wdt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/watchdog/starfive-wdt.c b/drivers/watchdog/starfive-wdt.c index 8f378900624d..8058fca4d05d 100644 --- a/drivers/watchdog/starfive-wdt.c +++ b/drivers/watchdog/starfive-wdt.c @@ -595,7 +595,7 @@ static struct platform_driver starfive_wdt_driver = { .driver = { .name = "starfive-wdt", .pm = &starfive_wdt_pm_ops, - .of_match_table = of_match_ptr(starfive_wdt_match), + .of_match_table = starfive_wdt_match, }, }; module_platform_driver(starfive_wdt_driver); -- GitLab From 7f5390750645756bd5da2b24fac285f2654dd922 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 26 Apr 2023 08:52:48 +0200 Subject: [PATCH 4308/5631] watchdog: dw_wdt: Fix the error handling path of dw_wdt_drv_probe() The commit in Fixes has only updated the remove function and missed the error handling path of the probe. Add the missing reset_control_assert() call. Fixes: 65a3b6935d92 ("watchdog: dw_wdt: get reset lines from dt") Signed-off-by: Christophe JAILLET Reviewed-by: Philipp Zabel Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/fbb650650bbb33a8fa2fd028c23157bedeed50e1.1682491863.git.christophe.jaillet@wanadoo.fr Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/dw_wdt.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c index 6f88bd81f8a1..a1354a59eb37 100644 --- a/drivers/watchdog/dw_wdt.c +++ b/drivers/watchdog/dw_wdt.c @@ -635,7 +635,7 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) ret = dw_wdt_init_timeouts(dw_wdt, dev); if (ret) - goto out_disable_clk; + goto out_assert_rst; wdd = &dw_wdt->wdd; wdd->ops = &dw_wdt_ops; @@ -667,12 +667,15 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) ret = watchdog_register_device(wdd); if (ret) - goto out_disable_pclk; + goto out_assert_rst; dw_wdt_dbgfs_init(dw_wdt); return 0; +out_assert_rst: + reset_control_assert(dw_wdt->rst); + out_disable_pclk: clk_disable_unprepare(dw_wdt->pclk); -- GitLab From 10f67d1fd275528e62109de2ece26371833638e5 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Wed, 26 Apr 2023 08:52:49 +0200 Subject: [PATCH 4309/5631] watchdog: dw_wdt: Simplify clk management Use devm_clk_get_enabled() instead of hand-writing it. This saves some LoC. Signed-off-by: Christophe JAILLET Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/f6094c55cacf9637d835cd49290d9e888faeb0f7.1682491863.git.christophe.jaillet@wanadoo.fr Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/dw_wdt.c | 44 ++++++++++----------------------------- 1 file changed, 11 insertions(+), 33 deletions(-) diff --git a/drivers/watchdog/dw_wdt.c b/drivers/watchdog/dw_wdt.c index a1354a59eb37..84dca3695f86 100644 --- a/drivers/watchdog/dw_wdt.c +++ b/drivers/watchdog/dw_wdt.c @@ -566,22 +566,16 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) * to the common timer/bus clocks configuration, in which the very * first found clock supply both timer and APB signals. */ - dw_wdt->clk = devm_clk_get(dev, "tclk"); + dw_wdt->clk = devm_clk_get_enabled(dev, "tclk"); if (IS_ERR(dw_wdt->clk)) { - dw_wdt->clk = devm_clk_get(dev, NULL); + dw_wdt->clk = devm_clk_get_enabled(dev, NULL); if (IS_ERR(dw_wdt->clk)) return PTR_ERR(dw_wdt->clk); } - ret = clk_prepare_enable(dw_wdt->clk); - if (ret) - return ret; - dw_wdt->rate = clk_get_rate(dw_wdt->clk); - if (dw_wdt->rate == 0) { - ret = -EINVAL; - goto out_disable_clk; - } + if (dw_wdt->rate == 0) + return -EINVAL; /* * Request APB clock if device is configured with async clocks mode. @@ -590,21 +584,13 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) * so the pclk phandle reference is left optional. If it couldn't be * found we consider the device configured in synchronous clocks mode. */ - dw_wdt->pclk = devm_clk_get_optional(dev, "pclk"); - if (IS_ERR(dw_wdt->pclk)) { - ret = PTR_ERR(dw_wdt->pclk); - goto out_disable_clk; - } - - ret = clk_prepare_enable(dw_wdt->pclk); - if (ret) - goto out_disable_clk; + dw_wdt->pclk = devm_clk_get_optional_enabled(dev, "pclk"); + if (IS_ERR(dw_wdt->pclk)) + return PTR_ERR(dw_wdt->pclk); dw_wdt->rst = devm_reset_control_get_optional_shared(&pdev->dev, NULL); - if (IS_ERR(dw_wdt->rst)) { - ret = PTR_ERR(dw_wdt->rst); - goto out_disable_pclk; - } + if (IS_ERR(dw_wdt->rst)) + return PTR_ERR(dw_wdt->rst); /* Enable normal reset without pre-timeout by default. */ dw_wdt_update_mode(dw_wdt, DW_WDT_RMOD_RESET); @@ -621,12 +607,12 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) IRQF_SHARED | IRQF_TRIGGER_RISING, pdev->name, dw_wdt); if (ret) - goto out_disable_pclk; + return ret; dw_wdt->wdd.info = &dw_wdt_pt_ident; } else { if (ret == -EPROBE_DEFER) - goto out_disable_pclk; + return ret; dw_wdt->wdd.info = &dw_wdt_ident; } @@ -675,12 +661,6 @@ static int dw_wdt_drv_probe(struct platform_device *pdev) out_assert_rst: reset_control_assert(dw_wdt->rst); - -out_disable_pclk: - clk_disable_unprepare(dw_wdt->pclk); - -out_disable_clk: - clk_disable_unprepare(dw_wdt->clk); return ret; } @@ -692,8 +672,6 @@ static void dw_wdt_drv_remove(struct platform_device *pdev) watchdog_unregister_device(&dw_wdt->wdd); reset_control_assert(dw_wdt->rst); - clk_disable_unprepare(dw_wdt->pclk); - clk_disable_unprepare(dw_wdt->clk); } #ifdef CONFIG_OF -- GitLab From 068550631fbe0b7fb41625cea6fb204fdc8cb224 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Wed, 18 Jan 2023 16:44:44 +0100 Subject: [PATCH 4310/5631] locking/arch: Rename all internal __xchg() names to __arch_xchg() Decrease the probability of this internal facility to be used by driver code. Signed-off-by: Andrzej Hajda Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Arnd Bergmann Reviewed-by: Andi Shyti Acked-by: Geert Uytterhoeven [m68k] Acked-by: Palmer Dabbelt [riscv] Link: https://lore.kernel.org/r/20230118154450.73842-1-andrzej.hajda@intel.com Cc: Linus Torvalds --- arch/alpha/include/asm/cmpxchg.h | 10 +++++----- arch/arc/include/asm/cmpxchg.h | 4 ++-- arch/arm/include/asm/cmpxchg.h | 7 ++++--- arch/arm64/include/asm/cmpxchg.h | 7 +++---- arch/hexagon/include/asm/cmpxchg.h | 10 +++++----- arch/ia64/include/asm/cmpxchg.h | 2 +- arch/ia64/include/uapi/asm/cmpxchg.h | 4 ++-- arch/loongarch/include/asm/cmpxchg.h | 4 ++-- arch/m68k/include/asm/cmpxchg.h | 6 +++--- arch/mips/include/asm/cmpxchg.h | 4 ++-- arch/openrisc/include/asm/cmpxchg.h | 10 +++++----- arch/parisc/include/asm/cmpxchg.h | 4 ++-- arch/powerpc/include/asm/cmpxchg.h | 4 ++-- arch/riscv/include/asm/atomic.h | 2 +- arch/riscv/include/asm/cmpxchg.h | 4 ++-- arch/s390/include/asm/cmpxchg.h | 8 ++++---- arch/sh/include/asm/cmpxchg.h | 4 ++-- arch/sparc/include/asm/cmpxchg_32.h | 4 ++-- arch/sparc/include/asm/cmpxchg_64.h | 6 +++--- arch/xtensa/include/asm/cmpxchg.h | 4 ++-- 20 files changed, 54 insertions(+), 54 deletions(-) diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h index 6e0a850aa9d3..91d4a4d9258c 100644 --- a/arch/alpha/include/asm/cmpxchg.h +++ b/arch/alpha/include/asm/cmpxchg.h @@ -6,15 +6,15 @@ * Atomic exchange routines. */ -#define ____xchg(type, args...) __xchg ## type ## _local(args) +#define ____xchg(type, args...) __arch_xchg ## type ## _local(args) #define ____cmpxchg(type, args...) __cmpxchg ## type ## _local(args) #include #define xchg_local(ptr, x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ - (__typeof__(*(ptr))) __xchg_local((ptr), (unsigned long)_x_, \ - sizeof(*(ptr))); \ + (__typeof__(*(ptr))) __arch_xchg_local((ptr), (unsigned long)_x_,\ + sizeof(*(ptr))); \ }) #define arch_cmpxchg_local(ptr, o, n) \ @@ -34,7 +34,7 @@ #undef ____xchg #undef ____cmpxchg -#define ____xchg(type, args...) __xchg ##type(args) +#define ____xchg(type, args...) __arch_xchg ##type(args) #define ____cmpxchg(type, args...) __cmpxchg ##type(args) #include @@ -48,7 +48,7 @@ __typeof__(*(ptr)) _x_ = (x); \ smp_mb(); \ __ret = (__typeof__(*(ptr))) \ - __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \ + __arch_xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \ smp_mb(); \ __ret; \ }) diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index c5b544a5fe81..e138fde067de 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -85,7 +85,7 @@ */ #ifdef CONFIG_ARC_HAS_LLSC -#define __xchg(ptr, val) \ +#define __arch_xchg(ptr, val) \ ({ \ __asm__ __volatile__( \ " ex %0, [%1] \n" /* set new value */ \ @@ -102,7 +102,7 @@ \ switch(sizeof(*(_p_))) { \ case 4: \ - _val_ = __xchg(_p_, _val_); \ + _val_ = __arch_xchg(_p_, _val_); \ break; \ default: \ BUILD_BUG(); \ diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h index 4dfe538dfc68..44667bdb4707 100644 --- a/arch/arm/include/asm/cmpxchg.h +++ b/arch/arm/include/asm/cmpxchg.h @@ -25,7 +25,8 @@ #define swp_is_buggy #endif -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size) +static inline unsigned long +__arch_xchg(unsigned long x, volatile void *ptr, int size) { extern void __bad_xchg(volatile void *, int); unsigned long ret; @@ -115,8 +116,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size } #define arch_xchg_relaxed(ptr, x) ({ \ - (__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), \ - sizeof(*(ptr))); \ + (__typeof__(*(ptr)))__arch_xchg((unsigned long)(x), (ptr), \ + sizeof(*(ptr))); \ }) #include diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 497acf134d99..c6bc5d8ec3ca 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -62,9 +62,8 @@ __XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE #define __XCHG_GEN(sfx) \ -static __always_inline unsigned long __xchg##sfx(unsigned long x, \ - volatile void *ptr, \ - int size) \ +static __always_inline unsigned long \ +__arch_xchg##sfx(unsigned long x, volatile void *ptr, int size) \ { \ switch (size) { \ case 1: \ @@ -93,7 +92,7 @@ __XCHG_GEN(_mb) ({ \ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ - __xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ __ret; \ }) diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h index cdb705e1496a..bf6cf5579cf4 100644 --- a/arch/hexagon/include/asm/cmpxchg.h +++ b/arch/hexagon/include/asm/cmpxchg.h @@ -9,7 +9,7 @@ #define _ASM_CMPXCHG_H /* - * __xchg - atomically exchange a register and a memory location + * __arch_xchg - atomically exchange a register and a memory location * @x: value to swap * @ptr: pointer to memory * @size: size of the value @@ -19,8 +19,8 @@ * Note: there was an errata for V2 about .new's and memw_locked. * */ -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, - int size) +static inline unsigned long +__arch_xchg(unsigned long x, volatile void *ptr, int size) { unsigned long retval; @@ -42,8 +42,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, * Atomically swap the contents of a register with memory. Should be atomic * between multiple CPU's and within interrupts on the same CPU. */ -#define arch_xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), \ - sizeof(*(ptr)))) +#define arch_xchg(ptr, v) ((__typeof__(*(ptr)))__arch_xchg((unsigned long)(v), (ptr), \ + sizeof(*(ptr)))) /* * see rt-mutex-design.txt; cmpxchg supposedly checks if *ptr == A and swaps. diff --git a/arch/ia64/include/asm/cmpxchg.h b/arch/ia64/include/asm/cmpxchg.h index 94ef84429843..8b2e644ef6a1 100644 --- a/arch/ia64/include/asm/cmpxchg.h +++ b/arch/ia64/include/asm/cmpxchg.h @@ -5,7 +5,7 @@ #include #define arch_xchg(ptr, x) \ -({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) +({(__typeof__(*(ptr))) __arch_xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) #define arch_cmpxchg(ptr, o, n) cmpxchg_acq((ptr), (o), (n)) #define arch_cmpxchg64(ptr, o, n) cmpxchg_acq((ptr), (o), (n)) diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index 259ae57570bf..85cba138311f 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -23,7 +23,7 @@ */ extern void ia64_xchg_called_with_bad_pointer(void); -#define __xchg(x, ptr, size) \ +#define __arch_xchg(x, ptr, size) \ ({ \ unsigned long __xchg_result; \ \ @@ -51,7 +51,7 @@ extern void ia64_xchg_called_with_bad_pointer(void); #ifndef __KERNEL__ #define xchg(ptr, x) \ -({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) +({(__typeof__(*(ptr))) __arch_xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) #endif /* diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h index ecfa6cf79806..979fde61bba8 100644 --- a/arch/loongarch/include/asm/cmpxchg.h +++ b/arch/loongarch/include/asm/cmpxchg.h @@ -62,7 +62,7 @@ static inline unsigned int __xchg_small(volatile void *ptr, unsigned int val, } static __always_inline unsigned long -__xchg(volatile void *ptr, unsigned long x, int size) +__arch_xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { case 1: @@ -87,7 +87,7 @@ __xchg(volatile void *ptr, unsigned long x, int size) __typeof__(*(ptr)) __res; \ \ __res = (__typeof__(*(ptr))) \ - __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ + __arch_xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ \ __res; \ }) diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h index 6cf464cdab06..d7f3de9c5d6f 100644 --- a/arch/m68k/include/asm/cmpxchg.h +++ b/arch/m68k/include/asm/cmpxchg.h @@ -9,7 +9,7 @@ extern unsigned long __invalid_xchg_size(unsigned long, volatile void *, int); #ifndef CONFIG_RMW_INSNS -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, int size) { unsigned long flags, tmp; @@ -40,7 +40,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz return x; } #else -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { case 1: @@ -75,7 +75,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz } #endif -#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));}) +#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));}) #include diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index 7ec9493b2861..feed343ad483 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -68,7 +68,7 @@ extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size); static __always_inline -unsigned long __xchg(volatile void *ptr, unsigned long x, int size) +unsigned long __arch_xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { case 1: @@ -102,7 +102,7 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size) smp_mb__before_llsc(); \ \ __res = (__typeof__(*(ptr))) \ - __xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ + __arch_xchg((ptr), (unsigned long)(x), sizeof(*(ptr))); \ \ smp_llsc_mb(); \ \ diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h index 79fd16162ccb..8ee151c072e4 100644 --- a/arch/openrisc/include/asm/cmpxchg.h +++ b/arch/openrisc/include/asm/cmpxchg.h @@ -147,8 +147,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, extern unsigned long __xchg_called_with_bad_pointer(void) __compiletime_error("Bad argument size for xchg"); -static inline unsigned long __xchg(volatile void *ptr, unsigned long with, - int size) +static inline unsigned long +__arch_xchg(volatile void *ptr, unsigned long with, int size) { switch (size) { case 1: @@ -163,9 +163,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long with, #define arch_xchg(ptr, with) \ ({ \ - (__typeof__(*(ptr))) __xchg((ptr), \ - (unsigned long)(with), \ - sizeof(*(ptr))); \ + (__typeof__(*(ptr))) __arch_xchg((ptr), \ + (unsigned long)(with), \ + sizeof(*(ptr))); \ }) #endif /* __ASM_OPENRISC_CMPXCHG_H */ diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index 5f274be10567..c1d776bb16b4 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -22,7 +22,7 @@ extern unsigned long __xchg64(unsigned long, volatile unsigned long *); /* optimizer better get rid of switch since size is a constant */ static inline unsigned long -__xchg(unsigned long x, volatile void *ptr, int size) +__arch_xchg(unsigned long x, volatile void *ptr, int size) { switch (size) { #ifdef CONFIG_64BIT @@ -49,7 +49,7 @@ __xchg(unsigned long x, volatile void *ptr, int size) __typeof__(*(ptr)) __ret; \ __typeof__(*(ptr)) _x_ = (x); \ __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)_x_, (ptr), sizeof(*(ptr))); \ + __arch_xchg((unsigned long)_x_, (ptr), sizeof(*(ptr))); \ __ret; \ }) diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index d0ea0571e79a..dbb50c06f0bf 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -229,7 +229,7 @@ __xchg_local(void *ptr, unsigned long x, unsigned int size) return __xchg_u64_local(ptr, x); #endif } - BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg"); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); return x; } @@ -248,7 +248,7 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size) return __xchg_u64_relaxed(ptr, x); #endif } - BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local"); + BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_relaxed"); return x; } #define arch_xchg_local(ptr,x) \ diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h index 0dfe9d857a76..bba472928b53 100644 --- a/arch/riscv/include/asm/atomic.h +++ b/arch/riscv/include/asm/atomic.h @@ -261,7 +261,7 @@ c_t arch_atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n) \ static __always_inline \ c_t arch_atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n) \ { \ - return __xchg(&(v->counter), n, size); \ + return __arch_xchg(&(v->counter), n, size); \ } \ static __always_inline \ c_t arch_atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v, \ diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index 12debce235e5..2f4726d3cfcc 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -114,7 +114,7 @@ _x_, sizeof(*(ptr))); \ }) -#define __xchg(ptr, new, size) \ +#define __arch_xchg(ptr, new, size) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ __typeof__(new) __new = (new); \ @@ -143,7 +143,7 @@ #define arch_xchg(ptr, x) \ ({ \ __typeof__(*(ptr)) _x_ = (x); \ - (__typeof__(*(ptr))) __xchg((ptr), _x_, sizeof(*(ptr))); \ + (__typeof__(*(ptr))) __arch_xchg((ptr), _x_, sizeof(*(ptr))); \ }) #define xchg32(ptr, x) \ diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h index 3f26416c2ad8..06e0e42f4eec 100644 --- a/arch/s390/include/asm/cmpxchg.h +++ b/arch/s390/include/asm/cmpxchg.h @@ -14,8 +14,8 @@ void __xchg_called_with_bad_pointer(void); -static __always_inline unsigned long __xchg(unsigned long x, - unsigned long address, int size) +static __always_inline unsigned long +__arch_xchg(unsigned long x, unsigned long address, int size) { unsigned long old; int shift; @@ -77,8 +77,8 @@ static __always_inline unsigned long __xchg(unsigned long x, __typeof__(*(ptr)) __ret; \ \ __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (unsigned long)(ptr), \ - sizeof(*(ptr))); \ + __arch_xchg((unsigned long)(x), (unsigned long)(ptr), \ + sizeof(*(ptr))); \ __ret; \ }) diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h index 0ed9b3f4a577..288f6f38d98f 100644 --- a/arch/sh/include/asm/cmpxchg.h +++ b/arch/sh/include/asm/cmpxchg.h @@ -22,7 +22,7 @@ extern void __xchg_called_with_bad_pointer(void); -#define __xchg(ptr, x, size) \ +#define __arch_xchg(ptr, x, size) \ ({ \ unsigned long __xchg__res; \ volatile void *__xchg_ptr = (ptr); \ @@ -46,7 +46,7 @@ extern void __xchg_called_with_bad_pointer(void); }) #define arch_xchg(ptr,x) \ - ((__typeof__(*(ptr)))__xchg((ptr),(unsigned long)(x), sizeof(*(ptr)))) + ((__typeof__(*(ptr)))__arch_xchg((ptr),(unsigned long)(x), sizeof(*(ptr)))) /* This function doesn't exist, so you'll get a linker error * if something tries to do an invalid cmpxchg(). */ diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index 27a57a3a7597..7a1339533d1d 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -15,7 +15,7 @@ unsigned long __xchg_u32(volatile u32 *m, u32 new); void __xchg_called_with_bad_pointer(void); -static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size) +static inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 4: @@ -25,7 +25,7 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int return x; } -#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));}) +#define arch_xchg(ptr,x) ({(__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr)));}) /* Emulate cmpxchg() the same way we emulate atomics, * by hashing the object address and indexing into an array diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index 12d00a42c0a3..66cd61dde9ec 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -55,7 +55,7 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long #define arch_xchg(ptr,x) \ ({ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __arch_xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ __ret; \ }) @@ -87,8 +87,8 @@ xchg16(__volatile__ unsigned short *m, unsigned short val) return (load32 & mask) >> bit_shift; } -static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, - int size) +static inline unsigned long +__arch_xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 2: diff --git a/arch/xtensa/include/asm/cmpxchg.h b/arch/xtensa/include/asm/cmpxchg.h index eb87810357ad..675a11ea8de7 100644 --- a/arch/xtensa/include/asm/cmpxchg.h +++ b/arch/xtensa/include/asm/cmpxchg.h @@ -170,7 +170,7 @@ static inline unsigned long xchg_u32(volatile int * m, unsigned long val) } #define arch_xchg(ptr,x) \ - ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) + ((__typeof__(*(ptr)))__arch_xchg((unsigned long)(x),(ptr),sizeof(*(ptr)))) static inline u32 xchg_small(volatile void *ptr, u32 x, int size) { @@ -203,7 +203,7 @@ static inline u32 xchg_small(volatile void *ptr, u32 x, int size) extern void __xchg_called_with_bad_pointer(void); static __inline__ unsigned long -__xchg(unsigned long x, volatile void * ptr, int size) +__arch_xchg(unsigned long x, volatile void * ptr, int size) { switch (size) { case 1: -- GitLab From 286deb7ec03d941664ac3ffaff58814b454adf65 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 21 Mar 2023 17:11:40 +0100 Subject: [PATCH 4311/5631] locking/rwbase: Mitigate indefinite writer starvation On PREEMPT_RT, rw_semaphore and rwlock_t locks are unfair to writers. Readers can indefinitely acquire the lock unless the writer fully acquired the lock, which might never happen if there is always a reader in the critical section owning the lock. Mel Gorman reported that since LTP-20220121 the dio_truncate test case went from having 1 reader to having 16 readers and that number of readers is sufficient to prevent the down_write ever succeeding while readers exist. Eventually the test is killed after 30 minutes as a failure. Mel proposed a timeout to limit how long a writer can be blocked until the reader is forced into the slowpath. Thomas argued that there is no added value by providing this timeout. From a PREEMPT_RT point of view, there are no critical rw_semaphore or rwlock_t locks left where the reader must be preferred. Mitigate indefinite writer starvation by forcing the READER into the slowpath once the WRITER attempts to acquire the lock. Reported-by: Mel Gorman Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Acked-by: Mel Gorman Link: https://lore.kernel.org/877cwbq4cq.ffs@tglx Link: https://lore.kernel.org/r/20230321161140.HMcQEhHb@linutronix.de Cc: Linus Torvalds --- kernel/locking/rwbase_rt.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/kernel/locking/rwbase_rt.c b/kernel/locking/rwbase_rt.c index c201aadb9301..25ec0239477c 100644 --- a/kernel/locking/rwbase_rt.c +++ b/kernel/locking/rwbase_rt.c @@ -72,15 +72,6 @@ static int __sched __rwbase_read_lock(struct rwbase_rt *rwb, int ret; raw_spin_lock_irq(&rtm->wait_lock); - /* - * Allow readers, as long as the writer has not completely - * acquired the semaphore for write. - */ - if (atomic_read(&rwb->readers) != WRITER_BIAS) { - atomic_inc(&rwb->readers); - raw_spin_unlock_irq(&rtm->wait_lock); - return 0; - } /* * Call into the slow lock path with the rtmutex->wait_lock -- GitLab From e6ce9d741163af0b846637ce6550ae8a671b1588 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 5 Apr 2023 16:17:06 +0200 Subject: [PATCH 4312/5631] locking/atomic: Add generic try_cmpxchg{,64}_local() support Add generic support for try_cmpxchg{,64}_local() and their falbacks. These provides the generic try_cmpxchg_local family of functions from the arch_ prefixed version, also adding explicit instrumentation. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230405141710.3551-2-ubizjak@gmail.com Cc: Linus Torvalds --- include/linux/atomic/atomic-arch-fallback.h | 24 ++++++++++++++++++++- include/linux/atomic/atomic-instrumented.h | 20 ++++++++++++++++- scripts/atomic/gen-atomic-fallback.sh | 4 ++++ scripts/atomic/gen-atomic-instrumented.sh | 2 +- 4 files changed, 47 insertions(+), 3 deletions(-) diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 4226379a232d..a6e4437c5f36 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -217,6 +217,28 @@ #endif /* arch_try_cmpxchg64_relaxed */ +#ifndef arch_try_cmpxchg_local +#define arch_try_cmpxchg_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg_local */ + +#ifndef arch_try_cmpxchg64_local +#define arch_try_cmpxchg64_local(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_local((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_local */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2646,4 +2668,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 00071fffa021cec66f6290d706d69c91df87bade +// ad2e2b4d168dbc60a73922616047a9bfa446af36 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 0496816738ca..245ba661c493 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2132,6 +2132,24 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) +#define try_cmpxchg_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_local(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_double(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2149,4 +2167,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 1b485de9cbaa4900de59e14ee2084357eaeb1c3a +// 97fe4d79aa058d2164df824632cbc4f716d2a407 diff --git a/scripts/atomic/gen-atomic-fallback.sh b/scripts/atomic/gen-atomic-fallback.sh index 3a07695e3c89..6e853f0dad8d 100755 --- a/scripts/atomic/gen-atomic-fallback.sh +++ b/scripts/atomic/gen-atomic-fallback.sh @@ -225,6 +225,10 @@ for cmpxchg in "cmpxchg" "cmpxchg64"; do gen_try_cmpxchg_fallbacks "${cmpxchg}" done +for cmpxchg in "cmpxchg_local" "cmpxchg64_local"; do + gen_try_cmpxchg_fallback "${cmpxchg}" "" +done + grep '^[a-z]' "$1" | while read name meta args; do gen_proto "${meta}" "${name}" "atomic" "int" ${args} done diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh index 77c06526a574..c8165e9431bf 100755 --- a/scripts/atomic/gen-atomic-instrumented.sh +++ b/scripts/atomic/gen-atomic-instrumented.sh @@ -173,7 +173,7 @@ for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg" "try_cmpxchg64"; do done done -for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg"; do +for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg" "try_cmpxchg_local" "try_cmpxchg64_local" ; do gen_xchg "${xchg}" "" "" printf "\n" done -- GitLab From 8fc4fddaf9a184eea7da21290236a1764e608a01 Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 5 Apr 2023 16:17:07 +0200 Subject: [PATCH 4313/5631] locking/generic: Wire up local{,64}_try_cmpxchg() Implement generic support for local{,64}_try_cmpxchg(). Redirect to the atomic_ family of functions when the target does not provide its own local.h definitions. For 64-bit targets, implement local64_try_cmpxchg and local64_cmpxchg using typed C wrappers that call local_ family of functions and provide additional checking of their input arguments. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20230405141710.3551-3-ubizjak@gmail.com Cc: Linus Torvalds --- include/asm-generic/local.h | 1 + include/asm-generic/local64.h | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/include/asm-generic/local.h b/include/asm-generic/local.h index fca7f1d84818..7f97018df66f 100644 --- a/include/asm-generic/local.h +++ b/include/asm-generic/local.h @@ -42,6 +42,7 @@ typedef struct #define local_inc_return(l) atomic_long_inc_return(&(l)->a) #define local_cmpxchg(l, o, n) atomic_long_cmpxchg((&(l)->a), (o), (n)) +#define local_try_cmpxchg(l, po, n) atomic_long_try_cmpxchg((&(l)->a), (po), (n)) #define local_xchg(l, n) atomic_long_xchg((&(l)->a), (n)) #define local_add_unless(l, _a, u) atomic_long_add_unless((&(l)->a), (_a), (u)) #define local_inc_not_zero(l) atomic_long_inc_not_zero(&(l)->a) diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h index 765be0b7d883..14963a7a6253 100644 --- a/include/asm-generic/local64.h +++ b/include/asm-generic/local64.h @@ -42,7 +42,16 @@ typedef struct { #define local64_sub_return(i, l) local_sub_return((i), (&(l)->a)) #define local64_inc_return(l) local_inc_return(&(l)->a) -#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n)) +static inline s64 local64_cmpxchg(local64_t *l, s64 old, s64 new) +{ + return local_cmpxchg(&l->a, old, new); +} + +static inline bool local64_try_cmpxchg(local64_t *l, s64 *old, s64 new) +{ + return local_try_cmpxchg(&l->a, (long *)old, new); +} + #define local64_xchg(l, n) local_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a) @@ -81,6 +90,7 @@ typedef struct { #define local64_inc_return(l) atomic64_inc_return(&(l)->a) #define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n)) +#define local64_try_cmpxchg(l, po, n) atomic64_try_cmpxchg((&(l)->a), (po), (n)) #define local64_xchg(l, n) atomic64_xchg((&(l)->a), (n)) #define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u)) #define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a) -- GitLab From d994f2c8e2410ebcb928df67baa6f04e29bc9d3e Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 5 Apr 2023 16:17:08 +0200 Subject: [PATCH 4314/5631] locking/arch: Wire up local_try_cmpxchg() Implement target specific support for local_try_cmpxchg() and local_cmpxchg() using typed C wrappers that call their _local counterpart and provide additional checking of their input arguments. Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230405141710.3551-4-ubizjak@gmail.com Cc: Linus Torvalds --- arch/alpha/include/asm/local.h | 12 ++++++++++-- arch/loongarch/include/asm/local.h | 13 +++++++++++-- arch/mips/include/asm/local.h | 13 +++++++++++-- arch/powerpc/include/asm/local.h | 11 +++++++++++ arch/x86/include/asm/local.h | 13 +++++++++++-- 5 files changed, 54 insertions(+), 8 deletions(-) diff --git a/arch/alpha/include/asm/local.h b/arch/alpha/include/asm/local.h index fab26a1c93d5..0fcaad642cc3 100644 --- a/arch/alpha/include/asm/local.h +++ b/arch/alpha/include/asm/local.h @@ -52,8 +52,16 @@ static __inline__ long local_sub_return(long i, local_t * l) return result; } -#define local_cmpxchg(l, o, n) \ - (cmpxchg_local(&((l)->a.counter), (o), (n))) +static __inline__ long local_cmpxchg(local_t *l, long old, long new) +{ + return cmpxchg_local(&l->a.counter, old, new); +} + +static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new) +{ + return try_cmpxchg_local(&l->a.counter, (s64 *)old, new); +} + #define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n))) /** diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h index 65fbbae9fc4d..83e995b30e47 100644 --- a/arch/loongarch/include/asm/local.h +++ b/arch/loongarch/include/asm/local.h @@ -56,8 +56,17 @@ static inline long local_sub_return(long i, local_t *l) return result; } -#define local_cmpxchg(l, o, n) \ - ((long)cmpxchg_local(&((l)->a.counter), (o), (n))) +static inline long local_cmpxchg(local_t *l, long old, long new) +{ + return cmpxchg_local(&l->a.counter, old, new); +} + +static inline bool local_try_cmpxchg(local_t *l, long *old, long new) +{ + typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; + return try_cmpxchg_local(&l->a.counter, __old, new); +} + #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n))) /** diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h index 08366b1fd273..5daf6fe8e3e9 100644 --- a/arch/mips/include/asm/local.h +++ b/arch/mips/include/asm/local.h @@ -94,8 +94,17 @@ static __inline__ long local_sub_return(long i, local_t * l) return result; } -#define local_cmpxchg(l, o, n) \ - ((long)cmpxchg_local(&((l)->a.counter), (o), (n))) +static __inline__ long local_cmpxchg(local_t *l, long old, long new) +{ + return cmpxchg_local(&l->a.counter, old, new); +} + +static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new) +{ + typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; + return try_cmpxchg_local(&l->a.counter, __old, new); +} + #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n))) /** diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h index bc4bd19b7fc2..45492fb5bf22 100644 --- a/arch/powerpc/include/asm/local.h +++ b/arch/powerpc/include/asm/local.h @@ -90,6 +90,17 @@ static __inline__ long local_cmpxchg(local_t *l, long o, long n) return t; } +static __inline__ bool local_try_cmpxchg(local_t *l, long *po, long n) +{ + long o = *po, r; + + r = local_cmpxchg(l, o, n); + if (unlikely(r != o)) + *po = r; + + return likely(r == o); +} + static __inline__ long local_xchg(local_t *l, long n) { long t; diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 349a47acaa4a..56d4ef604b91 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -120,8 +120,17 @@ static inline long local_sub_return(long i, local_t *l) #define local_inc_return(l) (local_add_return(1, l)) #define local_dec_return(l) (local_sub_return(1, l)) -#define local_cmpxchg(l, o, n) \ - (cmpxchg_local(&((l)->a.counter), (o), (n))) +static inline long local_cmpxchg(local_t *l, long old, long new) +{ + return cmpxchg_local(&l->a.counter, old, new); +} + +static inline bool local_try_cmpxchg(local_t *l, long *old, long new) +{ + typeof(l->a.counter) *__old = (typeof(l->a.counter) *) old; + return try_cmpxchg_local(&l->a.counter, __old, new); +} + /* Always has a lock prefix */ #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) -- GitLab From 5cd4c268412f802e71b7722c3ec4638b0fe04acd Mon Sep 17 00:00:00 2001 From: Uros Bizjak Date: Wed, 5 Apr 2023 16:17:09 +0200 Subject: [PATCH 4315/5631] locking/x86: Define arch_try_cmpxchg_local() Define target specific arch_try_cmpxchg_local(). This definition overrides the generic arch_try_cmpxchg_local() fallback definition and enables target-specific implementation of try_cmpxchg_local(). Signed-off-by: Uros Bizjak Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20230405141710.3551-5-ubizjak@gmail.com Cc: Linus Torvalds --- arch/x86/include/asm/cmpxchg.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 94fbe6ae7431..540573f515b7 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -221,9 +221,15 @@ extern void __add_wrong_size(void) #define __try_cmpxchg(ptr, pold, new, size) \ __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) +#define __try_cmpxchg_local(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), "") + #define arch_try_cmpxchg(ptr, pold, new) \ __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) +#define arch_try_cmpxchg_local(ptr, pold, new) \ + __try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr))) + /* * xadd() adds "inc" to "*ptr" and atomically returns the previous * value of "*ptr". -- GitLab From ec570320b09f76d52819e60abdccf372658216b6 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Thu, 13 Apr 2023 17:06:44 +0100 Subject: [PATCH 4316/5631] locking/atomic: Correct (cmp)xchg() instrumentation All xchg() and cmpxchg() ops are atomic RMWs, but currently we instrument these with instrument_atomic_write() rather than instrument_atomic_read_write(), missing the read aspect. Similarly, all try_cmpxchg() ops are non-atomic RMWs on *oldp, but we instrument these accesses with instrument_atomic_write() rather than instrument_read_write(), missing the read aspect and erroneously marking these as atomic. Fix the instrumentation for both points. Signed-off-by: Mark Rutland Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lkml.kernel.org/r/20230413160644.490976-1-mark.rutland@arm.com Cc: Linus Torvalds --- include/linux/atomic/atomic-instrumented.h | 76 +++++++++++----------- scripts/atomic/gen-atomic-instrumented.sh | 6 +- 2 files changed, 41 insertions(+), 41 deletions(-) diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 245ba661c493..03a232a1fa57 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1948,14 +1948,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg(__ai_ptr, __VA_ARGS__); \ }) #define xchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1963,14 +1963,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_release(__ai_ptr, __VA_ARGS__); \ }) #define xchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -1978,14 +1978,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -1993,14 +1993,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -2008,14 +2008,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_acquire(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \ }) @@ -2023,14 +2023,14 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_relaxed(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \ }) @@ -2039,8 +2039,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2048,8 +2048,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2058,8 +2058,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2067,8 +2067,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2077,8 +2077,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2086,8 +2086,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2096,8 +2096,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ kcsan_release(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2105,22 +2105,22 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \ }) #define cmpxchg64_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \ }) @@ -2128,7 +2128,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -2136,8 +2136,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2145,8 +2145,8 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ - instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ - instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) @@ -2154,7 +2154,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ kcsan_mb(); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) @@ -2162,9 +2162,9 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_double_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ - instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ + instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \ }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 97fe4d79aa058d2164df824632cbc4f716d2a407 +// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh index c8165e9431bf..d9ffd74f73ca 100755 --- a/scripts/atomic/gen-atomic-instrumented.sh +++ b/scripts/atomic/gen-atomic-instrumented.sh @@ -104,8 +104,8 @@ cat < Date: Thu, 30 Mar 2023 14:43:18 +0800 Subject: [PATCH 4317/5631] RISC-V: Change suspend_save_csrs and suspend_restore_csrs to public function Currently suspend_save_csrs() and suspend_restore_csrs() functions are statically defined in the suspend.c. Change the function's attribute to public so that the functions can be used by hibernation as well. Signed-off-by: Sia Jee Heng Reviewed-by: Ley Foon Tan Reviewed-by: Mason Huo Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230330064321.1008373-2-jeeheng.sia@starfivetech.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/suspend.h | 3 +++ arch/riscv/kernel/suspend.c | 4 ++-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 8be391c2aecb..67e047445662 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -33,4 +33,7 @@ int cpu_suspend(unsigned long arg, /* Low-level CPU resume entry function */ int __cpu_resume_enter(unsigned long hartid, unsigned long context); +/* Used to save and restore the CSRs */ +void suspend_save_csrs(struct suspend_context *context); +void suspend_restore_csrs(struct suspend_context *context); #endif diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 9ba24fb8cc93..3c89b8ec69c4 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -8,7 +8,7 @@ #include #include -static void suspend_save_csrs(struct suspend_context *context) +void suspend_save_csrs(struct suspend_context *context) { context->scratch = csr_read(CSR_SCRATCH); context->tvec = csr_read(CSR_TVEC); @@ -29,7 +29,7 @@ static void suspend_save_csrs(struct suspend_context *context) #endif } -static void suspend_restore_csrs(struct suspend_context *context) +void suspend_restore_csrs(struct suspend_context *context) { csr_write(CSR_SCRATCH, context->scratch); csr_write(CSR_TVEC, context->tvec); -- GitLab From fcb89863d1b798565db6bdaf8f97f65823c2fd1b Mon Sep 17 00:00:00 2001 From: Sia Jee Heng Date: Thu, 30 Mar 2023 14:43:19 +0800 Subject: [PATCH 4318/5631] RISC-V: Factor out common code of __cpu_resume_enter() The cpu_resume() function is very similar for the suspend to disk and suspend to ram cases. Factor out the common code into suspend_restore_csrs macro and suspend_restore_regs macro. Signed-off-by: Sia Jee Heng Reviewed-by: Andrew Jones Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230330064321.1008373-3-jeeheng.sia@starfivetech.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/assembler.h | 62 ++++++++++++++++++++++++++++++ arch/riscv/kernel/suspend_entry.S | 34 ++-------------- 2 files changed, 65 insertions(+), 31 deletions(-) create mode 100644 arch/riscv/include/asm/assembler.h diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h new file mode 100644 index 000000000000..ba59d38f8937 --- /dev/null +++ b/arch/riscv/include/asm/assembler.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#ifndef __ASSEMBLY__ +#error "Only include this from assembly code" +#endif + +#ifndef __ASM_ASSEMBLER_H +#define __ASM_ASSEMBLER_H + +#include +#include +#include + +/* + * suspend_restore_csrs - restore CSRs + */ + .macro suspend_restore_csrs + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrw CSR_EPC, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrw CSR_STATUS, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrw CSR_TVAL, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + csrw CSR_CAUSE, t0 + .endm + +/* + * suspend_restore_regs - Restore registers (except A0 and T0-T6) + */ + .macro suspend_restore_regs + REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + .endm + +#endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index aafcca58c19d..12b52afe09a4 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -83,39 +84,10 @@ ENTRY(__cpu_resume_enter) add a0, a1, zero /* Restore CSRs */ - REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) - csrw CSR_EPC, t0 - REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) - csrw CSR_STATUS, t0 - REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) - csrw CSR_TVAL, t0 - REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) - csrw CSR_CAUSE, t0 + suspend_restore_csrs /* Restore registers (except A0 and T0-T6) */ - REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) - REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) - REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) - REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) - REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) - REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) - REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) - REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) - REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) - REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) - REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) - REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) - REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) - REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) - REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) - REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) - REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) - REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) - REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) - REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) - REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) - REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) - REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + suspend_restore_regs /* Return zero value */ add a0, zero, zero -- GitLab From a15c90b67a662c75f469822a7f95c7aaa049e28f Mon Sep 17 00:00:00 2001 From: Sia Jee Heng Date: Thu, 30 Mar 2023 14:43:20 +0800 Subject: [PATCH 4319/5631] RISC-V: mm: Enable huge page support to kernel_page_present() function Currently kernel_page_present() function doesn't support huge page detection causes the function to mistakenly return false to the hibernation core. Add huge page detection to the function to solve the problem. Fixes: 9e953cda5cdf ("riscv: Introduce huge page support for 32/64bit kernel") Signed-off-by: Sia Jee Heng Reviewed-by: Ley Foon Tan Reviewed-by: Mason Huo Reviewed-by: Andrew Jones Reviewed-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230330064321.1008373-4-jeeheng.sia@starfivetech.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/pageattr.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index 86c56616e5de..ea3d61de065b 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -217,18 +217,26 @@ bool kernel_page_present(struct page *page) pgd = pgd_offset_k(addr); if (!pgd_present(*pgd)) return false; + if (pgd_leaf(*pgd)) + return true; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return false; + if (p4d_leaf(*p4d)) + return true; pud = pud_offset(p4d, addr); if (!pud_present(*pud)) return false; + if (pud_leaf(*pud)) + return true; pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) return false; + if (pmd_leaf(*pmd)) + return true; pte = pte_offset_kernel(pmd, addr); return pte_present(*pte); -- GitLab From c0317210012e3b985779ddd92a7c5db8424e1e97 Mon Sep 17 00:00:00 2001 From: Sia Jee Heng Date: Thu, 30 Mar 2023 14:43:21 +0800 Subject: [PATCH 4320/5631] RISC-V: Add arch functions to support hibernation/suspend-to-disk Low level Arch functions were created to support hibernation. swsusp_arch_suspend() relies code from __cpu_suspend_enter() to write cpu state onto the stack, then calling swsusp_save() to save the memory image. Arch specific hibernation header is implemented and is utilized by the arch_hibernation_header_restore() and arch_hibernation_header_save() functions. The arch specific hibernation header consists of satp, hartid, and the cpu_resume address. The kernel built version is also need to be saved into the hibernation image header to making sure only the same kernel is restore when resume. swsusp_arch_resume() creates a temporary page table that covering only the linear map. It copies the restore code to a 'safe' page, then start to restore the memory image. Once completed, it restores the original kernel's page table. It then calls into __hibernate_cpu_resume() to restore the CPU context. Finally, it follows the normal hibernation path back to the hibernation core. To enable hibernation/suspend to disk into RISCV, the below config need to be enabled: - CONFIG_HIBERNATION - CONFIG_ARCH_HIBERNATION_HEADER - CONFIG_ARCH_HIBERNATION_POSSIBLE Signed-off-by: Sia Jee Heng Reviewed-by: Ley Foon Tan Reviewed-by: Mason Huo Reviewed-by: Conor Dooley Reviewed-by: Andrew Jones Link: https://lore.kernel.org/r/20230330064321.1008373-5-jeeheng.sia@starfivetech.com Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 8 +- arch/riscv/include/asm/assembler.h | 20 ++ arch/riscv/include/asm/suspend.h | 19 ++ arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/asm-offsets.c | 5 + arch/riscv/kernel/hibernate-asm.S | 77 ++++++ arch/riscv/kernel/hibernate.c | 427 +++++++++++++++++++++++++++++ 7 files changed, 556 insertions(+), 1 deletion(-) create mode 100644 arch/riscv/kernel/hibernate-asm.S create mode 100644 arch/riscv/kernel/hibernate.c diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index c5e42cc37604..0950049f5a28 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -54,7 +54,7 @@ config RISCV select CLINT_TIMER if !MMU select CLONE_BACKWARDS select COMMON_CLK - select CPU_PM if CPU_IDLE + select CPU_PM if CPU_IDLE || HIBERNATION select EDAC_SUPPORT select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT @@ -707,6 +707,12 @@ menu "Power management options" source "kernel/power/Kconfig" +config ARCH_HIBERNATION_POSSIBLE + def_bool y + +config ARCH_HIBERNATION_HEADER + def_bool HIBERNATION + endmenu # "Power management options" menu "CPU Power Management" diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h index ba59d38f8937..44b1457d3e95 100644 --- a/arch/riscv/include/asm/assembler.h +++ b/arch/riscv/include/asm/assembler.h @@ -59,4 +59,24 @@ REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) .endm +/* + * copy_page - copy 1 page (4KB) of data from source to destination + * @a0 - destination + * @a1 - source + */ + .macro copy_page a0, a1 + lui a2, 0x1 + add a2, a2, a0 +1 : + REG_L t0, 0(a1) + REG_L t1, SZREG(a1) + + REG_S t0, 0(a0) + REG_S t1, SZREG(a0) + + addi a0, a0, 2 * SZREG + addi a1, a1, 2 * SZREG + bne a2, a0, 1b + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 67e047445662..02f87867389a 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -21,6 +21,11 @@ struct suspend_context { #endif }; +/* + * Used by hibernation core and cleared during resume sequence + */ +extern int in_suspend; + /* Low-level CPU suspend entry function */ int __cpu_suspend_enter(struct suspend_context *context); @@ -36,4 +41,18 @@ int __cpu_resume_enter(unsigned long hartid, unsigned long context); /* Used to save and restore the CSRs */ void suspend_save_csrs(struct suspend_context *context); void suspend_restore_csrs(struct suspend_context *context); + +/* Low-level API to support hibernation */ +int swsusp_arch_suspend(void); +int swsusp_arch_resume(void); +int arch_hibernation_header_save(void *addr, unsigned int max_size); +int arch_hibernation_header_restore(void *addr); +int __hibernate_cpu_resume(void); + +/* Used to resume on the CPU we hibernated on */ +int hibernate_resume_nonboot_cpu_disable(void); + +asmlinkage void hibernate_restore_image(unsigned long resume_satp, unsigned long satp_temp, + unsigned long cpu_resume); +asmlinkage int hibernate_core_restore_code(void); #endif diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 4cf303a779ab..daab341d55e4 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -64,6 +64,7 @@ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index df9444397908..d6a75aac1d27 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -116,6 +117,10 @@ void asm_offsets(void) OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs); + OFFSET(HIBERN_PBE_ADDR, pbe, address); + OFFSET(HIBERN_PBE_ORIG, pbe, orig_address); + OFFSET(HIBERN_PBE_NEXT, pbe, next); + OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero); OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra); OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp); diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S new file mode 100644 index 000000000000..effaf5ca5da0 --- /dev/null +++ b/arch/riscv/kernel/hibernate-asm.S @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Hibernation low level support for RISCV. + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include + +#include + +/* + * int __hibernate_cpu_resume(void) + * Switch back to the hibernated image's page table prior to restoring the CPU + * context. + * + * Always returns 0 + */ +ENTRY(__hibernate_cpu_resume) + /* switch to hibernated image's page table. */ + csrw CSR_SATP, s0 + sfence.vma + + REG_L a0, hibernate_cpu_context + + suspend_restore_csrs + suspend_restore_regs + + /* Return zero value. */ + mv a0, zero + + ret +END(__hibernate_cpu_resume) + +/* + * Prepare to restore the image. + * a0: satp of saved page tables. + * a1: satp of temporary page tables. + * a2: cpu_resume. + */ +ENTRY(hibernate_restore_image) + mv s0, a0 + mv s1, a1 + mv s2, a2 + REG_L s4, restore_pblist + REG_L a1, relocated_restore_code + + jalr a1 +END(hibernate_restore_image) + +/* + * The below code will be executed from a 'safe' page. + * It first switches to the temporary page table, then starts to copy the pages + * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume() + * to restore the CPU context. + */ +ENTRY(hibernate_core_restore_code) + /* switch to temp page table. */ + csrw satp, s1 + sfence.vma +.Lcopy: + /* The below code will restore the hibernated image. */ + REG_L a1, HIBERN_PBE_ADDR(s4) + REG_L a0, HIBERN_PBE_ORIG(s4) + + copy_page a0, a1 + + REG_L s4, HIBERN_PBE_NEXT(s4) + bnez s4, .Lcopy + + jalr s2 +END(hibernate_core_restore_code) diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c new file mode 100644 index 000000000000..264b2dcdd67e --- /dev/null +++ b/arch/riscv/kernel/hibernate.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hibernation support for RISCV + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* The logical cpu number we should resume on, initialised to a non-cpu number. */ +static int sleep_cpu = -EINVAL; + +/* Pointer to the temporary resume page table. */ +static pgd_t *resume_pg_dir; + +/* CPU context to be saved. */ +struct suspend_context *hibernate_cpu_context; +EXPORT_SYMBOL_GPL(hibernate_cpu_context); + +unsigned long relocated_restore_code; +EXPORT_SYMBOL_GPL(relocated_restore_code); + +/** + * struct arch_hibernate_hdr_invariants - container to store kernel build version. + * @uts_version: to save the build number and date so that we do not resume with + * a different kernel. + */ +struct arch_hibernate_hdr_invariants { + char uts_version[__NEW_UTS_LEN + 1]; +}; + +/** + * struct arch_hibernate_hdr - helper parameters that help us to restore the image. + * @invariants: container to store kernel build version. + * @hartid: to make sure same boot_cpu executes the hibernate/restore code. + * @saved_satp: original page table used by the hibernated image. + * @restore_cpu_addr: the kernel's image address to restore the CPU context. + */ +static struct arch_hibernate_hdr { + struct arch_hibernate_hdr_invariants invariants; + unsigned long hartid; + unsigned long saved_satp; + unsigned long restore_cpu_addr; +} resume_hdr; + +static void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i) +{ + memset(i, 0, sizeof(*i)); + memcpy(i->uts_version, init_utsname()->version, sizeof(i->uts_version)); +} + +/* + * Check if the given pfn is in the 'nosave' section. + */ +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1); + + return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)); +} + +void notrace save_processor_state(void) +{ + WARN_ON(num_online_cpus() != 1); +} + +void notrace restore_processor_state(void) +{ +} + +/* + * Helper parameters need to be saved to the hibernation image header. + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct arch_hibernate_hdr *hdr = addr; + + if (max_size < sizeof(*hdr)) + return -EOVERFLOW; + + arch_hdr_invariants(&hdr->invariants); + + hdr->hartid = cpuid_to_hartid_map(sleep_cpu); + hdr->saved_satp = csr_read(CSR_SATP); + hdr->restore_cpu_addr = (unsigned long)__hibernate_cpu_resume; + + return 0; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_save); + +/* + * Retrieve the helper parameters from the hibernation image header. + */ +int arch_hibernation_header_restore(void *addr) +{ + struct arch_hibernate_hdr_invariants invariants; + struct arch_hibernate_hdr *hdr = addr; + int ret = 0; + + arch_hdr_invariants(&invariants); + + if (memcmp(&hdr->invariants, &invariants, sizeof(invariants))) { + pr_crit("Hibernate image not generated by this kernel!\n"); + return -EINVAL; + } + + sleep_cpu = riscv_hartid_to_cpuid(hdr->hartid); + if (sleep_cpu < 0) { + pr_crit("Hibernated on a CPU not known to this kernel!\n"); + sleep_cpu = -EINVAL; + return -EINVAL; + } + +#ifdef CONFIG_SMP + ret = bringup_hibernate_cpu(sleep_cpu); + if (ret) { + sleep_cpu = -EINVAL; + return ret; + } +#endif + resume_hdr = *hdr; + + return ret; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_restore); + +int swsusp_arch_suspend(void) +{ + int ret = 0; + + if (__cpu_suspend_enter(hibernate_cpu_context)) { + sleep_cpu = smp_processor_id(); + suspend_save_csrs(hibernate_cpu_context); + ret = swsusp_save(); + } else { + suspend_restore_csrs(hibernate_cpu_context); + flush_tlb_all(); + flush_icache_all(); + + /* + * Tell the hibernation core that we've just restored the memory. + */ + in_suspend = 0; + sleep_cpu = -EINVAL; + } + + return ret; +} + +static int temp_pgtable_map_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + pte_t *src_ptep; + pte_t *dst_ptep; + + if (pmd_none(READ_ONCE(*dst_pmdp))) { + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) + return -ENOMEM; + + pmd_populate_kernel(NULL, dst_pmdp, dst_ptep); + } + + dst_ptep = pte_offset_kernel(dst_pmdp, start); + src_ptep = pte_offset_kernel(src_pmdp, start); + + do { + pte_t pte = READ_ONCE(*src_ptep); + + if (pte_present(pte)) + set_pte(dst_ptep, __pte(pte_val(pte) | pgprot_val(prot))); + } while (dst_ptep++, src_ptep++, start += PAGE_SIZE, start < end); + + return 0; +} + +static int temp_pgtable_map_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; + + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) + return -ENOMEM; + + pud_populate(NULL, dst_pudp, dst_pmdp); + } + + dst_pmdp = pmd_offset(dst_pudp, start); + src_pmdp = pmd_offset(src_pudp, start); + + do { + pmd_t pmd = READ_ONCE(*src_pmdp); + + next = pmd_addr_end(start, end); + + if (pmd_none(pmd)) + continue; + + if (pmd_leaf(pmd)) { + set_pmd(dst_pmdp, __pmd(pmd_val(pmd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pte(dst_pmdp, src_pmdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pmdp++, src_pmdp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pud_t *dst_pudp; + pud_t *src_pudp; + + if (p4d_none(READ_ONCE(*dst_p4dp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) + return -ENOMEM; + + p4d_populate(NULL, dst_p4dp, dst_pudp); + } + + dst_pudp = pud_offset(dst_p4dp, start); + src_pudp = pud_offset(src_p4dp, start); + + do { + pud_t pud = READ_ONCE(*src_pudp); + + next = pud_addr_end(start, end); + + if (pud_none(pud)) + continue; + + if (pud_leaf(pud)) { + set_pud(dst_pudp, __pud(pud_val(pud) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pmd(dst_pudp, src_pudp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pudp++, src_pudp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + p4d_t *dst_p4dp; + p4d_t *src_p4dp; + + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = (p4d_t *)get_safe_page(GFP_ATOMIC); + if (!dst_p4dp) + return -ENOMEM; + + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + + dst_p4dp = p4d_offset(dst_pgdp, start); + src_p4dp = p4d_offset(src_pgdp, start); + + do { + p4d_t p4d = READ_ONCE(*src_p4dp); + + next = p4d_addr_end(start, end); + + if (p4d_none(p4d)) + continue; + + if (p4d_leaf(p4d)) { + set_p4d(dst_p4dp, __p4d(p4d_val(p4d) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pud(dst_p4dp, src_p4dp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_p4dp++, src_p4dp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_mapping(pgd_t *pgdp, unsigned long start, unsigned long end, pgprot_t prot) +{ + pgd_t *dst_pgdp = pgd_offset_pgd(pgdp, start); + pgd_t *src_pgdp = pgd_offset_k(start); + unsigned long next; + unsigned long ret; + + do { + pgd_t pgd = READ_ONCE(*src_pgdp); + + next = pgd_addr_end(start, end); + + if (pgd_none(pgd)) + continue; + + if (pgd_leaf(pgd)) { + set_pgd(dst_pgdp, __pgd(pgd_val(pgd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_p4d(dst_pgdp, src_pgdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pgdp++, src_pgdp++, start = next, start != end); + + return 0; +} + +static unsigned long relocate_restore_code(void) +{ + void *page = (void *)get_safe_page(GFP_ATOMIC); + + if (!page) + return -ENOMEM; + + copy_page(page, hibernate_core_restore_code); + + /* Make the page containing the relocated code executable. */ + set_memory_x((unsigned long)page, 1); + + return (unsigned long)page; +} + +int swsusp_arch_resume(void) +{ + unsigned long end = (unsigned long)pfn_to_virt(max_low_pfn); + unsigned long start = PAGE_OFFSET; + int ret; + + /* + * Memory allocated by get_safe_page() will be dealt with by the hibernation core, + * we don't need to free it here. + */ + resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!resume_pg_dir) + return -ENOMEM; + + /* + * Create a temporary page table and map the whole linear region as executable and + * writable. + */ + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE | _PAGE_EXEC)); + if (ret) + return ret; + + /* Move the restore code to a new page so that it doesn't get overwritten by itself. */ + relocated_restore_code = relocate_restore_code(); + if (relocated_restore_code == -ENOMEM) + return -ENOMEM; + + /* + * Map the __hibernate_cpu_resume() address to the temporary page table so that the + * restore code can jumps to it after finished restore the image. The next execution + * code doesn't find itself in a different address space after switching over to the + * original page table used by the hibernated image. + * The __hibernate_cpu_resume() mapping is unnecessary for RV32 since the kernel and + * linear addresses are identical, but different for RV64. To ensure consistency, we + * map it for both RV32 and RV64 kernels. + * Additionally, we should ensure that the page is writable before restoring the image. + */ + start = (unsigned long)resume_hdr.restore_cpu_addr; + end = start + PAGE_SIZE; + + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE)); + if (ret) + return ret; + + hibernate_restore_image(resume_hdr.saved_satp, (PFN_DOWN(__pa(resume_pg_dir)) | satp_mode), + resume_hdr.restore_cpu_addr); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP_SMP +int hibernate_resume_nonboot_cpu_disable(void) +{ + if (sleep_cpu < 0) { + pr_err("Failing to resume from hibernate on an unknown CPU\n"); + return -ENODEV; + } + + return freeze_secondary_cpus(sleep_cpu); +} +#endif + +static int __init riscv_hibernate_init(void) +{ + hibernate_cpu_context = kzalloc(sizeof(*hibernate_cpu_context), GFP_KERNEL); + + if (WARN_ON(!hibernate_cpu_context)) + return -ENOMEM; + + return 0; +} + +early_initcall(riscv_hibernate_init); -- GitLab From b3d6bdfea21ce1bbb45c3e6f297dfaf570d36300 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 4 Apr 2023 13:34:21 -0700 Subject: [PATCH 4321/5631] riscv: Adjust dependencies of HAVE_DYNAMIC_FTRACE selection When building allmodconfig with clang and its integrated assembler and linking with a version of GNU ld prior to 2.36, the following link error occurs: riscv64-linux-gnu-ld: .init.data has both ordered [`__patchable_function_entries' in init/main.o] and unordered [`.init_array.0' in kernel/trace/trace_benchmark.o] sections riscv64-linux-gnu-ld: final link failed: bad value This is the same error addressed by commit 45bd8951806e ("arm64: Improve HAVE_DYNAMIC_FTRACE_WITH_REGS selection for clang") for arm64. See that changelog for a full description of why this error occurs with this combination of tools. In a similar manner as that change, restrict the CONFIG_HAVE_DYNAMIC_FTRACE selection to combinations of tools known to work so that there are no errors. Link: https://github.com/ClangBuiltLinux/linux/issues/1817 Signed-off-by: Nathan Chancellor Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230404-riscv-dynamic-ftrace-checks-clang-v1-1-0ce296b7d423@kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 5c88ac4b52be..7f4c5580753e 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -142,12 +142,23 @@ config RISCV select TRACE_IRQFLAGS_SUPPORT select UACCESS_MEMCPY if !MMU select ZONE_DMA32 if 64BIT - select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && $(cc-option,-fpatchable-function-entry=8) + select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION +config CLANG_SUPPORTS_DYNAMIC_FTRACE + def_bool CC_IS_CLANG + # https://github.com/llvm/llvm-project/commit/6ab8927931851bb42b2c93a00801dc499d7d9b1e + depends on CLANG_VERSION >= 130000 + # https://github.com/ClangBuiltLinux/linux/issues/1817 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + +config GCC_SUPPORTS_DYNAMIC_FTRACE + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=8) + config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT default 8 -- GitLab From e4ef93edd4e0b022529303db1915766ff9de450e Mon Sep 17 00:00:00 2001 From: Song Shuai Date: Wed, 26 Apr 2023 18:00:09 +0800 Subject: [PATCH 4322/5631] riscv: mm: remove redundant parameter of create_fdt_early_page_table create_fdt_early_page_table() explicitly uses early_pg_dir for 32-bit fdt mapping and the pgdir parameter is redundant here. So remove it and its caller. Reviewed-by: Alexandre Ghiti Signed-off-by: Song Shuai Reviewed-by: Conor Dooley Fixes: ef69d2559fe9 ("riscv: Move early dtb mapping into the fixmap region") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230426100009.685435-1-suagrfillet@gmail.com Signed-off-by: Palmer Dabbelt --- arch/riscv/mm/init.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index a39fe42baf55..747e5b1ef02d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -919,8 +919,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, bool early) * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR * entry. */ -static void __init create_fdt_early_page_table(pgd_t *pgdir, - uintptr_t fix_fdt_va, +static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, uintptr_t dtb_pa) { uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); @@ -1132,8 +1131,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_kernel_page_table(early_pg_dir, true); /* Setup early mapping for FDT early scan */ - create_fdt_early_page_table(early_pg_dir, - __fix_to_virt(FIX_FDT), dtb_pa); + create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa); /* * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap -- GitLab From 41cad8284d5e6bf1d49d3c10a6b52ee1ae866a20 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Thu, 27 Apr 2023 18:36:26 +0200 Subject: [PATCH 4323/5631] RISC-V: Align SBI probe implementation with spec sbi_probe_extension() is specified with "Returns 0 if the given SBI extension ID (EID) is not available, or 1 if it is available unless defined as any other non-zero value by the implementation." Additionally, sbiret.value is a long. Fix the implementation to ensure any nonzero long value is considered a success, rather than only positive int values. Fixes: b9dcd9e41587 ("RISC-V: Add basic support for SBI v0.2") Signed-off-by: Andrew Jones Reviewed-by: Conor Dooley Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230427163626.101042-1-ajones@ventanamicro.com Signed-off-by: Palmer Dabbelt --- arch/riscv/include/asm/sbi.h | 2 +- arch/riscv/kernel/cpu_ops.c | 2 +- arch/riscv/kernel/sbi.c | 17 ++++++++--------- arch/riscv/kvm/main.c | 2 +- drivers/cpuidle/cpuidle-riscv-sbi.c | 2 +- drivers/perf/riscv_pmu_sbi.c | 2 +- 6 files changed, 13 insertions(+), 14 deletions(-) diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index acab4410ef2a..5b4a1bf5f439 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -295,7 +295,7 @@ int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, unsigned long start, unsigned long size, unsigned long asid); -int sbi_probe_extension(int ext); +long sbi_probe_extension(int ext); /* Check if current SBI specification version is 0.1 or not */ static inline int sbi_spec_is_0_1(void) diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c index 8275f237a59d..eb479a88a954 100644 --- a/arch/riscv/kernel/cpu_ops.c +++ b/arch/riscv/kernel/cpu_ops.c @@ -27,7 +27,7 @@ const struct cpu_operations cpu_ops_spinwait = { void __init cpu_set_ops(int cpuid) { #if IS_ENABLED(CONFIG_RISCV_SBI) - if (sbi_probe_extension(SBI_EXT_HSM) > 0) { + if (sbi_probe_extension(SBI_EXT_HSM)) { if (!cpuid) pr_info("SBI HSM extension detected\n"); cpu_ops[cpuid] = &cpu_ops_sbi; diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 92b9b759ab3d..c672c8ba9a2a 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -524,19 +524,18 @@ static void sbi_srst_power_off(void) * sbi_probe_extension() - Check if an SBI extension ID is supported or not. * @extid: The extension ID to be probed. * - * Return: Extension specific nonzero value f yes, -ENOTSUPP otherwise. + * Return: 1 or an extension specific nonzero value if yes, 0 otherwise. */ -int sbi_probe_extension(int extid) +long sbi_probe_extension(int extid) { struct sbiret ret; ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid, 0, 0, 0, 0, 0); if (!ret.error) - if (ret.value) - return ret.value; + return ret.value; - return -ENOTSUPP; + return 0; } EXPORT_SYMBOL(sbi_probe_extension); @@ -599,26 +598,26 @@ void __init sbi_init(void) if (!sbi_spec_is_0_1()) { pr_info("SBI implementation ID=0x%lx Version=0x%lx\n", sbi_get_firmware_id(), sbi_get_firmware_version()); - if (sbi_probe_extension(SBI_EXT_TIME) > 0) { + if (sbi_probe_extension(SBI_EXT_TIME)) { __sbi_set_timer = __sbi_set_timer_v02; pr_info("SBI TIME extension detected\n"); } else { __sbi_set_timer = __sbi_set_timer_v01; } - if (sbi_probe_extension(SBI_EXT_IPI) > 0) { + if (sbi_probe_extension(SBI_EXT_IPI)) { __sbi_send_ipi = __sbi_send_ipi_v02; pr_info("SBI IPI extension detected\n"); } else { __sbi_send_ipi = __sbi_send_ipi_v01; } - if (sbi_probe_extension(SBI_EXT_RFENCE) > 0) { + if (sbi_probe_extension(SBI_EXT_RFENCE)) { __sbi_rfence = __sbi_rfence_v02; pr_info("SBI RFENCE extension detected\n"); } else { __sbi_rfence = __sbi_rfence_v01; } if ((sbi_spec_version >= sbi_mk_version(0, 3)) && - (sbi_probe_extension(SBI_EXT_SRST) > 0)) { + sbi_probe_extension(SBI_EXT_SRST)) { pr_info("SBI SRST extension detected\n"); pm_power_off = sbi_srst_power_off; sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot; diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 41ad7639a17b..c923c113a129 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -75,7 +75,7 @@ static int __init riscv_kvm_init(void) return -ENODEV; } - if (sbi_probe_extension(SBI_EXT_RFENCE) <= 0) { + if (!sbi_probe_extension(SBI_EXT_RFENCE)) { kvm_info("require SBI RFENCE extension\n"); return -ENODEV; } diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index f2ccda2c3871..e8094fc92491 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -613,7 +613,7 @@ static int __init sbi_cpuidle_init(void) * 2) SBI HSM extension is available */ if ((sbi_spec_version < sbi_mk_version(0, 3)) || - sbi_probe_extension(SBI_EXT_HSM) <= 0) { + !sbi_probe_extension(SBI_EXT_HSM)) { pr_info("HSM suspend not available\n"); return 0; } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 70cb50fd41c2..4f3ac296b3e2 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -924,7 +924,7 @@ static int __init pmu_sbi_devinit(void) struct platform_device *pdev; if (sbi_spec_version < sbi_mk_version(0, 3) || - sbi_probe_extension(SBI_EXT_PMU) <= 0) { + !sbi_probe_extension(SBI_EXT_PMU)) { return 0; } -- GitLab From a2a58b5ca124f4a0178d0ada801f1ed2c84c393d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 29 Apr 2023 08:52:47 -0700 Subject: [PATCH 4324/5631] RISC-V: fix sifive and thead section mismatches in errata When CONFIG_MODULES is set, __init_or_module becomes , but when CONFIG_MODULES is not set, __init_or_module becomes __init. In the latter case, it causes section mismatch warnings: WARNING: modpost: vmlinux.o: section mismatch in reference: riscv_fill_cpu_mfr_info (section: .text) -> sifive_errata_patch_func (section: .init.text) WARNING: modpost: vmlinux.o: section mismatch in reference: riscv_fill_cpu_mfr_info (section: .text) -> thead_errata_patch_func (section: .init.text) Fixes: bb3f89487fd9 ("RISC-V: hwprobe: Remove __init on probe_vendor_features()") Signed-off-by: Randy Dunlap Reviewed-by: Evan Green Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20230429155247.12131-1-rdunlap@infradead.org Signed-off-by: Palmer Dabbelt --- arch/riscv/errata/sifive/errata.c | 8 +++----- arch/riscv/errata/thead/errata.c | 6 +++--- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c index 8d8301d7b1ec..3d9a32d791f7 100644 --- a/arch/riscv/errata/sifive/errata.c +++ b/arch/riscv/errata/sifive/errata.c @@ -82,11 +82,9 @@ static void __init_or_module warn_miss_errata(u32 miss_errata) pr_warn("----------------------------------------------------------------\n"); } -void __init_or_module sifive_errata_patch_func(struct alt_entry *begin, - struct alt_entry *end, - unsigned long archid, - unsigned long impid, - unsigned int stage) +void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) { struct alt_entry *alt; u32 cpu_req_errata; diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index a86c4facc2a6..c259dc925ec1 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -83,9 +83,9 @@ static u32 thead_errata_probe(unsigned int stage, return cpu_req_errata; } -void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, - unsigned long archid, unsigned long impid, - unsigned int stage) +void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) { struct alt_entry *alt; u32 cpu_req_errata = thead_errata_probe(stage, archid, impid); -- GitLab From 26b0812f4cf824a02eec9a425c09e34a25420166 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Sat, 29 Apr 2023 10:27:33 +0100 Subject: [PATCH 4325/5631] RISC-V: fixup in-flight collision with ARCH_WANT_OPTIMIZE_VMEMMAP rename Lukas warned that ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP had been renamed in the mm tree & that RISC-V would need a fixup as part of the merge. The warning was missed however, and RISC-V is selecting the orphaned Kconfig option. Fixes: 89d77f71f493 ("Merge tag 'riscv-for-linus-6.4-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux") Reported-by: Lukas Bulwahn . Link: https://lore.kernel.org/linux-riscv/CAKXUXMyVeg2kQK_edKHtMD3eADrDK_PKhCSVkMrLDdYgTQQ5rg@mail.gmail.com/ Signed-off-by: Conor Dooley Reviewed-by: Palmer Dabbelt Link: https://lore.kernel.org/r/20230429-trilogy-jolly-12bf5c53d62d@spud Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 146ecd5f6a56..f6e7e1fb0a20 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -46,9 +46,9 @@ config RISCV select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT - select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_HUGE_PMD_SHARE if 64BIT select ARCH_WANT_LD_ORPHAN_WARN if !XIP_KERNEL + select ARCH_WANT_OPTIMIZE_VMEMMAP select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU -- GitLab From 9f855779a3874eee70e9f6be57b5f7774f14e510 Mon Sep 17 00:00:00 2001 From: Akhil R Date: Thu, 27 Apr 2023 18:09:14 +0530 Subject: [PATCH 4326/5631] i2c: tegra: Fix PEC support for SMBUS block read Update the msg->len value correctly for SMBUS block read. The discrepancy went unnoticed as msg->len is used in SMBUS transfers only when a PEC byte is added. Fixes: d7583c8a5748 ("i2c: tegra: Add SMBus block read function") Signed-off-by: Akhil R Acked-by: Thierry Reding Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-tegra.c | 40 +++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 13 deletions(-) diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 6aab84c8d22b..157066f06a32 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -242,9 +242,10 @@ struct tegra_i2c_hw_feature { * @is_dvc: identifies the DVC I2C controller, has a different register layout * @is_vi: identifies the VI I2C controller, has a different register layout * @msg_complete: transfer completion notifier + * @msg_buf_remaining: size of unsent data in the message buffer + * @msg_len: length of message in current transfer * @msg_err: error code for completed message * @msg_buf: pointer to current message data - * @msg_buf_remaining: size of unsent data in the message buffer * @msg_read: indicates that the transfer is a read access * @timings: i2c timings information like bus frequency * @multimaster_mode: indicates that I2C controller is in multi-master mode @@ -277,6 +278,7 @@ struct tegra_i2c_dev { struct completion msg_complete; size_t msg_buf_remaining; + unsigned int msg_len; int msg_err; u8 *msg_buf; @@ -1169,7 +1171,7 @@ static void tegra_i2c_push_packet_header(struct tegra_i2c_dev *i2c_dev, else i2c_writel(i2c_dev, packet_header, I2C_TX_FIFO); - packet_header = msg->len - 1; + packet_header = i2c_dev->msg_len - 1; if (i2c_dev->dma_mode && !i2c_dev->msg_read) *dma_buf++ = packet_header; @@ -1242,20 +1244,32 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, return err; i2c_dev->msg_buf = msg->buf; + i2c_dev->msg_len = msg->len; - /* The condition true implies smbus block read and len is already read */ - if (msg->flags & I2C_M_RECV_LEN && end_state != MSG_END_CONTINUE) - i2c_dev->msg_buf = msg->buf + 1; - - i2c_dev->msg_buf_remaining = msg->len; i2c_dev->msg_err = I2C_ERR_NONE; i2c_dev->msg_read = !!(msg->flags & I2C_M_RD); reinit_completion(&i2c_dev->msg_complete); + /* + * For SMBUS block read command, read only 1 byte in the first transfer. + * Adjust that 1 byte for the next transfer in the msg buffer and msg + * length. + */ + if (msg->flags & I2C_M_RECV_LEN) { + if (end_state == MSG_END_CONTINUE) { + i2c_dev->msg_len = 1; + } else { + i2c_dev->msg_buf += 1; + i2c_dev->msg_len -= 1; + } + } + + i2c_dev->msg_buf_remaining = i2c_dev->msg_len; + if (i2c_dev->msg_read) - xfer_size = msg->len; + xfer_size = i2c_dev->msg_len; else - xfer_size = msg->len + I2C_PACKET_HEADER_SIZE; + xfer_size = i2c_dev->msg_len + I2C_PACKET_HEADER_SIZE; xfer_size = ALIGN(xfer_size, BYTES_PER_FIFO_WORD); @@ -1295,7 +1309,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (!i2c_dev->msg_read) { if (i2c_dev->dma_mode) { memcpy(i2c_dev->dma_buf + I2C_PACKET_HEADER_SIZE, - msg->buf, msg->len); + msg->buf, i2c_dev->msg_len); dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, @@ -1352,7 +1366,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); - memcpy(i2c_dev->msg_buf, i2c_dev->dma_buf, msg->len); + memcpy(i2c_dev->msg_buf, i2c_dev->dma_buf, i2c_dev->msg_len); } } @@ -1408,8 +1422,8 @@ static int tegra_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], ret = tegra_i2c_xfer_msg(i2c_dev, &msgs[i], MSG_END_CONTINUE); if (ret) break; - /* Set the read byte as msg len */ - msgs[i].len = msgs[i].buf[0]; + /* Set the msg length from first byte */ + msgs[i].len += msgs[i].buf[0]; dev_dbg(i2c_dev->dev, "reading %d bytes\n", msgs[i].len); } ret = tegra_i2c_xfer_msg(i2c_dev, &msgs[i], end_type); -- GitLab From 7a6c3a035a2e133b41d01c1a479b50aac4aeecad Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Tue, 28 Feb 2023 20:40:51 +0800 Subject: [PATCH 4327/5631] ceph: do not print the whole xattr value if it's too long If the xattr's value size is long enough the kernel will warn and then will fail the xfstests test case. Just print part of the value string if it's too long. At the same time fix the function name issue in the debug logs. Link: https://tracker.ceph.com/issues/58404 Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/xattr.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index f65b07cc33a2..8b6b3075f4d1 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -535,6 +535,8 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, return NULL; } +#define MAX_XATTR_VAL_PRINT_LEN 256 + static int __set_xattr(struct ceph_inode_info *ci, const char *name, int name_len, const char *val, int val_len, @@ -597,7 +599,7 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr->should_free_name = update_xattr; ci->i_xattrs.count++; - dout("__set_xattr count=%d\n", ci->i_xattrs.count); + dout("%s count=%d\n", __func__, ci->i_xattrs.count); } else { kfree(*newxattr); *newxattr = NULL; @@ -625,11 +627,13 @@ static int __set_xattr(struct ceph_inode_info *ci, if (new) { rb_link_node(&xattr->node, parent, p); rb_insert_color(&xattr->node, &ci->i_xattrs.index); - dout("__set_xattr_val p=%p\n", p); + dout("%s p=%p\n", __func__, p); } - dout("__set_xattr_val added %llx.%llx xattr %p %.*s=%.*s\n", - ceph_vinop(&ci->netfs.inode), xattr, name_len, name, val_len, val); + dout("%s added %llx.%llx xattr %p %.*s=%.*s%s\n", __func__, + ceph_vinop(&ci->netfs.inode), xattr, name_len, name, + min(val_len, MAX_XATTR_VAL_PRINT_LEN), val, + val_len > MAX_XATTR_VAL_PRINT_LEN ? "..." : ""); return 0; } @@ -655,13 +659,15 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci, else if (c > 0) p = &(*p)->rb_right; else { - dout("__get_xattr %s: found %.*s\n", name, - xattr->val_len, xattr->val); + int len = min(xattr->val_len, MAX_XATTR_VAL_PRINT_LEN); + + dout("%s %s: found %.*s%s\n", __func__, name, len, + xattr->val, xattr->val_len > len ? "..." : ""); return xattr; } } - dout("__get_xattr %s: not found\n", name); + dout("%s %s: not found\n", __func__, name); return NULL; } -- GitLab From 7d41870d65db028234333c68e60a034ac335557a Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 8 Mar 2023 10:21:44 +0800 Subject: [PATCH 4328/5631] ceph: implement writeback livelock avoidance using page tagging While the mapped IOs continue if we try to flush a file's buffer we can see that the fsync() won't complete until the IOs finish. This is analogous to Jan Kara's commit (f446daaea9d4 mm: implement writeback livelock avoidance using page tagging), we will try to avoid livelocks of writeback when some steadily creates dirty pages in a mapping we are writing out. Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/addr.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index d5335f445233..6bb251a4d613 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -808,6 +808,7 @@ static int ceph_writepages_start(struct address_space *mapping, bool should_loop, range_whole = false; bool done = false; bool caching = ceph_is_cache_enabled(inode); + xa_mark_t tag; if (wbc->sync_mode == WB_SYNC_NONE && fsc->write_congested) @@ -834,6 +835,11 @@ static int ceph_writepages_start(struct address_space *mapping, start_index = wbc->range_cyclic ? mapping->writeback_index : 0; index = start_index; + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { + tag = PAGECACHE_TAG_TOWRITE; + } else { + tag = PAGECACHE_TAG_DIRTY; + } retry: /* find oldest snap context with dirty data */ snapc = get_oldest_context(inode, &ceph_wbc, NULL); @@ -872,6 +878,9 @@ static int ceph_writepages_start(struct address_space *mapping, dout(" non-head snapc, range whole\n"); } + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + tag_pages_for_writeback(mapping, index, end); + ceph_put_snap_context(last_snapc); last_snapc = snapc; @@ -888,7 +897,7 @@ static int ceph_writepages_start(struct address_space *mapping, get_more_pages: nr_folios = filemap_get_folios_tag(mapping, &index, - end, PAGECACHE_TAG_DIRTY, &fbatch); + end, tag, &fbatch); dout("pagevec_lookup_range_tag got %d\n", nr_folios); if (!nr_folios && !locked_pages) break; -- GitLab From aaf67de78807c59c35bafb5003d4fb457c764800 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 19 Apr 2023 10:39:14 +0800 Subject: [PATCH 4329/5631] ceph: fix potential use-after-free bug when trimming caps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When trimming the caps and just after the 'session->s_cap_lock' is released in ceph_iterate_session_caps() the cap maybe removed by another thread, and when using the stale cap memory in the callbacks it will trigger use-after-free crash. We need to check the existence of the cap just after the 'ci->i_ceph_lock' being acquired. And do nothing if it's already removed. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/43272 Signed-off-by: Xiubo Li Reviewed-by: Luís Henriques Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 2 +- fs/ceph/debugfs.c | 18 +++++++---- fs/ceph/mds_client.c | 72 ++++++++++++++++++++++++++++---------------- fs/ceph/mds_client.h | 3 +- fs/ceph/super.h | 2 ++ 5 files changed, 62 insertions(+), 35 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7cc20772eac9..789be30d6ee2 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -431,7 +431,7 @@ void ceph_reservation_status(struct ceph_fs_client *fsc, * * Called with i_ceph_lock held. */ -static struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds) +struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds) { struct ceph_cap *cap; struct rb_node *n = ci->i_caps.rb_node; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index bec3c4549c07..3904333fa6c3 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -248,14 +248,20 @@ static int metrics_caps_show(struct seq_file *s, void *p) return 0; } -static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p) +static int caps_show_cb(struct inode *inode, int mds, void *p) { + struct ceph_inode_info *ci = ceph_inode(inode); struct seq_file *s = p; - - seq_printf(s, "0x%-17llx%-3d%-17s%-17s\n", ceph_ino(inode), - cap->session->s_mds, - ceph_cap_string(cap->issued), - ceph_cap_string(cap->implemented)); + struct ceph_cap *cap; + + spin_lock(&ci->i_ceph_lock); + cap = __get_cap_for_mds(ci, mds); + if (cap) + seq_printf(s, "0x%-17llx%-3d%-17s%-17s\n", ceph_ino(inode), + cap->session->s_mds, + ceph_cap_string(cap->issued), + ceph_cap_string(cap->implemented)); + spin_unlock(&ci->i_ceph_lock); return 0; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 27a245d959c0..54e3c2ab21d2 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1632,8 +1632,8 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc, * Caller must hold session s_mutex. */ int ceph_iterate_session_caps(struct ceph_mds_session *session, - int (*cb)(struct inode *, struct ceph_cap *, - void *), void *arg) + int (*cb)(struct inode *, int mds, void *), + void *arg) { struct list_head *p; struct ceph_cap *cap; @@ -1645,6 +1645,8 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, spin_lock(&session->s_cap_lock); p = session->s_caps.next; while (p != &session->s_caps) { + int mds; + cap = list_entry(p, struct ceph_cap, session_caps); inode = igrab(&cap->ci->netfs.inode); if (!inode) { @@ -1652,6 +1654,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, continue; } session->s_cap_iterator = cap; + mds = cap->mds; spin_unlock(&session->s_cap_lock); if (last_inode) { @@ -1663,7 +1666,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, old_cap = NULL; } - ret = cb(inode, cap, arg); + ret = cb(inode, mds, arg); last_inode = inode; spin_lock(&session->s_cap_lock); @@ -1696,20 +1699,25 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session, return ret; } -static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, - void *arg) +static int remove_session_caps_cb(struct inode *inode, int mds, void *arg) { struct ceph_inode_info *ci = ceph_inode(inode); bool invalidate = false; - int iputs; + struct ceph_cap *cap; + int iputs = 0; - dout("removing cap %p, ci is %p, inode is %p\n", - cap, ci, &ci->netfs.inode); spin_lock(&ci->i_ceph_lock); - iputs = ceph_purge_inode_cap(inode, cap, &invalidate); + cap = __get_cap_for_mds(ci, mds); + if (cap) { + dout(" removing cap %p, ci is %p, inode is %p\n", + cap, ci, &ci->netfs.inode); + + iputs = ceph_purge_inode_cap(inode, cap, &invalidate); + } spin_unlock(&ci->i_ceph_lock); - wake_up_all(&ci->i_cap_wq); + if (cap) + wake_up_all(&ci->i_cap_wq); if (invalidate) ceph_queue_invalidate(inode); while (iputs--) @@ -1780,8 +1788,7 @@ enum { * * caller must hold s_mutex. */ -static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, - void *arg) +static int wake_up_session_cb(struct inode *inode, int mds, void *arg) { struct ceph_inode_info *ci = ceph_inode(inode); unsigned long ev = (unsigned long)arg; @@ -1792,12 +1799,14 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, ci->i_requested_max_size = 0; spin_unlock(&ci->i_ceph_lock); } else if (ev == RENEWCAPS) { - if (cap->cap_gen < atomic_read(&cap->session->s_cap_gen)) { - /* mds did not re-issue stale cap */ - spin_lock(&ci->i_ceph_lock); + struct ceph_cap *cap; + + spin_lock(&ci->i_ceph_lock); + cap = __get_cap_for_mds(ci, mds); + /* mds did not re-issue stale cap */ + if (cap && cap->cap_gen < atomic_read(&cap->session->s_cap_gen)) cap->issued = cap->implemented = CEPH_CAP_PIN; - spin_unlock(&ci->i_ceph_lock); - } + spin_unlock(&ci->i_ceph_lock); } else if (ev == FORCE_RO) { } wake_up_all(&ci->i_cap_wq); @@ -1959,16 +1968,22 @@ static bool drop_negative_children(struct dentry *dentry) * Yes, this is a bit sloppy. Our only real goal here is to respond to * memory pressure from the MDS, though, so it needn't be perfect. */ -static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) +static int trim_caps_cb(struct inode *inode, int mds, void *arg) { int *remaining = arg; struct ceph_inode_info *ci = ceph_inode(inode); int used, wanted, oissued, mine; + struct ceph_cap *cap; if (*remaining <= 0) return -1; spin_lock(&ci->i_ceph_lock); + cap = __get_cap_for_mds(ci, mds); + if (!cap) { + spin_unlock(&ci->i_ceph_lock); + return 0; + } mine = cap->issued | cap->implemented; used = __ceph_caps_used(ci); wanted = __ceph_caps_file_wanted(ci); @@ -3911,26 +3926,22 @@ static struct dentry* d_find_primary(struct inode *inode) /* * Encode information about a cap for a reconnect with the MDS. */ -static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, - void *arg) +static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) { union { struct ceph_mds_cap_reconnect v2; struct ceph_mds_cap_reconnect_v1 v1; } rec; - struct ceph_inode_info *ci = cap->ci; + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_reconnect_state *recon_state = arg; struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; + struct ceph_cap *cap; char *path; - int pathlen = 0, err; + int pathlen = 0, err = 0; u64 pathbase; u64 snap_follows; - dout(" adding %p ino %llx.%llx cap %p %lld %s\n", - inode, ceph_vinop(inode), cap, cap->cap_id, - ceph_cap_string(cap->issued)); - dentry = d_find_primary(inode); if (dentry) { /* set pathbase to parent dir when msg_version >= 2 */ @@ -3947,6 +3958,15 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, } spin_lock(&ci->i_ceph_lock); + cap = __get_cap_for_mds(ci, mds); + if (!cap) { + spin_unlock(&ci->i_ceph_lock); + goto out_err; + } + dout(" adding %p ino %llx.%llx cap %p %lld %s\n", + inode, ceph_vinop(inode), cap, cap->cap_id, + ceph_cap_string(cap->issued)); + cap->seq = 0; /* reset cap seq */ cap->issue_seq = 0; /* and issue_seq */ cap->mseq = 0; /* and migrate_seq */ diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 0598faa50e2e..18b026b1ac63 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -541,8 +541,7 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); extern int ceph_iterate_session_caps(struct ceph_mds_session *session, - int (*cb)(struct inode *, - struct ceph_cap *, void *), + int (*cb)(struct inode *, int mds, void *), void *arg); extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 6ecca2c6d137..d24bf0db5234 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -1192,6 +1192,8 @@ extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); void ceph_kick_flushing_inode_caps(struct ceph_mds_session *session, struct ceph_inode_info *ci); +extern struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, + int mds); extern struct ceph_cap *ceph_get_cap_for_mds(struct ceph_inode_info *ci, int mds); extern void ceph_take_cap_refs(struct ceph_inode_info *ci, int caps, -- GitLab From a5ffd7b6e91a12975ae30de863437cc04387576a Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Wed, 26 Apr 2023 10:38:57 +0800 Subject: [PATCH 4330/5631] ceph: pass ino# instead of old_dentry if it's disconnected When exporting the kceph to NFS it may pass a DCACHE_DISCONNECTED dentry for the link operation. Then it will parse this dentry as a snapdir, and the mds will fail the link request as -EROFS. MDS allow clients to pass a ino# instead of a path. Link: https://tracker.ceph.com/issues/59515 Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/dir.c | 13 +++++++++++-- fs/ceph/mds_client.c | 6 +++++- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0ced8b570e42..cb67ac821f0e 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1050,6 +1050,9 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, struct ceph_mds_request *req; int err; + if (dentry->d_flags & DCACHE_DISCONNECTED) + return -EINVAL; + err = ceph_wait_on_conflict_unlink(dentry); if (err) return err; @@ -1057,8 +1060,8 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, if (ceph_snap(dir) != CEPH_NOSNAP) return -EROFS; - dout("link in dir %p old_dentry %p dentry %p\n", dir, - old_dentry, dentry); + dout("link in dir %p %llx.%llx old_dentry %p:'%pd' dentry %p:'%pd'\n", + dir, ceph_vinop(dir), old_dentry, old_dentry, dentry, dentry); req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LINK, USE_AUTH_MDS); if (IS_ERR(req)) { d_drop(dentry); @@ -1067,6 +1070,12 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, req->r_dentry = dget(dentry); req->r_num_caps = 2; req->r_old_dentry = dget(old_dentry); + /* + * The old_dentry maybe a DCACHE_DISCONNECTED dentry, then we + * will just pass the ino# to MDSs. + */ + if (old_dentry->d_flags & DCACHE_DISCONNECTED) + req->r_ino2 = ceph_vino(d_inode(old_dentry)); req->r_parent = dir; ihold(dir); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 54e3c2ab21d2..29cf00220b09 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2570,6 +2570,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; bool freepath1 = false, freepath2 = false; + struct dentry *old_dentry = NULL; int len; u16 releases; void *p, *end; @@ -2587,7 +2588,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, } /* If r_old_dentry is set, then assume that its parent is locked */ - ret = set_request_path_attr(NULL, req->r_old_dentry, + if (req->r_old_dentry && + !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED)) + old_dentry = req->r_old_dentry; + ret = set_request_path_attr(NULL, old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, &path2, &pathlen2, &ino2, &freepath2, true); -- GitLab From db2993a423e3fd0e4878f4d3ac66fe717f5f072e Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Thu, 27 Apr 2023 20:05:42 +0200 Subject: [PATCH 4331/5631] ceph: reorder fields in 'struct ceph_snapid_map' Group some variables based on their sizes to reduce holes. On x86_64, this shrinks the size of 'struct ceph_snapid_map' from 72 to 64 bytes. When such a structure is allocated, because of the way memory allocation works, when 72 bytes were requested, 96 bytes were allocated. So, on x86_64, this change saves 32 bytes per allocation and has the structure fit in a single cacheline. Signed-off-by: Christophe JAILLET Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 18b026b1ac63..724307ff89cd 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -355,8 +355,8 @@ struct ceph_snapid_map { struct rb_node node; struct list_head lru; atomic_t ref; - u64 snap; dev_t dev; + u64 snap; unsigned long last_used; }; -- GitLab From 6b496a94c5905fca7879bc0dc438a47de40b7d4f Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sat, 29 Apr 2023 09:46:01 -0400 Subject: [PATCH 4332/5631] i3c: ast2600: set variable ast2600_i3c_ops storage-class-specifier to static smatch reports drivers/i3c/master/ast2600-i3c-master.c:121:34: warning: symbol 'ast2600_i3c_ops' was not declared. Should it be static? This variable is only used in its defining file, so it should be static. Signed-off-by: Tom Rix Reviewed-by: Jeremy Kerr Link: https://lore.kernel.org/r/20230429134601.2688558-1-trix@redhat.com Signed-off-by: Alexandre Belloni --- drivers/i3c/master/ast2600-i3c-master.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i3c/master/ast2600-i3c-master.c b/drivers/i3c/master/ast2600-i3c-master.c index b72c12c5168f..09ed19d489e9 100644 --- a/drivers/i3c/master/ast2600-i3c-master.c +++ b/drivers/i3c/master/ast2600-i3c-master.c @@ -118,7 +118,7 @@ static void ast2600_i3c_set_dat_ibi(struct dw_i3c_master *i3c, } } -const struct dw_i3c_platform_ops ast2600_i3c_ops = { +static const struct dw_i3c_platform_ops ast2600_i3c_ops = { .init = ast2600_i3c_init, .set_dat_ibi = ast2600_i3c_set_dat_ibi, }; -- GitLab From 7949aa46bb4b5c5e43ba3ba8298ffcb48bebf0ff Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 30 Apr 2023 16:15:08 -0600 Subject: [PATCH 4333/5631] mailmap: add mailmap entries for Jens Axboe There's an old entry in there already, but update it and add fb/meta and oracle entries as well. Signed-off-by: Jens Axboe --- .mailmap | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/.mailmap b/.mailmap index 424564f40733..77fb9cebb8d3 100644 --- a/.mailmap +++ b/.mailmap @@ -209,7 +209,10 @@ Jeff Garzik Jeff Layton Jeff Layton Jeff Layton -Jens Axboe +Jens Axboe +Jens Axboe +Jens Axboe +Jens Axboe Jens Osterkamp Jernej Skrabec Jessica Zhang -- GitLab From 526f28bd0fbdc699cda31426928802650c1528e5 Mon Sep 17 00:00:00 2001 From: Victor Nogueira Date: Wed, 26 Apr 2023 15:19:40 +0000 Subject: [PATCH 4334/5631] net/sched: act_mirred: Add carrier check There are cases where the device is adminstratively UP, but operationally down. For example, we have a physical device (Nvidia ConnectX-6 Dx, 25Gbps) who's cable was pulled out, here is its ip link output: 5: ens2f1: mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000 link/ether b8:ce:f6:4b:68:35 brd ff:ff:ff:ff:ff:ff altname enp179s0f1np1 As you can see, it's administratively UP but operationally down. In this case, sending a packet to this port caused a nasty kernel hang (so nasty that we were unable to capture it). Aborting a transmit based on operational status (in addition to administrative status) fixes the issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Acked-by: Jamal Hadi Salim Signed-off-by: Victor Nogueira v1->v2: Add fixes tag v2->v3: Remove blank line between tags + add change log, suggested by Leon Signed-off-by: David S. Miller --- net/sched/act_mirred.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index ec43764e92e7..0a711c184c29 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -264,7 +264,7 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, goto out; } - if (unlikely(!(dev->flags & IFF_UP))) { + if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; -- GitLab From 8ceda6d5a1e5402fd852e6cc59a286ce3dc545ee Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 28 Apr 2023 16:53:29 +0800 Subject: [PATCH 4335/5631] r8152: fix flow control issue of RTL8156A The feature of flow control becomes abnormal, if the device sends a pause frame and the tx/rx is disabled before sending a release frame. It causes the lost of packets. Set PLA_RX_FIFO_FULL and PLA_RX_FIFO_EMPTY to zeros before disabling the tx/rx. And, toggle FC_PATCH_TASK before enabling tx/rx to reset the flow control patch and timer. Then, the hardware could clear the state and the flow control becomes normal after enabling tx/rx. Besides, remove inline for fc_pause_on_auto() and fc_pause_off_auto(). Fixes: 195aae321c82 ("r8152: support new chips") Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 56 ++++++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 20 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 0fc4b959edc1..afd50e90d1fe 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -5986,6 +5986,25 @@ static void rtl8153_disable(struct r8152 *tp) r8153_aldps_en(tp, true); } +static u32 fc_pause_on_auto(struct r8152 *tp) +{ + return (ALIGN(mtu_to_size(tp->netdev->mtu), 1024) + 6 * 1024); +} + +static u32 fc_pause_off_auto(struct r8152 *tp) +{ + return (ALIGN(mtu_to_size(tp->netdev->mtu), 1024) + 14 * 1024); +} + +static void r8156_fc_parameter(struct r8152 *tp) +{ + u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp); + u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp); + + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16); +} + static int rtl8156_enable(struct r8152 *tp) { u32 ocp_data; @@ -5994,6 +6013,7 @@ static int rtl8156_enable(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return -ENODEV; + r8156_fc_parameter(tp); set_tx_qlen(tp); rtl_set_eee_plus(tp); r8153_set_rx_early_timeout(tp); @@ -6025,9 +6045,24 @@ static int rtl8156_enable(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_USB, USB_L1_CTRL, ocp_data); } + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_FW_TASK); + ocp_data &= ~FC_PATCH_TASK; + ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data); + usleep_range(1000, 2000); + ocp_data |= FC_PATCH_TASK; + ocp_write_word(tp, MCU_TYPE_USB, USB_FW_TASK, ocp_data); + return rtl_enable(tp); } +static void rtl8156_disable(struct r8152 *tp) +{ + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, 0); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, 0); + + rtl8153_disable(tp); +} + static int rtl8156b_enable(struct r8152 *tp) { u32 ocp_data; @@ -6429,25 +6464,6 @@ static void rtl8153c_up(struct r8152 *tp) r8153b_u1u2en(tp, true); } -static inline u32 fc_pause_on_auto(struct r8152 *tp) -{ - return (ALIGN(mtu_to_size(tp->netdev->mtu), 1024) + 6 * 1024); -} - -static inline u32 fc_pause_off_auto(struct r8152 *tp) -{ - return (ALIGN(mtu_to_size(tp->netdev->mtu), 1024) + 14 * 1024); -} - -static void r8156_fc_parameter(struct r8152 *tp) -{ - u32 pause_on = tp->fc_pause_on ? tp->fc_pause_on : fc_pause_on_auto(tp); - u32 pause_off = tp->fc_pause_off ? tp->fc_pause_off : fc_pause_off_auto(tp); - - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_FULL, pause_on / 16); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_RX_FIFO_EMPTY, pause_off / 16); -} - static void rtl8156_change_mtu(struct r8152 *tp) { u32 rx_max_size = mtu_to_size(tp->netdev->mtu); @@ -9340,7 +9356,7 @@ static int rtl_ops_init(struct r8152 *tp) case RTL_VER_10: ops->init = r8156_init; ops->enable = rtl8156_enable; - ops->disable = rtl8153_disable; + ops->disable = rtl8156_disable; ops->up = rtl8156_up; ops->down = rtl8156_down; ops->unload = rtl8153_unload; -- GitLab From 61b0ad6f58e2066e054c6d4839d67974d2861a7d Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 28 Apr 2023 16:53:30 +0800 Subject: [PATCH 4336/5631] r8152: fix the poor throughput for 2.5G devices Fix the poor throughput for 2.5G devices, when changing the speed from auto mode to force mode. This patch is used to notify the MAC when the mode is changed. Fixes: 195aae321c82 ("r8152: support new chips") Signed-off-by: Hayes Wang Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index afd50e90d1fe..58670a65b840 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -199,6 +199,7 @@ #define OCP_EEE_AR 0xa41a #define OCP_EEE_DATA 0xa41c #define OCP_PHY_STATUS 0xa420 +#define OCP_INTR_EN 0xa424 #define OCP_NCTL_CFG 0xa42c #define OCP_POWER_CFG 0xa430 #define OCP_EEE_CFG 0xa432 @@ -620,6 +621,9 @@ enum spd_duplex { #define PHY_STAT_LAN_ON 3 #define PHY_STAT_PWRDN 5 +/* OCP_INTR_EN */ +#define INTR_SPEED_FORCE BIT(3) + /* OCP_NCTL_CFG */ #define PGA_RETURN_EN BIT(1) @@ -7554,6 +7558,11 @@ static void r8156_hw_phy_cfg(struct r8152 *tp) ((swap_a & 0x1f) << 8) | ((swap_a >> 8) & 0x1f)); } + + /* Notify the MAC when the speed is changed to force mode. */ + data = ocp_reg_read(tp, OCP_INTR_EN); + data |= INTR_SPEED_FORCE; + ocp_reg_write(tp, OCP_INTR_EN, data); break; default: break; @@ -7949,6 +7958,11 @@ static void r8156b_hw_phy_cfg(struct r8152 *tp) break; } + /* Notify the MAC when the speed is changed to force mode. */ + data = ocp_reg_read(tp, OCP_INTR_EN); + data |= INTR_SPEED_FORCE; + ocp_reg_write(tp, OCP_INTR_EN, data); + if (rtl_phy_patch_request(tp, true, true)) return; -- GitLab From cce8334f4aacd9936309a002d4a4de92a07cd2c2 Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Fri, 28 Apr 2023 16:53:31 +0800 Subject: [PATCH 4337/5631] r8152: move setting r8153b_rx_agg_chg_indicate() Move setting r8153b_rx_agg_chg_indicate() for 2.5G devices. The r8153b_rx_agg_chg_indicate() has to be called after enabling tx/rx. Otherwise, the coalescing settings are useless. Fixes: 195aae321c82 ("r8152: support new chips") Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 58670a65b840..755b0f72dd44 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3027,12 +3027,16 @@ static int rtl_enable(struct r8152 *tp) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, ocp_data); switch (tp->version) { - case RTL_VER_08: - case RTL_VER_09: - case RTL_VER_14: - r8153b_rx_agg_chg_indicate(tp); + case RTL_VER_01: + case RTL_VER_02: + case RTL_VER_03: + case RTL_VER_04: + case RTL_VER_05: + case RTL_VER_06: + case RTL_VER_07: break; default: + r8153b_rx_agg_chg_indicate(tp); break; } @@ -3086,7 +3090,6 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp) 640 / 8); ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EXTRA_AGGR_TMR, ocp_data); - r8153b_rx_agg_chg_indicate(tp); break; default: @@ -3120,7 +3123,6 @@ static void r8153_set_rx_early_size(struct r8152 *tp) case RTL_VER_15: ocp_write_word(tp, MCU_TYPE_USB, USB_RX_EARLY_SIZE, ocp_data / 8); - r8153b_rx_agg_chg_indicate(tp); break; default: WARN_ON_ONCE(1); -- GitLab From 281900a923d4c50df109b52a22ae3cdac150159b Mon Sep 17 00:00:00 2001 From: Andy Moreton Date: Fri, 28 Apr 2023 12:33:33 +0100 Subject: [PATCH 4338/5631] sfc: Fix module EEPROM reporting for QSFP modules The sfc driver does not report QSFP module EEPROM contents correctly as only the first page is fetched from hardware. Commit 0e1a2a3e6e7d ("ethtool: Add SFF-8436 and SFF-8636 max EEPROM length definitions") added ETH_MODULE_SFF_8436_MAX_LEN for the overall size of the EEPROM info, so use that to report the full EEPROM contents. Fixes: 9b17010da57a ("sfc: Add ethtool -m support for QSFP modules") Signed-off-by: Andy Moreton Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/mcdi_port_common.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c index 899cc1671004..0ab14f3d01d4 100644 --- a/drivers/net/ethernet/sfc/mcdi_port_common.c +++ b/drivers/net/ethernet/sfc/mcdi_port_common.c @@ -972,12 +972,15 @@ static u32 efx_mcdi_phy_module_type(struct efx_nic *efx) /* A QSFP+ NIC may actually have an SFP+ module attached. * The ID is page 0, byte 0. + * QSFP28 is of type SFF_8636, however, this is treated + * the same by ethtool, so we can also treat them the same. */ switch (efx_mcdi_phy_get_module_eeprom_byte(efx, 0, 0)) { - case 0x3: + case 0x3: /* SFP */ return MC_CMD_MEDIA_SFP_PLUS; - case 0xc: - case 0xd: + case 0xc: /* QSFP */ + case 0xd: /* QSFP+ */ + case 0x11: /* QSFP28 */ return MC_CMD_MEDIA_QSFP_PLUS; default: return 0; @@ -1075,7 +1078,7 @@ int efx_mcdi_phy_get_module_info(struct efx_nic *efx, struct ethtool_modinfo *mo case MC_CMD_MEDIA_QSFP_PLUS: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; default: -- GitLab From 4f163bf82b0244bf4d1e9a6b0f4cf4e90b42496e Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Fri, 28 Apr 2023 17:43:21 -0400 Subject: [PATCH 4339/5631] net: atlantic: Define aq_pm_ops conditionally on CONFIG_PM For s390, gcc with W=1 reports drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c:458:32: error: 'aq_pm_ops' defined but not used [-Werror=unused-const-variable=] 458 | static const struct dev_pm_ops aq_pm_ops = { | ^~~~~~~~~ The only use of aq_pm_ops is conditional on CONFIG_PM. The definition of aq_pm_ops and its functions should also be conditional on CONFIG_PM. Signed-off-by: Tom Rix Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 8647125d60ae..baa5f8cc31f2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -379,6 +379,7 @@ static void aq_pci_shutdown(struct pci_dev *pdev) } } +#ifdef CONFIG_PM static int aq_suspend_common(struct device *dev) { struct aq_nic_s *nic = pci_get_drvdata(to_pci_dev(dev)); @@ -463,6 +464,7 @@ static const struct dev_pm_ops aq_pm_ops = { .restore = aq_pm_resume_restore, .thaw = aq_pm_thaw, }; +#endif static struct pci_driver aq_pci_ops = { .name = AQ_CFG_DRV_NAME, -- GitLab From 0d098d83c5d9e107b2df7f5e11f81492f56d2fe7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Apr 2023 21:27:54 +0100 Subject: [PATCH 4340/5631] rxrpc: Fix hard call timeout units The hard call timeout is specified in the RXRPC_SET_CALL_TIMEOUT cmsg in seconds, so fix the point at which sendmsg() applies it to the call to convert to jiffies from seconds, not milliseconds. Fixes: a158bdd3247b ("rxrpc: Fix timeout of a call that hasn't yet been granted a channel") Signed-off-by: David Howells cc: Marc Dionne cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- net/rxrpc/sendmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6caa47d352ed..7498a77b5d39 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -699,7 +699,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) fallthrough; case 1: if (p.call.timeouts.hard > 0) { - j = msecs_to_jiffies(p.call.timeouts.hard); + j = p.call.timeouts.hard * HZ; now = jiffies; j += now; WRITE_ONCE(call->expect_term_by, j); -- GitLab From 0eb362d254814ce04848730bf32e75b8ee1a4d6c Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Apr 2023 21:27:55 +0100 Subject: [PATCH 4341/5631] rxrpc: Make it so that a waiting process can be aborted When sendmsg() creates an rxrpc call, it queues it to wait for a connection and channel to be assigned and then waits before it can start shovelling data as the encrypted DATA packet content includes a summary of the connection parameters. However, sendmsg() may get interrupted before a connection gets assigned and further sendmsg() calls will fail with EBUSY until an assignment is made. Fix this so that the call can at least be aborted without failing on EBUSY. We have to be careful here as sendmsg() mustn't be allowed to start the call timer if the call doesn't yet have a connection assigned as an oops may follow shortly thereafter. Fixes: 540b1c48c37a ("rxrpc: Fix deadlock between call creation and sendmsg/recvmsg") Reported-by: Marc Dionne Signed-off-by: David Howells cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- net/rxrpc/sendmsg.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 7498a77b5d39..c1b074c17b33 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -656,10 +656,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) goto out_put_unlock; } else { switch (rxrpc_call_state(call)) { - case RXRPC_CALL_UNINITIALISED: case RXRPC_CALL_CLIENT_AWAIT_CONN: - case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: + if (p.command == RXRPC_CMD_SEND_ABORT) + break; + fallthrough; + case RXRPC_CALL_UNINITIALISED: + case RXRPC_CALL_SERVER_PREALLOC: rxrpc_put_call(call, rxrpc_call_put_sendmsg); ret = -EBUSY; goto error_release_sock; -- GitLab From db099c625b13a74d462521a46d98a8ce5b53af5d Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 28 Apr 2023 21:27:56 +0100 Subject: [PATCH 4342/5631] rxrpc: Fix timeout of a call that hasn't yet been granted a channel afs_make_call() calls rxrpc_kernel_begin_call() to begin a call (which may get stalled in the background waiting for a connection to become available); it then calls rxrpc_kernel_set_max_life() to set the timeouts - but that starts the call timer so the call timer might then expire before we get a connection assigned - leading to the following oops if the call stalled: BUG: kernel NULL pointer dereference, address: 0000000000000000 ... CPU: 1 PID: 5111 Comm: krxrpcio/0 Not tainted 6.3.0-rc7-build3+ #701 RIP: 0010:rxrpc_alloc_txbuf+0xc0/0x157 ... Call Trace: rxrpc_send_ACK+0x50/0x13b rxrpc_input_call_event+0x16a/0x67d rxrpc_io_thread+0x1b6/0x45f ? _raw_spin_unlock_irqrestore+0x1f/0x35 ? rxrpc_input_packet+0x519/0x519 kthread+0xe7/0xef ? kthread_complete_and_exit+0x1b/0x1b ret_from_fork+0x22/0x30 Fix this by noting the timeouts in struct rxrpc_call when the call is created. The timer will be started when the first packet is transmitted. It shouldn't be possible to trigger this directly from userspace through AF_RXRPC as sendmsg() will return EBUSY if the call is in the waiting-for-conn state if it dropped out of the wait due to a signal. Fixes: 9d35d880e0e4 ("rxrpc: Move client call connection to the I/O thread") Reported-by: Marc Dionne Signed-off-by: David Howells cc: "David S. Miller" cc: Eric Dumazet cc: Jakub Kicinski cc: Paolo Abeni cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller --- fs/afs/afs.h | 4 ++-- fs/afs/internal.h | 2 +- fs/afs/rxrpc.c | 8 +++----- include/net/af_rxrpc.h | 21 +++++++++++---------- net/rxrpc/af_rxrpc.c | 3 +++ net/rxrpc/ar-internal.h | 1 + net/rxrpc/call_object.c | 9 ++++++++- net/rxrpc/sendmsg.c | 1 + 8 files changed, 30 insertions(+), 19 deletions(-) diff --git a/fs/afs/afs.h b/fs/afs/afs.h index 432cb4b23961..81815724db6c 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -19,8 +19,8 @@ #define AFSPATHMAX 1024 /* Maximum length of a pathname plus NUL */ #define AFSOPAQUEMAX 1024 /* Maximum length of an opaque field */ -#define AFS_VL_MAX_LIFESPAN (120 * HZ) -#define AFS_PROBE_MAX_LIFESPAN (30 * HZ) +#define AFS_VL_MAX_LIFESPAN 120 +#define AFS_PROBE_MAX_LIFESPAN 30 typedef u64 afs_volid_t; typedef u64 afs_vnodeid_t; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index ad8523d0d038..68ae91d21b57 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -128,7 +128,7 @@ struct afs_call { spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ - unsigned int max_lifespan; /* Maximum lifespan to set if not 0 */ + unsigned int max_lifespan; /* Maximum lifespan in secs to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ unsigned count2; /* count used in unmarshalling */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index e08b850c3e6d..ed1644e7683f 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -335,7 +335,9 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) /* create a call */ rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key, (unsigned long)call, - tx_total_len, gfp, + tx_total_len, + call->max_lifespan, + gfp, (call->async ? afs_wake_up_async_call : afs_wake_up_call_waiter), @@ -350,10 +352,6 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) } call->rxcall = rxcall; - - if (call->max_lifespan) - rxrpc_kernel_set_max_life(call->net->socket, rxcall, - call->max_lifespan); call->issue_time = ktime_get_real(); /* send the request */ diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 01a35e113ab9..5531dd08061e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -40,16 +40,17 @@ typedef void (*rxrpc_user_attach_call_t)(struct rxrpc_call *, unsigned long); void rxrpc_kernel_new_call_notification(struct socket *, rxrpc_notify_new_call_t, rxrpc_discard_new_call_t); -struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, - struct sockaddr_rxrpc *, - struct key *, - unsigned long, - s64, - gfp_t, - rxrpc_notify_rx_t, - bool, - enum rxrpc_interruptibility, - unsigned int); +struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, + struct sockaddr_rxrpc *srx, + struct key *key, + unsigned long user_call_ID, + s64 tx_total_len, + u32 hard_timeout, + gfp_t gfp, + rxrpc_notify_rx_t notify_rx, + bool upgrade, + enum rxrpc_interruptibility interruptibility, + unsigned int debug_id); int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, struct msghdr *, size_t, rxrpc_notify_end_tx_t); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index c32b164206f9..31f738d65f1c 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -265,6 +265,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use * @tx_total_len: Total length of data to transmit during the call (or -1) + * @hard_timeout: The maximum lifespan of the call in sec * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue * @upgrade: Request service upgrade for call @@ -283,6 +284,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct key *key, unsigned long user_call_ID, s64 tx_total_len, + u32 hard_timeout, gfp_t gfp, rxrpc_notify_rx_t notify_rx, bool upgrade, @@ -313,6 +315,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, p.tx_total_len = tx_total_len; p.interruptibility = interruptibility; p.kernel = true; + p.timeouts.hard = hard_timeout; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 67b0a894162d..5d44dc08f66d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -616,6 +616,7 @@ struct rxrpc_call { unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ + u32 hard_timo; /* Maximum lifetime or 0 (jif) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index e9f1f49d18c2..fecbc73054bc 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -226,6 +226,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, if (cp->exclusive) __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); + if (p->timeouts.normal) + call->next_rx_timo = min(msecs_to_jiffies(p->timeouts.normal), 1UL); + if (p->timeouts.idle) + call->next_req_timo = min(msecs_to_jiffies(p->timeouts.idle), 1UL); + if (p->timeouts.hard) + call->hard_timo = p->timeouts.hard * HZ; + ret = rxrpc_init_client_call_security(call); if (ret < 0) { rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret); @@ -257,7 +264,7 @@ void rxrpc_start_call_timer(struct rxrpc_call *call) call->keepalive_at = j; call->expect_rx_by = j; call->expect_req_by = j; - call->expect_term_by = j; + call->expect_term_by = j + call->hard_timo; call->timer.expires = now; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index c1b074c17b33..8e0b94714e84 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -651,6 +651,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + p.call.nr_timeouts = 0; ret = 0; if (rxrpc_call_is_complete(call)) goto out_put_unlock; -- GitLab From 9e36fa42995a7c7fa8d84a429ca647736c4f1c66 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4343/5631] LoongArch: Clean up the architectural interrupt definitions While interrupts are assigned ECodes `64 + interrupt number`, all existing use sites of interrupt numbers want the 64 subtracted. Re-arrange the definitions so that the actual interrupt number is used everywhere, and make EXCCODE_INT_END inclusive as it is more intuitive that way. While at it, according to the asm/loongarch.h definitions, the total number of architectural interrupts should be 14, but various other places indicate otherwise (13 or 15). Those places have been adjusted to 14 as well for consistency. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/loongarch.h | 47 ++++++++++++++------------ arch/loongarch/kernel/irq.c | 2 +- arch/loongarch/kernel/perf_event.c | 2 +- arch/loongarch/kernel/time.c | 2 +- arch/loongarch/kernel/traps.c | 2 +- 5 files changed, 29 insertions(+), 26 deletions(-) diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 83da5d29e2d1..7d8b83dd32e9 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -311,8 +311,8 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define CSR_ECFG_VS_WIDTH 3 #define CSR_ECFG_VS (_ULCAST_(0x7) << CSR_ECFG_VS_SHIFT) #define CSR_ECFG_IM_SHIFT 0 -#define CSR_ECFG_IM_WIDTH 13 -#define CSR_ECFG_IM (_ULCAST_(0x1fff) << CSR_ECFG_IM_SHIFT) +#define CSR_ECFG_IM_WIDTH 14 +#define CSR_ECFG_IM (_ULCAST_(0x3fff) << CSR_ECFG_IM_SHIFT) #define LOONGARCH_CSR_ESTAT 0x5 /* Exception status */ #define CSR_ESTAT_ESUBCODE_SHIFT 22 @@ -322,8 +322,8 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define CSR_ESTAT_EXC_WIDTH 6 #define CSR_ESTAT_EXC (_ULCAST_(0x3f) << CSR_ESTAT_EXC_SHIFT) #define CSR_ESTAT_IS_SHIFT 0 -#define CSR_ESTAT_IS_WIDTH 15 -#define CSR_ESTAT_IS (_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT) +#define CSR_ESTAT_IS_WIDTH 14 +#define CSR_ESTAT_IS (_ULCAST_(0x3fff) << CSR_ESTAT_IS_SHIFT) #define LOONGARCH_CSR_ERA 0x6 /* ERA */ @@ -1090,7 +1090,7 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define ECFGF_IPI (_ULCAST_(1) << ECFGB_IPI) #define ECFGF(hwirq) (_ULCAST_(1) << hwirq) -#define ESTATF_IP 0x00001fff +#define ESTATF_IP 0x00003fff #define LOONGARCH_IOCSR_FEATURES 0x8 #define IOCSRF_TEMP BIT_ULL(0) @@ -1418,23 +1418,26 @@ __BUILD_CSR_OP(tlbidx) #define EXCSUBCODE_GCHC 1 /* Hardware caused */ #define EXCCODE_SE 25 /* Security */ -#define EXCCODE_INT_START 64 -#define EXCCODE_SIP0 64 -#define EXCCODE_SIP1 65 -#define EXCCODE_IP0 66 -#define EXCCODE_IP1 67 -#define EXCCODE_IP2 68 -#define EXCCODE_IP3 69 -#define EXCCODE_IP4 70 -#define EXCCODE_IP5 71 -#define EXCCODE_IP6 72 -#define EXCCODE_IP7 73 -#define EXCCODE_PMC 74 /* Performance Counter */ -#define EXCCODE_TIMER 75 -#define EXCCODE_IPI 76 -#define EXCCODE_NMI 77 -#define EXCCODE_INT_END 78 -#define EXCCODE_INT_NUM (EXCCODE_INT_END - EXCCODE_INT_START) +/* Interrupt numbers */ +#define INT_SWI0 0 /* Software Interrupts */ +#define INT_SWI1 1 +#define INT_HWI0 2 /* Hardware Interrupts */ +#define INT_HWI1 3 +#define INT_HWI2 4 +#define INT_HWI3 5 +#define INT_HWI4 6 +#define INT_HWI5 7 +#define INT_HWI6 8 +#define INT_HWI7 9 +#define INT_PCOV 10 /* Performance Counter Overflow */ +#define INT_TI 11 /* Timer */ +#define INT_IPI 12 +#define INT_NMI 13 + +/* ExcCodes corresponding to interrupts */ +#define EXCCODE_INT_NUM (INT_NMI + 1) +#define EXCCODE_INT_START 64 +#define EXCCODE_INT_END (EXCCODE_INT_START + EXCCODE_INT_NUM - 1) /* FPU register names */ #define LOONGARCH_FCSR0 $r0 diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 0524bf1169b7..883e5066ae44 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -92,7 +92,7 @@ static int __init get_ipi_irq(void) struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); if (d) - return irq_create_mapping(d, EXCCODE_IPI - EXCCODE_INT_START); + return irq_create_mapping(d, INT_IPI); return -EINVAL; } diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c index 707bd32e5c4f..ff28f99b47d7 100644 --- a/arch/loongarch/kernel/perf_event.c +++ b/arch/loongarch/kernel/perf_event.c @@ -461,7 +461,7 @@ static int get_pmc_irq(void) struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); if (d) - return irq_create_mapping(d, EXCCODE_PMC - EXCCODE_INT_START); + return irq_create_mapping(d, INT_PCOV); return -EINVAL; } diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 4351f69d9950..f377e50f3c66 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -133,7 +133,7 @@ static int get_timer_irq(void) struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY); if (d) - return irq_create_mapping(d, EXCCODE_TIMER - EXCCODE_INT_START); + return irq_create_mapping(d, INT_TI); return -EINVAL; } diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index de8ebe20b666..3fb4709c3b19 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -792,7 +792,7 @@ void __init trap_init(void) long i; /* Set interrupt vector handler */ - for (i = EXCCODE_INT_START; i < EXCCODE_INT_END; i++) + for (i = EXCCODE_INT_START; i <= EXCCODE_INT_END; i++) set_handler(i * VECSIZE, handle_vint, VECSIZE); set_handler(EXCCODE_ADE * VECSIZE, handle_ade, VECSIZE); -- GitLab From aa552254cf0039d83908105a07007f9ea616c119 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4344/5631] LoongArch: Define regular names for BCE/WATCH/HVC/GSPR exceptions Define them according to the ISA manual, in order to enable matching the sub-exceptions for humanization purposes later. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/loongarch.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 7d8b83dd32e9..b3323ab5b78d 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -1397,7 +1397,7 @@ __BUILD_CSR_OP(tlbidx) #define EXSUBCODE_ADEF 0 /* Fetch Instruction */ #define EXSUBCODE_ADEM 1 /* Access Memory*/ #define EXCCODE_ALE 9 /* Unalign Access */ -#define EXCCODE_OOB 10 /* Out of bounds */ +#define EXCCODE_BCE 10 /* Bounds Check Error */ #define EXCCODE_SYS 11 /* System call */ #define EXCCODE_BP 12 /* Breakpoint */ #define EXCCODE_INE 13 /* Inst. Not Exist */ @@ -1408,11 +1408,13 @@ __BUILD_CSR_OP(tlbidx) #define EXCCODE_FPE 18 /* Floating Point Exception */ #define EXCSUBCODE_FPE 0 /* Floating Point Exception */ #define EXCSUBCODE_VFPE 1 /* Vector Exception */ -#define EXCCODE_WATCH 19 /* Watch address reference */ +#define EXCCODE_WATCH 19 /* WatchPoint Exception */ + #define EXCSUBCODE_WPEF 0 /* ... on Instruction Fetch */ + #define EXCSUBCODE_WPEM 1 /* ... on Memory Accesses */ #define EXCCODE_BTDIS 20 /* Binary Trans. Disabled */ #define EXCCODE_BTE 21 /* Binary Trans. Exception */ -#define EXCCODE_PSI 22 /* Guest Privileged Error */ -#define EXCCODE_HYP 23 /* Hypercall */ +#define EXCCODE_GSPR 22 /* Guest Privileged Error */ +#define EXCCODE_HVC 23 /* Hypercall */ #define EXCCODE_GCM 24 /* Guest CSR modified */ #define EXCSUBCODE_GCSC 0 /* Software caused */ #define EXCSUBCODE_GCHC 1 /* Hardware caused */ -- GitLab From f6a79b6036ef220028db190c7424ce8099c98090 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4345/5631] LoongArch: Print GPRs with ABI names when showing registers Show PC (CSR.ERA) in place of $zero, and also show the syscall restart flag (conveniently stuffed in regs[0]) if non-zero. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 36 ++++++++++++++++++++++------------- 1 file changed, 23 insertions(+), 13 deletions(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 3fb4709c3b19..57768a6de1cf 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -158,22 +158,32 @@ static void __show_regs(const struct pt_regs *regs) const int field = 2 * sizeof(unsigned long); unsigned int excsubcode; unsigned int exccode; - int i; show_regs_print_info(KERN_DEFAULT); - /* - * Saved main processor registers - */ - for (i = 0; i < 32; ) { - if ((i % 4) == 0) - printk("$%2d :", i); - pr_cont(" %0*lx", field, regs->regs[i]); - - i++; - if ((i % 4) == 0) - pr_cont("\n"); - } + /* Print saved GPRs except $zero (substituting with PC/ERA) */ +#define GPR_FIELD(x) field, regs->regs[x] + printk("pc %0*lx ra %0*lx tp %0*lx sp %0*lx\n", + field, regs->csr_era, GPR_FIELD(1), GPR_FIELD(2), GPR_FIELD(3)); + printk("a0 %0*lx a1 %0*lx a2 %0*lx a3 %0*lx\n", + GPR_FIELD(4), GPR_FIELD(5), GPR_FIELD(6), GPR_FIELD(7)); + printk("a4 %0*lx a5 %0*lx a6 %0*lx a7 %0*lx\n", + GPR_FIELD(8), GPR_FIELD(9), GPR_FIELD(10), GPR_FIELD(11)); + printk("t0 %0*lx t1 %0*lx t2 %0*lx t3 %0*lx\n", + GPR_FIELD(12), GPR_FIELD(13), GPR_FIELD(14), GPR_FIELD(15)); + printk("t4 %0*lx t5 %0*lx t6 %0*lx t7 %0*lx\n", + GPR_FIELD(16), GPR_FIELD(17), GPR_FIELD(18), GPR_FIELD(19)); + printk("t8 %0*lx u0 %0*lx s9 %0*lx s0 %0*lx\n", + GPR_FIELD(20), GPR_FIELD(21), GPR_FIELD(22), GPR_FIELD(23)); + printk("s1 %0*lx s2 %0*lx s3 %0*lx s4 %0*lx\n", + GPR_FIELD(24), GPR_FIELD(25), GPR_FIELD(26), GPR_FIELD(27)); + printk("s5 %0*lx s6 %0*lx s7 %0*lx s8 %0*lx\n", + GPR_FIELD(28), GPR_FIELD(29), GPR_FIELD(30), GPR_FIELD(31)); + + /* The slot for $zero is reused as the syscall restart flag */ + if (regs->regs[0]) + printk("syscall restart flag: %0*lx\n", GPR_FIELD(0)); +#undef GPR_FIELD /* * Saved csr registers -- GitLab From 863b3795efae6458dbc24f03add50c575cf4fbd2 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4346/5631] LoongArch: Print symbol info for $ra and CSR.ERA only for kernel-mode contexts Otherwise the addresses wouldn't make sense at all. While at it, align the "map keys" to maintain right-alignment with the "estat:" line too; also swap the ERA and ra lines so all CSRs are shown together. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 57768a6de1cf..ab08548315b8 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -183,16 +183,19 @@ static void __show_regs(const struct pt_regs *regs) /* The slot for $zero is reused as the syscall restart flag */ if (regs->regs[0]) printk("syscall restart flag: %0*lx\n", GPR_FIELD(0)); + + if (user_mode(regs)) { + printk(" ra: %0*lx\n", GPR_FIELD(1)); + printk(" ERA: %0*lx\n", field, regs->csr_era); + } else { + printk(" ra: %0*lx %pS\n", GPR_FIELD(1), (void *) regs->regs[1]); + printk(" ERA: %0*lx %pS\n", field, regs->csr_era, (void *) regs->csr_era); + } #undef GPR_FIELD /* * Saved csr registers */ - printk("era : %0*lx %pS\n", field, regs->csr_era, - (void *) regs->csr_era); - printk("ra : %0*lx %pS\n", field, regs->regs[1], - (void *) regs->regs[1]); - printk("CSR crmd: %08lx ", regs->csr_crmd); printk("CSR prmd: %08lx ", regs->csr_prmd); printk("CSR euen: %08lx ", regs->csr_euen); -- GitLab From 05fa8d4977d727cf41294ea09b4a5085cba4ad54 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4347/5631] LoongArch: Fix format of CSR lines during show_regs() Use uppercase CSR names throughout for consistency with the manual wording, and right-align the keys. The "CSR" part is inferrable from context, hence dropped for more horizontal space. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index ab08548315b8..434a7717face 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -193,16 +193,12 @@ static void __show_regs(const struct pt_regs *regs) } #undef GPR_FIELD - /* - * Saved csr registers - */ - printk("CSR crmd: %08lx ", regs->csr_crmd); - printk("CSR prmd: %08lx ", regs->csr_prmd); - printk("CSR euen: %08lx ", regs->csr_euen); - printk("CSR ecfg: %08lx ", regs->csr_ecfg); - printk("CSR estat: %08lx ", regs->csr_estat); - - pr_cont("\n"); + /* Print saved important CSRs */ + printk(" CRMD: %08lx\n", regs->csr_crmd); + printk(" PRMD: %08lx\n", regs->csr_prmd); + printk(" EUEN: %08lx\n", regs->csr_euen); + printk(" ECFG: %08lx\n", regs->csr_ecfg); + printk("ESTAT: %08lx\n", regs->csr_estat); exccode = ((regs->csr_estat) & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT; excsubcode = ((regs->csr_estat) & CSR_ESTAT_ESUBCODE) >> CSR_ESTAT_ESUBCODE_SHIFT; -- GitLab From efada2afacee7b5e59b3182bc36ddfb0fad2b0e2 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4348/5631] LoongArch: Humanize the CRMD line when showing registers Example output looks like: [ xx.xxxxxx] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) Some initial machinery for this pretty-printing format has been included in this patch as well. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 51 ++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 434a7717face..97af82547725 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -3,6 +3,7 @@ * Author: Huacai Chen * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ +#include #include #include #include @@ -153,6 +154,54 @@ static void show_code(unsigned int *pc, bool user) pr_cont("\n"); } +static void print_bool_fragment(const char *key, unsigned long val, bool first) +{ + /* e.g. "+PG", "-DA" */ + pr_cont("%s%c%s", first ? "" : " ", val ? '+' : '-', key); +} + +static void print_plv_fragment(const char *key, int val) +{ + /* e.g. "PLV0", "PPLV3" */ + pr_cont("%s%d", key, val); +} + +static void print_memory_type_fragment(const char *key, unsigned long val) +{ + const char *humanized_type; + + switch (val) { + case 0: + humanized_type = "SUC"; + break; + case 1: + humanized_type = "CC"; + break; + case 2: + humanized_type = "WUC"; + break; + default: + pr_cont(" %s=Reserved(%lu)", key, val); + return; + } + + /* e.g. " DATM=WUC" */ + pr_cont(" %s=%s", key, humanized_type); +} + +static void print_crmd(unsigned long x) +{ + printk(" CRMD: %08lx (", x); + print_plv_fragment("PLV", (int) FIELD_GET(CSR_CRMD_PLV, x)); + print_bool_fragment("IE", FIELD_GET(CSR_CRMD_IE, x), false); + print_bool_fragment("DA", FIELD_GET(CSR_CRMD_DA, x), false); + print_bool_fragment("PG", FIELD_GET(CSR_CRMD_PG, x), false); + print_memory_type_fragment("DACF", FIELD_GET(CSR_CRMD_DACF, x)); + print_memory_type_fragment("DACM", FIELD_GET(CSR_CRMD_DACM, x)); + print_bool_fragment("WE", FIELD_GET(CSR_CRMD_WE, x), false); + pr_cont(")\n"); +} + static void __show_regs(const struct pt_regs *regs) { const int field = 2 * sizeof(unsigned long); @@ -194,7 +243,7 @@ static void __show_regs(const struct pt_regs *regs) #undef GPR_FIELD /* Print saved important CSRs */ - printk(" CRMD: %08lx\n", regs->csr_crmd); + print_crmd(regs->csr_crmd); printk(" PRMD: %08lx\n", regs->csr_prmd); printk(" EUEN: %08lx\n", regs->csr_euen); printk(" ECFG: %08lx\n", regs->csr_ecfg); -- GitLab From ce7f0b18b030e17fb3d8327f1b6f1719165ca51d Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:10 +0800 Subject: [PATCH 4349/5631] LoongArch: Humanize the PRMD line when showing registers Example output looks like: [ xx.xxxxxx] PRMD: 00000004 (PPLV0 +PIE -PWE) Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 97af82547725..9f092e1cc782 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -202,6 +202,15 @@ static void print_crmd(unsigned long x) pr_cont(")\n"); } +static void print_prmd(unsigned long x) +{ + printk(" PRMD: %08lx (", x); + print_plv_fragment("PPLV", (int) FIELD_GET(CSR_PRMD_PPLV, x)); + print_bool_fragment("PIE", FIELD_GET(CSR_PRMD_PIE, x), false); + print_bool_fragment("PWE", FIELD_GET(CSR_PRMD_PWE, x), false); + pr_cont(")\n"); +} + static void __show_regs(const struct pt_regs *regs) { const int field = 2 * sizeof(unsigned long); @@ -244,7 +253,7 @@ static void __show_regs(const struct pt_regs *regs) /* Print saved important CSRs */ print_crmd(regs->csr_crmd); - printk(" PRMD: %08lx\n", regs->csr_prmd); + print_prmd(regs->csr_prmd); printk(" EUEN: %08lx\n", regs->csr_euen); printk(" ECFG: %08lx\n", regs->csr_ecfg); printk("ESTAT: %08lx\n", regs->csr_estat); -- GitLab From 9718d96c035c594390600168cbca0ae4e0d867f5 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4350/5631] LoongArch: Humanize the EUEN line when showing registers Example output looks like: [ xx.xxxxxx] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 9f092e1cc782..bd6be798f81d 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -211,6 +211,16 @@ static void print_prmd(unsigned long x) pr_cont(")\n"); } +static void print_euen(unsigned long x) +{ + printk(" EUEN: %08lx (", x); + print_bool_fragment("FPE", FIELD_GET(CSR_EUEN_FPEN, x), true); + print_bool_fragment("SXE", FIELD_GET(CSR_EUEN_LSXEN, x), false); + print_bool_fragment("ASXE", FIELD_GET(CSR_EUEN_LASXEN, x), false); + print_bool_fragment("BTE", FIELD_GET(CSR_EUEN_LBTEN, x), false); + pr_cont(")\n"); +} + static void __show_regs(const struct pt_regs *regs) { const int field = 2 * sizeof(unsigned long); @@ -254,7 +264,7 @@ static void __show_regs(const struct pt_regs *regs) /* Print saved important CSRs */ print_crmd(regs->csr_crmd); print_prmd(regs->csr_prmd); - printk(" EUEN: %08lx\n", regs->csr_euen); + print_euen(regs->csr_euen); printk(" ECFG: %08lx\n", regs->csr_ecfg); printk("ESTAT: %08lx\n", regs->csr_estat); -- GitLab From 5e3e784d35c41ca21251f92c243780c791100b02 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4351/5631] LoongArch: Humanize the ECFG line when showing registers Example output looks like: [ xx.xxxxxx] ECFG: 00071c1c (LIE=2-4,10-12 VS=7) Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index bd6be798f81d..6376997f2ae9 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -189,6 +189,12 @@ static void print_memory_type_fragment(const char *key, unsigned long val) pr_cont(" %s=%s", key, humanized_type); } +static void print_intr_fragment(const char *key, unsigned long val) +{ + /* e.g. "LIE=0-1,3,5-7" */ + pr_cont("%s=%*pbl", key, EXCCODE_INT_NUM, &val); +} + static void print_crmd(unsigned long x) { printk(" CRMD: %08lx (", x); @@ -221,6 +227,13 @@ static void print_euen(unsigned long x) pr_cont(")\n"); } +static void print_ecfg(unsigned long x) +{ + printk(" ECFG: %08lx (", x); + print_intr_fragment("LIE", FIELD_GET(CSR_ECFG_IM, x)); + pr_cont(" VS=%d)\n", (int) FIELD_GET(CSR_ECFG_VS, x)); +} + static void __show_regs(const struct pt_regs *regs) { const int field = 2 * sizeof(unsigned long); @@ -265,7 +278,7 @@ static void __show_regs(const struct pt_regs *regs) print_crmd(regs->csr_crmd); print_prmd(regs->csr_prmd); print_euen(regs->csr_euen); - printk(" ECFG: %08lx\n", regs->csr_ecfg); + print_ecfg(regs->csr_ecfg); printk("ESTAT: %08lx\n", regs->csr_estat); exccode = ((regs->csr_estat) & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT; -- GitLab From 98b90ede59472de5931b7e4d72c3ff948eaa19a4 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4352/5631] LoongArch: Humanize the ESTAT line when showing registers Example output looks like: [ xx.xxxxxx] ESTAT: 00001000 [INT] (IS=12 ECode=0 EsubCode=0) Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 82 ++++++++++++++++++++++++++++++++--- 1 file changed, 75 insertions(+), 7 deletions(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 6376997f2ae9..748fe2f9aed0 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -234,11 +234,83 @@ static void print_ecfg(unsigned long x) pr_cont(" VS=%d)\n", (int) FIELD_GET(CSR_ECFG_VS, x)); } +static const char *humanize_exc_name(unsigned int ecode, unsigned int esubcode) +{ + /* + * LoongArch users and developers are probably more familiar with + * those names found in the ISA manual, so we are going to print out + * the latter. This will require some mapping. + */ + switch (ecode) { + case EXCCODE_RSV: return "INT"; + case EXCCODE_TLBL: return "PIL"; + case EXCCODE_TLBS: return "PIS"; + case EXCCODE_TLBI: return "PIF"; + case EXCCODE_TLBM: return "PME"; + case EXCCODE_TLBNR: return "PNR"; + case EXCCODE_TLBNX: return "PNX"; + case EXCCODE_TLBPE: return "PPI"; + case EXCCODE_ADE: + switch (esubcode) { + case EXSUBCODE_ADEF: return "ADEF"; + case EXSUBCODE_ADEM: return "ADEM"; + } + break; + case EXCCODE_ALE: return "ALE"; + case EXCCODE_BCE: return "BCE"; + case EXCCODE_SYS: return "SYS"; + case EXCCODE_BP: return "BRK"; + case EXCCODE_INE: return "INE"; + case EXCCODE_IPE: return "IPE"; + case EXCCODE_FPDIS: return "FPD"; + case EXCCODE_LSXDIS: return "SXD"; + case EXCCODE_LASXDIS: return "ASXD"; + case EXCCODE_FPE: + switch (esubcode) { + case EXCSUBCODE_FPE: return "FPE"; + case EXCSUBCODE_VFPE: return "VFPE"; + } + break; + case EXCCODE_WATCH: + switch (esubcode) { + case EXCSUBCODE_WPEF: return "WPEF"; + case EXCSUBCODE_WPEM: return "WPEM"; + } + break; + case EXCCODE_BTDIS: return "BTD"; + case EXCCODE_BTE: return "BTE"; + case EXCCODE_GSPR: return "GSPR"; + case EXCCODE_HVC: return "HVC"; + case EXCCODE_GCM: + switch (esubcode) { + case EXCSUBCODE_GCSC: return "GCSC"; + case EXCSUBCODE_GCHC: return "GCHC"; + } + break; + /* + * The manual did not mention the EXCCODE_SE case, but print out it + * nevertheless. + */ + case EXCCODE_SE: return "SE"; + } + + return "???"; +} + +static void print_estat(unsigned long x) +{ + unsigned int ecode = FIELD_GET(CSR_ESTAT_EXC, x); + unsigned int esubcode = FIELD_GET(CSR_ESTAT_ESUBCODE, x); + + printk("ESTAT: %08lx [%s] (", x, humanize_exc_name(ecode, esubcode)); + print_intr_fragment("IS", FIELD_GET(CSR_ESTAT_IS, x)); + pr_cont(" ECode=%d EsubCode=%d)\n", (int) ecode, (int) esubcode); +} + static void __show_regs(const struct pt_regs *regs) { const int field = 2 * sizeof(unsigned long); - unsigned int excsubcode; - unsigned int exccode; + unsigned int exccode = FIELD_GET(CSR_ESTAT_EXC, regs->csr_estat); show_regs_print_info(KERN_DEFAULT); @@ -279,11 +351,7 @@ static void __show_regs(const struct pt_regs *regs) print_prmd(regs->csr_prmd); print_euen(regs->csr_euen); print_ecfg(regs->csr_ecfg); - printk("ESTAT: %08lx\n", regs->csr_estat); - - exccode = ((regs->csr_estat) & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT; - excsubcode = ((regs->csr_estat) & CSR_ESTAT_ESUBCODE) >> CSR_ESTAT_ESUBCODE_SHIFT; - printk("ExcCode : %x (SubCode %x)\n", exccode, excsubcode); + print_estat(regs->csr_estat); if (exccode >= EXCCODE_TLBL && exccode <= EXCCODE_ALE) printk("BadVA : %0*lx\n", field, regs->csr_badvaddr); -- GitLab From 325a38b511caff53c10393bab1e59cbd37f15ec2 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4353/5631] LoongArch: Tweak the BADV and CPUCFG.PRID lines in show_regs() Use ISA manual names for BADV and CPUCFG.PRID lines in show_regs(), for stylistic consistency with the other lines already touched. While at it, also include current CPU's full name in show_regs() output. It may be more helpful for developers looking at the resulting dumps, because multiple distinct CPU models may share the same PRID. Not having this info available may hide problems only found on some but not all of the models sharing one specific PRID. Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/kernel/traps.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 748fe2f9aed0..569c3a5bb052 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -354,10 +354,10 @@ static void __show_regs(const struct pt_regs *regs) print_estat(regs->csr_estat); if (exccode >= EXCCODE_TLBL && exccode <= EXCCODE_ALE) - printk("BadVA : %0*lx\n", field, regs->csr_badvaddr); + printk(" BADV: %0*lx\n", field, regs->csr_badvaddr); - printk("PrId : %08x (%s)\n", read_cpucfg(LOONGARCH_CPUCFG0), - cpu_family_string()); + printk(" PRID: %08x (%s, %s)\n", read_cpucfg(LOONGARCH_CPUCFG0), + cpu_family_string(), cpu_full_name_string()); } void show_regs(struct pt_regs *regs) -- GitLab From c23e7f01cf621290770069d968ca4c8356a50d00 Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4354/5631] LoongArch: Relay BCE exceptions to userland as SIGSEGV with si_code=SEGV_BNDERR SEGV_BNDERR was introduced initially for supporting the Intel MPX, but fell into disuse after the MPX support was removed. The LoongArch bounds-checking instructions behave very differently than MPX, but overall the interface is still kind of suitable for conveying the information to userland when bounds-checking assertions trigger, so we wouldn't have to invent more UAPI. Specifically, when the BCE triggers, a SEGV_BNDERR is sent to userland, with si_addr set to the out-of-bounds address or value (in asrt{gt,le}'s case), and one of si_lower or si_upper set to the configured bound depending on the faulting instruction. The other bound is set to either 0 or ULONG_MAX to resemble a range with both lower and upper bounds. Note that it is possible to have si_addr == si_lower in case of a failing asrtgt or {ld,st}gt, because those instructions test for strict greater-than relationship. This should not pose a problem for userland, though, because the faulting PC is available for the application to associate back to the exact instruction for figuring out the expectation. Example exception context generated by a faulting `asrtgt.d t0, t1` (assert t0 > t1 or BCE) with t0=100 and t1=200: > pc 00005555558206a4 ra 00007ffff2d854fc tp 00007ffff2f2f180 sp 00007ffffbf9fb80 > a0 0000000000000002 a1 00007ffffbf9fce8 a2 00007ffffbf9fd00 a3 00007ffff2ed4558 > a4 0000000000000000 a5 00007ffff2f044c8 a6 00007ffffbf9fce0 a7 fffffffffffff000 > t0 0000000000000064 t1 00000000000000c8 t2 00007ffffbfa2d5e t3 00007ffff2f12aa0 > t4 00007ffff2ed6158 t5 00007ffff2ed6158 t6 000000000000002e t7 0000000003d8f538 > t8 0000000000000005 u0 0000000000000000 s9 0000000000000000 s0 00007ffffbf9fce8 > s1 0000000000000002 s2 0000000000000000 s3 00007ffff2f2c038 s4 0000555555820610 > s5 00007ffff2ed5000 s6 0000555555827e38 s7 00007ffffbf9fd00 s8 0000555555827e38 > ra: 00007ffff2d854fc > ERA: 00005555558206a4 > CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) > PRMD: 00000007 (PPLV3 +PIE -PWE) > EUEN: 00000000 (-FPE -SXE -ASXE -BTE) > ECFG: 0007181c (LIE=2-4,11-12 VS=7) > ESTAT: 000a0000 [BCE] (IS= ECode=10 EsubCode=0) > PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/inst.h | 26 +++++++++ arch/loongarch/kernel/genex.S | 1 + arch/loongarch/kernel/traps.c | 92 +++++++++++++++++++++++++++++++ 3 files changed, 119 insertions(+) diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index a04fe755d719..b09887ffcd15 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -121,6 +121,8 @@ enum reg2bstrd_op { }; enum reg3_op { + asrtle_op = 0x02, + asrtgt_op = 0x03, addw_op = 0x20, addd_op = 0x21, subw_op = 0x22, @@ -176,6 +178,30 @@ enum reg3_op { amord_op = 0x70c7, amxorw_op = 0x70c8, amxord_op = 0x70c9, + fldgts_op = 0x70e8, + fldgtd_op = 0x70e9, + fldles_op = 0x70ea, + fldled_op = 0x70eb, + fstgts_op = 0x70ec, + fstgtd_op = 0x70ed, + fstles_op = 0x70ee, + fstled_op = 0x70ef, + ldgtb_op = 0x70f0, + ldgth_op = 0x70f1, + ldgtw_op = 0x70f2, + ldgtd_op = 0x70f3, + ldleb_op = 0x70f4, + ldleh_op = 0x70f5, + ldlew_op = 0x70f6, + ldled_op = 0x70f7, + stgtb_op = 0x70f8, + stgth_op = 0x70f9, + stgtw_op = 0x70fa, + stgtd_op = 0x70fb, + stleb_op = 0x70fc, + stleh_op = 0x70fd, + stlew_op = 0x70fe, + stled_op = 0x70ff, }; enum reg3sa2_op { diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 44ff1ff64260..78f066384657 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -82,6 +82,7 @@ SYM_FUNC_END(except_vec_cex) BUILD_HANDLER ade ade badv BUILD_HANDLER ale ale badv + BUILD_HANDLER bce bce none BUILD_HANDLER bp bp none BUILD_HANDLER fpe fpe fcsr BUILD_HANDLER fpu fpu none diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 569c3a5bb052..8db26e4ca447 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,7 @@ extern asmlinkage void handle_ade(void); extern asmlinkage void handle_ale(void); +extern asmlinkage void handle_bce(void); extern asmlinkage void handle_sys(void); extern asmlinkage void handle_bp(void); extern asmlinkage void handle_ri(void); @@ -588,6 +590,95 @@ static void bug_handler(struct pt_regs *regs) } } +asmlinkage void noinstr do_bce(struct pt_regs *regs) +{ + bool user = user_mode(regs); + unsigned long era = exception_era(regs); + u64 badv = 0, lower = 0, upper = ULONG_MAX; + union loongarch_instruction insn; + irqentry_state_t state = irqentry_enter(regs); + + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_enable(); + + current->thread.trap_nr = read_csr_excode(); + + die_if_kernel("Bounds check error in kernel code", regs); + + /* + * Pull out the address that failed bounds checking, and the lower / + * upper bound, by minimally looking at the faulting instruction word + * and reading from the correct register. + */ + if (__get_inst(&insn.word, (u32 *)era, user)) + goto bad_era; + + switch (insn.reg3_format.opcode) { + case asrtle_op: + if (insn.reg3_format.rd != 0) + break; /* not asrtle */ + badv = regs->regs[insn.reg3_format.rj]; + upper = regs->regs[insn.reg3_format.rk]; + break; + + case asrtgt_op: + if (insn.reg3_format.rd != 0) + break; /* not asrtgt */ + badv = regs->regs[insn.reg3_format.rj]; + lower = regs->regs[insn.reg3_format.rk]; + break; + + case ldleb_op: + case ldleh_op: + case ldlew_op: + case ldled_op: + case stleb_op: + case stleh_op: + case stlew_op: + case stled_op: + case fldles_op: + case fldled_op: + case fstles_op: + case fstled_op: + badv = regs->regs[insn.reg3_format.rj]; + upper = regs->regs[insn.reg3_format.rk]; + break; + + case ldgtb_op: + case ldgth_op: + case ldgtw_op: + case ldgtd_op: + case stgtb_op: + case stgth_op: + case stgtw_op: + case stgtd_op: + case fldgts_op: + case fldgtd_op: + case fstgts_op: + case fstgtd_op: + badv = regs->regs[insn.reg3_format.rj]; + lower = regs->regs[insn.reg3_format.rk]; + break; + } + + force_sig_bnderr((void __user *)badv, (void __user *)lower, (void __user *)upper); + +out: + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_disable(); + + irqentry_exit(regs, state); + return; + +bad_era: + /* + * Cannot pull out the instruction word, hence cannot provide more + * info than a regular SIGSEGV in this case. + */ + force_sig(SIGSEGV); + goto out; +} + asmlinkage void noinstr do_bp(struct pt_regs *regs) { bool user = user_mode(regs); @@ -955,6 +1046,7 @@ void __init trap_init(void) set_handler(EXCCODE_ADE * VECSIZE, handle_ade, VECSIZE); set_handler(EXCCODE_ALE * VECSIZE, handle_ale, VECSIZE); + set_handler(EXCCODE_BCE * VECSIZE, handle_bce, VECSIZE); set_handler(EXCCODE_SYS * VECSIZE, handle_sys, VECSIZE); set_handler(EXCCODE_BP * VECSIZE, handle_bp, VECSIZE); set_handler(EXCCODE_INE * VECSIZE, handle_ri, VECSIZE); -- GitLab From 2b3bd32ea3a22ea2d5e591da4ac2c2b1fb17c0e0 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 1 May 2023 17:19:27 +0800 Subject: [PATCH 4355/5631] LoongArch: Provide kernel fpu functions Provide kernel_fpu_begin()/kernel_fpu_end() to allow the kernel itself to use fpu. They can be used by some other kernel components, e.g., the AMDGPU graphic driver for DCN. Reported-by: WANG Xuerui Tested-by: WANG Xuerui Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/fpu.h | 3 +++ arch/loongarch/kernel/Makefile | 2 +- arch/loongarch/kernel/kfpu.c | 43 ++++++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+), 1 deletion(-) create mode 100644 arch/loongarch/kernel/kfpu.c diff --git a/arch/loongarch/include/asm/fpu.h b/arch/loongarch/include/asm/fpu.h index 358b254d9c1d..192f8e35d912 100644 --- a/arch/loongarch/include/asm/fpu.h +++ b/arch/loongarch/include/asm/fpu.h @@ -21,6 +21,9 @@ struct sigcontext; +extern void kernel_fpu_begin(void); +extern void kernel_fpu_end(void); + extern void _init_fpu(unsigned int); extern void _save_fp(struct loongarch_fpu *); extern void _restore_fp(struct loongarch_fpu *); diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index 78d4e3384305..9a72d91cd104 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -13,7 +13,7 @@ obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o -obj-$(CONFIG_CPU_HAS_FPU) += fpu.o +obj-$(CONFIG_CPU_HAS_FPU) += fpu.o kfpu.o obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c new file mode 100644 index 000000000000..5c46ae8c6cac --- /dev/null +++ b/arch/loongarch/kernel/kfpu.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +#include +#include +#include +#include + +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +void kernel_fpu_begin(void) +{ + preempt_disable(); + + WARN_ON(this_cpu_read(in_kernel_fpu)); + + this_cpu_write(in_kernel_fpu, true); + + if (!is_fpu_owner()) + enable_fpu(); + else + _save_fp(¤t->thread.fpu); + + write_fcsr(LOONGARCH_FCSR0, 0); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + WARN_ON(!this_cpu_read(in_kernel_fpu)); + + if (!is_fpu_owner()) + disable_fpu(); + else + _restore_fp(¤t->thread.fpu); + + this_cpu_write(in_kernel_fpu, false); + + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); -- GitLab From 8941e93ca5906fcca87dc74255b58054ec4d7868 Mon Sep 17 00:00:00 2001 From: WANG Rui Date: Mon, 1 May 2023 17:19:43 +0800 Subject: [PATCH 4356/5631] LoongArch: Optimize memory ops (memset/memcpy/memmove) To optimize memset()/memcpy()/memmove() and so on, we use a jump table to dispatch cases for short data lengths; and for long data lengths, we split the destination into head part (first 8 bytes), tail part (last 8 bytes) and middle part. The head part and tail part may be at unaligned addresses, while the middle part is always aligned (the middle part is allowed to overlap the head/tail part). In this way, the first and last 8 bytes may be unaligned accesses, but we can make sure the data in the middle is processed at an aligned destination address. We have tested micro-bench[1] on a Loongson-3C5000 16-core machine (2.2GHz): 1. memset | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.191 | 1518.785 | 118.16% | | 8 | 0 | 1 | 696.325 | 1518.937 | 118.14% | | 50 | 0 | 0 | 969.976 | 8053.902 | 730.32% | | 50 | 0 | 1 | 970.034 | 8058.475 | 730.74% | | 300 | 0 | 0 | 5876.612 | 16544.703 | 181.53% | | 300 | 0 | 1 | 5030.849 | 16549.011 | 228.95% | | 1200 | 0 | 0 | 11797.077 | 16752.137 | 42.00% | | 1200 | 0 | 1 | 5687.141 | 16645.233 | 192.68% | | 4000 | 0 | 0 | 15723.27 | 16761.557 | 6.60% | | 4000 | 0 | 1 | 5906.114 | 16732.316 | 183.30% | | 8000 | 0 | 0 | 16751.403 | 16770.002 | 0.11% | | 8000 | 0 | 1 | 5995.449 | 16754.07 | 179.45% | 2. memcpy | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 696.2 | 1670.605 | 139.96% | | 8 | 0 | 1 | 696.325 | 1671.138 | 139.99% | | 50 | 0 | 0 | 969.974 | 8724.999 | 799.51% | | 50 | 0 | 1 | 970.032 | 8730.138 | 799.98% | | 300 | 0 | 0 | 5564.662 | 16272.652 | 192.43% | | 300 | 0 | 1 | 4670.436 | 14972.842 | 220.59% | | 1200 | 0 | 0 | 10740.23 | 16751.728 | 55.97% | | 1200 | 0 | 1 | 5027.741 | 14874.564 | 195.85% | | 4000 | 0 | 0 | 15122.367 | 16737.642 | 10.68% | | 4000 | 0 | 1 | 5536.918 | 14890.397 | 168.93% | | 8000 | 0 | 0 | 16505.453 | 16553.543 | 0.29% | | 8000 | 0 | 1 | 5821.619 | 14841.804 | 154.94% | 3. memmove | length | src offset | dst offset | speed before | speed after | % | |--------|------------|------------|--------------|-------------|---------| | 8 | 0 | 0 | 982.693 | 1670.568 | 70.00% | | 8 | 0 | 1 | 983.023 | 1671.174 | 70.00% | | 50 | 0 | 0 | 1230.87 | 8727.625 | 609.06% | | 50 | 0 | 1 | 1232.515 | 8730.138 | 608.32% | | 300 | 0 | 0 | 6490.375 | 16296.993 | 151.09% | | 300 | 0 | 1 | 4282.687 | 14972.842 | 249.61% | | 1200 | 0 | 0 | 11742.755 | 16752.546 | 42.66% | | 1200 | 0 | 1 | 5039.338 | 14872.951 | 195.14% | | 4000 | 0 | 0 | 15467.786 | 16737.09 | 8.21% | | 4000 | 0 | 1 | 5009.905 | 14890.542 | 197.22% | | 8000 | 0 | 0 | 16489.664 | 16553.273 | 0.39% | | 8000 | 0 | 1 | 5823.786 | 14858.646 | 155.14% | * speed: MB/s * length: byte [1] https://github.com/heiher/mem-bench Signed-off-by: WANG Rui Signed-off-by: Huacai Chen --- arch/loongarch/lib/clear_user.S | 136 +++++++++++++++-- arch/loongarch/lib/copy_user.S | 251 +++++++++++++++++++++++++------- arch/loongarch/lib/memcpy.S | 147 +++++++++++++++---- arch/loongarch/lib/memmove.S | 120 ++++++++------- arch/loongarch/lib/memset.S | 116 ++++++++++++--- 5 files changed, 603 insertions(+), 167 deletions(-) diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S index 2dc48e61a2c8..fd1d62b244f2 100644 --- a/arch/loongarch/lib/clear_user.S +++ b/arch/loongarch/lib/clear_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a1, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a1, -\to jr ra .endr @@ -44,7 +51,7 @@ SYM_FUNC_START(__clear_user_generic) 2: move a0, a1 jr ra - _asm_extable 1b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_generic) /* @@ -54,12 +61,21 @@ SYM_FUNC_END(__clear_user_generic) * a1: size */ SYM_FUNC_START(__clear_user_fast) - beqz a1, 10f + sltui t0, a1, 9 + bnez t0, .Lsmall - ori a2, zero, 64 - blt a1, a2, 9f + add.d a2, a0, a1 +0: st.d zero, a0, 0 + + /* align up address */ + addi.d a0, a0, 8 + bstrins.d a0, zero, 2, 0 + + addi.d a3, a2, -64 + bgeu a0, a3, .Llt64 /* set 64 bytes at a time */ +.Lloop64: 1: st.d zero, a0, 0 2: st.d zero, a0, 8 3: st.d zero, a0, 16 @@ -68,24 +84,95 @@ SYM_FUNC_START(__clear_user_fast) 6: st.d zero, a0, 40 7: st.d zero, a0, 48 8: st.d zero, a0, 56 - addi.d a0, a0, 64 - addi.d a1, a1, -64 - bge a1, a2, 1b - - beqz a1, 10f + bltu a0, a3, .Lloop64 /* set the remaining bytes */ -9: st.b zero, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, -1 - bgt a1, zero, 9b +.Llt64: + addi.d a3, a2, -32 + bgeu a0, a3, .Llt32 +9: st.d zero, a0, 0 +10: st.d zero, a0, 8 +11: st.d zero, a0, 16 +12: st.d zero, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a3, a2, -16 + bgeu a0, a3, .Llt16 +13: st.d zero, a0, 0 +14: st.d zero, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a3, a2, -8 + bgeu a0, a3, .Llt8 +15: st.d zero, a0, 0 + +.Llt8: +16: st.d zero, a2, -8 /* return */ -10: move a0, a1 + move a0, zero + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a1, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 + move a0, zero + jr ra + + .align 4 +17: st.b zero, a0, 0 + move a0, zero + jr ra + + .align 4 +18: st.h zero, a0, 0 + move a0, zero + jr ra + + .align 4 +19: st.h zero, a0, 0 +20: st.b zero, a0, 2 + move a0, zero + jr ra + + .align 4 +21: st.w zero, a0, 0 + move a0, zero + jr ra + + .align 4 +22: st.w zero, a0, 0 +23: st.b zero, a0, 4 + move a0, zero + jr ra + + .align 4 +24: st.w zero, a0, 0 +25: st.h zero, a0, 4 + move a0, zero + jr ra + + .align 4 +26: st.w zero, a0, 0 +27: st.w zero, a0, 3 + move a0, zero + jr ra + + .align 4 +28: st.d zero, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 _asm_extable 2b, .L_fixup_handle_1 _asm_extable 3b, .L_fixup_handle_2 @@ -95,4 +182,23 @@ SYM_FUNC_START(__clear_user_fast) _asm_extable 7b, .L_fixup_handle_6 _asm_extable 8b, .L_fixup_handle_7 _asm_extable 9b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_1 + _asm_extable 11b, .L_fixup_handle_2 + _asm_extable 12b, .L_fixup_handle_3 + _asm_extable 13b, .L_fixup_handle_0 + _asm_extable 14b, .L_fixup_handle_1 + _asm_extable 15b, .L_fixup_handle_0 + _asm_extable 16b, .L_fixup_handle_1 + _asm_extable 17b, .L_fixup_handle_s0 + _asm_extable 18b, .L_fixup_handle_s0 + _asm_extable 19b, .L_fixup_handle_s0 + _asm_extable 20b, .L_fixup_handle_s2 + _asm_extable 21b, .L_fixup_handle_s0 + _asm_extable 22b, .L_fixup_handle_s0 + _asm_extable 23b, .L_fixup_handle_s4 + _asm_extable 24b, .L_fixup_handle_s0 + _asm_extable 25b, .L_fixup_handle_s4 + _asm_extable 26b, .L_fixup_handle_s0 + _asm_extable 27b, .L_fixup_handle_s4 + _asm_extable 28b, .L_fixup_handle_s0 SYM_FUNC_END(__clear_user_fast) diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S index 55ac6020a1ad..b21f6d5d38f5 100644 --- a/arch/loongarch/lib/copy_user.S +++ b/arch/loongarch/lib/copy_user.S @@ -13,7 +13,14 @@ .irp to, 0, 1, 2, 3, 4, 5, 6, 7 .L_fixup_handle_\to\(): - addi.d a0, a2, (\to) * (-8) + sub.d a0, a2, a0 + addi.d a0, a0, (\to) * (-8) + jr ra +.endr + +.irp to, 0, 2, 4 +.L_fixup_handle_s\to\(): + addi.d a0, a2, -\to jr ra .endr @@ -47,8 +54,8 @@ SYM_FUNC_START(__copy_user_generic) 3: move a0, a2 jr ra - _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 1b, .L_fixup_handle_s0 + _asm_extable 2b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_generic) /* @@ -59,65 +66,209 @@ SYM_FUNC_END(__copy_user_generic) * a2: n */ SYM_FUNC_START(__copy_user_fast) - beqz a2, 19f + sltui t0, a2, 9 + bnez t0, .Lsmall - ori a3, zero, 64 - blt a2, a3, 17f + add.d a3, a1, a2 + add.d a2, a0, a2 +0: ld.d t0, a1, 0 +1: st.d t0, a0, 0 - /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 -2: ld.d t1, a1, 8 -3: ld.d t2, a1, 16 -4: ld.d t3, a1, 24 -5: ld.d t4, a1, 32 -6: ld.d t5, a1, 40 -7: ld.d t6, a1, 48 -8: ld.d t7, a1, 56 -9: st.d t0, a0, 0 -10: st.d t1, a0, 8 -11: st.d t2, a0, 16 -12: st.d t3, a0, 24 -13: st.d t4, a0, 32 -14: st.d t5, a0, 40 -15: st.d t6, a0, 48 -16: st.d t7, a0, 56 + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a0, a0, t0 - addi.d a0, a0, 64 - addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a3, 1b + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 - beqz a2, 19f + /* copy 64 bytes at a time */ +.Lloop64: +2: ld.d t0, a1, 0 +3: ld.d t1, a1, 8 +4: ld.d t2, a1, 16 +5: ld.d t3, a1, 24 +6: ld.d t4, a1, 32 +7: ld.d t5, a1, 40 +8: ld.d t6, a1, 48 +9: ld.d t7, a1, 56 + addi.d a1, a1, 64 +10: st.d t0, a0, 0 +11: st.d t1, a0, 8 +12: st.d t2, a0, 16 +13: st.d t3, a0, 24 +14: st.d t4, a0, 32 +15: st.d t5, a0, 40 +16: st.d t6, a0, 48 +17: st.d t7, a0, 56 + addi.d a0, a0, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -17: ld.b t0, a1, 0 -18: st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 17b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 +18: ld.d t0, a1, 0 +19: ld.d t1, a1, 8 +20: ld.d t2, a1, 16 +21: ld.d t3, a1, 24 + addi.d a1, a1, 32 +22: st.d t0, a0, 0 +23: st.d t1, a0, 8 +24: st.d t2, a0, 16 +25: st.d t3, a0, 24 + addi.d a0, a0, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 +26: ld.d t0, a1, 0 +27: ld.d t1, a1, 8 + addi.d a1, a1, 16 +28: st.d t0, a0, 0 +29: st.d t1, a0, 8 + addi.d a0, a0, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 +30: ld.d t0, a1, 0 +31: st.d t0, a0, 0 + +.Llt8: +32: ld.d t0, a3, -8 +33: st.d t0, a2, -8 /* return */ -19: move a0, a2 + move a0, zero + jr ra + + .align 5 +.Lsmall: + pcaddi t0, 8 + slli.d a3, a2, 5 + add.d t0, t0, a3 + jr t0 + + .align 5 + move a0, zero + jr ra + + .align 5 +34: ld.b t0, a1, 0 +35: st.b t0, a0, 0 + move a0, zero + jr ra + + .align 5 +36: ld.h t0, a1, 0 +37: st.h t0, a0, 0 + move a0, zero + jr ra + + .align 5 +38: ld.h t0, a1, 0 +39: ld.b t1, a1, 2 +40: st.h t0, a0, 0 +41: st.b t1, a0, 2 + move a0, zero + jr ra + + .align 5 +42: ld.w t0, a1, 0 +43: st.w t0, a0, 0 + move a0, zero + jr ra + + .align 5 +44: ld.w t0, a1, 0 +45: ld.b t1, a1, 4 +46: st.w t0, a0, 0 +47: st.b t1, a0, 4 + move a0, zero + jr ra + + .align 5 +48: ld.w t0, a1, 0 +49: ld.h t1, a1, 4 +50: st.w t0, a0, 0 +51: st.h t1, a0, 4 + move a0, zero + jr ra + + .align 5 +52: ld.w t0, a1, 0 +53: ld.w t1, a1, 3 +54: st.w t0, a0, 0 +55: st.w t1, a0, 3 + move a0, zero + jr ra + + .align 5 +56: ld.d t0, a1, 0 +57: st.d t0, a0, 0 + move a0, zero jr ra /* fixup and ex_table */ + _asm_extable 0b, .L_fixup_handle_0 _asm_extable 1b, .L_fixup_handle_0 - _asm_extable 2b, .L_fixup_handle_1 - _asm_extable 3b, .L_fixup_handle_2 - _asm_extable 4b, .L_fixup_handle_3 - _asm_extable 5b, .L_fixup_handle_4 - _asm_extable 6b, .L_fixup_handle_5 - _asm_extable 7b, .L_fixup_handle_6 - _asm_extable 8b, .L_fixup_handle_7 + _asm_extable 2b, .L_fixup_handle_0 + _asm_extable 3b, .L_fixup_handle_0 + _asm_extable 4b, .L_fixup_handle_0 + _asm_extable 5b, .L_fixup_handle_0 + _asm_extable 6b, .L_fixup_handle_0 + _asm_extable 7b, .L_fixup_handle_0 + _asm_extable 8b, .L_fixup_handle_0 _asm_extable 9b, .L_fixup_handle_0 - _asm_extable 10b, .L_fixup_handle_1 - _asm_extable 11b, .L_fixup_handle_2 - _asm_extable 12b, .L_fixup_handle_3 - _asm_extable 13b, .L_fixup_handle_4 - _asm_extable 14b, .L_fixup_handle_5 - _asm_extable 15b, .L_fixup_handle_6 - _asm_extable 16b, .L_fixup_handle_7 - _asm_extable 17b, .L_fixup_handle_0 + _asm_extable 10b, .L_fixup_handle_0 + _asm_extable 11b, .L_fixup_handle_1 + _asm_extable 12b, .L_fixup_handle_2 + _asm_extable 13b, .L_fixup_handle_3 + _asm_extable 14b, .L_fixup_handle_4 + _asm_extable 15b, .L_fixup_handle_5 + _asm_extable 16b, .L_fixup_handle_6 + _asm_extable 17b, .L_fixup_handle_7 _asm_extable 18b, .L_fixup_handle_0 + _asm_extable 19b, .L_fixup_handle_0 + _asm_extable 20b, .L_fixup_handle_0 + _asm_extable 21b, .L_fixup_handle_0 + _asm_extable 22b, .L_fixup_handle_0 + _asm_extable 23b, .L_fixup_handle_1 + _asm_extable 24b, .L_fixup_handle_2 + _asm_extable 25b, .L_fixup_handle_3 + _asm_extable 26b, .L_fixup_handle_0 + _asm_extable 27b, .L_fixup_handle_0 + _asm_extable 28b, .L_fixup_handle_0 + _asm_extable 29b, .L_fixup_handle_1 + _asm_extable 30b, .L_fixup_handle_0 + _asm_extable 31b, .L_fixup_handle_0 + _asm_extable 32b, .L_fixup_handle_0 + _asm_extable 33b, .L_fixup_handle_1 + _asm_extable 34b, .L_fixup_handle_s0 + _asm_extable 35b, .L_fixup_handle_s0 + _asm_extable 36b, .L_fixup_handle_s0 + _asm_extable 37b, .L_fixup_handle_s0 + _asm_extable 38b, .L_fixup_handle_s0 + _asm_extable 39b, .L_fixup_handle_s0 + _asm_extable 40b, .L_fixup_handle_s0 + _asm_extable 41b, .L_fixup_handle_s2 + _asm_extable 42b, .L_fixup_handle_s0 + _asm_extable 43b, .L_fixup_handle_s0 + _asm_extable 44b, .L_fixup_handle_s0 + _asm_extable 45b, .L_fixup_handle_s0 + _asm_extable 46b, .L_fixup_handle_s0 + _asm_extable 47b, .L_fixup_handle_s4 + _asm_extable 48b, .L_fixup_handle_s0 + _asm_extable 49b, .L_fixup_handle_s0 + _asm_extable 50b, .L_fixup_handle_s0 + _asm_extable 51b, .L_fixup_handle_s4 + _asm_extable 52b, .L_fixup_handle_s0 + _asm_extable 53b, .L_fixup_handle_s0 + _asm_extable 54b, .L_fixup_handle_s0 + _asm_extable 55b, .L_fixup_handle_s4 + _asm_extable 56b, .L_fixup_handle_s0 + _asm_extable 57b, .L_fixup_handle_s0 SYM_FUNC_END(__copy_user_fast) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 3b7e1dec7109..39ce6621c704 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -44,6 +44,66 @@ SYM_FUNC_START(__memcpy_generic) SYM_FUNC_END(__memcpy_generic) _ASM_NOKPROBE(__memcpy_generic) + .align 5 +SYM_FUNC_START_NOALIGN(__memcpy_small) + pcaddi t0, 8 + slli.d a2, a2, 5 + add.d t0, t0, a2 + jr t0 + + .align 5 +0: jr ra + + .align 5 +1: ld.b t0, a1, 0 + st.b t0, a0, 0 + jr ra + + .align 5 +2: ld.h t0, a1, 0 + st.h t0, a0, 0 + jr ra + + .align 5 +3: ld.h t0, a1, 0 + ld.b t1, a1, 2 + st.h t0, a0, 0 + st.b t1, a0, 2 + jr ra + + .align 5 +4: ld.w t0, a1, 0 + st.w t0, a0, 0 + jr ra + + .align 5 +5: ld.w t0, a1, 0 + ld.b t1, a1, 4 + st.w t0, a0, 0 + st.b t1, a0, 4 + jr ra + + .align 5 +6: ld.w t0, a1, 0 + ld.h t1, a1, 4 + st.w t0, a0, 0 + st.h t1, a0, 4 + jr ra + + .align 5 +7: ld.w t0, a1, 0 + ld.w t1, a1, 3 + st.w t0, a0, 0 + st.w t1, a0, 3 + jr ra + + .align 5 +8: ld.d t0, a1, 0 + st.d t0, a0, 0 + jr ra +SYM_FUNC_END(__memcpy_small) +_ASM_NOKPROBE(__memcpy_small) + /* * void *__memcpy_fast(void *dst, const void *src, size_t n) * @@ -52,14 +112,27 @@ _ASM_NOKPROBE(__memcpy_generic) * a2: n */ SYM_FUNC_START(__memcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small + + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a0, 7 + sub.d t0, zero, t1 + addi.d t0, t0, 8 + add.d a1, a1, t0 + add.d a5, a0, t0 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a3, -64 + bgeu a1, a4, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, 0 +.Lloop64: + ld.d t0, a1, 0 ld.d t1, a1, 8 ld.d t2, a1, 16 ld.d t3, a1, 24 @@ -67,32 +140,54 @@ SYM_FUNC_START(__memcpy_fast) ld.d t5, a1, 40 ld.d t6, a1, 48 ld.d t7, a1, 56 - st.d t0, a0, 0 - st.d t1, a0, 8 - st.d t2, a0, 16 - st.d t3, a0, 24 - st.d t4, a0, 32 - st.d t5, a0, 40 - st.d t6, a0, 48 - st.d t7, a0, 56 - - addi.d a0, a0, 64 addi.d a1, a1, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + st.d t4, a5, 32 + st.d t5, a5, 40 + st.d t6, a5, 48 + st.d t7, a5, 56 + addi.d a5, a5, 64 + bltu a1, a4, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, 0 - st.b t0, a0, 0 - addi.d a0, a0, 1 - addi.d a1, a1, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a3, -32 + bgeu a1, a4, .Llt32 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + ld.d t2, a1, 16 + ld.d t3, a1, 24 + addi.d a1, a1, 32 + st.d t0, a5, 0 + st.d t1, a5, 8 + st.d t2, a5, 16 + st.d t3, a5, 24 + addi.d a5, a5, 32 + +.Llt32: + addi.d a4, a3, -16 + bgeu a1, a4, .Llt16 + ld.d t0, a1, 0 + ld.d t1, a1, 8 + addi.d a1, a1, 16 + st.d t0, a5, 0 + st.d t1, a5, 8 + addi.d a5, a5, 16 + +.Llt16: + addi.d a4, a3, -8 + bgeu a1, a4, .Llt8 + ld.d t0, a1, 0 + st.d t0, a5, 0 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__memcpy_fast) _ASM_NOKPROBE(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index b796c3d6da05..45b725ba7867 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -11,23 +11,9 @@ #include SYM_FUNC_START(memmove) - blt a0, a1, 1f /* dst < src, memcpy */ - blt a1, a0, 3f /* src < dst, rmemcpy */ + blt a0, a1, memcpy /* dst < src, memcpy */ + blt a1, a0, rmemcpy /* src < dst, rmemcpy */ jr ra /* dst == src, return */ - - /* if (src - dst) < 64, copy 1 byte at a time */ -1: ori a3, zero, 64 - sub.d t0, a1, a0 - blt t0, a3, 2f - b memcpy -2: b __memcpy_generic - - /* if (dst - src) < 64, copy 1 byte at a time */ -3: ori a3, zero, 64 - sub.d t0, a0, a1 - blt t0, a3, 4f - b rmemcpy -4: b __rmemcpy_generic SYM_FUNC_END(memmove) _ASM_NOKPROBE(memmove) @@ -76,50 +62,80 @@ _ASM_NOKPROBE(__rmemcpy_generic) * a2: n */ SYM_FUNC_START(__rmemcpy_fast) - move a3, a0 - beqz a2, 3f + sltui t0, a2, 9 + bnez t0, __memcpy_small - add.d a0, a0, a2 - add.d a1, a1, a2 + add.d a3, a1, a2 + add.d a2, a0, a2 + ld.d a6, a1, 0 + ld.d a7, a3, -8 + + /* align up destination address */ + andi t1, a2, 7 + sub.d a3, a3, t1 + sub.d a5, a2, t1 - ori a4, zero, 64 - blt a2, a4, 2f + addi.d a4, a1, 64 + bgeu a4, a3, .Llt64 /* copy 64 bytes at a time */ -1: ld.d t0, a1, -8 - ld.d t1, a1, -16 - ld.d t2, a1, -24 - ld.d t3, a1, -32 - ld.d t4, a1, -40 - ld.d t5, a1, -48 - ld.d t6, a1, -56 - ld.d t7, a1, -64 - st.d t0, a0, -8 - st.d t1, a0, -16 - st.d t2, a0, -24 - st.d t3, a0, -32 - st.d t4, a0, -40 - st.d t5, a0, -48 - st.d t6, a0, -56 - st.d t7, a0, -64 - - addi.d a0, a0, -64 - addi.d a1, a1, -64 - addi.d a2, a2, -64 - bge a2, a4, 1b - - beqz a2, 3f +.Lloop64: + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + ld.d t4, a3, -40 + ld.d t5, a3, -48 + ld.d t6, a3, -56 + ld.d t7, a3, -64 + addi.d a3, a3, -64 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + st.d t4, a5, -40 + st.d t5, a5, -48 + st.d t6, a5, -56 + st.d t7, a5, -64 + addi.d a5, a5, -64 + bltu a4, a3, .Lloop64 /* copy the remaining bytes */ -2: ld.b t0, a1, -1 - st.b t0, a0, -1 - addi.d a0, a0, -1 - addi.d a1, a1, -1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a1, 32 + bgeu a4, a3, .Llt32 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + ld.d t2, a3, -24 + ld.d t3, a3, -32 + addi.d a3, a3, -32 + st.d t0, a5, -8 + st.d t1, a5, -16 + st.d t2, a5, -24 + st.d t3, a5, -32 + addi.d a5, a5, -32 + +.Llt32: + addi.d a4, a1, 16 + bgeu a4, a3, .Llt16 + ld.d t0, a3, -8 + ld.d t1, a3, -16 + addi.d a3, a3, -16 + st.d t0, a5, -8 + st.d t1, a5, -16 + addi.d a5, a5, -16 + +.Llt16: + addi.d a4, a1, 8 + bgeu a4, a3, .Llt8 + ld.d t0, a3, -8 + st.d t0, a5, -8 + +.Llt8: + st.d a6, a0, 0 + st.d a7, a2, -8 /* return */ -3: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_fast) _ASM_NOKPROBE(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index a9eb732ab2ad..b39c6194e3ae 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -56,39 +56,107 @@ _ASM_NOKPROBE(__memset_generic) * a2: n */ SYM_FUNC_START(__memset_fast) - move a3, a0 - beqz a2, 3f - - ori a4, zero, 64 - blt a2, a4, 2f - /* fill a1 to 64 bits */ fill_to_64 a1 - /* set 64 bytes at a time */ -1: st.d a1, a0, 0 - st.d a1, a0, 8 - st.d a1, a0, 16 - st.d a1, a0, 24 - st.d a1, a0, 32 - st.d a1, a0, 40 - st.d a1, a0, 48 - st.d a1, a0, 56 + sltui t0, a2, 9 + bnez t0, .Lsmall - addi.d a0, a0, 64 - addi.d a2, a2, -64 - bge a2, a4, 1b + add.d a2, a0, a2 + st.d a1, a0, 0 - beqz a2, 3f + /* align up address */ + addi.d a3, a0, 8 + bstrins.d a3, zero, 2, 0 + + addi.d a4, a2, -64 + bgeu a3, a4, .Llt64 + + /* set 64 bytes at a time */ +.Lloop64: + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + st.d a1, a3, 32 + st.d a1, a3, 40 + st.d a1, a3, 48 + st.d a1, a3, 56 + addi.d a3, a3, 64 + bltu a3, a4, .Lloop64 /* set the remaining bytes */ -2: st.b a1, a0, 0 - addi.d a0, a0, 1 - addi.d a2, a2, -1 - bgt a2, zero, 2b +.Llt64: + addi.d a4, a2, -32 + bgeu a3, a4, .Llt32 + st.d a1, a3, 0 + st.d a1, a3, 8 + st.d a1, a3, 16 + st.d a1, a3, 24 + addi.d a3, a3, 32 + +.Llt32: + addi.d a4, a2, -16 + bgeu a3, a4, .Llt16 + st.d a1, a3, 0 + st.d a1, a3, 8 + addi.d a3, a3, 16 + +.Llt16: + addi.d a4, a2, -8 + bgeu a3, a4, .Llt8 + st.d a1, a3, 0 + +.Llt8: + st.d a1, a2, -8 /* return */ -3: move a0, a3 + jr ra + + .align 4 +.Lsmall: + pcaddi t0, 4 + slli.d a2, a2, 4 + add.d t0, t0, a2 + jr t0 + + .align 4 +0: jr ra + + .align 4 +1: st.b a1, a0, 0 + jr ra + + .align 4 +2: st.h a1, a0, 0 + jr ra + + .align 4 +3: st.h a1, a0, 0 + st.b a1, a0, 2 + jr ra + + .align 4 +4: st.w a1, a0, 0 + jr ra + + .align 4 +5: st.w a1, a0, 0 + st.b a1, a0, 4 + jr ra + + .align 4 +6: st.w a1, a0, 0 + st.h a1, a0, 4 + jr ra + + .align 4 +7: st.w a1, a0, 0 + st.w a1, a0, 3 + jr ra + + .align 4 +8: st.d a1, a0, 0 jr ra SYM_FUNC_END(__memset_fast) _ASM_NOKPROBE(__memset_fast) -- GitLab From 69e3a6aa6be21de6aaf38130fad97ecde34a193c Mon Sep 17 00:00:00 2001 From: Bibo Mao Date: Mon, 1 May 2023 17:19:43 +0800 Subject: [PATCH 4357/5631] LoongArch: Add checksum optimization for 64-bit system LoongArch platform is 64-bit system, which supports 8-bytes memory accessing, but generic checksum functions use 4-byte memory access. So add 8-bytes memory access optimization for checksum functions on LoongArch. And the code comes from arm64 system. When network hw checksum is disabled, iperf performance improves about 10% with this patch. Signed-off-by: Bibo Mao Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/checksum.h | 66 ++++++++++++ arch/loongarch/lib/Makefile | 2 +- arch/loongarch/lib/csum.c | 141 ++++++++++++++++++++++++++ 3 files changed, 208 insertions(+), 1 deletion(-) create mode 100644 arch/loongarch/include/asm/checksum.h create mode 100644 arch/loongarch/lib/csum.c diff --git a/arch/loongarch/include/asm/checksum.h b/arch/loongarch/include/asm/checksum.h new file mode 100644 index 000000000000..cabbf6af44c4 --- /dev/null +++ b/arch/loongarch/include/asm/checksum.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2016 ARM Ltd. + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ +#ifndef __ASM_CHECKSUM_H +#define __ASM_CHECKSUM_H + +#include +#include + +#define _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum); + +/* + * turns a 32-bit partial checksum (e.g. from csum_partial) into a + * 1's complement 16-bit checksum. + */ +static inline __sum16 csum_fold(__wsum sum) +{ + u32 tmp = (__force u32)sum; + + /* + * swap the two 16-bit halves of sum + * if there is a carry from adding the two 16-bit halves, + * it will carry from the lower half into the upper half, + * giving us the correct sum in the upper half. + */ + return (__force __sum16)(~(tmp + rol32(tmp, 16)) >> 16); +} +#define csum_fold csum_fold + +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. ihl is the number + * of 32-bit words and is always >= 5. + */ +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + u64 sum; + __uint128_t tmp; + int n = ihl; /* we want it signed */ + + tmp = *(const __uint128_t *)iph; + iph += 16; + n -= 4; + tmp += ((tmp >> 64) | (tmp << 64)); + sum = tmp >> 64; + do { + sum += *(const u32 *)iph; + iph += 4; + } while (--n > 0); + + sum += ror64(sum, 32); + return csum_fold((__force __wsum)(sum >> 32)); +} +#define ip_fast_csum ip_fast_csum + +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + +#include + +#endif /* __ASM_CHECKSUM_H */ diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index 40bde632900f..271ed45f51bb 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -4,4 +4,4 @@ # lib-y += delay.o memset.o memcpy.o memmove.o \ - clear_user.o copy_user.o dump_tlb.o unaligned.o + clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c new file mode 100644 index 000000000000..a5e84b403c3b --- /dev/null +++ b/arch/loongarch/lib/csum.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2019-2020 Arm Ltd. + +#include +#include +#include + +#include + +static u64 accumulate(u64 sum, u64 data) +{ + sum += data; + if (sum < data) + sum += 1; + return sum; +} + +/* + * We over-read the buffer and this makes KASAN unhappy. Instead, disable + * instrumentation and call kasan explicitly. + */ +unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) +{ + unsigned int offset, shift, sum; + const u64 *ptr; + u64 data, sum64 = 0; + + if (unlikely(len == 0)) + return 0; + + offset = (unsigned long)buff & 7; + /* + * This is to all intents and purposes safe, since rounding down cannot + * result in a different page or cache line being accessed, and @buff + * should absolutely not be pointing to anything read-sensitive. We do, + * however, have to be careful not to piss off KASAN, which means using + * unchecked reads to accommodate the head and tail, for which we'll + * compensate with an explicit check up-front. + */ + kasan_check_read(buff, len); + ptr = (u64 *)(buff - offset); + len = len + offset - 8; + + /* + * Head: zero out any excess leading bytes. Shifting back by the same + * amount should be at least as fast as any other way of handling the + * odd/even alignment, and means we can ignore it until the very end. + */ + shift = offset * 8; + data = *ptr++; + data = (data >> shift) << shift; + + /* + * Body: straightforward aligned loads from here on (the paired loads + * underlying the quadword type still only need dword alignment). The + * main loop strictly excludes the tail, so the second loop will always + * run at least once. + */ + while (unlikely(len > 64)) { + __uint128_t tmp1, tmp2, tmp3, tmp4; + + tmp1 = *(__uint128_t *)ptr; + tmp2 = *(__uint128_t *)(ptr + 2); + tmp3 = *(__uint128_t *)(ptr + 4); + tmp4 = *(__uint128_t *)(ptr + 6); + + len -= 64; + ptr += 8; + + /* This is the "don't dump the carry flag into a GPR" idiom */ + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp2 += (tmp2 >> 64) | (tmp2 << 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp4 += (tmp4 >> 64) | (tmp4 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp2 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp3 = ((tmp3 >> 64) << 64) | (tmp4 >> 64); + tmp3 += (tmp3 >> 64) | (tmp3 << 64); + tmp1 = ((tmp1 >> 64) << 64) | (tmp3 >> 64); + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + tmp1 = ((tmp1 >> 64) << 64) | sum64; + tmp1 += (tmp1 >> 64) | (tmp1 << 64); + sum64 = tmp1 >> 64; + } + while (len > 8) { + __uint128_t tmp; + + sum64 = accumulate(sum64, data); + tmp = *(__uint128_t *)ptr; + + len -= 16; + ptr += 2; + + data = tmp >> 64; + sum64 = accumulate(sum64, tmp); + } + if (len > 0) { + sum64 = accumulate(sum64, data); + data = *ptr; + len -= 8; + } + /* + * Tail: zero any over-read bytes similarly to the head, again + * preserving odd/even alignment. + */ + shift = len * -8; + data = (data << shift) >> shift; + sum64 = accumulate(sum64, data); + + /* Finally, folding */ + sum64 += (sum64 >> 32) | (sum64 << 32); + sum = sum64 >> 32; + sum += (sum >> 16) | (sum << 16); + if (offset & 1) + return (u16)swab32(sum); + + return sum >> 16; +} + +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + __uint128_t src, dst; + u64 sum = (__force u64)csum; + + src = *(const __uint128_t *)saddr->s6_addr; + dst = *(const __uint128_t *)daddr->s6_addr; + + sum += (__force u32)htonl(len); + sum += (u32)proto << 24; + src += (src >> 64) | (src << 64); + dst += (dst >> 64) | (dst << 64); + + sum = accumulate(sum, src >> 64); + sum = accumulate(sum, dst >> 64); + + sum += ((sum >> 32) | (sum << 32)); + return csum_fold((__force __wsum)(sum >> 32)); +} +EXPORT_SYMBOL(csum_ipv6_magic); -- GitLab From 2f1648220214d18168e55920c21014e71c2d5bbc Mon Sep 17 00:00:00 2001 From: Min Zhou Date: Mon, 1 May 2023 17:19:43 +0800 Subject: [PATCH 4358/5631] LoongArch: crypto: Add crc32 and crc32c hw acceleration With a blatant copy of some MIPS bits we introduce the crc32 and crc32c hw accelerated module to LoongArch. LoongArch has provided these instructions to calculate crc32 and crc32c: * crc.w.b.w crcc.w.b.w * crc.w.h.w crcc.w.h.w * crc.w.w.w crcc.w.w.w * crc.w.d.w crcc.w.d.w So we can make use of these instructions to improve the performance of calculation for crc32(c) checksums. As can be seen from the following test results, crc32(c) instructions can improve the performance by 58%. Software implemention Hardware acceleration Buffer size time cost (seconds) time cost (seconds) Accel. 100 KB 0.000845 0.000534 59.1% 1 MB 0.007758 0.004836 59.4% 10 MB 0.076593 0.047682 59.4% 100 MB 0.756734 0.479126 58.5% 1000 MB 7.563841 4.778266 58.5% Signed-off-by: Min Zhou Signed-off-by: Huacai Chen --- arch/loongarch/Makefile | 2 + arch/loongarch/crypto/Kconfig | 14 ++ arch/loongarch/crypto/Makefile | 6 + arch/loongarch/crypto/crc32-loongarch.c | 304 ++++++++++++++++++++++++ crypto/Kconfig | 3 + 5 files changed, 329 insertions(+) create mode 100644 arch/loongarch/crypto/Kconfig create mode 100644 arch/loongarch/crypto/Makefile create mode 100644 arch/loongarch/crypto/crc32-loongarch.c diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index f71edf574101..a27e264bdaa5 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -115,6 +115,8 @@ endif libs-y += arch/loongarch/lib/ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +drivers-y += arch/loongarch/crypto/ + # suspend and hibernation support drivers-$(CONFIG_PM) += arch/loongarch/power/ diff --git a/arch/loongarch/crypto/Kconfig b/arch/loongarch/crypto/Kconfig new file mode 100644 index 000000000000..200a6e8b43b1 --- /dev/null +++ b/arch/loongarch/crypto/Kconfig @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Accelerated Cryptographic Algorithms for CPU (loongarch)" + +config CRYPTO_CRC32_LOONGARCH + tristate "CRC32c and CRC32" + select CRC32 + select CRYPTO_HASH + help + CRC32c and CRC32 CRC algorithms + + Architecture: LoongArch with CRC32 instructions + +endmenu diff --git a/arch/loongarch/crypto/Makefile b/arch/loongarch/crypto/Makefile new file mode 100644 index 000000000000..d22613d27ce9 --- /dev/null +++ b/arch/loongarch/crypto/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for LoongArch crypto files.. +# + +obj-$(CONFIG_CRYPTO_CRC32_LOONGARCH) += crc32-loongarch.o diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c new file mode 100644 index 000000000000..1f2a2c3839bc --- /dev/null +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * crc32.c - CRC32 and CRC32C using LoongArch crc* instructions + * + * Module based on mips/crypto/crc32-mips.c + * + * Copyright (C) 2014 Linaro Ltd + * Copyright (C) 2018 MIPS Tech, LLC + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#include +#include + +#include +#include + +#define _CRC32(crc, value, size, type) \ +do { \ + __asm__ __volatile__( \ + #type ".w." #size ".w" " %0, %1, %0\n\t"\ + : "+r" (crc) \ + : "r" (value) \ + : "memory"); \ +} while (0) + +#define CRC32(crc, value, size) _CRC32(crc, value, size, crc) +#define CRC32C(crc, value, size) _CRC32(crc, value, size, crcc) + +static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) +{ + u32 crc = crc_; + + while (len >= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32(crc, value, d); + p += sizeof(u64); + len -= sizeof(u64); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32(crc, value, w); + p += sizeof(u32); + len -= sizeof(u32); + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32(crc, value, b); + } + + return crc; +} + +static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) +{ + u32 crc = crc_; + + while (len >= sizeof(u64)) { + u64 value = get_unaligned_le64(p); + + CRC32C(crc, value, d); + p += sizeof(u64); + len -= sizeof(u64); + } + + if (len & sizeof(u32)) { + u32 value = get_unaligned_le32(p); + + CRC32C(crc, value, w); + p += sizeof(u32); + len -= sizeof(u32); + } + + if (len & sizeof(u16)) { + u16 value = get_unaligned_le16(p); + + CRC32C(crc, value, h); + p += sizeof(u16); + } + + if (len & sizeof(u8)) { + u8 value = *p++; + + CRC32C(crc, value, b); + } + + return crc; +} + +#define CHKSUM_BLOCK_SIZE 1 +#define CHKSUM_DIGEST_SIZE 4 + +struct chksum_ctx { + u32 key; +}; + +struct chksum_desc_ctx { + u32 crc; +}; + +static int chksum_init(struct shash_desc *desc) +{ + struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->crc = mctx->key; + + return 0; +} + +/* + * Setting the seed allows arbitrary accumulators and flexible XOR policy + * If your algorithm starts with ~0, then XOR with ~0 before you set the seed. + */ +static int chksum_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) +{ + struct chksum_ctx *mctx = crypto_shash_ctx(tfm); + + if (keylen != sizeof(mctx->key)) + return -EINVAL; + + mctx->key = get_unaligned_le32(key); + + return 0; +} + +static int chksum_update(struct shash_desc *desc, const u8 *data, unsigned int length) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->crc = crc32_loongarch_hw(ctx->crc, data, length); + return 0; +} + +static int chksumc_update(struct shash_desc *desc, const u8 *data, unsigned int length) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + ctx->crc = crc32c_loongarch_hw(ctx->crc, data, length); + return 0; +} + +static int chksum_final(struct shash_desc *desc, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + put_unaligned_le32(ctx->crc, out); + return 0; +} + +static int chksumc_final(struct shash_desc *desc, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + put_unaligned_le32(~ctx->crc, out); + return 0; +} + +static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) +{ + put_unaligned_le32(crc32_loongarch_hw(crc, data, len), out); + return 0; +} + +static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) +{ + put_unaligned_le32(~crc32c_loongarch_hw(crc, data, len), out); + return 0; +} + +static int chksum_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + return __chksum_finup(ctx->crc, data, len, out); +} + +static int chksumc_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + + return __chksumc_finup(ctx->crc, data, len, out); +} + +static int chksum_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) +{ + struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); + + return __chksum_finup(mctx->key, data, length, out); +} + +static int chksumc_digest(struct shash_desc *desc, const u8 *data, unsigned int length, u8 *out) +{ + struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm); + + return __chksumc_finup(mctx->key, data, length, out); +} + +static int chksum_cra_init(struct crypto_tfm *tfm) +{ + struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); + + mctx->key = 0; + return 0; +} + +static int chksumc_cra_init(struct crypto_tfm *tfm) +{ + struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); + + mctx->key = ~0; + return 0; +} + +static struct shash_alg crc32_alg = { + .digestsize = CHKSUM_DIGEST_SIZE, + .setkey = chksum_setkey, + .init = chksum_init, + .update = chksum_update, + .final = chksum_final, + .finup = chksum_finup, + .digest = chksum_digest, + .descsize = sizeof(struct chksum_desc_ctx), + .base = { + .cra_name = "crc32", + .cra_driver_name = "crc32-loongarch", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .cra_blocksize = CHKSUM_BLOCK_SIZE, + .cra_alignmask = 0, + .cra_ctxsize = sizeof(struct chksum_ctx), + .cra_module = THIS_MODULE, + .cra_init = chksum_cra_init, + } +}; + +static struct shash_alg crc32c_alg = { + .digestsize = CHKSUM_DIGEST_SIZE, + .setkey = chksum_setkey, + .init = chksum_init, + .update = chksumc_update, + .final = chksumc_final, + .finup = chksumc_finup, + .digest = chksumc_digest, + .descsize = sizeof(struct chksum_desc_ctx), + .base = { + .cra_name = "crc32c", + .cra_driver_name = "crc32c-loongarch", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_OPTIONAL_KEY, + .cra_blocksize = CHKSUM_BLOCK_SIZE, + .cra_alignmask = 0, + .cra_ctxsize = sizeof(struct chksum_ctx), + .cra_module = THIS_MODULE, + .cra_init = chksumc_cra_init, + } +}; + +static int __init crc32_mod_init(void) +{ + int err; + + if (!cpu_has(CPU_FEATURE_CRC32)) + return 0; + + err = crypto_register_shash(&crc32_alg); + if (err) + return err; + + err = crypto_register_shash(&crc32c_alg); + if (err) + return err; + + return 0; +} + +static void __exit crc32_mod_exit(void) +{ + if (!cpu_has(CPU_FEATURE_CRC32)) + return; + + crypto_unregister_shash(&crc32_alg); + crypto_unregister_shash(&crc32c_alg); +} + +module_init(crc32_mod_init); +module_exit(crc32_mod_exit); + +MODULE_AUTHOR("Min Zhou "); +MODULE_AUTHOR("Huacai Chen "); +MODULE_DESCRIPTION("CRC32 and CRC32C using LoongArch crc* instructions"); +MODULE_LICENSE("GPL v2"); diff --git a/crypto/Kconfig b/crypto/Kconfig index 9c86f7045157..a0e080d5f6ae 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1395,6 +1395,9 @@ endif if ARM64 source "arch/arm64/crypto/Kconfig" endif +if LOONGARCH +source "arch/loongarch/crypto/Kconfig" +endif if MIPS source "arch/mips/crypto/Kconfig" endif -- GitLab From d4c937c2a57bbba24790be6fe7a791456f5fbb60 Mon Sep 17 00:00:00 2001 From: Qing Zhang Date: Mon, 1 May 2023 17:19:52 +0800 Subject: [PATCH 4359/5631] LoongArch: Add ARCH_HAS_FORTIFY_SOURCE selection FORTIFY_SOURCE could detect various overflows at compile and run time. ARCH_HAS_FORTIFY_SOURCE means that the architecture can be built and run with CONFIG_FORTIFY_SOURCE. So select it in LoongArch. See more about this feature from commit 6974f0c4555e285 ("include/linux/ string.h: add the option of fortified string.h functions"). Signed-off-by: Qing Zhang Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 3ddde336e6a5..3e5d6acbf240 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -10,6 +10,7 @@ config LOONGARCH select ARCH_ENABLE_MEMORY_HOTPLUG select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST -- GitLab From 8b5ee2c66d5c4c1312fd193d4138e6963160ba43 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Mon, 1 May 2023 17:19:52 +0800 Subject: [PATCH 4360/5631] LoongArch: Add support for function error injection Inspired by the commit 42d038c4fb00f ("arm64: Add support for function error injection") and the commit ee55ff803b383 ("riscv: Add support for function error injection"), this patch supports function error injection for LoongArch. Mainly implement two functions: (1) regs_set_return_value() which is used to overwrite the return value, (2) override_function_with_return() which is used to override the probed function returning and jump to its caller. Here is a simple test under CONFIG_FUNCTION_ERROR_INJECTION and CONFIG_FAIL_FUNCTION: # echo sys_clone > /sys/kernel/debug/fail_function/inject # echo 100 > /sys/kernel/debug/fail_function/probability # dmesg bash: fork: Invalid argument # dmesg ... FAULT_INJECTION: forcing a failure. name fail_function, interval 1, probability 100, space 0, times 1 ... Call Trace: [<90000000002238f4>] show_stack+0x5c/0x180 [<90000000012e384c>] dump_stack_lvl+0x60/0x88 [<9000000000b1879c>] should_fail_ex+0x1b0/0x1f4 [<900000000032ead4>] fei_kprobe_handler+0x28/0x6c [<9000000000230970>] kprobe_breakpoint_handler+0xf0/0x118 [<90000000012e3e60>] do_bp+0x2c4/0x358 [<9000000002241924>] exception_handlers+0x1924/0x10000 [<900000000023b7d0>] sys_clone+0x0/0x4 [<90000000012e4744>] do_syscall+0x7c/0x94 [<9000000000221e44>] handle_syscall+0xc4/0x160 Tested-by: Hengqi Chen Acked-by: Masami Hiramatsu (Google) Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/ptrace.h | 5 +++++ arch/loongarch/lib/Makefile | 2 ++ arch/loongarch/lib/error-inject.c | 10 ++++++++++ 4 files changed, 18 insertions(+) create mode 100644 arch/loongarch/lib/error-inject.c diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 3e5d6acbf240..629a6dac33e1 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -100,6 +100,7 @@ config LOONGARCH select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GENERIC_VDSO diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index d761db943335..35f0958163ac 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -154,6 +154,11 @@ static inline long regs_return_value(struct pt_regs *regs) return regs->regs[4]; } +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long val) +{ + regs->regs[4] = val; +} + #define instruction_pointer(regs) ((regs)->csr_era) #define profile_pc(regs) instruction_pointer(regs) diff --git a/arch/loongarch/lib/Makefile b/arch/loongarch/lib/Makefile index 271ed45f51bb..d60d4e096cfa 100644 --- a/arch/loongarch/lib/Makefile +++ b/arch/loongarch/lib/Makefile @@ -5,3 +5,5 @@ lib-y += delay.o memset.o memcpy.o memmove.o \ clear_user.o copy_user.o csum.o dump_tlb.o unaligned.o + +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/loongarch/lib/error-inject.c b/arch/loongarch/lib/error-inject.c new file mode 100644 index 000000000000..afc9e1c7c973 --- /dev/null +++ b/arch/loongarch/lib/error-inject.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void override_function_with_return(struct pt_regs *regs) +{ + instruction_pointer_set(regs, regs->regs[1]); +} +NOKPROBE_SYMBOL(override_function_with_return); -- GitLab From 6fbff14a638293dcd0550cac2921f308ef6abe0e Mon Sep 17 00:00:00 2001 From: Qing Zhang Date: Mon, 1 May 2023 17:19:52 +0800 Subject: [PATCH 4361/5631] LoongArch: ftrace: Abstract DYNAMIC_FTRACE_WITH_ARGS accesses Add new ftrace_regs_{get,set}_*() helpers which can be used to manipulate ftrace_regs. When CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS=y, these can always be used on any ftrace_regs, and when CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS =n these can be used when regs are available. Signed-off-by: Qing Zhang Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/ftrace.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 3418d32d4fc7..aa5c57b5f333 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -54,6 +54,31 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return &fregs->regs; } +static __always_inline unsigned long +ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs) +{ + return instruction_pointer(&fregs->regs); +} + +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) +{ + regs_set_return_value(&fregs->regs, ip); +} + +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); -- GitLab From 819cf65575230bca02ad669daadba2ac04187ae1 Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Mon, 1 May 2023 17:19:52 +0800 Subject: [PATCH 4362/5631] LoongArch: ftrace: Fix build error if DYNAMIC_FTRACE_WITH_REGS is not set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We can see the following build error if CONFIG_DYNAMIC_FTRACE_WITH_REGS is not set on LoongArch: arch/loongarch/kernel/ftrace_dyn.c: In function ‘ftrace_make_call’: arch/loongarch/kernel/ftrace_dyn.c:167:23: error: implicit declaration of function ‘__get_mod’ 167 | ret = __get_mod(&mod, pc); | ^~~~~~~~~ arch/loongarch/kernel/ftrace_dyn.c:171:24: error: implicit declaration of function ‘get_plt_addr’ 171 | addr = get_plt_addr(mod, addr); | ^~~~~~~~~~~~ The reason is that the __get_mod() and get_plt_addr() may be called in ftrace_make_{call,nop}. Signed-off-by: Youling Tang Signed-off-by: Huacai Chen --- arch/loongarch/kernel/ftrace_dyn.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 4a3ef8516ccc..c5f4b4681ddc 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -30,8 +30,6 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, bool validate) return 0; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS - #ifdef CONFIG_MODULES static inline int __get_mod(struct module **mod, unsigned long addr) { @@ -72,6 +70,7 @@ static unsigned long get_plt_addr(struct module *mod, unsigned long addr) } #endif +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { u32 old, new; @@ -102,7 +101,6 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned return ftrace_modify_code(pc, old, new, true); } - #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ int ftrace_update_ftrace_func(ftrace_func_t func) -- GitLab From 24d4f52791dae16e478741cc397ba660a95b9d02 Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Mon, 1 May 2023 17:19:53 +0800 Subject: [PATCH 4363/5631] LoongArch: ftrace: Implement ftrace_find_callable_addr() to simplify code In the module processing functions, the same logic can be reused by implementing ftrace_find_callable_addr(). Signed-off-by: Youling Tang Signed-off-by: Huacai Chen --- arch/loongarch/kernel/ftrace_dyn.c | 116 ++++++++++++++--------------- 1 file changed, 57 insertions(+), 59 deletions(-) diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index c5f4b4681ddc..eb624af93617 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -31,16 +31,11 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, bool validate) } #ifdef CONFIG_MODULES -static inline int __get_mod(struct module **mod, unsigned long addr) +static bool reachable_by_bl(unsigned long addr, unsigned long pc) { - preempt_disable(); - *mod = __module_text_address(addr); - preempt_enable(); + long offset = (long)addr - (long)pc; - if (WARN_ON(!(*mod))) - return -EINVAL; - - return 0; + return offset >= -SZ_128M && offset < SZ_128M; } static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) @@ -56,17 +51,58 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) return NULL; } -static unsigned long get_plt_addr(struct module *mod, unsigned long addr) +/* + * Find the address the callsite must branch to in order to reach '*addr'. + * + * Due to the limited range of 'bl' instruction, modules may be placed too far + * away to branch directly and we must use a PLT. + * + * Returns true when '*addr' contains a reachable target address, or has been + * modified to contain a PLT address. Returns false otherwise. + */ +static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod, unsigned long *addr) { + unsigned long pc = rec->ip + LOONGARCH_INSN_SIZE; struct plt_entry *plt; - plt = get_ftrace_plt(mod, addr); + /* + * When the target is within range of the 'bl' instruction, use 'addr' + * as-is and branch to that directly. + */ + if (reachable_by_bl(*addr, pc)) + return true; + + /* + * 'mod' is only set at module load time, but if we end up + * dealing with an out-of-range condition, we can assume it + * is due to a module being loaded far away from the kernel. + * + * NOTE: __module_text_address() must be called with preemption + * disabled, but we can rely on ftrace_lock to ensure that 'mod' + * retains its validity throughout the remainder of this code. + */ + if (!mod) { + preempt_disable(); + mod = __module_text_address(pc); + preempt_enable(); + } + + if (WARN_ON(!mod)) + return false; + + plt = get_ftrace_plt(mod, *addr); if (!plt) { - pr_err("ftrace: no module PLT for %ps\n", (void *)addr); - return -EINVAL; + pr_err("ftrace: no module PLT for %ps\n", (void *)*addr); + return false; } - return (unsigned long)plt; + *addr = (unsigned long)plt; + return true; +} +#else /* !CONFIG_MODULES */ +static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod, unsigned long *addr) +{ + return true; } #endif @@ -75,26 +111,14 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned { u32 old, new; unsigned long pc; - long offset __maybe_unused; pc = rec->ip + LOONGARCH_INSN_SIZE; -#ifdef CONFIG_MODULES - offset = (long)pc - (long)addr; - - if (offset < -SZ_128M || offset >= SZ_128M) { - int ret; - struct module *mod; - - ret = __get_mod(&mod, pc); - if (ret) - return ret; - - addr = get_plt_addr(mod, addr); + if (!ftrace_find_callable_addr(rec, NULL, &addr)) + return -EINVAL; - old_addr = get_plt_addr(mod, old_addr); - } -#endif + if (!ftrace_find_callable_addr(rec, NULL, &old_addr)) + return -EINVAL; new = larch_insn_gen_bl(pc, addr); old = larch_insn_gen_bl(pc, old_addr); @@ -151,24 +175,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { u32 old, new; unsigned long pc; - long offset __maybe_unused; pc = rec->ip + LOONGARCH_INSN_SIZE; -#ifdef CONFIG_MODULES - offset = (long)pc - (long)addr; - - if (offset < -SZ_128M || offset >= SZ_128M) { - int ret; - struct module *mod; - - ret = __get_mod(&mod, pc); - if (ret) - return ret; - - addr = get_plt_addr(mod, addr); - } -#endif + if (!ftrace_find_callable_addr(rec, NULL, &addr)) + return -EINVAL; old = larch_insn_gen_nop(); new = larch_insn_gen_bl(pc, addr); @@ -180,24 +191,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long ad { u32 old, new; unsigned long pc; - long offset __maybe_unused; pc = rec->ip + LOONGARCH_INSN_SIZE; -#ifdef CONFIG_MODULES - offset = (long)pc - (long)addr; - - if (offset < -SZ_128M || offset >= SZ_128M) { - int ret; - struct module *mod; - - ret = __get_mod(&mod, pc); - if (ret) - return ret; - - addr = get_plt_addr(mod, addr); - } -#endif + if (!ftrace_find_callable_addr(rec, NULL, &addr)) + return -EINVAL; new = larch_insn_gen_nop(); old = larch_insn_gen_bl(pc, addr); -- GitLab From 9cdc3b6a299c6314485bcfb695546c11d35dac4c Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Mon, 1 May 2023 17:19:53 +0800 Subject: [PATCH 4364/5631] LoongArch: ftrace: Add direct call support Select the HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS to provide the register_ftrace_direct[_multi] interfaces allowing users to register the customed trampoline (direct_caller) as the mcount for one or more target functions. And modify_ftrace_direct[_multi] are also provided for modifying direct_caller. There are a few cases to distinguish: - If a direct call ops is the only one tracing a function AND the direct called trampoline is within the reach of a 'bl' instruction -> the ftrace patchsite jumps to the trampoline - Else -> the ftrace patchsite jumps to the ftrace_regs_caller trampoline points to ftrace_list_ops so it iterates over all registered ftrace ops, including the direct call ops and calls its call_direct_funcs handler which stores the direct called trampoline's address in the ftrace_regs and the ftrace_regs_caller trampoline will return to that address instead of returning to the traced function Signed-off-by: Qing Zhang Signed-off-by: Youling Tang Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/ftrace.h | 12 ++++++++++++ arch/loongarch/kernel/ftrace_dyn.c | 8 ++++++++ arch/loongarch/kernel/mcount_dyn.S | 13 ++++++++++++- 4 files changed, 33 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 629a6dac33e1..3a79bde6bf5b 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -93,6 +93,7 @@ config LOONGARCH select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index aa5c57b5f333..23e2ba78dcb0 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -82,6 +82,18 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +static inline void +__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + regs->regs[13] = addr; /* t1 */ +} + +#define arch_ftrace_set_direct_caller(fregs, addr) \ + __arch_ftrace_set_direct_caller(&(fregs)->regs, addr) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index eb624af93617..73858c9029cc 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -65,6 +65,14 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod unsigned long pc = rec->ip + LOONGARCH_INSN_SIZE; struct plt_entry *plt; + /* + * If a custom trampoline is unreachable, rely on the ftrace_regs_caller + * trampoline which knows how to indirectly reach that trampoline through + * ops->direct_call. + */ + if (*addr != FTRACE_ADDR && *addr != FTRACE_REGS_ADDR && !reachable_by_bl(*addr, pc)) + *addr = FTRACE_REGS_ADDR; + /* * When the target is within range of the 'bl' instruction, use 'addr' * as-is and branch to that directly. diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index bbabf06244c2..c7d961fc72c2 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -42,7 +42,6 @@ .if \allregs PTR_S tp, sp, PT_R2 PTR_S t0, sp, PT_R12 - PTR_S t1, sp, PT_R13 PTR_S t2, sp, PT_R14 PTR_S t3, sp, PT_R15 PTR_S t4, sp, PT_R16 @@ -64,6 +63,8 @@ PTR_S zero, sp, PT_R0 .endif PTR_S ra, sp, PT_ERA /* Save trace function ra at PT_ERA */ + move t1, zero + PTR_S t1, sp, PT_R13 PTR_ADDI t8, sp, PT_SIZE PTR_S t8, sp, PT_R3 .endm @@ -104,8 +105,12 @@ ftrace_common_return: PTR_L a7, sp, PT_R11 PTR_L fp, sp, PT_R22 PTR_L t0, sp, PT_ERA + PTR_L t1, sp, PT_R13 PTR_ADDI sp, sp, PT_SIZE + bnez t1, .Ldirect jr t0 +.Ldirect: + jr t1 SYM_CODE_END(ftrace_common) SYM_CODE_START(ftrace_caller) @@ -147,3 +152,9 @@ SYM_CODE_START(return_to_handler) jr ra SYM_CODE_END(return_to_handler) #endif + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + jr t0 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ -- GitLab From 22f367a689ceceb08d9ce6a65c43c9640f5cb935 Mon Sep 17 00:00:00 2001 From: Youling Tang Date: Mon, 1 May 2023 17:19:53 +0800 Subject: [PATCH 4365/5631] LoongArch: ftrace: Add direct call trampoline samples support The ftrace samples need per-architecture trampoline implementations to save and restore argument registers around the calls to my_direct_func* and to restore polluted registers (e.g: ra). Signed-off-by: Qing Zhang Signed-off-by: Youling Tang Signed-off-by: Huacai Chen --- arch/loongarch/Kconfig | 2 + samples/ftrace/ftrace-direct-modify.c | 34 +++++++++++++++++ samples/ftrace/ftrace-direct-multi-modify.c | 41 +++++++++++++++++++++ samples/ftrace/ftrace-direct-multi.c | 25 +++++++++++++ samples/ftrace/ftrace-direct-too.c | 27 ++++++++++++++ samples/ftrace/ftrace-direct.c | 23 ++++++++++++ 6 files changed, 152 insertions(+) diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 3a79bde6bf5b..ac3d3d9b5716 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -120,6 +120,8 @@ config LOONGARCH select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RSEQ + select HAVE_SAMPLE_FTRACE_DIRECT + select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_SETUP_PER_CPU_AREA if NUMA select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index d93abbcb1f4c..ca72c3b710eb 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -96,6 +96,40 @@ asm ( #endif /* CONFIG_S390 */ +#ifdef CONFIG_LOONGARCH + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp1, @function\n" +" .globl my_tramp1\n" +" my_tramp1:\n" +" addi.d $sp, $sp, -16\n" +" st.d $t0, $sp, 0\n" +" st.d $ra, $sp, 8\n" +" bl my_direct_func1\n" +" ld.d $t0, $sp, 0\n" +" ld.d $ra, $sp, 8\n" +" addi.d $sp, $sp, 16\n" +" jr $t0\n" +" .size my_tramp1, .-my_tramp1\n" + +" .type my_tramp2, @function\n" +" .globl my_tramp2\n" +" my_tramp2:\n" +" addi.d $sp, $sp, -16\n" +" st.d $t0, $sp, 0\n" +" st.d $ra, $sp, 8\n" +" bl my_direct_func2\n" +" ld.d $t0, $sp, 0\n" +" ld.d $ra, $sp, 8\n" +" addi.d $sp, $sp, 16\n" +" jr $t0\n" +" .size my_tramp2, .-my_tramp2\n" +" .popsection\n" +); + +#endif /* CONFIG_LOONGARCH */ + static unsigned long my_tramp = (unsigned long)my_tramp1; static unsigned long tramps[2] = { (unsigned long)my_tramp1, diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index b58c594efb51..4708c24d47c6 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -103,6 +103,47 @@ asm ( #endif /* CONFIG_S390 */ +#ifdef CONFIG_LOONGARCH +#include + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp1, @function\n" +" .globl my_tramp1\n" +" my_tramp1:\n" +" addi.d $sp, $sp, -32\n" +" st.d $a0, $sp, 0\n" +" st.d $t0, $sp, 8\n" +" st.d $ra, $sp, 16\n" +" move $a0, $t0\n" +" bl my_direct_func1\n" +" ld.d $a0, $sp, 0\n" +" ld.d $t0, $sp, 8\n" +" ld.d $ra, $sp, 16\n" +" addi.d $sp, $sp, 32\n" +" jr $t0\n" +" .size my_tramp1, .-my_tramp1\n" + +" .type my_tramp2, @function\n" +" .globl my_tramp2\n" +" my_tramp2:\n" +" addi.d $sp, $sp, -32\n" +" st.d $a0, $sp, 0\n" +" st.d $t0, $sp, 8\n" +" st.d $ra, $sp, 16\n" +" move $a0, $t0\n" +" bl my_direct_func2\n" +" ld.d $a0, $sp, 0\n" +" ld.d $t0, $sp, 8\n" +" ld.d $ra, $sp, 16\n" +" addi.d $sp, $sp, 32\n" +" jr $t0\n" +" .size my_tramp2, .-my_tramp2\n" +" .popsection\n" +); + +#endif /* CONFIG_LOONGARCH */ + static unsigned long my_tramp = (unsigned long)my_tramp1; static unsigned long tramps[2] = { (unsigned long)my_tramp1, diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c index c27cf130c319..c2f1652c67bc 100644 --- a/samples/ftrace/ftrace-direct-multi.c +++ b/samples/ftrace/ftrace-direct-multi.c @@ -66,6 +66,31 @@ asm ( #endif /* CONFIG_S390 */ +#ifdef CONFIG_LOONGARCH + +#include +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp, @function\n" +" .globl my_tramp\n" +" my_tramp:\n" +" addi.d $sp, $sp, -32\n" +" st.d $a0, $sp, 0\n" +" st.d $t0, $sp, 8\n" +" st.d $ra, $sp, 16\n" +" move $a0, $t0\n" +" bl my_direct_func\n" +" ld.d $a0, $sp, 0\n" +" ld.d $t0, $sp, 8\n" +" ld.d $ra, $sp, 16\n" +" addi.d $sp, $sp, 32\n" +" jr $t0\n" +" .size my_tramp, .-my_tramp\n" +" .popsection\n" +); + +#endif /* CONFIG_LOONGARCH */ + static struct ftrace_ops direct; static int __init ftrace_direct_multi_init(void) diff --git a/samples/ftrace/ftrace-direct-too.c b/samples/ftrace/ftrace-direct-too.c index 8139dce2a31c..ef64d7509773 100644 --- a/samples/ftrace/ftrace-direct-too.c +++ b/samples/ftrace/ftrace-direct-too.c @@ -70,6 +70,33 @@ asm ( #endif /* CONFIG_S390 */ +#ifdef CONFIG_LOONGARCH + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp, @function\n" +" .globl my_tramp\n" +" my_tramp:\n" +" addi.d $sp, $sp, -48\n" +" st.d $a0, $sp, 0\n" +" st.d $a1, $sp, 8\n" +" st.d $a2, $sp, 16\n" +" st.d $t0, $sp, 24\n" +" st.d $ra, $sp, 32\n" +" bl my_direct_func\n" +" ld.d $a0, $sp, 0\n" +" ld.d $a1, $sp, 8\n" +" ld.d $a2, $sp, 16\n" +" ld.d $t0, $sp, 24\n" +" ld.d $ra, $sp, 32\n" +" addi.d $sp, $sp, 48\n" +" jr $t0\n" +" .size my_tramp, .-my_tramp\n" +" .popsection\n" +); + +#endif /* CONFIG_LOONGARCH */ + static int __init ftrace_direct_init(void) { return register_ftrace_direct((unsigned long)handle_mm_fault, diff --git a/samples/ftrace/ftrace-direct.c b/samples/ftrace/ftrace-direct.c index 1d3d307ca33d..9be720957bf8 100644 --- a/samples/ftrace/ftrace-direct.c +++ b/samples/ftrace/ftrace-direct.c @@ -63,6 +63,29 @@ asm ( #endif /* CONFIG_S390 */ +#ifdef CONFIG_LOONGARCH + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp, @function\n" +" .globl my_tramp\n" +" my_tramp:\n" +" addi.d $sp, $sp, -32\n" +" st.d $a0, $sp, 0\n" +" st.d $t0, $sp, 8\n" +" st.d $ra, $sp, 16\n" +" bl my_direct_func\n" +" ld.d $a0, $sp, 0\n" +" ld.d $t0, $sp, 8\n" +" ld.d $ra, $sp, 16\n" +" addi.d $sp, $sp, 32\n" +" jr $t0\n" +" .size my_tramp, .-my_tramp\n" +" .popsection\n" +); + +#endif /* CONFIG_LOONGARCH */ + static int __init ftrace_direct_init(void) { return register_ftrace_direct((unsigned long)wake_up_process, -- GitLab From 2fa5ebe3bc4e31e07a99196455498472417842f2 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Mon, 1 May 2023 17:19:59 +0800 Subject: [PATCH 4366/5631] tools/perf: Add basic support for LoongArch Add basic support for LoongArch, which is very similar to the MIPS version. Signed-off-by: Ming Wang Signed-off-by: Huacai Chen --- .../loongarch/include/uapi/asm/perf_regs.h | 40 +++++++++ .../arch/loongarch/include/uapi/asm/unistd.h | 9 ++ tools/perf/Makefile.config | 12 ++- tools/perf/arch/loongarch/Build | 1 + tools/perf/arch/loongarch/Makefile | 28 +++++++ .../arch/loongarch/annotate/instructions.c | 45 ++++++++++ .../loongarch/entry/syscalls/mksyscalltbl | 61 ++++++++++++++ .../arch/loongarch/include/dwarf-regs-table.h | 16 ++++ tools/perf/arch/loongarch/include/perf_regs.h | 15 ++++ tools/perf/arch/loongarch/util/Build | 5 ++ tools/perf/arch/loongarch/util/dwarf-regs.c | 44 ++++++++++ tools/perf/arch/loongarch/util/perf_regs.c | 6 ++ tools/perf/arch/loongarch/util/unwind-libdw.c | 56 +++++++++++++ .../arch/loongarch/util/unwind-libunwind.c | 82 +++++++++++++++++++ tools/perf/check-headers.sh | 1 + tools/perf/util/annotate.c | 8 ++ tools/perf/util/dwarf-regs.c | 7 ++ tools/perf/util/env.c | 2 + tools/perf/util/genelf.h | 3 + tools/perf/util/perf_regs.c | 76 +++++++++++++++++ tools/perf/util/syscalltbl.c | 4 + 21 files changed, 518 insertions(+), 3 deletions(-) create mode 100644 tools/arch/loongarch/include/uapi/asm/perf_regs.h create mode 100644 tools/arch/loongarch/include/uapi/asm/unistd.h create mode 100644 tools/perf/arch/loongarch/Build create mode 100644 tools/perf/arch/loongarch/Makefile create mode 100644 tools/perf/arch/loongarch/annotate/instructions.c create mode 100755 tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl create mode 100644 tools/perf/arch/loongarch/include/dwarf-regs-table.h create mode 100644 tools/perf/arch/loongarch/include/perf_regs.h create mode 100644 tools/perf/arch/loongarch/util/Build create mode 100644 tools/perf/arch/loongarch/util/dwarf-regs.c create mode 100644 tools/perf/arch/loongarch/util/perf_regs.c create mode 100644 tools/perf/arch/loongarch/util/unwind-libdw.c create mode 100644 tools/perf/arch/loongarch/util/unwind-libunwind.c diff --git a/tools/arch/loongarch/include/uapi/asm/perf_regs.h b/tools/arch/loongarch/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..29d69c00fc7a --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/perf_regs.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_LOONGARCH_PERF_REGS_H +#define _ASM_LOONGARCH_PERF_REGS_H + +enum perf_event_loongarch_regs { + PERF_REG_LOONGARCH_PC, + PERF_REG_LOONGARCH_R1, + PERF_REG_LOONGARCH_R2, + PERF_REG_LOONGARCH_R3, + PERF_REG_LOONGARCH_R4, + PERF_REG_LOONGARCH_R5, + PERF_REG_LOONGARCH_R6, + PERF_REG_LOONGARCH_R7, + PERF_REG_LOONGARCH_R8, + PERF_REG_LOONGARCH_R9, + PERF_REG_LOONGARCH_R10, + PERF_REG_LOONGARCH_R11, + PERF_REG_LOONGARCH_R12, + PERF_REG_LOONGARCH_R13, + PERF_REG_LOONGARCH_R14, + PERF_REG_LOONGARCH_R15, + PERF_REG_LOONGARCH_R16, + PERF_REG_LOONGARCH_R17, + PERF_REG_LOONGARCH_R18, + PERF_REG_LOONGARCH_R19, + PERF_REG_LOONGARCH_R20, + PERF_REG_LOONGARCH_R21, + PERF_REG_LOONGARCH_R22, + PERF_REG_LOONGARCH_R23, + PERF_REG_LOONGARCH_R24, + PERF_REG_LOONGARCH_R25, + PERF_REG_LOONGARCH_R26, + PERF_REG_LOONGARCH_R27, + PERF_REG_LOONGARCH_R28, + PERF_REG_LOONGARCH_R29, + PERF_REG_LOONGARCH_R30, + PERF_REG_LOONGARCH_R31, + PERF_REG_LOONGARCH_MAX, +}; +#endif /* _ASM_LOONGARCH_PERF_REGS_H */ diff --git a/tools/arch/loongarch/include/uapi/asm/unistd.h b/tools/arch/loongarch/include/uapi/asm/unistd.h new file mode 100644 index 000000000000..0c743344e92d --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/unistd.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#define __ARCH_WANT_SYS_CLONE +#define __ARCH_WANT_SYS_CLONE3 + +#include diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 3519a0139026..c0a208f9b67b 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -38,7 +38,7 @@ ifneq ($(NO_SYSCALL_TABLE),1) NO_SYSCALL_TABLE := 0 endif else - ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips)) + ifeq ($(SRCARCH),$(filter $(SRCARCH),powerpc arm64 s390 mips loongarch)) NO_SYSCALL_TABLE := 0 endif endif @@ -80,6 +80,12 @@ ifeq ($(SRCARCH),arm64) LIBUNWIND_LIBS = -lunwind -lunwind-aarch64 endif +ifeq ($(SRCARCH),loongarch) + NO_PERF_REGS := 0 + CFLAGS += -I$(OUTPUT)arch/loongarch/include/generated + LIBUNWIND_LIBS = -lunwind -lunwind-loongarch64 +endif + ifeq ($(SRCARCH),riscv) NO_PERF_REGS := 0 endif @@ -107,7 +113,7 @@ endif # Disable it on all other architectures in case libdw unwind # support is detected in system. Add supported architectures # to the check. -ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv)) +ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390 csky riscv loongarch)) NO_LIBDW_DWARF_UNWIND := 1 endif @@ -129,7 +135,7 @@ endef ifdef LIBUNWIND_DIR LIBUNWIND_CFLAGS = -I$(LIBUNWIND_DIR)/include LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib - LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64 + LIBUNWIND_ARCHS = x86 x86_64 arm aarch64 debug-frame-arm debug-frame-aarch64 loongarch $(foreach libunwind_arch,$(LIBUNWIND_ARCHS),$(call libunwind_arch_set_flags,$(libunwind_arch))) endif diff --git a/tools/perf/arch/loongarch/Build b/tools/perf/arch/loongarch/Build new file mode 100644 index 000000000000..e4e5f33c84d8 --- /dev/null +++ b/tools/perf/arch/loongarch/Build @@ -0,0 +1 @@ +perf-y += util/ diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile new file mode 100644 index 000000000000..c392e7af4743 --- /dev/null +++ b/tools/perf/arch/loongarch/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +ifndef NO_DWARF +PERF_HAVE_DWARF_REGS := 1 +endif +PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 +PERF_HAVE_JITDUMP := 1 + +# +# Syscall table generation for perf +# + +out := $(OUTPUT)arch/loongarch/include/generated/asm +header := $(out)/syscalls.c +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/loongarch/include/uapi/asm/unistd.h +sysprf := $(srctree)/tools/perf/arch/loongarch/entry/syscalls/ +systbl := $(sysprf)/mksyscalltbl + +# Create output directory if not already present +_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') + +$(header): $(sysdef) $(systbl) + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ + +clean:: + $(call QUIET_CLEAN, loongarch) $(RM) $(header) + +archheaders: $(header) diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c new file mode 100644 index 000000000000..ab21bf122135 --- /dev/null +++ b/tools/perf/arch/loongarch/annotate/instructions.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Perf annotate functions. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +static +struct ins_ops *loongarch__associate_ins_ops(struct arch *arch, const char *name) +{ + struct ins_ops *ops = NULL; + + if (!strncmp(name, "beqz", 4) || + !strncmp(name, "bnez", 4) || + !strncmp(name, "beq", 3) || + !strncmp(name, "bne", 3) || + !strncmp(name, "blt", 3) || + !strncmp(name, "bge", 3) || + !strncmp(name, "bltu", 4) || + !strncmp(name, "bgeu", 4) || + !strncmp(name, "bl", 2)) + ops = &call_ops; + else if (!strncmp(name, "jirl", 4)) + ops = &ret_ops; + else if (name[0] == 'b') + ops = &jump_ops; + else + return NULL; + + arch__associate_ins_ops(arch, name, ops); + + return ops; +} + +static +int loongarch__annotate_init(struct arch *arch, char *cpuid __maybe_unused) +{ + if (!arch->initialized) { + arch->associate_instruction_ops = loongarch__associate_ins_ops; + arch->initialized = true; + arch->objdump.comment_char = '#'; + } + + return 0; +} diff --git a/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl new file mode 100755 index 000000000000..c52156f7204d --- /dev/null +++ b/tools/perf/arch/loongarch/entry/syscalls/mksyscalltbl @@ -0,0 +1,61 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Generate system call table for perf. Derived from +# powerpc script. +# +# Author(s): Ming Wang +# Author(s): Huacai Chen +# Copyright (C) 2020-2023 Loongson Technology Corporation Limited + +gcc=$1 +hostcc=$2 +incpath=$3 +input=$4 + +if ! test -r $input; then + echo "Could not read input file" >&2 + exit 1 +fi + +create_table_from_c() +{ + local sc nr last_sc + + create_table_exe=`mktemp ${TMPDIR:-/tmp}/create-table-XXXXXX` + + { + + cat <<-_EoHEADER + #include + #include "$input" + int main(int argc, char *argv[]) + { + _EoHEADER + + while read sc nr; do + printf "%s\n" " printf(\"\\t[%d] = \\\"$sc\\\",\\n\", $nr);" + last_sc=$nr + done + + printf "%s\n" " printf(\"#define SYSCALLTBL_LOONGARCH_MAX_ID %d\\n\", $last_sc);" + printf "}\n" + + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - + + $create_table_exe + + rm -f $create_table_exe +} + +create_table() +{ + echo "static const char *syscalltbl_loongarch[] = {" + create_table_from_c + echo "};" +} + +$gcc -E -dM -x c -I $incpath/include/uapi $input \ + |sed -ne 's/^#define __NR_//p' \ + |sort -t' ' -k2 -n \ + |create_table diff --git a/tools/perf/arch/loongarch/include/dwarf-regs-table.h b/tools/perf/arch/loongarch/include/dwarf-regs-table.h new file mode 100644 index 000000000000..bb3944f5764a --- /dev/null +++ b/tools/perf/arch/loongarch/include/dwarf-regs-table.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * dwarf-regs-table.h : Mapping of DWARF debug register numbers into + * register names. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#ifdef DEFINE_DWARF_REGSTR_TABLE +static const char * const loongarch_regstr_tbl[] = { + "%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7", + "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15", + "%r16", "%r17", "%r18", "%r19", "%r20", "%r21", "%r22", "%r23", + "%r24", "%r25", "%r26", "%r27", "%r28", "%r29", "%r30", "%r31", +}; +#endif diff --git a/tools/perf/arch/loongarch/include/perf_regs.h b/tools/perf/arch/loongarch/include/perf_regs.h new file mode 100644 index 000000000000..7833c7dbd38d --- /dev/null +++ b/tools/perf/arch/loongarch/include/perf_regs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_PERF_REGS_H +#define ARCH_PERF_REGS_H + +#include +#include +#include + +#define PERF_REGS_MAX PERF_REG_LOONGARCH_MAX +#define PERF_REG_IP PERF_REG_LOONGARCH_PC +#define PERF_REG_SP PERF_REG_LOONGARCH_R3 + +#define PERF_REGS_MASK ((1ULL << PERF_REG_LOONGARCH_MAX) - 1) + +#endif /* ARCH_PERF_REGS_H */ diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build new file mode 100644 index 000000000000..d776125a2d06 --- /dev/null +++ b/tools/perf/arch/loongarch/util/Build @@ -0,0 +1,5 @@ +perf-y += perf_regs.o + +perf-$(CONFIG_DWARF) += dwarf-regs.o +perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o +perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/loongarch/util/dwarf-regs.c b/tools/perf/arch/loongarch/util/dwarf-regs.c new file mode 100644 index 000000000000..0f6ebc387463 --- /dev/null +++ b/tools/perf/arch/loongarch/util/dwarf-regs.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * dwarf-regs.c : Mapping of DWARF debug register numbers into register names. + * + * Copyright (C) 2020-2023 Loongson Technology Corporation Limited + */ + +#include +#include /* for EINVAL */ +#include /* for strcmp */ +#include + +struct pt_regs_dwarfnum { + const char *name; + unsigned int dwarfnum; +}; + +static struct pt_regs_dwarfnum loongarch_gpr_table[] = { + {"%r0", 0}, {"%r1", 1}, {"%r2", 2}, {"%r3", 3}, + {"%r4", 4}, {"%r5", 5}, {"%r6", 6}, {"%r7", 7}, + {"%r8", 8}, {"%r9", 9}, {"%r10", 10}, {"%r11", 11}, + {"%r12", 12}, {"%r13", 13}, {"%r14", 14}, {"%r15", 15}, + {"%r16", 16}, {"%r17", 17}, {"%r18", 18}, {"%r19", 19}, + {"%r20", 20}, {"%r21", 21}, {"%r22", 22}, {"%r23", 23}, + {"%r24", 24}, {"%r25", 25}, {"%r26", 26}, {"%r27", 27}, + {"%r28", 28}, {"%r29", 29}, {"%r30", 30}, {"%r31", 31}, + {NULL, 0} +}; + +const char *get_arch_regstr(unsigned int n) +{ + n %= 32; + return loongarch_gpr_table[n].name; +} + +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_dwarfnum *roff; + + for (roff = loongarch_gpr_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->dwarfnum; + return -EINVAL; +} diff --git a/tools/perf/arch/loongarch/util/perf_regs.c b/tools/perf/arch/loongarch/util/perf_regs.c new file mode 100644 index 000000000000..2833e101a7c6 --- /dev/null +++ b/tools/perf/arch/loongarch/util/perf_regs.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../../../util/perf_regs.h" + +const struct sample_reg sample_reg_masks[] = { + SMPL_REG_END +}; diff --git a/tools/perf/arch/loongarch/util/unwind-libdw.c b/tools/perf/arch/loongarch/util/unwind-libdw.c new file mode 100644 index 000000000000..a9415385230a --- /dev/null +++ b/tools/perf/arch/loongarch/util/unwind-libdw.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2020-2023 Loongson Technology Corporation Limited */ + +#include +#include "../../util/unwind-libdw.h" +#include "../../util/perf_regs.h" +#include "../../util/sample.h" + +bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg) +{ + struct unwind_info *ui = arg; + struct regs_dump *user_regs = &ui->sample->user_regs; + Dwarf_Word dwarf_regs[PERF_REG_LOONGARCH_MAX]; + +#define REG(r) ({ \ + Dwarf_Word val = 0; \ + perf_reg_value(&val, user_regs, PERF_REG_LOONGARCH_##r); \ + val; \ +}) + + dwarf_regs[0] = 0; + dwarf_regs[1] = REG(R1); + dwarf_regs[2] = REG(R2); + dwarf_regs[3] = REG(R3); + dwarf_regs[4] = REG(R4); + dwarf_regs[5] = REG(R5); + dwarf_regs[6] = REG(R6); + dwarf_regs[7] = REG(R7); + dwarf_regs[8] = REG(R8); + dwarf_regs[9] = REG(R9); + dwarf_regs[10] = REG(R10); + dwarf_regs[11] = REG(R11); + dwarf_regs[12] = REG(R12); + dwarf_regs[13] = REG(R13); + dwarf_regs[14] = REG(R14); + dwarf_regs[15] = REG(R15); + dwarf_regs[16] = REG(R16); + dwarf_regs[17] = REG(R17); + dwarf_regs[18] = REG(R18); + dwarf_regs[19] = REG(R19); + dwarf_regs[20] = REG(R20); + dwarf_regs[21] = REG(R21); + dwarf_regs[22] = REG(R22); + dwarf_regs[23] = REG(R23); + dwarf_regs[24] = REG(R24); + dwarf_regs[25] = REG(R25); + dwarf_regs[26] = REG(R26); + dwarf_regs[27] = REG(R27); + dwarf_regs[28] = REG(R28); + dwarf_regs[29] = REG(R29); + dwarf_regs[30] = REG(R30); + dwarf_regs[31] = REG(R31); + dwfl_thread_state_register_pc(thread, REG(PC)); + + return dwfl_thread_state_registers(thread, 0, PERF_REG_LOONGARCH_MAX, dwarf_regs); +} diff --git a/tools/perf/arch/loongarch/util/unwind-libunwind.c b/tools/perf/arch/loongarch/util/unwind-libunwind.c new file mode 100644 index 000000000000..f693167b86ef --- /dev/null +++ b/tools/perf/arch/loongarch/util/unwind-libunwind.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include "perf_regs.h" +#include "../../util/unwind.h" +#include "util/debug.h" + +int libunwind__arch_reg_id(int regnum) +{ + switch (regnum) { + case UNW_LOONGARCH64_R1: + return PERF_REG_LOONGARCH_R1; + case UNW_LOONGARCH64_R2: + return PERF_REG_LOONGARCH_R2; + case UNW_LOONGARCH64_R3: + return PERF_REG_LOONGARCH_R3; + case UNW_LOONGARCH64_R4: + return PERF_REG_LOONGARCH_R4; + case UNW_LOONGARCH64_R5: + return PERF_REG_LOONGARCH_R5; + case UNW_LOONGARCH64_R6: + return PERF_REG_LOONGARCH_R6; + case UNW_LOONGARCH64_R7: + return PERF_REG_LOONGARCH_R7; + case UNW_LOONGARCH64_R8: + return PERF_REG_LOONGARCH_R8; + case UNW_LOONGARCH64_R9: + return PERF_REG_LOONGARCH_R9; + case UNW_LOONGARCH64_R10: + return PERF_REG_LOONGARCH_R10; + case UNW_LOONGARCH64_R11: + return PERF_REG_LOONGARCH_R11; + case UNW_LOONGARCH64_R12: + return PERF_REG_LOONGARCH_R12; + case UNW_LOONGARCH64_R13: + return PERF_REG_LOONGARCH_R13; + case UNW_LOONGARCH64_R14: + return PERF_REG_LOONGARCH_R14; + case UNW_LOONGARCH64_R15: + return PERF_REG_LOONGARCH_R15; + case UNW_LOONGARCH64_R16: + return PERF_REG_LOONGARCH_R16; + case UNW_LOONGARCH64_R17: + return PERF_REG_LOONGARCH_R17; + case UNW_LOONGARCH64_R18: + return PERF_REG_LOONGARCH_R18; + case UNW_LOONGARCH64_R19: + return PERF_REG_LOONGARCH_R19; + case UNW_LOONGARCH64_R20: + return PERF_REG_LOONGARCH_R20; + case UNW_LOONGARCH64_R21: + return PERF_REG_LOONGARCH_R21; + case UNW_LOONGARCH64_R22: + return PERF_REG_LOONGARCH_R22; + case UNW_LOONGARCH64_R23: + return PERF_REG_LOONGARCH_R23; + case UNW_LOONGARCH64_R24: + return PERF_REG_LOONGARCH_R24; + case UNW_LOONGARCH64_R25: + return PERF_REG_LOONGARCH_R25; + case UNW_LOONGARCH64_R26: + return PERF_REG_LOONGARCH_R26; + case UNW_LOONGARCH64_R27: + return PERF_REG_LOONGARCH_R27; + case UNW_LOONGARCH64_R28: + return PERF_REG_LOONGARCH_R28; + case UNW_LOONGARCH64_R29: + return PERF_REG_LOONGARCH_R29; + case UNW_LOONGARCH64_R30: + return PERF_REG_LOONGARCH_R30; + case UNW_LOONGARCH64_R31: + return PERF_REG_LOONGARCH_R31; + case UNW_LOONGARCH64_PC: + return PERF_REG_LOONGARCH_PC; + default: + pr_err("unwind: invalid reg id %d\n", regnum); + return -EINVAL; + } + + return -EINVAL; +} diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index eacca9a874e2..9d6232f681ce 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -40,6 +40,7 @@ arch/x86/lib/x86-opcode-map.txt arch/x86/tools/gen-insn-attr-x86.awk arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h +arch/loongarch/include/uapi/asm/perf_regs.h arch/mips/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h arch/s390/include/uapi/asm/perf_regs.h diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index db475e44f42f..0cc7710f32da 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -149,6 +149,7 @@ static int arch__associate_ins_ops(struct arch* arch, const char *name, struct i #include "arch/arm/annotate/instructions.c" #include "arch/arm64/annotate/instructions.c" #include "arch/csky/annotate/instructions.c" +#include "arch/loongarch/annotate/instructions.c" #include "arch/mips/annotate/instructions.c" #include "arch/x86/annotate/instructions.c" #include "arch/powerpc/annotate/instructions.c" @@ -211,6 +212,13 @@ static struct arch architectures[] = { .comment_char = '#', }, }, + { + .name = "loongarch", + .init = loongarch__annotate_init, + .objdump = { + .comment_char = '#', + }, + }, }; static void ins__delete(struct ins_operands *ops) diff --git a/tools/perf/util/dwarf-regs.c b/tools/perf/util/dwarf-regs.c index 3fa4486742cd..69cfaa5953bf 100644 --- a/tools/perf/util/dwarf-regs.c +++ b/tools/perf/util/dwarf-regs.c @@ -14,6 +14,10 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef EM_LOONGARCH +#define EM_LOONGARCH 258 /* LoongArch */ +#endif + /* Define const char * {arch}_register_tbl[] */ #define DEFINE_DWARF_REGSTR_TABLE #include "../arch/x86/include/dwarf-regs-table.h" @@ -25,6 +29,7 @@ #include "../arch/sparc/include/dwarf-regs-table.h" #include "../arch/xtensa/include/dwarf-regs-table.h" #include "../arch/mips/include/dwarf-regs-table.h" +#include "../arch/loongarch/include/dwarf-regs-table.h" #define __get_dwarf_regstr(tbl, n) (((n) < ARRAY_SIZE(tbl)) ? (tbl)[(n)] : NULL) @@ -56,6 +61,8 @@ const char *get_dwarf_regstr(unsigned int n, unsigned int machine) return __get_dwarf_regstr(xtensa_regstr_tbl, n); case EM_MIPS: return __get_dwarf_regstr(mips_regstr_tbl, n); + case EM_LOONGARCH: + return __get_dwarf_regstr(loongarch_regstr_tbl, n); default: pr_err("ELF MACHINE %x is not supported.\n", machine); } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 5b8cf6a421a4..0d5d40cb997b 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -435,6 +435,8 @@ static const char *normalize_arch(char *arch) return "mips"; if (!strncmp(arch, "sh", 2) && isdigit(arch[2])) return "sh"; + if (!strncmp(arch, "loongarch", 9)) + return "loongarch"; return arch; } diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index 6af062d1c452..5f18d20ea903 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -43,6 +43,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent #elif defined(__riscv) && __riscv_xlen == 64 #define GEN_ELF_ARCH EM_RISCV #define GEN_ELF_CLASS ELFCLASS64 +#elif defined(__loongarch__) +#define GEN_ELF_ARCH EM_LOONGARCH +#define GEN_ELF_CLASS ELFCLASS64 #else #error "unsupported architecture" #endif diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 57a567ee2cea..9bdbaa37f813 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -28,6 +28,7 @@ uint64_t __weak arch__user_reg_mask(void) #include "../../arch/arm/include/uapi/asm/perf_regs.h" #include "../../arch/csky/include/uapi/asm/perf_regs.h" +#include "../../arch/loongarch/include/uapi/asm/perf_regs.h" #include "../../arch/mips/include/uapi/asm/perf_regs.h" #include "../../arch/powerpc/include/uapi/asm/perf_regs.h" #include "../../arch/riscv/include/uapi/asm/perf_regs.h" @@ -236,6 +237,79 @@ static const char *__perf_reg_name_csky(int id) return NULL; } +static inline const char *__perf_reg_name_loongarch(int id) +{ + switch (id) { + case PERF_REG_LOONGARCH_PC: + return "PC"; + case PERF_REG_LOONGARCH_R1: + return "%r1"; + case PERF_REG_LOONGARCH_R2: + return "%r2"; + case PERF_REG_LOONGARCH_R3: + return "%r3"; + case PERF_REG_LOONGARCH_R4: + return "%r4"; + case PERF_REG_LOONGARCH_R5: + return "%r5"; + case PERF_REG_LOONGARCH_R6: + return "%r6"; + case PERF_REG_LOONGARCH_R7: + return "%r7"; + case PERF_REG_LOONGARCH_R8: + return "%r8"; + case PERF_REG_LOONGARCH_R9: + return "%r9"; + case PERF_REG_LOONGARCH_R10: + return "%r10"; + case PERF_REG_LOONGARCH_R11: + return "%r11"; + case PERF_REG_LOONGARCH_R12: + return "%r12"; + case PERF_REG_LOONGARCH_R13: + return "%r13"; + case PERF_REG_LOONGARCH_R14: + return "%r14"; + case PERF_REG_LOONGARCH_R15: + return "%r15"; + case PERF_REG_LOONGARCH_R16: + return "%r16"; + case PERF_REG_LOONGARCH_R17: + return "%r17"; + case PERF_REG_LOONGARCH_R18: + return "%r18"; + case PERF_REG_LOONGARCH_R19: + return "%r19"; + case PERF_REG_LOONGARCH_R20: + return "%r20"; + case PERF_REG_LOONGARCH_R21: + return "%r21"; + case PERF_REG_LOONGARCH_R22: + return "%r22"; + case PERF_REG_LOONGARCH_R23: + return "%r23"; + case PERF_REG_LOONGARCH_R24: + return "%r24"; + case PERF_REG_LOONGARCH_R25: + return "%r25"; + case PERF_REG_LOONGARCH_R26: + return "%r26"; + case PERF_REG_LOONGARCH_R27: + return "%r27"; + case PERF_REG_LOONGARCH_R28: + return "%r28"; + case PERF_REG_LOONGARCH_R29: + return "%r29"; + case PERF_REG_LOONGARCH_R30: + return "%r30"; + case PERF_REG_LOONGARCH_R31: + return "%r31"; + default: + break; + } + return NULL; +} + static const char *__perf_reg_name_mips(int id) { switch (id) { @@ -670,6 +744,8 @@ const char *perf_reg_name(int id, const char *arch) if (!strcmp(arch, "csky")) reg_name = __perf_reg_name_csky(id); + else if (!strcmp(arch, "loongarch")) + reg_name = __perf_reg_name_loongarch(id); else if (!strcmp(arch, "mips")) reg_name = __perf_reg_name_mips(id); else if (!strcmp(arch, "powerpc")) diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c index a2e906858891..313eccef6cb4 100644 --- a/tools/perf/util/syscalltbl.c +++ b/tools/perf/util/syscalltbl.c @@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_arm64; #include const int syscalltbl_native_max_id = SYSCALLTBL_MIPS_N64_MAX_ID; static const char **syscalltbl_native = syscalltbl_mips_n64; +#elif defined(__loongarch__) +#include +const int syscalltbl_native_max_id = SYSCALLTBL_LOONGARCH_MAX_ID; +static const char **syscalltbl_native = syscalltbl_loongarch; #endif struct syscall { -- GitLab From 53bea86b5712c7491bb3dae12e271666df0a308c Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 1 May 2023 15:11:55 -0700 Subject: [PATCH 4367/5631] Revert "Input: xpad - fix support for some third-party controllers" This reverts commit db7220c48d8d71476f881a7ae1285e1df4105409 because it causes crashes when trying to dereference xpad->dev->dev in xpad_probe() which has not been set up yet. Reported-by: syzbot+a3f758b8d8cb7e49afec@syzkaller.appspotmail.com Reported-by: Dongliang Mu Link: https://groups.google.com/g/syzkaller-bugs/c/iMhTgpGuIbM Signed-off-by: Dmitry Torokhov --- drivers/input/joystick/xpad.c | 23 ----------------------- 1 file changed, 23 deletions(-) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 138e4a9f341f..50ecff681b89 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -264,7 +264,6 @@ static const struct xpad_device { { 0x0f0d, 0x0067, "HORIPAD ONE", 0, XTYPE_XBOXONE }, { 0x0f0d, 0x0078, "Hori Real Arcade Pro V Kai Xbox One", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, { 0x0f0d, 0x00c5, "Hori Fighting Commander ONE", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, - { 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX }, { 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX }, { 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX }, @@ -2032,28 +2031,6 @@ static int xpad_probe(struct usb_interface *intf, const struct usb_device_id *id goto err_free_in_urb; } - if (xpad->xtype == XTYPE_XBOX360) { - /* - * Some third-party controllers Xbox 360-style controllers - * require this message to finish initialization. - */ - u8 dummy[20]; - - error = usb_control_msg_recv(udev, 0, - /* bRequest */ 0x01, - /* bmRequestType */ - USB_TYPE_VENDOR | USB_DIR_IN | - USB_RECIP_INTERFACE, - /* wValue */ 0x100, - /* wIndex */ 0x00, - dummy, sizeof(dummy), - 25, GFP_KERNEL); - if (error) - dev_warn(&xpad->dev->dev, - "unable to receive magic message: %d\n", - error); - } - ep_irq_in = ep_irq_out = NULL; for (i = 0; i < 2; i++) { -- GitLab From f9c4bbddece7eff1155c70d48e3c9c2a01b9d778 Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Mon, 1 May 2023 15:33:54 -0700 Subject: [PATCH 4368/5631] riscv: compat_syscall_table: Fixup compile warning ../arch/riscv/kernel/compat_syscall_table.c:12:41: warning: initialized field overwritten [-Woverride-init] 12 | #define __SYSCALL(nr, call) [nr] = (call), | ^ ../include/uapi/asm-generic/unistd.h:567:1: note: in expansion of macro '__SYSCALL' 567 | __SYSCALL(__NR_semget, sys_semget) Fixes: 59c10c52f573 ("riscv: compat: syscall: Add compat_sys_call_table implementation") Reviewed-by: Conor Dooley Reported-by: kernel test robot Tested-by: Jisheng Zhang Signed-off-by: Guo Ren Signed-off-by: Guo Ren Signed-off-by: Drew Fustini Link: https://lore.kernel.org/r/20230501223353.2833899-1-dfustini@baylibre.com Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a6a03edfd86e..fbdccc21418a 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -9,6 +9,7 @@ CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) +CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_KEXEC AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) -- GitLab From b82a5c42a5fa7e79426ed047ced3f8482bb66fbc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:14:27 +1000 Subject: [PATCH 4369/5631] xfs: don't unconditionally null args->pag in xfs_bmap_btalloc_at_eof xfs/170 on a filesystem with su=128k,sw=4 produces this splat: BUG: kernel NULL pointer dereference, address: 0000000000000010 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP CPU: 1 PID: 4022907 Comm: dd Tainted: G W 6.3.0-xfsx #2 6ebeeffbe9577d32 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20171121_152543-x86-ol7-bu RIP: 0010:xfs_perag_rele+0x10/0x70 [xfs] RSP: 0018:ffffc90001e43858 EFLAGS: 00010217 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000100 RDX: ffffffffa054e717 RSI: 0000000000000005 RDI: 0000000000000000 RBP: ffff888194eea000 R08: 0000000000000000 R09: 0000000000000037 R10: ffff888100ac1cb0 R11: 0000000000000018 R12: 0000000000000000 R13: ffffc90001e43a38 R14: ffff888194eea000 R15: ffff888194eea000 FS: 00007f93d1a0e740(0000) GS:ffff88843fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 000000018a34f000 CR4: 00000000003506e0 Call Trace: xfs_bmap_btalloc+0x1a7/0x5d0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_bmapi_allocate+0xee/0x470 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_bmapi_write+0x539/0x9e0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_iomap_write_direct+0x1bb/0x2b0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_direct_write_iomap_begin+0x51c/0x710 [xfs f85291d6841cbb3dc740083f1f331c0327394518] iomap_iter+0x132/0x2f0 __iomap_dio_rw+0x2f8/0x840 iomap_dio_rw+0xe/0x30 xfs_file_dio_write_aligned+0xad/0x180 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_file_write_iter+0xfb/0x190 [xfs f85291d6841cbb3dc740083f1f331c0327394518] vfs_write+0x2eb/0x410 ksys_write+0x65/0xe0 do_syscall_64+0x2b/0x80 This crash occurs under the "out_low_space" label. We grabbed a perag reference, passed it via args->pag into xfs_bmap_btalloc_at_eof, and afterwards args->pag is NULL. Fix the second function not to clobber args->pag if the caller had passed one in. Fixes: 85843327094f ("xfs: factor xfs_bmap_btalloc()") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b512de0540d5..cd8870a16fd1 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3494,8 +3494,10 @@ xfs_bmap_btalloc_at_eof( if (!caller_pag) args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno)); error = xfs_alloc_vextent_exact_bno(args, ap->blkno); - if (!caller_pag) + if (!caller_pag) { xfs_perag_put(args->pag); + args->pag = NULL; + } if (error) return error; @@ -3505,7 +3507,6 @@ xfs_bmap_btalloc_at_eof( * Exact allocation failed. Reset to try an aligned allocation * according to the original allocation specification. */ - args->pag = NULL; args->alignment = stripe_align; args->minlen = nextminlen; args->minalignslop = 0; -- GitLab From 8e698ee72c4ecbbf18264568eb310875839fd601 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:14:36 +1000 Subject: [PATCH 4370/5631] xfs: set bnobt/cntbt numrecs correctly when formatting new AGs Through generic/300, I discovered that mkfs.xfs creates corrupt filesystems when given these parameters: # mkfs.xfs -d size=512M /dev/sda -f -d su=128k,sw=4 --unsupported Filesystems formatted with --unsupported are not supported!! meta-data=/dev/sda isize=512 agcount=8, agsize=16352 blks = sectsz=512 attr=2, projid32bit=1 = crc=1 finobt=1, sparse=1, rmapbt=1 = reflink=1 bigtime=1 inobtcount=1 nrext64=1 data = bsize=4096 blocks=130816, imaxpct=25 = sunit=32 swidth=128 blks naming =version 2 bsize=4096 ascii-ci=0, ftype=1 log =internal log bsize=4096 blocks=8192, version=2 = sectsz=512 sunit=32 blks, lazy-count=1 realtime =none extsz=4096 blocks=0, rtextents=0 = rgcount=0 rgsize=0 blks Discarding blocks...Done. # xfs_repair -n /dev/sda Phase 1 - find and verify superblock... - reporting progress in intervals of 15 minutes Phase 2 - using internal log - zero log... - 16:30:50: zeroing log - 16320 of 16320 blocks done - scan filesystem freespace and inode maps... agf_freeblks 25, counted 0 in ag 4 sb_fdblocks 8823, counted 8798 The root cause of this problem is the numrecs handling in xfs_freesp_init_recs, which is used to initialize a new AG. Prior to calling the function, we set up the new bnobt block with numrecs == 1 and rely on _freesp_init_recs to format that new record. If the last record created has a blockcount of zero, then it sets numrecs = 0. That last bit isn't correct if the AG contains the log, the start of the log is not immediately after the initial blocks due to stripe alignment, and the end of the log is perfectly aligned with the end of the AG. For this case, we actually formatted a single bnobt record to handle the free space before the start of the (stripe aligned) log, and incremented arec to try to format a second record. That second record turned out to be unnecessary, so what we really want is to leave numrecs at 1. The numrecs handling itself is overly complicated because a different function sets numrecs == 1. Change the bnobt creation code to start with numrecs set to zero and only increment it after successfully formatting a free space extent into the btree block. Fixes: f327a00745ff ("xfs: account for log space when formatting new AGs") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_ag.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 1b078bbbf225..9b373a0c7aaf 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -495,10 +495,12 @@ xfs_freesp_init_recs( ASSERT(start >= mp->m_ag_prealloc_blocks); if (start != mp->m_ag_prealloc_blocks) { /* - * Modify first record to pad stripe align of log + * Modify first record to pad stripe align of log and + * bump the record count. */ arec->ar_blockcount = cpu_to_be32(start - mp->m_ag_prealloc_blocks); + be16_add_cpu(&block->bb_numrecs, 1); nrec = arec + 1; /* @@ -509,7 +511,6 @@ xfs_freesp_init_recs( be32_to_cpu(arec->ar_startblock) + be32_to_cpu(arec->ar_blockcount)); arec = nrec; - be16_add_cpu(&block->bb_numrecs, 1); } /* * Change record start to after the internal log @@ -518,15 +519,13 @@ xfs_freesp_init_recs( } /* - * Calculate the record block count and check for the case where - * the log might have consumed all available space in the AG. If - * so, reset the record count to 0 to avoid exposure of an invalid - * record start block. + * Calculate the block count of this record; if it is nonzero, + * increment the record count. */ arec->ar_blockcount = cpu_to_be32(id->agsize - be32_to_cpu(arec->ar_startblock)); - if (!arec->ar_blockcount) - block->bb_numrecs = 0; + if (arec->ar_blockcount) + be16_add_cpu(&block->bb_numrecs, 1); } /* @@ -538,7 +537,7 @@ xfs_bnoroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno); + xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } @@ -548,7 +547,7 @@ xfs_cntroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno); + xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno); xfs_freesp_init_recs(mp, bp, id); } -- GitLab From 397b2d7e0f3e28bbeaa05cf8e10d0fd601f446f4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:14:43 +1000 Subject: [PATCH 4371/5631] xfs: flush dirty data and drain directios before scrubbing cow fork When we're scrubbing the COW fork, we need to take MMAPLOCK_EXCL to prevent page_mkwrite from modifying any inode state. The ILOCK should suffice to avoid confusing online fsck, but let's take the same locks that we do everywhere else. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/scrub/bmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 87ab9f95a487..69bc89d0fc68 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -42,12 +42,12 @@ xchk_setup_inode_bmap( xfs_ilock(sc->ip, XFS_IOLOCK_EXCL); /* - * We don't want any ephemeral data fork updates sitting around + * We don't want any ephemeral data/cow fork updates sitting around * while we inspect block mappings, so wait for directio to finish * and flush dirty data if we have delalloc reservations. */ if (S_ISREG(VFS_I(sc->ip)->i_mode) && - sc->sm->sm_type == XFS_SCRUB_TYPE_BMBTD) { + sc->sm->sm_type != XFS_SCRUB_TYPE_BMBTA) { struct address_space *mapping = VFS_I(sc->ip)->i_mapping; sc->ilock_flags |= XFS_MMAPLOCK_EXCL; -- GitLab From 1f1397b7218d7f8e53e33c6b58cbf9601cd2d8e6 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:14:51 +1000 Subject: [PATCH 4372/5631] xfs: don't allocate into the data fork for an unshare request For an unshare request, we only have to take action if the data fork has a shared mapping. We don't care if someone else set up a cow operation. If we find nothing in the data fork, return a hole to avoid allocating space. Note that fallocate will replace the delalloc reservation with an unwritten extent anyway, so this has no user-visible effects outside of avoiding unnecessary updates. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_iomap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 285885c308bd..18c8f168b153 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1006,8 +1006,9 @@ xfs_buffered_write_iomap_begin( if (eof) imap.br_startoff = end_fsb; /* fake hole until the end */ - /* We never need to allocate blocks for zeroing a hole. */ - if ((flags & IOMAP_ZERO) && imap.br_startoff > offset_fsb) { + /* We never need to allocate blocks for zeroing or unsharing a hole. */ + if ((flags & (IOMAP_UNSHARE | IOMAP_ZERO)) && + imap.br_startoff > offset_fsb) { xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff); goto out_unlock; } -- GitLab From 1bba82fe1afac69c85c1f5ea137c8e73de3c8032 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:15:01 +1000 Subject: [PATCH 4373/5631] xfs: fix negative array access in xfs_getbmap In commit 8ee81ed581ff, Ye Bin complained about an ASSERT in the bmapx code that trips if we encounter a delalloc extent after flushing the pagecache to disk. The ioctl code does not hold MMAPLOCK so it's entirely possible that a racing write page fault can create a delalloc extent after the file has been flushed. The proposed solution was to replace the assertion with an early return that avoids filling out the bmap recordset with a delalloc entry if the caller didn't ask for it. At the time, I recall thinking that the forward logic sounded ok, but felt hesitant because I suspected that changing this code would cause something /else/ to burst loose due to some other subtlety. syzbot of course found that subtlety. If all the extent mappings found after the flush are delalloc mappings, we'll reach the end of the data fork without ever incrementing bmv->bmv_entries. This is new, since before we'd have emitted the delalloc mappings even though the caller didn't ask for them. Once we reach the end, we'll try to set BMV_OF_LAST on the -1st entry (because bmv_entries is zero) and go corrupt something else in memory. Yay. I really dislike all these stupid patches that fiddle around with debug code and break things that otherwise worked well enough. Nobody was complaining that calling XFS_IOC_BMAPX without BMV_IF_DELALLOC would return BMV_OF_DELALLOC records, and now we've gone from "weird behavior that nobody cared about" to "bad behavior that must be addressed immediately". Maybe I'll just ignore anything from Huawei from now on for my own sake. Reported-by: syzbot+c103d3808a0de5faaf80@syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-xfs/20230412024907.GP360889@frogsfrogsfrogs/ Fixes: 8ee81ed581ff ("xfs: fix BUG_ON in xfs_getbmap()") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_bmap_util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index f032d3a4b727..fbb675563208 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -558,7 +558,9 @@ xfs_getbmap( if (!xfs_iext_next_extent(ifp, &icur, &got)) { xfs_fileoff_t end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); - out[bmv->bmv_entries - 1].bmv_oflags |= BMV_OF_LAST; + if (bmv->bmv_entries > 0) + out[bmv->bmv_entries - 1].bmv_oflags |= + BMV_OF_LAST; if (whichfork != XFS_ATTR_FORK && bno < end && !xfs_getbmap_full(bmv)) { -- GitLab From 03e0add80f4cf3f7393edb574eeb3a89a1db7758 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:16:05 +1000 Subject: [PATCH 4374/5631] xfs: explicitly specify cpu when forcing inodegc delayed work to run immediately I've been noticing odd racing behavior in the inodegc code that could only be explained by one cpu adding an inode to its inactivation llist at the same time that another cpu is processing that cpu's llist. Preemption is disabled between get/put_cpu_ptr, so the only explanation is scheduler mayhem. I inserted the following debug code into xfs_inodegc_worker (see the next patch): ASSERT(gc->cpu == smp_processor_id()); This assertion tripped during overnight tests on the arm64 machines, but curiously not on x86_64. I think we haven't observed any resource leaks here because the lockfree list code can handle simultaneous llist_add and llist_del_all functions operating on the same list. However, the whole point of having percpu inodegc lists is to take advantage of warm memory caches by inactivating inodes on the last processor to touch the inode. The incorrect scheduling seems to occur after an inodegc worker is subjected to mod_delayed_work(). This wraps mod_delayed_work_on with WORK_CPU_UNBOUND specified as the cpu number. Unbound allows for scheduling on any cpu, not necessarily the same one that scheduled the work. Because preemption is disabled for as long as we have the gc pointer, I think it's safe to use current_cpu() (aka smp_processor_id) to queue the delayed work item on the correct cpu. Fixes: 7cf2b0f9611b ("xfs: bound maximum wait time for inodegc work") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 351849fc18ff..58712113d5d6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -2069,7 +2069,8 @@ xfs_inodegc_queue( queue_delay = 0; trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay); + mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, + queue_delay); put_cpu_ptr(gc); if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) { @@ -2113,7 +2114,8 @@ xfs_inodegc_cpu_dead( if (xfs_is_inodegc_enabled(mp)) { trace_xfs_inodegc_queue(mp, __return_address); - mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0); + mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work, + 0); } put_cpu_ptr(gc); } -- GitLab From b37c4c8339cd394ea6b8b415026603320a185651 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:16:12 +1000 Subject: [PATCH 4375/5631] xfs: check that per-cpu inodegc workers actually run on that cpu Now that we've allegedly worked out the problem of the per-cpu inodegc workers being scheduled on the wrong cpu, let's put in a debugging knob to let us know if a worker ever gets mis-scheduled again. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 2 ++ fs/xfs/xfs_mount.h | 3 +++ fs/xfs/xfs_super.c | 3 +++ 3 files changed, 8 insertions(+) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 58712113d5d6..4b63c065ef19 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1856,6 +1856,8 @@ xfs_inodegc_worker( struct xfs_inode *ip, *n; unsigned int nofs_flag; + ASSERT(gc->cpu == smp_processor_id()); + WRITE_ONCE(gc->items, 0); if (!node) diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f3269c0626f0..aaaf5ec13492 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -66,6 +66,9 @@ struct xfs_inodegc { /* approximate count of inodes in the list */ unsigned int items; unsigned int shrinker_hits; +#if defined(DEBUG) || defined(XFS_WARN) + unsigned int cpu; +#endif }; /* diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4d2e87462ac4..7e706255f165 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1095,6 +1095,9 @@ xfs_inodegc_init_percpu( for_each_possible_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); +#if defined(DEBUG) || defined(XFS_WARN) + gc->cpu = cpu; +#endif init_llist_head(&gc->list); gc->items = 0; INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker); -- GitLab From 2d5f38a31980d7090f5bf91021488dc61a0ba8ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:16:14 +1000 Subject: [PATCH 4376/5631] xfs: disable reaping in fscounters scrub The fscounters scrub code doesn't work properly because it cannot quiesce updates to the percpu counters in the filesystem, hence it returns false corruption reports. This has been fixed properly in one of the online repair patchsets that are under review by replacing the xchk_disable_reaping calls with an exclusive filesystem freeze. Disabling background gc isn't sufficient to fix the problem. In other words, scrub doesn't need to call xfs_inodegc_stop, which is just as well since it wasn't correct to allow scrub to call xfs_inodegc_start when something else could be calling xfs_inodegc_stop (e.g. trying to freeze the filesystem). Neuter the scrubber for now, and remove the xchk_*_reaping functions. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/scrub/common.c | 26 -------------------------- fs/xfs/scrub/common.h | 2 -- fs/xfs/scrub/fscounters.c | 13 ++++++------- fs/xfs/scrub/scrub.c | 2 -- fs/xfs/scrub/scrub.h | 1 - fs/xfs/scrub/trace.h | 1 - 6 files changed, 6 insertions(+), 39 deletions(-) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 9aa79665c608..7a20256be969 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -1164,32 +1164,6 @@ xchk_metadata_inode_forks( return 0; } -/* Pause background reaping of resources. */ -void -xchk_stop_reaping( - struct xfs_scrub *sc) -{ - sc->flags |= XCHK_REAPING_DISABLED; - xfs_blockgc_stop(sc->mp); - xfs_inodegc_stop(sc->mp); -} - -/* Restart background reaping of resources. */ -void -xchk_start_reaping( - struct xfs_scrub *sc) -{ - /* - * Readonly filesystems do not perform inactivation or speculative - * preallocation, so there's no need to restart the workers. - */ - if (!xfs_is_readonly(sc->mp)) { - xfs_inodegc_start(sc->mp); - xfs_blockgc_start(sc->mp); - } - sc->flags &= ~XCHK_REAPING_DISABLED; -} - /* * Enable filesystem hooks (i.e. runtime code patching) before starting a scrub * operation. Callers must not hold any locks that intersect with the CPU diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index 18b5f2b62f13..791235cd9b00 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -156,8 +156,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) } int xchk_metadata_inode_forks(struct xfs_scrub *sc); -void xchk_stop_reaping(struct xfs_scrub *sc); -void xchk_start_reaping(struct xfs_scrub *sc); /* * Setting up a hook to wait for intents to drain is costly -- we have to take diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index faa315be7978..e382a35e98d8 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -150,13 +150,6 @@ xchk_setup_fscounters( if (error) return error; - /* - * Pause background reclaim while we're scrubbing to reduce the - * likelihood of background perturbations to the counters throwing off - * our calculations. - */ - xchk_stop_reaping(sc); - return xchk_trans_alloc(sc, 0); } @@ -453,6 +446,12 @@ xchk_fscounters( if (frextents > mp->m_sb.sb_rextents) xchk_set_corrupt(sc); + /* + * XXX: We can't quiesce percpu counter updates, so exit early. + * This can be re-enabled when we gain exclusive freeze functionality. + */ + return 0; + /* * If ifree exceeds icount by more than the minimum variance then * something's probably wrong with the counters. diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 02819bedc5b1..3d98f604765e 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -186,8 +186,6 @@ xchk_teardown( } if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) mnt_drop_write_file(sc->file); - if (sc->flags & XCHK_REAPING_DISABLED) - xchk_start_reaping(sc); if (sc->buf) { if (sc->buf_cleanup) sc->buf_cleanup(sc->buf); diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index e71903474cd7..b38e93830dde 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -106,7 +106,6 @@ struct xfs_scrub { /* XCHK state flags grow up from zero, XREP state flags grown down from 2^31 */ #define XCHK_TRY_HARDER (1 << 0) /* can't get resources, try again */ -#define XCHK_REAPING_DISABLED (1 << 1) /* background block reaping paused */ #define XCHK_FSGATES_DRAIN (1 << 2) /* defer ops draining enabled */ #define XCHK_NEED_DRAIN (1 << 3) /* scrub needs to drain defer ops */ #define XREP_ALREADY_FIXED (1 << 31) /* checking our repair work */ diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 68efd6fda61c..b3894daeb86a 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -98,7 +98,6 @@ TRACE_DEFINE_ENUM(XFS_SCRUB_TYPE_FSCOUNTERS); #define XFS_SCRUB_STATE_STRINGS \ { XCHK_TRY_HARDER, "try_harder" }, \ - { XCHK_REAPING_DISABLED, "reaping_disabled" }, \ { XCHK_FSGATES_DRAIN, "fsgates_drain" }, \ { XCHK_NEED_DRAIN, "need_drain" }, \ { XREP_ALREADY_FIXED, "already_fixed" } -- GitLab From 2254a7396a0ca6309854948ee1c0a33fa4268cec Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:16:14 +1000 Subject: [PATCH 4377/5631] xfs: fix xfs_inodegc_stop racing with mod_delayed_work syzbot reported this warning from the faux inodegc shrinker that tries to kick off inodegc work: ------------[ cut here ]------------ WARNING: CPU: 1 PID: 102 at kernel/workqueue.c:1445 __queue_work+0xd44/0x1120 kernel/workqueue.c:1444 RIP: 0010:__queue_work+0xd44/0x1120 kernel/workqueue.c:1444 Call Trace: __queue_delayed_work+0x1c8/0x270 kernel/workqueue.c:1672 mod_delayed_work_on+0xe1/0x220 kernel/workqueue.c:1746 xfs_inodegc_shrinker_scan fs/xfs/xfs_icache.c:2212 [inline] xfs_inodegc_shrinker_scan+0x250/0x4f0 fs/xfs/xfs_icache.c:2191 do_shrink_slab+0x428/0xaa0 mm/vmscan.c:853 shrink_slab+0x175/0x660 mm/vmscan.c:1013 shrink_one+0x502/0x810 mm/vmscan.c:5343 shrink_many mm/vmscan.c:5394 [inline] lru_gen_shrink_node mm/vmscan.c:5511 [inline] shrink_node+0x2064/0x35f0 mm/vmscan.c:6459 kswapd_shrink_node mm/vmscan.c:7262 [inline] balance_pgdat+0xa02/0x1ac0 mm/vmscan.c:7452 kswapd+0x677/0xd60 mm/vmscan.c:7712 kthread+0x2e8/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 This warning corresponds to this code in __queue_work: /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq)))) return; For this to trip, we must have a thread draining the inodedgc workqueue and a second thread trying to queue inodegc work to that workqueue. This can happen if freezing or a ro remount race with reclaim poking our faux inodegc shrinker and another thread dropping an unlinked O_RDONLY file: Thread 0 Thread 1 Thread 2 xfs_inodegc_stop xfs_inodegc_shrinker_scan xfs_is_inodegc_enabled xfs_clear_inodegc_enabled xfs_inodegc_queue_all xfs_inodegc_queue xfs_is_inodegc_enabled drain_workqueue llist_empty mod_delayed_work_on(..., 0) __queue_work In other words, everything between the access to inodegc_enabled state and the decision to poke the inodegc workqueue requires some kind of coordination to avoid the WQ_DRAINING state. We could perhaps introduce a lock here, but we could also try to eliminate WQ_DRAINING from the picture. We could replace the drain_workqueue call with a loop that flushes the workqueue and queues workers as long as there is at least one inode present in the per-cpu inodegc llists. We've disabled inodegc at this point, so we know that the number of queued inodes will eventually hit zero as long as xfs_inodegc_start cannot reactivate the workers. There are four callers of xfs_inodegc_start. Three of them come from the VFS with s_umount held: filesystem thawing, failed filesystem freezing, and the rw remount transition. The fourth caller is mounting rw (no remount or freezing possible). There are three callers ofs xfs_inodegc_stop. One is unmounting (no remount or thaw possible). Two of them come from the VFS with s_umount held: fs freezing and ro remount transition. Hence, it is correct to replace the drain_workqueue call with a loop that drains the inodegc llists. Fixes: 6191cf3ad59f ("xfs: flush inodegc workqueue tasks before cancel") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/xfs_icache.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 4b63c065ef19..0f60e301eb1f 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -435,18 +435,23 @@ xfs_iget_check_free_state( } /* Make all pending inactivation work start immediately. */ -static void +static bool xfs_inodegc_queue_all( struct xfs_mount *mp) { struct xfs_inodegc *gc; int cpu; + bool ret = false; for_each_online_cpu(cpu) { gc = per_cpu_ptr(mp->m_inodegc, cpu); - if (!llist_empty(&gc->list)) + if (!llist_empty(&gc->list)) { mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0); + ret = true; + } } + + return ret; } /* @@ -1911,24 +1916,41 @@ xfs_inodegc_flush( /* * Flush all the pending work and then disable the inode inactivation background - * workers and wait for them to stop. + * workers and wait for them to stop. Caller must hold sb->s_umount to + * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_stop( struct xfs_mount *mp) { + bool rerun; + if (!xfs_clear_inodegc_enabled(mp)) return; + /* + * Drain all pending inodegc work, including inodes that could be + * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan + * threads that sample the inodegc state just prior to us clearing it. + * The inodegc flag state prevents new threads from queuing more + * inodes, so we queue pending work items and flush the workqueue until + * all inodegc lists are empty. IOWs, we cannot use drain_workqueue + * here because it does not allow other unserialized mechanisms to + * reschedule inodegc work while this draining is in progress. + */ xfs_inodegc_queue_all(mp); - drain_workqueue(mp->m_inodegc_wq); + do { + flush_workqueue(mp->m_inodegc_wq); + rerun = xfs_inodegc_queue_all(mp); + } while (rerun); trace_xfs_inodegc_stop(mp, __return_address); } /* * Enable the inode inactivation background workers and schedule deferred inode - * inactivation work if there is any. + * inactivation work if there is any. Caller must hold sb->s_umount to + * coordinate changes in the inodegc_enabled state. */ void xfs_inodegc_start( -- GitLab From 41ebfc91f785c202e8e8f9bd2f67154efad6287e Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 27 Apr 2023 11:43:42 +0100 Subject: [PATCH 4378/5631] dt-bindings: riscv: explicitly mention assumption of Zicsr & Zifencei support The dt-binding was defined before the extraction of csr access and fence.i into their own extensions, and thus the presence of the I base extension implies Zicsr and Zifencei. There's no harm in adding them obviously, but for backwards compatibility with DTs that existed prior to that extraction, software is unable to differentiate between "i" and "i_zicsr_zifencei" without any further information. Signed-off-by: Conor Dooley Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230427-fence-blurred-c92fb69d4137@wendy Signed-off-by: Palmer Dabbelt --- Documentation/devicetree/bindings/riscv/cpus.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 25d6e8dbffb8..3d2934b15e80 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -86,6 +86,12 @@ properties: User-Level ISA document, available from https://riscv.org/specifications/ + Due to revisions of the ISA specification, some deviations + have arisen over time. + Notably, riscv,isa was defined prior to the creation of the + Zicsr and Zifencei extensions and thus "i" implies + "zicsr_zifencei". + While the isa strings in ISA specification are case insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. -- GitLab From 4db9e253e7016e6588620ad02d4ed326107506db Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Fri, 28 Apr 2023 14:09:32 +0200 Subject: [PATCH 4379/5631] riscv: Move .rela.dyn to the init sections The recent introduction of relocatable kernels prepared the move of .rela.dyn to the init section, but actually forgot to do so, so do it here. Before this patch: "Freeing unused kernel image (initmem) memory: 2592K" After this patch: "Freeing unused kernel image (initmem) memory: 6288K" The difference corresponds to the size of the .rela.dyn section: "[42] .rela.dyn RELA ffffffff8197e798 0127f798 000000000039c660 0000000000000018 A 47 0 8" Fixes: 559d1e45a16d ("riscv: Use --emit-relocs in order to move .rela.dyn in init") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230428120932.22735-1-alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/vmlinux.lds.S | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 305877d85e96..f03b5697f8e0 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -104,6 +104,12 @@ SECTIONS *(.rel.dyn*) } + .rela.dyn : ALIGN(8) { + __rela_dyn_start = .; + *(.rela .rela*) + __rela_dyn_end = .; + } + __init_data_end = .; . = ALIGN(8); @@ -130,12 +136,6 @@ SECTIONS *(.sdata*) } - .rela.dyn : ALIGN(8) { - __rela_dyn_start = .; - *(.rela .rela*) - __rela_dyn_end = .; - } - .got : { *(.got*) } #ifdef CONFIG_RELOCATABLE -- GitLab From c2d3c8441e3ddbfe41fea9282ddc6ee372e154cd Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 20 Apr 2023 19:30:16 +0100 Subject: [PATCH 4380/5631] RISC-V: include cpufeature.h in cpufeature.c Automation complains: warning: symbol '__pcpu_scope_misaligned_access_speed' was not declared. Should it be static? cpufeature.c doesn't actually include the header of the same name, as it had not previously used anything from it. The per-cpu variable is declared there, so include it to silence the complaints. Fixes: 62a31d6e38bd ("RISC-V: hwprobe: Support probing of misaligned access performance") Signed-off-by: Conor Dooley Reviewed-by: Evan Green Link: https://lore.kernel.org/r/20230420-wound-gizzard-2b2b589d9bea@spud Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpufeature.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 52585e088873..00f9f57a8566 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include -- GitLab From 0af462f19e635ad522f28981238334620881badc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 1 May 2023 17:42:06 +0200 Subject: [PATCH 4381/5631] debugobject: Ensure pool refill (again) The recent fix to ensure atomicity of lookup and allocation inadvertently broke the pool refill mechanism. Prior to that change debug_objects_activate() and debug_objecs_assert_init() invoked debug_objecs_init() to set up the tracking object for statically initialized objects. That's not longer the case and debug_objecs_init() is now the only place which does pool refills. Depending on the number of statically initialized objects this can be enough to actually deplete the pool, which was observed by Ido via a debugobjects OOM warning. Restore the old behaviour by adding explicit refill opportunities to debug_objects_activate() and debug_objecs_assert_init(). Fixes: 63a759694eed ("debugobject: Prevent init race with static objects") Reported-by: Ido Schimmel Signed-off-by: Thomas Gleixner Tested-by: Ido Schimmel Link: https://lore.kernel.org/r/871qk05a9d.ffs@tglx --- lib/debugobjects.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index b796799fadb2..003edc5ebd67 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -587,6 +587,16 @@ static struct debug_obj *lookup_object_or_alloc(void *addr, struct debug_bucket return NULL; } +static void debug_objects_fill_pool(void) +{ + /* + * On RT enabled kernels the pool refill must happen in preemptible + * context: + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + fill_pool(); +} + static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { @@ -595,12 +605,7 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack struct debug_obj *obj; unsigned long flags; - /* - * On RT enabled kernels the pool refill must happen in preemptible - * context: - */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) - fill_pool(); + debug_objects_fill_pool(); db = get_bucket((unsigned long) addr); @@ -685,6 +690,8 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) if (!debug_objects_enabled) return 0; + debug_objects_fill_pool(); + db = get_bucket((unsigned long) addr); raw_spin_lock_irqsave(&db->lock, flags); @@ -894,6 +901,8 @@ void debug_object_assert_init(void *addr, const struct debug_obj_descr *descr) if (!debug_objects_enabled) return; + debug_objects_fill_pool(); + db = get_bucket((unsigned long) addr); raw_spin_lock_irqsave(&db->lock, flags); -- GitLab From b8969a1b69672b163d057e7745ebc915df689211 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Tue, 2 May 2023 10:02:33 +0200 Subject: [PATCH 4382/5631] crypto: api - Fix CRYPTO_USER checks for report function Checking the config via ifdef incorrectly compiles out the report functions when CRYPTO_USER is set to =m. Fix it by using IS_ENABLED() instead. Fixes: c0f9e01dd266 ("crypto: api - Check CRYPTO_USER instead of NET for report") Signed-off-by: Ondrej Mosnacek Signed-off-by: Herbert Xu --- crypto/acompress.c | 2 +- crypto/aead.c | 2 +- crypto/ahash.c | 2 +- crypto/akcipher.c | 2 +- crypto/kpp.c | 2 +- crypto/rng.c | 2 +- crypto/scompress.c | 2 +- crypto/shash.c | 2 +- crypto/skcipher.c | 2 +- 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/crypto/acompress.c b/crypto/acompress.c index 82a290df2822..1c682810a484 100644 --- a/crypto/acompress.c +++ b/crypto/acompress.c @@ -125,7 +125,7 @@ static const struct crypto_type crypto_acomp_type = { #ifdef CONFIG_PROC_FS .show = crypto_acomp_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_acomp_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/aead.c b/crypto/aead.c index ffc48a7dfb34..d5ba204ebdbf 100644 --- a/crypto/aead.c +++ b/crypto/aead.c @@ -242,7 +242,7 @@ static const struct crypto_type crypto_aead_type = { #ifdef CONFIG_PROC_FS .show = crypto_aead_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_aead_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/ahash.c b/crypto/ahash.c index b8a607928e72..324651040446 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -509,7 +509,7 @@ static const struct crypto_type crypto_ahash_type = { #ifdef CONFIG_PROC_FS .show = crypto_ahash_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_ahash_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/akcipher.c b/crypto/akcipher.c index 186e762b509a..7960ceb528c3 100644 --- a/crypto/akcipher.c +++ b/crypto/akcipher.c @@ -98,7 +98,7 @@ static const struct crypto_type crypto_akcipher_type = { #ifdef CONFIG_PROC_FS .show = crypto_akcipher_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_akcipher_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/kpp.c b/crypto/kpp.c index 74f2e8e918fa..33d44e59387f 100644 --- a/crypto/kpp.c +++ b/crypto/kpp.c @@ -96,7 +96,7 @@ static const struct crypto_type crypto_kpp_type = { #ifdef CONFIG_PROC_FS .show = crypto_kpp_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_kpp_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/rng.c b/crypto/rng.c index ffde0f64fb25..279dffdebf59 100644 --- a/crypto/rng.c +++ b/crypto/rng.c @@ -118,7 +118,7 @@ static const struct crypto_type crypto_rng_type = { #ifdef CONFIG_PROC_FS .show = crypto_rng_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_rng_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/scompress.c b/crypto/scompress.c index 24138b42a648..442a82c9de7d 100644 --- a/crypto/scompress.c +++ b/crypto/scompress.c @@ -240,7 +240,7 @@ static const struct crypto_type crypto_scomp_type = { #ifdef CONFIG_PROC_FS .show = crypto_scomp_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_scomp_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/shash.c b/crypto/shash.c index 5845b7d59b2f..717b42df3495 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -548,7 +548,7 @@ static const struct crypto_type crypto_shash_type = { #ifdef CONFIG_PROC_FS .show = crypto_shash_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_shash_report, #endif #ifdef CONFIG_CRYPTO_STATS diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 6caca02d7e55..7b275716cf4e 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -776,7 +776,7 @@ static const struct crypto_type crypto_skcipher_type = { #ifdef CONFIG_PROC_FS .show = crypto_skcipher_show, #endif -#ifdef CONFIG_CRYPTO_USER +#if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_skcipher_report, #endif #ifdef CONFIG_CRYPTO_STATS -- GitLab From e53de7b65a3ca59af268c78df2d773f277f717fd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 27 Apr 2023 16:48:32 -0700 Subject: [PATCH 4383/5631] perf lock contention: Fix struct rq lock access The BPF CO-RE's ignore suffix rule requires three underscores. Otherwise it'd fail like below: $ sudo perf lock contention -ab libbpf: prog 'collect_lock_syms': BPF program load failed: Invalid argument libbpf: prog 'collect_lock_syms': -- BEGIN PROG LOAD LOG -- reg type unsupported for arg#0 function collect_lock_syms#380 ; int BPF_PROG(collect_lock_syms) 0: (b7) r6 = 0 ; R6_w=0 1: (b7) r7 = 0 ; R7_w=0 2: (b7) r9 = 1 ; R9_w=1 3: failed to resolve CO-RE relocation [381] struct rq__new.__lock (0:0 @ offset 0) Fixes: 0c1228486befa3d6 ("perf lock contention: Support pre-5.14 kernels") Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Andrii Nakryiko Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230427234833.1576130-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8911e2a077d8..30c193078bdb 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -418,11 +418,11 @@ int contention_end(u64 *ctx) extern struct rq runqueues __ksym; -struct rq__old { +struct rq___old { raw_spinlock_t lock; } __attribute__((preserve_access_index)); -struct rq__new { +struct rq___new { raw_spinlock_t __lock; } __attribute__((preserve_access_index)); @@ -434,8 +434,8 @@ int BPF_PROG(collect_lock_syms) for (int i = 0; i < MAX_CPUS; i++) { struct rq *rq = bpf_per_cpu_ptr(&runqueues, i); - struct rq__new *rq_new = (void *)rq; - struct rq__old *rq_old = (void *)rq; + struct rq___new *rq_new = (void *)rq; + struct rq___old *rq_old = (void *)rq; if (rq == NULL) break; -- GitLab From b9f82b5c63bf5390da19e879275a792a959a8dac Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 27 Apr 2023 16:48:33 -0700 Subject: [PATCH 4384/5631] perf lock contention: Rework offset calculation with BPF CO-RE It seems BPF CO-RE reloc doesn't work well with the pattern that gets the field-offset only. Use offsetof() to make it explicit so that the compiler would generate the correct code. Fixes: 0c1228486befa3d6 ("perf lock contention: Support pre-5.14 kernels") Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Andrii Nakryiko Cc: Hao Luo Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Song Liu Cc: bpf@vger.kernel.org Co-developed-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20230427234833.1576130-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 30c193078bdb..8d3cfbb3cc65 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -429,21 +429,21 @@ struct rq___new { SEC("raw_tp/bpf_test_finish") int BPF_PROG(collect_lock_syms) { - __u64 lock_addr; + __u64 lock_addr, lock_off; __u32 lock_flag; + if (bpf_core_field_exists(struct rq___new, __lock)) + lock_off = offsetof(struct rq___new, __lock); + else + lock_off = offsetof(struct rq___old, lock); + for (int i = 0; i < MAX_CPUS; i++) { struct rq *rq = bpf_per_cpu_ptr(&runqueues, i); - struct rq___new *rq_new = (void *)rq; - struct rq___old *rq_old = (void *)rq; if (rq == NULL) break; - if (bpf_core_field_exists(rq_new->__lock)) - lock_addr = (__u64)&rq_new->__lock; - else - lock_addr = (__u64)&rq_old->lock; + lock_addr = (__u64)(void *)rq + lock_off; lock_flag = LOCK_CLASS_RQLOCK; bpf_map_update_elem(&lock_syms, &lock_addr, &lock_flag, BPF_ANY); } -- GitLab From 7586d11d36fad5e6a28736be7ac8f9495e28289a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 27 Apr 2023 16:05:01 -0700 Subject: [PATCH 4385/5631] perf list: Fix memory leaks in print_tracepoint_events() It should free entries (not only the array) filled by scandirat() after use. Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230427230502.1526136-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/print-events.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index 386b1ab0b60e..f5b2ea0c4fa1 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -83,11 +83,11 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus if (sys_dirent->d_type != DT_DIR || !strcmp(sys_dirent->d_name, ".") || !strcmp(sys_dirent->d_name, "..")) - continue; + goto next_sys; dir_fd = openat(events_fd, sys_dirent->d_name, O_PATH); if (dir_fd < 0) - continue; + goto next_sys; evt_items = scandirat(events_fd, sys_dirent->d_name, &evt_namelist, NULL, alphasort); for (int j = 0; j < evt_items; j++) { @@ -98,12 +98,12 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus if (evt_dirent->d_type != DT_DIR || !strcmp(evt_dirent->d_name, ".") || !strcmp(evt_dirent->d_name, "..")) - continue; + goto next_evt; snprintf(evt_path, sizeof(evt_path), "%s/id", evt_dirent->d_name); evt_fd = openat(dir_fd, evt_path, O_RDONLY); if (evt_fd < 0) - continue; + goto next_evt; close(evt_fd); snprintf(evt_path, MAXPATHLEN, "%s:%s", @@ -119,9 +119,13 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus /*desc=*/NULL, /*long_desc=*/NULL, /*encoding_desc=*/NULL); +next_evt: + free(evt_namelist[j]); } close(dir_fd); free(evt_namelist); +next_sys: + free(sys_namelist[i]); } free(sys_namelist); -- GitLab From 6a7b57d85f4a6232d435eac945b325d9048f030c Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 27 Apr 2023 16:05:02 -0700 Subject: [PATCH 4386/5631] perf list: Modify the warning message about scandirat(3) It should mention scandirat() instead of scandir(). Signed-off-by: Namhyung Kim Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Ingo Molnar Cc: Jiri Olsa Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230427230502.1526136-2-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/print-events.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index f5b2ea0c4fa1..ee145cec42c0 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -131,7 +131,7 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus free(sys_namelist); } #else - printf("\nWARNING: Your libc doesn't have the scandir function, please ask its maintainers to implement it.\n" + printf("\nWARNING: Your libc doesn't have the scandirat function, please ask its maintainers to implement it.\n" " As a rough fallback, please do 'ls %s' to see the available tracepoint events.\n", events_path); #endif close(events_fd); -- GitLab From 1511e4696acb715a4fe48be89e1e691daec91c0e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Thu, 27 Apr 2023 01:28:41 +0000 Subject: [PATCH 4387/5631] perf symbols: Fix return incorrect build_id size in elf_read_build_id() In elf_read_build_id(), if gnu build_id is found, should return the size of the actually copied data. If descsz is greater thanBuild_ID_SIZE, write_buildid data access may occur. Fixes: be96ea8ffa788dcc ("perf symbols: Fix issue with binaries using 16-bytes buildids (v2)") Reported-by: Will Ochowicz Signed-off-by: Yang Jihong Tested-by: Will Ochowicz Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: https://lore.kernel.org/lkml/CWLP265MB49702F7BA3D6D8F13E4B1A719C649@CWLP265MB4970.GBRP265.PROD.OUTLOOK.COM/T/ Link: https://lore.kernel.org/r/20230427012841.231729-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol-elf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 2a165d83aac4..ca75285aa656 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -886,7 +886,7 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size) size_t sz = min(size, descsz); memcpy(bf, ptr, sz); memset(bf + sz, 0, size - sz); - err = descsz; + err = sz; break; } } -- GitLab From 0e20f4311254193fbf9eebafb4dc5c922a885397 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 18 Apr 2023 11:18:23 +0800 Subject: [PATCH 4388/5631] perf script: Print raw ip instead of binary offset for callchain Before this, the raw ip is printed for non-callchain and dso offset for callchain. This inconsistent output for address may confuse people. And mostly what we expect is the raw ip. 'dso offset' is printed in callchain: $ perf script ... ls 1341034 2739463.008343: 2162417 cycles: ffffffff99d657a7 [unknown] ([unknown]) ffffffff99e00b67 [unknown] ([unknown]) 235d3 memset+0x53 (/usr/lib/x86_64-linux-gnu/ld-2.31.so) # dso offset a61b _dl_map_object+0x1bb (/usr/lib/x86_64-linux-gnu/ld-2.31.so) raw ip is printed for non-callchain: $ perf script -G ... ls 1341034 2739463.008876: 2053304 cycles: ffffffffc1596923 [unknown] ([unknown]) ls 1341034 2739463.009381: 1917049 cycles: 14def8e149e6 __strcoll_l+0xd96 (/usr/lib/x86_64-linux-gnu/libc-2.31.so) # raw ip Let's have consistent output for it. Later I'll add a new field 'dsoff' to print dso offset. Signed-off-by: Changbin Du Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Hui Wang Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230418031825.1262579-2-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel_fprintf.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c index a09ac00810b7..cc80ec554c0a 100644 --- a/tools/perf/util/evsel_fprintf.c +++ b/tools/perf/util/evsel_fprintf.c @@ -153,13 +153,8 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment, if (map) addr = map__map_ip(map, node->ip); - if (print_ip) { - /* Show binary offset for userspace addr */ - if (map && !map__dso(map)->kernel) - printed += fprintf(fp, "%c%16" PRIx64, s, addr); - else - printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); - } + if (print_ip) + printed += fprintf(fp, "%c%16" PRIx64, s, node->ip); if (print_sym) { printed += fprintf(fp, " "); -- GitLab From 69b0e112612be9e325ea682263d895f3c675772f Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Wed, 26 Apr 2023 12:41:49 +0200 Subject: [PATCH 4389/5631] perf script: Add new parameter in kfree_skb tracepoint to the python scripts using it Include reason parameter that was added in commit c504e5c2f9648a1e ("net: skb: introduce kfree_skb_reason()") Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Sriram Yagnaraman Link: https://lore.kernel.org/r/20230426104149.14089-1-sriram.yagnaraman@est.tech Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/net_dropmonitor.py | 4 ++-- tools/perf/scripts/python/netdev-times.py | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index 101059971738..a97e7a6e0940 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -68,9 +68,9 @@ def trace_end(): get_kallsyms_table() print_drop_table() -# called from perf, when it finds a correspoinding event +# called from perf, when it finds a corresponding event def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, - skbaddr, location, protocol): + skbaddr, location, protocol, reason): slocation = str(location) try: drop_log[slocation] = drop_log[slocation] + 1 diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py index a0cfc7fe5908..00552eeb7178 100644 --- a/tools/perf/scripts/python/netdev-times.py +++ b/tools/perf/scripts/python/netdev-times.py @@ -288,9 +288,9 @@ def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain, all_event_list.append(event_info) def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, - skbaddr, protocol, location): + skbaddr, location, protocol, reason): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, - skbaddr, protocol, location) + skbaddr, location, protocol, reason) all_event_list.append(event_info) def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr): @@ -430,7 +430,7 @@ def handle_net_dev_xmit(event_info): def handle_kfree_skb(event_info): (name, context, cpu, time, pid, comm, - skbaddr, protocol, location) = event_info + skbaddr, location, protocol, reason) = event_info for i in range(len(tx_queue_list)): skb = tx_queue_list[i] if skb['skbaddr'] == skbaddr: -- GitLab From c31380140f11195abb5b5f576355f886d32afd1c Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Wed, 26 Apr 2023 11:22:46 +0800 Subject: [PATCH 4390/5631] perf unwind: Suppress massive unsupported target platform errors When cross-analyzing perf data recorded on an another platform, massive unsupported target platform errors are printed. So let's show this message as warning and only once. Signed-off-by: Changbin Du Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Hui Wang Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230426032246.3608596-1-changbin.du@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libunwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index b54968e6a4e4..375d23d9a590 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -56,7 +56,7 @@ int unwind__prepare_access(struct maps *maps, struct map *map, bool *initialized } if (!ops) { - pr_err("unwind: target platform=%s is not supported\n", arch); + pr_warning_once("unwind: target platform=%s is not supported\n", arch); return 0; } out_register: -- GitLab From d199226143f0ef6919131120319766ece514314e Mon Sep 17 00:00:00 2001 From: James Clark Date: Tue, 25 Apr 2023 11:44:13 +0100 Subject: [PATCH 4391/5631] perf build: Fix unescaped # in perf build-test With the following bash and make versions: $ make --version GNU Make 4.2.1 Built for aarch64-unknown-linux-gnu $ bash --version GNU bash, version 5.0.17(1)-release (aarch64-unknown-linux-gnu) This error is encountered when running the build-test target: $ make -C tools/perf build-test tests/make:181: *** unterminated call to function 'shell': missing ')'. Stop. make: *** [Makefile:103: build-test] Error 2 Fix it by escaping the # which was causing make to interpret the rest of the line as a comment leaving the unclosed opening bracket. Fixes: 56d5229471ee1634 ("tools build: Pass libbpf feature only if libbpf 1.0+") Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230425104414.1723571-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/make | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/make b/tools/perf/tests/make index d75876126631..8dd3f8090352 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -178,7 +178,7 @@ run += make_install_prefix_slash # run += make_install_pdf run += make_minimal -old_libbpf := $(shell echo "#include " | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}") +old_libbpf := $(shell echo '\#include ' | $(CC) -E -dM -x c -| egrep -q "define[[:space:]]+LIBBPF_MAJOR_VERSION[[:space:]]+0{1}") ifneq ($(old_libbpf),) run += make_libbpf_dynamic -- GitLab From 6bf86cada3eb8ec3eb80cdce5280e7a22dac8b01 Mon Sep 17 00:00:00 2001 From: Ganapatrao Kulkarni Date: Thu, 20 Apr 2023 22:52:53 -0700 Subject: [PATCH 4392/5631] perf cs-etm: Add fix for coresight trace for any range of CPUs The current implementation supports coresight trace decode for a range of CPUs, if the first CPU is CPU0. Perf report segfaults, if tried for sparse CPUs list and also for any range of CPUs(non zero first CPU). Adding a fix to perf report for any range of CPUs and for sparse list. Signed-off-by: Ganapatrao Kulkarni Link: https://lore.kernel.org/r/20230421055253.83912-1-gankulkarni@os.amperecomputing.com Cc: suzuki.poulose@arm.com Cc: acme@kernel.org Cc: mathieu.poirier@linaro.org Cc: mike.leach@linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: darren@os.amperecomputing.com Cc: scclevenger@os.amperecomputing.com Cc: scott@os.amperecomputing.com Cc: linux-kernel@vger.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cs-etm.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 456994564d6e..91299cc56bf7 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -290,6 +290,25 @@ static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata) (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ }) +/* + * Get a metadata for a specific cpu from an array. + * + */ +static u64 *get_cpu_data(struct cs_etm_auxtrace *etm, int cpu) +{ + int i; + u64 *metadata = NULL; + + for (i = 0; i < etm->num_cpu; i++) { + if (etm->metadata[i][CS_ETM_CPU] == (u64)cpu) { + metadata = etm->metadata[i]; + break; + } + } + + return metadata; +} + /* * Handle the PERF_RECORD_AUX_OUTPUT_HW_ID event. * @@ -359,8 +378,11 @@ static int cs_etm__process_aux_output_hw_id(struct perf_session *session, return 0; } + cpu_data = get_cpu_data(etm, cpu); + if (cpu_data == NULL) + return err; + /* not one we've seen before - lets map it */ - cpu_data = etm->metadata[cpu]; err = cs_etm__map_trace_id(trace_chan_id, cpu_data); if (err) return err; -- GitLab From 9b86c49710eec7b4fbb78a0232b2dd0972a2b576 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Fri, 21 Apr 2023 02:59:53 +0000 Subject: [PATCH 4393/5631] perf tracepoint: Fix memory leak in is_valid_tracepoint() When is_valid_tracepoint() returns 1, need to call put_events_file() to free `dir_path`. Fixes: 25a7d914274de386 ("perf parse-events: Use get/put_events_file()") Signed-off-by: Yang Jihong Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230421025953.173826-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/tracepoint.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/tracepoint.c b/tools/perf/util/tracepoint.c index 89ef56c43311..92dd8b455b90 100644 --- a/tools/perf/util/tracepoint.c +++ b/tools/perf/util/tracepoint.c @@ -50,6 +50,7 @@ int is_valid_tracepoint(const char *event_string) sys_dirent->d_name, evt_dirent->d_name); if (!strcmp(evt_path, event_string)) { closedir(evt_dir); + put_events_file(dir_path); closedir(sys_dir); return 1; } -- GitLab From eda081d2efac50c9b314df7fb340a62306a7b07a Mon Sep 17 00:00:00 2001 From: Kristina Martsenko Date: Fri, 28 Apr 2023 14:25:46 +0100 Subject: [PATCH 4394/5631] arm64: cpufeature: Fix pointer auth hwcaps The pointer auth hwcaps are not getting reported to userspace, as they are missing the .matches field. Add the field back. Fixes: 876e3c8efe79 ("arm64/cpufeature: Pull out helper for CPUID register definitions") Signed-off-by: Kristina Martsenko Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20230428132546.2513834-1-kristina.martsenko@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/cpufeature.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 1bdad599e769..d26a11f78b9f 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2657,26 +2657,26 @@ static const struct arm64_cpu_capabilities arm64_features[] = { #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { - ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, APA, PAuth) + HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, APA, PAuth) }, { - ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, APA3, PAuth) + HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, APA3, PAuth) }, { - ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, API, PAuth) + HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, API, PAuth) }, {}, }; static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { { - ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPA, IMP) + HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPA, IMP) }, { - ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, GPA3, IMP) + HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, GPA3, IMP) }, { - ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPI, IMP) + HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPI, IMP) }, {}, }; -- GitLab From 4df69e0df295822cdf816442fe4897f214cccb08 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Fri, 28 Apr 2023 11:28:17 -0700 Subject: [PATCH 4395/5631] arm64: kernel: remove SHF_WRITE|SHF_EXECINSTR from .idmap.text commit d54170812ef1 ("arm64: fix .idmap.text assertion for large kernels") modified some of the section assembler directives that declare .idmap.text to be SHF_ALLOC instead of SHF_ALLOC|SHF_WRITE|SHF_EXECINSTR. This patch fixes up the remaining stragglers that were left behind. Add Fixes tag so that this doesn't precede related change in stable. Fixes: d54170812ef1 ("arm64: fix .idmap.text assertion for large kernels") Reported-by: Greg Thelen Reviewed-by: Ard Biesheuvel Signed-off-by: Nick Desaulniers Link: https://lore.kernel.org/r/20230428-awx-v2-1-b197ffa16edc@google.com Signed-off-by: Will Deacon --- arch/arm64/kernel/cpu-reset.S | 2 +- arch/arm64/kernel/sleep.S | 2 +- arch/arm64/mm/proc.S | 6 +++--- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 6b752fe89745..c87445dde674 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -14,7 +14,7 @@ #include .text -.pushsection .idmap.text, "awx" +.pushsection .idmap.text, "a" /* * cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 2ae7cff1953a..2aa5129d8253 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -97,7 +97,7 @@ SYM_FUNC_START(__cpu_suspend_enter) ret SYM_FUNC_END(__cpu_suspend_enter) - .pushsection ".idmap.text", "awx" + .pushsection ".idmap.text", "a" SYM_CODE_START(cpu_resume) mov x0, xzr bl init_kernel_el diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 91410f488090..c2cb437821ca 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -167,7 +167,7 @@ alternative_else_nop_endif SYM_FUNC_END(cpu_do_resume) #endif - .pushsection ".idmap.text", "awx" + .pushsection ".idmap.text", "a" .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 adrp \tmp1, reserved_pg_dir @@ -201,7 +201,7 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1) #define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) - .pushsection ".idmap.text", "awx" + .pushsection ".idmap.text", "a" .macro kpti_mk_tbl_ng, type, num_entries add end_\type\()p, cur_\type\()p, #\num_entries * 8 @@ -400,7 +400,7 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings) * Output: * Return in x0 the value of the SCTLR_EL1 register. */ - .pushsection ".idmap.text", "awx" + .pushsection ".idmap.text", "a" SYM_FUNC_START(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh -- GitLab From 0fddb79bf283a561eb81f09d01f5ac8f61bf8966 Mon Sep 17 00:00:00 2001 From: Fangrui Song Date: Tue, 2 May 2023 07:41:05 +0000 Subject: [PATCH 4396/5631] arm64: lds: move .got section out of .text Currently, the .got section is placed within the output section .text. However, when .got is non-empty, the SHF_WRITE flag is set for .text when linked by lld. GNU ld recognizes .text as a special section and ignores the SHF_WRITE flag. By renaming .text, we can also get the SHF_WRITE flag. The kernel has performed R_AARCH64_RELATIVE resolving very early, and can then assume that .got is read-only. Let's move .got to the vmlinux_rodata pseudo-segment. As Ard Biesheuvel notes: "This matters to consumers of the vmlinux ELF representation of the kernel image, such as syzkaller, which disregards writable PT_LOAD segments when resolving code symbols. The kernel itself does not care about this distinction, but given that the GOT contains data and not code, it does not require executable permissions, and therefore does not belong in .text to begin with." Reviewed-by: Ard Biesheuvel Signed-off-by: Fangrui Song Link: https://lore.kernel.org/r/20230502074105.1541926-1-maskray@google.com Signed-off-by: Will Deacon --- arch/arm64/kernel/vmlinux.lds.S | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index b9202c2ee18e..3cd7e76cc562 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -181,18 +181,8 @@ SECTIONS KPROBES_TEXT HYPERVISOR_TEXT *(.gnu.warning) - . = ALIGN(16); - *(.got) /* Global offset table */ } - /* - * Make sure that the .got.plt is either completely empty or it - * contains only the lazy dispatch entries. - */ - .got.plt : { *(.got.plt) } - ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, - "Unexpected GOT/PLT entries detected!") - . = ALIGN(SEGMENT_ALIGN); _etext = .; /* End of text section */ @@ -201,6 +191,15 @@ SECTIONS HYPERVISOR_DATA_SECTIONS + .got : { *(.got) } + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the lazy dispatch entries. + */ + .got.plt : { *(.got.plt) } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, + "Unexpected GOT/PLT entries detected!") + /* code sections that are never executed via the kernel mapping */ .rodata.text : { TRAMP_TEXT -- GitLab From e7db9e5c6b9615b287d01f0231904fbc1fbde9c5 Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Fri, 28 Apr 2023 14:02:11 -0700 Subject: [PATCH 4397/5631] btrfs: fix encoded write i_size corruption with no-holes We have observed a btrfs filesystem corruption on workloads using no-holes and encoded writes via send stream v2. The symptom is that a file appears to be truncated to the end of its last aligned extent, even though the final unaligned extent and even the file extent and otherwise correctly updated inode item have been written. So if we were writing out a 1MiB+X file via 8 128K extents and one extent of length X, i_size would be set to 1MiB, but the ninth extent, nbyte, etc. would all appear correct otherwise. The source of the race is a narrow (one line of code) window in which a no-holes fs has read in an updated i_size, but has not yet set a shared disk_i_size variable to write. Therefore, if two ordered extents run in parallel (par for the course for receive workloads), the following sequence can play out: (following "threads" a bit loosely, since there are callbacks involved for endio but extra threads aren't needed to cause the issue) ENC-WR1 (second to last) ENC-WR2 (last) ------- ------- btrfs_do_encoded_write set i_size = 1M submit bio B1 ending at 1M endio B1 btrfs_inode_safe_disk_i_size_write local i_size = 1M falls off a cliff for some reason btrfs_do_encoded_write set i_size = 1M+X submit bio B2 ending at 1M+X endio B2 btrfs_inode_safe_disk_i_size_write local i_size = 1M+X disk_i_size = 1M+X disk_i_size = 1M btrfs_delayed_update_inode btrfs_delayed_update_inode And the delayed inode ends up filled with nbytes=1M+X and isize=1M, and writes respect i_size and present a corrupted file missing its last extents. Fix this by holding the inode lock in the no-holes case so that a thread can't sneak in a write to disk_i_size that gets overwritten with an out of date i_size. Fixes: 41a2ee75aab0 ("btrfs: introduce per-inode file extent tree") CC: stable@vger.kernel.org # 5.10+ Reviewed-by: Josef Bacik Signed-off-by: Boris Burkov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/file-item.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 018c711a0bc8..cd4cce9ba443 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -52,13 +52,13 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz u64 start, end, i_size; int ret; + spin_lock(&inode->lock); i_size = new_i_size ?: i_size_read(&inode->vfs_inode); if (btrfs_fs_incompat(fs_info, NO_HOLES)) { inode->disk_i_size = i_size; - return; + goto out_unlock; } - spin_lock(&inode->lock); ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start, &end, EXTENT_DIRTY); if (!ret && start == 0) @@ -66,6 +66,7 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz else i_size = 0; inode->disk_i_size = i_size; +out_unlock: spin_unlock(&inode->lock); } -- GitLab From 0cce06ba859a515bd06224085d3addb870608b6d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 25 Apr 2023 17:03:13 +0200 Subject: [PATCH 4398/5631] debugobjects,locking: Annotate debug_object_fill_pool() wait type violation There is an explicit wait-type violation in debug_object_fill_pool() for PREEMPT_RT=n kernels which allows them to more easily fill the object pool and reduce the chance of allocation failures. Lockdep's wait-type checks are designed to check the PREEMPT_RT locking rules even for PREEMPT_RT=n kernels and object to this, so create a lockdep annotation to allow this to stand. Specifically, create a 'lock' type that overrides the inner wait-type while it is held -- allowing one to temporarily raise it, such that the violation is hidden. Reported-by: Vlastimil Babka Reported-by: Qi Zheng Signed-off-by: Peter Zijlstra (Intel) Tested-by: Qi Zheng Link: https://lkml.kernel.org/r/20230429100614.GA1489784@hirez.programming.kicks-ass.net --- include/linux/lockdep.h | 14 ++++++++++++++ include/linux/lockdep_types.h | 1 + kernel/locking/lockdep.c | 28 +++++++++++++++++++++------- lib/debugobjects.c | 15 +++++++++++++-- 4 files changed, 49 insertions(+), 9 deletions(-) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 1023f349af71..a3329fb49b33 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -339,6 +339,16 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) +/* + * Must use lock_map_aquire_try() with override maps to avoid + * lockdep thinking they participate in the block chain. + */ +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map _name = { \ + .name = #_name "-wait-type-override", \ + .wait_type_inner = _wait_type, \ + .lock_type = LD_LOCK_WAIT_OVERRIDE, } + #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) @@ -427,6 +437,9 @@ extern int lockdep_is_held(const void *); #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) +#define DEFINE_WAIT_OVERRIDE_MAP(_name, _wait_type) \ + struct lockdep_map __maybe_unused _name = {} + #endif /* !LOCKDEP */ enum xhlock_context_t { @@ -551,6 +564,7 @@ do { \ #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) +#define lock_map_acquire_try(l) lock_acquire_exclusive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index d22430840b53..59f4fb1626ea 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -33,6 +33,7 @@ enum lockdep_wait_type { enum lockdep_lock_type { LD_LOCK_NORMAL = 0, /* normal, catch all */ LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_WAIT_OVERRIDE, /* annotation */ LD_LOCK_MAX, }; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 50d4863974e7..62ef295e07e6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2253,6 +2253,9 @@ static inline bool usage_match(struct lock_list *entry, void *mask) static inline bool usage_skip(struct lock_list *entry, void *mask) { + if (entry->class->lock_type == LD_LOCK_NORMAL) + return false; + /* * Skip local_lock() for irq inversion detection. * @@ -2279,14 +2282,16 @@ static inline bool usage_skip(struct lock_list *entry, void *mask) * As a result, we will skip local_lock(), when we search for irq * inversion bugs. */ - if (entry->class->lock_type == LD_LOCK_PERCPU) { - if (DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) - return false; + if (entry->class->lock_type == LD_LOCK_PERCPU && + DEBUG_LOCKS_WARN_ON(entry->class->wait_type_inner < LD_WAIT_CONFIG)) + return false; - return true; - } + /* + * Skip WAIT_OVERRIDE for irq inversion detection -- it's not actually + * a lock and only used to override the wait_type. + */ - return false; + return true; } /* @@ -4752,7 +4757,8 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; - u8 prev_inner = hlock_class(prev)->wait_type_inner; + struct lock_class *class = hlock_class(prev); + u8 prev_inner = class->wait_type_inner; if (prev_inner) { /* @@ -4762,6 +4768,14 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) * Also due to trylocks. */ curr_inner = min(curr_inner, prev_inner); + + /* + * Allow override for annotations -- this is typically + * only valid/needed for code that only exists when + * CONFIG_PREEMPT_RT=n. + */ + if (unlikely(class->lock_type == LD_LOCK_WAIT_OVERRIDE)) + curr_inner = prev_inner; } } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 003edc5ebd67..826c617b10a7 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -591,10 +591,21 @@ static void debug_objects_fill_pool(void) { /* * On RT enabled kernels the pool refill must happen in preemptible - * context: + * context -- for !RT kernels we rely on the fact that spinlock_t and + * raw_spinlock_t are basically the same type and this lock-type + * inversion works just fine. */ - if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) { + /* + * Annotate away the spinlock_t inside raw_spinlock_t warning + * by temporarily raising the wait-type to WAIT_SLEEP, matching + * the preemptible() condition above. + */ + static DEFINE_WAIT_OVERRIDE_MAP(fill_pool_map, LD_WAIT_SLEEP); + lock_map_acquire_try(&fill_pool_map); fill_pool(); + lock_map_release(&fill_pool_map); + } } static void -- GitLab From 7e2d06628aab6324e1ac885910a52f4c038d4043 Mon Sep 17 00:00:00 2001 From: Mark Asselstine Date: Mon, 1 May 2023 19:13:46 -0400 Subject: [PATCH 4399/5631] ALSA: hda/realtek: Add quirk for ASUS UM3402YAR using CS35L41 This Asus Zenbook laptop uses Realtek HDA codec combined with 2xCS35L41 Amplifiers using I2C with External Boost. Signed-off-by: Mark Asselstine Cc: Link: https://lore.kernel.org/r/20230501231346.54979-1-asselsm@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4bb2179719e4..509afa4e4da6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9500,6 +9500,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS), -- GitLab From 3d6b15a8f3aeb4a6eed69a22822def0d0b039a16 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 30 Apr 2023 12:27:49 -0500 Subject: [PATCH 4400/5631] SMB3.1.1: correct definition for app_instance_id create contexts The name lengths were incorrect for two create contexts. SMB2_CREATE_APP_INSTANCE_ID SMB2_CREATE_APP_INSTANCE_VERSION Update the definitions for these two to match the protocol specs. Acked-by: Paulo Alcantara (SUSE) Reviewed-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.h | 16 ---------------- fs/smbfs_common/smb2pdu.h | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 16 deletions(-) diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 67dc552f2ef7..aca9cfc73caa 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -81,22 +81,6 @@ struct create_durable_reconn_v2_req { __le32 Flags; } __packed; -struct create_app_inst_id { - struct create_context ccontext; - __u8 Name[8]; - __u8 Reserved[8]; - __u8 AppInstanceId[16]; -} __packed; - -struct create_app_inst_id_vers { - struct create_context ccontext; - __u8 Name[8]; - __u8 Reserved[2]; - __u8 Padding[4]; - __le64 AppInstanceVersionHigh; - __le64 AppInstanceVersionLow; -} __packed; - struct create_alloc_size_req { struct create_context ccontext; __u8 Name[8]; diff --git a/fs/smbfs_common/smb2pdu.h b/fs/smbfs_common/smb2pdu.h index 3b43a51e6f7e..bae590eec871 100644 --- a/fs/smbfs_common/smb2pdu.h +++ b/fs/smbfs_common/smb2pdu.h @@ -1250,6 +1250,26 @@ struct create_disk_id_rsp { __u8 Reserved[16]; } __packed; +/* See MS-SMB2 2.2.13.2.13 */ +struct create_app_inst_id { + struct create_context ccontext; + __u8 Name[16]; + __le32 StructureSize; /* Must be 20 */ + __u16 Reserved; + __u8 AppInstanceId[16]; +} __packed; + +/* See MS-SMB2 2.2.13.2.15 */ +struct create_app_inst_id_vers { + struct create_context ccontext; + __u8 Name[16]; + __le32 StructureSize; /* Must be 24 */ + __u16 Reserved; + __u32 Padding; + __le64 AppInstanceVersionHigh; + __le64 AppInstanceVersionLow; +} __packed; + /* See MS-SMB2 2.2.31 and 2.2.32 */ struct smb2_ioctl_req { struct smb2_hdr hdr; -- GitLab From 5bff9f741af60b143a5ae73417a8ec47fd5ff2f4 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 27 Apr 2023 16:07:38 -0300 Subject: [PATCH 4401/5631] cifs: protect session status check in smb2_reconnect() Use @ses->ses_lock to protect access of @ses->ses_status. Cc: stable@vger.kernel.org Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 0521aa1da644..3ce63f0cd9f5 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -175,8 +175,17 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, } } spin_unlock(&tcon->tc_lock); - if ((!tcon->ses) || (tcon->ses->ses_status == SES_EXITING) || - (!tcon->ses->server) || !server) + + ses = tcon->ses; + if (!ses) + return -EIO; + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + return -EIO; + } + spin_unlock(&ses->ses_lock); + if (!ses->server || !server) return -EIO; spin_lock(&server->srv_lock); @@ -204,8 +213,6 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, if (rc) return rc; - ses = tcon->ses; - spin_lock(&ses->chan_lock); if (!cifs_chan_needs_reconnect(ses, server) && !tcon->need_reconnect) { spin_unlock(&ses->chan_lock); -- GitLab From 1810769e3a51375ca35d7a5e5f79542858ca495a Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 27 Apr 2023 16:20:13 -0300 Subject: [PATCH 4402/5631] cifs: print smb3_fs_context::source when mounting Print full device name (UNC + optional prefix) from @old_ctx->source when printing info about mount. Before patch mount.cifs //srv/share/dir /mnt -o ... dmesg ... CIFS: Attempting to mount \\srv\share After patch mount.cifs //srv/share/dir /mnt -o ... dmesg ... CIFS: Attempting to mount //srv/share/dir Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index ac9034fce409..32f7c81a7b89 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -874,14 +874,12 @@ cifs_smb3_do_mount(struct file_system_type *fs_type, struct cifs_mnt_data mnt_data; struct dentry *root; - /* - * Prints in Kernel / CIFS log the attempted mount operation - * If CIFS_DEBUG && cifs_FYI - */ - if (cifsFYI) - cifs_dbg(FYI, "Devname: %s flags: %d\n", old_ctx->UNC, flags); - else - cifs_info("Attempting to mount %s\n", old_ctx->UNC); + if (cifsFYI) { + cifs_dbg(FYI, "%s: devname=%s flags=0x%x\n", __func__, + old_ctx->source, flags); + } else { + cifs_info("Attempting to mount %s\n", old_ctx->source); + } cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL); if (cifs_sb == NULL) { -- GitLab From 90c49fce1c43e1cc152695e20363ff5087897c09 Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Fri, 21 Apr 2023 15:52:32 -0300 Subject: [PATCH 4403/5631] cifs: fix potential use-after-free bugs in TCP_Server_Info::hostname TCP_Server_Info::hostname may be updated once or many times during reconnect, so protect its access outside reconnect path as well and then prevent any potential use-after-free bugs. Cc: stable@vger.kernel.org Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifs_debug.c | 7 ++++++- fs/cifs/cifs_debug.h | 12 ++++++------ fs/cifs/connect.c | 10 +++++++--- fs/cifs/sess.c | 7 ++++--- 4 files changed, 23 insertions(+), 13 deletions(-) diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index e9c8c088d948..d4ed200a9471 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -280,8 +280,10 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) seq_printf(m, "\n%d) ConnectionId: 0x%llx ", c, server->conn_id); + spin_lock(&server->srv_lock); if (server->hostname) seq_printf(m, "Hostname: %s ", server->hostname); + spin_unlock(&server->srv_lock); #ifdef CONFIG_CIFS_SMB_DIRECT if (!server->rdma) goto skip_rdma; @@ -623,10 +625,13 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) server->fastest_cmd[j], server->slowest_cmd[j]); for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++) - if (atomic_read(&server->smb2slowcmd[j])) + if (atomic_read(&server->smb2slowcmd[j])) { + spin_lock(&server->srv_lock); seq_printf(m, " %d slow responses from %s for command %d\n", atomic_read(&server->smb2slowcmd[j]), server->hostname, j); + spin_unlock(&server->srv_lock); + } #endif /* STATS2 */ list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index d44808263cfb..ce5cfd236fdb 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -81,19 +81,19 @@ do { \ #define cifs_server_dbg_func(ratefunc, type, fmt, ...) \ do { \ - const char *sn = ""; \ - if (server && server->hostname) \ - sn = server->hostname; \ + spin_lock(&server->srv_lock); \ if ((type) & FYI && cifsFYI & CIFS_INFO) { \ pr_debug_ ## ratefunc("%s: \\\\%s " fmt, \ - __FILE__, sn, ##__VA_ARGS__); \ + __FILE__, server->hostname, \ + ##__VA_ARGS__); \ } else if ((type) & VFS) { \ pr_err_ ## ratefunc("VFS: \\\\%s " fmt, \ - sn, ##__VA_ARGS__); \ + server->hostname, ##__VA_ARGS__); \ } else if ((type) & NOISY && (NOISY != 0)) { \ pr_debug_ ## ratefunc("\\\\%s " fmt, \ - sn, ##__VA_ARGS__); \ + server->hostname, ##__VA_ARGS__); \ } \ + spin_unlock(&server->srv_lock); \ } while (0) #define cifs_server_dbg(type, fmt, ...) \ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 7bfef741f758..c71505a29482 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -403,8 +403,10 @@ static int __reconnect_target_unlocked(struct TCP_Server_Info *server, const cha if (server->hostname != target) { hostname = extract_hostname(target); if (!IS_ERR(hostname)) { + spin_lock(&server->srv_lock); kfree(server->hostname); server->hostname = hostname; + spin_unlock(&server->srv_lock); } else { cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %ld\n", __func__, PTR_ERR(hostname)); @@ -561,9 +563,7 @@ cifs_echo_request(struct work_struct *work) goto requeue_echo; rc = server->ops->echo ? server->ops->echo(server) : -ENOSYS; - if (rc) - cifs_dbg(FYI, "Unable to send echo request to server: %s\n", - server->hostname); + cifs_server_dbg(FYI, "send echo request: rc = %d\n", rc); /* Check witness registrations */ cifs_swn_check(); @@ -1404,6 +1404,8 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; + lockdep_assert_held(&server->srv_lock); + if (ctx->nosharesock) return 0; @@ -1810,7 +1812,9 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) if (tcon == NULL) return -ENOMEM; + spin_lock(&server->srv_lock); scnprintf(unc, sizeof(unc), "\\\\%s\\IPC$", server->hostname); + spin_unlock(&server->srv_lock); xid = get_xid(); tcon->ses = ses; diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index d2cbae4b5d21..335c078c42fb 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -159,6 +159,7 @@ cifs_chan_is_iface_active(struct cifs_ses *ses, /* returns number of channels added */ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) { + struct TCP_Server_Info *server = ses->server; int old_chan_count, new_chan_count; int left; int rc = 0; @@ -178,16 +179,16 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) return 0; } - if (ses->server->dialect < SMB30_PROT_ID) { + if (server->dialect < SMB30_PROT_ID) { spin_unlock(&ses->chan_lock); cifs_dbg(VFS, "multichannel is not supported on this protocol version, use 3.0 or above\n"); return 0; } - if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { + if (!(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { ses->chan_max = 1; spin_unlock(&ses->chan_lock); - cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname); + cifs_server_dbg(VFS, "no multichannel support\n"); return 0; } spin_unlock(&ses->chan_lock); -- GitLab From af97b7dfb0d4636d58f2341346fffce30c6c2259 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 1 May 2023 16:04:08 +0200 Subject: [PATCH 4404/5631] SUNRPC: Avoid relying on crypto API to derive CBC-CTS output IV Scott reports SUNRPC self-test failures regarding the output IV on arm64 when using the SIMD accelerated implementation of AES in CBC mode with ciphertext stealing ("cts(cbc(aes))" in crypto API speak). These failures are the result of the fact that, while RFC 3962 does specify what the output IV should be and includes test vectors for it, the general concept of an output IV is poorly defined, and generally, not specified by the various algorithms implemented by the crypto API. Only algorithms that support transparent chaining (e.g., CBC mode on a block boundary) have requirements on the output IV, but ciphertext stealing (CTS) is fundamentally about how to encapsulate CBC in a way where the length of the entire message may not be an integral multiple of the cipher block size, and the concept of an output IV does not exist here because it has no defined purpose past the end of the message. The generic CTS template takes advantage of this chaining capability of the CBC implementations, and as a result, happens to return an output IV, simply because it passes its IV buffer directly to the encapsulated CBC implementation, which operates on full blocks only, and always returns an IV. This output IV happens to match how RFC 3962 defines it, even though the CTS template itself does not contain any output IV logic whatsoever, and, for this reason, lacks any test vectors that exercise this accidental output IV generation. The arm64 SIMD implementation of cts(cbc(aes)) does not use the generic CTS template at all, but instead, implements the CBC mode and ciphertext stealing directly, and therefore does not encapsule a CBC implementation that returns an output IV in the same way. The arm64 SIMD implementation complies with the specification and passes all internal tests, but when invoked by the SUNRPC code, fails to produce the expected output IV and causes its selftests to fail. Given that the output IV is defined as the penultimate block (where the final block may smaller than the block size), we can quite easily derive it in the caller by copying the appropriate slice of ciphertext after encryption. Cc: Trond Myklebust Cc: Anna Schumaker Cc: Chuck Lever Cc: Jeff Layton Reported-by: Scott Mayhew Tested-by: Scott Mayhew Signed-off-by: Ard Biesheuvel Signed-off-by: Chuck Lever --- net/sunrpc/auth_gss/gss_krb5_crypto.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 212c5d57465a..9734e1d9f991 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -639,6 +639,16 @@ gss_krb5_cts_crypt(struct crypto_sync_skcipher *cipher, struct xdr_buf *buf, ret = write_bytes_to_xdr_buf(buf, offset, data, len); +#if IS_ENABLED(CONFIG_KUNIT) + /* + * CBC-CTS does not define an output IV but RFC 3962 defines it as the + * penultimate block of ciphertext, so copy that into the IV buffer + * before returning. + */ + if (encrypt) + memcpy(iv, data, crypto_sync_skcipher_ivsize(cipher)); +#endif + out: kfree(data); return ret; -- GitLab From d7f74e9a917503ee78f2b603a456d7227cf38919 Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Fri, 2 Dec 2022 10:07:01 -0400 Subject: [PATCH 4405/5631] afs: Fix updating of i_size with dv jump from server If the data version returned from the server is larger than expected, the local data is invalidated, but we may still want to note the remote file size. Since we're setting change_size, we have to also set data_changed for the i_size to get updated. Fixes: 3f4aa9818163 ("afs: Fix EOF corruption") Signed-off-by: Marc Dionne Signed-off-by: David Howells cc: linux-afs@lists.infradead.org --- fs/afs/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index b1bdffd5e888..82edd3351734 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -230,6 +230,7 @@ static void afs_apply_status(struct afs_operation *op, set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); } change_size = true; + data_changed = true; } else if (vnode->status.type == AFS_FTYPE_DIR) { /* Expected directory change is handled elsewhere so * that we can locally edit the directory and save on a -- GitLab From 45f66fa03ba9943cca5af88d691399332b8bde08 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 6 Dec 2022 13:49:42 +0000 Subject: [PATCH 4406/5631] afs: Fix getattr to report server i_size on dirs, not local size Fix afs_getattr() to report the server's idea of the file size of a directory rather than the local size. The local size may differ as we edit the local copy to avoid having to redownload it and we may end up with a differently structured blob of a different size. However, if the directory is discarded from the pagecache we then download it again and the user may see the directory file size apparently change. Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...") Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- fs/afs/inode.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 82edd3351734..866bab860a88 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -450,7 +450,7 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) 0 : FSCACHE_ADV_SINGLE_CHUNK, &key, sizeof(key), &aux, sizeof(aux), - vnode->status.size)); + i_size_read(&vnode->netfs.inode))); #endif } @@ -777,6 +777,13 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path, if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) && stat->nlink > 0) stat->nlink -= 1; + + /* Lie about the size of directories. We maintain a locally + * edited copy and may make different allocation decisions on + * it, but we need to give userspace the server's size. + */ + if (S_ISDIR(inode->i_mode)) + stat->size = vnode->netfs.remote_i_size; } while (need_seqretry(&vnode->cb_lock, seq)); done_seqretry(&vnode->cb_lock, seq); -- GitLab From 9ea4eff4b6f4f36546d537a74da44fd3f30903ab Mon Sep 17 00:00:00 2001 From: Marc Dionne Date: Fri, 2 Dec 2022 10:19:42 -0400 Subject: [PATCH 4407/5631] afs: Avoid endless loop if file is larger than expected afs_read_dir fetches an amount of data that's based on what the inode size is thought to be. If the file on the server is larger than what was fetched, the code rechecks i_size and retries. If the local i_size was not properly updated, this can lead to an endless loop of fetching i_size from the server and noticing each time that the size is larger on the server. If it is known that the remote size is larger than i_size, bump up the fetch size to that size. Fixes: f3ddee8dc4e2 ("afs: Fix directory handling") Signed-off-by: Marc Dionne Signed-off-by: David Howells cc: linux-afs@lists.infradead.org --- fs/afs/dir.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/afs/dir.c b/fs/afs/dir.c index f92b9e62d567..4dd97afa536c 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -275,6 +275,7 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) loff_t i_size; int nr_pages, i; int ret; + loff_t remote_size = 0; _enter(""); @@ -289,6 +290,8 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) expand: i_size = i_size_read(&dvnode->netfs.inode); + if (i_size < remote_size) + i_size = remote_size; if (i_size < 2048) { ret = afs_bad(dvnode, afs_file_error_dir_small); goto error; @@ -364,6 +367,7 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) * buffer. */ up_write(&dvnode->validate_lock); + remote_size = req->file_size; goto expand; } -- GitLab From 4c093cbb89f32762555f624882f1d31a79237eaf Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 2 May 2023 12:05:10 +0200 Subject: [PATCH 4408/5631] Documentation: timers: hrtimers: Make hybrid union historical Non-scalar time was removed from the ktime hybrid union in v3.17, and the union itself followed suit in v4.10. Make it clear that ktime_t is always a 64bit scalar type, to avoid confusing the casual reader. While at it, fix a spelling mistake. Fixes: 24e4a8c3e8868874 ("ktime: Kill non-scalar ktime_t implementation for 2038") Fixes: 2456e855354415bf ("ktime: Get rid of the union") Signed-off-by: Geert Uytterhoeven Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/59250a3d1c2c827b5c1833169a6e652ca6a784e6.1683021785.git.geert+renesas@glider.be Signed-off-by: Jonathan Corbet --- Documentation/timers/hrtimers.rst | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) diff --git a/Documentation/timers/hrtimers.rst b/Documentation/timers/hrtimers.rst index 7ac448908d1f..f88ff8bae89c 100644 --- a/Documentation/timers/hrtimers.rst +++ b/Documentation/timers/hrtimers.rst @@ -123,17 +123,12 @@ equivalent to timer_delete() and timer_delete_sync()] - so there's no direct potential for code sharing either. Basic data types: every time value, absolute or relative, is in a -special nanosecond-resolution type: ktime_t. The kernel-internal -representation of ktime_t values and operations is implemented via -macros and inline functions, and can be switched between a "hybrid -union" type and a plain "scalar" 64bit nanoseconds representation (at -compile time). The hybrid union type optimizes time conversions on 32bit -CPUs. This build-time-selectable ktime_t storage format was implemented -to avoid the performance impact of 64-bit multiplications and divisions -on 32bit CPUs. Such operations are frequently necessary to convert -between the storage formats provided by kernel and userspace interfaces -and the internal time format. (See include/linux/ktime.h for further -details.) +special nanosecond-resolution 64bit type: ktime_t. +(Originally, the kernel-internal representation of ktime_t values and +operations was implemented via macros and inline functions, and could be +switched between a "hybrid union" type and a plain "scalar" 64bit +nanoseconds representation (at compile time). This was abandoned in the +context of the Y2038 work.) hrtimers - rounding of timer values ----------------------------------- @@ -148,7 +143,7 @@ a given clock has - be it low-res, high-res, or artificially-low-res. hrtimers - testing and verification ----------------------------------- -We used the high-resolution clock subsystem ontop of hrtimers to verify +We used the high-resolution clock subsystem on top of hrtimers to verify the hrtimer implementation details in praxis, and we also ran the posix timer tests in order to ensure specification compliance. We also ran tests on low-resolution clocks. -- GitLab From be8ca5f4bcdb8f12f75e0fc64f37a13657440f22 Mon Sep 17 00:00:00 2001 From: Deming Wang Date: Mon, 1 May 2023 21:01:57 -0400 Subject: [PATCH 4409/5631] docs: fix "Reviewd" typo Spell "Reviewed" properly in Documentation/Translations/jp/SubmittingPatches Signed-off-by: Deming Wang Reviewed-by: Akira Yokosawa Link: https://lore.kernel.org/r/20230502010157.1655-1-wangdeming@inspur.com Signed-off-by: Jonathan Corbet --- Documentation/translations/ja_JP/SubmittingPatches | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/translations/ja_JP/SubmittingPatches b/Documentation/translations/ja_JP/SubmittingPatches index 04deb77b20c6..5334db471744 100644 --- a/Documentation/translations/ja_JP/SubmittingPatches +++ b/Documentation/translations/ja_JP/SubmittingPatches @@ -450,7 +450,7 @@ Reviewed-by: タグは、それとは異なり、下記のレビューア宣言 状況においてその宣言した目的や機能が正しく実現することに関して、 いかなる保証もしない(特にどこかで明示しない限り)。 -Reviewd-by タグはそのパッチがカーネルに対して適切な修正であって、深刻な技術的 +Reviewed-by タグはそのパッチがカーネルに対して適切な修正であって、深刻な技術的 問題を残していないという意見の宣言です。興味のあるレビューアは誰でも(レビュー 作業を終えたら)パッチに対して Reviewed-by タグを提示できます。このタグは レビューアの寄与をクレジットする働き、レビューの進捗の度合いをメンテナに -- GitLab From 4a2d80ad062e2f3722227a72ad6050aa3e2c7676 Mon Sep 17 00:00:00 2001 From: Tao Liu Date: Wed, 26 Apr 2023 10:14:52 +0800 Subject: [PATCH 4410/5631] docs: Remove unnecessary unicode character There is a non-printable unicode char '\u202a' or "0xe2 0x80 0xaa" in hex in the translation doc. It is unnecessary and should be removed for better text formatting when using editors like vi. Signed-off-by: Tao Liu Reviewed-by: Yanteng Si Link: https://lore.kernel.org/r/20230426021452.9745-1-ltao@redhat.com Signed-off-by: Jonathan Corbet --- Documentation/translations/zh_CN/process/magic-number.rst | 2 +- Documentation/translations/zh_TW/process/magic-number.rst | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/translations/zh_CN/process/magic-number.rst b/Documentation/translations/zh_CN/process/magic-number.rst index 0617ce125e12..6f22b728d4e7 100644 --- a/Documentation/translations/zh_CN/process/magic-number.rst +++ b/Documentation/translations/zh_CN/process/magic-number.rst @@ -25,7 +25,7 @@ Linux 魔术数 ... }; -当你以后给内核添加增强功能的时候，请遵守这条规则！这样就会节省数不清的调试时间，特别是一些古怪的情况，例如，数组超出范围并且重新写了超出部分。遵守这个规则，‪这些情况可以被快速地，安全地避免。 +当你以后给内核添加增强功能的时候，请遵守这条规则！这样就会节省数不清的调试时间，特别是一些古怪的情况，例如，数组超出范围并且重新写了超出部分。遵守这个规则，这些情况可以被快速地，安全地避免。 Theodore Ts'o 31 Mar 94 diff --git a/Documentation/translations/zh_TW/process/magic-number.rst b/Documentation/translations/zh_TW/process/magic-number.rst index f3f7082e17c6..a3dd87cadc26 100644 --- a/Documentation/translations/zh_TW/process/magic-number.rst +++ b/Documentation/translations/zh_TW/process/magic-number.rst @@ -28,7 +28,7 @@ Linux 魔術數 ... }; -當你以後給內核添加增強功能的時候，請遵守這條規則！這樣就會節省數不清的調試時間，特別是一些古怪的情況，例如，數組超出範圍並且重新寫了超出部分。遵守這個規則，‪這些情況可以被快速地，安全地避免。 +當你以後給內核添加增強功能的時候，請遵守這條規則！這樣就會節省數不清的調試時間，特別是一些古怪的情況，例如，數組超出範圍並且重新寫了超出部分。遵守這個規則，這些情況可以被快速地，安全地避免。 Theodore Ts'o 31 Mar 94 -- GitLab From 530421acaeda1d8c3533f241db944127f69efadc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=99=8F=E8=89=B3=28=E9=87=87=E8=8B=93=29?= Date: Tue, 28 Mar 2023 15:25:37 +0800 Subject: [PATCH 4411/5631] Documentation: update kernel stack for x86_64 Commit 6538b8ea886e ("x86_64: expand kernel stack to 16K") expanded kernel stack for x86_64 but left the wrong documentation, update it. Signed-off-by: Yan Yan Reviewed-by: Lai Jiangshan Link: https://lore.kernel.org/r/20230328072537.20188-1-yanyan.yan@antgroup.com Signed-off-by: Jonathan Corbet --- Documentation/arch/x86/kernel-stacks.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/arch/x86/kernel-stacks.rst b/Documentation/arch/x86/kernel-stacks.rst index 6b0bcf027ff1..738671a4070b 100644 --- a/Documentation/arch/x86/kernel-stacks.rst +++ b/Documentation/arch/x86/kernel-stacks.rst @@ -12,7 +12,7 @@ Most of the text from Keith Owens, hacked by AK x86_64 page size (PAGE_SIZE) is 4K. Like all other architectures, x86_64 has a kernel stack for every -active thread. These thread stacks are THREAD_SIZE (2*PAGE_SIZE) big. +active thread. These thread stacks are THREAD_SIZE (4*PAGE_SIZE) big. These stacks contain useful data as long as a thread is alive or a zombie. While the thread is in user space the kernel stack is empty except for the thread_info structure at the bottom. -- GitLab From 37c95f3a3d251a9319ed137ee0adf5ab9e431ce2 Mon Sep 17 00:00:00 2001 From: Mat Martineau Date: Mon, 1 May 2023 17:05:44 -0700 Subject: [PATCH 4412/5631] CREDITS: Update email address for Mat Martineau Changing my email address in CREDITS to be consistent with what's in use in MAINTAINERS and mailmap. Also removed extra date information from the CREDITS entry since I'm a maintainer for MPTCP again. Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20230502000545.2899055-1-martineau@kernel.org Signed-off-by: Jonathan Corbet --- CREDITS | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/CREDITS b/CREDITS index b6c93e0a62c3..fa076dba2f1a 100644 --- a/CREDITS +++ b/CREDITS @@ -2510,8 +2510,8 @@ D: XF86_8514 D: cfdisk (curses based disk partitioning program) N: Mat Martineau -E: mat@martineau.name -D: MPTCP subsystem co-maintainer 2020-2023 +E: martineau@kernel.org +D: MPTCP subsystem co-maintainer D: Keyctl restricted keyring and Diffie-Hellman UAPI D: Bluetooth L2CAP ERTM mode and AMP S: USA -- GitLab From cdc822dda6f82269b94d5fa60ddc71d98c160fa0 Mon Sep 17 00:00:00 2001 From: Carlos Bilbao Date: Wed, 15 Mar 2023 09:35:26 -0500 Subject: [PATCH 4413/5631] docs/sp_SP: Add translation of process/adding-syscalls Translate Documentation/process/adding-syscalls.rst into Spanish. Co-developed-by: Mauricio Fuentes Signed-off-by: Mauricio Fuentes Signed-off-by: Carlos Bilbao Link: https://lore.kernel.org/r/20230315143526.1213813-1-carlos.bilbao@amd.com --- .../sp_SP/process/adding-syscalls.rst | 632 ++++++++++++++++++ .../translations/sp_SP/process/index.rst | 1 + 2 files changed, 633 insertions(+) create mode 100644 Documentation/translations/sp_SP/process/adding-syscalls.rst diff --git a/Documentation/translations/sp_SP/process/adding-syscalls.rst b/Documentation/translations/sp_SP/process/adding-syscalls.rst new file mode 100644 index 000000000000..f21504c612b2 --- /dev/null +++ b/Documentation/translations/sp_SP/process/adding-syscalls.rst @@ -0,0 +1,632 @@ +.. include:: ../disclaimer-sp.rst + +:Original: :ref:`Documentation/process/adding-syscalls.rst ` +:Translator: Mauricio Fuentes + +.. _sp_addsyscalls: + +Agregando una Nueva Llamada del Sistema +======================================= + +Este documento describe qué involucra agregar una nueva llamada del sistema +al kernel Linux, más allá de la presentación y consejos normales en +:ref:`Documentation/process/submitting-patches.rst ` que +también puede encontrar traducido a este idioma. + +Alternativas a Llamadas del Sistema +----------------------------------- + +La primera cosa a considerar cuando se agrega una llamada al sistema es si +alguna alternativa es adecuada en su lugar. Aunque las llamadas al sistema +son los puntos de interacción entre el userspace y el kernel más obvios y +tradicionales, existen otras posibilidades -- elija la que mejor se adecúe +a su interfaz. + + - Si se puede hacer que la operación se parezca a un objeto filesystem, + podría tener más sentido crear un nuevo sistema de ficheros o + dispositivo. Esto también hará más fácil encapsular la nueva + funcionalidad en un módulo del kernel en vez de requerir que sea + construido junto al kernel principal. + + - Si la nueva funcionalidad involucra operaciones donde el kernel + notifica al userspace que algo ha pasado, entonces retornar un nuevo + descriptor de archivo para el objeto relevante permite al userspace + usar ``poll``/``select``/``epoll`` para recibir esta notificación. + + - Sin embargo, operaciones que no mapean a operaciones similares a + :manpage:`read(2)`/:manpage:`write(2)` tienen que ser implementadas + como solicitudes :manpage:`ioctl(2)`, las cuales pueden llevar a un + API algo opaca. + + - Si sólo está exponiendo información del runtime, un nuevo nodo en sysfs + (mire ``Documentation/filesystems/sysfs.rst``) o el filesystem ``/proc`` + podría ser más adecuado. Sin embargo, acceder a estos mecanismos + requiere que el filesystem relevante esté montado, lo que podría no ser + siempre el caso (e.g. en un ambiente namespaced/sandboxed/chrooted). + Evite agregar cualquier API a debugfs, ya que no se considera una + interfaz (interface) de 'producción' para el userspace. + + - Si la operación es específica a un archivo o descriptor de archivo + específico, entonces la opción de comando adicional :manpage:`fcntl(2)` + podría ser más apropiada. Sin embargo, :manpage:`fcntl(2)` es una + llamada al sistema multiplexada que esconde mucha complejidad, así que + esta opción es mejor cuando la nueva funcion es analogamente cercana a + la funcionalidad existente :manpage:`fcntl(2)`, o la nueva funcionalidad + es muy simple (por ejemplo, definir/obtener un flag simple relacionado a + un descriptor de archivo). + + - Si la operación es específica a un proceso o tarea particular, entonces + un comando adicional :manpage:`prctl(2)` podría ser más apropiado. Tal + como con :manpage:`fcntl(2)`, esta llamada al sistema es un multiplexor + complicado así que está reservado para comandos análogamente cercanos + del existente ``prctl()`` u obtener/definir un flag simple relacionado a + un proceso. + +Diseñando el API: Planeando para extensiones +-------------------------------------------- + +Una nueva llamada del sistema forma parte del API del kernel, y tiene que +ser soportada indefinidamente. Como tal, es una muy buena idea discutir +explícitamente el interface en las listas de correo del kernel, y es +importante planear para futuras extensiones del interface. + +(La tabla syscall está poblada con ejemplos históricos donde esto no se +hizo, junto con los correspondientes seguimientos de los system calls -- +``eventfd``/``eventfd2``, ``dup2``/``dup3``, ``inotify_init``/``inotify_init1``, +``pipe``/``pipe2``, ``renameat``/``renameat2`` -- así que aprenda de la +historia del kernel y planee extensiones desde el inicio.) + +Para llamadas al sistema más simples que sólo toman un par de argumentos, +la forma preferida de permitir futuras extensiones es incluir un argumento +flag a la llamada al sistema. Para asegurarse que el userspace pueda usar +de forma segura estos flags entre versiones del kernel, revise si los flags +contienen cualquier flag desconocido, y rechace la llamada al sistema (con +``EINVAL``) si ocurre:: + + if (flags & ~(THING_FLAG1 | THINGFLAG2 | THING_FLAG3)) + return -EINVAL; + +(Si no hay valores de flags usados aún, revise que los argumentos del flag +sean cero.) + +Para llamadas al sistema más sofisticadas que involucran un gran número de +argumentos, es preferible encapsular la mayoría de los argumentos en una +estructura que sea pasada a través de un puntero. Tal estructura puede +hacer frente a futuras extensiones mediante la inclusión de un argumento de +tamaño en la estructura:: + + struct xyzzy_params { + u32 size; /* userspace define p->size = sizeof(struct xyzzy_params) */ + u32 param_1; + u64 param_2; + u64 param_3; + }; + +Siempre que cualquier campo añadido subsecuente, digamos ``param_4``, sea +diseñado de forma tal que un valor cero, devuelva el comportamiento previo, +entonces permite versiones no coincidentes en ambos sentidos: + + - Para hacer frente a programas del userspace más modernos, haciendo + llamadas a un kernel más antiguo, el código del kernel debe revisar que + cualquier memoria más allá del tamaño de la estructura sea cero (revisar + de manera efectiva que ``param_4 == 0``). + - Para hacer frente a programas antiguos del userspace haciendo llamadas a + un kernel más nuevo, el código del kernel puede extender con ceros, una + instancia más pequeña de la estructura (definiendo efectivamente + ``param_4 == 0``). + +Revise :manpage:`perf_event_open(2)` y la función ``perf_copy_attr()`` (en +``kernel/events/code.c``) para un ejemplo de esta aproximación. + + +Diseñando el API: Otras consideraciones +--------------------------------------- + +Si su nueva llamada al sistema permite al userspace hacer referencia a un +objeto del kernel, esta debería usar un descriptor de archivo como el +manipulador de ese objeto -- no invente un nuevo tipo de objeto manipulador +userspace cuando el kernel ya tiene mecanismos y semánticas bien definidas +para usar los descriptores de archivos. + +Si su nueva llamada a sistema :manpage:`xyzzy(2)` retorna un nuevo +descriptor de archivo, entonces el argumento flag debe incluir un valor que +sea equivalente a definir ``O_CLOEXEC`` en el nuevo FD. Esto hace posible +al userspace acortar la brecha de tiempo entre ``xyzzy()`` y la llamada a +``fcntl(fd, F_SETFD, FD_CLOEXEC)``, donde un ``fork()`` inesperado y +``execve()`` en otro hilo podrían filtrar un descriptor al programa +ejecutado. (Sin embargo, resista la tentación de reusar el valor actual de +la constante ``O_CLOEXEC``, ya que es específica de la arquitectura y es +parte de un espacio numerado de flags ``O_*`` que está bastante lleno.) + +Si su llamada de sistema retorna un nuevo descriptor de archivo, debería +considerar también que significa usar la familia de llamadas de sistema +:manpage:`poll(2)` en ese descriptor de archivo. Hacer un descriptor de +archivo listo para leer o escribir es la forma normal para que el kernel +indique al espacio de usuario que un evento ha ocurrido en el +correspondiente objeto del kernel. + +Si su nueva llamada de sistema :manpage:`xyzzy(2)` involucra algún nombre +de archivo como argumento:: + + int sys_xyzzy(const char __user *path, ..., unsigned int flags); + +debería considerar también si una versión :manpage:`xyzzyat(2)` es mas +apropiada:: + + int sys_xyzzyat(int dfd, const char __user *path, ..., unsigned int flags); + +Esto permite más flexibilidad en como el userspace especifica el archivo en +cuestión; en particular esto permite al userspace pedir la funcionalidad a +un descriptor de archivo ya abierto usando el flag ``AT_EMPTY_PATH``, +efectivamente dando una operación :manpage:`fxyzzy(3)` gratis:: + + - xyzzyat(AT_FDCWD, path, ..., 0) es equivalente a xyzzy(path, ...) + - xyzzyat(fd, "", ..., AT_EMPTY_PATH) es equivalente a fxyzzy(fd, ...) + +(Para más detalles sobre la explicación racional de las llamadas \*at(), +revise el man page :manpage:`openat(2)`; para un ejemplo de AT_EMPTY_PATH, +mire el man page :manpage:`fstatat(2)` manpage.) + +Si su nueva llamada de sistema :manpage:`xyzzy(2)` involucra un parámetro +describiendo un describiendo un movimiento dentro de un archivo, ponga de +tipo ``loff_t`` para que movimientos de 64-bit puedan ser soportados +incluso en arquitecturas de 32-bit. + +Si su nueva llamada de sistema :manpage:`xyzzy` involucra una +funcionalidad privilegiada, esta necesita ser gobernada por la capability +bit linux apropiada (revisado con una llamada a ``capable()``), como se +describe en el man page :manpage:`capabilities(7)`. Elija una parte de +capability linux que govierne las funcionalidades relacionadas, pero trate +de evitar combinar muchas funciones sólo relacionadas vagamente bajo la +misma sección, ya que va en contra de los propósitos de las capabilities de +dividir el poder del usuario root. En particular, evite agregar nuevos usos +de la capacidad ya demasiado general de la capabilities ``CAP_SYS_ADMIN``. + +Si su nueva llamada de sistema :manpage:`xyzzy(2)` manipula un proceso que +no es el proceso invocado, este debería ser restringido (usando una llamada +a ``ptrace_may_access()``) de forma que el único proceso con los mismos +permisos del proceso objetivo, o con las capacidades (capabilities) +necesarias, pueda manipulador el proceso objetivo. + +Finalmente, debe ser conciente de que algunas arquitecturas no-x86 tienen +un manejo más sencillo si los parámetros que son explícitamente 64-bit +caigan en argumentos enumerados impares (i.e. parámetros 1,3,5), para +permitir el uso de pares contiguos de registros 32-bits. (Este cuidado no +aplica si el argumento es parte de una estructura que se pasa a través de +un puntero.) + +Proponiendo el API +------------------ + +Para hacer una nueva llamada al sistema fácil de revisar, es mejor dividir +el patchset (conjunto de parches) en trozos separados. Estos deberían +incluir al menos los siguientes items como commits distintos (cada uno de +los cuales se describirá más abajo): + + - La implementación central de la llamada al sistema, junto con + prototipos, numeración genérica, cambios Kconfig e implementaciones de + rutinas de respaldo (fallback stub) + - Conectar la nueva llamada a sistema a una arquitectura particular, + usualmente x86 (incluyendo todas las x86_64, x86_32 y x32). + - Una demostración del use de la nueva llamada a sistema en el userspace + vía un selftest en ``tools/testing/selftest/``. + - Un borrador de man-page para la nueva llamada a sistema, ya sea como + texto plano en la carta de presentación, o como un parche (separado) + para el repositorio man-pages. + +Nuevas propuestas de llamadas de sistema, como cualquier cambio al API del +kernel, debería siempre ser copiado a linux-api@vger.kernel.org. + + +Implementation de Llamada de Sistema Generica +--------------------------------------------- + +La entrada principal a su nueva llamada de sistema :manpage:`xyzzy(2)` será +llamada ``sys_xyzzy()``, pero incluya este punto de entrada con la macro +``SYSCALL_DEFINEn()`` apropiada en vez de explicitamente. El 'n' indica el +numero de argumentos de la llamada de sistema, y la macro toma el nombre de +la llamada de sistema seguida por el par (tipo, nombre) para los parámetros +como argumentos. Usar esta macro permite a la metadata de la nueva llamada +de sistema estar disponible para otras herramientas. + +El nuevo punto de entrada también necesita un prototipo de función +correspondiente en ``include/linux/syscalls.h``, marcado como asmlinkage +para calzar en la manera en que las llamadas de sistema son invocadas:: + + asmlinkage long sys_xyzzy(...); + +Algunas arquitecturas (e.g. x86) tienen sus propias tablas de syscall +específicas para la arquitectura, pero muchas otras arquitecturas comparten +una tabla de syscall genéricas. Agrega su nueva llamada de sistema a la +lista genérica agregando una entrada a la lista en +``include/uapi/asm-generic/unistd.h``:: + + #define __NR_xyzzy 292 + __SYSCALL(__NR_xyzzy, sys_xyzzy ) + +También actualice el conteo de __NR_syscalls para reflejar la llamada de +sistema adicional, y note que si multiples llamadas de sistema nuevas son +añadidas en la misma ventana unida, su nueva llamada de sistema podría +tener que ser ajustada para resolver conflictos. + +El archivo ``kernel/sys_ni.c`` provee una implementación fallback stub +(rutina de respaldo) para cada llamada de sistema, retornando ``-ENOSYS``. +Incluya su nueva llamada a sistema aquí también:: + + COND_SYSCALL(xyzzy); + +Su nueva funcionalidad del kernel, y la llamada de sistema que la controla, +debería normalmente ser opcional, así que incluya una opción ``CONFIG`` +(tipicamente en ``init/Kconfig``) para ella. Como es usual para opciones +``CONFIG`` nuevas: + + - Incluya una descripción para la nueva funcionalidad y llamada al sistema + controlada por la opción. + - Haga la opción dependiendo de EXPERT si esta debe estar escondida de los + usuarios normales. + - Haga que cualquier nuevo archivo fuente que implemente la función + dependa de la opción CONFIG en el Makefile (e.g. + ``obj-$(CONFIG_XYZZY_SYSCALL) += xyzzy.o``). + - Revise dos veces que el kernel se siga compilando con la nueva opción + CONFIG apagada. + +Para resumir, necesita un commit que incluya: + + - una opción ``CONFIG`` para la nueva función, normalmente en ``init/Kconfig`` + - ``SYSCALL_DEFINEn(xyzzy, ...)`` para el punto de entrada + - El correspondiente prototipo en ``include/linux/syscalls.h`` + - Una entrada genérica en ``include/uapi/asm-generic/unistd.h`` + - fallback stub en ``kernel/sys_ni.c`` + + +Implementación de Llamada de Sistema x86 +---------------------------------------- + +Para conectar su nueva llamada de sistema a plataformas x86, necesita +actualizar las tablas maestras syscall. Asumiendo que su nueva llamada de +sistema ni es especial de alguna manera (revise abajo), esto involucra una +entrada "común" (para x86_64 y x86_32) en +arch/x86/entry/syscalls/syscall_64.tbl:: + + 333 common xyzz sys_xyzzy + +y una entrada "i386" en ``arch/x86/entry/syscalls/syscall_32.tbl``:: + + 380 i386 xyzz sys_xyzzy + +De nuevo, estos número son propensos de ser cambiados si hay conflictos en +la ventana de integración relevante. + + +Compatibilidad de Llamadas de Sistema (Genérica) +------------------------------------------------ + +Para la mayoría de llamadas al sistema la misma implementación 64-bit puede +ser invocada incluso cuando el programa de userspace es en si mismo 32-bit; +incluso si los parámetros de la llamada de sistema incluyen un puntero +explícito, esto es manipulado de forma transparente. + +Sin embargo, existe un par de situaciones donde se necesita una capa de +compatibilidad para lidiar con las diferencias de tamaño entre 32-bit y +64-bit. + +La primera es si el kernel 64-bit también soporta programas del userspace +32-bit, y por lo tanto necesita analizar areas de memoria del (``__user``) +que podrían tener valores tanto 32-bit como 64-bit. En particular esto se +necesita siempre que un argumento de la llamada a sistema es: + + - un puntero a un puntero + - un puntero a un struc conteniendo un puntero (por ejemplo + ``struct iovec __user *``) + - un puntero a un type entero de tamaño entero variable (``time_t``, + ``off_t``, ``long``, ...) + - un puntero a un struct conteniendo un type entero de tamaño variable. + +La segunda situación que requiere una capa de compatibilidad es cuando uno +de los argumentos de la llamada a sistema tiene un argumento que es +explícitamente 64-bit incluso sobre arquitectura 32-bit, por ejemplo +``loff_t`` o ``__u64``. En este caso, el valor que llega a un kernel 64-bit +desde una aplicación de 32-bit se separará en dos valores de 32-bit, los +que luego necesitan ser reensamblados en la capa de compatibilidad. + +(Note que un argumento de una llamada a sistema que sea un puntero a un +type explicitamente de 64-bit **no** necesita una capa de compatibilidad; +por ejemplo, los argumentos de :manpage:`splice(2)`) del tipo +``loff_t __user *`` no significan la necesidad de una llamada a sistema +``compat_``.) + +La versión compatible de la llamada de sistema se llama +``compat_sys_xyzzy()``, y se agrega con la macro +``COMPAT_SYSCALL_DEFINEn``, de manera análoga a SYSCALL_DEFINEn. Esta +versión de la implementación se ejecuta como parte de un kernel de 64-bit, +pero espera recibir parametros con valores 32-bit y hace lo que tenga que +hacer para tratar con ellos. (Típicamente, la versión ``compat_sys_`` +convierte los valores a versiones de 64 bits y llama a la versión ``sys_`` +o ambas llaman a una función de implementación interna común.) + +El punto de entrada compat también necesita un prototipo de función +correspondiente, en ``include/linux/compat.h``, marcado como asmlinkage +para igualar la forma en que las llamadas al sistema son invocadas:: + + asmlinkage long compat_sys_xyzzy(...); + +Si la nueva llamada al sistema involucra una estructura que que se dispone +de forma distinta en sistema de 32-bit y 64-bit, digamos +``struct xyzzy_args``, entonces el archivo de cabecera +include/linux/compat.h también debería incluir una versión compatible de la +estructura (``struct compat_xyzzy_args``) donde cada campo de tamaño +variable tiene el tipo ``compat_`` apropiado que corresponde al tipo en +``struct xyzzy_args``. La rutina ``compat_sys_xyzzy()`` puede entonces usar +esta estructura ``compat_`` para analizar los argumentos de una invocación +de 32-bit. + +Por ejemplo, si hay campos:: + + struct xyzzy_args { + const char __user *ptr; + __kernel_long_t varying_val; + u64 fixed_val; + /* ... */ + }; + +en struct xyzzy_args, entonces struct compat_xyzzy_args debe tener:: + + struct compat_xyzzy_args { + compat_uptr_t ptr; + compat_long_t varying_val; + u64 fixed_val; + /* ... */ + }; + +la lista genérica de llamadas al sistema también necesita ajustes para +permitir la versión compat; la entrada en +``include/uapi/asm-generic/unistd.h`` debería usar ``__SC_COMP`` en vez de +``__SYSCALL``:: + + #define __NR_xyzzy 292 + __SC_COMP(__NR_xyzzy, sys_xyzzy, compat_sys_xyzzy) + +Para resumir, necesita: + + - una ``COMPAT_SYSCALL_DEFINEn(xyzzy, ...)`` para el punto de entrada de compat. + - el prototipo correspondiente en ``include/linux/compat.h`` + - (en caso de ser necesario) un struct de mapeo de 32-bit en ``include/linux/compat.h`` + - una instancia de ``__SC_COMP`` no ``__SYSCALL`` en ``include/uapi/asm-generic/unistd.h`` + +Compatibilidad de Llamadas de Sistema (x86) +------------------------------------------- + +Para conectar la arquitectura x86 de una llamada al sistema con una versión +de compatibilidad, las entradas en las tablas de syscall deben ser +ajustadas. + +Primero, la entrada en ``arch/x86/entry/syscalls/syscall_32.tbl`` recibe +una columna extra para indicar que un programa del userspace de 32-bit +corriendo en un kernel de 64-bit debe llegar al punto de entrada compat:: + + 380 i386 xyzzy sys_xyzzy __ia32_compat_sys_xyzzy + +Segundo, tienes que averiguar qué debería pasar para la versión x32 ABI de +la nueva llamada al sistema. Aquí hay una elección: el diseño de los +argumentos debería coincidir con la versión de 64-bit o la versión de +32-bit. + +Si hay involucrado un puntero-a-puntero, la decisión es fácil: x32 es +ILP32, por lo que el diseño debe coincidir con la versión 32-bit, y la +entrada en ``arch/x86/entry/syscalls/syscall_64.tbl`` se divide para que +progamas 32-bit lleguen al envoltorio de compatibilidad:: + + 333 64 xyzzy sys_xyzzy + ... + 555 x32 xyzzy __x32_compat_sys_xyzzy + +Si no hay punteros involucrados, entonces es preferible reutilizar el system +call 64-bit para el x32 ABI (y consecuentemente la entrada en +arch/x86/entry/syscalls/syscall_64.tbl no se cambia). + +En cualquier caso, debes revisar que lo tipos involucrados en su diseño de +argumentos de hecho asigne exactamente de x32 (-mx32) a 32-bit(-m32) o +equivalentes 64-bit (-m64). + + +Llamadas de Sistema Retornando a Otros Lugares +---------------------------------------------- + +Para la mayoría de las llamadas al sistema, una vez que se la llamada al +sistema se ha completado el programa de usuario continúa exactamente donde +quedó -- en la siguiente instrucción, con el stack igual y la mayoría de +los registros igual que antes de la llamada al sistema, y con el mismo +espacio en la memoria virtual. + +Sin embargo, unas pocas llamadas al sistema hacen las cosas diferente. +Estas podrían retornar a una ubicación distinta (``rt_sigreturn``) o +cambiar el espacio de memoria (``fork``/``vfork``/``clone``) o incluso de +arquitectura (``execve``/``execveat``) del programa. + +Para permitir esto, la implementación del kernel de la llamada al sistema +podría necesitar guardar y restaurar registros adicionales al stak del +kernel, brindandole control completo de donde y cómo la ejecución continúa +después de la llamada a sistema. + +Esto es arch-specific, pero típicamente involucra definir puntos de entrada +assembly que guardan/restauran registros adicionales e invocan el punto de +entrada real de la llamada a sistema. + +Para x86_64, esto es implementado como un punto de entrada ``stub_xyzzy`` +en ``arch/x86/entry/entry_64.S``, y la entrada en la tabla syscall +(``arch/x86/entry/syscalls/syscall_32.tbl``) es ajustada para calzar:: + + 333 common xyzzy stub_xyzzy + +El equivalente para programas 32-bit corriendo en un kernel 64-bit es +normalmente llamado ``stub32_xyzzy`` e implementado en +``arch/x86/entry/entry_64_compat.S``, con el correspondiente ajuste en la +tabla syscall en ``arch/x86/syscalls/syscall_32.tbl``:: + + 380 i386 xyzzy sys_xyzzy stub32_xyzzy + +Si la llamada a sistema necesita una capa de compatibilidad (como en la +sección anterior) entonces la versión ``stub32_`` necesita llamar a la +versión ``compat_sys_`` de la llamada a sistema, en vez de la versión +nativa de 64-bit. También, si la implementación de la versión x32 ABI no es +comun con la versión x86_64, entonces su tabla syscall también necesitará +invocar un stub que llame a la versión ``compat_sys_`` + +Para completar, también es agradable configurar un mapeo de modo que el +user-mode linux todavía funcione -- su tabla syscall referenciará +stub_xyzzy, pero el UML construido no incluye una implementación +``arch/x86/entry/entry_64.S``. Arreglar esto es tan simple como agregar un +#define a ``arch/x86/um/sys_call_table_64.c``:: + + #define stub_xyzzy sys_xyzzy + + +Otros detalles +-------------- + +La mayoría del kernel trata las llamadas a sistema de manera genérica, pero +está la excepción ocasional que pueda requerir actualización para su +llamada a sistema particular. + +El subsistema de auditoría es un caso especial; este incluye funciones +(arch-specific) que clasifican algunos tipos especiales de llamadas al +sistema -- específicamente file open (``open``/``openat``), program +execution (``execve`` /``execveat``) o operaciones multiplexores de socket +(``socketcall``). Si su nueva llamada de sistema es análoga a alguna de +estas, entonces el sistema auditor debe ser actualizado. + +Más generalmente, si existe una llamada al sistema que sea análoga a su +nueva llamada al sistema, entonces vale la pena hacer un grep a todo el +kernel de la llamada a sistema existente, para revisar que no exista otro +caso especial. + + +Testing +------- + +Una nueva llamada al sistema debe obviamente ser probada; también es útil +proveer a los revisores con una demostración de cómo los programas del +userspace usarán la llamada al sistema. Una buena forma de combinar estos +objetivos es incluir un simple programa self-test en un nuevo directorio +bajo ``tools/testing/selftests/``. + +Para una nueva llamada al sistema, obviamente no habrá una función +envoltorio libc por lo que el test necesitará ser invocado usando +``syscall()``; también, si la llamada al sistema involucra una nueva +estructura userspace-visible, el encabezado correspondiente necesitará ser +instalado para compilar el test. + +Asegure que selftest corra satisfactoriamente en todas las arquitecturas +soportadas. Por ejemplo, revise si funciona cuando es compilado como un +x86_64 (-m64), x86_32 (-m32) y x32 (-mx32) programa ABI. + +Para pruebas más amplias y exhautivas de la nueva funcionalidad, también +debería considerar agregar tests al Linus Test Project, o al proyecto +xfstests para cambios filesystem-related + + - https://linux-test-project.github.io/ + - git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git + + +Man Page +-------- + +Todas las llamada al sistema nueva deben venir con un man page completo, +idealmente usando groff markup, pero texto plano también funciona. Si se +usa groff, es útil incluir una versión ASCII pre-renderizada del man-page +en el cover del email para el patchset, para la conveniencia de los +revisores. + +El man page debe ser cc'do a linux-man@vger.kernel.org +Para más detalles, revise https://www.kernel.org/doc/man-pages/patches.html + + +No invoque las llamadas de sistemas en el kernel +------------------------------------------------ + +Las llamadas al sistema son, cómo se declaró más arriba, puntos de +interacción entre el userspace y el kernel. Por lo tanto, las funciones de +llamada al sistema como ``sys_xyzzy()`` o ``compat_sys_xyzzy()`` deberían +ser llamadas sólo desde el userspace vía la tabla de syscall, pero no de +otro lugar en el kernel. Si la funcionalidad syscall es útil para ser usada +dentro del kernel, necesita ser compartida entre syscalls nuevas o +antiguas, o necesita ser compartida entre una syscall y su variante de +compatibilidad, esta debería ser implementada mediante una función "helper" +(como ``ksys_xyzzy()``). Esta función del kernel puede ahora ser llamada +dentro del syscall stub (``sys_xyzzy()``), la syscall stub de +compatibilidad (``compat_sys_xyzzy()``), y/o otro código del kernel. + +Al menos en 64-bit x86, será un requerimiento duro desde la v4.17 en +adelante no invocar funciones de llamada al sistema (system call) en el +kernel. Este usa una convención de llamada diferente para llamadas al +sistema donde ``struct pt_regs`` es decodificado on-the-fly en un +envoltorio syscall que luego entrega el procesamiento al syscall real. Esto +significa que sólo aquellos parámetros que son realmente necesarios para +una syscall específica son pasados durante la entrada del syscall, en vez +de llenar en seis registros de CPU con contenido random del userspace todo +el tiempo (los cuales podrían causar serios problemas bajando la cadena de +llamadas). + +Más aún, reglas sobre cómo se debería acceder a la data pueden diferir +entre la data del kernel y la data de usuario. Esta es otra razón por la +cual llamar a ``sys_xyzzy()`` es generalmente una mala idea. + +Excepciones a esta regla están permitidas solamente en overrides +específicos de arquitectura, envoltorios de compatibilidad específicos de +arquitectura, u otro código en arch/. + + +Referencias y fuentes +--------------------- + + - Artículo LWN de Michael Kerrisk sobre el uso de argumentos flags en llamadas al + sistema: + https://lwn.net/Articles/585415/ + - Artículo LWN de Michael Kerrisk sobre cómo manejar flags desconocidos en una + llamada al sistema: https://lwn.net/Articles/588444/ + - Artículo LWN de Jake Edge describiendo restricciones en argumentos en + 64-bit system call: https://lwn.net/Articles/311630/ + - Par de artículos LWN de David Drysdale que describen la ruta de implementación + de llamadas al sistema en detalle para v3.14: + + - https://lwn.net/Articles/604287/ + - https://lwn.net/Articles/604515/ + + - Requerimientos arquitectura-específicos para llamadas al sistema son discutidos en el + :manpage:`syscall(2)` man-page: + http://man7.org/linux/man-pages/man2/syscall.2.html#NOTES + - Recopilación de emails de Linus Torvalds discutiendo problemas con ``ioctl()``: + https://yarchive.net/comp/linux/ioctl.html + - "How to not invent kernel interfaces", Arnd Bergmann, + https://www.ukuug.org/events/linux2007/2007/papers/Bergmann.pdf + - Artículo LWN de Michael Kerrisk sobre evitar nuevos usos de CAP_SYS_ADMIN: + https://lwn.net/Articles/486306/ + - Recomendaciones de Andrew Morton que toda la información relacionada a una nueva + llamada al sistema debe venir en el mismo hilo de correos: + https://lore.kernel.org/r/20140724144747.3041b208832bbdf9fbce5d96@linux-foundation.org + - Recomendaciones de Michael Kerrisk que una nueva llamada al sistema debe venir + con un man-page: https://lore.kernel.org/r/CAKgNAkgMA39AfoSoA5Pe1r9N+ZzfYQNvNPvcRN7tOvRb8+v06Q@mail.gmail.com + - Sugerencias de Thomas Gleixner que conexiones x86 deben ir en commits + separados: https://lore.kernel.org/r/alpine.DEB.2.11.1411191249560.3909@nanos + - Sugerencias de Greg Kroah-Hartman que es bueno para las nueva llamadas al sistema + que vengan con man-page y selftest: https://lore.kernel.org/r/20140320025530.GA25469@kroah.com + - Discusión de Michael Kerrisk de nuevas system call vs. extensiones :manpage:`prctl(2)`: + https://lore.kernel.org/r/CAHO5Pa3F2MjfTtfNxa8LbnkeeU8=YJ+9tDqxZpw7Gz59E-4AUg@mail.gmail.com + - Sugerencias de Ingo Molnar que llamadas al sistema que involucran múltiples + argumentos deben encapsular estos argumentos en una estructura, la cual incluye + un campo de tamaño para futura extensibilidad: https://lore.kernel.org/r/20150730083831.GA22182@gmail.com + - Enumerando rarezas por la (re-)utilización de O_* numbering space flags: + + - commit 75069f2b5bfb ("vfs: renumber FMODE_NONOTIFY and add to uniqueness + check") + - commit 12ed2e36c98a ("fanotify: FMODE_NONOTIFY and __O_SYNC in sparc + conflict") + - commit bb458c644a59 ("Safer ABI for O_TMPFILE") + + - Discusión de Matthew Wilcox sobre las restricciones en argumentos 64-bit: + https://lore.kernel.org/r/20081212152929.GM26095@parisc-linux.org + - Recomendaciones de Greg Kroah-Hartman sobre flags desconocidos deben ser + vigilados: https://lore.kernel.org/r/20140717193330.GB4703@kroah.com + - Recomendaciones de Linus Torvalds que las llamadas al sistema x32 deben favorecer + compatibilidad con versiones 64-bit sobre versiones 32-bit: + https://lore.kernel.org/r/CA+55aFxfmwfB7jbbrXxa=K7VBYPfAvmu3XOkGrLbB1UFjX1+Ew@mail.gmail.com diff --git a/Documentation/translations/sp_SP/process/index.rst b/Documentation/translations/sp_SP/process/index.rst index 3b0c32593726..0bdeb1eb4403 100644 --- a/Documentation/translations/sp_SP/process/index.rst +++ b/Documentation/translations/sp_SP/process/index.rst @@ -19,3 +19,4 @@ magic-number programming-language deprecated + adding-syscalls -- GitLab From 340086da9a87820b40601141a0e9e87c954ac006 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 2 May 2023 13:11:21 -0400 Subject: [PATCH 4414/5631] nfsd: define exports_proc_ops with CONFIG_PROC_FS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_PROC_FS fs/nfsd/nfsctl.c:161:30: error: ‘exports_proc_ops’ defined but not used [-Werror=unused-const-variable=] 161 | static const struct proc_ops exports_proc_ops = { | ^~~~~~~~~~~~~~~~ The only use of exports_proc_ops is when CONFIG_PROC_FS is defined, so its definition should be likewise conditional. Signed-off-by: Tom Rix Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/nfsctl.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7b8f17ee5224..c159817d1282 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -153,18 +153,6 @@ static int exports_net_open(struct net *net, struct file *file) return 0; } -static int exports_proc_open(struct inode *inode, struct file *file) -{ - return exports_net_open(current->nsproxy->net_ns, file); -} - -static const struct proc_ops exports_proc_ops = { - .proc_open = exports_proc_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - static int exports_nfsd_open(struct inode *inode, struct file *file) { return exports_net_open(inode->i_sb->s_fs_info, file); @@ -1458,6 +1446,19 @@ static struct file_system_type nfsd_fs_type = { MODULE_ALIAS_FS("nfsd"); #ifdef CONFIG_PROC_FS + +static int exports_proc_open(struct inode *inode, struct file *file) +{ + return exports_net_open(current->nsproxy->net_ns, file); +} + +static const struct proc_ops exports_proc_ops = { + .proc_open = exports_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + static int create_proc_exports_entry(void) { struct proc_dir_entry *entry; -- GitLab From fc412a6196a6f46ece0e6e6b118556464f165800 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 2 May 2023 14:07:13 -0400 Subject: [PATCH 4415/5631] lockd: define nlm_port_min,max with CONFIG_SYSCTL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_SYSCTL fs/lockd/svc.c:80:51: error: ‘nlm_port_max’ defined but not used [-Werror=unused-const-variable=] 80 | static const int nlm_port_min = 0, nlm_port_max = 65535; | ^~~~~~~~~~~~ fs/lockd/svc.c:80:33: error: ‘nlm_port_min’ defined but not used [-Werror=unused-const-variable=] 80 | static const int nlm_port_min = 0, nlm_port_max = 65535; | ^~~~~~~~~~~~ The only use of these variables is when CONFIG_SYSCTL is defined, so their definition should be likewise conditional. Signed-off-by: Tom Rix Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a47303b2cba..fe2f6dd9a874 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -77,9 +77,9 @@ static const unsigned long nlm_grace_period_min = 0; static const unsigned long nlm_grace_period_max = 240; static const unsigned long nlm_timeout_min = 3; static const unsigned long nlm_timeout_max = 20; -static const int nlm_port_min = 0, nlm_port_max = 65535; #ifdef CONFIG_SYSCTL +static const int nlm_port_min = 0, nlm_port_max = 65535; static struct ctl_table_header * nlm_sysctl_table; #endif -- GitLab From dd411433129c07a3bea43a0cc5ad9587bac1736a Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 8 Mar 2023 16:33:09 +0800 Subject: [PATCH 4416/5631] mm/damon/paddr: minor refactor of damon_pa_pageout() Patch series "mm/damon/paddr: minor code improvement", v3. Unify folio_put() to make code more clear, and also fix minor issue in damon_pa_young(). This patch (of 3): Omit three lines by unified folio_put(), and make code more clear. Link: https://lkml.kernel.org/r/20230308083311.120951-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20230308083311.120951-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- mm/damon/paddr.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index dd9c33fbe805..0db724aec5cb 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -238,21 +238,18 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s) if (!folio) continue; - if (damos_pa_filter_out(s, folio)) { - folio_put(folio); - continue; - } + if (damos_pa_filter_out(s, folio)) + goto put_folio; folio_clear_referenced(folio); folio_test_clear_young(folio); - if (!folio_isolate_lru(folio)) { - folio_put(folio); - continue; - } + if (!folio_isolate_lru(folio)) + goto put_folio; if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); +put_folio: folio_put(folio); } applied = reclaim_pages(&folio_list); -- GitLab From b6993be23601c8bc992dc9743fbf78c1ff5d6b6a Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 8 Mar 2023 16:33:10 +0800 Subject: [PATCH 4417/5631] mm/damon/paddr: minor refactor of damon_pa_mark_accessed_or_deactivate() Omit one line by unified folio_put(), and make code more clear. Link: https://lkml.kernel.org/r/20230308083311.120951-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- mm/damon/paddr.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 0db724aec5cb..b22f6fbb5816 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -268,16 +268,15 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( if (!folio) continue; - if (damos_pa_filter_out(s, folio)) { - folio_put(folio); - continue; - } + if (damos_pa_filter_out(s, folio)) + goto put_folio; if (mark_accessed) folio_mark_accessed(folio); else folio_deactivate(folio); applied += folio_nr_pages(folio); +put_folio: folio_put(folio); } return applied * PAGE_SIZE; -- GitLab From 70307b0e297a6634be855c49525ccbea50922a90 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 8 Mar 2023 16:33:11 +0800 Subject: [PATCH 4418/5631] mm/damon/paddr: fix missing folio_sz update in damon_pa_young() The *folio_sz in damon_pa_young() will be used(as last_folio_sz) by __damon_pa_check_access(), so it's need to be updated, fix missing branch. Link: https://lkml.kernel.org/r/20230308083311.120951-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- mm/damon/paddr.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index b22f6fbb5816..467b99166b43 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -134,10 +134,8 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz) } need_lock = !folio_test_anon(folio) || folio_test_ksm(folio); - if (need_lock && !folio_trylock(folio)) { - folio_put(folio); - return false; - } + if (need_lock && !folio_trylock(folio)) + goto out; rmap_walk(folio, &rwc); -- GitLab From 24139c07f413ef4b555482c758343d71392a19bc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 22:54:18 +0200 Subject: [PATCH 4419/5631] mm/ksm: unmerge and clear VM_MERGEABLE when setting PR_SET_MEMORY_MERGE=0 Patch series "mm/ksm: improve PR_SET_MEMORY_MERGE=0 handling and cleanup disabling KSM", v2. (1) Make PR_SET_MEMORY_MERGE=0 unmerge pages like setting MADV_UNMERGEABLE does, (2) add a selftest for it and (3) factor out disabling of KSM from s390/gmap code. This patch (of 3): Let's unmerge any KSM pages when setting PR_SET_MEMORY_MERGE=0, and clear the VM_MERGEABLE flag from all VMAs -- just like KSM would. Of course, only do that if we previously set PR_SET_MEMORY_MERGE=1. Link: https://lkml.kernel.org/r/20230422205420.30372-1-david@redhat.com Link: https://lkml.kernel.org/r/20230422205420.30372-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Janosch Frank Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- include/linux/ksm.h | 1 + kernel/sys.c | 12 +++------ mm/ksm.c | 59 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 9 deletions(-) diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7a9b76fb6c3f..429efa6ff4ae 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -21,6 +21,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); +int ksm_disable_merge_any(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); diff --git a/kernel/sys.c b/kernel/sys.c index 72cdb16e2636..339fee3eff6a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2695,16 +2695,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, if (mmap_write_lock_killable(me->mm)) return -EINTR; - if (arg2) { + if (arg2) error = ksm_enable_merge_any(me->mm); - } else { - /* - * TODO: we might want disable KSM on all VMAs and - * trigger unsharing to completely disable KSM. - */ - clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags); - error = 0; - } + else + error = ksm_disable_merge_any(me->mm); mmap_write_unlock(me->mm); break; case PR_GET_MEMORY_MERGE: diff --git a/mm/ksm.c b/mm/ksm.c index 9e48258985d2..823bb3475a68 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2520,6 +2520,22 @@ static void __ksm_add_vma(struct vm_area_struct *vma) vm_flags_set(vma, VM_MERGEABLE); } +static int __ksm_del_vma(struct vm_area_struct *vma) +{ + int err; + + if (!(vma->vm_flags & VM_MERGEABLE)) + return 0; + + if (vma->anon_vma) { + err = unmerge_ksm_pages(vma, vma->vm_start, vma->vm_end); + if (err) + return err; + } + + vm_flags_clear(vma, VM_MERGEABLE); + return 0; +} /** * ksm_add_vma - Mark vma as mergeable if compatible * @@ -2542,6 +2558,20 @@ static void ksm_add_vmas(struct mm_struct *mm) __ksm_add_vma(vma); } +static int ksm_del_vmas(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + int err; + + VMA_ITERATOR(vmi, mm, 0); + for_each_vma(vmi, vma) { + err = __ksm_del_vma(vma); + if (err) + return err; + } + return 0; +} + /** * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all * compatible VMA's @@ -2569,6 +2599,35 @@ int ksm_enable_merge_any(struct mm_struct *mm) return 0; } +/** + * ksm_disable_merge_any - Disable merging on all compatible VMA's of the mm, + * previously enabled via ksm_enable_merge_any(). + * + * Disabling merging implies unmerging any merged pages, like setting + * MADV_UNMERGEABLE would. If unmerging fails, the whole operation fails and + * merging on all compatible VMA's remains enabled. + * + * @mm: Pointer to mm + * + * Returns 0 on success, otherwise error code + */ +int ksm_disable_merge_any(struct mm_struct *mm) +{ + int err; + + if (!test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return 0; + + err = ksm_del_vmas(mm); + if (err) { + ksm_add_vmas(mm); + return err; + } + + clear_bit(MMF_VM_MERGE_ANY, &mm->flags); + return 0; +} + int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { -- GitLab From 1150ea9338554ee6685c9f8939cf7202bf5b27cf Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 22:54:19 +0200 Subject: [PATCH 4420/5631] selftests/ksm: ksm_functional_tests: add prctl unmerge test Let's test whether setting PR_SET_MEMORY_MERGE to 0 after setting it to 1 will unmerge pages, similar to how setting MADV_UNMERGEABLE after setting MADV_MERGEABLE would. Link: https://lkml.kernel.org/r/20230422205420.30372-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Janosch Frank Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- .../selftests/mm/ksm_functional_tests.c | 46 ++++++++++++++++--- 1 file changed, 40 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 7bc9fc17c9f0..26853badae70 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -91,9 +91,10 @@ static int ksm_merge(void) return 0; } -static char *mmap_and_merge_range(char val, unsigned long size) +static char *mmap_and_merge_range(char val, unsigned long size, bool use_prctl) { char *map; + int ret; map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); @@ -110,7 +111,17 @@ static char *mmap_and_merge_range(char val, unsigned long size) /* Make sure each page contains the same values to merge them. */ memset(map, val, size); - if (madvise(map, size, MADV_MERGEABLE)) { + + if (use_prctl) { + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + goto unmap; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + goto unmap; + } + } else if (madvise(map, size, MADV_MERGEABLE)) { ksft_test_result_fail("MADV_MERGEABLE failed\n"); goto unmap; } @@ -133,7 +144,7 @@ static void test_unmerge(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -155,7 +166,7 @@ static void test_unmerge_discarded(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -187,7 +198,7 @@ static void test_unmerge_uffd_wp(void) ksft_print_msg("[RUN] %s\n", __func__); - map = mmap_and_merge_range(0xcf, size); + map = mmap_and_merge_range(0xcf, size, false); if (map == MAP_FAILED) return; @@ -323,9 +334,31 @@ static void test_prctl_fork(void) ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); } +static void test_prctl_unmerge(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size, true); + if (map == MAP_FAILED) + return; + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + munmap(map, size); +} + int main(int argc, char **argv) { - unsigned int tests = 4; + unsigned int tests = 5; int err; #ifdef __NR_userfaultfd @@ -355,6 +388,7 @@ int main(int argc, char **argv) test_prctl(); test_prctl_fork(); + test_prctl_unmerge(); err = ksft_get_fail_cnt(); if (err) -- GitLab From 2c281f54f556e1f3266c8cb104adf9eea7a7b742 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Sat, 22 Apr 2023 23:01:56 +0200 Subject: [PATCH 4421/5631] mm/ksm: move disabling KSM from s390/gmap code to KSM code Let's factor out actual disabling of KSM. The existing "mm->def_flags &= ~VM_MERGEABLE;" was essentially a NOP and can be dropped, because def_flags should never include VM_MERGEABLE. Note that we don't currently prevent re-enabling KSM. This should now be faster in case KSM was never enabled, because we only conditionally iterate all VMAs. Further, it certainly looks cleaner. Link: https://lkml.kernel.org/r/20230422210156.33630-1-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Janosch Frank Acked-by: Stefan Roesch Cc: Christian Borntraeger Cc: Claudio Imbrenda Cc: Heiko Carstens Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Shuah Khan Cc: Sven Schnelle Cc: Vasily Gorbik Signed-off-by: Andrew Morton --- arch/s390/mm/gmap.c | 20 +------------------- include/linux/ksm.h | 6 ++++++ mm/ksm.c | 11 +++++++++++ 3 files changed, 18 insertions(+), 19 deletions(-) diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 0949811761e6..dfe905c7bd8e 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2585,30 +2585,12 @@ EXPORT_SYMBOL_GPL(s390_enable_sie); int gmap_mark_unmergeable(void) { - struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; - unsigned long vm_flags; - int ret; - VMA_ITERATOR(vmi, mm, 0); - /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ - clear_bit(MMF_VM_MERGE_ANY, &mm->flags); - - for_each_vma(vmi, vma) { - /* Copy vm_flags to avoid partial modifications in ksm_madvise */ - vm_flags = vma->vm_flags; - ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vm_flags); - if (ret) - return ret; - vm_flags_reset(vma, vm_flags); - } - mm->def_flags &= ~VM_MERGEABLE; - return 0; + return ksm_disable(current->mm); } EXPORT_SYMBOL_GPL(gmap_mark_unmergeable); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 429efa6ff4ae..899a314bc487 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -22,6 +22,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); +int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); @@ -80,6 +81,11 @@ static inline void ksm_add_vma(struct vm_area_struct *vma) { } +static inline int ksm_disable(struct mm_struct *mm) +{ + return 0; +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; diff --git a/mm/ksm.c b/mm/ksm.c index 823bb3475a68..0156bded3a66 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2628,6 +2628,17 @@ int ksm_disable_merge_any(struct mm_struct *mm) return 0; } +int ksm_disable(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + + if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) + return 0; + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return ksm_disable_merge_any(mm); + return ksm_del_vmas(mm); +} + int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { -- GitLab From 65f67a3e002f0e5ae84a65be915248d57d480060 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 25 Apr 2023 20:44:53 +0800 Subject: [PATCH 4422/5631] mm/page_alloc: add some comments to explain the possible hole in __pageblock_pfn_to_page() Now the __pageblock_pfn_to_page() is used by set_zone_contiguous(), which checks whether the given zone contains holes, and uses pfn_to_online_page() to validate if the start pfn is online and valid, as well as using pfn_valid() to validate the end pfn. However, the __pageblock_pfn_to_page() function may return non-NULL even if the end pfn of a pageblock is in a memory hole in some situations. For example, if the pageblock order is MAX_ORDER, which will fall into 2 sub-sections, and the end pfn of the pageblock may be hole even though the start pfn is online and valid. See below memory layout as an example and suppose the pageblock order is MAX_ORDER. [ 0.000000] Zone ranges: [ 0.000000] DMA [mem 0x0000000040000000-0x00000000ffffffff] [ 0.000000] DMA32 empty [ 0.000000] Normal [mem 0x0000000100000000-0x0000001fa7ffffff] [ 0.000000] Movable zone start for each node [ 0.000000] Early memory node ranges [ 0.000000] node 0: [mem 0x0000000040000000-0x0000001fa3c7ffff] [ 0.000000] node 0: [mem 0x0000001fa3c80000-0x0000001fa3ffffff] [ 0.000000] node 0: [mem 0x0000001fa4000000-0x0000001fa402ffff] [ 0.000000] node 0: [mem 0x0000001fa4030000-0x0000001fa40effff] [ 0.000000] node 0: [mem 0x0000001fa40f0000-0x0000001fa73cffff] [ 0.000000] node 0: [mem 0x0000001fa73d0000-0x0000001fa745ffff] [ 0.000000] node 0: [mem 0x0000001fa7460000-0x0000001fa746ffff] [ 0.000000] node 0: [mem 0x0000001fa7470000-0x0000001fa758ffff] [ 0.000000] node 0: [mem 0x0000001fa7590000-0x0000001fa7dfffff] Focus on the last memory range, and there is a hole for the range [mem 0x0000001fa7590000-0x0000001fa7dfffff]. That means the last pageblock will contain the range from 0x1fa7c00000 to 0x1fa7ffffff, since the pageblock must be 4M aligned. And in this pageblock, these pfns will fall into 2 sub-section (the sub-section size is 2M aligned). So, the 1st sub-section (indicates pfn range: 0x1fa7c00000 - 0x1fa7dfffff ) in this pageblock is valid by calling subsection_map_init() in free_area_init(), but the 2nd sub-section (indicates pfn range: 0x1fa7e00000 - 0x1fa7ffffff ) in this pageblock is not valid. This did not break anything until now, but the zone continuous is fragile in this possible scenario. So as previous discussion[1], it is better to add some comments to explain this possible issue in case there are some future pfn walkers that rely on this. [1] https://lore.kernel.org/all/87r0sdsmr6.fsf@yhuang6-desk2.ccr.corp.intel.com/ Link: https://lkml.kernel.org/r/5c26368865e79c743a453dea48d30670b19d2e4f.1682425534.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/5c26368865e79c743a453dea48d30670b19d2e4f.1682425534.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Acked-by: Michal Hocko Reviewed-by: "Huang, Ying" Cc: Baolin Wang Cc: David Hildenbrand Cc: Mel Gorman Cc: Mike Rapoport (IBM) Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- mm/page_alloc.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6da423ec356f..d71c80f29946 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1502,6 +1502,15 @@ void __free_pages_core(struct page *page, unsigned int order) * interleaving within a single pageblock. It is therefore sufficient to check * the first and last page of a pageblock and avoid checking each individual * page in a pageblock. + * + * Note: the function may return non-NULL struct page even for a page block + * which contains a memory hole (i.e. there is no physical memory for a subset + * of the pfn range). For example, if the pageblock order is MAX_ORDER, which + * will fall into 2 sub-sections, and the end pfn of the pageblock may be hole + * even though the start pfn is online and valid. This should be safe most of + * the time because struct pages are still initialized via init_unavailable_range() + * and pfn walkers shouldn't touch any physical memory range for which they do + * not recognize any specific metadata in struct pages. */ struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) -- GitLab From 245f0922689364b21163af4937a05ea0ba576fae Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 17 Apr 2023 12:53:23 +0800 Subject: [PATCH 4423/5631] mm: hwpoison: coredump: support recovery from dump_user_range() dump_user_range() is used to copy the user page to a coredump file, but if a hardware memory error occurred during copy, which called from __kernel_write_iter() in dump_user_range(), it crashes, CPU: 112 PID: 7014 Comm: mca-recover Not tainted 6.3.0-rc2 #425 pc : __memcpy+0x110/0x260 lr : _copy_from_iter+0x3bc/0x4c8 ... Call trace: __memcpy+0x110/0x260 copy_page_from_iter+0xcc/0x130 pipe_write+0x164/0x6d8 __kernel_write_iter+0x9c/0x210 dump_user_range+0xc8/0x1d8 elf_core_dump+0x308/0x368 do_coredump+0x2e8/0xa40 get_signal+0x59c/0x788 do_signal+0x118/0x1f8 do_notify_resume+0xf0/0x280 el0_da+0x130/0x138 el0t_64_sync_handler+0x68/0xc0 el0t_64_sync+0x188/0x190 Generally, the '->write_iter' of file ops will use copy_page_from_iter() and copy_page_from_iter_atomic(), change memcpy() to copy_mc_to_kernel() in both of them to handle #MC during source read, which stop coredump processing and kill the task instead of kernel panic, but the source address may not always a user address, so introduce a new copy_mc flag in struct iov_iter{} to indicate that the iter could do a safe memory copy, also introduce the helpers to set/cleck the flag, for now, it's only used in coredump's dump_user_range(), but it could expand to any other scenarios to fix the similar issue. Link: https://lkml.kernel.org/r/20230417045323.11054-1-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Alexander Viro Cc: Christian Brauner Cc: Miaohe Lin Cc: Naoya Horiguchi Cc: Tong Tiangen Cc: Jens Axboe Signed-off-by: Andrew Morton --- fs/coredump.c | 1 + include/linux/uio.h | 16 ++++++++++++++++ lib/iov_iter.c | 17 +++++++++++++++-- 3 files changed, 32 insertions(+), 2 deletions(-) diff --git a/fs/coredump.c b/fs/coredump.c index 5df1e6e1eb2b..ece7badf701b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -882,6 +882,7 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) pos = file->f_pos; bvec_set_page(&bvec, page, PAGE_SIZE, 0); iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); + iov_iter_set_copy_mc(&iter); n = __kernel_write_iter(cprm->file, &iter, &pos); if (n != PAGE_SIZE) return 0; diff --git a/include/linux/uio.h b/include/linux/uio.h index 3d386849a758..044c1d8c230c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -42,6 +42,7 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; + bool copy_mc; bool nofault; bool data_source; bool user_backed; @@ -256,8 +257,22 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); +static inline void iov_iter_set_copy_mc(struct iov_iter *i) +{ + i->copy_mc = true; +} + +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return i->copy_mc; +} #else #define _copy_mc_to_iter _copy_to_iter +static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } +static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) +{ + return false; +} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -380,6 +395,7 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, + .copy_mc = false, .user_backed = true, .data_source = direction, .ubuf = buf, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index c3dbe994112c..960223ed9199 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -434,6 +434,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, + .copy_mc = false, .nofault = false, .user_backed = true, .data_source = direction, @@ -630,6 +631,14 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ +static void *memcpy_from_iter(struct iov_iter *i, void *to, const void *from, + size_t size) +{ + if (iov_iter_is_copy_mc(i)) + return (void *)copy_mc_to_kernel(to, from, size); + return memcpy(to, from, size); +} + size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) @@ -639,7 +648,7 @@ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) might_fault(); iterate_and_advance(i, bytes, base, len, off, copyin(addr + off, base, len), - memcpy(addr + off, base, len) + memcpy_from_iter(i, addr + off, base, len) ) return bytes; @@ -862,7 +871,7 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t byt } iterate_and_advance(i, bytes, base, len, off, copyin(p + off, base, len), - memcpy(p + off, base, len) + memcpy_from_iter(i, p + off, base, len) ) kunmap_atomic(kaddr); return bytes; @@ -1043,6 +1052,7 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, + .copy_mc = false, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, @@ -1059,6 +1069,7 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, + .copy_mc = false, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, @@ -1105,6 +1116,7 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, + .copy_mc = false, .data_source = direction, .xarray = xarray, .xarray_start = start, @@ -1128,6 +1140,7 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, + .copy_mc = false, .data_source = false, .count = count, .iov_offset = 0 -- GitLab From 29083fd84da576bfb3563d044f98d38e6b338f00 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 18 Apr 2023 17:42:12 +0100 Subject: [PATCH 4424/5631] kasan: hw_tags: avoid invalid virt_to_page() When booting with 'kasan.vmalloc=off', a kernel configured with support for KASAN_HW_TAGS will explode at boot time due to bogus use of virt_to_page() on a vmalloc adddress. With CONFIG_DEBUG_VIRTUAL selected this will be reported explicitly, and with or without CONFIG_DEBUG_VIRTUAL the kernel will dereference a bogus address: | ------------[ cut here ]------------ | virt_to_phys used for non-linear address: (____ptrval____) (0xffff800008000000) | WARNING: CPU: 0 PID: 0 at arch/arm64/mm/physaddr.c:15 __virt_to_phys+0x78/0x80 | Modules linked in: | CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.3.0-rc3-00073-g83865133300d-dirty #4 | Hardware name: linux,dummy-virt (DT) | pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : __virt_to_phys+0x78/0x80 | lr : __virt_to_phys+0x78/0x80 | sp : ffffcd076afd3c80 | x29: ffffcd076afd3c80 x28: 0068000000000f07 x27: ffff800008000000 | x26: fffffbfff0000000 x25: fffffbffff000000 x24: ff00000000000000 | x23: ffffcd076ad3c000 x22: fffffc0000000000 x21: ffff800008000000 | x20: ffff800008004000 x19: ffff800008000000 x18: ffff800008004000 | x17: 666678302820295f x16: ffffffffffffffff x15: 0000000000000004 | x14: ffffcd076b009e88 x13: 0000000000000fff x12: 0000000000000003 | x11: 00000000ffffefff x10: c0000000ffffefff x9 : 0000000000000000 | x8 : 0000000000000000 x7 : 205d303030303030 x6 : 302e30202020205b | x5 : ffffcd076b41d63f x4 : ffffcd076afd3827 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffffcd076afd3a30 x0 : 000000000000004f | Call trace: | __virt_to_phys+0x78/0x80 | __kasan_unpoison_vmalloc+0xd4/0x478 | __vmalloc_node_range+0x77c/0x7b8 | __vmalloc_node+0x54/0x64 | init_IRQ+0x94/0xc8 | start_kernel+0x194/0x420 | __primary_switched+0xbc/0xc4 | ---[ end trace 0000000000000000 ]--- | Unable to handle kernel paging request at virtual address 03fffacbe27b8000 | Mem abort info: | ESR = 0x0000000096000004 | EC = 0x25: DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | FSC = 0x04: level 0 translation fault | Data abort info: | ISV = 0, ISS = 0x00000004 | CM = 0, WnR = 0 | swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000041bc5000 | [03fffacbe27b8000] pgd=0000000000000000, p4d=0000000000000000 | Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP | Modules linked in: | CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 6.3.0-rc3-00073-g83865133300d-dirty #4 | Hardware name: linux,dummy-virt (DT) | pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : __kasan_unpoison_vmalloc+0xe4/0x478 | lr : __kasan_unpoison_vmalloc+0xd4/0x478 | sp : ffffcd076afd3ca0 | x29: ffffcd076afd3ca0 x28: 0068000000000f07 x27: ffff800008000000 | x26: 0000000000000000 x25: 03fffacbe27b8000 x24: ff00000000000000 | x23: ffffcd076ad3c000 x22: fffffc0000000000 x21: ffff800008000000 | x20: ffff800008004000 x19: ffff800008000000 x18: ffff800008004000 | x17: 666678302820295f x16: ffffffffffffffff x15: 0000000000000004 | x14: ffffcd076b009e88 x13: 0000000000000fff x12: 0000000000000001 | x11: 0000800008000000 x10: ffff800008000000 x9 : ffffb2f8dee00000 | x8 : 000ffffb2f8dee00 x7 : 205d303030303030 x6 : 302e30202020205b | x5 : ffffcd076b41d63f x4 : ffffcd076afd3827 x3 : 0000000000000000 | x2 : 0000000000000000 x1 : ffffcd076afd3a30 x0 : ffffb2f8dee00000 | Call trace: | __kasan_unpoison_vmalloc+0xe4/0x478 | __vmalloc_node_range+0x77c/0x7b8 | __vmalloc_node+0x54/0x64 | init_IRQ+0x94/0xc8 | start_kernel+0x194/0x420 | __primary_switched+0xbc/0xc4 | Code: d34cfc08 aa1f03fa 8b081b39 d503201f (f9400328) | ---[ end trace 0000000000000000 ]--- | Kernel panic - not syncing: Attempted to kill the idle task! This is because init_vmalloc_pages() erroneously calls virt_to_page() on a vmalloc address, while virt_to_page() is only valid for addresses in the linear/direct map. Since init_vmalloc_pages() expects virtual addresses in the vmalloc range, it must use vmalloc_to_page() rather than virt_to_page(). We call init_vmalloc_pages() from __kasan_unpoison_vmalloc(), where we check !is_vmalloc_or_module_addr(), suggesting that we might encounter a non-vmalloc address. Luckily, this never happens. By design, we only call __kasan_unpoison_vmalloc() on pointers in the vmalloc area, and I have verified that we don't violate that expectation. Given that, is_vmalloc_or_module_addr() must always be true for any legitimate argument to __kasan_unpoison_vmalloc(). Correct init_vmalloc_pages() to use vmalloc_to_page(), and remove the redundant and misleading use of is_vmalloc_or_module_addr() in __kasan_unpoison_vmalloc(). Link: https://lkml.kernel.org/r/20230418164212.1775741-1-mark.rutland@arm.com Fixes: 6c2f761dad7851d8 ("kasan: fix zeroing vmalloc memory with HW_TAGS") Signed-off-by: Mark Rutland Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Marco Elver Cc: Signed-off-by: Andrew Morton --- mm/kasan/hw_tags.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index f98b9f4d9d3e..06141bbc1e51 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -285,7 +285,7 @@ static void init_vmalloc_pages(const void *start, unsigned long size) const void *addr; for (addr = start; addr < start + size; addr += PAGE_SIZE) { - struct page *page = virt_to_page(addr); + struct page *page = vmalloc_to_page(addr); clear_highpage_kasan_tagged(page); } @@ -297,7 +297,7 @@ void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, u8 tag; unsigned long redzone_start, redzone_size; - if (!kasan_vmalloc_enabled() || !is_vmalloc_or_module_addr(start)) { + if (!kasan_vmalloc_enabled()) { if (flags & KASAN_VMALLOC_INIT) init_vmalloc_pages(start, size); return (void *)start; -- GitLab From 43ec16f1450f4936025a9bdf1a273affdb9732c1 Mon Sep 17 00:00:00 2001 From: Zhang Zhengming Date: Wed, 19 Apr 2023 12:02:03 +0800 Subject: [PATCH 4425/5631] relayfs: fix out-of-bounds access in relay_file_read There is a crash in relay_file_read, as the var from point to the end of last subbuf. The oops looks something like: pc : __arch_copy_to_user+0x180/0x310 lr : relay_file_read+0x20c/0x2c8 Call trace: __arch_copy_to_user+0x180/0x310 full_proxy_read+0x68/0x98 vfs_read+0xb0/0x1d0 ksys_read+0x6c/0xf0 __arm64_sys_read+0x20/0x28 el0_svc_common.constprop.3+0x84/0x108 do_el0_svc+0x74/0x90 el0_svc+0x1c/0x28 el0_sync_handler+0x88/0xb0 el0_sync+0x148/0x180 We get the condition by analyzing the vmcore: 1). The last produced byte and last consumed byte both at the end of the last subbuf 2). A softirq calls function(e.g __blk_add_trace) to write relay buffer occurs when an program is calling relay_file_read_avail(). relay_file_read relay_file_read_avail relay_file_read_consume(buf, 0, 0); //interrupted by softirq who will write subbuf .... return 1; //read_start point to the end of the last subbuf read_start = relay_file_read_start_pos //avail is equal to subsize avail = relay_file_read_subbuf_avail //from points to an invalid memory address from = buf->start + read_start //system is crashed copy_to_user(buffer, from, avail) Link: https://lkml.kernel.org/r/20230419040203.37676-1-zhang.zhengming@h3c.com Fixes: 8d62fdebdaf9 ("relay file read: start-pos fix") Signed-off-by: Zhang Zhengming Reviewed-by: Zhao Lei Reviewed-by: Zhou Kete Reviewed-by: Pengcheng Yang Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton --- kernel/relay.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/relay.c b/kernel/relay.c index 9aa70ae53d24..a80fa01042e9 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -989,7 +989,8 @@ static size_t relay_file_read_start_pos(struct rchan_buf *buf) size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; - size_t read_pos = consumed * subbuf_size + buf->bytes_consumed; + size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) + % (n_subbufs * subbuf_size); read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; -- GitLab From 00ca0f2e86bf40b016a646e6323a8941a09cf106 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 30 Apr 2023 16:07:07 +0100 Subject: [PATCH 4426/5631] mm/mempolicy: correctly update prev when policy is equal on mbind The refactoring in commit f4e9e0e69468 ("mm/mempolicy: fix use-after-free of VMA iterator") introduces a subtle bug which arises when attempting to apply a new NUMA policy across a range of VMAs in mbind_range(). The refactoring passes a **prev pointer to keep track of the previous VMA in order to reduce duplication, and in all but one case it keeps this correctly updated. The bug arises when a VMA within the specified range has an equivalent policy as determined by mpol_equal() - which unlike other cases, does not update prev. This can result in a situation where, later in the iteration, a VMA is found whose policy does need to change. At this point, vma_merge() is invoked with prev pointing to a VMA which is before the previous VMA. Since vma_merge() discovers the curr VMA by looking for the one immediately after prev, it will now be in a situation where this VMA is incorrect and the merge will not proceed correctly. This is checked in the VM_WARN_ON() invariant case with end > curr->vm_end, which, if a merge is possible, results in a warning (if CONFIG_DEBUG_VM is specified). I note that vma_merge() performs these invariant checks only after merge_prev/merge_next are checked, which is debatable as it hides this issue if no merge is possible even though a buggy situation has arisen. The solution is simply to update the prev pointer even when policies are equal. This caused a bug to arise in the 6.2.y stable tree, and this patch resolves this bug. Link: https://lkml.kernel.org/r/83f1d612acb519d777bebf7f3359317c4e7f4265.1682866629.git.lstoakes@gmail.com Fixes: f4e9e0e69468 ("mm/mempolicy: fix use-after-free of VMA iterator") Signed-off-by: Lorenzo Stoakes Reported-by: kernel test robot Link: https://lore.kernel.org/oe-lkp/202304292203.44ddeff6-oliver.sang@intel.com Cc: Liam R. Howlett Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton --- mm/mempolicy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2068b594dc88..1756389a0609 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -808,8 +808,10 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, vmstart = vma->vm_start; } - if (mpol_equal(vma_policy(vma), new_pol)) + if (mpol_equal(vma_policy(vma), new_pol)) { + *prev = vma; return 0; + } pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags, -- GitLab From 3628d2bb155b0e4dfc1922a99de0631d3e2095d3 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 2 May 2023 15:55:00 +0200 Subject: [PATCH 4427/5631] MAINTAINERS: update Michal Simek's email @xilinx.com is still working but better to switch to new amd.com after AMD/Xilinx acquisition. Link: https://lkml.kernel.org/r/bd073d026f8c367a9cfb45d26d39f26e40c665dc.1683035692.git.michal.simek@amd.com Signed-off-by: Michal Simek Cc: Colin Ian King Cc: Jakub Kicinski Cc: Kirill Tkhai Cc: Konrad Dybcio Cc: Qais Yousef Cc: Michal Simek Signed-off-by: Andrew Morton --- .mailmap | 1 + MAINTAINERS | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/.mailmap b/.mailmap index adfed592f88b..d3eb862f71ab 100644 --- a/.mailmap +++ b/.mailmap @@ -328,6 +328,7 @@ Maxime Ripard Maxime Ripard Mayuresh Janorkar Michael Buesch +Michal Simek Michel Dänzer Michel Lespinasse Michel Lespinasse diff --git a/MAINTAINERS b/MAINTAINERS index 32772c383ab7..51f7682246be 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3036,7 +3036,7 @@ F: drivers/video/fbdev/wm8505fb* F: drivers/video/fbdev/wmt_ge_rops.* ARM/ZYNQ ARCHITECTURE -M: Michal Simek +M: Michal Simek L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported W: http://wiki.xilinx.com @@ -23084,7 +23084,7 @@ F: drivers/net/can/xilinx_can.c XILINX GPIO DRIVER M: Shubhrajyoti Datta R: Srinivas Neeli -R: Michal Simek +R: Michal Simek S: Maintained F: Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml F: Documentation/devicetree/bindings/gpio/gpio-zynq.yaml -- GitLab From 6152e53d9671b0ccc21c1bca842617b32ccfc5d8 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 28 Apr 2023 10:35:33 -0700 Subject: [PATCH 4428/5631] mm: change per-VMA lock statistics to be disabled by default Change CONFIG_PER_VMA_LOCK_STATS to be disabled by default, as most users don't need it. Add configuration help to clarify its usage. Link: https://lkml.kernel.org/r/20230428173533.18158-1-surenb@google.com Fixes: 52f238653e45 ("mm: introduce per-VMA lock statistics") Signed-off-by: Suren Baghdasaryan Suggested-by: Linus Torvalds Reviewed-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton --- mm/Kconfig.debug | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 6dae63b46368..a925415b4d10 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -274,6 +274,12 @@ config DEBUG_KMEMLEAK_AUTO_SCAN config PER_VMA_LOCK_STATS bool "Statistics for per-vma locks" depends on PER_VMA_LOCK - default y help - Statistics for per-vma locks. + Say Y here to enable success, retry and failure counters of page + faults handled under protection of per-vma locks. When enabled, the + counters are exposed in /proc/vmstat. This information is useful for + kernel developers to evaluate effectiveness of per-vma locks and to + identify pathological cases. Counting these events introduces a small + overhead in the page fault path. + + If in doubt, say N. -- GitLab From 690dccc4a0bf8b6b4eeb160882ec584d3d0bb642 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sun, 23 Apr 2023 07:38:27 -0500 Subject: [PATCH 4429/5631] Revert "clk: imx: composite-8m: Add support to determine_rate" This reverts commit 156e96ff2172518b6f83e97d8f11f677bc668e22. This patch was found to cause some division issues on the i.MX8MP which causes the video clocks to not properly divide when division was greate than 8. This causes video failures on disp1_pix and disp2_pix clocks. Until a better solution is found, we'll have to revert this. Signed-off-by: Adam Ford Link: https://lore.kernel.org/r/20230423123828.1346511-1-aford173@gmail.com Acked-by: Peng Fan Signed-off-by: Stephen Boyd --- drivers/clk/imx/clk-composite-8m.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index 6883a8199b6c..cbf0d7955a00 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -119,17 +119,10 @@ static int imx8m_clk_composite_divider_set_rate(struct clk_hw *hw, return ret; } -static int imx8m_clk_divider_determine_rate(struct clk_hw *hw, - struct clk_rate_request *req) -{ - return clk_divider_ops.determine_rate(hw, req); -} - static const struct clk_ops imx8m_clk_composite_divider_ops = { .recalc_rate = imx8m_clk_composite_divider_recalc_rate, .round_rate = imx8m_clk_composite_divider_round_rate, .set_rate = imx8m_clk_composite_divider_set_rate, - .determine_rate = imx8m_clk_divider_determine_rate, }; static u8 imx8m_clk_composite_mux_get_parent(struct clk_hw *hw) -- GitLab From 5c667d5a5a3ec16609229dddf25a46654186b52b Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 1 May 2023 14:34:47 -0700 Subject: [PATCH 4430/5631] clk: sp7021: Adjust width of _m in HWM_FIELD_PREP() When building with clang + W=1, there is a warning around an internal comparison check within the FIELD_PREP() macro, due to a 32-bit variable comparison against ~0ull: drivers/clk/clk-sp7021.c:316:8: error: result of comparison of constant 18446744073709551615 with expression of type 'typeof (_Generic((_m), ...' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare] r0 |= HWM_FIELD_PREP(MASK_SEL_FRA, clk->p[SEL_FRA]); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/clk/clk-sp7021.c:45:15: note: expanded from macro 'HWM_FIELD_PREP' (_m << 16) | FIELD_PREP(_m, value); \ ^~~~~~~~~~~~~~~~~~~~~ include/linux/bitfield.h:114:3: note: expanded from macro 'FIELD_PREP' __BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_PREP: "); \ ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/bitfield.h:71:53: note: expanded from macro '__BF_FIELD_CHECK' BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~ note: (skipping 1 expansions in backtrace; use -fmacro-backtrace-limit=0 to see all) include/linux/compiler_types.h:397:22: note: expanded from macro 'compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/compiler_types.h:385:23: note: expanded from macro '_compiletime_assert' __compiletime_assert(condition, msg, prefix, suffix) ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/compiler_types.h:377:9: note: expanded from macro '__compiletime_assert' if (!(condition)) \ ^~~~~~~~~ This is expected given the types of the input. Increase the size of the temporary variable in HWM_FIELD_PREP() to eliminate the warning, which follows the logic of commit cfd6fb45cfaf ("crypto: ccree - avoid out-of-range warnings from clang") for the same reasons. Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230501-sp7021-field_prep-warning-v1-1-5b36d71feefe@kernel.org Reported-by: kernel test robot Link: https://lore.kernel.org/202303221947.pXP2v4xJ-lkp@intel.com/ Reviewed-by: Nick Desaulniers Signed-off-by: Stephen Boyd --- drivers/clk/clk-sp7021.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/clk-sp7021.c b/drivers/clk/clk-sp7021.c index 8fec14120105..11d22043ddd7 100644 --- a/drivers/clk/clk-sp7021.c +++ b/drivers/clk/clk-sp7021.c @@ -41,7 +41,7 @@ enum { /* HIWORD_MASK FIELD_PREP */ #define HWM_FIELD_PREP(mask, value) \ ({ \ - u32 _m = mask; \ + u64 _m = mask; \ (_m << 16) | FIELD_PREP(_m, value); \ }) -- GitLab From 31c6ed4e89187beef8fe2f979c8881ca94839427 Mon Sep 17 00:00:00 2001 From: Hal Feng Date: Tue, 18 Apr 2023 20:37:56 +0800 Subject: [PATCH 4431/5631] clk: starfive: Fix RESET_STARFIVE_JH7110 can't be selected in a specified case When (ARCH_STARFIVE [=n] && COMPILE_TEST [=y] && RESET_CONTROLLER [=n]), RESET_STARFIVE_JH7110 can't be selected by CLK_STARFIVE_JH7110_SYS and CLK_STARFIVE_JH7110_AON. Add a condition `if RESET_CONTROLLER` to fix it. Also, delete redundant selected options of CLK_STARFIVE_JH7110_AON because these options are already selected by the dependency. Fixes: edab7204afe5 ("clk: starfive: Add StarFive JH7110 system clock driver") Fixes: b2ab3c94f41f ("clk: starfive: Add StarFive JH7110 always-on clock driver") Signed-off-by: Hal Feng Link: https://lore.kernel.org/r/20230418123756.62495-2-hal.feng@starfivetech.com Reviewed-by: Conor Dooley Signed-off-by: Stephen Boyd --- drivers/clk/starfive/Kconfig | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/clk/starfive/Kconfig b/drivers/clk/starfive/Kconfig index 71c1148ee5f6..5d2333106f13 100644 --- a/drivers/clk/starfive/Kconfig +++ b/drivers/clk/starfive/Kconfig @@ -26,7 +26,7 @@ config CLK_STARFIVE_JH7110_SYS depends on ARCH_STARFIVE || COMPILE_TEST select AUXILIARY_BUS select CLK_STARFIVE_JH71X0 - select RESET_STARFIVE_JH7110 + select RESET_STARFIVE_JH7110 if RESET_CONTROLLER default ARCH_STARFIVE help Say yes here to support the system clock controller on the @@ -35,9 +35,6 @@ config CLK_STARFIVE_JH7110_SYS config CLK_STARFIVE_JH7110_AON tristate "StarFive JH7110 always-on clock support" depends on CLK_STARFIVE_JH7110_SYS - select AUXILIARY_BUS - select CLK_STARFIVE_JH71X0 - select RESET_STARFIVE_JH7110 default m if ARCH_STARFIVE help Say yes here to support the always-on clock controller on the -- GitLab From 9e7c73c0b9f49bc73818e08e6282a32b94d96168 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 2 Mar 2023 12:28:23 -0800 Subject: [PATCH 4432/5631] kernel: pid_namespace: simplify sysctls with register_sysctl() register_sysctl_paths() is only required if your child (directories) have entries and pid_namespace does not. So use register_sysctl_init() instead where we don't care about the return value and use register_sysctl() where we do. Signed-off-by: Luis Chamberlain Acked-by: Jeff Xu Link: https://lore.kernel.org/r/20230302202826.776286-9-mcgrof@kernel.org --- kernel/pid_namespace.c | 3 +-- kernel/pid_sysctl.h | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 46e0d5a3f91f..b43eee07b00c 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -314,7 +314,6 @@ static struct ctl_table pid_ns_ctl_table[] = { }, { } }; -static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; #endif /* CONFIG_CHECKPOINT_RESTORE */ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) @@ -473,7 +472,7 @@ static __init int pid_namespaces_init(void) pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC | SLAB_ACCOUNT); #ifdef CONFIG_CHECKPOINT_RESTORE - register_sysctl_paths(kern_path, pid_ns_ctl_table); + register_sysctl_init("kernel", pid_ns_ctl_table); #endif register_pid_ns_sysctl_table_vm(); diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index e22d072e1e24..d67a4d45bb42 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -46,10 +46,9 @@ static struct ctl_table pid_ns_ctl_table_vm[] = { }, { } }; -static struct ctl_path vm_path[] = { { .procname = "vm", }, { } }; static inline void register_pid_ns_sysctl_table_vm(void) { - register_sysctl_paths(vm_path, pid_ns_ctl_table_vm); + register_sysctl("vm", pid_ns_ctl_table_vm); } #else static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {} -- GitLab From 0199849acd07d07e2a8e42757653ca8b14a122f5 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 2 May 2023 18:30:04 -0700 Subject: [PATCH 4433/5631] sysctl: remove register_sysctl_paths() The deprecation for register_sysctl_paths() is over. We can rejoice as we nuke register_sysctl_paths(). The routine register_sysctl_table() was the only user left of register_sysctl_paths(), so we can now just open code and move the implementation over to what used to be to __register_sysctl_paths(). The old dynamic struct ctl_table_set *set is now the point to sysctl_table_root.default_set. The old dynamic const struct ctl_path *path was being used in the routine register_sysctl_paths() with a static: static const struct ctl_path null_path[] = { {} }; Since this is a null path we can now just simplfy the old routine and remove its use as its always empty. This saves us a total of 230 bytes. $ ./scripts/bloat-o-meter vmlinux.old vmlinux add/remove: 2/7 grow/shrink: 1/1 up/down: 1015/-1245 (-230) Function old new delta register_leaf_sysctl_tables.constprop - 524 +524 register_sysctl_table 22 497 +475 __pfx_register_leaf_sysctl_tables.constprop - 16 +16 null_path 8 - -8 __pfx_register_sysctl_paths 16 - -16 __pfx_register_leaf_sysctl_tables 16 - -16 __pfx___register_sysctl_paths 16 - -16 __register_sysctl_base 29 12 -17 register_sysctl_paths 18 - -18 register_leaf_sysctl_tables 534 - -534 __register_sysctl_paths 620 - -620 Total: Before=21259666, After=21259436, chg -0.00% Signed-off-by: Luis Chamberlain --- fs/proc/proc_sysctl.c | 55 +++------------------------------------ include/linux/sysctl.h | 12 --------- scripts/check-sysctl-docs | 16 ------------ 3 files changed, 4 insertions(+), 79 deletions(-) diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 81dbb175017e..8038833ff5b0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1575,25 +1575,18 @@ static int register_leaf_sysctl_tables(const char *path, char *pos, } /** - * __register_sysctl_paths - register a sysctl table hierarchy - * @set: Sysctl tree to register on - * @path: The path to the directory the sysctl table is in. + * register_sysctl_table - register a sysctl table hierarchy * @table: the top-level table structure * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. * We are slowly deprecating this call so avoid its use. - * - * See __register_sysctl_table for more details. */ -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_set *set, - const struct ctl_path *path, struct ctl_table *table) +struct ctl_table_header *register_sysctl_table(struct ctl_table *table) { struct ctl_table *ctl_table_arg = table; int nr_subheaders = count_subheaders(table); struct ctl_table_header *header = NULL, **subheaders, **subheader; - const struct ctl_path *component; char *new_path, *pos; pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL); @@ -1601,11 +1594,6 @@ struct ctl_table_header *__register_sysctl_paths( return NULL; pos[0] = '\0'; - for (component = path; component->procname; component++) { - pos = append_path(new_path, pos, component->procname); - if (!pos) - goto out; - } while (table->procname && table->child && !table[1].procname) { pos = append_path(new_path, pos, table->procname); if (!pos) @@ -1613,7 +1601,7 @@ struct ctl_table_header *__register_sysctl_paths( table = table->child; } if (nr_subheaders == 1) { - header = __register_sysctl_table(set, new_path, table); + header = __register_sysctl_table(&sysctl_table_root.default_set, new_path, table); if (header) header->ctl_table_arg = ctl_table_arg; } else { @@ -1627,7 +1615,7 @@ struct ctl_table_header *__register_sysctl_paths( header->ctl_table_arg = ctl_table_arg; if (register_leaf_sysctl_tables(new_path, pos, &subheader, - set, table)) + &sysctl_table_root.default_set, table)) goto err_register_leaves; } @@ -1646,41 +1634,6 @@ struct ctl_table_header *__register_sysctl_paths( header = NULL; goto out; } - -/** - * register_sysctl_paths - register a sysctl table hierarchy - * @path: The path to the directory the sysctl table is in. - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * We are slowly deprecating this caller so avoid future uses of it. - * - * See __register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table) -{ - return __register_sysctl_paths(&sysctl_table_root.default_set, - path, table); -} -EXPORT_SYMBOL(register_sysctl_paths); - -/** - * register_sysctl_table - register a sysctl table hierarchy - * @table: the top-level table structure - * - * Register a sysctl table hierarchy. @table should be a filled in ctl_table - * array. A completely 0 filled entry terminates the table. - * - * See register_sysctl_paths for more details. - */ -struct ctl_table_header *register_sysctl_table(struct ctl_table *table) -{ - static const struct ctl_path null_path[] = { {} }; - - return register_sysctl_paths(null_path, table); -} EXPORT_SYMBOL(register_sysctl_table); int __register_sysctl_base(struct ctl_table *base_table) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 780690dc08cd..3d08277959af 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -221,14 +221,8 @@ extern void retire_sysctl_set(struct ctl_table_set *set); struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, struct ctl_table *table); -struct ctl_table_header *__register_sysctl_paths( - struct ctl_table_set *set, - const struct ctl_path *path, struct ctl_table *table); struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table); struct ctl_table_header *register_sysctl_table(struct ctl_table * table); -struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, - struct ctl_table *table); - void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init_bases(void); @@ -277,12 +271,6 @@ static inline struct ctl_table_header *register_sysctl_mount_point(const char *p return NULL; } -static inline struct ctl_table_header *register_sysctl_paths( - const struct ctl_path *path, struct ctl_table *table) -{ - return NULL; -} - static inline struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table) { return NULL; diff --git a/scripts/check-sysctl-docs b/scripts/check-sysctl-docs index 8bcb9e26c7bc..edc9a629d79e 100755 --- a/scripts/check-sysctl-docs +++ b/scripts/check-sysctl-docs @@ -156,22 +156,6 @@ curtable && /\.procname[\t ]*=[\t ]*".+"/ { } } -/register_sysctl_paths\(.*\)/ { - match($0, /register_sysctl_paths\(([^)]+), ([^)]+)\)/, tables) - if (debug) print "Attaching table " tables[2] " to path " tables[1] - if (paths[tables[1]] == table) { - for (entry in entries[tables[2]]) { - printentry(entry) - } - } - split(paths[tables[1]], components, "/") - if (length(components) > 1 && components[1] == table) { - # Count the first subdirectory as seen - seen[components[2]]++ - } -} - - END { for (entry in documented) { if (!seen[entry]) { -- GitLab From c6d96df9fa2c1d19525239d4262889cce594ce6c Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 26 Apr 2023 19:21:53 +0200 Subject: [PATCH 4434/5631] net: ethernet: mtk_eth_soc: drop generic vlan rx offload, only use DSA untagging MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Through testing I found out that hardware vlan rx offload support seems to have some hardware issues. At least when using multiple MACs and when receiving tagged packets on the secondary MAC, the hardware can sometimes start to emit wrong tags on the first MAC as well. In order to avoid such issues, drop the feature configuration and use the offload feature only for DSA hardware untagging on MT7621/MT7622 devices where this feature works properly. Fixes: 08666cbb7dd5 ("net: ethernet: mtk_eth_soc: add support for configuring vlan rx offload") Tested-by: Frank Wunderlich Signed-off-by: Felix Fietkau Signed-off-by: Frank Wunderlich Tested-by: Arınç ÜNAL Acked-by: Arınç ÜNAL Link: https://lore.kernel.org/r/20230426172153.8352-1-linux@fw-web.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 106 ++++++++------------ drivers/net/ethernet/mediatek/mtk_eth_soc.h | 1 - 2 files changed, 40 insertions(+), 67 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 9e948d091a69..a75fd072082c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1918,9 +1918,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, while (done < budget) { unsigned int pktlen, *rxdcsum; - bool has_hwaccel_tag = false; struct net_device *netdev; - u16 vlan_proto, vlan_tci; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -2055,31 +2053,16 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, skb_checksum_none_assert(skb); skb->protocol = eth_type_trans(skb, netdev); - if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { - if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - if (trxd.rxd3 & RX_DMA_VTAG_V2) { - vlan_proto = RX_DMA_VPID(trxd.rxd4); - vlan_tci = RX_DMA_VID(trxd.rxd4); - has_hwaccel_tag = true; - } - } else if (trxd.rxd2 & RX_DMA_VTAG) { - vlan_proto = RX_DMA_VPID(trxd.rxd3); - vlan_tci = RX_DMA_VID(trxd.rxd3); - has_hwaccel_tag = true; - } - } - /* When using VLAN untagging in combination with DSA, the * hardware treats the MTK special tag as a VLAN and untags it. */ - if (has_hwaccel_tag && netdev_uses_dsa(netdev)) { - unsigned int port = vlan_proto & GENMASK(2, 0); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2) && + (trxd.rxd2 & RX_DMA_VTAG) && netdev_uses_dsa(netdev)) { + unsigned int port = RX_DMA_VPID(trxd.rxd3) & GENMASK(2, 0); if (port < ARRAY_SIZE(eth->dsa_meta) && eth->dsa_meta[port]) skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - } else if (has_hwaccel_tag) { - __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci); } if (reason == MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) @@ -2907,29 +2890,11 @@ static netdev_features_t mtk_fix_features(struct net_device *dev, static int mtk_set_features(struct net_device *dev, netdev_features_t features) { - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; netdev_features_t diff = dev->features ^ features; - int i; if ((diff & NETIF_F_LRO) && !(features & NETIF_F_LRO)) mtk_hwlro_netdev_disable(dev); - /* Set RX VLAN offloading */ - if (!(diff & NETIF_F_HW_VLAN_CTAG_RX)) - return 0; - - mtk_w32(eth, !!(features & NETIF_F_HW_VLAN_CTAG_RX), - MTK_CDMP_EG_CTRL); - - /* sync features with other MAC */ - for (i = 0; i < MTK_MAC_COUNT; i++) { - if (!eth->netdev[i] || eth->netdev[i] == dev) - continue; - eth->netdev[i]->features &= ~NETIF_F_HW_VLAN_CTAG_RX; - eth->netdev[i]->features |= features & NETIF_F_HW_VLAN_CTAG_RX; - } - return 0; } @@ -3247,30 +3212,6 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if (mtk_uses_dsa(dev) && !eth->prog) { - for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { - struct metadata_dst *md_dst = eth->dsa_meta[i]; - - if (md_dst) - continue; - - md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, - GFP_KERNEL); - if (!md_dst) - return -ENOMEM; - - md_dst->u.port_info.port_id = i; - eth->dsa_meta[i] = md_dst; - } - } else { - /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA. - */ - u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); - val &= ~MTK_CDMP_STAG_EN; - mtk_w32(eth, val, MTK_CDMP_IG_CTRL); - } - err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0); if (err) { netdev_err(dev, "%s: could not attach PHY: %d\n", __func__, @@ -3309,6 +3250,40 @@ static int mtk_open(struct net_device *dev) phylink_start(mac->phylink); netif_tx_start_all_queues(dev); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + return 0; + + if (mtk_uses_dsa(dev) && !eth->prog) { + for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { + struct metadata_dst *md_dst = eth->dsa_meta[i]; + + if (md_dst) + continue; + + md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, + GFP_KERNEL); + if (!md_dst) + return -ENOMEM; + + md_dst->u.port_info.port_id = i; + eth->dsa_meta[i] = md_dst; + } + } else { + /* Hardware special tag parsing needs to be disabled if at least + * one MAC does not use DSA. + */ + u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); + + val &= ~MTK_CDMP_STAG_EN; + mtk_w32(eth, val, MTK_CDMP_IG_CTRL); + + val = mtk_r32(eth, MTK_CDMQ_IG_CTRL); + val &= ~MTK_CDMQ_STAG_EN; + mtk_w32(eth, val, MTK_CDMQ_IG_CTRL); + + mtk_w32(eth, 0, MTK_CDMP_EG_CTRL); + } + return 0; } @@ -3793,10 +3768,9 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) if (!MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { val = mtk_r32(eth, MTK_CDMP_IG_CTRL); mtk_w32(eth, val | MTK_CDMP_STAG_EN, MTK_CDMP_IG_CTRL); - } - /* Enable RX VLan Offloading */ - mtk_w32(eth, 1, MTK_CDMP_EG_CTRL); + mtk_w32(eth, 1, MTK_CDMP_EG_CTRL); + } /* set interrupt delays based on current Net DIM sample */ mtk_dim_rx(ð->rx_dim.work); @@ -4453,7 +4427,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->hw_features |= NETIF_F_LRO; eth->netdev[id]->vlan_features = eth->soc->hw_features & - ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); + ~NETIF_F_HW_VLAN_CTAG_TX; eth->netdev[id]->features |= eth->soc->hw_features; eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index cdcf8534283e..707445f6bcb1 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -48,7 +48,6 @@ #define MTK_HW_FEATURES (NETIF_F_IP_CSUM | \ NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_TX | \ - NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_SG | NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_IPV6_CSUM |\ -- GitLab From 0b891c83d8c54cb70e186456c2191adb5fd98c56 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 29 Apr 2023 22:36:04 +0200 Subject: [PATCH 4435/5631] module: include internal.h in module/dups.c Two newly introduced functions are declared in a header that is not included before the definition, causing a warning with sparse or 'make W=1': kernel/module/dups.c:118:6: error: no previous prototype for 'kmod_dup_request_exists_wait' [-Werror=missing-prototypes] 118 | bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ kernel/module/dups.c:220:6: error: no previous prototype for 'kmod_dup_request_announce' [-Werror=missing-prototypes] 220 | void kmod_dup_request_announce(char *module_name, int ret) | ^~~~~~~~~~~~~~~~~~~~~~~~~ Add an explicit include to ensure the prototypes match. Fixes: 8660484ed1cf ("module: add debugging auto-load duplicate module support") Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304141440.DYO4NAzp-lkp@intel.com/ Signed-off-by: Arnd Bergmann Signed-off-by: Luis Chamberlain --- kernel/module/dups.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/kernel/module/dups.c b/kernel/module/dups.c index aa8e1361fdb5..f3d7ea1e96d8 100644 --- a/kernel/module/dups.c +++ b/kernel/module/dups.c @@ -32,6 +32,8 @@ #include #include +#include "internal.h" + #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." static bool enable_dups_trace = IS_ENABLED(CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS_TRACE); -- GitLab From 1816f4a17f54a01afa2f06d6571c39890b97d282 Mon Sep 17 00:00:00 2001 From: John Harrison Date: Fri, 21 Apr 2023 15:47:42 -0700 Subject: [PATCH 4436/5631] drm/i915/guc: Actually return an error if GuC version range check fails Dan Carpenter pointed out that 'err' was not being set in the case where the GuC firmware version range check fails. Fix that. Note that while this is a bug fix for a previous patch (see Fixes tag below). It is an exceedingly low risk bug. The range check is asserting that the GuC firmware version is within spec. So it should not be possible to ever have a firmware file that fails this check. If larger version numbers are required in the future, that would be a backwards breaking spec change and thus require a major version bump, in which case an old i915 driver would not load that new version anyway. Fixes: 9bbba0667f37 ("drm/i915/guc: Use GuC submission API version number") Reported-by: Dan Carpenter Signed-off-by: John Harrison Cc: John Harrison Cc: Daniele Ceraolo Spurio Cc: Alan Previn Cc: Umesh Nerlige Ramappa Cc: Rodrigo Vivi Cc: Matthew Brost Cc: Andi Shyti Cc: Matthew Auld Cc: Tvrtko Ursulin Cc: Lucas De Marchi Cc: Jani Nikula Reviewed-by: Andi Shyti Link: https://patchwork.freedesktop.org/patch/msgid/20230421224742.2357198-1-John.C.Harrison@Intel.com (cherry picked from commit 80ab31799002166ac7c660bacfbff4f85bc29107) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 24765c30a0e1..c36e68e23a14 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -635,9 +635,10 @@ static bool is_ver_8bit(struct intel_uc_fw_ver *ver) return ver->major < 0xFF && ver->minor < 0xFF && ver->patch < 0xFF; } -static bool guc_check_version_range(struct intel_uc_fw *uc_fw) +static int guc_check_version_range(struct intel_uc_fw *uc_fw) { struct intel_guc *guc = container_of(uc_fw, struct intel_guc, fw); + struct intel_gt *gt = __uc_fw_to_gt(uc_fw); /* * GuC version number components are defined as being 8-bits. @@ -646,24 +647,24 @@ static bool guc_check_version_range(struct intel_uc_fw *uc_fw) */ if (!is_ver_8bit(&uc_fw->file_selected.ver)) { - gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid file version: 0x%02X:%02X:%02X\n", + gt_warn(gt, "%s firmware: invalid file version: 0x%02X:%02X:%02X\n", intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.ver.major, uc_fw->file_selected.ver.minor, uc_fw->file_selected.ver.patch); - return false; + return -EINVAL; } if (!is_ver_8bit(&guc->submission_version)) { - gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n", + gt_warn(gt, "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n", intel_uc_fw_type_repr(uc_fw->type), guc->submission_version.major, guc->submission_version.minor, guc->submission_version.patch); - return false; + return -EINVAL; } - return true; + return i915_inject_probe_error(gt->i915, -EINVAL); } static int check_fw_header(struct intel_gt *gt, @@ -772,8 +773,11 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (err) goto fail; - if (uc_fw->type == INTEL_UC_FW_TYPE_GUC && !guc_check_version_range(uc_fw)) - goto fail; + if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) { + err = guc_check_version_range(uc_fw); + if (err) + goto fail; + } if (uc_fw->file_wanted.ver.major && uc_fw->file_selected.ver.major) { /* Check the file's major version was as it claimed */ -- GitLab From 6ece90e3665a9b7fb2637fcca26cebd42991580b Mon Sep 17 00:00:00 2001 From: Radhakrishna Sripada Date: Thu, 20 Apr 2023 15:12:47 -0700 Subject: [PATCH 4437/5631] drm/i915/mtl: Add the missing CPU transcoder mask in intel_device_info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CPU transcoder mask is used to iterate over the available CPU transcoders in the macro for_each_cpu_transcoder(). The macro is broken on MTL and got highlighted when audio state was being tracked for each transcoder added in [1]. Add the missing CPU transcoder mask which is similar to ADL-P mask but without DSI transcoders. [1]: https://patchwork.freedesktop.org/patch/523723/ Fixes: 7835303982d1 ("drm/i915/mtl: Add MeteorLake PCI IDs") Cc: Ville Syrjälä Signed-off-by: Radhakrishna Sripada Acked-by: Haridhar Kalvala Reviewed-by: Gustavo Sousa Link: https://patchwork.freedesktop.org/patch/msgid/20230420221248.2511314-1-radhakrishna.sripada@intel.com (cherry picked from commit bddc18913bd44adae5c828fd514d570f43ba1576) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/i915_pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index cddb6e197972..2a012da8ccfa 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1134,6 +1134,8 @@ static const struct intel_gt_definition xelpmp_extra_gt[] = { static const struct intel_device_info mtl_info = { XE_HP_FEATURES, XE_LPDP_FEATURES, + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + BIT(TRANSCODER_C) | BIT(TRANSCODER_D), /* * Real graphics IP version will be obtained from hardware GMD_ID * register. Value provided here is just for sanity checking. -- GitLab From c8c2969bfcba5fcba3a5b078315c1b586d927d9f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 25 Apr 2023 21:44:41 +0200 Subject: [PATCH 4438/5631] drm/i915/dsi: Use unconditional msleep() instead of intel_dsi_msleep() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The intel_dsi_msleep() helper skips sleeping if the MIPI-sequences have a version of 3 or newer and the panel is in vid-mode. This is based on the big comment around line 730 which starts with "Panel enable/disable sequences from the VBT spec.", where the "v3 video mode seq" column does not have any wait t# entries. Checking the Windows driver shows that it does always honor the VBT delays independent of the version of the VBT sequences. Commit 6fdb335f1c9c ("drm/i915/dsi: Use unconditional msleep for the panel_on_delay when there is no reset-deassert MIPI-sequence") switched to a direct msleep() instead of intel_dsi_msleep() when there is no MIPI_SEQ_DEASSERT_RESET sequence, to fix the panel on an Acer Aspire Switch 10 E SW3-016 not turning on. And now testing on a Nextbook Ares 8A shows that panel_on_delay must always be honored otherwise the panel will not turn on. Instead of only always using regular msleep() for panel_on_delay do as Windows does and always use regular msleep() everywhere were intel_dsi_msleep() is used and drop the intel_dsi_msleep() helper. Changes in v2: - Replace all intel_dsi_msleep() calls instead of just the intel_dsi_msleep(panel_on_delay) call Cc: stable@vger.kernel.org Fixes: 6fdb335f1c9c ("drm/i915/dsi: Use unconditional msleep for the panel_on_delay when there is no reset-deassert MIPI-sequence") Signed-off-by: Hans de Goede Signed-off-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20230425194441.68086-1-hdegoede@redhat.com (cherry picked from commit fa83c12132f71302f7d4b02758dc0d46048d3f5f) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/icl_dsi.c | 2 +- drivers/gpu/drm/i915/display/intel_dsi_vbt.c | 11 ---------- drivers/gpu/drm/i915/display/intel_dsi_vbt.h | 1 - drivers/gpu/drm/i915/display/vlv_dsi.c | 22 +++++--------------- 4 files changed, 6 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index ad78148e0788..c9aeba0ecf91 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1140,7 +1140,7 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) /* panel power on related mipi dsi vbt sequences */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); + msleep(intel_dsi->panel_on_delay); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 695b0d69a4cb..c7935ea498c4 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -763,17 +763,6 @@ void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 0); } -void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec) -{ - struct intel_connector *connector = intel_dsi->attached_connector; - - /* For v3 VBTs in vid-mode the delays are part of the VBT sequences */ - if (is_vid_mode(intel_dsi) && connector->panel.vbt.dsi.seq_version >= 3) - return; - - msleep(msec); -} - void intel_dsi_log_params(struct intel_dsi *intel_dsi) { struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h index dc642c1fe7ef..468d873fab1a 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h @@ -16,7 +16,6 @@ void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on); void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi); void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, enum mipi_seq seq_id); -void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec); void intel_dsi_log_params(struct intel_dsi *intel_dsi); #endif /* __INTEL_DSI_VBT_H__ */ diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 028965ab442d..61d008d4e5f1 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -737,7 +737,6 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, { struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); - struct intel_connector *connector = to_intel_connector(conn_state->connector); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; enum port port; @@ -779,21 +778,10 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, if (!IS_GEMINILAKE(dev_priv)) intel_dsi_prepare(encoder, pipe_config); + /* Give the panel time to power-on and then deassert its reset */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON); - - /* - * Give the panel time to power-on and then deassert its reset. - * Depending on the VBT MIPI sequences version the deassert-seq - * may contain the necessary delay, intel_dsi_msleep() will skip - * the delay in that case. If there is no deassert-seq, then an - * unconditional msleep is used to give the panel time to power-on. - */ - if (connector->panel.vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) { - intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); - intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); - } else { - msleep(intel_dsi->panel_on_delay); - } + msleep(intel_dsi->panel_on_delay); + intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); if (IS_GEMINILAKE(dev_priv)) { glk_cold_boot = glk_dsi_enable_io(encoder); @@ -827,7 +815,7 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, msleep(20); /* XXX */ for_each_dsi_port(port, intel_dsi->ports) dpi_send_cmd(intel_dsi, TURN_ON, false, port); - intel_dsi_msleep(intel_dsi, 100); + msleep(100); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); @@ -949,7 +937,7 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state, /* Assert reset */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay); + msleep(intel_dsi->panel_off_delay); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF); intel_dsi->panel_power_off_time = ktime_get_boottime(); -- GitLab From 1604f51b401bfd881ab5c6401eaedac97f2166ca Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Mon, 1 May 2023 14:16:34 +0400 Subject: [PATCH 4439/5631] ALSA: docs: Extend module parameters description Common ALSA module parameters look a little bit confusing because of the description lacking, and it took me a while to understand the purpose of their existence. To figure it out I asked the question about them to the "alsa-devel" mailing list, and Takashi Iwai answered me with the text I appended to the ALSA documentation in this patch. These common module parameters aren't used a lot nowadays, but as I understand they are important for providing compatibility with some existing user-space apps. So in my opinion it is a good idea to document why we need them. Signed-off-by: Ivan Orlov Link: https://lore.kernel.org/r/20230501101634.476297-1-ivan.orlov0322@gmail.com Signed-off-by: Takashi Iwai --- Documentation/sound/alsa-configuration.rst | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst index af71c68f1e4e..829c672d9fe6 100644 --- a/Documentation/sound/alsa-configuration.rst +++ b/Documentation/sound/alsa-configuration.rst @@ -133,6 +133,19 @@ enable enable card; Default: enabled, for PCI and ISA PnP cards +These options are used for either specifying the order of instances or +controlling enabling and disabling of each one of the devices if there +are multiple devices bound with the same driver. For example, there are +many machines which have two HD-audio controllers (one for HDMI/DP +audio and another for onboard analog). In most cases, the second one is +in primary usage, and people would like to assign it as the first +appearing card. They can do it by specifying "index=1,0" module +parameter, which will swap the assignment slots. + +Today, with the sound backend like PulseAudio and PipeWire which +supports dynamic configuration, it's of little use, but that was a +help for static configuration in the past. + Module snd-adlib ---------------- -- GitLab From e4212ed0ba58264fbe7706c5493b9600339f60ae Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Wed, 3 May 2023 10:54:16 +0700 Subject: [PATCH 4440/5631] ALSA: docs: Fix code block indentation in ALSA driver example Sphinx reports htmldocs warnings: Documentation/sound/kernel-api/writing-an-alsa-driver.rst:3997: WARNING: Literal block expected; none found. Documentation/sound/kernel-api/writing-an-alsa-driver.rst:4004: WARNING: Literal block expected; none found. Documentation/sound/kernel-api/writing-an-alsa-driver.rst:4009: WARNING: Unexpected indentation. Documentation/sound/kernel-api/writing-an-alsa-driver.rst:4035: WARNING: Literal block expected; none found. These are due to indentation of example driver snippets which is outside the code block scope. Fix these by indenting code blocks in question to the scope. Fixes: 4d421eebe1465d ("ALSA: docs: writing-an-alsa-driver.rst: polishing") Reported-by: kernel test robot Closes: https://lore.kernel.org/linux-doc/202305021822.4U6XOvGf-lkp@intel.com/ Signed-off-by: Bagas Sanjaya Link: https://lore.kernel.org/r/20230503035416.62722-1-bagasdotme@gmail.com Signed-off-by: Takashi Iwai --- .../kernel-api/writing-an-alsa-driver.rst | 22 +++++++++---------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst index c0f97b5e4249..4335c98b3d82 100644 --- a/Documentation/sound/kernel-api/writing-an-alsa-driver.rst +++ b/Documentation/sound/kernel-api/writing-an-alsa-driver.rst @@ -3994,21 +3994,21 @@ Driver with A Single Source File Suppose you have a file xyz.c. Add the following two lines:: - snd-xyz-objs := xyz.o - obj-$(CONFIG_SND_XYZ) += snd-xyz.o + snd-xyz-objs := xyz.o + obj-$(CONFIG_SND_XYZ) += snd-xyz.o 2. Create the Kconfig entry Add the new entry of Kconfig for your xyz driver:: - config SND_XYZ - tristate "Foobar XYZ" - depends on SND - select SND_PCM - help - Say Y here to include support for Foobar XYZ soundcard. - To compile this driver as a module, choose M here: - the module will be called snd-xyz. + config SND_XYZ + tristate "Foobar XYZ" + depends on SND + select SND_PCM + help + Say Y here to include support for Foobar XYZ soundcard. + To compile this driver as a module, choose M here: + the module will be called snd-xyz. The line ``select SND_PCM`` specifies that the driver xyz supports PCM. In addition to SND_PCM, the following components are supported for @@ -4032,7 +4032,7 @@ located in the new subdirectory, sound/pci/xyz. 1. Add a new directory (``sound/pci/xyz``) in ``sound/pci/Makefile`` as below:: - obj-$(CONFIG_SND) += sound/pci/xyz/ + obj-$(CONFIG_SND) += sound/pci/xyz/ 2. Under the directory ``sound/pci/xyz``, create a Makefile:: -- GitLab From 8509f62b0b07ae8d6dec5aa9613ab1b250ff632f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 25 Apr 2023 16:50:32 +0200 Subject: [PATCH 4441/5631] netfilter: nf_tables: hit ENOENT on unexisting chain/flowtable update with missing attributes If user does not specify hook number and priority, then assume this is a chain/flowtable update. Therefore, report ENOENT which provides a better hint than EINVAL. Set on extended netlink error report to refer to the chain name. Fixes: 5b6743fb2c2a ("netfilter: nf_tables: skip flowtable hooknum and priority on device updates") Fixes: 5efe72698a97 ("netfilter: nf_tables: support for adding new devices to an existing netdev chain") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 09542951656c..8b6c61a2196c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2075,8 +2075,10 @@ static int nft_chain_parse_hook(struct net *net, if (!basechain) { if (!ha[NFTA_HOOK_HOOKNUM] || - !ha[NFTA_HOOK_PRIORITY]) - return -EINVAL; + !ha[NFTA_HOOK_PRIORITY]) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); + return -ENOENT; + } hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); @@ -7693,7 +7695,7 @@ static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX }; static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, - const struct nlattr *attr, + const struct nlattr * const nla[], struct nft_flowtable_hook *flowtable_hook, struct nft_flowtable *flowtable, struct netlink_ext_ack *extack, bool add) @@ -7705,15 +7707,18 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, INIT_LIST_HEAD(&flowtable_hook->list); - err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr, + err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, + nla[NFTA_FLOWTABLE_HOOK], nft_flowtable_hook_policy, NULL); if (err < 0) return err; if (add) { if (!tb[NFTA_FLOWTABLE_HOOK_NUM] || - !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) - return -EINVAL; + !tb[NFTA_FLOWTABLE_HOOK_PRIORITY]) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); + return -ENOENT; + } hooknum = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_NUM])); if (hooknum != NF_NETDEV_INGRESS) @@ -7898,8 +7903,8 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, u32 flags; int err; - err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, extack, false); + err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, + extack, false); if (err < 0) return err; @@ -8044,8 +8049,8 @@ static int nf_tables_newflowtable(struct sk_buff *skb, if (err < 0) goto err3; - err = nft_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, extack, true); + err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, + extack, true); if (err < 0) goto err4; @@ -8107,8 +8112,8 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, struct nft_trans *trans; int err; - err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], - &flowtable_hook, flowtable, extack, false); + err = nft_flowtable_parse_hook(ctx, nla, &flowtable_hook, flowtable, + extack, false); if (err < 0) return err; -- GitLab From de4773f0235acf74554f6a64ea60adc0d7b01895 Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Tue, 25 Apr 2023 22:11:39 +0100 Subject: [PATCH 4442/5631] selftests: netfilter: fix libmnl pkg-config usage 1. Don't hard-code pkg-config 2. Remove distro-specific default for CFLAGS 3. Use pkg-config for LDLIBS Fixes: a50a88f026fb ("selftests: netfilter: fix a build error on openSUSE") Suggested-by: Jan Engelhardt Signed-off-by: Jeremy Sowden Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 4504ee07be08..3686bfa6c58d 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -8,8 +8,11 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ conntrack_vrf.sh nft_synproxy.sh rpath.sh -CFLAGS += $(shell pkg-config --cflags libmnl 2>/dev/null || echo "-I/usr/include/libmnl") -LDLIBS = -lmnl +HOSTPKG_CONFIG := pkg-config + +CFLAGS += $(shell $(HOSTPKG_CONFIG) --cflags libmnl 2>/dev/null) +LDLIBS += $(shell $(HOSTPKG_CONFIG) --libs libmnl 2>/dev/null || echo -lmnl) + TEST_GEN_FILES = nf-queue connect_close include ../lib.mk -- GitLab From c1592a89942e9678f7d9c8030efa777c0d57edab Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 2 May 2023 10:25:24 +0200 Subject: [PATCH 4443/5631] netfilter: nf_tables: deactivate anonymous set from preparation phase Toggle deleted anonymous sets as inactive in the next generation, so users cannot perform any update on it. Clear the generation bitmask in case the transaction is aborted. The following KASAN splat shows a set element deletion for a bound anonymous set that has been already removed in the same transaction. [ 64.921510] ================================================================== [ 64.923123] BUG: KASAN: wild-memory-access in nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.924745] Write of size 8 at addr dead000000000122 by task test/890 [ 64.927903] CPU: 3 PID: 890 Comm: test Not tainted 6.3.0+ #253 [ 64.931120] Call Trace: [ 64.932699] [ 64.934292] dump_stack_lvl+0x33/0x50 [ 64.935908] ? nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.937551] kasan_report+0xda/0x120 [ 64.939186] ? nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.940814] nf_tables_commit+0xa24/0x1490 [nf_tables] [ 64.942452] ? __kasan_slab_alloc+0x2d/0x60 [ 64.944070] ? nf_tables_setelem_notify+0x190/0x190 [nf_tables] [ 64.945710] ? kasan_set_track+0x21/0x30 [ 64.947323] nfnetlink_rcv_batch+0x709/0xd90 [nfnetlink] [ 64.948898] ? nfnetlink_rcv_msg+0x480/0x480 [nfnetlink] Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 + net/netfilter/nf_tables_api.c | 12 ++++++++++++ net/netfilter/nft_dynset.c | 2 +- net/netfilter/nft_lookup.c | 2 +- net/netfilter/nft_objref.c | 2 +- 5 files changed, 16 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 3ed21d2d5659..2e24ea1d744c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -619,6 +619,7 @@ struct nft_set_binding { }; enum nft_trans_phase; +void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set); void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 8b6c61a2196c..59fb8320ab4d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5127,12 +5127,24 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } } +void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) +{ + if (nft_set_is_anonymous(set)) + nft_clear(ctx->net, set); + + set->use++; +} +EXPORT_SYMBOL_GPL(nf_tables_activate_set); + void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { switch (phase) { case NFT_TRANS_PREPARE: + if (nft_set_is_anonymous(set)) + nft_deactivate_next(ctx->net, set); + set->use--; return; case NFT_TRANS_ABORT: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 274579b1696e..bd19c7aec92e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -342,7 +342,7 @@ static void nft_dynset_activate(const struct nft_ctx *ctx, { struct nft_dynset *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_dynset_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index cecf8ab90e58..03ef4fdaa460 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -167,7 +167,7 @@ static void nft_lookup_activate(const struct nft_ctx *ctx, { struct nft_lookup *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_lookup_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index cb37169608ba..a48dd5b5d45b 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -185,7 +185,7 @@ static void nft_objref_map_activate(const struct nft_ctx *ctx, { struct nft_objref_map *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, -- GitLab From 048486f81d01db4d100af021ee2ea211d19732a0 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Wed, 3 May 2023 12:39:34 +0530 Subject: [PATCH 4444/5631] octeontx2-af: Secure APR table update with the lock APR table contains the lmtst base address of PF/VFs. These entries are updated by the PF/VF during the device probe. The lmtst address is fetched from HW using "TXN_REQ" and "ADDR_RSP_STS" registers. The lock tries to protect these registers from getting overwritten when multiple PFs invokes rvu_get_lmtaddr() simultaneously. For example, if PF1 submit the request and got permitted before it reads the response and PF2 got scheduled submit the request then the response of PF1 is overwritten by the PF2 response. Fixes: 893ae97214c3 ("octeontx2-af: cn10k: Support configurable LMTST regions") Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/rvu_cn10k.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 4ad9ff025c96..0e74c5a2231e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -60,13 +60,14 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 iova, u64 *lmt_addr) { u64 pa, val, pf; - int err; + int err = 0; if (!iova) { dev_err(rvu->dev, "%s Requested Null address for transulation\n", __func__); return -EINVAL; } + mutex_lock(&rvu->rsrc_lock); rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova); pf = rvu_get_pf(pcifunc) & 0x1F; val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 | @@ -76,12 +77,13 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, err = rvu_poll_reg(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS, BIT_ULL(0), false); if (err) { dev_err(rvu->dev, "%s LMTLINE iova transulation failed\n", __func__); - return err; + goto exit; } val = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS); if (val & ~0x1ULL) { dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val); - return -EIO; + err = -EIO; + goto exit; } /* PA[51:12] = RVU_AF_SMMU_TLN_FLIT0[57:18] * PA[11:0] = IOVA[11:0] @@ -89,8 +91,9 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc, pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT0) >> 18; pa &= GENMASK_ULL(39, 0); *lmt_addr = (pa << 12) | (iova & 0xFFF); - - return 0; +exit: + mutex_unlock(&rvu->rsrc_lock); + return err; } static int rvu_update_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 lmt_addr) -- GitLab From c60a6b90e7890453f09e0d2163d6acadabe3415b Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:35 +0530 Subject: [PATCH 4445/5631] octeontx2-af: Fix start and end bit for scan config In the current driver, NPC exact match feature was not getting enabled as configured bit was not read properly. for_each_set_bit_from() need end bit as one bit post position in the bit map to read NPC exact nibble enable bits properly. This patch fixes the same. Fixes: b747923afff8 ("octeontx2-af: Exact match support") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 006beb5cf98d..f15efd41972e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -594,8 +594,7 @@ static int npc_scan_kex(struct rvu *rvu, int blkaddr, u8 intf) */ masked_cfg = cfg & NPC_EXACT_NIBBLE; bitnr = NPC_EXACT_NIBBLE_START; - for_each_set_bit_from(bitnr, (unsigned long *)&masked_cfg, - NPC_EXACT_NIBBLE_START) { + for_each_set_bit_from(bitnr, (unsigned long *)&masked_cfg, NPC_EXACT_NIBBLE_END + 1) { npc_scan_exact_result(mcam, bitnr, key_nibble, intf); key_nibble++; } -- GitLab From 60999cb83554ebcf6cfff8894bc2c3d99ea858ba Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:36 +0530 Subject: [PATCH 4446/5631] octeontx2-af: Fix depth of cam and mem table. In current driver, NPC cam and mem table sizes are read from wrong register offset. This patch fixes the register offset so that correct values are populated on read. Fixes: b747923afff8 ("octeontx2-af: Exact match support") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 20ebb9c95c73..6597af84aa36 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1868,9 +1868,9 @@ int rvu_npc_exact_init(struct rvu *rvu) rvu->hw->table = table; /* Read table size, ways and depth */ - table->mem_table.depth = FIELD_GET(GENMASK_ULL(31, 24), npc_const3); table->mem_table.ways = FIELD_GET(GENMASK_ULL(19, 16), npc_const3); - table->cam_table.depth = FIELD_GET(GENMASK_ULL(15, 0), npc_const3); + table->mem_table.depth = FIELD_GET(GENMASK_ULL(15, 0), npc_const3); + table->cam_table.depth = FIELD_GET(GENMASK_ULL(31, 24), npc_const3); dev_dbg(rvu->dev, "%s: NPC exact match 4way_2k table(ways=%d, depth=%d)\n", __func__, table->mem_table.ways, table->cam_table.depth); -- GitLab From 2a6eecc592b4d59a04d513aa25fc0f30d52100cd Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:37 +0530 Subject: [PATCH 4447/5631] octeontx2-pf: Increase the size of dmac filter flows CN10kb supports large number of dmac filter flows to be inserted. Increase the field size to accommodate the same Fixes: b747923afff8 ("octeontx2-af: Exact match support") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index f42b2b65bfd7..0c8fc66ade82 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -335,11 +335,11 @@ struct otx2_flow_config { #define OTX2_PER_VF_VLAN_FLOWS 2 /* Rx + Tx per VF */ #define OTX2_VF_VLAN_RX_INDEX 0 #define OTX2_VF_VLAN_TX_INDEX 1 - u16 max_flows; - u8 dmacflt_max_flows; u32 *bmap_to_dmacindex; unsigned long *dmacflt_bmap; struct list_head flow_list; + u32 dmacflt_max_flows; + u16 max_flows; }; struct otx2_tc_info { -- GitLab From cb5edce271764524b88b1a6866b3e626686d9a33 Mon Sep 17 00:00:00 2001 From: Hariprasad Kelam Date: Wed, 3 May 2023 12:39:38 +0530 Subject: [PATCH 4448/5631] octeontx2-af: Add validation for lmac type Upon physical link change, firmware reports to the kernel about the change along with the details like speed, lmac_type_id, etc. Kernel derives lmac_type based on lmac_type_id received from firmware. In a few scenarios, firmware returns an invalid lmac_type_id, which is resulting in below kernel panic. This patch adds the missing validation of the lmac_type_id field. Internal error: Oops: 96000005 [#1] PREEMPT SMP [ 35.321595] Modules linked in: [ 35.328982] CPU: 0 PID: 31 Comm: kworker/0:1 Not tainted 5.4.210-g2e3169d8e1bc-dirty #17 [ 35.337014] Hardware name: Marvell CN103XX board (DT) [ 35.344297] Workqueue: events work_for_cpu_fn [ 35.352730] pstate: 40400089 (nZcv daIf +PAN -UAO) [ 35.360267] pc : strncpy+0x10/0x30 [ 35.366595] lr : cgx_link_change_handler+0x90/0x180 Fixes: 61071a871ea6 ("octeontx2-af: Forward CGX link notifications to PFs") Signed-off-by: Hariprasad Kelam Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 724df6398bbe..bd77152bb8d7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1231,6 +1231,14 @@ static inline void link_status_user_format(u64 lstat, linfo->an = FIELD_GET(RESP_LINKSTAT_AN, lstat); linfo->fec = FIELD_GET(RESP_LINKSTAT_FEC, lstat); linfo->lmac_type_id = FIELD_GET(RESP_LINKSTAT_LMAC_TYPE, lstat); + + if (linfo->lmac_type_id >= LMAC_MODE_MAX) { + dev_err(&cgx->pdev->dev, "Unknown lmac_type_id %d reported by firmware on cgx port%d:%d", + linfo->lmac_type_id, cgx->cgx_id, lmac_id); + strncpy(linfo->lmac_type, "Unknown", LMACTYPE_STR_LEN - 1); + return; + } + lmac_string = cgx_lmactype_string[linfo->lmac_type_id]; strncpy(linfo->lmac_type, lmac_string, LMACTYPE_STR_LEN - 1); } -- GitLab From 2075bf150ddf320df02c05e242774dc0f73be1a1 Mon Sep 17 00:00:00 2001 From: Suman Ghosh Date: Wed, 3 May 2023 12:39:39 +0530 Subject: [PATCH 4449/5631] octeontx2-af: Update correct mask to filter IPv4 fragments During the initial design, the IPv4 ip_flag mask was set to 0xff. Which results to filter only fragmets with (fragment_offset == 0). As part of the fix, updated the mask to 0x20 to filter all the fragmented packets irrespective of the fragment_offset value. Fixes: c672e3727989 ("octeontx2-pf: Add support to filter packet based on IP fragment") Signed-off-by: Suman Ghosh Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 044cc211424e..8392f63e433f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -544,7 +544,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { if (ntohs(flow_spec->etype) == ETH_P_IP) { flow_spec->ip_flag = IPV4_FLAG_MORE; - flow_mask->ip_flag = 0xff; + flow_mask->ip_flag = IPV4_FLAG_MORE; req->features |= BIT_ULL(NPC_IPFRAG_IPV4); } else if (ntohs(flow_spec->etype) == ETH_P_IPV6) { flow_spec->next_header = IPPROTO_FRAGMENT; -- GitLab From 406bed11fb91a0b35c26fe633d8700febaec6439 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:40 +0530 Subject: [PATCH 4450/5631] octeontx2-af: Update/Fix NPC field hash extract feature 1. As per previous implementation, mask and control parameter to generate the field hash value was not passed to the caller program. Updated the secret key mbox to share that information as well, as a part of the fix. 2. Earlier implementation did not consider hash reduction of both source and destination IPv6 addresses. Only source IPv6 address was considered. This fix solves that and provides option to hash Fixes: 56d9f5fd2246 ("octeontx2-af: Use hashed field in MCAM key") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.h | 16 +++++--- .../marvell/octeontx2/af/rvu_npc_hash.c | 37 ++++++++++++------- .../marvell/octeontx2/af/rvu_npc_hash.h | 6 +++ 3 files changed, 41 insertions(+), 18 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 8fb5cae7285b..4c1e374bb376 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -245,9 +245,9 @@ M(NPC_MCAM_READ_BASE_RULE, 0x6011, npc_read_base_steer_rule, \ M(NPC_MCAM_GET_STATS, 0x6012, npc_mcam_entry_stats, \ npc_mcam_get_stats_req, \ npc_mcam_get_stats_rsp) \ -M(NPC_GET_SECRET_KEY, 0x6013, npc_get_secret_key, \ - npc_get_secret_key_req, \ - npc_get_secret_key_rsp) \ +M(NPC_GET_FIELD_HASH_INFO, 0x6013, npc_get_field_hash_info, \ + npc_get_field_hash_info_req, \ + npc_get_field_hash_info_rsp) \ M(NPC_GET_FIELD_STATUS, 0x6014, npc_get_field_status, \ npc_get_field_status_req, \ npc_get_field_status_rsp) \ @@ -1524,14 +1524,20 @@ struct npc_mcam_get_stats_rsp { u8 stat_ena; /* enabled */ }; -struct npc_get_secret_key_req { +struct npc_get_field_hash_info_req { struct mbox_msghdr hdr; u8 intf; }; -struct npc_get_secret_key_rsp { +struct npc_get_field_hash_info_rsp { struct mbox_msghdr hdr; u64 secret_key[3]; +#define NPC_MAX_HASH 2 +#define NPC_MAX_HASH_MASK 2 + /* NPC_AF_INTF(0..1)_HASH(0..1)_MASK(0..1) */ + u64 hash_mask[NPC_MAX_INTF][NPC_MAX_HASH][NPC_MAX_HASH_MASK]; + /* NPC_AF_INTF(0..1)_HASH(0..1)_RESULT_CTRL */ + u64 hash_ctrl[NPC_MAX_INTF][NPC_MAX_HASH]; }; enum ptp_op { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 6597af84aa36..68f813040363 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -110,8 +110,8 @@ static u64 npc_update_use_hash(int lt, int ld) * in KEX_LD_CFG */ cfg = KEX_LD_CFG_USE_HASH(0x1, 0x03, - ld ? 0x8 : 0x18, - 0x1, 0x0, 0x10); + ld ? 0x18 : 0x8, + 0x1, 0x0, ld ? 0x14 : 0x10); break; } @@ -134,7 +134,6 @@ static void npc_program_mkex_hash_rx(struct rvu *rvu, int blkaddr, if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][ld]) { u64 cfg = npc_update_use_hash(lt, ld); - hash_cnt++; if (hash_cnt == NPC_MAX_HASH) return; @@ -149,6 +148,8 @@ static void npc_program_mkex_hash_rx(struct rvu *rvu, int blkaddr, mkex_hash->hash_mask[intf][ld][1]); SET_KEX_LD_HASH_CTRL(intf, ld, mkex_hash->hash_ctrl[intf][ld]); + + hash_cnt++; } } } @@ -171,7 +172,6 @@ static void npc_program_mkex_hash_tx(struct rvu *rvu, int blkaddr, if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][ld]) { u64 cfg = npc_update_use_hash(lt, ld); - hash_cnt++; if (hash_cnt == NPC_MAX_HASH) return; @@ -187,8 +187,6 @@ static void npc_program_mkex_hash_tx(struct rvu *rvu, int blkaddr, SET_KEX_LD_HASH_CTRL(intf, ld, mkex_hash->hash_ctrl[intf][ld]); hash_cnt++; - if (hash_cnt == NPC_MAX_HASH) - return; } } } @@ -238,8 +236,8 @@ void npc_update_field_hash(struct rvu *rvu, u8 intf, struct flow_msg *omask) { struct npc_mcam_kex_hash *mkex_hash = rvu->kpu.mkex_hash; - struct npc_get_secret_key_req req; - struct npc_get_secret_key_rsp rsp; + struct npc_get_field_hash_info_req req; + struct npc_get_field_hash_info_rsp rsp; u64 ldata[2], cfg; u32 field_hash; u8 hash_idx; @@ -250,7 +248,7 @@ void npc_update_field_hash(struct rvu *rvu, u8 intf, } req.intf = intf; - rvu_mbox_handler_npc_get_secret_key(rvu, &req, &rsp); + rvu_mbox_handler_npc_get_field_hash_info(rvu, &req, &rsp); for (hash_idx = 0; hash_idx < NPC_MAX_HASH; hash_idx++) { cfg = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_HASHX_CFG(intf, hash_idx)); @@ -311,13 +309,13 @@ void npc_update_field_hash(struct rvu *rvu, u8 intf, } } -int rvu_mbox_handler_npc_get_secret_key(struct rvu *rvu, - struct npc_get_secret_key_req *req, - struct npc_get_secret_key_rsp *rsp) +int rvu_mbox_handler_npc_get_field_hash_info(struct rvu *rvu, + struct npc_get_field_hash_info_req *req, + struct npc_get_field_hash_info_rsp *rsp) { u64 *secret_key = rsp->secret_key; u8 intf = req->intf; - int blkaddr; + int i, j, blkaddr; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) { @@ -329,6 +327,19 @@ int rvu_mbox_handler_npc_get_secret_key(struct rvu *rvu, secret_key[1] = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_SECRET_KEY1(intf)); secret_key[2] = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_SECRET_KEY2(intf)); + for (i = 0; i < NPC_MAX_HASH; i++) { + for (j = 0; j < NPC_MAX_HASH_MASK; j++) { + rsp->hash_mask[NIX_INTF_RX][i][j] = + GET_KEX_LD_HASH_MASK(NIX_INTF_RX, i, j); + rsp->hash_mask[NIX_INTF_TX][i][j] = + GET_KEX_LD_HASH_MASK(NIX_INTF_TX, i, j); + } + } + + for (i = 0; i < NPC_MAX_INTF; i++) + for (j = 0; j < NPC_MAX_HASH; j++) + rsp->hash_ctrl[i][j] = GET_KEX_LD_HASH_CTRL(i, j); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h index 3efeb09c58de..65936f4aeaac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h @@ -31,6 +31,12 @@ rvu_write64(rvu, blkaddr, \ NPC_AF_INTFX_HASHX_MASKX(intf, ld, mask_idx), cfg) +#define GET_KEX_LD_HASH_CTRL(intf, ld) \ + rvu_read64(rvu, blkaddr, NPC_AF_INTFX_HASHX_RESULT_CTRL(intf, ld)) + +#define GET_KEX_LD_HASH_MASK(intf, ld, mask_idx) \ + rvu_read64(rvu, blkaddr, NPC_AF_INTFX_HASHX_MASKX(intf, ld, mask_idx)) + #define SET_KEX_LD_HASH_CTRL(intf, ld, cfg) \ rvu_write64(rvu, blkaddr, \ NPC_AF_INTFX_HASHX_RESULT_CTRL(intf, ld), cfg) -- GitLab From f66155905959076619c9c519fb099e8ae6cb6f7b Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:41 +0530 Subject: [PATCH 4451/5631] octeontx2-af: Fix issues with NPC field hash extract 1. Allow field hash configuration for both source and destination IPv6. 2. Configure hardware parser based on hash extract feature enable flag for IPv6. 3. Fix IPv6 endianness issue while updating the source/destination IP address via ntuple rule. Fixes: 56d9f5fd2246 ("octeontx2-af: Use hashed field in MCAM key") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- .../marvell/octeontx2/af/rvu_npc_fs.c | 23 +++-- .../marvell/octeontx2/af/rvu_npc_fs.h | 4 + .../marvell/octeontx2/af/rvu_npc_hash.c | 88 ++++++++++--------- .../marvell/octeontx2/af/rvu_npc_hash.h | 4 +- 4 files changed, 69 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index f15efd41972e..952319453701 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -13,11 +13,6 @@ #include "rvu_npc_fs.h" #include "rvu_npc_hash.h" -#define NPC_BYTESM GENMASK_ULL(19, 16) -#define NPC_HDR_OFFSET GENMASK_ULL(15, 8) -#define NPC_KEY_OFFSET GENMASK_ULL(5, 0) -#define NPC_LDATA_EN BIT_ULL(7) - static const char * const npc_flow_names[] = { [NPC_DMAC] = "dmac", [NPC_SMAC] = "smac", @@ -442,6 +437,7 @@ static void npc_handle_multi_layer_fields(struct rvu *rvu, int blkaddr, u8 intf) static void npc_scan_ldata(struct rvu *rvu, int blkaddr, u8 lid, u8 lt, u64 cfg, u8 intf) { + struct npc_mcam_kex_hash *mkex_hash = rvu->kpu.mkex_hash; struct npc_mcam *mcam = &rvu->hw->mcam; u8 hdr, key, nr_bytes, bit_offset; u8 la_ltype, la_start; @@ -490,8 +486,21 @@ do { \ NPC_SCAN_HDR(NPC_SIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 12, 4); NPC_SCAN_HDR(NPC_DIP_IPV4, NPC_LID_LC, NPC_LT_LC_IP, 16, 4); NPC_SCAN_HDR(NPC_IPFRAG_IPV6, NPC_LID_LC, NPC_LT_LC_IP6_EXT, 6, 1); - NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 16); - NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 16); + if (rvu->hw->cap.npc_hash_extract) { + if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][0]) + NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 4); + else + NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 16); + + if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][1]) + NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 4); + else + NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 16); + } else { + NPC_SCAN_HDR(NPC_SIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 8, 16); + NPC_SCAN_HDR(NPC_DIP_IPV6, NPC_LID_LC, NPC_LT_LC_IP6, 24, 16); + } + NPC_SCAN_HDR(NPC_SPORT_UDP, NPC_LID_LD, NPC_LT_LD_UDP, 0, 2); NPC_SCAN_HDR(NPC_DPORT_UDP, NPC_LID_LD, NPC_LT_LD_UDP, 2, 2); NPC_SCAN_HDR(NPC_SPORT_TCP, NPC_LID_LD, NPC_LT_LD_TCP, 0, 2); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.h index bdd65ce56a32..3f5c9042d10e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.h @@ -9,6 +9,10 @@ #define __RVU_NPC_FS_H #define IPV6_WORDS 4 +#define NPC_BYTESM GENMASK_ULL(19, 16) +#define NPC_HDR_OFFSET GENMASK_ULL(15, 8) +#define NPC_KEY_OFFSET GENMASK_ULL(5, 0) +#define NPC_LDATA_EN BIT_ULL(7) void npc_update_entry(struct rvu *rvu, enum key_fields type, struct mcam_entry *entry, u64 val_lo, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 68f813040363..51209119f0f2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -78,42 +78,43 @@ static u32 rvu_npc_toeplitz_hash(const u64 *data, u64 *key, size_t data_bit_len, return hash_out; } -u32 npc_field_hash_calc(u64 *ldata, struct npc_mcam_kex_hash *mkex_hash, - u64 *secret_key, u8 intf, u8 hash_idx) +u32 npc_field_hash_calc(u64 *ldata, struct npc_get_field_hash_info_rsp rsp, + u8 intf, u8 hash_idx) { u64 hash_key[3]; u64 data_padded[2]; u32 field_hash; - hash_key[0] = secret_key[1] << 31; - hash_key[0] |= secret_key[2]; - hash_key[1] = secret_key[1] >> 33; - hash_key[1] |= secret_key[0] << 31; - hash_key[2] = secret_key[0] >> 33; + hash_key[0] = rsp.secret_key[1] << 31; + hash_key[0] |= rsp.secret_key[2]; + hash_key[1] = rsp.secret_key[1] >> 33; + hash_key[1] |= rsp.secret_key[0] << 31; + hash_key[2] = rsp.secret_key[0] >> 33; - data_padded[0] = mkex_hash->hash_mask[intf][hash_idx][0] & ldata[0]; - data_padded[1] = mkex_hash->hash_mask[intf][hash_idx][1] & ldata[1]; + data_padded[0] = rsp.hash_mask[intf][hash_idx][0] & ldata[0]; + data_padded[1] = rsp.hash_mask[intf][hash_idx][1] & ldata[1]; field_hash = rvu_npc_toeplitz_hash(data_padded, hash_key, 128, 159); - field_hash &= mkex_hash->hash_ctrl[intf][hash_idx] >> 32; - field_hash |= mkex_hash->hash_ctrl[intf][hash_idx]; + field_hash &= FIELD_GET(GENMASK(63, 32), rsp.hash_ctrl[intf][hash_idx]); + field_hash += FIELD_GET(GENMASK(31, 0), rsp.hash_ctrl[intf][hash_idx]); return field_hash; } -static u64 npc_update_use_hash(int lt, int ld) +static u64 npc_update_use_hash(struct rvu *rvu, int blkaddr, + u8 intf, int lid, int lt, int ld) { - u64 cfg = 0; - - switch (lt) { - case NPC_LT_LC_IP6: - /* Update use_hash(bit-20) and bytesm1 (bit-16:19) - * in KEX_LD_CFG - */ - cfg = KEX_LD_CFG_USE_HASH(0x1, 0x03, - ld ? 0x18 : 0x8, - 0x1, 0x0, ld ? 0x14 : 0x10); - break; - } + u8 hdr, key; + u64 cfg; + + cfg = rvu_read64(rvu, blkaddr, NPC_AF_INTFX_LIDX_LTX_LDX_CFG(intf, lid, lt, ld)); + hdr = FIELD_GET(NPC_HDR_OFFSET, cfg); + key = FIELD_GET(NPC_KEY_OFFSET, cfg); + + /* Update use_hash(bit-20) to 'true' and + * bytesm1(bit-16:19) to '0x3' in KEX_LD_CFG + */ + cfg = KEX_LD_CFG_USE_HASH(0x1, 0x03, + hdr, 0x1, 0x0, key); return cfg; } @@ -132,11 +133,13 @@ static void npc_program_mkex_hash_rx(struct rvu *rvu, int blkaddr, for (lt = 0; lt < NPC_MAX_LT; lt++) { for (ld = 0; ld < NPC_MAX_LD; ld++) { if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][ld]) { - u64 cfg = npc_update_use_hash(lt, ld); + u64 cfg; if (hash_cnt == NPC_MAX_HASH) return; + cfg = npc_update_use_hash(rvu, blkaddr, + intf, lid, lt, ld); /* Set updated KEX configuration */ SET_KEX_LD(intf, lid, lt, ld, cfg); /* Set HASH configuration */ @@ -170,11 +173,13 @@ static void npc_program_mkex_hash_tx(struct rvu *rvu, int blkaddr, for (lt = 0; lt < NPC_MAX_LT; lt++) { for (ld = 0; ld < NPC_MAX_LD; ld++) if (mkex_hash->lid_lt_ld_hash_en[intf][lid][lt][ld]) { - u64 cfg = npc_update_use_hash(lt, ld); + u64 cfg; if (hash_cnt == NPC_MAX_HASH) return; + cfg = npc_update_use_hash(rvu, blkaddr, + intf, lid, lt, ld); /* Set updated KEX configuration */ SET_KEX_LD(intf, lid, lt, ld, cfg); /* Set HASH configuration */ @@ -264,44 +269,45 @@ void npc_update_field_hash(struct rvu *rvu, u8 intf, * is hashed to 32 bit value. */ case NPC_LT_LC_IP6: - if (features & BIT_ULL(NPC_SIP_IPV6)) { + /* ld[0] == hash_idx[0] == Source IPv6 + * ld[1] == hash_idx[1] == Destination IPv6 + */ + if ((features & BIT_ULL(NPC_SIP_IPV6)) && !hash_idx) { u32 src_ip[IPV6_WORDS]; be32_to_cpu_array(src_ip, pkt->ip6src, IPV6_WORDS); - ldata[0] = (u64)src_ip[0] << 32 | src_ip[1]; - ldata[1] = (u64)src_ip[2] << 32 | src_ip[3]; + ldata[1] = (u64)src_ip[0] << 32 | src_ip[1]; + ldata[0] = (u64)src_ip[2] << 32 | src_ip[3]; field_hash = npc_field_hash_calc(ldata, - mkex_hash, - rsp.secret_key, + rsp, intf, hash_idx); npc_update_entry(rvu, NPC_SIP_IPV6, entry, - field_hash, 0, 32, 0, intf); + field_hash, 0, + GENMASK(31, 0), 0, intf); memcpy(&opkt->ip6src, &pkt->ip6src, sizeof(pkt->ip6src)); memcpy(&omask->ip6src, &mask->ip6src, sizeof(mask->ip6src)); - break; - } - - if (features & BIT_ULL(NPC_DIP_IPV6)) { + } else if ((features & BIT_ULL(NPC_DIP_IPV6)) && hash_idx) { u32 dst_ip[IPV6_WORDS]; be32_to_cpu_array(dst_ip, pkt->ip6dst, IPV6_WORDS); - ldata[0] = (u64)dst_ip[0] << 32 | dst_ip[1]; - ldata[1] = (u64)dst_ip[2] << 32 | dst_ip[3]; + ldata[1] = (u64)dst_ip[0] << 32 | dst_ip[1]; + ldata[0] = (u64)dst_ip[2] << 32 | dst_ip[3]; field_hash = npc_field_hash_calc(ldata, - mkex_hash, - rsp.secret_key, + rsp, intf, hash_idx); npc_update_entry(rvu, NPC_DIP_IPV6, entry, - field_hash, 0, 32, 0, intf); + field_hash, 0, + GENMASK(31, 0), 0, intf); memcpy(&opkt->ip6dst, &pkt->ip6dst, sizeof(pkt->ip6dst)); memcpy(&omask->ip6dst, &mask->ip6dst, sizeof(mask->ip6dst)); } + break; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h index 65936f4aeaac..a1c3d987b804 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h @@ -62,8 +62,8 @@ void npc_update_field_hash(struct rvu *rvu, u8 intf, struct flow_msg *omask); void npc_config_secret_key(struct rvu *rvu, int blkaddr); void npc_program_mkex_hash(struct rvu *rvu, int blkaddr); -u32 npc_field_hash_calc(u64 *ldata, struct npc_mcam_kex_hash *mkex_hash, - u64 *secret_key, u8 intf, u8 hash_idx); +u32 npc_field_hash_calc(u64 *ldata, struct npc_get_field_hash_info_rsp rsp, + u8 intf, u8 hash_idx); static struct npc_mcam_kex_hash npc_mkex_hash_default __maybe_unused = { .lid_lt_ld_hash_en = { -- GitLab From 5eb1b7220948a69298a436148a735f32ec325289 Mon Sep 17 00:00:00 2001 From: Ratheesh Kannoth Date: Wed, 3 May 2023 12:39:42 +0530 Subject: [PATCH 4452/5631] octeontx2-af: Skip PFs if not enabled Firmware enables PFs and allocate mbox resources for each of the PFs. Currently PF driver configures mbox resources without checking whether PF is enabled or not. This results in crash. This patch fixes this issue by skipping disabled PF's mbox initialization. Fixes: 9bdc47a6e328 ("octeontx2-af: Mbox communication support btw AF and it's VFs") Signed-off-by: Ratheesh Kannoth Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller --- .../net/ethernet/marvell/octeontx2/af/mbox.c | 5 +- .../net/ethernet/marvell/octeontx2/af/mbox.h | 3 +- .../net/ethernet/marvell/octeontx2/af/rvu.c | 49 +++++++++++++++---- 3 files changed, 46 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 2898931d5260..9690ac01f02c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -157,7 +157,7 @@ EXPORT_SYMBOL(otx2_mbox_init); */ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void **hwbase, struct pci_dev *pdev, void *reg_base, - int direction, int ndevs) + int direction, int ndevs, unsigned long *pf_bmap) { struct otx2_mbox_dev *mdev; int devid, err; @@ -169,6 +169,9 @@ int otx2_mbox_regions_init(struct otx2_mbox *mbox, void **hwbase, mbox->hwbase = hwbase[0]; for (devid = 0; devid < ndevs; devid++) { + if (!test_bit(devid, pf_bmap)) + continue; + mdev = &mbox->dev[devid]; mdev->mbase = hwbase[devid]; mdev->hwbase = hwbase[devid]; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 4c1e374bb376..6389ed83637d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -96,9 +96,10 @@ void otx2_mbox_destroy(struct otx2_mbox *mbox); int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase, struct pci_dev *pdev, void __force *reg_base, int direction, int ndevs); + int otx2_mbox_regions_init(struct otx2_mbox *mbox, void __force **hwbase, struct pci_dev *pdev, void __force *reg_base, - int direction, int ndevs); + int direction, int ndevs, unsigned long *bmap); void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid); int otx2_mbox_wait_for_rsp(struct otx2_mbox *mbox, int devid); int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 8683ce57ed3f..9f673bda9dbd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2282,7 +2282,7 @@ static inline void rvu_afvf_mbox_up_handler(struct work_struct *work) } static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr, - int num, int type) + int num, int type, unsigned long *pf_bmap) { struct rvu_hwinfo *hw = rvu->hw; int region; @@ -2294,6 +2294,9 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr, */ if (type == TYPE_AFVF) { for (region = 0; region < num; region++) { + if (!test_bit(region, pf_bmap)) + continue; + if (hw->cap.per_pf_mbox_regs) { bar4 = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFX_BAR4_ADDR(0)) + @@ -2315,6 +2318,9 @@ static int rvu_get_mbox_regions(struct rvu *rvu, void **mbox_addr, * RVU_AF_PF_BAR4_ADDR register. */ for (region = 0; region < num; region++) { + if (!test_bit(region, pf_bmap)) + continue; + if (hw->cap.per_pf_mbox_regs) { bar4 = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFX_BAR4_ADDR(region)); @@ -2343,20 +2349,41 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, int err = -EINVAL, i, dir, dir_up; void __iomem *reg_base; struct rvu_work *mwork; + unsigned long *pf_bmap; void **mbox_regions; const char *name; + u64 cfg; - mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL); - if (!mbox_regions) + pf_bmap = bitmap_zalloc(num, GFP_KERNEL); + if (!pf_bmap) return -ENOMEM; + /* RVU VFs */ + if (type == TYPE_AFVF) + bitmap_set(pf_bmap, 0, num); + + if (type == TYPE_AFPF) { + /* Mark enabled PFs in bitmap */ + for (i = 0; i < num; i++) { + cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(i)); + if (cfg & BIT_ULL(20)) + set_bit(i, pf_bmap); + } + } + + mbox_regions = kcalloc(num, sizeof(void *), GFP_KERNEL); + if (!mbox_regions) { + err = -ENOMEM; + goto free_bitmap; + } + switch (type) { case TYPE_AFPF: name = "rvu_afpf_mailbox"; dir = MBOX_DIR_AFPF; dir_up = MBOX_DIR_AFPF_UP; reg_base = rvu->afreg_base; - err = rvu_get_mbox_regions(rvu, mbox_regions, num, TYPE_AFPF); + err = rvu_get_mbox_regions(rvu, mbox_regions, num, TYPE_AFPF, pf_bmap); if (err) goto free_regions; break; @@ -2365,7 +2392,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, dir = MBOX_DIR_PFVF; dir_up = MBOX_DIR_PFVF_UP; reg_base = rvu->pfreg_base; - err = rvu_get_mbox_regions(rvu, mbox_regions, num, TYPE_AFVF); + err = rvu_get_mbox_regions(rvu, mbox_regions, num, TYPE_AFVF, pf_bmap); if (err) goto free_regions; break; @@ -2396,16 +2423,19 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, } err = otx2_mbox_regions_init(&mw->mbox, mbox_regions, rvu->pdev, - reg_base, dir, num); + reg_base, dir, num, pf_bmap); if (err) goto exit; err = otx2_mbox_regions_init(&mw->mbox_up, mbox_regions, rvu->pdev, - reg_base, dir_up, num); + reg_base, dir_up, num, pf_bmap); if (err) goto exit; for (i = 0; i < num; i++) { + if (!test_bit(i, pf_bmap)) + continue; + mwork = &mw->mbox_wrk[i]; mwork->rvu = rvu; INIT_WORK(&mwork->work, mbox_handler); @@ -2414,8 +2444,7 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, mwork->rvu = rvu; INIT_WORK(&mwork->work, mbox_up_handler); } - kfree(mbox_regions); - return 0; + goto free_regions; exit: destroy_workqueue(mw->mbox_wq); @@ -2424,6 +2453,8 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw, iounmap((void __iomem *)mbox_regions[num]); free_regions: kfree(mbox_regions); +free_bitmap: + bitmap_free(pf_bmap); return err; } -- GitLab From c926252205c424c4842dbdbe02f8e3296f623204 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 3 May 2023 12:39:43 +0530 Subject: [PATCH 4453/5631] octeontx2-pf: Disable packet I/O for graceful exit At the stage of enabling packet I/O in otx2_open, If mailbox timeout occurs then interface ends up in down state where as hardware packet I/O is enabled. Hence disable packet I/O also before bailing out. Fixes: 1ea0166da050 ("octeontx2-pf: Fix the device state on error") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index a75c944cc739..18284ad75157 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1835,13 +1835,22 @@ int otx2_open(struct net_device *netdev) otx2_dmacflt_reinstall_flows(pf); err = otx2_rxtx_enable(pf, true); - if (err) + /* If a mbox communication error happens at this point then interface + * will end up in a state such that it is in down state but hardware + * mcam entries are enabled to receive the packets. Hence disable the + * packet I/O. + */ + if (err == EIO) + goto err_disable_rxtx; + else if (err) goto err_tx_stop_queues; otx2_do_set_rx_mode(pf); return 0; +err_disable_rxtx: + otx2_rxtx_enable(pf, false); err_tx_stop_queues: netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); -- GitLab From 99ae1260fdb5f15beab8a3adfb93a9041c87a2c1 Mon Sep 17 00:00:00 2001 From: Subbaraya Sundeep Date: Wed, 3 May 2023 12:39:44 +0530 Subject: [PATCH 4454/5631] octeontx2-vf: Detach LF resources on probe cleanup When a VF device probe fails due to error in MSIX vector allocation then the resources NIX and NPA LFs were not detached. Fix this by detaching the LFs when MSIX vector allocation fails. Fixes: 3184fb5ba96e ("octeontx2-vf: Virtual function driver support") Signed-off-by: Subbaraya Sundeep Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: Sai Krishna Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index ab126f8706c7..53366dbfbf27 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -621,7 +621,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = otx2vf_realloc_msix_vectors(vf); if (err) - goto err_mbox_destroy; + goto err_detach_rsrc; err = otx2_set_real_num_queues(netdev, qcount, qcount); if (err) -- GitLab From 3711d44fac1f80ea69ecb7315fed05b3812a7401 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 2 May 2023 11:47:40 -0700 Subject: [PATCH 4455/5631] ionic: remove noise from ethtool rxnfc error msg It seems that ethtool is calling into .get_rxnfc more often with ETHTOOL_GRXCLSRLCNT which ionic doesn't know about. We don't need to log a message about it, just return not supported. Fixes: aa3198819bea6 ("ionic: Add RSS support") Signed-off-by: Shannon Nelson Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index cf33503468a3..9b2b96fa36af 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -794,7 +794,7 @@ static int ionic_get_rxnfc(struct net_device *netdev, info->data = lif->nxqs; break; default: - netdev_err(netdev, "Command parameter %d is not supported\n", + netdev_dbg(netdev, "Command parameter %d is not supported\n", info->cmd); err = -EOPNOTSUPP; } -- GitLab From 0fbd79c01a9a657348f7032df70c57a406468c86 Mon Sep 17 00:00:00 2001 From: Hayes Wang Date: Tue, 2 May 2023 11:36:27 +0800 Subject: [PATCH 4456/5631] r8152: fix the autosuspend doesn't work Set supports_autosuspend = 1 for the rtl8152_cfgselector_driver. Fixes: ec51fbd1b8a2 ("r8152: add USB device driver for config selection") Signed-off-by: Hayes Wang Signed-off-by: David S. Miller --- drivers/net/usb/r8152.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 755b0f72dd44..0999a58ca9d2 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9910,6 +9910,7 @@ static struct usb_device_driver rtl8152_cfgselector_driver = { .probe = rtl8152_cfgselector_probe, .id_table = rtl8152_table, .generic_subclass = 1, + .supports_autosuspend = 1, }; static int __init rtl8152_driver_init(void) -- GitLab From 9ad685dbfe7e856bbf17a7177b64676d324d6ed7 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 2 May 2023 15:20:50 +0300 Subject: [PATCH 4457/5631] ethtool: Fix uninitialized number of lanes It is not possible to set the number of lanes when setting link modes using the legacy IOCTL ethtool interface. Since 'struct ethtool_link_ksettings' is not initialized in this path, drivers receive an uninitialized number of lanes in 'struct ethtool_link_ksettings::lanes'. When this information is later queried from drivers, it results in the ethtool code making decisions based on uninitialized memory, leading to the following KMSAN splat [1]. In practice, this most likely only happens with the tun driver that simply returns whatever it got in the set operation. As far as I can tell, this uninitialized memory is not leaked to user space thanks to the 'ethtool_ops->cap_link_lanes_supported' check in linkmodes_prepare_data(). Fix by initializing the structure in the IOCTL path. Did not find any more call sites that pass an uninitialized structure when calling 'ethtool_ops::set_link_ksettings()'. [1] BUG: KMSAN: uninit-value in ethnl_update_linkmodes net/ethtool/linkmodes.c:273 [inline] BUG: KMSAN: uninit-value in ethnl_set_linkmodes+0x190b/0x19d0 net/ethtool/linkmodes.c:333 ethnl_update_linkmodes net/ethtool/linkmodes.c:273 [inline] ethnl_set_linkmodes+0x190b/0x19d0 net/ethtool/linkmodes.c:333 ethnl_default_set_doit+0x88d/0xde0 net/ethtool/netlink.c:640 genl_family_rcv_msg_doit net/netlink/genetlink.c:968 [inline] genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x141a/0x14c0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x3f8/0x750 net/netlink/af_netlink.c:2577 genl_rcv+0x40/0x60 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0xf41/0x1270 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x127d/0x1430 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmsg net/socket.c:2584 [inline] __do_sys_sendmsg net/socket.c:2593 [inline] __se_sys_sendmsg net/socket.c:2591 [inline] __x64_sys_sendmsg+0x36b/0x540 net/socket.c:2591 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was stored to memory at: tun_get_link_ksettings+0x37/0x60 drivers/net/tun.c:3544 __ethtool_get_link_ksettings+0x17b/0x260 net/ethtool/ioctl.c:441 ethnl_set_linkmodes+0xee/0x19d0 net/ethtool/linkmodes.c:327 ethnl_default_set_doit+0x88d/0xde0 net/ethtool/netlink.c:640 genl_family_rcv_msg_doit net/netlink/genetlink.c:968 [inline] genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline] genl_rcv_msg+0x141a/0x14c0 net/netlink/genetlink.c:1065 netlink_rcv_skb+0x3f8/0x750 net/netlink/af_netlink.c:2577 genl_rcv+0x40/0x60 net/netlink/genetlink.c:1076 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0xf41/0x1270 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x127d/0x1430 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmsg net/socket.c:2584 [inline] __do_sys_sendmsg net/socket.c:2593 [inline] __se_sys_sendmsg net/socket.c:2591 [inline] __x64_sys_sendmsg+0x36b/0x540 net/socket.c:2591 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was stored to memory at: tun_set_link_ksettings+0x37/0x60 drivers/net/tun.c:3553 ethtool_set_link_ksettings+0x600/0x690 net/ethtool/ioctl.c:609 __dev_ethtool net/ethtool/ioctl.c:3024 [inline] dev_ethtool+0x1db9/0x2a70 net/ethtool/ioctl.c:3078 dev_ioctl+0xb07/0x1270 net/core/dev_ioctl.c:524 sock_do_ioctl+0x295/0x540 net/socket.c:1213 sock_ioctl+0x729/0xd90 net/socket.c:1316 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0x222/0x400 fs/ioctl.c:856 __x64_sys_ioctl+0x96/0xe0 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Local variable link_ksettings created at: ethtool_set_link_ksettings+0x54/0x690 net/ethtool/ioctl.c:577 __dev_ethtool net/ethtool/ioctl.c:3024 [inline] dev_ethtool+0x1db9/0x2a70 net/ethtool/ioctl.c:3078 Fixes: 012ce4dd3102 ("ethtool: Extend link modes settings uAPI with lanes") Reported-and-tested-by: syzbot+ef6edd9f1baaa54d6235@syzkaller.appspotmail.com Link: https://lore.kernel.org/netdev/0000000000004bb41105fa70f361@google.com/ Reviewed-by: Danielle Ratson Signed-off-by: Ido Schimmel Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- net/ethtool/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 59adc4e6e9ee..6bb778e10461 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -574,8 +574,8 @@ static int ethtool_get_link_ksettings(struct net_device *dev, static int ethtool_set_link_ksettings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings = {}; int err; - struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); -- GitLab From 4a54903ff68ddb33b6463c94b4eb37fc584ef760 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 2 May 2023 11:35:36 -0700 Subject: [PATCH 4458/5631] ionic: catch failure from devlink_alloc Add a check for NULL on the alloc return. If devlink_alloc() fails and we try to use devlink_priv() on the NULL return, the kernel gets very unhappy and panics. With this fix, the driver load will still fail, but at least it won't panic the kernel. Fixes: df69ba43217d ("ionic: Add basic framework for IONIC Network device driver") Signed-off-by: Shannon Nelson Reviewed-by: Simon Horman Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/pensando/ionic/ionic_devlink.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index e6ff757895ab..4ec66a6be073 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -61,6 +61,8 @@ struct ionic *ionic_devlink_alloc(struct device *dev) struct devlink *dl; dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic), dev); + if (!dl) + return NULL; return devlink_priv(dl); } -- GitLab From ec788f7e96ad4cd30338a09d466d9368acd73c26 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 2 May 2023 13:27:52 -0700 Subject: [PATCH 4459/5631] pds_core: remove CONFIG_DEBUG_FS from makefile This cruft from previous drafts should have been removed when the code was updated to not use the old style dummy helpers. Fixes: 55435ea7729a ("pds_core: initial framework for pds_core PF driver") Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/pds_core/Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/Makefile b/drivers/net/ethernet/amd/pds_core/Makefile index 0abc33ce826c..8239742e681f 100644 --- a/drivers/net/ethernet/amd/pds_core/Makefile +++ b/drivers/net/ethernet/amd/pds_core/Makefile @@ -9,6 +9,5 @@ pds_core-y := main.o \ dev.o \ adminq.o \ core.o \ + debugfs.o \ fw.o - -pds_core-$(CONFIG_DEBUG_FS) += debugfs.o -- GitLab From 1eeb807ffd8da5180f8d64d89ce332876acb5dbd Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 2 May 2023 13:40:32 -0700 Subject: [PATCH 4460/5631] pds_core: add AUXILIARY_BUS and NET_DEVLINK to Kconfig Add selecting of AUXILIARY_BUS and NET_DEVLINK to the pds_core Kconfig. Link: https://lore.kernel.org/netdev/ZE%2FduNH3lBLreNkJ@corigine.com/ Fixes: ddbcb22055d1 ("pds_core: Kconfig and pds_core.rst") Suggested-by: Simon Horman Signed-off-by: Shannon Nelson Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/Kconfig | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index 235fcacef5c5..f8cc8925161c 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -189,6 +189,8 @@ config AMD_XGBE_HAVE_ECC config PDS_CORE tristate "AMD/Pensando Data Systems Core Device Support" depends on 64BIT && PCI + select AUXILIARY_BUS + select NET_DEVLINK help This enables the support for the AMD/Pensando Core device family of adapters. More specific information on this driver can be -- GitLab From 3ce29c17dc847bf4245e16aad78a7617afa96297 Mon Sep 17 00:00:00 2001 From: Song Yoong Siang Date: Tue, 2 May 2023 08:48:06 -0700 Subject: [PATCH 4461/5631] igc: read before write to SRRCTL register igc_configure_rx_ring() function will be called as part of XDP program setup. If Rx hardware timestamp is enabled prio to XDP program setup, this timestamp enablement will be overwritten when buffer size is written into SRRCTL register. Thus, this commit read the register value before write to SRRCTL register. This commit is tested by using xdp_hw_metadata bpf selftest tool. The tool enables Rx hardware timestamp and then attach XDP program to igc driver. It will display hardware timestamp of UDP packet with port number 9092. Below are detail of test steps and results. Command on DUT: sudo ./xdp_hw_metadata Command on Link Partner: echo -n skb | nc -u -q1 9092 Result before this patch: skb hwtstamp is not found! Result after this patch: found skb hwtstamp = 1677800973.642836757 Optionally, read PHC to confirm the values obtained are almost the same: Command: sudo ./testptp -d /dev/ptp0 -g Result: clock time: 1677800973.913598978 or Fri Mar 3 07:49:33 2023 Fixes: fc9df2a0b520 ("igc: Enable RX via AF_XDP zero-copy") Cc: # 5.14+ Signed-off-by: Song Yoong Siang Reviewed-by: Jacob Keller Reviewed-by: Jesper Dangaard Brouer Tested-by: Jesper Dangaard Brouer Tested-by: Naama Meir Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/igc/igc_base.h | 11 ++++++++--- drivers/net/ethernet/intel/igc/igc_main.c | 7 +++++-- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 7a992befca24..9f3827eda157 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -87,8 +87,13 @@ union igc_adv_rx_desc { #define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ -#define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ -#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */ -#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IGC_SRRCTL_BSIZEPKT_MASK GENMASK(6, 0) +#define IGC_SRRCTL_BSIZEPKT(x) FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \ + (x) / 1024) /* in 1 KB resolution */ +#define IGC_SRRCTL_BSIZEHDR_MASK GENMASK(13, 8) +#define IGC_SRRCTL_BSIZEHDR(x) FIELD_PREP(IGC_SRRCTL_BSIZEHDR_MASK, \ + (x) / 64) /* in 64 bytes resolution */ +#define IGC_SRRCTL_DESCTYPE_MASK GENMASK(27, 25) +#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF FIELD_PREP(IGC_SRRCTL_DESCTYPE_MASK, 1) #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ba49728be919..1c4676882082 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -640,8 +640,11 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, else buf_size = IGC_RXBUFFER_2048; - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; + srrctl = rd32(IGC_SRRCTL(reg_idx)); + srrctl &= ~(IGC_SRRCTL_BSIZEPKT_MASK | IGC_SRRCTL_BSIZEHDR_MASK | + IGC_SRRCTL_DESCTYPE_MASK); + srrctl |= IGC_SRRCTL_BSIZEHDR(IGC_RX_HDR_LEN); + srrctl |= IGC_SRRCTL_BSIZEPKT(buf_size); srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); -- GitLab From 6a341729fb31b4c5df9f74f24b4b1c98410c9b87 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 1 May 2023 13:28:57 -0700 Subject: [PATCH 4462/5631] af_packet: Don't send zero-byte data in packet_sendmsg_spkt(). syzkaller reported a warning below [0]. We can reproduce it by sending 0-byte data from the (AF_PACKET, SOCK_PACKET) socket via some devices whose dev->hard_header_len is 0. struct sockaddr_pkt addr = { .spkt_family = AF_PACKET, .spkt_device = "tun0", }; int fd; fd = socket(AF_PACKET, SOCK_PACKET, 0); sendto(fd, NULL, 0, 0, (struct sockaddr *)&addr, sizeof(addr)); We have a similar fix for the (AF_PACKET, SOCK_RAW) socket as commit dc633700f00f ("net/af_packet: check len when min_header_len equals to 0"). Let's add the same test for the SOCK_PACKET socket. [0]: skb_assert_len WARNING: CPU: 1 PID: 19945 at include/linux/skbuff.h:2552 skb_assert_len include/linux/skbuff.h:2552 [inline] WARNING: CPU: 1 PID: 19945 at include/linux/skbuff.h:2552 __dev_queue_xmit+0x1f26/0x31d0 net/core/dev.c:4159 Modules linked in: CPU: 1 PID: 19945 Comm: syz-executor.0 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 RIP: 0010:skb_assert_len include/linux/skbuff.h:2552 [inline] RIP: 0010:__dev_queue_xmit+0x1f26/0x31d0 net/core/dev.c:4159 Code: 89 de e8 1d a2 85 fd 84 db 75 21 e8 64 a9 85 fd 48 c7 c6 80 2a 1f 86 48 c7 c7 c0 06 1f 86 c6 05 23 cf 27 04 01 e8 fa ee 56 fd <0f> 0b e8 43 a9 85 fd 0f b6 1d 0f cf 27 04 31 ff 89 de e8 e3 a1 85 RSP: 0018:ffff8880217af6e0 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffc90001133000 RDX: 0000000000040000 RSI: ffffffff81186922 RDI: 0000000000000001 RBP: ffff8880217af8b0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888030045640 R13: ffff8880300456b0 R14: ffff888030045650 R15: ffff888030045718 FS: 00007fc5864da640(0000) GS:ffff88806cd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020005740 CR3: 000000003f856003 CR4: 0000000000770ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: dev_queue_xmit include/linux/netdevice.h:3085 [inline] packet_sendmsg_spkt+0xc4b/0x1230 net/packet/af_packet.c:2066 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x1b4/0x200 net/socket.c:747 ____sys_sendmsg+0x331/0x970 net/socket.c:2503 ___sys_sendmsg+0x11d/0x1c0 net/socket.c:2557 __sys_sendmmsg+0x18c/0x430 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x9c/0x100 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc RIP: 0033:0x7fc58791de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 73 9f 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007fc5864d9cc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133 RAX: ffffffffffffffda RBX: 00000000004bbf80 RCX: 00007fc58791de5d RDX: 0000000000000001 RSI: 0000000020005740 RDI: 0000000000000004 RBP: 00000000004bbf80 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 000000000000000b R14: 00007fc58797e530 R15: 0000000000000000 ---[ end trace 0000000000000000 ]--- skb len=0 headroom=16 headlen=0 tailroom=304 mac=(16,0) net=(16,-1) trans=-1 shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0)) csum(0x0 ip_summed=0 complete_sw=0 valid=0 level=0) hash(0x0 sw=0 l4=0) proto=0x0000 pkttype=0 iif=0 dev name=sit0 feat=0x00000006401d7869 sk family=17 type=10 proto=0 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/packet/af_packet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6080c0db0814..640d94e34635 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2033,7 +2033,7 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, goto retry; } - if (!dev_validate_header(dev, skb->data, len)) { + if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } -- GitLab From f057b63bc11d86a98176de31b437e46789f44d8f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 3 May 2023 12:00:18 +0200 Subject: [PATCH 4463/5631] netfilter: nf_tables: fix ct untracked match breakage "ct untracked" no longer works properly due to erroneous NFT_BREAK. We have to check ctinfo enum first. Fixes: d9e789147605 ("netfilter: nf_tables: avoid retpoline overhead for some ct expression calls") Reported-by: Rvfg Link: https://marc.info/?l=netfilter&m=168294996212038&w=2 Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_ct_fast.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nft_ct_fast.c b/net/netfilter/nft_ct_fast.c index 89983b0613fa..e684c8a91848 100644 --- a/net/netfilter/nft_ct_fast.c +++ b/net/netfilter/nft_ct_fast.c @@ -15,10 +15,6 @@ void nft_ct_get_fast_eval(const struct nft_expr *expr, unsigned int state; ct = nf_ct_get(pkt->skb, &ctinfo); - if (!ct) { - regs->verdict.code = NFT_BREAK; - return; - } switch (priv->key) { case NFT_CT_STATE: @@ -30,6 +26,16 @@ void nft_ct_get_fast_eval(const struct nft_expr *expr, state = NF_CT_STATE_INVALID_BIT; *dest = state; return; + default: + break; + } + + if (!ct) { + regs->verdict.code = NFT_BREAK; + return; + } + + switch (priv->key) { case NFT_CT_DIRECTION: nft_reg_store8(dest, CTINFO2DIR(ctinfo)); return; -- GitLab From 29cd2927fb914cc53b5ba4f67d2b74695c994ba4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 2 May 2023 14:59:10 -0400 Subject: [PATCH 4464/5631] SUNRPC: Fix encoding of accepted but unsuccessful RPC replies Jiri Slaby says: > I bisected to this ... as it breaks nfs3-only servers in 6.3. > I.e. /etc/nfs.conf containing: > [nfsd] > vers4=no > > The client sees: > mount("10.0.2.15:/tmp", "/mnt", "nfs", 0, "vers=4.2,addr=10.0.2.15,clientad"...) = -1 EIO (Input/output error) > write(2, "mount.nfs: mount system call fai"..., 45 > mount.nfs: mount system call failed for /mnt > > And the kernel says: > nfs4_discover_server_trunking unhandled error -5. Exiting with error EIO Reported-by: Jiri Slaby Link: https://bugzilla.suse.com/show_bug.cgi?id=1210995 Fixes: 4bcf0343e8a6 ("SUNRPC: Set rq_accept_statp inside ->accept methods") Tested-by: Jiri Slaby Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 26367cf4c17a..43e32129a583 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1416,7 +1416,7 @@ svc_process_common(struct svc_rqst *rqstp) /* Only RPCv2 supported */ xdr_stream_encode_u32(xdr, RPC_VERSION); xdr_stream_encode_u32(xdr, RPC_VERSION); - goto sendit; + return 1; /* don't wrap */ err_bad_auth: dprintk("svc: authentication failed (%d)\n", @@ -1432,7 +1432,7 @@ svc_process_common(struct svc_rqst *rqstp) err_bad_prog: dprintk("svc: unknown program %d\n", rqstp->rq_prog); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_UNAVAIL); + *rqstp->rq_accept_statp = rpc_prog_unavail; goto sendit; err_bad_vers: @@ -1440,7 +1440,12 @@ svc_process_common(struct svc_rqst *rqstp) rqstp->rq_vers, rqstp->rq_prog, progp->pg_name); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROG_MISMATCH); + *rqstp->rq_accept_statp = rpc_prog_mismatch; + + /* + * svc_authenticate() has already added the verifier and + * advanced the stream just past rq_accept_statp. + */ xdr_stream_encode_u32(xdr, process.mismatch.lovers); xdr_stream_encode_u32(xdr, process.mismatch.hivers); goto sendit; @@ -1449,19 +1454,19 @@ svc_process_common(struct svc_rqst *rqstp) svc_printk(rqstp, "unknown procedure (%d)\n", rqstp->rq_proc); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_PROC_UNAVAIL); + *rqstp->rq_accept_statp = rpc_proc_unavail; goto sendit; err_garbage_args: svc_printk(rqstp, "failed to decode RPC header\n"); serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_GARBAGE_ARGS); + *rqstp->rq_accept_statp = rpc_garbage_args; goto sendit; err_system_err: serv->sv_stats->rpcbadfmt++; - xdr_stream_encode_u32(xdr, RPC_SYSTEM_ERR); + *rqstp->rq_accept_statp = rpc_system_err; goto sendit; } -- GitLab From 311693ce81c9da3724d4294a4c3769a3b30b6a7f Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 3 May 2023 10:11:34 +0200 Subject: [PATCH 4465/5631] perf test record+probe_libc_inet_pton: Fix call chain match on s390 With Fedora 38 the perf test 86 probe libc's inet_pton fails on s390. The call chain of the ping command changed. The functions text_to_binary_address() and gaih_inet() do not show up in the call chain anymore. Output before: # ./perf test -v 86 86: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 541050 fgrep: warning: fgrep is obsolescent; using grep -F fgrep: warning: fgrep is obsolescent; using grep -F BFD: DWARF error: could not find variable specification at offset 0x22011 ... ping 541078 [002] 348826.679581: probe_libc:inet_pton_1: (3ffad84b940) 14b940 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) 10e9c3 __GI_getaddrinfo+0xeb3 (inlined) 4397 main+0x737 (/usr/bin/ping) FAIL: expected backtrace entry "gaih_inet.*\+0x[[:xdigit:]]\ +[[:space:]]\(/usr/lib64/libc.so.6|inlined\)$" got "4397 main+0x737 (/usr/bin/ping)" test child finished with -1 ---- end ---- probe libc's inet_pton & backtrace it with ping: FAILED! # Output after: # ./perf test -v 86 86: probe libc's inet_pton & backtrace it with ping : --- start --- test child forked, pid 541098 fgrep: warning: fgrep is obsolescent; using grep -F fgrep: warning: fgrep is obsolescent; using grep -F BFD: DWARF error: could not find variable specification at offset 0x309d1 ... ping 541126 [006] 349309.099067: probe_libc:inet_pton_1: (3ffb7f4b940) 14b940 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) 10e9c3 __GI_getaddrinfo+0xeb3 (inlined) 4397 main+0x737 (/usr/bin/ping) test child finished with 0 ---- end ---- probe libc's inet_pton & backtrace it with ping: Ok # Signed-off-by: Thomas Richter Cc: Heiko Carstens Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230503081134.3372415-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index b4149b2db4c6..4c739056cb65 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -38,8 +38,6 @@ trace_libc_inet_pton_backtrace() { case "$(uname -m)" in s390x) eventattr='call-graph=dwarf,max-stack=4' - echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected - echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; -- GitLab From 1f85d016768ff19f060f3cce014a43c761de8259 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 3 May 2023 10:12:55 +0200 Subject: [PATCH 4466/5631] perf test record+probe_libc_inet_pton: Fix call chain match on x86_64 The test case probe libc's inet_pton & backtrace it with ping fails with Fedora 38 on x86_64. Function getaddrinfo() does not show up in the call chain anymore: # ./perf script ping 1803 [000] 728.567146: probe_libc:inet_pton: (7f5275afc840) 133840 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) 27b4a __libc_start_call_main+0x7a (/usr/lib64/libc.so.6) 27c0b __libc_start_main@@GLIBC_2.34+0x8b (/usr/lib64/libc.so.6) ping 1803 [000] 728.567184: probe_libc:inet_pton: (7f5275afc840) 133840 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6) 493e main+0xcde (/usr/bin/ping) 27b4a __libc_start_call_main+0x7a (/usr/lib64/libc.so.6) # which causes the test case to fail. Remove function getaddrinfo() from list of expected functions. Output before: # ./perf test 'libc' 91: probe libc's inet_pton & backtrace it with ping : FAILED! # Output after: # ./perf test 'libc' 91: probe libc's inet_pton & backtrace it with ping : Ok # Signed-off-by: Thomas Richter Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230503081255.3372986-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 4c739056cb65..bbb5b3d185fa 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -49,7 +49,6 @@ trace_libc_inet_pton_backtrace() { ;; *) eventattr='max-stack=3' - echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected ;; esac -- GitLab From d246331b78cbef86237f9c22389205bc9b4e1cc1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 2 May 2023 16:00:06 -0400 Subject: [PATCH 4467/5631] btrfs: don't free qgroup space unless specified Boris noticed in his simple quotas testing that he was getting a leak with Sweet Tea's change to subvol create that stopped doing a transaction commit. This was just a side effect of that change. In the delayed inode code we have an optimization that will free extra reservations if we think we can pack a dir item into an already modified leaf. Previously this wouldn't be triggered in the subvolume create case because we'd commit the transaction, it was still possible but much harder to trigger. It could actually be triggered if we did a mkdir && subvol create with qgroups enabled. This occurs because in btrfs_insert_delayed_dir_index(), which gets called when we're adding the dir item, we do the following: btrfs_block_rsv_release(fs_info, trans->block_rsv, bytes, NULL); if we're able to skip reserving space. The problem here is that trans->block_rsv points at the temporary block rsv for the subvolume create, which has qgroup reservations in the block rsv. This is a problem because btrfs_block_rsv_release() will do the following: if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { qgroup_to_release = block_rsv->qgroup_rsv_reserved - block_rsv->qgroup_rsv_size; block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size; } The temporary block rsv just has ->qgroup_rsv_reserved set, ->qgroup_rsv_size == 0. The optimization in btrfs_insert_delayed_dir_index() sets ->qgroup_rsv_reserved = 0. Then later on when we call btrfs_subvolume_release_metadata() which has btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release); btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release); qgroup_to_release is set to 0, and we do not convert the reserved metadata space. The problem here is that the block rsv code has been unconditionally messing with ->qgroup_rsv_reserved, because the main place this is used is delalloc, and any time we call btrfs_block_rsv_release() we do it with qgroup_to_release set, and thus do the proper accounting. The subvolume code is the only other code that uses the qgroup reservation stuff, but it's intermingled with the above optimization, and thus was getting its reservation freed out from underneath it and thus leaking the reserved space. The solution is to simply not mess with the qgroup reservations if we don't have qgroup_to_release set. This works with the existing code as anything that messes with the delalloc reservations always have qgroup_to_release set. This fixes the leak that Boris was observing. Reviewed-by: Qu Wenruo CC: stable@vger.kernel.org # 5.4+ Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/block-rsv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 3ab707e26fa2..ac18c43fadad 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -124,7 +124,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info, } else { num_bytes = 0; } - if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { + if (qgroup_to_release_ret && + block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) { qgroup_to_release = block_rsv->qgroup_rsv_reserved - block_rsv->qgroup_rsv_size; block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size; -- GitLab From 776617db78c6d208780e7c69d4d68d1fa82913de Mon Sep 17 00:00:00 2001 From: Tobias Holl Date: Wed, 3 May 2023 08:59:50 -0600 Subject: [PATCH 4468/5631] io_uring/rsrc: check for nonconsecutive pages Pages that are from the same folio do not necessarily need to be consecutive. In that case, we cannot consolidate them into a single bvec entry. Before applying the huge page optimization from commit 57bebf807e2a ("io_uring/rsrc: optimise registered huge pages"), check that the memory is actually consecutive. Cc: stable@vger.kernel.org Fixes: 57bebf807e2a ("io_uring/rsrc: optimise registered huge pages") Signed-off-by: Tobias Holl [axboe: formatting] Signed-off-by: Jens Axboe --- io_uring/rsrc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index ddee7adb4006..00affcf811ad 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1117,7 +1117,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, if (nr_pages > 1) { folio = page_folio(pages[0]); for (i = 1; i < nr_pages; i++) { - if (page_folio(pages[i]) != folio) { + /* + * Pages must be consecutive and on the same folio for + * this to work + */ + if (page_folio(pages[i]) != folio || + pages[i] != pages[i - 1] + 1) { folio = NULL; break; } -- GitLab From c770657bd2611b077ec1e7b1fe6aa92f249399bd Mon Sep 17 00:00:00 2001 From: Reid Tonking Date: Wed, 26 Apr 2023 14:49:56 -0500 Subject: [PATCH 4469/5631] i2c: omap: Fix standard mode false ACK readings Using standard mode, rare false ACK responses were appearing with i2cdetect tool. This was happening due to NACK interrupt triggering ISR thread before register access interrupt was ready. Removing the NACK interrupt's ability to trigger ISR thread lets register access ready interrupt do this instead. Cc: # v3.7+ Fixes: 3b2f8f82dad7 ("i2c: omap: switch to threaded IRQ support") Signed-off-by: Reid Tonking Acked-by: Vignesh Raghavendra Reviewed-by: Tony Lindgren Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-omap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 2b4e2be51318..4199f57a6bf2 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1058,7 +1058,7 @@ omap_i2c_isr(int irq, void *dev_id) u16 stat; stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG); - mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG); + mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG) & ~OMAP_I2C_STAT_NACK; if (stat & mask) ret = IRQ_WAKE_THREAD; -- GitLab From fa39065833dbdb2059ffe25d071e722c31fbbb6c Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 24 Apr 2023 10:06:27 +0200 Subject: [PATCH 4470/5631] i2c: imx-lpi2c: avoid taking clk_prepare mutex in PM callbacks This is unsafe, as the runtime PM callbacks are called from the PM workqueue, so this may deadlock when handling an i2c attached clock, which may already hold the clk_prepare mutex from another context. Signed-off-by: Alexander Stein Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-imx-lpi2c.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index a49b14d52a98..1af0a637d7f1 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -639,7 +639,7 @@ static int __maybe_unused lpi2c_runtime_suspend(struct device *dev) { struct lpi2c_imx_struct *lpi2c_imx = dev_get_drvdata(dev); - clk_bulk_disable_unprepare(lpi2c_imx->num_clks, lpi2c_imx->clks); + clk_bulk_disable(lpi2c_imx->num_clks, lpi2c_imx->clks); pinctrl_pm_select_sleep_state(dev); return 0; @@ -651,7 +651,7 @@ static int __maybe_unused lpi2c_runtime_resume(struct device *dev) int ret; pinctrl_pm_select_default_state(dev); - ret = clk_bulk_prepare_enable(lpi2c_imx->num_clks, lpi2c_imx->clks); + ret = clk_bulk_enable(lpi2c_imx->num_clks, lpi2c_imx->clks); if (ret) { dev_err(dev, "failed to enable I2C clock, ret=%d\n", ret); return ret; -- GitLab From 5d388143fa6c351d985ffd23ea50c91c8839141b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 3 Apr 2023 09:49:13 +0200 Subject: [PATCH 4471/5631] i2c: gxp: fix build failure without CONFIG_I2C_SLAVE The gxp_i2c_slave_irq_handler() is hidden in an #ifdef, but the caller uses an IS_ENABLED() check: drivers/i2c/busses/i2c-gxp.c: In function 'gxp_i2c_irq_handler': drivers/i2c/busses/i2c-gxp.c:467:29: error: implicit declaration of function 'gxp_i2c_slave_irq_handler'; did you mean 'gxp_i2c_irq_handler'? [-Werror=implicit-function-declaration] It has to consistently use one method or the other to avoid warnings, so move to IS_ENABLED() here for readability and build coverage, and move the #ifdef in linux/i2c.h to allow building it as dead code. Fixes: 4a55ed6f89f5 ("i2c: Add GXP SoC I2C Controller") Signed-off-by: Arnd Bergmann Reviewed-by: Nick Hawkins Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-gxp.c | 2 -- include/linux/i2c.h | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/i2c/busses/i2c-gxp.c b/drivers/i2c/busses/i2c-gxp.c index d4b55d989a26..8ea3fb5e4c7f 100644 --- a/drivers/i2c/busses/i2c-gxp.c +++ b/drivers/i2c/busses/i2c-gxp.c @@ -353,7 +353,6 @@ static void gxp_i2c_chk_data_ack(struct gxp_i2c_drvdata *drvdata) writew(value, drvdata->base + GXP_I2CMCMD); } -#if IS_ENABLED(CONFIG_I2C_SLAVE) static bool gxp_i2c_slave_irq_handler(struct gxp_i2c_drvdata *drvdata) { u8 value; @@ -437,7 +436,6 @@ static bool gxp_i2c_slave_irq_handler(struct gxp_i2c_drvdata *drvdata) return true; } -#endif static irqreturn_t gxp_i2c_irq_handler(int irq, void *_drvdata) { diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5ba89663ea86..13a1ce38cb0c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -385,7 +385,6 @@ static inline void i2c_set_clientdata(struct i2c_client *client, void *data) /* I2C slave support */ -#if IS_ENABLED(CONFIG_I2C_SLAVE) enum i2c_slave_event { I2C_SLAVE_READ_REQUESTED, I2C_SLAVE_WRITE_REQUESTED, @@ -396,9 +395,10 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); -bool i2c_detect_slave_mode(struct device *dev); int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val); +#if IS_ENABLED(CONFIG_I2C_SLAVE) +bool i2c_detect_slave_mode(struct device *dev); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif -- GitLab From 3899d94e3831ee07ea6821c032dc297aec80586a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christoph=20B=C3=B6hmwalder?= Date: Wed, 3 May 2023 14:19:37 +0200 Subject: [PATCH 4472/5631] drbd: correctly submit flush bio on barrier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When we receive a flush command (or "barrier" in DRBD), we currently use a REQ_OP_FLUSH with the REQ_PREFLUSH flag set. The correct way to submit a flush bio is by using a REQ_OP_WRITE without any data, and set the REQ_PREFLUSH flag. Since commit b4a6bb3a67aa ("block: add a sanity check for non-write flush/fua bios"), this triggers a warning in the block layer, but this has been broken for quite some time before that. So use the correct set of flags to actually make the flush happen. Cc: Christoph Hellwig Cc: stable@vger.kernel.org Fixes: f9ff0da56437 ("drbd: allow parallel flushes for multi-volume resources") Reported-by: Thomas Voegtle Signed-off-by: Christoph Böhmwalder Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230503121937.17232-1-christoph.boehmwalder@linbit.com Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_receiver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index e54404c632e7..34b112752ab1 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1283,7 +1283,7 @@ static void one_flush_endio(struct bio *bio) static void submit_one_flush(struct drbd_device *device, struct issue_flush_context *ctx) { struct bio *bio = bio_alloc(device->ldev->backing_bdev, 0, - REQ_OP_FLUSH | REQ_PREFLUSH, GFP_NOIO); + REQ_OP_WRITE | REQ_PREFLUSH, GFP_NOIO); struct one_flush_context *octx = kmalloc(sizeof(*octx), GFP_NOIO); if (!octx) { -- GitLab From 1bd922877a084c1c6c1d0cb1bb9c3700fa0f6c61 Mon Sep 17 00:00:00 2001 From: Stanislav Jakubek Date: Sun, 23 Apr 2023 14:40:18 +0200 Subject: [PATCH 4473/5631] dt-bindings: i2c: brcm,kona-i2c: convert to YAML Changes during conversion: - add used, but previously undocumented SoC-specific compatibles - drop references to SoCs that are not upstream - add supported clock frequencies Signed-off-by: Stanislav Jakubek Reviewed-by: Krzysztof Kozlowski Signed-off-by: Wolfram Sang --- .../devicetree/bindings/i2c/brcm,kona-i2c.txt | 35 ----------- .../bindings/i2c/brcm,kona-i2c.yaml | 59 +++++++++++++++++++ 2 files changed, 59 insertions(+), 35 deletions(-) delete mode 100644 Documentation/devicetree/bindings/i2c/brcm,kona-i2c.txt create mode 100644 Documentation/devicetree/bindings/i2c/brcm,kona-i2c.yaml diff --git a/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.txt b/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.txt deleted file mode 100644 index 1b87b741fa8e..000000000000 --- a/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.txt +++ /dev/null @@ -1,35 +0,0 @@ -Broadcom Kona Family I2C -========================= - -This I2C controller is used in the following Broadcom SoCs: - - BCM11130 - BCM11140 - BCM11351 - BCM28145 - BCM28155 - -Required Properties -------------------- -- compatible: "brcm,bcm11351-i2c", "brcm,kona-i2c" -- reg: Physical base address and length of controller registers -- interrupts: The interrupt number used by the controller -- clocks: clock specifier for the kona i2c external clock -- clock-frequency: The I2C bus frequency in Hz -- #address-cells: Should be <1> -- #size-cells: Should be <0> - -Refer to clocks/clock-bindings.txt for generic clock consumer -properties. - -Example: - -i2c@3e016000 { - compatible = "brcm,bcm11351-i2c","brcm,kona-i2c"; - reg = <0x3e016000 0x80>; - interrupts = ; - clocks = <&bsc1_clk>; - clock-frequency = <400000>; - #address-cells = <1>; - #size-cells = <0>; -}; diff --git a/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.yaml b/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.yaml new file mode 100644 index 000000000000..7a694af90fc6 --- /dev/null +++ b/Documentation/devicetree/bindings/i2c/brcm,kona-i2c.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/i2c/brcm,kona-i2c.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Broadcom Kona family I2C controller + +maintainers: + - Florian Fainelli + +allOf: + - $ref: /schemas/i2c/i2c-controller.yaml# + +properties: + compatible: + items: + - enum: + - brcm,bcm11351-i2c + - brcm,bcm21664-i2c + - brcm,bcm23550-i2c + - const: brcm,kona-i2c + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-frequency: + enum: [ 100000, 400000, 1000000, 3400000 ] + +required: + - compatible + - reg + - interrupts + - clocks + - clock-frequency + +unevaluatedProperties: false + +examples: + - | + #include + #include + + i2c@3e016000 { + compatible = "brcm,bcm11351-i2c", "brcm,kona-i2c"; + reg = <0x3e016000 0x80>; + interrupts = ; + clocks = <&bsc1_clk>; + clock-frequency = <400000>; + #address-cells = <1>; + #size-cells = <0>; + }; +... -- GitLab From c0b79b0ff53be5b05be98e3caaa6a39de1fe9520 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 2 May 2023 10:42:31 +0800 Subject: [PATCH 4474/5631] ublk: add timeout handler Add timeout handler, so that we can provide forward progress guarantee for unprivileged ublk, which can't be trusted. One thing is that sync() calls sync_bdevs(wait) for all block devices after running sync_bdevs(no_wait), and if one device can't move on, the sync() won't return any more. Add timeout for unprivileged ublk to avoid such affect for other users which call sync() syscall. Meantime clear UBLK_F_USER_RECOVERY_REISSUE for unprivileged ublk since that feature may cause IO hang too. Fixes: 4093cb5a0634 ("ublk_drv: add mechanism for supporting unprivileged ublk device") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230502024231.888498-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 253008b2091d..e96309f2e1ad 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -129,6 +129,7 @@ struct ublk_queue { unsigned long io_addr; /* mapped vm address */ unsigned int max_io_sz; bool force_abort; + bool timeout; unsigned short nr_io_ready; /* how many ios setup */ struct ublk_device *dev; struct ublk_io ios[]; @@ -894,6 +895,22 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) } } +static enum blk_eh_timer_return ublk_timeout(struct request *rq) +{ + struct ublk_queue *ubq = rq->mq_hctx->driver_data; + + if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) { + if (!ubq->timeout) { + send_sig(SIGKILL, ubq->ubq_daemon, 0); + ubq->timeout = true; + } + + return BLK_EH_DONE; + } + + return BLK_EH_RESET_TIMER; +} + static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -953,6 +970,7 @@ static const struct blk_mq_ops ublk_mq_ops = { .queue_rq = ublk_queue_rq, .init_hctx = ublk_init_hctx, .init_request = ublk_init_rq, + .timeout = ublk_timeout, }; static int ublk_ch_open(struct inode *inode, struct file *filp) @@ -1713,6 +1731,18 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV)) return -EPERM; + /* + * unprivileged device can't be trusted, but RECOVERY and + * RECOVERY_REISSUE still may hang error handling, so can't + * support recovery features for unprivileged ublk now + * + * TODO: provide forward progress for RECOVERY handler, so that + * unprivileged device can benefit from it + */ + if (info.flags & UBLK_F_UNPRIVILEGED_DEV) + info.flags &= ~(UBLK_F_USER_RECOVERY_REISSUE | + UBLK_F_USER_RECOVERY); + /* the created device is always owned by current user */ ublk_store_owner_uid_gid(&info.owner_uid, &info.owner_gid); @@ -1981,6 +2011,7 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) put_task_struct(ubq->ubq_daemon); /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ ubq->ubq_daemon = NULL; + ubq->timeout = false; for (i = 0; i < ubq->q_depth; i++) { struct ublk_io *io = &ubq->ios[i]; -- GitLab From 82da62abe56263319a974a4d77c1e6fa19355de1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 28 Dec 2022 08:41:54 +0100 Subject: [PATCH 4475/5631] parisc: Limit amount of kgdb breakpoints on parisc kgdb is rarely used and 40 breakpoints seems enough to debug parisc specific bugs. Signed-off-by: Helge Deller --- arch/parisc/include/asm/kgdb.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/parisc/include/asm/kgdb.h b/arch/parisc/include/asm/kgdb.h index f23e7f8f13a5..317cd434bee3 100644 --- a/arch/parisc/include/asm/kgdb.h +++ b/arch/parisc/include/asm/kgdb.h @@ -17,6 +17,8 @@ #define NUMREGBYTES sizeof(struct parisc_gdb_regs) #define BUFMAX 4096 +#define KGDB_MAX_BREAKPOINTS 40 + #define CACHE_FLUSH_IS_SAFE 1 #ifndef __ASSEMBLY__ -- GitLab From e0838a99289e013d17496ed9464c3cf71d49b977 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 5 Feb 2023 08:37:52 -0800 Subject: [PATCH 4476/5631] parisc: update kbuild doc. aliases for parisc64 ARCH=parisc64 is now supported for 64-bit parisc builds, so add this alias to the kbuild.rst documentation. Fixes: 3dcfb729b5f4 ("parisc: Make CONFIG_64BIT available for ARCH=parisc64 only") Signed-off-by: Randy Dunlap Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: linux-parisc@vger.kernel.org Cc: Masahiro Yamada Cc: linux-kbuild@vger.kernel.org Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Acked-by: Masahiro Yamada Signed-off-by: Helge Deller --- Documentation/kbuild/kbuild.rst | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index e22621f4af0b..2a22ddb1b848 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -160,6 +160,7 @@ directory name found in the arch/ directory. But some architectures such as x86 and sparc have aliases. - x86: i386 for 32 bit, x86_64 for 64 bit +- parisc: parisc64 for 64 bit - sparc: sparc32 for 32 bit, sparc64 for 64 bit CROSS_COMPILE -- GitLab From 829632dae8321787525ee37dc4828bbe6edafdae Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Mon, 20 Feb 2023 18:11:05 -0300 Subject: [PATCH 4477/5631] parisc: Replace regular spinlock with spin_trylock on panic path The panic notifiers' callbacks execute in an atomic context, with interrupts/preemption disabled, and all CPUs not running the panic function are off, so it's very dangerous to wait on a regular spinlock, there's a risk of deadlock. Refactor the panic notifier of parisc/power driver to make use of spin_trylock - for that, we've added a second version of the soft-power function. Also, some comments were reorganized and trailing white spaces, useless header inclusion and blank lines were removed. Cc: "James E.J. Bottomley" Cc: Jeroen Roovers Acked-by: Helge Deller # parisc Signed-off-by: Guilherme G. Piccoli Signed-off-by: Helge Deller --- arch/parisc/include/asm/pdc.h | 1 + arch/parisc/kernel/firmware.c | 27 +++++++++++++++++++++++---- drivers/parisc/power.c | 16 ++++++++++------ 3 files changed, 34 insertions(+), 10 deletions(-) diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h index 40793bef8429..2b4fad8328e8 100644 --- a/arch/parisc/include/asm/pdc.h +++ b/arch/parisc/include/asm/pdc.h @@ -80,6 +80,7 @@ int pdc_do_firm_test_reset(unsigned long ftc_bitmap); int pdc_do_reset(void); int pdc_soft_power_info(unsigned long *power_reg); int pdc_soft_power_button(int sw_control); +int pdc_soft_power_button_panic(int sw_control); void pdc_io_reset(void); void pdc_io_reset_devices(void); int pdc_iodc_getc(void); diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 6817892a2c58..cc124d9f1f7f 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1232,15 +1232,18 @@ int __init pdc_soft_power_info(unsigned long *power_reg) } /* - * pdc_soft_power_button - Control the soft power button behaviour - * @sw_control: 0 for hardware control, 1 for software control + * pdc_soft_power_button{_panic} - Control the soft power button behaviour + * @sw_control: 0 for hardware control, 1 for software control * * * This PDC function places the soft power button under software or * hardware control. - * Under software control the OS may control to when to allow to shut - * down the system. Under hardware control pressing the power button + * Under software control the OS may control to when to allow to shut + * down the system. Under hardware control pressing the power button * powers off the system immediately. + * + * The _panic version relies on spin_trylock to prevent deadlock + * on panic path. */ int pdc_soft_power_button(int sw_control) { @@ -1254,6 +1257,22 @@ int pdc_soft_power_button(int sw_control) return retval; } +int pdc_soft_power_button_panic(int sw_control) +{ + int retval; + unsigned long flags; + + if (!spin_trylock_irqsave(&pdc_lock, flags)) { + pr_emerg("Couldn't enable soft power button\n"); + return -EBUSY; /* ignored by the panic notifier */ + } + + retval = mem_pdc_call(PDC_SOFT_POWER, PDC_SOFT_POWER_ENABLE, __pa(pdc_result), sw_control); + spin_unlock_irqrestore(&pdc_lock, flags); + + return retval; +} + /* * pdc_io_reset - Hack to avoid overlapping range registers of Bridges devices. * Primarily a problem on T600 (which parisc-linux doesn't support) but diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index 456776bd8ee6..6f5e5f0230d3 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -175,16 +174,21 @@ static void powerfail_interrupt(int code, void *x) -/* parisc_panic_event() is called by the panic handler. - * As soon as a panic occurs, our tasklets above will not be - * executed any longer. This function then re-enables the - * soft-power switch and allows the user to switch off the system +/* + * parisc_panic_event() is called by the panic handler. + * + * As soon as a panic occurs, our tasklets above will not + * be executed any longer. This function then re-enables + * the soft-power switch and allows the user to switch off + * the system. We rely in pdc_soft_power_button_panic() + * since this version spin_trylocks (instead of regular + * spinlock), preventing deadlocks on panic path. */ static int parisc_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { /* re-enable the soft-power switch */ - pdc_soft_power_button(0); + pdc_soft_power_button_panic(0); return NOTIFY_DONE; } -- GitLab From d755bd2caeb47fd806e12399fe8b56798fa5d2cc Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 15 Mar 2023 19:25:15 +0100 Subject: [PATCH 4478/5631] parisc: Ensure page alignment in flush functions Matthew Wilcox noticed, that if ARCH_HAS_FLUSH_ON_KUNMAP is defined (which is the case for PA-RISC), __kunmap_local() calls kunmap_flush_on_unmap(), which may call the parisc flush functions with a non-page-aligned address and thus the page might not be fully flushed. This patch ensures that flush_kernel_dcache_page_asm() and flush_kernel_dcache_page_asm() will always operate on page-aligned addresses. Signed-off-by: Helge Deller Cc: # v6.0+ --- arch/parisc/kernel/pacache.S | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 9a0018f1f42c..541370d14559 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -889,6 +889,7 @@ ENDPROC_CFI(flush_icache_page_asm) ENTRY_CFI(flush_kernel_dcache_page_asm) 88: ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 + depi_safe 0, 31,PAGE_SHIFT, %r26 /* Clear any offset bits */ #ifdef CONFIG_64BIT depdi,z 1, 63-PAGE_SHIFT,1, %r25 @@ -925,6 +926,7 @@ ENDPROC_CFI(flush_kernel_dcache_page_asm) ENTRY_CFI(purge_kernel_dcache_page_asm) 88: ldil L%dcache_stride, %r1 ldw R%dcache_stride(%r1), %r23 + depi_safe 0, 31,PAGE_SHIFT, %r26 /* Clear any offset bits */ #ifdef CONFIG_64BIT depdi,z 1, 63-PAGE_SHIFT,1, %r25 -- GitLab From 653f3ea73bf3e03070d370300805eee4f2a47bd9 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 23 Apr 2023 21:37:47 +0200 Subject: [PATCH 4479/5631] parisc: Drop HP-UX constants and structs from grfioctl.h Signed-off-by: Helge Deller --- arch/parisc/include/asm/grfioctl.h | 38 ------------------------------ 1 file changed, 38 deletions(-) diff --git a/arch/parisc/include/asm/grfioctl.h b/arch/parisc/include/asm/grfioctl.h index a740844a1581..597201530d20 100644 --- a/arch/parisc/include/asm/grfioctl.h +++ b/arch/parisc/include/asm/grfioctl.h @@ -59,42 +59,4 @@ #define CRT_ID_LEGO 0x35ACDA30 /* Lego FX5, FX10 ... */ #define CRT_ID_PINNACLE 0x35ACDA16 /* Pinnacle FXe */ -/* structure for ioctl(GCDESCRIBE) */ - -#define gaddr_t unsigned long /* FIXME: PA2.0 (64bit) portable ? */ - -struct grf_fbinfo { - unsigned int id; /* upper 32 bits of graphics id */ - unsigned int mapsize; /* mapped size of framebuffer */ - unsigned int dwidth, dlength;/* x and y sizes */ - unsigned int width, length; /* total x and total y size */ - unsigned int xlen; /* x pitch size */ - unsigned int bpp, bppu; /* bits per pixel and used bpp */ - unsigned int npl, nplbytes; /* # of planes and bytes per plane */ - char name[32]; /* name of the device (from ROM) */ - unsigned int attr; /* attributes */ - gaddr_t fbbase, regbase;/* framebuffer and register base addr */ - gaddr_t regions[6]; /* region bases */ -}; - -#define GCID _IOR('G', 0, int) -#define GCON _IO('G', 1) -#define GCOFF _IO('G', 2) -#define GCAON _IO('G', 3) -#define GCAOFF _IO('G', 4) -#define GCMAP _IOWR('G', 5, int) -#define GCUNMAP _IOWR('G', 6, int) -#define GCMAP_HPUX _IO('G', 5) -#define GCUNMAP_HPUX _IO('G', 6) -#define GCLOCK _IO('G', 7) -#define GCUNLOCK _IO('G', 8) -#define GCLOCK_MINIMUM _IO('G', 9) -#define GCUNLOCK_MINIMUM _IO('G', 10) -#define GCSTATIC_CMAP _IO('G', 11) -#define GCVARIABLE_CMAP _IO('G', 12) -#define GCTERM _IOWR('G',20,int) /* multi-headed Tomcat */ -#define GCDESCRIBE _IOR('G', 21, struct grf_fbinfo) -#define GCFASTLOCK _IO('G', 26) - #endif /* __ASM_PARISC_GRFIOCTL_H */ - -- GitLab From 567b35159e76997e95b643b9a8a5d9d2198f2522 Mon Sep 17 00:00:00 2001 From: John David Anglin Date: Sun, 26 Feb 2023 18:03:33 +0000 Subject: [PATCH 4480/5631] parisc: Cleanup mmap implementation regarding color alignment This change simplifies the randomization of file mapping regions. It reworks the code to remove duplication. The flow is now similar to that for mips. Finally, we consistently use the do_color_align variable to determine when color alignment is needed. Tested on rp3440. Signed-off-by: John David Anglin Signed-off-by: Helge Deller --- arch/parisc/kernel/sys_parisc.c | 166 ++++++++++++-------------------- 1 file changed, 63 insertions(+), 103 deletions(-) diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 09a34b07f02e..39acccabf2ed 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -25,31 +25,26 @@ #include #include -/* we construct an artificial offset for the mapping based on the physical - * address of the kernel mapping variable */ -#define GET_LAST_MMAP(filp) \ - (filp ? ((unsigned long) filp->f_mapping) >> 8 : 0UL) -#define SET_LAST_MMAP(filp, val) \ - { /* nothing */ } - -static int get_offset(unsigned int last_mmap) -{ - return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT; -} +/* + * Construct an artificial page offset for the mapping based on the physical + * address of the kernel file mapping variable. + */ +#define GET_FILP_PGOFF(filp) \ + (filp ? (((unsigned long) filp->f_mapping) >> 8) \ + & ((SHM_COLOUR-1) >> PAGE_SHIFT) : 0UL) -static unsigned long shared_align_offset(unsigned int last_mmap, +static unsigned long shared_align_offset(unsigned long filp_pgoff, unsigned long pgoff) { - return (get_offset(last_mmap) + pgoff) << PAGE_SHIFT; + return (filp_pgoff + pgoff) << PAGE_SHIFT; } static inline unsigned long COLOR_ALIGN(unsigned long addr, - unsigned int last_mmap, unsigned long pgoff) + unsigned long filp_pgoff, unsigned long pgoff) { unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1); unsigned long off = (SHM_COLOUR-1) & - (shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT); - + shared_align_offset(filp_pgoff, pgoff); return base + off; } @@ -98,126 +93,91 @@ static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) return PAGE_ALIGN(STACK_TOP - stack_base); } +enum mmap_allocation_direction {UP, DOWN}; -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +static unsigned long arch_get_unmapped_area_common(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags, enum mmap_allocation_direction dir) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; - unsigned long task_size = TASK_SIZE; - int do_color_align, last_mmap; + unsigned long filp_pgoff; + int do_color_align; struct vm_unmapped_area_info info; - if (len > task_size) + if (unlikely(len > TASK_SIZE)) return -ENOMEM; do_color_align = 0; if (filp || (flags & MAP_SHARED)) do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); + filp_pgoff = GET_FILP_PGOFF(filp); if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) + /* Even MAP_FIXED mappings must reside within TASK_SIZE */ + if (TASK_SIZE - len < addr) + return -EINVAL; + + if ((flags & MAP_SHARED) && filp && + (addr - shared_align_offset(filp_pgoff, pgoff)) & (SHM_COLOUR - 1)) return -EINVAL; - goto found_addr; + return addr; } if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); + if (do_color_align) + addr = COLOR_ALIGN(addr, filp_pgoff, pgoff); else addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); - if (task_size - len >= addr && + if (TASK_SIZE - len >= addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) - goto found_addr; + return addr; } - info.flags = 0; info.length = len; + info.align_mask = do_color_align ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; + info.align_offset = shared_align_offset(filp_pgoff, pgoff); + + if (dir == DOWN) { + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + return addr; + VM_BUG_ON(addr != -ENOMEM); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + } + + info.flags = 0; info.low_limit = mm->mmap_legacy_base; info.high_limit = mmap_upper_limit(NULL); - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); - - return addr; + return vm_unmapped_area(&info); } -unsigned long -arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - const unsigned long len, const unsigned long pgoff, - const unsigned long flags) +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) { - struct vm_area_struct *vma, *prev; - struct mm_struct *mm = current->mm; - unsigned long addr = addr0; - int do_color_align, last_mmap; - struct vm_unmapped_area_info info; - - /* requested length too big for entire address space */ - if (len > TASK_SIZE) - return -ENOMEM; - - do_color_align = 0; - if (filp || (flags & MAP_SHARED)) - do_color_align = 1; - last_mmap = GET_LAST_MMAP(filp); - - if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && last_mmap && - (addr - shared_align_offset(last_mmap, pgoff)) - & (SHM_COLOUR - 1)) - return -EINVAL; - goto found_addr; - } - - /* requesting a specific address */ - if (addr) { - if (do_color_align && last_mmap) - addr = COLOR_ALIGN(addr, last_mmap, pgoff); - else - addr = PAGE_ALIGN(addr); - - vma = find_vma_prev(mm, addr, &prev); - if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vm_start_gap(vma)) && - (!prev || addr >= vm_end_gap(prev))) - goto found_addr; - } - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; - info.low_limit = PAGE_SIZE; - info.high_limit = mm->mmap_base; - info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; - info.align_offset = shared_align_offset(last_mmap, pgoff); - addr = vm_unmapped_area(&info); - if (!(addr & ~PAGE_MASK)) - goto found_addr; - VM_BUG_ON(addr != -ENOMEM); - - /* - * A failed mmap() very likely causes application failure, - * so fall back to the bottom-up function here. This scenario - * can happen with large stack limits and large mmap() - * allocations. - */ - return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); - -found_addr: - if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) - SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, UP); +} - return addr; +unsigned long arch_get_unmapped_area_topdown(struct file *filp, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + return arch_get_unmapped_area_common(filp, + addr, len, pgoff, flags, DOWN); } static int mmap_is_legacy(void) -- GitLab From 6e3220ba3323a2c24be834aebf5d6e9f89d0993f Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 3 May 2023 16:39:56 +0200 Subject: [PATCH 4481/5631] parisc: Fix argument pointer in real64_call_asm() Fix the argument pointer (ap) to point to real-mode memory instead of virtual memory. It's interesting that this issue hasn't shown up earlier, as this could have happened with any 64-bit PDC ROM code. I just noticed it because I suddenly faced a HPMC while trying to execute the 64-bit STI ROM code of an Visualize-FXe graphics card for the STI text console. Signed-off-by: Helge Deller Cc: --- arch/parisc/kernel/real2.S | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S index 4dc12c4c0980..509d18b8e0e6 100644 --- a/arch/parisc/kernel/real2.S +++ b/arch/parisc/kernel/real2.S @@ -235,9 +235,6 @@ ENTRY_CFI(real64_call_asm) /* save fn */ copy %arg2, %r31 - /* set up the new ap */ - ldo 64(%arg1), %r29 - /* load up the arg registers from the saved arg area */ /* 32-bit calling convention passes first 4 args in registers */ ldd 0*REG_SZ(%arg1), %arg0 /* note overwriting arg0 */ @@ -249,7 +246,9 @@ ENTRY_CFI(real64_call_asm) ldd 7*REG_SZ(%arg1), %r19 ldd 1*REG_SZ(%arg1), %arg1 /* do this one last! */ + /* set up real-mode stack and real-mode ap */ tophys_r1 %sp + ldo -16(%sp), %r29 /* Reference param save area */ b,l rfi_virt2real,%r2 nop -- GitLab From 1616d6c3717bae9041a4240d381ec56ccdaafedc Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 3 May 2023 18:57:33 +0300 Subject: [PATCH 4482/5631] nvme-pci: add NVME_QUIRK_BOGUS_NID for HS-SSD-FUTURE 2048G Add a quirk to fix HS-SSD-FUTURE 2048G SSD drives reporting duplicate nsids. Link: https://bugzilla.kernel.org/show_bug.cgi?id=217384 Reported-by: Andrey God Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 593f86323e25..d8b660daf7c2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3433,6 +3433,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1d97, 0x2269), /* Lexar NM760 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), -- GitLab From bd375feeaf3408ed00e08c3bc918d6be15f691ad Mon Sep 17 00:00:00 2001 From: Hristo Venev Date: Tue, 25 Apr 2023 22:58:54 +0300 Subject: [PATCH 4483/5631] nvme-pci: add quirk for missing secondary temperature thresholds On Kingston KC3000 and Kingston FURY Renegade (both have the same PCI IDs) accessing temp3_{min,max} fails with an invalid field error (note that there is no problem setting the thresholds for temp1). This contradicts the NVM Express Base Specification 2.0b, page 292: The over temperature threshold and under temperature threshold features shall be implemented for all implemented temperature sensors (i.e., all Temperature Sensor fields that report a non-zero value). Define NVME_QUIRK_NO_SECONDARY_TEMP_THRESH that disables the thresholds for all but the composite temperature and set it for this device. Signed-off-by: Hristo Venev Reviewed-by: Guenter Roeck Signed-off-by: Christoph Hellwig --- drivers/nvme/host/hwmon.c | 4 +++- drivers/nvme/host/nvme.h | 5 +++++ drivers/nvme/host/pci.c | 2 ++ 3 files changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 9e6e56c20ec9..316f3e4ca7cc 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -163,7 +163,9 @@ static umode_t nvme_hwmon_is_visible(const void *_data, case hwmon_temp_max: case hwmon_temp_min: if ((!channel && data->ctrl->wctemp) || - (channel && data->log->temp_sensor[channel - 1])) { + (channel && data->log->temp_sensor[channel - 1] && + !(data->ctrl->quirks & + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH))) { if (data->ctrl->quirks & NVME_QUIRK_NO_TEMP_THRESH_CHANGE) return 0444; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index bf46f122e9e1..a2d4f59e0535 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -149,6 +149,11 @@ enum nvme_quirks { * Reports garbage in the namespace identifiers (eui64, nguid, uuid). */ NVME_QUIRK_BOGUS_NID = (1 << 18), + + /* + * No temperature thresholds for channels other than 0 (Composite). + */ + NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d8b660daf7c2..18ca1e3ae070 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3401,6 +3401,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(0x2646, 0x5013), /* Kingston KC3000, Kingston FURY Renegade */ + .driver_data = NVME_QUIRK_NO_SECONDARY_TEMP_THRESH, }, { PCI_DEVICE(0x2646, 0x5018), /* KINGSTON OM8SFP4xxxxP OS21012 NVMe SSD */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x5016), /* KINGSTON OM3PGP4xxxxP OS21011 NVMe SSD */ -- GitLab From 3710e2b056cb92ad816e4d79fa54a6a5b6ad8cbd Mon Sep 17 00:00:00 2001 From: Adrian Huang Date: Fri, 21 Apr 2023 16:08:00 +0800 Subject: [PATCH 4484/5631] nvme-pci: clamp max_hw_sectors based on DMA optimized limitation When running the fio test on a 448-core AMD server + a NVME disk, a soft lockup or a hard lockup call trace is shown: [soft lockup] watchdog: BUG: soft lockup - CPU#126 stuck for 23s! [swapper/126:0] RIP: 0010:_raw_spin_unlock_irqrestore+0x21/0x50 ... Call Trace: fq_flush_timeout+0x7d/0xd0 ? __pfx_fq_flush_timeout+0x10/0x10 call_timer_fn+0x2e/0x150 run_timer_softirq+0x48a/0x560 ? __pfx_fq_flush_timeout+0x10/0x10 ? clockevents_program_event+0xaf/0x130 __do_softirq+0xf1/0x335 irq_exit_rcu+0x9f/0xd0 sysvec_apic_timer_interrupt+0xb4/0xd0 asm_sysvec_apic_timer_interrupt+0x1f/0x30 ... Obvisouly, fq_flush_timeout spends over 20 seconds. Here is ftrace log: | fq_flush_timeout() { | fq_ring_free() { | put_pages_list() { 0.170 us | free_unref_page_list(); 0.810 us | } | free_iova_fast() { | free_iova() { * 85622.66 us | _raw_spin_lock_irqsave(); 2.860 us | remove_iova(); 0.600 us | _raw_spin_unlock_irqrestore(); 0.470 us | lock_info_report(); 2.420 us | free_iova_mem.part.0(); * 85638.27 us | } * 85638.84 us | } | put_pages_list() { 0.230 us | free_unref_page_list(); 0.470 us | } ... ... $ 31017069 us | } Most of cores are under lock contention for acquiring iova_rbtree_lock due to the iova flush queue mechanism. [hard lockup] NMI watchdog: Watchdog detected hard LOCKUP on cpu 351 RIP: 0010:native_queued_spin_lock_slowpath+0x2d8/0x330 Call Trace: _raw_spin_lock_irqsave+0x4f/0x60 free_iova+0x27/0xd0 free_iova_fast+0x4d/0x1d0 fq_ring_free+0x9b/0x150 iommu_dma_free_iova+0xb4/0x2e0 __iommu_dma_unmap+0x10b/0x140 iommu_dma_unmap_sg+0x90/0x110 dma_unmap_sg_attrs+0x4a/0x50 nvme_unmap_data+0x5d/0x120 [nvme] nvme_pci_complete_batch+0x77/0xc0 [nvme] nvme_irq+0x2ee/0x350 [nvme] ? __pfx_nvme_pci_complete_batch+0x10/0x10 [nvme] __handle_irq_event_percpu+0x53/0x1a0 handle_irq_event_percpu+0x19/0x60 handle_irq_event+0x3d/0x60 handle_edge_irq+0xb3/0x210 __common_interrupt+0x7f/0x150 common_interrupt+0xc5/0xf0 asm_common_interrupt+0x2b/0x40 ... ftrace shows fq_ring_free spends over 10 seconds [1]. Again, most of cores are under lock contention for acquiring iova_rbtree_lock due to the iova flush queue mechanism. [Root Cause] The root cause is that the max_hw_sectors_kb of nvme disk (mdts=10) is 4096kb, which streaming DMA mappings cannot benefit from the scalable IOVA mechanism introduced by the commit 9257b4a206fc ("iommu/iova: introduce per-cpu caching to iova allocation") if the length is greater than 128kb. To fix the lock contention issue, clamp max_hw_sectors based on DMA optimized limitation in order to leverage scalable IOVA mechanism. Note: The issue does not happen with another NVME disk (mdts = 5 and max_hw_sectors_kb = 128) [1] https://gist.github.com/AdrianHuang/bf8ec7338204837631fbdaed25d19cc4 Suggested-by: Keith Busch Reported-and-tested-by: Jiwei Sun Signed-off-by: Adrian Huang Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 18ca1e3ae070..922ffe4e2822 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2956,7 +2956,7 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, * over a single page. */ dev->ctrl.max_hw_sectors = min_t(u32, - NVME_MAX_KB_SZ << 1, dma_max_mapping_size(&pdev->dev) >> 9); + NVME_MAX_KB_SZ << 1, dma_opt_mapping_size(&pdev->dev) >> 9); dev->ctrl.max_segments = NVME_MAX_SEGS; /* -- GitLab From 4f94559f40ad06d627c0fdfc3319cec778a2845b Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Wed, 3 May 2023 16:01:14 +0200 Subject: [PATCH 4485/5631] tracing: Fix permissions for the buffer_percent file This file defines both read and write operations, yet it is being created as read-only. This means that it can't be written to without the CAP_DAC_OVERRIDE capability. Fix the permissions to allow root to write to it without the need to override DAC perms. Link: https://lore.kernel.org/linux-trace-kernel/20230503140114.3280002-1-omosnace@redhat.com Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Fixes: 03329f993978 ("tracing: Add tracefs file buffer_percentage") Signed-off-by: Ondrej Mosnacek Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 076d893d2965..b9be1af23a73 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9660,7 +9660,7 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) tr->buffer_percent = 50; - trace_create_file("buffer_percent", TRACE_MODE_READ, d_tracer, + trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer, tr, &buffer_percent_fops); create_trace_options_dir(tr); -- GitLab From 6014bc27561f2cc63e0acc18adbc4ed810834e32 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 28 Apr 2023 12:55:10 -0700 Subject: [PATCH 4486/5631] x86-64: make access_ok() independent of LAM The linear address masking (LAM) code made access_ok() more complicated, in that it now needs to untag the address in order to verify the access range. See commit 74c228d20a51 ("x86/uaccess: Provide untagged_addr() and remove tags before address check"). We were able to avoid that overhead in the get_user/put_user code paths by simply using the sign bit for the address check, and depending on the GP fault if the address was non-canonical, which made it all independent of LAM. And we can do the same thing for access_ok(): simply check that the user pointer range has the high bit clear. No need to bother with any address bit masking. In fact, we can go a bit further, and just check the starting address for known small accesses ranges: any accesses that overflow will still be in the non-canonical area and will still GP fault. To still make syzkaller catch any potentially unchecked user addresses, we'll continue to warn about GP faults that are caused by accesses in the non-canonical range. But we'll limit that to purely "high bit set and past the one-page 'slop' area". We could probably just do that "check only starting address" for any arbitrary range size: realistically all kernel accesses to user space will be done starting at the low address. But let's leave that kind of optimization for later. As it is, this already allows us to generate simpler code and not worry about any tag bits in the address. The one thing to look out for is the GUP address check: instead of actually copying data in the virtual address range (and thus bad addresses being caught by the GP fault), GUP will look up the page tables manually. As a result, the page table limits need to be checked, and that was previously implicitly done by the access_ok(). With the relaxed access_ok() check, we need to just do an explicit check for TASK_SIZE_MAX in the GUP code instead. The GUP code already needs to do the tag bit unmasking anyway, so there this is all very straightforward, and there are no LAM issues. Cc: Kirill A. Shutemov Cc: Dave Hansen Cc: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess.h | 39 +++++++++++++++++++++++++++++---- arch/x86/mm/extable.c | 40 +++++++++++++++++++++++++++++----- mm/gup.c | 2 ++ 3 files changed, 71 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 457e814712af..123135d60f72 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -75,6 +75,34 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, #define untagged_addr(addr) (addr) #endif +#ifdef CONFIG_X86_64 +/* + * On x86-64, we may have tag bits in the user pointer. Rather than + * mask them off, just change the rules for __access_ok(). + * + * Make the rule be that 'ptr+size' must not overflow, and must not + * have the high bit set. Compilers generally understand about + * unsigned overflow and the CF bit and generate reasonable code for + * this. Although it looks like the combination confuses at least + * clang (and instead of just doing an "add" followed by a test of + * SF and CF, you'll see that unnecessary comparison). + * + * For the common case of small sizes that can be checked at compile + * time, don't even bother with the addition, and just check that the + * base pointer is ok. + */ +static inline bool __access_ok(const void __user *ptr, unsigned long size) +{ + if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { + return (long)ptr >= 0; + } else { + unsigned long sum = size + (unsigned long)ptr; + return (long) sum >= 0 && sum >= (unsigned long)ptr; + } +} +#define __access_ok __access_ok +#endif + /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check @@ -91,11 +119,14 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, * * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. + * + * This should not be x86-specific. The only odd things out here is + * the WARN_ON_IN_IRQ(), which doesn't exist in the generic version. */ -#define access_ok(addr, size) \ -({ \ - WARN_ON_IN_IRQ(); \ - likely(__access_ok(untagged_addr(addr), size)); \ +#define access_ok(addr, size) \ +({ \ + WARN_ON_IN_IRQ(); \ + likely(__access_ok(addr, size)); \ }) #include diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 60814e110a54..8d38dedadbb1 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -130,10 +130,36 @@ static bool ex_handler_fprestore(const struct exception_table_entry *fixup, return true; } +/* + * On x86-64, we end up being imprecise with 'access_ok()', and allow + * non-canonical user addresses to make the range comparisons simpler, + * and to not have to worry about LAM being enabled. + * + * In fact, we allow up to one page of "slop" at the sign boundary, + * which means that we can do access_ok() by just checking the sign + * of the pointer for the common case of having a small access size. + */ +static bool gp_fault_address_ok(unsigned long fault_address) +{ +#ifdef CONFIG_X86_64 + /* Is it in the "user space" part of the non-canonical space? */ + if ((long) fault_address >= 0) + return true; + + /* .. or just above it? */ + fault_address -= PAGE_SIZE; + if ((long) fault_address >= 0) + return true; +#endif + return false; +} + static bool ex_handler_uaccess(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr) + struct pt_regs *regs, int trapnr, + unsigned long fault_address) { - WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?"); + WARN_ONCE(trapnr == X86_TRAP_GP && !gp_fault_address_ok(fault_address), + "General protection fault in user access. Non-canonical address?"); return ex_handler_default(fixup, regs); } @@ -189,10 +215,12 @@ static bool ex_handler_imm_reg(const struct exception_table_entry *fixup, } static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, - struct pt_regs *regs, int trapnr, int reg, int imm) + struct pt_regs *regs, int trapnr, + unsigned long fault_address, + int reg, int imm) { regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg); - return ex_handler_uaccess(fixup, regs, trapnr); + return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } int ex_get_fixup_type(unsigned long ip) @@ -238,7 +266,7 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, case EX_TYPE_FAULT_MCE_SAFE: return ex_handler_fault(e, regs, trapnr); case EX_TYPE_UACCESS: - return ex_handler_uaccess(e, regs, trapnr); + return ex_handler_uaccess(e, regs, trapnr, fault_addr); case EX_TYPE_COPY: return ex_handler_copy(e, regs, trapnr); case EX_TYPE_CLEAR_FS: @@ -269,7 +297,7 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, case EX_TYPE_FAULT_SGX: return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: - return ex_handler_ucopy_len(e, regs, trapnr, reg, imm); + return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); } diff --git a/mm/gup.c b/mm/gup.c index ff689c88a357..bbe416236593 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2970,6 +2970,8 @@ static int internal_get_user_pages_fast(unsigned long start, len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return 0; + if (end > TASK_SIZE_MAX) + return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; -- GitLab From 6ccdc91d6af922f3ded5de494ff27daedeb6d6c9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 2 May 2023 12:35:01 -0700 Subject: [PATCH 4487/5631] x86: mm: remove architecture-specific 'access_ok()' define There's already a generic definition of 'access_ok()' in the asm-generic/access_ok.h header file, and the only difference bwteen that and the x86-specific one is the added check for WARN_ON_IN_IRQ(). And it turns out that the reason for that check is long gone: it used to use a "user_addr_max()" inline function that depended on the current thread, and caused problems in non-thread contexts. For details, see commits 7c4788950ba5 ("x86/uaccess, sched/preempt: Verify access_ok() context") and in particular commit ae31fe51a3cc ("perf/x86: Restore TASK_SIZE check on frame pointer") about how and why this came to be. But that "current task" issue was removed in the big set_fs() removal by Christoph Hellwig in commit 47058bb54b57 ("x86: remove address space overrides using set_fs()"). So the reason for the test and the architecture-specific access_ok() define no longer exists, and is actually harmful these days. For example, it led various 'copy_from_user_nmi()' games (eg using __range_not_ok() instead, and then later converted to __access_ok() when that became ok). And that in turn meant that LAM was broken for the frame following before this series, because __access_ok() used to not do the address untagging. Accessing user state still needs care in many contexts, but access_ok() is not the place for this test. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds torvalds@linux-foundation.org> --- arch/x86/include/asm/uaccess.h | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 123135d60f72..cad17e11aa83 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -16,14 +16,6 @@ #include #include -#ifdef CONFIG_DEBUG_ATOMIC_SLEEP -static inline bool pagefault_disabled(void); -# define WARN_ON_IN_IRQ() \ - WARN_ON_ONCE(!in_task() && !pagefault_disabled()) -#else -# define WARN_ON_IN_IRQ() -#endif - #ifdef CONFIG_ADDRESS_MASKING /* * Mask out tag bits from the address. @@ -103,32 +95,6 @@ static inline bool __access_ok(const void __user *ptr, unsigned long size) #define __access_ok __access_ok #endif -/** - * access_ok - Checks if a user space pointer is valid - * @addr: User space pointer to start of block to check - * @size: Size of block to check - * - * Context: User context only. This function may sleep if pagefaults are - * enabled. - * - * Checks if a pointer to a block of memory in user space is valid. - * - * Note that, depending on architecture, this function probably just - * checks that the pointer is in the user space range - after calling - * this function, memory access functions may still return -EFAULT. - * - * Return: true (nonzero) if the memory block may be valid, false (zero) - * if it is definitely invalid. - * - * This should not be x86-specific. The only odd things out here is - * the WARN_ON_IN_IRQ(), which doesn't exist in the generic version. - */ -#define access_ok(addr, size) \ -({ \ - WARN_ON_IN_IRQ(); \ - likely(__access_ok(addr, size)); \ -}) - #include extern int __get_user_1(void); -- GitLab From b9bd9f605c4a6f04a83e6640a7d1d6dda80f17ca Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 2 May 2023 16:39:59 -0700 Subject: [PATCH 4488/5631] x86: uaccess: move 32-bit and 64-bit parts into proper header The x86 file has grown features that are specific to x86-64 like LAM support and the related access_ok() changes. They really should be in the file and not pollute the generic x86 header. Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess.h | 87 ++----------------------------- arch/x86/include/asm/uaccess_32.h | 3 ++ arch/x86/include/asm/uaccess_64.h | 77 ++++++++++++++++++++++++++- 3 files changed, 82 insertions(+), 85 deletions(-) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index cad17e11aa83..8bae40a66282 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -16,83 +16,10 @@ #include #include -#ifdef CONFIG_ADDRESS_MASKING -/* - * Mask out tag bits from the address. - * - * Magic with the 'sign' allows to untag userspace pointer without any branches - * while leaving kernel addresses intact. - */ -static inline unsigned long __untagged_addr(unsigned long addr) -{ - long sign; - - /* - * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation - * in alternative instructions. The relocation gets wrong when gets - * copied to the target place. - */ - asm (ALTERNATIVE("", - "sar $63, %[sign]\n\t" /* user_ptr ? 0 : -1UL */ - "or %%gs:tlbstate_untag_mask, %[sign]\n\t" - "and %[sign], %[addr]\n\t", X86_FEATURE_LAM) - : [addr] "+r" (addr), [sign] "=r" (sign) - : "m" (tlbstate_untag_mask), "[sign]" (addr)); - - return addr; -} - -#define untagged_addr(addr) ({ \ - unsigned long __addr = (__force unsigned long)(addr); \ - (__force __typeof__(addr))__untagged_addr(__addr); \ -}) - -static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, - unsigned long addr) -{ - long sign = addr >> 63; - - mmap_assert_locked(mm); - addr &= (mm)->context.untag_mask | sign; - - return addr; -} - -#define untagged_addr_remote(mm, addr) ({ \ - unsigned long __addr = (__force unsigned long)(addr); \ - (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ -}) - +#ifdef CONFIG_X86_32 +# include #else -#define untagged_addr(addr) (addr) -#endif - -#ifdef CONFIG_X86_64 -/* - * On x86-64, we may have tag bits in the user pointer. Rather than - * mask them off, just change the rules for __access_ok(). - * - * Make the rule be that 'ptr+size' must not overflow, and must not - * have the high bit set. Compilers generally understand about - * unsigned overflow and the CF bit and generate reasonable code for - * this. Although it looks like the combination confuses at least - * clang (and instead of just doing an "add" followed by a test of - * SF and CF, you'll see that unnecessary comparison). - * - * For the common case of small sizes that can be checked at compile - * time, don't even bother with the addition, and just check that the - * base pointer is ok. - */ -static inline bool __access_ok(const void __user *ptr, unsigned long size) -{ - if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { - return (long)ptr >= 0; - } else { - unsigned long sum = size + (unsigned long)ptr; - return (long) sum >= 0 && sum >= (unsigned long)ptr; - } -} -#define __access_ok __access_ok +# include #endif #include @@ -583,14 +510,6 @@ extern struct movsl_mask { #define ARCH_HAS_NOCACHE_UACCESS 1 -#ifdef CONFIG_X86_32 -unsigned long __must_check clear_user(void __user *mem, unsigned long len); -unsigned long __must_check __clear_user(void __user *mem, unsigned long len); -# include -#else -# include -#endif - /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 388a40660c7b..40379a1adbb8 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -33,4 +33,7 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, return __copy_from_user_ll_nocache_nozero(to, from, n); } +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); + #endif /* _ASM_X86_UACCESS_32_H */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index c972bd21aa23..20411e69e67f 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -12,6 +12,81 @@ #include #include +#ifdef CONFIG_ADDRESS_MASKING +/* + * Mask out tag bits from the address. + * + * Magic with the 'sign' allows to untag userspace pointer without any branches + * while leaving kernel addresses intact. + */ +static inline unsigned long __untagged_addr(unsigned long addr) +{ + long sign; + + /* + * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation + * in alternative instructions. The relocation gets wrong when gets + * copied to the target place. + */ + asm (ALTERNATIVE("", + "sar $63, %[sign]\n\t" /* user_ptr ? 0 : -1UL */ + "or %%gs:tlbstate_untag_mask, %[sign]\n\t" + "and %[sign], %[addr]\n\t", X86_FEATURE_LAM) + : [addr] "+r" (addr), [sign] "=r" (sign) + : "m" (tlbstate_untag_mask), "[sign]" (addr)); + + return addr; +} + +#define untagged_addr(addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr(__addr); \ +}) + +static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, + unsigned long addr) +{ + long sign = addr >> 63; + + mmap_assert_locked(mm); + addr &= (mm)->context.untag_mask | sign; + + return addr; +} + +#define untagged_addr_remote(mm, addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ +}) + +#endif + +/* + * On x86-64, we may have tag bits in the user pointer. Rather than + * mask them off, just change the rules for __access_ok(). + * + * Make the rule be that 'ptr+size' must not overflow, and must not + * have the high bit set. Compilers generally understand about + * unsigned overflow and the CF bit and generate reasonable code for + * this. Although it looks like the combination confuses at least + * clang (and instead of just doing an "add" followed by a test of + * SF and CF, you'll see that unnecessary comparison). + * + * For the common case of small sizes that can be checked at compile + * time, don't even bother with the addition, and just check that the + * base pointer is ok. + */ +static inline bool __access_ok(const void __user *ptr, unsigned long size) +{ + if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { + return (long)ptr >= 0; + } else { + unsigned long sum = size + (unsigned long)ptr; + return (long) sum >= 0 && sum >= (unsigned long)ptr; + } +} +#define __access_ok __access_ok + /* * Copy To/From Userspace */ @@ -106,7 +181,7 @@ static __always_inline __must_check unsigned long __clear_user(void __user *addr static __always_inline unsigned long clear_user(void __user *to, unsigned long n) { - if (access_ok(to, n)) + if (__access_ok(to, n)) return __clear_user(to, n); return n; } -- GitLab From 1dbc0a9515fdf1f0b9d6c9b1954a347c94e5f5f9 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 3 May 2023 09:38:58 -0700 Subject: [PATCH 4489/5631] x86: mm: remove 'sign' games from LAM untagged_addr*() macros The intent of the sign games was to not modify kernel addresses when untagging them. However, that had two issues: (a) it didn't actually work as intended, since the mask was calculated as 'addr >> 63' on an _unsigned_ address. So instead of getting a mask of all ones for kernel addresses, you just got '1'. (b) untagging a kernel address isn't actually a valid operation anyway. Now, (a) had originally been true for both 'untagged_addr()' and the remote version of it, but had accidentally been fixed for the regular version of untagged_addr() by commit e0bddc19ba95 ("x86/mm: Reduce untagged_addr() overhead for systems without LAM"). That one rewrote the shift to be part of the alternative asm code, and in the process changed the unsigned shift into a signed 'sar' instruction. And while it is true that we don't want to turn what looks like a kernel address into a user address by masking off the high bit, that doesn't need these sign masking games - all it needs is that the mm context 'untag_mask' value has the high bit set. Which it always does. So simplify the code by just removing the superfluous (and in the case of untagged_addr_remote(), still buggy) sign bit games in the address masking. Acked-by: Dave Hansen Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess_64.h | 18 +++--------------- 1 file changed, 3 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 20411e69e67f..e5b23e917f41 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -15,25 +15,17 @@ #ifdef CONFIG_ADDRESS_MASKING /* * Mask out tag bits from the address. - * - * Magic with the 'sign' allows to untag userspace pointer without any branches - * while leaving kernel addresses intact. */ static inline unsigned long __untagged_addr(unsigned long addr) { - long sign; - /* * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation * in alternative instructions. The relocation gets wrong when gets * copied to the target place. */ asm (ALTERNATIVE("", - "sar $63, %[sign]\n\t" /* user_ptr ? 0 : -1UL */ - "or %%gs:tlbstate_untag_mask, %[sign]\n\t" - "and %[sign], %[addr]\n\t", X86_FEATURE_LAM) - : [addr] "+r" (addr), [sign] "=r" (sign) - : "m" (tlbstate_untag_mask), "[sign]" (addr)); + "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM) + : [addr] "+r" (addr) : "m" (tlbstate_untag_mask)); return addr; } @@ -46,12 +38,8 @@ static inline unsigned long __untagged_addr(unsigned long addr) static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr) { - long sign = addr >> 63; - mmap_assert_locked(mm); - addr &= (mm)->context.untag_mask | sign; - - return addr; + return addr & (mm)->context.untag_mask; } #define untagged_addr_remote(mm, addr) ({ \ -- GitLab From 798dec3304f69b97cdf78f485473fb5653fc22d1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 3 May 2023 10:13:41 -0700 Subject: [PATCH 4490/5631] x86-64: mm: clarify the 'positive addresses' user address rules Dave Hansen found the "(long) addr >= 0" code in the x86-64 access_ok checks somewhat confusing, and suggested using a helper to clarify what the code is doing. So this does exactly that: clarifying what the sign bit check is all about, by adding a helper macro that makes it clear what it is testing. This also adds some explicit comments talking about how even with LAM enabled, any addresses with the sign bit will still GP-fault in the non-canonical region just above the sign bit. This is all what allows us to do the user address checks with just the sign bit, and furthermore be a bit cavalier about accesses that might be done with an additional offset even past that point. (And yes, this talks about 'positive' even though zero is also a valid user address and so technically we should call them 'non-negative'. But I don't think using 'non-negative' ends up being more understandable). Suggested-by: Dave Hansen Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess_64.h | 44 ++++++++++++++++++++++--------- arch/x86/mm/extable.c | 4 +-- 2 files changed, 33 insertions(+), 15 deletions(-) diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index e5b23e917f41..81b826d3b753 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -50,27 +50,45 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, #endif /* - * On x86-64, we may have tag bits in the user pointer. Rather than - * mask them off, just change the rules for __access_ok(). + * The virtual address space space is logically divided into a kernel + * half and a user half. When cast to a signed type, user pointers + * are positive and kernel pointers are negative. + */ +#define valid_user_address(x) ((long)(x) >= 0) + +/* + * User pointers can have tag bits on x86-64. This scheme tolerates + * arbitrary values in those bits rather then masking them off. + * + * Enforce two rules: + * 1. 'ptr' must be in the user half of the address space + * 2. 'ptr+size' must not overflow into kernel addresses + * + * Note that addresses around the sign change are not valid addresses, + * and will GP-fault even with LAM enabled if the sign bit is set (see + * "CR3.LAM_SUP" that can narrow the canonicality check if we ever + * enable it, but not remove it entirely). + * + * So the "overflow into kernel addresses" does not imply some sudden + * exact boundary at the sign bit, and we can allow a lot of slop on the + * size check. * - * Make the rule be that 'ptr+size' must not overflow, and must not - * have the high bit set. Compilers generally understand about - * unsigned overflow and the CF bit and generate reasonable code for - * this. Although it looks like the combination confuses at least - * clang (and instead of just doing an "add" followed by a test of - * SF and CF, you'll see that unnecessary comparison). + * In fact, we could probably remove the size check entirely, since + * any kernel accesses will be in increasing address order starting + * at 'ptr', and even if the end might be in kernel space, we'll + * hit the GP faults for non-canonical accesses before we ever get + * there. * - * For the common case of small sizes that can be checked at compile - * time, don't even bother with the addition, and just check that the - * base pointer is ok. + * That's a separate optimization, for now just handle the small + * constant case. */ static inline bool __access_ok(const void __user *ptr, unsigned long size) { if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { - return (long)ptr >= 0; + return valid_user_address(ptr); } else { unsigned long sum = size + (unsigned long)ptr; - return (long) sum >= 0 && sum >= (unsigned long)ptr; + return valid_user_address(sum) && sum >= (unsigned long)ptr; } } #define __access_ok __access_ok diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 8d38dedadbb1..271dcb2deabc 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -143,12 +143,12 @@ static bool gp_fault_address_ok(unsigned long fault_address) { #ifdef CONFIG_X86_64 /* Is it in the "user space" part of the non-canonical space? */ - if ((long) fault_address >= 0) + if (valid_user_address(fault_address)) return true; /* .. or just above it? */ fault_address -= PAGE_SIZE; - if ((long) fault_address >= 0) + if (valid_user_address(fault_address)) return true; #endif return false; -- GitLab From 84822215acd15bd86a7759a835271e63bba83a7b Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 3 May 2023 16:41:02 +0200 Subject: [PATCH 4491/5631] ASoC: codecs: wcd938x: fix accessing regmap on unattached devices The WCD938x comes with three devices on two Linux drivers: 1. RX Soundwire device (wcd938x-sdw.c driver), 2. TX Soundwire device, which is used to access devices via regmap (also wcd938x-sdw.c driver), 3. platform device (wcd938x.c driver) - glue and component master, actually having most of the code using TX Soundwire device regmap. When RX and TX Soundwire devices probe, the component master (platform device) bind tries to write micbias configuration via TX Soundwire regmap. This might happen before TX Soundwire enumerates, so the regmap access fails. On Qualcomm SM8550 board with WCD9385: qcom-soundwire 6d30000.soundwire-controller: Qualcomm Soundwire controller v2.0.0 Registered wcd938x_codec audio-codec: bound sdw:0:0217:010d:00:4 (ops wcd938x_sdw_component_ops) wcd938x_codec audio-codec: bound sdw:0:0217:010d:00:3 (ops wcd938x_sdw_component_ops) qcom-soundwire 6ad0000.soundwire-controller: swrm_wait_for_wr_fifo_avail err write overflow Fix the issue by: 1. Moving the regmap creation from platform device to TX Soundwire device. The regmap settings are moved as-is with one difference: making the wcd938x_regmap_config const. 2. Using regmap in cache only mode till the actual TX Soundwire device enumerates and then sync the regmap cache. Cc: # v3.14+ Signed-off-by: Krzysztof Kozlowski Reviewed-by: Pierre-Louis Bossart Message-Id: <20230503144102.242240-1-krzysztof.kozlowski@linaro.org> Signed-off-by: Mark Brown --- sound/soc/codecs/wcd938x-sdw.c | 1037 +++++++++++++++++++++++++++++++- sound/soc/codecs/wcd938x.c | 1003 +----------------------------- sound/soc/codecs/wcd938x.h | 1 + 3 files changed, 1030 insertions(+), 1011 deletions(-) diff --git a/sound/soc/codecs/wcd938x-sdw.c b/sound/soc/codecs/wcd938x-sdw.c index 33d1b5ffeaeb..402286dfaea4 100644 --- a/sound/soc/codecs/wcd938x-sdw.c +++ b/sound/soc/codecs/wcd938x-sdw.c @@ -161,6 +161,14 @@ EXPORT_SYMBOL_GPL(wcd938x_sdw_set_sdw_stream); static int wcd9380_update_status(struct sdw_slave *slave, enum sdw_slave_status status) { + struct wcd938x_sdw_priv *wcd = dev_get_drvdata(&slave->dev); + + if (wcd->regmap && (status == SDW_SLAVE_ATTACHED)) { + /* Write out any cached changes that happened between probe and attach */ + regcache_cache_only(wcd->regmap, false); + return regcache_sync(wcd->regmap); + } + return 0; } @@ -177,20 +185,1014 @@ static int wcd9380_interrupt_callback(struct sdw_slave *slave, { struct wcd938x_sdw_priv *wcd = dev_get_drvdata(&slave->dev); struct irq_domain *slave_irq = wcd->slave_irq; - struct regmap *regmap = dev_get_regmap(&slave->dev, NULL); u32 sts1, sts2, sts3; do { handle_nested_irq(irq_find_mapping(slave_irq, 0)); - regmap_read(regmap, WCD938X_DIGITAL_INTR_STATUS_0, &sts1); - regmap_read(regmap, WCD938X_DIGITAL_INTR_STATUS_1, &sts2); - regmap_read(regmap, WCD938X_DIGITAL_INTR_STATUS_2, &sts3); + regmap_read(wcd->regmap, WCD938X_DIGITAL_INTR_STATUS_0, &sts1); + regmap_read(wcd->regmap, WCD938X_DIGITAL_INTR_STATUS_1, &sts2); + regmap_read(wcd->regmap, WCD938X_DIGITAL_INTR_STATUS_2, &sts3); } while (sts1 || sts2 || sts3); return IRQ_HANDLED; } +static const struct reg_default wcd938x_defaults[] = { + {WCD938X_ANA_PAGE_REGISTER, 0x00}, + {WCD938X_ANA_BIAS, 0x00}, + {WCD938X_ANA_RX_SUPPLIES, 0x00}, + {WCD938X_ANA_HPH, 0x0C}, + {WCD938X_ANA_EAR, 0x00}, + {WCD938X_ANA_EAR_COMPANDER_CTL, 0x02}, + {WCD938X_ANA_TX_CH1, 0x20}, + {WCD938X_ANA_TX_CH2, 0x00}, + {WCD938X_ANA_TX_CH3, 0x20}, + {WCD938X_ANA_TX_CH4, 0x00}, + {WCD938X_ANA_MICB1_MICB2_DSP_EN_LOGIC, 0x00}, + {WCD938X_ANA_MICB3_DSP_EN_LOGIC, 0x00}, + {WCD938X_ANA_MBHC_MECH, 0x39}, + {WCD938X_ANA_MBHC_ELECT, 0x08}, + {WCD938X_ANA_MBHC_ZDET, 0x00}, + {WCD938X_ANA_MBHC_RESULT_1, 0x00}, + {WCD938X_ANA_MBHC_RESULT_2, 0x00}, + {WCD938X_ANA_MBHC_RESULT_3, 0x00}, + {WCD938X_ANA_MBHC_BTN0, 0x00}, + {WCD938X_ANA_MBHC_BTN1, 0x10}, + {WCD938X_ANA_MBHC_BTN2, 0x20}, + {WCD938X_ANA_MBHC_BTN3, 0x30}, + {WCD938X_ANA_MBHC_BTN4, 0x40}, + {WCD938X_ANA_MBHC_BTN5, 0x50}, + {WCD938X_ANA_MBHC_BTN6, 0x60}, + {WCD938X_ANA_MBHC_BTN7, 0x70}, + {WCD938X_ANA_MICB1, 0x10}, + {WCD938X_ANA_MICB2, 0x10}, + {WCD938X_ANA_MICB2_RAMP, 0x00}, + {WCD938X_ANA_MICB3, 0x10}, + {WCD938X_ANA_MICB4, 0x10}, + {WCD938X_BIAS_CTL, 0x2A}, + {WCD938X_BIAS_VBG_FINE_ADJ, 0x55}, + {WCD938X_LDOL_VDDCX_ADJUST, 0x01}, + {WCD938X_LDOL_DISABLE_LDOL, 0x00}, + {WCD938X_MBHC_CTL_CLK, 0x00}, + {WCD938X_MBHC_CTL_ANA, 0x00}, + {WCD938X_MBHC_CTL_SPARE_1, 0x00}, + {WCD938X_MBHC_CTL_SPARE_2, 0x00}, + {WCD938X_MBHC_CTL_BCS, 0x00}, + {WCD938X_MBHC_MOISTURE_DET_FSM_STATUS, 0x00}, + {WCD938X_MBHC_TEST_CTL, 0x00}, + {WCD938X_LDOH_MODE, 0x2B}, + {WCD938X_LDOH_BIAS, 0x68}, + {WCD938X_LDOH_STB_LOADS, 0x00}, + {WCD938X_LDOH_SLOWRAMP, 0x50}, + {WCD938X_MICB1_TEST_CTL_1, 0x1A}, + {WCD938X_MICB1_TEST_CTL_2, 0x00}, + {WCD938X_MICB1_TEST_CTL_3, 0xA4}, + {WCD938X_MICB2_TEST_CTL_1, 0x1A}, + {WCD938X_MICB2_TEST_CTL_2, 0x00}, + {WCD938X_MICB2_TEST_CTL_3, 0x24}, + {WCD938X_MICB3_TEST_CTL_1, 0x1A}, + {WCD938X_MICB3_TEST_CTL_2, 0x00}, + {WCD938X_MICB3_TEST_CTL_3, 0xA4}, + {WCD938X_MICB4_TEST_CTL_1, 0x1A}, + {WCD938X_MICB4_TEST_CTL_2, 0x00}, + {WCD938X_MICB4_TEST_CTL_3, 0xA4}, + {WCD938X_TX_COM_ADC_VCM, 0x39}, + {WCD938X_TX_COM_BIAS_ATEST, 0xE0}, + {WCD938X_TX_COM_SPARE1, 0x00}, + {WCD938X_TX_COM_SPARE2, 0x00}, + {WCD938X_TX_COM_TXFE_DIV_CTL, 0x22}, + {WCD938X_TX_COM_TXFE_DIV_START, 0x00}, + {WCD938X_TX_COM_SPARE3, 0x00}, + {WCD938X_TX_COM_SPARE4, 0x00}, + {WCD938X_TX_1_2_TEST_EN, 0xCC}, + {WCD938X_TX_1_2_ADC_IB, 0xE9}, + {WCD938X_TX_1_2_ATEST_REFCTL, 0x0A}, + {WCD938X_TX_1_2_TEST_CTL, 0x38}, + {WCD938X_TX_1_2_TEST_BLK_EN1, 0xFF}, + {WCD938X_TX_1_2_TXFE1_CLKDIV, 0x00}, + {WCD938X_TX_1_2_SAR2_ERR, 0x00}, + {WCD938X_TX_1_2_SAR1_ERR, 0x00}, + {WCD938X_TX_3_4_TEST_EN, 0xCC}, + {WCD938X_TX_3_4_ADC_IB, 0xE9}, + {WCD938X_TX_3_4_ATEST_REFCTL, 0x0A}, + {WCD938X_TX_3_4_TEST_CTL, 0x38}, + {WCD938X_TX_3_4_TEST_BLK_EN3, 0xFF}, + {WCD938X_TX_3_4_TXFE3_CLKDIV, 0x00}, + {WCD938X_TX_3_4_SAR4_ERR, 0x00}, + {WCD938X_TX_3_4_SAR3_ERR, 0x00}, + {WCD938X_TX_3_4_TEST_BLK_EN2, 0xFB}, + {WCD938X_TX_3_4_TXFE2_CLKDIV, 0x00}, + {WCD938X_TX_3_4_SPARE1, 0x00}, + {WCD938X_TX_3_4_TEST_BLK_EN4, 0xFB}, + {WCD938X_TX_3_4_TXFE4_CLKDIV, 0x00}, + {WCD938X_TX_3_4_SPARE2, 0x00}, + {WCD938X_CLASSH_MODE_1, 0x40}, + {WCD938X_CLASSH_MODE_2, 0x3A}, + {WCD938X_CLASSH_MODE_3, 0x00}, + {WCD938X_CLASSH_CTRL_VCL_1, 0x70}, + {WCD938X_CLASSH_CTRL_VCL_2, 0x82}, + {WCD938X_CLASSH_CTRL_CCL_1, 0x31}, + {WCD938X_CLASSH_CTRL_CCL_2, 0x80}, + {WCD938X_CLASSH_CTRL_CCL_3, 0x80}, + {WCD938X_CLASSH_CTRL_CCL_4, 0x51}, + {WCD938X_CLASSH_CTRL_CCL_5, 0x00}, + {WCD938X_CLASSH_BUCK_TMUX_A_D, 0x00}, + {WCD938X_CLASSH_BUCK_SW_DRV_CNTL, 0x77}, + {WCD938X_CLASSH_SPARE, 0x00}, + {WCD938X_FLYBACK_EN, 0x4E}, + {WCD938X_FLYBACK_VNEG_CTRL_1, 0x0B}, + {WCD938X_FLYBACK_VNEG_CTRL_2, 0x45}, + {WCD938X_FLYBACK_VNEG_CTRL_3, 0x74}, + {WCD938X_FLYBACK_VNEG_CTRL_4, 0x7F}, + {WCD938X_FLYBACK_VNEG_CTRL_5, 0x83}, + {WCD938X_FLYBACK_VNEG_CTRL_6, 0x98}, + {WCD938X_FLYBACK_VNEG_CTRL_7, 0xA9}, + {WCD938X_FLYBACK_VNEG_CTRL_8, 0x68}, + {WCD938X_FLYBACK_VNEG_CTRL_9, 0x64}, + {WCD938X_FLYBACK_VNEGDAC_CTRL_1, 0xED}, + {WCD938X_FLYBACK_VNEGDAC_CTRL_2, 0xF0}, + {WCD938X_FLYBACK_VNEGDAC_CTRL_3, 0xA6}, + {WCD938X_FLYBACK_CTRL_1, 0x65}, + {WCD938X_FLYBACK_TEST_CTL, 0x00}, + {WCD938X_RX_AUX_SW_CTL, 0x00}, + {WCD938X_RX_PA_AUX_IN_CONN, 0x01}, + {WCD938X_RX_TIMER_DIV, 0x32}, + {WCD938X_RX_OCP_CTL, 0x1F}, + {WCD938X_RX_OCP_COUNT, 0x77}, + {WCD938X_RX_BIAS_EAR_DAC, 0xA0}, + {WCD938X_RX_BIAS_EAR_AMP, 0xAA}, + {WCD938X_RX_BIAS_HPH_LDO, 0xA9}, + {WCD938X_RX_BIAS_HPH_PA, 0xAA}, + {WCD938X_RX_BIAS_HPH_RDACBUFF_CNP2, 0x8A}, + {WCD938X_RX_BIAS_HPH_RDAC_LDO, 0x88}, + {WCD938X_RX_BIAS_HPH_CNP1, 0x82}, + {WCD938X_RX_BIAS_HPH_LOWPOWER, 0x82}, + {WCD938X_RX_BIAS_AUX_DAC, 0xA0}, + {WCD938X_RX_BIAS_AUX_AMP, 0xAA}, + {WCD938X_RX_BIAS_VNEGDAC_BLEEDER, 0x50}, + {WCD938X_RX_BIAS_MISC, 0x00}, + {WCD938X_RX_BIAS_BUCK_RST, 0x08}, + {WCD938X_RX_BIAS_BUCK_VREF_ERRAMP, 0x44}, + {WCD938X_RX_BIAS_FLYB_ERRAMP, 0x40}, + {WCD938X_RX_BIAS_FLYB_BUFF, 0xAA}, + {WCD938X_RX_BIAS_FLYB_MID_RST, 0x14}, + {WCD938X_HPH_L_STATUS, 0x04}, + {WCD938X_HPH_R_STATUS, 0x04}, + {WCD938X_HPH_CNP_EN, 0x80}, + {WCD938X_HPH_CNP_WG_CTL, 0x9A}, + {WCD938X_HPH_CNP_WG_TIME, 0x14}, + {WCD938X_HPH_OCP_CTL, 0x28}, + {WCD938X_HPH_AUTO_CHOP, 0x16}, + {WCD938X_HPH_CHOP_CTL, 0x83}, + {WCD938X_HPH_PA_CTL1, 0x46}, + {WCD938X_HPH_PA_CTL2, 0x50}, + {WCD938X_HPH_L_EN, 0x80}, + {WCD938X_HPH_L_TEST, 0xE0}, + {WCD938X_HPH_L_ATEST, 0x50}, + {WCD938X_HPH_R_EN, 0x80}, + {WCD938X_HPH_R_TEST, 0xE0}, + {WCD938X_HPH_R_ATEST, 0x54}, + {WCD938X_HPH_RDAC_CLK_CTL1, 0x99}, + {WCD938X_HPH_RDAC_CLK_CTL2, 0x9B}, + {WCD938X_HPH_RDAC_LDO_CTL, 0x33}, + {WCD938X_HPH_RDAC_CHOP_CLK_LP_CTL, 0x00}, + {WCD938X_HPH_REFBUFF_UHQA_CTL, 0x68}, + {WCD938X_HPH_REFBUFF_LP_CTL, 0x0E}, + {WCD938X_HPH_L_DAC_CTL, 0x20}, + {WCD938X_HPH_R_DAC_CTL, 0x20}, + {WCD938X_HPH_SURGE_HPHLR_SURGE_COMP_SEL, 0x55}, + {WCD938X_HPH_SURGE_HPHLR_SURGE_EN, 0x19}, + {WCD938X_HPH_SURGE_HPHLR_SURGE_MISC1, 0xA0}, + {WCD938X_HPH_SURGE_HPHLR_SURGE_STATUS, 0x00}, + {WCD938X_EAR_EAR_EN_REG, 0x22}, + {WCD938X_EAR_EAR_PA_CON, 0x44}, + {WCD938X_EAR_EAR_SP_CON, 0xDB}, + {WCD938X_EAR_EAR_DAC_CON, 0x80}, + {WCD938X_EAR_EAR_CNP_FSM_CON, 0xB2}, + {WCD938X_EAR_TEST_CTL, 0x00}, + {WCD938X_EAR_STATUS_REG_1, 0x00}, + {WCD938X_EAR_STATUS_REG_2, 0x08}, + {WCD938X_ANA_NEW_PAGE_REGISTER, 0x00}, + {WCD938X_HPH_NEW_ANA_HPH2, 0x00}, + {WCD938X_HPH_NEW_ANA_HPH3, 0x00}, + {WCD938X_SLEEP_CTL, 0x16}, + {WCD938X_SLEEP_WATCHDOG_CTL, 0x00}, + {WCD938X_MBHC_NEW_ELECT_REM_CLAMP_CTL, 0x00}, + {WCD938X_MBHC_NEW_CTL_1, 0x02}, + {WCD938X_MBHC_NEW_CTL_2, 0x05}, + {WCD938X_MBHC_NEW_PLUG_DETECT_CTL, 0xE9}, + {WCD938X_MBHC_NEW_ZDET_ANA_CTL, 0x0F}, + {WCD938X_MBHC_NEW_ZDET_RAMP_CTL, 0x00}, + {WCD938X_MBHC_NEW_FSM_STATUS, 0x00}, + {WCD938X_MBHC_NEW_ADC_RESULT, 0x00}, + {WCD938X_TX_NEW_AMIC_MUX_CFG, 0x00}, + {WCD938X_AUX_AUXPA, 0x00}, + {WCD938X_LDORXTX_MODE, 0x0C}, + {WCD938X_LDORXTX_CONFIG, 0x10}, + {WCD938X_DIE_CRACK_DIE_CRK_DET_EN, 0x00}, + {WCD938X_DIE_CRACK_DIE_CRK_DET_OUT, 0x00}, + {WCD938X_HPH_NEW_INT_RDAC_GAIN_CTL, 0x40}, + {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L, 0x81}, + {WCD938X_HPH_NEW_INT_RDAC_VREF_CTL, 0x10}, + {WCD938X_HPH_NEW_INT_RDAC_OVERRIDE_CTL, 0x00}, + {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R, 0x81}, + {WCD938X_HPH_NEW_INT_PA_MISC1, 0x22}, + {WCD938X_HPH_NEW_INT_PA_MISC2, 0x00}, + {WCD938X_HPH_NEW_INT_PA_RDAC_MISC, 0x00}, + {WCD938X_HPH_NEW_INT_HPH_TIMER1, 0xFE}, + {WCD938X_HPH_NEW_INT_HPH_TIMER2, 0x02}, + {WCD938X_HPH_NEW_INT_HPH_TIMER3, 0x4E}, + {WCD938X_HPH_NEW_INT_HPH_TIMER4, 0x54}, + {WCD938X_HPH_NEW_INT_PA_RDAC_MISC2, 0x00}, + {WCD938X_HPH_NEW_INT_PA_RDAC_MISC3, 0x00}, + {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L_NEW, 0x90}, + {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R_NEW, 0x90}, + {WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_LOHIFI, 0x62}, + {WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_ULP, 0x01}, + {WCD938X_RX_NEW_INT_HPH_RDAC_LDO_LP, 0x11}, + {WCD938X_MBHC_NEW_INT_MOISTURE_DET_DC_CTRL, 0x57}, + {WCD938X_MBHC_NEW_INT_MOISTURE_DET_POLLING_CTRL, 0x01}, + {WCD938X_MBHC_NEW_INT_MECH_DET_CURRENT, 0x00}, + {WCD938X_MBHC_NEW_INT_SPARE_2, 0x00}, + {WCD938X_EAR_INT_NEW_EAR_CHOPPER_CON, 0xA8}, + {WCD938X_EAR_INT_NEW_CNP_VCM_CON1, 0x42}, + {WCD938X_EAR_INT_NEW_CNP_VCM_CON2, 0x22}, + {WCD938X_EAR_INT_NEW_EAR_DYNAMIC_BIAS, 0x00}, + {WCD938X_AUX_INT_EN_REG, 0x00}, + {WCD938X_AUX_INT_PA_CTRL, 0x06}, + {WCD938X_AUX_INT_SP_CTRL, 0xD2}, + {WCD938X_AUX_INT_DAC_CTRL, 0x80}, + {WCD938X_AUX_INT_CLK_CTRL, 0x50}, + {WCD938X_AUX_INT_TEST_CTRL, 0x00}, + {WCD938X_AUX_INT_STATUS_REG, 0x00}, + {WCD938X_AUX_INT_MISC, 0x00}, + {WCD938X_LDORXTX_INT_BIAS, 0x6E}, + {WCD938X_LDORXTX_INT_STB_LOADS_DTEST, 0x50}, + {WCD938X_LDORXTX_INT_TEST0, 0x1C}, + {WCD938X_LDORXTX_INT_STARTUP_TIMER, 0xFF}, + {WCD938X_LDORXTX_INT_TEST1, 0x1F}, + {WCD938X_LDORXTX_INT_STATUS, 0x00}, + {WCD938X_SLEEP_INT_WATCHDOG_CTL_1, 0x0A}, + {WCD938X_SLEEP_INT_WATCHDOG_CTL_2, 0x0A}, + {WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT1, 0x02}, + {WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT2, 0x60}, + {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L2, 0xFF}, + {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L1, 0x7F}, + {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L0, 0x3F}, + {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP1P2M, 0x1F}, + {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP0P6M, 0x0F}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L2L1, 0xD7}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L0, 0xC8}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_ULP, 0xC6}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L2L1, 0xD5}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L0, 0xCA}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_ULP, 0x05}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_L2L1L0, 0xA5}, + {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_ULP, 0x13}, + {WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L2L1, 0x88}, + {WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L0ULP, 0x42}, + {WCD938X_TX_COM_NEW_INT_TXADC_INT_L2, 0xFF}, + {WCD938X_TX_COM_NEW_INT_TXADC_INT_L1, 0x64}, + {WCD938X_TX_COM_NEW_INT_TXADC_INT_L0, 0x64}, + {WCD938X_TX_COM_NEW_INT_TXADC_INT_ULP, 0x77}, + {WCD938X_DIGITAL_PAGE_REGISTER, 0x00}, + {WCD938X_DIGITAL_CHIP_ID0, 0x00}, + {WCD938X_DIGITAL_CHIP_ID1, 0x00}, + {WCD938X_DIGITAL_CHIP_ID2, 0x0D}, + {WCD938X_DIGITAL_CHIP_ID3, 0x01}, + {WCD938X_DIGITAL_SWR_TX_CLK_RATE, 0x00}, + {WCD938X_DIGITAL_CDC_RST_CTL, 0x03}, + {WCD938X_DIGITAL_TOP_CLK_CFG, 0x00}, + {WCD938X_DIGITAL_CDC_ANA_CLK_CTL, 0x00}, + {WCD938X_DIGITAL_CDC_DIG_CLK_CTL, 0xF0}, + {WCD938X_DIGITAL_SWR_RST_EN, 0x00}, + {WCD938X_DIGITAL_CDC_PATH_MODE, 0x55}, + {WCD938X_DIGITAL_CDC_RX_RST, 0x00}, + {WCD938X_DIGITAL_CDC_RX0_CTL, 0xFC}, + {WCD938X_DIGITAL_CDC_RX1_CTL, 0xFC}, + {WCD938X_DIGITAL_CDC_RX2_CTL, 0xFC}, + {WCD938X_DIGITAL_CDC_TX_ANA_MODE_0_1, 0x00}, + {WCD938X_DIGITAL_CDC_TX_ANA_MODE_2_3, 0x00}, + {WCD938X_DIGITAL_CDC_COMP_CTL_0, 0x00}, + {WCD938X_DIGITAL_CDC_ANA_TX_CLK_CTL, 0x1E}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A1_0, 0x00}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A1_1, 0x01}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A2_0, 0x63}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A2_1, 0x04}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A3_0, 0xAC}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A3_1, 0x04}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A4_0, 0x1A}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A4_1, 0x03}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A5_0, 0xBC}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A5_1, 0x02}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A6_0, 0xC7}, + {WCD938X_DIGITAL_CDC_HPH_DSM_A7_0, 0xF8}, + {WCD938X_DIGITAL_CDC_HPH_DSM_C_0, 0x47}, + {WCD938X_DIGITAL_CDC_HPH_DSM_C_1, 0x43}, + {WCD938X_DIGITAL_CDC_HPH_DSM_C_2, 0xB1}, + {WCD938X_DIGITAL_CDC_HPH_DSM_C_3, 0x17}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R1, 0x4D}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R2, 0x29}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R3, 0x34}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R4, 0x59}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R5, 0x66}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R6, 0x87}, + {WCD938X_DIGITAL_CDC_HPH_DSM_R7, 0x64}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A1_0, 0x00}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A1_1, 0x01}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A2_0, 0x96}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A2_1, 0x09}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A3_0, 0xAB}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A3_1, 0x05}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A4_0, 0x1C}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A4_1, 0x02}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A5_0, 0x17}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A5_1, 0x02}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A6_0, 0xAA}, + {WCD938X_DIGITAL_CDC_AUX_DSM_A7_0, 0xE3}, + {WCD938X_DIGITAL_CDC_AUX_DSM_C_0, 0x69}, + {WCD938X_DIGITAL_CDC_AUX_DSM_C_1, 0x54}, + {WCD938X_DIGITAL_CDC_AUX_DSM_C_2, 0x02}, + {WCD938X_DIGITAL_CDC_AUX_DSM_C_3, 0x15}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R1, 0xA4}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R2, 0xB5}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R3, 0x86}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R4, 0x85}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R5, 0xAA}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R6, 0xE2}, + {WCD938X_DIGITAL_CDC_AUX_DSM_R7, 0x62}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_RX_0, 0x55}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_RX_1, 0xA9}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_0, 0x3D}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_1, 0x2E}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_2, 0x01}, + {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_0, 0x00}, + {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_1, 0xFC}, + {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_2, 0x01}, + {WCD938X_DIGITAL_CDC_HPH_GAIN_CTL, 0x00}, + {WCD938X_DIGITAL_CDC_AUX_GAIN_CTL, 0x00}, + {WCD938X_DIGITAL_CDC_EAR_PATH_CTL, 0x00}, + {WCD938X_DIGITAL_CDC_SWR_CLH, 0x00}, + {WCD938X_DIGITAL_SWR_CLH_BYP, 0x00}, + {WCD938X_DIGITAL_CDC_TX0_CTL, 0x68}, + {WCD938X_DIGITAL_CDC_TX1_CTL, 0x68}, + {WCD938X_DIGITAL_CDC_TX2_CTL, 0x68}, + {WCD938X_DIGITAL_CDC_TX_RST, 0x00}, + {WCD938X_DIGITAL_CDC_REQ_CTL, 0x01}, + {WCD938X_DIGITAL_CDC_RST, 0x00}, + {WCD938X_DIGITAL_CDC_AMIC_CTL, 0x0F}, + {WCD938X_DIGITAL_CDC_DMIC_CTL, 0x04}, + {WCD938X_DIGITAL_CDC_DMIC1_CTL, 0x01}, + {WCD938X_DIGITAL_CDC_DMIC2_CTL, 0x01}, + {WCD938X_DIGITAL_CDC_DMIC3_CTL, 0x01}, + {WCD938X_DIGITAL_CDC_DMIC4_CTL, 0x01}, + {WCD938X_DIGITAL_EFUSE_PRG_CTL, 0x00}, + {WCD938X_DIGITAL_EFUSE_CTL, 0x2B}, + {WCD938X_DIGITAL_CDC_DMIC_RATE_1_2, 0x11}, + {WCD938X_DIGITAL_CDC_DMIC_RATE_3_4, 0x11}, + {WCD938X_DIGITAL_PDM_WD_CTL0, 0x00}, + {WCD938X_DIGITAL_PDM_WD_CTL1, 0x00}, + {WCD938X_DIGITAL_PDM_WD_CTL2, 0x00}, + {WCD938X_DIGITAL_INTR_MODE, 0x00}, + {WCD938X_DIGITAL_INTR_MASK_0, 0xFF}, + {WCD938X_DIGITAL_INTR_MASK_1, 0xFF}, + {WCD938X_DIGITAL_INTR_MASK_2, 0x3F}, + {WCD938X_DIGITAL_INTR_STATUS_0, 0x00}, + {WCD938X_DIGITAL_INTR_STATUS_1, 0x00}, + {WCD938X_DIGITAL_INTR_STATUS_2, 0x00}, + {WCD938X_DIGITAL_INTR_CLEAR_0, 0x00}, + {WCD938X_DIGITAL_INTR_CLEAR_1, 0x00}, + {WCD938X_DIGITAL_INTR_CLEAR_2, 0x00}, + {WCD938X_DIGITAL_INTR_LEVEL_0, 0x00}, + {WCD938X_DIGITAL_INTR_LEVEL_1, 0x00}, + {WCD938X_DIGITAL_INTR_LEVEL_2, 0x00}, + {WCD938X_DIGITAL_INTR_SET_0, 0x00}, + {WCD938X_DIGITAL_INTR_SET_1, 0x00}, + {WCD938X_DIGITAL_INTR_SET_2, 0x00}, + {WCD938X_DIGITAL_INTR_TEST_0, 0x00}, + {WCD938X_DIGITAL_INTR_TEST_1, 0x00}, + {WCD938X_DIGITAL_INTR_TEST_2, 0x00}, + {WCD938X_DIGITAL_TX_MODE_DBG_EN, 0x00}, + {WCD938X_DIGITAL_TX_MODE_DBG_0_1, 0x00}, + {WCD938X_DIGITAL_TX_MODE_DBG_2_3, 0x00}, + {WCD938X_DIGITAL_LB_IN_SEL_CTL, 0x00}, + {WCD938X_DIGITAL_LOOP_BACK_MODE, 0x00}, + {WCD938X_DIGITAL_SWR_DAC_TEST, 0x00}, + {WCD938X_DIGITAL_SWR_HM_TEST_RX_0, 0x40}, + {WCD938X_DIGITAL_SWR_HM_TEST_TX_0, 0x40}, + {WCD938X_DIGITAL_SWR_HM_TEST_RX_1, 0x00}, + {WCD938X_DIGITAL_SWR_HM_TEST_TX_1, 0x00}, + {WCD938X_DIGITAL_SWR_HM_TEST_TX_2, 0x00}, + {WCD938X_DIGITAL_SWR_HM_TEST_0, 0x00}, + {WCD938X_DIGITAL_SWR_HM_TEST_1, 0x00}, + {WCD938X_DIGITAL_PAD_CTL_SWR_0, 0x8F}, + {WCD938X_DIGITAL_PAD_CTL_SWR_1, 0x06}, + {WCD938X_DIGITAL_I2C_CTL, 0x00}, + {WCD938X_DIGITAL_CDC_TX_TANGGU_SW_MODE, 0x00}, + {WCD938X_DIGITAL_EFUSE_TEST_CTL_0, 0x00}, + {WCD938X_DIGITAL_EFUSE_TEST_CTL_1, 0x00}, + {WCD938X_DIGITAL_EFUSE_T_DATA_0, 0x00}, + {WCD938X_DIGITAL_EFUSE_T_DATA_1, 0x00}, + {WCD938X_DIGITAL_PAD_CTL_PDM_RX0, 0xF1}, + {WCD938X_DIGITAL_PAD_CTL_PDM_RX1, 0xF1}, + {WCD938X_DIGITAL_PAD_CTL_PDM_TX0, 0xF1}, + {WCD938X_DIGITAL_PAD_CTL_PDM_TX1, 0xF1}, + {WCD938X_DIGITAL_PAD_CTL_PDM_TX2, 0xF1}, + {WCD938X_DIGITAL_PAD_INP_DIS_0, 0x00}, + {WCD938X_DIGITAL_PAD_INP_DIS_1, 0x00}, + {WCD938X_DIGITAL_DRIVE_STRENGTH_0, 0x00}, + {WCD938X_DIGITAL_DRIVE_STRENGTH_1, 0x00}, + {WCD938X_DIGITAL_DRIVE_STRENGTH_2, 0x00}, + {WCD938X_DIGITAL_RX_DATA_EDGE_CTL, 0x1F}, + {WCD938X_DIGITAL_TX_DATA_EDGE_CTL, 0x80}, + {WCD938X_DIGITAL_GPIO_MODE, 0x00}, + {WCD938X_DIGITAL_PIN_CTL_OE, 0x00}, + {WCD938X_DIGITAL_PIN_CTL_DATA_0, 0x00}, + {WCD938X_DIGITAL_PIN_CTL_DATA_1, 0x00}, + {WCD938X_DIGITAL_PIN_STATUS_0, 0x00}, + {WCD938X_DIGITAL_PIN_STATUS_1, 0x00}, + {WCD938X_DIGITAL_DIG_DEBUG_CTL, 0x00}, + {WCD938X_DIGITAL_DIG_DEBUG_EN, 0x00}, + {WCD938X_DIGITAL_ANA_CSR_DBG_ADD, 0x00}, + {WCD938X_DIGITAL_ANA_CSR_DBG_CTL, 0x48}, + {WCD938X_DIGITAL_SSP_DBG, 0x00}, + {WCD938X_DIGITAL_MODE_STATUS_0, 0x00}, + {WCD938X_DIGITAL_MODE_STATUS_1, 0x00}, + {WCD938X_DIGITAL_SPARE_0, 0x00}, + {WCD938X_DIGITAL_SPARE_1, 0x00}, + {WCD938X_DIGITAL_SPARE_2, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_0, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_1, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_2, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_3, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_4, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_5, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_6, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_7, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_8, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_9, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_10, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_11, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_12, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_13, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_14, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_15, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_16, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_17, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_18, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_19, 0xFF}, + {WCD938X_DIGITAL_EFUSE_REG_20, 0x0E}, + {WCD938X_DIGITAL_EFUSE_REG_21, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_22, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_23, 0xF8}, + {WCD938X_DIGITAL_EFUSE_REG_24, 0x16}, + {WCD938X_DIGITAL_EFUSE_REG_25, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_26, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_27, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_28, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_29, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_30, 0x00}, + {WCD938X_DIGITAL_EFUSE_REG_31, 0x00}, + {WCD938X_DIGITAL_TX_REQ_FB_CTL_0, 0x88}, + {WCD938X_DIGITAL_TX_REQ_FB_CTL_1, 0x88}, + {WCD938X_DIGITAL_TX_REQ_FB_CTL_2, 0x88}, + {WCD938X_DIGITAL_TX_REQ_FB_CTL_3, 0x88}, + {WCD938X_DIGITAL_TX_REQ_FB_CTL_4, 0x88}, + {WCD938X_DIGITAL_DEM_BYPASS_DATA0, 0x55}, + {WCD938X_DIGITAL_DEM_BYPASS_DATA1, 0x55}, + {WCD938X_DIGITAL_DEM_BYPASS_DATA2, 0x55}, + {WCD938X_DIGITAL_DEM_BYPASS_DATA3, 0x01}, +}; + +static bool wcd938x_rdwr_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case WCD938X_ANA_PAGE_REGISTER: + case WCD938X_ANA_BIAS: + case WCD938X_ANA_RX_SUPPLIES: + case WCD938X_ANA_HPH: + case WCD938X_ANA_EAR: + case WCD938X_ANA_EAR_COMPANDER_CTL: + case WCD938X_ANA_TX_CH1: + case WCD938X_ANA_TX_CH2: + case WCD938X_ANA_TX_CH3: + case WCD938X_ANA_TX_CH4: + case WCD938X_ANA_MICB1_MICB2_DSP_EN_LOGIC: + case WCD938X_ANA_MICB3_DSP_EN_LOGIC: + case WCD938X_ANA_MBHC_MECH: + case WCD938X_ANA_MBHC_ELECT: + case WCD938X_ANA_MBHC_ZDET: + case WCD938X_ANA_MBHC_BTN0: + case WCD938X_ANA_MBHC_BTN1: + case WCD938X_ANA_MBHC_BTN2: + case WCD938X_ANA_MBHC_BTN3: + case WCD938X_ANA_MBHC_BTN4: + case WCD938X_ANA_MBHC_BTN5: + case WCD938X_ANA_MBHC_BTN6: + case WCD938X_ANA_MBHC_BTN7: + case WCD938X_ANA_MICB1: + case WCD938X_ANA_MICB2: + case WCD938X_ANA_MICB2_RAMP: + case WCD938X_ANA_MICB3: + case WCD938X_ANA_MICB4: + case WCD938X_BIAS_CTL: + case WCD938X_BIAS_VBG_FINE_ADJ: + case WCD938X_LDOL_VDDCX_ADJUST: + case WCD938X_LDOL_DISABLE_LDOL: + case WCD938X_MBHC_CTL_CLK: + case WCD938X_MBHC_CTL_ANA: + case WCD938X_MBHC_CTL_SPARE_1: + case WCD938X_MBHC_CTL_SPARE_2: + case WCD938X_MBHC_CTL_BCS: + case WCD938X_MBHC_TEST_CTL: + case WCD938X_LDOH_MODE: + case WCD938X_LDOH_BIAS: + case WCD938X_LDOH_STB_LOADS: + case WCD938X_LDOH_SLOWRAMP: + case WCD938X_MICB1_TEST_CTL_1: + case WCD938X_MICB1_TEST_CTL_2: + case WCD938X_MICB1_TEST_CTL_3: + case WCD938X_MICB2_TEST_CTL_1: + case WCD938X_MICB2_TEST_CTL_2: + case WCD938X_MICB2_TEST_CTL_3: + case WCD938X_MICB3_TEST_CTL_1: + case WCD938X_MICB3_TEST_CTL_2: + case WCD938X_MICB3_TEST_CTL_3: + case WCD938X_MICB4_TEST_CTL_1: + case WCD938X_MICB4_TEST_CTL_2: + case WCD938X_MICB4_TEST_CTL_3: + case WCD938X_TX_COM_ADC_VCM: + case WCD938X_TX_COM_BIAS_ATEST: + case WCD938X_TX_COM_SPARE1: + case WCD938X_TX_COM_SPARE2: + case WCD938X_TX_COM_TXFE_DIV_CTL: + case WCD938X_TX_COM_TXFE_DIV_START: + case WCD938X_TX_COM_SPARE3: + case WCD938X_TX_COM_SPARE4: + case WCD938X_TX_1_2_TEST_EN: + case WCD938X_TX_1_2_ADC_IB: + case WCD938X_TX_1_2_ATEST_REFCTL: + case WCD938X_TX_1_2_TEST_CTL: + case WCD938X_TX_1_2_TEST_BLK_EN1: + case WCD938X_TX_1_2_TXFE1_CLKDIV: + case WCD938X_TX_3_4_TEST_EN: + case WCD938X_TX_3_4_ADC_IB: + case WCD938X_TX_3_4_ATEST_REFCTL: + case WCD938X_TX_3_4_TEST_CTL: + case WCD938X_TX_3_4_TEST_BLK_EN3: + case WCD938X_TX_3_4_TXFE3_CLKDIV: + case WCD938X_TX_3_4_TEST_BLK_EN2: + case WCD938X_TX_3_4_TXFE2_CLKDIV: + case WCD938X_TX_3_4_SPARE1: + case WCD938X_TX_3_4_TEST_BLK_EN4: + case WCD938X_TX_3_4_TXFE4_CLKDIV: + case WCD938X_TX_3_4_SPARE2: + case WCD938X_CLASSH_MODE_1: + case WCD938X_CLASSH_MODE_2: + case WCD938X_CLASSH_MODE_3: + case WCD938X_CLASSH_CTRL_VCL_1: + case WCD938X_CLASSH_CTRL_VCL_2: + case WCD938X_CLASSH_CTRL_CCL_1: + case WCD938X_CLASSH_CTRL_CCL_2: + case WCD938X_CLASSH_CTRL_CCL_3: + case WCD938X_CLASSH_CTRL_CCL_4: + case WCD938X_CLASSH_CTRL_CCL_5: + case WCD938X_CLASSH_BUCK_TMUX_A_D: + case WCD938X_CLASSH_BUCK_SW_DRV_CNTL: + case WCD938X_CLASSH_SPARE: + case WCD938X_FLYBACK_EN: + case WCD938X_FLYBACK_VNEG_CTRL_1: + case WCD938X_FLYBACK_VNEG_CTRL_2: + case WCD938X_FLYBACK_VNEG_CTRL_3: + case WCD938X_FLYBACK_VNEG_CTRL_4: + case WCD938X_FLYBACK_VNEG_CTRL_5: + case WCD938X_FLYBACK_VNEG_CTRL_6: + case WCD938X_FLYBACK_VNEG_CTRL_7: + case WCD938X_FLYBACK_VNEG_CTRL_8: + case WCD938X_FLYBACK_VNEG_CTRL_9: + case WCD938X_FLYBACK_VNEGDAC_CTRL_1: + case WCD938X_FLYBACK_VNEGDAC_CTRL_2: + case WCD938X_FLYBACK_VNEGDAC_CTRL_3: + case WCD938X_FLYBACK_CTRL_1: + case WCD938X_FLYBACK_TEST_CTL: + case WCD938X_RX_AUX_SW_CTL: + case WCD938X_RX_PA_AUX_IN_CONN: + case WCD938X_RX_TIMER_DIV: + case WCD938X_RX_OCP_CTL: + case WCD938X_RX_OCP_COUNT: + case WCD938X_RX_BIAS_EAR_DAC: + case WCD938X_RX_BIAS_EAR_AMP: + case WCD938X_RX_BIAS_HPH_LDO: + case WCD938X_RX_BIAS_HPH_PA: + case WCD938X_RX_BIAS_HPH_RDACBUFF_CNP2: + case WCD938X_RX_BIAS_HPH_RDAC_LDO: + case WCD938X_RX_BIAS_HPH_CNP1: + case WCD938X_RX_BIAS_HPH_LOWPOWER: + case WCD938X_RX_BIAS_AUX_DAC: + case WCD938X_RX_BIAS_AUX_AMP: + case WCD938X_RX_BIAS_VNEGDAC_BLEEDER: + case WCD938X_RX_BIAS_MISC: + case WCD938X_RX_BIAS_BUCK_RST: + case WCD938X_RX_BIAS_BUCK_VREF_ERRAMP: + case WCD938X_RX_BIAS_FLYB_ERRAMP: + case WCD938X_RX_BIAS_FLYB_BUFF: + case WCD938X_RX_BIAS_FLYB_MID_RST: + case WCD938X_HPH_CNP_EN: + case WCD938X_HPH_CNP_WG_CTL: + case WCD938X_HPH_CNP_WG_TIME: + case WCD938X_HPH_OCP_CTL: + case WCD938X_HPH_AUTO_CHOP: + case WCD938X_HPH_CHOP_CTL: + case WCD938X_HPH_PA_CTL1: + case WCD938X_HPH_PA_CTL2: + case WCD938X_HPH_L_EN: + case WCD938X_HPH_L_TEST: + case WCD938X_HPH_L_ATEST: + case WCD938X_HPH_R_EN: + case WCD938X_HPH_R_TEST: + case WCD938X_HPH_R_ATEST: + case WCD938X_HPH_RDAC_CLK_CTL1: + case WCD938X_HPH_RDAC_CLK_CTL2: + case WCD938X_HPH_RDAC_LDO_CTL: + case WCD938X_HPH_RDAC_CHOP_CLK_LP_CTL: + case WCD938X_HPH_REFBUFF_UHQA_CTL: + case WCD938X_HPH_REFBUFF_LP_CTL: + case WCD938X_HPH_L_DAC_CTL: + case WCD938X_HPH_R_DAC_CTL: + case WCD938X_HPH_SURGE_HPHLR_SURGE_COMP_SEL: + case WCD938X_HPH_SURGE_HPHLR_SURGE_EN: + case WCD938X_HPH_SURGE_HPHLR_SURGE_MISC1: + case WCD938X_EAR_EAR_EN_REG: + case WCD938X_EAR_EAR_PA_CON: + case WCD938X_EAR_EAR_SP_CON: + case WCD938X_EAR_EAR_DAC_CON: + case WCD938X_EAR_EAR_CNP_FSM_CON: + case WCD938X_EAR_TEST_CTL: + case WCD938X_ANA_NEW_PAGE_REGISTER: + case WCD938X_HPH_NEW_ANA_HPH2: + case WCD938X_HPH_NEW_ANA_HPH3: + case WCD938X_SLEEP_CTL: + case WCD938X_SLEEP_WATCHDOG_CTL: + case WCD938X_MBHC_NEW_ELECT_REM_CLAMP_CTL: + case WCD938X_MBHC_NEW_CTL_1: + case WCD938X_MBHC_NEW_CTL_2: + case WCD938X_MBHC_NEW_PLUG_DETECT_CTL: + case WCD938X_MBHC_NEW_ZDET_ANA_CTL: + case WCD938X_MBHC_NEW_ZDET_RAMP_CTL: + case WCD938X_TX_NEW_AMIC_MUX_CFG: + case WCD938X_AUX_AUXPA: + case WCD938X_LDORXTX_MODE: + case WCD938X_LDORXTX_CONFIG: + case WCD938X_DIE_CRACK_DIE_CRK_DET_EN: + case WCD938X_HPH_NEW_INT_RDAC_GAIN_CTL: + case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L: + case WCD938X_HPH_NEW_INT_RDAC_VREF_CTL: + case WCD938X_HPH_NEW_INT_RDAC_OVERRIDE_CTL: + case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R: + case WCD938X_HPH_NEW_INT_PA_MISC1: + case WCD938X_HPH_NEW_INT_PA_MISC2: + case WCD938X_HPH_NEW_INT_PA_RDAC_MISC: + case WCD938X_HPH_NEW_INT_HPH_TIMER1: + case WCD938X_HPH_NEW_INT_HPH_TIMER2: + case WCD938X_HPH_NEW_INT_HPH_TIMER3: + case WCD938X_HPH_NEW_INT_HPH_TIMER4: + case WCD938X_HPH_NEW_INT_PA_RDAC_MISC2: + case WCD938X_HPH_NEW_INT_PA_RDAC_MISC3: + case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L_NEW: + case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R_NEW: + case WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_LOHIFI: + case WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_ULP: + case WCD938X_RX_NEW_INT_HPH_RDAC_LDO_LP: + case WCD938X_MBHC_NEW_INT_MOISTURE_DET_DC_CTRL: + case WCD938X_MBHC_NEW_INT_MOISTURE_DET_POLLING_CTRL: + case WCD938X_MBHC_NEW_INT_MECH_DET_CURRENT: + case WCD938X_MBHC_NEW_INT_SPARE_2: + case WCD938X_EAR_INT_NEW_EAR_CHOPPER_CON: + case WCD938X_EAR_INT_NEW_CNP_VCM_CON1: + case WCD938X_EAR_INT_NEW_CNP_VCM_CON2: + case WCD938X_EAR_INT_NEW_EAR_DYNAMIC_BIAS: + case WCD938X_AUX_INT_EN_REG: + case WCD938X_AUX_INT_PA_CTRL: + case WCD938X_AUX_INT_SP_CTRL: + case WCD938X_AUX_INT_DAC_CTRL: + case WCD938X_AUX_INT_CLK_CTRL: + case WCD938X_AUX_INT_TEST_CTRL: + case WCD938X_AUX_INT_MISC: + case WCD938X_LDORXTX_INT_BIAS: + case WCD938X_LDORXTX_INT_STB_LOADS_DTEST: + case WCD938X_LDORXTX_INT_TEST0: + case WCD938X_LDORXTX_INT_STARTUP_TIMER: + case WCD938X_LDORXTX_INT_TEST1: + case WCD938X_SLEEP_INT_WATCHDOG_CTL_1: + case WCD938X_SLEEP_INT_WATCHDOG_CTL_2: + case WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT1: + case WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT2: + case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L2: + case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L1: + case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L0: + case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP1P2M: + case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP0P6M: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L2L1: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L0: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_ULP: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L2L1: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L0: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_ULP: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_L2L1L0: + case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_ULP: + case WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L2L1: + case WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L0ULP: + case WCD938X_TX_COM_NEW_INT_TXADC_INT_L2: + case WCD938X_TX_COM_NEW_INT_TXADC_INT_L1: + case WCD938X_TX_COM_NEW_INT_TXADC_INT_L0: + case WCD938X_TX_COM_NEW_INT_TXADC_INT_ULP: + case WCD938X_DIGITAL_PAGE_REGISTER: + case WCD938X_DIGITAL_SWR_TX_CLK_RATE: + case WCD938X_DIGITAL_CDC_RST_CTL: + case WCD938X_DIGITAL_TOP_CLK_CFG: + case WCD938X_DIGITAL_CDC_ANA_CLK_CTL: + case WCD938X_DIGITAL_CDC_DIG_CLK_CTL: + case WCD938X_DIGITAL_SWR_RST_EN: + case WCD938X_DIGITAL_CDC_PATH_MODE: + case WCD938X_DIGITAL_CDC_RX_RST: + case WCD938X_DIGITAL_CDC_RX0_CTL: + case WCD938X_DIGITAL_CDC_RX1_CTL: + case WCD938X_DIGITAL_CDC_RX2_CTL: + case WCD938X_DIGITAL_CDC_TX_ANA_MODE_0_1: + case WCD938X_DIGITAL_CDC_TX_ANA_MODE_2_3: + case WCD938X_DIGITAL_CDC_COMP_CTL_0: + case WCD938X_DIGITAL_CDC_ANA_TX_CLK_CTL: + case WCD938X_DIGITAL_CDC_HPH_DSM_A1_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A1_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_A2_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A2_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_A3_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A3_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_A4_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A4_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_A5_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A5_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_A6_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_A7_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_C_0: + case WCD938X_DIGITAL_CDC_HPH_DSM_C_1: + case WCD938X_DIGITAL_CDC_HPH_DSM_C_2: + case WCD938X_DIGITAL_CDC_HPH_DSM_C_3: + case WCD938X_DIGITAL_CDC_HPH_DSM_R1: + case WCD938X_DIGITAL_CDC_HPH_DSM_R2: + case WCD938X_DIGITAL_CDC_HPH_DSM_R3: + case WCD938X_DIGITAL_CDC_HPH_DSM_R4: + case WCD938X_DIGITAL_CDC_HPH_DSM_R5: + case WCD938X_DIGITAL_CDC_HPH_DSM_R6: + case WCD938X_DIGITAL_CDC_HPH_DSM_R7: + case WCD938X_DIGITAL_CDC_AUX_DSM_A1_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A1_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_A2_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A2_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_A3_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A3_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_A4_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A4_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_A5_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A5_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_A6_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_A7_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_C_0: + case WCD938X_DIGITAL_CDC_AUX_DSM_C_1: + case WCD938X_DIGITAL_CDC_AUX_DSM_C_2: + case WCD938X_DIGITAL_CDC_AUX_DSM_C_3: + case WCD938X_DIGITAL_CDC_AUX_DSM_R1: + case WCD938X_DIGITAL_CDC_AUX_DSM_R2: + case WCD938X_DIGITAL_CDC_AUX_DSM_R3: + case WCD938X_DIGITAL_CDC_AUX_DSM_R4: + case WCD938X_DIGITAL_CDC_AUX_DSM_R5: + case WCD938X_DIGITAL_CDC_AUX_DSM_R6: + case WCD938X_DIGITAL_CDC_AUX_DSM_R7: + case WCD938X_DIGITAL_CDC_HPH_GAIN_RX_0: + case WCD938X_DIGITAL_CDC_HPH_GAIN_RX_1: + case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_0: + case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_1: + case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_2: + case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_0: + case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_1: + case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_2: + case WCD938X_DIGITAL_CDC_HPH_GAIN_CTL: + case WCD938X_DIGITAL_CDC_AUX_GAIN_CTL: + case WCD938X_DIGITAL_CDC_EAR_PATH_CTL: + case WCD938X_DIGITAL_CDC_SWR_CLH: + case WCD938X_DIGITAL_SWR_CLH_BYP: + case WCD938X_DIGITAL_CDC_TX0_CTL: + case WCD938X_DIGITAL_CDC_TX1_CTL: + case WCD938X_DIGITAL_CDC_TX2_CTL: + case WCD938X_DIGITAL_CDC_TX_RST: + case WCD938X_DIGITAL_CDC_REQ_CTL: + case WCD938X_DIGITAL_CDC_RST: + case WCD938X_DIGITAL_CDC_AMIC_CTL: + case WCD938X_DIGITAL_CDC_DMIC_CTL: + case WCD938X_DIGITAL_CDC_DMIC1_CTL: + case WCD938X_DIGITAL_CDC_DMIC2_CTL: + case WCD938X_DIGITAL_CDC_DMIC3_CTL: + case WCD938X_DIGITAL_CDC_DMIC4_CTL: + case WCD938X_DIGITAL_EFUSE_PRG_CTL: + case WCD938X_DIGITAL_EFUSE_CTL: + case WCD938X_DIGITAL_CDC_DMIC_RATE_1_2: + case WCD938X_DIGITAL_CDC_DMIC_RATE_3_4: + case WCD938X_DIGITAL_PDM_WD_CTL0: + case WCD938X_DIGITAL_PDM_WD_CTL1: + case WCD938X_DIGITAL_PDM_WD_CTL2: + case WCD938X_DIGITAL_INTR_MODE: + case WCD938X_DIGITAL_INTR_MASK_0: + case WCD938X_DIGITAL_INTR_MASK_1: + case WCD938X_DIGITAL_INTR_MASK_2: + case WCD938X_DIGITAL_INTR_CLEAR_0: + case WCD938X_DIGITAL_INTR_CLEAR_1: + case WCD938X_DIGITAL_INTR_CLEAR_2: + case WCD938X_DIGITAL_INTR_LEVEL_0: + case WCD938X_DIGITAL_INTR_LEVEL_1: + case WCD938X_DIGITAL_INTR_LEVEL_2: + case WCD938X_DIGITAL_INTR_SET_0: + case WCD938X_DIGITAL_INTR_SET_1: + case WCD938X_DIGITAL_INTR_SET_2: + case WCD938X_DIGITAL_INTR_TEST_0: + case WCD938X_DIGITAL_INTR_TEST_1: + case WCD938X_DIGITAL_INTR_TEST_2: + case WCD938X_DIGITAL_TX_MODE_DBG_EN: + case WCD938X_DIGITAL_TX_MODE_DBG_0_1: + case WCD938X_DIGITAL_TX_MODE_DBG_2_3: + case WCD938X_DIGITAL_LB_IN_SEL_CTL: + case WCD938X_DIGITAL_LOOP_BACK_MODE: + case WCD938X_DIGITAL_SWR_DAC_TEST: + case WCD938X_DIGITAL_SWR_HM_TEST_RX_0: + case WCD938X_DIGITAL_SWR_HM_TEST_TX_0: + case WCD938X_DIGITAL_SWR_HM_TEST_RX_1: + case WCD938X_DIGITAL_SWR_HM_TEST_TX_1: + case WCD938X_DIGITAL_SWR_HM_TEST_TX_2: + case WCD938X_DIGITAL_PAD_CTL_SWR_0: + case WCD938X_DIGITAL_PAD_CTL_SWR_1: + case WCD938X_DIGITAL_I2C_CTL: + case WCD938X_DIGITAL_CDC_TX_TANGGU_SW_MODE: + case WCD938X_DIGITAL_EFUSE_TEST_CTL_0: + case WCD938X_DIGITAL_EFUSE_TEST_CTL_1: + case WCD938X_DIGITAL_PAD_CTL_PDM_RX0: + case WCD938X_DIGITAL_PAD_CTL_PDM_RX1: + case WCD938X_DIGITAL_PAD_CTL_PDM_TX0: + case WCD938X_DIGITAL_PAD_CTL_PDM_TX1: + case WCD938X_DIGITAL_PAD_CTL_PDM_TX2: + case WCD938X_DIGITAL_PAD_INP_DIS_0: + case WCD938X_DIGITAL_PAD_INP_DIS_1: + case WCD938X_DIGITAL_DRIVE_STRENGTH_0: + case WCD938X_DIGITAL_DRIVE_STRENGTH_1: + case WCD938X_DIGITAL_DRIVE_STRENGTH_2: + case WCD938X_DIGITAL_RX_DATA_EDGE_CTL: + case WCD938X_DIGITAL_TX_DATA_EDGE_CTL: + case WCD938X_DIGITAL_GPIO_MODE: + case WCD938X_DIGITAL_PIN_CTL_OE: + case WCD938X_DIGITAL_PIN_CTL_DATA_0: + case WCD938X_DIGITAL_PIN_CTL_DATA_1: + case WCD938X_DIGITAL_DIG_DEBUG_CTL: + case WCD938X_DIGITAL_DIG_DEBUG_EN: + case WCD938X_DIGITAL_ANA_CSR_DBG_ADD: + case WCD938X_DIGITAL_ANA_CSR_DBG_CTL: + case WCD938X_DIGITAL_SSP_DBG: + case WCD938X_DIGITAL_SPARE_0: + case WCD938X_DIGITAL_SPARE_1: + case WCD938X_DIGITAL_SPARE_2: + case WCD938X_DIGITAL_TX_REQ_FB_CTL_0: + case WCD938X_DIGITAL_TX_REQ_FB_CTL_1: + case WCD938X_DIGITAL_TX_REQ_FB_CTL_2: + case WCD938X_DIGITAL_TX_REQ_FB_CTL_3: + case WCD938X_DIGITAL_TX_REQ_FB_CTL_4: + case WCD938X_DIGITAL_DEM_BYPASS_DATA0: + case WCD938X_DIGITAL_DEM_BYPASS_DATA1: + case WCD938X_DIGITAL_DEM_BYPASS_DATA2: + case WCD938X_DIGITAL_DEM_BYPASS_DATA3: + return true; + } + + return false; +} + +static bool wcd938x_readonly_register(struct device *dev, unsigned int reg) +{ + switch (reg) { + case WCD938X_ANA_MBHC_RESULT_1: + case WCD938X_ANA_MBHC_RESULT_2: + case WCD938X_ANA_MBHC_RESULT_3: + case WCD938X_MBHC_MOISTURE_DET_FSM_STATUS: + case WCD938X_TX_1_2_SAR2_ERR: + case WCD938X_TX_1_2_SAR1_ERR: + case WCD938X_TX_3_4_SAR4_ERR: + case WCD938X_TX_3_4_SAR3_ERR: + case WCD938X_HPH_L_STATUS: + case WCD938X_HPH_R_STATUS: + case WCD938X_HPH_SURGE_HPHLR_SURGE_STATUS: + case WCD938X_EAR_STATUS_REG_1: + case WCD938X_EAR_STATUS_REG_2: + case WCD938X_MBHC_NEW_FSM_STATUS: + case WCD938X_MBHC_NEW_ADC_RESULT: + case WCD938X_DIE_CRACK_DIE_CRK_DET_OUT: + case WCD938X_AUX_INT_STATUS_REG: + case WCD938X_LDORXTX_INT_STATUS: + case WCD938X_DIGITAL_CHIP_ID0: + case WCD938X_DIGITAL_CHIP_ID1: + case WCD938X_DIGITAL_CHIP_ID2: + case WCD938X_DIGITAL_CHIP_ID3: + case WCD938X_DIGITAL_INTR_STATUS_0: + case WCD938X_DIGITAL_INTR_STATUS_1: + case WCD938X_DIGITAL_INTR_STATUS_2: + case WCD938X_DIGITAL_INTR_CLEAR_0: + case WCD938X_DIGITAL_INTR_CLEAR_1: + case WCD938X_DIGITAL_INTR_CLEAR_2: + case WCD938X_DIGITAL_SWR_HM_TEST_0: + case WCD938X_DIGITAL_SWR_HM_TEST_1: + case WCD938X_DIGITAL_EFUSE_T_DATA_0: + case WCD938X_DIGITAL_EFUSE_T_DATA_1: + case WCD938X_DIGITAL_PIN_STATUS_0: + case WCD938X_DIGITAL_PIN_STATUS_1: + case WCD938X_DIGITAL_MODE_STATUS_0: + case WCD938X_DIGITAL_MODE_STATUS_1: + case WCD938X_DIGITAL_EFUSE_REG_0: + case WCD938X_DIGITAL_EFUSE_REG_1: + case WCD938X_DIGITAL_EFUSE_REG_2: + case WCD938X_DIGITAL_EFUSE_REG_3: + case WCD938X_DIGITAL_EFUSE_REG_4: + case WCD938X_DIGITAL_EFUSE_REG_5: + case WCD938X_DIGITAL_EFUSE_REG_6: + case WCD938X_DIGITAL_EFUSE_REG_7: + case WCD938X_DIGITAL_EFUSE_REG_8: + case WCD938X_DIGITAL_EFUSE_REG_9: + case WCD938X_DIGITAL_EFUSE_REG_10: + case WCD938X_DIGITAL_EFUSE_REG_11: + case WCD938X_DIGITAL_EFUSE_REG_12: + case WCD938X_DIGITAL_EFUSE_REG_13: + case WCD938X_DIGITAL_EFUSE_REG_14: + case WCD938X_DIGITAL_EFUSE_REG_15: + case WCD938X_DIGITAL_EFUSE_REG_16: + case WCD938X_DIGITAL_EFUSE_REG_17: + case WCD938X_DIGITAL_EFUSE_REG_18: + case WCD938X_DIGITAL_EFUSE_REG_19: + case WCD938X_DIGITAL_EFUSE_REG_20: + case WCD938X_DIGITAL_EFUSE_REG_21: + case WCD938X_DIGITAL_EFUSE_REG_22: + case WCD938X_DIGITAL_EFUSE_REG_23: + case WCD938X_DIGITAL_EFUSE_REG_24: + case WCD938X_DIGITAL_EFUSE_REG_25: + case WCD938X_DIGITAL_EFUSE_REG_26: + case WCD938X_DIGITAL_EFUSE_REG_27: + case WCD938X_DIGITAL_EFUSE_REG_28: + case WCD938X_DIGITAL_EFUSE_REG_29: + case WCD938X_DIGITAL_EFUSE_REG_30: + case WCD938X_DIGITAL_EFUSE_REG_31: + return true; + } + return false; +} + +static bool wcd938x_readable_register(struct device *dev, unsigned int reg) +{ + bool ret; + + ret = wcd938x_readonly_register(dev, reg); + if (!ret) + return wcd938x_rdwr_register(dev, reg); + + return ret; +} + +static bool wcd938x_writeable_register(struct device *dev, unsigned int reg) +{ + return wcd938x_rdwr_register(dev, reg); +} + +static bool wcd938x_volatile_register(struct device *dev, unsigned int reg) +{ + if (reg <= WCD938X_BASE_ADDRESS) + return false; + + if (reg == WCD938X_DIGITAL_SWR_TX_CLK_RATE) + return true; + + if (wcd938x_readonly_register(dev, reg)) + return true; + + return false; +} + +static const struct regmap_config wcd938x_regmap_config = { + .name = "wcd938x_csr", + .reg_bits = 32, + .val_bits = 8, + .cache_type = REGCACHE_RBTREE, + .reg_defaults = wcd938x_defaults, + .num_reg_defaults = ARRAY_SIZE(wcd938x_defaults), + .max_register = WCD938X_MAX_REGISTER, + .readable_reg = wcd938x_readable_register, + .writeable_reg = wcd938x_writeable_register, + .volatile_reg = wcd938x_volatile_register, + .can_multi_write = true, +}; + static const struct sdw_slave_ops wcd9380_slave_ops = { .update_status = wcd9380_update_status, .interrupt_callback = wcd9380_interrupt_callback, @@ -261,6 +1263,16 @@ static int wcd9380_probe(struct sdw_slave *pdev, wcd->ch_info = &wcd938x_sdw_rx_ch_info[0]; } + if (wcd->is_tx) { + wcd->regmap = devm_regmap_init_sdw(pdev, &wcd938x_regmap_config); + if (IS_ERR(wcd->regmap)) + return dev_err_probe(dev, PTR_ERR(wcd->regmap), + "Regmap init failed\n"); + + /* Start in cache-only until device is enumerated */ + regcache_cache_only(wcd->regmap, true); + }; + pm_runtime_set_autosuspend_delay(dev, 3000); pm_runtime_use_autosuspend(dev); pm_runtime_mark_last_busy(dev); @@ -278,22 +1290,23 @@ MODULE_DEVICE_TABLE(sdw, wcd9380_slave_id); static int __maybe_unused wcd938x_sdw_runtime_suspend(struct device *dev) { - struct regmap *regmap = dev_get_regmap(dev, NULL); + struct wcd938x_sdw_priv *wcd = dev_get_drvdata(dev); - if (regmap) { - regcache_cache_only(regmap, true); - regcache_mark_dirty(regmap); + if (wcd->regmap) { + regcache_cache_only(wcd->regmap, true); + regcache_mark_dirty(wcd->regmap); } + return 0; } static int __maybe_unused wcd938x_sdw_runtime_resume(struct device *dev) { - struct regmap *regmap = dev_get_regmap(dev, NULL); + struct wcd938x_sdw_priv *wcd = dev_get_drvdata(dev); - if (regmap) { - regcache_cache_only(regmap, false); - regcache_sync(regmap); + if (wcd->regmap) { + regcache_cache_only(wcd->regmap, false); + regcache_sync(wcd->regmap); } pm_runtime_mark_last_busy(dev); diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index 11b264a63b04..e7d6a02cdec0 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -273,1001 +273,6 @@ static struct wcd_mbhc_field wcd_mbhc_fields[WCD_MBHC_REG_FUNC_MAX] = { WCD_MBHC_FIELD(WCD_MBHC_ELECT_ISRC_EN, WCD938X_ANA_MBHC_ZDET, 0x02), }; -static const struct reg_default wcd938x_defaults[] = { - {WCD938X_ANA_PAGE_REGISTER, 0x00}, - {WCD938X_ANA_BIAS, 0x00}, - {WCD938X_ANA_RX_SUPPLIES, 0x00}, - {WCD938X_ANA_HPH, 0x0C}, - {WCD938X_ANA_EAR, 0x00}, - {WCD938X_ANA_EAR_COMPANDER_CTL, 0x02}, - {WCD938X_ANA_TX_CH1, 0x20}, - {WCD938X_ANA_TX_CH2, 0x00}, - {WCD938X_ANA_TX_CH3, 0x20}, - {WCD938X_ANA_TX_CH4, 0x00}, - {WCD938X_ANA_MICB1_MICB2_DSP_EN_LOGIC, 0x00}, - {WCD938X_ANA_MICB3_DSP_EN_LOGIC, 0x00}, - {WCD938X_ANA_MBHC_MECH, 0x39}, - {WCD938X_ANA_MBHC_ELECT, 0x08}, - {WCD938X_ANA_MBHC_ZDET, 0x00}, - {WCD938X_ANA_MBHC_RESULT_1, 0x00}, - {WCD938X_ANA_MBHC_RESULT_2, 0x00}, - {WCD938X_ANA_MBHC_RESULT_3, 0x00}, - {WCD938X_ANA_MBHC_BTN0, 0x00}, - {WCD938X_ANA_MBHC_BTN1, 0x10}, - {WCD938X_ANA_MBHC_BTN2, 0x20}, - {WCD938X_ANA_MBHC_BTN3, 0x30}, - {WCD938X_ANA_MBHC_BTN4, 0x40}, - {WCD938X_ANA_MBHC_BTN5, 0x50}, - {WCD938X_ANA_MBHC_BTN6, 0x60}, - {WCD938X_ANA_MBHC_BTN7, 0x70}, - {WCD938X_ANA_MICB1, 0x10}, - {WCD938X_ANA_MICB2, 0x10}, - {WCD938X_ANA_MICB2_RAMP, 0x00}, - {WCD938X_ANA_MICB3, 0x10}, - {WCD938X_ANA_MICB4, 0x10}, - {WCD938X_BIAS_CTL, 0x2A}, - {WCD938X_BIAS_VBG_FINE_ADJ, 0x55}, - {WCD938X_LDOL_VDDCX_ADJUST, 0x01}, - {WCD938X_LDOL_DISABLE_LDOL, 0x00}, - {WCD938X_MBHC_CTL_CLK, 0x00}, - {WCD938X_MBHC_CTL_ANA, 0x00}, - {WCD938X_MBHC_CTL_SPARE_1, 0x00}, - {WCD938X_MBHC_CTL_SPARE_2, 0x00}, - {WCD938X_MBHC_CTL_BCS, 0x00}, - {WCD938X_MBHC_MOISTURE_DET_FSM_STATUS, 0x00}, - {WCD938X_MBHC_TEST_CTL, 0x00}, - {WCD938X_LDOH_MODE, 0x2B}, - {WCD938X_LDOH_BIAS, 0x68}, - {WCD938X_LDOH_STB_LOADS, 0x00}, - {WCD938X_LDOH_SLOWRAMP, 0x50}, - {WCD938X_MICB1_TEST_CTL_1, 0x1A}, - {WCD938X_MICB1_TEST_CTL_2, 0x00}, - {WCD938X_MICB1_TEST_CTL_3, 0xA4}, - {WCD938X_MICB2_TEST_CTL_1, 0x1A}, - {WCD938X_MICB2_TEST_CTL_2, 0x00}, - {WCD938X_MICB2_TEST_CTL_3, 0x24}, - {WCD938X_MICB3_TEST_CTL_1, 0x1A}, - {WCD938X_MICB3_TEST_CTL_2, 0x00}, - {WCD938X_MICB3_TEST_CTL_3, 0xA4}, - {WCD938X_MICB4_TEST_CTL_1, 0x1A}, - {WCD938X_MICB4_TEST_CTL_2, 0x00}, - {WCD938X_MICB4_TEST_CTL_3, 0xA4}, - {WCD938X_TX_COM_ADC_VCM, 0x39}, - {WCD938X_TX_COM_BIAS_ATEST, 0xE0}, - {WCD938X_TX_COM_SPARE1, 0x00}, - {WCD938X_TX_COM_SPARE2, 0x00}, - {WCD938X_TX_COM_TXFE_DIV_CTL, 0x22}, - {WCD938X_TX_COM_TXFE_DIV_START, 0x00}, - {WCD938X_TX_COM_SPARE3, 0x00}, - {WCD938X_TX_COM_SPARE4, 0x00}, - {WCD938X_TX_1_2_TEST_EN, 0xCC}, - {WCD938X_TX_1_2_ADC_IB, 0xE9}, - {WCD938X_TX_1_2_ATEST_REFCTL, 0x0A}, - {WCD938X_TX_1_2_TEST_CTL, 0x38}, - {WCD938X_TX_1_2_TEST_BLK_EN1, 0xFF}, - {WCD938X_TX_1_2_TXFE1_CLKDIV, 0x00}, - {WCD938X_TX_1_2_SAR2_ERR, 0x00}, - {WCD938X_TX_1_2_SAR1_ERR, 0x00}, - {WCD938X_TX_3_4_TEST_EN, 0xCC}, - {WCD938X_TX_3_4_ADC_IB, 0xE9}, - {WCD938X_TX_3_4_ATEST_REFCTL, 0x0A}, - {WCD938X_TX_3_4_TEST_CTL, 0x38}, - {WCD938X_TX_3_4_TEST_BLK_EN3, 0xFF}, - {WCD938X_TX_3_4_TXFE3_CLKDIV, 0x00}, - {WCD938X_TX_3_4_SAR4_ERR, 0x00}, - {WCD938X_TX_3_4_SAR3_ERR, 0x00}, - {WCD938X_TX_3_4_TEST_BLK_EN2, 0xFB}, - {WCD938X_TX_3_4_TXFE2_CLKDIV, 0x00}, - {WCD938X_TX_3_4_SPARE1, 0x00}, - {WCD938X_TX_3_4_TEST_BLK_EN4, 0xFB}, - {WCD938X_TX_3_4_TXFE4_CLKDIV, 0x00}, - {WCD938X_TX_3_4_SPARE2, 0x00}, - {WCD938X_CLASSH_MODE_1, 0x40}, - {WCD938X_CLASSH_MODE_2, 0x3A}, - {WCD938X_CLASSH_MODE_3, 0x00}, - {WCD938X_CLASSH_CTRL_VCL_1, 0x70}, - {WCD938X_CLASSH_CTRL_VCL_2, 0x82}, - {WCD938X_CLASSH_CTRL_CCL_1, 0x31}, - {WCD938X_CLASSH_CTRL_CCL_2, 0x80}, - {WCD938X_CLASSH_CTRL_CCL_3, 0x80}, - {WCD938X_CLASSH_CTRL_CCL_4, 0x51}, - {WCD938X_CLASSH_CTRL_CCL_5, 0x00}, - {WCD938X_CLASSH_BUCK_TMUX_A_D, 0x00}, - {WCD938X_CLASSH_BUCK_SW_DRV_CNTL, 0x77}, - {WCD938X_CLASSH_SPARE, 0x00}, - {WCD938X_FLYBACK_EN, 0x4E}, - {WCD938X_FLYBACK_VNEG_CTRL_1, 0x0B}, - {WCD938X_FLYBACK_VNEG_CTRL_2, 0x45}, - {WCD938X_FLYBACK_VNEG_CTRL_3, 0x74}, - {WCD938X_FLYBACK_VNEG_CTRL_4, 0x7F}, - {WCD938X_FLYBACK_VNEG_CTRL_5, 0x83}, - {WCD938X_FLYBACK_VNEG_CTRL_6, 0x98}, - {WCD938X_FLYBACK_VNEG_CTRL_7, 0xA9}, - {WCD938X_FLYBACK_VNEG_CTRL_8, 0x68}, - {WCD938X_FLYBACK_VNEG_CTRL_9, 0x64}, - {WCD938X_FLYBACK_VNEGDAC_CTRL_1, 0xED}, - {WCD938X_FLYBACK_VNEGDAC_CTRL_2, 0xF0}, - {WCD938X_FLYBACK_VNEGDAC_CTRL_3, 0xA6}, - {WCD938X_FLYBACK_CTRL_1, 0x65}, - {WCD938X_FLYBACK_TEST_CTL, 0x00}, - {WCD938X_RX_AUX_SW_CTL, 0x00}, - {WCD938X_RX_PA_AUX_IN_CONN, 0x01}, - {WCD938X_RX_TIMER_DIV, 0x32}, - {WCD938X_RX_OCP_CTL, 0x1F}, - {WCD938X_RX_OCP_COUNT, 0x77}, - {WCD938X_RX_BIAS_EAR_DAC, 0xA0}, - {WCD938X_RX_BIAS_EAR_AMP, 0xAA}, - {WCD938X_RX_BIAS_HPH_LDO, 0xA9}, - {WCD938X_RX_BIAS_HPH_PA, 0xAA}, - {WCD938X_RX_BIAS_HPH_RDACBUFF_CNP2, 0x8A}, - {WCD938X_RX_BIAS_HPH_RDAC_LDO, 0x88}, - {WCD938X_RX_BIAS_HPH_CNP1, 0x82}, - {WCD938X_RX_BIAS_HPH_LOWPOWER, 0x82}, - {WCD938X_RX_BIAS_AUX_DAC, 0xA0}, - {WCD938X_RX_BIAS_AUX_AMP, 0xAA}, - {WCD938X_RX_BIAS_VNEGDAC_BLEEDER, 0x50}, - {WCD938X_RX_BIAS_MISC, 0x00}, - {WCD938X_RX_BIAS_BUCK_RST, 0x08}, - {WCD938X_RX_BIAS_BUCK_VREF_ERRAMP, 0x44}, - {WCD938X_RX_BIAS_FLYB_ERRAMP, 0x40}, - {WCD938X_RX_BIAS_FLYB_BUFF, 0xAA}, - {WCD938X_RX_BIAS_FLYB_MID_RST, 0x14}, - {WCD938X_HPH_L_STATUS, 0x04}, - {WCD938X_HPH_R_STATUS, 0x04}, - {WCD938X_HPH_CNP_EN, 0x80}, - {WCD938X_HPH_CNP_WG_CTL, 0x9A}, - {WCD938X_HPH_CNP_WG_TIME, 0x14}, - {WCD938X_HPH_OCP_CTL, 0x28}, - {WCD938X_HPH_AUTO_CHOP, 0x16}, - {WCD938X_HPH_CHOP_CTL, 0x83}, - {WCD938X_HPH_PA_CTL1, 0x46}, - {WCD938X_HPH_PA_CTL2, 0x50}, - {WCD938X_HPH_L_EN, 0x80}, - {WCD938X_HPH_L_TEST, 0xE0}, - {WCD938X_HPH_L_ATEST, 0x50}, - {WCD938X_HPH_R_EN, 0x80}, - {WCD938X_HPH_R_TEST, 0xE0}, - {WCD938X_HPH_R_ATEST, 0x54}, - {WCD938X_HPH_RDAC_CLK_CTL1, 0x99}, - {WCD938X_HPH_RDAC_CLK_CTL2, 0x9B}, - {WCD938X_HPH_RDAC_LDO_CTL, 0x33}, - {WCD938X_HPH_RDAC_CHOP_CLK_LP_CTL, 0x00}, - {WCD938X_HPH_REFBUFF_UHQA_CTL, 0x68}, - {WCD938X_HPH_REFBUFF_LP_CTL, 0x0E}, - {WCD938X_HPH_L_DAC_CTL, 0x20}, - {WCD938X_HPH_R_DAC_CTL, 0x20}, - {WCD938X_HPH_SURGE_HPHLR_SURGE_COMP_SEL, 0x55}, - {WCD938X_HPH_SURGE_HPHLR_SURGE_EN, 0x19}, - {WCD938X_HPH_SURGE_HPHLR_SURGE_MISC1, 0xA0}, - {WCD938X_HPH_SURGE_HPHLR_SURGE_STATUS, 0x00}, - {WCD938X_EAR_EAR_EN_REG, 0x22}, - {WCD938X_EAR_EAR_PA_CON, 0x44}, - {WCD938X_EAR_EAR_SP_CON, 0xDB}, - {WCD938X_EAR_EAR_DAC_CON, 0x80}, - {WCD938X_EAR_EAR_CNP_FSM_CON, 0xB2}, - {WCD938X_EAR_TEST_CTL, 0x00}, - {WCD938X_EAR_STATUS_REG_1, 0x00}, - {WCD938X_EAR_STATUS_REG_2, 0x08}, - {WCD938X_ANA_NEW_PAGE_REGISTER, 0x00}, - {WCD938X_HPH_NEW_ANA_HPH2, 0x00}, - {WCD938X_HPH_NEW_ANA_HPH3, 0x00}, - {WCD938X_SLEEP_CTL, 0x16}, - {WCD938X_SLEEP_WATCHDOG_CTL, 0x00}, - {WCD938X_MBHC_NEW_ELECT_REM_CLAMP_CTL, 0x00}, - {WCD938X_MBHC_NEW_CTL_1, 0x02}, - {WCD938X_MBHC_NEW_CTL_2, 0x05}, - {WCD938X_MBHC_NEW_PLUG_DETECT_CTL, 0xE9}, - {WCD938X_MBHC_NEW_ZDET_ANA_CTL, 0x0F}, - {WCD938X_MBHC_NEW_ZDET_RAMP_CTL, 0x00}, - {WCD938X_MBHC_NEW_FSM_STATUS, 0x00}, - {WCD938X_MBHC_NEW_ADC_RESULT, 0x00}, - {WCD938X_TX_NEW_AMIC_MUX_CFG, 0x00}, - {WCD938X_AUX_AUXPA, 0x00}, - {WCD938X_LDORXTX_MODE, 0x0C}, - {WCD938X_LDORXTX_CONFIG, 0x10}, - {WCD938X_DIE_CRACK_DIE_CRK_DET_EN, 0x00}, - {WCD938X_DIE_CRACK_DIE_CRK_DET_OUT, 0x00}, - {WCD938X_HPH_NEW_INT_RDAC_GAIN_CTL, 0x40}, - {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L, 0x81}, - {WCD938X_HPH_NEW_INT_RDAC_VREF_CTL, 0x10}, - {WCD938X_HPH_NEW_INT_RDAC_OVERRIDE_CTL, 0x00}, - {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R, 0x81}, - {WCD938X_HPH_NEW_INT_PA_MISC1, 0x22}, - {WCD938X_HPH_NEW_INT_PA_MISC2, 0x00}, - {WCD938X_HPH_NEW_INT_PA_RDAC_MISC, 0x00}, - {WCD938X_HPH_NEW_INT_HPH_TIMER1, 0xFE}, - {WCD938X_HPH_NEW_INT_HPH_TIMER2, 0x02}, - {WCD938X_HPH_NEW_INT_HPH_TIMER3, 0x4E}, - {WCD938X_HPH_NEW_INT_HPH_TIMER4, 0x54}, - {WCD938X_HPH_NEW_INT_PA_RDAC_MISC2, 0x00}, - {WCD938X_HPH_NEW_INT_PA_RDAC_MISC3, 0x00}, - {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L_NEW, 0x90}, - {WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R_NEW, 0x90}, - {WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_LOHIFI, 0x62}, - {WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_ULP, 0x01}, - {WCD938X_RX_NEW_INT_HPH_RDAC_LDO_LP, 0x11}, - {WCD938X_MBHC_NEW_INT_MOISTURE_DET_DC_CTRL, 0x57}, - {WCD938X_MBHC_NEW_INT_MOISTURE_DET_POLLING_CTRL, 0x01}, - {WCD938X_MBHC_NEW_INT_MECH_DET_CURRENT, 0x00}, - {WCD938X_MBHC_NEW_INT_SPARE_2, 0x00}, - {WCD938X_EAR_INT_NEW_EAR_CHOPPER_CON, 0xA8}, - {WCD938X_EAR_INT_NEW_CNP_VCM_CON1, 0x42}, - {WCD938X_EAR_INT_NEW_CNP_VCM_CON2, 0x22}, - {WCD938X_EAR_INT_NEW_EAR_DYNAMIC_BIAS, 0x00}, - {WCD938X_AUX_INT_EN_REG, 0x00}, - {WCD938X_AUX_INT_PA_CTRL, 0x06}, - {WCD938X_AUX_INT_SP_CTRL, 0xD2}, - {WCD938X_AUX_INT_DAC_CTRL, 0x80}, - {WCD938X_AUX_INT_CLK_CTRL, 0x50}, - {WCD938X_AUX_INT_TEST_CTRL, 0x00}, - {WCD938X_AUX_INT_STATUS_REG, 0x00}, - {WCD938X_AUX_INT_MISC, 0x00}, - {WCD938X_LDORXTX_INT_BIAS, 0x6E}, - {WCD938X_LDORXTX_INT_STB_LOADS_DTEST, 0x50}, - {WCD938X_LDORXTX_INT_TEST0, 0x1C}, - {WCD938X_LDORXTX_INT_STARTUP_TIMER, 0xFF}, - {WCD938X_LDORXTX_INT_TEST1, 0x1F}, - {WCD938X_LDORXTX_INT_STATUS, 0x00}, - {WCD938X_SLEEP_INT_WATCHDOG_CTL_1, 0x0A}, - {WCD938X_SLEEP_INT_WATCHDOG_CTL_2, 0x0A}, - {WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT1, 0x02}, - {WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT2, 0x60}, - {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L2, 0xFF}, - {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L1, 0x7F}, - {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L0, 0x3F}, - {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP1P2M, 0x1F}, - {WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP0P6M, 0x0F}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L2L1, 0xD7}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L0, 0xC8}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_ULP, 0xC6}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L2L1, 0xD5}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L0, 0xCA}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_ULP, 0x05}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_L2L1L0, 0xA5}, - {WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_ULP, 0x13}, - {WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L2L1, 0x88}, - {WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L0ULP, 0x42}, - {WCD938X_TX_COM_NEW_INT_TXADC_INT_L2, 0xFF}, - {WCD938X_TX_COM_NEW_INT_TXADC_INT_L1, 0x64}, - {WCD938X_TX_COM_NEW_INT_TXADC_INT_L0, 0x64}, - {WCD938X_TX_COM_NEW_INT_TXADC_INT_ULP, 0x77}, - {WCD938X_DIGITAL_PAGE_REGISTER, 0x00}, - {WCD938X_DIGITAL_CHIP_ID0, 0x00}, - {WCD938X_DIGITAL_CHIP_ID1, 0x00}, - {WCD938X_DIGITAL_CHIP_ID2, 0x0D}, - {WCD938X_DIGITAL_CHIP_ID3, 0x01}, - {WCD938X_DIGITAL_SWR_TX_CLK_RATE, 0x00}, - {WCD938X_DIGITAL_CDC_RST_CTL, 0x03}, - {WCD938X_DIGITAL_TOP_CLK_CFG, 0x00}, - {WCD938X_DIGITAL_CDC_ANA_CLK_CTL, 0x00}, - {WCD938X_DIGITAL_CDC_DIG_CLK_CTL, 0xF0}, - {WCD938X_DIGITAL_SWR_RST_EN, 0x00}, - {WCD938X_DIGITAL_CDC_PATH_MODE, 0x55}, - {WCD938X_DIGITAL_CDC_RX_RST, 0x00}, - {WCD938X_DIGITAL_CDC_RX0_CTL, 0xFC}, - {WCD938X_DIGITAL_CDC_RX1_CTL, 0xFC}, - {WCD938X_DIGITAL_CDC_RX2_CTL, 0xFC}, - {WCD938X_DIGITAL_CDC_TX_ANA_MODE_0_1, 0x00}, - {WCD938X_DIGITAL_CDC_TX_ANA_MODE_2_3, 0x00}, - {WCD938X_DIGITAL_CDC_COMP_CTL_0, 0x00}, - {WCD938X_DIGITAL_CDC_ANA_TX_CLK_CTL, 0x1E}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A1_0, 0x00}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A1_1, 0x01}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A2_0, 0x63}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A2_1, 0x04}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A3_0, 0xAC}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A3_1, 0x04}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A4_0, 0x1A}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A4_1, 0x03}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A5_0, 0xBC}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A5_1, 0x02}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A6_0, 0xC7}, - {WCD938X_DIGITAL_CDC_HPH_DSM_A7_0, 0xF8}, - {WCD938X_DIGITAL_CDC_HPH_DSM_C_0, 0x47}, - {WCD938X_DIGITAL_CDC_HPH_DSM_C_1, 0x43}, - {WCD938X_DIGITAL_CDC_HPH_DSM_C_2, 0xB1}, - {WCD938X_DIGITAL_CDC_HPH_DSM_C_3, 0x17}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R1, 0x4D}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R2, 0x29}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R3, 0x34}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R4, 0x59}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R5, 0x66}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R6, 0x87}, - {WCD938X_DIGITAL_CDC_HPH_DSM_R7, 0x64}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A1_0, 0x00}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A1_1, 0x01}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A2_0, 0x96}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A2_1, 0x09}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A3_0, 0xAB}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A3_1, 0x05}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A4_0, 0x1C}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A4_1, 0x02}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A5_0, 0x17}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A5_1, 0x02}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A6_0, 0xAA}, - {WCD938X_DIGITAL_CDC_AUX_DSM_A7_0, 0xE3}, - {WCD938X_DIGITAL_CDC_AUX_DSM_C_0, 0x69}, - {WCD938X_DIGITAL_CDC_AUX_DSM_C_1, 0x54}, - {WCD938X_DIGITAL_CDC_AUX_DSM_C_2, 0x02}, - {WCD938X_DIGITAL_CDC_AUX_DSM_C_3, 0x15}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R1, 0xA4}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R2, 0xB5}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R3, 0x86}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R4, 0x85}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R5, 0xAA}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R6, 0xE2}, - {WCD938X_DIGITAL_CDC_AUX_DSM_R7, 0x62}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_RX_0, 0x55}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_RX_1, 0xA9}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_0, 0x3D}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_1, 0x2E}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_2, 0x01}, - {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_0, 0x00}, - {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_1, 0xFC}, - {WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_2, 0x01}, - {WCD938X_DIGITAL_CDC_HPH_GAIN_CTL, 0x00}, - {WCD938X_DIGITAL_CDC_AUX_GAIN_CTL, 0x00}, - {WCD938X_DIGITAL_CDC_EAR_PATH_CTL, 0x00}, - {WCD938X_DIGITAL_CDC_SWR_CLH, 0x00}, - {WCD938X_DIGITAL_SWR_CLH_BYP, 0x00}, - {WCD938X_DIGITAL_CDC_TX0_CTL, 0x68}, - {WCD938X_DIGITAL_CDC_TX1_CTL, 0x68}, - {WCD938X_DIGITAL_CDC_TX2_CTL, 0x68}, - {WCD938X_DIGITAL_CDC_TX_RST, 0x00}, - {WCD938X_DIGITAL_CDC_REQ_CTL, 0x01}, - {WCD938X_DIGITAL_CDC_RST, 0x00}, - {WCD938X_DIGITAL_CDC_AMIC_CTL, 0x0F}, - {WCD938X_DIGITAL_CDC_DMIC_CTL, 0x04}, - {WCD938X_DIGITAL_CDC_DMIC1_CTL, 0x01}, - {WCD938X_DIGITAL_CDC_DMIC2_CTL, 0x01}, - {WCD938X_DIGITAL_CDC_DMIC3_CTL, 0x01}, - {WCD938X_DIGITAL_CDC_DMIC4_CTL, 0x01}, - {WCD938X_DIGITAL_EFUSE_PRG_CTL, 0x00}, - {WCD938X_DIGITAL_EFUSE_CTL, 0x2B}, - {WCD938X_DIGITAL_CDC_DMIC_RATE_1_2, 0x11}, - {WCD938X_DIGITAL_CDC_DMIC_RATE_3_4, 0x11}, - {WCD938X_DIGITAL_PDM_WD_CTL0, 0x00}, - {WCD938X_DIGITAL_PDM_WD_CTL1, 0x00}, - {WCD938X_DIGITAL_PDM_WD_CTL2, 0x00}, - {WCD938X_DIGITAL_INTR_MODE, 0x00}, - {WCD938X_DIGITAL_INTR_MASK_0, 0xFF}, - {WCD938X_DIGITAL_INTR_MASK_1, 0xFF}, - {WCD938X_DIGITAL_INTR_MASK_2, 0x3F}, - {WCD938X_DIGITAL_INTR_STATUS_0, 0x00}, - {WCD938X_DIGITAL_INTR_STATUS_1, 0x00}, - {WCD938X_DIGITAL_INTR_STATUS_2, 0x00}, - {WCD938X_DIGITAL_INTR_CLEAR_0, 0x00}, - {WCD938X_DIGITAL_INTR_CLEAR_1, 0x00}, - {WCD938X_DIGITAL_INTR_CLEAR_2, 0x00}, - {WCD938X_DIGITAL_INTR_LEVEL_0, 0x00}, - {WCD938X_DIGITAL_INTR_LEVEL_1, 0x00}, - {WCD938X_DIGITAL_INTR_LEVEL_2, 0x00}, - {WCD938X_DIGITAL_INTR_SET_0, 0x00}, - {WCD938X_DIGITAL_INTR_SET_1, 0x00}, - {WCD938X_DIGITAL_INTR_SET_2, 0x00}, - {WCD938X_DIGITAL_INTR_TEST_0, 0x00}, - {WCD938X_DIGITAL_INTR_TEST_1, 0x00}, - {WCD938X_DIGITAL_INTR_TEST_2, 0x00}, - {WCD938X_DIGITAL_TX_MODE_DBG_EN, 0x00}, - {WCD938X_DIGITAL_TX_MODE_DBG_0_1, 0x00}, - {WCD938X_DIGITAL_TX_MODE_DBG_2_3, 0x00}, - {WCD938X_DIGITAL_LB_IN_SEL_CTL, 0x00}, - {WCD938X_DIGITAL_LOOP_BACK_MODE, 0x00}, - {WCD938X_DIGITAL_SWR_DAC_TEST, 0x00}, - {WCD938X_DIGITAL_SWR_HM_TEST_RX_0, 0x40}, - {WCD938X_DIGITAL_SWR_HM_TEST_TX_0, 0x40}, - {WCD938X_DIGITAL_SWR_HM_TEST_RX_1, 0x00}, - {WCD938X_DIGITAL_SWR_HM_TEST_TX_1, 0x00}, - {WCD938X_DIGITAL_SWR_HM_TEST_TX_2, 0x00}, - {WCD938X_DIGITAL_SWR_HM_TEST_0, 0x00}, - {WCD938X_DIGITAL_SWR_HM_TEST_1, 0x00}, - {WCD938X_DIGITAL_PAD_CTL_SWR_0, 0x8F}, - {WCD938X_DIGITAL_PAD_CTL_SWR_1, 0x06}, - {WCD938X_DIGITAL_I2C_CTL, 0x00}, - {WCD938X_DIGITAL_CDC_TX_TANGGU_SW_MODE, 0x00}, - {WCD938X_DIGITAL_EFUSE_TEST_CTL_0, 0x00}, - {WCD938X_DIGITAL_EFUSE_TEST_CTL_1, 0x00}, - {WCD938X_DIGITAL_EFUSE_T_DATA_0, 0x00}, - {WCD938X_DIGITAL_EFUSE_T_DATA_1, 0x00}, - {WCD938X_DIGITAL_PAD_CTL_PDM_RX0, 0xF1}, - {WCD938X_DIGITAL_PAD_CTL_PDM_RX1, 0xF1}, - {WCD938X_DIGITAL_PAD_CTL_PDM_TX0, 0xF1}, - {WCD938X_DIGITAL_PAD_CTL_PDM_TX1, 0xF1}, - {WCD938X_DIGITAL_PAD_CTL_PDM_TX2, 0xF1}, - {WCD938X_DIGITAL_PAD_INP_DIS_0, 0x00}, - {WCD938X_DIGITAL_PAD_INP_DIS_1, 0x00}, - {WCD938X_DIGITAL_DRIVE_STRENGTH_0, 0x00}, - {WCD938X_DIGITAL_DRIVE_STRENGTH_1, 0x00}, - {WCD938X_DIGITAL_DRIVE_STRENGTH_2, 0x00}, - {WCD938X_DIGITAL_RX_DATA_EDGE_CTL, 0x1F}, - {WCD938X_DIGITAL_TX_DATA_EDGE_CTL, 0x80}, - {WCD938X_DIGITAL_GPIO_MODE, 0x00}, - {WCD938X_DIGITAL_PIN_CTL_OE, 0x00}, - {WCD938X_DIGITAL_PIN_CTL_DATA_0, 0x00}, - {WCD938X_DIGITAL_PIN_CTL_DATA_1, 0x00}, - {WCD938X_DIGITAL_PIN_STATUS_0, 0x00}, - {WCD938X_DIGITAL_PIN_STATUS_1, 0x00}, - {WCD938X_DIGITAL_DIG_DEBUG_CTL, 0x00}, - {WCD938X_DIGITAL_DIG_DEBUG_EN, 0x00}, - {WCD938X_DIGITAL_ANA_CSR_DBG_ADD, 0x00}, - {WCD938X_DIGITAL_ANA_CSR_DBG_CTL, 0x48}, - {WCD938X_DIGITAL_SSP_DBG, 0x00}, - {WCD938X_DIGITAL_MODE_STATUS_0, 0x00}, - {WCD938X_DIGITAL_MODE_STATUS_1, 0x00}, - {WCD938X_DIGITAL_SPARE_0, 0x00}, - {WCD938X_DIGITAL_SPARE_1, 0x00}, - {WCD938X_DIGITAL_SPARE_2, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_0, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_1, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_2, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_3, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_4, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_5, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_6, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_7, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_8, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_9, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_10, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_11, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_12, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_13, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_14, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_15, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_16, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_17, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_18, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_19, 0xFF}, - {WCD938X_DIGITAL_EFUSE_REG_20, 0x0E}, - {WCD938X_DIGITAL_EFUSE_REG_21, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_22, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_23, 0xF8}, - {WCD938X_DIGITAL_EFUSE_REG_24, 0x16}, - {WCD938X_DIGITAL_EFUSE_REG_25, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_26, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_27, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_28, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_29, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_30, 0x00}, - {WCD938X_DIGITAL_EFUSE_REG_31, 0x00}, - {WCD938X_DIGITAL_TX_REQ_FB_CTL_0, 0x88}, - {WCD938X_DIGITAL_TX_REQ_FB_CTL_1, 0x88}, - {WCD938X_DIGITAL_TX_REQ_FB_CTL_2, 0x88}, - {WCD938X_DIGITAL_TX_REQ_FB_CTL_3, 0x88}, - {WCD938X_DIGITAL_TX_REQ_FB_CTL_4, 0x88}, - {WCD938X_DIGITAL_DEM_BYPASS_DATA0, 0x55}, - {WCD938X_DIGITAL_DEM_BYPASS_DATA1, 0x55}, - {WCD938X_DIGITAL_DEM_BYPASS_DATA2, 0x55}, - {WCD938X_DIGITAL_DEM_BYPASS_DATA3, 0x01}, -}; - -static bool wcd938x_rdwr_register(struct device *dev, unsigned int reg) -{ - switch (reg) { - case WCD938X_ANA_PAGE_REGISTER: - case WCD938X_ANA_BIAS: - case WCD938X_ANA_RX_SUPPLIES: - case WCD938X_ANA_HPH: - case WCD938X_ANA_EAR: - case WCD938X_ANA_EAR_COMPANDER_CTL: - case WCD938X_ANA_TX_CH1: - case WCD938X_ANA_TX_CH2: - case WCD938X_ANA_TX_CH3: - case WCD938X_ANA_TX_CH4: - case WCD938X_ANA_MICB1_MICB2_DSP_EN_LOGIC: - case WCD938X_ANA_MICB3_DSP_EN_LOGIC: - case WCD938X_ANA_MBHC_MECH: - case WCD938X_ANA_MBHC_ELECT: - case WCD938X_ANA_MBHC_ZDET: - case WCD938X_ANA_MBHC_BTN0: - case WCD938X_ANA_MBHC_BTN1: - case WCD938X_ANA_MBHC_BTN2: - case WCD938X_ANA_MBHC_BTN3: - case WCD938X_ANA_MBHC_BTN4: - case WCD938X_ANA_MBHC_BTN5: - case WCD938X_ANA_MBHC_BTN6: - case WCD938X_ANA_MBHC_BTN7: - case WCD938X_ANA_MICB1: - case WCD938X_ANA_MICB2: - case WCD938X_ANA_MICB2_RAMP: - case WCD938X_ANA_MICB3: - case WCD938X_ANA_MICB4: - case WCD938X_BIAS_CTL: - case WCD938X_BIAS_VBG_FINE_ADJ: - case WCD938X_LDOL_VDDCX_ADJUST: - case WCD938X_LDOL_DISABLE_LDOL: - case WCD938X_MBHC_CTL_CLK: - case WCD938X_MBHC_CTL_ANA: - case WCD938X_MBHC_CTL_SPARE_1: - case WCD938X_MBHC_CTL_SPARE_2: - case WCD938X_MBHC_CTL_BCS: - case WCD938X_MBHC_TEST_CTL: - case WCD938X_LDOH_MODE: - case WCD938X_LDOH_BIAS: - case WCD938X_LDOH_STB_LOADS: - case WCD938X_LDOH_SLOWRAMP: - case WCD938X_MICB1_TEST_CTL_1: - case WCD938X_MICB1_TEST_CTL_2: - case WCD938X_MICB1_TEST_CTL_3: - case WCD938X_MICB2_TEST_CTL_1: - case WCD938X_MICB2_TEST_CTL_2: - case WCD938X_MICB2_TEST_CTL_3: - case WCD938X_MICB3_TEST_CTL_1: - case WCD938X_MICB3_TEST_CTL_2: - case WCD938X_MICB3_TEST_CTL_3: - case WCD938X_MICB4_TEST_CTL_1: - case WCD938X_MICB4_TEST_CTL_2: - case WCD938X_MICB4_TEST_CTL_3: - case WCD938X_TX_COM_ADC_VCM: - case WCD938X_TX_COM_BIAS_ATEST: - case WCD938X_TX_COM_SPARE1: - case WCD938X_TX_COM_SPARE2: - case WCD938X_TX_COM_TXFE_DIV_CTL: - case WCD938X_TX_COM_TXFE_DIV_START: - case WCD938X_TX_COM_SPARE3: - case WCD938X_TX_COM_SPARE4: - case WCD938X_TX_1_2_TEST_EN: - case WCD938X_TX_1_2_ADC_IB: - case WCD938X_TX_1_2_ATEST_REFCTL: - case WCD938X_TX_1_2_TEST_CTL: - case WCD938X_TX_1_2_TEST_BLK_EN1: - case WCD938X_TX_1_2_TXFE1_CLKDIV: - case WCD938X_TX_3_4_TEST_EN: - case WCD938X_TX_3_4_ADC_IB: - case WCD938X_TX_3_4_ATEST_REFCTL: - case WCD938X_TX_3_4_TEST_CTL: - case WCD938X_TX_3_4_TEST_BLK_EN3: - case WCD938X_TX_3_4_TXFE3_CLKDIV: - case WCD938X_TX_3_4_TEST_BLK_EN2: - case WCD938X_TX_3_4_TXFE2_CLKDIV: - case WCD938X_TX_3_4_SPARE1: - case WCD938X_TX_3_4_TEST_BLK_EN4: - case WCD938X_TX_3_4_TXFE4_CLKDIV: - case WCD938X_TX_3_4_SPARE2: - case WCD938X_CLASSH_MODE_1: - case WCD938X_CLASSH_MODE_2: - case WCD938X_CLASSH_MODE_3: - case WCD938X_CLASSH_CTRL_VCL_1: - case WCD938X_CLASSH_CTRL_VCL_2: - case WCD938X_CLASSH_CTRL_CCL_1: - case WCD938X_CLASSH_CTRL_CCL_2: - case WCD938X_CLASSH_CTRL_CCL_3: - case WCD938X_CLASSH_CTRL_CCL_4: - case WCD938X_CLASSH_CTRL_CCL_5: - case WCD938X_CLASSH_BUCK_TMUX_A_D: - case WCD938X_CLASSH_BUCK_SW_DRV_CNTL: - case WCD938X_CLASSH_SPARE: - case WCD938X_FLYBACK_EN: - case WCD938X_FLYBACK_VNEG_CTRL_1: - case WCD938X_FLYBACK_VNEG_CTRL_2: - case WCD938X_FLYBACK_VNEG_CTRL_3: - case WCD938X_FLYBACK_VNEG_CTRL_4: - case WCD938X_FLYBACK_VNEG_CTRL_5: - case WCD938X_FLYBACK_VNEG_CTRL_6: - case WCD938X_FLYBACK_VNEG_CTRL_7: - case WCD938X_FLYBACK_VNEG_CTRL_8: - case WCD938X_FLYBACK_VNEG_CTRL_9: - case WCD938X_FLYBACK_VNEGDAC_CTRL_1: - case WCD938X_FLYBACK_VNEGDAC_CTRL_2: - case WCD938X_FLYBACK_VNEGDAC_CTRL_3: - case WCD938X_FLYBACK_CTRL_1: - case WCD938X_FLYBACK_TEST_CTL: - case WCD938X_RX_AUX_SW_CTL: - case WCD938X_RX_PA_AUX_IN_CONN: - case WCD938X_RX_TIMER_DIV: - case WCD938X_RX_OCP_CTL: - case WCD938X_RX_OCP_COUNT: - case WCD938X_RX_BIAS_EAR_DAC: - case WCD938X_RX_BIAS_EAR_AMP: - case WCD938X_RX_BIAS_HPH_LDO: - case WCD938X_RX_BIAS_HPH_PA: - case WCD938X_RX_BIAS_HPH_RDACBUFF_CNP2: - case WCD938X_RX_BIAS_HPH_RDAC_LDO: - case WCD938X_RX_BIAS_HPH_CNP1: - case WCD938X_RX_BIAS_HPH_LOWPOWER: - case WCD938X_RX_BIAS_AUX_DAC: - case WCD938X_RX_BIAS_AUX_AMP: - case WCD938X_RX_BIAS_VNEGDAC_BLEEDER: - case WCD938X_RX_BIAS_MISC: - case WCD938X_RX_BIAS_BUCK_RST: - case WCD938X_RX_BIAS_BUCK_VREF_ERRAMP: - case WCD938X_RX_BIAS_FLYB_ERRAMP: - case WCD938X_RX_BIAS_FLYB_BUFF: - case WCD938X_RX_BIAS_FLYB_MID_RST: - case WCD938X_HPH_CNP_EN: - case WCD938X_HPH_CNP_WG_CTL: - case WCD938X_HPH_CNP_WG_TIME: - case WCD938X_HPH_OCP_CTL: - case WCD938X_HPH_AUTO_CHOP: - case WCD938X_HPH_CHOP_CTL: - case WCD938X_HPH_PA_CTL1: - case WCD938X_HPH_PA_CTL2: - case WCD938X_HPH_L_EN: - case WCD938X_HPH_L_TEST: - case WCD938X_HPH_L_ATEST: - case WCD938X_HPH_R_EN: - case WCD938X_HPH_R_TEST: - case WCD938X_HPH_R_ATEST: - case WCD938X_HPH_RDAC_CLK_CTL1: - case WCD938X_HPH_RDAC_CLK_CTL2: - case WCD938X_HPH_RDAC_LDO_CTL: - case WCD938X_HPH_RDAC_CHOP_CLK_LP_CTL: - case WCD938X_HPH_REFBUFF_UHQA_CTL: - case WCD938X_HPH_REFBUFF_LP_CTL: - case WCD938X_HPH_L_DAC_CTL: - case WCD938X_HPH_R_DAC_CTL: - case WCD938X_HPH_SURGE_HPHLR_SURGE_COMP_SEL: - case WCD938X_HPH_SURGE_HPHLR_SURGE_EN: - case WCD938X_HPH_SURGE_HPHLR_SURGE_MISC1: - case WCD938X_EAR_EAR_EN_REG: - case WCD938X_EAR_EAR_PA_CON: - case WCD938X_EAR_EAR_SP_CON: - case WCD938X_EAR_EAR_DAC_CON: - case WCD938X_EAR_EAR_CNP_FSM_CON: - case WCD938X_EAR_TEST_CTL: - case WCD938X_ANA_NEW_PAGE_REGISTER: - case WCD938X_HPH_NEW_ANA_HPH2: - case WCD938X_HPH_NEW_ANA_HPH3: - case WCD938X_SLEEP_CTL: - case WCD938X_SLEEP_WATCHDOG_CTL: - case WCD938X_MBHC_NEW_ELECT_REM_CLAMP_CTL: - case WCD938X_MBHC_NEW_CTL_1: - case WCD938X_MBHC_NEW_CTL_2: - case WCD938X_MBHC_NEW_PLUG_DETECT_CTL: - case WCD938X_MBHC_NEW_ZDET_ANA_CTL: - case WCD938X_MBHC_NEW_ZDET_RAMP_CTL: - case WCD938X_TX_NEW_AMIC_MUX_CFG: - case WCD938X_AUX_AUXPA: - case WCD938X_LDORXTX_MODE: - case WCD938X_LDORXTX_CONFIG: - case WCD938X_DIE_CRACK_DIE_CRK_DET_EN: - case WCD938X_HPH_NEW_INT_RDAC_GAIN_CTL: - case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L: - case WCD938X_HPH_NEW_INT_RDAC_VREF_CTL: - case WCD938X_HPH_NEW_INT_RDAC_OVERRIDE_CTL: - case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R: - case WCD938X_HPH_NEW_INT_PA_MISC1: - case WCD938X_HPH_NEW_INT_PA_MISC2: - case WCD938X_HPH_NEW_INT_PA_RDAC_MISC: - case WCD938X_HPH_NEW_INT_HPH_TIMER1: - case WCD938X_HPH_NEW_INT_HPH_TIMER2: - case WCD938X_HPH_NEW_INT_HPH_TIMER3: - case WCD938X_HPH_NEW_INT_HPH_TIMER4: - case WCD938X_HPH_NEW_INT_PA_RDAC_MISC2: - case WCD938X_HPH_NEW_INT_PA_RDAC_MISC3: - case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_L_NEW: - case WCD938X_HPH_NEW_INT_RDAC_HD2_CTL_R_NEW: - case WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_LOHIFI: - case WCD938X_RX_NEW_INT_HPH_RDAC_BIAS_ULP: - case WCD938X_RX_NEW_INT_HPH_RDAC_LDO_LP: - case WCD938X_MBHC_NEW_INT_MOISTURE_DET_DC_CTRL: - case WCD938X_MBHC_NEW_INT_MOISTURE_DET_POLLING_CTRL: - case WCD938X_MBHC_NEW_INT_MECH_DET_CURRENT: - case WCD938X_MBHC_NEW_INT_SPARE_2: - case WCD938X_EAR_INT_NEW_EAR_CHOPPER_CON: - case WCD938X_EAR_INT_NEW_CNP_VCM_CON1: - case WCD938X_EAR_INT_NEW_CNP_VCM_CON2: - case WCD938X_EAR_INT_NEW_EAR_DYNAMIC_BIAS: - case WCD938X_AUX_INT_EN_REG: - case WCD938X_AUX_INT_PA_CTRL: - case WCD938X_AUX_INT_SP_CTRL: - case WCD938X_AUX_INT_DAC_CTRL: - case WCD938X_AUX_INT_CLK_CTRL: - case WCD938X_AUX_INT_TEST_CTRL: - case WCD938X_AUX_INT_MISC: - case WCD938X_LDORXTX_INT_BIAS: - case WCD938X_LDORXTX_INT_STB_LOADS_DTEST: - case WCD938X_LDORXTX_INT_TEST0: - case WCD938X_LDORXTX_INT_STARTUP_TIMER: - case WCD938X_LDORXTX_INT_TEST1: - case WCD938X_SLEEP_INT_WATCHDOG_CTL_1: - case WCD938X_SLEEP_INT_WATCHDOG_CTL_2: - case WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT1: - case WCD938X_DIE_CRACK_INT_DIE_CRK_DET_INT2: - case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L2: - case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L1: - case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_L0: - case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP1P2M: - case WCD938X_TX_COM_NEW_INT_TXFE_DIVSTOP_ULP0P6M: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L2L1: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_L0: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG1_ULP: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L2L1: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_L0: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2MAIN_ULP: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_L2L1L0: - case WCD938X_TX_COM_NEW_INT_TXFE_ICTRL_STG2CASC_ULP: - case WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L2L1: - case WCD938X_TX_COM_NEW_INT_TXADC_SCBIAS_L0ULP: - case WCD938X_TX_COM_NEW_INT_TXADC_INT_L2: - case WCD938X_TX_COM_NEW_INT_TXADC_INT_L1: - case WCD938X_TX_COM_NEW_INT_TXADC_INT_L0: - case WCD938X_TX_COM_NEW_INT_TXADC_INT_ULP: - case WCD938X_DIGITAL_PAGE_REGISTER: - case WCD938X_DIGITAL_SWR_TX_CLK_RATE: - case WCD938X_DIGITAL_CDC_RST_CTL: - case WCD938X_DIGITAL_TOP_CLK_CFG: - case WCD938X_DIGITAL_CDC_ANA_CLK_CTL: - case WCD938X_DIGITAL_CDC_DIG_CLK_CTL: - case WCD938X_DIGITAL_SWR_RST_EN: - case WCD938X_DIGITAL_CDC_PATH_MODE: - case WCD938X_DIGITAL_CDC_RX_RST: - case WCD938X_DIGITAL_CDC_RX0_CTL: - case WCD938X_DIGITAL_CDC_RX1_CTL: - case WCD938X_DIGITAL_CDC_RX2_CTL: - case WCD938X_DIGITAL_CDC_TX_ANA_MODE_0_1: - case WCD938X_DIGITAL_CDC_TX_ANA_MODE_2_3: - case WCD938X_DIGITAL_CDC_COMP_CTL_0: - case WCD938X_DIGITAL_CDC_ANA_TX_CLK_CTL: - case WCD938X_DIGITAL_CDC_HPH_DSM_A1_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A1_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_A2_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A2_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_A3_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A3_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_A4_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A4_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_A5_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A5_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_A6_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_A7_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_C_0: - case WCD938X_DIGITAL_CDC_HPH_DSM_C_1: - case WCD938X_DIGITAL_CDC_HPH_DSM_C_2: - case WCD938X_DIGITAL_CDC_HPH_DSM_C_3: - case WCD938X_DIGITAL_CDC_HPH_DSM_R1: - case WCD938X_DIGITAL_CDC_HPH_DSM_R2: - case WCD938X_DIGITAL_CDC_HPH_DSM_R3: - case WCD938X_DIGITAL_CDC_HPH_DSM_R4: - case WCD938X_DIGITAL_CDC_HPH_DSM_R5: - case WCD938X_DIGITAL_CDC_HPH_DSM_R6: - case WCD938X_DIGITAL_CDC_HPH_DSM_R7: - case WCD938X_DIGITAL_CDC_AUX_DSM_A1_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A1_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_A2_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A2_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_A3_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A3_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_A4_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A4_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_A5_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A5_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_A6_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_A7_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_C_0: - case WCD938X_DIGITAL_CDC_AUX_DSM_C_1: - case WCD938X_DIGITAL_CDC_AUX_DSM_C_2: - case WCD938X_DIGITAL_CDC_AUX_DSM_C_3: - case WCD938X_DIGITAL_CDC_AUX_DSM_R1: - case WCD938X_DIGITAL_CDC_AUX_DSM_R2: - case WCD938X_DIGITAL_CDC_AUX_DSM_R3: - case WCD938X_DIGITAL_CDC_AUX_DSM_R4: - case WCD938X_DIGITAL_CDC_AUX_DSM_R5: - case WCD938X_DIGITAL_CDC_AUX_DSM_R6: - case WCD938X_DIGITAL_CDC_AUX_DSM_R7: - case WCD938X_DIGITAL_CDC_HPH_GAIN_RX_0: - case WCD938X_DIGITAL_CDC_HPH_GAIN_RX_1: - case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_0: - case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_1: - case WCD938X_DIGITAL_CDC_HPH_GAIN_DSD_2: - case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_0: - case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_1: - case WCD938X_DIGITAL_CDC_AUX_GAIN_DSD_2: - case WCD938X_DIGITAL_CDC_HPH_GAIN_CTL: - case WCD938X_DIGITAL_CDC_AUX_GAIN_CTL: - case WCD938X_DIGITAL_CDC_EAR_PATH_CTL: - case WCD938X_DIGITAL_CDC_SWR_CLH: - case WCD938X_DIGITAL_SWR_CLH_BYP: - case WCD938X_DIGITAL_CDC_TX0_CTL: - case WCD938X_DIGITAL_CDC_TX1_CTL: - case WCD938X_DIGITAL_CDC_TX2_CTL: - case WCD938X_DIGITAL_CDC_TX_RST: - case WCD938X_DIGITAL_CDC_REQ_CTL: - case WCD938X_DIGITAL_CDC_RST: - case WCD938X_DIGITAL_CDC_AMIC_CTL: - case WCD938X_DIGITAL_CDC_DMIC_CTL: - case WCD938X_DIGITAL_CDC_DMIC1_CTL: - case WCD938X_DIGITAL_CDC_DMIC2_CTL: - case WCD938X_DIGITAL_CDC_DMIC3_CTL: - case WCD938X_DIGITAL_CDC_DMIC4_CTL: - case WCD938X_DIGITAL_EFUSE_PRG_CTL: - case WCD938X_DIGITAL_EFUSE_CTL: - case WCD938X_DIGITAL_CDC_DMIC_RATE_1_2: - case WCD938X_DIGITAL_CDC_DMIC_RATE_3_4: - case WCD938X_DIGITAL_PDM_WD_CTL0: - case WCD938X_DIGITAL_PDM_WD_CTL1: - case WCD938X_DIGITAL_PDM_WD_CTL2: - case WCD938X_DIGITAL_INTR_MODE: - case WCD938X_DIGITAL_INTR_MASK_0: - case WCD938X_DIGITAL_INTR_MASK_1: - case WCD938X_DIGITAL_INTR_MASK_2: - case WCD938X_DIGITAL_INTR_CLEAR_0: - case WCD938X_DIGITAL_INTR_CLEAR_1: - case WCD938X_DIGITAL_INTR_CLEAR_2: - case WCD938X_DIGITAL_INTR_LEVEL_0: - case WCD938X_DIGITAL_INTR_LEVEL_1: - case WCD938X_DIGITAL_INTR_LEVEL_2: - case WCD938X_DIGITAL_INTR_SET_0: - case WCD938X_DIGITAL_INTR_SET_1: - case WCD938X_DIGITAL_INTR_SET_2: - case WCD938X_DIGITAL_INTR_TEST_0: - case WCD938X_DIGITAL_INTR_TEST_1: - case WCD938X_DIGITAL_INTR_TEST_2: - case WCD938X_DIGITAL_TX_MODE_DBG_EN: - case WCD938X_DIGITAL_TX_MODE_DBG_0_1: - case WCD938X_DIGITAL_TX_MODE_DBG_2_3: - case WCD938X_DIGITAL_LB_IN_SEL_CTL: - case WCD938X_DIGITAL_LOOP_BACK_MODE: - case WCD938X_DIGITAL_SWR_DAC_TEST: - case WCD938X_DIGITAL_SWR_HM_TEST_RX_0: - case WCD938X_DIGITAL_SWR_HM_TEST_TX_0: - case WCD938X_DIGITAL_SWR_HM_TEST_RX_1: - case WCD938X_DIGITAL_SWR_HM_TEST_TX_1: - case WCD938X_DIGITAL_SWR_HM_TEST_TX_2: - case WCD938X_DIGITAL_PAD_CTL_SWR_0: - case WCD938X_DIGITAL_PAD_CTL_SWR_1: - case WCD938X_DIGITAL_I2C_CTL: - case WCD938X_DIGITAL_CDC_TX_TANGGU_SW_MODE: - case WCD938X_DIGITAL_EFUSE_TEST_CTL_0: - case WCD938X_DIGITAL_EFUSE_TEST_CTL_1: - case WCD938X_DIGITAL_PAD_CTL_PDM_RX0: - case WCD938X_DIGITAL_PAD_CTL_PDM_RX1: - case WCD938X_DIGITAL_PAD_CTL_PDM_TX0: - case WCD938X_DIGITAL_PAD_CTL_PDM_TX1: - case WCD938X_DIGITAL_PAD_CTL_PDM_TX2: - case WCD938X_DIGITAL_PAD_INP_DIS_0: - case WCD938X_DIGITAL_PAD_INP_DIS_1: - case WCD938X_DIGITAL_DRIVE_STRENGTH_0: - case WCD938X_DIGITAL_DRIVE_STRENGTH_1: - case WCD938X_DIGITAL_DRIVE_STRENGTH_2: - case WCD938X_DIGITAL_RX_DATA_EDGE_CTL: - case WCD938X_DIGITAL_TX_DATA_EDGE_CTL: - case WCD938X_DIGITAL_GPIO_MODE: - case WCD938X_DIGITAL_PIN_CTL_OE: - case WCD938X_DIGITAL_PIN_CTL_DATA_0: - case WCD938X_DIGITAL_PIN_CTL_DATA_1: - case WCD938X_DIGITAL_DIG_DEBUG_CTL: - case WCD938X_DIGITAL_DIG_DEBUG_EN: - case WCD938X_DIGITAL_ANA_CSR_DBG_ADD: - case WCD938X_DIGITAL_ANA_CSR_DBG_CTL: - case WCD938X_DIGITAL_SSP_DBG: - case WCD938X_DIGITAL_SPARE_0: - case WCD938X_DIGITAL_SPARE_1: - case WCD938X_DIGITAL_SPARE_2: - case WCD938X_DIGITAL_TX_REQ_FB_CTL_0: - case WCD938X_DIGITAL_TX_REQ_FB_CTL_1: - case WCD938X_DIGITAL_TX_REQ_FB_CTL_2: - case WCD938X_DIGITAL_TX_REQ_FB_CTL_3: - case WCD938X_DIGITAL_TX_REQ_FB_CTL_4: - case WCD938X_DIGITAL_DEM_BYPASS_DATA0: - case WCD938X_DIGITAL_DEM_BYPASS_DATA1: - case WCD938X_DIGITAL_DEM_BYPASS_DATA2: - case WCD938X_DIGITAL_DEM_BYPASS_DATA3: - return true; - } - - return false; -} - -static bool wcd938x_readonly_register(struct device *dev, unsigned int reg) -{ - switch (reg) { - case WCD938X_ANA_MBHC_RESULT_1: - case WCD938X_ANA_MBHC_RESULT_2: - case WCD938X_ANA_MBHC_RESULT_3: - case WCD938X_MBHC_MOISTURE_DET_FSM_STATUS: - case WCD938X_TX_1_2_SAR2_ERR: - case WCD938X_TX_1_2_SAR1_ERR: - case WCD938X_TX_3_4_SAR4_ERR: - case WCD938X_TX_3_4_SAR3_ERR: - case WCD938X_HPH_L_STATUS: - case WCD938X_HPH_R_STATUS: - case WCD938X_HPH_SURGE_HPHLR_SURGE_STATUS: - case WCD938X_EAR_STATUS_REG_1: - case WCD938X_EAR_STATUS_REG_2: - case WCD938X_MBHC_NEW_FSM_STATUS: - case WCD938X_MBHC_NEW_ADC_RESULT: - case WCD938X_DIE_CRACK_DIE_CRK_DET_OUT: - case WCD938X_AUX_INT_STATUS_REG: - case WCD938X_LDORXTX_INT_STATUS: - case WCD938X_DIGITAL_CHIP_ID0: - case WCD938X_DIGITAL_CHIP_ID1: - case WCD938X_DIGITAL_CHIP_ID2: - case WCD938X_DIGITAL_CHIP_ID3: - case WCD938X_DIGITAL_INTR_STATUS_0: - case WCD938X_DIGITAL_INTR_STATUS_1: - case WCD938X_DIGITAL_INTR_STATUS_2: - case WCD938X_DIGITAL_INTR_CLEAR_0: - case WCD938X_DIGITAL_INTR_CLEAR_1: - case WCD938X_DIGITAL_INTR_CLEAR_2: - case WCD938X_DIGITAL_SWR_HM_TEST_0: - case WCD938X_DIGITAL_SWR_HM_TEST_1: - case WCD938X_DIGITAL_EFUSE_T_DATA_0: - case WCD938X_DIGITAL_EFUSE_T_DATA_1: - case WCD938X_DIGITAL_PIN_STATUS_0: - case WCD938X_DIGITAL_PIN_STATUS_1: - case WCD938X_DIGITAL_MODE_STATUS_0: - case WCD938X_DIGITAL_MODE_STATUS_1: - case WCD938X_DIGITAL_EFUSE_REG_0: - case WCD938X_DIGITAL_EFUSE_REG_1: - case WCD938X_DIGITAL_EFUSE_REG_2: - case WCD938X_DIGITAL_EFUSE_REG_3: - case WCD938X_DIGITAL_EFUSE_REG_4: - case WCD938X_DIGITAL_EFUSE_REG_5: - case WCD938X_DIGITAL_EFUSE_REG_6: - case WCD938X_DIGITAL_EFUSE_REG_7: - case WCD938X_DIGITAL_EFUSE_REG_8: - case WCD938X_DIGITAL_EFUSE_REG_9: - case WCD938X_DIGITAL_EFUSE_REG_10: - case WCD938X_DIGITAL_EFUSE_REG_11: - case WCD938X_DIGITAL_EFUSE_REG_12: - case WCD938X_DIGITAL_EFUSE_REG_13: - case WCD938X_DIGITAL_EFUSE_REG_14: - case WCD938X_DIGITAL_EFUSE_REG_15: - case WCD938X_DIGITAL_EFUSE_REG_16: - case WCD938X_DIGITAL_EFUSE_REG_17: - case WCD938X_DIGITAL_EFUSE_REG_18: - case WCD938X_DIGITAL_EFUSE_REG_19: - case WCD938X_DIGITAL_EFUSE_REG_20: - case WCD938X_DIGITAL_EFUSE_REG_21: - case WCD938X_DIGITAL_EFUSE_REG_22: - case WCD938X_DIGITAL_EFUSE_REG_23: - case WCD938X_DIGITAL_EFUSE_REG_24: - case WCD938X_DIGITAL_EFUSE_REG_25: - case WCD938X_DIGITAL_EFUSE_REG_26: - case WCD938X_DIGITAL_EFUSE_REG_27: - case WCD938X_DIGITAL_EFUSE_REG_28: - case WCD938X_DIGITAL_EFUSE_REG_29: - case WCD938X_DIGITAL_EFUSE_REG_30: - case WCD938X_DIGITAL_EFUSE_REG_31: - return true; - } - return false; -} - -static bool wcd938x_readable_register(struct device *dev, unsigned int reg) -{ - bool ret; - - ret = wcd938x_readonly_register(dev, reg); - if (!ret) - return wcd938x_rdwr_register(dev, reg); - - return ret; -} - -static bool wcd938x_writeable_register(struct device *dev, unsigned int reg) -{ - return wcd938x_rdwr_register(dev, reg); -} - -static bool wcd938x_volatile_register(struct device *dev, unsigned int reg) -{ - if (reg <= WCD938X_BASE_ADDRESS) - return false; - - if (reg == WCD938X_DIGITAL_SWR_TX_CLK_RATE) - return true; - - if (wcd938x_readonly_register(dev, reg)) - return true; - - return false; -} - -static struct regmap_config wcd938x_regmap_config = { - .name = "wcd938x_csr", - .reg_bits = 32, - .val_bits = 8, - .cache_type = REGCACHE_RBTREE, - .reg_defaults = wcd938x_defaults, - .num_reg_defaults = ARRAY_SIZE(wcd938x_defaults), - .max_register = WCD938X_MAX_REGISTER, - .readable_reg = wcd938x_readable_register, - .writeable_reg = wcd938x_writeable_register, - .volatile_reg = wcd938x_volatile_register, - .can_multi_write = true, -}; - static const struct regmap_irq wcd938x_irqs[WCD938X_NUM_IRQS] = { REGMAP_IRQ_REG(WCD938X_IRQ_MBHC_BUTTON_PRESS_DET, 0, 0x01), REGMAP_IRQ_REG(WCD938X_IRQ_MBHC_BUTTON_RELEASE_DET, 0, 0x02), @@ -4405,10 +3410,10 @@ static int wcd938x_bind(struct device *dev) return -EINVAL; } - wcd938x->regmap = devm_regmap_init_sdw(wcd938x->tx_sdw_dev, &wcd938x_regmap_config); - if (IS_ERR(wcd938x->regmap)) { - dev_err(dev, "%s: tx csr regmap not found\n", __func__); - return PTR_ERR(wcd938x->regmap); + wcd938x->regmap = dev_get_regmap(&wcd938x->tx_sdw_dev->dev, NULL); + if (!wcd938x->regmap) { + dev_err(dev, "could not get TX device regmap\n"); + return -EINVAL; } ret = wcd938x_irq_init(wcd938x, dev); diff --git a/sound/soc/codecs/wcd938x.h b/sound/soc/codecs/wcd938x.h index ea82039e7843..74b1498fec38 100644 --- a/sound/soc/codecs/wcd938x.h +++ b/sound/soc/codecs/wcd938x.h @@ -663,6 +663,7 @@ struct wcd938x_sdw_priv { bool is_tx; struct wcd938x_priv *wcd938x; struct irq_domain *slave_irq; + struct regmap *regmap; }; #if IS_ENABLED(CONFIG_SND_SOC_WCD938X_SDW) -- GitLab From 4a1b5bc73e9ce8373d50fdb8f74badd2b4bf324e Mon Sep 17 00:00:00 2001 From: Andrey Rakhmatullin Date: Mon, 1 May 2023 22:51:34 +0400 Subject: [PATCH 4492/5631] ASoC: amd: yc: Add Asus VivoBook Pro 14 OLED M6400RC to the quirks list for acp6x This is needed (and enough) to get the internal mic visible and working. Signed-off-by: Andrey Rakhmatullin Message-Id: <20230501185134.34591-1-wrar@wrar.name> Signed-off-by: Mark Brown --- sound/soc/amd/yc/acp6x-mach.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 69b363dd0d10..0bc6e4066d0f 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -227,6 +227,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6400RC"), + } + }, { .driver_data = &acp6x_card, .matches = { -- GitLab From ec6f82b4c63cc68f8dc03316e725106d242706be Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 29 Apr 2023 12:47:21 +0200 Subject: [PATCH 4493/5631] ASoC: Intel: soc-acpi-cht: Add quirk for Nextbook Ares 8A tablet The Nextbook Ares 8A tablet which has Android as factory OS, has a buggy DSDT with both ESSX8316 and 10EC5651 ACPI devices. This tablet actually uses an rt5651 codec, but the matching code ends up picking the ESSX8316 device, add a quirk to ignote the ESSX8316 device on this tablet. Signed-off-by: Hans de Goede Acked-by: Pierre-Louis Bossart Message-Id: <20230429104721.7176-1-hdegoede@redhat.com> Signed-off-by: Mark Brown --- .../intel/common/soc-acpi-intel-cht-match.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c index 6beb00858c33..cdcbf04b8832 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c @@ -50,6 +50,31 @@ static struct snd_soc_acpi_mach *cht_quirk(void *arg) return mach; } +/* + * Some tablets with Android factory OS have buggy DSDTs with an ESSX8316 device + * in the ACPI tables. While they are not using an ESS8316 codec. These DSDTs + * also have an ACPI device for the correct codec, ignore the ESSX8316. + */ +static const struct dmi_system_id cht_ess8316_not_present_table[] = { + { + /* Nextbook Ares 8A */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "CherryTrail"), + DMI_MATCH(DMI_BIOS_VERSION, "M882"), + }, + }, + { } +}; + +static struct snd_soc_acpi_mach *cht_ess8316_quirk(void *arg) +{ + if (dmi_check_system(cht_ess8316_not_present_table)) + return NULL; + + return arg; +} + static const struct snd_soc_acpi_codecs rt5640_comp_ids = { .num_codecs = 2, .codecs = { "10EC5640", "10EC3276" }, @@ -113,6 +138,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[] = { .drv_name = "bytcht_es8316", .fw_filename = "intel/fw_sst_22a8.bin", .board = "bytcht_es8316", + .machine_quirk = cht_ess8316_quirk, .sof_tplg_filename = "sof-cht-es8316.tplg", }, /* some CHT-T platforms rely on RT5640, use Baytrail machine driver */ -- GitLab From 74a49415144035f171751d55b11ba04c9f348f9f Mon Sep 17 00:00:00 2001 From: lyndonli Date: Sun, 23 Apr 2023 16:46:30 +0800 Subject: [PATCH 4494/5631] drm/amdgpu: Fix mode2 reset for sienna cichlid Before this change, sienna_cichlid_get_reset_handler will always return NULL, although the module parameter reset_method is 3 when loading amdgpu driver. Signed-off-by: lyndonli Signed-off-by: Yunxiang Li Reviewed-by: Feifei Xu Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c index 81a6d5b94987..8b8086d5c864 100644 --- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c +++ b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c @@ -40,7 +40,7 @@ static bool sienna_cichlid_is_mode2_default(struct amdgpu_reset_control *reset_c adev->pm.fw_version >= 0x3a5500 && !amdgpu_sriov_vf(adev)) return true; #endif - return false; + return amdgpu_reset_method == AMD_RESET_METHOD_MODE2; } static struct amdgpu_reset_handler * -- GitLab From 4eea7fb980dc44545a32eec92e2662053b34cd9d Mon Sep 17 00:00:00 2001 From: lyndonli Date: Sun, 23 Apr 2023 17:05:15 +0800 Subject: [PATCH 4495/5631] drm/amdgpu: Use the default reset when loading or reloading the driver Below call trace and errors are observed when reloading amdgpu driver with the module parameter reset_method=3. It should do a default reset when loading or reloading the driver, regardless of the module parameter reset_method. v2: add comments inside and modify commit messages. [ +2.180243] [drm] psp gfx command ID_LOAD_TOC(0x20) failed and response status is (0x0) [ +0.000011] [drm:psp_hw_start [amdgpu]] *ERROR* Failed to load toc [ +0.000890] [drm:psp_hw_start [amdgpu]] *ERROR* PSP tmr init failed! [ +0.020683] [drm:amdgpu_fill_buffer [amdgpu]] *ERROR* Trying to clear memory with ring turned off. [ +0.000003] RIP: 0010:amdgpu_bo_release_notify+0x1ef/0x210 [amdgpu] [ +0.000004] Call Trace: [ +0.000003] [ +0.000008] ttm_bo_release+0x2c4/0x330 [amdttm] [ +0.000026] amdttm_bo_put+0x3c/0x70 [amdttm] [ +0.000020] amdgpu_bo_free_kernel+0xe6/0x140 [amdgpu] [ +0.000728] psp_v11_0_ring_destroy+0x34/0x60 [amdgpu] [ +0.000826] psp_hw_init+0xe7/0x2f0 [amdgpu] [ +0.000813] amdgpu_device_fw_loading+0x1ad/0x2d0 [amdgpu] [ +0.000731] amdgpu_device_init.cold+0x108e/0x2002 [amdgpu] [ +0.001071] ? do_pci_enable_device+0xe1/0x110 [ +0.000011] amdgpu_driver_load_kms+0x1a/0x160 [amdgpu] [ +0.000729] amdgpu_pci_probe+0x179/0x3a0 [amdgpu] Signed-off-by: lyndonli Signed-off-by: Yunxiang Li Reviewed-by: Feifei Xu Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 9b1eaba85bbd..981a9cfb63b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3578,6 +3578,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, int r, i; bool px = false; u32 max_MBps; + int tmp; adev->shutdown = false; adev->flags = flags; @@ -3799,7 +3800,13 @@ int amdgpu_device_init(struct amdgpu_device *adev, } } } else { + tmp = amdgpu_reset_method; + /* It should do a default reset when loading or reloading the driver, + * regardless of the module parameter reset_method. + */ + amdgpu_reset_method = AMD_RESET_METHOD_NONE; r = amdgpu_asic_reset(adev); + amdgpu_reset_method = tmp; if (r) { dev_err(adev->dev, "asic reset on init failed\n"); goto failed; -- GitLab From b03f38b9bd90d9eb29951e56f5a4375984c8dffb Mon Sep 17 00:00:00 2001 From: Shane Xiao Date: Tue, 25 Apr 2023 22:39:08 +0800 Subject: [PATCH 4496/5631] drm/amdgpu: Enable doorbell selfring after resize FB BAR MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit [Why] The selfring doorbell aperture will change when resize FB BAR successfully during gmc sw init, we should reorder the sequence of enabling doorbell selfring aperture. [How] Move enable_doorbell_selfring_aperture from *_common_hw_init to *_common_late_init. This fixes the potential issue that GPU ring its own doorbell when this device is in translated mode when iommu is on. v2: Remove *_enable_doorbell_aperture functions (Christian) v3: Add comments to note that why we need enable doorbell selfring late (Christian) Signed-off-by: Shane Xiao Signed-off-by: Aaron Liu Tested-by: Xiaomeng Hou Reviewed-by: Christian K�nig Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nv.c | 23 +++++++++++++---------- drivers/gpu/drm/amd/amdgpu/soc15.c | 25 +++++++++++++++---------- drivers/gpu/drm/amd/amdgpu/soc21.c | 23 +++++++++++++---------- 3 files changed, 41 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 47420b403871..98c826f1f89b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -531,13 +531,6 @@ static void nv_program_aspm(struct amdgpu_device *adev) } -static void nv_enable_doorbell_aperture(struct amdgpu_device *adev, - bool enable) -{ - adev->nbio.funcs->enable_doorbell_aperture(adev, enable); - adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable); -} - const struct amdgpu_ip_block_version nv_common_ip_block = { .type = AMD_IP_BLOCK_TYPE_COMMON, @@ -999,6 +992,11 @@ static int nv_common_late_init(void *handle) } } + /* Enable selfring doorbell aperture late because doorbell BAR + * aperture will change if resize BAR successfully in gmc sw_init. + */ + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true); + return 0; } @@ -1038,7 +1036,7 @@ static int nv_common_hw_init(void *handle) if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev)) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ - nv_enable_doorbell_aperture(adev, true); + adev->nbio.funcs->enable_doorbell_aperture(adev, true); return 0; } @@ -1047,8 +1045,13 @@ static int nv_common_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* disable the doorbell aperture */ - nv_enable_doorbell_aperture(adev, false); + /* Disable the doorbell aperture and selfring doorbell aperture + * separately in hw_fini because nv_enable_doorbell_aperture + * has been removed and there is no need to delay disabling + * selfring doorbell. + */ + adev->nbio.funcs->enable_doorbell_aperture(adev, false); + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index bc5dd80f10c1..6d15d5cd9e07 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -619,13 +619,6 @@ static void soc15_program_aspm(struct amdgpu_device *adev) adev->nbio.funcs->program_aspm(adev); } -static void soc15_enable_doorbell_aperture(struct amdgpu_device *adev, - bool enable) -{ - adev->nbio.funcs->enable_doorbell_aperture(adev, enable); - adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable); -} - const struct amdgpu_ip_block_version vega10_common_ip_block = { .type = AMD_IP_BLOCK_TYPE_COMMON, @@ -1125,6 +1118,11 @@ static int soc15_common_late_init(void *handle) if (amdgpu_sriov_vf(adev)) xgpu_ai_mailbox_get_irq(adev); + /* Enable selfring doorbell aperture late because doorbell BAR + * aperture will change if resize BAR successfully in gmc sw_init. + */ + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true); + return 0; } @@ -1182,7 +1180,8 @@ static int soc15_common_hw_init(void *handle) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ - soc15_enable_doorbell_aperture(adev, true); + adev->nbio.funcs->enable_doorbell_aperture(adev, true); + /* HW doorbell routing policy: doorbell writing not * in SDMA/IH/MM/ACV range will be routed to CP. So * we need to init SDMA doorbell range prior @@ -1198,8 +1197,14 @@ static int soc15_common_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* disable the doorbell aperture */ - soc15_enable_doorbell_aperture(adev, false); + /* Disable the doorbell aperture and selfring doorbell aperture + * separately in hw_fini because soc15_enable_doorbell_aperture + * has been removed and there is no need to delay disabling + * selfring doorbell. + */ + adev->nbio.funcs->enable_doorbell_aperture(adev, false); + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false); + if (amdgpu_sriov_vf(adev)) xgpu_ai_mailbox_put_irq(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 514bfc705d5a..744be2a05623 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -450,13 +450,6 @@ static void soc21_program_aspm(struct amdgpu_device *adev) adev->nbio.funcs->program_aspm(adev); } -static void soc21_enable_doorbell_aperture(struct amdgpu_device *adev, - bool enable) -{ - adev->nbio.funcs->enable_doorbell_aperture(adev, enable); - adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable); -} - const struct amdgpu_ip_block_version soc21_common_ip_block = { .type = AMD_IP_BLOCK_TYPE_COMMON, @@ -764,6 +757,11 @@ static int soc21_common_late_init(void *handle) amdgpu_irq_get(adev, &adev->nbio.ras_err_event_athub_irq, 0); } + /* Enable selfring doorbell aperture late because doorbell BAR + * aperture will change if resize BAR successfully in gmc sw_init. + */ + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true); + return 0; } @@ -797,7 +795,7 @@ static int soc21_common_hw_init(void *handle) if (adev->nbio.funcs->remap_hdp_registers) adev->nbio.funcs->remap_hdp_registers(adev); /* enable the doorbell aperture */ - soc21_enable_doorbell_aperture(adev, true); + adev->nbio.funcs->enable_doorbell_aperture(adev, true); return 0; } @@ -806,8 +804,13 @@ static int soc21_common_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - /* disable the doorbell aperture */ - soc21_enable_doorbell_aperture(adev, false); + /* Disable the doorbell aperture and selfring doorbell aperture + * separately in hw_fini because soc21_enable_doorbell_aperture + * has been removed and there is no need to delay disabling + * selfring doorbell. + */ + adev->nbio.funcs->enable_doorbell_aperture(adev, false); + adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false); if (amdgpu_sriov_vf(adev)) { xgpu_nv_mailbox_put_irq(adev); -- GitLab From 13af556104fa93b1945c70bbf8a0a62cd2c92879 Mon Sep 17 00:00:00 2001 From: Horatio Zhang Date: Tue, 25 Apr 2023 13:16:32 +0800 Subject: [PATCH 4497/5631] drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v11_0_hw_fini The gmc.ecc_irq is enabled by firmware per IFWI setting, and the host driver is not privileged to enable/disable the interrupt. So, it is meaningless to use the amdgpu_irq_put function in gmc_v11_0_hw_fini, which also leads to the call trace. [ 102.980303] Call Trace: [ 102.980303] [ 102.980304] gmc_v11_0_hw_fini+0x54/0x90 [amdgpu] [ 102.980357] gmc_v11_0_suspend+0xe/0x20 [amdgpu] [ 102.980409] amdgpu_device_ip_suspend_phase2+0x240/0x460 [amdgpu] [ 102.980459] amdgpu_device_ip_suspend+0x3d/0x80 [amdgpu] [ 102.980520] amdgpu_device_pre_asic_reset+0xd9/0x490 [amdgpu] [ 102.980573] amdgpu_device_gpu_recover.cold+0x548/0xce6 [amdgpu] [ 102.980687] amdgpu_debugfs_reset_work+0x4c/0x70 [amdgpu] [ 102.980740] process_one_work+0x21f/0x3f0 [ 102.980741] worker_thread+0x200/0x3e0 [ 102.980742] ? process_one_work+0x3f0/0x3f0 [ 102.980743] kthread+0xfd/0x130 [ 102.980743] ? kthread_complete_and_exit+0x20/0x20 [ 102.980744] ret_from_fork+0x22/0x30 Signed-off-by: Horatio Zhang Reviewed-by: Hawking Zhang Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Fixes: c8b5a95b5709 ("drm/amdgpu: Fix desktop freezed after gpu-reset") Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index d809f2ed5600..d95f9fe8f1c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -951,7 +951,6 @@ static int gmc_v11_0_hw_fini(void *handle) return 0; } - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); gmc_v11_0_gart_disable(adev); -- GitLab From 08c677cb0b436a96a836792bb35a8ec5de4999c2 Mon Sep 17 00:00:00 2001 From: Horatio Zhang Date: Tue, 25 Apr 2023 10:52:28 +0800 Subject: [PATCH 4498/5631] drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v10_0_hw_fini The gmc.ecc_irq is enabled by firmware per IFWI setting, and the host driver is not privileged to enable/disable the interrupt. So, it is meaningless to use the amdgpu_irq_put function in gmc_v10_0_hw_fini, which also leads to the call trace. [ 82.340264] Call Trace: [ 82.340265] [ 82.340269] gmc_v10_0_hw_fini+0x83/0xa0 [amdgpu] [ 82.340447] gmc_v10_0_suspend+0xe/0x20 [amdgpu] [ 82.340623] amdgpu_device_ip_suspend_phase2+0x127/0x1c0 [amdgpu] [ 82.340789] amdgpu_device_ip_suspend+0x3d/0x80 [amdgpu] [ 82.340955] amdgpu_device_pre_asic_reset+0xdd/0x2b0 [amdgpu] [ 82.341122] amdgpu_device_gpu_recover.cold+0x4dd/0xbb2 [amdgpu] [ 82.341359] amdgpu_debugfs_reset_work+0x4c/0x70 [amdgpu] [ 82.341529] process_one_work+0x21d/0x3f0 [ 82.341535] worker_thread+0x1fa/0x3c0 [ 82.341538] ? process_one_work+0x3f0/0x3f0 [ 82.341540] kthread+0xff/0x130 [ 82.341544] ? kthread_complete_and_exit+0x20/0x20 [ 82.341547] ret_from_fork+0x22/0x30 Signed-off-by: Horatio Zhang Reviewed-by: Hawking Zhang Reviewed-by: Guchun Chen Signed-off-by: Alex Deucher Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Fixes: c8b5a95b5709 ("drm/amdgpu: Fix desktop freezed after gpu-reset") Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 7d6f4a68f416..b213dcf8ca06 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1143,7 +1143,6 @@ static int gmc_v10_0_hw_fini(void *handle) return 0; } - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); return 0; -- GitLab From 922a76ba31adf84e72bc947267385be420c689ee Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz Date: Tue, 2 May 2023 11:59:08 -0400 Subject: [PATCH 4499/5631] drm/amdgpu: fix an amdgpu_irq_put() issue in gmc_v9_0_hw_fini() As made mention of in commit 08c677cb0b43 ("drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v10_0_hw_fini") and commit 13af556104fa ("drm/amdgpu: fix amdgpu_irq_put call trace in gmc_v11_0_hw_fini"). It is meaningless to call amdgpu_irq_put() for gmc.ecc_irq. So, remove it from gmc_v9_0_hw_fini(). Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Fixes: 3029c855d79f ("drm/amdgpu: Fix desktop freezed after gpu-reset") Reviewed-by: Mario Limonciello Signed-off-by: Hamza Mahfooz Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 64ab1a306dfe..2fe21cefd772 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1999,7 +1999,6 @@ static int gmc_v9_0_hw_fini(void *handle) if (adev->mmhub.funcs->update_power_gating) adev->mmhub.funcs->update_power_gating(adev, false); - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); return 0; -- GitLab From 2397e3d8d2e120355201a8310b61929f5a8bd2c0 Mon Sep 17 00:00:00 2001 From: Chia-I Wu Date: Wed, 26 Apr 2023 15:54:55 -0700 Subject: [PATCH 4500/5631] drm/amdgpu: add a missing lock for AMDGPU_SCHED MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit mgr->ctx_handles should be protected by mgr->lock. v2: improve commit message v3: add a Fixes tag Signed-off-by: Chia-I Wu Reviewed-by: Christian König Fixes: 52c6a62c64fa ("drm/amdgpu: add interface for editing a foreign process's priority v3") Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index e9b45089a28a..863b2a34b2d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -38,6 +38,7 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, { struct fd f = fdget(fd); struct amdgpu_fpriv *fpriv; + struct amdgpu_ctx_mgr *mgr; struct amdgpu_ctx *ctx; uint32_t id; int r; @@ -51,8 +52,11 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, return r; } - idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id) + mgr = &fpriv->ctx_mgr; + mutex_lock(&mgr->lock); + idr_for_each_entry(&mgr->ctx_handles, ctx, id) amdgpu_ctx_priority_override(ctx, priority); + mutex_unlock(&mgr->lock); fdput(f); return 0; -- GitLab From 100bd00881f8553d0ccfc99a575966d990c455eb Mon Sep 17 00:00:00 2001 From: Horace Chen Date: Tue, 25 Apr 2023 13:15:32 +0800 Subject: [PATCH 4501/5631] drm/amdgpu: disable SDMA WPTR_POLL_ENABLE for SR-IOV [Why] This WPTR_POLL_ENABLE is a hardware contigious polling which will cause FCLK and UCLK to keep on a high level. Mostly its case can be covered by F32_WPTR_POLL_ENABLE which polls by firmware. So to save power, SR-IOV also needs to disable this bit Signed-off-by: Horace Chen Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index eb722830531f..3d9a80511a45 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -510,10 +510,7 @@ static int sdma_v6_0_gfx_resume(struct amdgpu_device *adev) lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1); - if (amdgpu_sriov_vf(adev)) - rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 1); - else - rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 0); + rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 0); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, F32_WPTR_POLL_ENABLE, 1); WREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_RB_BASE), ring->gpu_addr >> 8); -- GitLab From 8f586cc16c1fc3c2202c9d54563db8c7ed365f82 Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Thu, 13 Apr 2023 17:34:24 -0400 Subject: [PATCH 4502/5631] drm/amd/display: Change default Z8 watermark values [Why & How] Previous Z8 watermark values were causing flickering and OTC underflow. Updating Z8 watermark values based on the measurement. Reviewed-by: Nicholas Kazlauskas Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Acked-by: Alan Liu Signed-off-by: Leo Chen Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 44082f65de1f..9e54e3d0eb78 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -149,8 +149,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = { .num_states = 5, .sr_exit_time_us = 16.5, .sr_enter_plus_exit_time_us = 18.5, - .sr_exit_z8_time_us = 210.0, - .sr_enter_plus_exit_z8_time_us = 310.0, + .sr_exit_z8_time_us = 268.0, + .sr_enter_plus_exit_z8_time_us = 393.0, .writeback_latency_us = 12.0, .dram_channel_width_bytes = 4, .round_trip_ping_latency_dcfclk_cycles = 106, -- GitLab From 682439fffad9fa9a38d37dd1b1318e9374232213 Mon Sep 17 00:00:00 2001 From: Samson Tam Date: Wed, 19 Apr 2023 18:17:14 -0400 Subject: [PATCH 4503/5631] drm/amd/display: filter out invalid bits in pipe_fuses [Why] Reading pipe_fuses from register may have invalid bits set, which may affect the num_pipes erroneously. [How] Add read_pipes_fuses() call and filter bits based on expected number of pipes. Reviewed-by: Alvin Lee Acked-by: Alan Liu Signed-off-by: Samson Tam Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c | 10 +++++++++- .../gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 10 +++++++++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index a876e6eb6cd8..22dd1ebea618 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -2079,6 +2079,14 @@ static struct resource_funcs dcn32_res_pool_funcs = { .restore_mall_state = dcn32_restore_mall_state, }; +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* DCN32 support max 4 pipes */ + value = value & 0xf; + return value; +} + static bool dcn32_resource_construct( uint8_t num_virtual_links, @@ -2122,7 +2130,7 @@ static bool dcn32_resource_construct( pool->base.res_cap = &res_cap_dcn32; /* max number of pipes for ASIC before checking for pipe fuses */ num_pipes = pool->base.res_cap->num_timing_generator; - pipe_fuses = REG_READ(CC_DC_PIPE_DIS); + pipe_fuses = read_pipe_fuses(ctx); for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) if (pipe_fuses & 1 << i) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index e5ab7f3077c4..a60ddb343d13 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1632,6 +1632,14 @@ static struct resource_funcs dcn321_res_pool_funcs = { .restore_mall_state = dcn32_restore_mall_state, }; +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* DCN321 support max 4 pipes */ + value = value & 0xf; + return value; +} + static bool dcn321_resource_construct( uint8_t num_virtual_links, @@ -1674,7 +1682,7 @@ static bool dcn321_resource_construct( pool->base.res_cap = &res_cap_dcn321; /* max number of pipes for ASIC before checking for pipe fuses */ num_pipes = pool->base.res_cap->num_timing_generator; - pipe_fuses = REG_READ(CC_DC_PIPE_DIS); + pipe_fuses = read_pipe_fuses(ctx); for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) if (pipe_fuses & 1 << i) -- GitLab From 1253685f0d3eb3eab0bfc4bf15ab341a5f3da0c8 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Wed, 26 Apr 2023 09:46:54 +0800 Subject: [PATCH 4504/5631] drm/amdgpu: drop redundant sched job cleanup when cs is aborted MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Once command submission failed due to userptr invalidation in amdgpu_cs_submit, legacy code will perform cleanup of scheduler job. However, it's not needed at all, as former commit has integrated job cleanup stuff into amdgpu_job_free. Otherwise, because of double free, a NULL pointer dereference will occur in such scenario. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2457 Fixes: f7d66fb2ea43 ("drm/amdgpu: cleanup scheduler job initialization v2") Signed-off-by: Guchun Chen Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 13 +++---------- 1 file changed, 3 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 08eced097bd8..2eb2c66843a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1276,7 +1276,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, r = drm_sched_job_add_dependency(&leader->base, fence); if (r) { dma_fence_put(fence); - goto error_cleanup; + return r; } } @@ -1303,7 +1303,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, } if (r) { r = -EAGAIN; - goto error_unlock; + mutex_unlock(&p->adev->notifier_lock); + return r; } p->fence = dma_fence_get(&leader->base.s_fence->finished); @@ -1350,14 +1351,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, mutex_unlock(&p->adev->notifier_lock); mutex_unlock(&p->bo_list->bo_list_mutex); return 0; - -error_unlock: - mutex_unlock(&p->adev->notifier_lock); - -error_cleanup: - for (i = 0; i < p->gang_size; ++i) - drm_sched_job_cleanup(&p->jobs[i]->base); - return r; } /* Cleanup the parser structure */ -- GitLab From 6d7cb549c2ca20e1f07593f15e936fd54b763028 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:26:45 +0900 Subject: [PATCH 4505/5631] ksmbd: fix memleak in session setup If client send session setup request with unknown NTLMSSP message type, session that does not included channel can be created. It will cause session memleak. because ksmbd_sessions_deregister() does not destroy session if channel is not included. This patch return error response if client send the request unknown NTLMSSP message type. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20593 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index bbc9e92935fb..1d3931994a5d 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1766,6 +1766,10 @@ int smb2_sess_setup(struct ksmbd_work *work) } kfree(sess->Preauth_HashValue); sess->Preauth_HashValue = NULL; + } else { + pr_info_ratelimited("Unknown NTLMSSP message type : 0x%x\n", + le32_to_cpu(negblob->MessageType)); + rc = -EINVAL; } } else { /* TODO: need one more negotiation */ -- GitLab From 3ac00a2ab69b34189942afa9e862d5170cdcb018 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:38:33 +0900 Subject: [PATCH 4506/5631] ksmbd: fix NULL pointer dereference in smb2_get_info_filesystem() If share is , share->path is NULL and it cause NULL pointer dereference issue. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20479 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 1d3931994a5d..b5f1a2a7389d 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -4885,6 +4885,9 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, int rc = 0, len; int fs_infoclass_size = 0; + if (!share->path) + return -EIO; + rc = kern_path(share->path, LOOKUP_NO_SYMLINKS, &path); if (rc) { pr_err("cannot create vfs path\n"); -- GitLab From f5c779b7ddbda30866cf2a27c63e34158f858c73 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 16:45:00 +0900 Subject: [PATCH 4507/5631] ksmbd: fix racy issue from session setup and logoff This racy issue is triggered by sending concurrent session setup and logoff requests. This patch does not set connection status as KSMBD_SESS_GOOD if state is KSMBD_SESS_NEED_RECONNECT in session setup. And relookup session to validate if session is deleted in logoff. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20481, ZDI-CAN-20590, ZDI-CAN-20596 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/connection.c | 14 ++++---- fs/ksmbd/connection.h | 39 ++++++++++++--------- fs/ksmbd/mgmt/user_session.c | 1 + fs/ksmbd/server.c | 3 +- fs/ksmbd/smb2pdu.c | 67 +++++++++++++++++++++++------------- fs/ksmbd/transport_tcp.c | 2 +- 6 files changed, 77 insertions(+), 49 deletions(-) diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 365ac32af505..1f5176d65df9 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -56,7 +56,7 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) return NULL; conn->need_neg = true; - conn->status = KSMBD_SESS_NEW; + ksmbd_conn_set_new(conn); conn->local_nls = load_nls("utf8"); if (!conn->local_nls) conn->local_nls = load_nls_default(); @@ -147,12 +147,12 @@ int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) return ret; } -static void ksmbd_conn_lock(struct ksmbd_conn *conn) +void ksmbd_conn_lock(struct ksmbd_conn *conn) { mutex_lock(&conn->srv_mutex); } -static void ksmbd_conn_unlock(struct ksmbd_conn *conn) +void ksmbd_conn_unlock(struct ksmbd_conn *conn) { mutex_unlock(&conn->srv_mutex); } @@ -243,7 +243,7 @@ bool ksmbd_conn_alive(struct ksmbd_conn *conn) if (!ksmbd_server_running()) return false; - if (conn->status == KSMBD_SESS_EXITING) + if (ksmbd_conn_exiting(conn)) return false; if (kthread_should_stop()) @@ -303,7 +303,7 @@ int ksmbd_conn_handler_loop(void *p) pdu_size = get_rfc1002_len(hdr_buf); ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size); - if (conn->status == KSMBD_SESS_GOOD) + if (ksmbd_conn_good(conn)) max_allowed_pdu_size = SMB3_MAX_MSGSIZE + conn->vals->max_write_size; else @@ -312,7 +312,7 @@ int ksmbd_conn_handler_loop(void *p) if (pdu_size > max_allowed_pdu_size) { pr_err_ratelimited("PDU length(%u) exceeded maximum allowed pdu size(%u) on connection(%d)\n", pdu_size, max_allowed_pdu_size, - conn->status); + READ_ONCE(conn->status)); break; } @@ -416,7 +416,7 @@ static void stop_sessions(void) if (task) ksmbd_debug(CONN, "Stop session handler %s/%d\n", task->comm, task_pid_nr(task)); - conn->status = KSMBD_SESS_EXITING; + ksmbd_conn_set_exiting(conn); if (t->ops->shutdown) { read_unlock(&conn_list_lock); t->ops->shutdown(t); diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h index 0e3a848defaf..98bb5f199fa2 100644 --- a/fs/ksmbd/connection.h +++ b/fs/ksmbd/connection.h @@ -162,6 +162,8 @@ void ksmbd_conn_init_server_callbacks(struct ksmbd_conn_ops *ops); int ksmbd_conn_handler_loop(void *p); int ksmbd_conn_transport_init(void); void ksmbd_conn_transport_destroy(void); +void ksmbd_conn_lock(struct ksmbd_conn *conn); +void ksmbd_conn_unlock(struct ksmbd_conn *conn); /* * WARNING @@ -169,43 +171,48 @@ void ksmbd_conn_transport_destroy(void); * This is a hack. We will move status to a proper place once we land * a multi-sessions support. */ -static inline bool ksmbd_conn_good(struct ksmbd_work *work) +static inline bool ksmbd_conn_good(struct ksmbd_conn *conn) { - return work->conn->status == KSMBD_SESS_GOOD; + return READ_ONCE(conn->status) == KSMBD_SESS_GOOD; } -static inline bool ksmbd_conn_need_negotiate(struct ksmbd_work *work) +static inline bool ksmbd_conn_need_negotiate(struct ksmbd_conn *conn) { - return work->conn->status == KSMBD_SESS_NEED_NEGOTIATE; + return READ_ONCE(conn->status) == KSMBD_SESS_NEED_NEGOTIATE; } -static inline bool ksmbd_conn_need_reconnect(struct ksmbd_work *work) +static inline bool ksmbd_conn_need_reconnect(struct ksmbd_conn *conn) { - return work->conn->status == KSMBD_SESS_NEED_RECONNECT; + return READ_ONCE(conn->status) == KSMBD_SESS_NEED_RECONNECT; } -static inline bool ksmbd_conn_exiting(struct ksmbd_work *work) +static inline bool ksmbd_conn_exiting(struct ksmbd_conn *conn) { - return work->conn->status == KSMBD_SESS_EXITING; + return READ_ONCE(conn->status) == KSMBD_SESS_EXITING; } -static inline void ksmbd_conn_set_good(struct ksmbd_work *work) +static inline void ksmbd_conn_set_new(struct ksmbd_conn *conn) { - work->conn->status = KSMBD_SESS_GOOD; + WRITE_ONCE(conn->status, KSMBD_SESS_NEW); } -static inline void ksmbd_conn_set_need_negotiate(struct ksmbd_work *work) +static inline void ksmbd_conn_set_good(struct ksmbd_conn *conn) { - work->conn->status = KSMBD_SESS_NEED_NEGOTIATE; + WRITE_ONCE(conn->status, KSMBD_SESS_GOOD); } -static inline void ksmbd_conn_set_need_reconnect(struct ksmbd_work *work) +static inline void ksmbd_conn_set_need_negotiate(struct ksmbd_conn *conn) { - work->conn->status = KSMBD_SESS_NEED_RECONNECT; + WRITE_ONCE(conn->status, KSMBD_SESS_NEED_NEGOTIATE); } -static inline void ksmbd_conn_set_exiting(struct ksmbd_work *work) +static inline void ksmbd_conn_set_need_reconnect(struct ksmbd_conn *conn) { - work->conn->status = KSMBD_SESS_EXITING; + WRITE_ONCE(conn->status, KSMBD_SESS_NEED_RECONNECT); +} + +static inline void ksmbd_conn_set_exiting(struct ksmbd_conn *conn) +{ + WRITE_ONCE(conn->status, KSMBD_SESS_EXITING); } #endif /* __CONNECTION_H__ */ diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/ksmbd/mgmt/user_session.c index 1ca2aae4c299..68d40025cfbf 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/ksmbd/mgmt/user_session.c @@ -315,6 +315,7 @@ static struct ksmbd_session *__session_create(int protocol) if (ksmbd_init_file_table(&sess->file_table)) goto error; + sess->state = SMB2_SESSION_IN_PROGRESS; set_session_flag(sess, protocol); xa_init(&sess->tree_conns); xa_init(&sess->ksmbd_chann_list); diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 0979577fd23e..2ebf6985a88d 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -93,7 +93,8 @@ static inline int check_conn_state(struct ksmbd_work *work) { struct smb_hdr *rsp_hdr; - if (ksmbd_conn_exiting(work) || ksmbd_conn_need_reconnect(work)) { + if (ksmbd_conn_exiting(work->conn) || + ksmbd_conn_need_reconnect(work->conn)) { rsp_hdr = work->response_buf; rsp_hdr->Status.CifsError = STATUS_CONNECTION_DISCONNECTED; return 1; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index b5f1a2a7389d..96974feb6d28 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -248,7 +248,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp = smb2_get_msg(work->response_buf); - WARN_ON(ksmbd_conn_good(work)); + WARN_ON(ksmbd_conn_good(conn)); rsp->StructureSize = cpu_to_le16(65); ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); @@ -277,7 +277,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE; conn->use_spnego = true; - ksmbd_conn_set_need_negotiate(work); + ksmbd_conn_set_need_negotiate(conn); return 0; } @@ -561,7 +561,7 @@ int smb2_check_user_session(struct ksmbd_work *work) cmd == SMB2_SESSION_SETUP_HE) return 0; - if (!ksmbd_conn_good(work)) + if (!ksmbd_conn_good(conn)) return -EINVAL; sess_id = le64_to_cpu(req_hdr->SessionId); @@ -594,7 +594,7 @@ static void destroy_previous_session(struct ksmbd_conn *conn, prev_sess->state = SMB2_SESSION_EXPIRED; xa_for_each(&prev_sess->ksmbd_chann_list, index, chann) - chann->conn->status = KSMBD_SESS_EXITING; + ksmbd_conn_set_exiting(chann->conn); } /** @@ -1051,7 +1051,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Received negotiate request\n"); conn->need_neg = false; - if (ksmbd_conn_good(work)) { + if (ksmbd_conn_good(conn)) { pr_err("conn->tcp_status is already in CifsGood State\n"); work->send_no_response = 1; return rc; @@ -1205,7 +1205,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) } conn->srv_sec_mode = le16_to_cpu(rsp->SecurityMode); - ksmbd_conn_set_need_negotiate(work); + ksmbd_conn_set_need_negotiate(conn); err_out: if (rc < 0) @@ -1628,6 +1628,7 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->SecurityBufferLength = 0; inc_rfc1001_len(work->response_buf, 9); + ksmbd_conn_lock(conn); if (!req->hdr.SessionId) { sess = ksmbd_smb2_session_create(); if (!sess) { @@ -1675,6 +1676,12 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } + if (ksmbd_conn_need_reconnect(conn)) { + rc = -EFAULT; + sess = NULL; + goto out_err; + } + if (ksmbd_session_lookup(conn, sess_id)) { rc = -EACCES; goto out_err; @@ -1694,12 +1701,20 @@ int smb2_sess_setup(struct ksmbd_work *work) rc = -ENOENT; goto out_err; } + + if (sess->state == SMB2_SESSION_EXPIRED) { + rc = -EFAULT; + goto out_err; + } + + if (ksmbd_conn_need_reconnect(conn)) { + rc = -EFAULT; + sess = NULL; + goto out_err; + } } work->sess = sess; - if (sess->state == SMB2_SESSION_EXPIRED) - sess->state = SMB2_SESSION_IN_PROGRESS; - negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || @@ -1729,8 +1744,10 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - ksmbd_conn_set_good(work); - sess->state = SMB2_SESSION_VALID; + if (!ksmbd_conn_need_reconnect(conn)) { + ksmbd_conn_set_good(conn); + sess->state = SMB2_SESSION_VALID; + } kfree(sess->Preauth_HashValue); sess->Preauth_HashValue = NULL; } else if (conn->preferred_auth_mech == KSMBD_AUTH_NTLMSSP) { @@ -1752,8 +1769,10 @@ int smb2_sess_setup(struct ksmbd_work *work) if (rc) goto out_err; - ksmbd_conn_set_good(work); - sess->state = SMB2_SESSION_VALID; + if (!ksmbd_conn_need_reconnect(conn)) { + ksmbd_conn_set_good(conn); + sess->state = SMB2_SESSION_VALID; + } if (conn->binding) { struct preauth_session *preauth_sess; @@ -1819,14 +1838,13 @@ int smb2_sess_setup(struct ksmbd_work *work) if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) try_delay = true; - xa_erase(&conn->sessions, sess->id); - ksmbd_session_destroy(sess); - work->sess = NULL; + sess->state = SMB2_SESSION_EXPIRED; if (try_delay) ssleep(5); } } + ksmbd_conn_unlock(conn); return rc; } @@ -2050,21 +2068,24 @@ int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct smb2_logoff_rsp *rsp = smb2_get_msg(work->response_buf); - struct ksmbd_session *sess = work->sess; + struct ksmbd_session *sess; + struct smb2_logoff_req *req = smb2_get_msg(work->request_buf); rsp->StructureSize = cpu_to_le16(4); inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); - /* setting CifsExiting here may race with start_tcp_sess */ - ksmbd_conn_set_need_reconnect(work); + ksmbd_conn_set_need_reconnect(conn); ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); + /* + * Re-lookup session to validate if session is deleted + * while waiting request complete + */ + sess = ksmbd_session_lookup(conn, le64_to_cpu(req->hdr.SessionId)); if (ksmbd_tree_conn_session_logoff(sess)) { - struct smb2_logoff_req *req = smb2_get_msg(work->request_buf); - ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); @@ -2076,9 +2097,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; - - /* let start_tcp_sess free connection info now */ - ksmbd_conn_set_need_negotiate(work); + ksmbd_conn_set_need_negotiate(conn); return 0; } diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 20e85e2701f2..eff7a1d793f0 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -333,7 +333,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, if (length == -EINTR) { total_read = -ESHUTDOWN; break; - } else if (conn->status == KSMBD_SESS_NEED_RECONNECT) { + } else if (ksmbd_conn_need_reconnect(conn)) { total_read = -EAGAIN; break; } else if (length == -ERESTARTSYS || length == -EAGAIN) { -- GitLab From ea174a91893956450510945a0c5d1a10b5323656 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:42:21 +0900 Subject: [PATCH 4508/5631] ksmbd: destroy expired sessions client can indefinitely send smb2 session setup requests with the SessionId set to 0, thus indefinitely spawning new sessions, and causing indefinite memory usage. This patch limit to the number of sessions using expired timeout and session state. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20478 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/mgmt/user_session.c | 68 ++++++++++++++++++++---------------- fs/ksmbd/mgmt/user_session.h | 1 + fs/ksmbd/smb2pdu.c | 1 + fs/ksmbd/smb2pdu.h | 2 ++ 4 files changed, 41 insertions(+), 31 deletions(-) diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/ksmbd/mgmt/user_session.c index 68d40025cfbf..3840de7773b9 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/ksmbd/mgmt/user_session.c @@ -165,70 +165,73 @@ static struct ksmbd_session *__session_lookup(unsigned long long id) struct ksmbd_session *sess; hash_for_each_possible(sessions_table, sess, hlist, id) { - if (id == sess->id) + if (id == sess->id) { + sess->last_active = jiffies; return sess; + } } return NULL; } +static void ksmbd_expire_session(struct ksmbd_conn *conn) +{ + unsigned long id; + struct ksmbd_session *sess; + + xa_for_each(&conn->sessions, id, sess) { + if (sess->state != SMB2_SESSION_VALID || + time_after(jiffies, + sess->last_active + SMB2_SESSION_TIMEOUT)) { + xa_erase(&conn->sessions, sess->id); + ksmbd_session_destroy(sess); + continue; + } + } +} + int ksmbd_session_register(struct ksmbd_conn *conn, struct ksmbd_session *sess) { sess->dialect = conn->dialect; memcpy(sess->ClientGUID, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); + ksmbd_expire_session(conn); return xa_err(xa_store(&conn->sessions, sess->id, sess, GFP_KERNEL)); } -static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) +static void ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) { struct channel *chann; chann = xa_erase(&sess->ksmbd_chann_list, (long)conn); if (!chann) - return -ENOENT; + return; kfree(chann); - - return 0; } void ksmbd_sessions_deregister(struct ksmbd_conn *conn) { struct ksmbd_session *sess; + unsigned long id; - if (conn->binding) { - int bkt; - - down_write(&sessions_table_lock); - hash_for_each(sessions_table, bkt, sess, hlist) { - if (!ksmbd_chann_del(conn, sess)) { - up_write(&sessions_table_lock); - goto sess_destroy; - } + xa_for_each(&conn->sessions, id, sess) { + ksmbd_chann_del(conn, sess); + if (xa_empty(&sess->ksmbd_chann_list)) { + xa_erase(&conn->sessions, sess->id); + ksmbd_session_destroy(sess); } - up_write(&sessions_table_lock); - } else { - unsigned long id; - - xa_for_each(&conn->sessions, id, sess) { - if (!ksmbd_chann_del(conn, sess)) - goto sess_destroy; - } - } - - return; - -sess_destroy: - if (xa_empty(&sess->ksmbd_chann_list)) { - xa_erase(&conn->sessions, sess->id); - ksmbd_session_destroy(sess); } } struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, unsigned long long id) { - return xa_load(&conn->sessions, id); + struct ksmbd_session *sess; + + sess = xa_load(&conn->sessions, id); + if (sess) + sess->last_active = jiffies; + return sess; } struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) @@ -237,6 +240,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + sess->last_active = jiffies; up_read(&sessions_table_lock); return sess; @@ -315,6 +320,7 @@ static struct ksmbd_session *__session_create(int protocol) if (ksmbd_init_file_table(&sess->file_table)) goto error; + sess->last_active = jiffies; sess->state = SMB2_SESSION_IN_PROGRESS; set_session_flag(sess, protocol); xa_init(&sess->tree_conns); diff --git a/fs/ksmbd/mgmt/user_session.h b/fs/ksmbd/mgmt/user_session.h index b6a9e7a6aae4..f99d475b28db 100644 --- a/fs/ksmbd/mgmt/user_session.h +++ b/fs/ksmbd/mgmt/user_session.h @@ -59,6 +59,7 @@ struct ksmbd_session { __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; struct ksmbd_file_table file_table; + unsigned long last_active; }; static inline int test_session_flag(struct ksmbd_session *sess, int bit) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 96974feb6d28..51cc1dfb9260 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1838,6 +1838,7 @@ int smb2_sess_setup(struct ksmbd_work *work) if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) try_delay = true; + sess->last_active = jiffies; sess->state = SMB2_SESSION_EXPIRED; if (try_delay) ssleep(5); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 9420dd2813fb..977a9ee6a5b3 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -61,6 +61,8 @@ struct preauth_integrity_info { #define SMB2_SESSION_IN_PROGRESS BIT(0) #define SMB2_SESSION_VALID BIT(1) +#define SMB2_SESSION_TIMEOUT (10 * HZ) + struct create_durable_req_v2 { struct create_context ccontext; __u8 Name[8]; -- GitLab From b096d97f47326b1e2dbdef1c91fab69ffda54d17 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:43:30 +0900 Subject: [PATCH 4509/5631] ksmbd: block asynchronous requests when making a delay on session setup ksmbd make a delay of 5 seconds on session setup to avoid dictionary attacks. But the 5 seconds delay can be bypassed by using asynchronous requests. This patch block all requests on current connection when making a delay on sesstion setup failure. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20482 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 51cc1dfb9260..234ab5f4104f 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1840,8 +1840,11 @@ int smb2_sess_setup(struct ksmbd_work *work) sess->last_active = jiffies; sess->state = SMB2_SESSION_EXPIRED; - if (try_delay) + if (try_delay) { + ksmbd_conn_set_need_reconnect(conn); ssleep(5); + ksmbd_conn_set_need_negotiate(conn); + } } } -- GitLab From 7b4323373d844954bb76e0e9f39c4e5fc785fa7b Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:44:14 +0900 Subject: [PATCH 4510/5631] ksmbd: fix deadlock in ksmbd_find_crypto_ctx() Deadlock is triggered by sending multiple concurrent session setup requests. It should be reused after releasing when getting ctx for crypto. Multiple consecutive ctx uses cause deadlock while waiting for releasing due to the limited number of ctx. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20591 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/auth.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index cead696b656a..df8fb076f6f1 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -221,22 +221,22 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, { char ntlmv2_hash[CIFS_ENCPWD_SIZE]; char ntlmv2_rsp[CIFS_HMAC_MD5_HASH_SIZE]; - struct ksmbd_crypto_ctx *ctx; + struct ksmbd_crypto_ctx *ctx = NULL; char *construct = NULL; int rc, len; - ctx = ksmbd_crypto_ctx_find_hmacmd5(); - if (!ctx) { - ksmbd_debug(AUTH, "could not crypto alloc hmacmd5\n"); - return -ENOMEM; - } - rc = calc_ntlmv2_hash(conn, sess, ntlmv2_hash, domain_name); if (rc) { ksmbd_debug(AUTH, "could not get v2 hash rc %d\n", rc); goto out; } + ctx = ksmbd_crypto_ctx_find_hmacmd5(); + if (!ctx) { + ksmbd_debug(AUTH, "could not crypto alloc hmacmd5\n"); + return -ENOMEM; + } + rc = crypto_shash_setkey(CRYPTO_HMACMD5_TFM(ctx), ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE); @@ -272,6 +272,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, ksmbd_debug(AUTH, "Could not generate md5 hash\n"); goto out; } + ksmbd_release_crypto_ctx(ctx); + ctx = NULL; rc = ksmbd_gen_sess_key(sess, ntlmv2_hash, ntlmv2_rsp); if (rc) { @@ -282,7 +284,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, if (memcmp(ntlmv2->ntlmv2_hash, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE) != 0) rc = -EINVAL; out: - ksmbd_release_crypto_ctx(ctx); + if (ctx) + ksmbd_release_crypto_ctx(ctx); kfree(construct); return rc; } -- GitLab From 3353ab2df5f68dab7da8d5ebb427a2d265a1f2b2 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:45:08 +0900 Subject: [PATCH 4511/5631] ksmbd: not allow guest user on multichannel This patch return STATUS_NOT_SUPPORTED if binding session is guest. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20480 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 234ab5f4104f..26db1dc38b45 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1431,7 +1431,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) * Reuse session if anonymous try to connect * on reauthetication. */ - if (ksmbd_anonymous_user(user)) { + if (conn->binding == false && ksmbd_anonymous_user(user)) { ksmbd_free_user(user); return 0; } @@ -1445,7 +1445,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) sess->user = user; } - if (user_guest(sess->user)) { + if (conn->binding == false && user_guest(sess->user)) { rsp->SessionFlags = SMB2_SESSION_FLAG_IS_GUEST_LE; } else { struct authenticate_message *authblob; @@ -1687,6 +1687,11 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } + if (user_guest(sess->user)) { + rc = -EOPNOTSUPP; + goto out_err; + } + conn->binding = true; } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && @@ -1811,6 +1816,8 @@ int smb2_sess_setup(struct ksmbd_work *work) rsp->hdr.Status = STATUS_NETWORK_SESSION_EXPIRED; else if (rc == -ENOMEM) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + else if (rc == -EOPNOTSUPP) + rsp->hdr.Status = STATUS_NOT_SUPPORTED; else if (rc) rsp->hdr.Status = STATUS_LOGON_FAILURE; -- GitLab From abcc506a9a71976a8b4c9bf3ee6efd13229c1e19 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 14:03:40 +0900 Subject: [PATCH 4512/5631] ksmbd: fix racy issue from smb2 close and logoff with multichannel When smb client send concurrent smb2 close and logoff request with multichannel connection, It can cause racy issue. logoff request free tcon and can cause UAF issues in smb2 close. When receiving logoff request with multichannel, ksmbd should wait until all remaning requests complete as well as ones in the current connection, and then make session expired. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20796 ZDI-CAN-20595 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/connection.c | 54 +++++++++++++++++++++++++++--------- fs/ksmbd/connection.h | 19 +++++++++++-- fs/ksmbd/mgmt/tree_connect.c | 3 ++ fs/ksmbd/mgmt/user_session.c | 36 ++++++++++++++++++++---- fs/ksmbd/smb2pdu.c | 21 +++++++------- 5 files changed, 101 insertions(+), 32 deletions(-) diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 1f5176d65df9..4ed379f9b1aa 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -20,7 +20,7 @@ static DEFINE_MUTEX(init_lock); static struct ksmbd_conn_ops default_conn_ops; LIST_HEAD(conn_list); -DEFINE_RWLOCK(conn_list_lock); +DECLARE_RWSEM(conn_list_lock); /** * ksmbd_conn_free() - free resources of the connection instance @@ -32,9 +32,9 @@ DEFINE_RWLOCK(conn_list_lock); */ void ksmbd_conn_free(struct ksmbd_conn *conn) { - write_lock(&conn_list_lock); + down_write(&conn_list_lock); list_del(&conn->conns_list); - write_unlock(&conn_list_lock); + up_write(&conn_list_lock); xa_destroy(&conn->sessions); kvfree(conn->request_buf); @@ -84,9 +84,9 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) spin_lock_init(&conn->llist_lock); INIT_LIST_HEAD(&conn->lock_list); - write_lock(&conn_list_lock); + down_write(&conn_list_lock); list_add(&conn->conns_list, &conn_list); - write_unlock(&conn_list_lock); + up_write(&conn_list_lock); return conn; } @@ -95,7 +95,7 @@ bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c) struct ksmbd_conn *t; bool ret = false; - read_lock(&conn_list_lock); + down_read(&conn_list_lock); list_for_each_entry(t, &conn_list, conns_list) { if (memcmp(t->ClientGUID, c->ClientGUID, SMB2_CLIENT_GUID_SIZE)) continue; @@ -103,7 +103,7 @@ bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c) ret = true; break; } - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); return ret; } @@ -157,9 +157,37 @@ void ksmbd_conn_unlock(struct ksmbd_conn *conn) mutex_unlock(&conn->srv_mutex); } -void ksmbd_conn_wait_idle(struct ksmbd_conn *conn) +void ksmbd_all_conn_set_status(u64 sess_id, u32 status) { + struct ksmbd_conn *conn; + + down_read(&conn_list_lock); + list_for_each_entry(conn, &conn_list, conns_list) { + if (conn->binding || xa_load(&conn->sessions, sess_id)) + WRITE_ONCE(conn->status, status); + } + up_read(&conn_list_lock); +} + +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id) +{ + struct ksmbd_conn *bind_conn; + wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2); + + down_read(&conn_list_lock); + list_for_each_entry(bind_conn, &conn_list, conns_list) { + if (bind_conn == conn) + continue; + + if ((bind_conn->binding || xa_load(&bind_conn->sessions, sess_id)) && + !ksmbd_conn_releasing(bind_conn) && + atomic_read(&bind_conn->req_running)) { + wait_event(bind_conn->req_running_q, + atomic_read(&bind_conn->req_running) == 0); + } + } + up_read(&conn_list_lock); } int ksmbd_conn_write(struct ksmbd_work *work) @@ -360,10 +388,10 @@ int ksmbd_conn_handler_loop(void *p) } out: + ksmbd_conn_set_releasing(conn); /* Wait till all reference dropped to the Server object*/ wait_event(conn->r_count_q, atomic_read(&conn->r_count) == 0); - if (IS_ENABLED(CONFIG_UNICODE)) utf8_unload(conn->um); unload_nls(conn->local_nls); @@ -407,7 +435,7 @@ static void stop_sessions(void) struct ksmbd_transport *t; again: - read_lock(&conn_list_lock); + down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) { struct task_struct *task; @@ -418,12 +446,12 @@ static void stop_sessions(void) task->comm, task_pid_nr(task)); ksmbd_conn_set_exiting(conn); if (t->ops->shutdown) { - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); t->ops->shutdown(t); - read_lock(&conn_list_lock); + down_read(&conn_list_lock); } } - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); if (!list_empty(&conn_list)) { schedule_timeout_interruptible(HZ / 10); /* 100ms */ diff --git a/fs/ksmbd/connection.h b/fs/ksmbd/connection.h index 98bb5f199fa2..ad8dfaa48ffb 100644 --- a/fs/ksmbd/connection.h +++ b/fs/ksmbd/connection.h @@ -26,7 +26,8 @@ enum { KSMBD_SESS_GOOD, KSMBD_SESS_EXITING, KSMBD_SESS_NEED_RECONNECT, - KSMBD_SESS_NEED_NEGOTIATE + KSMBD_SESS_NEED_NEGOTIATE, + KSMBD_SESS_RELEASING }; struct ksmbd_stats { @@ -140,10 +141,10 @@ struct ksmbd_transport { #define KSMBD_TCP_PEER_SOCKADDR(c) ((struct sockaddr *)&((c)->peer_addr)) extern struct list_head conn_list; -extern rwlock_t conn_list_lock; +extern struct rw_semaphore conn_list_lock; bool ksmbd_conn_alive(struct ksmbd_conn *conn); -void ksmbd_conn_wait_idle(struct ksmbd_conn *conn); +void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id); struct ksmbd_conn *ksmbd_conn_alloc(void); void ksmbd_conn_free(struct ksmbd_conn *conn); bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c); @@ -191,6 +192,11 @@ static inline bool ksmbd_conn_exiting(struct ksmbd_conn *conn) return READ_ONCE(conn->status) == KSMBD_SESS_EXITING; } +static inline bool ksmbd_conn_releasing(struct ksmbd_conn *conn) +{ + return READ_ONCE(conn->status) == KSMBD_SESS_RELEASING; +} + static inline void ksmbd_conn_set_new(struct ksmbd_conn *conn) { WRITE_ONCE(conn->status, KSMBD_SESS_NEW); @@ -215,4 +221,11 @@ static inline void ksmbd_conn_set_exiting(struct ksmbd_conn *conn) { WRITE_ONCE(conn->status, KSMBD_SESS_EXITING); } + +static inline void ksmbd_conn_set_releasing(struct ksmbd_conn *conn) +{ + WRITE_ONCE(conn->status, KSMBD_SESS_RELEASING); +} + +void ksmbd_all_conn_set_status(u64 sess_id, u32 status); #endif /* __CONNECTION_H__ */ diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c index 8ce17b3fb8da..aa9c138d5851 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/ksmbd/mgmt/tree_connect.c @@ -129,6 +129,9 @@ int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess) struct ksmbd_tree_connect *tc; unsigned long id; + if (!sess) + return -EINVAL; + xa_for_each(&sess->tree_conns, id, tc) ret |= ksmbd_tree_conn_disconnect(sess, tc); xa_destroy(&sess->tree_conns); diff --git a/fs/ksmbd/mgmt/user_session.c b/fs/ksmbd/mgmt/user_session.c index 3840de7773b9..8a5dcab05614 100644 --- a/fs/ksmbd/mgmt/user_session.c +++ b/fs/ksmbd/mgmt/user_session.c @@ -144,10 +144,6 @@ void ksmbd_session_destroy(struct ksmbd_session *sess) if (!sess) return; - down_write(&sessions_table_lock); - hash_del(&sess->hlist); - up_write(&sessions_table_lock); - if (sess->user) ksmbd_free_user(sess->user); @@ -178,15 +174,18 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) unsigned long id; struct ksmbd_session *sess; + down_write(&sessions_table_lock); xa_for_each(&conn->sessions, id, sess) { if (sess->state != SMB2_SESSION_VALID || time_after(jiffies, sess->last_active + SMB2_SESSION_TIMEOUT)) { xa_erase(&conn->sessions, sess->id); + hash_del(&sess->hlist); ksmbd_session_destroy(sess); continue; } } + up_write(&sessions_table_lock); } int ksmbd_session_register(struct ksmbd_conn *conn, @@ -198,15 +197,16 @@ int ksmbd_session_register(struct ksmbd_conn *conn, return xa_err(xa_store(&conn->sessions, sess->id, sess, GFP_KERNEL)); } -static void ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) +static int ksmbd_chann_del(struct ksmbd_conn *conn, struct ksmbd_session *sess) { struct channel *chann; chann = xa_erase(&sess->ksmbd_chann_list, (long)conn); if (!chann) - return; + return -ENOENT; kfree(chann); + return 0; } void ksmbd_sessions_deregister(struct ksmbd_conn *conn) @@ -214,13 +214,37 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) struct ksmbd_session *sess; unsigned long id; + down_write(&sessions_table_lock); + if (conn->binding) { + int bkt; + struct hlist_node *tmp; + + hash_for_each_safe(sessions_table, bkt, tmp, sess, hlist) { + if (!ksmbd_chann_del(conn, sess) && + xa_empty(&sess->ksmbd_chann_list)) { + hash_del(&sess->hlist); + ksmbd_session_destroy(sess); + } + } + } + xa_for_each(&conn->sessions, id, sess) { + unsigned long chann_id; + struct channel *chann; + + xa_for_each(&sess->ksmbd_chann_list, chann_id, chann) { + if (chann->conn != conn) + ksmbd_conn_set_exiting(chann->conn); + } + ksmbd_chann_del(conn, sess); if (xa_empty(&sess->ksmbd_chann_list)) { xa_erase(&conn->sessions, sess->id); + hash_del(&sess->hlist); ksmbd_session_destroy(sess); } } + up_write(&sessions_table_lock); } struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 26db1dc38b45..0ca1c5daf60a 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2081,21 +2081,22 @@ int smb2_session_logoff(struct ksmbd_work *work) struct smb2_logoff_rsp *rsp = smb2_get_msg(work->response_buf); struct ksmbd_session *sess; struct smb2_logoff_req *req = smb2_get_msg(work->request_buf); + u64 sess_id = le64_to_cpu(req->hdr.SessionId); rsp->StructureSize = cpu_to_le16(4); inc_rfc1001_len(work->response_buf, 4); ksmbd_debug(SMB, "request\n"); - ksmbd_conn_set_need_reconnect(conn); + ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_RECONNECT); ksmbd_close_session_fds(work); - ksmbd_conn_wait_idle(conn); + ksmbd_conn_wait_idle(conn, sess_id); /* * Re-lookup session to validate if session is deleted * while waiting request complete */ - sess = ksmbd_session_lookup(conn, le64_to_cpu(req->hdr.SessionId)); + sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -2108,7 +2109,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; - ksmbd_conn_set_need_negotiate(conn); + ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); return 0; } @@ -6863,7 +6864,7 @@ int smb2_lock(struct ksmbd_work *work) nolock = 1; /* check locks in connection list */ - read_lock(&conn_list_lock); + down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) { spin_lock(&conn->llist_lock); list_for_each_entry_safe(cmp_lock, tmp2, &conn->lock_list, clist) { @@ -6880,7 +6881,7 @@ int smb2_lock(struct ksmbd_work *work) list_del(&cmp_lock->flist); list_del(&cmp_lock->clist); spin_unlock(&conn->llist_lock); - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); locks_free_lock(cmp_lock->fl); kfree(cmp_lock); @@ -6902,7 +6903,7 @@ int smb2_lock(struct ksmbd_work *work) cmp_lock->start > smb_lock->start && cmp_lock->start < smb_lock->end) { spin_unlock(&conn->llist_lock); - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); pr_err("previous lock conflict with zero byte lock range\n"); goto out; } @@ -6911,7 +6912,7 @@ int smb2_lock(struct ksmbd_work *work) smb_lock->start > cmp_lock->start && smb_lock->start < cmp_lock->end) { spin_unlock(&conn->llist_lock); - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); pr_err("current lock conflict with zero byte lock range\n"); goto out; } @@ -6922,14 +6923,14 @@ int smb2_lock(struct ksmbd_work *work) cmp_lock->end >= smb_lock->end)) && !cmp_lock->zero_len && !smb_lock->zero_len) { spin_unlock(&conn->llist_lock); - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); pr_err("Not allow lock operation on exclusive lock range\n"); goto out; } } spin_unlock(&conn->llist_lock); } - read_unlock(&conn_list_lock); + up_read(&conn_list_lock); out_check_cl: if (smb_lock->fl->fl_type == F_UNLCK && nolock) { pr_err("Try to unlock nolocked range\n"); -- GitLab From 30210947a343b6b3ca13adc9bfc88e1543e16dd5 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:51:12 +0900 Subject: [PATCH 4513/5631] ksmbd: fix racy issue under cocurrent smb2 tree disconnect There is UAF issue under cocurrent smb2 tree disconnect. This patch introduce TREE_CONN_EXPIRE flags for tcon to avoid cocurrent access. Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20592 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/mgmt/tree_connect.c | 10 +++++++++- fs/ksmbd/mgmt/tree_connect.h | 3 +++ fs/ksmbd/smb2pdu.c | 3 ++- 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/fs/ksmbd/mgmt/tree_connect.c b/fs/ksmbd/mgmt/tree_connect.c index aa9c138d5851..f07a05f37651 100644 --- a/fs/ksmbd/mgmt/tree_connect.c +++ b/fs/ksmbd/mgmt/tree_connect.c @@ -109,7 +109,15 @@ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *ksmbd_tree_conn_lookup(struct ksmbd_session *sess, unsigned int id) { - return xa_load(&sess->tree_conns, id); + struct ksmbd_tree_connect *tcon; + + tcon = xa_load(&sess->tree_conns, id); + if (tcon) { + if (test_bit(TREE_CONN_EXPIRE, &tcon->status)) + tcon = NULL; + } + + return tcon; } struct ksmbd_share_config *ksmbd_tree_conn_share(struct ksmbd_session *sess, diff --git a/fs/ksmbd/mgmt/tree_connect.h b/fs/ksmbd/mgmt/tree_connect.h index 0f97ddc1e39c..700df36cf3e3 100644 --- a/fs/ksmbd/mgmt/tree_connect.h +++ b/fs/ksmbd/mgmt/tree_connect.h @@ -14,6 +14,8 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; +#define TREE_CONN_EXPIRE 1 + struct ksmbd_tree_connect { int id; @@ -25,6 +27,7 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; + unsigned long status; }; struct ksmbd_tree_conn_status { diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 0ca1c5daf60a..cb93fd231f4e 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2053,11 +2053,12 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_debug(SMB, "request\n"); - if (!tcon) { + if (!tcon || test_and_set_bit(TREE_CONN_EXPIRE, &tcon->status)) { struct smb2_tree_disconnect_req *req = smb2_get_msg(work->request_buf); ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); return 0; -- GitLab From eb307d09fe15844fdaebeb8cc8c9b9e925430aa5 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 3 May 2023 08:51:51 +0900 Subject: [PATCH 4514/5631] ksmbd: call rcu_barrier() in ksmbd_server_exit() racy issue is triggered the bug by racing between closing a connection and rmmod. In ksmbd, rcu_barrier() is not called at module unload time, so nothing prevents ksmbd from getting unloaded while it still has RCU callbacks pending. It leads to trigger unintended execution of kernel code locally and use to defeat protections such as Kernel Lockdown Cc: stable@vger.kernel.org Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-20477 Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/server.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 2ebf6985a88d..f9b2e0f19b03 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -606,6 +606,7 @@ static int __init ksmbd_server_init(void) static void __exit ksmbd_server_exit(void) { ksmbd_server_shutdown(); + rcu_barrier(); ksmbd_release_inode_hash(); } -- GitLab From ee20d7c6100752eaf2409d783f4f1449c29ea33d Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Tue, 25 Apr 2023 02:42:56 -0300 Subject: [PATCH 4515/5631] cifs: fix potential race when tree connecting ipc Protect access of TCP_Server_Info::hostname when building the ipc tree name as it might get freed in cifsd thread and thus causing an use-after-free bug in __tree_connect_dfs_target(). Also, while at it, update status of IPC tcon on success and then avoid any extra tree connects. Cc: stable@vger.kernel.org # v6.2+ Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/dfs.c | 57 ++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 50 insertions(+), 7 deletions(-) diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index 3a11716b6e13..37f7da4f5c8b 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -374,6 +374,54 @@ static int target_share_matches_server(struct TCP_Server_Info *server, char *sha return rc; } +static void __tree_connect_ipc(const unsigned int xid, char *tree, + struct cifs_sb_info *cifs_sb, + struct cifs_ses *ses) +{ + struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon = ses->tcon_ipc; + int rc; + + spin_lock(&ses->ses_lock); + spin_lock(&ses->chan_lock); + if (cifs_chan_needs_reconnect(ses, server) || + ses->ses_status != SES_GOOD) { + spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); + cifs_server_dbg(FYI, "%s: skipping ipc reconnect due to disconnected ses\n", + __func__); + return; + } + spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); + + cifs_server_lock(server); + scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); + cifs_server_unlock(server); + + rc = server->ops->tree_connect(xid, ses, tree, tcon, + cifs_sb->local_nls); + cifs_server_dbg(FYI, "%s: tree_reconnect %s: %d\n", __func__, tree, rc); + spin_lock(&tcon->tc_lock); + if (rc) { + tcon->status = TID_NEED_TCON; + } else { + tcon->status = TID_GOOD; + tcon->need_reconnect = false; + } + spin_unlock(&tcon->tc_lock); +} + +static void tree_connect_ipc(const unsigned int xid, char *tree, + struct cifs_sb_info *cifs_sb, + struct cifs_tcon *tcon) +{ + struct cifs_ses *ses = tcon->ses; + + __tree_connect_ipc(xid, tree, cifs_sb, ses); + __tree_connect_ipc(xid, tree, cifs_sb, CIFS_DFS_ROOT_SES(ses)); +} + static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, char *tree, bool islink, struct dfs_cache_tgt_list *tl) @@ -382,7 +430,6 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t struct TCP_Server_Info *server = tcon->ses->server; const struct smb_version_operations *ops = server->ops; struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses); - struct cifs_tcon *ipc = root_ses->tcon_ipc; char *share = NULL, *prefix = NULL; struct dfs_cache_tgt_iterator *tit; bool target_match; @@ -418,18 +465,14 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t } dfs_cache_noreq_update_tgthint(server->current_fullpath + 1, tit); - - if (ipc->need_reconnect) { - scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname); - rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls); - cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc); - } + tree_connect_ipc(xid, tree, cifs_sb, tcon); scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); if (!islink) { rc = ops->tree_connect(xid, tcon->ses, tree, tcon, cifs_sb->local_nls); break; } + /* * If no dfs referrals were returned from link target, then just do a TREE_CONNECT * to it. Otherwise, cache the dfs referral and then mark current tcp ses for -- GitLab From 3dc9c433c9dde15477d02b609ccb4328e2adb6dc Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Wed, 26 Apr 2023 13:43:53 -0300 Subject: [PATCH 4516/5631] cifs: protect access of TCP_Server_Info::{origin,leaf}_fullpath Protect access of TCP_Server_Info::{origin,leaf}_fullpath when matching DFS connections, and get rid of TCP_Server_Info::current_fullpath while we're at it. Cc: stable@vger.kernel.org # v6.2+ Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 20 +++++++++++++------- fs/cifs/connect.c | 10 ++++++---- fs/cifs/dfs.c | 14 ++++++++------ fs/cifs/dfs.h | 13 +++++++++++-- fs/cifs/dfs_cache.c | 6 +++++- 5 files changed, 43 insertions(+), 20 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 08a73dcb7786..a62447404851 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -736,17 +736,23 @@ struct TCP_Server_Info { #endif struct mutex refpath_lock; /* protects leaf_fullpath */ /* - * Canonical DFS full paths that were used to chase referrals in mount and reconnect. + * origin_fullpath: Canonical copy of smb3_fs_context::source. + * It is used for matching existing DFS tcons. * - * origin_fullpath: first or original referral path - * leaf_fullpath: last referral path (might be changed due to nested links in reconnect) + * leaf_fullpath: Canonical DFS referral path related to this + * connection. + * It is used in DFS cache refresher, reconnect and may + * change due to nested DFS links. * - * current_fullpath: pointer to either origin_fullpath or leaf_fullpath - * NOTE: cannot be accessed outside cifs_reconnect() and smb2_reconnect() + * Both protected by @refpath_lock and @srv_lock. The @refpath_lock is + * mosly used for not requiring a copy of @leaf_fullpath when getting + * cached or new DFS referrals (which might also sleep during I/O). + * While @srv_lock is held for making string and NULL comparions against + * both fields as in mount(2) and cache refresh. * - * format: \\HOST\SHARE\[OPTIONAL PATH] + * format: \\HOST\SHARE[\OPTIONAL PATH] */ - char *origin_fullpath, *leaf_fullpath, *current_fullpath; + char *origin_fullpath, *leaf_fullpath; }; static inline bool is_smb1(struct TCP_Server_Info *server) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c71505a29482..9451b1023af8 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -454,7 +454,6 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; - const char *refpath = server->current_fullpath + 1; struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); struct dfs_cache_tgt_iterator *target_hint = NULL; int num_targets = 0; @@ -467,8 +466,10 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) * through /proc/fs/cifs/dfscache or the target list is empty due to server settings after * refreshing the referral, so, in this case, default it to 1. */ - if (!dfs_cache_noreq_find(refpath, NULL, &tl)) + mutex_lock(&server->refpath_lock); + if (!dfs_cache_noreq_find(server->leaf_fullpath + 1, NULL, &tl)) num_targets = dfs_cache_get_nr_tgts(&tl); + mutex_unlock(&server->refpath_lock); if (!num_targets) num_targets = 1; @@ -512,7 +513,9 @@ static int reconnect_dfs_server(struct TCP_Server_Info *server) mod_delayed_work(cifsiod_wq, &server->reconnect, 0); } while (server->tcpStatus == CifsNeedReconnect); - dfs_cache_noreq_update_tgthint(refpath, target_hint); + mutex_lock(&server->refpath_lock); + dfs_cache_noreq_update_tgthint(server->leaf_fullpath + 1, target_hint); + mutex_unlock(&server->refpath_lock); dfs_cache_free_tgts(&tl); /* Need to set up echo worker again once connection has been established */ @@ -1582,7 +1585,6 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, rc = -ENOMEM; goto out_err; } - tcp_ses->current_fullpath = tcp_ses->leaf_fullpath; } if (ctx->nosharesock) diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index 37f7da4f5c8b..c4ec5c67087b 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -248,11 +248,12 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) tcon = mnt_ctx->tcon; mutex_lock(&server->refpath_lock); + spin_lock(&server->srv_lock); if (!server->origin_fullpath) { server->origin_fullpath = origin_fullpath; - server->current_fullpath = server->leaf_fullpath; origin_fullpath = NULL; } + spin_unlock(&server->srv_lock); mutex_unlock(&server->refpath_lock); if (list_empty(&tcon->dfs_ses_list)) { @@ -342,10 +343,11 @@ static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb rc = PTR_ERR(npath); } else { mutex_lock(&server->refpath_lock); + spin_lock(&server->srv_lock); kfree(server->leaf_fullpath); server->leaf_fullpath = npath; + spin_unlock(&server->srv_lock); mutex_unlock(&server->refpath_lock); - server->current_fullpath = server->leaf_fullpath; } return rc; } @@ -450,7 +452,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t share = prefix = NULL; /* Check if share matches with tcp ses */ - rc = dfs_cache_get_tgt_share(server->current_fullpath + 1, tit, &share, &prefix); + rc = dfs_cache_get_tgt_share(server->leaf_fullpath + 1, tit, &share, &prefix); if (rc) { cifs_dbg(VFS, "%s: failed to parse target share: %d\n", __func__, rc); break; @@ -464,7 +466,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t continue; } - dfs_cache_noreq_update_tgthint(server->current_fullpath + 1, tit); + dfs_cache_noreq_update_tgthint(server->leaf_fullpath + 1, tit); tree_connect_ipc(xid, tree, cifs_sb, tcon); scnprintf(tree, MAX_TREE_SIZE, "\\%s", share); @@ -582,8 +584,8 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru cifs_sb = CIFS_SB(sb); /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */ - if (!server->current_fullpath || - dfs_cache_noreq_find(server->current_fullpath + 1, &ref, &tl)) { + if (!server->leaf_fullpath || + dfs_cache_noreq_find(server->leaf_fullpath + 1, &ref, &tl)) { rc = ops->tree_connect(xid, tcon->ses, tcon->tree_name, tcon, cifs_sb->local_nls); goto out; } diff --git a/fs/cifs/dfs.h b/fs/cifs/dfs.h index 0b8cbf721fff..1c90df5ecfbd 100644 --- a/fs/cifs/dfs.h +++ b/fs/cifs/dfs.h @@ -43,8 +43,12 @@ static inline char *dfs_get_automount_devname(struct dentry *dentry, void *page) size_t len; char *s; - if (unlikely(!server->origin_fullpath)) + spin_lock(&server->srv_lock); + if (unlikely(!server->origin_fullpath)) { + spin_unlock(&server->srv_lock); return ERR_PTR(-EREMOTE); + } + spin_unlock(&server->srv_lock); s = dentry_path_raw(dentry, page, PATH_MAX); if (IS_ERR(s)) @@ -53,13 +57,18 @@ static inline char *dfs_get_automount_devname(struct dentry *dentry, void *page) if (!s[1]) s++; + spin_lock(&server->srv_lock); len = strlen(server->origin_fullpath); - if (s < (char *)page + len) + if (s < (char *)page + len) { + spin_unlock(&server->srv_lock); return ERR_PTR(-ENAMETOOLONG); + } s -= len; memcpy(s, server->origin_fullpath, len); + spin_unlock(&server->srv_lock); convert_delimiter(s, '/'); + return s; } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 30cbdf8514a5..6557d7b2798a 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1278,8 +1278,12 @@ static void refresh_cache_worker(struct work_struct *work) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - if (!server->leaf_fullpath) + spin_lock(&server->srv_lock); + if (!server->leaf_fullpath) { + spin_unlock(&server->srv_lock); continue; + } + spin_unlock(&server->srv_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { if (ses->tcon_ipc) { -- GitLab From 6be2ea33a4093402252724a00c4af8033725184c Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Thu, 27 Apr 2023 04:40:08 -0300 Subject: [PATCH 4517/5631] cifs: avoid potential races when handling multiple dfs tcons Now that a DFS tcon manages its own list of DFS referrals and sessions, there is no point in having a single worker to refresh referrals of all DFS tcons. Make it faster and less prone to race conditions when having several mounts by queueing a worker per DFS tcon that will take care of refreshing only the DFS referrals related to it. Cc: stable@vger.kernel.org # v6.2+ Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 2 +- fs/cifs/connect.c | 7 ++- fs/cifs/dfs.c | 4 ++ fs/cifs/dfs_cache.c | 137 +++++++++++++++++++------------------------- fs/cifs/dfs_cache.h | 9 +++ 5 files changed, 80 insertions(+), 79 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a62447404851..9c5cd332ce14 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1238,8 +1238,8 @@ struct cifs_tcon { struct cached_fids *cfids; /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - struct list_head ulist; /* cache update list */ struct list_head dfs_ses_list; + struct delayed_work dfs_cache_work; #endif struct delayed_work query_interfaces; /* query interfaces workqueue job */ }; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9451b1023af8..9a730efbce32 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2340,6 +2340,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) /* cancel polling of interfaces */ cancel_delayed_work_sync(&tcon->query_interfaces); +#ifdef CONFIG_CIFS_DFS_UPCALL + cancel_delayed_work_sync(&tcon->dfs_cache_work); +#endif if (tcon->use_witness) { int rc; @@ -2587,7 +2590,9 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, (SMB_INTERFACE_POLL_INTERVAL * HZ)); } - +#ifdef CONFIG_CIFS_DFS_UPCALL + INIT_DELAYED_WORK(&tcon->dfs_cache_work, dfs_cache_refresh); +#endif spin_lock(&cifs_tcp_ses_lock); list_add(&tcon->tcon_list, &ses->tcon_list); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index c4ec5c67087b..da4e083b1ab4 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -157,6 +157,8 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co rc = cifs_is_path_remote(mnt_ctx); } + dfs_cache_noreq_update_tgthint(ref_path + 1, tit); + if (rc == -EREMOTE && is_refsrv) { rc2 = get_root_smb_session(mnt_ctx); if (rc2) @@ -259,6 +261,8 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) if (list_empty(&tcon->dfs_ses_list)) { list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list); + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + dfs_cache_get_ttl() * HZ); } else { dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list); } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 6557d7b2798a..1513b2709889 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -20,12 +20,14 @@ #include "cifs_unicode.h" #include "smb2glob.h" #include "dns_resolve.h" +#include "dfs.h" #include "dfs_cache.h" -#define CACHE_HTABLE_SIZE 32 -#define CACHE_MAX_ENTRIES 64 -#define CACHE_MIN_TTL 120 /* 2 minutes */ +#define CACHE_HTABLE_SIZE 32 +#define CACHE_MAX_ENTRIES 64 +#define CACHE_MIN_TTL 120 /* 2 minutes */ +#define CACHE_DEFAULT_TTL 300 /* 5 minutes */ #define IS_DFS_INTERLINK(v) (((v) & DFSREF_REFERRAL_SERVER) && !((v) & DFSREF_STORAGE_SERVER)) @@ -50,10 +52,9 @@ struct cache_entry { }; static struct kmem_cache *cache_slab __read_mostly; -static struct workqueue_struct *dfscache_wq __read_mostly; +struct workqueue_struct *dfscache_wq; -static int cache_ttl; -static DEFINE_SPINLOCK(cache_ttl_lock); +atomic_t dfs_cache_ttl; static struct nls_table *cache_cp; @@ -65,10 +66,6 @@ static atomic_t cache_count; static struct hlist_head cache_htable[CACHE_HTABLE_SIZE]; static DECLARE_RWSEM(htable_rw_lock); -static void refresh_cache_worker(struct work_struct *work); - -static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker); - /** * dfs_cache_canonical_path - get a canonical DFS path * @@ -290,7 +287,9 @@ int dfs_cache_init(void) int rc; int i; - dfscache_wq = alloc_workqueue("cifs-dfscache", WQ_FREEZABLE | WQ_UNBOUND, 1); + dfscache_wq = alloc_workqueue("cifs-dfscache", + WQ_UNBOUND|WQ_FREEZABLE|WQ_MEM_RECLAIM, + 0); if (!dfscache_wq) return -ENOMEM; @@ -306,6 +305,7 @@ int dfs_cache_init(void) INIT_HLIST_HEAD(&cache_htable[i]); atomic_set(&cache_count, 0); + atomic_set(&dfs_cache_ttl, CACHE_DEFAULT_TTL); cache_cp = load_nls("utf8"); if (!cache_cp) cache_cp = load_nls_default(); @@ -480,6 +480,7 @@ static struct cache_entry *add_cache_entry_locked(struct dfs_info3_param *refs, int rc; struct cache_entry *ce; unsigned int hash; + int ttl; WARN_ON(!rwsem_is_locked(&htable_rw_lock)); @@ -496,15 +497,8 @@ static struct cache_entry *add_cache_entry_locked(struct dfs_info3_param *refs, if (IS_ERR(ce)) return ce; - spin_lock(&cache_ttl_lock); - if (!cache_ttl) { - cache_ttl = ce->ttl; - queue_delayed_work(dfscache_wq, &refresh_task, cache_ttl * HZ); - } else { - cache_ttl = min_t(int, cache_ttl, ce->ttl); - mod_delayed_work(dfscache_wq, &refresh_task, cache_ttl * HZ); - } - spin_unlock(&cache_ttl_lock); + ttl = min_t(int, atomic_read(&dfs_cache_ttl), ce->ttl); + atomic_set(&dfs_cache_ttl, ttl); hlist_add_head(&ce->hlist, &cache_htable[hash]); dump_ce(ce); @@ -616,7 +610,6 @@ static struct cache_entry *lookup_cache_entry(const char *path) */ void dfs_cache_destroy(void) { - cancel_delayed_work_sync(&refresh_task); unload_nls(cache_cp); flush_cache_ents(); kmem_cache_destroy(cache_slab); @@ -1142,6 +1135,7 @@ static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, c * target shares in @refs. */ static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server, + const char *path, struct dfs_cache_tgt_list *old_tl, struct dfs_cache_tgt_list *new_tl) { @@ -1153,8 +1147,10 @@ static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server, nit = dfs_cache_get_next_tgt(new_tl, nit)) { if (target_share_equal(server, dfs_cache_get_tgt_name(oit), - dfs_cache_get_tgt_name(nit))) + dfs_cache_get_tgt_name(nit))) { + dfs_cache_noreq_update_tgthint(path, nit); return; + } } } @@ -1162,13 +1158,28 @@ static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server, cifs_signal_cifsd_for_reconnect(server, true); } +static bool is_ses_good(struct cifs_ses *ses) +{ + struct TCP_Server_Info *server = ses->server; + struct cifs_tcon *tcon = ses->tcon_ipc; + bool ret; + + spin_lock(&ses->ses_lock); + spin_lock(&ses->chan_lock); + ret = !cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD && + !tcon->need_reconnect; + spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); + return ret; +} + /* Refresh dfs referral of tcon and mark it for reconnect if needed */ -static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_refresh) +static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh) { struct dfs_cache_tgt_list old_tl = DFS_CACHE_TGT_LIST_INIT(old_tl); struct dfs_cache_tgt_list new_tl = DFS_CACHE_TGT_LIST_INIT(new_tl); - struct cifs_ses *ses = CIFS_DFS_ROOT_SES(tcon->ses); - struct cifs_tcon *ipc = ses->tcon_ipc; + struct TCP_Server_Info *server = ses->server; bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; @@ -1190,20 +1201,19 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r goto out; } - spin_lock(&ipc->tc_lock); - if (ipc->status != TID_GOOD) { - spin_unlock(&ipc->tc_lock); - cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n", __func__); + ses = CIFS_DFS_ROOT_SES(ses); + if (!is_ses_good(ses)) { + cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n", + __func__); goto out; } - spin_unlock(&ipc->tc_lock); ce = cache_refresh_path(xid, ses, path, true); if (!IS_ERR(ce)) { rc = get_targets(ce, &new_tl); up_read(&htable_rw_lock); cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc); - mark_for_reconnect_if_needed(tcon->ses->server, &old_tl, &new_tl); + mark_for_reconnect_if_needed(server, path, &old_tl, &new_tl); } out: @@ -1216,10 +1226,11 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh) { struct TCP_Server_Info *server = tcon->ses->server; + struct cifs_ses *ses = tcon->ses; mutex_lock(&server->refpath_lock); if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, tcon, force_refresh); + __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh); mutex_unlock(&server->refpath_lock); return 0; } @@ -1263,60 +1274,32 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) return refresh_tcon(tcon, true); } -/* - * Worker that will refresh DFS cache from all active mounts based on lowest TTL value - * from a DFS referral. - */ -static void refresh_cache_worker(struct work_struct *work) +/* Refresh all DFS referrals related to DFS tcon */ +void dfs_cache_refresh(struct work_struct *work) { struct TCP_Server_Info *server; - struct cifs_tcon *tcon, *ntcon; - struct list_head tcons; + struct dfs_root_ses *rses; + struct cifs_tcon *tcon; struct cifs_ses *ses; - INIT_LIST_HEAD(&tcons); + tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); + ses = tcon->ses; + server = ses->server; - spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - spin_lock(&server->srv_lock); - if (!server->leaf_fullpath) { - spin_unlock(&server->srv_lock); - continue; - } - spin_unlock(&server->srv_lock); - - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - if (ses->tcon_ipc) { - ses->ses_count++; - list_add_tail(&ses->tcon_ipc->ulist, &tcons); - } - list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - if (!tcon->ipc) { - tcon->tc_count++; - list_add_tail(&tcon->ulist, &tcons); - } - } - } - } - spin_unlock(&cifs_tcp_ses_lock); - - list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { - struct TCP_Server_Info *server = tcon->ses->server; - - list_del_init(&tcon->ulist); + mutex_lock(&server->refpath_lock); + if (server->leaf_fullpath) + __refresh_tcon(server->leaf_fullpath + 1, ses, false); + mutex_unlock(&server->refpath_lock); + list_for_each_entry(rses, &tcon->dfs_ses_list, list) { + ses = rses->ses; + server = ses->server; mutex_lock(&server->refpath_lock); if (server->leaf_fullpath) - __refresh_tcon(server->leaf_fullpath + 1, tcon, false); + __refresh_tcon(server->leaf_fullpath + 1, ses, false); mutex_unlock(&server->refpath_lock); - - if (tcon->ipc) - cifs_put_smb_ses(tcon->ses); - else - cifs_put_tcon(tcon); } - spin_lock(&cache_ttl_lock); - queue_delayed_work(dfscache_wq, &refresh_task, cache_ttl * HZ); - spin_unlock(&cache_ttl_lock); + queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, + atomic_read(&dfs_cache_ttl) * HZ); } diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index e0d39393035a..c6d89cd6d4fd 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -13,6 +13,9 @@ #include #include "cifsglob.h" +extern struct workqueue_struct *dfscache_wq; +extern atomic_t dfs_cache_ttl; + #define DFS_CACHE_TGT_LIST_INIT(var) { .tl_numtgts = 0, .tl_list = LIST_HEAD_INIT((var).tl_list), } struct dfs_cache_tgt_list { @@ -42,6 +45,7 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, char **prefix); char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap); int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb); +void dfs_cache_refresh(struct work_struct *work); static inline struct dfs_cache_tgt_iterator * dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl, @@ -89,4 +93,9 @@ dfs_cache_get_nr_tgts(const struct dfs_cache_tgt_list *tl) return tl ? tl->tl_numtgts : 0; } +static inline int dfs_cache_get_ttl(void) +{ + return atomic_read(&dfs_cache_ttl); +} + #endif /* _CIFS_DFS_CACHE_H */ -- GitLab From be884585852e7d8336e765504399972b3034a89f Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 20 Apr 2023 08:27:17 +0100 Subject: [PATCH 4518/5631] mailbox: mailbox-test: Explicitly include header for spinlock support Presently the support appears to be implied. Signed-off-by: Lee Jones Signed-off-by: Jassi Brar --- drivers/mailbox/mailbox-test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 4555d678fadd..51e62817f243 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include -- GitLab From 2d1e952a2b8e5e92d8d55ac88a7cf7ca5ea591ad Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 20 Apr 2023 08:27:18 +0100 Subject: [PATCH 4519/5631] mailbox: mailbox-test: Fix potential double-free in mbox_test_message_write() If a user can make copy_from_user() fail, there is a potential for UAF/DF due to a lack of locking around the allocation, use and freeing of the data buffers. This issue is not theoretical. I managed to author a POC for it: BUG: KASAN: double-free in kfree+0x5c/0xac Free of addr ffff29280be5de00 by task poc/356 CPU: 1 PID: 356 Comm: poc Not tainted 6.1.0-00001-g961aa6552c04-dirty #20 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 show_stack+0x18/0x40 dump_stack_lvl+0x64/0x80 print_report+0x188/0x48c kasan_report_invalid_free+0xa0/0xc0 ____kasan_slab_free+0x174/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Allocated by task 356: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xc0 kmalloc_trace+0x58/0x70 mbox_test_message_write+0x6c/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Freed by task 357: kasan_save_stack+0x3c/0x70 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c ____kasan_slab_free+0x13c/0x1b0 __kasan_slab_free+0x18/0x24 __kmem_cache_free+0x130/0x2e0 kfree+0x5c/0xac mbox_test_message_write+0x208/0x29c full_proxy_write+0x90/0xf0 vfs_write+0x154/0x440 ksys_write+0xcc/0x180 __arm64_sys_write+0x44/0x60 invoke_syscall+0x60/0x190 el0_svc_common.constprop.0+0x7c/0x160 do_el0_svc+0x40/0xf0 el0_svc+0x2c/0x6c el0t_64_sync_handler+0xf4/0x120 el0t_64_sync+0x18c/0x190 Signed-off-by: Lee Jones Signed-off-by: Jassi Brar --- drivers/mailbox/mailbox-test.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/mailbox/mailbox-test.c b/drivers/mailbox/mailbox-test.c index 51e62817f243..c4a705c30331 100644 --- a/drivers/mailbox/mailbox-test.c +++ b/drivers/mailbox/mailbox-test.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -39,6 +40,7 @@ struct mbox_test_device { char *signal; char *message; spinlock_t lock; + struct mutex mutex; wait_queue_head_t waitq; struct fasync_struct *async_queue; struct dentry *root_debugfs_dir; @@ -111,6 +113,8 @@ static ssize_t mbox_test_message_write(struct file *filp, return -EINVAL; } + mutex_lock(&tdev->mutex); + tdev->message = kzalloc(MBOX_MAX_MSG_LEN, GFP_KERNEL); if (!tdev->message) return -ENOMEM; @@ -145,6 +149,8 @@ static ssize_t mbox_test_message_write(struct file *filp, kfree(tdev->message); tdev->signal = NULL; + mutex_unlock(&tdev->mutex); + return ret < 0 ? ret : count; } @@ -393,6 +399,7 @@ static int mbox_test_probe(struct platform_device *pdev) platform_set_drvdata(pdev, tdev); spin_lock_init(&tdev->lock); + mutex_init(&tdev->mutex); if (tdev->rx_channel) { tdev->rx_buffer = devm_kzalloc(&pdev->dev, -- GitLab From 7490b8fb98848df2e7ac5c4a0fc2e898146695d1 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:17:38 +0100 Subject: [PATCH 4520/5631] mailbox: rockchip: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/mailbox/rockchip-mailbox.c:158:34: error: ‘rockchip_mbox_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jassi Brar --- drivers/mailbox/rockchip-mailbox.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index e02d3c9e3693..5a4934d39ad6 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -248,7 +248,7 @@ static struct platform_driver rockchip_mbox_driver = { .probe = rockchip_mbox_probe, .driver = { .name = "rockchip-mailbox", - .of_match_table = of_match_ptr(rockchip_mbox_of_match), + .of_match_table = rockchip_mbox_of_match, }, }; -- GitLab From e2aa7993115cfab8a1e6efa7cae05b6817ea69be Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 11 Mar 2023 12:17:39 +0100 Subject: [PATCH 4521/5631] mailbox: bcm-pdc: drop of_match_ptr for ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can match only via the DT table so the table should be always used and the of_match_ptr does not have any sense (this also allows ACPI matching via PRP0001, even though it might not be relevant here). drivers/mailbox/bcm-pdc-mailbox.c:1474:34: error: ‘pdc_mbox_of_match’ defined but not used [-Werror=unused-const-variable=] Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jassi Brar --- drivers/mailbox/bcm-pdc-mailbox.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c index 8d3a4c1fe761..8c95e3ce295f 100644 --- a/drivers/mailbox/bcm-pdc-mailbox.c +++ b/drivers/mailbox/bcm-pdc-mailbox.c @@ -1635,7 +1635,7 @@ static struct platform_driver pdc_mbox_driver = { .remove = pdc_remove, .driver = { .name = "brcm-iproc-pdc-mbox", - .of_match_table = of_match_ptr(pdc_mbox_of_match), + .of_match_table = pdc_mbox_of_match, }, }; module_platform_driver(pdc_mbox_driver); -- GitLab From 5f84a056cf437c4ee5f7ca5bc6928cc56ea5206c Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 9 Mar 2023 20:44:50 +0000 Subject: [PATCH 4522/5631] mailbox: mpfs: convert SOC_MICROCHIP_POLARFIRE to ARCH_MICROCHIP_POLARFIRE As part of converting RISC-V SOC_FOO symbols to ARCH_FOO to match the use of such symbols on other architectures, convert the Microchip FPGA mailbox driver to use the new symbol. Signed-off-by: Conor Dooley Signed-off-by: Jassi Brar --- drivers/mailbox/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 1495965bc394..3f97d5535267 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -176,7 +176,7 @@ config MAILBOX_TEST config POLARFIRE_SOC_MAILBOX tristate "PolarFire SoC (MPFS) Mailbox" depends on HAS_IOMEM - depends on SOC_MICROCHIP_POLARFIRE || COMPILE_TEST + depends on ARCH_MICROCHIP_POLARFIRE || COMPILE_TEST help This driver adds support for the PolarFire SoC (MPFS) mailbox controller. -- GitLab From 26e02e6c1012793248096028287ae7296029cd29 Mon Sep 17 00:00:00 2001 From: AngeloGioacchino Del Regno Date: Mon, 27 Mar 2023 10:36:37 +0200 Subject: [PATCH 4523/5631] dt-bindings: mailbox: mediatek,gce-mailbox: Add support for MT6795 Add a compatible string for the MT6795 Helio X10 SoC using MT8173 binding and add a header for the MT6795's GCE mailbox. Signed-off-by: AngeloGioacchino Del Regno Reviewed-by: Krzysztof Kozlowski Signed-off-by: Jassi Brar --- .../mailbox/mediatek,gce-mailbox.yaml | 20 +-- include/dt-bindings/gce/mediatek,mt6795-gce.h | 123 ++++++++++++++++++ 2 files changed, 135 insertions(+), 8 deletions(-) create mode 100644 include/dt-bindings/gce/mediatek,mt6795-gce.h diff --git a/Documentation/devicetree/bindings/mailbox/mediatek,gce-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/mediatek,gce-mailbox.yaml index d383b2ab3ce8..cef9d7601398 100644 --- a/Documentation/devicetree/bindings/mailbox/mediatek,gce-mailbox.yaml +++ b/Documentation/devicetree/bindings/mailbox/mediatek,gce-mailbox.yaml @@ -16,14 +16,18 @@ description: properties: compatible: - enum: - - mediatek,mt6779-gce - - mediatek,mt8173-gce - - mediatek,mt8183-gce - - mediatek,mt8186-gce - - mediatek,mt8188-gce - - mediatek,mt8192-gce - - mediatek,mt8195-gce + oneOf: + - enum: + - mediatek,mt6779-gce + - mediatek,mt8173-gce + - mediatek,mt8183-gce + - mediatek,mt8186-gce + - mediatek,mt8188-gce + - mediatek,mt8192-gce + - mediatek,mt8195-gce + - items: + - const: mediatek,mt6795-gce + - const: mediatek,mt8173-gce "#mbox-cells": const: 2 diff --git a/include/dt-bindings/gce/mediatek,mt6795-gce.h b/include/dt-bindings/gce/mediatek,mt6795-gce.h new file mode 100644 index 000000000000..97d5ba2d2b44 --- /dev/null +++ b/include/dt-bindings/gce/mediatek,mt6795-gce.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2023 Collabora Ltd. + * Author: AngeloGioacchino Del Regno + */ +#ifndef _DT_BINDINGS_GCE_MT6795_H +#define _DT_BINDINGS_GCE_MT6795_H + +/* GCE HW thread priority */ +#define CMDQ_THR_PRIO_LOWEST 0 +#define CMDQ_THR_PRIO_NORMAL 1 +#define CMDQ_THR_PRIO_NORMAL_2 2 +#define CMDQ_THR_PRIO_MEDIUM 3 +#define CMDQ_THR_PRIO_MEDIUM_2 4 +#define CMDQ_THR_PRIO_HIGH 5 +#define CMDQ_THR_PRIO_HIGHER 6 +#define CMDQ_THR_PRIO_HIGHEST 7 + +/* GCE SUBSYS */ +#define SUBSYS_1300XXXX 0 +#define SUBSYS_1400XXXX 1 +#define SUBSYS_1401XXXX 2 +#define SUBSYS_1402XXXX 3 +#define SUBSYS_1500XXXX 4 +#define SUBSYS_1600XXXX 5 +#define SUBSYS_1700XXXX 6 +#define SUBSYS_1800XXXX 7 +#define SUBSYS_1000XXXX 8 +#define SUBSYS_1001XXXX 9 +#define SUBSYS_1002XXXX 10 +#define SUBSYS_1003XXXX 11 +#define SUBSYS_1004XXXX 12 +#define SUBSYS_1005XXXX 13 +#define SUBSYS_1020XXXX 14 +#define SUBSYS_1021XXXX 15 +#define SUBSYS_1120XXXX 16 +#define SUBSYS_1121XXXX 17 +#define SUBSYS_1122XXXX 18 +#define SUBSYS_1123XXXX 19 +#define SUBSYS_1124XXXX 20 +#define SUBSYS_1125XXXX 21 +#define SUBSYS_1126XXXX 22 + +/* GCE HW EVENT */ +#define CMDQ_EVENT_MDP_RDMA0_SOF 0 +#define CMDQ_EVENT_MDP_RDMA1_SOF 1 +#define CMDQ_EVENT_MDP_DSI0_TE_SOF 2 +#define CMDQ_EVENT_MDP_DSI1_TE_SOF 3 +#define CMDQ_EVENT_MDP_MVW_SOF 4 +#define CMDQ_EVENT_MDP_TDSHP0_SOF 5 +#define CMDQ_EVENT_MDP_TDSHP1_SOF 6 +#define CMDQ_EVENT_MDP_WDMA_SOF 7 +#define CMDQ_EVENT_MDP_WROT0_SOF 8 +#define CMDQ_EVENT_MDP_WROT1_SOF 9 +#define CMDQ_EVENT_MDP_CROP_SOF 10 +#define CMDQ_EVENT_DISP_OVL0_SOF 11 +#define CMDQ_EVENT_DISP_OVL1_SOF 12 +#define CMDQ_EVENT_DISP_RDMA0_SOF 13 +#define CMDQ_EVENT_DISP_RDMA1_SOF 14 +#define CMDQ_EVENT_DISP_RDMA2_SOF 15 +#define CMDQ_EVENT_DISP_WDMA0_SOF 16 +#define CMDQ_EVENT_DISP_WDMA1_SOF 17 +#define CMDQ_EVENT_DISP_COLOR0_SOF 18 +#define CMDQ_EVENT_DISP_COLOR1_SOF 19 +#define CMDQ_EVENT_DISP_AAL_SOF 20 +#define CMDQ_EVENT_DISP_GAMMA_SOF 21 +#define CMDQ_EVENT_DISP_UFOE_SOF 22 +#define CMDQ_EVENT_DISP_PWM0_SOF 23 +#define CMDQ_EVENT_DISP_PWM1_SOF 24 +#define CMDQ_EVENT_DISP_OD_SOF 25 +#define CMDQ_EVENT_MDP_RDMA0_EOF 26 +#define CMDQ_EVENT_MDP_RDMA1_EOF 27 +#define CMDQ_EVENT_MDP_RSZ0_EOF 28 +#define CMDQ_EVENT_MDP_RSZ1_EOF 29 +#define CMDQ_EVENT_MDP_RSZ2_EOF 30 +#define CMDQ_EVENT_MDP_TDSHP0_EOF 31 +#define CMDQ_EVENT_MDP_TDSHP1_EOF 32 +#define CMDQ_EVENT_MDP_WDMA_EOF 33 +#define CMDQ_EVENT_MDP_WROT0_WRITE_EOF 34 +#define CMDQ_EVENT_MDP_WROT0_READ_EOF 35 +#define CMDQ_EVENT_MDP_WROT1_WRITE_EOF 36 +#define CMDQ_EVENT_MDP_WROT1_READ_EOF 37 +#define CMDQ_EVENT_MDP_CROP_EOF 38 +#define CMDQ_EVENT_DISP_OVL0_EOF 39 +#define CMDQ_EVENT_DISP_OVL1_EOF 40 +#define CMDQ_EVENT_DISP_RDMA0_EOF 41 +#define CMDQ_EVENT_DISP_RDMA1_EOF 42 +#define CMDQ_EVENT_DISP_RDMA2_EOF 43 +#define CMDQ_EVENT_DISP_WDMA0_EOF 44 +#define CMDQ_EVENT_DISP_WDMA1_EOF 45 +#define CMDQ_EVENT_DISP_COLOR0_EOF 46 +#define CMDQ_EVENT_DISP_COLOR1_EOF 47 +#define CMDQ_EVENT_DISP_AAL_EOF 48 +#define CMDQ_EVENT_DISP_GAMMA_EOF 49 +#define CMDQ_EVENT_DISP_UFOE_EOF 50 +#define CMDQ_EVENT_DISP_DPI0_EOF 51 +#define CMDQ_EVENT_MUTEX0_STREAM_EOF 52 +#define CMDQ_EVENT_MUTEX1_STREAM_EOF 53 +#define CMDQ_EVENT_MUTEX2_STREAM_EOF 54 +#define CMDQ_EVENT_MUTEX3_STREAM_EOF 55 +#define CMDQ_EVENT_MUTEX4_STREAM_EOF 56 +#define CMDQ_EVENT_MUTEX5_STREAM_EOF 57 +#define CMDQ_EVENT_MUTEX6_STREAM_EOF 58 +#define CMDQ_EVENT_MUTEX7_STREAM_EOF 59 +#define CMDQ_EVENT_MUTEX8_STREAM_EOF 60 +#define CMDQ_EVENT_MUTEX9_STREAM_EOF 61 +#define CMDQ_EVENT_DISP_RDMA0_UNDERRUN 62 +#define CMDQ_EVENT_DISP_RDMA1_UNDERRUN 63 +#define CMDQ_EVENT_DISP_RDMA2_UNDERRUN 64 +#define CMDQ_EVENT_ISP_PASS2_2_EOF 129 +#define CMDQ_EVENT_ISP_PASS2_1_EOF 130 +#define CMDQ_EVENT_ISP_PASS2_0_EOF 131 +#define CMDQ_EVENT_ISP_PASS1_1_EOF 132 +#define CMDQ_EVENT_ISP_PASS1_0_EOF 133 +#define CMDQ_EVENT_CAMSV_2_PASS1_EOF 134 +#define CMDQ_EVENT_CAMSV_1_PASS1_EOF 135 +#define CMDQ_EVENT_SENINF_CAM1_2_3_FIFO_FULL 136 +#define CMDQ_EVENT_SENINF_CAM0_FIFO_FULL 137 +#define CMDQ_EVENT_JPGENC_PASS2_EOF 257 +#define CMDQ_EVENT_JPGENC_PASS1_EOF 258 +#define CMDQ_EVENT_JPGDEC_EOF 259 + +#endif -- GitLab From 34d8775a0edc479644414c0dd2d880fb8aad55b0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 4 May 2023 00:57:33 -0500 Subject: [PATCH 4524/5631] dt-bindings: mailbox: qcom,apcs-kpss-global: use fallbacks for few variants Rework the compatibles of IPQ8074, SC7180, SC8180X and SM8150 as compatible devices (same from Linux driver point of view). This allows smaller of_device_id table in the Linux driver and smaller allOf:if:then: constraints. Signed-off-by: Krzysztof Kozlowski Acked-by: Rob Herring Signed-off-by: Jassi Brar --- .../mailbox/qcom,apcs-kpss-global.yaml | 30 +++++++++---------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index d888ead09282..c466b5fe934d 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -19,22 +19,14 @@ properties: - items: - enum: - qcom,ipq5332-apcs-apps-global + - qcom,ipq8074-apcs-apps-global - const: qcom,ipq6018-apcs-apps-global - items: - enum: - - qcom,ipq6018-apcs-apps-global - - qcom,ipq8074-apcs-apps-global - - qcom,msm8996-apcs-hmss-global - - qcom,msm8998-apcs-hmss-global - - qcom,qcm2290-apcs-hmss-global - qcom,sc7180-apss-shared - qcom,sc8180x-apss-shared - - qcom,sdm660-apcs-hmss-global - - qcom,sdm845-apss-shared - - qcom,sm4250-apcs-hmss-global - - qcom,sm6125-apcs-hmss-global - - qcom,sm6115-apcs-hmss-global - qcom,sm8150-apss-shared + - const: qcom,sdm845-apss-shared - items: - enum: - qcom,msm8916-apcs-kpss-global @@ -45,6 +37,18 @@ properties: - qcom,qcs404-apcs-apps-global - qcom,sdx55-apcs-gcc - const: syscon + - enum: + - qcom,ipq6018-apcs-apps-global + - qcom,ipq8074-apcs-apps-global + - qcom,msm8996-apcs-hmss-global + - qcom,msm8998-apcs-hmss-global + - qcom,qcm2290-apcs-hmss-global + - qcom,sdm660-apcs-hmss-global + - qcom,sdm845-apss-shared + - qcom,sm4250-apcs-hmss-global + - qcom,sm6115-apcs-hmss-global + - qcom,sm6125-apcs-hmss-global + reg: maxItems: 1 @@ -88,6 +92,7 @@ allOf: items: - const: pll - const: aux + - if: properties: compatible: @@ -111,7 +116,6 @@ allOf: contains: enum: - qcom,ipq6018-apcs-apps-global - - qcom,ipq8074-apcs-apps-global then: properties: clocks: @@ -133,14 +137,11 @@ allOf: - qcom,msm8996-apcs-hmss-global - qcom,msm8998-apcs-hmss-global - qcom,qcm2290-apcs-hmss-global - - qcom,sc7180-apss-shared - - qcom,sc8180x-apss-shared - qcom,sdm660-apcs-hmss-global - qcom,sdm845-apss-shared - qcom,sm4250-apcs-hmss-global - qcom,sm6115-apcs-hmss-global - qcom,sm6125-apcs-hmss-global - - qcom,sm8150-apss-shared then: properties: clocks: false @@ -152,7 +153,6 @@ allOf: contains: enum: - qcom,ipq6018-apcs-apps-global - - qcom,ipq8074-apcs-apps-global then: properties: '#clock-cells': -- GitLab From e17225887005f5cc6f18cb0fe9519849856b01b5 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 27 Mar 2023 16:07:49 +0200 Subject: [PATCH 4525/5631] mailbox: qcom-apcs-ipc: do not grow the of_device_id Re-organize the compatible devices and add a comment to avoid unneeded of_device_id growth with every new SoC. These devices have quite a lot of similarities and they can use only one compatible fallback for driver binding. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Jassi Brar --- drivers/mailbox/qcom-apcs-ipc-mailbox.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c index 6bbf87c6d60b..002a135ee868 100644 --- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c +++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c @@ -141,9 +141,7 @@ static int qcom_apcs_ipc_remove(struct platform_device *pdev) /* .data is the offset of the ipc register within the global block */ static const struct of_device_id qcom_apcs_ipc_of_match[] = { - { .compatible = "qcom,ipq5332-apcs-apps-global", .data = &ipq6018_apcs_data }, { .compatible = "qcom,ipq6018-apcs-apps-global", .data = &ipq6018_apcs_data }, - { .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq6018_apcs_data }, { .compatible = "qcom,msm8916-apcs-kpss-global", .data = &msm8916_apcs_data }, { .compatible = "qcom,msm8939-apcs-kpss-global", .data = &msm8916_apcs_data }, { .compatible = "qcom,msm8953-apcs-kpss-global", .data = &msm8994_apcs_data }, @@ -153,15 +151,18 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = { { .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,qcm2290-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,qcs404-apcs-apps-global", .data = &msm8916_apcs_data }, - { .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data }, - { .compatible = "qcom,sc8180x-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sdm660-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sm4250-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,sm6125-apcs-hmss-global", .data = &msm8994_apcs_data }, - { .compatible = "qcom,sm8150-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sm6115-apcs-hmss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data }, + /* Do not add any more entries using existing driver data */ + { .compatible = "qcom,ipq5332-apcs-apps-global", .data = &ipq6018_apcs_data }, + { .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq6018_apcs_data }, + { .compatible = "qcom,sc7180-apss-shared", .data = &apps_shared_apcs_data }, + { .compatible = "qcom,sc8180x-apss-shared", .data = &apps_shared_apcs_data }, + { .compatible = "qcom,sm8150-apss-shared", .data = &apps_shared_apcs_data }, {} }; MODULE_DEVICE_TABLE(of, qcom_apcs_ipc_of_match); -- GitLab From d396133dced4cbaa52581d0e9c4aea8e04b8db10 Mon Sep 17 00:00:00 2001 From: Devi Priya Date: Thu, 6 Apr 2023 11:43:12 +0530 Subject: [PATCH 4526/5631] dt-bindings: mailbox: qcom: add compatible for IPQ9574 SoC Add the mailbox compatible for IPQ9574 SoC. Acked-by: Krzysztof Kozlowski Signed-off-by: Devi Priya Signed-off-by: Jassi Brar --- .../devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index c466b5fe934d..4e15eb49e989 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -20,6 +20,7 @@ properties: - enum: - qcom,ipq5332-apcs-apps-global - qcom,ipq8074-apcs-apps-global + - qcom,ipq9574-apcs-apps-global - const: qcom,ipq6018-apcs-apps-global - items: - enum: -- GitLab From e7477cb97607b373d175a759c8c0270a640ab3f2 Mon Sep 17 00:00:00 2001 From: Caleb Harper Date: Wed, 3 May 2023 12:50:26 -0500 Subject: [PATCH 4527/5631] ALSA: hda/realtek: support HP Pavilion Aero 13-be0xxx Mute LED This patch adds support for the mute LED on the HP Pavilion Aero Laptop 13-be0xxx. The current behavior is that the LED does not turn on at any time and does not indicate to the user whether the sound is muted. The solution is to add a PCI quirk to properly recognize and support the LED on this device. This change has been tested on the device in question using modified versions of kernels 6.0.7-6.2.12 on Arch Linux. Signed-off-by: Caleb Harper Cc: Link: https://lore.kernel.org/r/20230503175026.6796-1-calebharp2005@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 509afa4e4da6..068ce0db9562 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9428,6 +9428,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), -- GitLab From 7501f472977df233d039d86c6981e0641708e1ca Mon Sep 17 00:00:00 2001 From: Geraldo Nascimento Date: Wed, 3 May 2023 18:02:06 -0300 Subject: [PATCH 4528/5631] ALSA: usb-audio: Add quirk for Pioneer DDJ-800 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit One more Pioneer quirk, this time for DDJ-800, which is quite similar like other DJ DDJ models but with slightly different EPs or channels. Signed-off-by: Geraldo Nascimento Tested-by: Grégory Desor Cc: Link: https://lore.kernel.org/r/ZFLLzgEcsSF5aIHG@geday Signed-off-by: Takashi Iwai --- sound/usb/quirks-table.h | 58 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 271884e35003..efb4a3311cc5 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3884,6 +3884,64 @@ YAMAHA_DEVICE(0x7010, "UB99"), } }, +{ + /* + * PIONEER DJ DDJ-800 + * PCM is 6 channels out, 6 channels in @ 44.1 fixed + * The Feedback for the output is the input + */ + USB_DEVICE_VENDOR_SPEC(0x2b73, 0x0029), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = (const struct snd_usb_audio_quirk[]) { + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 6, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .endpoint = 0x01, + .ep_attr = USB_ENDPOINT_XFER_ISOC| + USB_ENDPOINT_SYNC_ASYNC, + .rates = SNDRV_PCM_RATE_44100, + .rate_min = 44100, + .rate_max = 44100, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 44100 } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 6, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .endpoint = 0x82, + .ep_idx = 1, + .ep_attr = USB_ENDPOINT_XFER_ISOC| + USB_ENDPOINT_SYNC_ASYNC| + USB_ENDPOINT_USAGE_IMPLICIT_FB, + .rates = SNDRV_PCM_RATE_44100, + .rate_min = 44100, + .rate_max = 44100, + .nr_rates = 1, + .rate_table = (unsigned int[]) { 44100 } + } + }, + { + .ifnum = -1 + } + } + } +}, + /* * MacroSilicon MS2100/MS2106 based AV capture cards * -- GitLab From a26cc2934331b57b5a7164bff344f0a2ec245fc0 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 9 Mar 2023 22:39:09 -0800 Subject: [PATCH 4529/5631] drm/mipi-dsi: Set the fwnode for mipi_dsi_device After commit 3fb16866b51d ("driver core: fw_devlink: Make cycle detection more robust"), fw_devlink prints an error when consumer devices don't have their fwnode set. This used to be ignored silently. Set the fwnode mipi_dsi_device so fw_devlink can find them and properly track their dependencies. This fixes errors like this: [ 0.334054] nwl-dsi 30a00000.mipi-dsi: Failed to create device link with regulator-lcd-1v8 [ 0.346964] nwl-dsi 30a00000.mipi-dsi: Failed to create device link with backlight-dsi Reported-by: Martin Kepplinger Link: https://lore.kernel.org/lkml/2a8e407f4f18c9350f8629a2b5fa18673355b2ae.camel@puri.sm/ Fixes: 068a00233969 ("drm: Add MIPI DSI bus support") Signed-off-by: Saravana Kannan Tested-by: Martin Kepplinger Link: https://lore.kernel.org/r/20230310063910.2474472-1-saravanak@google.com Signed-off-by: Maxime Ripard --- drivers/gpu/drm/drm_mipi_dsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index b41aaf2bb9f1..7923cc21b78e 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -221,7 +221,7 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host, return dsi; } - dsi->dev.of_node = info->node; + device_set_node(&dsi->dev, of_fwnode_handle(info->node)); dsi->channel = info->channel; strlcpy(dsi->name, info->type, sizeof(dsi->name)); -- GitLab From 0d727e1856ef22dd9337199430258cb64cbbc658 Mon Sep 17 00:00:00 2001 From: Ruliang Lin Date: Thu, 4 May 2023 14:50:53 +0800 Subject: [PATCH 4530/5631] ALSA: caiaq: input: Add error handling for unsupported input methods in `snd_usb_caiaq_input_init` Smatch complains that: snd_usb_caiaq_input_init() warn: missing error code 'ret' This patch adds a new case to handle the situation where the device does not support any input methods in the `snd_usb_caiaq_input_init` function. It returns an `-EINVAL` error code to indicate that no input methods are supported on the device. Fixes: 523f1dce3743 ("[ALSA] Add Native Instrument usb audio device support") Signed-off-by: Ruliang Lin Reviewed-by: Dongliang Mu Acked-by: Daniel Mack Link: https://lore.kernel.org/r/20230504065054.3309-1-u202112092@hust.edu.cn Signed-off-by: Takashi Iwai --- sound/usb/caiaq/input.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index 1e2cf2f08eec..84f26dce7f5d 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -804,6 +804,7 @@ int snd_usb_caiaq_input_init(struct snd_usb_caiaqdev *cdev) default: /* no input methods supported on this device */ + ret = -EINVAL; goto exit_free_idev; } -- GitLab From 96c7d4f81db0fea05c0792f7563ae0cb4ad5f022 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 4 May 2023 05:18:54 -0700 Subject: [PATCH 4531/5631] io_uring: Create a helper to return the SQE size Create a simple helper that returns the size of the SQE. The SQE could have two size, depending of the flags. If IO_URING_SETUP_SQE128 flag is set, then return a double SQE, otherwise returns the sizeof of io_uring_sqe (64 bytes). Signed-off-by: Breno Leitao Reviewed-by: Christoph Hellwig Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20230504121856.904491-2-leitao@debian.org Signed-off-by: Jens Axboe --- io_uring/io_uring.h | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 25515d69d205..259bf798a390 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -394,4 +394,14 @@ static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res) io_req_task_work_add(req); } +/* + * IORING_SETUP_SQE128 contexts allocate twice the normal SQE size for each + * slot. + */ +static inline size_t uring_sqe_size(struct io_ring_ctx *ctx) +{ + if (ctx->flags & IORING_SETUP_SQE128) + return 2 * sizeof(struct io_uring_sqe); + return sizeof(struct io_uring_sqe); +} #endif -- GitLab From fd9b8547bc5c34186dc42ea05fb4380d21695374 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 4 May 2023 05:18:55 -0700 Subject: [PATCH 4532/5631] io_uring: Pass whole sqe to commands Currently uring CMD operation relies on having large SQEs, but future operations might want to use normal SQE. The io_uring_cmd currently only saves the payload (cmd) part of the SQE, but, for commands that use normal SQE size, it might be necessary to access the initial SQE fields outside of the payload/cmd block. So, saves the whole SQE other than just the pdu. This changes slightly how the io_uring_cmd works, since the cmd structures and callbacks are not opaque to io_uring anymore. I.e, the callbacks can look at the SQE entries, not only, in the cmd structure. The main advantage is that we don't need to create custom structures for simple commands. Creates io_uring_sqe_cmd() that returns the cmd private data as a null pointer and avoids casting in the callee side. Also, make most of ublk_drv's sqe->cmd priv structure into const, and use io_uring_sqe_cmd() to get the private structure, removing the unwanted cast. (There is one case where the cast is still needed since the header->{len,addr} is updated in the private structure) Suggested-by: Pavel Begunkov Signed-off-by: Breno Leitao Reviewed-by: Keith Busch Reviewed-by: Christoph Hellwig Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20230504121856.904491-3-leitao@debian.org Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 26 +++++++++++++------------- drivers/nvme/host/ioctl.c | 2 +- include/linux/io_uring.h | 7 ++++++- io_uring/opdef.c | 2 +- io_uring/uring_cmd.c | 9 +++------ 5 files changed, 24 insertions(+), 22 deletions(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c73cc57ec547..42f4d7ca962e 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1019,7 +1019,7 @@ static int ublk_ch_mmap(struct file *filp, struct vm_area_struct *vma) } static void ublk_commit_completion(struct ublk_device *ub, - struct ublksrv_io_cmd *ub_cmd) + const struct ublksrv_io_cmd *ub_cmd) { u32 qid = ub_cmd->q_id, tag = ub_cmd->tag; struct ublk_queue *ubq = ublk_get_queue(ub, qid); @@ -1263,7 +1263,7 @@ static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { - struct ublksrv_io_cmd *ub_cmd = (struct ublksrv_io_cmd *)cmd->cmd; + const struct ublksrv_io_cmd *ub_cmd = io_uring_sqe_cmd(cmd->sqe); struct ublk_device *ub = cmd->file->private_data; struct ublk_queue *ubq; struct ublk_io *io; @@ -1567,7 +1567,7 @@ static struct ublk_device *ublk_get_device_from_id(int idx) static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ublksrv_pid = (int)header->data[0]; struct gendisk *disk; int ret = -EINVAL; @@ -1630,7 +1630,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) static int ublk_ctrl_get_queue_affinity(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; cpumask_var_t cpumask; unsigned long queue; @@ -1681,7 +1681,7 @@ static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublksrv_ctrl_dev_info info; struct ublk_device *ub; @@ -1844,7 +1844,7 @@ static int ublk_ctrl_del_dev(struct ublk_device **p_ub) static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); pr_devel("%s: cmd_op %x, dev id %d qid %d data %llx buf %llx len %u\n", __func__, cmd->cmd_op, header->dev_id, header->queue_id, @@ -1863,7 +1863,7 @@ static int ublk_ctrl_stop_dev(struct ublk_device *ub) static int ublk_ctrl_get_dev_info(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr) @@ -1894,7 +1894,7 @@ static void ublk_ctrl_fill_params_devt(struct ublk_device *ub) static int ublk_ctrl_get_params(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; int ret; @@ -1925,7 +1925,7 @@ static int ublk_ctrl_get_params(struct ublk_device *ub, static int ublk_ctrl_set_params(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; int ret = -EFAULT; @@ -1983,7 +1983,7 @@ static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) static int ublk_ctrl_start_recovery(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ret = -EINVAL; int i; @@ -2025,7 +2025,7 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, static int ublk_ctrl_end_recovery(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ublksrv_pid = (int)header->data[0]; int ret = -EINVAL; @@ -2092,7 +2092,7 @@ static int ublk_char_dev_permission(struct ublk_device *ub, static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, struct io_uring_cmd *cmd) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)io_uring_sqe_cmd(cmd->sqe); bool unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV; void __user *argp = (void __user *)(unsigned long)header->addr; char *dev_path = NULL; @@ -2171,7 +2171,7 @@ static int ublk_ctrl_uring_cmd_permission(struct ublk_device *ub, static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) { - struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd; + const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); struct ublk_device *ub = NULL; int ret = -EINVAL; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index d24ea2e05156..81c5c9e38477 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -552,7 +552,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); - const struct nvme_uring_cmd *cmd = ioucmd->cmd; + const struct nvme_uring_cmd *cmd = io_uring_sqe_cmd(ioucmd->sqe); struct request_queue *q = ns ? ns->queue : ctrl->admin_q; struct nvme_uring_data d; struct nvme_command c; diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 35b9328ca335..3399d979ee1c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -24,7 +24,7 @@ enum io_uring_cmd_flags { struct io_uring_cmd { struct file *file; - const void *cmd; + const struct io_uring_sqe *sqe; union { /* callback to defer completions to task context */ void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); @@ -66,6 +66,11 @@ static inline void io_uring_free(struct task_struct *tsk) if (tsk->io_uring) __io_uring_free(tsk); } + +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) diff --git a/io_uring/opdef.c b/io_uring/opdef.c index cca7c5b55208..3b9c6489b8b6 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -627,7 +627,7 @@ const struct io_cold_def io_cold_defs[] = { }, [IORING_OP_URING_CMD] = { .name = "URING_CMD", - .async_size = uring_cmd_pdu_size(1), + .async_size = 2 * sizeof(struct io_uring_sqe), .prep_async = io_uring_cmd_prep_async, }, [IORING_OP_SEND_ZC] = { diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 5113c9a48583..ed536d7499db 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -69,15 +69,12 @@ EXPORT_SYMBOL_GPL(io_uring_cmd_done); int io_uring_cmd_prep_async(struct io_kiocb *req) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - size_t cmd_size; BUILD_BUG_ON(uring_cmd_pdu_size(0) != 16); BUILD_BUG_ON(uring_cmd_pdu_size(1) != 80); - cmd_size = uring_cmd_pdu_size(req->ctx->flags & IORING_SETUP_SQE128); - - memcpy(req->async_data, ioucmd->cmd, cmd_size); - ioucmd->cmd = req->async_data; + memcpy(req->async_data, ioucmd->sqe, uring_sqe_size(req->ctx)); + ioucmd->sqe = req->async_data; return 0; } @@ -103,7 +100,7 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = ctx->user_bufs[index]; io_req_set_rsrc_node(req, ctx, 0); } - ioucmd->cmd = sqe->cmd; + ioucmd->sqe = sqe; ioucmd->cmd_op = READ_ONCE(sqe->cmd_op); return 0; } -- GitLab From d2b7fa6174bc4260e496cbf84375c73636914641 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 4 May 2023 05:18:56 -0700 Subject: [PATCH 4533/5631] io_uring: Remove unnecessary BUILD_BUG_ON In the io_uring_cmd_prep_async() there is an unnecessary compilation time check to check if cmd is correctly placed at field 48 of the SQE. This is unnecessary, since this check is already in place at io_uring_init(): BUILD_BUG_SQE_ELEM(48, __u64, addr3); Remove it and the uring_cmd_pdu_size() function, which is not used anymore. Keith started a discussion about this topic in the following thread: Link: https://lore.kernel.org/lkml/ZDBmQOhbyU0iLhMw@kbusch-mbp.dhcp.thefacebook.com/ Signed-off-by: Breno Leitao Reviewed-by: Christoph Hellwig Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/20230504121856.904491-4-leitao@debian.org Signed-off-by: Jens Axboe --- io_uring/uring_cmd.c | 3 --- io_uring/uring_cmd.h | 8 -------- 2 files changed, 11 deletions(-) diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index ed536d7499db..5e32db48696d 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -70,9 +70,6 @@ int io_uring_cmd_prep_async(struct io_kiocb *req) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - BUILD_BUG_ON(uring_cmd_pdu_size(0) != 16); - BUILD_BUG_ON(uring_cmd_pdu_size(1) != 80); - memcpy(req->async_data, ioucmd->sqe, uring_sqe_size(req->ctx)); ioucmd->sqe = req->async_data; return 0; diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 7c6697d13cb2..8117684ec3ca 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -3,11 +3,3 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); int io_uring_cmd_prep_async(struct io_kiocb *req); - -/* - * The URING_CMD payload starts at 'cmd' in the first sqe, and continues into - * the following sqe if SQE128 is used. - */ -#define uring_cmd_pdu_size(is_sqe128) \ - ((1 + !!(is_sqe128)) * sizeof(struct io_uring_sqe) - \ - offsetof(struct io_uring_sqe, cmd)) -- GitLab From 292a7d6fca33df70ca4b8e9b0d0e74adf87582dc Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Fri, 21 Apr 2023 10:50:36 +0200 Subject: [PATCH 4534/5631] KVM: s390: pv: fix asynchronous teardown for small VMs On machines without the Destroy Secure Configuration Fast UVC, the topmost level of page tables is set aside and freed asynchronously as last step of the asynchronous teardown. Each gmap has a host_to_guest radix tree mapping host (userspace) addresses (with 1M granularity) to gmap segment table entries (pmds). If a guest is smaller than 2GB, the topmost level of page tables is the segment table (i.e. there are only 2 levels). Replacing it means that the pointers in the host_to_guest mapping would become stale and cause all kinds of nasty issues. This patch fixes the issue by disallowing asynchronous teardown for guests with only 2 levels of page tables. Userspace should (and already does) try using the normal destroy if the asynchronous one fails. Update s390_replace_asce so it refuses to replace segment type ASCEs. This is still needed in case the normal destroy VM fails. Fixes: fb491d5500a7 ("KVM: s390: pv: asynchronous destroy for reboot") Reviewed-by: Marc Hartmayer Reviewed-by: Janosch Frank Signed-off-by: Claudio Imbrenda Message-Id: <20230421085036.52511-2-imbrenda@linux.ibm.com> --- arch/s390/kvm/pv.c | 5 +++++ arch/s390/mm/gmap.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index e032ebbf51b9..3ce5f4351156 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -314,6 +314,11 @@ int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc) */ if (kvm->arch.pv.set_aside) return -EINVAL; + + /* Guest with segment type ASCE, refuse to destroy asynchronously */ + if ((kvm->arch.gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) + return -EINVAL; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 5a716bdcba05..2267cf9819b2 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -2833,6 +2833,9 @@ EXPORT_SYMBOL_GPL(s390_unlist_old_asce); * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy * @gmap: the gmap whose ASCE needs to be replaced * + * If the ASCE is a SEGMENT type then this function will return -EINVAL, + * otherwise the pointers in the host_to_guest radix tree will keep pointing + * to the wrong pages, causing use-after-free and memory corruption. * If the allocation of the new top level page table fails, the ASCE is not * replaced. * In any case, the old ASCE is always removed from the gmap CRST list. @@ -2847,6 +2850,10 @@ int s390_replace_asce(struct gmap *gmap) s390_unlist_old_asce(gmap); + /* Replacing segment type ASCEs would cause serious issues */ + if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) + return -EINVAL; + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return -ENOMEM; -- GitLab From c148dc8e2fa403be501612ee409db866eeed35c0 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Fri, 28 Apr 2023 11:27:53 +0200 Subject: [PATCH 4535/5631] KVM: s390: fix race in gmap_make_secure() Fix a potential race in gmap_make_secure() and remove the last user of follow_page() without FOLL_GET. The old code is locking something it doesn't have a reference to, and as explained by Jason and David in this discussion: https://lore.kernel.org/linux-mm/Y9J4P%2FRNvY1Ztn0Q@nvidia.com/ it can lead to all kind of bad things, including the page getting unmapped (MADV_DONTNEED), freed, reallocated as a larger folio and the unlock_page() would target the wrong bit. There is also another race with the FOLL_WRITE, which could race between the follow_page() and the get_locked_pte(). The main point is to remove the last use of follow_page() without FOLL_GET or FOLL_PIN, removing the races can be considered a nice bonus. Link: https://lore.kernel.org/linux-mm/Y9J4P%2FRNvY1Ztn0Q@nvidia.com/ Suggested-by: Jason Gunthorpe Fixes: 214d9bbcd3a6 ("s390/mm: provide memory management functions for protected KVM guests") Reviewed-by: Jason Gunthorpe Signed-off-by: Claudio Imbrenda Message-Id: <20230428092753.27913-2-imbrenda@linux.ibm.com> --- arch/s390/kernel/uv.c | 32 +++++++++++--------------------- 1 file changed, 11 insertions(+), 21 deletions(-) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 9f18a4af9c13..cb2ee06df286 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -192,21 +192,10 @@ static int expected_page_refs(struct page *page) return res; } -static int make_secure_pte(pte_t *ptep, unsigned long addr, - struct page *exp_page, struct uv_cb_header *uvcb) +static int make_page_secure(struct page *page, struct uv_cb_header *uvcb) { - pte_t entry = READ_ONCE(*ptep); - struct page *page; int expected, cc = 0; - if (!pte_present(entry)) - return -ENXIO; - if (pte_val(entry) & _PAGE_INVALID) - return -ENXIO; - - page = pte_page(entry); - if (page != exp_page) - return -ENXIO; if (PageWriteback(page)) return -EAGAIN; expected = expected_page_refs(page); @@ -304,17 +293,18 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) goto out; rc = -ENXIO; - page = follow_page(vma, uaddr, FOLL_WRITE); - if (IS_ERR_OR_NULL(page)) - goto out; - - lock_page(page); ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); - if (should_export_before_import(uvcb, gmap->mm)) - uv_convert_from_secure(page_to_phys(page)); - rc = make_secure_pte(ptep, uaddr, page, uvcb); + if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) { + page = pte_page(*ptep); + rc = -EAGAIN; + if (trylock_page(page)) { + if (should_export_before_import(uvcb, gmap->mm)) + uv_convert_from_secure(page_to_phys(page)); + rc = make_page_secure(page, uvcb); + unlock_page(page); + } + } pte_unmap_unlock(ptep, ptelock); - unlock_page(page); out: mmap_read_unlock(gmap->mm); -- GitLab From 714dd3c29a2241fb799586a5b03773103ca50fe5 Mon Sep 17 00:00:00 2001 From: Guillaume Ranquet Date: Fri, 14 Apr 2023 18:07:46 +0200 Subject: [PATCH 4536/5631] phy: mediatek: hdmi: mt8195: fix uninitialized variable usage in pll_calc The ret variable in mtk_hdmi_pll_calc() was used unitialized as reported by the kernel test robot. Fix the issue by removing the variable altogether and testing out the return value of mtk_hdmi_pll_set_hw() Fixes: 45810d486bb44 ("phy: mediatek: add support for phy-mtk-hdmi-mt8195") Reported-by: kernel test robot Signed-off-by: Guillaume Ranquet Reviewed-by: Nathan Chancellor Reviewed-by: AngeloGioacchino Del Regno Link: https://lore.kernel.org/r/20230413-fixes-for-mt8195-hdmi-phy-v2-1-bbad62e64321@baylibre.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index abfc077fb0a8..054b73cb31ee 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -213,7 +213,7 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, u64 tmds_clk, pixel_clk, da_hdmitx21_ref_ck, ns_hdmipll_ck, pcw; u8 txpredivs[4] = { 2, 4, 6, 12 }; u32 fbkdiv_low; - int i, ret; + int i; pixel_clk = rate; tmds_clk = pixel_clk; @@ -292,13 +292,9 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, if (!(digital_div <= 32 && digital_div >= 1)) return -EINVAL; - mtk_hdmi_pll_set_hw(hw, PLL_PREDIV, fbkdiv_high, fbkdiv_low, + return mtk_hdmi_pll_set_hw(hw, PLL_PREDIV, fbkdiv_high, fbkdiv_low, PLL_FBKDIV_HS3, posdiv1, posdiv2, txprediv, txposdiv, digital_div); - if (ret) - return -EINVAL; - - return 0; } static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) -- GitLab From 9d9ff3d2a4a567b543b71c2967d2ccc5e0ac6816 Mon Sep 17 00:00:00 2001 From: Guillaume Ranquet Date: Fri, 14 Apr 2023 18:07:47 +0200 Subject: [PATCH 4537/5631] phy: mediatek: hdmi: mt8195: fix wrong pll calculus The clock rate calculus in mtk_hdmi_pll_calc() was wrong when it has been replaced by 'div_u64'. Fix the issue by multiplying the values in the denominator instead of dividing them. Fixes: 45810d486bb44 ("phy: mediatek: add support for phy-mtk-hdmi-mt8195") Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Guillaume Ranquet Link: https://lore.kernel.org/r/20230413-fixes-for-mt8195-hdmi-phy-v2-2-bbad62e64321@baylibre.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index 054b73cb31ee..caa953780bee 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -271,7 +271,7 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, * [32,24] 9bit integer, [23,0]:24bit fraction */ pcw = div_u64(((u64)ns_hdmipll_ck) << PCW_DECIMAL_WIDTH, - da_hdmitx21_ref_ck / PLL_FBKDIV_HS3); + da_hdmitx21_ref_ck * PLL_FBKDIV_HS3); if (pcw > GENMASK_ULL(32, 0)) return -EINVAL; @@ -288,7 +288,7 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, posdiv2 = 1; /* Digital clk divider, max /32 */ - digital_div = div_u64((u64)ns_hdmipll_ck, posdiv1 / posdiv2 / pixel_clk); + digital_div = div_u64(ns_hdmipll_ck, posdiv1 * posdiv2 * pixel_clk); if (!(digital_div <= 32 && digital_div >= 1)) return -EINVAL; -- GitLab From 3db66620ea90b0fd4134b31eabfec16d7b07d7e3 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 28 Apr 2023 15:23:50 +0200 Subject: [PATCH 4538/5631] ACPI: video: Remove acpi_backlight=video quirk for Lenovo ThinkPad W530 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove the acpi_backlight=video quirk for Lenovo ThinkPad W530. This was intended to help users of the (unsupported) Nvidia binary driver, but this has been reported to cause backlight control issues for users who have the gfx configured in hybrid (dual-GPU) mode, so drop this. The Nvidia binary driver should call acpi_video_register_backlight() when necessary and this has been reported to Nvidia. Until this is fixed Nvidia binary driver users can work around this by passing "acpi_backlight=video" on the kernel commandline (with the latest 6.1.y or newer stable series, kernels < 6.1.y don't need this). Fixes: a5b2781dcab2 ("ACPI: video: Add acpi_backlight=video quirk for Lenovo ThinkPad W530") Reported-by: Русев Путин Link: https://lore.kernel.org/linux-acpi/CAK4BXn0ngZRmzx1bodAF8nmYj0PWdUXzPGHofRrsyZj8MBpcVA@mail.gmail.com/ Cc: 6.1+ # 6.1+ Signed-off-by: Hans de Goede Signed-off-by: Rafael J. Wysocki --- drivers/acpi/video_detect.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 69ef2d9710c2..bcc25d457581 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -293,20 +293,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, - /* - * Older models with nvidia GPU which need acpi_video backlight - * control and where the old nvidia binary driver series does not - * call acpi_video_register_backlight(). - */ - { - .callback = video_detect_force_video, - /* ThinkPad W530 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W530"), - }, - }, - /* * These models have a working acpi_video backlight control, and using * native backlight causes a regression where backlight does not work -- GitLab From b5d68f84f4c62c78bc3d004911d80da5aa22df8b Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 3 May 2023 16:38:50 -0700 Subject: [PATCH 4539/5631] thermal: intel: powerclamp: Fix NULL pointer access issue If cur_state for the powerclamp cooling device is set to the default minimum state of 0, without setting first to cur_state > 0, this results in NULL pointer access. This NULL pointer access happens in the powercap core idle-inject function idle_inject_set_duration() as there is no NULL check for idle_inject_device pointer. This pointer must be allocated by calling idle_inject_register() or idle_inject_register_full(). In the function powerclamp_set_cur_state(), idle_inject_device pointer is allocated only when the cur_state > 0. But setting 0 without changing to any other state, idle_inject_set_duration() will be called with a NULL idle_inject_device pointer. To address this, just return from powerclamp_set_cur_state() if the current cooling device state is the same as the last one. Since the power-up default cooling device state is 0, changing the state to 0 again here will return without calling idle_inject_set_duration(). Signed-off-by: Srinivas Pandruvada Fixes: 8526eb7fc75a ("thermal: intel: powerclamp: Use powercap idle-inject feature") Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=217386 Tested-by: Risto A. Paju Cc: 6.3+ # 6.3+ Signed-off-by: Rafael J. Wysocki --- drivers/thermal/intel/intel_powerclamp.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index 91fc7e239497..36243a3972fd 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -703,6 +703,10 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev, new_target_ratio = clamp(new_target_ratio, 0UL, (unsigned long) (max_idle - 1)); + + if (powerclamp_data.target_ratio == new_target_ratio) + goto exit_set; + if (!powerclamp_data.target_ratio && new_target_ratio > 0) { pr_info("Start idle injection to reduce power\n"); powerclamp_data.target_ratio = new_target_ratio; -- GitLab From 37f225ecc2e06e21276700b42f682b0f2fe565e4 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Wed, 3 May 2023 10:40:55 +0200 Subject: [PATCH 4540/5631] dt-bindings: xilinx: Remove Naga from memory and mtd bindings Naga is no longer works for AMD/Xilinx and there is no activity from him to continue to maintain Xilinx related drivers. Two drivers have Miquel as maintainer and for the last one add myself instead to be kept in a loop if there is any change required. Signed-off-by: Michal Simek Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/6b4cdc7158599b4a38409a03eda56e38975b6233.1683103250.git.michal.simek@amd.com Signed-off-by: Rob Herring --- .../devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml | 1 - .../devicetree/bindings/mtd/arasan,nand-controller.yaml | 2 +- Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml | 1 - 3 files changed, 1 insertion(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml b/Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml index 6d3962a17e49..05dd6b3a1a3c 100644 --- a/Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml +++ b/Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml @@ -8,7 +8,6 @@ title: Arm PL35x Series Static Memory Controller (SMC) maintainers: - Miquel Raynal - - Naga Sureshkumar Relli description: | The PL35x Static Memory Controller is a bus where you can connect two kinds diff --git a/Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml b/Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml index d028269cdbaa..3050575566be 100644 --- a/Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml +++ b/Documentation/devicetree/bindings/mtd/arasan,nand-controller.yaml @@ -10,7 +10,7 @@ allOf: - $ref: "nand-controller.yaml" maintainers: - - Naga Sureshkumar Relli + - Michal Simek properties: compatible: diff --git a/Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml b/Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml index e552875040e2..859673ada10e 100644 --- a/Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml +++ b/Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml @@ -11,7 +11,6 @@ allOf: maintainers: - Miquel Raynal - - Naga Sureshkumar Relli properties: compatible: -- GitLab From d7385ba137711ea71527a605cac162610a621de8 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Thu, 4 May 2023 15:47:23 -0400 Subject: [PATCH 4541/5631] 9p: Remove INET dependency 9pfs can run over assorted transports, so it doesn't have an INET dependency. Drop it and remove the includes of linux/inet.h. NET_9P_FD/trans_fd.o builds without INET or UNIX and is usable over plain file descriptors. However, tcp and unix functionality is still built and would generate runtime failures if used. Add imply INET and UNIX to NET_9P_FD, so functionality is enabled by default but can still be explicitly disabled. This allows configuring 9pfs over Xen with INET and UNIX disabled. Signed-off-by: Jason Andryuk Signed-off-by: David S. Miller --- fs/9p/Kconfig | 2 +- fs/9p/vfs_addr.c | 1 - fs/9p/vfs_dentry.c | 1 - fs/9p/vfs_dir.c | 1 - fs/9p/vfs_file.c | 1 - fs/9p/vfs_inode.c | 1 - fs/9p/vfs_inode_dotl.c | 1 - fs/9p/vfs_super.c | 1 - net/9p/Kconfig | 2 ++ 9 files changed, 3 insertions(+), 8 deletions(-) diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig index d7bc93447c85..0c63df574ee7 100644 --- a/fs/9p/Kconfig +++ b/fs/9p/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config 9P_FS tristate "Plan 9 Resource Sharing Support (9P2000)" - depends on INET && NET_9P + depends on NET_9P select NETFS_SUPPORT help If you say Y here, you will get experimental support for diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 6f46d7e4c750..425956eb9fde 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 65fa2df5e49b..f16f73581634 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 3d74b04fe0de..52bf87934650 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 44c15eb2b908..367a851eaa82 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 1d523bec0a94..502ac74e4959 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 331ed60d8fcb..a7da49906d99 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 266c4693e20c..10449994a972 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/net/9p/Kconfig b/net/9p/Kconfig index deabbd376cb1..00ebce9e5a65 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -17,6 +17,8 @@ if NET_9P config NET_9P_FD default NET_9P + imply INET + imply UNIX tristate "9P FD Transport" help This builds support for transports over TCP, Unix sockets and -- GitLab From 8e3554150d6c80a84b3cb046615d1a0e943811dc Mon Sep 17 00:00:00 2001 From: Paulo Alcantara Date: Sun, 23 Apr 2023 23:26:51 -0300 Subject: [PATCH 4542/5631] cifs: fix sharing of DFS connections When matching DFS connections, we can't rely on the values set in cifs_sb_info::prepath and cifs_tcon::tree_name as they might change during DFS failover. The DFS referrals related to a specific DFS tcon are already matched earlier in match_server(), therefore we can safely skip those checks altogether as the connection is guaranteed to be unique for the DFS tcon. Besides, when creating or finding an SMB session, make sure to also refcount any DFS root session related to it (cifs_ses::dfs_root_ses), so if a new DFS mount ends up reusing the connection from the old mount while there was an umount(2) still in progress (e.g. umount(2) -> cifs_umount() -> reconnect -> cifs_put_tcon()), the connection could potentially be put right after the umount(2) finished. Patch has minor update to include fix for unused variable issue noted by the kernel test robot Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202305041040.j7W2xQSy-lkp@intel.com/ Cc: stable@vger.kernel.org # v6.2+ Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 1 - fs/cifs/cifsproto.h | 44 ++++++++++++++++- fs/cifs/connect.c | 114 ++++++++++++++++++++++---------------------- fs/cifs/dfs.c | 62 ++++++++++++++++-------- fs/cifs/ioctl.c | 2 +- fs/cifs/smb2pdu.c | 4 +- 6 files changed, 147 insertions(+), 80 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 9c5cd332ce14..414685c5d530 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1756,7 +1756,6 @@ struct cifs_mount_ctx { struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; - char *origin_fullpath, *leaf_fullpath; struct list_head dfs_ses_list; }; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index e2eff66eefab..c1c704990b98 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -8,6 +8,7 @@ #ifndef _CIFSPROTO_H #define _CIFSPROTO_H #include +#include #include "trace.h" #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" @@ -572,7 +573,7 @@ extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb3_fs_context *ctx); -extern void cifs_put_smb_ses(struct cifs_ses *ses); +void __cifs_put_smb_ses(struct cifs_ses *ses); extern struct cifs_ses * cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx); @@ -696,4 +697,45 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon); void cifs_put_tcon_super(struct super_block *sb); int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry); +/* Put references of @ses and @ses->dfs_root_ses */ +static inline void cifs_put_smb_ses(struct cifs_ses *ses) +{ + struct cifs_ses *rses = ses->dfs_root_ses; + + __cifs_put_smb_ses(ses); + if (rses) + __cifs_put_smb_ses(rses); +} + +/* Get an active reference of @ses and @ses->dfs_root_ses. + * + * NOTE: make sure to call this function when incrementing reference count of + * @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses) + * will also get its reference count incremented. + * + * cifs_put_smb_ses() will put both references, so call it when you're done. + */ +static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses) +{ + lockdep_assert_held(&cifs_tcp_ses_lock); + + ses->ses_count++; + if (ses->dfs_root_ses) + ses->dfs_root_ses->ses_count++; +} + +static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) +{ + if (strlen(s1) != strlen(s2)) + return false; + for (; *s1; s1++, s2++) { + if (*s1 == '/' || *s1 == '\\') { + if (*s2 != '/' && *s2 != '\\') + return false; + } else if (tolower(*s1) != tolower(*s2)) + return false; + } + return true; +} + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9a730efbce32..eeeed6fda13b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -996,10 +996,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) */ } -#ifdef CONFIG_CIFS_DFS_UPCALL kfree(server->origin_fullpath); kfree(server->leaf_fullpath); -#endif kfree(server); length = atomic_dec_return(&tcpSesAllocCount); @@ -1387,23 +1385,8 @@ match_security(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) return true; } -static bool dfs_src_pathname_equal(const char *s1, const char *s2) -{ - if (strlen(s1) != strlen(s2)) - return false; - for (; *s1; s1++, s2++) { - if (*s1 == '/' || *s1 == '\\') { - if (*s2 != '/' && *s2 != '\\') - return false; - } else if (tolower(*s1) != tolower(*s2)) - return false; - } - return true; -} - /* this function must be called with srv_lock held */ -static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context *ctx, - bool dfs_super_cmp) +static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; @@ -1434,27 +1417,41 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * (struct sockaddr *)&server->srcaddr)) return 0; /* - * When matching DFS superblocks, we only check for original source pathname as the - * currently connected target might be different than the one parsed earlier in i.e. - * mount.cifs(8). + * - Match for an DFS tcon (@server->origin_fullpath). + * - Match for an DFS root server connection (@server->leaf_fullpath). + * - If none of the above and @ctx->leaf_fullpath is set, then + * it is a new DFS connection. + * - If 'nodfs' mount option was passed, then match only connections + * that have no DFS referrals set + * (e.g. can't failover to other targets). */ - if (dfs_super_cmp) { - if (!ctx->source || !server->origin_fullpath || - !dfs_src_pathname_equal(server->origin_fullpath, ctx->source)) - return 0; - } else { - /* Skip addr, hostname and port matching for DFS connections */ - if (server->leaf_fullpath) { + if (!ctx->nodfs) { + if (ctx->source && server->origin_fullpath) { + if (!dfs_src_pathname_equal(ctx->source, + server->origin_fullpath)) + return 0; + } else if (server->leaf_fullpath) { if (!ctx->leaf_fullpath || - strcasecmp(server->leaf_fullpath, ctx->leaf_fullpath)) + strcasecmp(server->leaf_fullpath, + ctx->leaf_fullpath)) return 0; - } else if (strcasecmp(server->hostname, ctx->server_hostname) || - !match_server_address(server, addr) || - !match_port(server, addr)) { + } else if (ctx->leaf_fullpath) { return 0; } + } else if (server->origin_fullpath || server->leaf_fullpath) { + return 0; } + /* + * Match for a regular connection (address/hostname/port) which has no + * DFS referrals set. + */ + if (!server->origin_fullpath && !server->leaf_fullpath && + (strcasecmp(server->hostname, ctx->server_hostname) || + !match_server_address(server, addr) || + !match_port(server, addr))) + return 0; + if (!match_security(server, ctx)) return 0; @@ -1485,7 +1482,7 @@ cifs_find_tcp_session(struct smb3_fs_context *ctx) * Skip ses channels since they're only handled in lower layers * (e.g. cifs_send_recv). */ - if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx, false)) { + if (CIFS_SERVER_IS_CHAN(server) || !match_server(server, ctx)) { spin_unlock(&server->srv_lock); continue; } @@ -1869,7 +1866,7 @@ cifs_free_ipc(struct cifs_ses *ses) static struct cifs_ses * cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { - struct cifs_ses *ses; + struct cifs_ses *ses, *ret = NULL; spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { @@ -1879,23 +1876,22 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) continue; } spin_lock(&ses->chan_lock); - if (!match_session(ses, ctx)) { + if (match_session(ses, ctx)) { spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); - continue; + ret = ses; + break; } spin_unlock(&ses->chan_lock); spin_unlock(&ses->ses_lock); - - ++ses->ses_count; - spin_unlock(&cifs_tcp_ses_lock); - return ses; } + if (ret) + cifs_smb_ses_inc_refcount(ret); spin_unlock(&cifs_tcp_ses_lock); - return NULL; + return ret; } -void cifs_put_smb_ses(struct cifs_ses *ses) +void __cifs_put_smb_ses(struct cifs_ses *ses) { unsigned int rc, xid; unsigned int chan_count; @@ -2250,6 +2246,8 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) */ spin_lock(&cifs_tcp_ses_lock); ses->dfs_root_ses = ctx->dfs_root_ses; + if (ses->dfs_root_ses) + ses->dfs_root_ses->ses_count++; list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -2266,12 +2264,15 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) } /* this function must be called with tc_lock held */ -static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx, bool dfs_super_cmp) +static int match_tcon(struct cifs_tcon *tcon, struct smb3_fs_context *ctx) { + struct TCP_Server_Info *server = tcon->ses->server; + if (tcon->status == TID_EXITING) return 0; - /* Skip UNC validation when matching DFS superblocks */ - if (!dfs_super_cmp && strncmp(tcon->tree_name, ctx->UNC, MAX_TREE_SIZE)) + /* Skip UNC validation when matching DFS connections or superblocks */ + if (!server->origin_fullpath && !server->leaf_fullpath && + strncmp(tcon->tree_name, ctx->UNC, MAX_TREE_SIZE)) return 0; if (tcon->seal != ctx->seal) return 0; @@ -2294,7 +2295,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->tc_lock); - if (!match_tcon(tcon, ctx, false)) { + if (!match_tcon(tcon, ctx)) { spin_unlock(&tcon->tc_lock); continue; } @@ -2670,9 +2671,11 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) return 1; } -static int -match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data) +static int match_prepath(struct super_block *sb, + struct TCP_Server_Info *server, + struct cifs_mnt_data *mnt_data) { + struct smb3_fs_context *ctx = mnt_data->ctx; struct cifs_sb_info *old = CIFS_SB(sb); struct cifs_sb_info *new = mnt_data->cifs_sb; bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && @@ -2680,6 +2683,10 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data) bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && new->prepath; + if (server->origin_fullpath && + dfs_src_pathname_equal(server->origin_fullpath, ctx->source)) + return 1; + if (old_set && new_set && !strcmp(new->prepath, old->prepath)) return 1; else if (!old_set && !new_set) @@ -2698,7 +2705,6 @@ cifs_match_super(struct super_block *sb, void *data) struct cifs_ses *ses; struct cifs_tcon *tcon; struct tcon_link *tlink; - bool dfs_super_cmp; int rc = 0; spin_lock(&cifs_tcp_ses_lock); @@ -2713,18 +2719,16 @@ cifs_match_super(struct super_block *sb, void *data) ses = tcon->ses; tcp_srv = ses->server; - dfs_super_cmp = IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) && tcp_srv->origin_fullpath; - ctx = mnt_data->ctx; spin_lock(&tcp_srv->srv_lock); spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); spin_lock(&tcon->tc_lock); - if (!match_server(tcp_srv, ctx, dfs_super_cmp) || + if (!match_server(tcp_srv, ctx) || !match_session(ses, ctx) || - !match_tcon(tcon, ctx, dfs_super_cmp) || - !match_prepath(sb, mnt_data)) { + !match_tcon(tcon, ctx) || + !match_prepath(sb, tcp_srv, mnt_data)) { rc = 0; goto out; } @@ -3469,8 +3473,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) error: dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list); - kfree(mnt_ctx.origin_fullpath); - kfree(mnt_ctx.leaf_fullpath); cifs_mount_put_conns(&mnt_ctx); return rc; } diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c index da4e083b1ab4..a93dbca1411b 100644 --- a/fs/cifs/dfs.c +++ b/fs/cifs/dfs.c @@ -99,7 +99,7 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) return rc; } -static int get_root_smb_session(struct cifs_mount_ctx *mnt_ctx) +static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct dfs_root_ses *root_ses; @@ -127,7 +127,7 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; struct dfs_info3_param ref = {}; - bool is_refsrv = false; + bool is_refsrv; int rc, rc2; rc = dfs_cache_get_tgt_referral(ref_path + 1, tit, &ref); @@ -160,7 +160,7 @@ static int get_dfs_conn(struct cifs_mount_ctx *mnt_ctx, const char *ref_path, co dfs_cache_noreq_update_tgthint(ref_path + 1, tit); if (rc == -EREMOTE && is_refsrv) { - rc2 = get_root_smb_session(mnt_ctx); + rc2 = add_root_smb_session(mnt_ctx); if (rc2) rc = rc2; } @@ -277,15 +277,21 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) { - struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; + struct cifs_ses *ses; + char *source = ctx->source; + bool nodfs = ctx->nodfs; int rc; *isdfs = false; - + /* Temporarily set @ctx->source to NULL as we're not matching DFS + * superblocks yet. See cifs_match_super() and match_server(). + */ + ctx->source = NULL; rc = get_session(mnt_ctx, NULL); if (rc) - return rc; + goto out; + ctx->dfs_root_ses = mnt_ctx->ses; /* * If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally @@ -294,23 +300,41 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) * Skip prefix path to provide support for DFS referrals from w2k8 servers which don't seem * to respond with PATH_NOT_COVERED to requests that include the prefix. */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || - dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL)) { + if (!nodfs) { + rc = dfs_get_referral(mnt_ctx, ctx->UNC + 1, NULL, NULL); + if (rc) { + if (rc != -ENOENT && rc != -EOPNOTSUPP) + goto out; + nodfs = true; + } + } + if (nodfs) { rc = cifs_mount_get_tcon(mnt_ctx); - if (rc) - return rc; - - rc = cifs_is_path_remote(mnt_ctx); - if (!rc || rc != -EREMOTE) - return rc; + if (!rc) + rc = cifs_is_path_remote(mnt_ctx); + goto out; } *isdfs = true; - rc = get_root_smb_session(mnt_ctx); - if (rc) - return rc; - - return __dfs_mount_share(mnt_ctx); + /* + * Prevent DFS root session of being put in the first call to + * cifs_mount_put_conns(). If another DFS root server was not found + * while chasing the referrals (@ctx->dfs_root_ses == @ses), then we + * can safely put extra refcount of @ses. + */ + ses = mnt_ctx->ses; + mnt_ctx->ses = NULL; + mnt_ctx->server = NULL; + rc = __dfs_mount_share(mnt_ctx); + if (ses == ctx->dfs_root_ses) + cifs_put_smb_ses(ses); +out: + /* + * Restore previous value of @ctx->source so DFS superblock can be + * matched in cifs_match_super(). + */ + ctx->source = source; + return rc; } /* Update dfs referral path of superblock */ diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 6419ec47c2a8..cb3be58cd55e 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -239,7 +239,7 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * section, we need to make sure it won't be released * so increment its refcount */ - ses->ses_count++; + cifs_smb_ses_inc_refcount(ses); found = true; goto search_end; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 3ce63f0cd9f5..8e7c15e2fd91 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3801,7 +3801,7 @@ void smb2_reconnect_server(struct work_struct *work) if (ses->tcon_ipc && ses->tcon_ipc->need_reconnect) { list_add_tail(&ses->tcon_ipc->rlist, &tmp_list); tcon_selected = tcon_exist = true; - ses->ses_count++; + cifs_smb_ses_inc_refcount(ses); } /* * handle the case where channel needs to reconnect @@ -3812,7 +3812,7 @@ void smb2_reconnect_server(struct work_struct *work) if (!tcon_selected && cifs_chan_needs_reconnect(ses, server)) { list_add_tail(&ses->rlist, &tmp_ses_list); ses_exist = true; - ses->ses_count++; + cifs_smb_ses_inc_refcount(ses); } spin_unlock(&ses->chan_lock); } -- GitLab From 4d276e4d3bb4a503e75086faab54f92c0a8fd368 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 4 Apr 2023 19:03:22 +0100 Subject: [PATCH 4543/5631] dt-bindings: perf: riscv,pmu: fix property dependencies Seemingly I mis-implemented the dependencies here. The OpenSBI docs only point out that the "riscv,event-to-mhpmcounters property is mandatory if riscv,event-to-mhpmevent is present". It never claims that riscv,event-to-mhpmcounters requires riscv,event-to-mhpmevent. Drop the dependency of riscv,event-to-mhpmcounters on riscv,event-to-mhpmevent. Fixes: 7e38085d9c59 ("dt-bindings: riscv: add SBI PMU event mappings") Signed-off-by: Conor Dooley Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20230404-tractor-confusing-8852e552539a@spud Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/perf/riscv,pmu.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml index a55a4d047d3f..c8448de2f2a0 100644 --- a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml +++ b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml @@ -91,7 +91,6 @@ properties: dependencies: "riscv,event-to-mhpmevent": [ "riscv,event-to-mhpmcounters" ] - "riscv,event-to-mhpmcounters": [ "riscv,event-to-mhpmevent" ] required: - compatible -- GitLab From 37c218d8021e36e226add4bab93d071d30fe0704 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Wed, 3 May 2023 00:09:46 +0300 Subject: [PATCH 4544/5631] net: dsa: mt7530: fix corrupt frames using trgmii on 40 MHz XTAL MT7621 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The multi-chip module MT7530 switch with a 40 MHz oscillator on the MT7621AT, MT7621DAT, and MT7621ST SoCs forwards corrupt frames using trgmii. This is caused by the assumption that MT7621 SoCs have got 150 MHz PLL, hence using the ncpo1 value, 0x0780. My testing shows this value works on Unielec U7621-06, Bartel's testing shows it won't work on Hi-Link HLK-MT7621A and Netgear WAC104. All devices tested have got 40 MHz oscillators. Using the value for 125 MHz PLL, 0x0640, works on all boards at hand. The definitions for 125 MHz PLL exist on the Banana Pi BPI-R2 BSP source code whilst 150 MHz PLL don't. Forwarding frames using trgmii on the MCM MT7530 switch with a 25 MHz oscillator on the said MT7621 SoCs works fine because the ncpo1 value defined for it is for 125 MHz PLL. Change the 150 MHz PLL comment to 125 MHz PLL, and use the 125 MHz PLL ncpo1 values for both oscillator frequencies. Link: https://github.com/BPI-SINOVOIP/BPI-R2-bsp/blob/81d24bbce7d99524d0771a8bdb2d6663e4eb4faa/u-boot-mt/drivers/net/rt2880_eth.c#L2195 Fixes: 7ef6f6f8d237 ("net: dsa: mt7530: Add MT7621 TRGMII mode support") Tested-by: Bartel Eerdekens Signed-off-by: Arınç ÜNAL Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index c680873819b0..7d9f9563dbda 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -426,9 +426,9 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) else ssc_delta = 0x87; if (priv->id == ID_MT7621) { - /* PLL frequency: 150MHz: 1.2GBit */ + /* PLL frequency: 125MHz: 1.0GBit */ if (xtal == HWTRAP_XTAL_40MHZ) - ncpo1 = 0x0780; + ncpo1 = 0x0640; if (xtal == HWTRAP_XTAL_25MHZ) ncpo1 = 0x0a00; } else { /* PLL frequency: 250MHz: 2.0Gbit */ -- GitLab From 120a56b01beed51ab5956a734adcfd2760307107 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ar=C4=B1n=C3=A7=20=C3=9CNAL?= Date: Wed, 3 May 2023 00:09:47 +0300 Subject: [PATCH 4545/5631] net: dsa: mt7530: fix network connectivity with multiple CPU ports MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On mt753x_cpu_port_enable() there's code that enables flooding for the CPU port only. Since mt753x_cpu_port_enable() runs twice when both CPU ports are enabled, port 6 becomes the only port to forward the frames to. But port 5 is the active port, so no frames received from the user ports will be forwarded to port 5 which breaks network connectivity. Every bit of the BC_FFP, UNM_FFP, and UNU_FFP bits represents a port. Fix this issue by setting the bit that corresponds to the CPU port without overwriting the other bits. Clear the bits beforehand only for the MT7531 switch. According to the documents MT7621 Giga Switch Programming Guide v0.3 and MT7531 Reference Manual for Development Board v1.0, after reset, the BC_FFP, UNM_FFP, and UNU_FFP bits are set to 1 for MT7531, 0 for MT7530. The commit 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") silently changed the method to set the bits on the MT7530_MFC. Instead of clearing the relevant bits before mt7530_cpu_port_enable() which runs under a for loop, the commit started doing it on mt7530_cpu_port_enable(). Back then, this didn't really matter as only a single CPU port could be used since the CPU port number was hardcoded. The driver was later changed with commit 1f9a6abecf53 ("net: dsa: mt7530: get cpu-port via dp->cpu_dp instead of constant") to retrieve the CPU port via dp->cpu_dp. With that, this silent change became an issue for when using multiple CPU ports. Fixes: 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") Signed-off-by: Arınç ÜNAL Signed-off-by: David S. Miller --- drivers/net/dsa/mt7530.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 7d9f9563dbda..9bc54e1348cb 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1002,9 +1002,9 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) mt7530_write(priv, MT7530_PVC_P(port), PORT_SPEC_TAG); - /* Disable flooding by default */ - mt7530_rmw(priv, MT7530_MFC, BC_FFP_MASK | UNM_FFP_MASK | UNU_FFP_MASK, - BC_FFP(BIT(port)) | UNM_FFP(BIT(port)) | UNU_FFP(BIT(port))); + /* Enable flooding on the CPU port */ + mt7530_set(priv, MT7530_MFC, BC_FFP(BIT(port)) | UNM_FFP(BIT(port)) | + UNU_FFP(BIT(port))); /* Set CPU port number */ if (priv->id == ID_MT7621) @@ -2367,6 +2367,10 @@ mt7531_setup_common(struct dsa_switch *ds) /* Enable and reset MIB counters */ mt7530_mib_reset(ds); + /* Disable flooding on all ports */ + mt7530_clear(priv, MT7530_MFC, BC_FFP_MASK | UNM_FFP_MASK | + UNU_FFP_MASK); + for (i = 0; i < MT7530_NUM_PORTS; i++) { /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, -- GitLab From 9f699b71c2f31c51bd1483a20e1c8ddc5986a8c9 Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Wed, 3 May 2023 08:39:35 -0700 Subject: [PATCH 4546/5631] ice: block LAN in case of VF to VF offload VF to VF traffic shouldn't go outside. To enforce it, set only the loopback enable bit in case of all ingress type rules added via the tc tool. Fixes: 0d08a441fb1a ("ice: ndo_setup_tc implementation for PF") Reported-by: Sujai Buvaneswaran Signed-off-by: Michal Swiatkowski Tested-by: George Kuruvinakunnel Reviewed-by: Simon Horman Signed-off-by: Tony Nguyen Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice_tc_lib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 76f29a5bf8d7..d1a31f236d26 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -693,17 +693,18 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) * results into order of switch rule evaluation. */ rule_info.priority = 7; + rule_info.flags_info.act_valid = true; if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; rule_info.rx = true; + rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } else { rule_info.sw_act.flag |= ICE_FLTR_TX; rule_info.sw_act.src = vsi->idx; rule_info.rx = false; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; - rule_info.flags_info.act_valid = true; } /* specify the cookie as filter_rule_id */ -- GitLab From f8bb5104394560e29017c25bcade4c6b7aabd108 Mon Sep 17 00:00:00 2001 From: Wenliang Wang Date: Thu, 4 May 2023 10:27:06 +0800 Subject: [PATCH 4547/5631] virtio_net: suppress cpu stall when free_unused_bufs For multi-queue and large ring-size use case, the following error occurred when free_unused_bufs: rcu: INFO: rcu_sched self-detected stall on CPU. Fixes: 986a4f4d452d ("virtio_net: multiqueue support") Signed-off-by: Wenliang Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 8d8038538fc4..a12ae26db0e2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3560,12 +3560,14 @@ static void free_unused_bufs(struct virtnet_info *vi) struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); + cond_resched(); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_rq_free_unused_buf(vq, buf); + cond_resched(); } } -- GitLab From c00ce5470a8adeaf681865836085f72633c00a7e Mon Sep 17 00:00:00 2001 From: Martin Habets Date: Thu, 4 May 2023 08:28:01 +0100 Subject: [PATCH 4548/5631] sfc: Add back mailing list We used to have a mailing list in the MAINTAINERS file, but removed this when we became part of Xilinx as it stopped working. Now inside AMD we have the list again. Add it back so patches will be seen by all sfc developers. Signed-off-by: Martin Habets Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index ebd26b3ca90e..dcab6b41ad8d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18987,6 +18987,7 @@ SFC NETWORK DRIVER M: Edward Cree M: Martin Habets L: netdev@vger.kernel.org +L: linux-net-drivers@amd.com S: Supported F: Documentation/networking/devlink/sfc.rst F: drivers/net/ethernet/sfc/ -- GitLab From 299efdc2380aac588557f4d0b2ce7bee05bd0cf2 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Thu, 4 May 2023 16:03:59 +0800 Subject: [PATCH 4549/5631] net: enetc: check the index of the SFI rather than the handle We should check whether the current SFI (Stream Filter Instance) table is full before creating a new SFI entry. However, the previous logic checks the handle by mistake and might lead to unpredictable behavior. Fixes: 888ae5a3952b ("net: enetc: add tc flower psfp offload driver") Signed-off-by: Wei Fang Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc_qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index 130ebf6853e6..83c27bbbc6ed 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -1247,7 +1247,7 @@ static int enetc_psfp_parse_clsflower(struct enetc_ndev_priv *priv, int index; index = enetc_get_free_index(priv); - if (sfi->handle < 0) { + if (index < 0) { NL_SET_ERR_MSG_MOD(extack, "No Stream Filter resource!"); err = -ENOSPC; goto free_fmi; -- GitLab From cb9e6e584d58420df182102674e636fb841dae4c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 4 May 2023 11:52:49 +0200 Subject: [PATCH 4550/5631] bonding: add xdp_features support Introduce xdp_features support for bonding driver according to the slave devices attached to the master one. xdp_features is required whenever we want to xdp_redirect traffic into a bond device and then into selected slaves attached to it. Reviewed-by: Simon Horman Acked-by: Jay Vosburgh Fixes: 66c0e13ad236 ("drivers: net: turn on XDP features") Signed-off-by: Lorenzo Bianconi Reviewed-by: Jussi Maki Tested-by: Jussi Maki Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 29 +++++++++++++++++++++++++++++ drivers/net/bonding/bond_options.c | 2 ++ include/net/bonding.h | 1 + 3 files changed, 32 insertions(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 710548dbd0c1..3fed888629f7 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1789,6 +1789,26 @@ static void bond_ether_setup(struct net_device *bond_dev) bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING; } +void bond_xdp_set_features(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + xdp_features_t val = NETDEV_XDP_ACT_MASK; + struct list_head *iter; + struct slave *slave; + + ASSERT_RTNL(); + + if (!bond_xdp_check(bond)) { + xdp_clear_features_flag(bond_dev); + return; + } + + bond_for_each_slave(bond, slave, iter) + val &= slave->dev->xdp_features; + + xdp_set_features_flag(bond_dev, val); +} + /* enslave device to bond device */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) @@ -2236,6 +2256,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bpf_prog_inc(bond->xdp_prog); } + bond_xdp_set_features(bond_dev); + slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); @@ -2483,6 +2505,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (!netif_is_bond_master(slave_dev)) slave_dev->priv_flags &= ~IFF_BONDING; + bond_xdp_set_features(bond_dev); kobject_put(&slave->kobj); return 0; @@ -3930,6 +3953,9 @@ static int bond_slave_netdev_event(unsigned long event, /* Propagate to master device */ call_netdevice_notifiers(event, slave->bond->dev); break; + case NETDEV_XDP_FEAT_CHANGE: + bond_xdp_set_features(bond_dev); + break; default: break; } @@ -5874,6 +5900,9 @@ void bond_setup(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ + + if (bond_xdp_check(bond)) + bond_dev->xdp_features = NETDEV_XDP_ACT_MASK; } /* Destroy a bonding device. diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index f71d5517f829..0498fc6731f8 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -877,6 +877,8 @@ static int bond_option_mode_set(struct bonding *bond, netdev_update_features(bond->dev); } + bond_xdp_set_features(bond->dev); + return 0; } diff --git a/include/net/bonding.h b/include/net/bonding.h index c3843239517d..a60a24923b55 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -659,6 +659,7 @@ void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); +void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); -- GitLab From 26312c685ae0bca61e06ac75ee158b1e69546415 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Thu, 4 May 2023 10:35:17 -0500 Subject: [PATCH 4551/5631] net: fec: correct the counting of XDP sent frames In the current xdp_xmit implementation, if any single frame fails to transmit due to insufficient buffer descriptors, the function nevertheless reports success in sending all frames. This results in erroneously indicating that frames were transmitted when in fact they were dropped. This patch fixes the issue by ensureing the return value properly indicates the actual number of frames successfully transmitted, rather than potentially reporting success for all frames when some could not transmit. Fixes: 6d6b39f180b8 ("net: fec: add initial XDP support") Signed-off-by: Gagandeep Singh Signed-off-by: Shenwei Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 160c1b3525f5..42ec6ca3bf03 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3798,7 +3798,8 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { netdev_err(fep->netdev, "NOT enough BD for SG!\n"); - return NETDEV_TX_OK; + xdp_return_frame(frame); + return NETDEV_TX_BUSY; } /* Fill in a Tx ring entry */ @@ -3856,6 +3857,7 @@ static int fec_enet_xdp_xmit(struct net_device *dev, struct fec_enet_private *fep = netdev_priv(dev); struct fec_enet_priv_tx_q *txq; int cpu = smp_processor_id(); + unsigned int sent_frames = 0; struct netdev_queue *nq; unsigned int queue; int i; @@ -3866,8 +3868,11 @@ static int fec_enet_xdp_xmit(struct net_device *dev, __netif_tx_lock(nq, cpu); - for (i = 0; i < num_frames; i++) - fec_enet_txq_xmit_frame(fep, txq, frames[i]); + for (i = 0; i < num_frames; i++) { + if (fec_enet_txq_xmit_frame(fep, txq, frames[i]) != 0) + break; + sent_frames++; + } /* Make sure the update to bdp and tx_skbuff are performed. */ wmb(); @@ -3877,7 +3882,7 @@ static int fec_enet_xdp_xmit(struct net_device *dev, __netif_tx_unlock(nq); - return num_frames; + return sent_frames; } static const struct net_device_ops fec_netdev_ops = { -- GitLab From dd4f6bbfa646f258e5bcdfac57a5c413d687f588 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 4 May 2023 20:16:14 +0200 Subject: [PATCH 4552/5631] net/sched: flower: fix filter idr initialization The cited commit moved idr initialization too early in fl_change() which allows concurrent users to access the filter that is still being initialized and is in inconsistent state, which, in turn, can cause NULL pointer dereference [0]. Since there is no obvious way to fix the ordering without reverting the whole cited commit, alternative approach taken to first insert NULL pointer into idr in order to allocate the handle but still cause fl_get() to return NULL and prevent concurrent users from seeing the filter while providing miss-to-action infrastructure with valid handle id early in fl_change(). [ 152.434728] general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN [ 152.436163] KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] [ 152.437269] CPU: 4 PID: 3877 Comm: tc Not tainted 6.3.0-rc4+ #5 [ 152.438110] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 152.439644] RIP: 0010:fl_dump_key+0x8b/0x1d10 [cls_flower] [ 152.440461] Code: 01 f2 02 f2 c7 40 08 04 f2 04 f2 c7 40 0c 04 f3 f3 f3 65 48 8b 04 25 28 00 00 00 48 89 84 24 00 01 00 00 48 89 c8 48 c1 e8 03 <0f> b6 04 10 84 c0 74 08 3c 03 0f 8e 98 19 00 00 8b 13 85 d2 74 57 [ 152.442885] RSP: 0018:ffff88817a28f158 EFLAGS: 00010246 [ 152.443851] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 152.444826] RDX: dffffc0000000000 RSI: ffffffff8500ae80 RDI: ffff88810a987900 [ 152.445791] RBP: ffff888179d88240 R08: ffff888179d8845c R09: ffff888179d88240 [ 152.446780] R10: ffffed102f451e48 R11: 00000000fffffff2 R12: ffff88810a987900 [ 152.447741] R13: ffffffff8500ae80 R14: ffff88810a987900 R15: ffff888149b3c738 [ 152.448756] FS: 00007f5eb2a34800(0000) GS:ffff88881ec00000(0000) knlGS:0000000000000000 [ 152.449888] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 152.450685] CR2: 000000000046ad19 CR3: 000000010b0bd006 CR4: 0000000000370ea0 [ 152.451641] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 152.452628] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 152.453588] Call Trace: [ 152.454032] [ 152.454447] ? netlink_sendmsg+0x7a1/0xcb0 [ 152.455109] ? sock_sendmsg+0xc5/0x190 [ 152.455689] ? ____sys_sendmsg+0x535/0x6b0 [ 152.456320] ? ___sys_sendmsg+0xeb/0x170 [ 152.456916] ? do_syscall_64+0x3d/0x90 [ 152.457529] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 152.458321] ? ___sys_sendmsg+0xeb/0x170 [ 152.458958] ? __sys_sendmsg+0xb5/0x140 [ 152.459564] ? do_syscall_64+0x3d/0x90 [ 152.460122] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 152.460852] ? fl_dump_key_options.part.0+0xea0/0xea0 [cls_flower] [ 152.461710] ? _raw_spin_lock+0x7a/0xd0 [ 152.462299] ? _raw_read_lock_irq+0x30/0x30 [ 152.462924] ? nla_put+0x15e/0x1c0 [ 152.463480] fl_dump+0x228/0x650 [cls_flower] [ 152.464112] ? fl_tmplt_dump+0x210/0x210 [cls_flower] [ 152.464854] ? __kmem_cache_alloc_node+0x1a7/0x330 [ 152.465592] ? nla_put+0x15e/0x1c0 [ 152.466160] tcf_fill_node+0x515/0x9a0 [ 152.466766] ? tc_setup_offload_action+0xf0/0xf0 [ 152.467463] ? __alloc_skb+0x13c/0x2a0 [ 152.468067] ? __build_skb_around+0x330/0x330 [ 152.468814] ? fl_get+0x107/0x1a0 [cls_flower] [ 152.469503] tc_del_tfilter+0x718/0x1330 [ 152.470115] ? is_bpf_text_address+0xa/0x20 [ 152.470765] ? tc_ctl_chain+0xee0/0xee0 [ 152.471335] ? __kernel_text_address+0xe/0x30 [ 152.471948] ? unwind_get_return_address+0x56/0xa0 [ 152.472639] ? __thaw_task+0x150/0x150 [ 152.473218] ? arch_stack_walk+0x98/0xf0 [ 152.473839] ? __stack_depot_save+0x35/0x4c0 [ 152.474501] ? stack_trace_save+0x91/0xc0 [ 152.475119] ? security_capable+0x51/0x90 [ 152.475741] rtnetlink_rcv_msg+0x2c1/0x9d0 [ 152.476387] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 152.477042] ? __sys_sendmsg+0xb5/0x140 [ 152.477664] ? do_syscall_64+0x3d/0x90 [ 152.478255] ? entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 152.479010] ? __stack_depot_save+0x35/0x4c0 [ 152.479679] ? __stack_depot_save+0x35/0x4c0 [ 152.480346] netlink_rcv_skb+0x12c/0x360 [ 152.480929] ? rtnl_calcit.isra.0+0x2b0/0x2b0 [ 152.481517] ? do_syscall_64+0x3d/0x90 [ 152.482061] ? netlink_ack+0x1550/0x1550 [ 152.482612] ? rhashtable_walk_peek+0x170/0x170 [ 152.483262] ? kmem_cache_alloc_node+0x1af/0x390 [ 152.483875] ? _copy_from_iter+0x3d6/0xc70 [ 152.484528] netlink_unicast+0x553/0x790 [ 152.485168] ? netlink_attachskb+0x6a0/0x6a0 [ 152.485848] ? unwind_next_frame+0x11cc/0x1a10 [ 152.486538] ? arch_stack_walk+0x61/0xf0 [ 152.487169] netlink_sendmsg+0x7a1/0xcb0 [ 152.487799] ? netlink_unicast+0x790/0x790 [ 152.488355] ? iovec_from_user.part.0+0x4d/0x220 [ 152.488990] ? _raw_spin_lock+0x7a/0xd0 [ 152.489598] ? netlink_unicast+0x790/0x790 [ 152.490236] sock_sendmsg+0xc5/0x190 [ 152.490796] ____sys_sendmsg+0x535/0x6b0 [ 152.491394] ? import_iovec+0x7/0x10 [ 152.491964] ? kernel_sendmsg+0x30/0x30 [ 152.492561] ? __copy_msghdr+0x3c0/0x3c0 [ 152.493160] ? do_syscall_64+0x3d/0x90 [ 152.493706] ___sys_sendmsg+0xeb/0x170 [ 152.494283] ? may_open_dev+0xd0/0xd0 [ 152.494858] ? copy_msghdr_from_user+0x110/0x110 [ 152.495541] ? __handle_mm_fault+0x2678/0x4ad0 [ 152.496205] ? copy_page_range+0x2360/0x2360 [ 152.496862] ? __fget_light+0x57/0x520 [ 152.497449] ? mas_find+0x1c0/0x1c0 [ 152.498026] ? sockfd_lookup_light+0x1a/0x140 [ 152.498703] __sys_sendmsg+0xb5/0x140 [ 152.499306] ? __sys_sendmsg_sock+0x20/0x20 [ 152.499951] ? do_user_addr_fault+0x369/0xd80 [ 152.500595] do_syscall_64+0x3d/0x90 [ 152.501185] entry_SYSCALL_64_after_hwframe+0x46/0xb0 [ 152.501917] RIP: 0033:0x7f5eb294f887 [ 152.502494] Code: 0a 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 152.505008] RSP: 002b:00007ffd2c708f78 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 152.506152] RAX: ffffffffffffffda RBX: 00000000642d9472 RCX: 00007f5eb294f887 [ 152.507134] RDX: 0000000000000000 RSI: 00007ffd2c708fe0 RDI: 0000000000000003 [ 152.508113] RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000 [ 152.509119] R10: 00007f5eb2808708 R11: 0000000000000246 R12: 0000000000000001 [ 152.510068] R13: 0000000000000000 R14: 00007ffd2c70d1b8 R15: 0000000000485400 [ 152.511031] [ 152.511444] Modules linked in: cls_flower sch_ingress openvswitch nsh mlx5_vdpa vringh vhost_iotlb vdpa mlx5_ib mlx5_core rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm ib_uverbs ib_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter overlay zram zsmalloc fuse [last unloaded: mlx5_core] [ 152.515720] ---[ end trace 0000000000000000 ]--- Fixes: 08a0063df3ae ("net/sched: flower: Move filter handle initialization earlier") Signed-off-by: Vlad Buslov Reviewed-by: Pedro Tammela Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6ab6aadc07b8..4dc3a9007f30 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2210,10 +2210,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, spin_lock(&tp->lock); if (!handle) { handle = 1; - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + err = idr_alloc_u32(&head->handle_idr, NULL, &handle, INT_MAX, GFP_ATOMIC); } else { - err = idr_alloc_u32(&head->handle_idr, fnew, &handle, + err = idr_alloc_u32(&head->handle_idr, NULL, &handle, handle, GFP_ATOMIC); /* Filter with specified handle was concurrently @@ -2378,7 +2378,7 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, rcu_read_lock(); idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { /* don't return filters that are being deleted */ - if (!refcount_inc_not_zero(&f->refcnt)) + if (!f || !refcount_inc_not_zero(&f->refcnt)) continue; rcu_read_unlock(); -- GitLab From 5110f3ff6d3c986df9575c8da86630578b7f0846 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 4 May 2023 20:16:15 +0200 Subject: [PATCH 4553/5631] Revert "net/sched: flower: Fix wrong handle assignment during filter change" This reverts commit 32eff6bacec2cb574677c15378169a9fa30043ef. Superseded by the following commit in this series. Signed-off-by: Vlad Buslov Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 4dc3a9007f30..ac4f344c52e0 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2231,8 +2231,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(fnew); goto errout_tb; } - fnew->handle = handle; } + fnew->handle = handle; err = tcf_exts_init_ex(&fnew->exts, net, TCA_FLOWER_ACT, 0, tp, handle, !tc_skip_hw(fnew->flags)); -- GitLab From fd741f0d9f702c193b2b44225c004f8c5d5be163 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Thu, 4 May 2023 20:16:16 +0200 Subject: [PATCH 4554/5631] net/sched: flower: fix error handler on replace When replacing a filter (i.e. 'fold' pointer is not NULL) the insertion of new filter to idr is postponed until later in code since handle is already provided by the user. However, the error handling code in fl_change() always assumes that the new filter had been inserted into idr. If error handler is reached when replacing existing filter it may remove it from idr therefore making it unreachable for delete or dump afterwards. Fix the issue by verifying that 'fold' argument wasn't provided by caller before calling idr_remove(). Fixes: 08a0063df3ae ("net/sched: flower: Move filter handle initialization earlier") Signed-off-by: Vlad Buslov Reviewed-by: Pedro Tammela Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index ac4f344c52e0..9dbc43388e57 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2339,7 +2339,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, errout_mask: fl_mask_put(head, fnew->mask); errout_idr: - idr_remove(&head->handle_idr, fnew->handle); + if (!fold) + idr_remove(&head->handle_idr, fnew->handle); __fl_put(fnew); errout_tb: kfree(tb); -- GitLab From 1e76f42779d6a2e45107b34d79d86a57b8077630 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 4 May 2023 13:44:59 -0700 Subject: [PATCH 4555/5631] pds_core: fix mutex double unlock in error path Fix a double unlock in an error handling path by unlocking as soon as the error is seen and removing unlocks in the error cleanup path. Link: https://lore.kernel.org/kernel-janitors/209a09f6-5ec6-40c7-a5ec-6260d8f54d25@kili.mountain/ Fixes: 523847df1b37 ("pds_core: add devcmd device interfaces") Reported-by: Dan Carpenter Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/pds_core/main.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c index e2d14b1ca471..672757932246 100644 --- a/drivers/net/ethernet/amd/pds_core/main.c +++ b/drivers/net/ethernet/amd/pds_core/main.c @@ -244,11 +244,16 @@ static int pdsc_init_pf(struct pdsc *pdsc) set_bit(PDSC_S_FW_DEAD, &pdsc->state); err = pdsc_setup(pdsc, PDSC_SETUP_INIT); - if (err) + if (err) { + mutex_unlock(&pdsc->config_lock); goto err_out_unmap_bars; + } + err = pdsc_start(pdsc); - if (err) + if (err) { + mutex_unlock(&pdsc->config_lock); goto err_out_teardown; + } mutex_unlock(&pdsc->config_lock); @@ -257,13 +262,15 @@ static int pdsc_init_pf(struct pdsc *pdsc) err = devl_params_register(dl, pdsc_dl_params, ARRAY_SIZE(pdsc_dl_params)); if (err) { + devl_unlock(dl); dev_warn(pdsc->dev, "Failed to register devlink params: %pe\n", ERR_PTR(err)); - goto err_out_unlock_dl; + goto err_out_stop; } hr = devl_health_reporter_create(dl, &pdsc_fw_reporter_ops, 0, pdsc); if (IS_ERR(hr)) { + devl_unlock(dl); dev_warn(pdsc->dev, "Failed to create fw reporter: %pe\n", hr); err = PTR_ERR(hr); goto err_out_unreg_params; @@ -279,15 +286,13 @@ static int pdsc_init_pf(struct pdsc *pdsc) return 0; err_out_unreg_params: - devl_params_unregister(dl, pdsc_dl_params, - ARRAY_SIZE(pdsc_dl_params)); -err_out_unlock_dl: - devl_unlock(dl); + devlink_params_unregister(dl, pdsc_dl_params, + ARRAY_SIZE(pdsc_dl_params)); +err_out_stop: pdsc_stop(pdsc); err_out_teardown: pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING); err_out_unmap_bars: - mutex_unlock(&pdsc->config_lock); del_timer_sync(&pdsc->wdtimer); if (pdsc->wq) destroy_workqueue(pdsc->wq); -- GitLab From 93e0401e0fc0c54b0ac05b687cd135c2ac38187c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 4 May 2023 16:07:27 -0700 Subject: [PATCH 4556/5631] net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop() The call to phy_stop() races with the later call to phy_disconnect(), resulting in concurrent phy_suspend() calls being run from different CPUs. The final call to phy_disconnect() ensures that the PHY is stopped and suspended, too. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index d937daa8ee88..f28ffc31df22 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3465,7 +3465,6 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); - phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); -- GitLab From fa3eeb638de0c1a9d2d860e5b48259facdd65176 Mon Sep 17 00:00:00 2001 From: Haibo Li Date: Mon, 17 Apr 2023 10:17:07 +0100 Subject: [PATCH 4557/5631] ARM: 9295/1: unwind:fix unwind abort for uleb128 case When unwind instruction is 0xb2,the subsequent instructions are uleb128 bytes. For now,it uses only the first uleb128 byte in code. For vsp increments of 0x204~0x400,use one uleb128 byte like below: 0xc06a00e4 : 0x80b27fac Compact model index: 0 0xb2 0x7f vsp = vsp + 1024 0xac pop {r4, r5, r6, r7, r8, r14} For vsp increments larger than 0x400,use two uleb128 bytes like below: 0xc06a00e4 : @0xc0cc9e0c Compact model index: 1 0xb2 0x81 0x01 vsp = vsp + 1032 0xac pop {r4, r5, r6, r7, r8, r14} The unwind works well since the decoded uleb128 byte is also 0x81. For vsp increments larger than 0x600,use two uleb128 bytes like below: 0xc06a00e4 : @0xc0cc9e0c Compact model index: 1 0xb2 0x81 0x02 vsp = vsp + 1544 0xac pop {r4, r5, r6, r7, r8, r14} In this case,the decoded uleb128 result is 0x101(vsp=0x204+(0x101<<2)). While the uleb128 used in code is 0x81(vsp=0x204+(0x81<<2)). The unwind aborts at this frame since it gets incorrect vsp. To fix this,add uleb128 decode to cover all the above case. Signed-off-by: Haibo Li Reviewed-by: Linus Walleij Reviewed-by: Alexandre Mergnat Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Russell King (Oracle) --- arch/arm/kernel/unwind.c | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c index 53be7ea6181b..9d2192156087 100644 --- a/arch/arm/kernel/unwind.c +++ b/arch/arm/kernel/unwind.c @@ -308,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl, return URC_OK; } +static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl) +{ + unsigned long bytes = 0; + unsigned long insn; + unsigned long result = 0; + + /* + * unwind_get_byte() will advance `ctrl` one instruction at a time, so + * loop until we get an instruction byte where bit 7 is not set. + * + * Note: This decodes a maximum of 4 bytes to output 28 bits data where + * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence + * it is sufficient for unwinding the stack. + */ + do { + insn = unwind_get_byte(ctrl); + result |= (insn & 0x7f) << (bytes * 7); + bytes++; + } while (!!(insn & 0x80) && (bytes != sizeof(result))); + + return result; +} + /* * Execute the current unwind instruction. */ @@ -361,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) if (ret) goto error; } else if (insn == 0xb2) { - unsigned long uleb128 = unwind_get_byte(ctrl); + unsigned long uleb128 = unwind_decode_uleb128(ctrl); ctrl->vrs[SP] += 0x204 + (uleb128 << 2); } else { -- GitLab From 46dd6078dbc7e363a8bb01209da67015a1538929 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 23 Apr 2023 06:48:45 +0100 Subject: [PATCH 4558/5631] ARM: 9296/1: HP Jornada 7XX: fix kernel-doc warnings Fix kernel-doc warnings from the kernel test robot: jornada720_ssp.c:24: warning: Function parameter or member 'jornada_ssp_lock' not described in 'DEFINE_SPINLOCK' jornada720_ssp.c:24: warning: expecting prototype for arch/arm/mac(). Prototype was for DEFINE_SPINLOCK() instead jornada720_ssp.c:34: warning: Function parameter or member 'byte' not described in 'jornada_ssp_reverse' jornada720_ssp.c:57: warning: Function parameter or member 'byte' not described in 'jornada_ssp_byte' jornada720_ssp.c:85: warning: Function parameter or member 'byte' not described in 'jornada_ssp_inout' Link: lore.kernel.org/r/202304210535.tWby3jWF-lkp@intel.com Fixes: 69ebb22277a5 ("[ARM] 4506/1: HP Jornada 7XX: Addition of SSP Platform Driver") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Arnd Bergmann Cc: Kristoffer Ericson Cc: patches@armlinux.org.uk Signed-off-by: Russell King (Oracle) --- arch/arm/mach-sa1100/jornada720_ssp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c index 1dbe98948ce3..9627c4cf3e41 100644 --- a/arch/arm/mach-sa1100/jornada720_ssp.c +++ b/arch/arm/mach-sa1100/jornada720_ssp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * arch/arm/mac-sa1100/jornada720_ssp.c * * Copyright (C) 2006/2007 Kristoffer Ericson @@ -26,6 +26,7 @@ static unsigned long jornada_ssp_flags; /** * jornada_ssp_reverse - reverses input byte + * @byte: input byte to reverse * * we need to reverse all data we receive from the mcu due to its physical location * returns : 01110111 -> 11101110 @@ -46,6 +47,7 @@ EXPORT_SYMBOL(jornada_ssp_reverse); /** * jornada_ssp_byte - waits for ready ssp bus and sends byte + * @byte: input byte to transmit * * waits for fifo buffer to clear and then transmits, if it doesn't then we will * timeout after rounds. Needs mcu running before its called. @@ -77,6 +79,7 @@ EXPORT_SYMBOL(jornada_ssp_byte); /** * jornada_ssp_inout - decide if input is command or trading byte + * @byte: input byte to send (may be %TXDUMMY) * * returns : (jornada_ssp_byte(byte)) on success * : %-ETIMEDOUT on timeout failure -- GitLab From 9ee04875ae73412f5071f6ec1af01788ec271e7c Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 5 May 2023 08:49:25 +0800 Subject: [PATCH 4559/5631] cifs: Remove unneeded semicolon ./fs/cifs/smb2pdu.c:4140:2-3: Unneeded semicolon Reported-by: Abaci Robot Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4863 Signed-off-by: Yang Li Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 8e7c15e2fd91..e33ca0d33906 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -4137,7 +4137,7 @@ smb2_readv_callback(struct mid_q_entry *mid) if (rdata->got_bytes) { rqst.rq_iter = rdata->iter; rqst.rq_iter_size = iov_iter_count(&rdata->iter); - }; + } WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", -- GitLab From 6997f847cbb72082a2e9aa0fef8ebfcc3bd4ddc5 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Thu, 4 May 2023 22:58:39 +0100 Subject: [PATCH 4560/5631] MAINTAINERS: add Conor as a dt-bindings maintainer Rob asked if I would be interested in helping with the dt-bindings maintenance, and since I am a glutton for punishment I accepted. Signed-off-by: Conor Dooley Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230504-renderer-alive-1c01d431b2a7@spud Signed-off-by: Rob Herring --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 5d463f171c90..128a4a022d7b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15608,6 +15608,7 @@ K: of_overlay_remove OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring M: Krzysztof Kozlowski +M: Conor Dooley L: devicetree@vger.kernel.org S: Maintained C: irc://irc.libera.chat/devicetree -- GitLab From 2492ba4cd06dd24076f44327174816b04cddde90 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 5 May 2023 06:36:05 +0200 Subject: [PATCH 4561/5631] MAINTAINERS: remove section INTEL MENLOW THERMAL DRIVER Commit 2b6a7409ac39 ("thermal: intel: menlow: Get rid of this driver") removes the driver drivers/thermal/intel/intel_menlow.c, but misses to remove its reference in MAINTAINERS. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken reference. Remove the INTEL MENLOW THERMAL DRIVER section in MAINTAINERS. Fixes: 2b6a7409ac39 ("thermal: intel: menlow: Get rid of this driver") Signed-off-by: Lukas Bulwahn Signed-off-by: Rafael J. Wysocki --- MAINTAINERS | 6 ------ 1 file changed, 6 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index c0cde28c62c6..c28e45cb353d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10556,12 +10556,6 @@ F: drivers/hwmon/intel-m10-bmc-hwmon.c F: drivers/mfd/intel-m10-bmc* F: include/linux/mfd/intel-m10-bmc.h -INTEL MENLOW THERMAL DRIVER -M: Sujith Thomas -L: linux-pm@vger.kernel.org -S: Supported -F: drivers/thermal/intel/intel_menlow.c - INTEL P-Unit IPC DRIVER M: Zha Qipeng L: platform-driver-x86@vger.kernel.org -- GitLab From 6ce2c04fcbcaa5eb086e5142ab359be306cbc3e1 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 2 May 2023 21:32:33 -0400 Subject: [PATCH 4562/5631] ftrace: Add MODIFIED flag to show if IPMODIFY or direct was attached If a function had ever had IPMODIFY or DIRECT attached to it, where this is how live kernel patching and BPF overrides work, mark them and display an "M" in the enabled_functions and touched_functions files. This can be used for debugging. If a function had been modified and later there's a bug in the code related to that function, this can be used to know if the cause is possibly from a live kernel patch or a BPF program that changed the behavior of the code. Also update the documentation on the enabled_functions and touched_functions output, as it was missing direct callers and CALL_OPS. And include this new modify attribute. Link: https://lore.kernel.org/linux-trace-kernel/20230502213233.004e3ae4@gandalf.local.home Cc: Mark Rutland Acked-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/ftrace.rst | 25 +++++++++++++++++++++++++ include/linux/ftrace.h | 4 +++- kernel/trace/ftrace.c | 12 +++++++++--- 3 files changed, 37 insertions(+), 4 deletions(-) diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index aaebb821912e..d5766229c71a 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -350,6 +350,19 @@ of ftrace. Here is a list of some of the key files: an 'I' will be displayed on the same line as the function that can be overridden. + If a non ftrace trampoline is attached (BPF) a 'D' will be displayed. + Note, normal ftrace trampolines can also be attached, but only one + "direct" trampoline can be attached to a given function at a time. + + Some architectures can not call direct trampolines, but instead have + the ftrace ops function located above the function entry point. In + such cases an 'O' will be displayed. + + If a function had either the "ip modify" or a "direct" call attached to + it in the past, a 'M' will be shown. This flag is never cleared. It is + used to know if a function was every modified by the ftrace infrastructure, + and can be used for debugging. + If the architecture supports it, it will also show what callback is being directly called by the function. If the count is greater than 1 it most likely will be ftrace_ops_list_func(). @@ -359,6 +372,18 @@ of ftrace. Here is a list of some of the key files: its address will be printed as well as the function that the trampoline calls. + touched_functions: + + This file contains all the functions that ever had a function callback + to it via the ftrace infrastructure. It has the same format as + enabled_functions but shows all functions that have every been + traced. + + To see any function that has every been modified by "ip modify" or a + direct trampoline, one can perform the following command: + + grep ' M ' /sys/kernel/tracing/touched_functions + function_profile_enabled: When set it will enable all functions with either the function diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 327046f1278d..7dffd740e784 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -549,6 +549,7 @@ bool is_ftrace_trampoline(unsigned long addr); * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops * TOUCHED - A callback was added since boot up + * MODIFIED - The function had IPMODIFY or DIRECT attached to it * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -569,9 +570,10 @@ enum { FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), FTRACE_FL_TOUCHED = (1UL << 20), + FTRACE_FL_MODIFIED = (1UL << 19), }; -#define FTRACE_REF_MAX_SHIFT 20 +#define FTRACE_REF_MAX_SHIFT 19 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index db8532a4d5c8..885845fc851d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -46,7 +46,8 @@ #include "trace_stat.h" /* Flags that do not get reset */ -#define FTRACE_NOCLEAR_FLAGS (FTRACE_FL_DISABLED | FTRACE_FL_TOUCHED) +#define FTRACE_NOCLEAR_FLAGS (FTRACE_FL_DISABLED | FTRACE_FL_TOUCHED | \ + FTRACE_FL_MODIFIED) #define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__" @@ -2273,6 +2274,10 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) rec->flags &= ~FTRACE_FL_TRAMP_EN; } + /* Keep track of anything that modifies the function */ + if (rec->flags & (FTRACE_FL_DIRECT | FTRACE_FL_IPMODIFY)) + rec->flags |= FTRACE_FL_MODIFIED; + if (flag & FTRACE_FL_DIRECT) { /* * If there's only one user (direct_ops helper) @@ -3866,12 +3871,13 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & (FTRACE_ITER_ENABLED | FTRACE_ITER_TOUCHED)) { struct ftrace_ops *ops; - seq_printf(m, " (%ld)%s%s%s%s", + seq_printf(m, " (%ld)%s%s%s%s%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " ", rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ", rec->flags & FTRACE_FL_DIRECT ? " D" : " ", - rec->flags & FTRACE_FL_CALL_OPS ? " O" : " "); + rec->flags & FTRACE_FL_CALL_OPS ? " O" : " ", + rec->flags & FTRACE_FL_MODIFIED ? " M " : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { -- GitLab From 56fc217f0db4fc78e02a1b8450df06389474a5e5 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 5 May 2023 14:59:23 +0200 Subject: [PATCH 4563/5631] ALSA: hda/realtek: Fix mute and micmute LEDs for an HP laptop There's another laptop that needs the fixup to enable mute and micmute LEDs. So do it accordingly. Signed-off-by: Kai-Heng Feng Cc: Link: https://lore.kernel.org/r/20230505125925.543601-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 068ce0db9562..172ffc2c332b 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9479,6 +9479,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), -- GitLab From d7f5dd9790bbf9c7357672bafb1992ee7aadf45a Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 5 May 2023 17:52:38 +0200 Subject: [PATCH 4564/5631] ALSA: pcm: Revert "ALSA: pcm: rewrite snd_pcm_playback_silence()" This reverts commit 9f656705c5faa18afb26d922cfc64f9fd103c38d. There was a regression (in the top-up mode). Unfortunately, the patch provided from the author of this commit is not easy to review. Keep the updated and new comments in headers. Also add a new comment that documents the missed API constraint which led to the regression. Reported-by: Jeff Chua Link: https://lore.kernel.org/r/CAAJw_ZsbTVd3Es373x_wTNDF7RknGhCD0r+NKUSwAO7HpLAkYA@mail.gmail.com Signed-off-by: Jaroslav Kysela Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230505155244.2312199-1-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 90 ++++++++++++++++++++++++----------------- sound/core/pcm_local.h | 3 +- sound/core/pcm_native.c | 6 +-- 3 files changed, 59 insertions(+), 40 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index d21c73944efd..3357ffae635f 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -42,56 +42,74 @@ static int fill_silence_frames(struct snd_pcm_substream *substream, * * when runtime->silence_size >= runtime->boundary - fill processed area with silence immediately */ -void snd_pcm_playback_silence(struct snd_pcm_substream *substream) +void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_uframes_t new_hw_ptr) { struct snd_pcm_runtime *runtime = substream->runtime; - snd_pcm_uframes_t appl_ptr = READ_ONCE(runtime->control->appl_ptr); - snd_pcm_sframes_t added, hw_avail, frames; - snd_pcm_uframes_t noise_dist, ofs, transfer; + snd_pcm_uframes_t frames, ofs, transfer; int err; - added = appl_ptr - runtime->silence_start; - if (added) { - if (added < 0) - added += runtime->boundary; - if (added < runtime->silence_filled) - runtime->silence_filled -= added; - else - runtime->silence_filled = 0; - runtime->silence_start = appl_ptr; - } - - // This will "legitimately" turn negative on underrun, and will be mangled - // into a huge number by the boundary crossing handling. The initial state - // might also be not quite sane. The code below MUST account for these cases. - hw_avail = appl_ptr - runtime->status->hw_ptr; - if (hw_avail < 0) - hw_avail += runtime->boundary; - - noise_dist = hw_avail + runtime->silence_filled; if (runtime->silence_size < runtime->boundary) { - frames = runtime->silence_threshold - noise_dist; - if (frames <= 0) + snd_pcm_sframes_t noise_dist, n; + snd_pcm_uframes_t appl_ptr = READ_ONCE(runtime->control->appl_ptr); + if (runtime->silence_start != appl_ptr) { + n = appl_ptr - runtime->silence_start; + if (n < 0) + n += runtime->boundary; + if ((snd_pcm_uframes_t)n < runtime->silence_filled) + runtime->silence_filled -= n; + else + runtime->silence_filled = 0; + runtime->silence_start = appl_ptr; + } + if (runtime->silence_filled >= runtime->buffer_size) + return; + noise_dist = snd_pcm_playback_hw_avail(runtime) + runtime->silence_filled; + if (noise_dist >= (snd_pcm_sframes_t) runtime->silence_threshold) return; + frames = runtime->silence_threshold - noise_dist; if (frames > runtime->silence_size) frames = runtime->silence_size; } else { - frames = runtime->buffer_size - noise_dist; - if (frames <= 0) - return; + /* + * This filling mode aims at free-running mode (used for example by dmix), + * which doesn't update the application pointer. + */ + if (new_hw_ptr == ULONG_MAX) { /* initialization */ + snd_pcm_sframes_t avail = snd_pcm_playback_hw_avail(runtime); + if (avail > runtime->buffer_size) + avail = runtime->buffer_size; + runtime->silence_filled = avail > 0 ? avail : 0; + runtime->silence_start = (runtime->status->hw_ptr + + runtime->silence_filled) % + runtime->boundary; + } else { + ofs = runtime->status->hw_ptr; + frames = new_hw_ptr - ofs; + if ((snd_pcm_sframes_t)frames < 0) + frames += runtime->boundary; + runtime->silence_filled -= frames; + if ((snd_pcm_sframes_t)runtime->silence_filled < 0) { + runtime->silence_filled = 0; + runtime->silence_start = new_hw_ptr; + } else { + runtime->silence_start = ofs; + } + } + frames = runtime->buffer_size - runtime->silence_filled; } - if (snd_BUG_ON(frames > runtime->buffer_size)) return; - ofs = (runtime->silence_start + runtime->silence_filled) % runtime->buffer_size; - do { + if (frames == 0) + return; + ofs = runtime->silence_start % runtime->buffer_size; + while (frames > 0) { transfer = ofs + frames > runtime->buffer_size ? runtime->buffer_size - ofs : frames; err = fill_silence_frames(substream, ofs, transfer); snd_BUG_ON(err < 0); runtime->silence_filled += transfer; frames -= transfer; ofs = 0; - } while (frames > 0); + } snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); } @@ -425,6 +443,10 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream, return 0; } + if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && + runtime->silence_size > 0) + snd_pcm_playback_silence(substream, new_hw_ptr); + if (in_interrupt) { delta = new_hw_ptr - runtime->hw_ptr_interrupt; if (delta < 0) @@ -442,10 +464,6 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream, runtime->hw_ptr_wrap += runtime->boundary; } - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && - runtime->silence_size > 0) - snd_pcm_playback_silence(substream); - update_audio_tstamp(substream, &curr_tstamp, &audio_tstamp); return snd_pcm_update_state(substream, runtime); diff --git a/sound/core/pcm_local.h b/sound/core/pcm_local.h index 42fe3a4e9154..ecb21697ae3a 100644 --- a/sound/core/pcm_local.h +++ b/sound/core/pcm_local.h @@ -29,7 +29,8 @@ int snd_pcm_update_state(struct snd_pcm_substream *substream, struct snd_pcm_runtime *runtime); int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream); -void snd_pcm_playback_silence(struct snd_pcm_substream *substream); +void snd_pcm_playback_silence(struct snd_pcm_substream *substream, + snd_pcm_uframes_t new_hw_ptr); static inline snd_pcm_uframes_t snd_pcm_avail(struct snd_pcm_substream *substream) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 3d0c4a5b701b..94185267a7b9 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -958,7 +958,7 @@ static int snd_pcm_sw_params(struct snd_pcm_substream *substream, if (snd_pcm_running(substream)) { if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) - snd_pcm_playback_silence(substream); + snd_pcm_playback_silence(substream, ULONG_MAX); err = snd_pcm_update_state(substream, runtime); } snd_pcm_stream_unlock_irq(substream); @@ -1455,7 +1455,7 @@ static void snd_pcm_post_start(struct snd_pcm_substream *substream, __snd_pcm_set_state(runtime, state); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) - snd_pcm_playback_silence(substream); + snd_pcm_playback_silence(substream, ULONG_MAX); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MSTART); } @@ -1916,7 +1916,7 @@ static void snd_pcm_post_reset(struct snd_pcm_substream *substream, runtime->control->appl_ptr = runtime->status->hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) - snd_pcm_playback_silence(substream); + snd_pcm_playback_silence(substream, ULONG_MAX); snd_pcm_stream_unlock_irq(substream); } -- GitLab From 2fbaa44a59887f9fd70c986f39c4ac9aebd0c8a1 Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 5 May 2023 17:52:39 +0200 Subject: [PATCH 4565/5631] ALSA: pcm: fix playback silence - use the actual new_hw_ptr for the threshold mode The snd_pcm_playback_hw_avail() function uses runtime->status->hw_ptr. Unfortunately, in case when we call this function from snd_pcm_update_hw_ptr0(), this variable contains the previous hardware pointer. Use the new_hw_ptr argument to calculate hw_avail (filled samples by the user space) to correct the threshold comparison. The new_hw_ptr argument may also be set to ULONG_MAX which means the initialization phase. In this case, use runtime->status->hw_ptr. Suggested-by: Oswald Buddenhagen Signed-off-by: Jaroslav Kysela Reviewed-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230505155244.2312199-2-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 3357ffae635f..6ad67e7e740c 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -63,7 +63,15 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram } if (runtime->silence_filled >= runtime->buffer_size) return; - noise_dist = snd_pcm_playback_hw_avail(runtime) + runtime->silence_filled; + /* initialization outside pointer updates */ + if (new_hw_ptr == ULONG_MAX) + new_hw_ptr = runtime->status->hw_ptr; + /* get hw_avail with the boundary crossing */ + noise_dist = appl_ptr - new_hw_ptr; + if (noise_dist < 0) + noise_dist += runtime->boundary; + /* total noise distance */ + noise_dist += runtime->silence_filled; if (noise_dist >= (snd_pcm_sframes_t) runtime->silence_threshold) return; frames = runtime->silence_threshold - noise_dist; -- GitLab From 781b4da64b9e3dafb356b7365e7ecf273e879602 Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 5 May 2023 17:52:40 +0200 Subject: [PATCH 4566/5631] ALSA: pcm: fix playback silence - correct incremental silencing Commit 9a826ddba6e ("[ALSA] pcm core: fix silence_start calculations") came with exactly the right commit message, but the patch just made things broken in a different way: We'd fill at a too low address if the area was already partially zeroed, so we'd under-fill. This affected both thresholded mode (where it was somewhat less likely) and top-up mode (where it would be the case consistently). Co-developed-by: Oswald Buddenhagen Signed-off-by: Oswald Buddenhagen Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230505155244.2312199-3-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6ad67e7e740c..5ddb74a12030 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -87,9 +87,7 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram if (avail > runtime->buffer_size) avail = runtime->buffer_size; runtime->silence_filled = avail > 0 ? avail : 0; - runtime->silence_start = (runtime->status->hw_ptr + - runtime->silence_filled) % - runtime->boundary; + runtime->silence_start = runtime->status->hw_ptr; } else { ofs = runtime->status->hw_ptr; frames = new_hw_ptr - ofs; @@ -98,10 +96,8 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram runtime->silence_filled -= frames; if ((snd_pcm_sframes_t)runtime->silence_filled < 0) { runtime->silence_filled = 0; - runtime->silence_start = new_hw_ptr; - } else { - runtime->silence_start = ofs; } + runtime->silence_start = new_hw_ptr; } frames = runtime->buffer_size - runtime->silence_filled; } @@ -109,7 +105,7 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram return; if (frames == 0) return; - ofs = runtime->silence_start % runtime->buffer_size; + ofs = (runtime->silence_start + runtime->silence_filled) % runtime->buffer_size; while (frames > 0) { transfer = ofs + frames > runtime->buffer_size ? runtime->buffer_size - ofs : frames; err = fill_silence_frames(substream, ofs, transfer); -- GitLab From 190cb66a4ee0ac4419e1f8a9de46074a8c8e4c23 Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 5 May 2023 17:52:41 +0200 Subject: [PATCH 4567/5631] ALSA: pcm: playback silence - remove extra code The removed condition handles de facto only one situation where runtime->silence_filled variable is equal to runtime->buffer_size, because this variable cannot go over the buffer size. This case is implicitly caught by the required comparison of the noise distance with the threshold. Suggested-by: Oswald Buddenhagen Signed-off-by: Jaroslav Kysela Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230505155244.2312199-4-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 5ddb74a12030..a1838130c830 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -61,8 +61,6 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram runtime->silence_filled = 0; runtime->silence_start = appl_ptr; } - if (runtime->silence_filled >= runtime->buffer_size) - return; /* initialization outside pointer updates */ if (new_hw_ptr == ULONG_MAX) new_hw_ptr = runtime->status->hw_ptr; -- GitLab From 6d8d56db0cd14c415c26e27d949c615750c40d70 Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Fri, 5 May 2023 17:52:42 +0200 Subject: [PATCH 4568/5631] ALSA: pcm: playback silence - move silence variable updates to separate function The code tracking the added samples in thresholded mode and the code tracking the just played samples in top-up mode are semantically identical, so factor it out to a common function to enhance readability. Co-developed-by: Oswald Buddenhagen Signed-off-by: Oswald Buddenhagen Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20230505155244.2312199-5-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 42 ++++++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 20 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index a1838130c830..670572c9a8cc 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -33,6 +33,25 @@ static int fill_silence_frames(struct snd_pcm_substream *substream, snd_pcm_uframes_t off, snd_pcm_uframes_t frames); + +static inline void update_silence_vars(struct snd_pcm_runtime *runtime, + snd_pcm_uframes_t ptr, + snd_pcm_uframes_t new_ptr) +{ + snd_pcm_sframes_t delta; + + delta = new_ptr - ptr; + if (delta == 0) + return; + if (delta < 0) + delta += runtime->boundary; + if ((snd_pcm_uframes_t)delta < runtime->silence_filled) + runtime->silence_filled -= delta; + else + runtime->silence_filled = 0; + runtime->silence_start = new_ptr; +} + /* * fill ring buffer with silence * runtime->silence_start: starting pointer to silence area @@ -49,18 +68,9 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram int err; if (runtime->silence_size < runtime->boundary) { - snd_pcm_sframes_t noise_dist, n; + snd_pcm_sframes_t noise_dist; snd_pcm_uframes_t appl_ptr = READ_ONCE(runtime->control->appl_ptr); - if (runtime->silence_start != appl_ptr) { - n = appl_ptr - runtime->silence_start; - if (n < 0) - n += runtime->boundary; - if ((snd_pcm_uframes_t)n < runtime->silence_filled) - runtime->silence_filled -= n; - else - runtime->silence_filled = 0; - runtime->silence_start = appl_ptr; - } + update_silence_vars(runtime, runtime->silence_start, appl_ptr); /* initialization outside pointer updates */ if (new_hw_ptr == ULONG_MAX) new_hw_ptr = runtime->status->hw_ptr; @@ -87,15 +97,7 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram runtime->silence_filled = avail > 0 ? avail : 0; runtime->silence_start = runtime->status->hw_ptr; } else { - ofs = runtime->status->hw_ptr; - frames = new_hw_ptr - ofs; - if ((snd_pcm_sframes_t)frames < 0) - frames += runtime->boundary; - runtime->silence_filled -= frames; - if ((snd_pcm_sframes_t)runtime->silence_filled < 0) { - runtime->silence_filled = 0; - } - runtime->silence_start = new_hw_ptr; + update_silence_vars(runtime, runtime->status->hw_ptr, new_hw_ptr); } frames = runtime->buffer_size - runtime->silence_filled; } -- GitLab From 6ffa6f397e80bc196ed554e4dabfe43ecc0fe7c1 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Fri, 5 May 2023 17:52:43 +0200 Subject: [PATCH 4569/5631] ALSA: pcm: simplify top-up mode init in snd_pcm_playback_silence() Inline the remaining call of snd_pcm_playback_hw_avail(). This makes the top-up branch more congruent with the thresholded one, and allows simplifying the handling of the corner cases. Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230505155244.2312199-6-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 670572c9a8cc..17fc80a654be 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -90,15 +90,32 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram * This filling mode aims at free-running mode (used for example by dmix), * which doesn't update the application pointer. */ - if (new_hw_ptr == ULONG_MAX) { /* initialization */ - snd_pcm_sframes_t avail = snd_pcm_playback_hw_avail(runtime); - if (avail > runtime->buffer_size) - avail = runtime->buffer_size; - runtime->silence_filled = avail > 0 ? avail : 0; - runtime->silence_start = runtime->status->hw_ptr; + snd_pcm_uframes_t hw_ptr = runtime->status->hw_ptr; + if (new_hw_ptr == ULONG_MAX) { + /* + * Initialization, fill the whole unused buffer with silence. + * + * Usually, this is entered while stopped, before data is queued, + * so both pointers are expected to be zero. + */ + snd_pcm_sframes_t avail = runtime->control->appl_ptr - hw_ptr; + if (avail < 0) + avail += runtime->boundary; + /* + * In free-running mode, appl_ptr will be zero even while running, + * so we end up with a huge number. There is no useful way to + * handle this, so we just clear the whole buffer. + */ + runtime->silence_filled = avail > runtime->buffer_size ? 0 : avail; + runtime->silence_start = hw_ptr; } else { - update_silence_vars(runtime, runtime->status->hw_ptr, new_hw_ptr); + /* Silence the just played area immediately */ + update_silence_vars(runtime, hw_ptr, new_hw_ptr); } + /* + * In this mode, silence_filled actually includes the valid + * sample data from the user. + */ frames = runtime->buffer_size - runtime->silence_filled; } if (snd_BUG_ON(frames > runtime->buffer_size)) -- GitLab From ee2dd703470242f1672403e83f827391afeca808 Mon Sep 17 00:00:00 2001 From: Oswald Buddenhagen Date: Fri, 5 May 2023 17:52:44 +0200 Subject: [PATCH 4570/5631] ALSA: pcm: use exit controlled loop in snd_pcm_playback_silence() We already know that `frames` is greater than zero, because we just checked it. So we don't need to check the loop condition on the first iteration. Signed-off-by: Oswald Buddenhagen Link: https://lore.kernel.org/r/20230505155244.2312199-7-oswald.buddenhagen@gmx.de Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 17fc80a654be..9c121a921b04 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -123,14 +123,14 @@ void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_ufram if (frames == 0) return; ofs = (runtime->silence_start + runtime->silence_filled) % runtime->buffer_size; - while (frames > 0) { + do { transfer = ofs + frames > runtime->buffer_size ? runtime->buffer_size - ofs : frames; err = fill_silence_frames(substream, ofs, transfer); snd_BUG_ON(err < 0); runtime->silence_filled += transfer; frames -= transfer; ofs = 0; - } + } while (frames > 0); snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); } -- GitLab From ecc68ee216c6c5b2f84915e1441adf436f1b019b Mon Sep 17 00:00:00 2001 From: Dmitrii Dolgov <9erthalion6@gmail.com> Date: Wed, 12 Apr 2023 20:23:16 +0200 Subject: [PATCH 4571/5631] perf stat: Separate bperf from bpf_profiler It seems that perf stat -b doesn't produce any results: $ perf stat -e cycles -b 4 -I 10000 -vvv Control descriptor is not initialized cycles: 0 0 0 time counts unit events 10.007641640 cycles Looks like this happens because fentry/fexit progs are getting loaded, but the corresponding perf event is not enabled and not added into the events bpf map. I think there is some mixing up between two type of bpf support, one for bperf and one for bpf_profiler. Both are identified via evsel__is_bpf, based on which perf events are enabled, but for the latter (bpf_profiler) a perf event is required. Using evsel__is_bperf to check only bperf produces expected results: $ perf stat -e cycles -b 4 -I 10000 -vvv Control descriptor is not initialized ------------------------------------------------------------ perf_event_attr: size 136 sample_type IDENTIFIER read_format TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING disabled 1 exclude_guest 1 ------------------------------------------------------------ sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8 = 3 ------------------------------------------------------------ [...perf_event_attr for other CPUs...] ------------------------------------------------------------ cycles: 309426 169009 169009 time counts unit events 10.010091271 309426 cycles The final numbers correspond (at least in the level of magnitude) to the same metric obtained via bpftool. Fixes: 112cb56164bc2108 ("perf stat: Introduce config stat.bpf-counter-events") Reviewed-by: Song Liu Signed-off-by: Dmitrii Dolgov <9erthalion6@gmail.com> Tested-by: Song Liu Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Song Liu Link: https://lore.kernel.org/r/20230412182316.11628-1-9erthalion6@gmail.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 4 ++-- tools/perf/util/evsel.h | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index be9677aa642f..cc9fa48d636f 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -712,7 +712,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) counter->reset_group = false; if (bpf_counter__load(counter, &target)) return -1; - if (!evsel__is_bpf(counter)) + if (!(evsel__is_bperf(counter))) all_counters_use_bpf = false; } @@ -728,7 +728,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx) if (counter->reset_group || counter->errored) continue; - if (evsel__is_bpf(counter)) + if (evsel__is_bperf(counter)) continue; try_again: if (create_perf_stat_counter(counter, &stat_config, &target, diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 35805dcdb1b9..d575390d80bc 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -269,6 +269,11 @@ static inline bool evsel__is_bpf(struct evsel *evsel) return evsel->bpf_counter_ops != NULL; } +static inline bool evsel__is_bperf(struct evsel *evsel) +{ + return evsel->bpf_counter_ops != NULL && list_empty(&evsel->bpf_counter_list); +} + #define EVSEL__MAX_ALIASES 8 extern const char *const evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES]; -- GitLab From a887466562b425bd6183bf75b523c1477c9fd22d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 4 May 2023 19:03:51 -0300 Subject: [PATCH 4572/5631] perf bpf skels: Stop using vmlinux.h generated from BTF, use subset of used structs + CO-RE Linus reported a build break due to using a vmlinux without a BTF elf section to generate the vmlinux.h header with bpftool for use in the BPF tools in tools/perf/util/bpf_skel/*.bpf.c. Instead add a vmlinux.h file with the structs needed with the fields the tools need, marking the structs with __attribute__((preserve_access_index)), so that libbpf's CO-RE code can fixup the struct field offsets. In some cases the vmlinux.h file that was being generated by bpftool from the kernel BTF information was not needed at all, just including linux/bpf.h, sometimes linux/perf_event.h was enough as non-UAPI types were not being used. To keep te patch small, include those UAPI headers from the trimmed down vmlinux.h file, that then provides the tools with just the structs and the subset of its fields needed for them. Testing it: # perf lock contention -b find / > /dev/null ^C contended total wait max wait avg wait type caller 7 53.59 us 10.86 us 7.66 us rwlock:R start_this_handle+0xa0 2 30.35 us 21.99 us 15.17 us rwsem:R iterate_dir+0x52 1 9.04 us 9.04 us 9.04 us rwlock:W start_this_handle+0x291 1 8.73 us 8.73 us 8.73 us spinlock raw_spin_rq_lock_nested+0x1e # # perf lock contention -abl find / > /dev/null ^C contended total wait max wait avg wait address symbol 1 262.96 ms 262.96 ms 262.96 ms ffff8e67502d0170 (mutex) 12 244.24 us 39.91 us 20.35 us ffff8e6af56f8070 mmap_lock (rwsem) 7 30.28 us 6.85 us 4.33 us ffff8e6c865f1d40 rq_lock (spinlock) 3 7.42 us 4.03 us 2.47 us ffff8e6c864b1d40 rq_lock (spinlock) 2 3.72 us 2.19 us 1.86 us ffff8e6c86571d40 rq_lock (spinlock) 1 2.42 us 2.42 us 2.42 us ffff8e6c86471d40 rq_lock (spinlock) 4 2.11 us 559 ns 527 ns ffffffff9a146c80 rcu_state (spinlock) 3 1.45 us 818 ns 482 ns ffff8e674ae8384c (rwlock) 1 870 ns 870 ns 870 ns ffff8e68456ee060 (rwlock) 1 663 ns 663 ns 663 ns ffff8e6c864f1d40 rq_lock (spinlock) 1 573 ns 573 ns 573 ns ffff8e6c86531d40 rq_lock (spinlock) 1 472 ns 472 ns 472 ns ffff8e6c86431740 (spinlock) 1 397 ns 397 ns 397 ns ffff8e67413a4f04 (spinlock) # # perf test offcpu 95: perf record offcpu profiling tests : Ok # # perf kwork latency --use-bpf Starting trace, Hit to stop and report ^C Kwork Name | Cpu | Avg delay | Count | Max delay | Max delay start | Max delay end | -------------------------------------------------------------------------------------------------------------------------------- (w)flush_memcg_stats_dwork | 0000 | 1056.212 ms | 2 | 2112.345 ms | 550113.229573 s | 550115.341919 s | (w)toggle_allocation_gate | 0000 | 10.144 ms | 62 | 416.389 ms | 550113.453518 s | 550113.869907 s | (w)0xffff8e6748e28080 | 0002 | 0.623 ms | 1 | 0.623 ms | 550110.989841 s | 550110.990464 s | (w)vmstat_shepherd | 0000 | 0.586 ms | 10 | 2.828 ms | 550111.971536 s | 550111.974364 s | (w)vmstat_update | 0007 | 0.363 ms | 5 | 1.634 ms | 550113.222520 s | 550113.224154 s | (w)vmstat_update | 0000 | 0.324 ms | 10 | 2.827 ms | 550111.971526 s | 550111.974354 s | (w)0xffff8e674c5f4a58 | 0002 | 0.102 ms | 5 | 0.134 ms | 550110.989839 s | 550110.989972 s | (w)psi_avgs_work | 0001 | 0.086 ms | 3 | 0.107 ms | 550114.957852 s | 550114.957959 s | (w)psi_avgs_work | 0000 | 0.079 ms | 5 | 0.100 ms | 550118.605668 s | 550118.605768 s | (w)kfree_rcu_monitor | 0006 | 0.079 ms | 1 | 0.079 ms | 550110.925821 s | 550110.925900 s | (w)psi_avgs_work | 0004 | 0.079 ms | 1 | 0.079 ms | 550109.581835 s | 550109.581914 s | (w)psi_avgs_work | 0001 | 0.078 ms | 1 | 0.078 ms | 550109.197809 s | 550109.197887 s | (w)psi_avgs_work | 0002 | 0.077 ms | 5 | 0.086 ms | 550110.669819 s | 550110.669905 s | # strace -e bpf -o perf-stat-bpf-counters.output perf stat -e cycles --bpf-counters sleep 1 Performance counter stats for 'sleep 1': 6,197,983 cycles 1.003922848 seconds time elapsed 0.000000000 seconds user 0.002032000 seconds sys # head -7 perf-stat-bpf-counters.output bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/perf_attr_map", bpf_fd=0, file_flags=0}, 16) = 3 bpf(BPF_OBJ_GET_INFO_BY_FD, {info={bpf_fd=3, info_len=88, info=0x7ffcead64990}}, 16) = 0 bpf(BPF_MAP_LOOKUP_ELEM, {map_fd=3, key=0x24129e0, value=0x7ffcead65a48, flags=BPF_ANY}, 32) = 0 bpf(BPF_LINK_GET_FD_BY_ID, {link_id=1252}, 12) = -1 ENOENT (No such file or directory) bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_SOCKET_FILTER, insn_cnt=2, insns=0x7ffcead65780, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(0, 0, 0), prog_flags=0, prog_name="", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS, prog_btf_fd=0, func_info_rec_size=0, +func_info=NULL, func_info_cnt=0, line_info_rec_size=0, line_info=NULL, line_info_cnt=0, attach_btf_id=0, attach_prog_fd=0}, 116) = 4 bpf(BPF_PROG_LOAD, {prog_type=BPF_PROG_TYPE_SOCKET_FILTER, insn_cnt=2, insns=0x7ffcead65920, license="GPL", log_level=0, log_size=0, log_buf=NULL, kern_version=KERNEL_VERSION(0, 0, 0), prog_flags=0, prog_name="", prog_ifindex=0, expected_attach_type=BPF_CGROUP_INET_INGRESS, prog_btf_fd=0, func_info_rec_size=0, +func_info=NULL, func_info_cnt=0, line_info_rec_size=0, line_info=NULL, line_info_cnt=0, attach_btf_id=0, attach_prog_fd=0, fd_array=NULL}, 128) = 4 bpf(BPF_BTF_LOAD, {btf="\237\353\1\0\30\0\0\0\0\0\0\0\20\0\0\0\20\0\0\0\5\0\0\0\1\0\0\0\0\0\0\1"..., btf_log_buf=NULL, btf_size=45, btf_log_size=0, btf_log_level=0}, 28) = 4 # Reported-by: Linus Torvalds Suggested-by: Andrii Nakryiko Tested-by: Namhyung Kim Tested-by: Song Liu Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Ian Rogers Cc: Jiri Olsa Co-developed-by: Jiri Olsa Link: https://lore.kernel.org/lkml/ZFU1PJrn8YtHIqno@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 20 +--- tools/perf/util/bpf_skel/.gitignore | 1 - tools/perf/util/bpf_skel/vmlinux.h | 173 ++++++++++++++++++++++++++++ 3 files changed, 174 insertions(+), 20 deletions(-) create mode 100644 tools/perf/util/bpf_skel/vmlinux.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 48aba186ceb5..61c33d100b2b 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1063,25 +1063,7 @@ $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap -VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ - $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ - ../../vmlinux \ - /sys/kernel/btf/vmlinux \ - /boot/vmlinux-$(shell uname -r) -VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) - -$(SKEL_OUT)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) -ifeq ($(VMLINUX_H),) - $(QUIET_GEN)$(BPFTOOL) btf dump file $< format c > $@ || \ - (echo "Failure to generate vmlinux.h needed for the recommended BPF skeleton support." && \ - echo "To disable this use the build option NO_BPF_SKEL=1." && \ - echo "Alternatively point at a pre-generated vmlinux.h with VMLINUX_H=." && \ - false) -else - $(Q)cp "$(VMLINUX_H)" $@ -endif - -$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) $(SKEL_OUT)/vmlinux.h | $(SKEL_TMP_OUT) +$(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ diff --git a/tools/perf/util/bpf_skel/.gitignore b/tools/perf/util/bpf_skel/.gitignore index cd01455e1b53..7a1c832825de 100644 --- a/tools/perf/util/bpf_skel/.gitignore +++ b/tools/perf/util/bpf_skel/.gitignore @@ -1,4 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only .tmp *.skel.h -vmlinux.h diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h new file mode 100644 index 000000000000..449b1ea91fc4 --- /dev/null +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -0,0 +1,173 @@ +#ifndef __VMLINUX_H +#define __VMLINUX_H + +#include +#include +#include +#include + +// non-UAPI kernel data structures, used in the .bpf.c BPF tool component. + +// Just the fields used in these tools preserving the access index so that +// libbpf can fixup offsets with the ones used in the kernel when loading the +// BPF bytecode, if they differ from what is used here. + +typedef __u8 u8; +typedef __u32 u32; +typedef __u64 u64; +typedef __s64 s64; + +typedef int pid_t; + +enum cgroup_subsys_id { + perf_event_cgrp_id = 8, +}; + +enum { + HI_SOFTIRQ = 0, + TIMER_SOFTIRQ, + NET_TX_SOFTIRQ, + NET_RX_SOFTIRQ, + BLOCK_SOFTIRQ, + IRQ_POLL_SOFTIRQ, + TASKLET_SOFTIRQ, + SCHED_SOFTIRQ, + HRTIMER_SOFTIRQ, + RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ + + NR_SOFTIRQS +}; + +typedef struct { + s64 counter; +} __attribute__((preserve_access_index)) atomic64_t; + +typedef atomic64_t atomic_long_t; + +struct raw_spinlock { + int rawlock; +} __attribute__((preserve_access_index)); + +typedef struct raw_spinlock raw_spinlock_t; + +typedef struct { + struct raw_spinlock rlock; +} __attribute__((preserve_access_index)) spinlock_t; + +struct sighand_struct { + spinlock_t siglock; +} __attribute__((preserve_access_index)); + +struct rw_semaphore { + atomic_long_t owner; +} __attribute__((preserve_access_index)); + +struct mutex { + atomic_long_t owner; +} __attribute__((preserve_access_index)); + +struct kernfs_node { + u64 id; +} __attribute__((preserve_access_index)); + +struct cgroup { + struct kernfs_node *kn; + int level; +} __attribute__((preserve_access_index)); + +struct cgroup_subsys_state { + struct cgroup *cgroup; +} __attribute__((preserve_access_index)); + +struct css_set { + struct cgroup_subsys_state *subsys[13]; + struct cgroup *dfl_cgrp; +} __attribute__((preserve_access_index)); + +struct mm_struct { + struct rw_semaphore mmap_lock; +} __attribute__((preserve_access_index)); + +struct task_struct { + unsigned int flags; + struct mm_struct *mm; + pid_t pid; + pid_t tgid; + char comm[16]; + struct sighand_struct *sighand; + struct css_set *cgroups; +} __attribute__((preserve_access_index)); + +struct trace_entry { + short unsigned int type; + unsigned char flags; + unsigned char preempt_count; + int pid; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_irq_handler_entry { + struct trace_entry ent; + int irq; + u32 __data_loc_name; + char __data[]; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_irq_handler_exit { + struct trace_entry ent; + int irq; + int ret; + char __data[]; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_softirq { + struct trace_entry ent; + unsigned int vec; + char __data[]; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_workqueue_execute_start { + struct trace_entry ent; + void *work; + void *function; + char __data[]; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_workqueue_execute_end { + struct trace_entry ent; + void *work; + void *function; + char __data[]; +} __attribute__((preserve_access_index)); + +struct trace_event_raw_workqueue_activate_work { + struct trace_entry ent; + void *work; + char __data[]; +} __attribute__((preserve_access_index)); + +struct perf_sample_data { + u64 addr; + u64 period; + union perf_sample_weight weight; + u64 txn; + union perf_mem_data_src data_src; + u64 ip; + struct { + u32 pid; + u32 tid; + } tid_entry; + u64 time; + u64 id; + struct { + u32 cpu; + } cpu_entry; + u64 phys_addr; + u64 data_page_size; + u64 code_page_size; +} __attribute__((__aligned__(64))) __attribute__((preserve_access_index)); + +struct bpf_perf_event_data_kern { + struct perf_sample_data *data; + struct perf_event *event; +} __attribute__((preserve_access_index)); +#endif // __VMLINUX_H -- GitLab From 6c73f819b6b6d6f052e8dbe3f66f0693554ddf48 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 5 May 2023 13:41:19 -0700 Subject: [PATCH 4573/5631] perf metrics: Fix SEGV with --for-each-cgroup Ensure the metric threshold is copied correctly or else a use of uninitialized memory happens. Fixes: d0a3052f6faefffc ("perf metric: Compute and print threshold values") Reported-by: Namhyung Kim Signed-off-by: Ian Rogers Tested-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230505204119.3443491-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 4b9a16291b96..c566c6859302 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1730,6 +1730,7 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp, return -ENOMEM; new_expr->metric_expr = old_expr->metric_expr; + new_expr->metric_threshold = old_expr->metric_threshold; new_expr->metric_name = strdup(old_expr->metric_name); if (!new_expr->metric_name) return -ENOMEM; -- GitLab From 319050d4302ee9b216fb8cea847a9c4427628a98 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 4 May 2023 13:43:33 -0400 Subject: [PATCH 4574/5631] SUNRPC: Fix error handling in svc_setup_socket() Dan points out that sock_alloc_file() releases @sock on error, but so do all of svc_setup_socket's callers, resulting in a double- release if sock_alloc_file() returns an error. Rather than allocating a struct file for all new sockets, allocate one only for sockets created during a TCP accept. For the moment, those are the only ones that will ever be used with RPC-with-TLS. Reported-by: Dan Carpenter Fixes: ae0d77708aae ("SUNRPC: Ensure server-side sockets have a sock->file") Signed-off-by: Chuck Lever --- net/sunrpc/svcsock.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a51c9b989d58..9989194446a5 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -895,6 +895,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } + if (IS_ERR(sock_alloc_file(newsock, O_NONBLOCK, NULL))) + return NULL; + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin); @@ -935,7 +938,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) return &newsvsk->sk_xprt; failed: - sock_release(newsock); + sockfd_put(newsock); return NULL; } @@ -1430,7 +1433,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, struct socket *sock, int flags) { - struct file *filp = NULL; struct svc_sock *svsk; struct sock *inet; int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); @@ -1439,14 +1441,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, if (!svsk) return ERR_PTR(-ENOMEM); - if (!sock->file) { - filp = sock_alloc_file(sock, O_NONBLOCK, NULL); - if (IS_ERR(filp)) { - kfree(svsk); - return ERR_CAST(filp); - } - } - inet = sock->sk; if (pmap_register) { @@ -1456,8 +1450,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, inet->sk_protocol, ntohs(inet_sk(inet)->inet_sport)); if (err < 0) { - if (filp) - fput(filp); kfree(svsk); return ERR_PTR(err); } -- GitLab From c12753d5fa3eab636b5ced91d6a2155173c11527 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Sat, 6 May 2023 00:39:09 +0200 Subject: [PATCH 4575/5631] s390: remove the unneeded select GCC12_NO_ARRAY_BOUNDS Commit 0da6e5fd6c37 ("gcc: disable '-Warray-bounds' for gcc-13 too") makes config GCC11_NO_ARRAY_BOUNDS to be for disabling -Warray-bounds in any gcc version 11 and upwards, and with that, removes the GCC12_NO_ARRAY_BOUNDS config as it is now covered by the semantics of GCC11_NO_ARRAY_BOUNDS. As GCC11_NO_ARRAY_BOUNDS is yes by default, there is no need for the s390 architecture to explicitly select GCC11_NO_ARRAY_BOUNDS. Hence, the select GCC12_NO_ARRAY_BOUNDS in arch/s390/Kconfig can simply be dropped. Remove the unneeded "select GCC12_NO_ARRAY_BOUNDS". Signed-off-by: Lukas Bulwahn Signed-off-by: Linus Torvalds --- arch/s390/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index beb62f744c61..db20c1589a98 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -133,7 +133,6 @@ config S390 select DYNAMIC_FTRACE if FUNCTION_TRACER select FUNCTION_ALIGNMENT_8B if CC_IS_GCC select FUNCTION_ALIGNMENT_16B if !CC_IS_GCC - select GCC12_NO_ARRAY_BOUNDS select GENERIC_ALLOCATOR select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES -- GitLab From 38a55db9877cae9aa9cc53bb0464b7434fb03e75 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 6 May 2023 17:04:14 +0100 Subject: [PATCH 4576/5631] filemap: Handle error return from __filemap_get_folio() Smatch reports that filemap_fault() was missed in the conversion of __filemap_get_folio() error returns from NULL to ERR_PTR. Fixes: 66dabbb65d67 ("mm: return an ERR_PTR from __filemap_get_folio") Reported-by: Dan Carpenter Reported-by: syzbot+48011b86c8ea329af1b9@syzkaller.appspotmail.com Reported-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/filemap.c b/mm/filemap.c index a34abfe8c654..b4c9bd368b7e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3378,7 +3378,7 @@ vm_fault_t filemap_fault(struct vm_fault *vmf) * re-find the vma and come back and find our hopefully still populated * page. */ - if (folio) + if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); -- GitLab From 29417d292bd0fa174d20360326abaf6444a23c3b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Sun, 30 Apr 2023 21:19:17 +0100 Subject: [PATCH 4577/5631] mm/mmap/vma_merge: always check invariants We may still have inconsistent input parameters even if we choose not to merge and the vma_merge() invariant checks are useful for checking this with no production runtime cost (these are only relevant when CONFIG_DEBUG_VM is specified). Therefore, perform these checks regardless of whether we merge. This is relevant, as a recent issue (addressed in commit "mm/mempolicy: Correctly update prev when policy is equal on mbind") in the mbind logic was only picked up in the 6.2.y stable branch where these assertions are performed prior to determining mergeability. Had this remained the same in mainline this issue may have been picked up faster, so moving forward let's always check them. Link: https://lkml.kernel.org/r/df548a6ae3fa135eec3b446eb3dae8eb4227da97.1682885809.git.lstoakes@gmail.com Signed-off-by: Lorenzo Stoakes Acked-by: Vlastimil Babka Reviewed-by: David Hildenbrand Reviewed-by: Liam R. Howlett Signed-off-by: Andrew Morton --- mm/mmap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 5522130ae606..13678edaa22c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -960,17 +960,17 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, merge_next = true; } + /* Verify some invariant that must be enforced by the caller. */ + VM_WARN_ON(prev && addr <= prev->vm_start); + VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); + VM_WARN_ON(addr >= end); + if (!merge_prev && !merge_next) return NULL; /* Not mergeable. */ res = vma = prev; remove = remove2 = adjust = NULL; - /* Verify some invariant that must be enforced by the caller. */ - VM_WARN_ON(prev && addr <= prev->vm_start); - VM_WARN_ON(curr && (addr != curr->vm_start || end > curr->vm_end)); - VM_WARN_ON(addr >= end); - /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { -- GitLab From a6a491c048882e7e424d407d32cba0b52d9ef2bf Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Mon, 1 May 2023 04:30:46 +0900 Subject: [PATCH 4578/5631] nilfs2: fix infinite loop in nilfs_mdt_get_block() If the disk image that nilfs2 mounts is corrupted and a virtual block address obtained by block lookup for a metadata file is invalid, nilfs_bmap_lookup_at_level() may return the same internal return code as -ENOENT, meaning the block does not exist in the metadata file. This duplication of return codes confuses nilfs_mdt_get_block(), causing it to read and create a metadata block indefinitely. In particular, if this happens to the inode metadata file, ifile, semaphore i_rwsem can be left held, causing task hangs in lock_mount. Fix this issue by making nilfs_bmap_lookup_at_level() treat virtual block address translation failures with -ENOENT as metadata corruption instead of returning the error code. Link: https://lkml.kernel.org/r/20230430193046.6769-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+221d75710bde87fa0e97@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=221d75710bde87fa0e97 Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/bmap.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 798a2c1b38c6..7a8f166f2c8d 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -67,20 +67,28 @@ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp); - if (ret < 0) { - ret = nilfs_bmap_convert_error(bmap, __func__, ret); + if (ret < 0) goto out; - } + if (NILFS_BMAP_USE_VBN(bmap)) { ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp, &blocknr); if (!ret) *ptrp = blocknr; + else if (ret == -ENOENT) { + /* + * If there was no valid entry in DAT for the block + * address obtained by b_ops->bop_lookup, then pass + * internal code -EINVAL to nilfs_bmap_convert_error + * to treat it as metadata corruption. + */ + ret = -EINVAL; + } } out: up_read(&bmap->b_sem); - return ret; + return nilfs_bmap_convert_error(bmap, __func__, ret); } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, -- GitLab From d824ec2a154677f63c56cc71ffe4578274f6e32e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 28 Apr 2023 14:41:40 +0200 Subject: [PATCH 4579/5631] mm: do not reclaim private data from pinned page If the page is pinned, there's no point in trying to reclaim it. Furthermore if the page is from the page cache we don't want to reclaim fs-private data from the page because the pinning process may be writing to the page at any time and reclaiming fs private info on a dirty page can upset the filesystem (see link below). Link: https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz Link: https://lkml.kernel.org/r/20230428124140.30166-1-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Lorenzo Stoakes Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Acked-by: David Hildenbrand Acked-by: Peter Xu Cc: Signed-off-by: Andrew Morton --- mm/vmscan.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/mm/vmscan.c b/mm/vmscan.c index 5bde07409303..d257916f39e5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1967,6 +1967,16 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, } } + /* + * Folio is unmapped now so it cannot be newly pinned anymore. + * No point in trying to reclaim folio if it is pinned. + * Furthermore we don't want to reclaim underlying fs metadata + * if the folio is pinned and thus potentially modified by the + * pinning process as that may upset the filesystem. + */ + if (folio_maybe_dma_pinned(folio)) + goto activate_locked; + mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* -- GitLab From 28a65b49eb53e172d23567005465019658bfdb4d Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 27 Apr 2023 10:15:26 +0900 Subject: [PATCH 4580/5631] nilfs2: do not write dirty data after degenerating to read-only According to syzbot's report, mark_buffer_dirty() called from nilfs_segctor_do_construct() outputs a warning with some patterns after nilfs2 detects metadata corruption and degrades to read-only mode. After such read-only degeneration, page cache data may be cleared through nilfs_clear_dirty_page() which may also clear the uptodate flag for their buffer heads. However, even after the degeneration, log writes are still performed by unmount processing etc., which causes mark_buffer_dirty() to be called for buffer heads without the "uptodate" flag and causes the warning. Since any writes should not be done to a read-only file system in the first place, this fixes the warning in mark_buffer_dirty() by letting nilfs_segctor_do_construct() abort early if in read-only mode. This also changes the retry check of nilfs_segctor_write_out() to avoid unnecessary log write retries if it detects -EROFS that nilfs_segctor_do_construct() returned. Link: https://lkml.kernel.org/r/20230427011526.13457-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+2af3bc9585be7f23f290@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=2af3bc9585be7f23f290 Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 228659612c0d..ac949fd7603f 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2041,6 +2041,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; + if (sb_rdonly(sci->sc_super)) + return -EROFS; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; @@ -2724,7 +2727,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) flush_work(&sci->sc_iput_work); - } while (ret && retrycount-- > 0); + } while (ret && ret != -EROFS && retrycount-- > 0); } /** -- GitLab From 58f5f6698a72a8af5d7bfc5f49b6df60f378f167 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 3 May 2023 17:45:26 +0200 Subject: [PATCH 4581/5631] afs: fix the afs_dir_get_folio return value Keep returning NULL on failure instead of letting an ERR_PTR escape to callers that don't expect it. Link: https://lkml.kernel.org/r/20230503154526.1223095-2-hch@lst.de Fixes: 66dabbb65d67 ("mm: return an ERR_PTR from __filemap_get_folio") Signed-off-by: Christoph Hellwig Reported-by: Jan Kara Reviewed-by: Jan Kara Reviewed-by: David Howells Tested-by: David Howells Cc: Marc Dionne Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- fs/afs/dir_edit.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index f0eddccbdd95..e2fa577b66fe 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -115,11 +115,12 @@ static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index) folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping->gfp_mask); - if (IS_ERR(folio)) + if (IS_ERR(folio)) { clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags); - else if (folio && !folio_test_private(folio)) + return NULL; + } + if (!folio_test_private(folio)) folio_attach_private(folio, (void *)1); - return folio; } -- GitLab From 994e2419f1e77724479f0ffd5ad4eeae060dec95 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 6 May 2023 10:16:19 -0700 Subject: [PATCH 4582/5631] nfs: fix mis-merged __filemap_get_folio() error check Fix another case of an incorrect check for the returned 'folio' value from __filemap_get_folio(). The failure case used to return NULL, but was changed by commit 66dabbb65d67 ("mm: return an ERR_PTR from __filemap_get_folio"). But in the meantime, commit ec108d3cc766 ("NFS: Convert readdir page array functions to use a folio") added a new user of that function. And my merge of the two did not fix this up correctly. The ext4 merge had the same issue, but that one had been caught in linux-next and got properly fixed while merging. Fixes: 0127f25b5dfc ("Merge tag 'nfs-for-6.4-1' of git://git.linux-nfs.org/projects/anna/linux-nfs") Cc: Anna Schumaker Cc: Matthew Wilcox Cc: Christoph Hellwig Signed-off-by: Linus Torvalds --- fs/nfs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8257de6dba45..bacad0c57810 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -448,7 +448,7 @@ static struct folio *nfs_readdir_folio_get_next(struct address_space *mapping, folio = __filemap_get_folio(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); - if (!folio) + if (IS_ERR(folio)) return NULL; nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); if (nfs_readdir_folio_last_cookie(folio) != cookie) -- GitLab From 67a540c60c39d052d9599aa9909023152200a707 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:15 -0800 Subject: [PATCH 4583/5631] dmapool: remove checks for dev == NULL dmapool originally tried to support pools without a device because dma_alloc_coherent() supports allocations without a device. But nobody ended up using dma pools without a device, and trying to do so will result in an oops. So remove the checks for pool->dev == NULL since they are unneeded bloat. [kbusch@kernel.org: add check for null dev on create] Link: https://lkml.kernel.org/r/20230126215125.4069751-3-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 45 ++++++++++++++------------------------------- 1 file changed, 14 insertions(+), 31 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index a7eb5d0eb2da..559207e1c333 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -134,6 +134,9 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, size_t allocation; bool empty = false; + if (!dev) + return NULL; + if (align == 0) align = 1; else if (align & (align - 1)) @@ -275,7 +278,7 @@ void dma_pool_destroy(struct dma_pool *pool) mutex_lock(&pools_reg_lock); mutex_lock(&pools_lock); list_del(&pool->pools); - if (pool->dev && list_empty(&pool->dev->dma_pools)) + if (list_empty(&pool->dev->dma_pools)) empty = true; mutex_unlock(&pools_lock); if (empty) @@ -284,12 +287,8 @@ void dma_pool_destroy(struct dma_pool *pool) list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { if (is_page_busy(page)) { - if (pool->dev) - dev_err(pool->dev, "%s %s, %p busy\n", __func__, - pool->name, page->vaddr); - else - pr_err("%s %s, %p busy\n", __func__, - pool->name, page->vaddr); + dev_err(pool->dev, "%s %s, %p busy\n", __func__, + pool->name, page->vaddr); /* leak the still-in-use consistent memory */ list_del(&page->page_list); kfree(page); @@ -351,12 +350,8 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, for (i = sizeof(page->offset); i < pool->size; i++) { if (data[i] == POOL_POISON_FREED) continue; - if (pool->dev) - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); - else - pr_err("%s %s, %p (corrupted)\n", - __func__, pool->name, retval); + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); /* * Dump the first 4 bytes even if they are not @@ -411,12 +406,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) page = pool_find_page(pool, dma); if (!page) { spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); - else - pr_err("%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", + __func__, pool->name, vaddr, &dma); return; } @@ -426,12 +417,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) #ifdef DMAPOOL_DEBUG if ((dma - page->dma) != offset) { spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); - else - pr_err("%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); return; } { @@ -442,12 +429,8 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) continue; } spin_unlock_irqrestore(&pool->lock, flags); - if (pool->dev) - dev_err(pool->dev, "%s %s, dma %pad already free\n", - __func__, pool->name, &dma); - else - pr_err("%s %s, dma %pad already free\n", - __func__, pool->name, &dma); + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); return; } } -- GitLab From 08cc96c894848bcd1d15a79b15c56a8bb4f07ff5 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:16 -0800 Subject: [PATCH 4584/5631] dmapool: use sysfs_emit() instead of scnprintf() Use sysfs_emit instead of scnprintf, snprintf or sprintf. Link: https://lkml.kernel.org/r/20230126215125.4069751-4-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 559207e1c333..20616b760bb9 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -64,18 +64,11 @@ static DEFINE_MUTEX(pools_reg_lock); static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned temp; - unsigned size; - char *next; + int size; struct dma_page *page; struct dma_pool *pool; - next = buf; - size = PAGE_SIZE; - - temp = scnprintf(next, size, "poolinfo - 0.1\n"); - size -= temp; - next += temp; + size = sysfs_emit(buf, "poolinfo - 0.1\n"); mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { @@ -90,16 +83,14 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ - temp = scnprintf(next, size, "%-16s %4u %4zu %4zu %2u\n", - pool->name, blocks, - pages * (pool->allocation / pool->size), - pool->size, pages); - size -= temp; - next += temp; + size += sysfs_emit_at(buf, size, "%-16s %4u %4zu %4zu %2u\n", + pool->name, blocks, + pages * (pool->allocation / pool->size), + pool->size, pages); } mutex_unlock(&pools_lock); - return PAGE_SIZE - size; + return size; } static DEVICE_ATTR_RO(pools); -- GitLab From 790233528d338f1467662761cf1e871086483ab8 Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:17 -0800 Subject: [PATCH 4585/5631] dmapool: cleanup integer types To represent the size of a single allocation, dmapool currently uses 'unsigned int' in some places and 'size_t' in other places. Standardize on 'unsigned int' to reduce overhead, but use 'size_t' when counting all the blocks in the entire pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-5-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 20616b760bb9..ee993bb59fc2 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -43,10 +43,10 @@ struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; - size_t size; struct device *dev; - size_t allocation; - size_t boundary; + unsigned int size; + unsigned int allocation; + unsigned int boundary; char name[32]; struct list_head pools; }; @@ -73,7 +73,7 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { unsigned pages = 0; - unsigned blocks = 0; + size_t blocks = 0; spin_lock_irq(&pool->lock); list_for_each_entry(page, &pool->page_list, page_list) { @@ -83,9 +83,10 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha spin_unlock_irq(&pool->lock); /* per-pool info, no real statistics yet */ - size += sysfs_emit_at(buf, size, "%-16s %4u %4zu %4zu %2u\n", + size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2u\n", pool->name, blocks, - pages * (pool->allocation / pool->size), + (size_t) pages * + (pool->allocation / pool->size), pool->size, pages); } mutex_unlock(&pools_lock); @@ -133,7 +134,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, else if (align & (align - 1)) return NULL; - if (size == 0) + if (size == 0 || size > INT_MAX) return NULL; else if (size < 4) size = 4; @@ -146,6 +147,8 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, else if ((boundary < size) || (boundary & (boundary - 1))) return NULL; + boundary = min(boundary, allocation); + retval = kmalloc(sizeof(*retval), GFP_KERNEL); if (!retval) return retval; @@ -306,7 +309,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, { unsigned long flags; struct dma_page *page; - size_t offset; + unsigned int offset; void *retval; might_alloc(mem_flags); -- GitLab From 290911c56f98ac7af9354108f3d16da5d6c5189c Mon Sep 17 00:00:00 2001 From: Tony Battersby Date: Thu, 26 Jan 2023 13:51:18 -0800 Subject: [PATCH 4586/5631] dmapool: speedup DMAPOOL_DEBUG with init_on_alloc Avoid double-memset of the same allocated memory in dma_pool_alloc() when both DMAPOOL_DEBUG is enabled and init_on_alloc=1. Link: https://lkml.kernel.org/r/20230126215125.4069751-6-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Signed-off-by: Andrew Morton --- mm/dmapool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index ee993bb59fc2..eaed3ffb42aa 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -356,7 +356,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, break; } } - if (!(mem_flags & __GFP_ZERO)) + if (!want_init_on_alloc(mem_flags)) memset(retval, POOL_POISON_ALLOCATED, pool->size); #endif spin_unlock_irqrestore(&pool->lock, flags); -- GitLab From d93e08b7556fcd393b7fd1eb421cb44e5fae314c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:19 -0800 Subject: [PATCH 4587/5631] dmapool: move debug code to own functions Clean up the normal path by moving the debug code outside it. Link: https://lkml.kernel.org/r/20230126215125.4069751-7-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 128 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 77 insertions(+), 51 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index eaed3ffb42aa..30b069e99996 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -96,6 +96,78 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha static DEVICE_ATTR_RO(pools); +#ifdef DMAPOOL_DEBUG +static void pool_check_block(struct dma_pool *pool, void *retval, + unsigned int offset, gfp_t mem_flags) +{ + int i; + u8 *data = retval; + /* page->offset is stored in first 4 bytes */ + for (i = sizeof(offset); i < pool->size; i++) { + if (data[i] == POOL_POISON_FREED) + continue; + dev_err(pool->dev, "%s %s, %p (corrupted)\n", + __func__, pool->name, retval); + + /* + * Dump the first 4 bytes even if they are not + * POOL_POISON_FREED + */ + print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, + data, pool->size, 1); + break; + } + if (!want_init_on_alloc(mem_flags)) + memset(retval, POOL_POISON_ALLOCATED, pool->size); +} + +static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, + void *vaddr, dma_addr_t dma) +{ + unsigned int offset = vaddr - page->vaddr; + unsigned int chain = page->offset; + + if ((dma - page->dma) != offset) { + dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + __func__, pool->name, vaddr, &dma); + return true; + } + + while (chain < pool->allocation) { + if (chain != offset) { + chain = *(int *)(page->vaddr + chain); + continue; + } + dev_err(pool->dev, "%s %s, dma %pad already free\n", + __func__, pool->name, &dma); + return true; + } + memset(vaddr, POOL_POISON_FREED, pool->size); + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ + memset(page->vaddr, POOL_POISON_FREED, pool->allocation); +} +#else +static void pool_check_block(struct dma_pool *pool, void *retval, + unsigned int offset, gfp_t mem_flags) + +{ +} + +static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, + void *vaddr, dma_addr_t dma) +{ + return false; +} + +static void pool_init_page(struct dma_pool *pool, struct dma_page *page) +{ +} +#endif + /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. * @name: name of pool, for diagnostics @@ -223,9 +295,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); if (page->vaddr) { -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif + pool_init_page(pool, page); pool_initialise_page(pool, page); page->in_use = 0; page->offset = 0; @@ -245,9 +315,7 @@ static void pool_free_page(struct dma_pool *pool, struct dma_page *page) { dma_addr_t dma = page->dma; -#ifdef DMAPOOL_DEBUG - memset(page->vaddr, POOL_POISON_FREED, pool->allocation); -#endif + pool_init_page(pool, page); dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); list_del(&page->page_list); kfree(page); @@ -336,29 +404,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, page->offset = *(int *)(page->vaddr + offset); retval = offset + page->vaddr; *handle = offset + page->dma; -#ifdef DMAPOOL_DEBUG - { - int i; - u8 *data = retval; - /* page->offset is stored in first 4 bytes */ - for (i = sizeof(page->offset); i < pool->size; i++) { - if (data[i] == POOL_POISON_FREED) - continue; - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); - - /* - * Dump the first 4 bytes even if they are not - * POOL_POISON_FREED - */ - print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, - data, pool->size, 1); - break; - } - } - if (!want_init_on_alloc(mem_flags)) - memset(retval, POOL_POISON_ALLOCATED, pool->size); -#endif + pool_check_block(pool, retval, offset, mem_flags); spin_unlock_irqrestore(&pool->lock, flags); if (want_init_on_alloc(mem_flags)) @@ -394,7 +440,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { struct dma_page *page; unsigned long flags; - unsigned int offset; spin_lock_irqsave(&pool->lock, flags); page = pool_find_page(pool, dma); @@ -405,35 +450,16 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) return; } - offset = vaddr - page->vaddr; if (want_init_on_free()) memset(vaddr, 0, pool->size); -#ifdef DMAPOOL_DEBUG - if ((dma - page->dma) != offset) { + if (pool_page_err(pool, page, vaddr, dma)) { spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", - __func__, pool->name, vaddr, &dma); return; } - { - unsigned int chain = page->offset; - while (chain < pool->allocation) { - if (chain != offset) { - chain = *(int *)(page->vaddr + chain); - continue; - } - spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, dma %pad already free\n", - __func__, pool->name, &dma); - return; - } - } - memset(vaddr, POOL_POISON_FREED, pool->size); -#endif page->in_use--; *(int *)vaddr = page->offset; - page->offset = offset; + page->offset = vaddr - page->vaddr; /* * Resist a temptation to do * if (!is_page_busy(page)) pool_free_page(pool, page); -- GitLab From 5407df10e5754b80d43697a75484bacda048fef8 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:20 -0800 Subject: [PATCH 4588/5631] dmapool: rearrange page alloc failure handling Handle the error in a condition so the good path can be in the normal flow. Link: https://lkml.kernel.org/r/20230126215125.4069751-8-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 30b069e99996..900f2afa363a 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -292,17 +292,19 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) page = kmalloc(sizeof(*page), mem_flags); if (!page) return NULL; + page->vaddr = dma_alloc_coherent(pool->dev, pool->allocation, &page->dma, mem_flags); - if (page->vaddr) { - pool_init_page(pool, page); - pool_initialise_page(pool, page); - page->in_use = 0; - page->offset = 0; - } else { + if (!page->vaddr) { kfree(page); - page = NULL; + return NULL; } + + pool_init_page(pool, page); + pool_initialise_page(pool, page); + page->in_use = 0; + page->offset = 0; + return page; } -- GitLab From f0bccea6bc0caa0db9c68d28123f242a6295c5dd Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:21 -0800 Subject: [PATCH 4589/5631] dmapool: consolidate page initialization Various fields of the dma pool are set in different places. Move it all to one function. Link: https://lkml.kernel.org/r/20230126215125.4069751-9-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 900f2afa363a..9e98065a68b1 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -274,6 +274,9 @@ static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) unsigned int offset = 0; unsigned int next_boundary = pool->boundary; + pool_init_page(pool, page); + page->in_use = 0; + page->offset = 0; do { unsigned int next = offset + pool->size; if (unlikely((next + pool->size) >= next_boundary)) { @@ -300,11 +303,7 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) return NULL; } - pool_init_page(pool, page); pool_initialise_page(pool, page); - page->in_use = 0; - page->offset = 0; - return page; } -- GitLab From cc669954ab38866c1aba73c27e17bb07bcb4a194 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:22 -0800 Subject: [PATCH 4590/5631] dmapool: simplify freeing The actions for busy and not busy are mostly the same, so combine these and remove the unnecessary function. Also, the pool is about to be freed so there's no need to poison the page data since we only check for poison on alloc, which can't be done on a freed pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-10-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 9e98065a68b1..4dea2a0dbd33 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -312,16 +312,6 @@ static inline bool is_page_busy(struct dma_page *page) return page->in_use != 0; } -static void pool_free_page(struct dma_pool *pool, struct dma_page *page) -{ - dma_addr_t dma = page->dma; - - pool_init_page(pool, page); - dma_free_coherent(pool->dev, pool->allocation, page->vaddr, dma); - list_del(&page->page_list); - kfree(page); -} - /** * dma_pool_destroy - destroys a pool of dma memory blocks. * @pool: dma pool that will be destroyed @@ -349,14 +339,14 @@ void dma_pool_destroy(struct dma_pool *pool) mutex_unlock(&pools_reg_lock); list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { - if (is_page_busy(page)) { + if (!is_page_busy(page)) + dma_free_coherent(pool->dev, pool->allocation, + page->vaddr, page->dma); + else dev_err(pool->dev, "%s %s, %p busy\n", __func__, pool->name, page->vaddr); - /* leak the still-in-use consistent memory */ - list_del(&page->page_list); - kfree(page); - } else - pool_free_page(pool, page); + list_del(&page->page_list); + kfree(page); } kfree(pool); -- GitLab From 8ecc369554219060367fc589661d2b7ab201e923 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:23 -0800 Subject: [PATCH 4591/5631] dmapool: don't memset on free twice If debug is enabled, dmapool will poison the range, so no need to clear it to 0 immediately before writing over it. Link: https://lkml.kernel.org/r/20230126215125.4069751-11-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 4dea2a0dbd33..21e6d362c726 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -160,6 +160,8 @@ static void pool_check_block(struct dma_pool *pool, void *retval, static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, void *vaddr, dma_addr_t dma) { + if (want_init_on_free()) + memset(vaddr, 0, pool->size); return false; } @@ -441,8 +443,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) return; } - if (want_init_on_free()) - memset(vaddr, 0, pool->size); if (pool_page_err(pool, page, vaddr, dma)) { spin_unlock_irqrestore(&pool->lock, flags); return; -- GitLab From da9619a30e73b59605ed998bf7bc4359f5c0029a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 26 Jan 2023 13:51:24 -0800 Subject: [PATCH 4592/5631] dmapool: link blocks across pages The allocated dmapool pages are never freed for the lifetime of the pool. There is no need for the two level list+stack lookup for finding a free block since nothing is ever removed from the list. Just use a simple stack, reducing time complexity to constant. The implementation inserts the stack linking elements and the dma handle of the block within itself when freed. This means the smallest possible dmapool block is increased to at most 16 bytes to accommodate these fields, but there are no exisiting users requesting a dma pool smaller than that anyway. Removing the list has a significant change in performance. Using the kernel's micro-benchmarking self test: Before: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:57282 dmapool test: size:64 blocks:8192 time:172562 dmapool test: size:256 blocks:8192 time:789247 dmapool test: size:1024 blocks:2048 time:371823 dmapool test: size:4096 blocks:1024 time:362237 After: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:24997 dmapool test: size:64 blocks:8192 time:26584 dmapool test: size:256 blocks:8192 time:33542 dmapool test: size:1024 blocks:2048 time:9022 dmapool test: size:4096 blocks:1024 time:6045 The module test allocates quite a few blocks that may not accurately represent how these pools are used in real life. For a more marco level benchmark, running fio high-depth + high-batched on nvme, this patch shows submission and completion latency reduced by ~100usec each, 1% IOPs improvement, and perf record's time spent in dma_pool_alloc/free were reduced by half. [kbusch@kernel.org: push new blocks in ascending order] Link: https://lkml.kernel.org/r/20230221165400.1595247-1-kbusch@meta.com Link: https://lkml.kernel.org/r/20230126215125.4069751-12-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Tested-by: Bryan O'Donoghue Cc: Matthew Wilcox Cc: Tony Battersby Signed-off-by: Andrew Morton --- mm/dmapool.c | 257 ++++++++++++++++++++++++++------------------------- 1 file changed, 130 insertions(+), 127 deletions(-) diff --git a/mm/dmapool.c b/mm/dmapool.c index 21e6d362c726..d2b0f8fc9649 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -15,7 +15,7 @@ * represented by the 'struct dma_pool' which keeps a doubly-linked list of * allocated pages. Each page in the page_list is split into blocks of at * least 'size' bytes. Free blocks are tracked in an unsorted singly-linked - * list of free blocks within the page. Used blocks aren't tracked, but we + * list of free blocks across all pages. Used blocks aren't tracked, but we * keep a count of how many are currently allocated from each page. */ @@ -40,9 +40,18 @@ #define DMAPOOL_DEBUG 1 #endif +struct dma_block { + struct dma_block *next_block; + dma_addr_t dma; +}; + struct dma_pool { /* the pool */ struct list_head page_list; spinlock_t lock; + struct dma_block *next_block; + size_t nr_blocks; + size_t nr_active; + size_t nr_pages; struct device *dev; unsigned int size; unsigned int allocation; @@ -55,8 +64,6 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ struct list_head page_list; void *vaddr; dma_addr_t dma; - unsigned int in_use; - unsigned int offset; }; static DEFINE_MUTEX(pools_lock); @@ -64,30 +71,18 @@ static DEFINE_MUTEX(pools_reg_lock); static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { - int size; - struct dma_page *page; struct dma_pool *pool; + unsigned size; size = sysfs_emit(buf, "poolinfo - 0.1\n"); mutex_lock(&pools_lock); list_for_each_entry(pool, &dev->dma_pools, pools) { - unsigned pages = 0; - size_t blocks = 0; - - spin_lock_irq(&pool->lock); - list_for_each_entry(page, &pool->page_list, page_list) { - pages++; - blocks += page->in_use; - } - spin_unlock_irq(&pool->lock); - /* per-pool info, no real statistics yet */ - size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2u\n", - pool->name, blocks, - (size_t) pages * - (pool->allocation / pool->size), - pool->size, pages); + size += sysfs_emit_at(buf, size, "%-16s %4zu %4zu %4u %2zu\n", + pool->name, pool->nr_active, + pool->nr_blocks, pool->size, + pool->nr_pages); } mutex_unlock(&pools_lock); @@ -97,17 +92,17 @@ static ssize_t pools_show(struct device *dev, struct device_attribute *attr, cha static DEVICE_ATTR_RO(pools); #ifdef DMAPOOL_DEBUG -static void pool_check_block(struct dma_pool *pool, void *retval, - unsigned int offset, gfp_t mem_flags) +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) { + u8 *data = (void *)block; int i; - u8 *data = retval; - /* page->offset is stored in first 4 bytes */ - for (i = sizeof(offset); i < pool->size; i++) { + + for (i = sizeof(struct dma_block); i < pool->size; i++) { if (data[i] == POOL_POISON_FREED) continue; - dev_err(pool->dev, "%s %s, %p (corrupted)\n", - __func__, pool->name, retval); + dev_err(pool->dev, "%s %s, %p (corrupted)\n", __func__, + pool->name, block); /* * Dump the first 4 bytes even if they are not @@ -117,31 +112,46 @@ static void pool_check_block(struct dma_pool *pool, void *retval, data, pool->size, 1); break; } + if (!want_init_on_alloc(mem_flags)) - memset(retval, POOL_POISON_ALLOCATED, pool->size); + memset(block, POOL_POISON_ALLOCATED, pool->size); } -static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, - void *vaddr, dma_addr_t dma) +static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) { - unsigned int offset = vaddr - page->vaddr; - unsigned int chain = page->offset; + struct dma_page *page; - if ((dma - page->dma) != offset) { - dev_err(pool->dev, "%s %s, %p (bad vaddr)/%pad\n", + list_for_each_entry(page, &pool->page_list, page_list) { + if (dma < page->dma) + continue; + if ((dma - page->dma) < pool->allocation) + return page; + } + return NULL; +} + +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) +{ + struct dma_block *block = pool->next_block; + struct dma_page *page; + + page = pool_find_page(pool, dma); + if (!page) { + dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", __func__, pool->name, vaddr, &dma); return true; } - while (chain < pool->allocation) { - if (chain != offset) { - chain = *(int *)(page->vaddr + chain); + while (block) { + if (block != vaddr) { + block = block->next_block; continue; } dev_err(pool->dev, "%s %s, dma %pad already free\n", __func__, pool->name, &dma); return true; } + memset(vaddr, POOL_POISON_FREED, pool->size); return false; } @@ -151,14 +161,12 @@ static void pool_init_page(struct dma_pool *pool, struct dma_page *page) memset(page->vaddr, POOL_POISON_FREED, pool->allocation); } #else -static void pool_check_block(struct dma_pool *pool, void *retval, - unsigned int offset, gfp_t mem_flags) - +static void pool_check_block(struct dma_pool *pool, struct dma_block *block, + gfp_t mem_flags) { } -static bool pool_page_err(struct dma_pool *pool, struct dma_page *page, - void *vaddr, dma_addr_t dma) +static bool pool_block_err(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { if (want_init_on_free()) memset(vaddr, 0, pool->size); @@ -170,6 +178,26 @@ static void pool_init_page(struct dma_pool *pool, struct dma_page *page) } #endif +static struct dma_block *pool_block_pop(struct dma_pool *pool) +{ + struct dma_block *block = pool->next_block; + + if (block) { + pool->next_block = block->next_block; + pool->nr_active++; + } + return block; +} + +static void pool_block_push(struct dma_pool *pool, struct dma_block *block, + dma_addr_t dma) +{ + block->dma = dma; + block->next_block = pool->next_block; + pool->next_block = block; +} + + /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. * @name: name of pool, for diagnostics @@ -210,8 +238,8 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, if (size == 0 || size > INT_MAX) return NULL; - else if (size < 4) - size = 4; + if (size < sizeof(struct dma_block)) + size = sizeof(struct dma_block); size = ALIGN(size, align); allocation = max_t(size_t, size, PAGE_SIZE); @@ -223,7 +251,7 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, boundary = min(boundary, allocation); - retval = kmalloc(sizeof(*retval), GFP_KERNEL); + retval = kzalloc(sizeof(*retval), GFP_KERNEL); if (!retval) return retval; @@ -236,7 +264,6 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev, retval->size = size; retval->boundary = boundary; retval->allocation = allocation; - INIT_LIST_HEAD(&retval->pools); /* @@ -273,21 +300,36 @@ EXPORT_SYMBOL(dma_pool_create); static void pool_initialise_page(struct dma_pool *pool, struct dma_page *page) { - unsigned int offset = 0; - unsigned int next_boundary = pool->boundary; + unsigned int next_boundary = pool->boundary, offset = 0; + struct dma_block *block, *first = NULL, *last = NULL; pool_init_page(pool, page); - page->in_use = 0; - page->offset = 0; - do { - unsigned int next = offset + pool->size; - if (unlikely((next + pool->size) >= next_boundary)) { - next = next_boundary; + while (offset + pool->size <= pool->allocation) { + if (offset + pool->size > next_boundary) { + offset = next_boundary; next_boundary += pool->boundary; + continue; } - *(int *)(page->vaddr + offset) = next; - offset = next; - } while (offset < pool->allocation); + + block = page->vaddr + offset; + block->dma = page->dma + offset; + block->next_block = NULL; + + if (last) + last->next_block = block; + else + first = block; + last = block; + + offset += pool->size; + pool->nr_blocks++; + } + + last->next_block = pool->next_block; + pool->next_block = first; + + list_add(&page->page_list, &pool->page_list); + pool->nr_pages++; } static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) @@ -305,15 +347,9 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags) return NULL; } - pool_initialise_page(pool, page); return page; } -static inline bool is_page_busy(struct dma_page *page) -{ - return page->in_use != 0; -} - /** * dma_pool_destroy - destroys a pool of dma memory blocks. * @pool: dma pool that will be destroyed @@ -325,7 +361,7 @@ static inline bool is_page_busy(struct dma_page *page) void dma_pool_destroy(struct dma_pool *pool) { struct dma_page *page, *tmp; - bool empty = false; + bool empty = false, busy = false; if (unlikely(!pool)) return; @@ -340,13 +376,15 @@ void dma_pool_destroy(struct dma_pool *pool) device_remove_file(pool->dev, &dev_attr_pools); mutex_unlock(&pools_reg_lock); + if (pool->nr_active) { + dev_err(pool->dev, "%s %s busy\n", __func__, pool->name); + busy = true; + } + list_for_each_entry_safe(page, tmp, &pool->page_list, page_list) { - if (!is_page_busy(page)) + if (!busy) dma_free_coherent(pool->dev, pool->allocation, page->vaddr, page->dma); - else - dev_err(pool->dev, "%s %s, %p busy\n", __func__, - pool->name, page->vaddr); list_del(&page->page_list); kfree(page); } @@ -368,58 +406,40 @@ EXPORT_SYMBOL(dma_pool_destroy); void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle) { - unsigned long flags; + struct dma_block *block; struct dma_page *page; - unsigned int offset; - void *retval; + unsigned long flags; might_alloc(mem_flags); spin_lock_irqsave(&pool->lock, flags); - list_for_each_entry(page, &pool->page_list, page_list) { - if (page->offset < pool->allocation) - goto ready; - } - - /* pool_alloc_page() might sleep, so temporarily drop &pool->lock */ - spin_unlock_irqrestore(&pool->lock, flags); - - page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); - if (!page) - return NULL; + block = pool_block_pop(pool); + if (!block) { + /* + * pool_alloc_page() might sleep, so temporarily drop + * &pool->lock + */ + spin_unlock_irqrestore(&pool->lock, flags); - spin_lock_irqsave(&pool->lock, flags); + page = pool_alloc_page(pool, mem_flags & (~__GFP_ZERO)); + if (!page) + return NULL; - list_add(&page->page_list, &pool->page_list); - ready: - page->in_use++; - offset = page->offset; - page->offset = *(int *)(page->vaddr + offset); - retval = offset + page->vaddr; - *handle = offset + page->dma; - pool_check_block(pool, retval, offset, mem_flags); + spin_lock_irqsave(&pool->lock, flags); + pool_initialise_page(pool, page); + block = pool_block_pop(pool); + } spin_unlock_irqrestore(&pool->lock, flags); + *handle = block->dma; + pool_check_block(pool, block, mem_flags); if (want_init_on_alloc(mem_flags)) - memset(retval, 0, pool->size); + memset(block, 0, pool->size); - return retval; + return block; } EXPORT_SYMBOL(dma_pool_alloc); -static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) -{ - struct dma_page *page; - - list_for_each_entry(page, &pool->page_list, page_list) { - if (dma < page->dma) - continue; - if ((dma - page->dma) < pool->allocation) - return page; - } - return NULL; -} - /** * dma_pool_free - put block back into dma pool * @pool: the dma pool holding the block @@ -431,31 +451,14 @@ static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma) */ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma) { - struct dma_page *page; + struct dma_block *block = vaddr; unsigned long flags; spin_lock_irqsave(&pool->lock, flags); - page = pool_find_page(pool, dma); - if (!page) { - spin_unlock_irqrestore(&pool->lock, flags); - dev_err(pool->dev, "%s %s, %p/%pad (bad dma)\n", - __func__, pool->name, vaddr, &dma); - return; - } - - if (pool_page_err(pool, page, vaddr, dma)) { - spin_unlock_irqrestore(&pool->lock, flags); - return; + if (!pool_block_err(pool, vaddr, dma)) { + pool_block_push(pool, block, dma); + pool->nr_active--; } - - page->in_use--; - *(int *)vaddr = page->offset; - page->offset = vaddr - page->vaddr; - /* - * Resist a temptation to do - * if (!is_page_busy(page)) pool_free_page(pool, page); - * Better have a few empty pages hang around. - */ spin_unlock_irqrestore(&pool->lock, flags); } EXPORT_SYMBOL(dma_pool_free); -- GitLab From c3e6df97fa25ff310c3d5e7f1644248e072e3cb0 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 6 May 2023 18:06:43 -0300 Subject: [PATCH 4593/5631] Revert "perf build: Warn for BPF skeletons if endian mismatches" This reverts commit 51924ae69eea5bc90b5da525fbcf4bbd5f8551b3. We need to better polish building with BPF skels, so revert back to making it an experimental feature that has to be explicitely enabled using BUILD_BPF_SKEL=1. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 71442c54c25f..16bea51f0bcd 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -663,17 +663,14 @@ ifndef NO_BPF_SKEL $(call feature_check,clang-bpf-co-re) ifeq ($(feature-clang-bpf-co-re), 0) dummy := $(error: ERROR: BPF skeletons unsupported. clang too old/not installed or build with NO_BPF_SKEL=1.) + else + ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) + dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) + else + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL + endif endif - ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) - endif - host_byte_order=$(echo ""|$(HOSTCC) -dM -E -|grep __BYTE_ORDER__) - target_byte_order=$(echo ""|$(CC) -dM -E -|grep __BYTE_ORDER__) - ifneq ($(host_byte_order), $(target_byte_order)) - $(warning Possibly mismatched host and target endianness may break BPF skeletons) - endif - $(call detected,CONFIG_PERF_BPF_SKEL) - CFLAGS += -DHAVE_BPF_SKEL endif dwarf-post-unwind := 1 -- GitLab From 9a2d5178b9d51e1c5f9e08989ff97fc8d4893f31 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 6 May 2023 18:07:37 -0300 Subject: [PATCH 4594/5631] Revert "perf build: Make BUILD_BPF_SKEL default, rename to NO_BPF_SKEL" This reverts commit a980755beb5aca9002e1c95ba519b83a44242b5b. We need to better polish building with BPF skels, so revert back to making it an experimental feature that has to be explicitely enabled using BUILD_BPF_SKEL=1. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 19 +++++++------------ tools/perf/Makefile.perf | 8 ++++---- tools/perf/builtin-lock.c | 2 +- tools/perf/builtin-record.c | 2 +- tools/perf/builtin-version.c | 1 - tools/perf/tests/shell/record_offcpu.sh | 2 +- 6 files changed, 14 insertions(+), 20 deletions(-) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 16bea51f0bcd..ee467af49b62 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -415,7 +415,6 @@ ifdef NO_LIBELF NO_LIBUNWIND := 1 NO_LIBDW_DWARF_UNWIND := 1 NO_LIBBPF := 1 - NO_BPF_SKEL := 1 NO_JVMTI := 1 else ifeq ($(feature-libelf), 0) @@ -655,22 +654,18 @@ ifndef NO_LIBBPF msg := $(warning BPF API too old. Please install recent kernel headers. BPF support in 'perf record' is disabled.) NO_LIBBPF := 1 endif -else - NO_BPF_SKEL := 1 endif -ifndef NO_BPF_SKEL +ifdef BUILD_BPF_SKEL $(call feature_check,clang-bpf-co-re) ifeq ($(feature-clang-bpf-co-re), 0) - dummy := $(error: ERROR: BPF skeletons unsupported. clang too old/not installed or build with NO_BPF_SKEL=1.) - else - ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(error: ERROR: BPF skeletons unsupported. BPF skeleton support requires libbpf or build with NO_BPF_SKEL=1.) - else - $(call detected,CONFIG_PERF_BPF_SKEL) - CFLAGS += -DHAVE_BPF_SKEL - endif + dummy := $(error Error: clang too old/not installed. Please install recent clang to build with BUILD_BPF_SKEL) + endif + ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) + dummy := $(error Error: BPF skeleton support requires libbpf) endif + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL endif dwarf-post-unwind := 1 diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 61c33d100b2b..a42a6a99c2bc 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -124,7 +124,7 @@ include ../scripts/utilities.mak # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod # -# Define NO_BPF_SKEL to disable BPF skeletons +# Define BUILD_BPF_SKEL to enable BPF skeletons # # Define BUILD_NONDISTRO to enable building an linking against libbfd and # libiberty distribution license incompatible libraries. @@ -1055,7 +1055,7 @@ SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ -ifndef NO_BPF_SKEL +ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) @@ -1074,11 +1074,11 @@ bpf-skel: $(SKELETONS) .PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o -else # NO_BPF_SKEL +else # BUILD_BPF_SKEL bpf-skel: -endif # NO_BPF_SKEL +endif # BUILD_BPF_SKEL bpf-skel-clean: $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index ecb1fac8ba3c..70b14ba5fdd5 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2387,7 +2387,7 @@ int cmd_lock(int argc, const char **argv) #ifndef HAVE_BPF_SKEL set_option_nobuild(contention_options, 'b', "use-bpf", - "NO_BPF_SKEL=1", false); + "no BUILD_BPF_SKEL=1", false); #endif if (argc) { argc = parse_options(argc, argv, contention_options, diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 7b7e74a56346..efa03e4ac2c9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -3981,7 +3981,7 @@ int cmd_record(int argc, const char **argv) #ifndef HAVE_BPF_SKEL # define set_nobuild(s, l, m, c) set_option_nobuild(record_options, s, l, m, c) - set_nobuild('\0', "off-cpu", "NO_BPF_SKEL=1", true); + set_nobuild('\0', "off-cpu", "no BUILD_BPF_SKEL=1", true); # undef set_nobuild #endif diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index 1872c90a6667..e5859c70e195 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -81,7 +81,6 @@ static void library_status(void) STATUS(HAVE_ZSTD_SUPPORT, zstd); STATUS(HAVE_LIBPFM, libpfm4); STATUS(HAVE_LIBTRACEEVENT, libtraceevent); - STATUS(HAVE_BPF_SKEL, BPF skeletons); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index 155d4856551a..f062ae9a95e1 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -28,7 +28,7 @@ test_offcpu_priv() { err=2 return fi - if perf version --build-options 2>&1 | grep HAVE_BPF_SKEL | grep -q OFF + if perf record --off-cpu -o /dev/null --quiet true 2>&1 | grep BUILD_BPF_SKEL then echo "off-cpu test [Skipped missing BPF support]" err=2 -- GitLab From 424f8416bb39936df6365442d651ee729b283460 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 May 2023 17:06:18 +0000 Subject: [PATCH 4595/5631] net: skb_partial_csum_set() fix against transport header magic value skb->transport_header uses the special 0xFFFF value to mark if the transport header was set or not. We must prevent callers to accidentaly set skb->transport_header to 0xFFFF. Note that only fuzzers can possibly do this today. syzbot reported: WARNING: CPU: 0 PID: 2340 at include/linux/skbuff.h:2847 skb_transport_offset include/linux/skbuff.h:2956 [inline] WARNING: CPU: 0 PID: 2340 at include/linux/skbuff.h:2847 virtio_net_hdr_to_skb+0xbcc/0x10c0 include/linux/virtio_net.h:103 Modules linked in: CPU: 0 PID: 2340 Comm: syz-executor.0 Not tainted 6.3.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:skb_transport_header include/linux/skbuff.h:2847 [inline] RIP: 0010:skb_transport_offset include/linux/skbuff.h:2956 [inline] RIP: 0010:virtio_net_hdr_to_skb+0xbcc/0x10c0 include/linux/virtio_net.h:103 Code: 41 39 df 0f 82 c3 04 00 00 48 8b 7c 24 10 44 89 e6 e8 08 6e 59 ff 48 85 c0 74 54 e8 ce 36 7e fc e9 37 f8 ff ff e8 c4 36 7e fc <0f> 0b e9 93 f8 ff ff 44 89 f7 44 89 e6 e8 32 38 7e fc 45 39 e6 0f RSP: 0018:ffffc90004497880 EFLAGS: 00010293 RAX: ffffffff84fea55c RBX: 000000000000ffff RCX: ffff888120be2100 RDX: 0000000000000000 RSI: 000000000000ffff RDI: 000000000000ffff RBP: ffffc90004497990 R08: ffffffff84fe9de5 R09: 0000000000000034 R10: ffffea00048ebd80 R11: 0000000000000034 R12: ffff88811dc2d9c8 R13: dffffc0000000000 R14: ffff88811dc2d9ae R15: 1ffff11023b85b35 FS: 00007f9211a59700(0000) GS:ffff8881f6c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000200002c0 CR3: 00000001215a5000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: packet_snd net/packet/af_packet.c:3076 [inline] packet_sendmsg+0x4590/0x61a0 net/packet/af_packet.c:3115 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] __sys_sendto+0x472/0x630 net/socket.c:2144 __do_sys_sendto net/socket.c:2156 [inline] __se_sys_sendto net/socket.c:2152 [inline] __x64_sys_sendto+0xe5/0x100 net/socket.c:2152 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2f/0x50 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f9210c8c169 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9211a59168 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00007f9210dabf80 RCX: 00007f9210c8c169 RDX: 000000000000ffed RSI: 00000000200000c0 RDI: 0000000000000003 RBP: 00007f9210ce7ca1 R08: 0000000020000540 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe135d65cf R14: 00007f9211a59300 R15: 0000000000022000 Fixes: 66e4c8d95008 ("net: warn if transport header was not set") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Willem de Bruijn Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/core/skbuff.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26a586007d8b..515ec5cdc79c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5298,7 +5298,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) u32 csum_end = (u32)start + (u32)off + sizeof(__sum16); u32 csum_start = skb_headroom(skb) + (u32)start; - if (unlikely(csum_start > U16_MAX || csum_end > skb_headlen(skb))) { + if (unlikely(csum_start >= U16_MAX || csum_end > skb_headlen(skb))) { net_warn_ratelimited("bad partial csum: csum=%u/%u headroom=%u headlen=%u\n", start, off, skb_headroom(skb), skb_headlen(skb)); return false; @@ -5306,7 +5306,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = csum_start; skb->csum_offset = off; - skb_set_transport_header(skb, start); + skb->transport_header = csum_start; return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); -- GitLab From 27c1eaa07283b0c94becf8241f95368267cf558b Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 5 May 2023 20:39:33 +0200 Subject: [PATCH 4596/5631] net: mdio: mvusb: Fix an error handling path in mvusb_mdio_probe() Should of_mdiobus_register() fail, a previous usb_get_dev() call should be undone as in the .disconnect function. Fixes: 04e37d92fbed ("net: phy: add marvell usb to mdio controller") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/mdio/mdio-mvusb.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/mdio/mdio-mvusb.c b/drivers/net/mdio/mdio-mvusb.c index 68fc55906e78..554837c21e73 100644 --- a/drivers/net/mdio/mdio-mvusb.c +++ b/drivers/net/mdio/mdio-mvusb.c @@ -67,6 +67,7 @@ static int mvusb_mdio_probe(struct usb_interface *interface, struct device *dev = &interface->dev; struct mvusb_mdio *mvusb; struct mii_bus *mdio; + int ret; mdio = devm_mdiobus_alloc_size(dev, sizeof(*mvusb)); if (!mdio) @@ -87,7 +88,15 @@ static int mvusb_mdio_probe(struct usb_interface *interface, mdio->write = mvusb_mdio_write; usb_set_intfdata(interface, mvusb); - return of_mdiobus_register(mdio, dev->of_node); + ret = of_mdiobus_register(mdio, dev->of_node); + if (ret) + goto put_dev; + + return 0; + +put_dev: + usb_put_dev(mvusb->udev); + return ret; } static void mvusb_mdio_disconnect(struct usb_interface *interface) -- GitLab From ac9a78681b921877518763ba0e89202254349d1b Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 7 May 2023 13:34:35 -0700 Subject: [PATCH 4597/5631] Linux 6.4-rc1 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 5ac8f263f9b0..9d765ebcccf1 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 3 +PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* -- GitLab From 7b9891ad25246b18b5ccc19518da7abc7763aa0a Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Fri, 5 May 2023 10:14:58 -0600 Subject: [PATCH 4598/5631] ASoC: amd: yc: Add DMI entry to support System76 Pangolin 12 Add pang12 quirk to enable the internal microphone. Signed-off-by: Jeremy Soller Date: Fri, 5 May 2023 09:28:20 +0300 Subject: [PATCH 4599/5631] ASoC: dwc: limit the number of overrun messages On slow CPU (FPGA/QEMU emulated) printing overrun messages from interrupt handler to uart console may leads to more overrun errors. So use dev_err_ratelimited to limit the number of error messages. Signed-off-by: Maxim Kochetkov dev, "TX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "TX overrun (ch_id=%d)\n", i); irq_valid = true; } /* Error Handling: TX */ if (isr[i] & ISR_RXFO) { - dev_err(dev->dev, "RX overrun (ch_id=%d)\n", i); + dev_err_ratelimited(dev->dev, "RX overrun (ch_id=%d)\n", i); irq_valid = true; } } -- GitLab From 70a640c0efa7667453c3911b13335304ce46ad8b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Apr 2023 15:35:45 +0200 Subject: [PATCH 4600/5631] regmap: REGMAP_KUNIT should not select REGMAP Enabling a (modular) test should not silently enable additional kernel functionality, as that may increase the attack vector of a product. Fix this by: 1. making REGMAP visible if CONFIG_KUNIT_ALL_TESTS is enabled, 2. making REGMAP_KUNIT depend on REGMAP instead of selecting it. After this, one can safely enable CONFIG_KUNIT_ALL_TESTS=m to build modules for all appropriate tests for ones system, without pulling in extra unwanted functionality, while still allowing a tester to manually enable REGMAP and its test suite on a system where REGMAP is not enabled by default. Fixes: 2238959b6ad27040 ("regmap: Add some basic kunit tests") Signed-off-by: Geert Uytterhoeven Date: Mon, 16 Jan 2023 10:00:15 +0800 Subject: [PATCH 4601/5631] ext4: fix WARNING in mb_find_extent Syzbot found the following issue: EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support! EXT4-fs (loop0): orphan cleanup on readonly fs ------------[ cut here ]------------ WARNING: CPU: 1 PID: 5067 at fs/ext4/mballoc.c:1869 mb_find_extent+0x8a1/0xe30 Modules linked in: CPU: 1 PID: 5067 Comm: syz-executor307 Not tainted 6.2.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 RIP: 0010:mb_find_extent+0x8a1/0xe30 fs/ext4/mballoc.c:1869 RSP: 0018:ffffc90003c9e098 EFLAGS: 00010293 RAX: ffffffff82405731 RBX: 0000000000000041 RCX: ffff8880783457c0 RDX: 0000000000000000 RSI: 0000000000000041 RDI: 0000000000000040 RBP: 0000000000000040 R08: ffffffff82405723 R09: ffffed10053c9402 R10: ffffed10053c9402 R11: 1ffff110053c9401 R12: 0000000000000000 R13: ffffc90003c9e538 R14: dffffc0000000000 R15: ffffc90003c9e2cc FS: 0000555556665300(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000056312f6796f8 CR3: 0000000022437000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ext4_mb_complex_scan_group+0x353/0x1100 fs/ext4/mballoc.c:2307 ext4_mb_regular_allocator+0x1533/0x3860 fs/ext4/mballoc.c:2735 ext4_mb_new_blocks+0xddf/0x3db0 fs/ext4/mballoc.c:5605 ext4_ext_map_blocks+0x1868/0x6880 fs/ext4/extents.c:4286 ext4_map_blocks+0xa49/0x1cc0 fs/ext4/inode.c:651 ext4_getblk+0x1b9/0x770 fs/ext4/inode.c:864 ext4_bread+0x2a/0x170 fs/ext4/inode.c:920 ext4_quota_write+0x225/0x570 fs/ext4/super.c:7105 write_blk fs/quota/quota_tree.c:64 [inline] get_free_dqblk+0x34a/0x6d0 fs/quota/quota_tree.c:130 do_insert_tree+0x26b/0x1aa0 fs/quota/quota_tree.c:340 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 do_insert_tree+0x722/0x1aa0 fs/quota/quota_tree.c:375 dq_insert_tree fs/quota/quota_tree.c:401 [inline] qtree_write_dquot+0x3b6/0x530 fs/quota/quota_tree.c:420 v2_write_dquot+0x11b/0x190 fs/quota/quota_v2.c:358 dquot_acquire+0x348/0x670 fs/quota/dquot.c:444 ext4_acquire_dquot+0x2dc/0x400 fs/ext4/super.c:6740 dqget+0x999/0xdc0 fs/quota/dquot.c:914 __dquot_initialize+0x3d0/0xcf0 fs/quota/dquot.c:1492 ext4_process_orphan+0x57/0x2d0 fs/ext4/orphan.c:329 ext4_orphan_cleanup+0xb60/0x1340 fs/ext4/orphan.c:474 __ext4_fill_super fs/ext4/super.c:5516 [inline] ext4_fill_super+0x81cd/0x8700 fs/ext4/super.c:5644 get_tree_bdev+0x400/0x620 fs/super.c:1282 vfs_get_tree+0x88/0x270 fs/super.c:1489 do_new_mount+0x289/0xad0 fs/namespace.c:3145 do_mount fs/namespace.c:3488 [inline] __do_sys_mount fs/namespace.c:3697 [inline] __se_sys_mount+0x2d3/0x3c0 fs/namespace.c:3674 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Add some debug information: mb_find_extent: mb_find_extent block=41, order=0 needed=64 next=0 ex=0/41/1@3735929054 64 64 7 block_bitmap: ff 3f 0c 00 fc 01 00 00 d2 3d 00 00 00 00 00 00 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff Acctually, blocks per group is 64, but block bitmap indicate at least has 128 blocks. Now, ext4_validate_block_bitmap() didn't check invalid block's bitmap if set. To resolve above issue, add check like fsck "Padding at end of block bitmap is not set". Cc: stable@kernel.org Reported-by: syzbot+68223fe9f6c95ad43bed@syzkaller.appspotmail.com Signed-off-by: Ye Bin Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230116020015.1506120-1-yebin@huaweicloud.com Signed-off-by: Theodore Ts'o --- fs/ext4/balloc.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 094269488183..c49e612e3975 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -305,6 +305,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } +static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, + ext4_group_t block_group, + struct buffer_head *bh) +{ + ext4_grpblk_t next_zero_bit; + unsigned long bitmap_size = sb->s_blocksize * 8; + unsigned int offset = num_clusters_in_group(sb, block_group); + + if (bitmap_size <= offset) + return 0; + + next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset); + + return (next_zero_bit < bitmap_size ? next_zero_bit : 0); +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -402,6 +418,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb, EXT4_GROUP_INFO_BBITMAP_CORRUPT); return -EFSCORRUPTED; } + blk = ext4_valid_block_bitmap_padding(sb, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set", + block_group, blk); + ext4_mark_group_bitmap_corrupted(sb, block_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + return -EFSCORRUPTED; + } set_buffer_verified(bh); verified: ext4_unlock_group(sb, block_group); -- GitLab From 949f95ff39bf188e594e7ecd8e29b82eb108f5bf Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 11 Apr 2023 14:10:19 +0200 Subject: [PATCH 4602/5631] ext4: fix lockdep warning when enabling MMP When we enable MMP in ext4_multi_mount_protect() during mount or remount, we end up calling sb_start_write() from write_mmp_block(). This triggers lockdep warning because freeze protection ranks above s_umount semaphore we are holding during mount / remount. The problem is harmless because we are guaranteed the filesystem is not frozen during mount / remount but still let's fix the warning by not grabbing freeze protection from ext4_multi_mount_protect(). Cc: stable@kernel.org Reported-by: syzbot+6b7df7d5506b32467149@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=ab7e5b6f400b7778d46f01841422e5718fb81843 Signed-off-by: Jan Kara Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230411121019.21940-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/mmp.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 4022bc713421..0aaf38ffcb6e 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -39,28 +39,36 @@ static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) * Write the MMP block using REQ_SYNC to try to get the block on-disk * faster. */ -static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +static int write_mmp_block_thawed(struct super_block *sb, + struct buffer_head *bh) { struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); - /* - * We protect against freezing so that we don't create dirty buffers - * on frozen filesystem. - */ - sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); - sb_end_write(sb); if (unlikely(!buffer_uptodate(bh))) return -EIO; - return 0; } +static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) +{ + int err; + + /* + * We protect against freezing so that we don't create dirty buffers + * on frozen filesystem. + */ + sb_start_write(sb); + err = write_mmp_block_thawed(sb, bh); + sb_end_write(sb); + return err; +} + /* * Read the MMP block. It _must_ be read from disk and hence we clear the * uptodate flag on the buffer. @@ -344,7 +352,11 @@ int ext4_multi_mount_protect(struct super_block *sb, seq = mmp_new_seq(); mmp->mmp_seq = cpu_to_le32(seq); - retval = write_mmp_block(sb, bh); + /* + * On mount / remount we are protected against fs freezing (by s_umount + * semaphore) and grabbing freeze protection upsets lockdep + */ + retval = write_mmp_block_thawed(sb, bh); if (retval) goto failed; -- GitLab From 0a6b36c5dc3dda0196f4fb65bdb34c38b8d060c3 Mon Sep 17 00:00:00 2001 From: Jeremy Soller Date: Fri, 5 May 2023 10:36:51 -0600 Subject: [PATCH 4603/5631] ALSA: hda/realtek: Add quirk for Clevo L140AU Fixes headset detection on Clevo L140AU. Signed-off-by: Jeremy Soller Signed-off-by: Tim Crawford Cc: Link: https://lore.kernel.org/r/20230505163651.21257-1-tcrawford@system76.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 172ffc2c332b..e7d2e20b91f5 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9618,6 +9618,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x7716, "Clevo NS50PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7717, "Clevo NS70PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x7718, "Clevo L140PU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x7724, "Clevo L140AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8228, "Clevo NR40BU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8520, "Clevo NH50D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x8521, "Clevo NH77D[CD]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), -- GitLab From a4671b7fba59775845ee60cfbdfc4ba64300211b Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sat, 6 May 2023 11:58:24 +1200 Subject: [PATCH 4604/5631] ALSA: hda/realtek: Add quirk for 2nd ASUS GU603 Add quirk for GU603 with 0x1c62 variant of codec. Signed-off-by: Luke D. Jones Cc: Link: https://lore.kernel.org/r/20230505235824.49607-2-luke@ljones.dev Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index e7d2e20b91f5..7082b1d220c5 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9522,6 +9522,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401), -- GitLab From 90670ef774a8b6700c38ce1222e6aa263be54d5f Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Sat, 6 May 2023 10:26:53 +0800 Subject: [PATCH 4605/5631] ALSA: hda/realtek: Add a quirk for HP EliteDesk 805 Add a quirk for HP EliteDesk 805 to fixup ALC3867 headset MIC no sound. Signed-off-by: Ai Chao Cc: Link: https://lore.kernel.org/r/20230506022653.2074343-1-aichao@kylinos.cn Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7082b1d220c5..bc062c0a1916 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -11665,6 +11665,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1632, "HP RP5800", ALC662_FIXUP_HP_RP5800), SND_PCI_QUIRK(0x103c, 0x870c, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x8719, "HP", ALC897_FIXUP_HP_HSMIC_VERB), + SND_PCI_QUIRK(0x103c, 0x872b, "HP", ALC897_FIXUP_HP_HSMIC_VERB), SND_PCI_QUIRK(0x103c, 0x873e, "HP", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x877e, "HP 288 Pro G6", ALC671_FIXUP_HP_HEADSET_MIC2), SND_PCI_QUIRK(0x103c, 0x885f, "HP 288 Pro G8", ALC671_FIXUP_HP_HEADSET_MIC2), -- GitLab From 048bce15da19e46ce5e866a48338929c76ca4152 Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Wed, 19 Apr 2023 17:58:27 +0200 Subject: [PATCH 4606/5631] media: dt-bindings: ov2685: Correct data-lanes attribute When adapting the original doc conversion to support 2 lanes, minItems should've been added as well since the sensor supports either 1 or 2 lanes. Add minItems to make the validation happy again. Fixes: 8d561d78aeab ("media: dt-bindings: ov2685: convert to dtschema") Signed-off-by: Luca Weiss Acked-by: Rob Herring Link: https://lore.kernel.org/r/20230419-ov2685-dtschema-fixup-v1-1-c850a34b3a26@z3ntu.xyz Signed-off-by: Krzysztof Kozlowski --- Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml b/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml index 8b389314c352..e2ffe0a9c26b 100644 --- a/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml +++ b/Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml @@ -49,6 +49,7 @@ properties: properties: data-lanes: + minItems: 1 maxItems: 2 required: -- GitLab From 92cc5d00a431e96e5a49c0b97e5ad4fa7536bd4b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 3 May 2023 02:33:51 +0000 Subject: [PATCH 4607/5631] locking/rwsem: Add __always_inline annotation to __down_read_common() and inlined callers Apparently despite it being marked inline, the compiler may not inline __down_read_common() which makes it difficult to identify the cause of lock contention, as the blocked function in traceevents will always be listed as __down_read_common(). So this patch adds __always_inline annotation to the common function (as well as the inlined helper callers) to force it to be inlined so the blocking function will be listed (via Wchan) in traceevents. Fixes: c995e638ccbb ("locking/rwsem: Fold __down_{read,write}*()") Reported-by: Tim Murray Signed-off-by: John Stultz Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Waiman Long Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20230503023351.2832796-1-jstultz@google.com --- kernel/locking/rwsem.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index acb5a50309a1..9eabd585ce7a 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1240,7 +1240,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) /* * lock for reading */ -static inline int __down_read_common(struct rw_semaphore *sem, int state) +static __always_inline int __down_read_common(struct rw_semaphore *sem, int state) { int ret = 0; long count; @@ -1258,17 +1258,17 @@ static inline int __down_read_common(struct rw_semaphore *sem, int state) return ret; } -static inline void __down_read(struct rw_semaphore *sem) +static __always_inline void __down_read(struct rw_semaphore *sem) { __down_read_common(sem, TASK_UNINTERRUPTIBLE); } -static inline int __down_read_interruptible(struct rw_semaphore *sem) +static __always_inline int __down_read_interruptible(struct rw_semaphore *sem) { return __down_read_common(sem, TASK_INTERRUPTIBLE); } -static inline int __down_read_killable(struct rw_semaphore *sem) +static __always_inline int __down_read_killable(struct rw_semaphore *sem) { return __down_read_common(sem, TASK_KILLABLE); } -- GitLab From 1d1bfe30dad50d4bea83cd38d73c441972ea0173 Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Tue, 25 Apr 2023 10:32:17 +0000 Subject: [PATCH 4608/5631] perf/core: Fix perf_sample_data not properly initialized for different swevents in perf_tp_event() data->sample_flags may be modified in perf_prepare_sample(), in perf_tp_event(), different swevents use the same on-stack perf_sample_data, the previous swevent may change sample_flags in perf_prepare_sample(), as a result, some members of perf_sample_data are not correctly initialized when next swevent_event preparing sample (for example data->id, the value varies according to swevent). A simple scenario triggers this problem is as follows: # perf record -e sched:sched_switch --switch-output-event sched:sched_switch -a sleep 1 [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209014396 ] [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209014662 ] [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209014910 ] [ perf record: Woken up 0 times to write data ] [ perf record: Dump perf.data.2023041209015164 ] [ perf record: Captured and wrote 0.069 MB perf.data. ] # ls -l total 860 -rw------- 1 root root 95694 Apr 12 09:01 perf.data.2023041209014396 -rw------- 1 root root 606430 Apr 12 09:01 perf.data.2023041209014662 -rw------- 1 root root 82246 Apr 12 09:01 perf.data.2023041209014910 -rw------- 1 root root 82342 Apr 12 09:01 perf.data.2023041209015164 # perf script -i perf.data.2023041209014396 0x11d58 [0x80]: failed to process type: 9 [Bad address] Solution: Re-initialize perf_sample_data after each event is processed. Note that data->raw->frag.data may be accessed in perf_tp_event_match(). Therefore, need to init sample_data and then go through swevent hlist to prevent reference of NULL pointer, reported by [1]. After fix: # perf record -e sched:sched_switch --switch-output-event sched:sched_switch -a sleep 1 [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209442259 ] [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209442514 ] [ perf record: dump data: Woken up 0 times ] [ perf record: Dump perf.data.2023041209442760 ] [ perf record: Woken up 0 times to write data ] [ perf record: Dump perf.data.2023041209443003 ] [ perf record: Captured and wrote 0.069 MB perf.data. ] # ls -l total 864 -rw------- 1 root root 100166 Apr 12 09:44 perf.data.2023041209442259 -rw------- 1 root root 606438 Apr 12 09:44 perf.data.2023041209442514 -rw------- 1 root root 82246 Apr 12 09:44 perf.data.2023041209442760 -rw------- 1 root root 82342 Apr 12 09:44 perf.data.2023041209443003 # perf script -i perf.data.2023041209442259 | head -n 5 perf 232 [000] 66.846217: sched:sched_switch: prev_comm=perf prev_pid=232 prev_prio=120 prev_state=D ==> next_comm=perf next_pid=234 next_prio=120 perf 234 [000] 66.846449: sched:sched_switch: prev_comm=perf prev_pid=234 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=232 next_prio=120 perf 232 [000] 66.846546: sched:sched_switch: prev_comm=perf prev_pid=232 prev_prio=120 prev_state=R ==> next_comm=perf next_pid=234 next_prio=120 perf 234 [000] 66.846606: sched:sched_switch: prev_comm=perf prev_pid=234 prev_prio=120 prev_state=S ==> next_comm=perf next_pid=232 next_prio=120 perf 232 [000] 66.846646: sched:sched_switch: prev_comm=perf prev_pid=232 prev_prio=120 prev_state=R ==> next_comm=perf next_pid=234 next_prio=120 [1] Link: https://lore.kernel.org/oe-lkp/202304250929.efef2caa-yujie.liu@intel.com Fixes: bb447c27a467 ("perf/core: Set data->sample_flags in perf_prepare_sample()") Signed-off-by: Yang Jihong Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230425103217.130600-1-yangjihong1@huawei.com --- kernel/events/core.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 68baa8194d9f..db016e418931 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10150,8 +10150,20 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, perf_trace_buf_update(record, event_type); hlist_for_each_entry_rcu(event, head, hlist_entry) { - if (perf_tp_event_match(event, &data, regs)) + if (perf_tp_event_match(event, &data, regs)) { perf_swevent_event(event, count, &data, regs); + + /* + * Here use the same on-stack perf_sample_data, + * some members in data are event-specific and + * need to be re-computed for different sweveents. + * Re-initialize data->sample_flags safely to avoid + * the problem that next event skips preparing data + * because data->sample_flags is set. + */ + perf_sample_data_init(&data, 0, 0); + perf_sample_save_raw_data(&data, &raw); + } } /* -- GitLab From 90befef5a9e820ccccc33181ec14c015980300cc Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 26 Apr 2023 20:05:27 -0700 Subject: [PATCH 4609/5631] perf/x86: Fix missing sample size update on AMD BRS It missed to convert a PERF_SAMPLE_BRANCH_STACK user to call the new perf_sample_save_brstack() helper in order to update the dyn_size. This affects AMD Zen3 machines with the branch-brs event. Fixes: eb55b455ef9c ("perf/core: Add perf_sample_save_brstack() helper") Signed-off-by: Namhyung Kim Signed-off-by: Peter Zijlstra (Intel) Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20230427030527.580841-1-namhyung@kernel.org --- arch/x86/events/core.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index d096b04bf80e..9d248703cbdd 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1703,10 +1703,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) { - data.br_stack = &cpuc->lbr_stack; - data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); -- GitLab From b752ea0c28e3f7f0aaaad6abf84f735eebc37a60 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Fri, 21 Apr 2023 11:45:28 -0700 Subject: [PATCH 4610/5631] perf/x86/intel/ds: Flush PEBS DS when changing PEBS_DATA_CFG Several similar kernel warnings can be triggered, [56605.607840] CPU0 PEBS record size 0, expected 32, config 0 cpuc->record_size=208 when the below commands are running in parallel for a while on SPR. while true; do perf record --no-buildid -a --intr-regs=AX \ -e cpu/event=0xd0,umask=0x81/pp \ -c 10003 -o /dev/null ./triad; done & while true; do perf record -o /tmp/out -W -d \ -e '{ld_blocks.store_forward:period=1000000, \ MEM_TRANS_RETIRED.LOAD_LATENCY:u:precise=2:ldlat=4}' \ -c 1037 ./triad; done The triad program is just the generation of loads/stores. The warnings are triggered when an unexpected PEBS record (with a different config and size) is found. A system-wide PEBS event with the large PEBS config may be enabled during a context switch. Some PEBS records for the system-wide PEBS may be generated while the old task is sched out but the new one hasn't been sched in yet. When the new task is sched in, the cpuc->pebs_record_size may be updated for the per-task PEBS events. So the existing system-wide PEBS records have a different size from the later PEBS records. The PEBS buffer should be flushed right before the hardware is reprogrammed. The new size and threshold should be updated after the old buffer has been flushed. Reported-by: Stephane Eranian Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230421184529.3320912-1-kan.liang@linux.intel.com --- arch/x86/events/intel/ds.c | 56 ++++++++++++++++++------------- arch/x86/include/asm/perf_event.h | 3 ++ 2 files changed, 35 insertions(+), 24 deletions(-) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index a2e566e53076..df88576d6b2a 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1229,12 +1229,14 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct perf_event *event, bool add) { struct pmu *pmu = event->pmu; + /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but * that does not hurt: */ - bool update = cpuc->n_pebs == 1; + if (cpuc->n_pebs == 1) + cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { if (!needed_cb) @@ -1242,7 +1244,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, else perf_sched_cb_dec(pmu); - update = true; + cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW; } /* @@ -1252,24 +1254,13 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, if (x86_pmu.intel_cap.pebs_baseline && add) { u64 pebs_data_cfg; - /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ - if (cpuc->n_pebs == 1) { - cpuc->pebs_data_cfg = 0; - cpuc->pebs_record_size = sizeof(struct pebs_basic); - } - pebs_data_cfg = pebs_update_adaptive_cfg(event); - - /* Update pebs_record_size if new event requires more data. */ - if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { - cpuc->pebs_data_cfg |= pebs_data_cfg; - adaptive_pebs_record_size_update(); - update = true; - } + /* + * Be sure to update the thresholds when we change the record. + */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) + cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW; } - - if (update) - pebs_update_threshold(cpuc); } void intel_pmu_pebs_add(struct perf_event *event) @@ -1326,9 +1317,17 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) wrmsrl(base + idx, value); } +static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) +{ + if (cpuc->n_pebs == cpuc->n_large_pebs && + cpuc->n_pebs != cpuc->n_pebs_via_pt) + intel_pmu_drain_pebs_buffer(); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW; struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; unsigned int idx = hwc->idx; @@ -1344,11 +1343,22 @@ void intel_pmu_pebs_enable(struct perf_event *event) if (x86_pmu.intel_cap.pebs_baseline) { hwc->config |= ICL_EVENTSEL_ADAPTIVE; - if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { - wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); - cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + if (pebs_data_cfg != cpuc->active_pebs_data_cfg) { + /* + * drain_pebs() assumes uniform record size; + * hence we need to drain when changing said + * size. + */ + intel_pmu_drain_large_pebs(cpuc); + adaptive_pebs_record_size_update(); + wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg); + cpuc->active_pebs_data_cfg = pebs_data_cfg; } } + if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) { + cpuc->pebs_data_cfg = pebs_data_cfg; + pebs_update_threshold(cpuc); + } if (idx >= INTEL_PMC_IDX_FIXED) { if (x86_pmu.intel_cap.pebs_format < 5) @@ -1391,9 +1401,7 @@ void intel_pmu_pebs_disable(struct perf_event *event) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) - intel_pmu_drain_pebs_buffer(); + intel_pmu_drain_large_pebs(cpuc); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8fc15ed5e60b..abf09882f58b 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -121,6 +121,9 @@ #define PEBS_DATACFG_LBRS BIT_ULL(3) #define PEBS_DATACFG_LBR_SHIFT 24 +/* Steal the highest bit of pebs_data_cfg for SW usage */ +#define PEBS_UPDATE_DS_SW BIT_ULL(63) + /* * Intel "Architectural Performance Monitoring" CPUID * detection/enumeration details: -- GitLab From 0019a2d4b7e37a983d133d42b707b8a3018ae6f4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Thu, 27 Apr 2023 20:11:11 -0700 Subject: [PATCH 4611/5631] sched: fix cid_lock kernel-doc warnings Fix kernel-doc warnings for cid_lock and use_cid_lock. These comments are not in kernel-doc format. kernel/sched/core.c:11496: warning: Cannot understand * @cid_lock: Guarantee forward-progress of cid allocation. on line 11496 - I thought it was a doc line kernel/sched/core.c:11505: warning: Cannot understand * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock. on line 11505 - I thought it was a doc line Fixes: 223baf9d17f2 ("sched: Fix performance regression introduced by mm_cid") Signed-off-by: Randy Dunlap Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20230428031111.322-1-rdunlap@infradead.org --- kernel/sched/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 944c3ae39861..a68d1276bab0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -11492,7 +11492,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) #ifdef CONFIG_SCHED_MM_CID -/** +/* * @cid_lock: Guarantee forward-progress of cid allocation. * * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock @@ -11501,7 +11501,7 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) */ DEFINE_RAW_SPINLOCK(cid_lock); -/** +/* * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock. * * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is -- GitLab From 9bf03a0cbd80a256bc1e1c4bcc80bc2b06b8b2b9 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 2 May 2023 12:38:09 +0200 Subject: [PATCH 4612/5631] phy: qcom-qmp-combo: fix init-count imbalance The init counter is not decremented on initialisation errors, which prevents retrying initialisation and can lead to the runtime suspend callback attempting to disable resources that have never been enabled. Add the missing decrement on initialisation errors so that the counter reflects the state of the device. Fixes: e78f3d15e115 ("phy: qcom-qmp: new qmp phy driver for qcom-chipsets") Cc: stable@vger.kernel.org # 4.12 Signed-off-by: Johan Hovold Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230502103810.12061-2-johan+linaro@kernel.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 6850e04c329b..87b17e5877ab 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2472,7 +2472,7 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -2522,7 +2522,8 @@ static int qmp_combo_com_init(struct qmp_combo *qmp) reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; -- GitLab From e42f110700ed7293700c26145e1ed07ea05ac3f6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 2 May 2023 12:38:10 +0200 Subject: [PATCH 4613/5631] phy: qcom-qmp-pcie-msm8996: fix init-count imbalance The init counter is not decremented on initialisation errors, which prevents retrying initialisation. Add the missing decrement on initialisation errors so that the counter reflects the state of the device. Fixes: e78f3d15e115 ("phy: qcom-qmp: new qmp phy driver for qcom-chipsets") Cc: stable@vger.kernel.org # 4.12 Signed-off-by: Johan Hovold Reviewed-by: Dmitry Baryshkov Link: https://lore.kernel.org/r/20230502103810.12061-3-johan+linaro@kernel.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c index 09824be088c9..0c603bc06e09 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie-msm8996.c @@ -379,7 +379,7 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) ret = regulator_bulk_enable(cfg->num_vregs, qmp->vregs); if (ret) { dev_err(qmp->dev, "failed to enable regulators, err=%d\n", ret); - goto err_unlock; + goto err_decrement_count; } ret = reset_control_bulk_assert(cfg->num_resets, qmp->resets); @@ -409,7 +409,8 @@ static int qmp_pcie_msm8996_com_init(struct qmp_phy *qphy) reset_control_bulk_assert(cfg->num_resets, qmp->resets); err_disable_regulators: regulator_bulk_disable(cfg->num_vregs, qmp->vregs); -err_unlock: +err_decrement_count: + qmp->init_count--; mutex_unlock(&qmp->phy_mutex); return ret; -- GitLab From 23a5b8bb022c1e071ca91b1a9c10f0ad6a0966e9 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 27 Apr 2023 00:33:36 -0500 Subject: [PATCH 4614/5631] x86/amd_nb: Add PCI ID for family 19h model 78h Commit 310e782a99c7 ("platform/x86/amd: pmc: Utilize SMN index 0 for driver probe") switched to using amd_smn_read() which relies upon the misc PCI ID used by DF function 3 being included in a table. The ID for model 78h is missing in that table, so amd_smn_read() doesn't work. Add the missing ID into amd_nb, restoring s2idle on this system. [ bp: Simplify commit message. ] Fixes: 310e782a99c7 ("platform/x86/amd: pmc: Utilize SMN index 0 for driver probe") Signed-off-by: Mario Limonciello Signed-off-by: Borislav Petkov (AMD) Acked-by: Bjorn Helgaas # pci_ids.h Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20230427053338.16653-2-mario.limonciello@amd.com --- arch/x86/kernel/amd_nb.c | 2 ++ include/linux/pci_ids.h | 1 + 2 files changed, 3 insertions(+) diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4266b64631a4..7e331e8f3692 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -36,6 +36,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); @@ -79,6 +80,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, {} }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 45c3d62e616d..95f33dadb2be 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -567,6 +567,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 -- GitLab From 7d8accfaa0ab65e4282c8e58950f7d688342cd86 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Thu, 27 Apr 2023 00:33:37 -0500 Subject: [PATCH 4615/5631] hwmon: (k10temp) Add PCI ID for family 19, model 78h Enable k10temp on this system. [ bp: Massage. ] Signed-off-by: Mario Limonciello Signed-off-by: Borislav Petkov (AMD) Acked-by: Guenter Roeck Link: https://lore.kernel.org/r/20230427053338.16653-3-mario.limonciello@amd.com --- drivers/hwmon/k10temp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index ba2f6a4f8c16..7b177b9fbb09 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -507,6 +507,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_VDEVICE(HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, {} }; -- GitLab From 6ad9cf7a615287d640deb4a6530c4d9846621be0 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 24 Apr 2023 13:40:43 +0200 Subject: [PATCH 4616/5631] MAINTAINERS: adjust file entry for ARM/APPLE MACHINE SUPPORT Commit de614ac31955 ("MAINTAINERS: Add entries for Apple PWM driver") adds an entry for Documentation/devicetree/bindings/pwm/pwm-apple.yaml, but commit 87a3a3929c71 ("dt-bindings: pwm: Add Apple PWM controller") from the same patch series actually adds the devicetree binding file with the name apple,s5l-fpwm.yaml. Adjust the file entry to the file actually added. Fixes: de614ac31955 ("MAINTAINERS: Add entries for Apple PWM driver") Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230424114043.22475-1-lukas.bulwahn@gmail.com Signed-off-by: Krzysztof Kozlowski --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e0b87d5aa2e..47fa34c4cbb2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1961,7 +1961,7 @@ F: Documentation/devicetree/bindings/nvmem/apple,efuses.yaml F: Documentation/devicetree/bindings/pci/apple,pcie.yaml F: Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml F: Documentation/devicetree/bindings/power/apple* -F: Documentation/devicetree/bindings/pwm/pwm-apple.yaml +F: Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml F: Documentation/devicetree/bindings/watchdog/apple,wdt.yaml F: arch/arm64/boot/dts/apple/ F: drivers/bluetooth/hci_bcm4377.c -- GitLab From 879c5a458e532b95783ce27f704d1b21573066f7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 21:54:31 +0100 Subject: [PATCH 4617/5631] media: rcar-vin: Gen3 can not scale NV12 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The VIN modules on Gen3 can not scale NV12, fail format validation if the user tries. Currently no frames are produced if this is attempted. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil --- drivers/media/platform/renesas/rcar-vin/rcar-dma.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index 98bfd445a649..cc6b59e5621a 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -1312,6 +1312,11 @@ static int rvin_mc_validate_format(struct rvin_dev *vin, struct v4l2_subdev *sd, } if (rvin_scaler_needed(vin)) { + /* Gen3 can't scale NV12 */ + if (vin->info->model == RCAR_GEN3 && + vin->format.pixelformat == V4L2_PIX_FMT_NV12) + return -EPIPE; + if (!vin->scaler) return -EPIPE; } else { -- GitLab From cb88d8289fc222bd21b7a7f99b055e7e73e316f4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 21:54:32 +0100 Subject: [PATCH 4618/5631] media: rcar-vin: Fix NV12 size alignment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When doing format validation for NV12 the width and height should be aligned to 32 pixels. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil --- drivers/media/platform/renesas/rcar-vin/rcar-dma.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index cc6b59e5621a..23598e22adc7 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -1320,9 +1320,15 @@ static int rvin_mc_validate_format(struct rvin_dev *vin, struct v4l2_subdev *sd, if (!vin->scaler) return -EPIPE; } else { - if (fmt.format.width != vin->format.width || - fmt.format.height != vin->format.height) - return -EPIPE; + if (vin->format.pixelformat == V4L2_PIX_FMT_NV12) { + if (ALIGN(fmt.format.width, 32) != vin->format.width || + ALIGN(fmt.format.height, 32) != vin->format.height) + return -EPIPE; + } else { + if (fmt.format.width != vin->format.width || + fmt.format.height != vin->format.height) + return -EPIPE; + } } if (fmt.format.code != vin->mbus_code) -- GitLab From e10707d5865c90d3dfe4ef589ce02ff4287fef85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Niklas=20S=C3=B6derlund?= Date: Sat, 11 Feb 2023 21:55:34 +0100 Subject: [PATCH 4619/5631] media: rcar-vin: Select correct interrupt mode for V4L2_FIELD_ALTERNATE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When adding proper support for V4L2_FIELD_ALTERNATE it was missed that this field format should trigger an interrupt for each field, not just for the whole frame. Fix this by marking it as progressive in the capture setup, which will then select the correct interrupt mode. Tested on both Gen2 and Gen3 with the result of a doubling of the frame rate for V4L2_FIELD_ALTERNATE. From a PAL video source the frame rate is now 50, which is expected for alternate field capture. Signed-off-by: Niklas Söderlund Signed-off-by: Hans Verkuil --- drivers/media/platform/renesas/rcar-vin/rcar-dma.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c index 23598e22adc7..2a77353f10b5 100644 --- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c +++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c @@ -728,11 +728,9 @@ static int rvin_setup(struct rvin_dev *vin) case V4L2_FIELD_SEQ_TB: case V4L2_FIELD_SEQ_BT: case V4L2_FIELD_NONE: - vnmc = VNMC_IM_ODD_EVEN; - progressive = true; - break; case V4L2_FIELD_ALTERNATE: vnmc = VNMC_IM_ODD_EVEN; + progressive = true; break; default: vnmc = VNMC_IM_ODD; -- GitLab From 55e2a6e36be6d61f914898ce731f9321c0dcf4e8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 11:19:55 +0200 Subject: [PATCH 4620/5631] media: nxp: ignore unused suspend operations gcc warns about some functions being unused when CONFIG_PM_SLEEP is disabled: drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c:328:12: error: 'mxc_isi_pm_resume' defined but not used [-Werror=unused-function] 328 | static int mxc_isi_pm_resume(struct device *dev) | ^~~~~~~~~~~~~~~~~ drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c:314:12: error: 'mxc_isi_pm_suspend' defined but not used [-Werror=unused-function] 314 | static int mxc_isi_pm_suspend(struct device *dev) | ^~~~~~~~~~~~~~~~~~ Use the modern SYSTEM_SLEEP_PM_OPS()/RUNTIME_PM_OPS() helpers in place of the old SET_SYSTEM_SLEEP_PM_OPS()/SET_RUNTIME_PM_OPS() ones. By convention, use pm_ptr() to guard the reference to the operations. This makes no difference as long as the driver requires CONFIG_PM, but is what users of SET_RUNTIME_PM_OPS() are supposed to do. Fixes: cf21f328fcaf ("media: nxp: Add i.MX8 ISI driver") Reviewed-by: Laurent Pinchart Signed-off-by: Arnd Bergmann Signed-off-by: Hans Verkuil --- drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c index 238521622b75..253e77189b69 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-core.c @@ -378,8 +378,8 @@ static int mxc_isi_runtime_resume(struct device *dev) } static const struct dev_pm_ops mxc_isi_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(mxc_isi_pm_suspend, mxc_isi_pm_resume) - SET_RUNTIME_PM_OPS(mxc_isi_runtime_suspend, mxc_isi_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(mxc_isi_pm_suspend, mxc_isi_pm_resume) + RUNTIME_PM_OPS(mxc_isi_runtime_suspend, mxc_isi_runtime_resume, NULL) }; /* ----------------------------------------------------------------------------- @@ -528,7 +528,7 @@ static struct platform_driver mxc_isi_driver = { .driver = { .of_match_table = mxc_isi_of_match, .name = MXC_ISI_DRIVER_NAME, - .pm = &mxc_isi_pm_ops, + .pm = pm_ptr(&mxc_isi_pm_ops), } }; module_platform_driver(mxc_isi_driver); -- GitLab From ae3c253f595b31ff30d55b4c50b4470e56bc4e0d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 11:15:48 +0200 Subject: [PATCH 4621/5631] media: platform: mtk-mdp3: work around unused-variable warning When CONFIG_OF is disabled, the 'data' variable is not used at all because of_match_node() turns into a dummy macro: drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c: In function 'mdp_comp_sub_create': drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c:1038:36: error: unused variable 'data' [-Werror=unused-variable] 1038 | const struct mtk_mdp_driver_data *data = mdp->mdp_data; | ^~~~ Remove the variable again by moving the pointer dereference into the of_match_node call. Fixes: b385b991ef2f ("media: platform: mtk-mdp3: chip config split about subcomponents") Signed-off-by: Arnd Bergmann Signed-off-by: Hans Verkuil --- drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c index 75c92e282fa2..19a4a085f73a 100644 --- a/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c +++ b/drivers/media/platform/mediatek/mdp3/mtk-mdp3-comp.c @@ -1035,7 +1035,6 @@ static int mdp_comp_sub_create(struct mdp_dev *mdp) { struct device *dev = &mdp->pdev->dev; struct device_node *node, *parent; - const struct mtk_mdp_driver_data *data = mdp->mdp_data; parent = dev->of_node->parent; @@ -1045,7 +1044,7 @@ static int mdp_comp_sub_create(struct mdp_dev *mdp) int id, alias_id; struct mdp_comp *comp; - of_id = of_match_node(data->mdp_sub_comp_dt_ids, node); + of_id = of_match_node(mdp->mdp_data->mdp_sub_comp_dt_ids, node); if (!of_id) continue; if (!of_device_is_available(node)) { -- GitLab From 1a7edd041f2d252f251523ba3f2eaead076a8f8d Mon Sep 17 00:00:00 2001 From: Keoseong Park Date: Tue, 25 Apr 2023 12:17:21 +0900 Subject: [PATCH 4622/5631] scsi: ufs: core: Fix I/O hang that occurs when BKOPS fails in W-LUN suspend Even when urgent BKOPS fails, the consumer will get stuck in runtime suspend status. Like commit 1a5665fc8d7a ("scsi: ufs: core: WLUN suspend SSU/enter hibern8 fail recovery"), trigger the error handler and return -EBUSY to break the suspend. Fixes: b294ff3e3449 ("scsi: ufs: core: Enable power management for wlun") Signed-off-by: Keoseong Park Link: https://lore.kernel.org/r/20230425031721epcms2p5d4de65616478c967d466626e20c42a3a@epcms2p5 Reviewed-by: Avri Altman Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 17d7bb875fee..45fd374fe56c 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -9459,8 +9459,16 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) * that performance might be impacted. */ ret = ufshcd_urgent_bkops(hba); - if (ret) + if (ret) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; goto enable_scaling; + } } else { /* make sure that auto bkops is disabled */ ufshcd_disable_auto_bkops(hba); -- GitLab From 79de36042eecb684e0f748d17ba52f365fde0d65 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 5 May 2023 12:18:17 -0500 Subject: [PATCH 4623/5631] powerpc/isa-bridge: Fix ISA mapping when "ranges" is not present Commit e4ab08be5b49 ("powerpc/isa-bridge: Remove open coded "ranges" parsing") broke PASemi Nemo board booting. The issue is the ISA I/O range was not getting mapped as the logic to handle no "ranges" was inverted. If phb_io_base_phys is non-zero, then the ISA range defaults to the first 64K of the PCI I/O space. phb_io_base_phys should only be 0 when looking for a non-PCI ISA region. Fixes: e4ab08be5b49 ("powerpc/isa-bridge: Remove open coded "ranges" parsing") Reported-by: Christian Zigotzky Link: https://lore.kernel.org/all/301595ad-0edf-2113-b55f-f5b8051ed24c@xenosoft.de/ Signed-off-by: Rob Herring Tested-by: Christian Zigotzky Signed-off-by: Michael Ellerman Link: https://msgid.link/20230505171816.3175865-1-robh@kernel.org --- arch/powerpc/kernel/isa-bridge.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index 85bdd7d3652f..48e0eaf1ad61 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -93,11 +93,12 @@ static int process_ISA_OF_ranges(struct device_node *isa_node, } inval_range: - if (!phb_io_base_phys) { + if (phb_io_base_phys) { pr_err("no ISA IO ranges or unexpected isa range, mapping 64k\n"); remap_isa_base(phb_io_base_phys, 0x10000); + return 0; } - return 0; + return -EINVAL; } -- GitLab From 536d948a8dee21166d9c5b5a4189af56beba16e3 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 28 Apr 2023 21:35:19 -0700 Subject: [PATCH 4624/5631] powerpc/fsl_uli1575: fix kconfig warnings and build errors MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Neither FSL_SOC_BOOKE nor PPC_86xx enables CONFIG_PCI by default, so it may be unset in some randconfigs. When that happens, FSL_ULI1575 may be set when it should not be since it is a PCI driver. When it is set, there are 3 kconfig warnings and a slew of build errors WARNING: unmet direct dependencies detected for PCI_QUIRKS Depends on [n]: PCI [=n] Selected by [y]: - FSL_PCI [=y] WARNING: unmet direct dependencies detected for GENERIC_ISA_DMA Depends on [n]: ISA_DMA_API [=n] Selected by [y]: - FSL_ULI1575 [=y] && (FSL_SOC_BOOKE [=n] || PPC_86xx [=y]) WARNING: unmet direct dependencies detected for PPC_INDIRECT_PCI Depends on [n]: PCI [=n] Selected by [y]: - FSL_PCI [=y] and 30+ build errors. Fixes: 22fdf79171e8 ("powerpc/fsl_uli1575: Allow to disable FSL_ULI1575 support") Signed-off-by: Randy Dunlap Reviewed-by: Pali Rohár Signed-off-by: Michael Ellerman Link: https://msgid.link/20230429043519.19807-1-rdunlap@infradead.org --- arch/powerpc/platforms/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 0d9b7609c7d5..3e2e252016f7 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -265,6 +265,7 @@ config CPM2 config FSL_ULI1575 bool "ULI1575 PCIe south bridge support" depends on FSL_SOC_BOOKE || PPC_86xx + depends on PCI select FSL_PCI select GENERIC_ISA_DMA help -- GitLab From a5299ce4e96f3e8930e9c051b28d8093ada87b08 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:29 +0200 Subject: [PATCH 4625/5631] power: supply: ab8500: Fix external_power_changed race ab8500_btemp_external_power_changed() dereferences di->btemp_psy, which gets sets in ab8500_btemp_probe() like this: di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc, &psy_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where ab8500_btemp_external_power_changed() may get called while di->btemp_psy has not been set yet leading to a NULL pointer dereference. Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in di->btemp_psy, so ab8500_btemp_external_power_changed() can simply directly use the passed in psy argument which is always valid. And the same applies to ab8500_fg_external_power_changed(). Signed-off-by: Hans de Goede Reviewed-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/ab8500_btemp.c | 6 ++---- drivers/power/supply/ab8500_fg.c | 6 ++---- 2 files changed, 4 insertions(+), 8 deletions(-) diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 307ee6f71042..6f83e99d2eb7 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -624,10 +624,8 @@ static int ab8500_btemp_get_ext_psy_data(struct device *dev, void *data) */ static void ab8500_btemp_external_power_changed(struct power_supply *psy) { - struct ab8500_btemp *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->btemp_psy, ab8500_btemp_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_btemp_get_ext_psy_data); } /* ab8500 btemp driver interrupts and their respective isr */ diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index 41a7bff9ac37..53560fbb6dcd 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -2407,10 +2407,8 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di) */ static void ab8500_fg_external_power_changed(struct power_supply *psy) { - struct ab8500_fg *di = power_supply_get_drvdata(psy); - - class_for_each_device(power_supply_class, NULL, - di->fg_psy, ab8500_fg_get_ext_psy_data); + class_for_each_device(power_supply_class, NULL, psy, + ab8500_fg_get_ext_psy_data); } /** -- GitLab From f8319774d6f1567d6e7d03653174ab0c82c5c66d Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:30 +0200 Subject: [PATCH 4626/5631] power: supply: axp288_fuel_gauge: Fix external_power_changed race fuel_gauge_external_power_changed() dereferences info->bat, which gets sets in axp288_fuel_gauge_probe() like this: info->bat = devm_power_supply_register(dev, &fuel_gauge_desc, &psy_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where fuel_gauge_external_power_changed() may get called while info->bat has not been set yet leading to a NULL pointer dereference. Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in info->bat, so fuel_gauge_external_power_changed() can simply directly use the passed in psy argument which is always valid. Fixes: 30abb3d07929 ("power: supply: axp288_fuel_gauge: Take lock before updating the valid flag") Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/axp288_fuel_gauge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c index 05f413178462..3be6f3b10ea4 100644 --- a/drivers/power/supply/axp288_fuel_gauge.c +++ b/drivers/power/supply/axp288_fuel_gauge.c @@ -507,7 +507,7 @@ static void fuel_gauge_external_power_changed(struct power_supply *psy) mutex_lock(&info->lock); info->valid = 0; /* Force updating of the cached registers */ mutex_unlock(&info->lock); - power_supply_changed(info->bat); + power_supply_changed(psy); } static struct power_supply_desc fuel_gauge_desc = { -- GitLab From 029a443b9b6424170f00f6dd5b7682e682cce92e Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:31 +0200 Subject: [PATCH 4627/5631] power: supply: bq25890: Fix external_power_changed race bq25890_charger_external_power_changed() dereferences bq->charger, which gets sets in bq25890_power_supply_init() like this: bq->charger = devm_power_supply_register(bq->dev, &bq->desc, &psy_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where bq25890_charger_external_power_changed() may get called while bq->charger has not been set yet leading to a NULL pointer dereference. This race hits during boot sometimes on a Lenovo Yoga Book 1 yb1-x90f when the cht_wcove_pwrsrc (extcon) power_supply is done with detecting the connected charger-type which happens to exactly hit the small window: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:__power_supply_is_supplied_by+0xb/0xb0 Call Trace: __power_supply_get_supplier_property+0x19/0x50 class_for_each_device+0xb1/0xe0 power_supply_get_property_from_supplier+0x2e/0x50 bq25890_charger_external_power_changed+0x38/0x1b0 [bq25890_charger] __power_supply_changed_work+0x30/0x40 class_for_each_device+0xb1/0xe0 power_supply_changed_work+0x5f/0xe0 Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in bq->charger, so bq25890_charger_external_power_changed() can simply directly use the passed in psy argument which is always valid. Fixes: eab25b4f93aa ("power: supply: bq25890: On the bq25892 set the IINLIM based on external charger detection") Cc: stable@vger.kernel.org Cc: Marek Vasut Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq25890_charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index 22cde35eb144..557ba532d31a 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -750,7 +750,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) if (bq->chip_version != BQ25892) return; - ret = power_supply_get_property_from_supplier(bq->charger, + ret = power_supply_get_property_from_supplier(psy, POWER_SUPPLY_PROP_USB_TYPE, &val); if (ret) -- GitLab From 4d5c129d6c8993fe96e9ae712141eedcb9ca68c2 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 18:07:32 +0200 Subject: [PATCH 4628/5631] power: supply: sc27xx: Fix external_power_changed race sc27xx_fgu_external_power_changed() dereferences data->battery, which gets sets in ab8500_btemp_probe() like this: data->battery = devm_power_supply_register(dev, &sc27xx_fgu_desc, &fgu_cfg); As soon as devm_power_supply_register() has called device_add() the external_power_changed callback can get called. So there is a window where sc27xx_fgu_external_power_changed() may get called while data->battery has not been set yet leading to a NULL pointer dereference. Fixing this is easy. The external_power_changed callback gets passed the power_supply which will eventually get stored in data->battery, so sc27xx_fgu_external_power_changed() can simply directly use the passed in psy argument which is always valid. After this change sc27xx_fgu_external_power_changed() is reduced to just "power_supply_changed(psy);" and it has the same prototype. While at it simply replace it with making the external_power_changed callback directly point to power_supply_changed. Cc: Orson Zhai Cc: Chunyan Zhang Signed-off-by: Hans de Goede Reviewed-by: Baolin Wang Signed-off-by: Sebastian Reichel --- drivers/power/supply/sc27xx_fuel_gauge.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c index 632977f84b95..bd23c4d9fed4 100644 --- a/drivers/power/supply/sc27xx_fuel_gauge.c +++ b/drivers/power/supply/sc27xx_fuel_gauge.c @@ -733,13 +733,6 @@ static int sc27xx_fgu_set_property(struct power_supply *psy, return ret; } -static void sc27xx_fgu_external_power_changed(struct power_supply *psy) -{ - struct sc27xx_fgu_data *data = power_supply_get_drvdata(psy); - - power_supply_changed(data->battery); -} - static int sc27xx_fgu_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { @@ -774,7 +767,7 @@ static const struct power_supply_desc sc27xx_fgu_desc = { .num_properties = ARRAY_SIZE(sc27xx_fgu_props), .get_property = sc27xx_fgu_get_property, .set_property = sc27xx_fgu_set_property, - .external_power_changed = sc27xx_fgu_external_power_changed, + .external_power_changed = power_supply_changed, .property_is_writeable = sc27xx_fgu_property_is_writeable, .no_thermal = true, }; -- GitLab From e4484643991e0f6b89060092563f0dbab9450cbb Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 13 Apr 2023 12:09:41 +0200 Subject: [PATCH 4629/5631] power: supply: leds: Fix blink to LED on transition When a battery's status changes from charging to full then the charging-blink-full-solid trigger tries to change the LED from blinking to solid/on. As is documented in include/linux/leds.h to deactivate blinking / to make the LED solid a LED_OFF must be send: """ * Deactivate blinking again when the brightness is set to LED_OFF * via the brightness_set() callback. """ led_set_brighness() calls with a brightness value other then 0 / LED_OFF merely change the brightness of the LED in its on state while it is blinking. So power_supply_update_bat_leds() must first send a LED_OFF event before the LED_FULL to disable blinking. Fixes: 6501f728c56f ("power_supply: Add new LED trigger charging-blink-solid-full") Signed-off-by: Hans de Goede Reviewed-by: Vasily Khoruzhick Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_leds.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/power_supply_leds.c b/drivers/power/supply/power_supply_leds.c index 702bf83f6e6d..0674483279d7 100644 --- a/drivers/power/supply/power_supply_leds.c +++ b/drivers/power/supply/power_supply_leds.c @@ -35,8 +35,9 @@ static void power_supply_update_bat_leds(struct power_supply *psy) led_trigger_event(psy->charging_full_trig, LED_FULL); led_trigger_event(psy->charging_trig, LED_OFF); led_trigger_event(psy->full_trig, LED_FULL); - led_trigger_event(psy->charging_blink_full_solid_trig, - LED_FULL); + /* Going from blink to LED on requires a LED_OFF event to stop blink */ + led_trigger_event(psy->charging_blink_full_solid_trig, LED_OFF); + led_trigger_event(psy->charging_blink_full_solid_trig, LED_FULL); break; case POWER_SUPPLY_STATUS_CHARGING: led_trigger_event(psy->charging_full_trig, LED_FULL); -- GitLab From 5c34c0aef185dcd10881847b9ebf20046aa77cb4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:32 +0200 Subject: [PATCH 4630/5631] power: supply: bq27xxx: Fix bq27xxx_battery_update() race condition bq27xxx_battery_update() assumes / requires that it is only run once, not multiple times at the same time. But there are 3 possible callers: 1. bq27xxx_battery_poll() delayed_work item handler 2. bq27xxx_battery_irq_handler_thread() I2C IRQ handler 3. bq27xxx_battery_setup() And there is no protection against these racing with each other, fix this race condition by making all callers take di->lock: - Rename bq27xxx_battery_update() to bq27xxx_battery_update_unlocked() - Add new bq27xxx_battery_update() which takes di->lock and then calls bq27xxx_battery_update_unlocked() - Make stale cache check code in bq27xxx_battery_get_property(), which already takes di->lock directly to check the jiffies, call bq27xxx_battery_update_unlocked() instead of messing with the delayed_work item - Make bq27xxx_battery_update_unlocked() mod the delayed-work item so that the next poll is delayed to poll_interval milliseconds after the last update independent of the source of the update Fixes: 740b755a3b34 ("bq27x00: Poll battery state") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 5ff6f44fd47b..79aedf83cc8d 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1761,7 +1761,7 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -void bq27xxx_battery_update(struct bq27xxx_device_info *di) +static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { struct bq27xxx_reg_cache cache = {0, }; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; @@ -1800,6 +1800,16 @@ void bq27xxx_battery_update(struct bq27xxx_device_info *di) di->cache = cache; di->last_update = jiffies; + + if (poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_update); @@ -1810,9 +1820,6 @@ static void bq27xxx_battery_poll(struct work_struct *work) work.work); bq27xxx_battery_update(di); - - if (poll_interval > 0) - schedule_delayed_work(&di->work, poll_interval * HZ); } static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) @@ -1985,10 +1992,8 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); mutex_lock(&di->lock); - if (time_is_before_jiffies(di->last_update + 5 * HZ)) { - cancel_delayed_work_sync(&di->work); - bq27xxx_battery_poll(&di->work.work); - } + if (time_is_before_jiffies(di->last_update + 5 * HZ)) + bq27xxx_battery_update_unlocked(di); mutex_unlock(&di->lock); if (psp != POWER_SUPPLY_PROP_PRESENT && di->cache.flags < 0) -- GitLab From 444ff00734f3878cd54ddd1ed5e2e6dbea9326d5 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:33 +0200 Subject: [PATCH 4631/5631] power: supply: bq27xxx: Fix I2C IRQ race on remove devm_request_threaded_irq() requested IRQs are only free-ed after the driver's remove function has ran. So the IRQ could trigger and call bq27xxx_battery_update() after bq27xxx_battery_teardown() has already run. Switch to explicitly free-ing the IRQ in bq27xxx_battery_i2c_remove() to fix this. Fixes: 8807feb91b76 ("power: bq27xxx_battery: Add interrupt handling support") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery_i2c.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index f8768997333b..6d3c74876339 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -179,7 +179,7 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client) i2c_set_clientdata(client, di); if (client->irq) { - ret = devm_request_threaded_irq(&client->dev, client->irq, + ret = request_threaded_irq(client->irq, NULL, bq27xxx_battery_irq_handler_thread, IRQF_ONESHOT, di->name, di); @@ -209,6 +209,7 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); + free_irq(client->irq, di); bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); -- GitLab From c00bc80462afc7963f449d7f21d896d2f629cacc Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:34 +0200 Subject: [PATCH 4632/5631] power: supply: bq27xxx: Fix poll_interval handling and races on remove Before this patch bq27xxx_battery_teardown() was setting poll_interval = 0 to avoid bq27xxx_battery_update() requeuing the delayed_work item. There are 2 problems with this: 1. If the driver is unbound through sysfs, rather then the module being rmmod-ed, this changes poll_interval unexpectedly 2. This is racy, after it being set poll_interval could be changed before bq27xxx_battery_update() checks it through /sys/module/bq27xxx_battery/parameters/poll_interval Fix this by added a removed attribute to struct bq27xxx_device_info and using that instead of setting poll_interval to 0. There also is another poll_interval related race on remove(), writing /sys/module/bq27xxx_battery/parameters/poll_interval will requeue the delayed_work item for all devices on the bq27xxx_battery_devices list and the device being removed was only removed from that list after cancelling the delayed_work item. Fix this by moving the removal from the bq27xxx_battery_devices list to before cancelling the delayed_work item. Fixes: 8cfaaa811894 ("bq27x00_battery: Fix OOPS caused by unregistring bq27x00 driver") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 22 +++++++++------------- include/linux/power/bq27xxx_battery.h | 1 + 2 files changed, 10 insertions(+), 13 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 79aedf83cc8d..7411f1cf741b 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1801,7 +1801,7 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) di->last_update = jiffies; - if (poll_interval > 0) + if (!di->removed && poll_interval > 0) mod_delayed_work(system_wq, &di->work, poll_interval * HZ); } @@ -2132,22 +2132,18 @@ EXPORT_SYMBOL_GPL(bq27xxx_battery_setup); void bq27xxx_battery_teardown(struct bq27xxx_device_info *di) { - /* - * power_supply_unregister call bq27xxx_battery_get_property which - * call bq27xxx_battery_poll. - * Make sure that bq27xxx_battery_poll will not call - * schedule_delayed_work again after unregister (which cause OOPS). - */ - poll_interval = 0; - - cancel_delayed_work_sync(&di->work); - - power_supply_unregister(di->bat); - mutex_lock(&bq27xxx_list_lock); list_del(&di->list); mutex_unlock(&bq27xxx_list_lock); + /* Set removed to avoid bq27xxx_battery_update() re-queuing the work */ + mutex_lock(&di->lock); + di->removed = true; + mutex_unlock(&di->lock); + + cancel_delayed_work_sync(&di->work); + + power_supply_unregister(di->bat); mutex_destroy(&di->lock); } EXPORT_SYMBOL_GPL(bq27xxx_battery_teardown); diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index a1aa68141d0b..e3322dad9c85 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -68,6 +68,7 @@ struct bq27xxx_device_info { struct bq27xxx_access_methods bus; struct bq27xxx_reg_cache cache; int charge_design_full; + bool removed; unsigned long last_update; struct delayed_work work; struct power_supply *bat; -- GitLab From 35092c5819f8c5acc7bafe3fdbb13d6307c4f5e1 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:35 +0200 Subject: [PATCH 4633/5631] power: supply: bq27xxx: Add cache parameter to bq27xxx_battery_current_and_status() Add a cache parameter to bq27xxx_battery_current_and_status() so that it can optionally use cached flags instead of re-reading them itself. This is a preparation patch for making bq27xxx_battery_update() check the status and have it call power_supply_changed() on status changes. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 7411f1cf741b..1115f233d959 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1840,7 +1840,8 @@ static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) static int bq27xxx_battery_current_and_status( struct bq27xxx_device_info *di, union power_supply_propval *val_curr, - union power_supply_propval *val_status) + union power_supply_propval *val_status, + struct bq27xxx_reg_cache *cache) { bool single_flags = (di->opts & BQ27XXX_O_ZERO); int curr; @@ -1852,10 +1853,14 @@ static int bq27xxx_battery_current_and_status( return curr; } - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); - if (flags < 0) { - dev_err(di->dev, "error reading flags\n"); - return flags; + if (cache) { + flags = cache->flags; + } else { + flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, single_flags); + if (flags < 0) { + dev_err(di->dev, "error reading flags\n"); + return flags; + } } if (di->opts & BQ27XXX_O_ZERO) { @@ -2001,7 +2006,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, switch (psp) { case POWER_SUPPLY_PROP_STATUS: - ret = bq27xxx_battery_current_and_status(di, NULL, val); + ret = bq27xxx_battery_current_and_status(di, NULL, val, NULL); break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: ret = bq27xxx_battery_voltage(di, val); @@ -2010,7 +2015,7 @@ static int bq27xxx_battery_get_property(struct power_supply *psy, val->intval = di->cache.flags < 0 ? 0 : 1; break; case POWER_SUPPLY_PROP_CURRENT_NOW: - ret = bq27xxx_battery_current_and_status(di, val, NULL); + ret = bq27xxx_battery_current_and_status(di, val, NULL, NULL); break; case POWER_SUPPLY_PROP_CAPACITY: ret = bq27xxx_simple_value(di->cache.capacity, val); -- GitLab From ff4c4a2a4437a6d03787c7aafb2617f20c3ef45f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:36 +0200 Subject: [PATCH 4634/5631] power: supply: bq27xxx: Move bq27xxx_battery_update() down Move the bq27xxx_battery_update() functions to below the bq27xxx_battery_current_and_status() function. This is just moving a block of text, no functional changes. This is a preparation patch for making bq27xxx_battery_update() check the status and have it call power_supply_changed() on status changes. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 122 ++++++++++++------------- 1 file changed, 61 insertions(+), 61 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 1115f233d959..8f2995e9850a 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1761,67 +1761,6 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_GOOD; } -static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) -{ - struct bq27xxx_reg_cache cache = {0, }; - bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; - - cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ - if (cache.flags >= 0) { - cache.temperature = bq27xxx_battery_read_temperature(di); - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) - cache.cycle_count = bq27xxx_battery_read_cyct(di); - - /* We only have to read charge design full once */ - if (di->charge_design_full <= 0) - di->charge_design_full = bq27xxx_battery_read_dcap(di); - } - - if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) - power_supply_changed(di->bat); - - if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) - di->cache = cache; - - di->last_update = jiffies; - - if (!di->removed && poll_interval > 0) - mod_delayed_work(system_wq, &di->work, poll_interval * HZ); -} - -void bq27xxx_battery_update(struct bq27xxx_device_info *di) -{ - mutex_lock(&di->lock); - bq27xxx_battery_update_unlocked(di); - mutex_unlock(&di->lock); -} -EXPORT_SYMBOL_GPL(bq27xxx_battery_update); - -static void bq27xxx_battery_poll(struct work_struct *work) -{ - struct bq27xxx_device_info *di = - container_of(work, struct bq27xxx_device_info, - work.work); - - bq27xxx_battery_update(di); -} - static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) { if (di->opts & BQ27XXX_O_ZERO) @@ -1895,6 +1834,67 @@ static int bq27xxx_battery_current_and_status( return 0; } +static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) +{ + struct bq27xxx_reg_cache cache = {0, }; + bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; + + cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); + if ((cache.flags & 0xff) == 0xff) + cache.flags = -1; /* read error */ + if (cache.flags >= 0) { + cache.temperature = bq27xxx_battery_read_temperature(di); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); + if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) + cache.cycle_count = bq27xxx_battery_read_cyct(di); + + /* We only have to read charge design full once */ + if (di->charge_design_full <= 0) + di->charge_design_full = bq27xxx_battery_read_dcap(di); + } + + if ((di->cache.capacity != cache.capacity) || + (di->cache.flags != cache.flags)) + power_supply_changed(di->bat); + + if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) + di->cache = cache; + + di->last_update = jiffies; + + if (!di->removed && poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); +} +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); + +static void bq27xxx_battery_poll(struct work_struct *work) +{ + struct bq27xxx_device_info *di = + container_of(work, struct bq27xxx_device_info, + work.work); + + bq27xxx_battery_update(di); +} + /* * Get the average power in µW * Return < 0 if something fails. -- GitLab From 939a116142012926e25de0ea6b7e2f8d86a5f1b6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:37 +0200 Subject: [PATCH 4635/5631] power: supply: bq27xxx: Ensure power_supply_changed() is called on current sign changes On gauges where the current register is signed, there is no charging flag in the flags register. So only checking flags will not result in power_supply_changed() getting called when e.g. a charger is plugged in and the current sign changes from negative (discharging) to positive (charging). This causes userspace's notion of the status to lag until userspace does a poll. And when a power_supply_leds.c LED trigger is used to indicate charging status with a LED, this LED will lag until the capacity percentage changes, which may take many minutes (because the LED trigger only is updated on power_supply_changed() calls). Fix this by calling bq27xxx_battery_current_and_status() on gauges with a signed current register and checking if the status has changed. Fixes: 297a533b3e62 ("bq27x00: Cache battery registers") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 13 ++++++++++++- include/linux/power/bq27xxx_battery.h | 3 +++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 8f2995e9850a..f98b51ce19b5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1836,6 +1836,7 @@ static int bq27xxx_battery_current_and_status( static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) { + union power_supply_propval status = di->last_status; struct bq27xxx_reg_cache cache = {0, }; bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; @@ -1860,14 +1861,24 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) cache.cycle_count = bq27xxx_battery_read_cyct(di); + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + /* We only have to read charge design full once */ if (di->charge_design_full <= 0) di->charge_design_full = bq27xxx_battery_read_dcap(di); } if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; power_supply_changed(di->bat); + } if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) di->cache = cache; diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e3322dad9c85..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__ +#include + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -70,6 +72,7 @@ struct bq27xxx_device_info { int charge_design_full; bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; -- GitLab From 59a99cd462fbdf71f4e845e09f37783035088b4f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:38 +0200 Subject: [PATCH 4636/5631] power: supply: bq27xxx: After charger plug in/out wait 0.5s for things to stabilize bq27xxx_external_power_changed() gets called when the charger is plugged in or out. Rather then immediately scheduling an update wait 0.5 seconds for things to stabilize, so that e.g. the (dis)charge current is stable when bq27xxx_battery_update() runs. Fixes: 740b755a3b34 ("bq27x00: Poll battery state") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index f98b51ce19b5..929e813b9c44 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -2099,8 +2099,8 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) { struct bq27xxx_device_info *di = power_supply_get_drvdata(psy); - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &di->work, HZ / 2); } int bq27xxx_battery_setup(struct bq27xxx_device_info *di) -- GitLab From 59dddea9879713423c7b2ade43c423bb71e0d216 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:39 +0200 Subject: [PATCH 4637/5631] power: supply: bq27xxx: Use mod_delayed_work() instead of cancel() + schedule() Use mod_delayed_work() instead of separate cancel_delayed_work_sync() + schedule_delayed_work() calls. Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq27xxx_battery.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 929e813b9c44..4296600e8912 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1083,10 +1083,8 @@ static int poll_interval_param_set(const char *val, const struct kernel_param *k return ret; mutex_lock(&bq27xxx_list_lock); - list_for_each_entry(di, &bq27xxx_battery_devices, list) { - cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); - } + list_for_each_entry(di, &bq27xxx_battery_devices, list) + mod_delayed_work(system_wq, &di->work, 0); mutex_unlock(&bq27xxx_list_lock); return ret; -- GitLab From ad3d9c779b1f09f3f3a6fefd07af407c7bc7c9a7 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:40 +0200 Subject: [PATCH 4638/5631] power: supply: bq25890: Call power_supply_changed() after updating input current or voltage The bq25892 model relies on external charger-type detection and once that is done the bq25890_charger code will update the input current and if pumpexpress is used also the input voltage. In this case, when the initial power_supply_changed() call is made from the interrupt handler, the input settings are 5V/0.5A which on many devices is not enough power to charge (while the device is on). On many devices the fuel-gauge relies in its external_power_changed callback to timely signal userspace about charging <-> discharging status changes. Add a power_supply_changed() call after updating the input current or voltage. This allows the fuel-gauge driver to timely recheck if the battery is charging after the new input settings have been applied and then it can immediately notify userspace about this. Fixes: 48f45b094dbb ("power: supply: bq25890: Support higher charging voltages through Pump Express+ protocol") Fixes: eab25b4f93aa ("power: supply: bq25890: On the bq25892 set the IINLIM based on external charger detection") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq25890_charger.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c index 557ba532d31a..f8636cf86505 100644 --- a/drivers/power/supply/bq25890_charger.c +++ b/drivers/power/supply/bq25890_charger.c @@ -775,6 +775,7 @@ static void bq25890_charger_external_power_changed(struct power_supply *psy) } bq25890_field_write(bq, F_IINLIM, input_current_limit); + power_supply_changed(psy); } static int bq25890_get_chip_state(struct bq25890_device *bq, @@ -1106,6 +1107,8 @@ static void bq25890_pump_express_work(struct work_struct *data) dev_info(bq->dev, "Hi-voltage charging requested, input voltage is %d mV\n", voltage); + power_supply_changed(bq->charger); + return; error_print: bq25890_field_write(bq, F_PUMPX_EN, 0); -- GitLab From 77c2a3097d7029441e8a91aa0de1b4e5464593da Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sat, 15 Apr 2023 20:23:41 +0200 Subject: [PATCH 4639/5631] power: supply: bq24190: Call power_supply_changed() after updating input current The bq24192 model relies on external charger-type detection and once that is done the bq24190_charger code will update the input current. In this case, when the initial power_supply_changed() call is made from the interrupt handler, the input settings are 5V/0.5A which on many devices is not enough power to charge (while the device is on). On many devices the fuel-gauge relies in its external_power_changed callback to timely signal userspace about charging <-> discharging status changes. Add a power_supply_changed() call after updating the input current. This allows the fuel-gauge driver to timely recheck if the battery is charging after the new input current has been applied and then it can immediately notify userspace about this. Fixes: 18f8e6f695ac ("power: supply: bq24190_charger: Get input_current_limit from our supplier") Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/bq24190_charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index de67b985f0a9..dc33f00fcc06 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1262,6 +1262,7 @@ static void bq24190_input_current_limit_work(struct work_struct *work) bq24190_charger_set_property(bdi->charger, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + power_supply_changed(bdi->charger); } /* Sync the input-current-limit with our parent supply (if we have one) */ -- GitLab From 17955aba7877a4494d8093ae5498e19469b01d57 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Mon, 8 May 2023 18:16:36 +0800 Subject: [PATCH 4640/5631] ASoC: fsl_micfil: Fix error handler with pm_runtime_enable There is error message when defer probe happens: fsl-micfil-dai 30ca0000.micfil: Unbalanced pm_runtime_enable! Fix the error handler with pm_runtime_enable and add fsl_micfil_remove() for pm_runtime_disable. Fixes: 47a70e6fc9a8 ("ASoC: Add MICFIL SoC Digital Audio Interface driver.") Signed-off-by: Shengjiu Wang dev, NULL, 0); if (ret) { dev_err(&pdev->dev, "failed to pcm register\n"); - return ret; + goto err_pm_disable; } fsl_micfil_dai.capture.formats = micfil->soc->formats; @@ -1169,9 +1169,20 @@ static int fsl_micfil_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to register component %s\n", fsl_micfil_component.name); + goto err_pm_disable; } return ret; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void fsl_micfil_remove(struct platform_device *pdev) +{ + pm_runtime_disable(&pdev->dev); } static int __maybe_unused fsl_micfil_runtime_suspend(struct device *dev) @@ -1232,6 +1243,7 @@ static const struct dev_pm_ops fsl_micfil_pm_ops = { static struct platform_driver fsl_micfil_driver = { .probe = fsl_micfil_probe, + .remove_new = fsl_micfil_remove, .driver = { .name = "fsl-micfil-dai", .pm = &fsl_micfil_pm_ops, -- GitLab From e652be0f59d4ba4d5c636b1f7f4dcb73aae049fa Mon Sep 17 00:00:00 2001 From: Hao Zeng Date: Tue, 18 Apr 2023 09:30:56 +0800 Subject: [PATCH 4641/5631] cpupower:Fix resource leaks in sysfs_get_enabled() The sysfs_get_enabled() opened file processor not closed, may cause a file handle leak. Putting error handling and resource cleanup code together makes the code easy to maintain and read. Removed the unnecessary else if branch from the original function, as it should return an error in cases other than '0'. Signed-off-by: Hao Zeng Suggested-by: Shuah Khan Signed-off-by: Shuah Khan --- tools/power/cpupower/lib/powercap.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c index 0ce29ee4c2e4..a7a59c6bacda 100644 --- a/tools/power/cpupower/lib/powercap.c +++ b/tools/power/cpupower/lib/powercap.c @@ -40,25 +40,34 @@ static int sysfs_get_enabled(char *path, int *mode) { int fd; char yes_no; + int ret = 0; *mode = 0; fd = open(path, O_RDONLY); - if (fd == -1) - return -1; + if (fd == -1) { + ret = -1; + goto out; + } if (read(fd, &yes_no, 1) != 1) { - close(fd); - return -1; + ret = -1; + goto out_close; } if (yes_no == '1') { *mode = 1; - return 0; + goto out_close; } else if (yes_no == '0') { - return 0; + goto out_close; + } else { + ret = -1; + goto out_close; } - return -1; +out_close: + close(fd); +out: + return ret; } int powercap_get_enabled(int *mode) -- GitLab From 4a9b6850c794e4394cad99e2b863d75f5bc8e92f Mon Sep 17 00:00:00 2001 From: Julian Winkler Date: Sun, 16 Apr 2023 17:49:32 +0200 Subject: [PATCH 4642/5631] platform/x86: intel_scu_pcidrv: Add back PCI ID for Medfield This id was removed in commit b47018a778c1 ("platform/x86: intel_scu_ipc: Remove Lincroft support"), saying it is only used on Moorestown, but apparently the same id is also used on Medfield. Tested on the Medfield based Motorola RAZR i smartphone. Signed-off-by: Julian Winkler Link: https://lore.kernel.org/r/20230416154932.6579-1-julian.winkler1@web.de Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/intel_scu_pcidrv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/intel_scu_pcidrv.c b/drivers/platform/x86/intel_scu_pcidrv.c index 80abc708e4f2..d904fad499aa 100644 --- a/drivers/platform/x86/intel_scu_pcidrv.c +++ b/drivers/platform/x86/intel_scu_pcidrv.c @@ -34,6 +34,7 @@ static int intel_scu_pci_probe(struct pci_dev *pdev, static const struct pci_device_id pci_ids[] = { { PCI_VDEVICE(INTEL, 0x080e) }, + { PCI_VDEVICE(INTEL, 0x082a) }, { PCI_VDEVICE(INTEL, 0x08ea) }, { PCI_VDEVICE(INTEL, 0x0a94) }, { PCI_VDEVICE(INTEL, 0x11a0) }, -- GitLab From ba0ad6ed89fd5dada3b7b65ef2b08e95d449d4ab Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 18 Apr 2023 08:11:43 +0200 Subject: [PATCH 4643/5631] media: nxp: imx8-isi: fix buiding on 32-bit The #if check is wrong, leading to a build failure: drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c: In function 'mxc_isi_channel_set_inbuf': drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c:33:5: error: "CONFIG_ARCH_DMA_ADDR_T_64BIT" is not defined, evaluates to 0 [-Werror=undef] 33 | #if CONFIG_ARCH_DMA_ADDR_T_64BIT | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ This could just be an #ifdef, but it seems nicer to just remove the check entirely. Apparently the only reason for the #ifdef is to avoid another warning: drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c:55:24: error: right shift count >= width of type [-Werror=shift-count-overflow] But this is best avoided by using the lower_32_bits()/upper_32_bits() helpers. Fixes: cf21f328fcaf ("media: nxp: Add i.MX8 ISI driver") Signed-off-by: Arnd Bergmann Reviewed-by: Laurent Pinchart Signed-off-by: Linus Torvalds --- .../media/platform/nxp/imx8-isi/imx8-isi-hw.c | 41 ++++++++++--------- 1 file changed, 21 insertions(+), 20 deletions(-) diff --git a/drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c b/drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c index db538f3d88ec..19e80b95ffea 100644 --- a/drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c +++ b/drivers/media/platform/nxp/imx8-isi/imx8-isi-hw.c @@ -29,11 +29,10 @@ static inline void mxc_isi_write(struct mxc_isi_pipe *pipe, u32 reg, u32 val) void mxc_isi_channel_set_inbuf(struct mxc_isi_pipe *pipe, dma_addr_t dma_addr) { - mxc_isi_write(pipe, CHNL_IN_BUF_ADDR, dma_addr); -#if CONFIG_ARCH_DMA_ADDR_T_64BIT + mxc_isi_write(pipe, CHNL_IN_BUF_ADDR, lower_32_bits(dma_addr)); if (pipe->isi->pdata->has_36bit_dma) - mxc_isi_write(pipe, CHNL_IN_BUF_XTND_ADDR, dma_addr >> 32); -#endif + mxc_isi_write(pipe, CHNL_IN_BUF_XTND_ADDR, + upper_32_bits(dma_addr)); } void mxc_isi_channel_set_outbuf(struct mxc_isi_pipe *pipe, @@ -45,34 +44,36 @@ void mxc_isi_channel_set_outbuf(struct mxc_isi_pipe *pipe, val = mxc_isi_read(pipe, CHNL_OUT_BUF_CTRL); if (buf_id == MXC_ISI_BUF1) { - mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_Y, dma_addrs[0]); - mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_U, dma_addrs[1]); - mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_V, dma_addrs[2]); -#if CONFIG_ARCH_DMA_ADDR_T_64BIT + mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_Y, + lower_32_bits(dma_addrs[0])); + mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_U, + lower_32_bits(dma_addrs[1])); + mxc_isi_write(pipe, CHNL_OUT_BUF1_ADDR_V, + lower_32_bits(dma_addrs[2])); if (pipe->isi->pdata->has_36bit_dma) { mxc_isi_write(pipe, CHNL_Y_BUF1_XTND_ADDR, - dma_addrs[0] >> 32); + upper_32_bits(dma_addrs[0])); mxc_isi_write(pipe, CHNL_U_BUF1_XTND_ADDR, - dma_addrs[1] >> 32); + upper_32_bits(dma_addrs[1])); mxc_isi_write(pipe, CHNL_V_BUF1_XTND_ADDR, - dma_addrs[2] >> 32); + upper_32_bits(dma_addrs[2])); } -#endif val ^= CHNL_OUT_BUF_CTRL_LOAD_BUF1_ADDR; } else { - mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_Y, dma_addrs[0]); - mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_U, dma_addrs[1]); - mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_V, dma_addrs[2]); -#if CONFIG_ARCH_DMA_ADDR_T_64BIT + mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_Y, + lower_32_bits(dma_addrs[0])); + mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_U, + lower_32_bits(dma_addrs[1])); + mxc_isi_write(pipe, CHNL_OUT_BUF2_ADDR_V, + lower_32_bits(dma_addrs[2])); if (pipe->isi->pdata->has_36bit_dma) { mxc_isi_write(pipe, CHNL_Y_BUF2_XTND_ADDR, - dma_addrs[0] >> 32); + upper_32_bits(dma_addrs[0])); mxc_isi_write(pipe, CHNL_U_BUF2_XTND_ADDR, - dma_addrs[1] >> 32); + upper_32_bits(dma_addrs[1])); mxc_isi_write(pipe, CHNL_V_BUF2_XTND_ADDR, - dma_addrs[2] >> 32); + upper_32_bits(dma_addrs[2])); } -#endif val ^= CHNL_OUT_BUF_CTRL_LOAD_BUF2_ADDR; } -- GitLab From c2adb1877b76fc81ae041e1db1a6ed2078c6746b Mon Sep 17 00:00:00 2001 From: Wyes Karny Date: Thu, 4 May 2023 06:25:44 +0000 Subject: [PATCH 4644/5631] cpupower: Make TSC read per CPU for Mperf monitor System-wide TSC read could cause a drift in C0 percentage calculation. Because if first TSC is read and then one by one mperf is read for all cpus, this introduces drift between mperf reading of later CPUs and TSC reading. To lower this drift read TSC per CPU and also just after mperf read. This technique improves C0 percentage calculation in Mperf monitor. Before fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 0| 256| 84.62| 15.38| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 1| 87.15| 12.85| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 1| 257| 84.08| 15.92| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 2| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 2| 258| 83.26| 16.74| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 3| 86.61| 13.39| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 3| 259| 83.60| 16.40| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 4| 86.33| 13.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 4| 260| 83.33| 16.67| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 5| 86.06| 13.94| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 5| 261| 83.05| 16.95| 2695||168659003|3970468|| 0.00| 0.00| 0.00 0| 6| 6| 85.51| 14.49| 2695||168659003|3970468|| 0.00| 0.00| 0.00 After fix: (System 100% busy) | Mperf || RAPL || Idle_Stats PKG|CORE| CPU| C0 | Cx | Freq || pack | core || POLL | C1 | C2 0| 0| 0| 98.03| 1.97| 2415||163295480|3811189|| 0.00| 0.00| 0.00 0| 0| 256| 98.50| 1.50| 2394||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 1| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 1| 257| 99.99| 0.01| 2375||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 2| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 2| 258|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 3|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 3| 259| 99.99| 0.01| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 4|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 4| 260|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 5| 99.99| 0.01| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 5| 261|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 6|100.00| 0.00| 2401||163295480|3811189|| 0.00| 0.00| 0.00 0| 6| 262|100.00| 0.00| 2435||163295480|3811189|| 0.00| 0.00| 0.00 Cc: Thomas Renninger Cc: Shuah Khan Cc: Dominik Brodowski Fixes: 7fe2f6399a84 ("cpupowerutils - cpufrequtils extended with quite some features") Signed-off-by: Wyes Karny Signed-off-by: Shuah Khan --- .../utils/idle_monitor/mperf_monitor.c | 31 +++++++++---------- 1 file changed, 14 insertions(+), 17 deletions(-) diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index e7d48cb563c0..ae6af354a81d 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -70,8 +70,8 @@ static int max_freq_mode; */ static unsigned long max_frequency; -static unsigned long long tsc_at_measure_start; -static unsigned long long tsc_at_measure_end; +static unsigned long long *tsc_at_measure_start; +static unsigned long long *tsc_at_measure_end; static unsigned long long *mperf_previous_count; static unsigned long long *aperf_previous_count; static unsigned long long *mperf_current_count; @@ -169,7 +169,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, aperf_diff = aperf_current_count[cpu] - aperf_previous_count[cpu]; if (max_freq_mode == MAX_FREQ_TSC_REF) { - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; *percent = 100.0 * mperf_diff / tsc_diff; dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); @@ -206,7 +206,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, if (max_freq_mode == MAX_FREQ_TSC_REF) { /* Calculate max_freq from TSC count */ - tsc_diff = tsc_at_measure_end - tsc_at_measure_start; + tsc_diff = tsc_at_measure_end[cpu] - tsc_at_measure_start[cpu]; time_diff = timespec_diff_us(time_start, time_end); max_frequency = tsc_diff / time_diff; } @@ -225,33 +225,27 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, static int mperf_start(void) { int cpu; - unsigned long long dbg; clock_gettime(CLOCK_REALTIME, &time_start); - mperf_get_tsc(&tsc_at_measure_start); - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { + mperf_get_tsc(&tsc_at_measure_start[cpu]); mperf_init_stats(cpu); + } - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_start); return 0; } static int mperf_stop(void) { - unsigned long long dbg; int cpu; - for (cpu = 0; cpu < cpu_count; cpu++) + for (cpu = 0; cpu < cpu_count; cpu++) { mperf_measure_stats(cpu); + mperf_get_tsc(&tsc_at_measure_end[cpu]); + } - mperf_get_tsc(&tsc_at_measure_end); clock_gettime(CLOCK_REALTIME, &time_end); - - mperf_get_tsc(&dbg); - dprint("TSC diff: %llu\n", dbg - tsc_at_measure_end); - return 0; } @@ -353,7 +347,8 @@ struct cpuidle_monitor *mperf_register(void) aperf_previous_count = calloc(cpu_count, sizeof(unsigned long long)); mperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); aperf_current_count = calloc(cpu_count, sizeof(unsigned long long)); - + tsc_at_measure_start = calloc(cpu_count, sizeof(unsigned long long)); + tsc_at_measure_end = calloc(cpu_count, sizeof(unsigned long long)); mperf_monitor.name_len = strlen(mperf_monitor.name); return &mperf_monitor; } @@ -364,6 +359,8 @@ void mperf_unregister(void) free(aperf_previous_count); free(mperf_current_count); free(aperf_current_count); + free(tsc_at_measure_start); + free(tsc_at_measure_end); free(is_valid); } -- GitLab From d66cde50c3c868af7abddafce701bb86e4a93039 Mon Sep 17 00:00:00 2001 From: Pawel Witek Date: Fri, 5 May 2023 17:14:59 +0200 Subject: [PATCH 4645/5631] cifs: fix pcchunk length type in smb2_copychunk_range Change type of pcchunk->Length from u32 to u64 to match smb2_copychunk_range arguments type. Fixes the problem where performing server-side copy with CIFS_IOC_COPYCHUNK_FILE ioctl resulted in incomplete copy of large files while returning -EINVAL. Fixes: 9bf0c9cd4314 ("CIFS: Fix SMB2/SMB3 Copy offload support (refcopy) for large files") Cc: Signed-off-by: Pawel Witek Signed-off-by: Steve French --- fs/cifs/smb2ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a81758225fcd..a295e4c2d54e 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1682,7 +1682,7 @@ smb2_copychunk_range(const unsigned int xid, pcchunk->SourceOffset = cpu_to_le64(src_off); pcchunk->TargetOffset = cpu_to_le64(dest_off); pcchunk->Length = - cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); + cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ kfree(retbuf); -- GitLab From cbd4cbabef646f1719a73a01cc491b1c1fea4d41 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 7 May 2023 17:57:17 -0500 Subject: [PATCH 4646/5631] do not reuse connection if share marked as isolated "SHAREFLAG_ISOLATED_TRANSPORT" indicates that we should not reuse the socket for this share (for future mounts). Mark the socket as server->nosharesock if share flags returned include SHAREFLAG_ISOLATED_TRANSPORT. See MS-SMB2 MS-SMB2 2.2.10 and 3.2.5.5 Signed-off-by: Steve French --- fs/cifs/smb2pdu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e33ca0d33906..9ed61b6f9b21 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1947,6 +1947,9 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, init_copy_chunk_defaults(tcon); if (server->ops->validate_negotiate) rc = server->ops->validate_negotiate(xid, tcon); + if (rc == 0) /* See MS-SMB2 2.2.10 and 3.2.5.5 */ + if (tcon->share_flags & SMB2_SHAREFLAG_ISOLATED_TRANSPORT) + server->nosharesock = true; tcon_exit: free_rsp_buf(resp_buftype, rsp); -- GitLab From 4b79f76920a49fc13766b95df1df1f4d700acbad Mon Sep 17 00:00:00 2001 From: Yi Lai Date: Fri, 21 Apr 2023 11:31:23 +0800 Subject: [PATCH 4647/5631] selftests/sgx: Add "test_encl.elf" to TEST_FILES The "test_encl.elf" file used by test_sgx is not installed in INSTALL_PATH. Attempting to execute test_sgx causes false negative: " enclave executable open(): No such file or directory main.c:188:unclobbered_vdso:Failed to load the test enclave. " Add "test_encl.elf" to TEST_FILES so that it will be installed. Fixes: 2adcba79e69d ("selftests/x86: Add a selftest for SGX") Signed-off-by: Yi Lai Reviewed-by: Jarkko Sakkinen Signed-off-by: Shuah Khan --- tools/testing/selftests/sgx/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 75af864e07b6..50aab6b57da3 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -17,6 +17,7 @@ ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ -fno-stack-protector -mrdrnd $(INCLUDES) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx +TEST_FILES := $(OUTPUT)/test_encl.elf ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf -- GitLab From dbcf76390eb9a65d5d0c37b0cd57335218564e37 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 8 May 2023 22:15:42 +0900 Subject: [PATCH 4648/5631] selftests/ftrace: Improve integration with kselftest runner The ftrace selftests do not currently produce KTAP output, they produce a custom format much nicer for human consumption. This means that when run in automated test systems we just get a single result for the suite as a whole rather than recording results for individual test cases, making it harder to look at the test data and masking things like inappropriate skips. Address this by adding support for KTAP output to the ftracetest script and providing a trivial wrapper which will be invoked by the kselftest runner to generate output in this format by default, users using ftracetest directly will continue to get the existing output. This is not the most elegant solution but it is simple and effective. I did consider implementing this by post processing the existing output format but that felt more complex and likely to result in all output being lost if something goes seriously wrong during the run which would not be helpful. I did also consider just writing a separate runner script but there's enough going on with things like the signal handling for that to seem like it would be duplicating too much. Acked-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Tested-by: Masami Hiramatsu (Google) Signed-off-by: Mark Brown Signed-off-by: Shuah Khan --- tools/testing/selftests/ftrace/Makefile | 3 +- tools/testing/selftests/ftrace/ftracetest | 63 ++++++++++++++++++- .../testing/selftests/ftrace/ftracetest-ktap | 8 +++ 3 files changed, 70 insertions(+), 4 deletions(-) create mode 100755 tools/testing/selftests/ftrace/ftracetest-ktap diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index d6e106fbce11..a1e955d2de4c 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 all: -TEST_PROGS := ftracetest +TEST_PROGS_EXTENDED := ftracetest +TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c3311c8c4089..2506621e75df 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,6 +13,7 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" +echo " -K|--ktap Output in KTAP format" echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" @@ -85,6 +86,10 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; + --ktap|-K) + KTAP=1 + shift 1 + ;; --verbose|-v|-vv|-vvv) if [ $VERBOSE -eq -1 ]; then usage "--console can not use with --verbose" @@ -178,6 +183,7 @@ TEST_DIR=$TOP_DIR/test.d TEST_CASES=`find_testcases $TEST_DIR` LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ KEEP_LOG=0 +KTAP=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 @@ -229,7 +235,7 @@ prlog() { # messages newline= shift fi - printf "$*$newline" + [ "$KTAP" != "1" ] && printf "$*$newline" [ "$LOG_FILE" ] && printf "$*$newline" | strip_esc >> $LOG_FILE } catlog() { #file @@ -260,11 +266,11 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 +CASENAME= testcase() { # testfile CASENO=$((CASENO+1)) - desc=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` - prlog -n "[$CASENO]$INSTANCE$desc" + CASENAME=`grep "^#[ \t]*description:" $1 | cut -f2- -d:` } checkreq() { # testfile @@ -277,40 +283,68 @@ test_on_instance() { # testfile grep -q "^#[ \t]*flags:.*instance" $1 } +ktaptest() { # result comment + if [ "$KTAP" != "1" ]; then + return + fi + + local result= + if [ "$1" = "1" ]; then + result="ok" + else + result="not ok" + fi + shift + + local comment=$* + if [ "$comment" != "" ]; then + comment="# $comment" + fi + + echo $CASENO $result $INSTANCE$CASENAME $comment +} + eval_result() { # sigval case $1 in $PASS) prlog " [${color_green}PASS${color_reset}]" + ktaptest 1 PASSED_CASES="$PASSED_CASES $CASENO" return 0 ;; $FAIL) prlog " [${color_red}FAIL${color_reset}]" + ktaptest 0 FAILED_CASES="$FAILED_CASES $CASENO" return 1 # this is a bug. ;; $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" + ktaptest 0 UNRESOLVED UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" + ktaptest 1 SKIP UNTESTED_CASES="$UNTESTED_CASES $CASENO" return 0 ;; $UNSUPPORTED) prlog " [${color_blue}UNSUPPORTED${color_reset}]" + ktaptest 1 SKIP UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) prlog " [${color_green}XFAIL${color_reset}]" + ktaptest 1 XFAIL XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; *) prlog " [${color_blue}UNDEFINED${color_reset}]" + ktaptest 0 error UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" return 1 # this must be a test bug ;; @@ -371,6 +405,7 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` testcase $1 + prlog -n "[$CASENO]$INSTANCE$CASENAME" if [ ! -z "$LOG_FILE" ] ; then local testlog=`mktemp $LOG_DIR/${CASENO}-${testname}-log.XXXXXX` else @@ -405,6 +440,17 @@ run_test() { # testfile # load in the helper functions . $TEST_DIR/functions +if [ "$KTAP" = "1" ]; then + echo "TAP version 13" + + casecount=`echo $TEST_CASES | wc -w` + for t in $TEST_CASES; do + test_on_instance $t || continue + casecount=$((casecount+1)) + done + echo "1..${casecount}" +fi + # Main loop for t in $TEST_CASES; do run_test $t @@ -439,6 +485,17 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +if [ "$KTAP" = "1" ]; then + echo -n "# Totals:" + echo -n " pass:"`echo $PASSED_CASES | wc -w` + echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " xfail:"`echo $XFAILED_CASES | wc -w` + echo -n " xpass:0" + echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` + echo -n " error:"`echo $UNRESOLVED_CASES $UNDEFINED_CASES | wc -w` + echo +fi + cleanup # if no error, return 0 diff --git a/tools/testing/selftests/ftrace/ftracetest-ktap b/tools/testing/selftests/ftrace/ftracetest-ktap new file mode 100755 index 000000000000..b3284679ef3a --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest-ktap @@ -0,0 +1,8 @@ +#!/bin/sh -e +# SPDX-License-Identifier: GPL-2.0-only +# +# ftracetest-ktap: Wrapper to integrate ftracetest with the kselftest runner +# +# Copyright (C) Arm Ltd., 2023 + +./ftracetest -K -- GitLab From 44e8d5ad2dc01529eb1316b1521f24ac4aac8eaf Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 20 Apr 2023 09:33:49 -1000 Subject: [PATCH 4649/5631] firmware: arm_scmi: Fix incorrect alloc_workqueue() invocation scmi_xfer_raw_worker_init() is specifying a flag, WQ_SYSFS, as @max_active. Fix it by or'ing WQ_SYSFS into @flags so that it actually enables sysfs interface and using 0 for @max_active for the default setting. Signed-off-by: Tejun Heo Fixes: 3c3d818a9317 ("firmware: arm_scmi: Add core raw transmission support") Link: https://lore.kernel.org/r/ZEGTnajiQm7mkkZS@slm.duckdns.org Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/raw_mode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/firmware/arm_scmi/raw_mode.c b/drivers/firmware/arm_scmi/raw_mode.c index d40df099fd51..6971dcf72fb9 100644 --- a/drivers/firmware/arm_scmi/raw_mode.c +++ b/drivers/firmware/arm_scmi/raw_mode.c @@ -1066,7 +1066,7 @@ static int scmi_xfer_raw_worker_init(struct scmi_raw_mode_info *raw) raw->wait_wq = alloc_workqueue("scmi-raw-wait-wq-%d", WQ_UNBOUND | WQ_FREEZABLE | - WQ_HIGHPRI, WQ_SYSFS, raw->id); + WQ_HIGHPRI | WQ_SYSFS, 0, raw->id); if (!raw->wait_wq) return -ENOMEM; -- GitLab From 328acc5657c6197753238d7ce0a6924ead829347 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 23 Apr 2023 17:08:37 +0200 Subject: [PATCH 4650/5631] ARM: dts: vexpress: add missing cache properties As all level 2 and level 3 caches are unified, add required cache-unified property to fix warnings like: vexpress-v2p-ca5s.dtb: cache-controller@2c0f0000: 'cache-unified' is a required property Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230423150837.118466-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sudeep Holla --- arch/arm/boot/dts/vexpress-v2p-ca5s.dts | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts index 3b88209bacea..ff1f9a1bcfcf 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts @@ -132,6 +132,7 @@ reg = <0x2c0f0000 0x1000>; interrupts = <0 84 4>; cache-level = <2>; + cache-unified; }; pmu { -- GitLab From 55b37d9c8ba23d28c584aef0801fb1e60e4a817c Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 22 Apr 2023 00:32:12 +0200 Subject: [PATCH 4651/5631] arm64: dts: arm: add missing cache properties As all level 2 and level 3 caches are unified, add required cache-unified properties to fix warnings like: foundation-v8.dtb: l2-cache0: 'cache-unified' is a required property Signed-off-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230421223213.115639-1-krzysztof.kozlowski@linaro.org Signed-off-by: Sudeep Holla --- arch/arm64/boot/dts/arm/foundation-v8.dtsi | 1 + arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts | 1 + arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dtsi b/arch/arm64/boot/dts/arm/foundation-v8.dtsi index 029578072d8f..7b41537731a6 100644 --- a/arch/arm64/boot/dts/arm/foundation-v8.dtsi +++ b/arch/arm64/boot/dts/arm/foundation-v8.dtsi @@ -59,6 +59,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts index ef68f5aae7dd..afdf954206f1 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts +++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts @@ -72,6 +72,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts index 796cd7d02eb5..7bdeb965f0a9 100644 --- a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts +++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts @@ -58,6 +58,7 @@ L2_0: l2-cache0 { compatible = "cache"; cache-level = <2>; + cache-unified; }; }; -- GitLab From b71b55248a580e9c9befc4ae060539f1f8e477da Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 20 Apr 2023 16:06:01 +0100 Subject: [PATCH 4652/5631] firmware: arm_ffa: Check if ffa_driver remove is present before executing Currently ffa_drv->remove() is called unconditionally from ffa_device_remove(). Since the driver registration doesn't check for it and allows it to be registered without .remove callback, we need to check for the presence of it before executing it from ffa_device_remove() to above a NULL pointer dereference like the one below: | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 | Mem abort info: | ESR = 0x0000000086000004 | EC = 0x21: IABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | FSC = 0x04: level 0 translation fault | user pgtable: 4k pages, 48-bit VAs, pgdp=0000000881cc8000 | [0000000000000000] pgd=0000000000000000, p4d=0000000000000000 | Internal error: Oops: 0000000086000004 [#1] PREEMPT SMP | CPU: 3 PID: 130 Comm: rmmod Not tainted 6.3.0-rc7 #6 | Hardware name: FVP Base RevC (DT) | pstate: 63402809 (nZCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=-c) | pc : 0x0 | lr : ffa_device_remove+0x20/0x2c | Call trace: | 0x0 | device_release_driver_internal+0x16c/0x260 | driver_detach+0x90/0xd0 | bus_remove_driver+0xdc/0x11c | driver_unregister+0x30/0x54 | ffa_driver_unregister+0x14/0x20 | cleanup_module+0x18/0xeec | __arm64_sys_delete_module+0x234/0x378 | invoke_syscall+0x40/0x108 | el0_svc_common+0xb4/0xf0 | do_el0_svc+0x30/0xa4 | el0_svc+0x2c/0x7c | el0t_64_sync_handler+0x84/0xf0 | el0t_64_sync+0x190/0x194 Fixes: 244f5d597e1e ("firmware: arm_ffa: Add missing remove callback to ffa_bus_type") Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-1-d9108e43a176@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index f29d77ecf72d..36bd5423c2f0 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -53,7 +53,8 @@ static void ffa_device_remove(struct device *dev) { struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver); - ffa_drv->remove(to_ffa_dev(dev)); + if (ffa_drv->remove) + ffa_drv->remove(to_ffa_dev(dev)); } static int ffa_device_uevent(const struct device *dev, struct kobj_uevent_env *env) -- GitLab From c6e045361a27ecd4fac6413164e0d091d80eee99 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 20 Apr 2023 16:06:02 +0100 Subject: [PATCH 4653/5631] firmware: arm_ffa: Fix usage of partition info get count flag Commit bb1be7498500 ("firmware: arm_ffa: Add v1.1 get_partition_info support") adds support to discovery the UUIDs of the partitions or just fetch the partition count using the PARTITION_INFO_GET_RETURN_COUNT_ONLY flag. However the commit doesn't handle the fact that the older version doesn't understand the flag and must be MBZ which results in firmware returning invalid parameter error. That results in the failure of the driver probe which is in correct. Limit the usage of the PARTITION_INFO_GET_RETURN_COUNT_ONLY flag for the versions above v1.0(i.e v1.1 and onwards) which fixes the issue. Fixes: bb1be7498500 ("firmware: arm_ffa: Add v1.1 get_partition_info support") Reported-by: Jens Wiklander Reported-by: Marc Bonnici Tested-by: Jens Wiklander Reviewed-by: Jens Wiklander Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-2-d9108e43a176@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index fa85c64d3ded..4aced2e5b772 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -193,7 +193,8 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, int idx, count, flags = 0, sz, buf_sz; ffa_value_t partition_info; - if (!buffer || !num_partitions) /* Just get the count for now */ + if (drv_info->version > FFA_VERSION_1_0 && + (!buffer || !num_partitions)) /* Just get the count for now */ flags = PARTITION_INFO_GET_RETURN_COUNT_ONLY; mutex_lock(&drv_info->rx_lock); -- GitLab From 19b8766459c41c6f318f8a548cc1c66dffd18363 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 20 Apr 2023 16:06:03 +0100 Subject: [PATCH 4654/5631] firmware: arm_ffa: Fix FFA device names for logical partitions Each physical partition can provide multiple services each with UUID. Each such service can be presented as logical partition with a unique combination of VM ID and UUID. The number of distinct UUID in a system will be less than or equal to the number of logical partitions. However, currently it fails to register more than one logical partition or service within a physical partition as the device name contains only VM ID while both VM ID and UUID are maintained in the partition information. The kernel complains with the below message: | sysfs: cannot create duplicate filename '/devices/arm-ffa-8001' | CPU: 1 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7 #8 | Hardware name: FVP Base RevC (DT) | Call trace: | dump_backtrace+0xf8/0x118 | show_stack+0x18/0x24 | dump_stack_lvl+0x50/0x68 | dump_stack+0x18/0x24 | sysfs_create_dir_ns+0xe0/0x13c | kobject_add_internal+0x220/0x3d4 | kobject_add+0x94/0x100 | device_add+0x144/0x5d8 | device_register+0x20/0x30 | ffa_device_register+0x88/0xd8 | ffa_setup_partitions+0x108/0x1b8 | ffa_init+0x2ec/0x3a4 | do_one_initcall+0xcc/0x240 | do_initcall_level+0x8c/0xac | do_initcalls+0x54/0x94 | do_basic_setup+0x1c/0x28 | kernel_init_freeable+0x100/0x16c | kernel_init+0x20/0x1a0 | ret_from_fork+0x10/0x20 | kobject_add_internal failed for arm-ffa-8001 with -EEXIST, don't try to | register things with the same name in the same directory. | arm_ffa arm-ffa: unable to register device arm-ffa-8001 err=-17 | ARM FF-A: ffa_setup_partitions: failed to register partition ID 0x8001 By virtue of being random enough to avoid collisions when generated in a distributed system, there is no way to compress UUID keys to the number of bits required to identify each. We can eliminate '-' in the name but it is not worth eliminating 4 bytes and add unnecessary logic for doing that. Also v1.0 doesn't provide the UUID of the partitions which makes it hard to use the same for the device name. So to keep it simple, let us alloc an ID using ida_alloc() and append the same to "arm-ffa" to make up a unique device name. Also stash the id value in ffa_dev to help freeing the ID later when the device is destroyed. Fixes: e781858488b9 ("firmware: arm_ffa: Add initial FFA bus support for device enumeration") Reported-by: Lucian Paul-Trifu Link: https://lore.kernel.org/r/20230419-ffa_fixes_6-4-v2-3-d9108e43a176@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/bus.c | 16 +++++++++++++--- include/linux/arm_ffa.h | 1 + 2 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 36bd5423c2f0..2b8bfcd010f5 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -15,6 +15,8 @@ #include "common.h" +static DEFINE_IDA(ffa_bus_id); + static int ffa_device_match(struct device *dev, struct device_driver *drv) { const struct ffa_device_id *id_table; @@ -131,6 +133,7 @@ static void ffa_release_device(struct device *dev) { struct ffa_device *ffa_dev = to_ffa_dev(dev); + ida_free(&ffa_bus_id, ffa_dev->id); kfree(ffa_dev); } @@ -171,18 +174,24 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, const struct ffa_ops *ops) { - int ret; + int id, ret; struct device *dev; struct ffa_device *ffa_dev; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); + if (id < 0) + return NULL; + ffa_dev = kzalloc(sizeof(*ffa_dev), GFP_KERNEL); - if (!ffa_dev) + if (!ffa_dev) { + ida_free(&ffa_bus_id, id); return NULL; + } dev = &ffa_dev->dev; dev->bus = &ffa_bus_type; dev->release = ffa_release_device; - dev_set_name(&ffa_dev->dev, "arm-ffa-%04x", vm_id); + dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->vm_id = vm_id; ffa_dev->ops = ops; @@ -218,4 +227,5 @@ void arm_ffa_bus_exit(void) { ffa_devices_unregister(); bus_unregister(&ffa_bus_type); + ida_destroy(&ffa_bus_id); } diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c87aeecaa9b2..583fe3b49a49 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -96,6 +96,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { + u32 id; int vm_id; bool mode_32bit; uuid_t uuid; -- GitLab From 111a833dc5cbef3d05b2a796a7e23cb7f6ff2192 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 3 May 2023 14:12:52 +0100 Subject: [PATCH 4655/5631] firmware: arm_ffa: Set reserved/MBZ fields to zero in the memory descriptors The transmit buffers allocated by the driver can be used to transmit data by any messages/commands needing the buffer. However, it is not guaranteed to have been zero-ed before every new transmission and hence it will just contain residual value from the previous transmission. There are several reserved fields in the memory descriptors that must be zero(MBZ). The receiver can reject the transmission if any such MBZ fields are non-zero. While we can set the whole page to zero, it is not optimal as most of the fields get initialised to the value required for the current transmission. So, just set the reserved/MBZ fields to zero in the memory descriptors explicitly to honour the requirement and keep the receiver happy. Fixes: cc2195fe536c ("firmware: arm_ffa: Add support for MEM_* interfaces") Reported-by: Marc Bonnici Link: https://lore.kernel.org/r/20230503131252.12585-1-sudeep.holla@arm.com Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 4aced2e5b772..e23409138667 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -421,12 +421,17 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, ep_mem_access->receiver = args->attrs[idx].receiver; ep_mem_access->attrs = args->attrs[idx].attrs; ep_mem_access->composite_off = COMPOSITE_OFFSET(args->nattrs); + ep_mem_access->flag = 0; + ep_mem_access->reserved = 0; } + mem_region->reserved_0 = 0; + mem_region->reserved_1 = 0; mem_region->ep_count = args->nattrs; composite = buffer + COMPOSITE_OFFSET(args->nattrs); composite->total_pg_cnt = ffa_get_num_pages_sg(args->sg); composite->addr_range_cnt = num_entries; + composite->reserved = 0; length = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, num_entries); frag_len = COMPOSITE_CONSTITUENTS_OFFSET(args->nattrs, 0); @@ -461,6 +466,7 @@ ffa_setup_and_transmit(u32 func_id, void *buffer, u32 max_fragsize, constituents->address = sg_phys(args->sg); constituents->pg_cnt = args->sg->length / FFA_PAGE_SIZE; + constituents->reserved = 0; constituents++; frag_len += sizeof(struct ffa_mem_region_addr_range); } while ((args->sg = sg_next(args->sg))); -- GitLab From f9d36cf445ffff0b913ba187a3eff78028f9b1fb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 6 May 2023 18:40:57 +0200 Subject: [PATCH 4656/5631] tick/broadcast: Make broadcast device replacement work correctly When a tick broadcast clockevent device is initialized for one shot mode then tick_broadcast_setup_oneshot() OR's the periodic broadcast mode cpumask into the oneshot broadcast cpumask. This is required when switching from periodic broadcast mode to oneshot broadcast mode to ensure that CPUs which are waiting for periodic broadcast are woken up on the next tick. But it is subtly broken, when an active broadcast device is replaced and the system is already in oneshot (NOHZ/HIGHRES) mode. Victor observed this and debugged the issue. Then the OR of the periodic broadcast CPU mask is wrong as the periodic cpumask bits are sticky after tick_broadcast_enable() set it for a CPU unless explicitly cleared via tick_broadcast_disable(). That means that this sets all other CPUs which have tick broadcasting enabled at that point unconditionally in the oneshot broadcast mask. If the affected CPUs were already idle and had their bits set in the oneshot broadcast mask then this does no harm. But for non idle CPUs which were not set this corrupts their state. On their next invocation of tick_broadcast_enable() they observe the bit set, which indicates that the broadcast for the CPU is already set up. As a consequence they fail to update the broadcast event even if their earliest expiring timer is before the actually programmed broadcast event. If the programmed broadcast event is far in the future, then this can cause stalls or trigger the hung task detector. Avoid this by telling tick_broadcast_setup_oneshot() explicitly whether this is the initial switch over from periodic to oneshot broadcast which must take the periodic broadcast mask into account. In the case of initialization of a replacement device this prevents that the broadcast oneshot mask is modified. There is a second problem with broadcast device replacement in this function. The broadcast device is only armed when the previous state of the device was periodic. That is correct for the switch from periodic broadcast mode to oneshot broadcast mode as the underlying broadcast device could operate in oneshot state already due to lack of periodic state in hardware. In that case it is already armed to expire at the next tick. For the replacement case this is wrong as the device is in shutdown state. That means that any already pending broadcast event will not be armed. This went unnoticed because any CPU which goes idle will observe that the broadcast device has an expiry time of KTIME_MAX and therefore any CPUs next timer event will be earlier and cause a reprogramming of the broadcast device. But that does not guarantee that the events of the CPUs which were already in idle are delivered on time. Fix this by arming the newly installed device for an immediate event which will reevaluate the per CPU expiry times and reprogram the broadcast device accordingly. This is simpler than caching the last expiry time in yet another place or saving it before the device exchange and handing it down to the setup function. Replacement of broadcast devices is not a frequent operation and usually happens once somewhere late in the boot process. Fixes: 9c336c9935cf ("tick/broadcast: Allow late registered device to enter oneshot mode") Reported-by: Victor Hassan Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/87pm7d2z1i.ffs@tglx --- kernel/time/tick-broadcast.c | 120 +++++++++++++++++++++++++---------- 1 file changed, 88 insertions(+), 32 deletions(-) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 93bf2b4e47e5..771d1e040303 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -35,14 +35,15 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device); -static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); # ifdef CONFIG_HOTPLUG_CPU static void tick_broadcast_oneshot_offline(unsigned int cpu); # endif #else -static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } +static inline void +tick_broadcast_setup_oneshot(struct clock_event_device *bc, bool from_periodic) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } # ifdef CONFIG_HOTPLUG_CPU @@ -264,7 +265,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, false); ret = 1; } else { /* @@ -500,7 +501,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_broadcast_start_periodic(bc); else - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, false); } } out: @@ -1020,48 +1021,101 @@ static inline ktime_t tick_get_next_period(void) /** * tick_broadcast_setup_oneshot - setup the broadcast device */ -static void tick_broadcast_setup_oneshot(struct clock_event_device *bc) +static void tick_broadcast_setup_oneshot(struct clock_event_device *bc, + bool from_periodic) { int cpu = smp_processor_id(); + ktime_t nexttick = 0; if (!bc) return; - /* Set it up only once ! */ - if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = clockevent_state_periodic(bc); - - bc->event_handler = tick_handle_oneshot_broadcast; - + /* + * When the broadcast device was switched to oneshot by the first + * CPU handling the NOHZ change, the other CPUs will reach this + * code via hrtimer_run_queues() -> tick_check_oneshot_change() + * too. Set up the broadcast device only once! + */ + if (bc->event_handler == tick_handle_oneshot_broadcast) { /* - * We must be careful here. There might be other CPUs - * waiting for periodic broadcast. We need to set the - * oneshot_mask bits for those and program the - * broadcast device to fire. + * The CPU which switched from periodic to oneshot mode + * set the broadcast oneshot bit for all other CPUs which + * are in the general (periodic) broadcast mask to ensure + * that CPUs which wait for the periodic broadcast are + * woken up. + * + * Clear the bit for the local CPU as the set bit would + * prevent the first tick_broadcast_enter() after this CPU + * switched to oneshot state to program the broadcast + * device. + * + * This code can also be reached via tick_broadcast_control(), + * but this cannot avoid the tick_broadcast_clear_oneshot() + * as that would break the periodic to oneshot transition of + * secondary CPUs. But that's harmless as the below only + * clears already cleared bits. */ + tick_broadcast_clear_oneshot(cpu); + return; + } + + + bc->event_handler = tick_handle_oneshot_broadcast; + bc->next_event = KTIME_MAX; + + /* + * When the tick mode is switched from periodic to oneshot it must + * be ensured that CPUs which are waiting for periodic broadcast + * get their wake-up at the next tick. This is achieved by ORing + * tick_broadcast_mask into tick_broadcast_oneshot_mask. + * + * For other callers, e.g. broadcast device replacement, + * tick_broadcast_oneshot_mask must not be touched as this would + * set bits for CPUs which are already NOHZ, but not idle. Their + * next tick_broadcast_enter() would observe the bit set and fail + * to update the expiry time and the broadcast event device. + */ + if (from_periodic) { cpumask_copy(tmpmask, tick_broadcast_mask); + /* Remove the local CPU as it is obviously not idle */ cpumask_clear_cpu(cpu, tmpmask); - cpumask_or(tick_broadcast_oneshot_mask, - tick_broadcast_oneshot_mask, tmpmask); + cpumask_or(tick_broadcast_oneshot_mask, tick_broadcast_oneshot_mask, tmpmask); - if (was_periodic && !cpumask_empty(tmpmask)) { - ktime_t nextevt = tick_get_next_period(); + /* + * Ensure that the oneshot broadcast handler will wake the + * CPUs which are still waiting for periodic broadcast. + */ + nexttick = tick_get_next_period(); + tick_broadcast_init_next_event(tmpmask, nexttick); - clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); - tick_broadcast_init_next_event(tmpmask, nextevt); - tick_broadcast_set_event(bc, cpu, nextevt); - } else - bc->next_event = KTIME_MAX; - } else { /* - * The first cpu which switches to oneshot mode sets - * the bit for all other cpus which are in the general - * (periodic) broadcast mask. So the bit is set and - * would prevent the first broadcast enter after this - * to program the bc device. + * If the underlying broadcast clock event device is + * already in oneshot state, then there is nothing to do. + * The device was already armed for the next tick + * in tick_handle_broadcast_periodic() */ - tick_broadcast_clear_oneshot(cpu); + if (clockevent_state_oneshot(bc)) + return; } + + /* + * When switching from periodic to oneshot mode arm the broadcast + * device for the next tick. + * + * If the broadcast device has been replaced in oneshot mode and + * the oneshot broadcast mask is not empty, then arm it to expire + * immediately in order to reevaluate the next expiring timer. + * @nexttick is 0 and therefore in the past which will cause the + * clockevent code to force an event. + * + * For both cases the programming can be avoided when the oneshot + * broadcast mask is empty. + * + * tick_broadcast_set_event() implicitly switches the broadcast + * device to oneshot state. + */ + if (!cpumask_empty(tick_broadcast_oneshot_mask)) + tick_broadcast_set_event(bc, cpu, nexttick); } /* @@ -1070,14 +1124,16 @@ static void tick_broadcast_setup_oneshot(struct clock_event_device *bc) void tick_broadcast_switch_to_oneshot(void) { struct clock_event_device *bc; + enum tick_device_mode oldmode; unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + oldmode = tick_broadcast_device.mode; tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) - tick_broadcast_setup_oneshot(bc); + tick_broadcast_setup_oneshot(bc, oldmode == TICKDEV_MODE_PERIODIC); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } -- GitLab From 051d71e073614a72ad423d6dacba37a7eeff274d Mon Sep 17 00:00:00 2001 From: V sujith kumar Reddy Date: Mon, 8 May 2023 12:35:08 +0530 Subject: [PATCH 4657/5631] ASoC: SOF: amd: Fix NULL pointer crash in acp_sof_ipc_msg_data function Check substream and runtime variables before assigning. Signed-off-by: V sujith kumar Reddy substream; - struct acp_dsp_stream *stream = substream->runtime->private_data; + struct acp_dsp_stream *stream; + + if (!substream || !substream->runtime) + return -ESTRPIPE; + + stream = substream->runtime->private_data; if (!stream) return -ESTRPIPE; -- GitLab From ba8c2b75b02a162202d31e6200ab15da1035a7d0 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 8 May 2023 00:45:45 -0500 Subject: [PATCH 4658/5631] smb3: improve parallel reads of large files rasize (ra_pages) should be set higher than read size by default to allow parallel reads when reading large files in order to improve performance (otherwise there is much dead time on the network when doing readahead of large files). Default rasize to twice readsize. Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 32f7c81a7b89..81430abacf93 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -246,7 +246,7 @@ cifs_read_super(struct super_block *sb) if (cifs_sb->ctx->rasize) sb->s_bdi->ra_pages = cifs_sb->ctx->rasize / PAGE_SIZE; else - sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE; + sb->s_bdi->ra_pages = 2 * (cifs_sb->ctx->rsize / PAGE_SIZE); sb->s_blocksize = CIFS_MAX_MSGSIZE; sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */ -- GitLab From 8bbec86ce6d66fb33530c679f7bb3a123fc9e7da Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 8 May 2023 09:18:37 +0200 Subject: [PATCH 4659/5631] dt-bindings: PCI: fsl,imx6q: fix assigned-clocks warning assigned-clocks are a dependency of clocks, however the dtschema has limitation and expects clocks to be present in the binding using assigned-clocks, not in other referenced bindings. The clocks were defined in common fsl,imx6q-pcie-common.yaml, which is referenced by fsl,imx6q-pcie-ep.yaml. The fsl,imx6q-pcie-ep.yaml used assigned-clocks thus leading to warnings: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.example.dtb: pcie-ep@33800000: Unevaluated properties are not allowed ('assigned-clock-parents', 'assigned-clock-rates', 'assigned-clocks' were unexpected) From schema: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml Fix this by moving clocks to each specific schema from the common one and narrowing them to strictly match what is expected for given device. Fixes: b10f82380eeb ("dt-bindings: imx6q-pcie: Restruct i.MX PCIe schema") Acked-by: Conor Dooley Reviewed-by: Richard Zhu Link: https://lore.kernel.org/r/20230508071837.68552-1-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski --- .../bindings/pci/fsl,imx6q-pcie-common.yaml | 13 +--- .../bindings/pci/fsl,imx6q-pcie-ep.yaml | 38 +++++++++ .../bindings/pci/fsl,imx6q-pcie.yaml | 77 +++++++++++++++++++ 3 files changed, 117 insertions(+), 11 deletions(-) diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml index 9bff8ecb653c..d91b639ae7ae 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml @@ -17,20 +17,11 @@ description: properties: clocks: minItems: 3 - items: - - description: PCIe bridge clock. - - description: PCIe bus clock. - - description: PCIe PHY clock. - - description: Additional required clock entry for imx6sx-pcie, - imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + maxItems: 4 clock-names: minItems: 3 - items: - - const: pcie - - const: pcie_bus - - enum: [ pcie_phy, pcie_aux ] - - enum: [ pcie_inbound_axi, pcie_aux ] + maxItems: 4 num-lanes: const: 1 diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml index f4a328ec1daa..ee155ed5f181 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml @@ -31,6 +31,19 @@ properties: - const: dbi - const: addr_space + clocks: + minItems: 3 + items: + - description: PCIe bridge clock. + - description: PCIe bus clock. + - description: PCIe PHY clock. + - description: Additional required clock entry for imx6sx-pcie, + imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + + clock-names: + minItems: 3 + maxItems: 4 + interrupts: items: - description: builtin eDMA interrupter. @@ -49,6 +62,31 @@ required: allOf: - $ref: /schemas/pci/snps,dw-pcie-ep.yaml# - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml# + - if: + properties: + compatible: + enum: + - fsl,imx8mq-pcie-ep + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_aux + else: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_aux + unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml index 2443641754d3..81bbb8728f0f 100644 --- a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml @@ -40,6 +40,19 @@ properties: - const: dbi - const: config + clocks: + minItems: 3 + items: + - description: PCIe bridge clock. + - description: PCIe bus clock. + - description: PCIe PHY clock. + - description: Additional required clock entry for imx6sx-pcie, + imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep. + + clock-names: + minItems: 3 + maxItems: 4 + interrupts: items: - description: builtin MSI controller. @@ -77,6 +90,70 @@ required: allOf: - $ref: /schemas/pci/snps,dw-pcie.yaml# - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml# + - if: + properties: + compatible: + enum: + - fsl,imx6sx-pcie + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_inbound_axi + + - if: + properties: + compatible: + enum: + - fsl,imx8mq-pcie + then: + properties: + clocks: + minItems: 4 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + - const: pcie_aux + + - if: + properties: + compatible: + enum: + - fsl,imx6q-pcie + - fsl,imx6qp-pcie + - fsl,imx7d-pcie + then: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_phy + + - if: + properties: + compatible: + enum: + - fsl,imx8mm-pcie + - fsl,imx8mp-pcie + then: + properties: + clocks: + maxItems: 3 + clock-names: + items: + - const: pcie + - const: pcie_bus + - const: pcie_aux unevaluatedProperties: false -- GitLab From c4af8e3fecd03b0aedcd38145955605cfebe7e3a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 24 Apr 2023 14:55:54 -0500 Subject: [PATCH 4660/5631] thunderbolt: Clear registers properly when auto clear isn't in use When `QUIRK_AUTO_CLEAR_INT` isn't set, interrupt masking should be cleared by writing to Interrupt Mask Clear (IMR) and interrupt status should be cleared properly at shutdown/init. This fixes an error where interrupts are left enabled during resume from hibernation with `CONFIG_USB4=y`. Fixes: 468c49f44759 ("thunderbolt: Disable interrupt auto clear for rings") Cc: stable@vger.kernel.org # v6.3 Reported-by: Takashi Iwai Link: https://bugzilla.kernel.org/show_bug.cgi?id=217343 Signed-off-by: Mario Limonciello Signed-off-by: Mika Westerberg --- drivers/thunderbolt/nhi.c | 29 ++++++++++++++++++++++++----- drivers/thunderbolt/nhi_regs.h | 2 ++ 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index d76e923fbc6a..c0aee5dc5237 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -54,6 +54,21 @@ static int ring_interrupt_index(const struct tb_ring *ring) return bit; } +static void nhi_mask_interrupt(struct tb_nhi *nhi, int mask, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + return; + iowrite32(mask, nhi->iobase + REG_RING_INTERRUPT_MASK_CLEAR_BASE + ring); +} + +static void nhi_clear_interrupt(struct tb_nhi *nhi, int ring) +{ + if (nhi->quirks & QUIRK_AUTO_CLEAR_INT) + ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + ring); + else + iowrite32(~0, nhi->iobase + REG_RING_INT_CLEAR + ring); +} + /* * ring_interrupt_active() - activate/deactivate interrupts for a single ring * @@ -61,8 +76,8 @@ static int ring_interrupt_index(const struct tb_ring *ring) */ static void ring_interrupt_active(struct tb_ring *ring, bool active) { - int reg = REG_RING_INTERRUPT_BASE + - ring_interrupt_index(ring) / 32 * 4; + int index = ring_interrupt_index(ring) / 32 * 4; + int reg = REG_RING_INTERRUPT_BASE + index; int interrupt_bit = ring_interrupt_index(ring) & 31; int mask = 1 << interrupt_bit; u32 old, new; @@ -123,7 +138,11 @@ static void ring_interrupt_active(struct tb_ring *ring, bool active) "interrupt for %s %d is already %s\n", RING_TYPE(ring), ring->hop, active ? "enabled" : "disabled"); - iowrite32(new, ring->nhi->iobase + reg); + + if (active) + iowrite32(new, ring->nhi->iobase + reg); + else + nhi_mask_interrupt(ring->nhi, mask, index); } /* @@ -136,11 +155,11 @@ static void nhi_disable_interrupts(struct tb_nhi *nhi) int i = 0; /* disable interrupts */ for (i = 0; i < RING_INTERRUPT_REG_COUNT(nhi); i++) - iowrite32(0, nhi->iobase + REG_RING_INTERRUPT_BASE + 4 * i); + nhi_mask_interrupt(nhi, ~0, 4 * i); /* clear interrupt status bits */ for (i = 0; i < RING_NOTIFY_REG_COUNT(nhi); i++) - ioread32(nhi->iobase + REG_RING_NOTIFY_BASE + 4 * i); + nhi_clear_interrupt(nhi, 4 * i); } /* ring helper methods */ diff --git a/drivers/thunderbolt/nhi_regs.h b/drivers/thunderbolt/nhi_regs.h index faef165a919c..6ba295815477 100644 --- a/drivers/thunderbolt/nhi_regs.h +++ b/drivers/thunderbolt/nhi_regs.h @@ -93,6 +93,8 @@ struct ring_desc { #define REG_RING_INTERRUPT_BASE 0x38200 #define RING_INTERRUPT_REG_COUNT(nhi) ((31 + 2 * nhi->hop_count) / 32) +#define REG_RING_INTERRUPT_MASK_CLEAR_BASE 0x38208 + #define REG_INT_THROTTLING_RATE 0x38c00 /* Interrupt Vector Allocation */ -- GitLab From 44c524b642996148a8e94f1a1b8751076edcf577 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 9 May 2023 10:44:48 +0800 Subject: [PATCH 4661/5631] power: supply: Fix power_supply_get_battery_info() if parent is NULL After commit 27a2195efa8d26447c ("power: supply: core: auto-exposure of simple-battery data") we call power_supply_get_battery_info() in __power_supply_register(), but it causes test_battery crash with NULL pointer: [ 7.524846] __power_supply_register: Expected proper parent device for 'test_battery' [ 7.524856] CPU 3 Unable to handle kernel paging request at virtual address 0000000000000278, era == 9000000002fb279c, ra == 9000000003173434 [ 7.524862] Oops[#1]: [ 7.524866] CPU: 3 PID: 1 Comm: swapper/0 Not tainted 6.3.0+ #524 [ 7.524870] Hardware name: Loongson Loongson-3A5000-7A1000-1w-CRB/Loongson-LS3A5000-7A1000-1w-CRB, BIOS vUDK2018-LoongArch-V2.0.0-prebeta9 10/21/2022 [ 7.524872] pc 9000000002fb279c ra 9000000003173434 tp 90000001001f0000 sp 90000001001f3c00 [ 7.524875] a0 0000000000000000 a1 0000000000000000 a2 0000000000000000 a3 9000000004553e13 [ 7.524878] a4 9000000004553e16 a5 ffffffffffffffff a6 9000000003fd0948 a7 0000000000000030 [ 7.524881] t0 9000000003173434 t1 90000000035e2c00 t2 0000000000000001 t3 00000000fffff2b0 [ 7.524883] t4 0000000000000007 t5 fffffffffffffffe t6 0000000000000000 t7 0000000000000010 [ 7.524886] t8 00000000000000b4 u0 00000001c0840c76 s9 0000000000000000 s0 0000000000000000 [ 7.524889] s1 900000000370c458 s2 0000000000000001 s3 9000000101f81000 s4 9000000101f81038 [ 7.524891] s5 9000000101f813a0 s6 900000000370c398 s7 9000000003eebd18 s8 90000000037c0070 [ 7.524894] ra: 9000000003173434 power_supply_get_battery_info+0xe4/0x710 [ 7.591224] ERA: 9000000002fb279c __dev_fwnode+0x8/0x20 [ 7.853583] CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) [ 7.859740] PRMD: 00000004 (PPLV0 +PIE -PWE) [ 7.864073] EUEN: 00000000 (-FPE -SXE -ASXE -BTE) [ 7.868839] ECFG: 00071c1c (LIE=2-4,10-12 VS=7) [ 7.873430] ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) [ 7.878884] BADV: 0000000000000278 [ 7.882346] PRID: 0014c010 (Loongson-64bit, Loongson-3A5000) [ 7.888056] Modules linked in: [ 7.891088] Process swapper/0 (pid: 1, threadinfo=0000000091357ee8, task=00000000313d98cb) [ 7.899307] Stack : 00000000000000b4 900000000279aca8 0000000000000001 0000000000000000 [ 7.907274] 0000000000000049 0000000000000408 9000000100008c00 90000000035b6370 [ 7.915238] 900000000b801080 90000000029a440c 9000000003eb4680 9000000003eb4680 [ 7.923202] 9000000101f81038 900000000357cdcc 0000000000000001 900000000370c458 [ 7.931166] 9000000101f81000 90000000037c0070 9000000003eebd18 900000000370c398 [ 7.939131] 90000000045f4530 9000000101f81038 0000000000000000 0000000000000001 [ 7.947095] 900000000370c458 9000000101f81000 0000000000000000 9000000003173e64 [ 7.955059] 0000000000000026 9000000003de3880 9000000100562040 900000000357e07c [ 7.963023] 000000000000026f 0000000000000001 90000001001f3d68 fffffffffffffff5 [ 7.970987] 90000000036d2ca8 90000000027429d8 90000000037c0030 0000000000000001 [ 7.978951] ... [ 7.981379] Call Trace: [ 7.981382] [<9000000002fb279c>] __dev_fwnode+0x8/0x20 [ 7.988916] [<9000000003173434>] power_supply_get_battery_info+0xe4/0x710 [ 7.995666] [<9000000003173e64>] __power_supply_register+0x404/0x580 [ 8.001984] [<900000000379d368>] test_power_init+0x6c/0x124 [ 8.007527] [<90000000026e08f8>] do_one_initcall+0x58/0x1ec [ 8.013066] [<9000000003761614>] kernel_init_freeable+0x290/0x310 [ 8.019127] [<90000000035b40e8>] kernel_init+0x24/0x11c [ 8.024324] [<90000000026e2048>] ret_from_kernel_thread+0xc/0xa4 [ 8.030295] [ 8.031769] Code: 4c000020 0015002c 03400000 <28c9e08c> 40000d80 02c06184 4c000020 28ca0084 4c000020 Root cause: psy->dev.parent is NULL in power_supply_get_battery_info(), so change the else branch to be 'else if (psy->dev.parent)' and return -ENOENT if psy->dev.parent is NULL. Fixes: 27a2195efa8d26447c ("power: supply: core: auto-exposure of simple-battery data") Signed-off-by: Huacai Chen Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index ab986dbace16..d1b19027f53b 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -573,7 +573,7 @@ int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info *info; struct device_node *battery_np = NULL; struct fwnode_reference_args args; - struct fwnode_handle *fwnode; + struct fwnode_handle *fwnode = NULL; const char *value; int err, len, index; const __be32 *list; @@ -585,7 +585,7 @@ int power_supply_get_battery_info(struct power_supply *psy, return -ENODEV; fwnode = fwnode_handle_get(of_fwnode_handle(battery_np)); - } else { + } else if (psy->dev.parent) { err = fwnode_property_get_reference_args( dev_fwnode(psy->dev.parent), "monitored-battery", NULL, 0, 0, &args); @@ -595,6 +595,9 @@ int power_supply_get_battery_info(struct power_supply *psy, fwnode = args.fwnode; } + if (!fwnode) + return -ENOENT; + err = fwnode_property_read_string(fwnode, "compatible", &value); if (err) goto out_put_node; -- GitLab From 75e406b540c3eca67625d97bbefd4e3787eafbfe Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 18 Apr 2023 08:32:30 -0700 Subject: [PATCH 4662/5631] platform/x86/intel-uncore-freq: Return error on write frequency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently when the uncore_write() returns error, it is silently ignored. Return error to user space when uncore_write() fails. Fixes: 49a474c7ba51 ("platform/x86: Add support for Uncore frequency control") Signed-off-by: Srinivas Pandruvada Reviewed-by: Zhang Rui Tested-by: Wendy Wang Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20230418153230.679094-1-srinivas.pandruvada@linux.intel.com Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede --- .../x86/intel/uncore-frequency/uncore-frequency-common.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c index 1a300e14f350..064f186ae81b 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c @@ -44,14 +44,18 @@ static ssize_t store_min_max_freq_khz(struct uncore_data *data, int min_max) { unsigned int input; + int ret; if (kstrtouint(buf, 10, &input)) return -EINVAL; mutex_lock(&uncore_lock); - uncore_write(data, input, min_max); + ret = uncore_write(data, input, min_max); mutex_unlock(&uncore_lock); + if (ret) + return ret; + return count; } -- GitLab From decab2825c3ef9b154c6f76bce40872ffb41c36f Mon Sep 17 00:00:00 2001 From: Fae Date: Tue, 25 Apr 2023 01:36:44 -0500 Subject: [PATCH 4663/5631] platform/x86: hp-wmi: add micmute to hp_wmi_keymap struct Fixes micmute key of HP Envy X360 ey0xxx. Signed-off-by: Fae Link: https://lore.kernel.org/r/20230425063644.11828-1-faenkhauser@gmail.com Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/hp/hp-wmi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 873f59c3e280..6364ae262705 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -211,6 +211,7 @@ struct bios_rfkill2_state { static const struct key_entry hp_wmi_keymap[] = { { KE_KEY, 0x02, { KEY_BRIGHTNESSUP } }, { KE_KEY, 0x03, { KEY_BRIGHTNESSDOWN } }, + { KE_KEY, 0x270, { KEY_MICMUTE } }, { KE_KEY, 0x20e6, { KEY_PROG1 } }, { KE_KEY, 0x20e8, { KEY_MEDIA } }, { KE_KEY, 0x2142, { KEY_MEDIA } }, -- GitLab From 0c0cd3e25a5b64b541dd83ba6e032475a9d77432 Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Fri, 5 May 2023 09:25:22 -0400 Subject: [PATCH 4664/5631] platform/x86: thinkpad_acpi: Fix platform profiles on T490 I had incorrectly thought that PSC profiles were not usable on Intel platforms so had blocked them in the driver initialistion. This broke platform profiles on the T490. After discussion with the FW team PSC does work on Intel platforms and should be allowed. Note - it's possible this may impact other platforms where it is advertised but special driver support that only Windows has is needed. But if it does then they will need fixing via quirks. Please report any issues to me so I can get them addressed - but I haven't found any problems in testing...yet Fixes: bce6243f767f ("platform/x86: thinkpad_acpi: do not use PSC mode on Intel platforms") Link: https://bugzilla.redhat.com/show_bug.cgi?id=2177962 Cc: stable@vger.kernel.org Signed-off-by: Mark Pearson Link: https://lore.kernel.org/r/20230505132523.214338-1-mpearson-lenovo@squebb.ca Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/thinkpad_acpi.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 6fe82f805ea8..7976379887a5 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -10593,11 +10593,6 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) dytc_mmc_get_available = true; } } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { /* PSC MODE */ - /* Support for this only works on AMD platforms */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - dbg_printk(TPACPI_DBG_INIT, "PSC not support on Intel platforms\n"); - return -ENODEV; - } pr_debug("PSC is supported\n"); } else { dbg_printk(TPACPI_DBG_INIT, "No DYTC support available\n"); -- GitLab From 1684878952929e20a864af5df7b498941c750f45 Mon Sep 17 00:00:00 2001 From: Mark Pearson Date: Fri, 5 May 2023 09:25:23 -0400 Subject: [PATCH 4665/5631] platform/x86: thinkpad_acpi: Add profile force ability There has been a lot of confusion around which platform profiles are supported on various platforms and it would be useful to have a debug method to be able to override the profile mode that is selected. I don't expect this to be used in anything other than debugging in conjunction with Lenovo engineers - but it does give a way to get a system working whilst we wait for either FW fixes, or a driver fix to land upstream, if something is wonky in the mode detection logic Signed-off-by: Mark Pearson Link: https://lore.kernel.org/r/20230505132523.214338-2-mpearson-lenovo@squebb.ca Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/thinkpad_acpi.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 7976379887a5..b3808ad77278 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -10318,6 +10318,7 @@ static atomic_t dytc_ignore_event = ATOMIC_INIT(0); static DEFINE_MUTEX(dytc_mutex); static int dytc_capabilities; static bool dytc_mmc_get_available; +static int profile_force; static int convert_dytc_to_profile(int funcmode, int dytcmode, enum platform_profile_option *profile) @@ -10580,6 +10581,21 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (err) return err; + /* Check if user wants to override the profile selection */ + if (profile_force) { + switch (profile_force) { + case -1: + dytc_capabilities = 0; + break; + case 1: + dytc_capabilities = BIT(DYTC_FC_MMC); + break; + case 2: + dytc_capabilities = BIT(DYTC_FC_PSC); + break; + } + pr_debug("Profile selection forced: 0x%x\n", dytc_capabilities); + } if (dytc_capabilities & BIT(DYTC_FC_MMC)) { /* MMC MODE */ pr_debug("MMC is supported\n"); /* @@ -11641,6 +11657,9 @@ MODULE_PARM_DESC(uwb_state, "Initial state of the emulated UWB switch"); #endif +module_param(profile_force, int, 0444); +MODULE_PARM_DESC(profile_force, "Force profile mode. -1=off, 1=MMC, 2=PSC"); + static void thinkpad_acpi_module_exit(void) { struct ibm_struct *ibm, *itmp; -- GitLab From 6abfa99ce52f61a31bcfc2aaaae09006f5665495 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 5 May 2023 23:03:23 +0200 Subject: [PATCH 4666/5631] platform/x86: touchscreen_dmi: Add upside-down quirk for GDIX1002 ts on the Juno Tablet The Juno Computers Juno Tablet has an upside-down mounted Goodix touchscreen. Add a quirk to invert both axis to correct for this. Link: https://junocomputers.com/us/product/juno-tablet/ Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20230505210323.43177-1-hdegoede@redhat.com --- drivers/platform/x86/touchscreen_dmi.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 13802a3c3591..3b32c3346a45 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -378,6 +378,11 @@ static const struct ts_dmi_data gdix1001_01_upside_down_data = { .properties = gdix1001_upside_down_props, }; +static const struct ts_dmi_data gdix1002_00_upside_down_data = { + .acpi_name = "GDIX1002:00", + .properties = gdix1001_upside_down_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -1295,6 +1300,18 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BIOS_VERSION, "jumperx.T87.KFBNEEA"), }, }, + { + /* Juno Tablet */ + .driver_data = (void *)&gdix1002_00_upside_down_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Default string"), + /* Both product- and board-name being "Default string" is somewhat rare */ + DMI_MATCH(DMI_PRODUCT_NAME, "Default string"), + DMI_MATCH(DMI_BOARD_NAME, "Default string"), + /* Above matches are too generic, add partial bios-version match */ + DMI_MATCH(DMI_BIOS_VERSION, "JP2V1."), + }, + }, { /* Mediacom WinPad 7.0 W700 (same hw as Wintron surftab 7") */ .driver_data = (void *)&trekstor_surftab_wintron70_data, -- GitLab From 4b65f95c87c35699bc6ad540d6b9dd7f950d0924 Mon Sep 17 00:00:00 2001 From: Andrey Avdeev Date: Sun, 30 Apr 2023 11:01:10 +0300 Subject: [PATCH 4667/5631] platform/x86: touchscreen_dmi: Add info for the Dexp Ursus KX210i Add touchscreen info for the Dexp Ursus KX210i Signed-off-by: Andrey Avdeev Link: https://lore.kernel.org/r/ZE4gRgzRQCjXFYD0@avdeevavpc Cc: stable@vger.kernel.org Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/touchscreen_dmi.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 3b32c3346a45..68e66b60445c 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -336,6 +336,22 @@ static const struct ts_dmi_data dexp_ursus_7w_data = { .properties = dexp_ursus_7w_props, }; +static const struct property_entry dexp_ursus_kx210i_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 5), + PROPERTY_ENTRY_U32("touchscreen-min-y", 2), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1720), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1137), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-dexp-ursus-kx210i.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data dexp_ursus_kx210i_data = { + .acpi_name = "MSSL1680:00", + .properties = dexp_ursus_kx210i_props, +}; + static const struct property_entry digma_citi_e200_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), PROPERTY_ENTRY_U32("touchscreen-size-y", 1500), @@ -1190,6 +1206,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "7W"), }, }, + { + /* DEXP Ursus KX210i */ + .driver_data = (void *)&dexp_ursus_kx210i_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "INSYDE Corp."), + DMI_MATCH(DMI_PRODUCT_NAME, "S107I"), + }, + }, { /* Digma Citi E200 */ .driver_data = (void *)&digma_citi_e200_data, -- GitLab From 162bd18eb55adf464a0fa2b4144b8d61c75ff7c2 Mon Sep 17 00:00:00 2001 From: Roy Novich Date: Sun, 7 May 2023 16:57:43 +0300 Subject: [PATCH 4668/5631] linux/dim: Do nothing if no time delta between samples Add return value for dim_calc_stats. This is an indication for the caller if curr_stats was assigned by the function. Avoid using curr_stats uninitialized over {rdma/net}_dim, when no time delta between samples. Coverity reported this potential use of an uninitialized variable. Fixes: 4c4dbb4a7363 ("net/mlx5e: Move dynamic interrupt coalescing code to include/linux") Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing") Signed-off-by: Roy Novich Reviewed-by: Aya Levin Reviewed-by: Saeed Mahameed Signed-off-by: Tariq Toukan Reviewed-by: Leon Romanovsky Reviewed-by: Michal Kubiak Link: https://lore.kernel.org/r/20230507135743.138993-1-tariqt@nvidia.com Signed-off-by: Paolo Abeni --- include/linux/dim.h | 3 ++- lib/dim/dim.c | 5 +++-- lib/dim/net_dim.c | 3 ++- lib/dim/rdma_dim.c | 3 ++- 4 files changed, 9 insertions(+), 5 deletions(-) diff --git a/include/linux/dim.h b/include/linux/dim.h index 6c5733981563..f343bc9aa2ec 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -236,8 +236,9 @@ void dim_park_tired(struct dim *dim); * * Calculate the delta between two samples (in data rates). * Takes into consideration counter wrap-around. + * Returned boolean indicates whether curr_stats are reliable. */ -void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** diff --git a/lib/dim/dim.c b/lib/dim/dim.c index 38045d6d0538..e89aaf07bde5 100644 --- a/lib/dim/dim.c +++ b/lib/dim/dim.c @@ -54,7 +54,7 @@ void dim_park_tired(struct dim *dim) } EXPORT_SYMBOL(dim_park_tired); -void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, +bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats) { /* u32 holds up to 71 minutes, should be enough */ @@ -66,7 +66,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, start->comp_ctr); if (!delta_us) - return; + return false; curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); @@ -79,5 +79,6 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, else curr_stats->cpe_ratio = 0; + return true; } EXPORT_SYMBOL(dim_calc_stats); diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 53f6b9c6e936..4e32f7aaac86 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -227,7 +227,8 @@ void net_dim(struct dim *dim, struct dim_sample end_sample) dim->start_sample.event_ctr); if (nevents < DIM_NEVENTS) break; - dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats); + if (!dim_calc_stats(&dim->start_sample, &end_sample, &curr_stats)) + break; if (net_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); diff --git a/lib/dim/rdma_dim.c b/lib/dim/rdma_dim.c index 15462d54758d..88f779486707 100644 --- a/lib/dim/rdma_dim.c +++ b/lib/dim/rdma_dim.c @@ -88,7 +88,8 @@ void rdma_dim(struct dim *dim, u64 completions) nevents = curr_sample->event_ctr - dim->start_sample.event_ctr; if (nevents < DIM_NEVENTS) break; - dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats); + if (!dim_calc_stats(&dim->start_sample, curr_sample, &curr_stats)) + break; if (rdma_dim_decision(&curr_stats, dim)) { dim->state = DIM_APPLY_NEW_PROFILE; schedule_work(&dim->work); -- GitLab From 003fb0a51162d940f25fc35e70b0996a12c9e08a Mon Sep 17 00:00:00 2001 From: Christian Loehle Date: Wed, 26 Apr 2023 16:59:39 +0000 Subject: [PATCH 4669/5631] mmc: block: ensure error propagation for non-blk Requests to the mmc layer usually come through a block device IO. The exceptions are the ioctl interface, RPMB chardev ioctl and debugfs, which issue their own blk_mq requests through blk_execute_rq and do not query the BLK_STS error but the mmcblk-internal drv_op_result. This patch ensures that drv_op_result defaults to an error and has to be overwritten by the operation to be considered successful. The behavior leads to a bug where the request never propagates the error, e.g. by directly erroring out at mmc_blk_mq_issue_rq if mmc_blk_part_switch fails. The ioctl caller of the rpmb chardev then can never see an error (BLK_STS_IOERR, but drv_op_result is unchanged) and thus may assume that their call executed successfully when it did not. While always checking the blk_execute_rq return value would be advised, let's eliminate the error by always setting drv_op_result as -EIO to be overwritten on success (or other error) Fixes: 614f0388f580 ("mmc: block: move single ioctl() commands to block requests") Signed-off-by: Christian Loehle Acked-by: Adrian Hunter Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/59c17ada35664b818b7bd83752119b2d@hyperstone.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/block.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 00c33edb9fb9..d920c4178389 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -264,6 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev, goto out_put; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; blk_mq_free_request(req); @@ -651,6 +652,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, idatas[0] = idata; req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idatas; req_to_mmc_queue_req(req)->ioc_count = 1; blk_execute_rq(req, false); @@ -722,6 +724,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, } req_to_mmc_queue_req(req)->drv_op = rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = idata; req_to_mmc_queue_req(req)->ioc_count = n; blk_execute_rq(req, false); @@ -2806,6 +2809,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; if (ret >= 0) { @@ -2844,6 +2848,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) goto out_free; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD; + req_to_mmc_queue_req(req)->drv_op_result = -EIO; req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; blk_execute_rq(req, false); err = req_to_mmc_queue_req(req)->drv_op_result; -- GitLab From e5bce3c15ad20d7dd4f8393513b1c41373d2dc37 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 25 Apr 2023 15:41:26 +0200 Subject: [PATCH 4670/5631] mmc: sdhci-cadence: Fix an error handling path in sdhci_cdns_probe() If devm_reset_control_get_optional_exclusive() fails, some resources still need to be released. So branch to the error handling path instead of returning directly. Fixes: aad53d4ee756 ("mmc: sdhci-cadence: Support mmc hardware reset") Signed-off-by: Christophe JAILLET Acked-by: Adrian Hunter Acked-by: Brad Larson Link: https://lore.kernel.org/r/f61599a9ef23767c2d66e5af9c975f05ef1cec6b.1682430069.git.christophe.jaillet@wanadoo.fr Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-cadence.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c index b24aa27da50c..d2f625054689 100644 --- a/drivers/mmc/host/sdhci-cadence.c +++ b/drivers/mmc/host/sdhci-cadence.c @@ -540,9 +540,11 @@ static int sdhci_cdns_probe(struct platform_device *pdev) if (host->mmc->caps & MMC_CAP_HW_RESET) { priv->rst_hw = devm_reset_control_get_optional_exclusive(dev, NULL); - if (IS_ERR(priv->rst_hw)) - return dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), - "reset controller error\n"); + if (IS_ERR(priv->rst_hw)) { + ret = dev_err_probe(mmc_dev(host->mmc), PTR_ERR(priv->rst_hw), + "reset controller error\n"); + goto free; + } if (priv->rst_hw) host->mmc_host_ops.card_hw_reset = sdhci_cdns_mmc_hw_reset; } -- GitLab From 3d43f9f639542fadfb28f40b509bf147a6624d48 Mon Sep 17 00:00:00 2001 From: Liming Sun Date: Wed, 26 Apr 2023 10:23:44 -0400 Subject: [PATCH 4671/5631] platform/mellanox: fix potential race in mlxbf-tmfifo driver This commit adds memory barrier for the 'vq' update in function mlxbf_tmfifo_virtio_find_vqs() to avoid potential race due to out-of-order memory write. It also adds barrier for the 'is_ready' flag to make sure the initializations are visible before this flag is checked. Signed-off-by: Liming Sun Reviewed-by: Vadim Pasternak Link: https://lore.kernel.org/r/b98c0ab61d644ba38fa9b3fd1607b138b0dd820b.1682518748.git.limings@nvidia.com Signed-off-by: Hans de Goede --- drivers/platform/mellanox/mlxbf-tmfifo.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index 91a077c35b8b..a79318e90a13 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -784,7 +784,7 @@ static void mlxbf_tmfifo_rxtx(struct mlxbf_tmfifo_vring *vring, bool is_rx) fifo = vring->fifo; /* Return if vdev is not ready. */ - if (!fifo->vdev[devid]) + if (!fifo || !fifo->vdev[devid]) return; /* Return if another vring is running. */ @@ -980,9 +980,13 @@ static int mlxbf_tmfifo_virtio_find_vqs(struct virtio_device *vdev, vq->num_max = vring->num; + vq->priv = vring; + + /* Make vq update visible before using it. */ + virtio_mb(false); + vqs[i] = vq; vring->vq = vq; - vq->priv = vring; } return 0; @@ -1302,6 +1306,9 @@ static int mlxbf_tmfifo_probe(struct platform_device *pdev) mod_timer(&fifo->timer, jiffies + MLXBF_TMFIFO_TIMER_INTERVAL); + /* Make all updates visible before setting the 'is_ready' flag. */ + virtio_mb(false); + fifo->is_ready = true; return 0; -- GitLab From 81dce1490e28439c3cd8a8650b862a712f3061ba Mon Sep 17 00:00:00 2001 From: Haibo Chen Date: Thu, 4 May 2023 19:22:22 +0800 Subject: [PATCH 4672/5631] mmc: sdhci-esdhc-imx: make "no-mmc-hs400" works After commit 1ed5c3b22fc7 ("mmc: sdhci-esdhc-imx: Propagate ESDHC_FLAG_HS400* only on 8bit bus"), the property "no-mmc-hs400" from device tree file do not work any more. This patch reorder the code, which can avoid the warning message "drop HS400 support since no 8-bit bus" and also make the property "no-mmc-hs400" from dts file works. Fixes: 1ed5c3b22fc7 ("mmc: sdhci-esdhc-imx: Propagate ESDHC_FLAG_HS400* only on 8bit bus") Signed-off-by: Haibo Chen Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230504112222.3599602-1-haibo.chen@nxp.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/sdhci-esdhc-imx.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d7c0c0b9e26c..eebf94604a7f 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1634,6 +1634,10 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev, if (ret) return ret; + /* HS400/HS400ES require 8 bit bus */ + if (!(host->mmc->caps & MMC_CAP_8_BIT_DATA)) + host->mmc->caps2 &= ~(MMC_CAP2_HS400 | MMC_CAP2_HS400_ES); + if (mmc_gpio_get_cd(host->mmc) >= 0) host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; @@ -1724,10 +1728,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) host->mmc_host_ops.init_card = usdhc_init_card; } - err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); - if (err) - goto disable_ahb_clk; - if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) sdhci_esdhc_ops.platform_execute_tuning = esdhc_executing_tuning; @@ -1735,15 +1735,13 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536) host->quirks |= SDHCI_QUIRK_BROKEN_ADMA; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400) + if (imx_data->socdata->flags & ESDHC_FLAG_HS400) host->mmc->caps2 |= MMC_CAP2_HS400; if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23) host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN; - if (host->mmc->caps & MMC_CAP_8_BIT_DATA && - imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { + if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { host->mmc->caps2 |= MMC_CAP2_HS400_ES; host->mmc_host_ops.hs400_enhanced_strobe = esdhc_hs400_enhanced_strobe; @@ -1765,6 +1763,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) goto disable_ahb_clk; } + err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); + if (err) + goto disable_ahb_clk; + sdhci_esdhc_imx_hwinit(host); err = sdhci_add_host(host); -- GitLab From cc719a9ce7a455bef132e0211437847bcd89b4ef Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Tue, 9 May 2023 09:01:50 +0200 Subject: [PATCH 4673/5631] parisc: kexec: include reboot.h Include reboot.h in machine_kexec.c for declaration of machine_crash_shutdown and machine_shutdown. gcc-12 with W=1 reports: arch/parisc/kernel/kexec.c:57:6: warning: no previous prototype for 'machine_crash_shutdown' [-Wmissing-prototypes] 57 | void machine_crash_shutdown(struct pt_regs *regs) | ^~~~~~~~~~~~~~~~~~~~~~ arch/parisc/kernel/kexec.c:61:6: warning: no previous prototype for 'machine_shutdown' [-Wmissing-prototypes] 61 | void machine_shutdown(void) | ^~~~~~~~~~~~~~~~ No functional changes intended. Compile tested only. Signed-off-by: Simon Horman Acked-by: Baoquan He Signed-off-by: Helge Deller --- arch/parisc/kernel/kexec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/parisc/kernel/kexec.c b/arch/parisc/kernel/kexec.c index 5eb7f30edc1f..db57345a9daf 100644 --- a/arch/parisc/kernel/kexec.c +++ b/arch/parisc/kernel/kexec.c @@ -4,6 +4,8 @@ #include #include #include +#include + #include #include -- GitLab From 293007b033418c8c9d1b35d68dec49a500750fde Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 8 May 2023 12:13:27 -0600 Subject: [PATCH 4674/5631] io_uring: make io_uring_sqe_cmd() unconditionally available If CONFIG_IO_URING isn't set, then io_uring_sqe_cmd() is not defined. As the nvme driver uses this helper, it causes a compilation issue: drivers/nvme/host/ioctl.c: In function 'nvme_uring_cmd_io': drivers/nvme/host/ioctl.c:555:44: error: implicit declaration of function 'io_uring_sqe_cmd'; did you mean 'io_uring_free'? [-Werror=implicit-function-declaration] 555 | const struct nvme_uring_cmd *cmd = io_uring_sqe_cmd(ioucmd->sqe); | ^~~~~~~~~~~~~~~~ | io_uring_free Fix it by just making io_uring_sqe_cmd() generally available - the types are known, and there's no reason to hide it under CONFIG_IO_URING. Fixes: fd9b8547bc5c ("io_uring: Pass whole sqe to commands") Reported-by: kernel test robot Reported-by: Chen-Yu Tsai Tested-by: Chen-Yu Tsai Signed-off-by: Jens Axboe --- include/linux/io_uring.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 3399d979ee1c..7fe31b2cd02f 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -36,6 +36,11 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) +{ + return sqe->cmd; +} + #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); @@ -66,11 +71,6 @@ static inline void io_uring_free(struct task_struct *tsk) if (tsk->io_uring) __io_uring_free(tsk); } - -static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) -{ - return sqe->cmd; -} #else static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd) -- GitLab From 2cb6f968775a9fd60c90a6042b9550bcec3ea087 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 9 May 2023 01:00:42 -0500 Subject: [PATCH 4675/5631] SMB3: force unmount was failing to close deferred close files In investigating a failure with xfstest generic/392 it was noticed that mounts were reusing a superblock that should already have been freed. This turned out to be related to deferred close files keeping a reference count until the closetimeo expired. Currently the only way an fs knows that mount is beginning is when force unmount is called, but when this, ie umount_begin(), is called all deferred close files on the share (tree connection) should be closed immediately (unless shared by another mount) to avoid using excess resources on the server and to avoid reusing a superblock which should already be freed. In umount_begin, close all deferred close handles for that share if this is the last mount using that share on this client (ie send the SMB3 close request over the wire for those that have been already closed by the app but that we have kept a handle lease open for and have not sent closes to the server for yet). Reported-by: David Howells Acked-by: Bharath SM Cc: Fixes: 78c09634f7dc ("Cifs: Fix kernel oops caused by deferred close for files.") Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 81430abacf93..8b6b3b6985f3 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -744,6 +744,7 @@ static void cifs_umount_begin(struct super_block *sb) spin_unlock(&tcon->tc_lock); spin_unlock(&cifs_tcp_ses_lock); + cifs_close_all_deferred_files(tcon); /* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */ /* cancel_notify_requests(tcon); */ if (tcon->ses && tcon->ses->server) { -- GitLab From 716a3cf317456fa01d54398bb14ab354f50ed6a2 Mon Sep 17 00:00:00 2001 From: Steve French Date: Tue, 9 May 2023 01:37:19 -0500 Subject: [PATCH 4676/5631] smb3: fix problem remounting a share after shutdown xfstests generic/392 showed a problem where even after a shutdown call was made on a mount, we would still attempt to use the (now inaccessible) superblock if another mount was attempted for the same share. Reported-by: David Howells Reviewed-by: David Howells Cc: Fixes: 087f757b0129 ("cifs: add shutdown support") Signed-off-by: Steve French --- fs/cifs/connect.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index eeeed6fda13b..8e9a672320ab 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2709,6 +2709,13 @@ cifs_match_super(struct super_block *sb, void *data) spin_lock(&cifs_tcp_ses_lock); cifs_sb = CIFS_SB(sb); + + /* We do not want to use a superblock that has been shutdown */ + if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) { + spin_unlock(&cifs_tcp_ses_lock); + return 0; + } + tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); if (tlink == NULL) { /* can not match superblock if tlink were ever null */ -- GitLab From 16a8829130ca22666ac6236178a6233208d425c3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 9 May 2023 10:22:13 -0700 Subject: [PATCH 4677/5631] nfs: fix another case of NULL/IS_ERR confusion wrt folio pointers Dan has been improving on the smatch error pointer checks, and pointed at another case where the __filemap_get_folio() conversion to error pointers had been overlooked. This time because it was hidden behind the filemap_grab_folio() helper function that is a wrapper around it. Reported-by: Dan Carpenter Cc: Anna Schumaker Cc: Matthew Wilcox Cc: Christoph Hellwig Signed-off-by: Linus Torvalds --- fs/nfs/dir.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bacad0c57810..e63c1d46f189 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -402,7 +402,7 @@ static struct folio *nfs_readdir_folio_get_locked(struct address_space *mapping, struct folio *folio; folio = filemap_grab_folio(mapping, index); - if (!folio) + if (IS_ERR(folio)) return NULL; nfs_readdir_folio_init_and_validate(folio, cookie, change_attr); return folio; -- GitLab From c87f318e6f47696b4040b58f460d5c17ea0280e6 Mon Sep 17 00:00:00 2001 From: Anastasia Belova Date: Wed, 26 Apr 2023 14:53:23 +0300 Subject: [PATCH 4678/5631] btrfs: print-tree: parent bytenr must be aligned to sector size Check nodesize to sectorsize in alignment check in print_extent_item. The comment states that and this is correct, similar check is done elsewhere in the functions. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: ea57788eb76d ("btrfs: require only sector size alignment for parent eb bytenr") CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Qu Wenruo Signed-off-by: Anastasia Belova Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/print-tree.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index b93c96213304..497b9dbd8a13 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -151,10 +151,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); /* - * offset is supposed to be a tree block which - * must be aligned to nodesize. + * Offset is supposed to be a tree block which must be + * aligned to sectorsize. */ - if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + if (!IS_ALIGNED(offset, eb->fs_info->sectorsize)) pr_info( "\t\t\t(parent %llu not aligned to sectorsize %u)\n", offset, eb->fs_info->sectorsize); -- GitLab From 0004ff15ea26015a0a3a6182dca3b9d1df32e2b7 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 4 May 2023 12:04:18 +0100 Subject: [PATCH 4679/5631] btrfs: fix space cache inconsistency after error loading it from disk When loading a free space cache from disk, at __load_free_space_cache(), if we fail to insert a bitmap entry, we still increment the number of total bitmaps in the btrfs_free_space_ctl structure, which is incorrect since we failed to add the bitmap entry. On error we then empty the cache by calling __btrfs_remove_free_space_cache(), which will result in getting the total bitmaps counter set to 1. A failure to load a free space cache is not critical, so if a failure happens we just rebuild the cache by scanning the extent tree, which happens at block-group.c:caching_thread(). Yet the failure will result in having the total bitmaps of the btrfs_free_space_ctl always bigger by 1 then the number of bitmap entries we have. So fix this by having the total bitmaps counter be incremented only if we successfully added the bitmap entry. Fixes: a67509c30079 ("Btrfs: add a io_ctl struct and helpers for dealing with the space cache") Reviewed-by: Anand Jain CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/free-space-cache.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index d84cef89cdff..cf98a3c05480 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -870,15 +870,16 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); - ctl->total_bitmaps++; - recalculate_thresholds(ctl); - spin_unlock(&ctl->tree_lock); if (ret) { + spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } + ctl->total_bitmaps++; + recalculate_thresholds(ctl); + spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } -- GitLab From 0cad8f14d70cfeb5173dce93cafeba665a95430e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Tue, 9 May 2023 12:50:02 +0100 Subject: [PATCH 4680/5631] btrfs: fix backref walking not returning all inode refs When using the logical to ino ioctl v2, if the flag to ignore offsets of file extent items (BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET) is given, the backref walking code ends up not returning references for all file offsets of an inode that point to the given logical bytenr. This happens since kernel 6.2, commit 6ce6ba534418 ("btrfs: use a single argument for extent offset in backref walking functions") because: 1) It mistakenly skipped the search for file extent items in a leaf that point to the target extent if that flag is given. Instead it should only skip the filtering done by check_extent_in_eb() - that is, it should not avoid the calls to that function (or find_extent_in_eb(), which uses it). 2) It was also not building a list of inode extent elements (struct extent_inode_elem) if we have multiple inode references for an extent when the ignore offset flag is given to the logical to ino ioctl - it would leave a single element, only the last one that was found. These stem from the confusing old interface for backref walking functions where we had an extent item offset argument that was a pointer to a u64 and another boolean argument that indicated if the offset should be ignored, but the pointer could be NULL. That NULL case is used by relocation, qgroup extent accounting and fiemap, simply to avoid building the inode extent list for each reference, as it's not necessary for those use cases and therefore avoids memory allocations and some computations. Fix this by adding a boolean argument to the backref walk context structure to indicate that the inode extent list should not be built, make relocation set that argument to true and fix the backref walking logic to skip the calls to check_extent_in_eb() and find_extent_in_eb() only if this new argument is true, instead of 'ignore_extent_item_pos' being true. A test case for fstests will be added soon, to provide cover not only for these cases but to the logical to ino ioctl in general as well, as currently we do not have a test case for it. Reported-by: Vladimir Panteleev Link: https://lore.kernel.org/linux-btrfs/CAHhfkvwo=nmzrJSqZ2qMfF-rZB-ab6ahHnCD_sq9h4o8v+M7QQ@mail.gmail.com/ Fixes: 6ce6ba534418 ("btrfs: use a single argument for extent offset in backref walking functions") CC: stable@vger.kernel.org # 6.2+ Tested-by: Vladimir Panteleev Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/backref.c | 19 ++++++++++--------- fs/btrfs/backref.h | 6 ++++++ fs/btrfs/relocation.c | 2 +- 3 files changed, 17 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index e54f0884802a..79336fa853db 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -45,7 +45,8 @@ static int check_extent_in_eb(struct btrfs_backref_walk_ctx *ctx, int root_count; bool cached; - if (!btrfs_file_extent_compression(eb, fi) && + if (!ctx->ignore_extent_item_pos && + !btrfs_file_extent_compression(eb, fi) && !btrfs_file_extent_encryption(eb, fi) && !btrfs_file_extent_other_encoding(eb, fi)) { u64 data_offset; @@ -552,7 +553,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, count++; else goto next; - if (!ctx->ignore_extent_item_pos) { + if (!ctx->skip_inode_ref_list) { ret = check_extent_in_eb(ctx, &key, eb, fi, &eie); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) @@ -564,7 +565,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, eie, (void **)&old, GFP_NOFS); if (ret < 0) break; - if (!ret && !ctx->ignore_extent_item_pos) { + if (!ret && !ctx->skip_inode_ref_list) { while (old->next) old = old->next; old->next = eie; @@ -1606,7 +1607,7 @@ static int find_parent_nodes(struct btrfs_backref_walk_ctx *ctx, goto out; } if (ref->count && ref->parent) { - if (!ctx->ignore_extent_item_pos && !ref->inode_list && + if (!ctx->skip_inode_ref_list && !ref->inode_list && ref->level == 0) { struct btrfs_tree_parent_check check = { 0 }; struct extent_buffer *eb; @@ -1647,7 +1648,7 @@ static int find_parent_nodes(struct btrfs_backref_walk_ctx *ctx, (void **)&eie, GFP_NOFS); if (ret < 0) goto out; - if (!ret && !ctx->ignore_extent_item_pos) { + if (!ret && !ctx->skip_inode_ref_list) { /* * We've recorded that parent, so we must extend * its inode list here. @@ -1743,7 +1744,7 @@ int btrfs_find_all_leafs(struct btrfs_backref_walk_ctx *ctx) static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) { const u64 orig_bytenr = ctx->bytenr; - const bool orig_ignore_extent_item_pos = ctx->ignore_extent_item_pos; + const bool orig_skip_inode_ref_list = ctx->skip_inode_ref_list; bool roots_ulist_allocated = false; struct ulist_iterator uiter; int ret = 0; @@ -1764,7 +1765,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) roots_ulist_allocated = true; } - ctx->ignore_extent_item_pos = true; + ctx->skip_inode_ref_list = true; ULIST_ITER_INIT(&uiter); while (1) { @@ -1789,7 +1790,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) ulist_free(ctx->refs); ctx->refs = NULL; ctx->bytenr = orig_bytenr; - ctx->ignore_extent_item_pos = orig_ignore_extent_item_pos; + ctx->skip_inode_ref_list = orig_skip_inode_ref_list; return ret; } @@ -1912,7 +1913,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, goto out_trans; } - walk_ctx.ignore_extent_item_pos = true; + walk_ctx.skip_inode_ref_list = true; walk_ctx.trans = trans; walk_ctx.fs_info = fs_info; walk_ctx.refs = &ctx->refs; diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index ef6bbea3f456..1616e3e3f1e4 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -60,6 +60,12 @@ struct btrfs_backref_walk_ctx { * @extent_item_pos is ignored. */ bool ignore_extent_item_pos; + /* + * If true and bytenr corresponds to a data extent, then the inode list + * (each member describing inode number, file offset and root) is not + * added to each reference added to the @refs ulist. + */ + bool skip_inode_ref_list; /* A valid transaction handle or NULL. */ struct btrfs_trans_handle *trans; /* diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 09b1988d1791..59a06499c647 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3422,7 +3422,7 @@ int add_data_references(struct reloc_control *rc, btrfs_release_path(path); ctx.bytenr = extent_key->objectid; - ctx.ignore_extent_item_pos = true; + ctx.skip_inode_ref_list = true; ctx.fs_info = rc->extent_root->fs_info; ret = btrfs_find_all_leafs(&ctx); -- GitLab From 73a23d7710331a530e972903318528b75e5a5f58 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 25 Apr 2023 10:38:37 +0200 Subject: [PATCH 4681/5631] um: harddog: fix modular build Since we no longer (want to) export any libc symbols the _user portions of any drivers need to be built into image rather than the module. I missed this for the watchdog. Fix the watchdog accordingly. Reported-by: kernel test robot Signed-off-by: Johannes Berg Signed-off-by: Richard Weinberger --- arch/um/drivers/Makefile | 4 +++- arch/um/drivers/harddog.h | 9 +++++++++ arch/um/drivers/harddog_kern.c | 7 +------ arch/um/drivers/harddog_user.c | 1 + arch/um/drivers/harddog_user_exp.c | 9 +++++++++ 5 files changed, 23 insertions(+), 7 deletions(-) create mode 100644 arch/um/drivers/harddog.h create mode 100644 arch/um/drivers/harddog_user_exp.c diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index dee6f66353b3..a461a950f051 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -16,7 +16,8 @@ mconsole-objs := mconsole_kern.o mconsole_user.o hostaudio-objs := hostaudio_kern.o ubd-objs := ubd_kern.o ubd_user.o port-objs := port_kern.o port_user.o -harddog-objs := harddog_kern.o harddog_user.o +harddog-objs := harddog_kern.o +harddog-builtin-$(CONFIG_UML_WATCHDOG) := harddog_user.o harddog_user_exp.o rtc-objs := rtc_kern.o rtc_user.o LDFLAGS_pcap.o = $(shell $(CC) $(KBUILD_CFLAGS) -print-file-name=libpcap.a) @@ -60,6 +61,7 @@ obj-$(CONFIG_PTY_CHAN) += pty.o obj-$(CONFIG_TTY_CHAN) += tty.o obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o obj-$(CONFIG_UML_WATCHDOG) += harddog.o +obj-y += $(harddog-builtin-y) $(harddog-builtin-m) obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o diff --git a/arch/um/drivers/harddog.h b/arch/um/drivers/harddog.h new file mode 100644 index 000000000000..6d9ea60e7133 --- /dev/null +++ b/arch/um/drivers/harddog.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef UM_WATCHDOG_H +#define UM_WATCHDOG_H + +int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); +void stop_watchdog(int in_fd, int out_fd); +int ping_watchdog(int fd); + +#endif /* UM_WATCHDOG_H */ diff --git a/arch/um/drivers/harddog_kern.c b/arch/um/drivers/harddog_kern.c index e6d4f43deba8..60d1c6cab8a9 100644 --- a/arch/um/drivers/harddog_kern.c +++ b/arch/um/drivers/harddog_kern.c @@ -47,6 +47,7 @@ #include #include #include "mconsole.h" +#include "harddog.h" MODULE_LICENSE("GPL"); @@ -60,8 +61,6 @@ static int harddog_out_fd = -1; * Allow only one person to hold it open */ -extern int start_watchdog(int *in_fd_ret, int *out_fd_ret, char *sock); - static int harddog_open(struct inode *inode, struct file *file) { int err = -EBUSY; @@ -92,8 +91,6 @@ static int harddog_open(struct inode *inode, struct file *file) return err; } -extern void stop_watchdog(int in_fd, int out_fd); - static int harddog_release(struct inode *inode, struct file *file) { /* @@ -112,8 +109,6 @@ static int harddog_release(struct inode *inode, struct file *file) return 0; } -extern int ping_watchdog(int fd); - static ssize_t harddog_write(struct file *file, const char __user *data, size_t len, loff_t *ppos) { diff --git a/arch/um/drivers/harddog_user.c b/arch/um/drivers/harddog_user.c index 070468d22e39..9ed89304975e 100644 --- a/arch/um/drivers/harddog_user.c +++ b/arch/um/drivers/harddog_user.c @@ -7,6 +7,7 @@ #include #include #include +#include "harddog.h" struct dog_data { int stdin_fd; diff --git a/arch/um/drivers/harddog_user_exp.c b/arch/um/drivers/harddog_user_exp.c new file mode 100644 index 000000000000..c74d4b815d14 --- /dev/null +++ b/arch/um/drivers/harddog_user_exp.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "harddog.h" + +#if IS_MODULE(CONFIG_UML_WATCHDOG) +EXPORT_SYMBOL(start_watchdog); +EXPORT_SYMBOL(stop_watchdog); +EXPORT_SYMBOL(ping_watchdog); +#endif -- GitLab From 3b90b09af5be42491a8a74a549318cfa265b3029 Mon Sep 17 00:00:00 2001 From: Alexandre Ghiti Date: Thu, 4 May 2023 14:07:59 +0200 Subject: [PATCH 4682/5631] riscv: Fix orphan section warnings caused by kernel/pi kernel/pi gives rise to a lot of new sections that end up orphans: the first attempt to fix that tried to enumerate them all in the linker script, but kernel test robot with a random config keeps finding more of them. So prefix all those sections with .init.pi instead of only .init in order to be able to easily catch them all in the linker script. Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202304301606.Cgp113Ha-lkp@intel.com/ Fixes: 26e7aacb83df ("riscv: Allow to downgrade paging mode from the command line") Signed-off-by: Alexandre Ghiti Link: https://lore.kernel.org/r/20230504120759.18730-1-alexghiti@rivosinc.com Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/pi/Makefile | 2 +- arch/riscv/kernel/vmlinux.lds.S | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index 5d7cb991f2b8..7b593d44c712 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -22,7 +22,7 @@ KCOV_INSTRUMENT := n $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ --remove-section=.note.gnu.property \ - --prefix-alloc-sections=.init + --prefix-alloc-sections=.init.pi $(obj)/%.pi.o: $(obj)/%.o FORCE $(call if_changed,objcopy) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index f03b5697f8e0..e5f9f4677bbf 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -84,11 +84,8 @@ SECTIONS __init_data_begin = .; INIT_DATA_SECTION(16) - /* Those sections result from the compilation of kernel/pi/string.c */ - .init.pidata : { - *(.init.srodata.cst8*) - *(.init__bug_table*) - *(.init.sdata*) + .init.pi : { + *(.init.pi*) } .init.bss : { -- GitLab From 8efbdbfa99381a017dd2c0f6375a7d80a8118b74 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 7 May 2023 01:58:45 +0200 Subject: [PATCH 4683/5631] net: stmmac: Initialize MAC_ONEUS_TIC_COUNTER register Initialize MAC_ONEUS_TIC_COUNTER register with correct value derived from CSR clock, otherwise EEE is unstable on at least NXP i.MX8M Plus and Micrel KSZ9131RNX PHY, to the point where not even ARP request can be sent out. i.MX 8M Plus Applications Processor Reference Manual, Rev. 1, 06/2021 11.7.6.1.34 One-microsecond Reference Timer (MAC_ONEUS_TIC_COUNTER) defines this register as: " This register controls the generation of the Reference time (1 microsecond tic) for all the LPI timers. This timer has to be programmed by the software initially. ... The application must program this counter so that the number of clock cycles of CSR clock is 1us. (Subtract 1 from the value before programming). For example if the CSR clock is 100MHz then this field needs to be programmed to value 100 - 1 = 99 (which is 0x63). This is required to generate the 1US events that are used to update some of the EEE related counters. " The reset value is 0x63 on i.MX8M Plus, which means expected CSR clock are 100 MHz. However, the i.MX8M Plus "enet_qos_root_clk" are 266 MHz instead, which means the LPI timers reach their count much sooner on this platform. This is visible using a scope by monitoring e.g. exit from LPI mode on TX_CTL line from MAC to PHY. This should take 30us per STMMAC_DEFAULT_TWT_LS setting, during which the TX_CTL line transitions from tristate to low, and 30 us later from low to high. On i.MX8M Plus, this transition takes 11 us, which matches the 30us * 100/266 formula for misconfigured MAC_ONEUS_TIC_COUNTER register. Configure MAC_ONEUS_TIC_COUNTER based on CSR clock, so that the LPI timers have correct 1us reference. This then fixes EEE on i.MX8M Plus with Micrel KSZ9131RNX PHY. Fixes: 477286b53f55 ("stmmac: add GMAC4 core support") Signed-off-by: Marek Vasut Tested-by: Harald Seiler Reviewed-by: Francesco Dolcini Tested-by: Francesco Dolcini # Toradex Verdin iMX8MP Reviewed-by: Jesse Brandeburg Link: https://lore.kernel.org/r/20230506235845.246105-1-marex@denx.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 1 + drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 4538f334df57..d3c5306f1c41 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -181,6 +181,7 @@ enum power_event { #define GMAC4_LPI_CTRL_STATUS 0xd0 #define GMAC4_LPI_TIMER_CTRL 0xd4 #define GMAC4_LPI_ENTRY_TIMER 0xd8 +#define GMAC4_MAC_ONEUS_TIC_COUNTER 0xdc /* LPI control and status defines */ #define GMAC4_LPI_CTRL_STATUS_LPITCSE BIT(21) /* LPI Tx Clock Stop Enable */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index afaec3fb9ab6..03b1c5a97826 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -25,6 +25,7 @@ static void dwmac4_core_init(struct mac_device_info *hw, struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); + u32 clk_rate; value |= GMAC_CORE_INIT; @@ -47,6 +48,10 @@ static void dwmac4_core_init(struct mac_device_info *hw, writel(value, ioaddr + GMAC_CONFIG); + /* Configure LPI 1us counter to number of CSR clock ticks in 1us - 1 */ + clk_rate = clk_get_rate(priv->plat->stmmac_clk); + writel((clk_rate / 1000000) - 1, ioaddr + GMAC4_MAC_ONEUS_TIC_COUNTER); + /* Enable GMAC interrupts */ value = GMAC_INT_DEFAULT_ENABLE; -- GitLab From dfd9248c071a3710c24365897459538551cb7167 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 8 May 2023 10:55:43 -0700 Subject: [PATCH 4684/5631] net: Fix load-tearing on sk->sk_stamp in sock_recv_cmsgs(). KCSAN found a data race in sock_recv_cmsgs() where the read access to sk->sk_stamp needs READ_ONCE(). BUG: KCSAN: data-race in packet_recvmsg / packet_recvmsg write (marked) to 0xffff88803c81f258 of 8 bytes by task 19171 on cpu 0: sock_write_timestamp include/net/sock.h:2670 [inline] sock_recv_cmsgs include/net/sock.h:2722 [inline] packet_recvmsg+0xb97/0xd00 net/packet/af_packet.c:3489 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg+0x11a/0x130 net/socket.c:1040 sock_read_iter+0x176/0x220 net/socket.c:1118 call_read_iter include/linux/fs.h:1845 [inline] new_sync_read fs/read_write.c:389 [inline] vfs_read+0x5e0/0x630 fs/read_write.c:470 ksys_read+0x163/0x1a0 fs/read_write.c:613 __do_sys_read fs/read_write.c:623 [inline] __se_sys_read fs/read_write.c:621 [inline] __x64_sys_read+0x41/0x50 fs/read_write.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff88803c81f258 of 8 bytes by task 19183 on cpu 1: sock_recv_cmsgs include/net/sock.h:2721 [inline] packet_recvmsg+0xb64/0xd00 net/packet/af_packet.c:3489 sock_recvmsg_nosec net/socket.c:1019 [inline] sock_recvmsg+0x11a/0x130 net/socket.c:1040 sock_read_iter+0x176/0x220 net/socket.c:1118 call_read_iter include/linux/fs.h:1845 [inline] new_sync_read fs/read_write.c:389 [inline] vfs_read+0x5e0/0x630 fs/read_write.c:470 ksys_read+0x163/0x1a0 fs/read_write.c:613 __do_sys_read fs/read_write.c:623 [inline] __se_sys_read fs/read_write.c:621 [inline] __x64_sys_read+0x41/0x50 fs/read_write.c:621 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0xffffffffc4653600 -> 0x0000000000000000 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 19183 Comm: syz-executor.5 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 6c7c98bad488 ("sock: avoid dirtying sk_stamp, if possible") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20230508175543.55756-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/sock.h b/include/net/sock.h index 8b7ed7167243..656ea89f60ff 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2718,7 +2718,7 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); - else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) + else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } -- GitLab From 582dbb2cc1a0a7427840f5b1e3c65608e511b061 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 8 May 2023 16:17:49 -0700 Subject: [PATCH 4685/5631] net: phy: bcm7xx: Correct read from expansion register Since the driver works in the "legacy" addressing mode, we need to write to the expansion register (0x17) with bits 11:8 set to 0xf to properly select the expansion register passed as argument. Fixes: f68d08c437f9 ("net: phy: bcm7xxx: Add EPHY entry for 72165") Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230508231749.1681169-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/bcm-phy-lib.h | 5 +++++ drivers/net/phy/bcm7xxx.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index 9902fb182099..729db441797a 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -40,6 +40,11 @@ static inline int bcm_phy_write_exp_sel(struct phy_device *phydev, return bcm_phy_write_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER, val); } +static inline int bcm_phy_read_exp_sel(struct phy_device *phydev, u16 reg) +{ + return bcm_phy_read_exp(phydev, reg | MII_BCM54XX_EXP_SEL_ER); +} + int bcm54xx_auxctl_write(struct phy_device *phydev, u16 regnum, u16 val); int bcm54xx_auxctl_read(struct phy_device *phydev, u16 regnum); diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 06be71ecd2f8..f8c17a253f8b 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -486,7 +486,7 @@ static int bcm7xxx_16nm_ephy_afe_config(struct phy_device *phydev) bcm_phy_write_misc(phydev, 0x0038, 0x0002, 0xede0); /* Read CORE_EXPA9 */ - tmp = bcm_phy_read_exp(phydev, 0x00a9); + tmp = bcm_phy_read_exp_sel(phydev, 0x00a9); /* CORE_EXPA9[6:1] is rcalcode[5:0] */ rcalcode = (tmp & 0x7e) / 2; /* Correct RCAL code + 1 is -1% rprogr, LP: +16 */ -- GitLab From 3d776e31c841ba2f69895d2255a49320bec7cea6 Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 9 May 2023 10:59:58 +0200 Subject: [PATCH 4686/5631] xfrm: Reject optional tunnel/BEET mode templates in outbound policies xfrm_state_find() uses `encap_family` of the current template with the passed local and remote addresses to find a matching state. If an optional tunnel or BEET mode template is skipped in a mixed-family scenario, there could be a mismatch causing an out-of-bounds read as the addresses were not replaced to match the family of the next template. While there are theoretical use cases for optional templates in outbound policies, the only practical one is to skip IPComp states in inbound policies if uncompressed packets are received that are handled by an implicitly created IPIP state instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index af8fbcbfbe69..6794b9dea27a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1768,7 +1768,7 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, } static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { u16 prev_family; int i; @@ -1794,6 +1794,10 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, switch (ut[i].mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: + if (ut[i].optional && dir == XFRM_POLICY_OUT) { + NL_SET_ERR_MSG(extack, "Mode in optional template not allowed in outbound policy"); + return -EINVAL; + } break; default: if (ut[i].family != prev_family) { @@ -1831,7 +1835,7 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family, } static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, - struct netlink_ext_ack *extack) + int dir, struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_TMPL]; @@ -1842,7 +1846,7 @@ static int copy_from_user_tmpl(struct xfrm_policy *pol, struct nlattr **attrs, int nr = nla_len(rt) / sizeof(*utmpl); int err; - err = validate_tmpl(nr, utmpl, pol->family, extack); + err = validate_tmpl(nr, utmpl, pol->family, dir, extack); if (err) return err; @@ -1919,7 +1923,7 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, if (err) goto error; - if (!(err = copy_from_user_tmpl(xp, attrs, extack))) + if (!(err = copy_from_user_tmpl(xp, attrs, p->dir, extack))) err = copy_from_user_sec_ctx(xp, attrs); if (err) goto error; @@ -3498,7 +3502,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, return NULL; nr = ((len - sizeof(*p)) / sizeof(*ut)); - if (validate_tmpl(nr, ut, p->sel.family, NULL)) + if (validate_tmpl(nr, ut, p->sel.family, p->dir, NULL)) return NULL; if (p->dir > XFRM_POLICY_OUT) -- GitLab From cf3128a7aca55b2eefb68281d44749c683bdc96f Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 9 May 2023 11:00:06 +0200 Subject: [PATCH 4687/5631] af_key: Reject optional tunnel/BEET mode templates in outbound policies xfrm_state_find() uses `encap_family` of the current template with the passed local and remote addresses to find a matching state. If an optional tunnel or BEET mode template is skipped in a mixed-family scenario, there could be a mismatch causing an out-of-bounds read as the addresses were not replaced to match the family of the next template. While there are theoretical use cases for optional templates in outbound policies, the only practical one is to skip IPComp states in inbound policies if uncompressed packets are received that are handled by an implicitly created IPIP state instead. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/key/af_key.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index a815f5ab4c49..31ab12fd720a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1940,7 +1940,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1958,9 +1959,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2002,7 +2006,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); -- GitLab From 8680407b6f8f5fba59e8f1d63c869abc280f04df Mon Sep 17 00:00:00 2001 From: Benedict Wong Date: Wed, 10 May 2023 01:14:14 +0000 Subject: [PATCH 4688/5631] xfrm: Check if_id in inbound policy/secpath match This change ensures that if configured in the policy, the if_id set in the policy and secpath states match during the inbound policy check. Without this, there is potential for ambiguity where entries in the secpath differing by only the if_id could be mismatched. Notably, this is checked in the outbound direction when resolving templates to SAs, but not on the inbound path when matching SAs and policies. Test: Tested against Android kernel unit tests & CTS Signed-off-by: Benedict Wong Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 21a3a1cd3d6d..6d15788b5123 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3312,7 +3312,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -3323,7 +3323,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -3335,7 +3336,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -3345,7 +3346,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -3724,7 +3725,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ -- GitLab From dc1c9fd4a8bbe1e06add9053010b652449bfe411 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 4 May 2023 14:20:21 +0200 Subject: [PATCH 4689/5631] netfilter: nf_tables: always release netdev hooks from notifier This reverts "netfilter: nf_tables: skip netdev events generated on netns removal". The problem is that when a veth device is released, the veth release callback will also queue the peer netns device for removal. Its possible that the peer netns is also slated for removal. In this case, the device memory is already released before the pre_exit hook of the peer netns runs: BUG: KASAN: slab-use-after-free in nf_hook_entry_head+0x1b8/0x1d0 Read of size 8 at addr ffff88812c0124f0 by task kworker/u8:1/45 Workqueue: netns cleanup_net Call Trace: nf_hook_entry_head+0x1b8/0x1d0 __nf_unregister_net_hook+0x76/0x510 nft_netdev_unregister_hooks+0xa0/0x220 __nft_release_hook+0x184/0x490 nf_tables_pre_exit_net+0x12f/0x1b0 .. Order is: 1. First netns is released, veth_dellink() queues peer netns device for removal 2. peer netns is queued for removal 3. peer netns device is released, unreg event is triggered 4. unreg event is ignored because netns is going down 5. pre_exit hook calls nft_netdev_unregister_hooks but device memory might be free'd already. Fixes: 68a3765c659f ("netfilter: nf_tables: skip netdev events generated on netns removal") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_chain_filter.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index c3563f0be269..680fe557686e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -344,6 +344,12 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; } + /* UNREGISTER events are also happening on netns exit. + * + * Although nf_tables core releases all tables/chains, only this event + * handler provides guarantee that hook->ops.dev is still accessible, + * so we cannot skip exiting net namespaces. + */ __nft_release_basechain(ctx); } @@ -362,9 +368,6 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - if (!check_net(ctx.net)) - return NOTIFY_DONE; - nft_net = nft_pernet(ctx.net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { -- GitLab From e72eeab542dbf4f544e389e64fa13b82a1b6d003 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 4 May 2023 14:55:02 +0200 Subject: [PATCH 4690/5631] netfilter: conntrack: fix possible bug_on with enable_hooks=1 I received a bug report (no reproducer so far) where we trip over 712 rcu_read_lock(); 713 ct_hook = rcu_dereference(nf_ct_hook); 714 BUG_ON(ct_hook == NULL); // here In nf_conntrack_destroy(). First turn this BUG_ON into a WARN. I think it was triggered via enable_hooks=1 flag. When this flag is turned on, the conntrack hooks are registered before nf_ct_hook pointer gets assigned. This opens a short window where packets enter the conntrack machinery, can have skb->_nfct set up and a subsequent kfree_skb might occur before nf_ct_hook is set. Call nf_conntrack_init_end() to set nf_ct_hook before we register the pernet ops. Fixes: ba3fbe663635 ("netfilter: nf_conntrack: provide modparam to always register conntrack hooks") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/core.c | 6 ++++-- net/netfilter/nf_conntrack_standalone.c | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/net/netfilter/core.c b/net/netfilter/core.c index f0783e42108b..5f76ae86a656 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -711,9 +711,11 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct) rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); - BUG_ON(ct_hook == NULL); - ct_hook->destroy(nfct); + if (ct_hook) + ct_hook->destroy(nfct); rcu_read_unlock(); + + WARN_ON(!ct_hook); } EXPORT_SYMBOL(nf_conntrack_destroy); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 57f6724c99a7..169e16fc2bce 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -1218,11 +1218,12 @@ static int __init nf_conntrack_standalone_init(void) nf_conntrack_htable_size_user = nf_conntrack_htable_size; #endif + nf_conntrack_init_end(); + ret = register_pernet_subsys(&nf_conntrack_net_ops); if (ret < 0) goto out_pernet; - nf_conntrack_init_end(); return 0; out_pernet: -- GitLab From 0a11073e8e3362d715255d28d294aa7350c1c01f Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 4 May 2023 11:48:11 +0300 Subject: [PATCH 4691/5631] selftests: nft_flowtable.sh: use /proc for pid checking Some ps commands (e.g. busybox derived) have no -p option. Use /proc for pid existence check. Signed-off-by: Boris Sukholitko Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_flowtable.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 7060bae04ec8..4d8bc51b7a7b 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -288,11 +288,11 @@ test_tcp_forwarding_ip() sleep 3 - if ps -p $lpid > /dev/null;then + if test -d /proc/"$lpid"/; then kill $lpid fi - if ps -p $cpid > /dev/null;then + if test -d /proc/"$cpid"/; then kill $cpid fi -- GitLab From 0749d670d758099970c52ef70f4bbcfa5a15b3d3 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 4 May 2023 11:48:12 +0300 Subject: [PATCH 4692/5631] selftests: nft_flowtable.sh: no need for ps -x option Some ps commands (e.g. busybox derived) have no -x option. For the purposes of hash calculation of the list of processes this option is inessential. Signed-off-by: Boris Sukholitko Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_flowtable.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 4d8bc51b7a7b..3cf20e9bd3a6 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -489,8 +489,8 @@ ip -net $nsr1 addr add 10.0.1.1/24 dev veth0 ip -net $nsr1 addr add dead:1::1/64 dev veth0 ip -net $nsr1 link set up dev veth0 -KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1) -KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1) +KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1) +KEY_AES="0x"$(ps -af | md5sum | cut -d " " -f 1) SPI1=$RANDOM SPI2=$RANDOM -- GitLab From 1114803c2da974526ecbc0bd81e6c637bf257de5 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 4 May 2023 11:48:13 +0300 Subject: [PATCH 4693/5631] selftests: nft_flowtable.sh: wait for specific nc pids Doing wait with no parameters may interfere with some of the tests having their own background processes. Although no such test is currently present, the cleanup is useful to rely on the nft_flowtable.sh for local development (e.g. running background tcpdump command during the tests). Signed-off-by: Boris Sukholitko Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_flowtable.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 3cf20e9bd3a6..92bc308bf168 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -296,7 +296,8 @@ test_tcp_forwarding_ip() kill $cpid fi - wait + wait $lpid + wait $cpid if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then lret=1 -- GitLab From 90ab51226d52ad61e5ff175b572e08046b1b0a99 Mon Sep 17 00:00:00 2001 From: Boris Sukholitko Date: Thu, 4 May 2023 11:48:14 +0300 Subject: [PATCH 4694/5631] selftests: nft_flowtable.sh: monitor result file sizes When running nft_flowtable.sh in VM on a busy server we've found that the time of the netcat file transfers vary wildly. Therefore replace hardcoded 3 second sleep with the loop checking for a change in the file sizes. Once no change in detected we test the results. Nice side effect is that we shave 1 second sleep in the fast case (hard-coded 3 second sleep vs two 1 second sleeps). Acked-by: Florian Westphal Signed-off-by: Boris Sukholitko Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_flowtable.sh | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 92bc308bf168..51f986f19fee 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -286,7 +286,15 @@ test_tcp_forwarding_ip() ip netns exec $nsa nc -w 4 "$dstip" "$dstport" < "$nsin" > "$ns1out" & cpid=$! - sleep 3 + sleep 1 + + prev="$(ls -l $ns1out $ns2out)" + sleep 1 + + while [[ "$prev" != "$(ls -l $ns1out $ns2out)" ]]; do + sleep 1; + prev="$(ls -l $ns1out $ns2out)" + done if test -d /proc/"$lpid"/; then kill $lpid -- GitLab From 3acf8f6c14d0e42b889738d63b6d9cb63348fc94 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 9 May 2023 16:47:24 +0200 Subject: [PATCH 4695/5631] selftests: nft_flowtable.sh: check ingress/egress chain too Make sure flowtable interacts correctly with ingress and egress chains, i.e. those get handled before and after flow table respectively. Adds three more tests: 1. repeat flowtable test, but with 'ip dscp set cs3' done in inet forward chain. Expect that some packets have been mangled (before flowtable offload became effective) while some pass without mangling (after offload succeeds). 2. repeat flowtable test, but with 'ip dscp set cs3' done in veth0:ingress. Expect that all packets pass with cs3 dscp field. 3. same as 2, but use veth1:egress. Expect the same outcome. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../selftests/netfilter/nft_flowtable.sh | 124 ++++++++++++++++++ 1 file changed, 124 insertions(+) diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 51f986f19fee..a32f490f7539 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -188,6 +188,26 @@ if [ $? -ne 0 ]; then exit $ksft_skip fi +ip netns exec $ns2 nft -f - < /dev/null; then echo "ERROR: $ns1 cannot reach ns2" 1>&2 @@ -255,6 +275,60 @@ check_counters() fi } +check_dscp() +{ + local what=$1 + local ok=1 + + local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp3 | grep packets) + + local pc4=${counter%*bytes*} + local pc4=${pc4#*packets} + + local counter=$(ip netns exec $ns2 nft reset counter inet filter ip4dscp0 | grep packets) + local pc4z=${counter%*bytes*} + local pc4z=${pc4z#*packets} + + case "$what" in + "dscp_none") + if [ $pc4 -gt 0 ] || [ $pc4z -eq 0 ]; then + echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 + ret=1 + ok=0 + fi + ;; + "dscp_fwd") + if [ $pc4 -eq 0 ] || [ $pc4z -eq 0 ]; then + echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 + ret=1 + ok=0 + fi + ;; + "dscp_ingress") + if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then + echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + ret=1 + ok=0 + fi + ;; + "dscp_egress") + if [ $pc4 -eq 0 ] || [ $pc4z -gt 0 ]; then + echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + ret=1 + ok=0 + fi + ;; + *) + echo "FAIL: Unknown DSCP check" 1>&2 + ret=1 + ok=0 + esac + + if [ $ok -eq 1 ] ;then + echo "PASS: $what: dscp packet counters match" + fi +} + check_transfer() { in=$1 @@ -325,6 +399,51 @@ test_tcp_forwarding() return $? } +test_tcp_forwarding_set_dscp() +{ + check_dscp "dscp_none" + +ip netns exec $nsr1 nft -f - <&2 + exit 0 +fi + if ! test_tcp_forwarding_nat $ns1 $ns2 0 ""; then echo "FAIL: flow offload for ns1/ns2 with NAT" 1>&2 ip netns exec $nsr1 nft list ruleset -- GitLab From 7c83e28f10830aa5105c25eaabe890e3adac36aa Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Tue, 9 May 2023 03:20:06 +0200 Subject: [PATCH 4696/5631] net: ethernet: mtk_eth_soc: fix NULL pointer dereference Check for NULL pointer to avoid kernel crashing in case of missing WO firmware in case only a single WEDv2 device has been initialized, e.g. on MT7981 which can connect just one wireless frontend. Fixes: 86ce0d09e424 ("net: ethernet: mtk_eth_soc: use WO firmware for MT7981") Signed-off-by: Daniel Golle Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 4c205afbd230..985cff910f30 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -654,7 +654,7 @@ __mtk_wed_detach(struct mtk_wed_device *dev) BIT(hw->index), BIT(hw->index)); } - if (!hw_list[!hw->index]->wed_dev && + if ((!hw_list[!hw->index] || !hw_list[!hw->index]->wed_dev) && hw->eth->dma_dev != hw->eth->dev) mtk_eth_set_dma_device(hw->eth, hw->eth->dev); -- GitLab From 9949e2efb54eb3001cb2f6512ff3166dddbfb75d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 9 May 2023 11:11:57 +0800 Subject: [PATCH 4697/5631] bonding: fix send_peer_notif overflow Bonding send_peer_notif was defined as u8. Since commit 07a4ddec3ce9 ("bonding: add an option to specify a delay between peer notifications"). the bond->send_peer_notif will be num_peer_notif multiplied by peer_notif_delay, which is u8 * u32. This would cause the send_peer_notif overflow easily. e.g. ip link add bond0 type bond mode 1 miimon 100 num_grat_arp 30 peer_notify_delay 1000 To fix the overflow, let's set the send_peer_notif to u32 and limit peer_notif_delay to 300s. Reported-by: Liang Li Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2090053 Fixes: 07a4ddec3ce9 ("bonding: add an option to specify a delay between peer notifications") Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- drivers/net/bonding/bond_netlink.c | 7 ++++++- drivers/net/bonding/bond_options.c | 8 +++++++- include/net/bonding.h | 2 +- 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index c2d080fc4fc4..27cbe148f0db 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -84,6 +84,11 @@ static int bond_fill_slave_info(struct sk_buff *skb, return -EMSGSIZE; } +/* Limit the max delay range to 300s */ +static struct netlink_range_validation delay_range = { + .max = 300000, +}; + static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, @@ -114,7 +119,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, - [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, + [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, }; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 0498fc6731f8..f3f27f0bd2a6 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -169,6 +169,12 @@ static const struct bond_opt_value bond_num_peer_notif_tbl[] = { { NULL, -1, 0} }; +static const struct bond_opt_value bond_peer_notif_delay_tbl[] = { + { "off", 0, 0}, + { "maxval", 300000, BOND_VALFLAG_MAX}, + { NULL, -1, 0} +}; + static const struct bond_opt_value bond_primary_reselect_tbl[] = { { "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT}, { "better", BOND_PRI_RESELECT_BETTER, 0}, @@ -488,7 +494,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .id = BOND_OPT_PEER_NOTIF_DELAY, .name = "peer_notif_delay", .desc = "Delay between each peer notification on failover event, in milliseconds", - .values = bond_intmax_tbl, + .values = bond_peer_notif_delay_tbl, .set = bond_option_peer_notif_delay_set } }; diff --git a/include/net/bonding.h b/include/net/bonding.h index a60a24923b55..0efef2a952b7 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -233,7 +233,7 @@ struct bonding { */ spinlock_t mode_lock; spinlock_t stats_lock; - u8 send_peer_notif; + u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; -- GitLab From 84df83e0ecd3beba62c3d06b43ab51cc47efaca0 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 9 May 2023 11:11:58 +0800 Subject: [PATCH 4698/5631] Documentation: bonding: fix the doc of peer_notif_delay Bonding only supports setting peer_notif_delay with miimon set. Fixes: 0307d589c4d6 ("bonding: add documentation for peer_notif_delay") Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- Documentation/networking/bonding.rst | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index adc4bf4f3c50..28925e19622d 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -776,10 +776,11 @@ peer_notif_delay Specify the delay, in milliseconds, between each peer notification (gratuitous ARP and unsolicited IPv6 Neighbor Advertisement) when they are issued after a failover event. - This delay should be a multiple of the link monitor interval - (arp_interval or miimon, whichever is active). The default - value is 0 which means to match the value of the link monitor - interval. + This delay should be a multiple of the MII link monitor interval + (miimon). + + The valid range is 0 - 300000. The default value is 0, which means + to match the value of the MII link monitor interval. prio Slave priority. A higher number means higher priority. -- GitLab From b6d1599f8c282bfbc4d291af750436d93005b9ea Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 9 May 2023 11:11:59 +0800 Subject: [PATCH 4699/5631] selftests: forwarding: lib: add netns support for tc rule handle stats get When run the test in netns, it's not easy to get the tc stats via tc_rule_handle_stats_get(). With the new netns parameter, we can get stats from specific netns like num=$(tc_rule_handle_stats_get "dev eth0 ingress" 101 ".packets" "-n ns") Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- tools/testing/selftests/net/forwarding/lib.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 057c3d0ad620..9ddb68dd6a08 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -791,8 +791,9 @@ tc_rule_handle_stats_get() local id=$1; shift local handle=$1; shift local selector=${1:-.packets}; shift + local netns=${1:-""}; shift - tc -j -s filter show $id \ + tc $netns -j -s filter show $id \ | jq ".[] | select(.options.handle == $handle) | \ .options.actions[0].stats$selector" } -- GitLab From 6cbe791c0f4ed7310db212791e69c7ffedd4f4b6 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 9 May 2023 11:12:00 +0800 Subject: [PATCH 4700/5631] kselftest: bonding: add num_grat_arp test TEST: num_grat_arp (active-backup miimon num_grat_arp 10) [ OK ] TEST: num_grat_arp (active-backup miimon num_grat_arp 20) [ OK ] TEST: num_grat_arp (active-backup miimon num_grat_arp 30) [ OK ] TEST: num_grat_arp (active-backup miimon num_grat_arp 50) [ OK ] Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- .../drivers/net/bonding/bond_options.sh | 50 +++++++++++++++++++ .../drivers/net/bonding/bond_topo_3d1c.sh | 2 + 2 files changed, 52 insertions(+) diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index db29a3146a86..607ba5c38977 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -6,6 +6,7 @@ ALL_TESTS=" prio arp_validate + num_grat_arp " REQUIRE_MZ=no @@ -255,6 +256,55 @@ arp_validate() arp_validate_ns "active-backup" } +garp_test() +{ + local param="$1" + local active_slave exp_num real_num i + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "num_grat_arp" "$retmsg" + + + # Add tc rules to count GARP number + for i in $(seq 0 2); do + tc -n ${g_ns} filter add dev s$i ingress protocol arp pref 1 handle 101 \ + flower skip_hw arp_op request arp_sip ${s_ip4} arp_tip ${s_ip4} action pass + done + + # Do failover + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + ip -n ${s_ns} link set ${active_slave} down + + exp_num=$(echo "${param}" | cut -f6 -d ' ') + sleep $((exp_num + 2)) + + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + + # check result + real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}") + if [ "${real_num}" -ne "${exp_num}" ]; then + echo "$real_num garp packets sent on active slave ${active_slave}" + RET=1 + fi + + for i in $(seq 0 2); do + tc -n ${g_ns} filter del dev s$i ingress + done +} + +num_grat_arp() +{ + local val + for val in 10 20 30 50; do + garp_test "mode active-backup miimon 100 num_grat_arp $val peer_notify_delay 1000" + log_test "num_grat_arp" "active-backup miimon num_grat_arp $val" + done +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh index 4045ca97fb22..69ab99a56043 100644 --- a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -61,6 +61,8 @@ server_create() ip -n ${g_ns} link set s${i} up ip -n ${g_ns} link set s${i} master br0 ip -n ${s_ns} link set eth${i} master bond0 + + tc -n ${g_ns} qdisc add dev s${i} clsact done ip -n ${s_ns} link set bond0 up -- GitLab From a939d14919b799e6fff8a9c80296ca229ba2f8a4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 16:56:34 +0000 Subject: [PATCH 4701/5631] netlink: annotate accesses to nlk->cb_running Both netlink_recvmsg() and netlink_native_seq_show() read nlk->cb_running locklessly. Use READ_ONCE() there. Add corresponding WRITE_ONCE() to netlink_dump() and __netlink_dump_start() syzbot reported: BUG: KCSAN: data-race in __netlink_dump_start / netlink_recvmsg write to 0xffff88813ea4db59 of 1 bytes by task 28219 on cpu 0: __netlink_dump_start+0x3af/0x4d0 net/netlink/af_netlink.c:2399 netlink_dump_start include/linux/netlink.h:308 [inline] rtnetlink_rcv_msg+0x70f/0x8c0 net/core/rtnetlink.c:6130 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2577 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6192 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1942 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] sock_write_iter+0x1aa/0x230 net/socket.c:1138 call_write_iter include/linux/fs.h:1851 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x463/0x760 fs/read_write.c:584 ksys_write+0xeb/0x1a0 fs/read_write.c:637 __do_sys_write fs/read_write.c:649 [inline] __se_sys_write fs/read_write.c:646 [inline] __x64_sys_write+0x42/0x50 fs/read_write.c:646 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88813ea4db59 of 1 bytes by task 28222 on cpu 1: netlink_recvmsg+0x3b4/0x730 net/netlink/af_netlink.c:2022 sock_recvmsg_nosec+0x4c/0x80 net/socket.c:1017 ____sys_recvmsg+0x2db/0x310 net/socket.c:2718 ___sys_recvmsg net/socket.c:2762 [inline] do_recvmmsg+0x2e5/0x710 net/socket.c:2856 __sys_recvmmsg net/socket.c:2935 [inline] __do_sys_recvmmsg net/socket.c:2958 [inline] __se_sys_recvmmsg net/socket.c:2951 [inline] __x64_sys_recvmmsg+0xe2/0x160 net/socket.c:2951 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00 -> 0x01 Fixes: 16b304f3404f ("netlink: Eliminate kmalloc in netlink dump operation.") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7ef8b9a1e30c..c87804112d0c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1990,7 +1990,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (nlk->cb_running && + if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { @@ -2302,7 +2302,7 @@ static int netlink_dump(struct sock *sk) if (cb->done) cb->done(cb); - nlk->cb_running = false; + WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(nlk->cb_mutex); @@ -2365,7 +2365,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, goto error_put; } - nlk->cb_running = true; + WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); @@ -2703,7 +2703,7 @@ static int netlink_native_seq_show(struct seq_file *seq, void *v) nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), - nlk->cb_running, + READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) -- GitLab From e05a5f510f26607616fecdd4ac136310c8bea56b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 16:35:53 +0000 Subject: [PATCH 4702/5631] net: annotate sk->sk_err write from do_recvmmsg() do_recvmmsg() can write to sk->sk_err from multiple threads. As said before, many other points reading or writing sk_err need annotations. Fixes: 34b88a68f26a ("net: Fix use after free in the recvmmsg exit path") Signed-off-by: Eric Dumazet Reported-by: syzbot Reviewed-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/socket.c b/net/socket.c index a7b4b37d86df..b7e01d0fe082 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2911,7 +2911,7 @@ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ - sock->sk->sk_err = -err; + WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); -- GitLab From d0ac89f6f9879fae316c155de77b5173b3e2c9c9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 18:29:48 +0000 Subject: [PATCH 4703/5631] net: deal with most data-races in sk_wait_event() __condition is evaluated twice in sk_wait_event() macro. First invocation is lockless, and reads can race with writes, as spotted by syzbot. BUG: KCSAN: data-race in sk_stream_wait_connect / tcp_disconnect write to 0xffff88812d83d6a0 of 4 bytes by task 9065 on cpu 1: tcp_disconnect+0x2cd/0xdb0 inet_shutdown+0x19e/0x1f0 net/ipv4/af_inet.c:911 __sys_shutdown_sock net/socket.c:2343 [inline] __sys_shutdown net/socket.c:2355 [inline] __do_sys_shutdown net/socket.c:2363 [inline] __se_sys_shutdown+0xf8/0x140 net/socket.c:2361 __x64_sys_shutdown+0x31/0x40 net/socket.c:2361 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88812d83d6a0 of 4 bytes by task 9040 on cpu 0: sk_stream_wait_connect+0x1de/0x3a0 net/core/stream.c:75 tcp_sendmsg_locked+0x2e4/0x2120 net/ipv4/tcp.c:1266 tcp_sendmsg+0x30/0x50 net/ipv4/tcp.c:1484 inet6_sendmsg+0x63/0x80 net/ipv6/af_inet6.c:651 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] __sys_sendto+0x246/0x300 net/socket.c:2142 __do_sys_sendto net/socket.c:2154 [inline] __se_sys_sendto net/socket.c:2150 [inline] __x64_sys_sendto+0x78/0x90 net/socket.c:2150 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x00000000 -> 0x00000068 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/stream.c | 12 ++++++------ net/ipv4/tcp_bpf.c | 2 +- net/llc/af_llc.c | 8 +++++--- net/smc/smc_close.c | 4 ++-- net/smc/smc_rx.c | 4 ++-- net/smc/smc_tx.c | 4 ++-- net/tipc/socket.c | 4 ++-- net/tls/tls_main.c | 3 ++- 8 files changed, 22 insertions(+), 19 deletions(-) diff --git a/net/core/stream.c b/net/core/stream.c index 434446ab14c5..f5c4e47df165 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -73,8 +73,8 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, - !sk->sk_err && - !((1 << sk->sk_state) & + !READ_ONCE(sk->sk_err) && + !((1 << READ_ONCE(sk->sk_state)) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; @@ -87,9 +87,9 @@ EXPORT_SYMBOL(sk_stream_wait_connect); * sk_stream_closing - Return 1 if we still have things to send in our buffers. * @sk: socket to verify */ -static inline int sk_stream_closing(struct sock *sk) +static int sk_stream_closing(const struct sock *sk) { - return (1 << sk->sk_state) & + return (1 << READ_ONCE(sk->sk_state)) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK); } @@ -142,8 +142,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || (sk_stream_memory_free(sk) && !vm_wait), &wait); sk->sk_write_pending--; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ebf917511937..2e9547467edb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -168,7 +168,7 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); ret = sk_wait_event(sk, &timeo, !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); + !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index da7fe94bea2e..9ffbc667be6c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -583,7 +583,8 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) == TCP_CLOSE, &wait)) break; rc = -ERESTARTSYS; if (signal_pending(current)) @@ -603,7 +604,8 @@ static bool llc_ui_wait_for_conn(struct sock *sk, long timeout) add_wait_queue(sk_sleep(sk), &wait); while (1) { - if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT, &wait)) + if (sk_wait_event(sk, &timeout, + READ_ONCE(sk->sk_state) != TCP_SYN_SENT, &wait)) break; if (signal_pending(current) || !timeout) break; @@ -622,7 +624,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) while (1) { rc = 0; if (sk_wait_event(sk, &timeout, - (sk->sk_shutdown & RCV_SHUTDOWN) || + (READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN) || (!llc_data_accept_state(llc->state) && !llc->remote_busy_flag && !llc->p_flag), &wait)) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 31db7438857c..dbdf03e8aa5b 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -67,8 +67,8 @@ static void smc_close_stream_wait(struct smc_sock *smc, long timeout) rc = sk_wait_event(sk, &timeout, !smc_tx_prepared_sends(&smc->conn) || - sk->sk_err == ECONNABORTED || - sk->sk_err == ECONNRESET || + READ_ONCE(sk->sk_err) == ECONNABORTED || + READ_ONCE(sk->sk_err) == ECONNRESET || smc->conn.killed, &wait); if (rc) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 4380d32f5a5f..9a2f3638d161 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -267,9 +267,9 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); rc = sk_wait_event(sk, timeo, - sk->sk_err || + READ_ONCE(sk->sk_err) || cflags->peer_conn_abort || - sk->sk_shutdown & RCV_SHUTDOWN || + READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN || conn->killed || fcrit(conn), &wait); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f4b6a71ac488..45128443f1f1 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -113,8 +113,8 @@ static int smc_tx_wait(struct smc_sock *smc, int flags) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, - sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || + READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 37edfe10f8c6..dd73d71c02a9 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -314,9 +314,9 @@ static void tsk_rej_rx_queue(struct sock *sk, int error) tipc_sk_respond(sk, skb, error); } -static bool tipc_sk_connected(struct sock *sk) +static bool tipc_sk_connected(const struct sock *sk) { - return sk->sk_state == TIPC_ESTABLISHED; + return READ_ONCE(sk->sk_state) == TIPC_ESTABLISHED; } /* tipc_sk_type_connectionless - check if the socket is datagram socket diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b32c112984dd..f2e7302a4d96 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -111,7 +111,8 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + if (sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait)) break; } remove_wait_queue(sk_sleep(sk), &wait); -- GitLab From 43fb622d91a9f408322735d2f736495c1009f575 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 9 May 2023 12:50:04 +0100 Subject: [PATCH 4704/5631] net: pcs: xpcs: fix incorrect number of interfaces In synopsys_xpcs_compat[], the DW_XPCS_2500BASEX entry was setting the number of interfaces using the xpcs_2500basex_features array rather than xpcs_2500basex_interfaces. This causes us to overflow the array of interfaces. Fix this. Fixes: f27abde3042a ("net: pcs: add 2500BASEX support for Intel mGbE controller") Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Reviewed-by: Leon Romanovsky Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 539cd43eae8d..f19d48c94fe0 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -1203,7 +1203,7 @@ static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { [DW_XPCS_2500BASEX] = { .supported = xpcs_2500basex_features, .interface = xpcs_2500basex_interfaces, - .num_interfaces = ARRAY_SIZE(xpcs_2500basex_features), + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces), .an_mode = DW_2500BASEX, }, }; -- GitLab From 4063384ef762cc5946fc7a3f89879e76c6ec51e2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 13:18:57 +0000 Subject: [PATCH 4705/5631] net: add vlan_get_protocol_and_depth() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before blamed commit, pskb_may_pull() was used instead of skb_header_pointer() in __vlan_get_protocol() and friends. Few callers depended on skb->head being populated with MAC header, syzbot caught one of them (skb_mac_gso_segment()) Add vlan_get_protocol_and_depth() to make the intent clearer and use it where sensible. This is a more generic fix than commit e9d3f80935b6 ("net/af_packet: make sure to pull mac header") which was dealing with a similar issue. kernel BUG at include/linux/skbuff.h:2655 ! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 1441 Comm: syz-executor199 Not tainted 6.1.24-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:__skb_pull include/linux/skbuff.h:2655 [inline] RIP: 0010:skb_mac_gso_segment+0x68f/0x6a0 net/core/gro.c:136 Code: fd 48 8b 5c 24 10 44 89 6b 70 48 c7 c7 c0 ae 0d 86 44 89 e6 e8 a1 91 d0 00 48 c7 c7 00 af 0d 86 48 89 de 31 d2 e8 d1 4a e9 ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 RSP: 0018:ffffc90001bd7520 EFLAGS: 00010286 RAX: ffffffff8469736a RBX: ffff88810f31dac0 RCX: ffff888115a18b00 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffc90001bd75e8 R08: ffffffff84697183 R09: fffff5200037adf9 R10: 0000000000000000 R11: dffffc0000000001 R12: 0000000000000012 R13: 000000000000fee5 R14: 0000000000005865 R15: 000000000000fed7 FS: 000055555633f300(0000) GS:ffff8881f6a00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 0000000116fea000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [] __skb_gso_segment+0x32d/0x4c0 net/core/dev.c:3419 [] skb_gso_segment include/linux/netdevice.h:4819 [inline] [] validate_xmit_skb+0x3aa/0xee0 net/core/dev.c:3725 [] __dev_queue_xmit+0x1332/0x3300 net/core/dev.c:4313 [] dev_queue_xmit+0x17/0x20 include/linux/netdevice.h:3029 [] packet_snd net/packet/af_packet.c:3111 [inline] [] packet_sendmsg+0x49d2/0x6470 net/packet/af_packet.c:3142 [] sock_sendmsg_nosec net/socket.c:716 [inline] [] sock_sendmsg net/socket.c:736 [inline] [] __sys_sendto+0x472/0x5f0 net/socket.c:2139 [] __do_sys_sendto net/socket.c:2151 [inline] [] __se_sys_sendto net/socket.c:2147 [inline] [] __x64_sys_sendto+0xe5/0x100 net/socket.c:2147 [] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [] do_syscall_64+0x2f/0x50 arch/x86/entry/common.c:80 [] entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: 469aceddfa3e ("vlan: consolidate VLAN parsing code and limit max parsing depth") Reported-by: syzbot Signed-off-by: Eric Dumazet Cc: Toke Høiland-Jørgensen Cc: Willem de Bruijn Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/tap.c | 4 ++-- include/linux/if_vlan.h | 17 +++++++++++++++++ net/bridge/br_forward.c | 2 +- net/core/dev.c | 2 +- net/packet/af_packet.c | 6 ++---- 5 files changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index ce993cc75bf3..d30d730ed5a7 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -742,7 +742,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); /* copy skb_ubuf_info for callback when skb has no error */ @@ -1197,7 +1197,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) /* Move network header to the right position for VLAN tagged packets */ if (eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); rcu_read_lock(); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 0f40f379d75c..6ba71957851e 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -637,6 +637,23 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) return __vlan_get_protocol(skb, skb->protocol, NULL); } +/* This version of __vlan_get_protocol() also pulls mac header in skb->head */ +static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, + __be16 type, int *depth) +{ + int maclen; + + type = __vlan_get_protocol(skb, type, &maclen); + + if (type) { + if (!pskb_may_pull(skb, maclen)) + type = 0; + else if (depth) + *depth = maclen; + } + return type; +} + /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 57744704ff69..84d6dd5e5b1a 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -42,7 +42,7 @@ int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb eth_type_vlan(skb->protocol)) { int depth; - if (!__vlan_get_protocol(skb, skb->protocol, &depth)) + if (!vlan_get_protocol_and_depth(skb, skb->protocol, &depth)) goto drop; skb_set_network_header(skb, depth); diff --git a/net/core/dev.c b/net/core/dev.c index 735096d42c1d..b3c13e041935 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3335,7 +3335,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) type = eth->h_proto; } - return __vlan_get_protocol(skb, type, depth); + return vlan_get_protocol_and_depth(skb, type, depth); } /* openvswitch calls this on rx path, so we need a different check. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 640d94e34635..94c6a1ffa459 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1934,10 +1934,8 @@ static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && - __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { - if (pskb_may_pull(skb, depth)) - skb_set_network_header(skb, depth); - } + vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } -- GitLab From e14cadfd80d76f01bfaa1a8d745b1db19b57d6be Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 20:36:56 +0000 Subject: [PATCH 4706/5631] tcp: add annotations around sk->sk_shutdown accesses Now sk->sk_shutdown is no longer a bitfield, we can add standard READ_ONCE()/WRITE_ONCE() annotations to silence KCSAN reports like the following: BUG: KCSAN: data-race in tcp_disconnect / tcp_poll write to 0xffff88814588582c of 1 bytes by task 3404 on cpu 1: tcp_disconnect+0x4d6/0xdb0 net/ipv4/tcp.c:3121 __inet_stream_connect+0x5dd/0x6e0 net/ipv4/af_inet.c:715 inet_stream_connect+0x48/0x70 net/ipv4/af_inet.c:727 __sys_connect_file net/socket.c:2001 [inline] __sys_connect+0x19b/0x1b0 net/socket.c:2018 __do_sys_connect net/socket.c:2028 [inline] __se_sys_connect net/socket.c:2025 [inline] __x64_sys_connect+0x41/0x50 net/socket.c:2025 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd read to 0xffff88814588582c of 1 bytes by task 3374 on cpu 0: tcp_poll+0x2e6/0x7d0 net/ipv4/tcp.c:562 sock_poll+0x253/0x270 net/socket.c:1383 vfs_poll include/linux/poll.h:88 [inline] io_poll_check_events io_uring/poll.c:281 [inline] io_poll_task_func+0x15a/0x820 io_uring/poll.c:333 handle_tw_list io_uring/io_uring.c:1184 [inline] tctx_task_work+0x1fe/0x4d0 io_uring/io_uring.c:1246 task_work_run+0x123/0x160 kernel/task_work.c:179 get_signal+0xe64/0xff0 kernel/signal.c:2635 arch_do_signal_or_restart+0x89/0x2a0 arch/x86/kernel/signal.c:306 exit_to_user_mode_loop+0x6f/0xe0 kernel/entry/common.c:168 exit_to_user_mode_prepare+0x6c/0xb0 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x26/0x140 kernel/entry/common.c:297 do_syscall_64+0x4d/0xc0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd value changed: 0x03 -> 0x00 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- net/ipv4/tcp.c | 14 ++++++++------ net/ipv4/tcp_input.c | 4 ++-- 3 files changed, 11 insertions(+), 9 deletions(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 940062e08f57..c4aab3aacbd8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -894,7 +894,7 @@ int inet_shutdown(struct socket *sock, int how) EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: - sk->sk_shutdown |= how; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 20db115c38c4..4d6392c16b7a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -498,6 +498,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + u8 shutdown; int state; sock_poll_wait(file, sock, wait); @@ -540,9 +541,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ @@ -559,7 +561,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -2867,7 +2869,7 @@ void __tcp_close(struct sock *sk, long timeout) int data_was_unread = 0; int state; - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); @@ -3119,7 +3121,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet_bhash2_reset_saddr(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); @@ -4649,7 +4651,7 @@ void tcp_done(struct sock *sk) if (req) reqsk_fastopen_remove(sk, req, false); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a057330d6f59..61b6710f337a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4362,7 +4362,7 @@ void tcp_fin(struct sock *sk) inet_csk_schedule_ack(sk); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); sock_set_flag(sk, SOCK_DONE); switch (sk->sk_state) { @@ -6599,7 +6599,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) break; tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN); sk_dst_confirm(sk); -- GitLab From f4c2e67c1773d2a2632381ee30e9139c1e744c16 Mon Sep 17 00:00:00 2001 From: Ziwei Xiao Date: Tue, 9 May 2023 15:51:23 -0700 Subject: [PATCH 4707/5631] gve: Remove the code of clearing PBA bit Clearing the PBA bit from the driver is race prone and it may lead to dropped interrupt events. This could potentially lead to the traffic being completely halted. Fixes: 5e8c5adf95f8 ("gve: DQO: Add core netdev features") Signed-off-by: Ziwei Xiao Signed-off-by: Bailey Forrest Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/google/gve/gve_main.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 57ce74315eba..caa00c72aeeb 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -294,19 +294,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) bool reschedule = false; int work_done = 0; - /* Clear PCI MSI-X Pending Bit Array (PBA) - * - * This bit is set if an interrupt event occurs while the vector is - * masked. If this bit is set and we reenable the interrupt, it will - * fire again. Since we're just about to poll the queue state, we don't - * need it to fire again. - * - * Under high softirq load, it's possible that the interrupt condition - * is triggered twice before we got the chance to process it. - */ - gve_write_irq_doorbell_dqo(priv, block, - GVE_ITR_NO_UPDATE_DQO | GVE_ITR_CLEAR_PBA_BIT_DQO); - if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); -- GitLab From 77c964dad99a182a3df6add8bad73aca1be59890 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 9 May 2023 19:29:14 -0700 Subject: [PATCH 4708/5631] docs: networking: fix x25-iface.rst heading & index order Fix the chapter heading for "X.25 Device Driver Interface" so that it does not contain a trailing '-' character, which makes Sphinx omit this heading from the contents. Reverse the order of the x25.rst and x25-iface.rst files in the index so that the project introduction (x25.rst) comes first. Fixes: 883780af7209 ("docs: networking: convert x25-iface.txt to ReST") Signed-off-by: Randy Dunlap Cc: Mauro Carvalho Chehab Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Cc: Martin Schiller Cc: linux-x25@vger.kernel.org Reviewed-by: Bagas Sanjaya Signed-off-by: David S. Miller --- Documentation/networking/index.rst | 2 +- Documentation/networking/x25-iface.rst | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a164ff074356..5b75c3f7a137 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -116,8 +116,8 @@ Contents: udplite vrf vxlan - x25-iface x25 + x25-iface xfrm_device xfrm_proc xfrm_sync diff --git a/Documentation/networking/x25-iface.rst b/Documentation/networking/x25-iface.rst index f34e9ec64937..285cefcfce87 100644 --- a/Documentation/networking/x25-iface.rst +++ b/Documentation/networking/x25-iface.rst @@ -1,8 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 -============================- X.25 Device Driver Interface -============================- +============================ Version 1.1 -- GitLab From 90cbed5247439a966b645b34eb0a2e037836ea8e Mon Sep 17 00:00:00 2001 From: "t.feng" Date: Wed, 10 May 2023 11:50:44 +0800 Subject: [PATCH 4709/5631] ipvlan:Fix out-of-bounds caused by unclear skb->cb If skb enqueue the qdisc, fq_skb_cb(skb)->time_to_send is changed which is actually skb->cb, and IPCB(skb_in)->opt will be used in __ip_options_echo. It is possible that memcpy is out of bounds and lead to stack overflow. We should clear skb->cb before ip_local_out or ip6_local_out. v2: 1. clean the stack info 2. use IPCB/IP6CB instead of skb->cb crash on stable-5.10(reproduce in kasan kernel). Stack info: [ 2203.651571] BUG: KASAN: stack-out-of-bounds in __ip_options_echo+0x589/0x800 [ 2203.653327] Write of size 4 at addr ffff88811a388f27 by task swapper/3/0 [ 2203.655460] CPU: 3 PID: 0 Comm: swapper/3 Kdump: loaded Not tainted 5.10.0-60.18.0.50.h856.kasan.eulerosv2r11.x86_64 #1 [ 2203.655466] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.10.2-0-g5f4c7b1-20181220_000000-szxrtosci10000 04/01/2014 [ 2203.655475] Call Trace: [ 2203.655481] [ 2203.655501] dump_stack+0x9c/0xd3 [ 2203.655514] print_address_description.constprop.0+0x19/0x170 [ 2203.655530] __kasan_report.cold+0x6c/0x84 [ 2203.655586] kasan_report+0x3a/0x50 [ 2203.655594] check_memory_region+0xfd/0x1f0 [ 2203.655601] memcpy+0x39/0x60 [ 2203.655608] __ip_options_echo+0x589/0x800 [ 2203.655654] __icmp_send+0x59a/0x960 [ 2203.655755] nf_send_unreach+0x129/0x3d0 [nf_reject_ipv4] [ 2203.655763] reject_tg+0x77/0x1bf [ipt_REJECT] [ 2203.655772] ipt_do_table+0x691/0xa40 [ip_tables] [ 2203.655821] nf_hook_slow+0x69/0x100 [ 2203.655828] __ip_local_out+0x21e/0x2b0 [ 2203.655857] ip_local_out+0x28/0x90 [ 2203.655868] ipvlan_process_v4_outbound+0x21e/0x260 [ipvlan] [ 2203.655931] ipvlan_xmit_mode_l3+0x3bd/0x400 [ipvlan] [ 2203.655967] ipvlan_queue_xmit+0xb3/0x190 [ipvlan] [ 2203.655977] ipvlan_start_xmit+0x2e/0xb0 [ipvlan] [ 2203.655984] xmit_one.constprop.0+0xe1/0x280 [ 2203.655992] dev_hard_start_xmit+0x62/0x100 [ 2203.656000] sch_direct_xmit+0x215/0x640 [ 2203.656028] __qdisc_run+0x153/0x1f0 [ 2203.656069] __dev_queue_xmit+0x77f/0x1030 [ 2203.656173] ip_finish_output2+0x59b/0xc20 [ 2203.656244] __ip_finish_output.part.0+0x318/0x3d0 [ 2203.656312] ip_finish_output+0x168/0x190 [ 2203.656320] ip_output+0x12d/0x220 [ 2203.656357] __ip_queue_xmit+0x392/0x880 [ 2203.656380] __tcp_transmit_skb+0x1088/0x11c0 [ 2203.656436] __tcp_retransmit_skb+0x475/0xa30 [ 2203.656505] tcp_retransmit_skb+0x2d/0x190 [ 2203.656512] tcp_retransmit_timer+0x3af/0x9a0 [ 2203.656519] tcp_write_timer_handler+0x3ba/0x510 [ 2203.656529] tcp_write_timer+0x55/0x180 [ 2203.656542] call_timer_fn+0x3f/0x1d0 [ 2203.656555] expire_timers+0x160/0x200 [ 2203.656562] run_timer_softirq+0x1f4/0x480 [ 2203.656606] __do_softirq+0xfd/0x402 [ 2203.656613] asm_call_irq_on_stack+0x12/0x20 [ 2203.656617] [ 2203.656623] do_softirq_own_stack+0x37/0x50 [ 2203.656631] irq_exit_rcu+0x134/0x1a0 [ 2203.656639] sysvec_apic_timer_interrupt+0x36/0x80 [ 2203.656646] asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 2203.656654] RIP: 0010:default_idle+0x13/0x20 [ 2203.656663] Code: 89 f0 5d 41 5c 41 5d 41 5e c3 cc cc cc cc cc cc cc cc cc cc cc cc cc 0f 1f 44 00 00 0f 1f 44 00 00 0f 00 2d 9f 32 57 00 fb f4 cc cc cc cc 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 be 08 [ 2203.656668] RSP: 0018:ffff88810036fe78 EFLAGS: 00000256 [ 2203.656676] RAX: ffffffffaf2a87f0 RBX: ffff888100360000 RCX: ffffffffaf290191 [ 2203.656681] RDX: 0000000000098b5e RSI: 0000000000000004 RDI: ffff88811a3c4f60 [ 2203.656686] RBP: 0000000000000000 R08: 0000000000000001 R09: ffff88811a3c4f63 [ 2203.656690] R10: ffffed10234789ec R11: 0000000000000001 R12: 0000000000000003 [ 2203.656695] R13: ffff888100360000 R14: 0000000000000000 R15: 0000000000000000 [ 2203.656729] default_idle_call+0x5a/0x150 [ 2203.656735] cpuidle_idle_call+0x1c6/0x220 [ 2203.656780] do_idle+0xab/0x100 [ 2203.656786] cpu_startup_entry+0x19/0x20 [ 2203.656793] secondary_startup_64_no_verify+0xc2/0xcb [ 2203.657409] The buggy address belongs to the page: [ 2203.658648] page:0000000027a9842f refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11a388 [ 2203.658665] flags: 0x17ffffc0001000(reserved|node=0|zone=2|lastcpupid=0x1fffff) [ 2203.658675] raw: 0017ffffc0001000 ffffea000468e208 ffffea000468e208 0000000000000000 [ 2203.658682] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000 [ 2203.658686] page dumped because: kasan: bad access detected To reproduce(ipvlan with IPVLAN_MODE_L3): Env setting: ======================================================= modprobe ipvlan ipvlan_default_mode=1 sysctl net.ipv4.conf.eth0.forwarding=1 iptables -t nat -A POSTROUTING -s 20.0.0.0/255.255.255.0 -o eth0 -j MASQUERADE ip link add gw link eth0 type ipvlan ip -4 addr add 20.0.0.254/24 dev gw ip netns add net1 ip link add ipv1 link eth0 type ipvlan ip link set ipv1 netns net1 ip netns exec net1 ip link set ipv1 up ip netns exec net1 ip -4 addr add 20.0.0.4/24 dev ipv1 ip netns exec net1 route add default gw 20.0.0.254 ip netns exec net1 tc qdisc add dev ipv1 root netem loss 10% ifconfig gw up iptables -t filter -A OUTPUT -p tcp --dport 8888 -j REJECT --reject-with icmp-port-unreachable ======================================================= And then excute the shell(curl any address of eth0 can reach): for((i=1;i<=100000;i++)) do ip netns exec net1 curl x.x.x.x:8888 done ======================================================= Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.") Signed-off-by: "t.feng" Suggested-by: Florian Westphal Reviewed-by: Paolo Abeni Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 460b3d4f2245..ab5133eb1d51 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -436,6 +436,9 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, &rt->dst); + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + err = ip_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; @@ -474,6 +477,9 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, dst); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + err = ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(err))) dev->stats.tx_errors++; -- GitLab From 2b951b0efbaa6c805854b60c11f08811054d50cd Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 8 May 2023 13:40:19 +0100 Subject: [PATCH 4710/5631] ARM: 9297/1: vfp: avoid unbalanced stack on 'success' return path Commit c76c6c4ecbec0deb5 ("ARM: 9294/2: vfp: Fix broken softirq handling with instrumentation enabled") updated the VFP exception entry logic to go via a C function, so that we get the compiler's version of local_bh_disable(), which may be instrumented, and isn't generally callable from assembler. However, this assumes that passing an alternative 'success' return address works in C as it does in asm, and this is only the case if the C calls in question are tail calls, as otherwise, the stack will need some unwinding as well. I have already sent patches to the list that replace most of the asm logic with C code, and so it is preferable to have a minimal fix that addresses the issue and can be backported along with the commit that it fixes to v6.3 from v6.4. Hopefully, we can land the C conversion for v6.5. So instead of passing the 'success' return address as a function argument, pass the stack address from where to pop it so that both LR and SP have the expected value. Fixes: c76c6c4ecbec0deb5 ("ARM: 9294/2: vfp: Fix broken softirq handling with ...") Reported-by: syzbot+d4b00edc2d0c910d4bf4@syzkaller.appspotmail.com Tested-by: syzbot+d4b00edc2d0c910d4bf4@syzkaller.appspotmail.com Reviewed-by: Linus Walleij Tested-by: Andrew Lunn Signed-off-by: Ard Biesheuvel Tested-by: Andre Przywara Signed-off-by: Russell King (Oracle) --- arch/arm/vfp/entry.S | 7 +++++-- arch/arm/vfp/vfphw.S | 6 ++++-- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S index 7483ef8bccda..62206ef25037 100644 --- a/arch/arm/vfp/entry.S +++ b/arch/arm/vfp/entry.S @@ -23,6 +23,9 @@ @ ENTRY(do_vfp) mov r1, r10 - mov r3, r9 - b vfp_entry + str lr, [sp, #-8]! + add r3, sp, #4 + str r9, [r3] + bl vfp_entry + ldr pc, [sp], #8 ENDPROC(do_vfp) diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S index 4d8478264d82..a4610d0f3215 100644 --- a/arch/arm/vfp/vfphw.S +++ b/arch/arm/vfp/vfphw.S @@ -172,13 +172,14 @@ vfp_hw_state_valid: @ out before setting an FPEXC that @ stops us reading stuff VFPFMXR FPEXC, r1 @ Restore FPEXC last + mov sp, r3 @ we think we have handled things + pop {lr} sub r2, r2, #4 @ Retry current instruction - if Thumb str r2, [sp, #S_PC] @ mode it's two 16-bit instructions, @ else it's one 32-bit instruction, so @ always subtract 4 from the following @ instruction address. - mov lr, r3 @ we think we have handled things local_bh_enable_and_ret: adr r0, . mov r1, #SOFTIRQ_DISABLE_OFFSET @@ -209,8 +210,9 @@ skip: process_exception: DBGSTR "bounce" + mov sp, r3 @ setup for a return to the user code. + pop {lr} mov r2, sp @ nothing stacked - regdump is at TOS - mov lr, r3 @ setup for a return to the user code. @ Now call the C code to package up the bounce to the support code @ r0 holds the trigger instruction -- GitLab From cdc2e28e214fe9315cdd7e069c1c8e2428f93427 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Tue, 9 May 2023 21:48:51 -0700 Subject: [PATCH 4711/5631] net: mscc: ocelot: fix stat counter register values Commit d4c367650704 ("net: mscc: ocelot: keep ocelot_stat_layout by reg address, not offset") organized the stats counters for Ocelot chips, namely the VSC7512 and VSC7514. A few of the counter offsets were incorrect, and were caught by this warning: WARNING: CPU: 0 PID: 24 at drivers/net/ethernet/mscc/ocelot_stats.c:909 ocelot_stats_init+0x1fc/0x2d8 reg 0x5000078 had address 0x220 but reg 0x5000079 has address 0x214, bulking broken! Fix these register offsets. Fixes: d4c367650704 ("net: mscc: ocelot: keep ocelot_stat_layout by reg address, not offset") Signed-off-by: Colin Foster Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/vsc7514_regs.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c index ef6fd3f6be30..5595bfe84bbb 100644 --- a/drivers/net/ethernet/mscc/vsc7514_regs.c +++ b/drivers/net/ethernet/mscc/vsc7514_regs.c @@ -307,15 +307,15 @@ static const u32 vsc7514_sys_regmap[] = { REG(SYS_COUNT_DROP_YELLOW_PRIO_4, 0x000218), REG(SYS_COUNT_DROP_YELLOW_PRIO_5, 0x00021c), REG(SYS_COUNT_DROP_YELLOW_PRIO_6, 0x000220), - REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000214), - REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000218), - REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00021c), - REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000220), - REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000224), - REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000228), - REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00022c), - REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000230), - REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000234), + REG(SYS_COUNT_DROP_YELLOW_PRIO_7, 0x000224), + REG(SYS_COUNT_DROP_GREEN_PRIO_0, 0x000228), + REG(SYS_COUNT_DROP_GREEN_PRIO_1, 0x00022c), + REG(SYS_COUNT_DROP_GREEN_PRIO_2, 0x000230), + REG(SYS_COUNT_DROP_GREEN_PRIO_3, 0x000234), + REG(SYS_COUNT_DROP_GREEN_PRIO_4, 0x000238), + REG(SYS_COUNT_DROP_GREEN_PRIO_5, 0x00023c), + REG(SYS_COUNT_DROP_GREEN_PRIO_6, 0x000240), + REG(SYS_COUNT_DROP_GREEN_PRIO_7, 0x000244), REG(SYS_RESET_CFG, 0x000508), REG(SYS_CMID, 0x00050c), REG(SYS_VLAN_ETYPE_CFG, 0x000510), -- GitLab From f84353c7c20536ea7e01eca79430eccdf3cc7348 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Mon, 8 May 2023 22:14:20 +0000 Subject: [PATCH 4712/5631] btrfs: zoned: zone finish data relocation BG with last IO For data block groups, we zone finish a zone (or, just deactivate it) when seeing the last IO in btrfs_finish_ordered_io(). That is only called for IOs using ZONE_APPEND, but we use a regular WRITE command for data relocation IOs. Detect it and call btrfs_zone_finish_endio() properly. Fixes: be1a1d7a5d24 ("btrfs: zoned: finish fully written block group") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 57d070025c7a..19c707bc8801 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3108,6 +3108,9 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) btrfs_rewrite_logical_zoned(ordered_extent); btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, ordered_extent->disk_num_bytes); + } else if (btrfs_is_data_reloc_root(inode->root)) { + btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr, + ordered_extent->disk_num_bytes); } if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) { -- GitLab From 02ca9e6fb5f66a031df4fac508b8e477ca69e918 Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Tue, 9 May 2023 18:29:15 +0000 Subject: [PATCH 4713/5631] btrfs: zoned: fix full zone super block reading on ZNS When both of the superblock zones are full, we need to check which superblock is newer. The calculation of last superblock position is wrong as it does not consider zone_capacity and uses the length. Fixes: 9658b72ef300 ("btrfs: zoned: locate superblock position using zone capacity") CC: stable@vger.kernel.org # 6.1+ Reviewed-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index d51057608fc3..4243b0427a30 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -122,10 +122,9 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, int i; for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) { - u64 bytenr; - - bytenr = ((zones[i].start + zones[i].len) - << SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE; + u64 zone_end = (zones[i].start + zones[i].capacity) << SECTOR_SHIFT; + u64 bytenr = ALIGN_DOWN(zone_end, BTRFS_SUPER_INFO_SIZE) - + BTRFS_SUPER_INFO_SIZE; page[i] = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); -- GitLab From c83b56d1dd87cf67492bb770c26d6f87aee70ed6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 May 2023 07:58:37 -0700 Subject: [PATCH 4714/5631] btrfs: zero the buffer before marking it dirty in btrfs_redirty_list_add btrfs_redirty_list_add zeroes the buffer data and sets the EXTENT_BUFFER_NO_CHECK to make sure writeback is fine with a bogus header. But it does that after already marking the buffer dirty, which means that writeback could already be looking at the buffer. Switch the order of operations around so that the buffer is only marked dirty when we're ready to write it. Fixes: d3575156f662 ("btrfs: zoned: redirty released extent buffers") CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Christoph Hellwig Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 4243b0427a30..39828af4a4e8 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1609,11 +1609,11 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans, !list_empty(&eb->release_list)) return; + memzero_extent_buffer(eb, 0, eb->len); + set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); set_extent_buffer_dirty(eb); set_extent_bits_nowait(&trans->dirty_pages, eb->start, eb->start + eb->len - 1, EXTENT_DIRTY); - memzero_extent_buffer(eb, 0, eb->len); - set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags); spin_lock(&trans->releasing_ebs_lock); list_add_tail(&eb->release_list, &trans->releasing_ebs); -- GitLab From 1d6a4fc85717677e00fefffd847a50fc5928ce69 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 28 Apr 2023 14:13:05 +0800 Subject: [PATCH 4715/5631] btrfs: make clear_cache mount option to rebuild FST without disabling it Previously clear_cache mount option would simply disable free-space-tree feature temporarily then re-enable it to rebuild the whole free space tree. But this is problematic for block-group-tree feature, as we have an artificial dependency on free-space-tree feature. If we go the existing method, after clearing the free-space-tree feature, we would flip the filesystem to read-only mode, as we detect a super block write with block-group-tree but no free-space-tree feature. This patch would change the behavior by properly rebuilding the free space tree without disabling this feature, thus allowing clear_cache mount option to work with block group tree. Now we can mount a filesystem with block-group-tree feature and clear_mount option: $ mkfs.btrfs -O block-group-tree /dev/test/scratch1 -f $ sudo mount /dev/test/scratch1 /mnt/btrfs -o clear_cache $ sudo dmesg -t | head -n 5 BTRFS info (device dm-1): force clearing of disk cache BTRFS info (device dm-1): using free space tree BTRFS info (device dm-1): auto enabling async discard BTRFS info (device dm-1): rebuilding free space tree BTRFS info (device dm-1): checking UUID tree CC: stable@vger.kernel.org # 6.1+ Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 25 +++++++++++++------ fs/btrfs/free-space-tree.c | 50 +++++++++++++++++++++++++++++++++++++- fs/btrfs/free-space-tree.h | 3 ++- fs/btrfs/super.c | 3 +-- 4 files changed, 70 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59ea049fe7ee..fbf9006c6234 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3121,23 +3121,34 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) { int ret; const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE); - bool clear_free_space_tree = false; + bool rebuild_free_space_tree = false; if (btrfs_test_opt(fs_info, CLEAR_CACHE) && btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - clear_free_space_tree = true; + rebuild_free_space_tree = true; } else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) { btrfs_warn(fs_info, "free space tree is invalid"); - clear_free_space_tree = true; + rebuild_free_space_tree = true; } - if (clear_free_space_tree) { - btrfs_info(fs_info, "clearing free space tree"); - ret = btrfs_clear_free_space_tree(fs_info); + if (rebuild_free_space_tree) { + btrfs_info(fs_info, "rebuilding free space tree"); + ret = btrfs_rebuild_free_space_tree(fs_info); if (ret) { btrfs_warn(fs_info, - "failed to clear free space tree: %d", ret); + "failed to rebuild free space tree: %d", ret); + goto out; + } + } + + if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) && + !btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { + btrfs_info(fs_info, "disabling free space tree"); + ret = btrfs_delete_free_space_tree(fs_info); + if (ret) { + btrfs_warn(fs_info, + "failed to disable free space tree: %d", ret); goto out; } } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 4d155a48ec59..b21da1446f2a 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1252,7 +1252,7 @@ static int clear_free_space_tree(struct btrfs_trans_handle *trans, return ret; } -int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) +int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; @@ -1298,6 +1298,54 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) return ret; } +int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) +{ + struct btrfs_trans_handle *trans; + struct btrfs_key key = { + .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, + .type = BTRFS_ROOT_ITEM_KEY, + .offset = 0, + }; + struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); + struct rb_node *node; + int ret; + + trans = btrfs_start_transaction(free_space_root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + + ret = clear_free_space_tree(trans, free_space_root); + if (ret) + goto abort; + + node = rb_first_cached(&fs_info->block_group_cache_tree); + while (node) { + struct btrfs_block_group *block_group; + + block_group = rb_entry(node, struct btrfs_block_group, + cache_node); + ret = populate_free_space_tree(trans, block_group); + if (ret) + goto abort; + node = rb_next(node); + } + + btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); + btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); + clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); + + ret = btrfs_commit_transaction(trans); + clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); + return ret; +abort: + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; +} + static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h index dc2463e4cfe3..6d5551d0ced8 100644 --- a/fs/btrfs/free-space-tree.h +++ b/fs/btrfs/free-space-tree.h @@ -18,7 +18,8 @@ struct btrfs_caching_control; void set_free_space_tree_thresholds(struct btrfs_block_group *block_group); int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info); -int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info); +int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info); +int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info); int load_free_space_tree(struct btrfs_caching_control *caching_ctl); int add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0f2f915e42b0..ec18e2210602 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -828,8 +828,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, ret = -EINVAL; } if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) && - (btrfs_test_opt(info, CLEAR_CACHE) || - !btrfs_test_opt(info, FREE_SPACE_TREE))) { + !btrfs_test_opt(info, FREE_SPACE_TREE)) { btrfs_err(info, "cannot disable free space tree with block-group-tree feature"); ret = -EINVAL; } -- GitLab From 2da5bffe9eaa5819a868e8eaaa11b3fd0f16a691 Mon Sep 17 00:00:00 2001 From: Vitaly Prosyak Date: Wed, 10 May 2023 09:51:11 -0400 Subject: [PATCH 4716/5631] drm/sched: Check scheduler work queue before calling timeout handling During an IGT GPU reset test we see again oops despite of commit 0c8c901aaaebc9 (drm/sched: Check scheduler ready before calling timeout handling). It uses ready condition whether to call drm_sched_fault which unwind the TDR leads to GPU reset. However it looks the ready condition is overloaded with other meanings, for example, for the following stack is related GPU reset : 0 gfx_v9_0_cp_gfx_start 1 gfx_v9_0_cp_gfx_resume 2 gfx_v9_0_cp_resume 3 gfx_v9_0_hw_init 4 gfx_v9_0_resume 5 amdgpu_device_ip_resume_phase2 does the following: /* start the ring */ gfx_v9_0_cp_gfx_start(adev); ring->sched.ready = true; The same approach is for other ASICs as well : gfx_v8_0_cp_gfx_resume gfx_v10_0_kiq_resume, etc... As a result, our GPU reset test causes GPU fault which calls unconditionally gfx_v9_0_fault and then drm_sched_fault. However now it depends on whether the interrupt service routine drm_sched_fault is executed after gfx_v9_0_cp_gfx_start is completed which sets the ready field of the scheduler to true even for uninitialized schedulers and causes oops vs no fault or when ISR drm_sched_fault is completed prior gfx_v9_0_cp_gfx_start and NULL pointer dereference does not occur. Use the field timeout_wq to prevent oops for uninitialized schedulers. The field could be initialized by the work queue of resetting the domain. v1: Corrections to commit message (Luben) Fixes: 11b3b9f461c5c4 ("drm/sched: Check scheduler ready before calling timeout handling") Signed-off-by: Vitaly Prosyak Link: https://lore.kernel.org/r/20230510135111.58631-1-vitaly.prosyak@amd.com Reviewed-by: Luben Tuikov Signed-off-by: Luben Tuikov --- drivers/gpu/drm/scheduler/sched_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 1e08cc5a1702..78c959eaef0c 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -308,7 +308,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) */ void drm_sched_fault(struct drm_gpu_scheduler *sched) { - if (sched->ready) + if (sched->timeout_wq) mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0); } EXPORT_SYMBOL(drm_sched_fault); -- GitLab From 504a10d9e46bc37b23d0a1ae2f28973c8516e636 Mon Sep 17 00:00:00 2001 From: Bob Peterson Date: Fri, 28 Apr 2023 12:07:46 -0400 Subject: [PATCH 4717/5631] gfs2: Don't deref jdesc in evict On corrupt gfs2 file systems the evict code can try to reference the journal descriptor structure, jdesc, after it has been freed and set to NULL. The sequence of events is: init_journal() ... fail_jindex: gfs2_jindex_free(sdp); <------frees journals, sets jdesc = NULL if (gfs2_holder_initialized(&ji_gh)) gfs2_glock_dq_uninit(&ji_gh); fail: iput(sdp->sd_jindex); <--references jdesc in evict_linked_inode evict() gfs2_evict_inode() evict_linked_inode() ret = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); <------references the now freed/zeroed sd_jdesc pointer. The call to gfs2_trans_begin is done because the truncate_inode_pages call can cause gfs2 events that require a transaction, such as removing journaled data (jdata) blocks from the journal. This patch fixes the problem by adding a check for sdp->sd_jdesc to function gfs2_evict_inode. In theory, this should only happen to corrupt gfs2 file systems, when gfs2 detects the problem, reports it, then tries to evict all the system inodes it has read in up to that point. Reported-by: Yang Lan Signed-off-by: Bob Peterson Signed-off-by: Andreas Gruenbacher --- fs/gfs2/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5eed8c237500..a84bf6444bba 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1419,6 +1419,14 @@ static void gfs2_evict_inode(struct inode *inode) if (inode->i_nlink || sb_rdonly(sb) || !ip->i_no_addr) goto out; + /* + * In case of an incomplete mount, gfs2_evict_inode() may be called for + * system files without having an active journal to write to. In that + * case, skip the filesystem evict. + */ + if (!sdp->sd_jdesc) + goto out; + gfs2_holder_mark_uninitialized(&gh); ret = evict_should_delete(inode, &gh); if (ret == SHOULD_DEFER_EVICTION) -- GitLab From 2a939c8695035b11e00239610d88551be34c7a61 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:08 -0700 Subject: [PATCH 4718/5631] perf metric: Change divide by zero and !support events behavior Division by zero causes expression parsing to fail and no metric to be generated. This can mean for short running benchmarks metrics are not shown. Change the behavior to make the value nan, which gets shown like: ''' $ perf stat -M TopdownL2 true Performance counter stats for 'true': 1,031,492 INST_RETIRED.ANY # nan % tma_fetch_bandwidth # nan % tma_heavy_operations # nan % tma_light_operations 29,304 CPU_CLK_UNHALTED.REF_XCLK # nan % tma_fetch_latency # nan % tma_branch_mispredicts # nan % tma_machine_clears # nan % tma_core_bound # nan % tma_memory_bound 2,658,319 IDQ_UOPS_NOT_DELIVERED.CORE 11,167 EXE_ACTIVITY.BOUND_ON_STORES 262,058 EXE_ACTIVITY.1_PORTS_UTIL BR_MISP_RETIRED.ALL_BRANCHES (0.00%) INT_MISC.RECOVERY_CYCLES_ANY (0.00%) CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE (0.00%) CPU_CLK_UNHALTED.THREAD (0.00%) UOPS_RETIRED.RETIRE_SLOTS (0.00%) CYCLE_ACTIVITY.STALLS_MEM_ANY (0.00%) UOPS_RETIRED.MACRO_FUSED (0.00%) IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE (0.00%) EXE_ACTIVITY.2_PORTS_UTIL (0.00%) CYCLE_ACTIVITY.STALLS_TOTAL (0.00%) MACHINE_CLEARS.COUNT (0.00%) UOPS_ISSUED.ANY (0.00%) 0.002864879 seconds time elapsed 0.003012000 seconds user 0.000000000 seconds sys ''' When events aren't supported a count of 0 can be confusing and make metrics look meaningful. Change these to be nan also which, with the next change, gets shown like: ''' $ perf stat true Performance counter stats for 'true': 1.25 msec task-clock:u # 0.387 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 46 page-faults:u # 36.702 K/sec 255,942 cycles:u # 0.204 GHz (88.66%) 123,046 instructions:u # 0.48 insn per cycle 28,301 branches:u # 22.580 M/sec 2,489 branch-misses:u # 8.79% of all branches 4,719 CPU_CLK_UNHALTED.REF_XCLK:u # 3.765 M/sec # nan % tma_frontend_bound # nan % tma_retiring # nan % tma_backend_bound # nan % tma_bad_speculation 344,855 IDQ_UOPS_NOT_DELIVERED.CORE:u # 275.147 M/sec INT_MISC.RECOVERY_CYCLES_ANY:u CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u (0.00%) CPU_CLK_UNHALTED.THREAD:u (0.00%) UOPS_RETIRED.RETIRE_SLOTS:u (0.00%) UOPS_ISSUED.ANY:u (0.00%) 0.003238142 seconds time elapsed 0.000000000 seconds user 0.003434000 seconds sys ''' Ensure that nan metric values are quoted as nan isn't a valid number in JSON. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/expr.c | 3 ++- tools/perf/tests/parse-metric.c | 1 + tools/perf/util/expr.y | 6 +++++- tools/perf/util/stat-display.c | 2 +- tools/perf/util/stat-shadow.c | 25 +++++++++++++++++++------ 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index cbf0e0c74906..733ead151c63 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -120,7 +120,8 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u p = "FOO/0"; ret = expr__parse(&val, ctx, p); - TEST_ASSERT_VAL("division by zero", ret == -1); + TEST_ASSERT_VAL("division by zero", ret == 0); + TEST_ASSERT_VAL("division by zero", isnan(val)); p = "BAR/"; ret = expr__parse(&val, ctx, p); diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 1185b79e6274..c05148ea400c 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -38,6 +38,7 @@ static void load_runtime_stat(struct evlist *evlist, struct value *vals) evlist__alloc_aggr_stats(evlist, 1); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); + evsel->supported = true; evsel->stats->aggr->counts.val = count; if (evsel__name_is(evsel, "duration_time")) update_stats(&walltime_nsecs_stats, count); diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 250e444bf032..4ce931cccb63 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -225,7 +225,11 @@ expr: NUMBER { if (fpclassify($3.val) == FP_ZERO) { pr_debug("division by zero\n"); - YYABORT; + assert($3.ids == NULL); + if (compute_ids) + ids__free($1.ids); + $$.val = NAN; + $$.ids = NULL; } else if (!compute_ids || (is_const($1.val) && is_const($3.val))) { assert($1.ids == NULL); assert($3.ids == NULL); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 73b2ff2ddf29..bf5a6c14dfcd 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -431,7 +431,7 @@ static void print_metric_json(struct perf_stat_config *config __maybe_unused, struct outstate *os = ctx; FILE *out = os->fh; - fprintf(out, "\"metric-value\" : %f, ", val); + fprintf(out, "\"metric-value\" : \"%f\", ", val); fprintf(out, "\"metric-unit\" : \"%s\"", unit); if (!config->metric_only) fprintf(out, "}"); diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c index eeccab6751d7..1566a206ba42 100644 --- a/tools/perf/util/stat-shadow.c +++ b/tools/perf/util/stat-shadow.c @@ -403,12 +403,25 @@ static int prepare_metric(struct evsel **metric_events, if (!aggr) break; - /* - * If an event was scaled during stat gathering, reverse - * the scale before computing the metric. - */ - val = aggr->counts.val * (1.0 / metric_events[i]->scale); - source_count = evsel__source_count(metric_events[i]); + if (!metric_events[i]->supported) { + /* + * Not supported events will have a count of 0, + * which can be confusing in a + * metric. Explicitly set the value to NAN. Not + * counted events (enable time of 0) are read as + * 0. + */ + val = NAN; + source_count = 0; + } else { + /* + * If an event was scaled during stat gathering, + * reverse the scale before computing the + * metric. + */ + val = aggr->counts.val * (1.0 / metric_events[i]->scale); + source_count = evsel__source_count(metric_events[i]); + } } n = strdup(evsel__metric_id(metric_events[i])); if (!n) -- GitLab From 1b114824106ca4686276c94e414e06bf58b0934f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:09 -0700 Subject: [PATCH 4719/5631] perf stat: Introduce skippable evsels 'perf stat' with no arguments will use default events and metrics. These events may fail to open even with kernel and hypervisor disabled. When these fail then the permissions error appears even though they were implicitly selected. This is particularly a problem with the automatic selection of the TopdownL1 metric group on certain architectures like Skylake: $ perf stat true Error: Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open access to performance monitoring and observability operations for processes without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability. More information can be found at 'Perf events and tool security' document: https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html perf_event_paranoid setting is 2: -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK >= 0: Disallow raw and ftrace function tracepoint access >= 1: Disallow CPU event access >= 2: Disallow kernel profiling To make the adjusted perf_event_paranoid setting permanent preserve it in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = ) $ This patch adds skippable evsels that when they fail to open won't cause termination and will appear as "" in output. The TopdownL1 events, from the metric group, are marked as skippable. This turns the failure above to: $ perf stat perf bench internals synthesize Computing performance of single threaded perf event synthesis by synthesizing events on the perf process itself: Average synthesis took: 49.287 usec (+- 0.083 usec) Average num. events: 3.000 (+- 0.000) Average time per event 16.429 usec Average data synthesis took: 49.641 usec (+- 0.085 usec) Average num. events: 11.000 (+- 0.000) Average time per event 4.513 usec Performance counter stats for 'perf bench internals synthesize': 1,222.38 msec task-clock:u # 0.993 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 162 page-faults:u # 132.529 /sec 774,445,184 cycles:u # 0.634 GHz (49.61%) 1,640,969,811 instructions:u # 2.12 insn per cycle (59.67%) 302,052,148 branches:u # 247.102 M/sec (59.69%) 1,807,718 branch-misses:u # 0.60% of all branches (59.68%) 5,218,927 CPU_CLK_UNHALTED.REF_XCLK:u # 4.269 M/sec # 17.3 % tma_frontend_bound # 56.4 % tma_retiring # nan % tma_backend_bound # nan % tma_bad_speculation (60.01%) 536,580,469 IDQ_UOPS_NOT_DELIVERED.CORE:u # 438.965 M/sec (60.33%) INT_MISC.RECOVERY_CYCLES_ANY:u 5,223,936 CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u # 4.274 M/sec (40.31%) 774,127,250 CPU_CLK_UNHALTED.THREAD:u # 633.297 M/sec (50.34%) 1,746,579,518 UOPS_RETIRED.RETIRE_SLOTS:u # 1.429 G/sec (50.12%) 1,940,625,702 UOPS_ISSUED.ANY:u # 1.588 G/sec (49.70%) 1.231055525 seconds time elapsed 0.258327000 seconds user 0.965749000 seconds sys $ The event INT_MISC.RECOVERY_CYCLES_ANY:u is skipped as it can't be opened with paranoia 2 on Skylake. With a lower paranoia, or as root, all events/metrics are computed. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 38 +++++++++++++++++++++++++++++--------- tools/perf/util/evsel.c | 15 +++++++++++++-- tools/perf/util/evsel.h | 1 + 3 files changed, 43 insertions(+), 11 deletions(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index cc9fa48d636f..b9ad32f21e57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -667,6 +667,13 @@ static enum counter_recovery stat_handle_error(struct evsel *counter) evsel_list->core.threads->err_thread = -1; return COUNTER_RETRY; } + } else if (counter->skippable) { + if (verbose > 0) + ui__warning("skipping event %s that kernel failed to open .\n", + evsel__name(counter)); + counter->supported = false; + counter->errored = true; + return COUNTER_SKIP; } evsel__open_strerror(counter, &target, errno, msg, sizeof(msg)); @@ -1890,15 +1897,28 @@ static int add_default_attributes(void) * caused by exposing latent bugs. This is fixed properly in: * https://lore.kernel.org/lkml/bff481ba-e60a-763f-0aa0-3ee53302c480@linux.intel.com/ */ - if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid() && - metricgroup__parse_groups(evsel_list, "TopdownL1", - /*metric_no_group=*/false, - /*metric_no_merge=*/false, - /*metric_no_threshold=*/true, - stat_config.user_requested_cpu_list, - stat_config.system_wide, - &stat_config.metric_events) < 0) - return -1; + if (metricgroup__has_metric("TopdownL1") && !perf_pmu__has_hybrid()) { + struct evlist *metric_evlist = evlist__new(); + struct evsel *metric_evsel; + + if (!metric_evlist) + return -1; + + if (metricgroup__parse_groups(metric_evlist, "TopdownL1", + /*metric_no_group=*/false, + /*metric_no_merge=*/false, + /*metric_no_threshold=*/true, + stat_config.user_requested_cpu_list, + stat_config.system_wide, + &stat_config.metric_events) < 0) + return -1; + + evlist__for_each_entry(metric_evlist, metric_evsel) { + metric_evsel->skippable = true; + } + evlist__splice_list_tail(evsel_list, &metric_evlist->core.entries); + evlist__delete(metric_evlist); + } /* Platform specific attrs */ if (evlist__add_default_attrs(evsel_list, default_null_attrs) < 0) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 356c07f03be6..1cd04b5998d2 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -290,6 +290,7 @@ void evsel__init(struct evsel *evsel, evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; + evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) @@ -1725,9 +1726,13 @@ static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) return -1; fd = FD(leader, cpu_map_idx, thread); - BUG_ON(fd == -1); + BUG_ON(fd == -1 && !leader->skippable); - return fd; + /* + * When the leader has been skipped, return -2 to distinguish from no + * group leader case. + */ + return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) @@ -2109,6 +2114,12 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, group_fd = get_group_fd(evsel, idx, thread); + if (group_fd == -2) { + pr_debug("broken group leader for %s\n", evsel->name); + err = -EINVAL; + goto out_close; + } + test_attr__ready(); /* Debug message used by test scripts */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d575390d80bc..df8928745fc6 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -95,6 +95,7 @@ struct evsel { bool weak_group; bool bpf_counter; bool use_config_name; + bool skippable; int bpf_fd; struct bpf_object *bpf_obj; struct list_head config_terms; -- GitLab From ccc66c6092802d682537227136dcbd0527027e6f Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:10 -0700 Subject: [PATCH 4720/5631] perf metric: JSON flag to not group events if gathering a metric group Some metric groups have metrics that don't have fully overlapping events, meaning that the group's events become unique event groups that may need to multiplex with each other. This can be particularly unfortunate when the groups wouldn't need to multiplex because there are sufficient hardware counters. Add a flag so that if recording a metric group then the metrics within the group needn't use groups for their events. The flag is added to Intel TopdownL1 and TopdownL2 metrics. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/alderlake/adl-metrics.json | 26 +++++++++++++++++++ .../arch/x86/alderlaken/adln-metrics.json | 14 ++++++++++ .../arch/x86/broadwell/bdw-metrics.json | 12 +++++++++ .../arch/x86/broadwellde/bdwde-metrics.json | 12 +++++++++ .../arch/x86/broadwellx/bdx-metrics.json | 12 +++++++++ .../arch/x86/cascadelakex/clx-metrics.json | 12 +++++++++ .../arch/x86/haswell/hsw-metrics.json | 12 +++++++++ .../arch/x86/haswellx/hsx-metrics.json | 12 +++++++++ .../arch/x86/icelake/icl-metrics.json | 12 +++++++++ .../arch/x86/icelakex/icx-metrics.json | 12 +++++++++ .../arch/x86/ivybridge/ivb-metrics.json | 12 +++++++++ .../arch/x86/ivytown/ivt-metrics.json | 12 +++++++++ .../arch/x86/jaketown/jkt-metrics.json | 12 +++++++++ .../arch/x86/sandybridge/snb-metrics.json | 12 +++++++++ .../arch/x86/sapphirerapids/spr-metrics.json | 12 +++++++++ .../arch/x86/skylake/skl-metrics.json | 12 +++++++++ .../arch/x86/skylakex/skx-metrics.json | 12 +++++++++ .../arch/x86/tigerlake/tgl-metrics.json | 12 +++++++++ tools/perf/pmu-events/jevents.py | 4 ++- tools/perf/pmu-events/pmu-events.h | 1 + tools/perf/util/metricgroup.c | 8 +++--- 21 files changed, 240 insertions(+), 5 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index 75d80e70e5cd..1f9047553942 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -133,6 +133,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -143,6 +144,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -153,6 +155,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -163,6 +166,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -182,6 +186,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -209,6 +214,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -255,6 +261,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -264,6 +271,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -291,6 +299,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -593,6 +602,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -611,6 +621,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -629,6 +640,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -729,6 +741,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%", "Unit": "cpu_atom" @@ -739,6 +752,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%", "Unit": "cpu_atom" }, @@ -848,6 +862,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -858,6 +873,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -868,6 +884,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -919,6 +936,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1031,6 +1049,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1041,6 +1060,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1121,6 +1141,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -1141,6 +1162,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2023,6 +2045,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2082,6 +2105,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2112,6 +2136,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%", "Unit": "cpu_core" @@ -2310,6 +2335,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 1a85d935c733..0402adbf7d92 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -98,6 +98,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. The rest of these subevents count backend stalls, in cycles, due to an outstanding request which is memory bound vs core bound. The subevents are not slot based events and therefore can not be precisely added or subtracted from the Backend_Bound_Aux subevents which are slot based.", "ScaleUnit": "100%" }, @@ -107,6 +108,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound_aux", "MetricThreshold": "tma_backend_bound_aux > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that UOPS must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count. All of these subevents count backend stalls, in slots, due to a resource limitation. These are not cycle based events and therefore can not be precisely added or subtracted from the Backend_Bound subevents which are cycle based. These subevents are supplementary to Backend_Bound and can be used to analyze results from a resource perspective at allocation.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the instruction queue (IQ). Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", "ScaleUnit": "100%" }, @@ -125,6 +128,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_base", "MetricThreshold": "tma_base > 0.6", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -142,6 +146,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -166,6 +171,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -207,6 +213,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -215,6 +222,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.15", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -239,6 +247,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { @@ -499,6 +508,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_bad_speculation_group", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.05", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -515,6 +525,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "ScaleUnit": "100%" }, { @@ -531,6 +542,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_ms_uops", "MetricThreshold": "tma_ms_uops > 0.05", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the number of uops that are from the complex flows issued by the micro-sequencer (MS). This includes uops from flows due to complex instructions, faults, assists, and inserted flows.", "ScaleUnit": "100%" }, @@ -620,6 +632,7 @@ "MetricGroup": "TopdownL2;tma_L2_group;tma_backend_bound_aux_group", "MetricName": "tma_resource_bound", "MetricThreshold": "tma_resource_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend due to backend stalls. Note that uops must be available for consumption in order for this event to count. If a uop is not available (IQ is empty), this event will not count.", "ScaleUnit": "100%" }, @@ -629,6 +642,7 @@ "MetricGroup": "TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.75", + "MetricgroupNoGroup": "TopdownL1", "ScaleUnit": "100%" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json index 51cf8560a8d3..f9e2316601e1 100644 --- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -828,6 +836,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -858,6 +867,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -886,6 +896,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1048,6 +1059,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index fb57c7382408..e9c46d336a8e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -97,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -106,6 +107,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -116,6 +118,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -164,6 +167,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -248,6 +252,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -257,6 +262,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -311,6 +317,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -320,6 +327,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -795,6 +803,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -825,6 +834,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -853,6 +863,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1013,6 +1024,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json index 65ec0c9e55d1..437b9867acb9 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -170,6 +173,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -263,6 +267,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -272,6 +277,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -326,6 +332,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -335,6 +342,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -829,6 +837,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -869,6 +878,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -897,6 +907,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1079,6 +1090,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index 8f7dc72accd0..875c766222e3 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1142,6 +1150,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1196,6 +1205,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1224,6 +1234,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1458,6 +1469,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json index 2528418200bb..9570a88d6d1c 100644 --- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -663,6 +671,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -693,6 +702,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -721,6 +731,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -874,6 +885,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json index 11f152c346eb..a522202cf684 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -272,6 +278,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -281,6 +288,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -664,6 +672,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -704,6 +713,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -732,6 +742,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -905,6 +916,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index f45ae3483df4..1a2154f28b7b 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -115,6 +115,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -124,6 +125,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -141,6 +143,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -187,6 +190,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -288,6 +292,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -297,6 +302,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -369,6 +375,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -378,6 +385,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1111,6 +1119,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1164,6 +1173,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1191,6 +1201,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1360,6 +1371,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 0f9b174dfc22..1ef772b40e04 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -80,6 +80,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -89,6 +90,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -106,6 +108,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -152,6 +155,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -253,6 +257,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -262,6 +267,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -334,6 +340,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -343,6 +350,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1134,6 +1142,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1187,6 +1196,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1214,6 +1224,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1410,6 +1421,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json index 5247f69c13b6..11080ccffd51 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -724,6 +732,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -754,6 +763,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -782,6 +792,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -917,6 +928,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json index 89469b10fa30..65a46d659c0a 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json @@ -103,6 +103,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -112,6 +113,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -122,6 +124,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -161,6 +164,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -254,6 +258,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -263,6 +268,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -299,6 +305,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -308,6 +315,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -725,6 +733,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -765,6 +774,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -793,6 +803,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -948,6 +959,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json index e8f4e5c01c9f..66a6f657bd6f 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -412,6 +420,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -422,6 +431,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -450,6 +460,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -487,6 +498,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json index 4a99fe515f4b..4b8bc19392a4 100644 --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json @@ -76,6 +76,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -85,6 +86,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -95,6 +97,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -114,6 +117,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -160,6 +164,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_lcp", "ScaleUnit": "100%" }, @@ -169,6 +174,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: RS_EVENTS.EMPTY_END", "ScaleUnit": "100%" }, @@ -205,6 +211,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.", "ScaleUnit": "100%" }, @@ -214,6 +221,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -411,6 +419,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -421,6 +430,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -449,6 +459,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -486,6 +497,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 126300b7ae77..620fc5bd2217 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -87,6 +87,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -96,6 +97,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -105,6 +107,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: TOPDOWN.BR_MISPREDICT_SLOTS. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -151,6 +154,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -252,6 +256,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 6 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -261,6 +266,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -351,6 +357,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -369,6 +376,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences. Sample with: UOPS_RETIRED.HEAVY", "ScaleUnit": "100%" }, @@ -1216,6 +1224,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1269,6 +1278,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1304,6 +1314,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1509,6 +1520,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index a6d212b349f5..21ef6c9be816 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -345,6 +351,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -363,6 +370,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1065,6 +1073,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1110,6 +1119,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1138,6 +1148,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1343,6 +1354,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa2f7f126a30..eb6f12c0343d 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -101,6 +101,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.", "ScaleUnit": "100%" }, @@ -110,6 +111,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -120,6 +122,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -167,6 +170,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -271,6 +275,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 4 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -280,6 +285,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -354,6 +360,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1123,6 +1131,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1177,6 +1186,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1429,6 +1440,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.RETIRE_SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index 4c80d6be6cf1..b442ed4acfbb 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -109,6 +109,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_backend_bound", "MetricThreshold": "tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. Sample with: TOPDOWN.BACKEND_BOUND_SLOTS", "ScaleUnit": "100%" }, @@ -118,6 +119,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_bad_speculation", "MetricThreshold": "tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.", "ScaleUnit": "100%" }, @@ -135,6 +137,7 @@ "MetricGroup": "BadSpec;BrMispredicts;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueBM", "MetricName": "tma_branch_mispredicts", "MetricThreshold": "tma_branch_mispredicts > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Branch Misprediction. These slots are either wasted by uops fetched from an incorrectly speculated program path; or stalls when the out-of-order part of the machine needs to recover its state from a speculative path. Sample with: BR_MISP_RETIRED.ALL_BRANCHES. Related metrics: tma_info_branch_misprediction_cost, tma_info_mispredictions, tma_mispredicts_resteers", "ScaleUnit": "100%" }, @@ -181,6 +184,7 @@ "MetricGroup": "Backend;Compute;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_core_bound", "MetricThreshold": "tma_core_bound > 0.1 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where Core non-memory issues were of a bottleneck. Shortage in hardware compute resources; or dependencies in software's instructions are both categorized under Core Bound. Hence it may indicate the machine ran out of an out-of-order resource; certain execution units are overloaded or dependencies in program's data- or instruction-flow are limiting the performance (e.g. FP-chained long-latency arithmetic operations).", "ScaleUnit": "100%" }, @@ -282,6 +286,7 @@ "MetricGroup": "FetchBW;Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group;tma_issueFB", "MetricName": "tma_fetch_bandwidth", "MetricThreshold": "tma_fetch_bandwidth > 0.1 & tma_frontend_bound > 0.15 & tma_info_ipc / 5 > 0.35", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend bandwidth issues. For example; inefficiencies at the instruction decoders; or restrictions for caching in the DSB (decoded uops cache) are categorized under Fetch Bandwidth. In such cases; the Frontend typically delivers suboptimal amount of uops to the Backend. Sample with: FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_1_PS;FRONTEND_RETIRED.LATENCY_GE_2_PS. Related metrics: tma_dsb_switches, tma_info_dsb_coverage, tma_info_dsb_misses, tma_info_iptb, tma_lcp", "ScaleUnit": "100%" }, @@ -291,6 +296,7 @@ "MetricGroup": "Frontend;TmaL2;TopdownL2;tma_L2_group;tma_frontend_bound_group", "MetricName": "tma_fetch_latency", "MetricThreshold": "tma_fetch_latency > 0.1 & tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU was stalled due to Frontend latency issues. For example; instruction-cache misses; iTLB misses or fetch stalls after a branch misprediction are categorized under Frontend Latency. In such cases; the Frontend eventually delivers no uops for some period. Sample with: FRONTEND_RETIRED.LATENCY_GE_16_PS;FRONTEND_RETIRED.LATENCY_GE_8_PS", "ScaleUnit": "100%" }, @@ -363,6 +369,7 @@ "MetricGroup": "PGO;TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_frontend_bound", "MetricThreshold": "tma_frontend_bound > 0.15", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-operations (uops). Ideally the Frontend can issue Pipeline_Width uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. Sample with: FRONTEND_RETIRED.LATENCY_GE_4_PS", "ScaleUnit": "100%" }, @@ -372,6 +379,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_heavy_operations", "MetricThreshold": "tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring heavy-weight operations -- instructions that require two or more uops or micro-coded sequences. This highly-correlates with the uop length of these instructions/sequences.", "ScaleUnit": "100%" }, @@ -1125,6 +1133,7 @@ "MetricGroup": "Retire;TmaL2;TopdownL2;tma_L2_group;tma_retiring_group", "MetricName": "tma_light_operations", "MetricThreshold": "tma_light_operations > 0.6", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots where the CPU was retiring light-weight operations -- instructions that require no more than one uop (micro-operation). This correlates with total number of instructions used by the program. A uops-per-instruction (see UopPI metric) ratio of 1 or less should be expected for decently optimized software running on Intel Core/Xeon products. While this often indicates efficient X86 instructions were executed; high value does not necessarily mean better performance cannot be achieved. Sample with: INST_RETIRED.PREC_DIST", "ScaleUnit": "100%" }, @@ -1178,6 +1187,7 @@ "MetricGroup": "BadSpec;MachineClears;TmaL2;TopdownL2;tma_L2_group;tma_bad_speculation_group;tma_issueMC;tma_issueSyncxn", "MetricName": "tma_machine_clears", "MetricThreshold": "tma_machine_clears > 0.1 & tma_bad_speculation > 0.15", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the CPU has wasted due to Machine Clears. These slots are either wasted by uops fetched prior to the clear; or stalls the out-of-order portion of the machine needs to recover its state after the clear. For example; this can happen due to memory ordering Nukes (e.g. Memory Disambiguation) or Self-Modifying-Code (SMC) nukes. Sample with: MACHINE_CLEARS.COUNT. Related metrics: tma_clears_resteers, tma_contested_accesses, tma_data_sharing, tma_false_sharing, tma_l1_bound, tma_microcode_sequencer, tma_ms_switches, tma_remote_cache", "ScaleUnit": "100%" }, @@ -1205,6 +1215,7 @@ "MetricGroup": "Backend;TmaL2;TopdownL2;tma_L2_group;tma_backend_bound_group", "MetricName": "tma_memory_bound", "MetricThreshold": "tma_memory_bound > 0.2 & tma_backend_bound > 0.2", + "MetricgroupNoGroup": "TopdownL2", "PublicDescription": "This metric represents fraction of slots the Memory subsystem within the Backend was a bottleneck. Memory Bound estimates fraction of slots where pipeline is likely stalled due to demand load or store instructions. This accounts mainly for (1) non-completed in-flight memory demand loads which coincides with execution units starvation; in addition to (2) cases where stores could impose backpressure on the pipeline when many of them get buffered at the same time (less common out of the two).", "ScaleUnit": "100%" }, @@ -1374,6 +1385,7 @@ "MetricGroup": "TmaL1;TopdownL1;tma_L1_group", "MetricName": "tma_retiring", "MetricThreshold": "tma_retiring > 0.7 | tma_heavy_operations > 0.1", + "MetricgroupNoGroup": "TopdownL1", "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category. Retiring of 100% would indicate the maximum Pipeline_Width throughput was achieved. Maximizing Retiring typically increases the Instructions-per-cycle (see IPC metric). Note that a high Retiring value does not necessary mean there is no room for more performance. For example; Heavy-operations or Microcode Assists are categorized under Retiring. They often indicate suboptimal performance and can often be optimized or avoided. Sample with: UOPS_RETIRED.SLOTS", "ScaleUnit": "100%" }, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index ca99b9cfe4ad..f57a8f274025 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -52,7 +52,8 @@ _json_event_attributes = [ # Attributes that are in pmu_metric rather than pmu_event. _json_metric_attributes = [ 'metric_name', 'metric_group', 'metric_expr', 'metric_threshold', 'desc', - 'long_desc', 'unit', 'compat', 'aggr_mode', 'event_grouping' + 'long_desc', 'unit', 'compat', 'metricgroup_no_group', 'aggr_mode', + 'event_grouping' ] # Attributes that are bools or enum int values, encoded as '0', '1',... _json_enum_attributes = ['aggr_mode', 'deprecated', 'event_grouping', 'perpkg'] @@ -303,6 +304,7 @@ class JsonEvent: self.deprecated = jd.get('Deprecated') self.metric_name = jd.get('MetricName') self.metric_group = jd.get('MetricGroup') + self.metricgroup_no_group = jd.get('MetricgroupNoGroup') self.event_grouping = convert_metric_constraint(jd.get('MetricConstraint')) self.metric_expr = None if 'MetricExpr' in jd: diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h index b7dff8f1021f..80349685cf4d 100644 --- a/tools/perf/pmu-events/pmu-events.h +++ b/tools/perf/pmu-events/pmu-events.h @@ -59,6 +59,7 @@ struct pmu_metric { const char *compat; const char *desc; const char *long_desc; + const char *metricgroup_no_group; enum aggr_mode_class aggr_mode; enum metric_event_groups event_grouping; }; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index c566c6859302..4e7d41d285b4 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1144,12 +1144,12 @@ static int metricgroup__add_metric_callback(const struct pmu_metric *pm, struct metricgroup__add_metric_data *data = vdata; int ret = 0; - if (pm->metric_expr && - (match_metric(pm->metric_group, data->metric_name) || - match_metric(pm->metric_name, data->metric_name))) { + if (pm->metric_expr && match_pm_metric(pm, data->metric_name)) { + bool metric_no_group = data->metric_no_group || + match_metric(data->metric_name, pm->metricgroup_no_group); data->has_match = true; - ret = add_metric(data->list, pm, data->modifier, data->metric_no_group, + ret = add_metric(data->list, pm, data->modifier, metric_no_group, data->metric_no_threshold, data->user_requested_cpu_list, data->system_wide, /*root_metric=*/NULL, /*visited_metrics=*/NULL, table); -- GitLab From 327daf34554d20a6aa190dce5a625a555055435e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:11 -0700 Subject: [PATCH 4721/5631] perf parse-events: Don't reorder ungrouped events by PMU The pmu_group_name by default returns "cpu" which on non-hybrid/ARM means that ungrouped software, and hardware events are all going to sort by the original insertion index. However, on hybrid and ARM wildcard expansion may mean the PMU name is set and events will be unnecessarily reordered - triggering the reordering warning. Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/parse-events.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d71019dcd614..34ba840ae19a 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -2140,25 +2140,32 @@ static int evlist__cmp(void *state, const struct list_head *l, const struct list int *leader_idx = state; int lhs_leader_idx = *leader_idx, rhs_leader_idx = *leader_idx, ret; const char *lhs_pmu_name, *rhs_pmu_name; + bool lhs_has_group = false, rhs_has_group = false; /* * First sort by grouping/leader. Read the leader idx only if the evsel * is part of a group, as -1 indicates no group. */ - if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) + if (lhs_core->leader != lhs_core || lhs_core->nr_members > 1) { + lhs_has_group = true; lhs_leader_idx = lhs_core->leader->idx; - if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) + } + if (rhs_core->leader != rhs_core || rhs_core->nr_members > 1) { + rhs_has_group = true; rhs_leader_idx = rhs_core->leader->idx; + } if (lhs_leader_idx != rhs_leader_idx) return lhs_leader_idx - rhs_leader_idx; - /* Group by PMU. Groups can't span PMUs. */ - lhs_pmu_name = evsel__group_pmu_name(lhs); - rhs_pmu_name = evsel__group_pmu_name(rhs); - ret = strcmp(lhs_pmu_name, rhs_pmu_name); - if (ret) - return ret; + /* Group by PMU if there is a group. Groups can't span PMUs. */ + if (lhs_has_group && rhs_has_group) { + lhs_pmu_name = evsel__group_pmu_name(lhs); + rhs_pmu_name = evsel__group_pmu_name(rhs); + ret = strcmp(lhs_pmu_name, rhs_pmu_name); + if (ret) + return ret; + } /* Architecture specific sorting. */ return arch_evlist__cmp(lhs, rhs); -- GitLab From 5f0b89e632ed81b69993f3e68ed924ca3874d0d0 Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Tue, 9 May 2023 15:18:47 +0200 Subject: [PATCH 4722/5631] perf test java symbol: Remove needless debuginfod queries Test case 'Test java symbol' might run for a long time. On Fedora 38 the run time is very, very long: Output before: # time ./perf test 108 108: Test java symbol : Ok real 22m15.775s user 3m42.584s sys 4m30.685s # The reason is a lookup for the server for debug symbols as shown in: # cat /etc/debuginfod/elfutils.urls https://debuginfod.fedoraproject.org/ # This lookup is done for every symbol/sample, so about 3500 lookups will take place. To omit this lookup, which is not needed, unset environment variable DEBUGINFOD_URLS=''. Output after: # time ./perf test 108 108: Test java symbol : Ok real 0m6.242s user 0m4.982s sys 0m3.243s # Signed-off-by: Thomas Richter Tested-by: Arnaldo Carvalho de Melo Cc: Heiko Carstens Cc: Ian Rogers Cc: Leo Yan Cc: Sumanth Korikkar Cc: Sven Schnelle Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20230509131847.835974-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_java_symbol.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/tests/shell/test_java_symbol.sh b/tools/perf/tests/shell/test_java_symbol.sh index 90cea8811926..499539d1c479 100755 --- a/tools/perf/tests/shell/test_java_symbol.sh +++ b/tools/perf/tests/shell/test_java_symbol.sh @@ -56,7 +56,7 @@ if [ $? -ne 0 ]; then exit 1 fi -if ! perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then +if ! DEBUGINFOD_URLS='' perf inject -i $PERF_DATA -o $PERF_INJ_DATA -j; then echo "Fail to inject samples" exit 1 fi -- GitLab From b0618f38e2ab8ce3f094e4973955cfdbb55fceea Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 May 2023 15:42:38 -0300 Subject: [PATCH 4723/5631] perf build: Gracefully fail the build if BUILD_BPF_SKEL=1 is specified and clang isn't available Build BPF skels require having a compiler able to generate BPF bytecode, and so far this is only possible with clang, so check for its availability and fail the build when the user explicitely ask for BPF skels to be built. Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Andrii Nakryiko , Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Song Liu Yang: Yang Jihong , Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.config | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 4884520f954f..70268442f7ee 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,6 +216,12 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif +ifeq ($(BUILD_BPF_SKEL),1) + ifeq ($(call get-executable,$(CLANG)),) + dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) + endif +endif + ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= -- GitLab From 5d1ac59ff7445e51a0e4958fa39ac8aa23691698 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:21:44 +0800 Subject: [PATCH 4724/5631] tools headers UAPI: Sync the linux/in.h with the kernel sources Picking the changes from: 91d0b78c5177f3e4 ("inet: Add IP_LOCAL_PORT_RANGE socket option") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/23aabc69956ac94fbf388b05c8be08a64e8c7ccc.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/in.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index 07a4cb149305..4b7f2df66b99 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -162,6 +162,7 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 #define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 -- GitLab From e6232180e524e11205d285bb27045bf2c19db265 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:21:46 +0800 Subject: [PATCH 4725/5631] tools headers UAPI: Sync the drm/drm.h with the kernel sources Picking the changes from: 6068771673a38efc ("drm: document DRM_IOCTL_PRIME_HANDLE_TO_FD and PRIME_FD_TO_HANDLE") 61a55f8b1ebcde68 ("drm: document expectations for GETFB2 handles") 158350aae16a4e66 ("drm: document DRM_IOCTL_GEM_CLOSE") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/drm.h' differs from latest version at 'include/uapi/drm/drm.h' diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h No changes in tooling as these are just C comment documentation changes. Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/7552c61660bf079f2979fdcbcef8e921255f877a.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 57 ++++++++++++++++++++++++++++++++++-- 1 file changed, 55 insertions(+), 2 deletions(-) diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 642808520d92..a87bbbbca2d4 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -972,6 +972,19 @@ extern "C" { #define DRM_IOCTL_GET_STATS DRM_IOR( 0x06, struct drm_stats) #define DRM_IOCTL_SET_VERSION DRM_IOWR(0x07, struct drm_set_version) #define DRM_IOCTL_MODESET_CTL DRM_IOW(0x08, struct drm_modeset_ctl) +/** + * DRM_IOCTL_GEM_CLOSE - Close a GEM handle. + * + * GEM handles are not reference-counted by the kernel. User-space is + * responsible for managing their lifetime. For example, if user-space imports + * the same memory object twice on the same DRM file description, the same GEM + * handle is returned by both imports, and user-space needs to ensure + * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen + * when a memory object is allocated, then exported and imported again on the + * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception + * and always returns fresh new GEM handles even if an existing GEM handle + * already refers to the same memory object before the IOCTL is performed. + */ #define DRM_IOCTL_GEM_CLOSE DRM_IOW (0x09, struct drm_gem_close) #define DRM_IOCTL_GEM_FLINK DRM_IOWR(0x0a, struct drm_gem_flink) #define DRM_IOCTL_GEM_OPEN DRM_IOWR(0x0b, struct drm_gem_open) @@ -1012,7 +1025,37 @@ extern "C" { #define DRM_IOCTL_UNLOCK DRM_IOW( 0x2b, struct drm_lock) #define DRM_IOCTL_FINISH DRM_IOW( 0x2c, struct drm_lock) +/** + * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD. + * + * User-space sets &drm_prime_handle.handle with the GEM handle to export and + * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in + * &drm_prime_handle.fd. + * + * The export can fail for any driver-specific reason, e.g. because export is + * not supported for this specific GEM handle (but might be for others). + * + * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT. + */ #define DRM_IOCTL_PRIME_HANDLE_TO_FD DRM_IOWR(0x2d, struct drm_prime_handle) +/** + * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle. + * + * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to + * import, and gets back a GEM handle in &drm_prime_handle.handle. + * &drm_prime_handle.flags is unused. + * + * If an existing GEM handle refers to the memory object backing the DMA-BUF, + * that GEM handle is returned. Therefore user-space which needs to handle + * arbitrary DMA-BUFs must have a user-space lookup data structure to manually + * reference-count duplicated GEM handles. For more information see + * &DRM_IOCTL_GEM_CLOSE. + * + * The import can fail for any driver-specific reason, e.g. because import is + * only supported for DMA-BUFs allocated on this DRM device. + * + * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT. + */ #define DRM_IOCTL_PRIME_FD_TO_HANDLE DRM_IOWR(0x2e, struct drm_prime_handle) #define DRM_IOCTL_AGP_ACQUIRE DRM_IO( 0x30) @@ -1104,8 +1147,13 @@ extern "C" { * struct as the output. * * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles - * will be filled with GEM buffer handles. Planes are valid until one has a - * zero handle -- this can be used to compute the number of planes. + * will be filled with GEM buffer handles. Fresh new GEM handles are always + * returned, even if another GEM handle referring to the same memory object + * already exists on the DRM file description. The caller is responsible for + * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same + * new handle will be returned for multiple planes in case they use the same + * memory object. Planes are valid until one has a zero handle -- this can be + * used to compute the number of planes. * * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid * until one has a zero &drm_mode_fb_cmd2.pitches. @@ -1113,6 +1161,11 @@ extern "C" { * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier. + * + * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space + * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately + * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not + * double-close handles which are specified multiple times in the array. */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) -- GitLab From e7ec3a249c38a9c9be3a1eeb0142fcbaa3bd02d9 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:22:49 +0800 Subject: [PATCH 4726/5631] tools headers UAPI: Sync the i915_drm.h with the kernel sources Picking the changes from: 1cc064dce4ed0ff1 ("drm/i915/perf: Add support for OA media units") c61d04c9eb435498 ("drm/i915/perf: Add engine class instance parameters to perf") 02abecdeebfcd384 ("drm/i915/uapi: Replace fake flex-array with flexible-array member") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/4c0c150997ae1455f49094222daa121385643ae0.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 8df261c5ab9b..dba7c5a5b25e 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -2491,7 +2491,7 @@ struct i915_context_param_engines { #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */ #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */ #define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */ - struct i915_engine_class_instance engines[0]; + struct i915_engine_class_instance engines[]; } __attribute__((packed)); #define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \ @@ -2676,6 +2676,10 @@ enum drm_i915_oa_format { I915_OAR_FORMAT_A32u40_A4u32_B8_C8, I915_OA_FORMAT_A24u40_A14u32_B8_C8, + /* MTL OAM */ + I915_OAM_FORMAT_MPEC8u64_B8_C8, + I915_OAM_FORMAT_MPEC8u32_B8_C8, + I915_OA_FORMAT_MAX /* non-ABI */ }; @@ -2758,6 +2762,25 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_POLL_OA_PERIOD, + /** + * Multiple engines may be mapped to the same OA unit. The OA unit is + * identified by class:instance of any engine mapped to it. + * + * This parameter specifies the engine class and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_CLASS, + + /** + * This parameter specifies the engine instance and must be passed along + * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS. + * + * This property is available in perf revision 6. + */ + DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; -- GitLab From 92b8e61e8835109140139bc1eb60329429c32a0f Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:22:51 +0800 Subject: [PATCH 4727/5631] tools headers UAPI: Sync the linux/const.h with the kernel headers Picking the changes from: 31088f6f7906253e ("uapi/linux/const.h: prefer ISO-friendly __typeof__") Silencing these perf build warnings:: Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/33e963df304394f932d9108a1b0bb327f23a4eca.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/const.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h index af2a44c08683..a429381e7ca5 100644 --- a/tools/include/uapi/linux/const.h +++ b/tools/include/uapi/linux/const.h @@ -28,7 +28,7 @@ #define _BITUL(x) (_UL(1) << (x)) #define _BITULL(x) (_ULL(1) << (x)) -#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1) +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) #define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) #define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) -- GitLab From 8d6a41c8065e11206e03e7f9fa9018d35b398583 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:08 +0800 Subject: [PATCH 4728/5631] tools include UAPI: Sync the sound/asound.h copy with the kernel sources Picking the changes from: 102882b5c62f6bfe ("ALSA: document that struct __snd_pcm_mmap_control64 is messed up") 9f656705c5faa18a ("ALSA: pcm: rewrite snd_pcm_playback_silence()") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/sound/asound.h' differs from latest version at 'include/uapi/sound/asound.h' diff -u tools/include/uapi/sound/asound.h include/uapi/sound/asound.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/5606e7989bbb029c400117f2e455ab995208266f.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/sound/asound.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index de6810e94abe..0aa955aa8246 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -429,9 +429,14 @@ struct snd_pcm_sw_params { snd_pcm_uframes_t avail_min; /* min avail frames for wakeup */ snd_pcm_uframes_t xfer_align; /* obsolete: xfer size need to be a multiple */ snd_pcm_uframes_t start_threshold; /* min hw_avail frames for automatic start */ - snd_pcm_uframes_t stop_threshold; /* min avail frames for automatic stop */ - snd_pcm_uframes_t silence_threshold; /* min distance from noise for silence filling */ - snd_pcm_uframes_t silence_size; /* silence block size */ + /* + * The following two thresholds alleviate playback buffer underruns; when + * hw_avail drops below the threshold, the respective action is triggered: + */ + snd_pcm_uframes_t stop_threshold; /* - stop playback */ + snd_pcm_uframes_t silence_threshold; /* - pre-fill buffer with silence */ + snd_pcm_uframes_t silence_size; /* max size of silence pre-fill; when >= boundary, + * fill played area with silence immediately */ snd_pcm_uframes_t boundary; /* pointers wrap point */ unsigned int proto; /* protocol version */ unsigned int tstamp_type; /* timestamp type (req. proto >= 2.0.12) */ @@ -570,7 +575,8 @@ struct __snd_pcm_mmap_status64 { struct __snd_pcm_mmap_control64 { __pad_before_uframe __pad1; snd_pcm_uframes_t appl_ptr; /* RW: appl ptr (0...boundary-1) */ - __pad_before_uframe __pad2; + __pad_before_uframe __pad2; // This should be __pad_after_uframe, but binary + // backwards compatibility constraints prevent a fix. __pad_before_uframe __pad3; snd_pcm_uframes_t avail_min; /* RW: min available frames for wakeup */ -- GitLab From 705049ca4f5b7b00a792dfb559878945a6c7e084 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:11 +0800 Subject: [PATCH 4729/5631] tools headers kvm: Sync uapi/{asm/linux} kvm.h headers with the kernel sources Picking the changes from: e65733b5c59a1ea2 ("KVM: x86: Redefine 'longmode' as a flag for KVM_EXIT_HYPERCALL") 30ec7997d175cd68 ("KVM: arm64: timers: Allow userspace to set the global counter offset") 821d935c87bc9525 ("KVM: arm64: Introduce support for userspace SMCCC filtering") 81dc9504a7006b48 ("KVM: arm64: nv: timers: Support hyp timer emulation") a8308b3fc9494953 ("KVM: arm64: Refactor hvc filtering to support different actions") 0e5c9a9d6548e9b1 ("KVM: arm64: Expose SMC/HVC width to userspace") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h' diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h' diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/ac5adb58411d23b3360d436a65038fefe91c32a8.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/arm64/include/uapi/asm/kvm.h | 36 +++++++++++++++++++++++++ tools/arch/x86/include/uapi/asm/kvm.h | 3 +++ tools/include/uapi/linux/kvm.h | 12 +++++++-- 3 files changed, 49 insertions(+), 2 deletions(-) diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f8129c624b07..f7ddd73a8c0f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -198,6 +198,15 @@ struct kvm_arm_copy_mte_tags { __u64 reserved[2]; }; +/* + * Counter/Timer offset structure. Describe the virtual/physical offset. + * To be used with KVM_ARM_SET_COUNTER_OFFSET. + */ +struct kvm_arm_counter_offset { + __u64 counter_offset; + __u64 reserved; +}; + #define KVM_ARM_TAGS_TO_GUEST 0 #define KVM_ARM_TAGS_FROM_GUEST 1 @@ -372,6 +381,10 @@ enum { #endif }; +/* Device Control API on vm fd */ +#define KVM_ARM_VM_SMCCC_CTRL 0 +#define KVM_ARM_VM_SMCCC_FILTER 0 + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 @@ -411,6 +424,8 @@ enum { #define KVM_ARM_VCPU_TIMER_CTRL 1 #define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0 #define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1 +#define KVM_ARM_VCPU_TIMER_IRQ_HVTIMER 2 +#define KVM_ARM_VCPU_TIMER_IRQ_HPTIMER 3 #define KVM_ARM_VCPU_PVTIME_CTRL 2 #define KVM_ARM_VCPU_PVTIME_IPA 0 @@ -469,6 +484,27 @@ enum { /* run->fail_entry.hardware_entry_failure_reason codes. */ #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0) +enum kvm_smccc_filter_action { + KVM_SMCCC_FILTER_HANDLE = 0, + KVM_SMCCC_FILTER_DENY, + KVM_SMCCC_FILTER_FWD_TO_USER, + +#ifdef __KERNEL__ + NR_SMCCC_FILTER_ACTIONS +#endif +}; + +struct kvm_smccc_filter { + __u32 base; + __u32 nr_functions; + __u8 action; + __u8 pad[15]; +}; + +/* arm64-specific KVM_EXIT_HYPERCALL flags */ +#define KVM_HYPERCALL_EXIT_SMC (1U << 0) +#define KVM_HYPERCALL_EXIT_16BIT (1U << 1) + #endif #endif /* __ARM_KVM_H__ */ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 7f467fe05d42..1a6a1f987949 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -559,4 +559,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ +/* x86-specific KVM_EXIT_HYPERCALL flags. */ +#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 4003a166328c..737318b1c1d9 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -341,8 +341,13 @@ struct kvm_run { __u64 nr; __u64 args[6]; __u64 ret; - __u32 longmode; - __u32 pad; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; } hypercall; /* KVM_EXIT_TPR_ACCESS */ struct { @@ -1184,6 +1189,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 #ifdef KVM_CAP_IRQ_ROUTING @@ -1543,6 +1549,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) #define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) #define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) -- GitLab From 34e82891d995ab89b494032c5ab0ee939cbb7524 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Wed, 10 May 2023 18:24:52 +0800 Subject: [PATCH 4730/5631] tools arch x86: Sync the msr-index.h copy with the kernel sources Picking the changes from: c68e3d473988b9af ("x86/include/asm/msr-index.h: Add IFS Array test bits") Silencing these perf build warnings: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Signed-off-by: Yanteng Si Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: loongson-kernel@lists.loongnix.cn Link: https://lore.kernel.org/r/05778ab3c168c8030f6b20e60375dc803f0cd300.1683712945.git.siyanteng@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index ad35355ee43e..3aedae61af4f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -206,6 +206,8 @@ /* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ #define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) -- GitLab From 123361659fa405de8e21bff485fe22a65d85e64e Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Tue, 2 May 2023 15:38:26 -0700 Subject: [PATCH 4731/5631] perf evsel: Modify group pmu name for software events If we have a group of {cycles,faults} then we need the faults software event to appear to be on the same PMU as cycles so that we don't split the group in parse_events__sort_events_and_fix_groups. This case is relatively easy as cycles is the leader and will have a PMU name. In the reverse case, {faults,cycles} we still need faults to appear to have the PMU name of cycles but the old behavior is just to return "cpu". For hybrid this fails as cycles will be on "cpu_core" or "cpu_atom", causing faults to be split into a different group. Change the behavior for software events so that the whole group is searched for the named PMU. Signed-off-by: Ian Rogers Tested-by: Adrian Hunter Cc: Ahmad Yasin Cc: Alexander Shishkin Cc: Andi Kleen Cc: Athira Rajeev Cc: Caleb Biggers Cc: Edward Baker Cc: Florian Fischer Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Kajol Jain Cc: Kan Liang Cc: Kang Minchul Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Perry Taylor Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Rob Herring Cc: Samantha Alt Cc: Stephane Eranian Cc: Sumanth Korikkar Cc: Suzuki Poulouse Cc: Thomas Richter Cc: Tiezhu Yang Cc: Weilin Wang Cc: Xing Zhengjun Cc: Yang Jihong Link: https://lore.kernel.org/r/20230502223851.2234828-20-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1cd04b5998d2..63522322e118 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -829,23 +829,26 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - const struct evsel *leader; + struct evsel *leader, *pos; /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ if (evsel->pmu_name) return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use - * the pmu_name of the group leader to avoid breaking the software event - * out of the group. + * the pmu_name of the first non-software event to avoid breaking the + * software event out of the group. * * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ leader = evsel__leader(evsel); - if ((evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) && - leader->pmu_name) { - return leader->pmu_name; + if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { + /* Starting with the leader, find the first event with a named PMU. */ + for_each_group_evsel(pos, leader) { + if (pos->pmu_name) + return pos->pmu_name; + } } return "cpu"; -- GitLab From a468085011ea8bba7fc605a5423d6edaf46d35cf Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 8 May 2023 12:39:51 +0300 Subject: [PATCH 4732/5631] perf test test_intel_pt.sh: Test sample mode with event with PMU name br_misp_retired.all_branches is supported on processors that support Intel PT, so use it to test sample mode with an event that has been given a PMU name. Please note, the test fails prior to the fix "perf parse-events: Do not break up AUX event group". Signed-off-by: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230508093952.27482-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/test_intel_pt.sh | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 4ddb17cb83c5..3a8b9bffa022 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -506,6 +506,13 @@ test_sample() echo "perf record failed with --aux-sample" return 1 fi + # Check with event with PMU name + if perf_record_no_decode -o "${perfdatafile}" -e br_misp_retired.all_branches:u uname ; then + if ! perf_record_no_decode -o "${perfdatafile}" -e '{intel_pt//,br_misp_retired.all_branches/aux-sample-size=8192/}:u' uname ; then + echo "perf record failed with --aux-sample-size" + return 1 + fi + fi echo OK return 0 } -- GitLab From 7d161165d9072dcbb1f01ce947436b7a3101c254 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 8 May 2023 12:39:52 +0300 Subject: [PATCH 4733/5631] perf parse-events: Do not break up AUX event group Do not assume which events may have a PMU name, allowing the logic to keep an AUX event group together. Example: Before: $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 WARNING: events were regrouped to match PMUs Cannot add AUX area sampling to a group leader $ After: $ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.078 MB perf.data ] $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc8350 dl_main+0xa50 => 0 [unknown] sleep 20444 [003] 7939.510244: 1 branches:uH: 7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510245: 1 branches:uH: 7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown] sleep 20444 7939.510245: 10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc8862 dl_main+0xf62 => 0 [unknown] sleep 20444 [003] 7939.510255: 1 branches:uH: 7f5350cc9cdc dl_main+0x23dc => 0 [unknown] sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc89f6 dl_main+0x10f6 => 7f5350cb9530 _dl_setup_hash+0x0 sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc8a2d dl_main+0x112d => 7f5350cb3990 _dl_new_object+0x0 $ Fixes: 347c2f0a0988c59c ("perf parse-events: Sort and group parsed events") Suggested-by: Ian Rogers Signed-off-by: Adrian Hunter Tested-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/r/20230508093952.27482-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 63522322e118..2f5910b31fa9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -829,11 +829,9 @@ bool evsel__name_is(struct evsel *evsel, const char *name) const char *evsel__group_pmu_name(const struct evsel *evsel) { - struct evsel *leader, *pos; + struct evsel *leader = evsel__leader(evsel); + struct evsel *pos; - /* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ - if (evsel->pmu_name) - return evsel->pmu_name; /* * Software events may be in a group with other uncore PMU events. Use * the pmu_name of the first non-software event to avoid breaking the @@ -842,7 +840,6 @@ const char *evsel__group_pmu_name(const struct evsel *evsel) * Aux event leaders, like intel_pt, expect a group with events from * other PMUs, so substitute the AUX event's PMU in this case. */ - leader = evsel__leader(evsel); if (evsel->core.attr.type == PERF_TYPE_SOFTWARE || evsel__is_aux_event(leader)) { /* Starting with the leader, find the first event with a named PMU. */ for_each_group_evsel(pos, leader) { @@ -851,7 +848,7 @@ const char *evsel__group_pmu_name(const struct evsel *evsel) } } - return "cpu"; + return evsel->pmu_name ?: "cpu"; } const char *evsel__metric_id(const struct evsel *evsel) -- GitLab From 5be6cecda0802f2397504fd40c3402cd8ac8022e Mon Sep 17 00:00:00 2001 From: Yang Jihong Date: Wed, 10 May 2023 06:44:01 +0000 Subject: [PATCH 4734/5631] perf bpf skels: Make vmlinux.h use bpf.h and perf_event.h in source directory Currently, vmlinux.h uses the bpf.h and perf_event.h header files in the system path. If the header files in compilation environment are old, compilation may fail. For example: /home/yangjihong/linux/tools/perf/util/bpf_skel/.tmp/../vmlinux.h:151:27: error: field has incomplete type 'union perf_sample_weight' union perf_sample_weight weight; Use the bpf.h and perf_event.h files in the source code directory to avoid compilation compatibility problems. Signed-off-by: Yang Jihong Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Tom Rix Link: https://lore.kernel.org/r/20230510064401.225051-1-yangjihong1@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 3 ++- tools/perf/util/bpf_skel/vmlinux.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a42a6a99c2bc..9b92749280b2 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1058,13 +1058,14 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +TOOLS_UAPI_INCLUDE := -I$(srctree)/tools/include/uapi $(BPFTOOL): | $(SKEL_TMP_OUT) $(Q)CFLAGS= $(MAKE) -C ../bpf/bpftool \ OUTPUT=$(SKEL_TMP_OUT)/ bootstrap $(SKEL_TMP_OUT)/%.bpf.o: util/bpf_skel/%.bpf.c $(LIBBPF) | $(SKEL_TMP_OUT) - $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) \ + $(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -Wall -Werror $(BPF_INCLUDE) $(TOOLS_UAPI_INCLUDE) \ -c $(filter util/bpf_skel/%.bpf.c,$^) -o $@ && $(LLVM_STRIP) -g $@ $(SKEL_OUT)/%.skel.h: $(SKEL_TMP_OUT)/%.bpf.o | $(BPFTOOL) diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux.h index 449b1ea91fc4..c7ed51b0c1ef 100644 --- a/tools/perf/util/bpf_skel/vmlinux.h +++ b/tools/perf/util/bpf_skel/vmlinux.h @@ -1,6 +1,7 @@ #ifndef __VMLINUX_H #define __VMLINUX_H +#include // for define __always_inline #include #include #include -- GitLab From a2af0f6b8ef7ea402d6a531607bd0bc3dd3b4815 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 10 May 2023 14:23:52 -0300 Subject: [PATCH 4735/5631] perf build: Add system include paths to BPF builds There are insufficient headers in tools/include to satisfy building BPF programs and their header dependencies. Add the system include paths from the non-BPF clang compile so that these headers can be found. This code was taken from: tools/testing/selftests/bpf/Makefile Committer notes: Had to adjust the '#ifndef NO_BPF_SKEL' to '#ifdef BUILD_BPF_SKEL' as reverted that build BPF skels by default. Also cope with the addition of -I$(srctree)/tools/include/uapi done by Yang Jihong so that we prefer using the kernel sources headers instead of older ones in the system. Signed-off-by: Ian Rogers Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Andrii Nakryiko Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Paul Walmsley , Cc: Peter Zijlstra Cc: Song Liu Cc: Tom Rix Cc: Yang Jihong Link: https://lore.kernel.org/lkml/20230506021450.3499232-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 9b92749280b2..1593c5dcaa9e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -1057,7 +1057,24 @@ $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_ ifdef BUILD_BPF_SKEL BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool -BPF_INCLUDE := -I$(SKEL_TMP_OUT)/.. -I$(LIBBPF_INCLUDE) +# Get Clang's default includes on this system, as opposed to those seen by +# '-target bpf'. This fixes "missing" files on some architectures/distros, +# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc. +# +# Use '-idirafter': Don't interfere with include mechanics except where the +# build would have failed anyways. +define get_sys_includes +$(shell $(1) $(2) -v -E - &1 \ + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) $(2) -dM -E - Date: Fri, 5 May 2023 15:32:53 +0530 Subject: [PATCH 4736/5631] perf script: Skip aggregation for stat events The script command does not support aggregation modes by itself although that can be achieved using post-processing scripts. Because of this, it does not allocate memory for aggregated event values. Upon running perf stat record, the aggregation mode is set in the perf data file. If the mode is AGGR_GLOBAL, the aggregated event values are accessed and this leads to a segmentation fault since these were never allocated to begin with. Set the mode to AGGR_NONE explicitly to avoid this. E.g. $ perf stat record -e cycles true $ perf script Before: Segmentation fault (core dumped) After: CPU THREAD VAL ENA RUN TIME EVENT -1 231919 162831 362069 362069 935289 cycles:u Fixes: 8b76a3188b85724f ("perf stat: Remove unused perf_counts.aggr field") Signed-off-by: Sandipan Das Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Nick Terrell Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: stable@vger.kernel.org # v6.2+ Link: https://lore.kernel.org/r/83d6c6c05c54bf00c5a9df32ac160718efca0c7a.1683280603.git.sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 006f522d0e7f..c57be48d65bb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3647,6 +3647,13 @@ static int process_stat_config_event(struct perf_session *session __maybe_unused union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); + + /* + * Aggregation modes are not used since post-processing scripts are + * supposed to take care of such requirements + */ + stat_config.aggr_mode = AGGR_NONE; + return 0; } -- GitLab From 8669862388b01de7a248fea8b743aafd42169875 Mon Sep 17 00:00:00 2001 From: Sandipan Das Date: Fri, 5 May 2023 15:32:54 +0530 Subject: [PATCH 4737/5631] perf test: Add stat test for record and script When using the global aggregation mode, running perf script after perf stat record can result in a segmentation fault as seen with commit 8b76a3188b85 ("perf stat: Remove unused perf_counts.aggr field"). Add a basic test to the existing suite of stat-related tests for checking if that workflow runs without erroring out. Signed-off-by: Sandipan Das Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ananth Narayan Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Nick Terrell Cc: Peter Zijlstra Cc: Ravi Bangoria Link: https://lore.kernel.org/r/6a5429879764e3dac984cbb11ee2d95cc1604161.1683280603.git.sandipan.das@amd.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/shell/stat.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/perf/tests/shell/stat.sh b/tools/perf/tests/shell/stat.sh index 2c1d3f704995..b154fbb15d54 100755 --- a/tools/perf/tests/shell/stat.sh +++ b/tools/perf/tests/shell/stat.sh @@ -28,6 +28,18 @@ test_stat_record_report() { echo "stat record and report test [Success]" } +test_stat_record_script() { + echo "stat record and script test" + if ! perf stat record -o - true | perf script -i - 2>&1 | \ + grep -E -q "CPU[[:space:]]+THREAD[[:space:]]+VAL[[:space:]]+ENA[[:space:]]+RUN[[:space:]]+TIME[[:space:]]+EVENT" + then + echo "stat record and script test [Failed]" + err=1 + return + fi + echo "stat record and script test [Success]" +} + test_stat_repeat_weak_groups() { echo "stat repeat weak groups test" if ! perf stat -e '{cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles,cycles}' \ @@ -93,6 +105,7 @@ test_topdown_weak_groups() { test_default_stat test_stat_record_report +test_stat_record_script test_stat_repeat_weak_groups test_topdown_groups test_topdown_weak_groups -- GitLab From a3cee97446cc9ee1332b5f317024ccd23ac6c48c Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 4 May 2023 17:08:45 +0100 Subject: [PATCH 4738/5631] perf arm64: Fix build with refcount checking With EXTRA_CFLAGS=-DREFCNT_CHECKING=1 and build-test, some unwrapped map accesses appear. Wrap it in the new accessor to fix the error: error: 'struct perf_cpu_map' has no member named 'map' Signed-off-by: James Clark Acked-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Leo Yan Cc: Mark Rutland Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230504160845.2065510-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm64/util/header.c | 4 ++-- tools/perf/arch/arm64/util/pmu.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index d730666ab95d..80b9f6287fe2 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -29,8 +29,8 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus) char path[PATH_MAX]; FILE *file; - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR, + sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu); file = fopen(path, "r"); if (!file) { diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index fa143acb4c8d..ef1ed645097c 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -18,7 +18,7 @@ static struct perf_pmu *pmu__find_core_pmu(void) * The cpumap should cover all CPUs. Otherwise, some CPUs may * not support some events or have different event IDs. */ - if (pmu->cpus->nr != cpu__max_cpu().cpu) + if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) return NULL; return pmu; -- GitLab From bfd431cb2c68cbaec7a27b8a979d031f8501301b Mon Sep 17 00:00:00 2001 From: James Clark Date: Thu, 4 May 2023 15:48:22 +0100 Subject: [PATCH 4739/5631] perf cs-etm: Fix contextid validation Pre 5.11 kernels don't support 'contextid1' and 'contextid2' so validation would be skipped. By adding an additional check for 'contextid', old kernels will still have validation done even though contextid would either be contextid1 or contextid2. Additionally now that it's possible to override options, an existing bug in the validation is revealed. 'val' is overwritten by the contextid1 validation, and re-used for contextid2 validation causing it to always fail. '!val || val != 0x4' is the same as 'val != 0x4' because 0 is also != 4, so that expression can be simplified and the temp variable not overwritten. Fixes: 35c51f83dd1ed5db ("perf cs-etm: Validate options after applying them") Reviewed-by: Leo Yan Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: John Garry Cc: Mark Rutland Cc: Mathieu Poirier Cc: Mike Leach Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: Will Deacon Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/all/20230501073452.GA4660@leoy-yangtze.lan Link: https://lore.kernel.org/r/20230504144822.1938717-1-james.clark@arm.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/arm/util/cs-etm.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index 77cb03e6ff87..9ca040bfb1aa 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -78,9 +78,9 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, char path[PATH_MAX]; int err; u32 val; - u64 contextid = - evsel->core.attr.config & - (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | + u64 contextid = evsel->core.attr.config & + (perf_pmu__format_bits(&cs_etm_pmu->format, "contextid") | + perf_pmu__format_bits(&cs_etm_pmu->format, "contextid1") | perf_pmu__format_bits(&cs_etm_pmu->format, "contextid2")); if (!contextid) @@ -114,8 +114,7 @@ static int cs_etm_validate_context_id(struct auxtrace_record *itr, * 0b00100 Maximum of 32-bit Context ID size. * All other values are reserved. */ - val = BMVAL(val, 5, 9); - if (!val || val != 0x4) { + if (BMVAL(val, 5, 9) != 0x4) { pr_err("%s: CONTEXTIDR_EL1 isn't supported, disable with %s/contextid1=0/\n", CORESIGHT_ETM_PMU_NAME, CORESIGHT_ETM_PMU_NAME); return -EINVAL; -- GitLab From 760ebc45746b498a36332acefd9e2838a3f8fcf0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 10 May 2023 15:51:31 -0300 Subject: [PATCH 4740/5631] perf lock contention: Add empty 'struct rq' to satisfy libbpf 'runqueue' type verification If 'struct rq' isn't defined in lock_contention.bpf.c then the type for the 'runqueue' variable ends up being a forward declaration (BTF_KIND_FWD) while the kernel has it defined (BTF_KIND_STRUCT). This makes libbpf decide it has incompatible types and then fails to load the BPF skeleton: # perf lock con -ab sleep 1 libbpf: extern (var ksym) 'runqueues': incompatible types, expected [95] fwd rq, but kernel has [55509] struct rq libbpf: failed to load object 'lock_contention_bpf' libbpf: failed to load BPF skeleton 'lock_contention_bpf': -22 Failed to load lock-contention BPF skeleton lock contention BPF setup failed # Add it as an empty struct to satisfy that type verification: # perf lock con -ab sleep 1 contended total wait max wait avg wait type caller 2 50.64 us 25.38 us 25.32 us spinlock tick_do_update_jiffies64+0x25 1 26.18 us 26.18 us 26.18 us spinlock tick_do_update_jiffies64+0x25 # Committer notes: Extracted from a larger patch as Namhyung had already fixed the other issues in e53de7b65a3ca59a ("perf lock contention: Fix struct rq lock access"). Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Changbin Du Cc: Hao Luo Cc: Ian Rogers Cc: Namhyung Kim Cc: Song Liu Cc: Stephane Eranian Cc: Yang Jihong Link: https://lore.kernel.org/lkml/ZFVqeKLssg7uzxzI@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/bpf_skel/lock_contention.bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..1d48226ae75d 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -416,6 +416,8 @@ int contention_end(u64 *ctx) return 0; } +struct rq {}; + extern struct rq runqueues __ksym; struct rq___old { -- GitLab From d39fc592ef8ae9a89c5e85c8d9f760937a57d5ba Mon Sep 17 00:00:00 2001 From: Steve French Date: Wed, 10 May 2023 17:42:21 -0500 Subject: [PATCH 4741/5631] cifs: release leases for deferred close handles when freezing We should not be caching closed files when freeze is invoked on an fs (so we can release resources more gracefully). Fixes xfstests generic/068 generic/390 generic/491 Reviewed-by: David Howells Cc: Signed-off-by: Steve French --- fs/cifs/cifsfs.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8b6b3b6985f3..43a4d8603db3 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -760,6 +760,20 @@ static void cifs_umount_begin(struct super_block *sb) return; } +static int cifs_freeze(struct super_block *sb) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + struct cifs_tcon *tcon; + + if (cifs_sb == NULL) + return 0; + + tcon = cifs_sb_master_tcon(cifs_sb); + + cifs_close_all_deferred_files(tcon); + return 0; +} + #ifdef CONFIG_CIFS_STATS2 static int cifs_show_stats(struct seq_file *s, struct dentry *root) { @@ -798,6 +812,7 @@ static const struct super_operations cifs_super_ops = { as opens */ .show_options = cifs_show_options, .umount_begin = cifs_umount_begin, + .freeze_fs = cifs_freeze, #ifdef CONFIG_CIFS_STATS2 .show_stats = cifs_show_stats, #endif -- GitLab From f7dcc5e33c1e4b0d278a30f7d2f0c9a63d7b40ca Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 10 May 2023 10:35:33 +0900 Subject: [PATCH 4742/5631] firewire: net: fix unexpected release of object for asynchronous request packet The lifetime of object for asynchronous request packet is now maintained by reference counting, while current implementation of firewire-net releases the passed object in the handler. This commit fixes the bug. Reported-by: Dan Carpenter Link: https://lore.kernel.org/lkml/Y%2Fymx6WZIAlrtjLc@workstation/ Fixes: 13a55d6bb15f ("firewire: core: use kref structure to maintain lifetime of data for fw_request structure") Link: https://lore.kernel.org/lkml/20230510031205.782032-1-o-takashi@sakamocchi.jp/ Signed-off-by: Takashi Sakamoto --- drivers/firewire/net.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c index af22be84034b..538bd677c254 100644 --- a/drivers/firewire/net.c +++ b/drivers/firewire/net.c @@ -706,21 +706,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r, int rcode; if (destination == IEEE1394_ALL_NODES) { - kfree(r); - - return; - } - - if (offset != dev->handler.offset) + // Although the response to the broadcast packet is not necessarily required, the + // fw_send_response() function should still be called to maintain the reference + // counting of the object. In the case, the call of function just releases the + // object as a result to decrease the reference counting. + rcode = RCODE_COMPLETE; + } else if (offset != dev->handler.offset) { rcode = RCODE_ADDRESS_ERROR; - else if (tcode != TCODE_WRITE_BLOCK_REQUEST) + } else if (tcode != TCODE_WRITE_BLOCK_REQUEST) { rcode = RCODE_TYPE_ERROR; - else if (fwnet_incoming_packet(dev, payload, length, - source, generation, false) != 0) { + } else if (fwnet_incoming_packet(dev, payload, length, + source, generation, false) != 0) { dev_err(&dev->netdev->dev, "incoming packet failure\n"); rcode = RCODE_CONFLICT_ERROR; - } else + } else { rcode = RCODE_COMPLETE; + } fw_send_response(card, r, rcode); } -- GitLab From 80e62bc8487b049696e67ad133c503bf7f6806f7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 10 May 2023 20:04:04 -0500 Subject: [PATCH 4743/5631] MAINTAINERS: re-sort all entries and fields It's been a few years since we've sorted this thing, and the end result is that we've added MAINTAINERS entries in the wrong order, and a number of entries have their fields in non-canonical order too. So roll this boulder up the hill one more time by re-running ./scripts/parse-maintainers.pl --order on it. This file ends up being fairly painful for merge conflicts even normally, since unlike almost all other kernel files it's one of those "everybody touches the same thing", and re-ordering all entries is only going to make that worse. But the alternative is to never do it at all, and just let it all rot.. The rc2 week is likely the quietest and least painful time to do this. Requested-by: Randy Dunlap Requested-by: Joe Perches # "Please use --order" Signed-off-by: Linus Torvalds --- MAINTAINERS | 2298 +++++++++++++++++++++++++-------------------------- 1 file changed, 1149 insertions(+), 1149 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e0b87d5aa2e..e2fd64c2ebdc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -273,8 +273,8 @@ ABI/API L: linux-api@vger.kernel.org F: include/linux/syscalls.h F: kernel/sys_ni.c -X: include/uapi/ X: arch/*/include/uapi/ +X: include/uapi/ ABIT UGURU 1,2 HARDWARE MONITOR DRIVER M: Hans de Goede @@ -406,12 +406,6 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/acpi/arm64 -ACPI SERIAL MULTI INSTANTIATE DRIVER -M: Hans de Goede -L: platform-driver-x86@vger.kernel.org -S: Maintained -F: drivers/platform/x86/serial-multi-instantiate.c - ACPI PCC(Platform Communication Channel) MAILBOX DRIVER M: Sudeep Holla L: linux-acpi@vger.kernel.org @@ -430,6 +424,12 @@ B: https://bugzilla.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm F: drivers/acpi/pmic/ +ACPI SERIAL MULTI INSTANTIATE DRIVER +M: Hans de Goede +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/serial-multi-instantiate.c + ACPI THERMAL DRIVER M: Rafael J. Wysocki R: Zhang Rui @@ -823,6 +823,13 @@ L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/allwinner/ +ALLWINNER DMIC DRIVERS +M: Ban Tao +L: alsa-devel@alsa-project.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/sound/allwinner,sun50i-h6-dmic.yaml +F: sound/soc/sunxi/sun50i-dmic.c + ALLWINNER HARDWARE SPINLOCK SUPPORT M: Wilken Gottwalt S: Maintained @@ -844,13 +851,6 @@ L: linux-media@vger.kernel.org S: Maintained F: drivers/staging/media/sunxi/cedrus/ -ALLWINNER DMIC DRIVERS -M: Ban Tao -L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Maintained -F: Documentation/devicetree/bindings/sound/allwinner,sun50i-h6-dmic.yaml -F: sound/soc/sunxi/sun50i-dmic.c - ALPHA PORT M: Richard Henderson M: Ivan Kokshaysky @@ -1026,6 +1026,16 @@ F: drivers/char/hw_random/geode-rng.c F: drivers/crypto/geode* F: drivers/video/fbdev/geode/ +AMD HSMP DRIVER +M: Naveen Krishna Chatradhi +R: Carlos Bilbao +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: Documentation/arch/x86/amd_hsmp.rst +F: arch/x86/include/asm/amd_hsmp.h +F: arch/x86/include/uapi/asm/amd_hsmp.h +F: drivers/platform/x86/amd/hsmp.c + AMD IOMMU (AMD-VI) M: Joerg Roedel R: Suravee Suthikulpanit @@ -1049,6 +1059,13 @@ F: drivers/gpu/drm/amd/include/vi_structs.h F: include/uapi/linux/kfd_ioctl.h F: include/uapi/linux/kfd_sysfs.h +AMD MP2 I2C DRIVER +M: Elie Morisse +M: Shyam Sundar S K +L: linux-i2c@vger.kernel.org +S: Maintained +F: drivers/i2c/busses/i2c-amd-mp2* + AMD PDS CORE DRIVER M: Shannon Nelson M: Brett Creeley @@ -1058,18 +1075,6 @@ F: Documentation/networking/device_drivers/ethernet/amd/pds_core.rst F: drivers/net/ethernet/amd/pds_core/ F: include/linux/pds/ -AMD SPI DRIVER -M: Sanjay R Mehta -S: Maintained -F: drivers/spi/spi-amd.c - -AMD MP2 I2C DRIVER -M: Elie Morisse -M: Shyam Sundar S K -L: linux-i2c@vger.kernel.org -S: Maintained -F: drivers/i2c/busses/i2c-amd-mp2* - AMD PMC DRIVER M: Shyam Sundar S K L: platform-driver-x86@vger.kernel.org @@ -1083,16 +1088,6 @@ S: Maintained F: Documentation/ABI/testing/sysfs-amd-pmf F: drivers/platform/x86/amd/pmf/ -AMD HSMP DRIVER -M: Naveen Krishna Chatradhi -R: Carlos Bilbao -L: platform-driver-x86@vger.kernel.org -S: Maintained -F: Documentation/arch/x86/amd_hsmp.rst -F: arch/x86/include/asm/amd_hsmp.h -F: arch/x86/include/uapi/asm/amd_hsmp.h -F: drivers/platform/x86/amd/hsmp.c - AMD POWERPLAY AND SWSMU M: Evan Quan L: amd-gfx@lists.freedesktop.org @@ -1121,13 +1116,6 @@ M: Tom Lendacky S: Supported F: arch/arm64/boot/dts/amd/ -AMD XGBE DRIVER -M: "Shyam Sundar S K" -L: netdev@vger.kernel.org -S: Supported -F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi -F: drivers/net/ethernet/amd/xgbe/ - AMD SENSOR FUSION HUB DRIVER M: Basavaraj Natikar L: linux-input@vger.kernel.org @@ -1135,6 +1123,18 @@ S: Maintained F: Documentation/hid/amd-sfh* F: drivers/hid/amd-sfh-hid/ +AMD SPI DRIVER +M: Sanjay R Mehta +S: Maintained +F: drivers/spi/spi-amd.c + +AMD XGBE DRIVER +M: "Shyam Sundar S K" +L: netdev@vger.kernel.org +S: Supported +F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi +F: drivers/net/ethernet/amd/xgbe/ + AMLOGIC DDR PMU DRIVER M: Jiucheng Xu L: linux-amlogic@lists.infradead.org @@ -1169,6 +1169,14 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: drivers/net/amt.c +ANALOG DEVICES INC AD3552R DRIVER +M: Nuno Sá +L: linux-iio@vger.kernel.org +S: Supported +W: https://ez.analog.com/linux-software-drivers +F: Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml +F: drivers/iio/dac/ad3552r.c + ANALOG DEVICES INC AD4130 DRIVER M: Cosmin Tanislav L: linux-iio@vger.kernel.org @@ -1194,14 +1202,6 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml F: drivers/iio/adc/ad7292.c -ANALOG DEVICES INC AD3552R DRIVER -M: Nuno Sá -L: linux-iio@vger.kernel.org -S: Supported -W: https://ez.analog.com/linux-software-drivers -F: Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml -F: drivers/iio/dac/ad3552r.c - ANALOG DEVICES INC AD7293 DRIVER M: Antoniu Miclaus L: linux-iio@vger.kernel.org @@ -1210,23 +1210,6 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/iio/dac/adi,ad7293.yaml F: drivers/iio/dac/ad7293.c -ANALOG DEVICES INC AD7768-1 DRIVER -M: Michael Hennerich -L: linux-iio@vger.kernel.org -S: Supported -W: https://ez.analog.com/linux-software-drivers -F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml -F: drivers/iio/adc/ad7768-1.c - -ANALOG DEVICES INC AD7780 DRIVER -M: Michael Hennerich -M: Renato Lui Geh -L: linux-iio@vger.kernel.org -S: Supported -W: https://ez.analog.com/linux-software-drivers -F: Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml -F: drivers/iio/adc/ad7780.c - ANALOG DEVICES INC AD74115 DRIVER M: Cosmin Tanislav L: linux-iio@vger.kernel.org @@ -1244,6 +1227,23 @@ F: Documentation/devicetree/bindings/iio/addac/adi,ad74413r.yaml F: drivers/iio/addac/ad74413r.c F: include/dt-bindings/iio/addac/adi,ad74413r.h +ANALOG DEVICES INC AD7768-1 DRIVER +M: Michael Hennerich +L: linux-iio@vger.kernel.org +S: Supported +W: https://ez.analog.com/linux-software-drivers +F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.yaml +F: drivers/iio/adc/ad7768-1.c + +ANALOG DEVICES INC AD7780 DRIVER +M: Michael Hennerich +M: Renato Lui Geh +L: linux-iio@vger.kernel.org +S: Supported +W: https://ez.analog.com/linux-software-drivers +F: Documentation/devicetree/bindings/iio/adc/adi,ad7780.yaml +F: drivers/iio/adc/ad7780.c + ANALOG DEVICES INC ADA4250 DRIVER M: Antoniu Miclaus L: linux-iio@vger.kernel.org @@ -1294,10 +1294,10 @@ F: drivers/iio/imu/adis16460.c ANALOG DEVICES INC ADIS16475 DRIVER M: Nuno Sa L: linux-iio@vger.kernel.org -W: https://ez.analog.com/linux-software-drivers S: Supported -F: drivers/iio/imu/adis16475.c +W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/iio/imu/adi,adis16475.yaml +F: drivers/iio/imu/adis16475.c ANALOG DEVICES INC ADM1177 DRIVER M: Michael Hennerich @@ -1315,21 +1315,21 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/iio/frequency/adi,admv1013.yaml F: drivers/iio/frequency/admv1013.c -ANALOG DEVICES INC ADMV8818 DRIVER +ANALOG DEVICES INC ADMV1014 DRIVER M: Antoniu Miclaus L: linux-iio@vger.kernel.org S: Supported W: https://ez.analog.com/linux-software-drivers -F: Documentation/devicetree/bindings/iio/filter/adi,admv8818.yaml -F: drivers/iio/filter/admv8818.c +F: Documentation/devicetree/bindings/iio/frequency/adi,admv1014.yaml +F: drivers/iio/frequency/admv1014.c -ANALOG DEVICES INC ADMV1014 DRIVER +ANALOG DEVICES INC ADMV8818 DRIVER M: Antoniu Miclaus L: linux-iio@vger.kernel.org S: Supported W: https://ez.analog.com/linux-software-drivers -F: Documentation/devicetree/bindings/iio/frequency/adi,admv1014.yaml -F: drivers/iio/frequency/admv1014.c +F: Documentation/devicetree/bindings/iio/filter/adi,admv8818.yaml +F: drivers/iio/filter/admv8818.c ANALOG DEVICES INC ADP5061 DRIVER M: Michael Hennerich @@ -1351,8 +1351,8 @@ M: Lars-Peter Clausen L: linux-media@vger.kernel.org S: Supported W: https://ez.analog.com/linux-software-drivers -F: drivers/media/i2c/adv7180.c F: Documentation/devicetree/bindings/media/i2c/adv7180.yaml +F: drivers/media/i2c/adv7180.c ANALOG DEVICES INC ADV748X DRIVER M: Kieran Bingham @@ -1371,8 +1371,8 @@ ANALOG DEVICES INC ADV7604 DRIVER M: Hans Verkuil L: linux-media@vger.kernel.org S: Maintained -F: drivers/media/i2c/adv7604* F: Documentation/devicetree/bindings/media/i2c/adv7604.yaml +F: drivers/media/i2c/adv7604* ANALOG DEVICES INC ADV7842 DRIVER M: Hans Verkuil @@ -1384,8 +1384,8 @@ ANALOG DEVICES INC ADXRS290 DRIVER M: Nishant Malpani L: linux-iio@vger.kernel.org S: Supported -F: drivers/iio/gyro/adxrs290.c F: Documentation/devicetree/bindings/iio/gyroscope/adi,adxrs290.yaml +F: drivers/iio/gyro/adxrs290.c ANALOG DEVICES INC ASOC CODEC DRIVERS M: Lars-Peter Clausen @@ -1625,6 +1625,17 @@ S: Maintained F: drivers/net/arcnet/ F: include/uapi/linux/if_arcnet.h +ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) +M: Arnd Bergmann +M: Olof Johansson +M: soc@kernel.org +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +C: irc://irc.libera.chat/armlinux +T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git +F: arch/arm/boot/dts/Makefile +F: arch/arm64/boot/dts/Makefile + ARM ARCHITECTED TIMER DRIVER M: Mark Rutland M: Marc Zyngier @@ -1738,22 +1749,6 @@ S: Odd Fixes F: drivers/amba/ F: include/linux/amba/bus.h -ARM PRIMECELL PL35X NAND CONTROLLER DRIVER -M: Miquel Raynal -M: Naga Sureshkumar Relli -L: linux-mtd@lists.infradead.org -S: Maintained -F: Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml -F: drivers/mtd/nand/raw/pl35x-nand-controller.c - -ARM PRIMECELL PL35X SMC DRIVER -M: Miquel Raynal -M: Naga Sureshkumar Relli -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml -F: drivers/memory/pl353-smc.c - ARM PRIMECELL CLCD PL110 DRIVER M: Russell King S: Odd Fixes @@ -1771,6 +1766,22 @@ S: Odd Fixes F: drivers/mmc/host/mmci.* F: include/linux/amba/mmci.h +ARM PRIMECELL PL35X NAND CONTROLLER DRIVER +M: Miquel Raynal +M: Naga Sureshkumar Relli +L: linux-mtd@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/mtd/arm,pl353-nand-r2p1.yaml +F: drivers/mtd/nand/raw/pl35x-nand-controller.c + +ARM PRIMECELL PL35X SMC DRIVER +M: Miquel Raynal +M: Naga Sureshkumar Relli +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml +F: drivers/memory/pl353-smc.c + ARM PRIMECELL SSP PL022 SPI DRIVER M: Linus Walleij L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1807,17 +1818,6 @@ F: Documentation/devicetree/bindings/iommu/arm,smmu* F: drivers/iommu/arm/ F: drivers/iommu/io-pgtable-arm* -ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS) -M: Arnd Bergmann -M: Olof Johansson -M: soc@kernel.org -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -C: irc://irc.libera.chat/armlinux -T: git git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git -F: arch/arm/boot/dts/Makefile -F: arch/arm64/boot/dts/Makefile - ARM SUB-ARCHITECTURES L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -1869,9 +1869,9 @@ M: Chen-Yu Tsai M: Jernej Skrabec M: Samuel Holland L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-sunxi@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git -L: linux-sunxi@lists.linux.dev F: arch/arm/mach-sunxi/ F: arch/arm64/boot/dts/allwinner/ F: drivers/clk/sunxi-ng/ @@ -1934,6 +1934,15 @@ F: arch/arm/mach-alpine/ F: arch/arm64/boot/dts/amazon/ F: drivers/*/*alpine* +ARM/APPLE MACHINE SOUND DRIVERS +M: Martin Povišer +L: asahi@lists.linux.dev +L: alsa-devel@alsa-project.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/sound/apple,* +F: sound/soc/apple/* +F: sound/soc/codecs/cs42l83-i2c.c + ARM/APPLE MACHINE SUPPORT M: Hector Martin M: Sven Peter @@ -1985,15 +1994,6 @@ F: include/dt-bindings/pinctrl/apple.h F: include/linux/apple-mailbox.h F: include/linux/soc/apple/* -ARM/APPLE MACHINE SOUND DRIVERS -M: Martin Povišer -L: asahi@lists.linux.dev -L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Maintained -F: Documentation/devicetree/bindings/sound/apple,* -F: sound/soc/apple/* -F: sound/soc/codecs/cs42l83-i2c.c - ARM/ARTPEC MACHINE SUPPORT M: Jesper Nilsson M: Lars Persson @@ -2109,19 +2109,19 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/coresight/linux.git F: Documentation/ABI/testing/sysfs-bus-coresight-devices-* F: Documentation/devicetree/bindings/arm/arm,coresight-*.yaml -F: Documentation/devicetree/bindings/arm/qcom,coresight-*.yaml F: Documentation/devicetree/bindings/arm/arm,embedded-trace-extension.yaml F: Documentation/devicetree/bindings/arm/arm,trace-buffer-extension.yaml +F: Documentation/devicetree/bindings/arm/qcom,coresight-*.yaml F: Documentation/trace/coresight/* F: drivers/hwtracing/coresight/* F: include/dt-bindings/arm/coresight-cti-dt.h F: include/linux/coresight* F: samples/coresight/* -F: tools/perf/tests/shell/coresight/* F: tools/perf/arch/arm/util/auxtrace.c F: tools/perf/arch/arm/util/cs-etm.c F: tools/perf/arch/arm/util/cs-etm.h F: tools/perf/arch/arm/util/pmu.c +F: tools/perf/tests/shell/coresight/* F: tools/perf/util/cs-etm-decoder/* F: tools/perf/util/cs-etm.* @@ -2156,9 +2156,9 @@ F: Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml F: Documentation/devicetree/bindings/watchdog/armada-37xx-wdt.txt F: drivers/bus/moxtet.c F: drivers/firmware/turris-mox-rwtm.c +F: drivers/gpio/gpio-moxtet.c F: drivers/leds/leds-turris-omnia.c F: drivers/mailbox/armada-37xx-rwtm-mailbox.c -F: drivers/gpio/gpio-moxtet.c F: drivers/watchdog/armada_37xx_wdt.c F: include/dt-bindings/bus/moxtet.h F: include/linux/armada-37xx-rwtm-mailbox.h @@ -2188,10 +2188,10 @@ R: NXP Linux Team L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git -X: drivers/media/i2c/ F: arch/arm64/boot/dts/freescale/ X: arch/arm64/boot/dts/freescale/fsl-* X: arch/arm64/boot/dts/freescale/qoriq-* +X: drivers/media/i2c/ N: imx N: mxs @@ -2245,12 +2245,12 @@ ARM/HPE GXP ARCHITECTURE M: Jean-Marie Verdun M: Nick Hawkins S: Maintained -F: Documentation/hwmon/gxp-fan-ctrl.rst F: Documentation/devicetree/bindings/arm/hpe,gxp.yaml F: Documentation/devicetree/bindings/hwmon/hpe,gxp-fan-ctrl.yaml F: Documentation/devicetree/bindings/i2c/hpe,gxp-i2c.yaml F: Documentation/devicetree/bindings/spi/hpe,gxp-spifi.yaml F: Documentation/devicetree/bindings/timer/hpe,gxp-timer.yaml +F: Documentation/hwmon/gxp-fan-ctrl.rst F: arch/arm/boot/dts/hpe-bmc* F: arch/arm/boot/dts/hpe-gxp* F: arch/arm/mach-hpe/ @@ -2275,9 +2275,9 @@ M: Krzysztof Halasa L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/arm/intel-ixp4xx.yaml -F: Documentation/devicetree/bindings/memory-controllers/intel,ixp4xx-expansion* F: Documentation/devicetree/bindings/gpio/intel,ixp4xx-gpio.txt F: Documentation/devicetree/bindings/interrupt-controller/intel,ixp4xx-interrupt.yaml +F: Documentation/devicetree/bindings/memory-controllers/intel,ixp4xx-expansion* F: Documentation/devicetree/bindings/timer/intel,ixp4xx-timer.yaml F: arch/arm/boot/dts/intel-ixp* F: arch/arm/mach-ixp4xx/ @@ -2447,13 +2447,6 @@ F: drivers/net/ethernet/microchip/vcap/ F: drivers/pinctrl/pinctrl-microchip-sgpio.c N: sparx5 -Microchip Timer Counter Block (TCB) Capture Driver -M: Kamel Bouhara -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -L: linux-iio@vger.kernel.org -S: Maintained -F: drivers/counter/microchip-tcb-capture.c - ARM/MILBEAUT ARCHITECTURE M: Taichi Sugaya M: Takao Orito @@ -2525,8 +2518,8 @@ F: Documentation/devicetree/bindings/rtc/nuvoton,nct3018y.yaml F: arch/arm/boot/dts/nuvoton-npcm* F: arch/arm/mach-npcm/ F: arch/arm64/boot/dts/nuvoton/ -F: drivers/*/*npcm* F: drivers/*/*/*npcm* +F: drivers/*/*npcm* F: drivers/rtc/rtc-nct3018y.c F: include/dt-bindings/clock/nuvoton,npcm7xx-clock.h F: include/dt-bindings/clock/nuvoton,npcm845-clk.h @@ -2569,9 +2562,15 @@ F: arch/arm/mach-oxnas/ F: drivers/power/reset/oxnas-restart.c N: oxnas -ARM/QUALCOMM SUPPORT -M: Andy Gross -M: Bjorn Andersson +ARM/QUALCOMM CHROMEBOOK SUPPORT +R: cros-qcom-dts-watchers@chromium.org +F: arch/arm64/boot/dts/qcom/sc7180* +F: arch/arm64/boot/dts/qcom/sc7280* +F: arch/arm64/boot/dts/qcom/sdm845-cheza* + +ARM/QUALCOMM SUPPORT +M: Andy Gross +M: Bjorn Andersson R: Konrad Dybcio L: linux-arm-msm@vger.kernel.org S: Maintained @@ -2602,22 +2601,16 @@ F: drivers/pci/controller/dwc/pcie-qcom.c F: drivers/phy/qualcomm/ F: drivers/power/*/msm* F: drivers/reset/reset-qcom-* -F: drivers/ufs/host/ufs-qcom* F: drivers/spi/spi-geni-qcom.c F: drivers/spi/spi-qcom-qspi.c F: drivers/spi/spi-qup.c F: drivers/tty/serial/msm_serial.c +F: drivers/ufs/host/ufs-qcom* F: drivers/usb/dwc3/dwc3-qcom.c F: include/dt-bindings/*/qcom* F: include/linux/*/qcom* F: include/linux/soc/qcom/ -ARM/QUALCOMM CHROMEBOOK SUPPORT -R: cros-qcom-dts-watchers@chromium.org -F: arch/arm64/boot/dts/qcom/sc7180* -F: arch/arm64/boot/dts/qcom/sc7280* -F: arch/arm64/boot/dts/qcom/sdm845-cheza* - ARM/RDA MICRO ARCHITECTURE M: Manivannan Sadhasivam L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -2709,9 +2702,9 @@ R: Alim Akhtar L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org S: Maintained -C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ B: mailto:linux-samsung-soc@vger.kernel.org +C: irc://irc.libera.chat/linux-exynos T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux.git F: Documentation/arm/samsung/ F: Documentation/devicetree/bindings/arm/samsung/ @@ -2811,8 +2804,8 @@ M: Patrice Chotard L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained W: http://www.stlinux.com -F: Documentation/devicetree/bindings/spi/st,ssc-spi.yaml F: Documentation/devicetree/bindings/i2c/st,sti-i2c.yaml +F: Documentation/devicetree/bindings/spi/st,ssc-spi.yaml F: arch/arm/boot/dts/sti* F: arch/arm/mach-sti/ F: drivers/ata/ahci_st.c @@ -2959,15 +2952,15 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwamatsu/linux-visconti.git F: Documentation/devicetree/bindings/arm/toshiba.yaml F: Documentation/devicetree/bindings/clock/toshiba,tmpv770x-pipllct.yaml F: Documentation/devicetree/bindings/clock/toshiba,tmpv770x-pismu.yaml -F: Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml F: Documentation/devicetree/bindings/gpio/toshiba,gpio-visconti.yaml +F: Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml F: Documentation/devicetree/bindings/pci/toshiba,visconti-pcie.yaml F: Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml F: Documentation/devicetree/bindings/watchdog/toshiba,visconti-wdt.yaml F: arch/arm64/boot/dts/toshiba/ F: drivers/clk/visconti/ -F: drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c F: drivers/gpio/gpio-visconti.c +F: drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c F: drivers/pci/controller/dwc/pcie-visconti.c F: drivers/pinctrl/visconti/ F: drivers/watchdog/visconti_wdt.c @@ -3112,6 +3105,13 @@ S: Maintained F: Documentation/devicetree/bindings/net/asix,ax88796c.yaml F: drivers/net/ethernet/asix/ax88796c_* +ASPEED CRYPTO DRIVER +M: Neal Liu +L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/crypto/aspeed,* +F: drivers/crypto/aspeed/ + ASPEED PECI CONTROLLER M: Iwona Winiarska L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) @@ -3156,6 +3156,13 @@ S: Maintained F: Documentation/devicetree/bindings/spi/aspeed,ast2600-fmc.yaml F: drivers/spi/spi-aspeed-smc.c +ASPEED USB UDC DRIVER +M: Neal Liu +L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) +S: Maintained +F: Documentation/devicetree/bindings/usb/aspeed,ast2600-udc.yaml +F: drivers/usb/gadget/udc/aspeed_udc.c + ASPEED VIDEO ENGINE DRIVER M: Eddie James L: linux-media@vger.kernel.org @@ -3164,19 +3171,11 @@ S: Maintained F: Documentation/devicetree/bindings/media/aspeed-video.txt F: drivers/media/platform/aspeed/ -ASPEED USB UDC DRIVER -M: Neal Liu -L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) -S: Maintained -F: Documentation/devicetree/bindings/usb/aspeed,ast2600-udc.yaml -F: drivers/usb/gadget/udc/aspeed_udc.c - -ASPEED CRYPTO DRIVER -M: Neal Liu -L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) +ASUS EC HARDWARE MONITOR DRIVER +M: Eugene Shalygin +L: linux-hwmon@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/crypto/aspeed,* -F: drivers/crypto/aspeed/ +F: drivers/hwmon/asus-ec-sensors.c ASUS NOTEBOOKS AND EEEPC ACPI/WMI EXTRAS DRIVERS M: Corentin Chary @@ -3194,6 +3193,12 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git F: drivers/platform/x86/asus-tf103c-dock.c +ASUS WIRELESS RADIO CONTROL DRIVER +M: João Paulo Rechi Vita +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/asus-wireless.c + ASUS WMI HARDWARE MONITOR DRIVER M: Ed Brindley M: Denis Pauk @@ -3201,18 +3206,6 @@ L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/asus_wmi_sensors.c -ASUS EC HARDWARE MONITOR DRIVER -M: Eugene Shalygin -L: linux-hwmon@vger.kernel.org -S: Maintained -F: drivers/hwmon/asus-ec-sensors.c - -ASUS WIRELESS RADIO CONTROL DRIVER -M: João Paulo Rechi Vita -L: platform-driver-x86@vger.kernel.org -S: Maintained -F: drivers/platform/x86/asus-wireless.c - ASYMMETRIC KEYS M: David Howells L: keyrings@vger.kernel.org @@ -3352,10 +3345,10 @@ R: Boqun Feng R: Mark Rutland L: linux-kernel@vger.kernel.org S: Maintained +F: Documentation/atomic_*.txt F: arch/*/include/asm/atomic*.h F: include/*/atomic*.h F: include/linux/refcount.h -F: Documentation/atomic_*.txt F: scripts/atomic/ ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER @@ -3649,50 +3642,6 @@ S: Maintained F: Documentation/devicetree/bindings/iio/accel/bosch,bma400.yaml F: drivers/iio/accel/bma400* -BPF [GENERAL] (Safe Dynamic Programs and Tools) -M: Alexei Starovoitov -M: Daniel Borkmann -M: Andrii Nakryiko -R: Martin KaFai Lau -R: Song Liu -R: Yonghong Song -R: John Fastabend -R: KP Singh -R: Stanislav Fomichev -R: Hao Luo -R: Jiri Olsa -L: bpf@vger.kernel.org -S: Supported -W: https://bpf.io/ -Q: https://patchwork.kernel.org/project/netdevbpf/list/?delegate=121173 -T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git -F: Documentation/bpf/ -F: Documentation/networking/filter.rst -F: Documentation/userspace-api/ebpf/ -F: arch/*/net/* -F: include/linux/bpf* -F: include/linux/btf* -F: include/linux/filter.h -F: include/trace/events/xdp.h -F: include/uapi/linux/bpf* -F: include/uapi/linux/btf* -F: include/uapi/linux/filter.h -F: kernel/bpf/ -F: kernel/trace/bpf_trace.c -F: lib/test_bpf.c -F: net/bpf/ -F: net/core/filter.c -F: net/sched/act_bpf.c -F: net/sched/cls_bpf.c -F: samples/bpf/ -F: scripts/bpf_doc.py -F: scripts/pahole-flags.sh -F: scripts/pahole-version.sh -F: tools/bpf/ -F: tools/lib/bpf/ -F: tools/testing/selftests/bpf/ - BPF JIT for ARM M: Shubham Bansal L: bpf@vger.kernel.org @@ -3771,79 +3720,79 @@ S: Supported F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c +BPF [BTF] +M: Martin KaFai Lau +L: bpf@vger.kernel.org +S: Maintained +F: include/linux/btf* +F: kernel/bpf/btf.c + BPF [CORE] M: Alexei Starovoitov M: Daniel Borkmann R: John Fastabend L: bpf@vger.kernel.org S: Maintained -F: kernel/bpf/verifier.c -F: kernel/bpf/tnum.c -F: kernel/bpf/core.c -F: kernel/bpf/syscall.c -F: kernel/bpf/dispatcher.c -F: kernel/bpf/trampoline.c F: include/linux/bpf* F: include/linux/filter.h F: include/linux/tnum.h +F: kernel/bpf/core.c +F: kernel/bpf/dispatcher.c +F: kernel/bpf/syscall.c +F: kernel/bpf/tnum.c +F: kernel/bpf/trampoline.c +F: kernel/bpf/verifier.c -BPF [BTF] -M: Martin KaFai Lau -L: bpf@vger.kernel.org -S: Maintained -F: kernel/bpf/btf.c -F: include/linux/btf* - -BPF [TRACING] -M: Song Liu -R: Jiri Olsa +BPF [DOCUMENTATION] (Related to Standardization) +R: David Vernet L: bpf@vger.kernel.org +L: bpf@ietf.org S: Maintained -F: kernel/trace/bpf_trace.c -F: kernel/bpf/stackmap.c +F: Documentation/bpf/instruction-set.rst -BPF [NETWORKING] (tc BPF, sock_addr) -M: Martin KaFai Lau +BPF [GENERAL] (Safe Dynamic Programs and Tools) +M: Alexei Starovoitov M: Daniel Borkmann +M: Andrii Nakryiko +R: Martin KaFai Lau +R: Song Liu +R: Yonghong Song R: John Fastabend +R: KP Singh +R: Stanislav Fomichev +R: Hao Luo +R: Jiri Olsa L: bpf@vger.kernel.org -L: netdev@vger.kernel.org -S: Maintained +S: Supported +W: https://bpf.io/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/?delegate=121173 +T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git +F: Documentation/bpf/ +F: Documentation/networking/filter.rst +F: Documentation/userspace-api/ebpf/ +F: arch/*/net/* +F: include/linux/bpf* +F: include/linux/btf* +F: include/linux/filter.h +F: include/trace/events/xdp.h +F: include/uapi/linux/bpf* +F: include/uapi/linux/btf* +F: include/uapi/linux/filter.h +F: kernel/bpf/ +F: kernel/trace/bpf_trace.c +F: lib/test_bpf.c +F: net/bpf/ F: net/core/filter.c F: net/sched/act_bpf.c F: net/sched/cls_bpf.c - -BPF [NETWORKING] (struct_ops, reuseport) -M: Martin KaFai Lau -L: bpf@vger.kernel.org -L: netdev@vger.kernel.org -S: Maintained -F: kernel/bpf/bpf_struct* - -BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF) -M: KP Singh -R: Florent Revest -R: Brendan Jackman -L: bpf@vger.kernel.org -S: Maintained -F: Documentation/bpf/prog_lsm.rst -F: include/linux/bpf_lsm.h -F: kernel/bpf/bpf_lsm.c -F: security/bpf/ - -BPF [STORAGE & CGROUPS] -M: Martin KaFai Lau -L: bpf@vger.kernel.org -S: Maintained -F: kernel/bpf/cgroup.c -F: kernel/bpf/*storage.c -F: kernel/bpf/bpf_lru* - -BPF [RINGBUF] -M: Andrii Nakryiko -L: bpf@vger.kernel.org -S: Maintained -F: kernel/bpf/ringbuf.c +F: samples/bpf/ +F: scripts/bpf_doc.py +F: scripts/pahole-flags.sh +F: scripts/pahole-version.sh +F: tools/bpf/ +F: tools/lib/bpf/ +F: tools/testing/selftests/bpf/ BPF [ITERATOR] M: Yonghong Song @@ -3870,12 +3819,45 @@ L: bpf@vger.kernel.org S: Maintained F: tools/lib/bpf/ -BPF [TOOLING] (bpftool) -M: Quentin Monnet +BPF [MISC] +L: bpf@vger.kernel.org +S: Odd Fixes +K: (?:\b|_)bpf(?:\b|_) + +BPF [NETWORKING] (struct_ops, reuseport) +M: Martin KaFai Lau L: bpf@vger.kernel.org +L: netdev@vger.kernel.org S: Maintained -F: kernel/bpf/disasm.* -F: tools/bpf/bpftool/ +F: kernel/bpf/bpf_struct* + +BPF [NETWORKING] (tc BPF, sock_addr) +M: Martin KaFai Lau +M: Daniel Borkmann +R: John Fastabend +L: bpf@vger.kernel.org +L: netdev@vger.kernel.org +S: Maintained +F: net/core/filter.c +F: net/sched/act_bpf.c +F: net/sched/cls_bpf.c + +BPF [RINGBUF] +M: Andrii Nakryiko +L: bpf@vger.kernel.org +S: Maintained +F: kernel/bpf/ringbuf.c + +BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF) +M: KP Singh +R: Florent Revest +R: Brendan Jackman +L: bpf@vger.kernel.org +S: Maintained +F: Documentation/bpf/prog_lsm.rst +F: include/linux/bpf_lsm.h +F: kernel/bpf/bpf_lsm.c +F: security/bpf/ BPF [SELFTESTS] (Test Runners & Infrastructure) M: Andrii Nakryiko @@ -3884,17 +3866,28 @@ L: bpf@vger.kernel.org S: Maintained F: tools/testing/selftests/bpf/ -BPF [DOCUMENTATION] (Related to Standardization) -R: David Vernet +BPF [STORAGE & CGROUPS] +M: Martin KaFai Lau L: bpf@vger.kernel.org -L: bpf@ietf.org S: Maintained -F: Documentation/bpf/instruction-set.rst +F: kernel/bpf/*storage.c +F: kernel/bpf/bpf_lru* +F: kernel/bpf/cgroup.c -BPF [MISC] +BPF [TOOLING] (bpftool) +M: Quentin Monnet L: bpf@vger.kernel.org -S: Odd Fixes -K: (?:\b|_)bpf(?:\b|_) +S: Maintained +F: kernel/bpf/disasm.* +F: tools/bpf/bpftool/ + +BPF [TRACING] +M: Song Liu +R: Jiri Olsa +L: bpf@vger.kernel.org +S: Maintained +F: kernel/bpf/stackmap.c +F: kernel/trace/bpf_trace.c BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan @@ -3913,34 +3906,6 @@ F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h -BROADCOM BCMBCA ARM ARCHITECTURE -M: William Zhang -M: Anand Gore -M: Kursad Oney -M: Florian Fainelli -M: Rafał Miłecki -R: Broadcom internal kernel review list -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -T: git https://github.com/broadcom/stblinux.git -F: Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml -F: arch/arm64/boot/dts/broadcom/bcmbca/* -N: bcmbca -N: bcm[9]?47622 -N: bcm[9]?4912 -N: bcm[9]?63138 -N: bcm[9]?63146 -N: bcm[9]?63148 -N: bcm[9]?63158 -N: bcm[9]?63178 -N: bcm[9]?6756 -N: bcm[9]?6813 -N: bcm[9]?6846 -N: bcm[9]?6855 -N: bcm[9]?6856 -N: bcm[9]?6858 -N: bcm[9]?6878 - BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE M: Florian Fainelli R: Broadcom internal kernel review list @@ -4038,11 +4003,39 @@ N: brcmstb N: bcm7038 N: bcm7120 +BROADCOM BCMBCA ARM ARCHITECTURE +M: William Zhang +M: Anand Gore +M: Kursad Oney +M: Florian Fainelli +M: Rafał Miłecki +R: Broadcom internal kernel review list +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +T: git https://github.com/broadcom/stblinux.git +F: Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml +F: arch/arm64/boot/dts/broadcom/bcmbca/* +N: bcmbca +N: bcm[9]?47622 +N: bcm[9]?4912 +N: bcm[9]?63138 +N: bcm[9]?63146 +N: bcm[9]?63148 +N: bcm[9]?63158 +N: bcm[9]?63178 +N: bcm[9]?6756 +N: bcm[9]?6813 +N: bcm[9]?6846 +N: bcm[9]?6855 +N: bcm[9]?6856 +N: bcm[9]?6858 +N: bcm[9]?6878 + BROADCOM BDC DRIVER M: Justin Chen M: Al Cooper -L: linux-usb@vger.kernel.org R: Broadcom internal kernel review list +L: linux-usb@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/usb/brcm,bdc.yaml F: drivers/usb/gadget/udc/bdc/ @@ -4064,10 +4057,10 @@ F: arch/mips/bmips/* F: arch/mips/boot/dts/brcm/bcm*.dts* F: arch/mips/include/asm/mach-bmips/* F: arch/mips/kernel/*bmips* -F: drivers/soc/bcm/bcm63xx F: drivers/irqchip/irq-bcm63* F: drivers/irqchip/irq-bcm7* F: drivers/irqchip/irq-brcmstb* +F: drivers/soc/bcm/bcm63xx F: include/linux/bcm963xx_nvram.h F: include/linux/bcm963xx_tag.h @@ -4349,9 +4342,9 @@ M: Florian Fainelli R: Broadcom internal kernel review list L: netdev@vger.kernel.org S: Supported +F: Documentation/devicetree/bindings/net/brcm,systemport.yaml F: drivers/net/ethernet/broadcom/bcmsysport.* F: drivers/net/ethernet/broadcom/unimac.h -F: Documentation/devicetree/bindings/net/brcm,systemport.yaml BROADCOM TG3 GIGABIT ETHERNET DRIVER M: Siva Reddy Kallam @@ -4483,29 +4476,6 @@ W: https://github.com/Cascoda/ca8210-linux.git F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c -CANAAN/KENDRYTE K210 SOC FPIOA DRIVER -M: Damien Le Moal -L: linux-riscv@lists.infradead.org -L: linux-gpio@vger.kernel.org (pinctrl driver) -F: Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml -F: drivers/pinctrl/pinctrl-k210.c - -CANAAN/KENDRYTE K210 SOC RESET CONTROLLER DRIVER -M: Damien Le Moal -L: linux-kernel@vger.kernel.org -L: linux-riscv@lists.infradead.org -S: Maintained -F: Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml -F: drivers/reset/reset-k210.c - -CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER -M: Damien Le Moal -L: linux-riscv@lists.infradead.org -S: Maintained -F: Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml -F: drivers/soc/canaan/ -F: include/soc/canaan/ - CACHEFILES: FS-CACHE BACKEND FOR CACHING ON MOUNTED FILESYSTEMS M: David Howells L: linux-cachefs@redhat.com (moderated for non-subscribers) @@ -4627,6 +4597,29 @@ F: Documentation/networking/j1939.rst F: include/uapi/linux/can/j1939.h F: net/can/j1939/ +CANAAN/KENDRYTE K210 SOC FPIOA DRIVER +M: Damien Le Moal +L: linux-riscv@lists.infradead.org +L: linux-gpio@vger.kernel.org (pinctrl driver) +F: Documentation/devicetree/bindings/pinctrl/canaan,k210-fpioa.yaml +F: drivers/pinctrl/pinctrl-k210.c + +CANAAN/KENDRYTE K210 SOC RESET CONTROLLER DRIVER +M: Damien Le Moal +L: linux-kernel@vger.kernel.org +L: linux-riscv@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/reset/canaan,k210-rst.yaml +F: drivers/reset/reset-k210.c + +CANAAN/KENDRYTE K210 SOC SYSTEM CONTROLLER DRIVER +M: Damien Le Moal +L: linux-riscv@lists.infradead.org +S: Maintained +F: Documentation/devicetree/bindings/mfd/canaan,k210-sysctl.yaml +F: drivers/soc/canaan/ +F: include/soc/canaan/ + CAPABILITIES M: Serge Hallyn L: linux-security-module@vger.kernel.org @@ -4686,8 +4679,8 @@ F: arch/arm64/boot/dts/cavium/thunder2-99xx* CBS/ETF/TAPRIO QDISCS M: Vinicius Costa Gomes -S: Maintained L: netdev@vger.kernel.org +S: Maintained F: net/sched/sch_cbs.c F: net/sched/sch_etf.c F: net/sched/sch_taprio.c @@ -4710,10 +4703,10 @@ CCTRNG ARM TRUSTZONE CRYPTOCELL TRUE RANDOM NUMBER GENERATOR (TRNG) DRIVER M: Hadar Gat L: linux-crypto@vger.kernel.org S: Supported +W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family +F: Documentation/devicetree/bindings/rng/arm-cctrng.yaml F: drivers/char/hw_random/cctrng.c F: drivers/char/hw_random/cctrng.h -F: Documentation/devicetree/bindings/rng/arm-cctrng.yaml -W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family CEC FRAMEWORK M: Hans Verkuil @@ -4873,13 +4866,6 @@ S: Maintained F: Documentation/devicetree/bindings/sound/google,cros-ec-codec.yaml F: sound/soc/codecs/cros_ec_codec.* -CHROMEOS EC UART DRIVER -M: Bhanu Prakash Maiya -R: Benson Leung -R: Tzung-Bi Shih -S: Maintained -F: drivers/platform/chrome/cros_ec_uart.c - CHROMEOS EC SUBDRIVERS M: Benson Leung R: Guenter Roeck @@ -4889,13 +4875,12 @@ F: drivers/power/supply/cros_usbpd-charger.c N: cros_ec N: cros-ec -CHROMEOS EC USB TYPE-C DRIVER -M: Prashant Malani -L: chrome-platform@lists.linux.dev +CHROMEOS EC UART DRIVER +M: Bhanu Prakash Maiya +R: Benson Leung +R: Tzung-Bi Shih S: Maintained -F: drivers/platform/chrome/cros_ec_typec.* -F: drivers/platform/chrome/cros_typec_switch.c -F: drivers/platform/chrome/cros_typec_vdm.* +F: drivers/platform/chrome/cros_ec_uart.c CHROMEOS EC USB PD NOTIFY DRIVER M: Prashant Malani @@ -4904,6 +4889,14 @@ S: Maintained F: drivers/platform/chrome/cros_usbpd_notify.c F: include/linux/platform_data/cros_usbpd_notify.h +CHROMEOS EC USB TYPE-C DRIVER +M: Prashant Malani +L: chrome-platform@lists.linux.dev +S: Maintained +F: drivers/platform/chrome/cros_ec_typec.* +F: drivers/platform/chrome/cros_typec_switch.c +F: drivers/platform/chrome/cros_typec_vdm.* + CHROMEOS HPS DRIVER M: Dan Callaghan R: Sami Kyöstilä @@ -5021,6 +5014,18 @@ M: Nelson Escobar S: Supported F: drivers/infiniband/hw/usnic/ +CLANG CONTROL FLOW INTEGRITY SUPPORT +M: Sami Tolvanen +M: Kees Cook +R: Nathan Chancellor +R: Nick Desaulniers +L: llvm@lists.linux.dev +S: Supported +B: https://github.com/ClangBuiltLinux/linux/issues +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening +F: include/linux/cfi.h +F: kernel/cfi.c + CLANG-FORMAT FILE M: Miguel Ojeda S: Maintained @@ -5041,18 +5046,6 @@ F: scripts/Makefile.clang F: scripts/clang-tools/ K: \b(?i:clang|llvm)\b -CLANG CONTROL FLOW INTEGRITY SUPPORT -M: Sami Tolvanen -M: Kees Cook -R: Nathan Chancellor -R: Nick Desaulniers -L: llvm@lists.linux.dev -S: Supported -B: https://github.com/ClangBuiltLinux/linux/issues -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening -F: include/linux/cfi.h -F: kernel/cfi.c - CLK API M: Russell King L: linux-clk@vger.kernel.org @@ -5223,8 +5216,8 @@ CONTEXT TRACKING M: Frederic Weisbecker M: "Paul E. McKenney" S: Maintained -F: kernel/context_tracking.c F: include/linux/context_tracking* +F: kernel/context_tracking.c CONTROL GROUP (CGROUP) M: Tejun Heo @@ -5385,8 +5378,8 @@ F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVER - ARM EXYNOS M: Daniel Lezcano -R: Krzysztof Kozlowski M: Kukjin Kim +R: Krzysztof Kozlowski L: linux-pm@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Supported @@ -5407,8 +5400,8 @@ M: Ulf Hansson L: linux-pm@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported -F: drivers/cpuidle/cpuidle-psci.h F: drivers/cpuidle/cpuidle-psci-domain.c +F: drivers/cpuidle/cpuidle-psci.h CPUIDLE DRIVER - DT IDLE PM DOMAIN M: Ulf Hansson @@ -5552,19 +5545,19 @@ S: Supported W: http://www.chelsio.com F: drivers/crypto/chelsio -CXGB4 INLINE CRYPTO DRIVER -M: Ayush Sawal +CXGB4 ETHERNET DRIVER (CXGB4) +M: Raju Rangoju L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com -F: drivers/net/ethernet/chelsio/inline_crypto/ +F: drivers/net/ethernet/chelsio/cxgb4/ -CXGB4 ETHERNET DRIVER (CXGB4) -M: Raju Rangoju +CXGB4 INLINE CRYPTO DRIVER +M: Ayush Sawal L: netdev@vger.kernel.org S: Supported W: http://www.chelsio.com -F: drivers/net/ethernet/chelsio/cxgb4/ +F: drivers/net/ethernet/chelsio/inline_crypto/ CXGB4 ISCSI DRIVER (CXGB4I) M: Varun Prakash @@ -5621,16 +5614,6 @@ CYCLADES PC300 DRIVER S: Orphan F: drivers/net/wan/pc300* -CYPRESS_FIRMWARE MEDIA DRIVER -M: Antti Palosaari -L: linux-media@vger.kernel.org -S: Maintained -W: https://linuxtv.org -W: http://palosaari.fi/linux/ -Q: http://patchwork.linuxtv.org/project/linux-media/list/ -T: git git://linuxtv.org/anttip/media_tree.git -F: drivers/media/common/cypress_firmware* - CYPRESS CY8C95X0 PINCTRL DRIVER M: Patrick Rudolph L: linux-gpio@vger.kernel.org @@ -5650,6 +5633,16 @@ S: Maintained F: Documentation/devicetree/bindings/input/cypress-sf.yaml F: drivers/input/keyboard/cypress-sf.c +CYPRESS_FIRMWARE MEDIA DRIVER +M: Antti Palosaari +L: linux-media@vger.kernel.org +S: Maintained +W: https://linuxtv.org +W: http://palosaari.fi/linux/ +Q: http://patchwork.linuxtv.org/project/linux-media/list/ +T: git git://linuxtv.org/anttip/media_tree.git +F: drivers/media/common/cypress_firmware* + CYTTSP TOUCHSCREEN DRIVER M: Linus Walleij L: linux-input@vger.kernel.org @@ -5816,11 +5809,6 @@ S: Maintained F: Documentation/driver-api/dcdbas.rst F: drivers/platform/x86/dell/dcdbas.* -DELL WMI DESCRIPTOR DRIVER -L: Dell.Client.Kernel@dell.com -S: Maintained -F: drivers/platform/x86/dell/dell-wmi-descriptor.c - DELL WMI DDV DRIVER M: Armin Wolf S: Maintained @@ -5828,13 +5816,17 @@ F: Documentation/ABI/testing/debugfs-dell-wmi-ddv F: Documentation/ABI/testing/sysfs-platform-dell-wmi-ddv F: drivers/platform/x86/dell/dell-wmi-ddv.c -DELL WMI SYSMAN DRIVER -M: Prasanth Ksr +DELL WMI DESCRIPTOR DRIVER +L: Dell.Client.Kernel@dell.com +S: Maintained +F: drivers/platform/x86/dell/dell-wmi-descriptor.c + +DELL WMI HARDWARE PRIVACY SUPPORT +M: Perry Yuan L: Dell.Client.Kernel@dell.com L: platform-driver-x86@vger.kernel.org S: Maintained -F: Documentation/ABI/testing/sysfs-class-firmware-attributes -F: drivers/platform/x86/dell/dell-wmi-sysman/ +F: drivers/platform/x86/dell/dell-wmi-privacy.c DELL WMI NOTIFICATIONS DRIVER M: Matthew Garrett @@ -5842,20 +5834,13 @@ M: Pali Rohár S: Maintained F: drivers/platform/x86/dell/dell-wmi-base.c -DELL WMI HARDWARE PRIVACY SUPPORT -M: Perry Yuan +DELL WMI SYSMAN DRIVER +M: Prasanth Ksr L: Dell.Client.Kernel@dell.com L: platform-driver-x86@vger.kernel.org S: Maintained -F: drivers/platform/x86/dell/dell-wmi-privacy.c - -DELTA ST MEDIA DRIVER -M: Hugues Fruchet -L: linux-media@vger.kernel.org -S: Supported -W: https://linuxtv.org -T: git git://linuxtv.org/media_tree.git -F: drivers/media/platform/st/sti/delta +F: Documentation/ABI/testing/sysfs-class-firmware-attributes +F: drivers/platform/x86/dell/dell-wmi-sysman/ DELTA AHE-50DC FAN CONTROL MODULE DRIVER M: Zev Weiss @@ -5879,6 +5864,14 @@ F: Documentation/devicetree/bindings/reset/delta,tn48m-reset.yaml F: drivers/gpio/gpio-tn48m.c F: include/dt-bindings/reset/delta,tn48m-reset.h +DELTA ST MEDIA DRIVER +M: Hugues Fruchet +L: linux-media@vger.kernel.org +S: Supported +W: https://linuxtv.org +T: git git://linuxtv.org/media_tree.git +F: drivers/media/platform/st/sti/delta + DENALI NAND DRIVER L: linux-mtd@lists.infradead.org S: Orphan @@ -5891,13 +5884,6 @@ S: Maintained F: drivers/dma/dw-edma/ F: include/linux/dma/edma.h -DESIGNWARE XDATA IP DRIVER -M: Gustavo Pimentel -L: linux-pci@vger.kernel.org -S: Maintained -F: Documentation/misc-devices/dw-xdata-pcie.rst -F: drivers/misc/dw-xdata-pcie.c - DESIGNWARE USB2 DRD IP DRIVER M: Minas Harutyunyan L: linux-usb@vger.kernel.org @@ -5911,6 +5897,13 @@ L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/dwc3/ +DESIGNWARE XDATA IP DRIVER +M: Gustavo Pimentel +L: linux-pci@vger.kernel.org +S: Maintained +F: Documentation/misc-devices/dw-xdata-pcie.rst +F: drivers/misc/dw-xdata-pcie.c + DEVANTECH SRF ULTRASONIC RANGER IIO DRIVER M: Andreas Klinger L: linux-iio@vger.kernel.org @@ -6020,8 +6013,8 @@ F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt F: Documentation/devicetree/bindings/mfd/da90*.yaml -F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt +F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/slg51000.txt F: Documentation/devicetree/bindings/sound/da[79]*.txt F: Documentation/devicetree/bindings/thermal/da90??-thermal.txt @@ -6140,6 +6133,12 @@ F: include/linux/dma/ F: include/linux/dmaengine.h F: include/linux/of_dma.h +DMA MAPPING BENCHMARK +M: Xiang Chen +L: iommu@lists.linux.dev +F: kernel/dma/map_benchmark.c +F: tools/testing/selftests/dma/ + DMA MAPPING HELPERS M: Christoph Hellwig M: Marek Szyprowski @@ -6150,17 +6149,11 @@ W: http://git.infradead.org/users/hch/dma-mapping.git T: git git://git.infradead.org/users/hch/dma-mapping.git F: include/asm-generic/dma-mapping.h F: include/linux/dma-direct.h -F: include/linux/dma-mapping.h F: include/linux/dma-map-ops.h +F: include/linux/dma-mapping.h F: include/linux/swiotlb.h F: kernel/dma/ -DMA MAPPING BENCHMARK -M: Xiang Chen -L: iommu@lists.linux.dev -F: kernel/dma/map_benchmark.c -F: tools/testing/selftests/dma/ - DMA-BUF HEAPS FRAMEWORK M: Sumit Semwal R: Benjamin Gaignard @@ -6350,6 +6343,25 @@ S: Maintained F: drivers/soc/ti/smartreflex.c F: include/linux/power/smartreflex.h +DRM ACCEL DRIVERS FOR INTEL VPU +M: Jacek Lawrynowicz +M: Stanislaw Gruszka +L: dri-devel@lists.freedesktop.org +S: Supported +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/accel/ivpu/ +F: include/uapi/drm/ivpu_accel.h + +DRM COMPUTE ACCELERATORS DRIVERS AND FRAMEWORK +M: Oded Gabbay +L: dri-devel@lists.freedesktop.org +S: Maintained +C: irc://irc.oftc.net/dri-devel +T: git https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/accel.git +F: Documentation/accel/ +F: drivers/accel/ +F: include/drm/drm_accel.h + DRM DRIVER FOR ALLWINNER DE2 AND DE3 ENGINE M: Maxime Ripard M: Chen-Yu Tsai @@ -6432,6 +6444,21 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/feiyang,fy07024di26a30d.yaml F: drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c +DRM DRIVER FOR FIRMWARE FRAMEBUFFERS +M: Thomas Zimmermann +M: Javier Martinez Canillas +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/gpu/drm/drm_aperture.c +F: drivers/gpu/drm/tiny/ofdrm.c +F: drivers/gpu/drm/tiny/simpledrm.c +F: drivers/video/aperture.c +F: drivers/video/nomodeset.c +F: include/drm/drm_aperture.h +F: include/linux/aperture.h +F: include/video/nomodeset.h + DRM DRIVER FOR GENERIC EDP PANELS R: Douglas Anderson F: Documentation/devicetree/bindings/display/panel/panel-edp.yaml @@ -6466,6 +6493,14 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/himax,hx8357d.txt F: drivers/gpu/drm/tiny/hx8357d.c +DRM DRIVER FOR HYPERV SYNTHETIC VIDEO DEVICE +M: Deepak Rawat +L: linux-hyperv@vger.kernel.org +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/gpu/drm/hyperv + DRM DRIVER FOR ILITEK ILI9225 PANELS M: David Lechner S: Maintained @@ -6495,11 +6530,11 @@ F: drivers/gpu/drm/logicvc/ DRM DRIVER FOR LVDS PANELS M: Laurent Pinchart L: dri-devel@lists.freedesktop.org -T: git git://anongit.freedesktop.org/drm/drm-misc S: Maintained -F: drivers/gpu/drm/panel/panel-lvds.c +T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/lvds.yaml F: Documentation/devicetree/bindings/display/panel/panel-lvds.yaml +F: drivers/gpu/drm/panel/panel-lvds.c DRM DRIVER FOR MANTIX MLAF057WE51 PANELS M: Guido Günther @@ -6608,13 +6643,6 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/repaper.txt F: drivers/gpu/drm/tiny/repaper.c -DRM DRIVER FOR SOLOMON SSD130X OLED DISPLAYS -M: Javier Martinez Canillas -S: Maintained -T: git git://anongit.freedesktop.org/drm/drm-misc -F: Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml -F: drivers/gpu/drm/solomon/ssd130x* - DRM DRIVER FOR QEMU'S CIRRUS DEVICE M: Dave Airlie M: Gerd Hoffmann @@ -6663,29 +6691,6 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/samsung,s6d27a1.yaml F: drivers/gpu/drm/panel/panel-samsung-s6d27a1.c -DRM DRIVER FOR SITRONIX ST7703 PANELS -M: Guido Günther -R: Purism Kernel Team -R: Ondrej Jirman -S: Maintained -F: Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.yaml -F: drivers/gpu/drm/panel/panel-sitronix-st7703.c - -DRM DRIVER FOR FIRMWARE FRAMEBUFFERS -M: Thomas Zimmermann -M: Javier Martinez Canillas -L: dri-devel@lists.freedesktop.org -S: Maintained -T: git git://anongit.freedesktop.org/drm/drm-misc -F: drivers/gpu/drm/drm_aperture.c -F: drivers/gpu/drm/tiny/ofdrm.c -F: drivers/gpu/drm/tiny/simpledrm.c -F: drivers/video/aperture.c -F: drivers/video/nomodeset.c -F: include/drm/drm_aperture.h -F: include/linux/aperture.h -F: include/video/nomodeset.h - DRM DRIVER FOR SITRONIX ST7586 PANELS M: David Lechner S: Maintained @@ -6699,6 +6704,14 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/sitronix,st7701.yaml F: drivers/gpu/drm/panel/panel-sitronix-st7701.c +DRM DRIVER FOR SITRONIX ST7703 PANELS +M: Guido Günther +R: Purism Kernel Team +R: Ondrej Jirman +S: Maintained +F: Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.yaml +F: drivers/gpu/drm/panel/panel-sitronix-st7703.c + DRM DRIVER FOR SITRONIX ST7735R PANELS M: David Lechner S: Maintained @@ -6706,6 +6719,13 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/sitronix,st7735r.yaml F: drivers/gpu/drm/tiny/st7735r.c +DRM DRIVER FOR SOLOMON SSD130X OLED DISPLAYS +M: Javier Martinez Canillas +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml +F: drivers/gpu/drm/solomon/ssd130x* + DRM DRIVER FOR ST-ERICSSON MCDE M: Linus Walleij S: Maintained @@ -6804,25 +6824,6 @@ F: include/drm/drm* F: include/linux/vga* F: include/uapi/drm/drm* -DRM COMPUTE ACCELERATORS DRIVERS AND FRAMEWORK -M: Oded Gabbay -L: dri-devel@lists.freedesktop.org -S: Maintained -C: irc://irc.oftc.net/dri-devel -T: git https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/accel.git -F: Documentation/accel/ -F: drivers/accel/ -F: include/drm/drm_accel.h - -DRM ACCEL DRIVERS FOR INTEL VPU -M: Jacek Lawrynowicz -M: Stanislaw Gruszka -L: dri-devel@lists.freedesktop.org -S: Supported -T: git git://anongit.freedesktop.org/drm/drm-misc -F: drivers/accel/ivpu/ -F: include/uapi/drm/ivpu_accel.h - DRM DRIVERS FOR ALLWINNER A10 M: Maxime Ripard M: Chen-Yu Tsai @@ -6926,14 +6927,6 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/hisilicon/ F: drivers/gpu/drm/hisilicon/ -DRM DRIVER FOR HYPERV SYNTHETIC VIDEO DEVICE -M: Deepak Rawat -L: linux-hyperv@vger.kernel.org -L: dri-devel@lists.freedesktop.org -S: Maintained -T: git git://anongit.freedesktop.org/drm/drm-misc -F: drivers/gpu/drm/hyperv - DRM DRIVERS FOR LIMA M: Qiang Yu L: dri-devel@lists.freedesktop.org @@ -7085,6 +7078,14 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/xlnx/ F: drivers/gpu/drm/xlnx/ +DRM GPU SCHEDULER +M: Luben Tuikov +L: dri-devel@lists.freedesktop.org +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/gpu/drm/scheduler/ +F: include/drm/gpu_scheduler.h + DRM PANEL DRIVERS M: Neil Armstrong R: Sam Ravnborg @@ -7113,14 +7114,6 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/ttm/ F: include/drm/ttm/ -DRM GPU SCHEDULER -M: Luben Tuikov -L: dri-devel@lists.freedesktop.org -S: Maintained -T: git git://anongit.freedesktop.org/drm/drm-misc -F: drivers/gpu/drm/scheduler/ -F: include/drm/gpu_scheduler.h - DSBR100 USB FM RADIO DRIVER M: Alexey Klimov L: linux-media@vger.kernel.org @@ -7248,10 +7241,10 @@ F: drivers/media/usb/dvb-usb-v2/usb_urb.c DYNAMIC DEBUG M: Jason Baron +M: Jim Cromie S: Maintained F: include/linux/dynamic_debug.h F: lib/dynamic_debug.c -M: Jim Cromie F: lib/test_dynamic_debug.c DYNAMIC INTERRUPT MODERATION @@ -7261,6 +7254,15 @@ F: Documentation/networking/net_dim.rst F: include/linux/dim.h F: lib/dim/ +DYNAMIC THERMAL POWER MANAGEMENT (DTPM) +M: Daniel Lezcano +L: linux-pm@vger.kernel.org +S: Supported +B: https://bugzilla.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm +F: drivers/powercap/dtpm* +F: include/linux/dtpm.h + DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" S: Maintained @@ -7599,22 +7601,22 @@ W: http://www.broadcom.com F: drivers/infiniband/hw/ocrdma/ F: include/uapi/rdma/ocrdma-abi.h -EMULEX/BROADCOM LPFC FC/FCOE SCSI DRIVER +EMULEX/BROADCOM EFCT FC/FCOE SCSI TARGET DRIVER M: James Smart -M: Dick Kennedy +M: Ram Vegesna L: linux-scsi@vger.kernel.org +L: target-devel@vger.kernel.org S: Supported W: http://www.broadcom.com -F: drivers/scsi/lpfc/ +F: drivers/scsi/elx/ -EMULEX/BROADCOM EFCT FC/FCOE SCSI TARGET DRIVER +EMULEX/BROADCOM LPFC FC/FCOE SCSI DRIVER M: James Smart -M: Ram Vegesna +M: Dick Kennedy L: linux-scsi@vger.kernel.org -L: target-devel@vger.kernel.org S: Supported W: http://www.broadcom.com -F: drivers/scsi/elx/ +F: drivers/scsi/lpfc/ ENE CB710 FLASH CARD READER DRIVER M: Michał Mirosław @@ -7707,8 +7709,8 @@ F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ F: include/dt-bindings/net/qca-ar803x.h -F: include/linux/linkmode.h F: include/linux/*mdio*.h +F: include/linux/linkmode.h F: include/linux/mdio/*.h F: include/linux/mii.h F: include/linux/of_net.h @@ -7771,8 +7773,8 @@ M: Mimi Zohar L: linux-integrity@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git -F: security/integrity/evm/ F: security/integrity/ +F: security/integrity/evm/ EXTENSIBLE FIRMWARE INTERFACE (EFI) M: Ard Biesheuvel @@ -7803,8 +7805,8 @@ EXTRA BOOT CONFIG M: Masami Hiramatsu L: linux-kernel@vger.kernel.org L: linux-trace-kernel@vger.kernel.org -Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/admin-guide/bootconfig.rst F: fs/proc/bootconfig.c @@ -8091,21 +8093,6 @@ F: Documentation/fpga/ F: drivers/fpga/ F: include/linux/fpga/ -INTEL MAX10 BMC SECURE UPDATES -M: Russ Weight -L: linux-fpga@vger.kernel.org -S: Maintained -F: Documentation/ABI/testing/sysfs-driver-intel-m10-bmc-sec-update -F: drivers/fpga/intel-m10-bmc-sec-update.c - -MICROCHIP POLARFIRE FPGA DRIVERS -M: Conor Dooley -R: Ivan Bornyakov -L: linux-fpga@vger.kernel.org -S: Supported -F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml -F: drivers/fpga/microchip-spi.c - FPU EMULATOR M: Bill Metzenthen S: Maintained @@ -8114,9 +8101,9 @@ F: arch/x86/math-emu/ FRAMEBUFFER CORE M: Daniel Vetter -F: drivers/video/fbdev/core/ S: Odd Fixes T: git git://anongit.freedesktop.org/drm/drm-misc +F: drivers/video/fbdev/core/ FRAMEBUFFER LAYER M: Helge Deller @@ -8493,15 +8480,15 @@ M: Masami Hiramatsu R: Mark Rutland L: linux-kernel@vger.kernel.org L: linux-trace-kernel@vger.kernel.org -Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/ftrace* -F: kernel/trace/ftrace* -F: kernel/trace/fgraph.c F: arch/*/*/*/*ftrace* F: arch/*/*/*ftrace* F: include/*/ftrace.h +F: kernel/trace/fgraph.c +F: kernel/trace/ftrace* F: samples/ftrace FUNGIBLE ETHERNET DRIVERS @@ -8542,10 +8529,10 @@ GATEWORKS SYSTEM CONTROLLER (GSC) DRIVER M: Tim Harvey S: Maintained F: Documentation/devicetree/bindings/mfd/gateworks-gsc.yaml -F: drivers/mfd/gateworks-gsc.c -F: include/linux/mfd/gsc.h F: Documentation/hwmon/gsc-hwmon.rst F: drivers/hwmon/gsc-hwmon.c +F: drivers/mfd/gateworks-gsc.c +F: include/linux/mfd/gsc.h F: include/linux/platform_data/gsc_hwmon.h GCC PLUGINS @@ -8673,8 +8660,8 @@ R: Andy Shevchenko S: Maintained F: lib/string.c F: lib/string_helpers.c -F: lib/test_string.c F: lib/test-string_helpers.c +F: lib/test_string.c GENERIC UIO DRIVER FOR PCI DEVICES M: "Michael S. Tsirkin" @@ -9157,12 +9144,11 @@ L: linux-input@vger.kernel.org S: Maintained F: drivers/hid/hid-logitech-* -HID++ LOGITECH DRIVERS -R: Filipe Laíns -R: Bastien Nocera +HID PHOENIX RC FLIGHT CONTROLLER +M: Marcus Folkesson L: linux-input@vger.kernel.org S: Maintained -F: drivers/hid/hid-logitech-hidpp.c +F: drivers/hid/hid-pxrc.c HID PLAYSTATION DRIVER M: Roderick Colenbrander @@ -9170,12 +9156,6 @@ L: linux-input@vger.kernel.org S: Supported F: drivers/hid/hid-playstation.c -HID PHOENIX RC FLIGHT CONTROLLER -M: Marcus Folkesson -L: linux-input@vger.kernel.org -S: Maintained -F: drivers/hid/hid-pxrc.c - HID SENSOR HUB DRIVERS M: Jiri Kosina M: Jonathan Cameron @@ -9202,6 +9182,13 @@ S: Maintained F: drivers/hid/wacom.h F: drivers/hid/wacom_* +HID++ LOGITECH DRIVERS +R: Filipe Laíns +R: Bastien Nocera +L: linux-input@vger.kernel.org +S: Maintained +F: drivers/hid/hid-logitech-hidpp.c + HIGH-RESOLUTION TIMERS, CLOCKEVENTS M: Thomas Gleixner L: linux-kernel@vger.kernel.org @@ -9226,6 +9213,12 @@ W: http://www.highpoint-tech.com F: Documentation/scsi/hptiop.rst F: drivers/scsi/hptiop.c +HIKEY960 ONBOARD USB GPIO HUB DRIVER +M: John Stultz +L: linux-kernel@vger.kernel.org +S: Maintained +F: drivers/misc/hisi_hikey_usb.c + HIMAX HX83112B TOUCHSCREEN SUPPORT M: Job Noorman L: linux-input@vger.kernel.org @@ -9274,6 +9267,12 @@ F: drivers/crypto/hisilicon/hpre/hpre.h F: drivers/crypto/hisilicon/hpre/hpre_crypto.c F: drivers/crypto/hisilicon/hpre/hpre_main.c +HISILICON HNS3 PMU DRIVER +M: Guangbin Huang +S: Supported +F: Documentation/admin-guide/perf/hns3-pmu.rst +F: drivers/perf/hisilicon/hns3_pmu.c + HISILICON I2C CONTROLLER DRIVER M: Yicong Yang L: linux-i2c@vger.kernel.org @@ -9306,12 +9305,6 @@ W: http://www.hisilicon.com F: Documentation/devicetree/bindings/net/hisilicon*.txt F: drivers/net/ethernet/hisilicon/ -HIKEY960 ONBOARD USB GPIO HUB DRIVER -M: John Stultz -L: linux-kernel@vger.kernel.org -S: Maintained -F: drivers/misc/hisi_hikey_usb.c - HISILICON PMU DRIVER M: Shaokun Zhang M: Jonathan Cameron @@ -9321,12 +9314,6 @@ F: Documentation/admin-guide/perf/hisi-pcie-pmu.rst F: Documentation/admin-guide/perf/hisi-pmu.rst F: drivers/perf/hisilicon -HISILICON HNS3 PMU DRIVER -M: Guangbin Huang -S: Supported -F: Documentation/admin-guide/perf/hns3-pmu.rst -F: drivers/perf/hisilicon/hns3_pmu.c - HISILICON PTT DRIVER M: Yicong Yang M: Jonathan Cameron @@ -9350,14 +9337,6 @@ F: drivers/crypto/hisilicon/qm.c F: drivers/crypto/hisilicon/sgl.c F: include/linux/hisi_acc_qm.h -HISILICON ZIP Controller DRIVER -M: Yang Shen -M: Zhou Wang -L: linux-crypto@vger.kernel.org -S: Maintained -F: Documentation/ABI/testing/debugfs-hisi-zip -F: drivers/crypto/hisilicon/zip/ - HISILICON ROCE DRIVER M: Haoyue Xu M: Wenpeng Liang @@ -9416,6 +9395,14 @@ S: Maintained W: http://www.hisilicon.com F: drivers/spi/spi-hisi-sfc-v3xx.c +HISILICON ZIP Controller DRIVER +M: Yang Shen +M: Zhou Wang +L: linux-crypto@vger.kernel.org +S: Maintained +F: Documentation/ABI/testing/debugfs-hisi-zip +F: drivers/crypto/hisilicon/zip/ + HMM - Heterogeneous Memory Management M: Jérôme Glisse L: linux-mm@kvack.org @@ -9492,9 +9479,9 @@ F: drivers/input/touchscreen/htcpen.c HTE SUBSYSTEM M: Dipen Patel L: timestamp@lists.linux.dev -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pateldipen1984/linux.git -Q: https://patchwork.kernel.org/project/timestamp/list/ S: Maintained +Q: https://patchwork.kernel.org/project/timestamp/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/pateldipen1984/linux.git F: Documentation/devicetree/bindings/timestamp/ F: Documentation/driver-api/hte/ F: drivers/hte/ @@ -9589,8 +9576,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git F: Documentation/ABI/stable/sysfs-bus-vmbus F: Documentation/ABI/testing/debugfs-hyperv F: Documentation/devicetree/bindings/bus/microsoft,vmbus.yaml -F: Documentation/virt/hyperv F: Documentation/networking/device_drivers/ethernet/microsoft/netvsc.rst +F: Documentation/virt/hyperv F: arch/arm64/hyperv F: arch/arm64/include/asm/hyperv-tlfs.h F: arch/arm64/include/asm/mshyperv.h @@ -9772,6 +9759,12 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/i2c-stub.c +I3C DRIVER FOR ASPEED AST2600 +M: Jeremy Kerr +S: Maintained +F: Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml +F: drivers/i3c/master/ast2600-i3c-master.c + I3C DRIVER FOR CADENCE I3C MASTER IP M: Przemysław Gaj S: Maintained @@ -9783,12 +9776,6 @@ S: Orphan F: Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml F: drivers/i3c/master/dw* -I3C DRIVER FOR ASPEED AST2600 -M: Jeremy Kerr -S: Maintained -F: Documentation/devicetree/bindings/i3c/aspeed,ast2600-i3c.yaml -F: drivers/i3c/master/ast2600-i3c-master.c - I3C SUBSYSTEM M: Alexandre Belloni L: linux-i3c@lists.infradead.org (moderated for non-subscribers) @@ -9867,6 +9854,11 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* +IBM Power VFIO Support +M: Timothy Pearson +S: Supported +F: drivers/vfio/vfio_iommu_spapr_tce.c + IBM Power Virtual Ethernet Device Driver M: Nick Child L: netdev@vger.kernel.org @@ -9912,11 +9904,6 @@ F: drivers/crypto/vmx/ghash* F: drivers/crypto/vmx/ppc-xlate.pl F: drivers/crypto/vmx/vmx.c -IBM Power VFIO Support -M: Timothy Pearson -S: Supported -F: drivers/vfio/vfio_iommu_spapr_tce.c - IBM ServeRAID RAID DRIVER S: Orphan F: drivers/scsi/ips.* @@ -9984,6 +9971,10 @@ F: include/net/nl802154.h F: net/ieee802154/ F: net/mac802154/ +IFCVF VIRTIO DATA PATH ACCELERATOR +R: Zhu Lingshan +F: drivers/vdpa/ifcvf/ + IFE PROTOCOL M: Yotam Gigi M: Jamal Hadi Salim @@ -10248,8 +10239,8 @@ M: Dmitry Kasatkin L: linux-integrity@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git -F: security/integrity/ima/ F: security/integrity/ +F: security/integrity/ima/ INTEL 810/815 FRAMEBUFFER DRIVER M: Antonino Daplas @@ -10403,14 +10394,6 @@ S: Supported Q: https://patchwork.kernel.org/project/linux-dmaengine/list/ F: drivers/dma/ioat* -INTEL IDXD DRIVER -M: Fenghua Yu -M: Dave Jiang -L: dmaengine@vger.kernel.org -S: Supported -F: drivers/dma/idxd/* -F: include/uapi/linux/idxd.h - INTEL IDLE DRIVER M: Jacob Pan M: Len Brown @@ -10420,6 +10403,14 @@ B: https://bugzilla.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git F: drivers/idle/intel_idle.c +INTEL IDXD DRIVER +M: Fenghua Yu +M: Dave Jiang +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/idxd/* +F: include/uapi/linux/idxd.h + INTEL IN FIELD SCAN (IFS) DEVICE M: Jithu Joseph R: Ashok Raj @@ -10466,18 +10457,18 @@ F: Documentation/admin-guide/media/ipu3_rcb.svg F: Documentation/userspace-api/media/v4l/pixfmt-meta-intel-ipu3.rst F: drivers/staging/media/ipu3/ -INTEL IXP4XX CRYPTO SUPPORT -M: Corentin Labbe -L: linux-crypto@vger.kernel.org -S: Maintained -F: drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c - INTEL ISHTP ECLITE DRIVER M: Sumesh K Naduvalath L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/x86/intel/ishtp_eclite.c +INTEL IXP4XX CRYPTO SUPPORT +M: Corentin Labbe +L: linux-crypto@vger.kernel.org +S: Maintained +F: drivers/crypto/intel/ixp4xx/ixp4xx_crypto.c + INTEL IXP4XX QMGR, NPE, ETHERNET and HSS SUPPORT M: Krzysztof Halasa S: Maintained @@ -10556,6 +10547,13 @@ F: drivers/hwmon/intel-m10-bmc-hwmon.c F: drivers/mfd/intel-m10-bmc* F: include/linux/mfd/intel-m10-bmc.h +INTEL MAX10 BMC SECURE UPDATES +M: Russ Weight +L: linux-fpga@vger.kernel.org +S: Maintained +F: Documentation/ABI/testing/sysfs-driver-intel-m10-bmc-sec-update +F: drivers/fpga/intel-m10-bmc-sec-update.c + INTEL P-Unit IPC DRIVER M: Zha Qipeng L: platform-driver-x86@vger.kernel.org @@ -10603,6 +10601,13 @@ L: linux-pm@vger.kernel.org S: Supported F: drivers/cpufreq/intel_pstate.c +INTEL PTP DFL ToD DRIVER +M: Tianfei Zhang +L: linux-fpga@vger.kernel.org +L: netdev@vger.kernel.org +S: Maintained +F: drivers/ptp/ptp_dfl_tod.c + INTEL QUADRATURE ENCODER PERIPHERAL DRIVER M: Jarkko Nikula L: linux-iio@vger.kernel.org @@ -10621,6 +10626,21 @@ F: drivers/platform/x86/intel/sdsi.c F: tools/arch/x86/intel_sdsi/ F: tools/testing/selftests/drivers/sdsi/ +INTEL SGX +M: Jarkko Sakkinen +R: Dave Hansen +L: linux-sgx@vger.kernel.org +S: Supported +Q: https://patchwork.kernel.org/project/intel-sgx/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/sgx +F: Documentation/arch/x86/sgx.rst +F: arch/x86/entry/vdso/vsgx.S +F: arch/x86/include/asm/sgx.h +F: arch/x86/include/uapi/asm/sgx.h +F: arch/x86/kernel/cpu/sgx/* +F: tools/testing/selftests/sgx/* +K: \bSGX_ + INTEL SKYLAKE INT3472 ACPI DEVICE DRIVER M: Daniel Scally S: Maintained @@ -10638,13 +10658,13 @@ INTEL STRATIX10 FIRMWARE DRIVERS M: Dinh Nguyen L: linux-kernel@vger.kernel.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git F: Documentation/ABI/testing/sysfs-devices-platform-stratix10-rsu F: Documentation/devicetree/bindings/firmware/intel,stratix10-svc.txt F: drivers/firmware/stratix10-rsu.c F: drivers/firmware/stratix10-svc.c F: include/linux/firmware/intel/stratix10-smc.h F: include/linux/firmware/intel/stratix10-svc-client.h -T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git INTEL TELEMETRY DRIVER M: Rajneesh Bhardwaj @@ -10729,21 +10749,6 @@ F: Documentation/arch/x86/intel_txt.rst F: arch/x86/kernel/tboot.c F: include/linux/tboot.h -INTEL SGX -M: Jarkko Sakkinen -R: Dave Hansen -L: linux-sgx@vger.kernel.org -S: Supported -Q: https://patchwork.kernel.org/project/intel-sgx/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/sgx -F: Documentation/arch/x86/sgx.rst -F: arch/x86/entry/vdso/vsgx.S -F: arch/x86/include/asm/sgx.h -F: arch/x86/include/uapi/asm/sgx.h -F: arch/x86/kernel/cpu/sgx/* -F: tools/testing/selftests/sgx/* -K: \bSGX_ - INTERCONNECT API M: Georgi Djakov L: linux-pm@vger.kernel.org @@ -10812,18 +10817,6 @@ F: drivers/iommu/dma-iommu.h F: drivers/iommu/iova.c F: include/linux/iova.h -IOMMUFD -M: Jason Gunthorpe -M: Kevin Tian -L: iommu@lists.linux.dev -S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd.git -F: Documentation/userspace-api/iommufd.rst -F: drivers/iommu/iommufd/ -F: include/linux/iommufd.h -F: include/uapi/linux/iommufd.h -F: tools/testing/selftests/iommu/ - IOMMU SUBSYSTEM M: Joerg Roedel M: Will Deacon @@ -10839,6 +10832,18 @@ F: include/linux/iova.h F: include/linux/of_iommu.h F: include/uapi/linux/iommu.h +IOMMUFD +M: Jason Gunthorpe +M: Kevin Tian +L: iommu@lists.linux.dev +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd.git +F: Documentation/userspace-api/iommufd.rst +F: drivers/iommu/iommufd/ +F: include/linux/iommufd.h +F: include/uapi/linux/iommufd.h +F: tools/testing/selftests/iommu/ + IOSYS-MAP HELPERS M: Thomas Zimmermann L: dri-devel@lists.freedesktop.org @@ -10853,11 +10858,11 @@ L: io-uring@vger.kernel.org S: Maintained T: git git://git.kernel.dk/linux-block T: git git://git.kernel.dk/liburing -F: io_uring/ F: include/linux/io_uring.h F: include/linux/io_uring_types.h F: include/trace/events/io_uring.h F: include/uapi/linux/io_uring.h +F: io_uring/ F: tools/io_uring/ IPMI SUBSYSTEM @@ -10866,8 +10871,8 @@ L: openipmi-developer@lists.sourceforge.net (moderated for non-subscribers) S: Supported W: http://openipmi.sourceforge.net/ T: git https://github.com/cminyard/linux-ipmi.git for-next -F: Documentation/driver-api/ipmi.rst F: Documentation/devicetree/bindings/ipmi/ +F: Documentation/driver-api/ipmi.rst F: drivers/char/ipmi/ F: include/linux/ipmi* F: include/uapi/linux/ipmi* @@ -10919,8 +10924,8 @@ M: Thomas Gleixner L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core -F: kernel/irq/ F: include/linux/group_cpus.h +F: kernel/irq/ F: lib/group_cpus.c IRQCHIP DRIVERS @@ -11258,6 +11263,7 @@ L: linux-nfs@vger.kernel.org S: Supported W: http://nfs.sourceforge.net/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux.git +F: Documentation/filesystems/nfs/ F: fs/exportfs/ F: fs/lockd/ F: fs/nfs_common/ @@ -11273,7 +11279,6 @@ F: include/trace/misc/sunrpc.h F: include/uapi/linux/nfsd/ F: include/uapi/linux/sunrpc/ F: net/sunrpc/ -F: Documentation/filesystems/nfs/ KERNEL REGRESSIONS M: Thorsten Leemhuis @@ -11388,83 +11393,42 @@ F: arch/riscv/include/asm/kvm* F: arch/riscv/include/uapi/asm/kvm* F: arch/riscv/kvm/ F: tools/testing/selftests/kvm/*/riscv/ - -KERNEL VIRTUAL MACHINE for s390 (KVM/s390) -M: Christian Borntraeger -M: Janosch Frank -M: Claudio Imbrenda -R: David Hildenbrand -L: kvm@vger.kernel.org -S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git -F: Documentation/virt/kvm/s390* -F: arch/s390/include/asm/gmap.h -F: arch/s390/include/asm/kvm* -F: arch/s390/include/uapi/asm/kvm* -F: arch/s390/include/uapi/asm/uvdevice.h -F: arch/s390/kernel/uv.c -F: arch/s390/kvm/ -F: arch/s390/mm/gmap.c -F: drivers/s390/char/uvdevice.c -F: tools/testing/selftests/drivers/s390x/uvdevice/ -F: tools/testing/selftests/kvm/*/s390x/ -F: tools/testing/selftests/kvm/s390x/ - -KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) -M: Sean Christopherson -M: Paolo Bonzini -L: kvm@vger.kernel.org -S: Supported -T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git -F: arch/x86/include/asm/kvm* -F: arch/x86/include/asm/svm.h -F: arch/x86/include/asm/vmx*.h -F: arch/x86/include/uapi/asm/kvm* -F: arch/x86/include/uapi/asm/svm.h -F: arch/x86/include/uapi/asm/vmx.h -F: arch/x86/kvm/ -F: arch/x86/kvm/*/ - -KVM PARAVIRT (KVM/paravirt) -M: Paolo Bonzini -R: Wanpeng Li -R: Vitaly Kuznetsov -L: kvm@vger.kernel.org -S: Supported -T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git -F: arch/x86/kernel/kvm.c -F: arch/x86/kernel/kvmclock.c -F: arch/x86/include/asm/pvclock-abi.h -F: include/linux/kvm_para.h -F: include/uapi/linux/kvm_para.h -F: include/uapi/asm-generic/kvm_para.h -F: include/asm-generic/kvm_para.h -F: arch/um/include/asm/kvm_para.h -F: arch/x86/include/asm/kvm_para.h -F: arch/x86/include/uapi/asm/kvm_para.h - -KVM X86 HYPER-V (KVM/hyper-v) -M: Vitaly Kuznetsov -M: Sean Christopherson -M: Paolo Bonzini + +KERNEL VIRTUAL MACHINE for s390 (KVM/s390) +M: Christian Borntraeger +M: Janosch Frank +M: Claudio Imbrenda +R: David Hildenbrand L: kvm@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git -F: arch/x86/kvm/hyperv.* -F: arch/x86/kvm/kvm_onhyperv.* -F: arch/x86/kvm/svm/hyperv.* -F: arch/x86/kvm/svm/svm_onhyperv.* -F: arch/x86/kvm/vmx/hyperv.* +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git +F: Documentation/virt/kvm/s390* +F: arch/s390/include/asm/gmap.h +F: arch/s390/include/asm/kvm* +F: arch/s390/include/uapi/asm/kvm* +F: arch/s390/include/uapi/asm/uvdevice.h +F: arch/s390/kernel/uv.c +F: arch/s390/kvm/ +F: arch/s390/mm/gmap.c +F: drivers/s390/char/uvdevice.c +F: tools/testing/selftests/drivers/s390x/uvdevice/ +F: tools/testing/selftests/kvm/*/s390x/ +F: tools/testing/selftests/kvm/s390x/ -KVM X86 Xen (KVM/Xen) -M: David Woodhouse -M: Paul Durrant +KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86) M: Sean Christopherson M: Paolo Bonzini L: kvm@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git -F: arch/x86/kvm/xen.* +F: arch/x86/include/asm/kvm* +F: arch/x86/include/asm/svm.h +F: arch/x86/include/asm/vmx*.h +F: arch/x86/include/uapi/asm/kvm* +F: arch/x86/include/uapi/asm/svm.h +F: arch/x86/include/uapi/asm/vmx.h +F: arch/x86/kvm/ +F: arch/x86/kvm/*/ KERNFS M: Greg Kroah-Hartman @@ -11504,14 +11468,6 @@ F: include/keys/trusted-type.h F: include/keys/trusted_tpm.h F: security/keys/trusted-keys/ -KEYS-TRUSTED-TEE -M: Sumit Garg -L: linux-integrity@vger.kernel.org -L: keyrings@vger.kernel.org -S: Supported -F: include/keys/trusted_tee.h -F: security/keys/trusted-keys/trusted_tee.c - KEYS-TRUSTED-CAAM M: Ahmad Fatoum R: Pengutronix Kernel Team @@ -11521,6 +11477,14 @@ S: Maintained F: include/keys/trusted_caam.h F: security/keys/trusted-keys/trusted_caam.c +KEYS-TRUSTED-TEE +M: Sumit Garg +L: linux-integrity@vger.kernel.org +L: keyrings@vger.kernel.org +S: Supported +F: include/keys/trusted_tee.h +F: security/keys/trusted-keys/trusted_tee.c + KEYS/KEYRINGS M: David Howells M: Jarkko Sakkinen @@ -11583,8 +11547,8 @@ L: linux-amlogic@lists.infradead.org S: Maintained F: Documentation/devicetree/bindings/mfd/khadas,mcu.yaml F: drivers/mfd/khadas-mcu.c -F: include/linux/mfd/khadas-mcu.h F: drivers/thermal/khadas_mcu_fan.c +F: include/linux/mfd/khadas-mcu.h KIONIX/ROHM KX022A ACCELEROMETER M: Matti Vaittinen @@ -11621,8 +11585,8 @@ M: "David S. Miller" M: Masami Hiramatsu L: linux-kernel@vger.kernel.org L: linux-trace-kernel@vger.kernel.org -Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/kprobes.rst F: include/asm-generic/kprobes.h @@ -11656,6 +11620,47 @@ S: Maintained F: Documentation/devicetree/bindings/leds/backlight/kinetic,ktz8866.yaml F: drivers/video/backlight/ktz8866.c +KVM PARAVIRT (KVM/paravirt) +M: Paolo Bonzini +R: Wanpeng Li +R: Vitaly Kuznetsov +L: kvm@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git +F: arch/um/include/asm/kvm_para.h +F: arch/x86/include/asm/kvm_para.h +F: arch/x86/include/asm/pvclock-abi.h +F: arch/x86/include/uapi/asm/kvm_para.h +F: arch/x86/kernel/kvm.c +F: arch/x86/kernel/kvmclock.c +F: include/asm-generic/kvm_para.h +F: include/linux/kvm_para.h +F: include/uapi/asm-generic/kvm_para.h +F: include/uapi/linux/kvm_para.h + +KVM X86 HYPER-V (KVM/hyper-v) +M: Vitaly Kuznetsov +M: Sean Christopherson +M: Paolo Bonzini +L: kvm@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git +F: arch/x86/kvm/hyperv.* +F: arch/x86/kvm/kvm_onhyperv.* +F: arch/x86/kvm/svm/hyperv.* +F: arch/x86/kvm/svm/svm_onhyperv.* +F: arch/x86/kvm/vmx/hyperv.* + +KVM X86 Xen (KVM/Xen) +M: David Woodhouse +M: Paul Durrant +M: Sean Christopherson +M: Paolo Bonzini +L: kvm@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git +F: arch/x86/kvm/xen.* + L3MDEV M: David Ahern L: netdev@vger.kernel.org @@ -11897,9 +11902,9 @@ F: scripts/spdxexclude LINEAR RANGES HELPERS M: Mark Brown R: Matti Vaittinen +F: include/linux/linear_range.h F: lib/linear_ranges.c F: lib/test_linear_ranges.c -F: include/linux/linear_range.h LINUX FOR POWER MACINTOSH M: Benjamin Herrenschmidt @@ -12026,11 +12031,11 @@ M: Joel Stanley S: Maintained F: Documentation/devicetree/bindings/*/litex,*.yaml F: arch/openrisc/boot/dts/or1klitex.dts -F: include/linux/litex.h -F: drivers/tty/serial/liteuart.c -F: drivers/soc/litex/* -F: drivers/net/ethernet/litex/* F: drivers/mmc/host/litex_mmc.c +F: drivers/net/ethernet/litex/* +F: drivers/soc/litex/* +F: drivers/tty/serial/liteuart.c +F: include/linux/litex.h N: litex LIVE PATCHING @@ -12159,10 +12164,17 @@ R: WANG Xuerui L: loongarch@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson.git -F: arch/loongarch/ -F: drivers/*/*loongarch* F: Documentation/loongarch/ F: Documentation/translations/zh_CN/loongarch/ +F: arch/loongarch/ +F: drivers/*/*loongarch* + +LOONGSON GPIO DRIVER +M: Yinbo Zhu +L: linux-gpio@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml +F: drivers/gpio/gpio-loongson-64bit.c LOONGSON LS2X I2C DRIVER M: Binbin Zhou @@ -12171,6 +12183,14 @@ S: Maintained F: Documentation/devicetree/bindings/i2c/loongson,ls2x-i2c.yaml F: drivers/i2c/busses/i2c-ls2x.c +LOONGSON-2 SOC SERIES CLOCK DRIVER +M: Yinbo Zhu +L: linux-clk@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/clock/loongson,ls2k-clk.yaml +F: drivers/clk/clk-loongson2.c +F: include/dt-bindings/clock/loongson,ls2k-clk.h + LOONGSON-2 SOC SERIES GUTS DRIVER M: Yinbo Zhu L: loongarch@lists.linux.dev @@ -12186,21 +12206,6 @@ S: Maintained F: Documentation/devicetree/bindings/pinctrl/loongson,ls2k-pinctrl.yaml F: drivers/pinctrl/pinctrl-loongson2.c -LOONGSON GPIO DRIVER -M: Yinbo Zhu -L: linux-gpio@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml -F: drivers/gpio/gpio-loongson-64bit.c - -LOONGSON-2 SOC SERIES CLOCK DRIVER -M: Yinbo Zhu -L: linux-clk@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/clock/loongson,ls2k-clk.yaml -F: drivers/clk/clk-loongson2.c -F: include/dt-bindings/clock/loongson,ls2k-clk.h - LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Sathya Prakash M: Sreekanth Reddy @@ -12361,20 +12366,26 @@ MAILBOX API M: Jassi Brar L: linux-kernel@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/mailbox/ F: drivers/mailbox/ +F: include/dt-bindings/mailbox/ F: include/linux/mailbox_client.h F: include/linux/mailbox_controller.h -F: include/dt-bindings/mailbox/ -F: Documentation/devicetree/bindings/mailbox/ MAILBOX ARM MHUv2 M: Viresh Kumar M: Tushar Khandelwal L: linux-kernel@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/mailbox/arm,mhuv2.yaml F: drivers/mailbox/arm_mhuv2.c F: include/linux/mailbox/arm_mhuv2_message.h -F: Documentation/devicetree/bindings/mailbox/arm,mhuv2.yaml + +MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7 +M: Michael Kerrisk +L: linux-man@vger.kernel.org +S: Maintained +W: http://www.kernel.org/doc/man-pages MANAGEMENT COMPONENT TRANSPORT PROTOCOL (MCTP) M: Jeremy Kerr @@ -12388,12 +12399,6 @@ F: include/net/mctpdevice.h F: include/net/netns/mctp.h F: net/mctp/ -MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7 -M: Michael Kerrisk -L: linux-man@vger.kernel.org -S: Maintained -W: http://www.kernel.org/doc/man-pages - MAPLE TREE M: Liam R. Howlett L: linux-mm@kvack.org @@ -12425,8 +12430,8 @@ F: include/linux/platform_data/mv88e6xxx.h MARVELL ARMADA 3700 PHY DRIVERS M: Miquel Raynal S: Maintained -F: Documentation/devicetree/bindings/phy/phy-mvebu-comphy.txt F: Documentation/devicetree/bindings/phy/marvell,armada-3700-utmi-phy.yaml +F: Documentation/devicetree/bindings/phy/phy-mvebu-comphy.txt F: drivers/phy/marvell/phy-mvebu-a3700-comphy.c F: drivers/phy/marvell/phy-mvebu-a3700-utmi.c @@ -12528,6 +12533,13 @@ S: Maintained F: Documentation/devicetree/bindings/mtd/marvell-nand.txt F: drivers/mtd/nand/raw/marvell_nand.c +MARVELL OCTEON ENDPOINT DRIVER +M: Veerasenareddy Burru +M: Abhijit Ayarekar +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/marvell/octeon_ep + MARVELL OCTEONTX2 PHYSICAL FUNCTION DRIVER M: Sunil Goutham M: Geetha sowjanya @@ -12575,13 +12587,6 @@ S: Supported F: Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.yaml F: drivers/mmc/host/sdhci-xenon* -MARVELL OCTEON ENDPOINT DRIVER -M: Veerasenareddy Burru -M: Abhijit Ayarekar -L: netdev@vger.kernel.org -S: Supported -F: drivers/net/ethernet/marvell/octeon_ep - MATROX FRAMEBUFFER DRIVER L: linux-fbdev@vger.kernel.org S: Orphan @@ -12781,12 +12786,6 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/phy/mxl-gpy.c -MCBA MICROCHIP CAN BUS ANALYZER TOOL DRIVER -R: Yasushi SHOJI -L: linux-can@vger.kernel.org -S: Maintained -F: drivers/net/can/usb/mcba_usb.c - MCAN MMIO DEVICE DRIVER M: Chandrasekar Ramakrishnan L: linux-can@vger.kernel.org @@ -12796,6 +12795,12 @@ F: drivers/net/can/m_can/m_can.c F: drivers/net/can/m_can/m_can.h F: drivers/net/can/m_can/m_can_platform.c +MCBA MICROCHIP CAN BUS ANALYZER TOOL DRIVER +R: Yasushi SHOJI +L: linux-can@vger.kernel.org +S: Maintained +F: drivers/net/can/usb/mcba_usb.c + MCP2221A MICROCHIP USB-HID TO I2C BRIDGE DRIVER M: Rishi Gupta L: linux-i2c@vger.kernel.org @@ -13204,13 +13209,6 @@ S: Maintained F: Documentation/devicetree/bindings/clock/mediatek,mt7621-sysc.yaml F: drivers/clk/ralink/clk-mt7621.c -MEDIATEK MT7621/28/88 I2C DRIVER -M: Stefan Roese -L: linux-i2c@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/i2c/mediatek,mt7621-i2c.yaml -F: drivers/i2c/busses/i2c-mt7621.c - MEDIATEK MT7621 PCIE CONTROLLER DRIVER M: Sergio Paracuellos S: Maintained @@ -13223,6 +13221,13 @@ S: Maintained F: Documentation/devicetree/bindings/phy/mediatek,mt7621-pci-phy.yaml F: drivers/phy/ralink/phy-mt7621-pci.c +MEDIATEK MT7621/28/88 I2C DRIVER +M: Stefan Roese +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/mediatek,mt7621-i2c.yaml +F: drivers/i2c/busses/i2c-mt7621.c + MEDIATEK NAND CONTROLLER DRIVER L: linux-mtd@lists.infradead.org S: Orphan @@ -13482,10 +13487,22 @@ MEMORY FREQUENCY SCALING DRIVERS FOR NVIDIA TEGRA M: Dmitry Osipenko L: linux-pm@vger.kernel.org L: linux-tegra@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git F: drivers/devfreq/tegra30-devfreq.c +MEMORY HOT(UN)PLUG +M: David Hildenbrand +M: Oscar Salvador +L: linux-mm@kvack.org +S: Maintained +F: Documentation/admin-guide/mm/memory-hotplug.rst +F: Documentation/core-api/memory-hotplug.rst +F: drivers/base/memory.c +F: include/linux/memory_hotplug.h +F: mm/memory_hotplug.c +F: tools/testing/selftests/memory-hotplug/ + MEMORY MANAGEMENT M: Andrew Morton L: linux-mm@kvack.org @@ -13504,30 +13521,6 @@ F: mm/ F: tools/mm/ F: tools/testing/selftests/mm/ -VMALLOC -M: Andrew Morton -R: Uladzislau Rezki -R: Christoph Hellwig -R: Lorenzo Stoakes -L: linux-mm@kvack.org -S: Maintained -W: http://www.linux-mm.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm -F: include/linux/vmalloc.h -F: mm/vmalloc.c - -MEMORY HOT(UN)PLUG -M: David Hildenbrand -M: Oscar Salvador -L: linux-mm@kvack.org -S: Maintained -F: Documentation/admin-guide/mm/memory-hotplug.rst -F: Documentation/core-api/memory-hotplug.rst -F: drivers/base/memory.c -F: include/linux/memory_hotplug.h -F: mm/memory_hotplug.c -F: tools/testing/selftests/memory-hotplug/ - MEMORY TECHNOLOGY DEVICES (MTD) M: Miquel Raynal M: Richard Weinberger @@ -13638,6 +13631,12 @@ W: http://www.monstr.eu/fdt/ T: git git://git.monstr.eu/linux-2.6-microblaze.git F: arch/microblaze/ +MICROBLAZE TMR INJECT +M: Appana Durga Kedareswara rao +S: Supported +F: Documentation/devicetree/bindings/misc/xlnx,tmr-inject.yaml +F: drivers/misc/xilinx_tmr_inject.c + MICROBLAZE TMR MANAGER M: Appana Durga Kedareswara rao S: Supported @@ -13645,12 +13644,6 @@ F: Documentation/ABI/testing/sysfs-driver-xilinx-tmr-manager F: Documentation/devicetree/bindings/misc/xlnx,tmr-manager.yaml F: drivers/misc/xilinx_tmr_manager.c -MICROBLAZE TMR INJECT -M: Appana Durga Kedareswara rao -S: Supported -F: Documentation/devicetree/bindings/misc/xlnx,tmr-inject.yaml -F: drivers/misc/xilinx_tmr_inject.c - MICROCHIP AT91 DMA DRIVERS M: Ludovic Desroches M: Tudor Ambarus @@ -13725,11 +13718,11 @@ M: Eugen Hristev L: linux-media@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/media/atmel,isc.yaml -F: Documentation/devicetree/bindings/media/microchip,xisc.yaml -F: drivers/staging/media/deprecated/atmel/atmel-isc* -F: drivers/staging/media/deprecated/atmel/atmel-sama*-isc* +F: Documentation/devicetree/bindings/media/microchip,xisc.yaml F: drivers/media/platform/microchip/microchip-isc* F: drivers/media/platform/microchip/microchip-sama*-isc* +F: drivers/staging/media/deprecated/atmel/atmel-isc* +F: drivers/staging/media/deprecated/atmel/atmel-sama*-isc* F: include/linux/atmel-isc-media.h MICROCHIP ISI DRIVER @@ -13751,13 +13744,6 @@ F: include/linux/dsa/ksz_common.h F: include/linux/platform_data/microchip-ksz.h F: net/dsa/tag_ksz.c -MICROCHIP LAN87xx/LAN937x T1 PHY DRIVER -M: Arun Ramadoss -R: UNGLinuxDriver@microchip.com -L: netdev@vger.kernel.org -S: Maintained -F: drivers/net/phy/microchip_t1.c - MICROCHIP LAN743X ETHERNET DRIVER M: Bryan Whitehead M: UNGLinuxDriver@microchip.com @@ -13765,6 +13751,13 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/microchip/lan743x_* +MICROCHIP LAN87xx/LAN937x T1 PHY DRIVER +M: Arun Ramadoss +R: UNGLinuxDriver@microchip.com +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/microchip_t1.c + MICROCHIP LAN966X ETHERNET DRIVER M: Horatiu Vultur M: UNGLinuxDriver@microchip.com @@ -13806,14 +13799,6 @@ S: Supported F: Documentation/devicetree/bindings/mtd/atmel-nand.txt F: drivers/mtd/nand/raw/atmel/* -MICROCHIP PCI1XXXX GP DRIVER -M: Kumaravel Thiagarajan -L: linux-gpio@vger.kernel.org -S: Supported -F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c -F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.h -F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c - MICROCHIP OTPC DRIVER M: Claudiu Beznea L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -13822,6 +13807,14 @@ F: Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml F: drivers/nvmem/microchip-otpc.c F: include/dt-bindings/nvmem/microchip,sama7g5-otpc.h +MICROCHIP PCI1XXXX GP DRIVER +M: Kumaravel Thiagarajan +L: linux-gpio@vger.kernel.org +S: Supported +F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c +F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.h +F: drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c + MICROCHIP PCI1XXXX I2C DRIVER M: Tharun Kumar P M: Kumaravel Thiagarajan @@ -13837,6 +13830,14 @@ L: linux-serial@vger.kernel.org S: Maintained F: drivers/tty/serial/8250/8250_pci1xxxx.c +MICROCHIP POLARFIRE FPGA DRIVERS +M: Conor Dooley +R: Ivan Bornyakov +L: linux-fpga@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml +F: drivers/fpga/microchip-spi.c + MICROCHIP PWM DRIVER M: Claudiu Beznea L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -13858,6 +13859,12 @@ M: Claudiu Beznea S: Supported F: drivers/power/reset/at91-sama5d2_shdwc.c +MICROCHIP SOC DRIVERS +M: Conor Dooley +S: Supported +T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ +F: drivers/soc/microchip/ + MICROCHIP SPI DRIVER M: Tudor Ambarus S: Supported @@ -13871,11 +13878,12 @@ F: Documentation/devicetree/bindings/misc/atmel-ssc.txt F: drivers/misc/atmel-ssc.c F: include/linux/atmel-ssc.h -MICROCHIP SOC DRIVERS -M: Conor Dooley -S: Supported -T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ -F: drivers/soc/microchip/ +Microchip Timer Counter Block (TCB) Capture Driver +M: Kamel Bouhara +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-iio@vger.kernel.org +S: Maintained +F: drivers/counter/microchip-tcb-capture.c MICROCHIP USB251XB DRIVER M: Richard Leitner @@ -13992,6 +14000,12 @@ L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/surface/surfacepro3_button.c +MICROSOFT SURFACE SYSTEM AGGREGATOR HUB DRIVER +M: Maximilian Luz +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/surface/surface_aggregator_hub.c + MICROSOFT SURFACE SYSTEM AGGREGATOR SUBSYSTEM M: Maximilian Luz L: platform-driver-x86@vger.kernel.org @@ -14007,12 +14021,6 @@ F: include/linux/surface_acpi_notify.h F: include/linux/surface_aggregator/ F: include/uapi/linux/surface_aggregator/ -MICROSOFT SURFACE SYSTEM AGGREGATOR HUB DRIVER -M: Maximilian Luz -L: platform-driver-x86@vger.kernel.org -S: Maintained -F: drivers/platform/surface/surface_aggregator_hub.c - MICROTEK X6 SCANNER M: Oliver Neukum S: Maintained @@ -14178,11 +14186,11 @@ L: linux-modules@vger.kernel.org L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git modules-next -F: include/linux/module.h F: include/linux/kmod.h +F: include/linux/module.h F: kernel/module/ -F: scripts/module* F: lib/test_kmod.c +F: scripts/module* F: tools/testing/selftests/kmod/ MONOLITHIC POWER SYSTEM PMIC DRIVER @@ -14771,6 +14779,7 @@ L: linux-nfs@vger.kernel.org S: Maintained W: http://client.linux-nfs.org T: git git://git.linux-nfs.org/projects/trondmy/linux-nfs.git +F: Documentation/filesystems/nfs/ F: fs/lockd/ F: fs/nfs/ F: fs/nfs_common/ @@ -14780,7 +14789,6 @@ F: include/linux/sunrpc/ F: include/uapi/linux/nfs* F: include/uapi/linux/sunrpc/ F: net/sunrpc/ -F: Documentation/filesystems/nfs/ NILFS2 FILESYSTEM M: Ryusuke Konishi @@ -14984,12 +14992,6 @@ F: drivers/nvme/target/auth.c F: drivers/nvme/target/fabrics-cmd-auth.c F: include/linux/nvme-auth.h -NVM EXPRESS HARDWARE MONITORING SUPPORT -M: Guenter Roeck -L: linux-nvme@lists.infradead.org -S: Supported -F: drivers/nvme/host/hwmon.c - NVM EXPRESS FC TRANSPORT DRIVERS M: James Smart L: linux-nvme@lists.infradead.org @@ -15000,6 +15002,12 @@ F: drivers/nvme/target/fcloop.c F: include/linux/nvme-fc-driver.h F: include/linux/nvme-fc.h +NVM EXPRESS HARDWARE MONITORING SUPPORT +M: Guenter Roeck +L: linux-nvme@lists.infradead.org +S: Supported +F: drivers/nvme/host/hwmon.c + NVM EXPRESS TARGET DRIVER M: Christoph Hellwig M: Sagi Grimberg @@ -15020,6 +15028,13 @@ F: drivers/nvmem/ F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h +NXP BLUETOOTH WIRELESS DRIVERS +M: Amitkumar Karwar +M: Neeraj Kale +S: Maintained +F: Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml +F: drivers/bluetooth/btnxpuart.c + NXP C45 TJA11XX PHY DRIVER M: Radu Pirea L: netdev@vger.kernel.org @@ -15045,16 +15060,17 @@ F: drivers/iio/gyro/fxas21002c_core.c F: drivers/iio/gyro/fxas21002c_i2c.c F: drivers/iio/gyro/fxas21002c_spi.c -NXP i.MX CLOCK DRIVERS -M: Abel Vesa -R: Peng Fan -L: linux-clk@vger.kernel.org +NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER +M: Haibo Chen +L: linux-iio@vger.kernel.org L: linux-imx@nxp.com S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx -F: Documentation/devicetree/bindings/clock/imx* -F: drivers/clk/imx/ -F: include/dt-bindings/clock/imx* +F: Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml +F: Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml +F: Documentation/devicetree/bindings/iio/adc/nxp,imx93-adc.yaml +F: drivers/iio/adc/imx7d_adc.c +F: drivers/iio/adc/imx93_adc.c +F: drivers/iio/adc/vf610_adc.c NXP i.MX 8M ISI DRIVER M: Laurent Pinchart @@ -15063,6 +15079,15 @@ S: Maintained F: Documentation/devicetree/bindings/media/nxp,imx8-isi.yaml F: drivers/media/platform/nxp/imx8-isi/ +NXP i.MX 8MP DW100 V4L2 DRIVER +M: Xavier Roumegue +L: linux-media@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/media/nxp,dw100.yaml +F: Documentation/userspace-api/media/drivers/dw100.rst +F: drivers/media/platform/nxp/dw100/ +F: include/uapi/linux/dw100.h + NXP i.MX 8MQ DCSS DRIVER M: Laurentiu Palcu R: Lucas Stach @@ -15080,17 +15105,24 @@ S: Maintained F: Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml F: drivers/iio/adc/imx8qxp-adc.c -NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER -M: Haibo Chen -L: linux-iio@vger.kernel.org +NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER +M: Mirela Rabulea +R: NXP Linux Team +L: linux-media@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml +F: drivers/media/platform/nxp/imx-jpeg + +NXP i.MX CLOCK DRIVERS +M: Abel Vesa +R: Peng Fan +L: linux-clk@vger.kernel.org L: linux-imx@nxp.com S: Maintained -F: Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml -F: Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml -F: Documentation/devicetree/bindings/iio/adc/nxp,imx93-adc.yaml -F: drivers/iio/adc/imx7d_adc.c -F: drivers/iio/adc/imx93_adc.c -F: drivers/iio/adc/vf610_adc.c +T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx +F: Documentation/devicetree/bindings/clock/imx* +F: drivers/clk/imx/ +F: include/dt-bindings/clock/imx* NXP PF8100/PF8121A/PF8200 PMIC REGULATOR DEVICE DRIVER M: Jagan Teki @@ -15136,34 +15168,17 @@ S: Maintained F: Documentation/devicetree/bindings/sound/tfa9879.txt F: sound/soc/codecs/tfa9879* -NXP/Goodix TFA989X (TFA1) DRIVER -M: Stephan Gerhold -L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Maintained -F: Documentation/devicetree/bindings/sound/nxp,tfa989x.yaml -F: sound/soc/codecs/tfa989x.c - NXP-NCI NFC DRIVER S: Orphan F: Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml F: drivers/nfc/nxp-nci -NXP i.MX 8MP DW100 V4L2 DRIVER -M: Xavier Roumegue -L: linux-media@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/media/nxp,dw100.yaml -F: Documentation/userspace-api/media/drivers/dw100.rst -F: drivers/media/platform/nxp/dw100/ -F: include/uapi/linux/dw100.h - -NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER -M: Mirela Rabulea -R: NXP Linux Team -L: linux-media@vger.kernel.org +NXP/Goodix TFA989X (TFA1) DRIVER +M: Stephan Gerhold +L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained -F: Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml -F: drivers/media/platform/nxp/imx-jpeg +F: Documentation/devicetree/bindings/sound/nxp,tfa989x.yaml +F: sound/soc/codecs/tfa989x.c NZXT-KRAKEN2 HARDWARE MONITORING DRIVER M: Jonas Malaco @@ -15689,8 +15704,8 @@ M: Rob Herring M: Frank Rowand L: devicetree@vger.kernel.org S: Maintained -C: irc://irc.libera.chat/devicetree W: http://www.devicetree.org/ +C: irc://irc.libera.chat/devicetree T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git F: Documentation/ABI/testing/sysfs-firmware-ofw F: drivers/of/ @@ -15706,8 +15721,8 @@ M: Krzysztof Kozlowski M: Conor Dooley L: devicetree@vger.kernel.org S: Maintained -C: irc://irc.libera.chat/devicetree Q: http://patchwork.ozlabs.org/project/devicetree-bindings/list/ +C: irc://irc.libera.chat/devicetree T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git F: Documentation/devicetree/ F: arch/*/boot/dts/ @@ -15720,13 +15735,6 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/ptp/ptp_ocp.c -INTEL PTP DFL ToD DRIVER -M: Tianfei Zhang -L: linux-fpga@vger.kernel.org -L: netdev@vger.kernel.org -S: Maintained -F: drivers/ptp/ptp_dfl_tod.c - OPENCORES I2C BUS DRIVER M: Peter Korsgaard M: Andrew Lunn @@ -15745,8 +15753,8 @@ L: linux-openrisc@vger.kernel.org S: Maintained W: http://openrisc.io T: git https://github.com/openrisc/linux.git -F: Documentation/devicetree/bindings/openrisc/ F: Documentation/arch/openrisc/ +F: Documentation/devicetree/bindings/openrisc/ F: arch/openrisc/ F: drivers/irqchip/irq-ompic.c F: drivers/irqchip/irq-or1k-* @@ -16062,6 +16070,14 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: drivers/pci/controller/dwc/*layerscape* +PCI DRIVER FOR FU740 +M: Paul Walmsley +M: Greentime Hu +L: linux-pci@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml +F: drivers/pci/controller/dwc/pcie-fu740.c + PCI DRIVER FOR GENERIC OF HOSTS M: Will Deacon L: linux-pci@vger.kernel.org @@ -16082,14 +16098,6 @@ F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml F: drivers/pci/controller/dwc/*imx6* -PCI DRIVER FOR FU740 -M: Paul Walmsley -M: Greentime Hu -L: linux-pci@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml -F: drivers/pci/controller/dwc/pcie-fu740.c - PCI DRIVER FOR INTEL IXP4XX M: Linus Walleij S: Maintained @@ -16169,8 +16177,8 @@ M: Jingoo Han M: Gustavo Pimentel L: linux-pci@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml F: Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml +F: Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml F: drivers/pci/controller/dwc/*designware* PCI DRIVER FOR TI DRA7XX/J721E @@ -16190,6 +16198,14 @@ S: Maintained F: Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt F: drivers/pci/controller/pci-v3-semi.c +PCI DRIVER FOR XILINX VERSAL CPM +M: Bharat Kumar Gogada +M: Michal Simek +L: linux-pci@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml +F: drivers/pci/controller/pcie-xilinx-cpm.c + PCI ENDPOINT SUBSYSTEM M: Lorenzo Pieralisi M: Krzysztof Wilczyński @@ -16227,19 +16243,6 @@ L: linux-pci@vger.kernel.org S: Supported F: Documentation/PCI/pci-error-recovery.rst -PCI PEER-TO-PEER DMA (P2PDMA) -M: Bjorn Helgaas -M: Logan Gunthorpe -L: linux-pci@vger.kernel.org -S: Supported -Q: https://patchwork.kernel.org/project/linux-pci/list/ -B: https://bugzilla.kernel.org -C: irc://irc.oftc.net/linux-pci -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git -F: Documentation/driver-api/pci/p2pdma.rst -F: drivers/pci/p2pdma.c -F: include/linux/pci-p2pdma.h - PCI MSI DRIVER FOR ALTERA MSI IP M: Joyce Ooi L: linux-pci@vger.kernel.org @@ -16270,6 +16273,19 @@ F: drivers/pci/controller/ F: drivers/pci/pci-bridge-emul.c F: drivers/pci/pci-bridge-emul.h +PCI PEER-TO-PEER DMA (P2PDMA) +M: Bjorn Helgaas +M: Logan Gunthorpe +L: linux-pci@vger.kernel.org +S: Supported +Q: https://patchwork.kernel.org/project/linux-pci/list/ +B: https://bugzilla.kernel.org +C: irc://irc.oftc.net/linux-pci +T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git +F: Documentation/driver-api/pci/p2pdma.rst +F: drivers/pci/p2pdma.c +F: include/linux/pci-p2pdma.h + PCI SUBSYSTEM M: Bjorn Helgaas L: linux-pci@vger.kernel.org @@ -16378,14 +16394,6 @@ L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/pci/controller/dwc/pcie-qcom.c -PCIE ENDPOINT DRIVER FOR QUALCOMM -M: Manivannan Sadhasivam -L: linux-pci@vger.kernel.org -L: linux-arm-msm@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml -F: drivers/pci/controller/dwc/pcie-qcom-ep.c - PCIE DRIVER FOR ROCKCHIP M: Shawn Lin L: linux-pci@vger.kernel.org @@ -16407,13 +16415,13 @@ L: linux-pci@vger.kernel.org S: Maintained F: drivers/pci/controller/dwc/*spear* -PCI DRIVER FOR XILINX VERSAL CPM -M: Bharat Kumar Gogada -M: Michal Simek +PCIE ENDPOINT DRIVER FOR QUALCOMM +M: Manivannan Sadhasivam L: linux-pci@vger.kernel.org +L: linux-arm-msm@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/pci/xilinx-versal-cpm.yaml -F: drivers/pci/controller/pcie-xilinx-cpm.c +F: Documentation/devicetree/bindings/pci/qcom,pcie-ep.yaml +F: drivers/pci/controller/dwc/pcie-qcom-ep.c PCMCIA SUBSYSTEM M: Dominik Brodowski @@ -16683,9 +16691,9 @@ R: Alim Akhtar L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org S: Maintained -C: irc://irc.libera.chat/linux-exynos Q: https://patchwork.kernel.org/project/linux-samsung-soc/list/ B: mailto:linux-samsung-soc@vger.kernel.org +C: irc://irc.libera.chat/linux-exynos T: git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/samsung.git F: Documentation/devicetree/bindings/pinctrl/samsung,pinctrl*yaml F: drivers/pinctrl/samsung/ @@ -16747,13 +16755,6 @@ M: Logan Gunthorpe S: Maintained F: drivers/dma/plx_dma.c -PM6764TR DRIVER -M: Charles Hsu -L: linux-hwmon@vger.kernel.org -S: Maintained -F: Documentation/hwmon/pm6764tr.rst -F: drivers/hwmon/pmbus/pm6764tr.c - PM-GRAPH UTILITY M: "Todd E Brandt" L: linux-pm@vger.kernel.org @@ -16763,6 +16764,13 @@ B: https://bugzilla.kernel.org/buglist.cgi?component=pm-graph&product=Tools T: git git://github.com/intel/pm-graph F: tools/power/pm-graph +PM6764TR DRIVER +M: Charles Hsu +L: linux-hwmon@vger.kernel.org +S: Maintained +F: Documentation/hwmon/pm6764tr.rst +F: drivers/hwmon/pmbus/pm6764tr.c + PMBUS HARDWARE MONITORING DRIVERS M: Guenter Roeck L: linux-hwmon@vger.kernel.org @@ -16843,15 +16851,6 @@ F: include/linux/pm_* F: include/linux/powercap.h F: kernel/configs/nopm.config -DYNAMIC THERMAL POWER MANAGEMENT (DTPM) -M: Daniel Lezcano -L: linux-pm@vger.kernel.org -S: Supported -B: https://bugzilla.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm -F: drivers/powercap/dtpm* -F: include/linux/dtpm.h - POWER STATE COORDINATION INTERFACE (PSCI) M: Mark Rutland M: Lorenzo Pieralisi @@ -17010,8 +17009,8 @@ R: Guilherme G. Piccoli L: linux-hardening@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore -F: Documentation/admin-guide/ramoops.rst F: Documentation/admin-guide/pstore-blk.rst +F: Documentation/admin-guide/ramoops.rst F: Documentation/devicetree/bindings/reserved-memory/ramoops.yaml F: drivers/acpi/apei/erst.c F: drivers/firmware/efi/efi-pstore.c @@ -17160,10 +17159,10 @@ F: sound/soc/codecs/lpass-va-macro.c F: sound/soc/codecs/lpass-wsa-macro.* F: sound/soc/codecs/msm8916-wcd-analog.c F: sound/soc/codecs/msm8916-wcd-digital.c -F: sound/soc/codecs/wcd9335.* -F: sound/soc/codecs/wcd934x.c F: sound/soc/codecs/wcd-clsh-v2.* F: sound/soc/codecs/wcd-mbhc-v2.* +F: sound/soc/codecs/wcd9335.* +F: sound/soc/codecs/wcd934x.c F: sound/soc/codecs/wsa881x.c F: sound/soc/codecs/wsa883x.c F: sound/soc/qcom/ @@ -17320,14 +17319,21 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/tuners/qt1010* +QUALCOMM ATH12K WIRELESS DRIVER +M: Kalle Valo +L: ath12k@lists.infradead.org +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git +F: drivers/net/wireless/ath/ath12k/ + QUALCOMM ATHEROS ATH10K WIRELESS DRIVER M: Kalle Valo L: ath10k@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git -F: drivers/net/wireless/ath/ath10k/ F: Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml +F: drivers/net/wireless/ath/ath10k/ QUALCOMM ATHEROS ATH11K WIRELESS DRIVER M: Kalle Valo @@ -17337,13 +17343,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml F: drivers/net/wireless/ath/ath11k/ -QUALCOMM ATH12K WIRELESS DRIVER -M: Kalle Valo -L: ath12k@lists.infradead.org -S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git -F: drivers/net/wireless/ath/ath12k/ - QUALCOMM ATHEROS ATH9K WIRELESS DRIVER M: Toke Høiland-Jørgensen L: linux-wireless@vger.kernel.org @@ -17440,8 +17439,8 @@ F: include/uapi/misc/fastrpc.h QUALCOMM HEXAGON ARCHITECTURE M: Brian Cain L: linux-hexagon@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/bcain/linux.git S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/bcain/linux.git F: arch/hexagon/ QUALCOMM HIDMA DRIVER @@ -17563,9 +17562,9 @@ M: Christian König M: Pan, Xinhui L: amd-gfx@lists.freedesktop.org S: Supported -T: git https://gitlab.freedesktop.org/agd5f/linux.git B: https://gitlab.freedesktop.org/drm/amd/-/issues C: irc://irc.oftc.net/radeon +T: git https://gitlab.freedesktop.org/agd5f/linux.git F: Documentation/gpu/amdgpu/ F: drivers/gpu/drm/amd/ F: drivers/gpu/drm/radeon/ @@ -17653,8 +17652,8 @@ F: arch/mips/generic/board-ranchu.c RANDOM NUMBER DRIVER M: "Theodore Ts'o" M: Jason A. Donenfeld -T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git S: Maintained +T: git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git F: drivers/char/random.c F: drivers/virt/vmgenid.c @@ -17688,8 +17687,8 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/driver-api/media/rc-core.rst F: Documentation/userspace-api/media/rc/ F: drivers/media/rc/ -F: include/media/rc-map.h F: include/media/rc-core.h +F: include/media/rc-map.h F: include/uapi/linux/lirc.h RCMM REMOTE CONTROLS DECODER @@ -17806,6 +17805,14 @@ F: include/linux/rtc/ F: include/uapi/linux/rtc.h F: tools/testing/selftests/rtc/ +Real-time Linux Analysis (RTLA) tools +M: Daniel Bristot de Oliveira +M: Steven Rostedt +L: linux-trace-devel@vger.kernel.org +S: Maintained +F: Documentation/tools/rtla/ +F: tools/tracing/rtla/ + REALTEK AUDIO CODECS M: Oder Chiou S: Maintained @@ -17929,6 +17936,14 @@ S: Maintained F: Documentation/devicetree/bindings/sound/renesas,idt821034.yaml F: sound/soc/codecs/idt821034.c +RENESAS R-CAR GEN3 & RZ/N1 NAND CONTROLLER DRIVER +M: Miquel Raynal +L: linux-mtd@lists.infradead.org +L: linux-renesas-soc@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/mtd/renesas-nandc.yaml +F: drivers/mtd/nand/raw/renesas-nand-controller.c + RENESAS R-CAR GYROADC DRIVER M: Marek Vasut L: linux-iio@vger.kernel.org @@ -17947,9 +17962,9 @@ F: drivers/i2c/busses/i2c-sh_mobile.c RENESAS R-CAR SATA DRIVER R: Sergey Shtylyov -S: Supported L: linux-ide@vger.kernel.org L: linux-renesas-soc@vger.kernel.org +S: Supported F: Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml F: drivers/ata/sata_rcar.c @@ -17969,12 +17984,6 @@ S: Supported F: Documentation/devicetree/bindings/i2c/renesas,riic.yaml F: drivers/i2c/busses/i2c-riic.c -RENESAS USB PHY DRIVER -M: Yoshihiro Shimoda -L: linux-renesas-soc@vger.kernel.org -S: Maintained -F: drivers/phy/renesas/phy-rcar-gen3-usb*.c - RENESAS RZ/G2L A/D DRIVER M: Lad Prabhakar L: linux-iio@vger.kernel.org @@ -18020,13 +18029,11 @@ S: Maintained F: Documentation/devicetree/bindings/usb/renesas,rzn1-usbf.yaml F: drivers/usb/gadget/udc/renesas_usbf.c -RENESAS R-CAR GEN3 & RZ/N1 NAND CONTROLLER DRIVER -M: Miquel Raynal -L: linux-mtd@lists.infradead.org +RENESAS USB PHY DRIVER +M: Yoshihiro Shimoda L: linux-renesas-soc@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/mtd/renesas-nandc.yaml -F: drivers/mtd/nand/raw/renesas-nand-controller.c +F: drivers/phy/renesas/phy-rcar-gen3-usb*.c RENESAS VERSACLOCK 7 CLOCK DRIVER M: Alex Helms @@ -18094,15 +18101,6 @@ S: Maintained F: drivers/mtd/nand/raw/r852.c F: drivers/mtd/nand/raw/r852.h -RISC-V PMU DRIVERS -M: Atish Patra -R: Anup Patel -L: linux-riscv@lists.infradead.org -S: Supported -F: drivers/perf/riscv_pmu.c -F: drivers/perf/riscv_pmu_legacy.c -F: drivers/perf/riscv_pmu_sbi.c - RISC-V ARCHITECTURE M: Paul Walmsley M: Palmer Dabbelt @@ -18155,6 +18153,15 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ F: Documentation/devicetree/bindings/riscv/ F: arch/riscv/boot/dts/ +RISC-V PMU DRIVERS +M: Atish Patra +R: Anup Patel +L: linux-riscv@lists.infradead.org +S: Supported +F: drivers/perf/riscv_pmu.c +F: drivers/perf/riscv_pmu_legacy.c +F: drivers/perf/riscv_pmu_sbi.c + RNBD BLOCK DRIVERS M: Md. Haris Iqbal M: Jack Wang @@ -18459,14 +18466,6 @@ F: drivers/s390/net/*iucv* F: include/net/iucv/ F: net/iucv/ -S390 NETWORK DRIVERS -M: Alexandra Winter -M: Wenjia Zhang -L: linux-s390@vger.kernel.org -L: netdev@vger.kernel.org -S: Supported -F: drivers/s390/net/ - S390 MM M: Alexander Gordeev M: Gerald Schaefer @@ -18476,14 +18475,22 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git F: arch/s390/include/asm/pgtable.h F: arch/s390/mm +S390 NETWORK DRIVERS +M: Alexandra Winter +M: Wenjia Zhang +L: linux-s390@vger.kernel.org +L: netdev@vger.kernel.org +S: Supported +F: drivers/s390/net/ + S390 PCI SUBSYSTEM M: Niklas Schnelle M: Gerald Schaefer L: linux-s390@vger.kernel.org S: Supported +F: Documentation/s390/pci.rst F: arch/s390/pci/ F: drivers/pci/hotplug/s390_pci_hpc.c -F: Documentation/s390/pci.rst S390 SCM DRIVER M: Vineeth Vijayan @@ -18916,6 +18923,13 @@ L: linux-mmc@vger.kernel.org S: Supported F: drivers/mmc/host/sdhci-of-at91.c +SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER +M: Haibo Chen +L: linux-imx@nxp.com +L: linux-mmc@vger.kernel.org +S: Maintained +F: drivers/mmc/host/sdhci-esdhc-imx.c + SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) SAMSUNG DRIVER M: Ben Dooks M: Jaehoon Chung @@ -18935,13 +18949,6 @@ L: linux-mmc@vger.kernel.org S: Maintained F: drivers/mmc/host/sdhci-omap.c -SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER -M: Haibo Chen -L: linux-imx@nxp.com -L: linux-mmc@vger.kernel.org -S: Maintained -F: drivers/mmc/host/sdhci-esdhc-imx.c - SECURE ENCRYPTING DEVICE (SED) OPAL DRIVER M: Jonathan Derrick L: linux-block@vger.kernel.org @@ -18951,6 +18958,15 @@ F: block/sed* F: include/linux/sed* F: include/uapi/linux/sed* +SECURE MONITOR CALL(SMC) CALLING CONVENTION (SMCCC) +M: Mark Rutland +M: Lorenzo Pieralisi +M: Sudeep Holla +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: drivers/firmware/smccc/ +F: include/linux/arm-smccc.h + SECURITY CONTACT M: Security Officers S: Supported @@ -19400,15 +19416,6 @@ M: Nicolas Pitre S: Odd Fixes F: drivers/net/ethernet/smsc/smc91x.* -SECURE MONITOR CALL(SMC) CALLING CONVENTION (SMCCC) -M: Mark Rutland -M: Lorenzo Pieralisi -M: Sudeep Holla -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: drivers/firmware/smccc/ -F: include/linux/arm-smccc.h - SMM665 HARDWARE MONITOR DRIVER M: Guenter Roeck L: linux-hwmon@vger.kernel.org @@ -19456,6 +19463,10 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/smsc/smsc9420.* +SNET DPU VIRTIO DATA PATH ACCELERATOR +R: Alvaro Karsz +F: drivers/vdpa/solidrun/ + SOCIONEXT (SNI) AVE NETWORK DRIVER M: Kunihiko Hayashi L: netdev@vger.kernel.org @@ -19725,6 +19736,13 @@ F: include/uapi/sound/ F: sound/ F: tools/testing/selftests/alsa +SOUND - ALSA SELFTESTS +M: Mark Brown +L: alsa-devel@alsa-project.org (moderated for non-subscribers) +L: linux-kselftest@vger.kernel.org +S: Supported +F: tools/testing/selftests/alsa + SOUND - COMPRESSED AUDIO M: Vinod Koul L: alsa-devel@alsa-project.org (moderated for non-subscribers) @@ -19743,13 +19761,6 @@ F: include/sound/dmaengine_pcm.h F: sound/core/pcm_dmaengine.c F: sound/soc/soc-generic-dmaengine-pcm.c -SOUND - ALSA SELFTESTS -M: Mark Brown -L: alsa-devel@alsa-project.org (moderated for non-subscribers) -L: linux-kselftest@vger.kernel.org -S: Supported -F: tools/testing/selftests/alsa - SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC) M: Liam Girdwood M: Mark Brown @@ -19769,8 +19780,8 @@ M: Liam Girdwood M: Peter Ujfalusi M: Bard Liao M: Ranjani Sridharan -R: Kai Vehmanen M: Daniel Baluta +R: Kai Vehmanen L: sound-open-firmware@alsa-project.org (moderated for non-subscribers) S: Supported W: https://github.com/thesofproject/linux/ @@ -19832,9 +19843,9 @@ M: "Luc Van Oostenryck" L: linux-sparse@vger.kernel.org S: Maintained W: https://sparse.docs.kernel.org/ -T: git git://git.kernel.org/pub/scm/devel/sparse/sparse.git Q: https://patchwork.kernel.org/project/linux-sparse/list/ B: https://bugzilla.kernel.org/enter_bug.cgi?component=Sparse&product=Tools +T: git git://git.kernel.org/pub/scm/devel/sparse/sparse.git F: include/linux/compiler.h SPEAKUP CONSOLE SPEECH DRIVER @@ -20203,6 +20214,11 @@ W: http://www.stlinux.com F: Documentation/networking/device_drivers/ethernet/stmicro/ F: drivers/net/ethernet/stmicro/stmmac/ +SUN HAPPY MEAL ETHERNET DRIVER +M: Sean Anderson +S: Maintained +F: drivers/net/ethernet/sun/sunhme.* + SUN3/3X M: Sam Creasey S: Maintained @@ -20225,11 +20241,6 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/dlink/sundance.c -SUN HAPPY MEAL ETHERNET DRIVER -M: Sean Anderson -S: Maintained -F: drivers/net/ethernet/sun/sunhme.* - SUNPLUS ETHERNET DRIVER M: Wells Lu L: netdev@vger.kernel.org @@ -20251,15 +20262,6 @@ S: Maintained F: Documentation/devicetree/bindings/nvmem/sunplus,sp7021-ocotp.yaml F: drivers/nvmem/sunplus-ocotp.c -SUNPLUS USB2 PHY DRIVER -M: Vincent Shih -L: linux-usb@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml -F: drivers/phy/sunplus/Kconfig -F: drivers/phy/sunplus/Makefile -F: drivers/phy/sunplus/phy-sunplus-usb2.c - SUNPLUS PWM DRIVER M: Hammer Hsieh S: Maintained @@ -20286,6 +20288,15 @@ S: Maintained F: Documentation/devicetree/bindings/serial/sunplus,sp7021-uart.yaml F: drivers/tty/serial/sunplus-uart.c +SUNPLUS USB2 PHY DRIVER +M: Vincent Shih +L: linux-usb@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/phy/sunplus,sp7021-usb2-phy.yaml +F: drivers/phy/sunplus/Kconfig +F: drivers/phy/sunplus/Makefile +F: drivers/phy/sunplus/phy-sunplus-usb2.c + SUNPLUS WATCHDOG DRIVER M: Xiantao Hu L: linux-watchdog@vger.kernel.org @@ -20697,6 +20708,14 @@ F: include/linux/if_team.h F: include/uapi/linux/if_team.h F: tools/testing/selftests/drivers/net/team/ +TECHNICAL ADVISORY BOARD PROCESS DOCS +M: "Theodore Ts'o" +M: Greg Kroah-Hartman +L: tech-board-discuss@lists.linux-foundation.org +S: Maintained +F: Documentation/process/contribution-maturity-model.rst +F: Documentation/process/researcher-guidelines.rst + TECHNOLOGIC SYSTEMS TS-5500 PLATFORM SUPPORT M: "Savoir-faire Linux Inc." S: Maintained @@ -20776,6 +20795,14 @@ M: Thierry Reding S: Supported F: drivers/pwm/pwm-tegra.c +TEGRA QUAD SPI DRIVER +M: Thierry Reding +M: Jonathan Hunter +M: Sowjanya Komatineni +L: linux-tegra@vger.kernel.org +S: Maintained +F: drivers/spi/spi-tegra210-quad.c + TEGRA SERIAL DRIVER M: Laxman Dewangan S: Supported @@ -20786,14 +20813,6 @@ M: Laxman Dewangan S: Supported F: drivers/spi/spi-tegra* -TEGRA QUAD SPI DRIVER -M: Thierry Reding -M: Jonathan Hunter -M: Sowjanya Komatineni -L: linux-tegra@vger.kernel.org -S: Maintained -F: drivers/spi/spi-tegra210-quad.c - TEGRA VIDEO DRIVER M: Thierry Reding M: Jonathan Hunter @@ -20842,13 +20861,6 @@ S: Maintained F: Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml F: sound/soc/ti/ -TEXAS INSTRUMENTS' DAC7612 DAC DRIVER -M: Ricardo Ribalda -L: linux-iio@vger.kernel.org -S: Supported -F: Documentation/devicetree/bindings/iio/dac/ti,dac7612.yaml -F: drivers/iio/dac/ti-dac7612.c - TEXAS INSTRUMENTS DMA DRIVERS M: Peter Ujfalusi L: dmaengine@vger.kernel.org @@ -20857,10 +20869,26 @@ F: Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt F: Documentation/devicetree/bindings/dma/ti-edma.txt F: Documentation/devicetree/bindings/dma/ti/ F: drivers/dma/ti/ -X: drivers/dma/ti/cppi41.c +F: include/linux/dma/k3-psil.h F: include/linux/dma/k3-udma-glue.h F: include/linux/dma/ti-cppi5.h -F: include/linux/dma/k3-psil.h +X: drivers/dma/ti/cppi41.c + +TEXAS INSTRUMENTS TPS23861 PoE PSE DRIVER +M: Robert Marko +M: Luka Perkov +L: linux-hwmon@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/hwmon/ti,tps23861.yaml +F: Documentation/hwmon/tps23861.rst +F: drivers/hwmon/tps23861.c + +TEXAS INSTRUMENTS' DAC7612 DAC DRIVER +M: Ricardo Ribalda +L: linux-iio@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/iio/dac/ti,dac7612.yaml +F: drivers/iio/dac/ti-dac7612.c TEXAS INSTRUMENTS' SYSTEM CONTROL INTERFACE (TISCI) PROTOCOL DRIVER M: Nishanth Menon @@ -20886,15 +20914,6 @@ F: include/dt-bindings/soc/ti,sci_pm_domain.h F: include/linux/soc/ti/ti_sci_inta_msi.h F: include/linux/soc/ti/ti_sci_protocol.h -TEXAS INSTRUMENTS TPS23861 PoE PSE DRIVER -M: Robert Marko -M: Luka Perkov -L: linux-hwmon@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/hwmon/ti,tps23861.yaml -F: Documentation/hwmon/tps23861.rst -F: drivers/hwmon/tps23861.c - TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER M: Puranjay Mohan L: linux-iio@vger.kernel.org @@ -21371,8 +21390,8 @@ M: Steven Rostedt M: Masami Hiramatsu L: linux-kernel@vger.kernel.org L: linux-trace-kernel@vger.kernel.org -Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/* F: fs/tracefs/ @@ -21400,31 +21419,15 @@ TRACING OS NOISE / LATENCY TRACERS M: Steven Rostedt M: Daniel Bristot de Oliveira S: Maintained -F: kernel/trace/trace_osnoise.c +F: Documentation/trace/hwlat_detector.rst +F: Documentation/trace/osnoise-tracer.rst +F: Documentation/trace/timerlat-tracer.rst +F: arch/*/kernel/trace.c F: include/trace/events/osnoise.h F: kernel/trace/trace_hwlat.c F: kernel/trace/trace_irqsoff.c +F: kernel/trace/trace_osnoise.c F: kernel/trace/trace_sched_wakeup.c -F: Documentation/trace/osnoise-tracer.rst -F: Documentation/trace/timerlat-tracer.rst -F: Documentation/trace/hwlat_detector.rst -F: arch/*/kernel/trace.c - -Real-time Linux Analysis (RTLA) tools -M: Daniel Bristot de Oliveira -M: Steven Rostedt -L: linux-trace-devel@vger.kernel.org -S: Maintained -F: Documentation/tools/rtla/ -F: tools/tracing/rtla/ - -TECHNICAL ADVISORY BOARD PROCESS DOCS -M: "Theodore Ts'o" -M: Greg Kroah-Hartman -L: tech-board-discuss@lists.linux-foundation.org -S: Maintained -F: Documentation/process/researcher-guidelines.rst -F: Documentation/process/contribution-maturity-model.rst TRADITIONAL CHINESE DOCUMENTATION M: Hu Haowen @@ -21782,8 +21785,8 @@ USB ISP1760 DRIVER M: Rui Miguel Silva L: linux-usb@vger.kernel.org S: Maintained -F: drivers/usb/isp1760/* F: Documentation/devicetree/bindings/usb/nxp,isp1760.yaml +F: drivers/usb/isp1760/* USB LAN78XX ETHERNET DRIVER M: Woojung Huh @@ -21854,6 +21857,13 @@ L: linux-usb@vger.kernel.org S: Supported F: drivers/usb/class/usblp.c +USB QMI WWAN NETWORK DRIVER +M: Bjørn Mork +L: netdev@vger.kernel.org +S: Maintained +F: Documentation/ABI/testing/sysfs-class-net-qmi +F: drivers/net/usb/qmi_wwan.c + USB RAW GADGET DRIVER R: Andrey Konovalov L: linux-usb@vger.kernel.org @@ -21862,13 +21872,6 @@ F: Documentation/usb/raw-gadget.rst F: drivers/usb/gadget/legacy/raw_gadget.c F: include/uapi/linux/usb/raw_gadget.h -USB QMI WWAN NETWORK DRIVER -M: Bjørn Mork -L: netdev@vger.kernel.org -S: Maintained -F: Documentation/ABI/testing/sysfs-class-net-qmi -F: drivers/net/usb/qmi_wwan.c - USB RTL8150 DRIVER M: Petko Manolov L: linux-usb@vger.kernel.org @@ -22120,6 +22123,12 @@ F: drivers/vfio/mdev/ F: include/linux/mdev.h F: samples/vfio-mdev/ +VFIO MLX5 PCI DRIVER +M: Yishai Hadas +L: kvm@vger.kernel.org +S: Maintained +F: drivers/vfio/pci/mlx5/ + VFIO PCI DEVICE SPECIFIC DRIVERS R: Jason Gunthorpe R: Yishai Hadas @@ -22136,12 +22145,6 @@ L: kvm@vger.kernel.org S: Maintained F: drivers/vfio/platform/ -VFIO MLX5 PCI DRIVER -M: Yishai Hadas -L: kvm@vger.kernel.org -S: Maintained -F: drivers/vfio/pci/mlx5/ - VGA_SWITCHEROO R: Lukas Wunner S: Maintained @@ -22151,8 +22154,8 @@ F: drivers/gpu/vga/vga_switcheroo.c F: include/linux/vga_switcheroo.h VIA RHINE NETWORK DRIVER -S: Maintained M: Kevin Brace +S: Maintained F: drivers/net/ethernet/via/via-rhine.c VIA SD/MMC CARD CONTROLLER DRIVER @@ -22204,6 +22207,14 @@ S: Maintained F: drivers/media/common/videobuf2/* F: include/media/videobuf2-* +VIDTV VIRTUAL DIGITAL TV DRIVER +M: Daniel W. S. Almeida +L: linux-media@vger.kernel.org +S: Maintained +W: https://linuxtv.org +T: git git://linuxtv.org/media_tree.git +F: drivers/media/test-drivers/vidtv/* + VIMC VIRTUAL MEDIA CONTROLLER DRIVER M: Shuah Khan R: Kieran Bingham @@ -22233,6 +22244,16 @@ F: include/uapi/linux/virtio_vsock.h F: net/vmw_vsock/virtio_transport.c F: net/vmw_vsock/virtio_transport_common.c +VIRTIO BALLOON +M: "Michael S. Tsirkin" +M: David Hildenbrand +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/virtio/virtio_balloon.c +F: include/linux/balloon_compaction.h +F: include/uapi/linux/virtio_balloon.h +F: mm/balloon_compaction.c + VIRTIO BLOCK AND SCSI DRIVERS M: "Michael S. Tsirkin" M: Jason Wang @@ -22275,30 +22296,6 @@ F: include/linux/vringh.h F: include/uapi/linux/virtio_*.h F: tools/virtio/ -VISL VIRTUAL STATELESS DECODER DRIVER -M: Daniel Almeida -L: linux-media@vger.kernel.org -S: Supported -F: drivers/media/test-drivers/visl - -IFCVF VIRTIO DATA PATH ACCELERATOR -R: Zhu Lingshan -F: drivers/vdpa/ifcvf/ - -SNET DPU VIRTIO DATA PATH ACCELERATOR -R: Alvaro Karsz -F: drivers/vdpa/solidrun/ - -VIRTIO BALLOON -M: "Michael S. Tsirkin" -M: David Hildenbrand -L: virtualization@lists.linux-foundation.org -S: Maintained -F: drivers/virtio/virtio_balloon.c -F: include/uapi/linux/virtio_balloon.h -F: include/linux/balloon_compaction.h -F: mm/balloon_compaction.c - VIRTIO CRYPTO DRIVER M: Gonglei L: virtualization@lists.linux-foundation.org @@ -22359,11 +22356,20 @@ L: virtualization@lists.linux-foundation.org L: netdev@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git -F: kernel/vhost_task.c F: drivers/vhost/ F: include/linux/sched/vhost_task.h F: include/linux/vhost_iotlb.h F: include/uapi/linux/vhost.h +F: kernel/vhost_task.c + +VIRTIO I2C DRIVER +M: Conghui Chen +M: Viresh Kumar +L: linux-i2c@vger.kernel.org +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/i2c/busses/i2c-virtio.c +F: include/uapi/linux/virtio_i2c.h VIRTIO INPUT DRIVER M: Gerd Hoffmann @@ -22386,6 +22392,13 @@ W: https://virtio-mem.gitlab.io/ F: drivers/virtio/virtio_mem.c F: include/uapi/linux/virtio_mem.h +VIRTIO PMEM DRIVER +M: Pankaj Gupta +L: virtualization@lists.linux-foundation.org +S: Maintained +F: drivers/nvdimm/nd_virtio.c +F: drivers/nvdimm/virtio_pmem.c + VIRTIO SOUND DRIVER M: Anton Yakovlev M: "Michael S. Tsirkin" @@ -22395,22 +22408,6 @@ S: Maintained F: include/uapi/linux/virtio_snd.h F: sound/virtio/* -VIRTIO I2C DRIVER -M: Conghui Chen -M: Viresh Kumar -L: linux-i2c@vger.kernel.org -L: virtualization@lists.linux-foundation.org -S: Maintained -F: drivers/i2c/busses/i2c-virtio.c -F: include/uapi/linux/virtio_i2c.h - -VIRTIO PMEM DRIVER -M: Pankaj Gupta -L: virtualization@lists.linux-foundation.org -S: Maintained -F: drivers/nvdimm/virtio_pmem.c -F: drivers/nvdimm/nd_virtio.c - VIRTUAL BOX GUEST DEVICE DRIVER M: Hans de Goede M: Arnd Bergmann @@ -22432,6 +22429,12 @@ S: Maintained F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h +VISL VIRTUAL STATELESS DECODER DRIVER +M: Daniel Almeida +L: linux-media@vger.kernel.org +S: Supported +F: drivers/media/test-drivers/visl + VIVID VIRTUAL VIDEO DRIVER M: Hans Verkuil L: linux-media@vger.kernel.org @@ -22440,14 +22443,6 @@ W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git F: drivers/media/test-drivers/vivid/* -VIDTV VIRTUAL DIGITAL TV DRIVER -M: Daniel W. S. Almeida -L: linux-media@vger.kernel.org -S: Maintained -W: https://linuxtv.org -T: git git://linuxtv.org/media_tree.git -F: drivers/media/test-drivers/vidtv/* - VLYNQ BUS M: Florian Fainelli L: openwrt-devel@lists.openwrt.org (subscribers-only) @@ -22455,16 +22450,6 @@ S: Maintained F: drivers/vlynq/vlynq.c F: include/linux/vlynq.h -VME SUBSYSTEM -M: Martyn Welch -M: Manohar Vanga -M: Greg Kroah-Hartman -L: linux-kernel@vger.kernel.org -S: Odd fixes -T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git -F: Documentation/driver-api/vme.rst -F: drivers/staging/vme_user/ - VM SOCKETS (AF_VSOCK) M: Stefano Garzarella L: virtualization@lists.linux-foundation.org @@ -22478,6 +22463,28 @@ F: include/uapi/linux/vsockmon.h F: net/vmw_vsock/ F: tools/testing/vsock/ +VMALLOC +M: Andrew Morton +R: Uladzislau Rezki +R: Christoph Hellwig +R: Lorenzo Stoakes +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/linux/vmalloc.h +F: mm/vmalloc.c + +VME SUBSYSTEM +M: Martyn Welch +M: Manohar Vanga +M: Greg Kroah-Hartman +L: linux-kernel@vger.kernel.org +S: Odd fixes +T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git +F: Documentation/driver-api/vme.rst +F: drivers/staging/vme_user/ + VMWARE BALLOON DRIVER M: Nadav Amit R: VMware PV-Drivers Reviewers @@ -22659,9 +22666,9 @@ F: drivers/input/tablet/wacom_serial4.c WANGXUN ETHERNET DRIVER M: Jiawen Wu M: Mengyuan Lou -W: https://www.net-swift.com L: netdev@vger.kernel.org S: Maintained +W: https://www.net-swift.com F: Documentation/networking/device_drivers/ethernet/wangxun/* F: drivers/net/ethernet/wangxun/ @@ -22676,8 +22683,8 @@ F: Documentation/devicetree/bindings/watchdog/ F: Documentation/watchdog/ F: drivers/watchdog/ F: include/linux/watchdog.h -F: include/uapi/linux/watchdog.h F: include/trace/events/watchdog.h +F: include/uapi/linux/watchdog.h WHISKEYCOVE PMIC GPIO DRIVER M: Kuppuswamy Sathyanarayanan @@ -22834,8 +22841,8 @@ R: "H. Peter Anvin" L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core -F: Documentation/devicetree/bindings/x86/ F: Documentation/arch/x86/ +F: Documentation/devicetree/bindings/x86/ F: arch/x86/ X86 ENTRY CODE @@ -22966,6 +22973,8 @@ M: John Fastabend L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Supported +F: drivers/net/ethernet/*/*/*/*/*xdp* +F: drivers/net/ethernet/*/*/*xdp* F: include/net/xdp.h F: include/net/xdp_priv.h F: include/trace/events/xdp.h @@ -22973,10 +22982,8 @@ F: kernel/bpf/cpumap.c F: kernel/bpf/devmap.c F: net/core/xdp.c F: samples/bpf/xdp* -F: tools/testing/selftests/bpf/*xdp* F: tools/testing/selftests/bpf/*/*xdp* -F: drivers/net/ethernet/*/*/*/*/*xdp* -F: drivers/net/ethernet/*/*/*xdp* +F: tools/testing/selftests/bpf/*xdp* K: (?:\b|_)xdp(?:\b|_) XDP SOCKETS (AF_XDP) @@ -22988,11 +22995,11 @@ L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained F: Documentation/networking/af_xdp.rst +F: include/net/netns/xdp.h F: include/net/xdp_sock* F: include/net/xsk_buff_pool.h F: include/uapi/linux/if_xdp.h F: include/uapi/linux/xdp_diag.h -F: include/net/netns/xdp.h F: net/xdp/ F: tools/testing/selftests/bpf/*xsk* @@ -23094,11 +23101,11 @@ F: include/xen/arm/swiotlb-xen.h F: include/xen/swiotlb-xen.h XFS FILESYSTEM -C: irc://irc.oftc.net/xfs M: Darrick J. Wong L: linux-xfs@vger.kernel.org S: Supported W: http://xfs.org/ +C: irc://irc.oftc.net/xfs T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git F: Documentation/ABI/testing/sysfs-fs-xfs F: Documentation/admin-guide/xfs.rst @@ -23128,16 +23135,28 @@ S: Maintained F: Documentation/devicetree/bindings/net/can/xilinx,can.yaml F: drivers/net/can/xilinx_can.c +XILINX EVENT MANAGEMENT DRIVER +M: Abhyuday Godhasara +S: Maintained +F: drivers/soc/xilinx/xlnx_event_manager.c +F: include/linux/firmware/xlnx-event-manager.h + XILINX GPIO DRIVER M: Shubhrajyoti Datta R: Srinivas Neeli R: Michal Simek S: Maintained -F: Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml F: Documentation/devicetree/bindings/gpio/gpio-zynq.yaml +F: Documentation/devicetree/bindings/gpio/xlnx,gpio-xilinx.yaml F: drivers/gpio/gpio-xilinx.c F: drivers/gpio/gpio-zynq.c +XILINX PWM DRIVER +M: Sean Anderson +S: Maintained +F: drivers/pwm/pwm-xilinx.c +F: include/clocksource/timer-xilinx.h + XILINX SD-FEC IP CORES M: Derek Kiernan M: Dragan Cvetic @@ -23149,12 +23168,6 @@ F: drivers/misc/Makefile F: drivers/misc/xilinx_sdfec.c F: include/uapi/misc/xilinx_sdfec.h -XILINX PWM DRIVER -M: Sean Anderson -S: Maintained -F: drivers/pwm/pwm-xilinx.c -F: include/clocksource/timer-xilinx.h - XILINX UARTLITE SERIAL DRIVER M: Peter Korsgaard L: linux-serial@vger.kernel.org @@ -23220,12 +23233,6 @@ M: Harsha S: Maintained F: drivers/crypto/xilinx/zynqmp-sha.c -XILINX EVENT MANAGEMENT DRIVER -M: Abhyuday Godhasara -S: Maintained -F: drivers/soc/xilinx/xlnx_event_manager.c -F: include/linux/firmware/xlnx-event-manager.h - XILLYBUS DRIVER M: Eli Billauer L: linux-kernel@vger.kernel.org @@ -23273,6 +23280,13 @@ S: Maintained F: Documentation/input/devices/yealink.rst F: drivers/input/misc/yealink.* +Z3FOLD COMPRESSED PAGE ALLOCATOR +M: Vitaly Wool +R: Miaohe Lin +L: linux-mm@kvack.org +S: Maintained +F: mm/z3fold.c + Z8530 DRIVER FOR AX.25 M: Joerg Reuter L: linux-hams@vger.kernel.org @@ -23290,13 +23304,6 @@ L: linux-mm@kvack.org S: Maintained F: mm/zbud.c -Z3FOLD COMPRESSED PAGE ALLOCATOR -M: Vitaly Wool -R: Miaohe Lin -L: linux-mm@kvack.org -S: Maintained -F: mm/z3fold.c - ZD1211RW WIRELESS DRIVER M: Ulrich Kunitz L: linux-wireless@vger.kernel.org @@ -23383,10 +23390,10 @@ M: Nick Terrell S: Maintained B: https://github.com/facebook/zstd/issues T: git https://github.com/terrelln/linux.git +F: crypto/zstd.c F: include/linux/zstd* -F: lib/zstd/ F: lib/decompress_unzstd.c -F: crypto/zstd.c +F: lib/zstd/ N: zstd K: zstd @@ -23398,13 +23405,6 @@ L: linux-mm@kvack.org S: Maintained F: mm/zswap.c -NXP BLUETOOTH WIRELESS DRIVERS -M: Amitkumar Karwar -M: Neeraj Kale -S: Maintained -F: Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml -F: drivers/bluetooth/btnxpuart.c - THE REST M: Linus Torvalds L: linux-kernel@vger.kernel.org -- GitLab From ad721bc919edfd8b4b06977458a412011e2f0c50 Mon Sep 17 00:00:00 2001 From: Aidan MacDonald Date: Tue, 9 May 2023 13:51:34 +0100 Subject: [PATCH 4744/5631] ASoC: jz4740-i2s: Make I2S divider calculations more robust When the CPU supplies bit/frame clocks, the system clock (clk_i2s) is divided to produce the bit clock. This is a simple 1/N divider with a fairly limited range, so for a given system clock frequency only a few sample rates can be produced. Usually a wider range of sample rates is supported by varying the system clock frequency. The old calculation method was not very robust and could easily produce the wrong clock rate, especially with non-standard rates. For example, if the system clock is 1.99x the target bit clock rate, the divider would be calculated as 1 instead of the more accurate 2. Instead, use a more accurate method that considers two adjacent divider settings and selects the one that produces the least error versus the requested rate. If the error is 5% or higher then the rate setting is rejected to prevent garbled audio. Skip divider calculation when the codec is supplying both the bit and frame clock; in that case, the divider outputs are unused and we don't want to constrain the sample rate. Signed-off-by: Aidan MacDonald regmap, JZ_REG_AIC_CTRL, &ctrl); - - div = clk_get_rate(i2s->clk_i2s) / (64 * params_rate(params)); + regmap_read(i2s->regmap, JZ_REG_AIC_CONF, &conf); switch (params_format(params)) { case SNDRV_PCM_FORMAT_S8: @@ -258,11 +288,27 @@ static int jz4740_i2s_hw_params(struct snd_pcm_substream *substream, ctrl &= ~JZ_AIC_CTRL_MONO_TO_STEREO; div_field = i2s->field_i2sdiv_playback; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_playback.msb, + i2s->soc_info->field_i2sdiv_playback.lsb); } else { ctrl &= ~JZ_AIC_CTRL_INPUT_SAMPLE_SIZE; ctrl |= FIELD_PREP(JZ_AIC_CTRL_INPUT_SAMPLE_SIZE, sample_size); div_field = i2s->field_i2sdiv_capture; + i2sdiv_max = GENMASK(i2s->soc_info->field_i2sdiv_capture.msb, + i2s->soc_info->field_i2sdiv_capture.lsb); + } + + /* + * Only calculate I2SDIV if we're supplying the bit or frame clock. + * If the codec is supplying both clocks then the divider output is + * unused, and we don't want it to limit the allowed sample rates. + */ + if (conf & (JZ_AIC_CONF_BIT_CLK_MASTER | JZ_AIC_CONF_SYNC_CLK_MASTER)) { + div = jz4740_i2s_get_i2sdiv(clk_get_rate(i2s->clk_i2s), + params_rate(params), i2sdiv_max); + if (div < 0) + return div; } regmap_write(i2s->regmap, JZ_REG_AIC_CTRL, ctrl); -- GitLab From efb2bfd7b3d210c479b9361c176d7426e5eb8663 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Povi=C5=A1er?= Date: Tue, 9 May 2023 17:34:12 +0200 Subject: [PATCH 4745/5631] ASoC: dt-bindings: Adjust #sound-dai-cells on TI's single-DAI codecs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A bunch of TI's codecs have binding schemas which force #sound-dai-cells to one despite those codecs only having a single DAI. Allow for bindings with zero DAI cells and deprecate the former non-zero value. Signed-off-by: Martin Povišer ; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -72,7 +74,7 @@ examples: codec: codec@4c { compatible = "ti,tas2562"; reg = <0x4c>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; shutdown-gpios = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas2770.yaml b/Documentation/devicetree/bindings/sound/tas2770.yaml index 26088adb9dc2..8908bf1122e9 100644 --- a/Documentation/devicetree/bindings/sound/tas2770.yaml +++ b/Documentation/devicetree/bindings/sound/tas2770.yaml @@ -57,7 +57,9 @@ properties: - 1 # Falling edge '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -74,7 +76,7 @@ examples: codec: codec@41 { compatible = "ti,tas2770"; reg = <0x41>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpio = <&gpio1 15 0>; diff --git a/Documentation/devicetree/bindings/sound/tas27xx.yaml b/Documentation/devicetree/bindings/sound/tas27xx.yaml index 8cba01316855..a876545ec87d 100644 --- a/Documentation/devicetree/bindings/sound/tas27xx.yaml +++ b/Documentation/devicetree/bindings/sound/tas27xx.yaml @@ -50,7 +50,9 @@ properties: description: TDM TX voltage sense time slot. '#sound-dai-cells': - const: 1 + # The codec has a single DAI, the #sound-dai-cells=<1>; case is left in for backward + # compatibility but is deprecated. + enum: [0, 1] required: - compatible @@ -67,7 +69,7 @@ examples: codec: codec@38 { compatible = "ti,tas2764"; reg = <0x38>; - #sound-dai-cells = <1>; + #sound-dai-cells = <0>; interrupt-parent = <&gpio1>; interrupts = <14>; reset-gpios = <&gpio1 15 0>; -- GitLab From 4c329f5da7cfa366bacfda1328a025dd38951317 Mon Sep 17 00:00:00 2001 From: Vijaya Krishna Nivarthi Date: Tue, 9 May 2023 15:31:36 +0530 Subject: [PATCH 4746/5631] spi: spi-geni-qcom: Select FIFO mode for chip select Spi geni driver switches between FIFO and DMA modes based on xfer length. FIFO mode relies on M_CMD_DONE_EN interrupt for completion while DMA mode relies on XX_DMA_DONE. During dynamic switching, if FIFO mode is chosen, FIFO related interrupts are enabled and DMA related interrupts are disabled. And viceversa. Chip select shares M_CMD_DONE_EN interrupt with FIFO to check completion. Now, if a chip select operation is preceded by a DMA xfer, M_CMD_DONE_EN interrupt would have been disabled and hence it will never receive one resulting in timeout. For chip select, in addition to setting the xfer mode to FIFO, select_mode() to FIFO so that required interrupts are enabled. Fixes: e5f0dfa78ac7 ("spi: spi-geni-qcom: Add support for SE DMA mode") Suggested-by: Praveen Talari cs_flag = set_flag; /* set xfer_mode to FIFO to complete cs_done in isr */ mas->cur_xfer_mode = GENI_SE_FIFO; + geni_se_select_mode(se, mas->cur_xfer_mode); + reinit_completion(&mas->cs_done); if (set_flag) geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0); -- GitLab From 5bca1d081f44c9443e61841842ce4e9179d327b6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 9 May 2023 17:31:31 +0000 Subject: [PATCH 4747/5631] net: datagram: fix data-races in datagram_poll() datagram_poll() runs locklessly, we should add READ_ONCE() annotations while reading sk->sk_err, sk->sk_shutdown and sk->sk_state. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230509173131.3263780-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/core/datagram.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/net/core/datagram.c b/net/core/datagram.c index 5662dff3d381..176eb5834746 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -807,18 +807,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) + if (READ_ONCE(sk->sk_err) || + !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -827,10 +830,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* Connection-based need to check for termination and startup */ if (connection_based(sk)) { - if (sk->sk_state == TCP_CLOSE) + int state = READ_ONCE(sk->sk_state); + + if (state == TCP_CLOSE) mask |= EPOLLHUP; /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) + if (state == TCP_SYN_SENT) return mask; } -- GitLab From 679ed006d416ea0cecfe24a99d365d1dea69c683 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 9 May 2023 17:34:55 -0700 Subject: [PATCH 4748/5631] af_unix: Fix a data race of sk->sk_receive_queue->qlen. KCSAN found a data race of sk->sk_receive_queue->qlen where recvmsg() updates qlen under the queue lock and sendmsg() checks qlen under unix_state_sock(), not the queue lock, so the reader side needs READ_ONCE(). BUG: KCSAN: data-race in __skb_try_recv_from_queue / unix_wait_for_peer write (marked) to 0xffff888019fe7c68 of 4 bytes by task 49792 on cpu 0: __skb_unlink include/linux/skbuff.h:2347 [inline] __skb_try_recv_from_queue+0x3de/0x470 net/core/datagram.c:197 __skb_try_recv_datagram+0xf7/0x390 net/core/datagram.c:263 __unix_dgram_recvmsg+0x109/0x8a0 net/unix/af_unix.c:2452 unix_dgram_recvmsg+0x94/0xa0 net/unix/af_unix.c:2549 sock_recvmsg_nosec net/socket.c:1019 [inline] ____sys_recvmsg+0x3a3/0x3b0 net/socket.c:2720 ___sys_recvmsg+0xc8/0x150 net/socket.c:2764 do_recvmmsg+0x182/0x560 net/socket.c:2858 __sys_recvmmsg net/socket.c:2937 [inline] __do_sys_recvmmsg net/socket.c:2960 [inline] __se_sys_recvmmsg net/socket.c:2953 [inline] __x64_sys_recvmmsg+0x153/0x170 net/socket.c:2953 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff888019fe7c68 of 4 bytes by task 49793 on cpu 1: skb_queue_len include/linux/skbuff.h:2127 [inline] unix_recvq_full net/unix/af_unix.c:229 [inline] unix_wait_for_peer+0x154/0x1a0 net/unix/af_unix.c:1445 unix_dgram_sendmsg+0x13bc/0x14b0 net/unix/af_unix.c:2048 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg+0x148/0x160 net/socket.c:747 ____sys_sendmsg+0x20e/0x620 net/socket.c:2503 ___sys_sendmsg+0xc6/0x140 net/socket.c:2557 __sys_sendmmsg+0x11d/0x370 net/socket.c:2643 __do_sys_sendmmsg net/socket.c:2672 [inline] __se_sys_sendmmsg net/socket.c:2669 [inline] __x64_sys_sendmmsg+0x58/0x70 net/socket.c:2669 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x0000000b -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 49793 Comm: syz-executor.0 Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Michal Kubiak Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fb31e8a4409e..08102e728b15 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1442,7 +1442,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - unix_recvq_full(other); + unix_recvq_full_lockless(other); unix_state_unlock(other); -- GitLab From e1d09c2c2f5793474556b60f83900e088d0d366d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Tue, 9 May 2023 17:34:56 -0700 Subject: [PATCH 4749/5631] af_unix: Fix data races around sk->sk_shutdown. KCSAN found a data race around sk->sk_shutdown where unix_release_sock() and unix_shutdown() update it under unix_state_lock(), OTOH unix_poll() and unix_dgram_poll() read it locklessly. We need to annotate the writes and reads with WRITE_ONCE() and READ_ONCE(). BUG: KCSAN: data-race in unix_poll / unix_release_sock write to 0xffff88800d0f8aec of 1 bytes by task 264 on cpu 0: unix_release_sock+0x75c/0x910 net/unix/af_unix.c:631 unix_release+0x59/0x80 net/unix/af_unix.c:1042 __sock_release+0x7d/0x170 net/socket.c:653 sock_close+0x19/0x30 net/socket.c:1397 __fput+0x179/0x5e0 fs/file_table.c:321 ____fput+0x15/0x20 fs/file_table.c:349 task_work_run+0x116/0x1a0 kernel/task_work.c:179 resume_user_mode_work include/linux/resume_user_mode.h:49 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x174/0x180 kernel/entry/common.c:204 __syscall_exit_to_user_mode_work kernel/entry/common.c:286 [inline] syscall_exit_to_user_mode+0x1a/0x30 kernel/entry/common.c:297 do_syscall_64+0x4b/0x90 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x72/0xdc read to 0xffff88800d0f8aec of 1 bytes by task 222 on cpu 1: unix_poll+0xa3/0x2a0 net/unix/af_unix.c:3170 sock_poll+0xcf/0x2b0 net/socket.c:1385 vfs_poll include/linux/poll.h:88 [inline] ep_item_poll.isra.0+0x78/0xc0 fs/eventpoll.c:855 ep_send_events fs/eventpoll.c:1694 [inline] ep_poll fs/eventpoll.c:1823 [inline] do_epoll_wait+0x6c4/0xea0 fs/eventpoll.c:2258 __do_sys_epoll_wait fs/eventpoll.c:2270 [inline] __se_sys_epoll_wait fs/eventpoll.c:2265 [inline] __x64_sys_epoll_wait+0xcc/0x190 fs/eventpoll.c:2265 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3b/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x72/0xdc value changed: 0x00 -> 0x03 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 222 Comm: dbus-broker Not tainted 6.3.0-rc7-02330-gca6270c12e20 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Fixes: 3c73419c09a5 ("af_unix: fix 'poll for write'/ connected DGRAM sockets") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: Michal Kubiak Signed-off-by: Jakub Kicinski --- net/unix/af_unix.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 08102e728b15..cc695c9f09ec 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -603,7 +603,7 @@ static void unix_release_sock(struct sock *sk, int embrion) /* Clear state */ unix_state_lock(sk); sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); path = u->path; u->path.dentry = NULL; u->path.mnt = NULL; @@ -628,7 +628,7 @@ static void unix_release_sock(struct sock *sk, int embrion) if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); /* No more writes */ - skpair->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); @@ -3008,7 +3008,7 @@ static int unix_shutdown(struct socket *sock, int mode) ++mode; unix_state_lock(sk); - sk->sk_shutdown |= mode; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode); other = unix_peer(sk); if (other) sock_hold(other); @@ -3028,7 +3028,7 @@ static int unix_shutdown(struct socket *sock, int mode) if (mode&SEND_SHUTDOWN) peer_mode |= RCV_SHUTDOWN; unix_state_lock(other); - other->sk_shutdown |= peer_mode; + WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode); unix_state_unlock(other); other->sk_state_change(other); if (peer_mode == SHUTDOWN_MASK) @@ -3160,16 +3160,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ @@ -3203,9 +3205,11 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int writable; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (READ_ONCE(sk->sk_err) || @@ -3213,9 +3217,9 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ -- GitLab From 476ac50fc30540e29191615a26aaf5f9dee91c49 Mon Sep 17 00:00:00 2001 From: Thong Thai Date: Mon, 1 May 2023 11:04:36 -0400 Subject: [PATCH 4750/5631] drm/amdgpu/nv: update VCN 3 max HEVC encoding resolution Update the maximum resolution reported for HEVC encoding on VCN 3 devices to reflect its 8K encoding capability. v2: Also update the max height for H.264 encoding to match spec. (Ruijing) Signed-off-by: Thong Thai Reviewed-by: Ruijing Dong Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/nv.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 98c826f1f89b..0fb6013441f0 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -98,6 +98,16 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = }; /* Sienna Cichlid */ +static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, +}; + +static const struct amdgpu_video_codecs sc_video_codecs_encode = { + .codec_count = ARRAY_SIZE(sc_video_codecs_encode_array), + .codec_array = sc_video_codecs_encode_array, +}; + static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] = { {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)}, @@ -136,8 +146,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = /* SRIOV Sienna Cichlid, not const since data is controlled by host */ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, }; static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = @@ -237,12 +247,12 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, } else { if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) { if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn1; } else { if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn0; } @@ -251,14 +261,14 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, case IP_VERSION(3, 0, 16): case IP_VERSION(3, 0, 2): if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &sc_video_codecs_decode_vcn0; return 0; case IP_VERSION(3, 1, 1): case IP_VERSION(3, 1, 2): if (encode) - *codecs = &nv_video_codecs_encode; + *codecs = &sc_video_codecs_encode; else *codecs = &yc_video_codecs_decode; return 0; -- GitLab From af7828fbceed4f9e503034111066a0adef3db383 Mon Sep 17 00:00:00 2001 From: Yifan Zhang Date: Thu, 27 Apr 2023 14:01:05 +0800 Subject: [PATCH 4751/5631] drm/amdgpu: set gfx9 onwards APU atomics support to be true APUs w/ gfx9 onwards doesn't reply on PCIe atomics, rather it is internal path w/ native atomic support. Set have_atomics_support to true. Signed-off-by: Yifan Zhang Reviewed-by: Lang Yu Acked-by: Felix Kuehling Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 981a9cfb63b5..e348a62ec0ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3757,6 +3757,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *) adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_support_flags == (PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64); + /* APUs w/ gfx9 onwards doesn't reply on PCIe atomics, rather it is a + * internal path natively support atomics, set have_atomics_support to true. + */ + else if ((adev->flags & AMD_IS_APU) && + (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))) + adev->have_atomics_support = true; else adev->have_atomics_support = !pci_enable_atomic_ops_to_root(adev->pdev, -- GitLab From 58d9b9a14b47c2a3da6effcbb01607ad7edc0275 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Fri, 5 May 2023 13:20:11 +0800 Subject: [PATCH 4752/5631] drm/amd/pm: parse pp_handle under appropriate conditions amdgpu_dpm_is_overdrive_supported is a common API across all asics, so we should cast pp_handle into correct structure under different power frameworks. v2: using return directly to simplify code v3: SI asic does not carry od_enabled member in pp_handle, and update Fixes tag Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2541 Fixes: eb4900aa4c49 ("drm/amdgpu: Fix kernel NULL pointer dereference in dpm functions") Suggested-by: Mario Limonciello Signed-off-by: Guchun Chen Reviewed-by: Mario Limonciello Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/amdgpu_dpm.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 300e156b924f..86246f69dbe1 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -1460,15 +1460,21 @@ int amdgpu_dpm_get_smu_prv_buf_details(struct amdgpu_device *adev, int amdgpu_dpm_is_overdrive_supported(struct amdgpu_device *adev) { - struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; - struct smu_context *smu = adev->powerplay.pp_handle; + if (is_support_sw_smu(adev)) { + struct smu_context *smu = adev->powerplay.pp_handle; + + return (smu->od_enabled || smu->is_apu); + } else { + struct pp_hwmgr *hwmgr; - if ((is_support_sw_smu(adev) && smu->od_enabled) || - (is_support_sw_smu(adev) && smu->is_apu) || - (!is_support_sw_smu(adev) && hwmgr->od_enabled)) - return true; + /* SI asic does not carry od_enabled */ + if (adev->family == AMDGPU_FAMILY_SI) + return false; - return false; + hwmgr = (struct pp_hwmgr *)adev->powerplay.pp_handle; + + return hwmgr->od_enabled; + } } int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev, -- GitLab From f57fa0f23d9707747272b0d09af8b93b19cf8ee4 Mon Sep 17 00:00:00 2001 From: Leo Chen Date: Wed, 26 Apr 2023 16:02:28 -0400 Subject: [PATCH 4753/5631] drm/amd/display: Add symclk workaround during disable link output [Why & How] This is originally a change (9c75891f) in DCN32 because of the lack of interface to set TX while keeping symclk on. Adding this workaround to DCN314 will resolve the current issue. Fixes: 9c75891feef0 ("drm/amd/display: rework recent update PHY state commit") Reviewed-by: Nicholas Kazlauskas Acked-by: Alex Hung Signed-off-by: Leo Chen Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../drm/amd/display/dc/dcn314/dcn314_hwseq.c | 65 +++++++++++++++++++ .../drm/amd/display/dc/dcn314/dcn314_hwseq.h | 2 + .../drm/amd/display/dc/dcn314/dcn314_init.c | 2 +- 3 files changed, 68 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 40c488b26901..cc3fe9cac5b5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -423,3 +423,68 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool PERF_TRACE(); } +static void apply_symclk_on_tx_off_wa(struct dc_link *link) +{ + /* There are use cases where SYMCLK is referenced by OTG. For instance + * for TMDS signal, OTG relies SYMCLK even if TX video output is off. + * However current link interface will power off PHY when disabling link + * output. This will turn off SYMCLK generated by PHY. The workaround is + * to identify such case where SYMCLK is still in use by OTG when we + * power off PHY. When this is detected, we will temporarily power PHY + * back on and move PHY's SYMCLK state to SYMCLK_ON_TX_OFF by calling + * program_pix_clk interface. When OTG is disabled, we will then power + * off PHY by calling disable link output again. + * + * In future dcn generations, we plan to rework transmitter control + * interface so that we could have an option to set SYMCLK ON TX OFF + * state in one step without this workaround + */ + + struct dc *dc = link->ctx->dc; + struct pipe_ctx *pipe_ctx = NULL; + uint8_t i; + + if (link->phy_state.symclk_ref_cnts.otg > 0) { + for (i = 0; i < MAX_PIPES; i++) { + pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + if (pipe_ctx->stream && pipe_ctx->stream->link == link && pipe_ctx->top_pipe == NULL) { + pipe_ctx->clock_source->funcs->program_pix_clk( + pipe_ctx->clock_source, + &pipe_ctx->stream_res.pix_clk_params, + dc->link_srv->dp_get_encoding_format( + &pipe_ctx->link_config.dp_link_settings), + &pipe_ctx->pll_settings); + link->phy_state.symclk_state = SYMCLK_ON_TX_OFF; + break; + } + } + } +} + +void dcn314_disable_link_output(struct dc_link *link, + const struct link_resource *link_res, + enum signal_type signal) +{ + struct dc *dc = link->ctx->dc; + const struct link_hwss *link_hwss = get_link_hwss(link, link_res); + struct dmcu *dmcu = dc->res_pool->dmcu; + + if (signal == SIGNAL_TYPE_EDP && + link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + else if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->lock_phy(dmcu); + + link_hwss->disable_link_output(link, link_res, signal); + link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF; + /* + * Add the logic to extract BOTH power up and power down sequences + * from enable/disable link output and only call edp panel control + * in enable_link_dp and disable_link_dp once. + */ + if (dmcu != NULL && dmcu->funcs->lock_phy) + dmcu->funcs->unlock_phy(dmcu); + dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY); + + apply_symclk_on_tx_off_wa(link); +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h index c786d5e6a428..6d0b62503caa 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h @@ -45,4 +45,6 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on); +void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal); + #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index 5267e901a35c..a588f46b166f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -105,7 +105,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = { .enable_lvds_link_output = dce110_enable_lvds_link_output, .enable_tmds_link_output = dce110_enable_tmds_link_output, .enable_dp_link_output = dce110_enable_dp_link_output, - .disable_link_output = dce110_disable_link_output, + .disable_link_output = dcn314_disable_link_output, .z10_restore = dcn31_z10_restore, .z10_save_init = dcn31_z10_save_init, .set_disp_pattern_generator = dcn30_set_disp_pattern_generator, -- GitLab From b504f99ccaa64da364443431e388ecf30b604e38 Mon Sep 17 00:00:00 2001 From: Alvin Lee Date: Thu, 27 Apr 2023 15:10:13 -0400 Subject: [PATCH 4754/5631] drm/amd/display: Enforce 60us prefetch for 200Mhz DCFCLK modes [Description] - Due to bandwidth / arbitration issues at 200Mhz DCFCLK, we want to enforce minimum 60us of prefetch to avoid intermittent underflow issues - Since 60us prefetch is already enforced for UCLK DPM0, and many DCFCLK's > 200Mhz are mapped to UCLK DPM1, in theory there should not be any UCLK DPM regressions by enforcing greater prefetch Reviewed-by: Nevenko Stupar Reviewed-by: Jun Lei Cc: Mario Limonciello Cc: Alex Deucher Cc: stable@vger.kernel.org Acked-by: Alex Hung Signed-off-by: Alvin Lee Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c | 5 +++-- .../gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 13c7e7394b1c..d75248b6cae9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -810,7 +810,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || + v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], @@ -3310,7 +3311,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index 500b3dd6052d..d98e36a9a09c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -53,6 +53,7 @@ #define BPP_BLENDED_PIPE 0xffffffff #define MEM_STROBE_FREQ_MHZ 1600 +#define MIN_DCFCLK_FREQ_MHZ 200 #define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 struct display_mode_lib; -- GitLab From 720b47229a5b24061d1c2e29ddb6043a59178d79 Mon Sep 17 00:00:00 2001 From: Horatio Zhang Date: Thu, 4 May 2023 01:46:12 -0400 Subject: [PATCH 4755/5631] drm/amdgpu: drop gfx_v11_0_cp_ecc_error_irq_funcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The gfx.cp_ecc_error_irq is retired in gfx11. In gfx_v11_0_hw_fini still use amdgpu_irq_put to disable this interrupt, which caused the call trace in this function. [ 102.873958] Call Trace: [ 102.873959] [ 102.873961] gfx_v11_0_hw_fini+0x23/0x1e0 [amdgpu] [ 102.874019] gfx_v11_0_suspend+0xe/0x20 [amdgpu] [ 102.874072] amdgpu_device_ip_suspend_phase2+0x240/0x460 [amdgpu] [ 102.874122] amdgpu_device_ip_suspend+0x3d/0x80 [amdgpu] [ 102.874172] amdgpu_device_pre_asic_reset+0xd9/0x490 [amdgpu] [ 102.874223] amdgpu_device_gpu_recover.cold+0x548/0xce6 [amdgpu] [ 102.874321] amdgpu_debugfs_reset_work+0x4c/0x70 [amdgpu] [ 102.874375] process_one_work+0x21f/0x3f0 [ 102.874377] worker_thread+0x200/0x3e0 [ 102.874378] ? process_one_work+0x3f0/0x3f0 [ 102.874379] kthread+0xfd/0x130 [ 102.874380] ? kthread_complete_and_exit+0x20/0x20 [ 102.874381] ret_from_fork+0x22/0x30 v2: - Handle umc and gfx ras cases in separated patch - Retired the gfx_v11_0_cp_ecc_error_irq_funcs in gfx11 v3: - Improve the subject and code comments - Add judgment on gfx11 in the function of amdgpu_gfx_ras_late_init v4: - Drop the define of CP_ME1_PIPE_INST_ADDR_INTERVAL and SET_ECC_ME_PIPE_STATE which using in gfx_v11_0_set_cp_ecc_error_state - Check cp_ecc_error_irq.funcs rather than ip version for a more sustainable life v5: - Simplify judgment conditions Signed-off-by: Horatio Zhang Reviewed-by: Hawking Zhang Acked-by: Christian König Reviewed-by: Guchun Chen Reviewed-by: Feifei Xu Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 8 +++-- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 46 ------------------------- 2 files changed, 5 insertions(+), 49 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 9d3a0542c996..f3f541ba0aca 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -687,9 +687,11 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r if (r) return r; - r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0); - if (r) - goto late_fini; + if (adev->gfx.cp_ecc_error_irq.funcs) { + r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (r) + goto late_fini; + } } else { amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index a9da0486467a..f5c376276984 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -1315,13 +1315,6 @@ static int gfx_v11_0_sw_init(void *handle) if (r) return r; - /* ECC error */ - r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP, - GFX_11_0_0__SRCID__CP_ECC_ERROR, - &adev->gfx.cp_ecc_error_irq); - if (r) - return r; - /* FED error */ r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GFX, GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT, @@ -4444,7 +4437,6 @@ static int gfx_v11_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int r; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); @@ -5897,36 +5889,6 @@ static void gfx_v11_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev } } -#define CP_ME1_PIPE_INST_ADDR_INTERVAL 0x1 -#define SET_ECC_ME_PIPE_STATE(reg_addr, state) \ - do { \ - uint32_t tmp = RREG32_SOC15_IP(GC, reg_addr); \ - tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, state); \ - WREG32_SOC15_IP(GC, reg_addr, tmp); \ - } while (0) - -static int gfx_v11_0_set_cp_ecc_error_state(struct amdgpu_device *adev, - struct amdgpu_irq_src *source, - unsigned type, - enum amdgpu_interrupt_state state) -{ - uint32_t ecc_irq_state = 0; - uint32_t pipe0_int_cntl_addr = 0; - int i = 0; - - ecc_irq_state = (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0; - - pipe0_int_cntl_addr = SOC15_REG_OFFSET(GC, 0, regCP_ME1_PIPE0_INT_CNTL); - - WREG32_FIELD15_PREREG(GC, 0, CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, ecc_irq_state); - - for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++) - SET_ECC_ME_PIPE_STATE(pipe0_int_cntl_addr + i * CP_ME1_PIPE_INST_ADDR_INTERVAL, - ecc_irq_state); - - return 0; -} - static int gfx_v11_0_set_eop_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type, @@ -6341,11 +6303,6 @@ static const struct amdgpu_irq_src_funcs gfx_v11_0_priv_inst_irq_funcs = { .process = gfx_v11_0_priv_inst_irq, }; -static const struct amdgpu_irq_src_funcs gfx_v11_0_cp_ecc_error_irq_funcs = { - .set = gfx_v11_0_set_cp_ecc_error_state, - .process = amdgpu_gfx_cp_ecc_error_irq, -}; - static const struct amdgpu_irq_src_funcs gfx_v11_0_rlc_gc_fed_irq_funcs = { .process = gfx_v11_0_rlc_gc_fed_irq, }; @@ -6361,9 +6318,6 @@ static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev) adev->gfx.priv_inst_irq.num_types = 1; adev->gfx.priv_inst_irq.funcs = &gfx_v11_0_priv_inst_irq_funcs; - adev->gfx.cp_ecc_error_irq.num_types = 1; /* CP ECC error */ - adev->gfx.cp_ecc_error_irq.funcs = &gfx_v11_0_cp_ecc_error_irq_funcs; - adev->gfx.rlc_gc_fed_irq.num_types = 1; /* 0x80 FED error */ adev->gfx.rlc_gc_fed_irq.funcs = &gfx_v11_0_rlc_gc_fed_irq_funcs; -- GitLab From 6c032c37ac3ef3b7df30937c785ecc4da428edc0 Mon Sep 17 00:00:00 2001 From: "Lin.Cao" Date: Mon, 8 May 2023 17:28:41 +0800 Subject: [PATCH 4756/5631] drm/amdgpu: Fix vram recover doesn't work after whole GPU reset (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit v1: Vmbo->shadow is used to back vram bo up when vram lost. So that we should set shadow as vmbo->shadow to recover vmbo->bo v2: Modify if(vmbo->shadow) shadow = vmbo->shadow as if(!vmbo->shadow) continue; Fixes: e18aaea733da ("drm/amdgpu: move shadow_list to amdgpu_bo_vm") Reviewed-by: Christian König Signed-off-by: Lin.Cao Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e348a62ec0ec..5c7d40873ee2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4512,7 +4512,11 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) dev_info(adev->dev, "recover vram bo from shadow start\n"); mutex_lock(&adev->shadow_list_lock); list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - shadow = &vmbo->bo; + /* If vm is compute context or adev is APU, shadow will be NULL */ + if (!vmbo->shadow) + continue; + shadow = vmbo->shadow; + /* No need to recover an evicted BO */ if (shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || -- GitLab From 8b229ada2669b74fdae06c83fbfda5a5a99fc253 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Sat, 6 May 2023 16:52:59 +0800 Subject: [PATCH 4757/5631] drm/amdgpu: disable sdma ecc irq only when sdma RAS is enabled in suspend sdma_v4_0_ip is shared on a few asics, but in sdma_v4_0_hw_fini, driver unconditionally disables ecc_irq which is only enabled on those asics enabling sdma ecc. This will introduce a warning in suspend cycle on those chips with sdma ip v4.0, while without sdma ecc. So this patch correct this. [ 7283.166354] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu] [ 7283.167001] RSP: 0018:ffff9a5fc3967d08 EFLAGS: 00010246 [ 7283.167019] RAX: ffff98d88afd3770 RBX: 0000000000000001 RCX: 0000000000000000 [ 7283.167023] RDX: 0000000000000000 RSI: ffff98d89da30390 RDI: ffff98d89da20000 [ 7283.167025] RBP: ffff98d89da20000 R08: 0000000000036838 R09: 0000000000000006 [ 7283.167028] R10: ffffd5764243c008 R11: 0000000000000000 R12: ffff98d89da30390 [ 7283.167030] R13: ffff98d89da38978 R14: ffffffff999ae15a R15: ffff98d880130105 [ 7283.167032] FS: 0000000000000000(0000) GS:ffff98d996f00000(0000) knlGS:0000000000000000 [ 7283.167036] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7283.167039] CR2: 00000000f7a9d178 CR3: 00000001c42ea000 CR4: 00000000003506e0 [ 7283.167041] Call Trace: [ 7283.167046] [ 7283.167048] sdma_v4_0_hw_fini+0x38/0xa0 [amdgpu] [ 7283.167704] amdgpu_device_ip_suspend_phase2+0x101/0x1a0 [amdgpu] [ 7283.168296] amdgpu_device_suspend+0x103/0x180 [amdgpu] [ 7283.168875] amdgpu_pmops_freeze+0x21/0x60 [amdgpu] [ 7283.169464] pci_pm_freeze+0x54/0xc0 Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Signed-off-by: Guchun Chen Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index b3cc04dd8653..9295ac7edd56 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1917,9 +1917,11 @@ static int sdma_v4_0_hw_fini(void *handle) return 0; } - for (i = 0; i < adev->sdma.num_instances; i++) { - amdgpu_irq_put(adev, &adev->sdma.ecc_irq, - AMDGPU_SDMA_IRQ_INSTANCE0 + i); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) { + for (i = 0; i < adev->sdma.num_instances; i++) { + amdgpu_irq_put(adev, &adev->sdma.ecc_irq, + AMDGPU_SDMA_IRQ_INSTANCE0 + i); + } } sdma_v4_0_ctx_switch_enable(adev, false); -- GitLab From eb4b8eca1bad98f4b8574558a74f041f9acb5a54 Mon Sep 17 00:00:00 2001 From: Milo Spadacini Date: Mon, 8 May 2023 15:18:48 +0200 Subject: [PATCH 4758/5631] tools: gpio: fix debounce_period_us output of lsgpio Fix incorrect output that could occur when more attributes are used and GPIO_V2_LINE_ATTR_ID_DEBOUNCE is not the first one. Signed-off-by: Milo Spadacini Reviewed-by: Linus Walleij Reviewed-by: Andy Shevchenko Signed-off-by: Bartosz Golaszewski --- tools/gpio/lsgpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/gpio/lsgpio.c b/tools/gpio/lsgpio.c index c61d061247e1..52a0be45410c 100644 --- a/tools/gpio/lsgpio.c +++ b/tools/gpio/lsgpio.c @@ -94,7 +94,7 @@ static void print_attributes(struct gpio_v2_line_info *info) for (i = 0; i < info->num_attrs; i++) { if (info->attrs[i].id == GPIO_V2_LINE_ATTR_ID_DEBOUNCE) fprintf(stdout, ", debounce_period=%dusec", - info->attrs[0].debounce_period_us); + info->attrs[i].debounce_period_us); } } -- GitLab From f67bc15e526bb9920683ad6c1891ff9e08981335 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 21 Apr 2023 13:42:41 +0300 Subject: [PATCH 4759/5631] coresight: Fix signedness bug in tmc_etr_buf_insert_barrier_packet() This code generates a Smatch warning: drivers/hwtracing/coresight/coresight-tmc-etr.c:947 tmc_etr_buf_insert_barrier_packet() error: uninitialized symbol 'bufp'. The problem is that if tmc_sg_table_get_data() returns -EINVAL, then when we test if "len < CORESIGHT_BARRIER_PKT_SIZE", the negative "len" value is type promoted to a high unsigned long value which is greater than CORESIGHT_BARRIER_PKT_SIZE. Fix this bug by adding an explicit check for error codes. Fixes: 75f4e3619fe2 ("coresight: tmc-etr: Add transparent buffer management") Signed-off-by: Dan Carpenter Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/7d33e244-d8b9-4c27-9653-883a13534b01@kili.mountain --- drivers/hwtracing/coresight/coresight-tmc-etr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 918d461fcf4a..eaa296ced167 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -942,7 +942,7 @@ tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset) len = tmc_etr_buf_get_data(etr_buf, offset, CORESIGHT_BARRIER_PKT_SIZE, &bufp); - if (WARN_ON(len < CORESIGHT_BARRIER_PKT_SIZE)) + if (WARN_ON(len < 0 || len < CORESIGHT_BARRIER_PKT_SIZE)) return -EINVAL; coresight_insert_barrier_packet(bufp); return offset + CORESIGHT_BARRIER_PKT_SIZE; -- GitLab From 04ac7f98b92181179ea84439642493f3826d04a2 Mon Sep 17 00:00:00 2001 From: Ruidong Tian Date: Tue, 25 Apr 2023 11:24:16 +0800 Subject: [PATCH 4760/5631] coresight: perf: Release Coresight path when alloc trace id failed Error handler for etm_setup_aux can not release coresight path because cpu mask was cleared when coresight_trace_id_get_cpu_id failed. Call coresight_release_path function explicitly when alloc trace id filed. Fixes: 4ff1fdb4125c4 ("coresight: perf: traceid: Add perf ID allocation and notifiers") Signed-off-by: Ruidong Tian Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20230425032416.125542-1-tianruidong@linux.alibaba.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 711f451b6946..89e8ed214ea4 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -402,6 +402,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, trace_id = coresight_trace_id_get_cpu_id(cpu); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); + coresight_release_path(path); continue; } -- GitLab From 275dac1f7f5e9c2a2e806b34d3b10804eec0ac3c Mon Sep 17 00:00:00 2001 From: John Harrison Date: Fri, 28 Apr 2023 11:56:33 -0700 Subject: [PATCH 4761/5631] drm/i915/guc: Don't capture Gen8 regs on Xe devices A pair of pre-Xe registers were being included in the Xe capture list. GuC was rejecting those as being invalid and logging errors about them. So, stop doing it. Signed-off-by: John Harrison Reviewed-by: Alan Previn Fixes: dce2bd542337 ("drm/i915/guc: Add Gen9 registers for GuC error state capture.") Cc: Alan Previn Cc: Umesh Nerlige Ramappa Cc: Lucas De Marchi Cc: John Harrison Cc: Jani Nikula Cc: Matt Roper Cc: Balasubramani Vivekanandan Cc: Daniele Ceraolo Spurio Link: https://patchwork.freedesktop.org/patch/msgid/20230428185636.457407-2-John.C.Harrison@Intel.com (cherry picked from commit b049132d61336f643d8faf2f6574b063667088cf) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index cf49188db6a6..e0e793167d61 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -31,12 +31,14 @@ { FORCEWAKE_MT, 0, 0, "FORCEWAKE" } #define COMMON_GEN9BASE_GLOBAL \ - { GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \ - { GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" }, \ { ERROR_GEN6, 0, 0, "ERROR_GEN6" }, \ { DONE_REG, 0, 0, "DONE_REG" }, \ { HSW_GTT_CACHE_EN, 0, 0, "HSW_GTT_CACHE_EN" } +#define GEN9_GLOBAL \ + { GEN8_FAULT_TLB_DATA0, 0, 0, "GEN8_FAULT_TLB_DATA0" }, \ + { GEN8_FAULT_TLB_DATA1, 0, 0, "GEN8_FAULT_TLB_DATA1" } + #define COMMON_GEN12BASE_GLOBAL \ { GEN12_FAULT_TLB_DATA0, 0, 0, "GEN12_FAULT_TLB_DATA0" }, \ { GEN12_FAULT_TLB_DATA1, 0, 0, "GEN12_FAULT_TLB_DATA1" }, \ @@ -142,6 +144,7 @@ static const struct __guc_mmio_reg_descr xe_lpd_gsc_inst_regs[] = { static const struct __guc_mmio_reg_descr default_global_regs[] = { COMMON_BASE_GLOBAL, COMMON_GEN9BASE_GLOBAL, + GEN9_GLOBAL, }; static const struct __guc_mmio_reg_descr default_rc_class_regs[] = { -- GitLab From a41d985902c153c31c616fe183cf2ee331e95ecb Mon Sep 17 00:00:00 2001 From: Stanislav Lisovskiy Date: Fri, 5 May 2023 11:22:12 +0300 Subject: [PATCH 4762/5631] drm/i915: Fix NULL ptr deref by checking new_crtc_state intel_atomic_get_new_crtc_state can return NULL, unless crtc state wasn't obtained previously with intel_atomic_get_crtc_state, so we must check it for NULLness here, just as in many other places, where we can't guarantee that intel_atomic_get_crtc_state was called. We are currently getting NULL ptr deref because of that, so this fix was confirmed to help. Fixes: 74a75dc90869 ("drm/i915/display: move plane prepare/cleanup to intel_atomic_plane.c") Signed-off-by: Stanislav Lisovskiy Reviewed-by: Andrzej Hajda Link: https://patchwork.freedesktop.org/patch/msgid/20230505082212.27089-1-stanislav.lisovskiy@intel.com (cherry picked from commit 1d5b09f8daf859247a1ea65b0d732a24d88980d8) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_atomic_plane.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 40de9f0f171b..f33164b10292 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -1028,7 +1028,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, int ret; if (old_obj) { - const struct intel_crtc_state *crtc_state = + const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, to_intel_crtc(old_plane_state->hw.crtc)); @@ -1043,7 +1043,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane, * This should only fail upon a hung GPU, in which case we * can safely continue. */ - if (intel_crtc_needs_modeset(crtc_state)) { + if (new_crtc_state && intel_crtc_needs_modeset(new_crtc_state)) { ret = i915_sw_fence_await_reservation(&state->commit_ready, old_obj->base.resv, false, 0, -- GitLab From 0ff80028e2702c7c3d78b69705dc47c1ccba8c39 Mon Sep 17 00:00:00 2001 From: Nikita Zhandarovich Date: Tue, 18 Apr 2023 07:04:30 -0700 Subject: [PATCH 4763/5631] drm/i915/dp: prevent potential div-by-zero drm_dp_dsc_sink_max_slice_count() may return 0 if something goes wrong on the part of the DSC sink and its DPCD register. This null value may be later used as a divisor in intel_dsc_compute_params(), which will lead to an error. In the unlikely event that this issue occurs, fix it by testing the return value of drm_dp_dsc_sink_max_slice_count() against zero. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: a4a157777c80 ("drm/i915/dp: Compute DSC pipe config in atomic check") Signed-off-by: Nikita Zhandarovich Reviewed-by: Rodrigo Vivi Signed-off-by: Rodrigo Vivi Link: https://patchwork.freedesktop.org/patch/msgid/20230418140430.69902-1-n.zhandarovich@fintech.ru (cherry picked from commit 51f7008239de011370c5067bbba07f0207f06b72) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_dp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index f0bace9d98a1..529ee22be872 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1601,6 +1601,11 @@ int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, pipe_config->dsc.slice_count = drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, true); + if (!pipe_config->dsc.slice_count) { + drm_dbg_kms(&dev_priv->drm, "Unsupported Slice Count %d\n", + pipe_config->dsc.slice_count); + return -EINVAL; + } } else { u16 dsc_max_output_bpp = 0; u8 dsc_dp_slice_count; -- GitLab From 79c901c93562bdf1c84ce6c1b744fbbe4389a6eb Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Thu, 4 May 2023 13:35:08 +0300 Subject: [PATCH 4764/5631] drm/i915: taint kernel when force probing unsupported devices For development and testing purposes, the i915.force_probe module parameter and DRM_I915_FORCE_PROBE kconfig option allow probing of devices that aren't supported by the driver. The i915.force_probe module parameter is "unsafe" and setting it taints the kernel. However, using the kconfig option does not. Always taint the kernel when force probing a device that is not supported. v2: Drop "depends on EXPERT" to avoid build breakage (kernel test robot) Fixes: 7ef5ef5cdead ("drm/i915: add force_probe module parameter to replace alpha_support") Cc: Joonas Lahtinen Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Cc: Daniel Vetter Cc: Dave Airlie Acked-by: Daniel Vetter Reviewed-by: Rodrigo Vivi Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/20230504103508.1818540-1-jani.nikula@intel.com (cherry picked from commit 3312bb4ad09ca6423bd4a5b15a94588a8962fb8e) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/Kconfig | 12 +++++++----- drivers/gpu/drm/i915/i915_pci.c | 6 ++++++ 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 06a0ca157e89..e4f4d2e3fdfe 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -62,10 +62,11 @@ config DRM_I915_FORCE_PROBE This is the default value for the i915.force_probe module parameter. Using the module parameter overrides this option. - Force probe the i915 for Intel graphics devices that are - recognized but not properly supported by this kernel version. It is - recommended to upgrade to a kernel version with proper support as soon - as it is available. + Force probe the i915 driver for Intel graphics devices that are + recognized but not properly supported by this kernel version. Force + probing an unsupported device taints the kernel. It is recommended to + upgrade to a kernel version with proper support as soon as it is + available. It can also be used to block the probe of recognized and fully supported devices. @@ -75,7 +76,8 @@ config DRM_I915_FORCE_PROBE Use "[,,...]" to force probe the i915 for listed devices. For example, "4500" or "4500,4571". - Use "*" to force probe the driver for all known devices. + Use "*" to force probe the driver for all known devices. Not + recommended. Use "!" right before the ID to block the probe of the device. For example, "4500,!4571" forces the probe of 4500 and blocks the probe of diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 2a012da8ccfa..edcfb5fe20b2 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1344,6 +1344,12 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } + if (intel_info->require_force_probe) { + dev_info(&pdev->dev, "Force probing unsupported Device ID %04x, tainting kernel\n", + pdev->device); + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + } + /* Only bind to function 0 of the device. Early generations * used function 1 as a placeholder for multi-head. This causes * us confusion instead, especially on the systems where both -- GitLab From 66b2ca086210732954a7790d63d35542936fc664 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 11 May 2023 21:42:24 +1000 Subject: [PATCH 4765/5631] powerpc/64s/radix: Fix soft dirty tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It was reported that soft dirty tracking doesn't work when using the Radix MMU. The tracking is supposed to work by clearing the soft dirty bit for a mapping and then write protecting the PTE. If/when the page is written to, a page fault occurs and the soft dirty bit is added back via pte_mkdirty(). For example in wp_page_reuse(): entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); Unfortunately on radix _PAGE_SOFTDIRTY is being dropped by radix__ptep_set_access_flags(), called from ptep_set_access_flags(), meaning the soft dirty bit is not set even though the page has been written to. Fix it by adding _PAGE_SOFTDIRTY to the set of bits that are able to be changed in radix__ptep_set_access_flags(). Fixes: b0b5e9b13047 ("powerpc/mm/radix: Add radix pte #defines") Cc: stable@vger.kernel.org # v4.7+ Reported-by: Dan Horák Link: https://lore.kernel.org/r/20230511095558.56663a50f86bdc4cd97700b7@danny.cz Signed-off-by: Michael Ellerman Link: https://msgid.link/20230511114224.977423-1-mpe@ellerman.id.au --- arch/powerpc/mm/book3s64/radix_pgtable.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 26245aaf12b8..2297aa764ecd 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -1040,8 +1040,8 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep, pte_t entry, unsigned long address, int psize) { struct mm_struct *mm = vma->vm_mm; - unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED | - _PAGE_RW | _PAGE_EXEC); + unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_SOFT_DIRTY | + _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC); unsigned long change = pte_val(entry) ^ pte_val(*ptep); /* -- GitLab From 5247f05eadf1081a74b2233f291cee2efed25e3a Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Tue, 9 May 2023 09:36:49 +0800 Subject: [PATCH 4766/5631] drm/amd/pm: avoid potential UBSAN issue on legacy asics Prevent further dpm casting on legacy asics without od_enabled in amdgpu_dpm_is_overdrive_supported. This can avoid UBSAN complain in init sequence. v2: add a macro to check legacy dpm instead of checking asic family/type v3: refine macro name for naming consistency Suggested-by: Evan Quan Signed-off-by: Guchun Chen Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/amdgpu_dpm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 86246f69dbe1..078aaaa53162 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -36,6 +36,8 @@ #define amdgpu_dpm_enable_bapm(adev, e) \ ((adev)->powerplay.pp_funcs->enable_bapm((adev)->powerplay.pp_handle, (e))) +#define amdgpu_dpm_is_legacy_dpm(adev) ((adev)->powerplay.pp_handle == (adev)) + int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; @@ -1467,8 +1469,11 @@ int amdgpu_dpm_is_overdrive_supported(struct amdgpu_device *adev) } else { struct pp_hwmgr *hwmgr; - /* SI asic does not carry od_enabled */ - if (adev->family == AMDGPU_FAMILY_SI) + /* + * dpm on some legacy asics don't carry od_enabled member + * as its pp_handle is casted directly from adev. + */ + if (amdgpu_dpm_is_legacy_dpm(adev)) return false; hwmgr = (struct pp_hwmgr *)adev->powerplay.pp_handle; -- GitLab From 976d3c6778e99390c6d854d140b746d12ea18a51 Mon Sep 17 00:00:00 2001 From: Mirsad Todorovac Date: Tue, 11 Apr 2023 20:15:20 +0300 Subject: [PATCH 4767/5631] selftests: gpio: gpio-sim: Fix BUG: test FAILED due to recent change According to Mirsad the gpio-sim.sh test appears to FAIL in a wrong way due to missing initialisation of shell variables: 4.2. Bias settings work correctly cat: /sys/devices/platform/gpio-sim.0/gpiochip18/sim_gpio0/value: No such file or directory ./gpio-sim.sh: line 393: test: =: unary operator expected bias setting does not work GPIO gpio-sim test FAIL After this change the test passed: 4.2. Bias settings work correctly GPIO gpio-sim test PASS His testing environment is AlmaLinux 8.7 on Lenovo desktop box with the latest Linux kernel based on v6.2: Linux 6.2.0-mglru-kmlk-andy-09238-gd2980d8d8265 x86_64 Suggested-by: Mirsad Todorovac Signed-off-by: Andy Shevchenko Tested-by: Mirsad Goran Todorovac Signed-off-by: Mirsad Goran Todorovac Signed-off-by: Bartosz Golaszewski --- tools/testing/selftests/gpio/gpio-sim.sh | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 9f539d454ee4..fa2ce2b9dd5f 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -389,6 +389,9 @@ create_chip chip create_bank chip bank set_num_lines chip bank 8 enable_chip chip +DEVNAME=`configfs_dev_name chip` +CHIPNAME=`configfs_chip_name chip bank` +SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" remove_chip chip -- GitLab From 4a76680311330aefe5074bed8f06afa354b85c48 Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Sat, 6 May 2023 20:06:45 +0800 Subject: [PATCH 4768/5631] drm/amdgpu/gfx: disable gfx9 cp_ecc_error_irq only when enabling legacy gfx ras gfx9 cp_ecc_error_irq is only enabled when legacy gfx ras is assert. So in gfx_v9_0_hw_fini, interrupt disablement for cp_ecc_error_irq should be executed under such condition, otherwise, an amdgpu_irq_put calltrace will occur. [ 7283.170322] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu] [ 7283.170964] RSP: 0018:ffff9a5fc3967d00 EFLAGS: 00010246 [ 7283.170967] RAX: ffff98d88afd3040 RBX: ffff98d89da20000 RCX: 0000000000000000 [ 7283.170969] RDX: 0000000000000000 RSI: ffff98d89da2bef8 RDI: ffff98d89da20000 [ 7283.170971] RBP: ffff98d89da20000 R08: ffff98d89da2ca18 R09: 0000000000000006 [ 7283.170973] R10: ffffd5764243c008 R11: 0000000000000000 R12: 0000000000001050 [ 7283.170975] R13: ffff98d89da38978 R14: ffffffff999ae15a R15: ffff98d880130105 [ 7283.170978] FS: 0000000000000000(0000) GS:ffff98d996f00000(0000) knlGS:0000000000000000 [ 7283.170981] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 7283.170983] CR2: 00000000f7a9d178 CR3: 00000001c42ea000 CR4: 00000000003506e0 [ 7283.170986] Call Trace: [ 7283.170988] [ 7283.170989] gfx_v9_0_hw_fini+0x1c/0x6d0 [amdgpu] [ 7283.171655] amdgpu_device_ip_suspend_phase2+0x101/0x1a0 [amdgpu] [ 7283.172245] amdgpu_device_suspend+0x103/0x180 [amdgpu] [ 7283.172823] amdgpu_pmops_freeze+0x21/0x60 [amdgpu] [ 7283.173412] pci_pm_freeze+0x54/0xc0 [ 7283.173419] ? __pfx_pci_pm_freeze+0x10/0x10 [ 7283.173425] dpm_run_callback+0x98/0x200 [ 7283.173430] __device_suspend+0x164/0x5f0 v2: drop gfx11 as it's fixed in a different solution by retiring cp_ecc_irq funcs(Hawking) Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2522 Signed-off-by: Guchun Chen Reviewed-by: Tao Zhou Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index adbcd8127c82..f46d4b18a3fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3764,7 +3764,8 @@ static int gfx_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); -- GitLab From 5b94db73e45e2e6c2840f39c022fd71dfa47fc58 Mon Sep 17 00:00:00 2001 From: Saleemkhan Jamadar Date: Tue, 9 May 2023 12:37:50 +0530 Subject: [PATCH 4769/5631] drm/amdgpu/jpeg: Remove harvest checking for JPEG3 Register CC_UVD_HARVESTING is obsolete for JPEG 3.1.2 Signed-off-by: Saleemkhan Jamadar Reviewed-by: Veerabadhran Gopalakrishnan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index c55e09432e26..1c2292cc5f2c 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -54,6 +54,7 @@ static int jpeg_v3_0_early_init(void *handle) switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 1, 1): + case IP_VERSION(3, 1, 2): break; default: harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING); -- GitLab From 996e93a3fe74dcf9d467ae3020aea42cc3ff65e3 Mon Sep 17 00:00:00 2001 From: Yifan Zhang Date: Wed, 10 May 2023 16:13:48 +0800 Subject: [PATCH 4770/5631] drm/amdgpu: change gfx 11.0.4 external_id range gfx 11.0.4 range starts from 0x80. Fixes: 311d52367d0a ("drm/amdgpu: add soc21 common ip block support for GC 11.0.4") Cc: stable@vger.kernel.org Signed-off-by: Yifan Zhang Reported-by: Yogesh Mohan Marimuthu Acked-by: Alex Deucher Reviewed-by: Tim Huang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/soc21.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 744be2a05623..d77162536514 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -711,7 +711,7 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_GFX_PG | AMD_PG_SUPPORT_JPEG; - adev->external_rev_id = adev->rev_id + 0x1; + adev->external_rev_id = adev->rev_id + 0x80; break; default: -- GitLab From ad81e23426a651eb89a4b306e1c4169e6308c124 Mon Sep 17 00:00:00 2001 From: Jocelyn Falempe Date: Wed, 10 May 2023 15:10:34 +0200 Subject: [PATCH 4771/5631] drm/mgag200: Fix gamma lut not initialized. When mgag200 switched from simple KMS to regular atomic helpers, the initialization of the gamma settings was lost. This leads to a black screen, if the bios/uefi doesn't use the same pixel color depth. v2: rebase on top of drm-misc-fixes, and add Cc stable tag. Link: https://bugzilla.redhat.com/show_bug.cgi?id=2171155 Fixes: 1baf9127c482 ("drm/mgag200: Replace simple-KMS with regular atomic helpers") Cc: Tested-by: Phil Oester Reviewed-by: Thomas Zimmermann Signed-off-by: Jocelyn Falempe Link: https://patchwork.freedesktop.org/patch/msgid/20230510131034.284078-1-jfalempe@redhat.com --- drivers/gpu/drm/mgag200/mgag200_mode.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 0a5aaf78172a..576c4c838a33 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -640,6 +640,11 @@ void mgag200_crtc_helper_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_ if (funcs->pixpllc_atomic_update) funcs->pixpllc_atomic_update(crtc, old_state); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) -- GitLab From 5a6bef734247c7a8c19511664ff77634ab86f45b Mon Sep 17 00:00:00 2001 From: Zongjie Li Date: Tue, 9 May 2023 19:27:26 +0800 Subject: [PATCH 4772/5631] fbdev: arcfb: Fix error handling in arcfb_probe() Smatch complains that: arcfb_probe() warn: 'irq' from request_irq() not released on lines: 587. Fix error handling in the arcfb_probe() function. If IO addresses are not provided or framebuffer registration fails, the code will jump to the err_addr or err_register_fb label to release resources. If IRQ request fails, previously allocated resources will be freed. Fixes: 1154ea7dcd8e ("[PATCH] Framebuffer driver for Arc LCD board") Signed-off-by: Zongjie Li Reviewed-by: Dongliang Mu Signed-off-by: Helge Deller --- drivers/video/fbdev/arcfb.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c index 45e64016db32..024d0ee4f04f 100644 --- a/drivers/video/fbdev/arcfb.c +++ b/drivers/video/fbdev/arcfb.c @@ -523,7 +523,7 @@ static int arcfb_probe(struct platform_device *dev) info = framebuffer_alloc(sizeof(struct arcfb_par), &dev->dev); if (!info) - goto err; + goto err_fb_alloc; info->screen_base = (char __iomem *)videomemory; info->fbops = &arcfb_ops; @@ -535,7 +535,7 @@ static int arcfb_probe(struct platform_device *dev) if (!dio_addr || !cio_addr || !c2io_addr) { printk(KERN_WARNING "no IO addresses supplied\n"); - goto err1; + goto err_addr; } par->dio_addr = dio_addr; par->cio_addr = cio_addr; @@ -551,12 +551,12 @@ static int arcfb_probe(struct platform_device *dev) printk(KERN_INFO "arcfb: Failed req IRQ %d\n", par->irq); retval = -EBUSY; - goto err1; + goto err_addr; } } retval = register_framebuffer(info); if (retval < 0) - goto err1; + goto err_register_fb; platform_set_drvdata(dev, info); fb_info(info, "Arc frame buffer device, using %dK of video memory\n", videomemorysize >> 10); @@ -580,9 +580,12 @@ static int arcfb_probe(struct platform_device *dev) } return 0; -err1: + +err_register_fb: + free_irq(par->irq, info); +err_addr: framebuffer_release(info); -err: +err_fb_alloc: vfree(videomemory); return retval; } -- GitLab From 3f6cb84839dcdd53cc002a198b5f92705bd793b3 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:00 +0200 Subject: [PATCH 4773/5631] fbdev: 68328fb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/68328fb.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/video/fbdev/68328fb.c b/drivers/video/fbdev/68328fb.c index 3ccf46f8ffd0..07d6e8dc686b 100644 --- a/drivers/video/fbdev/68328fb.c +++ b/drivers/video/fbdev/68328fb.c @@ -124,7 +124,7 @@ static u_long get_line_length(int xres_virtual, int bpp) * First part, xxxfb_check_var, must not write anything * to hardware, it should only verify and adjust var. * This means it doesn't alter par but it does use hardware - * data from it to check this var. + * data from it to check this var. */ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, @@ -182,7 +182,7 @@ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, /* * Now that we checked it we alter var. The reason being is that the video - * mode passed in might not work but slight changes to it might make it + * mode passed in might not work but slight changes to it might make it * work. This way we let the user know what is acceptable. */ switch (var->bits_per_pixel) { @@ -257,8 +257,8 @@ static int mc68x328fb_check_var(struct fb_var_screeninfo *var, } /* This routine actually sets the video mode. It's in here where we - * the hardware state info->par and fix which can be affected by the - * change in par. For this driver it doesn't do much. + * the hardware state info->par and fix which can be affected by the + * change in par. For this driver it doesn't do much. */ static int mc68x328fb_set_par(struct fb_info *info) { @@ -295,7 +295,7 @@ static int mc68x328fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, * {hardwarespecific} contains width of RAMDAC * cmap[X] is programmed to (X << red.offset) | (X << green.offset) | (X << blue.offset) * RAMDAC[X] is programmed to (red, green, blue) - * + * * Pseudocolor: * uses offset = 0 && length = RAMDAC register width. * var->{color}.offset is 0 @@ -384,7 +384,7 @@ static int mc68x328fb_pan_display(struct fb_var_screeninfo *var, } /* - * Most drivers don't need their own mmap function + * Most drivers don't need their own mmap function */ static int mc68x328fb_mmap(struct fb_info *info, struct vm_area_struct *vma) -- GitLab From 486357bbdafb43bcc99fcf943ea76fcd69aae7b7 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:01 +0200 Subject: [PATCH 4774/5631] fbdev: atmel_lcdfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Reviewed-by: Sui Jingfeng --- drivers/video/fbdev/atmel_lcdfb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 8187a7c4f910..987c5f5f0241 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -317,7 +317,7 @@ static inline void atmel_lcdfb_free_video_memory(struct atmel_lcdfb_info *sinfo) /** * atmel_lcdfb_alloc_video_memory - Allocate framebuffer memory * @sinfo: the frame buffer to allocate memory for - * + * * This function is called only from the atmel_lcdfb_probe() * so no locking by fb_info->mm_lock around smem_len setting is needed. */ -- GitLab From ca047de0e00e9cf55775f1f6b90461ed1f76c424 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:02 +0200 Subject: [PATCH 4775/5631] fbdev: cg14: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/cg14.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/cg14.c b/drivers/video/fbdev/cg14.c index a028ede39c12..832a82f45c80 100644 --- a/drivers/video/fbdev/cg14.c +++ b/drivers/video/fbdev/cg14.c @@ -512,7 +512,7 @@ static int cg14_probe(struct platform_device *op) is_8mb = (resource_size(&op->resource[1]) == (8 * 1024 * 1024)); BUILD_BUG_ON(sizeof(par->mmap_map) != sizeof(__cg14_mmap_map)); - + memcpy(&par->mmap_map, &__cg14_mmap_map, sizeof(par->mmap_map)); for (i = 0; i < CG14_MMAP_ENTRIES; i++) { -- GitLab From 56fd9558357bdfa5c187dbd59990b62d358ed66e Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:03 +0200 Subject: [PATCH 4776/5631] fbdev: controlfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/controlfb.c | 34 ++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index 77dbf94aae5f..82eeb139c4eb 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -113,14 +113,14 @@ struct fb_info_control { struct fb_info info; struct fb_par_control par; u32 pseudo_palette[16]; - + struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + struct control_regs __iomem *control_regs; unsigned long control_regs_phys; unsigned long control_regs_size; - + __u8 __iomem *frame_buffer; unsigned long frame_buffer_phys; unsigned long fb_orig_base; @@ -196,7 +196,7 @@ static void set_control_clock(unsigned char *params) while (!req.complete) cuda_poll(); } -#endif +#endif } /* @@ -233,19 +233,19 @@ static void control_set_hardware(struct fb_info_control *p, struct fb_par_contro if (p->par.xoffset != par->xoffset || p->par.yoffset != par->yoffset) set_screen_start(par->xoffset, par->yoffset, p); - + return; } - + p->par = *par; cmode = p->par.cmode; r = &par->regvals; - + /* Turn off display */ out_le32(CNTRL_REG(p,ctrl), 0x400 | par->ctrl); - + set_control_clock(r->clock_params); - + RADACAL_WRITE(0x20, r->radacal_ctrl); RADACAL_WRITE(0x21, p->control_use_bank2 ? 0 : 1); RADACAL_WRITE(0x10, 0); @@ -254,7 +254,7 @@ static void control_set_hardware(struct fb_info_control *p, struct fb_par_contro rp = &p->control_regs->vswin; for (i = 0; i < 16; ++i, ++rp) out_le32(&rp->r, r->regs[i]); - + out_le32(CNTRL_REG(p,pitch), par->pitch); out_le32(CNTRL_REG(p,mode), r->mode); out_le32(CNTRL_REG(p,vram_attr), p->vram_attr); @@ -366,7 +366,7 @@ static int read_control_sense(struct fb_info_control *p) sense |= (in_le32(CNTRL_REG(p,mon_sense)) & 0x180) >> 7; out_le32(CNTRL_REG(p,mon_sense), 077); /* turn off drivers */ - + return sense; } @@ -558,9 +558,9 @@ static int control_var_to_par(struct fb_var_screeninfo *var, static void control_par_to_var(struct fb_par_control *par, struct fb_var_screeninfo *var) { struct control_regints *rv; - + rv = (struct control_regints *) par->regvals.regs; - + memset(var, 0, sizeof(*var)); var->xres = par->xres; var->yres = par->yres; @@ -568,7 +568,7 @@ static void control_par_to_var(struct fb_par_control *par, struct fb_var_screeni var->yres_virtual = par->vyres; var->xoffset = par->xoffset; var->yoffset = par->yoffset; - + switch(par->cmode) { default: case CMODE_8: @@ -634,7 +634,7 @@ static int controlfb_check_var (struct fb_var_screeninfo *var, struct fb_info *i err = control_var_to_par(var, &par, info); if (err) - return err; + return err; control_par_to_var(&par, var); return 0; @@ -655,7 +655,7 @@ static int controlfb_set_par (struct fb_info *info) " control_var_to_par: %d.\n", err); return err; } - + control_set_hardware(p, &par); info->fix.visual = (p->par.cmode == CMODE_8) ? @@ -840,7 +840,7 @@ static int __init init_control(struct fb_info_control *p) int full, sense, vmode, cmode, vyres; struct fb_var_screeninfo var; int rc; - + printk(KERN_INFO "controlfb: "); full = p->total_vram == 0x400000; -- GitLab From 353e4441199b4106e5a5148bcff5c6b8ea268134 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:04 +0200 Subject: [PATCH 4777/5631] fbdev: g364fb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/g364fb.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/video/fbdev/g364fb.c b/drivers/video/fbdev/g364fb.c index 05837a3b985c..c5b7673ddc6c 100644 --- a/drivers/video/fbdev/g364fb.c +++ b/drivers/video/fbdev/g364fb.c @@ -6,7 +6,7 @@ * * This driver is based on tgafb.c * - * Copyright (C) 1997 Geert Uytterhoeven + * Copyright (C) 1997 Geert Uytterhoeven * Copyright (C) 1995 Jay Estabrook * * This file is subject to the terms and conditions of the GNU General Public @@ -28,7 +28,7 @@ #include #include -/* +/* * Various defines for the G364 */ #define G364_MEM_BASE 0xe4400000 @@ -125,7 +125,7 @@ static const struct fb_ops g364fb_ops = { * * This call looks only at xoffset, yoffset and the FB_VMODE_YWRAP flag */ -static int g364fb_pan_display(struct fb_var_screeninfo *var, +static int g364fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) { if (var->xoffset || -- GitLab From f15d296317a73a81394600050702264bbe99fa37 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:05 +0200 Subject: [PATCH 4778/5631] fbdev: hgafb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/hgafb.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/drivers/video/fbdev/hgafb.c b/drivers/video/fbdev/hgafb.c index 20bdab738ab7..0af58018441d 100644 --- a/drivers/video/fbdev/hgafb.c +++ b/drivers/video/fbdev/hgafb.c @@ -1,6 +1,6 @@ /* * linux/drivers/video/hgafb.c -- Hercules graphics adaptor frame buffer device - * + * * Created 25 Nov 1999 by Ferenc Bakonyi (fero@drama.obuda.kando.hu) * Based on skeletonfb.c by Geert Uytterhoeven and * mdacon.c by Andrew Apted @@ -8,14 +8,14 @@ * History: * * - Revision 0.1.8 (23 Oct 2002): Ported to new framebuffer api. - * - * - Revision 0.1.7 (23 Jan 2001): fix crash resulting from MDA only cards + * + * - Revision 0.1.7 (23 Jan 2001): fix crash resulting from MDA only cards * being detected as Hercules. (Paul G.) * - Revision 0.1.6 (17 Aug 2000): new style structs * documentation * - Revision 0.1.5 (13 Mar 2000): spinlocks instead of saveflags();cli();etc * minor fixes - * - Revision 0.1.4 (24 Jan 2000): fixed a bug in hga_card_detect() for + * - Revision 0.1.4 (24 Jan 2000): fixed a bug in hga_card_detect() for * HGA-only systems * - Revision 0.1.3 (22 Jan 2000): modified for the new fb_info structure * screen is cleared after rmmod @@ -143,7 +143,7 @@ static bool nologo = 0; static void write_hga_b(unsigned int val, unsigned char reg) { - outb_p(reg, HGA_INDEX_PORT); + outb_p(reg, HGA_INDEX_PORT); outb_p(val, HGA_VALUE_PORT); } @@ -155,7 +155,7 @@ static void write_hga_w(unsigned int val, unsigned char reg) static int test_hga_b(unsigned char val, unsigned char reg) { - outb_p(reg, HGA_INDEX_PORT); + outb_p(reg, HGA_INDEX_PORT); outb (val, HGA_VALUE_PORT); udelay(20); val = (inb_p(HGA_VALUE_PORT) == val); return val; @@ -244,7 +244,7 @@ static void hga_show_logo(struct fb_info *info) void __iomem *dest = hga_vram; char *logo = linux_logo_bw; int x, y; - + for (y = 134; y < 134 + 80 ; y++) * this needs some cleanup * for (x = 0; x < 10 ; x++) writeb(~*(logo++),(dest + HGA_ROWADDR(y) + x + 40)); @@ -255,7 +255,7 @@ static void hga_pan(unsigned int xoffset, unsigned int yoffset) { unsigned int base; unsigned long flags; - + base = (yoffset / 8) * 90 + xoffset; spin_lock_irqsave(&hga_reg_lock, flags); write_hga_w(base, 0x0c); /* start address */ @@ -310,7 +310,7 @@ static int hga_card_detect(void) /* Ok, there is definitely a card registering at the correct * memory location, so now we do an I/O port test. */ - + if (!test_hga_b(0x66, 0x0f)) /* cursor low register */ goto error; @@ -321,7 +321,7 @@ static int hga_card_detect(void) * bit of the status register is changing. This test lasts for * approximately 1/10th of a second. */ - + p_save = q_save = inb_p(HGA_STATUS_PORT) & HGA_STATUS_VSYNC; for (count=0; count < 50000 && p_save == q_save; count++) { @@ -329,7 +329,7 @@ static int hga_card_detect(void) udelay(2); } - if (p_save == q_save) + if (p_save == q_save) goto error; switch (inb_p(HGA_STATUS_PORT) & 0x70) { @@ -415,7 +415,7 @@ static int hgafb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, * @info:pointer to fb_info object containing info for current hga board * * This function looks only at xoffset, yoffset and the %FB_VMODE_YWRAP - * flag in @var. If input parameters are correct it calls hga_pan() to + * flag in @var. If input parameters are correct it calls hga_pan() to * program the hardware. @info->var is updated to the new values. * A zero is returned on success and %-EINVAL for failure. */ @@ -442,9 +442,9 @@ static int hgafb_pan_display(struct fb_var_screeninfo *var, * hgafb_blank - (un)blank the screen * @blank_mode:blanking method to use * @info:unused - * - * Blank the screen if blank_mode != 0, else unblank. - * Implements VESA suspend and powerdown modes on hardware that supports + * + * Blank the screen if blank_mode != 0, else unblank. + * Implements VESA suspend and powerdown modes on hardware that supports * disabling hsync/vsync: * @blank_mode == 2 means suspend vsync, * @blank_mode == 3 means suspend hsync, @@ -539,15 +539,15 @@ static const struct fb_ops hgafb_ops = { .fb_copyarea = hgafb_copyarea, .fb_imageblit = hgafb_imageblit, }; - + /* ------------------------------------------------------------------------- * * * Functions in fb_info - * + * * ------------------------------------------------------------------------- */ /* ------------------------------------------------------------------------- */ - + /* * Initialization */ -- GitLab From 4311776fd8f789c3fa15e051cf9ec94df6ca5a46 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:06 +0200 Subject: [PATCH 4779/5631] fbdev: hpfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/hpfb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c index cdd44e5deafe..77fbff47b1a8 100644 --- a/drivers/video/fbdev/hpfb.c +++ b/drivers/video/fbdev/hpfb.c @@ -92,7 +92,7 @@ static int hpfb_setcolreg(unsigned regno, unsigned red, unsigned green, if (regno >= info->cmap.len) return 1; - + while (in_be16(fb_regs + 0x6002) & 0x4) udelay(1); out_be16(fb_regs + 0x60ba, 0xff); @@ -143,7 +143,7 @@ static void topcat_blit(int x0, int y0, int x1, int y1, int w, int h, int rr) out_8(fb_regs + WMOVE, fb_bitmask); } -static void hpfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) +static void hpfb_copyarea(struct fb_info *info, const struct fb_copyarea *area) { topcat_blit(area->sx, area->sy, area->dx, area->dy, area->width, area->height, RR_COPY); } @@ -315,7 +315,7 @@ static int hpfb_init_one(unsigned long phys_base, unsigned long virt_base) return ret; } -/* +/* * Check that the secondary ID indicates that we have some hope of working with this * framebuffer. The catseye boards are pretty much like topcats and we can muddle through. */ @@ -323,7 +323,7 @@ static int hpfb_init_one(unsigned long phys_base, unsigned long virt_base) #define topcat_sid_ok(x) (((x) == DIO_ID2_LRCATSEYE) || ((x) == DIO_ID2_HRCCATSEYE) \ || ((x) == DIO_ID2_HRMCATSEYE) || ((x) == DIO_ID2_TOPCAT)) -/* +/* * Initialise the framebuffer */ static int hpfb_dio_probe(struct dio_dev *d, const struct dio_device_id *ent) -- GitLab From 41aaa2ecfca87afaebc40f00100a5d19ba381e4b Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:07 +0200 Subject: [PATCH 4780/5631] fbdev: macfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/macfb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/video/fbdev/macfb.c b/drivers/video/fbdev/macfb.c index 312e35c9aa6c..44ff860a3f37 100644 --- a/drivers/video/fbdev/macfb.c +++ b/drivers/video/fbdev/macfb.c @@ -339,7 +339,7 @@ static int civic_setpalette(unsigned int regno, unsigned int red, { unsigned long flags; int clut_status; - + local_irq_save(flags); /* Set the register address */ @@ -439,7 +439,7 @@ static int macfb_setcolreg(unsigned regno, unsigned red, unsigned green, * (according to the entries in the `var' structure). * Return non-zero for invalid regno. */ - + if (regno >= fb_info->cmap.len) return 1; @@ -548,7 +548,7 @@ static int __init macfb_init(void) return -ENODEV; macfb_setup(option); - if (!MACH_IS_MAC) + if (!MACH_IS_MAC) return -ENODEV; if (mac_bi_data.id == MAC_MODEL_Q630 || @@ -644,7 +644,7 @@ static int __init macfb_init(void) err = -EINVAL; goto fail_unmap; } - + /* * We take a wild guess that if the video physical address is * in nubus slot space, that the nubus card is driving video. @@ -774,7 +774,7 @@ static int __init macfb_init(void) civic_cmap_regs = ioremap(CIVIC_BASE, 0x1000); break; - + /* * Assorted weirdos * We think this may be like the LC II -- GitLab From 8c13c9de80b516d2a168e18744c9b7f586135ea4 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:08 +0200 Subject: [PATCH 4781/5631] fbdev: maxinefb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/maxinefb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/video/fbdev/maxinefb.c b/drivers/video/fbdev/maxinefb.c index ae1a42bcb0ea..4e6b05232ae2 100644 --- a/drivers/video/fbdev/maxinefb.c +++ b/drivers/video/fbdev/maxinefb.c @@ -138,7 +138,7 @@ int __init maxinefb_init(void) *(volatile unsigned char *)fboff = 0x0; maxinefb_fix.smem_start = fb_start; - + /* erase hardware cursor */ for (i = 0; i < 512; i++) { maxinefb_ims332_write_register(IMS332_REG_CURSOR_RAM + i, -- GitLab From 58b0aca735ff008ff32e494d87869556d299f0c4 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:09 +0200 Subject: [PATCH 4782/5631] fbdev: p9100: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/p9100.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/p9100.c b/drivers/video/fbdev/p9100.c index 3e44f9516318..0876962c52eb 100644 --- a/drivers/video/fbdev/p9100.c +++ b/drivers/video/fbdev/p9100.c @@ -65,7 +65,7 @@ static const struct fb_ops p9100_ops = { #define P9100_FB_OFF 0x0UL /* 3 bits: 2=8bpp 3=16bpp 5=32bpp 7=24bpp */ -#define SYS_CONFIG_PIXELSIZE_SHIFT 26 +#define SYS_CONFIG_PIXELSIZE_SHIFT 26 #define SCREENPAINT_TIMECTL1_ENABLE_VIDEO 0x20 /* 0 = off, 1 = on */ @@ -110,7 +110,7 @@ struct p9100_regs { u32 vram_xxx[25]; /* Registers for IBM RGB528 Palette */ - u32 ramdac_cmap_wridx; + u32 ramdac_cmap_wridx; u32 ramdac_palette_data; u32 ramdac_pixel_mask; u32 ramdac_palette_rdaddr; -- GitLab From a124ee3271ccd498689e4dc8ccd610e41e1579c9 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:10 +0200 Subject: [PATCH 4783/5631] fbdev: platinumfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/platinumfb.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index 82f019f0a0d6..f8283fcd5edb 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -52,17 +52,17 @@ struct fb_info_platinum { __u8 red, green, blue; } palette[256]; u32 pseudo_palette[16]; - + volatile struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + volatile struct platinum_regs __iomem *platinum_regs; unsigned long platinum_regs_phys; - + __u8 __iomem *frame_buffer; volatile __u8 __iomem *base_frame_buffer; unsigned long frame_buffer_phys; - + unsigned long total_vram; int clktype; int dactype; @@ -133,7 +133,7 @@ static int platinumfb_set_par (struct fb_info *info) platinum_set_hardware(pinfo); init = platinum_reg_init[pinfo->vmode-1]; - + if ((pinfo->vmode == VMODE_832_624_75) && (pinfo->cmode > CMODE_8)) offset = 0x10; @@ -214,7 +214,7 @@ static int platinumfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, break; } } - + return 0; } @@ -269,7 +269,7 @@ static void platinum_set_hardware(struct fb_info_platinum *pinfo) struct platinum_regvals *init; int i; int vmode, cmode; - + vmode = pinfo->vmode; cmode = pinfo->cmode; @@ -436,7 +436,7 @@ static int read_platinum_sense(struct fb_info_platinum *info) * This routine takes a user-supplied var, and picks the best vmode/cmode from it. * It also updates the var structure to the actual mode data obtained */ -static int platinum_var_to_par(struct fb_var_screeninfo *var, +static int platinum_var_to_par(struct fb_var_screeninfo *var, struct fb_info_platinum *pinfo, int check_only) { @@ -478,12 +478,12 @@ static int platinum_var_to_par(struct fb_var_screeninfo *var, pinfo->yoffset = 0; pinfo->vxres = pinfo->xres; pinfo->vyres = pinfo->yres; - + return 0; } -/* +/* * Parse user specified options (`video=platinumfb:') */ static int __init platinumfb_setup(char *options) @@ -624,7 +624,7 @@ static int platinumfb_probe(struct platform_device* odev) break; } dev_set_drvdata(&odev->dev, info); - + rc = platinum_init_fb(info); if (rc != 0) { iounmap(pinfo->frame_buffer); @@ -640,9 +640,9 @@ static void platinumfb_remove(struct platform_device* odev) { struct fb_info *info = dev_get_drvdata(&odev->dev); struct fb_info_platinum *pinfo = info->par; - + unregister_framebuffer (info); - + /* Unmap frame buffer and registers */ iounmap(pinfo->frame_buffer); iounmap(pinfo->platinum_regs); @@ -656,7 +656,7 @@ static void platinumfb_remove(struct platform_device* odev) framebuffer_release(info); } -static struct of_device_id platinumfb_match[] = +static struct of_device_id platinumfb_match[] = { { .name = "platinum", @@ -664,7 +664,7 @@ static struct of_device_id platinumfb_match[] = {}, }; -static struct platform_driver platinum_driver = +static struct platform_driver platinum_driver = { .driver = { .name = "platinumfb", -- GitLab From 6a7be526157940a71f363f24badccf545ff40541 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:11 +0200 Subject: [PATCH 4784/5631] fbdev: sa1100fb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/sa1100fb.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c index b1b8ccdbac4a..a2408bf00ca0 100644 --- a/drivers/video/fbdev/sa1100fb.c +++ b/drivers/video/fbdev/sa1100fb.c @@ -57,14 +57,14 @@ * - Driver appears to be working for Brutus 320x200x8bpp mode. Other * resolutions are working, but only the 8bpp mode is supported. * Changes need to be made to the palette encode and decode routines - * to support 4 and 16 bpp modes. + * to support 4 and 16 bpp modes. * Driver is not designed to be a module. The FrameBuffer is statically - * allocated since dynamic allocation of a 300k buffer cannot be - * guaranteed. + * allocated since dynamic allocation of a 300k buffer cannot be + * guaranteed. * * 1999/06/17: * - FrameBuffer memory is now allocated at run-time when the - * driver is initialized. + * driver is initialized. * * 2000/04/10: Nicolas Pitre * - Big cleanup for dynamic selection of machine type at run time. @@ -74,8 +74,8 @@ * * 2000/08/07: Tak-Shing Chan * Jeff Sutherland - * - Resolved an issue caused by a change made to the Assabet's PLD - * earlier this year which broke the framebuffer driver for newer + * - Resolved an issue caused by a change made to the Assabet's PLD + * earlier this year which broke the framebuffer driver for newer * Phase 4 Assabets. Some other parameters were changed to optimize * for the Sharp display. * @@ -102,7 +102,7 @@ * 2000/11/23: Eric Peng * - Freebird add * - * 2001/02/07: Jamey Hicks + * 2001/02/07: Jamey Hicks * Cliff Brake * - Added PM callback * @@ -500,7 +500,7 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con, * the shortest recovery time * Suspend * This refers to a level of power management in which substantial power - * reduction is achieved by the display. The display can have a longer + * reduction is achieved by the display. The display can have a longer * recovery time from this state than from the Stand-by state * Off * This indicates that the display is consuming the lowest level of power @@ -522,9 +522,9 @@ sa1100fb_set_cmap(struct fb_cmap *cmap, int kspc, int con, */ /* * sa1100fb_blank(): - * Blank the display by setting all palette values to zero. Note, the + * Blank the display by setting all palette values to zero. Note, the * 12 and 16 bpp modes don't really use the palette, so this will not - * blank the display in all modes. + * blank the display in all modes. */ static int sa1100fb_blank(int blank, struct fb_info *info) { @@ -603,8 +603,8 @@ static inline unsigned int get_pcd(struct sa1100fb_info *fbi, /* * sa1100fb_activate_var(): - * Configures LCD Controller based on entries in var parameter. Settings are - * only written to the controller if changes were made. + * Configures LCD Controller based on entries in var parameter. Settings are + * only written to the controller if changes were made. */ static int sa1100fb_activate_var(struct fb_var_screeninfo *var, struct sa1100fb_info *fbi) { @@ -747,7 +747,7 @@ static void sa1100fb_setup_gpio(struct sa1100fb_info *fbi) * * SA1110 spec update nr. 25 says we can and should * clear LDD15 to 12 for 4 or 8bpp modes with active - * panels. + * panels. */ if ((fbi->reg_lccr0 & LCCR0_CMS) == LCCR0_Color && (fbi->reg_lccr0 & (LCCR0_Dual|LCCR0_Act)) != 0) { @@ -1020,9 +1020,9 @@ static int sa1100fb_resume(struct platform_device *dev) /* * sa1100fb_map_video_memory(): - * Allocates the DRAM memory for the frame buffer. This buffer is - * remapped into a non-cached, non-buffered, memory region to - * allow palette and pixel writes to occur without flushing the + * Allocates the DRAM memory for the frame buffer. This buffer is + * remapped into a non-cached, non-buffered, memory region to + * allow palette and pixel writes to occur without flushing the * cache. Once this area is remapped, all virtual memory * access to the video memory should occur at the new region. */ -- GitLab From 8000425739dc49beceecdcd6f76c7b3bf40093fb Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:12 +0200 Subject: [PATCH 4785/5631] fbdev: stifb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/stifb.c | 156 ++++++++++++++++++------------------ 1 file changed, 78 insertions(+), 78 deletions(-) diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index ef8a4c5fc687..29912ee80f5b 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1,11 +1,11 @@ /* - * linux/drivers/video/stifb.c - - * Low level Frame buffer driver for HP workstations with + * linux/drivers/video/stifb.c - + * Low level Frame buffer driver for HP workstations with * STI (standard text interface) video firmware. * * Copyright (C) 2001-2006 Helge Deller * Portions Copyright (C) 2001 Thomas Bogendoerfer - * + * * Based on: * - linux/drivers/video/artistfb.c -- Artist frame buffer driver * Copyright (C) 2000 Philipp Rumpf @@ -14,7 +14,7 @@ * - HP Xhp cfb-based X11 window driver for XFree86 * (c)Copyright 1992 Hewlett-Packard Co. * - * + * * The following graphics display devices (NGLE family) are supported by this driver: * * HPA4070A known as "HCRX", a 1280x1024 color device with 8 planes @@ -30,7 +30,7 @@ * supports 1280x1024 color displays with 8 planes. * HP710G same as HP710C, 1280x1024 grayscale only * HP710L same as HP710C, 1024x768 color only - * HP712 internal graphics support on HP9000s712 SPU, supports 640x480, + * HP712 internal graphics support on HP9000s712 SPU, supports 640x480, * 1024x768 or 1280x1024 color displays on 8 planes (Artist) * * This file is subject to the terms and conditions of the GNU General Public @@ -92,7 +92,7 @@ typedef struct { __s32 misc_video_end; } video_setup_t; -typedef struct { +typedef struct { __s16 sizeof_ngle_data; __s16 x_size_visible; /* visible screen dim in pixels */ __s16 y_size_visible; @@ -177,10 +177,10 @@ static int __initdata stifb_bpp_pref[MAX_STI_ROMS]; #endif /* DEBUG_STIFB_REGS */ -#define ENABLE 1 /* for enabling/disabling screen */ +#define ENABLE 1 /* for enabling/disabling screen */ #define DISABLE 0 -#define NGLE_LOCK(fb_info) do { } while (0) +#define NGLE_LOCK(fb_info) do { } while (0) #define NGLE_UNLOCK(fb_info) do { } while (0) static void @@ -198,9 +198,9 @@ SETUP_HW(struct stifb_info *fb) static void SETUP_FB(struct stifb_info *fb) -{ +{ unsigned int reg10_value = 0; - + SETUP_HW(fb); switch (fb->id) { @@ -210,15 +210,15 @@ SETUP_FB(struct stifb_info *fb) reg10_value = 0x13601000; break; case S9000_ID_A1439A: - if (fb->info.var.bits_per_pixel == 32) + if (fb->info.var.bits_per_pixel == 32) reg10_value = 0xBBA0A000; - else + else reg10_value = 0x13601000; break; case S9000_ID_HCRX: if (fb->info.var.bits_per_pixel == 32) reg10_value = 0xBBA0A000; - else + else reg10_value = 0x13602000; break; case S9000_ID_TIMBER: @@ -243,7 +243,7 @@ START_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) } static void -WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) +WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) { SETUP_HW(fb); WRITE_WORD(((0x100+index)<<2), fb, REG_3); @@ -251,30 +251,30 @@ WRITE_IMAGE_COLOR(struct stifb_info *fb, int index, int color) } static void -FINISH_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) -{ +FINISH_IMAGE_COLORMAP_ACCESS(struct stifb_info *fb) +{ WRITE_WORD(0x400, fb, REG_2); if (fb->info.var.bits_per_pixel == 32) { WRITE_WORD(0x83000100, fb, REG_1); } else { if (fb->id == S9000_ID_ARTIST || fb->id == CRT_ID_VISUALIZE_EG) WRITE_WORD(0x80000100, fb, REG_26); - else + else WRITE_WORD(0x80000100, fb, REG_1); } SETUP_FB(fb); } static void -SETUP_RAMDAC(struct stifb_info *fb) +SETUP_RAMDAC(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x04000000, fb, 0x1020); WRITE_WORD(0xff000000, fb, 0x1028); } -static void -CRX24_SETUP_RAMDAC(struct stifb_info *fb) +static void +CRX24_SETUP_RAMDAC(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x04000000, fb, 0x1000); @@ -286,14 +286,14 @@ CRX24_SETUP_RAMDAC(struct stifb_info *fb) } #if 0 -static void +static void HCRX_SETUP_RAMDAC(struct stifb_info *fb) { WRITE_WORD(0xffffffff, fb, REG_32); } #endif -static void +static void CRX24_SET_OVLY_MASK(struct stifb_info *fb) { SETUP_HW(fb); @@ -314,7 +314,7 @@ ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) WRITE_WORD(value, fb, 0x1038); } -static void +static void CRX24_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) { unsigned int value = enable ? 0x10000000 : 0x30000000; @@ -325,11 +325,11 @@ CRX24_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) } static void -ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) +ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) { u32 DregsMiscVideo = REG_21; u32 DregsMiscCtl = REG_27; - + SETUP_HW(fb); if (enable) { WRITE_WORD(READ_WORD(fb, DregsMiscVideo) | 0x0A000000, fb, DregsMiscVideo); @@ -344,7 +344,7 @@ ARTIST_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable) (READ_BYTE(fb, REG_16b3) - 1) #define HYPER_CONFIG_PLANES_24 0x00000100 - + #define IS_24_DEVICE(fb) \ (fb->deviceSpecificConfig & HYPER_CONFIG_PLANES_24) @@ -470,15 +470,15 @@ SETUP_ATTR_ACCESS(struct stifb_info *fb, unsigned BufferNumber) } static void -SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) +SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) { - /* REG_6 seems to have special values when run on a + /* REG_6 seems to have special values when run on a RDI precisionbook parisc laptop (INTERNAL_EG_DX1024 or INTERNAL_EG_X1024). The values are: 0x2f0: internal (LCD) & external display enabled 0x2a0: external display only 0x000: zero on standard artist graphic cards - */ + */ WRITE_WORD(0x00000000, fb, REG_6); WRITE_WORD((width<<16) | height, fb, REG_9); WRITE_WORD(0x05000000, fb, REG_6); @@ -486,7 +486,7 @@ SET_ATTR_SIZE(struct stifb_info *fb, int width, int height) } static void -FINISH_ATTR_ACCESS(struct stifb_info *fb) +FINISH_ATTR_ACCESS(struct stifb_info *fb) { SETUP_HW(fb); WRITE_WORD(0x00000000, fb, REG_12); @@ -499,7 +499,7 @@ elkSetupPlanes(struct stifb_info *fb) SETUP_FB(fb); } -static void +static void ngleSetupAttrPlanes(struct stifb_info *fb, int BufferNumber) { SETUP_ATTR_ACCESS(fb, BufferNumber); @@ -519,7 +519,7 @@ rattlerSetupPlanes(struct stifb_info *fb) * read mask register for overlay planes, not image planes). */ CRX24_SETUP_RAMDAC(fb); - + /* change fb->id temporarily to fool SETUP_FB() */ saved_id = fb->id; fb->id = CRX24_OVERLAY_PLANES; @@ -565,7 +565,7 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) lutBltCtl.all = 0x80000000; lutBltCtl.fields.length = length; - switch (fb->id) + switch (fb->id) { case S9000_ID_A1439A: /* CRX24 */ if (fb->var.bits_per_pixel == 8) { @@ -576,12 +576,12 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) lutBltCtl.fields.lutOffset = 0 * 256; } break; - + case S9000_ID_ARTIST: lutBltCtl.fields.lutType = NGLE_CMAP_INDEXED0_TYPE; lutBltCtl.fields.lutOffset = 0 * 256; break; - + default: lutBltCtl.fields.lutType = NGLE_CMAP_INDEXED0_TYPE; lutBltCtl.fields.lutOffset = 0; @@ -596,7 +596,7 @@ setNgleLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) #endif static NgleLutBltCtl -setHyperLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) +setHyperLutBltCtl(struct stifb_info *fb, int offsetWithinLut, int length) { NgleLutBltCtl lutBltCtl; @@ -633,7 +633,7 @@ static void hyperUndoITE(struct stifb_info *fb) /* Hardware setup for full-depth write to "magic" location */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 7); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc04, Ots08, AddrLong, BAJustPoint(0), BINovly, BAIndexBase(0))); NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, @@ -653,13 +653,13 @@ static void hyperUndoITE(struct stifb_info *fb) NGLE_UNLOCK(fb); } -static void +static void ngleDepth8_ClearImagePlanes(struct stifb_info *fb) { /* FIXME! */ } -static void +static void ngleDepth24_ClearImagePlanes(struct stifb_info *fb) { /* FIXME! */ @@ -675,7 +675,7 @@ ngleResetAttrPlanes(struct stifb_info *fb, unsigned int ctlPlaneReg) NGLE_LOCK(fb); GET_FIFO_SLOTS(fb, nFreeFifoSlots, 4); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc32, OtsIndirect, AddrLong, BAJustPoint(0), BINattr, BAIndexBase(0))); @@ -713,22 +713,22 @@ ngleResetAttrPlanes(struct stifb_info *fb, unsigned int ctlPlaneReg) /**** Finally, set the Control Plane Register back to zero: ****/ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 1); NGLE_QUICK_SET_CTL_PLN_REG(fb, 0); - + NGLE_UNLOCK(fb); } - + static void ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) { int nFreeFifoSlots = 0; u32 packed_dst; u32 packed_len; - + NGLE_LOCK(fb); /* Hardware setup */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 8); - NGLE_QUICK_SET_DST_BM_ACCESS(fb, + NGLE_QUICK_SET_DST_BM_ACCESS(fb, BA(IndexedDcd, Otc04, Ots08, AddrLong, BAJustPoint(0), BINovly, BAIndexBase(0))); @@ -736,23 +736,23 @@ ngleClearOverlayPlanes(struct stifb_info *fb, int mask, int data) NGLE_REALLY_SET_IMAGE_FG_COLOR(fb, data); NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, mask); - + packed_dst = 0; packed_len = (fb->info.var.xres << 16) | fb->info.var.yres; NGLE_SET_DSTXY(fb, packed_dst); - - /* Write zeroes to overlay planes */ + + /* Write zeroes to overlay planes */ NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb, IBOvals(RopSrc, MaskAddrOffset(0), BitmapExtent08, StaticReg(0), DataDynamic, MaskOtc, BGx(0), FGx(0))); - + SET_LENXY_START_RECFILL(fb, packed_len); NGLE_UNLOCK(fb); } -static void +static void hyperResetPlanes(struct stifb_info *fb, int enable) { unsigned int controlPlaneReg; @@ -783,7 +783,7 @@ hyperResetPlanes(struct stifb_info *fb, int enable) ngleClearOverlayPlanes(fb, 0xff, 255); /************************************************** - ** Also need to counteract ITE settings + ** Also need to counteract ITE settings **************************************************/ hyperUndoITE(fb); break; @@ -803,13 +803,13 @@ hyperResetPlanes(struct stifb_info *fb, int enable) ngleResetAttrPlanes(fb, controlPlaneReg); break; } - + NGLE_UNLOCK(fb); } /* Return pointer to in-memory structure holding ELK device-dependent ROM values. */ -static void +static void ngleGetDeviceRomData(struct stifb_info *fb) { #if 0 @@ -821,7 +821,7 @@ XXX: FIXME: !!! char *pCard8; int i; char *mapOrigin = NULL; - + int romTableIdx; pPackedDevRomData = fb->ngle_rom; @@ -888,7 +888,7 @@ SETUP_HCRX(struct stifb_info *fb) /* Initialize Hyperbowl registers */ GET_FIFO_SLOTS(fb, nFreeFifoSlots, 7); - + if (IS_24_DEVICE(fb)) { hyperbowl = (fb->info.var.bits_per_pixel == 32) ? HYPERBOWL_MODE01_8_24_LUT0_TRANSPARENT_LUT1_OPAQUE : @@ -897,9 +897,9 @@ SETUP_HCRX(struct stifb_info *fb) /* First write to Hyperbowl must happen twice (bug) */ WRITE_WORD(hyperbowl, fb, REG_40); WRITE_WORD(hyperbowl, fb, REG_40); - + WRITE_WORD(HYPERBOWL_MODE2_8_24, fb, REG_39); - + WRITE_WORD(0x014c0148, fb, REG_42); /* Set lut 0 to be the direct color */ WRITE_WORD(0x404c4048, fb, REG_43); WRITE_WORD(0x034c0348, fb, REG_44); @@ -990,7 +990,7 @@ stifb_setcolreg(u_int regno, u_int red, u_int green, 0, /* Offset w/i LUT */ 256); /* Load entire LUT */ NGLE_BINC_SET_SRCADDR(fb, - NGLE_LONG_FB_ADDRESS(0, 0x100, 0)); + NGLE_LONG_FB_ADDRESS(0, 0x100, 0)); /* 0x100 is same as used in WRITE_IMAGE_COLOR() */ START_COLORMAPLOAD(fb, lutBltCtl.all); SETUP_FB(fb); @@ -1028,7 +1028,7 @@ stifb_blank(int blank_mode, struct fb_info *info) ENABLE_DISABLE_DISPLAY(fb, enable); break; } - + SETUP_FB(fb); return 0; } @@ -1114,15 +1114,15 @@ stifb_init_display(struct stifb_info *fb) /* HCRX specific initialization */ SETUP_HCRX(fb); - + /* if (id == S9000_ID_HCRX) hyperInitSprite(fb); else ngleInitSprite(fb); */ - - /* Initialize the image planes. */ + + /* Initialize the image planes. */ switch (id) { case S9000_ID_HCRX: hyperResetPlanes(fb, ENABLE); @@ -1194,7 +1194,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb = kzalloc(sizeof(*fb), GFP_ATOMIC); if (!fb) return -ENOMEM; - + info = &fb->info; /* set struct to a known state */ @@ -1235,7 +1235,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) dev_name, fb->id); goto out_err0; } - + /* default to 8 bpp on most graphic chips */ bpp = 8; xres = sti_onscreen_x(fb->sti); @@ -1256,7 +1256,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb->id = S9000_ID_A1659A; break; case S9000_ID_TIMBER: /* HP9000/710 Any (may be a grayscale device) */ - if (strstr(dev_name, "GRAYSCALE") || + if (strstr(dev_name, "GRAYSCALE") || strstr(dev_name, "Grayscale") || strstr(dev_name, "grayscale")) var->grayscale = 1; @@ -1295,16 +1295,16 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) case CRT_ID_VISUALIZE_EG: case S9000_ID_ARTIST: /* Artist */ break; - default: + default: #ifdef FALLBACK_TO_1BPP - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- now trying 1bpp mode instead\n", fb->id); bpp = 1; /* default to 1 bpp */ break; #else - printk(KERN_WARNING + printk(KERN_WARNING "stifb: Unsupported graphics card (id=0x%08x) " "- skipping.\n", fb->id); @@ -1320,11 +1320,11 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fix->line_length = (fb->sti->glob_cfg->total_x * bpp) / 8; if (!fix->line_length) fix->line_length = 2048; /* default */ - + /* limit fbsize to max visible screen size */ if (fix->smem_len > yres*fix->line_length) fix->smem_len = ALIGN(yres*fix->line_length, 4*1024*1024); - + fix->accel = FB_ACCEL_NONE; switch (bpp) { @@ -1350,7 +1350,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) default: break; } - + var->xres = var->xres_virtual = xres; var->yres = var->yres_virtual = yres; var->bits_per_pixel = bpp; @@ -1379,7 +1379,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fix->smem_start, fix->smem_start+fix->smem_len); goto out_err2; } - + if (!request_mem_region(fix->mmio_start, fix->mmio_len, "stifb mmio")) { printk(KERN_ERR "stifb: cannot reserve sti mmio region 0x%04lx-0x%04lx\n", fix->mmio_start, fix->mmio_start+fix->mmio_len); @@ -1393,11 +1393,11 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) fb_info(&fb->info, "%s %dx%d-%d frame buffer device, %s, id: %04x, mmio: 0x%04lx\n", fix->id, - var->xres, + var->xres, var->yres, var->bits_per_pixel, dev_name, - fb->id, + fb->id, fix->mmio_start); return 0; @@ -1426,7 +1426,7 @@ static int __init stifb_init(void) struct sti_struct *sti; struct sti_struct *def_sti; int i; - + #ifndef MODULE char *option = NULL; @@ -1438,7 +1438,7 @@ static int __init stifb_init(void) printk(KERN_INFO "stifb: disabled by \"stifb=off\" kernel parameter\n"); return -ENXIO; } - + def_sti = sti_get_rom(0); if (def_sti) { for (i = 1; i <= MAX_STI_ROMS; i++) { @@ -1472,7 +1472,7 @@ stifb_cleanup(void) { struct sti_struct *sti; int i; - + for (i = 1; i <= MAX_STI_ROMS; i++) { sti = sti_get_rom(i); if (!sti) @@ -1495,10 +1495,10 @@ int __init stifb_setup(char *options) { int i; - + if (!options || !*options) return 1; - + if (strncmp(options, "off", 3) == 0) { stifb_disabled = 1; options += 3; -- GitLab From 2fce6899b110f117edb6c27c7ad18a29e7c622db Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:13 +0200 Subject: [PATCH 4786/5631] fbdev: valkyriefb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/valkyriefb.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 1007023a5e88..b166b7cfe0e5 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -1,7 +1,7 @@ /* * valkyriefb.c -- frame buffer device for the PowerMac 'valkyrie' display * - * Created 8 August 1998 by + * Created 8 August 1998 by * Martin Costabel and Kevin Schoedel * * Vmode-switching changes and vmode 15/17 modifications created 29 August @@ -77,13 +77,13 @@ struct fb_info_valkyrie { struct fb_par_valkyrie par; struct cmap_regs __iomem *cmap_regs; unsigned long cmap_regs_phys; - + struct valkyrie_regs __iomem *valkyrie_regs; unsigned long valkyrie_regs_phys; - + __u8 __iomem *frame_buffer; unsigned long frame_buffer_phys; - + int sense; unsigned long total_vram; @@ -244,7 +244,7 @@ static inline int valkyrie_vram_reqd(int video_mode, int color_mode) { int pitch; struct valkyrie_regvals *init = valkyrie_reg_init[video_mode-1]; - + if ((pitch = init->pitch[color_mode]) == 0) pitch = 2 * init->pitch[0]; return init->vres * pitch; @@ -467,7 +467,7 @@ static int valkyrie_var_to_par(struct fb_var_screeninfo *var, printk(KERN_ERR "valkyriefb: vmode %d not valid.\n", vmode); return -EINVAL; } - + if (cmode != CMODE_8 && cmode != CMODE_16) { printk(KERN_ERR "valkyriefb: cmode %d not valid.\n", cmode); return -EINVAL; @@ -516,7 +516,7 @@ static void valkyrie_init_fix(struct fb_fix_screeninfo *fix, struct fb_info_valk fix->ywrapstep = 0; fix->ypanstep = 0; fix->xpanstep = 0; - + } /* Fix must already be inited above */ -- GitLab From 6208890495ded5429424b0335c7fd2d47fdffb83 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Fri, 31 Mar 2023 11:23:14 +0200 Subject: [PATCH 4787/5631] fbdev: vfb: Remove trailing whitespaces Fix coding style. No functional changes. Signed-off-by: Thomas Zimmermann Acked-by: Helge Deller Signed-off-by: Helge Deller --- drivers/video/fbdev/vfb.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c index a94573997d15..6f1990969361 100644 --- a/drivers/video/fbdev/vfb.c +++ b/drivers/video/fbdev/vfb.c @@ -111,7 +111,7 @@ static u_long get_line_length(int xres_virtual, int bpp) * First part, xxxfb_check_var, must not write anything * to hardware, it should only verify and adjust var. * This means it doesn't alter par but it does use hardware - * data from it to check this var. + * data from it to check this var. */ static int vfb_check_var(struct fb_var_screeninfo *var, @@ -169,7 +169,7 @@ static int vfb_check_var(struct fb_var_screeninfo *var, /* * Now that we checked it we alter var. The reason being is that the video - * mode passed in might not work but slight changes to it might make it + * mode passed in might not work but slight changes to it might make it * work. This way we let the user know what is acceptable. */ switch (var->bits_per_pixel) { @@ -235,8 +235,8 @@ static int vfb_check_var(struct fb_var_screeninfo *var, } /* This routine actually sets the video mode. It's in here where we - * the hardware state info->par and fix which can be affected by the - * change in par. For this driver it doesn't do much. + * the hardware state info->par and fix which can be affected by the + * change in par. For this driver it doesn't do much. */ static int vfb_set_par(struct fb_info *info) { @@ -379,7 +379,7 @@ static int vfb_pan_display(struct fb_var_screeninfo *var, } /* - * Most drivers don't need their own mmap function + * Most drivers don't need their own mmap function */ static int vfb_mmap(struct fb_info *info, -- GitLab From e910baa9c1efdf7634519c135c6723b0fd499683 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 May 2023 19:21:41 +0100 Subject: [PATCH 4788/5631] KVM: arm64: vgic: Add Apple M2 PRO/MAX cpus to the list of broken SEIS implementations Unsurprisingly, the M2 PRO is also affected by the SEIS bug, so add it to the naughty list. And since M2 MAX is likely to be of the same ilk, flag it as well. Tested on a M2 PRO mini machine. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20230501182141.39770-1-maz@kernel.org --- arch/arm64/include/asm/cputype.h | 8 ++++++++ arch/arm64/kvm/vgic/vgic-v3.c | 4 ++++ 2 files changed, 12 insertions(+) diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..93a47a515c13 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; -- GitLab From db40d2928d245f3a6cba9a6a2547ec955b00f0fc Mon Sep 17 00:00:00 2001 From: Luca Weiss Date: Mon, 8 May 2023 22:26:45 +0200 Subject: [PATCH 4789/5631] drm/msm/iommu: Fix null pointer dereference in no-IOMMU case In the case that no IOMMU is available, msm_iommu_new can return NULL which should be handled. Without we will get a NULL pointer dereference in the next statement when we try to use the mmu variable. Fixes: 8cceb773f565 ("drm/msm/adreno: stall translation on fault for all GPU families") Signed-off-by: Luca Weiss Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/535915/ Link: https://lore.kernel.org/r/20230508-6-4-drm-msm-iommu-fixup-v1-1-a7a21ec94f5b@z3ntu.xyz Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_iommu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 418e1e06cdde..5080319ae4cf 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -410,7 +410,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig struct msm_mmu *mmu; mmu = msm_iommu_new(dev, quirks); - if (IS_ERR(mmu)) + if (IS_ERR_OR_NULL(mmu)) return mmu; iommu = to_msm_iommu(mmu); -- GitLab From 68dc6c2d5eec45515855cce99256162f45651a0b Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 9 May 2023 13:30:41 -0700 Subject: [PATCH 4790/5631] drm/msm: Fix submit error-path leaks For errors after msm_submitqueue_get(), we need to drop the submitqueue reference. Additionally after get_unused_fd() we need to drop the fd. The ordering for dropping the queue lock and put_unused_fd() is not important, so just move this all into out_post_unlock. v2: Only drop queue ref if submit doesn't take it v3: Fix unitialized submit ref in error path v4: IS_ERR_OR_NULL() Reported-by: pinkperfect2021@gmail.com Fixes: f0de40a131d9 drm/msm: ("Reorder lock vs submit alloc") Signed-off-by: Rob Clark Patchwork: https://patchwork.freedesktop.org/patch/536073/ Link: https://lore.kernel.org/r/20230509203041.440619-1-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_gem_submit.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index aff18c2f600a..9f5933c75e3d 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -722,7 +722,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; - struct msm_gem_submit *submit; + struct msm_gem_submit *submit = NULL; struct msm_gpu *gpu = priv->gpu; struct msm_gpu_submitqueue *queue; struct msm_ringbuffer *ring; @@ -769,13 +769,15 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { ret = out_fence_fd; - return ret; + goto out_post_unlock; } } submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); - if (IS_ERR(submit)) - return PTR_ERR(submit); + if (IS_ERR(submit)) { + ret = PTR_ERR(submit); + goto out_post_unlock; + } trace_msm_gpu_submit(pid_nr(submit->pid), ring->id, submit->ident, args->nr_bos, args->nr_cmds); @@ -962,11 +964,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (has_ww_ticket) ww_acquire_fini(&submit->ticket); out_unlock: - if (ret && (out_fence_fd >= 0)) - put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); out_post_unlock: - msm_gem_submit_put(submit); + if (ret && (out_fence_fd >= 0)) + put_unused_fd(out_fence_fd); + + if (!IS_ERR_OR_NULL(submit)) { + msm_gem_submit_put(submit); + } else { + /* + * If the submit hasn't yet taken ownership of the queue + * then we need to drop the reference ourself: + */ + msm_submitqueue_put(queue); + } if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); -- GitLab From 3e10f6ca76c4d00019badebd235c9d7f0068261e Mon Sep 17 00:00:00 2001 From: Vitaly Rodionov Date: Wed, 10 May 2023 15:22:27 +0100 Subject: [PATCH 4791/5631] ALSA: hda/realtek: Add quirk for HP EliteBook G10 laptops Add support for HP EliteBook 835/845/845W/865 G10 laptops with CS35L41 amplifiers on I2C/SPI bus connected to Realtek codec. Signed-off-by: Vitaly Rodionov Cc: Link: https://lore.kernel.org/r/20230510142227.32945-1-vitalyr@opensource.cirrus.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index bc062c0a1916..5166f1eb510d 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9458,7 +9458,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), - SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9469,8 +9469,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b47, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b63, "HP Elite Dragonfly 13.5 inch G4", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b65, "HP ProBook 455 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b66, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b70, "HP EliteBook 835 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b72, "HP EliteBook 845 G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b74, "HP EliteBook 845W G10", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8b77, "HP ElieBook 865 G10", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8b7a, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b7d, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b87, "HP", ALC236_FIXUP_HP_GPIO_LED), @@ -9481,6 +9486,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), -- GitLab From 4b963ae1df6426f0e51de64133d379d9bde50c48 Mon Sep 17 00:00:00 2001 From: Alexandru Sorodoc Date: Thu, 11 May 2023 19:15:10 +0300 Subject: [PATCH 4792/5631] ALSA: hda/realtek: Add quirks for ASUS GU604V and GU603V These models use 2 CS35L41 amplifiers using SPI for down-facing speakers. alc285_fixup_speaker2_to_dac1 is needed to fix volume control of the down-facing speakers. Pin configs are needed to enable headset mic detection. Note that these models lack the ACPI _DSD properties needed to initialize the amplifiers. They can be added during boot to get working sound out of the speakers: https://gist.github.com/lamperez/862763881c0e1c812392b5574727f6ff Signed-off-by: Alexandru Sorodoc Link: https://lore.kernel.org/r/20230511161510.315170-1-ealex95@gmail.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 5166f1eb510d..3df32eced8e4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7063,6 +7063,8 @@ enum { ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC295_FIXUP_DISABLE_DAC3, ALC285_FIXUP_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1, + ALC285_FIXUP_ASUS_HEADSET_MIC, ALC280_FIXUP_HP_HEADSET_MIC, ALC221_FIXUP_HP_FRONT_MIC, ALC292_FIXUP_TPT460, @@ -8033,6 +8035,22 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_speaker2_to_dac1, + .chained = true, + .chain_id = ALC245_FIXUP_CS35L41_SPI_2 + }, + [ALC285_FIXUP_ASUS_HEADSET_MIC] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x03a11050 }, + { 0x1b, 0x03a11c30 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_ASUS_SPEAKER2_TO_DAC1 + }, [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -9506,6 +9524,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK), + SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604V", ALC285_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), -- GitLab From 155c45a25679f571c2ae57d10db843a9dfc63430 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sun, 5 Mar 2023 21:52:26 +0100 Subject: [PATCH 4793/5631] power: supply: Ratelimit no data debug output Reduce the amount of output this dev_dbg() statement emits into logs, otherwise if system software polls the sysfs entry for data and keeps getting -ENODATA, it could end up filling the logs up. This does in fact make systemd journald choke, since during boot the sysfs power supply entries are polled and if journald starts at the same time, the journal is just being repeatedly filled up, and the system stops on trying to start journald without booting any further. Signed-off-by: Marek Vasut Reviewed-by: Hans de Goede Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_sysfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index ba3b125cd66e..06e5b6b0e255 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -286,7 +286,8 @@ static ssize_t power_supply_show_property(struct device *dev, if (ret < 0) { if (ret == -ENODATA) - dev_dbg(dev, "driver has no data for `%s' property\n", + dev_dbg_ratelimited(dev, + "driver has no data for `%s' property\n", attr->attr.name); else if (ret != -ENODEV && ret != -EAGAIN) dev_err_ratelimited(dev, -- GitLab From c75f5a55061091030a13fef71b9995b89bc86213 Mon Sep 17 00:00:00 2001 From: Zheng Wang Date: Thu, 27 Apr 2023 11:08:41 +0800 Subject: [PATCH 4794/5631] fbdev: imsttfb: Fix use after free bug in imsttfb_probe A use-after-free bug may occur if init_imstt invokes framebuffer_release and free the info ptr. The caller, imsttfb_probe didn't notice that and still keep the ptr as private data in pdev. If we remove the driver which will call imsttfb_remove to make cleanup, UAF happens. Fix it by return error code if bad case happens in init_imstt. Signed-off-by: Zheng Wang Signed-off-by: Helge Deller --- drivers/video/fbdev/imsttfb.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index bea45647184e..975dd682fae4 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1347,7 +1347,7 @@ static const struct fb_ops imsttfb_ops = { .fb_ioctl = imsttfb_ioctl, }; -static void init_imstt(struct fb_info *info) +static int init_imstt(struct fb_info *info) { struct imstt_par *par = info->par; __u32 i, tmp, *ip, *end; @@ -1420,7 +1420,7 @@ static void init_imstt(struct fb_info *info) || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) { printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); framebuffer_release(info); - return; + return -ENODEV; } sprintf(info->fix.id, "IMS TT (%s)", par->ramdac == IBM ? "IBM" : "TVP"); @@ -1456,12 +1456,13 @@ static void init_imstt(struct fb_info *info) if (register_framebuffer(info) < 0) { framebuffer_release(info); - return; + return -ENODEV; } tmp = (read_reg_le32(par->dc_regs, SSTATUS) & 0x0f00) >> 8; fb_info(info, "%s frame buffer; %uMB vram; chip version %u\n", info->fix.id, info->fix.smem_len >> 20, tmp); + return 0; } static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) @@ -1529,10 +1530,10 @@ static int imsttfb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!par->cmap_regs) goto error; info->pseudo_palette = par->palette; - init_imstt(info); - - pci_set_drvdata(pdev, info); - return 0; + ret = init_imstt(info); + if (!ret) + pci_set_drvdata(pdev, info); + return ret; error: if (par->dc_regs) -- GitLab From 3b8803494a0612acdeee714cb72aa142b1e05ce5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 11 May 2023 15:19:05 +0300 Subject: [PATCH 4795/5631] PCI/DPC: Quirk PIO log size for Intel Ice Lake Root Ports Commit 5459c0b70467 ("PCI/DPC: Quirk PIO log size for certain Intel Root Ports") added quirks for Tiger and Alder Lake Root Ports but missed that the same issue exists also in the previous generation, Ice Lake. Apply the quirk for Ice Lake Root Ports as well. This prevents kernel complaints like: DPC: RP PIO log size 0 is invalid and also enables the DPC driver to dump the RP PIO Log registers when DPC is triggered. [bhelgaas: add dmesg warning and RP PIO Log dump info] Closes: https://bugzilla.kernel.org/show_bug.cgi?id=209943 Link: https://lore.kernel.org/r/20230511121905.73949-1-mika.westerberg@linux.intel.com Reported-by: Mark Blakeney Signed-off-by: Mika Westerberg Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index f4e2a88729fd..c525867760bf 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -6003,8 +6003,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x56c1, aspm_l1_acceptable_latency #ifdef CONFIG_PCIE_DPC /* - * Intel Tiger Lake and Alder Lake BIOS has a bug that clears the DPC - * RP PIO Log Size of the integrated Thunderbolt PCIe Root Ports. + * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears + * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root + * Ports. */ static void dpc_log_size(struct pci_dev *dev) { @@ -6027,6 +6028,10 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x461f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size); -- GitLab From 21a933c79a33add3612808f3be4ad65dd4dc026b Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 10 May 2023 13:16:37 +0200 Subject: [PATCH 4796/5631] selftests: seg6: disable DAD on IPv6 router cfg for srv6_end_dt4_l3vpn_test The srv6_end_dt4_l3vpn_test instantiates a virtual network consisting of several routers (rt-1, rt-2) and hosts. When the IPv6 addresses of rt-{1,2} routers are configured, the Deduplicate Address Detection (DAD) kicks in when enabled in the Linux distros running the selftests. DAD is used to check whether an IPv6 address is already assigned in a network. Such a mechanism consists of sending an ICMPv6 Echo Request and waiting for a reply. As the DAD process could take too long to complete, it may cause the failing of some tests carried out by the srv6_end_dt4_l3vpn_test script. To make the srv6_end_dt4_l3vpn_test more robust, we disable DAD on routers since we configure the virtual network manually and do not need any address deduplication mechanism at all. Fixes: 2195444e09b4 ("selftests: add selftest for the SRv6 End.DT4 behavior") Signed-off-by: Andrea Mayer Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 1003119773e5..37f08d582d2f 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -232,10 +232,14 @@ setup_rt_networking() local nsname=rt-${rt} ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link set veth-rt-${rt} netns ${nsname} ip -netns ${nsname} link set veth-rt-${rt} name veth0 - ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad ip -netns ${nsname} link set veth0 up ip -netns ${nsname} link set lo up -- GitLab From f97b8401e0deb46ad1e4245c21f651f64f55aaa6 Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Wed, 10 May 2023 13:16:38 +0200 Subject: [PATCH 4797/5631] selftets: seg6: disable rp_filter by default in srv6_end_dt4_l3vpn_test On some distributions, the rp_filter is automatically set (=1) by default on a netdev basis (also on VRFs). In an SRv6 End.DT4 behavior, decapsulated IPv4 packets are routed using the table associated with the VRF bound to that tunnel. During lookup operations, the rp_filter can lead to packet loss when activated on the VRF. Therefore, we chose to make this selftest more robust by explicitly disabling the rp_filter during tests (as it is automatically set by some Linux distributions). Fixes: 2195444e09b4 ("selftests: add selftest for the SRv6 End.DT4 behavior") Reported-by: Hangbin Liu Signed-off-by: Andrea Mayer Tested-by: Hangbin Liu Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/srv6_end_dt4_l3vpn_test.sh | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh index 37f08d582d2f..f96282362811 100755 --- a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh @@ -258,6 +258,12 @@ setup_hs() # set the networking for the host ip netns add ${hsname} + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.default.rp_filter=0 + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} ip -netns ${hsname} link set ${rtveth} netns ${rtname} ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 @@ -276,11 +282,6 @@ setup_hs() ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 - # disable the rp_filter otherwise the kernel gets confused about how - # to route decap ipv4 packets. - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 - ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 - ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" } -- GitLab From e93c9378e33f68b61ea9318580d841caa22fb9ea Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 10 May 2023 16:46:21 +0200 Subject: [PATCH 4798/5631] devlink: change per-devlink netdev notifier to static one The commit 565b4824c39f ("devlink: change port event netdev notifier from per-net to global") changed original per-net notifier to be per-devlink instance. That fixed the issue of non-receiving events of netdev uninit if that moved to a different namespace. That worked fine in -net tree. However, later on when commit ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") and commit 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend") were merged, a deadlock was introduced when removing a namespace with devlink instance with another nested instance. Here there is the bad flow example resulting in deadlock with mlx5: net_cleanup_work -> cleanup_net (takes down_read(&pernet_ops_rwsem) -> devlink_pernet_pre_exit() -> devlink_reload() -> mlx5_devlink_reload_down() -> mlx5_unload_one_devl_locked() -> mlx5_detach_device() -> del_adev() -> mlx5e_remove() -> mlx5e_destroy_devlink() -> devlink_free() -> unregister_netdevice_notifier() (takes down_write(&pernet_ops_rwsem) Steps to reproduce: $ modprobe mlx5_core $ ip netns add ns1 $ devlink dev reload pci/0000:08:00.0 netns ns1 $ ip netns del ns1 Resolve this by converting the notifier from per-devlink instance to a static one registered during init phase and leaving it registered forever. Use this notifier for all devlink port instances created later on. Note what a tree needs this fix only in case all of the cited fixes commits are present. Reported-by: Moshe Shemesh Fixes: 565b4824c39f ("devlink: change port event netdev notifier from per-net to global") Fixes: ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") Fixes: 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend") Signed-off-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230510144621.932017-1-jiri@resnulli.us Signed-off-by: Jakub Kicinski --- net/devlink/core.c | 16 +++++++--------- net/devlink/devl_internal.h | 1 - net/devlink/leftover.c | 5 ++--- 3 files changed, 9 insertions(+), 13 deletions(-) diff --git a/net/devlink/core.c b/net/devlink/core.c index 777b091ef74d..0e58eee44bdb 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -204,11 +204,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier(&devlink->netdevice_nb); - if (ret) - goto err_register_netdevice_notifier; - devlink->dev = dev; devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); @@ -233,8 +228,6 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, return devlink; -err_register_netdevice_notifier: - xa_erase(&devlinks, devlink->index); err_xa_alloc: kfree(devlink); return NULL; @@ -266,8 +259,6 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->params); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); - xa_erase(&devlinks, devlink->index); devlink_put(devlink); @@ -303,6 +294,10 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; +static struct notifier_block devlink_port_netdevice_nb __net_initdata = { + .notifier_call = devlink_port_netdevice_event, +}; + static int __init devlink_init(void) { int err; @@ -311,6 +306,9 @@ static int __init devlink_init(void) if (err) goto out; err = register_pernet_subsys(&devlink_pernet_ops); + if (err) + goto out; + err = register_netdevice_notifier(&devlink_port_netdevice_nb); out: WARN_ON(err); diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index e133f423294a..62921b2eb0d3 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -50,7 +50,6 @@ struct devlink { u8 reload_failed:1; refcount_t refcount; struct rcu_work rwork; - struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index dffca2f9bfa7..cd0254968076 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -7073,10 +7073,9 @@ int devlink_port_netdevice_event(struct notifier_block *nb, struct devlink_port *devlink_port = netdev->devlink_port; struct devlink *devlink; - devlink = container_of(nb, struct devlink, netdevice_nb); - - if (!devlink_port || devlink_port->devlink != devlink) + if (!devlink_port) return NOTIFY_OK; + devlink = devlink_port->devlink; switch (event) { case NETDEV_POST_INIT: -- GitLab From ef1148d4487438a3408d6face2a8360d91b4af70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 10 May 2023 15:46:46 +0000 Subject: [PATCH 4799/5631] ipv6: remove nexthop_fib6_nh_bh() After blamed commit, nexthop_fib6_nh_bh() and nexthop_fib6_nh() are the same. Delete nexthop_fib6_nh_bh(), and convert /proc/net/ipv6_route to standard rcu to avoid this splat: [ 5723.180080] WARNING: suspicious RCU usage [ 5723.180083] ----------------------------- [ 5723.180084] include/net/nexthop.h:516 suspicious rcu_dereference_check() usage! [ 5723.180086] other info that might help us debug this: [ 5723.180087] rcu_scheduler_active = 2, debug_locks = 1 [ 5723.180089] 2 locks held by cat/55856: [ 5723.180091] #0: ffff9440a582afa8 (&p->lock){+.+.}-{3:3}, at: seq_read_iter (fs/seq_file.c:188) [ 5723.180100] #1: ffffffffaac07040 (rcu_read_lock_bh){....}-{1:2}, at: rcu_lock_acquire (include/linux/rcupdate.h:326) [ 5723.180109] stack backtrace: [ 5723.180111] CPU: 14 PID: 55856 Comm: cat Tainted: G S I 6.3.0-dbx-DEV #528 [ 5723.180115] Call Trace: [ 5723.180117] [ 5723.180119] dump_stack_lvl (lib/dump_stack.c:107) [ 5723.180124] dump_stack (lib/dump_stack.c:114) [ 5723.180126] lockdep_rcu_suspicious (include/linux/context_tracking.h:122) [ 5723.180132] ipv6_route_seq_show (include/net/nexthop.h:?) [ 5723.180135] ? ipv6_route_seq_next (net/ipv6/ip6_fib.c:2605) [ 5723.180140] seq_read_iter (fs/seq_file.c:272) [ 5723.180145] seq_read (fs/seq_file.c:163) [ 5723.180151] proc_reg_read (fs/proc/inode.c:316 fs/proc/inode.c:328) [ 5723.180155] vfs_read (fs/read_write.c:468) [ 5723.180160] ? up_read (kernel/locking/rwsem.c:1617) [ 5723.180164] ksys_read (fs/read_write.c:613) [ 5723.180168] __x64_sys_read (fs/read_write.c:621) [ 5723.180170] do_syscall_64 (arch/x86/entry/common.c:?) [ 5723.180174] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) [ 5723.180177] RIP: 0033:0x7fa455677d2a Fixes: 09eed1192cec ("neighbour: switch to standard rcu, instead of rcu_bh") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230510154646.370659-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/net/nexthop.h | 23 ----------------------- net/ipv6/ip6_fib.c | 16 ++++++++-------- 2 files changed, 8 insertions(+), 31 deletions(-) diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 9fa291a04621..2b12725de9c0 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -497,29 +497,6 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } -/* Variant of nexthop_fib6_nh(). - * Caller should either hold rcu_read_lock(), or RTNL. - */ -static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) -{ - struct nh_info *nhi; - - if (nh->is_group) { - struct nh_group *nh_grp; - - nh_grp = rcu_dereference_rtnl(nh->nh_grp); - nh = nexthop_mpath_select(nh_grp, 0); - if (!nh) - return NULL; - } - - nhi = rcu_dereference_rtnl(nh->nh_info); - if (nhi->family == AF_INET6) - return &nhi->fib6_nh; - - return NULL; -} - static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2438da5ff6da..bac768d36cc1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2491,7 +2491,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh_bh(rt->nh); + fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); @@ -2556,14 +2556,14 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; - node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist)); + node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { - node = rcu_dereference_bh( + node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); @@ -2593,7 +2593,7 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!v) goto iter_table; - n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); + n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; @@ -2619,12 +2619,12 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU_BH) + __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; - rcu_read_lock_bh(); + rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; @@ -2645,7 +2645,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) - __releases(RCU_BH) + __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; @@ -2653,7 +2653,7 @@ static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); - rcu_read_unlock_bh(); + rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) -- GitLab From f816b9829b19394d318e01953aa3b2721bca040d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 10 May 2023 22:00:20 +0200 Subject: [PATCH 4800/5631] net: fec: Better handle pm_runtime_get() failing in .remove() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the (unlikely) event that pm_runtime_get() (disguised as pm_runtime_resume_and_get()) fails, the remove callback returned an error early. The problem with this is that the driver core ignores the error value and continues removing the device. This results in a resource leak. Worse the devm allocated resources are freed and so if a callback of the driver is called later the register mapping is already gone which probably results in a crash. Fixes: a31eda65ba21 ("net: fec: fix clock count mis-match") Signed-off-by: Uwe Kleine-König Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/20230510200020.1534610-1-u.kleine-koenig@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/fec_main.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 42ec6ca3bf03..241df41d500f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4478,9 +4478,11 @@ fec_drv_remove(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; int ret; - ret = pm_runtime_resume_and_get(&pdev->dev); + ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) - return ret; + dev_err(&pdev->dev, + "Failed to resume device in remove callback (%pe)\n", + ERR_PTR(ret)); cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -4493,8 +4495,13 @@ fec_drv_remove(struct platform_device *pdev) of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); - clk_disable_unprepare(fep->clk_ahb); - clk_disable_unprepare(fep->clk_ipg); + /* After pm_runtime_get_sync() failed, the clks are still off, so skip + * disabling them again. + */ + if (ret >= 0) { + clk_disable_unprepare(fep->clk_ahb); + clk_disable_unprepare(fep->clk_ipg); + } pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); -- GitLab From f63550e2b165208a2f382afcaf5551df9569e1d4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pawe=C5=82=20Anikiel?= Date: Mon, 8 May 2023 13:30:37 +0200 Subject: [PATCH 4801/5631] ASoC: ssm2602: Add workaround for playback distortions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apply a workaround for what appears to be a hardware quirk. The problem seems to happen when enabling "whole chip power" (bit D7 register R6) for the very first time after the chip receives power. If either "output" (D4) or "DAC" (D3) aren't powered on at that time, playback becomes very distorted later on. This happens on the Google Chameleon v3, as well as on a ZYBO Z7-10: https://ez.analog.com/audio/f/q-a/543726/solved-ssm2603-right-output-offset-issue/480229 I suspect this happens only when using an external MCLK signal (which is the case for both of these boards). Here are some experiments run on a Google Chameleon v3. These were run in userspace using a wrapper around the i2cset utility: ssmset() { i2cset -y 0 0x1a $(($1*2)) $2 } For each of the following sequences, we apply power to the ssm2603 chip, set the configuration registers R0-R5 and R7-R8, run the selected sequence, and check for distortions on playback. ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac OK ssmset 0x09 0x01 # core ssmset 0x06 0x87 # out, dac ssmset 0x06 0x07 # chip OK (disable MCLK) ssmset 0x09 0x01 # core ssmset 0x06 0x1f # chip ssmset 0x06 0x07 # out, dac (enable MCLK) OK ssmset 0x09 0x01 # core ssmset 0x06 0x1f # chip ssmset 0x06 0x07 # out, dac NOT OK ssmset 0x06 0x1f # chip ssmset 0x09 0x01 # core ssmset 0x06 0x07 # out, dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x0f # chip, out ssmset 0x06 0x07 # dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x17 # chip, dac ssmset 0x06 0x07 # out NOT OK For each of the following sequences, we apply power to the ssm2603 chip, run the selected sequence, issue a reset with R15, configure R0-R5 and R7-R8, run one of the NOT OK sequences from above, and check for distortions. ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac OK (disable MCLK) ssmset 0x09 0x01 # core ssmset 0x06 0x07 # chip, out, dac (enable MCLK after reset) NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x17 # chip, dac NOT OK ssmset 0x09 0x01 # core ssmset 0x06 0x0f # chip, out NOT OK ssmset 0x06 0x07 # chip, out, dac NOT OK Signed-off-by: Paweł Anikiel regmap, ssm2602_patch, + ARRAY_SIZE(ssm2602_patch)); + /* set the update bits */ regmap_update_bits(ssm2602->regmap, SSM2602_LINVOL, LINVOL_LRIN_BOTH, LINVOL_LRIN_BOTH); -- GitLab From 2b694fc96fe33a7c042e3a142d27d945c8c668b0 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Thu, 27 Apr 2023 12:34:53 -0700 Subject: [PATCH 4802/5631] powerpc/boot: Disable power10 features after BOOTAFLAGS assignment When building the boot wrapper assembly files with clang after commit 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU"), the following warnings appear for each file built: '-prefixed' is not a recognized feature for this target (ignoring feature) '-pcrel' is not a recognized feature for this target (ignoring feature) While it is questionable whether or not LLVM should be emitting a warning when passed negative versions of code generation flags when building assembly files (since it does not emit a warning for the altivec and vsx flags), it is easy enough to work around this by just moving the disabled flags to BOOTCFLAGS after the assignment of BOOTAFLAGS, so that they are not added when building assembly files. Do so to silence the warnings. Fixes: 648a1783fe25 ("powerpc/boot: Fix boot wrapper code generation with CONFIG_POWER10_CPU") Link: https://github.com/ClangBuiltLinux/linux/issues/1839 Reviewed-by: Nicholas Piggin Signed-off-by: Nathan Chancellor Signed-off-by: Michael Ellerman Link: https://msgid.link/20230427-remove-power10-args-from-boot-aflags-clang-v1-1-9107f7c943bc@kernel.org --- arch/powerpc/boot/Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 85cde5bf04b7..771b79423bbc 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,8 +34,6 @@ endif BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ - $(call cc-option,-mno-prefixed) $(call cc-option,-mno-pcrel) \ - $(call cc-option,-mno-mma) \ $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE) @@ -71,6 +69,10 @@ BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc BOOTARFLAGS := -crD +BOOTCFLAGS += $(call cc-option,-mno-prefixed) \ + $(call cc-option,-mno-pcrel) \ + $(call cc-option,-mno-mma) + ifdef CONFIG_CC_IS_CLANG BOOTCFLAGS += $(CLANG_FLAGS) BOOTAFLAGS += $(CLANG_FLAGS) -- GitLab From 0b01db274028f5acd207332686ffc92ac77491ac Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Wed, 10 May 2023 18:21:39 +0530 Subject: [PATCH 4803/5631] net: phy: dp83867: add w/a for packet errors seen with short cables Introduce the W/A for packet errors seen with short cables (<1m) between two DP83867 PHYs. The W/A recommended by DM requires FFE Equalizer Configuration tuning by writing value 0x0E81 to DSP_FFE_CFG register (0x012C), surrounded by hard and soft resets as follows: write_reg(0x001F, 0x8000); //hard reset write_reg(DSP_FFE_CFG, 0x0E81); write_reg(0x001F, 0x4000); //soft reset Since DP83867 PHY DM says "Changing this register to 0x0E81, will not affect Long Cable performance.", enable the W/A by default. Fixes: 2a10154abcb7 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Grygorii Strashko Signed-off-by: Siddharth Vadapalli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/dp83867.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index d75f526a20a4..76f5a2402fb0 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -44,6 +44,7 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_STRAP_STS2 0x006f #define DP83867_RGMIIDCTL 0x0086 +#define DP83867_DSP_FFE_CFG 0x012c #define DP83867_RXFCFG 0x0134 #define DP83867_RXFPMD1 0x0136 #define DP83867_RXFPMD2 0x0137 @@ -941,8 +942,27 @@ static int dp83867_phy_reset(struct phy_device *phydev) usleep_range(10, 20); - return phy_modify(phydev, MII_DP83867_PHYCTRL, + err = phy_modify(phydev, MII_DP83867_PHYCTRL, DP83867_PHYCR_FORCE_LINK_GOOD, 0); + if (err < 0) + return err; + + /* Configure the DSP Feedforward Equalizer Configuration register to + * improve short cable (< 1 meter) performance. This will not affect + * long cable performance. + */ + err = phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_DSP_FFE_CFG, + 0x0e81); + if (err < 0) + return err; + + err = phy_write(phydev, DP83867_CTRL, DP83867_SW_RESTART); + if (err < 0) + return err; + + usleep_range(10, 20); + + return 0; } static void dp83867_link_change_notify(struct phy_device *phydev) -- GitLab From d03a2f17627e8f94ce8c4790fede3ef7efe9be53 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 10 May 2023 19:42:43 -0300 Subject: [PATCH 4804/5631] MAINTAINERS: sctp: move Neil to CREDITS Neil moved away from SCTP related duties. Move him to CREDITS then and while at it, update SCTP project website. Signed-off-by: Marcelo Ricardo Leitner Acked-by: Xin Long Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- CREDITS | 4 ++++ MAINTAINERS | 3 +-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/CREDITS b/CREDITS index 2d9da9a7defa..de7e4dbbc599 100644 --- a/CREDITS +++ b/CREDITS @@ -1706,6 +1706,10 @@ S: Panoramastrasse 18 S: D-69126 Heidelberg S: Germany +N: Neil Horman +M: nhorman@tuxdriver.com +D: SCTP protocol maintainer. + N: Simon Horman M: horms@verge.net.au D: Renesas ARM/ARM64 SoC maintainer diff --git a/MAINTAINERS b/MAINTAINERS index e2fd64c2ebdc..69107014d39b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18842,12 +18842,11 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Neil Horman M: Marcelo Ricardo Leitner M: Xin Long L: linux-sctp@vger.kernel.org S: Maintained -W: http://lksctp.sourceforge.net +W: https://github.com/sctp/lksctp-tools/wiki F: Documentation/networking/sctp.rst F: include/linux/sctp.h F: include/net/sctp/ -- GitLab From 01e8f6cd108b8702d206c6352d919c045b842b82 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 10 May 2023 18:43:39 -0700 Subject: [PATCH 4805/5631] MAINTAINERS: don't CC docs@ for netlink spec changes Documentation/netlink/ contains machine-readable protocol specs in YAML. Those are much like device tree bindings, no point CCing docs@ for the changes. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 69107014d39b..13e20a9754e9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6211,6 +6211,7 @@ X: Documentation/devicetree/ X: Documentation/driver-api/media/ X: Documentation/firmware-guide/acpi/ X: Documentation/i2c/ +X: Documentation/netlink/ X: Documentation/power/ X: Documentation/spi/ X: Documentation/userspace-api/media/ @@ -14615,6 +14616,7 @@ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/core-api/netlink.rst +F: Documentation/netlink/ F: Documentation/networking/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ -- GitLab From de9c1a23add9e7842ce63ce6f498a05c66344311 Mon Sep 17 00:00:00 2001 From: Huayu Chen Date: Thu, 11 May 2023 08:50:56 +0200 Subject: [PATCH 4806/5631] nfp: fix NFP_NET_MAX_DSCP definition error The patch corrects the NFP_NET_MAX_DSCP definition in the main.h file. The incorrect definition result DSCP bits not being mapped properly when DCB is set. When NFP_NET_MAX_DSCP was defined as 4, the next 60 DSCP bits failed to be set. Fixes: 9b7fe8046d74 ("nfp: add DCB IEEE support") Cc: stable@vger.kernel.org Signed-off-by: Huayu Chen Acked-by: Simon Horman Signed-off-by: Louis Peens Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nic/main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.h b/drivers/net/ethernet/netronome/nfp/nic/main.h index 094374df42b8..38b8b10b03cd 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.h +++ b/drivers/net/ethernet/netronome/nfp/nic/main.h @@ -8,7 +8,7 @@ #ifdef CONFIG_DCB /* DCB feature definitions */ -#define NFP_NET_MAX_DSCP 4 +#define NFP_NET_MAX_DSCP 64 #define NFP_NET_MAX_TC IEEE_8021QAZ_MAX_TCS #define NFP_NET_MAX_PRIO 8 #define NFP_DCB_CFG_STRIDE 256 -- GitLab From 47af4291711f21e1282dbc1002baebba30595aa2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 11 May 2023 09:03:10 -0700 Subject: [PATCH 4807/5631] MAINTAINERS: exclude wireless drivers from netdev It seems that we mostly get netdev CCed on wireless patches which are written by people who don't know any better and CC everything that get_maintainers spits out. Rather than patches which indeed could benefit from general networking review. Marking them down in patchwork as Awaiting Upstream is a bit tedious. Signed-off-by: Jakub Kicinski Acked-by: Johannes Berg Acked-by: Kalle Valo Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 13e20a9754e9..e884937f0e28 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14567,6 +14567,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ F: drivers/connector/ F: drivers/net/ +X: drivers/net/wireless/ F: include/dt-bindings/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h -- GitLab From c0e72058d5e21982e61a29de6b098f7c1f0db498 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 9 May 2023 12:07:11 +0300 Subject: [PATCH 4808/5631] ALSA: firewire-digi00x: prevent potential use after free This code was supposed to return an error code if init_stream() failed, but it instead freed dg00x->rx_stream and returned success. This potentially leads to a use after free. Fixes: 9a08067ec318 ("ALSA: firewire-digi00x: support AMDTP domain") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/c224cbd5-d9e2-4cd4-9bcf-2138eb1d35c6@kili.mountain Signed-off-by: Takashi Iwai --- sound/firewire/digi00x/digi00x-stream.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index a15f55b0dce3..295163bb8abb 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -259,8 +259,10 @@ int snd_dg00x_stream_init_duplex(struct snd_dg00x *dg00x) return err; err = init_stream(dg00x, &dg00x->tx_stream); - if (err < 0) + if (err < 0) { destroy_stream(dg00x, &dg00x->rx_stream); + return err; + } err = amdtp_domain_init(&dg00x->domain); if (err < 0) { -- GitLab From 359b4315471181f108723c61612d96e383e56179 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 09:58:58 +0200 Subject: [PATCH 4809/5631] ALSA: usb-audio: Add a sample rate workaround for Line6 Pod Go Line6 Pod Go (0e41:424b) requires the similar workaround for the fixed 48k sample rate like other Line6 models. This patch adds the corresponding entry to line6_parse_audio_format_rate_quirk(). Reported-by: John Humlick Cc: Link: https://lore.kernel.org/r/20230512075858.22813-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/usb/format.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/format.c b/sound/usb/format.c index 4b1c5ba121f3..ab5fed9f55b6 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -423,6 +423,7 @@ static int line6_parse_audio_format_rates_quirk(struct snd_usb_audio *chip, case USB_ID(0x0e41, 0x4248): /* Line6 Helix >= fw 2.82 */ case USB_ID(0x0e41, 0x4249): /* Line6 Helix Rack >= fw 2.82 */ case USB_ID(0x0e41, 0x424a): /* Line6 Helix LT >= fw 2.82 */ + case USB_ID(0x0e41, 0x424b): /* Line6 Pod Go */ case USB_ID(0x19f7, 0x0011): /* Rode Rodecaster Pro */ return set_fixed_rate(fp, 48000, SNDRV_PCM_RATE_48000); } -- GitLab From cdc26ee89bddb9b6b2ae026a46d97855d5ba6694 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 24 Apr 2023 05:39:05 +0800 Subject: [PATCH 4810/5631] wifi: mt76: mt7996: fix endianness of MT_TXD6_TX_RATE To avoid sparse warning: sparse: warning: invalid assignment: |= sparse: left side has type restricted __le32 sparse: right side has type unsigned lon Fixes: 15ee62e73705 ("wifi: mt76: mt7996: enable BSS_CHANGED_BASIC_RATES support") Signed-off-by: Ryder Lee Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/16fa938373e3b145cb07a2c98d2428fea2abadba.1682285873.git.ryder.lee@mediatek.com --- drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 130eb7b4fd91..39a4a73ef8e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1088,7 +1088,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, else if (beacon && mvif->beacon_rates_idx) idx = mvif->beacon_rates_idx; - txwi[6] |= FIELD_PREP(MT_TXD6_TX_RATE, idx); + txwi[6] |= cpu_to_le32(FIELD_PREP(MT_TXD6_TX_RATE, idx)); txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE); } } -- GitLab From c7ab7a29ef5c0779574120d922256ce4651555d3 Mon Sep 17 00:00:00 2001 From: Ryder Lee Date: Mon, 24 Apr 2023 05:39:06 +0800 Subject: [PATCH 4811/5631] wifi: mt76: connac: fix stats->tx_bytes calculation The stats->tx_bytes shall subtract retry byte from tx byte. Fixes: 43eaa3689507 ("wifi: mt76: add PPDU based TxS support for WED device") Signed-off-by: Ryder Lee Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/b3cd45596943cf5a06b2e08e2fe732ab0b51311b.1682285873.git.ryder.lee@mediatek.com --- drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h | 2 +- drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h index a5ec0f631385..fabf637bdf7f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h @@ -173,7 +173,7 @@ enum { #define MT_TXS5_MPDU_TX_CNT GENMASK(31, 23) #define MT_TXS6_MPDU_FAIL_CNT GENMASK(31, 23) - +#define MT_TXS7_MPDU_RETRY_BYTE GENMASK(22, 0) #define MT_TXS7_MPDU_RETRY_CNT GENMASK(31, 23) /* RXD DW0 */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index ee0fbfcd07d6..d39a3cc5e381 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -608,7 +608,8 @@ bool mt76_connac2_mac_fill_txs(struct mt76_dev *dev, struct mt76_wcid *wcid, /* PPDU based reporting */ if (FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) { stats->tx_bytes += - le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE); + le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_BYTE) - + le32_get_bits(txs_data[7], MT_TXS7_MPDU_RETRY_BYTE); stats->tx_packets += le32_get_bits(txs_data[5], MT_TXS5_MPDU_TX_CNT); stats->tx_failed += -- GitLab From c0426c446d92023d344131d01d929bc25db7a24e Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Wed, 26 Apr 2023 11:47:37 +0800 Subject: [PATCH 4812/5631] wifi: rtw89: 8852b: adjust quota to avoid SER L1 caused by access null page Though SER can recover this case, traffic can get stuck for a while. Fix it by adjusting page quota to avoid hardware access null page of CMAC/DMAC. Fixes: a1cb097168fa ("wifi: rtw89: 8852b: configure DLE mem") Fixes: 3e870b481733 ("wifi: rtw89: 8852b: add HFC quota arrays") Cc: stable@vger.kernel.org Tested-by: Larry Finger Link: https://github.com/lwfinger/rtw89/issues/226#issuecomment-1520776761 Link: https://github.com/lwfinger/rtw89/issues/240 Signed-off-by: Ping-Ke Shih Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230426034737.24870-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw89/mac.c | 4 +++ drivers/net/wireless/realtek/rtw89/mac.h | 2 ++ drivers/net/wireless/realtek/rtw89/rtw8852b.c | 28 +++++++++---------- 3 files changed, 20 insertions(+), 14 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b8019cfc11b2..512de491a064 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -1425,6 +1425,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_size4 = {RTW89_WDE_PG_64, 0, 4096,}, /* PCIE 64 */ .wde_size6 = {RTW89_WDE_PG_64, 512, 0,}, + /* 8852B PCIE SCC */ + .wde_size7 = {RTW89_WDE_PG_64, 510, 2,}, /* DLFW */ .wde_size9 = {RTW89_WDE_PG_64, 0, 1024,}, /* 8852C DLFW */ @@ -1449,6 +1451,8 @@ const struct rtw89_mac_size_set rtw89_mac_size = { .wde_qt4 = {0, 0, 0, 0,}, /* PCIE 64 */ .wde_qt6 = {448, 48, 0, 16,}, + /* 8852B PCIE SCC */ + .wde_qt7 = {446, 48, 0, 16,}, /* 8852C DLFW */ .wde_qt17 = {0, 0, 0, 0,}, /* 8852C PCIE SCC */ diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index a8d9847ef0b4..6ba633ccdd03 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -792,6 +792,7 @@ struct rtw89_mac_size_set { const struct rtw89_dle_size wde_size0; const struct rtw89_dle_size wde_size4; const struct rtw89_dle_size wde_size6; + const struct rtw89_dle_size wde_size7; const struct rtw89_dle_size wde_size9; const struct rtw89_dle_size wde_size18; const struct rtw89_dle_size wde_size19; @@ -804,6 +805,7 @@ struct rtw89_mac_size_set { const struct rtw89_wde_quota wde_qt0; const struct rtw89_wde_quota wde_qt4; const struct rtw89_wde_quota wde_qt6; + const struct rtw89_wde_quota wde_qt7; const struct rtw89_wde_quota wde_qt17; const struct rtw89_wde_quota wde_qt18; const struct rtw89_ple_quota ple_qt4; diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index eaa2ea0586bc..6da1b603a9a9 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -18,25 +18,25 @@ RTW8852B_FW_BASENAME "-" __stringify(RTW8852B_FW_FORMAT_MAX) ".bin" static const struct rtw89_hfc_ch_cfg rtw8852b_hfc_chcfg_pcie[] = { - {5, 343, grp_0}, /* ACH 0 */ - {5, 343, grp_0}, /* ACH 1 */ - {5, 343, grp_0}, /* ACH 2 */ - {5, 343, grp_0}, /* ACH 3 */ + {5, 341, grp_0}, /* ACH 0 */ + {5, 341, grp_0}, /* ACH 1 */ + {4, 342, grp_0}, /* ACH 2 */ + {4, 342, grp_0}, /* ACH 3 */ {0, 0, grp_0}, /* ACH 4 */ {0, 0, grp_0}, /* ACH 5 */ {0, 0, grp_0}, /* ACH 6 */ {0, 0, grp_0}, /* ACH 7 */ - {4, 344, grp_0}, /* B0MGQ */ - {4, 344, grp_0}, /* B0HIQ */ + {4, 342, grp_0}, /* B0MGQ */ + {4, 342, grp_0}, /* B0HIQ */ {0, 0, grp_0}, /* B1MGQ */ {0, 0, grp_0}, /* B1HIQ */ {40, 0, 0} /* FWCMDQ */ }; static const struct rtw89_hfc_pub_cfg rtw8852b_hfc_pubcfg_pcie = { - 448, /* Group 0 */ + 446, /* Group 0 */ 0, /* Group 1 */ - 448, /* Public Max */ + 446, /* Public Max */ 0 /* WP threshold */ }; @@ -49,13 +49,13 @@ static const struct rtw89_hfc_param_ini rtw8852b_hfc_param_ini_pcie[] = { }; static const struct rtw89_dle_mem rtw8852b_dle_mem_pcie[] = { - [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt58}, - [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size6, - &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt6, - &rtw89_mac_size.wde_qt6, &rtw89_mac_size.ple_qt18, + [RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size7, + &rtw89_mac_size.ple_size6, &rtw89_mac_size.wde_qt7, + &rtw89_mac_size.wde_qt7, &rtw89_mac_size.ple_qt18, &rtw89_mac_size.ple_qt_52b_wow}, [RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_mac_size.wde_size9, &rtw89_mac_size.ple_size8, &rtw89_mac_size.wde_qt4, -- GitLab From bcafcb959a57a6890e900199690c5fc47da1a304 Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Mon, 8 May 2023 16:54:29 +0800 Subject: [PATCH 4813/5631] wifi: rtw88: use work to update rate to avoid RCU warning The ieee80211_ops::sta_rc_update must be atomic, because ieee80211_chan_bw_change() holds rcu_read lock while calling drv_sta_rc_update(), so create a work to do original things. Voluntary context switch within RCU read-side critical section! WARNING: CPU: 0 PID: 4621 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x571/0x5d0 CPU: 0 PID: 4621 Comm: kworker/u16:2 Tainted: G W OE Workqueue: phy3 ieee80211_chswitch_work [mac80211] RIP: 0010:rcu_note_context_switch+0x571/0x5d0 Call Trace: __schedule+0xb0/0x1460 ? __mod_timer+0x116/0x360 schedule+0x5a/0xc0 schedule_timeout+0x87/0x150 ? trace_raw_output_tick_stop+0x60/0x60 wait_for_completion_timeout+0x7b/0x140 usb_start_wait_urb+0x82/0x160 [usbcore usb_control_msg+0xe3/0x140 [usbcore rtw_usb_read+0x88/0xe0 [rtw_usb rtw_usb_read8+0xf/0x10 [rtw_usb rtw_fw_send_h2c_command+0xa0/0x170 [rtw_core rtw_fw_send_ra_info+0xc9/0xf0 [rtw_core drv_sta_rc_update+0x7c/0x160 [mac80211 ieee80211_chan_bw_change+0xfb/0x110 [mac80211 ieee80211_change_chanctx+0x38/0x130 [mac80211 ieee80211_vif_use_reserved_switch+0x34e/0x900 [mac80211 ieee80211_link_use_reserved_context+0x88/0xe0 [mac80211 ieee80211_chswitch_work+0x95/0x170 [mac80211 process_one_work+0x201/0x410 worker_thread+0x4a/0x3b0 ? process_one_work+0x410/0x410 kthread+0xe1/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 Cc: stable@vger.kernel.org Fixes: c1edc86472fc ("rtw88: add ieee80211:sta_rc_update ops") Reported-by: Larry Finger Link: https://lore.kernel.org/linux-wireless/f1e31e8e-f84e-3791-50fb-663a83c5c6e9@lwfinger.net/T/#t Signed-off-by: Ping-Ke Shih Tested-by: Larry Finger Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230508085429.46653-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw88/mac80211.c | 2 +- drivers/net/wireless/realtek/rtw88/main.c | 15 +++++++++++++++ drivers/net/wireless/realtek/rtw88/main.h | 3 +++ 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index 7aa6edad0d01..a6c024cab7ee 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -918,7 +918,7 @@ static void rtw_ops_sta_rc_update(struct ieee80211_hw *hw, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; if (changed & IEEE80211_RC_BW_CHANGED) - rtw_update_sta_info(rtwdev, si, true); + ieee80211_queue_work(rtwdev->hw, &si->rc_work); } const struct ieee80211_ops rtw_ops = { diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 5bf6b4581557..d30a191c9291 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -319,6 +319,17 @@ static u8 rtw_acquire_macid(struct rtw_dev *rtwdev) return mac_id; } +static void rtw_sta_rc_work(struct work_struct *work) +{ + struct rtw_sta_info *si = container_of(work, struct rtw_sta_info, + rc_work); + struct rtw_dev *rtwdev = si->rtwdev; + + mutex_lock(&rtwdev->mutex); + rtw_update_sta_info(rtwdev, si, true); + mutex_unlock(&rtwdev->mutex); +} + int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct ieee80211_vif *vif) { @@ -329,12 +340,14 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, if (si->mac_id >= RTW_MAX_MAC_ID_NUM) return -ENOSPC; + si->rtwdev = rtwdev; si->sta = sta; si->vif = vif; si->init_ra_lv = 1; ewma_rssi_init(&si->avg_rssi); for (i = 0; i < ARRAY_SIZE(sta->txq); i++) rtw_txq_init(rtwdev, sta->txq[i]); + INIT_WORK(&si->rc_work, rtw_sta_rc_work); rtw_update_sta_info(rtwdev, si, true); rtw_fw_media_status_report(rtwdev, si->mac_id, true); @@ -353,6 +366,8 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv; int i; + cancel_work_sync(&si->rc_work); + rtw_release_macid(rtwdev, si->mac_id); if (fw_exist) rtw_fw_media_status_report(rtwdev, si->mac_id, false); diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index a563285e90ed..9e841f6991a9 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -743,6 +743,7 @@ struct rtw_txq { DECLARE_EWMA(rssi, 10, 16); struct rtw_sta_info { + struct rtw_dev *rtwdev; struct ieee80211_sta *sta; struct ieee80211_vif *vif; @@ -767,6 +768,8 @@ struct rtw_sta_info { bool use_cfg_mask; struct cfg80211_bitrate_mask *mask; + + struct work_struct rc_work; }; enum rtw_bfee_role { -- GitLab From 92553ee03166ef8fa978e7683f9f4af30c9c4e6b Mon Sep 17 00:00:00 2001 From: "Ryan C. Underwood" Date: Thu, 11 May 2023 12:32:21 -0500 Subject: [PATCH 4814/5631] ALSA: hda/realtek: Apply HP B&O top speaker profile to Pavilion 15 The Pavilion 15 line has B&O top speakers similar to the x360 and applying the same profile produces good sound. Without this, the sound would be tinny and underpowered without either applying model=alc295-hp-x360 or booting another OS first. Signed-off-by: Ryan Underwood Fixes: 563785edfcef ("ALSA: hda/realtek - Add quirk entry for HP Pavilion 15") Link: https://lore.kernel.org/r/ZF0mpcMz3ezP9KQw@icequake.net Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3df32eced8e4..92a920f46b7c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9381,7 +9381,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x802f, "HP Z240", ALC221_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8077, "HP", ALC256_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x103c, 0x8158, "HP", ALC256_FIXUP_HP_HEADSET_MIC), - SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x820d, "HP Pavilion 15", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x8256, "HP", ALC221_FIXUP_HP_FRONT_MIC), SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360), SND_PCI_QUIRK(0x103c, 0x827f, "HP x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), -- GitLab From 9113302bb43cf7a6d5a414d49b29478e57451c86 Mon Sep 17 00:00:00 2001 From: Jan Sokolowski Date: Thu, 11 May 2023 08:53:19 -0700 Subject: [PATCH 4815/5631] ice: Fix undersized tx_flags variable As not all ICE_TX_FLAGS_* fit in current 16-bit limited tx_flags field that was introduced in the Fixes commit, VLAN-related information would be discarded completely. As such, creating a vlan and trying to run ping through would result in no traffic passing. Fix that by refactoring tx_flags variable into flags only and a separate variable that holds VLAN ID. As there is some space left, type variable can fit between those two. Pahole reports no size change to ice_tx_buf struct. Fixes: aa1d3faf71a6 ("ice: Robustify cleaning/completing XDP Tx buffers") Signed-off-by: Jan Sokolowski Reviewed-by: Alexander Lobakin Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 5 ++--- drivers/net/ethernet/intel/ice/ice_txrx.c | 8 +++----- drivers/net/ethernet/intel/ice/ice_txrx.h | 9 +++------ 3 files changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index c6d4926f0fcf..850db8e0e6b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -932,10 +932,9 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { - first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; + first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->tx_flags |= (skb->priority & 0x7) << - ICE_TX_FLAGS_VLAN_PR_S; + first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4fcf2d07eb85..059bd911c51d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1664,8 +1664,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) { td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1; - td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + td_tag = first->vid; } dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -1998,7 +1997,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { - first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; + first->vid = skb_vlan_tag_get(skb); if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; else @@ -2388,8 +2387,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_IL2TAG2 << ICE_TXD_CTX_QW1_CMD_S)); - offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + offload.cd_l2tag2 = first->vid; } /* set up TSO offload */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fff0efe28373..166413fc33f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -127,10 +127,6 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) #define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) -#define ICE_TX_FLAGS_VLAN_M 0xffff0000 -#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 -#define ICE_TX_FLAGS_VLAN_PR_S 29 -#define ICE_TX_FLAGS_VLAN_S 16 #define ICE_XDP_PASS 0 #define ICE_XDP_CONSUMED BIT(0) @@ -182,8 +178,9 @@ struct ice_tx_buf { unsigned int gso_segs; unsigned int nr_frags; /* used for mbuf XDP */ }; - u32 type:16; /* &ice_tx_buf_type */ - u32 tx_flags:16; + u32 tx_flags:12; + u32 type:4; /* &ice_tx_buf_type */ + u32 vid:16; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); }; -- GitLab From c8902258b2b8ecaa1b8d88c312853c5b14c2553d Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 22 Apr 2023 23:24:26 +0200 Subject: [PATCH 4816/5631] fbdev: modedb: Add 1920x1080 at 60 Hz video mode Add typical resolution for Full-HD monitors. Signed-off-by: Helge Deller --- drivers/video/fbdev/core/modedb.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 23cf8eba785d..f7e019dded0f 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -257,6 +257,11 @@ static const struct fb_videomode modedb[] = { { NULL, 72, 480, 300, 33386, 40, 24, 11, 19, 80, 3, 0, FB_VMODE_DOUBLE }, + /* 1920x1080 @ 60 Hz, 67.3 kHz hsync */ + { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, 0, + FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, + FB_VMODE_NONINTERLACED }, + /* 1920x1200 @ 60 Hz, 74.5 Khz hsync */ { NULL, 60, 1920, 1200, 5177, 128, 336, 1, 38, 208, 3, FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, -- GitLab From 134120b066044399ef59564ff3ba66ab344cfc5b Mon Sep 17 00:00:00 2001 From: Pieter Jansen van Vuuren Date: Thu, 11 May 2023 10:43:33 +0100 Subject: [PATCH 4817/5631] sfc: disable RXFCS and RXALL features by default By default we would not want RXFCS and RXALL features enabled as they are mainly intended for debugging purposes. This does not stop users from enabling them later on as needed. Fixes: 8e57daf70671 ("sfc_ef100: RX path for EF100") Signed-off-by: Pieter Jansen van Vuuren Co-developed-by: Edward Cree Signed-off-by: Edward Cree Reviewed-by: Martin Habets Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ef100_netdev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index d916877b5a9a..be395cd8770b 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -378,7 +378,9 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data) efx->net_dev = net_dev; SET_NETDEV_DEV(net_dev, &efx->pci_dev->dev); - net_dev->features |= efx->type->offload_features; + /* enable all supported features except rx-fcs and rx-all */ + net_dev->features |= efx->type->offload_features & + ~(NETIF_F_RXFCS | NETIF_F_RXALL); net_dev->hw_features |= efx->type->offload_features; net_dev->hw_enc_features |= efx->type->offload_features; net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | -- GitLab From 6d4486efe9c69626cab423456169e250a5cd3af5 Mon Sep 17 00:00:00 2001 From: Zhuang Shengen Date: Thu, 11 May 2023 19:34:30 +0800 Subject: [PATCH 4818/5631] vsock: avoid to close connected socket after the timeout MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When client and server establish a connection through vsock, the client send a request to the server to initiate the connection, then start a timer to wait for the server's response. When the server's RESPONSE message arrives, the timer also times out and exits. The server's RESPONSE message is processed first, and the connection is established. However, the client's timer also times out, the original processing logic of the client is to directly set the state of this vsock to CLOSE and return ETIMEDOUT. It will not notify the server when the port is released, causing the server port remain. when client's vsock_connect timeout，it should check sk state is ESTABLISHED or not. if sk state is ESTABLISHED, it means the connection is established, the client should not set the sk state to CLOSE Note: I encountered this issue on kernel-4.18, which can be fixed by this patch. Then I checked the latest code in the community and found similar issue. Fixes: d021c344051a ("VSOCK: Introduce VM Sockets") Signed-off-by: Zhuang Shengen Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 413407bb646c..efb8a0937a13 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1462,7 +1462,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; -- GitLab From 9dc68a4fe70893b000fb3c92c68b9f72369cf448 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 12 May 2023 16:34:16 +0800 Subject: [PATCH 4819/5631] ALSA: hda/realtek: Fix mute and micmute LEDs for yet another HP laptop There's yet another laptop that needs the fixup to enable mute and micmute LEDs. So do it accordingly. Signed-off-by: Kai-Heng Feng Cc: Link: https://lore.kernel.org/r/20230512083417.157127-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 92a920f46b7c..a7e4765eff80 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9503,6 +9503,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b8f, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c26, "HP HP EliteBook 800G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), -- GitLab From 1e306ec49a1f206fd2cc89a42fac6e6f592a8cc1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 May 2023 11:47:49 +0000 Subject: [PATCH 4820/5631] tcp: fix possible sk_priority leak in tcp_v4_send_reset() When tcp_v4_send_reset() is called with @sk == NULL, we do not change ctl_sk->sk_priority, which could have been set from a prior invocation. Change tcp_v4_send_reset() to set sk_priority and sk_mark fields before calling ip_send_unicast_reply(). This means tcp_v4_send_reset() and tcp_v4_send_ack() no longer have to clear ctl_sk->sk_mark after their call to ip_send_unicast_reply(). Fixes: f6c0f5d209fa ("tcp: honor SO_PRIORITY in TIME_WAIT state") Signed-off-by: Eric Dumazet Cc: Antoine Tenart Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 39bda2b1066e..06d2573685ca 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -829,6 +829,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); xfrm_sk_clone_policy(ctl_sk, sk); + } else { + ctl_sk->sk_mark = 0; + ctl_sk->sk_priority = 0; } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -836,7 +839,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; xfrm_sk_free_policy(ctl_sk); sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); @@ -935,7 +937,6 @@ static void tcp_v4_send_ack(const struct sock *sk, &arg, arg.iov[0].iov_len, transmit_time); - ctl_sk->sk_mark = 0; sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); -- GitLab From 0bdf1ad8d10bd4e50a8b1a2c53d15984165f7fea Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Fri, 12 May 2023 11:50:33 +0200 Subject: [PATCH 4821/5631] fbdev: stifb: Fix info entry in sti_struct on error path Minor fix to reset the info field to NULL in case of error. Signed-off-by: Helge Deller --- drivers/video/fbdev/stifb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 29912ee80f5b..14c9215284c5 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1413,6 +1413,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref) iounmap(info->screen_base); out_err0: kfree(fb); + sti->info = NULL; return -ENXIO; } -- GitLab From 4913cfcf014c95f0437db2df1734472fd3e15098 Mon Sep 17 00:00:00 2001 From: Ivan Orlov Date: Fri, 12 May 2023 17:05:32 +0400 Subject: [PATCH 4822/5631] nbd: Fix debugfs_create_dir error checking The debugfs_create_dir function returns ERR_PTR in case of error, and the only correct way to check if an error occurred is 'IS_ERR' inline function. This patch will replace the null-comparison with IS_ERR. Signed-off-by: Ivan Orlov Link: https://lore.kernel.org/r/20230512130533.98709-1-ivan.orlov0322@gmail.com Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 9c35c958f2c8..65ecde3e2a5b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1666,7 +1666,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) return -EIO; dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir); - if (!dir) { + if (IS_ERR(dir)) { dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n", nbd_name(nbd)); return -EIO; @@ -1692,7 +1692,7 @@ static int nbd_dbg_init(void) struct dentry *dbg_dir; dbg_dir = debugfs_create_dir("nbd", NULL); - if (!dbg_dir) + if (IS_ERR(dbg_dir)) return -EIO; nbd_dbg_dir = dbg_dir; -- GitLab From 5e6e08087a4acb4ee3574cea32dbff0f63c7f608 Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Fri, 12 May 2023 11:46:31 +0800 Subject: [PATCH 4823/5631] block/rnbd: replace REQ_OP_FLUSH with REQ_OP_WRITE Since flush bios are implemented as writes with no data and the preflush flag per Christoph's comment [1]. And we need to change it in rnbd accordingly. Otherwise, I got splatting when create fs from rnbd client. [ 464.028545] ------------[ cut here ]------------ [ 464.028553] WARNING: CPU: 0 PID: 65 at block/blk-core.c:751 submit_bio_noacct+0x32c/0x5d0 [ ... ] [ 464.028668] CPU: 0 PID: 65 Comm: kworker/0:1H Tainted: G OE 6.4.0-rc1 #9 [ 464.028671] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 [ 464.028673] Workqueue: ib-comp-wq ib_cq_poll_work [ib_core] [ 464.028717] RIP: 0010:submit_bio_noacct+0x32c/0x5d0 [ 464.028720] Code: 03 0f 85 51 fe ff ff 48 8b 43 18 8b 88 04 03 00 00 85 c9 0f 85 3f fe ff ff e9 be fd ff ff 0f b6 d0 3c 0d 74 26 83 fa 01 74 21 <0f> 0b b8 0a 00 00 00 e9 56 fd ff ff 4c 89 e7 e8 70 a1 03 00 84 c0 [ 464.028722] RSP: 0018:ffffaf3680b57c68 EFLAGS: 00010202 [ 464.028724] RAX: 0000000000060802 RBX: ffffa09dcc18bf00 RCX: 0000000000000000 [ 464.028726] RDX: 0000000000000002 RSI: 0000000000000000 RDI: ffffa09dde081d00 [ 464.028727] RBP: ffffaf3680b57c98 R08: ffffa09dde081d00 R09: ffffa09e38327200 [ 464.028729] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa09dde081d00 [ 464.028730] R13: ffffa09dcb06e1e8 R14: 0000000000000000 R15: 0000000000200000 [ 464.028733] FS: 0000000000000000(0000) GS:ffffa09e3bc00000(0000) knlGS:0000000000000000 [ 464.028735] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 464.028736] CR2: 000055a4e8206c40 CR3: 0000000119f06000 CR4: 00000000003506f0 [ 464.028738] Call Trace: [ 464.028740] [ 464.028746] submit_bio+0x1b/0x80 [ 464.028748] rnbd_srv_rdma_ev+0x50d/0x10c0 [rnbd_server] [ 464.028754] ? percpu_ref_get_many.constprop.0+0x55/0x140 [rtrs_server] [ 464.028760] ? __this_cpu_preempt_check+0x13/0x20 [ 464.028769] process_io_req+0x1dc/0x450 [rtrs_server] [ 464.028775] rtrs_srv_inv_rkey_done+0x67/0xb0 [rtrs_server] [ 464.028780] __ib_process_cq+0xbc/0x1f0 [ib_core] [ 464.028793] ib_cq_poll_work+0x2b/0xa0 [ib_core] [ 464.028804] process_one_work+0x2a9/0x580 [1]. https://lore.kernel.org/all/ZFHgefWofVt24tRl@infradead.org/ Signed-off-by: Guoqing Jiang Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20230512034631.28686-1-guoqing.jiang@linux.dev Signed-off-by: Jens Axboe --- drivers/block/rnbd/rnbd-proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index ea7ac8bca63c..da1d0542d7e2 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -241,7 +241,7 @@ static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf) bio_opf = REQ_OP_WRITE; break; case RNBD_OP_FLUSH: - bio_opf = REQ_OP_FLUSH | REQ_PREFLUSH; + bio_opf = REQ_OP_WRITE | REQ_PREFLUSH; break; case RNBD_OP_DISCARD: bio_opf = REQ_OP_DISCARD; -- GitLab From e485bd9e2c419142430ae6fe3e8f64e3059aef50 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 5 May 2023 23:31:42 +0800 Subject: [PATCH 4824/5631] ublk: fix command op code check In case of CONFIG_BLKDEV_UBLK_LEGACY_OPCODES, type of cmd opcode could be 0 or 'u'; and type can only be 'u' if CONFIG_BLKDEV_UBLK_LEGACY_OPCODES isn't set. So fix the wrong check. Fixes: 2d786e66c966 ("block: ublk: switch to ioctl command encoding") Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20230505153142.1258336-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7331f519750..c7ed5d69e9ee 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1281,7 +1281,7 @@ static inline int ublk_check_cmd_op(u32 cmd_op) { u32 ioc_type = _IOC_TYPE(cmd_op); - if (IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u') + if (!IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u') return -EOPNOTSUPP; if (ioc_type != 'u' && ioc_type != 0) -- GitLab From c04fe8e32f907ea668f3f802387c1148fdb0e6c9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 9 May 2023 09:12:24 -0600 Subject: [PATCH 4825/5631] pipe: check for IOCB_NOWAIT alongside O_NONBLOCK Pipe reads or writes need to enable nonblocking attempts, if either O_NONBLOCK is set on the file, or IOCB_NOWAIT is set in the iocb being passed in. The latter isn't currently true, ensure we check for both before waiting on data or space. Fixes: afed6271f5b0 ("pipe: set FMODE_NOWAIT on pipes") Signed-off-by: Jens Axboe Message-Id: Signed-off-by: Christian Brauner --- fs/pipe.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index ceb17d2dfa19..2d88f73f585a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -342,7 +342,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) break; if (ret) break; - if (filp->f_flags & O_NONBLOCK) { + if ((filp->f_flags & O_NONBLOCK) || + (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } @@ -547,7 +548,8 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) continue; /* Wait for buffer space to become available. */ - if (filp->f_flags & O_NONBLOCK) { + if ((filp->f_flags & O_NONBLOCK) || + (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; -- GitLab From 9c2cc74fb31ec76b8b118c97041a6a154a3ff219 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Tue, 2 May 2023 03:20:47 -0700 Subject: [PATCH 4826/5631] xtensa: fix signal delivery to FDPIC process Fetch function descriptor pointed to by the signal handler pointer from userspace on signal delivery and function pointer pointed to by the sa_restorer on return from the signal handler. Cc: stable@vger.kernel.org Fixes: e3ddb8bbe0f8 ("xtensa: add FDPIC and static PIE support for noMMU") Signed-off-by: Max Filippov --- arch/xtensa/kernel/signal.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c index 876d5df157ed..5c01d7e70d90 100644 --- a/arch/xtensa/kernel/signal.c +++ b/arch/xtensa/kernel/signal.c @@ -343,7 +343,19 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, struct rt_sigframe *frame; int err = 0, sig = ksig->sig; unsigned long sp, ra, tp, ps; + unsigned long handler = (unsigned long)ksig->ka.sa.sa_handler; + unsigned long handler_fdpic_GOT = 0; unsigned int base; + bool fdpic = IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) && + (current->personality & FDPIC_FUNCPTRS); + + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)handler; + if (__get_user(handler, &fdpic_func_desc[0]) || + __get_user(handler_fdpic_GOT, &fdpic_func_desc[1])) + return -EFAULT; + } sp = regs->areg[1]; @@ -373,20 +385,26 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (ksig->ka.sa.sa_flags & SA_RESTORER) { - ra = (unsigned long)ksig->ka.sa.sa_restorer; + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)ksig->ka.sa.sa_restorer; + + err |= __get_user(ra, fdpic_func_desc); + } else { + ra = (unsigned long)ksig->ka.sa.sa_restorer; + } } else { /* Create sys_rt_sigreturn syscall in stack frame */ err |= gen_return_code(frame->retcode); - - if (err) { - return -EFAULT; - } ra = (unsigned long) frame->retcode; } - /* + if (err) + return -EFAULT; + + /* * Create signal handler execution context. * Return context not modified until this point. */ @@ -394,8 +412,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, /* Set up registers for signal handler; preserve the threadptr */ tp = regs->threadptr; ps = regs->ps; - start_thread(regs, (unsigned long) ksig->ka.sa.sa_handler, - (unsigned long) frame); + start_thread(regs, handler, (unsigned long)frame); /* Set up a stack frame for a call4 if userspace uses windowed ABI */ if (ps & PS_WOE_MASK) { @@ -413,6 +430,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set, regs->areg[base + 4] = (unsigned long) &frame->uc; regs->threadptr = tp; regs->ps = ps; + if (fdpic) + regs->areg[base + 11] = handler_fdpic_GOT; pr_debug("SIG rt deliver (%s:%d): signal=%d sp=%p pc=%08lx\n", current->comm, current->pid, sig, frame, regs->pc); -- GitLab From 034f4a7877c32a8efd6beee4d71ed14e424499a9 Mon Sep 17 00:00:00 2001 From: Max Filippov Date: Sat, 6 May 2023 17:10:36 -0700 Subject: [PATCH 4827/5631] xtensa: add __bswap{si,di}2 helpers gcc-13 may generate calls for __bswap{si,di}2. This breaks the kernel build when optimization for size is selected. Add __bswap{si,di}2 helpers to fix that. Cc: stable@vger.kernel.org Fixes: 19c5699f9aff ("xtensa: don't link with libgcc") Signed-off-by: Max Filippov --- arch/xtensa/kernel/xtensa_ksyms.c | 4 ++++ arch/xtensa/lib/Makefile | 2 +- arch/xtensa/lib/bswapdi2.S | 21 +++++++++++++++++++++ arch/xtensa/lib/bswapsi2.S | 16 ++++++++++++++++ 4 files changed, 42 insertions(+), 1 deletion(-) create mode 100644 arch/xtensa/lib/bswapdi2.S create mode 100644 arch/xtensa/lib/bswapsi2.S diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 2a31b1ab0c9f..17a7ef86fd0d 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -56,6 +56,8 @@ EXPORT_SYMBOL(empty_zero_page); */ extern long long __ashrdi3(long long, int); extern long long __ashldi3(long long, int); +extern long long __bswapdi2(long long); +extern int __bswapsi2(int); extern long long __lshrdi3(long long, int); extern int __divsi3(int, int); extern int __modsi3(int, int); @@ -66,6 +68,8 @@ extern unsigned long long __umulsidi3(unsigned int, unsigned int); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__bswapdi2); +EXPORT_SYMBOL(__bswapsi2); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__divsi3); EXPORT_SYMBOL(__modsi3); diff --git a/arch/xtensa/lib/Makefile b/arch/xtensa/lib/Makefile index 7ecef0519a27..c9c2614188f7 100644 --- a/arch/xtensa/lib/Makefile +++ b/arch/xtensa/lib/Makefile @@ -4,7 +4,7 @@ # lib-y += memcopy.o memset.o checksum.o \ - ashldi3.o ashrdi3.o lshrdi3.o \ + ashldi3.o ashrdi3.o bswapdi2.o bswapsi2.o lshrdi3.o \ divsi3.o udivsi3.o modsi3.o umodsi3.o mulsi3.o umulsidi3.o \ usercopy.o strncpy_user.o strnlen_user.o lib-$(CONFIG_PCI) += pci-auto.o diff --git a/arch/xtensa/lib/bswapdi2.S b/arch/xtensa/lib/bswapdi2.S new file mode 100644 index 000000000000..d8e52e05eba6 --- /dev/null +++ b/arch/xtensa/lib/bswapdi2.S @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include +#include +#include + +ENTRY(__bswapdi2) + + abi_entry_default + ssai 8 + srli a4, a2, 16 + src a4, a4, a2 + src a4, a4, a4 + src a4, a2, a4 + srli a2, a3, 16 + src a2, a2, a3 + src a2, a2, a2 + src a2, a3, a2 + mov a3, a4 + abi_ret_default + +ENDPROC(__bswapdi2) diff --git a/arch/xtensa/lib/bswapsi2.S b/arch/xtensa/lib/bswapsi2.S new file mode 100644 index 000000000000..9c1de1344f79 --- /dev/null +++ b/arch/xtensa/lib/bswapsi2.S @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later WITH GCC-exception-2.0 */ +#include +#include +#include + +ENTRY(__bswapsi2) + + abi_entry_default + ssai 8 + srli a3, a2, 16 + src a3, a3, a2 + src a3, a3, a3 + src a2, a2, a3 + abi_ret_default + +ENDPROC(__bswapsi2) -- GitLab From 56cdea92ed915f8eb37575331fb4a269991e8026 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 7 May 2023 11:26:06 -0700 Subject: [PATCH 4828/5631] Documentation/block: drop the request.rst file Documentation/block/request.rst is outdated and should be removed. Also delete its entry in the block/index.rst file. Signed-off-by: Randy Dunlap Cc: Jens Axboe Cc: linux-block@vger.kernel.org Cc: Jonathan Corbet Cc: linux-doc@vger.kernel.org Link: https://lore.kernel.org/r/20230507182606.12647-1-rdunlap@infradead.org Signed-off-by: Jens Axboe --- Documentation/block/index.rst | 1 - Documentation/block/request.rst | 99 --------------------------------- 2 files changed, 100 deletions(-) delete mode 100644 Documentation/block/request.rst diff --git a/Documentation/block/index.rst b/Documentation/block/index.rst index 102953166429..9fea696f9daa 100644 --- a/Documentation/block/index.rst +++ b/Documentation/block/index.rst @@ -18,7 +18,6 @@ Block kyber-iosched null_blk pr - request stat switching-sched writeback_cache_control diff --git a/Documentation/block/request.rst b/Documentation/block/request.rst deleted file mode 100644 index 747021e1ffdb..000000000000 --- a/Documentation/block/request.rst +++ /dev/null @@ -1,99 +0,0 @@ -============================ -struct request documentation -============================ - -Jens Axboe 27/05/02 - - -.. FIXME: - No idea about what does mean - seems just some noise, so comment it - - 1.0 - Index - - 2.0 Struct request members classification - - 2.1 struct request members explanation - - 3.0 - - - 2.0 - - - -Short explanation of request members -==================================== - -Classification flags: - - = ==================== - D driver member - B block layer member - I I/O scheduler member - = ==================== - -Unless an entry contains a D classification, a device driver must not access -this member. Some members may contain D classifications, but should only be -access through certain macros or functions (eg ->flags). - - - -=============================== ======= ======================================= -Member Flag Comment -=============================== ======= ======================================= -struct list_head queuelist BI Organization on various internal - queues - -``void *elevator_private`` I I/O scheduler private data - -unsigned char cmd[16] D Driver can use this for setting up - a cdb before execution, see - blk_queue_prep_rq - -unsigned long flags DBI Contains info about data direction, - request type, etc. - -int rq_status D Request status bits - -kdev_t rq_dev DBI Target device - -int errors DB Error counts - -sector_t sector DBI Target location - -unsigned long hard_nr_sectors B Used to keep sector sane - -unsigned long nr_sectors DBI Total number of sectors in request - -unsigned long hard_nr_sectors B Used to keep nr_sectors sane - -unsigned short nr_phys_segments DB Number of physical scatter gather - segments in a request - -unsigned short nr_hw_segments DB Number of hardware scatter gather - segments in a request - -unsigned int current_nr_sectors DB Number of sectors in first segment - of request - -unsigned int hard_cur_sectors B Used to keep current_nr_sectors sane - -int tag DB TCQ tag, if assigned - -``void *special`` D Free to be used by driver - -``char *buffer`` D Map of first segment, also see - section on bouncing SECTION - -``struct completion *waiting`` D Can be used by driver to get signalled - on request completion - -``struct bio *bio`` DBI First bio in request - -``struct bio *biotail`` DBI Last bio in request - -``struct request_queue *q`` DB Request queue this request belongs to - -``struct request_list *rl`` B Request list this request came from -=============================== ======= ======================================= -- GitLab From 08c7f09356e45d093d1867c7a3c6ac6526e2f98b Mon Sep 17 00:00:00 2001 From: Selvin Xavier Date: Sun, 7 May 2023 11:29:29 -0700 Subject: [PATCH 4829/5631] RDMA/bnxt_re: Fix the page_size used during the MR creation Driver populates the list of pages used for Memory region wrongly when page size is more than system page size. This is causing a failure when some of the applications that creates MR with page size as 2M. Since HW can support multiple page sizes, pass the correct page size while creating the MR. Also, driver need not adjust the number of pages when HW Queues are created with user memory. It should work with the number of dma blocks returned by ib_umem_num_dma_blocks. Fix this calculation also. Fixes: 0c4dcd602817 ("RDMA/bnxt_re: Refactor hardware queue memory allocation") Fixes: f6919d56388c ("RDMA/bnxt_re: Code refactor while populating user MRs") Link: https://lore.kernel.org/r/1683484169-9539-1-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Kalesh AP Signed-off-by: Kashyap Desai Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/qplib_res.c | 12 ++---------- drivers/infiniband/hw/bnxt_re/qplib_sp.c | 7 +++---- 2 files changed, 5 insertions(+), 14 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c index 126d4f26f75a..81b0c5e879f9 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_res.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c @@ -215,17 +215,9 @@ int bnxt_qplib_alloc_init_hwq(struct bnxt_qplib_hwq *hwq, return -EINVAL; hwq_attr->sginfo->npages = npages; } else { - unsigned long sginfo_num_pages = ib_umem_num_dma_blocks( - hwq_attr->sginfo->umem, hwq_attr->sginfo->pgsize); - + npages = ib_umem_num_dma_blocks(hwq_attr->sginfo->umem, + hwq_attr->sginfo->pgsize); hwq->is_user = true; - npages = sginfo_num_pages; - npages = (npages * PAGE_SIZE) / - BIT_ULL(hwq_attr->sginfo->pgshft); - if ((sginfo_num_pages * PAGE_SIZE) % - BIT_ULL(hwq_attr->sginfo->pgshft)) - if (!npages) - npages++; } if (npages == MAX_PBL_LVL_0_PGS && !hwq_attr->sginfo->nopte) { diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index 1714a1e23113..b967a17a44be 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -617,16 +617,15 @@ int bnxt_qplib_reg_mr(struct bnxt_qplib_res *res, struct bnxt_qplib_mrw *mr, /* Free the hwq if it already exist, must be a rereg */ if (mr->hwq.max_elements) bnxt_qplib_free_hwq(res, &mr->hwq); - /* Use system PAGE_SIZE */ hwq_attr.res = res; hwq_attr.depth = pages; - hwq_attr.stride = buf_pg_size; + hwq_attr.stride = sizeof(dma_addr_t); hwq_attr.type = HWQ_TYPE_MR; hwq_attr.sginfo = &sginfo; hwq_attr.sginfo->umem = umem; hwq_attr.sginfo->npages = pages; - hwq_attr.sginfo->pgsize = PAGE_SIZE; - hwq_attr.sginfo->pgshft = PAGE_SHIFT; + hwq_attr.sginfo->pgsize = buf_pg_size; + hwq_attr.sginfo->pgshft = ilog2(buf_pg_size); rc = bnxt_qplib_alloc_init_hwq(&mr->hwq, &hwq_attr); if (rc) { dev_err(&res->pdev->dev, -- GitLab From 78b6a9a3f445e121ca08195084206cb8faa6999f Mon Sep 17 00:00:00 2001 From: Haoyue Xu Date: Sat, 6 May 2023 15:06:04 +0800 Subject: [PATCH 4830/5631] MAINTAINERS: Update maintainers of HiSilicon RoCE Wenpeng has moved to other technical areas, and Junxian will take over his responsibilities in maintaining this module. Link: https://lore.kernel.org/r/20230506070604.2982542-1-xuhaoyue1@hisilicon.com Signed-off-by: Haoyue Xu Signed-off-by: Jason Gunthorpe --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e0b87d5aa2e..c56043737848 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9360,7 +9360,7 @@ F: drivers/crypto/hisilicon/zip/ HISILICON ROCE DRIVER M: Haoyue Xu -M: Wenpeng Liang +M: Junxian Huang L: linux-rdma@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt -- GitLab From 9a48d604672220545d209e9996c2a1edbb5637f6 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Fri, 12 May 2023 23:12:26 +0200 Subject: [PATCH 4831/5631] x86/retbleed: Fix return thunk alignment SYM_FUNC_START_LOCAL_NOALIGN() adds an endbr leading to this layout (leaving only the last 2 bytes of the address): 3bff : 3bff: f3 0f 1e fa endbr64 3c03: f6 test $0xcc,%bl 3c04 <__x86_return_thunk>: 3c04: c3 ret 3c05: cc int3 3c06: 0f ae e8 lfence However, "the RET at __x86_return_thunk must be on a 64 byte boundary, for alignment within the BTB." Use SYM_START instead. Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Thomas Gleixner Cc: Signed-off-by: Linus Torvalds --- arch/x86/lib/retpoline.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 27ef53fab6bd..b3b1e376dce8 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -144,8 +144,8 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ .align 64 .skip 63, 0xcc -SYM_FUNC_START_NOALIGN(zen_untrain_ret); - +SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR /* * As executed from zen_untrain_ret, this is: * -- GitLab From 270205be711056534d1f86d275d4ec922fb62102 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 12 May 2023 14:31:35 -0700 Subject: [PATCH 4832/5631] tools/testing/cxl: Use DEFINE_STATIC_SRCU() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Starting with commit: 95433f726301 ("srcu: Begin offloading srcu_struct fields to srcu_update") ...it is no longer possible to do: static DEFINE_SRCU(x) Switch to DEFINE_STATIC_SRCU(x) to fix: tools/testing/cxl/test/mock.c:22:1: error: duplicate ‘static’ 22 | static DEFINE_SRCU(cxl_mock_srcu); | ^~~~~~ Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/168392709546.1135523.10424917245934547117.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- tools/testing/cxl/test/mock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index c4e53f22e421..de3933a776fd 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -19,7 +19,7 @@ void register_cxl_mock_ops(struct cxl_mock_ops *ops) } EXPORT_SYMBOL_GPL(register_cxl_mock_ops); -static DEFINE_SRCU(cxl_mock_srcu); +DEFINE_STATIC_SRCU(cxl_mock_srcu); void unregister_cxl_mock_ops(struct cxl_mock_ops *ops) { -- GitLab From 53558de2b5c4f4ee6bfcfbe34e27071c2d0073d5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 17 Jan 2023 17:10:16 +0000 Subject: [PATCH 4833/5631] media: pvrusb2: fix DVB_CORE dependency Now that DVB_CORE can be a loadable module, pvrusb2 can run into a link error: ld.lld: error: undefined symbol: dvb_module_probe >>> referenced by pvrusb2-devattr.c >>> drivers/media/usb/pvrusb2/pvrusb2-devattr.o:(pvr2_lgdt3306a_attach) in archive vmlinux.a ld.lld: error: undefined symbol: dvb_module_release >>> referenced by pvrusb2-devattr.c >>> drivers/media/usb/pvrusb2/pvrusb2-devattr.o:(pvr2_dual_fe_attach) in archive vmlinux.a Refine the Kconfig dependencies to avoid this case. Link: https://lore.kernel.org/linux-media/20230117171055.2714621-1-arnd@kernel.org Fixes: 7655c342dbc4 ("media: Kconfig: Make DVB_CORE=m possible when MEDIA_SUPPORT=y") Signed-off-by: Arnd Bergmann Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/pvrusb2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/usb/pvrusb2/Kconfig b/drivers/media/usb/pvrusb2/Kconfig index 9501b10b31aa..0df10270dbdf 100644 --- a/drivers/media/usb/pvrusb2/Kconfig +++ b/drivers/media/usb/pvrusb2/Kconfig @@ -37,6 +37,7 @@ config VIDEO_PVRUSB2_DVB bool "pvrusb2 ATSC/DVB support" default y depends on VIDEO_PVRUSB2 && DVB_CORE + depends on VIDEO_PVRUSB2=m || DVB_CORE=y select DVB_LGDT330X if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1409 if MEDIA_SUBDRV_AUTOSELECT select DVB_S5H1411 if MEDIA_SUBDRV_AUTOSELECT -- GitLab From 7efb10d8dc70ea3000cc70dca53407c52488acd1 Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Sun, 5 Mar 2023 21:25:19 +0000 Subject: [PATCH 4834/5631] media: dvb_demux: fix a bug for the continuity counter In dvb_demux.c, some logics exist which compare the expected continuity counter and the real continuity counter. If they are not matched each other, both of the expected continuity counter and the real continuity counter should be printed. But there exists a bug that the expected continuity counter is not correctly printed. The expected continuity counter is replaced with the real countinuity counter + 1 so that the epected continuity counter is not correclty printed. This is wrong. This bug is fixed. Link: https://lore.kernel.org/linux-media/20230305212519.499-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_demux.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c index 398c86279b5b..7c4d86bfdd6c 100644 --- a/drivers/media/dvb-core/dvb_demux.c +++ b/drivers/media/dvb-core/dvb_demux.c @@ -115,12 +115,12 @@ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } + feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; @@ -300,7 +300,6 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; - feed->cc = cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ @@ -336,6 +335,7 @@ static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } + feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ -- GitLab From 764d102ef94e880ca834a7fe3968a00a05b1fb12 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Sat, 13 May 2023 00:20:06 -0700 Subject: [PATCH 4835/5631] cxl: Add missing return to cdat read error path Add a return to the error path when cxl_cdat_read_table() fails. Current code continues with the table pointer points to freed memory. Fixes: 7a877c923995 ("cxl/pci: Simplify CDAT retrieval error path") Signed-off-by: Dave Jiang Reviewed-by: Davidlohr Bueso Link: https://lore.kernel.org/r/168382793506.3510737.4792518576623749076.stgit@djiang5-mobl3 Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index bdbd907884ce..f332fe7af92b 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -571,6 +571,7 @@ void read_cdat_data(struct cxl_port *port) /* Don't leave table data allocated on error */ devm_kfree(dev, cdat_table); dev_err(dev, "CDAT data read error\n"); + return; } port->cdat.table = cdat_table + sizeof(__le32); -- GitLab From 94d25e9128988c6a1fc9070f6e98215a95795bd8 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 1 May 2023 14:22:35 -0400 Subject: [PATCH 4836/5631] USB: usbtmc: Fix direction for 0-length ioctl control messages The syzbot fuzzer found a problem in the usbtmc driver: When a user submits an ioctl for a 0-length control transfer, the driver does not check that the direction is set to OUT: ------------[ cut here ]------------ usb 3-1: BOGUS control dir, pipe 80000b80 doesn't match bRequestType fd WARNING: CPU: 0 PID: 5100 at drivers/usb/core/urb.c:411 usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Modules linked in: CPU: 0 PID: 5100 Comm: syz-executor428 Not tainted 6.3.0-syzkaller-12049-g58390c8ce1bd #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 RIP: 0010:usb_submit_urb+0x14a7/0x1880 drivers/usb/core/urb.c:411 Code: 7c 24 40 e8 1b 13 5c fb 48 8b 7c 24 40 e8 21 1d f0 fe 45 89 e8 44 89 f1 4c 89 e2 48 89 c6 48 c7 c7 e0 b5 fc 8a e8 19 c8 23 fb <0f> 0b e9 9f ee ff ff e8 ed 12 5c fb 0f b6 1d 12 8a 3c 08 31 ff 41 RSP: 0018:ffffc90003d2fb00 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff8880789e9058 RCX: 0000000000000000 RDX: ffff888029593b80 RSI: ffffffff814c1447 RDI: 0000000000000001 RBP: ffff88801ea742f8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88802915e528 R13: 00000000000000fd R14: 0000000080000b80 R15: ffff8880222b3100 FS: 0000555556ca63c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f9ef4d18150 CR3: 0000000073e5b000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: usb_start_wait_urb+0x101/0x4b0 drivers/usb/core/message.c:58 usb_internal_control_msg drivers/usb/core/message.c:102 [inline] usb_control_msg+0x320/0x4a0 drivers/usb/core/message.c:153 usbtmc_ioctl_request drivers/usb/class/usbtmc.c:1954 [inline] usbtmc_ioctl+0x1b3d/0x2840 drivers/usb/class/usbtmc.c:2097 To fix this, we must override the direction in the bRequestType field of the control request structure when the length is 0. Reported-and-tested-by: syzbot+ce77725b89b7bd52425c@syzkaller.appspotmail.com Signed-off-by: Alan Stern Link: https://lore.kernel.org/linux-usb/000000000000716a3705f9adb8ee@google.com/ CC: Link: https://lore.kernel.org/r/ede1ee02-b718-49e7-a44c-51339fec706b@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/class/usbtmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 4bb6d304eb4b..311007b1d904 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -1928,6 +1928,8 @@ static int usbtmc_ioctl_request(struct usbtmc_device_data *data, if (request.req.wLength > USBTMC_BUFSIZE) return -EMSGSIZE; + if (request.req.wLength == 0) /* Length-0 requests are never IN */ + request.req.bRequestType &= ~USB_DIR_IN; is_in = request.req.bRequestType & USB_DIR_IN; -- GitLab From c8540870af4ce6ddeb27a7bb5498b75fb29b643c Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Wed, 3 May 2023 14:00:48 +0300 Subject: [PATCH 4837/5631] usb: dwc3: gadget: Improve dwc3_gadget_suspend() and dwc3_gadget_resume() Prevent -ETIMEDOUT error on .suspend(). e.g. If gadget driver is loaded and we are connected to a USB host, all transfers must be stopped before stopping the controller else we will not get a clean stop i.e. dwc3_gadget_run_stop() will take several seconds to complete and will return -ETIMEDOUT. Handle error cases properly in dwc3_gadget_suspend(). Simplify dwc3_gadget_resume() by using the introduced helper function. Fixes: 9f8a67b65a49 ("usb: dwc3: gadget: fix gadget suspend/resume") Cc: stable@vger.kernel.org Suggested-by: Thinh Nguyen Signed-off-by: Roger Quadros Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230503110048.30617-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/gadget.c | 67 ++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 33 deletions(-) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index c0ca4d12f95d..2996bcb4d53d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2699,6 +2699,21 @@ static int dwc3_gadget_soft_disconnect(struct dwc3 *dwc) return ret; } +static int dwc3_gadget_soft_connect(struct dwc3 *dwc) +{ + /* + * In the Synopsys DWC_usb31 1.90a programming guide section + * 4.1.9, it specifies that for a reconnect after a + * device-initiated disconnect requires a core soft reset + * (DCTL.CSftRst) before enabling the run/stop bit. + */ + dwc3_core_soft_reset(dwc); + + dwc3_event_buffers_setup(dwc); + __dwc3_gadget_start(dwc); + return dwc3_gadget_run_stop(dwc, true); +} + static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) { struct dwc3 *dwc = gadget_to_dwc(g); @@ -2737,21 +2752,10 @@ static int dwc3_gadget_pullup(struct usb_gadget *g, int is_on) synchronize_irq(dwc->irq_gadget); - if (!is_on) { + if (!is_on) ret = dwc3_gadget_soft_disconnect(dwc); - } else { - /* - * In the Synopsys DWC_usb31 1.90a programming guide section - * 4.1.9, it specifies that for a reconnect after a - * device-initiated disconnect requires a core soft reset - * (DCTL.CSftRst) before enabling the run/stop bit. - */ - dwc3_core_soft_reset(dwc); - - dwc3_event_buffers_setup(dwc); - __dwc3_gadget_start(dwc); - ret = dwc3_gadget_run_stop(dwc, true); - } + else + ret = dwc3_gadget_soft_connect(dwc); pm_runtime_put(dwc->dev); @@ -4655,42 +4659,39 @@ void dwc3_gadget_exit(struct dwc3 *dwc) int dwc3_gadget_suspend(struct dwc3 *dwc) { unsigned long flags; + int ret; if (!dwc->gadget_driver) return 0; - dwc3_gadget_run_stop(dwc, false); + ret = dwc3_gadget_soft_disconnect(dwc); + if (ret) + goto err; spin_lock_irqsave(&dwc->lock, flags); dwc3_disconnect_gadget(dwc); - __dwc3_gadget_stop(dwc); spin_unlock_irqrestore(&dwc->lock, flags); return 0; + +err: + /* + * Attempt to reset the controller's state. Likely no + * communication can be established until the host + * performs a port reset. + */ + if (dwc->softconnect) + dwc3_gadget_soft_connect(dwc); + + return ret; } int dwc3_gadget_resume(struct dwc3 *dwc) { - int ret; - if (!dwc->gadget_driver || !dwc->softconnect) return 0; - ret = __dwc3_gadget_start(dwc); - if (ret < 0) - goto err0; - - ret = dwc3_gadget_run_stop(dwc, true); - if (ret < 0) - goto err1; - - return 0; - -err1: - __dwc3_gadget_stop(dwc); - -err0: - return ret; + return dwc3_gadget_soft_connect(dwc); } void dwc3_gadget_process_pending_events(struct dwc3 *dwc) -- GitLab From 4e8ef34e36f2839ef8c8da521ab7035956436818 Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Fri, 12 May 2023 08:45:24 +0800 Subject: [PATCH 4838/5631] usb: dwc3: fix gadget mode suspend interrupt handler issue When work in gadget mode, currently driver doesn't update software level link_state correctly as link state change event is not enabled for most devices, in function dwc3_gadget_suspend_interrupt(), it will only pass suspend event to UDC core when software level link state changes, so when interrupt generated in sequences of suspend -> reset -> conndone -> suspend, link state is not updated during reset and conndone, so second suspend interrupt event will not pass to UDC core. Remove link_state compare in dwc3_gadget_suspend_interrupt() and add a suspended flag to replace the compare function. Fixes: 799e9dc82968 ("usb: dwc3: gadget: conditionally disable Link State change events") Cc: stable Acked-by: Thinh Nguyen Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/20230512004524.31950-1-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.h | 2 ++ drivers/usb/dwc3/gadget.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index d56457c02996..1f043c31a096 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1116,6 +1116,7 @@ struct dwc3_scratchpad_array { * @dis_metastability_quirk: set to disable metastability quirk. * @dis_split_quirk: set to disable split boundary. * @wakeup_configured: set if the device is configured for remote wakeup. + * @suspended: set to track suspend event due to U3/L2. * @imod_interval: set the interrupt moderation interval in 250ns * increments or 0 to disable. * @max_cfg_eps: current max number of IN eps used across all USB configs. @@ -1332,6 +1333,7 @@ struct dwc3 { unsigned dis_split_quirk:1; unsigned async_callbacks:1; unsigned wakeup_configured:1; + unsigned suspended:1; u16 imod_interval; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 2996bcb4d53d..d831f5acf7b5 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2440,6 +2440,7 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) return -EINVAL; } dwc3_resume_gadget(dwc); + dwc->suspended = false; dwc->link_state = DWC3_LINK_STATE_U0; } @@ -3942,6 +3943,8 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) { int reg; + dwc->suspended = false; + dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RX_DET); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -3966,6 +3969,8 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) { u32 reg; + dwc->suspended = false; + /* * Ideally, dwc3_reset_gadget() would trigger the function * drivers to stop any active transfers through ep disable. @@ -4184,6 +4189,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc, unsigned int evtinfo) { + dwc->suspended = false; + /* * TODO take core out of low power mode when that's * implemented. @@ -4281,6 +4288,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, if (dwc->gadget->wakeup_armed) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); + dwc->suspended = false; } break; case DWC3_LINK_STATE_U1: @@ -4307,8 +4315,10 @@ static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; - if (dwc->link_state != next && next == DWC3_LINK_STATE_U3) + if (!dwc->suspended && next == DWC3_LINK_STATE_U3) { + dwc->suspended = true; dwc3_suspend_gadget(dwc); + } dwc->link_state = next; } -- GitLab From dddb342b5b9e482bb213aecc08cbdb201ea4f8da Mon Sep 17 00:00:00 2001 From: Weitao Wang Date: Sun, 23 Apr 2023 18:59:52 +0800 Subject: [PATCH 4839/5631] USB: UHCI: adjust zhaoxin UHCI controllers OverCurrent bit value OverCurrent condition is not standardized in the UHCI spec. Zhaoxin UHCI controllers report OverCurrent bit active off. In order to handle OverCurrent condition correctly, the uhci-hcd driver needs to be told to expect the active-off behavior. Suggested-by: Alan Stern Cc: stable@vger.kernel.org Signed-off-by: Weitao Wang Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230423105952.4526-1-WeitaoWang-oc@zhaoxin.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/uhci-pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/host/uhci-pci.c b/drivers/usb/host/uhci-pci.c index 3592f757fe05..7bd2fddde770 100644 --- a/drivers/usb/host/uhci-pci.c +++ b/drivers/usb/host/uhci-pci.c @@ -119,11 +119,13 @@ static int uhci_pci_init(struct usb_hcd *hcd) uhci->rh_numports = uhci_count_ports(hcd); - /* Intel controllers report the OverCurrent bit active on. - * VIA controllers report it active off, so we'll adjust the - * bit value. (It's not standardized in the UHCI spec.) + /* + * Intel controllers report the OverCurrent bit active on. VIA + * and ZHAOXIN controllers report it active off, so we'll adjust + * the bit value. (It's not standardized in the UHCI spec.) */ - if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA) + if (to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_VIA || + to_pci_dev(uhci_dev(uhci))->vendor == PCI_VENDOR_ID_ZHAOXIN) uhci->oc_low = 1; /* HP's server management chip requires a longer port reset delay. */ -- GitLab From 614ce6a2ea50068b45339257891e51e639ac9001 Mon Sep 17 00:00:00 2001 From: Udipto Goswami Date: Tue, 9 May 2023 20:18:36 +0530 Subject: [PATCH 4840/5631] usb: dwc3: debugfs: Resume dwc3 before accessing registers When the dwc3 device is runtime suspended, various required clocks are in disabled state and it is not guaranteed that access to any registers would work. Depending on the SoC glue, a register read could be as benign as returning 0 or be fatal enough to hang the system. In order to prevent such scenarios of fatal errors, make sure to resume dwc3 then allow the function to proceed. Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver") Cc: stable@vger.kernel.org #3.2: 30332eeefec8: debugfs: regset32: Add Runtime PM support Signed-off-by: Udipto Goswami Reviewed-by: Johan Hovold Tested-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/20230509144836.6803-1-quic_ugoswami@quicinc.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/debugfs.c | 109 +++++++++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/drivers/usb/dwc3/debugfs.c b/drivers/usb/dwc3/debugfs.c index e4a2560b9dc0..ebf03468fac4 100644 --- a/drivers/usb/dwc3/debugfs.c +++ b/drivers/usb/dwc3/debugfs.c @@ -332,6 +332,11 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) unsigned int current_mode; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); @@ -350,6 +355,8 @@ static int dwc3_lsp_show(struct seq_file *s, void *unused) } spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -395,6 +402,11 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GCTL); @@ -414,6 +426,8 @@ static int dwc3_mode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %08x\n", DWC3_GCTL_PRTCAP(reg)); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -463,6 +477,11 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) struct dwc3 *dwc = s->private; unsigned long flags; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_DCTL); @@ -493,6 +512,8 @@ static int dwc3_testmode_show(struct seq_file *s, void *unused) seq_printf(s, "UNKNOWN %d\n", reg); } + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -509,6 +530,7 @@ static ssize_t dwc3_testmode_write(struct file *file, unsigned long flags; u32 testmode = 0; char buf[32]; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -526,10 +548,16 @@ static ssize_t dwc3_testmode_write(struct file *file, else testmode = 0; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); dwc3_gadget_set_test_mode(dwc, testmode); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -548,12 +576,18 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) enum dwc3_link_state state; u32 reg; u8 speed; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { seq_puts(s, "Not available\n"); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return 0; } @@ -566,6 +600,8 @@ static int dwc3_link_state_show(struct seq_file *s, void *unused) dwc3_gadget_hs_link_string(state)); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -584,6 +620,7 @@ static ssize_t dwc3_link_state_write(struct file *file, char buf[32]; u32 reg; u8 speed; + int ret; if (copy_from_user(&buf, ubuf, min_t(size_t, sizeof(buf) - 1, count))) return -EFAULT; @@ -603,10 +640,15 @@ static ssize_t dwc3_link_state_write(struct file *file, else return -EINVAL; + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; + spin_lock_irqsave(&dwc->lock, flags); reg = dwc3_readl(dwc->regs, DWC3_GSTS); if (DWC3_GSTS_CURMOD(reg) != DWC3_GSTS_CURMOD_DEVICE) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } @@ -616,12 +658,15 @@ static ssize_t dwc3_link_state_write(struct file *file, if (speed < DWC3_DSTS_SUPERSPEED && state != DWC3_LINK_STATE_RECOV) { spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); return -EINVAL; } dwc3_gadget_set_link_state(dwc, state); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return count; } @@ -645,6 +690,11 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXFIFO); @@ -657,6 +707,8 @@ static int dwc3_tx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -667,6 +719,11 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) unsigned long flags; u32 mdwidth; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXFIFO); @@ -679,6 +736,8 @@ static int dwc3_rx_fifo_size_show(struct seq_file *s, void *unused) seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -688,12 +747,19 @@ static int dwc3_tx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_TXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -703,12 +769,19 @@ static int dwc3_rx_request_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXREQQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -718,12 +791,19 @@ static int dwc3_rx_info_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_RXINFOQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -733,12 +813,19 @@ static int dwc3_descriptor_fetch_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_DESCFETCHQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -748,12 +835,19 @@ static int dwc3_event_queue_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; u32 val; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); val = dwc3_core_fifo_space(dep, DWC3_EVENTQ); seq_printf(s, "%u\n", val); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -798,6 +892,11 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) struct dwc3 *dwc = dep->dwc; unsigned long flags; int i; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); if (dep->number <= 1) { @@ -827,6 +926,8 @@ static int dwc3_trb_ring_show(struct seq_file *s, void *unused) out: spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -839,6 +940,11 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) u32 lower_32_bits; u32 upper_32_bits; u32 reg; + int ret; + + ret = pm_runtime_resume_and_get(dwc->dev); + if (ret < 0) + return ret; spin_lock_irqsave(&dwc->lock, flags); reg = DWC3_GDBGLSPMUX_EPSELECT(dep->number); @@ -851,6 +957,8 @@ static int dwc3_ep_info_register_show(struct seq_file *s, void *unused) seq_printf(s, "0x%016llx\n", ep_info); spin_unlock_irqrestore(&dwc->lock, flags); + pm_runtime_put_sync(dwc->dev); + return 0; } @@ -910,6 +1018,7 @@ void dwc3_debugfs_init(struct dwc3 *dwc) dwc->regset->regs = dwc3_regs; dwc->regset->nregs = ARRAY_SIZE(dwc3_regs); dwc->regset->base = dwc->regs - DWC3_GLOBALS_REGS_START; + dwc->regset->dev = dwc->dev; root = debugfs_create_dir(dev_name(dwc->dev), usb_debug_root); dwc->debug_root = root; -- GitLab From 8432a15cd810c99db464b7e7858d559f3e1920e3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B3=20=C3=81gila=20Bitsch?= Date: Sat, 22 Apr 2023 18:05:32 +0200 Subject: [PATCH 4841/5631] usb: gadget: drop superfluous ':' in doc string MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There was one superfluous ':' that kernel-doc complained about. Reported-by: Randy Dunlap Closes: https://lore.kernel.org/all/c718a490-028d-2682-9ad7-8256d16504bf@infradead.org/ Fixes: fb6211f1584a ("usb: gadget: add doc to struct usb_composite_dev") Signed-off-by: Jó Ágila Bitsch Reviewed-by: Randy Dunlap Link: https://lore.kernel.org/r/ZEQFzMntIrwvZl4+@jo-einhundert Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/composite.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a2448e98854f..07531c4f4350 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -443,7 +443,7 @@ static inline struct usb_composite_driver *to_cdriver( * @bcd_webusb_version: 0x0100 by default, WebUSB specification version * @b_webusb_vendor_code: 0x0 by default, vendor code for WebUSB * @landing_page: empty by default, landing page to announce in WebUSB - * @use_webusb:: false by default, interested gadgets set it + * @use_webusb: false by default, interested gadgets set it * @os_desc_config: the configuration to be used with OS descriptors * @setup_pending: true when setup request is queued but not completed * @os_desc_pending: true when os_desc request is queued but not completed -- GitLab From 5e1617210aede9f1b91bb9819c93097b6da481f9 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Fri, 12 May 2023 15:14:34 +0200 Subject: [PATCH 4842/5631] Revert "usb: gadget: udc: core: Prevent redundant calls to pullup" This reverts commit a3afbf5cc887fc3401f012fe629810998ed61859. This depends on commit 0db213ea8eed ("usb: gadget: udc: core: Invoke usb_gadget_connect only when started") that introduces a regression, revert it till the issue is fixed. Cc: stable@vger.kernel.org Reported-by: Stephan Gerhold Reported-by: Francesco Dolcini Link: https://lore.kernel.org/all/ZF4BvgsOyoKxdPFF@francesco-nb.int.toradex.com/ Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230512131435.205464-2-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 4641153e9706..583c339876ab 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -703,9 +703,6 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->connected) - goto out; - if (gadget->deactivated || !gadget->udc->started) { /* * If gadget is deactivated we only save new state. -- GitLab From f22e9b67f19ccc73de1ae04375d4b30684e261f8 Mon Sep 17 00:00:00 2001 From: Francesco Dolcini Date: Fri, 12 May 2023 15:14:35 +0200 Subject: [PATCH 4843/5631] Revert "usb: gadget: udc: core: Invoke usb_gadget_connect only when started" This reverts commit 0db213ea8eed5534a5169e807f28103cbc9d23df. It introduces an issues with configuring the USB gadget hangs forever on multiple Qualcomm and NXP i.MX SoC at least. Cc: stable@vger.kernel.org Fixes: 0db213ea8eed ("usb: gadget: udc: core: Invoke usb_gadget_connect only when started") Reported-by: Stephan Gerhold Reported-by: Francesco Dolcini Link: https://lore.kernel.org/all/ZF4BvgsOyoKxdPFF@francesco-nb.int.toradex.com/ Signed-off-by: Francesco Dolcini Link: https://lore.kernel.org/r/20230512131435.205464-3-francesco@dolcini.it Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/udc/core.c | 148 ++++++++++------------------------ 1 file changed, 44 insertions(+), 104 deletions(-) diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 583c339876ab..52e6d2e84e35 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -37,10 +37,6 @@ static const struct bus_type gadget_bus_type; * @vbus: for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * @started: the UDC's started state. True if the UDC had started. - * @connect_lock: protects udc->vbus, udc->started, gadget->connect, gadget->deactivate related - * functions. usb_gadget_connect_locked, usb_gadget_disconnect_locked, - * usb_udc_connect_control_locked, usb_gadget_udc_start_locked, usb_gadget_udc_stop_locked are - * called with this lock held. * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. @@ -52,7 +48,6 @@ struct usb_udc { struct list_head list; bool vbus; bool started; - struct mutex connect_lock; }; static struct class *udc_class; @@ -692,9 +687,17 @@ int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); -/* Internal version of usb_gadget_connect needs to be called with connect_lock held. */ -static int usb_gadget_connect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +/** + * usb_gadget_connect - software-controlled connect to USB host + * @gadget:the peripheral being connected + * + * Enables the D+ (or potentially D-) pullup. The host will start + * enumerating this gadget when the pullup is active and a VBUS session + * is active (the link is powered). + * + * Returns zero on success, else negative errno. + */ +int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; @@ -703,12 +706,10 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) goto out; } - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. - * - * udc first needs to be started before gadget can be pulled up. */ gadget->connected = true; goto out; @@ -723,32 +724,22 @@ static int usb_gadget_connect_locked(struct usb_gadget *gadget) return ret; } +EXPORT_SYMBOL_GPL(usb_gadget_connect); /** - * usb_gadget_connect - software-controlled connect to USB host - * @gadget:the peripheral being connected + * usb_gadget_disconnect - software-controlled disconnect from USB host + * @gadget:the peripheral being disconnected * - * Enables the D+ (or potentially D-) pullup. The host will start - * enumerating this gadget when the pullup is active and a VBUS session - * is active (the link is powered). + * Disables the D+ (or potentially D-) pullup, which the host may see + * as a disconnect (when a VBUS session is active). Not all systems + * support software pullup controls. + * + * Following a successful disconnect, invoke the ->disconnect() callback + * for the current gadget driver so that UDC drivers don't need to. * * Returns zero on success, else negative errno. */ -int usb_gadget_connect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(usb_gadget_connect); - -/* Internal version of usb_gadget_disconnect needs to be called with connect_lock held. */ -static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) - __must_hold(&gadget->udc->connect_lock) +int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret = 0; @@ -760,12 +751,10 @@ static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) if (!gadget->connected) goto out; - if (gadget->deactivated || !gadget->udc->started) { + if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. - * - * udc should have been started before gadget being pulled down. */ gadget->connected = false; goto out; @@ -785,30 +774,6 @@ static int usb_gadget_disconnect_locked(struct usb_gadget *gadget) return ret; } - -/** - * usb_gadget_disconnect - software-controlled disconnect from USB host - * @gadget:the peripheral being disconnected - * - * Disables the D+ (or potentially D-) pullup, which the host may see - * as a disconnect (when a VBUS session is active). Not all systems - * support software pullup controls. - * - * Following a successful disconnect, invoke the ->disconnect() callback - * for the current gadget driver so that UDC drivers don't need to. - * - * Returns zero on success, else negative errno. - */ -int usb_gadget_disconnect(struct usb_gadget *gadget) -{ - int ret; - - mutex_lock(&gadget->udc->connect_lock); - ret = usb_gadget_disconnect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); - - return ret; -} EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** @@ -829,11 +794,10 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) if (gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); if (gadget->connected) { - ret = usb_gadget_disconnect_locked(gadget); + ret = usb_gadget_disconnect(gadget); if (ret) - goto unlock; + goto out; /* * If gadget was being connected before deactivation, we want @@ -843,8 +807,6 @@ int usb_gadget_deactivate(struct usb_gadget *gadget) } gadget->deactivated = true; -unlock: - mutex_unlock(&gadget->udc->connect_lock); out: trace_usb_gadget_deactivate(gadget, ret); @@ -868,7 +830,6 @@ int usb_gadget_activate(struct usb_gadget *gadget) if (!gadget->deactivated) goto out; - mutex_lock(&gadget->udc->connect_lock); gadget->deactivated = false; /* @@ -876,8 +837,7 @@ int usb_gadget_activate(struct usb_gadget *gadget) * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) - ret = usb_gadget_connect_locked(gadget); - mutex_unlock(&gadget->udc->connect_lock); + ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); @@ -1118,13 +1078,12 @@ EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ -/* Acquire connect_lock before calling this function. */ -static void usb_udc_connect_control_locked(struct usb_udc *udc) __must_hold(&udc->connect_lock) +static void usb_udc_connect_control(struct usb_udc *udc) { - if (udc->vbus && udc->started) - usb_gadget_connect_locked(udc->gadget); + if (udc->vbus) + usb_gadget_connect(udc->gadget); else - usb_gadget_disconnect_locked(udc->gadget); + usb_gadget_disconnect(udc->gadget); } /** @@ -1140,12 +1099,10 @@ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; - mutex_lock(&udc->connect_lock); if (udc) { udc->vbus = status; - usb_udc_connect_control_locked(udc); + usb_udc_connect_control(udc); } - mutex_unlock(&udc->connect_lock); } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); @@ -1167,7 +1124,7 @@ void usb_gadget_udc_reset(struct usb_gadget *gadget, EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** - * usb_gadget_udc_start_locked - tells usb device controller to start up + * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about @@ -1178,11 +1135,8 @@ EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); * necessary to have it powered on. * * Returns zero on success, else negative errno. - * - * Caller should acquire connect_lock before invoking this function. */ -static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline int usb_gadget_udc_start(struct usb_udc *udc) { int ret; @@ -1199,7 +1153,7 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) } /** - * usb_gadget_udc_stop_locked - tells usb device controller we don't need it anymore + * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @udc: The UDC to be stopped * * This call is issued by the UDC Class driver after calling @@ -1208,11 +1162,8 @@ static inline int usb_gadget_udc_start_locked(struct usb_udc *udc) * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. - * - * Caller should acquire connect lock before invoking this function. */ -static inline void usb_gadget_udc_stop_locked(struct usb_udc *udc) - __must_hold(&udc->connect_lock) +static inline void usb_gadget_udc_stop(struct usb_udc *udc) { if (!udc->started) { dev_err(&udc->dev, "UDC had already stopped\n"); @@ -1371,7 +1322,6 @@ int usb_add_gadget(struct usb_gadget *gadget) udc->gadget = gadget; gadget->udc = udc; - mutex_init(&udc->connect_lock); udc->started = false; @@ -1573,15 +1523,11 @@ static int gadget_bind_driver(struct device *dev) if (ret) goto err_bind; - mutex_lock(&udc->connect_lock); - ret = usb_gadget_udc_start_locked(udc); - if (ret) { - mutex_unlock(&udc->connect_lock); + ret = usb_gadget_udc_start(udc); + if (ret) goto err_start; - } usb_gadget_enable_async_callbacks(udc); - usb_udc_connect_control_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; @@ -1612,14 +1558,12 @@ static void gadget_unbind_driver(struct device *dev) kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(gadget); + usb_gadget_disconnect(gadget); usb_gadget_disable_async_callbacks(udc); if (gadget->irq) synchronize_irq(gadget->irq); udc->driver->unbind(gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_stop(udc); mutex_lock(&udc_lock); driver->is_bound = false; @@ -1705,15 +1649,11 @@ static ssize_t soft_connect_store(struct device *dev, } if (sysfs_streq(buf, "connect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_udc_start_locked(udc); - usb_gadget_connect_locked(udc->gadget); - mutex_unlock(&udc->connect_lock); + usb_gadget_udc_start(udc); + usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { - mutex_lock(&udc->connect_lock); - usb_gadget_disconnect_locked(udc->gadget); - usb_gadget_udc_stop_locked(udc); - mutex_unlock(&udc->connect_lock); + usb_gadget_disconnect(udc->gadget); + usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; -- GitLab From d8f28269dd4bf9b55c3fb376ae31512730a96fce Mon Sep 17 00:00:00 2001 From: Badhri Jagan Sridharan Date: Mon, 8 May 2023 21:44:43 +0000 Subject: [PATCH 4844/5631] usb: typec: altmodes/displayport: fix pin_assignment_show This patch fixes negative indexing of buf array in pin_assignment_show when get_current_pin_assignments returns 0 i.e. no compatible pin assignments are found. BUG: KASAN: use-after-free in pin_assignment_show+0x26c/0x33c ... Call trace: dump_backtrace+0x110/0x204 dump_stack_lvl+0x84/0xbc print_report+0x358/0x974 kasan_report+0x9c/0xfc __do_kernel_fault+0xd4/0x2d4 do_bad_area+0x48/0x168 do_tag_check_fault+0x24/0x38 do_mem_abort+0x6c/0x14c el1_abort+0x44/0x68 el1h_64_sync_handler+0x64/0xa4 el1h_64_sync+0x78/0x7c pin_assignment_show+0x26c/0x33c dev_attr_show+0x50/0xc0 Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode") Cc: stable@vger.kernel.org Signed-off-by: Badhri Jagan Sridharan Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230508214443.893436-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/altmodes/displayport.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 8f3e884222ad..66de880b28d0 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -516,6 +516,10 @@ static ssize_t pin_assignment_show(struct device *dev, mutex_unlock(&dp->lock); + /* get_current_pin_assignments can return 0 when no matching pin assignments are found */ + if (len == 0) + len++; + buf[len - 1] = '\n'; return len; } -- GitLab From 3c0f4f09c063e143822393d99cb2b19a85451c07 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Konrad=20Gr=C3=A4fe?= Date: Fri, 5 May 2023 16:36:40 +0200 Subject: [PATCH 4845/5631] usb: gadget: u_ether: Fix host MAC address case MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CDC-ECM specification [1] requires to send the host MAC address as an uppercase hexadecimal string in chapter "5.4 Ethernet Networking Functional Descriptor": The Unicode character is chosen from the set of values 30h through 39h and 41h through 46h (0-9 and A-F). However, snprintf(.., "%pm", ..) generates a lowercase MAC address string. While most host drivers are tolerant to this, UsbNcm.sys on Windows 10 is not. Instead it uses a different MAC address with all bytes set to zero including and after the first byte containing a lowercase letter. On Windows 11 Microsoft fixed it, but apparently they did not backport the fix. This change fixes the issue by upper-casing the MAC to comply with the specification. [1]: https://www.usb.org/document-library/class-definitions-communication-devices-12, file ECM120.pdf Fixes: bcd4a1c40bee ("usb: gadget: u_ether: construct with default values and add setters/getters") Cc: stable@vger.kernel.org Signed-off-by: Konrad Gräfe Link: https://lore.kernel.org/r/20230505143640.443014-1-k.graefe@gateware.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/u_ether.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 6956ad8ba8dd..a366abb45623 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "u_ether.h" @@ -965,6 +966,8 @@ int gether_get_host_addr_cdc(struct net_device *net, char *host_addr, int len) dev = netdev_priv(net); snprintf(host_addr, len, "%pm", dev->host_mac); + string_upper(host_addr, host_addr); + return strlen(host_addr); } EXPORT_SYMBOL_GPL(gether_get_host_addr_cdc); -- GitLab From 94ea04ec790887b5b0e43429a92c18a1e692ec08 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Fri, 21 Apr 2023 13:17:20 +0300 Subject: [PATCH 4846/5631] usb: typec: tps6598x: Fix fault at module removal We need to cancel the delayed workqueue if it is being used else it will cause paging request fault during module removal. Fixes: 0d6a119cecd7 ("usb: typec: tps6598x: Add support for polling interrupts status") Signed-off-by: Roger Quadros Reviewed-by: Heikki Krogerus Link: https://lore.kernel.org/r/20230421101720.34318-1-rogerq@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/tipd/core.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 8b075ca82ef6..438cc40660a1 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -886,6 +886,9 @@ static void tps6598x_remove(struct i2c_client *client) { struct tps6598x *tps = i2c_get_clientdata(client); + if (!client->irq) + cancel_delayed_work_sync(&tps->wq_poll); + tps6598x_disconnect(tps, 0); typec_unregister_port(tps->port); usb_role_switch_put(tps->role_sw); -- GitLab From 8018018d9c56473067e5358986ce0ee9ce56949f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 4 May 2023 17:59:24 +0300 Subject: [PATCH 4847/5631] usb: dwc3: fix a test for error in dwc3_core_init() This was refactored recently and the "ret = " was accidentally deleted so the errors aren't checked. Fixes: 1d72fab47656 ("USB: dwc3: refactor phy handling") Signed-off-by: Dan Carpenter Reviewed-by: Johan Hovold Acked-by: Thinh Nguyen Link: https://lore.kernel.org/r/d0c5a04f-deee-4ebe-9b0b-dc5492564519@kili.mountain Signed-off-by: Greg Kroah-Hartman --- drivers/usb/dwc3/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 0beaab932e7d..7b2ce013cc5b 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1137,7 +1137,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_set_incr_burst_type(dwc); - dwc3_phy_power_on(dwc); + ret = dwc3_phy_power_on(dwc); if (ret) goto err_exit_phy; -- GitLab From a398d5eac6984316e71474e25b975688f282379b Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Fri, 5 May 2023 13:47:59 +0200 Subject: [PATCH 4848/5631] usb-storage: fix deadlock when a scsi command timeouts more than once With faulty usb-storage devices, read/write can timeout, in that case the SCSI layer will abort and re-issue the command. USB storage has no internal timeout, it relies on SCSI layer aborting commands via .eh_abort_handler() for non those responsive devices. After two consecutive timeouts of the same command, SCSI layer calls .eh_device_reset_handler(), without calling .eh_abort_handler() first. With usb-storage, this causes a deadlock: -> .eh_device_reset_handler -> device_reset -> mutex_lock(&(us->dev_mutex)); mutex already by usb_stor_control_thread(), which is waiting for command completion: -> usb_stor_control_thread (mutex taken here) -> usb_stor_invoke_transport -> usb_stor_Bulk_transport -> usb_stor_bulk_srb -> usb_stor_bulk_transfer_sglist -> usb_sg_wait Make sure we cancel any pending command in .eh_device_reset_handler() to avoid this. Signed-off-by: Maxime Bizon Cc: linux-usb@vger.kernel.org Cc: stable Link: https://lore.kernel.org/all/ZEllnjMKT8ulZbJh@sakura/ Reviewed-by: Alan Stern Acked-by: Alan Stern Link: https://lore.kernel.org/r/20230505114759.1189741-1-mbizon@freebox.fr Signed-off-by: Greg Kroah-Hartman --- drivers/usb/storage/scsiglue.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 8931df5a85fd..c54e9805da53 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -406,22 +406,25 @@ static DEF_SCSI_QCMD(queuecommand) ***********************************************************************/ /* Command timeout and abort */ -static int command_abort(struct scsi_cmnd *srb) +static int command_abort_matching(struct us_data *us, struct scsi_cmnd *srb_match) { - struct us_data *us = host_to_us(srb->device->host); - - usb_stor_dbg(us, "%s called\n", __func__); - /* * us->srb together with the TIMED_OUT, RESETTING, and ABORTING * bits are protected by the host lock. */ scsi_lock(us_to_host(us)); - /* Is this command still active? */ - if (us->srb != srb) { + /* is there any active pending command to abort ? */ + if (!us->srb) { scsi_unlock(us_to_host(us)); usb_stor_dbg(us, "-- nothing to abort\n"); + return SUCCESS; + } + + /* Does the command match the passed srb if any ? */ + if (srb_match && us->srb != srb_match) { + scsi_unlock(us_to_host(us)); + usb_stor_dbg(us, "-- pending command mismatch\n"); return FAILED; } @@ -444,6 +447,14 @@ static int command_abort(struct scsi_cmnd *srb) return SUCCESS; } +static int command_abort(struct scsi_cmnd *srb) +{ + struct us_data *us = host_to_us(srb->device->host); + + usb_stor_dbg(us, "%s called\n", __func__); + return command_abort_matching(us, srb); +} + /* * This invokes the transport reset mechanism to reset the state of the * device @@ -455,6 +466,9 @@ static int device_reset(struct scsi_cmnd *srb) usb_stor_dbg(us, "%s called\n", __func__); + /* abort any pending command before reset */ + command_abort_matching(us, NULL); + /* lock the device pointers and do the reset */ mutex_lock(&(us->dev_mutex)); result = us->transport_reset(us); -- GitLab From 95d698869b404772cc8b72560df71548491c10bc Mon Sep 17 00:00:00 2001 From: Andrew Davis Date: Thu, 20 Apr 2023 11:02:09 -0500 Subject: [PATCH 4849/5631] serial: 8250_exar: Add support for USR298x PCI Modems Possibly the last PCI controller-based (i.e. not a soft/winmodem) dial-up modem one can still buy. Looks to have a stock XR17C154 PCI UART chip for communication, but for some reason when provisioning the PCI IDs they swapped the vendor and subvendor IDs. Otherwise this card would have worked out of the box. Searching online, some folks seem to not have this issue and others do, so it is possible only some batches of cards have this error. Create a new macro to handle the switched IDs and add support here. Signed-off-by: Andrew Davis Cc: stable Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20230420160209.28221-1-afd@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_exar.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 64770c62bbec..b406cba10b0e 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -40,9 +40,13 @@ #define PCI_DEVICE_ID_COMMTECH_4224PCIE 0x0020 #define PCI_DEVICE_ID_COMMTECH_4228PCIE 0x0021 #define PCI_DEVICE_ID_COMMTECH_4222PCIE 0x0022 + #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_SUBDEVICE_ID_USR_2980 0x0128 +#define PCI_SUBDEVICE_ID_USR_2981 0x0129 + #define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 #define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 #define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 @@ -829,6 +833,15 @@ static const struct exar8250_board pbn_exar_XR17V8358 = { (kernel_ulong_t)&bd \ } +#define USR_DEVICE(devid, sdevid, bd) { \ + PCI_DEVICE_SUB( \ + PCI_VENDOR_ID_USR, \ + PCI_DEVICE_ID_EXAR_##devid, \ + PCI_VENDOR_ID_EXAR, \ + PCI_SUBDEVICE_ID_USR_##sdevid), 0, 0, \ + (kernel_ulong_t)&bd \ + } + static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(ACCESSIO, COM_2S, pbn_exar_XR17C15x), EXAR_DEVICE(ACCESSIO, COM_4S, pbn_exar_XR17C15x), @@ -853,6 +866,10 @@ static const struct pci_device_id exar_pci_tbl[] = { IBM_DEVICE(XR17C152, SATURN_SERIAL_ONE_PORT, pbn_exar_ibm_saturn), + /* USRobotics USR298x-OEM PCI Modems */ + USR_DEVICE(XR17C152, 2980, pbn_exar_XR17C15x), + USR_DEVICE(XR17C152, 2981, pbn_exar_XR17C15x), + /* Exar Corp. XR17C15[248] Dual/Quad/Octal UART */ EXAR_DEVICE(EXAR, XR17C152, pbn_exar_XR17C15x), EXAR_DEVICE(EXAR, XR17C154, pbn_exar_XR17C15x), -- GitLab From d2b00516de0e1d696724247098f6733a6ea53908 Mon Sep 17 00:00:00 2001 From: Vitaliy Tomin Date: Sun, 23 Apr 2023 11:45:12 +0800 Subject: [PATCH 4850/5631] serial: Add support for Advantech PCI-1611U card Add support for Advantech PCI-1611U card Advantech provides opensource drivers for this and many others card based on legacy copy of 8250_pci driver called adv950 https://www.advantech.com/emt/support/details/driver?id=1-TDOIMJ It is hard to maintain to run as out of tree module on newer kernels. Just adding PCI ID to kernel 8250_pci works perfect. Signed-off-by: Vitaliy Tomin Cc: stable Link: https://lore.kernel.org/r/20230423034512.2671157-1-tomin@iszf.irk.ru Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index c55be6fda0ca..e80c4f6551a1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1920,6 +1920,8 @@ pci_moxa_setup(struct serial_private *priv, #define PCI_SUBDEVICE_ID_SIIG_DUAL_30 0x2530 #define PCI_VENDOR_ID_ADVANTECH 0x13fe #define PCI_DEVICE_ID_INTEL_CE4100_UART 0x2e66 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600 0x1600 +#define PCI_DEVICE_ID_ADVANTECH_PCI1600_1611 0x1611 #define PCI_DEVICE_ID_ADVANTECH_PCI3620 0x3620 #define PCI_DEVICE_ID_ADVANTECH_PCI3618 0x3618 #define PCI_DEVICE_ID_ADVANTECH_PCIf618 0xf618 @@ -4085,6 +4087,9 @@ static SIMPLE_DEV_PM_OPS(pciserial_pm_ops, pciserial_suspend_one, pciserial_resume_one); static const struct pci_device_id serial_pci_tbl[] = { + { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI1600, + PCI_DEVICE_ID_ADVANTECH_PCI1600_1611, PCI_ANY_ID, 0, 0, + pbn_b0_4_921600 }, /* Advantech use PCI_DEVICE_ID_ADVANTECH_PCI3620 (0x3620) as 'PCI_SUBVENDOR_ID' */ { PCI_VENDOR_ID_ADVANTECH, PCI_DEVICE_ID_ADVANTECH_PCI3620, PCI_DEVICE_ID_ADVANTECH_PCI3620, 0x0001, 0, 0, -- GitLab From f16182ed9d8430adfab77f5929c23756c94b0230 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Fri, 21 Apr 2023 11:58:06 +0200 Subject: [PATCH 4851/5631] serial: 8250: Document termios parameter of serial8250_em485_config() With W=1: drivers/tty/serial/8250/8250_port.c:679: warning: Function parameter or member 'termios' not described in 'serial8250_em485_config' Fix this by documenting the parameter. Fixes: ae50bb2752836277 ("serial: take termios_rwsem for ->rs485_config() & pass termios as param") Signed-off-by: Geert Uytterhoeven Reviewed-by: Jiri Slaby Link: https://lore.kernel.org/r/2bd1e62be1d5d33333002910372feecc6d52e78f.1682071013.git.geert+renesas@glider.be Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_port.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index fe8d79c4ae95..c153ba3a018a 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -669,6 +669,7 @@ EXPORT_SYMBOL_GPL(serial8250_em485_supported); /** * serial8250_em485_config() - generic ->rs485_config() callback * @port: uart port + * @termios: termios structure * @rs485: rs485 settings * * Generic callback usable by 8250 uart drivers to activate rs485 settings -- GitLab From 8ab5fc55d7f65d58a3c3aeadf11bdf60267cd2bd Mon Sep 17 00:00:00 2001 From: Ke Zhang Date: Fri, 28 Apr 2023 11:16:36 +0800 Subject: [PATCH 4852/5631] serial: arc_uart: fix of_iomap leak in `arc_serial_probe` Smatch reports: drivers/tty/serial/arc_uart.c:631 arc_serial_probe() warn: 'port->membase' from of_iomap() not released on lines: 631. In arc_serial_probe(), if uart_add_one_port() fails, port->membase is not released, which would cause a resource leak. To fix this, I replace of_iomap with devm_platform_ioremap_resource. Fixes: 8dbe1d5e09a7 ("serial/arc: inline the probe helper") Signed-off-by: Ke Zhang Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230428031636.44642-1-m202171830@hust.edu.cn Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/arc_uart.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c index 59e25f2b6632..4b2512eef577 100644 --- a/drivers/tty/serial/arc_uart.c +++ b/drivers/tty/serial/arc_uart.c @@ -606,10 +606,11 @@ static int arc_serial_probe(struct platform_device *pdev) } uart->baud = val; - port->membase = of_iomap(np, 0); - if (!port->membase) + port->membase = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(port->membase)) { /* No point of dev_err since UART itself is hosed here */ - return -ENXIO; + return PTR_ERR(port->membase); + } port->irq = irq_of_parse_and_map(np, 0); -- GitLab From 8a3b5477256a54ae4a470dcebbcf8cdc18e4696d Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 27 Apr 2023 11:19:15 -0700 Subject: [PATCH 4853/5631] serial: 8250_bcm7271: balance clk_enable calls The sw_baud clock must be disabled when the device driver is not connected to the device. This now occurs when probe fails and upon remove. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Reported-by: XuDong Liu Link: https://lore.kernel.org/lkml/20230424125100.4783-1-m202071377@hust.edu.cn/ Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20230427181916.2983697-2-opendmb@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_bcm7271.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index f801b1f5b46c..90ee7bc12f77 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1032,7 +1032,7 @@ static int brcmuart_probe(struct platform_device *pdev) if (clk_rate == 0) { dev_err(dev, "clock-frequency or clk not defined\n"); ret = -EINVAL; - goto release_dma; + goto err_clk_disable; } dev_dbg(dev, "DMA is %senabled\n", priv->dma_enabled ? "" : "not "); @@ -1119,6 +1119,8 @@ static int brcmuart_probe(struct platform_device *pdev) serial8250_unregister_port(priv->line); err: brcmuart_free_bufs(dev, priv); +err_clk_disable: + clk_disable_unprepare(baud_mux_clk); release_dma: if (priv->dma_enabled) brcmuart_arbitration(priv, 0); @@ -1133,6 +1135,7 @@ static int brcmuart_remove(struct platform_device *pdev) hrtimer_cancel(&priv->hrt); serial8250_unregister_port(priv->line); brcmuart_free_bufs(&pdev->dev, priv); + clk_disable_unprepare(priv->baud_mux_clk); if (priv->dma_enabled) brcmuart_arbitration(priv, 0); return 0; -- GitLab From f264f2f6f4788dc031cef60a0cf2881902736709 Mon Sep 17 00:00:00 2001 From: Doug Berger Date: Thu, 27 Apr 2023 11:19:16 -0700 Subject: [PATCH 4854/5631] serial: 8250_bcm7271: fix leak in `brcmuart_probe` Smatch reports: drivers/tty/serial/8250/8250_bcm7271.c:1120 brcmuart_probe() warn: 'baud_mux_clk' from clk_prepare_enable() not released on lines: 1032. The issue is fixed by using a managed clock. Fixes: 41a469482de2 ("serial: 8250: Add new 8250-core based Broadcom STB driver") Reported-by: XuDong Liu Link: https://lore.kernel.org/lkml/20230424125100.4783-1-m202071377@hust.edu.cn/ Signed-off-by: Doug Berger Acked-by: Florian Fainelli Link: https://lore.kernel.org/r/20230427181916.2983697-3-opendmb@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250_bcm7271.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index 90ee7bc12f77..af0e1c070187 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -1012,7 +1012,7 @@ static int brcmuart_probe(struct platform_device *pdev) of_property_read_u32(np, "clock-frequency", &clk_rate); /* See if a Baud clock has been specified */ - baud_mux_clk = of_clk_get_by_name(np, "sw_baud"); + baud_mux_clk = devm_clk_get(dev, "sw_baud"); if (IS_ERR(baud_mux_clk)) { if (PTR_ERR(baud_mux_clk) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; -- GitLab From 5f949f140f73696f64acb89a1f16ff9153d017e0 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 5 May 2023 17:23:01 +0200 Subject: [PATCH 4855/5631] serial: qcom-geni: fix enabling deactivated interrupt The driver have a race, experienced only with PREEMPT_RT patchset: CPU0 | CPU1 ================================================================== qcom_geni_serial_probe | uart_add_one_port | | serdev_drv_probe | qca_serdev_probe | serdev_device_open | uart_open | uart_startup | qcom_geni_serial_startup | enable_irq | __irq_startup | WARN_ON() | IRQ not activated request_threaded_irq | irq_domain_activate_irq | The warning: 894000.serial: ttyHS1 at MMIO 0x894000 (irq = 144, base_baud = 0) is a MSM serial serial0: tty port ttyHS1 registered WARNING: CPU: 7 PID: 107 at kernel/irq/chip.c:241 __irq_startup+0x78/0xd8 ... qcom_geni_serial 894000.serial: serial engine reports 0 RX bytes in! Adding UART port triggers probe of child serial devices - serdev and eventually Qualcomm Bluetooth hci_qca driver. This opens UART port which enables the interrupt before it got activated in request_threaded_irq(). The issue originates in commit f3974413cf02 ("tty: serial: qcom_geni_serial: Wakeup IRQ cleanup") and discussion on mailing list [1]. However the above commit does not explain why the uart_add_one_port() is moved above requesting interrupt. [1] https://lore.kernel.org/all/5d9f3dfa.1c69fb81.84c4b.30bf@mx.google.com/ Fixes: f3974413cf02 ("tty: serial: qcom_geni_serial: Wakeup IRQ cleanup") Cc: Cc: Stephen Boyd Signed-off-by: Krzysztof Kozlowski Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/20230505152301.2181270-1-krzysztof.kozlowski@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/qcom_geni_serial.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 08dc3e2a729c..8582479f0211 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1664,19 +1664,18 @@ static int qcom_geni_serial_probe(struct platform_device *pdev) uport->private_data = &port->private_data; platform_set_drvdata(pdev, port); - ret = uart_add_one_port(drv, uport); - if (ret) - return ret; - irq_set_status_flags(uport->irq, IRQ_NOAUTOEN); ret = devm_request_irq(uport->dev, uport->irq, qcom_geni_serial_isr, IRQF_TRIGGER_HIGH, port->name, uport); if (ret) { dev_err(uport->dev, "Failed to get IRQ ret %d\n", ret); - uart_remove_one_port(drv, uport); return ret; } + ret = uart_add_one_port(drv, uport); + if (ret) + return ret; + /* * Set pm_runtime status as ACTIVE so that wakeup_irq gets * enabled/disabled from dev_pm_arm_wake_irq during system -- GitLab From 8fb9ea65c9d1338b0d2bb0a9122dc942cdd32357 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Fri, 12 May 2023 06:08:48 -0500 Subject: [PATCH 4856/5631] vc_screen: reload load of struct vc_data pointer in vcs_write() to avoid UAF MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After a call to console_unlock() in vcs_write() the vc_data struct can be freed by vc_port_destruct(). Because of that, the struct vc_data pointer must be reloaded in the while loop in vcs_write() after console_lock() to avoid a UAF when vcs_size() is called. Syzkaller reported a UAF in vcs_size(). BUG: KASAN: slab-use-after-free in vcs_size (drivers/tty/vt/vc_screen.c:215) Read of size 4 at addr ffff8880beab89a8 by task repro_vcs_size/4119 Call Trace: __asan_report_load4_noabort (mm/kasan/report_generic.c:380) vcs_size (drivers/tty/vt/vc_screen.c:215) vcs_write (drivers/tty/vt/vc_screen.c:664) vfs_write (fs/read_write.c:582 fs/read_write.c:564) ... Allocated by task 1213: kmalloc_trace (mm/slab_common.c:1064) vc_allocate (./include/linux/slab.h:559 ./include/linux/slab.h:680 drivers/tty/vt/vt.c:1078 drivers/tty/vt/vt.c:1058) con_install (drivers/tty/vt/vt.c:3334) tty_init_dev (drivers/tty/tty_io.c:1303 drivers/tty/tty_io.c:1415 drivers/tty/tty_io.c:1392) tty_open (drivers/tty/tty_io.c:2082 drivers/tty/tty_io.c:2128) chrdev_open (fs/char_dev.c:415) do_dentry_open (fs/open.c:921) vfs_open (fs/open.c:1052) ... Freed by task 4116: kfree (mm/slab_common.c:1016) vc_port_destruct (drivers/tty/vt/vt.c:1044) tty_port_destructor (drivers/tty/tty_port.c:296) tty_port_put (drivers/tty/tty_port.c:312) vt_disallocate_all (drivers/tty/vt/vt_ioctl.c:662 (discriminator 2)) vt_ioctl (drivers/tty/vt/vt_ioctl.c:903) tty_ioctl (drivers/tty/tty_io.c:2778) ... The buggy address belongs to the object at ffff8880beab8800 which belongs to the cache kmalloc-1k of size 1024 The buggy address is located 424 bytes inside of freed 1024-byte region [ffff8880beab8800, ffff8880beab8c00) The buggy address belongs to the physical page: page:00000000afc77580 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0xbeab8 head:00000000afc77580 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 flags: 0xfffffc0010200(slab|head|node=0|zone=1|lastcpupid=0x1fffff) page_type: 0xffffffff() raw: 000fffffc0010200 ffff888100042dc0 ffffea000426de00 dead000000000002 raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880beab8880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880beab8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880beab8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880beab8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Disabling lock debugging due to kernel taint Fixes: ac751efa6a0d ("console: rename acquire/release_console_sem() to console_lock/unlock()") Cc: stable Reported-by: syzkaller Signed-off-by: George Kennedy Reviewed-by: Thomas Weißschuh Link: https://lore.kernel.org/r/1683889728-10411-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/vt/vc_screen.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 498ba9c0ee93..829c4be66f3b 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -656,10 +656,17 @@ vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) } } - /* The vcs_size might have changed while we slept to grab - * the user buffer, so recheck. + /* The vc might have been freed or vcs_size might have changed + * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ + vc = vcs_vc(inode, &viewed); + if (!vc) { + if (written) + break; + ret = -ENXIO; + goto unlock_out; + } size = vcs_size(vc, attr, false); if (size < 0) { if (written) -- GitLab From bdc1c5fac982845a58d28690cdb56db8c88a530d Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Fri, 5 May 2023 20:30:20 +0000 Subject: [PATCH 4857/5631] binder: fix UAF caused by faulty buffer cleanup In binder_transaction_buffer_release() the 'failed_at' offset indicates the number of objects to clean up. However, this function was changed by commit 44d8047f1d87 ("binder: use standard functions to allocate fds"), to release all the objects in the buffer when 'failed_at' is zero. This introduced an issue when a transaction buffer is released without any objects having been processed so far. In this case, 'failed_at' is indeed zero yet it is misinterpreted as releasing the entire buffer. This leads to use-after-free errors where nodes are incorrectly freed and subsequently accessed. Such is the case in the following KASAN report: ================================================================== BUG: KASAN: slab-use-after-free in binder_thread_read+0xc40/0x1f30 Read of size 8 at addr ffff4faf037cfc58 by task poc/474 CPU: 6 PID: 474 Comm: poc Not tainted 6.3.0-12570-g7df047b3f0aa #5 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x94/0xec show_stack+0x18/0x24 dump_stack_lvl+0x48/0x60 print_report+0xf8/0x5b8 kasan_report+0xb8/0xfc __asan_load8+0x9c/0xb8 binder_thread_read+0xc40/0x1f30 binder_ioctl+0xd9c/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Allocated by task 474: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_alloc_info+0x24/0x34 __kasan_kmalloc+0xb8/0xbc kmalloc_trace+0x48/0x5c binder_new_node+0x3c/0x3a4 binder_transaction+0x2b58/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] Freed by task 475: kasan_save_stack+0x3c/0x64 kasan_set_track+0x2c/0x40 kasan_save_free_info+0x38/0x5c __kasan_slab_free+0xe8/0x154 __kmem_cache_free+0x128/0x2bc kfree+0x58/0x70 binder_dec_node_tmpref+0x178/0x1fc binder_transaction_buffer_release+0x430/0x628 binder_transaction+0x1954/0x36f0 binder_thread_write+0x8e0/0x1b78 binder_ioctl+0x14a0/0x1768 __arm64_sys_ioctl+0xd4/0x118 invoke_syscall+0x60/0x188 [...] ================================================================== In order to avoid these issues, let's always calculate the intended 'failed_at' offset beforehand. This is renamed and wrapped in a helper function to make it clear and convenient. Fixes: 32e9f56a96d8 ("binder: don't detect sender/target during buffer cleanup") Reported-by: Zi Fan Tan Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Acked-by: Todd Kjos Link: https://lore.kernel.org/r/20230505203020.4101154-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index fb56bfc45096..8fb7672021ee 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1934,24 +1934,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset; binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2111,6 +2110,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } } +/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -2806,7 +2820,7 @@ static int binder_proc_transaction(struct binder_transaction *t, t_outdated->buffer = NULL; buffer->transaction = NULL; trace_binder_transaction_update_buffer_release(buffer); - binder_transaction_buffer_release(proc, NULL, buffer, 0, 0); + binder_release_entire_buffer(proc, NULL, buffer, false); binder_alloc_free_buf(&proc->alloc, buffer); kfree(t_outdated); binder_stats_deleted(BINDER_STAT_TRANSACTION); @@ -3775,7 +3789,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); } -- GitLab From b15655b12ddca7ade09807f790bafb6fab61b50a Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 2 May 2023 20:12:17 +0000 Subject: [PATCH 4858/5631] Revert "binder_alloc: add missing mmap_lock calls when using the VMA" This reverts commit 44e602b4e52f70f04620bbbf4fe46ecb40170bde. This caused a performance regression particularly when pages are getting reclaimed. We don't need to acquire the mmap_lock to determine when the binder buffer has been fully initialized. A subsequent patch will bring back the lockless approach for this. [cmllamas: resolved trivial conflicts with renaming of alloc->mm] Fixes: 44e602b4e52f ("binder_alloc: add missing mmap_lock calls when using the VMA") Cc: Liam Howlett Cc: Suren Baghdasaryan Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20230502201220.1756319-1-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder_alloc.c | 31 ++++++++++--------------------- 1 file changed, 10 insertions(+), 21 deletions(-) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 55a3c3c2409f..92c814ec44fe 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -380,15 +380,12 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - mmap_read_lock(alloc->mm); if (!binder_alloc_get_vma(alloc)) { - mmap_read_unlock(alloc->mm); binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); return ERR_PTR(-ESRCH); } - mmap_read_unlock(alloc->mm); data_offsets_size = ALIGN(data_size, sizeof(void *)) + ALIGN(offsets_size, sizeof(void *)); @@ -916,25 +913,17 @@ void binder_alloc_print_pages(struct seq_file *m, * Make sure the binder_alloc is fully initialized, otherwise we might * read inconsistent state. */ - - mmap_read_lock(alloc->mm); - if (binder_alloc_get_vma(alloc) == NULL) { - mmap_read_unlock(alloc->mm); - goto uninitialized; - } - - mmap_read_unlock(alloc->mm); - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) - free++; - else if (list_empty(&page->lru)) - active++; - else - lru++; + if (binder_alloc_get_vma(alloc) != NULL) { + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + page = &alloc->pages[i]; + if (!page->page_ptr) + free++; + else if (list_empty(&page->lru)) + active++; + else + lru++; + } } - -uninitialized: mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); -- GitLab From c0fd2101781ef761b636769b2f445351f71c3626 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 2 May 2023 20:12:18 +0000 Subject: [PATCH 4859/5631] Revert "android: binder: stop saving a pointer to the VMA" This reverts commit a43cfc87caaf46710c8027a8c23b8a55f1078f19. This patch fixed an issue reported by syzkaller in [1]. However, this turned out to be only a band-aid in binder. The root cause, as bisected by syzkaller, was fixed by commit 5789151e48ac ("mm/mmap: undo ->mmap() when mas_preallocate() fails"). We no longer need the patch for binder. Reverting such patch allows us to have a lockless access to alloc->vma in specific cases where the mmap_lock is not required. This approach avoids the contention that caused a performance regression. [1] https://lore.kernel.org/all/0000000000004a0dbe05e1d749e0@google.com [cmllamas: resolved conflicts with rework of alloc->mm and removal of binder_alloc_set_vma() also fixed comment section] Fixes: a43cfc87caaf ("android: binder: stop saving a pointer to the VMA") Cc: Liam Howlett Cc: Suren Baghdasaryan Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20230502201220.1756319-2-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder_alloc.c | 17 +++++++++-------- drivers/android/binder_alloc.h | 4 ++-- drivers/android/binder_alloc_selftest.c | 2 +- 3 files changed, 12 insertions(+), 11 deletions(-) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 92c814ec44fe..eb082b33115b 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -213,7 +213,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, if (mm) { mmap_read_lock(mm); - vma = vma_lookup(mm, alloc->vma_addr); + vma = alloc->vma; } if (!vma && need_mm) { @@ -314,9 +314,11 @@ static inline struct vm_area_struct *binder_alloc_get_vma( { struct vm_area_struct *vma = NULL; - if (alloc->vma_addr) - vma = vma_lookup(alloc->mm, alloc->vma_addr); - + if (alloc->vma) { + /* Look at description in binder_alloc_set_vma */ + smp_rmb(); + vma = alloc->vma; + } return vma; } @@ -775,7 +777,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - alloc->vma_addr = vma->vm_start; + alloc->vma = vma; return 0; @@ -805,8 +807,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) buffers = 0; mutex_lock(&alloc->mutex); - BUG_ON(alloc->vma_addr && - vma_lookup(alloc->mm, alloc->vma_addr)); + BUG_ON(alloc->vma); while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -958,7 +959,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - alloc->vma_addr = 0; + alloc->vma = 0; } /** diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 0f811ac4bcff..138d1d5af9ce 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -75,7 +75,7 @@ struct binder_lru_page { /** * struct binder_alloc - per-binder proc state for binder allocator * @mutex: protects binder_alloc fields - * @vma_addr: vm_area_struct->vm_start passed to mmap_handler + * @vma: vm_area_struct passed to mmap_handler * (invariant after mmap) * @mm: copy of task->mm (invariant after open) * @buffer: base of per-proc address space mapped via mmap @@ -99,7 +99,7 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - unsigned long vma_addr; + struct vm_area_struct *vma; struct mm_struct *mm; void __user *buffer; struct list_head buffers; diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 43a881073a42..c2b323bc3b3a 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma_addr) + if (!binder_selftest_run || !alloc->vma) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); -- GitLab From 0fa53349c3acba0239369ba4cd133740a408d246 Mon Sep 17 00:00:00 2001 From: Carlos Llamas Date: Tue, 2 May 2023 20:12:19 +0000 Subject: [PATCH 4860/5631] binder: add lockless binder_alloc_(set|get)_vma() Bring back the original lockless design in binder_alloc to determine whether the buffer setup has been completed by the ->mmap() handler. However, this time use smp_load_acquire() and smp_store_release() to wrap all the ordering in a single macro call. Also, add comments to make it evident that binder uses alloc->vma to determine when the binder_alloc has been fully initialized. In these scenarios acquiring the mmap_lock is not required. Fixes: a43cfc87caaf ("android: binder: stop saving a pointer to the VMA") Cc: Liam Howlett Cc: Suren Baghdasaryan Cc: stable@vger.kernel.org Signed-off-by: Carlos Llamas Link: https://lore.kernel.org/r/20230502201220.1756319-3-cmllamas@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder_alloc.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index eb082b33115b..e7c9d466f8e8 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -309,17 +309,18 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, return vma ? -ENOMEM : -ESRCH; } +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + /* pairs with smp_load_acquire in binder_alloc_get_vma() */ + smp_store_release(&alloc->vma, vma); +} + static inline struct vm_area_struct *binder_alloc_get_vma( struct binder_alloc *alloc) { - struct vm_area_struct *vma = NULL; - - if (alloc->vma) { - /* Look at description in binder_alloc_set_vma */ - smp_rmb(); - vma = alloc->vma; - } - return vma; + /* pairs with smp_store_release in binder_alloc_set_vma() */ + return smp_load_acquire(&alloc->vma); } static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) @@ -382,6 +383,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; + /* Check binder_alloc is fully initialized */ if (!binder_alloc_get_vma(alloc)) { binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", @@ -777,7 +779,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - alloc->vma = vma; + + /* Signal binder_alloc is fully initialized */ + binder_alloc_set_vma(alloc, vma); return 0; @@ -959,7 +963,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - alloc->vma = 0; + binder_alloc_set_vma(alloc, NULL); } /** -- GitLab From d80fc101d2eb9b3188c228d61223890aeea480a4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 11 May 2023 19:22:11 -0400 Subject: [PATCH 4861/5631] erspan: get the proto with the md version for collect_md In commit 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver"), it gets the proto with t->parms.erspan_ver, but t->parms.erspan_ver is not used by collect_md branch, and instead it should get the proto with md->version for collect_md. Thanks to Kevin for pointing this out. Fixes: 20704bd1633d ("erspan: build the header with the right proto according to erspan_ver") Fixes: 94d7d8f29287 ("ip6_gre: add erspan v2 support") Reported-by: Kevin Traynor Signed-off-by: Xin Long Reviewed-by: Simon Horman Reviewed-by: William Tu Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a4ecfc9d2593..da80974ad23a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1015,12 +1015,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1043,24 +1045,25 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ -- GitLab From 9e4b45f20c5aac786c728619e5ee746bffce1798 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Fri, 12 May 2023 09:27:10 +0200 Subject: [PATCH 4862/5631] net: dsa: rzn1-a5psw: enable management frames for CPU port MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, management frame were discarded before reaching the CPU port due to a misconfiguration of the MGMT_CONFIG register. Enable them by setting the correct value in this register in order to correctly receive management frame and handle STP. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Reviewed-by: Piotr Raczynski Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 2 +- drivers/net/dsa/rzn1_a5psw.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 919027cf2012..8a419e2ffe2a 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -673,7 +673,7 @@ static int a5psw_setup(struct dsa_switch *ds) } /* Configure management port */ - reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_DISCARD; + reg = A5PSW_CPU_PORT | A5PSW_MGMT_CFG_ENABLE; a5psw_reg_writel(a5psw, A5PSW_MGMT_CFG, reg); /* Set pattern 0 to forward all frame to mgmt port */ diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index c67abd49c013..b4fbf453ff74 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -36,7 +36,7 @@ #define A5PSW_INPUT_LEARN_BLOCK(p) BIT(p) #define A5PSW_MGMT_CFG 0x20 -#define A5PSW_MGMT_CFG_DISCARD BIT(7) +#define A5PSW_MGMT_CFG_ENABLE BIT(6) #define A5PSW_MODE_CFG 0x24 #define A5PSW_MODE_STATS_RESET BIT(31) -- GitLab From ebe9bc50952757b4b25eaf514da7c464196c9606 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alexis=20Lothor=C3=A9?= Date: Fri, 12 May 2023 09:27:11 +0200 Subject: [PATCH 4863/5631] net: dsa: rzn1-a5psw: fix STP states handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit stp_set_state() should actually allow receiving BPDU while in LEARNING mode which is not the case. Additionally, the BLOCKEN bit does not actually forbid sending forwarded frames from that port. To fix this, add a5psw_port_tx_enable() function which allows to disable TX. However, while its name suggest that TX is totally disabled, it is not and can still allow to send BPDUs even if disabled. This can be done by using forced forwarding with the switch tagging mechanism but keeping "filtering" disabled (which is already the case in the rzn1-a5sw tag driver). With these fixes, STP support is now functional. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 57 ++++++++++++++++++++++++++++++------ drivers/net/dsa/rzn1_a5psw.h | 1 + 2 files changed, 49 insertions(+), 9 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index 8a419e2ffe2a..e2549cb31d00 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -120,6 +120,22 @@ static void a5psw_port_mgmtfwd_set(struct a5psw *a5psw, int port, bool enable) a5psw_port_pattern_set(a5psw, port, A5PSW_PATTERN_MGMTFWD, enable); } +static void a5psw_port_tx_enable(struct a5psw *a5psw, int port, bool enable) +{ + u32 mask = A5PSW_PORT_ENA_TX(port); + u32 reg = enable ? mask : 0; + + /* Even though the port TX is disabled through TXENA bit in the + * PORT_ENA register, it can still send BPDUs. This depends on the tag + * configuration added when sending packets from the CPU port to the + * switch port. Indeed, when using forced forwarding without filtering, + * even disabled ports will be able to send packets that are tagged. + * This allows to implement STP support when ports are in a state where + * forwarding traffic should be stopped but BPDUs should still be sent. + */ + a5psw_reg_rmw(a5psw, A5PSW_PORT_ENA, mask, reg); +} + static void a5psw_port_enable_set(struct a5psw *a5psw, int port, bool enable) { u32 port_ena = 0; @@ -292,6 +308,22 @@ static int a5psw_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) return 0; } +static void a5psw_port_learning_set(struct a5psw *a5psw, int port, bool learn) +{ + u32 mask = A5PSW_INPUT_LEARN_DIS(port); + u32 reg = !learn ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + +static void a5psw_port_rx_block_set(struct a5psw *a5psw, int port, bool block) +{ + u32 mask = A5PSW_INPUT_LEARN_BLOCK(port); + u32 reg = block ? mask : 0; + + a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); +} + static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, bool set) { @@ -344,28 +376,35 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, static void a5psw_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - u32 mask = A5PSW_INPUT_LEARN_DIS(port) | A5PSW_INPUT_LEARN_BLOCK(port); + bool learning_enabled, rx_enabled, tx_enabled; struct a5psw *a5psw = ds->priv; - u32 reg = 0; switch (state) { case BR_STATE_DISABLED: case BR_STATE_BLOCKING: - reg |= A5PSW_INPUT_LEARN_DIS(port); - reg |= A5PSW_INPUT_LEARN_BLOCK(port); - break; case BR_STATE_LISTENING: - reg |= A5PSW_INPUT_LEARN_DIS(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = false; break; case BR_STATE_LEARNING: - reg |= A5PSW_INPUT_LEARN_BLOCK(port); + rx_enabled = false; + tx_enabled = false; + learning_enabled = true; break; case BR_STATE_FORWARDING: - default: + rx_enabled = true; + tx_enabled = true; + learning_enabled = true; break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; } - a5psw_reg_rmw(a5psw, A5PSW_INPUT_LEARN, mask, reg); + a5psw_port_learning_set(a5psw, port, learning_enabled); + a5psw_port_rx_block_set(a5psw, port, !rx_enabled); + a5psw_port_tx_enable(a5psw, port, tx_enabled); } static void a5psw_port_fast_age(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/rzn1_a5psw.h b/drivers/net/dsa/rzn1_a5psw.h index b4fbf453ff74..b869192eef3f 100644 --- a/drivers/net/dsa/rzn1_a5psw.h +++ b/drivers/net/dsa/rzn1_a5psw.h @@ -19,6 +19,7 @@ #define A5PSW_PORT_OFFSET(port) (0x400 * (port)) #define A5PSW_PORT_ENA 0x8 +#define A5PSW_PORT_ENA_TX(port) BIT(port) #define A5PSW_PORT_ENA_RX_SHIFT 16 #define A5PSW_PORT_ENA_TX_RX(port) (BIT((port) + A5PSW_PORT_ENA_RX_SHIFT) | \ BIT(port)) -- GitLab From ec52b69c046a6219011af780aca155a96719637b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= Date: Fri, 12 May 2023 09:27:12 +0200 Subject: [PATCH 4864/5631] net: dsa: rzn1-a5psw: disable learning for standalone ports MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When ports are in standalone mode, they should have learning disabled to avoid adding new entries in the MAC lookup table which might be used by other bridge ports to forward packets. While adding that, also make sure learning is enabled for CPU port. Fixes: 888cdb892b61 ("net: dsa: rzn1-a5psw: add Renesas RZ/N1 advanced 5 port switch driver") Signed-off-by: Clément Léger Signed-off-by: Alexis Lothoré Reviewed-by: Piotr Raczynski Signed-off-by: David S. Miller --- drivers/net/dsa/rzn1_a5psw.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c index e2549cb31d00..c37d2e537230 100644 --- a/drivers/net/dsa/rzn1_a5psw.c +++ b/drivers/net/dsa/rzn1_a5psw.c @@ -340,6 +340,14 @@ static void a5psw_flooding_set_resolution(struct a5psw *a5psw, int port, a5psw_reg_writel(a5psw, offsets[i], a5psw->bridged_ports); } +static void a5psw_port_set_standalone(struct a5psw *a5psw, int port, + bool standalone) +{ + a5psw_port_learning_set(a5psw, port, !standalone); + a5psw_flooding_set_resolution(a5psw, port, !standalone); + a5psw_port_mgmtfwd_set(a5psw, port, standalone); +} + static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, @@ -355,8 +363,7 @@ static int a5psw_port_bridge_join(struct dsa_switch *ds, int port, } a5psw->br_dev = bridge.dev; - a5psw_flooding_set_resolution(a5psw, port, true); - a5psw_port_mgmtfwd_set(a5psw, port, false); + a5psw_port_set_standalone(a5psw, port, false); return 0; } @@ -366,8 +373,7 @@ static void a5psw_port_bridge_leave(struct dsa_switch *ds, int port, { struct a5psw *a5psw = ds->priv; - a5psw_flooding_set_resolution(a5psw, port, false); - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); /* No more ports bridged */ if (a5psw->bridged_ports == BIT(A5PSW_CPU_PORT)) @@ -761,13 +767,15 @@ static int a5psw_setup(struct dsa_switch *ds) if (dsa_port_is_unused(dp)) continue; - /* Enable egress flooding for CPU port */ - if (dsa_port_is_cpu(dp)) + /* Enable egress flooding and learning for CPU port */ + if (dsa_port_is_cpu(dp)) { a5psw_flooding_set_resolution(a5psw, port, true); + a5psw_port_learning_set(a5psw, port, true); + } - /* Enable management forward only for user ports */ + /* Enable standalone mode for user ports */ if (dsa_port_is_user(dp)) - a5psw_port_mgmtfwd_set(a5psw, port, true); + a5psw_port_set_standalone(a5psw, port, true); } return 0; -- GitLab From 89f6bfb071182f05d7188c255b0e7251c3806f16 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 12 May 2023 18:00:11 +0800 Subject: [PATCH 4865/5631] net: hns3: fix output information incomplete for dumping tx queue info with debugfs In function hns3_dump_tx_queue_info, The print buffer is not enough when the tx BD number is configured to 32760. As a result several BD information wouldn't be displayed. So fix it by increasing the tx queue print buffer length. Fixes: 630a6738da82 ("net: hns3: adjust string spaces of some parameters of tx bd info in debugfs") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 4c3e90a1c4d0..d385ffc21876 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -130,7 +130,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .name = "tx_bd_queue", .cmd = HNAE3_DBG_CMD_TX_BD, .dentry = HNS3_DBG_DENTRY_TX_BD, - .buf_len = HNS3_DBG_READ_LEN_4MB, + .buf_len = HNS3_DBG_READ_LEN_5MB, .init = hns3_dbg_bd_file_init, }, { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h index 97578eabb7d8..4a5ef8a90a10 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -10,6 +10,7 @@ #define HNS3_DBG_READ_LEN_128KB 0x20000 #define HNS3_DBG_READ_LEN_1MB 0x100000 #define HNS3_DBG_READ_LEN_4MB 0x400000 +#define HNS3_DBG_READ_LEN_5MB 0x500000 #define HNS3_DBG_WRITE_LEN 1024 #define HNS3_DBG_DATA_STR_LEN 32 -- GitLab From f14db07064727dd3bc0906c77a6d2759c1bbb395 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 12 May 2023 18:00:12 +0800 Subject: [PATCH 4866/5631] net: hns3: fix sending pfc frames after reset issue To prevent the system from abnormally sending PFC frames after an abnormal reset. The hns3 driver notifies the firmware to disable pfc before reset. Fixes: 35d93a30040c ("net: hns3: adjust the process of PF reset") Signed-off-by: Jijie Shao Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 15 +++++++++------ .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 4 ++-- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h | 5 +++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 4fb5406c1951..2689b108f7df 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -8053,12 +8053,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET && - hdev->reset_type != HNAE3_FLR_RESET) { - hclge_mac_stop_phy(hdev); - hclge_update_link_status(hdev); - return; + if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) { + hclge_pfc_pause_en_cfg(hdev, HCLGE_PFC_TX_RX_DISABLE, + HCLGE_PFC_DISABLE); + if (hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { + hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); + return; + } } hclge_reset_tqp(handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 4a33f65190e2..922c0da3660c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -171,8 +171,8 @@ int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) return hclge_cmd_send(&hdev->hw, &desc, 1); } -static int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, - u8 pfc_bitmap) +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap) { struct hclge_desc desc; struct hclge_pfc_en_cmd *pfc = (struct hclge_pfc_en_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 68f28a98e380..dd6f1fd486cf 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -164,6 +164,9 @@ struct hclge_bp_to_qs_map_cmd { u32 rsvd1; }; +#define HCLGE_PFC_DISABLE 0 +#define HCLGE_PFC_TX_RX_DISABLE 0 + struct hclge_pfc_en_cmd { u8 tx_rx_en_bitmap; u8 pri_en_bitmap; @@ -235,6 +238,8 @@ void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc); void hclge_tm_pfc_info_update(struct hclge_dev *hdev); int hclge_tm_dwrr_cfg(struct hclge_dev *hdev); int hclge_tm_init_hw(struct hclge_dev *hdev, bool init); +int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, + u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); -- GitLab From 814d0c786068e858d889ada3153bff82f64223ad Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 12 May 2023 18:00:13 +0800 Subject: [PATCH 4867/5631] net: hns3: fix reset delay time to avoid configuration timeout Currently the hns3 vf function reset delays 5000ms before vf rebuild process. In product applications, this delay is too long for application configurations and causes configuration timeout. According to the tests, 500ms delay is enough for reset process except PF FLR. So this patch modifies delay to 500ms in these scenarios. Fixes: 6988eb2a9b77 ("net: hns3: Add support to reset the enet/ring mgmt layer") Signed-off-by: Jie Wang Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index f24046250341..dd08989a4c7c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1436,7 +1436,10 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) * might happen in case reset assertion was made by PF. Yes, this also * means we might end up waiting bit more even for VF reset. */ - msleep(5000); + if (hdev->reset_type == HNAE3_VF_FULL_RESET) + msleep(5000); + else + msleep(500); return 0; } -- GitLab From 6b45d5ff8c2c61baddd67d7510075ae121c5e704 Mon Sep 17 00:00:00 2001 From: Jijie Shao Date: Fri, 12 May 2023 18:00:14 +0800 Subject: [PATCH 4868/5631] net: hns3: fix reset timeout when enable full VF The timeout of the cmdq reset command has been increased to resolve the reset timeout issue in the full VF scenario. The timeout of other cmdq commands remains unchanged. Fixes: 8d307f8e8cf1 ("net: hns3: create new set of unified hclge_comm_cmd_send APIs") Signed-off-by: Jijie Shao Signed-off-by: Hao Lan Signed-off-by: David S. Miller --- .../hns3/hns3_common/hclge_comm_cmd.c | 25 ++++++++++++++++--- .../hns3/hns3_common/hclge_comm_cmd.h | 8 +++++- 2 files changed, 28 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index cbbab5b2b402..b85c412683dd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -331,9 +331,25 @@ static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw) return head == hw->cmq.csq.next_to_use; } -static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, +static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout) +{ + static const struct hclge_cmdq_tx_timeout_map cmdq_tx_timeout_map[] = { + {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS}, + }; + u32 i; + + for (i = 0; i < ARRAY_SIZE(cmdq_tx_timeout_map); i++) + if (cmdq_tx_timeout_map[i].opcode == opcode) + return cmdq_tx_timeout_map[i].tx_timeout; + + return tx_timeout; +} + +static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, u16 opcode, bool *is_completed) { + u32 cmdq_tx_timeout = hclge_get_cmdq_tx_timeout(opcode, + hw->cmq.tx_timeout); u32 timeout = 0; do { @@ -343,7 +359,7 @@ static void hclge_comm_wait_for_resp(struct hclge_comm_hw *hw, } udelay(1); timeout++; - } while (timeout < hw->cmq.tx_timeout); + } while (timeout < cmdq_tx_timeout); } static int hclge_comm_cmd_convert_err_code(u16 desc_ret) @@ -407,7 +423,8 @@ static int hclge_comm_cmd_check_result(struct hclge_comm_hw *hw, * if multi descriptors to be sent, use the first one to check */ if (HCLGE_COMM_SEND_SYNC(le16_to_cpu(desc->flag))) - hclge_comm_wait_for_resp(hw, &is_completed); + hclge_comm_wait_for_resp(hw, le16_to_cpu(desc->opcode), + &is_completed); if (!is_completed) ret = -EBADE; @@ -529,7 +546,7 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw) cmdq->crq.desc_num = HCLGE_COMM_NIC_CMQ_DESC_NUM; /* Setup Tx write back timeout */ - cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT; + cmdq->tx_timeout = HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT; /* Setup queue rings */ ret = hclge_comm_alloc_cmd_queue(hw, HCLGE_COMM_TYPE_CSQ); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index de72ecbfd5ad..18f1b4bf362d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -54,7 +54,8 @@ #define HCLGE_COMM_NIC_SW_RST_RDY BIT(HCLGE_COMM_NIC_SW_RST_RDY_B) #define HCLGE_COMM_NIC_CMQ_DESC_NUM_S 3 #define HCLGE_COMM_NIC_CMQ_DESC_NUM 1024 -#define HCLGE_COMM_CMDQ_TX_TIMEOUT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT 30000 +#define HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS 500000 enum hclge_opcode_type { /* Generic commands */ @@ -360,6 +361,11 @@ struct hclge_comm_caps_bit_map { u16 local_bit; }; +struct hclge_cmdq_tx_timeout_map { + u32 opcode; + u32 tx_timeout; +}; + struct hclge_comm_firmware_compat_cmd { __le32 compat; u8 rsv[20]; -- GitLab From 20f291b88ecf23f674ee2ed980a4d93b7f16a06f Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 14 Feb 2023 18:47:30 +0300 Subject: [PATCH 4869/5631] iio: adc: imx93: fix a signedness bug in imx93_adc_read_raw() The problem is these lines: ret = vref_uv = regulator_get_voltage(adc->vref); if (ret < 0) The "ret" variable is type long and "vref_uv" is u32 so that means the condition can never be true on a 64bit system. A negative error code from regulator_get_voltage() would be cast to a high positive u32 value and then remain a high positive value when cast to a long. The "ret" variable only ever stores ints so it should be declared as an int. We can delete the "vref_uv" variable and use "ret" directly. Fixes: 7d02296ac8b8 ("iio: adc: add imx93 adc support") Signed-off-by: Dan Carpenter Reviewed-by: Haibo Chen Link: https://lore.kernel.org/r/Y+utEvjfjQRQo2QB@kili Signed-off-by: Jonathan Cameron --- drivers/iio/adc/imx93_adc.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c index a775d2e40567..dce9ec91e4a7 100644 --- a/drivers/iio/adc/imx93_adc.c +++ b/drivers/iio/adc/imx93_adc.c @@ -236,8 +236,7 @@ static int imx93_adc_read_raw(struct iio_dev *indio_dev, { struct imx93_adc *adc = iio_priv(indio_dev); struct device *dev = adc->dev; - long ret; - u32 vref_uv; + int ret; switch (mask) { case IIO_CHAN_INFO_RAW: @@ -253,10 +252,10 @@ static int imx93_adc_read_raw(struct iio_dev *indio_dev, return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: - ret = vref_uv = regulator_get_voltage(adc->vref); + ret = regulator_get_voltage(adc->vref); if (ret < 0) return ret; - *val = vref_uv / 1000; + *val = ret / 1000; *val2 = 12; return IIO_VAL_FRACTIONAL_LOG2; -- GitLab From 00ffdd6fa90298522d45ca0c348b23485584dcdc Mon Sep 17 00:00:00 2001 From: ChiaEn Wu Date: Mon, 10 Apr 2023 18:34:22 +0800 Subject: [PATCH 4870/5631] iio: adc: mt6370: Fix ibus and ibat scaling value of some specific vendor ID chips The scale value of ibus and ibat on the datasheet is incorrect due to the customer report after the experimentation with some specific vendor ID chips. Fixes: c1404d1b659f ("iio: adc: mt6370: Add MediaTek MT6370 support") Signed-off-by: ChiaEn Wu Reviewed-by: Alexandre Mergnat Link: https://lore.kernel.org/r/1681122862-1994-1-git-send-email-chiaen_wu@richtek.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/mt6370-adc.c | 53 ++++++++++++++++++++++++++++++++++-- 1 file changed, 51 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/mt6370-adc.c b/drivers/iio/adc/mt6370-adc.c index bc62e5a9d50d..0bc112135bca 100644 --- a/drivers/iio/adc/mt6370-adc.c +++ b/drivers/iio/adc/mt6370-adc.c @@ -19,6 +19,7 @@ #include +#define MT6370_REG_DEV_INFO 0x100 #define MT6370_REG_CHG_CTRL3 0x113 #define MT6370_REG_CHG_CTRL7 0x117 #define MT6370_REG_CHG_ADC 0x121 @@ -27,6 +28,7 @@ #define MT6370_ADC_START_MASK BIT(0) #define MT6370_ADC_IN_SEL_MASK GENMASK(7, 4) #define MT6370_AICR_ICHG_MASK GENMASK(7, 2) +#define MT6370_VENID_MASK GENMASK(7, 4) #define MT6370_AICR_100_mA 0x0 #define MT6370_AICR_150_mA 0x1 @@ -47,6 +49,10 @@ #define ADC_CONV_TIME_MS 35 #define ADC_CONV_POLLING_TIME_US 1000 +#define MT6370_VID_RT5081 0x8 +#define MT6370_VID_RT5081A 0xA +#define MT6370_VID_MT6370 0xE + struct mt6370_adc_data { struct device *dev; struct regmap *regmap; @@ -55,6 +61,7 @@ struct mt6370_adc_data { * from being read at the same time. */ struct mutex adc_lock; + unsigned int vid; }; static int mt6370_adc_read_channel(struct mt6370_adc_data *priv, int chan, @@ -98,6 +105,30 @@ static int mt6370_adc_read_channel(struct mt6370_adc_data *priv, int chan, return ret; } +static int mt6370_adc_get_ibus_scale(struct mt6370_adc_data *priv) +{ + switch (priv->vid) { + case MT6370_VID_RT5081: + case MT6370_VID_RT5081A: + case MT6370_VID_MT6370: + return 3350; + default: + return 3875; + } +} + +static int mt6370_adc_get_ibat_scale(struct mt6370_adc_data *priv) +{ + switch (priv->vid) { + case MT6370_VID_RT5081: + case MT6370_VID_RT5081A: + case MT6370_VID_MT6370: + return 2680; + default: + return 3870; + } +} + static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, int chan, int *val1, int *val2) { @@ -123,7 +154,7 @@ static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, case MT6370_AICR_250_mA: case MT6370_AICR_300_mA: case MT6370_AICR_350_mA: - *val1 = 3350; + *val1 = mt6370_adc_get_ibus_scale(priv); break; default: *val1 = 5000; @@ -150,7 +181,7 @@ static int mt6370_adc_read_scale(struct mt6370_adc_data *priv, case MT6370_ICHG_600_mA: case MT6370_ICHG_700_mA: case MT6370_ICHG_800_mA: - *val1 = 2680; + *val1 = mt6370_adc_get_ibat_scale(priv); break; default: *val1 = 5000; @@ -251,6 +282,20 @@ static const struct iio_chan_spec mt6370_adc_channels[] = { MT6370_ADC_CHAN(TEMP_JC, IIO_TEMP, 12, BIT(IIO_CHAN_INFO_OFFSET)), }; +static int mt6370_get_vendor_info(struct mt6370_adc_data *priv) +{ + unsigned int dev_info; + int ret; + + ret = regmap_read(priv->regmap, MT6370_REG_DEV_INFO, &dev_info); + if (ret) + return ret; + + priv->vid = FIELD_GET(MT6370_VENID_MASK, dev_info); + + return 0; +} + static int mt6370_adc_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -272,6 +317,10 @@ static int mt6370_adc_probe(struct platform_device *pdev) priv->regmap = regmap; mutex_init(&priv->adc_lock); + ret = mt6370_get_vendor_info(priv); + if (ret) + return dev_err_probe(dev, ret, "Failed to get vid\n"); + ret = regmap_write(priv->regmap, MT6370_REG_CHG_ADC, 0); if (ret) return dev_err_probe(dev, ret, "Failed to reset ADC\n"); -- GitLab From 265c82ea8b172129cb6d4eff41af856c3aff6168 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Thu, 13 Apr 2023 18:37:52 -0700 Subject: [PATCH 4871/5631] iio: tmag5273: Fix runtime PM leak on measurement error The tmag5273 gets a runtime PM reference before reading a measurement and releases it when done. But if the measurement fails the tmag5273_read_raw() function exits before releasing the reference. Make sure that this error path also releases the runtime PM reference. Fixes: 866a1389174b ("iio: magnetometer: add ti tmag5273 driver") Signed-off-by: Lars-Peter Clausen Acked-by: Gerald Loacker Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230414013752.498767-1-lars@metafoo.de Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/magnetometer/tmag5273.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c index 28bb7efe8df8..e155a75b3cd2 100644 --- a/drivers/iio/magnetometer/tmag5273.c +++ b/drivers/iio/magnetometer/tmag5273.c @@ -296,12 +296,13 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev, return ret; ret = tmag5273_get_measure(data, &t, &x, &y, &z, &angle, &magnitude); - if (ret) - return ret; pm_runtime_mark_last_busy(data->dev); pm_runtime_put_autosuspend(data->dev); + if (ret) + return ret; + switch (chan->address) { case TEMPERATURE: *val = t; -- GitLab From 28f73ded19d403697f87473c9b85a27eb8ed9cf2 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Fri, 14 Apr 2023 08:07:02 -0700 Subject: [PATCH 4872/5631] iio: ad4130: Make sure clock provider gets removed The ad4130 driver registers a clock provider, but never removes it. This leaves a stale clock provider behind that references freed clocks when the device is unbound. Register a managed action to remove the clock provider when the device is removed. Fixes: 62094060cf3a ("iio: adc: ad4130: add AD4130 driver") Signed-off-by: Lars-Peter Clausen Link: https://lore.kernel.org/r/20230414150702.518441-1-lars@metafoo.de Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad4130.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c index 38394341fd6e..5a5dd5e87ffc 100644 --- a/drivers/iio/adc/ad4130.c +++ b/drivers/iio/adc/ad4130.c @@ -1817,6 +1817,11 @@ static const struct clk_ops ad4130_int_clk_ops = { .unprepare = ad4130_int_clk_unprepare, }; +static void ad4130_clk_del_provider(void *of_node) +{ + of_clk_del_provider(of_node); +} + static int ad4130_setup_int_clk(struct ad4130_state *st) { struct device *dev = &st->spi->dev; @@ -1824,6 +1829,7 @@ static int ad4130_setup_int_clk(struct ad4130_state *st) struct clk_init_data init; const char *clk_name; struct clk *clk; + int ret; if (st->int_pin_sel == AD4130_INT_PIN_CLK || st->mclk_sel != AD4130_MCLK_76_8KHZ) @@ -1843,7 +1849,11 @@ static int ad4130_setup_int_clk(struct ad4130_state *st) if (IS_ERR(clk)) return PTR_ERR(clk); - return of_clk_add_provider(of_node, of_clk_src_simple_get, clk); + ret = of_clk_add_provider(of_node, of_clk_src_simple_get, clk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, ad4130_clk_del_provider, of_node); } static int ad4130_setup(struct iio_dev *indio_dev) -- GitLab From 27b2ed5b6d53cd62fc61c3f259ae52f5cac23b66 Mon Sep 17 00:00:00 2001 From: Jiakai Luo Date: Sat, 22 Apr 2023 06:34:06 -0700 Subject: [PATCH 4873/5631] iio: adc: mxs-lradc: fix the order of two cleanup operations Smatch reports: drivers/iio/adc/mxs-lradc-adc.c:766 mxs_lradc_adc_probe() warn: missing unwind goto? the order of three init operation: 1.mxs_lradc_adc_trigger_init 2.iio_triggered_buffer_setup 3.mxs_lradc_adc_hw_init thus, the order of three cleanup operation should be: 1.mxs_lradc_adc_hw_stop 2.iio_triggered_buffer_cleanup 3.mxs_lradc_adc_trigger_remove we exchange the order of two cleanup operations, introducing the following differences: 1.if mxs_lradc_adc_trigger_init fails, returns directly; 2.if trigger_init succeeds but iio_triggered_buffer_setup fails, goto err_trig and remove the trigger. In addition, we also reorder the unwind that goes on in the remove() callback to match the new ordering. Fixes: 6dd112b9f85e ("iio: adc: mxs-lradc: Add support for ADC driver") Signed-off-by: Jiakai Luo Reviewed-by: Dongliang Mu Link: https://lore.kernel.org/r/20230422133407.72908-1-jkluo@hust.edu.cn Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/mxs-lradc-adc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/adc/mxs-lradc-adc.c b/drivers/iio/adc/mxs-lradc-adc.c index bca79a93cbe4..a50f39143d3e 100644 --- a/drivers/iio/adc/mxs-lradc-adc.c +++ b/drivers/iio/adc/mxs-lradc-adc.c @@ -757,13 +757,13 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) ret = mxs_lradc_adc_trigger_init(iio); if (ret) - goto err_trig; + return ret; ret = iio_triggered_buffer_setup(iio, &iio_pollfunc_store_time, &mxs_lradc_adc_trigger_handler, &mxs_lradc_adc_buffer_ops); if (ret) - return ret; + goto err_trig; adc->vref_mv = mxs_lradc_adc_vref_mv[lradc->soc]; @@ -801,9 +801,9 @@ static int mxs_lradc_adc_probe(struct platform_device *pdev) err_dev: mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); -err_trig: iio_triggered_buffer_cleanup(iio); +err_trig: + mxs_lradc_adc_trigger_remove(iio); return ret; } @@ -814,8 +814,8 @@ static int mxs_lradc_adc_remove(struct platform_device *pdev) iio_device_unregister(iio); mxs_lradc_adc_hw_stop(adc); - mxs_lradc_adc_trigger_remove(iio); iio_triggered_buffer_cleanup(iio); + mxs_lradc_adc_trigger_remove(iio); return 0; } -- GitLab From 279c3a2a5eb2c1054fbe38e5c33be08584229047 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 21 Apr 2023 13:41:56 +0300 Subject: [PATCH 4874/5631] iio: adc: palmas: fix off by one bugs Valid values for "adc_chan" are zero to (PALMAS_ADC_CH_MAX - 1). Smatch detects some buffer overflows caused by this: drivers/iio/adc/palmas_gpadc.c:721 palmas_gpadc_read_event_value() error: buffer overflow 'adc->thresholds' 16 <= 16 drivers/iio/adc/palmas_gpadc.c:758 palmas_gpadc_write_event_value() error: buffer overflow 'adc->thresholds' 16 <= 16 The effect of this bug in other functions is more complicated but obviously we should fix all of them. Fixes: a99544c6c883 ("iio: adc: palmas: add support for iio threshold events") Signed-off-by: Dan Carpenter Link: https://lore.kernel.org/r/14fee94a-7db7-4371-b7d6-e94d86b9561e@kili.mountain Signed-off-by: Jonathan Cameron --- drivers/iio/adc/palmas_gpadc.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index c1c439215aeb..7dfc9c927a23 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -547,7 +547,7 @@ static int palmas_gpadc_read_raw(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret = 0; - if (adc_chan > PALMAS_ADC_CH_MAX) + if (adc_chan >= PALMAS_ADC_CH_MAX) return -EINVAL; mutex_lock(&adc->lock); @@ -595,7 +595,7 @@ static int palmas_gpadc_read_event_config(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret = 0; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -684,7 +684,7 @@ static int palmas_gpadc_write_event_config(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -710,7 +710,7 @@ static int palmas_gpadc_read_event_value(struct iio_dev *indio_dev, int adc_chan = chan->channel; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); @@ -744,7 +744,7 @@ static int palmas_gpadc_write_event_value(struct iio_dev *indio_dev, int old; int ret; - if (adc_chan > PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) + if (adc_chan >= PALMAS_ADC_CH_MAX || type != IIO_EV_TYPE_THRESH) return -EINVAL; mutex_lock(&adc->lock); -- GitLab From 672cde9ef80ffde9e76d38f7aa2b287c4a18de9a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 21 Apr 2023 08:46:11 +0300 Subject: [PATCH 4875/5631] iio: fix doc for iio_gts_find_sel_by_int_time The kerneldoc for iio_gts_find_sel_by_int_time() has an error. Documentation states that function is searching a selector for a HW-gain while it is searching a selector for an integration time. Fix the documentation by saying the function is looking for a selector for an integration time. Fixes: 38416c28e168 ("iio: light: Add gain-time-scale helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/ZEIjI4YUzqPZk/9X@fedora Signed-off-by: Jonathan Cameron --- include/linux/iio/iio-gts-helper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h index dd64e544a3da..9cb6c80dea71 100644 --- a/include/linux/iio/iio-gts-helper.h +++ b/include/linux/iio/iio-gts-helper.h @@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) /** * iio_gts_find_sel_by_int_time - find selector matching integration time * @gts: Gain time scale descriptor - * @gain: HW-gain for which matching selector is searched for + * @time: Integration time for which matching selector is searched for * * Return: a selector matching given integration time or -EINVAL if * selector was not found. -- GitLab From b7b04f393ffa1530213f522115e7d77761eb5c4f Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 17 Apr 2023 12:19:57 +0300 Subject: [PATCH 4876/5631] iio: bu27034: Fix integration time The bu27034 uses micro seconds for integration time configuration. This is incorrect as the ABI mandates use of seconds. Change BU27034 driver to use seconds for integration time. Fixes: e52afbd61039 ("iio: light: ROHM BU27034 Ambient Light Sensor") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/a05647669af22ba919c7c87dccb43975e3235a87.1681722914.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/light/rohm-bu27034.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c index e486dcf35eba..25c9b79574a5 100644 --- a/drivers/iio/light/rohm-bu27034.c +++ b/drivers/iio/light/rohm-bu27034.c @@ -1167,11 +1167,12 @@ static int bu27034_read_raw(struct iio_dev *idev, switch (mask) { case IIO_CHAN_INFO_INT_TIME: - *val = bu27034_get_int_time(data); - if (*val < 0) - return *val; + *val = 0; + *val2 = bu27034_get_int_time(data); + if (*val2 < 0) + return *val2; - return IIO_VAL_INT; + return IIO_VAL_INT_PLUS_MICRO; case IIO_CHAN_INFO_SCALE: return bu27034_get_scale(data, chan->channel, val, val2); @@ -1229,7 +1230,10 @@ static int bu27034_write_raw(struct iio_dev *idev, ret = bu27034_set_scale(data, chan->channel, val, val2); break; case IIO_CHAN_INFO_INT_TIME: - ret = bu27034_try_set_int_time(data, val); + if (!val) + ret = bu27034_try_set_int_time(data, val2); + else + ret = -EINVAL; break; default: ret = -EINVAL; -- GitLab From e65065132fa6d9e1fd3b7418eae5215e3b7bf6c7 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 17 Apr 2023 12:20:18 +0300 Subject: [PATCH 4877/5631] iio: gts-helpers: fix integration time units The IIO ABI mandates expressing integration times in seconds. The GTS helper errorneously uses micro seconds in integration_times_available. Fix this by converting the lists to IIO_VAL_INT_PLUS_MICRO. Fixes: 38416c28e168 ("iio: light: Add gain-time-scale helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/eeacd192c259e885850b5a2dd8b776bccfc44fa8.1681722914.git.mazziesaccount@gmail.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-gts-helper.c | 42 ++++++++++++++++++++------- 1 file changed, 32 insertions(+), 10 deletions(-) diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c index 8bb68975b259..7653261d2dc2 100644 --- a/drivers/iio/industrialio-gts-helper.c +++ b/drivers/iio/industrialio-gts-helper.c @@ -337,6 +337,17 @@ static int iio_gts_build_avail_scale_table(struct iio_gts *gts) return ret; } +static void iio_gts_us_to_int_micro(int *time_us, int *int_micro_times, + int num_times) +{ + int i; + + for (i = 0; i < num_times; i++) { + int_micro_times[i * 2] = time_us[i] / 1000000; + int_micro_times[i * 2 + 1] = time_us[i] % 1000000; + } +} + /** * iio_gts_build_avail_time_table - build table of available integration times * @gts: Gain time scale descriptor @@ -351,7 +362,7 @@ static int iio_gts_build_avail_scale_table(struct iio_gts *gts) */ static int iio_gts_build_avail_time_table(struct iio_gts *gts) { - int *times, i, j, idx = 0; + int *times, i, j, idx = 0, *int_micro_times; if (!gts->num_itime) return 0; @@ -378,13 +389,24 @@ static int iio_gts_build_avail_time_table(struct iio_gts *gts) } } } - gts->avail_time_tables = times; - /* - * This is just to survive a unlikely corner-case where times in the - * given time table were not unique. Else we could just trust the - * gts->num_itime. - */ - gts->num_avail_time_tables = idx; + + /* create a list of times formatted as list of IIO_VAL_INT_PLUS_MICRO */ + int_micro_times = kcalloc(idx, sizeof(int) * 2, GFP_KERNEL); + if (int_micro_times) { + /* + * This is just to survive a unlikely corner-case where times in + * the given time table were not unique. Else we could just + * trust the gts->num_itime. + */ + gts->num_avail_time_tables = idx; + iio_gts_us_to_int_micro(times, int_micro_times, idx); + } + + gts->avail_time_tables = int_micro_times; + kfree(times); + + if (!int_micro_times) + return -ENOMEM; return 0; } @@ -683,8 +705,8 @@ int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, return -EINVAL; *vals = gts->avail_time_tables; - *type = IIO_VAL_INT; - *length = gts->num_avail_time_tables; + *type = IIO_VAL_INT_PLUS_MICRO; + *length = gts->num_avail_time_tables * 2; return IIO_AVAIL_LIST; } -- GitLab From 79b8ded9d9c595db9bd5b2f62f5f738b36de1e22 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 16 Apr 2023 23:24:09 +0200 Subject: [PATCH 4878/5631] iio: accel: st_accel: Fix invalid mount_matrix on devices without ACPI _ONT method When apply_acpi_orientation() fails, st_accel_common_probe() will fall back to iio_read_mount_matrix(), which checks for a mount-matrix device property and if that is not set falls back to the identity matrix. But when a sensor has no ACPI companion fwnode, or when the ACPI fwnode does not have a "_ONT" method apply_acpi_orientation() was returning 0, causing iio_read_mount_matrix() to never get called resulting in an invalid mount_matrix: [root@fedora ~]# cat /sys/bus/iio/devices/iio\:device0/mount_matrix (null), (null), (null); (null), (null), (null); (null), (null), (null) Fix this by making apply_acpi_orientation() always return an error when it did not set the mount_matrix. Fixes: 3d8ad94bb175 ("iio: accel: st_sensors: Support generic mounting matrix") Signed-off-by: Hans de Goede Reviewed-by: Linus Walleij Tested-by: Marius Hoch Link: https://lore.kernel.org/r/20230416212409.310936-1-hdegoede@redhat.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 5f7d81b44b1d..282e539157f8 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1291,12 +1291,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) adev = ACPI_COMPANION(indio_dev->dev.parent); if (!adev) - return 0; + return -ENXIO; /* Read _ONT data, which should be a package of 6 integers. */ status = acpi_evaluate_object(adev->handle, "_ONT", NULL, &buffer); if (status == AE_NOT_FOUND) { - return 0; + return -ENXIO; } else if (ACPI_FAILURE(status)) { dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", status); -- GitLab From e55245d115bb9054cb72cdd5dda5660f4484873a Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Thu, 30 Mar 2023 12:21:00 +0200 Subject: [PATCH 4879/5631] iio: adc: ad7192: Change "shorted" channels to differential The AD7192 provides a specific channel configuration where both negative and positive inputs are connected to AIN2. This was represented in the ad7192 driver as a IIO channel with .channel = 2 and .extended_name set to "shorted". The problem with this approach, is that the driver provided two IIO channels with the identifier .channel = 2; one "shorted" and the other not. This goes against the IIO ABI, as a channel identifier should be unique. Address this issue by changing "shorted" channels to being differential instead, with channel 2 vs. itself, as we're actually measuring AIN2 vs. itself. Note that the fix tag is for the commit that moved the driver out of staging. The bug existed before that, but backporting would become very complex further down and unlikely to happen. Fixes: b581f748cce0 ("staging: iio: adc: ad7192: move out of staging") Signed-off-by: Paul Cercueil Co-developed-by: Alisa Roman Signed-off-by: Alisa Roman Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230330102100.17590-1-paul@crapouillou.net Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ad7192.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 55a6ab591016..99bb604b78c8 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -897,10 +897,6 @@ static const struct iio_info ad7195_info = { __AD719x_CHANNEL(_si, _channel1, -1, _address, NULL, IIO_VOLTAGE, \ BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) -#define AD719x_SHORTED_CHANNEL(_si, _channel1, _address) \ - __AD719x_CHANNEL(_si, _channel1, -1, _address, "shorted", IIO_VOLTAGE, \ - BIT(IIO_CHAN_INFO_SCALE), ad7192_calibsys_ext_info) - #define AD719x_TEMP_CHANNEL(_si, _address) \ __AD719x_CHANNEL(_si, 0, -1, _address, NULL, IIO_TEMP, 0, NULL) @@ -908,7 +904,7 @@ static const struct iio_chan_spec ad7192_channels[] = { AD719x_DIFF_CHANNEL(0, 1, 2, AD7192_CH_AIN1P_AIN2M), AD719x_DIFF_CHANNEL(1, 3, 4, AD7192_CH_AIN3P_AIN4M), AD719x_TEMP_CHANNEL(2, AD7192_CH_TEMP), - AD719x_SHORTED_CHANNEL(3, 2, AD7192_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(3, 2, 2, AD7192_CH_AIN2P_AIN2M), AD719x_CHANNEL(4, 1, AD7192_CH_AIN1), AD719x_CHANNEL(5, 2, AD7192_CH_AIN2), AD719x_CHANNEL(6, 3, AD7192_CH_AIN3), @@ -922,7 +918,7 @@ static const struct iio_chan_spec ad7193_channels[] = { AD719x_DIFF_CHANNEL(2, 5, 6, AD7193_CH_AIN5P_AIN6M), AD719x_DIFF_CHANNEL(3, 7, 8, AD7193_CH_AIN7P_AIN8M), AD719x_TEMP_CHANNEL(4, AD7193_CH_TEMP), - AD719x_SHORTED_CHANNEL(5, 2, AD7193_CH_AIN2P_AIN2M), + AD719x_DIFF_CHANNEL(5, 2, 2, AD7193_CH_AIN2P_AIN2M), AD719x_CHANNEL(6, 1, AD7193_CH_AIN1), AD719x_CHANNEL(7, 2, AD7193_CH_AIN2), AD719x_CHANNEL(8, 3, AD7193_CH_AIN3), -- GitLab From 9c0d6ccd7d6bbd275e390b55a3390b4274291d95 Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Wed, 3 May 2023 18:20:28 +0200 Subject: [PATCH 4880/5631] iio: adc: stm32-adc: skip adc-diff-channels setup if none is present If no adc differential channels are defined driver will fail with EINVAL: stm32-adc: probe of 48003000.adc:adc@0 failed with error -22 Fix this by skipping the initialization if no channels are defined. This applies only to the legacy way of initializing adc channels. Fixes: d7705f35448a ("iio: adc: stm32-adc: convert to device properties") Signed-off-by: Sean Nyekjaer Link: https://lore.kernel.org/r/20230503162029.3654093-1-sean@geanix.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/stm32-adc.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 1aadb2ad2cab..c105d82c3e45 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -2006,16 +2006,15 @@ static int stm32_adc_get_legacy_chan_count(struct iio_dev *indio_dev, struct stm * to get the *real* number of channels. */ ret = device_property_count_u32(dev, "st,adc-diff-channels"); - if (ret < 0) - return ret; - - ret /= (int)(sizeof(struct stm32_adc_diff_channel) / sizeof(u32)); - if (ret > adc_info->max_channels) { - dev_err(&indio_dev->dev, "Bad st,adc-diff-channels?\n"); - return -EINVAL; - } else if (ret > 0) { - adc->num_diff = ret; - num_channels += ret; + if (ret > 0) { + ret /= (int)(sizeof(struct stm32_adc_diff_channel) / sizeof(u32)); + if (ret > adc_info->max_channels) { + dev_err(&indio_dev->dev, "Bad st,adc-diff-channels?\n"); + return -EINVAL; + } else if (ret > 0) { + adc->num_diff = ret; + num_channels += ret; + } } /* Optional sample time is provided either for each, or all channels */ -- GitLab From 3e27ef0ced49f8ae7883c25fadf76a2086e99025 Mon Sep 17 00:00:00 2001 From: Sean Nyekjaer Date: Wed, 3 May 2023 18:20:29 +0200 Subject: [PATCH 4881/5631] iio: adc: stm32-adc: skip adc-channels setup if none is present If only adc differential channels are defined driver will fail with stm32-adc: probe of 48003000.adc:adc@0 failed with error -22 Fix this by skipping the initialization if no channels are defined. This applies only to the legacy way of initializing adc channels. Fixes: d7705f35448a ("iio: adc: stm32-adc: convert to device properties") Signed-off-by: Sean Nyekjaer Reviewed-by: Olivier Moysan Link: https://lore.kernel.org/r/20230503162029.3654093-2-sean@geanix.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/stm32-adc.c | 42 ++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index c105d82c3e45..bd7e2408bf28 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -2036,6 +2036,7 @@ static int stm32_adc_legacy_chan_init(struct iio_dev *indio_dev, struct stm32_adc_diff_channel diff[STM32_ADC_CH_MAX]; struct device *dev = &indio_dev->dev; u32 num_diff = adc->num_diff; + int num_se = nchans - num_diff; int size = num_diff * sizeof(*diff) / sizeof(u32); int scan_index = 0, ret, i, c; u32 smp = 0, smps[STM32_ADC_CH_MAX], chans[STM32_ADC_CH_MAX]; @@ -2062,29 +2063,32 @@ static int stm32_adc_legacy_chan_init(struct iio_dev *indio_dev, scan_index++; } } - - ret = device_property_read_u32_array(dev, "st,adc-channels", chans, - nchans); - if (ret) - return ret; - - for (c = 0; c < nchans; c++) { - if (chans[c] >= adc_info->max_channels) { - dev_err(&indio_dev->dev, "Invalid channel %d\n", - chans[c]); - return -EINVAL; + if (num_se > 0) { + ret = device_property_read_u32_array(dev, "st,adc-channels", chans, num_se); + if (ret) { + dev_err(&indio_dev->dev, "Failed to get st,adc-channels %d\n", ret); + return ret; } - /* Channel can't be configured both as single-ended & diff */ - for (i = 0; i < num_diff; i++) { - if (chans[c] == diff[i].vinp) { - dev_err(&indio_dev->dev, "channel %d misconfigured\n", chans[c]); + for (c = 0; c < num_se; c++) { + if (chans[c] >= adc_info->max_channels) { + dev_err(&indio_dev->dev, "Invalid channel %d\n", + chans[c]); return -EINVAL; } + + /* Channel can't be configured both as single-ended & diff */ + for (i = 0; i < num_diff; i++) { + if (chans[c] == diff[i].vinp) { + dev_err(&indio_dev->dev, "channel %d misconfigured\n", + chans[c]); + return -EINVAL; + } + } + stm32_adc_chan_init_one(indio_dev, &channels[scan_index], + chans[c], 0, scan_index, false); + scan_index++; } - stm32_adc_chan_init_one(indio_dev, &channels[scan_index], - chans[c], 0, scan_index, false); - scan_index++; } if (adc->nsmps > 0) { @@ -2305,7 +2309,7 @@ static int stm32_adc_chan_fw_init(struct iio_dev *indio_dev, bool timestamping) if (legacy) ret = stm32_adc_legacy_chan_init(indio_dev, adc, channels, - num_channels); + timestamping ? num_channels - 1 : num_channels); else ret = stm32_adc_generic_chan_init(indio_dev, adc, channels); if (ret < 0) -- GitLab From 72c1d11074d6160f19760d57fc78b2a7f52bcb1a Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Mon, 24 Apr 2023 11:23:12 +0200 Subject: [PATCH 4882/5631] dt-bindings: iio: imx8qxp-adc: add missing vref-supply Although this property is used right now for IIO_CHAN_INFO_SCALE, this ADC has two internal reference voltages, which the driver currently doesn't make use of. Fixes: db73419d8c06 ("dt-bindings: iio: adc: Add binding documentation for NXP IMX8QXP ADC") Signed-off-by: Alexander Stein Reviewed-by: Haibo Chen Acked-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20230424092312.61746-1-alexander.stein@ew.tq-group.com Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml b/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml index 63369ba388e4..0a192ca192c5 100644 --- a/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml @@ -39,6 +39,12 @@ properties: power-domains: maxItems: 1 + vref-supply: + description: | + External ADC reference voltage supply on VREFH pad. If VERID[MVI] is + set, there are additional, internal reference voltages selectable. + VREFH1 is always from VREFH pad. + "#io-channel-cells": const: 1 @@ -72,6 +78,7 @@ examples: assigned-clocks = <&clk IMX_SC_R_ADC_0>; assigned-clock-rates = <24000000>; power-domains = <&pd IMX_SC_R_ADC_0>; + vref-supply = <®_1v8>; #io-channel-cells = <1>; }; }; -- GitLab From a551c26e8e568fad42120843521529241b9bceec Mon Sep 17 00:00:00 2001 From: Frank Li Date: Mon, 1 May 2023 10:36:04 -0400 Subject: [PATCH 4883/5631] iio: light: vcnl4035: fixed chip ID check VCNL4035 register(0xE) ID_L and ID_M define as: ID_L: 0x80 ID_H: 7:6 (0:0) 5:4 (0:0) slave address = 0x60 (7-bit) (0:1) slave address = 0x51 (7-bit) (1:0) slave address = 0x40 (7-bit) (1:0) slave address = 0x41 (7-bit) 3:0 Version code default (0:0:0:0) So just check ID_L. Fixes: 55707294c4eb ("iio: light: Add support for vishay vcnl4035") Signed-off-by: Frank Li Link: https://lore.kernel.org/r/20230501143605.1615549-1-Frank.Li@nxp.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/light/vcnl4035.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 14e29330e972..94f5d611e98c 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -8,6 +8,7 @@ * TODO: Proximity */ #include +#include #include #include #include @@ -42,6 +43,7 @@ #define VCNL4035_ALS_PERS_MASK GENMASK(3, 2) #define VCNL4035_INT_ALS_IF_H_MASK BIT(12) #define VCNL4035_INT_ALS_IF_L_MASK BIT(13) +#define VCNL4035_DEV_ID_MASK GENMASK(7, 0) /* Default values */ #define VCNL4035_MODE_ALS_ENABLE BIT(0) @@ -413,6 +415,7 @@ static int vcnl4035_init(struct vcnl4035_data *data) return ret; } + id = FIELD_GET(VCNL4035_DEV_ID_MASK, id); if (id != VCNL4035_DEV_ID_VAL) { dev_err(&data->client->dev, "Wrong id, got %x, expected %x\n", id, VCNL4035_DEV_ID_VAL); -- GitLab From 24febc99ca725dcf42d57168a2f4e8a75a5ade92 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Wed, 3 May 2023 11:58:17 +0200 Subject: [PATCH 4884/5631] iio: addac: ad74413: fix resistance input processing On success, ad74413r_get_single_adc_result() returns IIO_VAL_INT aka 1. So currently, the IIO_CHAN_INFO_PROCESSED case is effectively equivalent to the IIO_CHAN_INFO_RAW case, and we never call ad74413r_adc_to_resistance_result() to convert the adc measurement to ohms. Check ret for being negative rather than non-zero. Fixes: fea251b6a5dbd (iio: addac: add AD74413R driver) Signed-off-by: Rasmus Villemoes Reviewed-by: Nuno Sa Link: https://lore.kernel.org/r/20230503095817.452551-1-linux@rasmusvillemoes.dk Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/addac/ad74413r.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index 07e9f6ae16a8..e3366cf5eb31 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -1007,7 +1007,7 @@ static int ad74413r_read_raw(struct iio_dev *indio_dev, ret = ad74413r_get_single_adc_result(indio_dev, chan->channel, val); - if (ret) + if (ret < 0) return ret; ad74413r_adc_to_resistance_result(*val, val); -- GitLab From a146eccb68be161ae9eab5f3f68bb0ed7c0fbaa8 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 8 May 2023 06:02:08 +0200 Subject: [PATCH 4885/5631] iio: dac: build ad5758 driver when AD5758 is selected Commit 28d1a7ac2a0d ("iio: dac: Add AD5758 support") adds the config AD5758 and the corresponding driver ad5758.c. In the Makefile, the ad5758 driver is however included when AD5755 is selected, not when AD5758 is selected. Probably, this was simply a mistake that happened by copy-and-paste and forgetting to adjust the actual line. Surprisingly, no one has ever noticed that this driver is actually only included when AD5755 is selected and that the config AD5758 has actually no effect on the build. Fixes: 28d1a7ac2a0d ("iio: dac: Add AD5758 support") Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230508040208.12033-1-lukas.bulwahn@gmail.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/dac/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/dac/Makefile b/drivers/iio/dac/Makefile index 6c74fea21736..addd97a78838 100644 --- a/drivers/iio/dac/Makefile +++ b/drivers/iio/dac/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_AD5592R_BASE) += ad5592r-base.o obj-$(CONFIG_AD5592R) += ad5592r.o obj-$(CONFIG_AD5593R) += ad5593r.o obj-$(CONFIG_AD5755) += ad5755.o -obj-$(CONFIG_AD5755) += ad5758.o +obj-$(CONFIG_AD5758) += ad5758.o obj-$(CONFIG_AD5761) += ad5761.o obj-$(CONFIG_AD5764) += ad5764.o obj-$(CONFIG_AD5766) += ad5766.o -- GitLab From d049151adde4ec17392592d145e94f0086f8ee80 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Mon, 8 May 2023 14:01:25 +0300 Subject: [PATCH 4886/5631] iio: bu27034: Ensure reset is written The reset bit must be always written to the hardware no matter what value is in a cache or register. Ensure this by using regmap_write_bits() instead of the regmap_update_bits(). Furthermore, the SWRESET bit may be self-clearing, so mark the SYSTEM_CONTROL register volatile to guarantee we do also read the right state - should we ever need to read it. Finally, writing the SWRESET bit will restore the default register values. This can cause register cache to be outdated if there are any register values cached. Rebuild register cache after SWRESET and use regmap_update_bits() when performing the reset. Signed-off-by: Matti Vaittinen Fixes: e52afbd61039 ("iio: light: ROHM BU27034 Ambient Light Sensor") Link: https://lore.kernel.org/r/ZFjWhbfuN5XcKty+@fedora Signed-off-by: Jonathan Cameron --- drivers/iio/light/rohm-bu27034.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/iio/light/rohm-bu27034.c b/drivers/iio/light/rohm-bu27034.c index 25c9b79574a5..f85194fda6b0 100644 --- a/drivers/iio/light/rohm-bu27034.c +++ b/drivers/iio/light/rohm-bu27034.c @@ -231,6 +231,9 @@ struct bu27034_result { static const struct regmap_range bu27034_volatile_ranges[] = { { + .range_min = BU27034_REG_SYSTEM_CONTROL, + .range_max = BU27034_REG_SYSTEM_CONTROL, + }, { .range_min = BU27034_REG_MODE_CONTROL4, .range_max = BU27034_REG_MODE_CONTROL4, }, { @@ -1272,12 +1275,19 @@ static int bu27034_chip_init(struct bu27034_data *data) int ret, sel; /* Reset */ - ret = regmap_update_bits(data->regmap, BU27034_REG_SYSTEM_CONTROL, + ret = regmap_write_bits(data->regmap, BU27034_REG_SYSTEM_CONTROL, BU27034_MASK_SW_RESET, BU27034_MASK_SW_RESET); if (ret) return dev_err_probe(data->dev, ret, "Sensor reset failed\n"); msleep(1); + + ret = regmap_reinit_cache(data->regmap, &bu27034_regmap); + if (ret) { + dev_err(data->dev, "Failed to reinit reg cache\n"); + return ret; + } + /* * Read integration time here to ensure it is in regmap cache. We do * this to speed-up the int-time acquisition in the start of the buffer -- GitLab From 56cd3d1c5c5b073a1a444eafdcf97d4d866d351a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Fri, 12 May 2023 10:53:41 +0300 Subject: [PATCH 4887/5631] iio: accel: kx022a fix irq getting The fwnode_irq_get_byname() was returning 0 at device-tree mapping error. If this occurred, the KX022A driver did abort the probe but errorneously directly returned the return value from fwnode_irq_get_byname() from probe. In case of a device-tree mapping error this indicated success. The fwnode_irq_get_byname() has since been fixed to not return zero on error so the check for fwnode_irq_get_byname() can be relaxed to only treat negative values as errors. This will also do decent fix even when backported to branches where fwnode_irq_get_byname() can still return zero on error because KX022A probe should later fail at IRQ requesting and a prober error handling should follow. Relax the return value check for fwnode_irq_get_byname() to only treat negative values as errors. Reported-by: kernel test robot Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/202305110245.MFxC9bUj-lkp@intel.com/ Link: https://lore.kernel.org/r/202305110245.MFxC9bUj-lkp@intel.com/ Signed-off-by: Matti Vaittinen Fixes: 7c1d1677b322 ("iio: accel: Support Kionix/ROHM KX022A accelerometer") Link: https://lore.kernel.org/r/b45b4b638db109c6078d243252df3a7b0485f7d5.1683875389.git.mazziesaccount@gmail.com Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/accel/kionix-kx022a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index f98393d74666..b8636fa8eaeb 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -1048,7 +1048,7 @@ int kx022a_probe_internal(struct device *dev) data->ien_reg = KX022A_REG_INC4; } else { irq = fwnode_irq_get_byname(fwnode, "INT2"); - if (irq <= 0) + if (irq < 0) return dev_err_probe(dev, irq, "No suitable IRQ\n"); data->inc_reg = KX022A_REG_INC5; -- GitLab From 09d3bec7009186bdba77039df01e5834788b3f95 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 11 May 2023 02:43:30 +0200 Subject: [PATCH 4888/5631] iio: dac: mcp4725: Fix i2c_master_send() return value handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The i2c_master_send() returns number of sent bytes on success, or negative on error. The suspend/resume callbacks expect zero on success and non-zero on error. Adapt the return value of the i2c_master_send() to the expectation of the suspend and resume callbacks, including proper validation of the return value. Fixes: cf35ad61aca2 ("iio: add mcp4725 I2C DAC driver") Signed-off-by: Marek Vasut Reviewed-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20230511004330.206942-1-marex@denx.de Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/dac/mcp4725.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 46bf758760f8..3f5661a3718f 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -47,12 +47,18 @@ static int mcp4725_suspend(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; outbuf[0] = (data->powerdown_mode + 1) << 4; outbuf[1] = 0; data->powerdown = true; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static int mcp4725_resume(struct device *dev) @@ -60,13 +66,19 @@ static int mcp4725_resume(struct device *dev) struct mcp4725_data *data = iio_priv(i2c_get_clientdata( to_i2c_client(dev))); u8 outbuf[2]; + int ret; /* restore previous DAC value */ outbuf[0] = (data->dac_value >> 8) & 0xf; outbuf[1] = data->dac_value & 0xff; data->powerdown = false; - return i2c_master_send(data->client, outbuf, 2); + ret = i2c_master_send(data->client, outbuf, 2); + if (ret < 0) + return ret; + else if (ret != 2) + return -EIO; + return 0; } static DEFINE_SIMPLE_DEV_PM_OPS(mcp4725_pm_ops, mcp4725_suspend, mcp4725_resume); -- GitLab From 55720d242052e860b9fde445e302e0425722e7f1 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 9 May 2023 14:34:22 +0200 Subject: [PATCH 4889/5631] dt-bindings: iio: adc: renesas,rcar-gyroadc: Fix adi,ad7476 compatible value The conversion to json-schema accidentally dropped the "ad" part prefix from the compatible value. Fixes: 8c41245872e2 ("dt-bindings:iio:adc:renesas,rcar-gyroadc: txt to yaml conversion.") Signed-off-by: Geert Uytterhoeven Reviewed-by: Marek Vasut Reviewed-by: Krzysztof Kozlowski Reviewed-by: Wolfram Sang Link: https://lore.kernel.org/r/6b328a3f52657c20759f3a5bb2fe033d47644ba8.1683635404.git.geert+renesas@glider.be Cc: Signed-off-by: Jonathan Cameron --- .../devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml index 1c7aee5ed3e0..36dff3250ea7 100644 --- a/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/renesas,rcar-gyroadc.yaml @@ -90,7 +90,7 @@ patternProperties: of the MAX chips to the GyroADC, while MISO line of each Maxim ADC connects to a shared input pin of the GyroADC. enum: - - adi,7476 + - adi,ad7476 - fujitsu,mb88101a - maxim,max1162 - maxim,max11100 -- GitLab From 5354b2af34064a4579be8bc0e2f15a7b70f14b5f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 29 Apr 2023 00:06:28 -0400 Subject: [PATCH 4890/5631] ext4: allow ext4_get_group_info() to fail Previously, ext4_get_group_info() would treat an invalid group number as BUG(), since in theory it should never happen. However, if a malicious attaker (or fuzzer) modifies the superblock via the block device while it is the file system is mounted, it is possible for s_first_data_block to get set to a very large number. In that case, when calculating the block group of some block number (such as the starting block of a preallocation region), could result in an underflow and very large block group number. Then the BUG_ON check in ext4_get_group_info() would fire, resutling in a denial of service attack that can be triggered by root or someone with write access to the block device. For a quality of implementation perspective, it's best that even if the system administrator does something that they shouldn't, that it will not trigger a BUG. So instead of BUG'ing, ext4_get_group_info() will call ext4_error and return NULL. We also add fallback code in all of the callers of ext4_get_group_info() that it might NULL. Also, since ext4_get_group_info() was already borderline to be an inline function, un-inline it. The results in a next reduction of the compiled text size of ext4 by roughly 2k. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430154311.579720-2-tytso@mit.edu Reported-by: syzbot+e2efa3efc15a1c9e95c3@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=69b28112e098b070f639efb356393af3ffec4220 Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- fs/ext4/balloc.c | 18 ++++++++++++- fs/ext4/ext4.h | 15 ++--------- fs/ext4/ialloc.c | 12 ++++++--- fs/ext4/mballoc.c | 64 +++++++++++++++++++++++++++++++++++++++-------- fs/ext4/super.c | 2 ++ 5 files changed, 82 insertions(+), 29 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index c49e612e3975..c1edde817be8 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -321,6 +321,22 @@ static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb, return (next_zero_bit < bitmap_size ? next_zero_bit : 0); } +struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group) +{ + struct ext4_group_info **grp_info; + long indexv, indexh; + + if (unlikely(group >= EXT4_SB(sb)->s_groups_count)) { + ext4_error(sb, "invalid group %u", group); + return NULL; + } + indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); + indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); + grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); + return grp_info[indexh]; +} + /* * Return the block number which was discovered to be invalid, or 0 if * the block bitmap is valid. @@ -395,7 +411,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 18cb2680dc39..7e8f66ba17f4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2625,6 +2625,8 @@ extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, struct buffer_head ** bh); +extern struct ext4_group_info *ext4_get_group_info(struct super_block *sb, + ext4_group_t group); extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, @@ -3232,19 +3234,6 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) raw_inode->i_size_high = cpu_to_le32(i_size >> 32); } -static inline -struct ext4_group_info *ext4_get_group_info(struct super_block *sb, - ext4_group_t group) -{ - struct ext4_group_info **grp_info; - long indexv, indexh; - BUG_ON(group >= EXT4_SB(sb)->s_groups_count); - indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb)); - indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1); - grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv); - return grp_info[indexh]; -} - /* * Reading s_groups_count requires using smp_rmb() afterwards. See * the locking protocol documented in the comments of ext4_group_add() diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 787ab89c2c26..754f961cd9fd 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -91,7 +91,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, if (buffer_verified(bh)) return 0; - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) return -EFSCORRUPTED; ext4_lock_group(sb, block_group); @@ -293,7 +293,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) } if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, block_group); - if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { + if (!grp || unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) { fatal = -EFSCORRUPTED; goto error_return; } @@ -1046,7 +1046,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap, * Skip groups with already-known suspicious inode * tables */ - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + if (!grp || EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) goto next_group; } @@ -1183,6 +1183,10 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap, if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { grp = ext4_get_group_info(sb, group); + if (!grp) { + err = -EFSCORRUPTED; + goto out; + } down_read(&grp->alloc_sem); /* * protect vs itable * lazyinit @@ -1526,7 +1530,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, } gdp = ext4_get_group_desc(sb, group, &group_desc_bh); - if (!gdp) + if (!gdp || !grp) goto out; /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 78259bddbc4d..a857db48b383 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -745,6 +745,8 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file, MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); + if (!grp) + return NULL; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; @@ -1060,9 +1062,9 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, - void *buddy, void *bitmap, ext4_group_t group) + void *buddy, void *bitmap, ext4_group_t group, + struct ext4_group_info *grp) { - struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; @@ -1181,6 +1183,8 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) break; grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + continue; /* * If page is uptodate then we came here after online resize * which added some new uninitialized group info structs, so @@ -1246,6 +1250,10 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -1256,7 +1264,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); - ext4_mb_generate_buddy(sb, data, incore, group); + ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { @@ -1370,6 +1378,9 @@ int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); + if (!this_grp) + return -EFSCORRUPTED; + /* * This ensures that we don't reinit the buddy cache * page which map to the group from which we are already @@ -1444,6 +1455,8 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, blocks_per_page = PAGE_SIZE / sb->s_blocksize; grp = ext4_get_group_info(sb, group); + if (!grp) + return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; @@ -2159,6 +2172,8 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; + if (!grp) + return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) @@ -2385,7 +2400,7 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp) || !grp)) return false; free = grp->bb_free; @@ -2454,6 +2469,8 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_grpblk_t free; int ret = 0; + if (!grp) + return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) { @@ -2534,7 +2551,7 @@ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, * prefetch once, so we avoid getblk() call, which can * be expensive. */ - if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && @@ -2578,7 +2595,7 @@ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, gdp = ext4_get_group_desc(sb, group, NULL); grp = ext4_get_group_info(sb, group); - if (EXT4_MB_GRP_NEED_INIT(grp) && + if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { @@ -2837,6 +2854,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); + if (!grinfo) + return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); @@ -2847,7 +2866,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) buddy_loaded = 1; } - memcpy(&sg, ext4_get_group_info(sb, group), i); + memcpy(&sg, grinfo, i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); @@ -3208,8 +3227,12 @@ static int ext4_mb_init_backend(struct super_block *sb) err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); - while (i-- > 0) - kmem_cache_free(cachep, ext4_get_group_info(sb, i)); + while (i-- > 0) { + struct ext4_group_info *grp = ext4_get_group_info(sb, i); + + if (grp) + kmem_cache_free(cachep, grp); + } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); @@ -3522,6 +3545,8 @@ int ext4_mb_release(struct super_block *sb) for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); + if (!grinfo) + continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); @@ -4606,6 +4631,8 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, struct ext4_free_data *entry; grp = ext4_get_group_info(sb, group); + if (!grp) + return; n = rb_first(&(grp->bb_free_root)); while (n) { @@ -4633,6 +4660,9 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, int preallocated = 0; int len; + if (!grp) + return; + /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here @@ -4869,6 +4899,8 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; @@ -4918,6 +4950,8 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac) atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); + if (!grp) + return; lg = ac->ac_lg; BUG_ON(lg == NULL); @@ -5043,6 +5077,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, int err; int free = 0; + if (!grp) + return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; @@ -5297,6 +5333,9 @@ static inline void ext4_mb_show_pa(struct super_block *sb) struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; + + if (!grp) + continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, @@ -6064,6 +6103,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, struct buffer_head *bitmap_bh = NULL; struct super_block *sb = inode->i_sb; struct ext4_group_desc *gdp; + struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; struct buffer_head *gd_bh; @@ -6089,8 +6129,8 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT( - ext4_get_group_info(sb, block_group)))) + grp = ext4_get_group_info(sb, block_group); + if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* @@ -6692,6 +6732,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) for (group = first_group; group <= last_group; group++) { grp = ext4_get_group_info(sb, group); + if (!grp) + continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d39f386e9baf..4037c8611c02 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1048,6 +1048,8 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb, struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; + if (!grp || !gdp) + return; if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) { ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); -- GitLab From 463808f237cf73e98a1a45ff7460c2406a150a0b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 29 Apr 2023 16:14:46 -0400 Subject: [PATCH 4891/5631] ext4: remove a BUG_ON in ext4_mb_release_group_pa() If a malicious fuzzer overwrites the ext4 superblock while it is mounted such that the s_first_data_block is set to a very large number, the calculation of the block group can underflow, and trigger a BUG_ON check. Change this to be an ext4_warning so that we don't crash the kernel. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430154311.579720-3-tytso@mit.edu Reported-by: syzbot+e2efa3efc15a1c9e95c3@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=69b28112e098b070f639efb356393af3ffec4220 Signed-off-by: Theodore Ts'o --- fs/ext4/mballoc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a857db48b383..7b2e36d103cb 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5047,7 +5047,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); - BUG_ON(group != e4b->bd_group && pa->pa_len != 0); + if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { + ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", + e4b->bd_group, group, pa->pa_pstart); + return 0; + } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); -- GitLab From b87c7cdf2bed4928b899e1ce91ef0d147017ba45 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 30 Apr 2023 03:04:13 -0400 Subject: [PATCH 4892/5631] ext4: fix invalid free tracking in ext4_xattr_move_to_block() In ext4_xattr_move_to_block(), the value of the extended attribute which we need to move to an external block may be allocated by kvmalloc() if the value is stored in an external inode. So at the end of the function the code tried to check if this was the case by testing entry->e_value_inum. However, at this point, the pointer to the xattr entry is no longer valid, because it was removed from the original location where it had been stored. So we could end up calling kvfree() on a pointer which was not allocated by kvmalloc(); or we could also potentially leak memory by not freeing the buffer when it should be freed. Fix this by storing whether it should be freed in a separate variable. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230430160426.581366-1-tytso@mit.edu Link: https://syzkaller.appspot.com/bug?id=5c2aee8256e30b55ccf57312c16d88417adbd5e1 Link: https://syzkaller.appspot.com/bug?id=41a6b5d4917c0412eb3b3c3c604965bed7d7420b Reported-by: syzbot+64b645917ce07d89bde5@syzkaller.appspotmail.com Reported-by: syzbot+0d042627c4f2ad332195@syzkaller.appspotmail.com Signed-off-by: Theodore Ts'o --- fs/ext4/xattr.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index dadad29bd81b..dfc2e223bd10 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2614,6 +2614,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); + int needs_kvfree = 0; int error; is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); @@ -2636,7 +2637,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, error = -ENOMEM; goto out; } - + needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; @@ -2675,7 +2676,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, out: kfree(b_entry_name); - if (entry->e_value_inum && buffer) + if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); -- GitLab From 00d873c17e29cc32d90ca852b82685f1673acaa5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 4 May 2023 14:47:23 +0200 Subject: [PATCH 4893/5631] ext4: avoid deadlock in fs reclaim with page writeback Ext4 has a filesystem wide lock protecting ext4_writepages() calls to avoid races with switching of journalled data flag or inode format. This lock can however cause a deadlock like: CPU0 CPU1 ext4_writepages() percpu_down_read(sbi->s_writepages_rwsem); ext4_change_inode_journal_flag() percpu_down_write(sbi->s_writepages_rwsem); - blocks, all readers block from now on ext4_do_writepages() ext4_init_io_end() kmem_cache_zalloc(io_end_cachep, GFP_KERNEL) fs_reclaim frees dentry... dentry_unlink_inode() iput() - last ref => iput_final() - inode dirty => write_inode_now()... ext4_writepages() tries to acquire sbi->s_writepages_rwsem and blocks forever Make sure we cannot recurse into filesystem reclaim from writeback code to avoid the deadlock. Reported-by: syzbot+6898da502aef574c5f8a@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/0000000000004c66b405fa108e27@google.com Fixes: c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") CC: stable@vger.kernel.org Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230504124723.20205-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 24 ++++++++++++++++++++++++ fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/migrate.c | 11 ++++++----- 3 files changed, 40 insertions(+), 13 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 7e8f66ba17f4..6948d673bba2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1684,6 +1684,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode) return container_of(inode, struct ext4_inode_info, vfs_inode); } +static inline int ext4_writepages_down_read(struct super_block *sb) +{ + percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_read(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); +} + +static inline int ext4_writepages_down_write(struct super_block *sb) +{ + percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem); + return memalloc_nofs_save(); +} + +static inline void ext4_writepages_up_write(struct super_block *sb, int ctx) +{ + memalloc_nofs_restore(ctx); + percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem); +} + static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) { return ino == EXT4_ROOT_INO || diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0d5ba922e411..3cb774d9e3f1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2783,11 +2783,12 @@ static int ext4_writepages(struct address_space *mapping, .can_map = 1, }; int ret; + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) return -EIO; - percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(sb); ret = ext4_do_writepages(&mpd); /* * For data=journal writeback we could have come across pages marked @@ -2796,7 +2797,7 @@ static int ext4_writepages(struct address_space *mapping, */ if (!ret && mpd.journalled_more_data) ret = ext4_do_writepages(&mpd); - percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem); + ext4_writepages_up_read(sb, alloc_ctx); return ret; } @@ -2824,17 +2825,18 @@ static int ext4_dax_writepages(struct address_space *mapping, long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + int alloc_ctx; if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - percpu_down_read(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); - percpu_up_read(&sbi->s_writepages_rwsem); + ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } @@ -5928,7 +5930,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) journal_t *journal; handle_t *handle; int err; - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int alloc_ctx; /* * We have to be very careful here: changing a data block's @@ -5966,7 +5968,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) } } - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* @@ -5983,7 +5985,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) err = jbd2_journal_flush(journal, 0); if (err < 0) { jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); @@ -5991,7 +5993,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) filemap_invalidate_unlock(inode->i_mapping); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index a19a9661646e..d98ac2af8199 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -408,7 +408,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode) int ext4_ext_migrate(struct inode *inode) { - struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; @@ -418,6 +417,7 @@ int ext4_ext_migrate(struct inode *inode) unsigned long max_entries; __u32 goal, tmp_csum_seed; uid_t owner[2]; + int alloc_ctx; /* * If the filesystem does not support extents, or the inode @@ -434,7 +434,7 @@ int ext4_ext_migrate(struct inode *inode) */ return retval; - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); /* * Worst case we can touch the allocation bitmaps and a block @@ -586,7 +586,7 @@ int ext4_ext_migrate(struct inode *inode) unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return retval; } @@ -605,6 +605,7 @@ int ext4_ind_migrate(struct inode *inode) ext4_fsblk_t blk; handle_t *handle; int ret, ret2 = 0; + int alloc_ctx; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) @@ -621,7 +622,7 @@ int ext4_ind_migrate(struct inode *inode) if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); - percpu_down_write(&sbi->s_writepages_rwsem); + alloc_ctx = ext4_writepages_down_write(inode->i_sb); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { @@ -665,6 +666,6 @@ int ext4_ind_migrate(struct inode *inode) ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: - percpu_up_write(&sbi->s_writepages_rwsem); + ext4_writepages_up_write(inode->i_sb, alloc_ctx); return ret; } -- GitLab From 492888df0c7b42fc0843631168b0021bc4caee84 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 4 May 2023 14:55:24 +0200 Subject: [PATCH 4894/5631] ext4: fix data races when using cached status extents When using cached extent stored in extent status tree in tree->cache_es another process holding ei->i_es_lock for reading can be racing with us setting new value of tree->cache_es. If the compiler would decide to refetch tree->cache_es at an unfortunate moment, it could result in a bogus in_range() check. Fix the possible race by using READ_ONCE() when using tree->cache_es only under ei->i_es_lock for reading. Cc: stable@kernel.org Reported-by: syzbot+4a03518df1e31b537066@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/000000000000d3b33905fa0fd4a6@google.com Suggested-by: Dmitry Vyukov Signed-off-by: Jan Kara Link: https://lore.kernel.org/r/20230504125524.10802-1-jack@suse.cz Signed-off-by: Theodore Ts'o --- fs/ext4/extents_status.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 7bc221038c6c..595abb9e7d74 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -267,14 +267,12 @@ static void __es_find_extent_range(struct inode *inode, /* see if the extent has been cached */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u) %llu %x\n", - lblk, es1->es_lblk, es1->es_len, - ext4_es_pblock(es1), ext4_es_status(es1)); - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u) %llu %x\n", + lblk, es1->es_lblk, es1->es_len, + ext4_es_pblock(es1), ext4_es_status(es1)); + goto out; } es1 = __es_tree_search(&tree->root, lblk); @@ -293,7 +291,7 @@ static void __es_find_extent_range(struct inode *inode, } if (es1 && matching_fn(es1)) { - tree->cache_es = es1; + WRITE_ONCE(tree->cache_es, es1); es->es_lblk = es1->es_lblk; es->es_len = es1->es_len; es->es_pblk = es1->es_pblk; @@ -931,14 +929,12 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk, /* find extent in cache firstly */ es->es_lblk = es->es_len = es->es_pblk = 0; - if (tree->cache_es) { - es1 = tree->cache_es; - if (in_range(lblk, es1->es_lblk, es1->es_len)) { - es_debug("%u cached by [%u/%u)\n", - lblk, es1->es_lblk, es1->es_len); - found = 1; - goto out; - } + es1 = READ_ONCE(tree->cache_es); + if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) { + es_debug("%u cached by [%u/%u)\n", + lblk, es1->es_lblk, es1->es_len); + found = 1; + goto out; } node = tree->root.rb_node; -- GitLab From 4f04351888a83e595571de672e0a4a8b74f4fb31 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Thu, 4 May 2023 12:15:25 +0000 Subject: [PATCH 4895/5631] ext4: avoid a potential slab-out-of-bounds in ext4_group_desc_csum When modifying the block device while it is mounted by the filesystem, syzbot reported the following: BUG: KASAN: slab-out-of-bounds in crc16+0x206/0x280 lib/crc16.c:58 Read of size 1 at addr ffff888075f5c0a8 by task syz-executor.2/15586 CPU: 1 PID: 15586 Comm: syz-executor.2 Not tainted 6.2.0-rc5-syzkaller-00205-gc96618275234 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1b1/0x290 lib/dump_stack.c:106 print_address_description+0x74/0x340 mm/kasan/report.c:306 print_report+0x107/0x1f0 mm/kasan/report.c:417 kasan_report+0xcd/0x100 mm/kasan/report.c:517 crc16+0x206/0x280 lib/crc16.c:58 ext4_group_desc_csum+0x81b/0xb20 fs/ext4/super.c:3187 ext4_group_desc_csum_set+0x195/0x230 fs/ext4/super.c:3210 ext4_mb_clear_bb fs/ext4/mballoc.c:6027 [inline] ext4_free_blocks+0x191a/0x2810 fs/ext4/mballoc.c:6173 ext4_remove_blocks fs/ext4/extents.c:2527 [inline] ext4_ext_rm_leaf fs/ext4/extents.c:2710 [inline] ext4_ext_remove_space+0x24ef/0x46a0 fs/ext4/extents.c:2958 ext4_ext_truncate+0x177/0x220 fs/ext4/extents.c:4416 ext4_truncate+0xa6a/0xea0 fs/ext4/inode.c:4342 ext4_setattr+0x10c8/0x1930 fs/ext4/inode.c:5622 notify_change+0xe50/0x1100 fs/attr.c:482 do_truncate+0x200/0x2f0 fs/open.c:65 handle_truncate fs/namei.c:3216 [inline] do_open fs/namei.c:3561 [inline] path_openat+0x272b/0x2dd0 fs/namei.c:3714 do_filp_open+0x264/0x4f0 fs/namei.c:3741 do_sys_openat2+0x124/0x4e0 fs/open.c:1310 do_sys_open fs/open.c:1326 [inline] __do_sys_creat fs/open.c:1402 [inline] __se_sys_creat fs/open.c:1396 [inline] __x64_sys_creat+0x11f/0x160 fs/open.c:1396 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f72f8a8c0c9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f72f97e3168 EFLAGS: 00000246 ORIG_RAX: 0000000000000055 RAX: ffffffffffffffda RBX: 00007f72f8bac050 RCX: 00007f72f8a8c0c9 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020000280 RBP: 00007f72f8ae7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffd165348bf R14: 00007f72f97e3300 R15: 0000000000022000 Replace le16_to_cpu(sbi->s_es->s_desc_size) with sbi->s_desc_size It reduces ext4's compiled text size, and makes the code more efficient (we remove an extra indirect reference and a potential byte swap on big endian systems), and there is no downside. It also avoids the potential KASAN / syzkaller failure, as a bonus. Reported-by: syzbot+fc51227e7100c9294894@syzkaller.appspotmail.com Reported-by: syzbot+8785e41224a3afd04321@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=70d28d11ab14bd7938f3e088365252aa923cff42 Link: https://syzkaller.appspot.com/bug?id=b85721b38583ecc6b5e72ff524c67302abbc30f3 Link: https://lore.kernel.org/all/000000000000ece18705f3b20934@google.com/ Fixes: 717d50e4971b ("Ext4: Uninitialized Block Groups") Cc: stable@vger.kernel.org Signed-off-by: Tudor Ambarus Link: https://lore.kernel.org/r/20230504121525.3275886-1-tudor.ambarus@linaro.org Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4037c8611c02..425b95a7a0ab 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3240,11 +3240,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group, crc = crc16(crc, (__u8 *)gdp, offset); offset += sizeof(gdp->bg_checksum); /* skip checksum */ /* for checksum of struct ext4_group_desc do the rest...*/ - if (ext4_has_feature_64bit(sb) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) + if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size) crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + sbi->s_desc_size - offset); out: return cpu_to_le16(crc); -- GitLab From fa83c34e3e56b3c672af38059e066242655271b1 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Fri, 5 May 2023 21:24:29 +0800 Subject: [PATCH 4896/5631] ext4: check iomap type only if ext4_iomap_begin() does not fail When ext4_iomap_overwrite_begin() calls ext4_iomap_begin() map blocks may fail for some reason (e.g. memory allocation failure, bare disk write), and later because "iomap->type ! = IOMAP_MAPPED" triggers WARN_ON(). When ext4 iomap_begin() returns an error, it is normal that the type of iomap->type may not match the expectation. Therefore, we only determine if iomap->type is as expected when ext4_iomap_begin() is executed successfully. Cc: stable@kernel.org Reported-by: syzbot+08106c4b7d60702dbc14@syzkaller.appspotmail.com Link: https://lore.kernel.org/all/00000000000015760b05f9b4eee9@google.com Signed-off-by: Baokun Li Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20230505132429.714648-1-libaokun1@huawei.com Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3cb774d9e3f1..ce5f21b6c2b3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3377,7 +3377,7 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, */ flags &= ~IOMAP_WRITE; ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); - WARN_ON_ONCE(iomap->type != IOMAP_MAPPED); + WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED); return ret; } -- GitLab From a44be64bbecb15a452496f60db6eacfee2b59c79 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 5 May 2023 21:02:30 -0400 Subject: [PATCH 4897/5631] ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled When a file system currently mounted read/only is remounted read/write, if we clear the SB_RDONLY flag too early, before the quota is initialized, and there is another process/thread constantly attempting to create a directory, it's possible to trigger the WARN_ON_ONCE(dquot_initialize_needed(inode)); in ext4_xattr_block_set(), with the following stack trace: WARNING: CPU: 0 PID: 5338 at fs/ext4/xattr.c:2141 ext4_xattr_block_set+0x2ef2/0x3680 RIP: 0010:ext4_xattr_block_set+0x2ef2/0x3680 fs/ext4/xattr.c:2141 Call Trace: ext4_xattr_set_handle+0xcd4/0x15c0 fs/ext4/xattr.c:2458 ext4_initxattrs+0xa3/0x110 fs/ext4/xattr_security.c:44 security_inode_init_security+0x2df/0x3f0 security/security.c:1147 __ext4_new_inode+0x347e/0x43d0 fs/ext4/ialloc.c:1324 ext4_mkdir+0x425/0xce0 fs/ext4/namei.c:2992 vfs_mkdir+0x29d/0x450 fs/namei.c:4038 do_mkdirat+0x264/0x520 fs/namei.c:4061 __do_sys_mkdirat fs/namei.c:4076 [inline] __se_sys_mkdirat fs/namei.c:4074 [inline] __x64_sys_mkdirat+0x89/0xa0 fs/namei.c:4074 Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230506142419.984260-1-tytso@mit.edu Reported-by: syzbot+6385d7d3065524c5ca6d@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=6513f6cb5cd6b5fc9f37e3bb70d273b94be9c34c Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 425b95a7a0ab..c7bc4a2709cc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6387,6 +6387,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int enable_rw = 0; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6573,7 +6574,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (err) goto restore_opts; - sb->s_flags &= ~SB_RDONLY; + enable_rw = 1; if (ext4_has_feature_mmp(sb)) { err = ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)); @@ -6632,6 +6633,9 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); + if (enable_rw) + sb->s_flags &= ~SB_RDONLY; + if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb)) ext4_stop_mmpd(sbi); -- GitLab From 4b3cb1d108bfc2aebb0d7c8a52261a53cf7f5786 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 6 May 2023 11:59:13 -0400 Subject: [PATCH 4898/5631] ext4: improve error handling from ext4_dirhash() The ext4_dirhash() will *almost* never fail, especially when the hash tree feature was first introduced. However, with the addition of support of encrypted, casefolded file names, that function can most certainly fail today. So make sure the callers of ext4_dirhash() properly check for failures, and reflect the errors back up to their callers. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230506142419.984260-1-tytso@mit.edu Reported-by: syzbot+394aa8a792cb99dbc837@syzkaller.appspotmail.com Reported-by: syzbot+344aaa8697ebd232bfc8@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=db56459ea4ac4a676ae4b4678f633e55da005a9b Signed-off-by: Theodore Ts'o --- fs/ext4/hash.c | 6 +++++- fs/ext4/namei.c | 53 ++++++++++++++++++++++++++++++++++--------------- 2 files changed, 42 insertions(+), 17 deletions(-) diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 147b5241dd94..46c3423ddfa1 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -277,7 +277,11 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, } default: hinfo->hash = 0; - return -1; + hinfo->minor_hash = 0; + ext4_warning(dir->i_sb, + "invalid/unsupported hash tree version %u", + hinfo->hash_version); + return -EINVAL; } hash = hash & ~1; if (hash == (EXT4_HTREE_EOF_32BIT << 1)) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a5010b5b8a8c..45b579805c95 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -674,7 +674,7 @@ static struct stats dx_show_leaf(struct inode *dir, len = de->name_len; if (!IS_ENCRYPTED(dir)) { /* Directory is not encrypted */ - ext4fs_dirhash(dir, de->name, + (void) ext4fs_dirhash(dir, de->name, de->name_len, &h); printk("%*.s:(U)%x.%u ", len, name, h.hash, @@ -709,8 +709,9 @@ static struct stats dx_show_leaf(struct inode *dir, if (IS_CASEFOLDED(dir)) h.hash = EXT4_DIRENT_HASH(de); else - ext4fs_dirhash(dir, de->name, - de->name_len, &h); + (void) ext4fs_dirhash(dir, + de->name, + de->name_len, &h); printk("%*.s:(E)%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); @@ -720,7 +721,8 @@ static struct stats dx_show_leaf(struct inode *dir, #else int len = de->name_len; char *name = de->name; - ext4fs_dirhash(dir, de->name, de->name_len, &h); + (void) ext4fs_dirhash(dir, de->name, + de->name_len, &h); printk("%*.s:%x.%u ", len, name, h.hash, (unsigned) ((char *) de - base)); #endif @@ -849,8 +851,14 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; /* hash is already computed for encrypted casefolded directory */ if (fname && fname_name(fname) && - !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) - ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo); + !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) { + int ret = ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), hinfo); + if (ret < 0) { + ret_err = ERR_PTR(ret); + goto fail; + } + } hash = hinfo->hash; if (root->info.unused_flags & 1) { @@ -1111,7 +1119,12 @@ static int htree_dirblock_to_tree(struct file *dir_file, hinfo->minor_hash = 0; } } else { - ext4fs_dirhash(dir, de->name, de->name_len, hinfo); + err = ext4fs_dirhash(dir, de->name, + de->name_len, hinfo); + if (err < 0) { + count = err; + goto errout; + } } if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && @@ -1313,8 +1326,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, if (de->name_len && de->inode) { if (ext4_hash_in_dirent(dir)) h.hash = EXT4_DIRENT_HASH(de); - else - ext4fs_dirhash(dir, de->name, de->name_len, &h); + else { + int err = ext4fs_dirhash(dir, de->name, + de->name_len, &h); + if (err < 0) + return err; + } map_tail--; map_tail->hash = h.hash; map_tail->offs = ((char *) de - base)>>2; @@ -1452,10 +1469,9 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, hinfo->hash_version = DX_HASH_SIPHASH; hinfo->seed = NULL; if (cf_name->name) - ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); + return ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo); else - ext4fs_dirhash(dir, iname->name, iname->len, hinfo); - return 0; + return ext4fs_dirhash(dir, iname->name, iname->len, hinfo); } #endif @@ -2298,10 +2314,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; /* casefolded encrypted hashes are computed on fname setup */ - if (!ext4_hash_in_dirent(dir)) - ext4fs_dirhash(dir, fname_name(fname), - fname_len(fname), &fname->hinfo); - + if (!ext4_hash_in_dirent(dir)) { + int err = ext4fs_dirhash(dir, fname_name(fname), + fname_len(fname), &fname->hinfo); + if (err < 0) { + brelse(bh2); + brelse(bh); + return err; + } + } memset(frames, 0, sizeof(frames)); frame = frames; frame->entries = entries; -- GitLab From 4c0b4818b1f636bc96359f7817a2d8bab6370162 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 5 May 2023 22:20:29 -0400 Subject: [PATCH 4899/5631] ext4: improve error recovery code paths in __ext4_remount() If there are failures while changing the mount options in __ext4_remount(), we need to restore the old mount options. This commit fixes two problem. The first is there is a chance that we will free the old quota file names before a potential failure leading to a use-after-free. The second problem addressed in this commit is if there is a failed read/write to read-only transition, if the quota has already been suspended, we need to renable quota handling. Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230506142419.984260-2-tytso@mit.edu Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c7bc4a2709cc..bc0b4a98b337 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6617,9 +6617,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } #ifdef CONFIG_QUOTA - /* Release old quota file names */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(old_opts.s_qf_names[i]); if (enable_quota) { if (sb_any_quota_suspended(sb)) dquot_resume(sb, -1); @@ -6629,6 +6626,9 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) goto restore_opts; } } + /* Release old quota file names */ + for (i = 0; i < EXT4_MAXQUOTAS; i++) + kfree(old_opts.s_qf_names[i]); #endif if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); @@ -6642,6 +6642,13 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) return 0; restore_opts: + /* + * If there was a failing r/w to ro transition, we may need to + * re-enable quota + */ + if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) && + sb_any_quota_suspended(sb)) + dquot_resume(sb, -1); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; -- GitLab From f4ce24f54d9cca4f09a395f3eecce20d6bec4663 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 6 May 2023 21:04:01 -0400 Subject: [PATCH 4900/5631] ext4: fix deadlock when converting an inline directory in nojournal mode In no journal mode, ext4_finish_convert_inline_dir() can self-deadlock by calling ext4_handle_dirty_dirblock() when it already has taken the directory lock. There is a similar self-deadlock in ext4_incvert_inline_data_nolock() for data files which we'll fix at the same time. A simple reproducer demonstrating the problem: mke2fs -Fq -t ext2 -O inline_data -b 4k /dev/vdc 64 mount -t ext4 -o dirsync /dev/vdc /vdc cd /vdc mkdir file0 cd file0 touch file0 touch file1 attr -s BurnSpaceInEA -V abcde . touch supercalifragilisticexpialidocious Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230507021608.1290720-1-tytso@mit.edu Reported-by: syzbot+91dccab7c64e2850a4e5@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=ba84cc80a9491d65416bc7877e1650c87530fe8a Signed-off-by: Theodore Ts'o --- fs/ext4/inline.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 859bc4e2c9b0..d3dfc51a43c5 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1175,6 +1175,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, ext4_initialize_dirent_tail(dir_block, inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); + unlock_buffer(dir_block); err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; @@ -1249,6 +1250,7 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, if (!S_ISDIR(inode->i_mode)) { memcpy(data_bh->b_data, buf, inline_size); set_buffer_uptodate(data_bh); + unlock_buffer(data_bh); error = ext4_handle_dirty_metadata(handle, inode, data_bh); } else { @@ -1256,7 +1258,6 @@ static int ext4_convert_inline_data_nolock(handle_t *handle, buf, inline_size); } - unlock_buffer(data_bh); out_restore: if (error) ext4_restore_inline_data(handle, inode, iloc, buf, inline_size); -- GitLab From 6dcc98fbc46511f7a6650946f198df6951a5a88c Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 12 May 2023 14:49:57 -0400 Subject: [PATCH 4901/5631] ext4: add indication of ro vs r/w mounts in the mount message Whether the file system is mounted read-only or read/write is more important than the quota mode, which we are already printing. Add the ro vs r/w indication since this can be helpful in debugging problems from the console log. Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index bc0b4a98b337..9680fe753e59 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5684,8 +5684,9 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) descr = "out journal"; if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount")) - ext4_msg(sb, KERN_INFO, "mounted filesystem %pU with%s. " - "Quota mode: %s.", &sb->s_uuid, descr, + ext4_msg(sb, KERN_INFO, "mounted filesystem %pU %s with%s. " + "Quota mode: %s.", &sb->s_uuid, + sb_rdonly(sb) ? "ro" : "r/w", descr, ext4_quota_mode(sb)); /* Update the s_overhead_clusters if necessary */ @@ -6689,8 +6690,9 @@ static int ext4_reconfigure(struct fs_context *fc) if (ret < 0) return ret; - ext4_msg(sb, KERN_INFO, "re-mounted %pU. Quota mode: %s.", - &sb->s_uuid, ext4_quota_mode(sb)); + ext4_msg(sb, KERN_INFO, "re-mounted %pU %s. Quota mode: %s.", + &sb->s_uuid, sb_rdonly(sb) ? "ro" : "r/w", + ext4_quota_mode(sb)); return 0; } -- GitLab From 2220eaf90992c11d888fe771055d4de330385f01 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 12 May 2023 15:11:02 -0400 Subject: [PATCH 4902/5631] ext4: add bounds checking in get_max_inline_xattr_value_size() Normally the extended attributes in the inode body would have been checked when the inode is first opened, but if someone is writing to the block device while the file system is mounted, it's possible for the inode table to get corrupted. Add bounds checking to avoid reading beyond the end of allocated memory if this happens. Reported-by: syzbot+1966db24521e5f6e23f7@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=1966db24521e5f6e23f7 Cc: stable@kernel.org Signed-off-by: Theodore Ts'o --- fs/ext4/inline.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d3dfc51a43c5..f47adb284e90 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -34,6 +34,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; + void *end; int free, min_offs; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) @@ -57,14 +58,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode, raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); entry = IFIRST(header); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; /* Compute min_offs. */ - for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { + while (!IS_LAST_ENTRY(entry)) { + void *next = EXT4_XATTR_NEXT(entry); + + if (next >= end) { + EXT4_ERROR_INODE(inode, + "corrupt xattr in inline inode"); + return 0; + } if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; } + entry = next; } free = min_offs - ((void *)entry - (void *)IFIRST(header)) - sizeof(__u32); -- GitLab From 2a534e1d0d1591e951f9ece2fb460b2ff92edabd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 12 May 2023 15:16:27 -0400 Subject: [PATCH 4903/5631] ext4: bail out of ext4_xattr_ibody_get() fails for any reason In ext4_update_inline_data(), if ext4_xattr_ibody_get() fails for any reason, it's best if we just fail as opposed to stumbling on, especially if the failure is EFSCORRUPTED. Cc: stable@kernel.org Signed-off-by: Theodore Ts'o --- fs/ext4/inline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f47adb284e90..5854bd5a3352 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -360,7 +360,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_get(inode, i.name_index, i.name, value, len); - if (error == -ENODATA) + if (error < 0) goto out; BUFFER_TRACE(is.iloc.bh, "get_write_access"); -- GitLab From 6f9e98849edaa8aefc4030ff3500e41556e83ff7 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sat, 13 May 2023 22:30:06 +0200 Subject: [PATCH 4904/5631] parisc: Fix encoding of swp_entry due to added SWP_EXCLUSIVE flag Fix the __swp_offset() and __swp_entry() macros due to commit 6d239fc78c0b ("parisc/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE") which introduced the SWP_EXCLUSIVE flag by reusing the _PAGE_ACCESSED flag. Reported-by: Christoph Biedl Tested-by: Christoph Biedl Reviewed-by: David Hildenbrand Signed-off-by: Helge Deller Fixes: 6d239fc78c0b ("parisc/mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE") Cc: # v6.3+ --- arch/parisc/include/asm/pgtable.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index e2950f5db7c9..e715df5385d6 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -413,12 +413,12 @@ extern void paging_init (void); * For the 64bit version, the offset is extended by 32bit. */ #define __swp_type(x) ((x).val & 0x1f) -#define __swp_offset(x) ( (((x).val >> 6) & 0x7) | \ - (((x).val >> 8) & ~0x7) ) +#define __swp_offset(x) ( (((x).val >> 5) & 0x7) | \ + (((x).val >> 10) << 3) ) #define __swp_entry(type, offset) ((swp_entry_t) { \ ((type) & 0x1f) | \ - ((offset & 0x7) << 6) | \ - ((offset & ~0x7) << 8) }) + ((offset & 0x7) << 5) | \ + ((offset >> 3) << 10) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -- GitLab From 0f5bb36bf9b39a2a96e730bf4455095b50713f63 Mon Sep 17 00:00:00 2001 From: Duoming Zhou Date: Wed, 8 Mar 2023 12:55:14 +0000 Subject: [PATCH 4905/5631] media: netup_unidvb: fix use-after-free at del_timer() When Universal DVB card is detaching, netup_unidvb_dma_fini() uses del_timer() to stop dma->timeout timer. But when timer handler netup_unidvb_dma_timeout() is running, del_timer() could not stop it. As a result, the use-after-free bug could happen. The process is shown below: (cleanup routine) | (timer routine) | mod_timer(&dev->tx_sim_timer, ..) netup_unidvb_finidev() | (wait a time) netup_unidvb_dma_fini() | netup_unidvb_dma_timeout() del_timer(&dma->timeout); | | ndev->pci_dev->dev //USE Fix by changing del_timer() to del_timer_sync(). Link: https://lore.kernel.org/linux-media/20230308125514.4208-1-duoming@zju.edu.cn Fixes: 52b1eaf4c59a ("[media] netup_unidvb: NetUP Universal DVB-S/S2/T/T2/C PCI-E card driver") Signed-off-by: Duoming Zhou Signed-off-by: Mauro Carvalho Chehab --- drivers/media/pci/netup_unidvb/netup_unidvb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 8287851b5ffd..aaa1d2dedebd 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -697,7 +697,7 @@ static void netup_unidvb_dma_fini(struct netup_unidvb_dev *ndev, int num) netup_unidvb_dma_enable(dma, 0); msleep(50); cancel_work_sync(&dma->work); - del_timer(&dma->timeout); + del_timer_sync(&dma->timeout); } static int netup_unidvb_dma_setup(struct netup_unidvb_dev *ndev) -- GitLab From 858e97d7956d17a2cb56a9413468704a4d5abfe1 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Fri, 10 Mar 2023 16:56:04 +0000 Subject: [PATCH 4906/5631] media: dvb-usb: az6027: fix three null-ptr-deref in az6027_i2c_xfer() In az6027_i2c_xfer, msg is controlled by user. When msg[i].buf is null, commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") fix the null-ptr-deref bug when msg[i].addr is 0x99. However, null-ptr-deref also happens when msg[i].addr is 0xd0 and 0xc0. We add check on msg[i].len to prevent null-ptr-deref. Link: https://lore.kernel.org/linux-media/20230310165604.3093483-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/az6027.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 7d78ee09be5e..a31c6f82f4e9 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -988,6 +988,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* write/read request */ if (i + 1 < num && (msg[i + 1].flags & I2C_M_RD)) { req = 0xB9; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (msg[i].len << 8); length = msg[i + 1].len + 6; @@ -1001,6 +1005,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n /* demod 16bit addr */ req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = (((msg[i].buf[0] << 8) & 0xff00) | (msg[i].buf[1] & 0x00ff)); value = msg[i].addr + (2 << 8); length = msg[i].len - 2; @@ -1026,6 +1034,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n } else { req = 0xBD; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } index = msg[i].buf[0] & 0x00FF; value = msg[i].addr + (1 << 8); length = msg[i].len - 1; -- GitLab From a6dcefcc08eca1bf4e3d213c97c3cfb75f377935 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 08:58:53 +0000 Subject: [PATCH 4907/5631] media: dvb-usb-v2: ec168: fix null-ptr-deref in ec168_i2c_xfer() In ec168_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. If accessing msg[i].buf[0] without sanity check, null pointer deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313085853.3252349-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/ec168.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ec168.c b/drivers/media/usb/dvb-usb-v2/ec168.c index 7ed0ab9e429b..0e4773fc025c 100644 --- a/drivers/media/usb/dvb-usb-v2/ec168.c +++ b/drivers/media/usb/dvb-usb-v2/ec168.c @@ -115,6 +115,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], while (i < num) { if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = READ_DEMOD; req.value = 0; req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -131,6 +135,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], } } else { if (msg[i].addr == ec168_ec100_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_DEMOD; req.value = msg[i].buf[1]; /* val */ req.index = 0xff00 + msg[i].buf[0]; /* reg */ @@ -139,6 +147,10 @@ static int ec168_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = ec168_ctrl_msg(d, &req); i += 1; } else { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = WRITE_I2C; req.value = msg[i].buf[0]; /* val */ req.index = 0x0100 + msg[i].addr; /* I2C addr */ -- GitLab From dff919090155fb22679869e8469168f270dcd97f Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:27:51 +0000 Subject: [PATCH 4908/5631] media: dvb-usb-v2: ce6230: fix null-ptr-deref in ce6230_i2c_master_xfer() In ce6230_i2c_master_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach ce6230_i2c_master_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313092751.209496-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/ce6230.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/ce6230.c b/drivers/media/usb/dvb-usb-v2/ce6230.c index 44540de1a206..d3b5cb4a24da 100644 --- a/drivers/media/usb/dvb-usb-v2/ce6230.c +++ b/drivers/media/usb/dvb-usb-v2/ce6230.c @@ -101,6 +101,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_READ; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; @@ -117,6 +121,10 @@ static int ce6230_i2c_master_xfer(struct i2c_adapter *adap, } else { if (msg[i].addr == ce6230_zl10353_config.demod_address) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } req.cmd = DEMOD_WRITE; req.value = msg[i].addr >> 1; req.index = msg[i].buf[0]; -- GitLab From aa4a447b81b84f69c1a89ad899df157f386d7636 Mon Sep 17 00:00:00 2001 From: Zhang Shurong Date: Sun, 7 May 2023 15:52:47 +0100 Subject: [PATCH 4909/5631] media: dvb-usb-v2: rtl28xxu: fix null-ptr-deref in rtl28xxu_i2c_xfer In rtl28xxu_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach rtl28xxu_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/tencent_3623572106754AC2F266B316798B0F6CCA05@qq.com Signed-off-by: Zhang Shurong Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c index 795a012d4020..f7884bb56fcc 100644 --- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c +++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c @@ -176,6 +176,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1 || msg[1].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { /* return demod page from driver cache */ @@ -189,6 +193,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if (msg[0].len < 2) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_RD; @@ -217,8 +225,16 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = -EOPNOTSUPP; goto err_mutex_unlock; } else if (msg[0].addr == 0x10) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 1 - integrated demod */ if (msg[0].buf[0] == 0x00) { + if (msg[0].len < 2) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* save demod page for later demod access */ dev->page = msg[0].buf[1]; ret = 0; @@ -231,6 +247,10 @@ static int rtl28xxu_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], ret = rtl28xxu_ctrl_msg(d, &req); } } else if ((msg[0].len < 23) && (!dev->new_i2c_write)) { + if (msg[0].len < 1) { + ret = -EOPNOTSUPP; + goto err_mutex_unlock; + } /* method 2 - old I2C */ req.value = (msg[0].buf[0] << 8) | (msg[0].addr << 1); req.index = CMD_I2C_WR; -- GitLab From 9ded5bd2a49ce3015b7c936743eec0a0e6e11f0c Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Mon, 13 Mar 2023 09:50:08 +0000 Subject: [PATCH 4910/5631] media: dvb-usb: digitv: fix null-ptr-deref in digitv_i2c_xfer() In digitv_i2c_xfer, msg is controlled by user. When msg[i].buf is null and msg[i].len is zero, former checks on msg[i].buf would be passed. Malicious data finally reach digitv_i2c_xfer. If accessing msg[i].buf[0] without sanity check, null ptr deref would happen. We add check on msg[i].len to prevent crash. Similar commit: commit 0ed554fd769a ("media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()") Link: https://lore.kernel.org/linux-media/20230313095008.1039689-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/digitv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c index 2756815a780b..32134be16914 100644 --- a/drivers/media/usb/dvb-usb/digitv.c +++ b/drivers/media/usb/dvb-usb/digitv.c @@ -63,6 +63,10 @@ static int digitv_i2c_xfer(struct i2c_adapter *adap,struct i2c_msg msg[],int num warn("more than 2 i2c messages at a time is not handled yet. TODO."); for (i = 0; i < num; i++) { + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } /* write/read request */ if (i+1 < num && (msg[i+1].flags & I2C_M_RD)) { if (digitv_ctrl_msg(d, USB_READ_COFDM, msg[i].buf[0], NULL, 0, -- GitLab From a3fd1ef27aa686d871cefe207bd6168c4b0cd29e Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Tue, 28 Mar 2023 13:44:16 +0100 Subject: [PATCH 4911/5631] media: dvb-usb: dw2102: fix uninit-value in su3000_read_mac_address In su3000_read_mac_address, if i2c_transfer fails to execute two messages, array mac address will not be initialized. Without handling such error, later in function dvb_usb_adapter_dvb_init, proposed_mac is accessed before initialization. Fix this error by returning a negative value if message execution fails. Link: https://lore.kernel.org/linux-media/20230328124416.560889-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/dvb-usb/dw2102.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c index 0ca764282c76..8747960e6146 100644 --- a/drivers/media/usb/dvb-usb/dw2102.c +++ b/drivers/media/usb/dvb-usb/dw2102.c @@ -946,7 +946,7 @@ static int su3000_read_mac_address(struct dvb_usb_device *d, u8 mac[6]) for (i = 0; i < 6; i++) { obuf[1] = 0xf0 + i; if (i2c_transfer(&d->i2c_adap, msg, 2) != 2) - break; + return -1; else mac[i] = ibuf[0]; } -- GitLab From e6ad6233592593079db5c8fa592c298e51bc1356 Mon Sep 17 00:00:00 2001 From: Wei Chen Date: Wed, 15 Mar 2023 13:45:18 +0000 Subject: [PATCH 4912/5631] media: netup_unidvb: fix irq init by register it at the end of probe IRQ handler netup_spi_interrupt() takes spinlock spi->lock. The lock is initialized in netup_spi_init(). However, irq handler is registered before initializing the lock. Spinlock dma->lock and i2c->lock suffer from the same problem. Fix this by registering the irq at the end of probe. Link: https://lore.kernel.org/linux-media/20230315134518.1074497-1-harperchen1110@gmail.com Signed-off-by: Wei Chen Signed-off-by: Mauro Carvalho Chehab --- .../media/pci/netup_unidvb/netup_unidvb_core.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index aaa1d2dedebd..d85bfbb77a25 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -887,12 +887,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, ndev->lmmio0, (u32)pci_resource_len(pci_dev, 0), ndev->lmmio1, (u32)pci_resource_len(pci_dev, 1), pci_dev->irq); - if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, - "netup_unidvb", pci_dev) < 0) { - dev_err(&pci_dev->dev, - "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); - goto irq_request_err; - } + ndev->dma_size = 2 * 188 * NETUP_DMA_BLOCKS_COUNT * NETUP_DMA_PACKETS_COUNT; ndev->dma_virt = dma_alloc_coherent(&pci_dev->dev, @@ -933,6 +928,14 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dev_err(&pci_dev->dev, "netup_unidvb: DMA setup failed\n"); goto dma_setup_err; } + + if (request_irq(pci_dev->irq, netup_unidvb_isr, IRQF_SHARED, + "netup_unidvb", pci_dev) < 0) { + dev_err(&pci_dev->dev, + "%s(): can't get IRQ %d\n", __func__, pci_dev->irq); + goto dma_setup_err; + } + dev_info(&pci_dev->dev, "netup_unidvb: device has been initialized\n"); return 0; @@ -951,8 +954,6 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, dma_free_coherent(&pci_dev->dev, ndev->dma_size, ndev->dma_virt, ndev->dma_phys); dma_alloc_err: - free_irq(pci_dev->irq, pci_dev); -irq_request_err: iounmap(ndev->lmmio1); pci_bar1_error: iounmap(ndev->lmmio0); -- GitLab From a4315e5be7020aac9b24a8151caf4bb85224cd0e Mon Sep 17 00:00:00 2001 From: YongSu Yoo Date: Thu, 18 Aug 2022 13:50:27 +0100 Subject: [PATCH 4913/5631] media: dvb_ca_en50221: fix a size write bug The function of "dvb_ca_en50221_write_data" at source/drivers/media /dvb-core/dvb_ca_en50221.c is used for two cases. The first case is for writing APDU data in the function of "dvb_ca_en50221_io_write" at source/drivers/media/dvb-core/ dvb_ca_en50221.c. The second case is for writing the host link buf size on the Command Register in the function of "dvb_ca_en50221_link_init" at source/drivers/media/dvb-core/dvb_ca_en50221.c. In the second case, there exists a bug like following. In the function of the "dvb_ca_en50221_link_init", after a TV host calculates the host link buf_size, the TV host writes the calculated host link buf_size on the Size Register. Accroding to the en50221 Spec (the page 60 of https://dvb.org/wp-content/uploads/2020/02/En50221.V1.pdf), before this writing operation, the "SW(CMDREG_SW)" flag in the Command Register should be set. We can see this setting operation in the function of the "dvb_ca_en50221_link_init" like below. ... if ((ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_SW)) != 0) return ret; ... But, after that, the real writing operation is implemented using the function of the "dvb_ca_en50221_write_data" in the function of "dvb_ca_en50221_link_init", and the "dvb_ca_en50221_write_data" includes the function of "ca->pub->write_cam_control", and the function of the "ca->pub->write_cam_control" in the function of the "dvb_ca_en50221_wrte_data" does not include "CMDREG_SW" flag like below. ... if ((status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN | CMDREG_HC)) != 0) ... In the above source code, we can see only the "IRQEN | CMDREG_HC", but we cannot see the "CMDREG_SW". The "CMDREG_SW" flag which was set in the function of the "dvb_ca_en50221_link_init" was rollbacked by the follwoing function of the "dvb_ca_en50221_write_data". This is a bug. and this bug causes that the calculated host link buf_size is not properly written in the CI module. Through this patch, we fix this bug. Link: https://lore.kernel.org/linux-media/20220818125027.1131-1-yongsuyoo0215@gmail.com Signed-off-by: YongSu Yoo Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_ca_en50221.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index c2d2792227f8..b6ca29dfb184 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -187,7 +187,7 @@ static void dvb_ca_en50221_thread_wakeup(struct dvb_ca_private *ca); static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, u8 *ebuf, int ecount); static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *ebuf, int ecount); + u8 *ebuf, int ecount, int size_write_flag); /** * findstr - Safely find needle in haystack. @@ -370,7 +370,7 @@ static int dvb_ca_en50221_link_init(struct dvb_ca_private *ca, int slot) ret = dvb_ca_en50221_wait_if_status(ca, slot, STATUSREG_FR, HZ / 10); if (ret) return ret; - ret = dvb_ca_en50221_write_data(ca, slot, buf, 2); + ret = dvb_ca_en50221_write_data(ca, slot, buf, 2, CMDREG_SW); if (ret != 2) return -EIO; ret = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, IRQEN); @@ -778,11 +778,13 @@ static int dvb_ca_en50221_read_data(struct dvb_ca_private *ca, int slot, * @buf: The data in this buffer is treated as a complete link-level packet to * be written. * @bytes_write: Size of ebuf. + * @size_write_flag: A flag on Command Register which says whether the link size + * information will be writen or not. * * return: Number of bytes written, or < 0 on error. */ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, - u8 *buf, int bytes_write) + u8 *buf, int bytes_write, int size_write_flag) { struct dvb_ca_slot *sl = &ca->slot_info[slot]; int status; @@ -817,7 +819,7 @@ static int dvb_ca_en50221_write_data(struct dvb_ca_private *ca, int slot, /* OK, set HC bit */ status = ca->pub->write_cam_control(ca->pub, slot, CTRLIF_COMMAND, - IRQEN | CMDREG_HC); + IRQEN | CMDREG_HC | size_write_flag); if (status) goto exit; @@ -1508,7 +1510,7 @@ static ssize_t dvb_ca_en50221_io_write(struct file *file, mutex_lock(&sl->slot_lock); status = dvb_ca_en50221_write_data(ca, slot, fragbuf, - fraglen + 2); + fraglen + 2, 0); mutex_unlock(&sl->slot_lock); if (status == (fraglen + 2)) { written = 1; -- GitLab From 517a281338322ff8293f988771c98aaa7205e457 Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:25 +0000 Subject: [PATCH 4914/5631] media: ttusb-dec: fix memory leak in ttusb_dec_exit_dvb() Since dvb_frontend_detach() is not called in ttusb_dec_exit_dvb(), which is called when the device is disconnected, dvb_frontend_free() is not finally called. This causes a memory leak just by repeatedly plugging and unplugging the device. Fix this issue by adding dvb_frontend_detach() to ttusb_dec_exit_dvb(). Link: https://lore.kernel.org/linux-media/20221117045925.14297-5-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/usb/ttusb-dec/ttusb_dec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/media/usb/ttusb-dec/ttusb_dec.c b/drivers/media/usb/ttusb-dec/ttusb_dec.c index 38822cedd93a..c4474d4c44e2 100644 --- a/drivers/media/usb/ttusb-dec/ttusb_dec.c +++ b/drivers/media/usb/ttusb-dec/ttusb_dec.c @@ -1544,8 +1544,7 @@ static void ttusb_dec_exit_dvb(struct ttusb_dec *dec) dvb_dmx_release(&dec->demux); if (dec->fe) { dvb_unregister_frontend(dec->fe); - if (dec->fe->ops.release) - dec->fe->ops.release(dec->fe); + dvb_frontend_detach(dec->fe); } dvb_unregister_adapter(&dec->adapter); } -- GitLab From ae11c0efaec32fb45130ee9886689f467232eebc Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 12 Mar 2023 13:13:18 +0000 Subject: [PATCH 4915/5631] media: mn88443x: fix !CONFIG_OF error by drop of_match_ptr from ID table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver will match mostly by DT table (even thought there is regular ID table) so there is little benefit in of_match_ptr (this also allows ACPI matching via PRP0001, even though it might not be relevant here). This also fixes !CONFIG_OF error: drivers/media/dvb-frontends/mn88443x.c:782:34: error: ‘mn88443x_of_match’ defined but not used [-Werror=unused-const-variable=] Link: https://lore.kernel.org/linux-media/20230312131318.351173-28-krzysztof.kozlowski@linaro.org Signed-off-by: Krzysztof Kozlowski Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-frontends/mn88443x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c index 1f1753f2ab1a..0782f8377eb2 100644 --- a/drivers/media/dvb-frontends/mn88443x.c +++ b/drivers/media/dvb-frontends/mn88443x.c @@ -798,7 +798,7 @@ MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id); static struct i2c_driver mn88443x_driver = { .driver = { .name = "mn88443x", - .of_match_table = of_match_ptr(mn88443x_of_match), + .of_match_table = mn88443x_of_match, }, .probe_new = mn88443x_probe, .remove = mn88443x_remove, -- GitLab From 6769a0b7ee0c3b31e1b22c3fadff2bfb642de23f Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:22 +0000 Subject: [PATCH 4916/5631] media: dvb-core: Fix use-after-free on race condition at dvb_frontend If the device node of dvb_frontend is open() and the device is disconnected, many kinds of UAFs may occur when calling close() on the device node. The root cause of this is that wake_up() for dvbdev->wait_queue is implemented in the dvb_frontend_release() function, but wait_event() is not implemented in the dvb_frontend_stop() function. So, implement wait_event() function in dvb_frontend_stop() and add 'remove_mutex' which prevents race condition for 'fe->exit'. [mchehab: fix a couple of checkpatch warnings and some mistakes at the error handling logic] Link: https://lore.kernel.org/linux-media/20221117045925.14297-2-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 53 ++++++++++++++++++++++----- include/media/dvb_frontend.h | 6 ++- 2 files changed, 49 insertions(+), 10 deletions(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index cc0a789f09ae..947b61959b2b 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -809,15 +809,26 @@ static void dvb_frontend_stop(struct dvb_frontend *fe) dev_dbg(fe->dvb->device, "%s:\n", __func__); + mutex_lock(&fe->remove_mutex); + if (fe->exit != DVB_FE_DEVICE_REMOVED) fe->exit = DVB_FE_NORMAL_EXIT; mb(); - if (!fepriv->thread) + if (!fepriv->thread) { + mutex_unlock(&fe->remove_mutex); return; + } kthread_stop(fepriv->thread); + mutex_unlock(&fe->remove_mutex); + + if (fepriv->dvbdev->users < -1) { + wait_event(fepriv->dvbdev->wait_queue, + fepriv->dvbdev->users == -1); + } + sema_init(&fepriv->sem, 1); fepriv->state = FESTATE_IDLE; @@ -2761,9 +2772,13 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) struct dvb_adapter *adapter = fe->dvb; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); - if (fe->exit == DVB_FE_DEVICE_REMOVED) - return -ENODEV; + if (fe->exit == DVB_FE_DEVICE_REMOVED) { + ret = -ENODEV; + goto err_remove_mutex; + } if (adapter->mfe_shared == 2) { mutex_lock(&adapter->mfe_lock); @@ -2771,7 +2786,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_dvbdev && !adapter->mfe_dvbdev->writers) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2794,8 +2810,10 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) while (mferetry-- && (mfedev->users != -1 || mfepriv->thread)) { if (msleep_interruptible(500)) { - if (signal_pending(current)) - return -EINTR; + if (signal_pending(current)) { + ret = -EINTR; + goto err_remove_mutex; + } } } @@ -2807,7 +2825,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (mfedev->users != -1 || mfepriv->thread) { mutex_unlock(&adapter->mfe_lock); - return -EBUSY; + ret = -EBUSY; + goto err_remove_mutex; } adapter->mfe_dvbdev = dvbdev; } @@ -2866,6 +2885,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + + mutex_unlock(&fe->remove_mutex); return ret; err3: @@ -2887,6 +2908,9 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) err0: if (adapter->mfe_shared) mutex_unlock(&adapter->mfe_lock); + +err_remove_mutex: + mutex_unlock(&fe->remove_mutex); return ret; } @@ -2897,6 +2921,8 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) struct dvb_frontend_private *fepriv = fe->frontend_priv; int ret; + mutex_lock(&fe->remove_mutex); + dev_dbg(fe->dvb->device, "%s:\n", __func__); if ((file->f_flags & O_ACCMODE) != O_RDONLY) { @@ -2918,10 +2944,18 @@ static int dvb_frontend_release(struct inode *inode, struct file *file) } mutex_unlock(&fe->dvb->mdev_lock); #endif - if (fe->exit != DVB_FE_NO_EXIT) - wake_up(&dvbdev->wait_queue); if (fe->ops.ts_bus_ctrl) fe->ops.ts_bus_ctrl(fe, 0); + + if (fe->exit != DVB_FE_NO_EXIT) { + mutex_unlock(&fe->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&fe->remove_mutex); + } + + } else { + mutex_unlock(&fe->remove_mutex); } dvb_frontend_put(fe); @@ -3022,6 +3056,7 @@ int dvb_register_frontend(struct dvb_adapter *dvb, fepriv = fe->frontend_priv; kref_init(&fe->refcount); + mutex_init(&fe->remove_mutex); /* * After initialization, there need to be two references: one diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h index e7c44870f20d..367d5381217b 100644 --- a/include/media/dvb_frontend.h +++ b/include/media/dvb_frontend.h @@ -686,7 +686,10 @@ struct dtv_frontend_properties { * @id: Frontend ID * @exit: Used to inform the DVB core that the frontend * thread should exit (usually, means that the hardware - * got disconnected. + * got disconnected). + * @remove_mutex: mutex that avoids a race condition between a callback + * called when the hardware is disconnected and the + * file_operations of dvb_frontend. */ struct dvb_frontend { @@ -704,6 +707,7 @@ struct dvb_frontend { int (*callback)(void *adapter_priv, int component, int cmd, int arg); int id; unsigned int exit; + struct mutex remove_mutex; }; /** -- GitLab From 4172385b0c9ac366dcab78eda48c26814b87ed1a Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Thu, 17 Nov 2022 04:59:23 +0000 Subject: [PATCH 4917/5631] media: dvb-core: Fix use-after-free due on race condition at dvb_net A race condition may occur between the .disconnect function, which is called when the device is disconnected, and the dvb_device_open() function, which is called when the device node is open()ed. This results in several types of UAFs. The root cause of this is that you use the dvb_device_open() function, which does not implement a conditional statement that checks 'dvbnet->exit'. So, add 'remove_mutex` to protect 'dvbnet->exit' and use locked_dvb_net_open() function to check 'dvbnet->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221117045925.14297-3-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_net.c | 38 +++++++++++++++++++++++++++++--- include/media/dvb_net.h | 4 ++++ 2 files changed, 39 insertions(+), 3 deletions(-) diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8a2febf33ce2..8bb8dd34c223 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -1564,15 +1564,43 @@ static long dvb_net_ioctl(struct file *file, return dvb_usercopy(file, cmd, arg, dvb_net_do_ioctl); } +static int locked_dvb_net_open(struct inode *inode, struct file *file) +{ + struct dvb_device *dvbdev = file->private_data; + struct dvb_net *dvbnet = dvbdev->priv; + int ret; + + if (mutex_lock_interruptible(&dvbnet->remove_mutex)) + return -ERESTARTSYS; + + if (dvbnet->exit) { + mutex_unlock(&dvbnet->remove_mutex); + return -ENODEV; + } + + ret = dvb_generic_open(inode, file); + + mutex_unlock(&dvbnet->remove_mutex); + + return ret; +} + static int dvb_net_close(struct inode *inode, struct file *file) { struct dvb_device *dvbdev = file->private_data; struct dvb_net *dvbnet = dvbdev->priv; + mutex_lock(&dvbnet->remove_mutex); + dvb_generic_release(inode, file); - if(dvbdev->users == 1 && dvbnet->exit == 1) + if (dvbdev->users == 1 && dvbnet->exit == 1) { + mutex_unlock(&dvbnet->remove_mutex); wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&dvbnet->remove_mutex); + } + return 0; } @@ -1580,7 +1608,7 @@ static int dvb_net_close(struct inode *inode, struct file *file) static const struct file_operations dvb_net_fops = { .owner = THIS_MODULE, .unlocked_ioctl = dvb_net_ioctl, - .open = dvb_generic_open, + .open = locked_dvb_net_open, .release = dvb_net_close, .llseek = noop_llseek, }; @@ -1599,10 +1627,13 @@ void dvb_net_release (struct dvb_net *dvbnet) { int i; + mutex_lock(&dvbnet->remove_mutex); dvbnet->exit = 1; + mutex_unlock(&dvbnet->remove_mutex); + if (dvbnet->dvbdev->users < 1) wait_event(dvbnet->dvbdev->wait_queue, - dvbnet->dvbdev->users==1); + dvbnet->dvbdev->users == 1); dvb_unregister_device(dvbnet->dvbdev); @@ -1621,6 +1652,7 @@ int dvb_net_init (struct dvb_adapter *adap, struct dvb_net *dvbnet, int i; mutex_init(&dvbnet->ioctl_mutex); + mutex_init(&dvbnet->remove_mutex); dvbnet->demux = dmx; for (i=0; i Date: Thu, 17 Nov 2022 04:59:24 +0000 Subject: [PATCH 4918/5631] media: dvb-core: Fix use-after-free due to race at dvb_register_device() dvb_register_device() dynamically allocates fops with kmemdup() to set the fops->owner. And these fops are registered in 'file->f_ops' using replace_fops() in the dvb_device_open() process, and kfree()d in dvb_free_device(). However, it is not common to use dynamically allocated fops instead of 'static const' fops as an argument of replace_fops(), and UAF may occur. These UAFs can occur on any dvb type using dvb_register_device(), such as dvb_dvr, dvb_demux, dvb_frontend, dvb_net, etc. So, instead of kfree() the fops dynamically allocated in dvb_register_device() in dvb_free_device() called during the .disconnect() process, kfree() it collectively in exit_dvbdev() called when the dvbdev.c module is removed. Link: https://lore.kernel.org/linux-media/20221117045925.14297-4-imv4bel@gmail.com Signed-off-by: Hyunwoo Kim Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvbdev.c | 84 ++++++++++++++++++++++++--------- include/media/dvbdev.h | 15 ++++++ 2 files changed, 78 insertions(+), 21 deletions(-) diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c index e9b3ce09e534..a4b05e366ccc 100644 --- a/drivers/media/dvb-core/dvbdev.c +++ b/drivers/media/dvb-core/dvbdev.c @@ -27,6 +27,7 @@ #include static DEFINE_MUTEX(dvbdev_mutex); +static LIST_HEAD(dvbdevfops_list); static int dvbdev_debug; module_param(dvbdev_debug, int, 0644); @@ -453,14 +454,15 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, enum dvb_device_type type, int demux_sink_pads) { struct dvb_device *dvbdev; - struct file_operations *dvbdevfops; + struct file_operations *dvbdevfops = NULL; + struct dvbdevfops_node *node = NULL, *new_node = NULL; struct device *clsdev; int minor; int id, ret; mutex_lock(&dvbdev_register_lock); - if ((id = dvbdev_get_free_id (adap, type)) < 0){ + if ((id = dvbdev_get_free_id (adap, type)) < 0) { mutex_unlock(&dvbdev_register_lock); *pdvbdev = NULL; pr_err("%s: couldn't find free device id\n", __func__); @@ -468,18 +470,45 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, } *pdvbdev = dvbdev = kzalloc(sizeof(*dvbdev), GFP_KERNEL); - if (!dvbdev){ mutex_unlock(&dvbdev_register_lock); return -ENOMEM; } - dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + /* + * When a device of the same type is probe()d more than once, + * the first allocated fops are used. This prevents memory leaks + * that can occur when the same device is probe()d repeatedly. + */ + list_for_each_entry(node, &dvbdevfops_list, list_head) { + if (node->fops->owner == adap->module && + node->type == type && + node->template == template) { + dvbdevfops = node->fops; + break; + } + } - if (!dvbdevfops){ - kfree (dvbdev); - mutex_unlock(&dvbdev_register_lock); - return -ENOMEM; + if (dvbdevfops == NULL) { + dvbdevfops = kmemdup(template->fops, sizeof(*dvbdevfops), GFP_KERNEL); + if (!dvbdevfops) { + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node = kzalloc(sizeof(struct dvbdevfops_node), GFP_KERNEL); + if (!new_node) { + kfree(dvbdevfops); + kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); + return -ENOMEM; + } + + new_node->fops = dvbdevfops; + new_node->type = type; + new_node->template = template; + list_add_tail (&new_node->list_head, &dvbdevfops_list); } memcpy(dvbdev, template, sizeof(struct dvb_device)); @@ -490,20 +519,20 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, dvbdev->priv = priv; dvbdev->fops = dvbdevfops; init_waitqueue_head (&dvbdev->wait_queue); - dvbdevfops->owner = adap->module; - list_add_tail (&dvbdev->list_head, &adap->device_list); - down_write(&minor_rwsem); #ifdef CONFIG_DVB_DYNAMIC_MINORS for (minor = 0; minor < MAX_DVB_MINORS; minor++) if (dvb_minors[minor] == NULL) break; - if (minor == MAX_DVB_MINORS) { + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); up_write(&minor_rwsem); mutex_unlock(&dvbdev_register_lock); @@ -512,41 +541,47 @@ int dvb_register_device(struct dvb_adapter *adap, struct dvb_device **pdvbdev, #else minor = nums2minor(adap->num, type, id); #endif - dvbdev->minor = minor; dvb_minors[minor] = dvb_device_get(dvbdev); up_write(&minor_rwsem); - ret = dvb_register_media_device(dvbdev, type, minor, demux_sink_pads); if (ret) { pr_err("%s: dvb_register_media_device failed to create the mediagraph\n", __func__); - + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); mutex_unlock(&dvbdev_register_lock); return ret; } - mutex_unlock(&dvbdev_register_lock); - clsdev = device_create(dvb_class, adap->device, MKDEV(DVB_MAJOR, minor), dvbdev, "dvb%d.%s%d", adap->num, dnames[type], id); if (IS_ERR(clsdev)) { pr_err("%s: failed to create device dvb%d.%s%d (%ld)\n", __func__, adap->num, dnames[type], id, PTR_ERR(clsdev)); + if (new_node) { + list_del (&new_node->list_head); + kfree(dvbdevfops); + kfree(new_node); + } dvb_media_device_free(dvbdev); list_del (&dvbdev->list_head); - kfree(dvbdevfops); kfree(dvbdev); + mutex_unlock(&dvbdev_register_lock); return PTR_ERR(clsdev); } + dprintk("DVB: register adapter%d/%s%d @ minor: %i (0x%02x)\n", adap->num, dnames[type], id, minor, minor); + mutex_unlock(&dvbdev_register_lock); return 0; } EXPORT_SYMBOL(dvb_register_device); @@ -575,7 +610,6 @@ static void dvb_free_device(struct kref *ref) { struct dvb_device *dvbdev = container_of(ref, struct dvb_device, ref); - kfree (dvbdev->fops); kfree (dvbdev); } @@ -1081,9 +1115,17 @@ static int __init init_dvbdev(void) static void __exit exit_dvbdev(void) { + struct dvbdevfops_node *node, *next; + class_destroy(dvb_class); cdev_del(&dvb_device_cdev); unregister_chrdev_region(MKDEV(DVB_MAJOR, 0), MAX_DVB_MINORS); + + list_for_each_entry_safe(node, next, &dvbdevfops_list, list_head) { + list_del (&node->list_head); + kfree(node->fops); + kfree(node); + } } subsys_initcall(init_dvbdev); diff --git a/include/media/dvbdev.h b/include/media/dvbdev.h index 29d25c8a6f13..8958e5e2fc5b 100644 --- a/include/media/dvbdev.h +++ b/include/media/dvbdev.h @@ -193,6 +193,21 @@ struct dvb_device { void *priv; }; +/** + * struct dvbdevfops_node - fops nodes registered in dvbdevfops_list + * + * @fops: Dynamically allocated fops for ->owner registration + * @type: type of dvb_device + * @template: dvb_device used for registration + * @list_head: list_head for dvbdevfops_list + */ +struct dvbdevfops_node { + struct file_operations *fops; + enum dvb_device_type type; + const struct dvb_device *template; + struct list_head list_head; +}; + /** * dvb_device_get - Increase dvb_device reference * -- GitLab From b8c75e4a1b325ea0a9433fa8834be97b5836b946 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Fri, 12 May 2023 16:18:00 +0100 Subject: [PATCH 4919/5631] media: dvb-core: Fix kernel WARNING for blocking operation in wait_event*() Using a semaphore in the wait_event*() condition is no good idea. It hits a kernel WARN_ON() at prepare_to_wait_event() like: do not call blocking ops when !TASK_RUNNING; state=1 set at prepare_to_wait_event+0x6d/0x690 For avoiding the potential deadlock, rewrite to an open-coded loop instead. Unlike the loop in wait_event*(), this uses wait_woken() after the condition check, hence the task state stays consistent. CVE-2023-31084 was assigned to this bug. Link: https://lore.kernel.org/r/CA+UBctCu7fXn4q41O_3=id1+OdyQ85tZY1x+TkT-6OVBL6KAUw@mail.gmail.com/ Link: https://lore.kernel.org/linux-media/20230512151800.1874-1-tiwai@suse.de Reported-by: Yu Hao Closes: https://nvd.nist.gov/vuln/detail/CVE-2023-31084 Signed-off-by: Takashi Iwai Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_frontend.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c index 947b61959b2b..bc6950a5740f 100644 --- a/drivers/media/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb-core/dvb_frontend.c @@ -293,14 +293,22 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe, } if (events->eventw == events->eventr) { - int ret; + struct wait_queue_entry wait; + int ret = 0; if (flags & O_NONBLOCK) return -EWOULDBLOCK; - ret = wait_event_interruptible(events->wait_queue, - dvb_frontend_test_event(fepriv, events)); - + init_waitqueue_entry(&wait, current); + add_wait_queue(&events->wait_queue, &wait); + while (!dvb_frontend_test_event(fepriv, events)) { + wait_woken(&wait, TASK_INTERRUPTIBLE, 0); + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + } + remove_wait_queue(&events->wait_queue, &wait); if (ret < 0) return ret; } -- GitLab From 2ac6c4a637132b79863426223242e680cc4f8e27 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Sun, 23 Apr 2023 07:35:13 -0500 Subject: [PATCH 4920/5631] arm64: dts: imx8mn: Fix video clock parents There are a few clocks whose parents are set in mipi_dsi and mxsfb nodes, but these clocks are used by the disp_blk_ctrl power domain which may cause an issue when re-parenting, resuling in a disp_pixel clock having the wrong parent and wrong rate. Fix this by moving the assigned-clock-parents as associate clock assignments to the power-domain node to setup these clocks before they are enabled. Fixes: d825fb6455d5 ("arm64: dts: imx8mn: Add display pipeline components") Signed-off-by: Adam Ford Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn.dtsi | 28 ++++++++++++----------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index bd84db550053..8be8f090e8b8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -1069,13 +1069,6 @@ <&clk IMX8MN_CLK_DISP_APB_ROOT>, <&clk IMX8MN_CLK_DISP_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MN_CLK_DISP_PIXEL_ROOT>, - <&clk IMX8MN_CLK_DISP_AXI>, - <&clk IMX8MN_CLK_DISP_APB>; - assigned-clock-parents = <&clk IMX8MN_CLK_DISP_PIXEL>, - <&clk IMX8MN_SYS_PLL2_1000M>, - <&clk IMX8MN_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = ; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_LCDIF>; status = "disabled"; @@ -1093,12 +1086,6 @@ clocks = <&clk IMX8MN_CLK_DSI_CORE>, <&clk IMX8MN_CLK_DSI_PHY_REF>; clock-names = "bus_clk", "sclk_mipi"; - assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, - <&clk IMX8MN_CLK_DSI_PHY_REF>; - assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, - <&clk IMX8MN_CLK_24M>; - assigned-clock-rates = <266000000>, <24000000>; - samsung,pll-clock-frequency = <24000000>; interrupts = ; power-domains = <&disp_blk_ctrl IMX8MN_DISPBLK_PD_MIPI_DSI>; status = "disabled"; @@ -1142,6 +1129,21 @@ "lcdif-axi", "lcdif-apb", "lcdif-pix", "dsi-pclk", "dsi-ref", "csi-aclk", "csi-pclk"; + assigned-clocks = <&clk IMX8MN_CLK_DSI_CORE>, + <&clk IMX8MN_CLK_DSI_PHY_REF>, + <&clk IMX8MN_CLK_DISP_PIXEL>, + <&clk IMX8MN_CLK_DISP_AXI>, + <&clk IMX8MN_CLK_DISP_APB>; + assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_266M>, + <&clk IMX8MN_CLK_24M>, + <&clk IMX8MN_VIDEO_PLL1_OUT>, + <&clk IMX8MN_SYS_PLL2_1000M>, + <&clk IMX8MN_SYS_PLL1_800M>; + assigned-clock-rates = <266000000>, + <24000000>, + <594000000>, + <500000000>, + <200000000>; #power-domain-cells = <1>; }; -- GitLab From f161cea5a20f3aeeb637a88ad1705fc2720b4d58 Mon Sep 17 00:00:00 2001 From: Hugo Villeneuve Date: Mon, 1 May 2023 13:05:32 -0400 Subject: [PATCH 4921/5631] arm64: dts: imx8mn-var-som: fix PHY detection bug by adding deassert delay While testing the ethernet interface on a Variscite symphony carrier board using an imx8mn SOM with an onboard ADIN1300 PHY (EC hardware configuration), the ethernet PHY is not detected. The ADIN1300 datasheet indicate that the "Management interface active (t4)" state is reached at most 5ms after the reset signal is deasserted. The device tree in Variscite custom git repository uses the following property: phy-reset-post-delay = <20>; Add a new MDIO property 'reset-deassert-us' of 20ms to have the same delay inside the ethphy node. Adding this property fixes the problem with the PHY detection. Note that this SOM can also have an Atheros AR8033 PHY. In this case, a 1ms deassert delay is sufficient. Add a comment to that effect. Fixes: ade0176dd8a0 ("arm64: dts: imx8mn-var-som: Add Variscite VAR-SOM-MX8MN System on Module") Signed-off-by: Hugo Villeneuve Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi index 67072e6c77d5..cbd9d124c80d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-var-som.dtsi @@ -98,11 +98,17 @@ #address-cells = <1>; #size-cells = <0>; - ethphy: ethernet-phy@4 { + ethphy: ethernet-phy@4 { /* AR8033 or ADIN1300 */ compatible = "ethernet-phy-ieee802.3-c22"; reg = <4>; reset-gpios = <&gpio1 9 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; + /* + * Deassert delay: + * ADIN1300 requires 5ms. + * AR8033 requires 1ms. + */ + reset-deassert-us = <20000>; }; }; }; -- GitLab From 892943d7729bbfb2edeed9e323eba9a5cec21c49 Mon Sep 17 00:00:00 2001 From: Christoph Niedermaier Date: Tue, 2 May 2023 13:14:24 +0200 Subject: [PATCH 4922/5631] ARM: dts: imx6ull-dhcor: Set and limit the mode for PMIC buck 1, 2 and 3 According to Renesas Electronics (formerly Dialog Semiconductor), the standard AUTO mode of the PMIC DA9061 can lead to stability problems depending on the hardware revision. It is recommended to set a defined mode such as PFM or PWM permanently. So set and limit the mode for buck 1, 2 and 3 to a fixed one. Fixes: 611b6c891e40 ("ARM: dts: imx6ull-dhcom: Add DH electronics DHCOM i.MX6ULL SoM and PDK2 board") Signed-off-by: Christoph Niedermaier Reviewed-by: Marek Vasut Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6ull-dhcor-som.dtsi | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi index 5882c7565f64..32a6022625d9 100644 --- a/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi +++ b/arch/arm/boot/dts/imx6ull-dhcor-som.dtsi @@ -8,6 +8,7 @@ #include #include #include +#include #include "imx6ull.dtsi" / { @@ -84,16 +85,20 @@ regulators { vdd_soc_in_1v4: buck1 { + regulator-allowed-modes = ; /* PFM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = ; regulator-max-microvolt = <1400000>; regulator-min-microvolt = <1400000>; regulator-name = "vdd_soc_in_1v4"; }; vcc_3v3: buck2 { + regulator-allowed-modes = ; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = ; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; regulator-name = "vcc_3v3"; @@ -106,8 +111,10 @@ * the voltage is set to 1.5V. */ vcc_ddr_1v35: buck3 { + regulator-allowed-modes = ; /* PWM */ regulator-always-on; regulator-boot-on; + regulator-initial-mode = ; regulator-max-microvolt = <1500000>; regulator-min-microvolt = <1500000>; regulator-name = "vcc_ddr_1v35"; -- GitLab From 91aa4b3782448a7a13baa8cbcdfd5fd19defcbd9 Mon Sep 17 00:00:00 2001 From: Alexander Stein Date: Wed, 3 May 2023 13:31:10 +0200 Subject: [PATCH 4923/5631] ARM: dts: imx6qdl-mba6: Add missing pvcie-supply regulator This worked before by coincidence, as the regulator was probed and enabled before PCI RC probe. But probe order changed since commit 259b93b21a9f ("regulator: Set PROBE_PREFER_ASYNCHRONOUS for drivers that existed in 4.14") and PCIe supply is enabled after RC. Fix this by adding the regulator to RC node. The PCIe vaux regulator still needs to be enabled unconditionally for Mini-PCIe USB-only devices. Fixes: ef3846247b41 ("ARM: dts: imx6qdl: add TQ-Systems MBa6x device trees") Signed-off-by: Alexander Stein Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl-mba6.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/imx6qdl-mba6.dtsi b/arch/arm/boot/dts/imx6qdl-mba6.dtsi index 78555a618851..7b7e6c2ad190 100644 --- a/arch/arm/boot/dts/imx6qdl-mba6.dtsi +++ b/arch/arm/boot/dts/imx6qdl-mba6.dtsi @@ -209,6 +209,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; reset-gpio = <&gpio6 7 GPIO_ACTIVE_LOW>; + vpcie-supply = <®_pcie>; status = "okay"; }; -- GitLab From 280a8ab81733da8bc442253c700a52c4c0886ffd Mon Sep 17 00:00:00 2001 From: Hyunwoo Kim Date: Mon, 21 Nov 2022 06:33:08 +0000 Subject: [PATCH 4924/5631] media: dvb-core: Fix use-after-free due to race condition at dvb_ca_en50221 If the device node of dvb_ca_en50221 is open() and the device is disconnected, a UAF may occur when calling close() on the device node. The root cause is that wake_up() and wait_event() for dvbdev->wait_queue are not implemented. So implement wait_event() function in dvb_ca_en50221_release() and add 'remove_mutex' which prevents race condition for 'ca->exit'. [mchehab: fix a checkpatch warning] Link: https://lore.kernel.org/linux-media/20221121063308.GA33821@ubuntu Signed-off-by: Hyunwoo Kim Signed-off-by: Mauro Carvalho Chehab --- drivers/media/dvb-core/dvb_ca_en50221.c | 37 ++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c index b6ca29dfb184..baf64540dc00 100644 --- a/drivers/media/dvb-core/dvb_ca_en50221.c +++ b/drivers/media/dvb-core/dvb_ca_en50221.c @@ -151,6 +151,12 @@ struct dvb_ca_private { /* mutex serializing ioctls */ struct mutex ioctl_mutex; + + /* A mutex used when a device is disconnected */ + struct mutex remove_mutex; + + /* Whether the device is disconnected */ + int exit; }; static void dvb_ca_private_free(struct dvb_ca_private *ca) @@ -1711,12 +1717,22 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dprintk("%s\n", __func__); - if (!try_module_get(ca->pub->owner)) + mutex_lock(&ca->remove_mutex); + + if (ca->exit) { + mutex_unlock(&ca->remove_mutex); + return -ENODEV; + } + + if (!try_module_get(ca->pub->owner)) { + mutex_unlock(&ca->remove_mutex); return -EIO; + } err = dvb_generic_open(inode, file); if (err < 0) { module_put(ca->pub->owner); + mutex_unlock(&ca->remove_mutex); return err; } @@ -1741,6 +1757,7 @@ static int dvb_ca_en50221_io_open(struct inode *inode, struct file *file) dvb_ca_private_get(ca); + mutex_unlock(&ca->remove_mutex); return 0; } @@ -1760,6 +1777,8 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + /* mark the CA device as closed */ ca->open = 0; dvb_ca_en50221_thread_update_delay(ca); @@ -1770,6 +1789,13 @@ static int dvb_ca_en50221_io_release(struct inode *inode, struct file *file) dvb_ca_private_put(ca); + if (dvbdev->users == 1 && ca->exit == 1) { + mutex_unlock(&ca->remove_mutex); + wake_up(&dvbdev->wait_queue); + } else { + mutex_unlock(&ca->remove_mutex); + } + return err; } @@ -1893,6 +1919,7 @@ int dvb_ca_en50221_init(struct dvb_adapter *dvb_adapter, } mutex_init(&ca->ioctl_mutex); + mutex_init(&ca->remove_mutex); if (signal_pending(current)) { ret = -EINTR; @@ -1935,6 +1962,14 @@ void dvb_ca_en50221_release(struct dvb_ca_en50221 *pubca) dprintk("%s\n", __func__); + mutex_lock(&ca->remove_mutex); + ca->exit = 1; + mutex_unlock(&ca->remove_mutex); + + if (ca->dvbdev->users < 1) + wait_event(ca->dvbdev->wait_queue, + ca->dvbdev->users == 1); + /* shutdown the thread if there was one */ kthread_stop(ca->thread); -- GitLab From f1fcbaa18b28dec10281551dfe6ed3a3ed80e3d6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 14 May 2023 12:51:40 -0700 Subject: [PATCH 4925/5631] Linux 6.4-rc2 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9d765ebcccf1..f836936fb4d8 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* -- GitLab From eb8d3a2c809abd73ab0a060fe971d6b9019aa3c1 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 9 May 2023 09:41:49 +1000 Subject: [PATCH 4926/5631] SUNRPC: double free xprt_ctxt while still in use When an RPC request is deferred, the rq_xprt_ctxt pointer is moved out of the svc_rqst into the svc_deferred_req. When the deferred request is revisited, the pointer is copied into the new svc_rqst - and also remains in the svc_deferred_req. In the (rare?) case that the request is deferred a second time, the old svc_deferred_req is reused - it still has all the correct content. However in that case the rq_xprt_ctxt pointer is NOT cleared so that when xpo_release_xprt is called, the ctxt is freed (UDP) or possible added to a free list (RDMA). When the deferred request is revisited for a second time, it will reference this ctxt which may be invalid, and the free the object a second time which is likely to oops. So change svc_defer() to *always* clear rq_xprt_ctxt, and assert that the value is now stored in the svc_deferred_req. Fixes: 773f91b2cf3f ("SUNRPC: Fix NFSD's request deferral on RDMA transports") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- net/sunrpc/svc_xprt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 84e5d7d31481..5fd94f6bdc75 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1223,13 +1223,14 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; dr->xprt_ctxt = rqstp->rq_xprt_ctxt; - rqstp->rq_xprt_ctxt = NULL; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } + WARN_ON_ONCE(rqstp->rq_xprt_ctxt != dr->xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; -- GitLab From 948f072ada23e0a504c5e4d7d71d4c83bd0785ec Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 9 May 2023 09:42:47 +1000 Subject: [PATCH 4927/5631] SUNRPC: always free ctxt when freeing deferred request Since the ->xprt_ctxt pointer was added to svc_deferred_req, it has not been sufficient to use kfree() to free a deferred request. We may need to free the ctxt as well. As freeing the ctxt is all that ->xpo_release_rqst() does, we repurpose it to explicit do that even when the ctxt is not stored in an rqst. So we now have ->xpo_release_ctxt() which is given an xprt and a ctxt, which may have been taken either from an rqst or from a dreq. The caller is now responsible for clearing that pointer after the call to ->xpo_release_ctxt. We also clear dr->xprt_ctxt when the ctxt is moved into a new rqst when revisiting a deferred request. This ensures there is only one pointer to the ctxt, so the risk of double freeing in future is reduced. The new code in svc_xprt_release which releases both the ctxt and any rq_deferred depends on this. Fixes: 773f91b2cf3f ("SUNRPC: Fix NFSD's request deferral on RDMA transports") Signed-off-by: NeilBrown Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc_rdma.h | 2 +- include/linux/sunrpc/svc_xprt.h | 2 +- net/sunrpc/svc_xprt.c | 23 +++++++++++++----- net/sunrpc/svcsock.c | 30 +++++++++++++----------- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 11 ++++----- net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +- 6 files changed, 41 insertions(+), 29 deletions(-) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24aa159d29a7..fbc4bd423b35 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -176,7 +176,7 @@ extern struct svc_rdma_recv_ctxt * extern void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt); extern void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma); -extern void svc_rdma_release_rqst(struct svc_rqst *rqstp); +extern void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *ctxt); extern int svc_rdma_recvfrom(struct svc_rqst *); /* svc_rdma_rw.c */ diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 867479204840..a6b12631db21 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -23,7 +23,7 @@ struct svc_xprt_ops { int (*xpo_sendto)(struct svc_rqst *); int (*xpo_result_payload)(struct svc_rqst *, unsigned int, unsigned int); - void (*xpo_release_rqst)(struct svc_rqst *); + void (*xpo_release_ctxt)(struct svc_xprt *xprt, void *ctxt); void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 5fd94f6bdc75..13a14897bc17 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -532,13 +532,23 @@ void svc_reserve(struct svc_rqst *rqstp, int space) } EXPORT_SYMBOL_GPL(svc_reserve); +static void free_deferred(struct svc_xprt *xprt, struct svc_deferred_req *dr) +{ + if (!dr) + return; + + xprt->xpt_ops->xpo_release_ctxt(xprt, dr->xprt_ctxt); + kfree(dr); +} + static void svc_xprt_release(struct svc_rqst *rqstp) { struct svc_xprt *xprt = rqstp->rq_xprt; - xprt->xpt_ops->xpo_release_rqst(rqstp); + xprt->xpt_ops->xpo_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; - kfree(rqstp->rq_deferred); + free_deferred(xprt, rqstp->rq_deferred); rqstp->rq_deferred = NULL; svc_rqst_release_pages(rqstp); @@ -1054,7 +1064,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) spin_unlock_bh(&serv->sv_lock); while ((dr = svc_deferred_dequeue(xprt)) != NULL) - kfree(dr); + free_deferred(xprt, dr); call_xpt_users(xprt); svc_xprt_put(xprt); @@ -1176,8 +1186,8 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); trace_svc_defer_drop(dr); + free_deferred(xprt, dr); svc_xprt_put(xprt); - kfree(dr); return; } dr->xprt = NULL; @@ -1222,14 +1232,13 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) dr->addrlen = rqstp->rq_addrlen; dr->daddr = rqstp->rq_daddr; dr->argslen = rqstp->rq_arg.len >> 2; - dr->xprt_ctxt = rqstp->rq_xprt_ctxt; /* back up head to the start of the buffer and copy */ skip = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len; memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } - WARN_ON_ONCE(rqstp->rq_xprt_ctxt != dr->xprt_ctxt); + dr->xprt_ctxt = rqstp->rq_xprt_ctxt; rqstp->rq_xprt_ctxt = NULL; trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); @@ -1263,6 +1272,8 @@ static noinline int svc_deferred_recv(struct svc_rqst *rqstp) rqstp->rq_daddr = dr->daddr; rqstp->rq_respages = rqstp->rq_pages; rqstp->rq_xprt_ctxt = dr->xprt_ctxt; + + dr->xprt_ctxt = NULL; svc_xprt_received(rqstp->rq_xprt); return dr->argslen << 2; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 9989194446a5..63fe7a338992 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -121,27 +121,27 @@ static void svc_reclassify_socket(struct socket *sock) #endif /** - * svc_tcp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_tcp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_tcp_release_rqst(struct svc_rqst *rqstp) +static void svc_tcp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { } /** - * svc_udp_release_rqst - Release transport-related resources - * @rqstp: request structure with resources to be released + * svc_udp_release_ctxt - Release transport-related resources + * @xprt: the transport which owned the context + * @ctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * */ -static void svc_udp_release_rqst(struct svc_rqst *rqstp) +static void svc_udp_release_ctxt(struct svc_xprt *xprt, void *ctxt) { - struct sk_buff *skb = rqstp->rq_xprt_ctxt; + struct sk_buff *skb = ctxt; - if (skb) { - rqstp->rq_xprt_ctxt = NULL; + if (skb) consume_skb(skb); - } } union svc_pktinfo_u { @@ -696,7 +696,8 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_udp_release_rqst(rqstp); + svc_udp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; svc_set_cmsg_data(rqstp, cmh); @@ -768,7 +769,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_udp_release_rqst, + .xpo_release_ctxt = svc_udp_release_ctxt, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -1301,7 +1302,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int sent; int err; - svc_tcp_release_rqst(rqstp); + svc_tcp_release_ctxt(xprt, rqstp->rq_xprt_ctxt); + rqstp->rq_xprt_ctxt = NULL; atomic_inc(&svsk->sk_sendqlen); mutex_lock(&xprt->xpt_mutex); @@ -1346,7 +1348,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_result_payload = svc_sock_result_payload, - .xpo_release_rqst = svc_tcp_release_rqst, + .xpo_release_ctxt = svc_tcp_release_ctxt, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 1c658fa43063..a22fe7587fa6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -239,21 +239,20 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, } /** - * svc_rdma_release_rqst - Release transport-specific per-rqst resources - * @rqstp: svc_rqst being released + * svc_rdma_release_ctxt - Release transport-specific per-rqst resources + * @xprt: the transport which owned the context + * @vctxt: the context from rqstp->rq_xprt_ctxt or dr->xprt_ctxt * * Ensure that the recv_ctxt is released whether or not a Reply * was sent. For example, the client could close the connection, * or svc_process could drop an RPC, before the Reply is sent. */ -void svc_rdma_release_rqst(struct svc_rqst *rqstp) +void svc_rdma_release_ctxt(struct svc_xprt *xprt, void *vctxt) { - struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; - struct svc_xprt *xprt = rqstp->rq_xprt; + struct svc_rdma_recv_ctxt *ctxt = vctxt; struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); - rqstp->rq_xprt_ctxt = NULL; if (ctxt) svc_rdma_recv_ctxt_put(rdma, ctxt); } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 416b298f74dd..ca04f7a6a085 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, .xpo_result_payload = svc_rdma_result_payload, - .xpo_release_rqst = svc_rdma_release_rqst, + .xpo_release_ctxt = svc_rdma_release_ctxt, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, .xpo_has_wspace = svc_rdma_has_wspace, -- GitLab From 07a27305938559fb35f7a46fb90a5e37728bdee6 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sun, 14 May 2023 15:51:48 -0400 Subject: [PATCH 4928/5631] SUNRPC: Fix trace_svc_register() call site The trace event recorded incorrect values for the registered family, protocol, and port because the arguments are in the wrong order. Fixes: b4af59328c25 ("SUNRPC: Trace server-side rpcbind registration events") Signed-off-by: Chuck Lever --- net/sunrpc/svc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 43e32129a583..79967b6925bd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1052,7 +1052,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } - trace_svc_register(progname, version, protocol, port, family, error); + trace_svc_register(progname, version, family, protocol, port, error); return error; } -- GitLab From 5f5486b620cd43b16a1787ef92b9bc21bd72ef2e Mon Sep 17 00:00:00 2001 From: Jeremy Sowden Date: Wed, 26 Apr 2023 22:50:32 +0100 Subject: [PATCH 4929/5631] selftests/bpf: Fix pkg-config call building sign-file When building sign-file, the call to get the CFLAGS for libcrypto is missing white-space between `pkg-config` and `--cflags`: $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) Removing the redirection of stderr, we see: $ make -C tools/testing/selftests/bpf sign-file make: Entering directory '[...]/tools/testing/selftests/bpf' make: pkg-config--cflags: No such file or directory SIGN-FILE sign-file make: Leaving directory '[...]/tools/testing/selftests/bpf' Add the missing space. Fixes: fc97590668ae ("selftests/bpf: Add test for bpf_verify_pkcs7_signature() kfunc") Signed-off-by: Jeremy Sowden Signed-off-by: Daniel Borkmann Reviewed-by: Roberto Sassu Link: https://lore.kernel.org/bpf/20230426215032.415792-1-jeremy@azazel.net Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c49e5403ad0e..28d2c77262be 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -197,7 +197,7 @@ $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_r $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $(call msg,SIGN-FILE,,$@) - $(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \ + $(Q)$(CC) $(shell $(HOSTPKG_CONFIG) --cflags libcrypto 2> /dev/null) \ $< -o $@ \ $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) -- GitLab From a7844528722619d2f97740ae5ec747afff18c4be Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Fri, 12 May 2023 13:52:04 +0200 Subject: [PATCH 4930/5631] dt-bindings: ata: ahci-ceva: Cover all 4 iommus entries Current only one entry is enabled but IP itself is using 4 different IDs which are already listed in zynqmp.dtsi. sata: ahci@fd0c0000 { compatible = "ceva,ahci-1v84"; ... iommus = <&smmu 0x4c0>, <&smmu 0x4c1>, <&smmu 0x4c2>, <&smmu 0x4c3>; }; Fixes: 8ac47837f0e0 ("arm64: dts: zynqmp: Add missing iommu IDs") Cc: stable@vger.kernel.org # v5.12+ Signed-off-by: Michal Simek Acked-by: Krzysztof Kozlowski Signed-off-by: Damien Le Moal --- Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml index 9b31f864e071..71364c6081ff 100644 --- a/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml +++ b/Documentation/devicetree/bindings/ata/ceva,ahci-1v84.yaml @@ -32,7 +32,7 @@ properties: maxItems: 1 iommus: - maxItems: 1 + maxItems: 4 power-domains: maxItems: 1 -- GitLab From bc97139ff13598fa5becf6b582ef99ab428c03ef Mon Sep 17 00:00:00 2001 From: ChiaEn Wu Date: Fri, 12 May 2023 13:44:23 +0800 Subject: [PATCH 4931/5631] power: supply: rt9467: Fix passing zero to 'dev_err_probe' Fix passing zero to 'dev_err_probe()' in 'rt9467_request_interrupt()' Fixes: 6f7f70e3a8dd ("power: supply: rt9467: Add Richtek RT9467 charger driver") Reported-by: kernel test robot Reported-by: Dan Carpenter Link: https://lore.kernel.org/r/202305111228.bHLWU6bq-lkp@intel.com/ Signed-off-by: ChiaEn Wu Signed-off-by: Sebastian Reichel --- drivers/power/supply/rt9467-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/rt9467-charger.c b/drivers/power/supply/rt9467-charger.c index 73f744a3155d..ea33693b6977 100644 --- a/drivers/power/supply/rt9467-charger.c +++ b/drivers/power/supply/rt9467-charger.c @@ -1023,7 +1023,7 @@ static int rt9467_request_interrupt(struct rt9467_chg_data *data) for (i = 0; i < num_chg_irqs; i++) { virq = regmap_irq_get_virq(data->irq_chip_data, chg_irqs[i].hwirq); if (virq <= 0) - return dev_err_probe(dev, virq, "Failed to get (%s) irq\n", + return dev_err_probe(dev, -EINVAL, "Failed to get (%s) irq\n", chg_irqs[i].name); ret = devm_request_threaded_irq(dev, virq, NULL, chg_irqs[i].handler, -- GitLab From 7430dea49410de3d154fb87f931d079a0a643b1a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:06 -0500 Subject: [PATCH 4932/5631] ASoC: SOF: Intel: hda-mlink: fix sublink refcounting In hindsight it was a very bad idea to use the same refcount for Extended and 'legacy' HDaudio multi-links. The existing solution only powers-up the first sublink, which causes SoundWire and SSP tests to fail when more than one DAI is used concurrently. Solving this problem requires per-sublink refcounting, as suggested in this patch. The existing refcounting remains for 'legacy' HdAudio links, mainly to avoid changing the obscure programming sequence in snd_hdac_ext_bus_link_put(). Signed-off-by: Pierre-Louis Bossart eml_lock); - if (++hlink->ref_count > 1) - goto skip_init; + if (!alt) { + if (++hlink->ref_count > 1) + goto skip_init; + } else { + if (++h2link->sublink_ref_count[sublink] > 1) + goto skip_init; + } ret = hdaml_link_init(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); @@ -684,9 +694,13 @@ static int hdac_bus_eml_power_down_base(struct hdac_bus *bus, bool alt, int elid if (eml_lock) mutex_lock(&h2link->eml_lock); - if (--hlink->ref_count > 0) - goto skip_shutdown; - + if (!alt) { + if (--hlink->ref_count > 0) + goto skip_shutdown; + } else { + if (--h2link->sublink_ref_count[sublink] > 0) + goto skip_shutdown; + } ret = hdaml_link_shutdown(hlink->ml_addr + AZX_REG_ML_LCTL, sublink); skip_shutdown: -- GitLab From dcb88fc47d0e79fd54a19a63a4c8a7594ba0838e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:07 -0500 Subject: [PATCH 4933/5631] ASoC: SOF: Intel: hda-mlink: add helper to get SoundWire hlink Same functionality as for DMIC/SSP with different ID. Signed-off-by: Pierre-Louis Bossart hext_link; +} +EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_get_hlink, SND_SOC_SOF_HDA_MLINK); + int hdac_bus_eml_enable_offload(struct hdac_bus *bus, bool alt, int elid, bool enable) { struct hdac_ext2_link *h2link; -- GitLab From af8c32b1a3d55f9b42294aee7e7c7eca85ee3bd2 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:08 -0500 Subject: [PATCH 4934/5631] ASoC: SOF: Intel: hda-mlink: fix base_ptr computation The base_ptr value needs to be derived from the remap_addr pointer, not the ml_addr. This base_ptr was used only in debug logs that were so far not contributed upstream so the issue was not detected. It needs to be fixed for SoundWire support on LunarLake. Fixes: 17c9b6ec35c0 ("ASoC: SOF: Intel: hda-mlink: add structures to parse ALT links") Signed-off-by: Pierre-Louis Bossart hext_link; u32 base_offset; @@ -136,7 +136,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); base_offset = FIELD_GET(AZX_REG_ML_LEPTR_PTR, h2link->leptr); - h2link->base_ptr = hlink->ml_addr + base_offset; + h2link->base_ptr = remap_addr + base_offset; switch (h2link->elid) { case AZX_REG_ML_LEPTR_ID_SDW: @@ -369,7 +369,7 @@ static int hda_ml_alloc_h2link(struct hdac_bus *bus, int index) hlink->bus = bus; hlink->ml_addr = bus->mlcap + AZX_ML_BASE + (AZX_ML_INTERVAL * index); - ret = hdaml_lnk_enum(bus->dev, h2link, hlink->ml_addr, index); + ret = hdaml_lnk_enum(bus->dev, h2link, bus->remap_addr, hlink->ml_addr, index); if (ret < 0) { kfree(h2link); return ret; -- GitLab From 7dfd1ccdb71e5b819c2898b59c58b89f26038292 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:09 -0500 Subject: [PATCH 4935/5631] ASoC: SOF: Intel: hda-mlink: use 'ml_addr' parameter consistently We mix the use of hlink->ml_addr and the 'ml_addr' parameter. It's the same thing, let's align on using the parameter. Signed-off-by: Pierre-Louis Bossart slcount); /* find IP ID and offsets */ - h2link->leptr = readl(hlink->ml_addr + AZX_REG_ML_LEPTR); + h2link->leptr = readl(ml_addr + AZX_REG_ML_LEPTR); h2link->elid = FIELD_GET(AZX_REG_ML_LEPTR_ID, h2link->leptr); -- GitLab From 9643456ec3c48adfe535c56f659ab705365f4572 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:10 -0500 Subject: [PATCH 4936/5631] ASoC: SOF: Intel: hda-mlink: initialize instance_offset member We defined the values but never initialized it for SoundWire/SSP, fix this miss. A Fixes: tag is not provided as instance_offset was not used so far, so nothing was really broken. This patch is only required for the SoundWire support in the following patch. Signed-off-by: Pierre-Louis Bossart elid) { case AZX_REG_ML_LEPTR_ID_SDW: + h2link->instance_offset = AZX_REG_SDW_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_SDW_SHIM_OFFSET; h2link->ip_offset = AZX_REG_SDW_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_SDW_VS_SHIM_OFFSET; @@ -154,6 +155,7 @@ static int hdaml_lnk_enum(struct device *dev, struct hdac_ext2_link *h2link, link_idx, base_offset); break; case AZX_REG_ML_LEPTR_ID_INTEL_SSP: + h2link->instance_offset = AZX_REG_INTEL_SSP_INSTANCE_OFFSET; h2link->shim_offset = AZX_REG_INTEL_SSP_SHIM_OFFSET; h2link->ip_offset = AZX_REG_INTEL_SSP_IP_OFFSET; h2link->shim_vs_offset = AZX_REG_INTEL_SSP_VS_SHIM_OFFSET; -- GitLab From ccc2f0c1b6b613cd0014c3dcd465a4b57856b0fe Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 12:46:11 -0500 Subject: [PATCH 4937/5631] ASoC: SOF: Intel: hda-mlink: add helper to program SoundWire PCMSyCM registers These registers enable the HDaudio DMA hardware to split/merge data from different PDIs, possibly on different links. This capability exists for all types of HDaudio extended links, but for now is only required for SoundWire. In the SSP/DMIC case, the IP is programmed by the DSP firmware. Signed-off-by: Pierre-Louis Bossart base_ptr + h2link->shim_offset + + h2link->instance_offset * sublink + + AZX_REG_SDW_SHIM_PCMSyCM(y); + + mutex_lock(&h2link->eml_lock); + + hdaml_shim_map_stream_ch(pcmsycm, 0, hweight32(channel_mask), + stream_id, dir); + + mutex_unlock(&h2link->eml_lock); + + val = readw(pcmsycm); + + dev_dbg(bus->dev, "channel_mask %#x stream_id %d dir %d pcmscm %#x\n", + channel_mask, stream_id, dir, val); + + return 0; +} EXPORT_SYMBOL_NS(hdac_bus_eml_sdw_map_stream_ch, SND_SOC_SOF_HDA_MLINK); + void hda_bus_ml_put_all(struct hdac_bus *bus) { struct hdac_ext_link *hlink; -- GitLab From 3de975862f985f1c9e225a0d13aa3d501373f7c3 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:13 +0300 Subject: [PATCH 4938/5631] ASoC: SOF: debug: conditionally bump runtime_pm counter on exceptions When a firmware IPC error happens during a pm_runtime suspend, we ignore the error and suspend anyways. However, the code unconditionally increases the runtime_pm counter. This results in a confusing configuration where the code will suspend, resume but never suspend again due to the use of pm_runtime_get_noresume(). The intent of the counter increase was to prevent entry in D3, but if that transition to D3 is already started it cannot be stopped. In addition, there's no point in that case in trying to prevent anything, the firmware error is handled and the next resume will re-initialize the firmware completely. This patch changes the logic to prevent suspend when the device is pm_runtime active and has a use_count > 0. Signed-off-by: Pierre-Louis Bossart ipc_dump_printed) dev_info(sdev->dev, - "preventing DSP entering D3 state to preserve context\n"); - pm_runtime_get_noresume(sdev->dev); + "Attempting to prevent DSP from entering D3 state to preserve context\n"); + pm_runtime_get_if_in_use(sdev->dev); } /* dump vital information to the logs */ -- GitLab From da0fe8fd515a471d373acc3682bfb5522cca4d55 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:14 +0300 Subject: [PATCH 4939/5631] ASoC: SOF: pcm: fix pm_runtime imbalance in error handling When an error occurs, we need to make sure the device can pm_runtime suspend instead of keeping it active. Signed-off-by: Pierre-Louis Bossart tplg_filename_prefix, plat_data->tplg_filename); - if (!tplg_filename) - return -ENOMEM; + if (!tplg_filename) { + ret = -ENOMEM; + goto pm_error; + } ret = snd_sof_load_topology(component, tplg_filename); - if (ret < 0) { + if (ret < 0) dev_err(component->dev, "error: failed to load DSP topology %d\n", ret); - return ret; - } +pm_error: pm_runtime_mark_last_busy(component->dev); pm_runtime_put_autosuspend(component->dev); -- GitLab From bc424273c74c1565c459c8f2a6ed95caee368d0a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 12 May 2023 13:33:15 +0300 Subject: [PATCH 4940/5631] ASoC: SOF: sof-client-probes: fix pm_runtime imbalance in error handling When an error occurs, we need to make sure the device can pm_runtime suspend instead of keeping it active. Signed-off-by: Pierre-Louis Bossart points_info(cdev, &desc, &num_desc); if (ret < 0) - goto exit; - - pm_runtime_mark_last_busy(dev); - err = pm_runtime_put_autosuspend(dev); - if (err < 0) - dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + goto pm_error; for (i = 0; i < num_desc; i++) { offset = strlen(buf); @@ -241,6 +236,13 @@ static ssize_t sof_probes_dfs_points_read(struct file *file, char __user *to, ret = simple_read_from_buffer(to, count, ppos, buf, strlen(buf)); kfree(desc); + +pm_error: + pm_runtime_mark_last_busy(dev); + err = pm_runtime_put_autosuspend(dev); + if (err < 0) + dev_err_ratelimited(dev, "debugfs read failed to idle %d\n", err); + exit: kfree(buf); return ret; -- GitLab From 4708449eafe60742334606168926985798c9c9b8 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 12 May 2023 14:03:17 +0300 Subject: [PATCH 4941/5631] ASoC: SOF: ipc3-topology: Make sure that only one cmd is sent in dai_config The commands in sof_ipc_dai_config.flags are encoded as bits: 1 (bit0) - hw_params 2 (bit1) - hw_free 4 (bit2) - pause These are commands, they cannot be combined as one would assume, for example 3 (bit0 | bit1) is invalid. This can happen right at the second start of a stream as at the end of the first stream we set the hw_free command (bit1) and on the second start we would OR on top of it the hw_params (bit0). Fixes: b66bfc3a9810 ("ASoC: SOF: sof-audio: Fix broken early bclk feature for SSP") Signed-off-by: Peter Ujfalusi flags &= ~SOF_DAI_CONFIG_FLAGS_CMD_MASK; config->flags |= flags; - else + } else { config->flags = flags; + } /* only send the IPC if the widget is set up in the DSP */ if (swidget->use_count > 0) { -- GitLab From a93d2afd3f77a7331271a0f25c6a11003db69b3c Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Thu, 11 May 2023 09:25:12 -0700 Subject: [PATCH 4942/5631] ASoC: mediatek: mt8186: Fix use-after-free in driver remove path When devm runs function in the "remove" path for a device it runs them in the reverse order. That means that if you have parts of your driver that aren't using devm or are using "roll your own" devm w/ devm_add_action_or_reset() you need to keep that in mind. The mt8186 audio driver didn't quite get this right. Specifically, in mt8186_init_clock() it called mt8186_audsys_clk_register() and then went on to call a bunch of other devm function. The caller of mt8186_init_clock() used devm_add_action_or_reset() to call mt8186_deinit_clock() but, because of the intervening devm functions, the order was wrong. Specifically at probe time, the order was: 1. mt8186_audsys_clk_register() 2. afe_priv->clk = devm_kcalloc(...) 3. afe_priv->clk[i] = devm_clk_get(...) At remove time, the order (which should have been 3, 2, 1) was: 1. mt8186_audsys_clk_unregister() 3. Free all of afe_priv->clk[i] 2. Free afe_priv->clk The above seemed to be causing a use-after-free. Luckily, it's easy to fix this by simply using devm more correctly. Let's move the devm_add_action_or_reset() to the right place. In addition to fixing the use-after-free, code inspection shows that this fixes a leak (missing call to mt8186_audsys_clk_unregister()) that would have happened if any of the syscon_regmap_lookup_by_phandle() calls in mt8186_init_clock() had failed. Fixes: 55b423d5623c ("ASoC: mediatek: mt8186: support audio clock control in platform driver") Signed-off-by: Douglas Anderson memif_32bit_supported = 0; afe->memif_size = MT8186_MEMIF_NUM; diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c index 578969ca91c8..5666be6b1bd2 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.c @@ -84,6 +84,29 @@ static const struct afe_gate aud_clks[CLK_AUD_NR_CLK] = { GATE_AUD2(CLK_AUD_ETDM_OUT1_BCLK, "aud_etdm_out1_bclk", "top_audio", 24), }; +static void mt8186_audsys_clk_unregister(void *data) +{ + struct mtk_base_afe *afe = data; + struct mt8186_afe_private *afe_priv = afe->platform_priv; + struct clk *clk; + struct clk_lookup *cl; + int i; + + if (!afe_priv) + return; + + for (i = 0; i < CLK_AUD_NR_CLK; i++) { + cl = afe_priv->lookup[i]; + if (!cl) + continue; + + clk = cl->clk; + clk_unregister_gate(clk); + + clkdev_drop(cl); + } +} + int mt8186_audsys_clk_register(struct mtk_base_afe *afe) { struct mt8186_afe_private *afe_priv = afe->platform_priv; @@ -124,27 +147,6 @@ int mt8186_audsys_clk_register(struct mtk_base_afe *afe) afe_priv->lookup[i] = cl; } - return 0; + return devm_add_action_or_reset(afe->dev, mt8186_audsys_clk_unregister, afe); } -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe) -{ - struct mt8186_afe_private *afe_priv = afe->platform_priv; - struct clk *clk; - struct clk_lookup *cl; - int i; - - if (!afe_priv) - return; - - for (i = 0; i < CLK_AUD_NR_CLK; i++) { - cl = afe_priv->lookup[i]; - if (!cl) - continue; - - clk = cl->clk; - clk_unregister_gate(clk); - - clkdev_drop(cl); - } -} diff --git a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h index b8d6a06e11e8..897a2914dc19 100644 --- a/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h +++ b/sound/soc/mediatek/mt8186/mt8186-audsys-clk.h @@ -10,6 +10,5 @@ #define _MT8186_AUDSYS_CLK_H_ int mt8186_audsys_clk_register(struct mtk_base_afe *afe); -void mt8186_audsys_clk_unregister(struct mtk_base_afe *afe); #endif -- GitLab From 647b5f5fdcbaba6f6fd8db69508fcbeb1fdfc2a6 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 13 May 2023 11:02:28 +0200 Subject: [PATCH 4943/5631] ASoC: MAINTAINERS: drop Krzysztof Kozlowski from Samsung audio Remove Krzysztof Kozlowski from maintainer of Samsung SoC Audio drivers and change the status to maintenance (no one is reality being paid for looking at this). Signed-off-by: Krzysztof Kozlowski M: Sylwester Nawrocki L: alsa-devel@alsa-project.org (moderated for non-subscribers) -S: Supported +S: Maintained B: mailto:linux-samsung-soc@vger.kernel.org F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ -- GitLab From 171b53be635ac15d4feafeb33946035649b1ca14 Mon Sep 17 00:00:00 2001 From: Kai Vehmanen Date: Fri, 12 May 2023 13:46:38 +0300 Subject: [PATCH 4944/5631] ASoC: SOF: pm: save io region state in case of errors in resume MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If there are failures in DSP runtime resume, the device state will not reach active and this makes it impossible e.g. to retrieve a possible DSP panic dump via "exception" debugfs node. If CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE=y is set, the data in cache is stale. If debugfs cache is not used, the region simply cannot be read. To allow debugging these scenarios, update the debugfs cache contents in resume error handler. User-space can then later retrieve DSP panic and other state via debugfs (requires SOF debugfs cache to be enabled in build). Reported-by: Curtis Malainey set_up_all_pipelines(sdev, false); if (ret < 0) { dev_err(sdev->dev, "Failed to restore pipeline after resume %d\n", ret); - return ret; + goto setup_fail; } } @@ -178,6 +178,18 @@ static int sof_resume(struct device *dev, bool runtime_resume) dev_err(sdev->dev, "ctx_restore IPC error during resume: %d\n", ret); } +setup_fail: +#if IS_ENABLED(CONFIG_SND_SOC_SOF_DEBUG_ENABLE_DEBUGFS_CACHE) + if (ret < 0) { + /* + * Debugfs cannot be read in runtime suspend, so cache + * the contents upon failure. This allows to capture + * possible DSP coredump information. + */ + sof_cache_debugfs(sdev); + } +#endif + return ret; } -- GitLab From 41c5305cc3d827d2ea686533777a285176ae01a0 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Fri, 12 May 2023 14:46:30 +0300 Subject: [PATCH 4945/5631] ASoC: SOF: topology: Fix logic for copying tuples MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Topology could have more instances of the tokens being searched for than the number of sets that need to be copied. Stop copying token after the limit of number of token instances has been reached. This worked before only by chance as we had allocated more size for the tuples array than the number of actual tokens being parsed. Fixes: 7006d20e5e9d ("ASoC: SOF: Introduce IPC3 ops") Signed-off-by: Ranjani Sridharan Date: Fri, 12 May 2023 10:19:34 +0200 Subject: [PATCH 4946/5631] regulator: pca9450: Fix BUCK2 enable_mask This fixes a copy & paste error. No functional change intended, BUCK1_ENMODE_MASK equals BUCK2_ENMODE_MASK. Fixes: 0935ff5f1f0a ("regulator: pca9450: add pca9450 pmic driver") Originally-from: Robin Gong Date: Tue, 9 May 2023 17:41:52 +0100 Subject: [PATCH 4947/5631] spi: spi-cadence: Avoid read of RX FIFO before its ready Recent changes to cdns_spi_irq introduced some issues. Firstly, when writing the end of a longer transaction, the code in cdns_spi_irq will write data into the TX FIFO, then immediately fall into the if (!xspi->tx_bytes) path and attempt to read data from the RX FIFO. However this required waiting for the TX FIFO to empty before the RX data was ready. Secondly, the variable trans_cnt is now rather inaccurately named since in cases, where the watermark is set to 1, trans_cnt will be 1 but the count of bytes transferred would be much longer. Finally, when setting up the transaction we set the watermark to 50% of the FIFO if the transaction is great than 50% of the FIFO. However, there is no need to split a tranaction that is smaller than the whole FIFO, so anything up to the FIFO size can be done in a single transaction. Tidy up the code a little, to avoid repeatedly calling cdns_spi_read_rx_fifo with a count of 1, and correct the three issues noted above. Fixes: b1b90514eaa3 ("spi: spi-cadence: Add support for Slave mode") Signed-off-by: Charles Keepax tx_fifo_depth) && - (xspi->tx_bytes > 0)) { - + while ((trans_cnt < avail) && (xspi->tx_bytes > 0)) { /* When xspi in busy condition, bytes may send failed, * then spi control did't work thoroughly, add one byte delay */ @@ -381,33 +379,23 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id) spi_finalize_current_transfer(ctlr); status = IRQ_HANDLED; } else if (intr_status & CDNS_SPI_IXR_TXOW) { - int trans_cnt = cdns_spi_read(xspi, CDNS_SPI_THLD); + int threshold = cdns_spi_read(xspi, CDNS_SPI_THLD); + int trans_cnt = xspi->rx_bytes - xspi->tx_bytes; + + if (threshold > 1) + trans_cnt -= threshold; + /* Set threshold to one if number of pending are * less than half fifo */ if (xspi->tx_bytes < xspi->tx_fifo_depth >> 1) cdns_spi_write(xspi, CDNS_SPI_THLD, 1); - while (trans_cnt) { - cdns_spi_read_rx_fifo(xspi, 1); - - if (xspi->tx_bytes) { - if (xspi->txbuf) - cdns_spi_write(xspi, CDNS_SPI_TXD, - *xspi->txbuf++); - else - cdns_spi_write(xspi, CDNS_SPI_TXD, 0); - xspi->tx_bytes--; - } - trans_cnt--; - } - if (!xspi->tx_bytes) { - /* Fixed delay due to controller limitation with - * RX_NEMPTY incorrect status - * Xilinx AR:65885 contains more details - */ - udelay(10); - cdns_spi_read_rx_fifo(xspi, xspi->rx_bytes); + cdns_spi_read_rx_fifo(xspi, trans_cnt); + + if (xspi->tx_bytes) { + cdns_spi_fill_tx_fifo(xspi, trans_cnt); + } else { cdns_spi_write(xspi, CDNS_SPI_IDR, CDNS_SPI_IXR_DEFAULT); spi_finalize_current_transfer(ctlr); @@ -456,10 +444,10 @@ static int cdns_transfer_one(struct spi_controller *ctlr, /* Set TX empty threshold to half of FIFO depth * only if TX bytes are more than half FIFO depth. */ - if (xspi->tx_bytes > (xspi->tx_fifo_depth >> 1)) + if (xspi->tx_bytes > xspi->tx_fifo_depth) cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); - cdns_spi_fill_tx_fifo(xspi); + cdns_spi_fill_tx_fifo(xspi, xspi->tx_fifo_depth); spi_transfer_delay_exec(transfer); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); -- GitLab From a0eb7be22c0f934d1fe7e1131f174ef5bc59d3f9 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 9 May 2023 17:41:53 +0100 Subject: [PATCH 4948/5631] spi: spi-cadence: Only overlap FIFO transactions in slave mode Commit b1b90514eaa3 ("spi: spi-cadence: Add support for Slave mode") updated the code to trigger the IRQ when the FIFO was half empty, overlapping filling more data into the FIFO and sending what is left. This appears to cause regressions on the Zynq 7000, for transactions longer than the FIFO size, below that no overlapping occurs. It would appear from my testing that any attempt to put new data into the FIFO whilst data is still transmitting causes data corruption on both send and receive. If I am reading the commit message right on commit 49530e641178 ("spi: cadence: Add usleep_range() for cdns_spi_fill_tx_fifo()"), that would also seem to imply this is the case. On the assumption that this isn't an issue on the platform the original slave mode support was added for, update the cdns_transfer_one to only set the watermark to 50% of the FIFO size when in slave mode. There by retaining the new behaviour for slave mode but reverting to the older behaviour when the SPI is used a master. Fixes: b1b90514eaa3 ("spi: spi-cadence: Add support for Slave mode") Signed-off-by: Charles Keepax tx_bytes = transfer->len; xspi->rx_bytes = transfer->len; - if (!spi_controller_is_slave(ctlr)) + if (!spi_controller_is_slave(ctlr)) { cdns_spi_setup_transfer(spi, transfer); - - /* Set TX empty threshold to half of FIFO depth - * only if TX bytes are more than half FIFO depth. - */ - if (xspi->tx_bytes > xspi->tx_fifo_depth) - cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); + } else { + /* Set TX empty threshold to half of FIFO depth + * only if TX bytes are more than half FIFO depth. + */ + if (xspi->tx_bytes > xspi->tx_fifo_depth) + cdns_spi_write(xspi, CDNS_SPI_THLD, xspi->tx_fifo_depth >> 1); + } cdns_spi_fill_tx_fifo(xspi, xspi->tx_fifo_depth); spi_transfer_delay_exec(transfer); -- GitLab From ec9452594e04804cabbc561e88e96b48ab4655e4 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 13 May 2023 19:36:46 +0200 Subject: [PATCH 4949/5631] spi: MAINTAINERS: drop Krzysztof Kozlowski from Samsung SPI Remove Krzysztof Kozlowski from maintainers of Samsung SoC SPI drivers. Signed-off-by: Krzysztof Kozlowski M: Andi Shyti L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org -- GitLab From 17082e09b94cfe60bf39088f3d37c1f10e6c5928 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Fri, 12 May 2023 15:42:37 +0100 Subject: [PATCH 4950/5631] ASoC: cs35l56: Prevent unbalanced pm_runtime in dsp_work() on SoundWire Flush the SoundWire interrupt handler work instead of cancelling it. When a SoundWire interrupt is triggered the pm_runtime is held until the work has completed. It's therefore unsafe to cancel the work, it must be flushed. Signed-off-by: Simon Trimmer sdw_peripheral) { cs35l56->sdw_irq_no_unmask = true; - cancel_work_sync(&cs35l56->sdw_irq_work); + flush_work(&cs35l56->sdw_irq_work); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_MASK_1, 0); sdw_read_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1); sdw_write_no_pm(cs35l56->sdw_peripheral, CS35L56_SDW_GEN_INT_STAT_1, 0xFF); + flush_work(&cs35l56->sdw_irq_work); } ret = cs35l56_mbox_send(cs35l56, CS35L56_MBOX_CMD_SHUTDOWN); -- GitLab From dc60b67d259ea63196dcd0400dd43ba062e2e097 Mon Sep 17 00:00:00 2001 From: Lucas Tanure Date: Fri, 12 May 2023 16:45:03 +0100 Subject: [PATCH 4951/5631] MAINTAINERS: Remove self from Cirrus Codec drivers I'm leaving Cirrus Logic, and will no longer have access to hardware and documentation necessary to be effective in a maintainership role. Signed-off-by: Lucas Tanure M: David Rhodes -M: Lucas Tanure M: Richard Fitzgerald L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: patches@opensource.cirrus.com -- GitLab From 07bb2e368820a4de9b4b586691e143976b74ea44 Mon Sep 17 00:00:00 2001 From: Adam Ford Date: Thu, 11 May 2023 20:04:23 -0500 Subject: [PATCH 4952/5631] arm64: dts: imx8mp: Fix video clock parents There are a few clocks whose parents are set in mipi_dsi and lcdif nodes, but these clocks are used by the media_blk_ctrl power domain. This may cause an issue when re-parenting, because the media_blk_ctrl may start the clocks before the reparent is done resulting in a disp_pixel clock having the wrong parent and rate. Fix this by moving the assigned-clock-parents and rates to the media_blk_ctrl node to configure these clocks before they are enabled. After this patch, both disp1_pix_root and dixp2_pix_root clock become children of the video_pll1. video_pll1_ref_sel 24000000 video_pll1 1039500000 video_pll1_bypass 1039500000 video_pll1_out 1039500000 media_disp2_pix 1039500000 media_disp2_pix_root_clk 1039500000 media_disp1_pix 1039500000 media_disp1_pix_root_clk 1039500000 Fixes: eda09fe149df ("arm64: dts: imx8mp: Add display pipeline components") Signed-off-by: Adam Ford Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8mp.dtsi | 25 ++++++++--------------- 1 file changed, 9 insertions(+), 16 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index f81391993354..428c60462e3d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1211,13 +1211,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT>, - <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; - assigned-clock-parents = <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, - <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <594000000>, <500000000>, <200000000>; interrupts = ; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_1>; status = "disabled"; @@ -1237,11 +1230,6 @@ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>, <&clk IMX8MP_CLK_MEDIA_AXI_ROOT>; clock-names = "pix", "axi", "disp_axi"; - assigned-clocks = <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, - <&clk IMX8MP_VIDEO_PLL1>; - assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>, - <&clk IMX8MP_VIDEO_PLL1_REF_SEL>; - assigned-clock-rates = <0>, <1039500000>; power-domains = <&media_blk_ctrl IMX8MP_MEDIABLK_PD_LCDIF_2>; status = "disabled"; @@ -1296,11 +1284,16 @@ "disp1", "disp2", "isp", "phy"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_AXI>, - <&clk IMX8MP_CLK_MEDIA_APB>; + <&clk IMX8MP_CLK_MEDIA_APB>, + <&clk IMX8MP_CLK_MEDIA_DISP1_PIX>, + <&clk IMX8MP_CLK_MEDIA_DISP2_PIX>, + <&clk IMX8MP_VIDEO_PLL1>; assigned-clock-parents = <&clk IMX8MP_SYS_PLL2_1000M>, - <&clk IMX8MP_SYS_PLL1_800M>; - assigned-clock-rates = <500000000>, <200000000>; - + <&clk IMX8MP_SYS_PLL1_800M>, + <&clk IMX8MP_VIDEO_PLL1_OUT>, + <&clk IMX8MP_VIDEO_PLL1_OUT>; + assigned-clock-rates = <500000000>, <200000000>, + <0>, <0>, <1039500000>; #power-domain-cells = <1>; lvds_bridge: bridge@5c { -- GitLab From a346d4dc74d94ac3c197283d0a7ec673a59a0674 Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Sun, 14 May 2023 11:22:43 +0200 Subject: [PATCH 4953/5631] arm64: dts: colibri-imx8x: fix eval board pin configuration Fix pinctrl groups to have SODIMM 75 only in one group. Remove configuration of the pin at SoM level because it is normally used as CSI_MCLK at camera interface connector. Without this fix it is not possible, without redefining iomuxc pinctrl, to use CSI_MCLK signal and leads to the following error messages: imx8qxp-pinctrl scu:pinctrl: pin IMX8QXP_CSI_MCLK already requested imx8qxp-pinctrl scu:pinctrl: pin-147 (16-003c) status -22 Fixes: 4d2adf738169 ("arm64: dts: colibri-imx8x: Split pinctrl_hog1") Signed-off-by: Emanuele Ghidoli Signed-off-by: Andrejs Cainikovs Signed-off-by: Francesco Dolcini Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi index 7cad79102e1a..6f88c11f16e1 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi @@ -365,7 +365,7 @@ &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, - <&pinctrl_hog2>, <&pinctrl_lpspi2_cs2>; + <&pinctrl_lpspi2_cs2>; /* On-module touch pen-down interrupt */ pinctrl_ad7879_int: ad7879intgrp { @@ -499,8 +499,7 @@ }; pinctrl_hog1: hog1grp { - fsl,pins = , /* SODIMM 75 */ - ; /* SODIMM 93 */ + fsl,pins = ; /* SODIMM 93 */ }; pinctrl_hog2: hog2grp { -- GitLab From 25acffb00899d3ac85a9701c99f7929f97a5d9af Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Sun, 14 May 2023 11:22:44 +0200 Subject: [PATCH 4954/5631] arm64: dts: colibri-imx8x: move pinctrl property from SoM to eval board Each carrier board device tree except the eval board one already override iomuxc pinctrl property to configure unused pins as gpio. So move also the pinctrl property to eval board device tree. Leave the pin group definition in imx8x-colibri.dtsi to avoid duplication and simplify configuration of gpio. Signed-off-by: Emanuele Ghidoli Signed-off-by: Andrejs Cainikovs Signed-off-by: Francesco Dolcini Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi | 6 ++++++ arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi | 4 ---- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi index 7264d784ae72..9af769ab8ceb 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-eval-v3.dtsi @@ -33,6 +33,12 @@ }; }; +&iomuxc { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, + <&pinctrl_lpspi2_cs2>; +}; + /* Colibri SPI */ &lpspi2 { status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi index 6f88c11f16e1..b0d6f632622c 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi @@ -363,10 +363,6 @@ /* TODO VPU Encoder/Decoder */ &iomuxc { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ext_io0>, <&pinctrl_hog0>, <&pinctrl_hog1>, - <&pinctrl_lpspi2_cs2>; - /* On-module touch pen-down interrupt */ pinctrl_ad7879_int: ad7879intgrp { fsl,pins = ; -- GitLab From 34e5c0cd55af7258d819cb203da7d202bae3b97d Mon Sep 17 00:00:00 2001 From: Emanuele Ghidoli Date: Sun, 14 May 2023 11:22:45 +0200 Subject: [PATCH 4955/5631] arm64: dts: colibri-imx8x: fix iris pinctrl configuration Remove GPIO3_IO10 from Iris carrier board pinctrl configuration, this is already defined in the SOM dtsi since this is a standard SOM functionality (wake-up button). Duplicating it leads to the following error message imx8qxp-pinctrl scu:pinctrl: pin IMX8QXP_QSPI0A_DATA1 already requested Fixes: aefb5e2d974d ("arm64: dts: colibri-imx8x: Add iris carrier board") Signed-off-by: Emanuele Ghidoli Signed-off-by: Andrejs Cainikovs Signed-off-by: Francesco Dolcini Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi index 5f30c88855e7..f8953067bc3b 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri-iris.dtsi @@ -48,8 +48,7 @@ , /* SODIMM 101 */ , /* SODIMM 97 */ , /* SODIMM 85 */ - , /* SODIMM 79 */ - ; /* SODIMM 45 */ + ; /* SODIMM 79 */ }; pinctrl_uart1_forceoff: uart1forceoffgrp { -- GitLab From b8b23fbe93b34e595a7b0f31b4ed22400c47ec07 Mon Sep 17 00:00:00 2001 From: Andrejs Cainikovs Date: Sun, 14 May 2023 11:22:46 +0200 Subject: [PATCH 4956/5631] arm64: dts: colibri-imx8x: delete adc1 and dsp i.MX8, i.MX8X, i.MX8XP and i.MX8XL SOC device trees are all based on imx8-ss-*.dtsi files. For i.MX8X and i.MX8XP these device trees should be updated with some peripherals removed or updated, similar to i.MX8XL (imx8dxl-ss-*.dtsi files). However, it looks like only i.MX8 and i.MX8XL are up to date, but for i.MX8X and i.MX8XP some of the peripherals got inherited from imx8-ss-*.dtsi files, but in reality they are not present on SOC. As a result, during resource partition ownership check U-Boot receives messages from SCU firmware about these resources not owned by boot partition. In reality, these resources are not owned by anyone, as they simply does not exist, but are defined in Linux device tree. This change removes those peripherals, which are listed during U-Boot resource partition ownership check as warnings: ## Flattened Device Tree blob at 9d400000 Booting using the fdt blob at 0x9d400000 Loading Device Tree to 00000000fd652000, end 00000000fd67efff ... OK Disable clock-controller@59580000 rsrc 512 not owned Disable clock-controller@5ac90000 rsrc 102 not owned Starting kernel ... Fixes: ba5a5615d54f ("arm64: dts: freescale: add initial support for colibri imx8x") Signed-off-by: Andrejs Cainikovs Signed-off-by: Francesco Dolcini Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi index b0d6f632622c..49d105eb4769 100644 --- a/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8x-colibri.dtsi @@ -769,3 +769,10 @@ fsl,pins = ; }; }; + +/* Delete peripherals which are not present on SOC, but are defined in imx8-ss-*.dtsi */ + +/delete-node/ &adc1; +/delete-node/ &adc1_lpcg; +/delete-node/ &dsp; +/delete-node/ &dsp_lpcg; -- GitLab From 2ef0785b30bd6549ddbc124979f1b6596e065ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Apr 2023 23:04:11 +0200 Subject: [PATCH 4957/5631] drm/exynos: fix g2d_open/close helper function definitions The empty stub functions are defined as global functions, which causes a warning because of missing prototypes: drivers/gpu/drm/exynos/exynos_drm_g2d.h:37:5: error: no previous prototype for 'g2d_open' drivers/gpu/drm/exynos/exynos_drm_g2d.h:42:5: error: no previous prototype for 'g2d_close' Mark them as 'static inline' to avoid the warning and to make them behave as intended. Fixes: eb4d9796fa34 ("drm/exynos: g2d: Convert to driver component API") Signed-off-by: Arnd Bergmann Reviewed-by: Andi Shyti Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_g2d.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h index 74ea3c26dead..1a5ae781b56c 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h @@ -34,11 +34,11 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data, return -ENODEV; } -int g2d_open(struct drm_device *drm_dev, struct drm_file *file) +static inline int g2d_open(struct drm_device *drm_dev, struct drm_file *file) { return 0; } -void g2d_close(struct drm_device *drm_dev, struct drm_file *file) +static inline void g2d_close(struct drm_device *drm_dev, struct drm_file *file) { } #endif -- GitLab From 35a4b8ce4ac00e940b46b1034916ccb22ce9bdef Mon Sep 17 00:00:00 2001 From: Hari Bathini Date: Tue, 25 Apr 2023 12:28:29 +0530 Subject: [PATCH 4958/5631] powerpc/bpf: populate extable entries only during the last pass Since commit 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses"), two additional passes are performed to avoid space and CPU time wastage on powerpc. But these extra passes led to WARN_ON_ONCE() hits in bpf_add_extable_entry() as extable entries are populated again, during the extra pass, without resetting the index. Fix it by resetting entry index before repopulating extable entries, if and when there is an additional pass. Fixes: 85e031154c7c ("powerpc/bpf: Perform complete extra passes to update addresses") Cc: stable@vger.kernel.org # v6.3+ Signed-off-by: Hari Bathini Reviewed-by: Naveen N. Rao Signed-off-by: Michael Ellerman Link: https://msgid.link/20230425065829.18189-1-hbathini@linux.ibm.com --- arch/powerpc/net/bpf_jit_comp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index e93aefcfb83f..37043dfc1add 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -101,6 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) bpf_hdr = jit_data->header; proglen = jit_data->proglen; extra_pass = true; + /* During extra pass, ensure index is reset before repopulating extable entries */ + cgctx.exentry_idx = 0; goto skip_init_ctx; } -- GitLab From c83b49383b595be50647f0c764a48c78b5f3c4f8 Mon Sep 17 00:00:00 2001 From: Dong Chenchen Date: Thu, 11 May 2023 20:54:40 +0800 Subject: [PATCH 4959/5631] net: nsh: Use correct mac_offset to unwind gso skb in nsh_gso_segment() As the call trace shows, skb_panic was caused by wrong skb->mac_header in nsh_gso_segment(): invalid opcode: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 3 PID: 2737 Comm: syz Not tainted 6.3.0-next-20230505 #1 RIP: 0010:skb_panic+0xda/0xe0 call Trace: skb_push+0x91/0xa0 nsh_gso_segment+0x4f3/0x570 skb_mac_gso_segment+0x19e/0x270 __skb_gso_segment+0x1e8/0x3c0 validate_xmit_skb+0x452/0x890 validate_xmit_skb_list+0x99/0xd0 sch_direct_xmit+0x294/0x7c0 __dev_queue_xmit+0x16f0/0x1d70 packet_xmit+0x185/0x210 packet_snd+0xc15/0x1170 packet_sendmsg+0x7b/0xa0 sock_sendmsg+0x14f/0x160 The root cause is: nsh_gso_segment() use skb->network_header - nhoff to reset mac_header in skb_gso_error_unwind() if inner-layer protocol gso fails. However, skb->network_header may be reset by inner-layer protocol gso function e.g. mpls_gso_segment. skb->mac_header reset by the inaccurate network_header will be larger than skb headroom. nsh_gso_segment nhoff = skb->network_header - skb->mac_header; __skb_pull(skb,nsh_len) skb_mac_gso_segment mpls_gso_segment skb_reset_network_header(skb);//skb->network_header+=nsh_len return -EINVAL; skb_gso_error_unwind skb_push(skb, nsh_len); skb->mac_header = skb->network_header - nhoff; // skb->mac_header > skb->headroom, cause skb_push panic Use correct mac_offset to restore mac_header and get rid of nhoff. Fixes: c411ed854584 ("nsh: add GSO support") Reported-by: syzbot+632b5d9964208bfef8c0@syzkaller.appspotmail.com Suggested-by: Eric Dumazet Signed-off-by: Dong Chenchen Signed-off-by: David S. Miller --- net/nsh/nsh.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index e9ca007718b7..0f23e5e8e03e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -77,13 +77,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -108,15 +107,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } -- GitLab From 5896f2d363d5cfb7510856c90d5e0ed934a1d340 Mon Sep 17 00:00:00 2001 From: Suraj Kandpal Date: Fri, 5 May 2023 09:45:12 +0530 Subject: [PATCH 4960/5631] drm/i915/hdcp: Check if media_gt exists Check if media_gt exists if we are using gsc cs --v2 -correct typo [Ankit] -assign gsc variable if gt exists [Ankit] --v3 -declare gsc and gt variables in if block [Ankit] --v4 -add fixes tag [Ankit] Fixes: 883631771038 ("drm/i915/mtl: Add HDCP GSC interface") Cc: Tomas Winkler Cc: Rodrigo Vivi Cc: Uma Shankar Cc: Anshuman Gupta Cc: Ankit Nautiyal Signed-off-by: Suraj Kandpal Reviewed-by: Gustavo Sousa Reviewed-by: Ankit Nautiyal Signed-off-by: Animesh Manna Link: https://patchwork.freedesktop.org/patch/msgid/20230505041512.585486-1-suraj.kandpal@intel.com (cherry picked from commit 6986f05b557bf1efea5bac8dbdffb7ee89d0cf77) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_hdcp.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 650232c4892b..b183efab04a1 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -204,8 +204,6 @@ bool intel_hdcp2_capable(struct intel_connector *connector) struct intel_digital_port *dig_port = intel_attached_dig_port(connector); struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_hdcp *hdcp = &connector->hdcp; - struct intel_gt *gt = dev_priv->media_gt; - struct intel_gsc_uc *gsc = >->uc.gsc; bool capable = false; /* I915 support for HDCP2.2 */ @@ -213,9 +211,13 @@ bool intel_hdcp2_capable(struct intel_connector *connector) return false; /* If MTL+ make sure gsc is loaded and proxy is setup */ - if (intel_hdcp_gsc_cs_required(dev_priv)) - if (!intel_uc_fw_is_running(&gsc->fw)) + if (intel_hdcp_gsc_cs_required(dev_priv)) { + struct intel_gt *gt = dev_priv->media_gt; + struct intel_gsc_uc *gsc = gt ? >->uc.gsc : NULL; + + if (!gsc || !intel_uc_fw_is_running(&gsc->fw)) return false; + } /* MEI/GSC interface is solid depending on which is used */ mutex_lock(&dev_priv->display.hdcp.comp_mutex); -- GitLab From 6ead9c98cafcbc6992cf35f0ca393df2c03e3316 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Fri, 12 May 2023 08:38:43 -0500 Subject: [PATCH 4961/5631] net: fec: remove the xdp_return_frame when lack of tx BDs In the implementation, the sent_frame count does not increment when transmit errors occur. Therefore, bq_xmit_all() will take care of returning the XDP frames. Fixes: 26312c685ae0 ("net: fec: correct the counting of XDP sent frames") Signed-off-by: Shenwei Wang Reviewed-by: Horatiu Vultur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 241df41d500f..577d94821b3e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3798,7 +3798,6 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, entries_free = fec_enet_get_free_txdesc_num(txq); if (entries_free < MAX_SKB_FRAGS + 1) { netdev_err(fep->netdev, "NOT enough BD for SG!\n"); - xdp_return_frame(frame); return NETDEV_TX_BUSY; } -- GitLab From 5306623a9826aa7d63b32c6a3803c798a765474d Mon Sep 17 00:00:00 2001 From: Feng Liu Date: Fri, 12 May 2023 11:18:12 -0400 Subject: [PATCH 4962/5631] virtio_net: Fix error unwinding of XDP initialization When initializing XDP in virtnet_open(), some rq xdp initialization may hit an error causing net device open failed. However, previous rqs have already initialized XDP and enabled NAPI, which is not the expected behavior. Need to roll back the previous rq initialization to avoid leaks in error unwinding of init code. Also extract helper functions of disable and enable queue pairs. Use newly introduced disable helper function in error unwinding and virtnet_close. Use enable helper function in virtnet_open. Fixes: 754b8a21a96d ("virtio_net: setup xdp_rxq_info") Signed-off-by: Feng Liu Reviewed-by: Jiri Pirko Reviewed-by: William Tu Acked-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Xuan Zhuo Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 61 +++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 17 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a12ae26db0e2..56ca1d270304 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1868,6 +1868,38 @@ static int virtnet_poll(struct napi_struct *napi, int budget) return received; } +static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + virtnet_napi_tx_disable(&vi->sq[qp_index].napi); + napi_disable(&vi->rq[qp_index].napi); + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); +} + +static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) +{ + struct net_device *dev = vi->dev; + int err; + + err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, + vi->rq[qp_index].napi.napi_id); + if (err < 0) + return err; + + err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) + goto err_xdp_reg_mem_model; + + virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); + virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + + return 0; + +err_xdp_reg_mem_model: + xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); + return err; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -1881,22 +1913,20 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); + err = virtnet_enable_queue_pair(vi, i); if (err < 0) - return err; - - err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err < 0) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - return err; - } - - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); + goto err_enable_qp; } return 0; + +err_enable_qp: + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + + for (i--; i >= 0; i--) + virtnet_disable_queue_pair(vi, i); + return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) @@ -2305,11 +2335,8 @@ static int virtnet_close(struct net_device *dev) /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_tx_disable(&vi->sq[i].napi); - napi_disable(&vi->rq[i].napi); - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_disable_queue_pair(vi, i); return 0; } -- GitLab From b48a18644046c9bc0667493a147dfa01e8241eab Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 13 May 2023 09:57:27 +0100 Subject: [PATCH 4963/5631] net: mdio: i2c: fix rollball accessors Commit 87e3bee0f247 ("net: mdio: i2c: Separate C22 and C45 transactions") separated the non-rollball bus accessors, but left the rollball accessors as is. As rollball accessors are clause 45, this results in the rollball protocol being completely non-functional. Fix this. Fixes: 87e3bee0f247 ("net: mdio: i2c: Separate C22 and C45 transactions") Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/mdio/mdio-i2c.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c index 1e0c206d0f2e..da2001ea1f99 100644 --- a/drivers/net/mdio/mdio-i2c.c +++ b/drivers/net/mdio/mdio-i2c.c @@ -291,7 +291,8 @@ static int i2c_rollball_mii_cmd(struct mii_bus *bus, int bus_addr, u8 cmd, return i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs)); } -static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) +static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg) { u8 buf[4], res[6]; int bus_addr, ret; @@ -302,7 +303,7 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return 0xffff; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; @@ -322,8 +323,8 @@ static int i2c_mii_read_rollball(struct mii_bus *bus, int phy_id, int reg) return val; } -static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, - u16 val) +static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int devad, + int reg, u16 val) { int bus_addr, ret; u8 buf[6]; @@ -333,7 +334,7 @@ static int i2c_mii_write_rollball(struct mii_bus *bus, int phy_id, int reg, return 0; buf[0] = ROLLBALL_DATA_ADDR; - buf[1] = (reg >> 16) & 0x1f; + buf[1] = devad; buf[2] = (reg >> 8) & 0xff; buf[3] = reg & 0xff; buf[4] = val >> 8; @@ -405,8 +406,8 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c, return ERR_PTR(ret); } - mii->read = i2c_mii_read_rollball; - mii->write = i2c_mii_write_rollball; + mii->read_c45 = i2c_mii_read_rollball; + mii->write_c45 = i2c_mii_write_rollball; break; default: mii->read = i2c_mii_read_default_c22; -- GitLab From 3ae6d66b605be604644d4bb5708a7ffd9cf1abe8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:27 -0400 Subject: [PATCH 4964/5631] tipc: add tipc_bearer_min_mtu to calculate min mtu As different media may requires different min mtu, and even the same media with different net family requires different min mtu, add tipc_bearer_min_mtu() to calculate min mtu accordingly. This API will be used to check the new mtu when doing the link mtu negotiation in the next patch. Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bearer.c | 13 +++++++++++++ net/tipc/bearer.h | 3 +++ net/tipc/udp_media.c | 5 +++-- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 35cac7733fd3..0e9a29e1536b 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -541,6 +541,19 @@ int tipc_bearer_mtu(struct net *net, u32 bearer_id) return mtu; } +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id) +{ + int mtu = TIPC_MIN_BEARER_MTU; + struct tipc_bearer *b; + + rcu_read_lock(); + b = bearer_get(net, bearer_id); + if (b) + mtu += b->encap_hlen; + rcu_read_unlock(); + return mtu; +} + /* tipc_bearer_xmit_skb - sends buffer to destination over bearer */ void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 490ad6e5f7a3..bd0cc5c287ef 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -146,6 +146,7 @@ struct tipc_media { * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * @@ -170,6 +171,7 @@ struct tipc_bearer { u32 identity; struct tipc_discoverer *disc; char net_plane; + u16 encap_hlen; unsigned long up; refcount_t refcnt; }; @@ -232,6 +234,7 @@ int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); +int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c2bb818704c8..0a85244fd618 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -738,8 +738,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = local.ipv4.s_addr; udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; - if (tipc_mtu_bad(dev, sizeof(struct iphdr) + - sizeof(struct udphdr))) { + b->encap_hlen = sizeof(struct iphdr) + sizeof(struct udphdr); + if (tipc_mtu_bad(dev, b->encap_hlen)) { err = -EINVAL; goto err; } @@ -760,6 +760,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, else udp_conf.local_ip6 = local.ipv6; ub->ifindex = dev->ifindex; + b->encap_hlen = sizeof(struct ipv6hdr) + sizeof(struct udphdr); b->mtu = 1280; #endif } else { -- GitLab From 56077b56cd3fb78e1c8619e29581ba25a5c55e86 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:28 -0400 Subject: [PATCH 4965/5631] tipc: do not update mtu if msg_max is too small in mtu negotiation When doing link mtu negotiation, a malicious peer may send Activate msg with a very small mtu, e.g. 4 in Shuang's testing, without checking for the minimum mtu, l->mtu will be set to 4 in tipc_link_proto_rcv(), then n->links[bearer_id].mtu is set to 4294967228, which is a overflow of '4 - INT_H_SIZE - EMSG_OVERHEAD' in tipc_link_mss(). With tipc_link.mtu = 4, tipc_link_xmit() kept printing the warning: tipc: Too large msg, purging xmit list 1 5 0 40 4! tipc: Too large msg, purging xmit list 1 15 0 60 4! And with tipc_link_entry.mtu 4294967228, a huge skb was allocated in named_distribute(), and when purging it in tipc_link_xmit(), a crash was even caused: general protection fault, probably for non-canonical address 0x2100001011000dd: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 0 Comm: swapper/0 Kdump: loaded Not tainted 6.3.0.neta #19 RIP: 0010:kfree_skb_list_reason+0x7e/0x1f0 Call Trace: skb_release_data+0xf9/0x1d0 kfree_skb_reason+0x40/0x100 tipc_link_xmit+0x57a/0x740 [tipc] tipc_node_xmit+0x16c/0x5c0 [tipc] tipc_named_node_up+0x27f/0x2c0 [tipc] tipc_node_write_unlock+0x149/0x170 [tipc] tipc_rcv+0x608/0x740 [tipc] tipc_udp_recv+0xdc/0x1f0 [tipc] udp_queue_rcv_one_skb+0x33e/0x620 udp_unicast_rcv_skb.isra.72+0x75/0x90 __udp4_lib_rcv+0x56d/0xc20 ip_protocol_deliver_rcu+0x100/0x2d0 This patch fixes it by checking the new mtu against tipc_bearer_min_mtu(), and not updating mtu if it is too small. Fixes: ed193ece2649 ("tipc: simplify link mtu negotiation") Reported-by: Shuang Li Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index b3ce24823f50..2eff1c7949cb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u32 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0, msg_max; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2239,6 +2239,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, switch (mtyp) { case RESET_MSG: case ACTIVATE_MSG: + msg_max = msg_max_pkt(hdr); + if (msg_max < tipc_bearer_min_mtu(l->net, l->bearer_id)) + break; /* Complete own link name with peer's interface name */ if_name = strrchr(l->name, ':') + 1; if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) @@ -2283,8 +2286,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, l->peer_session = msg_session(hdr); l->in_session = true; l->peer_bearer_id = msg_bearer_id(hdr); - if (l->mtu > msg_max_pkt(hdr)) - l->mtu = msg_max_pkt(hdr); + if (l->mtu > msg_max) + l->mtu = msg_max; break; case STATE_MSG: -- GitLab From 35a089b5d793d2bfd2cc7cfa6104545184de2ce7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 14 May 2023 15:52:29 -0400 Subject: [PATCH 4966/5631] tipc: check the bearer min mtu properly when setting it by netlink Checking the bearer min mtu with tipc_udp_mtu_bad() only works for IPv4 UDP bearer, and IPv6 UDP bearer has a different value for the min mtu. This patch checks with encap_hlen + TIPC_MIN_BEARER_MTU for min mtu, which works for both IPv4 and IPv6 UDP bearer. Note that tipc_udp_mtu_bad() is still used to check media min mtu in __tipc_nl_media_set(), as m->mtu currently is only used by the IPv4 UDP bearer as its default mtu value. Fixes: 682cd3cf946b ("tipc: confgiure and apply UDP bearer MTU on running links") Signed-off-by: Xin Long Acked-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/bearer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 0e9a29e1536b..53881406e200 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1151,8 +1151,8 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } #ifdef CONFIG_TIPC_MEDIA_UDP - if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) { + if (nla_get_u32(props[TIPC_NLA_PROP_MTU]) < + b->encap_hlen + TIPC_MIN_BEARER_MTU) { NL_SET_ERR_MSG(info->extack, "MTU value is out-of-range"); return -EINVAL; -- GitLab From df0acdc59b094cdaef19b1c8d83c9721082bab7b Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Sat, 13 May 2023 22:03:45 +0100 Subject: [PATCH 4967/5631] net: phylink: fix ksettings_set() ethtool call While testing a Fiberstore SFP-10G-T module (which uses 10GBASE-R with rate adaption) in a Clearfog platform (which can't do that) it was found that the PHYs advertisement was not limited according to the hosts capabilities when using ethtool to change it. Fix this by ensuring that we mask the advertisement with the computed support mask as the very first thing we do. Fixes: cbc1bb1e4689 ("net: phylink: simplify phy case for ksettings_set method") Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a4111f1be375..e237949deee6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2225,6 +2225,10 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, ASSERT_RTNL(); + /* Mask out unsupported advertisements */ + linkmode_and(config.advertising, kset->link_modes.advertising, + pl->supported); + if (pl->phydev) { /* We can rely on phylib for this update; we also do not need * to update the pl->link_config settings: @@ -2249,10 +2253,6 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, config = pl->link_config; - /* Mask out unsupported advertisements */ - linkmode_and(config.advertising, kset->link_modes.advertising, - pl->supported); - /* FIXME: should we reject autoneg if phy/mac does not support it? */ switch (kset->base.autoneg) { case AUTONEG_DISABLE: -- GitLab From be3c215342956313845308e0e631341e62370a2b Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Mon, 15 May 2023 13:44:03 +0300 Subject: [PATCH 4968/5631] ASoC: SOF: Separate the tokens for input and output pin index MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Using the same token ID for both input and output format pin index results in collisions and incorrect pin index getting parsed from topology. Signed-off-by: Ranjani Sridharan Date: Mon, 15 May 2023 11:52:00 +0300 Subject: [PATCH 4969/5631] ASoC: SOF: topology: Fix tuples array allocation The memory allocated for the tuples array assumes that there's 1 instance of all tokens already. So for those tokens that have multiple instances in topology, we need to exclude the initial instance that has already been accounted for. Fixes: 4fdef47a44d6 ("ASoC: SOF: ipc4-topology: Add new tokens for input/output pin format count") Signed-off-by: Ranjani Sridharan 1) { struct snd_sof_tuple *new_tuples; - num_tuples += token_list[object_token_list[i]].count * num_sets; + num_tuples += token_list[object_token_list[i]].count * (num_sets - 1); new_tuples = krealloc(swidget->tuples, sizeof(*new_tuples) * num_tuples, GFP_KERNEL); if (!new_tuples) { -- GitLab From 21a3f3328972bdb774c62b301a715b5cebf03fa2 Mon Sep 17 00:00:00 2001 From: Azeem Shaikh Date: Mon, 15 May 2023 02:40:44 +0000 Subject: [PATCH 4970/5631] NFSD: Remove open coding of string copy Instead of open coding a __dynamic_array(), use the __string() and __assign_str() helper macros that exist for this kind of use case. Part of an effort to remove deprecated strlcpy() [1] completely from the kernel[2]. [1] https://www.kernel.org/doc/html/latest/process/deprecated.html#strlcpy [2] https://github.com/KSPP/linux/issues/89 Fixes: 3c92fba557c6 ("NFSD: Enhance the nfsd_cb_setup tracepoint") Signed-off-by: Azeem Shaikh Reviewed-by: Jeff Layton Signed-off-by: Chuck Lever --- fs/nfsd/trace.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 4183819ea082..72a906a053dc 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -1365,19 +1365,19 @@ TRACE_EVENT(nfsd_cb_setup, __field(u32, cl_id) __field(unsigned long, authflavor) __sockaddr(addr, clp->cl_cb_conn.cb_addrlen) - __array(unsigned char, netid, 8) + __string(netid, netid) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; __entry->cl_id = clp->cl_clientid.cl_id; - strlcpy(__entry->netid, netid, sizeof(__entry->netid)); + __assign_str(netid, netid); __entry->authflavor = authflavor; __assign_sockaddr(addr, &clp->cl_cb_conn.cb_addr, clp->cl_cb_conn.cb_addrlen) ), TP_printk("addr=%pISpc client %08x:%08x proto=%s flavor=%s", __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, - __entry->netid, show_nfsd_authflavor(__entry->authflavor)) + __get_str(netid), show_nfsd_authflavor(__entry->authflavor)) ); TRACE_EVENT(nfsd_cb_setup_err, -- GitLab From 8703dd6b238da0ec6c276e53836f8200983d3d9b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 20 Apr 2023 13:31:29 +0200 Subject: [PATCH 4971/5631] s390/crypto: use vector instructions only if available for ChaCha20 Commit 349d03ffd5f6 ("crypto: s390 - add crypto library interface for ChaCha20") added a library interface to the s390 specific ChaCha20 implementation. However no check was added to verify if the required facilities are installed before branching into the assembler code. If compiled into the kernel, this will lead to the following crash, if vector instructions are not available: data exception: 0007 ilc:3 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc7+ #11 Hardware name: IBM 3931 A01 704 (KVM/Linux) Krnl PSW : 0704e00180000000 000000001857277a (chacha20_vx+0x32/0x818) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0000037f0000000a ffffffffffffff60 000000008184b000 0000000019f5c8e6 0000000000000109 0000037fffb13c58 0000037fffb13c78 0000000019bb1780 0000037fffb13c58 0000000019f5c8e6 000000008184b000 0000000000000109 00000000802d8000 0000000000000109 0000000018571ebc 0000037fffb13718 Krnl Code: 000000001857276a: c07000b1f80b larl %r7,0000000019bb1780 0000000018572770: a708000a lhi %r0,10 #0000000018572774: e78950000c36 vlm %v24,%v25,0(%r5),0 >000000001857277a: e7a060000806 vl %v26,0(%r6),0 0000000018572780: e7bf70004c36 vlm %v27,%v31,0(%r7),4 0000000018572786: e70b00000456 vlr %v0,%v27 000000001857278c: e71800000456 vlr %v1,%v24 0000000018572792: e74b00000456 vlr %v4,%v27 Call Trace: [<000000001857277a>] chacha20_vx+0x32/0x818 Last Breaking-Event-Address: [<0000000018571eb6>] chacha20_crypt_s390.constprop.0+0x6e/0xd8 ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Fix this by adding a missing MACHINE_HAS_VX check. Fixes: 349d03ffd5f6 ("crypto: s390 - add crypto library interface for ChaCha20") Reported-by: Marc Hartmayer Cc: # 5.19+ Reviewed-by: Harald Freudenberger [agordeev@linux.ibm.com: remove duplicates in commit message] Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/crypto/chacha-glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index 7752bd314558..5fae187f947a 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -82,7 +82,7 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, * it cannot handle a block of data or less, but otherwise * it can handle data of arbitrary size */ - if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20) + if (bytes <= CHACHA_BLOCK_SIZE || nrounds != 20 || !MACHINE_HAS_VX) chacha_crypt_generic(state, dst, src, bytes, nrounds); else chacha20_crypt_s390(state, dst, src, bytes, -- GitLab From 844cf829e5f33e00b279230470c8c93b58b8c16f Mon Sep 17 00:00:00 2001 From: Holger Dengler Date: Thu, 20 Apr 2023 14:34:10 +0200 Subject: [PATCH 4972/5631] s390/pkey: zeroize key blobs Key blobs for the IOCTLs PKEY_KBLOB2PROTK[23] may contain clear key material. Zeroize the copies of these keys in kernel memory after creating the protected key. Reviewed-by: Harald Freudenberger Signed-off-by: Holger Dengler Signed-off-by: Alexander Gordeev --- drivers/s390/crypto/pkey_api.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 5a05d1cdfec2..a8def50c149b 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -1293,6 +1293,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return PTR_ERR(kkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1426,6 +1427,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, &ktp.protkey); DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) break; @@ -1552,6 +1554,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, protkey, &protkeylen); DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); + memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) { kfree(protkey); -- GitLab From 124acbe275040809abfa5fbe6e25790a53d5a161 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 4 May 2023 13:40:46 +0200 Subject: [PATCH 4973/5631] s390/defconfigs: set CONFIG_INIT_STACK_NONE=y Set CONFIG_INIT_STACK_NONE=y in defconfigs to avoid the extra overhead of initializing all stack variables by default. Users who want to have that must change the configuration on their own. Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/configs/debug_defconfig | 1 + arch/s390/configs/defconfig | 1 + arch/s390/configs/zfcpdump_defconfig | 1 + 3 files changed, 3 insertions(+) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 4ccf66d29fc2..1b68156f2040 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -703,6 +703,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set CONFIG_CRYPTO_PCRYPT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 693297a2e897..b0643283bbdd 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -686,6 +686,7 @@ CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" +CONFIG_INIT_STACK_NONE=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 33a232bb68af..6f68b39817ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -67,6 +67,7 @@ CONFIG_ZFCP=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +CONFIG_INIT_STACK_NONE=y # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y -- GitLab From b1b0d5aec1cf9f9a900a14964f869c68688d923e Mon Sep 17 00:00:00 2001 From: Vineeth Vijayan Date: Tue, 2 May 2023 11:12:42 +0200 Subject: [PATCH 4974/5631] s390/cio: include subchannels without devices also for evaluation Currently when the new channel-path is enabled, we do evaluation only on the subchannels with a device connected on it. This is because, in the past, if the device in the subchannel is not working or not available, we used to unregister the subchannels. But, from the 'commit 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers")' we allow subchannels with or without an active device connected on it. So, when we do the io_subchannel_verify, make sure that, we are evaluating the subchannels without any device too. Fixes: 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers") Reported-by: Boris Fiuczynski Signed-off-by: Vineeth Vijayan Reviewed-by: Peter Oberparleiter Signed-off-by: Alexander Gordeev --- drivers/s390/cio/device.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 8eb089b99cde..d5c43e9b5128 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -1111,6 +1111,8 @@ static void io_subchannel_verify(struct subchannel *sch) cdev = sch_get_cdev(sch); if (cdev) dev_fsm_event(cdev, DEV_EVENT_VERIFY); + else + css_schedule_eval(sch->schid); } static void io_subchannel_terminate_path(struct subchannel *sch, u8 mask) -- GitLab From a33239be2d38ff5a44427db1707c08787508d34a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Thu, 4 May 2023 16:21:48 +0200 Subject: [PATCH 4975/5631] s390/topology: honour nr_cpu_ids when adding CPUs When SMT thread CPUs are added to CPU masks the nr_cpu_ids limit is not checked and could be exceeded. This leads to a warning for example if CONFIG_DEBUG_PER_CPU_MAPS is set and the command line parameter nr_cpus is set to 1. Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/kernel/topology.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 9fd19530c9a5..68adf1de8888 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -95,7 +95,7 @@ static void cpu_group_map(cpumask_t *dst, struct mask_info *info, unsigned int c static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) { static cpumask_t mask; - int i; + unsigned int max_cpu; cpumask_clear(&mask); if (!cpumask_test_cpu(cpu, &cpu_setup_mask)) @@ -104,9 +104,10 @@ static void cpu_thread_map(cpumask_t *dst, unsigned int cpu) if (topology_mode != TOPOLOGY_MODE_HW) goto out; cpu -= cpu % (smp_cpu_mtid + 1); - for (i = 0; i <= smp_cpu_mtid; i++) { - if (cpumask_test_cpu(cpu + i, &cpu_setup_mask)) - cpumask_set_cpu(cpu + i, &mask); + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + if (cpumask_test_cpu(cpu, &cpu_setup_mask)) + cpumask_set_cpu(cpu, &mask); } out: cpumask_copy(dst, &mask); @@ -123,25 +124,26 @@ static void add_cpus_to_mask(struct topology_core *tl_core, unsigned int core; for_each_set_bit(core, &tl_core->mask, TOPOLOGY_CORE_BITS) { - unsigned int rcore; - int lcpu, i; + unsigned int max_cpu, rcore; + int cpu; rcore = TOPOLOGY_CORE_BITS - 1 - core + tl_core->origin; - lcpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); - if (lcpu < 0) + cpu = smp_find_processor_id(rcore << smp_cpu_mt_shift); + if (cpu < 0) continue; - for (i = 0; i <= smp_cpu_mtid; i++) { - topo = &cpu_topology[lcpu + i]; + max_cpu = min(cpu + smp_cpu_mtid, nr_cpu_ids - 1); + for (; cpu <= max_cpu; cpu++) { + topo = &cpu_topology[cpu]; topo->drawer_id = drawer->id; topo->book_id = book->id; topo->socket_id = socket->id; topo->core_id = rcore; - topo->thread_id = lcpu + i; + topo->thread_id = cpu; topo->dedicated = tl_core->d; - cpumask_set_cpu(lcpu + i, &drawer->mask); - cpumask_set_cpu(lcpu + i, &book->mask); - cpumask_set_cpu(lcpu + i, &socket->mask); - smp_cpu_set_polarization(lcpu + i, tl_core->pp); + cpumask_set_cpu(cpu, &drawer->mask); + cpumask_set_cpu(cpu, &book->mask); + cpumask_set_cpu(cpu, &socket->mask); + smp_cpu_set_polarization(cpu, tl_core->pp); } } } -- GitLab From 2facd5d3980f3a26c04fe6ec8689a1d019a5812c Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Sun, 7 May 2023 18:09:02 +0200 Subject: [PATCH 4976/5631] s390/ipl: fix IPIB virtual vs physical address confusion The pointer to IPL Parameter Information Block is stored in the absolute lowcore for later use by dump tools. That pointer is a virtual address, though it should be physical instead. Note, this does not fix a real issue, since virtual and physical addresses are currently the same. Suggested-by: Heiko Carstens Reviewed-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- arch/s390/kernel/ipl.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 43de939b7af1..f44f70de9661 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1935,14 +1935,13 @@ static struct shutdown_action __refdata dump_action = { static void dump_reipl_run(struct shutdown_trigger *trigger) { - unsigned long ipib = (unsigned long) reipl_block_actual; struct lowcore *abs_lc; unsigned int csum; csum = (__force unsigned int) csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); - abs_lc->ipib = ipib; + abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; put_abs_lowcore(abs_lc); dump_run(trigger); -- GitLab From 71a485624c4cbb144169852d7bb8ca8c0667d7a3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rub=C3=A9n=20G=C3=B3mez?= Date: Mon, 8 May 2023 18:03:07 +0000 Subject: [PATCH 4977/5631] ACPI: resource: Add IRQ override quirk for LG UltraPC 17U70P MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an ACPI IRQ override quirk for LG UltraPC 17U70P to address the internal keyboard problem on it. Link: https://bugzilla.kernel.org/show_bug.cgi?id=213031 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216983 Signed-off-by: Rubén Gómez Agudo [ rjw: Subject, changelog, white space damage fixes ] Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index e8492b3a393a..0800a9d77558 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -516,6 +516,17 @@ static const struct dmi_system_id maingear_laptop[] = { { } }; +static const struct dmi_system_id lg_laptop[] = { + { + .ident = "LG Electronics 17U70P", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "17U70P"), + }, + }, + { } +}; + struct irq_override_cmp { const struct dmi_system_id *system; unsigned char irq; @@ -532,6 +543,7 @@ static const struct irq_override_cmp override_table[] = { { lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true }, { tongfang_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, { maingear_laptop, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true }, + { lg_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false }, }; static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, -- GitLab From 8133a3f0aa66ed3d7d974c89ac6aca6fe6cec837 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Mon, 15 May 2023 22:40:08 +1000 Subject: [PATCH 4978/5631] powerpc/crypto: Fix aes-gcm-p10 build when VSX=n MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When VSX is disabled, eg. microwatt_defconfig, the build fails with: In function ‘enable_kernel_vsx’, inlined from ‘vsx_begin’ at arch/powerpc/crypto/aes-gcm-p10-glue.c:68:2, inlined from ‘p10_aes_gcm_crypt.constprop’ at arch/powerpc/crypto/aes-gcm-p10-glue.c:244:2: ... arch/powerpc/include/asm/switch_to.h:86:9: note: in expansion of macro ‘BUILD_BUG’ 86 | BUILD_BUG(); | ^~~~~~~~~ Fix it by making the p10-aes-gcm code depend on VSX. Signed-off-by: Michael Ellerman Link: https://msgid.link/20230515124731.122962-1-mpe%40ellerman.id.au --- arch/powerpc/crypto/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7113f9355165..ad1872518992 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -96,7 +96,7 @@ config CRYPTO_AES_PPC_SPE config CRYPTO_AES_GCM_P10 tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)" - depends on PPC64 && CPU_LITTLE_ENDIAN + depends on PPC64 && CPU_LITTLE_ENDIAN && VSX select CRYPTO_LIB_AES select CRYPTO_ALGAPI select CRYPTO_AEAD -- GitLab From 362c1f2ec82cb65940e1c73e15a395a7a891fc6f Mon Sep 17 00:00:00 2001 From: Alexandru Sorodoc Date: Fri, 12 May 2023 13:15:17 +0300 Subject: [PATCH 4979/5631] platform/x86: asus-wmi: Ignore WMI events with codes 0x7B, 0xC0 On ASUS GU604V the key 0x7B is issued when the charger is connected or disconnected, and key 0xC0 is issued when an external display is connected or disconnected. This commit maps them to KE_IGNORE to slience kernel messages about unknown keys, such as: kernel: asus_wmi: Unknown key code 0x7b Signed-off-by: Alexandru Sorodoc Link: https://lore.kernel.org/r/20230512101517.47416-1-ealex95@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-nb-wmi.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index e2c9a68d12df..fdf7da06af30 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -555,6 +555,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x71, { KEY_F13 } }, /* General-purpose button */ { KE_IGNORE, 0x79, }, /* Charger type dectection notification */ { KE_KEY, 0x7a, { KEY_ALS_TOGGLE } }, /* Ambient Light Sensor Toggle */ + { KE_IGNORE, 0x7B, }, /* Charger connect/disconnect notification */ { KE_KEY, 0x7c, { KEY_MICMUTE } }, { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ @@ -584,6 +585,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xAE, { KEY_FN_F5 } }, /* Fn+F5 fan mode on 2020+ */ { KE_KEY, 0xB3, { KEY_PROG4 } }, /* AURA */ { KE_KEY, 0xB5, { KEY_CALC } }, + { KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */ { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ -- GitLab From b54147fa374dbeadcb01b1762db1a793e06e37de Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 12 May 2023 20:14:08 -0500 Subject: [PATCH 4980/5631] platform/x86/amd/pmf: Fix CnQF and auto-mode after resume After suspend/resume cycle there is an error message and auto-mode or CnQF stops working. [ 5741.447511] amd-pmf AMDI0100:00: SMU cmd failed. err: 0xff [ 5741.447523] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_RESPONSE:ff [ 5741.447527] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_ARGUMENT:7 [ 5741.447531] amd-pmf AMDI0100:00: AMD_PMF_REGISTER_MESSAGE:16 [ 5741.447540] amd-pmf AMDI0100:00: [AUTO_MODE] avg power: 0 mW mode: QUIET This is because the DRAM address used for accessing metrics table needs to be refreshed after a suspend resume cycle. Add a resume callback to reset this again. Fixes: 1a409b35c995 ("platform/x86/amd/pmf: Get performance metrics from PMFW") Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20230513011408.958-1-mario.limonciello@amd.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/amd/pmf/core.c | 32 ++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index d5bb775dadcf..ee5f124f78b6 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -245,24 +245,29 @@ static const struct pci_device_id pmf_pci_ids[] = { { } }; -int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +static void amd_pmf_set_dram_addr(struct amd_pmf_dev *dev) { u64 phys_addr; u32 hi, low; - INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); + phys_addr = virt_to_phys(dev->buf); + hi = phys_addr >> 32; + low = phys_addr & GENMASK(31, 0); + + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); + amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); +} +int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) +{ /* Get Metrics Table Address */ dev->buf = kzalloc(sizeof(dev->m_table), GFP_KERNEL); if (!dev->buf) return -ENOMEM; - phys_addr = virt_to_phys(dev->buf); - hi = phys_addr >> 32; - low = phys_addr & GENMASK(31, 0); + INIT_DELAYED_WORK(&dev->work_buffer, amd_pmf_get_metrics); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_HIGH, 0, hi, NULL); - amd_pmf_send_cmd(dev, SET_DRAM_ADDR_LOW, 0, low, NULL); + amd_pmf_set_dram_addr(dev); /* * Start collecting the metrics data after a small delay @@ -273,6 +278,18 @@ int amd_pmf_init_metrics_table(struct amd_pmf_dev *dev) return 0; } +static int amd_pmf_resume_handler(struct device *dev) +{ + struct amd_pmf_dev *pdev = dev_get_drvdata(dev); + + if (pdev->buf) + amd_pmf_set_dram_addr(pdev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmf_pm, NULL, amd_pmf_resume_handler); + static void amd_pmf_init_features(struct amd_pmf_dev *dev) { int ret; @@ -413,6 +430,7 @@ static struct platform_driver amd_pmf_driver = { .name = "amd-pmf", .acpi_match_table = amd_pmf_acpi_ids, .dev_groups = amd_pmf_driver_groups, + .pm = pm_sleep_ptr(&amd_pmf_pm), }, .probe = amd_pmf_probe, .remove_new = amd_pmf_remove, -- GitLab From 95e4b25192e9238fd2dbe85d96dd2f8fd1ce9d14 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 15 May 2023 13:32:37 +0300 Subject: [PATCH 4981/5631] platform/mellanox: mlxbf-pmc: fix sscanf() error checking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sscanf() function never returns negatives. It returns the number of items successfully read. Fixes: 1a218d312e65 ("platform/mellanox: mlxbf-pmc: Add Mellanox BlueField PMC driver") Signed-off-by: Dan Carpenter Reviewed-by: Ilpo Järvinen Link: https://lore.kernel.org/r/4ccdfd28-099b-40bf-8d77-ad4ea2e76b93@kili.mountain Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/mellanox/mlxbf-pmc.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index c2c9b0d3244c..be967d797c28 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1348,9 +1348,8 @@ static int mlxbf_pmc_map_counters(struct device *dev) for (i = 0; i < pmc->total_blocks; ++i) { if (strstr(pmc->block_name[i], "tile")) { - ret = sscanf(pmc->block_name[i], "tile%d", &tile_num); - if (ret < 0) - return ret; + if (sscanf(pmc->block_name[i], "tile%d", &tile_num) != 1) + return -EINVAL; if (tile_num >= pmc->tile_count) continue; -- GitLab From e1505c1cc8d527fcc5bcaf9c1ad82eed817e3e10 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 5 May 2023 14:58:36 -0700 Subject: [PATCH 4982/5631] bpf: netdev: init the offload table earlier Some netdevices may get unregistered before late_initcall(), we have to move the hashtable init earlier. Fixes: f1fc43d03946 ("bpf: Move offload initialization into late_initcall") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217399 Signed-off-by: Jakub Kicinski Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20230505215836.491485-1-kuba@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/bpf/offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index d9c9f45e3529..8a26cd8814c1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -859,4 +859,4 @@ static int __init bpf_offload_init(void) return rhashtable_init(&offdevs, &offdevs_params); } -late_initcall(bpf_offload_init); +core_initcall(bpf_offload_init); -- GitLab From 73c7f8246539da12c76bb731a2fe7389ae55eae8 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 11 May 2023 14:53:12 +0200 Subject: [PATCH 4983/5631] cpufreq: ACPI: Prevent a warning when another frequency driver is loaded The recent change to use platform devices to load ACPI PPC and PCC drivers caused that a misleading warning is reported when a respective module cannot be loaded because another CPU frequency driver is already registered: kernel: acpi-cpufreq: probe of acpi-cpufreq failed with error -17 Address it by changing the return code in acpi-cpufreq and pcc-cpufreq for this case from -EEXIST to -ENODEV which silences the warning in call_driver_probe(). The change has also a benefit for users of init_module() as this return code is propagated out from the syscall. The previous -EEXIST code made the callers, such as kmod, wrongly believe that the module was already loaded instead of that it failed to load. Fixes: 691a63712347 ("ACPI: cpufreq: Use platform devices to load ACPI PPC and PCC drivers") Reported-by: Kevin Locke Link: https://lore.kernel.org/lkml/ZFreh8SDMX67EaB6@kevinlocke.name/ Signed-off-by: Petr Pavlu Tested-by: Kevin Locke Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 2 +- drivers/cpufreq/pcc-cpufreq.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 29904395e95f..b2f05d27167e 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -975,7 +975,7 @@ static int __init acpi_cpufreq_probe(struct platform_device *pdev) /* don't keep reloading if cpufreq_driver exists */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; pr_debug("%s\n", __func__); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 1d2cfea9858a..73efbcf5513b 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -583,7 +583,7 @@ static int __init pcc_cpufreq_probe(struct platform_device *pdev) /* Skip initialization if another cpufreq driver is there. */ if (cpufreq_get_current_driver()) - return -EEXIST; + return -ENODEV; if (acpi_disabled) return -ENODEV; -- GitLab From 8e4942db5f5ed7b7d9690d93235b3ca49c5c59ce Mon Sep 17 00:00:00 2001 From: Ping-Ke Shih Date: Mon, 8 May 2023 16:55:39 +0800 Subject: [PATCH 4984/5631] wifi: rtw88: correct qsel_to_ep[] type as int qsel_to_ep[] can be assigned negative value, so change type from 'u8' to 'int'. Otherwise, Smatch static checker warns: drivers/net/wireless/realtek/rtw88/usb.c:219 rtw_usb_parse() warn: assigning (-22) to unsigned variable 'rtwusb->qsel_to_ep[8]' Cc: stable@vger.kernel.org Fixes: a6f187f92bcc ("wifi: rtw88: usb: fix priority queue to endpoint mapping") Reported-by: Dan Carpenter Link: https://lore.kernel.org/linux-wireless/c3f70197-829d-48ed-ae15-66a9de80fa90@kili.mountain/ Cc: Sascha Hauer Signed-off-by: Ping-Ke Shih Acked-by: Sascha Hauer Tested-by: Larry Finger Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230508085539.46795-1-pkshih@realtek.com --- drivers/net/wireless/realtek/rtw88/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtw88/usb.h b/drivers/net/wireless/realtek/rtw88/usb.h index 30647f0dd61c..ad1d7955c6a5 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.h +++ b/drivers/net/wireless/realtek/rtw88/usb.h @@ -78,7 +78,7 @@ struct rtw_usb { u8 pipe_interrupt; u8 pipe_in; u8 out_ep[RTW_USB_EP_MAX]; - u8 qsel_to_ep[TX_DESC_QSEL_MAX]; + int qsel_to_ep[TX_DESC_QSEL_MAX]; u8 usb_txagg_num; struct workqueue_struct *txwq, *rxwq; -- GitLab From 60fc756fc8e6954a5618eecac73b255d651602e4 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 10 May 2023 16:18:56 +0200 Subject: [PATCH 4985/5631] wifi: brcmfmac: Check for probe() id argument being NULL The probe() id argument may be NULL in 2 scenarios: 1. brcmf_pcie_pm_leave_D3() calling brcmf_pcie_probe() to reprobe the device. 2. If a user tries to manually bind the driver from sysfs then the sdio / pcie / usb probe() function gets called with NULL as id argument. 1. Is being hit by users causing the following oops on resume and causing wifi to stop working: BUG: kernel NULL pointer dereference, address: 0000000000000018 Hardware name: Dell Inc. XPS 13 9350/0PWNCR, BIDS 1.13.0 02/10/2020 Workgueue: events_unbound async_run_entry_fn RIP: 0010:brcmf_pcie_probe+Ox16b/0x7a0 [brcmfmac] Call Trace: brcmf_pcie_pm_leave_D3+0xc5/8x1a0 [brcmfmac be3b4cefca451e190fa35be8f00db1bbec293887] ? pci_pm_resume+0x5b/0xf0 ? pci_legacy_resume+0x80/0x80 dpm_run_callback+0x47/0x150 device_resume+0xa2/0x1f0 async_resume+0x1d/0x30 Fix this by checking for id being NULL. In the PCI and USB cases try a manual lookup of the id so that manually binding the driver through sysfs and more importantly brcmf_pcie_probe() on resume will work. For the SDIO case there is no helper to do a manual sdio_device_id lookup, so just directly error out on a NULL id there. Fixes: da6d9c8ecd00 ("wifi: brcmfmac: add firmware vendor info in driver info") Reported-by: Felix Link: https://lore.kernel.org/regressions/4ef3f252ff530cbfa336f5a0d80710020fc5cb1e.camel@gmail.com/ Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Reviewed-by: Arend van Spriel Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230510141856.46532-1-hdegoede@redhat.com --- .../net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 5 +++++ .../net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 11 +++++++++++ .../net/wireless/broadcom/brcm80211/brcmfmac/usb.c | 11 +++++++++++ 3 files changed, 27 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index ff710b0b5071..00679a990e3d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -1039,6 +1039,11 @@ static int brcmf_ops_sdio_probe(struct sdio_func *func, struct brcmf_sdio_dev *sdiodev; struct brcmf_bus *bus_if; + if (!id) { + dev_err(&func->dev, "Error no sdio_device_id passed for %x:%x\n", func->vendor, func->device); + return -ENODEV; + } + brcmf_dbg(SDIO, "Enter\n"); brcmf_dbg(SDIO, "Class=%x\n", func->class); brcmf_dbg(SDIO, "sdio vendor ID: 0x%04x\n", func->vendor); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 59f3e9c5e139..80220685f5e4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -2394,6 +2394,9 @@ static void brcmf_pcie_debugfs_create(struct device *dev) } #endif +/* Forward declaration for pci_match_id() call */ +static const struct pci_device_id brcmf_pcie_devid_table[]; + static int brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -2404,6 +2407,14 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct brcmf_core *core; struct brcmf_bus *bus; + if (!id) { + id = pci_match_id(brcmf_pcie_devid_table, pdev); + if (!id) { + pci_err(pdev, "Error could not find pci_device_id for %x:%x\n", pdev->vendor, pdev->device); + return -ENODEV; + } + } + brcmf_dbg(PCIE, "Enter %x:%x\n", pdev->vendor, pdev->device); ret = -ENOMEM; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index 246843aeb696..2178675ae1a4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1331,6 +1331,9 @@ brcmf_usb_disconnect_cb(struct brcmf_usbdev_info *devinfo) brcmf_usb_detach(devinfo); } +/* Forward declaration for usb_match_id() call */ +static const struct usb_device_id brcmf_usb_devid_table[]; + static int brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -1342,6 +1345,14 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) u32 num_of_eps; u8 endpoint_num, ep; + if (!id) { + id = usb_match_id(intf, brcmf_usb_devid_table); + if (!id) { + dev_err(&intf->dev, "Error could not find matching usb_device_id\n"); + return -ENODEV; + } + } + brcmf_dbg(USB, "Enter 0x%04x:0x%04x\n", id->idVendor, id->idProduct); devinfo = kzalloc(sizeof(*devinfo), GFP_ATOMIC); -- GitLab From 20429444e653ee8242dfbf815c0c37866beb371b Mon Sep 17 00:00:00 2001 From: Yun Lu Date: Fri, 12 May 2023 09:20:55 +0800 Subject: [PATCH 4986/5631] wifi: rtl8xxxu: fix authentication timeout due to incorrect RCR value When using rtl8192cu with rtl8xxxu driver to connect wifi, there is a probability of failure, which shows "authentication with ... timed out". Through debugging, it was found that the RCR register has been inexplicably modified to an incorrect value, resulting in the nic not being able to receive authenticated frames. To fix this problem, add regrcr in rtl8xxxu_priv struct, and store the RCR value every time the register is written, and use it the next time the register need to be modified. Signed-off-by: Yun Lu Link: https://lore.kernel.org/all/20230427020512.1221062-1-luyun_611@163.com Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230512012055.2990472-1-luyun_611@163.com --- drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h | 1 + drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 8eafbf1cee71..808c1c895113 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1803,6 +1803,7 @@ struct rtl8xxxu_priv { u32 rege9c; u32 regeb4; u32 regebc; + u32 regrcr; int next_mbox; int nr_out_eps; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index fd8c8c6d53d6..831639d73657 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4171,6 +4171,7 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) RCR_ACCEPT_MGMT_FRAME | RCR_HTC_LOC_CTRL | RCR_APPEND_PHYSTAT | RCR_APPEND_ICV | RCR_APPEND_MIC; rtl8xxxu_write32(priv, REG_RCR, val32); + priv->regrcr = val32; if (fops->init_reg_rxfltmap) { /* Accept all data frames */ @@ -6501,7 +6502,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, unsigned int *total_flags, u64 multicast) { struct rtl8xxxu_priv *priv = hw->priv; - u32 rcr = rtl8xxxu_read32(priv, REG_RCR); + u32 rcr = priv->regrcr; dev_dbg(&priv->udev->dev, "%s: changed_flags %08x, total_flags %08x\n", __func__, changed_flags, *total_flags); @@ -6547,6 +6548,7 @@ static void rtl8xxxu_configure_filter(struct ieee80211_hw *hw, */ rtl8xxxu_write32(priv, REG_RCR, rcr); + priv->regrcr = rcr; *total_flags &= (FIF_ALLMULTI | FIF_FCSFAIL | FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL | FIF_OTHER_BSS | FIF_PSPOLL | -- GitLab From db2773d65b02aed319a93efdfb958087771d4e19 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 4987/5631] can: isotp: recvmsg(): allow MSG_CMSG_COMPAT flag The control message provided by isotp support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Fixes: 42bf50a1795a ("can: isotp: support MSG_TRUNC flag when reading from socket") Link: https://lore.kernel.org/20230505110308.81087-2-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/isotp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/isotp.c b/net/can/isotp.c index a750259cb79c..84f9aba02901 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1139,7 +1139,7 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, struct isotp_sock *so = isotp_sk(sk); int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK)) + if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) -- GitLab From 1db080cbdbab28752bbb1c86d64daf96253a5da1 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Thu, 6 Apr 2023 13:08:45 +0200 Subject: [PATCH 4988/5631] can: j1939: recvmsg(): allow MSG_CMSG_COMPAT flag The control message provided by J1939 support MSG_CMSG_COMPAT but blocked recvmsg() syscalls that have set this flag, i.e. on 32bit user space on 64 bit kernels. Link: https://github.com/hartkopp/can-isotp/issues/59 Cc: Oleksij Rempel Suggested-by: Marc Kleine-Budde Signed-off-by: Oliver Hartkopp Tested-by: Oleksij Rempel Acked-by: Oleksij Rempel Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/20230505110308.81087-3-mkl@pengutronix.de Cc: stable@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- net/can/j1939/socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 7e90f9e61d9b..1790469b2580 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -798,7 +798,7 @@ static int j1939_sk_recvmsg(struct socket *sock, struct msghdr *msg, struct j1939_sk_buff_cb *skcb; int ret = 0; - if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE)) + if (flags & ~(MSG_DONTWAIT | MSG_ERRQUEUE | MSG_CMSG_COMPAT)) return -EINVAL; if (flags & MSG_ERRQUEUE) -- GitLab From 6bffdc38f9935bae49f980448f3f6be2dada0564 Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 6 May 2023 20:45:15 +0200 Subject: [PATCH 4989/5631] can: dev: fix missing CAN XL support in can_put_echo_skb() can_put_echo_skb() checks for the enabled IFF_ECHO flag and the correct ETH_P type of the given skbuff. When implementing the CAN XL support the new check for ETH_P_CANXL has been forgotten. Fixes: fb08cba12b52 ("can: canxl: update CAN infrastructure for CAN XL frames") Signed-off-by: Oliver Hartkopp Link: https://lore.kernel.org/all/20230506184515.39241-1-socketcan@hartkopp.net Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/skb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 241ec636e91f..f6d05b3ef59a 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -54,7 +54,8 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, /* check flag whether this packet has to be looped back */ if (!(dev->flags & IFF_ECHO) || (skb->protocol != htons(ETH_P_CAN) && - skb->protocol != htons(ETH_P_CANFD))) { + skb->protocol != htons(ETH_P_CANFD) && + skb->protocol != htons(ETH_P_CANXL))) { kfree_skb(skb); return 0; } -- GitLab From 4920bded3ee077c99cd52666519cb50f9ee35b26 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 4 Apr 2023 13:59:00 +0200 Subject: [PATCH 4990/5631] can: CAN_BXCAN should depend on ARCH_STM32 The STMicroelectronics STM32 basic extended CAN Controller (bxCAN) is only present on STM32 SoCs. Hence drop the "|| OF" part from its dependency rule, to prevent asking the user about this driver when configuring a kernel without STM32 SoC support. Fixes: f00647d8127be4d3 ("can: bxcan: add support for ST bxCAN controller") Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Link: https://lore.kernel.org/all/40095112efd1b2214e4223109fd9f0c6d0158a2d.1680609318.git.geert+renesas@glider.be Signed-off-by: Marc Kleine-Budde --- drivers/net/can/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 3ceccafd701b..b190007c01be 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -95,7 +95,7 @@ config CAN_AT91 config CAN_BXCAN tristate "STM32 Basic Extended CAN (bxCAN) devices" - depends on OF || ARCH_STM32 || COMPILE_TEST + depends on ARCH_STM32 || COMPILE_TEST depends on HAS_IOMEM select CAN_RX_OFFLOAD help -- GitLab From caf78f0f491981893b6a5a71c9dabd2734909c4a Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:36 +0200 Subject: [PATCH 4991/5631] dt-bindings: net: can: add "st,can-secondary" property On the stm32f7 Socs the can peripheral can be in single or dual configuration. In the dual configuration, in turn, it can be in primary or secondary mode. The addition of the 'st,can-secondary' property allows you to specify this mode in the dual configuration. CAN peripheral nodes in single configuration contain neither "st,can-primary" nor "st,can-secondary". Signed-off-by: Dario Binacchi Reviewed-by: Rob Herring Link: https://lore.kernel.org/all/20230427204540.3126234-2-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- .../bindings/net/can/st,stm32-bxcan.yaml | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index 769fa5c27b76..de1d4298893b 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -21,11 +21,22 @@ properties: st,can-primary: description: - Primary and secondary mode of the bxCAN peripheral is only relevant - if the chip has two CAN peripherals. In that case they share some - of the required logic. + Primary mode of the bxCAN peripheral is only relevant if the chip has + two CAN peripherals in dual CAN configuration. In that case they share + some of the required logic. + Not to be used if the peripheral is in single CAN configuration. To avoid misunderstandings, it should be noted that ST documentation - uses the terms master/slave instead of primary/secondary. + uses the terms master instead of primary. + type: boolean + + st,can-secondary: + description: + Secondary mode of the bxCAN peripheral is only relevant if the chip + has two CAN peripherals in dual CAN configuration. In that case they + share some of the required logic. + Not to be used if the peripheral is in single CAN configuration. + To avoid misunderstandings, it should be noted that ST documentation + uses the terms slave instead of secondary. type: boolean reg: -- GitLab From 6b443faa313c519db755ff90be32758fd9c66453 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:37 +0200 Subject: [PATCH 4992/5631] ARM: dts: stm32f429: put can2 in secondary mode This is a preparation patch for the upcoming support to manage CAN peripherals in single configuration. The addition ensures backwards compatibility. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-3-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f429.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/boot/dts/stm32f429.dtsi b/arch/arm/boot/dts/stm32f429.dtsi index c9e05e3540d6..00bf53f99c29 100644 --- a/arch/arm/boot/dts/stm32f429.dtsi +++ b/arch/arm/boot/dts/stm32f429.dtsi @@ -387,6 +387,7 @@ interrupt-names = "tx", "rx0", "rx1", "sce"; resets = <&rcc STM32F4_APB1_RESET(CAN2)>; clocks = <&rcc 0 STM32F4_APB1_CLOCK(CAN2)>; + st,can-secondary; st,gcan = <&gcan>; status = "disabled"; }; -- GitLab From 011644249686f2675e142519cd59e81e04cfc231 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:38 +0200 Subject: [PATCH 4993/5631] ARM: dts: stm32: add pin map for CAN controller on stm32f7 Add pin configurations for using CAN controller on stm32f7. Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-4-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f7-pinctrl.dtsi | 82 ++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) diff --git a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi index c8e6c52fb248..9f65403295ca 100644 --- a/arch/arm/boot/dts/stm32f7-pinctrl.dtsi +++ b/arch/arm/boot/dts/stm32f7-pinctrl.dtsi @@ -283,6 +283,88 @@ slew-rate = <2>; }; }; + + can1_pins_a: can1-0 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_b: can1-1 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + }; + }; + + can1_pins_c: can1-2 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can1_pins_d: can1-3 { + pins1 { + pinmux = ; /* CAN1_TX */ + }; + pins2 { + pinmux = ; /* CAN1_RX */ + bias-pull-up; + + }; + }; + + can2_pins_a: can2-0 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can2_pins_b: can2-1 { + pins1 { + pinmux = ; /* CAN2_TX */ + }; + pins2 { + pinmux = ; /* CAN2_RX */ + bias-pull-up; + }; + }; + + can3_pins_a: can3-0 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; + + can3_pins_b: can3-1 { + pins1 { + pinmux = ; /* CAN3_TX */ + }; + pins2 { + pinmux = ; /* CAN3_RX */ + bias-pull-up; + }; + }; }; }; }; -- GitLab From 85a79b971164c4636b2db7f4aef9788142e3f885 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:39 +0200 Subject: [PATCH 4994/5631] can: bxcan: add support for single peripheral configuration Add support for bxCAN controller in single peripheral configuration: - primary bxCAN - dedicated Memory Access Controller unit - 512-byte SRAM memory - 14 filter banks Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-5-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/bxcan.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index e26ccd41e3cb..027a8a162fe4 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -118,7 +118,7 @@ #define BXCAN_FiR1_REG(b) (0x40 + (b) * 8) #define BXCAN_FiR2_REG(b) (0x44 + (b) * 8) -#define BXCAN_FILTER_ID(primary) (primary ? 0 : 14) +#define BXCAN_FILTER_ID(cfg) ((cfg) == BXCAN_CFG_DUAL_SECONDARY ? 14 : 0) /* Filter primary register (FMR) bits */ #define BXCAN_FMR_CANSB_MASK GENMASK(13, 8) @@ -135,6 +135,12 @@ enum bxcan_lec_code { BXCAN_LEC_UNUSED }; +enum bxcan_cfg { + BXCAN_CFG_SINGLE = 0, + BXCAN_CFG_DUAL_PRIMARY, + BXCAN_CFG_DUAL_SECONDARY +}; + /* Structure of the message buffer */ struct bxcan_mb { u32 id; /* can identifier */ @@ -167,7 +173,7 @@ struct bxcan_priv { struct regmap *gcan; int tx_irq; int sce_irq; - bool primary; + enum bxcan_cfg cfg; struct clk *clk; spinlock_t rmw_lock; /* lock for read-modify-write operations */ unsigned int tx_head; @@ -202,17 +208,17 @@ static inline void bxcan_rmw(struct bxcan_priv *priv, void __iomem *addr, spin_unlock_irqrestore(&priv->rmw_lock, flags); } -static void bxcan_disable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_disable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); regmap_update_bits(priv->gcan, BXCAN_FA1R_REG, fmask, 0); } -static void bxcan_enable_filters(struct bxcan_priv *priv, bool primary) +static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) { - unsigned int fid = BXCAN_FILTER_ID(primary); + unsigned int fid = BXCAN_FILTER_ID(cfg); u32 fmask = BIT(fid); /* Filter settings: @@ -680,7 +686,7 @@ static int bxcan_chip_start(struct net_device *ndev) BXCAN_BTR_BRP_MASK | BXCAN_BTR_TS1_MASK | BXCAN_BTR_TS2_MASK | BXCAN_BTR_SJW_MASK, set); - bxcan_enable_filters(priv, priv->primary); + bxcan_enable_filters(priv, priv->cfg); /* Clear all internal status */ priv->tx_head = 0; @@ -806,7 +812,7 @@ static void bxcan_chip_stop(struct net_device *ndev) BXCAN_IER_EPVIE | BXCAN_IER_EWGIE | BXCAN_IER_FOVIE1 | BXCAN_IER_FFIE1 | BXCAN_IER_FMPIE1 | BXCAN_IER_FOVIE0 | BXCAN_IER_FFIE0 | BXCAN_IER_FMPIE0 | BXCAN_IER_TMEIE, 0); - bxcan_disable_filters(priv, priv->primary); + bxcan_disable_filters(priv, priv->cfg); bxcan_enter_sleep_mode(priv); priv->can.state = CAN_STATE_STOPPED; } @@ -931,7 +937,7 @@ static int bxcan_probe(struct platform_device *pdev) struct clk *clk = NULL; void __iomem *regs; struct regmap *gcan; - bool primary; + enum bxcan_cfg cfg; int err, rx_irq, tx_irq, sce_irq; regs = devm_platform_ioremap_resource(pdev, 0); @@ -946,7 +952,13 @@ static int bxcan_probe(struct platform_device *pdev) return PTR_ERR(gcan); } - primary = of_property_read_bool(np, "st,can-primary"); + if (of_property_read_bool(np, "st,can-primary")) + cfg = BXCAN_CFG_DUAL_PRIMARY; + else if (of_property_read_bool(np, "st,can-secondary")) + cfg = BXCAN_CFG_DUAL_SECONDARY; + else + cfg = BXCAN_CFG_SINGLE; + clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { dev_err(dev, "failed to get clock\n"); @@ -992,7 +1004,7 @@ static int bxcan_probe(struct platform_device *pdev) priv->clk = clk; priv->tx_irq = tx_irq; priv->sce_irq = sce_irq; - priv->primary = primary; + priv->cfg = cfg; priv->can.clock.freq = clk_get_rate(clk); spin_lock_init(&priv->rmw_lock); priv->tx_head = 0; -- GitLab From 0920ccdf41e3078a4dd2567eb905ea154bc826e6 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 27 Apr 2023 22:45:40 +0200 Subject: [PATCH 4995/5631] ARM: dts: stm32: add CAN support on stm32f746 Add support for bxcan (Basic eXtended CAN controller) to STM32F746. The chip contains three CAN peripherals, CAN1 and CAN2 in dual peripheral configuration and CAN3 in single peripheral configuration: - Dual CAN peripheral configuration: * CAN1: Primary bxCAN for managing the communication between a secondary bxCAN and the 512-byte SRAM memory. * CAN2: Secondary bxCAN with no direct access to the SRAM memory. This means that the two bxCAN cells share the 512-byte SRAM memory and CAN2 can't be used without enabling CAN1. - Single CAN peripheral configuration: * CAN3: Primary bxCAN with dedicated Memory Access Controller unit and 512-byte SRAM memory. ------------------------------------------------------------------------- | features | CAN1 | CAN2 | CAN 3 | ------------------------------------------------------------------------- | SRAM | 512-byte shared between CAN1 & CAN2 | 512-byte | ------------------------------------------------------------------------- | Filters | 26 filters shared between CAN1 & CAN2 | 14 filters | ------------------------------------------------------------------------- Signed-off-by: Dario Binacchi Link: https://lore.kernel.org/all/20230427204540.3126234-6-dario.binacchi@amarulasolutions.com Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f746.dtsi | 47 ++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi index dc868e6da40e..973698bc9ef4 100644 --- a/arch/arm/boot/dts/stm32f746.dtsi +++ b/arch/arm/boot/dts/stm32f746.dtsi @@ -257,6 +257,23 @@ status = "disabled"; }; + can3: can@40003400 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40003400 0x200>; + interrupts = <104>, <105>, <106>, <107>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN3)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; + st,gcan = <&gcan3>; + status = "disabled"; + }; + + gcan3: gcan@40003600 { + compatible = "st,stm32f4-gcan", "syscon"; + reg = <0x40003600 0x200>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; + }; + usart2: serial@40004400 { compatible = "st,stm32f7-uart"; reg = <0x40004400 0x400>; @@ -337,6 +354,36 @@ status = "disabled"; }; + can1: can@40006400 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40006400 0x200>; + interrupts = <19>, <20>, <21>, <22>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN1)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; + st,can-primary; + st,gcan = <&gcan1>; + status = "disabled"; + }; + + gcan1: gcan@40006600 { + compatible = "st,stm32f4-gcan", "syscon"; + reg = <0x40006600 0x200>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; + }; + + can2: can@40006800 { + compatible = "st,stm32f4-bxcan"; + reg = <0x40006800 0x200>; + interrupts = <63>, <64>, <65>, <66>; + interrupt-names = "tx", "rx0", "rx1", "sce"; + resets = <&rcc STM32F7_APB1_RESET(CAN2)>; + clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN2)>; + st,can-secondary; + st,gcan = <&gcan1>; + status = "disabled"; + }; + cec: cec@40006c00 { compatible = "st,stm32-cec"; reg = <0x40006C00 0x400>; -- GitLab From b2f2a3c9800208b0db2c2e34b05323757117faa2 Mon Sep 17 00:00:00 2001 From: Daisuke Nojiri Date: Mon, 24 Apr 2023 11:25:58 -0700 Subject: [PATCH 4996/5631] power: supply: sbs-charger: Fix INHIBITED bit for Status reg CHARGE_INHIBITED bit position of the ChargerStatus register is actually 0 not 1. This patch corrects it. Fixes: feb583e37f8a8 ("power: supply: add sbs-charger driver") Signed-off-by: Daisuke Nojiri Signed-off-by: Sebastian Reichel --- drivers/power/supply/sbs-charger.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c index 75ebcbf0a788..a14e89ac0369 100644 --- a/drivers/power/supply/sbs-charger.c +++ b/drivers/power/supply/sbs-charger.c @@ -24,7 +24,7 @@ #define SBS_CHARGER_REG_STATUS 0x13 #define SBS_CHARGER_REG_ALARM_WARNING 0x16 -#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(1) +#define SBS_CHARGER_STATUS_CHARGE_INHIBITED BIT(0) #define SBS_CHARGER_STATUS_RES_COLD BIT(9) #define SBS_CHARGER_STATUS_RES_HOT BIT(10) #define SBS_CHARGER_STATUS_BATTERY_PRESENT BIT(14) -- GitLab From 4cbb0d358883a27e432714b5256f0362946f5e25 Mon Sep 17 00:00:00 2001 From: Kang Chen Date: Mon, 27 Feb 2023 11:14:10 +0800 Subject: [PATCH 4997/5631] power: supply: mt6360: add a check of devm_work_autocancel in mt6360_charger_probe devm_work_autocancel may fail, add a check and return early. Fixes: 0402e8ebb8b86 ("power: supply: mt6360_charger: add MT6360 charger support") Signed-off-by: Kang Chen Signed-off-by: Sebastian Reichel --- drivers/power/supply/mt6360_charger.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/power/supply/mt6360_charger.c b/drivers/power/supply/mt6360_charger.c index 92e48e3a4853..1305cba61edd 100644 --- a/drivers/power/supply/mt6360_charger.c +++ b/drivers/power/supply/mt6360_charger.c @@ -796,7 +796,9 @@ static int mt6360_charger_probe(struct platform_device *pdev) mci->vinovp = 6500000; mutex_init(&mci->chgdet_lock); platform_set_drvdata(pdev, mci); - devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + ret = devm_work_autocancel(&pdev->dev, &mci->chrdet_work, mt6360_chrdet_work); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to set delayed work\n"); ret = device_property_read_u32(&pdev->dev, "richtek,vinovp-microvolt", &mci->vinovp); if (ret) -- GitLab From 1398aa803f198b7a386fdd8404666043e95f4c16 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 20:29:27 +0300 Subject: [PATCH 4998/5631] tpm_tis: Use tpm_chip_{start,stop} decoration inside tpm_tis_resume Before sending a TPM command, CLKRUN protocol must be disabled. This is not done in the case of tpm1_do_selftest() call site inside tpm_tis_resume(). Address this by decorating the calls with tpm_chip_{start,stop}, which should be always used to arm and disarm the TPM chip for transmission. Finally, move the call to the main TPM driver callback as the last step because it should arm the chip by itself, if it needs that type of functionality. Cc: stable@vger.kernel.org Reported-by: Jason A. Donenfeld Closes: https://lore.kernel.org/linux-integrity/CS68AWILHXS4.3M36M1EKZLUMS@suppilovahvero/ Fixes: a3fbfae82b4c ("tpm: take TPM chip power gating out of tpm_transmit()") Reviewed-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis_core.c | 43 +++++++++++++++------------------ 1 file changed, 19 insertions(+), 24 deletions(-) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 02945d53fcef..558144fa707a 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -1209,25 +1209,20 @@ static void tpm_tis_reenable_interrupts(struct tpm_chip *chip) u32 intmask; int rc; - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, true); - - /* reenable interrupts that device may have lost or - * BIOS/firmware may have disabled + /* + * Re-enable interrupts that device may have lost or BIOS/firmware may + * have disabled. */ rc = tpm_tis_write8(priv, TPM_INT_VECTOR(priv->locality), priv->irq); - if (rc < 0) - goto out; + if (rc < 0) { + dev_err(&chip->dev, "Setting IRQ failed.\n"); + return; + } intmask = priv->int_mask | TPM_GLOBAL_INT_ENABLE; - - tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); - -out: - if (chip->ops->clk_enable != NULL) - chip->ops->clk_enable(chip, false); - - return; + rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); + if (rc < 0) + dev_err(&chip->dev, "Enabling interrupts failed.\n"); } int tpm_tis_resume(struct device *dev) @@ -1235,27 +1230,27 @@ int tpm_tis_resume(struct device *dev) struct tpm_chip *chip = dev_get_drvdata(dev); int ret; - ret = tpm_tis_request_locality(chip, 0); - if (ret < 0) + ret = tpm_chip_start(chip); + if (ret) return ret; if (chip->flags & TPM_CHIP_FLAG_IRQ) tpm_tis_reenable_interrupts(chip); - ret = tpm_pm_resume(dev); - if (ret) - goto out; - /* * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) tpm1_do_selftest(chip); -out: - tpm_tis_relinquish_locality(chip, 0); - return ret; + tpm_chip_stop(chip); + + ret = tpm_pm_resume(dev); + if (ret) + return ret; + + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); #endif -- GitLab From 99d46450625590d410f86fe4660a5eff7d3b8343 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Wed, 26 Apr 2023 20:29:28 +0300 Subject: [PATCH 4999/5631] tpm: Prevent hwrng from activating during resume Set TPM_CHIP_FLAG_SUSPENDED in tpm_pm_suspend() and reset in tpm_pm_resume(). While the flag is set, tpm_hwrng() gives back zero bytes. This prevents hwrng from racing during resume. Cc: stable@vger.kernel.org Fixes: 6e592a065d51 ("tpm: Move Linux RNG connection to hwrng") Reviewed-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 4 ++++ drivers/char/tpm/tpm-interface.c | 10 ++++++++++ include/linux/tpm.h | 1 + 3 files changed, 15 insertions(+) diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index c10a4aa97373..cd48033b804a 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -571,6 +571,10 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { struct tpm_chip *chip = container_of(rng, struct tpm_chip, hwrng); + /* Give back zero bytes, as TPM chip has not yet fully resumed: */ + if (chip->flags & TPM_CHIP_FLAG_SUSPENDED) + return 0; + return tpm_get_random(chip, data, max); } diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 4463d0018290..586ca10b0d72 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -412,6 +412,8 @@ int tpm_pm_suspend(struct device *dev) } suspended: + chip->flags |= TPM_CHIP_FLAG_SUSPENDED; + if (rc) dev_err(dev, "Ignoring error %d while suspending\n", rc); return 0; @@ -429,6 +431,14 @@ int tpm_pm_resume(struct device *dev) if (chip == NULL) return -ENODEV; + chip->flags &= ~TPM_CHIP_FLAG_SUSPENDED; + + /* + * Guarantee that SUSPENDED is written last, so that hwrng does not + * activate before the chip has been fully resumed. + */ + wmb(); + return 0; } EXPORT_SYMBOL_GPL(tpm_pm_resume); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 77693389c3f9..6a1e8f157255 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -282,6 +282,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), + TPM_CHIP_FLAG_SUSPENDED = BIT(8), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) -- GitLab From e7d3e5c4b1dd50a70b31524c3228c62bb41bbab2 Mon Sep 17 00:00:00 2001 From: Jerry Snitselaar Date: Wed, 10 May 2023 17:54:03 -0700 Subject: [PATCH 5000/5631] tpm/tpm_tis: Disable interrupts for more Lenovo devices The P360 Tiny suffers from an irq storm issue like the T490s, so add an entry for it to tpm_tis_dmi_table, and force polling. There also previously was a report from the previous attempt to enable interrupts that involved a ThinkPad L490. So an entry is added for it as well. Cc: stable@vger.kernel.org Reported-by: Peter Zijlstra # P360 Tiny Closes: https://lore.kernel.org/linux-integrity/20230505130731.GO83892@hirez.programming.kicks-ass.net/ Signed-off-by: Jerry Snitselaar Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 7af389806643..709b4e13bd6e 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -122,6 +122,22 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T490s"), }, }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkStation P360 Tiny", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkStation P360 Tiny"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L490", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L490"), + }, + }, {} }; -- GitLab From 2bf1c45be3b8f3a3f898d0756c1282f09719debd Mon Sep 17 00:00:00 2001 From: Osama Muhammad Date: Mon, 15 May 2023 22:29:38 +0500 Subject: [PATCH 5001/5631] regulator: Fix error checking for debugfs_create_dir This patch fixes the error checking in core.c in debugfs_create_dir. The correct way to check if an error occurred is 'IS_ERR' inline function. Signed-off-by: Osama Muhammad debugfs = debugfs_create_dir(rname, debugfs_root); - if (!rdev->debugfs) { + if (IS_ERR(rdev->debugfs)) { rdev_warn(rdev, "Failed to create debugfs directory\n"); return; } @@ -6178,7 +6178,7 @@ static int __init regulator_init(void) ret = class_register(®ulator_class); debugfs_root = debugfs_create_dir("regulator", NULL); - if (!debugfs_root) + if (IS_ERR(debugfs_root)) pr_warn("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS -- GitLab From 445164e8c136f1445caf735d6d268c948e71caf1 Mon Sep 17 00:00:00 2001 From: Amit Kumar Mahapatra Date: Mon, 15 May 2023 18:33:43 +0530 Subject: [PATCH 5002/5631] spi: dw: Replace spi->chip_select references with function calls New set/get APIs for accessing spi->chip_select were introduced by 'commit 9e264f3f85a5 ("spi: Replace all spi->chip_select and spi->cs_gpiod references with function call")', but the 'commit 2c8606040a80 ("spi: dw: Add support for AMD Pensando Elba SoC")' uses the old interface by directly accessing spi->chip_select. So, replace all spi->chip_select references in the driver with new get/set APIs. Signed-off-by: Amit Kumar Mahapatra priv; u8 cs; - cs = spi->chip_select; + cs = spi_get_chipselect(spi, 0); if (cs < 2) - dw_spi_elba_override_cs(syscon, spi->chip_select, enable); + dw_spi_elba_override_cs(syscon, spi_get_chipselect(spi, 0), enable); /* * The DW SPI controller needs a native CS bit selected to start * the serial engine. */ - spi->chip_select = 0; + spi_set_chipselect(spi, 0, 0); dw_spi_set_cs(spi, enable); - spi->chip_select = cs; + spi_get_chipselect(spi, cs); } static int dw_spi_elba_init(struct platform_device *pdev, -- GitLab From 225c657945c4a6307741cb3cc89467eadcc26e9b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sun, 14 May 2023 19:56:07 -0700 Subject: [PATCH 5003/5631] net: bcmgenet: Restore phy_stop() depending upon suspend/close Removing the phy_stop() from bcmgenet_netif_stop() ended up causing warnings from the PHY library that phy_start() is called from the RUNNING state since we are no longer stopping the PHY state machine during bcmgenet_suspend(). Restore the call to phy_stop() but make it conditional on being called from the close or suspend path. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Fixes: 93e0401e0fc0 ("net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop()") Signed-off-by: Florian Fainelli Reviewed-by: Pavan Chebbi Link: https://lore.kernel.org/r/20230515025608.2587012-1-f.fainelli@gmail.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index f28ffc31df22..eca0c92c0c84 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3450,7 +3450,7 @@ static int bcmgenet_open(struct net_device *dev) return ret; } -static void bcmgenet_netif_stop(struct net_device *dev) +static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -3465,6 +3465,8 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); + if (stop_phy) + phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); @@ -3485,7 +3487,7 @@ static int bcmgenet_close(struct net_device *dev) netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, false); /* Really kill the PHY state machine and disconnect from it */ phy_disconnect(dev->phydev); @@ -4303,7 +4305,7 @@ static int bcmgenet_suspend(struct device *d) netif_device_detach(dev); - bcmgenet_netif_stop(dev); + bcmgenet_netif_stop(dev, true); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); -- GitLab From 140809738d969376f26f13264b16669703956f6c Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 15 May 2023 11:29:43 +0200 Subject: [PATCH 5004/5631] drm/pl111: Fix FB depth on IMPD-1 framebuffer The last argument to the function drm_fbdev_dma_setup() was changed from desired BPP to desired depth. In our case the desired depth was 15 but BPP was 16, so we specified 16 as BPP and we relied on the FB emulation core to select a format with a suitable depth for the limited bandwidth and end up with e.g. XRGB1555 like in the past: [drm] Initialized pl111 1.0.0 20170317 for c1000000.display on minor 0 drm-clcd-pl111 c1000000.display: [drm] requested bpp 16, scaled depth down to 15 drm-clcd-pl111 c1000000.display: enable IM-PD1 CLCD connectors Console: switching to colour frame buffer device 80x30 drm-clcd-pl111 c1000000.display: [drm] fb0: pl111drmfb frame buffer device However the current code will fail at that: [drm] Initialized pl111 1.0.0 20170317 for c1000000.display on minor 0 drm-clcd-pl111 c1000000.display: [drm] bpp/depth value of 16/16 not supported drm-clcd-pl111 c1000000.display: [drm] No compatible format found drm-clcd-pl111 c1000000.display: [drm] *ERROR* fbdev: Failed to setup generic emulation (ret=-12) Fix this by passing the desired depth of 15 for the IM/PD-1 display instead of 16 to drm_fbdev_dma_setup(). The desired depth is however in turn used for bandwidth limiting calculations and that was done with a simple / integer division, whereas we now have to modify that to use DIV_ROUND_UP() so that we get DIV_ROUND_UP(15, 2) = 2 not 15/2 = 1. After this the display works again on the Integrator/AP IM/PD-1. Cc: Emma Anholt Cc: stable@vger.kernel.org Suggested-by: Thomas Zimmermann Fixes: 37c90d589dc0 ("drm/fb-helper: Fix single-probe color-format selection") Link: https://lore.kernel.org/dri-devel/20230102112927.26565-1-tzimmermann@suse.de/ Reviewed-by: Thomas Zimmermann Signed-off-by: Linus Walleij Link: https://patchwork.freedesktop.org/patch/msgid/20230515092943.1401558-1-linus.walleij@linaro.org --- drivers/gpu/drm/pl111/pl111_display.c | 2 +- drivers/gpu/drm/pl111/pl111_drm.h | 4 ++-- drivers/gpu/drm/pl111/pl111_drv.c | 8 ++++---- drivers/gpu/drm/pl111/pl111_versatile.c | 10 +++++----- 4 files changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c index 6afdf260a4e2..b9fe926a49e8 100644 --- a/drivers/gpu/drm/pl111/pl111_display.c +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -53,7 +53,7 @@ pl111_mode_valid(struct drm_simple_display_pipe *pipe, { struct drm_device *drm = pipe->crtc.dev; struct pl111_drm_dev_private *priv = drm->dev_private; - u32 cpp = priv->variant->fb_bpp / 8; + u32 cpp = DIV_ROUND_UP(priv->variant->fb_depth, 8); u64 bw; /* diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h index 2a46b5bd8576..d1fe756444ee 100644 --- a/drivers/gpu/drm/pl111/pl111_drm.h +++ b/drivers/gpu/drm/pl111/pl111_drm.h @@ -114,7 +114,7 @@ struct drm_minor; * extensions to the control register * @formats: array of supported pixel formats on this variant * @nformats: the length of the array of supported pixel formats - * @fb_bpp: desired bits per pixel on the default framebuffer + * @fb_depth: desired depth per pixel on the default framebuffer */ struct pl111_variant_data { const char *name; @@ -126,7 +126,7 @@ struct pl111_variant_data { bool st_bitmux_control; const u32 *formats; unsigned int nformats; - unsigned int fb_bpp; + unsigned int fb_depth; }; struct pl111_drm_dev_private { diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c index 4b2a9e9753f6..43049c8028b2 100644 --- a/drivers/gpu/drm/pl111/pl111_drv.c +++ b/drivers/gpu/drm/pl111/pl111_drv.c @@ -308,7 +308,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev, if (ret < 0) goto dev_put; - drm_fbdev_dma_setup(drm, priv->variant->fb_bpp); + drm_fbdev_dma_setup(drm, priv->variant->fb_depth); return 0; @@ -351,7 +351,7 @@ static const struct pl111_variant_data pl110_variant = { .is_pl110 = true, .formats = pl110_pixel_formats, .nformats = ARRAY_SIZE(pl110_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* RealView, Versatile Express etc use this modern variant */ @@ -376,7 +376,7 @@ static const struct pl111_variant_data pl111_variant = { .name = "PL111", .formats = pl111_pixel_formats, .nformats = ARRAY_SIZE(pl111_pixel_formats), - .fb_bpp = 32, + .fb_depth = 32, }; static const u32 pl110_nomadik_pixel_formats[] = { @@ -405,7 +405,7 @@ static const struct pl111_variant_data pl110_nomadik_variant = { .is_lcdc = true, .st_bitmux_control = true, .broken_vblank = true, - .fb_bpp = 16, + .fb_depth = 16, }; static const struct amba_id pl111_id_table[] = { diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c index 1b436b75fd39..00c3ebd32359 100644 --- a/drivers/gpu/drm/pl111/pl111_versatile.c +++ b/drivers/gpu/drm/pl111/pl111_versatile.c @@ -316,7 +316,7 @@ static const struct pl111_variant_data pl110_integrator = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -330,7 +330,7 @@ static const struct pl111_variant_data pl110_impd1 = { .broken_vblank = true, .formats = pl110_integrator_pixel_formats, .nformats = ARRAY_SIZE(pl110_integrator_pixel_formats), - .fb_bpp = 16, + .fb_depth = 15, }; /* @@ -343,7 +343,7 @@ static const struct pl111_variant_data pl110_versatile = { .external_bgr = true, .formats = pl110_versatile_pixel_formats, .nformats = ARRAY_SIZE(pl110_versatile_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -355,7 +355,7 @@ static const struct pl111_variant_data pl111_realview = { .name = "PL111 RealView", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, }; /* @@ -367,7 +367,7 @@ static const struct pl111_variant_data pl111_vexpress = { .name = "PL111 Versatile Express", .formats = pl111_realview_pixel_formats, .nformats = ARRAY_SIZE(pl111_realview_pixel_formats), - .fb_bpp = 16, + .fb_depth = 16, .broken_clockdivider = true, }; -- GitLab From 43cd3ddbff3c1635d0e09fe5b09af48d39dbb9d7 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 15 May 2023 13:13:50 -0700 Subject: [PATCH 5005/5631] dt-bindings: interrupt-controller: arm,gic-v3: Add quirk for Mediatek SoCs w/ broken FW When trying to turn on the "pseudo NMI" kernel feature in Linux, it was discovered that all Mediatek-based Chromebooks that ever shipped (at least ones with GICv3) had a firmware bug where they wouldn't save certain GIC "GICR" registers properly. If a processor ever entered a suspend/idle mode where the GICR registers lost state then they'd be reset to their default state. As a result of the bug, if you try to enable "pseudo NMIs" on the affected devices then certain interrupts will unexpectedly get promoted to be "pseudo NMIs" and cause crashes / freezes / general mayhem. ChromeOS is looking to start turning on "pseudo NMIs" in production to make crash reports more actionable. To do so, we will release firmware updates for at least some of the affected Mediatek Chromebooks. However, even when we update the firmware of a Chromebook it's always possible that a user will end up booting with old firmware. We need to be able to detect when we're running with firmware that will crash and burn if pseudo NMIs are enabled. The current plan is: * Update the device trees of all affected Chromebooks to include the 'mediatek,broken-save-restore-fw' property. The kernel can use this to know not to enable certain features like "pseudo NMI". NOTE: device trees for Chromebooks are never baked into the firmware but are bundled with the kernel. A kernel will never be configured to use "pseudo NMIs" and be bundled with an old device tree. * When we get a fixed firmware for one of these Chromebooks, it will patch the device tree to remove this property. For some details, you can also see the public bug Reviewed-by: Julius Werner Signed-off-by: Douglas Anderson Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230515131353.v2.1.Iabe67a827e206496efec6beb5616d5a3b99c1e65@changeid --- .../bindings/interrupt-controller/arm,gic-v3.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 92117261e1e1..39e64c7f6360 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -166,6 +166,12 @@ properties: resets: maxItems: 1 + mediatek,broken-save-restore-fw: + type: boolean + description: + Asserts that the firmware on this device has issues saving and restoring + GICR registers when the GIC redistributors are powered off. + dependencies: mbi-ranges: [ msi-controller ] msi-controller: [ mbi-ranges ] -- GitLab From 44bd78dd2b8897f59b7e3963f088caadb7e4f047 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 15 May 2023 13:13:51 -0700 Subject: [PATCH 5006/5631] irqchip/gic-v3: Disable pseudo NMIs on Mediatek devices w/ firmware issues Some Chromebooks with Mediatek SoCs have a problem where the firmware doesn't properly save/restore certain GICR registers. Newer Chromebooks should fix this issue and we may be able to do firmware updates for old Chromebooks. At the moment, the only known issue with these Chromebooks is that we can't enable "pseudo NMIs" since the priority register can be lost. Enabling "pseudo NMIs" on Chromebooks with the problematic firmware causes crashes and freezes. Let's detect devices with this problem and then disable "pseudo NMIs" on them. We'll detect the problem by looking for the presence of the "mediatek,broken-save-restore-fw" property in the GIC device tree node. Any devices with fixed firmware will not have this property. Our detection plan works because we never bake a Chromebook's device tree into firmware. Instead, device trees are always bundled with the kernel. We'll update the device trees of all affected Chromebooks and then we'll never enable "pseudo NMI" on a kernel that is bundled with old device trees. When a firmware update is shipped that fixes this issue it will know to patch the device tree to remove the property. In order to make this work, the quick detection mechanism of the GICv3 code is extended to be able to look for properties in addition to looking at "compatible". Reviewed-by: Julius Werner Signed-off-by: Douglas Anderson Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230515131353.v2.2.I88dc0a0eb1d9d537de61604cd8994ecc55c0cac1@changeid --- drivers/irqchip/irq-gic-common.c | 8 ++++++-- drivers/irqchip/irq-gic-common.h | 1 + drivers/irqchip/irq-gic-v3.c | 20 ++++++++++++++++++++ 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c index a610821c8ff2..de47b51cdadb 100644 --- a/drivers/irqchip/irq-gic-common.c +++ b/drivers/irqchip/irq-gic-common.c @@ -16,7 +16,11 @@ void gic_enable_of_quirks(const struct device_node *np, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (!of_device_is_compatible(np, quirks->compatible)) + if (quirks->compatible && + !of_device_is_compatible(np, quirks->compatible)) + continue; + if (quirks->property && + !of_property_read_bool(np, quirks->property)) continue; if (quirks->init(data)) pr_info("GIC: enabling workaround for %s\n", @@ -28,7 +32,7 @@ void gic_enable_quirks(u32 iidr, const struct gic_quirk *quirks, void *data) { for (; quirks->desc; quirks++) { - if (quirks->compatible) + if (quirks->compatible || quirks->property) continue; if (quirks->iidr != (quirks->mask & iidr)) continue; diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h index 27e3d4ed4f32..3db4592cda1c 100644 --- a/drivers/irqchip/irq-gic-common.h +++ b/drivers/irqchip/irq-gic-common.h @@ -13,6 +13,7 @@ struct gic_quirk { const char *desc; const char *compatible; + const char *property; bool (*init)(void *data); u32 iidr; u32 mask; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fcee221f201..a605aa79435a 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -39,6 +39,7 @@ #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) +#define FLAGS_WORKAROUND_MTK_GICR_SAVE (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -1720,6 +1721,15 @@ static bool gic_enable_quirk_msm8996(void *data) return true; } +static bool gic_enable_quirk_mtk_gicr(void *data) +{ + struct gic_chip_data *d = data; + + d->flags |= FLAGS_WORKAROUND_MTK_GICR_SAVE; + + return true; +} + static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; @@ -1792,6 +1802,11 @@ static const struct gic_quirk gic_quirks[] = { .compatible = "qcom,msm8996-gic-v3", .init = gic_enable_quirk_msm8996, }, + { + .desc = "GICv3: Mediatek Chromebook GICR save problem", + .property = "mediatek,broken-save-restore-fw", + .init = gic_enable_quirk_mtk_gicr, + }, { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, @@ -1834,6 +1849,11 @@ static void gic_enable_nmi_support(void) if (!gic_prio_masking_enabled()) return; + if (gic_data.flags & FLAGS_WORKAROUND_MTK_GICR_SAVE) { + pr_warn("Skipping NMI enable due to firmware issues\n"); + return; + } + ppi_nmi_refs = kcalloc(gic_data.ppi_nr, sizeof(*ppi_nmi_refs), GFP_KERNEL); if (!ppi_nmi_refs) return; -- GitLab From 2c6c9c049510163090b979ea5f92a68ae8d93c45 Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Mon, 24 Apr 2023 11:31:55 +0100 Subject: [PATCH 5007/5631] irqchip/mips-gic: Don't touch vl_map if a local interrupt is not routable When a GIC local interrupt is not routable, it's vl_map will be used to control some internal states for core (providing IPTI, IPPCI, IPFDC input signal for core). Overriding it will interfere core's intetrupt controller. Do not touch vl_map if a local interrupt is not routable, we are not going to remap it. Before dd098a0e0319 (" irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()"), if a local interrupt is not routable, then it won't be requested from GIC Local domain, and thus gic_all_vpes_irq_cpu_online won't be called for that particular interrupt. Fixes: dd098a0e0319 (" irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()") Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Reviewed-by: Serge Semin Tested-by: Serge Semin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230424103156.66753-2-jiaxun.yang@flygoat.com --- drivers/irqchip/irq-mips-gic.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 046c355e120b..b568d55ef7c5 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -399,6 +399,8 @@ static void gic_all_vpes_irq_cpu_online(void) unsigned int intr = local_intrs[i]; struct gic_all_vpes_chip_data *cd; + if (!gic_local_irq_is_routable(intr)) + continue; cd = &gic_all_vpes_chip_data[intr]; write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); if (cd->mask) -- GitLab From 3d6a0e4197c04599d75d85a608c8bb16a630a38c Mon Sep 17 00:00:00 2001 From: Jiaxun Yang Date: Mon, 24 Apr 2023 11:31:56 +0100 Subject: [PATCH 5008/5631] irqchip/mips-gic: Use raw spinlock for gic_lock Since we may hold gic_lock in hardirq context, use raw spinlock makes more sense given that it is for low-level interrupt handling routine and the critical section is small. Fixes BUG: [ 0.426106] ============================= [ 0.426257] [ BUG: Invalid wait context ] [ 0.426422] 6.3.0-rc7-next-20230421-dirty #54 Not tainted [ 0.426638] ----------------------------- [ 0.426766] swapper/0/1 is trying to lock: [ 0.426954] ffffffff8104e7b8 (gic_lock){....}-{3:3}, at: gic_set_type+0x30/08 Fixes: 95150ae8b330 ("irqchip: mips-gic: Implement irq_set_type callback") Cc: stable@vger.kernel.org Signed-off-by: Jiaxun Yang Reviewed-by: Serge Semin Tested-by: Serge Semin Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230424103156.66753-3-jiaxun.yang@flygoat.com --- drivers/irqchip/irq-mips-gic.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index b568d55ef7c5..6d5ecc10a870 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -50,7 +50,7 @@ void __iomem *mips_gic_base; static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks); -static DEFINE_SPINLOCK(gic_lock); +static DEFINE_RAW_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; @@ -210,7 +210,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) irq = GIC_HWIRQ_TO_SHARED(d->hwirq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_FALLING: pol = GIC_POL_FALLING_EDGE; @@ -250,7 +250,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) else irq_set_chip_handler_name_locked(d, &gic_level_irq_controller, handle_level_irq, NULL); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -268,7 +268,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, return -EINVAL; /* Assumption : cpumask refers to a single CPU */ - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); /* Re-route this IRQ */ write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu))); @@ -279,7 +279,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, set_bit(irq, per_cpu_ptr(pcpu_masks, cpu)); irq_data_update_effective_affinity(d, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return IRQ_SET_MASK_OK; } @@ -357,12 +357,12 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = false; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_rmask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_unmask_local_irq_all_vpes(struct irq_data *d) @@ -375,12 +375,12 @@ static void gic_unmask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = true; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static void gic_all_vpes_irq_cpu_online(void) @@ -393,7 +393,7 @@ static void gic_all_vpes_irq_cpu_online(void) unsigned long flags; int i; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for (i = 0; i < ARRAY_SIZE(local_intrs); i++) { unsigned int intr = local_intrs[i]; @@ -407,7 +407,7 @@ static void gic_all_vpes_irq_cpu_online(void) write_gic_vl_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); } static struct irq_chip gic_all_vpes_local_irq_controller = { @@ -437,11 +437,11 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, data = irq_get_irq_data(virq); - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); irq_data_update_effective_affinity(data, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } @@ -533,12 +533,12 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, if (!gic_local_irq_is_routable(intr)) return -EPERM; - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_map(mips_gic_vx_map_reg(intr), map); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); return 0; } -- GitLab From 14130211be5366a91ec07c3284c183b75d8fba17 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Fri, 12 May 2023 18:45:06 +0200 Subject: [PATCH 5009/5631] irqchip/meson-gpio: Mark OF related data as maybe unused MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver can be compile tested with !CONFIG_OF making certain data unused: drivers/irqchip/irq-meson-gpio.c:153:34: error: ‘meson_irq_gpio_matches’ defined but not used [-Werror=unused-const-variable=] Acked-by: Martin Blumenstingl Signed-off-by: Krzysztof Kozlowski Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230512164506.212267-1-krzysztof.kozlowski@linaro.org --- drivers/irqchip/irq-meson-gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c index 2aaa9aad3e87..7da18ef95211 100644 --- a/drivers/irqchip/irq-meson-gpio.c +++ b/drivers/irqchip/irq-meson-gpio.c @@ -150,7 +150,7 @@ static const struct meson_gpio_irq_params s4_params = { INIT_MESON_S4_COMMON_DATA(82) }; -static const struct of_device_id meson_irq_gpio_matches[] = { +static const struct of_device_id meson_irq_gpio_matches[] __maybe_unused = { { .compatible = "amlogic,meson8-gpio-intc", .data = &meson8_params }, { .compatible = "amlogic,meson8b-gpio-intc", .data = &meson8b_params }, { .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params }, -- GitLab From cddb536a73ef2c82ce04059dc61c65e85a355561 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 May 2023 17:06:54 +0800 Subject: [PATCH 5010/5631] irqchip/mbigen: Unify the error handling in mbigen_of_create_domain() Dan Carpenter reported that commit fea087fc291b "irqchip/mbigen: move to use bus_get_dev_root()" leads to the following Smatch static checker warning: drivers/irqchip/irq-mbigen.c:258 mbigen_of_create_domain() error: potentially dereferencing uninitialized 'child'. It should not cause a problem on real hardware, but better to fix the warning, let's move the bus_get_dev_root() out of the loop, and unify the error handling to silence it. Reported-by: Dan Carpenter Signed-off-by: Kefeng Wang Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230505090654.12793-1-wangkefeng.wang@huawei.com --- drivers/irqchip/irq-mbigen.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index eada5e0e3eb9..5101a3fb11df 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -240,26 +240,27 @@ static int mbigen_of_create_domain(struct platform_device *pdev, struct irq_domain *domain; struct device_node *np; u32 num_pins; + int ret = 0; + + parent = bus_get_dev_root(&platform_bus_type); + if (!parent) + return -ENODEV; for_each_child_of_node(pdev->dev.of_node, np) { if (!of_property_read_bool(np, "interrupt-controller")) continue; - parent = bus_get_dev_root(&platform_bus_type); - if (parent) { - child = of_platform_device_create(np, NULL, parent); - put_device(parent); - if (!child) { - of_node_put(np); - return -ENOMEM; - } + child = of_platform_device_create(np, NULL, parent); + if (!child) { + ret = -ENOMEM; + break; } if (of_property_read_u32(child->dev.of_node, "num-pins", &num_pins) < 0) { dev_err(&pdev->dev, "No num-pins property\n"); - of_node_put(np); - return -EINVAL; + ret = -EINVAL; + break; } domain = platform_msi_create_device_domain(&child->dev, num_pins, @@ -267,12 +268,16 @@ static int mbigen_of_create_domain(struct platform_device *pdev, &mbigen_domain_ops, mgn_chip); if (!domain) { - of_node_put(np); - return -ENOMEM; + ret = -ENOMEM; + break; } } - return 0; + put_device(parent); + if (ret) + of_node_put(np); + + return ret; } #ifdef CONFIG_ACPI -- GitLab From 50a1726b148ff30778cb8a6cf3736130b07c93fd Mon Sep 17 00:00:00 2001 From: Frank Li Date: Mon, 15 May 2023 12:20:52 -0400 Subject: [PATCH 5011/5631] dt-binding: cdns,usb3: Fix cdns,on-chip-buff-size type In cdns3-gadget.c, 'cdns,on-chip-buff-size' was read using device_property_read_u16(). It resulted in 0 if a 32bit value was used in dts. This commit fixes the dt binding doc to declare it as u16. Cc: stable@vger.kernel.org Fixes: 68989fe1c39d ("dt-bindings: usb: Convert cdns-usb3.txt to YAML schema") Signed-off-by: Frank Li Reviewed-by: Krzysztof Kozlowski Signed-off-by: Shawn Guo --- Documentation/devicetree/bindings/usb/cdns,usb3.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml index cae46c4982ad..69a93a0722f0 100644 --- a/Documentation/devicetree/bindings/usb/cdns,usb3.yaml +++ b/Documentation/devicetree/bindings/usb/cdns,usb3.yaml @@ -64,7 +64,7 @@ properties: description: size of memory intended as internal memory for endpoints buffers expressed in KB - $ref: /schemas/types.yaml#/definitions/uint32 + $ref: /schemas/types.yaml#/definitions/uint16 cdns,phyrst-a-enable: description: Enable resetting of PHY if Rx fail is detected -- GitLab From 0f554e37dad416f445cd3ec5935f5aec1b0e7ba5 Mon Sep 17 00:00:00 2001 From: Frank Li Date: Mon, 15 May 2023 12:20:53 -0400 Subject: [PATCH 5012/5631] arm64: dts: imx8: fix USB 3.0 Gadget Failure in QM & QXPB0 at super speed Resolve USB 3.0 gadget failure for QM and QXPB0 in super speed mode with single IN and OUT endpoints, like mass storage devices, due to incorrect ACTUAL_MEM_SIZE in ep_cap2 (32k instead of actual 18k). Implement dt property cdns,on-chip-buff-size to override ep_cap2 and set it to 18k for imx8QM and imx8QXP chips. No adverse effects for 8QXP C0. Cc: stable@vger.kernel.org Fixes: dce49449e04f ("usb: cdns3: allocate TX FIFO size according to composite EP number") Signed-off-by: Frank Li Signed-off-by: Shawn Guo --- arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 2209c1ac6e9b..e62a43591361 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -171,6 +171,7 @@ conn_subsys: bus@5b000000 { interrupt-names = "host", "peripheral", "otg", "wakeup"; phys = <&usb3_phy>; phy-names = "cdns3,usb3-phy"; + cdns,on-chip-buff-size = /bits/ 16 <18>; status = "disabled"; }; }; -- GitLab From f7ba52f302fdc392e0047f38e50841483d997144 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 18 Apr 2023 14:49:25 -0700 Subject: [PATCH 5013/5631] vmlinux.lds.h: Discard .note.gnu.property section MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When tooling reads ELF notes, it assumes each note entry is aligned to the value listed in the .note section header's sh_addralign field. The kernel-created ELF notes in the .note.Linux and .note.Xen sections are aligned to 4 bytes. This causes the toolchain to set those sections' sh_addralign values to 4. On the other hand, the GCC-created .note.gnu.property section has an sh_addralign value of 8 for some reason, despite being based on struct Elf32_Nhdr which only needs 4-byte alignment. When the mismatched input sections get linked together into the vmlinux .notes output section, the higher alignment "wins", resulting in an sh_addralign of 8, which confuses tooling. For example: $ readelf -n .tmp_vmlinux.btf ... readelf: .tmp_vmlinux.btf: Warning: note with invalid namesz and/or descsz found at offset 0x170 readelf: .tmp_vmlinux.btf: Warning: type: 0x4, namesize: 0x006e6558, descsize: 0x00008801, alignment: 8 In this case readelf thinks there's alignment padding where there is none, so it starts reading an ELF note in the middle. With newer toolchains (e.g., latest Fedora Rawhide), a similar mismatch triggers a build failure when combined with CONFIG_X86_KERNEL_IBT: btf_encoder__encode: btf__dedup failed! Failed to encode BTF libbpf: failed to find '.BTF' ELF section in vmlinux FAILED: load BTF from vmlinux: No data available make[1]: *** [scripts/Makefile.vmlinux:35: vmlinux] Error 255 This latter error was caused by pahole crashing when it encountered the corrupt .notes section. This crash has been fixed in dwarves version 1.25. As Tianyi Liu describes: "Pahole reads .notes to look for LINUX_ELFNOTE_BUILD_LTO. When LTO is enabled, pahole needs to call cus__merge_and_process_cu to merge compile units, at which point there should only be one unspecified type (used to represent some compilation information) in the global context. However, when the kernel is compiled without LTO, if pahole calls cus__merge_and_process_cu due to alignment issues with notes, multiple unspecified types may appear after merging the cus, and older versions of pahole only support up to one. This is why pahole 1.24 crashes, while newer versions support multiple. However, the latest version of pahole still does not solve the problem of incorrect LTO recognition, so compiling the kernel may be slower than normal." Even with the newer pahole, the note section misaligment issue still exists and pahole is misinterpreting the LTO note. Fix it by discarding the .note.gnu.property section. While GNU properties are important for user space (and VDSO), they don't seem to have any use for vmlinux. (In fact, they're already getting (inadvertently) stripped from vmlinux when CONFIG_DEBUG_INFO_BTF is enabled. The BTF data is extracted from vmlinux.o with "objcopy --only-section=.BTF" into .btf.vmlinux.bin.o. That file doesn't have .note.gnu.property, so when it gets modified and linked back into the main object, the linker automatically strips it (see "How GNU properties are merged" in the ld man page).) Reported-by: Daniel Xu Link: https://lkml.kernel.org/bpf/57830c30-cd77-40cf-9cd1-3bb608aa602e@app.fastmail.com Debugged-by: Tianyi Liu Suggested-by: Joan Bruguera Micó Link: https://lore.kernel.org/r/20230418214925.ay3jpf2zhw75kgmd@treble Signed-off-by: Josh Poimboeuf --- include/asm-generic/vmlinux.lds.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index d1f57e4868ed..cebdf1ca415d 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -891,9 +891,16 @@ /* * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler. * Otherwise, the type of .notes section would become PROGBITS instead of NOTES. + * + * Also, discard .note.gnu.property, otherwise it forces the notes section to + * be 8-byte aligned which causes alignment mismatches with the kernel's custom + * 4-byte aligned notes. */ #define NOTES \ - /DISCARD/ : { *(.note.GNU-stack) } \ + /DISCARD/ : { \ + *(.note.GNU-stack) \ + *(.note.gnu.property) \ + } \ .notes : AT(ADDR(.notes) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.note.*, _notes) \ } NOTES_HEADERS \ -- GitLab From 2e4be0d011f21593c6b316806779ba1eba2cd7e0 Mon Sep 17 00:00:00 2001 From: Vernon Lovejoy Date: Fri, 12 May 2023 12:42:32 +0200 Subject: [PATCH 5014/5631] x86/show_trace_log_lvl: Ensure stack pointer is aligned, again The commit e335bb51cc15 ("x86/unwind: Ensure stack pointer is aligned") tried to align the stack pointer in show_trace_log_lvl(), otherwise the "stack < stack_info.end" check can't guarantee that the last read does not go past the end of the stack. However, we have the same problem with the initial value of the stack pointer, it can also be unaligned. So without this patch this trivial kernel module #include static int init(void) { asm volatile("sub $0x4,%rsp"); dump_stack(); asm volatile("add $0x4,%rsp"); return -EAGAIN; } module_init(init); MODULE_LICENSE("GPL"); crashes the kernel. Fixes: e335bb51cc15 ("x86/unwind: Ensure stack pointer is aligned") Signed-off-by: Vernon Lovejoy Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20230512104232.GA10227@redhat.com Signed-off-by: Josh Poimboeuf --- arch/x86/kernel/dumpstack.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 0bf6779187dd..f18ca44c904b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -195,7 +195,6 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, printk("%sCall Trace:\n", log_lvl); unwind_start(&state, task, regs, stack); - stack = stack ? : get_stack_pointer(task, regs); regs = unwind_get_entry_regs(&state, &partial); /* @@ -214,9 +213,13 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - hardirq stack * - entry stack */ - for ( ; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { + for (stack = stack ?: get_stack_pointer(task, regs); + stack; + stack = stack_info.next_sp) { const char *stack_name; + stack = PTR_ALIGN(stack, sizeof(long)); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { /* * We weren't on a valid stack. It's possible that -- GitLab From d91d580878064b880f3574ac35b98d8b70ee8620 Mon Sep 17 00:00:00 2001 From: Min-Hua Chen Date: Tue, 2 May 2023 23:19:06 +0800 Subject: [PATCH 5015/5631] arm64/mm: mark private VM_FAULT_X defines as vm_fault_t This patch fixes several sparse warnings for fault.c: arch/arm64/mm/fault.c:493:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:493:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:493:24: sparse: got int arch/arm64/mm/fault.c:501:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:501:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:501:32: sparse: got int arch/arm64/mm/fault.c:503:32: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:503:32: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:503:32: sparse: got int arch/arm64/mm/fault.c:511:24: sparse: warning: incorrect type in return expression (different base types) arch/arm64/mm/fault.c:511:24: sparse: expected restricted vm_fault_t arch/arm64/mm/fault.c:511:24: sparse: got int arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:670:13: sparse: warning: restricted vm_fault_t degrades to integer arch/arm64/mm/fault.c:713:39: sparse: warning: restricted vm_fault_t degrades to integer Reported-by: kernel test robot Signed-off-by: Min-Hua Chen Link: https://lore.kernel.org/r/20230502151909.128810-1-minhuadotchen@gmail.com Signed-off-by: Will Deacon --- arch/arm64/mm/fault.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9e0db5c387e3..cb21ccd7940d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -480,8 +480,8 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -#define VM_FAULT_BADMAP 0x010000 -#define VM_FAULT_BADACCESS 0x020000 +#define VM_FAULT_BADMAP ((__force vm_fault_t)0x010000) +#define VM_FAULT_BADACCESS ((__force vm_fault_t)0x020000) static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, -- GitLab From b0abde80620f42d1ceb3de5e4c1a49cdd5628229 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 10 May 2023 08:48:11 +0200 Subject: [PATCH 5016/5631] arm64: vdso: Pass (void *) to virt_to_page() Like the other calls in this function virt_to_page() expects a pointer, not an integer. However since many architectures implement virt_to_pfn() as a macro, this function becomes polymorphic and accepts both a (unsigned long) and a (void *). Fix this up with an explicit cast. Signed-off-by: Linus Walleij Link: http://lists.infradead.org/pipermail/linux-arm-kernel/2023-May/832583.html Signed-off-by: Will Deacon --- arch/arm64/kernel/vdso.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } -- GitLab From 68e3f61eb9f58798e28b18152cd38cb269eebc34 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 May 2023 18:05:18 +0200 Subject: [PATCH 5017/5631] ARM: perf: Mark all accessor functions inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When just including : arch/arm/include/asm/arm_pmuv3.h:110:13: error: ‘write_pmevtypern’ defined but not used [-Werror=unused-function] 110 | static void write_pmevtypern(int n, unsigned long val) | ^~~~~~~~~~~~~~~~ arch/arm/include/asm/arm_pmuv3.h:103:13: error: ‘write_pmevcntrn’ defined but not used [-Werror=unused-function] 103 | static void write_pmevcntrn(int n, unsigned long val) | ^~~~~~~~~~~~~~~ arch/arm/include/asm/arm_pmuv3.h:95:22: error: ‘read_pmevcntrn’ defined but not used [-Werror=unused-function] 95 | static unsigned long read_pmevcntrn(int n) | ^~~~~~~~~~~~~~ Fix this by adding the missing "inline" keywords to the three accessor functions that lack them. Fixes: 009d6dc87a56 ("ARM: perf: Allow the use of the PMUv3 driver on 32bit ARM") Signed-off-by: Geert Uytterhoeven Acked-by: Mark Rutland Reviewed-by: Marc Zyngier Link: https://lore.kernel.org/r/3a7d9bc7470aa2d85696ee9765c74f8c03fb5454.1683561482.git.geert+renesas@glider.be Signed-off-by: Will Deacon --- arch/arm/include/asm/arm_pmuv3.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/include/asm/arm_pmuv3.h b/arch/arm/include/asm/arm_pmuv3.h index 78d3d4b82c6c..f4db3e75d75f 100644 --- a/arch/arm/include/asm/arm_pmuv3.h +++ b/arch/arm/include/asm/arm_pmuv3.h @@ -92,7 +92,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(PMEVCNTR##n) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -100,14 +100,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, PMEVCNTR##n) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, PMEVTYPER##n) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } -- GitLab From 3bc879e355da4ff925e9d82278a829547d9d54bf Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 8 May 2023 18:05:19 +0200 Subject: [PATCH 5018/5631] arm64: perf: Mark all accessor functions inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When just including : arch/arm64/include/asm/arm_pmuv3.h:31:13: error: ‘write_pmevtypern’ defined but not used [-Werror=unused-function] 31 | static void write_pmevtypern(int n, unsigned long val) | ^~~~~~~~~~~~~~~~ arch/arm64/include/asm/arm_pmuv3.h:24:13: error: ‘write_pmevcntrn’ defined but not used [-Werror=unused-function] 24 | static void write_pmevcntrn(int n, unsigned long val) | ^~~~~~~~~~~~~~~ arch/arm64/include/asm/arm_pmuv3.h:16:22: error: ‘read_pmevcntrn’ defined but not used [-Werror=unused-function] 16 | static unsigned long read_pmevcntrn(int n) | ^~~~~~~~~~~~~~ Fix this by adding the missing "inline" keywords to the three accessor functions that lack them. Fixes: df29ddf4f04b ("arm64: perf: Abstract system register accesses away") Signed-off-by: Geert Uytterhoeven Reviewed-by: Marc Zyngier Acked-by: Mark Rutland Link: https://lore.kernel.org/r/d53a19043c0c3bd25f6c203e73a2fb08a9661824.1683561482.git.geert+renesas@glider.be Signed-off-by: Will Deacon --- arch/arm64/include/asm/arm_pmuv3.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h index d6b51deb7bf0..18dc2fb3d7b7 100644 --- a/arch/arm64/include/asm/arm_pmuv3.h +++ b/arch/arm64/include/asm/arm_pmuv3.h @@ -13,7 +13,7 @@ #define RETURN_READ_PMEVCNTRN(n) \ return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) +static inline unsigned long read_pmevcntrn(int n) { PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); return 0; @@ -21,14 +21,14 @@ static unsigned long read_pmevcntrn(int n) #define WRITE_PMEVCNTRN(n) \ write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) +static inline void write_pmevcntrn(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVCNTRN); } #define WRITE_PMEVTYPERN(n) \ write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) +static inline void write_pmevtypern(int n, unsigned long val) { PMEVN_SWITCH(n, WRITE_PMEVTYPERN); } -- GitLab From 2efbafb91e12ff5a16cbafb0085e4c10c3fca493 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 20 Apr 2023 14:09:45 -0700 Subject: [PATCH 5019/5631] arm64: Also reset KASAN tag if page is not PG_mte_tagged Consider the following sequence of events: 1) A page in a PROT_READ|PROT_WRITE VMA is faulted. 2) Page migration allocates a page with the KASAN allocator, causing it to receive a non-match-all tag, and uses it to replace the page faulted in 1. 3) The program uses mprotect() to enable PROT_MTE on the page faulted in 1. As a result of step 3, we are left with a non-match-all tag for a page with tags accessible to userspace, which can lead to the same kind of tag check faults that commit e74a68468062 ("arm64: Reset KASAN tag in copy_highpage with HW tags only") intended to fix. The general invariant that we have for pages in a VMA with VM_MTE_ALLOWED is that they cannot have a non-match-all tag. As a result of step 2, the invariant is broken. This means that the fix in the referenced commit was incomplete and we also need to reset the tag for pages without PG_mte_tagged. Fixes: e5b8d9218951 ("arm64: mte: reset the page tag in page->flags") Cc: # 5.15 Link: https://linux-review.googlesource.com/id/I7409cdd41acbcb215c2a7417c1e50d37b875beff Signed-off-by: Peter Collingbourne Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20230420210945.2313627-1-pcc@google.com Signed-off-by: Will Deacon --- arch/arm64/mm/copypage.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 4aadcfb01754..a7bb20055ce0 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -21,9 +21,10 @@ void copy_highpage(struct page *to, struct page *from) copy_page(kto, kfrom); + if (kasan_hw_tags_enabled()) + page_kasan_tag_reset(to); + if (system_supports_mte() && page_mte_tagged(from)) { - if (kasan_hw_tags_enabled()) - page_kasan_tag_reset(to); /* It's a new page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(to)); mte_copy_page_tags(kto, kfrom); -- GitLab From c4c597f1b367433c52c531dccd6859a39b4580fb Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 20 Apr 2023 14:43:27 -0700 Subject: [PATCH 5020/5631] arm64: mte: Do not set PG_mte_tagged if tags were not initialized The mte_sync_page_tags() function sets PG_mte_tagged if it initializes page tags. Then we return to mte_sync_tags(), which sets PG_mte_tagged again. At best, this is redundant. However, it is possible for mte_sync_page_tags() to return without having initialized tags for the page, i.e. in the case where check_swap is true (non-compound page), is_swap_pte(old_pte) is false and pte_is_tagged is false. So at worst, we set PG_mte_tagged on a page with uninitialized tags. This can happen if, for example, page migration causes a PTE for an untagged page to be replaced. If the userspace program subsequently uses mprotect() to enable PROT_MTE for that page, the uninitialized tags will be exposed to userspace. Fix it by removing the redundant call to set_page_mte_tagged(). Fixes: e059853d14ca ("arm64: mte: Fix/clarify the PG_mte_tagged semantics") Signed-off-by: Peter Collingbourne Cc: # 6.1 Link: https://linux-review.googlesource.com/id/Ib02d004d435b2ed87603b858ef7480f7b1463052 Reviewed-by: Catalin Marinas Reviewed-by: Alexandru Elisei Link: https://lore.kernel.org/r/20230420214327.2357985-1-pcc@google.com Signed-off-by: Will Deacon --- arch/arm64/kernel/mte.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..7e89968bd282 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); -- GitLab From 03262a3f5b5b910c7c2900c2f8884832794355f5 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Tue, 2 May 2023 10:50:05 -0400 Subject: [PATCH 5021/5631] phy: mediatek: rework the floating point comparisons to fixed point MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc on aarch64 reports drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c: In function ‘mtk_hdmi_pll_set_rate’: drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c:240:52: error: ‘-mgeneral-regs-only’ is incompatible with the use of floating-point types 240 | else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) Floating point should not be used, so rework the floating point comparisons to fixed point. Signed-off-by: Tom Rix Reviewed-by: Chunfeng Yun Link: https://lore.kernel.org/r/20230502145005.2927101-1-trix@redhat.com Signed-off-by: Vinod Koul --- drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index caa953780bee..8aa7251de4a9 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -237,11 +237,11 @@ static int mtk_hdmi_pll_calc(struct mtk_hdmi_phy *hdmi_phy, struct clk_hw *hw, */ if (tmds_clk < 54 * MEGA) txposdiv = 8; - else if (tmds_clk >= 54 * MEGA && tmds_clk < 148.35 * MEGA) + else if (tmds_clk >= 54 * MEGA && (tmds_clk * 100) < 14835 * MEGA) txposdiv = 4; - else if (tmds_clk >= 148.35 * MEGA && tmds_clk < 296.7 * MEGA) + else if ((tmds_clk * 100) >= 14835 * MEGA && (tmds_clk * 10) < 2967 * MEGA) txposdiv = 2; - else if (tmds_clk >= 296.7 * MEGA && tmds_clk <= 594 * MEGA) + else if ((tmds_clk * 10) >= 2967 * MEGA && tmds_clk <= 594 * MEGA) txposdiv = 1; else return -EINVAL; @@ -324,12 +324,12 @@ static int mtk_hdmi_pll_drv_setting(struct clk_hw *hw) clk_channel_bias = 0x34; /* 20mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 74.175 * MEGA && pixel_clk <= 300 * MEGA) { + } else if (((u64)pixel_clk * 1000) >= 74175 * MEGA && pixel_clk <= 300 * MEGA) { data_channel_bias = 0x34; /* 20mA */ clk_channel_bias = 0x2c; /* 16mA */ impedance_en = 0xf; impedance = 0x36; /* 100ohm */ - } else if (pixel_clk >= 27 * MEGA && pixel_clk < 74.175 * MEGA) { + } else if (pixel_clk >= 27 * MEGA && ((u64)pixel_clk * 1000) < 74175 * MEGA) { data_channel_bias = 0x14; /* 10mA */ clk_channel_bias = 0x14; /* 10mA */ impedance_en = 0x0; -- GitLab From b949193011540bb17cf1da7795ec42af1b875203 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Fri, 12 May 2023 15:11:41 +0200 Subject: [PATCH 5022/5631] phy: amlogic: phy-meson-g12a-mipi-dphy-analog: fix CNTL2_DIF_TX_CTL0 value Use the same CNTL2_DIF_TX_CTL0 value used by the vendor, it was reported fixing timings issues. Fixes: 2a56dc650e54 ("phy: amlogic: Add G12A Analog MIPI D-PHY driver") Signed-off-by: Neil Armstrong Link: https://lore.kernel.org/r/20230512-amlogic-v6-4-upstream-dsi-ccf-vim3-v4-10-2592c29ea263@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c index c14089fa7db4..cabdddbbabfd 100644 --- a/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c +++ b/drivers/phy/amlogic/phy-meson-g12a-mipi-dphy-analog.c @@ -70,7 +70,7 @@ static int phy_g12a_mipi_dphy_analog_power_on(struct phy *phy) HHI_MIPI_CNTL1_BANDGAP); regmap_write(priv->regmap, HHI_MIPI_CNTL2, - FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x459) | + FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL0, 0x45a) | FIELD_PREP(HHI_MIPI_CNTL2_DIF_TX_CTL1, 0x2680)); reg = DSI_LANE_CLK; -- GitLab From 2a881183dc5ab2474ef602e48fe7af34db460d95 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sun, 7 May 2023 16:48:18 +0200 Subject: [PATCH 5023/5631] phy: qcom-snps: correct struct qcom_snps_hsphy kerneldoc Update kerneldoc of struct qcom_snps_hsphy to fix: drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c:135: warning: Function parameter or member 'update_seq_cfg' not described in 'qcom_snps_hsphy' Signed-off-by: Krzysztof Kozlowski Reviewed-by: Konrad Dybcio Link: https://lore.kernel.org/r/20230507144818.193039-1-krzysztof.kozlowski@linaro.org Signed-off-by: Vinod Koul --- drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c index a59063596214..6c237f3cc66d 100644 --- a/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c +++ b/drivers/phy/qualcomm/phy-qcom-snps-femto-v2.c @@ -115,11 +115,11 @@ struct phy_override_seq { * * @cfg_ahb_clk: AHB2PHY interface clock * @ref_clk: phy reference clock - * @iface_clk: phy interface clock * @phy_reset: phy reset control * @vregs: regulator supplies bulk data * @phy_initialized: if PHY has been initialized correctly * @mode: contains the current mode the PHY is in + * @update_seq_cfg: tuning parameters for phy init */ struct qcom_snps_hsphy { struct phy *phy; -- GitLab From ad593827db9b73f15eb65416ec975ec0311f773a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 15 May 2023 21:12:31 -0300 Subject: [PATCH 5024/5631] powerpc/iommu: Remove iommu_del_device() Now that power calls iommu_device_register() and populates its groups using iommu_ops->device_group it should not be calling iommu_group_remove_device(). The core code owns the groups and all the other related iommu data, it will clean it up automatically. Remove the bus notifiers and explicit calls to iommu_group_remove_device(). Fixes: a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") Signed-off-by: Jason Gunthorpe Signed-off-by: Michael Ellerman Link: https://msgid.link/0-v1-1421774b874b+167-ppc_device_group_jgg@nvidia.com --- arch/powerpc/include/asm/iommu.h | 5 ----- arch/powerpc/kernel/iommu.c | 17 ----------------- arch/powerpc/platforms/powernv/pci.c | 25 ------------------------- arch/powerpc/platforms/pseries/iommu.c | 25 ------------------------- 4 files changed, 72 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 678b5bdc79b1..34e14dfd8e04 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -205,7 +205,6 @@ extern void iommu_register_group(struct iommu_table_group *table_group, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct iommu_table_group *table_group, struct device *dev); -extern void iommu_del_device(struct device *dev); extern long iommu_tce_xchg(struct mm_struct *mm, struct iommu_table *tbl, unsigned long entry, unsigned long *hpa, enum dma_data_direction *direction); @@ -229,10 +228,6 @@ static inline int iommu_add_device(struct iommu_table_group *table_group, { return 0; } - -static inline void iommu_del_device(struct device *dev) -{ -} #endif /* !CONFIG_IOMMU_API */ u64 dma_iommu_get_required_mask(struct device *dev); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 0089dd49b4cb..8fce2da109eb 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1168,23 +1168,6 @@ int iommu_add_device(struct iommu_table_group *table_group, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_add_device); -void iommu_del_device(struct device *dev) -{ - /* - * Some devices might not have IOMMU table and group - * and we needn't detach them from the associated - * IOMMU groups - */ - if (!device_iommu_mapped(dev)) { - pr_debug("iommu_tce: skipping device %s with no tbl\n", - dev_name(dev)); - return; - } - - iommu_group_remove_device(dev); -} -EXPORT_SYMBOL_GPL(iommu_del_device); - /* * A simple iommu_table_group_ops which only allows reusing the existing * iommu_table. This handles VFIO for POWER7 or the nested KVM. diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 233a50e65fce..7725492097b6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -865,28 +865,3 @@ void __init pnv_pci_init(void) /* Configure IOMMU DMA hooks */ set_pci_dma_ops(&dma_iommu_ops); } - -static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block pnv_tce_iommu_bus_nb = { - .notifier_call = pnv_tce_iommu_bus_notifier, -}; - -static int __init pnv_tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &pnv_tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(powernv, pnv_tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 7464fa6e4145..e44d3c4a0781 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1695,31 +1695,6 @@ static int __init disable_multitce(char *str) __setup("multitce=", disable_multitce); -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_DEL_DEVICE: - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} -machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); - #ifdef CONFIG_SPAPR_TCE_IOMMU struct iommu_group *pSeries_pci_device_group(struct pci_controller *hose, struct pci_dev *pdev) -- GitLab From 096339ab84f36beae0b1db25e0ce63fb3873e8b2 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Thu, 4 May 2023 12:59:13 -0500 Subject: [PATCH 5025/5631] powerpc/iommu: DMA address offset is incorrectly calculated with 2MB TCEs When DMA window is backed by 2MB TCEs, the DMA address for the mapped page should be the offset of the page relative to the 2MB TCE. The code was incorrectly setting the DMA address to the beginning of the TCE range. Mellanox driver is reporting timeout trying to ENABLE_HCA for an SR-IOV ethernet port, when DMA window is backed by 2MB TCEs. Fixes: 387273118714 ("powerps/pseries/dma: Add support for 2M IOMMU page size") Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Gaurav Batra Reviewed-by: Greg Joyce Reviewed-by: Brian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20230504175913.83844-1-gbatra@linux.vnet.ibm.com --- arch/powerpc/kernel/iommu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 8fce2da109eb..67f0b01e6ff5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -518,7 +518,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Convert entry to a dma_addr_t */ entry += tbl->it_offset; dma_addr = entry << tbl->it_page_shift; - dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl)); + dma_addr |= (vaddr & ~IOMMU_PAGE_MASK(tbl)); DBG(" - %lu pages, entry: %lx, dma_addr: %lx\n", npages, entry, dma_addr); @@ -905,6 +905,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, unsigned int order; unsigned int nio_pages, io_order; struct page *page; + int tcesize = (1 << tbl->it_page_shift); size = PAGE_ALIGN(size); order = get_order(size); @@ -931,7 +932,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, memset(ret, 0, size); /* Set up tces to cover the allocated range */ - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; + io_order = get_iommu_order(size, tbl); mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL, mask >> tbl->it_page_shift, io_order, 0); @@ -939,7 +941,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl, free_pages((unsigned long)ret, order); return NULL; } - *dma_handle = mapping; + + *dma_handle = mapping | ((u64)ret & (tcesize - 1)); return ret; } @@ -950,7 +953,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, unsigned int nio_pages; size = PAGE_ALIGN(size); - nio_pages = size >> tbl->it_page_shift; + nio_pages = IOMMU_PAGE_ALIGN(size, tbl) >> tbl->it_page_shift; iommu_free(tbl, dma_handle, nio_pages); size = PAGE_ALIGN(size); free_pages((unsigned long)vaddr, get_order(size)); -- GitLab From 1f7aacc5eb9ed2cc17be7a90da5cd559effb9d59 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Fri, 5 May 2023 13:47:01 -0500 Subject: [PATCH 5026/5631] powerpc/iommu: Incorrect DDW Table is referenced for SR-IOV device For an SR-IOV device, while enabling DDW, a new table is created and added at index 1 in the group. In the below 2 scenarios, the table is incorrectly referenced at index 0 (which is where the table is for default DMA window). 1. When adding DDW This issue is exposed with "slub_debug". Error thrown out from dma_iommu_dma_supported() Warning: IOMMU offset too big for device mask mask: 0xffffffff, table offset: 0x800000000000000 2. During Dynamic removal of the PCI device. Error is from iommu_tce_table_put() since a NULL table pointer is passed in. Fixes: 381ceda88c4c ("powerpc/pseries/iommu: Make use of DDW for indirect mapping") Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Gaurav Batra Reviewed-by: Brian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20230505184701.91613-1-gbatra@linux.vnet.ibm.com --- arch/powerpc/kernel/dma-iommu.c | 4 +++- arch/powerpc/platforms/pseries/iommu.c | 13 +++++++++---- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 038ce8d9061d..8920862ffd79 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -144,7 +144,7 @@ static bool dma_iommu_bypass_supported(struct device *dev, u64 mask) /* We support DMA to/from any memory page via the iommu */ int dma_iommu_dma_supported(struct device *dev, u64 mask) { - struct iommu_table *tbl = get_iommu_table_base(dev); + struct iommu_table *tbl; if (dev_is_pci(dev) && dma_iommu_bypass_supported(dev, mask)) { /* @@ -162,6 +162,8 @@ int dma_iommu_dma_supported(struct device *dev, u64 mask) return 1; } + tbl = get_iommu_table_base(dev); + if (!tbl) { dev_err(dev, "Warning: IOMMU dma not supported: mask 0x%08llx, table unavailable\n", mask); return 0; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e44d3c4a0781..918f511837db 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -91,19 +91,24 @@ static struct iommu_table_group *iommu_pseries_alloc_group(int node) static void iommu_pseries_free_group(struct iommu_table_group *table_group, const char *node_name) { - struct iommu_table *tbl; - if (!table_group) return; - tbl = table_group->tables[0]; #ifdef CONFIG_IOMMU_API if (table_group->group) { iommu_group_put(table_group->group); BUG_ON(table_group->group); } #endif - iommu_tce_table_put(tbl); + + /* Default DMA window table is at index 0, while DDW at 1. SR-IOV + * adapters only have table on index 1. + */ + if (table_group->tables[0]) + iommu_tce_table_put(table_group->tables[0]); + + if (table_group->tables[1]) + iommu_tce_table_put(table_group->tables[1]); kfree(table_group); } -- GitLab From 2a821fc3136d5d99dcb9de152be8a052ca27d870 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Mon, 15 May 2023 16:40:58 +0300 Subject: [PATCH 5027/5631] xhci-pci: Only run d3cold avoidance quirk for s2idle Donghun reports that a notebook that has an AMD Ryzen 5700U but supports S3 has problems with USB after resuming from suspend. The issue was bisected down to commit d1658268e439 ("usb: pci-quirks: disable D3cold on xhci suspend for s2idle on AMD Renoir"). As this issue only happens on S3, narrow the broken D3cold quirk to only run in s2idle. Fixes: d1658268e439 ("usb: pci-quirks: disable D3cold on xhci suspend for s2idle on AMD Renoir") Reported-and-tested-by: Donghun Yoon Cc: stable@vger.kernel.org Signed-off-by: Mario Limonciello Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230515134059.161110-2-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-pci.c | 12 ++++++++++-- drivers/usb/host/xhci.h | 2 +- 2 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index ddb79f23fb3b..79b3691f373f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "xhci.h" #include "xhci-trace.h" @@ -387,7 +388,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) if (pdev->vendor == PCI_VENDOR_ID_AMD && pdev->device == PCI_DEVICE_ID_AMD_RENOIR_XHCI) - xhci->quirks |= XHCI_BROKEN_D3COLD; + xhci->quirks |= XHCI_BROKEN_D3COLD_S2I; if (pdev->vendor == PCI_VENDOR_ID_INTEL) { xhci->quirks |= XHCI_LPM_SUPPORT; @@ -801,9 +802,16 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup) * Systems with the TI redriver that loses port status change events * need to have the registers polled during D3, so avoid D3cold. */ - if (xhci->quirks & (XHCI_COMP_MODE_QUIRK | XHCI_BROKEN_D3COLD)) + if (xhci->quirks & XHCI_COMP_MODE_QUIRK) pci_d3cold_disable(pdev); +#ifdef CONFIG_SUSPEND + /* d3cold is broken, but only when s2idle is used */ + if (pm_suspend_target_state == PM_SUSPEND_TO_IDLE && + xhci->quirks & (XHCI_BROKEN_D3COLD_S2I)) + pci_d3cold_disable(pdev); +#endif + if (xhci->quirks & XHCI_PME_STUCK_QUIRK) xhci_pme_quirk(hcd); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 08d721921b7b..6b690ec91ff3 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1901,7 +1901,7 @@ struct xhci_hcd { #define XHCI_DISABLE_SPARSE BIT_ULL(38) #define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39) #define XHCI_NO_SOFT_RETRY BIT_ULL(40) -#define XHCI_BROKEN_D3COLD BIT_ULL(41) +#define XHCI_BROKEN_D3COLD_S2I BIT_ULL(41) #define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42) #define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43) #define XHCI_RESET_TO_DEFAULT BIT_ULL(44) -- GitLab From fe82f16aafdaf8002281d3b9524291d4a4a28460 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Mon, 15 May 2023 16:40:59 +0300 Subject: [PATCH 5028/5631] xhci: Fix incorrect tracking of free space on transfer rings This incorrect tracking caused unnecessary ring expansion in some usecases which over days of use consume a lot of memory. xhci driver tries to keep track of free transfer blocks (TRBs) on the ring buffer, but failed to add back some cancelled transfers that were turned into no-op operations instead of just moving past them. This can happen if there are several queued pending transfers which then are cancelled in reverse order. Solve this by counting the numer of steps we move the dequeue pointer once we complete a transfer, and add it to the number of free trbs instead of just adding the trb number of the current transfer. This way we ensure we count the no-op trbs on the way as well. Fixes: 55f6153d8cc8 ("xhci: remove extra loop in interrupt context") Cc: stable@vger.kernel.org Reported-by: Miller Hunter Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217242 Tested-by: Miller Hunter Signed-off-by: Mathias Nyman Link: https://lore.kernel.org/r/20230515134059.161110-3-mathias.nyman@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/host/xhci-ring.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1ad12d5a4857..2bc82b3a2f98 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -276,6 +276,26 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring, trace_xhci_inc_enq(ring); } +static int xhci_num_trbs_to(struct xhci_segment *start_seg, union xhci_trb *start, + struct xhci_segment *end_seg, union xhci_trb *end, + unsigned int num_segs) +{ + union xhci_trb *last_on_seg; + int num = 0; + int i = 0; + + do { + if (start_seg == end_seg && end >= start) + return num + (end - start); + last_on_seg = &start_seg->trbs[TRBS_PER_SEGMENT - 1]; + num += last_on_seg - start; + start_seg = start_seg->next; + start = start_seg->trbs; + } while (i++ <= num_segs); + + return -EINVAL; +} + /* * Check to see if there's room to enqueue num_trbs on the ring and make sure * enqueue pointer will not advance into dequeue segment. See rules above. @@ -2140,6 +2160,7 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, u32 trb_comp_code) { struct xhci_ep_ctx *ep_ctx; + int trbs_freed; ep_ctx = xhci_get_ep_ctx(xhci, ep->vdev->out_ctx, ep->ep_index); @@ -2209,9 +2230,15 @@ static int finish_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, } /* Update ring dequeue pointer */ + trbs_freed = xhci_num_trbs_to(ep_ring->deq_seg, ep_ring->dequeue, + td->last_trb_seg, td->last_trb, + ep_ring->num_segs); + if (trbs_freed < 0) + xhci_dbg(xhci, "Failed to count freed trbs at TD finish\n"); + else + ep_ring->num_trbs_free += trbs_freed; ep_ring->dequeue = td->last_trb; ep_ring->deq_seg = td->last_trb_seg; - ep_ring->num_trbs_free += td->num_trbs - 1; inc_deq(xhci, ep_ring); return xhci_td_cleanup(xhci, td, ep_ring, td->status); -- GitLab From 02f76c401d17e409ed45bf7887148fcc22c93c85 Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sun, 14 May 2023 12:05:05 +0900 Subject: [PATCH 5029/5631] ksmbd: fix global-out-of-bounds in smb2_find_context_vals Add tag_len argument in smb2_find_context_vals() to avoid out-of-bound read when create_context's name_len is larger than tag length. [ 7.995411] ================================================================== [ 7.995866] BUG: KASAN: global-out-of-bounds in memcmp+0x83/0xa0 [ 7.996248] Read of size 8 at addr ffffffff8258d940 by task kworker/0:0/7 ... [ 7.998191] Call Trace: [ 7.998358] [ 7.998503] dump_stack_lvl+0x33/0x50 [ 7.998743] print_report+0xcc/0x620 [ 7.999458] kasan_report+0xae/0xe0 [ 7.999895] kasan_check_range+0x35/0x1b0 [ 8.000152] memcmp+0x83/0xa0 [ 8.000347] smb2_find_context_vals+0xf7/0x1e0 [ 8.000635] smb2_open+0x1df2/0x43a0 [ 8.006398] handle_ksmbd_work+0x274/0x810 [ 8.006666] process_one_work+0x419/0x760 [ 8.006922] worker_thread+0x2a2/0x6f0 [ 8.007429] kthread+0x160/0x190 [ 8.007946] ret_from_fork+0x1f/0x30 [ 8.008181] Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/oplock.c | 5 +++-- fs/ksmbd/oplock.h | 2 +- fs/ksmbd/smb2pdu.c | 14 +++++++------- 3 files changed, 11 insertions(+), 10 deletions(-) diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 2e54ded4d92c..6d1ccb999893 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1449,11 +1449,12 @@ struct lease_ctx_info *parse_lease_state(void *open_req) * smb2_find_context_vals() - find a particular context info in open request * @open_req: buffer containing smb2 file open(create) request * @tag: context name to search for + * @tag_len: the length of tag * * Return: pointer to requested context, NULL if @str context not found * or error pointer if name length is invalid. */ -struct create_context *smb2_find_context_vals(void *open_req, const char *tag) +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len) { struct create_context *cc; unsigned int next = 0; @@ -1492,7 +1493,7 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag) return ERR_PTR(-EINVAL); name = (char *)cc + name_off; - if (memcmp(name, tag, name_len) == 0) + if (name_len == tag_len && !memcmp(name, tag, name_len)) return cc; remain_len -= next; diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 09753448f779..4b0fe6da7694 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -118,7 +118,7 @@ void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp); void create_mxac_rsp_buf(char *cc, int maximal_access); void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id); void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); -struct create_context *smb2_find_context_vals(void *open_req, const char *str); +struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index cb93fd231f4e..f317ce2461ee 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2464,7 +2464,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, return -ENOENT; /* Parse SD BUFFER create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_SD_BUFFER, 4); if (!context) return -ENOENT; else if (IS_ERR(context)) @@ -2666,7 +2666,7 @@ int smb2_open(struct ksmbd_work *work) if (req->CreateContextsOffset) { /* Parse non-durable handle create contexts */ - context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER); + context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2686,7 +2686,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST); + SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2697,7 +2697,7 @@ int smb2_open(struct ksmbd_work *work) } context = smb2_find_context_vals(req, - SMB2_CREATE_TIMEWARP_REQUEST); + SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -2709,7 +2709,7 @@ int smb2_open(struct ksmbd_work *work) if (tcon->posix_extensions) { context = smb2_find_context_vals(req, - SMB2_CREATE_TAG_POSIX); + SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out1; @@ -3107,7 +3107,7 @@ int smb2_open(struct ksmbd_work *work) struct create_alloc_size_req *az_req; az_req = (struct create_alloc_size_req *)smb2_find_context_vals(req, - SMB2_CREATE_ALLOCATION_SIZE); + SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); goto err_out; @@ -3134,7 +3134,7 @@ int smb2_open(struct ksmbd_work *work) err); } - context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID); + context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); goto err_out; -- GitLab From f0a96d1aafd8964e1f9955c830a3e5cb3c60a90f Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sat, 6 May 2023 00:01:54 +0900 Subject: [PATCH 5030/5631] ksmbd: fix wrong UserName check in session_user The offset of UserName is related to the address of security buffer. To ensure the validaty of UserName, we need to compare name_off + name_len with secbuf_len instead of auth_msg_len. [ 27.096243] ================================================================== [ 27.096890] BUG: KASAN: slab-out-of-bounds in smb_strndup_from_utf16+0x188/0x350 [ 27.097609] Read of size 2 at addr ffff888005e3b542 by task kworker/0:0/7 ... [ 27.099950] Call Trace: [ 27.100194] [ 27.100397] dump_stack_lvl+0x33/0x50 [ 27.100752] print_report+0xcc/0x620 [ 27.102305] kasan_report+0xae/0xe0 [ 27.103072] kasan_check_range+0x35/0x1b0 [ 27.103757] smb_strndup_from_utf16+0x188/0x350 [ 27.105474] smb2_sess_setup+0xaf8/0x19c0 [ 27.107935] handle_ksmbd_work+0x274/0x810 [ 27.108315] process_one_work+0x419/0x760 [ 27.108689] worker_thread+0x2a2/0x6f0 [ 27.109385] kthread+0x160/0x190 [ 27.110129] ret_from_fork+0x1f/0x30 [ 27.110454] Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2pdu.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index f317ce2461ee..717bcd20545b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1356,7 +1356,7 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, struct authenticate_message *authblob; struct ksmbd_user *user; char *name; - unsigned int auth_msg_len, name_off, name_len, secbuf_len; + unsigned int name_off, name_len, secbuf_len; secbuf_len = le16_to_cpu(req->SecurityBufferLength); if (secbuf_len < sizeof(struct authenticate_message)) { @@ -1366,9 +1366,8 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn, authblob = user_authblob(conn, req); name_off = le32_to_cpu(authblob->UserName.BufferOffset); name_len = le16_to_cpu(authblob->UserName.Length); - auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len; - if (auth_msg_len < (u64)name_off + name_len) + if (secbuf_len < (u64)name_off + name_len) return NULL; name = smb_strndup_from_utf16((const char *)authblob + name_off, -- GitLab From 443d61d1fa9faa60ef925513d83742902390100f Mon Sep 17 00:00:00 2001 From: Chih-Yen Chang Date: Sat, 6 May 2023 00:03:54 +0900 Subject: [PATCH 5031/5631] ksmbd: allocate one more byte for implied bcc[0] ksmbd_smb2_check_message allows client to return one byte more, so we need to allocate additional memory in ksmbd_conn_handler_loop to avoid out-of-bound access. Cc: stable@vger.kernel.org Signed-off-by: Chih-Yen Chang Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/connection.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 4ed379f9b1aa..4882a812ea86 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -351,7 +351,8 @@ int ksmbd_conn_handler_loop(void *p) break; /* 4 for rfc1002 length field */ - size = pdu_size + 4; + /* 1 for implied bcc[0] */ + size = pdu_size + 4 + 1; conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; -- GitLab From e7b8b8ed9960bf699bf4029f482d9e869c094ed6 Mon Sep 17 00:00:00 2001 From: Gustav Johansson Date: Sat, 6 May 2023 00:05:07 +0900 Subject: [PATCH 5032/5631] ksmbd: smb2: Allow messages padded to 8byte boundary clc length is now accepted to <= 8 less than length, rather than < 8. Solve issues on some of Axis's smb clients which send messages where clc length is 8 bytes less than length. The specific client was running kernel 4.19.217 with smb dialect 3.0.2 on armv7l. Cc: stable@vger.kernel.org Signed-off-by: Gustav Johansson Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/ksmbd/smb2misc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c index fbdde426dd01..0ffe663b7590 100644 --- a/fs/ksmbd/smb2misc.c +++ b/fs/ksmbd/smb2misc.c @@ -416,8 +416,11 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work) /* * Allow a message that padded to 8byte boundary. + * Linux 4.19.217 with smb 3.0.2 are sometimes + * sending messages where the cls_len is exactly + * 8 bytes less than len. */ - if (clc_len < len && (len - clc_len) < 8) + if (clc_len < len && (len - clc_len) <= 8) goto validate_credit; pr_err_ratelimited( -- GitLab From ab7470bc6d8fb5f3004ccc8e4dfd49aab0f27561 Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Mon, 17 Apr 2023 17:44:45 -0600 Subject: [PATCH 5033/5631] ice: Fix stats after PF reset After a core PF reset, the VFs were showing wrong Rx/Tx stats. This is a regression in commit 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") caused by missing to set "stat_offsets_loaded = false" in the ice_vsi_rebuild() path. Fixes: 6624e780a577 ("ice: split ice_vsi_setup into smaller functions") Signed-off-by: Ahmed Zaki Reviewed-by: Alexander Lobakin Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 450317dfcca7..11ae0e41f518 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2745,6 +2745,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -2793,6 +2795,9 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value -- GitLab From 7255355a0636b4eff08d5e8139c77d98f151c4fc Mon Sep 17 00:00:00 2001 From: Dawid Wesierski Date: Tue, 18 Apr 2023 11:52:55 +0200 Subject: [PATCH 5034/5631] ice: Fix ice VF reset during iavf initialization Fix the current implementation that causes ice_trigger_vf_reset() to start resetting the VF even when the VF-NIC is still initializing. When we reset NIC with ice driver it can interfere with iavf-vf initialization e.g. during consecutive resets induced by ice iavf ice | | |<-----------------| | ice resets vf iavf | reset | start | |<-----------------| | ice resets vf | causing iavf | initialization | error | | iavf reset end This leads to a series of -53 errors (failed to init adminq) from the IAVF. Change the state of the vf_state field to be not active when the IAVF is still initializing. Make sure to wait until receiving the message on the message box to ensure that the vf is ready and initializded. In simple terms we use the ACTIVE flag to make sure that the ice driver knows if the iavf is ready for another reset iavf ice | | | | |<------------- ice resets vf iavf vf_state != ACTIVE reset | start | | | | | iavf | reset-------> vf_state == ACTIVE end ice resets vf | | | | Fixes: c54d209c78b8 ("ice: Wait for VF to be reset/ready before configuration") Signed-off-by: Dawid Wesierski Signed-off-by: Kamil Maziarz Acked-by: Jacob Keller Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_sriov.c | 8 ++++---- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 19 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_vf_lib.h | 1 + drivers/net/ethernet/intel/ice/ice_virtchnl.c | 1 + 4 files changed, 25 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index f1dca59bd844..588ad8696756 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1171,7 +1171,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1286,7 +1286,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1340,7 +1340,7 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) return -EOPNOTSUPP; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1653,7 +1653,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 89fd6982df09..bf74a2f3a4f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -185,6 +185,25 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return 0; } +/** + * ice_check_vf_ready_for_reset - check if VF is ready to be reset + * @vf: VF to check if it's ready to be reset + * + * The purpose of this function is to ensure that the VF is not in reset, + * disabled, and is both initialized and active, thus enabling us to safely + * initialize another reset. + */ +int ice_check_vf_ready_for_reset(struct ice_vf *vf) +{ + int ret; + + ret = ice_check_vf_ready_for_cfg(vf); + if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ret = -EAGAIN; + + return ret; +} + /** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index e3cda6fb71ab..a38ef00a3679 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -215,6 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 97243c616d5d..f4a524f80b11 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3955,6 +3955,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: -- GitLab From 7dcbdf29282fbcdb646dc785e8a57ed2c2fec8ba Mon Sep 17 00:00:00 2001 From: Ahmed Zaki Date: Mon, 17 Apr 2023 12:09:39 -0600 Subject: [PATCH 5035/5631] iavf: send VLAN offloading caps once after VFR When the user disables rxvlan offloading and then changes the number of channels, all VLAN ports are unable to receive traffic. Changing the number of channels triggers a VFR reset. During re-init, when VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS is received, we do: 1 - set the IAVF_FLAG_SETUP_NETDEV_FEATURES flag 2 - call iavf_set_vlan_offload_features(adapter, 0, netdev->features); The second step sends to the PF the __default__ features, in this case aq_required |= IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_STRIPPING While the first step forces the watchdog task to call netdev_update_features() -> iavf_set_features() -> iavf_set_vlan_offload_features(adapter, netdev->features, features). Since the user disabled the "rxvlan", this sets: aq_required |= IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_STRIPPING When we start processing the AQ commands, both flags are enabled. Since we process DISABLE_XTAG first then ENABLE_XTAG, this results in the PF enabling the rxvlan offload. This breaks all communications on the VLAN net devices. Fix by removing the call to iavf_set_vlan_offload_features() (second step). Calling netdev_update_features() from watchdog task is enough for both init and reset paths. Fixes: 7598f4b40bd6 ("iavf: Move netdev_update_features() into watchdog task") Signed-off-by: Ahmed Zaki Tested-by: Rafal Romanowski Reviewed-by: Leon Romanovsky Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 9afbbdac3590..7c0578b5457b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2238,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter); was_mac_changed = !ether_addr_equal(netdev->dev_addr, -- GitLab From 2d2f5f1e8fd91fe848aacde28f738fb8e8d95a27 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 3 May 2023 13:41:27 +0300 Subject: [PATCH 5036/5631] accel/qaic: silence some uninitialized variable warnings Smatch complains that these are not initialized if get_cntl_version() fails but we still print them in the debug message. Not the end of the world, but true enough. Let's just initialize them to a dummy value to make the checker happy. Fixes: c501ca23a6a3 ("accel/qaic: Add uapi and core driver file") Signed-off-by: Dan Carpenter Reviewed-by: Jeffrey Hugo Reviewed-by: Carl Vanderlip Reviewed-by: Pranjal Ramajor Asha Kanojiya [jhugo: Add fixes and reorder varable declarations for style] Signed-off-by: Jeffrey Hugo Link: https://patchwork.freedesktop.org/patch/msgid/d11ee378-7b06-4b5e-b56f-d66174be1ab3@kili.mountain --- drivers/accel/qaic/qaic_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c index ff80eb571729..2d0828db28d8 100644 --- a/drivers/accel/qaic/qaic_drv.c +++ b/drivers/accel/qaic/qaic_drv.c @@ -262,8 +262,8 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id) static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id) { + u16 major = -1, minor = -1; struct qaic_device *qdev; - u16 major, minor; int ret; /* -- GitLab From 1b6b4ed01493b7ea2205ab83c49198f7d13ca9d2 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Mon, 24 Apr 2023 10:32:24 +0300 Subject: [PATCH 5037/5631] wifi: cfg80211: Drop entries with invalid BSSIDs in RNR Ignore AP information for entries that include an invalid BSSID in the TBTT information field, e.g., all zeros BSSIDs. Fixes: c8cb5b854b40 ("nl80211/cfg80211: support 6 GHz scanning") Signed-off-by: Ilan Peer Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230424103224.5e65d04d1448.Ic10c8577ae4a85272c407106c9d0a2ecb5372743@changeid Signed-off-by: Johannes Berg --- net/wireless/scan.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index a1382255fab3..c501db7bbdb3 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2022 Intel Corporation + * Copyright (C) 2018-2023 Intel Corporation */ #include #include @@ -540,6 +540,10 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, /* skip the TBTT offset */ pos++; + /* ignore entries with invalid BSSID */ + if (!is_valid_ether_addr(pos)) + return -EINVAL; + memcpy(entry->bssid, pos, ETH_ALEN); pos += ETH_ALEN; -- GitLab From ef6e1997da63ad0ac3fe33153fec9524c9ae56c9 Mon Sep 17 00:00:00 2001 From: Mirsad Goran Todorovac Date: Tue, 25 Apr 2023 18:40:08 +0200 Subject: [PATCH 5038/5631] wifi: mac80211: fortify the spinlock against deadlock by interrupt In the function ieee80211_tx_dequeue() there is a particular locking sequence: begin: spin_lock(&local->queue_stop_reason_lock); q_stopped = local->queue_stop_reasons[q]; spin_unlock(&local->queue_stop_reason_lock); However small the chance (increased by ftracetest), an asynchronous interrupt can occur in between of spin_lock() and spin_unlock(), and the interrupt routine will attempt to lock the same &local->queue_stop_reason_lock again. This will cause a costly reset of the CPU and the wifi device or an altogether hang in the single CPU and single core scenario. The only remaining spin_lock(&local->queue_stop_reason_lock) that did not disable interrupts was patched, which should prevent any deadlocks on the same CPU/core and the same wifi device. This is the probable trace of the deadlock: kernel: ================================ kernel: WARNING: inconsistent lock state kernel: 6.3.0-rc6-mt-20230401-00001-gf86822a1170f #4 Tainted: G W kernel: -------------------------------- kernel: inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. kernel: kworker/5:0/25656 [HC0[0]:SC0[0]:HE1:SE1] takes: kernel: ffff9d6190779478 (&local->queue_stop_reason_lock){+.?.}-{2:2}, at: return_to_handler+0x0/0x40 kernel: {IN-SOFTIRQ-W} state was registered at: kernel: lock_acquire+0xc7/0x2d0 kernel: _raw_spin_lock+0x36/0x50 kernel: ieee80211_tx_dequeue+0xb4/0x1330 [mac80211] kernel: iwl_mvm_mac_itxq_xmit+0xae/0x210 [iwlmvm] kernel: iwl_mvm_mac_wake_tx_queue+0x2d/0xd0 [iwlmvm] kernel: ieee80211_queue_skb+0x450/0x730 [mac80211] kernel: __ieee80211_xmit_fast.constprop.66+0x834/0xa50 [mac80211] kernel: __ieee80211_subif_start_xmit+0x217/0x530 [mac80211] kernel: ieee80211_subif_start_xmit+0x60/0x580 [mac80211] kernel: dev_hard_start_xmit+0xb5/0x260 kernel: __dev_queue_xmit+0xdbe/0x1200 kernel: neigh_resolve_output+0x166/0x260 kernel: ip_finish_output2+0x216/0xb80 kernel: __ip_finish_output+0x2a4/0x4d0 kernel: ip_finish_output+0x2d/0xd0 kernel: ip_output+0x82/0x2b0 kernel: ip_local_out+0xec/0x110 kernel: igmpv3_sendpack+0x5c/0x90 kernel: igmp_ifc_timer_expire+0x26e/0x4e0 kernel: call_timer_fn+0xa5/0x230 kernel: run_timer_softirq+0x27f/0x550 kernel: __do_softirq+0xb4/0x3a4 kernel: irq_exit_rcu+0x9b/0xc0 kernel: sysvec_apic_timer_interrupt+0x80/0xa0 kernel: asm_sysvec_apic_timer_interrupt+0x1f/0x30 kernel: _raw_spin_unlock_irqrestore+0x3f/0x70 kernel: free_to_partial_list+0x3d6/0x590 kernel: __slab_free+0x1b7/0x310 kernel: kmem_cache_free+0x52d/0x550 kernel: putname+0x5d/0x70 kernel: do_sys_openat2+0x1d7/0x310 kernel: do_sys_open+0x51/0x80 kernel: __x64_sys_openat+0x24/0x30 kernel: do_syscall_64+0x5c/0x90 kernel: entry_SYSCALL_64_after_hwframe+0x72/0xdc kernel: irq event stamp: 5120729 kernel: hardirqs last enabled at (5120729): [] trace_graph_return+0xd6/0x120 kernel: hardirqs last disabled at (5120728): [] trace_graph_return+0xf0/0x120 kernel: softirqs last enabled at (5069900): [] return_to_handler+0x0/0x40 kernel: softirqs last disabled at (5067555): [] return_to_handler+0x0/0x40 kernel: other info that might help us debug this: kernel: Possible unsafe locking scenario: kernel: CPU0 kernel: ---- kernel: lock(&local->queue_stop_reason_lock); kernel: kernel: lock(&local->queue_stop_reason_lock); kernel: *** DEADLOCK *** kernel: 8 locks held by kworker/5:0/25656: kernel: #0: ffff9d618009d138 ((wq_completion)events_freezable){+.+.}-{0:0}, at: process_one_work+0x1ca/0x530 kernel: #1: ffffb1ef4637fe68 ((work_completion)(&local->restart_work)){+.+.}-{0:0}, at: process_one_work+0x1ce/0x530 kernel: #2: ffffffff9f166548 (rtnl_mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #3: ffff9d6190778728 (&rdev->wiphy.mtx){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #4: ffff9d619077b480 (&mvm->mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #5: ffff9d61907bacd8 (&trans_pcie->mutex){+.+.}-{3:3}, at: return_to_handler+0x0/0x40 kernel: #6: ffffffff9ef9cda0 (rcu_read_lock){....}-{1:2}, at: iwl_mvm_queue_state_change+0x59/0x3a0 [iwlmvm] kernel: #7: ffffffff9ef9cda0 (rcu_read_lock){....}-{1:2}, at: iwl_mvm_mac_itxq_xmit+0x42/0x210 [iwlmvm] kernel: stack backtrace: kernel: CPU: 5 PID: 25656 Comm: kworker/5:0 Tainted: G W 6.3.0-rc6-mt-20230401-00001-gf86822a1170f #4 kernel: Hardware name: LENOVO 82H8/LNVNB161216, BIOS GGCN51WW 11/16/2022 kernel: Workqueue: events_freezable ieee80211_restart_work [mac80211] kernel: Call Trace: kernel: kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: dump_stack_lvl+0x5f/0xa0 kernel: dump_stack+0x14/0x20 kernel: print_usage_bug.part.46+0x208/0x2a0 kernel: mark_lock.part.47+0x605/0x630 kernel: ? sched_clock+0xd/0x20 kernel: ? trace_clock_local+0x14/0x30 kernel: ? __rb_reserve_next+0x5f/0x490 kernel: ? _raw_spin_lock+0x1b/0x50 kernel: __lock_acquire+0x464/0x1990 kernel: ? mark_held_locks+0x4e/0x80 kernel: lock_acquire+0xc7/0x2d0 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ? ftrace_return_to_handler+0x8b/0x100 kernel: ? preempt_count_add+0x4/0x70 kernel: _raw_spin_lock+0x36/0x50 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_tx_dequeue+0xb4/0x1330 [mac80211] kernel: ? prepare_ftrace_return+0xc5/0x190 kernel: ? ftrace_graph_func+0x16/0x20 kernel: ? 0xffffffffc02ab0b1 kernel: ? lock_acquire+0xc7/0x2d0 kernel: ? iwl_mvm_mac_itxq_xmit+0x42/0x210 [iwlmvm] kernel: ? ieee80211_tx_dequeue+0x9/0x1330 [mac80211] kernel: ? __rcu_read_lock+0x4/0x40 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_mac_itxq_xmit+0xae/0x210 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_queue_state_change+0x311/0x3a0 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_wake_sw_queue+0x17/0x20 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_unmap+0x1c9/0x1f0 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_free+0x55/0x130 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_txq_gen2_tx_free+0x63/0x80 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: _iwl_trans_pcie_gen2_stop_device+0x3f3/0x5b0 [iwlwifi] kernel: ? _iwl_trans_pcie_gen2_stop_device+0x9/0x5b0 [iwlwifi] kernel: ? mutex_lock_nested+0x4/0x30 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_trans_pcie_gen2_stop_device+0x5f/0x90 [iwlwifi] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_stop_device+0x78/0xd0 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: __iwl_mvm_mac_start+0x114/0x210 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: iwl_mvm_mac_start+0x76/0x150 [iwlmvm] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: drv_start+0x79/0x180 [mac80211] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_reconfig+0x1523/0x1ce0 [mac80211] kernel: ? synchronize_net+0x4/0x50 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: ieee80211_restart_work+0x108/0x170 [mac80211] kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: process_one_work+0x250/0x530 kernel: ? ftrace_regs_caller_end+0x66/0x66 kernel: worker_thread+0x48/0x3a0 kernel: ? __pfx_worker_thread+0x10/0x10 kernel: kthread+0x10f/0x140 kernel: ? __pfx_kthread+0x10/0x10 kernel: ret_from_fork+0x29/0x50 kernel: Fixes: 4444bc2116ae ("wifi: mac80211: Proper mark iTXQs for resumption") Link: https://lore.kernel.org/all/1f58a0d1-d2b9-d851-73c3-93fcc607501c@alu.unizg.hr/ Reported-by: Mirsad Goran Todorovac Cc: Gregory Greenman Cc: Johannes Berg Link: https://lore.kernel.org/all/cdc80531-f25f-6f9d-b15f-25e16130b53a@alu.unizg.hr/ Cc: David S. Miller Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Cc: Alexander Wetzel Signed-off-by: Mirsad Goran Todorovac Reviewed-by: Leon Romanovsky Reviewed-by: tag, or it goes automatically? Link: https://lore.kernel.org/r/20230425164005.25272-1-mirsad.todorovac@alu.unizg.hr Signed-off-by: Johannes Berg --- net/mac80211/tx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1a3327407552..0d9fbc8458fd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3791,6 +3791,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; int q = vif->hw_queue[txq->ac]; + unsigned long flags; bool q_stopped; WARN_ON_ONCE(softirq_count() == 0); @@ -3799,9 +3800,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, return NULL; begin: - spin_lock(&local->queue_stop_reason_lock); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); q_stopped = local->queue_stop_reasons[q]; - spin_unlock(&local->queue_stop_reason_lock); + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); if (unlikely(q_stopped)) { /* mark for waking later */ -- GitLab From 13ad2b1eeacd48ec0f31f55964e6dc7dfc2c0299 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 24 Apr 2023 19:42:04 +0200 Subject: [PATCH 5039/5631] wifi: mac80211: Fix puncturing bitmap handling in __ieee80211_csa_finalize() 'changed' can be OR'ed with BSS_CHANGED_EHT_PUNCTURING which is larger than an u32. So, turn 'changed' into an u64 and update ieee80211_set_after_csa_beacon() accordingly. In the commit in Fixes, only ieee80211_start_ap() was updated. Fixes: 2cc25e4b2a04 ("wifi: mac80211: configure puncturing bitmap") Signed-off-by: Christophe JAILLET Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/e84a3f80fe536787f7a2c7180507efc36cd14f95.1682358088.git.christophe.jaillet@wanadoo.fr Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7317e4a5d1ff..c5e5f783f137 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -3589,7 +3589,7 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, - u32 *changed) + u64 *changed) { int err; @@ -3632,7 +3632,7 @@ static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata, static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - u32 changed = 0; + u64 changed = 0; int err; sdata_assert_lock(sdata); -- GitLab From 9e26f098a2a5a4c4cd327ad911ed2eb9a067a7b8 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 30 Apr 2023 20:18:30 +0300 Subject: [PATCH 5040/5631] wifi: iwlwifi: mvm: rfi: disable RFI feature This feature depends on a platform bugfix. Until we have a mechanism that can verify a platform has the required bugfix, disable RFI. Fixes: ef3ed33dfc8f ("wifi: iwlwifi: bump FW API to 77 for AX devices") Reported-by: Jeff Chua Link: https://lore.kernel.org/linux-wireless/CAAJw_ZvZdFpw9W2Hisc9c2BAFbYAnQuaFFaFG6N7qPUP2fOL_w@mail.gmail.com/ Signed-off-by: Gregory Greenman Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 3 +-- drivers/net/wireless/intel/iwlwifi/mvm/mvm.h | 1 + drivers/net/wireless/intel/iwlwifi/mvm/rfi.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index b35c96cf7ad2..e2573a9d6f27 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1727,8 +1727,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm) iwl_mvm_tas_init(mvm); iwl_mvm_leds_sync(mvm); - if (fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) { + if (iwl_rfi_supported(mvm)) { if (iwl_mvm_eval_dsm_rfi(mvm) == DSM_VALUE_RFI_ENABLE) iwl_rfi_send_config_cmd(mvm, NULL); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 6e7470d3a826..9e5008e0e47f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -2347,6 +2347,7 @@ int iwl_mvm_mld_update_sta_keys(struct iwl_mvm *mvm, u32 old_sta_mask, u32 new_sta_mask); +bool iwl_rfi_supported(struct iwl_mvm *mvm); int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table); struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index bb77bc9aa821..2ecd32bed752 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2020 - 2021 Intel Corporation + * Copyright (C) 2020 - 2022 Intel Corporation */ #include "mvm.h" @@ -70,6 +70,16 @@ static const struct iwl_rfi_lut_entry iwl_rfi_table[IWL_RFI_LUT_SIZE] = { PHY_BAND_6, PHY_BAND_6,}}, }; +bool iwl_rfi_supported(struct iwl_mvm *mvm) +{ + /* The feature depends on a platform bugfix, so for now + * it's always disabled. + * When the platform support detection is implemented we should + * check FW TLV and platform support instead. + */ + return false; +} + int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_table) { int ret; @@ -81,7 +91,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t .len[0] = sizeof(cmd), }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return -EOPNOTSUPP; lockdep_assert_held(&mvm->mutex); @@ -113,7 +123,7 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm) .flags = CMD_WANT_SKB, }; - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) + if (!iwl_rfi_supported(mvm)) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&mvm->mutex); -- GitLab From 248e4776514bf70236e6b1a54c65aa5324c8b1eb Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:01 +0300 Subject: [PATCH 5041/5631] wifi: mac80211: fix min center freq offset tracing We need to set the correct trace variable, otherwise we're overwriting something else instead and the right one that we print later is not initialized. Fixes: b6011960f392 ("mac80211: handle channel frequency offset") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-2-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/trace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index de5d69f21306..db0d0132c58c 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -67,7 +67,7 @@ __entry->min_freq_offset = (c)->chan ? (c)->chan->freq_offset : 0; \ __entry->min_chan_width = (c)->width; \ __entry->min_center_freq1 = (c)->center_freq1; \ - __entry->freq1_offset = (c)->freq1_offset; \ + __entry->min_freq1_offset = (c)->freq1_offset; \ __entry->min_center_freq2 = (c)->center_freq2; #define MIN_CHANDEF_PR_FMT " min_control:%d.%03d MHz min_width:%d min_center: %d.%03d/%d MHz" #define MIN_CHANDEF_PR_ARG __entry->min_control_freq, __entry->min_freq_offset, \ -- GitLab From a23d7f5b2fbda114de60c4b53311e052281d7533 Mon Sep 17 00:00:00 2001 From: Michael Lee Date: Thu, 4 May 2023 16:04:41 +0800 Subject: [PATCH 5042/5631] wifi: mac80211: Abort running color change when stopping the AP When stopping the AP, there might be a color change in progress. It should be deactivated here, or the driver might later finalize a color change on a stopped AP. Fixes: 5f9404abdf2a (mac80211: add support for BSS color change) Signed-off-by: Michael Lee Link: https://lore.kernel.org/r/20230504080441.22958-1-michael-cy.lee@mediatek.com Signed-off-by: Johannes Berg --- net/mac80211/cfg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c5e5f783f137..86b2036d73ff 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1578,9 +1578,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); - /* abort any running channel switch */ + /* abort any running channel switch or color change */ mutex_lock(&local->mtx); link_conf->csa_active = false; + link_conf->color_change_active = false; if (link->csa_block_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); -- GitLab From 860e1b43da94551cd1e73adc36b3c64cc3e5dc01 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:02 +0300 Subject: [PATCH 5043/5631] wifi: mac80211: simplify chanctx allocation There's no need to call ieee80211_recalc_chanctx_min_def() since it cannot and won't call the driver anyway; just use _ieee80211_recalc_chanctx_min_def() instead. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-3-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index dbc34fbe7c8f..d23d1a7b4cc3 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -638,7 +638,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx); return ctx; } -- GitLab From b72a455a2409fd94d6d9b4eb51d659a88213243b Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:03 +0300 Subject: [PATCH 5044/5631] wifi: mac80211: consider reserved chanctx for mindef When a chanctx is reserved for a new vif and we recalculate the minimal definition for it, we need to consider the new interface it's being reserved for before we assign it, so it can be used directly with the correct min channel width. Fix the code to - optionally - consider that, and use that option just before doing the reassignment. Also, when considering channel context reservations, we should only consider the one link we're currently working with. Change the boolean argument to a link pointer to do that. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-4-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 72 +++++++++++++++++++++++--------------- net/mac80211/ieee80211_i.h | 3 +- net/mac80211/util.c | 2 +- 3 files changed, 47 insertions(+), 30 deletions(-) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index d23d1a7b4cc3..1b182cf9d661 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -258,7 +258,8 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; struct ieee80211_vif *vif = &sdata->vif; @@ -267,13 +268,14 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; - struct ieee80211_bss_conf *link_conf = - rcu_dereference(sdata->vif.link_conf[link_id]); + struct ieee80211_link_data *link = + rcu_dereference(sdata->link[link_id]); - if (!link_conf) + if (!link) continue; - if (rcu_access_pointer(link_conf->chanctx_conf) != conf) + if (link != rsvd_for && + rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) continue; switch (vif->type) { @@ -287,7 +289,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, * point, so take the width from the chandef, but * account also for TDLS peers */ - width = max(link_conf->chandef.width, + width = max(link->conf->chandef.width, ieee80211_get_max_required_bw(sdata, link_id)); break; case NL80211_IFTYPE_P2P_DEVICE: @@ -296,7 +298,7 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: - width = link_conf->chandef.width; + width = link->conf->chandef.width; break; case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_UNSPECIFIED: @@ -316,7 +318,8 @@ ieee80211_get_chanctx_vif_max_required_bw(struct ieee80211_sub_if_data *sdata, static enum nl80211_chan_width ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, - struct ieee80211_chanctx_conf *conf) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { struct ieee80211_sub_if_data *sdata; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; @@ -328,7 +331,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, if (!ieee80211_sdata_running(sdata)) continue; - width = ieee80211_get_chanctx_vif_max_required_bw(sdata, conf); + width = ieee80211_get_chanctx_vif_max_required_bw(sdata, ctx, + rsvd_for); max_bw = max(max_bw, width); } @@ -336,8 +340,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, /* use the configured bandwidth in case of monitor interface */ sdata = rcu_dereference(local->monitor_sdata); if (sdata && - rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == conf) - max_bw = max(max_bw, conf->def.width); + rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) == &ctx->conf) + max_bw = max(max_bw, ctx->conf.def.width); rcu_read_unlock(); @@ -349,8 +353,10 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +static u32 +_ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -370,7 +376,7 @@ static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, return 0; } - max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); + max_bw = ieee80211_get_chanctx_max_required_bw(local, ctx, rsvd_for); /* downgrade chandef up to max_bw */ min_def = ctx->conf.def; @@ -448,9 +454,10 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, * channel context. */ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for) { - u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx); + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); if (!changed) return; @@ -464,10 +471,11 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chan_bw_change(local, ctx, false); } -static void ieee80211_change_chanctx(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_chanctx *old_ctx, - const struct cfg80211_chan_def *chandef) +static void _ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef, + struct ieee80211_link_data *rsvd_for) { u32 changed; @@ -492,7 +500,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, true); if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); return; } @@ -502,7 +510,7 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, /* check if min chanctx also changed */ changed = IEEE80211_CHANCTX_CHANGE_WIDTH | - _ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); drv_change_chanctx(local, ctx, changed); if (!local->use_chanctx) { @@ -514,6 +522,14 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, false); } +static void ieee80211_change_chanctx(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, + const struct cfg80211_chan_def *chandef) +{ + _ieee80211_change_chanctx(local, ctx, old_ctx, chandef, NULL); +} + static struct ieee80211_chanctx * ieee80211_find_chanctx(struct ieee80211_local *local, const struct cfg80211_chan_def *chandef, @@ -638,7 +654,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - _ieee80211_recalc_chanctx_min_def(local, ctx); + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL); return ctx; } @@ -873,12 +889,12 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, ieee80211_recalc_chanctx_chantype(local, curr_ctx); ieee80211_recalc_smps_chanctx(local, curr_ctx); ieee80211_recalc_radar_chanctx(local, curr_ctx); - ieee80211_recalc_chanctx_min_def(local, curr_ctx); + ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL); } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { ieee80211_recalc_txpower(sdata, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); } if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && @@ -1270,7 +1286,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) ieee80211_link_update_chandef(link, &link->reserved_chandef); - ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef); + _ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef, link); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1300,7 +1316,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); - ieee80211_recalc_chanctx_min_def(local, new_ctx); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); @@ -1665,7 +1681,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx); + ieee80211_recalc_chanctx_min_def(local, ctx, NULL); list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, reserved_chanctx_list) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a0a7839cb961..b0372e76f373 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2537,7 +2537,8 @@ int ieee80211_chanctx_refcount(struct ieee80211_local *local, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx); + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for); bool ieee80211_is_radar_required(struct ieee80211_local *local); void ieee80211_dfs_cac_timer(unsigned long data); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1527d6aafc14..4bf76150925d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3015,7 +3015,7 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - ieee80211_recalc_chanctx_min_def(local, chanctx); + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL); } unlock: mutex_unlock(&local->chanctx_mtx); -- GitLab From 04312de4ced4b152749614e8179f3978a20a992f Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 4 May 2023 16:45:04 +0300 Subject: [PATCH 5045/5631] wifi: mac80211: recalc chanctx mindef before assigning When we allocate a new channel context, or find an existing one that is compatible, we currently assign it to a link before its mindef is updated. This leads to strange situations, especially in link switching where you switch to an 80 MHz link and expect it to be active immediately, but the mindef is still configured to 20 MHz while assigning. Also, it's strange that the chandef passed to the assign method's argument is wider than the one in the context. Fix this by calculating the mindef with the new link considered before calling the driver. In particular, this fixes an iwlwifi problem during link switch where the firmware would assert because the (link) station that was added for the AP is configured to transmit at a bandwidth that's wider than the channel context that it's configured on. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230504134511.828474-5-gregory.greenman@intel.com Signed-off-by: Johannes Berg --- net/mac80211/chan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 1b182cf9d661..77c90ed8f5d7 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -871,6 +871,9 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, } if (new_ctx) { + /* recalc considering the link we'll use it for now */ + ieee80211_recalc_chanctx_min_def(local, new_ctx, link); + ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); if (ret) goto out; -- GitLab From 783336b05f06821c9af3b057ecd5a7aa082ed973 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:44 +0300 Subject: [PATCH 5046/5631] wifi: iwlwifi: mvm: always free dup_data There are some assertions in the STA removal code that can fail, and in that case we may leak memory since we skip the freeing. Fix this by freeing the dup_data earlier in the function, we already have a check for when we free the station, and this we don't need to do it with and without MLD API, so it's a win all around. Fixes: a571f5f635ef ("iwlwifi: mvm: add duplicate packet detection per rx queue") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.173938681d72.Iff4b55fc52943825d6e3e28d78a24b155ea5cd22@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 3 +++ drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 -- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 3 --- 3 files changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 0f01b62357c6..1c96cf020801 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3889,6 +3889,9 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw, * from the AP now. */ iwl_mvm_reset_cca_40mhz_workaround(mvm, vif); + + /* Also free dup data just in case any assertions below fail */ + kfree(mvm_sta->dup_data); } mutex_lock(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 0bfdf4462755..f877be850589 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -791,8 +791,6 @@ int iwl_mvm_mld_rm_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, lockdep_assert_held(&mvm->mutex); - kfree(mvm_sta->dup_data); - /* flush its queues here since we are freeing mvm_sta */ for_each_sta_active_link(vif, sta, link_sta, link_id) { struct iwl_mvm_link_sta *mvm_link_sta = diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 5469d634e289..1e8592d3bcd6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -2089,9 +2089,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, lockdep_assert_held(&mvm->mutex); - if (iwl_mvm_has_new_rx_api(mvm)) - kfree(mvm_sta->dup_data); - ret = iwl_mvm_drain_sta(mvm, mvm_sta, true); if (ret) return ret; -- GitLab From 9e949dfdc5d1697ccbcc19c06f5133e1833d8eea Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:45 +0300 Subject: [PATCH 5047/5631] wifi: iwlwifi: mvm: don't double-init spinlock We don't need to (and shouldn't) initialize the spinlock during HW restart that was already initialized, so move that into the correct if block. Since then we have two consecutive if statements with the same (though inverted) condition, unify those as well. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.221c22cfdf4e.I2e30113ef4bd8cb5bd9e1a69e52a95671914961c@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index f877be850589..19f1545b3c7e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -667,15 +667,15 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, ret = iwl_mvm_mld_alloc_sta_links(mvm, vif, sta); if (ret) return ret; - } - spin_lock_init(&mvm_sta->lock); + spin_lock_init(&mvm_sta->lock); - if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) - ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); - else ret = iwl_mvm_sta_init(mvm, vif, sta, IWL_MVM_INVALID_STA, STATION_TYPE_PEER); + } else { + ret = iwl_mvm_alloc_sta_after_restart(mvm, vif, sta); + } + if (ret) goto err; -- GitLab From c2d8b7f257b2398f2d866205365895e038beca12 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:46 +0300 Subject: [PATCH 5048/5631] wifi: iwlwifi: mvm: fix cancel_delayed_work_sync() deadlock Lockdep points out that we can deadlock here by calling cancel_delayed_work_sync() because that might be already running and gotten interrupted by the NAPI soft-IRQ. Even just calling something that can sleep is wrong in this context though. Luckily, it doesn't even really matter since the things we need to do are idempotent, so just drop the _sync(). Fixes: e5d153ec54f0 ("iwlwifi: mvm: fix CSA AP side") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.b1813c823b4d.I9d20cc06d24fa40b6774d3dd95ea5e2bf8dd015b@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index e1d02c260e69..01432274a6da 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -2512,7 +2512,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, RCU_INIT_POINTER(mvm->csa_tx_blocked_vif, NULL); /* Unblock BCAST / MCAST station */ iwl_mvm_modify_all_sta_disable_tx(mvm, mvmvif, false); - cancel_delayed_work_sync(&mvm->cs_tx_unblock_dwork); + cancel_delayed_work(&mvm->cs_tx_unblock_dwork); } } -- GitLab From 204bfec9168ddd869a05e7f70dc5b0a9ae513722 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:47 +0300 Subject: [PATCH 5049/5631] wifi: iwlwifi: mvm: fix number of concurrent link checks The concurrent link checks need to correctly differentiate between AP and non-AP, fix that. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.992b2f981ef6.I7d386c19354e9be39c4822f436dd22c93422b660@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/link.c | 12 +++++++----- .../net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 9 +++++---- 2 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c index eb828de40a3c..3814915cb1a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -123,11 +123,13 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (mvmvif->link[i]->phy_ctxt) count++; - /* FIXME: IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM should be - * defined per HW - */ - if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) - return -EINVAL; + if (vif->type == NL80211_IFTYPE_AP) { + if (count > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + /* this should be per HW or such */ + } else if (count >= IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM) { + return -EOPNOTSUPP; + } } /* Catch early if driver tries to activate or deactivate a link diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index fbc2d5ed1006..7fb66c570959 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -906,11 +906,12 @@ iwl_mvm_mld_change_vif_links(struct ieee80211_hw *hw, n_active++; } - if (vif->type == NL80211_IFTYPE_AP && - n_active > mvm->fw->ucode_capa.num_beacons) - return -EOPNOTSUPP; - else if (n_active > 1) + if (vif->type == NL80211_IFTYPE_AP) { + if (n_active > mvm->fw->ucode_capa.num_beacons) + return -EOPNOTSUPP; + } else if (n_active > 1) { return -EOPNOTSUPP; + } } for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) { -- GitLab From d3ae69180bbd74bcbc03a2b6d10ed7eccbe98c23 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:48 +0300 Subject: [PATCH 5050/5631] wifi: iwlwifi: fw: fix DBGI dump The DBGI dump is (unsurprisingly) of type DBGI, not SRAM. This leads to bad register accesses because the union is built differently, there's no allocation ID, and thus the allocation ID ends up being 0x8000. Note that this was already wrong for DRAM vs. SMEM since they use different parts of the union, but the allocation ID is at the same place, so it worked. Fix all of this but set the allocation ID in a way that the offset calculation ends up without any offset. Fixes: 34bc27783a31 ("iwlwifi: yoyo: fix DBGI_SRAM ini dump header.") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.19a302ae4c65.I12272599f7c1930666157b9d5e7f81fe9ec4c421@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index d9faaae01abd..55219974b92b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1664,14 +1664,10 @@ static __le32 iwl_get_mon_reg(struct iwl_fw_runtime *fwrt, u32 alloc_id, } static void * -iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, - struct iwl_dump_ini_region_data *reg_data, +iwl_dump_ini_mon_fill_header(struct iwl_fw_runtime *fwrt, u32 alloc_id, struct iwl_fw_ini_monitor_dump *data, const struct iwl_fw_mon_regs *addrs) { - struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; - u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - if (!iwl_trans_grab_nic_access(fwrt->trans)) { IWL_ERR(fwrt, "Failed to get monitor header\n"); return NULL; @@ -1702,8 +1698,10 @@ iwl_dump_ini_mon_dram_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->dram_alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_dram_regs); } @@ -1713,8 +1711,10 @@ iwl_dump_ini_mon_smem_fill_header(struct iwl_fw_runtime *fwrt, void *data, u32 data_len) { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; + struct iwl_fw_ini_region_tlv *reg = (void *)reg_data->reg_tlv->data; + u32 alloc_id = le32_to_cpu(reg->internal_buffer.alloc_id); - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, alloc_id, mon_dump, &fwrt->trans->cfg->mon_smem_regs); } @@ -1725,7 +1725,10 @@ iwl_dump_ini_mon_dbgi_fill_header(struct iwl_fw_runtime *fwrt, { struct iwl_fw_ini_monitor_dump *mon_dump = (void *)data; - return iwl_dump_ini_mon_fill_header(fwrt, reg_data, mon_dump, + return iwl_dump_ini_mon_fill_header(fwrt, + /* no offset calculation later */ + IWL_FW_INI_ALLOCATION_ID_DBGC1, + mon_dump, &fwrt->trans->cfg->mon_dbgi_regs); } -- GitLab From 6818266283d191549afa87ac5d7b86635a5fb105 Mon Sep 17 00:00:00 2001 From: Gregory Greenman Date: Sun, 14 May 2023 12:15:49 +0300 Subject: [PATCH 5051/5631] wifi: iwlwifi: mvm: fix access to fw_id_to_mac_id RCU protected fw_id_to_mac_id can be initialized with either an error code or NULL. Thus, after dereferencing need to check the value with IS_ERR_OR_NULL() and not only that it is not NULL. Fix it. Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.ec5f2880e81c.Ifa8c0f451df2835bde800f5c3670cc46238a3bd8@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c | 5 +++++ drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 7 +++++++ drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 10 +++++++++- drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 2 +- 4 files changed, 22 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 3963a0d4ed04..652a603c4500 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -526,6 +526,11 @@ iwl_mvm_ftm_put_target(struct iwl_mvm *mvm, struct ieee80211_vif *vif, rcu_read_lock(); sta = rcu_dereference(mvm->fw_id_to_mac_id[mvmvif->deflink.ap_sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + return PTR_ERR_OR_ZERO(sta); + } + if (sta->mfp && (peer->ftm.trigger_based || peer->ftm.non_trigger_based)) FTM_PUT_FLAG(PMF); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 01432274a6da..6226e4e54a51 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -691,6 +691,11 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) rcu_read_lock(); sta = rcu_dereference(buf->mvm->fw_id_to_mac_id[sta_id]); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) { + rcu_read_unlock(); + goto out; + } + mvmsta = iwl_mvm_sta_from_mac80211(sta); /* SN is set to the last expired frame + 1 */ @@ -712,6 +717,8 @@ void iwl_mvm_reorder_timer_expired(struct timer_list *t) entries[index].e.reorder_time + 1 + RX_REORDER_BUF_TIMEOUT_MQ); } + +out: spin_unlock(&buf->lock); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index 1e8592d3bcd6..05a54a69c135 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -281,7 +281,7 @@ static void iwl_mvm_rx_agg_session_expired(struct timer_list *t) * A-MDPU and hence the timer continues to run. Then, the * timer expires and sta is NULL. */ - if (!sta) + if (IS_ERR_OR_NULL(sta)) goto unlock; mvm_sta = iwl_mvm_sta_from_mac80211(sta); @@ -3782,6 +3782,9 @@ static inline u8 *iwl_mvm_get_mac_addr(struct iwl_mvm *mvm, u8 sta_id = mvmvif->deflink.ap_sta_id; sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], lockdep_is_held(&mvm->mutex)); + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta))) + return NULL; + return sta->addr; } @@ -3819,6 +3822,11 @@ static int __iwl_mvm_set_sta_key(struct iwl_mvm *mvm, if (keyconf->cipher == WLAN_CIPHER_SUITE_TKIP) { addr = iwl_mvm_get_mac_addr(mvm, vif, sta); + if (!addr) { + IWL_ERR(mvm, "Failed to find mac address\n"); + return -EINVAL; + } + /* get phase 1 key from mac80211 */ ieee80211_get_key_rx_seq(keyconf, 0, &seq); ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 10d7178f1071..00719e130438 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1875,7 +1875,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm, mvmsta = iwl_mvm_sta_from_staid_rcu(mvm, sta_id); sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); - if (WARN_ON_ONCE(!sta || !sta->wme)) { + if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta) || !sta->wme)) { rcu_read_unlock(); return; } -- GitLab From e234c36290430a833aa87532a7740fef031c2c85 Mon Sep 17 00:00:00 2001 From: Mukesh Sisodiya Date: Sun, 14 May 2023 12:15:50 +0300 Subject: [PATCH 5052/5631] wifi: iwlwifi: mvm: fix initialization of a return value In iwl_mvm_mld_update_sta(), if the flow doesn't enter for_each_sta_active_link(), the default value is returned. Set this default to -EINVAL instead of 0 to better reflect this. Signed-off-by: Mukesh Sisodiya Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.98b7e3aacf0b.I2fc274dd7e374ef7fac8e26d71c9cd73323da665@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 19f1545b3c7e..85a4ce8449ad 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -728,7 +728,7 @@ int iwl_mvm_mld_update_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); struct ieee80211_link_sta *link_sta; unsigned int link_id; - int ret = 0; + int ret = -EINVAL; lockdep_assert_held(&mvm->mutex); -- GitLab From eca7296d9a671e9961834d2ace9cc0ce21fc15b3 Mon Sep 17 00:00:00 2001 From: Alon Giladi Date: Sun, 14 May 2023 12:15:51 +0300 Subject: [PATCH 5053/5631] wifi: iwlwifi: fix OEM's name in the ppag approved list Fix a spelling mistake. Fixes: e8e10a37c51c ("iwlwifi: acpi: move ppag code from mvm to fw/acpi") Signed-off-by: Alon Giladi Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.fdd07f36a8bf.I223e5fb16ab5c95d504c3fdaffd0bd70affad1c2@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index 5f4a51310add..cb9181f05501 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -38,7 +38,7 @@ static const struct dmi_system_id dmi_ppag_approved_list[] = { }, { .ident = "ASUS", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek COMPUTER INC."), + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), }, }, {} -- GitLab From d0246a0e49efee0f8649d0e4f2350614cdfe6565 Mon Sep 17 00:00:00 2001 From: Alon Giladi Date: Sun, 14 May 2023 12:15:52 +0300 Subject: [PATCH 5054/5631] wifi: iwlwifi: mvm: fix OEM's name in the tas approved list Fix a spelling mistake. Fixes: 2856f623ce48 ("iwlwifi: mvm: Add list of OEMs allowed to use TAS") Signed-off-by: Alon Giladi Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.4090de6d1878.If9391ef6da78f1b2cc5eb6cb8f6965816bb7a7f5@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index e2573a9d6f27..205c09bc9863 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1091,7 +1091,7 @@ static const struct dmi_system_id dmi_tas_approved_list[] = { }, { .ident = "LENOVO", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Lenovo"), + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), }, }, { .ident = "DELL", -- GitLab From 682b6dc29d98e857e6ca4bbc077c7dc2899b7473 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sun, 14 May 2023 12:15:53 +0300 Subject: [PATCH 5055/5631] wifi: iwlwifi: mvm: don't trust firmware n_channels If the firmware sends us a corrupted MCC response with n_channels much larger than the command response can be, we might copy far too much (uninitialized) memory and even crash if the n_channels is large enough to make it run out of the one page allocated for the FW response. Fix that by checking the lengths. Doing a < comparison would be sufficient, but the firmware should be doing it correctly, so check more strictly. Fixes: dcaf9f5ecb6f ("iwlwifi: mvm: add MCC update FW API") Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.d7b233139eb4.I51fd319df8e9d41881fc8450e83d78049518a79a@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 6d18a1fd649b..fdf60afb0f3f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -445,6 +445,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp *mcc_resp = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kmemdup(mcc_resp, resp_len, GFP_KERNEL); @@ -456,6 +461,11 @@ iwl_mvm_update_mcc(struct iwl_mvm *mvm, const char *alpha2, struct iwl_mcc_update_resp_v3 *mcc_resp_v3 = (void *)pkt->data; n_channels = __le32_to_cpu(mcc_resp_v3->n_channels); + if (iwl_rx_packet_payload_len(pkt) != + struct_size(mcc_resp_v3, channels, n_channels)) { + resp_cp = ERR_PTR(-EINVAL); + goto exit; + } resp_len = sizeof(struct iwl_mcc_update_resp) + n_channels * sizeof(__le32); resp_cp = kzalloc(resp_len, GFP_KERNEL); -- GitLab From 207be64f4e60bf5de13fc69fcf7fe2441bf71a97 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Sun, 14 May 2023 12:15:54 +0300 Subject: [PATCH 5056/5631] wifi: iwlwifi: Don't use valid_links to iterate sta links This bitmap equals to zero when in a non-MLO mode, and then we won't be iterating on any link. Use for_each_sta_active_link() instead, as it handles also the case of non-MLO mode. Signed-off-by: Miri Korenblit Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.f32a8c08730a.Ib02248cd0b7f2bc885f91005c3c110dd027f9dcd@changeid Signed-off-by: Johannes Berg --- .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 52 ++++++++----------- 1 file changed, 22 insertions(+), 30 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 1c96cf020801..17f788a5ff6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2022 Intel Corporation + * Copyright (C) 2012-2014, 2018-2023 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3607,7 +3607,8 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; /* Beacon interval check - firmware will crash if the beacon * interval is less than 16. We can't avoid connecting at all, @@ -3616,14 +3617,11 @@ static bool iwl_mvm_vif_conf_from_sta(struct iwl_mvm *mvm, * wpa_s will blocklist the AP... */ - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta) + if (!link_conf) continue; if (link_conf->beacon_int < IWL_MVM_MIN_BEACON_INTERVAL_TU) { @@ -3645,24 +3643,23 @@ static void iwl_mvm_vif_set_he_support(struct ieee80211_hw *hw, bool is_sta) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { - struct ieee80211_link_sta *link_sta = - link_sta_dereference_protected(sta, i); + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); - if (!link_conf || !link_sta || !mvmvif->link[i]) + if (!link_conf || !mvmvif->link[link_id]) continue; link_conf->he_support = link_sta->he_cap.has_he; if (is_sta) { - mvmvif->link[i]->he_ru_2mhz_block = false; + mvmvif->link[link_id]->he_ru_2mhz_block = false; if (link_sta->he_cap.has_he) - iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, i, + iwl_mvm_check_he_obss_narrow_bw_ru(hw, vif, + link_id, link_conf); } } @@ -3675,6 +3672,7 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, struct iwl_mvm_sta_state_ops *callbacks) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + struct ieee80211_link_sta *link_sta; unsigned int i; int ret; @@ -3699,15 +3697,9 @@ iwl_mvm_sta_state_notexist_to_none(struct iwl_mvm *mvm, NL80211_TDLS_SETUP); } - for (i = 0; i < ARRAY_SIZE(sta->link); i++) { - struct ieee80211_link_sta *link_sta; - - link_sta = link_sta_dereference_protected(sta, i); - if (!link_sta) - continue; - + for_each_sta_active_link(vif, sta, link_sta, i) link_sta->agg.max_rc_amsdu_len = 1; - } + ieee80211_sta_recalc_aggregates(sta); if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) @@ -3725,7 +3717,8 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); - unsigned int i; + struct ieee80211_link_sta *link_sta; + unsigned int link_id; lockdep_assert_held(&mvm->mutex); @@ -3751,14 +3744,13 @@ iwl_mvm_sta_state_auth_to_assoc(struct ieee80211_hw *hw, if (!mvm->mld_api_is_used) goto out; - for_each_set_bit(i, (unsigned long *)&sta->valid_links, - IEEE80211_MLD_MAX_NUM_LINKS) { + for_each_sta_active_link(vif, sta, link_sta, link_id) { struct ieee80211_bss_conf *link_conf = - link_conf_dereference_protected(vif, i); + link_conf_dereference_protected(vif, link_id); if (WARN_ON(!link_conf)) return -EINVAL; - if (!mvmvif->link[i]) + if (!mvmvif->link[link_id]) continue; iwl_mvm_link_changed(mvm, vif, link_conf, -- GitLab From a8938bc881d2a03f9b77f19fae924fe798a01285 Mon Sep 17 00:00:00 2001 From: Ariel Malamud Date: Sun, 14 May 2023 12:15:55 +0300 Subject: [PATCH 5057/5631] wifi: iwlwifi: mvm: Add locking to the rate read flow The rs_drv_get_rate flow reads the lq_sta to return the optimal rate for tx frames. This read flow is not protected thereby leaving a small window, a few instructions wide, open to contention by an asynchronous rate update. Indeed this race condition was hit and the update occurred in the middle of the read. Fix this by locking the lq_sta struct during read. Signed-off-by: Ariel Malamud Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230514120631.b52c9ed5c379.I15290b78e0d966c1b68278263776ca9de841d5fe@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index a4c1e3bf4ff1..23266d0c9ce4 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -2691,6 +2691,8 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, return; lq_sta = mvm_sta; + + spin_lock(&lq_sta->pers.lock); iwl_mvm_hwrate_to_tx_rate_v1(lq_sta->last_rate_n_flags, info->band, &info->control.rates[0]); info->control.rates[0].count = 1; @@ -2705,6 +2707,7 @@ static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta, iwl_mvm_hwrate_to_tx_rate_v1(last_ucode_rate, info->band, &txrc->reported_rate); } + spin_unlock(&lq_sta->pers.lock); } static void *rs_drv_alloc_sta(void *mvm_rate, struct ieee80211_sta *sta, -- GitLab From 098abbd48ec1accf111dde50a2a5392f2a15f59c Mon Sep 17 00:00:00 2001 From: Zhengchao Shao Date: Mon, 15 May 2023 17:22:27 +0800 Subject: [PATCH 5058/5631] mac80211_hwsim: fix memory leak in hwsim_new_radio_nl When parse_pmsr_capa failed in hwsim_new_radio_nl, the memory resources applied for by pmsr_capa are not released. Add release processing to the incorrect path. Fixes: 92d13386ec55 ("mac80211_hwsim: add PMSR capability support") Reported-by: syzbot+904ce6fbb38532d9795c@syzkaller.appspotmail.com Signed-off-by: Zhengchao Shao Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230515092227.2691437-1-shaozhengchao@huawei.com Signed-off-by: Johannes Berg --- drivers/net/wireless/virtual/mac80211_hwsim.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 9a8faaf4c6b6..89c7a1420381 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -5964,10 +5964,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) ret = -ENOMEM; goto out_free; } + param.pmsr_capa = pmsr_capa; + ret = parse_pmsr_capa(info->attrs[HWSIM_ATTR_PMSR_SUPPORT], pmsr_capa, info); if (ret) goto out_free; - param.pmsr_capa = pmsr_capa; } ret = mac80211_hwsim_new_radio(info, ¶m); -- GitLab From a820ca1a739b7e3ee0ddb48bdfa3c09dc7cd4302 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Mon, 15 May 2023 17:17:18 -0700 Subject: [PATCH 5059/5631] samples/bpf: Drop unnecessary fallthrough __fallthrough is now not supported. Instead of renaming it to now-canonical ([0]) fallthrough pseudo-keyword, just get rid of it and equate 'h' case to default case, as both emit usage information and succeed. [0] https://www.kernel.org/doc/html/latest/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-through Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20230516001718.317177-1-andrii@kernel.org --- samples/bpf/hbm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 6448b7826107..bf66277115e2 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -498,7 +498,6 @@ int main(int argc, char **argv) "Option -%c requires an argument.\n\n", optopt); case 'h': - __fallthrough; default: Usage(); return 0; -- GitLab From 9dde12767aa19696a7fb28b2320119b87fb9d299 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Mon, 15 May 2023 15:45:30 -0700 Subject: [PATCH 5060/5631] perf metrics: Avoid segv with --topdown for metrics without a group Some metrics may not have a metric_group which can result in segvs with "perf stat --topdown". Add a condition for the no metric_group case. Fixes: 1647cd5b8802698f ("perf stat: Implement --topdown using json metrics") Reported-by: Kan Liang Signed-off-by: Ian Rogers Tested-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kajol Jain Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20230515224530.671331-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/metricgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 4e7d41d285b4..5e9c657dd3f7 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -1672,7 +1672,7 @@ static int metricgroup__topdown_max_level_callback(const struct pmu_metric *pm, { unsigned int *max_level = data; unsigned int level; - const char *p = strstr(pm->metric_group, "TopdownL"); + const char *p = strstr(pm->metric_group ?: "", "TopdownL"); if (!p || p[8] == '\0') return 0; -- GitLab From 71852cd8825077d2d90466ac34d3b94e0be3bfae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 May 2023 15:23:47 -0300 Subject: [PATCH 5061/5631] tools headers UAPI: Sync linux/prctl.h with the kernel sources ddc65971bb677aa9 ("prctl: add PR_GET_AUXV to copy auxv to userspace") To pick the changes in: That don't result in any changes in tooling: $ tools/perf/trace/beauty/prctl_option.sh > before $ cp include/uapi/linux/prctl.h tools/include/uapi/linux/prctl.h $ tools/perf/trace/beauty/prctl_option.sh > after $ diff -u before after $ This actually adds a new prctl arg, but it has to be dealt with differently, as it is not in sequence with the other arguments. Just silences this perf tools build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/prctl.h' differs from latest version at 'include/uapi/linux/prctl.h' diff -u tools/include/uapi/linux/prctl.h include/uapi/linux/prctl.h Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/prctl.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 759b3f53e53f..f23d9a16507f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,6 +290,8 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_GET_AUXV 0x41555856 + #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ -- GitLab From b633896314c0f78f2b4eb7b19a530d68f2a35445 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 16 May 2023 15:27:50 -0300 Subject: [PATCH 5062/5631] tools headers UAPI: Sync s390 syscall table file that wires up the memfd_secret syscall To pick the changes in these csets: 7608f70adcb1ea69 ("s390: wire up memfd_secret system call") That add support for this new syscall in tools such as 'perf trace'. For instance, this is now possible (adapted from the x86_64 test output): # perf trace -v -e memfd_secret event qualifier tracepoint filter: (common_pid != 13375 && common_pid != 3713) && (id == 447) ^C# That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ grep memfd_secret tools/perf/arch/x86/entry/syscalls/syscall_64.tbl 447 common memfd_secret sys_memfd_secret $ This addresses this perf build warnings: Warning: Kernel ABI header at 'tools/perf/arch/s390/entry/syscalls/syscall.tbl' differs from latest version at 'arch/s390/kernel/syscalls/syscall.tbl' diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl Cc: Adrian Hunter Cc: Heiko Carstens Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Vasily Gorbik Link: https://lore.kernel.org/lkml/ZGPMW0p++D1Jdvf6@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/s390/entry/syscalls/syscall.tbl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 799147658dee..b68f47541169 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -449,7 +449,7 @@ 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self -# 447 reserved for memfd_secret +447 common memfd_secret sys_memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node -- GitLab From 3b44ec8c5c44790a82f07e90db45643c762878c6 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 May 2023 20:44:12 +0200 Subject: [PATCH 5063/5631] ALSA: hda: Fix Oops by 9.1 surround channel names get_line_out_pfx() may trigger an Oops by overflowing the static array with more than 8 channels. This was reported for MacBookPro 12,1 with Cirrus codec. As a workaround, extend for the 9.1 channels and also fix the potential Oops by unifying the code paths accessing the same array with the proper size check. Reported-by: Olliver Schinagl Cc: Link: https://lore.kernel.org/r/64d95eb0-dbdb-cff8-a8b1-988dc22b24cd@schinagl.nl Link: https://lore.kernel.org/r/20230516184412.24078-1-tiwai@suse.de Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_generic.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index fc114e522480..dbf7aa88e0e3 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -1155,8 +1155,8 @@ static bool path_has_mixer(struct hda_codec *codec, int path_idx, int ctl_type) return path && path->ctls[ctl_type]; } -static const char * const channel_name[4] = { - "Front", "Surround", "CLFE", "Side" +static const char * const channel_name[] = { + "Front", "Surround", "CLFE", "Side", "Back", }; /* give some appropriate ctl name prefix for the given line out channel */ @@ -1182,7 +1182,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, /* multi-io channels */ if (ch >= cfg->line_outs) - return channel_name[ch]; + goto fixed_name; switch (cfg->line_out_type) { case AUTO_PIN_SPEAKER_OUT: @@ -1234,6 +1234,7 @@ static const char *get_line_out_pfx(struct hda_codec *codec, int ch, if (cfg->line_outs == 1 && !spec->multi_ios) return "Line Out"; + fixed_name: if (ch >= ARRAY_SIZE(channel_name)) { snd_BUG(); return "PCM"; -- GitLab From 96e3cc270d61cb9945b1c2894effcba15010f097 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 15 May 2023 17:15:18 -0700 Subject: [PATCH 5064/5631] Documentation: use capitalization for chapters and acronyms Use capital letters in acronyms for CD-ROM, FPGA, and PCMCIA. Use capital letter in the first word of chapter headings for Locking, Timers, and "Brief tutorial on CRC computation". Signed-off-by: Randy Dunlap Cc: Moritz Fischer Cc: Wu Hao Cc: Tom Rix Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Dominik Brodowski Cc: Thomas Gleixner Acked-by: Xu Yilun Reviewed-by: Phillip Potter Link: https://lore.kernel.org/r/20230516001518.14514-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/cdrom/index.rst | 6 +++--- Documentation/fpga/index.rst | 2 +- Documentation/locking/index.rst | 2 +- Documentation/pcmcia/index.rst | 2 +- Documentation/staging/crc32.rst | 2 +- Documentation/timers/index.rst | 2 +- 6 files changed, 8 insertions(+), 8 deletions(-) diff --git a/Documentation/cdrom/index.rst b/Documentation/cdrom/index.rst index e87a8785bc1a..e9b022d70939 100644 --- a/Documentation/cdrom/index.rst +++ b/Documentation/cdrom/index.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -===== -cdrom -===== +====== +CD-ROM +====== .. toctree:: :maxdepth: 1 diff --git a/Documentation/fpga/index.rst b/Documentation/fpga/index.rst index f80f95667ca2..43c968871d99 100644 --- a/Documentation/fpga/index.rst +++ b/Documentation/fpga/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ==== -fpga +FPGA ==== .. toctree:: diff --git a/Documentation/locking/index.rst b/Documentation/locking/index.rst index 7003bd5aeff4..6a9ea96c8bcb 100644 --- a/Documentation/locking/index.rst +++ b/Documentation/locking/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ======= -locking +Locking ======= .. toctree:: diff --git a/Documentation/pcmcia/index.rst b/Documentation/pcmcia/index.rst index 7ae1f62fca14..8067236c51ab 100644 --- a/Documentation/pcmcia/index.rst +++ b/Documentation/pcmcia/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -pcmcia +PCMCIA ====== .. toctree:: diff --git a/Documentation/staging/crc32.rst b/Documentation/staging/crc32.rst index 8a6860f33b4e..7542220967cb 100644 --- a/Documentation/staging/crc32.rst +++ b/Documentation/staging/crc32.rst @@ -1,5 +1,5 @@ ================================= -brief tutorial on CRC computation +Brief tutorial on CRC computation ================================= A CRC is a long-division remainder. You add the CRC to the message, diff --git a/Documentation/timers/index.rst b/Documentation/timers/index.rst index df510ad0c989..983f91f8f023 100644 --- a/Documentation/timers/index.rst +++ b/Documentation/timers/index.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: GPL-2.0 ====== -timers +Timers ====== .. toctree:: -- GitLab From 0d8aa3212e042bfcb7011e4de841dfdea39dc4b7 Mon Sep 17 00:00:00 2001 From: Thorsten Leemhuis Date: Mon, 15 May 2023 10:52:19 +0200 Subject: [PATCH 5065/5631] docs: quickly-build-trimmed-linux: various small fixes and improvements * improve the short description of localmodconfig in the step-by-step guide while fixing its broken first sentence * briefly mention immutable Linux distributions * use '--shallow-exclude=v6.0' throughout the document * instead of "git reset --hard; git checkout ..." use "git checkout --force ..." in the step-by-step guide: this matches the TLDR and is one command less to execute. This led to a few small adjustments to the text and the flow in the surrounding area. * fix two thinkos in the section explaining full git clones Signed-off-by: Thorsten Leemhuis Link: https://lore.kernel.org/r/6f4684b9a5d11d3adb04e0af3cfc60db8b28eeb2.1684140700.git.linux@leemhuis.info Signed-off-by: Jonathan Corbet --- .../quickly-build-trimmed-linux.rst | 49 ++++++++++--------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/Documentation/admin-guide/quickly-build-trimmed-linux.rst b/Documentation/admin-guide/quickly-build-trimmed-linux.rst index ff4f4cc8522b..f08149bc53f8 100644 --- a/Documentation/admin-guide/quickly-build-trimmed-linux.rst +++ b/Documentation/admin-guide/quickly-build-trimmed-linux.rst @@ -215,12 +215,14 @@ again. reduce the compile time enormously, especially if you are running an universal kernel from a commodity Linux distribution. - There is a catch: the make target 'localmodconfig' will disable kernel - features you have not directly or indirectly through some program utilized - since you booted the system. You can reduce or nearly eliminate that risk by - using tricks outlined in the reference section; for quick testing purposes - that risk is often negligible, but it is an aspect you want to keep in mind - in case your kernel behaves oddly. + There is a catch: 'localmodconfig' is likely to disable kernel features you + did not use since you booted your Linux -- like drivers for currently + disconnected peripherals or a virtualization software not haven't used yet. + You can reduce or nearly eliminate that risk with tricks the reference + section outlines; but when building a kernel just for quick testing purposes + it is often negligible if such features are missing. But you should keep that + aspect in mind when using a kernel built with this make target, as it might + be the reason why something you only use occasionally stopped working. [:ref:`details`] @@ -271,6 +273,9 @@ again. does nothing at all; in that case you have to manually install your kernel, as outlined in the reference section. + If you are running a immutable Linux distribution, check its documentation + and the web to find out how to install your own kernel there. + [:ref:`details`] .. _another_sbs: @@ -291,29 +296,29 @@ again. version you care about, as git otherwise might retrieve the entire commit history:: - git fetch --shallow-exclude=v6.1 origin - - If you modified the sources (for example by applying a patch), you now need - to discard those modifications; that's because git otherwise will not be able - to switch to the sources of another version due to potential conflicting - changes:: - - git reset --hard + git fetch --shallow-exclude=v6.0 origin - Now checkout the version you are interested in, as explained above:: + Now switch to the version you are interested in -- but be aware the command + used here will discard any modifications you performed, as they would + conflict with the sources you want to checkout:: - git checkout --detach origin/master + git checkout --force --detach origin/master At this point you might want to patch the sources again or set/modify a build - tag, as explained earlier; afterwards adjust the build configuration to the - new codebase and build your next kernel:: + tag, as explained earlier. Afterwards adjust the build configuration to the + new codebase using olddefconfig, which will now adjust the configuration file + you prepared earlier using localmodconfig (~/linux/.config) for your next + kernel:: # reminder: if you want to apply patches, do it at this point # reminder: you might want to update your build tag at this point make olddefconfig + + Now build your kernel:: + make -j $(nproc --all) - Install the kernel as outlined above:: + Afterwards install the kernel as outlined above:: command -v installkernel && sudo make modules_install install @@ -584,11 +589,11 @@ versions and individual commits at hand at any time:: curl -L \ https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/clone.bundle \ -o linux-stable.git.bundle - git clone clone.bundle ~/linux/ + git clone linux-stable.git.bundle ~/linux/ rm linux-stable.git.bundle cd ~/linux/ - git remote set-url origin - https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git + git remote set-url origin \ + https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git git fetch origin git checkout --detach origin/master -- GitLab From 7b38ecfdf9fbb133b4d2ea3738c02291a262abe2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 7 May 2023 22:59:38 -0700 Subject: [PATCH 5066/5631] Documentation/filesystems: sharedsubtree: add section headings Several of the sections are missing underlines. This makes the generated contents have missing entries, so add the underlines. Fixes: 16c01b20ae05 ("doc/filesystems: more mount cleanups") Fixes: 9cfcceea8f7e ("[PATCH] Complete description of shared subtrees.") Signed-off-by: Randy Dunlap Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230508055938.6550-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/filesystems/sharedsubtree.rst | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/Documentation/filesystems/sharedsubtree.rst b/Documentation/filesystems/sharedsubtree.rst index d83395354250..1cf56489ed48 100644 --- a/Documentation/filesystems/sharedsubtree.rst +++ b/Documentation/filesystems/sharedsubtree.rst @@ -147,6 +147,7 @@ replicas continue to be exactly same. 3) Setting mount states +----------------------- The mount command (util-linux package) can be used to set mount states:: @@ -612,6 +613,7 @@ replicas continue to be exactly same. 6) Quiz +------- A. What is the result of the following command sequence? @@ -673,6 +675,7 @@ replicas continue to be exactly same. /mnt/1/test be? 7) FAQ +------ Q1. Why is bind mount needed? How is it different from symbolic links? symbolic links can get stale if the destination mount gets @@ -841,6 +844,7 @@ replicas continue to be exactly same. tmp usr tmp usr tmp usr 8) Implementation +----------------- 8A) Datastructure -- GitLab From bd415b5c9552d44069d4e7c1e018b6d42f25af9e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 7 May 2023 22:59:28 -0700 Subject: [PATCH 5067/5631] Documentation/filesystems: ramfs-rootfs-initramfs: use :Author: Use the :Author: markup instead of making it a chapter heading. This cleans up the table of contents for this file. Fixes: 7f46a240b0a1 ("[PATCH] ramfs, rootfs, and initramfs docs") Signed-off-by: Randy Dunlap Cc: Rob Landley Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20230508055928.3548-1-rdunlap@infradead.org Signed-off-by: Jonathan Corbet --- Documentation/filesystems/ramfs-rootfs-initramfs.rst | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.rst b/Documentation/filesystems/ramfs-rootfs-initramfs.rst index 164960631925..447f767c6462 100644 --- a/Documentation/filesystems/ramfs-rootfs-initramfs.rst +++ b/Documentation/filesystems/ramfs-rootfs-initramfs.rst @@ -6,8 +6,7 @@ Ramfs, rootfs and initramfs October 17, 2005 -Rob Landley -============================= +:Author: Rob Landley What is ramfs? -------------- -- GitLab From 17eabd6a044b57b2c1b5459eb9d11af3ea909e63 Mon Sep 17 00:00:00 2001 From: Bob Pearson Date: Mon, 15 May 2023 15:10:57 -0500 Subject: [PATCH 5068/5631] RDMA/rxe: Fix double unlock in rxe_qp.c A recent patch can cause a double spin_unlock_bh() in rxe_qp_to_attr() at line 715 in rxe_qp.c. Move the 2nd unlock into the if statement. Fixes: f605f26ea196 ("RDMA/rxe: Protect QP state with qp->state_lock") Link: https://lore.kernel.org/r/20230515201056.1591140-1-rpearsonhpe@gmail.com Reported-by: Dan Carpenter Closes: https://lore.kernel.org/r/27773078-40ce-414f-8b97-781954da9f25@kili.mountain Signed-off-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_qp.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index c5451a4488ca..245dd36638c7 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -712,8 +712,9 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) if (qp->attr.sq_draining) { spin_unlock_bh(&qp->state_lock); cond_resched(); + } else { + spin_unlock_bh(&qp->state_lock); } - spin_unlock_bh(&qp->state_lock); return 0; } -- GitLab From 95339f40a8b652b5b1773def31e63fc53c26378a Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Tue, 16 May 2023 13:25:40 -0500 Subject: [PATCH 5069/5631] power: supply: Fix logic checking if system is running from battery The logic used for power_supply_is_system_supplied() counts all power supplies and assumes that the system is running from AC if there is either a non-battery power-supply reporting to be online or if no power-supplies exist at all. The second rule is for desktop systems, that don't have any battery/charger devices. These systems will incorrectly report to be powered from battery once a device scope power-supply is registered (e.g. a HID device), since these power-supplies increase the counter. Apart from HID devices, recent dGPUs provide UCSI power supplies on a desktop systems. The dGPU by default doesn't have anything plugged in so it's 'offline'. This makes power_supply_is_system_supplied() return 0 with a count of 1 meaning all drivers that use this get a wrong judgement. To fix this case adjust the logic to also examine the scope of the power supply. If the power supply is deemed a device power supply, then don't count it. Cc: Evan Quan Suggested-by: Lijo Lazar Signed-off-by: Mario Limonciello Signed-off-by: Sebastian Reichel --- drivers/power/supply/power_supply_core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index d1b19027f53b..3791aec69ddc 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -348,6 +348,10 @@ static int __power_supply_is_system_supplied(struct device *dev, void *data) struct power_supply *psy = dev_get_drvdata(dev); unsigned int *count = data; + if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_SCOPE, &ret)) + if (ret.intval == POWER_SUPPLY_SCOPE_DEVICE) + return 0; + (*count)++; if (psy->desc->type != POWER_SUPPLY_TYPE_BATTERY) if (!psy->desc->get_property(psy, POWER_SUPPLY_PROP_ONLINE, @@ -366,8 +370,8 @@ int power_supply_is_system_supplied(void) __power_supply_is_system_supplied); /* - * If no power class device was found at all, most probably we are - * running on a desktop system, so assume we are on mains power. + * If no system scope power class device was found at all, most probably we + * are running on a desktop system, so assume we are on mains power. */ if (count == 0) return 1; -- GitLab From b5f3fe27c54b1fe77d4dd834ccd48a6d694f872e Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Wed, 10 May 2023 11:50:56 +0800 Subject: [PATCH 5070/5631] RDMA/rxe: Convert spin_{lock_bh,unlock_bh} to spin_{lock_irqsave,unlock_irqrestore} We need to call spin_lock_irqsave()/spin_unlock_irqrestore() for state_lock in rxe, otherwsie the callchain: ib_post_send_mad -> spin_lock_irqsave -> ib_post_send -> rxe_post_send -> spin_lock_bh -> spin_unlock_bh -> spin_unlock_irqrestore Causes below traces during run block nvmeof-mp/001 test due to mismatched spinlock nesting: WARNING: CPU: 0 PID: 94794 at kernel/softirq.c:376 __local_bh_enable_ip+0xc2/0x140 [ ... ] CPU: 0 PID: 94794 Comm: kworker/u4:1 Tainted: G E 6.4.0-rc1 #9 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 Workqueue: rdma_cm cma_work_handler [rdma_cm] RIP: 0010:__local_bh_enable_ip+0xc2/0x140 Code: 48 85 c0 74 72 5b 41 5c 5d 31 c0 89 c2 89 c1 89 c6 89 c7 41 89 c0 e9 bd 0e 11 01 65 8b 05 f2 65 72 48 85 c0 0f 85 76 ff ff ff <0f> 0b e9 6f ff ff ff e8 d2 39 1c 00 eb 80 4c 89 e7 e8 68 ad 0a 00 RSP: 0018:ffffb7cf818539f0 EFLAGS: 00010046 RAX: 0000000000000000 RBX: 0000000000000201 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000201 RDI: ffffffffc0f25f79 RBP: ffffb7cf81853a00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffc0f25f79 R13: ffff8db1f0fa6000 R14: ffff8db2c63ff000 R15: 00000000000000e8 FS: 0000000000000000(0000) GS:ffff8db33bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000559758db0f20 CR3: 0000000105124000 CR4: 00000000003506f0 Call Trace: _raw_spin_unlock_bh+0x31/0x40 rxe_post_send+0x59/0x8b0 [rdma_rxe] ib_send_mad+0x26b/0x470 [ib_core] ib_post_send_mad+0x150/0xb40 [ib_core] ? cm_form_tid+0x5b/0x90 [ib_cm] ib_send_cm_req+0x7c8/0xb70 [ib_cm] rdma_connect_locked+0x433/0x940 [rdma_cm] nvme_rdma_cm_handler+0x5d7/0x9c0 [nvme_rdma] cma_cm_event_handler+0x4f/0x170 [rdma_cm] cma_work_handler+0x6a/0xe0 [rdma_cm] process_one_work+0x2a9/0x580 worker_thread+0x52/0x3f0 ? __pfx_worker_thread+0x10/0x10 kthread+0x109/0x140 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 raw_local_irq_restore() called with IRQs enabled WARNING: CPU: 0 PID: 94794 at kernel/locking/irqflag-debug.c:10 warn_bogus_irq_restore+0x37/0x60 [ ... ] CPU: 0 PID: 94794 Comm: kworker/u4:1 Tainted: G W E 6.4.0-rc1 #9 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-0-g2dd4b9b-rebuilt.opensuse.org 04/01/2014 Workqueue: rdma_cm cma_work_handler [rdma_cm] RIP: 0010:warn_bogus_irq_restore+0x37/0x60 Code: fb 01 77 36 83 e3 01 74 0e 48 8b 5d f8 c9 31 f6 89 f7 e9 ac ea 01 00 48 c7 c7 e0 52 33 b9 c6 05 bb 1c 69 01 01 e8 39 24 f0 fe <0f> 0b 48 8b 5d f8 c9 31 f6 89 f7 e9 89 ea 01 00 0f b6 f3 48 c7 c7 RSP: 0018:ffffb7cf81853a58 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffffb7cf81853a60 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8db2cfb1a9e8 R13: ffff8db2cfb1a9d8 R14: ffff8db2c63ff000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff8db33bc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000559758db0f20 CR3: 0000000105124000 CR4: 00000000003506f0 Call Trace: _raw_spin_unlock_irqrestore+0x91/0xa0 ib_send_mad+0x1e3/0x470 [ib_core] ib_post_send_mad+0x150/0xb40 [ib_core] ? cm_form_tid+0x5b/0x90 [ib_cm] ib_send_cm_req+0x7c8/0xb70 [ib_cm] rdma_connect_locked+0x433/0x940 [rdma_cm] nvme_rdma_cm_handler+0x5d7/0x9c0 [nvme_rdma] cma_cm_event_handler+0x4f/0x170 [rdma_cm] cma_work_handler+0x6a/0xe0 [rdma_cm] process_one_work+0x2a9/0x580 worker_thread+0x52/0x3f0 ? __pfx_worker_thread+0x10/0x10 kthread+0x109/0x140 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 Fixes: f605f26ea196 ("RDMA/rxe: Protect QP state with qp->state_lock") Link: https://lore.kernel.org/r/20230510035056.881196-1-guoqing.jiang@linux.dev Signed-off-by: Guoqing Jiang Reviewed-by: Bob Pearson Signed-off-by: Jason Gunthorpe --- drivers/infiniband/sw/rxe/rxe_comp.c | 26 +++++++++++-------- drivers/infiniband/sw/rxe/rxe_net.c | 7 +++--- drivers/infiniband/sw/rxe/rxe_qp.c | 36 +++++++++++++++++---------- drivers/infiniband/sw/rxe/rxe_recv.c | 9 ++++--- drivers/infiniband/sw/rxe/rxe_req.c | 30 ++++++++++++---------- drivers/infiniband/sw/rxe/rxe_resp.c | 14 ++++++----- drivers/infiniband/sw/rxe/rxe_verbs.c | 25 ++++++++++--------- 7 files changed, 86 insertions(+), 61 deletions(-) diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c index db18ace74d2b..f46c5a5fd0ae 100644 --- a/drivers/infiniband/sw/rxe/rxe_comp.c +++ b/drivers/infiniband/sw/rxe/rxe_comp.c @@ -115,15 +115,16 @@ static enum ib_wc_opcode wr_to_wc_opcode(enum ib_wr_opcode opcode) void retransmit_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, retrans_timer); + unsigned long flags; rxe_dbg_qp(qp, "retransmit timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { qp->comp.timeout = 1; rxe_sched_task(&qp->comp.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } void rxe_comp_queue_pkt(struct rxe_qp *qp, struct sk_buff *skb) @@ -481,11 +482,13 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe) static void comp_check_sq_drain_done(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_SQD)) { if (qp->attr.sq_draining && qp->comp.psn == qp->req.psn) { qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -499,7 +502,7 @@ static void comp_check_sq_drain_done(struct rxe_qp *qp) return; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static inline enum comp_state complete_ack(struct rxe_qp *qp, @@ -625,13 +628,15 @@ static void free_pkt(struct rxe_pkt_info *pkt) */ static void reset_retry_timer(struct rxe_qp *qp) { + unsigned long flags; + if (qp_type(qp) == IB_QPT_RC && qp->qp_timeout_jiffies) { - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) >= IB_QPS_RTS && psn_compare(qp->req.psn, qp->comp.psn) > 0) mod_timer(&qp->retrans_timer, jiffies + qp->qp_timeout_jiffies); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } } @@ -643,18 +648,19 @@ int rxe_completer(struct rxe_qp *qp) struct rxe_pkt_info *pkt = NULL; enum comp_state state; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_resp_pkts(qp); flush_send_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->comp.timeout) { qp->comp.timeout_retry = 1; diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 2bc7361152ea..a38fab19bed1 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -412,15 +412,16 @@ int rxe_xmit_packet(struct rxe_qp *qp, struct rxe_pkt_info *pkt, int err; int is_request = pkt->mask & RXE_REQ_MASK; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if ((is_request && (qp_state(qp) < IB_QPS_RTS)) || (!is_request && (qp_state(qp) < IB_QPS_RTR))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_dbg_qp(qp, "Packet dropped. QP is not in ready state\n"); goto drop; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_icrc_generate(skb, pkt); diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 245dd36638c7..61a2eb77d999 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -300,6 +300,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct rxe_cq *rcq = to_rcq(init->recv_cq); struct rxe_cq *scq = to_rcq(init->send_cq); struct rxe_srq *srq = init->srq ? to_rsrq(init->srq) : NULL; + unsigned long flags; rxe_get(pd); rxe_get(rcq); @@ -325,10 +326,10 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, if (err) goto err2; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; @@ -492,24 +493,28 @@ static void rxe_qp_reset(struct rxe_qp *qp) /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->resp.task); rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); qp->attr.sq_draining = 1; rxe_sched_task(&qp->comp.task); rxe_sched_task(&qp->req.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } /* caller should hold qp->state_lock */ @@ -555,14 +560,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, qp->attr.cur_qp_state = attr->qp_state; if (mask & IB_QP_STATE) { - spin_lock_bh(&qp->state_lock); + unsigned long flags; + + spin_lock_irqsave(&qp->state_lock, flags); err = __qp_chk_state(qp, attr, mask); if (!err) { qp->attr.qp_state = attr->qp_state; rxe_dbg_qp(qp, "state -> %s\n", qps2str[attr->qp_state]); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (err) return err; @@ -688,6 +695,8 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, /* called by the query qp verb */ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { + unsigned long flags; + *attr = qp->attr; attr->rq_psn = qp->resp.psn; @@ -708,12 +717,12 @@ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) /* Applications that get this state typically spin on it. * Yield the processor */ - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->attr.sq_draining) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); cond_resched(); } else { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } return 0; @@ -737,10 +746,11 @@ int rxe_qp_chk_destroy(struct rxe_qp *qp) static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); qp->valid = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c index 2f953cc74256..5861e4244049 100644 --- a/drivers/infiniband/sw/rxe/rxe_recv.c +++ b/drivers/infiniband/sw/rxe/rxe_recv.c @@ -14,6 +14,7 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, struct rxe_qp *qp) { unsigned int pkt_type; + unsigned long flags; if (unlikely(!qp->valid)) return -EINVAL; @@ -38,19 +39,19 @@ static int check_type_state(struct rxe_dev *rxe, struct rxe_pkt_info *pkt, return -EINVAL; } - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (pkt->mask & RXE_REQ_MASK) { if (unlikely(qp_state(qp) < IB_QPS_RTR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } else { if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return -EINVAL; } } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return 0; } diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c index 65134a9aefe7..5fe7cbae3031 100644 --- a/drivers/infiniband/sw/rxe/rxe_req.c +++ b/drivers/infiniband/sw/rxe/rxe_req.c @@ -99,17 +99,18 @@ static void req_retry(struct rxe_qp *qp) void rnr_nak_timer(struct timer_list *t) { struct rxe_qp *qp = from_timer(qp, t, rnr_nak_timer); + unsigned long flags; rxe_dbg_qp(qp, "nak timer fired\n"); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp->valid) { /* request a send queue retry */ qp->req.need_retry = 1; qp->req.wait_for_rnr_timer = 0; rxe_sched_task(&qp->req.task); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static void req_check_sq_drain_done(struct rxe_qp *qp) @@ -118,8 +119,9 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) unsigned int index; unsigned int cons; struct rxe_send_wqe *wqe; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_SQD) { q = qp->sq.queue; index = qp->req.wqe_index; @@ -140,7 +142,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) break; qp->attr.sq_draining = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->ibqp.event_handler) { struct ib_event ev; @@ -154,7 +156,7 @@ static void req_check_sq_drain_done(struct rxe_qp *qp) return; } while (0); } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); } static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) @@ -173,6 +175,7 @@ static struct rxe_send_wqe *__req_next_wqe(struct rxe_qp *qp) static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) { struct rxe_send_wqe *wqe; + unsigned long flags; req_check_sq_drain_done(qp); @@ -180,13 +183,13 @@ static struct rxe_send_wqe *req_next_wqe(struct rxe_qp *qp) if (wqe == NULL) return NULL; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely((qp_state(qp) == IB_QPS_SQD) && (wqe->state != wqe_state_processing))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return NULL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); wqe->mask = wr_opcode_mask(wqe->wr.opcode, qp); return wqe; @@ -676,16 +679,17 @@ int rxe_requester(struct rxe_qp *qp) struct rxe_queue *q = qp->sq.queue; struct rxe_ah *ah; struct rxe_av *av; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } if (unlikely(qp_state(qp) == IB_QPS_ERR)) { wqe = __req_next_wqe(qp); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (wqe) goto err; else @@ -700,10 +704,10 @@ int rxe_requester(struct rxe_qp *qp) qp->req.wait_psn = 0; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); /* we come here if the retransmit timer has fired * or if the rnr timer has fired. If the retransmit diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index 68f6cd188d8e..1da044f6b7d4 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -1047,6 +1047,7 @@ static enum resp_states do_complete(struct rxe_qp *qp, struct ib_uverbs_wc *uwc = &cqe.uibwc; struct rxe_recv_wqe *wqe = qp->resp.wqe; struct rxe_dev *rxe = to_rdev(qp->ibqp.device); + unsigned long flags; if (!wqe) goto finish; @@ -1137,12 +1138,12 @@ static enum resp_states do_complete(struct rxe_qp *qp, return RESPST_ERR_CQ_OVERFLOW; finish: - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (unlikely(qp_state(qp) == IB_QPS_ERR)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return RESPST_CHK_RESOURCE; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(!pkt)) return RESPST_DONE; @@ -1468,18 +1469,19 @@ int rxe_responder(struct rxe_qp *qp) enum resp_states state; struct rxe_pkt_info *pkt = NULL; int ret; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (!qp->valid || qp_state(qp) == IB_QPS_ERR || qp_state(qp) == IB_QPS_RESET) { bool notify = qp->valid && (qp_state(qp) == IB_QPS_ERR); drain_req_pkts(qp); flush_recv_queue(qp, notify); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); goto exit; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index dea605b7f683..4d8f6b8051ff 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -904,10 +904,10 @@ static int rxe_post_send_kernel(struct rxe_qp *qp, if (!err) rxe_sched_task(&qp->req.task); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->comp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } @@ -917,22 +917,23 @@ static int rxe_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, { struct rxe_qp *qp = to_rqp(ibqp); int err; + unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } if (unlikely(qp_state(qp) < IB_QPS_RTS)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_err_qp(qp, "qp not ready to send"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (qp->is_user) { /* Utilize process context to do protocol processing */ @@ -1008,22 +1009,22 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, struct rxe_rq *rq = &qp->rq; unsigned long flags; - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); /* caller has already called destroy_qp */ if (WARN_ON_ONCE(!qp->valid)) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); rxe_err_qp(qp, "qp has been destroyed"); return -EINVAL; } /* see C10-97.2.1 */ if (unlikely((qp_state(qp) < IB_QPS_INIT))) { - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); *bad_wr = wr; rxe_dbg_qp(qp, "qp not ready to post recv"); return -EINVAL; } - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); if (unlikely(qp->srq)) { *bad_wr = wr; @@ -1044,10 +1045,10 @@ static int rxe_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, spin_unlock_irqrestore(&rq->producer_lock, flags); - spin_lock_bh(&qp->state_lock); + spin_lock_irqsave(&qp->state_lock, flags); if (qp_state(qp) == IB_QPS_ERR) rxe_sched_task(&qp->resp.task); - spin_unlock_bh(&qp->state_lock); + spin_unlock_irqrestore(&qp->state_lock, flags); return err; } -- GitLab From 866422cdddcdf59d8c68e9472d49ba1be29b5fcf Mon Sep 17 00:00:00 2001 From: Yonatan Nachum Date: Thu, 11 May 2023 11:51:03 +0000 Subject: [PATCH 5071/5631] RDMA/efa: Fix unsupported page sizes in device Device uses 4KB size blocks for user pages indirect list while the driver creates those blocks with the size of PAGE_SIZE of the kernel. On kernels with PAGE_SIZE different than 4KB (ARM RHEL), this leads to a failure on register MR with indirect list because of the miss communication between driver and device. Fixes: 40909f664d27 ("RDMA/efa: Add EFA verbs implementation") Link: https://lore.kernel.org/r/20230511115103.13876-1-ynachum@amazon.com Reviewed-by: Firas Jahjah Reviewed-by: Michael Margolin Signed-off-by: Yonatan Nachum Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/efa/efa_verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index 8eca6c14d0cf..2a195c4b0f17 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1403,7 +1403,7 @@ static int pbl_continuous_initialize(struct efa_dev *dev, */ static int pbl_indirect_initialize(struct efa_dev *dev, struct pbl_context *pbl) { - u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, PAGE_SIZE); + u32 size_in_pages = DIV_ROUND_UP(pbl->pbl_buf_size_in_bytes, EFA_CHUNK_PAYLOAD_SIZE); struct scatterlist *sgl; int sg_dma_cnt, err; -- GitLab From 5149452ca66289ef33d13897ee845a2f6f5b680f Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:49 +0800 Subject: [PATCH 5072/5631] scsi: ufs: core: Fix MCQ tag calculation The transfer command descriptor is allocated in ufshcd_memory_alloc() and referenced by the transfer request descriptor with stride size sizeof_utp_transfer_cmd_desc() instead of sizeof(struct utp_transfer_cmd_desc). Consequently, computing tag by address offset should also refer to the same stride. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-2-powen.kao@mediatek.com Reviewed-by: Bart Van Assche Reviewed-by: Manivannan Sadhasivam Reviewed-by: Stanley Chu Reviewed-by: Ziqi Chen Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 2 +- drivers/ufs/core/ufshcd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 202ff71e1b58..b7c5f39b50e6 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -265,7 +265,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof(struct utp_transfer_cmd_desc)); + return div_u64(addr, sizeof_utp_transfer_cmd_desc(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 45fd374fe56c..984abbe1fb93 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof(struct utp_transfer_cmd_desc) * nutrs; + ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); -- GitLab From 06caeb536b2b21668efd2d6fa97c09461957b3a7 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:50 +0800 Subject: [PATCH 5073/5631] scsi: ufs: core: Rename symbol sizeof_utp_transfer_cmd_desc() Naming the functions after standard operators like sizeof() may cause confusion. Rename it to ufshcd_get_ucd_size(). Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-3-powen.kao@mediatek.com Suggested-by: Manivannan Sadhasivam Reviewed-by: Stanley Chu Reviewed-by: Ziqi Chen Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 2 +- drivers/ufs/core/ufshcd.c | 10 +++++----- include/ufs/ufshcd.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index b7c5f39b50e6..937933d3f77c 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -265,7 +265,7 @@ static int ufshcd_mcq_get_tag(struct ufs_hba *hba, addr = (le64_to_cpu(cqe->command_desc_base_addr) & CQE_UCD_BA) - hba->ucdl_dma_addr; - return div_u64(addr, sizeof_utp_transfer_cmd_desc(hba)); + return div_u64(addr, ufshcd_get_ucd_size(hba)); } static void ufshcd_mcq_process_cqe(struct ufs_hba *hba, diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 984abbe1fb93..e7e79f515e14 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2849,10 +2849,10 @@ static void ufshcd_map_queues(struct Scsi_Host *shost) static void ufshcd_init_lrb(struct ufs_hba *hba, struct ufshcd_lrb *lrb, int i) { struct utp_transfer_cmd_desc *cmd_descp = (void *)hba->ucdl_base_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); struct utp_transfer_req_desc *utrdlp = hba->utrdl_base_addr; dma_addr_t cmd_desc_element_addr = hba->ucdl_dma_addr + - i * sizeof_utp_transfer_cmd_desc(hba); + i * ufshcd_get_ucd_size(hba); u16 response_offset = offsetof(struct utp_transfer_cmd_desc, response_upiu); u16 prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); @@ -3761,7 +3761,7 @@ static int ufshcd_memory_alloc(struct ufs_hba *hba) size_t utmrdl_size, utrdl_size, ucdl_size; /* Allocate memory for UTP command descriptors */ - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * hba->nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * hba->nutrs; hba->ucdl_base_addr = dmam_alloc_coherent(hba->dev, ucdl_size, &hba->ucdl_dma_addr, @@ -3861,7 +3861,7 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba) prdt_offset = offsetof(struct utp_transfer_cmd_desc, prd_table); - cmd_desc_size = sizeof_utp_transfer_cmd_desc(hba); + cmd_desc_size = ufshcd_get_ucd_size(hba); cmd_desc_dma_addr = hba->ucdl_dma_addr; for (i = 0; i < hba->nutrs; i++) { @@ -8452,7 +8452,7 @@ static void ufshcd_release_sdb_queue(struct ufs_hba *hba, int nutrs) { size_t ucdl_size, utrdl_size; - ucdl_size = sizeof_utp_transfer_cmd_desc(hba) * nutrs; + ucdl_size = ufshcd_get_ucd_size(hba) * nutrs; dmam_free_coherent(hba->dev, ucdl_size, hba->ucdl_base_addr, hba->ucdl_dma_addr); diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index f7553293ba98..df1d04f7a542 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1133,7 +1133,7 @@ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba) ({ (void)(hba); BUILD_BUG_ON(sg_entry_size != sizeof(struct ufshcd_sg_entry)); }) #endif -static inline size_t sizeof_utp_transfer_cmd_desc(const struct ufs_hba *hba) +static inline size_t ufshcd_get_ucd_size(const struct ufs_hba *hba) { return sizeof(struct utp_transfer_cmd_desc) + SG_ALL * ufshcd_sg_entry_size(hba); } -- GitLab From 72a81bb0b6fc9b759ac0fdaca3ec5884a8b2f304 Mon Sep 17 00:00:00 2001 From: Po-Wen Kao Date: Thu, 4 May 2023 23:44:51 +0800 Subject: [PATCH 5074/5631] scsi: ufs: core: Fix MCQ nr_hw_queues Since MAXQ is 0-based value, add one to obtain number of hardware queues. Signed-off-by: Po-Wen Kao Link: https://lore.kernel.org/r/20230504154454.26654-4-powen.kao@mediatek.com Reviewed-by: Bean Huo Reviewed-by: Manivannan Sadhasivam Reviewed-by: Bart Van Assche Reviewed-by: Stanley Chu Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufs-mcq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 937933d3f77c..51b3c6ae781d 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -150,7 +150,8 @@ static int ufshcd_mcq_config_nr_queues(struct ufs_hba *hba) u32 hba_maxq, rem, tot_queues; struct Scsi_Host *host = hba->host; - hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities); + /* maxq is 0 based value */ + hba_maxq = FIELD_GET(MAX_QUEUE_SUP, hba->mcq_capabilities) + 1; tot_queues = UFS_MCQ_NUM_DEV_CMD_QUEUES + read_queues + poll_queues + rw_queues; -- GitLab From 75e5fab7db0cecb6e16b22c34608f0b40a4c7cd1 Mon Sep 17 00:00:00 2001 From: Ravulapati Vishnu Vardhan Rao Date: Thu, 11 May 2023 16:55:32 +0530 Subject: [PATCH 5075/5631] ASoC: lpass: Fix for KASAN use_after_free out of bounds When we run syzkaller we get below Out of Bounds error. "KASAN: slab-out-of-bounds Read in regcache_flat_read" Below is the backtrace of the issue: BUG: KASAN: slab-out-of-bounds in regcache_flat_read+0x10c/0x110 Read of size 4 at addr ffffff8088fbf714 by task syz-executor.4/14144 CPU: 6 PID: 14144 Comm: syz-executor.4 Tainted: G W Hardware name: Qualcomm Technologies, Inc. sc7280 CRD platform (rev5+) (DT) Call trace: dump_backtrace+0x0/0x4ec show_stack+0x34/0x50 dump_stack_lvl+0xdc/0x11c print_address_description+0x30/0x2d8 kasan_report+0x178/0x1e4 __asan_report_load4_noabort+0x44/0x50 regcache_flat_read+0x10c/0x110 regcache_read+0xf8/0x5a0 _regmap_read+0x45c/0x86c _regmap_update_bits+0x128/0x290 regmap_update_bits_base+0xc0/0x15c snd_soc_component_update_bits+0xa8/0x22c snd_soc_component_write_field+0x68/0xd4 tx_macro_put_dec_enum+0x1d0/0x268 snd_ctl_elem_write+0x288/0x474 By Error checking and checking valid values issue gets rectifies. Signed-off-by: Ravulapati Vishnu Vardhan Rao value.enumerated.item[0]; + if (val >= e->items) + return -EINVAL; switch (e->reg) { case CDC_TX_INP_MUX_ADC_MUX0_CFG0: @@ -772,6 +774,9 @@ static int tx_macro_put_dec_enum(struct snd_kcontrol *kcontrol, case CDC_TX_INP_MUX_ADC_MUX7_CFG0: mic_sel_reg = CDC_TX7_TX_PATH_CFG0; break; + default: + dev_err(component->dev, "Error in configuration!!\n"); + return -EINVAL; } if (val != 0) { -- GitLab From 8b271370e963370703819bd9795a54d658071bed Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Tue, 16 May 2023 16:46:30 +0000 Subject: [PATCH 5076/5631] ASoC: rt5682: Disable jack detection interrupt during suspend The rt5682 driver switches its regmap to cache-only when the device suspends and back to regular mode on resume. When the jack detect interrupt fires rt5682_irq() schedules the jack detect work. This can result in invalid reads from the regmap in cache-only mode if the work runs before the device has resumed: [ 56.245502] rt5682 9-001a: ASoC: error at soc_component_read_no_lock on rt5682.9-001a for register: [0x000000f0] -16 Disable the jack detection interrupt during suspend and re-enable it on resume. The driver already schedules the jack detection work on resume, so any state change during suspend is still handled. This is essentially the same as commit f7d00a9be147 ("SoC: rt5682s: Disable jack detection interrupt during suspend") for the rt5682s. Cc: stable@kernel.org Signed-off-by: Matthias Kaehlcke dev, i2c->irq, NULL, rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, "rt5682", rt5682); - if (ret) + if (!ret) + rt5682->irq = i2c->irq; + else dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret); } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index f6c798b65c08..5d992543b791 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -2959,6 +2959,9 @@ static int rt5682_suspend(struct snd_soc_component *component) if (rt5682->is_sdw) return 0; + if (rt5682->irq) + disable_irq(rt5682->irq); + cancel_delayed_work_sync(&rt5682->jack_detect_work); cancel_delayed_work_sync(&rt5682->jd_check_work); if (rt5682->hs_jack && (rt5682->jack_type & SND_JACK_HEADSET) == SND_JACK_HEADSET) { @@ -3027,6 +3030,9 @@ static int rt5682_resume(struct snd_soc_component *component) mod_delayed_work(system_power_efficient_wq, &rt5682->jack_detect_work, msecs_to_jiffies(0)); + if (rt5682->irq) + enable_irq(rt5682->irq); + return 0; } #else diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index d568c6993c33..e8efd8a84a6c 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -1462,6 +1462,7 @@ struct rt5682_priv { int pll_out[RT5682_PLLS]; int jack_type; + int irq; int irq_work_delay_time; }; -- GitLab From 4e81a6cba517cb33584308a331f14f5e3fec369b Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 15 May 2023 10:20:41 -0700 Subject: [PATCH 5077/5631] scsi: storvsc: Don't pass unused PFNs to Hyper-V host In a SCSI request, storvsc pre-allocates space for up to MAX_PAGE_BUFFER_COUNT physical frame numbers to be passed to Hyper-V. If the size of the I/O request requires more PFNs, a separate memory area of exactly the correct size is dynamically allocated. But when the pre-allocated area is used, current code always passes MAX_PAGE_BUFFER_COUNT PFNs to Hyper-V, even if fewer are needed. While this doesn't break anything because the additional PFNs are always zero, more bytes than necessary are copied into the VMBus channel ring buffer. This takes CPU cycles and wastes space in the ring buffer. For a typical 4 Kbyte I/O that requires only a single PFN, 248 unnecessary bytes are copied. Fix this by setting the payload_sz based on the actual number of PFNs required, not the size of the pre-allocated space. Reported-by: John Starks Fixes: 8f43710543ef ("scsi: storvsc: Support PAGE_SIZE larger than 4K") Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1684171241-16209-1-git-send-email-mikelley@microsoft.com Signed-off-by: Martin K. Petersen --- drivers/scsi/storvsc_drv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d9ce379c4d2e..e6bc622954cf 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1780,7 +1780,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; - payload_sz = sizeof(cmd_request->mpb); + payload_sz = 0; if (scsi_sg_count(scmnd)) { unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); @@ -1789,10 +1789,10 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) unsigned long hvpfn, hvpfns_to_add; int j, i = 0, sg_count; - if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { + payload_sz = (hvpg_count * sizeof(u64) + + sizeof(struct vmbus_packet_mpb_array)); - payload_sz = (hvpg_count * sizeof(u64) + - sizeof(struct vmbus_packet_mpb_array)); + if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { payload = kzalloc(payload_sz, GFP_ATOMIC); if (!payload) return SCSI_MLQUEUE_DEVICE_BUSY; -- GitLab From 6ca9818d1624e136a76ae8faedb6b6c95ca66903 Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Mon, 15 May 2023 15:01:55 +0800 Subject: [PATCH 5078/5631] scsi: Revert "scsi: core: Do not increase scsi_device's iorequest_cnt if dispatch failed" The "atomic_inc(&cmd->device->iorequest_cnt)" in scsi_queue_rq() would cause kernel panic because cmd->device may be freed after returning from scsi_dispatch_cmd(). This reverts commit cfee29ffb45b1c9798011b19d454637d1b0fe87d. Signed-off-by: Wenchao Hao Reported-by: Ming Lei Closes: https://lore.kernel.org/r/ZF+zB+bB7iqe0wGd@ovpn-8-17.pek2.redhat.com Link: https://lore.kernel.org/r/20230515070156.1790181-2-haowenchao2@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index b7c569a42aa4..03964b26f3f2 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1463,6 +1463,8 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) struct Scsi_Host *host = cmd->device->host; int rtn = 0; + atomic_inc(&cmd->device->iorequest_cnt); + /* check if the device is still usable */ if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { /* in SDEV_DEL we error all commands. DID_NO_CONNECT @@ -1761,7 +1763,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, goto out_dec_host_busy; } - atomic_inc(&cmd->device->iorequest_cnt); return BLK_STS_OK; out_dec_host_busy: -- GitLab From 09e797c8641f6ad435c33ae24c223351197ea29a Mon Sep 17 00:00:00 2001 From: Wenchao Hao Date: Mon, 15 May 2023 15:01:56 +0800 Subject: [PATCH 5079/5631] scsi: core: Decrease scsi_device's iorequest_cnt if dispatch failed If scsi_dispatch_cmd() failed, the SCSI command was not sent to the target, scsi_queue_rq() would return BLK_STS_RESOURCE and the related request would be requeued. The timeout of this request would not fire, no one would increase iodone_cnt. The above flow would result the iodone_cnt smaller than iorequest_cnt. So decrease the iorequest_cnt if dispatch failed to workaround the issue. Signed-off-by: Wenchao Hao Reported-by: Ming Lei Closes: https://lore.kernel.org/r/ZF+zB+bB7iqe0wGd@ovpn-8-17.pek2.redhat.com Link: https://lore.kernel.org/r/20230515070156.1790181-3-haowenchao2@huawei.com Reviewed-by: Ming Lei Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_lib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 03964b26f3f2..0226c9279cef 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1485,6 +1485,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) */ SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, "queuecommand : device blocked\n")); + atomic_dec(&cmd->device->iorequest_cnt); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1517,6 +1518,7 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) trace_scsi_dispatch_cmd_start(cmd); rtn = host->hostt->queuecommand(host, cmd); if (rtn) { + atomic_dec(&cmd->device->iorequest_cnt); trace_scsi_dispatch_cmd_error(cmd, rtn); if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && rtn != SCSI_MLQUEUE_TARGET_BUSY) -- GitLab From d6352dae0903fe8beae4c007dc320e9e9f1fed45 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 May 2023 19:29:25 +0300 Subject: [PATCH 5080/5631] devlink: Fix crash with CONFIG_NET_NS=n '__net_initdata' becomes a no-op with CONFIG_NET_NS=y, but when this option is disabled it becomes '__initdata', which means the data can be freed after the initialization phase. This annotation is obviously incorrect for the devlink net device notifier block which is still registered after the initialization phase [1]. Fix this crash by removing the '__net_initdata' annotation. [1] general protection fault, probably for non-canonical address 0xcccccccccccccccc: 0000 [#1] PREEMPT SMP CPU: 3 PID: 117 Comm: (udev-worker) Not tainted 6.4.0-rc1-custom-gdf0acdc59b09 #64 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-1.fc37 04/01/2014 RIP: 0010:notifier_call_chain+0x58/0xc0 [...] Call Trace: dev_set_mac_address+0x85/0x120 dev_set_mac_address_user+0x30/0x50 do_setlink+0x219/0x1270 rtnl_setlink+0xf7/0x1a0 rtnetlink_rcv_msg+0x142/0x390 netlink_rcv_skb+0x58/0x100 netlink_unicast+0x188/0x270 netlink_sendmsg+0x214/0x470 __sys_sendto+0x12f/0x1a0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x38/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: e93c9378e33f ("devlink: change per-devlink netdev notifier to static one") Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/netdev/600ddf9e-589a-2aa0-7b69-a438f833ca10@samsung.com/ Tested-by: Marek Szyprowski Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230515162925.1144416-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/devlink/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/devlink/core.c b/net/devlink/core.c index 0e58eee44bdb..c23ebabadc52 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -294,7 +294,7 @@ static struct pernet_operations devlink_pernet_ops __net_initdata = { .pre_exit = devlink_pernet_pre_exit, }; -static struct notifier_block devlink_port_netdevice_nb __net_initdata = { +static struct notifier_block devlink_port_netdevice_nb = { .notifier_call = devlink_port_netdevice_event, }; -- GitLab From cb0ddaaa5db09d7d216fcbf0e68779be223a1128 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Mon, 15 May 2023 21:50:43 +0200 Subject: [PATCH 5081/5631] wifi: rtw88: sdio: Always use two consecutive bytes for word operations The Allwinner sunxi-mmc controller cannot handle word (16 bit) transfers. So and sdio_{read,write}w fails with messages like the following example using an RTL8822BS (but the same problems were also observed with RTL8822CS and RTL8723DS chips): rtw_8822bs mmc1:0001:1: Firmware version 27.2.0, H2C version 13 sunxi-mmc 4021000.mmc: unaligned scatterlist: os f80 length 2 sunxi-mmc 4021000.mmc: map DMA failed rtw_8822bs mmc1:0001:1: sdio read16 failed (0x10230): -22 Use two consecutive single byte accesses for word operations instead. It turns out that upon closer inspection this is also what the vendor driver does, even though it does have support for sdio_{read,write}w. So we can conclude that the rtw88 chips do support word access but only on SDIO controllers that also support it. Since there's no way to detect if the controller supports word access or not the rtw88 sdio driver switches to the easiest approach: avoiding word access. Reported-by: Larry Finger Closes: https://lore.kernel.org/linux-wireless/527585e5-9cdd-66ed-c3af-6da162f4b720@lwfinger.net/ Reported-by: Rudi Heitbaum Link: https://github.com/LibreELEC/LibreELEC.tv/pull/7837#issue-1708469467 Fixes: 65371a3f14e7 ("wifi: rtw88: sdio: Add HCI implementation for SDIO based chipsets") Reviewed-by: Ping-Ke Shih Signed-off-by: Martin Blumenstingl Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230515195043.572375-1-martin.blumenstingl@googlemail.com --- drivers/net/wireless/realtek/rtw88/sdio.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c index af0459a79899..06fce7c3adda 100644 --- a/drivers/net/wireless/realtek/rtw88/sdio.c +++ b/drivers/net/wireless/realtek/rtw88/sdio.c @@ -87,11 +87,6 @@ static void rtw_sdio_writew(struct rtw_dev *rtwdev, u16 val, u32 addr, u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) { - sdio_writew(rtwsdio->sdio_func, val, addr, err_ret); - return; - } - *(__le16 *)buf = cpu_to_le16(val); for (i = 0; i < 2; i++) { @@ -125,9 +120,6 @@ static u16 rtw_sdio_readw(struct rtw_dev *rtwdev, u32 addr, int *err_ret) u8 buf[2]; int i; - if (rtw_sdio_use_memcpy_io(rtwdev, addr, 2)) - return sdio_readw(rtwsdio->sdio_func, addr, err_ret); - for (i = 0; i < 2; i++) { buf[i] = sdio_readb(rtwsdio->sdio_func, addr + i, err_ret); if (*err_ret) -- GitLab From 212457ccbd60dba34f965e4ffbe62f0e4f970538 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 20:34:22 +0200 Subject: [PATCH 5082/5631] wifi: b43: fix incorrect __packed annotation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit clang warns about an unpacked structure inside of a packed one: drivers/net/wireless/broadcom/b43/b43.h:654:4: error: field data within 'struct b43_iv' is less aligned than 'union (unnamed union at /home/arnd/arm-soc/drivers/net/wireless/broadcom/b43/b43.h:651:2)' and is usually due to 'struct b43_iv' being packed, which can lead to unaligned accesses [-Werror,-Wunaligned-access] The problem here is that the anonymous union has the default alignment from its members, apparently because the original author mixed up the placement of the __packed attribute by placing it next to the struct member rather than the union definition. As the struct itself is also marked as __packed, there is no need to mark its members, so just move the annotation to the inner type instead. As Michael noted, the same problem is present in b43legacy, so change both at the same time. Acked-by: Michael Büsch Reported-by: kernel test robot Reviewed-by: Simon Horman Tested-by: Larry Finger Link: https://lore.kernel.org/oe-kbuild-all/202305160749.ay1HAoyP-lkp@intel.com/ Signed-off-by: Arnd Bergmann Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20230516183442.536589-1-arnd@kernel.org --- drivers/net/wireless/broadcom/b43/b43.h | 2 +- drivers/net/wireless/broadcom/b43legacy/b43legacy.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/broadcom/b43/b43.h b/drivers/net/wireless/broadcom/b43/b43.h index 9fc7c088a539..67b4bac048e5 100644 --- a/drivers/net/wireless/broadcom/b43/b43.h +++ b/drivers/net/wireless/broadcom/b43/b43.h @@ -651,7 +651,7 @@ struct b43_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; diff --git a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h index 6b0cec467938..f49365d14619 100644 --- a/drivers/net/wireless/broadcom/b43legacy/b43legacy.h +++ b/drivers/net/wireless/broadcom/b43legacy/b43legacy.h @@ -379,7 +379,7 @@ struct b43legacy_iv { union { __be16 d16; __be32 d32; - } data __packed; + } __packed data; } __packed; #define B43legacy_PHYMODE(phytype) (1 << (phytype)) -- GitLab From 0642287e3ecdd0d1f88e6a2e63768e16153a990c Mon Sep 17 00:00:00 2001 From: Harshit Mogalapalli Date: Mon, 8 May 2023 23:07:16 -0700 Subject: [PATCH 5083/5631] dmaengine: idxd: Fix passing freed memory in idxd_cdev_open() Smatch warns: drivers/dma/idxd/cdev.c:327: idxd_cdev_open() warn: 'sva' was already freed. When idxd_wq_set_pasid() fails, the current code unbinds sva and then goes to 'failed_set_pasid' where iommu_sva_unbind_device is called again causing the above warning. [ device_user_pasid_enabled(idxd) is still true when calling failed_set_pasid ] Fix this by removing additional unbind when idxd_wq_set_pasid() fails Fixes: b022f59725f0 ("dmaengine: idxd: add idxd_copy_cr() to copy user completion record during page fault handling") Signed-off-by: Harshit Mogalapalli Acked-by: Fenghua Yu Acked-by: Dave Jiang Link: https://lore.kernel.org/r/20230509060716.2830630-1-harshit.m.mogalapalli@oracle.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index ecbf67c2ad2b..d32deb9b4e3d 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -277,7 +277,6 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) if (wq_dedicated(wq)) { rc = idxd_wq_set_pasid(wq, pasid); if (rc < 0) { - iommu_sva_unbind_device(sva); dev_err(dev, "wq set pasid failed: %d\n", rc); goto failed_set_pasid; } -- GitLab From 38de368a66360f1859428d5e191b45bd01c20786 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 16 May 2023 23:13:11 +0530 Subject: [PATCH 5084/5631] dmaengine: ti: k3-udma: annotate pm function with __maybe_unused We get a warning when PM is not set: ../drivers/dma/ti/k3-udma.c:5552:12: warning: 'udma_pm_resume' defined but not used [-Wunused-function] 5552 | static int udma_pm_resume(struct device *dev) | ^~~~~~~~~~~~~~ ../drivers/dma/ti/k3-udma.c:5530:12: warning: 'udma_pm_suspend' defined but not used [-Wunused-function] 5530 | static int udma_pm_suspend(struct device *dev) | ^~~~~~~~~~~~~~~ Fix this by annotating pm function with __maybe_unused Fixes: fbe05149e40b ("dmaengine: ti: k3-udma: Add system suspend/resume support") Reported-by: Randy Dunlap Signed-off-by: Vinod Koul Acked-by: Randy Dunlap Tested-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/r/20230516174311.117264-1-vkoul@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/ti/k3-udma.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index fc3a2a05ab7b..b8329a23728d 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5527,7 +5527,7 @@ static int udma_probe(struct platform_device *pdev) return ret; } -static int udma_pm_suspend(struct device *dev) +static int __maybe_unused udma_pm_suspend(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; @@ -5549,7 +5549,7 @@ static int udma_pm_suspend(struct device *dev) return 0; } -static int udma_pm_resume(struct device *dev) +static int __maybe_unused udma_pm_resume(struct device *dev) { struct udma_dev *ud = dev_get_drvdata(dev); struct dma_device *dma_dev = &ud->ddev; -- GitLab From aed0e6ca7dbb8fbea9bc69c9ac663d5533c8c5d8 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:13 +0200 Subject: [PATCH 5085/5631] can: kvaser_pciefd: Set CAN_STATE_STOPPED in kvaser_pciefd_stop() Set can.state to CAN_STATE_STOPPED in kvaser_pciefd_stop(). Without this fix, wrong CAN state was repported after the interface was brought down. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-2-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 53e8a914c88b..867b421b9506 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -719,6 +719,7 @@ static int kvaser_pciefd_stop(struct net_device *netdev) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); del_timer(&can->bec_poll_timer); } + can->can.state = CAN_STATE_STOPPED; close_candev(netdev); return ret; -- GitLab From bf7ac55e991ca177f1ac16be51152f1ef291a4df Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:14 +0200 Subject: [PATCH 5086/5631] can: kvaser_pciefd: Clear listen-only bit if not explicitly requested The listen-only bit was never cleared, causing the controller to always use listen-only mode, if previously set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-3-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 867b421b9506..cdc894d12885 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -554,6 +554,8 @@ static void kvaser_pciefd_setup_controller(struct kvaser_pciefd_can *can) if (can->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) mode |= KVASER_PCIEFD_KCAN_MODE_LOM; + else + mode &= ~KVASER_PCIEFD_KCAN_MODE_LOM; mode |= KVASER_PCIEFD_KCAN_MODE_EEN; mode |= KVASER_PCIEFD_KCAN_MODE_EPEN; -- GitLab From 84762d8da89d29ba842317eb842973e628c27391 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:15 +0200 Subject: [PATCH 5087/5631] can: kvaser_pciefd: Call request_irq() before enabling interrupts Make sure the interrupt handler is registered before enabling interrupts. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-4-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index cdc894d12885..4b8591d48735 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1827,6 +1827,11 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, if (err) goto err_teardown_can_ctrls; + err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, + IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); + if (err) + goto err_teardown_can_ctrls; + iowrite32(KVASER_PCIEFD_SRB_IRQ_DPD0 | KVASER_PCIEFD_SRB_IRQ_DPD1, pcie->reg_base + KVASER_PCIEFD_SRB_IRQ_REG); @@ -1847,11 +1852,6 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); - err = request_irq(pcie->pci->irq, kvaser_pciefd_irq_handler, - IRQF_SHARED, KVASER_PCIEFD_DRV_NAME, pcie); - if (err) - goto err_teardown_can_ctrls; - err = kvaser_pciefd_reg_candev(pcie); if (err) goto err_free_irq; -- GitLab From c589557dd1426f5adf90c7a919d4fde5a3e4ef64 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:16 +0200 Subject: [PATCH 5088/5631] can: kvaser_pciefd: Empty SRB buffer in probe Empty the "Shared receive buffer" (SRB) in probe, to assure we start in a known state, and don't process any irrelevant packets. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-5-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 4b8591d48735..0e03c1cd47b3 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -71,10 +71,12 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SYSID_BUILD_REG (KVASER_PCIEFD_SYSID_BASE + 0x14) /* Shared receive buffer registers */ #define KVASER_PCIEFD_SRB_BASE 0x1f200 +#define KVASER_PCIEFD_SRB_FIFO_LAST_REG (KVASER_PCIEFD_SRB_BASE + 0x1f4) #define KVASER_PCIEFD_SRB_CMD_REG (KVASER_PCIEFD_SRB_BASE + 0x200) #define KVASER_PCIEFD_SRB_IEN_REG (KVASER_PCIEFD_SRB_BASE + 0x204) #define KVASER_PCIEFD_SRB_IRQ_REG (KVASER_PCIEFD_SRB_BASE + 0x20c) #define KVASER_PCIEFD_SRB_STAT_REG (KVASER_PCIEFD_SRB_BASE + 0x210) +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG (KVASER_PCIEFD_SRB_BASE + 0x214) #define KVASER_PCIEFD_SRB_CTRL_REG (KVASER_PCIEFD_SRB_BASE + 0x218) /* EPCS flash controller registers */ #define KVASER_PCIEFD_SPI_BASE 0x1fc00 @@ -111,6 +113,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* DMA support */ #define KVASER_PCIEFD_SRB_STAT_DMA BIT(24) +/* SRB current packet level */ +#define KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK 0xff + /* DMA Enable */ #define KVASER_PCIEFD_SRB_CTRL_DMA_ENABLE BIT(0) @@ -1061,6 +1066,7 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) { int i; u32 srb_status; + u32 srb_packet_count; dma_addr_t dma_addr[KVASER_PCIEFD_DMA_COUNT]; /* Disable the DMA */ @@ -1088,6 +1094,15 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie) KVASER_PCIEFD_SRB_CMD_RDB1, pcie->reg_base + KVASER_PCIEFD_SRB_CMD_REG); + /* Empty Rx FIFO */ + srb_packet_count = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_RX_NR_PACKETS_REG) & + KVASER_PCIEFD_SRB_RX_NR_PACKETS_MASK; + while (srb_packet_count) { + /* Drop current packet in FIFO */ + ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_FIFO_LAST_REG); + srb_packet_count--; + } + srb_status = ioread32(pcie->reg_base + KVASER_PCIEFD_SRB_STAT_REG); if (!(srb_status & KVASER_PCIEFD_SRB_STAT_DI)) { dev_err(&pcie->pci->dev, "DMA not idle before enabling\n"); -- GitLab From 262d7a52ba27525e3c1203230c9f0524e48bbb34 Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:17 +0200 Subject: [PATCH 5089/5631] can: kvaser_pciefd: Do not send EFLUSH command on TFD interrupt Under certain circumstances we send two EFLUSH commands, resulting in two EFLUSH ack packets, while only expecting a single EFLUSH ack. This can cause the driver Tx flush completion to get out of sync. To avoid this problem, don't enable the "Transmit buffer flush done" (TFD) interrupt and remove the code handling it. Now we only send EFLUSH command after receiving status packet with "Init detected" (IDET) bit set. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-6-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 0e03c1cd47b3..4fafb7658349 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -531,7 +531,7 @@ static int kvaser_pciefd_set_tx_irq(struct kvaser_pciefd_can *can) KVASER_PCIEFD_KCAN_IRQ_TOF | KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TAE | KVASER_PCIEFD_KCAN_IRQ_TAL | KVASER_PCIEFD_KCAN_IRQ_FDIC | KVASER_PCIEFD_KCAN_IRQ_BPP | - KVASER_PCIEFD_KCAN_IRQ_TAR | KVASER_PCIEFD_KCAN_IRQ_TFD; + KVASER_PCIEFD_KCAN_IRQ_TAR; iowrite32(msk, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); @@ -579,7 +579,7 @@ static void kvaser_pciefd_start_controller_flush(struct kvaser_pciefd_can *can) spin_lock_irqsave(&can->lock, irq); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); @@ -622,7 +622,7 @@ static int kvaser_pciefd_bus_on(struct kvaser_pciefd_can *can) iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); mode = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_MODE_REG); @@ -1015,8 +1015,7 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) SET_NETDEV_DEV(netdev, &pcie->pci->dev); iowrite32(-1, can->reg_base + KVASER_PCIEFD_KCAN_IRQ_REG); - iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD | - KVASER_PCIEFD_KCAN_IRQ_TFD, + iowrite32(KVASER_PCIEFD_KCAN_IRQ_ABD, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); pcie->can[i] = can; @@ -1443,9 +1442,6 @@ static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, cmd = KVASER_PCIEFD_KCAN_CMD_AT; cmd |= ++can->cmd_seq << KVASER_PCIEFD_KCAN_CMD_SEQ_SHIFT; iowrite32(cmd, can->reg_base + KVASER_PCIEFD_KCAN_CMD_REG); - - iowrite32(KVASER_PCIEFD_KCAN_IRQ_TFD, - can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG); } else if (p->header[0] & KVASER_PCIEFD_SPACK_IDET && p->header[0] & KVASER_PCIEFD_SPACK_IRM && cmdseq == (p->header[1] & KVASER_PCIEFD_PACKET_SEQ_MSK) && @@ -1732,15 +1728,6 @@ static int kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can) if (irq & KVASER_PCIEFD_KCAN_IRQ_TOF) netdev_err(can->can.dev, "Tx FIFO overflow\n"); - if (irq & KVASER_PCIEFD_KCAN_IRQ_TFD) { - u8 count = ioread32(can->reg_base + - KVASER_PCIEFD_KCAN_TX_NPACKETS_REG) & 0xff; - - if (count == 0) - iowrite32(KVASER_PCIEFD_KCAN_CTRL_EFLUSH, - can->reg_base + KVASER_PCIEFD_KCAN_CTRL_REG); - } - if (irq & KVASER_PCIEFD_KCAN_IRQ_BPP) netdev_err(can->can.dev, "Fail to change bittiming, when not in reset mode\n"); -- GitLab From 11164bc39459335ab93c6e99d53b7e4292fba38b Mon Sep 17 00:00:00 2001 From: Jimmy Assarsson Date: Tue, 16 May 2023 15:43:18 +0200 Subject: [PATCH 5090/5631] can: kvaser_pciefd: Disable interrupts in probe error path Disable interrupts in error path of probe function. Fixes: 26ad340e582d ("can: kvaser_pciefd: Add driver for Kvaser PCIEcan devices") Cc: stable@vger.kernel.org Signed-off-by: Jimmy Assarsson Link: https://lore.kernel.org/r/20230516134318.104279-7-extja@kvaser.com Signed-off-by: Marc Kleine-Budde --- drivers/net/can/kvaser_pciefd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 4fafb7658349..be189edb256c 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -1861,6 +1861,8 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev, return 0; err_free_irq: + /* Disable PCI interrupts */ + iowrite32(0, pcie->reg_base + KVASER_PCIEFD_IEN_REG); free_irq(pcie->pci->irq, pcie); err_teardown_can_ctrls: -- GitLab From 82b2bc279467c875ec36f8ef820f00997c2a4e8e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 15 May 2023 11:42:04 -0700 Subject: [PATCH 5091/5631] tun: Fix memory leak for detached NAPI queue. syzkaller reported [0] memory leaks of sk and skb related to the TUN device with no repro, but we can reproduce it easily with: struct ifreq ifr = {} int fd_tun, fd_tmp; char buf[4] = {}; fd_tun = openat(AT_FDCWD, "/dev/net/tun", O_WRONLY, 0); ifr.ifr_flags = IFF_TUN | IFF_NAPI | IFF_MULTI_QUEUE; ioctl(fd_tun, TUNSETIFF, &ifr); ifr.ifr_flags = IFF_DETACH_QUEUE; ioctl(fd_tun, TUNSETQUEUE, &ifr); fd_tmp = socket(AF_PACKET, SOCK_PACKET, 0); ifr.ifr_flags = IFF_UP; ioctl(fd_tmp, SIOCSIFFLAGS, &ifr); write(fd_tun, buf, sizeof(buf)); close(fd_tun); If we enable NAPI and multi-queue on a TUN device, we can put skb into tfile->sk.sk_write_queue after the queue is detached. We should prevent it by checking tfile->detached before queuing skb. Note this must be done under tfile->sk.sk_write_queue.lock because write() and ioctl(IFF_DETACH_QUEUE) can run concurrently. Otherwise, there would be a small race window: write() ioctl(IFF_DETACH_QUEUE) `- tun_get_user `- __tun_detach |- if (tfile->detached) |- tun_disable_queue | `-> false | `- tfile->detached = tun | `- tun_queue_purge |- spin_lock_bh(&queue->lock) `- __skb_queue_tail(queue, skb) Another solution is to call tun_queue_purge() when closing and reattaching the detached queue, but it could paper over another problems. Also, we do the same kind of test for IFF_NAPI_FRAGS. [0]: unreferenced object 0xffff88801edbc800 (size 2048): comm "syz-executor.1", pid 33269, jiffies 4295743834 (age 18.756s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00 ...@............ backtrace: [<000000008c16ea3d>] __do_kmalloc_node mm/slab_common.c:965 [inline] [<000000008c16ea3d>] __kmalloc+0x4a/0x130 mm/slab_common.c:979 [<000000003addde56>] kmalloc include/linux/slab.h:563 [inline] [<000000003addde56>] sk_prot_alloc+0xef/0x1b0 net/core/sock.c:2035 [<000000003e20621f>] sk_alloc+0x36/0x2f0 net/core/sock.c:2088 [<0000000028e43843>] tun_chr_open+0x3d/0x190 drivers/net/tun.c:3438 [<000000001b0f1f28>] misc_open+0x1a6/0x1f0 drivers/char/misc.c:165 [<000000004376f706>] chrdev_open+0x111/0x300 fs/char_dev.c:414 [<00000000614d379f>] do_dentry_open+0x2f9/0x750 fs/open.c:920 [<000000008eb24774>] do_open fs/namei.c:3636 [inline] [<000000008eb24774>] path_openat+0x143f/0x1a30 fs/namei.c:3791 [<00000000955077b5>] do_filp_open+0xce/0x1c0 fs/namei.c:3818 [<00000000b78973b0>] do_sys_openat2+0xf0/0x260 fs/open.c:1356 [<00000000057be699>] do_sys_open fs/open.c:1372 [inline] [<00000000057be699>] __do_sys_openat fs/open.c:1388 [inline] [<00000000057be699>] __se_sys_openat fs/open.c:1383 [inline] [<00000000057be699>] __x64_sys_openat+0x83/0xf0 fs/open.c:1383 [<00000000a7d2182d>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000a7d2182d>] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 [<000000004cc4e8c4>] entry_SYSCALL_64_after_hwframe+0x72/0xdc unreferenced object 0xffff88802f671700 (size 240): comm "syz-executor.1", pid 33269, jiffies 4295743854 (age 18.736s) hex dump (first 32 bytes): 68 c9 db 1e 80 88 ff ff 68 c9 db 1e 80 88 ff ff h.......h....... 00 c0 7b 2f 80 88 ff ff 00 c8 db 1e 80 88 ff ff ..{/............ backtrace: [<00000000e9d9fdb6>] __alloc_skb+0x223/0x250 net/core/skbuff.c:644 [<000000002c3e4e0b>] alloc_skb include/linux/skbuff.h:1288 [inline] [<000000002c3e4e0b>] alloc_skb_with_frags+0x6f/0x350 net/core/skbuff.c:6378 [<00000000825f98d7>] sock_alloc_send_pskb+0x3ac/0x3e0 net/core/sock.c:2729 [<00000000e9eb3df3>] tun_alloc_skb drivers/net/tun.c:1529 [inline] [<00000000e9eb3df3>] tun_get_user+0x5e1/0x1f90 drivers/net/tun.c:1841 [<0000000053096912>] tun_chr_write_iter+0xac/0x120 drivers/net/tun.c:2035 [<00000000b9282ae0>] call_write_iter include/linux/fs.h:1868 [inline] [<00000000b9282ae0>] new_sync_write fs/read_write.c:491 [inline] [<00000000b9282ae0>] vfs_write+0x40f/0x530 fs/read_write.c:584 [<00000000524566e4>] ksys_write+0xa1/0x170 fs/read_write.c:637 [<00000000a7d2182d>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<00000000a7d2182d>] do_syscall_64+0x3c/0x90 arch/x86/entry/common.c:80 [<000000004cc4e8c4>] entry_SYSCALL_64_after_hwframe+0x72/0xdc Fixes: cde8b15f1aab ("tuntap: add ioctl to attach or detach a file form tuntap device") Reported-by: syzkaller Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- drivers/net/tun.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index d4d0a41a905a..d75456adc62a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1977,6 +1977,14 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, int queue_len; spin_lock_bh(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock_bh(&queue->lock); + rcu_read_unlock(); + err = -EBUSY; + goto free_skb; + } + __skb_queue_tail(queue, skb); queue_len = skb_queue_len(queue); spin_unlock(&queue->lock); @@ -2512,6 +2520,13 @@ static int tun_xdp_one(struct tun_struct *tun, if (tfile->napi_enabled) { queue = &tfile->sk.sk_write_queue; spin_lock(&queue->lock); + + if (unlikely(tfile->detached)) { + spin_unlock(&queue->lock); + kfree_skb(skb); + return -EBUSY; + } + __skb_queue_tail(queue, skb); spin_unlock(&queue->lock); ret = 1; -- GitLab From 412cd77a2c24b191c65ea53025222418db09817c Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Mon, 15 May 2023 21:09:11 +0200 Subject: [PATCH 5092/5631] cassini: Fix a memory leak in the error handling path of cas_init_one() cas_saturn_firmware_init() allocates some memory using vmalloc(). This memory is freed in the .remove() function but not it the error handling path of the probe. Add the missing vfree() to avoid a memory leak, should an error occur. Fixes: fcaa40669cd7 ("cassini: use request_firmware") Signed-off-by: Christophe JAILLET Reviewed-by: Pavan Chebbi Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/ethernet/sun/cassini.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 4ef05bad4613..d61dfa250feb 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -5077,6 +5077,8 @@ static int cas_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) cas_shutdown(cp); mutex_unlock(&cp->pm_mutex); + vfree(cp->fw_data); + pci_iounmap(pdev, cp->regs); -- GitLab From 1323e0c6e1d7e103d59384c3ac50f72b17a6936c Mon Sep 17 00:00:00 2001 From: Marco Migliore Date: Tue, 16 May 2023 09:38:54 +0200 Subject: [PATCH 5093/5631] net: dsa: mv88e6xxx: Fix mv88e6393x EPC write command offset According to datasheet, the command opcode must be specified into bits [14:12] of the Extended Port Control register (EPC). Fixes: de776d0d316f ("net: dsa: mv88e6xxx: add support for mv88e6393x family") Signed-off-by: Marco Migliore Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/port.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index aec9d4fd20e3..d19b6303b91f 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -276,7 +276,7 @@ /* Offset 0x10: Extended Port Control Command */ #define MV88E6393X_PORT_EPC_CMD 0x10 #define MV88E6393X_PORT_EPC_CMD_BUSY 0x8000 -#define MV88E6393X_PORT_EPC_CMD_WRITE 0x0300 +#define MV88E6393X_PORT_EPC_CMD_WRITE 0x3000 #define MV88E6393X_PORT_EPC_INDEX_PORT_ETYPE 0x02 /* Offset 0x11: Extended Port Control Data */ -- GitLab From 60d758659f1fb49e0d5b6ac2691ede8c0958795b Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Tue, 16 May 2023 10:41:46 -0700 Subject: [PATCH 5094/5631] igb: fix bit_shift to be in [1..8] range In igb_hash_mc_addr() the expression: "mc_addr[4] >> 8 - bit_shift", right shifting "mc_addr[4]" shift by more than 7 bits always yields zero, so hash becomes not so different. Add initialization with bit_shift = 1 and add a loop condition to ensure bit_shift will be always in [1..8] range. Fixes: 9d5c824399de ("igb: PCI-Express 82575 Gigabit Ethernet driver") Signed-off-by: Aleksandr Loktionov Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/igb/e1000_mac.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 205d577bdbba..caf91c6f52b4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table -- GitLab From 66353baf3762fa0968b4424a2075fb395b329e9d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 16 May 2023 11:48:49 +0300 Subject: [PATCH 5095/5631] mailmap: add entries for Nikolay Aleksandrov Turns out I missed a few patches due to use of old addresses by senders. Add a mailmap entry with my old addresses. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- .mailmap | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/.mailmap b/.mailmap index 71127b2608d2..bf076bbc36b1 100644 --- a/.mailmap +++ b/.mailmap @@ -364,6 +364,11 @@ Nicolas Pitre Nicolas Saenz Julienne Nicolas Saenz Julienne Niklas Söderlund +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov +Nikolay Aleksandrov Oleksandr Natalenko Oleksij Rempel Oleksij Rempel -- GitLab From 0a1bb16e0fe6650c3841e611de374bfd5578ad70 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Tue, 16 May 2023 22:47:56 -0700 Subject: [PATCH 5096/5631] gpio: mockup: Fix mode of debugfs files This driver's debugfs files have had a read operation since commit 2a9e27408e12 ("gpio: mockup: rework debugfs interface"), but were still being created with write-only mode bits. Update them to indicate that the files can also be read. Signed-off-by: Zev Weiss Fixes: 2a9e27408e12 ("gpio: mockup: rework debugfs interface") Cc: stable@kernel.org # v5.1+ Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-mockup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index e6a7049bef64..b32063ac845a 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -369,7 +369,7 @@ static void gpio_mockup_debugfs_setup(struct device *dev, priv->offset = i; priv->desc = gpiochip_get_desc(gc, i); - debugfs_create_file(name, 0200, chip->dbg_dir, priv, + debugfs_create_file(name, 0600, chip->dbg_dir, priv, &gpio_mockup_debugfs_ops); } } -- GitLab From 1aa7f416175619e0286fddc5fc44e968b06bf2aa Mon Sep 17 00:00:00 2001 From: Maya Matuszczyk Date: Mon, 15 May 2023 20:48:43 +0200 Subject: [PATCH 5097/5631] drm: panel-orientation-quirks: Change Air's quirk to support Air Plus It turned out that Aya Neo Air Plus had a different board name than expected. This patch changes Aya Neo Air's quirk to account for that, as both devices share "Air" in DMI product name. Tested on Air claiming to be an Air Pro, and on Air Plus. Signed-off-by: Maya Matuszczyk Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20230515184843.1552612-1-maccraft123mc@gmail.com --- drivers/gpu/drm/drm_panel_orientation_quirks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index b1a38e6ce2f8..0cb646cb04ee 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -179,7 +179,7 @@ static const struct dmi_system_id orientation_data[] = { }, { /* AYA NEO AIR */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYANEO"), - DMI_MATCH(DMI_BOARD_NAME, "AIR"), + DMI_MATCH(DMI_PRODUCT_NAME, "AIR"), }, .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* AYA NEO NEXT */ -- GitLab From 7dd3d9bd873f138675cb727eaa51a498d99f0e89 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Thu, 4 May 2023 08:04:21 +0200 Subject: [PATCH 5098/5631] gpiolib: fix allocation of mixed dynamic/static GPIOs If static allocation and dynamic allocation GPIOs are present, dynamic allocation pollutes the numberspace for static allocation, causing static allocation to fail. Enforce dynamic allocation above GPIO_DYNAMIC_BASE. Seen on a GTA04 when omap-gpio (static) and twl-gpio (dynamic) raced: [some successful registrations of omap_gpio instances] [ 2.553833] twl4030_gpio twl4030-gpio: gpio (irq 145) chaining IRQs 161..178 [ 2.561401] gpiochip_find_base: found new base at 160 [ 2.564392] gpio gpiochip5: (twl4030): added GPIO chardev (254:5) [ 2.564544] gpio gpiochip5: registered GPIOs 160 to 177 on twl4030 [...] [ 2.692169] omap-gpmc 6e000000.gpmc: GPMC revision 5.0 [ 2.697357] gpmc_mem_init: disabling cs 0 mapped at 0x0-0x1000000 [ 2.703643] gpiochip_find_base: found new base at 178 [ 2.704376] gpio gpiochip6: (omap-gpmc): added GPIO chardev (254:6) [ 2.704589] gpio gpiochip6: registered GPIOs 178 to 181 on omap-gpmc [...] [ 2.840393] gpio gpiochip7: Static allocation of GPIO base is deprecated, use dynamic allocation. [ 2.849365] gpio gpiochip7: (gpio-160-191): GPIO integer space overlap, cannot add chip [ 2.857513] gpiochip_add_data_with_key: GPIOs 160..191 (gpio-160-191) failed to register, -16 [ 2.866149] omap_gpio 48310000.gpio: error -EBUSY: Could not register gpio chip On that device it is fixed invasively by commit 92bf78b33b0b4 ("gpio: omap: use dynamic allocation of base") but let's also fix that for devices where there is still a mixture of static and dynamic allocation. Fixes: 7b61212f2a07 ("gpiolib: Get rid of ARCH_NR_GPIOS") Signed-off-by: Andreas Kemnade Reviewed-by: Reviewed-by: Andy Shevchenko Reviewed-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpiolib.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 04fb05df805b..a7220e04a93e 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -209,6 +209,8 @@ static int gpiochip_find_base(int ngpio) break; /* nope, check the space right after the chip */ base = gdev->base + gdev->ngpio; + if (base < GPIO_DYNAMIC_BASE) + base = GPIO_DYNAMIC_BASE; } if (gpio_is_valid(base)) { -- GitLab From 7561551e7ba870b9659083b95feb520fb2dacce3 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 13 Apr 2023 13:57:17 +0800 Subject: [PATCH 5099/5631] btrfs: scrub: try harder to mark RAID56 block groups read-only Currently we allow a block group not to be marked read-only for scrub. But for RAID56 block groups if we require the block group to be read-only, then we're allowed to use cached content from scrub stripe to reduce unnecessary RAID56 reads. So this patch would: - Make btrfs_inc_block_group_ro() try harder During my tests, for cases like btrfs/061 and btrfs/064, we can hit ENOSPC from btrfs_inc_block_group_ro() calls during scrub. The reason is if we only have one single data chunk, and trying to scrub it, we won't have any space left for any newer data writes. But this check should be done by the caller, especially for scrub cases we only temporarily mark the chunk read-only. And newer data writes would always try to allocate a new data chunk when needed. - Return error for scrub if we failed to mark a RAID56 chunk read-only Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 14 ++++++++++++-- fs/btrfs/scrub.c | 9 ++++++++- 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 957ad1c31c4f..590b03560265 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2818,10 +2818,20 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, } ret = inc_block_group_ro(cache, 0); - if (!do_chunk_alloc || ret == -ETXTBSY) - goto unlock_out; if (!ret) goto out; + if (ret == -ETXTBSY) + goto unlock_out; + + /* + * Skip chunk alloction if the bg is SYSTEM, this is to avoid system + * chunk allocation storm to exhaust the system chunk array. Otherwise + * we still want to try our best to mark the block group read-only. + */ + if (!do_chunk_alloc && ret == -ENOSPC && + (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM)) + goto unlock_out; + alloc_flags = btrfs_get_alloc_profile(fs_info, cache->space_info->flags); ret = btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); if (ret < 0) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 836725a19661..dd37cba58022 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2518,13 +2518,20 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (ret == 0) { ro_set = 1; - } else if (ret == -ENOSPC && !sctx->is_dev_replace) { + } else if (ret == -ENOSPC && !sctx->is_dev_replace && + !(cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK)) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. + * + * For RAID56 chunks, we have to mark them read-only + * for scrub, as later we would use our own cache + * out of RAID56 realm. + * Thus we want the RAID56 bg to be marked RO to + * prevent RMW from screwing up out cache. */ ro_set = 0; } else if (ret == -ETXTBSY) { -- GitLab From 806570c0bb7b4847828c22c4934fcf2dc8fc572f Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 4 May 2023 13:58:13 +0200 Subject: [PATCH 5100/5631] btrfs: handle memory allocation failure in btrfs_csum_one_bio Since f8a53bb58ec7 ("btrfs: handle checksum generation in the storage layer") the failures of btrfs_csum_one_bio() are handled via bio_end_io(). This means, we can return BLK_STS_RESOURCE from btrfs_csum_one_bio() in case the allocation of the ordered sums fails. This also fixes a syzkaller report, where injecting a failure into the kvzalloc() call results in a BUG_ON(). Reported-by: syzbot+d8941552e21eac774778@syzkaller.appspotmail.com Reviewed-by: Christoph Hellwig Reviewed-by: Anand Jain Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/file-item.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index cd4cce9ba443..d1cd0a692f8e 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -792,7 +792,9 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_bio *bbio) sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); - BUG_ON(!sums); /* -ENOMEM */ + if (!sums) + return BLK_STS_RESOURCE; + sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, offset); -- GitLab From 597441b3436a43011f31ce71dc0a6c0bf5ce958a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 11 May 2023 12:45:59 -0400 Subject: [PATCH 5101/5631] btrfs: use nofs when cleaning up aborted transactions Our CI system caught a lockdep splat: ====================================================== WARNING: possible circular locking dependency detected 6.3.0-rc7+ #1167 Not tainted ------------------------------------------------------ kswapd0/46 is trying to acquire lock: ffff8c6543abd650 (sb_internal#2){++++}-{0:0}, at: btrfs_commit_inode_delayed_inode+0x5f/0x120 but task is already holding lock: ffffffffabe61b40 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x4aa/0x7a0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (fs_reclaim){+.+.}-{0:0}: fs_reclaim_acquire+0xa5/0xe0 kmem_cache_alloc+0x31/0x2c0 alloc_extent_state+0x1d/0xd0 __clear_extent_bit+0x2e0/0x4f0 try_release_extent_mapping+0x216/0x280 btrfs_release_folio+0x2e/0x90 invalidate_inode_pages2_range+0x397/0x470 btrfs_cleanup_dirty_bgs+0x9e/0x210 btrfs_cleanup_one_transaction+0x22/0x760 btrfs_commit_transaction+0x3b7/0x13a0 create_subvol+0x59b/0x970 btrfs_mksubvol+0x435/0x4f0 __btrfs_ioctl_snap_create+0x11e/0x1b0 btrfs_ioctl_snap_create_v2+0xbf/0x140 btrfs_ioctl+0xa45/0x28f0 __x64_sys_ioctl+0x88/0xc0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc -> #0 (sb_internal#2){++++}-{0:0}: __lock_acquire+0x1435/0x21a0 lock_acquire+0xc2/0x2b0 start_transaction+0x401/0x730 btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_evict_inode+0x292/0x3d0 evict+0xcc/0x1d0 inode_lru_isolate+0x14d/0x1e0 __list_lru_walk_one+0xbe/0x1c0 list_lru_walk_one+0x58/0x80 prune_icache_sb+0x39/0x60 super_cache_scan+0x161/0x1f0 do_shrink_slab+0x163/0x340 shrink_slab+0x1d3/0x290 shrink_node+0x300/0x720 balance_pgdat+0x35c/0x7a0 kswapd+0x205/0x410 kthread+0xf0/0x120 ret_from_fork+0x29/0x50 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(fs_reclaim); lock(sb_internal#2); lock(fs_reclaim); lock(sb_internal#2); *** DEADLOCK *** 3 locks held by kswapd0/46: #0: ffffffffabe61b40 (fs_reclaim){+.+.}-{0:0}, at: balance_pgdat+0x4aa/0x7a0 #1: ffffffffabe50270 (shrinker_rwsem){++++}-{3:3}, at: shrink_slab+0x113/0x290 #2: ffff8c6543abd0e0 (&type->s_umount_key#44){++++}-{3:3}, at: super_cache_scan+0x38/0x1f0 stack backtrace: CPU: 0 PID: 46 Comm: kswapd0 Not tainted 6.3.0-rc7+ #1167 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 Call Trace: dump_stack_lvl+0x58/0x90 check_noncircular+0xd6/0x100 ? save_trace+0x3f/0x310 ? add_lock_to_list+0x97/0x120 __lock_acquire+0x1435/0x21a0 lock_acquire+0xc2/0x2b0 ? btrfs_commit_inode_delayed_inode+0x5f/0x120 start_transaction+0x401/0x730 ? btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_commit_inode_delayed_inode+0x5f/0x120 btrfs_evict_inode+0x292/0x3d0 ? lock_release+0x134/0x270 ? __pfx_wake_bit_function+0x10/0x10 evict+0xcc/0x1d0 inode_lru_isolate+0x14d/0x1e0 __list_lru_walk_one+0xbe/0x1c0 ? __pfx_inode_lru_isolate+0x10/0x10 ? __pfx_inode_lru_isolate+0x10/0x10 list_lru_walk_one+0x58/0x80 prune_icache_sb+0x39/0x60 super_cache_scan+0x161/0x1f0 do_shrink_slab+0x163/0x340 shrink_slab+0x1d3/0x290 shrink_node+0x300/0x720 balance_pgdat+0x35c/0x7a0 kswapd+0x205/0x410 ? __pfx_autoremove_wake_function+0x10/0x10 ? __pfx_kswapd+0x10/0x10 kthread+0xf0/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x29/0x50 This happens because when we abort the transaction in the transaction commit path we call invalidate_inode_pages2_range on our block group cache inodes (if we have space cache v1) and any delalloc inodes we may have. The plain invalidate_inode_pages2_range() call passes through GFP_KERNEL, which makes sense in most cases, but not here. Wrap these two invalidate callees with memalloc_nofs_save/memalloc_nofs_restore to make sure we don't end up with the fs reclaim dependency under the transaction dependency. CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/disk-io.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index fbf9006c6234..6de6dcf2743e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4936,7 +4936,11 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) */ inode = igrab(&btrfs_inode->vfs_inode); if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); iput(inode); } spin_lock(&root->delalloc_lock); @@ -5042,7 +5046,12 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache) inode = cache->io_ctl.inode; if (inode) { + unsigned int nofs_flag; + + nofs_flag = memalloc_nofs_save(); invalidate_inode_pages2(inode->i_mapping); + memalloc_nofs_restore(nofs_flag); + BTRFS_I(inode)->generation = 0; cache->io_ctl.inode = NULL; iput(inode); -- GitLab From 6049674b5720edbbb13a7cb3e2f3d2affaa40c19 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Sun, 9 Apr 2023 11:28:31 +0900 Subject: [PATCH 5102/5631] tracing: fprobe: Initialize ret valiable to fix smatch error The commit 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns !0") introduced a hidden dependency of 'ret' local variable in the fprobe_handler(), Smatch warns the `ret` can be accessed without initialization. kernel/trace/fprobe.c:59 fprobe_handler() error: uninitialized symbol 'ret'. kernel/trace/fprobe.c 49 fpr->entry_ip = ip; 50 if (fp->entry_data_size) 51 entry_data = fpr->data; 52 } 53 54 if (fp->entry_handler) 55 ret = fp->entry_handler(fp, ip, ftrace_get_regs(fregs), entry_data); ret is only initialized if there is an ->entry_handler 56 57 /* If entry_handler returns !0, nmissed is not counted. */ 58 if (rh) { rh is only true if there is an ->exit_handler. Presumably if you have and ->exit_handler that means you also have a ->entry_handler but Smatch is not smart enough to figure it out. --> 59 if (ret) ^^^ Warning here. 60 rethook_recycle(rh); 61 else 62 rethook_hook(rh, ftrace_get_regs(fregs), true); 63 } 64 out: 65 ftrace_test_recursion_unlock(bit); 66 } Link: https://lore.kernel.org/all/168100731160.79534.374827110083836722.stgit@devnote2/ Reported-by: Dan Carpenter Link: https://lore.kernel.org/all/85429a5c-a4b9-499e-b6c0-cbd313291c49@kili.mountain Fixes: 39d954200bf6 ("fprobe: Skip exit_handler if entry_handler returns !0") Acked-by: Dan Carpenter Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 9abb3905bc8e..293184227394 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -27,7 +27,7 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret; + int bit, ret = 0; fp = container_of(ops, struct fprobe, ops); if (fprobe_disabled(fp)) -- GitLab From dacab578c7c6cd06c50c89dfa36b0e0f10decd4e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2023 14:23:42 +0000 Subject: [PATCH 5103/5631] vlan: fix a potential uninit-value in vlan_dev_hard_start_xmit() syzbot triggered the following splat [1], sending an empty message through pppoe_sendmsg(). When VLAN_FLAG_REORDER_HDR flag is set, vlan_dev_hard_header() does not push extra bytes for the VLAN header, because vlan is offloaded. Unfortunately vlan_dev_hard_start_xmit() first reads veth->h_vlan_proto before testing (vlan->flags & VLAN_FLAG_REORDER_HDR). We need to swap the two conditions. [1] BUG: KMSAN: uninit-value in vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 vlan_dev_hard_start_xmit+0x171/0x7f0 net/8021q/vlan_dev.c:111 __netdev_start_xmit include/linux/netdevice.h:4883 [inline] netdev_start_xmit include/linux/netdevice.h:4897 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x253/0xa20 net/core/dev.c:3596 __dev_queue_xmit+0x3c7f/0x5ac0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3053 [inline] pppoe_sendmsg+0xa93/0xb80 drivers/net/ppp/pppoe.c:900 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Uninit was created at: slab_post_alloc_hook+0x12d/0xb60 mm/slab.h:774 slab_alloc_node mm/slub.c:3452 [inline] kmem_cache_alloc_node+0x543/0xab0 mm/slub.c:3497 kmalloc_reserve+0x148/0x470 net/core/skbuff.c:520 __alloc_skb+0x3a7/0x850 net/core/skbuff.c:606 alloc_skb include/linux/skbuff.h:1277 [inline] sock_wmalloc+0xfe/0x1a0 net/core/sock.c:2583 pppoe_sendmsg+0x3af/0xb80 drivers/net/ppp/pppoe.c:867 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0xa24/0xe40 net/socket.c:2501 ___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2555 __sys_sendmmsg+0x411/0xa50 net/socket.c:2641 __do_sys_sendmmsg net/socket.c:2670 [inline] __se_sys_sendmmsg net/socket.c:2667 [inline] __x64_sys_sendmmsg+0xbc/0x120 net/socket.c:2667 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd CPU: 0 PID: 29770 Comm: syz-executor.0 Not tainted 6.3.0-rc6-syzkaller-gc478e5b17829 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/30/2023 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/8021q/vlan_dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 870e4935d6e6..b90781b9ece6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -109,8 +109,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); -- GitLab From 60829145f1e2650b31ebe6a0ec70a9725b38fa2c Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Tue, 16 May 2023 21:09:46 +0530 Subject: [PATCH 5104/5631] net: wwan: iosm: fix NULL pointer dereference when removing device In suspend and resume cycle, the removal and rescan of device ends up in NULL pointer dereference. During driver initialization, if the ipc_imem_wwan_channel_init() fails to get the valid device capabilities it returns an error and further no resource (wwan struct) will be allocated. Now in this situation if driver removal procedure is initiated it would result in NULL pointer exception since unallocated wwan struct is dereferenced inside ipc_wwan_deinit(). ipc_imem_run_state_worker() to handle the called functions return value and to release the resource in failure case. It also reports the link down event in failure cases. The user space application can handle this event to do a device reset for restoring the device communication. Fixes: 3670970dd8c6 ("net: iosm: shared memory IPC interface") Reported-by: Samuel Wein PhD Closes: https://lore.kernel.org/netdev/20230427140819.1310f4bd@kernel.org/T/ Signed-off-by: M Chetan Kumar Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_imem.c | 27 ++++++++++++++++++----- drivers/net/wwan/iosm/iosm_ipc_imem_ops.c | 12 ++++++---- drivers/net/wwan/iosm/iosm_ipc_imem_ops.h | 6 +++-- 3 files changed, 33 insertions(+), 12 deletions(-) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index c066b0040a3f..829515a601b3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -565,24 +565,32 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) struct ipc_mux_config mux_cfg; struct iosm_imem *ipc_imem; u8 ctrl_chl_idx = 0; + int ret; ipc_imem = container_of(instance, struct iosm_imem, run_state_worker); if (ipc_imem->phase != IPC_P_RUN) { dev_err(ipc_imem->dev, "Modem link down. Exit run state worker."); - return; + goto err_out; } if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) ipc_devlink_deinit(ipc_imem->ipc_devlink); - if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) - ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + ret = ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg); + if (ret < 0) + goto err_out; + + ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + if (!ipc_imem->mux) + goto err_out; + + ret = ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); + if (ret < 0) + goto err_ipc_mux_deinit; - ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); - if (ipc_imem->mux) - ipc_imem->mux->wwan = ipc_imem->wwan; + ipc_imem->mux->wwan = ipc_imem->wwan; while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { @@ -622,6 +630,13 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) /* Complete all memory stores after setting bit */ smp_mb__after_atomic(); + + return; + +err_ipc_mux_deinit: + ipc_mux_deinit(ipc_imem->mux); +err_out: + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN); } static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 66b90cc4c346..109cf8930488 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -77,8 +77,8 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, } /* Initialize wwan channel */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type) +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type) { struct ipc_chnl_cfg chnl_cfg = { 0 }; @@ -87,7 +87,7 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* If modem version is invalid (0xffffffff), do not initialize WWAN. */ if (ipc_imem->cp_version == -1) { dev_err(ipc_imem->dev, "invalid CP version"); - return; + return -EIO; } ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); @@ -104,9 +104,13 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, /* WWAN registration. */ ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev); - if (!ipc_imem->wwan) + if (!ipc_imem->wwan) { dev_err(ipc_imem->dev, "failed to register the ipc_wwan interfaces"); + return -ENOMEM; + } + + return 0; } /* Map SKB to DMA for transfer */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index f8afb217d9e2..026c5bd0f999 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -91,9 +91,11 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, * MUX. * @ipc_imem: Pointer to iosm_imem struct. * @mux_type: Type of mux protocol. + * + * Return: 0 on success and failure value on error */ -void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, - enum ipc_mux_protocol mux_type); +int ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type); /** * ipc_imem_sys_devlink_open - Open a Flash/CD Channel link to CP -- GitLab From c46e78ba9a7a09da4f192dc8df15c4e8a07fb9e0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 16 May 2023 18:44:10 +0300 Subject: [PATCH 5105/5631] net: pcs: xpcs: fix C73 AN not getting enabled The XPCS expects clause 73 (copper backplane) autoneg to follow the ethtool autoneg bit. It actually did that until the blamed commit inaptly replaced state->an_enabled (coming from ethtool) with phylink_autoneg_inband() (coming from the device tree or struct phylink_config), as part of an unrelated phylink_pcs API conversion. Russell King suggests that state->an_enabled from the original code was just a proxy for the ethtool Autoneg bit, and that the correct way of restoring the functionality is to check for this bit in the advertising mask. Fixes: 11059740e616 ("net: pcs: xpcs: convert to phylink_pcs_ops") Link: https://lore.kernel.org/netdev/ZGNt2MFeRolKGFck@shell.armlinux.org.uk/ Suggested-by: Russell King (Oracle) Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/pcs/pcs-xpcs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index f19d48c94fe0..72f25e778840 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -873,7 +873,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, switch (compat->an_mode) { case DW_AN_C73: - if (phylink_autoneg_inband(mode)) { + if (test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, advertising)) { ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; -- GitLab From 9ba9485b87ac97fd159abdb4cbd53099bc9f01c6 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Tue, 16 May 2023 14:49:24 -0400 Subject: [PATCH 5106/5631] net: selftests: Fix optstring The cited commit added a stray colon to the 'v' option. That makes the option work incorrectly. ex: tools/testing/selftests/net# ./fib_nexthops.sh -v (should enable verbose mode, instead it shows help text due to missing arg) Fixes: 5feba4727395 ("selftests: fib_nexthops: Make ping timeout configurable") Reviewed-by: Ido Schimmel Signed-off-by: Benjamin Poirier Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_nexthops.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index a47b26ab48f2..0f5e88c8f4ff 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2283,7 +2283,7 @@ EOF ################################################################################ # main -while getopts :t:pP46hv:w: o +while getopts :t:pP46hvw: o do case $o in t) TESTS=$OPTARG;; -- GitLab From ab87603b251134441a67385ecc9d3371be17b7a7 Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Wed, 17 May 2023 13:24:51 +0800 Subject: [PATCH 5107/5631] net: wwan: t7xx: Ensure init is completed before system sleep When the system attempts to sleep while mtk_t7xx is not ready, the driver cannot put the device to sleep: [ 12.472918] mtk_t7xx 0000:57:00.0: [PM] Exiting suspend, modem in invalid state [ 12.472936] mtk_t7xx 0000:57:00.0: PM: pci_pm_suspend(): t7xx_pci_pm_suspend+0x0/0x20 [mtk_t7xx] returns -14 [ 12.473678] mtk_t7xx 0000:57:00.0: PM: dpm_run_callback(): pci_pm_suspend+0x0/0x1b0 returns -14 [ 12.473711] mtk_t7xx 0000:57:00.0: PM: failed to suspend async: error -14 [ 12.764776] PM: Some devices failed to suspend, or early wake event detected Mediatek confirmed the device can take a rather long time to complete its initialization, so wait for up to 20 seconds until init is done. Signed-off-by: Kai-Heng Feng Signed-off-by: David S. Miller --- drivers/net/wwan/t7xx/t7xx_pci.c | 18 ++++++++++++++++++ drivers/net/wwan/t7xx/t7xx_pci.h | 1 + 2 files changed, 19 insertions(+) diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 226fc1703e90..91256e005b84 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -45,6 +45,7 @@ #define T7XX_PCI_IREG_BASE 0 #define T7XX_PCI_EREG_BASE 2 +#define T7XX_INIT_TIMEOUT 20 #define PM_SLEEP_DIS_TIMEOUT_MS 20 #define PM_ACK_TIMEOUT_MS 1500 #define PM_AUTOSUSPEND_MS 20000 @@ -96,6 +97,7 @@ static int t7xx_pci_pm_init(struct t7xx_pci_dev *t7xx_dev) spin_lock_init(&t7xx_dev->md_pm_lock); init_completion(&t7xx_dev->sleep_lock_acquire); init_completion(&t7xx_dev->pm_sr_ack); + init_completion(&t7xx_dev->init_done); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_INIT); device_init_wakeup(&pdev->dev, true); @@ -124,6 +126,7 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + complete_all(&t7xx_dev->init_done); } static int t7xx_pci_pm_reinit(struct t7xx_pci_dev *t7xx_dev) @@ -529,6 +532,20 @@ static void t7xx_pci_shutdown(struct pci_dev *pdev) __t7xx_pci_pm_suspend(pdev); } +static int t7xx_pci_pm_prepare(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct t7xx_pci_dev *t7xx_dev; + + t7xx_dev = pci_get_drvdata(pdev); + if (!wait_for_completion_timeout(&t7xx_dev->init_done, T7XX_INIT_TIMEOUT * HZ)) { + dev_warn(dev, "Not ready for system sleep.\n"); + return -ETIMEDOUT; + } + + return 0; +} + static int t7xx_pci_pm_suspend(struct device *dev) { return __t7xx_pci_pm_suspend(to_pci_dev(dev)); @@ -555,6 +572,7 @@ static int t7xx_pci_pm_runtime_resume(struct device *dev) } static const struct dev_pm_ops t7xx_pci_pm_ops = { + .prepare = t7xx_pci_pm_prepare, .suspend = t7xx_pci_pm_suspend, .resume = t7xx_pci_pm_resume, .resume_noirq = t7xx_pci_pm_resume_noirq, diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 112efa534eac..f08f1ab74469 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -69,6 +69,7 @@ struct t7xx_pci_dev { struct t7xx_modem *md; struct t7xx_ccmni_ctrl *ccmni_ctlb; bool rgu_pci_irq_en; + struct completion init_done; /* Low Power Items */ struct list_head md_pm_entities; -- GitLab From 224a876e37543eee111bf9b6aa4935080e619335 Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 14 May 2023 10:00:10 -0400 Subject: [PATCH 5108/5631] netfilter: conntrack: define variables exp_nat_nla_policy and any_addr with CONFIG_NF_NAT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit gcc with W=1 and ! CONFIG_NF_NAT net/netfilter/nf_conntrack_netlink.c:3463:32: error: ‘exp_nat_nla_policy’ defined but not used [-Werror=unused-const-variable=] 3463 | static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { | ^~~~~~~~~~~~~~~~~~ net/netfilter/nf_conntrack_netlink.c:2979:33: error: ‘any_addr’ defined but not used [-Werror=unused-const-variable=] 2979 | static const union nf_inet_addr any_addr; | ^~~~~~~~ These variables use is controlled by CONFIG_NF_NAT, so should their definitions. Signed-off-by: Tom Rix Reviewed-by: Simon Horman Signed-off-by: Florian Westphal --- net/netfilter/nf_conntrack_netlink.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d40544cd61a6..69c8c8c7e9b8 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2976,7 +2976,9 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -3460,10 +3462,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, -- GitLab From e3c361b8acd636f5fe80c02849ca175201edf10c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 May 2023 14:15:15 +0200 Subject: [PATCH 5109/5631] netfilter: nf_tables: fix nft_trans type confusion nft_trans_FOO objects all share a common nft_trans base structure, but trailing fields depend on the real object size. Access is only safe after trans->msg_type check. Check for rule type first. Found by code inspection. Fixes: 1a94e38d254b ("netfilter: nf_tables: add NFTA_RULE_ID attribute") Signed-off-by: Florian Westphal --- net/netfilter/nf_tables_api.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 59fb8320ab4d..dc5675962de4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3865,12 +3865,10 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { - struct nft_rule *rule = nft_trans_rule(trans); - if (trans->msg_type == NFT_MSG_NEWRULE && trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) - return rule; + return nft_trans_rule(trans); } return ERR_PTR(-ENOENT); } -- GitLab From 61ae320a29b0540c16931816299eb86bf2b66c08 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 May 2023 22:39:30 +0200 Subject: [PATCH 5110/5631] netfilter: nft_set_rbtree: fix null deref on element insertion There is no guarantee that rb_prev() will not return NULL in nft_rbtree_gc_elem(): general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f] nft_add_set_elem+0x14b0/0x2990 nf_tables_newsetelem+0x528/0xb30 Furthermore, there is a possible use-after-free while iterating, 'node' can be free'd so we need to cache the next value to use. Fixes: c9e6978e2725 ("netfilter: nft_set_rbtree: Switch to node list walk for overlap detection") Signed-off-by: Florian Westphal --- net/netfilter/nft_set_rbtree.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 19ea4d3c3553..2f114aa10f1a 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -221,7 +221,7 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); - struct nft_rbtree_elem *rbe_prev; + struct nft_rbtree_elem *rbe_prev = NULL; struct nft_set_gc_batch *gcb; gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); @@ -229,17 +229,21 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, return -ENOMEM; /* search for expired end interval coming before this element. */ - do { + while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev)) break; prev = rb_prev(prev); - } while (prev != NULL); + } + + if (rbe_prev) { + rb_erase(&rbe_prev->node, &priv->root); + atomic_dec(&set->nelems); + } - rb_erase(&rbe_prev->node, &priv->root); rb_erase(&rbe->node, &priv->root); - atomic_sub(2, &set->nelems); + atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); nft_set_gc_batch_complete(gcb); @@ -268,7 +272,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_set_ext **ext) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; - struct rb_node *node, *parent, **p, *first = NULL; + struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); int d, err; @@ -307,7 +311,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ - for (node = first; node != NULL; node = rb_next(node)) { + for (node = first; node != NULL; node = next) { + next = rb_next(node); + rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) -- GitLab From 2862a2fdfae875888e3c1c3634e3422e01d98147 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Thu, 11 May 2023 17:04:41 +0200 Subject: [PATCH 5111/5631] s390/qdio: fix do_sqbs() inline assembly constraint Use "a" constraint instead of "d" constraint to pass the state parameter to the do_sqbs() inline assembly. This prevents that general purpose register zero is used for the state parameter. If the compiler would select general purpose register zero this would be problematic for the used instruction in rsy format: the register used for the state parameter is a base register. If the base register is general purpose register zero the contents of the register are unexpectedly ignored when the instruction is executed. This only applies to z/VM guests using QIOASSIST with dedicated (pass through) QDIO-based devices such as FCP [zfcp driver] as well as real OSA or HiperSockets [qeth driver]. A possible symptom for this case using zfcp is the following repeating kernel message pattern: zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred zfcp : qdio: ZFCP on SC using AI:1 QEBSM:1 PRI:1 TDD:1 SIGA: W zfcp : A QDIO problem occurred zfcp : A QDIO problem occurred Each of the qdio problem message can be accompanied by the following entries for the affected subchannel in /sys/kernel/debug/s390dbf/qdio_error/hex_ascii for zfcp or qeth: ccq: 69.... SQBS ERROR. Reviewed-by: Benjamin Block Cc: Steffen Maier Fixes: 8129ee164267 ("[PATCH] s390: qdio V=V pass-through") Cc: Signed-off-by: Heiko Carstens Signed-off-by: Alexander Gordeev --- drivers/s390/cio/qdio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 5ea6249d8180..641f0dbb65a9 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -95,7 +95,7 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue, " lgr 1,%[token]\n" " .insn rsy,0xeb000000008a,%[qs],%[ccq],0(%[state])" : [ccq] "+&d" (_ccq), [qs] "+&d" (_queuestart) - : [state] "d" ((unsigned long)state), [token] "d" (token) + : [state] "a" ((unsigned long)state), [token] "d" (token) : "memory", "cc", "1"); *count = _ccq & 0xff; *start = _queuestart & 0xff; -- GitLab From ed40866ec7d328b3dfb70db7e2011640a16202c3 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 4 May 2023 16:40:20 +0200 Subject: [PATCH 5112/5631] statfs: enforce statfs[64] structure initialization s390's struct statfs and struct statfs64 contain padding, which field-by-field copying does not set. Initialize the respective structs with zeros before filling them and copying them to userspace, like it's already done for the compat versions of these structs. Found by KMSAN. [agordeev@linux.ibm.com: fixed typo in patch description] Acked-by: Heiko Carstens Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Ilya Leoshkevich Reviewed-by: Andrew Morton Link: https://lore.kernel.org/r/20230504144021.808932-2-iii@linux.ibm.com Signed-off-by: Alexander Gordeev --- fs/statfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/statfs.c b/fs/statfs.c index 0ba34c135593..96d1c3edf289 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -130,6 +130,7 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); if (sizeof buf.f_blocks == 4) { if ((st->f_blocks | st->f_bfree | st->f_bavail | st->f_bsize | st->f_frsize) & @@ -158,7 +159,6 @@ static int do_statfs_native(struct kstatfs *st, struct statfs __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; @@ -171,6 +171,7 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) if (sizeof(buf) == sizeof(*st)) memcpy(&buf, st, sizeof(*st)); else { + memset(&buf, 0, sizeof(buf)); buf.f_type = st->f_type; buf.f_bsize = st->f_bsize; buf.f_blocks = st->f_blocks; @@ -182,7 +183,6 @@ static int do_statfs64(struct kstatfs *st, struct statfs64 __user *p) buf.f_namelen = st->f_namelen; buf.f_frsize = st->f_frsize; buf.f_flags = st->f_flags; - memset(buf.f_spare, 0, sizeof(buf.f_spare)); } if (copy_to_user(p, &buf, sizeof(buf))) return -EFAULT; -- GitLab From 6d9406f80cd82964c8ed75d482d885f18921e0b8 Mon Sep 17 00:00:00 2001 From: Ilya Leoshkevich Date: Thu, 4 May 2023 16:40:21 +0200 Subject: [PATCH 5113/5631] s390/uapi: cover statfs padding by growing f_spare pahole says: struct compat_statfs64 { ... u32 f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ struct statfs { ... unsigned int f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ struct statfs64 { ... unsigned int f_spare[4]; /* 68 16 */ /* size: 88, cachelines: 1, members: 12 */ /* padding: 4 */ One has to keep the existence of padding in mind when working with these structs. Grow f_spare arrays to 5 in order to simplify things. Acked-by: Heiko Carstens Signed-off-by: Ilya Leoshkevich Link: https://lore.kernel.org/r/20230504144021.808932-3-iii@linux.ibm.com Signed-off-by: Alexander Gordeev --- arch/s390/include/asm/compat.h | 2 +- arch/s390/include/uapi/asm/statfs.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index a386070f1d56..3cb9d813f022 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -112,7 +112,7 @@ struct compat_statfs64 { u32 f_namelen; u32 f_frsize; u32 f_flags; - u32 f_spare[4]; + u32 f_spare[5]; }; /* diff --git a/arch/s390/include/uapi/asm/statfs.h b/arch/s390/include/uapi/asm/statfs.h index 72604f7792c3..f85b50723dd3 100644 --- a/arch/s390/include/uapi/asm/statfs.h +++ b/arch/s390/include/uapi/asm/statfs.h @@ -30,7 +30,7 @@ struct statfs { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; struct statfs64 { @@ -45,7 +45,7 @@ struct statfs64 { unsigned int f_namelen; unsigned int f_frsize; unsigned int f_flags; - unsigned int f_spare[4]; + unsigned int f_spare[5]; }; #endif -- GitLab From e534167cee150d900bf800ddb9bf1514d966635f Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 8 May 2023 06:09:16 +0200 Subject: [PATCH 5114/5631] s390/Kconfig: remove obsolete configs SCHED_{BOOK,DRAWER} Commit f1045056c726 ("topology/sysfs: rework book and drawer topology ifdefery") activates the book and drawer topology, previously activated by CONFIG_SCHED_{BOOK,DRAWER}, dependent on the existence of certain macro definitions. Hence, since then, CONFIG_SCHED_{BOOK,DRAWER} have no effect and any further purpose. Remove the obsolete configs SCHED_{BOOK,DRAWER}. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20230508040916.16733-1-lukas.bulwahn@gmail.com Signed-off-by: Alexander Gordeev --- arch/s390/Kconfig | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index db20c1589a98..886948a6105b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -469,19 +469,11 @@ config SCHED_SMT config SCHED_MC def_bool n -config SCHED_BOOK - def_bool n - -config SCHED_DRAWER - def_bool n - config SCHED_TOPOLOGY def_bool y prompt "Topology scheduler support" select SCHED_SMT select SCHED_MC - select SCHED_BOOK - select SCHED_DRAWER help Topology scheduler support improves the CPU scheduler's decision making when dealing with machines that have multi-threading, -- GitLab From 0f1cbf941d5949110adf70725a9614e622de8d99 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Mon, 1 May 2023 14:11:28 -0300 Subject: [PATCH 5115/5631] s390/iommu: get rid of S390_CCW_IOMMU and S390_AP_IOMMU These don't do anything anymore, the only user of the symbol was VFIO_CCW/AP which already "depends on VFIO" and VFIO itself selects IOMMU_API. When this was added VFIO was wrongly doing "depends on IOMMU_API" which required some contortions like this to ensure IOMMU_API was turned on. Reviewed-by: Eric Farman Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v2-eb322ce2e547+188f-rm_iommu_ccw_jgg@nvidia.com Signed-off-by: Alexander Gordeev --- Documentation/s390/vfio-ap.rst | 1 - arch/s390/Kconfig | 3 +-- arch/s390/configs/debug_defconfig | 2 -- arch/s390/configs/defconfig | 2 -- drivers/iommu/Kconfig | 16 ---------------- 5 files changed, 1 insertion(+), 23 deletions(-) diff --git a/Documentation/s390/vfio-ap.rst b/Documentation/s390/vfio-ap.rst index d46e98c7c1ec..bb3f4c4e2885 100644 --- a/Documentation/s390/vfio-ap.rst +++ b/Documentation/s390/vfio-ap.rst @@ -551,7 +551,6 @@ These are the steps: * IOMMU_SUPPORT * S390 * ZCRYPT - * S390_AP_IOMMU * VFIO * KVM diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 886948a6105b..6dab9c1be508 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -708,7 +708,6 @@ config EADM_SCH config VFIO_CCW def_tristate n prompt "Support for VFIO-CCW subchannels" - depends on S390_CCW_IOMMU depends on VFIO select VFIO_MDEV help @@ -720,7 +719,7 @@ config VFIO_CCW config VFIO_AP def_tristate n prompt "VFIO support for AP devices" - depends on S390_AP_IOMMU && KVM + depends on KVM depends on VFIO depends on ZCRYPT select VFIO_MDEV diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 1b68156f2040..be3bf03bf361 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -591,8 +591,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index b0643283bbdd..769c7eed8b6a 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -580,8 +580,6 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m -CONFIG_S390_CCW_IOMMU=y -CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index db98c3f86e8c..6de900776e24 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -417,22 +417,6 @@ config S390_IOMMU help Support for the IOMMU API for s390 PCI devices. -config S390_CCW_IOMMU - bool "S390 CCW IOMMU Support" - depends on S390 && CCW || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - -config S390_AP_IOMMU - bool "S390 AP IOMMU Support" - depends on S390 && ZCRYPT || COMPILE_TEST - select IOMMU_API - help - Enables bits of IOMMU API required by VFIO. The iommu_ops - is not implemented as it is not necessary for VFIO. - config MTK_IOMMU tristate "MediaTek IOMMU Support" depends on ARCH_MEDIATEK || COMPILE_TEST -- GitLab From f15afbd34d8fadbd375f1212e97837e32bc170cc Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Mon, 24 Apr 2023 13:18:35 +0800 Subject: [PATCH 5116/5631] fs: fix undefined behavior in bit shift for SB_NOUSER Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. It was spotted by UBSAN. So let's just fix this by using the BIT() helper for all SB_* flags. Fixes: e462ec50cb5f ("VFS: Differentiate mount flags (MS_*) from internal superblock flags") Signed-off-by: Hao Ge Message-Id: <20230424051835.374204-1-gehao@kylinos.cn> [brauner@kernel.org: use BIT() for all SB_* flags] Signed-off-by: Christian Brauner --- include/linux/fs.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) -- GitLab From 3a7bb21b6f49b4d1695d4ba8ff31e9619cbcebe3 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 16 May 2023 08:46:54 -0400 Subject: [PATCH 5117/5631] fs: don't call posix_acl_listxattr in generic_listxattr Commit f2620f166e2a caused the kernel to start emitting POSIX ACL xattrs for NFSv4 inodes, which it doesn't support. The only other user of generic_listxattr is HFS (classic) and it doesn't support POSIX ACLs either. Fixes: f2620f166e2a xattr: simplify listxattr helpers Reported-by: Ondrej Valousek Signed-off-by: Jeff Layton Message-Id: <20230516124655.82283-1-jlayton@kernel.org> Signed-off-by: Christian Brauner --- fs/xattr.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index fcf67d80d7f9..e7bbb7f57557 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -985,9 +985,16 @@ int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) return 0; } -/* +/** + * generic_listxattr - run through a dentry's xattr list() operations + * @dentry: dentry to list the xattrs + * @buffer: result buffer + * @buffer_size: size of @buffer + * * Combine the results of the list() operation from every xattr_handler in the - * list. + * xattr_handler stack. + * + * Note that this will not include the entries for POSIX ACLs. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) @@ -996,10 +1003,6 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) ssize_t remaining_size = buffer_size; int err = 0; - err = posix_acl_listxattr(d_inode(dentry), &buffer, &remaining_size); - if (err) - return err; - for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; -- GitLab From 48524463f807ec516a291bdf717dcf2c8e059f51 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 17 May 2023 16:07:39 +0900 Subject: [PATCH 5118/5631] ntfs: Add myself as a reviewer I'm volunteering to help review patches for current unmaintained ntfs filesytem. Signed-off-by: Namjae Jeon Acked-by: Bagas Sanjaya Message-Id: <20230517070739.6505-1-linkinjeon@kernel.org> Signed-off-by: Christian Brauner --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e0ad886d3163..83888aa3298c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14928,6 +14928,7 @@ F: drivers/ntb/hw/intel/ NTFS FILESYSTEM M: Anton Altaparmakov +R: Namjae Jeon L: linux-ntfs-dev@lists.sourceforge.net S: Supported W: http://www.tuxera.com/ -- GitLab From 9bc83d6e3824f09cef73b01256962d950965ddc4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 10:10:57 -0300 Subject: [PATCH 5119/5631] tools headers x86 cpufeatures: Sync with the kernel sources To pick the changes from: 3d8f61bf8bcd69bc ("x86: KVM: Add common feature flag for AMD's PSFD") 3763bf58029f3459 ("x86/cpufeatures: Redefine synthetic virtual NMI bit as AMD's "real" vNMI") 6449dcb0cac73821 ("x86: CPUID and CR3/CR4 flags for Linear Address Masking") be8de49bea505e77 ("x86/speculation: Identify processors vulnerable to SMT RSB predictions") e7862eda309ecfcc ("x86/cpu: Support AMD Automatic IBRS") faabfcb194a8d068 ("x86/cpu, kvm: Add the SMM_CTL MSR not present feature") 5b909d4ae59aedc7 ("x86/cpu, kvm: Add the Null Selector Clears Base feature") 84168ae786f8a15a ("x86/cpu, kvm: Move X86_FEATURE_LFENCE_RDTSC to its native leaf") a9dc9ec5a1fafc3d ("x86/cpu, kvm: Add the NO_NESTED_DATA_BP feature") f8df91e73a6827a4 ("x86/cpufeatures: Add macros for Intel's new fast rep string features") 78335aac6156eada ("x86/cpufeatures: Add Bandwidth Monitoring Event Configuration feature flag") f334f723a63cfc25 ("x86/cpufeatures: Add Slow Memory Bandwidth Allocation feature flag") a018d2e3d4b1abc4 ("x86/cpufeatures: Add Architectural PerfMon Extension bit") This causes these perf files to be rebuilt and brings some X86_FEATURE that will be used when updating the copies of tools/arch/x86/lib/mem{cpy,set}_64.S with the kernel sources: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Cc: Borislav Petkov (AMD) Cc: Kim Phillips Cc: Jim Mattson Cc: Babu Moger Cc: Ingo Molnar Cc: Kan Liang Cc: Sean Christopherson Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Paolo Bonzini Cc: Tom Lendacky Link: https://lore.kernel.org/lkml/ZGTTw642q8mWgv2Y@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 26 +++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index b89005819cd5..cb8ca46213be 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */ +/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ @@ -226,10 +226,9 @@ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ -#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ -#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ -#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ -#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -307,14 +306,21 @@ #define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ #define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ #define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* "" Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ @@ -331,6 +337,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* "" Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ @@ -363,6 +370,7 @@ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ #define X86_FEATURE_X2AVIC (15*32+18) /* Virtual x2apic */ #define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* Virtual NMI */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -427,6 +435,13 @@ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* "" SMM_CTL MSR is not present */ + /* * BUG word(s) */ @@ -467,5 +482,6 @@ #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ #define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ -- GitLab From 7f02ce62a6cfc0feb164bb7eb36c6647c00b43c8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 10:34:59 -0300 Subject: [PATCH 5120/5631] tools headers: Update the copy of x86's mem{cpy,set}_64.S used in 'perf bench' This is to get the changes from: 68674f94ffc9dddc ("x86: don't use REP_GOOD or ERMS for small memory copies") 20f3337d350c4e1b ("x86: don't use REP_GOOD or ERMS for small memory clearing") This also make the 'perf bench mem' files stop referring to the erms versions that gone away with the above patches. That addresses these perf tools build warning: Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/lib/memcpy_64.S | 34 +++++--------- tools/arch/x86/lib/memset_64.S | 47 +++++--------------- tools/include/asm/alternative.h | 3 +- tools/perf/bench/mem-memcpy-x86-64-asm-def.h | 4 -- tools/perf/bench/mem-memcpy-x86-64-asm.S | 2 +- tools/perf/bench/mem-memset-x86-64-asm-def.h | 4 -- tools/perf/bench/mem-memset-x86-64-asm.S | 2 +- 7 files changed, 24 insertions(+), 72 deletions(-) diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index a91ac666f758..d055b82d22cc 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -9,13 +9,6 @@ .section .noinstr.text, "ax" -/* - * We build a jump to memcpy_orig by default which gets NOPped out on - * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which - * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs - * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. - */ - /* * memcpy - Copy a memory block. * @@ -26,17 +19,21 @@ * * Output: * rax original destination + * + * The FSRM alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep movsb' itself is small enough to replace the call, but the + * two register moves blow up the code. And one of them is "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_TYPED_FUNC_START(__memcpy) - ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memcpy_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM movq %rdi, %rax movq %rdx, %rcx - shrq $3, %rcx - andl $7, %edx - rep movsq - movl %edx, %ecx rep movsb RET SYM_FUNC_END(__memcpy) @@ -45,17 +42,6 @@ EXPORT_SYMBOL(__memcpy) SYM_FUNC_ALIAS(memcpy, __memcpy) EXPORT_SYMBOL(memcpy) -/* - * memcpy_erms() - enhanced fast string memcpy. This is faster and - * simpler than memcpy. Use memcpy_erms when possible. - */ -SYM_FUNC_START_LOCAL(memcpy_erms) - movq %rdi, %rax - movq %rdx, %rcx - rep movsb - RET -SYM_FUNC_END(memcpy_erms) - SYM_FUNC_START_LOCAL(memcpy_orig) movq %rdi, %rax diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 6143b1a6fa2c..7c59a704c458 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -18,27 +18,22 @@ * rdx count (bytes) * * rax original destination + * + * The FSRS alternative should be done inline (avoiding the call and + * the disgusting return handling), but that would require some help + * from the compiler for better calling conventions. + * + * The 'rep stosb' itself is small enough to replace the call, but all + * the register moves blow up the code. And two of them are "needed" + * only for the return value that is the same as the source input, + * which the compiler could/should do much better anyway. */ SYM_FUNC_START(__memset) - /* - * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended - * to use it when possible. If not available, use fast string instructions. - * - * Otherwise, use original memset function. - */ - ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ - "jmp memset_erms", X86_FEATURE_ERMS + ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS movq %rdi,%r9 + movb %sil,%al movq %rdx,%rcx - andl $7,%edx - shrq $3,%rcx - /* expand byte value */ - movzbl %sil,%esi - movabs $0x0101010101010101,%rax - imulq %rsi,%rax - rep stosq - movl %edx,%ecx rep stosb movq %r9,%rax RET @@ -48,26 +43,6 @@ EXPORT_SYMBOL(__memset) SYM_FUNC_ALIAS(memset, __memset) EXPORT_SYMBOL(memset) -/* - * ISO C memset - set a memory block to a byte value. This function uses - * enhanced rep stosb to override the fast string function. - * The code is simpler and shorter than the fast string function as well. - * - * rdi destination - * rsi value (char) - * rdx count (bytes) - * - * rax original destination - */ -SYM_FUNC_START_LOCAL(memset_erms) - movq %rdi,%r9 - movb %sil,%al - movq %rdx,%rcx - rep stosb - movq %r9,%rax - RET -SYM_FUNC_END(memset_erms) - SYM_FUNC_START_LOCAL(memset_orig) movq %rdi,%r10 diff --git a/tools/include/asm/alternative.h b/tools/include/asm/alternative.h index b54bd860dff6..7ce02a223732 100644 --- a/tools/include/asm/alternative.h +++ b/tools/include/asm/alternative.h @@ -4,7 +4,6 @@ /* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ -#define altinstruction_entry # -#define ALTERNATIVE_2 # +#define ALTERNATIVE # #endif diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h index 50ae8bd58296..6188e19d3129 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMCPY_FN(memcpy_orig, MEMCPY_FN(__memcpy, "x86-64-movsq", "movsq-based memcpy() in arch/x86/lib/memcpy_64.S") - -MEMCPY_FN(memcpy_erms, - "x86-64-movsb", - "movsb-based memcpy() in arch/x86/lib/memcpy_64.S") diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 6eb45a2aa8db..1b9fef7efcdc 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -2,7 +2,7 @@ /* Various wrappers to make the kernel .S file build in user-space: */ -// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it +// memcpy_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memcpy MEMCPY /* don't hide glibc's memcpy() */ diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h index dac6d2b7c39b..247c72fdfb9d 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm-def.h +++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h @@ -7,7 +7,3 @@ MEMSET_FN(memset_orig, MEMSET_FN(__memset, "x86-64-stosq", "movsq-based memset() in arch/x86/lib/memset_64.S") - -MEMSET_FN(memset_erms, - "x86-64-stosb", - "movsb-based memset() in arch/x86/lib/memset_64.S") diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index 6f093c483842..abd26c95f1aa 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it +// memset_orig is being defined as SYM_L_LOCAL but we need it #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #define memset MEMSET /* don't hide glibc's memset() */ -- GitLab From 29719e319869c6b3f09e6e92310b019e32943696 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 11:15:53 -0300 Subject: [PATCH 5121/5631] tools headers UAPI: Sync arch prctl headers with the kernel sources To pick the changes in this cset: a03c376ebaf38394 ("x86/arch_prctl: Add AMX feature numbers as ABI constants") 23e5d9ec2bab53c4 ("x86/mm/iommu/sva: Make LAM and SVA mutually exclusive") 2f8794bd087e7958 ("x86/mm: Provide arch_prctl() interface for LAM") This picks these new prctls in a third range, that was also added to the tools/perf/trace/beauty/arch_prctl.c beautifier. $ tools/perf/trace/beauty/x86_arch_prctl.sh > /tmp/before $ cp arch/x86/include/uapi/asm/prctl.h tools/arch/x86/include/uapi/asm/prctl.h $ tools/perf/trace/beauty/x86_arch_prctl.sh > /tmp/after $ diff -u /tmp/before /tmp/after @@ -20,3 +20,11 @@ [0x2003 - 0x2001]= "MAP_VDSO_64", }; +#define x86_arch_prctl_codes_3_offset 0x4001 +static const char *x86_arch_prctl_codes_3[] = { + [0x4001 - 0x4001]= "GET_UNTAG_MASK", + [0x4002 - 0x4001]= "ENABLE_TAGGED_ADDR", + [0x4003 - 0x4001]= "GET_MAX_TAG_BITS", + [0x4004 - 0x4001]= "FORCE_TAGGED_SVA", +}; + $ With this 'perf trace' can translate those numbers into strings and use the strings in filter expressions: # perf trace -e prctl 0.000 ( 0.011 ms): DOM Worker/3722622 prctl(option: SET_NAME, arg2: 0x7f9c014b7df5) = 0 0.032 ( 0.002 ms): DOM Worker/3722622 prctl(option: SET_NAME, arg2: 0x7f9bb6b51580) = 0 5.452 ( 0.003 ms): StreamT~ns #30/3722623 prctl(option: SET_NAME, arg2: 0x7f9bdbdfeb70) = 0 5.468 ( 0.002 ms): StreamT~ns #30/3722623 prctl(option: SET_NAME, arg2: 0x7f9bdbdfea70) = 0 24.494 ( 0.009 ms): IndexedDB #556/3722624 prctl(option: SET_NAME, arg2: 0x7f562a32ae28) = 0 24.540 ( 0.002 ms): IndexedDB #556/3722624 prctl(option: SET_NAME, arg2: 0x7f563c6d4b30) = 0 670.281 ( 0.008 ms): systemd-userwo/3722339 prctl(option: SET_NAME, arg2: 0x564be30805c8) = 0 670.293 ( 0.002 ms): systemd-userwo/3722339 prctl(option: SET_NAME, arg2: 0x564be30800f0) = 0 ^C# This addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/prctl.h' differs from latest version at 'arch/x86/include/uapi/asm/prctl.h' diff -u tools/arch/x86/include/uapi/asm/prctl.h arch/x86/include/uapi/asm/prctl.h Cc: Adrian Hunter Cc: Chang S. Bae Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Kirill A. Shutemov Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZGTjNPpD3FOWfetM@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/prctl.h | 8 ++++++++ tools/perf/trace/beauty/arch_prctl.c | 2 ++ tools/perf/trace/beauty/x86_arch_prctl.sh | 1 + 3 files changed, 11 insertions(+) diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/arch/x86/include/uapi/asm/prctl.h index 500b96e71f18..e8d7ebbca1a4 100644 --- a/tools/arch/x86/include/uapi/asm/prctl.h +++ b/tools/arch/x86/include/uapi/asm/prctl.h @@ -16,8 +16,16 @@ #define ARCH_GET_XCOMP_GUEST_PERM 0x1024 #define ARCH_REQ_XCOMP_GUEST_PERM 0x1025 +#define ARCH_XCOMP_TILECFG 17 +#define ARCH_XCOMP_TILEDATA 18 + #define ARCH_MAP_VDSO_X32 0x2001 #define ARCH_MAP_VDSO_32 0x2002 #define ARCH_MAP_VDSO_64 0x2003 +#define ARCH_GET_UNTAG_MASK 0x4001 +#define ARCH_ENABLE_TAGGED_ADDR 0x4002 +#define ARCH_GET_MAX_TAG_BITS 0x4003 +#define ARCH_FORCE_TAGGED_SVA 0x4004 + #endif /* _ASM_X86_PRCTL_H */ diff --git a/tools/perf/trace/beauty/arch_prctl.c b/tools/perf/trace/beauty/arch_prctl.c index fe022ca67e60..a211348d3204 100644 --- a/tools/perf/trace/beauty/arch_prctl.c +++ b/tools/perf/trace/beauty/arch_prctl.c @@ -12,10 +12,12 @@ static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_1, "ARCH_", x86_arch_prctl_codes_1_offset); static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_2, "ARCH_", x86_arch_prctl_codes_2_offset); +static DEFINE_STRARRAY_OFFSET(x86_arch_prctl_codes_3, "ARCH_", x86_arch_prctl_codes_3_offset); static struct strarray *x86_arch_prctl_codes[] = { &strarray__x86_arch_prctl_codes_1, &strarray__x86_arch_prctl_codes_2, + &strarray__x86_arch_prctl_codes_3, }; static DEFINE_STRARRAYS(x86_arch_prctl_codes); diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh index 57fa6aaffe70..fd5c740512c5 100755 --- a/tools/perf/trace/beauty/x86_arch_prctl.sh +++ b/tools/perf/trace/beauty/x86_arch_prctl.sh @@ -24,3 +24,4 @@ print_range () { print_range 1 0x1 0x1001 print_range 2 0x2 0x2001 +print_range 3 0x4 0x4001 -- GitLab From 1743e5f6000901a11f4e1cd741bfa9136f3ec9b1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 May 2023 09:53:45 +0200 Subject: [PATCH 5122/5631] nvme-multipath: don't call blk_mark_disk_dead in nvme_mpath_remove_disk nvme_mpath_remove_disk is called after del_gendisk, at which point a blk_mark_disk_dead call doesn't make any sense. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch --- drivers/nvme/host/multipath.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63..187c9de0d6d5 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -884,7 +884,6 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) { if (!head->disk) return; - blk_mark_disk_dead(head->disk); /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); -- GitLab From 2eb94dd56a4a4e3fe286def3e2ba207804a37345 Mon Sep 17 00:00:00 2001 From: Maurizio Lombardi Date: Thu, 11 May 2023 13:07:41 +0200 Subject: [PATCH 5123/5631] nvme: do not let the user delete a ctrl before a complete initialization If a userspace application performes a "delete_controller" command early during the ctrl initialization, the delete operation may race against the init code and the kernel will crash. nvme nvme5: Connect command failed: host path error nvme nvme5: failed to connect queue: 0 ret=880 PF: supervisor write access in kernel mode PF: error_code(0x0002) - not-present page blk_mq_quiesce_queue+0x18/0x90 nvme_tcp_delete_ctrl+0x24/0x40 [nvme_tcp] nvme_do_delete_ctrl+0x7f/0x8b [nvme_core] nvme_sysfs_delete.cold+0x8/0xd [nvme_core] kernfs_fop_write_iter+0x124/0x1b0 new_sync_write+0xff/0x190 vfs_write+0x1ef/0x280 Fix the crash by checking the NVME_CTRL_STARTED_ONCE bit; if it's not set it means that the nvme controller is still in the process of getting initialized and the kernel will return an -EBUSY error to userspace. Set the NVME_CTRL_STARTED_ONCE later in the nvme_start_ctrl() function, after the controller start operation is completed. Signed-off-by: Maurizio Lombardi Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch --- drivers/nvme/host/core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6c1e7d6709e0..22e9e90aa671 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3574,6 +3574,9 @@ static ssize_t nvme_sysfs_delete(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); + if (!test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags)) + return -EBUSY; + if (device_remove_file_self(dev, attr)) nvme_delete_ctrl_sync(ctrl); return count; @@ -5034,7 +5037,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) * that were missed. We identify persistent discovery controllers by * checking that they started once before, hence are reconnecting back. */ - if (test_and_set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && + if (test_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags) && nvme_discovery_ctrl(ctrl)) nvme_change_uevent(ctrl, "NVME_EVENT=rediscover"); @@ -5045,6 +5048,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl) } nvme_change_uevent(ctrl, "NVME_EVENT=connected"); + set_bit(NVME_CTRL_STARTED_ONCE, &ctrl->flags); } EXPORT_SYMBOL_GPL(nvme_start_ctrl); -- GitLab From 1b5f159ce8751b61aea426293cd71a510a081939 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 17 May 2023 11:47:38 -0300 Subject: [PATCH 5124/5631] tools headers disabled-features: Sync with the kernel sources To pick the changes from: e0bddc19ba9578bc ("x86/mm: Reduce untagged_addr() overhead for systems without LAM") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Cc: Adrian Hunter Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Kirill A. Shutemov Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZGTpdlzrlRjjnY6K@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/disabled-features.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 5dfa4fb76f4b..fafe9be7a6f4 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -75,6 +75,12 @@ # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) #endif +#ifdef CONFIG_ADDRESS_MASKING +# define DISABLE_LAM 0 +#else +# define DISABLE_LAM (1 << (X86_FEATURE_LAM & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -115,7 +121,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING) -#define DISABLED_MASK12 0 +#define DISABLED_MASK12 (DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -- GitLab From ccecefa4f89971e34745abbffdaf4d2c3fb2f457 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:50:41 +0200 Subject: [PATCH 5125/5631] ALSA: cs46xx: mark snd_cs46xx_download_image as static snd_cs46xx_download_image() was originally called from dsp_spos.c, but is now local to cs46xx_lib.c. Mark it as 'static' to avoid a warning about it lacking a declaration, and '__maybe_unused' to avoid a warning about it being unused when CONFIG_SND_CS46XX_NEW_DSP is disabled: sound/pci/cs46xx/cs46xx_lib.c:534:5: error: no previous prototype for 'snd_cs46xx_download_image' Fixes: 89f157d9e6bf ("[ALSA] cs46xx - Fix PM resume") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516195046.550584-1-arnd@kernel.org Signed-off-by: Takashi Iwai --- sound/pci/cs46xx/cs46xx_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c index 62f45847b351..7d882b33d45e 100644 --- a/sound/pci/cs46xx/cs46xx_lib.c +++ b/sound/pci/cs46xx/cs46xx_lib.c @@ -531,7 +531,7 @@ static int load_firmware(struct snd_cs46xx *chip) return err; } -int snd_cs46xx_download_image(struct snd_cs46xx *chip) +static __maybe_unused int snd_cs46xx_download_image(struct snd_cs46xx *chip) { int idx, err; unsigned int offset = 0; -- GitLab From 040b5a046a9e18098580d3ccd029e2318fca7859 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:50:42 +0200 Subject: [PATCH 5126/5631] ALSA: oss: avoid missing-prototype warnings Two functions are defined and used in pcm_oss.c but also optionally used from io.c, with an optional prototype. If CONFIG_SND_PCM_OSS_PLUGINS is disabled, this causes a warning as the functions are not static and have no prototype: sound/core/oss/pcm_oss.c:1235:19: error: no previous prototype for 'snd_pcm_oss_write3' [-Werror=missing-prototypes] sound/core/oss/pcm_oss.c:1266:19: error: no previous prototype for 'snd_pcm_oss_read3' [-Werror=missing-prototypes] Avoid this by making the prototypes unconditional. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516195046.550584-2-arnd@kernel.org Signed-off-by: Takashi Iwai --- sound/core/oss/pcm_plugin.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/sound/core/oss/pcm_plugin.h b/sound/core/oss/pcm_plugin.h index 46e273bd4a78..50a6b50f5db4 100644 --- a/sound/core/oss/pcm_plugin.h +++ b/sound/core/oss/pcm_plugin.h @@ -141,6 +141,14 @@ int snd_pcm_area_copy(const struct snd_pcm_channel_area *src_channel, void *snd_pcm_plug_buf_alloc(struct snd_pcm_substream *plug, snd_pcm_uframes_t size); void snd_pcm_plug_buf_unlock(struct snd_pcm_substream *plug, void *ptr); +#else + +static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } +static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } +static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } + +#endif + snd_pcm_sframes_t snd_pcm_oss_write3(struct snd_pcm_substream *substream, const char *ptr, snd_pcm_uframes_t size, int in_kernel); @@ -151,14 +159,6 @@ snd_pcm_sframes_t snd_pcm_oss_writev3(struct snd_pcm_substream *substream, snd_pcm_sframes_t snd_pcm_oss_readv3(struct snd_pcm_substream *substream, void **bufs, snd_pcm_uframes_t frames); -#else - -static inline snd_pcm_sframes_t snd_pcm_plug_client_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t drv_size) { return drv_size; } -static inline snd_pcm_sframes_t snd_pcm_plug_slave_size(struct snd_pcm_substream *handle, snd_pcm_uframes_t clt_size) { return clt_size; } -static inline int snd_pcm_plug_slave_format(int format, const struct snd_mask *format_mask) { return format; } - -#endif - #ifdef PLUGIN_DEBUG #define pdprintf(fmt, args...) printk(KERN_DEBUG "plugin: " fmt, ##args) #else -- GitLab From dc4f2ccaedddb489a83e7b12ebbdc347272aacc9 Mon Sep 17 00:00:00 2001 From: Nikhil Mahale Date: Wed, 17 May 2023 14:37:36 +0530 Subject: [PATCH 5127/5631] ALSA: hda: Add NVIDIA codec IDs a3 through a7 to patch table These IDs are for AD102, AD103, AD104, AD106, and AD107 gpus with audio functions that are largely similar to the existing ones. Tested audio using gnome-settings, over HDMI, DP-SST and DP-MST connections on AD106 gpu. Signed-off-by: Nikhil Mahale Cc: Link: https://lore.kernel.org/r/20230517090736.15088-1-nmahale@nvidia.com Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_hdmi.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 64a944016c78..5c0b1a09fd57 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -4589,6 +4589,11 @@ HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP", patch_nvhdmi), +HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP", patch_nvhdmi), HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI", patch_nvhdmi_2ch), HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP", patch_gf_hdmi), -- GitLab From e36ca2fad6bb4ef0603bdb5556578e9082fe0056 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 May 2023 15:20:36 -0700 Subject: [PATCH 5128/5631] iommu/arm-smmu-qcom: Fix missing adreno_smmu's When the special handling of qcom,adreno-smmu was moved into qcom_smmu_create(), it was overlooked that we didn't have all the required entries in qcom_smmu_impl_of_match. So we stopped getting adreno_smmu_priv on sc7180, breaking per-process pgtables. Fixes: 30b912a03d91 ("iommu/arm-smmu-qcom: Move the qcom,adreno-smmu check into qcom_smmu_create") Cc: Suggested-by: Lepton Wu Signed-off-by: Rob Clark Reviewed-by: Konrad Dybcio Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/537357/ Link: https://lore.kernel.org/r/20230516222039.907690-1-robdclark@gmail.com --- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c index d1b296b95c86..ec743a9ec67a 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c @@ -503,6 +503,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = { { .compatible = "qcom,qcm2290-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,qdu1000-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc7180-smmu-500", .data = &qcom_smmu_500_impl0_data }, + { .compatible = "qcom,sc7180-smmu-v2", .data = &qcom_smmu_v2_data }, { .compatible = "qcom,sc7280-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8180x-smmu-500", .data = &qcom_smmu_500_impl0_data }, { .compatible = "qcom,sc8280xp-smmu-500", .data = &qcom_smmu_500_impl0_data }, @@ -547,5 +548,14 @@ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu) if (match) return qcom_smmu_create(smmu, match->data); + /* + * If you hit this WARN_ON() you are missing an entry in the + * qcom_smmu_impl_of_match[] table, and GPU per-process page- + * tables will be broken. + */ + WARN(of_device_is_compatible(np, "qcom,adreno-smmu"), + "Missing qcom_smmu_impl_of_match entry for: %s", + dev_name(smmu->dev)); + return smmu; } -- GitLab From 5c054db54c43a5fcb5cc81012361f5e3fac37637 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Tue, 16 May 2023 15:20:37 -0700 Subject: [PATCH 5129/5631] drm/msm: Be more shouty if per-process pgtables aren't working Otherwise it is not always obvious if a dt or iommu change is causing us to fall back to global pgtable. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Patchwork: https://patchwork.freedesktop.org/patch/537359/ Link: https://lore.kernel.org/r/20230516222039.907690-2-robdclark@gmail.com --- drivers/gpu/drm/msm/msm_iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 5080319ae4cf..5cc8d358cc97 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -234,7 +234,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Get the pagetable configuration from the domain */ if (adreno_smmu->cookie) ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); - if (!ttbr1_cfg) + + /* + * If you hit this WARN_ONCE() you are probably missing an entry in + * qcom_smmu_impl_of_match[] in arm-smmu-qcom.c + */ + if (WARN_ONCE(!ttbr1_cfg, "No per-process page tables")) return ERR_PTR(-ENODEV); pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL); -- GitLab From ce0b15d11ad837fbacc5356941712218e38a0a83 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 16 May 2023 12:24:25 -0700 Subject: [PATCH 5130/5631] x86/mm: Avoid incomplete Global INVLPG flushes The INVLPG instruction is used to invalidate TLB entries for a specified virtual address. When PCIDs are enabled, INVLPG is supposed to invalidate TLB entries for the specified address for both the current PCID *and* Global entries. (Note: Only kernel mappings set Global=1.) Unfortunately, some INVLPG implementations can leave Global translations unflushed when PCIDs are enabled. As a workaround, never enable PCIDs on affected processors. I expect there to eventually be microcode mitigations to replace this software workaround. However, the exact version numbers where that will happen are not known today. Once the version numbers are set in stone, the processor list can be tweaked to only disable PCIDs on affected processors with affected microcode. Note: if anyone wants a quick fix that doesn't require patching, just stick 'nopcid' on your kernel command-line. Signed-off-by: Dave Hansen Reviewed-by: Thomas Gleixner Cc: stable@vger.kernel.org --- arch/x86/mm/init.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 3cdac0f0055d..8192452d1d2d 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -261,6 +262,24 @@ static void __init probe_page_size_mask(void) } } +#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ + .family = 6, \ + .model = _model, \ + } +/* + * INVLPG may not properly flush Global entries + * on these CPUs when PCIDs are enabled. + */ +static const struct x86_cpu_id invlpg_miss_ids[] = { + INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), + INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), + INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + {} +}; + static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) @@ -269,6 +288,12 @@ static void setup_pcid(void) if (!boot_cpu_has(X86_FEATURE_PCID)) return; + if (x86_match_cpu(invlpg_miss_ids)) { + pr_info("Incomplete global flushes, disabling PCID"); + setup_clear_cpu_cap(X86_FEATURE_PCID); + return; + } + if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the -- GitLab From a18ef64fe1e4558b14a6e0ca9fbe8264475b7013 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 May 2023 14:47:12 +0200 Subject: [PATCH 5131/5631] tracing: make ftrace_likely_update() declaration visible This function is only used when CONFIG_TRACE_BRANCH_PROFILING is set and DISABLE_BRANCH_PROFILING is not set, and the declaration is hidden behind this combination of tests. But that causes a warning when building with CONFIG_TRACING_BRANCHES, since that sets DISABLE_BRANCH_PROFILING for the tracing code, and the declaration is thus hidden: kernel/trace/trace_branch.c:205:6: error: no previous prototype for 'ftrace_likely_update' [-Werror=missing-prototypes] Move the declaration out of the #ifdef to avoid the warning. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 947a60b801db..d7779a18b24f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -12,11 +12,10 @@ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ -#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ - && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); - +#if defined(CONFIG_TRACE_BRANCH_PROFILING) \ + && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) -- GitLab From d5aa417808cf14c052ca042920b3c6b9f1dc6aa4 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 10 Apr 2023 12:02:29 -0400 Subject: [PATCH 5132/5631] drm/amdgpu/gfx11: update gpu_clock_counter logic This code was written prior to previous updates to this logic for other chips. The RSC registers are part of SMUIO which is an always on block so there is no need to disable gfxoff. Additionally add the carryover and preemption checks. v2: rebase Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method Cc: stable@vger.kernel.org # 6.2.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method Cc: stable@vger.kernel.org # 6.3.y: 5591a051b86b: drm/amdgpu: refine get gpu clock counter method --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index f5c376276984..db2543d8fde9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4667,24 +4667,27 @@ static uint64_t gfx_v11_0_get_gpu_clock_counter(struct amdgpu_device *adev) uint64_t clock; uint64_t clock_counter_lo, clock_counter_hi_pre, clock_counter_hi_after; - amdgpu_gfx_off_ctrl(adev, false); - mutex_lock(&adev->gfx.gpu_clock_mutex); if (amdgpu_sriov_vf(adev)) { + amdgpu_gfx_off_ctrl(adev, false); + mutex_lock(&adev->gfx.gpu_clock_mutex); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); clock_counter_hi_after = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_HI); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(GC, 0, regCP_MES_MTIME_LO); + mutex_unlock(&adev->gfx.gpu_clock_mutex); + amdgpu_gfx_off_ctrl(adev, true); } else { + preempt_disable(); clock_counter_hi_pre = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); clock_counter_hi_after = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_UPPER); if (clock_counter_hi_pre != clock_counter_hi_after) clock_counter_lo = (uint64_t)RREG32_SOC15(SMUIO, 0, regGOLDEN_TSC_COUNT_LOWER); + preempt_enable(); } clock = clock_counter_lo | (clock_counter_hi_after << 32ULL); - mutex_unlock(&adev->gfx.gpu_clock_mutex); - amdgpu_gfx_off_ctrl(adev, true); + return clock; } -- GitLab From 47592fa8eb03742048b096b4696ec133384c45eb Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Wed, 3 May 2023 14:38:35 +0000 Subject: [PATCH 5133/5631] SMB3: Close all deferred handles of inode in case of handle lease break Oplock break may occur for different file handle than the deferred handle. Check for inode deferred closes list, if it's not empty then close all the deferred handles of inode because we should not cache handles if we dont have handle lease. Eg: If openfilelist has one deferred file handle and another open file handle from app for a same file, then on a lease break we choose the first handle in openfile list. The first handle in list can be deferred handle or actual open file handle from app. In case if it is actual open handle then today, we don't close deferred handles if we lose handle lease on a file. Problem with this is, later if app decides to close the existing open handle then we still be caching deferred handles until deferred close timeout. Leaving open handle may result in sharing violation when windows client tries to open a file with limited file share access. So we should check for deferred list of inode and walk through the list of deferred files in inode and close all deferred files. Fixes: 9e31678fb403 ("SMB3: fix lease break timeout when multiple deferred close handles for the same file.") Cc: stable@kernel.org Signed-off-by: Bharath SM Signed-off-by: Steve French --- fs/cifs/file.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c5fcefdfd797..e7868e47c61c 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4882,8 +4882,6 @@ void cifs_oplock_break(struct work_struct *work) struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; bool purge_cache = false; - struct cifs_deferred_close *dclose; - bool is_deferred = false; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4924,14 +4922,9 @@ void cifs_oplock_break(struct work_struct *work) * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ - spin_lock(&CIFS_I(inode)->deferred_lock); - is_deferred = cifs_is_deferred_close(cfile, &dclose); - spin_unlock(&CIFS_I(inode)->deferred_lock); - if (!CIFS_CACHE_HANDLE(cinode) && is_deferred && - cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { + if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); - } /* * releasing stale oplock after recent reconnect of smb session using -- GitLab From 59a556aebc43dded08535fe97d94ca3f657915e4 Mon Sep 17 00:00:00 2001 From: Bharath SM Date: Mon, 15 May 2023 21:25:12 +0000 Subject: [PATCH 5134/5631] SMB3: drop reference to cfile before sending oplock break In cifs_oplock_break function we drop reference to a cfile at the end of function, due to which close command goes on wire after lease break acknowledgment even if file is already closed by application but we had deferred the handle close. If other client with limited file shareaccess waiting on lease break ack proceeds operation on that file as soon as first client sends ack, then we may encounter status sharing violation error because of open handle. Solution is to put reference to cfile(send close on wire if last ref) and then send oplock acknowledgment to server. Fixes: 9e31678fb403 ("SMB3: fix lease break timeout when multiple deferred close handles for the same file.") Cc: stable@kernel.org Signed-off-by: Bharath SM Reviewed-by: Shyam Prasad N Signed-off-by: Steve French --- fs/cifs/cifsglob.h | 4 ++-- fs/cifs/file.c | 17 ++++++++++++----- fs/cifs/smb1ops.c | 9 ++++----- fs/cifs/smb2ops.c | 7 +++---- 4 files changed, 21 insertions(+), 16 deletions(-) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 414685c5d530..5f8fd20951af 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -424,8 +424,8 @@ struct smb_version_operations { /* check for STATUS_NETWORK_SESSION_EXPIRED */ bool (*is_session_expired)(char *); /* send oplock break response */ - int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, - struct cifsInodeInfo *); + int (*oplock_response)(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, + __u16 net_fid, struct cifsInodeInfo *cifs_inode); /* query remote filesystem */ int (*queryfs)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, struct kstatfs *); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index e7868e47c61c..ba7f2e09d6c8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4881,7 +4881,9 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; - bool purge_cache = false; + bool purge_cache = false, oplock_break_cancelled; + __u64 persistent_fid, volatile_fid; + __u16 net_fid; wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -4926,19 +4928,24 @@ void cifs_oplock_break(struct work_struct *work) if (!CIFS_CACHE_HANDLE(cinode) && !list_empty(&cinode->deferred_closes)) cifs_close_deferred_file(cinode); + persistent_fid = cfile->fid.persistent_fid; + volatile_fid = cfile->fid.volatile_fid; + net_fid = cfile->fid.netfid; + oplock_break_cancelled = cfile->oplock_break_cancelled; + + _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do * not bother sending an oplock release if session to server still is * disconnected since oplock already released by the server */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); + if (!oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid, + volatile_fid, net_fid, cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } - _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index abda6148be10..7d1b3fc014d9 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -897,12 +897,11 @@ cifs_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } static int -cifs_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { - return CIFSSMBLock(0, tcon, fid->netfid, current->tgid, 0, 0, 0, 0, - LOCKING_ANDX_OPLOCK_RELEASE, false, - CIFS_CACHE_READ(cinode) ? 1 : 0); + return CIFSSMBLock(0, tcon, net_fid, current->tgid, 0, 0, 0, 0, + LOCKING_ANDX_OPLOCK_RELEASE, false, CIFS_CACHE_READ(cinode) ? 1 : 0); } static int diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a295e4c2d54e..5065398665f1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2383,15 +2383,14 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) } static int -smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, - struct cifsInodeInfo *cinode) +smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, + __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode) { if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) return SMB2_lease_break(0, tcon, cinode->lease_key, smb2_get_lease_state(cinode)); - return SMB2_oplock_break(0, tcon, fid->persistent_fid, - fid->volatile_fid, + return SMB2_oplock_break(0, tcon, persistent_fid, volatile_fid, CIFS_CACHE_READ(cinode) ? 1 : 0); } -- GitLab From 36a6418bb125944838b91a33eddca4064a5eb610 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 17 May 2023 20:02:51 +0200 Subject: [PATCH 5135/5631] Revert "ARM: dts: stm32: add CAN support on stm32f746" This reverts commit 0920ccdf41e3078a4dd2567eb905ea154bc826e6. The commit 0920ccdf41e3 ("ARM: dts: stm32: add CAN support on stm32f746") depends on the patch "dt-bindings: mfd: stm32f7: add binding definition for CAN3" [1], which is not in net/main, yet. This results in a parsing error of "stm32f746.dtsi". So revert this commit. [1] https://lore.kernel.org/all/20230423172528.1398158-2-dario.binacchi@amarulasolutions.com Cc: Dario Binacchi Cc: Alexandre TORGUE Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202305172108.x5acbaQG-lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202305172130.eGGEUhpi-lkp@intel.com Fixes: 0920ccdf41e3 ("ARM: dts: stm32: add CAN support on stm32f746") Suggested-by: Krzysztof Kozlowski Link: https://lore.kernel.org/20230517181950.1106697-1-mkl@pengutronix.de Signed-off-by: Marc Kleine-Budde --- arch/arm/boot/dts/stm32f746.dtsi | 47 -------------------------------- 1 file changed, 47 deletions(-) diff --git a/arch/arm/boot/dts/stm32f746.dtsi b/arch/arm/boot/dts/stm32f746.dtsi index 973698bc9ef4..dc868e6da40e 100644 --- a/arch/arm/boot/dts/stm32f746.dtsi +++ b/arch/arm/boot/dts/stm32f746.dtsi @@ -257,23 +257,6 @@ status = "disabled"; }; - can3: can@40003400 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40003400 0x200>; - interrupts = <104>, <105>, <106>, <107>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN3)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; - st,gcan = <&gcan3>; - status = "disabled"; - }; - - gcan3: gcan@40003600 { - compatible = "st,stm32f4-gcan", "syscon"; - reg = <0x40003600 0x200>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN3)>; - }; - usart2: serial@40004400 { compatible = "st,stm32f7-uart"; reg = <0x40004400 0x400>; @@ -354,36 +337,6 @@ status = "disabled"; }; - can1: can@40006400 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40006400 0x200>; - interrupts = <19>, <20>, <21>, <22>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN1)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; - st,can-primary; - st,gcan = <&gcan1>; - status = "disabled"; - }; - - gcan1: gcan@40006600 { - compatible = "st,stm32f4-gcan", "syscon"; - reg = <0x40006600 0x200>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN1)>; - }; - - can2: can@40006800 { - compatible = "st,stm32f4-bxcan"; - reg = <0x40006800 0x200>; - interrupts = <63>, <64>, <65>, <66>; - interrupt-names = "tx", "rx0", "rx1", "sce"; - resets = <&rcc STM32F7_APB1_RESET(CAN2)>; - clocks = <&rcc 0 STM32F7_APB1_CLOCK(CAN2)>; - st,can-secondary; - st,gcan = <&gcan1>; - status = "disabled"; - }; - cec: cec@40006c00 { compatible = "st,stm32-cec"; reg = <0x40006C00 0x400>; -- GitLab From 58caa2a51ad4fd21763696cc6c4defc9fc1b4b4f Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Fri, 12 May 2023 17:22:43 +0800 Subject: [PATCH 5136/5631] RDMA/hns: Fix timeout attr in query qp for HIP08 On HIP08, the queried timeout attr is different from the timeout attr configured by the user. It is found by rdma-core testcase test_rdmacm_async_traffic: ====================================================================== FAIL: test_rdmacm_async_traffic (tests.test_rdmacm.CMTestCase) ---------------------------------------------------------------------- Traceback (most recent call last): File "./tests/test_rdmacm.py", line 33, in test_rdmacm_async_traffic self.two_nodes_rdmacm_traffic(CMAsyncConnection, self.rdmacm_traffic, File "./tests/base.py", line 382, in two_nodes_rdmacm_traffic raise(res) AssertionError Fixes: 926a01dc000d ("RDMA/hns: Add QP operations support for hip08 SoC") Link: https://lore.kernel.org/r/20230512092245.344442-2-huangjunxian6@hisilicon.com Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 17 ++++++++++++++--- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 2 ++ 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 84f1167de1d9..3a1c90406ed9 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -5012,7 +5012,6 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp, static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) { #define QP_ACK_TIMEOUT_MAX_HIP08 20 -#define QP_ACK_TIMEOUT_OFFSET 10 #define QP_ACK_TIMEOUT_MAX 31 if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) { @@ -5021,7 +5020,7 @@ static bool check_qp_timeout_cfg_range(struct hns_roce_dev *hr_dev, u8 *timeout) "local ACK timeout shall be 0 to 20.\n"); return false; } - *timeout += QP_ACK_TIMEOUT_OFFSET; + *timeout += HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; } else if (hr_dev->pci_dev->revision > PCI_REVISION_ID_HIP08) { if (*timeout > QP_ACK_TIMEOUT_MAX) { ibdev_warn(&hr_dev->ib_dev, @@ -5307,6 +5306,18 @@ static int hns_roce_v2_query_qpc(struct hns_roce_dev *hr_dev, u32 qpn, return ret; } +static u8 get_qp_timeout_attr(struct hns_roce_dev *hr_dev, + struct hns_roce_v2_qp_context *context) +{ + u8 timeout; + + timeout = (u8)hr_reg_read(context, QPC_AT); + if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) + timeout -= HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08; + + return timeout; +} + static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) @@ -5384,7 +5395,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, qp_attr->max_dest_rd_atomic = 1 << hr_reg_read(&context, QPC_RR_MAX); qp_attr->min_rnr_timer = (u8)hr_reg_read(&context, QPC_MIN_RNR_TIME); - qp_attr->timeout = (u8)hr_reg_read(&context, QPC_AT); + qp_attr->timeout = get_qp_timeout_attr(hr_dev, &context); qp_attr->retry_cnt = hr_reg_read(&context, QPC_RETRY_NUM_INIT); qp_attr->rnr_retry = hr_reg_read(&context, QPC_RNR_NUM_INIT); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1b44d2434ab4..7033eae2407c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -44,6 +44,8 @@ #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 +#define HNS_ROCE_V2_QP_ACK_TIMEOUT_OFS_HIP08 10 + #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 -- GitLab From 7f3969b14f356dd65fa95b3528eb05c32e68bc06 Mon Sep 17 00:00:00 2001 From: Chengchang Tang Date: Fri, 12 May 2023 17:22:44 +0800 Subject: [PATCH 5137/5631] RDMA/hns: Fix base address table allocation For hns, the specification of an entry like resource (E.g. WQE/CQE/EQE) depends on BT page size, buf page size and hopnum. For user mode, the buf page size depends on UMEM. Therefore, the actual specification is controlled by BT page size and hopnum. The current BT page size and hopnum are obtained from firmware. This makes the driver inflexible and introduces unnecessary constraints. Resource allocation failures occur in many scenarios. This patch will calculate whether the BT page size set by firmware is sufficient before allocating BT, and increase the BT page size if it is insufficient. Fixes: 1133401412a9 ("RDMA/hns: Optimize base address table config flow for qp buffer") Link: https://lore.kernel.org/r/20230512092245.344442-3-huangjunxian6@hisilicon.com Signed-off-by: Chengchang Tang Signed-off-by: Junxian Huang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_mr.c | 43 +++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index 37a5cf62f88b..14376490ac22 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -33,6 +33,7 @@ #include #include +#include #include "hns_roce_device.h" #include "hns_roce_cmd.h" #include "hns_roce_hem.h" @@ -909,6 +910,44 @@ static int mtr_init_buf_cfg(struct hns_roce_dev *hr_dev, return page_cnt; } +static u64 cal_pages_per_l1ba(unsigned int ba_per_bt, unsigned int hopnum) +{ + return int_pow(ba_per_bt, hopnum - 1); +} + +static unsigned int cal_best_bt_pg_sz(struct hns_roce_dev *hr_dev, + struct hns_roce_mtr *mtr, + unsigned int pg_shift) +{ + unsigned long cap = hr_dev->caps.page_size_cap; + struct hns_roce_buf_region *re; + unsigned int pgs_per_l1ba; + unsigned int ba_per_bt; + unsigned int ba_num; + int i; + + for_each_set_bit_from(pg_shift, &cap, sizeof(cap) * BITS_PER_BYTE) { + if (!(BIT(pg_shift) & cap)) + continue; + + ba_per_bt = BIT(pg_shift) / BA_BYTE_LEN; + ba_num = 0; + for (i = 0; i < mtr->hem_cfg.region_count; i++) { + re = &mtr->hem_cfg.region[i]; + if (re->hopnum == 0) + continue; + + pgs_per_l1ba = cal_pages_per_l1ba(ba_per_bt, re->hopnum); + ba_num += DIV_ROUND_UP(re->count, pgs_per_l1ba); + } + + if (ba_num <= ba_per_bt) + return pg_shift; + } + + return 0; +} + static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, unsigned int ba_page_shift) { @@ -917,6 +956,10 @@ static int mtr_alloc_mtt(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, hns_roce_hem_list_init(&mtr->hem_list); if (!cfg->is_direct) { + ba_page_shift = cal_best_bt_pg_sz(hr_dev, mtr, ba_page_shift); + if (!ba_page_shift) + return -ERANGE; + ret = hns_roce_hem_list_request(hr_dev, &mtr->hem_list, cfg->region, cfg->region_count, ba_page_shift); -- GitLab From 56518a603fd2bf74762d176ac980572db84a3e14 Mon Sep 17 00:00:00 2001 From: Yangyang Li Date: Fri, 12 May 2023 17:22:45 +0800 Subject: [PATCH 5138/5631] RDMA/hns: Modify the value of long message loopback slice Long message loopback slice is used for achieving traffic balance between QPs. It prevents the problem that QPs with large traffic occupying the hardware pipeline for a long time and QPs with small traffic cannot be scheduled. Currently, its maximum value is set to 16K, which means only after a QP sends 16K will the second QP be scheduled. This value is too large, which will lead to unbalanced traffic scheduling, and thus it needs to be modified. The setting range of the long message loopback slice is modified to be from 1024 (the lower limit supported by hardware) to mtu. Actual testing shows that this value can significantly reduce error in hardware traffic scheduling. This solution is compatible with both HIP08 and HIP09. The modified lp_pktn_ini has a maximum value of 2 (when mtu is 256), so the range checking code for lp_pktn_ini is no longer necessary and needs to be deleted. Fixes: 0e60778efb07 ("RDMA/hns: Modify the value of MAX_LP_MSG_LEN to meet hardware compatibility") Link: https://lore.kernel.org/r/20230512092245.344442-4-huangjunxian6@hisilicon.com Signed-off-by: Yangyang Li Signed-off-by: Junxian Huang Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 3a1c90406ed9..d4c6b9bc0a4e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4583,11 +4583,9 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp, mtu = ib_mtu_enum_to_int(ib_mtu); if (WARN_ON(mtu <= 0)) return -EINVAL; -#define MAX_LP_MSG_LEN 16384 - /* MTU * (2 ^ LP_PKTN_INI) shouldn't be bigger than 16KB */ - lp_pktn_ini = ilog2(MAX_LP_MSG_LEN / mtu); - if (WARN_ON(lp_pktn_ini >= 0xF)) - return -EINVAL; +#define MIN_LP_MSG_LEN 1024 + /* mtu * (2 ^ lp_pktn_ini) should be in the range of 1024 to mtu */ + lp_pktn_ini = ilog2(max(mtu, MIN_LP_MSG_LEN) / mtu); if (attr_mask & IB_QP_PATH_MTU) { hr_reg_write(context, QPC_MTU, ib_mtu); -- GitLab From be243bacfb25f5219f2396d787408e8cf1301dd1 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:06 +0800 Subject: [PATCH 5139/5631] rethook: use preempt_{disable, enable}_notrace in rethook_trampoline_handler This patch replaces preempt_{disable, enable} with its corresponding notrace version in rethook_trampoline_handler so no worries about stack recursion or overflow introduced by preempt_count_{add, sub} under fprobe + rethook context. Link: https://lore.kernel.org/all/20230517034510.15639-2-zegao@tencent.com/ Fixes: 54ecbe6f1ed5 ("rethook: Add a generic return hook") Signed-off-by: Ze Gao Acked-by: Masami Hiramatsu (Google) Cc: Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/rethook.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 32c3dfdb4d6a..60f6cb2b486b 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -288,7 +288,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, * These loops must be protected from rethook_free_rcu() because those * are accessing 'rhn->rethook'. */ - preempt_disable(); + preempt_disable_notrace(); /* * Run the handler on the shadow stack. Do not unlink the list here because @@ -321,7 +321,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, first = first->next; rethook_recycle(rhn); } - preempt_enable(); + preempt_enable_notrace(); return correct_ret_addr; } -- GitLab From 3cc4e2c5fbae84e5033723fb7e350bc6c164e3a2 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:07 +0800 Subject: [PATCH 5140/5631] fprobe: make fprobe_kprobe_handler recursion free Current implementation calls kprobe related functions before doing ftrace recursion check in fprobe_kprobe_handler, which opens door to kernel crash due to stack recursion if preempt_count_{add, sub} is traceable in kprobe_busy_{begin, end}. Things goes like this without this patch quoted from Steven: " fprobe_kprobe_handler() { kprobe_busy_begin() { preempt_disable() { preempt_count_add() { <-- trace fprobe_kprobe_handler() { [ wash, rinse, repeat, CRASH!!! ] " By refactoring the common part out of fprobe_kprobe_handler and fprobe_handler and call ftrace recursion detection at the very beginning, the whole fprobe_kprobe_handler is free from recursion. [ Fix the indentation of __fprobe_handler() parameters. ] Link: https://lore.kernel.org/all/20230517034510.15639-3-zegao@tencent.com/ Fixes: ab51e15d535e ("fprobe: Introduce FPROBE_FL_KPROBE_SHARED flag for fprobe") Signed-off-by: Ze Gao Acked-by: Masami Hiramatsu (Google) Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 59 ++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 15 deletions(-) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 293184227394..7a692c02f787 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -20,30 +20,22 @@ struct fprobe_rethook_node { char data[]; }; -static void fprobe_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct ftrace_regs *fregs) +static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct fprobe_rethook_node *fpr; struct rethook_node *rh = NULL; struct fprobe *fp; void *entry_data = NULL; - int bit, ret = 0; + int ret = 0; fp = container_of(ops, struct fprobe, ops); - if (fprobe_disabled(fp)) - return; - - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) { - fp->nmissed++; - return; - } if (fp->exit_handler) { rh = rethook_try_get(fp->rethook); if (!rh) { fp->nmissed++; - goto out; + return; } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; @@ -61,23 +53,60 @@ static void fprobe_handler(unsigned long ip, unsigned long parent_ip, else rethook_hook(rh, ftrace_get_regs(fregs), true); } -out: +} + +static void fprobe_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + __fprobe_handler(ip, parent_ip, ops, fregs); ftrace_test_recursion_unlock(bit); + } NOKPROBE_SYMBOL(fprobe_handler); static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { - struct fprobe *fp = container_of(ops, struct fprobe, ops); + struct fprobe *fp; + int bit; + + fp = container_of(ops, struct fprobe, ops); + if (fprobe_disabled(fp)) + return; + + /* recursion detection has to go before any traceable function and + * all functions called before this point should be marked as notrace + */ + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } if (unlikely(kprobe_running())) { fp->nmissed++; return; } + kprobe_busy_begin(); - fprobe_handler(ip, parent_ip, ops, fregs); + __fprobe_handler(ip, parent_ip, ops, fregs); kprobe_busy_end(); + ftrace_test_recursion_unlock(bit); } static void fprobe_exit_handler(struct rethook_node *rh, void *data, -- GitLab From 2752741080f84f9b2fc93fa92735315d10a415bf Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:08 +0800 Subject: [PATCH 5141/5631] fprobe: add recursion detection in fprobe_exit_handler fprobe_hander and fprobe_kprobe_handler has guarded ftrace recursion detection but fprobe_exit_handler has not, which possibly introduce recursive calls if the fprobe exit callback calls any traceable functions. Checking in fprobe_hander or fprobe_kprobe_handler is not enough and misses this case. So add recursion free guard the same way as fprobe_hander. Since ftrace recursion check does not employ ip(s), so here use entry_ip and entry_parent_ip the same as fprobe_handler. Link: https://lore.kernel.org/all/20230517034510.15639-4-zegao@tencent.com/ Fixes: 5b0ab78998e3 ("fprobe: Add exit_handler support") Signed-off-by: Ze Gao Cc: stable@vger.kernel.org Acked-by: Masami Hiramatsu (Google) Signed-off-by: Masami Hiramatsu (Google) --- kernel/trace/fprobe.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 7a692c02f787..18d36842faf5 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -17,6 +17,7 @@ struct fprobe_rethook_node { struct rethook_node node; unsigned long entry_ip; + unsigned long entry_parent_ip; char data[]; }; @@ -39,6 +40,7 @@ static inline void __fprobe_handler(unsigned long ip, unsigned long parent_ip, } fpr = container_of(rh, struct fprobe_rethook_node, node); fpr->entry_ip = ip; + fpr->entry_parent_ip = parent_ip; if (fp->entry_data_size) entry_data = fpr->data; } @@ -114,14 +116,26 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data, { struct fprobe *fp = (struct fprobe *)data; struct fprobe_rethook_node *fpr; + int bit; if (!fp || fprobe_disabled(fp)) return; fpr = container_of(rh, struct fprobe_rethook_node, node); + /* + * we need to assure no calls to traceable functions in-between the + * end of fprobe_handler and the beginning of fprobe_exit_handler. + */ + bit = ftrace_test_recursion_trylock(fpr->entry_ip, fpr->entry_parent_ip); + if (bit < 0) { + fp->nmissed++; + return; + } + fp->exit_handler(fp, fpr->entry_ip, regs, fp->entry_data_size ? (void *)fpr->data : NULL); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(fprobe_exit_handler); -- GitLab From 571a2a50a8fc546145ffd3bf673547e9fe128ed2 Mon Sep 17 00:00:00 2001 From: Ze Gao Date: Wed, 17 May 2023 11:45:09 +0800 Subject: [PATCH 5142/5631] rethook, fprobe: do not trace rethook related functions These functions are already marked as NOKPROBE to prevent recursion and we have the same reason to blacklist them if rethook is used with fprobe, since they are beyond the recursion-free region ftrace can guard. Link: https://lore.kernel.org/all/20230517034510.15639-5-zegao@tencent.com/ Fixes: f3a112c0c40d ("x86,rethook,kprobes: Replace kretprobe with rethook on x86") Signed-off-by: Ze Gao Reviewed-by: Steven Rostedt (Google) Acked-by: Masami Hiramatsu (Google) Cc: stable@vger.kernel.org Signed-off-by: Masami Hiramatsu (Google) --- arch/riscv/kernel/probes/Makefile | 2 ++ arch/s390/kernel/Makefile | 1 + arch/x86/kernel/Makefile | 1 + 3 files changed, 4 insertions(+) diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile index c40139e9ca47..8265ff497977 100644 --- a/arch/riscv/kernel/probes/Makefile +++ b/arch/riscv/kernel/probes/Makefile @@ -4,3 +4,5 @@ obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o obj-$(CONFIG_KPROBES_ON_FTRACE) += ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 8983837b3565..6b2a051e1f8a 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -10,6 +10,7 @@ CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) # Do not trace early setup code CFLAGS_REMOVE_early.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index dd61752f4c96..4070a01c11b7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -17,6 +17,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_rethook.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n -- GitLab From 0257d9908d38c0b1669af4bb1bc4dbca1f273fe6 Mon Sep 17 00:00:00 2001 From: Peng Zhang Date: Fri, 5 May 2023 22:58:29 +0800 Subject: [PATCH 5143/5631] maple_tree: make maple state reusable after mas_empty_area() Make mas->min and mas->max point to a node range instead of a leaf entry range. This allows mas to still be usable after mas_empty_area() returns. Users would get unexpected results from other operations on the maple state after calling the affected function. For example, x86 MAP_32BIT mmap() acts as if there is no suitable gap when there should be one. Link: https://lkml.kernel.org/r/20230505145829.74574-1-zhangpeng.00@bytedance.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Peng Zhang Reported-by: "Edgecombe, Rick P" Reported-by: Tad Reported-by: Michael Keyes Link: https://lore.kernel.org/linux-mm/32f156ba80010fd97dbaf0a0cdfc84366608624d.camel@intel.com/ Link: https://lore.kernel.org/linux-mm/e6108286ac025c268964a7ead3aab9899f9bc6e9.camel@spotco.us/ Reviewed-by: Liam R. Howlett Tested-by: Rick Edgecombe Cc: Signed-off-by: Andrew Morton --- lib/maple_tree.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 110a36479dce..8ebc43d4cc8c 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5317,15 +5317,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min, mt = mte_node_type(mas->node); pivots = ma_pivots(mas_mn(mas), mt); - if (offset) - mas->min = pivots[offset - 1] + 1; - - if (offset < mt_pivots[mt]) - mas->max = pivots[offset]; - - if (mas->index < mas->min) - mas->index = mas->min; - + min = mas_safe_min(mas, pivots, offset); + if (mas->index < min) + mas->index = min; mas->last = mas->index + size - 1; return 0; } -- GitLab From 26e239b37ebdfd189a2e6f94d3407e70313348bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Joan=20Bruguera=20Mic=C3=B3?= Date: Wed, 3 May 2023 01:32:32 +0000 Subject: [PATCH 5144/5631] mm: shrinkers: fix race condition on debugfs cleanup MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When something registers and unregisters many shrinkers, such as: for x in $(seq 10000); do unshare -Ui true; done Sometimes the following error is printed to the kernel log: debugfs: Directory '...' with parent 'shrinker' already present! This occurs since commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") / v6.2: Since the call to `debugfs_remove_recursive` was moved outside the `shrinker_rwsem`/`shrinker_mutex` lock, but the call to `ida_free` stayed inside, a newly registered shrinker can be re-assigned that ID and attempt to create the debugfs directory before the directory from the previous shrinker has been removed. The locking changes in commit f95bdb700bc6 ("mm: vmscan: make global slab shrink lockless") made the race condition more likely, though it existed before then. Commit badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") could be reverted since the issue is addressed should no longer occur since the count and scan operations are lockless since commit 20cd1892fcc3 ("mm: shrinkers: make count and scan in shrinker debugfs lockless"). However, since this is a contended lock, prefer instead moving `ida_free` outside the lock to avoid the race. Link: https://lkml.kernel.org/r/20230503013232.299211-1-joanbrugueram@gmail.com Fixes: badc28d4924b ("mm: shrinkers: fix deadlock in shrinker debugfs") Signed-off-by: Joan Bruguera Micó Cc: Qi Zheng Cc: Roman Gushchin Signed-off-by: Andrew Morton --- include/linux/shrinker.h | 13 +++++++++++-- mm/shrinker_debug.c | 15 ++++++++++----- mm/vmscan.c | 5 +++-- 3 files changed, 24 insertions(+), 9 deletions(-) diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 7bde8e1c228a..224293b2dd06 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,7 +107,10 @@ extern void synchronize_shrinkers(void); #ifdef CONFIG_SHRINKER_DEBUG extern int shrinker_debugfs_add(struct shrinker *shrinker); -extern struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker); +extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id); +extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id); extern int __printf(2, 3) shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...); #else /* CONFIG_SHRINKER_DEBUG */ @@ -115,10 +118,16 @@ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } -static inline struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { + *debugfs_id = -1; return NULL; } +static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, + int debugfs_id) +{ +} static inline __printf(2, 3) int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) { diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 3f83b10c5031..fe10436d9911 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -237,7 +237,8 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) } EXPORT_SYMBOL(shrinker_debugfs_rename); -struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) +struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, + int *debugfs_id) { struct dentry *entry = shrinker->debugfs_entry; @@ -246,14 +247,18 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker) kfree_const(shrinker->name); shrinker->name = NULL; - if (entry) { - ida_free(&shrinker_debugfs_ida, shrinker->debugfs_id); - shrinker->debugfs_entry = NULL; - } + *debugfs_id = entry ? shrinker->debugfs_id : -1; + shrinker->debugfs_entry = NULL; return entry; } +void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) +{ + debugfs_remove_recursive(debugfs_entry); + ida_free(&shrinker_debugfs_ida, debugfs_id); +} + static int __init shrinker_debugfs_init(void) { struct shrinker *shrinker; diff --git a/mm/vmscan.c b/mm/vmscan.c index d257916f39e5..6d0cd2840cf0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -805,6 +805,7 @@ EXPORT_SYMBOL(register_shrinker); void unregister_shrinker(struct shrinker *shrinker) { struct dentry *debugfs_entry; + int debugfs_id; if (!(shrinker->flags & SHRINKER_REGISTERED)) return; @@ -814,13 +815,13 @@ void unregister_shrinker(struct shrinker *shrinker) shrinker->flags &= ~SHRINKER_REGISTERED; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_remove(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); mutex_unlock(&shrinker_mutex); atomic_inc(&shrinker_srcu_generation); synchronize_srcu(&shrinker_srcu); - debugfs_remove_recursive(debugfs_entry); + shrinker_debugfs_remove(debugfs_entry, debugfs_id); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; -- GitLab From d461aac924b937bcb4fd0ca1242b3ef6868ecddd Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Fri, 5 May 2023 11:50:54 -0700 Subject: [PATCH 5145/5631] zsmalloc: move LRU update from zs_map_object() to zs_malloc() Under memory pressure, we sometimes observe the following crash: [ 5694.832838] ------------[ cut here ]------------ [ 5694.842093] list_del corruption, ffff888014b6a448->next is LIST_POISON1 (dead000000000100) [ 5694.858677] WARNING: CPU: 33 PID: 418824 at lib/list_debug.c:47 __list_del_entry_valid+0x42/0x80 [ 5694.961820] CPU: 33 PID: 418824 Comm: fuse_counters.s Kdump: loaded Tainted: G S 5.19.0-0_fbk3_rc3_hoangnhatpzsdynshrv41_10870_g85a9558a25de #1 [ 5694.990194] Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM16 05/24/2021 [ 5695.007072] RIP: 0010:__list_del_entry_valid+0x42/0x80 [ 5695.017351] Code: 08 48 83 c2 22 48 39 d0 74 24 48 8b 10 48 39 f2 75 2c 48 8b 51 08 b0 01 48 39 f2 75 34 c3 48 c7 c7 55 d7 78 82 e8 4e 45 3b 00 <0f> 0b eb 31 48 c7 c7 27 a8 70 82 e8 3e 45 3b 00 0f 0b eb 21 48 c7 [ 5695.054919] RSP: 0018:ffffc90027aef4f0 EFLAGS: 00010246 [ 5695.065366] RAX: 41fe484987275300 RBX: ffff888008988180 RCX: 0000000000000000 [ 5695.079636] RDX: ffff88886006c280 RSI: ffff888860060480 RDI: ffff888860060480 [ 5695.093904] RBP: 0000000000000002 R08: 0000000000000000 R09: ffffc90027aef370 [ 5695.108175] R10: 0000000000000000 R11: ffffffff82fdf1c0 R12: 0000000010000002 [ 5695.122447] R13: ffff888014b6a448 R14: ffff888014b6a420 R15: 00000000138dc240 [ 5695.136717] FS: 00007f23a7d3f740(0000) GS:ffff888860040000(0000) knlGS:0000000000000000 [ 5695.152899] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 5695.164388] CR2: 0000560ceaab6ac0 CR3: 000000001c06c001 CR4: 00000000007706e0 [ 5695.178659] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 5695.192927] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 5695.207197] PKRU: 55555554 [ 5695.212602] Call Trace: [ 5695.217486] [ 5695.221674] zs_map_object+0x91/0x270 [ 5695.229000] zswap_frontswap_store+0x33d/0x870 [ 5695.237885] ? do_raw_spin_lock+0x5d/0xa0 [ 5695.245899] __frontswap_store+0x51/0xb0 [ 5695.253742] swap_writepage+0x3c/0x60 [ 5695.261063] shrink_page_list+0x738/0x1230 [ 5695.269255] shrink_lruvec+0x5ec/0xcd0 [ 5695.276749] ? shrink_slab+0x187/0x5f0 [ 5695.284240] ? mem_cgroup_iter+0x6e/0x120 [ 5695.292255] shrink_node+0x293/0x7b0 [ 5695.299402] do_try_to_free_pages+0xea/0x550 [ 5695.307940] try_to_free_pages+0x19a/0x490 [ 5695.316126] __folio_alloc+0x19ff/0x3e40 [ 5695.323971] ? __filemap_get_folio+0x8a/0x4e0 [ 5695.332681] ? walk_component+0x2a8/0xb50 [ 5695.340697] ? generic_permission+0xda/0x2a0 [ 5695.349231] ? __filemap_get_folio+0x8a/0x4e0 [ 5695.357940] ? walk_component+0x2a8/0xb50 [ 5695.365955] vma_alloc_folio+0x10e/0x570 [ 5695.373796] ? walk_component+0x52/0xb50 [ 5695.381634] wp_page_copy+0x38c/0xc10 [ 5695.388953] ? filename_lookup+0x378/0xbc0 [ 5695.397140] handle_mm_fault+0x87f/0x1800 [ 5695.405157] do_user_addr_fault+0x1bd/0x570 [ 5695.413520] exc_page_fault+0x5d/0x110 [ 5695.421017] asm_exc_page_fault+0x22/0x30 After some investigation, I have found the following issue: unlike other zswap backends, zsmalloc performs the LRU list update at the object mapping time, rather than when the slot for the object is allocated. This deviation was discussed and agreed upon during the review process of the zsmalloc writeback patch series: https://lore.kernel.org/lkml/Y3flcAXNxxrvy3ZH@cmpxchg.org/ Unfortunately, this introduces a subtle bug that occurs when there is a concurrent store and reclaim, which interleave as follows: zswap_frontswap_store() shrink_worker() zs_malloc() zs_zpool_shrink() spin_lock(&pool->lock) zs_reclaim_page() zspage = find_get_zspage() spin_unlock(&pool->lock) spin_lock(&pool->lock) zspage = list_first_entry(&pool->lru) list_del(&zspage->lru) zspage->lru.next = LIST_POISON1 zspage->lru.prev = LIST_POISON2 spin_unlock(&pool->lock) zs_map_object() spin_lock(&pool->lock) if (!list_empty(&zspage->lru)) list_del(&zspage->lru) CHECK_DATA_CORRUPTION(next == LIST_POISON1) /* BOOM */ With the current upstream code, this issue rarely happens. zswap only triggers writeback when the pool is already full, at which point all further store attempts are short-circuited. This creates an implicit pseudo-serialization between reclaim and store. I am working on a new zswap shrinking mechanism, which makes interleaving reclaim and store more likely, exposing this bug. zbud and z3fold do not have this problem, because they perform the LRU list update in the alloc function, while still holding the pool's lock. This patch fixes the aforementioned bug by moving the LRU update back to zs_malloc(), analogous to zbud and z3fold. Link: https://lkml.kernel.org/r/20230505185054.2417128-1-nphamcs@gmail.com Fixes: 64f768c6b32e ("zsmalloc: add a LRU to zs_pool to keep track of zspages in LRU order") Signed-off-by: Nhat Pham Suggested-by: Johannes Weiner Acked-by: Johannes Weiner Reviewed-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Dan Streetman Cc: Nitin Gupta Cc: Seth Jennings Cc: Vitaly Wool Cc: Signed-off-by: Andrew Morton --- mm/zsmalloc.c | 36 +++++++++--------------------------- 1 file changed, 9 insertions(+), 27 deletions(-) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 44ddaf5d601e..02f7f414aade 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1331,31 +1331,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); -#ifdef CONFIG_ZPOOL - /* - * Move the zspage to front of pool's LRU. - * - * Note that this is swap-specific, so by definition there are no ongoing - * accesses to the memory while the page is swapped out that would make - * it "hot". A new entry is hot, then ages to the tail until it gets either - * written back or swaps back in. - * - * Furthermore, map is also called during writeback. We must not put an - * isolated page on the LRU mid-reclaim. - * - * As a result, only update the LRU when the page is mapped for write - * when it's first instantiated. - * - * This is a deviation from the other backends, which perform this update - * in the allocation function (zbud_alloc, z3fold_alloc). - */ - if (mm == ZS_MM_WO) { - if (!list_empty(&zspage->lru)) - list_del(&zspage->lru); - list_add(&zspage->lru, &pool->lru); - } -#endif - /* * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls @@ -1525,9 +1500,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, ZS_OBJS_INUSE, 1); - spin_unlock(&pool->lock); - return handle; + goto out; } spin_unlock(&pool->lock); @@ -1550,6 +1524,14 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); +out: +#ifdef CONFIG_ZPOOL + /* Add/move zspage to beginning of LRU */ + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); +#endif + spin_unlock(&pool->lock); return handle; -- GitLab From 7581495ac82d6cb073609284c7f7186a48021d1e Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 5 May 2023 13:51:27 +1000 Subject: [PATCH 5146/5631] mm: kfence: fix false positives on big endian Since commit 1ba3cbf3ec3b ("mm: kfence: improve the performance of __kfence_alloc() and __kfence_free()"), kfence reports failures in random places at boot on big endian machines. The problem is that the new KFENCE_CANARY_PATTERN_U64 encodes the address of each byte in its value, so it needs to be byte swapped on big endian machines. The compiler is smart enough to do the le64_to_cpu() at compile time, so there is no runtime overhead. Link: https://lkml.kernel.org/r/20230505035127.195387-1-mpe@ellerman.id.au Fixes: 1ba3cbf3ec3b ("mm: kfence: improve the performance of __kfence_alloc() and __kfence_free()") Signed-off-by: Michael Ellerman Reviewed-by: Alexander Potapenko Reviewed-by: Marco Elver Cc: Peng Zhang Cc: David Laight Signed-off-by: Andrew Morton --- mm/kfence/kfence.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 2aafc46a4aaf..392fb273e7bd 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -29,7 +29,7 @@ * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ -#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(0x0706050403020100)) +#define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 -- GitLab From 04fc7816089c5a32c29a04ec94b998e219dfb946 Mon Sep 17 00:00:00 2001 From: Domenico Cerasuolo Date: Wed, 3 May 2023 17:12:00 +0200 Subject: [PATCH 5147/5631] mm: fix zswap writeback race condition The zswap writeback mechanism can cause a race condition resulting in memory corruption, where a swapped out page gets swapped in with data that was written to a different page. The race unfolds like this: 1. a page with data A and swap offset X is stored in zswap 2. page A is removed off the LRU by zpool driver for writeback in zswap-shrink work, data for A is mapped by zpool driver 3. user space program faults and invalidates page entry A, offset X is considered free 4. kswapd stores page B at offset X in zswap (zswap could also be full, if so, page B would then be IOed to X, then skip step 5.) 5. entry A is replaced by B in tree->rbroot, this doesn't affect the local reference held by zswap-shrink work 6. zswap-shrink work writes back A at X, and frees zswap entry A 7. swapin of slot X brings A in memory instead of B The fix: Once the swap page cache has been allocated (case ZSWAP_SWAPCACHE_NEW), zswap-shrink work just checks that the local zswap_entry reference is still the same as the one in the tree. If it's not the same it means that it's either been invalidated or replaced, in both cases the writeback is aborted because the local entry contains stale data. Reproducer: I originally found this by running `stress` overnight to validate my work on the zswap writeback mechanism, it manifested after hours on my test machine. The key to make it happen is having zswap writebacks, so whatever setup pumps /sys/kernel/debug/zswap/written_back_pages should do the trick. In order to reproduce this faster on a vm, I setup a system with ~100M of available memory and a 500M swap file, then running `stress --vm 1 --vm-bytes 300000000 --vm-stride 4000` makes it happen in matter of tens of minutes. One can speed things up even more by swinging /sys/module/zswap/parameters/max_pool_percent up and down between, say, 20 and 1; this makes it reproduce in tens of seconds. It's crucial to set `--vm-stride` to something other than 4096 otherwise `stress` won't realize that memory has been corrupted because all pages would have the same data. Link: https://lkml.kernel.org/r/20230503151200.19707-1-cerasuolodomenico@gmail.com Signed-off-by: Domenico Cerasuolo Acked-by: Johannes Weiner Reviewed-by: Chris Li (Google) Cc: Dan Streetman Cc: Johannes Weiner Cc: Minchan Kim Cc: Nitin Gupta Cc: Seth Jennings Cc: Vitaly Wool Cc: Signed-off-by: Andrew Morton --- mm/zswap.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/mm/zswap.c b/mm/zswap.c index e1e621d0b6a0..59da2a415fbb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1020,6 +1020,22 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) goto fail; case ZSWAP_SWAPCACHE_NEW: /* page is locked */ + /* + * Having a local reference to the zswap entry doesn't exclude + * swapping from invalidating and recycling the swap slot. Once + * the swapcache is secured against concurrent swapping to and + * from the slot, recheck that the entry is still current before + * writing. + */ + spin_lock(&tree->lock); + if (zswap_rb_search(&tree->rbroot, entry->offset) != entry) { + spin_unlock(&tree->lock); + delete_from_swap_cache(page_folio(page)); + ret = -ENOMEM; + goto fail; + } + spin_unlock(&tree->lock); + /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; -- GitLab From 9b5a04ac3ad9898c4745cba46ea26de74ba56a8e Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Wed, 10 May 2023 00:29:56 +0900 Subject: [PATCH 5148/5631] nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode() During unmount process of nilfs2, nothing holds nilfs_root structure after nilfs2 detaches its writer in nilfs_detach_log_writer(). However, since nilfs_evict_inode() uses nilfs_root for some cleanup operations, it may cause use-after-free read if inodes are left in "garbage_list" and released by nilfs_dispose_list() at the end of nilfs_detach_log_writer(). Fix this issue by modifying nilfs_evict_inode() to only clear inode without additional metadata changes that use nilfs_root if the file system is degraded to read-only or the writer is detached. Link: https://lkml.kernel.org/r/20230509152956.8313-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+78d4495558999f55d1da@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000099e5ac05fb1c3b85@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/inode.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 1310d2d5feb3..a8ce522ac747 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -917,6 +917,7 @@ void nilfs_evict_inode(struct inode *inode) struct nilfs_transaction_info ti; struct super_block *sb = inode->i_sb; struct nilfs_inode_info *ii = NILFS_I(inode); + struct the_nilfs *nilfs; int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { @@ -929,6 +930,23 @@ void nilfs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); + nilfs = sb->s_fs_info; + if (unlikely(sb_rdonly(sb) || !nilfs->ns_writer)) { + /* + * If this inode is about to be disposed after the file system + * has been degraded to read-only due to file system corruption + * or after the writer has been detached, do not make any + * changes that cause writes, just clear it. + * Do this check after read-locking ns_segctor_sem by + * nilfs_transaction_begin() in order to avoid a race with + * the writer detach operation. + */ + clear_inode(inode); + nilfs_clear_inode(inode); + nilfs_transaction_abort(sb); + return; + } + /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); -- GitLab From 158fb07ba6e77a21f46c3e9c5be44ebd8c4dd2cc Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Tue, 9 May 2023 09:48:34 +0200 Subject: [PATCH 5149/5631] MAINTAINERS: repair pattern in DIALOG SEMICONDUCTOR DRIVERS Commit 361104b05684c ("dt-bindings: mfd: Convert da9063 to yaml") converts da9063.txt to dlg,da9063.yaml and adds a new file pattern in MAINTAINERS. Unfortunately, the file pattern matches da90*.yaml, but the yaml file is prefixed with dlg,da90. Hence, ./scripts/get_maintainer.pl --self-test=patterns complains about a broken file pattern. Repair this file pattern in DIALOG SEMICONDUCTOR DRIVERS. Link: https://lkml.kernel.org/r/20230509074834.21521-1-lukas.bulwahn@gmail.com Fixes: 361104b05684c ("dt-bindings: mfd: Convert da9063 to yaml") Signed-off-by: Lukas Bulwahn Acked-by: Conor Dooley Cc: Lee Jones Signed-off-by: Andrew Morton --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7e0b87d5aa2e..21d66f969602 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6019,7 +6019,7 @@ W: http://www.dialog-semiconductor.com/products F: Documentation/devicetree/bindings/input/da90??-onkey.txt F: Documentation/devicetree/bindings/input/dlg,da72??.txt F: Documentation/devicetree/bindings/mfd/da90*.txt -F: Documentation/devicetree/bindings/mfd/da90*.yaml +F: Documentation/devicetree/bindings/mfd/dlg,da90*.yaml F: Documentation/devicetree/bindings/regulator/dlg,da9*.yaml F: Documentation/devicetree/bindings/regulator/da92*.txt F: Documentation/devicetree/bindings/regulator/slg51000.txt -- GitLab From c7394fa9aa4ccd4e477626c4f7aef0b360c92efb Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Wed, 10 May 2023 13:28:11 +0100 Subject: [PATCH 5150/5631] MAINTAINERS: Cleanup Arm Display IP maintainers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some people have moved to different roles and are no longer involved in the upstream development. As there is only one person left, remove the mailing list as well as it serves no purpose. Link: https://lkml.kernel.org/r/20230510122811.1872358-1-liviu.dudau@arm.com Signed-off-by: Liviu Dudau Acked-by: Brian Starkey Cc: Mihail Atanassov Cc: Greg Kroah-Hartman Cc: Joe Perches # "Please use --order" Cc: Mihail Atanassov Cc: Uwe Kleine-König Signed-off-by: Andrew Morton --- MAINTAINERS | 5 ----- 1 file changed, 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 21d66f969602..789ceee3424a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1666,10 +1666,7 @@ F: drivers/power/reset/arm-versatile-reboot.c F: drivers/soc/versatile/ ARM KOMEDA DRM-KMS DRIVER -M: James (Qian) Wang M: Liviu Dudau -M: Mihail Atanassov -L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,komeda.yaml @@ -1690,8 +1687,6 @@ F: include/uapi/drm/panfrost_drm.h ARM MALI-DP DRM DRIVER M: Liviu Dudau -M: Brian Starkey -L: Mali DP Maintainers S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/arm,malidp.yaml -- GitLab From 3981514180c987a79ea98f0ae06a7cbf58a9ac0f Mon Sep 17 00:00:00 2001 From: Jim Wylder Date: Wed, 17 May 2023 10:20:11 -0500 Subject: [PATCH 5151/5631] regmap: Account for register length when chunking Currently, when regmap_raw_write() splits the data, it uses the max_raw_write value defined for the bus. For any bus that includes the target register address in the max_raw_write value, the chunked transmission will always exceed the maximum transmission length. To avoid this problem, subtract the length of the register and the padding from the maximum transmission. Signed-off-by: Jim Wylder max_raw_write - map->format.reg_bytes - + map->format.pad_bytes; int ret, i; if (!val_count) @@ -2089,8 +2091,8 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, if (map->use_single_write) chunk_regs = 1; - else if (map->max_raw_write && val_len > map->max_raw_write) - chunk_regs = map->max_raw_write / val_bytes; + else if (map->max_raw_write && val_len > max_data) + chunk_regs = max_data / val_bytes; chunk_count = val_count / chunk_regs; chunk_bytes = chunk_regs * val_bytes; -- GitLab From 067dee65751bcd14fcaaee769cee84c65ce99360 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:33 +0200 Subject: [PATCH 5152/5631] net: isa: include net/Space.h The legacy drivers that still get called from net/Space.c have prototypes in net/Space, but this header is not included in most of the files that define those functions: drivers/net/ethernet/cirrus/cs89x0.c:1649:28: error: no previous prototype for 'cs89x0_probe' [-Werror=missing-prototypes] drivers/net/ethernet/8390/ne.c:947:28: error: no previous prototype for 'ne_probe' [-Werror=missing-prototypes] drivers/net/ethernet/8390/smc-ultra.c:167:28: error: no previous prototype for 'ultra_probe' [-Werror=missing-prototypes] drivers/net/ethernet/amd/lance.c:438:28: error: no previous prototype for 'lance_probe' [-Werror=missing-prototypes] drivers/net/ethernet/3com/3c515.c:422:20: error: no previous prototype for 'tc515_probe' [-Werror=missing-prototypes] Add the inclusion to avoids the warnings. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/3com/3c515.c | 4 +++- drivers/net/ethernet/8390/ne.c | 1 + drivers/net/ethernet/8390/smc-ultra.c | 1 + drivers/net/ethernet/8390/wd.c | 1 + drivers/net/ethernet/amd/lance.c | 1 + drivers/net/ethernet/cirrus/cs89x0.c | 2 ++ 6 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index d2f4358cc550..ba3e7aa1a28f 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -66,8 +66,10 @@ static int max_interrupt_work = 20; #include #include #include - #include + +#include + #include #include diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 0a9118b8be0c..bc9c81dc00fd 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -52,6 +52,7 @@ static const char version2[] = #include #include #include +#include #include diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 6e62c37c9400..7465650c8078 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -66,6 +66,7 @@ static const char version[] = #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/8390/wd.c b/drivers/net/ethernet/8390/wd.c index 5b00c452bede..119021d41451 100644 --- a/drivers/net/ethernet/8390/wd.c +++ b/drivers/net/ethernet/8390/wd.c @@ -37,6 +37,7 @@ static const char version[] = #include #include #include +#include #include diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 8971665a4b2a..6cf38180cc01 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -59,6 +59,7 @@ static const char version[] = "lance.c:v1.16 2006/11/09 dplatt@3do.com, becker@c #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 06a0c00af99c..276c32c3926a 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -72,6 +72,8 @@ #include #include +#include + #include #include #if ALLOW_DMA -- GitLab From fb1b7be9b16c1f4626969ba4e95a97da2a452b41 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:34 +0200 Subject: [PATCH 5153/5631] atm: hide unused procfs functions When CONFIG_PROC_FS is disabled, the function declarations for some procfs functions are hidden, but the definitions are still build, as shown by this compiler warning: net/atm/resources.c:403:7: error: no previous prototype for 'atm_dev_seq_start' [-Werror=missing-prototypes] net/atm/resources.c:409:6: error: no previous prototype for 'atm_dev_seq_stop' [-Werror=missing-prototypes] net/atm/resources.c:414:7: error: no previous prototype for 'atm_dev_seq_next' [-Werror=missing-prototypes] Add another #ifdef to leave these out of the build. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-2-arnd@kernel.org Signed-off-by: Jakub Kicinski --- net/atm/resources.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/atm/resources.c b/net/atm/resources.c index 2b2d33eeaf20..995d29e7fb13 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -400,6 +400,7 @@ int atm_dev_ioctl(unsigned int cmd, void __user *buf, int __user *sioc_len, return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -415,3 +416,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif -- GitLab From 89dcd87ce534a3a7f267cfd58505803006f51301 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:35 +0200 Subject: [PATCH 5154/5631] bridge: always declare tunnel functions When CONFIG_BRIDGE_VLAN_FILTERING is disabled, two functions are still defined but have no prototype or caller. This causes a W=1 warning for the missing prototypes: net/bridge/br_netlink_tunnel.c:29:6: error: no previous prototype for 'vlan_tunid_inrange' [-Werror=missing-prototypes] net/bridge/br_netlink_tunnel.c:199:5: error: no previous prototype for 'br_vlan_tunnel_info' [-Werror=missing-prototypes] The functions are already contitional on CONFIG_BRIDGE_VLAN_FILTERING, and I coulnd't easily figure out the right set of #ifdefs, so just move the declarations out of the #ifdef to avoid the warning, at a small cost in code size over a more elaborate fix. Fixes: 188c67dd1906 ("net: bridge: vlan options: add support for tunnel id dumping") Fixes: 569da0822808 ("net: bridge: vlan options: add support for tunnel mapping set/del") Signed-off-by: Arnd Bergmann Acked-by: Nikolay Aleksandrov Link: https://lore.kernel.org/r/20230516194625.549249-3-arnd@kernel.org Signed-off-by: Jakub Kicinski --- net/bridge/br_private_tunnel.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/bridge/br_private_tunnel.h b/net/bridge/br_private_tunnel.h index 2b053289f016..efb096025151 100644 --- a/net/bridge/br_private_tunnel.h +++ b/net/bridge/br_private_tunnel.h @@ -27,6 +27,10 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, int br_get_vlan_tunnel_info_size(struct net_bridge_vlan_group *vg); int br_fill_vlan_tunnel_info(struct sk_buff *skb, struct net_bridge_vlan_group *vg); +bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *v_last); +int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, + u16 vid, u32 tun_id, bool *changed); #ifdef CONFIG_BRIDGE_VLAN_FILTERING /* br_vlan_tunnel.c */ @@ -43,10 +47,6 @@ void br_handle_ingress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan_group *vg); int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan); -bool vlan_tunid_inrange(const struct net_bridge_vlan *v_curr, - const struct net_bridge_vlan *v_last); -int br_vlan_tunnel_info(const struct net_bridge_port *p, int cmd, - u16 vid, u32 tun_id, bool *changed); #else static inline int vlan_tunnel_init(struct net_bridge_vlan_group *vg) { -- GitLab From 2e9f8ab68f42b059e80db71266c1675c07c664bd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 21:45:36 +0200 Subject: [PATCH 5155/5631] mdio_bus: unhide mdio_bus_init prototype mdio_bus_init() is either used as a local module_init() entry, or it gets called in phy_device.c. In the former case, there is no declaration, which causes a warning: drivers/net/phy/mdio_bus.c:1371:12: error: no previous prototype for 'mdio_bus_init' [-Werror=missing-prototypes] Remove the #ifdef around the declaration to avoid the warning.. Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20230516194625.549249-4-arnd@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/phy.h b/include/linux/phy.h index c5a0dc829714..6478838405a0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1900,10 +1900,8 @@ void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size); -#if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); -#endif int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); -- GitLab From bfa00d8f98f7c5e582b04f874aecb83af8da84c6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:42:53 -0700 Subject: [PATCH 5156/5631] MAINTAINERS: skip CCing netdev for Bluetooth patches As requested by Marcel skip netdev for Bluetooth patches. Bluetooth has its own mailing list and overloading netdev leads to fewer people reading it. Link: https://lore.kernel.org/netdev/639C8EA4-1F6E-42BE-8F04-E4A753A6EFFC@holtmann.org/ Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230517014253.1233333-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index e884937f0e28..5b02298467fa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14632,6 +14632,7 @@ F: include/uapi/linux/netdevice.h F: lib/net_utils.c F: lib/random32.c F: net/ +X: net/bluetooth/ F: tools/net/ F: tools/testing/selftests/net/ -- GitLab From 9aaa7eb018661b2da221362d9bacb096bd596f52 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Mon, 8 May 2023 14:45:01 +0800 Subject: [PATCH 5157/5631] ceph: silence smatch warning in reconnect_caps_cb() Smatch static checker warning: fs/ceph/mds_client.c:3968 reconnect_caps_cb() warn: missing error code here? '__get_cap_for_mds()' failed. 'err' = '0' [ idryomov: Dan says that Smatch considers it intentional only if the "ret = 0;" assignment is within 4 or 5 lines of the goto. ] Reported-by: Dan Carpenter Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 29cf00220b09..4c0f22acf53d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3942,7 +3942,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct dentry *dentry; struct ceph_cap *cap; char *path; - int pathlen = 0, err = 0; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3965,6 +3965,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap = __get_cap_for_mds(ci, mds); if (!cap) { spin_unlock(&ci->i_ceph_lock); + err = 0; goto out_err; } dout(" adding %p ino %llx.%llx cap %p %lld %s\n", -- GitLab From 4cafd0400bcb6187c0d4ab4d4b0229a89ac4f8c2 Mon Sep 17 00:00:00 2001 From: Xiubo Li Date: Thu, 18 May 2023 09:47:23 +0800 Subject: [PATCH 5158/5631] ceph: force updating the msg pointer in non-split case When the MClientSnap reqeust's op is not CEPH_SNAP_OP_SPLIT the request may still contain a list of 'split_realms', and we need to skip it anyway. Or it will be parsed as a corrupt snaptrace. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/61200 Reported-by: Frank Schilder Signed-off-by: Xiubo Li Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- fs/ceph/snap.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 87007203f130..0b236ebd989f 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1111,6 +1111,19 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, continue; adjust_snap_realm_parent(mdsc, child, realm->ino); } + } else { + /* + * In the non-split case both 'num_split_inos' and + * 'num_split_realms' should be 0, making this a no-op. + * However the MDS happens to populate 'split_realms' list + * in one of the UPDATE op cases by mistake. + * + * Skip both lists just in case to ensure that 'p' is + * positioned at the start of realm info, as expected by + * ceph_update_snap_trace(). + */ + p += sizeof(u64) * num_split_inos; + p += sizeof(u64) * num_split_realms; } /* -- GitLab From a511637502b1caa135046d0f8fdabd55a31af8ef Mon Sep 17 00:00:00 2001 From: Sen Chu Date: Thu, 18 May 2023 12:06:46 +0800 Subject: [PATCH 5159/5631] regulator: mt6359: add read check for PMIC MT6359 Add hardware version read check for PMIC MT6359 Signed-off-by: Sen Chu regmap, MT6359P_HWCID, &hw_ver); + if (ret) + return ret; - regmap_read(mt6397->regmap, MT6359P_HWCID, &hw_ver); if (hw_ver >= MT6359P_CHIP_VER) mt6359_info = mt6359p_regulators; else -- GitLab From 8173cab3368a13cdc3cad0bd5cf14e9399b0f501 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Tue, 9 May 2023 18:49:46 +0200 Subject: [PATCH 5160/5631] drm/amdgpu/gfx10: Disable gfxoff before disabling powergating. Otherwise we get a full system lock (looks like a FW mess). Copied the order from the GFX9 powergating code. Fixes: 366468ff6c34 ("drm/amdgpu: Allow GfxOff on Vangogh as default") Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2545 Signed-off-by: Bas Nieuwenhuizen Tested-by: Guilherme G. Piccoli Cc: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f5b5ce1051a2..1ec076517c96 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -8152,8 +8152,14 @@ static int gfx_v10_0_set_powergating_state(void *handle, case IP_VERSION(10, 3, 3): case IP_VERSION(10, 3, 6): case IP_VERSION(10, 3, 7): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v10_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; -- GitLab From 11fbdda2ab6bf049e2869139c07016022b4e045b Mon Sep 17 00:00:00 2001 From: "Guilherme G. Piccoli" Date: Tue, 9 May 2023 18:49:47 +0200 Subject: [PATCH 5161/5631] drm/amdgpu/gfx11: Adjust gfxoff before powergating on gfx11 as well (Bas: speculative change to mirror gfx10/gfx9) Signed-off-by: Guilherme G. Piccoli Signed-off-by: Bas Nieuwenhuizen Cc: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index db2543d8fde9..c4940b6ea1c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -5153,8 +5153,14 @@ static int gfx_v11_0_set_powergating_state(void *handle, break; case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 4): + if (!enable) + amdgpu_gfx_off_ctrl(adev, false); + gfx_v11_cntl_pg(adev, enable); - amdgpu_gfx_off_ctrl(adev, enable); + + if (enable) + amdgpu_gfx_off_ctrl(adev, true); + break; default: break; -- GitLab From 9d2d1827af295fd6971786672c41c4dba3657154 Mon Sep 17 00:00:00 2001 From: Jesse Zhang Date: Fri, 12 May 2023 09:29:17 +0800 Subject: [PATCH 5162/5631] drm/amdgpu: Differentiate between Raven2 and Raven/Picasso according to revision id Due to the raven2 and raven/picasso maybe have the same GC_HWIP version. So differentiate them by revision id. Signed-off-by: shanshengwang Signed-off-by: Jesse Zhang Acked-by: Evan Quan Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 33 ++++++++++++--------------- 1 file changed, 14 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f46d4b18a3fa..9818743ec419 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4003,30 +4003,25 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev) clock = clock_lo | (clock_hi << 32ULL); break; case IP_VERSION(9, 1, 0): + case IP_VERSION(9, 2, 2): preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); - /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ - if (hi_check != clock_hi) { + if (adev->rev_id >= 0x8) { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); + } else { + clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); - clock_hi = hi_check; + hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven); } - preempt_enable(); - clock = clock_lo | (clock_hi << 32ULL); - break; - case IP_VERSION(9, 2, 2): - preempt_disable(); - clock_hi = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); - hi_check = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_UPPER_Raven2); /* The PWR TSC clock frequency is 100MHz, which sets 32-bit carry over - * roughly every 42 seconds. - */ + * roughly every 42 seconds. + */ if (hi_check != clock_hi) { - clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + if (adev->rev_id >= 0x8) + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven2); + else + clock_lo = RREG32_SOC15_NO_KIQ(PWR, 0, mmGOLDEN_TSC_COUNT_LOWER_Raven); clock_hi = hi_check; } preempt_enable(); -- GitLab From 68518294d00da6a2433357af75a63abc6030676e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 11 May 2023 10:40:03 -0400 Subject: [PATCH 5163/5631] drm/amdgpu/gmc11: implement get_vbios_fb_size() Implement get_vbios_fb_size() so we can properly reserve the vbios splash screen to avoid potential artifacts on the screen during the transition from the pre-OS console to the OS console. Acked-by: Sunil Khatri Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 6.1.x --- drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index d95f9fe8f1c5..4116c112e8a0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -31,6 +31,8 @@ #include "umc_v8_10.h" #include "athub/athub_3_0_0_sh_mask.h" #include "athub/athub_3_0_0_offset.h" +#include "dcn/dcn_3_2_0_offset.h" +#include "dcn/dcn_3_2_0_sh_mask.h" #include "oss/osssys_6_0_0_offset.h" #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h" #include "navi10_enum.h" @@ -546,7 +548,24 @@ static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev, static unsigned gmc_v11_0_get_vbios_fb_size(struct amdgpu_device *adev) { - return 0; + u32 d1vga_control = RREG32_SOC15(DCE, 0, regD1VGA_CONTROL); + unsigned size; + + if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) { + size = AMDGPU_VBIOS_VGA_ALLOCATION; + } else { + u32 viewport; + u32 pitch; + + viewport = RREG32_SOC15(DCE, 0, regHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION); + pitch = RREG32_SOC15(DCE, 0, regHUBPREQ0_DCSURF_SURFACE_PITCH); + size = (REG_GET_FIELD(viewport, + HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION, PRI_VIEWPORT_HEIGHT) * + REG_GET_FIELD(pitch, HUBPREQ0_DCSURF_SURFACE_PITCH, PITCH) * + 4); + } + + return size; } static const struct amdgpu_gmc_funcs gmc_v11_0_gmc_funcs = { -- GitLab From c1a322a7a4a96cd0a3dde32ce37af437a78bf8cd Mon Sep 17 00:00:00 2001 From: Guchun Chen Date: Tue, 9 May 2023 16:15:27 +0800 Subject: [PATCH 5164/5631] drm/amdgpu: skip disabling fence driver src_irqs when device is unplugged When performing device unbind or halt, we have disabled all irqs at the very begining like amdgpu_pci_remove or amdgpu_device_halt. So amdgpu_irq_put for irqs stored in fence driver should not be called any more, otherwise, below calltrace will arrive. [ 139.114088] WARNING: CPU: 2 PID: 1550 at drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c:616 amdgpu_irq_put+0xf6/0x110 [amdgpu] [ 139.114655] Call Trace: [ 139.114655] [ 139.114657] amdgpu_fence_driver_hw_fini+0x93/0x130 [amdgpu] [ 139.114836] amdgpu_device_fini_hw+0xb6/0x350 [amdgpu] [ 139.114955] amdgpu_driver_unload_kms+0x51/0x70 [amdgpu] [ 139.115075] amdgpu_pci_remove+0x63/0x160 [amdgpu] [ 139.115193] ? __pm_runtime_resume+0x64/0x90 [ 139.115195] pci_device_remove+0x3a/0xb0 [ 139.115197] device_remove+0x43/0x70 [ 139.115198] device_release_driver_internal+0xbd/0x140 Signed-off-by: Guchun Chen Acked-by: Alex Deucher Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index f52d0ba91a77..a7d250809da9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -582,7 +582,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev) if (r) amdgpu_fence_driver_force_completion(ring); - if (ring->fence_drv.irq_src) + if (!drm_dev_is_unplugged(adev_to_drm(adev)) && + ring->fence_drv.irq_src) amdgpu_irq_put(adev, ring->fence_drv.irq_src, ring->fence_drv.irq_type); -- GitLab From bf4823267a817f7c155876a125b94336d7113e77 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 11 May 2023 15:41:27 +0800 Subject: [PATCH 5165/5631] drm/amd/pm: fix possible power mode mismatch between driver and PMFW PMFW may boots the ASIC with a different power mode from the system's real one. Notify PMFW explicitly the power mode the system in. This is needed only when ACDC switch via gpio is not supported. Signed-off-by: Evan Quan Reviewed-by: Kenneth Feng Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 18 +++++++++++++++++ .../gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c | 20 +------------------ .../drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 1 + 3 files changed, 20 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 5633c5797e85..2ddf5198e5c4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -733,6 +733,24 @@ static int smu_late_init(void *handle) return ret; } + /* + * Explicitly notify PMFW the power mode the system in. Since + * the PMFW may boot the ASIC with a different mode. + * For those supporting ACDC switch via gpio, PMFW will + * handle the switch automatically. Driver involvement + * is unnecessary. + */ + if (!smu->dc_controlled_by_gpio) { + ret = smu_set_power_source(smu, + adev->pm.ac_power ? SMU_POWER_SOURCE_AC : + SMU_POWER_SOURCE_DC); + if (ret) { + dev_err(adev->dev, "Failed to switch to %s mode!\n", + adev->pm.ac_power ? "AC" : "DC"); + return ret; + } + } + if ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 1)) || (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 3))) return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index c4000518dc56..275f708db636 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3413,26 +3413,8 @@ static int navi10_post_smu_init(struct smu_context *smu) return 0; ret = navi10_run_umc_cdr_workaround(smu); - if (ret) { + if (ret) dev_err(adev->dev, "Failed to apply umc cdr workaround!\n"); - return ret; - } - - if (!smu->dc_controlled_by_gpio) { - /* - * For Navi1X, manually switch it to AC mode as PMFW - * may boot it with DC mode. - */ - ret = smu_v11_0_set_power_source(smu, - adev->pm.ac_power ? - SMU_POWER_SOURCE_AC : - SMU_POWER_SOURCE_DC); - if (ret) { - dev_err(adev->dev, "Failed to switch to %s mode!\n", - adev->pm.ac_power ? "AC" : "DC"); - return ret; - } - } return ret; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 3d9ff46706fb..98a33f8ee209 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -1770,6 +1770,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .enable_mgpu_fan_boost = smu_v13_0_7_enable_mgpu_fan_boost, .get_power_limit = smu_v13_0_7_get_power_limit, .set_power_limit = smu_v13_0_set_power_limit, + .set_power_source = smu_v13_0_set_power_source, .get_power_profile_mode = smu_v13_0_7_get_power_profile_mode, .set_power_profile_mode = smu_v13_0_7_set_power_profile_mode, .set_tool_table_location = smu_v13_0_set_tool_table_location, -- GitLab From 6d600229df1ed06f46ba68ac706d9f44ba8c5fb4 Mon Sep 17 00:00:00 2001 From: Mustapha Ghaddar Date: Fri, 28 Apr 2023 12:13:21 -0400 Subject: [PATCH 5166/5631] drm/amd/display: enable dpia validate Use dpia_validate_usb4_bw() function Fixes: a8b537605e22 ("drm/amd/display: Add function pointer for validate bw usb4") Reviewed-by: Roman Li Reviewed-by: Meenakshikumar Somasundaram Acked-by: Aurabindo Pillai Signed-off-by: Mustapha Ghaddar Tested-by: Daniel Wheeler Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/dc/link/link_validation.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c index d4b7da526f0a..e8b2fc4002a5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c @@ -359,5 +359,8 @@ bool link_validate_dpia_bandwidth(const struct dc_stream_state *stream, const un link[i] = stream[i].link; bw_needed[i] = dc_bandwidth_in_kbps_from_timing(&stream[i].timing); } + + ret = dpia_validate_usb4_bw(link, bw_needed, num_streams); + return ret; } -- GitLab From ac5902f84bb546c64aea02c439c2579cbf40318f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 17 May 2023 21:34:08 +0800 Subject: [PATCH 5167/5631] ublk: fix AB-BA lockdep warning When handling UBLK_IO_FETCH_REQ, ctx->uring_lock is grabbed first, then ub->mutex is acquired. When handling UBLK_CMD_STOP_DEV or UBLK_CMD_DEL_DEV, ub->mutex is grabbed first, then calling io_uring_cmd_done() for canceling uring command, in which ctx->uring_lock may be required. Real deadlock only happens when all the above commands are issued from same uring context, and in reality different uring contexts are often used for handing control command and IO command. Fix the issue by using io_uring_cmd_complete_in_task() to cancel command in ublk_cancel_dev(ublk_cancel_queue). Reported-by: Shinichiro Kawasaki Closes: https://lore.kernel.org/linux-block/becol2g7sawl4rsjq2dztsbc7mqypfqko6wzsyoyazqydoasml@rcxarzwidrhk Cc: Ziyang Zhang Signed-off-by: Ming Lei Tested-by: Shinichiro Kawasaki Link: https://lore.kernel.org/r/20230517133408.210944-1-ming.lei@redhat.com Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index c7ed5d69e9ee..33d3298a0da1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1120,6 +1120,11 @@ static inline bool ublk_queue_ready(struct ublk_queue *ubq) return ubq->nr_io_ready == ubq->q_depth; } +static void ublk_cmd_cancel_cb(struct io_uring_cmd *cmd, unsigned issue_flags) +{ + io_uring_cmd_done(cmd, UBLK_IO_RES_ABORT, 0, issue_flags); +} + static void ublk_cancel_queue(struct ublk_queue *ubq) { int i; @@ -1131,8 +1136,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, - IO_URING_F_UNLOCKED); + io_uring_cmd_complete_in_task(io->cmd, + ublk_cmd_cancel_cb); } /* all io commands are canceled */ -- GitLab From e123036be377ddf628226a7c6d4f9af5efd113d3 Mon Sep 17 00:00:00 2001 From: Ranjani Sridharan Date: Wed, 17 May 2023 13:57:31 -0500 Subject: [PATCH 5168/5631] ASoC: soc-pcm: test if a BE can be prepared In the BE hw_params configuration, the existing code checks if any of the existing FEs are prepared, running, paused or suspended - and skips the configuration in those cases. This allows multiple calls of hw_params which the ALSA state machine supports. This check is not handled for the prepare stage, which can lead to the same BE being prepared multiple times. This patch adds a check similar to that of the hw_params, with the main difference being that the suspended state is allowed: the ALSA state machine allows a transition from suspended to prepared with hw_params skipped. This problem was detected on Intel IPC4/SoundWire devices, where the BE dailink .prepare stage is used to configure the SoundWire stream with a bank switch. Multiple .prepare calls lead to conflicts with the .trigger operation with IPC4 configurations. This problem was not detected earlier on Intel devices, HDaudio BE dailinks detect that the link is already prepared and skip the configuration, and for IPC3 devices there is no BE trigger. Link: https://github.com/thesofproject/sof/issues/7596 Signed-off-by: Ranjani Sridharan dpcm[stream].state != SND_SOC_DPCM_STATE_HW_PARAMS) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND) && @@ -3042,3 +3045,20 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe, return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); } EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params); + +/* + * We can only prepare a BE DAI if any of it's FE are not prepared, + * running or paused for the specified stream direction. + */ +int snd_soc_dpcm_can_be_prepared(struct snd_soc_pcm_runtime *fe, + struct snd_soc_pcm_runtime *be, int stream) +{ + const enum snd_soc_dpcm_state state[] = { + SND_SOC_DPCM_STATE_START, + SND_SOC_DPCM_STATE_PAUSED, + SND_SOC_DPCM_STATE_PREPARE, + }; + + return snd_soc_dpcm_check_state(fe, be, stream, state, ARRAY_SIZE(state)); +} +EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_prepared); -- GitLab From eb0764b822b9b26880b28ccb9100b2983e01bc17 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 May 2023 20:19:43 -0700 Subject: [PATCH 5169/5631] cxl/port: Enable the HDM decoder capability for switch ports Derick noticed, when testing hot plug, that hot-add behaves nominally after a removal. However, if the hot-add is done without a prior removal, CXL.mem accesses fail. It turns out that the original implementation of the port driver and region programming wrongly assumed that platform-firmware always enables the host-bridge HDM decoder capability. Add support turning on switch-level HDM decoders in the case where platform-firmware has not. The implementation is careful to only arrange for the enable to be undone if the current instance of the driver was the one that did the enable. This is to interoperate with platform-firmware that may expect CXL.mem to remain active after the driver is shutdown. This comes at the cost of potentially not shutting down the enable on kexec flows, but it is mitigated by the fact that the related HDM decoders still need to be enabled on an individual basis. Cc: Reported-by: Derick Marks Fixes: 54cdbf845cf7 ("cxl/port: Add a driver for 'struct cxl_port' objects") Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/168437998331.403037.15719879757678389217.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 27 +++++++++++++++++++++++---- drivers/cxl/cxl.h | 1 + drivers/cxl/port.c | 14 +++++++++----- tools/testing/cxl/Kbuild | 1 + tools/testing/cxl/test/mock.c | 15 +++++++++++++++ 5 files changed, 49 insertions(+), 9 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index f332fe7af92b..c35c002b65dd 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -241,17 +241,36 @@ static void disable_hdm(void *_cxlhdm) hdm + CXL_HDM_DECODER_CTRL_OFFSET); } -static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) { - void __iomem *hdm = cxlhdm->regs.hdm_decoder; + void __iomem *hdm; u32 global_ctrl; + /* + * If the hdm capability was not mapped there is nothing to enable and + * the caller is responsible for what happens next. For example, + * emulate a passthrough decoder. + */ + if (IS_ERR(cxlhdm)) + return 0; + + hdm = cxlhdm->regs.hdm_decoder; global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET); + + /* + * If the HDM decoder capability was enabled on entry, skip + * registering disable_hdm() since this decode capability may be + * owned by platform firmware. + */ + if (global_ctrl & CXL_HDM_DECODER_ENABLE) + return 0; + writel(global_ctrl | CXL_HDM_DECODER_ENABLE, hdm + CXL_HDM_DECODER_CTRL_OFFSET); - return devm_add_action_or_reset(host, disable_hdm, cxlhdm); + return devm_add_action_or_reset(&port->dev, disable_hdm, cxlhdm); } +EXPORT_SYMBOL_NS_GPL(devm_cxl_enable_hdm, CXL); int cxl_dvsec_rr_decode(struct device *dev, int d, struct cxl_endpoint_dvsec_info *info) @@ -425,7 +444,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm, if (info->mem_enabled) return 0; - rc = devm_cxl_enable_hdm(&port->dev, cxlhdm); + rc = devm_cxl_enable_hdm(port, cxlhdm); if (rc) return rc; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 044a92d9813e..f93a28538962 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -710,6 +710,7 @@ struct cxl_endpoint_dvsec_info { struct cxl_hdm; struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, struct cxl_endpoint_dvsec_info *info); +int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm); int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index eb57324c4ad4..17a95f469c26 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -60,13 +60,17 @@ static int discover_region(struct device *dev, void *root) static int cxl_switch_port_probe(struct cxl_port *port) { struct cxl_hdm *cxlhdm; - int rc; + int rc, nr_dports; - rc = devm_cxl_port_enumerate_dports(port); - if (rc < 0) - return rc; + nr_dports = devm_cxl_port_enumerate_dports(port); + if (nr_dports < 0) + return nr_dports; cxlhdm = devm_cxl_setup_hdm(port, NULL); + rc = devm_cxl_enable_hdm(port, cxlhdm); + if (rc) + return rc; + if (!IS_ERR(cxlhdm)) return devm_cxl_enumerate_decoders(cxlhdm, NULL); @@ -75,7 +79,7 @@ static int cxl_switch_port_probe(struct cxl_port *port) return PTR_ERR(cxlhdm); } - if (rc == 1) { + if (nr_dports == 1) { dev_dbg(&port->dev, "Fallback to passthrough decoder\n"); return devm_cxl_add_passthrough_decoder(port); } diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index fba7bec96acd..6f9347ade82c 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -6,6 +6,7 @@ ldflags-y += --wrap=acpi_pci_find_root ldflags-y += --wrap=nvdimm_bus_register ldflags-y += --wrap=devm_cxl_port_enumerate_dports ldflags-y += --wrap=devm_cxl_setup_hdm +ldflags-y += --wrap=devm_cxl_enable_hdm ldflags-y += --wrap=devm_cxl_add_passthrough_decoder ldflags-y += --wrap=devm_cxl_enumerate_decoders ldflags-y += --wrap=cxl_await_media_ready diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index de3933a776fd..284416527644 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -149,6 +149,21 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port, } EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL); +int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm) +{ + int index, rc; + struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); + + if (ops && ops->is_mock_port(port->uport)) + rc = 0; + else + rc = devm_cxl_enable_hdm(port, cxlhdm); + put_cxl_mock_ops(index); + + return rc; +} +EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL); + int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port) { int rc, index; -- GitLab From ce17ad0d54985e2595a3e615fda31df61808a08c Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 18 May 2023 14:54:34 -0700 Subject: [PATCH 5170/5631] cxl: Wait Memory_Info_Valid before access memory related info The Memory_Info_Valid bit (CXL 3.0 8.1.3.8.2) indicates that the CXL Range Size High and Size Low registers are valid. The bit must be set within 1 second of reset deassertion to the device. Check valid bit before we check the Memory_Active bit when waiting for cxl_await_media_ready() to ensure that the memory info is valid for consumption. Also ensures both DVSEC ranges 1 and 2 are ready if DVSEC Capability indicates they are both supported. Fixes: 523e594d9cc0 ("cxl/pci: Implement wait for media active") Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/168444687469.3134781.11033518965387297327.stgit@djiang5-mobl3 Signed-off-by: Dan Williams --- drivers/cxl/core/pci.c | 85 +++++++++++++++++++++++++++++++++++++----- drivers/cxl/cxlpci.h | 2 + 2 files changed, 78 insertions(+), 9 deletions(-) diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index c35c002b65dd..67f4ab6daa34 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -101,23 +101,57 @@ int devm_cxl_port_enumerate_dports(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(devm_cxl_port_enumerate_dports, CXL); -/* - * Wait up to @media_ready_timeout for the device to report memory - * active. - */ -int cxl_await_media_ready(struct cxl_dev_state *cxlds) +static int cxl_dvsec_mem_range_valid(struct cxl_dev_state *cxlds, int id) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + bool valid = false; + int rc, i; + u32 temp; + + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + + /* Check MEM INFO VALID bit first, give up after 1s */ + i = 1; + do { + rc = pci_read_config_dword(pdev, + d + CXL_DVSEC_RANGE_SIZE_LOW(id), + &temp); + if (rc) + return rc; + + valid = FIELD_GET(CXL_DVSEC_MEM_INFO_VALID, temp); + if (valid) + break; + msleep(1000); + } while (i--); + + if (!valid) { + dev_err(&pdev->dev, + "Timeout awaiting memory range %d valid after 1s.\n", + id); + return -ETIMEDOUT; + } + + return 0; +} + +static int cxl_dvsec_mem_range_active(struct cxl_dev_state *cxlds, int id) { struct pci_dev *pdev = to_pci_dev(cxlds->dev); int d = cxlds->cxl_dvsec; bool active = false; - u64 md_status; int rc, i; + u32 temp; - for (i = media_ready_timeout; i; i--) { - u32 temp; + if (id > CXL_DVSEC_RANGE_MAX) + return -EINVAL; + /* Check MEM ACTIVE bit, up to 60s timeout by default */ + for (i = media_ready_timeout; i; i--) { rc = pci_read_config_dword( - pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); + pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(id), &temp); if (rc) return rc; @@ -134,6 +168,39 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) return -ETIMEDOUT; } + return 0; +} + +/* + * Wait up to @media_ready_timeout for the device to report memory + * active. + */ +int cxl_await_media_ready(struct cxl_dev_state *cxlds) +{ + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + int d = cxlds->cxl_dvsec; + int rc, i, hdm_count; + u64 md_status; + u16 cap; + + rc = pci_read_config_word(pdev, + d + CXL_DVSEC_CAP_OFFSET, &cap); + if (rc) + return rc; + + hdm_count = FIELD_GET(CXL_DVSEC_HDM_COUNT_MASK, cap); + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_valid(cxlds, i); + if (rc) + return rc; + } + + for (i = 0; i < hdm_count; i++) { + rc = cxl_dvsec_mem_range_active(cxlds, i); + if (rc) + return rc; + } + md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET); if (!CXLMDEV_READY(md_status)) return -EIO; diff --git a/drivers/cxl/cxlpci.h b/drivers/cxl/cxlpci.h index 0465ef963cd6..7c02e55b8042 100644 --- a/drivers/cxl/cxlpci.h +++ b/drivers/cxl/cxlpci.h @@ -31,6 +31,8 @@ #define CXL_DVSEC_RANGE_BASE_LOW(i) (0x24 + (i * 0x10)) #define CXL_DVSEC_MEM_BASE_LOW_MASK GENMASK(31, 28) +#define CXL_DVSEC_RANGE_MAX 2 + /* CXL 2.0 8.1.4: Non-CXL Function Map DVSEC */ #define CXL_DVSEC_FUNCTION_MAP 2 -- GitLab From e764f12208b99ac7892c4e3f6bf88d71ca71036f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Thu, 18 May 2023 16:38:20 -0700 Subject: [PATCH 5171/5631] cxl: Move cxl_await_media_ready() to before capacity info retrieval Move cxl_await_media_ready() to cxl_pci probe before driver starts issuing IDENTIFY and retrieving memory device information to ensure that the device is ready to provide the information. Allow cxl_pci_probe() to succeed even if media is not ready. Cache the media failure in cxlds and don't ask the device for any media information. The rationale for proceeding in the !media_ready case is to allow for mailbox operations to interrogate and/or remediate the device. After media is repaired then rebinding the cxl_pci driver is expected to restart the capacity scan. Suggested-by: Dan Williams Fixes: b39cb1052a5c ("cxl/mem: Register CXL memX devices") Reviewed-by: Ira Weiny Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/168445310026.3251520.8124296540679268206.stgit@djiang5-mobl3 [djbw: fixup cxl_test] Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 15 ++++++++++----- drivers/cxl/cxlmem.h | 2 ++ drivers/cxl/mem.c | 3 +++ drivers/cxl/pci.c | 6 ++++++ drivers/cxl/port.c | 6 ------ tools/testing/cxl/test/mem.c | 1 + 6 files changed, 22 insertions(+), 11 deletions(-) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 23b9ff920d7e..2c8dc7e2b84d 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -1028,7 +1028,7 @@ static int cxl_mem_get_partition_info(struct cxl_dev_state *cxlds) * cxl_dev_state_identify() - Send the IDENTIFY command to the device. * @cxlds: The device data for the operation * - * Return: 0 if identify was executed successfully. + * Return: 0 if identify was executed successfully or media not ready. * * This will dispatch the identify command to the device and on success populate * structures to be exported to sysfs. @@ -1041,6 +1041,9 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds) u32 val; int rc; + if (!cxlds->media_ready) + return 0; + mbox_cmd = (struct cxl_mbox_cmd) { .opcode = CXL_MBOX_OP_IDENTIFY, .size_out = sizeof(id), @@ -1115,10 +1118,12 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds) cxlds->persistent_only_bytes, "pmem"); } - rc = cxl_mem_get_partition_info(cxlds); - if (rc) { - dev_err(dev, "Failed to query partition information\n"); - return rc; + if (cxlds->media_ready) { + rc = cxl_mem_get_partition_info(cxlds); + if (rc) { + dev_err(dev, "Failed to query partition information\n"); + return rc; + } } rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->ram_res, 0, diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index db12b6313afb..a2845a7a69d8 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -266,6 +266,7 @@ struct cxl_poison_state { * @regs: Parsed register blocks * @cxl_dvsec: Offset to the PCIe device DVSEC * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH) + * @media_ready: Indicate whether the device media is usable * @payload_size: Size of space for payload * (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register) * @lsa_size: Size of Label Storage Area @@ -303,6 +304,7 @@ struct cxl_dev_state { int cxl_dvsec; bool rcd; + bool media_ready; size_t payload_size; size_t lsa_size; struct mutex mbox_mutex; /* Protects device mailbox and firmware */ diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 10caf180b3fa..519edd0eb196 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -124,6 +124,9 @@ static int cxl_mem_probe(struct device *dev) struct dentry *dentry; int rc; + if (!cxlds->media_ready) + return -EBUSY; + /* * Someone is trying to reattach this device after it lost its port * connection (an endpoint port previously registered by this memdev was diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index f7a5b8e9c102..0872f2233ed0 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -708,6 +708,12 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) dev_dbg(&pdev->dev, "Failed to map RAS capability.\n"); + rc = cxl_await_media_ready(cxlds); + if (rc == 0) + cxlds->media_ready = true; + else + dev_warn(&pdev->dev, "Media not active (%d)\n", rc); + rc = cxl_pci_setup_mailbox(cxlds); if (rc) return rc; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 17a95f469c26..c23b6164e1c0 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -117,12 +117,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) if (rc) return rc; - rc = cxl_await_media_ready(cxlds); - if (rc) { - dev_err(&port->dev, "Media not active (%d)\n", rc); - return rc; - } - rc = devm_cxl_enumerate_decoders(cxlhdm, &info); if (rc) return rc; diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index ba572d03c687..34b48027b3de 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev) if (rc) return rc; + cxlds->media_ready = true; rc = cxl_dev_state_identify(cxlds); if (rc) return rc; -- GitLab From 0649728123cf6a5518e154b4e1735fc85ea4f55c Mon Sep 17 00:00:00 2001 From: Daniel Smith Date: Wed, 17 May 2023 14:32:32 -0700 Subject: [PATCH 5172/5631] nvme-pci: Add quirk for Teamgroup MP33 SSD Add a quirk for Teamgroup MP33 that reports duplicate ids for disk. Signed-off-by: Daniel Smith [kch: patch formatting] Signed-off-by: Chaitanya Kulkarni Tested-by: Daniel Smith Signed-off-by: Keith Busch --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 922ffe4e2822..e90f824ffed8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3437,6 +3437,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e4b, 0x1602), /* HS-SSD-FUTURE 2048G */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x10ec, 0x5765), /* TEAMGROUP MP33 2TB SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), -- GitLab From 7e01c7f7046efc2c7c192c3619db43292b98e997 Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Wed, 17 May 2023 13:38:08 +0000 Subject: [PATCH 5173/5631] net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize Currently in cdc_ncm_check_tx_max(), if dwNtbOutMaxSize is lower than the calculated "min" value, but greater than zero, the logic sets tx_max to dwNtbOutMaxSize. This is then used to allocate a new SKB in cdc_ncm_fill_tx_frame() where all the data is handled. For small values of dwNtbOutMaxSize the memory allocated during alloc_skb(dwNtbOutMaxSize, GFP_ATOMIC) will have the same size, due to how size is aligned at alloc time: size = SKB_DATA_ALIGN(size); size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); Thus we hit the same bug that we tried to squash with commit 2be6d4d16a084 ("net: cdc_ncm: Allow for dwNtbOutMaxSize to be unset or zero") Low values of dwNtbOutMaxSize do not cause an issue presently because at alloc_skb() time more memory (512b) is allocated than required for the SKB headers alone (320b), leaving some space (512b - 320b = 192b) for CDC data (172b). However, if more elements (for example 3 x u64 = [24b]) were added to one of the SKB header structs, say 'struct skb_shared_info', increasing its original size (320b [320b aligned]) to something larger (344b [384b aligned]), then suddenly the CDC data (172b) no longer fits in the spare SKB data area (512b - 384b = 128b). Consequently the SKB bounds checking semantics fails and panics: skbuff: skb_over_panic: text:ffffffff831f755b len:184 put:172 head:ffff88811f1c6c00 data:ffff88811f1c6c00 tail:0xb8 end:0x80 dev: ------------[ cut here ]------------ kernel BUG at net/core/skbuff.c:113! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 57 Comm: kworker/0:2 Not tainted 5.15.106-syzkaller-00249-g19c0ed55a470 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/14/2023 Workqueue: mld mld_ifc_work RIP: 0010:skb_panic net/core/skbuff.c:113 [inline] RIP: 0010:skb_over_panic+0x14c/0x150 net/core/skbuff.c:118 [snip] Call Trace: skb_put+0x151/0x210 net/core/skbuff.c:2047 skb_put_zero include/linux/skbuff.h:2422 [inline] cdc_ncm_ndp16 drivers/net/usb/cdc_ncm.c:1131 [inline] cdc_ncm_fill_tx_frame+0x11ab/0x3da0 drivers/net/usb/cdc_ncm.c:1308 cdc_ncm_tx_fixup+0xa3/0x100 Deal with too low values of dwNtbOutMaxSize, clamp it in the range [USB_CDC_NCM_NTB_MIN_OUT_SIZE, CDC_NCM_NTB_MAX_SIZE_TX]. We ensure enough data space is allocated to handle CDC data by making sure dwNtbOutMaxSize is not smaller than USB_CDC_NCM_NTB_MIN_OUT_SIZE. Fixes: 289507d3364f ("net: cdc_ncm: use sysfs for rx/tx aggregation tuning") Cc: stable@vger.kernel.org Reported-by: syzbot+9f575a1f15fc0c01ed69@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=b982f1059506db48409d Link: https://lore.kernel.org/all/20211202143437.1411410-1-lee.jones@linaro.org/ Signed-off-by: Tudor Ambarus Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20230517133808.1873695-2-tudor.ambarus@linaro.org Signed-off-by: Jakub Kicinski --- drivers/net/usb/cdc_ncm.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 6ce8f4f0c70e..db05622f1f70 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -181,9 +181,12 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) else min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32); - max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize)); - if (max == 0) + if (le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) == 0) max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */ + else + max = clamp_t(u32, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize), + USB_CDC_NCM_NTB_MIN_OUT_SIZE, + CDC_NCM_NTB_MAX_SIZE_TX); /* some devices set dwNtbOutMaxSize too low for the above default */ min = min(min, max); @@ -1244,6 +1247,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) * further. */ if (skb_out == NULL) { + /* If even the smallest allocation fails, abort. */ + if (ctx->tx_curr_size == USB_CDC_NCM_NTB_MIN_OUT_SIZE) + goto alloc_failed; ctx->tx_low_mem_max_cnt = min(ctx->tx_low_mem_max_cnt + 1, (unsigned)CDC_NCM_LOW_MEM_MAX_CNT); ctx->tx_low_mem_val = ctx->tx_low_mem_max_cnt; @@ -1262,13 +1268,8 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) skb_out = alloc_skb(ctx->tx_curr_size, GFP_ATOMIC); /* No allocation possible so we will abort */ - if (skb_out == NULL) { - if (skb != NULL) { - dev_kfree_skb_any(skb); - dev->net->stats.tx_dropped++; - } - goto exit_no_skb; - } + if (!skb_out) + goto alloc_failed; ctx->tx_low_mem_val--; } if (ctx->is_ndp16) { @@ -1461,6 +1462,11 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) return skb_out; +alloc_failed: + if (skb) { + dev_kfree_skb_any(skb); + dev->net->stats.tx_dropped++; + } exit_no_skb: /* Start timer, if there is a remaining non-empty skb */ if (ctx->tx_curr_skb != NULL && n > 0) -- GitLab From b3a03b540e3cf62a255213d084d76d71c02793d5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:36 -0700 Subject: [PATCH 5174/5631] tls: rx: device: fix checking decryption status skb->len covers the entire skb, including the frag_list. In fact we're guaranteed that rxm->full_len <= skb->len, so since the change under Fixes we were not checking decrypt status of any skb but the first. Note that the skb_pagelen() added here may feel a bit costly, but it's removed by subsequent fixes, anyway. Reported-by: Tariq Toukan Fixes: 86b259f6f888 ("tls: rx: device: bound the frag walk") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index a7cc4f9faac2..3b87c7b04ac8 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1012,7 +1012,7 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct sk_buff *skb_iter; int left; - left = rxm->full_len - skb->len; + left = rxm->full_len + rxm->offset - skb_pagelen(skb); /* Check if all the data is decrypted already */ skb_iter = skb_shinfo(skb)->frag_list; while (skb_iter && left > 0) { -- GitLab From 210620ae44a83f25220450bbfcc22e6fe986b25f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:37 -0700 Subject: [PATCH 5175/5631] tls: rx: strp: set the skb->len of detached / CoW'ed skbs alloc_skb_with_frags() fills in page frag sizes but does not set skb->len and skb->data_len. Set those correctly otherwise device offload will most likely generate an empty skb and hit the BUG() at the end of __skb_nsg(). Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 955ac3e0bf4d..24016c865e00 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -56,6 +56,8 @@ static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) offset += skb_frag_size(frag); } + skb->len = strp->stm.full_len; + skb->data_len = strp->stm.full_len; skb_copy_header(skb, strp->anchor); rxm = strp_msg(skb); rxm->offset = 0; -- GitLab From 14c4be92ebb3e36e392aa9dd8f314038a9f96f3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:38 -0700 Subject: [PATCH 5176/5631] tls: rx: strp: force mixed decrypted records into copy mode If a record is partially decrypted we'll have to CoW it, anyway, so go into copy mode and allocate a writable skb right away. This will make subsequent fix simpler because we won't have to teach tls_strp_msg_make_copy() how to copy skbs while preserving decrypt status. Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 10 ++++++++++ net/tls/tls_strp.c | 16 +++++++++++----- 2 files changed, 21 insertions(+), 5 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 738776ab8838..0b40417457cd 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1587,6 +1587,16 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) to->l4_hash = from->l4_hash; }; +static inline int skb_cmp_decrypted(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ +#ifdef CONFIG_TLS_DEVICE + return skb2->decrypted - skb1->decrypted; +#else + return 0; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 24016c865e00..2b6fa9855999 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -317,15 +317,19 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; } -static bool tls_strp_check_no_dup(struct tls_strparser *strp) +static bool tls_strp_check_queue_ok(struct tls_strparser *strp) { unsigned int len = strp->stm.offset + strp->stm.full_len; - struct sk_buff *skb; + struct sk_buff *first, *skb; u32 seq; - skb = skb_shinfo(strp->anchor)->frag_list; - seq = TCP_SKB_CB(skb)->seq; + first = skb_shinfo(strp->anchor)->frag_list; + skb = first; + seq = TCP_SKB_CB(first)->seq; + /* Make sure there's no duplicate data in the queue, + * and the decrypted status matches. + */ while (skb->len < len) { seq += skb->len; len -= skb->len; @@ -333,6 +337,8 @@ static bool tls_strp_check_no_dup(struct tls_strparser *strp) if (TCP_SKB_CB(skb)->seq != seq) return false; + if (skb_cmp_decrypted(first, skb)) + return false; } return true; @@ -413,7 +419,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copy(strp, true); } - if (!tls_strp_check_no_dup(strp)) + if (!tls_strp_check_queue_ok(strp)) return tls_strp_read_copy(strp, false); strp->msg_ready = 1; -- GitLab From 8b0c0dc9fbbd01e58a573a41c38885f9e4c17696 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:39 -0700 Subject: [PATCH 5177/5631] tls: rx: strp: fix determining record length in copy mode We call tls_rx_msg_size(skb) before doing skb->len += chunk. So the tls_rx_msg_size() code will see old skb->len, most likely leading to an over-read. Worst case we will over read an entire record, next iteration will try to trim the skb but may end up turning frag len negative or discarding the subsequent record (since we already told TCP we've read it during previous read but now we'll trim it out of the skb). Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 2b6fa9855999..e2e48217e7ac 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -210,19 +210,28 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size(frag), chunk)); - sz = tls_rx_msg_size(strp, strp->anchor); + skb->len += chunk; + skb->data_len += chunk; + skb_frag_size_add(frag, chunk); + + sz = tls_rx_msg_size(strp, skb); if (sz < 0) { desc->error = sz; return 0; } /* We may have over-read, sz == 0 is guaranteed under-read */ - if (sz > 0) - chunk = min_t(size_t, chunk, sz - skb->len); + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + skb_frag_size_add(frag, -over); + + chunk -= over; + } - skb->len += chunk; - skb->data_len += chunk; - skb_frag_size_add(frag, chunk); frag++; len -= chunk; offset += chunk; -- GitLab From c1c607b1e5d5477d82ca6a86a05a4f10907b33ee Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:40 -0700 Subject: [PATCH 5178/5631] tls: rx: strp: factor out copying skb data We'll need to copy input skbs individually in the next patch. Factor that code out (without assuming we're copying a full record). Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_strp.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index e2e48217e7ac..61fbf84baf9e 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -34,31 +34,44 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) strp->anchor = NULL; } -/* Create a new skb with the contents of input copied to its page frags */ -static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +static struct sk_buff * +tls_strp_skb_copy(struct tls_strparser *strp, struct sk_buff *in_skb, + int offset, int len) { - struct strp_msg *rxm; struct sk_buff *skb; - int i, err, offset; + int i, err; - skb = alloc_skb_with_frags(0, strp->stm.full_len, TLS_PAGE_ORDER, + skb = alloc_skb_with_frags(0, len, TLS_PAGE_ORDER, &err, strp->sk->sk_allocation); if (!skb) return NULL; - offset = strp->stm.offset; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - WARN_ON_ONCE(skb_copy_bits(strp->anchor, offset, + WARN_ON_ONCE(skb_copy_bits(in_skb, offset, skb_frag_address(frag), skb_frag_size(frag))); offset += skb_frag_size(frag); } - skb->len = strp->stm.full_len; - skb->data_len = strp->stm.full_len; - skb_copy_header(skb, strp->anchor); + skb->len = len; + skb->data_len = len; + skb_copy_header(skb, in_skb); + return skb; +} + +/* Create a new skb with the contents of input copied to its page frags */ +static struct sk_buff *tls_strp_msg_make_copy(struct tls_strparser *strp) +{ + struct strp_msg *rxm; + struct sk_buff *skb; + + skb = tls_strp_skb_copy(strp, strp->anchor, strp->stm.offset, + strp->stm.full_len); + if (!skb) + return NULL; + rxm = strp_msg(skb); rxm->offset = 0; return skb; -- GitLab From eca9bfafee3a0487e59c59201ae14c7594ba940a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:41 -0700 Subject: [PATCH 5179/5631] tls: rx: strp: preserve decryption status of skbs when needed When receive buffer is small we try to copy out the data from TCP into a skb maintained by TLS to prevent connection from stalling. Unfortunately if a single record is made up of a mix of decrypted and non-decrypted skbs combining them into a single skb leads to loss of decryption status, resulting in decryption errors or data corruption. Similarly when trying to use TCP receive queue directly we need to make sure that all the skbs within the record have the same status. If we don't the mixed status will be detected correctly but we'll CoW the anchor, again collapsing it into a single paged skb without decrypted status preserved. So the "fixup" code will not know which parts of skb to re-encrypt. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/net/tls.h | 1 + net/tls/tls.h | 5 ++ net/tls/tls_device.c | 22 +++----- net/tls/tls_strp.c | 117 ++++++++++++++++++++++++++++++++++++------- 4 files changed, 114 insertions(+), 31 deletions(-) diff --git a/include/net/tls.h b/include/net/tls.h index 6056ce5a2aa5..596595c4b1af 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -126,6 +126,7 @@ struct tls_strparser { u32 mark : 8; u32 stopped : 1; u32 copy_mode : 1; + u32 mixed_decrypted : 1; u32 msg_ready : 1; struct strp_msg stm; diff --git a/net/tls/tls.h b/net/tls/tls.h index 804c3880d028..0672acab2773 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -167,6 +167,11 @@ static inline bool tls_strp_msg_ready(struct tls_sw_context_rx *ctx) return ctx->strp.msg_ready; } +static inline bool tls_strp_msg_mixed_decrypted(struct tls_sw_context_rx *ctx) +{ + return ctx->strp.mixed_decrypted; +} + #ifdef CONFIG_TLS_DEVICE int tls_device_init(void); void tls_device_cleanup(void); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 3b87c7b04ac8..bf69c9d6d06c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1007,20 +1007,14 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx) struct tls_sw_context_rx *sw_ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb = tls_strp_msg(sw_ctx); struct strp_msg *rxm = strp_msg(skb); - int is_decrypted = skb->decrypted; - int is_encrypted = !is_decrypted; - struct sk_buff *skb_iter; - int left; - - left = rxm->full_len + rxm->offset - skb_pagelen(skb); - /* Check if all the data is decrypted already */ - skb_iter = skb_shinfo(skb)->frag_list; - while (skb_iter && left > 0) { - is_decrypted &= skb_iter->decrypted; - is_encrypted &= !skb_iter->decrypted; - - left -= skb_iter->len; - skb_iter = skb_iter->next; + int is_decrypted, is_encrypted; + + if (!tls_strp_msg_mixed_decrypted(sw_ctx)) { + is_decrypted = skb->decrypted; + is_encrypted = !is_decrypted; + } else { + is_decrypted = 0; + is_encrypted = 0; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 61fbf84baf9e..da95abbb7ea3 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -29,7 +29,8 @@ static void tls_strp_anchor_free(struct tls_strparser *strp) struct skb_shared_info *shinfo = skb_shinfo(strp->anchor); DEBUG_NET_WARN_ON_ONCE(atomic_read(&shinfo->dataref) != 1); - shinfo->frag_list = NULL; + if (!strp->copy_mode) + shinfo->frag_list = NULL; consume_skb(strp->anchor); strp->anchor = NULL; } @@ -195,22 +196,22 @@ static void tls_strp_flush_anchor_copy(struct tls_strparser *strp) for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], false); shinfo->nr_frags = 0; + if (strp->copy_mode) { + kfree_skb_list(shinfo->frag_list); + shinfo->frag_list = NULL; + } strp->copy_mode = 0; + strp->mixed_decrypted = 0; } -static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, - unsigned int offset, size_t in_len) +static int tls_strp_copyin_frag(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) { - struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; - struct sk_buff *skb; - skb_frag_t *frag; size_t len, chunk; + skb_frag_t *frag; int sz; - if (strp->msg_ready) - return 0; - - skb = strp->anchor; frag = &skb_shinfo(skb)->frags[skb->len / PAGE_SIZE]; len = in_len; @@ -228,10 +229,8 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, skb_frag_size_add(frag, chunk); sz = tls_rx_msg_size(strp, skb); - if (sz < 0) { - desc->error = sz; - return 0; - } + if (sz < 0) + return sz; /* We may have over-read, sz == 0 is guaranteed under-read */ if (unlikely(sz && sz < skb->len)) { @@ -271,15 +270,99 @@ static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, offset += chunk; } - if (strp->stm.full_len == skb->len) { +read_done: + return in_len - len; +} + +static int tls_strp_copyin_skb(struct tls_strparser *strp, struct sk_buff *skb, + struct sk_buff *in_skb, unsigned int offset, + size_t in_len) +{ + struct sk_buff *nskb, *first, *last; + struct skb_shared_info *shinfo; + size_t chunk; + int sz; + + if (strp->stm.full_len) + chunk = strp->stm.full_len - skb->len; + else + chunk = TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; + chunk = min(chunk, in_len); + + nskb = tls_strp_skb_copy(strp, in_skb, offset, chunk); + if (!nskb) + return -ENOMEM; + + shinfo = skb_shinfo(skb); + if (!shinfo->frag_list) { + shinfo->frag_list = nskb; + nskb->prev = nskb; + } else { + first = shinfo->frag_list; + last = first->prev; + last->next = nskb; + first->prev = nskb; + } + + skb->len += chunk; + skb->data_len += chunk; + + if (!strp->stm.full_len) { + sz = tls_rx_msg_size(strp, skb); + if (sz < 0) + return sz; + + /* We may have over-read, sz == 0 is guaranteed under-read */ + if (unlikely(sz && sz < skb->len)) { + int over = skb->len - sz; + + WARN_ON_ONCE(over > chunk); + skb->len -= over; + skb->data_len -= over; + __pskb_trim(nskb, nskb->len - over); + + chunk -= over; + } + + strp->stm.full_len = sz; + } + + return chunk; +} + +static int tls_strp_copyin(read_descriptor_t *desc, struct sk_buff *in_skb, + unsigned int offset, size_t in_len) +{ + struct tls_strparser *strp = (struct tls_strparser *)desc->arg.data; + struct sk_buff *skb; + int ret; + + if (strp->msg_ready) + return 0; + + skb = strp->anchor; + if (!skb->len) + skb_copy_decrypted(skb, in_skb); + else + strp->mixed_decrypted |= !!skb_cmp_decrypted(skb, in_skb); + + if (IS_ENABLED(CONFIG_TLS_DEVICE) && strp->mixed_decrypted) + ret = tls_strp_copyin_skb(strp, skb, in_skb, offset, in_len); + else + ret = tls_strp_copyin_frag(strp, skb, in_skb, offset, in_len); + if (ret < 0) { + desc->error = ret; + ret = 0; + } + + if (strp->stm.full_len && strp->stm.full_len == skb->len) { desc->count = 0; strp->msg_ready = 1; tls_rx_msg_ready(strp); } -read_done: - return in_len - len; + return ret; } static int tls_strp_read_copyin(struct tls_strparser *strp) -- GitLab From 74836ec828fe17b63f2006fdbf53311d691396bf Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:50:42 -0700 Subject: [PATCH 5180/5631] tls: rx: strp: don't use GFP_KERNEL in softirq context When receive buffer is small, or the TCP rx queue looks too complicated to bother using it directly - we allocate a new skb and copy data into it. We already use sk->sk_allocation... but nothing actually sets it to GFP_ATOMIC on the ->sk_data_ready() path. Users of HW offload are far more likely to experience problems due to scheduling while atomic. "Copy mode" is very rarely triggered with SW crypto. Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser") Tested-by: Shai Amiram Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- net/tls/tls_sw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 635b8bf6b937..6e6a7c37d685 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2304,10 +2304,14 @@ static void tls_data_ready(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; + gfp_t alloc_save; trace_sk_data_ready(sk); + alloc_save = sk->sk_allocation; + sk->sk_allocation = GFP_ATOMIC; tls_strp_data_ready(&ctx->strp); + sk->sk_allocation = alloc_save; psock = sk_psock_get(sk); if (psock) { -- GitLab From afbed3f74830163f9559579dee382cac3cff82da Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 16 May 2023 18:59:35 -0700 Subject: [PATCH 5181/5631] net/mlx5e: do as little as possible in napi poll when budget is 0 NAPI gets called with budget of 0 from netpoll, which has interrupts disabled. We should try to free some space on Tx rings and nothing else. Specifically do not try to handle XDP TX or try to refill Rx buffers - we can't use the page pool from IRQ context. Don't check if IRQs moved, either, that makes no sense in netpoll. Netpoll calls _all_ the rings from whatever CPU it happens to be invoked on. In general do as little as possible, the work quickly adds up when there's tens of rings to poll. The immediate stack trace I was seeing is: __do_softirq+0xd1/0x2c0 __local_bh_enable_ip+0xc7/0x120 page_pool_put_defragged_page+0x267/0x320 mlx5e_free_xdpsq_desc+0x99/0xd0 mlx5e_poll_xdpsq_cq+0x138/0x3b0 mlx5e_napi_poll+0xc3/0x8b0 netpoll_poll_dev+0xce/0x150 AFAIU page pool takes a BH lock, releases it and since BH is now enabled tries to run softirqs. Reviewed-by: Tariq Toukan Fixes: 60bbf7eeef10 ("mlx5: use page_pool for xdp_return_frame call") Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_txrx.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index a50bfda18e96..fbb2d963fb7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -161,20 +161,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } } + /* budget=0 means we may be in IRQ context, do as little as possible */ + if (unlikely(!budget)) + goto out; + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); if (c->xdp) busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq); - if (likely(budget)) { /* budget=0 means: don't poll rx rings */ - if (xsk_open) - work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); + if (xsk_open) + work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); - if (likely(budget - work_done)) - work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); + if (likely(budget - work_done)) + work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); - busy |= work_done == budget; - } + busy |= work_done == budget; mlx5e_poll_ico_cq(&c->icosq.cq); if (mlx5e_poll_ico_cq(&c->async_icosq.cq)) -- GitLab From d226b1df361988f885c298737d6019c863a25f26 Mon Sep 17 00:00:00 2001 From: Po-Hsu Lin Date: Thu, 18 May 2023 12:37:59 +0800 Subject: [PATCH 5182/5631] selftests: fib_tests: mute cleanup error message In the end of the test, there will be an error message induced by the `ip netns del ns1` command in cleanup() Tests passed: 201 Tests failed: 0 Cannot remove namespace file "/run/netns/ns1": No such file or directory This can even be reproduced with just `./fib_tests.sh -h` as we're calling cleanup() on exit. Redirect the error message to /dev/null to mute it. V2: Update commit message and fixes tag. V3: resubmit due to missing netdev ML in V2 Fixes: b60417a9f2b8 ("selftest: fib_tests: Always cleanup before exit") Signed-off-by: Po-Hsu Lin Reviewed-by: Ido Schimmel Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_tests.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 7da8ec838c63..35d89dfa6f11 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -68,7 +68,7 @@ setup() cleanup() { $IP link del dev dummy0 &> /dev/null - ip netns del ns1 + ip netns del ns1 &> /dev/null ip netns del ns2 &> /dev/null } -- GitLab From 35112271672ae98f45df7875244a4e33aa215e31 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Thu, 18 May 2023 13:14:55 +0800 Subject: [PATCH 5183/5631] net/smc: Reset connection when trying to use SMCRv2 fails. We found a crash when using SMCRv2 with 2 Mellanox ConnectX-4. It can be reproduced by: - smc_run nginx - smc_run wrk -t 32 -c 500 -d 30 http://: BUG: kernel NULL pointer dereference, address: 0000000000000014 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 8000000108713067 P4D 8000000108713067 PUD 151127067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 4 PID: 2441 Comm: kworker/4:249 Kdump: loaded Tainted: G W E 6.4.0-rc1+ #42 Workqueue: smc_hs_wq smc_listen_work [smc] RIP: 0010:smc_clc_send_confirm_accept+0x284/0x580 [smc] RSP: 0018:ffffb8294b2d7c78 EFLAGS: 00010a06 RAX: ffff8f1873238880 RBX: ffffb8294b2d7dc8 RCX: 0000000000000000 RDX: 00000000000000b4 RSI: 0000000000000001 RDI: 0000000000b40c00 RBP: ffffb8294b2d7db8 R08: ffff8f1815c5860c R09: 0000000000000000 R10: 0000000000000400 R11: 0000000000000000 R12: ffff8f1846f56180 R13: ffff8f1815c5860c R14: 0000000000000001 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8f1aefd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000014 CR3: 00000001027a0001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? mlx5_ib_map_mr_sg+0xa1/0xd0 [mlx5_ib] ? smcr_buf_map_link+0x24b/0x290 [smc] ? __smc_buf_create+0x4ee/0x9b0 [smc] smc_clc_send_accept+0x4c/0xb0 [smc] smc_listen_work+0x346/0x650 [smc] ? __schedule+0x279/0x820 process_one_work+0x1e5/0x3f0 worker_thread+0x4d/0x2f0 ? __pfx_worker_thread+0x10/0x10 kthread+0xe5/0x120 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x2c/0x50 During the CLC handshake, server sequentially tries available SMCRv2 and SMCRv1 devices in smc_listen_work(). If an SMCRv2 device is found. SMCv2 based link group and link will be assigned to the connection. Then assumed that some buffer assignment errors happen later in the CLC handshake, such as RMB registration failure, server will give up SMCRv2 and try SMCRv1 device instead. But the resources assigned to the connection won't be reset. When server tries SMCRv1 device, the connection creation process will be executed again. Since conn->lnk has been assigned when trying SMCRv2, it will not be set to the correct SMCRv1 link in smcr_lgr_conn_assign_link(). So in such situation, conn->lgr points to correct SMCRv1 link group but conn->lnk points to the SMCRv2 link mistakenly. Then in smc_clc_send_confirm_accept(), conn->rmb_desc->mr[link->link_idx] will be accessed. Since the link->link_idx is not correct, the related MR may not have been initialized, so crash happens. | Try SMCRv2 device first | |-> conn->lgr: assign existed SMCRv2 link group; | |-> conn->link: assign existed SMCRv2 link (link_idx may be 1 in SMC_LGR_SYMMETRIC); | |-> sndbuf & RMB creation fails, quit; | | Try SMCRv1 device then | |-> conn->lgr: create SMCRv1 link group and assign; | |-> conn->link: keep SMCRv2 link mistakenly; | |-> sndbuf & RMB creation succeed, only RMB->mr[link_idx = 0] | initialized. | | Then smc_clc_send_confirm_accept() accesses | conn->rmb_desc->mr[conn->link->link_idx, which is 1], then crash. v This patch tries to fix this by cleaning conn->lnk before assigning link. In addition, it is better to reset the connection and clean the resources assigned if trying SMCRv2 failed in buffer creation or registration. Fixes: e49300a6bf62 ("net/smc: add listen processing for SMC-Rv2") Link: https://lore.kernel.org/r/20220523055056.2078994-1-liuyacan@corp.netease.com/ Signed-off-by: Wen Gu Reviewed-by: Tony Lu Signed-off-by: David S. Miller --- net/smc/af_smc.c | 9 +++++++-- net/smc/smc_core.c | 1 + 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 50c38b624f77..538e9c6ec8c9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2000,8 +2000,10 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc, return rc; /* create send buffer and rmb */ - if (smc_buf_create(new_smc, false)) + if (smc_buf_create(new_smc, false)) { + smc_conn_abort(new_smc, ini->first_contact_local); return SMC_CLC_DECL_MEM; + } return 0; } @@ -2217,8 +2219,11 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, smcr_version = ini->smcr_version; ini->smcr_version = SMC_V2; rc = smc_listen_rdma_init(new_smc, ini); - if (!rc) + if (!rc) { rc = smc_listen_rdma_reg(new_smc, ini->first_contact_local); + if (rc) + smc_conn_abort(new_smc, ini->first_contact_local); + } if (!rc) return; ini->smcr_version = smcr_version; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 454356771cda..3f465faf2b68 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -127,6 +127,7 @@ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) int i, j; /* do link balancing */ + conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; -- GitLab From cfcb942863f6fce9266e1957a021e6c7295dee42 Mon Sep 17 00:00:00 2001 From: Alejandro Lucero Date: Thu, 18 May 2023 06:48:22 +0100 Subject: [PATCH 5184/5631] sfc: fix devlink info error handling Avoid early devlink info return if errors arise with MCDI commands executed for getting the required info from the device. The rationale is some commands can fail but later ones could still give useful data. Moreover, some nvram partitions could not be present which needs to be handled as a non error. The specific errors are reported through system messages and if any error appears, it will be reported generically through extack. Fixes 14743ddd2495 ("sfc: add devlink info support for ef100") Signed-off-by: Alejandro Lucero Acked-by: Martin Habets Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/efx_devlink.c | 95 ++++++++++++-------------- 1 file changed, 45 insertions(+), 50 deletions(-) diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c index 381b805659d3..ef9971cbb695 100644 --- a/drivers/net/ethernet/sfc/efx_devlink.c +++ b/drivers/net/ethernet/sfc/efx_devlink.c @@ -171,9 +171,14 @@ static int efx_devlink_info_nvram_partition(struct efx_nic *efx, rc = efx_mcdi_nvram_metadata(efx, partition_type, NULL, version, NULL, 0); + + /* If the partition does not exist, that is not an error. */ + if (rc == -ENOENT) + return 0; + if (rc) { - netif_err(efx, drv, efx->net_dev, "mcdi nvram %s: failed\n", - version_name); + netif_err(efx, drv, efx->net_dev, "mcdi nvram %s: failed (rc=%d)\n", + version_name, rc); return rc; } @@ -187,36 +192,33 @@ static int efx_devlink_info_nvram_partition(struct efx_nic *efx, static int efx_devlink_info_stored_versions(struct efx_nic *efx, struct devlink_info_req *req) { - int rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_BUNDLE, - DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_MC_FIRMWARE, - DEVLINK_INFO_VERSION_GENERIC_FW_MGMT); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_SUC_FIRMWARE, - EFX_DEVLINK_INFO_VERSION_FW_MGMT_SUC); - if (rc) - return rc; - - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_EXPANSION_ROM, - EFX_DEVLINK_INFO_VERSION_FW_EXPROM); - if (rc) - return rc; + int err; - rc = efx_devlink_info_nvram_partition(efx, req, - NVRAM_PARTITION_TYPE_EXPANSION_UEFI, - EFX_DEVLINK_INFO_VERSION_FW_UEFI); - return rc; + /* We do not care here about the specific error but just if an error + * happened. The specific error will be reported inside the call + * through system messages, and if any error happened in any call + * below, we report it through extack. + */ + err = efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_BUNDLE, + DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_MC_FIRMWARE, + DEVLINK_INFO_VERSION_GENERIC_FW_MGMT); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_SUC_FIRMWARE, + EFX_DEVLINK_INFO_VERSION_FW_MGMT_SUC); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_EXPANSION_ROM, + EFX_DEVLINK_INFO_VERSION_FW_EXPROM); + + err |= efx_devlink_info_nvram_partition(efx, req, + NVRAM_PARTITION_TYPE_EXPANSION_UEFI, + EFX_DEVLINK_INFO_VERSION_FW_UEFI); + return err; } #define EFX_VER_FLAG(_f) \ @@ -587,27 +589,20 @@ static int efx_devlink_info_get(struct devlink *devlink, { struct efx_devlink *devlink_private = devlink_priv(devlink); struct efx_nic *efx = devlink_private->efx; - int rc; + int err; - /* Several different MCDI commands are used. We report first error - * through extack returning at that point. Specific error - * information via system messages. + /* Several different MCDI commands are used. We report if errors + * happened through extack. Specific error information via system + * messages inside the calls. */ - rc = efx_devlink_info_board_cfg(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting board info failed"); - return rc; - } - rc = efx_devlink_info_stored_versions(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting stored versions failed"); - return rc; - } - rc = efx_devlink_info_running_versions(efx, req); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Getting running versions failed"); - return rc; - } + err = efx_devlink_info_board_cfg(efx, req); + + err |= efx_devlink_info_stored_versions(efx, req); + + err |= efx_devlink_info_running_versions(efx, req); + + if (err) + NL_SET_ERR_MSG_MOD(extack, "Errors when getting device info. Check system messages"); return 0; } -- GitLab From de678ca38861f2eb58814048076dcf95ed1b5bf9 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Thu, 18 May 2023 12:10:42 +0530 Subject: [PATCH 5185/5631] octeontx2-pf: Fix TSOv6 offload HW adds segment size to the payload length in the IPv6 header. Fix payload length to just TCP header length instead of 'TCP header size + IPv6 header size'. Fixes: 86d7476078b8 ("octeontx2-pf: TCP segmentation offload support") Signed-off-by: Sunil Goutham Signed-off-by: Ratheesh Kannoth Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 7045fedfd73a..7af223b0a37f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -652,9 +652,7 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, htons(ext->lso_sb - skb_network_offset(skb)); } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { ext->lso_format = pfvf->hw.lso_tsov6_idx; - - ipv6_hdr(skb)->payload_len = - htons(ext->lso_sb - skb_network_offset(skb)); + ipv6_hdr(skb)->payload_len = htons(tcp_hdrlen(skb)); } else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) { __be16 l3_proto = vlan_get_protocol(skb); struct udphdr *udph = udp_hdr(skb); -- GitLab From 3be5f6cd4a52b72ae31b77171da0912829c02096 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 18 May 2023 18:41:46 +0300 Subject: [PATCH 5186/5631] MAINTAINERS: add myself as maintainer for enetc I would like to be copied on new patches submitted on this driver. I am relatively familiar with the code, having practically maintained it for a while. Signed-off-by: Vladimir Oltean Acked-by: Claudiu Manoil Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 5c22c828ab46..02bfd2c39fe8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8159,6 +8159,7 @@ F: include/linux/spi/spi-fsl-dspi.h FREESCALE ENETC ETHERNET DRIVERS M: Claudiu Manoil +M: Vladimir Oltean L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/freescale/enetc/ -- GitLab From 9025944fddfed5966c8f102f1fe921ab3aee2c12 Mon Sep 17 00:00:00 2001 From: Shenwei Wang Date: Thu, 18 May 2023 10:02:02 -0500 Subject: [PATCH 5187/5631] net: fec: add dma_wmb to ensure correct descriptor values Two dma_wmb() are added in the XDP TX path to ensure proper ordering of descriptor and buffer updates: 1. A dma_wmb() is added after updating the last BD to make sure the updates to rest of the descriptor are visible before transferring ownership to FEC. 2. A dma_wmb() is also added after updating the bdp to ensure these updates are visible before updating txq->bd.cur. 3. Start the xmit of the frame immediately right after configuring the tx descriptor. Fixes: 6d6b39f180b8 ("net: fec: add initial XDP support") Signed-off-by: Shenwei Wang Reviewed-by: Wei Fang Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 577d94821b3e..38e5b5abe067 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3834,6 +3834,11 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, index = fec_enet_get_bd_index(last_bdp, &txq->bd); txq->tx_skbuff[index] = NULL; + /* Make sure the updates to rest of the descriptor are performed before + * transferring ownership. + */ + dma_wmb(); + /* Send it on its way. Tell FEC it's ready, interrupt when done, * it's the last BD of the frame, and to put the CRC on the end. */ @@ -3843,8 +3848,14 @@ static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, /* If this was the last BD in the ring, start at the beginning again. */ bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd); + /* Make sure the update to bdp are performed before txq->bd.cur. */ + dma_wmb(); + txq->bd.cur = bdp; + /* Trigger transmission start */ + writel(0, txq->bd.reg_desc_active); + return 0; } @@ -3873,12 +3884,6 @@ static int fec_enet_xdp_xmit(struct net_device *dev, sent_frames++; } - /* Make sure the update to bdp and tx_skbuff are performed. */ - wmb(); - - /* Trigger transmission start */ - writel(0, txq->bd.reg_desc_active); - __netif_tx_unlock(nq); return sent_frames; -- GitLab From 59112e9c390be595224e427827475a6cd3726021 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 18 May 2023 11:09:15 +0100 Subject: [PATCH 5188/5631] KVM: arm64: vgic: Fix a circular locking issue Lockdep reports a circular lock dependency between the srcu and the config_lock: [ 262.179917] -> #1 (&kvm->srcu){.+.+}-{0:0}: [ 262.182010] __synchronize_srcu+0xb0/0x224 [ 262.183422] synchronize_srcu_expedited+0x24/0x34 [ 262.184554] kvm_io_bus_register_dev+0x324/0x50c [ 262.185650] vgic_register_redist_iodev+0x254/0x398 [ 262.186740] vgic_v3_set_redist_base+0x3b0/0x724 [ 262.188087] kvm_vgic_addr+0x364/0x600 [ 262.189189] vgic_set_common_attr+0x90/0x544 [ 262.190278] vgic_v3_set_attr+0x74/0x9c [ 262.191432] kvm_device_ioctl+0x2a0/0x4e4 [ 262.192515] __arm64_sys_ioctl+0x7ac/0x1ba8 [ 262.193612] invoke_syscall.constprop.0+0x70/0x1e0 [ 262.195006] do_el0_svc+0xe4/0x2d4 [ 262.195929] el0_svc+0x44/0x8c [ 262.196917] el0t_64_sync_handler+0xf4/0x120 [ 262.198238] el0t_64_sync+0x190/0x194 [ 262.199224] [ 262.199224] -> #0 (&kvm->arch.config_lock){+.+.}-{3:3}: [ 262.201094] __lock_acquire+0x2b70/0x626c [ 262.202245] lock_acquire+0x454/0x778 [ 262.203132] __mutex_lock+0x190/0x8b4 [ 262.204023] mutex_lock_nested+0x24/0x30 [ 262.205100] vgic_mmio_write_v3_misc+0x5c/0x2a0 [ 262.206178] dispatch_mmio_write+0xd8/0x258 [ 262.207498] __kvm_io_bus_write+0x1e0/0x350 [ 262.208582] kvm_io_bus_write+0xe0/0x1cc [ 262.209653] io_mem_abort+0x2ac/0x6d8 [ 262.210569] kvm_handle_guest_abort+0x9b8/0x1f88 [ 262.211937] handle_exit+0xc4/0x39c [ 262.212971] kvm_arch_vcpu_ioctl_run+0x90c/0x1c04 [ 262.214154] kvm_vcpu_ioctl+0x450/0x12f8 [ 262.215233] __arm64_sys_ioctl+0x7ac/0x1ba8 [ 262.216402] invoke_syscall.constprop.0+0x70/0x1e0 [ 262.217774] do_el0_svc+0xe4/0x2d4 [ 262.218758] el0_svc+0x44/0x8c [ 262.219941] el0t_64_sync_handler+0xf4/0x120 [ 262.221110] el0t_64_sync+0x190/0x194 Note that the current report, which can be triggered by the vgic_irq kselftest, is a triple chain that includes slots_lock, but after inverting the slots_lock/config_lock dependency, the actual problem reported above remains. In several places, the vgic code calls kvm_io_bus_register_dev(), which synchronizes the srcu, while holding config_lock (#1). And the MMIO handler takes the config_lock while holding the srcu read lock (#0). Break dependency #1, by registering the distributor and redistributors without holding config_lock. The ITS also uses kvm_io_bus_register_dev() but already relies on slots_lock to serialize calls. The distributor iodev is created on the first KVM_RUN call. Multiple threads will race for vgic initialization, and only the first one will see !vgic_ready() under the lock. To serialize those threads, rely on slots_lock rather than config_lock. Redistributors are created earlier, through KVM_DEV_ARM_VGIC_GRP_ADDR ioctls and vCPU creation. Similarly, serialize the iodev creation with slots_lock, and the rest with config_lock. Fixes: f00327731131 ("KVM: arm64: Use config_lock to protect vgic state") Signed-off-by: Jean-Philippe Brucker Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230518100914.2837292-2-jean-philippe@linaro.org --- arch/arm64/kvm/vgic/vgic-init.c | 25 ++++++++++++++++----- arch/arm64/kvm/vgic/vgic-kvm-device.c | 10 +++++++-- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 31 ++++++++++++++++++--------- arch/arm64/kvm/vgic/vgic-mmio.c | 9 ++------ arch/arm64/kvm/vgic/vgic-v2.c | 6 ------ arch/arm64/kvm/vgic/vgic-v3.c | 7 ------ 6 files changed, 51 insertions(+), 37 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 9d42c7cb2b58..c199ba2f192e 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -235,9 +235,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - mutex_lock(&vcpu->kvm->arch.config_lock); + mutex_lock(&vcpu->kvm->slots_lock); ret = vgic_register_redist_iodev(vcpu); - mutex_unlock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->kvm->slots_lock); } return ret; } @@ -446,11 +446,13 @@ int vgic_lazy_init(struct kvm *kvm) int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + gpa_t dist_base; int ret = 0; if (likely(vgic_ready(kvm))) return 0; + mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); if (vgic_ready(kvm)) goto out; @@ -463,13 +465,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) else ret = vgic_v3_map_resources(kvm); - if (ret) + if (ret) { __kvm_vgic_destroy(kvm); - else - dist->ready = true; + goto out; + } + dist->ready = true; + dist_base = dist->vgic_dist_base; + mutex_unlock(&kvm->arch.config_lock); + + ret = vgic_register_dist_iodev(kvm, dist_base, + kvm_vgic_global_state.type); + if (ret) { + kvm_err("Unable to register VGIC dist MMIO regions\n"); + kvm_vgic_destroy(kvm); + } + mutex_unlock(&kvm->slots_lock); + return ret; out: mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 35cfa268fd5d..212b73a715c1 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -102,7 +102,11 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (get_user(addr, uaddr)) return -EFAULT; - mutex_lock(&kvm->arch.config_lock); + /* + * Since we can't hold config_lock while registering the redistributor + * iodevs, take the slots_lock immediately. + */ + mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -182,6 +186,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (r) goto out; + mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) @@ -189,9 +194,10 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri } else { addr = *addr_ptr; } + mutex_unlock(&kvm->arch.config_lock); out: - mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 472b18ac92a2..188d2187eede 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -769,10 +769,13 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; struct vgic_redist_region *rdreg; gpa_t rd_base; - int ret; + int ret = 0; + + lockdep_assert_held(&kvm->slots_lock); + mutex_lock(&kvm->arch.config_lock); if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) - return 0; + goto out_unlock; /* * We may be creating VCPUs before having set the base address for the @@ -782,10 +785,12 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) */ rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); if (!rdreg) - return 0; + goto out_unlock; - if (!vgic_v3_check_base(kvm)) - return -EINVAL; + if (!vgic_v3_check_base(kvm)) { + ret = -EINVAL; + goto out_unlock; + } vgic_cpu->rdreg = rdreg; vgic_cpu->rdreg_index = rdreg->free_index; @@ -799,16 +804,20 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers); rd_dev->redist_vcpu = vcpu; - mutex_lock(&kvm->slots_lock); + mutex_unlock(&kvm->arch.config_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base, 2 * SZ_64K, &rd_dev->dev); - mutex_unlock(&kvm->slots_lock); - if (ret) return ret; + /* Protected by slots_lock */ rdreg->free_index++; return 0; + +out_unlock: + mutex_unlock(&kvm->arch.config_lock); + return ret; } static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) @@ -834,12 +843,10 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) /* The current c failed, so iterate over the previous ones. */ int i; - mutex_lock(&kvm->slots_lock); for (i = 0; i < c; i++) { vcpu = kvm_get_vcpu(kvm, i); vgic_unregister_redist_iodev(vcpu); } - mutex_unlock(&kvm->slots_lock); } return ret; @@ -938,7 +945,9 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) { int ret; + mutex_lock(&kvm->arch.config_lock); ret = vgic_v3_alloc_redist_region(kvm, index, addr, count); + mutex_unlock(&kvm->arch.config_lock); if (ret) return ret; @@ -950,8 +959,10 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) if (ret) { struct vgic_redist_region *rdreg; + mutex_lock(&kvm->arch.config_lock); rdreg = vgic_v3_rdist_region_from_index(kvm, index); vgic_v3_free_redist_region(rdreg); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 1939c94e0b24..ff558c05e990 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -1096,7 +1096,6 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type type) { struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; - int ret = 0; unsigned int len; switch (type) { @@ -1114,10 +1113,6 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, io_device->iodev_type = IODEV_DIST; io_device->redist_vcpu = NULL; - mutex_lock(&kvm->slots_lock); - ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, - len, &io_device->dev); - mutex_unlock(&kvm->slots_lock); - - return ret; + return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, + len, &io_device->dev); } diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index 645648349c99..7e9cdb78f7ce 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -312,12 +312,6 @@ int vgic_v2_map_resources(struct kvm *kvm) return ret; } - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); - if (ret) { - kvm_err("Unable to register VGIC MMIO regions\n"); - return ret; - } - if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { ret = kvm_phys_addr_ioremap(kvm, dist->vgic_cpu_base, kvm_vgic_global_state.vcpu_base, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 93a47a515c13..c3b8e132d599 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -539,7 +539,6 @@ int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { @@ -569,12 +568,6 @@ int vgic_v3_map_resources(struct kvm *kvm) return -EBUSY; } - ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); - if (ret) { - kvm_err("Unable to register VGICv3 dist MMIO regions\n"); - return ret; - } - if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); -- GitLab From 9cf2f840c439b6b23bd99f584f2917ca425ae406 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 18 May 2023 11:09:16 +0100 Subject: [PATCH 5189/5631] KVM: arm64: vgic: Wrap vgic_its_create() with config_lock vgic_its_create() changes the vgic state without holding the config_lock, which triggers a lockdep warning in vgic_v4_init(): [ 358.667941] WARNING: CPU: 3 PID: 178 at arch/arm64/kvm/vgic/vgic-v4.c:245 vgic_v4_init+0x15c/0x7a8 ... [ 358.707410] vgic_v4_init+0x15c/0x7a8 [ 358.708550] vgic_its_create+0x37c/0x4a4 [ 358.709640] kvm_vm_ioctl+0x1518/0x2d80 [ 358.710688] __arm64_sys_ioctl+0x7ac/0x1ba8 [ 358.711960] invoke_syscall.constprop.0+0x70/0x1e0 [ 358.713245] do_el0_svc+0xe4/0x2d4 [ 358.714289] el0_svc+0x44/0x8c [ 358.715329] el0t_64_sync_handler+0xf4/0x120 [ 358.716615] el0t_64_sync+0x190/0x194 Wrap the whole of vgic_its_create() with config_lock since, in addition to calling vgic_v4_init(), it also modifies the global kvm->arch.vgic state. Fixes: f00327731131 ("KVM: arm64: Use config_lock to protect vgic state") Signed-off-by: Jean-Philippe Brucker Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230518100914.2837292-3-jean-philippe@linaro.org --- arch/arm64/kvm/vgic/vgic-its.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 750e51e3779a..5fe2365a629f 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -1936,6 +1936,7 @@ void vgic_lpi_translation_cache_destroy(struct kvm *kvm) static int vgic_its_create(struct kvm_device *dev, u32 type) { + int ret; struct vgic_its *its; if (type != KVM_DEV_TYPE_ARM_VGIC_ITS) @@ -1945,9 +1946,12 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) if (!its) return -ENOMEM; + mutex_lock(&dev->kvm->arch.config_lock); + if (vgic_initialized(dev->kvm)) { - int ret = vgic_v4_init(dev->kvm); + ret = vgic_v4_init(dev->kvm); if (ret < 0) { + mutex_unlock(&dev->kvm->arch.config_lock); kfree(its); return ret; } @@ -1960,12 +1964,10 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) /* Yep, even more trickery for lock ordering... */ #ifdef CONFIG_LOCKDEP - mutex_lock(&dev->kvm->arch.config_lock); mutex_lock(&its->cmd_lock); mutex_lock(&its->its_lock); mutex_unlock(&its->its_lock); mutex_unlock(&its->cmd_lock); - mutex_unlock(&dev->kvm->arch.config_lock); #endif its->vgic_its_base = VGIC_ADDR_UNDEF; @@ -1986,7 +1988,11 @@ static int vgic_its_create(struct kvm_device *dev, u32 type) dev->private = its; - return vgic_its_set_abi(its, NR_ITS_ABIS - 1); + ret = vgic_its_set_abi(its, NR_ITS_ABIS - 1); + + mutex_unlock(&dev->kvm->arch.config_lock); + + return ret; } static void vgic_its_destroy(struct kvm_device *kvm_dev) -- GitLab From c38b8400aef99d63be2b1ff131bb993465dcafe1 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 18 May 2023 11:09:17 +0100 Subject: [PATCH 5190/5631] KVM: arm64: vgic: Fix locking comment It is now config_lock that must be held, not kvm lock. Replace the comment with a lockdep annotation. Fixes: f00327731131 ("KVM: arm64: Use config_lock to protect vgic state") Signed-off-by: Jean-Philippe Brucker Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230518100914.2837292-4-jean-philippe@linaro.org --- arch/arm64/kvm/vgic/vgic-v4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 3bb003478060..c1c28fe680ba 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -184,13 +184,14 @@ static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) } } -/* Must be called with the kvm lock held */ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + kvm_arm_halt_guest(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { -- GitLab From 62548732260976ca88fcb17ef98ab661e7ce7504 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Thu, 18 May 2023 11:09:18 +0100 Subject: [PATCH 5191/5631] KVM: arm64: vgic: Fix a comment It is host userspace, not the guest, that issues KVM_DEV_ARM_VGIC_GRP_CTRL Signed-off-by: Jean-Philippe Brucker Reviewed-by: Oliver Upton Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230518100914.2837292-5-jean-philippe@linaro.org --- arch/arm64/kvm/vgic/vgic-init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index c199ba2f192e..6eafc2c45cfc 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -406,7 +406,7 @@ void kvm_vgic_destroy(struct kvm *kvm) /** * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest - * is a GICv2. A GICv3 must be explicitly initialized by the guest using the + * is a GICv2. A GICv3 must be explicitly initialized by userspace using the * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. * @kvm: kvm struct pointer */ -- GitLab From 09cce60bddd6461a93a5bf434265a47827d1bc6f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 18 May 2023 10:58:44 +0100 Subject: [PATCH 5192/5631] KVM: arm64: Prevent unconditional donation of unmapped regions from the host Since host stage-2 mappings are created lazily, we cannot rely solely on the pte in order to recover the target physical address when checking a host-initiated memory transition as this permits donation of unmapped regions corresponding to MMIO or "no-map" memory. Instead of inspecting the pte, move the addr_is_allowed_memory() check into the host callback function where it is passed the physical address directly from the walker. Cc: Quentin Perret Fixes: e82edcc75c4e ("KVM: arm64: Implement do_share() helper for sharing memory") Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230518095844.1178-1-will@kernel.org --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 2e9ec4a2a4a3..a8813b212996 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -575,7 +575,7 @@ struct pkvm_mem_donation { struct check_walk_data { enum pkvm_page_state desired; - enum pkvm_page_state (*get_page_state)(kvm_pte_t pte); + enum pkvm_page_state (*get_page_state)(kvm_pte_t pte, u64 addr); }; static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, @@ -583,10 +583,7 @@ static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, { struct check_walk_data *d = ctx->arg; - if (kvm_pte_valid(ctx->old) && !addr_is_allowed_memory(kvm_pte_to_phys(ctx->old))) - return -EINVAL; - - return d->get_page_state(ctx->old) == d->desired ? 0 : -EPERM; + return d->get_page_state(ctx->old, ctx->addr) == d->desired ? 0 : -EPERM; } static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, @@ -601,8 +598,11 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, return kvm_pgtable_walk(pgt, addr, size, &walker); } -static enum pkvm_page_state host_get_page_state(kvm_pte_t pte) +static enum pkvm_page_state host_get_page_state(kvm_pte_t pte, u64 addr) { + if (!addr_is_allowed_memory(addr)) + return PKVM_NOPAGE; + if (!kvm_pte_valid(pte) && pte) return PKVM_NOPAGE; @@ -709,7 +709,7 @@ static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx return host_stage2_set_owner_locked(addr, size, host_id); } -static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) +static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr) { if (!kvm_pte_valid(pte)) return PKVM_NOPAGE; -- GitLab From ddaf098ea779b3c1302c7843f6ff01e89b1fd380 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 16 May 2023 21:20:14 +0200 Subject: [PATCH 5193/5631] driver core: class: properly reference count class_dev_iter() When class_dev_iter is initialized, the reference count for the subsys private structure is incremented, but never decremented, causing a memory leak over time. To resolve this, save off a pointer to the internal structure into the class_dev_iter structure and then when the iterator is finished, drop the reference count. Reported-and-tested-by: syzbot+e7afd76ad060fa0d2605@syzkaller.appspotmail.com Fixes: 7b884b7f24b4 ("driver core: class.c: convert to only use class_to_subsys") Reported-by: Mirsad Goran Todorovac Cc: Alan Stern Acked-by: Rafael J. Wysocki Tested-by: Mirsad Goran Todorovac Link: https://lore.kernel.org/r/2023051610-stove-condense-9a77@gregkh Signed-off-by: Greg Kroah-Hartman --- drivers/base/class.c | 2 ++ include/linux/device/class.h | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/base/class.c b/drivers/base/class.c index ac1808d1a2e8..05d9df90f621 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -320,6 +320,7 @@ void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, start_knode = &start->p->knode_class; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; + iter->sp = sp; } EXPORT_SYMBOL_GPL(class_dev_iter_init); @@ -361,6 +362,7 @@ EXPORT_SYMBOL_GPL(class_dev_iter_next); void class_dev_iter_exit(struct class_dev_iter *iter) { klist_iter_exit(&iter->ki); + subsys_put(iter->sp); } EXPORT_SYMBOL_GPL(class_dev_iter_exit); diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 9deeaeb457bb..abf3d3bfb6fe 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -74,6 +74,7 @@ struct class { struct class_dev_iter { struct klist_iter ki; const struct device_type *type; + struct subsys_private *sp; }; int __must_check class_register(const struct class *class); -- GitLab From 4d43acb145c363626d76f49febb4240c488cd1cf Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 15 May 2023 13:32:10 +0300 Subject: [PATCH 5194/5631] dmaengine: at_xdmac: fix potential Oops in at_xdmac_prep_interleaved() There are two place if the at_xdmac_interleaved_queue_desc() fails which could lead to a NULL dereference where "first" is NULL and we call list_add_tail(&first->desc_node, ...). In the first caller, the return is not checked so add a check for that. In the next caller, the return is checked but if it fails on the first iteration through the loop then it will lead to a NULL pointer dereference. Fixes: 4e5385784e69 ("dmaengine: at_xdmac: handle numf > 1") Fixes: 62b5cb757f1d ("dmaengine: at_xdmac: fix memory leak in interleaved mode") Signed-off-by: Dan Carpenter Reviewed-by: Tudor Ambarus Link: https://lore.kernel.org/r/21282b66-9860-410a-83df-39c17fcf2f1b@kili.mountain Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 7da6d9b6098e..c3b37168b21f 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1102,6 +1102,8 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, NULL, src_addr, dst_addr, xt, xt->sgl); + if (!first) + return NULL; /* Length of the block is (BLEN+1) microblocks. */ for (i = 0; i < xt->numf - 1; i++) @@ -1132,8 +1134,9 @@ at_xdmac_prep_interleaved(struct dma_chan *chan, src_addr, dst_addr, xt, chunk); if (!desc) { - list_splice_tail_init(&first->descs_list, - &atchan->free_descs_list); + if (first) + list_splice_tail_init(&first->descs_list, + &atchan->free_descs_list); return NULL; } -- GitLab From 951efb9976ce453342a86b29d7bfe9fa483c7c4d Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 17 May 2023 15:57:05 -0700 Subject: [PATCH 5195/5631] perf test attr: Update no event/metric expectations Previously hard coded events/metrics were used, update for the use of the TopdownL1 json metric group. Reported-by: Arnaldo Carvalho de Melo Fixes: 94b1a603fca78388 ("perf stat: Add TopdownL1 metric as a default if present") Reviewed-by: James Clark Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Tested-by: Kan Liang Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Link: https://lore.kernel.org/r/20230517225707.2682235-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr/base-stat | 2 +- tools/perf/tests/attr/test-stat-default | 80 ++++++++----- tools/perf/tests/attr/test-stat-detailed-1 | 95 +++++++++------ tools/perf/tests/attr/test-stat-detailed-2 | 119 +++++++++++-------- tools/perf/tests/attr/test-stat-detailed-3 | 127 ++++++++++++--------- 5 files changed, 249 insertions(+), 174 deletions(-) diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index a21fb65bc012..fccd8ec4d1b0 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -16,7 +16,7 @@ pinned=0 exclusive=0 exclude_user=0 exclude_kernel=0|1 -exclude_hv=0 +exclude_hv=0|1 exclude_idle=0 mmap=0 comm=0 diff --git a/tools/perf/tests/attr/test-stat-default b/tools/perf/tests/attr/test-stat-default index d8ea6a88163f..a1e2da0a9a6d 100644 --- a/tools/perf/tests/attr/test-stat-default +++ b/tools/perf/tests/attr/test-stat-default @@ -40,7 +40,6 @@ fd=6 type=0 config=7 optional=1 - # PERF_TYPE_HARDWARE / PERF_COUNT_HW_STALLED_CYCLES_BACKEND [event7:base-stat] fd=7 @@ -89,79 +88,98 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-1 b/tools/perf/tests/attr/test-stat-detailed-1 index b656ab93c5bf..1c52cb05c900 100644 --- a/tools/perf/tests/attr/test-stat-detailed-1 +++ b/tools/perf/tests/attr/test-stat-detailed-1 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-2 b/tools/perf/tests/attr/test-stat-detailed-2 index 97625090a1c4..7e961d24a885 100644 --- a/tools/perf/tests/attr/test-stat-detailed-2 +++ b/tools/perf/tests/attr/test-stat-detailed-2 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 diff --git a/tools/perf/tests/attr/test-stat-detailed-3 b/tools/perf/tests/attr/test-stat-detailed-3 index d555042e3fbf..e50535f45977 100644 --- a/tools/perf/tests/attr/test-stat-detailed-3 +++ b/tools/perf/tests/attr/test-stat-detailed-3 @@ -90,89 +90,108 @@ enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-bad-spec (0x8100) +# PERF_TYPE_RAW / topdown-fe-bound (0x8200) [event13:base-stat] fd=13 group_fd=11 type=4 -config=33024 +config=33280 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-fe-bound (0x8200) +# PERF_TYPE_RAW / topdown-be-bound (0x8300) [event14:base-stat] fd=14 group_fd=11 type=4 -config=33280 +config=33536 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-be-bound (0x8300) +# PERF_TYPE_RAW / topdown-bad-spec (0x8100) [event15:base-stat] fd=15 group_fd=11 type=4 -config=33536 +config=33024 disabled=0 enable_on_exec=0 read_format=15 optional=1 -# PERF_TYPE_RAW / topdown-heavy-ops (0x8400) +# PERF_TYPE_RAW / INT_MISC.UOP_DROPPING [event16:base-stat] fd=16 -group_fd=11 type=4 -config=33792 -disabled=0 -enable_on_exec=0 -read_format=15 +config=4109 optional=1 -# PERF_TYPE_RAW / topdown-br-mispredict (0x8500) +# PERF_TYPE_RAW / cpu/INT_MISC.RECOVERY_CYCLES,cmask=1,edge/ [event17:base-stat] fd=17 -group_fd=11 type=4 -config=34048 -disabled=0 -enable_on_exec=0 -read_format=15 +config=17039629 optional=1 -# PERF_TYPE_RAW / topdown-fetch-lat (0x8600) +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.THREAD [event18:base-stat] fd=18 -group_fd=11 type=4 -config=34304 -disabled=0 -enable_on_exec=0 -read_format=15 +config=60 optional=1 -# PERF_TYPE_RAW / topdown-mem-bound (0x8700) +# PERF_TYPE_RAW / INT_MISC.RECOVERY_CYCLES_ANY [event19:base-stat] fd=19 -group_fd=11 type=4 -config=34560 -disabled=0 -enable_on_exec=0 -read_format=15 +config=2097421 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.REF_XCLK +[event20:base-stat] +fd=20 +type=4 +config=316 +optional=1 + +# PERF_TYPE_RAW / IDQ_UOPS_NOT_DELIVERED.CORE +[event21:base-stat] +fd=21 +type=4 +config=412 +optional=1 + +# PERF_TYPE_RAW / CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE +[event22:base-stat] +fd=22 +type=4 +config=572 +optional=1 + +# PERF_TYPE_RAW / UOPS_RETIRED.RETIRE_SLOTS +[event23:base-stat] +fd=23 +type=4 +config=706 +optional=1 + +# PERF_TYPE_RAW / UOPS_ISSUED.ANY +[event24:base-stat] +fd=24 +type=4 +config=270 optional=1 # PERF_TYPE_HW_CACHE / # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event20:base-stat] -fd=20 +[event25:base-stat] +fd=25 type=3 config=0 optional=1 @@ -181,8 +200,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event21:base-stat] -fd=21 +[event26:base-stat] +fd=26 type=3 config=65536 optional=1 @@ -191,8 +210,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event22:base-stat] -fd=22 +[event27:base-stat] +fd=27 type=3 config=2 optional=1 @@ -201,8 +220,8 @@ optional=1 # PERF_COUNT_HW_CACHE_LL << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event23:base-stat] -fd=23 +[event28:base-stat] +fd=28 type=3 config=65538 optional=1 @@ -211,8 +230,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event24:base-stat] -fd=24 +[event29:base-stat] +fd=29 type=3 config=1 optional=1 @@ -221,8 +240,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1I << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event25:base-stat] -fd=25 +[event30:base-stat] +fd=30 type=3 config=65537 optional=1 @@ -231,8 +250,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event26:base-stat] -fd=26 +[event31:base-stat] +fd=31 type=3 config=3 optional=1 @@ -241,8 +260,8 @@ optional=1 # PERF_COUNT_HW_CACHE_DTLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event27:base-stat] -fd=27 +[event32:base-stat] +fd=32 type=3 config=65539 optional=1 @@ -251,8 +270,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event28:base-stat] -fd=28 +[event33:base-stat] +fd=33 type=3 config=4 optional=1 @@ -261,8 +280,8 @@ optional=1 # PERF_COUNT_HW_CACHE_ITLB << 0 | # (PERF_COUNT_HW_CACHE_OP_READ << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event29:base-stat] -fd=29 +[event34:base-stat] +fd=34 type=3 config=65540 optional=1 @@ -271,8 +290,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) -[event30:base-stat] -fd=30 +[event35:base-stat] +fd=35 type=3 config=512 optional=1 @@ -281,8 +300,8 @@ optional=1 # PERF_COUNT_HW_CACHE_L1D << 0 | # (PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) | # (PERF_COUNT_HW_CACHE_RESULT_MISS << 16) -[event31:base-stat] -fd=31 +[event36:base-stat] +fd=36 type=3 config=66048 optional=1 -- GitLab From 75438f24a4d4adcaea6f04ad3a94b7a145e63327 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 17 May 2023 15:57:06 -0700 Subject: [PATCH 5196/5631] perf test attr: Fix python SafeConfigParser() deprecation warning Address the warning: ``` tests/attr.py:155: DeprecationWarning: The SafeConfigParser class has been renamed to ConfigParser in Python 3.2. This alias will be removed in Python 3.12. Use ConfigParser directly instead. parser = configparser.SafeConfigParser() ``` by removing the word 'Safe'. Reviewed-by: James Clark Signed-off-by: Ian Rogers Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Richter Link: https://lore.kernel.org/r/20230517225707.2682235-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/attr.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index ccfef861e931..e890c261ad26 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -152,7 +152,7 @@ def parse_version(version): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = configparser.SafeConfigParser() + parser = configparser.ConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -247,7 +247,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = configparser.SafeConfigParser() + parser_event = configparser.ConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -261,7 +261,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = configparser.SafeConfigParser() + parser_base = configparser.ConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') -- GitLab From aa8bf93101a185b49f83c9137453571a08be6e76 Mon Sep 17 00:00:00 2001 From: Vladislav Efanov Date: Wed, 17 May 2023 15:52:47 +0300 Subject: [PATCH 5197/5631] drm/sched: Remove redundant check The rq pointer points inside the drm_gpu_scheduler structure. Thus it can't be NULL. Found by Linux Verification Center (linuxtesting.org) with SVACE. Fixes: c61cdbdbffc1 ("drm/scheduler: Fix hang when sched_entity released") Signed-off-by: Vladislav Efanov Link: https://lore.kernel.org/r/20230517125247.434103-1-VEfanov@ispras.ru Reviewed-by: Luben Tuikov Signed-off-by: Luben Tuikov --- drivers/gpu/drm/scheduler/sched_main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 8c183639603e..aea5a90ff98b 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1141,9 +1141,6 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched) for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { struct drm_sched_rq *rq = &sched->sched_rq[i]; - if (!rq) - continue; - spin_lock(&rq->lock); list_for_each_entry(s_entity, &rq->entities, list) /* -- GitLab From 46f5dd7439e35ae63cdf04d7967152936c8a511e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 15 May 2023 13:32:47 +0300 Subject: [PATCH 5198/5631] fbdev: omapfb: panel-tpo-td043mtea1: fix error code in probe() This was using the wrong variable, "r", instead of "ddata->vcc_reg", so it returned success instead of a negative error code. Fixes: 0d3dbeb8142a ("video: fbdev: omapfb: panel-tpo-td043mtea1: Make use of the helper function dev_err_probe()") Signed-off-by: Dan Carpenter Signed-off-by: Helge Deller --- .../video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c index 1eaa35c27835..477789cff8e0 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td043mtea1.c @@ -491,7 +491,8 @@ static int tpo_td043_probe(struct spi_device *spi) ddata->vcc_reg = devm_regulator_get(&spi->dev, "vcc"); if (IS_ERR(ddata->vcc_reg)) { - r = dev_err_probe(&spi->dev, r, "failed to get LCD VCC regulator\n"); + r = dev_err_probe(&spi->dev, PTR_ERR(ddata->vcc_reg), + "failed to get LCD VCC regulator\n"); goto err_regulator; } -- GitLab From 4e111f0cf0ee973ce7e7e012b4ceb07867d2dae5 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 19 May 2023 15:17:37 +0800 Subject: [PATCH 5199/5631] perf bench syscall: Fix __NR_execve undeclared build error The __NR_execve definition for i386 was deleted by mistake in the commit ece7f7c0507c ("perf bench syscall: Add fork syscall benchmark"), add it to fix the build error on i386. Fixes: ece7f7c0507cc147 ("perf bench syscall: Add fork syscall benchmark") Reported-by: Linux Kernel Functional Testing Signed-off-by: Tiezhu Yang Tested-by: Naresh Kamboju Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Tiezhu Yang Cc: loongson-kernel@lists.loongnix.cn Closes: https://lore.kernel.org/all/CA+G9fYvgBR1iB0CorM8OC4AM_w_tFzyQKHc+rF6qPzJL=TbfDQ@mail.gmail.com/ Link: https://lore.kernel.org/r/1684480657-2375-1-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/unistd_32.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index b8ddfc4c4ab0..bc48a4dabe5d 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -2,6 +2,9 @@ #ifndef __NR_fork #define __NR_fork 2 #endif +#ifndef __NR_execve +#define __NR_execve 11 +#endif #ifndef __NR_getppid #define __NR_getppid 64 #endif -- GitLab From 349e3c0cf239cc01d58a1e6c749e171de014cd6a Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 01:10:59 -0700 Subject: [PATCH 5200/5631] RDMA/bnxt_re: Fix a possible memory leak Inside bnxt_qplib_create_cq(), when the check for NULL DPI fails, driver returns directly without freeing the memory allocated inside bnxt_qplib_alloc_init_hwq() routine. Fixed this by moving the check for NULL DPI before invoking bnxt_qplib_alloc_init_hwq(). Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684397461-23082-2-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Kashyap Desai Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index f139d4cd1712..8974f6235cfa 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -2056,6 +2056,12 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) u32 pg_sz_lvl; int rc; + if (!cq->dpi) { + dev_err(&rcfw->pdev->dev, + "FP: CREATE_CQ failed due to NULL DPI\n"); + return -EINVAL; + } + hwq_attr.res = res; hwq_attr.depth = cq->max_wqe; hwq_attr.stride = sizeof(struct cq_base); @@ -2069,11 +2075,6 @@ int bnxt_qplib_create_cq(struct bnxt_qplib_res *res, struct bnxt_qplib_cq *cq) CMDQ_BASE_OPCODE_CREATE_CQ, sizeof(req)); - if (!cq->dpi) { - dev_err(&rcfw->pdev->dev, - "FP: CREATE_CQ failed due to NULL DPI\n"); - return -EINVAL; - } req.dpi = cpu_to_le32(cq->dpi->dpi); req.cq_handle = cpu_to_le64(cq->cq_handle); req.cq_size = cpu_to_le32(cq->hwq.max_elements); -- GitLab From 0fa0d520e2a878cb4c94c4dc84395905d3f14f54 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 01:11:00 -0700 Subject: [PATCH 5201/5631] RDMA/bnxt_re: Fix return value of bnxt_re_process_raw_qp_pkt_rx bnxt_re_process_raw_qp_pkt_rx() always return 0 and ignores the return value of bnxt_re_post_send_shadow_qp(). Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Link: https://lore.kernel.org/r/1684397461-23082-3-git-send-email-selvin.xavier@broadcom.com Reviewed-by: Hongguang Gao Reviewed-by: Ajit Khaparde Signed-off-by: Kalesh AP Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/ib_verbs.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index e86afecfbe46..b1c36412025f 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -3341,9 +3341,7 @@ static int bnxt_re_process_raw_qp_pkt_rx(struct bnxt_re_qp *gsi_qp, udwr.remote_qkey = gsi_sqp->qplib_qp.qkey; /* post data received in the send queue */ - rc = bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); - - return 0; + return bnxt_re_post_send_shadow_qp(rdev, gsi_sqp, swr); } static void bnxt_re_process_res_rawqp1_wc(struct ib_wc *wc, -- GitLab From dd5fb04857d7346c9ea4901ec3ebe5b90b0e8868 Mon Sep 17 00:00:00 2001 From: Kalesh AP Date: Thu, 18 May 2023 01:11:01 -0700 Subject: [PATCH 5202/5631] RDMA/bnxt_re: Do not enable congestion control on VFs Congestion control needs to be enabled only on the PFs. FW fails the command if issued on VFs. Avoid sending the command on VFs. Fixes: f13bcef04ba0 ("RDMA/bnxt_re: Enable congestion control by default") Link: https://lore.kernel.org/r/1684397461-23082-4-git-send-email-selvin.xavier@broadcom.com Signed-off-by: Kalesh AP Reviewed-by: Selvin Thyparampil Xavier Signed-off-by: Selvin Xavier Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/bnxt_re/main.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index b9e2f89337e8..e34eccd178d0 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1336,6 +1336,10 @@ static void bnxt_re_setup_cc(struct bnxt_re_dev *rdev, bool enable) { struct bnxt_qplib_cc_param cc_param = {}; + /* Do not enable congestion control on VFs */ + if (rdev->is_virtfn) + return; + /* Currently enabling only for GenP5 adapters */ if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) return; -- GitLab From 0613d8ca9ab382caabe9ed2dceb429e9781e443f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 18 May 2023 11:25:28 +0100 Subject: [PATCH 5203/5631] bpf: Fix mask generation for 32-bit narrow loads of 64-bit fields A narrow load from a 64-bit context field results in a 64-bit load followed potentially by a 64-bit right-shift and then a bitwise AND operation to extract the relevant data. In the case of a 32-bit access, an immediate mask of 0xffffffff is used to construct a 64-bit BPP_AND operation which then sign-extends the mask value and effectively acts as a glorified no-op. For example: 0: 61 10 00 00 00 00 00 00 r0 = *(u32 *)(r1 + 0) results in the following code generation for a 64-bit field: ldr x7, [x7] // 64-bit load mov x10, #0xffffffffffffffff and x7, x7, x10 Fix the mask generation so that narrow loads always perform a 32-bit AND operation: ldr x7, [x7] // 64-bit load mov w10, #0xffffffff and w7, w7, w10 Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: John Fastabend Cc: Krzesimir Nowak Cc: Andrey Ignatov Acked-by: Yonghong Song Fixes: 31fd85816dbe ("bpf: permits narrower load from bpf program context fields") Signed-off-by: Will Deacon Link: https://lore.kernel.org/r/20230518102528.1341-1-will@kernel.org Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fbcf5a4e2fcd..5871aa78d01a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -17033,7 +17033,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH, insn->dst_reg, shift); - insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg, + insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg, (1ULL << size * 8) - 1); } } -- GitLab From 6735150b69978a9f73e3d1bab719e81a5dfafa83 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 12 May 2023 16:31:26 -0700 Subject: [PATCH 5204/5631] KVM: Use syscore_ops instead of reboot_notifier to hook restart/shutdown Use syscore_ops.shutdown to disable hardware virtualization during a reboot instead of using the dedicated reboot_notifier so that KVM disables virtualization _after_ system_state has been updated. This will allow fixing a race in KVM's handling of a forced reboot where KVM can end up enabling hardware virtualization between kernel_restart_prepare() and machine_restart(). Rename KVM's hook to match the syscore op to avoid any possible confusion from wiring up a "reboot" helper to a "shutdown" hook (neither "shutdown nor "reboot" is completely accurate as the hook handles both). Opportunistically rewrite kvm_shutdown()'s comment to make it less VMX specific, and to explain why kvm_rebooting exists. Cc: Marc Zyngier Cc: Oliver Upton Cc: James Morse Cc: Suzuki K Poulose Cc: Zenghui Yu Cc: kvmarm@lists.linux.dev Cc: Huacai Chen Cc: Aleksandar Markovic Cc: Anup Patel Cc: Atish Patra Cc: kvm-riscv@lists.infradead.org Signed-off-by: Sean Christopherson Acked-by: Marc Zyngier Message-Id: <20230512233127.804012-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cb5c13eee193..2079d6065795 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5213,26 +5213,24 @@ static int hardware_enable_all(void) return r; } -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) +static void kvm_shutdown(void) { /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - * - * And Intel TXT required VMX off for all cpu when system shutdown. + * Disable hardware virtualization and set kvm_rebooting to indicate + * that KVM has asynchronously disabled hardware virtualization, i.e. + * that relevant errors and exceptions aren't entirely unexpected. + * Some flavors of hardware virtualization need to be disabled before + * transferring control to firmware (to perform shutdown/reboot), e.g. + * on x86, virtualization can block INIT interrupts, which are used by + * firmware to pull APs back under firmware control. Note, this path + * is used for both shutdown and reboot scenarios, i.e. neither name is + * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); - return NOTIFY_OK; } -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - static int kvm_suspend(void) { /* @@ -5263,6 +5261,7 @@ static void kvm_resume(void) static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, + .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) @@ -5967,7 +5966,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) if (r) return r; - register_reboot_notifier(&kvm_reboot_notifier); register_syscore_ops(&kvm_syscore_ops); #endif @@ -6039,7 +6037,6 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; @@ -6065,7 +6062,6 @@ void kvm_exit(void) kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); - unregister_reboot_notifier(&kvm_reboot_notifier); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); -- GitLab From e0ceec221f62deb5d6c32c0327030028d3db5f27 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 12 May 2023 16:31:27 -0700 Subject: [PATCH 5205/5631] KVM: Don't enable hardware after a restart/shutdown is initiated Reject hardware enabling, i.e. VM creation, if a restart/shutdown has been initiated to avoid re-enabling hardware between kvm_reboot() and machine_{halt,power_off,restart}(). The restart case is especially problematic (for x86) as enabling VMX (or clearing GIF in KVM_RUN on SVM) blocks INIT, which results in the restart/reboot hanging as BIOS is unable to wake and rendezvous with APs. Note, this bug, and the original issue that motivated the addition of kvm_reboot(), is effectively limited to a forced reboot, e.g. `reboot -f`. In a "normal" reboot, userspace will gracefully teardown userspace before triggering the kernel reboot (modulo bugs, errors, etc), i.e. any process that might do ioctl(KVM_CREATE_VM) is long gone. Fixes: 8e1c18157d87 ("KVM: VMX: Disable VMX when system shutdown") Signed-off-by: Sean Christopherson Acked-by: Marc Zyngier Message-Id: <20230512233127.804012-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2079d6065795..540e2bbf00f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5184,7 +5184,20 @@ static void hardware_disable_all(void) static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); - int r = 0; + int r; + + /* + * Do not enable hardware virtualization if the system is going down. + * If userspace initiated a forced reboot, e.g. reboot -f, then it's + * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling + * after kvm_reboot() is called. Note, this relies on system_state + * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops + * hook instead of registering a dedicated reboot notifier (the latter + * runs before system_state is updated). + */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || + system_state == SYSTEM_RESTART) + return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() @@ -5197,6 +5210,8 @@ static int hardware_enable_all(void) cpus_read_lock(); mutex_lock(&kvm_lock); + r = 0; + kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); -- GitLab From 3367eeab975145e65136c2d091fe6e0c6cb29636 Mon Sep 17 00:00:00 2001 From: Jacob Xu Date: Thu, 24 Feb 2022 17:29:59 -0800 Subject: [PATCH 5206/5631] KVM: VMX: Fix header file dependency of asm/vmx.h Include a definition of WARN_ON_ONCE() before using it. Fixes: bb1fcc70d98f ("KVM: nVMX: Allow L1 to use 5-level page walks for nested EPT") Cc: Sean Christopherson Signed-off-by: Jacob Xu [reworded commit message; changed to ] Signed-off-by: Jim Mattson Reviewed-by: Sean Christopherson Message-Id: <20220225012959.1554168-1-jmattson@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/vmx.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 498dc600bd5c..0d02c4aafa6f 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -13,7 +13,9 @@ #include +#include #include + #include #include -- GitLab From afb2acb2e3a32e4d56f7fbd819769b98ed1b7520 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Wed, 10 May 2023 16:04:09 +0200 Subject: [PATCH 5207/5631] KVM: Fix vcpu_array[0] races In kvm_vm_ioctl_create_vcpu(), add vcpu to vcpu_array iff it's safe to access vcpu via kvm_get_vcpu() and kvm_for_each_vcpu(), i.e. when there's no failure path requiring vcpu removal and destruction. Such order is important because vcpu_array accessors may end up referencing vcpu at vcpu_array[0] even before online_vcpus is set to 1. When online_vcpus=0, any call to kvm_get_vcpu() goes through array_index_nospec() and ends with an attempt to xa_load(vcpu_array, 0): int num_vcpus = atomic_read(&kvm->online_vcpus); i = array_index_nospec(i, num_vcpus); return xa_load(&kvm->vcpu_array, i); Similarly, when online_vcpus=0, a kvm_for_each_vcpu() does not iterate over an "empty" range, but actually [0, ULONG_MAX]: xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ (atomic_read(&kvm->online_vcpus) - 1)) In both cases, such online_vcpus=0 edge case, even if leading to unnecessary calls to XArray API, should not be an issue; requesting unpopulated indexes/ranges is handled by xa_load() and xa_for_each_range(). However, this means that when the first vCPU is created and inserted in vcpu_array *and* before online_vcpus is incremented, code calling kvm_get_vcpu()/kvm_for_each_vcpu() already has access to that first vCPU. This should not pose a problem assuming that once a vcpu is stored in vcpu_array, it will remain there, but that's not the case: kvm_vm_ioctl_create_vcpu() first inserts to vcpu_array, then requests a file descriptor. If create_vcpu_fd() fails, newly inserted vcpu is removed from the vcpu_array, then destroyed: vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } atomic_inc(&kvm->online_vcpus); This results in a possible race condition when a reference to a vcpu is acquired (via kvm_get_vcpu() or kvm_for_each_vcpu()) moments before said vcpu is destroyed. Signed-off-by: Michal Luczaj Message-Id: <20230510140410.1093987-2-mhal@rbox.co> Cc: stable@vger.kernel.org Fixes: c5b077549136 ("KVM: Convert the kvm->vcpus array to a xarray", 2021-12-08) Signed-off-by: Paolo Bonzini --- virt/kvm/kvm_main.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 540e2bbf00f7..479802a892d4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3962,18 +3962,19 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); - BUG_ON(r == -EBUSY); + r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); - if (r < 0) { - xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); - kvm_put_kvm_no_destroy(kvm); - goto unlock_vcpu_destroy; + if (r < 0) + goto kvm_put_xa_release; + + if (KVM_BUG_ON(!!xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { + r = -EINVAL; + goto kvm_put_xa_release; } /* @@ -3988,6 +3989,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_create_vcpu_debugfs(vcpu); return r; +kvm_put_xa_release: + kvm_put_kvm_no_destroy(kvm); + xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); -- GitLab From 4b71e2416ec4cb3edd6c667243bce357b0c6f7b3 Mon Sep 17 00:00:00 2001 From: "Fabio M. De Francesco" Date: Wed, 3 May 2023 19:24:11 +0200 Subject: [PATCH 5208/5631] NFS: Convert kmap_atomic() to kmap_local_folio() kmap_atomic() is deprecated in favor of kmap_local_{folio,page}(). Therefore, replace kmap_atomic() with kmap_local_folio() in nfs_readdir_folio_array_append(). kmap_atomic() disables page-faults and preemption (the latter only for !PREEMPT_RT kernels), However, the code within the mapping/un-mapping in nfs_readdir_folio_array_append() does not depend on the above-mentioned side effects. Therefore, a mere replacement of the old API with the new one is all that is required (i.e., there is no need to explicitly add any calls to pagefault_disable() and/or preempt_disable()). Tested with (x)fstests in a QEMU/KVM x86_32 VM, 6GB RAM, booting a kernel with HIGHMEM64GB enabled. Cc: Ira Weiny Signed-off-by: Fabio M. De Francesco Fixes: ec108d3cc766 ("NFS: Convert readdir page array functions to use a folio") Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e63c1d46f189..8f3112e71a6a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -317,7 +317,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, name = nfs_readdir_copy_name(entry->name, entry->len); - array = kmap_atomic(folio_page(folio, 0)); + array = kmap_local_folio(folio, 0); if (!name) goto out; ret = nfs_readdir_array_can_expand(array); @@ -340,7 +340,7 @@ static int nfs_readdir_folio_array_append(struct folio *folio, nfs_readdir_array_set_eof(array); out: *cookie = array->last_cookie; - kunmap_atomic(array); + kunmap_local(array); return ret; } -- GitLab From d180891fba995bd54e25b089b1ec98d134873586 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 10 May 2023 12:28:00 -0400 Subject: [PATCH 5209/5631] SUNRPC: Don't change task->tk_status after the call to rpc_exit_task Some calls to rpc_exit_task() may deliberately change the value of task->tk_status, for instance because it gets checked by the RPC call's rpc_release() callback. That makes it wrong to reset the value to task->tk_rpc_status. In particular this causes a bug where the rpc_call_done() callback tries to fail over a set of pNFS/flexfiles writes to a different IP address, but the reset of task->tk_status causes nfs_commit_release_pages() to immediately mark the file as having a fatal error. Fixes: 39494194f93b ("SUNRPC: Fix races with rpc_killall_tasks()") Cc: stable@vger.kernel.org # 6.1.x Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- net/sunrpc/sched.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index c8321de341ee..6debf4fd42d4 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -927,11 +927,10 @@ static void __rpc_execute(struct rpc_task *task) */ do_action = task->tk_action; /* Tasks with an RPC error status should exit */ - if (do_action != rpc_exit_task && + if (do_action && do_action != rpc_exit_task && (status = READ_ONCE(task->tk_rpc_status)) != 0) { task->tk_status = status; - if (do_action != NULL) - do_action = rpc_exit_task; + do_action = rpc_exit_task; } /* Callbacks override all actions */ if (task->tk_callback) { -- GitLab From 43439d858bbae244a510de47f9a55f667ca4ed52 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Tue, 16 May 2023 11:19:25 -0400 Subject: [PATCH 5210/5631] NFSv4.2: Fix a potential double free with READ_PLUS kfree()-ing the scratch page isn't enough, we also need to set the pointer back to NULL to avoid a double-free in the case of a resend. Fixes: fbd2a05f29a9 (NFSv4.2: Rework scratch handling for READ_PLUS) Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 18f25ff4bff7..d3665390c4cb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5437,10 +5437,18 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task, return false; } -static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +static inline void nfs4_read_plus_scratch_free(struct nfs_pgio_header *hdr) { - if (hdr->res.scratch) + if (hdr->res.scratch) { kfree(hdr->res.scratch); + hdr->res.scratch = NULL; + } +} + +static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr) +{ + nfs4_read_plus_scratch_free(hdr); + if (!nfs4_sequence_done(task, &hdr->res.seq_res)) return -EAGAIN; if (nfs4_read_stateid_changed(task, &hdr->args)) -- GitLab From ca1fd42e7dbfcb34890ffbf1f2f4b356776dab6f Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Wed, 3 May 2023 21:39:34 +0800 Subject: [PATCH 5211/5631] Bluetooth: Fix potential double free caused by hci_conn_unlink The hci_conn_unlink function is being called by hci_conn_del, which means it should not call hci_conn_del with the input parameter conn again. If it does, conn may have already been released when hci_conn_unlink returns, leading to potential UAF and double-free issues. This patch resolves the problem by modifying hci_conn_unlink to release only conn's child links when necessary, but never release conn itself. Reported-by: syzbot+690b90b14f14f43f4688@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-bluetooth/000000000000484a8205faafe216@google.com/ Fixes: 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") Signed-off-by: Ruihan Li Signed-off-by: Luiz Augusto von Dentz Reported-by: syzbot+690b90b14f14f43f4688@syzkaller.appspotmail.com Reported-by: Luiz Augusto von Dentz Reported-by: syzbot+8bb72f86fc823817bc5d@syzkaller.appspotmail.com --- net/bluetooth/hci_conn.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 640b951bf40a..70e1655a9df6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1083,8 +1083,18 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->parent) { struct hci_link *link, *t; - list_for_each_entry_safe(link, t, &conn->link_list, list) - hci_conn_unlink(link->conn); + list_for_each_entry_safe(link, t, &conn->link_list, list) { + struct hci_conn *child = link->conn; + + hci_conn_unlink(child); + + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if (child->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(child); + } return; } @@ -1100,13 +1110,6 @@ static void hci_conn_unlink(struct hci_conn *conn) kfree(conn->link); conn->link = NULL; - - /* Due to race, SCO connection might be not established - * yet at this point. Delete it now, otherwise it is - * possible for it to be stuck and can't be deleted. - */ - if (conn->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(conn); } int hci_conn_del(struct hci_conn *conn) -- GitLab From 2910431ab0e500dfc5df12299bb15eef0f30b43e Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Wed, 3 May 2023 21:39:35 +0800 Subject: [PATCH 5212/5631] Bluetooth: Refcnt drop must be placed last in hci_conn_unlink If hci_conn_put(conn->parent) reduces conn->parent's reference count to zero, it can immediately deallocate conn->parent. At the same time, conn->link->list has its head in conn->parent, causing use-after-free problems in the latter list_del_rcu(&conn->link->list). This problem can be easily solved by reordering the two operations, i.e., first performing the list removal with list_del_rcu and then decreasing the refcnt with hci_conn_put. Reported-by: Luiz Augusto von Dentz Closes: https://lore.kernel.org/linux-bluetooth/CABBYNZ+1kce8_RJrLNOXd_8=Mdpb=2bx4Nto-hFORk=qiOkoCg@mail.gmail.com/ Fixes: 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") Signed-off-by: Ruihan Li Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_conn.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 70e1655a9df6..44d0643fc681 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1102,12 +1102,12 @@ static void hci_conn_unlink(struct hci_conn *conn) if (!conn->link) return; - hci_conn_put(conn->parent); - conn->parent = NULL; - list_del_rcu(&conn->link->list); synchronize_rcu(); + hci_conn_put(conn->parent); + conn->parent = NULL; + kfree(conn->link); conn->link = NULL; } -- GitLab From a2ac591cb4d83e1f2d4b4adb3c14b2c79764650a Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Wed, 3 May 2023 21:39:36 +0800 Subject: [PATCH 5213/5631] Bluetooth: Fix UAF in hci_conn_hash_flush again Commit 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") reintroduced a previously fixed bug [1] ("KASAN: slab-use-after-free Read in hci_conn_hash_flush"). This bug was originally fixed by commit 5dc7d23e167e ("Bluetooth: hci_conn: Fix possible UAF"). The hci_conn_unlink function was added to avoid invalidating the link traversal caused by successive hci_conn_del operations releasing extra connections. However, currently hci_conn_unlink itself also releases extra connections, resulted in the reintroduced bug. This patch follows a more robust solution for cleaning up all connections, by repeatedly removing the first connection until there are none left. This approach does not rely on the inner workings of hci_conn_del and ensures proper cleanup of all connections. Meanwhile, we need to make sure that hci_conn_del never fails. Indeed it doesn't, as it now always returns zero. To make this a bit clearer, this patch also changes its return type to void. Reported-by: syzbot+8bb72f86fc823817bc5d@syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-bluetooth/000000000000aa920505f60d25ad@google.com/ Fixes: 06149746e720 ("Bluetooth: hci_conn: Add support for linking multiple hcon") Signed-off-by: Ruihan Li Co-developed-by: Luiz Augusto von Dentz Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_conn.c | 33 +++++++++++++++++++++----------- 2 files changed, 23 insertions(+), 12 deletions(-) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index a6c8aee2f256..8baf34639939 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1327,7 +1327,7 @@ int hci_le_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); -int hci_conn_del(struct hci_conn *conn); +void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 44d0643fc681..ce588359b290 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1088,6 +1088,14 @@ static void hci_conn_unlink(struct hci_conn *conn) hci_conn_unlink(child); + /* If hdev is down it means + * hci_dev_close_sync/hci_conn_hash_flush is in progress + * and links don't need to be cleanup as all connections + * would be cleanup. + */ + if (!test_bit(HCI_UP, &hdev->flags)) + continue; + /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. @@ -1112,7 +1120,7 @@ static void hci_conn_unlink(struct hci_conn *conn) conn->link = NULL; } -int hci_conn_del(struct hci_conn *conn) +void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1163,8 +1171,6 @@ int hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); - - return 0; } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -2465,22 +2471,27 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c, *n; + struct list_head *head = &hdev->conn_hash.list; + struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); - list_for_each_entry_safe(c, n, &h->list, list) { - c->state = BT_CLOSED; - - hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + /* We should not traverse the list here, because hci_conn_del + * can remove extra links, which may cause the list traversal + * to hit items that have already been released. + */ + while ((conn = list_first_entry_or_null(head, + struct hci_conn, + list)) != NULL) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); /* Unlink before deleting otherwise it is possible that * hci_conn_del removes the link which may cause the list to * contain items already freed. */ - hci_conn_unlink(c); - hci_conn_del(c); + hci_conn_unlink(conn); + hci_conn_del(conn); } } -- GitLab From a2904d2825536aa896a149a9174d11b0958e7095 Mon Sep 17 00:00:00 2001 From: Ruihan Li Date: Wed, 3 May 2023 21:39:37 +0800 Subject: [PATCH 5214/5631] Bluetooth: Unlink CISes when LE disconnects in hci_conn_del Currently, hci_conn_del calls hci_conn_unlink for BR/EDR, (e)SCO, and CIS connections, i.e., everything except LE connections. However, if (e)SCO connections are unlinked when BR/EDR disconnects, CIS connections should also be unlinked when LE disconnects. In terms of disconnection behavior, CIS and (e)SCO connections are not too different. One peculiarity of CIS is that when CIS connections are disconnected, the CIS handle isn't deleted, as per [BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E] 7.1.6 Disconnect command: All SCO, eSCO, and CIS connections on a physical link should be disconnected before the ACL connection on the same physical connection is disconnected. If it does not, they will be implicitly disconnected as part of the ACL disconnection. ... Note: As specified in Section 7.7.5, on the Central, the handle for a CIS remains valid even after disconnection and, therefore, the Host can recreate a disconnected CIS at a later point in time using the same connection handle. Since hci_conn_link invokes both hci_conn_get and hci_conn_hold, hci_conn_unlink should perform both hci_conn_put and hci_conn_drop as well. However, currently it performs only hci_conn_put. This patch makes hci_conn_unlink call hci_conn_drop as well, which simplifies the logic in hci_conn_del a bit and may benefit future users of hci_conn_unlink. But it is noted that this change additionally implies that hci_conn_unlink can queue disc_work on conn itself, with the following call stack: hci_conn_unlink(conn) [conn->parent == NULL] -> hci_conn_unlink(child) [child->parent == conn] -> hci_conn_drop(child->parent) -> queue_delayed_work(&conn->disc_work) Queued disc_work after hci_conn_del can be spurious, so during the process of hci_conn_del, it is necessary to make the call to cancel_delayed_work(&conn->disc_work) after invoking hci_conn_unlink. Signed-off-by: Ruihan Li Co-developed-by: Luiz Augusto von Dentz Signed-off-by: Luiz Augusto von Dentz --- net/bluetooth/hci_conn.c | 21 ++++++--------------- 1 file changed, 6 insertions(+), 15 deletions(-) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index ce588359b290..f75ef12f18f7 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1100,7 +1100,9 @@ static void hci_conn_unlink(struct hci_conn *conn) * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (child->handle == HCI_CONN_HANDLE_UNSET) + if ((child->type == SCO_LINK || + child->type == ESCO_LINK) && + child->handle == HCI_CONN_HANDLE_UNSET) hci_conn_del(child); } @@ -1113,6 +1115,7 @@ static void hci_conn_unlink(struct hci_conn *conn) list_del_rcu(&conn->link->list); synchronize_rcu(); + hci_conn_drop(conn->parent); hci_conn_put(conn->parent); conn->parent = NULL; @@ -1126,12 +1129,13 @@ void hci_conn_del(struct hci_conn *conn) BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); + hci_conn_unlink(conn); + cancel_delayed_work_sync(&conn->disc_work); cancel_delayed_work_sync(&conn->auto_accept_work); cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - hci_conn_unlink(conn); /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { @@ -1142,13 +1146,6 @@ void hci_conn_del(struct hci_conn *conn) else hdev->acl_cnt += conn->sent; } else { - struct hci_conn *acl = conn->parent; - - if (acl) { - hci_conn_unlink(conn); - hci_conn_drop(acl); - } - /* Unacked ISO frames */ if (conn->type == ISO_LINK) { if (hdev->iso_pkts) @@ -2485,12 +2482,6 @@ void hci_conn_hash_flush(struct hci_dev *hdev) list)) != NULL) { conn->state = BT_CLOSED; hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); - - /* Unlink before deleting otherwise it is possible that - * hci_conn_del removes the link which may cause the list to - * contain items already freed. - */ - hci_conn_unlink(conn); hci_conn_del(conn); } } -- GitLab From 6ce5169e05aa5360a49a574cc1490ceea6b651a6 Mon Sep 17 00:00:00 2001 From: Neeraj Sanjay Kale Date: Thu, 18 May 2023 22:13:47 +0530 Subject: [PATCH 5215/5631] Bluetooth: btnxpuart: Fix compiler warnings This fixes the follwing compiler warning reported by kernel test robot: drivers/bluetooth/btnxpuart.c:1332:34: warning: unused variable 'nxpuart_of_match_table' [-Wunused-const-variable] Signed-off-by: Neeraj Sanjay Kale Reported-by: kernel test robot Link: https://lore.kernel.org/oe-kbuild-all/202305161345.eClvTYQ9-lkp@intel.com/ Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btnxpuart.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 3a34d7c1475b..52ef44688d38 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1319,17 +1319,17 @@ static void nxp_serdev_remove(struct serdev_device *serdev) hci_free_dev(hdev); } -static struct btnxpuart_data w8987_data = { +static struct btnxpuart_data w8987_data __maybe_unused = { .helper_fw_name = NULL, .fw_name = FIRMWARE_W8987, }; -static struct btnxpuart_data w8997_data = { +static struct btnxpuart_data w8997_data __maybe_unused = { .helper_fw_name = FIRMWARE_HELPER, .fw_name = FIRMWARE_W8997, }; -static const struct of_device_id nxpuart_of_match_table[] = { +static const struct of_device_id nxpuart_of_match_table[] __maybe_unused = { { .compatible = "nxp,88w8987-bt", .data = &w8987_data }, { .compatible = "nxp,88w8997-bt", .data = &w8997_data }, { } -- GitLab From a70fc4ed20a6118837b0aecbbf789074935f473b Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Fri, 19 May 2023 23:54:35 +0200 Subject: [PATCH 5216/5631] cxl/port: Fix NULL pointer access in devm_cxl_add_port() In devm_cxl_add_port() the port creation may fail and its associated pointer does not contain a valid address. During error message generation this invalid port address is used. Fix that wrong address access. Fixes: f3cd264c4ec1 ("cxl: Unify debug messages when calling devm_cxl_add_port()") Signed-off-by: Robert Richter Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20230519215436.3394532-1-rrichter@amd.com Signed-off-by: Dan Williams --- drivers/cxl/core/port.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index da2068475fa2..e7c284c890bc 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -750,11 +750,10 @@ struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport, parent_port = parent_dport ? parent_dport->port : NULL; if (IS_ERR(port)) { - dev_dbg(uport, "Failed to add %s%s%s%s: %ld\n", - dev_name(&port->dev), - parent_port ? " to " : "", + dev_dbg(uport, "Failed to add%s%s%s: %ld\n", + parent_port ? " port to " : "", parent_port ? dev_name(&parent_port->dev) : "", - parent_port ? "" : " (root port)", + parent_port ? "" : " root port", PTR_ERR(port)); } else { dev_dbg(uport, "%s added%s%s%s\n", -- GitLab From c99bff34290f1b994073557b754aff86e4c7b22e Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 19 May 2023 12:23:40 +0200 Subject: [PATCH 5217/5631] s390/dasd: fix command reject error on ESE devices Formatting a thin-provisioned (ESE) device that is part of a PPRC copy relation might fail with the following error: dasd-eckd 0.0.f500: An error occurred in the DASD device driver, reason=09 [...] 24 Byte: 0 MSG 4, no MSGb to SYSOP During format of an ESE disk the Release Allocated Space command is used. A bit in the payload of the command is set that is not allowed to be set for devices in a copy relation. This bit is set to allow the partial release of an extent. Check for the existence of a copy relation before setting the respective bit. Fixes: 91dc4a197569 ("s390/dasd: Add new ioctl to release space") Cc: stable@kernel.org # 5.3+ Signed-off-by: Stefan Haberland Reviewed-by: Jan Hoeppner Link: https://lore.kernel.org/r/20230519102340.3854819-2-sth@linux.ibm.com Signed-off-by: Jens Axboe --- drivers/s390/block/dasd_eckd.c | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index ade1369fe5ed..113c509bf6d0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -127,6 +127,8 @@ static int prepare_itcw(struct itcw *, unsigned int, unsigned int, int, struct dasd_device *, struct dasd_device *, unsigned int, int, unsigned int, unsigned int, unsigned int, unsigned int); +static int dasd_eckd_query_pprc_status(struct dasd_device *, + struct dasd_pprc_data_sc4 *); /* initial attempt at a probe function. this can be simplified once * the other detection code is gone */ @@ -3733,6 +3735,26 @@ static int count_exts(unsigned int from, unsigned int to, int trks_per_ext) return count; } +static int dasd_in_copy_relation(struct dasd_device *device) +{ + struct dasd_pprc_data_sc4 *temp; + int rc; + + if (!dasd_eckd_pprc_enabled(device)) + return 0; + + temp = kzalloc(sizeof(*temp), GFP_KERNEL); + if (!temp) + return -ENOMEM; + + rc = dasd_eckd_query_pprc_status(device, temp); + if (!rc) + rc = temp->dev_info[0].state; + + kfree(temp); + return rc; +} + /* * Release allocated space for a given range or an entire volume. */ @@ -3749,6 +3771,7 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, int cur_to_trk, cur_from_trk; struct dasd_ccw_req *cqr; u32 beg_cyl, end_cyl; + int copy_relation; struct ccw1 *ccw; int trks_per_ext; size_t ras_size; @@ -3760,6 +3783,10 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, if (dasd_eckd_ras_sanity_checks(device, first_trk, last_trk)) return ERR_PTR(-EINVAL); + copy_relation = dasd_in_copy_relation(device); + if (copy_relation < 0) + return ERR_PTR(copy_relation); + rq = req ? blk_mq_rq_to_pdu(req) : NULL; features = &private->features; @@ -3788,9 +3815,11 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, /* * This bit guarantees initialisation of tracks within an extent that is * not fully specified, but is only supported with a certain feature - * subset. + * subset and for devices not in a copy relation. */ - ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); + if (features->feature[56] & 0x01 && !copy_relation) + ras_data->op_flags.guarantee_init = 1; + ras_data->lss = private->conf.ned->ID; ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; -- GitLab From 69baa3a623fd2e58624f24f2f23d46f87b817c93 Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Wed, 10 May 2023 09:42:23 +0200 Subject: [PATCH 5218/5631] block: Deny writable memory mapping if block is read-only User should not be able to write block device if it is read-only at block level (e.g force_ro attribute). This is ensured in the regular fops write operation (blkdev_write_iter) but not when writing via user mapping (mmap), allowing user to actually write a read-only block device via a PROT_WRITE mapping. Example: This can lead to integrity issue of eMMC boot partition (e.g mmcblk0boot0) which is read-only by default. To fix this issue, simply deny shared writable mapping if the block is readonly. Note: Block remains writable if switch to read-only is performed after the initial mapping, but this is expected behavior according to commit a32e236eb93e ("Partially revert "block: fail op_is_write() requests to read-only partitions"")'. Signed-off-by: Loic Poulain Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230510074223.991297-1-loic.poulain@linaro.org Signed-off-by: Jens Axboe --- block/fops.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/block/fops.c b/block/fops.c index d2e6be4e3d1c..58d0aebc7313 100644 --- a/block/fops.c +++ b/block/fops.c @@ -678,6 +678,16 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return error; } +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + + if (bdev_read_only(I_BDEV(bd_inode))) + return generic_file_readonly_mmap(file, vma); + + return generic_file_mmap(file, vma); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -685,7 +695,7 @@ const struct file_operations def_blk_fops = { .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, .iopoll = iocb_bio_iopoll, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, #ifdef CONFIG_COMPAT -- GitLab From 19abb4583d5eba06459930932e72c862a83cd9c2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:22:48 +0200 Subject: [PATCH 5219/5631] fbdev: fbmem: mark get_fb_unmapped_area() static There is a global function with this name on sparc, but no global declaration: drivers/video/fbdev/core/fbmem.c:1469:15: error: no previous prototype for 'get_fb_unmapped_area' Make the generic definition static to avoid this warning. On sparc, this is never seen. Edit by Helge: Update Kconfig text as suggested by Geert Uytterhoeven. Signed-off-by: Arnd Bergmann Signed-off-by: Helge Deller --- drivers/video/fbdev/Kconfig | 2 +- drivers/video/fbdev/core/fbmem.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 96e91570cdd3..0fdf5f46802c 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -124,7 +124,7 @@ config FB_PROVIDE_GET_FB_UNMAPPED_AREA depends on FB help Allow generic frame-buffer to provide get_fb_unmapped_area - function. + function to provide shareable character device support on nommu. menuconfig FB_FOREIGN_ENDIAN bool "Framebuffer foreign endianness support" diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e808dc86001c..28739f1cb5e7 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1468,7 +1468,7 @@ __releases(&info->lock) } #if defined(CONFIG_FB_PROVIDE_GET_FB_UNMAPPED_AREA) && !defined(CONFIG_MMU) -unsigned long get_fb_unmapped_area(struct file *filp, +static unsigned long get_fb_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { -- GitLab From f6cd4c96b2c201be1ca3c17daeec52bf20880d69 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 May 2023 22:28:09 +0200 Subject: [PATCH 5220/5631] fbdev: i810: include i810_main.h in i810_dvt.c Building with W=1 shows that a header needs to be included to make the prototypes visible: drivers/video/fbdev/i810/i810_dvt.c:194:6: error: no previous prototype for 'round_off_xres' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:233:6: error: no previous prototype for 'i810fb_encode_registers' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:245:6: error: no previous prototype for 'i810fb_fill_var_timings' [-Werror=missing-prototypes] drivers/video/fbdev/i810/i810_dvt.c:279:5: error: no previous prototype for 'i810_get_watermark' [-Werror=missing-prototypes] Adding the header leads to another warning from a mismatched prototype, so fix this as well: drivers/video/fbdev/i810/i810_dvt.c:280:5: error: conflicting types for 'i810_get_watermark'; have 'u32(struct fb_var_screeninfo *, Signed-off-by: Arnd Bergmann Reviewed-by: Jani Nikula Signed-off-by: Helge Deller --- drivers/video/fbdev/i810/i810_dvt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/i810/i810_dvt.c b/drivers/video/fbdev/i810/i810_dvt.c index b4b3670667ab..2082b5c92e8f 100644 --- a/drivers/video/fbdev/i810/i810_dvt.c +++ b/drivers/video/fbdev/i810/i810_dvt.c @@ -14,6 +14,7 @@ #include "i810_regs.h" #include "i810.h" +#include "i810_main.h" struct mode_registers std_modes[] = { /* 640x480 @ 60Hz */ @@ -276,7 +277,7 @@ void i810fb_fill_var_timings(struct fb_var_screeninfo *var) var->upper_margin = total - (yres + var->lower_margin + var->vsync_len); } -u32 i810_get_watermark(struct fb_var_screeninfo *var, +u32 i810_get_watermark(const struct fb_var_screeninfo *var, struct i810fb_par *par) { struct mode_registers *params = &par->regs; -- GitLab From 93f57c7a10890645d1d3b88eea1692b285bf3f38 Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Tue, 16 May 2023 13:00:33 +0200 Subject: [PATCH 5221/5631] fbdev: atyfb: Remove unused clock determination MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just below the removed lines par->clk_wr_offset is hard coded to 3 so there is no use in determining a different clock just to then ignore it anyway. This also removes the only I/O port use remaining in the driver allowing it to be built without CONFIG_HAS_IOPORT. Link: https://lore.kernel.org/all/ZBx5aLo5h546BzBt@intel.com/ Suggested-by: Ville Syrjälä Signed-off-by: Niklas Schnelle Reviewed-by: Ville Syrjälä Signed-off-by: Helge Deller --- drivers/video/fbdev/aty/atyfb_base.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index b02e4e645035..cba2b113b28b 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3498,11 +3498,6 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, if (ret) goto atyfb_setup_generic_fail; #endif - if (!(aty_ld_le32(CRTC_GEN_CNTL, par) & CRTC_EXT_DISP_EN)) - par->clk_wr_offset = (inb(R_GENMO) & 0x0CU) >> 2; - else - par->clk_wr_offset = aty_ld_8(CLOCK_CNTL, par) & 0x03U; - /* according to ATI, we should use clock 3 for acelerated mode */ par->clk_wr_offset = 3; -- GitLab From ed9de4ed39875706607fb08118a58344ae6c5f42 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 19 May 2023 15:32:30 -0400 Subject: [PATCH 5222/5631] fbdev: udlfb: Fix endpoint check The syzbot fuzzer detected a problem in the udlfb driver, caused by an endpoint not having the expected type: usb 1-1: Read EDID byte 0 failed: -71 usb 1-1: Unable to get valid EDID from device/display ------------[ cut here ]------------ usb 1-1: BOGUS urb xfer, pipe 3 != type 1 WARNING: CPU: 0 PID: 9 at drivers/usb/core/urb.c:504 usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 Modules linked in: CPU: 0 PID: 9 Comm: kworker/0:1 Not tainted 6.4.0-rc1-syzkaller-00016-ga4422ff22142 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/28/2023 Workqueue: usb_hub_wq hub_event RIP: 0010:usb_submit_urb+0xed6/0x1880 drivers/usb/core/urb.c:504 ... Call Trace: dlfb_submit_urb+0x92/0x180 drivers/video/fbdev/udlfb.c:1980 dlfb_set_video_mode+0x21f0/0x2950 drivers/video/fbdev/udlfb.c:315 dlfb_ops_set_par+0x2a7/0x8d0 drivers/video/fbdev/udlfb.c:1111 dlfb_usb_probe+0x149a/0x2710 drivers/video/fbdev/udlfb.c:1743 The current approach for this issue failed to catch the problem because it only checks for the existence of a bulk-OUT endpoint; it doesn't check whether this endpoint is the one that the driver will actually use. We can fix the problem by instead checking that the endpoint used by the driver does exist and is bulk-OUT. Reported-and-tested-by: syzbot+0e22d63dcebb802b9bc8@syzkaller.appspotmail.com Signed-off-by: Alan Stern CC: Pavel Skripkin Fixes: aaf7dbe07385 ("video: fbdev: udlfb: properly check endpoint type") Signed-off-by: Helge Deller --- drivers/video/fbdev/udlfb.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c index 216d49c9d47e..256d9b61f4ea 100644 --- a/drivers/video/fbdev/udlfb.c +++ b/drivers/video/fbdev/udlfb.c @@ -27,6 +27,8 @@ #include